Re: [PATCHES] Networking

Re: [PATCHES] Networking

[Jiri Slaby]

On 04/21/2015, 08:30 PM, David Miller wrote:
> 
> Please queue up the following networking bug fixes for 3.12, 3.14, 3.18,
> 3.19, and 4.0 -stable, respectively.

FWIW if anyone else wants to put there the missing "commit upstream"
tags for some patches too, I dug them out:
    gianfar: Carefully free skbs in functions called by netpoll.
    commit c9974ad4aeb36003860100221a594f3c0ccc3f78 upstream.

    benet: Call dev_kfree_skby_any instead of kfree_skb.
    commit d8ec2c02caa3515f35d6c33eedf529394c419298 upstream.

    ixgb: Call dev_kfree_skby_any instead of dev_kfree_skb.
    commit f7e79913a1d6a6139211ead3b03579b317d25a1f upstream.

    tg3: Call dev_kfree_skby_any instead of dev_kfree_skb.
    commit 497a27b9e1bcf6dbaea7a466cfcd866927e1b431 upstream.

    bnx2: Call dev_kfree_skby_any instead of dev_kfree_skb.
    commit f458b2ee93ee3606c83f76213fbe49e026bac754 upstream.

    bonding: Call dev_kfree_skby_any instead of kfree_skb.
    commit 2bb77ab42a6a40162a367b80394b96bb756ad5f1 upstream.

    r8169: Call dev_kfree_skby_any instead of dev_kfree_skb.
    commit 989c9ba104d9ce53c1ca918262f3fdfb33aca12a upstream.

    8139too: Call dev_kfree_skby_any instead of dev_kfree_skb.
    commit a2ccd2e4bd70122523a7bf21cec4dd6e34427089 upstream.

    8139cp: Call dev_kfree_skby_any instead of kfree_skb.
    commit 508f81d517ed1f3f0197df63ea7ab5cd91b6f3b3 upstream.


thanks,
-- 
js
suse labs

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 126 bytes --]


Please queue up the following networking bug fixes for
3.12, 3.14, 3.18, 3.19, and 4.0 -stable, respectively.

Thanks a lot!

[-- Attachment #2: net_312.mbox --]
[-- Type: Application/Octet-Stream, Size: 16831 bytes --]

From bdcb6cd66c3adbd2518dc1c1c3341cd0762133b6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Sebastian=20P=C3=B6hn?= <sebastian.poehn@gmail.com>
Date: Mon, 20 Apr 2015 09:19:20 +0200
Subject: [PATCH 1/5] ip_forward: Drop frames with attached skb->sk

[ Upstream commit 2ab957492d13bb819400ac29ae55911d50a82a13 ]

Initial discussion was:
[FYI] xfrm: Don't lookup sk_policy for timewait sockets

Forwarded frames should not have a socket attached. Especially
tw sockets will lead to panics later-on in the stack.

This was observed with TPROXY assigning a tw socket and broken
policy routing (misconfigured). As a result frame enters
forwarding path instead of input. We cannot solve this in
TPROXY as it cannot know that policy routing is broken.

v2:
Remove useless comment

Signed-off-by: Sebastian Poehn <sebastian.poehn@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_forward.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 31ee5c6..479e8a6 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -126,6 +126,9 @@ int ip_forward(struct sk_buff *skb)
 	struct rtable *rt;	/* Route we use */
 	struct ip_options *opt	= &(IPCB(skb)->opt);
 
+	if (unlikely(skb->sk))
+		goto drop;
+
 	if (skb_warn_if_lro(skb))
 		goto drop;
 
-- 
2.3.6


From 9772a9cb09a564d45972b2b875080d5e96dcb88a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 21 Apr 2015 18:32:24 -0700
Subject: [PATCH 2/5] tcp: fix possible deadlock in tcp_send_fin()

[ Upstream commit d83769a580f1132ac26439f50068a29b02be535e ]

Using sk_stream_alloc_skb() in tcp_send_fin() is dangerous in
case a huge process is killed by OOM, and tcp_mem[2] is hit.

To be able to free memory we need to make progress, so this
patch allows FIN packets to not care about tcp_mem[2], if
skb allocation succeeded.

In a follow-up patch, we might abort tcp_send_fin() infinite loop
in case TIF_MEMDIE is set on this thread, as memory allocator
did its best getting extra memory already.

This patch reverts d22e15371811 ("tcp: fix tcp fin memory accounting")

Fixes: d22e15371811 ("tcp: fix tcp fin memory accounting")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index e07ccba..5719f7e 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2581,6 +2581,21 @@ begin_fwd:
 	}
 }
 
+/* We allow to exceed memory limits for FIN packets to expedite
+ * connection tear down and (memory) recovery.
+ * Otherwise tcp_send_fin() could loop forever.
+ */
+static void sk_forced_wmem_schedule(struct sock *sk, int size)
+{
+	int amt, status;
+
+	if (size <= sk->sk_forward_alloc)
+		return;
+	amt = sk_mem_pages(size);
+	sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
+	sk_memory_allocated_add(sk, amt, &status);
+}
+
 /* Send a fin.  The caller locks the socket for us.  This cannot be
  * allowed to fail queueing a FIN frame under any circumstances.
  */
@@ -2603,11 +2618,14 @@ void tcp_send_fin(struct sock *sk)
 	} else {
 		/* Socket is locked, keep trying until memory is available. */
 		for (;;) {
-			skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation);
+			skb = alloc_skb_fclone(MAX_TCP_HEADER,
+					       sk->sk_allocation);
 			if (skb)
 				break;
 			yield();
 		}
+		skb_reserve(skb, MAX_TCP_HEADER);
+		sk_forced_wmem_schedule(sk, skb->truesize);
 		/* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */
 		tcp_init_nondata_skb(skb, tp->write_seq,
 				     TCPHDR_ACK | TCPHDR_FIN);
-- 
2.3.6


From 02439e9ceb92fe05b1548cfb04a3814779576b0a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 23 Apr 2015 10:42:39 -0700
Subject: [PATCH 3/5] tcp: avoid looping in tcp_send_fin()

[ Upstream commit 845704a535e9b3c76448f52af1b70e4422ea03fd ]

Presence of an unbound loop in tcp_send_fin() had always been hard
to explain when analyzing crash dumps involving gigantic dying processes
with millions of sockets.

Lets try a different strategy :

In case of memory pressure, try to add the FIN flag to last packet
in write queue, even if packet was already sent. TCP stack will
be able to deliver this FIN after a timeout event. Note that this
FIN being delivered by a retransmit, it also carries a Push flag
given our current implementation.

By checking sk_under_memory_pressure(), we anticipate that cooking
many FIN packets might deplete tcp memory.

In the case we could not allocate a packet, even with __GFP_WAIT
allocation, then not sending a FIN seems quite reasonable if it allows
to get rid of this socket, free memory, and not block the process from
eventually doing other useful work.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 50 +++++++++++++++++++++++++++++---------------------
 1 file changed, 29 insertions(+), 21 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 5719f7e..e164848 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2583,7 +2583,8 @@ begin_fwd:
 
 /* We allow to exceed memory limits for FIN packets to expedite
  * connection tear down and (memory) recovery.
- * Otherwise tcp_send_fin() could loop forever.
+ * Otherwise tcp_send_fin() could be tempted to either delay FIN
+ * or even be forced to close flow without any FIN.
  */
 static void sk_forced_wmem_schedule(struct sock *sk, int size)
 {
@@ -2596,33 +2597,40 @@ static void sk_forced_wmem_schedule(struct sock *sk, int size)
 	sk_memory_allocated_add(sk, amt, &status);
 }
 
-/* Send a fin.  The caller locks the socket for us.  This cannot be
- * allowed to fail queueing a FIN frame under any circumstances.
+/* Send a FIN. The caller locks the socket for us.
+ * We should try to send a FIN packet really hard, but eventually give up.
  */
 void tcp_send_fin(struct sock *sk)
 {
+	struct sk_buff *skb, *tskb = tcp_write_queue_tail(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct sk_buff *skb = tcp_write_queue_tail(sk);
-	int mss_now;
 
-	/* Optimization, tack on the FIN if we have a queue of
-	 * unsent frames.  But be careful about outgoing SACKS
-	 * and IP options.
+	/* Optimization, tack on the FIN if we have one skb in write queue and
+	 * this skb was not yet sent, or we are under memory pressure.
+	 * Note: in the latter case, FIN packet will be sent after a timeout,
+	 * as TCP stack thinks it has already been transmitted.
 	 */
-	mss_now = tcp_current_mss(sk);
-
-	if (tcp_send_head(sk) != NULL) {
-		TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_FIN;
-		TCP_SKB_CB(skb)->end_seq++;
+	if (tskb && (tcp_send_head(sk) || sk_under_memory_pressure(sk))) {
+coalesce:
+		TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN;
+		TCP_SKB_CB(tskb)->end_seq++;
 		tp->write_seq++;
+		if (!tcp_send_head(sk)) {
+			/* This means tskb was already sent.
+			 * Pretend we included the FIN on previous transmit.
+			 * We need to set tp->snd_nxt to the value it would have
+			 * if FIN had been sent. This is because retransmit path
+			 * does not change tp->snd_nxt.
+			 */
+			tp->snd_nxt++;
+			return;
+		}
 	} else {
-		/* Socket is locked, keep trying until memory is available. */
-		for (;;) {
-			skb = alloc_skb_fclone(MAX_TCP_HEADER,
-					       sk->sk_allocation);
-			if (skb)
-				break;
-			yield();
+		skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation);
+		if (unlikely(!skb)) {
+			if (tskb)
+				goto coalesce;
+			return;
 		}
 		skb_reserve(skb, MAX_TCP_HEADER);
 		sk_forced_wmem_schedule(sk, skb->truesize);
@@ -2631,7 +2639,7 @@ void tcp_send_fin(struct sock *sk)
 				     TCPHDR_ACK | TCPHDR_FIN);
 		tcp_queue_skb(sk, skb);
 	}
-	__tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_OFF);
+	__tcp_push_pending_frames(sk, tcp_current_mss(sk), TCP_NAGLE_OFF);
 }
 
 /* We get here when a process closes a file descriptor (either due to
-- 
2.3.6


From 32051b050b548bdf743ca4648a36175995fbb413 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 22 Apr 2015 07:33:36 -0700
Subject: [PATCH 4/5] net: do not deplete pfmemalloc reserve

[ Upstream commit 79930f5892e134c6da1254389577fffb8bd72c66 ]

build_skb() should look at the page pfmemalloc status.
If set, this means page allocator allocated this page in the
expectation it would help to free other pages. Networking
stack can do that only if skb->pfmemalloc is also set.

Also, we must refrain using high order pages from the pfmemalloc
reserve, so __page_frag_refill() must also use __GFP_NOMEMALLOC for
them. Under memory pressure, using order-0 pages is probably the best
strategy.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 17313d1..d354bb2 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -308,7 +308,11 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
 
 	memset(skb, 0, offsetof(struct sk_buff, tail));
 	skb->truesize = SKB_TRUESIZE(size);
-	skb->head_frag = frag_size != 0;
+	if (frag_size) {
+		skb->head_frag = 1;
+		if (virt_to_head_page(data)->pfmemalloc)
+			skb->pfmemalloc = 1;
+	}
 	atomic_set(&skb->users, 1);
 	skb->head = data;
 	skb->data = data;
@@ -351,7 +355,8 @@ refill:
 			gfp_t gfp = gfp_mask;
 
 			if (order)
-				gfp |= __GFP_COMP | __GFP_NOWARN;
+				gfp |= __GFP_COMP | __GFP_NOWARN |
+				       __GFP_NOMEMALLOC;
 			nc->frag.page = alloc_pages(gfp, order);
 			if (likely(nc->frag.page))
 				break;
-- 
2.3.6


From 049a34206f41a81216bd74a442a005ae26766961 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 24 Apr 2015 16:05:01 -0700
Subject: [PATCH 5/5] net: fix crash in build_skb()

[ Upstream commit 2ea2f62c8bda242433809c7f4e9eae1c52c40bbe ]

When I added pfmemalloc support in build_skb(), I forgot netlink
was using build_skb() with a vmalloc() area.

In this patch I introduce __build_skb() for netlink use,
and build_skb() is a wrapper handling both skb->head_frag and
skb->pfmemalloc

This means netlink no longer has to hack skb->head_frag

[ 1567.700067] kernel BUG at arch/x86/mm/physaddr.c:26!
[ 1567.700067] invalid opcode: 0000 [#1] PREEMPT SMP KASAN
[ 1567.700067] Dumping ftrace buffer:
[ 1567.700067]    (ftrace buffer empty)
[ 1567.700067] Modules linked in:
[ 1567.700067] CPU: 9 PID: 16186 Comm: trinity-c182 Not tainted 4.0.0-next-20150424-sasha-00037-g4796e21 #2167
[ 1567.700067] task: ffff880127efb000 ti: ffff880246770000 task.ti: ffff880246770000
[ 1567.700067] RIP: __phys_addr (arch/x86/mm/physaddr.c:26 (discriminator 3))
[ 1567.700067] RSP: 0018:ffff8802467779d8  EFLAGS: 00010202
[ 1567.700067] RAX: 000041000ed8e000 RBX: ffffc9008ed8e000 RCX: 000000000000002c
[ 1567.700067] RDX: 0000000000000004 RSI: 0000000000000000 RDI: ffffffffb3fd6049
[ 1567.700067] RBP: ffff8802467779f8 R08: 0000000000000019 R09: ffff8801d0168000
[ 1567.700067] R10: ffff8801d01680c7 R11: ffffed003a02d019 R12: ffffc9000ed8e000
[ 1567.700067] R13: 0000000000000f40 R14: 0000000000001180 R15: ffffc9000ed8e000
[ 1567.700067] FS:  00007f2a7da3f700(0000) GS:ffff8801d1000000(0000) knlGS:0000000000000000
[ 1567.700067] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 1567.700067] CR2: 0000000000738308 CR3: 000000022e329000 CR4: 00000000000007e0
[ 1567.700067] Stack:
[ 1567.700067]  ffffc9000ed8e000 ffff8801d0168000 ffffc9000ed8e000 ffff8801d0168000
[ 1567.700067]  ffff880246777a28 ffffffffad7c0a21 0000000000001080 ffff880246777c08
[ 1567.700067]  ffff88060d302e68 ffff880246777b58 ffff880246777b88 ffffffffad9a6821
[ 1567.700067] Call Trace:
[ 1567.700067] build_skb (include/linux/mm.h:508 net/core/skbuff.c:316)
[ 1567.700067] netlink_sendmsg (net/netlink/af_netlink.c:1633 net/netlink/af_netlink.c:2329)
[ 1567.774369] ? sched_clock_cpu (kernel/sched/clock.c:311)
[ 1567.774369] ? netlink_unicast (net/netlink/af_netlink.c:2273)
[ 1567.774369] ? netlink_unicast (net/netlink/af_netlink.c:2273)
[ 1567.774369] sock_sendmsg (net/socket.c:614 net/socket.c:623)
[ 1567.774369] sock_write_iter (net/socket.c:823)
[ 1567.774369] ? sock_sendmsg (net/socket.c:806)
[ 1567.774369] __vfs_write (fs/read_write.c:479 fs/read_write.c:491)
[ 1567.774369] ? get_lock_stats (kernel/locking/lockdep.c:249)
[ 1567.774369] ? default_llseek (fs/read_write.c:487)
[ 1567.774369] ? vtime_account_user (kernel/sched/cputime.c:701)
[ 1567.774369] ? rw_verify_area (fs/read_write.c:406 (discriminator 4))
[ 1567.774369] vfs_write (fs/read_write.c:539)
[ 1567.774369] SyS_write (fs/read_write.c:586 fs/read_write.c:577)
[ 1567.774369] ? SyS_read (fs/read_write.c:577)
[ 1567.774369] ? __this_cpu_preempt_check (lib/smp_processor_id.c:63)
[ 1567.774369] ? trace_hardirqs_on_caller (kernel/locking/lockdep.c:2594 kernel/locking/lockdep.c:2636)
[ 1567.774369] ? trace_hardirqs_on_thunk (arch/x86/lib/thunk_64.S:42)
[ 1567.774369] system_call_fastpath (arch/x86/kernel/entry_64.S:261)

Fixes: 79930f5892e ("net: do not deplete pfmemalloc reserve")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h   |  1 +
 net/core/skbuff.c        | 31 ++++++++++++++++++++++---------
 net/netlink/af_netlink.c |  6 ++----
 3 files changed, 25 insertions(+), 13 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 2960dab..79147dc 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -638,6 +638,7 @@ extern bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
 
 extern struct sk_buff *__alloc_skb(unsigned int size,
 				   gfp_t priority, int flags, int node);
+struct sk_buff *__build_skb(void *data, unsigned int frag_size);
 extern struct sk_buff *build_skb(void *data, unsigned int frag_size);
 static inline struct sk_buff *alloc_skb(unsigned int size,
 					gfp_t priority)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index d354bb2..fa8448a 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -277,13 +277,14 @@ nodata:
 EXPORT_SYMBOL(__alloc_skb);
 
 /**
- * build_skb - build a network buffer
+ * __build_skb - build a network buffer
  * @data: data buffer provided by caller
- * @frag_size: size of fragment, or 0 if head was kmalloced
+ * @frag_size: size of data, or 0 if head was kmalloced
  *
  * Allocate a new &sk_buff. Caller provides space holding head and
  * skb_shared_info. @data must have been allocated by kmalloc() only if
- * @frag_size is 0, otherwise data should come from the page allocator.
+ * @frag_size is 0, otherwise data should come from the page allocator
+ *  or vmalloc()
  * The return is the new skb buffer.
  * On a failure the return is %NULL, and @data is not freed.
  * Notes :
@@ -294,7 +295,7 @@ EXPORT_SYMBOL(__alloc_skb);
  *  before giving packet to stack.
  *  RX rings only contains data buffers, not full skbs.
  */
-struct sk_buff *build_skb(void *data, unsigned int frag_size)
+struct sk_buff *__build_skb(void *data, unsigned int frag_size)
 {
 	struct skb_shared_info *shinfo;
 	struct sk_buff *skb;
@@ -308,11 +309,6 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
 
 	memset(skb, 0, offsetof(struct sk_buff, tail));
 	skb->truesize = SKB_TRUESIZE(size);
-	if (frag_size) {
-		skb->head_frag = 1;
-		if (virt_to_head_page(data)->pfmemalloc)
-			skb->pfmemalloc = 1;
-	}
 	atomic_set(&skb->users, 1);
 	skb->head = data;
 	skb->data = data;
@@ -329,6 +325,23 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
 
 	return skb;
 }
+
+/* build_skb() is wrapper over __build_skb(), that specifically
+ * takes care of skb->head and skb->pfmemalloc
+ * This means that if @frag_size is not zero, then @data must be backed
+ * by a page fragment, not kmalloc() or vmalloc()
+ */
+struct sk_buff *build_skb(void *data, unsigned int frag_size)
+{
+	struct sk_buff *skb = __build_skb(data, frag_size);
+
+	if (skb && frag_size) {
+		skb->head_frag = 1;
+		if (virt_to_head_page(data)->pfmemalloc)
+			skb->pfmemalloc = 1;
+	}
+	return skb;
+}
 EXPORT_SYMBOL(build_skb);
 
 struct netdev_alloc_cache {
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 0059013..5a75a1e 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1616,13 +1616,11 @@ static struct sk_buff *netlink_alloc_large_skb(unsigned int size,
 	if (data == NULL)
 		return NULL;
 
-	skb = build_skb(data, size);
+	skb = __build_skb(data, size);
 	if (skb == NULL)
 		vfree(data);
-	else {
-		skb->head_frag = 0;
+	else
 		skb->destructor = netlink_skb_destructor;
-	}
 
 	return skb;
 }
-- 
2.3.6


[-- Attachment #3: net_314.mbox --]
[-- Type: Application/Octet-Stream, Size: 16810 bytes --]

From ec2d4b839fdd51fd45eeb053a7ec998209771e5e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Sebastian=20P=C3=B6hn?= <sebastian.poehn@gmail.com>
Date: Mon, 20 Apr 2015 09:19:20 +0200
Subject: [PATCH 1/5] ip_forward: Drop frames with attached skb->sk

[ Upstream commit 2ab957492d13bb819400ac29ae55911d50a82a13 ]

Initial discussion was:
[FYI] xfrm: Don't lookup sk_policy for timewait sockets

Forwarded frames should not have a socket attached. Especially
tw sockets will lead to panics later-on in the stack.

This was observed with TPROXY assigning a tw socket and broken
policy routing (misconfigured). As a result frame enters
forwarding path instead of input. We cannot solve this in
TPROXY as it cannot know that policy routing is broken.

v2:
Remove useless comment

Signed-off-by: Sebastian Poehn <sebastian.poehn@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_forward.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index ecb34b5..57075c4 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -127,6 +127,9 @@ int ip_forward(struct sk_buff *skb)
 	struct rtable *rt;	/* Route we use */
 	struct ip_options *opt	= &(IPCB(skb)->opt);
 
+	if (unlikely(skb->sk))
+		goto drop;
+
 	if (skb_warn_if_lro(skb))
 		goto drop;
 
-- 
2.3.6


From 615c559226122548bd7c96c9f2616af68ec359a4 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 21 Apr 2015 18:32:24 -0700
Subject: [PATCH 2/5] tcp: fix possible deadlock in tcp_send_fin()

[ Upstream commit d83769a580f1132ac26439f50068a29b02be535e ]

Using sk_stream_alloc_skb() in tcp_send_fin() is dangerous in
case a huge process is killed by OOM, and tcp_mem[2] is hit.

To be able to free memory we need to make progress, so this
patch allows FIN packets to not care about tcp_mem[2], if
skb allocation succeeded.

In a follow-up patch, we might abort tcp_send_fin() infinite loop
in case TIF_MEMDIE is set on this thread, as memory allocator
did its best getting extra memory already.

This patch reverts d22e15371811 ("tcp: fix tcp fin memory accounting")

Fixes: d22e15371811 ("tcp: fix tcp fin memory accounting")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 96f64e5..54b3250 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2595,6 +2595,21 @@ begin_fwd:
 	}
 }
 
+/* We allow to exceed memory limits for FIN packets to expedite
+ * connection tear down and (memory) recovery.
+ * Otherwise tcp_send_fin() could loop forever.
+ */
+static void sk_forced_wmem_schedule(struct sock *sk, int size)
+{
+	int amt, status;
+
+	if (size <= sk->sk_forward_alloc)
+		return;
+	amt = sk_mem_pages(size);
+	sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
+	sk_memory_allocated_add(sk, amt, &status);
+}
+
 /* Send a fin.  The caller locks the socket for us.  This cannot be
  * allowed to fail queueing a FIN frame under any circumstances.
  */
@@ -2617,11 +2632,14 @@ void tcp_send_fin(struct sock *sk)
 	} else {
 		/* Socket is locked, keep trying until memory is available. */
 		for (;;) {
-			skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation);
+			skb = alloc_skb_fclone(MAX_TCP_HEADER,
+					       sk->sk_allocation);
 			if (skb)
 				break;
 			yield();
 		}
+		skb_reserve(skb, MAX_TCP_HEADER);
+		sk_forced_wmem_schedule(sk, skb->truesize);
 		/* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */
 		tcp_init_nondata_skb(skb, tp->write_seq,
 				     TCPHDR_ACK | TCPHDR_FIN);
-- 
2.3.6


From 2ff5bc8c0c9655f9b8f5fec2834153292e791d39 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 23 Apr 2015 10:42:39 -0700
Subject: [PATCH 3/5] tcp: avoid looping in tcp_send_fin()

[ Upstream commit 845704a535e9b3c76448f52af1b70e4422ea03fd ]

Presence of an unbound loop in tcp_send_fin() had always been hard
to explain when analyzing crash dumps involving gigantic dying processes
with millions of sockets.

Lets try a different strategy :

In case of memory pressure, try to add the FIN flag to last packet
in write queue, even if packet was already sent. TCP stack will
be able to deliver this FIN after a timeout event. Note that this
FIN being delivered by a retransmit, it also carries a Push flag
given our current implementation.

By checking sk_under_memory_pressure(), we anticipate that cooking
many FIN packets might deplete tcp memory.

In the case we could not allocate a packet, even with __GFP_WAIT
allocation, then not sending a FIN seems quite reasonable if it allows
to get rid of this socket, free memory, and not block the process from
eventually doing other useful work.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 50 +++++++++++++++++++++++++++++---------------------
 1 file changed, 29 insertions(+), 21 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 54b3250..99449f8 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2597,7 +2597,8 @@ begin_fwd:
 
 /* We allow to exceed memory limits for FIN packets to expedite
  * connection tear down and (memory) recovery.
- * Otherwise tcp_send_fin() could loop forever.
+ * Otherwise tcp_send_fin() could be tempted to either delay FIN
+ * or even be forced to close flow without any FIN.
  */
 static void sk_forced_wmem_schedule(struct sock *sk, int size)
 {
@@ -2610,33 +2611,40 @@ static void sk_forced_wmem_schedule(struct sock *sk, int size)
 	sk_memory_allocated_add(sk, amt, &status);
 }
 
-/* Send a fin.  The caller locks the socket for us.  This cannot be
- * allowed to fail queueing a FIN frame under any circumstances.
+/* Send a FIN. The caller locks the socket for us.
+ * We should try to send a FIN packet really hard, but eventually give up.
  */
 void tcp_send_fin(struct sock *sk)
 {
+	struct sk_buff *skb, *tskb = tcp_write_queue_tail(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct sk_buff *skb = tcp_write_queue_tail(sk);
-	int mss_now;
 
-	/* Optimization, tack on the FIN if we have a queue of
-	 * unsent frames.  But be careful about outgoing SACKS
-	 * and IP options.
+	/* Optimization, tack on the FIN if we have one skb in write queue and
+	 * this skb was not yet sent, or we are under memory pressure.
+	 * Note: in the latter case, FIN packet will be sent after a timeout,
+	 * as TCP stack thinks it has already been transmitted.
 	 */
-	mss_now = tcp_current_mss(sk);
-
-	if (tcp_send_head(sk) != NULL) {
-		TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_FIN;
-		TCP_SKB_CB(skb)->end_seq++;
+	if (tskb && (tcp_send_head(sk) || sk_under_memory_pressure(sk))) {
+coalesce:
+		TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN;
+		TCP_SKB_CB(tskb)->end_seq++;
 		tp->write_seq++;
+		if (!tcp_send_head(sk)) {
+			/* This means tskb was already sent.
+			 * Pretend we included the FIN on previous transmit.
+			 * We need to set tp->snd_nxt to the value it would have
+			 * if FIN had been sent. This is because retransmit path
+			 * does not change tp->snd_nxt.
+			 */
+			tp->snd_nxt++;
+			return;
+		}
 	} else {
-		/* Socket is locked, keep trying until memory is available. */
-		for (;;) {
-			skb = alloc_skb_fclone(MAX_TCP_HEADER,
-					       sk->sk_allocation);
-			if (skb)
-				break;
-			yield();
+		skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation);
+		if (unlikely(!skb)) {
+			if (tskb)
+				goto coalesce;
+			return;
 		}
 		skb_reserve(skb, MAX_TCP_HEADER);
 		sk_forced_wmem_schedule(sk, skb->truesize);
@@ -2645,7 +2653,7 @@ void tcp_send_fin(struct sock *sk)
 				     TCPHDR_ACK | TCPHDR_FIN);
 		tcp_queue_skb(sk, skb);
 	}
-	__tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_OFF);
+	__tcp_push_pending_frames(sk, tcp_current_mss(sk), TCP_NAGLE_OFF);
 }
 
 /* We get here when a process closes a file descriptor (either due to
-- 
2.3.6


From a2013ed3a02e66e5fb587da52ccf9d716295f51a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 22 Apr 2015 07:33:36 -0700
Subject: [PATCH 4/5] net: do not deplete pfmemalloc reserve

[ Upstream commit 79930f5892e134c6da1254389577fffb8bd72c66 ]

build_skb() should look at the page pfmemalloc status.
If set, this means page allocator allocated this page in the
expectation it would help to free other pages. Networking
stack can do that only if skb->pfmemalloc is also set.

Also, we must refrain using high order pages from the pfmemalloc
reserve, so __page_frag_refill() must also use __GFP_NOMEMALLOC for
them. Under memory pressure, using order-0 pages is probably the best
strategy.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index e2b1bba..8334c70 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -309,7 +309,11 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
 
 	memset(skb, 0, offsetof(struct sk_buff, tail));
 	skb->truesize = SKB_TRUESIZE(size);
-	skb->head_frag = frag_size != 0;
+	if (frag_size) {
+		skb->head_frag = 1;
+		if (virt_to_head_page(data)->pfmemalloc)
+			skb->pfmemalloc = 1;
+	}
 	atomic_set(&skb->users, 1);
 	skb->head = data;
 	skb->data = data;
@@ -352,7 +356,8 @@ refill:
 			gfp_t gfp = gfp_mask;
 
 			if (order)
-				gfp |= __GFP_COMP | __GFP_NOWARN;
+				gfp |= __GFP_COMP | __GFP_NOWARN |
+				       __GFP_NOMEMALLOC;
 			nc->frag.page = alloc_pages(gfp, order);
 			if (likely(nc->frag.page))
 				break;
-- 
2.3.6


From 271f4b70826d976bc7567d8200a60c058e28cbe8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 24 Apr 2015 16:05:01 -0700
Subject: [PATCH 5/5] net: fix crash in build_skb()

[ Upstream commit 2ea2f62c8bda242433809c7f4e9eae1c52c40bbe ]

When I added pfmemalloc support in build_skb(), I forgot netlink
was using build_skb() with a vmalloc() area.

In this patch I introduce __build_skb() for netlink use,
and build_skb() is a wrapper handling both skb->head_frag and
skb->pfmemalloc

This means netlink no longer has to hack skb->head_frag

[ 1567.700067] kernel BUG at arch/x86/mm/physaddr.c:26!
[ 1567.700067] invalid opcode: 0000 [#1] PREEMPT SMP KASAN
[ 1567.700067] Dumping ftrace buffer:
[ 1567.700067]    (ftrace buffer empty)
[ 1567.700067] Modules linked in:
[ 1567.700067] CPU: 9 PID: 16186 Comm: trinity-c182 Not tainted 4.0.0-next-20150424-sasha-00037-g4796e21 #2167
[ 1567.700067] task: ffff880127efb000 ti: ffff880246770000 task.ti: ffff880246770000
[ 1567.700067] RIP: __phys_addr (arch/x86/mm/physaddr.c:26 (discriminator 3))
[ 1567.700067] RSP: 0018:ffff8802467779d8  EFLAGS: 00010202
[ 1567.700067] RAX: 000041000ed8e000 RBX: ffffc9008ed8e000 RCX: 000000000000002c
[ 1567.700067] RDX: 0000000000000004 RSI: 0000000000000000 RDI: ffffffffb3fd6049
[ 1567.700067] RBP: ffff8802467779f8 R08: 0000000000000019 R09: ffff8801d0168000
[ 1567.700067] R10: ffff8801d01680c7 R11: ffffed003a02d019 R12: ffffc9000ed8e000
[ 1567.700067] R13: 0000000000000f40 R14: 0000000000001180 R15: ffffc9000ed8e000
[ 1567.700067] FS:  00007f2a7da3f700(0000) GS:ffff8801d1000000(0000) knlGS:0000000000000000
[ 1567.700067] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 1567.700067] CR2: 0000000000738308 CR3: 000000022e329000 CR4: 00000000000007e0
[ 1567.700067] Stack:
[ 1567.700067]  ffffc9000ed8e000 ffff8801d0168000 ffffc9000ed8e000 ffff8801d0168000
[ 1567.700067]  ffff880246777a28 ffffffffad7c0a21 0000000000001080 ffff880246777c08
[ 1567.700067]  ffff88060d302e68 ffff880246777b58 ffff880246777b88 ffffffffad9a6821
[ 1567.700067] Call Trace:
[ 1567.700067] build_skb (include/linux/mm.h:508 net/core/skbuff.c:316)
[ 1567.700067] netlink_sendmsg (net/netlink/af_netlink.c:1633 net/netlink/af_netlink.c:2329)
[ 1567.774369] ? sched_clock_cpu (kernel/sched/clock.c:311)
[ 1567.774369] ? netlink_unicast (net/netlink/af_netlink.c:2273)
[ 1567.774369] ? netlink_unicast (net/netlink/af_netlink.c:2273)
[ 1567.774369] sock_sendmsg (net/socket.c:614 net/socket.c:623)
[ 1567.774369] sock_write_iter (net/socket.c:823)
[ 1567.774369] ? sock_sendmsg (net/socket.c:806)
[ 1567.774369] __vfs_write (fs/read_write.c:479 fs/read_write.c:491)
[ 1567.774369] ? get_lock_stats (kernel/locking/lockdep.c:249)
[ 1567.774369] ? default_llseek (fs/read_write.c:487)
[ 1567.774369] ? vtime_account_user (kernel/sched/cputime.c:701)
[ 1567.774369] ? rw_verify_area (fs/read_write.c:406 (discriminator 4))
[ 1567.774369] vfs_write (fs/read_write.c:539)
[ 1567.774369] SyS_write (fs/read_write.c:586 fs/read_write.c:577)
[ 1567.774369] ? SyS_read (fs/read_write.c:577)
[ 1567.774369] ? __this_cpu_preempt_check (lib/smp_processor_id.c:63)
[ 1567.774369] ? trace_hardirqs_on_caller (kernel/locking/lockdep.c:2594 kernel/locking/lockdep.c:2636)
[ 1567.774369] ? trace_hardirqs_on_thunk (arch/x86/lib/thunk_64.S:42)
[ 1567.774369] system_call_fastpath (arch/x86/kernel/entry_64.S:261)

Fixes: 79930f5892e ("net: do not deplete pfmemalloc reserve")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h   |  1 +
 net/core/skbuff.c        | 31 ++++++++++++++++++++++---------
 net/netlink/af_netlink.c |  6 ++----
 3 files changed, 25 insertions(+), 13 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index ad8f859..ab31337 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -661,6 +661,7 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
 
 struct sk_buff *__alloc_skb(unsigned int size, gfp_t priority, int flags,
 			    int node);
+struct sk_buff *__build_skb(void *data, unsigned int frag_size);
 struct sk_buff *build_skb(void *data, unsigned int frag_size);
 static inline struct sk_buff *alloc_skb(unsigned int size,
 					gfp_t priority)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 8334c70..69ec61a 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -278,13 +278,14 @@ nodata:
 EXPORT_SYMBOL(__alloc_skb);
 
 /**
- * build_skb - build a network buffer
+ * __build_skb - build a network buffer
  * @data: data buffer provided by caller
- * @frag_size: size of fragment, or 0 if head was kmalloced
+ * @frag_size: size of data, or 0 if head was kmalloced
  *
  * Allocate a new &sk_buff. Caller provides space holding head and
  * skb_shared_info. @data must have been allocated by kmalloc() only if
- * @frag_size is 0, otherwise data should come from the page allocator.
+ * @frag_size is 0, otherwise data should come from the page allocator
+ *  or vmalloc()
  * The return is the new skb buffer.
  * On a failure the return is %NULL, and @data is not freed.
  * Notes :
@@ -295,7 +296,7 @@ EXPORT_SYMBOL(__alloc_skb);
  *  before giving packet to stack.
  *  RX rings only contains data buffers, not full skbs.
  */
-struct sk_buff *build_skb(void *data, unsigned int frag_size)
+struct sk_buff *__build_skb(void *data, unsigned int frag_size)
 {
 	struct skb_shared_info *shinfo;
 	struct sk_buff *skb;
@@ -309,11 +310,6 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
 
 	memset(skb, 0, offsetof(struct sk_buff, tail));
 	skb->truesize = SKB_TRUESIZE(size);
-	if (frag_size) {
-		skb->head_frag = 1;
-		if (virt_to_head_page(data)->pfmemalloc)
-			skb->pfmemalloc = 1;
-	}
 	atomic_set(&skb->users, 1);
 	skb->head = data;
 	skb->data = data;
@@ -330,6 +326,23 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
 
 	return skb;
 }
+
+/* build_skb() is wrapper over __build_skb(), that specifically
+ * takes care of skb->head and skb->pfmemalloc
+ * This means that if @frag_size is not zero, then @data must be backed
+ * by a page fragment, not kmalloc() or vmalloc()
+ */
+struct sk_buff *build_skb(void *data, unsigned int frag_size)
+{
+	struct sk_buff *skb = __build_skb(data, frag_size);
+
+	if (skb && frag_size) {
+		skb->head_frag = 1;
+		if (virt_to_head_page(data)->pfmemalloc)
+			skb->pfmemalloc = 1;
+	}
+	return skb;
+}
 EXPORT_SYMBOL(build_skb);
 
 struct netdev_alloc_cache {
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 1d52506..a0b0ea9 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1624,13 +1624,11 @@ static struct sk_buff *netlink_alloc_large_skb(unsigned int size,
 	if (data == NULL)
 		return NULL;
 
-	skb = build_skb(data, size);
+	skb = __build_skb(data, size);
 	if (skb == NULL)
 		vfree(data);
-	else {
-		skb->head_frag = 0;
+	else
 		skb->destructor = netlink_skb_destructor;
-	}
 
 	return skb;
 }
-- 
2.3.6


[-- Attachment #4: net_318.mbox --]
[-- Type: Application/Octet-Stream, Size: 19297 bytes --]

From 69ee70ff843afd8d6922dbc151993ab2cef5fd41 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Sebastian=20P=C3=B6hn?= <sebastian.poehn@gmail.com>
Date: Mon, 20 Apr 2015 09:19:20 +0200
Subject: [PATCH 1/7] ip_forward: Drop frames with attached skb->sk

[ Upstream commit 2ab957492d13bb819400ac29ae55911d50a82a13 ]

Initial discussion was:
[FYI] xfrm: Don't lookup sk_policy for timewait sockets

Forwarded frames should not have a socket attached. Especially
tw sockets will lead to panics later-on in the stack.

This was observed with TPROXY assigning a tw socket and broken
policy routing (misconfigured). As a result frame enters
forwarding path instead of input. We cannot solve this in
TPROXY as it cannot know that policy routing is broken.

v2:
Remove useless comment

Signed-off-by: Sebastian Poehn <sebastian.poehn@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_forward.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 787b3c2..d5410b5 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -81,6 +81,9 @@ int ip_forward(struct sk_buff *skb)
 	if (skb->pkt_type != PACKET_HOST)
 		goto drop;
 
+	if (unlikely(skb->sk))
+		goto drop;
+
 	if (skb_warn_if_lro(skb))
 		goto drop;
 
-- 
2.3.5


From 9cc1e7e7d42bebe606b5850759a1a9295369ca45 Mon Sep 17 00:00:00 2001
From: Tom Herbert <tom@herbertland.com>
Date: Mon, 20 Apr 2015 14:10:04 -0700
Subject: [PATCH 2/7] net: add skb_checksum_complete_unset

[ Upstream commit 4e18b9adf2f910ec4d30b811a74a5b626e6c6125 ]

This function changes ip_summed to CHECKSUM_NONE if CHECKSUM_COMPLETE
is set. This is called to discard checksum-complete when packet
is being modified and checksum is not pulled for headers in a layer.

Signed-off-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 6c8b6f6..ab4a319 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2958,6 +2958,18 @@ static inline bool __skb_checksum_validate_needed(struct sk_buff *skb,
  */
 #define CHECKSUM_BREAK 76
 
+/* Unset checksum-complete
+ *
+ * Unset checksum complete can be done when packet is being modified
+ * (uncompressed for instance) and checksum-complete value is
+ * invalidated.
+ */
+static inline void skb_checksum_complete_unset(struct sk_buff *skb)
+{
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		skb->ip_summed = CHECKSUM_NONE;
+}
+
 /* Validate (init) checksum based on checksum complete.
  *
  * Return values:
-- 
2.3.5


From c11b6e6c3b2758397e35ddd214aa008224643211 Mon Sep 17 00:00:00 2001
From: Tom Herbert <tom@herbertland.com>
Date: Mon, 20 Apr 2015 14:10:05 -0700
Subject: [PATCH 3/7] ppp: call skb_checksum_complete_unset in
 ppp_receive_frame

[ Upstream commit 3dfb05340ec6676e6fc71a9ae87bbbe66d3c2998 ]

Call checksum_complete_unset in PPP receive to discard checksum-complete
value. PPP does not pull checksum for headers and also modifies packet
as in VJ compression.

Signed-off-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/ppp_generic.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 794a473..6d6c20c 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -1714,6 +1714,7 @@ ppp_receive_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch)
 {
 	/* note: a 0-length skb is used as an error indication */
 	if (skb->len > 0) {
+		skb_checksum_complete_unset(skb);
 #ifdef CONFIG_PPP_MULTILINK
 		/* XXX do channel-level decompression here */
 		if (PPP_PROTO(skb) == PPP_MP)
-- 
2.3.5


From fa0bc23ff0a35dc94f51c487f663a29daaa72a27 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 21 Apr 2015 18:32:24 -0700
Subject: [PATCH 4/7] tcp: fix possible deadlock in tcp_send_fin()

[ Upstream commit d83769a580f1132ac26439f50068a29b02be535e ]

Using sk_stream_alloc_skb() in tcp_send_fin() is dangerous in
case a huge process is killed by OOM, and tcp_mem[2] is hit.

To be able to free memory we need to make progress, so this
patch allows FIN packets to not care about tcp_mem[2], if
skb allocation succeeded.

In a follow-up patch, we might abort tcp_send_fin() infinite loop
in case TIF_MEMDIE is set on this thread, as memory allocator
did its best getting extra memory already.

This patch reverts d22e15371811 ("tcp: fix tcp fin memory accounting")

Fixes: d22e15371811 ("tcp: fix tcp fin memory accounting")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 022ecbc..6a62c3b 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2717,6 +2717,21 @@ begin_fwd:
 	}
 }
 
+/* We allow to exceed memory limits for FIN packets to expedite
+ * connection tear down and (memory) recovery.
+ * Otherwise tcp_send_fin() could loop forever.
+ */
+static void sk_forced_wmem_schedule(struct sock *sk, int size)
+{
+	int amt, status;
+
+	if (size <= sk->sk_forward_alloc)
+		return;
+	amt = sk_mem_pages(size);
+	sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
+	sk_memory_allocated_add(sk, amt, &status);
+}
+
 /* Send a fin.  The caller locks the socket for us.  This cannot be
  * allowed to fail queueing a FIN frame under any circumstances.
  */
@@ -2739,11 +2754,14 @@ void tcp_send_fin(struct sock *sk)
 	} else {
 		/* Socket is locked, keep trying until memory is available. */
 		for (;;) {
-			skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation);
+			skb = alloc_skb_fclone(MAX_TCP_HEADER,
+					       sk->sk_allocation);
 			if (skb)
 				break;
 			yield();
 		}
+		skb_reserve(skb, MAX_TCP_HEADER);
+		sk_forced_wmem_schedule(sk, skb->truesize);
 		/* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */
 		tcp_init_nondata_skb(skb, tp->write_seq,
 				     TCPHDR_ACK | TCPHDR_FIN);
-- 
2.3.5


From 2abed4fa65bc56870a9b867c2303e69503787a47 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 23 Apr 2015 10:42:39 -0700
Subject: [PATCH 5/7] tcp: avoid looping in tcp_send_fin()

[ Upstream commit 845704a535e9b3c76448f52af1b70e4422ea03fd ]

Presence of an unbound loop in tcp_send_fin() had always been hard
to explain when analyzing crash dumps involving gigantic dying processes
with millions of sockets.

Lets try a different strategy :

In case of memory pressure, try to add the FIN flag to last packet
in write queue, even if packet was already sent. TCP stack will
be able to deliver this FIN after a timeout event. Note that this
FIN being delivered by a retransmit, it also carries a Push flag
given our current implementation.

By checking sk_under_memory_pressure(), we anticipate that cooking
many FIN packets might deplete tcp memory.

In the case we could not allocate a packet, even with __GFP_WAIT
allocation, then not sending a FIN seems quite reasonable if it allows
to get rid of this socket, free memory, and not block the process from
eventually doing other useful work.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 50 +++++++++++++++++++++++++++++---------------------
 1 file changed, 29 insertions(+), 21 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 6a62c3b..d872d39 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2719,7 +2719,8 @@ begin_fwd:
 
 /* We allow to exceed memory limits for FIN packets to expedite
  * connection tear down and (memory) recovery.
- * Otherwise tcp_send_fin() could loop forever.
+ * Otherwise tcp_send_fin() could be tempted to either delay FIN
+ * or even be forced to close flow without any FIN.
  */
 static void sk_forced_wmem_schedule(struct sock *sk, int size)
 {
@@ -2732,33 +2733,40 @@ static void sk_forced_wmem_schedule(struct sock *sk, int size)
 	sk_memory_allocated_add(sk, amt, &status);
 }
 
-/* Send a fin.  The caller locks the socket for us.  This cannot be
- * allowed to fail queueing a FIN frame under any circumstances.
+/* Send a FIN. The caller locks the socket for us.
+ * We should try to send a FIN packet really hard, but eventually give up.
  */
 void tcp_send_fin(struct sock *sk)
 {
+	struct sk_buff *skb, *tskb = tcp_write_queue_tail(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct sk_buff *skb = tcp_write_queue_tail(sk);
-	int mss_now;
 
-	/* Optimization, tack on the FIN if we have a queue of
-	 * unsent frames.  But be careful about outgoing SACKS
-	 * and IP options.
+	/* Optimization, tack on the FIN if we have one skb in write queue and
+	 * this skb was not yet sent, or we are under memory pressure.
+	 * Note: in the latter case, FIN packet will be sent after a timeout,
+	 * as TCP stack thinks it has already been transmitted.
 	 */
-	mss_now = tcp_current_mss(sk);
-
-	if (tcp_send_head(sk) != NULL) {
-		TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_FIN;
-		TCP_SKB_CB(skb)->end_seq++;
+	if (tskb && (tcp_send_head(sk) || sk_under_memory_pressure(sk))) {
+coalesce:
+		TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN;
+		TCP_SKB_CB(tskb)->end_seq++;
 		tp->write_seq++;
+		if (!tcp_send_head(sk)) {
+			/* This means tskb was already sent.
+			 * Pretend we included the FIN on previous transmit.
+			 * We need to set tp->snd_nxt to the value it would have
+			 * if FIN had been sent. This is because retransmit path
+			 * does not change tp->snd_nxt.
+			 */
+			tp->snd_nxt++;
+			return;
+		}
 	} else {
-		/* Socket is locked, keep trying until memory is available. */
-		for (;;) {
-			skb = alloc_skb_fclone(MAX_TCP_HEADER,
-					       sk->sk_allocation);
-			if (skb)
-				break;
-			yield();
+		skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation);
+		if (unlikely(!skb)) {
+			if (tskb)
+				goto coalesce;
+			return;
 		}
 		skb_reserve(skb, MAX_TCP_HEADER);
 		sk_forced_wmem_schedule(sk, skb->truesize);
@@ -2767,7 +2775,7 @@ void tcp_send_fin(struct sock *sk)
 				     TCPHDR_ACK | TCPHDR_FIN);
 		tcp_queue_skb(sk, skb);
 	}
-	__tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_OFF);
+	__tcp_push_pending_frames(sk, tcp_current_mss(sk), TCP_NAGLE_OFF);
 }
 
 /* We get here when a process closes a file descriptor (either due to
-- 
2.3.5


From fc51d6c699fb64ff3b46d2d0f35f5a2850436b29 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 22 Apr 2015 07:33:36 -0700
Subject: [PATCH 6/7] net: do not deplete pfmemalloc reserve

[ Upstream commit 79930f5892e134c6da1254389577fffb8bd72c66 ]

build_skb() should look at the page pfmemalloc status.
If set, this means page allocator allocated this page in the
expectation it would help to free other pages. Networking
stack can do that only if skb->pfmemalloc is also set.

Also, we must refrain using high order pages from the pfmemalloc
reserve, so __page_frag_refill() must also use __GFP_NOMEMALLOC for
them. Under memory pressure, using order-0 pages is probably the best
strategy.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 79589ae..17157fc 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -309,7 +309,11 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
 
 	memset(skb, 0, offsetof(struct sk_buff, tail));
 	skb->truesize = SKB_TRUESIZE(size);
-	skb->head_frag = frag_size != 0;
+	if (frag_size) {
+		skb->head_frag = 1;
+		if (virt_to_head_page(data)->pfmemalloc)
+			skb->pfmemalloc = 1;
+	}
 	atomic_set(&skb->users, 1);
 	skb->head = data;
 	skb->data = data;
@@ -352,7 +356,8 @@ refill:
 			gfp_t gfp = gfp_mask;
 
 			if (order)
-				gfp |= __GFP_COMP | __GFP_NOWARN;
+				gfp |= __GFP_COMP | __GFP_NOWARN |
+				       __GFP_NOMEMALLOC;
 			nc->frag.page = alloc_pages(gfp, order);
 			if (likely(nc->frag.page))
 				break;
-- 
2.3.5


From 43b9a9ce030ef88445b45984b1e3ad2c6c7c514e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 24 Apr 2015 16:05:01 -0700
Subject: [PATCH 7/7] net: fix crash in build_skb()

[ Upstream commit 2ea2f62c8bda242433809c7f4e9eae1c52c40bbe ]

When I added pfmemalloc support in build_skb(), I forgot netlink
was using build_skb() with a vmalloc() area.

In this patch I introduce __build_skb() for netlink use,
and build_skb() is a wrapper handling both skb->head_frag and
skb->pfmemalloc

This means netlink no longer has to hack skb->head_frag

[ 1567.700067] kernel BUG at arch/x86/mm/physaddr.c:26!
[ 1567.700067] invalid opcode: 0000 [#1] PREEMPT SMP KASAN
[ 1567.700067] Dumping ftrace buffer:
[ 1567.700067]    (ftrace buffer empty)
[ 1567.700067] Modules linked in:
[ 1567.700067] CPU: 9 PID: 16186 Comm: trinity-c182 Not tainted 4.0.0-next-20150424-sasha-00037-g4796e21 #2167
[ 1567.700067] task: ffff880127efb000 ti: ffff880246770000 task.ti: ffff880246770000
[ 1567.700067] RIP: __phys_addr (arch/x86/mm/physaddr.c:26 (discriminator 3))
[ 1567.700067] RSP: 0018:ffff8802467779d8  EFLAGS: 00010202
[ 1567.700067] RAX: 000041000ed8e000 RBX: ffffc9008ed8e000 RCX: 000000000000002c
[ 1567.700067] RDX: 0000000000000004 RSI: 0000000000000000 RDI: ffffffffb3fd6049
[ 1567.700067] RBP: ffff8802467779f8 R08: 0000000000000019 R09: ffff8801d0168000
[ 1567.700067] R10: ffff8801d01680c7 R11: ffffed003a02d019 R12: ffffc9000ed8e000
[ 1567.700067] R13: 0000000000000f40 R14: 0000000000001180 R15: ffffc9000ed8e000
[ 1567.700067] FS:  00007f2a7da3f700(0000) GS:ffff8801d1000000(0000) knlGS:0000000000000000
[ 1567.700067] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 1567.700067] CR2: 0000000000738308 CR3: 000000022e329000 CR4: 00000000000007e0
[ 1567.700067] Stack:
[ 1567.700067]  ffffc9000ed8e000 ffff8801d0168000 ffffc9000ed8e000 ffff8801d0168000
[ 1567.700067]  ffff880246777a28 ffffffffad7c0a21 0000000000001080 ffff880246777c08
[ 1567.700067]  ffff88060d302e68 ffff880246777b58 ffff880246777b88 ffffffffad9a6821
[ 1567.700067] Call Trace:
[ 1567.700067] build_skb (include/linux/mm.h:508 net/core/skbuff.c:316)
[ 1567.700067] netlink_sendmsg (net/netlink/af_netlink.c:1633 net/netlink/af_netlink.c:2329)
[ 1567.774369] ? sched_clock_cpu (kernel/sched/clock.c:311)
[ 1567.774369] ? netlink_unicast (net/netlink/af_netlink.c:2273)
[ 1567.774369] ? netlink_unicast (net/netlink/af_netlink.c:2273)
[ 1567.774369] sock_sendmsg (net/socket.c:614 net/socket.c:623)
[ 1567.774369] sock_write_iter (net/socket.c:823)
[ 1567.774369] ? sock_sendmsg (net/socket.c:806)
[ 1567.774369] __vfs_write (fs/read_write.c:479 fs/read_write.c:491)
[ 1567.774369] ? get_lock_stats (kernel/locking/lockdep.c:249)
[ 1567.774369] ? default_llseek (fs/read_write.c:487)
[ 1567.774369] ? vtime_account_user (kernel/sched/cputime.c:701)
[ 1567.774369] ? rw_verify_area (fs/read_write.c:406 (discriminator 4))
[ 1567.774369] vfs_write (fs/read_write.c:539)
[ 1567.774369] SyS_write (fs/read_write.c:586 fs/read_write.c:577)
[ 1567.774369] ? SyS_read (fs/read_write.c:577)
[ 1567.774369] ? __this_cpu_preempt_check (lib/smp_processor_id.c:63)
[ 1567.774369] ? trace_hardirqs_on_caller (kernel/locking/lockdep.c:2594 kernel/locking/lockdep.c:2636)
[ 1567.774369] ? trace_hardirqs_on_thunk (arch/x86/lib/thunk_64.S:42)
[ 1567.774369] system_call_fastpath (arch/x86/kernel/entry_64.S:261)

Fixes: 79930f5892e ("net: do not deplete pfmemalloc reserve")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h   |  1 +
 net/core/skbuff.c        | 31 ++++++++++++++++++++++---------
 net/netlink/af_netlink.c |  6 ++----
 3 files changed, 25 insertions(+), 13 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index ab4a319..522d837 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -772,6 +772,7 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
 
 struct sk_buff *__alloc_skb(unsigned int size, gfp_t priority, int flags,
 			    int node);
+struct sk_buff *__build_skb(void *data, unsigned int frag_size);
 struct sk_buff *build_skb(void *data, unsigned int frag_size);
 static inline struct sk_buff *alloc_skb(unsigned int size,
 					gfp_t priority)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 17157fc..01f2d89 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -278,13 +278,14 @@ nodata:
 EXPORT_SYMBOL(__alloc_skb);
 
 /**
- * build_skb - build a network buffer
+ * __build_skb - build a network buffer
  * @data: data buffer provided by caller
- * @frag_size: size of fragment, or 0 if head was kmalloced
+ * @frag_size: size of data, or 0 if head was kmalloced
  *
  * Allocate a new &sk_buff. Caller provides space holding head and
  * skb_shared_info. @data must have been allocated by kmalloc() only if
- * @frag_size is 0, otherwise data should come from the page allocator.
+ * @frag_size is 0, otherwise data should come from the page allocator
+ *  or vmalloc()
  * The return is the new skb buffer.
  * On a failure the return is %NULL, and @data is not freed.
  * Notes :
@@ -295,7 +296,7 @@ EXPORT_SYMBOL(__alloc_skb);
  *  before giving packet to stack.
  *  RX rings only contains data buffers, not full skbs.
  */
-struct sk_buff *build_skb(void *data, unsigned int frag_size)
+struct sk_buff *__build_skb(void *data, unsigned int frag_size)
 {
 	struct skb_shared_info *shinfo;
 	struct sk_buff *skb;
@@ -309,11 +310,6 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
 
 	memset(skb, 0, offsetof(struct sk_buff, tail));
 	skb->truesize = SKB_TRUESIZE(size);
-	if (frag_size) {
-		skb->head_frag = 1;
-		if (virt_to_head_page(data)->pfmemalloc)
-			skb->pfmemalloc = 1;
-	}
 	atomic_set(&skb->users, 1);
 	skb->head = data;
 	skb->data = data;
@@ -330,6 +326,23 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
 
 	return skb;
 }
+
+/* build_skb() is wrapper over __build_skb(), that specifically
+ * takes care of skb->head and skb->pfmemalloc
+ * This means that if @frag_size is not zero, then @data must be backed
+ * by a page fragment, not kmalloc() or vmalloc()
+ */
+struct sk_buff *build_skb(void *data, unsigned int frag_size)
+{
+	struct sk_buff *skb = __build_skb(data, frag_size);
+
+	if (skb && frag_size) {
+		skb->head_frag = 1;
+		if (virt_to_head_page(data)->pfmemalloc)
+			skb->pfmemalloc = 1;
+	}
+	return skb;
+}
 EXPORT_SYMBOL(build_skb);
 
 struct netdev_alloc_cache {
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 79c965a..c0a4187 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1599,13 +1599,11 @@ static struct sk_buff *netlink_alloc_large_skb(unsigned int size,
 	if (data == NULL)
 		return NULL;
 
-	skb = build_skb(data, size);
+	skb = __build_skb(data, size);
 	if (skb == NULL)
 		vfree(data);
-	else {
-		skb->head_frag = 0;
+	else
 		skb->destructor = netlink_skb_destructor;
-	}
 
 	return skb;
 }
-- 
2.3.5


[-- Attachment #5: net_319.mbox --]
[-- Type: Application/Octet-Stream, Size: 25055 bytes --]

From 9cf79deb7dc6c9a5b40833d88b76e9ecb0ef06c0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Sebastian=20P=C3=B6hn?= <sebastian.poehn@gmail.com>
Date: Mon, 20 Apr 2015 09:19:20 +0200
Subject: [PATCH 1/9] ip_forward: Drop frames with attached skb->sk

[ Upstream commit 2ab957492d13bb819400ac29ae55911d50a82a13 ]

Initial discussion was:
[FYI] xfrm: Don't lookup sk_policy for timewait sockets

Forwarded frames should not have a socket attached. Especially
tw sockets will lead to panics later-on in the stack.

This was observed with TPROXY assigning a tw socket and broken
policy routing (misconfigured). As a result frame enters
forwarding path instead of input. We cannot solve this in
TPROXY as it cannot know that policy routing is broken.

v2:
Remove useless comment

Signed-off-by: Sebastian Poehn <sebastian.poehn@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_forward.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 787b3c2..d5410b5 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -81,6 +81,9 @@ int ip_forward(struct sk_buff *skb)
 	if (skb->pkt_type != PACKET_HOST)
 		goto drop;
 
+	if (unlikely(skb->sk))
+		goto drop;
+
 	if (skb_warn_if_lro(skb))
 		goto drop;
 
-- 
2.3.6


From 4c5f317475bfe735a452aec181cae1e861e13819 Mon Sep 17 00:00:00 2001
From: Tom Herbert <tom@herbertland.com>
Date: Mon, 20 Apr 2015 14:10:04 -0700
Subject: [PATCH 2/9] net: add skb_checksum_complete_unset

[ Upstream commit 4e18b9adf2f910ec4d30b811a74a5b626e6c6125 ]

This function changes ip_summed to CHECKSUM_NONE if CHECKSUM_COMPLETE
is set. This is called to discard checksum-complete when packet
is being modified and checksum is not pulled for headers in a layer.

Signed-off-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 85ab7d7..00e0ab9 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2998,6 +2998,18 @@ static inline bool __skb_checksum_validate_needed(struct sk_buff *skb,
  */
 #define CHECKSUM_BREAK 76
 
+/* Unset checksum-complete
+ *
+ * Unset checksum complete can be done when packet is being modified
+ * (uncompressed for instance) and checksum-complete value is
+ * invalidated.
+ */
+static inline void skb_checksum_complete_unset(struct sk_buff *skb)
+{
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		skb->ip_summed = CHECKSUM_NONE;
+}
+
 /* Validate (init) checksum based on checksum complete.
  *
  * Return values:
-- 
2.3.6


From ae7168d19a1e29a8fb77359be7a9ce9ea25da2c6 Mon Sep 17 00:00:00 2001
From: Tom Herbert <tom@herbertland.com>
Date: Mon, 20 Apr 2015 14:10:05 -0700
Subject: [PATCH 3/9] ppp: call skb_checksum_complete_unset in
 ppp_receive_frame

[ Upstream commit 3dfb05340ec6676e6fc71a9ae87bbbe66d3c2998 ]

Call checksum_complete_unset in PPP receive to discard checksum-complete
value. PPP does not pull checksum for headers and also modifies packet
as in VJ compression.

Signed-off-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/ppp_generic.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index af034db..9d15566 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -1716,6 +1716,7 @@ ppp_receive_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch)
 {
 	/* note: a 0-length skb is used as an error indication */
 	if (skb->len > 0) {
+		skb_checksum_complete_unset(skb);
 #ifdef CONFIG_PPP_MULTILINK
 		/* XXX do channel-level decompression here */
 		if (PPP_PROTO(skb) == PPP_MP)
-- 
2.3.6


From 9c193b660fe0da988b5ab5deb57658818390073d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 21 Apr 2015 18:32:24 -0700
Subject: [PATCH 4/9] tcp: fix possible deadlock in tcp_send_fin()

[ Upstream commit d83769a580f1132ac26439f50068a29b02be535e ]

Using sk_stream_alloc_skb() in tcp_send_fin() is dangerous in
case a huge process is killed by OOM, and tcp_mem[2] is hit.

To be able to free memory we need to make progress, so this
patch allows FIN packets to not care about tcp_mem[2], if
skb allocation succeeded.

In a follow-up patch, we might abort tcp_send_fin() infinite loop
in case TIF_MEMDIE is set on this thread, as memory allocator
did its best getting extra memory already.

This patch reverts d22e15371811 ("tcp: fix tcp fin memory accounting")

Fixes: d22e15371811 ("tcp: fix tcp fin memory accounting")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 9790f39..db50c38 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2753,6 +2753,21 @@ begin_fwd:
 	}
 }
 
+/* We allow to exceed memory limits for FIN packets to expedite
+ * connection tear down and (memory) recovery.
+ * Otherwise tcp_send_fin() could loop forever.
+ */
+static void sk_forced_wmem_schedule(struct sock *sk, int size)
+{
+	int amt, status;
+
+	if (size <= sk->sk_forward_alloc)
+		return;
+	amt = sk_mem_pages(size);
+	sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
+	sk_memory_allocated_add(sk, amt, &status);
+}
+
 /* Send a fin.  The caller locks the socket for us.  This cannot be
  * allowed to fail queueing a FIN frame under any circumstances.
  */
@@ -2775,11 +2790,14 @@ void tcp_send_fin(struct sock *sk)
 	} else {
 		/* Socket is locked, keep trying until memory is available. */
 		for (;;) {
-			skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation);
+			skb = alloc_skb_fclone(MAX_TCP_HEADER,
+					       sk->sk_allocation);
 			if (skb)
 				break;
 			yield();
 		}
+		skb_reserve(skb, MAX_TCP_HEADER);
+		sk_forced_wmem_schedule(sk, skb->truesize);
 		/* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */
 		tcp_init_nondata_skb(skb, tp->write_seq,
 				     TCPHDR_ACK | TCPHDR_FIN);
-- 
2.3.6


From 7d26e4e7adcb938180c19c252a4da77014e799d1 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 23 Apr 2015 10:42:39 -0700
Subject: [PATCH 5/9] tcp: avoid looping in tcp_send_fin()

[ Upstream commit 845704a535e9b3c76448f52af1b70e4422ea03fd ]

Presence of an unbound loop in tcp_send_fin() had always been hard
to explain when analyzing crash dumps involving gigantic dying processes
with millions of sockets.

Lets try a different strategy :

In case of memory pressure, try to add the FIN flag to last packet
in write queue, even if packet was already sent. TCP stack will
be able to deliver this FIN after a timeout event. Note that this
FIN being delivered by a retransmit, it also carries a Push flag
given our current implementation.

By checking sk_under_memory_pressure(), we anticipate that cooking
many FIN packets might deplete tcp memory.

In the case we could not allocate a packet, even with __GFP_WAIT
allocation, then not sending a FIN seems quite reasonable if it allows
to get rid of this socket, free memory, and not block the process from
eventually doing other useful work.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 50 +++++++++++++++++++++++++++++---------------------
 1 file changed, 29 insertions(+), 21 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index db50c38..08ff6d7 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2755,7 +2755,8 @@ begin_fwd:
 
 /* We allow to exceed memory limits for FIN packets to expedite
  * connection tear down and (memory) recovery.
- * Otherwise tcp_send_fin() could loop forever.
+ * Otherwise tcp_send_fin() could be tempted to either delay FIN
+ * or even be forced to close flow without any FIN.
  */
 static void sk_forced_wmem_schedule(struct sock *sk, int size)
 {
@@ -2768,33 +2769,40 @@ static void sk_forced_wmem_schedule(struct sock *sk, int size)
 	sk_memory_allocated_add(sk, amt, &status);
 }
 
-/* Send a fin.  The caller locks the socket for us.  This cannot be
- * allowed to fail queueing a FIN frame under any circumstances.
+/* Send a FIN. The caller locks the socket for us.
+ * We should try to send a FIN packet really hard, but eventually give up.
  */
 void tcp_send_fin(struct sock *sk)
 {
+	struct sk_buff *skb, *tskb = tcp_write_queue_tail(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct sk_buff *skb = tcp_write_queue_tail(sk);
-	int mss_now;
 
-	/* Optimization, tack on the FIN if we have a queue of
-	 * unsent frames.  But be careful about outgoing SACKS
-	 * and IP options.
+	/* Optimization, tack on the FIN if we have one skb in write queue and
+	 * this skb was not yet sent, or we are under memory pressure.
+	 * Note: in the latter case, FIN packet will be sent after a timeout,
+	 * as TCP stack thinks it has already been transmitted.
 	 */
-	mss_now = tcp_current_mss(sk);
-
-	if (tcp_send_head(sk) != NULL) {
-		TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_FIN;
-		TCP_SKB_CB(skb)->end_seq++;
+	if (tskb && (tcp_send_head(sk) || sk_under_memory_pressure(sk))) {
+coalesce:
+		TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN;
+		TCP_SKB_CB(tskb)->end_seq++;
 		tp->write_seq++;
+		if (!tcp_send_head(sk)) {
+			/* This means tskb was already sent.
+			 * Pretend we included the FIN on previous transmit.
+			 * We need to set tp->snd_nxt to the value it would have
+			 * if FIN had been sent. This is because retransmit path
+			 * does not change tp->snd_nxt.
+			 */
+			tp->snd_nxt++;
+			return;
+		}
 	} else {
-		/* Socket is locked, keep trying until memory is available. */
-		for (;;) {
-			skb = alloc_skb_fclone(MAX_TCP_HEADER,
-					       sk->sk_allocation);
-			if (skb)
-				break;
-			yield();
+		skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation);
+		if (unlikely(!skb)) {
+			if (tskb)
+				goto coalesce;
+			return;
 		}
 		skb_reserve(skb, MAX_TCP_HEADER);
 		sk_forced_wmem_schedule(sk, skb->truesize);
@@ -2803,7 +2811,7 @@ void tcp_send_fin(struct sock *sk)
 				     TCPHDR_ACK | TCPHDR_FIN);
 		tcp_queue_skb(sk, skb);
 	}
-	__tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_OFF);
+	__tcp_push_pending_frames(sk, tcp_current_mss(sk), TCP_NAGLE_OFF);
 }
 
 /* We get here when a process closes a file descriptor (either due to
-- 
2.3.6


From fae44d7c61bda854cb2671e5db61f69bab84e573 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 22 Apr 2015 07:33:36 -0700
Subject: [PATCH 6/9] net: do not deplete pfmemalloc reserve

[ Upstream commit 79930f5892e134c6da1254389577fffb8bd72c66 ]

build_skb() should look at the page pfmemalloc status.
If set, this means page allocator allocated this page in the
expectation it would help to free other pages. Networking
stack can do that only if skb->pfmemalloc is also set.

Also, we must refrain using high order pages from the pfmemalloc
reserve, so __page_frag_refill() must also use __GFP_NOMEMALLOC for
them. Under memory pressure, using order-0 pages is probably the best
strategy.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 62c67be..42d12c7 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -309,7 +309,11 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
 
 	memset(skb, 0, offsetof(struct sk_buff, tail));
 	skb->truesize = SKB_TRUESIZE(size);
-	skb->head_frag = frag_size != 0;
+	if (frag_size) {
+		skb->head_frag = 1;
+		if (virt_to_head_page(data)->pfmemalloc)
+			skb->pfmemalloc = 1;
+	}
 	atomic_set(&skb->users, 1);
 	skb->head = data;
 	skb->data = data;
@@ -346,7 +350,8 @@ static struct page *__page_frag_refill(struct netdev_alloc_cache *nc,
 	gfp_t gfp = gfp_mask;
 
 	if (order) {
-		gfp_mask |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY;
+		gfp_mask |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY |
+			    __GFP_NOMEMALLOC;
 		page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, order);
 		nc->frag.size = PAGE_SIZE << (page ? order : 0);
 	}
-- 
2.3.6


From 795b45179ea27ccebd645b06de0937302f00956d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 24 Apr 2015 16:05:01 -0700
Subject: [PATCH 7/9] net: fix crash in build_skb()

[ Upstream commit 2ea2f62c8bda242433809c7f4e9eae1c52c40bbe ]

When I added pfmemalloc support in build_skb(), I forgot netlink
was using build_skb() with a vmalloc() area.

In this patch I introduce __build_skb() for netlink use,
and build_skb() is a wrapper handling both skb->head_frag and
skb->pfmemalloc

This means netlink no longer has to hack skb->head_frag

[ 1567.700067] kernel BUG at arch/x86/mm/physaddr.c:26!
[ 1567.700067] invalid opcode: 0000 [#1] PREEMPT SMP KASAN
[ 1567.700067] Dumping ftrace buffer:
[ 1567.700067]    (ftrace buffer empty)
[ 1567.700067] Modules linked in:
[ 1567.700067] CPU: 9 PID: 16186 Comm: trinity-c182 Not tainted 4.0.0-next-20150424-sasha-00037-g4796e21 #2167
[ 1567.700067] task: ffff880127efb000 ti: ffff880246770000 task.ti: ffff880246770000
[ 1567.700067] RIP: __phys_addr (arch/x86/mm/physaddr.c:26 (discriminator 3))
[ 1567.700067] RSP: 0018:ffff8802467779d8  EFLAGS: 00010202
[ 1567.700067] RAX: 000041000ed8e000 RBX: ffffc9008ed8e000 RCX: 000000000000002c
[ 1567.700067] RDX: 0000000000000004 RSI: 0000000000000000 RDI: ffffffffb3fd6049
[ 1567.700067] RBP: ffff8802467779f8 R08: 0000000000000019 R09: ffff8801d0168000
[ 1567.700067] R10: ffff8801d01680c7 R11: ffffed003a02d019 R12: ffffc9000ed8e000
[ 1567.700067] R13: 0000000000000f40 R14: 0000000000001180 R15: ffffc9000ed8e000
[ 1567.700067] FS:  00007f2a7da3f700(0000) GS:ffff8801d1000000(0000) knlGS:0000000000000000
[ 1567.700067] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 1567.700067] CR2: 0000000000738308 CR3: 000000022e329000 CR4: 00000000000007e0
[ 1567.700067] Stack:
[ 1567.700067]  ffffc9000ed8e000 ffff8801d0168000 ffffc9000ed8e000 ffff8801d0168000
[ 1567.700067]  ffff880246777a28 ffffffffad7c0a21 0000000000001080 ffff880246777c08
[ 1567.700067]  ffff88060d302e68 ffff880246777b58 ffff880246777b88 ffffffffad9a6821
[ 1567.700067] Call Trace:
[ 1567.700067] build_skb (include/linux/mm.h:508 net/core/skbuff.c:316)
[ 1567.700067] netlink_sendmsg (net/netlink/af_netlink.c:1633 net/netlink/af_netlink.c:2329)
[ 1567.774369] ? sched_clock_cpu (kernel/sched/clock.c:311)
[ 1567.774369] ? netlink_unicast (net/netlink/af_netlink.c:2273)
[ 1567.774369] ? netlink_unicast (net/netlink/af_netlink.c:2273)
[ 1567.774369] sock_sendmsg (net/socket.c:614 net/socket.c:623)
[ 1567.774369] sock_write_iter (net/socket.c:823)
[ 1567.774369] ? sock_sendmsg (net/socket.c:806)
[ 1567.774369] __vfs_write (fs/read_write.c:479 fs/read_write.c:491)
[ 1567.774369] ? get_lock_stats (kernel/locking/lockdep.c:249)
[ 1567.774369] ? default_llseek (fs/read_write.c:487)
[ 1567.774369] ? vtime_account_user (kernel/sched/cputime.c:701)
[ 1567.774369] ? rw_verify_area (fs/read_write.c:406 (discriminator 4))
[ 1567.774369] vfs_write (fs/read_write.c:539)
[ 1567.774369] SyS_write (fs/read_write.c:586 fs/read_write.c:577)
[ 1567.774369] ? SyS_read (fs/read_write.c:577)
[ 1567.774369] ? __this_cpu_preempt_check (lib/smp_processor_id.c:63)
[ 1567.774369] ? trace_hardirqs_on_caller (kernel/locking/lockdep.c:2594 kernel/locking/lockdep.c:2636)
[ 1567.774369] ? trace_hardirqs_on_thunk (arch/x86/lib/thunk_64.S:42)
[ 1567.774369] system_call_fastpath (arch/x86/kernel/entry_64.S:261)

Fixes: 79930f5892e ("net: do not deplete pfmemalloc reserve")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h   |  1 +
 net/core/skbuff.c        | 31 ++++++++++++++++++++++---------
 net/netlink/af_netlink.c |  6 ++----
 3 files changed, 25 insertions(+), 13 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 00e0ab9..5fcc606 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -762,6 +762,7 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
 
 struct sk_buff *__alloc_skb(unsigned int size, gfp_t priority, int flags,
 			    int node);
+struct sk_buff *__build_skb(void *data, unsigned int frag_size);
 struct sk_buff *build_skb(void *data, unsigned int frag_size);
 static inline struct sk_buff *alloc_skb(unsigned int size,
 					gfp_t priority)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 42d12c7..de052c9 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -278,13 +278,14 @@ nodata:
 EXPORT_SYMBOL(__alloc_skb);
 
 /**
- * build_skb - build a network buffer
+ * __build_skb - build a network buffer
  * @data: data buffer provided by caller
- * @frag_size: size of fragment, or 0 if head was kmalloced
+ * @frag_size: size of data, or 0 if head was kmalloced
  *
  * Allocate a new &sk_buff. Caller provides space holding head and
  * skb_shared_info. @data must have been allocated by kmalloc() only if
- * @frag_size is 0, otherwise data should come from the page allocator.
+ * @frag_size is 0, otherwise data should come from the page allocator
+ *  or vmalloc()
  * The return is the new skb buffer.
  * On a failure the return is %NULL, and @data is not freed.
  * Notes :
@@ -295,7 +296,7 @@ EXPORT_SYMBOL(__alloc_skb);
  *  before giving packet to stack.
  *  RX rings only contains data buffers, not full skbs.
  */
-struct sk_buff *build_skb(void *data, unsigned int frag_size)
+struct sk_buff *__build_skb(void *data, unsigned int frag_size)
 {
 	struct skb_shared_info *shinfo;
 	struct sk_buff *skb;
@@ -309,11 +310,6 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
 
 	memset(skb, 0, offsetof(struct sk_buff, tail));
 	skb->truesize = SKB_TRUESIZE(size);
-	if (frag_size) {
-		skb->head_frag = 1;
-		if (virt_to_head_page(data)->pfmemalloc)
-			skb->pfmemalloc = 1;
-	}
 	atomic_set(&skb->users, 1);
 	skb->head = data;
 	skb->data = data;
@@ -330,6 +326,23 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
 
 	return skb;
 }
+
+/* build_skb() is wrapper over __build_skb(), that specifically
+ * takes care of skb->head and skb->pfmemalloc
+ * This means that if @frag_size is not zero, then @data must be backed
+ * by a page fragment, not kmalloc() or vmalloc()
+ */
+struct sk_buff *build_skb(void *data, unsigned int frag_size)
+{
+	struct sk_buff *skb = __build_skb(data, frag_size);
+
+	if (skb && frag_size) {
+		skb->head_frag = 1;
+		if (virt_to_head_page(data)->pfmemalloc)
+			skb->pfmemalloc = 1;
+	}
+	return skb;
+}
 EXPORT_SYMBOL(build_skb);
 
 struct netdev_alloc_cache {
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 75532ef..4b4a2a4 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1616,13 +1616,11 @@ static struct sk_buff *netlink_alloc_large_skb(unsigned int size,
 	if (data == NULL)
 		return NULL;
 
-	skb = build_skb(data, size);
+	skb = __build_skb(data, size);
 	if (skb == NULL)
 		vfree(data);
-	else {
-		skb->head_frag = 0;
+	else
 		skb->destructor = netlink_skb_destructor;
-	}
 
 	return skb;
 }
-- 
2.3.6


From d8e03f0454b99d90963c26c7c99cf18e6c1a5b6c Mon Sep 17 00:00:00 2001
From: Alexey Khoroshilov <khoroshilov@ispras.ru>
Date: Sat, 25 Apr 2015 04:07:03 +0300
Subject: [PATCH 8/9] pxa168: fix double deallocation of managed resources

[ Upstream commit 0e03fd3e335d272bee88fe733d5fd13f5c5b7140 ]

Commit 43d3ddf87a57 ("net: pxa168_eth: add device tree support") starts
to use managed resources by adding devm_clk_get() and
devm_ioremap_resource(), but it leaves explicit iounmap() and clock_put()
in pxa168_eth_remove() and in failure handling code of pxa168_eth_probe().
As a result double free can happen.

The patch removes explicit resource deallocation. Also it converts
clk_disable() to clk_disable_unprepare() to make it symmetrical with
clk_prepare_enable().

Found by Linux Driver Verification project (linuxtesting.org).

Signed-off-by: Alexey Khoroshilov <khoroshilov@ispras.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/pxa168_eth.c | 16 +++++-----------
 1 file changed, 5 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c
index af829c5..7ace07d 100644
--- a/drivers/net/ethernet/marvell/pxa168_eth.c
+++ b/drivers/net/ethernet/marvell/pxa168_eth.c
@@ -1508,7 +1508,8 @@ static int pxa168_eth_probe(struct platform_device *pdev)
 		np = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0);
 		if (!np) {
 			dev_err(&pdev->dev, "missing phy-handle\n");
-			return -EINVAL;
+			err = -EINVAL;
+			goto err_netdev;
 		}
 		of_property_read_u32(np, "reg", &pep->phy_addr);
 		pep->phy_intf = of_get_phy_mode(pdev->dev.of_node);
@@ -1526,7 +1527,7 @@ static int pxa168_eth_probe(struct platform_device *pdev)
 	pep->smi_bus = mdiobus_alloc();
 	if (pep->smi_bus == NULL) {
 		err = -ENOMEM;
-		goto err_base;
+		goto err_netdev;
 	}
 	pep->smi_bus->priv = pep;
 	pep->smi_bus->name = "pxa168_eth smi";
@@ -1551,13 +1552,10 @@ err_mdiobus:
 	mdiobus_unregister(pep->smi_bus);
 err_free_mdio:
 	mdiobus_free(pep->smi_bus);
-err_base:
-	iounmap(pep->base);
 err_netdev:
 	free_netdev(dev);
 err_clk:
-	clk_disable(clk);
-	clk_put(clk);
+	clk_disable_unprepare(clk);
 	return err;
 }
 
@@ -1574,13 +1572,9 @@ static int pxa168_eth_remove(struct platform_device *pdev)
 	if (pep->phy)
 		phy_disconnect(pep->phy);
 	if (pep->clk) {
-		clk_disable(pep->clk);
-		clk_put(pep->clk);
-		pep->clk = NULL;
+		clk_disable_unprepare(pep->clk);
 	}
 
-	iounmap(pep->base);
-	pep->base = NULL;
 	mdiobus_unregister(pep->smi_bus);
 	mdiobus_free(pep->smi_bus);
 	unregister_netdev(dev);
-- 
2.3.6


From 43406229e803a132d4e1991684c5edd52afafde9 Mon Sep 17 00:00:00 2001
From: Amir Vadai <amirv@mellanox.com>
Date: Mon, 27 Apr 2015 13:40:56 +0300
Subject: [PATCH 9/9] net/mlx4_en: Prevent setting invalid RSS hash function

[ Upstream commit b37069090b7c5615610a8aa6b36533d67b364d38 ]

mlx4_en_check_rxfh_func() was checking for hardware support before
setting a known RSS hash function, but didn't do any check before
setting unknown RSS hash function. Need to make it fail on such values.
In this occasion, moved the actual setting of the new value from the
check function into mlx4_en_set_rxfh().

Fixes: 947cbb0 ("net/mlx4_en: Support for configurable RSS hash function")
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 29 ++++++++++++++-----------
 1 file changed, 16 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 90e0f04..33637eb 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -983,20 +983,21 @@ static int mlx4_en_check_rxfh_func(struct net_device *dev, u8 hfunc)
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 
 	/* check if requested function is supported by the device */
-	if ((hfunc == ETH_RSS_HASH_TOP &&
-	     !(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS_TOP)) ||
-	    (hfunc == ETH_RSS_HASH_XOR &&
-	     !(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS_XOR)))
-		return -EINVAL;
+	if (hfunc == ETH_RSS_HASH_TOP) {
+		if (!(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS_TOP))
+			return -EINVAL;
+		if (!(dev->features & NETIF_F_RXHASH))
+			en_warn(priv, "Toeplitz hash function should be used in conjunction with RX hashing for optimal performance\n");
+		return 0;
+	} else if (hfunc == ETH_RSS_HASH_XOR) {
+		if (!(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS_XOR))
+			return -EINVAL;
+		if (dev->features & NETIF_F_RXHASH)
+			en_warn(priv, "Enabling both XOR Hash function and RX Hashing can limit RPS functionality\n");
+		return 0;
+	}
 
-	priv->rss_hash_fn = hfunc;
-	if (hfunc == ETH_RSS_HASH_TOP && !(dev->features & NETIF_F_RXHASH))
-		en_warn(priv,
-			"Toeplitz hash function should be used in conjunction with RX hashing for optimal performance\n");
-	if (hfunc == ETH_RSS_HASH_XOR && (dev->features & NETIF_F_RXHASH))
-		en_warn(priv,
-			"Enabling both XOR Hash function and RX Hashing can limit RPS functionality\n");
-	return 0;
+	return -EINVAL;
 }
 
 static int mlx4_en_get_rxfh(struct net_device *dev, u32 *ring_index, u8 *key,
@@ -1070,6 +1071,8 @@ static int mlx4_en_set_rxfh(struct net_device *dev, const u32 *ring_index,
 		priv->prof->rss_rings = rss_rings;
 	if (key)
 		memcpy(priv->rss_key, key, MLX4_EN_RSS_KEY_SIZE);
+	if (hfunc !=  ETH_RSS_HASH_NO_CHANGE)
+		priv->rss_hash_fn = hfunc;
 
 	if (port_up) {
 		err = mlx4_en_start_port(dev);
-- 
2.3.6


[-- Attachment #6: net_40.mbox --]
[-- Type: Application/Octet-Stream, Size: 29319 bytes --]

From 38f81e01a6a4d266a2ce723c61fdbb697038fe5b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Sebastian=20P=C3=B6hn?= <sebastian.poehn@gmail.com>
Date: Mon, 20 Apr 2015 09:19:20 +0200
Subject: [PATCH 01/10] ip_forward: Drop frames with attached skb->sk

[ Upstream commit 2ab957492d13bb819400ac29ae55911d50a82a13 ]

Initial discussion was:
[FYI] xfrm: Don't lookup sk_policy for timewait sockets

Forwarded frames should not have a socket attached. Especially
tw sockets will lead to panics later-on in the stack.

This was observed with TPROXY assigning a tw socket and broken
policy routing (misconfigured). As a result frame enters
forwarding path instead of input. We cannot solve this in
TPROXY as it cannot know that policy routing is broken.

v2:
Remove useless comment

Signed-off-by: Sebastian Poehn <sebastian.poehn@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_forward.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index d9bc28a..53bd53f 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -82,6 +82,9 @@ int ip_forward(struct sk_buff *skb)
 	if (skb->pkt_type != PACKET_HOST)
 		goto drop;
 
+	if (unlikely(skb->sk))
+		goto drop;
+
 	if (skb_warn_if_lro(skb))
 		goto drop;
 
-- 
2.3.5


From 165d0c7e95698cd892d76245835ef612a31b3324 Mon Sep 17 00:00:00 2001
From: Tom Herbert <tom@herbertland.com>
Date: Mon, 20 Apr 2015 14:10:04 -0700
Subject: [PATCH 02/10] net: add skb_checksum_complete_unset

[ Upstream commit 4e18b9adf2f910ec4d30b811a74a5b626e6c6125 ]

This function changes ip_summed to CHECKSUM_NONE if CHECKSUM_COMPLETE
is set. This is called to discard checksum-complete when packet
is being modified and checksum is not pulled for headers in a layer.

Signed-off-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index f54d665..b5c204c 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3013,6 +3013,18 @@ static inline bool __skb_checksum_validate_needed(struct sk_buff *skb,
  */
 #define CHECKSUM_BREAK 76
 
+/* Unset checksum-complete
+ *
+ * Unset checksum complete can be done when packet is being modified
+ * (uncompressed for instance) and checksum-complete value is
+ * invalidated.
+ */
+static inline void skb_checksum_complete_unset(struct sk_buff *skb)
+{
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		skb->ip_summed = CHECKSUM_NONE;
+}
+
 /* Validate (init) checksum based on checksum complete.
  *
  * Return values:
-- 
2.3.5


From ee0aed8f52def12d122d719c68b522377dc9f3df Mon Sep 17 00:00:00 2001
From: Tom Herbert <tom@herbertland.com>
Date: Mon, 20 Apr 2015 14:10:05 -0700
Subject: [PATCH 03/10] ppp: call skb_checksum_complete_unset in
 ppp_receive_frame

[ Upstream commit 3dfb05340ec6676e6fc71a9ae87bbbe66d3c2998 ]

Call checksum_complete_unset in PPP receive to discard checksum-complete
value. PPP does not pull checksum for headers and also modifies packet
as in VJ compression.

Signed-off-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/ppp_generic.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index af034db..9d15566 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -1716,6 +1716,7 @@ ppp_receive_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch)
 {
 	/* note: a 0-length skb is used as an error indication */
 	if (skb->len > 0) {
+		skb_checksum_complete_unset(skb);
 #ifdef CONFIG_PPP_MULTILINK
 		/* XXX do channel-level decompression here */
 		if (PPP_PROTO(skb) == PPP_MP)
-- 
2.3.5


From 8ff7b94c5d2d0666d74a92a49152b31d97f97414 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 21 Apr 2015 18:32:24 -0700
Subject: [PATCH 04/10] tcp: fix possible deadlock in tcp_send_fin()

[ Upstream commit d83769a580f1132ac26439f50068a29b02be535e ]

Using sk_stream_alloc_skb() in tcp_send_fin() is dangerous in
case a huge process is killed by OOM, and tcp_mem[2] is hit.

To be able to free memory we need to make progress, so this
patch allows FIN packets to not care about tcp_mem[2], if
skb allocation succeeded.

In a follow-up patch, we might abort tcp_send_fin() infinite loop
in case TIF_MEMDIE is set on this thread, as memory allocator
did its best getting extra memory already.

This patch reverts d22e15371811 ("tcp: fix tcp fin memory accounting")

Fixes: d22e15371811 ("tcp: fix tcp fin memory accounting")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 1db253e..4bb095b 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2751,6 +2751,21 @@ begin_fwd:
 	}
 }
 
+/* We allow to exceed memory limits for FIN packets to expedite
+ * connection tear down and (memory) recovery.
+ * Otherwise tcp_send_fin() could loop forever.
+ */
+static void sk_forced_wmem_schedule(struct sock *sk, int size)
+{
+	int amt, status;
+
+	if (size <= sk->sk_forward_alloc)
+		return;
+	amt = sk_mem_pages(size);
+	sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
+	sk_memory_allocated_add(sk, amt, &status);
+}
+
 /* Send a fin.  The caller locks the socket for us.  This cannot be
  * allowed to fail queueing a FIN frame under any circumstances.
  */
@@ -2773,11 +2788,14 @@ void tcp_send_fin(struct sock *sk)
 	} else {
 		/* Socket is locked, keep trying until memory is available. */
 		for (;;) {
-			skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation);
+			skb = alloc_skb_fclone(MAX_TCP_HEADER,
+					       sk->sk_allocation);
 			if (skb)
 				break;
 			yield();
 		}
+		skb_reserve(skb, MAX_TCP_HEADER);
+		sk_forced_wmem_schedule(sk, skb->truesize);
 		/* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */
 		tcp_init_nondata_skb(skb, tp->write_seq,
 				     TCPHDR_ACK | TCPHDR_FIN);
-- 
2.3.5


From 6978b183200ab8b504888147faa694bbe07e56b3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 23 Apr 2015 10:42:39 -0700
Subject: [PATCH 05/10] tcp: avoid looping in tcp_send_fin()

[ Upstream commit 845704a535e9b3c76448f52af1b70e4422ea03fd ]

Presence of an unbound loop in tcp_send_fin() had always been hard
to explain when analyzing crash dumps involving gigantic dying processes
with millions of sockets.

Lets try a different strategy :

In case of memory pressure, try to add the FIN flag to last packet
in write queue, even if packet was already sent. TCP stack will
be able to deliver this FIN after a timeout event. Note that this
FIN being delivered by a retransmit, it also carries a Push flag
given our current implementation.

By checking sk_under_memory_pressure(), we anticipate that cooking
many FIN packets might deplete tcp memory.

In the case we could not allocate a packet, even with __GFP_WAIT
allocation, then not sending a FIN seems quite reasonable if it allows
to get rid of this socket, free memory, and not block the process from
eventually doing other useful work.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 50 +++++++++++++++++++++++++++++---------------------
 1 file changed, 29 insertions(+), 21 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 4bb095b..12d0a95 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2753,7 +2753,8 @@ begin_fwd:
 
 /* We allow to exceed memory limits for FIN packets to expedite
  * connection tear down and (memory) recovery.
- * Otherwise tcp_send_fin() could loop forever.
+ * Otherwise tcp_send_fin() could be tempted to either delay FIN
+ * or even be forced to close flow without any FIN.
  */
 static void sk_forced_wmem_schedule(struct sock *sk, int size)
 {
@@ -2766,33 +2767,40 @@ static void sk_forced_wmem_schedule(struct sock *sk, int size)
 	sk_memory_allocated_add(sk, amt, &status);
 }
 
-/* Send a fin.  The caller locks the socket for us.  This cannot be
- * allowed to fail queueing a FIN frame under any circumstances.
+/* Send a FIN. The caller locks the socket for us.
+ * We should try to send a FIN packet really hard, but eventually give up.
  */
 void tcp_send_fin(struct sock *sk)
 {
+	struct sk_buff *skb, *tskb = tcp_write_queue_tail(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct sk_buff *skb = tcp_write_queue_tail(sk);
-	int mss_now;
 
-	/* Optimization, tack on the FIN if we have a queue of
-	 * unsent frames.  But be careful about outgoing SACKS
-	 * and IP options.
+	/* Optimization, tack on the FIN if we have one skb in write queue and
+	 * this skb was not yet sent, or we are under memory pressure.
+	 * Note: in the latter case, FIN packet will be sent after a timeout,
+	 * as TCP stack thinks it has already been transmitted.
 	 */
-	mss_now = tcp_current_mss(sk);
-
-	if (tcp_send_head(sk) != NULL) {
-		TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_FIN;
-		TCP_SKB_CB(skb)->end_seq++;
+	if (tskb && (tcp_send_head(sk) || sk_under_memory_pressure(sk))) {
+coalesce:
+		TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN;
+		TCP_SKB_CB(tskb)->end_seq++;
 		tp->write_seq++;
+		if (!tcp_send_head(sk)) {
+			/* This means tskb was already sent.
+			 * Pretend we included the FIN on previous transmit.
+			 * We need to set tp->snd_nxt to the value it would have
+			 * if FIN had been sent. This is because retransmit path
+			 * does not change tp->snd_nxt.
+			 */
+			tp->snd_nxt++;
+			return;
+		}
 	} else {
-		/* Socket is locked, keep trying until memory is available. */
-		for (;;) {
-			skb = alloc_skb_fclone(MAX_TCP_HEADER,
-					       sk->sk_allocation);
-			if (skb)
-				break;
-			yield();
+		skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation);
+		if (unlikely(!skb)) {
+			if (tskb)
+				goto coalesce;
+			return;
 		}
 		skb_reserve(skb, MAX_TCP_HEADER);
 		sk_forced_wmem_schedule(sk, skb->truesize);
@@ -2801,7 +2809,7 @@ void tcp_send_fin(struct sock *sk)
 				     TCPHDR_ACK | TCPHDR_FIN);
 		tcp_queue_skb(sk, skb);
 	}
-	__tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_OFF);
+	__tcp_push_pending_frames(sk, tcp_current_mss(sk), TCP_NAGLE_OFF);
 }
 
 /* We get here when a process closes a file descriptor (either due to
-- 
2.3.5


From 23016a189d8661fd7f96a38d68ca38b8392fdc0e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 22 Apr 2015 07:33:36 -0700
Subject: [PATCH 06/10] net: do not deplete pfmemalloc reserve

[ Upstream commit 79930f5892e134c6da1254389577fffb8bd72c66 ]

build_skb() should look at the page pfmemalloc status.
If set, this means page allocator allocated this page in the
expectation it would help to free other pages. Networking
stack can do that only if skb->pfmemalloc is also set.

Also, we must refrain using high order pages from the pfmemalloc
reserve, so __page_frag_refill() must also use __GFP_NOMEMALLOC for
them. Under memory pressure, using order-0 pages is probably the best
strategy.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 8e4ac97..9f708d3 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -311,7 +311,11 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
 
 	memset(skb, 0, offsetof(struct sk_buff, tail));
 	skb->truesize = SKB_TRUESIZE(size);
-	skb->head_frag = frag_size != 0;
+	if (frag_size) {
+		skb->head_frag = 1;
+		if (virt_to_head_page(data)->pfmemalloc)
+			skb->pfmemalloc = 1;
+	}
 	atomic_set(&skb->users, 1);
 	skb->head = data;
 	skb->data = data;
@@ -348,7 +352,8 @@ static struct page *__page_frag_refill(struct netdev_alloc_cache *nc,
 	gfp_t gfp = gfp_mask;
 
 	if (order) {
-		gfp_mask |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY;
+		gfp_mask |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY |
+			    __GFP_NOMEMALLOC;
 		page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, order);
 		nc->frag.size = PAGE_SIZE << (page ? order : 0);
 	}
-- 
2.3.5


From 93117e27c6ac7edeb7cb8e71e11c3dfe676df8be Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 24 Apr 2015 16:05:01 -0700
Subject: [PATCH 07/10] net: fix crash in build_skb()

[ Upstream commit 2ea2f62c8bda242433809c7f4e9eae1c52c40bbe ]

When I added pfmemalloc support in build_skb(), I forgot netlink
was using build_skb() with a vmalloc() area.

In this patch I introduce __build_skb() for netlink use,
and build_skb() is a wrapper handling both skb->head_frag and
skb->pfmemalloc

This means netlink no longer has to hack skb->head_frag

[ 1567.700067] kernel BUG at arch/x86/mm/physaddr.c:26!
[ 1567.700067] invalid opcode: 0000 [#1] PREEMPT SMP KASAN
[ 1567.700067] Dumping ftrace buffer:
[ 1567.700067]    (ftrace buffer empty)
[ 1567.700067] Modules linked in:
[ 1567.700067] CPU: 9 PID: 16186 Comm: trinity-c182 Not tainted 4.0.0-next-20150424-sasha-00037-g4796e21 #2167
[ 1567.700067] task: ffff880127efb000 ti: ffff880246770000 task.ti: ffff880246770000
[ 1567.700067] RIP: __phys_addr (arch/x86/mm/physaddr.c:26 (discriminator 3))
[ 1567.700067] RSP: 0018:ffff8802467779d8  EFLAGS: 00010202
[ 1567.700067] RAX: 000041000ed8e000 RBX: ffffc9008ed8e000 RCX: 000000000000002c
[ 1567.700067] RDX: 0000000000000004 RSI: 0000000000000000 RDI: ffffffffb3fd6049
[ 1567.700067] RBP: ffff8802467779f8 R08: 0000000000000019 R09: ffff8801d0168000
[ 1567.700067] R10: ffff8801d01680c7 R11: ffffed003a02d019 R12: ffffc9000ed8e000
[ 1567.700067] R13: 0000000000000f40 R14: 0000000000001180 R15: ffffc9000ed8e000
[ 1567.700067] FS:  00007f2a7da3f700(0000) GS:ffff8801d1000000(0000) knlGS:0000000000000000
[ 1567.700067] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 1567.700067] CR2: 0000000000738308 CR3: 000000022e329000 CR4: 00000000000007e0
[ 1567.700067] Stack:
[ 1567.700067]  ffffc9000ed8e000 ffff8801d0168000 ffffc9000ed8e000 ffff8801d0168000
[ 1567.700067]  ffff880246777a28 ffffffffad7c0a21 0000000000001080 ffff880246777c08
[ 1567.700067]  ffff88060d302e68 ffff880246777b58 ffff880246777b88 ffffffffad9a6821
[ 1567.700067] Call Trace:
[ 1567.700067] build_skb (include/linux/mm.h:508 net/core/skbuff.c:316)
[ 1567.700067] netlink_sendmsg (net/netlink/af_netlink.c:1633 net/netlink/af_netlink.c:2329)
[ 1567.774369] ? sched_clock_cpu (kernel/sched/clock.c:311)
[ 1567.774369] ? netlink_unicast (net/netlink/af_netlink.c:2273)
[ 1567.774369] ? netlink_unicast (net/netlink/af_netlink.c:2273)
[ 1567.774369] sock_sendmsg (net/socket.c:614 net/socket.c:623)
[ 1567.774369] sock_write_iter (net/socket.c:823)
[ 1567.774369] ? sock_sendmsg (net/socket.c:806)
[ 1567.774369] __vfs_write (fs/read_write.c:479 fs/read_write.c:491)
[ 1567.774369] ? get_lock_stats (kernel/locking/lockdep.c:249)
[ 1567.774369] ? default_llseek (fs/read_write.c:487)
[ 1567.774369] ? vtime_account_user (kernel/sched/cputime.c:701)
[ 1567.774369] ? rw_verify_area (fs/read_write.c:406 (discriminator 4))
[ 1567.774369] vfs_write (fs/read_write.c:539)
[ 1567.774369] SyS_write (fs/read_write.c:586 fs/read_write.c:577)
[ 1567.774369] ? SyS_read (fs/read_write.c:577)
[ 1567.774369] ? __this_cpu_preempt_check (lib/smp_processor_id.c:63)
[ 1567.774369] ? trace_hardirqs_on_caller (kernel/locking/lockdep.c:2594 kernel/locking/lockdep.c:2636)
[ 1567.774369] ? trace_hardirqs_on_thunk (arch/x86/lib/thunk_64.S:42)
[ 1567.774369] system_call_fastpath (arch/x86/kernel/entry_64.S:261)

Fixes: 79930f5892e ("net: do not deplete pfmemalloc reserve")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h   |  1 +
 net/core/skbuff.c        | 31 ++++++++++++++++++++++---------
 net/netlink/af_netlink.c |  6 ++----
 3 files changed, 25 insertions(+), 13 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index b5c204c..bdccc4b 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -769,6 +769,7 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
 
 struct sk_buff *__alloc_skb(unsigned int size, gfp_t priority, int flags,
 			    int node);
+struct sk_buff *__build_skb(void *data, unsigned int frag_size);
 struct sk_buff *build_skb(void *data, unsigned int frag_size);
 static inline struct sk_buff *alloc_skb(unsigned int size,
 					gfp_t priority)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 9f708d3..7d6861f 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -280,13 +280,14 @@ nodata:
 EXPORT_SYMBOL(__alloc_skb);
 
 /**
- * build_skb - build a network buffer
+ * __build_skb - build a network buffer
  * @data: data buffer provided by caller
- * @frag_size: size of fragment, or 0 if head was kmalloced
+ * @frag_size: size of data, or 0 if head was kmalloced
  *
  * Allocate a new &sk_buff. Caller provides space holding head and
  * skb_shared_info. @data must have been allocated by kmalloc() only if
- * @frag_size is 0, otherwise data should come from the page allocator.
+ * @frag_size is 0, otherwise data should come from the page allocator
+ *  or vmalloc()
  * The return is the new skb buffer.
  * On a failure the return is %NULL, and @data is not freed.
  * Notes :
@@ -297,7 +298,7 @@ EXPORT_SYMBOL(__alloc_skb);
  *  before giving packet to stack.
  *  RX rings only contains data buffers, not full skbs.
  */
-struct sk_buff *build_skb(void *data, unsigned int frag_size)
+struct sk_buff *__build_skb(void *data, unsigned int frag_size)
 {
 	struct skb_shared_info *shinfo;
 	struct sk_buff *skb;
@@ -311,11 +312,6 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
 
 	memset(skb, 0, offsetof(struct sk_buff, tail));
 	skb->truesize = SKB_TRUESIZE(size);
-	if (frag_size) {
-		skb->head_frag = 1;
-		if (virt_to_head_page(data)->pfmemalloc)
-			skb->pfmemalloc = 1;
-	}
 	atomic_set(&skb->users, 1);
 	skb->head = data;
 	skb->data = data;
@@ -332,6 +328,23 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
 
 	return skb;
 }
+
+/* build_skb() is wrapper over __build_skb(), that specifically
+ * takes care of skb->head and skb->pfmemalloc
+ * This means that if @frag_size is not zero, then @data must be backed
+ * by a page fragment, not kmalloc() or vmalloc()
+ */
+struct sk_buff *build_skb(void *data, unsigned int frag_size)
+{
+	struct sk_buff *skb = __build_skb(data, frag_size);
+
+	if (skb && frag_size) {
+		skb->head_frag = 1;
+		if (virt_to_head_page(data)->pfmemalloc)
+			skb->pfmemalloc = 1;
+	}
+	return skb;
+}
 EXPORT_SYMBOL(build_skb);
 
 struct netdev_alloc_cache {
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 05919bf..d1d7a81 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1616,13 +1616,11 @@ static struct sk_buff *netlink_alloc_large_skb(unsigned int size,
 	if (data == NULL)
 		return NULL;
 
-	skb = build_skb(data, size);
+	skb = __build_skb(data, size);
 	if (skb == NULL)
 		vfree(data);
-	else {
-		skb->head_frag = 0;
+	else
 		skb->destructor = netlink_skb_destructor;
-	}
 
 	return skb;
 }
-- 
2.3.5


From 6221373210f38bae1c9bc2a8286611927ba298cc Mon Sep 17 00:00:00 2001
From: Alexey Khoroshilov <khoroshilov@ispras.ru>
Date: Sat, 25 Apr 2015 04:07:03 +0300
Subject: [PATCH 08/10] pxa168: fix double deallocation of managed resources

[ Upstream commit 0e03fd3e335d272bee88fe733d5fd13f5c5b7140 ]

Commit 43d3ddf87a57 ("net: pxa168_eth: add device tree support") starts
to use managed resources by adding devm_clk_get() and
devm_ioremap_resource(), but it leaves explicit iounmap() and clock_put()
in pxa168_eth_remove() and in failure handling code of pxa168_eth_probe().
As a result double free can happen.

The patch removes explicit resource deallocation. Also it converts
clk_disable() to clk_disable_unprepare() to make it symmetrical with
clk_prepare_enable().

Found by Linux Driver Verification project (linuxtesting.org).

Signed-off-by: Alexey Khoroshilov <khoroshilov@ispras.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/pxa168_eth.c | 16 +++++-----------
 1 file changed, 5 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c
index af829c5..7ace07d 100644
--- a/drivers/net/ethernet/marvell/pxa168_eth.c
+++ b/drivers/net/ethernet/marvell/pxa168_eth.c
@@ -1508,7 +1508,8 @@ static int pxa168_eth_probe(struct platform_device *pdev)
 		np = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0);
 		if (!np) {
 			dev_err(&pdev->dev, "missing phy-handle\n");
-			return -EINVAL;
+			err = -EINVAL;
+			goto err_netdev;
 		}
 		of_property_read_u32(np, "reg", &pep->phy_addr);
 		pep->phy_intf = of_get_phy_mode(pdev->dev.of_node);
@@ -1526,7 +1527,7 @@ static int pxa168_eth_probe(struct platform_device *pdev)
 	pep->smi_bus = mdiobus_alloc();
 	if (pep->smi_bus == NULL) {
 		err = -ENOMEM;
-		goto err_base;
+		goto err_netdev;
 	}
 	pep->smi_bus->priv = pep;
 	pep->smi_bus->name = "pxa168_eth smi";
@@ -1551,13 +1552,10 @@ err_mdiobus:
 	mdiobus_unregister(pep->smi_bus);
 err_free_mdio:
 	mdiobus_free(pep->smi_bus);
-err_base:
-	iounmap(pep->base);
 err_netdev:
 	free_netdev(dev);
 err_clk:
-	clk_disable(clk);
-	clk_put(clk);
+	clk_disable_unprepare(clk);
 	return err;
 }
 
@@ -1574,13 +1572,9 @@ static int pxa168_eth_remove(struct platform_device *pdev)
 	if (pep->phy)
 		phy_disconnect(pep->phy);
 	if (pep->clk) {
-		clk_disable(pep->clk);
-		clk_put(pep->clk);
-		pep->clk = NULL;
+		clk_disable_unprepare(pep->clk);
 	}
 
-	iounmap(pep->base);
-	pep->base = NULL;
 	mdiobus_unregister(pep->smi_bus);
 	mdiobus_free(pep->smi_bus);
 	unregister_netdev(dev);
-- 
2.3.5


From 48af260e93a46f24b882856b1dd79d86b275f79d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 25 Apr 2015 09:35:24 -0700
Subject: [PATCH 09/10] net: rfs: fix crash in get_rps_cpus()

[ Upstream commit a31196b07f8034eba6a3487a1ad1bb5ec5cd58a5 ]

Commit 567e4b79731c ("net: rfs: add hash collision detection") had one
mistake :

RPS_NO_CPU is no longer the marker for invalid cpu in set_rps_cpu()
and get_rps_cpu(), as @next_cpu was the result of an AND with
rps_cpu_mask

This bug showed up on a host with 72 cpus :
next_cpu was 0x7f, and the code was trying to access percpu data of an
non existent cpu.

In a follow up patch, we might get rid of compares against nr_cpu_ids,
if we init the tables with 0. This is silly to test for a very unlikely
condition that exists only shortly after table initialization, as
we got rid of rps_reset_sock_flow() and similar functions that were
writing this RPS_NO_CPU magic value at flow dismantle : When table is
old enough, it never contains this value anymore.

Fixes: 567e4b79731c ("net: rfs: add hash collision detection")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Tom Herbert <tom@herbertland.com>
Cc: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/scaling.txt |  2 +-
 net/core/dev.c                       | 12 ++++++------
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/Documentation/networking/scaling.txt b/Documentation/networking/scaling.txt
index 99ca40e..5c204df 100644
--- a/Documentation/networking/scaling.txt
+++ b/Documentation/networking/scaling.txt
@@ -282,7 +282,7 @@ following is true:
 
 - The current CPU's queue head counter >= the recorded tail counter
   value in rps_dev_flow[i]
-- The current CPU is unset (equal to RPS_NO_CPU)
+- The current CPU is unset (>= nr_cpu_ids)
 - The current CPU is offline
 
 After this check, the packet is sent to the (possibly updated) current
diff --git a/net/core/dev.c b/net/core/dev.c
index 45109b7..22a53ac 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3041,7 +3041,7 @@ static struct rps_dev_flow *
 set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 	    struct rps_dev_flow *rflow, u16 next_cpu)
 {
-	if (next_cpu != RPS_NO_CPU) {
+	if (next_cpu < nr_cpu_ids) {
 #ifdef CONFIG_RFS_ACCEL
 		struct netdev_rx_queue *rxqueue;
 		struct rps_dev_flow_table *flow_table;
@@ -3146,7 +3146,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		 * If the desired CPU (where last recvmsg was done) is
 		 * different from current CPU (one in the rx-queue flow
 		 * table entry), switch if one of the following holds:
-		 *   - Current CPU is unset (equal to RPS_NO_CPU).
+		 *   - Current CPU is unset (>= nr_cpu_ids).
 		 *   - Current CPU is offline.
 		 *   - The current CPU's queue tail has advanced beyond the
 		 *     last packet that was enqueued using this table entry.
@@ -3154,14 +3154,14 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		 *     have been dequeued, thus preserving in order delivery.
 		 */
 		if (unlikely(tcpu != next_cpu) &&
-		    (tcpu == RPS_NO_CPU || !cpu_online(tcpu) ||
+		    (tcpu >= nr_cpu_ids || !cpu_online(tcpu) ||
 		     ((int)(per_cpu(softnet_data, tcpu).input_queue_head -
 		      rflow->last_qtail)) >= 0)) {
 			tcpu = next_cpu;
 			rflow = set_rps_cpu(dev, skb, rflow, next_cpu);
 		}
 
-		if (tcpu != RPS_NO_CPU && cpu_online(tcpu)) {
+		if (tcpu < nr_cpu_ids && cpu_online(tcpu)) {
 			*rflowp = rflow;
 			cpu = tcpu;
 			goto done;
@@ -3202,14 +3202,14 @@ bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index,
 	struct rps_dev_flow_table *flow_table;
 	struct rps_dev_flow *rflow;
 	bool expire = true;
-	int cpu;
+	unsigned int cpu;
 
 	rcu_read_lock();
 	flow_table = rcu_dereference(rxqueue->rps_flow_table);
 	if (flow_table && flow_id <= flow_table->mask) {
 		rflow = &flow_table->flows[flow_id];
 		cpu = ACCESS_ONCE(rflow->cpu);
-		if (rflow->filter == filter_id && cpu != RPS_NO_CPU &&
+		if (rflow->filter == filter_id && cpu < nr_cpu_ids &&
 		    ((int)(per_cpu(softnet_data, cpu).input_queue_head -
 			   rflow->last_qtail) <
 		     (int)(10 * flow_table->mask)))
-- 
2.3.5


From 45ebf05754604192a744b64fc5c789c7c49caae1 Mon Sep 17 00:00:00 2001
From: Amir Vadai <amirv@mellanox.com>
Date: Mon, 27 Apr 2015 13:40:56 +0300
Subject: [PATCH 10/10] net/mlx4_en: Prevent setting invalid RSS hash function

[ Upstream commit b37069090b7c5615610a8aa6b36533d67b364d38 ]

mlx4_en_check_rxfh_func() was checking for hardware support before
setting a known RSS hash function, but didn't do any check before
setting unknown RSS hash function. Need to make it fail on such values.
In this occasion, moved the actual setting of the new value from the
check function into mlx4_en_set_rxfh().

Fixes: 947cbb0 ("net/mlx4_en: Support for configurable RSS hash function")
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 29 ++++++++++++++-----------
 1 file changed, 16 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index a7b58ba..3dccf01 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -981,20 +981,21 @@ static int mlx4_en_check_rxfh_func(struct net_device *dev, u8 hfunc)
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 
 	/* check if requested function is supported by the device */
-	if ((hfunc == ETH_RSS_HASH_TOP &&
-	     !(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS_TOP)) ||
-	    (hfunc == ETH_RSS_HASH_XOR &&
-	     !(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS_XOR)))
-		return -EINVAL;
+	if (hfunc == ETH_RSS_HASH_TOP) {
+		if (!(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS_TOP))
+			return -EINVAL;
+		if (!(dev->features & NETIF_F_RXHASH))
+			en_warn(priv, "Toeplitz hash function should be used in conjunction with RX hashing for optimal performance\n");
+		return 0;
+	} else if (hfunc == ETH_RSS_HASH_XOR) {
+		if (!(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS_XOR))
+			return -EINVAL;
+		if (dev->features & NETIF_F_RXHASH)
+			en_warn(priv, "Enabling both XOR Hash function and RX Hashing can limit RPS functionality\n");
+		return 0;
+	}
 
-	priv->rss_hash_fn = hfunc;
-	if (hfunc == ETH_RSS_HASH_TOP && !(dev->features & NETIF_F_RXHASH))
-		en_warn(priv,
-			"Toeplitz hash function should be used in conjunction with RX hashing for optimal performance\n");
-	if (hfunc == ETH_RSS_HASH_XOR && (dev->features & NETIF_F_RXHASH))
-		en_warn(priv,
-			"Enabling both XOR Hash function and RX Hashing can limit RPS functionality\n");
-	return 0;
+	return -EINVAL;
 }
 
 static int mlx4_en_get_rxfh(struct net_device *dev, u32 *ring_index, u8 *key,
@@ -1068,6 +1069,8 @@ static int mlx4_en_set_rxfh(struct net_device *dev, const u32 *ring_index,
 		priv->prof->rss_rings = rss_rings;
 	if (key)
 		memcpy(priv->rss_key, key, MLX4_EN_RSS_KEY_SIZE);
+	if (hfunc !=  ETH_RSS_HASH_NO_CHANGE)
+		priv->rss_hash_fn = hfunc;
 
 	if (port_up) {
 		err = mlx4_en_start_port(dev);
-- 
2.3.5

Re: [PATCHES] Networking

[Greg KH]

On Wed, Apr 29, 2015 at 12:48:05AM -0400, David Miller wrote:
> 
> Please queue up the following networking bug fixes for
> 3.12, 3.14, 3.18, 3.19, and 4.0 -stable, respectively.

I've queued up the 3.14, 3.19, and 4.0 patches, and took a few for 3.10
that looked "safe".

No need to make up 3.19 patches anymore, this is going to be the last
3.19 kernel I release.

thanks again,

greg k-h

Re: [PATCHES] Networking

[David Miller]

From: Greg KH <gregkh@linuxfoundation.org>
Date: Wed, 29 Apr 2015 13:09:50 +0200

> No need to make up 3.19 patches anymore, this is going to be the last
> 3.19 kernel I release.

Ok thanks for the info.

Re: [PATCHES] Networking

[Jiri Slaby]

On 04/29/2015, 06:48 AM, David Miller wrote:
> 
> Please queue up the following networking bug fixes for
> 3.12, 3.14, 3.18, 3.19, and 4.0 -stable, respectively.

Thanks, now applied to 3.12.

-- 
js
suse labs

Re: [PATCHES] Networking

[Ben Hutchings]

[-- Attachment #1: Type: text/plain, Size: 477 bytes --]

On Mon, 2015-04-27 at 11:23 +0200, Jiri Slaby wrote:
> On 04/21/2015, 08:30 PM, David Miller wrote:
> > 
> > Please queue up the following networking bug fixes for 3.12, 3.14, 3.18,
> > 3.19, and 4.0 -stable, respectively.
> 
> FWIW if anyone else wants to put there the missing "commit upstream"
> tags for some patches too, I dug them out:
[...]

Thanks for these.

Ben.

-- 
Ben Hutchings
If you seem to know what you are doing, you'll be given more to do.

[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 811 bytes --]

[PATCHES] NETWORKING

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 284 bytes --]


Greg, I know you said to skip v3.19 going forward, but the ping unhashing crash
fix might justify one more release so I present it here for your consideration.

Please queue up the following networking bug fixes for v3.12, v3.14, v3.18,
v3.19, and v4.0, respectively.

Thanks a lot!

[-- Attachment #2: net_312.mbox --]
[-- Type: Application/Octet-Stream, Size: 1041 bytes --]

From 14eb35f21710598d4cf175a891903176e4e4418f Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 1 May 2015 22:02:47 -0400
Subject: [PATCH] ipv4: Missing sk_nulls_node_init() in ping_unhash().

[ Upstream commit a134f083e79fb4c3d0a925691e732c56911b4326 ]

If we don't do that, then the poison value is left in the ->pprev
backlink.

This can cause crashes if we do a disconnect, followed by a connect().

Tested-by: Linus Torvalds <torvalds@linux-foundation.org>
Reported-by: Wen Xu <hotdog3645@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ping.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index a9f8e66..54012b8 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -154,6 +154,7 @@ void ping_unhash(struct sock *sk)
 	if (sk_hashed(sk)) {
 		write_lock_bh(&ping_table.lock);
 		hlist_nulls_del(&sk->sk_nulls_node);
+		sk_nulls_node_init(&sk->sk_nulls_node);
 		sock_put(sk);
 		isk->inet_num = 0;
 		isk->inet_sport = 0;
-- 
2.3.6


[-- Attachment #3: net_314.mbox --]
[-- Type: Application/Octet-Stream, Size: 1041 bytes --]

From 400d79798a9195fe2eaa2aaad30d22c39a96c6b8 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 1 May 2015 22:02:47 -0400
Subject: [PATCH] ipv4: Missing sk_nulls_node_init() in ping_unhash().

[ Upstream commit a134f083e79fb4c3d0a925691e732c56911b4326 ]

If we don't do that, then the poison value is left in the ->pprev
backlink.

This can cause crashes if we do a disconnect, followed by a connect().

Tested-by: Linus Torvalds <torvalds@linux-foundation.org>
Reported-by: Wen Xu <hotdog3645@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ping.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index b94002a..1e2e9bf 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -158,6 +158,7 @@ void ping_unhash(struct sock *sk)
 	if (sk_hashed(sk)) {
 		write_lock_bh(&ping_table.lock);
 		hlist_nulls_del(&sk->sk_nulls_node);
+		sk_nulls_node_init(&sk->sk_nulls_node);
 		sock_put(sk);
 		isk->inet_num = 0;
 		isk->inet_sport = 0;
-- 
2.3.6


[-- Attachment #4: net_318.mbox --]
[-- Type: Application/Octet-Stream, Size: 7287 bytes --]

From 9fa9427c8df9adc18c2309f6dbddd9d1b72e3e2b Mon Sep 17 00:00:00 2001
From: Benjamin Poirier <bpoirier@suse.de>
Date: Tue, 28 Apr 2015 14:49:29 -0700
Subject: [PATCH 1/3] mlx4: Fix tx ring affinity_mask creation

[ Upstream commit 42eab005a5dd5d7ea2b0328aecc4d6cc0c23c9c2 ]

By default, the number of tx queues is limited by the number of online cpus
in mlx4_en_get_profile(). However, this limit no longer holds after the
ethtool .set_channels method has been called. In that situation, the driver
may access invalid bits of certain cpumask variables when queue_index >=
nr_cpu_ids.

Signed-off-by: Benjamin Poirier <bpoirier@suse.de>
Acked-by: Ido Shamay <idos@mellanox.com>
Fixes: d03a68f ("net/mlx4_en: Configure the XPS queue mapping on driver load")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_tx.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 11ff28b..142ddd5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -137,8 +137,10 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 	ring->hwtstamp_tx_type = priv->hwtstamp_config.tx_type;
 	ring->queue_index = queue_index;
 
-	if (queue_index < priv->num_tx_rings_p_up && cpu_online(queue_index))
-		cpumask_set_cpu(queue_index, &ring->affinity_mask);
+	if (queue_index < priv->num_tx_rings_p_up)
+		cpumask_set_cpu_local_first(queue_index,
+					    priv->mdev->dev->numa_node,
+					    &ring->affinity_mask);
 
 	*pring = ring;
 	return 0;
@@ -205,7 +207,7 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv,
 
 	err = mlx4_qp_to_ready(mdev->dev, &ring->wqres.mtt, &ring->context,
 			       &ring->qp, &ring->qp_state);
-	if (!user_prio && cpu_online(ring->queue_index))
+	if (!cpumask_empty(&ring->affinity_mask))
 		netif_set_xps_queue(priv->dev, &ring->affinity_mask,
 				    ring->queue_index);
 
-- 
2.3.6


From 4453fc4d25f67142879acdcad553f3e52413bdf7 Mon Sep 17 00:00:00 2001
From: Ido Shamay <idos@mellanox.com>
Date: Thu, 30 Apr 2015 17:32:46 +0300
Subject: [PATCH 2/3] net/mlx4_en: Schedule napi when RX buffers allocation
 fails

[ Upstream commit 07841f9d94c11afe00c0498cf242edf4075729f4 ]

When system is out of memory, refilling of RX buffers fails while
the driver continue to pass the received packets to the kernel stack.
At some point, when all RX buffers deplete, driver may fall into a
sleep, and not recover when memory for new RX buffers is once again
availible. This is because hardware does not have valid descriptors,
so no interrupt will be generated for the driver to return to work
in napi context. Fix it by schedule the napi poll function from
stats_task delayed workqueue, as long as the allocations fail.

Signed-off-by: Ido Shamay <idos@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c |  1 +
 drivers/net/ethernet/mellanox/mlx4/en_rx.c     | 26 ++++++++++++++++++++++++--
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h   |  1 +
 3 files changed, 26 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 6bdaa31..79ff615 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1466,6 +1466,7 @@ static void mlx4_en_service_task(struct work_struct *work)
 		if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS)
 			mlx4_en_ptp_overflow_check(mdev);
 
+		mlx4_en_recover_from_oom(priv);
 		queue_delayed_work(mdev->workqueue, &priv->service_task,
 				   SERVICE_TASK_DELAY);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 01660c5..5bbb59d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -237,6 +237,12 @@ static int mlx4_en_prepare_rx_desc(struct mlx4_en_priv *priv,
 	return mlx4_en_alloc_frags(priv, rx_desc, frags, ring->page_alloc, gfp);
 }
 
+static inline bool mlx4_en_is_ring_empty(struct mlx4_en_rx_ring *ring)
+{
+	BUG_ON((u32)(ring->prod - ring->cons) > ring->actual_size);
+	return ring->prod == ring->cons;
+}
+
 static inline void mlx4_en_update_rx_prod_db(struct mlx4_en_rx_ring *ring)
 {
 	*ring->wqres.db.db = cpu_to_be32(ring->prod & 0xffff);
@@ -308,8 +314,7 @@ static void mlx4_en_free_rx_buf(struct mlx4_en_priv *priv,
 	       ring->cons, ring->prod);
 
 	/* Unmap and free Rx buffers */
-	BUG_ON((u32) (ring->prod - ring->cons) > ring->actual_size);
-	while (ring->cons != ring->prod) {
+	while (!mlx4_en_is_ring_empty(ring)) {
 		index = ring->cons & ring->size_mask;
 		en_dbg(DRV, priv, "Processing descriptor:%d\n", index);
 		mlx4_en_free_rx_desc(priv, ring, index);
@@ -484,6 +489,23 @@ err_allocator:
 	return err;
 }
 
+/* We recover from out of memory by scheduling our napi poll
+ * function (mlx4_en_process_cq), which tries to allocate
+ * all missing RX buffers (call to mlx4_en_refill_rx_buffers).
+ */
+void mlx4_en_recover_from_oom(struct mlx4_en_priv *priv)
+{
+	int ring;
+
+	if (!priv->port_up)
+		return;
+
+	for (ring = 0; ring < priv->rx_ring_num; ring++) {
+		if (mlx4_en_is_ring_empty(priv->rx_ring[ring]))
+			napi_reschedule(&priv->rx_cq[ring]->napi);
+	}
+}
+
 void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv,
 			     struct mlx4_en_rx_ring **pring,
 			     u32 size, u16 stride)
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 8fef658..692bd4e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -779,6 +779,7 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv,
 void mlx4_en_deactivate_tx_ring(struct mlx4_en_priv *priv,
 				struct mlx4_en_tx_ring *ring);
 void mlx4_en_set_num_rx_rings(struct mlx4_en_dev *mdev);
+void mlx4_en_recover_from_oom(struct mlx4_en_priv *priv);
 int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
 			   struct mlx4_en_rx_ring **pring,
 			   u32 size, u16 stride, int node);
-- 
2.3.6


From b0b94b20aa3874bc5acdcb2ebbcbf3c054927d82 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 1 May 2015 22:02:47 -0400
Subject: [PATCH 3/3] ipv4: Missing sk_nulls_node_init() in ping_unhash().

[ Upstream commit a134f083e79fb4c3d0a925691e732c56911b4326 ]

If we don't do that, then the poison value is left in the ->pprev
backlink.

This can cause crashes if we do a disconnect, followed by a connect().

Tested-by: Linus Torvalds <torvalds@linux-foundation.org>
Reported-by: Wen Xu <hotdog3645@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ping.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index a5c49d6..64f4edb 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -158,6 +158,7 @@ void ping_unhash(struct sock *sk)
 	if (sk_hashed(sk)) {
 		write_lock_bh(&ping_table.lock);
 		hlist_nulls_del(&sk->sk_nulls_node);
+		sk_nulls_node_init(&sk->sk_nulls_node);
 		sock_put(sk);
 		isk->inet_num = 0;
 		isk->inet_sport = 0;
-- 
2.3.6


[-- Attachment #5: net_319.mbox --]
[-- Type: Application/Octet-Stream, Size: 11950 bytes --]

From deb9a92eaa4e82179e11e3e3fa94b0c5bbd645f4 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@plumgrid.com>
Date: Mon, 27 Apr 2015 14:40:37 -0700
Subject: [PATCH 1/6] bpf: fix 64-bit divide

[ Upstream commit 876a7ae65b86d8cec8efe7d15d050ac61116874e ]

ALU64_DIV instruction should be dividing 64-bit by 64-bit,
whereas do_div() does 64-bit by 32-bit divide.
x64 and arm64 JITs correctly implement 64 by 64 unsigned divide.
llvm BPF backend emits code assuming that ALU64_DIV does 64 by 64.

Fixes: 89aa075832b0 ("net: sock: allow eBPF programs to be attached to sockets")
Reported-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/core.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index a64e7a2..0c5796e 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -357,8 +357,8 @@ select_insn:
 	ALU64_MOD_X:
 		if (unlikely(SRC == 0))
 			return 0;
-		tmp = DST;
-		DST = do_div(tmp, SRC);
+		div64_u64_rem(DST, SRC, &tmp);
+		DST = tmp;
 		CONT;
 	ALU_MOD_X:
 		if (unlikely(SRC == 0))
@@ -367,8 +367,8 @@ select_insn:
 		DST = do_div(tmp, (u32) SRC);
 		CONT;
 	ALU64_MOD_K:
-		tmp = DST;
-		DST = do_div(tmp, IMM);
+		div64_u64_rem(DST, IMM, &tmp);
+		DST = tmp;
 		CONT;
 	ALU_MOD_K:
 		tmp = (u32) DST;
@@ -377,7 +377,7 @@ select_insn:
 	ALU64_DIV_X:
 		if (unlikely(SRC == 0))
 			return 0;
-		do_div(DST, SRC);
+		DST = div64_u64(DST, SRC);
 		CONT;
 	ALU_DIV_X:
 		if (unlikely(SRC == 0))
@@ -387,7 +387,7 @@ select_insn:
 		DST = (u32) tmp;
 		CONT;
 	ALU64_DIV_K:
-		do_div(DST, IMM);
+		DST = div64_u64(DST, IMM);
 		CONT;
 	ALU_DIV_K:
 		tmp = (u32) DST;
-- 
2.3.6


From 97e52bb4147ccc3d61e3f576aa3d1e2450e61983 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Tue, 28 Apr 2015 11:43:15 +0800
Subject: [PATCH 2/6] route: Use ipv4_mtu instead of raw rt_pmtu

[ Upstream commit cb6ccf09d6b94bec4def1ac5cf4678d12b216474 ]

The commit 3cdaa5be9e81a914e633a6be7b7d2ef75b528562 ("ipv4: Don't
increase PMTU with Datagram Too Big message") broke PMTU in cases
where the rt_pmtu value has expired but is smaller than the new
PMTU value.

This obsolete rt_pmtu then prevents the new PMTU value from being
installed.

Fixes: 3cdaa5be9e81 ("ipv4: Don't increase PMTU with Datagram Too Big message")
Reported-by: Gerd v. Egidy <gerd.von.egidy@intra2net.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 52e1f2b..ac40410 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -963,10 +963,7 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
 	if (dst_metric_locked(dst, RTAX_MTU))
 		return;
 
-	if (dst->dev->mtu < mtu)
-		return;
-
-	if (rt->rt_pmtu && rt->rt_pmtu < mtu)
+	if (ipv4_mtu(dst) < mtu)
 		return;
 
 	if (mtu < ip_rt_min_pmtu)
-- 
2.3.6


From 1b0a725a019cc6b40c107587a78524aed98f6cae Mon Sep 17 00:00:00 2001
From: Benjamin Poirier <bpoirier@suse.de>
Date: Tue, 28 Apr 2015 14:49:29 -0700
Subject: [PATCH 3/6] mlx4: Fix tx ring affinity_mask creation

[ Upstream commit 42eab005a5dd5d7ea2b0328aecc4d6cc0c23c9c2 ]

By default, the number of tx queues is limited by the number of online cpus
in mlx4_en_get_profile(). However, this limit no longer holds after the
ethtool .set_channels method has been called. In that situation, the driver
may access invalid bits of certain cpumask variables when queue_index >=
nr_cpu_ids.

Signed-off-by: Benjamin Poirier <bpoirier@suse.de>
Acked-by: Ido Shamay <idos@mellanox.com>
Fixes: d03a68f ("net/mlx4_en: Configure the XPS queue mapping on driver load")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_tx.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index e3357bf..18db895 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -143,8 +143,10 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 	ring->hwtstamp_tx_type = priv->hwtstamp_config.tx_type;
 	ring->queue_index = queue_index;
 
-	if (queue_index < priv->num_tx_rings_p_up && cpu_online(queue_index))
-		cpumask_set_cpu(queue_index, &ring->affinity_mask);
+	if (queue_index < priv->num_tx_rings_p_up)
+		cpumask_set_cpu_local_first(queue_index,
+					    priv->mdev->dev->numa_node,
+					    &ring->affinity_mask);
 
 	*pring = ring;
 	return 0;
@@ -213,7 +215,7 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv,
 
 	err = mlx4_qp_to_ready(mdev->dev, &ring->wqres.mtt, &ring->context,
 			       &ring->qp, &ring->qp_state);
-	if (!user_prio && cpu_online(ring->queue_index))
+	if (!cpumask_empty(&ring->affinity_mask))
 		netif_set_xps_queue(priv->dev, &ring->affinity_mask,
 				    ring->queue_index);
 
-- 
2.3.6


From 4bc3da9e830e0da5be1e7ad9c983f5640df28617 Mon Sep 17 00:00:00 2001
From: Hariprasad Shenai <hariprasad@chelsio.com>
Date: Wed, 29 Apr 2015 17:19:05 +0530
Subject: [PATCH 4/6] cxgb4: Fix MC1 memory offset calculation

[ Upstream commit 7f0b8a56c978b0a3315ac84c6cbb065413afb8e9 ]

Commit 6559a7e8296002b4 ("cxgb4: Cleanup macros so they follow the same
style and look consistent") introduced a regression where reading MC1
memory in adapters where MC0 isn't present or MC0 size is not equal to MC1
size caused the adapter to crash due to incorrect computation of memoffset.
Fix is to read the size of MC0 instead of MC1 for offset calculation

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/t4_hw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index c132d90..0589a84 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -489,7 +489,7 @@ int t4_memory_rw(struct adapter *adap, int win, int mtype, u32 addr,
 		memoffset = (mtype * (edc_size * 1024 * 1024));
 	else {
 		mc_size = EXT_MEM0_SIZE_G(t4_read_reg(adap,
-						      MA_EXT_MEMORY1_BAR_A));
+						      MA_EXT_MEMORY0_BAR_A));
 		memoffset = (MEM_MC0 * edc_size + mc_size) * 1024 * 1024;
 	}
 
-- 
2.3.6


From 480d0a96e7c14b5a09e93cb321b0a4a661eed14a Mon Sep 17 00:00:00 2001
From: Ido Shamay <idos@mellanox.com>
Date: Thu, 30 Apr 2015 17:32:46 +0300
Subject: [PATCH 5/6] net/mlx4_en: Schedule napi when RX buffers allocation
 fails

[ Upstream commit 07841f9d94c11afe00c0498cf242edf4075729f4 ]

When system is out of memory, refilling of RX buffers fails while
the driver continue to pass the received packets to the kernel stack.
At some point, when all RX buffers deplete, driver may fall into a
sleep, and not recover when memory for new RX buffers is once again
availible. This is because hardware does not have valid descriptors,
so no interrupt will be generated for the driver to return to work
in napi context. Fix it by schedule the napi poll function from
stats_task delayed workqueue, as long as the allocations fail.

Signed-off-by: Ido Shamay <idos@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c |  1 +
 drivers/net/ethernet/mellanox/mlx4/en_rx.c     | 26 ++++++++++++++++++++++++--
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h   |  1 +
 3 files changed, 26 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 2617c9d..c998c4d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1467,6 +1467,7 @@ static void mlx4_en_service_task(struct work_struct *work)
 		if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS)
 			mlx4_en_ptp_overflow_check(mdev);
 
+		mlx4_en_recover_from_oom(priv);
 		queue_delayed_work(mdev->workqueue, &priv->service_task,
 				   SERVICE_TASK_DELAY);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index a0474eb..10d3533 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -240,6 +240,12 @@ static int mlx4_en_prepare_rx_desc(struct mlx4_en_priv *priv,
 	return mlx4_en_alloc_frags(priv, rx_desc, frags, ring->page_alloc, gfp);
 }
 
+static inline bool mlx4_en_is_ring_empty(struct mlx4_en_rx_ring *ring)
+{
+	BUG_ON((u32)(ring->prod - ring->cons) > ring->actual_size);
+	return ring->prod == ring->cons;
+}
+
 static inline void mlx4_en_update_rx_prod_db(struct mlx4_en_rx_ring *ring)
 {
 	*ring->wqres.db.db = cpu_to_be32(ring->prod & 0xffff);
@@ -311,8 +317,7 @@ static void mlx4_en_free_rx_buf(struct mlx4_en_priv *priv,
 	       ring->cons, ring->prod);
 
 	/* Unmap and free Rx buffers */
-	BUG_ON((u32) (ring->prod - ring->cons) > ring->actual_size);
-	while (ring->cons != ring->prod) {
+	while (!mlx4_en_is_ring_empty(ring)) {
 		index = ring->cons & ring->size_mask;
 		en_dbg(DRV, priv, "Processing descriptor:%d\n", index);
 		mlx4_en_free_rx_desc(priv, ring, index);
@@ -487,6 +492,23 @@ err_allocator:
 	return err;
 }
 
+/* We recover from out of memory by scheduling our napi poll
+ * function (mlx4_en_process_cq), which tries to allocate
+ * all missing RX buffers (call to mlx4_en_refill_rx_buffers).
+ */
+void mlx4_en_recover_from_oom(struct mlx4_en_priv *priv)
+{
+	int ring;
+
+	if (!priv->port_up)
+		return;
+
+	for (ring = 0; ring < priv->rx_ring_num; ring++) {
+		if (mlx4_en_is_ring_empty(priv->rx_ring[ring]))
+			napi_reschedule(&priv->rx_cq[ring]->napi);
+	}
+}
+
 void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv,
 			     struct mlx4_en_rx_ring **pring,
 			     u32 size, u16 stride)
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 8805ef1..6cc49c1 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -788,6 +788,7 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv,
 void mlx4_en_deactivate_tx_ring(struct mlx4_en_priv *priv,
 				struct mlx4_en_tx_ring *ring);
 void mlx4_en_set_num_rx_rings(struct mlx4_en_dev *mdev);
+void mlx4_en_recover_from_oom(struct mlx4_en_priv *priv);
 int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
 			   struct mlx4_en_rx_ring **pring,
 			   u32 size, u16 stride, int node);
-- 
2.3.6


From bf2bb2f8dc65fcc753c05ac00c790dcb20a32692 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 1 May 2015 22:02:47 -0400
Subject: [PATCH 6/6] ipv4: Missing sk_nulls_node_init() in ping_unhash().

[ Upstream commit a134f083e79fb4c3d0a925691e732c56911b4326 ]

If we don't do that, then the poison value is left in the ->pprev
backlink.

This can cause crashes if we do a disconnect, followed by a connect().

Tested-by: Linus Torvalds <torvalds@linux-foundation.org>
Reported-by: Wen Xu <hotdog3645@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ping.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 0ae28f5..c0db43d 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -158,6 +158,7 @@ void ping_unhash(struct sock *sk)
 	if (sk_hashed(sk)) {
 		write_lock_bh(&ping_table.lock);
 		hlist_nulls_del(&sk->sk_nulls_node);
+		sk_nulls_node_init(&sk->sk_nulls_node);
 		sock_put(sk);
 		isk->inet_num = 0;
 		isk->inet_sport = 0;
-- 
2.3.6


[-- Attachment #6: net_40.mbox --]
[-- Type: Application/Octet-Stream, Size: 11950 bytes --]

From fe9b90d102b31c241b5b5f33d01830341833deac Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@plumgrid.com>
Date: Mon, 27 Apr 2015 14:40:37 -0700
Subject: [PATCH 1/6] bpf: fix 64-bit divide

[ Upstream commit 876a7ae65b86d8cec8efe7d15d050ac61116874e ]

ALU64_DIV instruction should be dividing 64-bit by 64-bit,
whereas do_div() does 64-bit by 32-bit divide.
x64 and arm64 JITs correctly implement 64 by 64 unsigned divide.
llvm BPF backend emits code assuming that ALU64_DIV does 64 by 64.

Fixes: 89aa075832b0 ("net: sock: allow eBPF programs to be attached to sockets")
Reported-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/core.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index a64e7a2..0c5796e 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -357,8 +357,8 @@ select_insn:
 	ALU64_MOD_X:
 		if (unlikely(SRC == 0))
 			return 0;
-		tmp = DST;
-		DST = do_div(tmp, SRC);
+		div64_u64_rem(DST, SRC, &tmp);
+		DST = tmp;
 		CONT;
 	ALU_MOD_X:
 		if (unlikely(SRC == 0))
@@ -367,8 +367,8 @@ select_insn:
 		DST = do_div(tmp, (u32) SRC);
 		CONT;
 	ALU64_MOD_K:
-		tmp = DST;
-		DST = do_div(tmp, IMM);
+		div64_u64_rem(DST, IMM, &tmp);
+		DST = tmp;
 		CONT;
 	ALU_MOD_K:
 		tmp = (u32) DST;
@@ -377,7 +377,7 @@ select_insn:
 	ALU64_DIV_X:
 		if (unlikely(SRC == 0))
 			return 0;
-		do_div(DST, SRC);
+		DST = div64_u64(DST, SRC);
 		CONT;
 	ALU_DIV_X:
 		if (unlikely(SRC == 0))
@@ -387,7 +387,7 @@ select_insn:
 		DST = (u32) tmp;
 		CONT;
 	ALU64_DIV_K:
-		do_div(DST, IMM);
+		DST = div64_u64(DST, IMM);
 		CONT;
 	ALU_DIV_K:
 		tmp = (u32) DST;
-- 
2.3.6


From 168f84b44776a2dfbb3c7a44efc5bbe94bd9e2da Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Tue, 28 Apr 2015 11:43:15 +0800
Subject: [PATCH 2/6] route: Use ipv4_mtu instead of raw rt_pmtu

[ Upstream commit cb6ccf09d6b94bec4def1ac5cf4678d12b216474 ]

The commit 3cdaa5be9e81a914e633a6be7b7d2ef75b528562 ("ipv4: Don't
increase PMTU with Datagram Too Big message") broke PMTU in cases
where the rt_pmtu value has expired but is smaller than the new
PMTU value.

This obsolete rt_pmtu then prevents the new PMTU value from being
installed.

Fixes: 3cdaa5be9e81 ("ipv4: Don't increase PMTU with Datagram Too Big message")
Reported-by: Gerd v. Egidy <gerd.von.egidy@intra2net.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index ad50643..20fc020 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -963,10 +963,7 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
 	if (dst_metric_locked(dst, RTAX_MTU))
 		return;
 
-	if (dst->dev->mtu < mtu)
-		return;
-
-	if (rt->rt_pmtu && rt->rt_pmtu < mtu)
+	if (ipv4_mtu(dst) < mtu)
 		return;
 
 	if (mtu < ip_rt_min_pmtu)
-- 
2.3.6


From 52417f04873e1b501c4a00cdc450e11ceadb27d5 Mon Sep 17 00:00:00 2001
From: Benjamin Poirier <bpoirier@suse.de>
Date: Tue, 28 Apr 2015 14:49:29 -0700
Subject: [PATCH 3/6] mlx4: Fix tx ring affinity_mask creation

[ Upstream commit 42eab005a5dd5d7ea2b0328aecc4d6cc0c23c9c2 ]

By default, the number of tx queues is limited by the number of online cpus
in mlx4_en_get_profile(). However, this limit no longer holds after the
ethtool .set_channels method has been called. In that situation, the driver
may access invalid bits of certain cpumask variables when queue_index >=
nr_cpu_ids.

Signed-off-by: Benjamin Poirier <bpoirier@suse.de>
Acked-by: Ido Shamay <idos@mellanox.com>
Fixes: d03a68f ("net/mlx4_en: Configure the XPS queue mapping on driver load")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_tx.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 55f9f5c..8c234ec 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -143,8 +143,10 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 	ring->hwtstamp_tx_type = priv->hwtstamp_config.tx_type;
 	ring->queue_index = queue_index;
 
-	if (queue_index < priv->num_tx_rings_p_up && cpu_online(queue_index))
-		cpumask_set_cpu(queue_index, &ring->affinity_mask);
+	if (queue_index < priv->num_tx_rings_p_up)
+		cpumask_set_cpu_local_first(queue_index,
+					    priv->mdev->dev->numa_node,
+					    &ring->affinity_mask);
 
 	*pring = ring;
 	return 0;
@@ -213,7 +215,7 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv,
 
 	err = mlx4_qp_to_ready(mdev->dev, &ring->wqres.mtt, &ring->context,
 			       &ring->qp, &ring->qp_state);
-	if (!user_prio && cpu_online(ring->queue_index))
+	if (!cpumask_empty(&ring->affinity_mask))
 		netif_set_xps_queue(priv->dev, &ring->affinity_mask,
 				    ring->queue_index);
 
-- 
2.3.6


From 79a96953ea03d9b2e247b0e192f62389131f2105 Mon Sep 17 00:00:00 2001
From: Hariprasad Shenai <hariprasad@chelsio.com>
Date: Wed, 29 Apr 2015 17:19:05 +0530
Subject: [PATCH 4/6] cxgb4: Fix MC1 memory offset calculation

[ Upstream commit 7f0b8a56c978b0a3315ac84c6cbb065413afb8e9 ]

Commit 6559a7e8296002b4 ("cxgb4: Cleanup macros so they follow the same
style and look consistent") introduced a regression where reading MC1
memory in adapters where MC0 isn't present or MC0 size is not equal to MC1
size caused the adapter to crash due to incorrect computation of memoffset.
Fix is to read the size of MC0 instead of MC1 for offset calculation

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/t4_hw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index ee394dc..ec1ea8b 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -492,7 +492,7 @@ int t4_memory_rw(struct adapter *adap, int win, int mtype, u32 addr,
 		memoffset = (mtype * (edc_size * 1024 * 1024));
 	else {
 		mc_size = EXT_MEM0_SIZE_G(t4_read_reg(adap,
-						      MA_EXT_MEMORY1_BAR_A));
+						      MA_EXT_MEMORY0_BAR_A));
 		memoffset = (MEM_MC0 * edc_size + mc_size) * 1024 * 1024;
 	}
 
-- 
2.3.6


From f0be2a4fa5dd797db99326a526d5ad382a4811a0 Mon Sep 17 00:00:00 2001
From: Ido Shamay <idos@mellanox.com>
Date: Thu, 30 Apr 2015 17:32:46 +0300
Subject: [PATCH 5/6] net/mlx4_en: Schedule napi when RX buffers allocation
 fails

[ Upstream commit 07841f9d94c11afe00c0498cf242edf4075729f4 ]

When system is out of memory, refilling of RX buffers fails while
the driver continue to pass the received packets to the kernel stack.
At some point, when all RX buffers deplete, driver may fall into a
sleep, and not recover when memory for new RX buffers is once again
availible. This is because hardware does not have valid descriptors,
so no interrupt will be generated for the driver to return to work
in napi context. Fix it by schedule the napi poll function from
stats_task delayed workqueue, as long as the allocations fail.

Signed-off-by: Ido Shamay <idos@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c |  1 +
 drivers/net/ethernet/mellanox/mlx4/en_rx.c     | 26 ++++++++++++++++++++++++--
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h   |  1 +
 3 files changed, 26 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 3485acf..2f1324b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1467,6 +1467,7 @@ static void mlx4_en_service_task(struct work_struct *work)
 		if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS)
 			mlx4_en_ptp_overflow_check(mdev);
 
+		mlx4_en_recover_from_oom(priv);
 		queue_delayed_work(mdev->workqueue, &priv->service_task,
 				   SERVICE_TASK_DELAY);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 698d60d..05ec5e1 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -244,6 +244,12 @@ static int mlx4_en_prepare_rx_desc(struct mlx4_en_priv *priv,
 	return mlx4_en_alloc_frags(priv, rx_desc, frags, ring->page_alloc, gfp);
 }
 
+static inline bool mlx4_en_is_ring_empty(struct mlx4_en_rx_ring *ring)
+{
+	BUG_ON((u32)(ring->prod - ring->cons) > ring->actual_size);
+	return ring->prod == ring->cons;
+}
+
 static inline void mlx4_en_update_rx_prod_db(struct mlx4_en_rx_ring *ring)
 {
 	*ring->wqres.db.db = cpu_to_be32(ring->prod & 0xffff);
@@ -315,8 +321,7 @@ static void mlx4_en_free_rx_buf(struct mlx4_en_priv *priv,
 	       ring->cons, ring->prod);
 
 	/* Unmap and free Rx buffers */
-	BUG_ON((u32) (ring->prod - ring->cons) > ring->actual_size);
-	while (ring->cons != ring->prod) {
+	while (!mlx4_en_is_ring_empty(ring)) {
 		index = ring->cons & ring->size_mask;
 		en_dbg(DRV, priv, "Processing descriptor:%d\n", index);
 		mlx4_en_free_rx_desc(priv, ring, index);
@@ -491,6 +496,23 @@ err_allocator:
 	return err;
 }
 
+/* We recover from out of memory by scheduling our napi poll
+ * function (mlx4_en_process_cq), which tries to allocate
+ * all missing RX buffers (call to mlx4_en_refill_rx_buffers).
+ */
+void mlx4_en_recover_from_oom(struct mlx4_en_priv *priv)
+{
+	int ring;
+
+	if (!priv->port_up)
+		return;
+
+	for (ring = 0; ring < priv->rx_ring_num; ring++) {
+		if (mlx4_en_is_ring_empty(priv->rx_ring[ring]))
+			napi_reschedule(&priv->rx_cq[ring]->napi);
+	}
+}
+
 void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv,
 			     struct mlx4_en_rx_ring **pring,
 			     u32 size, u16 stride)
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index ebbe244..8687c8d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -790,6 +790,7 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv,
 void mlx4_en_deactivate_tx_ring(struct mlx4_en_priv *priv,
 				struct mlx4_en_tx_ring *ring);
 void mlx4_en_set_num_rx_rings(struct mlx4_en_dev *mdev);
+void mlx4_en_recover_from_oom(struct mlx4_en_priv *priv);
 int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
 			   struct mlx4_en_rx_ring **pring,
 			   u32 size, u16 stride, int node);
-- 
2.3.6


From e40c618ec2293230c9004a47c66b23d89254f1eb Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 1 May 2015 22:02:47 -0400
Subject: [PATCH 6/6] ipv4: Missing sk_nulls_node_init() in ping_unhash().

[ Upstream commit a134f083e79fb4c3d0a925691e732c56911b4326 ]

If we don't do that, then the poison value is left in the ->pprev
backlink.

This can cause crashes if we do a disconnect, followed by a connect().

Tested-by: Linus Torvalds <torvalds@linux-foundation.org>
Reported-by: Wen Xu <hotdog3645@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ping.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 208d543..787b0d6 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -158,6 +158,7 @@ void ping_unhash(struct sock *sk)
 	if (sk_hashed(sk)) {
 		write_lock_bh(&ping_table.lock);
 		hlist_nulls_del(&sk->sk_nulls_node);
+		sk_nulls_node_init(&sk->sk_nulls_node);
 		sock_put(sk);
 		isk->inet_num = 0;
 		isk->inet_sport = 0;
-- 
2.3.6

Re: [PATCHES] NETWORKING

[Jiri Slaby]

On 05/05/2015, 07:34 PM, David Miller wrote:
> Please queue up the following networking bug fixes for v3.12, v3.14, v3.18,
> v3.19, and v4.0, respectively.

Thanks, now applied to 3.12.

-- 
js
suse labs

Re: [PATCHES] NETWORKING

[Greg KH]

On Tue, May 05, 2015 at 01:34:00PM -0400, David Miller wrote:
> 
> Greg, I know you said to skip v3.19 going forward, but the ping unhashing crash
> fix might justify one more release so I present it here for your consideration.

Thanks, I've included the 3.19 patches in a last release now.

greg k-h

Re: [PATCHES] NETWORKING

[Greg KH]

On Tue, May 05, 2015 at 01:34:00PM -0400, David Miller wrote:
> 
> Greg, I know you said to skip v3.19 going forward, but the ping unhashing crash
> fix might justify one more release so I present it here for your consideration.
> 
> Please queue up the following networking bug fixes for v3.12, v3.14, v3.18,
> v3.19, and v4.0, respectively.

Applied to the trees I care about.  No need to do 3.19 patches anymore,
this really is going to be the last one I release for that branch :)

thanks,

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 128 bytes --]


Please queue up the following networking bug fixes for 3.12.x, 3.14.x,
3.18.x, and 4.0.x -stable, respectively.

Thanks a lot!

[-- Attachment #2: net_312.mbox --]
[-- Type: Application/Octet-Stream, Size: 20361 bytes --]

From b962a9bda8d62f055bd09afa70c0747b604c157f Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@plumgrid.com>
Date: Fri, 22 May 2015 15:42:55 -0700
Subject: [PATCH 1/8] x86: bpf_jit: fix compilation of large bpf programs

[ Upstream commit 3f7352bf21f8fd7ba3e2fcef9488756f188e12be ]

x86 has variable length encoding. x86 JIT compiler is trying
to pick the shortest encoding for given bpf instruction.
While doing so the jump targets are changing, so JIT is doing
multiple passes over the program. Typical program needs 3 passes.
Some very short programs converge with 2 passes. Large programs
may need 4 or 5. But specially crafted bpf programs may hit the
pass limit and if the program converges on the last iteration
the JIT compiler will be producing an image full of 'int 3' insns.
Fix this corner case by doing final iteration over bpf program.

Fixes: 0a14842f5a3c ("net: filter: Just In Time compiler for x86-64")
Reported-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Tested-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/x86/net/bpf_jit_comp.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 4ed75dd..1b72000 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -211,7 +211,12 @@ void bpf_jit_compile(struct sk_filter *fp)
 	}
 	cleanup_addr = proglen; /* epilogue address */
 
-	for (pass = 0; pass < 10; pass++) {
+	/* JITed image shrinks with every pass and the loop iterates
+	 * until the image stops shrinking. Very large bpf programs
+	 * may converge on the last pass. In such case do one more
+	 * pass to emit the final image
+	 */
+	for (pass = 0; pass < 10 || image; pass++) {
 		u8 seen_or_pass0 = (pass == 0) ? (SEEN_XREG | SEEN_DATAREF | SEEN_MEM) : seen;
 		/* no prologue/epilogue for trivial filters (RET something) */
 		proglen = 0;
-- 
2.1.0


From 4dda89ff42c0c6d98a893caa412dce9d73deb9ae Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 22 May 2015 04:58:12 -0500
Subject: [PATCH 2/8] ipv4: Avoid crashing in ip_error

[ Upstream commit 381c759d9916c42959515ad34a6d467e24a88e93 ]

ip_error does not check if in_dev is NULL before dereferencing it.

IThe following sequence of calls is possible:
CPU A                          CPU B
ip_rcv_finish
    ip_route_input_noref()
        ip_route_input_slow()
                               inetdev_destroy()
    dst_input()

With the result that a network device can be destroyed while processing
an input packet.

A crash was triggered with only unicast packets in flight, and
forwarding enabled on the only network device.   The error condition
was created by the removal of the network device.

As such it is likely the that error code was -EHOSTUNREACH, and the
action taken by ip_error (if in_dev had been accessible) would have
been to not increment any counters and to have tried and likely failed
to send an icmp error as the network device is going away.

Therefore handle this weird case by just dropping the packet if
!in_dev.  It will result in dropping the packet sooner, and will not
result in an actual change of behavior.

Fixes: 251da4130115b ("ipv4: Cache ip_error() routes even when not forwarding.")
Reported-by: Vittorio Gambaletta <linuxbugs@vittgam.net>
Tested-by: Vittorio Gambaletta <linuxbugs@vittgam.net>
Signed-off-by: Vittorio Gambaletta <linuxbugs@vittgam.net>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 3663200..bd5f346 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -921,6 +921,10 @@ static int ip_error(struct sk_buff *skb)
 	bool send;
 	int code;
 
+	/* IP on this device is disabled. */
+	if (!in_dev)
+		goto out;
+
 	net = dev_net(rt->dst.dev);
 	if (!IN_DEV_FORWARD(in_dev)) {
 		switch (rt->dst.error) {
-- 
2.1.0


From 6d5361ce0c0980d93298d44ed7916bbe9e6953b5 Mon Sep 17 00:00:00 2001
From: Thadeu Lima de Souza Cascardo <cascardo@redhat.com>
Date: Fri, 22 May 2015 12:18:59 -0300
Subject: [PATCH 3/8] bridge: fix parsing of MLDv2 reports

[ Upstream commit 47cc84ce0c2fe75c99ea5963c4b5704dd78ead54 ]

When more than a multicast address is present in a MLDv2 report, all but
the first address is ignored, because the code breaks out of the loop if
there has not been an error adding that address.

This has caused failures when two guests connected through the bridge
tried to communicate using IPv6. Neighbor discoveries would not be
transmitted to the other guest when both used a link-local address and a
static address.

This only happens when there is a MLDv2 querier in the network.

The fix will only break out of the loop when there is a failure adding a
multicast address.

The mdb before the patch:

dev ovirtmgmt port vnet0 grp ff02::1:ff7d:6603 temp
dev ovirtmgmt port vnet1 grp ff02::1:ff7d:6604 temp
dev ovirtmgmt port bond0.86 grp ff02::2 temp

After the patch:

dev ovirtmgmt port vnet0 grp ff02::1:ff7d:6603 temp
dev ovirtmgmt port vnet1 grp ff02::1:ff7d:6604 temp
dev ovirtmgmt port bond0.86 grp ff02::fb temp
dev ovirtmgmt port bond0.86 grp ff02::2 temp
dev ovirtmgmt port bond0.86 grp ff02::d temp
dev ovirtmgmt port vnet0 grp ff02::1:ff00:76 temp
dev ovirtmgmt port bond0.86 grp ff02::16 temp
dev ovirtmgmt port vnet1 grp ff02::1:ff00:77 temp
dev ovirtmgmt port bond0.86 grp ff02::1:ff00:def temp
dev ovirtmgmt port bond0.86 grp ff02::1:ffa1:40bf temp

Fixes: 08b202b67264 ("bridge br_multicast: IPv6 MLD support.")
Reported-by: Rik Theys <Rik.Theys@esat.kuleuven.be>
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@redhat.com>
Tested-by: Rik Theys <Rik.Theys@esat.kuleuven.be>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 162d6c7..b11736a 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1058,7 +1058,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br,
 
 		err = br_ip6_multicast_add_group(br, port, &grec->grec_mca,
 						 vid);
-		if (!err)
+		if (err)
 			break;
 	}
 
-- 
2.1.0


From 14a5f6891ae5c1cfa191d925c877a66af76d964b Mon Sep 17 00:00:00 2001
From: Richard Cochran <richardcochran@gmail.com>
Date: Mon, 25 May 2015 11:55:43 +0200
Subject: [PATCH 4/8] net: dp83640: fix broken calibration routine.

[ Upstream commit 397a253af5031de4a4612210055935309af4472c ]

Currently, the calibration function that corrects the initial offsets
among multiple devices only works the first time.  If the function is
called more than once, the calibration fails and bogus offsets will be
programmed into the devices.

In a well hidden spot, the device documentation tells that trigger indexes
0 and 1 are special in allowing the TRIG_IF_LATE flag to actually work.

This patch fixes the issue by using one of the special triggers during the
recalibration method.

Signed-off-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/dp83640.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index 7490b6c..d2907a6 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -45,7 +45,7 @@
 #define PSF_TX		0x1000
 #define EXT_EVENT	1
 #define CAL_EVENT	7
-#define CAL_TRIGGER	7
+#define CAL_TRIGGER	1
 #define PER_TRIGGER	6
 
 #define MII_DP83640_MICR 0x11
-- 
2.1.0


From 90d5ba0abac307f9f7d7804cdd648b239d4ecbf4 Mon Sep 17 00:00:00 2001
From: Mark Salyzyn <salyzyn@android.com>
Date: Tue, 26 May 2015 08:22:19 -0700
Subject: [PATCH 5/8] unix/caif: sk_socket can disappear when state is unlocked

[ Upstream commit b48732e4a48d80ed4a14812f0bab09560846514e ]

got a rare NULL pointer dereference in clear_bit

Signed-off-by: Mark Salyzyn <salyzyn@android.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
----
v2: switch to sock_flag(sk, SOCK_DEAD) and added net/caif/caif_socket.c
v3: return -ECONNRESET in upstream caller of wait function for SOCK_DEAD
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/caif/caif_socket.c | 8 ++++++++
 net/unix/af_unix.c     | 8 ++++++++
 2 files changed, 16 insertions(+)

diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 526bf56..afeb8e0 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -332,6 +332,10 @@ static long caif_stream_data_wait(struct sock *sk, long timeo)
 		release_sock(sk);
 		timeo = schedule_timeout(timeo);
 		lock_sock(sk);
+
+		if (sock_flag(sk, SOCK_DEAD))
+			break;
+
 		clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
 	}
 
@@ -376,6 +380,10 @@ static int caif_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 		struct sk_buff *skb;
 
 		lock_sock(sk);
+		if (sock_flag(sk, SOCK_DEAD)) {
+			err = -ECONNRESET;
+			goto unlock;
+		}
 		skb = skb_dequeue(&sk->sk_receive_queue);
 		caif_check_flow_release(sk);
 
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index c3975bc..9afa362 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1891,6 +1891,10 @@ static long unix_stream_data_wait(struct sock *sk, long timeo,
 		unix_state_unlock(sk);
 		timeo = freezable_schedule_timeout(timeo);
 		unix_state_lock(sk);
+
+		if (sock_flag(sk, SOCK_DEAD))
+			break;
+
 		clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
 	}
 
@@ -1955,6 +1959,10 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 		struct sk_buff *skb, *last;
 
 		unix_state_lock(sk);
+		if (sock_flag(sk, SOCK_DEAD)) {
+			err = -ECONNRESET;
+			goto unlock;
+		}
 		last = skb = skb_peek(&sk->sk_receive_queue);
 again:
 		if (skb == NULL) {
-- 
2.1.0


From 98e2a75cb6e081e6f0077dda7921c584611a06f5 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Tue, 26 May 2015 16:08:48 -0700
Subject: [PATCH 6/8] net_sched: invoke ->attach() after setting dev->qdisc

[ Upstream commit 86e363dc3b50bfd50a1f315934583fbda673ab8d ]

For mq qdisc, we add per tx queue qdisc to root qdisc
for display purpose, however, that happens too early,
before the new dev->qdisc is finally set, this causes
q->list points to an old root qdisc which is going to be
freed right before assigning with a new one.

Fix this by moving ->attach() after setting dev->qdisc.

For the record, this fixes the following crash:

 ------------[ cut here ]------------
 WARNING: CPU: 1 PID: 975 at lib/list_debug.c:59 __list_del_entry+0x5a/0x98()
 list_del corruption. prev->next should be ffff8800d1998ae8, but was 6b6b6b6b6b6b6b6b
 CPU: 1 PID: 975 Comm: tc Not tainted 4.1.0-rc4+ #1019
 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
  0000000000000009 ffff8800d73fb928 ffffffff81a44e7f 0000000047574756
  ffff8800d73fb978 ffff8800d73fb968 ffffffff810790da ffff8800cfc4cd20
  ffffffff814e725b ffff8800d1998ae8 ffffffff82381250 0000000000000000
 Call Trace:
  [<ffffffff81a44e7f>] dump_stack+0x4c/0x65
  [<ffffffff810790da>] warn_slowpath_common+0x9c/0xb6
  [<ffffffff814e725b>] ? __list_del_entry+0x5a/0x98
  [<ffffffff81079162>] warn_slowpath_fmt+0x46/0x48
  [<ffffffff81820eb0>] ? dev_graft_qdisc+0x5e/0x6a
  [<ffffffff814e725b>] __list_del_entry+0x5a/0x98
  [<ffffffff814e72a7>] list_del+0xe/0x2d
  [<ffffffff81822f05>] qdisc_list_del+0x1e/0x20
  [<ffffffff81820cd1>] qdisc_destroy+0x30/0xd6
  [<ffffffff81822676>] qdisc_graft+0x11d/0x243
  [<ffffffff818233c1>] tc_get_qdisc+0x1a6/0x1d4
  [<ffffffff810b5eaf>] ? mark_lock+0x2e/0x226
  [<ffffffff817ff8f5>] rtnetlink_rcv_msg+0x181/0x194
  [<ffffffff817ff72e>] ? rtnl_lock+0x17/0x19
  [<ffffffff817ff72e>] ? rtnl_lock+0x17/0x19
  [<ffffffff817ff774>] ? __rtnl_unlock+0x17/0x17
  [<ffffffff81855dc6>] netlink_rcv_skb+0x4d/0x93
  [<ffffffff817ff756>] rtnetlink_rcv+0x26/0x2d
  [<ffffffff818544b2>] netlink_unicast+0xcb/0x150
  [<ffffffff81161db9>] ? might_fault+0x59/0xa9
  [<ffffffff81854f78>] netlink_sendmsg+0x4fa/0x51c
  [<ffffffff817d6e09>] sock_sendmsg_nosec+0x12/0x1d
  [<ffffffff817d8967>] sock_sendmsg+0x29/0x2e
  [<ffffffff817d8cf3>] ___sys_sendmsg+0x1b4/0x23a
  [<ffffffff8100a1b8>] ? native_sched_clock+0x35/0x37
  [<ffffffff810a1d83>] ? sched_clock_local+0x12/0x72
  [<ffffffff810a1fd4>] ? sched_clock_cpu+0x9e/0xb7
  [<ffffffff810def2a>] ? current_kernel_time+0xe/0x32
  [<ffffffff810b4bc5>] ? lock_release_holdtime.part.29+0x71/0x7f
  [<ffffffff810ddebf>] ? read_seqcount_begin.constprop.27+0x5f/0x76
  [<ffffffff810b6292>] ? trace_hardirqs_on_caller+0x17d/0x199
  [<ffffffff811b14d5>] ? __fget_light+0x50/0x78
  [<ffffffff817d9808>] __sys_sendmsg+0x42/0x60
  [<ffffffff817d9838>] SyS_sendmsg+0x12/0x1c
  [<ffffffff81a50e97>] system_call_fastpath+0x12/0x6f
 ---[ end trace ef29d3fb28e97ae7 ]---

For long term, we probably need to clean up the qdisc_graft() code
in case it hides other bugs like this.

Fixes: 95dc19299f74 ("pkt_sched: give visibility to mq slave qdiscs")
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_api.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 3f5fe03..1b693a8 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -804,10 +804,8 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent,
 		if (dev->flags & IFF_UP)
 			dev_deactivate(dev);
 
-		if (new && new->ops->attach) {
-			new->ops->attach(new);
-			num_q = 0;
-		}
+		if (new && new->ops->attach)
+			goto skip;
 
 		for (i = 0; i < num_q; i++) {
 			struct netdev_queue *dev_queue = dev_ingress_queue(dev);
@@ -823,12 +821,16 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent,
 				qdisc_destroy(old);
 		}
 
+skip:
 		if (!ingress) {
 			notify_and_destroy(net, skb, n, classid,
 					   dev->qdisc, new);
 			if (new && !new->ops->attach)
 				atomic_inc(&new->refcnt);
 			dev->qdisc = new ? : &noop_qdisc;
+
+			if (new && new->ops->attach)
+				new->ops->attach(new);
 		} else {
 			notify_and_destroy(net, skb, n, classid, old, new);
 		}
-- 
2.1.0


From d60ab2cc3f68ff0d71f341552421f6dbf76c5e18 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 30 May 2015 09:16:53 -0700
Subject: [PATCH 7/8] udp: fix behavior of wrong checksums

[ Upstream commit beb39db59d14990e401e235faf66a6b9b31240b0 ]

We have two problems in UDP stack related to bogus checksums :

1) We return -EAGAIN to application even if receive queue is not empty.
   This breaks applications using edge trigger epoll()

2) Under UDP flood, we can loop forever without yielding to other
   processes, potentially hanging the host, especially on non SMP.

This patch is an attempt to make things better.

We might in the future add extra support for rt applications
wanting to better control time spent doing a recv() in a hostile
environment. For example we could validate checksums before queuing
packets in socket receive queue.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 6 ++----
 net/ipv6/udp.c | 6 ++----
 2 files changed, 4 insertions(+), 8 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 6ca9907..268ed25 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1295,10 +1295,8 @@ csum_copy_err:
 	}
 	unlock_sock_fast(sk, slow);
 
-	if (noblock)
-		return -EAGAIN;
-
-	/* starting over for a new packet */
+	/* starting over for a new packet, but check if we need to yield */
+	cond_resched();
 	msg->msg_flags &= ~MSG_TRUNC;
 	goto try_again;
 }
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 3d2758d..e09ca28 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -495,10 +495,8 @@ csum_copy_err:
 	}
 	unlock_sock_fast(sk, slow);
 
-	if (noblock)
-		return -EAGAIN;
-
-	/* starting over for a new packet */
+	/* starting over for a new packet, but check if we need to yield */
+	cond_resched();
 	msg->msg_flags &= ~MSG_TRUNC;
 	goto try_again;
 }
-- 
2.1.0


From af100b0c9b676125fc344fabbfe19cdc12a774dd Mon Sep 17 00:00:00 2001
From: Ian Campbell <Ian.Campbell@citrix.com>
Date: Mon, 1 Jun 2015 11:30:24 +0100
Subject: [PATCH 8/8] xen: netback: read hotplug script once at start of day.

[ Upstream commit 31a418986a5852034d520a5bab546821ff1ccf3d ]

When we come to tear things down in netback_remove() and generate the
uevent it is possible that the xenstore directory has already been
removed (details below).

In such cases netback_uevent() won't be able to read the hotplug
script and will write a xenstore error node.

A recent change to the hypervisor exposed this race such that we now
sometimes lose it (where apparently we didn't ever before).

Instead read the hotplug script configuration during setup and use it
for the lifetime of the backend device.

The apparently more obvious fix of moving the transition to
state=Closed in netback_remove() to after the uevent does not work
because it is possible that we are already in state=Closed (in
reaction to the guest having disconnected as it shutdown). Being
already in Closed means the toolstack is at liberty to start tearing
down the xenstore directories. In principal it might be possible to
arrange to unregister the device sooner (e.g on transition to Closing)
such that xenstore would still be there but this state machine is
fragile and prone to anger...

A modern Xen system only relies on the hotplug uevent for driver
domains, when the backend is in the same domain as the toolstack it
will run the necessary setup/teardown directly in the correct sequence
wrt xenstore changes.

Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Acked-by: Wei Liu <wei.liu2@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netback/xenbus.c | 33 +++++++++++++++++++--------------
 1 file changed, 19 insertions(+), 14 deletions(-)

diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index 1b08d87..659a6f2 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -33,6 +33,8 @@ struct backend_info {
 	enum xenbus_state frontend_state;
 	struct xenbus_watch hotplug_status_watch;
 	u8 have_hotplug_status_watch:1;
+
+	const char *hotplug_script;
 };
 
 static int connect_rings(struct backend_info *);
@@ -55,6 +57,7 @@ static int netback_remove(struct xenbus_device *dev)
 		xenvif_free(be->vif);
 		be->vif = NULL;
 	}
+	kfree(be->hotplug_script);
 	kfree(be);
 	dev_set_drvdata(&dev->dev, NULL);
 	return 0;
@@ -72,6 +75,7 @@ static int netback_probe(struct xenbus_device *dev,
 	struct xenbus_transaction xbt;
 	int err;
 	int sg;
+	const char *script;
 	struct backend_info *be = kzalloc(sizeof(struct backend_info),
 					  GFP_KERNEL);
 	if (!be) {
@@ -142,6 +146,15 @@ static int netback_probe(struct xenbus_device *dev,
 	if (err)
 		pr_debug("Error writing feature-split-event-channels\n");
 
+	script = xenbus_read(XBT_NIL, dev->nodename, "script", NULL);
+	if (IS_ERR(script)) {
+		err = PTR_ERR(script);
+		xenbus_dev_fatal(dev, err, "reading script");
+		goto fail;
+	}
+
+	be->hotplug_script = script;
+
 	err = xenbus_switch_state(dev, XenbusStateInitWait);
 	if (err)
 		goto fail;
@@ -172,22 +185,14 @@ static int netback_uevent(struct xenbus_device *xdev,
 			  struct kobj_uevent_env *env)
 {
 	struct backend_info *be = dev_get_drvdata(&xdev->dev);
-	char *val;
 
-	val = xenbus_read(XBT_NIL, xdev->nodename, "script", NULL);
-	if (IS_ERR(val)) {
-		int err = PTR_ERR(val);
-		xenbus_dev_fatal(xdev, err, "reading script");
-		return err;
-	} else {
-		if (add_uevent_var(env, "script=%s", val)) {
-			kfree(val);
-			return -ENOMEM;
-		}
-		kfree(val);
-	}
+	if (!be)
+		return 0;
+
+	if (add_uevent_var(env, "script=%s", be->hotplug_script))
+		return -ENOMEM;
 
-	if (!be || !be->vif)
+	if (!be->vif)
 		return 0;
 
 	return add_uevent_var(env, "vif=%s", be->vif->dev->name);
-- 
2.1.0


[-- Attachment #3: net_314.mbox --]
[-- Type: Application/Octet-Stream, Size: 33194 bytes --]

From 601a86e658d96af8ed8f07f169491086f983fae2 Mon Sep 17 00:00:00 2001
From: Vlad Yasevich <vyasevich@gmail.com>
Date: Sat, 2 May 2015 21:33:44 -0400
Subject: [PATCH 01/14] net: core: Correct an over-stringent device loop
 detection.

[ Upstream commit d66bf7dd27573ee5ea90484899ee952c19ccb194 ]

The code in __netdev_upper_dev_link() has an over-stringent
loop detection logic that actually prevents valid configurations
from working correctly.

In particular, the logic returns an error if an upper device
is already in the list of all upper devices for a given dev.
This particular check seems to be a overzealous as it disallows
perfectly valid configurations.  For example:
  # ip l a link eth0 name eth0.10 type vlan id 10
  # ip l a dev br0 typ bridge
  # ip l s eth0.10 master br0
  # ip l s eth0 master br0  <--- Will fail

If you switch the last two commands (add eth0 first), then both
will succeed.  If after that, you remove eth0 and try to re-add
it, it will fail!

It appears to be enough to simply check adj_list to keeps things
safe.

I've tried stacking multiple devices multiple times in all different
combinations, and either rx_handler registration prevented the stacking
of the device linking cought the error.

Signed-off-by: Vladislav Yasevich <vyasevic@redhat.com>
Acked-by: Jiri Pirko <jiri@resnulli.us>
Acked-by: Veaceslav Falico <vfalico@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 73abbd7..1b9e700 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4903,7 +4903,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 	if (__netdev_find_adj(upper_dev, dev, &upper_dev->all_adj_list.upper))
 		return -EBUSY;
 
-	if (__netdev_find_adj(dev, upper_dev, &dev->all_adj_list.upper))
+	if (__netdev_find_adj(dev, upper_dev, &dev->adj_list.upper))
 		return -EEXIST;
 
 	if (master && netdev_master_upper_dev_get(dev))
-- 
2.1.0


From 9b47f4a99408811eba072858c0a43d640db12ef2 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@plumgrid.com>
Date: Fri, 22 May 2015 15:42:55 -0700
Subject: [PATCH 02/14] x86: bpf_jit: fix compilation of large bpf programs

[ Upstream commit 3f7352bf21f8fd7ba3e2fcef9488756f188e12be ]

x86 has variable length encoding. x86 JIT compiler is trying
to pick the shortest encoding for given bpf instruction.
While doing so the jump targets are changing, so JIT is doing
multiple passes over the program. Typical program needs 3 passes.
Some very short programs converge with 2 passes. Large programs
may need 4 or 5. But specially crafted bpf programs may hit the
pass limit and if the program converges on the last iteration
the JIT compiler will be producing an image full of 'int 3' insns.
Fix this corner case by doing final iteration over bpf program.

Fixes: 0a14842f5a3c ("net: filter: Just In Time compiler for x86-64")
Reported-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Tested-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/x86/net/bpf_jit_comp.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index af2d431..1fed139 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -211,7 +211,12 @@ void bpf_jit_compile(struct sk_filter *fp)
 	}
 	cleanup_addr = proglen; /* epilogue address */
 
-	for (pass = 0; pass < 10; pass++) {
+	/* JITed image shrinks with every pass and the loop iterates
+	 * until the image stops shrinking. Very large bpf programs
+	 * may converge on the last pass. In such case do one more
+	 * pass to emit the final image
+	 */
+	for (pass = 0; pass < 10 || image; pass++) {
 		u8 seen_or_pass0 = (pass == 0) ? (SEEN_XREG | SEEN_DATAREF | SEEN_MEM) : seen;
 		/* no prologue/epilogue for trivial filters (RET something) */
 		proglen = 0;
-- 
2.1.0


From d0047de65c9d9c81281bb8e0730b0bf9400fc60d Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 15 May 2015 16:30:41 -0700
Subject: [PATCH 03/14] net: phy: Allow EEE for all RGMII variants

[ Upstream commit 7e14069651591c81046ffaec13c3dac8cb70f5fb ]

RGMII interfaces come in multiple flavors: RGMII with transmit or
receive internal delay, no delays at all, or delays in both direction.

This change extends the initial check for PHY_INTERFACE_MODE_RGMII to
cover all of these variants since EEE should be allowed for any of these
modes, since it is a property of the RGMII, hence Gigabit PHY capability
more than the RGMII electrical interface and its delays.

Fixes: a59a4d192166 ("phy: add the EEE support and the way to access to the MMD registers")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 1d56878..65cfc5a 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -965,12 +965,14 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable)
 {
 	/* According to 802.3az,the EEE is supported only in full duplex-mode.
 	 * Also EEE feature is active when core is operating with MII, GMII
-	 * or RGMII.
+	 * or RGMII (all kinds). Internal PHYs are also allowed to proceed and
+	 * should return an error if they do not support EEE.
 	 */
 	if ((phydev->duplex == DUPLEX_FULL) &&
 	    ((phydev->interface == PHY_INTERFACE_MODE_MII) ||
 	    (phydev->interface == PHY_INTERFACE_MODE_GMII) ||
-	    (phydev->interface == PHY_INTERFACE_MODE_RGMII))) {
+	     (phydev->interface >= PHY_INTERFACE_MODE_RGMII &&
+	      phydev->interface <= PHY_INTERFACE_MODE_RGMII_TXID))) {
 		int eee_lp, eee_cap, eee_adv;
 		u32 lp, cap, adv;
 		int status;
-- 
2.1.0


From 18edc4c019bb7f2c8f3578b356c12ff6282c0ee0 Mon Sep 17 00:00:00 2001
From: Florent Fourcot <florent.fourcot@enst-bretagne.fr>
Date: Sat, 16 May 2015 00:24:59 +0200
Subject: [PATCH 04/14] tcp/ipv6: fix flow label setting in TIME_WAIT state

[ Upstream commit 21858cd02dabcf290564cbf4769b101eba54d7bb ]

commit 1d13a96c74fc ("ipv6: tcp: fix flowlabel value in ACK messages
send from TIME_WAIT") added the flow label in the last TCP packets.
Unfortunately, it was not casted properly.

This patch replace the buggy shift with be32_to_cpu/cpu_to_be32.

Fixes: 1d13a96c74fc ("ipv6: tcp: fix flowlabel value in ACK messages")
Reported-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Florent Fourcot <florent.fourcot@enst-bretagne.fr>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_minisocks.c | 2 +-
 net/ipv6/tcp_ipv6.c      | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 7a436c5..9128d0a 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -297,7 +297,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 			tw->tw_v6_daddr = sk->sk_v6_daddr;
 			tw->tw_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
 			tw->tw_tclass = np->tclass;
-			tw->tw_flowlabel = np->flow_label >> 12;
+			tw->tw_flowlabel = be32_to_cpu(np->flow_label & IPV6_FLOWLABEL_MASK);
 			tw->tw_ipv6only = np->ipv6only;
 		}
 #endif
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 9d4332d..b50ae29 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -905,7 +905,7 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb)
 			tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
 			tcp_time_stamp + tcptw->tw_ts_offset,
 			tcptw->tw_ts_recent, tcp_twsk_md5_key(tcptw),
-			tw->tw_tclass, (tw->tw_flowlabel << 12));
+			tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel));
 
 	inet_twsk_put(tw);
 }
-- 
2.1.0


From a091b2c0cb835888ca003e858e0046c602d898d2 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 22 May 2015 04:58:12 -0500
Subject: [PATCH 05/14] ipv4: Avoid crashing in ip_error

[ Upstream commit 381c759d9916c42959515ad34a6d467e24a88e93 ]

ip_error does not check if in_dev is NULL before dereferencing it.

IThe following sequence of calls is possible:
CPU A                          CPU B
ip_rcv_finish
    ip_route_input_noref()
        ip_route_input_slow()
                               inetdev_destroy()
    dst_input()

With the result that a network device can be destroyed while processing
an input packet.

A crash was triggered with only unicast packets in flight, and
forwarding enabled on the only network device.   The error condition
was created by the removal of the network device.

As such it is likely the that error code was -EHOSTUNREACH, and the
action taken by ip_error (if in_dev had been accessible) would have
been to not increment any counters and to have tried and likely failed
to send an icmp error as the network device is going away.

Therefore handle this weird case by just dropping the packet if
!in_dev.  It will result in dropping the packet sooner, and will not
result in an actual change of behavior.

Fixes: 251da4130115b ("ipv4: Cache ip_error() routes even when not forwarding.")
Reported-by: Vittorio Gambaletta <linuxbugs@vittgam.net>
Tested-by: Vittorio Gambaletta <linuxbugs@vittgam.net>
Signed-off-by: Vittorio Gambaletta <linuxbugs@vittgam.net>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index b64330f..625615c 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -910,6 +910,10 @@ static int ip_error(struct sk_buff *skb)
 	bool send;
 	int code;
 
+	/* IP on this device is disabled. */
+	if (!in_dev)
+		goto out;
+
 	net = dev_net(rt->dst.dev);
 	if (!IN_DEV_FORWARD(in_dev)) {
 		switch (rt->dst.error) {
-- 
2.1.0


From 1a90ae737aa0d6393be8be86574470d89f4acc43 Mon Sep 17 00:00:00 2001
From: Thadeu Lima de Souza Cascardo <cascardo@redhat.com>
Date: Fri, 22 May 2015 12:18:59 -0300
Subject: [PATCH 06/14] bridge: fix parsing of MLDv2 reports

[ Upstream commit 47cc84ce0c2fe75c99ea5963c4b5704dd78ead54 ]

When more than a multicast address is present in a MLDv2 report, all but
the first address is ignored, because the code breaks out of the loop if
there has not been an error adding that address.

This has caused failures when two guests connected through the bridge
tried to communicate using IPv6. Neighbor discoveries would not be
transmitted to the other guest when both used a link-local address and a
static address.

This only happens when there is a MLDv2 querier in the network.

The fix will only break out of the loop when there is a failure adding a
multicast address.

The mdb before the patch:

dev ovirtmgmt port vnet0 grp ff02::1:ff7d:6603 temp
dev ovirtmgmt port vnet1 grp ff02::1:ff7d:6604 temp
dev ovirtmgmt port bond0.86 grp ff02::2 temp

After the patch:

dev ovirtmgmt port vnet0 grp ff02::1:ff7d:6603 temp
dev ovirtmgmt port vnet1 grp ff02::1:ff7d:6604 temp
dev ovirtmgmt port bond0.86 grp ff02::fb temp
dev ovirtmgmt port bond0.86 grp ff02::2 temp
dev ovirtmgmt port bond0.86 grp ff02::d temp
dev ovirtmgmt port vnet0 grp ff02::1:ff00:76 temp
dev ovirtmgmt port bond0.86 grp ff02::16 temp
dev ovirtmgmt port vnet1 grp ff02::1:ff00:77 temp
dev ovirtmgmt port bond0.86 grp ff02::1:ff00:def temp
dev ovirtmgmt port bond0.86 grp ff02::1:ffa1:40bf temp

Fixes: 08b202b67264 ("bridge br_multicast: IPv6 MLD support.")
Reported-by: Rik Theys <Rik.Theys@esat.kuleuven.be>
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@redhat.com>
Tested-by: Rik Theys <Rik.Theys@esat.kuleuven.be>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 93067ec..11a2e6c 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1056,7 +1056,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br,
 
 		err = br_ip6_multicast_add_group(br, port, &grec->grec_mca,
 						 vid);
-		if (!err)
+		if (err)
 			break;
 	}
 
-- 
2.1.0


From b5beaf1e1677174572fb7e06205f6bd4b43082aa Mon Sep 17 00:00:00 2001
From: Richard Cochran <richardcochran@gmail.com>
Date: Mon, 25 May 2015 11:55:43 +0200
Subject: [PATCH 07/14] net: dp83640: fix broken calibration routine.

[ Upstream commit 397a253af5031de4a4612210055935309af4472c ]

Currently, the calibration function that corrects the initial offsets
among multiple devices only works the first time.  If the function is
called more than once, the calibration fails and bogus offsets will be
programmed into the devices.

In a well hidden spot, the device documentation tells that trigger indexes
0 and 1 are special in allowing the TRIG_IF_LATE flag to actually work.

This patch fixes the issue by using one of the special triggers during the
recalibration method.

Signed-off-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/dp83640.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index 98e7cbf..857eb76 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -45,7 +45,7 @@
 #define PSF_TX		0x1000
 #define EXT_EVENT	1
 #define CAL_EVENT	7
-#define CAL_TRIGGER	7
+#define CAL_TRIGGER	1
 #define PER_TRIGGER	6
 
 #define MII_DP83640_MICR 0x11
-- 
2.1.0


From 426b46234faeeec9c5d96db35126e478a1d7b76c Mon Sep 17 00:00:00 2001
From: Richard Cochran <richardcochran@gmail.com>
Date: Mon, 25 May 2015 11:55:44 +0200
Subject: [PATCH 08/14] net: dp83640: reinforce locking rules.

[ Upstream commit a935865c828c8cd20501f618c69f659a5b6d6a5f ]

Callers of the ext_write function are supposed to hold a mutex that
protects the state of the dialed page, but one caller was missing the
lock from the very start, and over time the code has been changed
without following the rule.  This patch cleans up the call sites in
violation of the rule.

Signed-off-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/dp83640.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index 857eb76..0be3f9d 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -442,7 +442,9 @@ static int ptp_dp83640_enable(struct ptp_clock_info *ptp,
 			else
 				evnt |= EVNT_RISE;
 		}
+		mutex_lock(&clock->extreg_lock);
 		ext_write(0, phydev, PAGE5, PTP_EVNT, evnt);
+		mutex_unlock(&clock->extreg_lock);
 		return 0;
 
 	case PTP_CLK_REQ_PEROUT:
@@ -463,6 +465,8 @@ static u8 status_frame_src[6] = { 0x08, 0x00, 0x17, 0x0B, 0x6B, 0x0F };
 
 static void enable_status_frames(struct phy_device *phydev, bool on)
 {
+	struct dp83640_private *dp83640 = phydev->priv;
+	struct dp83640_clock *clock = dp83640->clock;
 	u16 cfg0 = 0, ver;
 
 	if (on)
@@ -470,9 +474,13 @@ static void enable_status_frames(struct phy_device *phydev, bool on)
 
 	ver = (PSF_PTPVER & VERSIONPTP_MASK) << VERSIONPTP_SHIFT;
 
+	mutex_lock(&clock->extreg_lock);
+
 	ext_write(0, phydev, PAGE5, PSF_CFG0, cfg0);
 	ext_write(0, phydev, PAGE6, PSF_CFG1, ver);
 
+	mutex_unlock(&clock->extreg_lock);
+
 	if (!phydev->attached_dev) {
 		pr_warn("expected to find an attached netdevice\n");
 		return;
@@ -1063,11 +1071,18 @@ static int dp83640_config_init(struct phy_device *phydev)
 
 	if (clock->chosen && !list_empty(&clock->phylist))
 		recalibrate(clock);
-	else
+	else {
+		mutex_lock(&clock->extreg_lock);
 		enable_broadcast(phydev, clock->page, 1);
+		mutex_unlock(&clock->extreg_lock);
+	}
 
 	enable_status_frames(phydev, true);
+
+	mutex_lock(&clock->extreg_lock);
 	ext_write(0, phydev, PAGE4, PTP_CTL, PTP_ENABLE);
+	mutex_unlock(&clock->extreg_lock);
+
 	return 0;
 }
 
-- 
2.1.0


From 884e4c6ac1a340fcb667b2a1a0fadda1b1b28dce Mon Sep 17 00:00:00 2001
From: Mark Salyzyn <salyzyn@android.com>
Date: Tue, 26 May 2015 08:22:19 -0700
Subject: [PATCH 09/14] unix/caif: sk_socket can disappear when state is
 unlocked

[ Upstream commit b48732e4a48d80ed4a14812f0bab09560846514e ]

got a rare NULL pointer dereference in clear_bit

Signed-off-by: Mark Salyzyn <salyzyn@android.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
----
v2: switch to sock_flag(sk, SOCK_DEAD) and added net/caif/caif_socket.c
v3: return -ECONNRESET in upstream caller of wait function for SOCK_DEAD
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/caif/caif_socket.c | 8 ++++++++
 net/unix/af_unix.c     | 8 ++++++++
 2 files changed, 16 insertions(+)

diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 526bf56..afeb8e0 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -332,6 +332,10 @@ static long caif_stream_data_wait(struct sock *sk, long timeo)
 		release_sock(sk);
 		timeo = schedule_timeout(timeo);
 		lock_sock(sk);
+
+		if (sock_flag(sk, SOCK_DEAD))
+			break;
+
 		clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
 	}
 
@@ -376,6 +380,10 @@ static int caif_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 		struct sk_buff *skb;
 
 		lock_sock(sk);
+		if (sock_flag(sk, SOCK_DEAD)) {
+			err = -ECONNRESET;
+			goto unlock;
+		}
 		skb = skb_dequeue(&sk->sk_receive_queue);
 		caif_check_flow_release(sk);
 
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 94404f1..4757f1c 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1893,6 +1893,10 @@ static long unix_stream_data_wait(struct sock *sk, long timeo,
 		unix_state_unlock(sk);
 		timeo = freezable_schedule_timeout(timeo);
 		unix_state_lock(sk);
+
+		if (sock_flag(sk, SOCK_DEAD))
+			break;
+
 		clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
 	}
 
@@ -1957,6 +1961,10 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 		struct sk_buff *skb, *last;
 
 		unix_state_lock(sk);
+		if (sock_flag(sk, SOCK_DEAD)) {
+			err = -ECONNRESET;
+			goto unlock;
+		}
 		last = skb = skb_peek(&sk->sk_receive_queue);
 again:
 		if (skb == NULL) {
-- 
2.1.0


From b4763b44244e778edffabaf9a8a141b5b418ff93 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Tue, 26 May 2015 16:08:48 -0700
Subject: [PATCH 10/14] net_sched: invoke ->attach() after setting dev->qdisc

[ Upstream commit 86e363dc3b50bfd50a1f315934583fbda673ab8d ]

For mq qdisc, we add per tx queue qdisc to root qdisc
for display purpose, however, that happens too early,
before the new dev->qdisc is finally set, this causes
q->list points to an old root qdisc which is going to be
freed right before assigning with a new one.

Fix this by moving ->attach() after setting dev->qdisc.

For the record, this fixes the following crash:

 ------------[ cut here ]------------
 WARNING: CPU: 1 PID: 975 at lib/list_debug.c:59 __list_del_entry+0x5a/0x98()
 list_del corruption. prev->next should be ffff8800d1998ae8, but was 6b6b6b6b6b6b6b6b
 CPU: 1 PID: 975 Comm: tc Not tainted 4.1.0-rc4+ #1019
 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
  0000000000000009 ffff8800d73fb928 ffffffff81a44e7f 0000000047574756
  ffff8800d73fb978 ffff8800d73fb968 ffffffff810790da ffff8800cfc4cd20
  ffffffff814e725b ffff8800d1998ae8 ffffffff82381250 0000000000000000
 Call Trace:
  [<ffffffff81a44e7f>] dump_stack+0x4c/0x65
  [<ffffffff810790da>] warn_slowpath_common+0x9c/0xb6
  [<ffffffff814e725b>] ? __list_del_entry+0x5a/0x98
  [<ffffffff81079162>] warn_slowpath_fmt+0x46/0x48
  [<ffffffff81820eb0>] ? dev_graft_qdisc+0x5e/0x6a
  [<ffffffff814e725b>] __list_del_entry+0x5a/0x98
  [<ffffffff814e72a7>] list_del+0xe/0x2d
  [<ffffffff81822f05>] qdisc_list_del+0x1e/0x20
  [<ffffffff81820cd1>] qdisc_destroy+0x30/0xd6
  [<ffffffff81822676>] qdisc_graft+0x11d/0x243
  [<ffffffff818233c1>] tc_get_qdisc+0x1a6/0x1d4
  [<ffffffff810b5eaf>] ? mark_lock+0x2e/0x226
  [<ffffffff817ff8f5>] rtnetlink_rcv_msg+0x181/0x194
  [<ffffffff817ff72e>] ? rtnl_lock+0x17/0x19
  [<ffffffff817ff72e>] ? rtnl_lock+0x17/0x19
  [<ffffffff817ff774>] ? __rtnl_unlock+0x17/0x17
  [<ffffffff81855dc6>] netlink_rcv_skb+0x4d/0x93
  [<ffffffff817ff756>] rtnetlink_rcv+0x26/0x2d
  [<ffffffff818544b2>] netlink_unicast+0xcb/0x150
  [<ffffffff81161db9>] ? might_fault+0x59/0xa9
  [<ffffffff81854f78>] netlink_sendmsg+0x4fa/0x51c
  [<ffffffff817d6e09>] sock_sendmsg_nosec+0x12/0x1d
  [<ffffffff817d8967>] sock_sendmsg+0x29/0x2e
  [<ffffffff817d8cf3>] ___sys_sendmsg+0x1b4/0x23a
  [<ffffffff8100a1b8>] ? native_sched_clock+0x35/0x37
  [<ffffffff810a1d83>] ? sched_clock_local+0x12/0x72
  [<ffffffff810a1fd4>] ? sched_clock_cpu+0x9e/0xb7
  [<ffffffff810def2a>] ? current_kernel_time+0xe/0x32
  [<ffffffff810b4bc5>] ? lock_release_holdtime.part.29+0x71/0x7f
  [<ffffffff810ddebf>] ? read_seqcount_begin.constprop.27+0x5f/0x76
  [<ffffffff810b6292>] ? trace_hardirqs_on_caller+0x17d/0x199
  [<ffffffff811b14d5>] ? __fget_light+0x50/0x78
  [<ffffffff817d9808>] __sys_sendmsg+0x42/0x60
  [<ffffffff817d9838>] SyS_sendmsg+0x12/0x1c
  [<ffffffff81a50e97>] system_call_fastpath+0x12/0x6f
 ---[ end trace ef29d3fb28e97ae7 ]---

For long term, we probably need to clean up the qdisc_graft() code
in case it hides other bugs like this.

Fixes: 95dc19299f74 ("pkt_sched: give visibility to mq slave qdiscs")
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_api.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 98532cf..bdaed31 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -812,10 +812,8 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent,
 		if (dev->flags & IFF_UP)
 			dev_deactivate(dev);
 
-		if (new && new->ops->attach) {
-			new->ops->attach(new);
-			num_q = 0;
-		}
+		if (new && new->ops->attach)
+			goto skip;
 
 		for (i = 0; i < num_q; i++) {
 			struct netdev_queue *dev_queue = dev_ingress_queue(dev);
@@ -831,12 +829,16 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent,
 				qdisc_destroy(old);
 		}
 
+skip:
 		if (!ingress) {
 			notify_and_destroy(net, skb, n, classid,
 					   dev->qdisc, new);
 			if (new && !new->ops->attach)
 				atomic_inc(&new->refcnt);
 			dev->qdisc = new ? : &noop_qdisc;
+
+			if (new && new->ops->attach)
+				new->ops->attach(new);
 		} else {
 			notify_and_destroy(net, skb, n, classid, old, new);
 		}
-- 
2.1.0


From f8fc4f869ca1a6a0c271ca0e931e76232ceee5e4 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 30 May 2015 09:16:53 -0700
Subject: [PATCH 11/14] udp: fix behavior of wrong checksums

[ Upstream commit beb39db59d14990e401e235faf66a6b9b31240b0 ]

We have two problems in UDP stack related to bogus checksums :

1) We return -EAGAIN to application even if receive queue is not empty.
   This breaks applications using edge trigger epoll()

2) Under UDP flood, we can loop forever without yielding to other
   processes, potentially hanging the host, especially on non SMP.

This patch is an attempt to make things better.

We might in the future add extra support for rt applications
wanting to better control time spent doing a recv() in a hostile
environment. For example we could validate checksums before queuing
packets in socket receive queue.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 6 ++----
 net/ipv6/udp.c | 6 ++----
 2 files changed, 4 insertions(+), 8 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index b25e852..5db3e2c 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1317,10 +1317,8 @@ csum_copy_err:
 	}
 	unlock_sock_fast(sk, slow);
 
-	if (noblock)
-		return -EAGAIN;
-
-	/* starting over for a new packet */
+	/* starting over for a new packet, but check if we need to yield */
+	cond_resched();
 	msg->msg_flags &= ~MSG_TRUNC;
 	goto try_again;
 }
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 20b63d2..38625a9 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -515,10 +515,8 @@ csum_copy_err:
 	}
 	unlock_sock_fast(sk, slow);
 
-	if (noblock)
-		return -EAGAIN;
-
-	/* starting over for a new packet */
+	/* starting over for a new packet, but check if we need to yield */
+	cond_resched();
 	msg->msg_flags &= ~MSG_TRUNC;
 	goto try_again;
 }
-- 
2.1.0


From 6864a0b0aa9d130597d2d25789ada18772a6bf8a Mon Sep 17 00:00:00 2001
From: Ian Campbell <Ian.Campbell@citrix.com>
Date: Mon, 1 Jun 2015 11:30:24 +0100
Subject: [PATCH 12/14] xen: netback: read hotplug script once at start of day.

[ Upstream commit 31a418986a5852034d520a5bab546821ff1ccf3d ]

When we come to tear things down in netback_remove() and generate the
uevent it is possible that the xenstore directory has already been
removed (details below).

In such cases netback_uevent() won't be able to read the hotplug
script and will write a xenstore error node.

A recent change to the hypervisor exposed this race such that we now
sometimes lose it (where apparently we didn't ever before).

Instead read the hotplug script configuration during setup and use it
for the lifetime of the backend device.

The apparently more obvious fix of moving the transition to
state=Closed in netback_remove() to after the uevent does not work
because it is possible that we are already in state=Closed (in
reaction to the guest having disconnected as it shutdown). Being
already in Closed means the toolstack is at liberty to start tearing
down the xenstore directories. In principal it might be possible to
arrange to unregister the device sooner (e.g on transition to Closing)
such that xenstore would still be there but this state machine is
fragile and prone to anger...

A modern Xen system only relies on the hotplug uevent for driver
domains, when the backend is in the same domain as the toolstack it
will run the necessary setup/teardown directly in the correct sequence
wrt xenstore changes.

Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Acked-by: Wei Liu <wei.liu2@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netback/xenbus.c | 33 +++++++++++++++++++--------------
 1 file changed, 19 insertions(+), 14 deletions(-)

diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index 7a206cf..d18e653 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -32,6 +32,8 @@ struct backend_info {
 	enum xenbus_state frontend_state;
 	struct xenbus_watch hotplug_status_watch;
 	u8 have_hotplug_status_watch:1;
+
+	const char *hotplug_script;
 };
 
 static int connect_rings(struct backend_info *);
@@ -54,6 +56,7 @@ static int netback_remove(struct xenbus_device *dev)
 		xenvif_free(be->vif);
 		be->vif = NULL;
 	}
+	kfree(be->hotplug_script);
 	kfree(be);
 	dev_set_drvdata(&dev->dev, NULL);
 	return 0;
@@ -71,6 +74,7 @@ static int netback_probe(struct xenbus_device *dev,
 	struct xenbus_transaction xbt;
 	int err;
 	int sg;
+	const char *script;
 	struct backend_info *be = kzalloc(sizeof(struct backend_info),
 					  GFP_KERNEL);
 	if (!be) {
@@ -157,6 +161,15 @@ static int netback_probe(struct xenbus_device *dev,
 	if (err)
 		pr_debug("Error writing feature-split-event-channels\n");
 
+	script = xenbus_read(XBT_NIL, dev->nodename, "script", NULL);
+	if (IS_ERR(script)) {
+		err = PTR_ERR(script);
+		xenbus_dev_fatal(dev, err, "reading script");
+		goto fail;
+	}
+
+	be->hotplug_script = script;
+
 	err = xenbus_switch_state(dev, XenbusStateInitWait);
 	if (err)
 		goto fail;
@@ -187,22 +200,14 @@ static int netback_uevent(struct xenbus_device *xdev,
 			  struct kobj_uevent_env *env)
 {
 	struct backend_info *be = dev_get_drvdata(&xdev->dev);
-	char *val;
 
-	val = xenbus_read(XBT_NIL, xdev->nodename, "script", NULL);
-	if (IS_ERR(val)) {
-		int err = PTR_ERR(val);
-		xenbus_dev_fatal(xdev, err, "reading script");
-		return err;
-	} else {
-		if (add_uevent_var(env, "script=%s", val)) {
-			kfree(val);
-			return -ENOMEM;
-		}
-		kfree(val);
-	}
+	if (!be)
+		return 0;
+
+	if (add_uevent_var(env, "script=%s", be->hotplug_script))
+		return -ENOMEM;
 
-	if (!be || !be->vif)
+	if (!be->vif)
 		return 0;
 
 	return add_uevent_var(env, "vif=%s", be->vif->dev->name);
-- 
2.1.0


From 4ce7aeff62d4bac39f7339a21ba3c5015673862e Mon Sep 17 00:00:00 2001
From: Shawn Bohrer <sbohrer@rgmadvisors.com>
Date: Wed, 3 Jun 2015 16:27:38 -0500
Subject: [PATCH 13/14] ipv4/udp: Verify multicast group is ours in
 upd_v4_early_demux()

[ Upstream commit 6e540309326188f769e03bb4c6dd8ff6752930c2 ]

421b3885bf6d56391297844f43fb7154a6396e12 "udp: ipv4: Add udp early
demux" introduced a regression that allowed sockets bound to INADDR_ANY
to receive packets from multicast groups that the socket had not joined.
For example a socket that had joined 224.168.2.9 could also receive
packets from 225.168.2.9 despite not having joined that group if
ip_early_demux is enabled.

Fix this by calling ip_check_mc_rcu() in udp_v4_early_demux() to verify
that the multicast packet is indeed ours.

Signed-off-by: Shawn Bohrer <sbohrer@rgmadvisors.com>
Reported-by: Yurij M. Plotnikov <Yurij.Plotnikov@oktetlabs.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 5db3e2c..21a3a9e 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -90,6 +90,7 @@
 #include <linux/socket.h>
 #include <linux/sockios.h>
 #include <linux/igmp.h>
+#include <linux/inetdevice.h>
 #include <linux/in.h>
 #include <linux/errno.h>
 #include <linux/timer.h>
@@ -1922,6 +1923,7 @@ void udp_v4_early_demux(struct sk_buff *skb)
 	struct sock *sk;
 	struct dst_entry *dst;
 	int dif = skb->dev->ifindex;
+	int ours;
 
 	/* validate the packet */
 	if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr)))
@@ -1931,14 +1933,24 @@ void udp_v4_early_demux(struct sk_buff *skb)
 	uh = udp_hdr(skb);
 
 	if (skb->pkt_type == PACKET_BROADCAST ||
-	    skb->pkt_type == PACKET_MULTICAST)
+	    skb->pkt_type == PACKET_MULTICAST) {
+		struct in_device *in_dev = __in_dev_get_rcu(skb->dev);
+
+		if (!in_dev)
+			return;
+
+		ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr,
+				       iph->protocol);
+		if (!ours)
+			return;
 		sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr,
 						   uh->source, iph->saddr, dif);
-	else if (skb->pkt_type == PACKET_HOST)
+	} else if (skb->pkt_type == PACKET_HOST) {
 		sk = __udp4_lib_demux_lookup(net, uh->dest, iph->daddr,
 					     uh->source, iph->saddr, dif);
-	else
+	} else {
 		return;
+	}
 
 	if (!sk)
 		return;
-- 
2.1.0


From bf8048b2ec134ebd2640c2ffb6c503a59111292a Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Sat, 6 Jun 2015 06:49:00 -0700
Subject: [PATCH 14/14] bridge: disable softirqs around br_fdb_update to avoid
 lockup

[ Upstream commit c4c832f89dc468cf11dc0dd17206bace44526651 ]

br_fdb_update() can be called in process context in the following way:
br_fdb_add() -> __br_fdb_add() -> br_fdb_update() (if NTF_USE flag is set)
so we need to disable softirqs because there are softirq users of the
hash_lock. One easy way to reproduce this is to modify the bridge utility
to set NTF_USE, enable stp and then set maxageing to a low value so
br_fdb_cleanup() is called frequently and then just add new entries in
a loop. This happens because br_fdb_cleanup() is called from timer/softirq
context. The spin locks in br_fdb_update were _bh before commit f8ae737deea1
("[BRIDGE]: forwarding remove unneeded preempt and bh diasables")
and at the time that commit was correct because br_fdb_update() couldn't be
called from process context, but that changed after commit:
292d1398983f ("bridge: add NTF_USE support")
Using local_bh_disable/enable around br_fdb_update() allows us to keep
using the spin_lock/unlock in br_fdb_update for the fast-path.

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Fixes: 292d1398983f ("bridge: add NTF_USE support")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_fdb.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index 9203d5a..09152d1 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -705,9 +705,11 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge_port *p,
 	int err = 0;
 
 	if (ndm->ndm_flags & NTF_USE) {
+		local_bh_disable();
 		rcu_read_lock();
 		br_fdb_update(p->br, p, addr, vid, true);
 		rcu_read_unlock();
+		local_bh_enable();
 	} else {
 		spin_lock_bh(&p->br->hash_lock);
 		err = fdb_add_entry(p, addr, ndm->ndm_state,
-- 
2.1.0


[-- Attachment #4: net_318.mbox --]
[-- Type: Application/Octet-Stream, Size: 69475 bytes --]

From 3c47e81daf5a3bf32faecbf2019beb7f79064439 Mon Sep 17 00:00:00 2001
From: Vlad Yasevich <vyasevich@gmail.com>
Date: Sat, 2 May 2015 21:33:44 -0400
Subject: [PATCH 01/25] net: core: Correct an over-stringent device loop
 detection.

[ Upstream commit d66bf7dd27573ee5ea90484899ee952c19ccb194 ]

The code in __netdev_upper_dev_link() has an over-stringent
loop detection logic that actually prevents valid configurations
from working correctly.

In particular, the logic returns an error if an upper device
is already in the list of all upper devices for a given dev.
This particular check seems to be a overzealous as it disallows
perfectly valid configurations.  For example:
  # ip l a link eth0 name eth0.10 type vlan id 10
  # ip l a dev br0 typ bridge
  # ip l s eth0.10 master br0
  # ip l s eth0 master br0  <--- Will fail

If you switch the last two commands (add eth0 first), then both
will succeed.  If after that, you remove eth0 and try to re-add
it, it will fail!

It appears to be enough to simply check adj_list to keeps things
safe.

I've tried stacking multiple devices multiple times in all different
combinations, and either rx_handler registration prevented the stacking
of the device linking cought the error.

Signed-off-by: Vladislav Yasevich <vyasevic@redhat.com>
Acked-by: Jiri Pirko <jiri@resnulli.us>
Acked-by: Veaceslav Falico <vfalico@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 5cdbc1b..fb96258 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5080,7 +5080,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 	if (__netdev_find_adj(upper_dev, dev, &upper_dev->all_adj_list.upper))
 		return -EBUSY;
 
-	if (__netdev_find_adj(dev, upper_dev, &dev->all_adj_list.upper))
+	if (__netdev_find_adj(dev, upper_dev, &dev->adj_list.upper))
 		return -EEXIST;
 
 	if (master && netdev_master_upper_dev_get(dev))
-- 
2.1.0


From a119bae4e7e128c0c7653bb6e4fdd9296832c10b Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@plumgrid.com>
Date: Mon, 11 May 2015 23:25:16 -0700
Subject: [PATCH 02/25] x86: bpf_jit: fix FROM_BE16 and FROM_LE16/32
 instructions

[ Upstream commit 343f845b375989f1753f605902931fa939aa2223 ]

FROM_BE16:
'ror %reg, 8' doesn't clear upper bits of the register,
so use additional 'movzwl' insn to zero extend 16 bits into 64

FROM_LE16:
should zero extend lower 16 bits into 64 bit

FROM_LE32:
should zero extend lower 32 bits into 64 bit

Fixes: 89aa075832b0 ("net: sock: allow eBPF programs to be attached to sockets")
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/x86/net/bpf_jit_comp.c | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 3f62734..3de886f 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -558,6 +558,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 				if (is_ereg(dst_reg))
 					EMIT1(0x41);
 				EMIT3(0xC1, add_1reg(0xC8, dst_reg), 8);
+
+				/* emit 'movzwl eax, ax' */
+				if (is_ereg(dst_reg))
+					EMIT3(0x45, 0x0F, 0xB7);
+				else
+					EMIT2(0x0F, 0xB7);
+				EMIT1(add_2reg(0xC0, dst_reg, dst_reg));
 				break;
 			case 32:
 				/* emit 'bswap eax' to swap lower 4 bytes */
@@ -576,6 +583,27 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			break;
 
 		case BPF_ALU | BPF_END | BPF_FROM_LE:
+			switch (imm32) {
+			case 16:
+				/* emit 'movzwl eax, ax' to zero extend 16-bit
+				 * into 64 bit
+				 */
+				if (is_ereg(dst_reg))
+					EMIT3(0x45, 0x0F, 0xB7);
+				else
+					EMIT2(0x0F, 0xB7);
+				EMIT1(add_2reg(0xC0, dst_reg, dst_reg));
+				break;
+			case 32:
+				/* emit 'mov eax, eax' to clear upper 32-bits */
+				if (is_ereg(dst_reg))
+					EMIT1(0x45);
+				EMIT2(0x89, add_2reg(0xC0, dst_reg, dst_reg));
+				break;
+			case 64:
+				/* nop */
+				break;
+			}
 			break;
 
 			/* ST: *(u8*)(dst_reg + off) = imm */
-- 
2.1.0


From 354295ab418b0a31e0babf19d0d6d6cf1a661150 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@plumgrid.com>
Date: Fri, 22 May 2015 15:42:55 -0700
Subject: [PATCH 03/25] x86: bpf_jit: fix compilation of large bpf programs

[ Upstream commit 3f7352bf21f8fd7ba3e2fcef9488756f188e12be ]

x86 has variable length encoding. x86 JIT compiler is trying
to pick the shortest encoding for given bpf instruction.
While doing so the jump targets are changing, so JIT is doing
multiple passes over the program. Typical program needs 3 passes.
Some very short programs converge with 2 passes. Large programs
may need 4 or 5. But specially crafted bpf programs may hit the
pass limit and if the program converges on the last iteration
the JIT compiler will be producing an image full of 'int 3' insns.
Fix this corner case by doing final iteration over bpf program.

Fixes: 0a14842f5a3c ("net: filter: Just In Time compiler for x86-64")
Reported-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Tested-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/x86/net/bpf_jit_comp.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 3de886f..82003a3 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -964,7 +964,12 @@ void bpf_int_jit_compile(struct bpf_prog *prog)
 	}
 	ctx.cleanup_addr = proglen;
 
-	for (pass = 0; pass < 10; pass++) {
+	/* JITed image shrinks with every pass and the loop iterates
+	 * until the image stops shrinking. Very large bpf programs
+	 * may converge on the last pass. In such case do one more
+	 * pass to emit the final image
+	 */
+	for (pass = 0; pass < 10 || image; pass++) {
 		proglen = do_jit(prog, addrs, image, oldproglen, &ctx);
 		if (proglen <= 0) {
 			image = NULL;
-- 
2.1.0


From c88e9554a6ee237b1feac1330738f8f15ed3bb36 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 15 May 2015 16:30:41 -0700
Subject: [PATCH 04/25] net: phy: Allow EEE for all RGMII variants

[ Upstream commit 7e14069651591c81046ffaec13c3dac8cb70f5fb ]

RGMII interfaces come in multiple flavors: RGMII with transmit or
receive internal delay, no delays at all, or delays in both direction.

This change extends the initial check for PHY_INTERFACE_MODE_RGMII to
cover all of these variants since EEE should be allowed for any of these
modes, since it is a property of the RGMII, hence Gigabit PHY capability
more than the RGMII electrical interface and its delays.

Fixes: a59a4d192166 ("phy: add the EEE support and the way to access to the MMD registers")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index dc1f6f0..91d6d03 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -1050,13 +1050,14 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable)
 {
 	/* According to 802.3az,the EEE is supported only in full duplex-mode.
 	 * Also EEE feature is active when core is operating with MII, GMII
-	 * or RGMII. Internal PHYs are also allowed to proceed and should
-	 * return an error if they do not support EEE.
+	 * or RGMII (all kinds). Internal PHYs are also allowed to proceed and
+	 * should return an error if they do not support EEE.
 	 */
 	if ((phydev->duplex == DUPLEX_FULL) &&
 	    ((phydev->interface == PHY_INTERFACE_MODE_MII) ||
 	    (phydev->interface == PHY_INTERFACE_MODE_GMII) ||
-	    (phydev->interface == PHY_INTERFACE_MODE_RGMII) ||
+	    (phydev->interface >= PHY_INTERFACE_MODE_RGMII &&
+	     phydev->interface <= PHY_INTERFACE_MODE_RGMII_TXID) ||
 	     phy_is_internal(phydev))) {
 		int eee_lp, eee_cap, eee_adv;
 		u32 lp, cap, adv;
-- 
2.1.0


From 36823e70016a650148521c5322ff42570725431e Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Wed, 13 May 2015 14:19:42 +0200
Subject: [PATCH 05/25] rtnl/bond: don't send rtnl msg for unregistered iface

[ Upstream commit ed2a80ab7b76f11af0b2c6255709c4ebf164b667 ]

Before the patch, the command 'ip link add bond2 type bond mode 802.3ad'
causes the kernel to send a rtnl message for the bond2 interface, with an
ifindex 0.

'ip monitor' shows:
0: bond2: <BROADCAST,MULTICAST,MASTER> mtu 1500 state DOWN group default
    link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff
9: bond2@NONE: <BROADCAST,MULTICAST,MASTER> mtu 1500 qdisc noop state DOWN group default
    link/ether ea:3e:1f:53:92:7b brd ff:ff:ff:ff:ff:ff
[snip]

The patch fixes the spotted bug by checking in bond driver if the interface
is registered before calling the notifier chain.
It also adds a check in rtmsg_ifinfo() to prevent this kind of bug in the
future.

Fixes: d4261e565000 ("bonding: create netlink event when bonding option is changed")
CC: Jiri Pirko <jiri@resnulli.us>
Reported-by: Julien Meunier <julien.meunier@6wind.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_options.c | 2 +-
 net/core/rtnetlink.c               | 3 +++
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index b62697f..f1c5394 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -625,7 +625,7 @@ int __bond_opt_set(struct bonding *bond,
 out:
 	if (ret)
 		bond_opt_error_interpret(bond, opt, ret, val);
-	else
+	else if (bond->dev->reg_state == NETREG_REGISTERED)
 		call_netdevice_notifiers(NETDEV_CHANGEINFODATA, bond->dev);
 
 	return ret;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index c522f7a..24d3242 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2229,6 +2229,9 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change,
 	int err = -ENOBUFS;
 	size_t if_info_size;
 
+	if (dev->reg_state != NETREG_REGISTERED)
+		return;
+
 	skb = nlmsg_new((if_info_size = if_nlmsg_size(dev, 0)), flags);
 	if (skb == NULL)
 		goto errout;
-- 
2.1.0


From 5909100f73b8101c4048102fe839e3f266c821de Mon Sep 17 00:00:00 2001
From: Florent Fourcot <florent.fourcot@enst-bretagne.fr>
Date: Sat, 16 May 2015 00:24:59 +0200
Subject: [PATCH 06/25] tcp/ipv6: fix flow label setting in TIME_WAIT state

[ Upstream commit 21858cd02dabcf290564cbf4769b101eba54d7bb ]

commit 1d13a96c74fc ("ipv6: tcp: fix flowlabel value in ACK messages
send from TIME_WAIT") added the flow label in the last TCP packets.
Unfortunately, it was not casted properly.

This patch replace the buggy shift with be32_to_cpu/cpu_to_be32.

Fixes: 1d13a96c74fc ("ipv6: tcp: fix flowlabel value in ACK messages")
Reported-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Florent Fourcot <florent.fourcot@enst-bretagne.fr>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_minisocks.c | 2 +-
 net/ipv6/tcp_ipv6.c      | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 63d2680..71d001d 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -297,7 +297,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 			tw->tw_v6_daddr = sk->sk_v6_daddr;
 			tw->tw_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
 			tw->tw_tclass = np->tclass;
-			tw->tw_flowlabel = np->flow_label >> 12;
+			tw->tw_flowlabel = be32_to_cpu(np->flow_label & IPV6_FLOWLABEL_MASK);
 			tw->tw_ipv6only = sk->sk_ipv6only;
 		}
 #endif
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 79fe5851..a3f9f11 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -975,7 +975,7 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb)
 			tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
 			tcp_time_stamp + tcptw->tw_ts_offset,
 			tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw),
-			tw->tw_tclass, (tw->tw_flowlabel << 12));
+			tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel));
 
 	inet_twsk_put(tw);
 }
-- 
2.1.0


From d9f1967611424402bb47a30422f1c637bca2c57b Mon Sep 17 00:00:00 2001
From: Henning Rogge <hrogge@gmail.com>
Date: Mon, 18 May 2015 21:08:49 +0200
Subject: [PATCH 07/25] net/ipv6/udp: Fix ipv6 multicast socket filter
 regression

[ Upstream commit 33b4b015e1a1ca7a8fdce40af5e71642a8ea355c ]

Commit <5cf3d46192fc> ("udp: Simplify__udp*_lib_mcast_deliver")
simplified the filter for incoming IPv6 multicast but removed
the check of the local socket address and the UDP destination
address.

This patch restores the filter to prevent sockets bound to a IPv6
multicast IP to receive other UDP traffic link unicast.

Signed-off-by: Henning Rogge <hrogge@gmail.com>
Fixes: 5cf3d46192fc ("udp: Simplify__udp*_lib_mcast_deliver")
Cc: "David S. Miller" <davem@davemloft.net>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/udp.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index f6ba535..d651691 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -721,7 +721,9 @@ static bool __udp_v6_is_mcast_sock(struct net *net, struct sock *sk,
 	    (inet->inet_dport && inet->inet_dport != rmt_port) ||
 	    (!ipv6_addr_any(&sk->sk_v6_daddr) &&
 		    !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) ||
-	    (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif))
+	    (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif) ||
+	    (!ipv6_addr_any(&sk->sk_v6_rcv_saddr) &&
+		    !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr)))
 		return false;
 	if (!inet6_mc_check(sk, loc_addr, rmt_addr))
 		return false;
-- 
2.1.0


From 9fb2d46c311edd47adfebafe26e77aacc15d15b2 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 20 May 2015 17:13:33 +0200
Subject: [PATCH 08/25] net: sched: fix call_rcu() race on classifier module
 unloads

[ Upstream commit c78e1746d3ad7d548bdf3fe491898cc453911a49 ]

Vijay reported that a loop as simple as ...

  while true; do
    tc qdisc add dev foo root handle 1: prio
    tc filter add dev foo parent 1: u32 match u32 0 0  flowid 1
    tc qdisc del dev foo root
    rmmod cls_u32
  done

... will panic the kernel. Moreover, he bisected the change
apparently introducing it to 78fd1d0ab072 ("netlink: Re-add
locking to netlink_lookup() and seq walker").

The removal of synchronize_net() from the netlink socket
triggering the qdisc to be removed, seems to have uncovered
an RCU resp. module reference count race from the tc API.
Given that RCU conversion was done after e341694e3eb5 ("netlink:
Convert netlink_lookup() to use RCU protected hash table")
which added the synchronize_net() originally, occasion of
hitting the bug was less likely (not impossible though):

When qdiscs that i) support attaching classifiers and,
ii) have at least one of them attached, get deleted, they
invoke tcf_destroy_chain(), and thus call into ->destroy()
handler from a classifier module.

After RCU conversion, all classifier that have an internal
prio list, unlink them and initiate freeing via call_rcu()
deferral.

Meanhile, tcf_destroy() releases already reference to the
tp->ops->owner module before the queued RCU callback handler
has been invoked.

Subsequent rmmod on the classifier module is then not prevented
since all module references are already dropped.

By the time, the kernel invokes the RCU callback handler from
the module, that function address is then invalid.

One way to fix it would be to add an rcu_barrier() to
unregister_tcf_proto_ops() to wait for all pending call_rcu()s
to complete.

synchronize_rcu() is not appropriate as under heavy RCU
callback load, registered call_rcu()s could be deferred
longer than a grace period. In case we don't have any pending
call_rcu()s, the barrier is allowed to return immediately.

Since we came here via unregister_tcf_proto_ops(), there
are no users of a given classifier anymore. Further nested
call_rcu()s pointing into the module space are not being
done anywhere.

Only cls_bpf_delete_prog() may schedule a work item, to
unlock pages eventually, but that is not in the range/context
of cls_bpf anymore.

Fixes: 25d8c0d55f24 ("net: rcu-ify tcf_proto")
Fixes: 9888faefe132 ("net: sched: cls_basic use RCU")
Reported-by: Vijay Subramanian <subramanian.vijay@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: John Fastabend <john.r.fastabend@intel.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Thomas Graf <tgraf@suug.ch>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Alexei Starovoitov <ast@plumgrid.com>
Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index aad6a67..fae8870 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -81,6 +81,11 @@ int unregister_tcf_proto_ops(struct tcf_proto_ops *ops)
 	struct tcf_proto_ops *t;
 	int rc = -ENOENT;
 
+	/* Wait for outstanding call_rcu()s, if any, from a
+	 * tcf_proto_ops's destroy() handler.
+	 */
+	rcu_barrier();
+
 	write_lock(&cls_mod_lock);
 	list_for_each_entry(t, &tcf_proto_base, head) {
 		if (t == ops) {
-- 
2.1.0


From bfaf3f7522abd9c868035327b9bbe1a4c5deea42 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 22 May 2015 04:58:12 -0500
Subject: [PATCH 09/25] ipv4: Avoid crashing in ip_error

[ Upstream commit 381c759d9916c42959515ad34a6d467e24a88e93 ]

ip_error does not check if in_dev is NULL before dereferencing it.

IThe following sequence of calls is possible:
CPU A                          CPU B
ip_rcv_finish
    ip_route_input_noref()
        ip_route_input_slow()
                               inetdev_destroy()
    dst_input()

With the result that a network device can be destroyed while processing
an input packet.

A crash was triggered with only unicast packets in flight, and
forwarding enabled on the only network device.   The error condition
was created by the removal of the network device.

As such it is likely the that error code was -EHOSTUNREACH, and the
action taken by ip_error (if in_dev had been accessible) would have
been to not increment any counters and to have tried and likely failed
to send an icmp error as the network device is going away.

Therefore handle this weird case by just dropping the packet if
!in_dev.  It will result in dropping the packet sooner, and will not
result in an actual change of behavior.

Fixes: 251da4130115b ("ipv4: Cache ip_error() routes even when not forwarding.")
Reported-by: Vittorio Gambaletta <linuxbugs@vittgam.net>
Tested-by: Vittorio Gambaletta <linuxbugs@vittgam.net>
Signed-off-by: Vittorio Gambaletta <linuxbugs@vittgam.net>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d58dd0e..b7ac498 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -903,6 +903,10 @@ static int ip_error(struct sk_buff *skb)
 	bool send;
 	int code;
 
+	/* IP on this device is disabled. */
+	if (!in_dev)
+		goto out;
+
 	net = dev_net(rt->dst.dev);
 	if (!IN_DEV_FORWARD(in_dev)) {
 		switch (rt->dst.error) {
-- 
2.1.0


From 6f67f3d68cb7e8b7bd8ccdf20d30b36c1ac0aa85 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Fri, 22 May 2015 13:15:22 +0200
Subject: [PATCH 10/25] cdc_ncm: Fix tx_bytes statistics
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 44f6731d8b68fa02f5ed65eaceac41f8c3c9279e ]

The tx_curr_frame_payload field is u32. When we try to calculate a
small negative delta based on it, we end up with a positive integer
close to 2^32 instead.  So the tx_bytes pointer increases by about
2^32 for every transmitted frame.

Fix by calculating the delta as a signed long.

Cc: Ben Hutchings <ben.hutchings@codethink.co.uk>
Reported-by: Florian Bruhin <me@the-compiler.org>
Fixes: 7a1e890e2168 ("usbnet: Fix tx_bytes statistic running backward in cdc_ncm")
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ncm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index c3e4da9..8067b8f 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -1182,7 +1182,7 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign)
 	 * payload data instead.
 	 */
 	usbnet_set_skb_tx_stats(skb_out, n,
-				ctx->tx_curr_frame_payload - skb_out->len);
+				(long)ctx->tx_curr_frame_payload - skb_out->len);
 
 	return skb_out;
 
-- 
2.1.0


From 4fd2e1a7642c2ae23278b17e694b66f5d36f370b Mon Sep 17 00:00:00 2001
From: Thadeu Lima de Souza Cascardo <cascardo@redhat.com>
Date: Fri, 22 May 2015 12:18:59 -0300
Subject: [PATCH 11/25] bridge: fix parsing of MLDv2 reports

[ Upstream commit 47cc84ce0c2fe75c99ea5963c4b5704dd78ead54 ]

When more than a multicast address is present in a MLDv2 report, all but
the first address is ignored, because the code breaks out of the loop if
there has not been an error adding that address.

This has caused failures when two guests connected through the bridge
tried to communicate using IPv6. Neighbor discoveries would not be
transmitted to the other guest when both used a link-local address and a
static address.

This only happens when there is a MLDv2 querier in the network.

The fix will only break out of the loop when there is a failure adding a
multicast address.

The mdb before the patch:

dev ovirtmgmt port vnet0 grp ff02::1:ff7d:6603 temp
dev ovirtmgmt port vnet1 grp ff02::1:ff7d:6604 temp
dev ovirtmgmt port bond0.86 grp ff02::2 temp

After the patch:

dev ovirtmgmt port vnet0 grp ff02::1:ff7d:6603 temp
dev ovirtmgmt port vnet1 grp ff02::1:ff7d:6604 temp
dev ovirtmgmt port bond0.86 grp ff02::fb temp
dev ovirtmgmt port bond0.86 grp ff02::2 temp
dev ovirtmgmt port bond0.86 grp ff02::d temp
dev ovirtmgmt port vnet0 grp ff02::1:ff00:76 temp
dev ovirtmgmt port bond0.86 grp ff02::16 temp
dev ovirtmgmt port vnet1 grp ff02::1:ff00:77 temp
dev ovirtmgmt port bond0.86 grp ff02::1:ff00:def temp
dev ovirtmgmt port bond0.86 grp ff02::1:ffa1:40bf temp

Fixes: 08b202b67264 ("bridge br_multicast: IPv6 MLD support.")
Reported-by: Rik Theys <Rik.Theys@esat.kuleuven.be>
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@redhat.com>
Tested-by: Rik Theys <Rik.Theys@esat.kuleuven.be>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index c465876..cd02185 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1071,7 +1071,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br,
 
 		err = br_ip6_multicast_add_group(br, port, &grec->grec_mca,
 						 vid);
-		if (!err)
+		if (err)
 			break;
 	}
 
-- 
2.1.0


From ec3eede4f1fae98c3c39c660df85245b7b87aa2b Mon Sep 17 00:00:00 2001
From: Richard Cochran <richardcochran@gmail.com>
Date: Mon, 25 May 2015 11:55:43 +0200
Subject: [PATCH 12/25] net: dp83640: fix broken calibration routine.

[ Upstream commit 397a253af5031de4a4612210055935309af4472c ]

Currently, the calibration function that corrects the initial offsets
among multiple devices only works the first time.  If the function is
called more than once, the calibration fails and bogus offsets will be
programmed into the devices.

In a well hidden spot, the device documentation tells that trigger indexes
0 and 1 are special in allowing the TRIG_IF_LATE flag to actually work.

This patch fixes the issue by using one of the special triggers during the
recalibration method.

Signed-off-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/dp83640.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index e22e602..5eb3c8e 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -47,7 +47,7 @@
 #define PSF_TX		0x1000
 #define EXT_EVENT	1
 #define CAL_EVENT	7
-#define CAL_TRIGGER	7
+#define CAL_TRIGGER	1
 #define DP83640_N_PINS	12
 
 #define MII_DP83640_MICR 0x11
-- 
2.1.0


From 62fc85a98dd2d275a40ae0218dee83401850e21e Mon Sep 17 00:00:00 2001
From: Richard Cochran <richardcochran@gmail.com>
Date: Mon, 25 May 2015 11:55:44 +0200
Subject: [PATCH 13/25] net: dp83640: reinforce locking rules.

[ Upstream commit a935865c828c8cd20501f618c69f659a5b6d6a5f ]

Callers of the ext_write function are supposed to hold a mutex that
protects the state of the dialed page, but one caller was missing the
lock from the very start, and over time the code has been changed
without following the rule.  This patch cleans up the call sites in
violation of the rule.

Signed-off-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/dp83640.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index 5eb3c8e..4f3cf1b 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -495,7 +495,9 @@ static int ptp_dp83640_enable(struct ptp_clock_info *ptp,
 			else
 				evnt |= EVNT_RISE;
 		}
+		mutex_lock(&clock->extreg_lock);
 		ext_write(0, phydev, PAGE5, PTP_EVNT, evnt);
+		mutex_unlock(&clock->extreg_lock);
 		return 0;
 
 	case PTP_CLK_REQ_PEROUT:
@@ -531,6 +533,8 @@ static u8 status_frame_src[6] = { 0x08, 0x00, 0x17, 0x0B, 0x6B, 0x0F };
 
 static void enable_status_frames(struct phy_device *phydev, bool on)
 {
+	struct dp83640_private *dp83640 = phydev->priv;
+	struct dp83640_clock *clock = dp83640->clock;
 	u16 cfg0 = 0, ver;
 
 	if (on)
@@ -538,9 +542,13 @@ static void enable_status_frames(struct phy_device *phydev, bool on)
 
 	ver = (PSF_PTPVER & VERSIONPTP_MASK) << VERSIONPTP_SHIFT;
 
+	mutex_lock(&clock->extreg_lock);
+
 	ext_write(0, phydev, PAGE5, PSF_CFG0, cfg0);
 	ext_write(0, phydev, PAGE6, PSF_CFG1, ver);
 
+	mutex_unlock(&clock->extreg_lock);
+
 	if (!phydev->attached_dev) {
 		pr_warn("expected to find an attached netdevice\n");
 		return;
@@ -1172,11 +1180,18 @@ static int dp83640_config_init(struct phy_device *phydev)
 
 	if (clock->chosen && !list_empty(&clock->phylist))
 		recalibrate(clock);
-	else
+	else {
+		mutex_lock(&clock->extreg_lock);
 		enable_broadcast(phydev, clock->page, 1);
+		mutex_unlock(&clock->extreg_lock);
+	}
 
 	enable_status_frames(phydev, true);
+
+	mutex_lock(&clock->extreg_lock);
 	ext_write(0, phydev, PAGE4, PTP_CTL, PTP_ENABLE);
+	mutex_unlock(&clock->extreg_lock);
+
 	return 0;
 }
 
-- 
2.1.0


From 421ed4f658f31d13182875a15765889d33afd7d6 Mon Sep 17 00:00:00 2001
From: Richard Cochran <richardcochran@gmail.com>
Date: Mon, 25 May 2015 11:55:45 +0200
Subject: [PATCH 14/25] net: dp83640: fix improper double spin locking.

[ Upstream commit adbe088f6f8b0b7701fe07f51fe6f2bd602a6665 ]

A pair of nested spin locks was introduced in commit 63502b8d0
"dp83640: Fix receive timestamp race condition".

Unfortunately the 'flags' parameter was reused for the inner lock,
clobbering the originally saved IRQ state.  This patch fixes the issue
by changing the inner lock to plain spin_lock without irqsave.

Signed-off-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/dp83640.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index 4f3cf1b..c5789cd 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -845,7 +845,7 @@ static void decode_rxts(struct dp83640_private *dp83640,
 	list_del_init(&rxts->list);
 	phy2rxts(phy_rxts, rxts);
 
-	spin_lock_irqsave(&dp83640->rx_queue.lock, flags);
+	spin_lock(&dp83640->rx_queue.lock);
 	skb_queue_walk(&dp83640->rx_queue, skb) {
 		struct dp83640_skb_info *skb_info;
 
@@ -860,7 +860,7 @@ static void decode_rxts(struct dp83640_private *dp83640,
 			break;
 		}
 	}
-	spin_unlock_irqrestore(&dp83640->rx_queue.lock, flags);
+	spin_unlock(&dp83640->rx_queue.lock);
 
 	if (!shhwtstamps)
 		list_add_tail(&rxts->list, &dp83640->rxts);
-- 
2.1.0


From 6faf5700606abea0118defdeb2e65c06dac52a02 Mon Sep 17 00:00:00 2001
From: Mark Salyzyn <salyzyn@android.com>
Date: Tue, 26 May 2015 08:22:19 -0700
Subject: [PATCH 15/25] unix/caif: sk_socket can disappear when state is
 unlocked

[ Upstream commit b48732e4a48d80ed4a14812f0bab09560846514e ]

got a rare NULL pointer dereference in clear_bit

Signed-off-by: Mark Salyzyn <salyzyn@android.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
----
v2: switch to sock_flag(sk, SOCK_DEAD) and added net/caif/caif_socket.c
v3: return -ECONNRESET in upstream caller of wait function for SOCK_DEAD
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/caif/caif_socket.c | 8 ++++++++
 net/unix/af_unix.c     | 8 ++++++++
 2 files changed, 16 insertions(+)

diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 765c781..5e10ee0 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -330,6 +330,10 @@ static long caif_stream_data_wait(struct sock *sk, long timeo)
 		release_sock(sk);
 		timeo = schedule_timeout(timeo);
 		lock_sock(sk);
+
+		if (sock_flag(sk, SOCK_DEAD))
+			break;
+
 		clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
 	}
 
@@ -374,6 +378,10 @@ static int caif_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 		struct sk_buff *skb;
 
 		lock_sock(sk);
+		if (sock_flag(sk, SOCK_DEAD)) {
+			err = -ECONNRESET;
+			goto unlock;
+		}
 		skb = skb_dequeue(&sk->sk_receive_queue);
 		caif_check_flow_release(sk);
 
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index e968843..8232118 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1899,6 +1899,10 @@ static long unix_stream_data_wait(struct sock *sk, long timeo,
 		unix_state_unlock(sk);
 		timeo = freezable_schedule_timeout(timeo);
 		unix_state_lock(sk);
+
+		if (sock_flag(sk, SOCK_DEAD))
+			break;
+
 		clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
 	}
 
@@ -1963,6 +1967,10 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 		struct sk_buff *skb, *last;
 
 		unix_state_lock(sk);
+		if (sock_flag(sk, SOCK_DEAD)) {
+			err = -ECONNRESET;
+			goto unlock;
+		}
 		last = skb = skb_peek(&sk->sk_receive_queue);
 again:
 		if (skb == NULL) {
-- 
2.1.0


From 567e7bac192bf0d7a70663f0d8d657ecf3401846 Mon Sep 17 00:00:00 2001
From: Ross Lagerwall <ross.lagerwall@citrix.com>
Date: Wed, 27 May 2015 11:44:32 +0100
Subject: [PATCH 16/25] xen/netback: Properly initialize credit_bytes

[ Upstream commit ce0e5c522d3924090c20e774359809a7aa08c44c ]

Commit e9ce7cb6b107 ("xen-netback: Factor queue-specific data into queue
struct") introduced a regression when moving queue-specific data into
the queue struct by failing to set the credit_bytes field. This
prevented bandwidth limiting from working. Initialize the field as it
was done before multiqueue support was added.

Signed-off-by: Ross Lagerwall <ross.lagerwall@citrix.com>
Acked-by: Wei Liu <wei.liu2@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netback/xenbus.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index c047282..7cda7a4 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -735,6 +735,7 @@ static void connect(struct backend_info *be)
 			goto err;
 		}
 
+		queue->credit_bytes = credit_bytes;
 		queue->remaining_credit = credit_bytes;
 		queue->credit_usec = credit_usec;
 
-- 
2.1.0


From 57ba459ed39186e77cdb6183cf78f8624a99c2d0 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Tue, 26 May 2015 16:08:48 -0700
Subject: [PATCH 17/25] net_sched: invoke ->attach() after setting dev->qdisc

[ Upstream commit 86e363dc3b50bfd50a1f315934583fbda673ab8d ]

For mq qdisc, we add per tx queue qdisc to root qdisc
for display purpose, however, that happens too early,
before the new dev->qdisc is finally set, this causes
q->list points to an old root qdisc which is going to be
freed right before assigning with a new one.

Fix this by moving ->attach() after setting dev->qdisc.

For the record, this fixes the following crash:

 ------------[ cut here ]------------
 WARNING: CPU: 1 PID: 975 at lib/list_debug.c:59 __list_del_entry+0x5a/0x98()
 list_del corruption. prev->next should be ffff8800d1998ae8, but was 6b6b6b6b6b6b6b6b
 CPU: 1 PID: 975 Comm: tc Not tainted 4.1.0-rc4+ #1019
 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
  0000000000000009 ffff8800d73fb928 ffffffff81a44e7f 0000000047574756
  ffff8800d73fb978 ffff8800d73fb968 ffffffff810790da ffff8800cfc4cd20
  ffffffff814e725b ffff8800d1998ae8 ffffffff82381250 0000000000000000
 Call Trace:
  [<ffffffff81a44e7f>] dump_stack+0x4c/0x65
  [<ffffffff810790da>] warn_slowpath_common+0x9c/0xb6
  [<ffffffff814e725b>] ? __list_del_entry+0x5a/0x98
  [<ffffffff81079162>] warn_slowpath_fmt+0x46/0x48
  [<ffffffff81820eb0>] ? dev_graft_qdisc+0x5e/0x6a
  [<ffffffff814e725b>] __list_del_entry+0x5a/0x98
  [<ffffffff814e72a7>] list_del+0xe/0x2d
  [<ffffffff81822f05>] qdisc_list_del+0x1e/0x20
  [<ffffffff81820cd1>] qdisc_destroy+0x30/0xd6
  [<ffffffff81822676>] qdisc_graft+0x11d/0x243
  [<ffffffff818233c1>] tc_get_qdisc+0x1a6/0x1d4
  [<ffffffff810b5eaf>] ? mark_lock+0x2e/0x226
  [<ffffffff817ff8f5>] rtnetlink_rcv_msg+0x181/0x194
  [<ffffffff817ff72e>] ? rtnl_lock+0x17/0x19
  [<ffffffff817ff72e>] ? rtnl_lock+0x17/0x19
  [<ffffffff817ff774>] ? __rtnl_unlock+0x17/0x17
  [<ffffffff81855dc6>] netlink_rcv_skb+0x4d/0x93
  [<ffffffff817ff756>] rtnetlink_rcv+0x26/0x2d
  [<ffffffff818544b2>] netlink_unicast+0xcb/0x150
  [<ffffffff81161db9>] ? might_fault+0x59/0xa9
  [<ffffffff81854f78>] netlink_sendmsg+0x4fa/0x51c
  [<ffffffff817d6e09>] sock_sendmsg_nosec+0x12/0x1d
  [<ffffffff817d8967>] sock_sendmsg+0x29/0x2e
  [<ffffffff817d8cf3>] ___sys_sendmsg+0x1b4/0x23a
  [<ffffffff8100a1b8>] ? native_sched_clock+0x35/0x37
  [<ffffffff810a1d83>] ? sched_clock_local+0x12/0x72
  [<ffffffff810a1fd4>] ? sched_clock_cpu+0x9e/0xb7
  [<ffffffff810def2a>] ? current_kernel_time+0xe/0x32
  [<ffffffff810b4bc5>] ? lock_release_holdtime.part.29+0x71/0x7f
  [<ffffffff810ddebf>] ? read_seqcount_begin.constprop.27+0x5f/0x76
  [<ffffffff810b6292>] ? trace_hardirqs_on_caller+0x17d/0x199
  [<ffffffff811b14d5>] ? __fget_light+0x50/0x78
  [<ffffffff817d9808>] __sys_sendmsg+0x42/0x60
  [<ffffffff817d9838>] SyS_sendmsg+0x12/0x1c
  [<ffffffff81a50e97>] system_call_fastpath+0x12/0x6f
 ---[ end trace ef29d3fb28e97ae7 ]---

For long term, we probably need to clean up the qdisc_graft() code
in case it hides other bugs like this.

Fixes: 95dc19299f74 ("pkt_sched: give visibility to mq slave qdiscs")
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_api.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 76f402e..a25fae3 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -815,10 +815,8 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent,
 		if (dev->flags & IFF_UP)
 			dev_deactivate(dev);
 
-		if (new && new->ops->attach) {
-			new->ops->attach(new);
-			num_q = 0;
-		}
+		if (new && new->ops->attach)
+			goto skip;
 
 		for (i = 0; i < num_q; i++) {
 			struct netdev_queue *dev_queue = dev_ingress_queue(dev);
@@ -834,12 +832,16 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent,
 				qdisc_destroy(old);
 		}
 
+skip:
 		if (!ingress) {
 			notify_and_destroy(net, skb, n, classid,
 					   dev->qdisc, new);
 			if (new && !new->ops->attach)
 				atomic_inc(&new->refcnt);
 			dev->qdisc = new ? : &noop_qdisc;
+
+			if (new && new->ops->attach)
+				new->ops->attach(new);
 		} else {
 			notify_and_destroy(net, skb, n, classid, old, new);
 		}
-- 
2.1.0


From 0bc21e7829d19b1a88e9bb6b7a5c1ef08a48f985 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Date: Tue, 26 May 2015 17:30:17 -0600
Subject: [PATCH 18/25] sctp: Fix mangled IPv4 addresses on a IPv6 listening
 socket

[ Upstream commit 9302d7bb0c5cd46be5706859301f18c137b2439f ]

sctp_v4_map_v6 was subtly writing and reading from members
of a union in a way the clobbered data it needed to read before
it read it.

Zeroing the v6 flowinfo overwrites the v4 sin_addr with 0, meaning
that every place that calls sctp_v4_map_v6 gets ::ffff:0.0.0.0 as the
result.

Reorder things to guarantee correct behaviour no matter what the
union layout is.

This impacts user space clients that open an IPv6 SCTP socket and
receive IPv4 connections. Prior to 299ee user space would see a
sockaddr with AF_INET and a correct address, after 299ee the sockaddr
is AF_INET6, but the address is wrong.

Fixes: 299ee123e198 (sctp: Fixup v4mapped behaviour to comply with Sock API)
Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/sctp.h | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 856f01c..230775f 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -571,11 +571,14 @@ static inline void sctp_v6_map_v4(union sctp_addr *addr)
 /* Map v4 address to v4-mapped v6 address */
 static inline void sctp_v4_map_v6(union sctp_addr *addr)
 {
+	__be16 port;
+
+	port = addr->v4.sin_port;
+	addr->v6.sin6_addr.s6_addr32[3] = addr->v4.sin_addr.s_addr;
+	addr->v6.sin6_port = port;
 	addr->v6.sin6_family = AF_INET6;
 	addr->v6.sin6_flowinfo = 0;
 	addr->v6.sin6_scope_id = 0;
-	addr->v6.sin6_port = addr->v4.sin_port;
-	addr->v6.sin6_addr.s6_addr32[3] = addr->v4.sin_addr.s_addr;
 	addr->v6.sin6_addr.s6_addr32[0] = 0;
 	addr->v6.sin6_addr.s6_addr32[1] = 0;
 	addr->v6.sin6_addr.s6_addr32[2] = htonl(0x0000ffff);
-- 
2.1.0


From afeb5e58c20d8ab45d34cf93367faf302a28f0a3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 28 May 2015 04:42:54 -0700
Subject: [PATCH 19/25] bridge: fix br_multicast_query_expired() bug
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 71d9f6149cac8fc6646adfb2a6f3b0de6ddd23f6 ]

br_multicast_query_expired() querier argument is a pointer to
a struct bridge_mcast_querier :

struct bridge_mcast_querier {
        struct br_ip addr;
        struct net_bridge_port __rcu    *port;
};

Intent of the code was to clear port field, not the pointer to querier.

Fixes: 2cd4143192e8 ("bridge: memorize and export selected IGMP/MLD querier port")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Thadeu Lima de Souza Cascardo <cascardo@redhat.com>
Acked-by: Linus Lüssing <linus.luessing@c0d3.blue>
Cc: Linus Lüssing <linus.luessing@web.de>
Cc: Steinar H. Gunderson <sesse@samfundet.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index cd02185..b0aee78 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1821,7 +1821,7 @@ static void br_multicast_query_expired(struct net_bridge *br,
 	if (query->startup_sent < br->multicast_startup_query_count)
 		query->startup_sent++;
 
-	RCU_INIT_POINTER(querier, NULL);
+	RCU_INIT_POINTER(querier->port, NULL);
 	br_multicast_send_query(br, NULL, query);
 	spin_unlock(&br->multicast_lock);
 }
-- 
2.1.0


From 674860baf020f984e3c6ebfd551da3b03b13a9a7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 30 May 2015 09:16:53 -0700
Subject: [PATCH 20/25] udp: fix behavior of wrong checksums

[ Upstream commit beb39db59d14990e401e235faf66a6b9b31240b0 ]

We have two problems in UDP stack related to bogus checksums :

1) We return -EAGAIN to application even if receive queue is not empty.
   This breaks applications using edge trigger epoll()

2) Under UDP flood, we can loop forever without yielding to other
   processes, potentially hanging the host, especially on non SMP.

This patch is an attempt to make things better.

We might in the future add extra support for rt applications
wanting to better control time spent doing a recv() in a hostile
environment. For example we could validate checksums before queuing
packets in socket receive queue.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 6 ++----
 net/ipv6/udp.c | 6 ++----
 2 files changed, 4 insertions(+), 8 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index cd0db54..52d2db8 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1336,10 +1336,8 @@ csum_copy_err:
 	}
 	unlock_sock_fast(sk, slow);
 
-	if (noblock)
-		return -EAGAIN;
-
-	/* starting over for a new packet */
+	/* starting over for a new packet, but check if we need to yield */
+	cond_resched();
 	msg->msg_flags &= ~MSG_TRUNC;
 	goto try_again;
 }
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index d651691..dd530f0 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -514,10 +514,8 @@ csum_copy_err:
 	}
 	unlock_sock_fast(sk, slow);
 
-	if (noblock)
-		return -EAGAIN;
-
-	/* starting over for a new packet */
+	/* starting over for a new packet, but check if we need to yield */
+	cond_resched();
 	msg->msg_flags &= ~MSG_TRUNC;
 	goto try_again;
 }
-- 
2.1.0


From dfb621e25b595b3f24fe80e5e69f029fdf8db52b Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Fri, 29 May 2015 13:47:07 -0400
Subject: [PATCH 21/25] tcp: fix child sockets to use system default congestion
 control if not set

[ Upstream commit 9f950415e4e28e7cfae2e416b43e862e8101d996 ]

Linux 3.17 and earlier are explicitly engineered so that if the app
doesn't specifically request a CC module on a listener before the SYN
arrives, then the child gets the system default CC when the connection
is established. See tcp_init_congestion_control() in 3.17 or earlier,
which says "if no choice made yet assign the current value set as
default". The change ("net: tcp: assign tcp cong_ops when tcp sk is
created") altered these semantics, so that children got their parent
listener's congestion control even if the system default had changed
after the listener was created.

This commit returns to those original semantics from 3.17 and earlier,
since they are the original semantics from 2007 in 4d4d3d1e8 ("[TCP]:
Congestion control initialization."), and some Linux congestion
control workflows depend on that.

In summary, if a listener socket specifically sets TCP_CONGESTION to
"x", or the route locks the CC module to "x", then the child gets
"x". Otherwise the child gets current system default from
net.ipv4.tcp_congestion_control. That's the behavior in 3.17 and
earlier, and this commit restores that.

Fixes: 55d8694fa82c ("net: tcp: assign tcp cong_ops when tcp sk is created")
Cc: Florian Westphal <fw@strlen.de>
Cc: Daniel Borkmann <dborkman@redhat.com>
Cc: Glenn Judd <glenn.judd@morganstanley.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_connection_sock.h | 3 ++-
 net/ipv4/tcp_cong.c                | 6 ++++--
 net/ipv4/tcp_minisocks.c           | 3 ++-
 3 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 848e85c..24d5c09 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -98,7 +98,8 @@ struct inet_connection_sock {
 	const struct tcp_congestion_ops *icsk_ca_ops;
 	const struct inet_connection_sock_af_ops *icsk_af_ops;
 	unsigned int		  (*icsk_sync_mss)(struct sock *sk, u32 pmtu);
-	__u8			  icsk_ca_state;
+	__u8			  icsk_ca_state:7,
+				  icsk_ca_setsockopt:1;
 	__u8			  icsk_retransmits;
 	__u8			  icsk_pending;
 	__u8			  icsk_backoff;
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index b1c5970..b3316c8 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -248,9 +248,10 @@ int tcp_set_congestion_control(struct sock *sk, const char *name)
 	ca = tcp_ca_find(name);
 
 	/* no change asking for existing value */
-	if (ca == icsk->icsk_ca_ops)
+	if (ca == icsk->icsk_ca_ops) {
+		icsk->icsk_ca_setsockopt = 1;
 		goto out;
-
+	}
 #ifdef CONFIG_MODULES
 	/* not found attempt to autoload module */
 	if (!ca && capable(CAP_NET_ADMIN)) {
@@ -273,6 +274,7 @@ int tcp_set_congestion_control(struct sock *sk, const char *name)
 	else {
 		tcp_cleanup_congestion_control(sk);
 		icsk->icsk_ca_ops = ca;
+		icsk->icsk_ca_setsockopt = 1;
 
 		if (sk->sk_state != TCP_CLOSE && icsk->icsk_ca_ops->init)
 			icsk->icsk_ca_ops->init(sk);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 71d001d..2f66671 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -451,7 +451,8 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
 		newtp->snd_cwnd = TCP_INIT_CWND;
 		newtp->snd_cwnd_cnt = 0;
 
-		if (!try_module_get(newicsk->icsk_ca_ops->owner))
+		if (!newicsk->icsk_ca_setsockopt ||
+		    !try_module_get(newicsk->icsk_ca_ops->owner))
 			tcp_assign_congestion_control(newsk);
 
 		tcp_set_ca_state(newsk, TCP_CA_Open);
-- 
2.1.0


From 2b0e3f1c741929d210c58bdf3db6105918ae70b0 Mon Sep 17 00:00:00 2001
From: Ian Campbell <Ian.Campbell@citrix.com>
Date: Mon, 1 Jun 2015 11:30:24 +0100
Subject: [PATCH 22/25] xen: netback: read hotplug script once at start of day.

[ Upstream commit 31a418986a5852034d520a5bab546821ff1ccf3d ]

When we come to tear things down in netback_remove() and generate the
uevent it is possible that the xenstore directory has already been
removed (details below).

In such cases netback_uevent() won't be able to read the hotplug
script and will write a xenstore error node.

A recent change to the hypervisor exposed this race such that we now
sometimes lose it (where apparently we didn't ever before).

Instead read the hotplug script configuration during setup and use it
for the lifetime of the backend device.

The apparently more obvious fix of moving the transition to
state=Closed in netback_remove() to after the uevent does not work
because it is possible that we are already in state=Closed (in
reaction to the guest having disconnected as it shutdown). Being
already in Closed means the toolstack is at liberty to start tearing
down the xenstore directories. In principal it might be possible to
arrange to unregister the device sooner (e.g on transition to Closing)
such that xenstore would still be there but this state machine is
fragile and prone to anger...

A modern Xen system only relies on the hotplug uevent for driver
domains, when the backend is in the same domain as the toolstack it
will run the necessary setup/teardown directly in the correct sequence
wrt xenstore changes.

Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Acked-by: Wei Liu <wei.liu2@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netback/xenbus.c | 33 +++++++++++++++++++--------------
 1 file changed, 19 insertions(+), 14 deletions(-)

diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index 7cda7a4..d9d1e2a 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -34,6 +34,8 @@ struct backend_info {
 	enum xenbus_state frontend_state;
 	struct xenbus_watch hotplug_status_watch;
 	u8 have_hotplug_status_watch:1;
+
+	const char *hotplug_script;
 };
 
 static int connect_rings(struct backend_info *be, struct xenvif_queue *queue);
@@ -236,6 +238,7 @@ static int netback_remove(struct xenbus_device *dev)
 		xenvif_free(be->vif);
 		be->vif = NULL;
 	}
+	kfree(be->hotplug_script);
 	kfree(be);
 	dev_set_drvdata(&dev->dev, NULL);
 	return 0;
@@ -253,6 +256,7 @@ static int netback_probe(struct xenbus_device *dev,
 	struct xenbus_transaction xbt;
 	int err;
 	int sg;
+	const char *script;
 	struct backend_info *be = kzalloc(sizeof(struct backend_info),
 					  GFP_KERNEL);
 	if (!be) {
@@ -345,6 +349,15 @@ static int netback_probe(struct xenbus_device *dev,
 	if (err)
 		pr_debug("Error writing multi-queue-max-queues\n");
 
+	script = xenbus_read(XBT_NIL, dev->nodename, "script", NULL);
+	if (IS_ERR(script)) {
+		err = PTR_ERR(script);
+		xenbus_dev_fatal(dev, err, "reading script");
+		goto fail;
+	}
+
+	be->hotplug_script = script;
+
 	err = xenbus_switch_state(dev, XenbusStateInitWait);
 	if (err)
 		goto fail;
@@ -377,22 +390,14 @@ static int netback_uevent(struct xenbus_device *xdev,
 			  struct kobj_uevent_env *env)
 {
 	struct backend_info *be = dev_get_drvdata(&xdev->dev);
-	char *val;
 
-	val = xenbus_read(XBT_NIL, xdev->nodename, "script", NULL);
-	if (IS_ERR(val)) {
-		int err = PTR_ERR(val);
-		xenbus_dev_fatal(xdev, err, "reading script");
-		return err;
-	} else {
-		if (add_uevent_var(env, "script=%s", val)) {
-			kfree(val);
-			return -ENOMEM;
-		}
-		kfree(val);
-	}
+	if (!be)
+		return 0;
+
+	if (add_uevent_var(env, "script=%s", be->hotplug_script))
+		return -ENOMEM;
 
-	if (!be || !be->vif)
+	if (!be->vif)
 		return 0;
 
 	return add_uevent_var(env, "vif=%s", be->vif->dev->name);
-- 
2.1.0


From 2c62fcb347574ec69adad3a2f20751c1d71ad653 Mon Sep 17 00:00:00 2001
From: Shawn Bohrer <sbohrer@rgmadvisors.com>
Date: Wed, 3 Jun 2015 16:27:38 -0500
Subject: [PATCH 23/25] ipv4/udp: Verify multicast group is ours in
 upd_v4_early_demux()

[ Upstream commit 6e540309326188f769e03bb4c6dd8ff6752930c2 ]

421b3885bf6d56391297844f43fb7154a6396e12 "udp: ipv4: Add udp early
demux" introduced a regression that allowed sockets bound to INADDR_ANY
to receive packets from multicast groups that the socket had not joined.
For example a socket that had joined 224.168.2.9 could also receive
packets from 225.168.2.9 despite not having joined that group if
ip_early_demux is enabled.

Fix this by calling ip_check_mc_rcu() in udp_v4_early_demux() to verify
that the multicast packet is indeed ours.

Signed-off-by: Shawn Bohrer <sbohrer@rgmadvisors.com>
Reported-by: Yurij M. Plotnikov <Yurij.Plotnikov@oktetlabs.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 52d2db8..c5e3194 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -90,6 +90,7 @@
 #include <linux/socket.h>
 #include <linux/sockios.h>
 #include <linux/igmp.h>
+#include <linux/inetdevice.h>
 #include <linux/in.h>
 #include <linux/errno.h>
 #include <linux/timer.h>
@@ -1948,6 +1949,7 @@ void udp_v4_early_demux(struct sk_buff *skb)
 	struct sock *sk;
 	struct dst_entry *dst;
 	int dif = skb->dev->ifindex;
+	int ours;
 
 	/* validate the packet */
 	if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr)))
@@ -1957,14 +1959,24 @@ void udp_v4_early_demux(struct sk_buff *skb)
 	uh = udp_hdr(skb);
 
 	if (skb->pkt_type == PACKET_BROADCAST ||
-	    skb->pkt_type == PACKET_MULTICAST)
+	    skb->pkt_type == PACKET_MULTICAST) {
+		struct in_device *in_dev = __in_dev_get_rcu(skb->dev);
+
+		if (!in_dev)
+			return;
+
+		ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr,
+				       iph->protocol);
+		if (!ours)
+			return;
 		sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr,
 						   uh->source, iph->saddr, dif);
-	else if (skb->pkt_type == PACKET_HOST)
+	} else if (skb->pkt_type == PACKET_HOST) {
 		sk = __udp4_lib_demux_lookup(net, uh->dest, iph->daddr,
 					     uh->source, iph->saddr, dif);
-	else
+	} else {
 		return;
+	}
 
 	if (!sk)
 		return;
-- 
2.1.0


From 5f04e797a2b5b1924b5fb28cfa1f08ed7faddf1c Mon Sep 17 00:00:00 2001
From: Sriharsha Basavapatna <sriharsha.basavapatna@avagotech.com>
Date: Fri, 5 Jun 2015 15:33:59 +0530
Subject: [PATCH 24/25] be2net: Replace dma/pci_alloc_coherent() calls with
 dma_zalloc_coherent()

[ Upstream commit e51000db4c880165eab06ec0990605f24e75203f ]

There are several places in the driver (all in control paths) where
coherent dma memory is being allocated using either dma_alloc_coherent()
or the deprecated pci_alloc_consistent(). All these calls should be
changed to use dma_zalloc_coherent() to avoid uninitialized fields in
data structures backed by this memory.

Reported-by: Joerg Roedel <jroedel@suse.de>
Tested-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Sriharsha Basavapatna <sriharsha.basavapatna@avagotech.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/emulex/benet/be_cmds.c    | 87 +++++++++++++++-----------
 drivers/net/ethernet/emulex/benet/be_ethtool.c | 18 +++---
 drivers/net/ethernet/emulex/benet/be_main.c    | 16 ++---
 3 files changed, 68 insertions(+), 53 deletions(-)

diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index fead5c6..9c827b7 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -1705,9 +1705,9 @@ int be_cmd_get_regs(struct be_adapter *adapter, u32 buf_len, void *buf)
 	total_size = buf_len;
 
 	get_fat_cmd.size = sizeof(struct be_cmd_req_get_fat) + 60*1024;
-	get_fat_cmd.va = pci_alloc_consistent(adapter->pdev,
-					      get_fat_cmd.size,
-					      &get_fat_cmd.dma);
+	get_fat_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+					     get_fat_cmd.size,
+					     &get_fat_cmd.dma, GFP_ATOMIC);
 	if (!get_fat_cmd.va) {
 		dev_err(&adapter->pdev->dev,
 			"Memory allocation failure while reading FAT data\n");
@@ -1752,8 +1752,8 @@ int be_cmd_get_regs(struct be_adapter *adapter, u32 buf_len, void *buf)
 		log_offset += buf_size;
 	}
 err:
-	pci_free_consistent(adapter->pdev, get_fat_cmd.size,
-			    get_fat_cmd.va, get_fat_cmd.dma);
+	dma_free_coherent(&adapter->pdev->dev, get_fat_cmd.size,
+			  get_fat_cmd.va, get_fat_cmd.dma);
 	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
@@ -2223,12 +2223,12 @@ int be_cmd_read_port_transceiver_data(struct be_adapter *adapter,
 		return -EINVAL;
 
 	cmd.size = sizeof(struct be_cmd_resp_port_type);
-	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma);
+	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				     GFP_ATOMIC);
 	if (!cmd.va) {
 		dev_err(&adapter->pdev->dev, "Memory allocation failed\n");
 		return -ENOMEM;
 	}
-	memset(cmd.va, 0, cmd.size);
 
 	spin_lock_bh(&adapter->mcc_lock);
 
@@ -2253,7 +2253,7 @@ int be_cmd_read_port_transceiver_data(struct be_adapter *adapter,
 	}
 err:
 	spin_unlock_bh(&adapter->mcc_lock);
-	pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
+	dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va, cmd.dma);
 	return status;
 }
 
@@ -2702,7 +2702,8 @@ int be_cmd_get_phy_info(struct be_adapter *adapter)
 		goto err;
 	}
 	cmd.size = sizeof(struct be_cmd_req_get_phy_info);
-	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma);
+	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				     GFP_ATOMIC);
 	if (!cmd.va) {
 		dev_err(&adapter->pdev->dev, "Memory alloc failure\n");
 		status = -ENOMEM;
@@ -2736,7 +2737,7 @@ int be_cmd_get_phy_info(struct be_adapter *adapter)
 				BE_SUPPORTED_SPEED_1GBPS;
 		}
 	}
-	pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
+	dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va, cmd.dma);
 err:
 	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
@@ -2787,8 +2788,9 @@ int be_cmd_get_cntl_attributes(struct be_adapter *adapter)
 
 	memset(&attribs_cmd, 0, sizeof(struct be_dma_mem));
 	attribs_cmd.size = sizeof(struct be_cmd_resp_cntl_attribs);
-	attribs_cmd.va = pci_alloc_consistent(adapter->pdev, attribs_cmd.size,
-					      &attribs_cmd.dma);
+	attribs_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+					     attribs_cmd.size,
+					     &attribs_cmd.dma, GFP_ATOMIC);
 	if (!attribs_cmd.va) {
 		dev_err(&adapter->pdev->dev, "Memory allocation failure\n");
 		status = -ENOMEM;
@@ -2815,8 +2817,8 @@ int be_cmd_get_cntl_attributes(struct be_adapter *adapter)
 err:
 	mutex_unlock(&adapter->mbox_lock);
 	if (attribs_cmd.va)
-		pci_free_consistent(adapter->pdev, attribs_cmd.size,
-				    attribs_cmd.va, attribs_cmd.dma);
+		dma_free_coherent(&adapter->pdev->dev, attribs_cmd.size,
+				  attribs_cmd.va, attribs_cmd.dma);
 	return status;
 }
 
@@ -2954,9 +2956,10 @@ int be_cmd_get_mac_from_list(struct be_adapter *adapter, u8 *mac,
 
 	memset(&get_mac_list_cmd, 0, sizeof(struct be_dma_mem));
 	get_mac_list_cmd.size = sizeof(struct be_cmd_resp_get_mac_list);
-	get_mac_list_cmd.va = pci_alloc_consistent(adapter->pdev,
-						   get_mac_list_cmd.size,
-						   &get_mac_list_cmd.dma);
+	get_mac_list_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+						  get_mac_list_cmd.size,
+						  &get_mac_list_cmd.dma,
+						  GFP_ATOMIC);
 
 	if (!get_mac_list_cmd.va) {
 		dev_err(&adapter->pdev->dev,
@@ -3029,8 +3032,8 @@ int be_cmd_get_mac_from_list(struct be_adapter *adapter, u8 *mac,
 
 out:
 	spin_unlock_bh(&adapter->mcc_lock);
-	pci_free_consistent(adapter->pdev, get_mac_list_cmd.size,
-			    get_mac_list_cmd.va, get_mac_list_cmd.dma);
+	dma_free_coherent(&adapter->pdev->dev, get_mac_list_cmd.size,
+			  get_mac_list_cmd.va, get_mac_list_cmd.dma);
 	return status;
 }
 
@@ -3083,8 +3086,8 @@ int be_cmd_set_mac_list(struct be_adapter *adapter, u8 *mac_array,
 
 	memset(&cmd, 0, sizeof(struct be_dma_mem));
 	cmd.size = sizeof(struct be_cmd_req_set_mac_list);
-	cmd.va = dma_alloc_coherent(&adapter->pdev->dev, cmd.size,
-				    &cmd.dma, GFP_KERNEL);
+	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				     GFP_KERNEL);
 	if (!cmd.va)
 		return -ENOMEM;
 
@@ -3255,7 +3258,8 @@ int be_cmd_get_acpi_wol_cap(struct be_adapter *adapter)
 
 	memset(&cmd, 0, sizeof(struct be_dma_mem));
 	cmd.size = sizeof(struct be_cmd_resp_acpi_wol_magic_config_v1);
-	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma);
+	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				     GFP_ATOMIC);
 	if (!cmd.va) {
 		dev_err(&adapter->pdev->dev, "Memory allocation failure\n");
 		status = -ENOMEM;
@@ -3290,7 +3294,8 @@ int be_cmd_get_acpi_wol_cap(struct be_adapter *adapter)
 err:
 	mutex_unlock(&adapter->mbox_lock);
 	if (cmd.va)
-		pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
+		dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va,
+				  cmd.dma);
 	return status;
 
 }
@@ -3304,8 +3309,9 @@ int be_cmd_set_fw_log_level(struct be_adapter *adapter, u32 level)
 
 	memset(&extfat_cmd, 0, sizeof(struct be_dma_mem));
 	extfat_cmd.size = sizeof(struct be_cmd_resp_get_ext_fat_caps);
-	extfat_cmd.va = pci_alloc_consistent(adapter->pdev, extfat_cmd.size,
-					     &extfat_cmd.dma);
+	extfat_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+					    extfat_cmd.size, &extfat_cmd.dma,
+					    GFP_ATOMIC);
 	if (!extfat_cmd.va)
 		return -ENOMEM;
 
@@ -3327,8 +3333,8 @@ int be_cmd_set_fw_log_level(struct be_adapter *adapter, u32 level)
 
 	status = be_cmd_set_ext_fat_capabilites(adapter, &extfat_cmd, cfgs);
 err:
-	pci_free_consistent(adapter->pdev, extfat_cmd.size, extfat_cmd.va,
-			    extfat_cmd.dma);
+	dma_free_coherent(&adapter->pdev->dev, extfat_cmd.size, extfat_cmd.va,
+			  extfat_cmd.dma);
 	return status;
 }
 
@@ -3341,8 +3347,9 @@ int be_cmd_get_fw_log_level(struct be_adapter *adapter)
 
 	memset(&extfat_cmd, 0, sizeof(struct be_dma_mem));
 	extfat_cmd.size = sizeof(struct be_cmd_resp_get_ext_fat_caps);
-	extfat_cmd.va = pci_alloc_consistent(adapter->pdev, extfat_cmd.size,
-					     &extfat_cmd.dma);
+	extfat_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+					    extfat_cmd.size, &extfat_cmd.dma,
+					    GFP_ATOMIC);
 
 	if (!extfat_cmd.va) {
 		dev_err(&adapter->pdev->dev, "%s: Memory allocation failure\n",
@@ -3360,8 +3367,8 @@ int be_cmd_get_fw_log_level(struct be_adapter *adapter)
 				level = cfgs->module[0].trace_lvl[j].dbg_lvl;
 		}
 	}
-	pci_free_consistent(adapter->pdev, extfat_cmd.size, extfat_cmd.va,
-			    extfat_cmd.dma);
+	dma_free_coherent(&adapter->pdev->dev, extfat_cmd.size, extfat_cmd.va,
+			  extfat_cmd.dma);
 err:
 	return level;
 }
@@ -3567,7 +3574,8 @@ int be_cmd_get_func_config(struct be_adapter *adapter, struct be_resources *res)
 
 	memset(&cmd, 0, sizeof(struct be_dma_mem));
 	cmd.size = sizeof(struct be_cmd_resp_get_func_config);
-	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma);
+	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				     GFP_ATOMIC);
 	if (!cmd.va) {
 		dev_err(&adapter->pdev->dev, "Memory alloc failure\n");
 		status = -ENOMEM;
@@ -3607,7 +3615,8 @@ int be_cmd_get_func_config(struct be_adapter *adapter, struct be_resources *res)
 err:
 	mutex_unlock(&adapter->mbox_lock);
 	if (cmd.va)
-		pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
+		dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va,
+				  cmd.dma);
 	return status;
 }
 
@@ -3628,7 +3637,8 @@ int be_cmd_get_profile_config(struct be_adapter *adapter,
 
 	memset(&cmd, 0, sizeof(struct be_dma_mem));
 	cmd.size = sizeof(struct be_cmd_resp_get_profile_config);
-	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma);
+	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				     GFP_ATOMIC);
 	if (!cmd.va)
 		return -ENOMEM;
 
@@ -3667,7 +3677,8 @@ int be_cmd_get_profile_config(struct be_adapter *adapter,
 		res->vf_if_cap_flags = vf_res->cap_flags;
 err:
 	if (cmd.va)
-		pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
+		dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va,
+				  cmd.dma);
 	return status;
 }
 
@@ -3682,7 +3693,8 @@ static int be_cmd_set_profile_config(struct be_adapter *adapter, void *desc,
 
 	memset(&cmd, 0, sizeof(struct be_dma_mem));
 	cmd.size = sizeof(struct be_cmd_req_set_profile_config);
-	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma);
+	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				     GFP_ATOMIC);
 	if (!cmd.va)
 		return -ENOMEM;
 
@@ -3698,7 +3710,8 @@ static int be_cmd_set_profile_config(struct be_adapter *adapter, void *desc,
 	status = be_cmd_notify_wait(adapter, &wrb);
 
 	if (cmd.va)
-		pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
+		dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va,
+				  cmd.dma);
 	return status;
 }
 
diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c
index e42a791..a11c5e0 100644
--- a/drivers/net/ethernet/emulex/benet/be_ethtool.c
+++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c
@@ -266,8 +266,8 @@ static int lancer_cmd_read_file(struct be_adapter *adapter, u8 *file_name,
 	int status = 0;
 
 	read_cmd.size = LANCER_READ_FILE_CHUNK;
-	read_cmd.va = pci_alloc_consistent(adapter->pdev, read_cmd.size,
-					   &read_cmd.dma);
+	read_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, read_cmd.size,
+					  &read_cmd.dma, GFP_ATOMIC);
 
 	if (!read_cmd.va) {
 		dev_err(&adapter->pdev->dev,
@@ -291,8 +291,8 @@ static int lancer_cmd_read_file(struct be_adapter *adapter, u8 *file_name,
 			break;
 		}
 	}
-	pci_free_consistent(adapter->pdev, read_cmd.size, read_cmd.va,
-			    read_cmd.dma);
+	dma_free_coherent(&adapter->pdev->dev, read_cmd.size, read_cmd.va,
+			  read_cmd.dma);
 
 	return status;
 }
@@ -818,8 +818,9 @@ static int be_test_ddr_dma(struct be_adapter *adapter)
 	};
 
 	ddrdma_cmd.size = sizeof(struct be_cmd_req_ddrdma_test);
-	ddrdma_cmd.va = dma_alloc_coherent(&adapter->pdev->dev, ddrdma_cmd.size,
-					   &ddrdma_cmd.dma, GFP_KERNEL);
+	ddrdma_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+					    ddrdma_cmd.size, &ddrdma_cmd.dma,
+					    GFP_KERNEL);
 	if (!ddrdma_cmd.va)
 		return -ENOMEM;
 
@@ -941,8 +942,9 @@ static int be_read_eeprom(struct net_device *netdev,
 
 	memset(&eeprom_cmd, 0, sizeof(struct be_dma_mem));
 	eeprom_cmd.size = sizeof(struct be_cmd_req_seeprom_read);
-	eeprom_cmd.va = dma_alloc_coherent(&adapter->pdev->dev, eeprom_cmd.size,
-					   &eeprom_cmd.dma, GFP_KERNEL);
+	eeprom_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+					    eeprom_cmd.size, &eeprom_cmd.dma,
+					    GFP_KERNEL);
 
 	if (!eeprom_cmd.va)
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index e51faf0..fdd3679 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -4113,8 +4113,8 @@ static int lancer_fw_download(struct be_adapter *adapter,
 
 	flash_cmd.size = sizeof(struct lancer_cmd_req_write_object)
 				+ LANCER_FW_DOWNLOAD_CHUNK;
-	flash_cmd.va = dma_alloc_coherent(dev, flash_cmd.size,
-					  &flash_cmd.dma, GFP_KERNEL);
+	flash_cmd.va = dma_zalloc_coherent(dev, flash_cmd.size,
+					   &flash_cmd.dma, GFP_KERNEL);
 	if (!flash_cmd.va)
 		return -ENOMEM;
 
@@ -4209,8 +4209,8 @@ static int be_fw_download(struct be_adapter *adapter, const struct firmware* fw)
 	int status = 0, i = 0, num_imgs = 0, ufi_type = 0;
 
 	flash_cmd.size = sizeof(struct be_cmd_write_flashrom);
-	flash_cmd.va = dma_alloc_coherent(&adapter->pdev->dev, flash_cmd.size,
-					  &flash_cmd.dma, GFP_KERNEL);
+	flash_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, flash_cmd.size,
+					   &flash_cmd.dma, GFP_KERNEL);
 	if (!flash_cmd.va) {
 		status = -ENOMEM;
 		goto be_fw_exit;
@@ -4587,10 +4587,10 @@ static int be_ctrl_init(struct be_adapter *adapter)
 		goto done;
 
 	mbox_mem_alloc->size = sizeof(struct be_mcc_mailbox) + 16;
-	mbox_mem_alloc->va = dma_alloc_coherent(&adapter->pdev->dev,
-						mbox_mem_alloc->size,
-						&mbox_mem_alloc->dma,
-						GFP_KERNEL);
+	mbox_mem_alloc->va = dma_zalloc_coherent(&adapter->pdev->dev,
+						 mbox_mem_alloc->size,
+						 &mbox_mem_alloc->dma,
+						 GFP_KERNEL);
 	if (!mbox_mem_alloc->va) {
 		status = -ENOMEM;
 		goto unmap_pci_bars;
-- 
2.1.0


From 6701f9ce7650c7b7bee5b70a5a221413c7c97905 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Sat, 6 Jun 2015 06:49:00 -0700
Subject: [PATCH 25/25] bridge: disable softirqs around br_fdb_update to avoid
 lockup

[ Upstream commit c4c832f89dc468cf11dc0dd17206bace44526651 ]

br_fdb_update() can be called in process context in the following way:
br_fdb_add() -> __br_fdb_add() -> br_fdb_update() (if NTF_USE flag is set)
so we need to disable softirqs because there are softirq users of the
hash_lock. One easy way to reproduce this is to modify the bridge utility
to set NTF_USE, enable stp and then set maxageing to a low value so
br_fdb_cleanup() is called frequently and then just add new entries in
a loop. This happens because br_fdb_cleanup() is called from timer/softirq
context. The spin locks in br_fdb_update were _bh before commit f8ae737deea1
("[BRIDGE]: forwarding remove unneeded preempt and bh diasables")
and at the time that commit was correct because br_fdb_update() couldn't be
called from process context, but that changed after commit:
292d1398983f ("bridge: add NTF_USE support")
Using local_bh_disable/enable around br_fdb_update() allows us to keep
using the spin_lock/unlock in br_fdb_update for the fast-path.

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Fixes: 292d1398983f ("bridge: add NTF_USE support")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_fdb.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index 6f6c95c..eab8862 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -789,9 +789,11 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge_port *p,
 	int err = 0;
 
 	if (ndm->ndm_flags & NTF_USE) {
+		local_bh_disable();
 		rcu_read_lock();
 		br_fdb_update(p->br, p, addr, vid, true);
 		rcu_read_unlock();
+		local_bh_enable();
 	} else {
 		spin_lock_bh(&p->br->hash_lock);
 		err = fdb_add_entry(p, addr, ndm->ndm_state,
-- 
2.1.0


[-- Attachment #5: net_40.mbox --]
[-- Type: Application/Octet-Stream, Size: 72303 bytes --]

From bdc56d44f4dcafab530db52e625b225ee104f2bc Mon Sep 17 00:00:00 2001
From: Vlad Yasevich <vyasevich@gmail.com>
Date: Sat, 2 May 2015 21:33:44 -0400
Subject: [PATCH 01/27] net: core: Correct an over-stringent device loop
 detection.

[ Upstream commit d66bf7dd27573ee5ea90484899ee952c19ccb194 ]

The code in __netdev_upper_dev_link() has an over-stringent
loop detection logic that actually prevents valid configurations
from working correctly.

In particular, the logic returns an error if an upper device
is already in the list of all upper devices for a given dev.
This particular check seems to be a overzealous as it disallows
perfectly valid configurations.  For example:
  # ip l a link eth0 name eth0.10 type vlan id 10
  # ip l a dev br0 typ bridge
  # ip l s eth0.10 master br0
  # ip l s eth0 master br0  <--- Will fail

If you switch the last two commands (add eth0 first), then both
will succeed.  If after that, you remove eth0 and try to re-add
it, it will fail!

It appears to be enough to simply check adj_list to keeps things
safe.

I've tried stacking multiple devices multiple times in all different
combinations, and either rx_handler registration prevented the stacking
of the device linking cought the error.

Signed-off-by: Vladislav Yasevich <vyasevic@redhat.com>
Acked-by: Jiri Pirko <jiri@resnulli.us>
Acked-by: Veaceslav Falico <vfalico@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 22a53ac..e977e15 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5170,7 +5170,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 	if (__netdev_find_adj(upper_dev, dev, &upper_dev->all_adj_list.upper))
 		return -EBUSY;
 
-	if (__netdev_find_adj(dev, upper_dev, &dev->all_adj_list.upper))
+	if (__netdev_find_adj(dev, upper_dev, &dev->adj_list.upper))
 		return -EEXIST;
 
 	if (master && netdev_master_upper_dev_get(dev))
-- 
2.1.0


From 5c4b7ad9c9c35a2926e88df50c975343932ea003 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@plumgrid.com>
Date: Mon, 11 May 2015 23:25:16 -0700
Subject: [PATCH 02/27] x86: bpf_jit: fix FROM_BE16 and FROM_LE16/32
 instructions

[ Upstream commit 343f845b375989f1753f605902931fa939aa2223 ]

FROM_BE16:
'ror %reg, 8' doesn't clear upper bits of the register,
so use additional 'movzwl' insn to zero extend 16 bits into 64

FROM_LE16:
should zero extend lower 16 bits into 64 bit

FROM_LE32:
should zero extend lower 32 bits into 64 bit

Fixes: 89aa075832b0 ("net: sock: allow eBPF programs to be attached to sockets")
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/x86/net/bpf_jit_comp.c | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 9875143..99f7610 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -559,6 +559,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 				if (is_ereg(dst_reg))
 					EMIT1(0x41);
 				EMIT3(0xC1, add_1reg(0xC8, dst_reg), 8);
+
+				/* emit 'movzwl eax, ax' */
+				if (is_ereg(dst_reg))
+					EMIT3(0x45, 0x0F, 0xB7);
+				else
+					EMIT2(0x0F, 0xB7);
+				EMIT1(add_2reg(0xC0, dst_reg, dst_reg));
 				break;
 			case 32:
 				/* emit 'bswap eax' to swap lower 4 bytes */
@@ -577,6 +584,27 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			break;
 
 		case BPF_ALU | BPF_END | BPF_FROM_LE:
+			switch (imm32) {
+			case 16:
+				/* emit 'movzwl eax, ax' to zero extend 16-bit
+				 * into 64 bit
+				 */
+				if (is_ereg(dst_reg))
+					EMIT3(0x45, 0x0F, 0xB7);
+				else
+					EMIT2(0x0F, 0xB7);
+				EMIT1(add_2reg(0xC0, dst_reg, dst_reg));
+				break;
+			case 32:
+				/* emit 'mov eax, eax' to clear upper 32-bits */
+				if (is_ereg(dst_reg))
+					EMIT1(0x45);
+				EMIT2(0x89, add_2reg(0xC0, dst_reg, dst_reg));
+				break;
+			case 64:
+				/* nop */
+				break;
+			}
 			break;
 
 			/* ST: *(u8*)(dst_reg + off) = imm */
-- 
2.1.0


From 45bd379d4f3ea08378c71a56454eee5aa0b74a05 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@plumgrid.com>
Date: Fri, 22 May 2015 15:42:55 -0700
Subject: [PATCH 03/27] x86: bpf_jit: fix compilation of large bpf programs

[ Upstream commit 3f7352bf21f8fd7ba3e2fcef9488756f188e12be ]

x86 has variable length encoding. x86 JIT compiler is trying
to pick the shortest encoding for given bpf instruction.
While doing so the jump targets are changing, so JIT is doing
multiple passes over the program. Typical program needs 3 passes.
Some very short programs converge with 2 passes. Large programs
may need 4 or 5. But specially crafted bpf programs may hit the
pass limit and if the program converges on the last iteration
the JIT compiler will be producing an image full of 'int 3' insns.
Fix this corner case by doing final iteration over bpf program.

Fixes: 0a14842f5a3c ("net: filter: Just In Time compiler for x86-64")
Reported-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Tested-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/x86/net/bpf_jit_comp.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 99f7610..ddeff48 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -966,7 +966,12 @@ void bpf_int_jit_compile(struct bpf_prog *prog)
 	}
 	ctx.cleanup_addr = proglen;
 
-	for (pass = 0; pass < 10; pass++) {
+	/* JITed image shrinks with every pass and the loop iterates
+	 * until the image stops shrinking. Very large bpf programs
+	 * may converge on the last pass. In such case do one more
+	 * pass to emit the final image
+	 */
+	for (pass = 0; pass < 10 || image; pass++) {
 		proglen = do_jit(prog, addrs, image, oldproglen, &ctx);
 		if (proglen <= 0) {
 			image = NULL;
-- 
2.1.0


From 533d1048847b170f298bd91313be9b8507e51909 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 15 May 2015 16:30:41 -0700
Subject: [PATCH 04/27] net: phy: Allow EEE for all RGMII variants

[ Upstream commit 7e14069651591c81046ffaec13c3dac8cb70f5fb ]

RGMII interfaces come in multiple flavors: RGMII with transmit or
receive internal delay, no delays at all, or delays in both direction.

This change extends the initial check for PHY_INTERFACE_MODE_RGMII to
cover all of these variants since EEE should be allowed for any of these
modes, since it is a property of the RGMII, hence Gigabit PHY capability
more than the RGMII electrical interface and its delays.

Fixes: a59a4d192166 ("phy: add the EEE support and the way to access to the MMD registers")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 52cd8db..757f28a 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -1053,13 +1053,14 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable)
 {
 	/* According to 802.3az,the EEE is supported only in full duplex-mode.
 	 * Also EEE feature is active when core is operating with MII, GMII
-	 * or RGMII. Internal PHYs are also allowed to proceed and should
-	 * return an error if they do not support EEE.
+	 * or RGMII (all kinds). Internal PHYs are also allowed to proceed and
+	 * should return an error if they do not support EEE.
 	 */
 	if ((phydev->duplex == DUPLEX_FULL) &&
 	    ((phydev->interface == PHY_INTERFACE_MODE_MII) ||
 	    (phydev->interface == PHY_INTERFACE_MODE_GMII) ||
-	    (phydev->interface == PHY_INTERFACE_MODE_RGMII) ||
+	    (phydev->interface >= PHY_INTERFACE_MODE_RGMII &&
+	     phydev->interface <= PHY_INTERFACE_MODE_RGMII_TXID) ||
 	     phy_is_internal(phydev))) {
 		int eee_lp, eee_cap, eee_adv;
 		u32 lp, cap, adv;
-- 
2.1.0


From 9b67f281b2e297f38da0dea31986a12eebef0726 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Sat, 16 May 2015 21:50:28 +0800
Subject: [PATCH 05/27] netlink: Reset portid after netlink_insert failure

[ Upstream commit c0bb07df7d981e4091432754e30c9c720e2c0c78 ]

The commit c5adde9468b0714a051eac7f9666f23eb10b61f7 ("netlink:
eliminate nl_sk_hash_lock") breaks the autobind retry mechanism
because it doesn't reset portid after a failed netlink_insert.

This means that should autobind fail the first time around, then
the socket will be stuck in limbo as it can never be bound again
since it already has a non-zero portid.

Fixes: c5adde9468b0 ("netlink: eliminate nl_sk_hash_lock")
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index d1d7a81..e98dc53 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1069,6 +1069,7 @@ static int netlink_insert(struct sock *sk, u32 portid)
 	err = 0;
 	if (!__netlink_insert(table, sk)) {
 		err = -EADDRINUSE;
+		nlk_sk(sk)->portid = 0;
 		sock_put(sk);
 	}
 
-- 
2.1.0


From 99a7b67c7f44d6c24ad6313ae59627fcd4283a75 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Wed, 13 May 2015 14:19:42 +0200
Subject: [PATCH 06/27] rtnl/bond: don't send rtnl msg for unregistered iface

[ Upstream commit ed2a80ab7b76f11af0b2c6255709c4ebf164b667 ]

Before the patch, the command 'ip link add bond2 type bond mode 802.3ad'
causes the kernel to send a rtnl message for the bond2 interface, with an
ifindex 0.

'ip monitor' shows:
0: bond2: <BROADCAST,MULTICAST,MASTER> mtu 1500 state DOWN group default
    link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff
9: bond2@NONE: <BROADCAST,MULTICAST,MASTER> mtu 1500 qdisc noop state DOWN group default
    link/ether ea:3e:1f:53:92:7b brd ff:ff:ff:ff:ff:ff
[snip]

The patch fixes the spotted bug by checking in bond driver if the interface
is registered before calling the notifier chain.
It also adds a check in rtmsg_ifinfo() to prevent this kind of bug in the
future.

Fixes: d4261e565000 ("bonding: create netlink event when bonding option is changed")
CC: Jiri Pirko <jiri@resnulli.us>
Reported-by: Julien Meunier <julien.meunier@6wind.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_options.c | 2 +-
 net/core/rtnetlink.c               | 3 +++
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 4df2894..e8d3c1d 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -624,7 +624,7 @@ int __bond_opt_set(struct bonding *bond,
 out:
 	if (ret)
 		bond_opt_error_interpret(bond, opt, ret, val);
-	else
+	else if (bond->dev->reg_state == NETREG_REGISTERED)
 		call_netdevice_notifiers(NETDEV_CHANGEINFODATA, bond->dev);
 
 	return ret;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 7ebed55..a2b90e1 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2337,6 +2337,9 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change,
 {
 	struct sk_buff *skb;
 
+	if (dev->reg_state != NETREG_REGISTERED)
+		return;
+
 	skb = rtmsg_ifinfo_build_skb(type, dev, change, flags);
 	if (skb)
 		rtmsg_ifinfo_send(skb, dev, flags);
-- 
2.1.0


From 76d27e2d3c07c186c1c13046802ec8e685de2be0 Mon Sep 17 00:00:00 2001
From: Florent Fourcot <florent.fourcot@enst-bretagne.fr>
Date: Sat, 16 May 2015 00:24:59 +0200
Subject: [PATCH 07/27] tcp/ipv6: fix flow label setting in TIME_WAIT state

[ Upstream commit 21858cd02dabcf290564cbf4769b101eba54d7bb ]

commit 1d13a96c74fc ("ipv6: tcp: fix flowlabel value in ACK messages
send from TIME_WAIT") added the flow label in the last TCP packets.
Unfortunately, it was not casted properly.

This patch replace the buggy shift with be32_to_cpu/cpu_to_be32.

Fixes: 1d13a96c74fc ("ipv6: tcp: fix flowlabel value in ACK messages")
Reported-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Florent Fourcot <florent.fourcot@enst-bretagne.fr>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_minisocks.c | 2 +-
 net/ipv6/tcp_ipv6.c      | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index dd11ac7..1143748 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -316,7 +316,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 			tw->tw_v6_daddr = sk->sk_v6_daddr;
 			tw->tw_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
 			tw->tw_tclass = np->tclass;
-			tw->tw_flowlabel = np->flow_label >> 12;
+			tw->tw_flowlabel = be32_to_cpu(np->flow_label & IPV6_FLOWLABEL_MASK);
 			tw->tw_ipv6only = sk->sk_ipv6only;
 		}
 #endif
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 1f5e622..5ca3bc8 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -975,7 +975,7 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb)
 			tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
 			tcp_time_stamp + tcptw->tw_ts_offset,
 			tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw),
-			tw->tw_tclass, (tw->tw_flowlabel << 12));
+			tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel));
 
 	inet_twsk_put(tw);
 }
-- 
2.1.0


From 3597c5d5f84aa4c694e3257ea057a274cfde7cb5 Mon Sep 17 00:00:00 2001
From: Henning Rogge <hrogge@gmail.com>
Date: Mon, 18 May 2015 21:08:49 +0200
Subject: [PATCH 08/27] net/ipv6/udp: Fix ipv6 multicast socket filter
 regression

[ Upstream commit 33b4b015e1a1ca7a8fdce40af5e71642a8ea355c ]

Commit <5cf3d46192fc> ("udp: Simplify__udp*_lib_mcast_deliver")
simplified the filter for incoming IPv6 multicast but removed
the check of the local socket address and the UDP destination
address.

This patch restores the filter to prevent sockets bound to a IPv6
multicast IP to receive other UDP traffic link unicast.

Signed-off-by: Henning Rogge <hrogge@gmail.com>
Fixes: 5cf3d46192fc ("udp: Simplify__udp*_lib_mcast_deliver")
Cc: "David S. Miller" <davem@davemloft.net>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/udp.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index d048d46..0c80ca7 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -734,7 +734,9 @@ static bool __udp_v6_is_mcast_sock(struct net *net, struct sock *sk,
 	    (inet->inet_dport && inet->inet_dport != rmt_port) ||
 	    (!ipv6_addr_any(&sk->sk_v6_daddr) &&
 		    !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) ||
-	    (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif))
+	    (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif) ||
+	    (!ipv6_addr_any(&sk->sk_v6_rcv_saddr) &&
+		    !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr)))
 		return false;
 	if (!inet6_mc_check(sk, loc_addr, rmt_addr))
 		return false;
-- 
2.1.0


From f8a6d562a9735d923da18999c8c8bf83e382e46d Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 20 May 2015 17:13:33 +0200
Subject: [PATCH 09/27] net: sched: fix call_rcu() race on classifier module
 unloads

[ Upstream commit c78e1746d3ad7d548bdf3fe491898cc453911a49 ]

Vijay reported that a loop as simple as ...

  while true; do
    tc qdisc add dev foo root handle 1: prio
    tc filter add dev foo parent 1: u32 match u32 0 0  flowid 1
    tc qdisc del dev foo root
    rmmod cls_u32
  done

... will panic the kernel. Moreover, he bisected the change
apparently introducing it to 78fd1d0ab072 ("netlink: Re-add
locking to netlink_lookup() and seq walker").

The removal of synchronize_net() from the netlink socket
triggering the qdisc to be removed, seems to have uncovered
an RCU resp. module reference count race from the tc API.
Given that RCU conversion was done after e341694e3eb5 ("netlink:
Convert netlink_lookup() to use RCU protected hash table")
which added the synchronize_net() originally, occasion of
hitting the bug was less likely (not impossible though):

When qdiscs that i) support attaching classifiers and,
ii) have at least one of them attached, get deleted, they
invoke tcf_destroy_chain(), and thus call into ->destroy()
handler from a classifier module.

After RCU conversion, all classifier that have an internal
prio list, unlink them and initiate freeing via call_rcu()
deferral.

Meanhile, tcf_destroy() releases already reference to the
tp->ops->owner module before the queued RCU callback handler
has been invoked.

Subsequent rmmod on the classifier module is then not prevented
since all module references are already dropped.

By the time, the kernel invokes the RCU callback handler from
the module, that function address is then invalid.

One way to fix it would be to add an rcu_barrier() to
unregister_tcf_proto_ops() to wait for all pending call_rcu()s
to complete.

synchronize_rcu() is not appropriate as under heavy RCU
callback load, registered call_rcu()s could be deferred
longer than a grace period. In case we don't have any pending
call_rcu()s, the barrier is allowed to return immediately.

Since we came here via unregister_tcf_proto_ops(), there
are no users of a given classifier anymore. Further nested
call_rcu()s pointing into the module space are not being
done anywhere.

Only cls_bpf_delete_prog() may schedule a work item, to
unlock pages eventually, but that is not in the range/context
of cls_bpf anymore.

Fixes: 25d8c0d55f24 ("net: rcu-ify tcf_proto")
Fixes: 9888faefe132 ("net: sched: cls_basic use RCU")
Reported-by: Vijay Subramanian <subramanian.vijay@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: John Fastabend <john.r.fastabend@intel.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Thomas Graf <tgraf@suug.ch>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Alexei Starovoitov <ast@plumgrid.com>
Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index baef987..d3328a1 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -81,6 +81,11 @@ int unregister_tcf_proto_ops(struct tcf_proto_ops *ops)
 	struct tcf_proto_ops *t;
 	int rc = -ENOENT;
 
+	/* Wait for outstanding call_rcu()s, if any, from a
+	 * tcf_proto_ops's destroy() handler.
+	 */
+	rcu_barrier();
+
 	write_lock(&cls_mod_lock);
 	list_for_each_entry(t, &tcf_proto_base, head) {
 		if (t == ops) {
-- 
2.1.0


From 180ccea016875090b71772e8ef0629828f9a06cf Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 22 May 2015 04:58:12 -0500
Subject: [PATCH 10/27] ipv4: Avoid crashing in ip_error

[ Upstream commit 381c759d9916c42959515ad34a6d467e24a88e93 ]

ip_error does not check if in_dev is NULL before dereferencing it.

IThe following sequence of calls is possible:
CPU A                          CPU B
ip_rcv_finish
    ip_route_input_noref()
        ip_route_input_slow()
                               inetdev_destroy()
    dst_input()

With the result that a network device can be destroyed while processing
an input packet.

A crash was triggered with only unicast packets in flight, and
forwarding enabled on the only network device.   The error condition
was created by the removal of the network device.

As such it is likely the that error code was -EHOSTUNREACH, and the
action taken by ip_error (if in_dev had been accessible) would have
been to not increment any counters and to have tried and likely failed
to send an icmp error as the network device is going away.

Therefore handle this weird case by just dropping the packet if
!in_dev.  It will result in dropping the packet sooner, and will not
result in an actual change of behavior.

Fixes: 251da4130115b ("ipv4: Cache ip_error() routes even when not forwarding.")
Reported-by: Vittorio Gambaletta <linuxbugs@vittgam.net>
Tested-by: Vittorio Gambaletta <linuxbugs@vittgam.net>
Signed-off-by: Vittorio Gambaletta <linuxbugs@vittgam.net>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 20fc020..e262a08 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -903,6 +903,10 @@ static int ip_error(struct sk_buff *skb)
 	bool send;
 	int code;
 
+	/* IP on this device is disabled. */
+	if (!in_dev)
+		goto out;
+
 	net = dev_net(rt->dst.dev);
 	if (!IN_DEV_FORWARD(in_dev)) {
 		switch (rt->dst.error) {
-- 
2.1.0


From d3614a0016d398b089ff6709b281687a226f3a9f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Fri, 22 May 2015 13:15:22 +0200
Subject: [PATCH 11/27] cdc_ncm: Fix tx_bytes statistics
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 44f6731d8b68fa02f5ed65eaceac41f8c3c9279e ]

The tx_curr_frame_payload field is u32. When we try to calculate a
small negative delta based on it, we end up with a positive integer
close to 2^32 instead.  So the tx_bytes pointer increases by about
2^32 for every transmitted frame.

Fix by calculating the delta as a signed long.

Cc: Ben Hutchings <ben.hutchings@codethink.co.uk>
Reported-by: Florian Bruhin <me@the-compiler.org>
Fixes: 7a1e890e2168 ("usbnet: Fix tx_bytes statistic running backward in cdc_ncm")
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ncm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index c3e4da9..8067b8f 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -1182,7 +1182,7 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign)
 	 * payload data instead.
 	 */
 	usbnet_set_skb_tx_stats(skb_out, n,
-				ctx->tx_curr_frame_payload - skb_out->len);
+				(long)ctx->tx_curr_frame_payload - skb_out->len);
 
 	return skb_out;
 
-- 
2.1.0


From ab72d37e1cd7166b685b8de2829a578b7622c78e Mon Sep 17 00:00:00 2001
From: Thadeu Lima de Souza Cascardo <cascardo@redhat.com>
Date: Fri, 22 May 2015 12:18:59 -0300
Subject: [PATCH 12/27] bridge: fix parsing of MLDv2 reports

[ Upstream commit 47cc84ce0c2fe75c99ea5963c4b5704dd78ead54 ]

When more than a multicast address is present in a MLDv2 report, all but
the first address is ignored, because the code breaks out of the loop if
there has not been an error adding that address.

This has caused failures when two guests connected through the bridge
tried to communicate using IPv6. Neighbor discoveries would not be
transmitted to the other guest when both used a link-local address and a
static address.

This only happens when there is a MLDv2 querier in the network.

The fix will only break out of the loop when there is a failure adding a
multicast address.

The mdb before the patch:

dev ovirtmgmt port vnet0 grp ff02::1:ff7d:6603 temp
dev ovirtmgmt port vnet1 grp ff02::1:ff7d:6604 temp
dev ovirtmgmt port bond0.86 grp ff02::2 temp

After the patch:

dev ovirtmgmt port vnet0 grp ff02::1:ff7d:6603 temp
dev ovirtmgmt port vnet1 grp ff02::1:ff7d:6604 temp
dev ovirtmgmt port bond0.86 grp ff02::fb temp
dev ovirtmgmt port bond0.86 grp ff02::2 temp
dev ovirtmgmt port bond0.86 grp ff02::d temp
dev ovirtmgmt port vnet0 grp ff02::1:ff00:76 temp
dev ovirtmgmt port bond0.86 grp ff02::16 temp
dev ovirtmgmt port vnet1 grp ff02::1:ff00:77 temp
dev ovirtmgmt port bond0.86 grp ff02::1:ff00:def temp
dev ovirtmgmt port bond0.86 grp ff02::1:ffa1:40bf temp

Fixes: 08b202b67264 ("bridge br_multicast: IPv6 MLD support.")
Reported-by: Rik Theys <Rik.Theys@esat.kuleuven.be>
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@redhat.com>
Tested-by: Rik Theys <Rik.Theys@esat.kuleuven.be>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index c465876..cd02185 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1071,7 +1071,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br,
 
 		err = br_ip6_multicast_add_group(br, port, &grec->grec_mca,
 						 vid);
-		if (!err)
+		if (err)
 			break;
 	}
 
-- 
2.1.0


From 21da0e7abbc9d260d467d7e7da5f84c19f676f66 Mon Sep 17 00:00:00 2001
From: Richard Cochran <richardcochran@gmail.com>
Date: Mon, 25 May 2015 11:55:43 +0200
Subject: [PATCH 13/27] net: dp83640: fix broken calibration routine.

[ Upstream commit 397a253af5031de4a4612210055935309af4472c ]

Currently, the calibration function that corrects the initial offsets
among multiple devices only works the first time.  If the function is
called more than once, the calibration fails and bogus offsets will be
programmed into the devices.

In a well hidden spot, the device documentation tells that trigger indexes
0 and 1 are special in allowing the TRIG_IF_LATE flag to actually work.

This patch fixes the issue by using one of the special triggers during the
recalibration method.

Signed-off-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/dp83640.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index e22e602..5eb3c8e 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -47,7 +47,7 @@
 #define PSF_TX		0x1000
 #define EXT_EVENT	1
 #define CAL_EVENT	7
-#define CAL_TRIGGER	7
+#define CAL_TRIGGER	1
 #define DP83640_N_PINS	12
 
 #define MII_DP83640_MICR 0x11
-- 
2.1.0


From 9d52e1a391c4b7f5aa38b49f56799d296be2e02b Mon Sep 17 00:00:00 2001
From: Richard Cochran <richardcochran@gmail.com>
Date: Mon, 25 May 2015 11:55:44 +0200
Subject: [PATCH 14/27] net: dp83640: reinforce locking rules.

[ Upstream commit a935865c828c8cd20501f618c69f659a5b6d6a5f ]

Callers of the ext_write function are supposed to hold a mutex that
protects the state of the dialed page, but one caller was missing the
lock from the very start, and over time the code has been changed
without following the rule.  This patch cleans up the call sites in
violation of the rule.

Signed-off-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/dp83640.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index 5eb3c8e..4f3cf1b 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -495,7 +495,9 @@ static int ptp_dp83640_enable(struct ptp_clock_info *ptp,
 			else
 				evnt |= EVNT_RISE;
 		}
+		mutex_lock(&clock->extreg_lock);
 		ext_write(0, phydev, PAGE5, PTP_EVNT, evnt);
+		mutex_unlock(&clock->extreg_lock);
 		return 0;
 
 	case PTP_CLK_REQ_PEROUT:
@@ -531,6 +533,8 @@ static u8 status_frame_src[6] = { 0x08, 0x00, 0x17, 0x0B, 0x6B, 0x0F };
 
 static void enable_status_frames(struct phy_device *phydev, bool on)
 {
+	struct dp83640_private *dp83640 = phydev->priv;
+	struct dp83640_clock *clock = dp83640->clock;
 	u16 cfg0 = 0, ver;
 
 	if (on)
@@ -538,9 +542,13 @@ static void enable_status_frames(struct phy_device *phydev, bool on)
 
 	ver = (PSF_PTPVER & VERSIONPTP_MASK) << VERSIONPTP_SHIFT;
 
+	mutex_lock(&clock->extreg_lock);
+
 	ext_write(0, phydev, PAGE5, PSF_CFG0, cfg0);
 	ext_write(0, phydev, PAGE6, PSF_CFG1, ver);
 
+	mutex_unlock(&clock->extreg_lock);
+
 	if (!phydev->attached_dev) {
 		pr_warn("expected to find an attached netdevice\n");
 		return;
@@ -1172,11 +1180,18 @@ static int dp83640_config_init(struct phy_device *phydev)
 
 	if (clock->chosen && !list_empty(&clock->phylist))
 		recalibrate(clock);
-	else
+	else {
+		mutex_lock(&clock->extreg_lock);
 		enable_broadcast(phydev, clock->page, 1);
+		mutex_unlock(&clock->extreg_lock);
+	}
 
 	enable_status_frames(phydev, true);
+
+	mutex_lock(&clock->extreg_lock);
 	ext_write(0, phydev, PAGE4, PTP_CTL, PTP_ENABLE);
+	mutex_unlock(&clock->extreg_lock);
+
 	return 0;
 }
 
-- 
2.1.0


From 3e82f56ee455496ee56475cc021cfc6e0f8e05c8 Mon Sep 17 00:00:00 2001
From: Richard Cochran <richardcochran@gmail.com>
Date: Mon, 25 May 2015 11:55:45 +0200
Subject: [PATCH 15/27] net: dp83640: fix improper double spin locking.

[ Upstream commit adbe088f6f8b0b7701fe07f51fe6f2bd602a6665 ]

A pair of nested spin locks was introduced in commit 63502b8d0
"dp83640: Fix receive timestamp race condition".

Unfortunately the 'flags' parameter was reused for the inner lock,
clobbering the originally saved IRQ state.  This patch fixes the issue
by changing the inner lock to plain spin_lock without irqsave.

Signed-off-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/dp83640.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index 4f3cf1b..c5789cd 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -845,7 +845,7 @@ static void decode_rxts(struct dp83640_private *dp83640,
 	list_del_init(&rxts->list);
 	phy2rxts(phy_rxts, rxts);
 
-	spin_lock_irqsave(&dp83640->rx_queue.lock, flags);
+	spin_lock(&dp83640->rx_queue.lock);
 	skb_queue_walk(&dp83640->rx_queue, skb) {
 		struct dp83640_skb_info *skb_info;
 
@@ -860,7 +860,7 @@ static void decode_rxts(struct dp83640_private *dp83640,
 			break;
 		}
 	}
-	spin_unlock_irqrestore(&dp83640->rx_queue.lock, flags);
+	spin_unlock(&dp83640->rx_queue.lock);
 
 	if (!shhwtstamps)
 		list_add_tail(&rxts->list, &dp83640->rxts);
-- 
2.1.0


From 62a879ed449a3433bcac2909c5de3924a276160f Mon Sep 17 00:00:00 2001
From: Mark Salyzyn <salyzyn@android.com>
Date: Tue, 26 May 2015 08:22:19 -0700
Subject: [PATCH 16/27] unix/caif: sk_socket can disappear when state is
 unlocked

[ Upstream commit b48732e4a48d80ed4a14812f0bab09560846514e ]

got a rare NULL pointer dereference in clear_bit

Signed-off-by: Mark Salyzyn <salyzyn@android.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
----
v2: switch to sock_flag(sk, SOCK_DEAD) and added net/caif/caif_socket.c
v3: return -ECONNRESET in upstream caller of wait function for SOCK_DEAD
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/caif/caif_socket.c | 8 ++++++++
 net/unix/af_unix.c     | 8 ++++++++
 2 files changed, 16 insertions(+)

diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index a6e2da0..982101c 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -330,6 +330,10 @@ static long caif_stream_data_wait(struct sock *sk, long timeo)
 		release_sock(sk);
 		timeo = schedule_timeout(timeo);
 		lock_sock(sk);
+
+		if (sock_flag(sk, SOCK_DEAD))
+			break;
+
 		clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
 	}
 
@@ -374,6 +378,10 @@ static int caif_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 		struct sk_buff *skb;
 
 		lock_sock(sk);
+		if (sock_flag(sk, SOCK_DEAD)) {
+			err = -ECONNRESET;
+			goto unlock;
+		}
 		skb = skb_dequeue(&sk->sk_receive_queue);
 		caif_check_flow_release(sk);
 
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 526b6ed..146881f 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1887,6 +1887,10 @@ static long unix_stream_data_wait(struct sock *sk, long timeo,
 		unix_state_unlock(sk);
 		timeo = freezable_schedule_timeout(timeo);
 		unix_state_lock(sk);
+
+		if (sock_flag(sk, SOCK_DEAD))
+			break;
+
 		clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
 	}
 
@@ -1947,6 +1951,10 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 		struct sk_buff *skb, *last;
 
 		unix_state_lock(sk);
+		if (sock_flag(sk, SOCK_DEAD)) {
+			err = -ECONNRESET;
+			goto unlock;
+		}
 		last = skb = skb_peek(&sk->sk_receive_queue);
 again:
 		if (skb == NULL) {
-- 
2.1.0


From 3c6df93b0d880478e64feff05237631018543459 Mon Sep 17 00:00:00 2001
From: Ross Lagerwall <ross.lagerwall@citrix.com>
Date: Wed, 27 May 2015 11:44:32 +0100
Subject: [PATCH 17/27] xen/netback: Properly initialize credit_bytes

[ Upstream commit ce0e5c522d3924090c20e774359809a7aa08c44c ]

Commit e9ce7cb6b107 ("xen-netback: Factor queue-specific data into queue
struct") introduced a regression when moving queue-specific data into
the queue struct by failing to set the credit_bytes field. This
prevented bandwidth limiting from working. Initialize the field as it
was done before multiqueue support was added.

Signed-off-by: Ross Lagerwall <ross.lagerwall@citrix.com>
Acked-by: Wei Liu <wei.liu2@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netback/xenbus.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index 794204e..784a624 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -736,6 +736,7 @@ static void connect(struct backend_info *be)
 			goto err;
 		}
 
+		queue->credit_bytes = credit_bytes;
 		queue->remaining_credit = credit_bytes;
 		queue->credit_usec = credit_usec;
 
-- 
2.1.0


From 66ca1a291a306cd468ddee44619dc602e0ae2b1f Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Tue, 26 May 2015 16:08:48 -0700
Subject: [PATCH 18/27] net_sched: invoke ->attach() after setting dev->qdisc

[ Upstream commit 86e363dc3b50bfd50a1f315934583fbda673ab8d ]

For mq qdisc, we add per tx queue qdisc to root qdisc
for display purpose, however, that happens too early,
before the new dev->qdisc is finally set, this causes
q->list points to an old root qdisc which is going to be
freed right before assigning with a new one.

Fix this by moving ->attach() after setting dev->qdisc.

For the record, this fixes the following crash:

 ------------[ cut here ]------------
 WARNING: CPU: 1 PID: 975 at lib/list_debug.c:59 __list_del_entry+0x5a/0x98()
 list_del corruption. prev->next should be ffff8800d1998ae8, but was 6b6b6b6b6b6b6b6b
 CPU: 1 PID: 975 Comm: tc Not tainted 4.1.0-rc4+ #1019
 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
  0000000000000009 ffff8800d73fb928 ffffffff81a44e7f 0000000047574756
  ffff8800d73fb978 ffff8800d73fb968 ffffffff810790da ffff8800cfc4cd20
  ffffffff814e725b ffff8800d1998ae8 ffffffff82381250 0000000000000000
 Call Trace:
  [<ffffffff81a44e7f>] dump_stack+0x4c/0x65
  [<ffffffff810790da>] warn_slowpath_common+0x9c/0xb6
  [<ffffffff814e725b>] ? __list_del_entry+0x5a/0x98
  [<ffffffff81079162>] warn_slowpath_fmt+0x46/0x48
  [<ffffffff81820eb0>] ? dev_graft_qdisc+0x5e/0x6a
  [<ffffffff814e725b>] __list_del_entry+0x5a/0x98
  [<ffffffff814e72a7>] list_del+0xe/0x2d
  [<ffffffff81822f05>] qdisc_list_del+0x1e/0x20
  [<ffffffff81820cd1>] qdisc_destroy+0x30/0xd6
  [<ffffffff81822676>] qdisc_graft+0x11d/0x243
  [<ffffffff818233c1>] tc_get_qdisc+0x1a6/0x1d4
  [<ffffffff810b5eaf>] ? mark_lock+0x2e/0x226
  [<ffffffff817ff8f5>] rtnetlink_rcv_msg+0x181/0x194
  [<ffffffff817ff72e>] ? rtnl_lock+0x17/0x19
  [<ffffffff817ff72e>] ? rtnl_lock+0x17/0x19
  [<ffffffff817ff774>] ? __rtnl_unlock+0x17/0x17
  [<ffffffff81855dc6>] netlink_rcv_skb+0x4d/0x93
  [<ffffffff817ff756>] rtnetlink_rcv+0x26/0x2d
  [<ffffffff818544b2>] netlink_unicast+0xcb/0x150
  [<ffffffff81161db9>] ? might_fault+0x59/0xa9
  [<ffffffff81854f78>] netlink_sendmsg+0x4fa/0x51c
  [<ffffffff817d6e09>] sock_sendmsg_nosec+0x12/0x1d
  [<ffffffff817d8967>] sock_sendmsg+0x29/0x2e
  [<ffffffff817d8cf3>] ___sys_sendmsg+0x1b4/0x23a
  [<ffffffff8100a1b8>] ? native_sched_clock+0x35/0x37
  [<ffffffff810a1d83>] ? sched_clock_local+0x12/0x72
  [<ffffffff810a1fd4>] ? sched_clock_cpu+0x9e/0xb7
  [<ffffffff810def2a>] ? current_kernel_time+0xe/0x32
  [<ffffffff810b4bc5>] ? lock_release_holdtime.part.29+0x71/0x7f
  [<ffffffff810ddebf>] ? read_seqcount_begin.constprop.27+0x5f/0x76
  [<ffffffff810b6292>] ? trace_hardirqs_on_caller+0x17d/0x199
  [<ffffffff811b14d5>] ? __fget_light+0x50/0x78
  [<ffffffff817d9808>] __sys_sendmsg+0x42/0x60
  [<ffffffff817d9838>] SyS_sendmsg+0x12/0x1c
  [<ffffffff81a50e97>] system_call_fastpath+0x12/0x6f
 ---[ end trace ef29d3fb28e97ae7 ]---

For long term, we probably need to clean up the qdisc_graft() code
in case it hides other bugs like this.

Fixes: 95dc19299f74 ("pkt_sched: give visibility to mq slave qdiscs")
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_api.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 243b7d1..d9c2ee6 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -815,10 +815,8 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent,
 		if (dev->flags & IFF_UP)
 			dev_deactivate(dev);
 
-		if (new && new->ops->attach) {
-			new->ops->attach(new);
-			num_q = 0;
-		}
+		if (new && new->ops->attach)
+			goto skip;
 
 		for (i = 0; i < num_q; i++) {
 			struct netdev_queue *dev_queue = dev_ingress_queue(dev);
@@ -834,12 +832,16 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent,
 				qdisc_destroy(old);
 		}
 
+skip:
 		if (!ingress) {
 			notify_and_destroy(net, skb, n, classid,
 					   dev->qdisc, new);
 			if (new && !new->ops->attach)
 				atomic_inc(&new->refcnt);
 			dev->qdisc = new ? : &noop_qdisc;
+
+			if (new && new->ops->attach)
+				new->ops->attach(new);
 		} else {
 			notify_and_destroy(net, skb, n, classid, old, new);
 		}
-- 
2.1.0


From ecf2be8dcd27bdf08ab2a746b026d69b6a6c1b2b Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Date: Tue, 26 May 2015 17:30:17 -0600
Subject: [PATCH 19/27] sctp: Fix mangled IPv4 addresses on a IPv6 listening
 socket

[ Upstream commit 9302d7bb0c5cd46be5706859301f18c137b2439f ]

sctp_v4_map_v6 was subtly writing and reading from members
of a union in a way the clobbered data it needed to read before
it read it.

Zeroing the v6 flowinfo overwrites the v4 sin_addr with 0, meaning
that every place that calls sctp_v4_map_v6 gets ::ffff:0.0.0.0 as the
result.

Reorder things to guarantee correct behaviour no matter what the
union layout is.

This impacts user space clients that open an IPv6 SCTP socket and
receive IPv4 connections. Prior to 299ee user space would see a
sockaddr with AF_INET and a correct address, after 299ee the sockaddr
is AF_INET6, but the address is wrong.

Fixes: 299ee123e198 (sctp: Fixup v4mapped behaviour to comply with Sock API)
Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/sctp.h | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 856f01c..230775f 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -571,11 +571,14 @@ static inline void sctp_v6_map_v4(union sctp_addr *addr)
 /* Map v4 address to v4-mapped v6 address */
 static inline void sctp_v4_map_v6(union sctp_addr *addr)
 {
+	__be16 port;
+
+	port = addr->v4.sin_port;
+	addr->v6.sin6_addr.s6_addr32[3] = addr->v4.sin_addr.s_addr;
+	addr->v6.sin6_port = port;
 	addr->v6.sin6_family = AF_INET6;
 	addr->v6.sin6_flowinfo = 0;
 	addr->v6.sin6_scope_id = 0;
-	addr->v6.sin6_port = addr->v4.sin_port;
-	addr->v6.sin6_addr.s6_addr32[3] = addr->v4.sin_addr.s_addr;
 	addr->v6.sin6_addr.s6_addr32[0] = 0;
 	addr->v6.sin6_addr.s6_addr32[1] = 0;
 	addr->v6.sin6_addr.s6_addr32[2] = htonl(0x0000ffff);
-- 
2.1.0


From 40e05de535656197c5aac14a7fb0af5579a277d0 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 28 May 2015 04:42:54 -0700
Subject: [PATCH 20/27] bridge: fix br_multicast_query_expired() bug
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 71d9f6149cac8fc6646adfb2a6f3b0de6ddd23f6 ]

br_multicast_query_expired() querier argument is a pointer to
a struct bridge_mcast_querier :

struct bridge_mcast_querier {
        struct br_ip addr;
        struct net_bridge_port __rcu    *port;
};

Intent of the code was to clear port field, not the pointer to querier.

Fixes: 2cd4143192e8 ("bridge: memorize and export selected IGMP/MLD querier port")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Thadeu Lima de Souza Cascardo <cascardo@redhat.com>
Acked-by: Linus Lüssing <linus.luessing@c0d3.blue>
Cc: Linus Lüssing <linus.luessing@web.de>
Cc: Steinar H. Gunderson <sesse@samfundet.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index cd02185..b0aee78 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1821,7 +1821,7 @@ static void br_multicast_query_expired(struct net_bridge *br,
 	if (query->startup_sent < br->multicast_startup_query_count)
 		query->startup_sent++;
 
-	RCU_INIT_POINTER(querier, NULL);
+	RCU_INIT_POINTER(querier->port, NULL);
 	br_multicast_send_query(br, NULL, query);
 	spin_unlock(&br->multicast_lock);
 }
-- 
2.1.0


From d09524071b65fa8dbeb91767ae1e03e8ee7dd5ad Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 30 May 2015 09:16:53 -0700
Subject: [PATCH 21/27] udp: fix behavior of wrong checksums

[ Upstream commit beb39db59d14990e401e235faf66a6b9b31240b0 ]

We have two problems in UDP stack related to bogus checksums :

1) We return -EAGAIN to application even if receive queue is not empty.
   This breaks applications using edge trigger epoll()

2) Under UDP flood, we can loop forever without yielding to other
   processes, potentially hanging the host, especially on non SMP.

This patch is an attempt to make things better.

We might in the future add extra support for rt applications
wanting to better control time spent doing a recv() in a hostile
environment. For example we could validate checksums before queuing
packets in socket receive queue.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 6 ++----
 net/ipv6/udp.c | 6 ++----
 2 files changed, 4 insertions(+), 8 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 97ef1f8b..e09cd47 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1348,10 +1348,8 @@ csum_copy_err:
 	}
 	unlock_sock_fast(sk, slow);
 
-	if (noblock)
-		return -EAGAIN;
-
-	/* starting over for a new packet */
+	/* starting over for a new packet, but check if we need to yield */
+	cond_resched();
 	msg->msg_flags &= ~MSG_TRUNC;
 	goto try_again;
 }
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 0c80ca7..1c9512a 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -528,10 +528,8 @@ csum_copy_err:
 	}
 	unlock_sock_fast(sk, slow);
 
-	if (noblock)
-		return -EAGAIN;
-
-	/* starting over for a new packet */
+	/* starting over for a new packet, but check if we need to yield */
+	cond_resched();
 	msg->msg_flags &= ~MSG_TRUNC;
 	goto try_again;
 }
-- 
2.1.0


From 8e3896e3a8bee3d3d093a5ba2f2d20b9aa461d46 Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Fri, 29 May 2015 13:47:07 -0400
Subject: [PATCH 22/27] tcp: fix child sockets to use system default congestion
 control if not set

[ Upstream commit 9f950415e4e28e7cfae2e416b43e862e8101d996 ]

Linux 3.17 and earlier are explicitly engineered so that if the app
doesn't specifically request a CC module on a listener before the SYN
arrives, then the child gets the system default CC when the connection
is established. See tcp_init_congestion_control() in 3.17 or earlier,
which says "if no choice made yet assign the current value set as
default". The change ("net: tcp: assign tcp cong_ops when tcp sk is
created") altered these semantics, so that children got their parent
listener's congestion control even if the system default had changed
after the listener was created.

This commit returns to those original semantics from 3.17 and earlier,
since they are the original semantics from 2007 in 4d4d3d1e8 ("[TCP]:
Congestion control initialization."), and some Linux congestion
control workflows depend on that.

In summary, if a listener socket specifically sets TCP_CONGESTION to
"x", or the route locks the CC module to "x", then the child gets
"x". Otherwise the child gets current system default from
net.ipv4.tcp_congestion_control. That's the behavior in 3.17 and
earlier, and this commit restores that.

Fixes: 55d8694fa82c ("net: tcp: assign tcp cong_ops when tcp sk is created")
Cc: Florian Westphal <fw@strlen.de>
Cc: Daniel Borkmann <dborkman@redhat.com>
Cc: Glenn Judd <glenn.judd@morganstanley.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_connection_sock.h | 3 ++-
 net/ipv4/tcp_cong.c                | 5 ++++-
 net/ipv4/tcp_minisocks.c           | 5 ++++-
 3 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 5976bde..9fe865c 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -98,7 +98,8 @@ struct inet_connection_sock {
 	const struct tcp_congestion_ops *icsk_ca_ops;
 	const struct inet_connection_sock_af_ops *icsk_af_ops;
 	unsigned int		  (*icsk_sync_mss)(struct sock *sk, u32 pmtu);
-	__u8			  icsk_ca_state:7,
+	__u8			  icsk_ca_state:6,
+				  icsk_ca_setsockopt:1,
 				  icsk_ca_dst_locked:1;
 	__u8			  icsk_retransmits;
 	__u8			  icsk_pending;
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 62856e1..9d2fbd8 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -187,6 +187,7 @@ static void tcp_reinit_congestion_control(struct sock *sk,
 
 	tcp_cleanup_congestion_control(sk);
 	icsk->icsk_ca_ops = ca;
+	icsk->icsk_ca_setsockopt = 1;
 
 	if (sk->sk_state != TCP_CLOSE && icsk->icsk_ca_ops->init)
 		icsk->icsk_ca_ops->init(sk);
@@ -335,8 +336,10 @@ int tcp_set_congestion_control(struct sock *sk, const char *name)
 	rcu_read_lock();
 	ca = __tcp_ca_find_autoload(name);
 	/* No change asking for existing value */
-	if (ca == icsk->icsk_ca_ops)
+	if (ca == icsk->icsk_ca_ops) {
+		icsk->icsk_ca_setsockopt = 1;
 		goto out;
+	}
 	if (!ca)
 		err = -ENOENT;
 	else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) ||
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 1143748..50277af 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -437,7 +437,10 @@ void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst)
 		rcu_read_unlock();
 	}
 
-	if (!ca_got_dst && !try_module_get(icsk->icsk_ca_ops->owner))
+	/* If no valid choice made yet, assign current system default ca. */
+	if (!ca_got_dst &&
+	    (!icsk->icsk_ca_setsockopt ||
+	     !try_module_get(icsk->icsk_ca_ops->owner)))
 		tcp_assign_congestion_control(sk);
 
 	tcp_set_ca_state(sk, TCP_CA_Open);
-- 
2.1.0


From 8ecb6113b8187c56a3720fb5cb148b3d98f6a230 Mon Sep 17 00:00:00 2001
From: Ian Campbell <Ian.Campbell@citrix.com>
Date: Mon, 1 Jun 2015 11:30:24 +0100
Subject: [PATCH 23/27] xen: netback: read hotplug script once at start of day.

[ Upstream commit 31a418986a5852034d520a5bab546821ff1ccf3d ]

When we come to tear things down in netback_remove() and generate the
uevent it is possible that the xenstore directory has already been
removed (details below).

In such cases netback_uevent() won't be able to read the hotplug
script and will write a xenstore error node.

A recent change to the hypervisor exposed this race such that we now
sometimes lose it (where apparently we didn't ever before).

Instead read the hotplug script configuration during setup and use it
for the lifetime of the backend device.

The apparently more obvious fix of moving the transition to
state=Closed in netback_remove() to after the uevent does not work
because it is possible that we are already in state=Closed (in
reaction to the guest having disconnected as it shutdown). Being
already in Closed means the toolstack is at liberty to start tearing
down the xenstore directories. In principal it might be possible to
arrange to unregister the device sooner (e.g on transition to Closing)
such that xenstore would still be there but this state machine is
fragile and prone to anger...

A modern Xen system only relies on the hotplug uevent for driver
domains, when the backend is in the same domain as the toolstack it
will run the necessary setup/teardown directly in the correct sequence
wrt xenstore changes.

Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Acked-by: Wei Liu <wei.liu2@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netback/xenbus.c | 33 +++++++++++++++++++--------------
 1 file changed, 19 insertions(+), 14 deletions(-)

diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index 784a624..152131a 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -34,6 +34,8 @@ struct backend_info {
 	enum xenbus_state frontend_state;
 	struct xenbus_watch hotplug_status_watch;
 	u8 have_hotplug_status_watch:1;
+
+	const char *hotplug_script;
 };
 
 static int connect_rings(struct backend_info *be, struct xenvif_queue *queue);
@@ -236,6 +238,7 @@ static int netback_remove(struct xenbus_device *dev)
 		xenvif_free(be->vif);
 		be->vif = NULL;
 	}
+	kfree(be->hotplug_script);
 	kfree(be);
 	dev_set_drvdata(&dev->dev, NULL);
 	return 0;
@@ -253,6 +256,7 @@ static int netback_probe(struct xenbus_device *dev,
 	struct xenbus_transaction xbt;
 	int err;
 	int sg;
+	const char *script;
 	struct backend_info *be = kzalloc(sizeof(struct backend_info),
 					  GFP_KERNEL);
 	if (!be) {
@@ -345,6 +349,15 @@ static int netback_probe(struct xenbus_device *dev,
 	if (err)
 		pr_debug("Error writing multi-queue-max-queues\n");
 
+	script = xenbus_read(XBT_NIL, dev->nodename, "script", NULL);
+	if (IS_ERR(script)) {
+		err = PTR_ERR(script);
+		xenbus_dev_fatal(dev, err, "reading script");
+		goto fail;
+	}
+
+	be->hotplug_script = script;
+
 	err = xenbus_switch_state(dev, XenbusStateInitWait);
 	if (err)
 		goto fail;
@@ -377,22 +390,14 @@ static int netback_uevent(struct xenbus_device *xdev,
 			  struct kobj_uevent_env *env)
 {
 	struct backend_info *be = dev_get_drvdata(&xdev->dev);
-	char *val;
 
-	val = xenbus_read(XBT_NIL, xdev->nodename, "script", NULL);
-	if (IS_ERR(val)) {
-		int err = PTR_ERR(val);
-		xenbus_dev_fatal(xdev, err, "reading script");
-		return err;
-	} else {
-		if (add_uevent_var(env, "script=%s", val)) {
-			kfree(val);
-			return -ENOMEM;
-		}
-		kfree(val);
-	}
+	if (!be)
+		return 0;
+
+	if (add_uevent_var(env, "script=%s", be->hotplug_script))
+		return -ENOMEM;
 
-	if (!be || !be->vif)
+	if (!be->vif)
 		return 0;
 
 	return add_uevent_var(env, "vif=%s", be->vif->dev->name);
-- 
2.1.0


From af3eb203734f0acc07ec10478cecc2f5f2ec7a29 Mon Sep 17 00:00:00 2001
From: Shawn Bohrer <sbohrer@rgmadvisors.com>
Date: Wed, 3 Jun 2015 16:27:38 -0500
Subject: [PATCH 24/27] ipv4/udp: Verify multicast group is ours in
 upd_v4_early_demux()

[ Upstream commit 6e540309326188f769e03bb4c6dd8ff6752930c2 ]

421b3885bf6d56391297844f43fb7154a6396e12 "udp: ipv4: Add udp early
demux" introduced a regression that allowed sockets bound to INADDR_ANY
to receive packets from multicast groups that the socket had not joined.
For example a socket that had joined 224.168.2.9 could also receive
packets from 225.168.2.9 despite not having joined that group if
ip_early_demux is enabled.

Fix this by calling ip_check_mc_rcu() in udp_v4_early_demux() to verify
that the multicast packet is indeed ours.

Signed-off-by: Shawn Bohrer <sbohrer@rgmadvisors.com>
Reported-by: Yurij M. Plotnikov <Yurij.Plotnikov@oktetlabs.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index e09cd47..51f1745 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -90,6 +90,7 @@
 #include <linux/socket.h>
 #include <linux/sockios.h>
 #include <linux/igmp.h>
+#include <linux/inetdevice.h>
 #include <linux/in.h>
 #include <linux/errno.h>
 #include <linux/timer.h>
@@ -1966,6 +1967,7 @@ void udp_v4_early_demux(struct sk_buff *skb)
 	struct sock *sk;
 	struct dst_entry *dst;
 	int dif = skb->dev->ifindex;
+	int ours;
 
 	/* validate the packet */
 	if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr)))
@@ -1975,14 +1977,24 @@ void udp_v4_early_demux(struct sk_buff *skb)
 	uh = udp_hdr(skb);
 
 	if (skb->pkt_type == PACKET_BROADCAST ||
-	    skb->pkt_type == PACKET_MULTICAST)
+	    skb->pkt_type == PACKET_MULTICAST) {
+		struct in_device *in_dev = __in_dev_get_rcu(skb->dev);
+
+		if (!in_dev)
+			return;
+
+		ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr,
+				       iph->protocol);
+		if (!ours)
+			return;
 		sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr,
 						   uh->source, iph->saddr, dif);
-	else if (skb->pkt_type == PACKET_HOST)
+	} else if (skb->pkt_type == PACKET_HOST) {
 		sk = __udp4_lib_demux_lookup(net, uh->dest, iph->daddr,
 					     uh->source, iph->saddr, dif);
-	else
+	} else {
 		return;
+	}
 
 	if (!sk)
 		return;
-- 
2.1.0


From ebf0202e44d2186722ca154f5e7d6e2d8037aeba Mon Sep 17 00:00:00 2001
From: Sriharsha Basavapatna <sriharsha.basavapatna@avagotech.com>
Date: Fri, 5 Jun 2015 15:33:59 +0530
Subject: [PATCH 25/27] be2net: Replace dma/pci_alloc_coherent() calls with
 dma_zalloc_coherent()

[ Upstream commit e51000db4c880165eab06ec0990605f24e75203f ]

There are several places in the driver (all in control paths) where
coherent dma memory is being allocated using either dma_alloc_coherent()
or the deprecated pci_alloc_consistent(). All these calls should be
changed to use dma_zalloc_coherent() to avoid uninitialized fields in
data structures backed by this memory.

Reported-by: Joerg Roedel <jroedel@suse.de>
Tested-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Sriharsha Basavapatna <sriharsha.basavapatna@avagotech.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/emulex/benet/be_cmds.c    | 87 +++++++++++++++-----------
 drivers/net/ethernet/emulex/benet/be_ethtool.c | 18 +++---
 drivers/net/ethernet/emulex/benet/be_main.c    | 16 ++---
 3 files changed, 68 insertions(+), 53 deletions(-)

diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index 7f05f30..da36bcf 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -1773,9 +1773,9 @@ int be_cmd_get_regs(struct be_adapter *adapter, u32 buf_len, void *buf)
 	total_size = buf_len;
 
 	get_fat_cmd.size = sizeof(struct be_cmd_req_get_fat) + 60*1024;
-	get_fat_cmd.va = pci_alloc_consistent(adapter->pdev,
-					      get_fat_cmd.size,
-					      &get_fat_cmd.dma);
+	get_fat_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+					     get_fat_cmd.size,
+					     &get_fat_cmd.dma, GFP_ATOMIC);
 	if (!get_fat_cmd.va) {
 		dev_err(&adapter->pdev->dev,
 			"Memory allocation failure while reading FAT data\n");
@@ -1820,8 +1820,8 @@ int be_cmd_get_regs(struct be_adapter *adapter, u32 buf_len, void *buf)
 		log_offset += buf_size;
 	}
 err:
-	pci_free_consistent(adapter->pdev, get_fat_cmd.size,
-			    get_fat_cmd.va, get_fat_cmd.dma);
+	dma_free_coherent(&adapter->pdev->dev, get_fat_cmd.size,
+			  get_fat_cmd.va, get_fat_cmd.dma);
 	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
@@ -2272,12 +2272,12 @@ int be_cmd_read_port_transceiver_data(struct be_adapter *adapter,
 		return -EINVAL;
 
 	cmd.size = sizeof(struct be_cmd_resp_port_type);
-	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma);
+	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				     GFP_ATOMIC);
 	if (!cmd.va) {
 		dev_err(&adapter->pdev->dev, "Memory allocation failed\n");
 		return -ENOMEM;
 	}
-	memset(cmd.va, 0, cmd.size);
 
 	spin_lock_bh(&adapter->mcc_lock);
 
@@ -2302,7 +2302,7 @@ int be_cmd_read_port_transceiver_data(struct be_adapter *adapter,
 	}
 err:
 	spin_unlock_bh(&adapter->mcc_lock);
-	pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
+	dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va, cmd.dma);
 	return status;
 }
 
@@ -2777,7 +2777,8 @@ int be_cmd_get_phy_info(struct be_adapter *adapter)
 		goto err;
 	}
 	cmd.size = sizeof(struct be_cmd_req_get_phy_info);
-	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma);
+	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				     GFP_ATOMIC);
 	if (!cmd.va) {
 		dev_err(&adapter->pdev->dev, "Memory alloc failure\n");
 		status = -ENOMEM;
@@ -2811,7 +2812,7 @@ int be_cmd_get_phy_info(struct be_adapter *adapter)
 				BE_SUPPORTED_SPEED_1GBPS;
 		}
 	}
-	pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
+	dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va, cmd.dma);
 err:
 	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
@@ -2862,8 +2863,9 @@ int be_cmd_get_cntl_attributes(struct be_adapter *adapter)
 
 	memset(&attribs_cmd, 0, sizeof(struct be_dma_mem));
 	attribs_cmd.size = sizeof(struct be_cmd_resp_cntl_attribs);
-	attribs_cmd.va = pci_alloc_consistent(adapter->pdev, attribs_cmd.size,
-					      &attribs_cmd.dma);
+	attribs_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+					     attribs_cmd.size,
+					     &attribs_cmd.dma, GFP_ATOMIC);
 	if (!attribs_cmd.va) {
 		dev_err(&adapter->pdev->dev, "Memory allocation failure\n");
 		status = -ENOMEM;
@@ -2890,8 +2892,8 @@ int be_cmd_get_cntl_attributes(struct be_adapter *adapter)
 err:
 	mutex_unlock(&adapter->mbox_lock);
 	if (attribs_cmd.va)
-		pci_free_consistent(adapter->pdev, attribs_cmd.size,
-				    attribs_cmd.va, attribs_cmd.dma);
+		dma_free_coherent(&adapter->pdev->dev, attribs_cmd.size,
+				  attribs_cmd.va, attribs_cmd.dma);
 	return status;
 }
 
@@ -3029,9 +3031,10 @@ int be_cmd_get_mac_from_list(struct be_adapter *adapter, u8 *mac,
 
 	memset(&get_mac_list_cmd, 0, sizeof(struct be_dma_mem));
 	get_mac_list_cmd.size = sizeof(struct be_cmd_resp_get_mac_list);
-	get_mac_list_cmd.va = pci_alloc_consistent(adapter->pdev,
-						   get_mac_list_cmd.size,
-						   &get_mac_list_cmd.dma);
+	get_mac_list_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+						  get_mac_list_cmd.size,
+						  &get_mac_list_cmd.dma,
+						  GFP_ATOMIC);
 
 	if (!get_mac_list_cmd.va) {
 		dev_err(&adapter->pdev->dev,
@@ -3104,8 +3107,8 @@ int be_cmd_get_mac_from_list(struct be_adapter *adapter, u8 *mac,
 
 out:
 	spin_unlock_bh(&adapter->mcc_lock);
-	pci_free_consistent(adapter->pdev, get_mac_list_cmd.size,
-			    get_mac_list_cmd.va, get_mac_list_cmd.dma);
+	dma_free_coherent(&adapter->pdev->dev, get_mac_list_cmd.size,
+			  get_mac_list_cmd.va, get_mac_list_cmd.dma);
 	return status;
 }
 
@@ -3158,8 +3161,8 @@ int be_cmd_set_mac_list(struct be_adapter *adapter, u8 *mac_array,
 
 	memset(&cmd, 0, sizeof(struct be_dma_mem));
 	cmd.size = sizeof(struct be_cmd_req_set_mac_list);
-	cmd.va = dma_alloc_coherent(&adapter->pdev->dev, cmd.size,
-				    &cmd.dma, GFP_KERNEL);
+	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				     GFP_KERNEL);
 	if (!cmd.va)
 		return -ENOMEM;
 
@@ -3348,7 +3351,8 @@ int be_cmd_get_acpi_wol_cap(struct be_adapter *adapter)
 
 	memset(&cmd, 0, sizeof(struct be_dma_mem));
 	cmd.size = sizeof(struct be_cmd_resp_acpi_wol_magic_config_v1);
-	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma);
+	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				     GFP_ATOMIC);
 	if (!cmd.va) {
 		dev_err(&adapter->pdev->dev, "Memory allocation failure\n");
 		status = -ENOMEM;
@@ -3383,7 +3387,8 @@ int be_cmd_get_acpi_wol_cap(struct be_adapter *adapter)
 err:
 	mutex_unlock(&adapter->mbox_lock);
 	if (cmd.va)
-		pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
+		dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va,
+				  cmd.dma);
 	return status;
 
 }
@@ -3397,8 +3402,9 @@ int be_cmd_set_fw_log_level(struct be_adapter *adapter, u32 level)
 
 	memset(&extfat_cmd, 0, sizeof(struct be_dma_mem));
 	extfat_cmd.size = sizeof(struct be_cmd_resp_get_ext_fat_caps);
-	extfat_cmd.va = pci_alloc_consistent(adapter->pdev, extfat_cmd.size,
-					     &extfat_cmd.dma);
+	extfat_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+					    extfat_cmd.size, &extfat_cmd.dma,
+					    GFP_ATOMIC);
 	if (!extfat_cmd.va)
 		return -ENOMEM;
 
@@ -3420,8 +3426,8 @@ int be_cmd_set_fw_log_level(struct be_adapter *adapter, u32 level)
 
 	status = be_cmd_set_ext_fat_capabilites(adapter, &extfat_cmd, cfgs);
 err:
-	pci_free_consistent(adapter->pdev, extfat_cmd.size, extfat_cmd.va,
-			    extfat_cmd.dma);
+	dma_free_coherent(&adapter->pdev->dev, extfat_cmd.size, extfat_cmd.va,
+			  extfat_cmd.dma);
 	return status;
 }
 
@@ -3434,8 +3440,9 @@ int be_cmd_get_fw_log_level(struct be_adapter *adapter)
 
 	memset(&extfat_cmd, 0, sizeof(struct be_dma_mem));
 	extfat_cmd.size = sizeof(struct be_cmd_resp_get_ext_fat_caps);
-	extfat_cmd.va = pci_alloc_consistent(adapter->pdev, extfat_cmd.size,
-					     &extfat_cmd.dma);
+	extfat_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+					    extfat_cmd.size, &extfat_cmd.dma,
+					    GFP_ATOMIC);
 
 	if (!extfat_cmd.va) {
 		dev_err(&adapter->pdev->dev, "%s: Memory allocation failure\n",
@@ -3453,8 +3460,8 @@ int be_cmd_get_fw_log_level(struct be_adapter *adapter)
 				level = cfgs->module[0].trace_lvl[j].dbg_lvl;
 		}
 	}
-	pci_free_consistent(adapter->pdev, extfat_cmd.size, extfat_cmd.va,
-			    extfat_cmd.dma);
+	dma_free_coherent(&adapter->pdev->dev, extfat_cmd.size, extfat_cmd.va,
+			  extfat_cmd.dma);
 err:
 	return level;
 }
@@ -3652,7 +3659,8 @@ int be_cmd_get_func_config(struct be_adapter *adapter, struct be_resources *res)
 
 	memset(&cmd, 0, sizeof(struct be_dma_mem));
 	cmd.size = sizeof(struct be_cmd_resp_get_func_config);
-	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma);
+	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				     GFP_ATOMIC);
 	if (!cmd.va) {
 		dev_err(&adapter->pdev->dev, "Memory alloc failure\n");
 		status = -ENOMEM;
@@ -3692,7 +3700,8 @@ int be_cmd_get_func_config(struct be_adapter *adapter, struct be_resources *res)
 err:
 	mutex_unlock(&adapter->mbox_lock);
 	if (cmd.va)
-		pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
+		dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va,
+				  cmd.dma);
 	return status;
 }
 
@@ -3713,7 +3722,8 @@ int be_cmd_get_profile_config(struct be_adapter *adapter,
 
 	memset(&cmd, 0, sizeof(struct be_dma_mem));
 	cmd.size = sizeof(struct be_cmd_resp_get_profile_config);
-	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma);
+	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				     GFP_ATOMIC);
 	if (!cmd.va)
 		return -ENOMEM;
 
@@ -3752,7 +3762,8 @@ int be_cmd_get_profile_config(struct be_adapter *adapter,
 		res->vf_if_cap_flags = vf_res->cap_flags;
 err:
 	if (cmd.va)
-		pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
+		dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va,
+				  cmd.dma);
 	return status;
 }
 
@@ -3767,7 +3778,8 @@ static int be_cmd_set_profile_config(struct be_adapter *adapter, void *desc,
 
 	memset(&cmd, 0, sizeof(struct be_dma_mem));
 	cmd.size = sizeof(struct be_cmd_req_set_profile_config);
-	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma);
+	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				     GFP_ATOMIC);
 	if (!cmd.va)
 		return -ENOMEM;
 
@@ -3783,7 +3795,8 @@ static int be_cmd_set_profile_config(struct be_adapter *adapter, void *desc,
 	status = be_cmd_notify_wait(adapter, &wrb);
 
 	if (cmd.va)
-		pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
+		dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va,
+				  cmd.dma);
 	return status;
 }
 
diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c
index 4d2de47..22ffcd8 100644
--- a/drivers/net/ethernet/emulex/benet/be_ethtool.c
+++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c
@@ -264,8 +264,8 @@ static int lancer_cmd_read_file(struct be_adapter *adapter, u8 *file_name,
 	int status = 0;
 
 	read_cmd.size = LANCER_READ_FILE_CHUNK;
-	read_cmd.va = pci_alloc_consistent(adapter->pdev, read_cmd.size,
-					   &read_cmd.dma);
+	read_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, read_cmd.size,
+					  &read_cmd.dma, GFP_ATOMIC);
 
 	if (!read_cmd.va) {
 		dev_err(&adapter->pdev->dev,
@@ -289,8 +289,8 @@ static int lancer_cmd_read_file(struct be_adapter *adapter, u8 *file_name,
 			break;
 		}
 	}
-	pci_free_consistent(adapter->pdev, read_cmd.size, read_cmd.va,
-			    read_cmd.dma);
+	dma_free_coherent(&adapter->pdev->dev, read_cmd.size, read_cmd.va,
+			  read_cmd.dma);
 
 	return status;
 }
@@ -818,8 +818,9 @@ static int be_test_ddr_dma(struct be_adapter *adapter)
 	};
 
 	ddrdma_cmd.size = sizeof(struct be_cmd_req_ddrdma_test);
-	ddrdma_cmd.va = dma_alloc_coherent(&adapter->pdev->dev, ddrdma_cmd.size,
-					   &ddrdma_cmd.dma, GFP_KERNEL);
+	ddrdma_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+					    ddrdma_cmd.size, &ddrdma_cmd.dma,
+					    GFP_KERNEL);
 	if (!ddrdma_cmd.va)
 		return -ENOMEM;
 
@@ -941,8 +942,9 @@ static int be_read_eeprom(struct net_device *netdev,
 
 	memset(&eeprom_cmd, 0, sizeof(struct be_dma_mem));
 	eeprom_cmd.size = sizeof(struct be_cmd_req_seeprom_read);
-	eeprom_cmd.va = dma_alloc_coherent(&adapter->pdev->dev, eeprom_cmd.size,
-					   &eeprom_cmd.dma, GFP_KERNEL);
+	eeprom_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+					    eeprom_cmd.size, &eeprom_cmd.dma,
+					    GFP_KERNEL);
 
 	if (!eeprom_cmd.va)
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index e6b790f..893753f 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -4392,8 +4392,8 @@ static int lancer_fw_download(struct be_adapter *adapter,
 
 	flash_cmd.size = sizeof(struct lancer_cmd_req_write_object)
 				+ LANCER_FW_DOWNLOAD_CHUNK;
-	flash_cmd.va = dma_alloc_coherent(dev, flash_cmd.size,
-					  &flash_cmd.dma, GFP_KERNEL);
+	flash_cmd.va = dma_zalloc_coherent(dev, flash_cmd.size,
+					   &flash_cmd.dma, GFP_KERNEL);
 	if (!flash_cmd.va)
 		return -ENOMEM;
 
@@ -4526,8 +4526,8 @@ static int be_fw_download(struct be_adapter *adapter, const struct firmware* fw)
 	}
 
 	flash_cmd.size = sizeof(struct be_cmd_write_flashrom);
-	flash_cmd.va = dma_alloc_coherent(dev, flash_cmd.size, &flash_cmd.dma,
-					  GFP_KERNEL);
+	flash_cmd.va = dma_zalloc_coherent(dev, flash_cmd.size, &flash_cmd.dma,
+					   GFP_KERNEL);
 	if (!flash_cmd.va)
 		return -ENOMEM;
 
@@ -4941,10 +4941,10 @@ static int be_ctrl_init(struct be_adapter *adapter)
 		goto done;
 
 	mbox_mem_alloc->size = sizeof(struct be_mcc_mailbox) + 16;
-	mbox_mem_alloc->va = dma_alloc_coherent(&adapter->pdev->dev,
-						mbox_mem_alloc->size,
-						&mbox_mem_alloc->dma,
-						GFP_KERNEL);
+	mbox_mem_alloc->va = dma_zalloc_coherent(&adapter->pdev->dev,
+						 mbox_mem_alloc->size,
+						 &mbox_mem_alloc->dma,
+						 GFP_KERNEL);
 	if (!mbox_mem_alloc->va) {
 		status = -ENOMEM;
 		goto unmap_pci_bars;
-- 
2.1.0


From 9e59cd5e5126d2572fa44a8766cbd76ce0fb503b Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Sat, 6 Jun 2015 06:49:00 -0700
Subject: [PATCH 26/27] bridge: disable softirqs around br_fdb_update to avoid
 lockup

[ Upstream commit c4c832f89dc468cf11dc0dd17206bace44526651 ]

br_fdb_update() can be called in process context in the following way:
br_fdb_add() -> __br_fdb_add() -> br_fdb_update() (if NTF_USE flag is set)
so we need to disable softirqs because there are softirq users of the
hash_lock. One easy way to reproduce this is to modify the bridge utility
to set NTF_USE, enable stp and then set maxageing to a low value so
br_fdb_cleanup() is called frequently and then just add new entries in
a loop. This happens because br_fdb_cleanup() is called from timer/softirq
context. The spin locks in br_fdb_update were _bh before commit f8ae737deea1
("[BRIDGE]: forwarding remove unneeded preempt and bh diasables")
and at the time that commit was correct because br_fdb_update() couldn't be
called from process context, but that changed after commit:
292d1398983f ("bridge: add NTF_USE support")
Using local_bh_disable/enable around br_fdb_update() allows us to keep
using the spin_lock/unlock in br_fdb_update for the fast-path.

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Fixes: 292d1398983f ("bridge: add NTF_USE support")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_fdb.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index e0670d7..659fb96 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -796,9 +796,11 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge_port *p,
 	int err = 0;
 
 	if (ndm->ndm_flags & NTF_USE) {
+		local_bh_disable();
 		rcu_read_lock();
 		br_fdb_update(p->br, p, addr, vid, true);
 		rcu_read_unlock();
+		local_bh_enable();
 	} else {
 		spin_lock_bh(&p->br->hash_lock);
 		err = fdb_add_entry(p, addr, ndm->ndm_state,
-- 
2.1.0


From 52fc0505b428fdb5cfeb4015af793efc3b3933d5 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Sat, 16 May 2015 21:16:28 +0800
Subject: [PATCH 27/27] netlink: Disable insertions/removals during rehash

[ Upstream commit: Not applicable ]

The current rhashtable rehash code is buggy and can't deal with
parallel insertions/removals without corrupting the hash table.

This patch disables it by partially reverting
c5adde9468b0714a051eac7f9666f23eb10b61f7 ("netlink: eliminate
nl_sk_hash_lock").

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 net/netlink/af_netlink.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index e98dc53..0e9c28d 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1052,7 +1052,7 @@ static int netlink_insert(struct sock *sk, u32 portid)
 	struct netlink_table *table = &nl_table[sk->sk_protocol];
 	int err;
 
-	lock_sock(sk);
+	mutex_lock(&table->hash.mutex);
 
 	err = -EBUSY;
 	if (nlk_sk(sk)->portid)
@@ -1074,7 +1074,7 @@ static int netlink_insert(struct sock *sk, u32 portid)
 	}
 
 err:
-	release_sock(sk);
+	mutex_unlock(&table->hash.mutex);
 	return err;
 }
 
@@ -1083,10 +1083,12 @@ static void netlink_remove(struct sock *sk)
 	struct netlink_table *table;
 
 	table = &nl_table[sk->sk_protocol];
+	mutex_lock(&table->hash.mutex);
 	if (rhashtable_remove(&table->hash, &nlk_sk(sk)->node)) {
 		WARN_ON(atomic_read(&sk->sk_refcnt) == 1);
 		__sock_put(sk);
 	}
+	mutex_unlock(&table->hash.mutex);
 
 	netlink_table_grab();
 	if (nlk_sk(sk)->subscriptions) {
-- 
2.1.0

Re: [PATCHES] Networking

[Jiri Slaby]

On 06/10/2015, 05:01 AM, David Miller wrote:
> 
> Please queue up the following networking bug fixes for 3.12.x, 3.14.x,
> 3.18.x, and 4.0.x -stable, respectively.

Applied to 3.12. Thanks!

-- 
js
suse labs

Re: [PATCHES] Networking

[Greg KH]

On Tue, Jun 09, 2015 at 08:01:04PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for 3.12.x, 3.14.x,
> 3.18.x, and 4.0.x -stable, respectively.

All queued up, thanks.

greg k-h
--
To unsubscribe from this list: send the line "unsubscribe stable" in

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 113 bytes --]


Please queue up the following networking bug fixes for 3.14, 3.18,
4.0, and 4.1 -stable, respectively.

Thanks!

[-- Attachment #2: net_314.mbox --]
[-- Type: Application/Octet-Stream, Size: 33801 bytes --]

From ce0a14da13ebb05ca80440d618b78a7a9d046abb Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <razor@blackwall.org>
Date: Tue, 9 Jun 2015 10:23:57 -0700
Subject: [PATCH 01/10] bridge: fix multicast router rlist endless loop

[ Upstream commit 1a040eaca1a22f8da8285ceda6b5e4a2cb704867 ]

Since the addition of sysfs multicast router support if one set
multicast_router to "2" more than once, then the port would be added to
the hlist every time and could end up linking to itself and thus causing an
endless loop for rlist walkers.
So to reproduce just do:
echo 2 > multicast_router; echo 2 > multicast_router;
in a bridge port and let some igmp traffic flow, for me it hangs up
in br_multicast_flood().
Fix this by adding a check in br_multicast_add_router() if the port is
already linked.
The reason this didn't happen before the addition of multicast_router
sysfs entries is because there's a !hlist_unhashed check that prevents
it.

Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Fixes: 0909e11758bd ("bridge: Add multicast_router sysfs entries")
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 11a2e6c..7bbc8fe 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1086,6 +1086,9 @@ static void br_multicast_add_router(struct net_bridge *br,
 	struct net_bridge_port *p;
 	struct hlist_node *slot = NULL;
 
+	if (!hlist_unhashed(&port->rlist))
+		return;
+
 	hlist_for_each_entry(p, &br->router_list, rlist) {
 		if ((unsigned long) port >= (unsigned long) p)
 			break;
@@ -1113,12 +1116,8 @@ static void br_multicast_mark_router(struct net_bridge *br,
 	if (port->multicast_router != 1)
 		return;
 
-	if (!hlist_unhashed(&port->rlist))
-		goto timer;
-
 	br_multicast_add_router(br, port);
 
-timer:
 	mod_timer(&port->multicast_router_timer,
 		  now + br->multicast_querier_interval);
 }
-- 
2.1.0


From e24dddfe3b6c2aa6d7f3a17f13e140d7a01c8f35 Mon Sep 17 00:00:00 2001
From: Shaohua Li <shli@fb.com>
Date: Thu, 11 Jun 2015 16:50:48 -0700
Subject: [PATCH 02/10] net: don't wait for order-3 page allocation

[ Upstream commit fb05e7a89f500cfc06ae277bdc911b281928995d ]

We saw excessive direct memory compaction triggered by skb_page_frag_refill.
This causes performance issues and add latency. Commit 5640f7685831e0
introduces the order-3 allocation. According to the changelog, the order-3
allocation isn't a must-have but to improve performance. But direct memory
compaction has high overhead. The benefit of order-3 allocation can't
compensate the overhead of direct memory compaction.

This patch makes the order-3 page allocation atomic. If there is no memory
pressure and memory isn't fragmented, the alloction will still success, so we
don't sacrifice the order-3 benefit here. If the atomic allocation fails,
direct memory compaction will not be triggered, skb_page_frag_refill will
fallback to order-0 immediately, hence the direct memory compaction overhead is
avoided. In the allocation failure case, kswapd is waken up and doing
compaction, so chances are allocation could success next time.

alloc_skb_with_frags is the same.

The mellanox driver does similar thing, if this is accepted, we must fix
the driver too.

V3: fix the same issue in alloc_skb_with_frags as pointed out by Eric
V2: make the changelog clearer

Cc: Eric Dumazet <edumazet@google.com>
Cc: Chris Mason <clm@fb.com>
Cc: Debabrata Banerjee <dbavatar@gmail.com>
Signed-off-by: Shaohua Li <shli@fb.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 4 +++-
 net/core/sock.c   | 4 +++-
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 69ec61a..8207f8d 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -368,9 +368,11 @@ refill:
 		for (order = NETDEV_FRAG_PAGE_MAX_ORDER; ;) {
 			gfp_t gfp = gfp_mask;
 
-			if (order)
+			if (order) {
 				gfp |= __GFP_COMP | __GFP_NOWARN |
 				       __GFP_NOMEMALLOC;
+				gfp &= ~__GFP_WAIT;
+			}
 			nc->frag.page = alloc_pages(gfp, order);
 			if (likely(nc->frag.page))
 				break;
diff --git a/net/core/sock.c b/net/core/sock.c
index 650dd58..8ebfa52 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1914,8 +1914,10 @@ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio)
 	do {
 		gfp_t gfp = prio;
 
-		if (order)
+		if (order) {
 			gfp |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY;
+			gfp &= ~__GFP_WAIT;
+		}
 		pfrag->page = alloc_pages(gfp, order);
 		if (likely(pfrag->page)) {
 			pfrag->offset = 0;
-- 
2.1.0


From 7a6b6feb69549c6a0e5ae8312de255829c490a4b Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Fri, 12 Jun 2015 10:16:41 -0300
Subject: [PATCH 03/10] sctp: fix ASCONF list handling

[ Upstream commit 2d45a02d0166caf2627fe91897c6ffc3b19514c4 ]

->auto_asconf_splist is per namespace and mangled by functions like
sctp_setsockopt_auto_asconf() which doesn't guarantee any serialization.

Also, the call to inet_sk_copy_descendant() was backuping
->auto_asconf_list through the copy but was not honoring
->do_auto_asconf, which could lead to list corruption if it was
different between both sockets.

This commit thus fixes the list handling by using ->addr_wq_lock
spinlock to protect the list. A special handling is done upon socket
creation and destruction for that. Error handlig on sctp_init_sock()
will never return an error after having initialized asconf, so
sctp_destroy_sock() can be called without addrq_wq_lock. The lock now
will be take on sctp_close_sock(), before locking the socket, so we
don't do it in inverse order compared to sctp_addr_wq_timeout_handler().

Instead of taking the lock on sctp_sock_migrate() for copying and
restoring the list values, it's preferred to avoid rewritting it by
implementing sctp_copy_descendant().

Issue was found with a test application that kept flipping sysctl
default_auto_asconf on and off, but one could trigger it by issuing
simultaneous setsockopt() calls on multiple sockets or by
creating/destroying sockets fast enough. This is only triggerable
locally.

Fixes: 9f7d653b67ae ("sctp: Add Auto-ASCONF support (core).")
Reported-by: Ji Jianwen <jiji@redhat.com>
Suggested-by: Neil Horman <nhorman@tuxdriver.com>
Suggested-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netns/sctp.h   |  1 +
 include/net/sctp/structs.h |  4 ++++
 net/sctp/socket.c          | 43 ++++++++++++++++++++++++++++++++-----------
 3 files changed, 37 insertions(+), 11 deletions(-)

diff --git a/include/net/netns/sctp.h b/include/net/netns/sctp.h
index 3573a81..8ba379f 100644
--- a/include/net/netns/sctp.h
+++ b/include/net/netns/sctp.h
@@ -31,6 +31,7 @@ struct netns_sctp {
 	struct list_head addr_waitq;
 	struct timer_list addr_wq_timer;
 	struct list_head auto_asconf_splist;
+	/* Lock that protects both addr_waitq and auto_asconf_splist */
 	spinlock_t addr_wq_lock;
 
 	/* Lock that protects the local_addr_list writers */
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 0dfcc92..2c2d388 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -219,6 +219,10 @@ struct sctp_sock {
 	atomic_t pd_mode;
 	/* Receive to here while partial delivery is in effect. */
 	struct sk_buff_head pd_lobby;
+
+	/* These must be the last fields, as they will skipped on copies,
+	 * like on accept and peeloff operations
+	 */
 	struct list_head auto_asconf_list;
 	int do_auto_asconf;
 };
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 604a6ac..f940fdc 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1532,8 +1532,10 @@ static void sctp_close(struct sock *sk, long timeout)
 
 	/* Supposedly, no process has access to the socket, but
 	 * the net layers still may.
+	 * Also, sctp_destroy_sock() needs to be called with addr_wq_lock
+	 * held and that should be grabbed before socket lock.
 	 */
-	local_bh_disable();
+	spin_lock_bh(&net->sctp.addr_wq_lock);
 	bh_lock_sock(sk);
 
 	/* Hold the sock, since sk_common_release() will put sock_put()
@@ -1543,7 +1545,7 @@ static void sctp_close(struct sock *sk, long timeout)
 	sk_common_release(sk);
 
 	bh_unlock_sock(sk);
-	local_bh_enable();
+	spin_unlock_bh(&net->sctp.addr_wq_lock);
 
 	sock_put(sk);
 
@@ -3511,6 +3513,7 @@ static int sctp_setsockopt_auto_asconf(struct sock *sk, char __user *optval,
 	if ((val && sp->do_auto_asconf) || (!val && !sp->do_auto_asconf))
 		return 0;
 
+	spin_lock_bh(&sock_net(sk)->sctp.addr_wq_lock);
 	if (val == 0 && sp->do_auto_asconf) {
 		list_del(&sp->auto_asconf_list);
 		sp->do_auto_asconf = 0;
@@ -3519,6 +3522,7 @@ static int sctp_setsockopt_auto_asconf(struct sock *sk, char __user *optval,
 		    &sock_net(sk)->sctp.auto_asconf_splist);
 		sp->do_auto_asconf = 1;
 	}
+	spin_unlock_bh(&sock_net(sk)->sctp.addr_wq_lock);
 	return 0;
 }
 
@@ -4009,18 +4013,28 @@ static int sctp_init_sock(struct sock *sk)
 	local_bh_disable();
 	percpu_counter_inc(&sctp_sockets_allocated);
 	sock_prot_inuse_add(net, sk->sk_prot, 1);
+
+	/* Nothing can fail after this block, otherwise
+	 * sctp_destroy_sock() will be called without addr_wq_lock held
+	 */
 	if (net->sctp.default_auto_asconf) {
+		spin_lock(&sock_net(sk)->sctp.addr_wq_lock);
 		list_add_tail(&sp->auto_asconf_list,
 		    &net->sctp.auto_asconf_splist);
 		sp->do_auto_asconf = 1;
-	} else
+		spin_unlock(&sock_net(sk)->sctp.addr_wq_lock);
+	} else {
 		sp->do_auto_asconf = 0;
+	}
+
 	local_bh_enable();
 
 	return 0;
 }
 
-/* Cleanup any SCTP per socket resources.  */
+/* Cleanup any SCTP per socket resources. Must be called with
+ * sock_net(sk)->sctp.addr_wq_lock held if sp->do_auto_asconf is true
+ */
 static void sctp_destroy_sock(struct sock *sk)
 {
 	struct sctp_sock *sp;
@@ -6973,6 +6987,19 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk,
 	newinet->mc_list = NULL;
 }
 
+static inline void sctp_copy_descendant(struct sock *sk_to,
+					const struct sock *sk_from)
+{
+	int ancestor_size = sizeof(struct inet_sock) +
+			    sizeof(struct sctp_sock) -
+			    offsetof(struct sctp_sock, auto_asconf_list);
+
+	if (sk_from->sk_family == PF_INET6)
+		ancestor_size += sizeof(struct ipv6_pinfo);
+
+	__inet_sk_copy_descendant(sk_to, sk_from, ancestor_size);
+}
+
 /* Populate the fields of the newsk from the oldsk and migrate the assoc
  * and its messages to the newsk.
  */
@@ -6987,7 +7014,6 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
 	struct sk_buff *skb, *tmp;
 	struct sctp_ulpevent *event;
 	struct sctp_bind_hashbucket *head;
-	struct list_head tmplist;
 
 	/* Migrate socket buffer sizes and all the socket level options to the
 	 * new socket.
@@ -6995,12 +7021,7 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
 	newsk->sk_sndbuf = oldsk->sk_sndbuf;
 	newsk->sk_rcvbuf = oldsk->sk_rcvbuf;
 	/* Brute force copy old sctp opt. */
-	if (oldsp->do_auto_asconf) {
-		memcpy(&tmplist, &newsp->auto_asconf_list, sizeof(tmplist));
-		inet_sk_copy_descendant(newsk, oldsk);
-		memcpy(&newsp->auto_asconf_list, &tmplist, sizeof(tmplist));
-	} else
-		inet_sk_copy_descendant(newsk, oldsk);
+	sctp_copy_descendant(newsk, oldsk);
 
 	/* Restore the ep value that was overwritten with the above structure
 	 * copy.
-- 
2.1.0


From c01ad8fca91c171e7a877e227272f92ec4a16559 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <razor@blackwall.org>
Date: Mon, 15 Jun 2015 20:28:51 +0300
Subject: [PATCH 04/10] bridge: fix br_stp_set_bridge_priority race conditions

[ Upstream commit 2dab80a8b486f02222a69daca6859519e05781d9 ]

After the ->set() spinlocks were removed br_stp_set_bridge_priority
was left running without any protection when used via sysfs. It can
race with port add/del and could result in use-after-free cases and
corrupted lists. Tested by running port add/del in a loop with stp
enabled while setting priority in a loop, crashes are easily
reproducible.
The spinlocks around sysfs ->set() were removed in commit:
14f98f258f19 ("bridge: range check STP parameters")
There's also a race condition in the netlink priority support that is
fixed by this change, but it was introduced recently and the fixes tag
covers it, just in case it's needed the commit is:
af615762e972 ("bridge: add ageing_time, stp_state, priority over netlink")

Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Fixes: 14f98f258f19 ("bridge: range check STP parameters")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_ioctl.c  | 2 --
 net/bridge/br_stp_if.c | 4 +++-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c
index a9a4a1b..8d423bc 100644
--- a/net/bridge/br_ioctl.c
+++ b/net/bridge/br_ioctl.c
@@ -247,9 +247,7 @@ static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 		if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN))
 			return -EPERM;
 
-		spin_lock_bh(&br->lock);
 		br_stp_set_bridge_priority(br, args[1]);
-		spin_unlock_bh(&br->lock);
 		return 0;
 
 	case BRCTL_SET_PORT_PRIORITY:
diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
index 189ba1e..9a0005a 100644
--- a/net/bridge/br_stp_if.c
+++ b/net/bridge/br_stp_if.c
@@ -243,12 +243,13 @@ bool br_stp_recalculate_bridge_id(struct net_bridge *br)
 	return true;
 }
 
-/* called under bridge lock */
+/* Acquires and releases bridge lock */
 void br_stp_set_bridge_priority(struct net_bridge *br, u16 newprio)
 {
 	struct net_bridge_port *p;
 	int wasroot;
 
+	spin_lock_bh(&br->lock);
 	wasroot = br_is_root_bridge(br);
 
 	list_for_each_entry(p, &br->port_list, list) {
@@ -266,6 +267,7 @@ void br_stp_set_bridge_priority(struct net_bridge *br, u16 newprio)
 	br_port_state_selection(br);
 	if (br_is_root_bridge(br) && !wasroot)
 		br_become_root_bridge(br);
+	spin_unlock_bh(&br->lock);
 }
 
 /* called under bridge lock */
-- 
2.1.0


From 7eaeca482f0b10db9e87dcfe24b23c901c238508 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 16 Jun 2015 07:59:11 -0700
Subject: [PATCH 05/10] packet: read num_members once in packet_rcv_fanout()

[ Upstream commit f98f4514d07871da7a113dd9e3e330743fd70ae4 ]

We need to tell compiler it must not read f->num_members multiple
times. Otherwise testing if num is not zero is flaky, and we could
attempt an invalid divide by 0 in fanout_demux_cpu()

Note bug was present in packet_rcv_fanout_hash() and
packet_rcv_fanout_lb() but final 3.1 had a simple location
after commit 95ec3eb417115fb ("packet: Add 'cpu' fanout policy.")

Fixes: dc99f600698dc ("packet: Add fanout support.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 48b1817..f238530 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1345,7 +1345,7 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
 			     struct packet_type *pt, struct net_device *orig_dev)
 {
 	struct packet_fanout *f = pt->af_packet_priv;
-	unsigned int num = f->num_members;
+	unsigned int num = ACCESS_ONCE(f->num_members);
 	struct packet_sock *po;
 	unsigned int idx;
 
-- 
2.1.0


From 8ce7b05834926e77bd319904fc039e8ae05649e7 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 17 Jun 2015 15:59:34 -0400
Subject: [PATCH 06/10] packet: avoid out of bounds read in round robin fanout

[ Upstream commit 468479e6043c84f5a65299cc07cb08a22a28c2b1 ]

PACKET_FANOUT_LB computes f->rr_cur such that it is modulo
f->num_members. It returns the old value unconditionally, but
f->num_members may have changed since the last store. Ensure
that the return value is always < num.

When modifying the logic, simplify it further by replacing the loop
with an unconditional atomic increment.

Fixes: dc99f600698d ("packet: Add fanout support.")
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 18 ++----------------
 1 file changed, 2 insertions(+), 16 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index f238530..84a60b8 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1264,16 +1264,6 @@ static void packet_sock_destruct(struct sock *sk)
 	sk_refcnt_debug_dec(sk);
 }
 
-static int fanout_rr_next(struct packet_fanout *f, unsigned int num)
-{
-	int x = atomic_read(&f->rr_cur) + 1;
-
-	if (x >= num)
-		x = 0;
-
-	return x;
-}
-
 static unsigned int fanout_demux_hash(struct packet_fanout *f,
 				      struct sk_buff *skb,
 				      unsigned int num)
@@ -1285,13 +1275,9 @@ static unsigned int fanout_demux_lb(struct packet_fanout *f,
 				    struct sk_buff *skb,
 				    unsigned int num)
 {
-	int cur, old;
+	unsigned int val = atomic_inc_return(&f->rr_cur);
 
-	cur = atomic_read(&f->rr_cur);
-	while ((old = atomic_cmpxchg(&f->rr_cur, cur,
-				     fanout_rr_next(f, num))) != cur)
-		cur = old;
-	return cur;
+	return val % num;
 }
 
 static unsigned int fanout_demux_cpu(struct packet_fanout *f,
-- 
2.1.0


From 60cbc8b9178271d4c9e671bae16003d825d401e8 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Tue, 16 Jun 2015 22:56:39 +0300
Subject: [PATCH 07/10] neigh: do not modify unlinked entries

[ Upstream commit 2c51a97f76d20ebf1f50fef908b986cb051fdff9 ]

The lockless lookups can return entry that is unlinked.
Sometimes they get reference before last neigh_cleanup_and_release,
sometimes they do not need reference. Later, any
modification attempts may result in the following problems:

1. entry is not destroyed immediately because neigh_update
can start the timer for dead entry, eg. on change to NUD_REACHABLE
state. As result, entry lives for some time but is invisible
and out of control.

2. __neigh_event_send can run in parallel with neigh_destroy
while refcnt=0 but if timer is started and expired refcnt can
reach 0 for second time leading to second neigh_destroy and
possible crash.

Thanks to Eric Dumazet and Ying Xue for their work and analyze
on the __neigh_event_send change.

Fixes: 767e97e1e0db ("neigh: RCU conversion of struct neighbour")
Fixes: a263b3093641 ("ipv4: Make neigh lookups directly in output packet path.")
Fixes: 6fd6ce2056de ("ipv6: Do not depend on rt->n in ip6_finish_output2().")
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 7d95f69..0f062c6 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -976,6 +976,8 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
 	rc = 0;
 	if (neigh->nud_state & (NUD_CONNECTED | NUD_DELAY | NUD_PROBE))
 		goto out_unlock_bh;
+	if (neigh->dead)
+		goto out_dead;
 
 	if (!(neigh->nud_state & (NUD_STALE | NUD_INCOMPLETE))) {
 		if (NEIGH_VAR(neigh->parms, MCAST_PROBES) +
@@ -1032,6 +1034,13 @@ out_unlock_bh:
 		write_unlock(&neigh->lock);
 	local_bh_enable();
 	return rc;
+
+out_dead:
+	if (neigh->nud_state & NUD_STALE)
+		goto out_unlock_bh;
+	write_unlock_bh(&neigh->lock);
+	kfree_skb(skb);
+	return 1;
 }
 EXPORT_SYMBOL(__neigh_event_send);
 
@@ -1095,6 +1104,8 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
 	if (!(flags & NEIGH_UPDATE_F_ADMIN) &&
 	    (old & (NUD_NOARP | NUD_PERMANENT)))
 		goto out;
+	if (neigh->dead)
+		goto out;
 
 	if (!(new & NUD_VALID)) {
 		neigh_del_timer(neigh);
@@ -1244,6 +1255,8 @@ EXPORT_SYMBOL(neigh_update);
  */
 void __neigh_set_probe_once(struct neighbour *neigh)
 {
+	if (neigh->dead)
+		return;
 	neigh->updated = jiffies;
 	if (!(neigh->nud_state & NUD_FAILED))
 		return;
-- 
2.1.0


From fd4c16c4bd895d9ac6e0a75ab32ead1e4be6b0cd Mon Sep 17 00:00:00 2001
From: Christoph Paasch <cpaasch@apple.com>
Date: Thu, 18 Jun 2015 09:15:34 -0700
Subject: [PATCH 08/10] tcp: Do not call tcp_fastopen_reset_cipher from
 interrupt context

[ Upstream commit dfea2aa654243f70dc53b8648d0bbdeec55a7df1 ]

tcp_fastopen_reset_cipher really cannot be called from interrupt
context. It allocates the tcp_fastopen_context with GFP_KERNEL and
calls crypto_alloc_cipher, which allocates all kind of stuff with
GFP_KERNEL.

Thus, we might sleep when the key-generation is triggered by an
incoming TFO cookie-request which would then happen in interrupt-
context, as shown by enabling CONFIG_DEBUG_ATOMIC_SLEEP:

[   36.001813] BUG: sleeping function called from invalid context at mm/slub.c:1266
[   36.003624] in_atomic(): 1, irqs_disabled(): 0, pid: 1016, name: packetdrill
[   36.004859] CPU: 1 PID: 1016 Comm: packetdrill Not tainted 4.1.0-rc7 #14
[   36.006085] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.7.5-0-ge51488c-20140602_164612-nilsson.home.kraxel.org 04/01/2014
[   36.008250]  00000000000004f2 ffff88007f8838a8 ffffffff8171d53a ffff880075a084a8
[   36.009630]  ffff880075a08000 ffff88007f8838c8 ffffffff810967d3 ffff88007f883928
[   36.011076]  0000000000000000 ffff88007f8838f8 ffffffff81096892 ffff88007f89be00
[   36.012494] Call Trace:
[   36.012953]  <IRQ>  [<ffffffff8171d53a>] dump_stack+0x4f/0x6d
[   36.014085]  [<ffffffff810967d3>] ___might_sleep+0x103/0x170
[   36.015117]  [<ffffffff81096892>] __might_sleep+0x52/0x90
[   36.016117]  [<ffffffff8118e887>] kmem_cache_alloc_trace+0x47/0x190
[   36.017266]  [<ffffffff81680d82>] ? tcp_fastopen_reset_cipher+0x42/0x130
[   36.018485]  [<ffffffff81680d82>] tcp_fastopen_reset_cipher+0x42/0x130
[   36.019679]  [<ffffffff81680f01>] tcp_fastopen_init_key_once+0x61/0x70
[   36.020884]  [<ffffffff81680f2c>] __tcp_fastopen_cookie_gen+0x1c/0x60
[   36.022058]  [<ffffffff816814ff>] tcp_try_fastopen+0x58f/0x730
[   36.023118]  [<ffffffff81671788>] tcp_conn_request+0x3e8/0x7b0
[   36.024185]  [<ffffffff810e3872>] ? __module_text_address+0x12/0x60
[   36.025327]  [<ffffffff8167b2e1>] tcp_v4_conn_request+0x51/0x60
[   36.026410]  [<ffffffff816727e0>] tcp_rcv_state_process+0x190/0xda0
[   36.027556]  [<ffffffff81661f97>] ? __inet_lookup_established+0x47/0x170
[   36.028784]  [<ffffffff8167c2ad>] tcp_v4_do_rcv+0x16d/0x3d0
[   36.029832]  [<ffffffff812e6806>] ? security_sock_rcv_skb+0x16/0x20
[   36.030936]  [<ffffffff8167cc8a>] tcp_v4_rcv+0x77a/0x7b0
[   36.031875]  [<ffffffff816af8c3>] ? iptable_filter_hook+0x33/0x70
[   36.032953]  [<ffffffff81657d22>] ip_local_deliver_finish+0x92/0x1f0
[   36.034065]  [<ffffffff81657f1a>] ip_local_deliver+0x9a/0xb0
[   36.035069]  [<ffffffff81657c90>] ? ip_rcv+0x3d0/0x3d0
[   36.035963]  [<ffffffff81657569>] ip_rcv_finish+0x119/0x330
[   36.036950]  [<ffffffff81657ba7>] ip_rcv+0x2e7/0x3d0
[   36.037847]  [<ffffffff81610652>] __netif_receive_skb_core+0x552/0x930
[   36.038994]  [<ffffffff81610a57>] __netif_receive_skb+0x27/0x70
[   36.040033]  [<ffffffff81610b72>] process_backlog+0xd2/0x1f0
[   36.041025]  [<ffffffff81611482>] net_rx_action+0x122/0x310
[   36.042007]  [<ffffffff81076743>] __do_softirq+0x103/0x2f0
[   36.042978]  [<ffffffff81723e3c>] do_softirq_own_stack+0x1c/0x30

This patch moves the call to tcp_fastopen_init_key_once to the places
where a listener socket creates its TFO-state, which always happens in
user-context (either from the setsockopt, or implicitly during the
listen()-call)

Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Fixes: 222e83d2e0ae ("tcp: switch tcp_fastopen key generation to net_get_random_once")
Signed-off-by: Christoph Paasch <cpaasch@apple.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/af_inet.c      | 2 ++
 net/ipv4/tcp.c          | 7 +++++--
 net/ipv4/tcp_fastopen.c | 2 --
 3 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 07bd8ed..951fe55 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -228,6 +228,8 @@ int inet_listen(struct socket *sock, int backlog)
 				err = 0;
 			if (err)
 				goto out;
+
+			tcp_fastopen_init_key_once(true);
 		}
 		err = inet_csk_listen_start(sk, backlog);
 		if (err)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 29d240b..dc45221 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2684,10 +2684,13 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 
 	case TCP_FASTOPEN:
 		if (val >= 0 && ((1 << sk->sk_state) & (TCPF_CLOSE |
-		    TCPF_LISTEN)))
+		    TCPF_LISTEN))) {
+			tcp_fastopen_init_key_once(true);
+
 			err = fastopen_init_queue(sk, val);
-		else
+		} else {
 			err = -EINVAL;
+		}
 		break;
 	case TCP_TIMESTAMP:
 		if (!tp->repair)
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index f195d93..ee6518d 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -84,8 +84,6 @@ void tcp_fastopen_cookie_gen(__be32 src, __be32 dst,
 	__be32 path[4] = { src, dst, 0, 0 };
 	struct tcp_fastopen_context *ctx;
 
-	tcp_fastopen_init_key_once(true);
-
 	rcu_read_lock();
 	ctx = rcu_dereference(tcp_fastopen_ctx);
 	if (ctx) {
-- 
2.1.0


From 699dad6e73ec6618dfd7379a087ea553bfe631fb Mon Sep 17 00:00:00 2001
From: Mugunthan V N <mugunthanvnm@ti.com>
Date: Thu, 25 Jun 2015 22:21:02 +0530
Subject: [PATCH 09/10] net: phy: fix phy link up when limiting speed via
 device tree

[ Upstream commit eb686231fce3770299760f24fdcf5ad041f44153 ]

When limiting phy link speed using "max-speed" to 100mbps or less on a
giga bit phy, phy never completes auto negotiation and phy state
machine is held in PHY_AN. Fixing this issue by comparing the giga
bit advertise though phydev->supported doesn't have it but phy has
BMSR_ESTATEN set. So that auto negotiation is restarted as old and
new advertise are different and link comes up fine.

Signed-off-by: Mugunthan V N <mugunthanvnm@ti.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 25f7419..62c3fb9 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -765,10 +765,11 @@ static int genphy_config_advert(struct phy_device *phydev)
 	if (phydev->supported & (SUPPORTED_1000baseT_Half |
 				 SUPPORTED_1000baseT_Full)) {
 		adv |= ethtool_adv_to_mii_ctrl1000_t(advertise);
-		if (adv != oldadv)
-			changed = 1;
 	}
 
+	if (adv != oldadv)
+		changed = 1;
+
 	err = phy_write(phydev, MII_CTRL1000, adv);
 	if (err < 0)
 		return err;
-- 
2.1.0


From 5580bdbdf203d2feba885ac06193a780a1b7a146 Mon Sep 17 00:00:00 2001
From: Alexander Sverdlin <alexander.sverdlin@nokia.com>
Date: Mon, 29 Jun 2015 10:41:03 +0200
Subject: [PATCH 10/10] sctp: Fix race between OOTB responce and route removal

[ Upstream commit 29c4afc4e98f4dc0ea9df22c631841f9c220b944 ]

There is NULL pointer dereference possible during statistics update if the route
used for OOTB responce is removed at unfortunate time. If the route exists when
we receive OOTB packet and we finally jump into sctp_packet_transmit() to send
ABORT, but in the meantime route is removed under our feet, we take "no_route"
path and try to update stats with IP_INC_STATS(sock_net(asoc->base.sk), ...).

But sctp_ootb_pkt_new() used to prepare responce packet doesn't call
sctp_transport_set_owner() and therefore there is no asoc associated with this
packet. Probably temporary asoc just for OOTB responces is overkill, so just
introduce a check like in all other places in sctp_packet_transmit(), where
"asoc" is dereferenced.

To reproduce this, one needs to
0. ensure that sctp module is loaded (otherwise ABORT is not generated)
1. remove default route on the machine
2. while true; do
     ip route del [interface-specific route]
     ip route add [interface-specific route]
   done
3. send enough OOTB packets (i.e. HB REQs) from another host to trigger ABORT
   responce

On x86_64 the crash looks like this:

BUG: unable to handle kernel NULL pointer dereference at 0000000000000020
IP: [<ffffffffa05ec9ac>] sctp_packet_transmit+0x63c/0x730 [sctp]
PGD 0
Oops: 0000 [#1] PREEMPT SMP
Modules linked in: ...
CPU: 0 PID: 0 Comm: swapper/0 Tainted: G           O    4.0.5-1-ARCH #1
Hardware name: ...
task: ffffffff818124c0 ti: ffffffff81800000 task.ti: ffffffff81800000
RIP: 0010:[<ffffffffa05ec9ac>]  [<ffffffffa05ec9ac>] sctp_packet_transmit+0x63c/0x730 [sctp]
RSP: 0018:ffff880127c037b8  EFLAGS: 00010296
RAX: 0000000000000000 RBX: 0000000000000000 RCX: 00000015ff66b480
RDX: 00000015ff66b400 RSI: ffff880127c17200 RDI: ffff880123403700
RBP: ffff880127c03888 R08: 0000000000017200 R09: ffffffff814625af
R10: ffffea00047e4680 R11: 00000000ffffff80 R12: ffff8800b0d38a28
R13: ffff8800b0d38a28 R14: ffff8800b3e88000 R15: ffffffffa05f24e0
FS:  0000000000000000(0000) GS:ffff880127c00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
CR2: 0000000000000020 CR3: 00000000c855b000 CR4: 00000000000007f0
Stack:
 ffff880127c03910 ffff8800b0d38a28 ffffffff8189d240 ffff88011f91b400
 ffff880127c03828 ffffffffa05c94c5 0000000000000000 ffff8800baa1c520
 0000000000000000 0000000000000001 0000000000000000 0000000000000000
Call Trace:
 <IRQ>
 [<ffffffffa05c94c5>] ? sctp_sf_tabort_8_4_8.isra.20+0x85/0x140 [sctp]
 [<ffffffffa05d6b42>] ? sctp_transport_put+0x52/0x80 [sctp]
 [<ffffffffa05d0bfc>] sctp_do_sm+0xb8c/0x19a0 [sctp]
 [<ffffffff810b0e00>] ? trigger_load_balance+0x90/0x210
 [<ffffffff810e0329>] ? update_process_times+0x59/0x60
 [<ffffffff812c7a40>] ? timerqueue_add+0x60/0xb0
 [<ffffffff810e0549>] ? enqueue_hrtimer+0x29/0xa0
 [<ffffffff8101f599>] ? read_tsc+0x9/0x10
 [<ffffffff8116d4b5>] ? put_page+0x55/0x60
 [<ffffffff810ee1ad>] ? clockevents_program_event+0x6d/0x100
 [<ffffffff81462b68>] ? skb_free_head+0x58/0x80
 [<ffffffffa029a10b>] ? chksum_update+0x1b/0x27 [crc32c_generic]
 [<ffffffff81283f3e>] ? crypto_shash_update+0xce/0xf0
 [<ffffffffa05d3993>] sctp_endpoint_bh_rcv+0x113/0x280 [sctp]
 [<ffffffffa05dd4e6>] sctp_inq_push+0x46/0x60 [sctp]
 [<ffffffffa05ed7a0>] sctp_rcv+0x880/0x910 [sctp]
 [<ffffffffa05ecb50>] ? sctp_packet_transmit_chunk+0xb0/0xb0 [sctp]
 [<ffffffffa05ecb70>] ? sctp_csum_update+0x20/0x20 [sctp]
 [<ffffffff814b05a5>] ? ip_route_input_noref+0x235/0xd30
 [<ffffffff81051d6b>] ? ack_ioapic_level+0x7b/0x150
 [<ffffffff814b27be>] ip_local_deliver_finish+0xae/0x210
 [<ffffffff814b2e15>] ip_local_deliver+0x35/0x90
 [<ffffffff814b2a15>] ip_rcv_finish+0xf5/0x370
 [<ffffffff814b3128>] ip_rcv+0x2b8/0x3a0
 [<ffffffff81474193>] __netif_receive_skb_core+0x763/0xa50
 [<ffffffff81476c28>] __netif_receive_skb+0x18/0x60
 [<ffffffff81476cb0>] netif_receive_skb_internal+0x40/0xd0
 [<ffffffff814776c8>] napi_gro_receive+0xe8/0x120
 [<ffffffffa03946aa>] rtl8169_poll+0x2da/0x660 [r8169]
 [<ffffffff8147896a>] net_rx_action+0x21a/0x360
 [<ffffffff81078dc1>] __do_softirq+0xe1/0x2d0
 [<ffffffff8107912d>] irq_exit+0xad/0xb0
 [<ffffffff8157d158>] do_IRQ+0x58/0xf0
 [<ffffffff8157b06d>] common_interrupt+0x6d/0x6d
 <EOI>
 [<ffffffff810e1218>] ? hrtimer_start+0x18/0x20
 [<ffffffffa05d65f9>] ? sctp_transport_destroy_rcu+0x29/0x30 [sctp]
 [<ffffffff81020c50>] ? mwait_idle+0x60/0xa0
 [<ffffffff810216ef>] arch_cpu_idle+0xf/0x20
 [<ffffffff810b731c>] cpu_startup_entry+0x3ec/0x480
 [<ffffffff8156b365>] rest_init+0x85/0x90
 [<ffffffff818eb035>] start_kernel+0x48b/0x4ac
 [<ffffffff818ea120>] ? early_idt_handlers+0x120/0x120
 [<ffffffff818ea339>] x86_64_start_reservations+0x2a/0x2c
 [<ffffffff818ea49c>] x86_64_start_kernel+0x161/0x184
Code: 90 48 8b 80 b8 00 00 00 48 89 85 70 ff ff ff 48 83 bd 70 ff ff ff 00 0f 85 cd fa ff ff 48 89 df 31 db e8 18 63 e7 e0 48 8b 45 80 <48> 8b 40 20 48 8b 40 30 48 8b 80 68 01 00 00 65 48 ff 40 78 e9
RIP  [<ffffffffa05ec9ac>] sctp_packet_transmit+0x63c/0x730 [sctp]
 RSP <ffff880127c037b8>
CR2: 0000000000000020
---[ end trace 5aec7fd2dc983574 ]---
Kernel panic - not syncing: Fatal exception in interrupt
Kernel Offset: 0x0 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffff9fffffff)
drm_kms_helper: panic occurred, switching back to text console
---[ end Kernel panic - not syncing: Fatal exception in interrupt

Signed-off-by: Alexander Sverdlin <alexander.sverdlin@nokia.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/output.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sctp/output.c b/net/sctp/output.c
index 740ca5f..e39e6d5 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -599,7 +599,9 @@ out:
 	return err;
 no_route:
 	kfree_skb(nskb);
-	IP_INC_STATS(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES);
+
+	if (asoc)
+		IP_INC_STATS(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES);
 
 	/* FIXME: Returning the 'err' will effect all the associations
 	 * associated with a socket, although only one of the paths of the
-- 
2.1.0


[-- Attachment #3: net_318.mbox --]
[-- Type: Application/Octet-Stream, Size: 55616 bytes --]

From b1a1d95420dcd1175c9fafcb9d21f9d86bd585f6 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <razor@blackwall.org>
Date: Tue, 9 Jun 2015 10:23:57 -0700
Subject: [PATCH 01/16] bridge: fix multicast router rlist endless loop

[ Upstream commit 1a040eaca1a22f8da8285ceda6b5e4a2cb704867 ]

Since the addition of sysfs multicast router support if one set
multicast_router to "2" more than once, then the port would be added to
the hlist every time and could end up linking to itself and thus causing an
endless loop for rlist walkers.
So to reproduce just do:
echo 2 > multicast_router; echo 2 > multicast_router;
in a bridge port and let some igmp traffic flow, for me it hangs up
in br_multicast_flood().
Fix this by adding a check in br_multicast_add_router() if the port is
already linked.
The reason this didn't happen before the addition of multicast_router
sysfs entries is because there's a !hlist_unhashed check that prevents
it.

Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Fixes: 0909e11758bd ("bridge: Add multicast_router sysfs entries")
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index b0aee78..c08f510 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1166,6 +1166,9 @@ static void br_multicast_add_router(struct net_bridge *br,
 	struct net_bridge_port *p;
 	struct hlist_node *slot = NULL;
 
+	if (!hlist_unhashed(&port->rlist))
+		return;
+
 	hlist_for_each_entry(p, &br->router_list, rlist) {
 		if ((unsigned long) port >= (unsigned long) p)
 			break;
@@ -1193,12 +1196,8 @@ static void br_multicast_mark_router(struct net_bridge *br,
 	if (port->multicast_router != 1)
 		return;
 
-	if (!hlist_unhashed(&port->rlist))
-		goto timer;
-
 	br_multicast_add_router(br, port);
 
-timer:
 	mod_timer(&port->multicast_router_timer,
 		  now + br->multicast_querier_interval);
 }
-- 
2.1.0


From e9916309e726585b46f40c3f0c14484471d9a2b9 Mon Sep 17 00:00:00 2001
From: Shaohua Li <shli@fb.com>
Date: Thu, 11 Jun 2015 16:50:48 -0700
Subject: [PATCH 02/16] net: don't wait for order-3 page allocation

[ Upstream commit fb05e7a89f500cfc06ae277bdc911b281928995d ]

We saw excessive direct memory compaction triggered by skb_page_frag_refill.
This causes performance issues and add latency. Commit 5640f7685831e0
introduces the order-3 allocation. According to the changelog, the order-3
allocation isn't a must-have but to improve performance. But direct memory
compaction has high overhead. The benefit of order-3 allocation can't
compensate the overhead of direct memory compaction.

This patch makes the order-3 page allocation atomic. If there is no memory
pressure and memory isn't fragmented, the alloction will still success, so we
don't sacrifice the order-3 benefit here. If the atomic allocation fails,
direct memory compaction will not be triggered, skb_page_frag_refill will
fallback to order-0 immediately, hence the direct memory compaction overhead is
avoided. In the allocation failure case, kswapd is waken up and doing
compaction, so chances are allocation could success next time.

alloc_skb_with_frags is the same.

The mellanox driver does similar thing, if this is accepted, we must fix
the driver too.

V3: fix the same issue in alloc_skb_with_frags as pointed out by Eric
V2: make the changelog clearer

Cc: Eric Dumazet <edumazet@google.com>
Cc: Chris Mason <clm@fb.com>
Cc: Debabrata Banerjee <dbavatar@gmail.com>
Signed-off-by: Shaohua Li <shli@fb.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 2 +-
 net/core/sock.c   | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 02ebb71..72400a1 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4199,7 +4199,7 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len,
 
 		while (order) {
 			if (npages >= 1 << order) {
-				page = alloc_pages(gfp_mask |
+				page = alloc_pages((gfp_mask & ~__GFP_WAIT) |
 						   __GFP_COMP |
 						   __GFP_NOWARN |
 						   __GFP_NORETRY,
diff --git a/net/core/sock.c b/net/core/sock.c
index 852acbc..1e5130d 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1854,7 +1854,7 @@ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t gfp)
 
 	pfrag->offset = 0;
 	if (SKB_FRAG_PAGE_ORDER) {
-		pfrag->page = alloc_pages(gfp | __GFP_COMP |
+		pfrag->page = alloc_pages((gfp & ~__GFP_WAIT) | __GFP_COMP |
 					  __GFP_NOWARN | __GFP_NORETRY,
 					  SKB_FRAG_PAGE_ORDER);
 		if (likely(pfrag->page)) {
-- 
2.1.0


From e20043fa2981663fe62ab011a314405bae1b7b6c Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Fri, 12 Jun 2015 10:16:41 -0300
Subject: [PATCH 03/16] sctp: fix ASCONF list handling

[ Upstream commit 2d45a02d0166caf2627fe91897c6ffc3b19514c4 ]

->auto_asconf_splist is per namespace and mangled by functions like
sctp_setsockopt_auto_asconf() which doesn't guarantee any serialization.

Also, the call to inet_sk_copy_descendant() was backuping
->auto_asconf_list through the copy but was not honoring
->do_auto_asconf, which could lead to list corruption if it was
different between both sockets.

This commit thus fixes the list handling by using ->addr_wq_lock
spinlock to protect the list. A special handling is done upon socket
creation and destruction for that. Error handlig on sctp_init_sock()
will never return an error after having initialized asconf, so
sctp_destroy_sock() can be called without addrq_wq_lock. The lock now
will be take on sctp_close_sock(), before locking the socket, so we
don't do it in inverse order compared to sctp_addr_wq_timeout_handler().

Instead of taking the lock on sctp_sock_migrate() for copying and
restoring the list values, it's preferred to avoid rewritting it by
implementing sctp_copy_descendant().

Issue was found with a test application that kept flipping sysctl
default_auto_asconf on and off, but one could trigger it by issuing
simultaneous setsockopt() calls on multiple sockets or by
creating/destroying sockets fast enough. This is only triggerable
locally.

Fixes: 9f7d653b67ae ("sctp: Add Auto-ASCONF support (core).")
Reported-by: Ji Jianwen <jiji@redhat.com>
Suggested-by: Neil Horman <nhorman@tuxdriver.com>
Suggested-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netns/sctp.h   |  1 +
 include/net/sctp/structs.h |  4 ++++
 net/sctp/socket.c          | 43 ++++++++++++++++++++++++++++++++-----------
 3 files changed, 37 insertions(+), 11 deletions(-)

diff --git a/include/net/netns/sctp.h b/include/net/netns/sctp.h
index 3573a81..8ba379f 100644
--- a/include/net/netns/sctp.h
+++ b/include/net/netns/sctp.h
@@ -31,6 +31,7 @@ struct netns_sctp {
 	struct list_head addr_waitq;
 	struct timer_list addr_wq_timer;
 	struct list_head auto_asconf_splist;
+	/* Lock that protects both addr_waitq and auto_asconf_splist */
 	spinlock_t addr_wq_lock;
 
 	/* Lock that protects the local_addr_list writers */
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 4ff3f67..2ad3a7b 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -223,6 +223,10 @@ struct sctp_sock {
 	atomic_t pd_mode;
 	/* Receive to here while partial delivery is in effect. */
 	struct sk_buff_head pd_lobby;
+
+	/* These must be the last fields, as they will skipped on copies,
+	 * like on accept and peeloff operations
+	 */
 	struct list_head auto_asconf_list;
 	int do_auto_asconf;
 };
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 634a2ab..99e640c 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1533,8 +1533,10 @@ static void sctp_close(struct sock *sk, long timeout)
 
 	/* Supposedly, no process has access to the socket, but
 	 * the net layers still may.
+	 * Also, sctp_destroy_sock() needs to be called with addr_wq_lock
+	 * held and that should be grabbed before socket lock.
 	 */
-	local_bh_disable();
+	spin_lock_bh(&net->sctp.addr_wq_lock);
 	bh_lock_sock(sk);
 
 	/* Hold the sock, since sk_common_release() will put sock_put()
@@ -1544,7 +1546,7 @@ static void sctp_close(struct sock *sk, long timeout)
 	sk_common_release(sk);
 
 	bh_unlock_sock(sk);
-	local_bh_enable();
+	spin_unlock_bh(&net->sctp.addr_wq_lock);
 
 	sock_put(sk);
 
@@ -3581,6 +3583,7 @@ static int sctp_setsockopt_auto_asconf(struct sock *sk, char __user *optval,
 	if ((val && sp->do_auto_asconf) || (!val && !sp->do_auto_asconf))
 		return 0;
 
+	spin_lock_bh(&sock_net(sk)->sctp.addr_wq_lock);
 	if (val == 0 && sp->do_auto_asconf) {
 		list_del(&sp->auto_asconf_list);
 		sp->do_auto_asconf = 0;
@@ -3589,6 +3592,7 @@ static int sctp_setsockopt_auto_asconf(struct sock *sk, char __user *optval,
 		    &sock_net(sk)->sctp.auto_asconf_splist);
 		sp->do_auto_asconf = 1;
 	}
+	spin_unlock_bh(&sock_net(sk)->sctp.addr_wq_lock);
 	return 0;
 }
 
@@ -4122,18 +4126,28 @@ static int sctp_init_sock(struct sock *sk)
 	local_bh_disable();
 	percpu_counter_inc(&sctp_sockets_allocated);
 	sock_prot_inuse_add(net, sk->sk_prot, 1);
+
+	/* Nothing can fail after this block, otherwise
+	 * sctp_destroy_sock() will be called without addr_wq_lock held
+	 */
 	if (net->sctp.default_auto_asconf) {
+		spin_lock(&sock_net(sk)->sctp.addr_wq_lock);
 		list_add_tail(&sp->auto_asconf_list,
 		    &net->sctp.auto_asconf_splist);
 		sp->do_auto_asconf = 1;
-	} else
+		spin_unlock(&sock_net(sk)->sctp.addr_wq_lock);
+	} else {
 		sp->do_auto_asconf = 0;
+	}
+
 	local_bh_enable();
 
 	return 0;
 }
 
-/* Cleanup any SCTP per socket resources.  */
+/* Cleanup any SCTP per socket resources. Must be called with
+ * sock_net(sk)->sctp.addr_wq_lock held if sp->do_auto_asconf is true
+ */
 static void sctp_destroy_sock(struct sock *sk)
 {
 	struct sctp_sock *sp;
@@ -7201,6 +7215,19 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk,
 	newinet->mc_list = NULL;
 }
 
+static inline void sctp_copy_descendant(struct sock *sk_to,
+					const struct sock *sk_from)
+{
+	int ancestor_size = sizeof(struct inet_sock) +
+			    sizeof(struct sctp_sock) -
+			    offsetof(struct sctp_sock, auto_asconf_list);
+
+	if (sk_from->sk_family == PF_INET6)
+		ancestor_size += sizeof(struct ipv6_pinfo);
+
+	__inet_sk_copy_descendant(sk_to, sk_from, ancestor_size);
+}
+
 /* Populate the fields of the newsk from the oldsk and migrate the assoc
  * and its messages to the newsk.
  */
@@ -7215,7 +7242,6 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
 	struct sk_buff *skb, *tmp;
 	struct sctp_ulpevent *event;
 	struct sctp_bind_hashbucket *head;
-	struct list_head tmplist;
 
 	/* Migrate socket buffer sizes and all the socket level options to the
 	 * new socket.
@@ -7223,12 +7249,7 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
 	newsk->sk_sndbuf = oldsk->sk_sndbuf;
 	newsk->sk_rcvbuf = oldsk->sk_rcvbuf;
 	/* Brute force copy old sctp opt. */
-	if (oldsp->do_auto_asconf) {
-		memcpy(&tmplist, &newsp->auto_asconf_list, sizeof(tmplist));
-		inet_sk_copy_descendant(newsk, oldsk);
-		memcpy(&newsp->auto_asconf_list, &tmplist, sizeof(tmplist));
-	} else
-		inet_sk_copy_descendant(newsk, oldsk);
+	sctp_copy_descendant(newsk, oldsk);
 
 	/* Restore the ep value that was overwritten with the above structure
 	 * copy.
-- 
2.1.0


From a1ab008f2a33ea1be282cffcace3636a102107a8 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <razor@blackwall.org>
Date: Mon, 15 Jun 2015 20:28:51 +0300
Subject: [PATCH 04/16] bridge: fix br_stp_set_bridge_priority race conditions

[ Upstream commit 2dab80a8b486f02222a69daca6859519e05781d9 ]

After the ->set() spinlocks were removed br_stp_set_bridge_priority
was left running without any protection when used via sysfs. It can
race with port add/del and could result in use-after-free cases and
corrupted lists. Tested by running port add/del in a loop with stp
enabled while setting priority in a loop, crashes are easily
reproducible.
The spinlocks around sysfs ->set() were removed in commit:
14f98f258f19 ("bridge: range check STP parameters")
There's also a race condition in the netlink priority support that is
fixed by this change, but it was introduced recently and the fixes tag
covers it, just in case it's needed the commit is:
af615762e972 ("bridge: add ageing_time, stp_state, priority over netlink")

Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Fixes: 14f98f258f19 ("bridge: range check STP parameters")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_ioctl.c  | 2 --
 net/bridge/br_stp_if.c | 4 +++-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c
index a9a4a1b..8d423bc 100644
--- a/net/bridge/br_ioctl.c
+++ b/net/bridge/br_ioctl.c
@@ -247,9 +247,7 @@ static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 		if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN))
 			return -EPERM;
 
-		spin_lock_bh(&br->lock);
 		br_stp_set_bridge_priority(br, args[1]);
-		spin_unlock_bh(&br->lock);
 		return 0;
 
 	case BRCTL_SET_PORT_PRIORITY:
diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
index 4114687..7832d07 100644
--- a/net/bridge/br_stp_if.c
+++ b/net/bridge/br_stp_if.c
@@ -243,12 +243,13 @@ bool br_stp_recalculate_bridge_id(struct net_bridge *br)
 	return true;
 }
 
-/* called under bridge lock */
+/* Acquires and releases bridge lock */
 void br_stp_set_bridge_priority(struct net_bridge *br, u16 newprio)
 {
 	struct net_bridge_port *p;
 	int wasroot;
 
+	spin_lock_bh(&br->lock);
 	wasroot = br_is_root_bridge(br);
 
 	list_for_each_entry(p, &br->port_list, list) {
@@ -266,6 +267,7 @@ void br_stp_set_bridge_priority(struct net_bridge *br, u16 newprio)
 	br_port_state_selection(br);
 	if (br_is_root_bridge(br) && !wasroot)
 		br_become_root_bridge(br);
+	spin_unlock_bh(&br->lock);
 }
 
 /* called under bridge lock */
-- 
2.1.0


From 15b8574426df8909a9c45c72ea2f55fa9e3fcca5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 16 Jun 2015 07:59:11 -0700
Subject: [PATCH 05/16] packet: read num_members once in packet_rcv_fanout()

[ Upstream commit f98f4514d07871da7a113dd9e3e330743fd70ae4 ]

We need to tell compiler it must not read f->num_members multiple
times. Otherwise testing if num is not zero is flaky, and we could
attempt an invalid divide by 0 in fanout_demux_cpu()

Note bug was present in packet_rcv_fanout_hash() and
packet_rcv_fanout_lb() but final 3.1 had a simple location
after commit 95ec3eb417115fb ("packet: Add 'cpu' fanout policy.")

Fixes: dc99f600698dc ("packet: Add fanout support.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 07c04a8..d465f9f 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1336,7 +1336,7 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
 			     struct packet_type *pt, struct net_device *orig_dev)
 {
 	struct packet_fanout *f = pt->af_packet_priv;
-	unsigned int num = f->num_members;
+	unsigned int num = READ_ONCE(f->num_members);
 	struct packet_sock *po;
 	unsigned int idx;
 
-- 
2.1.0


From 7190bd7f56064234156b1c3268b003de9a299661 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 17 Jun 2015 15:59:34 -0400
Subject: [PATCH 06/16] packet: avoid out of bounds read in round robin fanout

[ Upstream commit 468479e6043c84f5a65299cc07cb08a22a28c2b1 ]

PACKET_FANOUT_LB computes f->rr_cur such that it is modulo
f->num_members. It returns the old value unconditionally, but
f->num_members may have changed since the last store. Ensure
that the return value is always < num.

When modifying the logic, simplify it further by replacing the loop
with an unconditional atomic increment.

Fixes: dc99f600698d ("packet: Add fanout support.")
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 18 ++----------------
 1 file changed, 2 insertions(+), 16 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index d465f9f..5dcfe05 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1255,16 +1255,6 @@ static void packet_sock_destruct(struct sock *sk)
 	sk_refcnt_debug_dec(sk);
 }
 
-static int fanout_rr_next(struct packet_fanout *f, unsigned int num)
-{
-	int x = atomic_read(&f->rr_cur) + 1;
-
-	if (x >= num)
-		x = 0;
-
-	return x;
-}
-
 static unsigned int fanout_demux_hash(struct packet_fanout *f,
 				      struct sk_buff *skb,
 				      unsigned int num)
@@ -1276,13 +1266,9 @@ static unsigned int fanout_demux_lb(struct packet_fanout *f,
 				    struct sk_buff *skb,
 				    unsigned int num)
 {
-	int cur, old;
+	unsigned int val = atomic_inc_return(&f->rr_cur);
 
-	cur = atomic_read(&f->rr_cur);
-	while ((old = atomic_cmpxchg(&f->rr_cur, cur,
-				     fanout_rr_next(f, num))) != cur)
-		cur = old;
-	return cur;
+	return val % num;
 }
 
 static unsigned int fanout_demux_cpu(struct packet_fanout *f,
-- 
2.1.0


From c8950f973159741a39daaf031c12c812d8144f2d Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Tue, 16 Jun 2015 22:56:39 +0300
Subject: [PATCH 07/16] neigh: do not modify unlinked entries

[ Upstream commit 2c51a97f76d20ebf1f50fef908b986cb051fdff9 ]

The lockless lookups can return entry that is unlinked.
Sometimes they get reference before last neigh_cleanup_and_release,
sometimes they do not need reference. Later, any
modification attempts may result in the following problems:

1. entry is not destroyed immediately because neigh_update
can start the timer for dead entry, eg. on change to NUD_REACHABLE
state. As result, entry lives for some time but is invisible
and out of control.

2. __neigh_event_send can run in parallel with neigh_destroy
while refcnt=0 but if timer is started and expired refcnt can
reach 0 for second time leading to second neigh_destroy and
possible crash.

Thanks to Eric Dumazet and Ying Xue for their work and analyze
on the __neigh_event_send change.

Fixes: 767e97e1e0db ("neigh: RCU conversion of struct neighbour")
Fixes: a263b3093641 ("ipv4: Make neigh lookups directly in output packet path.")
Fixes: 6fd6ce2056de ("ipv6: Do not depend on rt->n in ip6_finish_output2().")
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index ef31fef..2b0d99d 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -977,6 +977,8 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
 	rc = 0;
 	if (neigh->nud_state & (NUD_CONNECTED | NUD_DELAY | NUD_PROBE))
 		goto out_unlock_bh;
+	if (neigh->dead)
+		goto out_dead;
 
 	if (!(neigh->nud_state & (NUD_STALE | NUD_INCOMPLETE))) {
 		if (NEIGH_VAR(neigh->parms, MCAST_PROBES) +
@@ -1033,6 +1035,13 @@ out_unlock_bh:
 		write_unlock(&neigh->lock);
 	local_bh_enable();
 	return rc;
+
+out_dead:
+	if (neigh->nud_state & NUD_STALE)
+		goto out_unlock_bh;
+	write_unlock_bh(&neigh->lock);
+	kfree_skb(skb);
+	return 1;
 }
 EXPORT_SYMBOL(__neigh_event_send);
 
@@ -1096,6 +1105,8 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
 	if (!(flags & NEIGH_UPDATE_F_ADMIN) &&
 	    (old & (NUD_NOARP | NUD_PERMANENT)))
 		goto out;
+	if (neigh->dead)
+		goto out;
 
 	if (!(new & NUD_VALID)) {
 		neigh_del_timer(neigh);
@@ -1245,6 +1256,8 @@ EXPORT_SYMBOL(neigh_update);
  */
 void __neigh_set_probe_once(struct neighbour *neigh)
 {
+	if (neigh->dead)
+		return;
 	neigh->updated = jiffies;
 	if (!(neigh->nud_state & NUD_FAILED))
 		return;
-- 
2.1.0


From 80f32b21d36ec29220643243f24ba3c548a00aa2 Mon Sep 17 00:00:00 2001
From: Christoph Paasch <cpaasch@apple.com>
Date: Thu, 18 Jun 2015 09:15:34 -0700
Subject: [PATCH 08/16] tcp: Do not call tcp_fastopen_reset_cipher from
 interrupt context

[ Upstream commit dfea2aa654243f70dc53b8648d0bbdeec55a7df1 ]

tcp_fastopen_reset_cipher really cannot be called from interrupt
context. It allocates the tcp_fastopen_context with GFP_KERNEL and
calls crypto_alloc_cipher, which allocates all kind of stuff with
GFP_KERNEL.

Thus, we might sleep when the key-generation is triggered by an
incoming TFO cookie-request which would then happen in interrupt-
context, as shown by enabling CONFIG_DEBUG_ATOMIC_SLEEP:

[   36.001813] BUG: sleeping function called from invalid context at mm/slub.c:1266
[   36.003624] in_atomic(): 1, irqs_disabled(): 0, pid: 1016, name: packetdrill
[   36.004859] CPU: 1 PID: 1016 Comm: packetdrill Not tainted 4.1.0-rc7 #14
[   36.006085] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.7.5-0-ge51488c-20140602_164612-nilsson.home.kraxel.org 04/01/2014
[   36.008250]  00000000000004f2 ffff88007f8838a8 ffffffff8171d53a ffff880075a084a8
[   36.009630]  ffff880075a08000 ffff88007f8838c8 ffffffff810967d3 ffff88007f883928
[   36.011076]  0000000000000000 ffff88007f8838f8 ffffffff81096892 ffff88007f89be00
[   36.012494] Call Trace:
[   36.012953]  <IRQ>  [<ffffffff8171d53a>] dump_stack+0x4f/0x6d
[   36.014085]  [<ffffffff810967d3>] ___might_sleep+0x103/0x170
[   36.015117]  [<ffffffff81096892>] __might_sleep+0x52/0x90
[   36.016117]  [<ffffffff8118e887>] kmem_cache_alloc_trace+0x47/0x190
[   36.017266]  [<ffffffff81680d82>] ? tcp_fastopen_reset_cipher+0x42/0x130
[   36.018485]  [<ffffffff81680d82>] tcp_fastopen_reset_cipher+0x42/0x130
[   36.019679]  [<ffffffff81680f01>] tcp_fastopen_init_key_once+0x61/0x70
[   36.020884]  [<ffffffff81680f2c>] __tcp_fastopen_cookie_gen+0x1c/0x60
[   36.022058]  [<ffffffff816814ff>] tcp_try_fastopen+0x58f/0x730
[   36.023118]  [<ffffffff81671788>] tcp_conn_request+0x3e8/0x7b0
[   36.024185]  [<ffffffff810e3872>] ? __module_text_address+0x12/0x60
[   36.025327]  [<ffffffff8167b2e1>] tcp_v4_conn_request+0x51/0x60
[   36.026410]  [<ffffffff816727e0>] tcp_rcv_state_process+0x190/0xda0
[   36.027556]  [<ffffffff81661f97>] ? __inet_lookup_established+0x47/0x170
[   36.028784]  [<ffffffff8167c2ad>] tcp_v4_do_rcv+0x16d/0x3d0
[   36.029832]  [<ffffffff812e6806>] ? security_sock_rcv_skb+0x16/0x20
[   36.030936]  [<ffffffff8167cc8a>] tcp_v4_rcv+0x77a/0x7b0
[   36.031875]  [<ffffffff816af8c3>] ? iptable_filter_hook+0x33/0x70
[   36.032953]  [<ffffffff81657d22>] ip_local_deliver_finish+0x92/0x1f0
[   36.034065]  [<ffffffff81657f1a>] ip_local_deliver+0x9a/0xb0
[   36.035069]  [<ffffffff81657c90>] ? ip_rcv+0x3d0/0x3d0
[   36.035963]  [<ffffffff81657569>] ip_rcv_finish+0x119/0x330
[   36.036950]  [<ffffffff81657ba7>] ip_rcv+0x2e7/0x3d0
[   36.037847]  [<ffffffff81610652>] __netif_receive_skb_core+0x552/0x930
[   36.038994]  [<ffffffff81610a57>] __netif_receive_skb+0x27/0x70
[   36.040033]  [<ffffffff81610b72>] process_backlog+0xd2/0x1f0
[   36.041025]  [<ffffffff81611482>] net_rx_action+0x122/0x310
[   36.042007]  [<ffffffff81076743>] __do_softirq+0x103/0x2f0
[   36.042978]  [<ffffffff81723e3c>] do_softirq_own_stack+0x1c/0x30

This patch moves the call to tcp_fastopen_init_key_once to the places
where a listener socket creates its TFO-state, which always happens in
user-context (either from the setsockopt, or implicitly during the
listen()-call)

Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Fixes: 222e83d2e0ae ("tcp: switch tcp_fastopen key generation to net_get_random_once")
Signed-off-by: Christoph Paasch <cpaasch@apple.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/af_inet.c      | 2 ++
 net/ipv4/tcp.c          | 7 +++++--
 net/ipv4/tcp_fastopen.c | 2 --
 3 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index e67da4e..9a17357 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -228,6 +228,8 @@ int inet_listen(struct socket *sock, int backlog)
 				err = 0;
 			if (err)
 				goto out;
+
+			tcp_fastopen_init_key_once(true);
 		}
 		err = inet_csk_listen_start(sk, backlog);
 		if (err)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index de61954..32b25cc 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2585,10 +2585,13 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 
 	case TCP_FASTOPEN:
 		if (val >= 0 && ((1 << sk->sk_state) & (TCPF_CLOSE |
-		    TCPF_LISTEN)))
+		    TCPF_LISTEN))) {
+			tcp_fastopen_init_key_once(true);
+
 			err = fastopen_init_queue(sk, val);
-		else
+		} else {
 			err = -EINVAL;
+		}
 		break;
 	case TCP_TIMESTAMP:
 		if (!tp->repair)
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index c730772..b01d5bd 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -78,8 +78,6 @@ static bool __tcp_fastopen_cookie_gen(const void *path,
 	struct tcp_fastopen_context *ctx;
 	bool ok = false;
 
-	tcp_fastopen_init_key_once(true);
-
 	rcu_read_lock();
 	ctx = rcu_dereference(tcp_fastopen_ctx);
 	if (ctx) {
-- 
2.1.0


From 071f8a2f6e46582e718e54d31b147eb5e616838b Mon Sep 17 00:00:00 2001
From: Ido Shamay <idos@mellanox.com>
Date: Thu, 25 Jun 2015 11:29:42 +0300
Subject: [PATCH 09/16] net/mlx4_en: Wake TX queues only when there's enough
 room

[ Upstream commit 488a9b48e398b157703766e2cd91ea45ac6997c5 ]

Indication of a single completed packet, marked by txbbs_skipped
being bigger then zero, in not enough in order to wake up a
stopped TX queue. The completed packet may contain a single TXBB,
while next packet to be sent (after the wake up) may have multiple
TXBBs (LSO/TSO packets for example), causing overflow in queue followed
by WQE corruption and TX queue timeout.
Instead, wake the stopped queue only when there's enough room for the
worst case (maximum sized WQE) packet that we should need to handle after
the queue is opened again.

Also created an helper routine - mlx4_en_is_tx_ring_full, which checks
if the current TX ring is full or not. It provides better code readability
and removes code duplication.

Signed-off-by: Ido Shamay <idos@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_tx.c   | 19 +++++++++++--------
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h |  1 +
 2 files changed, 12 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 142ddd5..5980d3f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -66,6 +66,7 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 	ring->size = size;
 	ring->size_mask = size - 1;
 	ring->stride = stride;
+	ring->full_size = ring->size - HEADROOM - MAX_DESC_TXBBS;
 
 	tmp = size * sizeof(struct mlx4_en_tx_info);
 	ring->tx_info = kmalloc_node(tmp, GFP_KERNEL | __GFP_NOWARN, node);
@@ -223,6 +224,11 @@ void mlx4_en_deactivate_tx_ring(struct mlx4_en_priv *priv,
 		       MLX4_QP_STATE_RST, NULL, 0, 0, &ring->qp);
 }
 
+static inline bool mlx4_en_is_tx_ring_full(struct mlx4_en_tx_ring *ring)
+{
+	return ring->prod - ring->cons > ring->full_size;
+}
+
 static void mlx4_en_stamp_wqe(struct mlx4_en_priv *priv,
 			      struct mlx4_en_tx_ring *ring, int index,
 			      u8 owner)
@@ -465,11 +471,10 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev,
 
 	netdev_tx_completed_queue(ring->tx_queue, packets, bytes);
 
-	/*
-	 * Wakeup Tx queue if this stopped, and at least 1 packet
-	 * was completed
+	/* Wakeup Tx queue if this stopped, and ring is not full.
 	 */
-	if (netif_tx_queue_stopped(ring->tx_queue) && txbbs_skipped > 0) {
+	if (netif_tx_queue_stopped(ring->tx_queue) &&
+	    !mlx4_en_is_tx_ring_full(ring)) {
 		netif_tx_wake_queue(ring->tx_queue);
 		ring->wake_queue++;
 	}
@@ -913,8 +918,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	skb_tx_timestamp(skb);
 
 	/* Check available TXBBs And 2K spare for prefetch */
-	stop_queue = (int)(ring->prod - ring_cons) >
-		      ring->size - HEADROOM - MAX_DESC_TXBBS;
+	stop_queue = mlx4_en_is_tx_ring_full(ring);
 	if (unlikely(stop_queue)) {
 		netif_tx_stop_queue(ring->tx_queue);
 		ring->queue_stopped++;
@@ -983,8 +987,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 		smp_rmb();
 
 		ring_cons = ACCESS_ONCE(ring->cons);
-		if (unlikely(((int)(ring->prod - ring_cons)) <=
-			     ring->size - HEADROOM - MAX_DESC_TXBBS)) {
+		if (unlikely(!mlx4_en_is_tx_ring_full(ring))) {
 			netif_tx_wake_queue(ring->tx_queue);
 			ring->wake_queue++;
 		}
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 692bd4e..4f90806 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -280,6 +280,7 @@ struct mlx4_en_tx_ring {
 	u32			size; /* number of TXBBs */
 	u32			size_mask;
 	u16			stride;
+	u32			full_size;
 	u16			cqn;	/* index of port CQ associated with this ring */
 	u32			buf_size;
 	__be32			doorbell_qpn;
-- 
2.1.0


From 41394531e05a2bbfd7627a24ae8dac0f7dc1fba9 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Date: Fri, 26 Jun 2015 13:48:17 +0300
Subject: [PATCH 10/16] lib/rhashtable: fix race between
 rhashtable_lookup_compare and hashtable resize

[ No applicable upstream commit ]

Hash value passed as argument into rhashtable_lookup_compare could be
computed using different hash table than rhashtable_lookup_compare sees.

This patch passes key into rhashtable_lookup_compare() instead of hash and
compures hash value right in place using the same table as for lookup.

Also it adds comment for rhashtable_hashfn and rhashtable_obj_hashfn:
user must prevent concurrent insert/remove otherwise returned hash value
could be invalid.

Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Fixes: e341694e3eb5 ("netlink: Convert netlink_lookup() to use RCU protected hash table")
Link: http://lkml.kernel.org/r/20150514042151.GA5482@gondor.apana.org.au
Cc: Stable <stable@vger.kernel.org> (v3.17 .. v3.19)
Acked-by: Thomas Graf <tgraf@suug.ch>
---
 include/linux/rhashtable.h |  2 +-
 lib/rhashtable.c           | 12 ++++++++----
 net/netlink/af_netlink.c   |  5 +----
 3 files changed, 10 insertions(+), 9 deletions(-)

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index fb298e9d..8405674 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -108,7 +108,7 @@ int rhashtable_expand(struct rhashtable *ht, gfp_t flags);
 int rhashtable_shrink(struct rhashtable *ht, gfp_t flags);
 
 void *rhashtable_lookup(const struct rhashtable *ht, const void *key);
-void *rhashtable_lookup_compare(const struct rhashtable *ht, u32 hash,
+void *rhashtable_lookup_compare(const struct rhashtable *ht, void *key,
 				bool (*compare)(void *, void *), void *arg);
 
 void rhashtable_destroy(const struct rhashtable *ht);
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 624a0b7..cb22073 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -61,6 +61,8 @@ static u32 __hashfn(const struct rhashtable *ht, const void *key,
  * Computes the hash value using the hash function provided in the 'hashfn'
  * of struct rhashtable_params. The returned value is guaranteed to be
  * smaller than the number of buckets in the hash table.
+ *
+ * The caller must ensure that no concurrent table mutations occur.
  */
 u32 rhashtable_hashfn(const struct rhashtable *ht, const void *key, u32 len)
 {
@@ -92,6 +94,8 @@ static u32 obj_hashfn(const struct rhashtable *ht, const void *ptr, u32 hsize)
  * 'obj_hashfn' depending on whether the hash table is set up to work with
  * a fixed length key. The returned value is guaranteed to be smaller than
  * the number of buckets in the hash table.
+ *
+ * The caller must ensure that no concurrent table mutations occur.
  */
 u32 rhashtable_obj_hashfn(const struct rhashtable *ht, void *ptr)
 {
@@ -474,7 +478,7 @@ EXPORT_SYMBOL_GPL(rhashtable_lookup);
 /**
  * rhashtable_lookup_compare - search hash table with compare function
  * @ht:		hash table
- * @hash:	hash value of desired entry
+ * @key:	pointer to key
  * @compare:	compare function, must return true on match
  * @arg:	argument passed on to compare function
  *
@@ -486,14 +490,14 @@ EXPORT_SYMBOL_GPL(rhashtable_lookup);
  *
  * Returns the first entry on which the compare function returned true.
  */
-void *rhashtable_lookup_compare(const struct rhashtable *ht, u32 hash,
+void *rhashtable_lookup_compare(const struct rhashtable *ht, void *key,
 				bool (*compare)(void *, void *), void *arg)
 {
 	const struct bucket_table *tbl = rht_dereference_rcu(ht->tbl, ht);
 	struct rhash_head *he;
+	u32 hash;
 
-	if (unlikely(hash >= tbl->size))
-		return NULL;
+	hash = __hashfn(ht, key, ht->p.key_len, tbl->size);
 
 	rht_for_each_rcu(he, tbl->buckets[hash], ht) {
 		if (!compare(rht_obj(ht, he), arg))
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index c0a4187..c82b2e3 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1003,11 +1003,8 @@ static struct sock *__netlink_lookup(struct netlink_table *table, u32 portid,
 		.net = net,
 		.portid = portid,
 	};
-	u32 hash;
 
-	hash = rhashtable_hashfn(&table->hash, &portid, sizeof(portid));
-
-	return rhashtable_lookup_compare(&table->hash, hash,
+	return rhashtable_lookup_compare(&table->hash, &portid,
 					 &netlink_compare, &arg);
 }
 
-- 
2.1.0


From 4155ee8c5d9be3e7074d68182ed2546dd8002f18 Mon Sep 17 00:00:00 2001
From: Mugunthan V N <mugunthanvnm@ti.com>
Date: Thu, 25 Jun 2015 22:21:02 +0530
Subject: [PATCH 11/16] net: phy: fix phy link up when limiting speed via
 device tree

[ Upstream commit eb686231fce3770299760f24fdcf5ad041f44153 ]

When limiting phy link speed using "max-speed" to 100mbps or less on a
giga bit phy, phy never completes auto negotiation and phy state
machine is held in PHY_AN. Fixing this issue by comparing the giga
bit advertise though phydev->supported doesn't have it but phy has
BMSR_ESTATEN set. So that auto negotiation is restarted as old and
new advertise are different and link comes up fine.

Signed-off-by: Mugunthan V N <mugunthanvnm@ti.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 3fc91e8..70a0d88 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -782,10 +782,11 @@ static int genphy_config_advert(struct phy_device *phydev)
 	if (phydev->supported & (SUPPORTED_1000baseT_Half |
 				 SUPPORTED_1000baseT_Full)) {
 		adv |= ethtool_adv_to_mii_ctrl1000_t(advertise);
-		if (adv != oldadv)
-			changed = 1;
 	}
 
+	if (adv != oldadv)
+		changed = 1;
+
 	err = phy_write(phydev, MII_CTRL1000, adv);
 	if (err < 0)
 		return err;
-- 
2.1.0


From ed0c52f35c16dec4ea7a4c70d744a71d7914b61e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 26 Jun 2015 07:32:29 +0200
Subject: [PATCH 12/16] bnx2x: fix lockdep splat

[ Upstream commit d53c66a5b80698620f7c9ba2372fff4017e987b8 ]

Michel reported following lockdep splat

[   44.718117] INFO: trying to register non-static key.
[   44.723081] the code is fine but needs lockdep annotation.
[   44.728559] turning off the locking correctness validator.
[   44.734036] CPU: 8 PID: 5483 Comm: ethtool Not tainted 4.1.0
[   44.770289] Call Trace:
[   44.772741]  [<ffffffff816eb1cd>] dump_stack+0x4c/0x65
[   44.777879]  [<ffffffff8111d921>] ? console_unlock+0x1f1/0x510
[   44.783708]  [<ffffffff811121f5>] __lock_acquire+0x1d05/0x1f10
[   44.789538]  [<ffffffff8111370a>] ? mark_held_locks+0x6a/0x90
[   44.795276]  [<ffffffff81113835>] ? trace_hardirqs_on_caller+0x105/0x1d0
[   44.801967]  [<ffffffff8111390d>] ? trace_hardirqs_on+0xd/0x10
[   44.807793]  [<ffffffff811330fa>] ? hrtimer_try_to_cancel+0x4a/0x250
[   44.814142]  [<ffffffff81112ba6>] lock_acquire+0xb6/0x290
[   44.819537]  [<ffffffff810d6675>] ? flush_work+0x5/0x280
[   44.824844]  [<ffffffff810d66ad>] flush_work+0x3d/0x280
[   44.830061]  [<ffffffff810d6675>] ? flush_work+0x5/0x280
[   44.835366]  [<ffffffff816f3c43>] ? schedule_hrtimeout_range+0x13/0x20
[   44.841889]  [<ffffffff8112ec9b>] ? usleep_range+0x4b/0x50
[   44.847365]  [<ffffffff8111370a>] ? mark_held_locks+0x6a/0x90
[   44.853102]  [<ffffffff810d8585>] ? __cancel_work_timer+0x105/0x1c0
[   44.859359]  [<ffffffff81113835>] ? trace_hardirqs_on_caller+0x105/0x1d0
[   44.866045]  [<ffffffff810d851f>] __cancel_work_timer+0x9f/0x1c0
[   44.872048]  [<ffffffffa0010982>] ? bnx2x_func_stop+0x42/0x90 [bnx2x]
[   44.878481]  [<ffffffff810d8670>] cancel_work_sync+0x10/0x20
[   44.884134]  [<ffffffffa00259e5>] bnx2x_chip_cleanup+0x245/0x730 [bnx2x]
[   44.890829]  [<ffffffff8110ce02>] ? up+0x32/0x50
[   44.895439]  [<ffffffff811306b5>] ? del_timer_sync+0x5/0xd0
[   44.901005]  [<ffffffffa005596d>] bnx2x_nic_unload+0x20d/0x8e0 [bnx2x]
[   44.907527]  [<ffffffff811f1aef>] ? might_fault+0x5f/0xb0
[   44.912921]  [<ffffffffa005851c>] bnx2x_reload_if_running+0x2c/0x50 [bnx2x]
[   44.919879]  [<ffffffffa005a3c5>] bnx2x_set_ringparam+0x2b5/0x460 [bnx2x]
[   44.926664]  [<ffffffff815d498b>] dev_ethtool+0x55b/0x1c40
[   44.932148]  [<ffffffff815dfdc7>] ? rtnl_lock+0x17/0x20
[   44.937364]  [<ffffffff815e7f8b>] dev_ioctl+0x17b/0x630
[   44.942582]  [<ffffffff815abf8d>] sock_do_ioctl+0x5d/0x70
[   44.947972]  [<ffffffff815ac013>] sock_ioctl+0x73/0x280
[   44.953192]  [<ffffffff8124c1c8>] do_vfs_ioctl+0x88/0x5b0
[   44.958587]  [<ffffffff8110d0b3>] ? up_read+0x23/0x40
[   44.963631]  [<ffffffff812584cc>] ? __fget_light+0x6c/0xa0
[   44.969105]  [<ffffffff8124c781>] SyS_ioctl+0x91/0xb0
[   44.974149]  [<ffffffff816f4dd7>] system_call_fastpath+0x12/0x6f

As bnx2x_init_ptp() is only called if bp->flags contains PTP_SUPPORTED,
we also need to guard bnx2x_stop_ptp() with same condition, otherwise
ptp_task workqueue is not initialized and kernel barfs on
cancel_work_sync()

Fixes: eeed018cbfa30 ("bnx2x: Add timestamping and PTP hardware clock support")
Reported-by: Michel Lespinasse <walken@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Michal Kalderon <Michal.Kalderon@qlogic.com>
Cc: Ariel Elior <Ariel.Elior@qlogic.com>
Cc: Yuval Mintz <Yuval.Mintz@qlogic.com>
Cc: David Decotigny <decot@google.com>
Acked-by: Sony Chacko <sony.chacko@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 710eb57..1217eaf 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -9307,7 +9307,8 @@ unload_error:
 	 * function stop ramrod is sent, since as part of this ramrod FW access
 	 * PTP registers.
 	 */
-	bnx2x_stop_ptp(bp);
+	if (bp->flags & PTP_SUPPORTED)
+		bnx2x_stop_ptp(bp);
 
 	/* Disable HW interrupts, NAPI */
 	bnx2x_netif_stop(bp, 1);
-- 
2.1.0


From feb1cd51f229894612d78e1a44d1ad6ffb980ab7 Mon Sep 17 00:00:00 2001
From: Alexander Sverdlin <alexander.sverdlin@nokia.com>
Date: Mon, 29 Jun 2015 10:41:03 +0200
Subject: [PATCH 13/16] sctp: Fix race between OOTB responce and route removal

[ Upstream commit 29c4afc4e98f4dc0ea9df22c631841f9c220b944 ]

There is NULL pointer dereference possible during statistics update if the route
used for OOTB responce is removed at unfortunate time. If the route exists when
we receive OOTB packet and we finally jump into sctp_packet_transmit() to send
ABORT, but in the meantime route is removed under our feet, we take "no_route"
path and try to update stats with IP_INC_STATS(sock_net(asoc->base.sk), ...).

But sctp_ootb_pkt_new() used to prepare responce packet doesn't call
sctp_transport_set_owner() and therefore there is no asoc associated with this
packet. Probably temporary asoc just for OOTB responces is overkill, so just
introduce a check like in all other places in sctp_packet_transmit(), where
"asoc" is dereferenced.

To reproduce this, one needs to
0. ensure that sctp module is loaded (otherwise ABORT is not generated)
1. remove default route on the machine
2. while true; do
     ip route del [interface-specific route]
     ip route add [interface-specific route]
   done
3. send enough OOTB packets (i.e. HB REQs) from another host to trigger ABORT
   responce

On x86_64 the crash looks like this:

BUG: unable to handle kernel NULL pointer dereference at 0000000000000020
IP: [<ffffffffa05ec9ac>] sctp_packet_transmit+0x63c/0x730 [sctp]
PGD 0
Oops: 0000 [#1] PREEMPT SMP
Modules linked in: ...
CPU: 0 PID: 0 Comm: swapper/0 Tainted: G           O    4.0.5-1-ARCH #1
Hardware name: ...
task: ffffffff818124c0 ti: ffffffff81800000 task.ti: ffffffff81800000
RIP: 0010:[<ffffffffa05ec9ac>]  [<ffffffffa05ec9ac>] sctp_packet_transmit+0x63c/0x730 [sctp]
RSP: 0018:ffff880127c037b8  EFLAGS: 00010296
RAX: 0000000000000000 RBX: 0000000000000000 RCX: 00000015ff66b480
RDX: 00000015ff66b400 RSI: ffff880127c17200 RDI: ffff880123403700
RBP: ffff880127c03888 R08: 0000000000017200 R09: ffffffff814625af
R10: ffffea00047e4680 R11: 00000000ffffff80 R12: ffff8800b0d38a28
R13: ffff8800b0d38a28 R14: ffff8800b3e88000 R15: ffffffffa05f24e0
FS:  0000000000000000(0000) GS:ffff880127c00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
CR2: 0000000000000020 CR3: 00000000c855b000 CR4: 00000000000007f0
Stack:
 ffff880127c03910 ffff8800b0d38a28 ffffffff8189d240 ffff88011f91b400
 ffff880127c03828 ffffffffa05c94c5 0000000000000000 ffff8800baa1c520
 0000000000000000 0000000000000001 0000000000000000 0000000000000000
Call Trace:
 <IRQ>
 [<ffffffffa05c94c5>] ? sctp_sf_tabort_8_4_8.isra.20+0x85/0x140 [sctp]
 [<ffffffffa05d6b42>] ? sctp_transport_put+0x52/0x80 [sctp]
 [<ffffffffa05d0bfc>] sctp_do_sm+0xb8c/0x19a0 [sctp]
 [<ffffffff810b0e00>] ? trigger_load_balance+0x90/0x210
 [<ffffffff810e0329>] ? update_process_times+0x59/0x60
 [<ffffffff812c7a40>] ? timerqueue_add+0x60/0xb0
 [<ffffffff810e0549>] ? enqueue_hrtimer+0x29/0xa0
 [<ffffffff8101f599>] ? read_tsc+0x9/0x10
 [<ffffffff8116d4b5>] ? put_page+0x55/0x60
 [<ffffffff810ee1ad>] ? clockevents_program_event+0x6d/0x100
 [<ffffffff81462b68>] ? skb_free_head+0x58/0x80
 [<ffffffffa029a10b>] ? chksum_update+0x1b/0x27 [crc32c_generic]
 [<ffffffff81283f3e>] ? crypto_shash_update+0xce/0xf0
 [<ffffffffa05d3993>] sctp_endpoint_bh_rcv+0x113/0x280 [sctp]
 [<ffffffffa05dd4e6>] sctp_inq_push+0x46/0x60 [sctp]
 [<ffffffffa05ed7a0>] sctp_rcv+0x880/0x910 [sctp]
 [<ffffffffa05ecb50>] ? sctp_packet_transmit_chunk+0xb0/0xb0 [sctp]
 [<ffffffffa05ecb70>] ? sctp_csum_update+0x20/0x20 [sctp]
 [<ffffffff814b05a5>] ? ip_route_input_noref+0x235/0xd30
 [<ffffffff81051d6b>] ? ack_ioapic_level+0x7b/0x150
 [<ffffffff814b27be>] ip_local_deliver_finish+0xae/0x210
 [<ffffffff814b2e15>] ip_local_deliver+0x35/0x90
 [<ffffffff814b2a15>] ip_rcv_finish+0xf5/0x370
 [<ffffffff814b3128>] ip_rcv+0x2b8/0x3a0
 [<ffffffff81474193>] __netif_receive_skb_core+0x763/0xa50
 [<ffffffff81476c28>] __netif_receive_skb+0x18/0x60
 [<ffffffff81476cb0>] netif_receive_skb_internal+0x40/0xd0
 [<ffffffff814776c8>] napi_gro_receive+0xe8/0x120
 [<ffffffffa03946aa>] rtl8169_poll+0x2da/0x660 [r8169]
 [<ffffffff8147896a>] net_rx_action+0x21a/0x360
 [<ffffffff81078dc1>] __do_softirq+0xe1/0x2d0
 [<ffffffff8107912d>] irq_exit+0xad/0xb0
 [<ffffffff8157d158>] do_IRQ+0x58/0xf0
 [<ffffffff8157b06d>] common_interrupt+0x6d/0x6d
 <EOI>
 [<ffffffff810e1218>] ? hrtimer_start+0x18/0x20
 [<ffffffffa05d65f9>] ? sctp_transport_destroy_rcu+0x29/0x30 [sctp]
 [<ffffffff81020c50>] ? mwait_idle+0x60/0xa0
 [<ffffffff810216ef>] arch_cpu_idle+0xf/0x20
 [<ffffffff810b731c>] cpu_startup_entry+0x3ec/0x480
 [<ffffffff8156b365>] rest_init+0x85/0x90
 [<ffffffff818eb035>] start_kernel+0x48b/0x4ac
 [<ffffffff818ea120>] ? early_idt_handlers+0x120/0x120
 [<ffffffff818ea339>] x86_64_start_reservations+0x2a/0x2c
 [<ffffffff818ea49c>] x86_64_start_kernel+0x161/0x184
Code: 90 48 8b 80 b8 00 00 00 48 89 85 70 ff ff ff 48 83 bd 70 ff ff ff 00 0f 85 cd fa ff ff 48 89 df 31 db e8 18 63 e7 e0 48 8b 45 80 <48> 8b 40 20 48 8b 40 30 48 8b 80 68 01 00 00 65 48 ff 40 78 e9
RIP  [<ffffffffa05ec9ac>] sctp_packet_transmit+0x63c/0x730 [sctp]
 RSP <ffff880127c037b8>
CR2: 0000000000000020
---[ end trace 5aec7fd2dc983574 ]---
Kernel panic - not syncing: Fatal exception in interrupt
Kernel Offset: 0x0 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffff9fffffff)
drm_kms_helper: panic occurred, switching back to text console
---[ end Kernel panic - not syncing: Fatal exception in interrupt

Signed-off-by: Alexander Sverdlin <alexander.sverdlin@nokia.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/output.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sctp/output.c b/net/sctp/output.c
index fc5e45b..abe7c2d 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -599,7 +599,9 @@ out:
 	return err;
 no_route:
 	kfree_skb(nskb);
-	IP_INC_STATS(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES);
+
+	if (asoc)
+		IP_INC_STATS(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES);
 
 	/* FIXME: Returning the 'err' will effect all the associations
 	 * associated with a socket, although only one of the paths of the
-- 
2.1.0


From a1cdc2dc80589fb885fd1419dc0f5d4ecbae2d1a Mon Sep 17 00:00:00 2001
From: Simon Guinot <simon.guinot@sequanux.org>
Date: Tue, 30 Jun 2015 16:20:20 +0200
Subject: [PATCH 14/16] net: mvneta: introduce compatible string "marvell,
 armada-xp-neta"

[ Upstream commit f522a975a8101895a85354b9c143f41b8248e71a ]

The mvneta driver supports the Ethernet IP found in the Armada 370, XP,
380 and 385 SoCs. Since at least one more hardware feature is available
for the Armada XP SoCs then a way to identify them is needed.

This patch introduces a new compatible string "marvell,armada-xp-neta".

Signed-off-by: Simon Guinot <simon.guinot@sequanux.org>
Fixes: c5aff18204da ("net: mvneta: driver for Marvell Armada 370/XP network unit")
Cc: <stable@vger.kernel.org> # v3.8+
Acked-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
Acked-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt | 2 +-
 drivers/net/ethernet/marvell/mvneta.c                             | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt b/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt
index 750d577..f5a8ca2 100644
--- a/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt
+++ b/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt
@@ -1,7 +1,7 @@
 * Marvell Armada 370 / Armada XP Ethernet Controller (NETA)
 
 Required properties:
-- compatible: should be "marvell,armada-370-neta".
+- compatible: "marvell,armada-370-neta" or "marvell,armada-xp-neta".
 - reg: address and length of the register set for the device.
 - interrupts: interrupt for the device
 - phy: See ethernet.txt file in the same directory.
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 67a84cf..e62c951 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -3101,6 +3101,7 @@ static int mvneta_remove(struct platform_device *pdev)
 
 static const struct of_device_id mvneta_match[] = {
 	{ .compatible = "marvell,armada-370-neta" },
+	{ .compatible = "marvell,armada-xp-neta" },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, mvneta_match);
-- 
2.1.0


From 34edbd06c7e56f81878bd6d9169ad34b8a8be3f7 Mon Sep 17 00:00:00 2001
From: Simon Guinot <simon.guinot@sequanux.org>
Date: Tue, 30 Jun 2015 16:20:21 +0200
Subject: [PATCH 15/16] ARM: mvebu: update Ethernet compatible string for
 Armada XP

[ Upstream commit ea3b55fe83b5fcede82d183164b9d6831b26e33b ]

This patch updates the Ethernet DT nodes for Armada XP SoCs with the
compatible string "marvell,armada-xp-neta".

Signed-off-by: Simon Guinot <simon.guinot@sequanux.org>
Fixes: 77916519cba3 ("arm: mvebu: Armada XP MV78230 has only three Ethernet interfaces")
Cc: <stable@vger.kernel.org> # v3.8+
Acked-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
Reviewed-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/arm/boot/dts/armada-370-xp.dtsi     |  2 --
 arch/arm/boot/dts/armada-370.dtsi        |  8 ++++++++
 arch/arm/boot/dts/armada-xp-mv78260.dtsi |  2 +-
 arch/arm/boot/dts/armada-xp-mv78460.dtsi |  2 +-
 arch/arm/boot/dts/armada-xp.dtsi         | 10 +++++++++-
 5 files changed, 19 insertions(+), 5 deletions(-)

diff --git a/arch/arm/boot/dts/armada-370-xp.dtsi b/arch/arm/boot/dts/armada-370-xp.dtsi
index 83286ec..84366cd 100644
--- a/arch/arm/boot/dts/armada-370-xp.dtsi
+++ b/arch/arm/boot/dts/armada-370-xp.dtsi
@@ -225,7 +225,6 @@
 			};
 
 			eth0: ethernet@70000 {
-				compatible = "marvell,armada-370-neta";
 				reg = <0x70000 0x4000>;
 				interrupts = <8>;
 				clocks = <&gateclk 4>;
@@ -241,7 +240,6 @@
 			};
 
 			eth1: ethernet@74000 {
-				compatible = "marvell,armada-370-neta";
 				reg = <0x74000 0x4000>;
 				interrupts = <10>;
 				clocks = <&gateclk 3>;
diff --git a/arch/arm/boot/dts/armada-370.dtsi b/arch/arm/boot/dts/armada-370.dtsi
index 7513410..b6e0268 100644
--- a/arch/arm/boot/dts/armada-370.dtsi
+++ b/arch/arm/boot/dts/armada-370.dtsi
@@ -302,6 +302,14 @@
 					dmacap,memset;
 				};
 			};
+
+			ethernet@70000 {
+				compatible = "marvell,armada-370-neta";
+			};
+
+			ethernet@74000 {
+				compatible = "marvell,armada-370-neta";
+			};
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/armada-xp-mv78260.dtsi b/arch/arm/boot/dts/armada-xp-mv78260.dtsi
index 480e237..677160e 100644
--- a/arch/arm/boot/dts/armada-xp-mv78260.dtsi
+++ b/arch/arm/boot/dts/armada-xp-mv78260.dtsi
@@ -296,7 +296,7 @@
 			};
 
 			eth3: ethernet@34000 {
-				compatible = "marvell,armada-370-neta";
+				compatible = "marvell,armada-xp-neta";
 				reg = <0x34000 0x4000>;
 				interrupts = <14>;
 				clocks = <&gateclk 1>;
diff --git a/arch/arm/boot/dts/armada-xp-mv78460.dtsi b/arch/arm/boot/dts/armada-xp-mv78460.dtsi
index 2c7b1fe..e143776 100644
--- a/arch/arm/boot/dts/armada-xp-mv78460.dtsi
+++ b/arch/arm/boot/dts/armada-xp-mv78460.dtsi
@@ -334,7 +334,7 @@
 			};
 
 			eth3: ethernet@34000 {
-				compatible = "marvell,armada-370-neta";
+				compatible = "marvell,armada-xp-neta";
 				reg = <0x34000 0x4000>;
 				interrupts = <14>;
 				clocks = <&gateclk 1>;
diff --git a/arch/arm/boot/dts/armada-xp.dtsi b/arch/arm/boot/dts/armada-xp.dtsi
index bff9f6c..66d25b7 100644
--- a/arch/arm/boot/dts/armada-xp.dtsi
+++ b/arch/arm/boot/dts/armada-xp.dtsi
@@ -125,7 +125,7 @@
 			};
 
 			eth2: ethernet@30000 {
-				compatible = "marvell,armada-370-neta";
+				compatible = "marvell,armada-xp-neta";
 				reg = <0x30000 0x4000>;
 				interrupts = <12>;
 				clocks = <&gateclk 2>;
@@ -168,6 +168,14 @@
 				};
 			};
 
+			ethernet@70000 {
+				compatible = "marvell,armada-xp-neta";
+			};
+
+			ethernet@74000 {
+				compatible = "marvell,armada-xp-neta";
+			};
+
 			xor@f0900 {
 				compatible = "marvell,orion-xor";
 				reg = <0xF0900 0x100
-- 
2.1.0


From 2e77bed3abb42a8db27d1c8d0970c0bc8651b871 Mon Sep 17 00:00:00 2001
From: Simon Guinot <simon.guinot@sequanux.org>
Date: Tue, 30 Jun 2015 16:20:22 +0200
Subject: [PATCH 16/16] net: mvneta: disable IP checksum with jumbo frames for
 Armada 370

[ Upstream commit b65657fc240ae6c1d2a1e62db9a0e61ac9631d7a ]

The Ethernet controller found in the Armada 370, 380 and 385 SoCs don't
support TCP/IP checksumming with frame sizes larger than 1600 bytes.

This patch fixes the issue by disabling the features NETIF_F_IP_CSUM and
NETIF_F_TSO for the Armada 370 and compatibles SoCs when the MTU is set
to a value greater than 1600 bytes.

Signed-off-by: Simon Guinot <simon.guinot@sequanux.org>
Fixes: c5aff18204da ("net: mvneta: driver for Marvell Armada 370/XP network unit")
Cc: <stable@vger.kernel.org> # v3.8+
Acked-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 26 +++++++++++++++++++++++++-
 1 file changed, 25 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index e62c951..fb34708 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -304,6 +304,7 @@ struct mvneta_port {
 	unsigned int link;
 	unsigned int duplex;
 	unsigned int speed;
+	unsigned int tx_csum_limit;
 };
 
 /* The mvneta_tx_desc and mvneta_rx_desc structures describe the
@@ -2441,8 +2442,10 @@ static int mvneta_change_mtu(struct net_device *dev, int mtu)
 
 	dev->mtu = mtu;
 
-	if (!netif_running(dev))
+	if (!netif_running(dev)) {
+		netdev_update_features(dev);
 		return 0;
+	}
 
 	/* The interface is running, so we have to force a
 	 * reallocation of the queues
@@ -2471,9 +2474,26 @@ static int mvneta_change_mtu(struct net_device *dev, int mtu)
 	mvneta_start_dev(pp);
 	mvneta_port_up(pp);
 
+	netdev_update_features(dev);
+
 	return 0;
 }
 
+static netdev_features_t mvneta_fix_features(struct net_device *dev,
+					     netdev_features_t features)
+{
+	struct mvneta_port *pp = netdev_priv(dev);
+
+	if (pp->tx_csum_limit && dev->mtu > pp->tx_csum_limit) {
+		features &= ~(NETIF_F_IP_CSUM | NETIF_F_TSO);
+		netdev_info(dev,
+			    "Disable IP checksum for MTU greater than %dB\n",
+			    pp->tx_csum_limit);
+	}
+
+	return features;
+}
+
 /* Get mac address */
 static void mvneta_get_mac_addr(struct mvneta_port *pp, unsigned char *addr)
 {
@@ -2791,6 +2811,7 @@ static const struct net_device_ops mvneta_netdev_ops = {
 	.ndo_set_rx_mode     = mvneta_set_rx_mode,
 	.ndo_set_mac_address = mvneta_set_mac_addr,
 	.ndo_change_mtu      = mvneta_change_mtu,
+	.ndo_fix_features    = mvneta_fix_features,
 	.ndo_get_stats64     = mvneta_get_stats64,
 	.ndo_do_ioctl        = mvneta_ioctl,
 };
@@ -3029,6 +3050,9 @@ static int mvneta_probe(struct platform_device *pdev)
 		}
 	}
 
+	if (of_device_is_compatible(dn, "marvell,armada-370-neta"))
+		pp->tx_csum_limit = 1600;
+
 	pp->tx_ring_size = MVNETA_MAX_TXD;
 	pp->rx_ring_size = MVNETA_MAX_RXD;
 
-- 
2.1.0


[-- Attachment #4: net_40.mbox --]
[-- Type: Application/Octet-Stream, Size: 64817 bytes --]

From 6641105f8ad113359438b915a76b6c78eddb3d83 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <razor@blackwall.org>
Date: Tue, 9 Jun 2015 10:23:57 -0700
Subject: [PATCH 01/21] bridge: fix multicast router rlist endless loop

[ Upstream commit 1a040eaca1a22f8da8285ceda6b5e4a2cb704867 ]

Since the addition of sysfs multicast router support if one set
multicast_router to "2" more than once, then the port would be added to
the hlist every time and could end up linking to itself and thus causing an
endless loop for rlist walkers.
So to reproduce just do:
echo 2 > multicast_router; echo 2 > multicast_router;
in a bridge port and let some igmp traffic flow, for me it hangs up
in br_multicast_flood().
Fix this by adding a check in br_multicast_add_router() if the port is
already linked.
The reason this didn't happen before the addition of multicast_router
sysfs entries is because there's a !hlist_unhashed check that prevents
it.

Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Fixes: 0909e11758bd ("bridge: Add multicast_router sysfs entries")
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index b0aee78..c08f510 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1166,6 +1166,9 @@ static void br_multicast_add_router(struct net_bridge *br,
 	struct net_bridge_port *p;
 	struct hlist_node *slot = NULL;
 
+	if (!hlist_unhashed(&port->rlist))
+		return;
+
 	hlist_for_each_entry(p, &br->router_list, rlist) {
 		if ((unsigned long) port >= (unsigned long) p)
 			break;
@@ -1193,12 +1196,8 @@ static void br_multicast_mark_router(struct net_bridge *br,
 	if (port->multicast_router != 1)
 		return;
 
-	if (!hlist_unhashed(&port->rlist))
-		goto timer;
-
 	br_multicast_add_router(br, port);
 
-timer:
 	mod_timer(&port->multicast_router_timer,
 		  now + br->multicast_querier_interval);
 }
-- 
2.1.0


From f36f6b7dc0a529ea475321e3008144ac03e5ec3b Mon Sep 17 00:00:00 2001
From: Richard Cochran <richardcochran@gmail.com>
Date: Thu, 11 Jun 2015 14:51:30 +0200
Subject: [PATCH 02/21] net: igb: fix the start time for periodic output
 signals

[ Upstream commit 58c98be137830d34b79024cc5dc95ef54fcd7ffe ]

When programming the start of a periodic output, the code wrongly places
the seconds value into the "low" register and the nanoseconds into the
"high" register.  Even though this is backwards, it slipped through my
testing, because the re-arming code in the interrupt service routine is
correct, and the signal does appear starting with the second edge.

This patch fixes the issue by programming the registers correctly.

Signed-off-by: Richard Cochran <richardcochran@gmail.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Acked-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/igb/igb_ptp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c
index d20fc8e..c365765 100644
--- a/drivers/net/ethernet/intel/igb/igb_ptp.c
+++ b/drivers/net/ethernet/intel/igb/igb_ptp.c
@@ -540,8 +540,8 @@ static int igb_ptp_feature_enable_i210(struct ptp_clock_info *ptp,
 			igb->perout[i].start.tv_nsec = rq->perout.start.nsec;
 			igb->perout[i].period.tv_sec = ts.tv_sec;
 			igb->perout[i].period.tv_nsec = ts.tv_nsec;
-			wr32(trgttiml, rq->perout.start.sec);
-			wr32(trgttimh, rq->perout.start.nsec);
+			wr32(trgttimh, rq->perout.start.sec);
+			wr32(trgttiml, rq->perout.start.nsec);
 			tsauxc |= tsauxc_mask;
 			tsim |= tsim_mask;
 		} else {
-- 
2.1.0


From e8b570a1d27393398e19183305cea6d1e300c246 Mon Sep 17 00:00:00 2001
From: Shaohua Li <shli@fb.com>
Date: Thu, 11 Jun 2015 16:50:48 -0700
Subject: [PATCH 03/21] net: don't wait for order-3 page allocation

[ Upstream commit fb05e7a89f500cfc06ae277bdc911b281928995d ]

We saw excessive direct memory compaction triggered by skb_page_frag_refill.
This causes performance issues and add latency. Commit 5640f7685831e0
introduces the order-3 allocation. According to the changelog, the order-3
allocation isn't a must-have but to improve performance. But direct memory
compaction has high overhead. The benefit of order-3 allocation can't
compensate the overhead of direct memory compaction.

This patch makes the order-3 page allocation atomic. If there is no memory
pressure and memory isn't fragmented, the alloction will still success, so we
don't sacrifice the order-3 benefit here. If the atomic allocation fails,
direct memory compaction will not be triggered, skb_page_frag_refill will
fallback to order-0 immediately, hence the direct memory compaction overhead is
avoided. In the allocation failure case, kswapd is waken up and doing
compaction, so chances are allocation could success next time.

alloc_skb_with_frags is the same.

The mellanox driver does similar thing, if this is accepted, we must fix
the driver too.

V3: fix the same issue in alloc_skb_with_frags as pointed out by Eric
V2: make the changelog clearer

Cc: Eric Dumazet <edumazet@google.com>
Cc: Chris Mason <clm@fb.com>
Cc: Debabrata Banerjee <dbavatar@gmail.com>
Signed-off-by: Shaohua Li <shli@fb.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 2 +-
 net/core/sock.c   | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index e9f9a15..1e3abb8 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4443,7 +4443,7 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len,
 
 		while (order) {
 			if (npages >= 1 << order) {
-				page = alloc_pages(gfp_mask |
+				page = alloc_pages((gfp_mask & ~__GFP_WAIT) |
 						   __GFP_COMP |
 						   __GFP_NOWARN |
 						   __GFP_NORETRY,
diff --git a/net/core/sock.c b/net/core/sock.c
index 71e3e5f..c77d5d2 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1895,7 +1895,7 @@ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t gfp)
 
 	pfrag->offset = 0;
 	if (SKB_FRAG_PAGE_ORDER) {
-		pfrag->page = alloc_pages(gfp | __GFP_COMP |
+		pfrag->page = alloc_pages((gfp & ~__GFP_WAIT) | __GFP_COMP |
 					  __GFP_NOWARN | __GFP_NORETRY,
 					  SKB_FRAG_PAGE_ORDER);
 		if (likely(pfrag->page)) {
-- 
2.1.0


From 8b52b28ac808de685397b2891d6cd294a775e5c6 Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Fri, 12 Jun 2015 10:16:41 -0300
Subject: [PATCH 04/21] sctp: fix ASCONF list handling

[ Upstream commit 2d45a02d0166caf2627fe91897c6ffc3b19514c4 ]

->auto_asconf_splist is per namespace and mangled by functions like
sctp_setsockopt_auto_asconf() which doesn't guarantee any serialization.

Also, the call to inet_sk_copy_descendant() was backuping
->auto_asconf_list through the copy but was not honoring
->do_auto_asconf, which could lead to list corruption if it was
different between both sockets.

This commit thus fixes the list handling by using ->addr_wq_lock
spinlock to protect the list. A special handling is done upon socket
creation and destruction for that. Error handlig on sctp_init_sock()
will never return an error after having initialized asconf, so
sctp_destroy_sock() can be called without addrq_wq_lock. The lock now
will be take on sctp_close_sock(), before locking the socket, so we
don't do it in inverse order compared to sctp_addr_wq_timeout_handler().

Instead of taking the lock on sctp_sock_migrate() for copying and
restoring the list values, it's preferred to avoid rewritting it by
implementing sctp_copy_descendant().

Issue was found with a test application that kept flipping sysctl
default_auto_asconf on and off, but one could trigger it by issuing
simultaneous setsockopt() calls on multiple sockets or by
creating/destroying sockets fast enough. This is only triggerable
locally.

Fixes: 9f7d653b67ae ("sctp: Add Auto-ASCONF support (core).")
Reported-by: Ji Jianwen <jiji@redhat.com>
Suggested-by: Neil Horman <nhorman@tuxdriver.com>
Suggested-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netns/sctp.h   |  1 +
 include/net/sctp/structs.h |  4 ++++
 net/sctp/socket.c          | 43 ++++++++++++++++++++++++++++++++-----------
 3 files changed, 37 insertions(+), 11 deletions(-)

diff --git a/include/net/netns/sctp.h b/include/net/netns/sctp.h
index 3573a81..8ba379f 100644
--- a/include/net/netns/sctp.h
+++ b/include/net/netns/sctp.h
@@ -31,6 +31,7 @@ struct netns_sctp {
 	struct list_head addr_waitq;
 	struct timer_list addr_wq_timer;
 	struct list_head auto_asconf_splist;
+	/* Lock that protects both addr_waitq and auto_asconf_splist */
 	spinlock_t addr_wq_lock;
 
 	/* Lock that protects the local_addr_list writers */
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 2bb2fcf..495c87e 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -223,6 +223,10 @@ struct sctp_sock {
 	atomic_t pd_mode;
 	/* Receive to here while partial delivery is in effect. */
 	struct sk_buff_head pd_lobby;
+
+	/* These must be the last fields, as they will skipped on copies,
+	 * like on accept and peeloff operations
+	 */
 	struct list_head auto_asconf_list;
 	int do_auto_asconf;
 };
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index aafe94b..4e56571 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1533,8 +1533,10 @@ static void sctp_close(struct sock *sk, long timeout)
 
 	/* Supposedly, no process has access to the socket, but
 	 * the net layers still may.
+	 * Also, sctp_destroy_sock() needs to be called with addr_wq_lock
+	 * held and that should be grabbed before socket lock.
 	 */
-	local_bh_disable();
+	spin_lock_bh(&net->sctp.addr_wq_lock);
 	bh_lock_sock(sk);
 
 	/* Hold the sock, since sk_common_release() will put sock_put()
@@ -1544,7 +1546,7 @@ static void sctp_close(struct sock *sk, long timeout)
 	sk_common_release(sk);
 
 	bh_unlock_sock(sk);
-	local_bh_enable();
+	spin_unlock_bh(&net->sctp.addr_wq_lock);
 
 	sock_put(sk);
 
@@ -3587,6 +3589,7 @@ static int sctp_setsockopt_auto_asconf(struct sock *sk, char __user *optval,
 	if ((val && sp->do_auto_asconf) || (!val && !sp->do_auto_asconf))
 		return 0;
 
+	spin_lock_bh(&sock_net(sk)->sctp.addr_wq_lock);
 	if (val == 0 && sp->do_auto_asconf) {
 		list_del(&sp->auto_asconf_list);
 		sp->do_auto_asconf = 0;
@@ -3595,6 +3598,7 @@ static int sctp_setsockopt_auto_asconf(struct sock *sk, char __user *optval,
 		    &sock_net(sk)->sctp.auto_asconf_splist);
 		sp->do_auto_asconf = 1;
 	}
+	spin_unlock_bh(&sock_net(sk)->sctp.addr_wq_lock);
 	return 0;
 }
 
@@ -4128,18 +4132,28 @@ static int sctp_init_sock(struct sock *sk)
 	local_bh_disable();
 	percpu_counter_inc(&sctp_sockets_allocated);
 	sock_prot_inuse_add(net, sk->sk_prot, 1);
+
+	/* Nothing can fail after this block, otherwise
+	 * sctp_destroy_sock() will be called without addr_wq_lock held
+	 */
 	if (net->sctp.default_auto_asconf) {
+		spin_lock(&sock_net(sk)->sctp.addr_wq_lock);
 		list_add_tail(&sp->auto_asconf_list,
 		    &net->sctp.auto_asconf_splist);
 		sp->do_auto_asconf = 1;
-	} else
+		spin_unlock(&sock_net(sk)->sctp.addr_wq_lock);
+	} else {
 		sp->do_auto_asconf = 0;
+	}
+
 	local_bh_enable();
 
 	return 0;
 }
 
-/* Cleanup any SCTP per socket resources.  */
+/* Cleanup any SCTP per socket resources. Must be called with
+ * sock_net(sk)->sctp.addr_wq_lock held if sp->do_auto_asconf is true
+ */
 static void sctp_destroy_sock(struct sock *sk)
 {
 	struct sctp_sock *sp;
@@ -7202,6 +7216,19 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk,
 	newinet->mc_list = NULL;
 }
 
+static inline void sctp_copy_descendant(struct sock *sk_to,
+					const struct sock *sk_from)
+{
+	int ancestor_size = sizeof(struct inet_sock) +
+			    sizeof(struct sctp_sock) -
+			    offsetof(struct sctp_sock, auto_asconf_list);
+
+	if (sk_from->sk_family == PF_INET6)
+		ancestor_size += sizeof(struct ipv6_pinfo);
+
+	__inet_sk_copy_descendant(sk_to, sk_from, ancestor_size);
+}
+
 /* Populate the fields of the newsk from the oldsk and migrate the assoc
  * and its messages to the newsk.
  */
@@ -7216,7 +7243,6 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
 	struct sk_buff *skb, *tmp;
 	struct sctp_ulpevent *event;
 	struct sctp_bind_hashbucket *head;
-	struct list_head tmplist;
 
 	/* Migrate socket buffer sizes and all the socket level options to the
 	 * new socket.
@@ -7224,12 +7250,7 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
 	newsk->sk_sndbuf = oldsk->sk_sndbuf;
 	newsk->sk_rcvbuf = oldsk->sk_rcvbuf;
 	/* Brute force copy old sctp opt. */
-	if (oldsp->do_auto_asconf) {
-		memcpy(&tmplist, &newsp->auto_asconf_list, sizeof(tmplist));
-		inet_sk_copy_descendant(newsk, oldsk);
-		memcpy(&newsp->auto_asconf_list, &tmplist, sizeof(tmplist));
-	} else
-		inet_sk_copy_descendant(newsk, oldsk);
+	sctp_copy_descendant(newsk, oldsk);
 
 	/* Restore the ep value that was overwritten with the above structure
 	 * copy.
-- 
2.1.0


From 591ded7a930c5d14cc9f4fbb94e5e94c7952792f Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <razor@blackwall.org>
Date: Mon, 15 Jun 2015 20:28:51 +0300
Subject: [PATCH 05/21] bridge: fix br_stp_set_bridge_priority race conditions

[ Upstream commit 2dab80a8b486f02222a69daca6859519e05781d9 ]

After the ->set() spinlocks were removed br_stp_set_bridge_priority
was left running without any protection when used via sysfs. It can
race with port add/del and could result in use-after-free cases and
corrupted lists. Tested by running port add/del in a loop with stp
enabled while setting priority in a loop, crashes are easily
reproducible.
The spinlocks around sysfs ->set() were removed in commit:
14f98f258f19 ("bridge: range check STP parameters")
There's also a race condition in the netlink priority support that is
fixed by this change, but it was introduced recently and the fixes tag
covers it, just in case it's needed the commit is:
af615762e972 ("bridge: add ageing_time, stp_state, priority over netlink")

Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Fixes: 14f98f258f19 ("bridge: range check STP parameters")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_ioctl.c  | 2 --
 net/bridge/br_stp_if.c | 4 +++-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c
index a9a4a1b..8d423bc 100644
--- a/net/bridge/br_ioctl.c
+++ b/net/bridge/br_ioctl.c
@@ -247,9 +247,7 @@ static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 		if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN))
 			return -EPERM;
 
-		spin_lock_bh(&br->lock);
 		br_stp_set_bridge_priority(br, args[1]);
-		spin_unlock_bh(&br->lock);
 		return 0;
 
 	case BRCTL_SET_PORT_PRIORITY:
diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
index 4114687..7832d07 100644
--- a/net/bridge/br_stp_if.c
+++ b/net/bridge/br_stp_if.c
@@ -243,12 +243,13 @@ bool br_stp_recalculate_bridge_id(struct net_bridge *br)
 	return true;
 }
 
-/* called under bridge lock */
+/* Acquires and releases bridge lock */
 void br_stp_set_bridge_priority(struct net_bridge *br, u16 newprio)
 {
 	struct net_bridge_port *p;
 	int wasroot;
 
+	spin_lock_bh(&br->lock);
 	wasroot = br_is_root_bridge(br);
 
 	list_for_each_entry(p, &br->port_list, list) {
@@ -266,6 +267,7 @@ void br_stp_set_bridge_priority(struct net_bridge *br, u16 newprio)
 	br_port_state_selection(br);
 	if (br_is_root_bridge(br) && !wasroot)
 		br_become_root_bridge(br);
+	spin_unlock_bh(&br->lock);
 }
 
 /* called under bridge lock */
-- 
2.1.0


From 51f2798e99939352aafa83b1e81835872fe18cc4 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 16 Jun 2015 07:59:11 -0700
Subject: [PATCH 06/21] packet: read num_members once in packet_rcv_fanout()

[ Upstream commit f98f4514d07871da7a113dd9e3e330743fd70ae4 ]

We need to tell compiler it must not read f->num_members multiple
times. Otherwise testing if num is not zero is flaky, and we could
attempt an invalid divide by 0 in fanout_demux_cpu()

Note bug was present in packet_rcv_fanout_hash() and
packet_rcv_fanout_lb() but final 3.1 had a simple location
after commit 95ec3eb417115fb ("packet: Add 'cpu' fanout policy.")

Fixes: dc99f600698dc ("packet: Add fanout support.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index f8db706..b4dfdff 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1347,7 +1347,7 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
 			     struct packet_type *pt, struct net_device *orig_dev)
 {
 	struct packet_fanout *f = pt->af_packet_priv;
-	unsigned int num = f->num_members;
+	unsigned int num = READ_ONCE(f->num_members);
 	struct packet_sock *po;
 	unsigned int idx;
 
-- 
2.1.0


From dc65c0b38936edfe476131df39d2a3ca12246007 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 17 Jun 2015 15:59:34 -0400
Subject: [PATCH 07/21] packet: avoid out of bounds read in round robin fanout

[ Upstream commit 468479e6043c84f5a65299cc07cb08a22a28c2b1 ]

PACKET_FANOUT_LB computes f->rr_cur such that it is modulo
f->num_members. It returns the old value unconditionally, but
f->num_members may have changed since the last store. Ensure
that the return value is always < num.

When modifying the logic, simplify it further by replacing the loop
with an unconditional atomic increment.

Fixes: dc99f600698d ("packet: Add fanout support.")
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 18 ++----------------
 1 file changed, 2 insertions(+), 16 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index b4dfdff..bfe5c69 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1266,16 +1266,6 @@ static void packet_sock_destruct(struct sock *sk)
 	sk_refcnt_debug_dec(sk);
 }
 
-static int fanout_rr_next(struct packet_fanout *f, unsigned int num)
-{
-	int x = atomic_read(&f->rr_cur) + 1;
-
-	if (x >= num)
-		x = 0;
-
-	return x;
-}
-
 static unsigned int fanout_demux_hash(struct packet_fanout *f,
 				      struct sk_buff *skb,
 				      unsigned int num)
@@ -1287,13 +1277,9 @@ static unsigned int fanout_demux_lb(struct packet_fanout *f,
 				    struct sk_buff *skb,
 				    unsigned int num)
 {
-	int cur, old;
+	unsigned int val = atomic_inc_return(&f->rr_cur);
 
-	cur = atomic_read(&f->rr_cur);
-	while ((old = atomic_cmpxchg(&f->rr_cur, cur,
-				     fanout_rr_next(f, num))) != cur)
-		cur = old;
-	return cur;
+	return val % num;
 }
 
 static unsigned int fanout_demux_cpu(struct packet_fanout *f,
-- 
2.1.0


From 3e32111e0f4825d79313eaa1fdc22adb3441a520 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Tue, 16 Jun 2015 22:56:39 +0300
Subject: [PATCH 08/21] neigh: do not modify unlinked entries

[ Upstream commit 2c51a97f76d20ebf1f50fef908b986cb051fdff9 ]

The lockless lookups can return entry that is unlinked.
Sometimes they get reference before last neigh_cleanup_and_release,
sometimes they do not need reference. Later, any
modification attempts may result in the following problems:

1. entry is not destroyed immediately because neigh_update
can start the timer for dead entry, eg. on change to NUD_REACHABLE
state. As result, entry lives for some time but is invisible
and out of control.

2. __neigh_event_send can run in parallel with neigh_destroy
while refcnt=0 but if timer is started and expired refcnt can
reach 0 for second time leading to second neigh_destroy and
possible crash.

Thanks to Eric Dumazet and Ying Xue for their work and analyze
on the __neigh_event_send change.

Fixes: 767e97e1e0db ("neigh: RCU conversion of struct neighbour")
Fixes: a263b3093641 ("ipv4: Make neigh lookups directly in output packet path.")
Fixes: 6fd6ce2056de ("ipv6: Do not depend on rt->n in ip6_finish_output2().")
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 70fe9e1..d0e5d66 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -971,6 +971,8 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
 	rc = 0;
 	if (neigh->nud_state & (NUD_CONNECTED | NUD_DELAY | NUD_PROBE))
 		goto out_unlock_bh;
+	if (neigh->dead)
+		goto out_dead;
 
 	if (!(neigh->nud_state & (NUD_STALE | NUD_INCOMPLETE))) {
 		if (NEIGH_VAR(neigh->parms, MCAST_PROBES) +
@@ -1027,6 +1029,13 @@ out_unlock_bh:
 		write_unlock(&neigh->lock);
 	local_bh_enable();
 	return rc;
+
+out_dead:
+	if (neigh->nud_state & NUD_STALE)
+		goto out_unlock_bh;
+	write_unlock_bh(&neigh->lock);
+	kfree_skb(skb);
+	return 1;
 }
 EXPORT_SYMBOL(__neigh_event_send);
 
@@ -1090,6 +1099,8 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
 	if (!(flags & NEIGH_UPDATE_F_ADMIN) &&
 	    (old & (NUD_NOARP | NUD_PERMANENT)))
 		goto out;
+	if (neigh->dead)
+		goto out;
 
 	if (!(new & NUD_VALID)) {
 		neigh_del_timer(neigh);
@@ -1239,6 +1250,8 @@ EXPORT_SYMBOL(neigh_update);
  */
 void __neigh_set_probe_once(struct neighbour *neigh)
 {
+	if (neigh->dead)
+		return;
 	neigh->updated = jiffies;
 	if (!(neigh->nud_state & NUD_FAILED))
 		return;
-- 
2.1.0


From 4eeffe9068f66db69429a808e6ddf27b1a8f8d91 Mon Sep 17 00:00:00 2001
From: Christoph Paasch <cpaasch@apple.com>
Date: Thu, 18 Jun 2015 09:15:34 -0700
Subject: [PATCH 09/21] tcp: Do not call tcp_fastopen_reset_cipher from
 interrupt context

[ Upstream commit dfea2aa654243f70dc53b8648d0bbdeec55a7df1 ]

tcp_fastopen_reset_cipher really cannot be called from interrupt
context. It allocates the tcp_fastopen_context with GFP_KERNEL and
calls crypto_alloc_cipher, which allocates all kind of stuff with
GFP_KERNEL.

Thus, we might sleep when the key-generation is triggered by an
incoming TFO cookie-request which would then happen in interrupt-
context, as shown by enabling CONFIG_DEBUG_ATOMIC_SLEEP:

[   36.001813] BUG: sleeping function called from invalid context at mm/slub.c:1266
[   36.003624] in_atomic(): 1, irqs_disabled(): 0, pid: 1016, name: packetdrill
[   36.004859] CPU: 1 PID: 1016 Comm: packetdrill Not tainted 4.1.0-rc7 #14
[   36.006085] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.7.5-0-ge51488c-20140602_164612-nilsson.home.kraxel.org 04/01/2014
[   36.008250]  00000000000004f2 ffff88007f8838a8 ffffffff8171d53a ffff880075a084a8
[   36.009630]  ffff880075a08000 ffff88007f8838c8 ffffffff810967d3 ffff88007f883928
[   36.011076]  0000000000000000 ffff88007f8838f8 ffffffff81096892 ffff88007f89be00
[   36.012494] Call Trace:
[   36.012953]  <IRQ>  [<ffffffff8171d53a>] dump_stack+0x4f/0x6d
[   36.014085]  [<ffffffff810967d3>] ___might_sleep+0x103/0x170
[   36.015117]  [<ffffffff81096892>] __might_sleep+0x52/0x90
[   36.016117]  [<ffffffff8118e887>] kmem_cache_alloc_trace+0x47/0x190
[   36.017266]  [<ffffffff81680d82>] ? tcp_fastopen_reset_cipher+0x42/0x130
[   36.018485]  [<ffffffff81680d82>] tcp_fastopen_reset_cipher+0x42/0x130
[   36.019679]  [<ffffffff81680f01>] tcp_fastopen_init_key_once+0x61/0x70
[   36.020884]  [<ffffffff81680f2c>] __tcp_fastopen_cookie_gen+0x1c/0x60
[   36.022058]  [<ffffffff816814ff>] tcp_try_fastopen+0x58f/0x730
[   36.023118]  [<ffffffff81671788>] tcp_conn_request+0x3e8/0x7b0
[   36.024185]  [<ffffffff810e3872>] ? __module_text_address+0x12/0x60
[   36.025327]  [<ffffffff8167b2e1>] tcp_v4_conn_request+0x51/0x60
[   36.026410]  [<ffffffff816727e0>] tcp_rcv_state_process+0x190/0xda0
[   36.027556]  [<ffffffff81661f97>] ? __inet_lookup_established+0x47/0x170
[   36.028784]  [<ffffffff8167c2ad>] tcp_v4_do_rcv+0x16d/0x3d0
[   36.029832]  [<ffffffff812e6806>] ? security_sock_rcv_skb+0x16/0x20
[   36.030936]  [<ffffffff8167cc8a>] tcp_v4_rcv+0x77a/0x7b0
[   36.031875]  [<ffffffff816af8c3>] ? iptable_filter_hook+0x33/0x70
[   36.032953]  [<ffffffff81657d22>] ip_local_deliver_finish+0x92/0x1f0
[   36.034065]  [<ffffffff81657f1a>] ip_local_deliver+0x9a/0xb0
[   36.035069]  [<ffffffff81657c90>] ? ip_rcv+0x3d0/0x3d0
[   36.035963]  [<ffffffff81657569>] ip_rcv_finish+0x119/0x330
[   36.036950]  [<ffffffff81657ba7>] ip_rcv+0x2e7/0x3d0
[   36.037847]  [<ffffffff81610652>] __netif_receive_skb_core+0x552/0x930
[   36.038994]  [<ffffffff81610a57>] __netif_receive_skb+0x27/0x70
[   36.040033]  [<ffffffff81610b72>] process_backlog+0xd2/0x1f0
[   36.041025]  [<ffffffff81611482>] net_rx_action+0x122/0x310
[   36.042007]  [<ffffffff81076743>] __do_softirq+0x103/0x2f0
[   36.042978]  [<ffffffff81723e3c>] do_softirq_own_stack+0x1c/0x30

This patch moves the call to tcp_fastopen_init_key_once to the places
where a listener socket creates its TFO-state, which always happens in
user-context (either from the setsockopt, or implicitly during the
listen()-call)

Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Fixes: 222e83d2e0ae ("tcp: switch tcp_fastopen key generation to net_get_random_once")
Signed-off-by: Christoph Paasch <cpaasch@apple.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/af_inet.c      | 2 ++
 net/ipv4/tcp.c          | 7 +++++--
 net/ipv4/tcp_fastopen.c | 2 --
 3 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index d2e49ba..61edc49 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -228,6 +228,8 @@ int inet_listen(struct socket *sock, int backlog)
 				err = 0;
 			if (err)
 				goto out;
+
+			tcp_fastopen_init_key_once(true);
 		}
 		err = inet_csk_listen_start(sk, backlog);
 		if (err)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 995a225..d03a344 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2541,10 +2541,13 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 
 	case TCP_FASTOPEN:
 		if (val >= 0 && ((1 << sk->sk_state) & (TCPF_CLOSE |
-		    TCPF_LISTEN)))
+		    TCPF_LISTEN))) {
+			tcp_fastopen_init_key_once(true);
+
 			err = fastopen_init_queue(sk, val);
-		else
+		} else {
 			err = -EINVAL;
+		}
 		break;
 	case TCP_TIMESTAMP:
 		if (!tp->repair)
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index ea82fd4..9c37181 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -78,8 +78,6 @@ static bool __tcp_fastopen_cookie_gen(const void *path,
 	struct tcp_fastopen_context *ctx;
 	bool ok = false;
 
-	tcp_fastopen_init_key_once(true);
-
 	rcu_read_lock();
 	ctx = rcu_dereference(tcp_fastopen_ctx);
 	if (ctx) {
-- 
2.1.0


From 602553606746ad766f0d91a32890ee0b47eddefa Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Tue, 23 Jun 2015 08:34:39 +0300
Subject: [PATCH 10/21] ip: report the original address of ICMP messages

[ Upstream commit 34b99df4e6256ddafb663c6de0711dceceddfe0e ]

ICMP messages can trigger ICMP and local errors. In this case
serr->port is 0 and starting from Linux 4.0 we do not return
the original target address to the error queue readers.
Add function to define which errors provide addr_offset.
With this fix my ping command is not silent anymore.

Fixes: c247f0534cc5 ("ip: fix error queue empty skb handling")
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_sockglue.c | 11 ++++++++++-
 net/ipv6/datagram.c    | 12 +++++++++++-
 2 files changed, 21 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 5cd9927..d9e8ff3 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -432,6 +432,15 @@ void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 inf
 		kfree_skb(skb);
 }
 
+/* For some errors we have valid addr_offset even with zero payload and
+ * zero port. Also, addr_offset should be supported if port is set.
+ */
+static inline bool ipv4_datagram_support_addr(struct sock_exterr_skb *serr)
+{
+	return serr->ee.ee_origin == SO_EE_ORIGIN_ICMP ||
+	       serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL || serr->port;
+}
+
 /* IPv4 supports cmsg on all imcp errors and some timestamps
  *
  * Timestamp code paths do not initialize the fields expected by cmsg:
@@ -498,7 +507,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 
 	serr = SKB_EXT_ERR(skb);
 
-	if (sin && serr->port) {
+	if (sin && ipv4_datagram_support_addr(serr)) {
 		sin->sin_family = AF_INET;
 		sin->sin_addr.s_addr = *(__be32 *)(skb_network_header(skb) +
 						   serr->addr_offset);
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index ace8dac..d174b91 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -325,6 +325,16 @@ void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu)
 	kfree_skb(skb);
 }
 
+/* For some errors we have valid addr_offset even with zero payload and
+ * zero port. Also, addr_offset should be supported if port is set.
+ */
+static inline bool ipv6_datagram_support_addr(struct sock_exterr_skb *serr)
+{
+	return serr->ee.ee_origin == SO_EE_ORIGIN_ICMP6 ||
+	       serr->ee.ee_origin == SO_EE_ORIGIN_ICMP ||
+	       serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL || serr->port;
+}
+
 /* IPv6 supports cmsg on all origins aside from SO_EE_ORIGIN_LOCAL.
  *
  * At one point, excluding local errors was a quick test to identify icmp/icmp6
@@ -389,7 +399,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 
 	serr = SKB_EXT_ERR(skb);
 
-	if (sin && serr->port) {
+	if (sin && ipv6_datagram_support_addr(serr)) {
 		const unsigned char *nh = skb_network_header(skb);
 		sin->sin6_family = AF_INET6;
 		sin->sin6_flowinfo = 0;
-- 
2.1.0


From 4b0fd50391fd0ad685791ac85c3e6356425cac8c Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Thu, 25 Jun 2015 11:29:41 +0300
Subject: [PATCH 11/21] net/mlx4_en: Release TX QP when destroying TX ring

[ Upstream commit 0eb08514fdbdcd16fd6870680cd638f203662e9d ]

TX ring QP wasn't released at mlx4_en_destroy_tx_ring. Instead, the code
used the deprecated base_tx_qpn field. Move TX QP release to
mlx4_en_destroy_tx_ring and remove the base_tx_qpn field.

Fixes: ddae0349fdb7 ('net/mlx4: Change QP allocation scheme')
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 4 ----
 drivers/net/ethernet/mellanox/mlx4/en_tx.c     | 1 +
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h   | 1 -
 3 files changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 2f1324b..f30c322 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1971,10 +1971,6 @@ void mlx4_en_free_resources(struct mlx4_en_priv *priv)
 			mlx4_en_destroy_cq(priv, &priv->rx_cq[i]);
 	}
 
-	if (priv->base_tx_qpn) {
-		mlx4_qp_release_range(priv->mdev->dev, priv->base_tx_qpn, priv->tx_ring_num);
-		priv->base_tx_qpn = 0;
-	}
 }
 
 int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 8c234ec..998615b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -180,6 +180,7 @@ void mlx4_en_destroy_tx_ring(struct mlx4_en_priv *priv,
 		mlx4_bf_free(mdev->dev, &ring->bf);
 	mlx4_qp_remove(mdev->dev, &ring->qp);
 	mlx4_qp_free(mdev->dev, &ring->qp);
+	mlx4_qp_release_range(priv->mdev->dev, ring->qpn, 1);
 	mlx4_en_unmap_buffer(&ring->wqres.buf);
 	mlx4_free_hwq_res(mdev->dev, &ring->wqres, ring->buf_size);
 	kfree(ring->bounce_buf);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 8687c8d..c3e4dfd 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -601,7 +601,6 @@ struct mlx4_en_priv {
 	int vids[128];
 	bool wol;
 	struct device *ddev;
-	int base_tx_qpn;
 	struct hlist_head mac_hash[MLX4_EN_MAC_HASH_SIZE];
 	struct hwtstamp_config hwtstamp_config;
 
-- 
2.1.0


From 781559a23a57776f0ac4c21fe3fee0670285861f Mon Sep 17 00:00:00 2001
From: Ido Shamay <idos@mellanox.com>
Date: Thu, 25 Jun 2015 11:29:42 +0300
Subject: [PATCH 12/21] net/mlx4_en: Wake TX queues only when there's enough
 room

[ Upstream commit 488a9b48e398b157703766e2cd91ea45ac6997c5 ]

Indication of a single completed packet, marked by txbbs_skipped
being bigger then zero, in not enough in order to wake up a
stopped TX queue. The completed packet may contain a single TXBB,
while next packet to be sent (after the wake up) may have multiple
TXBBs (LSO/TSO packets for example), causing overflow in queue followed
by WQE corruption and TX queue timeout.
Instead, wake the stopped queue only when there's enough room for the
worst case (maximum sized WQE) packet that we should need to handle after
the queue is opened again.

Also created an helper routine - mlx4_en_is_tx_ring_full, which checks
if the current TX ring is full or not. It provides better code readability
and removes code duplication.

Signed-off-by: Ido Shamay <idos@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_tx.c   | 19 +++++++++++--------
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h |  1 +
 2 files changed, 12 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 998615b..35dd887 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -66,6 +66,7 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 	ring->size = size;
 	ring->size_mask = size - 1;
 	ring->stride = stride;
+	ring->full_size = ring->size - HEADROOM - MAX_DESC_TXBBS;
 
 	tmp = size * sizeof(struct mlx4_en_tx_info);
 	ring->tx_info = kmalloc_node(tmp, GFP_KERNEL | __GFP_NOWARN, node);
@@ -232,6 +233,11 @@ void mlx4_en_deactivate_tx_ring(struct mlx4_en_priv *priv,
 		       MLX4_QP_STATE_RST, NULL, 0, 0, &ring->qp);
 }
 
+static inline bool mlx4_en_is_tx_ring_full(struct mlx4_en_tx_ring *ring)
+{
+	return ring->prod - ring->cons > ring->full_size;
+}
+
 static void mlx4_en_stamp_wqe(struct mlx4_en_priv *priv,
 			      struct mlx4_en_tx_ring *ring, int index,
 			      u8 owner)
@@ -474,11 +480,10 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev,
 
 	netdev_tx_completed_queue(ring->tx_queue, packets, bytes);
 
-	/*
-	 * Wakeup Tx queue if this stopped, and at least 1 packet
-	 * was completed
+	/* Wakeup Tx queue if this stopped, and ring is not full.
 	 */
-	if (netif_tx_queue_stopped(ring->tx_queue) && txbbs_skipped > 0) {
+	if (netif_tx_queue_stopped(ring->tx_queue) &&
+	    !mlx4_en_is_tx_ring_full(ring)) {
 		netif_tx_wake_queue(ring->tx_queue);
 		ring->wake_queue++;
 	}
@@ -922,8 +927,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	skb_tx_timestamp(skb);
 
 	/* Check available TXBBs And 2K spare for prefetch */
-	stop_queue = (int)(ring->prod - ring_cons) >
-		      ring->size - HEADROOM - MAX_DESC_TXBBS;
+	stop_queue = mlx4_en_is_tx_ring_full(ring);
 	if (unlikely(stop_queue)) {
 		netif_tx_stop_queue(ring->tx_queue);
 		ring->queue_stopped++;
@@ -992,8 +996,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 		smp_rmb();
 
 		ring_cons = ACCESS_ONCE(ring->cons);
-		if (unlikely(((int)(ring->prod - ring_cons)) <=
-			     ring->size - HEADROOM - MAX_DESC_TXBBS)) {
+		if (unlikely(!mlx4_en_is_tx_ring_full(ring))) {
 			netif_tx_wake_queue(ring->tx_queue);
 			ring->wake_queue++;
 		}
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index c3e4dfd..0bf0fdd 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -280,6 +280,7 @@ struct mlx4_en_tx_ring {
 	u32			size; /* number of TXBBs */
 	u32			size_mask;
 	u16			stride;
+	u32			full_size;
 	u16			cqn;	/* index of port CQ associated with this ring */
 	u32			buf_size;
 	__be32			doorbell_qpn;
-- 
2.1.0


From b2d1d0cb847f05e62bfe27024a5c881b89090b69 Mon Sep 17 00:00:00 2001
From: Ido Shamay <idos@mellanox.com>
Date: Thu, 25 Jun 2015 11:29:43 +0300
Subject: [PATCH 13/21] net/mlx4_en: Fix wrong csum complete report when rxvlan
 offload is disabled

[ Upstream commit 79a258526ce1051cb9684018c25a89d51ac21be8 ]

The check_csum() function relied on hwtstamp_rx_filter to know if rxvlan
offload is disabled. This is wrong since rxvlan offload can be switched
on/off regardless of hwtstamp_rx_filter.

Also moved check_csum to query CQE information to identify VLAN packets
and removed the check of IP packets, since it has been validated before.

Fixes: f8c6455bb04b ('net/mlx4_en: Extend checksum offloading by CHECKSUM COMPLETE')
Signed-off-by: Ido Shamay <idos@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_rx.c | 17 ++++++-----------
 1 file changed, 6 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 05ec5e1..3478c87 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -723,7 +723,7 @@ static int get_fixed_ipv6_csum(__wsum hw_checksum, struct sk_buff *skb,
 }
 #endif
 static int check_csum(struct mlx4_cqe *cqe, struct sk_buff *skb, void *va,
-		      int hwtstamp_rx_filter)
+		      netdev_features_t dev_features)
 {
 	__wsum hw_checksum = 0;
 
@@ -731,14 +731,8 @@ static int check_csum(struct mlx4_cqe *cqe, struct sk_buff *skb, void *va,
 
 	hw_checksum = csum_unfold((__force __sum16)cqe->checksum);
 
-	if (((struct ethhdr *)va)->h_proto == htons(ETH_P_8021Q) &&
-	    hwtstamp_rx_filter != HWTSTAMP_FILTER_NONE) {
-		/* next protocol non IPv4 or IPv6 */
-		if (((struct vlan_hdr *)hdr)->h_vlan_encapsulated_proto
-		    != htons(ETH_P_IP) &&
-		    ((struct vlan_hdr *)hdr)->h_vlan_encapsulated_proto
-		    != htons(ETH_P_IPV6))
-			return -1;
+	if (cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_VLAN_PRESENT_MASK) &&
+	    !(dev_features & NETIF_F_HW_VLAN_CTAG_RX)) {
 		hw_checksum = get_fixed_vlan_csum(hw_checksum, hdr);
 		hdr += sizeof(struct vlan_hdr);
 	}
@@ -901,7 +895,8 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 
 			if (ip_summed == CHECKSUM_COMPLETE) {
 				void *va = skb_frag_address(skb_shinfo(gro_skb)->frags);
-				if (check_csum(cqe, gro_skb, va, ring->hwtstamp_rx_filter)) {
+				if (check_csum(cqe, gro_skb, va,
+					       dev->features)) {
 					ip_summed = CHECKSUM_NONE;
 					ring->csum_none++;
 					ring->csum_complete--;
@@ -956,7 +951,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 		}
 
 		if (ip_summed == CHECKSUM_COMPLETE) {
-			if (check_csum(cqe, skb, skb->data, ring->hwtstamp_rx_filter)) {
+			if (check_csum(cqe, skb, skb->data, dev->features)) {
 				ip_summed = CHECKSUM_NONE;
 				ring->csum_complete--;
 				ring->csum_none++;
-- 
2.1.0


From 763078fa436c9f6a43801499a72d8b5233b52919 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Thu, 25 Jun 2015 11:29:44 +0300
Subject: [PATCH 14/21] mlx4: Disable HA for SRIOV PF RoCE devices

[ Upstream commit 7254acffeeec3c0a75b9c5364c29a6eb00014930 ]

When in HA mode, the driver exposes an IB (RoCE) device instance with only
one port. Under SRIOV, the existing implementation doesn't go well with
the PF RoCE driver's role of Special QPs Para-Virtualization, etc.

As such, disable HA for the mlx4 PF RoCE device in SRIOV mode.

Fixes: a57500903093 ('IB/mlx4: Add port aggregation support')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/intf.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c
index 6fce587..0d80aed 100644
--- a/drivers/net/ethernet/mellanox/mlx4/intf.c
+++ b/drivers/net/ethernet/mellanox/mlx4/intf.c
@@ -93,8 +93,14 @@ int mlx4_register_interface(struct mlx4_interface *intf)
 	mutex_lock(&intf_mutex);
 
 	list_add_tail(&intf->list, &intf_list);
-	list_for_each_entry(priv, &dev_list, dev_list)
+	list_for_each_entry(priv, &dev_list, dev_list) {
+		if (mlx4_is_mfunc(&priv->dev) && (intf->flags & MLX4_INTFF_BONDING)) {
+			mlx4_dbg(&priv->dev,
+				 "SRIOV, disabling HA mode for intf proto %d\n", intf->protocol);
+			intf->flags &= ~MLX4_INTFF_BONDING;
+		}
 		mlx4_add_device(intf, priv);
+	}
 
 	mutex_unlock(&intf_mutex);
 
-- 
2.1.0


From 82a914a21da6e910784eddae6f26a9b0f5ae9490 Mon Sep 17 00:00:00 2001
From: Mugunthan V N <mugunthanvnm@ti.com>
Date: Thu, 25 Jun 2015 22:21:02 +0530
Subject: [PATCH 15/21] net: phy: fix phy link up when limiting speed via
 device tree

[ Upstream commit eb686231fce3770299760f24fdcf5ad041f44153 ]

When limiting phy link speed using "max-speed" to 100mbps or less on a
giga bit phy, phy never completes auto negotiation and phy state
machine is held in PHY_AN. Fixing this issue by comparing the giga
bit advertise though phydev->supported doesn't have it but phy has
BMSR_ESTATEN set. So that auto negotiation is restarted as old and
new advertise are different and link comes up fine.

Signed-off-by: Mugunthan V N <mugunthanvnm@ti.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index bdfe51f..d551df6 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -796,10 +796,11 @@ static int genphy_config_advert(struct phy_device *phydev)
 	if (phydev->supported & (SUPPORTED_1000baseT_Half |
 				 SUPPORTED_1000baseT_Full)) {
 		adv |= ethtool_adv_to_mii_ctrl1000_t(advertise);
-		if (adv != oldadv)
-			changed = 1;
 	}
 
+	if (adv != oldadv)
+		changed = 1;
+
 	err = phy_write(phydev, MII_CTRL1000, adv);
 	if (err < 0)
 		return err;
-- 
2.1.0


From 931f226c83c6d836f4e98ae7b1c5209bea32c1f1 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 26 Jun 2015 07:32:29 +0200
Subject: [PATCH 16/21] bnx2x: fix lockdep splat

[ Upstream commit d53c66a5b80698620f7c9ba2372fff4017e987b8 ]

Michel reported following lockdep splat

[   44.718117] INFO: trying to register non-static key.
[   44.723081] the code is fine but needs lockdep annotation.
[   44.728559] turning off the locking correctness validator.
[   44.734036] CPU: 8 PID: 5483 Comm: ethtool Not tainted 4.1.0
[   44.770289] Call Trace:
[   44.772741]  [<ffffffff816eb1cd>] dump_stack+0x4c/0x65
[   44.777879]  [<ffffffff8111d921>] ? console_unlock+0x1f1/0x510
[   44.783708]  [<ffffffff811121f5>] __lock_acquire+0x1d05/0x1f10
[   44.789538]  [<ffffffff8111370a>] ? mark_held_locks+0x6a/0x90
[   44.795276]  [<ffffffff81113835>] ? trace_hardirqs_on_caller+0x105/0x1d0
[   44.801967]  [<ffffffff8111390d>] ? trace_hardirqs_on+0xd/0x10
[   44.807793]  [<ffffffff811330fa>] ? hrtimer_try_to_cancel+0x4a/0x250
[   44.814142]  [<ffffffff81112ba6>] lock_acquire+0xb6/0x290
[   44.819537]  [<ffffffff810d6675>] ? flush_work+0x5/0x280
[   44.824844]  [<ffffffff810d66ad>] flush_work+0x3d/0x280
[   44.830061]  [<ffffffff810d6675>] ? flush_work+0x5/0x280
[   44.835366]  [<ffffffff816f3c43>] ? schedule_hrtimeout_range+0x13/0x20
[   44.841889]  [<ffffffff8112ec9b>] ? usleep_range+0x4b/0x50
[   44.847365]  [<ffffffff8111370a>] ? mark_held_locks+0x6a/0x90
[   44.853102]  [<ffffffff810d8585>] ? __cancel_work_timer+0x105/0x1c0
[   44.859359]  [<ffffffff81113835>] ? trace_hardirqs_on_caller+0x105/0x1d0
[   44.866045]  [<ffffffff810d851f>] __cancel_work_timer+0x9f/0x1c0
[   44.872048]  [<ffffffffa0010982>] ? bnx2x_func_stop+0x42/0x90 [bnx2x]
[   44.878481]  [<ffffffff810d8670>] cancel_work_sync+0x10/0x20
[   44.884134]  [<ffffffffa00259e5>] bnx2x_chip_cleanup+0x245/0x730 [bnx2x]
[   44.890829]  [<ffffffff8110ce02>] ? up+0x32/0x50
[   44.895439]  [<ffffffff811306b5>] ? del_timer_sync+0x5/0xd0
[   44.901005]  [<ffffffffa005596d>] bnx2x_nic_unload+0x20d/0x8e0 [bnx2x]
[   44.907527]  [<ffffffff811f1aef>] ? might_fault+0x5f/0xb0
[   44.912921]  [<ffffffffa005851c>] bnx2x_reload_if_running+0x2c/0x50 [bnx2x]
[   44.919879]  [<ffffffffa005a3c5>] bnx2x_set_ringparam+0x2b5/0x460 [bnx2x]
[   44.926664]  [<ffffffff815d498b>] dev_ethtool+0x55b/0x1c40
[   44.932148]  [<ffffffff815dfdc7>] ? rtnl_lock+0x17/0x20
[   44.937364]  [<ffffffff815e7f8b>] dev_ioctl+0x17b/0x630
[   44.942582]  [<ffffffff815abf8d>] sock_do_ioctl+0x5d/0x70
[   44.947972]  [<ffffffff815ac013>] sock_ioctl+0x73/0x280
[   44.953192]  [<ffffffff8124c1c8>] do_vfs_ioctl+0x88/0x5b0
[   44.958587]  [<ffffffff8110d0b3>] ? up_read+0x23/0x40
[   44.963631]  [<ffffffff812584cc>] ? __fget_light+0x6c/0xa0
[   44.969105]  [<ffffffff8124c781>] SyS_ioctl+0x91/0xb0
[   44.974149]  [<ffffffff816f4dd7>] system_call_fastpath+0x12/0x6f

As bnx2x_init_ptp() is only called if bp->flags contains PTP_SUPPORTED,
we also need to guard bnx2x_stop_ptp() with same condition, otherwise
ptp_task workqueue is not initialized and kernel barfs on
cancel_work_sync()

Fixes: eeed018cbfa30 ("bnx2x: Add timestamping and PTP hardware clock support")
Reported-by: Michel Lespinasse <walken@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Michal Kalderon <Michal.Kalderon@qlogic.com>
Cc: Ariel Elior <Ariel.Elior@qlogic.com>
Cc: Yuval Mintz <Yuval.Mintz@qlogic.com>
Cc: David Decotigny <decot@google.com>
Acked-by: Sony Chacko <sony.chacko@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 1ec635f..196474f 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -9323,7 +9323,8 @@ unload_error:
 	 * function stop ramrod is sent, since as part of this ramrod FW access
 	 * PTP registers.
 	 */
-	bnx2x_stop_ptp(bp);
+	if (bp->flags & PTP_SUPPORTED)
+		bnx2x_stop_ptp(bp);
 
 	/* Disable HW interrupts, NAPI */
 	bnx2x_netif_stop(bp, 1);
-- 
2.1.0


From 6767cb2803624e27e65a40a6cd996736faca845f Mon Sep 17 00:00:00 2001
From: Alexander Sverdlin <alexander.sverdlin@nokia.com>
Date: Mon, 29 Jun 2015 10:41:03 +0200
Subject: [PATCH 17/21] sctp: Fix race between OOTB responce and route removal

[ Upstream commit 29c4afc4e98f4dc0ea9df22c631841f9c220b944 ]

There is NULL pointer dereference possible during statistics update if the route
used for OOTB responce is removed at unfortunate time. If the route exists when
we receive OOTB packet and we finally jump into sctp_packet_transmit() to send
ABORT, but in the meantime route is removed under our feet, we take "no_route"
path and try to update stats with IP_INC_STATS(sock_net(asoc->base.sk), ...).

But sctp_ootb_pkt_new() used to prepare responce packet doesn't call
sctp_transport_set_owner() and therefore there is no asoc associated with this
packet. Probably temporary asoc just for OOTB responces is overkill, so just
introduce a check like in all other places in sctp_packet_transmit(), where
"asoc" is dereferenced.

To reproduce this, one needs to
0. ensure that sctp module is loaded (otherwise ABORT is not generated)
1. remove default route on the machine
2. while true; do
     ip route del [interface-specific route]
     ip route add [interface-specific route]
   done
3. send enough OOTB packets (i.e. HB REQs) from another host to trigger ABORT
   responce

On x86_64 the crash looks like this:

BUG: unable to handle kernel NULL pointer dereference at 0000000000000020
IP: [<ffffffffa05ec9ac>] sctp_packet_transmit+0x63c/0x730 [sctp]
PGD 0
Oops: 0000 [#1] PREEMPT SMP
Modules linked in: ...
CPU: 0 PID: 0 Comm: swapper/0 Tainted: G           O    4.0.5-1-ARCH #1
Hardware name: ...
task: ffffffff818124c0 ti: ffffffff81800000 task.ti: ffffffff81800000
RIP: 0010:[<ffffffffa05ec9ac>]  [<ffffffffa05ec9ac>] sctp_packet_transmit+0x63c/0x730 [sctp]
RSP: 0018:ffff880127c037b8  EFLAGS: 00010296
RAX: 0000000000000000 RBX: 0000000000000000 RCX: 00000015ff66b480
RDX: 00000015ff66b400 RSI: ffff880127c17200 RDI: ffff880123403700
RBP: ffff880127c03888 R08: 0000000000017200 R09: ffffffff814625af
R10: ffffea00047e4680 R11: 00000000ffffff80 R12: ffff8800b0d38a28
R13: ffff8800b0d38a28 R14: ffff8800b3e88000 R15: ffffffffa05f24e0
FS:  0000000000000000(0000) GS:ffff880127c00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
CR2: 0000000000000020 CR3: 00000000c855b000 CR4: 00000000000007f0
Stack:
 ffff880127c03910 ffff8800b0d38a28 ffffffff8189d240 ffff88011f91b400
 ffff880127c03828 ffffffffa05c94c5 0000000000000000 ffff8800baa1c520
 0000000000000000 0000000000000001 0000000000000000 0000000000000000
Call Trace:
 <IRQ>
 [<ffffffffa05c94c5>] ? sctp_sf_tabort_8_4_8.isra.20+0x85/0x140 [sctp]
 [<ffffffffa05d6b42>] ? sctp_transport_put+0x52/0x80 [sctp]
 [<ffffffffa05d0bfc>] sctp_do_sm+0xb8c/0x19a0 [sctp]
 [<ffffffff810b0e00>] ? trigger_load_balance+0x90/0x210
 [<ffffffff810e0329>] ? update_process_times+0x59/0x60
 [<ffffffff812c7a40>] ? timerqueue_add+0x60/0xb0
 [<ffffffff810e0549>] ? enqueue_hrtimer+0x29/0xa0
 [<ffffffff8101f599>] ? read_tsc+0x9/0x10
 [<ffffffff8116d4b5>] ? put_page+0x55/0x60
 [<ffffffff810ee1ad>] ? clockevents_program_event+0x6d/0x100
 [<ffffffff81462b68>] ? skb_free_head+0x58/0x80
 [<ffffffffa029a10b>] ? chksum_update+0x1b/0x27 [crc32c_generic]
 [<ffffffff81283f3e>] ? crypto_shash_update+0xce/0xf0
 [<ffffffffa05d3993>] sctp_endpoint_bh_rcv+0x113/0x280 [sctp]
 [<ffffffffa05dd4e6>] sctp_inq_push+0x46/0x60 [sctp]
 [<ffffffffa05ed7a0>] sctp_rcv+0x880/0x910 [sctp]
 [<ffffffffa05ecb50>] ? sctp_packet_transmit_chunk+0xb0/0xb0 [sctp]
 [<ffffffffa05ecb70>] ? sctp_csum_update+0x20/0x20 [sctp]
 [<ffffffff814b05a5>] ? ip_route_input_noref+0x235/0xd30
 [<ffffffff81051d6b>] ? ack_ioapic_level+0x7b/0x150
 [<ffffffff814b27be>] ip_local_deliver_finish+0xae/0x210
 [<ffffffff814b2e15>] ip_local_deliver+0x35/0x90
 [<ffffffff814b2a15>] ip_rcv_finish+0xf5/0x370
 [<ffffffff814b3128>] ip_rcv+0x2b8/0x3a0
 [<ffffffff81474193>] __netif_receive_skb_core+0x763/0xa50
 [<ffffffff81476c28>] __netif_receive_skb+0x18/0x60
 [<ffffffff81476cb0>] netif_receive_skb_internal+0x40/0xd0
 [<ffffffff814776c8>] napi_gro_receive+0xe8/0x120
 [<ffffffffa03946aa>] rtl8169_poll+0x2da/0x660 [r8169]
 [<ffffffff8147896a>] net_rx_action+0x21a/0x360
 [<ffffffff81078dc1>] __do_softirq+0xe1/0x2d0
 [<ffffffff8107912d>] irq_exit+0xad/0xb0
 [<ffffffff8157d158>] do_IRQ+0x58/0xf0
 [<ffffffff8157b06d>] common_interrupt+0x6d/0x6d
 <EOI>
 [<ffffffff810e1218>] ? hrtimer_start+0x18/0x20
 [<ffffffffa05d65f9>] ? sctp_transport_destroy_rcu+0x29/0x30 [sctp]
 [<ffffffff81020c50>] ? mwait_idle+0x60/0xa0
 [<ffffffff810216ef>] arch_cpu_idle+0xf/0x20
 [<ffffffff810b731c>] cpu_startup_entry+0x3ec/0x480
 [<ffffffff8156b365>] rest_init+0x85/0x90
 [<ffffffff818eb035>] start_kernel+0x48b/0x4ac
 [<ffffffff818ea120>] ? early_idt_handlers+0x120/0x120
 [<ffffffff818ea339>] x86_64_start_reservations+0x2a/0x2c
 [<ffffffff818ea49c>] x86_64_start_kernel+0x161/0x184
Code: 90 48 8b 80 b8 00 00 00 48 89 85 70 ff ff ff 48 83 bd 70 ff ff ff 00 0f 85 cd fa ff ff 48 89 df 31 db e8 18 63 e7 e0 48 8b 45 80 <48> 8b 40 20 48 8b 40 30 48 8b 80 68 01 00 00 65 48 ff 40 78 e9
RIP  [<ffffffffa05ec9ac>] sctp_packet_transmit+0x63c/0x730 [sctp]
 RSP <ffff880127c037b8>
CR2: 0000000000000020
---[ end trace 5aec7fd2dc983574 ]---
Kernel panic - not syncing: Fatal exception in interrupt
Kernel Offset: 0x0 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffff9fffffff)
drm_kms_helper: panic occurred, switching back to text console
---[ end Kernel panic - not syncing: Fatal exception in interrupt

Signed-off-by: Alexander Sverdlin <alexander.sverdlin@nokia.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/output.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sctp/output.c b/net/sctp/output.c
index fc5e45b..abe7c2d 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -599,7 +599,9 @@ out:
 	return err;
 no_route:
 	kfree_skb(nskb);
-	IP_INC_STATS(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES);
+
+	if (asoc)
+		IP_INC_STATS(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES);
 
 	/* FIXME: Returning the 'err' will effect all the associations
 	 * associated with a socket, although only one of the paths of the
-- 
2.1.0


From 42ac34e940440a884922d731c82035a8d1c6397f Mon Sep 17 00:00:00 2001
From: Tom Lendacky <thomas.lendacky@amd.com>
Date: Mon, 29 Jun 2015 11:22:12 -0500
Subject: [PATCH 18/21] amd-xgbe: Add the __GFP_NOWARN flag to Rx buffer
 allocation

[ Upstream commit 472cfe7127760d68b819cf35a26e5a1b44b30f4e ]

When allocating Rx related buffers, alloc_pages is called using an order
number that is decreased until successful. A system under stress can
experience failures during this allocation process resulting in a warning
being issued. This message can be of concern to end users even though the
failure is not fatal. Since the failure is not fatal and can occur
multiple times, the driver should include the __GFP_NOWARN flag to
suppress the warning message from being issued.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe-desc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
index d81fc6b..5c92fb7 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
@@ -263,7 +263,7 @@ static int xgbe_alloc_pages(struct xgbe_prv_data *pdata,
 	int ret;
 
 	/* Try to obtain pages, decreasing order if necessary */
-	gfp |= __GFP_COLD | __GFP_COMP;
+	gfp |= __GFP_COLD | __GFP_COMP | __GFP_NOWARN;
 	while (order >= 0) {
 		pages = alloc_pages(gfp, order);
 		if (pages)
-- 
2.1.0


From bb499410e6ac5ebb70e5a925618212f485fe9258 Mon Sep 17 00:00:00 2001
From: Simon Guinot <simon.guinot@sequanux.org>
Date: Tue, 30 Jun 2015 16:20:20 +0200
Subject: [PATCH 19/21] net: mvneta: introduce compatible string "marvell,
 armada-xp-neta"

[ Upstream commit f522a975a8101895a85354b9c143f41b8248e71a ]

The mvneta driver supports the Ethernet IP found in the Armada 370, XP,
380 and 385 SoCs. Since at least one more hardware feature is available
for the Armada XP SoCs then a way to identify them is needed.

This patch introduces a new compatible string "marvell,armada-xp-neta".

Signed-off-by: Simon Guinot <simon.guinot@sequanux.org>
Fixes: c5aff18204da ("net: mvneta: driver for Marvell Armada 370/XP network unit")
Cc: <stable@vger.kernel.org> # v3.8+
Acked-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
Acked-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt | 2 +-
 drivers/net/ethernet/marvell/mvneta.c                             | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt b/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt
index 750d577..f5a8ca2 100644
--- a/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt
+++ b/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt
@@ -1,7 +1,7 @@
 * Marvell Armada 370 / Armada XP Ethernet Controller (NETA)
 
 Required properties:
-- compatible: should be "marvell,armada-370-neta".
+- compatible: "marvell,armada-370-neta" or "marvell,armada-xp-neta".
 - reg: address and length of the register set for the device.
 - interrupts: interrupt for the device
 - phy: See ethernet.txt file in the same directory.
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 2db6532..387cedb 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -3095,6 +3095,7 @@ static int mvneta_remove(struct platform_device *pdev)
 
 static const struct of_device_id mvneta_match[] = {
 	{ .compatible = "marvell,armada-370-neta" },
+	{ .compatible = "marvell,armada-xp-neta" },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, mvneta_match);
-- 
2.1.0


From 9adfe45b22eb618e7ac403aa470fa3a69e1dad5a Mon Sep 17 00:00:00 2001
From: Simon Guinot <simon.guinot@sequanux.org>
Date: Tue, 30 Jun 2015 16:20:21 +0200
Subject: [PATCH 20/21] ARM: mvebu: update Ethernet compatible string for
 Armada XP

[ Upstream commit ea3b55fe83b5fcede82d183164b9d6831b26e33b ]

This patch updates the Ethernet DT nodes for Armada XP SoCs with the
compatible string "marvell,armada-xp-neta".

Signed-off-by: Simon Guinot <simon.guinot@sequanux.org>
Fixes: 77916519cba3 ("arm: mvebu: Armada XP MV78230 has only three Ethernet interfaces")
Cc: <stable@vger.kernel.org> # v3.8+
Acked-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
Reviewed-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/arm/boot/dts/armada-370-xp.dtsi     |  2 --
 arch/arm/boot/dts/armada-370.dtsi        |  8 ++++++++
 arch/arm/boot/dts/armada-xp-mv78260.dtsi |  2 +-
 arch/arm/boot/dts/armada-xp-mv78460.dtsi |  2 +-
 arch/arm/boot/dts/armada-xp.dtsi         | 10 +++++++++-
 5 files changed, 19 insertions(+), 5 deletions(-)

diff --git a/arch/arm/boot/dts/armada-370-xp.dtsi b/arch/arm/boot/dts/armada-370-xp.dtsi
index 8a322ad..a038c20 100644
--- a/arch/arm/boot/dts/armada-370-xp.dtsi
+++ b/arch/arm/boot/dts/armada-370-xp.dtsi
@@ -265,7 +265,6 @@
 			};
 
 			eth0: ethernet@70000 {
-				compatible = "marvell,armada-370-neta";
 				reg = <0x70000 0x4000>;
 				interrupts = <8>;
 				clocks = <&gateclk 4>;
@@ -281,7 +280,6 @@
 			};
 
 			eth1: ethernet@74000 {
-				compatible = "marvell,armada-370-neta";
 				reg = <0x74000 0x4000>;
 				interrupts = <10>;
 				clocks = <&gateclk 3>;
diff --git a/arch/arm/boot/dts/armada-370.dtsi b/arch/arm/boot/dts/armada-370.dtsi
index 27397f1..3773025 100644
--- a/arch/arm/boot/dts/armada-370.dtsi
+++ b/arch/arm/boot/dts/armada-370.dtsi
@@ -306,6 +306,14 @@
 					dmacap,memset;
 				};
 			};
+
+			ethernet@70000 {
+				compatible = "marvell,armada-370-neta";
+			};
+
+			ethernet@74000 {
+				compatible = "marvell,armada-370-neta";
+			};
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/armada-xp-mv78260.dtsi b/arch/arm/boot/dts/armada-xp-mv78260.dtsi
index 4a7cbed..1676d30 100644
--- a/arch/arm/boot/dts/armada-xp-mv78260.dtsi
+++ b/arch/arm/boot/dts/armada-xp-mv78260.dtsi
@@ -319,7 +319,7 @@
 			};
 
 			eth3: ethernet@34000 {
-				compatible = "marvell,armada-370-neta";
+				compatible = "marvell,armada-xp-neta";
 				reg = <0x34000 0x4000>;
 				interrupts = <14>;
 				clocks = <&gateclk 1>;
diff --git a/arch/arm/boot/dts/armada-xp-mv78460.dtsi b/arch/arm/boot/dts/armada-xp-mv78460.dtsi
index 36ce63a..d41fe88 100644
--- a/arch/arm/boot/dts/armada-xp-mv78460.dtsi
+++ b/arch/arm/boot/dts/armada-xp-mv78460.dtsi
@@ -357,7 +357,7 @@
 			};
 
 			eth3: ethernet@34000 {
-				compatible = "marvell,armada-370-neta";
+				compatible = "marvell,armada-xp-neta";
 				reg = <0x34000 0x4000>;
 				interrupts = <14>;
 				clocks = <&gateclk 1>;
diff --git a/arch/arm/boot/dts/armada-xp.dtsi b/arch/arm/boot/dts/armada-xp.dtsi
index 8291723..9ce7d5f 100644
--- a/arch/arm/boot/dts/armada-xp.dtsi
+++ b/arch/arm/boot/dts/armada-xp.dtsi
@@ -175,7 +175,7 @@
 			};
 
 			eth2: ethernet@30000 {
-				compatible = "marvell,armada-370-neta";
+				compatible = "marvell,armada-xp-neta";
 				reg = <0x30000 0x4000>;
 				interrupts = <12>;
 				clocks = <&gateclk 2>;
@@ -218,6 +218,14 @@
 				};
 			};
 
+			ethernet@70000 {
+				compatible = "marvell,armada-xp-neta";
+			};
+
+			ethernet@74000 {
+				compatible = "marvell,armada-xp-neta";
+			};
+
 			xor@f0900 {
 				compatible = "marvell,orion-xor";
 				reg = <0xF0900 0x100
-- 
2.1.0


From d9f65a9ac62784a5e2c70400c24d8f12cc1f82b9 Mon Sep 17 00:00:00 2001
From: Simon Guinot <simon.guinot@sequanux.org>
Date: Tue, 30 Jun 2015 16:20:22 +0200
Subject: [PATCH 21/21] net: mvneta: disable IP checksum with jumbo frames for
 Armada 370

[ Upstream commit b65657fc240ae6c1d2a1e62db9a0e61ac9631d7a ]

The Ethernet controller found in the Armada 370, 380 and 385 SoCs don't
support TCP/IP checksumming with frame sizes larger than 1600 bytes.

This patch fixes the issue by disabling the features NETIF_F_IP_CSUM and
NETIF_F_TSO for the Armada 370 and compatibles SoCs when the MTU is set
to a value greater than 1600 bytes.

Signed-off-by: Simon Guinot <simon.guinot@sequanux.org>
Fixes: c5aff18204da ("net: mvneta: driver for Marvell Armada 370/XP network unit")
Cc: <stable@vger.kernel.org> # v3.8+
Acked-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 26 +++++++++++++++++++++++++-
 1 file changed, 25 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 387cedb..87c7f52c 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -304,6 +304,7 @@ struct mvneta_port {
 	unsigned int link;
 	unsigned int duplex;
 	unsigned int speed;
+	unsigned int tx_csum_limit;
 };
 
 /* The mvneta_tx_desc and mvneta_rx_desc structures describe the
@@ -2441,8 +2442,10 @@ static int mvneta_change_mtu(struct net_device *dev, int mtu)
 
 	dev->mtu = mtu;
 
-	if (!netif_running(dev))
+	if (!netif_running(dev)) {
+		netdev_update_features(dev);
 		return 0;
+	}
 
 	/* The interface is running, so we have to force a
 	 * reallocation of the queues
@@ -2471,9 +2474,26 @@ static int mvneta_change_mtu(struct net_device *dev, int mtu)
 	mvneta_start_dev(pp);
 	mvneta_port_up(pp);
 
+	netdev_update_features(dev);
+
 	return 0;
 }
 
+static netdev_features_t mvneta_fix_features(struct net_device *dev,
+					     netdev_features_t features)
+{
+	struct mvneta_port *pp = netdev_priv(dev);
+
+	if (pp->tx_csum_limit && dev->mtu > pp->tx_csum_limit) {
+		features &= ~(NETIF_F_IP_CSUM | NETIF_F_TSO);
+		netdev_info(dev,
+			    "Disable IP checksum for MTU greater than %dB\n",
+			    pp->tx_csum_limit);
+	}
+
+	return features;
+}
+
 /* Get mac address */
 static void mvneta_get_mac_addr(struct mvneta_port *pp, unsigned char *addr)
 {
@@ -2785,6 +2805,7 @@ static const struct net_device_ops mvneta_netdev_ops = {
 	.ndo_set_rx_mode     = mvneta_set_rx_mode,
 	.ndo_set_mac_address = mvneta_set_mac_addr,
 	.ndo_change_mtu      = mvneta_change_mtu,
+	.ndo_fix_features    = mvneta_fix_features,
 	.ndo_get_stats64     = mvneta_get_stats64,
 	.ndo_do_ioctl        = mvneta_ioctl,
 };
@@ -3023,6 +3044,9 @@ static int mvneta_probe(struct platform_device *pdev)
 		}
 	}
 
+	if (of_device_is_compatible(dn, "marvell,armada-370-neta"))
+		pp->tx_csum_limit = 1600;
+
 	pp->tx_ring_size = MVNETA_MAX_TXD;
 	pp->rx_ring_size = MVNETA_MAX_RXD;
 
-- 
2.1.0


[-- Attachment #5: net_41.mbox --]
[-- Type: Application/Octet-Stream, Size: 64778 bytes --]

From 88a177706968e0270a0cfa47beff6ba91105d37c Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Fri, 12 Jun 2015 10:16:41 -0300
Subject: [PATCH 01/21] sctp: fix ASCONF list handling

[ Upstream commit 2d45a02d0166caf2627fe91897c6ffc3b19514c4 ]

->auto_asconf_splist is per namespace and mangled by functions like
sctp_setsockopt_auto_asconf() which doesn't guarantee any serialization.

Also, the call to inet_sk_copy_descendant() was backuping
->auto_asconf_list through the copy but was not honoring
->do_auto_asconf, which could lead to list corruption if it was
different between both sockets.

This commit thus fixes the list handling by using ->addr_wq_lock
spinlock to protect the list. A special handling is done upon socket
creation and destruction for that. Error handlig on sctp_init_sock()
will never return an error after having initialized asconf, so
sctp_destroy_sock() can be called without addrq_wq_lock. The lock now
will be take on sctp_close_sock(), before locking the socket, so we
don't do it in inverse order compared to sctp_addr_wq_timeout_handler().

Instead of taking the lock on sctp_sock_migrate() for copying and
restoring the list values, it's preferred to avoid rewritting it by
implementing sctp_copy_descendant().

Issue was found with a test application that kept flipping sysctl
default_auto_asconf on and off, but one could trigger it by issuing
simultaneous setsockopt() calls on multiple sockets or by
creating/destroying sockets fast enough. This is only triggerable
locally.

Fixes: 9f7d653b67ae ("sctp: Add Auto-ASCONF support (core).")
Reported-by: Ji Jianwen <jiji@redhat.com>
Suggested-by: Neil Horman <nhorman@tuxdriver.com>
Suggested-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netns/sctp.h   |  1 +
 include/net/sctp/structs.h |  4 ++++
 net/sctp/socket.c          | 43 ++++++++++++++++++++++++++++++++-----------
 3 files changed, 37 insertions(+), 11 deletions(-)

diff --git a/include/net/netns/sctp.h b/include/net/netns/sctp.h
index 3573a81..8ba379f 100644
--- a/include/net/netns/sctp.h
+++ b/include/net/netns/sctp.h
@@ -31,6 +31,7 @@ struct netns_sctp {
 	struct list_head addr_waitq;
 	struct timer_list addr_wq_timer;
 	struct list_head auto_asconf_splist;
+	/* Lock that protects both addr_waitq and auto_asconf_splist */
 	spinlock_t addr_wq_lock;
 
 	/* Lock that protects the local_addr_list writers */
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 2bb2fcf..495c87e 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -223,6 +223,10 @@ struct sctp_sock {
 	atomic_t pd_mode;
 	/* Receive to here while partial delivery is in effect. */
 	struct sk_buff_head pd_lobby;
+
+	/* These must be the last fields, as they will skipped on copies,
+	 * like on accept and peeloff operations
+	 */
 	struct list_head auto_asconf_list;
 	int do_auto_asconf;
 };
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index f09de7f..5f6c4e6 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1528,8 +1528,10 @@ static void sctp_close(struct sock *sk, long timeout)
 
 	/* Supposedly, no process has access to the socket, but
 	 * the net layers still may.
+	 * Also, sctp_destroy_sock() needs to be called with addr_wq_lock
+	 * held and that should be grabbed before socket lock.
 	 */
-	local_bh_disable();
+	spin_lock_bh(&net->sctp.addr_wq_lock);
 	bh_lock_sock(sk);
 
 	/* Hold the sock, since sk_common_release() will put sock_put()
@@ -1539,7 +1541,7 @@ static void sctp_close(struct sock *sk, long timeout)
 	sk_common_release(sk);
 
 	bh_unlock_sock(sk);
-	local_bh_enable();
+	spin_unlock_bh(&net->sctp.addr_wq_lock);
 
 	sock_put(sk);
 
@@ -3580,6 +3582,7 @@ static int sctp_setsockopt_auto_asconf(struct sock *sk, char __user *optval,
 	if ((val && sp->do_auto_asconf) || (!val && !sp->do_auto_asconf))
 		return 0;
 
+	spin_lock_bh(&sock_net(sk)->sctp.addr_wq_lock);
 	if (val == 0 && sp->do_auto_asconf) {
 		list_del(&sp->auto_asconf_list);
 		sp->do_auto_asconf = 0;
@@ -3588,6 +3591,7 @@ static int sctp_setsockopt_auto_asconf(struct sock *sk, char __user *optval,
 		    &sock_net(sk)->sctp.auto_asconf_splist);
 		sp->do_auto_asconf = 1;
 	}
+	spin_unlock_bh(&sock_net(sk)->sctp.addr_wq_lock);
 	return 0;
 }
 
@@ -4121,18 +4125,28 @@ static int sctp_init_sock(struct sock *sk)
 	local_bh_disable();
 	percpu_counter_inc(&sctp_sockets_allocated);
 	sock_prot_inuse_add(net, sk->sk_prot, 1);
+
+	/* Nothing can fail after this block, otherwise
+	 * sctp_destroy_sock() will be called without addr_wq_lock held
+	 */
 	if (net->sctp.default_auto_asconf) {
+		spin_lock(&sock_net(sk)->sctp.addr_wq_lock);
 		list_add_tail(&sp->auto_asconf_list,
 		    &net->sctp.auto_asconf_splist);
 		sp->do_auto_asconf = 1;
-	} else
+		spin_unlock(&sock_net(sk)->sctp.addr_wq_lock);
+	} else {
 		sp->do_auto_asconf = 0;
+	}
+
 	local_bh_enable();
 
 	return 0;
 }
 
-/* Cleanup any SCTP per socket resources.  */
+/* Cleanup any SCTP per socket resources. Must be called with
+ * sock_net(sk)->sctp.addr_wq_lock held if sp->do_auto_asconf is true
+ */
 static void sctp_destroy_sock(struct sock *sk)
 {
 	struct sctp_sock *sp;
@@ -7195,6 +7209,19 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk,
 	newinet->mc_list = NULL;
 }
 
+static inline void sctp_copy_descendant(struct sock *sk_to,
+					const struct sock *sk_from)
+{
+	int ancestor_size = sizeof(struct inet_sock) +
+			    sizeof(struct sctp_sock) -
+			    offsetof(struct sctp_sock, auto_asconf_list);
+
+	if (sk_from->sk_family == PF_INET6)
+		ancestor_size += sizeof(struct ipv6_pinfo);
+
+	__inet_sk_copy_descendant(sk_to, sk_from, ancestor_size);
+}
+
 /* Populate the fields of the newsk from the oldsk and migrate the assoc
  * and its messages to the newsk.
  */
@@ -7209,7 +7236,6 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
 	struct sk_buff *skb, *tmp;
 	struct sctp_ulpevent *event;
 	struct sctp_bind_hashbucket *head;
-	struct list_head tmplist;
 
 	/* Migrate socket buffer sizes and all the socket level options to the
 	 * new socket.
@@ -7217,12 +7243,7 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
 	newsk->sk_sndbuf = oldsk->sk_sndbuf;
 	newsk->sk_rcvbuf = oldsk->sk_rcvbuf;
 	/* Brute force copy old sctp opt. */
-	if (oldsp->do_auto_asconf) {
-		memcpy(&tmplist, &newsp->auto_asconf_list, sizeof(tmplist));
-		inet_sk_copy_descendant(newsk, oldsk);
-		memcpy(&newsp->auto_asconf_list, &tmplist, sizeof(tmplist));
-	} else
-		inet_sk_copy_descendant(newsk, oldsk);
+	sctp_copy_descendant(newsk, oldsk);
 
 	/* Restore the ep value that was overwritten with the above structure
 	 * copy.
-- 
2.1.0


From 1213924626ae9df5231a08d2b1e4d0887c504c68 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <razor@blackwall.org>
Date: Mon, 15 Jun 2015 20:28:51 +0300
Subject: [PATCH 02/21] bridge: fix br_stp_set_bridge_priority race conditions

[ Upstream commit 2dab80a8b486f02222a69daca6859519e05781d9 ]

After the ->set() spinlocks were removed br_stp_set_bridge_priority
was left running without any protection when used via sysfs. It can
race with port add/del and could result in use-after-free cases and
corrupted lists. Tested by running port add/del in a loop with stp
enabled while setting priority in a loop, crashes are easily
reproducible.
The spinlocks around sysfs ->set() were removed in commit:
14f98f258f19 ("bridge: range check STP parameters")
There's also a race condition in the netlink priority support that is
fixed by this change, but it was introduced recently and the fixes tag
covers it, just in case it's needed the commit is:
af615762e972 ("bridge: add ageing_time, stp_state, priority over netlink")

Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Fixes: 14f98f258f19 ("bridge: range check STP parameters")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_ioctl.c  | 2 --
 net/bridge/br_stp_if.c | 4 +++-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c
index a9a4a1b..8d423bc 100644
--- a/net/bridge/br_ioctl.c
+++ b/net/bridge/br_ioctl.c
@@ -247,9 +247,7 @@ static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 		if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN))
 			return -EPERM;
 
-		spin_lock_bh(&br->lock);
 		br_stp_set_bridge_priority(br, args[1]);
-		spin_unlock_bh(&br->lock);
 		return 0;
 
 	case BRCTL_SET_PORT_PRIORITY:
diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
index 4114687..7832d07 100644
--- a/net/bridge/br_stp_if.c
+++ b/net/bridge/br_stp_if.c
@@ -243,12 +243,13 @@ bool br_stp_recalculate_bridge_id(struct net_bridge *br)
 	return true;
 }
 
-/* called under bridge lock */
+/* Acquires and releases bridge lock */
 void br_stp_set_bridge_priority(struct net_bridge *br, u16 newprio)
 {
 	struct net_bridge_port *p;
 	int wasroot;
 
+	spin_lock_bh(&br->lock);
 	wasroot = br_is_root_bridge(br);
 
 	list_for_each_entry(p, &br->port_list, list) {
@@ -266,6 +267,7 @@ void br_stp_set_bridge_priority(struct net_bridge *br, u16 newprio)
 	br_port_state_selection(br);
 	if (br_is_root_bridge(br) && !wasroot)
 		br_become_root_bridge(br);
+	spin_unlock_bh(&br->lock);
 }
 
 /* called under bridge lock */
-- 
2.1.0


From fe7b5387d56d0599544316cd38c61bad46e3fae0 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 16 Jun 2015 07:59:11 -0700
Subject: [PATCH 03/21] packet: read num_members once in packet_rcv_fanout()

[ Upstream commit f98f4514d07871da7a113dd9e3e330743fd70ae4 ]

We need to tell compiler it must not read f->num_members multiple
times. Otherwise testing if num is not zero is flaky, and we could
attempt an invalid divide by 0 in fanout_demux_cpu()

Note bug was present in packet_rcv_fanout_hash() and
packet_rcv_fanout_lb() but final 3.1 had a simple location
after commit 95ec3eb417115fb ("packet: Add 'cpu' fanout policy.")

Fixes: dc99f600698dc ("packet: Add fanout support.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index b5989c6..131545a 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1353,7 +1353,7 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
 			     struct packet_type *pt, struct net_device *orig_dev)
 {
 	struct packet_fanout *f = pt->af_packet_priv;
-	unsigned int num = f->num_members;
+	unsigned int num = READ_ONCE(f->num_members);
 	struct packet_sock *po;
 	unsigned int idx;
 
-- 
2.1.0


From e67d56e09c3565366d2232f6d90bd9152277043f Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 17 Jun 2015 15:59:34 -0400
Subject: [PATCH 04/21] packet: avoid out of bounds read in round robin fanout

[ Upstream commit 468479e6043c84f5a65299cc07cb08a22a28c2b1 ]

PACKET_FANOUT_LB computes f->rr_cur such that it is modulo
f->num_members. It returns the old value unconditionally, but
f->num_members may have changed since the last store. Ensure
that the return value is always < num.

When modifying the logic, simplify it further by replacing the loop
with an unconditional atomic increment.

Fixes: dc99f600698d ("packet: Add fanout support.")
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 18 ++----------------
 1 file changed, 2 insertions(+), 16 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 131545a..fe1610d 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1272,16 +1272,6 @@ static void packet_sock_destruct(struct sock *sk)
 	sk_refcnt_debug_dec(sk);
 }
 
-static int fanout_rr_next(struct packet_fanout *f, unsigned int num)
-{
-	int x = atomic_read(&f->rr_cur) + 1;
-
-	if (x >= num)
-		x = 0;
-
-	return x;
-}
-
 static unsigned int fanout_demux_hash(struct packet_fanout *f,
 				      struct sk_buff *skb,
 				      unsigned int num)
@@ -1293,13 +1283,9 @@ static unsigned int fanout_demux_lb(struct packet_fanout *f,
 				    struct sk_buff *skb,
 				    unsigned int num)
 {
-	int cur, old;
+	unsigned int val = atomic_inc_return(&f->rr_cur);
 
-	cur = atomic_read(&f->rr_cur);
-	while ((old = atomic_cmpxchg(&f->rr_cur, cur,
-				     fanout_rr_next(f, num))) != cur)
-		cur = old;
-	return cur;
+	return val % num;
 }
 
 static unsigned int fanout_demux_cpu(struct packet_fanout *f,
-- 
2.1.0


From 93f6561c13c1da2dab4bbc5a41a1304ee739455f Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Tue, 16 Jun 2015 22:56:39 +0300
Subject: [PATCH 05/21] neigh: do not modify unlinked entries

[ Upstream commit 2c51a97f76d20ebf1f50fef908b986cb051fdff9 ]

The lockless lookups can return entry that is unlinked.
Sometimes they get reference before last neigh_cleanup_and_release,
sometimes they do not need reference. Later, any
modification attempts may result in the following problems:

1. entry is not destroyed immediately because neigh_update
can start the timer for dead entry, eg. on change to NUD_REACHABLE
state. As result, entry lives for some time but is invisible
and out of control.

2. __neigh_event_send can run in parallel with neigh_destroy
while refcnt=0 but if timer is started and expired refcnt can
reach 0 for second time leading to second neigh_destroy and
possible crash.

Thanks to Eric Dumazet and Ying Xue for their work and analyze
on the __neigh_event_send change.

Fixes: 767e97e1e0db ("neigh: RCU conversion of struct neighbour")
Fixes: a263b3093641 ("ipv4: Make neigh lookups directly in output packet path.")
Fixes: 6fd6ce2056de ("ipv6: Do not depend on rt->n in ip6_finish_output2().")
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 3de6542..2237c1b 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -957,6 +957,8 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
 	rc = 0;
 	if (neigh->nud_state & (NUD_CONNECTED | NUD_DELAY | NUD_PROBE))
 		goto out_unlock_bh;
+	if (neigh->dead)
+		goto out_dead;
 
 	if (!(neigh->nud_state & (NUD_STALE | NUD_INCOMPLETE))) {
 		if (NEIGH_VAR(neigh->parms, MCAST_PROBES) +
@@ -1013,6 +1015,13 @@ out_unlock_bh:
 		write_unlock(&neigh->lock);
 	local_bh_enable();
 	return rc;
+
+out_dead:
+	if (neigh->nud_state & NUD_STALE)
+		goto out_unlock_bh;
+	write_unlock_bh(&neigh->lock);
+	kfree_skb(skb);
+	return 1;
 }
 EXPORT_SYMBOL(__neigh_event_send);
 
@@ -1076,6 +1085,8 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
 	if (!(flags & NEIGH_UPDATE_F_ADMIN) &&
 	    (old & (NUD_NOARP | NUD_PERMANENT)))
 		goto out;
+	if (neigh->dead)
+		goto out;
 
 	if (!(new & NUD_VALID)) {
 		neigh_del_timer(neigh);
@@ -1225,6 +1236,8 @@ EXPORT_SYMBOL(neigh_update);
  */
 void __neigh_set_probe_once(struct neighbour *neigh)
 {
+	if (neigh->dead)
+		return;
 	neigh->updated = jiffies;
 	if (!(neigh->nud_state & NUD_FAILED))
 		return;
-- 
2.1.0


From 0f2a5969f4c7f6da272592b2a400d1b55b2c70fa Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 17 Jun 2015 13:54:54 +0200
Subject: [PATCH 06/21] mac80211: fix locking in
 update_vlan_tailroom_need_count()

[ Upstream commit 51f458d9612177f69c2e2c437034ae15f93078e7 ]

Unfortunately, Michal's change to fix AP_VLAN crypto tailroom
caused a locking issue that was reported by lockdep, but only
in a few cases - the issue was a classic ABBA deadlock caused
by taking the mtx after the key_mtx, where normally they're
taken the other way around.

As the key mutex protects the field in question (I'm adding a
few annotations to make that clear) only the iteration needs
to be protected, but we can also iterate the interface list
with just RCU protection while holding the key mutex.

Fixes: f9dca80b98ca ("mac80211: fix AP_VLAN crypto tailroom calculation")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mac80211/key.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index a907f2d..81e9785 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -66,12 +66,15 @@ update_vlan_tailroom_need_count(struct ieee80211_sub_if_data *sdata, int delta)
 	if (sdata->vif.type != NL80211_IFTYPE_AP)
 		return;
 
-	mutex_lock(&sdata->local->mtx);
+	/* crypto_tx_tailroom_needed_cnt is protected by this */
+	assert_key_lock(sdata->local);
+
+	rcu_read_lock();
 
-	list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list)
+	list_for_each_entry_rcu(vlan, &sdata->u.ap.vlans, u.vlan.list)
 		vlan->crypto_tx_tailroom_needed_cnt += delta;
 
-	mutex_unlock(&sdata->local->mtx);
+	rcu_read_unlock();
 }
 
 static void increment_tailroom_need_count(struct ieee80211_sub_if_data *sdata)
@@ -95,6 +98,8 @@ static void increment_tailroom_need_count(struct ieee80211_sub_if_data *sdata)
 	 * http://mid.gmane.org/1308590980.4322.19.camel@jlt3.sipsolutions.net
 	 */
 
+	assert_key_lock(sdata->local);
+
 	update_vlan_tailroom_need_count(sdata, 1);
 
 	if (!sdata->crypto_tx_tailroom_needed_cnt++) {
@@ -109,6 +114,8 @@ static void increment_tailroom_need_count(struct ieee80211_sub_if_data *sdata)
 static void decrease_tailroom_need_count(struct ieee80211_sub_if_data *sdata,
 					 int delta)
 {
+	assert_key_lock(sdata->local);
+
 	WARN_ON_ONCE(sdata->crypto_tx_tailroom_needed_cnt < delta);
 
 	update_vlan_tailroom_need_count(sdata, -delta);
-- 
2.1.0


From 4f03921ef978ca4b09403c52508d7d0a8ff6f1ec Mon Sep 17 00:00:00 2001
From: Stas Sergeev <stsp@list.ru>
Date: Thu, 18 Jun 2015 18:36:03 +0300
Subject: [PATCH 07/21] mvneta: add forgotten initialization of autonegotiation
 bits

[ Upstream commit 538761b794c1542f1c6e31eadd9d7aae118889f7 ]

The commit 898b2970e2c9 ("mvneta: implement SGMII-based in-band link state
signaling")
changed mvneta_adjust_link() so that it does not clear the auto-negotiation
bits in MVNETA_GMAC_AUTONEG_CONFIG register. This was necessary for
auto-negotiation mode to work.
Unfortunately I haven't checked if these bits are ever initialized.
It appears they are not.
This patch adds the missing initialization of the auto-negotiation bits
in the MVNETA_GMAC_AUTONEG_CONFIG register.
It fixes the following regression:
https://www.mail-archive.com/netdev@vger.kernel.org/msg67928.html

Since the patch was tested to fix a regression, it should be applied to
stable tree.

Tested-by: Arnaud Ebalard <arno@natisbad.org>

CC: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
CC: Florian Fainelli <f.fainelli@gmail.com>
CC: netdev@vger.kernel.org
CC: linux-kernel@vger.kernel.org
CC: stable@vger.kernel.org

Signed-off-by: Stas Sergeev <stsp@users.sourceforge.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index ce5f7f9..74176ec 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -1013,6 +1013,12 @@ static void mvneta_defaults_set(struct mvneta_port *pp)
 		val = mvreg_read(pp, MVNETA_GMAC_CLOCK_DIVIDER);
 		val |= MVNETA_GMAC_1MS_CLOCK_ENABLE;
 		mvreg_write(pp, MVNETA_GMAC_CLOCK_DIVIDER, val);
+	} else {
+		val = mvreg_read(pp, MVNETA_GMAC_AUTONEG_CONFIG);
+		val &= ~(MVNETA_GMAC_INBAND_AN_ENABLE |
+		       MVNETA_GMAC_AN_SPEED_EN |
+		       MVNETA_GMAC_AN_DUPLEX_EN);
+		mvreg_write(pp, MVNETA_GMAC_AUTONEG_CONFIG, val);
 	}
 
 	mvneta_set_ucast_table(pp, -1);
-- 
2.1.0


From eac15f346e1fcffb8baff2ff8fb59fd1f6e91c12 Mon Sep 17 00:00:00 2001
From: Christoph Paasch <cpaasch@apple.com>
Date: Thu, 18 Jun 2015 09:15:34 -0700
Subject: [PATCH 08/21] tcp: Do not call tcp_fastopen_reset_cipher from
 interrupt context

[ Upstream commit dfea2aa654243f70dc53b8648d0bbdeec55a7df1 ]

tcp_fastopen_reset_cipher really cannot be called from interrupt
context. It allocates the tcp_fastopen_context with GFP_KERNEL and
calls crypto_alloc_cipher, which allocates all kind of stuff with
GFP_KERNEL.

Thus, we might sleep when the key-generation is triggered by an
incoming TFO cookie-request which would then happen in interrupt-
context, as shown by enabling CONFIG_DEBUG_ATOMIC_SLEEP:

[   36.001813] BUG: sleeping function called from invalid context at mm/slub.c:1266
[   36.003624] in_atomic(): 1, irqs_disabled(): 0, pid: 1016, name: packetdrill
[   36.004859] CPU: 1 PID: 1016 Comm: packetdrill Not tainted 4.1.0-rc7 #14
[   36.006085] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.7.5-0-ge51488c-20140602_164612-nilsson.home.kraxel.org 04/01/2014
[   36.008250]  00000000000004f2 ffff88007f8838a8 ffffffff8171d53a ffff880075a084a8
[   36.009630]  ffff880075a08000 ffff88007f8838c8 ffffffff810967d3 ffff88007f883928
[   36.011076]  0000000000000000 ffff88007f8838f8 ffffffff81096892 ffff88007f89be00
[   36.012494] Call Trace:
[   36.012953]  <IRQ>  [<ffffffff8171d53a>] dump_stack+0x4f/0x6d
[   36.014085]  [<ffffffff810967d3>] ___might_sleep+0x103/0x170
[   36.015117]  [<ffffffff81096892>] __might_sleep+0x52/0x90
[   36.016117]  [<ffffffff8118e887>] kmem_cache_alloc_trace+0x47/0x190
[   36.017266]  [<ffffffff81680d82>] ? tcp_fastopen_reset_cipher+0x42/0x130
[   36.018485]  [<ffffffff81680d82>] tcp_fastopen_reset_cipher+0x42/0x130
[   36.019679]  [<ffffffff81680f01>] tcp_fastopen_init_key_once+0x61/0x70
[   36.020884]  [<ffffffff81680f2c>] __tcp_fastopen_cookie_gen+0x1c/0x60
[   36.022058]  [<ffffffff816814ff>] tcp_try_fastopen+0x58f/0x730
[   36.023118]  [<ffffffff81671788>] tcp_conn_request+0x3e8/0x7b0
[   36.024185]  [<ffffffff810e3872>] ? __module_text_address+0x12/0x60
[   36.025327]  [<ffffffff8167b2e1>] tcp_v4_conn_request+0x51/0x60
[   36.026410]  [<ffffffff816727e0>] tcp_rcv_state_process+0x190/0xda0
[   36.027556]  [<ffffffff81661f97>] ? __inet_lookup_established+0x47/0x170
[   36.028784]  [<ffffffff8167c2ad>] tcp_v4_do_rcv+0x16d/0x3d0
[   36.029832]  [<ffffffff812e6806>] ? security_sock_rcv_skb+0x16/0x20
[   36.030936]  [<ffffffff8167cc8a>] tcp_v4_rcv+0x77a/0x7b0
[   36.031875]  [<ffffffff816af8c3>] ? iptable_filter_hook+0x33/0x70
[   36.032953]  [<ffffffff81657d22>] ip_local_deliver_finish+0x92/0x1f0
[   36.034065]  [<ffffffff81657f1a>] ip_local_deliver+0x9a/0xb0
[   36.035069]  [<ffffffff81657c90>] ? ip_rcv+0x3d0/0x3d0
[   36.035963]  [<ffffffff81657569>] ip_rcv_finish+0x119/0x330
[   36.036950]  [<ffffffff81657ba7>] ip_rcv+0x2e7/0x3d0
[   36.037847]  [<ffffffff81610652>] __netif_receive_skb_core+0x552/0x930
[   36.038994]  [<ffffffff81610a57>] __netif_receive_skb+0x27/0x70
[   36.040033]  [<ffffffff81610b72>] process_backlog+0xd2/0x1f0
[   36.041025]  [<ffffffff81611482>] net_rx_action+0x122/0x310
[   36.042007]  [<ffffffff81076743>] __do_softirq+0x103/0x2f0
[   36.042978]  [<ffffffff81723e3c>] do_softirq_own_stack+0x1c/0x30

This patch moves the call to tcp_fastopen_init_key_once to the places
where a listener socket creates its TFO-state, which always happens in
user-context (either from the setsockopt, or implicitly during the
listen()-call)

Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Fixes: 222e83d2e0ae ("tcp: switch tcp_fastopen key generation to net_get_random_once")
Signed-off-by: Christoph Paasch <cpaasch@apple.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/af_inet.c      | 2 ++
 net/ipv4/tcp.c          | 7 +++++--
 net/ipv4/tcp_fastopen.c | 2 --
 3 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 8b47a4d..a5aa54e 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -228,6 +228,8 @@ int inet_listen(struct socket *sock, int backlog)
 				err = 0;
 			if (err)
 				goto out;
+
+			tcp_fastopen_init_key_once(true);
 		}
 		err = inet_csk_listen_start(sk, backlog);
 		if (err)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f1377f2..bb2ce74 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2545,10 +2545,13 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 
 	case TCP_FASTOPEN:
 		if (val >= 0 && ((1 << sk->sk_state) & (TCPF_CLOSE |
-		    TCPF_LISTEN)))
+		    TCPF_LISTEN))) {
+			tcp_fastopen_init_key_once(true);
+
 			err = fastopen_init_queue(sk, val);
-		else
+		} else {
 			err = -EINVAL;
+		}
 		break;
 	case TCP_TIMESTAMP:
 		if (!tp->repair)
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 46b087a..f9c0fb8 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -78,8 +78,6 @@ static bool __tcp_fastopen_cookie_gen(const void *path,
 	struct tcp_fastopen_context *ctx;
 	bool ok = false;
 
-	tcp_fastopen_init_key_once(true);
-
 	rcu_read_lock();
 	ctx = rcu_dereference(tcp_fastopen_ctx);
 	if (ctx) {
-- 
2.1.0


From 593c8a4bd06b59ed964aa61ea8f2a8781683bc49 Mon Sep 17 00:00:00 2001
From: "Palik, Imre" <imrep@amazon.de>
Date: Fri, 19 Jun 2015 14:21:51 +0200
Subject: [PATCH 09/21] xen-netback: fix a BUG() during initialization

[ Upstream commit 12b322ac85208de564ecf23aa754d796a91de21f ]

Commit edafc132baac ("xen-netback: making the bandwidth limiter runtime settable")
introduced the capability to change the bandwidth rate limit at runtime.
But it also introduced a possible crashing bug.

If netback receives two XenbusStateConnected without getting the
hotplug-status watch firing in between, then it will try to register the
watches for the rate limiter again.  But this triggers a BUG() in the watch
registration code.

The fix modifies connect() to remove the possibly existing packet-rate
watches before trying to install those watches.  This behaviour is in line
with how connect() deals with the hotplug-status watch.

Signed-off-by: Imre Palik <imrep@amazon.de>
Cc: Matt Wilson <msw@amazon.com>
Acked-by: Wei Liu <wei.liu2@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netback/xenbus.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index 968787a..ec383b0 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -681,6 +681,9 @@ static int xen_register_watchers(struct xenbus_device *dev, struct xenvif *vif)
 	char *node;
 	unsigned maxlen = strlen(dev->nodename) + sizeof("/rate");
 
+	if (vif->credit_watch.node)
+		return -EADDRINUSE;
+
 	node = kmalloc(maxlen, GFP_KERNEL);
 	if (!node)
 		return -ENOMEM;
@@ -770,6 +773,7 @@ static void connect(struct backend_info *be)
 	}
 
 	xen_net_read_rate(dev, &credit_bytes, &credit_usec);
+	xen_unregister_watchers(be->vif);
 	xen_register_watchers(dev, be->vif);
 	read_xenbus_vif_flags(be);
 
-- 
2.1.0


From 0e1299b6fe880118bf01f84ad785541b338f067b Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Tue, 23 Jun 2015 08:34:39 +0300
Subject: [PATCH 10/21] ip: report the original address of ICMP messages

[ Upstream commit 34b99df4e6256ddafb663c6de0711dceceddfe0e ]

ICMP messages can trigger ICMP and local errors. In this case
serr->port is 0 and starting from Linux 4.0 we do not return
the original target address to the error queue readers.
Add function to define which errors provide addr_offset.
With this fix my ping command is not silent anymore.

Fixes: c247f0534cc5 ("ip: fix error queue empty skb handling")
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_sockglue.c | 11 ++++++++++-
 net/ipv6/datagram.c    | 12 +++++++++++-
 2 files changed, 21 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 7cfb089..6ddde89 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -432,6 +432,15 @@ void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 inf
 		kfree_skb(skb);
 }
 
+/* For some errors we have valid addr_offset even with zero payload and
+ * zero port. Also, addr_offset should be supported if port is set.
+ */
+static inline bool ipv4_datagram_support_addr(struct sock_exterr_skb *serr)
+{
+	return serr->ee.ee_origin == SO_EE_ORIGIN_ICMP ||
+	       serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL || serr->port;
+}
+
 /* IPv4 supports cmsg on all imcp errors and some timestamps
  *
  * Timestamp code paths do not initialize the fields expected by cmsg:
@@ -498,7 +507,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 
 	serr = SKB_EXT_ERR(skb);
 
-	if (sin && serr->port) {
+	if (sin && ipv4_datagram_support_addr(serr)) {
 		sin->sin_family = AF_INET;
 		sin->sin_addr.s_addr = *(__be32 *)(skb_network_header(skb) +
 						   serr->addr_offset);
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 762a58c..62d908e 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -325,6 +325,16 @@ void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu)
 	kfree_skb(skb);
 }
 
+/* For some errors we have valid addr_offset even with zero payload and
+ * zero port. Also, addr_offset should be supported if port is set.
+ */
+static inline bool ipv6_datagram_support_addr(struct sock_exterr_skb *serr)
+{
+	return serr->ee.ee_origin == SO_EE_ORIGIN_ICMP6 ||
+	       serr->ee.ee_origin == SO_EE_ORIGIN_ICMP ||
+	       serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL || serr->port;
+}
+
 /* IPv6 supports cmsg on all origins aside from SO_EE_ORIGIN_LOCAL.
  *
  * At one point, excluding local errors was a quick test to identify icmp/icmp6
@@ -389,7 +399,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 
 	serr = SKB_EXT_ERR(skb);
 
-	if (sin && serr->port) {
+	if (sin && ipv6_datagram_support_addr(serr)) {
 		const unsigned char *nh = skb_network_header(skb);
 		sin->sin6_family = AF_INET6;
 		sin->sin6_flowinfo = 0;
-- 
2.1.0


From 9cfd9897505bddf59db0f480ebcb2e956012f196 Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Thu, 25 Jun 2015 11:29:41 +0300
Subject: [PATCH 11/21] net/mlx4_en: Release TX QP when destroying TX ring

[ Upstream commit 0eb08514fdbdcd16fd6870680cd638f203662e9d ]

TX ring QP wasn't released at mlx4_en_destroy_tx_ring. Instead, the code
used the deprecated base_tx_qpn field. Move TX QP release to
mlx4_en_destroy_tx_ring and remove the base_tx_qpn field.

Fixes: ddae0349fdb7 ('net/mlx4: Change QP allocation scheme')
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 4 ----
 drivers/net/ethernet/mellanox/mlx4/en_tx.c     | 1 +
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h   | 1 -
 3 files changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index cf467a9..a5a0b84 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1973,10 +1973,6 @@ void mlx4_en_free_resources(struct mlx4_en_priv *priv)
 			mlx4_en_destroy_cq(priv, &priv->rx_cq[i]);
 	}
 
-	if (priv->base_tx_qpn) {
-		mlx4_qp_release_range(priv->mdev->dev, priv->base_tx_qpn, priv->tx_ring_num);
-		priv->base_tx_qpn = 0;
-	}
 }
 
 int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 7bed3a8..0ab298f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -180,6 +180,7 @@ void mlx4_en_destroy_tx_ring(struct mlx4_en_priv *priv,
 		mlx4_bf_free(mdev->dev, &ring->bf);
 	mlx4_qp_remove(mdev->dev, &ring->qp);
 	mlx4_qp_free(mdev->dev, &ring->qp);
+	mlx4_qp_release_range(priv->mdev->dev, ring->qpn, 1);
 	mlx4_en_unmap_buffer(&ring->wqres.buf);
 	mlx4_free_hwq_res(mdev->dev, &ring->wqres, ring->buf_size);
 	kfree(ring->bounce_buf);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index d021f07..9a4b380 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -579,7 +579,6 @@ struct mlx4_en_priv {
 	int vids[128];
 	bool wol;
 	struct device *ddev;
-	int base_tx_qpn;
 	struct hlist_head mac_hash[MLX4_EN_MAC_HASH_SIZE];
 	struct hwtstamp_config hwtstamp_config;
 
-- 
2.1.0


From 32334e974fb2c819ad4d0c7bbd4e2e3551002f99 Mon Sep 17 00:00:00 2001
From: Ido Shamay <idos@mellanox.com>
Date: Thu, 25 Jun 2015 11:29:42 +0300
Subject: [PATCH 12/21] net/mlx4_en: Wake TX queues only when there's enough
 room

[ Upstream commit 488a9b48e398b157703766e2cd91ea45ac6997c5 ]

Indication of a single completed packet, marked by txbbs_skipped
being bigger then zero, in not enough in order to wake up a
stopped TX queue. The completed packet may contain a single TXBB,
while next packet to be sent (after the wake up) may have multiple
TXBBs (LSO/TSO packets for example), causing overflow in queue followed
by WQE corruption and TX queue timeout.
Instead, wake the stopped queue only when there's enough room for the
worst case (maximum sized WQE) packet that we should need to handle after
the queue is opened again.

Also created an helper routine - mlx4_en_is_tx_ring_full, which checks
if the current TX ring is full or not. It provides better code readability
and removes code duplication.

Signed-off-by: Ido Shamay <idos@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_tx.c   | 19 +++++++++++--------
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h |  1 +
 2 files changed, 12 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 0ab298f..c10d98f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -66,6 +66,7 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 	ring->size = size;
 	ring->size_mask = size - 1;
 	ring->stride = stride;
+	ring->full_size = ring->size - HEADROOM - MAX_DESC_TXBBS;
 
 	tmp = size * sizeof(struct mlx4_en_tx_info);
 	ring->tx_info = kmalloc_node(tmp, GFP_KERNEL | __GFP_NOWARN, node);
@@ -232,6 +233,11 @@ void mlx4_en_deactivate_tx_ring(struct mlx4_en_priv *priv,
 		       MLX4_QP_STATE_RST, NULL, 0, 0, &ring->qp);
 }
 
+static inline bool mlx4_en_is_tx_ring_full(struct mlx4_en_tx_ring *ring)
+{
+	return ring->prod - ring->cons > ring->full_size;
+}
+
 static void mlx4_en_stamp_wqe(struct mlx4_en_priv *priv,
 			      struct mlx4_en_tx_ring *ring, int index,
 			      u8 owner)
@@ -474,11 +480,10 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev,
 
 	netdev_tx_completed_queue(ring->tx_queue, packets, bytes);
 
-	/*
-	 * Wakeup Tx queue if this stopped, and at least 1 packet
-	 * was completed
+	/* Wakeup Tx queue if this stopped, and ring is not full.
 	 */
-	if (netif_tx_queue_stopped(ring->tx_queue) && txbbs_skipped > 0) {
+	if (netif_tx_queue_stopped(ring->tx_queue) &&
+	    !mlx4_en_is_tx_ring_full(ring)) {
 		netif_tx_wake_queue(ring->tx_queue);
 		ring->wake_queue++;
 	}
@@ -922,8 +927,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	skb_tx_timestamp(skb);
 
 	/* Check available TXBBs And 2K spare for prefetch */
-	stop_queue = (int)(ring->prod - ring_cons) >
-		      ring->size - HEADROOM - MAX_DESC_TXBBS;
+	stop_queue = mlx4_en_is_tx_ring_full(ring);
 	if (unlikely(stop_queue)) {
 		netif_tx_stop_queue(ring->tx_queue);
 		ring->queue_stopped++;
@@ -992,8 +996,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 		smp_rmb();
 
 		ring_cons = ACCESS_ONCE(ring->cons);
-		if (unlikely(((int)(ring->prod - ring_cons)) <=
-			     ring->size - HEADROOM - MAX_DESC_TXBBS)) {
+		if (unlikely(!mlx4_en_is_tx_ring_full(ring))) {
 			netif_tx_wake_queue(ring->tx_queue);
 			ring->wake_queue++;
 		}
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 9a4b380..909fcf8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -279,6 +279,7 @@ struct mlx4_en_tx_ring {
 	u32			size; /* number of TXBBs */
 	u32			size_mask;
 	u16			stride;
+	u32			full_size;
 	u16			cqn;	/* index of port CQ associated with this ring */
 	u32			buf_size;
 	__be32			doorbell_qpn;
-- 
2.1.0


From 4d84400c01fa1ab6be6f974fb5eeae5280c9861f Mon Sep 17 00:00:00 2001
From: Ido Shamay <idos@mellanox.com>
Date: Thu, 25 Jun 2015 11:29:43 +0300
Subject: [PATCH 13/21] net/mlx4_en: Fix wrong csum complete report when rxvlan
 offload is disabled

[ Upstream commit 79a258526ce1051cb9684018c25a89d51ac21be8 ]

The check_csum() function relied on hwtstamp_rx_filter to know if rxvlan
offload is disabled. This is wrong since rxvlan offload can be switched
on/off regardless of hwtstamp_rx_filter.

Also moved check_csum to query CQE information to identify VLAN packets
and removed the check of IP packets, since it has been validated before.

Fixes: f8c6455bb04b ('net/mlx4_en: Extend checksum offloading by CHECKSUM COMPLETE')
Signed-off-by: Ido Shamay <idos@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_rx.c | 17 ++++++-----------
 1 file changed, 6 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 2a77a6b..eab4e08 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -723,7 +723,7 @@ static int get_fixed_ipv6_csum(__wsum hw_checksum, struct sk_buff *skb,
 }
 #endif
 static int check_csum(struct mlx4_cqe *cqe, struct sk_buff *skb, void *va,
-		      int hwtstamp_rx_filter)
+		      netdev_features_t dev_features)
 {
 	__wsum hw_checksum = 0;
 
@@ -731,14 +731,8 @@ static int check_csum(struct mlx4_cqe *cqe, struct sk_buff *skb, void *va,
 
 	hw_checksum = csum_unfold((__force __sum16)cqe->checksum);
 
-	if (((struct ethhdr *)va)->h_proto == htons(ETH_P_8021Q) &&
-	    hwtstamp_rx_filter != HWTSTAMP_FILTER_NONE) {
-		/* next protocol non IPv4 or IPv6 */
-		if (((struct vlan_hdr *)hdr)->h_vlan_encapsulated_proto
-		    != htons(ETH_P_IP) &&
-		    ((struct vlan_hdr *)hdr)->h_vlan_encapsulated_proto
-		    != htons(ETH_P_IPV6))
-			return -1;
+	if (cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_VLAN_PRESENT_MASK) &&
+	    !(dev_features & NETIF_F_HW_VLAN_CTAG_RX)) {
 		hw_checksum = get_fixed_vlan_csum(hw_checksum, hdr);
 		hdr += sizeof(struct vlan_hdr);
 	}
@@ -901,7 +895,8 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 
 			if (ip_summed == CHECKSUM_COMPLETE) {
 				void *va = skb_frag_address(skb_shinfo(gro_skb)->frags);
-				if (check_csum(cqe, gro_skb, va, ring->hwtstamp_rx_filter)) {
+				if (check_csum(cqe, gro_skb, va,
+					       dev->features)) {
 					ip_summed = CHECKSUM_NONE;
 					ring->csum_none++;
 					ring->csum_complete--;
@@ -956,7 +951,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 		}
 
 		if (ip_summed == CHECKSUM_COMPLETE) {
-			if (check_csum(cqe, skb, skb->data, ring->hwtstamp_rx_filter)) {
+			if (check_csum(cqe, skb, skb->data, dev->features)) {
 				ip_summed = CHECKSUM_NONE;
 				ring->csum_complete--;
 				ring->csum_none++;
-- 
2.1.0


From 92a58d5336918d43eb296382bf6106aa96a3d995 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Thu, 25 Jun 2015 11:29:44 +0300
Subject: [PATCH 14/21] mlx4: Disable HA for SRIOV PF RoCE devices

[ Upstream commit 7254acffeeec3c0a75b9c5364c29a6eb00014930 ]

When in HA mode, the driver exposes an IB (RoCE) device instance with only
one port. Under SRIOV, the existing implementation doesn't go well with
the PF RoCE driver's role of Special QPs Para-Virtualization, etc.

As such, disable HA for the mlx4 PF RoCE device in SRIOV mode.

Fixes: a57500903093 ('IB/mlx4: Add port aggregation support')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/intf.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c
index 6fce587..0d80aed 100644
--- a/drivers/net/ethernet/mellanox/mlx4/intf.c
+++ b/drivers/net/ethernet/mellanox/mlx4/intf.c
@@ -93,8 +93,14 @@ int mlx4_register_interface(struct mlx4_interface *intf)
 	mutex_lock(&intf_mutex);
 
 	list_add_tail(&intf->list, &intf_list);
-	list_for_each_entry(priv, &dev_list, dev_list)
+	list_for_each_entry(priv, &dev_list, dev_list) {
+		if (mlx4_is_mfunc(&priv->dev) && (intf->flags & MLX4_INTFF_BONDING)) {
+			mlx4_dbg(&priv->dev,
+				 "SRIOV, disabling HA mode for intf proto %d\n", intf->protocol);
+			intf->flags &= ~MLX4_INTFF_BONDING;
+		}
 		mlx4_add_device(intf, priv);
+	}
 
 	mutex_unlock(&intf_mutex);
 
-- 
2.1.0


From ad3cf1fa154d79993813828e73a05587606ca229 Mon Sep 17 00:00:00 2001
From: Mugunthan V N <mugunthanvnm@ti.com>
Date: Thu, 25 Jun 2015 22:21:02 +0530
Subject: [PATCH 15/21] net: phy: fix phy link up when limiting speed via
 device tree

[ Upstream commit eb686231fce3770299760f24fdcf5ad041f44153 ]

When limiting phy link speed using "max-speed" to 100mbps or less on a
giga bit phy, phy never completes auto negotiation and phy state
machine is held in PHY_AN. Fixing this issue by comparing the giga
bit advertise though phydev->supported doesn't have it but phy has
BMSR_ESTATEN set. So that auto negotiation is restarted as old and
new advertise are different and link comes up fine.

Signed-off-by: Mugunthan V N <mugunthanvnm@ti.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index bdfe51f..d551df6 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -796,10 +796,11 @@ static int genphy_config_advert(struct phy_device *phydev)
 	if (phydev->supported & (SUPPORTED_1000baseT_Half |
 				 SUPPORTED_1000baseT_Full)) {
 		adv |= ethtool_adv_to_mii_ctrl1000_t(advertise);
-		if (adv != oldadv)
-			changed = 1;
 	}
 
+	if (adv != oldadv)
+		changed = 1;
+
 	err = phy_write(phydev, MII_CTRL1000, adv);
 	if (err < 0)
 		return err;
-- 
2.1.0


From 1864f97a7de821d0d45d919c9db1a4acb4d1122a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 26 Jun 2015 07:32:29 +0200
Subject: [PATCH 16/21] bnx2x: fix lockdep splat

[ Upstream commit d53c66a5b80698620f7c9ba2372fff4017e987b8 ]

Michel reported following lockdep splat

[   44.718117] INFO: trying to register non-static key.
[   44.723081] the code is fine but needs lockdep annotation.
[   44.728559] turning off the locking correctness validator.
[   44.734036] CPU: 8 PID: 5483 Comm: ethtool Not tainted 4.1.0
[   44.770289] Call Trace:
[   44.772741]  [<ffffffff816eb1cd>] dump_stack+0x4c/0x65
[   44.777879]  [<ffffffff8111d921>] ? console_unlock+0x1f1/0x510
[   44.783708]  [<ffffffff811121f5>] __lock_acquire+0x1d05/0x1f10
[   44.789538]  [<ffffffff8111370a>] ? mark_held_locks+0x6a/0x90
[   44.795276]  [<ffffffff81113835>] ? trace_hardirqs_on_caller+0x105/0x1d0
[   44.801967]  [<ffffffff8111390d>] ? trace_hardirqs_on+0xd/0x10
[   44.807793]  [<ffffffff811330fa>] ? hrtimer_try_to_cancel+0x4a/0x250
[   44.814142]  [<ffffffff81112ba6>] lock_acquire+0xb6/0x290
[   44.819537]  [<ffffffff810d6675>] ? flush_work+0x5/0x280
[   44.824844]  [<ffffffff810d66ad>] flush_work+0x3d/0x280
[   44.830061]  [<ffffffff810d6675>] ? flush_work+0x5/0x280
[   44.835366]  [<ffffffff816f3c43>] ? schedule_hrtimeout_range+0x13/0x20
[   44.841889]  [<ffffffff8112ec9b>] ? usleep_range+0x4b/0x50
[   44.847365]  [<ffffffff8111370a>] ? mark_held_locks+0x6a/0x90
[   44.853102]  [<ffffffff810d8585>] ? __cancel_work_timer+0x105/0x1c0
[   44.859359]  [<ffffffff81113835>] ? trace_hardirqs_on_caller+0x105/0x1d0
[   44.866045]  [<ffffffff810d851f>] __cancel_work_timer+0x9f/0x1c0
[   44.872048]  [<ffffffffa0010982>] ? bnx2x_func_stop+0x42/0x90 [bnx2x]
[   44.878481]  [<ffffffff810d8670>] cancel_work_sync+0x10/0x20
[   44.884134]  [<ffffffffa00259e5>] bnx2x_chip_cleanup+0x245/0x730 [bnx2x]
[   44.890829]  [<ffffffff8110ce02>] ? up+0x32/0x50
[   44.895439]  [<ffffffff811306b5>] ? del_timer_sync+0x5/0xd0
[   44.901005]  [<ffffffffa005596d>] bnx2x_nic_unload+0x20d/0x8e0 [bnx2x]
[   44.907527]  [<ffffffff811f1aef>] ? might_fault+0x5f/0xb0
[   44.912921]  [<ffffffffa005851c>] bnx2x_reload_if_running+0x2c/0x50 [bnx2x]
[   44.919879]  [<ffffffffa005a3c5>] bnx2x_set_ringparam+0x2b5/0x460 [bnx2x]
[   44.926664]  [<ffffffff815d498b>] dev_ethtool+0x55b/0x1c40
[   44.932148]  [<ffffffff815dfdc7>] ? rtnl_lock+0x17/0x20
[   44.937364]  [<ffffffff815e7f8b>] dev_ioctl+0x17b/0x630
[   44.942582]  [<ffffffff815abf8d>] sock_do_ioctl+0x5d/0x70
[   44.947972]  [<ffffffff815ac013>] sock_ioctl+0x73/0x280
[   44.953192]  [<ffffffff8124c1c8>] do_vfs_ioctl+0x88/0x5b0
[   44.958587]  [<ffffffff8110d0b3>] ? up_read+0x23/0x40
[   44.963631]  [<ffffffff812584cc>] ? __fget_light+0x6c/0xa0
[   44.969105]  [<ffffffff8124c781>] SyS_ioctl+0x91/0xb0
[   44.974149]  [<ffffffff816f4dd7>] system_call_fastpath+0x12/0x6f

As bnx2x_init_ptp() is only called if bp->flags contains PTP_SUPPORTED,
we also need to guard bnx2x_stop_ptp() with same condition, otherwise
ptp_task workqueue is not initialized and kernel barfs on
cancel_work_sync()

Fixes: eeed018cbfa30 ("bnx2x: Add timestamping and PTP hardware clock support")
Reported-by: Michel Lespinasse <walken@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Michal Kalderon <Michal.Kalderon@qlogic.com>
Cc: Ariel Elior <Ariel.Elior@qlogic.com>
Cc: Yuval Mintz <Yuval.Mintz@qlogic.com>
Cc: David Decotigny <decot@google.com>
Acked-by: Sony Chacko <sony.chacko@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 33501bc..8a97d28 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -9323,7 +9323,8 @@ unload_error:
 	 * function stop ramrod is sent, since as part of this ramrod FW access
 	 * PTP registers.
 	 */
-	bnx2x_stop_ptp(bp);
+	if (bp->flags & PTP_SUPPORTED)
+		bnx2x_stop_ptp(bp);
 
 	/* Disable HW interrupts, NAPI */
 	bnx2x_netif_stop(bp, 1);
-- 
2.1.0


From 862302cda6c51cd5644e3314189c47ff8a1b0ff4 Mon Sep 17 00:00:00 2001
From: Alexander Sverdlin <alexander.sverdlin@nokia.com>
Date: Mon, 29 Jun 2015 10:41:03 +0200
Subject: [PATCH 17/21] sctp: Fix race between OOTB responce and route removal

[ Upstream commit 29c4afc4e98f4dc0ea9df22c631841f9c220b944 ]

There is NULL pointer dereference possible during statistics update if the route
used for OOTB responce is removed at unfortunate time. If the route exists when
we receive OOTB packet and we finally jump into sctp_packet_transmit() to send
ABORT, but in the meantime route is removed under our feet, we take "no_route"
path and try to update stats with IP_INC_STATS(sock_net(asoc->base.sk), ...).

But sctp_ootb_pkt_new() used to prepare responce packet doesn't call
sctp_transport_set_owner() and therefore there is no asoc associated with this
packet. Probably temporary asoc just for OOTB responces is overkill, so just
introduce a check like in all other places in sctp_packet_transmit(), where
"asoc" is dereferenced.

To reproduce this, one needs to
0. ensure that sctp module is loaded (otherwise ABORT is not generated)
1. remove default route on the machine
2. while true; do
     ip route del [interface-specific route]
     ip route add [interface-specific route]
   done
3. send enough OOTB packets (i.e. HB REQs) from another host to trigger ABORT
   responce

On x86_64 the crash looks like this:

BUG: unable to handle kernel NULL pointer dereference at 0000000000000020
IP: [<ffffffffa05ec9ac>] sctp_packet_transmit+0x63c/0x730 [sctp]
PGD 0
Oops: 0000 [#1] PREEMPT SMP
Modules linked in: ...
CPU: 0 PID: 0 Comm: swapper/0 Tainted: G           O    4.0.5-1-ARCH #1
Hardware name: ...
task: ffffffff818124c0 ti: ffffffff81800000 task.ti: ffffffff81800000
RIP: 0010:[<ffffffffa05ec9ac>]  [<ffffffffa05ec9ac>] sctp_packet_transmit+0x63c/0x730 [sctp]
RSP: 0018:ffff880127c037b8  EFLAGS: 00010296
RAX: 0000000000000000 RBX: 0000000000000000 RCX: 00000015ff66b480
RDX: 00000015ff66b400 RSI: ffff880127c17200 RDI: ffff880123403700
RBP: ffff880127c03888 R08: 0000000000017200 R09: ffffffff814625af
R10: ffffea00047e4680 R11: 00000000ffffff80 R12: ffff8800b0d38a28
R13: ffff8800b0d38a28 R14: ffff8800b3e88000 R15: ffffffffa05f24e0
FS:  0000000000000000(0000) GS:ffff880127c00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
CR2: 0000000000000020 CR3: 00000000c855b000 CR4: 00000000000007f0
Stack:
 ffff880127c03910 ffff8800b0d38a28 ffffffff8189d240 ffff88011f91b400
 ffff880127c03828 ffffffffa05c94c5 0000000000000000 ffff8800baa1c520
 0000000000000000 0000000000000001 0000000000000000 0000000000000000
Call Trace:
 <IRQ>
 [<ffffffffa05c94c5>] ? sctp_sf_tabort_8_4_8.isra.20+0x85/0x140 [sctp]
 [<ffffffffa05d6b42>] ? sctp_transport_put+0x52/0x80 [sctp]
 [<ffffffffa05d0bfc>] sctp_do_sm+0xb8c/0x19a0 [sctp]
 [<ffffffff810b0e00>] ? trigger_load_balance+0x90/0x210
 [<ffffffff810e0329>] ? update_process_times+0x59/0x60
 [<ffffffff812c7a40>] ? timerqueue_add+0x60/0xb0
 [<ffffffff810e0549>] ? enqueue_hrtimer+0x29/0xa0
 [<ffffffff8101f599>] ? read_tsc+0x9/0x10
 [<ffffffff8116d4b5>] ? put_page+0x55/0x60
 [<ffffffff810ee1ad>] ? clockevents_program_event+0x6d/0x100
 [<ffffffff81462b68>] ? skb_free_head+0x58/0x80
 [<ffffffffa029a10b>] ? chksum_update+0x1b/0x27 [crc32c_generic]
 [<ffffffff81283f3e>] ? crypto_shash_update+0xce/0xf0
 [<ffffffffa05d3993>] sctp_endpoint_bh_rcv+0x113/0x280 [sctp]
 [<ffffffffa05dd4e6>] sctp_inq_push+0x46/0x60 [sctp]
 [<ffffffffa05ed7a0>] sctp_rcv+0x880/0x910 [sctp]
 [<ffffffffa05ecb50>] ? sctp_packet_transmit_chunk+0xb0/0xb0 [sctp]
 [<ffffffffa05ecb70>] ? sctp_csum_update+0x20/0x20 [sctp]
 [<ffffffff814b05a5>] ? ip_route_input_noref+0x235/0xd30
 [<ffffffff81051d6b>] ? ack_ioapic_level+0x7b/0x150
 [<ffffffff814b27be>] ip_local_deliver_finish+0xae/0x210
 [<ffffffff814b2e15>] ip_local_deliver+0x35/0x90
 [<ffffffff814b2a15>] ip_rcv_finish+0xf5/0x370
 [<ffffffff814b3128>] ip_rcv+0x2b8/0x3a0
 [<ffffffff81474193>] __netif_receive_skb_core+0x763/0xa50
 [<ffffffff81476c28>] __netif_receive_skb+0x18/0x60
 [<ffffffff81476cb0>] netif_receive_skb_internal+0x40/0xd0
 [<ffffffff814776c8>] napi_gro_receive+0xe8/0x120
 [<ffffffffa03946aa>] rtl8169_poll+0x2da/0x660 [r8169]
 [<ffffffff8147896a>] net_rx_action+0x21a/0x360
 [<ffffffff81078dc1>] __do_softirq+0xe1/0x2d0
 [<ffffffff8107912d>] irq_exit+0xad/0xb0
 [<ffffffff8157d158>] do_IRQ+0x58/0xf0
 [<ffffffff8157b06d>] common_interrupt+0x6d/0x6d
 <EOI>
 [<ffffffff810e1218>] ? hrtimer_start+0x18/0x20
 [<ffffffffa05d65f9>] ? sctp_transport_destroy_rcu+0x29/0x30 [sctp]
 [<ffffffff81020c50>] ? mwait_idle+0x60/0xa0
 [<ffffffff810216ef>] arch_cpu_idle+0xf/0x20
 [<ffffffff810b731c>] cpu_startup_entry+0x3ec/0x480
 [<ffffffff8156b365>] rest_init+0x85/0x90
 [<ffffffff818eb035>] start_kernel+0x48b/0x4ac
 [<ffffffff818ea120>] ? early_idt_handlers+0x120/0x120
 [<ffffffff818ea339>] x86_64_start_reservations+0x2a/0x2c
 [<ffffffff818ea49c>] x86_64_start_kernel+0x161/0x184
Code: 90 48 8b 80 b8 00 00 00 48 89 85 70 ff ff ff 48 83 bd 70 ff ff ff 00 0f 85 cd fa ff ff 48 89 df 31 db e8 18 63 e7 e0 48 8b 45 80 <48> 8b 40 20 48 8b 40 30 48 8b 80 68 01 00 00 65 48 ff 40 78 e9
RIP  [<ffffffffa05ec9ac>] sctp_packet_transmit+0x63c/0x730 [sctp]
 RSP <ffff880127c037b8>
CR2: 0000000000000020
---[ end trace 5aec7fd2dc983574 ]---
Kernel panic - not syncing: Fatal exception in interrupt
Kernel Offset: 0x0 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffff9fffffff)
drm_kms_helper: panic occurred, switching back to text console
---[ end Kernel panic - not syncing: Fatal exception in interrupt

Signed-off-by: Alexander Sverdlin <alexander.sverdlin@nokia.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/output.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sctp/output.c b/net/sctp/output.c
index fc5e45b..abe7c2d 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -599,7 +599,9 @@ out:
 	return err;
 no_route:
 	kfree_skb(nskb);
-	IP_INC_STATS(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES);
+
+	if (asoc)
+		IP_INC_STATS(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES);
 
 	/* FIXME: Returning the 'err' will effect all the associations
 	 * associated with a socket, although only one of the paths of the
-- 
2.1.0


From a4d501a32c7ffbc356a2c6677251a5613dd77434 Mon Sep 17 00:00:00 2001
From: Tom Lendacky <thomas.lendacky@amd.com>
Date: Mon, 29 Jun 2015 11:22:12 -0500
Subject: [PATCH 18/21] amd-xgbe: Add the __GFP_NOWARN flag to Rx buffer
 allocation

[ Upstream commit 472cfe7127760d68b819cf35a26e5a1b44b30f4e ]

When allocating Rx related buffers, alloc_pages is called using an order
number that is decreased until successful. A system under stress can
experience failures during this allocation process resulting in a warning
being issued. This message can be of concern to end users even though the
failure is not fatal. Since the failure is not fatal and can occur
multiple times, the driver should include the __GFP_NOWARN flag to
suppress the warning message from being issued.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe-desc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
index d81fc6b..5c92fb7 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
@@ -263,7 +263,7 @@ static int xgbe_alloc_pages(struct xgbe_prv_data *pdata,
 	int ret;
 
 	/* Try to obtain pages, decreasing order if necessary */
-	gfp |= __GFP_COLD | __GFP_COMP;
+	gfp |= __GFP_COLD | __GFP_COMP | __GFP_NOWARN;
 	while (order >= 0) {
 		pages = alloc_pages(gfp, order);
 		if (pages)
-- 
2.1.0


From 2c5317116ecc9ab45da091fbaa957d20d993752a Mon Sep 17 00:00:00 2001
From: Simon Guinot <simon.guinot@sequanux.org>
Date: Tue, 30 Jun 2015 16:20:20 +0200
Subject: [PATCH 19/21] net: mvneta: introduce compatible string "marvell,
 armada-xp-neta"

[ Upstream commit f522a975a8101895a85354b9c143f41b8248e71a ]

The mvneta driver supports the Ethernet IP found in the Armada 370, XP,
380 and 385 SoCs. Since at least one more hardware feature is available
for the Armada XP SoCs then a way to identify them is needed.

This patch introduces a new compatible string "marvell,armada-xp-neta".

Signed-off-by: Simon Guinot <simon.guinot@sequanux.org>
Fixes: c5aff18204da ("net: mvneta: driver for Marvell Armada 370/XP network unit")
Cc: <stable@vger.kernel.org> # v3.8+
Acked-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
Acked-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt | 2 +-
 drivers/net/ethernet/marvell/mvneta.c                             | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt b/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt
index 750d577..f5a8ca2 100644
--- a/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt
+++ b/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt
@@ -1,7 +1,7 @@
 * Marvell Armada 370 / Armada XP Ethernet Controller (NETA)
 
 Required properties:
-- compatible: should be "marvell,armada-370-neta".
+- compatible: "marvell,armada-370-neta" or "marvell,armada-xp-neta".
 - reg: address and length of the register set for the device.
 - interrupts: interrupt for the device
 - phy: See ethernet.txt file in the same directory.
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 74176ec..4fb27ea 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -3185,6 +3185,7 @@ static int mvneta_remove(struct platform_device *pdev)
 
 static const struct of_device_id mvneta_match[] = {
 	{ .compatible = "marvell,armada-370-neta" },
+	{ .compatible = "marvell,armada-xp-neta" },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, mvneta_match);
-- 
2.1.0


From 267b31d1607df11b289559d837c5d1812c078bc6 Mon Sep 17 00:00:00 2001
From: Simon Guinot <simon.guinot@sequanux.org>
Date: Tue, 30 Jun 2015 16:20:21 +0200
Subject: [PATCH 20/21] ARM: mvebu: update Ethernet compatible string for
 Armada XP

[ Upstream commit ea3b55fe83b5fcede82d183164b9d6831b26e33b ]

This patch updates the Ethernet DT nodes for Armada XP SoCs with the
compatible string "marvell,armada-xp-neta".

Signed-off-by: Simon Guinot <simon.guinot@sequanux.org>
Fixes: 77916519cba3 ("arm: mvebu: Armada XP MV78230 has only three Ethernet interfaces")
Cc: <stable@vger.kernel.org> # v3.8+
Acked-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
Reviewed-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/arm/boot/dts/armada-370-xp.dtsi     |  2 --
 arch/arm/boot/dts/armada-370.dtsi        |  8 ++++++++
 arch/arm/boot/dts/armada-xp-mv78260.dtsi |  2 +-
 arch/arm/boot/dts/armada-xp-mv78460.dtsi |  2 +-
 arch/arm/boot/dts/armada-xp.dtsi         | 10 +++++++++-
 5 files changed, 19 insertions(+), 5 deletions(-)

diff --git a/arch/arm/boot/dts/armada-370-xp.dtsi b/arch/arm/boot/dts/armada-370-xp.dtsi
index ec96f0b..06a2f2a 100644
--- a/arch/arm/boot/dts/armada-370-xp.dtsi
+++ b/arch/arm/boot/dts/armada-370-xp.dtsi
@@ -270,7 +270,6 @@
 			};
 
 			eth0: ethernet@70000 {
-				compatible = "marvell,armada-370-neta";
 				reg = <0x70000 0x4000>;
 				interrupts = <8>;
 				clocks = <&gateclk 4>;
@@ -286,7 +285,6 @@
 			};
 
 			eth1: ethernet@74000 {
-				compatible = "marvell,armada-370-neta";
 				reg = <0x74000 0x4000>;
 				interrupts = <10>;
 				clocks = <&gateclk 3>;
diff --git a/arch/arm/boot/dts/armada-370.dtsi b/arch/arm/boot/dts/armada-370.dtsi
index 00b50db5..ca4257b 100644
--- a/arch/arm/boot/dts/armada-370.dtsi
+++ b/arch/arm/boot/dts/armada-370.dtsi
@@ -307,6 +307,14 @@
 					dmacap,memset;
 				};
 			};
+
+			ethernet@70000 {
+				compatible = "marvell,armada-370-neta";
+			};
+
+			ethernet@74000 {
+				compatible = "marvell,armada-370-neta";
+			};
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/armada-xp-mv78260.dtsi b/arch/arm/boot/dts/armada-xp-mv78260.dtsi
index 8479fdc..c5fdc99 100644
--- a/arch/arm/boot/dts/armada-xp-mv78260.dtsi
+++ b/arch/arm/boot/dts/armada-xp-mv78260.dtsi
@@ -318,7 +318,7 @@
 			};
 
 			eth3: ethernet@34000 {
-				compatible = "marvell,armada-370-neta";
+				compatible = "marvell,armada-xp-neta";
 				reg = <0x34000 0x4000>;
 				interrupts = <14>;
 				clocks = <&gateclk 1>;
diff --git a/arch/arm/boot/dts/armada-xp-mv78460.dtsi b/arch/arm/boot/dts/armada-xp-mv78460.dtsi
index 661d54c..0e24f1a 100644
--- a/arch/arm/boot/dts/armada-xp-mv78460.dtsi
+++ b/arch/arm/boot/dts/armada-xp-mv78460.dtsi
@@ -356,7 +356,7 @@
 			};
 
 			eth3: ethernet@34000 {
-				compatible = "marvell,armada-370-neta";
+				compatible = "marvell,armada-xp-neta";
 				reg = <0x34000 0x4000>;
 				interrupts = <14>;
 				clocks = <&gateclk 1>;
diff --git a/arch/arm/boot/dts/armada-xp.dtsi b/arch/arm/boot/dts/armada-xp.dtsi
index 013d63f..8fdd6d7 100644
--- a/arch/arm/boot/dts/armada-xp.dtsi
+++ b/arch/arm/boot/dts/armada-xp.dtsi
@@ -177,7 +177,7 @@
 			};
 
 			eth2: ethernet@30000 {
-				compatible = "marvell,armada-370-neta";
+				compatible = "marvell,armada-xp-neta";
 				reg = <0x30000 0x4000>;
 				interrupts = <12>;
 				clocks = <&gateclk 2>;
@@ -220,6 +220,14 @@
 				};
 			};
 
+			ethernet@70000 {
+				compatible = "marvell,armada-xp-neta";
+			};
+
+			ethernet@74000 {
+				compatible = "marvell,armada-xp-neta";
+			};
+
 			xor@f0900 {
 				compatible = "marvell,orion-xor";
 				reg = <0xF0900 0x100
-- 
2.1.0


From 69fa67f20ca03f9f524404db30ffe4897ad3da86 Mon Sep 17 00:00:00 2001
From: Simon Guinot <simon.guinot@sequanux.org>
Date: Tue, 30 Jun 2015 16:20:22 +0200
Subject: [PATCH 21/21] net: mvneta: disable IP checksum with jumbo frames for
 Armada 370

[ Upstream commit b65657fc240ae6c1d2a1e62db9a0e61ac9631d7a ]

The Ethernet controller found in the Armada 370, 380 and 385 SoCs don't
support TCP/IP checksumming with frame sizes larger than 1600 bytes.

This patch fixes the issue by disabling the features NETIF_F_IP_CSUM and
NETIF_F_TSO for the Armada 370 and compatibles SoCs when the MTU is set
to a value greater than 1600 bytes.

Signed-off-by: Simon Guinot <simon.guinot@sequanux.org>
Fixes: c5aff18204da ("net: mvneta: driver for Marvell Armada 370/XP network unit")
Cc: <stable@vger.kernel.org> # v3.8+
Acked-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 26 +++++++++++++++++++++++++-
 1 file changed, 25 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 4fb27ea..74d0389 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -310,6 +310,7 @@ struct mvneta_port {
 	unsigned int link;
 	unsigned int duplex;
 	unsigned int speed;
+	unsigned int tx_csum_limit;
 	int use_inband_status:1;
 };
 
@@ -2508,8 +2509,10 @@ static int mvneta_change_mtu(struct net_device *dev, int mtu)
 
 	dev->mtu = mtu;
 
-	if (!netif_running(dev))
+	if (!netif_running(dev)) {
+		netdev_update_features(dev);
 		return 0;
+	}
 
 	/* The interface is running, so we have to force a
 	 * reallocation of the queues
@@ -2538,9 +2541,26 @@ static int mvneta_change_mtu(struct net_device *dev, int mtu)
 	mvneta_start_dev(pp);
 	mvneta_port_up(pp);
 
+	netdev_update_features(dev);
+
 	return 0;
 }
 
+static netdev_features_t mvneta_fix_features(struct net_device *dev,
+					     netdev_features_t features)
+{
+	struct mvneta_port *pp = netdev_priv(dev);
+
+	if (pp->tx_csum_limit && dev->mtu > pp->tx_csum_limit) {
+		features &= ~(NETIF_F_IP_CSUM | NETIF_F_TSO);
+		netdev_info(dev,
+			    "Disable IP checksum for MTU greater than %dB\n",
+			    pp->tx_csum_limit);
+	}
+
+	return features;
+}
+
 /* Get mac address */
 static void mvneta_get_mac_addr(struct mvneta_port *pp, unsigned char *addr)
 {
@@ -2862,6 +2882,7 @@ static const struct net_device_ops mvneta_netdev_ops = {
 	.ndo_set_rx_mode     = mvneta_set_rx_mode,
 	.ndo_set_mac_address = mvneta_set_mac_addr,
 	.ndo_change_mtu      = mvneta_change_mtu,
+	.ndo_fix_features    = mvneta_fix_features,
 	.ndo_get_stats64     = mvneta_get_stats64,
 	.ndo_do_ioctl        = mvneta_ioctl,
 };
@@ -3107,6 +3128,9 @@ static int mvneta_probe(struct platform_device *pdev)
 		}
 	}
 
+	if (of_device_is_compatible(dn, "marvell,armada-370-neta"))
+		pp->tx_csum_limit = 1600;
+
 	pp->tx_ring_size = MVNETA_MAX_TXD;
 	pp->rx_ring_size = MVNETA_MAX_RXD;
 
-- 
2.1.0

Re: [PATCHES] Networking

[Greg KH]

On Fri, Jul 03, 2015 at 03:31:36PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for 3.14, 3.18,
> 4.0, and 4.1 -stable, respectively.

All queued up for the kernels I care about thanks.

Oh, no need to do any more 4.0-stable patches anymore, after this kernel
it's going to be end-of-life.

thanks,

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 118 bytes --]


Please queue up the following networking bug fixes for v3.12, v3.14, v3.18,
and v4.1 -stable, respectively.

Thanks!

[-- Attachment #2: net_312.mbox --]
[-- Type: Application/Octet-Stream, Size: 57876 bytes --]

From 680f36fd0f121b528bfa46e16052ebf6f1eedf7a Mon Sep 17 00:00:00 2001
From: Angga <Hermin.Anggawijaya@alliedtelesis.co.nz>
Date: Fri, 3 Jul 2015 14:40:52 +1200
Subject: [PATCH 01/21] ipv6: Make MLD packets to only be processed locally

[ Upstream commit 4c938d22c88a9ddccc8c55a85e0430e9c62b1ac5 ]

Before commit daad151263cf ("ipv6: Make ipv6_is_mld() inline and use it
from ip6_mc_input().") MLD packets were only processed locally. After the
change, a copy of MLD packet goes through ip6_mr_input, causing
MRT6MSG_NOCACHE message to be generated to user space.

Make MLD packet only processed locally.

Fixes: daad151263cf ("ipv6: Make ipv6_is_mld() inline and use it from ip6_mc_input().")
Signed-off-by: Hermin Anggawijaya <hermin.anggawijaya@alliedtelesis.co.nz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_input.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 51d54dc..05c94d9 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -329,10 +329,10 @@ int ip6_mc_input(struct sk_buff *skb)
 				if (offset < 0)
 					goto out;
 
-				if (!ipv6_is_mld(skb, nexthdr, offset))
-					goto out;
+				if (ipv6_is_mld(skb, nexthdr, offset))
+					deliver = true;
 
-				deliver = true;
+				goto out;
 			}
 			/* unknown RA - process it normally */
 		}
-- 
2.1.0


From 4f61262ef35eaad278378b47ee2f67052a8cd0e4 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 6 Jul 2015 17:13:26 +0200
Subject: [PATCH 02/21] net: graceful exit from netif_alloc_netdev_queues()

[ Upstream commit d339727c2b1a10f25e6636670ab6e1841170e328 ]

User space can crash kernel with

ip link add ifb10 numtxqueues 100000 type ifb

We must replace a BUG_ON() by proper test and return -EINVAL for
crazy values.

Fixes: 60877a32bce00 ("net: allow large number of tx queues")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 3ca487e..5a407f0 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5559,7 +5559,8 @@ static int netif_alloc_netdev_queues(struct net_device *dev)
 	struct netdev_queue *tx;
 	size_t sz = count * sizeof(*tx);
 
-	BUG_ON(count < 1 || count > 0xffff);
+	if (count < 1 || count > 0xffff)
+		return -EINVAL;
 
 	tx = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
 	if (!tx) {
-- 
2.1.0


From 3e06aae90c51db18c54bcdb2c794854413a9ba2a Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Tue, 7 Jul 2015 00:07:52 +0200
Subject: [PATCH 03/21] rtnetlink: verify IFLA_VF_INFO attributes before
 passing them to driver

[ Upstream commit 4f7d2cdfdde71ffe962399b7020c674050329423 ]

Jason Gunthorpe reported that since commit c02db8c6290b ("rtnetlink: make
SR-IOV VF interface symmetric"), we don't verify IFLA_VF_INFO attributes
anymore with respect to their policy, that is, ifla_vfinfo_policy[].

Before, they were part of ifla_policy[], but they have been nested since
placed under IFLA_VFINFO_LIST, that contains the attribute IFLA_VF_INFO,
which is another nested attribute for the actual VF attributes such as
IFLA_VF_MAC, IFLA_VF_VLAN, etc.

Despite the policy being split out from ifla_policy[] in this commit,
it's never applied anywhere. nla_for_each_nested() only does basic nla_ok()
testing for struct nlattr, but it doesn't know about the data context and
their requirements.

Fix, on top of Jason's initial work, does 1) parsing of the attributes
with the right policy, and 2) using the resulting parsed attribute table
from 1) instead of the nla_for_each_nested() loop (just like we used to
do when still part of ifla_policy[]).

Reference: http://thread.gmane.org/gmane.linux.network/368913
Fixes: c02db8c6290b ("rtnetlink: make SR-IOV VF interface symmetric")
Reported-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Cc: Chris Wright <chrisw@sous-sol.org>
Cc: Sucheta Chakraborty <sucheta.chakraborty@qlogic.com>
Cc: Greg Rose <gregory.v.rose@intel.com>
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Cc: Rony Efraim <ronye@mellanox.com>
Cc: Vlad Zolotarov <vladz@cloudius-systems.com>
Cc: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Cc: Thomas Graf <tgraf@suug.ch>
Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Vlad Zolotarov <vladz@cloudius-systems.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 128 ++++++++++++++++++++++++++-------------------------
 1 file changed, 65 insertions(+), 63 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 76cc27f..fd3a16e 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1197,10 +1197,6 @@ static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
 	[IFLA_INFO_DATA]	= { .type = NLA_NESTED },
 };
 
-static const struct nla_policy ifla_vfinfo_policy[IFLA_VF_INFO_MAX+1] = {
-	[IFLA_VF_INFO]		= { .type = NLA_NESTED },
-};
-
 static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = {
 	[IFLA_VF_MAC]		= { .len = sizeof(struct ifla_vf_mac) },
 	[IFLA_VF_VLAN]		= { .len = sizeof(struct ifla_vf_vlan) },
@@ -1274,67 +1270,66 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[])
 	return 0;
 }
 
-static int do_setvfinfo(struct net_device *dev, struct nlattr *attr)
+static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
 {
-	int rem, err = -EINVAL;
-	struct nlattr *vf;
 	const struct net_device_ops *ops = dev->netdev_ops;
+	int err = -EINVAL;
 
-	nla_for_each_nested(vf, attr, rem) {
-		switch (nla_type(vf)) {
-		case IFLA_VF_MAC: {
-			struct ifla_vf_mac *ivm;
-			ivm = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_mac)
-				err = ops->ndo_set_vf_mac(dev, ivm->vf,
-							  ivm->mac);
-			break;
-		}
-		case IFLA_VF_VLAN: {
-			struct ifla_vf_vlan *ivv;
-			ivv = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_vlan)
-				err = ops->ndo_set_vf_vlan(dev, ivv->vf,
-							   ivv->vlan,
-							   ivv->qos);
-			break;
-		}
-		case IFLA_VF_TX_RATE: {
-			struct ifla_vf_tx_rate *ivt;
-			ivt = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_tx_rate)
-				err = ops->ndo_set_vf_tx_rate(dev, ivt->vf,
-							      ivt->rate);
-			break;
-		}
-		case IFLA_VF_SPOOFCHK: {
-			struct ifla_vf_spoofchk *ivs;
-			ivs = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_spoofchk)
-				err = ops->ndo_set_vf_spoofchk(dev, ivs->vf,
-							       ivs->setting);
-			break;
-		}
-		case IFLA_VF_LINK_STATE: {
-			struct ifla_vf_link_state *ivl;
-			ivl = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_link_state)
-				err = ops->ndo_set_vf_link_state(dev, ivl->vf,
-								 ivl->link_state);
-			break;
-		}
-		default:
-			err = -EINVAL;
-			break;
-		}
-		if (err)
-			break;
+	if (tb[IFLA_VF_MAC]) {
+		struct ifla_vf_mac *ivm = nla_data(tb[IFLA_VF_MAC]);
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_mac)
+			err = ops->ndo_set_vf_mac(dev, ivm->vf,
+						  ivm->mac);
+		if (err < 0)
+			return err;
+	}
+
+	if (tb[IFLA_VF_VLAN]) {
+		struct ifla_vf_vlan *ivv = nla_data(tb[IFLA_VF_VLAN]);
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_vlan)
+			err = ops->ndo_set_vf_vlan(dev, ivv->vf, ivv->vlan,
+						   ivv->qos);
+		if (err < 0)
+			return err;
+	}
+
+	if (tb[IFLA_VF_TX_RATE]) {
+		struct ifla_vf_tx_rate *ivt = nla_data(tb[IFLA_VF_TX_RATE]);
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_tx_rate)
+			err = ops->ndo_set_vf_tx_rate(dev, ivt->vf,
+						      ivt->rate);
+		if (err < 0)
+			return err;
 	}
+
+	if (tb[IFLA_VF_SPOOFCHK]) {
+		struct ifla_vf_spoofchk *ivs = nla_data(tb[IFLA_VF_SPOOFCHK]);
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_spoofchk)
+			err = ops->ndo_set_vf_spoofchk(dev, ivs->vf,
+						       ivs->setting);
+		if (err < 0)
+			return err;
+	}
+
+	if (tb[IFLA_VF_LINK_STATE]) {
+		struct ifla_vf_link_state *ivl = nla_data(tb[IFLA_VF_LINK_STATE]);
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_link_state)
+			err = ops->ndo_set_vf_link_state(dev, ivl->vf,
+							 ivl->link_state);
+		if (err < 0)
+			return err;
+	}
+
 	return err;
 }
 
@@ -1517,14 +1512,21 @@ static int do_setlink(const struct sk_buff *skb,
 	}
 
 	if (tb[IFLA_VFINFO_LIST]) {
+		struct nlattr *vfinfo[IFLA_VF_MAX + 1];
 		struct nlattr *attr;
 		int rem;
+
 		nla_for_each_nested(attr, tb[IFLA_VFINFO_LIST], rem) {
-			if (nla_type(attr) != IFLA_VF_INFO) {
+			if (nla_type(attr) != IFLA_VF_INFO ||
+			    nla_len(attr) < NLA_HDRLEN) {
 				err = -EINVAL;
 				goto errout;
 			}
-			err = do_setvfinfo(dev, attr);
+			err = nla_parse_nested(vfinfo, IFLA_VF_MAX, attr,
+					       ifla_vf_policy);
+			if (err < 0)
+				goto errout;
+			err = do_setvfinfo(dev, vfinfo);
 			if (err < 0)
 				goto errout;
 			modified = 1;
-- 
2.1.0


From 0192fd7d2ab7521ab363a75113213444ae707ca5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timo=20Ter=C3=A4s?= <timo.teras@iki.fi>
Date: Tue, 7 Jul 2015 08:34:13 +0300
Subject: [PATCH 04/21] ip_tunnel: fix ipv4 pmtu check to honor inner ip header
 df
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit fc24f2b2094366da8786f59f2606307e934cea17 ]

Frag needed should be sent only if the inner header asked
to not fragment. Currently fragmentation is broken if the
tunnel has df set, but df was not asked in the original
packet. The tunnel's df needs to be still checked to update
internally the pmtu cache.

Commit 23a3647bc4f93bac broke it, and this commit fixes
the ipv4 df check back to the way it was.

Fixes: 23a3647bc4f93bac ("ip_tunnels: Use skb-len to PMTU check.")
Cc: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: Timo Teräs <timo.teras@iki.fi>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_tunnel.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index edd5a81..6913e2f 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -476,7 +476,8 @@ drop:
 EXPORT_SYMBOL_GPL(ip_tunnel_rcv);
 
 static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
-			    struct rtable *rt, __be16 df)
+			    struct rtable *rt, __be16 df,
+			    const struct iphdr *inner_iph)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	int pkt_size = skb->len - tunnel->hlen - dev->hard_header_len;
@@ -493,7 +494,8 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
 
 	if (skb->protocol == htons(ETH_P_IP)) {
 		if (!skb_is_gso(skb) &&
-		    (df & htons(IP_DF)) && mtu < pkt_size) {
+		    (inner_iph->frag_off & htons(IP_DF)) &&
+		    mtu < pkt_size) {
 			memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
 			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
 			return -E2BIG;
@@ -611,7 +613,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		goto tx_error;
 	}
 
-	if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off)) {
+	if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off, inner_iph)) {
 		ip_rt_put(rt);
 		goto tx_error;
 	}
-- 
2.1.0


From d779a21c871cd45ddff5e9027a5c9a984f78ec39 Mon Sep 17 00:00:00 2001
From: Stephen Smalley <sds@tycho.nsa.gov>
Date: Tue, 7 Jul 2015 09:43:45 -0400
Subject: [PATCH 05/21] net/tipc: initialize security state for new connection
 socket

[ Upstream commit fdd75ea8df370f206a8163786e7470c1277a5064 ]

Calling connect() with an AF_TIPC socket would trigger a series
of error messages from SELinux along the lines of:
SELinux: Invalid class 0
type=AVC msg=audit(1434126658.487:34500): avc:  denied  { <unprintable> }
  for pid=292 comm="kworker/u16:5" scontext=system_u:system_r:kernel_t:s0
  tcontext=system_u:object_r:unlabeled_t:s0 tclass=<unprintable>
  permissive=0

This was due to a failure to initialize the security state of the new
connection sock by the tipc code, leaving it with junk in the security
class field and an unlabeled secid.  Add a call to security_sk_clone()
to inherit the security state from the parent socket.

Reported-by: Tim Shearer <tim.shearer@overturenetworks.com>
Signed-off-by: Stephen Smalley <sds@tycho.nsa.gov>
Acked-by: Paul Moore <paul@paul-moore.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/socket.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index dffdbea..d123308 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1607,6 +1607,7 @@ static int accept(struct socket *sock, struct socket *new_sock, int flags)
 	res = tipc_sk_create(sock_net(sock->sk), new_sock, 0, 1);
 	if (res)
 		goto exit;
+	security_sk_clone(sock->sk, new_sock->sk);
 
 	new_sk = new_sock->sk;
 	new_tsock = tipc_sk(new_sk);
-- 
2.1.0


From 7a98168c7d83a6f231fb4ba72adac881d6be2661 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <razor@blackwall.org>
Date: Tue, 7 Jul 2015 15:55:56 +0200
Subject: [PATCH 06/21] bridge: mdb: zero out the local br_ip variable before
 use

[ Upstream commit f1158b74e54f2e2462ba5e2f45a118246d9d5b43 ]

Since commit b0e9a30dd669 ("bridge: Add vlan id to multicast groups")
there's a check in br_ip_equal() for a matching vlan id, but the mdb
functions were not modified to use (or at least zero it) so when an
entry was added it would have a garbage vlan id (from the local br_ip
variable in __br_mdb_add/del) and this would prevent it from being
matched and also deleted. So zero out the whole local ip var to protect
ourselves from future changes and also to fix the current bug, since
there's no vlan id support in the mdb uapi - use always vlan id 0.
Example before patch:
root@debian:~# bridge mdb add dev br0 port eth1 grp 239.0.0.1 permanent
root@debian:~# bridge mdb
dev br0 port eth1 grp 239.0.0.1 permanent
root@debian:~# bridge mdb del dev br0 port eth1 grp 239.0.0.1 permanent
RTNETLINK answers: Invalid argument

After patch:
root@debian:~# bridge mdb add dev br0 port eth1 grp 239.0.0.1 permanent
root@debian:~# bridge mdb
dev br0 port eth1 grp 239.0.0.1 permanent
root@debian:~# bridge mdb del dev br0 port eth1 grp 239.0.0.1 permanent
root@debian:~# bridge mdb

Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Fixes: b0e9a30dd669 ("bridge: Add vlan id to multicast groups")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_mdb.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index b7b1914..13421bf 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -370,6 +370,7 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br,
 	if (!p || p->br != br || p->state == BR_STATE_DISABLED)
 		return -EINVAL;
 
+	memset(&ip, 0, sizeof(ip));
 	ip.proto = entry->addr.proto;
 	if (ip.proto == htons(ETH_P_IP))
 		ip.u.ip4 = entry->addr.u.ip4;
@@ -416,6 +417,7 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry)
 	if (!netif_running(br->dev) || br->multicast_disabled)
 		return -EINVAL;
 
+	memset(&ip, 0, sizeof(ip));
 	ip.proto = entry->addr.proto;
 	if (ip.proto == htons(ETH_P_IP)) {
 		if (timer_pending(&br->ip4_querier.timer))
-- 
2.1.0


From 453c3cb2bedf04d9b2d594d620ff108e949ac4df Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Wed, 8 Jul 2015 21:42:11 +0200
Subject: [PATCH 07/21] net: pktgen: fix race between pktgen_thread_worker()
 and kthread_stop()

[ Upstream commit fecdf8be2d91e04b0a9a4f79ff06499a36f5d14f ]

pktgen_thread_worker() is obviously racy, kthread_stop() can come
between the kthread_should_stop() check and set_current_state().

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Reported-by: Jan Stancek <jstancek@redhat.com>
Reported-by: Marcelo Leitner <mleitner@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/pktgen.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index a104ba3..cea4734 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -3423,8 +3423,10 @@ static int pktgen_thread_worker(void *arg)
 	pktgen_rem_thread(t);
 
 	/* Wait for kthread_stop */
-	while (!kthread_should_stop()) {
+	for (;;) {
 		set_current_state(TASK_INTERRUPTIBLE);
+		if (kthread_should_stop())
+			break;
 		schedule();
 	}
 	__set_current_state(TASK_RUNNING);
-- 
2.1.0


From 88f420711a35df55a0bea0b9b9312b74d4446c9d Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Thu, 9 Jul 2015 09:59:09 +0300
Subject: [PATCH 08/21] net: do not process device backlog during
 unregistration

[ Upstream commit e9e4dd3267d0c5234c5c0f47440456b10875dec9 ]

commit 381c759d9916 ("ipv4: Avoid crashing in ip_error")
fixes a problem where processed packet comes from device
with destroyed inetdev (dev->ip_ptr). This is not expected
because inetdev_destroy is called in NETDEV_UNREGISTER
phase and packets should not be processed after
dev_close_many() and synchronize_net(). Above fix is still
required because inetdev_destroy can be called for other
reasons. But it shows the real problem: backlog can keep
packets for long time and they do not hold reference to
device. Such packets are then delivered to upper levels
at the same time when device is unregistered.
Calling flush_backlog after NETDEV_UNREGISTER_FINAL still
accounts all packets from backlog but before that some packets
continue to be delivered to upper levels long after the
synchronize_net call which is supposed to wait the last
ones. Also, as Eric pointed out, processed packets, mostly
from other devices, can continue to add new packets to backlog.

Fix the problem by moving flush_backlog early, after the
device driver is stopped and before the synchronize_net() call.
Then use netif_running check to make sure we do not add more
packets to backlog. We have to do it in enqueue_to_backlog
context when the local IRQ is disabled. As result, after the
flush_backlog and synchronize_net sequence all packets
should be accounted.

Thanks to Eric W. Biederman for the test script and his
valuable feedback!

Reported-by: Vittorio Gambaletta <linuxbugs@vittgam.net>
Fixes: 6e583ce5242f ("net: eliminate refcounting in backlog queue")
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 5a407f0..89c6134 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3193,6 +3193,8 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
 	local_irq_save(flags);
 
 	rps_lock(sd);
+	if (!netif_running(skb->dev))
+		goto drop;
 	qlen = skb_queue_len(&sd->input_pkt_queue);
 	if (qlen <= netdev_max_backlog && !skb_flow_limit(skb, qlen)) {
 		if (skb_queue_len(&sd->input_pkt_queue)) {
@@ -3214,6 +3216,7 @@ enqueue:
 		goto enqueue;
 	}
 
+drop:
 	sd->dropped++;
 	rps_unlock(sd);
 
@@ -5302,6 +5305,7 @@ static void rollback_registered_many(struct list_head *head)
 		unlist_netdevice(dev);
 
 		dev->reg_state = NETREG_UNREGISTERING;
+		on_each_cpu(flush_backlog, dev, 1);
 	}
 
 	synchronize_net();
@@ -5918,8 +5922,6 @@ void netdev_run_todo(void)
 
 		dev->reg_state = NETREG_UNREGISTERED;
 
-		on_each_cpu(flush_backlog, dev, 1);
-
 		netdev_wait_allrefs(dev);
 
 		/* paranoia */
-- 
2.1.0


From beaff0ae8fa3e2e2e9777d142369f71578d5b682 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Thu, 9 Jul 2015 09:59:10 +0300
Subject: [PATCH 09/21] net: call rcu_read_lock early in process_backlog

[ Upstream commit 2c17d27c36dcce2b6bf689f41a46b9e909877c21 ]

Incoming packet should be either in backlog queue or
in RCU read-side section. Otherwise, the final sequence of
flush_backlog() and synchronize_net() may miss packets
that can run without device reference:

CPU 1                  CPU 2
                       skb->dev: no reference
                       process_backlog:__skb_dequeue
                       process_backlog:local_irq_enable

on_each_cpu for
flush_backlog =>       IPI(hardirq): flush_backlog
                       - packet not found in backlog

                       CPU delayed ...
synchronize_net
- no ongoing RCU
read-side sections

netdev_run_todo,
rcu_barrier: no
ongoing callbacks
                       __netif_receive_skb_core:rcu_read_lock
                       - too late
free dev
                       process packet for freed dev

Fixes: 6e583ce5242f ("net: eliminate refcounting in backlog queue")
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 29 ++++++++++++++---------------
 1 file changed, 14 insertions(+), 15 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 89c6134..f991f5d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3521,8 +3521,6 @@ static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc)
 
 	pt_prev = NULL;
 
-	rcu_read_lock();
-
 another_round:
 	skb->skb_iif = skb->dev->ifindex;
 
@@ -3532,7 +3530,7 @@ another_round:
 	    skb->protocol == cpu_to_be16(ETH_P_8021AD)) {
 		skb = skb_vlan_untag(skb);
 		if (unlikely(!skb))
-			goto unlock;
+			goto out;
 	}
 
 #ifdef CONFIG_NET_CLS_ACT
@@ -3557,7 +3555,7 @@ skip_taps:
 #ifdef CONFIG_NET_CLS_ACT
 	skb = handle_ing(skb, &pt_prev, &ret, orig_dev);
 	if (!skb)
-		goto unlock;
+		goto out;
 ncls:
 #endif
 
@@ -3572,7 +3570,7 @@ ncls:
 		if (vlan_do_receive(&skb))
 			goto another_round;
 		else if (unlikely(!skb))
-			goto unlock;
+			goto out;
 	}
 
 	rx_handler = rcu_dereference(skb->dev->rx_handler);
@@ -3584,7 +3582,7 @@ ncls:
 		switch (rx_handler(&skb)) {
 		case RX_HANDLER_CONSUMED:
 			ret = NET_RX_SUCCESS;
-			goto unlock;
+			goto out;
 		case RX_HANDLER_ANOTHER:
 			goto another_round;
 		case RX_HANDLER_EXACT:
@@ -3636,8 +3634,6 @@ drop:
 		ret = NET_RX_DROP;
 	}
 
-unlock:
-	rcu_read_unlock();
 out:
 	return ret;
 }
@@ -3684,29 +3680,30 @@ static int __netif_receive_skb(struct sk_buff *skb)
  */
 int netif_receive_skb(struct sk_buff *skb)
 {
+	int ret;
+
 	net_timestamp_check(netdev_tstamp_prequeue, skb);
 
 	if (skb_defer_rx_timestamp(skb))
 		return NET_RX_SUCCESS;
 
+	rcu_read_lock();
+
 #ifdef CONFIG_RPS
 	if (static_key_false(&rps_needed)) {
 		struct rps_dev_flow voidflow, *rflow = &voidflow;
-		int cpu, ret;
-
-		rcu_read_lock();
-
-		cpu = get_rps_cpu(skb->dev, skb, &rflow);
+		int cpu = get_rps_cpu(skb->dev, skb, &rflow);
 
 		if (cpu >= 0) {
 			ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
 			rcu_read_unlock();
 			return ret;
 		}
-		rcu_read_unlock();
 	}
 #endif
-	return __netif_receive_skb(skb);
+	ret = __netif_receive_skb(skb);
+	rcu_read_unlock();
+	return ret;
 }
 EXPORT_SYMBOL(netif_receive_skb);
 
@@ -4116,8 +4113,10 @@ static int process_backlog(struct napi_struct *napi, int quota)
 		unsigned int qlen;
 
 		while ((skb = __skb_dequeue(&sd->process_queue))) {
+			rcu_read_lock();
 			local_irq_enable();
 			__netif_receive_skb(skb);
+			rcu_read_unlock();
 			local_irq_disable();
 			input_queue_head_incr(sd);
 			if (++work >= quota) {
-- 
2.1.0


From b7f5e793acb25da0bbe9b5e5a070844b88b8d412 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Mon, 13 Jul 2015 16:04:13 +0800
Subject: [PATCH 10/21] net: Clone skb before setting peeked flag

[ Upstream commit 738ac1ebb96d02e0d23bc320302a6ea94c612dec ]

Shared skbs must not be modified and this is crucial for broadcast
and/or multicast paths where we use it as an optimisation to avoid
unnecessary cloning.

The function skb_recv_datagram breaks this rule by setting peeked
without cloning the skb first.  This causes funky races which leads
to double-free.

This patch fixes this by cloning the skb and replacing the skb
in the list when setting skb->peeked.

Fixes: a59322be07c9 ("[UDP]: Only increment counter on first peek/recv")
Reported-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/datagram.c | 41 ++++++++++++++++++++++++++++++++++++++---
 1 file changed, 38 insertions(+), 3 deletions(-)

diff --git a/net/core/datagram.c b/net/core/datagram.c
index af814e7..005131e 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -130,6 +130,35 @@ out_noerr:
 	goto out;
 }
 
+static int skb_set_peeked(struct sk_buff *skb)
+{
+	struct sk_buff *nskb;
+
+	if (skb->peeked)
+		return 0;
+
+	/* We have to unshare an skb before modifying it. */
+	if (!skb_shared(skb))
+		goto done;
+
+	nskb = skb_clone(skb, GFP_ATOMIC);
+	if (!nskb)
+		return -ENOMEM;
+
+	skb->prev->next = nskb;
+	skb->next->prev = nskb;
+	nskb->prev = skb->prev;
+	nskb->next = skb->next;
+
+	consume_skb(skb);
+	skb = nskb;
+
+done:
+	skb->peeked = 1;
+
+	return 0;
+}
+
 /**
  *	__skb_recv_datagram - Receive a datagram skbuff
  *	@sk: socket
@@ -164,7 +193,9 @@ out_noerr:
 struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
 				    int *peeked, int *off, int *err)
 {
+	struct sk_buff_head *queue = &sk->sk_receive_queue;
 	struct sk_buff *skb, *last;
+	unsigned long cpu_flags;
 	long timeo;
 	/*
 	 * Caller is allowed not to check sk->sk_err before skb_recv_datagram()
@@ -183,8 +214,6 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
 		 * Look at current nfs client by the way...
 		 * However, this function was correct in any case. 8)
 		 */
-		unsigned long cpu_flags;
-		struct sk_buff_head *queue = &sk->sk_receive_queue;
 		int _off = *off;
 
 		last = (struct sk_buff *)queue;
@@ -198,7 +227,11 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
 					_off -= skb->len;
 					continue;
 				}
-				skb->peeked = 1;
+
+				error = skb_set_peeked(skb);
+				if (error)
+					goto unlock_err;
+
 				atomic_inc(&skb->users);
 			} else
 				__skb_unlink(skb, queue);
@@ -222,6 +255,8 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
 
 	return NULL;
 
+unlock_err:
+	spin_unlock_irqrestore(&queue->lock, cpu_flags);
 no_packet:
 	*err = error;
 	return NULL;
-- 
2.1.0


From d58ba5e51dea879e5566f4599404fe75642cd9ce Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Mon, 13 Jul 2015 20:01:42 +0800
Subject: [PATCH 11/21] net: Fix skb csum races when peeking

[ Upstream commit 89c22d8c3b278212eef6a8cc66b570bc840a6f5a ]

When we calculate the checksum on the recv path, we store the
result in the skb as an optimisation in case we need the checksum
again down the line.

This is in fact bogus for the MSG_PEEK case as this is done without
any locking.  So multiple threads can peek and then store the result
to the same skb, potentially resulting in bogus skb states.

This patch fixes this by only storing the result if the skb is not
shared.  This preserves the optimisations for the few cases where
it can be done safely due to locking or other reasons, e.g., SIOCINQ.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/datagram.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/datagram.c b/net/core/datagram.c
index 005131e..a22ec6a 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -777,7 +777,8 @@ __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len)
 	if (likely(!sum)) {
 		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE))
 			netdev_rx_csum_fault(skb->dev);
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		if (!skb_shared(skb))
+			skb->ip_summed = CHECKSUM_UNNECESSARY;
 	}
 	return sum;
 }
-- 
2.1.0


From 9d55af91e7bf5d402af55e7f7ad73054da1d25eb Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Tue, 4 Aug 2015 15:42:47 +0800
Subject: [PATCH 12/21] net: Fix skb_set_peeked use-after-free bug

[ Upstream commit a0a2a6602496a45ae838a96db8b8173794b5d398 ]

The commit 738ac1ebb96d02e0d23bc320302a6ea94c612dec ("net: Clone
skb before setting peeked flag") introduced a use-after-free bug
in skb_recv_datagram.  This is because skb_set_peeked may create
a new skb and free the existing one.  As it stands the caller will
continue to use the old freed skb.

This patch fixes it by making skb_set_peeked return the new skb
(or the old one if unchanged).

Fixes: 738ac1ebb96d ("net: Clone skb before setting peeked flag")
Reported-by: Brenden Blanco <bblanco@plumgrid.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Tested-by: Brenden Blanco <bblanco@plumgrid.com>
Reviewed-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/datagram.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/net/core/datagram.c b/net/core/datagram.c
index a22ec6a..98e3d61 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -130,12 +130,12 @@ out_noerr:
 	goto out;
 }
 
-static int skb_set_peeked(struct sk_buff *skb)
+static struct sk_buff *skb_set_peeked(struct sk_buff *skb)
 {
 	struct sk_buff *nskb;
 
 	if (skb->peeked)
-		return 0;
+		return skb;
 
 	/* We have to unshare an skb before modifying it. */
 	if (!skb_shared(skb))
@@ -143,7 +143,7 @@ static int skb_set_peeked(struct sk_buff *skb)
 
 	nskb = skb_clone(skb, GFP_ATOMIC);
 	if (!nskb)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	skb->prev->next = nskb;
 	skb->next->prev = nskb;
@@ -156,7 +156,7 @@ static int skb_set_peeked(struct sk_buff *skb)
 done:
 	skb->peeked = 1;
 
-	return 0;
+	return skb;
 }
 
 /**
@@ -228,8 +228,9 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
 					continue;
 				}
 
-				error = skb_set_peeked(skb);
-				if (error)
+				skb = skb_set_peeked(skb);
+				error = PTR_ERR(skb);
+				if (IS_ERR(skb))
 					goto unlock_err;
 
 				atomic_inc(&skb->users);
-- 
2.1.0


From 012bae4dbc30f95dbf1068c60a6b626ac43f737f Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Mon, 13 Jul 2015 06:36:19 -0700
Subject: [PATCH 13/21] bridge: mdb: fix double add notification

[ Upstream commit 5ebc784625ea68a9570d1f70557e7932988cd1b4 ]

Since the mdb add/del code was introduced there have been 2 br_mdb_notify
calls when doing br_mdb_add() resulting in 2 notifications on each add.

Example:
 Command: bridge mdb add dev br0 port eth1 grp 239.0.0.1 permanent
 Before patch:
 root@debian:~# bridge monitor all
 [MDB]dev br0 port eth1 grp 239.0.0.1 permanent
 [MDB]dev br0 port eth1 grp 239.0.0.1 permanent

 After patch:
 root@debian:~# bridge monitor all
 [MDB]dev br0 port eth1 grp 239.0.0.1 permanent

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Fixes: cfd567543590 ("bridge: add support of adding and deleting mdb entries")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_mdb.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index 13421bf..27cf128 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -347,7 +347,6 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
 		return -ENOMEM;
 	rcu_assign_pointer(*pp, p);
 
-	br_mdb_notify(br->dev, port, group, RTM_NEWMDB);
 	return 0;
 }
 
-- 
2.1.0


From f643941611ddce0162319f02300c35044020b5ab Mon Sep 17 00:00:00 2001
From: Tilman Schmidt <tilman@imap.cc>
Date: Tue, 14 Jul 2015 00:37:13 +0200
Subject: [PATCH 14/21] isdn/gigaset: reset tty->receive_room when attaching
 ser_gigaset

[ Upstream commit fd98e9419d8d622a4de91f76b306af6aa627aa9c ]

Commit 79901317ce80 ("n_tty: Don't flush buffer when closing ldisc"),
first merged in kernel release 3.10, caused the following regression
in the Gigaset M101 driver:

Before that commit, when closing the N_TTY line discipline in
preparation to switching to N_GIGASET_M101, receive_room would be
reset to a non-zero value by the call to n_tty_flush_buffer() in
n_tty's close method. With the removal of that call, receive_room
might be left at zero, blocking data reception on the serial line.

The present patch fixes that regression by setting receive_room
to an appropriate value in the ldisc open method.

Fixes: 79901317ce80 ("n_tty: Don't flush buffer when closing ldisc")
Signed-off-by: Tilman Schmidt <tilman@imap.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/gigaset/ser-gigaset.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/isdn/gigaset/ser-gigaset.c b/drivers/isdn/gigaset/ser-gigaset.c
index 8c91fd5..3ac9c41 100644
--- a/drivers/isdn/gigaset/ser-gigaset.c
+++ b/drivers/isdn/gigaset/ser-gigaset.c
@@ -524,9 +524,18 @@ gigaset_tty_open(struct tty_struct *tty)
 	cs->hw.ser->tty = tty;
 	atomic_set(&cs->hw.ser->refcnt, 1);
 	init_completion(&cs->hw.ser->dead_cmp);
-
 	tty->disc_data = cs;
 
+	/* Set the amount of data we're willing to receive per call
+	 * from the hardware driver to half of the input buffer size
+	 * to leave some reserve.
+	 * Note: We don't do flow control towards the hardware driver.
+	 * If more data is received than will fit into the input buffer,
+	 * it will be dropped and an error will be logged. This should
+	 * never happen as the device is slow and the buffer size ample.
+	 */
+	tty->receive_room = RBUFSIZE/2;
+
 	/* OK.. Initialization of the datastructures and the HW is done.. Now
 	 * startup system and notify the LL that we are ready to run
 	 */
-- 
2.1.0


From 3f7aeaae2863047a5025713653e22f7285da49f1 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 14 Jul 2015 08:10:22 +0200
Subject: [PATCH 15/21] ipv6: lock socket in ip6_datagram_connect()

[ Upstream commit 03645a11a570d52e70631838cb786eb4253eb463 ]

ip6_datagram_connect() is doing a lot of socket changes without
socket being locked.

This looks wrong, at least for udp_lib_rehash() which could corrupt
lists because of concurrent udp_sk(sk)->udp_portaddr_hash accesses.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h    |  1 +
 net/ipv4/datagram.c | 16 ++++++++++++----
 net/ipv6/datagram.c | 20 +++++++++++++++-----
 3 files changed, 28 insertions(+), 9 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index 1b1269e..553c075 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -141,6 +141,7 @@ static inline struct sk_buff *ip_finish_skb(struct sock *sk, struct flowi4 *fl4)
 }
 
 /* datagram.c */
+int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
 extern int		ip4_datagram_connect(struct sock *sk, 
 					     struct sockaddr *uaddr, int addr_len);
 
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index 5f3dc1d..291b082 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -20,7 +20,7 @@
 #include <net/route.h>
 #include <net/tcp_states.h>
 
-int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct sockaddr_in *usin = (struct sockaddr_in *) uaddr;
@@ -39,8 +39,6 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 
 	sk_dst_reset(sk);
 
-	lock_sock(sk);
-
 	oif = sk->sk_bound_dev_if;
 	saddr = inet->inet_saddr;
 	if (ipv4_is_multicast(usin->sin_addr.s_addr)) {
@@ -81,9 +79,19 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	sk_dst_set(sk, &rt->dst);
 	err = 0;
 out:
-	release_sock(sk);
 	return err;
 }
+EXPORT_SYMBOL(__ip4_datagram_connect);
+
+int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+{
+	int res;
+
+	lock_sock(sk);
+	res = __ip4_datagram_connect(sk, uaddr, addr_len);
+	release_sock(sk);
+	return res;
+}
 EXPORT_SYMBOL(ip4_datagram_connect);
 
 /* Because UDP xmit path can manipulate sk_dst_cache without holding
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 9f9ad99..da44cb4 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -40,7 +40,7 @@ static bool ipv6_mapped_addr_any(const struct in6_addr *a)
 	return ipv6_addr_v4mapped(a) && (a->s6_addr32[3] == 0);
 }
 
-int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+static int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
 	struct sockaddr_in6	*usin = (struct sockaddr_in6 *) uaddr;
 	struct inet_sock      	*inet = inet_sk(sk);
@@ -56,7 +56,7 @@ int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	if (usin->sin6_family == AF_INET) {
 		if (__ipv6_only_sock(sk))
 			return -EAFNOSUPPORT;
-		err = ip4_datagram_connect(sk, uaddr, addr_len);
+		err = __ip4_datagram_connect(sk, uaddr, addr_len);
 		goto ipv4_connected;
 	}
 
@@ -99,9 +99,9 @@ int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 		sin.sin_addr.s_addr = daddr->s6_addr32[3];
 		sin.sin_port = usin->sin6_port;
 
-		err = ip4_datagram_connect(sk,
-					   (struct sockaddr *) &sin,
-					   sizeof(sin));
+		err = __ip4_datagram_connect(sk,
+					     (struct sockaddr *) &sin,
+					     sizeof(sin));
 
 ipv4_connected:
 		if (err)
@@ -204,6 +204,16 @@ out:
 	fl6_sock_release(flowlabel);
 	return err;
 }
+
+int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+{
+	int res;
+
+	lock_sock(sk);
+	res = __ip6_datagram_connect(sk, uaddr, addr_len);
+	release_sock(sk);
+	return res;
+}
 EXPORT_SYMBOL_GPL(ip6_datagram_connect);
 
 void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err,
-- 
2.1.0


From 3b9c43b31cd829c5e9018e6dceaf66ea5411dd31 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Wed, 15 Jul 2015 21:52:51 +0200
Subject: [PATCH 16/21] bonding: fix destruction of bond with devices different
 from arphrd_ether

[ Upstream commit 06f6d1094aa0992432b1e2a0920b0ee86ccd83bf ]

When the bonding is being unloaded and the netdevice notifier is
unregistered it executes NETDEV_UNREGISTER for each device which should
remove the bond's proc entry but if the device enslaved is not of
ARPHRD_ETHER type and is in front of the bonding, it may execute
bond_release_and_destroy() first which would release the last slave and
destroy the bond device leaving the proc entry and thus we will get the
following error (with dynamic debug on for bond_netdev_event to see the
events order):
[  908.963051] eql: event: 9
[  908.963052] eql: IFF_SLAVE
[  908.963054] eql: event: 2
[  908.963056] eql: IFF_SLAVE
[  908.963058] eql: event: 6
[  908.963059] eql: IFF_SLAVE
[  908.963110] bond0: Releasing active interface eql
[  908.976168] bond0: Destroying bond bond0
[  908.976266] bond0 (unregistering): Released all slaves
[  908.984097] ------------[ cut here ]------------
[  908.984107] WARNING: CPU: 0 PID: 1787 at fs/proc/generic.c:575
remove_proc_entry+0x112/0x160()
[  908.984110] remove_proc_entry: removing non-empty directory
'net/bonding', leaking at least 'bond0'
[  908.984111] Modules linked in: bonding(-) eql(O) 9p nfsd auth_rpcgss
oid_registry nfs_acl nfs lockd grace fscache sunrpc crct10dif_pclmul
crc32_pclmul crc32c_intel ghash_clmulni_intel ppdev qxl drm_kms_helper
snd_hda_codec_generic aesni_intel ttm aes_x86_64 glue_helper pcspkr lrw
gf128mul ablk_helper cryptd snd_hda_intel virtio_console snd_hda_codec
psmouse serio_raw snd_hwdep snd_hda_core 9pnet_virtio 9pnet evdev joydev
drm virtio_balloon snd_pcm snd_timer snd soundcore i2c_piix4 i2c_core
pvpanic acpi_cpufreq parport_pc parport processor thermal_sys button
autofs4 ext4 crc16 mbcache jbd2 hid_generic usbhid hid sg sr_mod cdrom
ata_generic virtio_blk virtio_net floppy ata_piix e1000 libata ehci_pci
virtio_pci scsi_mod uhci_hcd ehci_hcd virtio_ring virtio usbcore
usb_common [last unloaded: bonding]

[  908.984168] CPU: 0 PID: 1787 Comm: rmmod Tainted: G        W  O
4.2.0-rc2+ #8
[  908.984170] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
[  908.984172]  0000000000000000 ffffffff81732d41 ffffffff81525b34
ffff8800358dfda8
[  908.984175]  ffffffff8106c521 ffff88003595af78 ffff88003595af40
ffff88003e3a4280
[  908.984178]  ffffffffa058d040 0000000000000000 ffffffff8106c59a
ffffffff8172ebd0
[  908.984181] Call Trace:
[  908.984188]  [<ffffffff81525b34>] ? dump_stack+0x40/0x50
[  908.984193]  [<ffffffff8106c521>] ? warn_slowpath_common+0x81/0xb0
[  908.984196]  [<ffffffff8106c59a>] ? warn_slowpath_fmt+0x4a/0x50
[  908.984199]  [<ffffffff81218352>] ? remove_proc_entry+0x112/0x160
[  908.984205]  [<ffffffffa05850e6>] ? bond_destroy_proc_dir+0x26/0x30
[bonding]
[  908.984208]  [<ffffffffa057540e>] ? bond_net_exit+0x8e/0xa0 [bonding]
[  908.984217]  [<ffffffff8142f407>] ? ops_exit_list.isra.4+0x37/0x70
[  908.984225]  [<ffffffff8142f52d>] ?
unregister_pernet_operations+0x8d/0xd0
[  908.984228]  [<ffffffff8142f58d>] ?
unregister_pernet_subsys+0x1d/0x30
[  908.984232]  [<ffffffffa0585269>] ? bonding_exit+0x23/0xdba [bonding]
[  908.984236]  [<ffffffff810e28ba>] ? SyS_delete_module+0x18a/0x250
[  908.984241]  [<ffffffff81086f99>] ? task_work_run+0x89/0xc0
[  908.984244]  [<ffffffff8152b732>] ?
entry_SYSCALL_64_fastpath+0x16/0x75
[  908.984247] ---[ end trace 7c006ed4abbef24b ]---

Thus remove the proc entry manually if bond_release_and_destroy() is
used. Because of the checks in bond_remove_proc_entry() it's not a
problem for a bond device to change namespaces (the bug fixed by the
Fixes commit) but since commit
f9399814927ad ("bonding: Don't allow bond devices to change network
namespaces.") that can't happen anyway.

Reported-by: Carol Soto <clsoto@linux.vnet.ibm.com>
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Fixes: a64d49c3dd50 ("bonding: Manage /proc/net/bonding/ entries from
                      the netdev events")
Tested-by: Carol L Soto <clsoto@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 5f95537..806ada9 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1917,6 +1917,7 @@ static int  bond_release_and_destroy(struct net_device *bond_dev,
 		bond_dev->priv_flags |= IFF_DISABLE_NETPOLL;
 		pr_info("%s: destroying bond %s.\n",
 			bond_dev->name, bond_dev->name);
+		bond_remove_proc_entry(bond);
 		unregister_netdevice(bond_dev);
 	}
 	return ret;
-- 
2.1.0


From 7c8576dd90bc6e857f8a90963cbbdfa85b049a40 Mon Sep 17 00:00:00 2001
From: dingtianhong <dingtianhong@huawei.com>
Date: Thu, 16 Jul 2015 16:30:02 +0800
Subject: [PATCH 17/21] bonding: correct the MAC address for "follow"
 fail_over_mac policy

[ Upstream commit a951bc1e6ba58f11df5ed5ddc41311e10f5fd20b ]

The "follow" fail_over_mac policy is useful for multiport devices that
either become confused or incur a performance penalty when multiple
ports are programmed with the same MAC address, but the same MAC
address still may happened by this steps for this policy:

1) echo +eth0 > /sys/class/net/bond0/bonding/slaves
   bond0 has the same mac address with eth0, it is MAC1.

2) echo +eth1 > /sys/class/net/bond0/bonding/slaves
   eth1 is backup, eth1 has MAC2.

3) ifconfig eth0 down
   eth1 became active slave, bond will swap MAC for eth0 and eth1,
   so eth1 has MAC1, and eth0 has MAC2.

4) ifconfig eth1 down
   there is no active slave, and eth1 still has MAC1, eth2 has MAC2.

5) ifconfig eth0 up
   the eth0 became active slave again, the bond set eth0 to MAC1.

Something wrong here, then if you set eth1 up, the eth0 and eth1 will have the same
MAC address, it will break this policy for ACTIVE_BACKUP mode.

This patch will fix this problem by finding the old active slave and
swap them MAC address before change active slave.

Signed-off-by: Ding Tianhong <dingtianhong@huawei.com>
Tested-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 806ada9..b3892b0 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -671,6 +671,22 @@ static void bond_set_dev_addr(struct net_device *bond_dev,
 	call_netdevice_notifiers(NETDEV_CHANGEADDR, bond_dev);
 }
 
+static struct slave *bond_get_old_active(struct bonding *bond,
+					 struct slave *new_active)
+{
+	struct slave *slave;
+
+	bond_for_each_slave(bond, slave) {
+		if (slave == new_active)
+			continue;
+
+		if (ether_addr_equal(bond->dev->dev_addr, slave->dev->dev_addr))
+			return slave;
+	}
+
+	return NULL;
+}
+
 /*
  * bond_do_fail_over_mac
  *
@@ -712,6 +728,9 @@ static void bond_do_fail_over_mac(struct bonding *bond,
 		write_unlock_bh(&bond->curr_slave_lock);
 		read_unlock(&bond->lock);
 
+		if (!old_active)
+			old_active = bond_get_old_active(bond, new_active);
+
 		if (old_active) {
 			memcpy(tmp_mac, new_active->dev->dev_addr, ETH_ALEN);
 			memcpy(saddr.sa_data, old_active->dev->dev_addr,
-- 
2.1.0


From c7d7863a9e6f3290b0ecc4e04627ccff88418f0a Mon Sep 17 00:00:00 2001
From: Edward Hyunkoo Jee <edjee@google.com>
Date: Tue, 21 Jul 2015 09:43:59 +0200
Subject: [PATCH 18/21] inet: frags: fix defragmented packet's IP header for
 af_packet

[ Upstream commit 0848f6428ba3a2e42db124d41ac6f548655735bf ]

When ip_frag_queue() computes positions, it assumes that the passed
sk_buff does not contain L2 headers.

However, when PACKET_FANOUT_FLAG_DEFRAG is used, IP reassembly
functions can be called on outgoing packets that contain L2 headers.

Also, IPv4 checksum is not corrected after reassembly.

Fixes: 7736d33f4262 ("packet: Add pre-defragmentation support for ipv4 fanouts.")
Signed-off-by: Edward Hyunkoo Jee <edjee@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Jerry Chu <hkchu@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_fragment.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 4c1884f..4d98a6b 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -356,7 +356,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 	ihl = ip_hdrlen(skb);
 
 	/* Determine the position of this fragment. */
-	end = offset + skb->len - ihl;
+	end = offset + skb->len - skb_network_offset(skb) - ihl;
 	err = -EINVAL;
 
 	/* Is this the final fragment? */
@@ -386,7 +386,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 		goto err;
 
 	err = -ENOMEM;
-	if (pskb_pull(skb, ihl) == NULL)
+	if (!pskb_pull(skb, skb_network_offset(skb) + ihl))
 		goto err;
 
 	err = pskb_trim_rcsum(skb, end - offset);
@@ -627,6 +627,9 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 	iph->frag_off = qp->q.max_size ? htons(IP_DF) : 0;
 	iph->tot_len = htons(len);
 	iph->tos |= ecn;
+
+	ip_send_check(iph);
+
 	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMOKS);
 	qp->q.fragments = NULL;
 	qp->q.fragments_tail = NULL;
-- 
2.1.0


From 57bd34f0357052876974c420bcf33fd4b26de42b Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 21 Jul 2015 16:33:50 +0200
Subject: [PATCH 19/21] netlink: don't hold mutex in rcu callback when
 releasing mmapd ring

[ Upstream commit 0470eb99b4721586ccac954faac3fa4472da0845 ]

Kirill A. Shutemov says:

This simple test-case trigers few locking asserts in kernel:

int main(int argc, char **argv)
{
        unsigned int block_size = 16 * 4096;
        struct nl_mmap_req req = {
                .nm_block_size          = block_size,
                .nm_block_nr            = 64,
                .nm_frame_size          = 16384,
                .nm_frame_nr            = 64 * block_size / 16384,
        };
        unsigned int ring_size;
	int fd;

	fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_GENERIC);
        if (setsockopt(fd, SOL_NETLINK, NETLINK_RX_RING, &req, sizeof(req)) < 0)
                exit(1);
        if (setsockopt(fd, SOL_NETLINK, NETLINK_TX_RING, &req, sizeof(req)) < 0)
                exit(1);

	ring_size = req.nm_block_nr * req.nm_block_size;
	mmap(NULL, 2 * ring_size, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0);
	return 0;
}

+++ exited with 0 +++
BUG: sleeping function called from invalid context at /home/kas/git/public/linux-mm/kernel/locking/mutex.c:616
in_atomic(): 1, irqs_disabled(): 0, pid: 1, name: init
3 locks held by init/1:
 #0:  (reboot_mutex){+.+...}, at: [<ffffffff81080959>] SyS_reboot+0xa9/0x220
 #1:  ((reboot_notifier_list).rwsem){.+.+..}, at: [<ffffffff8107f379>] __blocking_notifier_call_chain+0x39/0x70
 #2:  (rcu_callback){......}, at: [<ffffffff810d32e0>] rcu_do_batch.isra.49+0x160/0x10c0
Preemption disabled at:[<ffffffff8145365f>] __delay+0xf/0x20

CPU: 1 PID: 1 Comm: init Not tainted 4.1.0-00009-gbddf4c4818e0 #253
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS Debian-1.8.2-1 04/01/2014
 ffff88017b3d8000 ffff88027bc03c38 ffffffff81929ceb 0000000000000102
 0000000000000000 ffff88027bc03c68 ffffffff81085a9d 0000000000000002
 ffffffff81ca2a20 0000000000000268 0000000000000000 ffff88027bc03c98
Call Trace:
 <IRQ>  [<ffffffff81929ceb>] dump_stack+0x4f/0x7b
 [<ffffffff81085a9d>] ___might_sleep+0x16d/0x270
 [<ffffffff81085bed>] __might_sleep+0x4d/0x90
 [<ffffffff8192e96f>] mutex_lock_nested+0x2f/0x430
 [<ffffffff81932fed>] ? _raw_spin_unlock_irqrestore+0x5d/0x80
 [<ffffffff81464143>] ? __this_cpu_preempt_check+0x13/0x20
 [<ffffffff8182fc3d>] netlink_set_ring+0x1ed/0x350
 [<ffffffff8182e000>] ? netlink_undo_bind+0x70/0x70
 [<ffffffff8182fe20>] netlink_sock_destruct+0x80/0x150
 [<ffffffff817e484d>] __sk_free+0x1d/0x160
 [<ffffffff817e49a9>] sk_free+0x19/0x20
[..]

Cong Wang says:

We can't hold mutex lock in a rcu callback, [..]

Thomas Graf says:

The socket should be dead at this point. It might be simpler to
add a netlink_release_ring() function which doesn't require
locking at all.

Reported-by: "Kirill A. Shutemov" <kirill@shutemov.name>
Diagnosed-by: Cong Wang <cwang@twopensource.com>
Suggested-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 79 ++++++++++++++++++++++++++++--------------------
 1 file changed, 47 insertions(+), 32 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 5a75a1e..22e0f47 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -342,25 +342,52 @@ err1:
 	return NULL;
 }
 
+
+static void
+__netlink_set_ring(struct sock *sk, struct nl_mmap_req *req, bool tx_ring, void **pg_vec,
+		   unsigned int order)
+{
+	struct netlink_sock *nlk = nlk_sk(sk);
+	struct sk_buff_head *queue;
+	struct netlink_ring *ring;
+
+	queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue;
+	ring  = tx_ring ? &nlk->tx_ring : &nlk->rx_ring;
+
+	spin_lock_bh(&queue->lock);
+
+	ring->frame_max		= req->nm_frame_nr - 1;
+	ring->head		= 0;
+	ring->frame_size	= req->nm_frame_size;
+	ring->pg_vec_pages	= req->nm_block_size / PAGE_SIZE;
+
+	swap(ring->pg_vec_len, req->nm_block_nr);
+	swap(ring->pg_vec_order, order);
+	swap(ring->pg_vec, pg_vec);
+
+	__skb_queue_purge(queue);
+	spin_unlock_bh(&queue->lock);
+
+	WARN_ON(atomic_read(&nlk->mapped));
+
+	if (pg_vec)
+		free_pg_vec(pg_vec, order, req->nm_block_nr);
+}
+
 static int netlink_set_ring(struct sock *sk, struct nl_mmap_req *req,
-			    bool closing, bool tx_ring)
+			    bool tx_ring)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
 	struct netlink_ring *ring;
-	struct sk_buff_head *queue;
 	void **pg_vec = NULL;
 	unsigned int order = 0;
-	int err;
 
 	ring  = tx_ring ? &nlk->tx_ring : &nlk->rx_ring;
-	queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue;
 
-	if (!closing) {
-		if (atomic_read(&nlk->mapped))
-			return -EBUSY;
-		if (atomic_read(&ring->pending))
-			return -EBUSY;
-	}
+	if (atomic_read(&nlk->mapped))
+		return -EBUSY;
+	if (atomic_read(&ring->pending))
+		return -EBUSY;
 
 	if (req->nm_block_nr) {
 		if (ring->pg_vec != NULL)
@@ -392,31 +419,19 @@ static int netlink_set_ring(struct sock *sk, struct nl_mmap_req *req,
 			return -EINVAL;
 	}
 
-	err = -EBUSY;
 	mutex_lock(&nlk->pg_vec_lock);
-	if (closing || atomic_read(&nlk->mapped) == 0) {
-		err = 0;
-		spin_lock_bh(&queue->lock);
-
-		ring->frame_max		= req->nm_frame_nr - 1;
-		ring->head		= 0;
-		ring->frame_size	= req->nm_frame_size;
-		ring->pg_vec_pages	= req->nm_block_size / PAGE_SIZE;
-
-		swap(ring->pg_vec_len, req->nm_block_nr);
-		swap(ring->pg_vec_order, order);
-		swap(ring->pg_vec, pg_vec);
-
-		__skb_queue_purge(queue);
-		spin_unlock_bh(&queue->lock);
-
-		WARN_ON(atomic_read(&nlk->mapped));
+	if (atomic_read(&nlk->mapped) == 0) {
+		__netlink_set_ring(sk, req, tx_ring, pg_vec, order);
+		mutex_unlock(&nlk->pg_vec_lock);
+		return 0;
 	}
+
 	mutex_unlock(&nlk->pg_vec_lock);
 
 	if (pg_vec)
 		free_pg_vec(pg_vec, order, req->nm_block_nr);
-	return err;
+
+	return -EBUSY;
 }
 
 static void netlink_mm_open(struct vm_area_struct *vma)
@@ -885,10 +900,10 @@ static void netlink_sock_destruct(struct sock *sk)
 
 		memset(&req, 0, sizeof(req));
 		if (nlk->rx_ring.pg_vec)
-			netlink_set_ring(sk, &req, true, false);
+			__netlink_set_ring(sk, &req, false, NULL, 0);
 		memset(&req, 0, sizeof(req));
 		if (nlk->tx_ring.pg_vec)
-			netlink_set_ring(sk, &req, true, true);
+			__netlink_set_ring(sk, &req, true, NULL, 0);
 	}
 #endif /* CONFIG_NETLINK_MMAP */
 
@@ -2182,7 +2197,7 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 			return -EINVAL;
 		if (copy_from_user(&req, optval, sizeof(req)))
 			return -EFAULT;
-		err = netlink_set_ring(sk, &req, false,
+		err = netlink_set_ring(sk, &req,
 				       optname == NETLINK_TX_RING);
 		break;
 	}
-- 
2.1.0


From fef403fdacd46d3723c1a11054b7903719218c0d Mon Sep 17 00:00:00 2001
From: Jack Morgenstein <jackm@dev.mellanox.co.il>
Date: Wed, 22 Jul 2015 16:53:47 +0300
Subject: [PATCH 20/21] net/mlx4_core: Fix wrong index in propagating port
 change event to VFs

[ Upstream commit 1c1bf34951e8d17941bf708d1901c47e81b15d55 ]

The port-change event processing in procedure mlx4_eq_int() uses "slave"
as the vf_oper array index. Since the value of "slave" is the PF function
index, the result is that the PF link state is used for deciding to
propagate the event for all the VFs. The VF link state should be used,
so the VF function index should be used here.

Fixes: 948e306d7d64 ('net/mlx4: Add VF link state support')
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/eq.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index 0416c5b..3990b43 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -558,7 +558,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 						mlx4_dbg(dev, "%s: Sending MLX4_PORT_CHANGE_SUBTYPE_DOWN"
 							 " to slave: %d, port:%d\n",
 							 __func__, i, port);
-						s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state;
+						s_info = &priv->mfunc.master.vf_oper[i].vport[port].state;
 						if (IFLA_VF_LINK_STATE_AUTO == s_info->link_state)
 							mlx4_slave_event(dev, i, eqe);
 					} else {  /* IB port */
@@ -584,7 +584,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 					for (i = 0; i < dev->num_slaves; i++) {
 						if (i == mlx4_master_func_num(dev))
 							continue;
-						s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state;
+						s_info = &priv->mfunc.master.vf_oper[i].vport[port].state;
 						if (IFLA_VF_LINK_STATE_AUTO == s_info->link_state)
 							mlx4_slave_event(dev, i, eqe);
 					}
-- 
2.1.0


From 76b152b30f0fcb93f7ccfe1daa5a00403bcfa466 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Sat, 1 Aug 2015 15:33:26 +0300
Subject: [PATCH 21/21] rds: fix an integer overflow test in
 rds_info_getsockopt()

[ Upstream commit 468b732b6f76b138c0926eadf38ac88467dcd271 ]

"len" is a signed integer.  We check that len is not negative, so it
goes from zero to INT_MAX.  PAGE_SIZE is unsigned long so the comparison
is type promoted to unsigned long.  ULONG_MAX - 4095 is a higher than
INT_MAX so the condition can never be true.

I don't know if this is harmful but it seems safe to limit "len" to
INT_MAX - 4095.

Fixes: a8c879a7ee98 ('RDS: Info and stats')
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/info.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/rds/info.c b/net/rds/info.c
index 9a6b4f6..140a44a 100644
--- a/net/rds/info.c
+++ b/net/rds/info.c
@@ -176,7 +176,7 @@ int rds_info_getsockopt(struct socket *sock, int optname, char __user *optval,
 
 	/* check for all kinds of wrapping and the like */
 	start = (unsigned long)optval;
-	if (len < 0 || len + PAGE_SIZE - 1 < len || start + len < start) {
+	if (len < 0 || len > INT_MAX - PAGE_SIZE + 1 || start + len < start) {
 		ret = -EINVAL;
 		goto out;
 	}
-- 
2.1.0


[-- Attachment #3: net_314.mbox --]
[-- Type: Application/Octet-Stream, Size: 67661 bytes --]

From f9a931c149ca7d0f6370b2f4c2cb956e20778fab Mon Sep 17 00:00:00 2001
From: Angga <Hermin.Anggawijaya@alliedtelesis.co.nz>
Date: Fri, 3 Jul 2015 14:40:52 +1200
Subject: [PATCH 01/25] ipv6: Make MLD packets to only be processed locally

[ Upstream commit 4c938d22c88a9ddccc8c55a85e0430e9c62b1ac5 ]

Before commit daad151263cf ("ipv6: Make ipv6_is_mld() inline and use it
from ip6_mc_input().") MLD packets were only processed locally. After the
change, a copy of MLD packet goes through ip6_mr_input, causing
MRT6MSG_NOCACHE message to be generated to user space.

Make MLD packet only processed locally.

Fixes: daad151263cf ("ipv6: Make ipv6_is_mld() inline and use it from ip6_mc_input().")
Signed-off-by: Hermin Anggawijaya <hermin.anggawijaya@alliedtelesis.co.nz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_input.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 51d54dc..05c94d9 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -329,10 +329,10 @@ int ip6_mc_input(struct sk_buff *skb)
 				if (offset < 0)
 					goto out;
 
-				if (!ipv6_is_mld(skb, nexthdr, offset))
-					goto out;
+				if (ipv6_is_mld(skb, nexthdr, offset))
+					deliver = true;
 
-				deliver = true;
+				goto out;
 			}
 			/* unknown RA - process it normally */
 		}
-- 
2.1.0


From 39220bc3a4eab1177b0befe2055be976f0fa7e1f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 6 Jul 2015 17:13:26 +0200
Subject: [PATCH 02/25] net: graceful exit from netif_alloc_netdev_queues()

[ Upstream commit d339727c2b1a10f25e6636670ab6e1841170e328 ]

User space can crash kernel with

ip link add ifb10 numtxqueues 100000 type ifb

We must replace a BUG_ON() by proper test and return -EINVAL for
crazy values.

Fixes: 60877a32bce00 ("net: allow large number of tx queues")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 1b9e700..bfb56c0 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5951,7 +5951,8 @@ static int netif_alloc_netdev_queues(struct net_device *dev)
 	struct netdev_queue *tx;
 	size_t sz = count * sizeof(*tx);
 
-	BUG_ON(count < 1 || count > 0xffff);
+	if (count < 1 || count > 0xffff)
+		return -EINVAL;
 
 	tx = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
 	if (!tx) {
-- 
2.1.0


From 6bd018f7e71ecd0d9322f546cca453aacd23a5e1 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Tue, 7 Jul 2015 00:07:52 +0200
Subject: [PATCH 03/25] rtnetlink: verify IFLA_VF_INFO attributes before
 passing them to driver

[ Upstream commit 4f7d2cdfdde71ffe962399b7020c674050329423 ]

Jason Gunthorpe reported that since commit c02db8c6290b ("rtnetlink: make
SR-IOV VF interface symmetric"), we don't verify IFLA_VF_INFO attributes
anymore with respect to their policy, that is, ifla_vfinfo_policy[].

Before, they were part of ifla_policy[], but they have been nested since
placed under IFLA_VFINFO_LIST, that contains the attribute IFLA_VF_INFO,
which is another nested attribute for the actual VF attributes such as
IFLA_VF_MAC, IFLA_VF_VLAN, etc.

Despite the policy being split out from ifla_policy[] in this commit,
it's never applied anywhere. nla_for_each_nested() only does basic nla_ok()
testing for struct nlattr, but it doesn't know about the data context and
their requirements.

Fix, on top of Jason's initial work, does 1) parsing of the attributes
with the right policy, and 2) using the resulting parsed attribute table
from 1) instead of the nla_for_each_nested() loop (just like we used to
do when still part of ifla_policy[]).

Reference: http://thread.gmane.org/gmane.linux.network/368913
Fixes: c02db8c6290b ("rtnetlink: make SR-IOV VF interface symmetric")
Reported-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Cc: Chris Wright <chrisw@sous-sol.org>
Cc: Sucheta Chakraborty <sucheta.chakraborty@qlogic.com>
Cc: Greg Rose <gregory.v.rose@intel.com>
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Cc: Rony Efraim <ronye@mellanox.com>
Cc: Vlad Zolotarov <vladz@cloudius-systems.com>
Cc: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Cc: Thomas Graf <tgraf@suug.ch>
Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Vlad Zolotarov <vladz@cloudius-systems.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 128 ++++++++++++++++++++++++++-------------------------
 1 file changed, 65 insertions(+), 63 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 8aadd6a..465092f 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1259,10 +1259,6 @@ static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
 	[IFLA_INFO_SLAVE_DATA]	= { .type = NLA_NESTED },
 };
 
-static const struct nla_policy ifla_vfinfo_policy[IFLA_VF_INFO_MAX+1] = {
-	[IFLA_VF_INFO]		= { .type = NLA_NESTED },
-};
-
 static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = {
 	[IFLA_VF_MAC]		= { .len = sizeof(struct ifla_vf_mac) },
 	[IFLA_VF_VLAN]		= { .len = sizeof(struct ifla_vf_vlan) },
@@ -1336,67 +1332,66 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[])
 	return 0;
 }
 
-static int do_setvfinfo(struct net_device *dev, struct nlattr *attr)
+static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
 {
-	int rem, err = -EINVAL;
-	struct nlattr *vf;
 	const struct net_device_ops *ops = dev->netdev_ops;
+	int err = -EINVAL;
 
-	nla_for_each_nested(vf, attr, rem) {
-		switch (nla_type(vf)) {
-		case IFLA_VF_MAC: {
-			struct ifla_vf_mac *ivm;
-			ivm = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_mac)
-				err = ops->ndo_set_vf_mac(dev, ivm->vf,
-							  ivm->mac);
-			break;
-		}
-		case IFLA_VF_VLAN: {
-			struct ifla_vf_vlan *ivv;
-			ivv = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_vlan)
-				err = ops->ndo_set_vf_vlan(dev, ivv->vf,
-							   ivv->vlan,
-							   ivv->qos);
-			break;
-		}
-		case IFLA_VF_TX_RATE: {
-			struct ifla_vf_tx_rate *ivt;
-			ivt = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_tx_rate)
-				err = ops->ndo_set_vf_tx_rate(dev, ivt->vf,
-							      ivt->rate);
-			break;
-		}
-		case IFLA_VF_SPOOFCHK: {
-			struct ifla_vf_spoofchk *ivs;
-			ivs = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_spoofchk)
-				err = ops->ndo_set_vf_spoofchk(dev, ivs->vf,
-							       ivs->setting);
-			break;
-		}
-		case IFLA_VF_LINK_STATE: {
-			struct ifla_vf_link_state *ivl;
-			ivl = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_link_state)
-				err = ops->ndo_set_vf_link_state(dev, ivl->vf,
-								 ivl->link_state);
-			break;
-		}
-		default:
-			err = -EINVAL;
-			break;
-		}
-		if (err)
-			break;
+	if (tb[IFLA_VF_MAC]) {
+		struct ifla_vf_mac *ivm = nla_data(tb[IFLA_VF_MAC]);
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_mac)
+			err = ops->ndo_set_vf_mac(dev, ivm->vf,
+						  ivm->mac);
+		if (err < 0)
+			return err;
+	}
+
+	if (tb[IFLA_VF_VLAN]) {
+		struct ifla_vf_vlan *ivv = nla_data(tb[IFLA_VF_VLAN]);
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_vlan)
+			err = ops->ndo_set_vf_vlan(dev, ivv->vf, ivv->vlan,
+						   ivv->qos);
+		if (err < 0)
+			return err;
+	}
+
+	if (tb[IFLA_VF_TX_RATE]) {
+		struct ifla_vf_tx_rate *ivt = nla_data(tb[IFLA_VF_TX_RATE]);
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_tx_rate)
+			err = ops->ndo_set_vf_tx_rate(dev, ivt->vf,
+						      ivt->rate);
+		if (err < 0)
+			return err;
 	}
+
+	if (tb[IFLA_VF_SPOOFCHK]) {
+		struct ifla_vf_spoofchk *ivs = nla_data(tb[IFLA_VF_SPOOFCHK]);
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_spoofchk)
+			err = ops->ndo_set_vf_spoofchk(dev, ivs->vf,
+						       ivs->setting);
+		if (err < 0)
+			return err;
+	}
+
+	if (tb[IFLA_VF_LINK_STATE]) {
+		struct ifla_vf_link_state *ivl = nla_data(tb[IFLA_VF_LINK_STATE]);
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_link_state)
+			err = ops->ndo_set_vf_link_state(dev, ivl->vf,
+							 ivl->link_state);
+		if (err < 0)
+			return err;
+	}
+
 	return err;
 }
 
@@ -1579,14 +1574,21 @@ static int do_setlink(const struct sk_buff *skb,
 	}
 
 	if (tb[IFLA_VFINFO_LIST]) {
+		struct nlattr *vfinfo[IFLA_VF_MAX + 1];
 		struct nlattr *attr;
 		int rem;
+
 		nla_for_each_nested(attr, tb[IFLA_VFINFO_LIST], rem) {
-			if (nla_type(attr) != IFLA_VF_INFO) {
+			if (nla_type(attr) != IFLA_VF_INFO ||
+			    nla_len(attr) < NLA_HDRLEN) {
 				err = -EINVAL;
 				goto errout;
 			}
-			err = do_setvfinfo(dev, attr);
+			err = nla_parse_nested(vfinfo, IFLA_VF_MAX, attr,
+					       ifla_vf_policy);
+			if (err < 0)
+				goto errout;
+			err = do_setvfinfo(dev, vfinfo);
 			if (err < 0)
 				goto errout;
 			modified = 1;
-- 
2.1.0


From 125c4651b222f4aea24539919ee1ad7b7e42a0a0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timo=20Ter=C3=A4s?= <timo.teras@iki.fi>
Date: Tue, 7 Jul 2015 08:34:13 +0300
Subject: [PATCH 04/25] ip_tunnel: fix ipv4 pmtu check to honor inner ip header
 df
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit fc24f2b2094366da8786f59f2606307e934cea17 ]

Frag needed should be sent only if the inner header asked
to not fragment. Currently fragmentation is broken if the
tunnel has df set, but df was not asked in the original
packet. The tunnel's df needs to be still checked to update
internally the pmtu cache.

Commit 23a3647bc4f93bac broke it, and this commit fixes
the ipv4 df check back to the way it was.

Fixes: 23a3647bc4f93bac ("ip_tunnels: Use skb-len to PMTU check.")
Cc: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: Timo Teräs <timo.teras@iki.fi>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_tunnel.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 0a4af09..2d4be69 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -484,7 +484,8 @@ drop:
 EXPORT_SYMBOL_GPL(ip_tunnel_rcv);
 
 static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
-			    struct rtable *rt, __be16 df)
+			    struct rtable *rt, __be16 df,
+			    const struct iphdr *inner_iph)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	int pkt_size = skb->len - tunnel->hlen - dev->hard_header_len;
@@ -501,7 +502,8 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
 
 	if (skb->protocol == htons(ETH_P_IP)) {
 		if (!skb_is_gso(skb) &&
-		    (df & htons(IP_DF)) && mtu < pkt_size) {
+		    (inner_iph->frag_off & htons(IP_DF)) &&
+		    mtu < pkt_size) {
 			memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
 			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
 			return -E2BIG;
@@ -632,7 +634,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		goto tx_error;
 	}
 
-	if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off)) {
+	if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off, inner_iph)) {
 		ip_rt_put(rt);
 		goto tx_error;
 	}
-- 
2.1.0


From 25171735d807be7da0ab5e14be9ae0db5f1a3f25 Mon Sep 17 00:00:00 2001
From: Stephen Smalley <sds@tycho.nsa.gov>
Date: Tue, 7 Jul 2015 09:43:45 -0400
Subject: [PATCH 05/25] net/tipc: initialize security state for new connection
 socket

[ Upstream commit fdd75ea8df370f206a8163786e7470c1277a5064 ]

Calling connect() with an AF_TIPC socket would trigger a series
of error messages from SELinux along the lines of:
SELinux: Invalid class 0
type=AVC msg=audit(1434126658.487:34500): avc:  denied  { <unprintable> }
  for pid=292 comm="kworker/u16:5" scontext=system_u:system_r:kernel_t:s0
  tcontext=system_u:object_r:unlabeled_t:s0 tclass=<unprintable>
  permissive=0

This was due to a failure to initialize the security state of the new
connection sock by the tipc code, leaving it with junk in the security
class field and an unlabeled secid.  Add a call to security_sk_clone()
to inherit the security state from the parent socket.

Reported-by: Tim Shearer <tim.shearer@overturenetworks.com>
Signed-off-by: Stephen Smalley <sds@tycho.nsa.gov>
Acked-by: Paul Moore <paul@paul-moore.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/socket.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 0ed0eaa..830e40b 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1681,6 +1681,7 @@ static int accept(struct socket *sock, struct socket *new_sock, int flags)
 	res = tipc_sk_create(sock_net(sock->sk), new_sock, 0, 1);
 	if (res)
 		goto exit;
+	security_sk_clone(sock->sk, new_sock->sk);
 
 	new_sk = new_sock->sk;
 	new_tsock = tipc_sk(new_sk);
-- 
2.1.0


From 49f9e8baee1df39b843e95944908dd9d825a5aeb Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <razor@blackwall.org>
Date: Tue, 7 Jul 2015 15:55:56 +0200
Subject: [PATCH 06/25] bridge: mdb: zero out the local br_ip variable before
 use

[ Upstream commit f1158b74e54f2e2462ba5e2f45a118246d9d5b43 ]

Since commit b0e9a30dd669 ("bridge: Add vlan id to multicast groups")
there's a check in br_ip_equal() for a matching vlan id, but the mdb
functions were not modified to use (or at least zero it) so when an
entry was added it would have a garbage vlan id (from the local br_ip
variable in __br_mdb_add/del) and this would prevent it from being
matched and also deleted. So zero out the whole local ip var to protect
ourselves from future changes and also to fix the current bug, since
there's no vlan id support in the mdb uapi - use always vlan id 0.
Example before patch:
root@debian:~# bridge mdb add dev br0 port eth1 grp 239.0.0.1 permanent
root@debian:~# bridge mdb
dev br0 port eth1 grp 239.0.0.1 permanent
root@debian:~# bridge mdb del dev br0 port eth1 grp 239.0.0.1 permanent
RTNETLINK answers: Invalid argument

After patch:
root@debian:~# bridge mdb add dev br0 port eth1 grp 239.0.0.1 permanent
root@debian:~# bridge mdb
dev br0 port eth1 grp 239.0.0.1 permanent
root@debian:~# bridge mdb del dev br0 port eth1 grp 239.0.0.1 permanent
root@debian:~# bridge mdb

Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Fixes: b0e9a30dd669 ("bridge: Add vlan id to multicast groups")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_mdb.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index b7b1914..13421bf 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -370,6 +370,7 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br,
 	if (!p || p->br != br || p->state == BR_STATE_DISABLED)
 		return -EINVAL;
 
+	memset(&ip, 0, sizeof(ip));
 	ip.proto = entry->addr.proto;
 	if (ip.proto == htons(ETH_P_IP))
 		ip.u.ip4 = entry->addr.u.ip4;
@@ -416,6 +417,7 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry)
 	if (!netif_running(br->dev) || br->multicast_disabled)
 		return -EINVAL;
 
+	memset(&ip, 0, sizeof(ip));
 	ip.proto = entry->addr.proto;
 	if (ip.proto == htons(ETH_P_IP)) {
 		if (timer_pending(&br->ip4_querier.timer))
-- 
2.1.0


From d70c2a520682b2278971c58c6632da53d63caa4a Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Wed, 8 Jul 2015 21:42:11 +0200
Subject: [PATCH 07/25] net: pktgen: fix race between pktgen_thread_worker()
 and kthread_stop()

[ Upstream commit fecdf8be2d91e04b0a9a4f79ff06499a36f5d14f ]

pktgen_thread_worker() is obviously racy, kthread_stop() can come
between the kthread_should_stop() check and set_current_state().

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Reported-by: Jan Stancek <jstancek@redhat.com>
Reported-by: Marcelo Leitner <mleitner@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/pktgen.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index ca68d32..dbd797a 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -3464,8 +3464,10 @@ static int pktgen_thread_worker(void *arg)
 	pktgen_rem_thread(t);
 
 	/* Wait for kthread_stop */
-	while (!kthread_should_stop()) {
+	for (;;) {
 		set_current_state(TASK_INTERRUPTIBLE);
+		if (kthread_should_stop())
+			break;
 		schedule();
 	}
 	__set_current_state(TASK_RUNNING);
-- 
2.1.0


From 43f470def883d1e9e16d40d66568bf392fbd871a Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Thu, 9 Jul 2015 09:59:09 +0300
Subject: [PATCH 08/25] net: do not process device backlog during
 unregistration

[ Upstream commit e9e4dd3267d0c5234c5c0f47440456b10875dec9 ]

commit 381c759d9916 ("ipv4: Avoid crashing in ip_error")
fixes a problem where processed packet comes from device
with destroyed inetdev (dev->ip_ptr). This is not expected
because inetdev_destroy is called in NETDEV_UNREGISTER
phase and packets should not be processed after
dev_close_many() and synchronize_net(). Above fix is still
required because inetdev_destroy can be called for other
reasons. But it shows the real problem: backlog can keep
packets for long time and they do not hold reference to
device. Such packets are then delivered to upper levels
at the same time when device is unregistered.
Calling flush_backlog after NETDEV_UNREGISTER_FINAL still
accounts all packets from backlog but before that some packets
continue to be delivered to upper levels long after the
synchronize_net call which is supposed to wait the last
ones. Also, as Eric pointed out, processed packets, mostly
from other devices, can continue to add new packets to backlog.

Fix the problem by moving flush_backlog early, after the
device driver is stopped and before the synchronize_net() call.
Then use netif_running check to make sure we do not add more
packets to backlog. We have to do it in enqueue_to_backlog
context when the local IRQ is disabled. As result, after the
flush_backlog and synchronize_net sequence all packets
should be accounted.

Thanks to Eric W. Biederman for the test script and his
valuable feedback!

Reported-by: Vittorio Gambaletta <linuxbugs@vittgam.net>
Fixes: 6e583ce5242f ("net: eliminate refcounting in backlog queue")
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index bfb56c0..1fe07b2 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3214,6 +3214,8 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
 	local_irq_save(flags);
 
 	rps_lock(sd);
+	if (!netif_running(skb->dev))
+		goto drop;
 	qlen = skb_queue_len(&sd->input_pkt_queue);
 	if (qlen <= netdev_max_backlog && !skb_flow_limit(skb, qlen)) {
 		if (skb_queue_len(&sd->input_pkt_queue)) {
@@ -3235,6 +3237,7 @@ enqueue:
 		goto enqueue;
 	}
 
+drop:
 	sd->dropped++;
 	rps_unlock(sd);
 
@@ -5694,6 +5697,7 @@ static void rollback_registered_many(struct list_head *head)
 		unlist_netdevice(dev);
 
 		dev->reg_state = NETREG_UNREGISTERING;
+		on_each_cpu(flush_backlog, dev, 1);
 	}
 
 	synchronize_net();
@@ -6310,8 +6314,6 @@ void netdev_run_todo(void)
 
 		dev->reg_state = NETREG_UNREGISTERED;
 
-		on_each_cpu(flush_backlog, dev, 1);
-
 		netdev_wait_allrefs(dev);
 
 		/* paranoia */
-- 
2.1.0


From e5c28ee2e29f15b344e09d7bfe08ebf25f4a9320 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Thu, 9 Jul 2015 09:59:10 +0300
Subject: [PATCH 09/25] net: call rcu_read_lock early in process_backlog

[ Upstream commit 2c17d27c36dcce2b6bf689f41a46b9e909877c21 ]

Incoming packet should be either in backlog queue or
in RCU read-side section. Otherwise, the final sequence of
flush_backlog() and synchronize_net() may miss packets
that can run without device reference:

CPU 1                  CPU 2
                       skb->dev: no reference
                       process_backlog:__skb_dequeue
                       process_backlog:local_irq_enable

on_each_cpu for
flush_backlog =>       IPI(hardirq): flush_backlog
                       - packet not found in backlog

                       CPU delayed ...
synchronize_net
- no ongoing RCU
read-side sections

netdev_run_todo,
rcu_barrier: no
ongoing callbacks
                       __netif_receive_skb_core:rcu_read_lock
                       - too late
free dev
                       process packet for freed dev

Fixes: 6e583ce5242f ("net: eliminate refcounting in backlog queue")
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 29 ++++++++++++++---------------
 1 file changed, 14 insertions(+), 15 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 1fe07b2..ae3260f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3554,8 +3554,6 @@ static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc)
 
 	pt_prev = NULL;
 
-	rcu_read_lock();
-
 another_round:
 	skb->skb_iif = skb->dev->ifindex;
 
@@ -3565,7 +3563,7 @@ another_round:
 	    skb->protocol == cpu_to_be16(ETH_P_8021AD)) {
 		skb = skb_vlan_untag(skb);
 		if (unlikely(!skb))
-			goto unlock;
+			goto out;
 	}
 
 #ifdef CONFIG_NET_CLS_ACT
@@ -3590,7 +3588,7 @@ skip_taps:
 #ifdef CONFIG_NET_CLS_ACT
 	skb = handle_ing(skb, &pt_prev, &ret, orig_dev);
 	if (!skb)
-		goto unlock;
+		goto out;
 ncls:
 #endif
 
@@ -3605,7 +3603,7 @@ ncls:
 		if (vlan_do_receive(&skb))
 			goto another_round;
 		else if (unlikely(!skb))
-			goto unlock;
+			goto out;
 	}
 
 	rx_handler = rcu_dereference(skb->dev->rx_handler);
@@ -3617,7 +3615,7 @@ ncls:
 		switch (rx_handler(&skb)) {
 		case RX_HANDLER_CONSUMED:
 			ret = NET_RX_SUCCESS;
-			goto unlock;
+			goto out;
 		case RX_HANDLER_ANOTHER:
 			goto another_round;
 		case RX_HANDLER_EXACT:
@@ -3669,8 +3667,6 @@ drop:
 		ret = NET_RX_DROP;
 	}
 
-unlock:
-	rcu_read_unlock();
 out:
 	return ret;
 }
@@ -3702,29 +3698,30 @@ static int __netif_receive_skb(struct sk_buff *skb)
 
 static int netif_receive_skb_internal(struct sk_buff *skb)
 {
+	int ret;
+
 	net_timestamp_check(netdev_tstamp_prequeue, skb);
 
 	if (skb_defer_rx_timestamp(skb))
 		return NET_RX_SUCCESS;
 
+	rcu_read_lock();
+
 #ifdef CONFIG_RPS
 	if (static_key_false(&rps_needed)) {
 		struct rps_dev_flow voidflow, *rflow = &voidflow;
-		int cpu, ret;
-
-		rcu_read_lock();
-
-		cpu = get_rps_cpu(skb->dev, skb, &rflow);
+		int cpu = get_rps_cpu(skb->dev, skb, &rflow);
 
 		if (cpu >= 0) {
 			ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
 			rcu_read_unlock();
 			return ret;
 		}
-		rcu_read_unlock();
 	}
 #endif
-	return __netif_receive_skb(skb);
+	ret = __netif_receive_skb(skb);
+	rcu_read_unlock();
+	return ret;
 }
 
 /**
@@ -4185,8 +4182,10 @@ static int process_backlog(struct napi_struct *napi, int quota)
 		unsigned int qlen;
 
 		while ((skb = __skb_dequeue(&sd->process_queue))) {
+			rcu_read_lock();
 			local_irq_enable();
 			__netif_receive_skb(skb);
+			rcu_read_unlock();
 			local_irq_disable();
 			input_queue_head_incr(sd);
 			if (++work >= quota) {
-- 
2.1.0


From 1db74fcfe8820cc9fd2b39537006e2959eb10b20 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Mon, 13 Jul 2015 16:04:13 +0800
Subject: [PATCH 10/25] net: Clone skb before setting peeked flag

[ Upstream commit 738ac1ebb96d02e0d23bc320302a6ea94c612dec ]

Shared skbs must not be modified and this is crucial for broadcast
and/or multicast paths where we use it as an optimisation to avoid
unnecessary cloning.

The function skb_recv_datagram breaks this rule by setting peeked
without cloning the skb first.  This causes funky races which leads
to double-free.

This patch fixes this by cloning the skb and replacing the skb
in the list when setting skb->peeked.

Fixes: a59322be07c9 ("[UDP]: Only increment counter on first peek/recv")
Reported-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/datagram.c | 41 ++++++++++++++++++++++++++++++++++++++---
 1 file changed, 38 insertions(+), 3 deletions(-)

diff --git a/net/core/datagram.c b/net/core/datagram.c
index a16ed7b..7f6f929 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -130,6 +130,35 @@ out_noerr:
 	goto out;
 }
 
+static int skb_set_peeked(struct sk_buff *skb)
+{
+	struct sk_buff *nskb;
+
+	if (skb->peeked)
+		return 0;
+
+	/* We have to unshare an skb before modifying it. */
+	if (!skb_shared(skb))
+		goto done;
+
+	nskb = skb_clone(skb, GFP_ATOMIC);
+	if (!nskb)
+		return -ENOMEM;
+
+	skb->prev->next = nskb;
+	skb->next->prev = nskb;
+	nskb->prev = skb->prev;
+	nskb->next = skb->next;
+
+	consume_skb(skb);
+	skb = nskb;
+
+done:
+	skb->peeked = 1;
+
+	return 0;
+}
+
 /**
  *	__skb_recv_datagram - Receive a datagram skbuff
  *	@sk: socket
@@ -164,7 +193,9 @@ out_noerr:
 struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
 				    int *peeked, int *off, int *err)
 {
+	struct sk_buff_head *queue = &sk->sk_receive_queue;
 	struct sk_buff *skb, *last;
+	unsigned long cpu_flags;
 	long timeo;
 	/*
 	 * Caller is allowed not to check sk->sk_err before skb_recv_datagram()
@@ -183,8 +214,6 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
 		 * Look at current nfs client by the way...
 		 * However, this function was correct in any case. 8)
 		 */
-		unsigned long cpu_flags;
-		struct sk_buff_head *queue = &sk->sk_receive_queue;
 		int _off = *off;
 
 		last = (struct sk_buff *)queue;
@@ -198,7 +227,11 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
 					_off -= skb->len;
 					continue;
 				}
-				skb->peeked = 1;
+
+				error = skb_set_peeked(skb);
+				if (error)
+					goto unlock_err;
+
 				atomic_inc(&skb->users);
 			} else
 				__skb_unlink(skb, queue);
@@ -222,6 +255,8 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
 
 	return NULL;
 
+unlock_err:
+	spin_unlock_irqrestore(&queue->lock, cpu_flags);
 no_packet:
 	*err = error;
 	return NULL;
-- 
2.1.0


From 5142d102097e9356469812fdc7bdc31fcdd1e237 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Mon, 13 Jul 2015 20:01:42 +0800
Subject: [PATCH 11/25] net: Fix skb csum races when peeking

[ Upstream commit 89c22d8c3b278212eef6a8cc66b570bc840a6f5a ]

When we calculate the checksum on the recv path, we store the
result in the skb as an optimisation in case we need the checksum
again down the line.

This is in fact bogus for the MSG_PEEK case as this is done without
any locking.  So multiple threads can peek and then store the result
to the same skb, potentially resulting in bogus skb states.

This patch fixes this by only storing the result if the skb is not
shared.  This preserves the optimisations for the few cases where
it can be done safely due to locking or other reasons, e.g., SIOCINQ.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/datagram.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/datagram.c b/net/core/datagram.c
index 7f6f929..32a0087 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -777,7 +777,8 @@ __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len)
 	if (likely(!sum)) {
 		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE))
 			netdev_rx_csum_fault(skb->dev);
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		if (!skb_shared(skb))
+			skb->ip_summed = CHECKSUM_UNNECESSARY;
 	}
 	return sum;
 }
-- 
2.1.0


From cca04cae3608285f5bb46ed0816fd7ccd4266223 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Tue, 4 Aug 2015 15:42:47 +0800
Subject: [PATCH 12/25] net: Fix skb_set_peeked use-after-free bug

[ Upstream commit a0a2a6602496a45ae838a96db8b8173794b5d398 ]

The commit 738ac1ebb96d02e0d23bc320302a6ea94c612dec ("net: Clone
skb before setting peeked flag") introduced a use-after-free bug
in skb_recv_datagram.  This is because skb_set_peeked may create
a new skb and free the existing one.  As it stands the caller will
continue to use the old freed skb.

This patch fixes it by making skb_set_peeked return the new skb
(or the old one if unchanged).

Fixes: 738ac1ebb96d ("net: Clone skb before setting peeked flag")
Reported-by: Brenden Blanco <bblanco@plumgrid.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Tested-by: Brenden Blanco <bblanco@plumgrid.com>
Reviewed-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/datagram.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/net/core/datagram.c b/net/core/datagram.c
index 32a0087..13bc7da 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -130,12 +130,12 @@ out_noerr:
 	goto out;
 }
 
-static int skb_set_peeked(struct sk_buff *skb)
+static struct sk_buff *skb_set_peeked(struct sk_buff *skb)
 {
 	struct sk_buff *nskb;
 
 	if (skb->peeked)
-		return 0;
+		return skb;
 
 	/* We have to unshare an skb before modifying it. */
 	if (!skb_shared(skb))
@@ -143,7 +143,7 @@ static int skb_set_peeked(struct sk_buff *skb)
 
 	nskb = skb_clone(skb, GFP_ATOMIC);
 	if (!nskb)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	skb->prev->next = nskb;
 	skb->next->prev = nskb;
@@ -156,7 +156,7 @@ static int skb_set_peeked(struct sk_buff *skb)
 done:
 	skb->peeked = 1;
 
-	return 0;
+	return skb;
 }
 
 /**
@@ -228,8 +228,9 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
 					continue;
 				}
 
-				error = skb_set_peeked(skb);
-				if (error)
+				skb = skb_set_peeked(skb);
+				error = PTR_ERR(skb);
+				if (IS_ERR(skb))
 					goto unlock_err;
 
 				atomic_inc(&skb->users);
-- 
2.1.0


From 3f9aec33c50926e36840e7503dc5b981dd981de8 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Mon, 13 Jul 2015 06:36:19 -0700
Subject: [PATCH 13/25] bridge: mdb: fix double add notification

[ Upstream commit 5ebc784625ea68a9570d1f70557e7932988cd1b4 ]

Since the mdb add/del code was introduced there have been 2 br_mdb_notify
calls when doing br_mdb_add() resulting in 2 notifications on each add.

Example:
 Command: bridge mdb add dev br0 port eth1 grp 239.0.0.1 permanent
 Before patch:
 root@debian:~# bridge monitor all
 [MDB]dev br0 port eth1 grp 239.0.0.1 permanent
 [MDB]dev br0 port eth1 grp 239.0.0.1 permanent

 After patch:
 root@debian:~# bridge monitor all
 [MDB]dev br0 port eth1 grp 239.0.0.1 permanent

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Fixes: cfd567543590 ("bridge: add support of adding and deleting mdb entries")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_mdb.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index 13421bf..27cf128 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -347,7 +347,6 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
 		return -ENOMEM;
 	rcu_assign_pointer(*pp, p);
 
-	br_mdb_notify(br->dev, port, group, RTM_NEWMDB);
 	return 0;
 }
 
-- 
2.1.0


From d6c8ba17f3657f30cc68cf741805fc19da405387 Mon Sep 17 00:00:00 2001
From: Tilman Schmidt <tilman@imap.cc>
Date: Tue, 14 Jul 2015 00:37:13 +0200
Subject: [PATCH 14/25] isdn/gigaset: reset tty->receive_room when attaching
 ser_gigaset

[ Upstream commit fd98e9419d8d622a4de91f76b306af6aa627aa9c ]

Commit 79901317ce80 ("n_tty: Don't flush buffer when closing ldisc"),
first merged in kernel release 3.10, caused the following regression
in the Gigaset M101 driver:

Before that commit, when closing the N_TTY line discipline in
preparation to switching to N_GIGASET_M101, receive_room would be
reset to a non-zero value by the call to n_tty_flush_buffer() in
n_tty's close method. With the removal of that call, receive_room
might be left at zero, blocking data reception on the serial line.

The present patch fixes that regression by setting receive_room
to an appropriate value in the ldisc open method.

Fixes: 79901317ce80 ("n_tty: Don't flush buffer when closing ldisc")
Signed-off-by: Tilman Schmidt <tilman@imap.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/gigaset/ser-gigaset.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/isdn/gigaset/ser-gigaset.c b/drivers/isdn/gigaset/ser-gigaset.c
index 8c91fd5..3ac9c41 100644
--- a/drivers/isdn/gigaset/ser-gigaset.c
+++ b/drivers/isdn/gigaset/ser-gigaset.c
@@ -524,9 +524,18 @@ gigaset_tty_open(struct tty_struct *tty)
 	cs->hw.ser->tty = tty;
 	atomic_set(&cs->hw.ser->refcnt, 1);
 	init_completion(&cs->hw.ser->dead_cmp);
-
 	tty->disc_data = cs;
 
+	/* Set the amount of data we're willing to receive per call
+	 * from the hardware driver to half of the input buffer size
+	 * to leave some reserve.
+	 * Note: We don't do flow control towards the hardware driver.
+	 * If more data is received than will fit into the input buffer,
+	 * it will be dropped and an error will be logged. This should
+	 * never happen as the device is slow and the buffer size ample.
+	 */
+	tty->receive_room = RBUFSIZE/2;
+
 	/* OK.. Initialization of the datastructures and the HW is done.. Now
 	 * startup system and notify the LL that we are ready to run
 	 */
-- 
2.1.0


From 7dc1f3296953ff00e690883c70737c94aee6bbd9 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 14 Jul 2015 08:10:22 +0200
Subject: [PATCH 15/25] ipv6: lock socket in ip6_datagram_connect()

[ Upstream commit 03645a11a570d52e70631838cb786eb4253eb463 ]

ip6_datagram_connect() is doing a lot of socket changes without
socket being locked.

This looks wrong, at least for udp_lib_rehash() which could corrupt
lists because of concurrent udp_sk(sk)->udp_portaddr_hash accesses.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h    |  1 +
 net/ipv4/datagram.c | 16 ++++++++++++----
 net/ipv6/datagram.c | 20 +++++++++++++++-----
 3 files changed, 28 insertions(+), 9 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index 5128fa7..476bab2 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -154,6 +154,7 @@ static inline __u8 get_rtconn_flags(struct ipcm_cookie* ipc, struct sock* sk)
 }
 
 /* datagram.c */
+int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
 int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
 
 void ip4_datagram_release_cb(struct sock *sk);
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index a3095fd..f0c307c 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -20,7 +20,7 @@
 #include <net/route.h>
 #include <net/tcp_states.h>
 
-int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct sockaddr_in *usin = (struct sockaddr_in *) uaddr;
@@ -39,8 +39,6 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 
 	sk_dst_reset(sk);
 
-	lock_sock(sk);
-
 	oif = sk->sk_bound_dev_if;
 	saddr = inet->inet_saddr;
 	if (ipv4_is_multicast(usin->sin_addr.s_addr)) {
@@ -81,9 +79,19 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	sk_dst_set(sk, &rt->dst);
 	err = 0;
 out:
-	release_sock(sk);
 	return err;
 }
+EXPORT_SYMBOL(__ip4_datagram_connect);
+
+int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+{
+	int res;
+
+	lock_sock(sk);
+	res = __ip4_datagram_connect(sk, uaddr, addr_len);
+	release_sock(sk);
+	return res;
+}
 EXPORT_SYMBOL(ip4_datagram_connect);
 
 /* Because UDP xmit path can manipulate sk_dst_cache without holding
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 841cfa2..6b89b2a 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -40,7 +40,7 @@ static bool ipv6_mapped_addr_any(const struct in6_addr *a)
 	return ipv6_addr_v4mapped(a) && (a->s6_addr32[3] == 0);
 }
 
-int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+static int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
 	struct sockaddr_in6	*usin = (struct sockaddr_in6 *) uaddr;
 	struct inet_sock      	*inet = inet_sk(sk);
@@ -56,7 +56,7 @@ int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	if (usin->sin6_family == AF_INET) {
 		if (__ipv6_only_sock(sk))
 			return -EAFNOSUPPORT;
-		err = ip4_datagram_connect(sk, uaddr, addr_len);
+		err = __ip4_datagram_connect(sk, uaddr, addr_len);
 		goto ipv4_connected;
 	}
 
@@ -98,9 +98,9 @@ int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 		sin.sin_addr.s_addr = daddr->s6_addr32[3];
 		sin.sin_port = usin->sin6_port;
 
-		err = ip4_datagram_connect(sk,
-					   (struct sockaddr *) &sin,
-					   sizeof(sin));
+		err = __ip4_datagram_connect(sk,
+					     (struct sockaddr *) &sin,
+					     sizeof(sin));
 
 ipv4_connected:
 		if (err)
@@ -203,6 +203,16 @@ out:
 	fl6_sock_release(flowlabel);
 	return err;
 }
+
+int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+{
+	int res;
+
+	lock_sock(sk);
+	res = __ip6_datagram_connect(sk, uaddr, addr_len);
+	release_sock(sk);
+	return res;
+}
 EXPORT_SYMBOL_GPL(ip6_datagram_connect);
 
 int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr *uaddr,
-- 
2.1.0


From af81da77aa0c965b042c95f306cfa343dd50cf91 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Wed, 15 Jul 2015 21:52:51 +0200
Subject: [PATCH 16/25] bonding: fix destruction of bond with devices different
 from arphrd_ether

[ Upstream commit 06f6d1094aa0992432b1e2a0920b0ee86ccd83bf ]

When the bonding is being unloaded and the netdevice notifier is
unregistered it executes NETDEV_UNREGISTER for each device which should
remove the bond's proc entry but if the device enslaved is not of
ARPHRD_ETHER type and is in front of the bonding, it may execute
bond_release_and_destroy() first which would release the last slave and
destroy the bond device leaving the proc entry and thus we will get the
following error (with dynamic debug on for bond_netdev_event to see the
events order):
[  908.963051] eql: event: 9
[  908.963052] eql: IFF_SLAVE
[  908.963054] eql: event: 2
[  908.963056] eql: IFF_SLAVE
[  908.963058] eql: event: 6
[  908.963059] eql: IFF_SLAVE
[  908.963110] bond0: Releasing active interface eql
[  908.976168] bond0: Destroying bond bond0
[  908.976266] bond0 (unregistering): Released all slaves
[  908.984097] ------------[ cut here ]------------
[  908.984107] WARNING: CPU: 0 PID: 1787 at fs/proc/generic.c:575
remove_proc_entry+0x112/0x160()
[  908.984110] remove_proc_entry: removing non-empty directory
'net/bonding', leaking at least 'bond0'
[  908.984111] Modules linked in: bonding(-) eql(O) 9p nfsd auth_rpcgss
oid_registry nfs_acl nfs lockd grace fscache sunrpc crct10dif_pclmul
crc32_pclmul crc32c_intel ghash_clmulni_intel ppdev qxl drm_kms_helper
snd_hda_codec_generic aesni_intel ttm aes_x86_64 glue_helper pcspkr lrw
gf128mul ablk_helper cryptd snd_hda_intel virtio_console snd_hda_codec
psmouse serio_raw snd_hwdep snd_hda_core 9pnet_virtio 9pnet evdev joydev
drm virtio_balloon snd_pcm snd_timer snd soundcore i2c_piix4 i2c_core
pvpanic acpi_cpufreq parport_pc parport processor thermal_sys button
autofs4 ext4 crc16 mbcache jbd2 hid_generic usbhid hid sg sr_mod cdrom
ata_generic virtio_blk virtio_net floppy ata_piix e1000 libata ehci_pci
virtio_pci scsi_mod uhci_hcd ehci_hcd virtio_ring virtio usbcore
usb_common [last unloaded: bonding]

[  908.984168] CPU: 0 PID: 1787 Comm: rmmod Tainted: G        W  O
4.2.0-rc2+ #8
[  908.984170] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
[  908.984172]  0000000000000000 ffffffff81732d41 ffffffff81525b34
ffff8800358dfda8
[  908.984175]  ffffffff8106c521 ffff88003595af78 ffff88003595af40
ffff88003e3a4280
[  908.984178]  ffffffffa058d040 0000000000000000 ffffffff8106c59a
ffffffff8172ebd0
[  908.984181] Call Trace:
[  908.984188]  [<ffffffff81525b34>] ? dump_stack+0x40/0x50
[  908.984193]  [<ffffffff8106c521>] ? warn_slowpath_common+0x81/0xb0
[  908.984196]  [<ffffffff8106c59a>] ? warn_slowpath_fmt+0x4a/0x50
[  908.984199]  [<ffffffff81218352>] ? remove_proc_entry+0x112/0x160
[  908.984205]  [<ffffffffa05850e6>] ? bond_destroy_proc_dir+0x26/0x30
[bonding]
[  908.984208]  [<ffffffffa057540e>] ? bond_net_exit+0x8e/0xa0 [bonding]
[  908.984217]  [<ffffffff8142f407>] ? ops_exit_list.isra.4+0x37/0x70
[  908.984225]  [<ffffffff8142f52d>] ?
unregister_pernet_operations+0x8d/0xd0
[  908.984228]  [<ffffffff8142f58d>] ?
unregister_pernet_subsys+0x1d/0x30
[  908.984232]  [<ffffffffa0585269>] ? bonding_exit+0x23/0xdba [bonding]
[  908.984236]  [<ffffffff810e28ba>] ? SyS_delete_module+0x18a/0x250
[  908.984241]  [<ffffffff81086f99>] ? task_work_run+0x89/0xc0
[  908.984244]  [<ffffffff8152b732>] ?
entry_SYSCALL_64_fastpath+0x16/0x75
[  908.984247] ---[ end trace 7c006ed4abbef24b ]---

Thus remove the proc entry manually if bond_release_and_destroy() is
used. Because of the checks in bond_remove_proc_entry() it's not a
problem for a bond device to change namespaces (the bug fixed by the
Fixes commit) but since commit
f9399814927ad ("bonding: Don't allow bond devices to change network
namespaces.") that can't happen anyway.

Reported-by: Carol Soto <clsoto@linux.vnet.ibm.com>
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Fixes: a64d49c3dd50 ("bonding: Manage /proc/net/bonding/ entries from
                      the netdev events")
Tested-by: Carol L Soto <clsoto@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 32b0e705..7008cf4 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1825,6 +1825,7 @@ static int  bond_release_and_destroy(struct net_device *bond_dev,
 		bond_dev->priv_flags |= IFF_DISABLE_NETPOLL;
 		pr_info("%s: destroying bond %s.\n",
 			bond_dev->name, bond_dev->name);
+		bond_remove_proc_entry(bond);
 		unregister_netdevice(bond_dev);
 	}
 	return ret;
-- 
2.1.0


From 9afef0efa21616b6aa1c756e3c8d0625ff1d6d16 Mon Sep 17 00:00:00 2001
From: dingtianhong <dingtianhong@huawei.com>
Date: Thu, 16 Jul 2015 16:30:02 +0800
Subject: [PATCH 17/25] bonding: correct the MAC address for "follow"
 fail_over_mac policy

[ Upstream commit a951bc1e6ba58f11df5ed5ddc41311e10f5fd20b ]

The "follow" fail_over_mac policy is useful for multiport devices that
either become confused or incur a performance penalty when multiple
ports are programmed with the same MAC address, but the same MAC
address still may happened by this steps for this policy:

1) echo +eth0 > /sys/class/net/bond0/bonding/slaves
   bond0 has the same mac address with eth0, it is MAC1.

2) echo +eth1 > /sys/class/net/bond0/bonding/slaves
   eth1 is backup, eth1 has MAC2.

3) ifconfig eth0 down
   eth1 became active slave, bond will swap MAC for eth0 and eth1,
   so eth1 has MAC1, and eth0 has MAC2.

4) ifconfig eth1 down
   there is no active slave, and eth1 still has MAC1, eth2 has MAC2.

5) ifconfig eth0 up
   the eth0 became active slave again, the bond set eth0 to MAC1.

Something wrong here, then if you set eth1 up, the eth0 and eth1 will have the same
MAC address, it will break this policy for ACTIVE_BACKUP mode.

This patch will fix this problem by finding the old active slave and
swap them MAC address before change active slave.

Signed-off-by: Ding Tianhong <dingtianhong@huawei.com>
Tested-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 7008cf4..0697d8f 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -636,6 +636,23 @@ static void bond_set_dev_addr(struct net_device *bond_dev,
 	call_netdevice_notifiers(NETDEV_CHANGEADDR, bond_dev);
 }
 
+static struct slave *bond_get_old_active(struct bonding *bond,
+					 struct slave *new_active)
+{
+	struct slave *slave;
+	struct list_head *iter;
+
+	bond_for_each_slave(bond, slave, iter) {
+		if (slave == new_active)
+			continue;
+
+		if (ether_addr_equal(bond->dev->dev_addr, slave->dev->dev_addr))
+			return slave;
+	}
+
+	return NULL;
+}
+
 /*
  * bond_do_fail_over_mac
  *
@@ -672,6 +689,9 @@ static void bond_do_fail_over_mac(struct bonding *bond,
 
 		write_unlock_bh(&bond->curr_slave_lock);
 
+		if (!old_active)
+			old_active = bond_get_old_active(bond, new_active);
+
 		if (old_active) {
 			memcpy(tmp_mac, new_active->dev->dev_addr, ETH_ALEN);
 			memcpy(saddr.sa_data, old_active->dev->dev_addr,
-- 
2.1.0


From 08b9dc857827dde14dfae187991701b5d6b16f38 Mon Sep 17 00:00:00 2001
From: Edward Hyunkoo Jee <edjee@google.com>
Date: Tue, 21 Jul 2015 09:43:59 +0200
Subject: [PATCH 18/25] inet: frags: fix defragmented packet's IP header for
 af_packet

[ Upstream commit 0848f6428ba3a2e42db124d41ac6f548655735bf ]

When ip_frag_queue() computes positions, it assumes that the passed
sk_buff does not contain L2 headers.

However, when PACKET_FANOUT_FLAG_DEFRAG is used, IP reassembly
functions can be called on outgoing packets that contain L2 headers.

Also, IPv4 checksum is not corrected after reassembly.

Fixes: 7736d33f4262 ("packet: Add pre-defragmentation support for ipv4 fanouts.")
Signed-off-by: Edward Hyunkoo Jee <edjee@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Jerry Chu <hkchu@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_fragment.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 9ff497d..3f3a424 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -357,7 +357,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 	ihl = ip_hdrlen(skb);
 
 	/* Determine the position of this fragment. */
-	end = offset + skb->len - ihl;
+	end = offset + skb->len - skb_network_offset(skb) - ihl;
 	err = -EINVAL;
 
 	/* Is this the final fragment? */
@@ -387,7 +387,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 		goto err;
 
 	err = -ENOMEM;
-	if (pskb_pull(skb, ihl) == NULL)
+	if (!pskb_pull(skb, skb_network_offset(skb) + ihl))
 		goto err;
 
 	err = pskb_trim_rcsum(skb, end - offset);
@@ -628,6 +628,9 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 	iph->frag_off = qp->q.max_size ? htons(IP_DF) : 0;
 	iph->tot_len = htons(len);
 	iph->tos |= ecn;
+
+	ip_send_check(iph);
+
 	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMOKS);
 	qp->q.fragments = NULL;
 	qp->q.fragments_tail = NULL;
-- 
2.1.0


From ac187218b1bc3a9004a38f6804df155a92282a2b Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 21 Jul 2015 16:33:50 +0200
Subject: [PATCH 19/25] netlink: don't hold mutex in rcu callback when
 releasing mmapd ring

[ Upstream commit 0470eb99b4721586ccac954faac3fa4472da0845 ]

Kirill A. Shutemov says:

This simple test-case trigers few locking asserts in kernel:

int main(int argc, char **argv)
{
        unsigned int block_size = 16 * 4096;
        struct nl_mmap_req req = {
                .nm_block_size          = block_size,
                .nm_block_nr            = 64,
                .nm_frame_size          = 16384,
                .nm_frame_nr            = 64 * block_size / 16384,
        };
        unsigned int ring_size;
	int fd;

	fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_GENERIC);
        if (setsockopt(fd, SOL_NETLINK, NETLINK_RX_RING, &req, sizeof(req)) < 0)
                exit(1);
        if (setsockopt(fd, SOL_NETLINK, NETLINK_TX_RING, &req, sizeof(req)) < 0)
                exit(1);

	ring_size = req.nm_block_nr * req.nm_block_size;
	mmap(NULL, 2 * ring_size, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0);
	return 0;
}

+++ exited with 0 +++
BUG: sleeping function called from invalid context at /home/kas/git/public/linux-mm/kernel/locking/mutex.c:616
in_atomic(): 1, irqs_disabled(): 0, pid: 1, name: init
3 locks held by init/1:
 #0:  (reboot_mutex){+.+...}, at: [<ffffffff81080959>] SyS_reboot+0xa9/0x220
 #1:  ((reboot_notifier_list).rwsem){.+.+..}, at: [<ffffffff8107f379>] __blocking_notifier_call_chain+0x39/0x70
 #2:  (rcu_callback){......}, at: [<ffffffff810d32e0>] rcu_do_batch.isra.49+0x160/0x10c0
Preemption disabled at:[<ffffffff8145365f>] __delay+0xf/0x20

CPU: 1 PID: 1 Comm: init Not tainted 4.1.0-00009-gbddf4c4818e0 #253
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS Debian-1.8.2-1 04/01/2014
 ffff88017b3d8000 ffff88027bc03c38 ffffffff81929ceb 0000000000000102
 0000000000000000 ffff88027bc03c68 ffffffff81085a9d 0000000000000002
 ffffffff81ca2a20 0000000000000268 0000000000000000 ffff88027bc03c98
Call Trace:
 <IRQ>  [<ffffffff81929ceb>] dump_stack+0x4f/0x7b
 [<ffffffff81085a9d>] ___might_sleep+0x16d/0x270
 [<ffffffff81085bed>] __might_sleep+0x4d/0x90
 [<ffffffff8192e96f>] mutex_lock_nested+0x2f/0x430
 [<ffffffff81932fed>] ? _raw_spin_unlock_irqrestore+0x5d/0x80
 [<ffffffff81464143>] ? __this_cpu_preempt_check+0x13/0x20
 [<ffffffff8182fc3d>] netlink_set_ring+0x1ed/0x350
 [<ffffffff8182e000>] ? netlink_undo_bind+0x70/0x70
 [<ffffffff8182fe20>] netlink_sock_destruct+0x80/0x150
 [<ffffffff817e484d>] __sk_free+0x1d/0x160
 [<ffffffff817e49a9>] sk_free+0x19/0x20
[..]

Cong Wang says:

We can't hold mutex lock in a rcu callback, [..]

Thomas Graf says:

The socket should be dead at this point. It might be simpler to
add a netlink_release_ring() function which doesn't require
locking at all.

Reported-by: "Kirill A. Shutemov" <kirill@shutemov.name>
Diagnosed-by: Cong Wang <cwang@twopensource.com>
Suggested-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 79 ++++++++++++++++++++++++++++--------------------
 1 file changed, 47 insertions(+), 32 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index a0b0ea9..15dab9c 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -350,25 +350,52 @@ err1:
 	return NULL;
 }
 
+
+static void
+__netlink_set_ring(struct sock *sk, struct nl_mmap_req *req, bool tx_ring, void **pg_vec,
+		   unsigned int order)
+{
+	struct netlink_sock *nlk = nlk_sk(sk);
+	struct sk_buff_head *queue;
+	struct netlink_ring *ring;
+
+	queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue;
+	ring  = tx_ring ? &nlk->tx_ring : &nlk->rx_ring;
+
+	spin_lock_bh(&queue->lock);
+
+	ring->frame_max		= req->nm_frame_nr - 1;
+	ring->head		= 0;
+	ring->frame_size	= req->nm_frame_size;
+	ring->pg_vec_pages	= req->nm_block_size / PAGE_SIZE;
+
+	swap(ring->pg_vec_len, req->nm_block_nr);
+	swap(ring->pg_vec_order, order);
+	swap(ring->pg_vec, pg_vec);
+
+	__skb_queue_purge(queue);
+	spin_unlock_bh(&queue->lock);
+
+	WARN_ON(atomic_read(&nlk->mapped));
+
+	if (pg_vec)
+		free_pg_vec(pg_vec, order, req->nm_block_nr);
+}
+
 static int netlink_set_ring(struct sock *sk, struct nl_mmap_req *req,
-			    bool closing, bool tx_ring)
+			    bool tx_ring)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
 	struct netlink_ring *ring;
-	struct sk_buff_head *queue;
 	void **pg_vec = NULL;
 	unsigned int order = 0;
-	int err;
 
 	ring  = tx_ring ? &nlk->tx_ring : &nlk->rx_ring;
-	queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue;
 
-	if (!closing) {
-		if (atomic_read(&nlk->mapped))
-			return -EBUSY;
-		if (atomic_read(&ring->pending))
-			return -EBUSY;
-	}
+	if (atomic_read(&nlk->mapped))
+		return -EBUSY;
+	if (atomic_read(&ring->pending))
+		return -EBUSY;
 
 	if (req->nm_block_nr) {
 		if (ring->pg_vec != NULL)
@@ -400,31 +427,19 @@ static int netlink_set_ring(struct sock *sk, struct nl_mmap_req *req,
 			return -EINVAL;
 	}
 
-	err = -EBUSY;
 	mutex_lock(&nlk->pg_vec_lock);
-	if (closing || atomic_read(&nlk->mapped) == 0) {
-		err = 0;
-		spin_lock_bh(&queue->lock);
-
-		ring->frame_max		= req->nm_frame_nr - 1;
-		ring->head		= 0;
-		ring->frame_size	= req->nm_frame_size;
-		ring->pg_vec_pages	= req->nm_block_size / PAGE_SIZE;
-
-		swap(ring->pg_vec_len, req->nm_block_nr);
-		swap(ring->pg_vec_order, order);
-		swap(ring->pg_vec, pg_vec);
-
-		__skb_queue_purge(queue);
-		spin_unlock_bh(&queue->lock);
-
-		WARN_ON(atomic_read(&nlk->mapped));
+	if (atomic_read(&nlk->mapped) == 0) {
+		__netlink_set_ring(sk, req, tx_ring, pg_vec, order);
+		mutex_unlock(&nlk->pg_vec_lock);
+		return 0;
 	}
+
 	mutex_unlock(&nlk->pg_vec_lock);
 
 	if (pg_vec)
 		free_pg_vec(pg_vec, order, req->nm_block_nr);
-	return err;
+
+	return -EBUSY;
 }
 
 static void netlink_mm_open(struct vm_area_struct *vma)
@@ -893,10 +908,10 @@ static void netlink_sock_destruct(struct sock *sk)
 
 		memset(&req, 0, sizeof(req));
 		if (nlk->rx_ring.pg_vec)
-			netlink_set_ring(sk, &req, true, false);
+			__netlink_set_ring(sk, &req, false, NULL, 0);
 		memset(&req, 0, sizeof(req));
 		if (nlk->tx_ring.pg_vec)
-			netlink_set_ring(sk, &req, true, true);
+			__netlink_set_ring(sk, &req, true, NULL, 0);
 	}
 #endif /* CONFIG_NETLINK_MMAP */
 
@@ -2190,7 +2205,7 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 			return -EINVAL;
 		if (copy_from_user(&req, optval, sizeof(req)))
 			return -EFAULT;
-		err = netlink_set_ring(sk, &req, false,
+		err = netlink_set_ring(sk, &req,
 				       optname == NETLINK_TX_RING);
 		break;
 	}
-- 
2.1.0


From 019f5a95d359740045bf56bf2cbe7f58f1ccde7e Mon Sep 17 00:00:00 2001
From: Jack Morgenstein <jackm@dev.mellanox.co.il>
Date: Wed, 22 Jul 2015 16:53:47 +0300
Subject: [PATCH 20/25] net/mlx4_core: Fix wrong index in propagating port
 change event to VFs

[ Upstream commit 1c1bf34951e8d17941bf708d1901c47e81b15d55 ]

The port-change event processing in procedure mlx4_eq_int() uses "slave"
as the vf_oper array index. Since the value of "slave" is the PF function
index, the result is that the PF link state is used for deciding to
propagate the event for all the VFs. The VF link state should be used,
so the VF function index should be used here.

Fixes: 948e306d7d64 ('net/mlx4: Add VF link state support')
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/eq.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index 8992b38..3398f7a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -557,7 +557,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 						mlx4_dbg(dev, "%s: Sending MLX4_PORT_CHANGE_SUBTYPE_DOWN"
 							 " to slave: %d, port:%d\n",
 							 __func__, i, port);
-						s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state;
+						s_info = &priv->mfunc.master.vf_oper[i].vport[port].state;
 						if (IFLA_VF_LINK_STATE_AUTO == s_info->link_state)
 							mlx4_slave_event(dev, i, eqe);
 					} else {  /* IB port */
@@ -583,7 +583,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 					for (i = 0; i < dev->num_slaves; i++) {
 						if (i == mlx4_master_func_num(dev))
 							continue;
-						s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state;
+						s_info = &priv->mfunc.master.vf_oper[slave].vport[i].state;
 						if (IFLA_VF_LINK_STATE_AUTO == s_info->link_state)
 							mlx4_slave_event(dev, i, eqe);
 					}
-- 
2.1.0


From 67f48eb182393995fb24e2f7657ca63d6ec515e4 Mon Sep 17 00:00:00 2001
From: Lars Westerhoff <lars.westerhoff@newtec.eu>
Date: Tue, 28 Jul 2015 01:32:21 +0300
Subject: [PATCH 21/25] packet: missing dev_put() in packet_do_bind()

[ Upstream commit 158cd4af8dedbda0d612d448c724c715d0dda649 ]

When binding a PF_PACKET socket, the use count of the bound interface is
always increased with dev_hold in dev_get_by_{index,name}.  However,
when rebound with the same protocol and device as in the previous bind
the use count of the interface was not decreased.  Ultimately, this
caused the deletion of the interface to fail with the following message:

unregister_netdevice: waiting for dummy0 to become free. Usage count = 1

This patch moves the dev_put out of the conditional part that was only
executed when either the protocol or device changed on a bind.

Fixes: 902fefb82ef7 ('packet: improve socket create/bind latency in some cases')
Signed-off-by: Lars Westerhoff <lars.westerhoff@newtec.eu>
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 84a60b8..fee7dcc 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2645,7 +2645,7 @@ static int packet_release(struct socket *sock)
 static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
 {
 	struct packet_sock *po = pkt_sk(sk);
-	const struct net_device *dev_curr;
+	struct net_device *dev_curr;
 	__be16 proto_curr;
 	bool need_rehook;
 
@@ -2669,15 +2669,13 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
 
 		po->num = proto;
 		po->prot_hook.type = proto;
-
-		if (po->prot_hook.dev)
-			dev_put(po->prot_hook.dev);
-
 		po->prot_hook.dev = dev;
 
 		po->ifindex = dev ? dev->ifindex : 0;
 		packet_cached_dev_assign(po, dev);
 	}
+	if (dev_curr)
+		dev_put(dev_curr);
 
 	if (proto == 0 || !need_rehook)
 		goto out_unlock;
-- 
2.1.0


From a591f51f993121c090a7ea5e7f860a7a5ed0f236 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Sat, 1 Aug 2015 15:33:26 +0300
Subject: [PATCH 22/25] rds: fix an integer overflow test in
 rds_info_getsockopt()

[ Upstream commit 468b732b6f76b138c0926eadf38ac88467dcd271 ]

"len" is a signed integer.  We check that len is not negative, so it
goes from zero to INT_MAX.  PAGE_SIZE is unsigned long so the comparison
is type promoted to unsigned long.  ULONG_MAX - 4095 is a higher than
INT_MAX so the condition can never be true.

I don't know if this is harmful but it seems safe to limit "len" to
INT_MAX - 4095.

Fixes: a8c879a7ee98 ('RDS: Info and stats')
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/info.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/rds/info.c b/net/rds/info.c
index 9a6b4f6..140a44a 100644
--- a/net/rds/info.c
+++ b/net/rds/info.c
@@ -176,7 +176,7 @@ int rds_info_getsockopt(struct socket *sock, int optname, char __user *optval,
 
 	/* check for all kinds of wrapping and the like */
 	start = (unsigned long)optval;
-	if (len < 0 || len + PAGE_SIZE - 1 < len || start + len < start) {
+	if (len < 0 || len > INT_MAX - PAGE_SIZE + 1 || start + len < start) {
 		ret = -EINVAL;
 		goto out;
 	}
-- 
2.1.0


From abccadac494f004e53c786fb3a87fad19cbd3cb5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 1 Aug 2015 12:14:33 +0200
Subject: [PATCH 23/25] udp: fix dst races with multicast early demux
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 10e2eb878f3ca07ac2f05fa5ca5e6c4c9174a27a ]

Multicast dst are not cached. They carry DST_NOCACHE.

As mentioned in commit f8864972126899 ("ipv4: fix dst race in
sk_dst_get()"), these dst need special care before caching them
into a socket.

Caching them is allowed only if their refcnt was not 0, ie we
must use atomic_inc_not_zero()

Also, we must use READ_ONCE() to fetch sk->sk_rx_dst, as mentioned
in commit d0c294c53a771 ("tcp: prevent fetching dst twice in early demux
code")

Fixes: 421b3885bf6d ("udp: ipv4: Add udp early demux")
Tested-by: Gregory Hoggarth <Gregory.Hoggarth@alliedtelesis.co.nz>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Gregory Hoggarth <Gregory.Hoggarth@alliedtelesis.co.nz>
Reported-by: Alex Gartrell <agartrell@fb.com>
Cc: Michal Kubeček <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 21a3a9e..947dcae 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1957,12 +1957,19 @@ void udp_v4_early_demux(struct sk_buff *skb)
 
 	skb->sk = sk;
 	skb->destructor = sock_edemux;
-	dst = sk->sk_rx_dst;
+	dst = ACCESS_ONCE(sk->sk_rx_dst);
 
 	if (dst)
 		dst = dst_check(dst, 0);
-	if (dst)
-		skb_dst_set_noref(skb, dst);
+	if (dst) {
+		/* DST_NOCACHE can not be used without taking a reference */
+		if (dst->flags & DST_NOCACHE) {
+			if (likely(atomic_inc_not_zero(&dst->__refcnt)))
+				skb_dst_set(skb, dst);
+		} else {
+			skb_dst_set_noref(skb, dst);
+		}
+	}
 }
 
 int udp_rcv(struct sk_buff *skb)
-- 
2.1.0


From 2e2b1b29d0b4ef34bb99a5913582127633dbaa82 Mon Sep 17 00:00:00 2001
From: Ivan Vecera <ivecera@redhat.com>
Date: Thu, 6 Aug 2015 22:48:23 +0200
Subject: [PATCH 24/25] bna: fix interrupts storm caused by erroneous packets

[ Upstream commit ade4dc3e616e33c80d7e62855fe1b6f9895bc7c3 ]

The commit "e29aa33 bna: Enable Multi Buffer RX" moved packets counter
increment from the beginning of the NAPI processing loop after the check
for erroneous packets so they are never accounted. This counter is used
to inform firmware about number of processed completions (packets).
As these packets are never acked the firmware fires IRQs for them again
and again.

Fixes: e29aa33 ("bna: Enable Multi Buffer RX")
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Acked-by: Rasesh Mody <rasesh.mody@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/brocade/bna/bnad.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index 669eeb4..f051783 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -674,6 +674,7 @@ bnad_cq_process(struct bnad *bnad, struct bna_ccb *ccb, int budget)
 			if (!next_cmpl->valid)
 				break;
 		}
+		packets++;
 
 		/* TODO: BNA_CQ_EF_LOCAL ? */
 		if (unlikely(flags & (BNA_CQ_EF_MAC_ERROR |
@@ -690,7 +691,6 @@ bnad_cq_process(struct bnad *bnad, struct bna_ccb *ccb, int budget)
 		else
 			bnad_cq_setup_skb_frags(rcb, skb, sop_ci, nvecs, len);
 
-		packets++;
 		rcb->rxq->rx_packets++;
 		rcb->rxq->rx_bytes += totlen;
 		ccb->bytes_per_intr += totlen;
-- 
2.1.0


From 13d1eb50219e8fb8b1e03a06d74fd1561028538a Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 26 Aug 2015 22:17:39 -0700
Subject: [PATCH 25/25] Subject: [PATCH 3.14-stable] net: gso: use feature flag
 argument in all protocol gso handlers

[ Upstream commit 1e16aa3ddf863c6b9f37eddf52503230a62dedb3 ]

skb_gso_segment() has a 'features' argument representing offload features
available to the output path.

A few handlers, e.g. GRE, instead re-fetch the features of skb->dev and use
those instead of the provided ones when handing encapsulation/tunnels.

Depending on dev->hw_enc_features of the output device skb_gso_segment() can
then return NULL even when the caller has disabled all GSO feature bits,
as segmentation of inner header thinks device will take care of segmentation.

This e.g. affects the tbf scheduler, which will silently drop GRE-encap GSO skbs
that did not fit the remaining token quota as the segmentation does not work
when device supports corresponding hw offload capabilities.

Cc: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
[jay.vosburgh: backported to 3.14. ]
Signed-off-by: Jay Vosburgh <jay.vosburgh@canonical.com>
---
 net/ipv4/af_inet.c     | 2 +-
 net/ipv4/gre_offload.c | 2 +-
 net/ipv4/udp.c         | 2 +-
 net/ipv6/ip6_offload.c | 2 +-
 net/mpls/mpls_gso.c    | 2 +-
 5 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 951fe55..f4c804d 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1291,7 +1291,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 
 	encap = SKB_GSO_CB(skb)->encap_level > 0;
 	if (encap)
-		features = skb->dev->hw_enc_features & netif_skb_features(skb);
+		features &= skb->dev->hw_enc_features;
 	SKB_GSO_CB(skb)->encap_level += ihl;
 
 	skb_reset_transport_header(skb);
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index 278836f..0da513e 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -69,7 +69,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 	skb->mac_len = skb_inner_network_offset(skb);
 
 	/* segment inner packet. */
-	enc_features = skb->dev->hw_enc_features & netif_skb_features(skb);
+	enc_features = skb->dev->hw_enc_features & features;
 	segs = skb_mac_gso_segment(skb, enc_features);
 	if (!segs || IS_ERR(segs)) {
 		skb_gso_error_unwind(skb, protocol, ghl, mac_offset, mac_len);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 947dcae..6970e36 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2517,7 +2517,7 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
 	skb->protocol = htons(ETH_P_TEB);
 
 	/* segment inner packet. */
-	enc_features = skb->dev->hw_enc_features & netif_skb_features(skb);
+	enc_features = skb->dev->hw_enc_features & features;
 	segs = skb_mac_gso_segment(skb, enc_features);
 	if (!segs || IS_ERR(segs)) {
 		skb_gso_error_unwind(skb, protocol, tnl_hlen, mac_offset,
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index b2f0915..dc46eba 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -112,7 +112,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 
 	encap = SKB_GSO_CB(skb)->encap_level > 0;
 	if (encap)
-		features = skb->dev->hw_enc_features & netif_skb_features(skb);
+		features &= skb->dev->hw_enc_features;
 	SKB_GSO_CB(skb)->encap_level += sizeof(*ipv6h);
 
 	ipv6h = ipv6_hdr(skb);
diff --git a/net/mpls/mpls_gso.c b/net/mpls/mpls_gso.c
index 851cd88..0c970cb 100644
--- a/net/mpls/mpls_gso.c
+++ b/net/mpls/mpls_gso.c
@@ -47,7 +47,7 @@ static struct sk_buff *mpls_gso_segment(struct sk_buff *skb,
 	__skb_push(skb, skb->mac_len);
 
 	/* Segment inner packet. */
-	mpls_features = skb->dev->mpls_features & netif_skb_features(skb);
+	mpls_features = skb->dev->mpls_features & features;
 	segs = skb_mac_gso_segment(skb, mpls_features);
 
 
-- 
2.1.0


[-- Attachment #4: net_318.mbox --]
[-- Type: Application/Octet-Stream, Size: 82034 bytes --]

From bbd725f0d9e8515e61cd50ec5ae9c655b6fd9fa0 Mon Sep 17 00:00:00 2001
From: Angga <Hermin.Anggawijaya@alliedtelesis.co.nz>
Date: Fri, 3 Jul 2015 14:40:52 +1200
Subject: [PATCH 01/32] ipv6: Make MLD packets to only be processed locally

[ Upstream commit 4c938d22c88a9ddccc8c55a85e0430e9c62b1ac5 ]

Before commit daad151263cf ("ipv6: Make ipv6_is_mld() inline and use it
from ip6_mc_input().") MLD packets were only processed locally. After the
change, a copy of MLD packet goes through ip6_mr_input, causing
MRT6MSG_NOCACHE message to be generated to user space.

Make MLD packet only processed locally.

Fixes: daad151263cf ("ipv6: Make ipv6_is_mld() inline and use it from ip6_mc_input().")
Signed-off-by: Hermin Anggawijaya <hermin.anggawijaya@alliedtelesis.co.nz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_input.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index a3084ab..ac5e973 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -329,10 +329,10 @@ int ip6_mc_input(struct sk_buff *skb)
 				if (offset < 0)
 					goto out;
 
-				if (!ipv6_is_mld(skb, nexthdr, offset))
-					goto out;
+				if (ipv6_is_mld(skb, nexthdr, offset))
+					deliver = true;
 
-				deliver = true;
+				goto out;
 			}
 			/* unknown RA - process it normally */
 		}
-- 
2.1.0


From ed6dfb597b48c85c4e0dcbbbf5bd2480a00940d7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 6 Jul 2015 17:13:26 +0200
Subject: [PATCH 02/32] net: graceful exit from netif_alloc_netdev_queues()

[ Upstream commit d339727c2b1a10f25e6636670ab6e1841170e328 ]

User space can crash kernel with

ip link add ifb10 numtxqueues 100000 type ifb

We must replace a BUG_ON() by proper test and return -EINVAL for
crazy values.

Fixes: 60877a32bce00 ("net: allow large number of tx queues")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index fb96258..7b65c58 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6128,7 +6128,8 @@ static int netif_alloc_netdev_queues(struct net_device *dev)
 	struct netdev_queue *tx;
 	size_t sz = count * sizeof(*tx);
 
-	BUG_ON(count < 1 || count > 0xffff);
+	if (count < 1 || count > 0xffff)
+		return -EINVAL;
 
 	tx = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
 	if (!tx) {
-- 
2.1.0


From 74bf674522da39dba01ed5fa7fbd6b30806f46ff Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Tue, 7 Jul 2015 00:07:52 +0200
Subject: [PATCH 03/32] rtnetlink: verify IFLA_VF_INFO attributes before
 passing them to driver

[ Upstream commit 4f7d2cdfdde71ffe962399b7020c674050329423 ]

Jason Gunthorpe reported that since commit c02db8c6290b ("rtnetlink: make
SR-IOV VF interface symmetric"), we don't verify IFLA_VF_INFO attributes
anymore with respect to their policy, that is, ifla_vfinfo_policy[].

Before, they were part of ifla_policy[], but they have been nested since
placed under IFLA_VFINFO_LIST, that contains the attribute IFLA_VF_INFO,
which is another nested attribute for the actual VF attributes such as
IFLA_VF_MAC, IFLA_VF_VLAN, etc.

Despite the policy being split out from ifla_policy[] in this commit,
it's never applied anywhere. nla_for_each_nested() only does basic nla_ok()
testing for struct nlattr, but it doesn't know about the data context and
their requirements.

Fix, on top of Jason's initial work, does 1) parsing of the attributes
with the right policy, and 2) using the resulting parsed attribute table
from 1) instead of the nla_for_each_nested() loop (just like we used to
do when still part of ifla_policy[]).

Reference: http://thread.gmane.org/gmane.linux.network/368913
Fixes: c02db8c6290b ("rtnetlink: make SR-IOV VF interface symmetric")
Reported-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Cc: Chris Wright <chrisw@sous-sol.org>
Cc: Sucheta Chakraborty <sucheta.chakraborty@qlogic.com>
Cc: Greg Rose <gregory.v.rose@intel.com>
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Cc: Rony Efraim <ronye@mellanox.com>
Cc: Vlad Zolotarov <vladz@cloudius-systems.com>
Cc: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Cc: Thomas Graf <tgraf@suug.ch>
Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Vlad Zolotarov <vladz@cloudius-systems.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 166 ++++++++++++++++++++++++++-------------------------
 1 file changed, 85 insertions(+), 81 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index c522f7a..34fe173 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1207,10 +1207,6 @@ static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
 	[IFLA_INFO_SLAVE_DATA]	= { .type = NLA_NESTED },
 };
 
-static const struct nla_policy ifla_vfinfo_policy[IFLA_VF_INFO_MAX+1] = {
-	[IFLA_VF_INFO]		= { .type = NLA_NESTED },
-};
-
 static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = {
 	[IFLA_VF_MAC]		= { .len = sizeof(struct ifla_vf_mac) },
 	[IFLA_VF_VLAN]		= { .len = sizeof(struct ifla_vf_vlan) },
@@ -1356,85 +1352,86 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[])
 	return 0;
 }
 
-static int do_setvfinfo(struct net_device *dev, struct nlattr *attr)
+static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
 {
-	int rem, err = -EINVAL;
-	struct nlattr *vf;
 	const struct net_device_ops *ops = dev->netdev_ops;
+	int err = -EINVAL;
 
-	nla_for_each_nested(vf, attr, rem) {
-		switch (nla_type(vf)) {
-		case IFLA_VF_MAC: {
-			struct ifla_vf_mac *ivm;
-			ivm = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_mac)
-				err = ops->ndo_set_vf_mac(dev, ivm->vf,
-							  ivm->mac);
-			break;
-		}
-		case IFLA_VF_VLAN: {
-			struct ifla_vf_vlan *ivv;
-			ivv = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_vlan)
-				err = ops->ndo_set_vf_vlan(dev, ivv->vf,
-							   ivv->vlan,
-							   ivv->qos);
-			break;
-		}
-		case IFLA_VF_TX_RATE: {
-			struct ifla_vf_tx_rate *ivt;
-			struct ifla_vf_info ivf;
-			ivt = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_get_vf_config)
-				err = ops->ndo_get_vf_config(dev, ivt->vf,
-							     &ivf);
-			if (err)
-				break;
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_rate)
-				err = ops->ndo_set_vf_rate(dev, ivt->vf,
-							   ivf.min_tx_rate,
-							   ivt->rate);
-			break;
-		}
-		case IFLA_VF_RATE: {
-			struct ifla_vf_rate *ivt;
-			ivt = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_rate)
-				err = ops->ndo_set_vf_rate(dev, ivt->vf,
-							   ivt->min_tx_rate,
-							   ivt->max_tx_rate);
-			break;
-		}
-		case IFLA_VF_SPOOFCHK: {
-			struct ifla_vf_spoofchk *ivs;
-			ivs = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_spoofchk)
-				err = ops->ndo_set_vf_spoofchk(dev, ivs->vf,
-							       ivs->setting);
-			break;
-		}
-		case IFLA_VF_LINK_STATE: {
-			struct ifla_vf_link_state *ivl;
-			ivl = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_link_state)
-				err = ops->ndo_set_vf_link_state(dev, ivl->vf,
-								 ivl->link_state);
-			break;
-		}
-		default:
-			err = -EINVAL;
-			break;
-		}
-		if (err)
-			break;
+	if (tb[IFLA_VF_MAC]) {
+		struct ifla_vf_mac *ivm = nla_data(tb[IFLA_VF_MAC]);
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_mac)
+			err = ops->ndo_set_vf_mac(dev, ivm->vf,
+						  ivm->mac);
+		if (err < 0)
+			return err;
+	}
+
+	if (tb[IFLA_VF_VLAN]) {
+		struct ifla_vf_vlan *ivv = nla_data(tb[IFLA_VF_VLAN]);
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_vlan)
+			err = ops->ndo_set_vf_vlan(dev, ivv->vf, ivv->vlan,
+						   ivv->qos);
+		if (err < 0)
+			return err;
+	}
+
+	if (tb[IFLA_VF_TX_RATE]) {
+		struct ifla_vf_tx_rate *ivt = nla_data(tb[IFLA_VF_TX_RATE]);
+		struct ifla_vf_info ivf;
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_get_vf_config)
+			err = ops->ndo_get_vf_config(dev, ivt->vf, &ivf);
+		if (err < 0)
+			return err;
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_rate)
+			err = ops->ndo_set_vf_rate(dev, ivt->vf,
+						   ivf.min_tx_rate,
+						   ivt->rate);
+		if (err < 0)
+			return err;
 	}
+
+	if (tb[IFLA_VF_RATE]) {
+		struct ifla_vf_rate *ivt = nla_data(tb[IFLA_VF_RATE]);
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_rate)
+			err = ops->ndo_set_vf_rate(dev, ivt->vf,
+						   ivt->min_tx_rate,
+						   ivt->max_tx_rate);
+		if (err < 0)
+			return err;
+	}
+
+	if (tb[IFLA_VF_SPOOFCHK]) {
+		struct ifla_vf_spoofchk *ivs = nla_data(tb[IFLA_VF_SPOOFCHK]);
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_spoofchk)
+			err = ops->ndo_set_vf_spoofchk(dev, ivs->vf,
+						       ivs->setting);
+		if (err < 0)
+			return err;
+	}
+
+	if (tb[IFLA_VF_LINK_STATE]) {
+		struct ifla_vf_link_state *ivl = nla_data(tb[IFLA_VF_LINK_STATE]);
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_link_state)
+			err = ops->ndo_set_vf_link_state(dev, ivl->vf,
+							 ivl->link_state);
+		if (err < 0)
+			return err;
+	}
+
 	return err;
 }
 
@@ -1630,14 +1627,21 @@ static int do_setlink(const struct sk_buff *skb,
 	}
 
 	if (tb[IFLA_VFINFO_LIST]) {
+		struct nlattr *vfinfo[IFLA_VF_MAX + 1];
 		struct nlattr *attr;
 		int rem;
+
 		nla_for_each_nested(attr, tb[IFLA_VFINFO_LIST], rem) {
-			if (nla_type(attr) != IFLA_VF_INFO) {
+			if (nla_type(attr) != IFLA_VF_INFO ||
+			    nla_len(attr) < NLA_HDRLEN) {
 				err = -EINVAL;
 				goto errout;
 			}
-			err = do_setvfinfo(dev, attr);
+			err = nla_parse_nested(vfinfo, IFLA_VF_MAX, attr,
+					       ifla_vf_policy);
+			if (err < 0)
+				goto errout;
+			err = do_setvfinfo(dev, vfinfo);
 			if (err < 0)
 				goto errout;
 			status |= DO_SETLINK_NOTIFY;
-- 
2.1.0


From 490e7d242a2d321c5dbd19c722e62adf523e4f06 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timo=20Ter=C3=A4s?= <timo.teras@iki.fi>
Date: Tue, 7 Jul 2015 08:34:13 +0300
Subject: [PATCH 04/32] ip_tunnel: fix ipv4 pmtu check to honor inner ip header
 df
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit fc24f2b2094366da8786f59f2606307e934cea17 ]

Frag needed should be sent only if the inner header asked
to not fragment. Currently fragmentation is broken if the
tunnel has df set, but df was not asked in the original
packet. The tunnel's df needs to be still checked to update
internally the pmtu cache.

Commit 23a3647bc4f93bac broke it, and this commit fixes
the ipv4 df check back to the way it was.

Fixes: 23a3647bc4f93bac ("ip_tunnels: Use skb-len to PMTU check.")
Cc: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: Timo Teräs <timo.teras@iki.fi>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_tunnel.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 0bb8e14..6822572 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -587,7 +587,8 @@ int ip_tunnel_encap(struct sk_buff *skb, struct ip_tunnel *t,
 EXPORT_SYMBOL(ip_tunnel_encap);
 
 static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
-			    struct rtable *rt, __be16 df)
+			    struct rtable *rt, __be16 df,
+			    const struct iphdr *inner_iph)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	int pkt_size = skb->len - tunnel->hlen - dev->hard_header_len;
@@ -604,7 +605,8 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
 
 	if (skb->protocol == htons(ETH_P_IP)) {
 		if (!skb_is_gso(skb) &&
-		    (df & htons(IP_DF)) && mtu < pkt_size) {
+		    (inner_iph->frag_off & htons(IP_DF)) &&
+		    mtu < pkt_size) {
 			memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
 			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
 			return -E2BIG;
@@ -738,7 +740,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		goto tx_error;
 	}
 
-	if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off)) {
+	if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off, inner_iph)) {
 		ip_rt_put(rt);
 		goto tx_error;
 	}
-- 
2.1.0


From ef2a1f6d0bf06affda2e23910ca253a329f2fe75 Mon Sep 17 00:00:00 2001
From: Stephen Smalley <sds@tycho.nsa.gov>
Date: Tue, 7 Jul 2015 09:43:45 -0400
Subject: [PATCH 05/32] net/tipc: initialize security state for new connection
 socket

[ Upstream commit fdd75ea8df370f206a8163786e7470c1277a5064 ]

Calling connect() with an AF_TIPC socket would trigger a series
of error messages from SELinux along the lines of:
SELinux: Invalid class 0
type=AVC msg=audit(1434126658.487:34500): avc:  denied  { <unprintable> }
  for pid=292 comm="kworker/u16:5" scontext=system_u:system_r:kernel_t:s0
  tcontext=system_u:object_r:unlabeled_t:s0 tclass=<unprintable>
  permissive=0

This was due to a failure to initialize the security state of the new
connection sock by the tipc code, leaving it with junk in the security
class field and an unlabeled secid.  Add a call to security_sk_clone()
to inherit the security state from the parent socket.

Reported-by: Tim Shearer <tim.shearer@overturenetworks.com>
Signed-off-by: Stephen Smalley <sds@tycho.nsa.gov>
Acked-by: Paul Moore <paul@paul-moore.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/socket.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 51bddc2..8224016 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1996,6 +1996,7 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags)
 	res = tipc_sk_create(sock_net(sock->sk), new_sock, 0, 1);
 	if (res)
 		goto exit;
+	security_sk_clone(sock->sk, new_sock->sk);
 
 	new_sk = new_sock->sk;
 	new_tsock = tipc_sk(new_sk);
-- 
2.1.0


From 3e718543419e128277865439498bf8bd015e3ec2 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <razor@blackwall.org>
Date: Tue, 7 Jul 2015 15:55:56 +0200
Subject: [PATCH 06/32] bridge: mdb: zero out the local br_ip variable before
 use

[ Upstream commit f1158b74e54f2e2462ba5e2f45a118246d9d5b43 ]

Since commit b0e9a30dd669 ("bridge: Add vlan id to multicast groups")
there's a check in br_ip_equal() for a matching vlan id, but the mdb
functions were not modified to use (or at least zero it) so when an
entry was added it would have a garbage vlan id (from the local br_ip
variable in __br_mdb_add/del) and this would prevent it from being
matched and also deleted. So zero out the whole local ip var to protect
ourselves from future changes and also to fix the current bug, since
there's no vlan id support in the mdb uapi - use always vlan id 0.
Example before patch:
root@debian:~# bridge mdb add dev br0 port eth1 grp 239.0.0.1 permanent
root@debian:~# bridge mdb
dev br0 port eth1 grp 239.0.0.1 permanent
root@debian:~# bridge mdb del dev br0 port eth1 grp 239.0.0.1 permanent
RTNETLINK answers: Invalid argument

After patch:
root@debian:~# bridge mdb add dev br0 port eth1 grp 239.0.0.1 permanent
root@debian:~# bridge mdb
dev br0 port eth1 grp 239.0.0.1 permanent
root@debian:~# bridge mdb del dev br0 port eth1 grp 239.0.0.1 permanent
root@debian:~# bridge mdb

Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Fixes: b0e9a30dd669 ("bridge: Add vlan id to multicast groups")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_mdb.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index 5df0526..b077664 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -370,6 +370,7 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br,
 	if (!p || p->br != br || p->state == BR_STATE_DISABLED)
 		return -EINVAL;
 
+	memset(&ip, 0, sizeof(ip));
 	ip.proto = entry->addr.proto;
 	if (ip.proto == htons(ETH_P_IP))
 		ip.u.ip4 = entry->addr.u.ip4;
@@ -416,6 +417,7 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry)
 	if (!netif_running(br->dev) || br->multicast_disabled)
 		return -EINVAL;
 
+	memset(&ip, 0, sizeof(ip));
 	ip.proto = entry->addr.proto;
 	if (ip.proto == htons(ETH_P_IP)) {
 		if (timer_pending(&br->ip4_other_query.timer))
-- 
2.1.0


From 0ccba09c1ed213cdbe410ef70e8c6639803a0de2 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Wed, 8 Jul 2015 21:42:11 +0200
Subject: [PATCH 07/32] net: pktgen: fix race between pktgen_thread_worker()
 and kthread_stop()

[ Upstream commit fecdf8be2d91e04b0a9a4f79ff06499a36f5d14f ]

pktgen_thread_worker() is obviously racy, kthread_stop() can come
between the kthread_should_stop() check and set_current_state().

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Reported-by: Jan Stancek <jstancek@redhat.com>
Reported-by: Marcelo Leitner <mleitner@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/pktgen.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 0b320d9..4ff3eac 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -3490,8 +3490,10 @@ static int pktgen_thread_worker(void *arg)
 	pktgen_rem_thread(t);
 
 	/* Wait for kthread_stop */
-	while (!kthread_should_stop()) {
+	for (;;) {
 		set_current_state(TASK_INTERRUPTIBLE);
+		if (kthread_should_stop())
+			break;
 		schedule();
 	}
 	__set_current_state(TASK_RUNNING);
-- 
2.1.0


From 5a31085376372619eb29261577e5b912f04d14b5 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Thu, 9 Jul 2015 09:59:09 +0300
Subject: [PATCH 08/32] net: do not process device backlog during
 unregistration

[ Upstream commit e9e4dd3267d0c5234c5c0f47440456b10875dec9 ]

commit 381c759d9916 ("ipv4: Avoid crashing in ip_error")
fixes a problem where processed packet comes from device
with destroyed inetdev (dev->ip_ptr). This is not expected
because inetdev_destroy is called in NETDEV_UNREGISTER
phase and packets should not be processed after
dev_close_many() and synchronize_net(). Above fix is still
required because inetdev_destroy can be called for other
reasons. But it shows the real problem: backlog can keep
packets for long time and they do not hold reference to
device. Such packets are then delivered to upper levels
at the same time when device is unregistered.
Calling flush_backlog after NETDEV_UNREGISTER_FINAL still
accounts all packets from backlog but before that some packets
continue to be delivered to upper levels long after the
synchronize_net call which is supposed to wait the last
ones. Also, as Eric pointed out, processed packets, mostly
from other devices, can continue to add new packets to backlog.

Fix the problem by moving flush_backlog early, after the
device driver is stopped and before the synchronize_net() call.
Then use netif_running check to make sure we do not add more
packets to backlog. We have to do it in enqueue_to_backlog
context when the local IRQ is disabled. As result, after the
flush_backlog and synchronize_net sequence all packets
should be accounted.

Thanks to Eric W. Biederman for the test script and his
valuable feedback!

Reported-by: Vittorio Gambaletta <linuxbugs@vittgam.net>
Fixes: 6e583ce5242f ("net: eliminate refcounting in backlog queue")
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 7b65c58..1ad7d5f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3309,6 +3309,8 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
 	local_irq_save(flags);
 
 	rps_lock(sd);
+	if (!netif_running(skb->dev))
+		goto drop;
 	qlen = skb_queue_len(&sd->input_pkt_queue);
 	if (qlen <= netdev_max_backlog && !skb_flow_limit(skb, qlen)) {
 		if (skb_queue_len(&sd->input_pkt_queue)) {
@@ -3330,6 +3332,7 @@ enqueue:
 		goto enqueue;
 	}
 
+drop:
 	sd->dropped++;
 	rps_unlock(sd);
 
@@ -5867,6 +5870,7 @@ static void rollback_registered_many(struct list_head *head)
 		unlist_netdevice(dev);
 
 		dev->reg_state = NETREG_UNREGISTERING;
+		on_each_cpu(flush_backlog, dev, 1);
 	}
 
 	synchronize_net();
@@ -6487,8 +6491,6 @@ void netdev_run_todo(void)
 
 		dev->reg_state = NETREG_UNREGISTERED;
 
-		on_each_cpu(flush_backlog, dev, 1);
-
 		netdev_wait_allrefs(dev);
 
 		/* paranoia */
-- 
2.1.0


From b4804d4b6dd73bb2b872fb34ab550a627db14123 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Thu, 9 Jul 2015 09:59:10 +0300
Subject: [PATCH 09/32] net: call rcu_read_lock early in process_backlog

[ Upstream commit 2c17d27c36dcce2b6bf689f41a46b9e909877c21 ]

Incoming packet should be either in backlog queue or
in RCU read-side section. Otherwise, the final sequence of
flush_backlog() and synchronize_net() may miss packets
that can run without device reference:

CPU 1                  CPU 2
                       skb->dev: no reference
                       process_backlog:__skb_dequeue
                       process_backlog:local_irq_enable

on_each_cpu for
flush_backlog =>       IPI(hardirq): flush_backlog
                       - packet not found in backlog

                       CPU delayed ...
synchronize_net
- no ongoing RCU
read-side sections

netdev_run_todo,
rcu_barrier: no
ongoing callbacks
                       __netif_receive_skb_core:rcu_read_lock
                       - too late
free dev
                       process packet for freed dev

Fixes: 6e583ce5242f ("net: eliminate refcounting in backlog queue")
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 30 +++++++++++++++---------------
 1 file changed, 15 insertions(+), 15 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 1ad7d5f..93612b2 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3641,8 +3641,6 @@ static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc)
 
 	pt_prev = NULL;
 
-	rcu_read_lock();
-
 another_round:
 	skb->skb_iif = skb->dev->ifindex;
 
@@ -3652,7 +3650,7 @@ another_round:
 	    skb->protocol == cpu_to_be16(ETH_P_8021AD)) {
 		skb = skb_vlan_untag(skb);
 		if (unlikely(!skb))
-			goto unlock;
+			goto out;
 	}
 
 #ifdef CONFIG_NET_CLS_ACT
@@ -3677,7 +3675,7 @@ skip_taps:
 #ifdef CONFIG_NET_CLS_ACT
 	skb = handle_ing(skb, &pt_prev, &ret, orig_dev);
 	if (!skb)
-		goto unlock;
+		goto out;
 ncls:
 #endif
 
@@ -3692,7 +3690,7 @@ ncls:
 		if (vlan_do_receive(&skb))
 			goto another_round;
 		else if (unlikely(!skb))
-			goto unlock;
+			goto out;
 	}
 
 	rx_handler = rcu_dereference(skb->dev->rx_handler);
@@ -3704,7 +3702,7 @@ ncls:
 		switch (rx_handler(&skb)) {
 		case RX_HANDLER_CONSUMED:
 			ret = NET_RX_SUCCESS;
-			goto unlock;
+			goto out;
 		case RX_HANDLER_ANOTHER:
 			goto another_round;
 		case RX_HANDLER_EXACT:
@@ -3756,8 +3754,7 @@ drop:
 		ret = NET_RX_DROP;
 	}
 
-unlock:
-	rcu_read_unlock();
+out:
 	return ret;
 }
 
@@ -3788,29 +3785,30 @@ static int __netif_receive_skb(struct sk_buff *skb)
 
 static int netif_receive_skb_internal(struct sk_buff *skb)
 {
+	int ret;
+
 	net_timestamp_check(netdev_tstamp_prequeue, skb);
 
 	if (skb_defer_rx_timestamp(skb))
 		return NET_RX_SUCCESS;
 
+	rcu_read_lock();
+
 #ifdef CONFIG_RPS
 	if (static_key_false(&rps_needed)) {
 		struct rps_dev_flow voidflow, *rflow = &voidflow;
-		int cpu, ret;
-
-		rcu_read_lock();
-
-		cpu = get_rps_cpu(skb->dev, skb, &rflow);
+		int cpu = get_rps_cpu(skb->dev, skb, &rflow);
 
 		if (cpu >= 0) {
 			ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
 			rcu_read_unlock();
 			return ret;
 		}
-		rcu_read_unlock();
 	}
 #endif
-	return __netif_receive_skb(skb);
+	ret = __netif_receive_skb(skb);
+	rcu_read_unlock();
+	return ret;
 }
 
 /**
@@ -4346,8 +4344,10 @@ static int process_backlog(struct napi_struct *napi, int quota)
 		struct sk_buff *skb;
 
 		while ((skb = __skb_dequeue(&sd->process_queue))) {
+			rcu_read_lock();
 			local_irq_enable();
 			__netif_receive_skb(skb);
+			rcu_read_unlock();
 			local_irq_disable();
 			input_queue_head_incr(sd);
 			if (++work >= quota) {
-- 
2.1.0


From de0acb5d624afc3d68dfe00bb1480700aed734ba Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Sun, 12 Jul 2015 01:20:55 +0300
Subject: [PATCH 10/32] net/xen-netback: off by one in BUG_ON() condition

[ Upstream commit 50c2e4dd6749725338621fff456b26d3a592259f ]

The > should be >=.  I also added spaces around the '-' operations so
the code is a little more consistent and matches the condition better.

Fixes: f53c3fe8dad7 ('xen-netback: Introduce TX grant mapping')
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netback/netback.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index c39aace..bccd4b6 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -1760,13 +1760,13 @@ static inline void xenvif_tx_dealloc_action(struct xenvif_queue *queue)
 		smp_rmb();
 
 		while (dc != dp) {
-			BUG_ON(gop - queue->tx_unmap_ops > MAX_PENDING_REQS);
+			BUG_ON(gop - queue->tx_unmap_ops >= MAX_PENDING_REQS);
 			pending_idx =
 				queue->dealloc_ring[pending_index(dc++)];
 
-			pending_idx_release[gop-queue->tx_unmap_ops] =
+			pending_idx_release[gop - queue->tx_unmap_ops] =
 				pending_idx;
-			queue->pages_to_unmap[gop-queue->tx_unmap_ops] =
+			queue->pages_to_unmap[gop - queue->tx_unmap_ops] =
 				queue->mmap_pages[pending_idx];
 			gnttab_set_unmap_op(gop,
 					    idx_to_kaddr(queue, pending_idx),
-- 
2.1.0


From ac50ed9b8fd495ef608a43d5ff9d18fe1768f98b Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Mon, 13 Jul 2015 16:04:13 +0800
Subject: [PATCH 11/32] net: Clone skb before setting peeked flag

[ Upstream commit 738ac1ebb96d02e0d23bc320302a6ea94c612dec ]

Shared skbs must not be modified and this is crucial for broadcast
and/or multicast paths where we use it as an optimisation to avoid
unnecessary cloning.

The function skb_recv_datagram breaks this rule by setting peeked
without cloning the skb first.  This causes funky races which leads
to double-free.

This patch fixes this by cloning the skb and replacing the skb
in the list when setting skb->peeked.

Fixes: a59322be07c9 ("[UDP]: Only increment counter on first peek/recv")
Reported-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/datagram.c | 41 ++++++++++++++++++++++++++++++++++++++---
 1 file changed, 38 insertions(+), 3 deletions(-)

diff --git a/net/core/datagram.c b/net/core/datagram.c
index fdbc9a8..a3c0189 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -130,6 +130,35 @@ out_noerr:
 	goto out;
 }
 
+static int skb_set_peeked(struct sk_buff *skb)
+{
+	struct sk_buff *nskb;
+
+	if (skb->peeked)
+		return 0;
+
+	/* We have to unshare an skb before modifying it. */
+	if (!skb_shared(skb))
+		goto done;
+
+	nskb = skb_clone(skb, GFP_ATOMIC);
+	if (!nskb)
+		return -ENOMEM;
+
+	skb->prev->next = nskb;
+	skb->next->prev = nskb;
+	nskb->prev = skb->prev;
+	nskb->next = skb->next;
+
+	consume_skb(skb);
+	skb = nskb;
+
+done:
+	skb->peeked = 1;
+
+	return 0;
+}
+
 /**
  *	__skb_recv_datagram - Receive a datagram skbuff
  *	@sk: socket
@@ -164,7 +193,9 @@ out_noerr:
 struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
 				    int *peeked, int *off, int *err)
 {
+	struct sk_buff_head *queue = &sk->sk_receive_queue;
 	struct sk_buff *skb, *last;
+	unsigned long cpu_flags;
 	long timeo;
 	/*
 	 * Caller is allowed not to check sk->sk_err before skb_recv_datagram()
@@ -183,8 +214,6 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
 		 * Look at current nfs client by the way...
 		 * However, this function was correct in any case. 8)
 		 */
-		unsigned long cpu_flags;
-		struct sk_buff_head *queue = &sk->sk_receive_queue;
 		int _off = *off;
 
 		last = (struct sk_buff *)queue;
@@ -198,7 +227,11 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
 					_off -= skb->len;
 					continue;
 				}
-				skb->peeked = 1;
+
+				error = skb_set_peeked(skb);
+				if (error)
+					goto unlock_err;
+
 				atomic_inc(&skb->users);
 			} else
 				__skb_unlink(skb, queue);
@@ -222,6 +255,8 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
 
 	return NULL;
 
+unlock_err:
+	spin_unlock_irqrestore(&queue->lock, cpu_flags);
 no_packet:
 	*err = error;
 	return NULL;
-- 
2.1.0


From 0754c28bed41b442edd74f455d3504c8b73c20e8 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Mon, 13 Jul 2015 20:01:42 +0800
Subject: [PATCH 12/32] net: Fix skb csum races when peeking

[ Upstream commit 89c22d8c3b278212eef6a8cc66b570bc840a6f5a ]

When we calculate the checksum on the recv path, we store the
result in the skb as an optimisation in case we need the checksum
again down the line.

This is in fact bogus for the MSG_PEEK case as this is done without
any locking.  So multiple threads can peek and then store the result
to the same skb, potentially resulting in bogus skb states.

This patch fixes this by only storing the result if the skb is not
shared.  This preserves the optimisations for the few cases where
it can be done safely due to locking or other reasons, e.g., SIOCINQ.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/datagram.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/net/core/datagram.c b/net/core/datagram.c
index a3c0189..61e99f3 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -779,7 +779,8 @@ __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len)
 		    !skb->csum_complete_sw)
 			netdev_rx_csum_fault(skb->dev);
 	}
-	skb->csum_valid = !sum;
+	if (!skb_shared(skb))
+		skb->csum_valid = !sum;
 	return sum;
 }
 EXPORT_SYMBOL(__skb_checksum_complete_head);
@@ -799,11 +800,13 @@ __sum16 __skb_checksum_complete(struct sk_buff *skb)
 			netdev_rx_csum_fault(skb->dev);
 	}
 
-	/* Save full packet checksum */
-	skb->csum = csum;
-	skb->ip_summed = CHECKSUM_COMPLETE;
-	skb->csum_complete_sw = 1;
-	skb->csum_valid = !sum;
+	if (!skb_shared(skb)) {
+		/* Save full packet checksum */
+		skb->csum = csum;
+		skb->ip_summed = CHECKSUM_COMPLETE;
+		skb->csum_complete_sw = 1;
+		skb->csum_valid = !sum;
+	}
 
 	return sum;
 }
-- 
2.1.0


From bf128571e84cb500fce6878908692cc239fab450 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Tue, 4 Aug 2015 15:42:47 +0800
Subject: [PATCH 13/32] net: Fix skb_set_peeked use-after-free bug

[ Upstream commit a0a2a6602496a45ae838a96db8b8173794b5d398 ]

The commit 738ac1ebb96d02e0d23bc320302a6ea94c612dec ("net: Clone
skb before setting peeked flag") introduced a use-after-free bug
in skb_recv_datagram.  This is because skb_set_peeked may create
a new skb and free the existing one.  As it stands the caller will
continue to use the old freed skb.

This patch fixes it by making skb_set_peeked return the new skb
(or the old one if unchanged).

Fixes: 738ac1ebb96d ("net: Clone skb before setting peeked flag")
Reported-by: Brenden Blanco <bblanco@plumgrid.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Tested-by: Brenden Blanco <bblanco@plumgrid.com>
Reviewed-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/datagram.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/net/core/datagram.c b/net/core/datagram.c
index 61e99f3..2850ab3 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -130,12 +130,12 @@ out_noerr:
 	goto out;
 }
 
-static int skb_set_peeked(struct sk_buff *skb)
+static struct sk_buff *skb_set_peeked(struct sk_buff *skb)
 {
 	struct sk_buff *nskb;
 
 	if (skb->peeked)
-		return 0;
+		return skb;
 
 	/* We have to unshare an skb before modifying it. */
 	if (!skb_shared(skb))
@@ -143,7 +143,7 @@ static int skb_set_peeked(struct sk_buff *skb)
 
 	nskb = skb_clone(skb, GFP_ATOMIC);
 	if (!nskb)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	skb->prev->next = nskb;
 	skb->next->prev = nskb;
@@ -156,7 +156,7 @@ static int skb_set_peeked(struct sk_buff *skb)
 done:
 	skb->peeked = 1;
 
-	return 0;
+	return skb;
 }
 
 /**
@@ -228,8 +228,9 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
 					continue;
 				}
 
-				error = skb_set_peeked(skb);
-				if (error)
+				skb = skb_set_peeked(skb);
+				error = PTR_ERR(skb);
+				if (IS_ERR(skb))
 					goto unlock_err;
 
 				atomic_inc(&skb->users);
-- 
2.1.0


From d83794129f6718b8921fe6387247df5514e63fae Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Mon, 13 Jul 2015 06:36:19 -0700
Subject: [PATCH 14/32] bridge: mdb: fix double add notification

[ Upstream commit 5ebc784625ea68a9570d1f70557e7932988cd1b4 ]

Since the mdb add/del code was introduced there have been 2 br_mdb_notify
calls when doing br_mdb_add() resulting in 2 notifications on each add.

Example:
 Command: bridge mdb add dev br0 port eth1 grp 239.0.0.1 permanent
 Before patch:
 root@debian:~# bridge monitor all
 [MDB]dev br0 port eth1 grp 239.0.0.1 permanent
 [MDB]dev br0 port eth1 grp 239.0.0.1 permanent

 After patch:
 root@debian:~# bridge monitor all
 [MDB]dev br0 port eth1 grp 239.0.0.1 permanent

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Fixes: cfd567543590 ("bridge: add support of adding and deleting mdb entries")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_mdb.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index b077664..cc64154 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -347,7 +347,6 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
 		return -ENOMEM;
 	rcu_assign_pointer(*pp, p);
 
-	br_mdb_notify(br->dev, port, group, RTM_NEWMDB);
 	return 0;
 }
 
-- 
2.1.0


From 3dec5a1af01da9091368c2c005a897e80c88fa9f Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Mon, 13 Jul 2015 12:30:07 -0700
Subject: [PATCH 15/32] fq_codel: fix a use-after-free

[ Upstream commit 052cbda41fdc243a8d40cce7ab3a6327b4b2887e ]

Fixes: 25331d6ce42b ("net: sched: implement qstat helper routines")
Cc: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Cong Wang <cwang@twopensource.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_fq_codel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 1e52dec..b61fd84 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -162,10 +162,10 @@ static unsigned int fq_codel_drop(struct Qdisc *sch)
 	skb = dequeue_head(flow);
 	len = qdisc_pkt_len(skb);
 	q->backlogs[idx] -= len;
-	kfree_skb(skb);
 	sch->q.qlen--;
 	qdisc_qstats_drop(sch);
 	qdisc_qstats_backlog_dec(sch, skb);
+	kfree_skb(skb);
 	flow->dropped++;
 	return idx;
 }
-- 
2.1.0


From 435a69218f79c7e90fd3de965db474fa629f8e90 Mon Sep 17 00:00:00 2001
From: Tilman Schmidt <tilman@imap.cc>
Date: Tue, 14 Jul 2015 00:37:13 +0200
Subject: [PATCH 16/32] isdn/gigaset: reset tty->receive_room when attaching
 ser_gigaset

[ Upstream commit fd98e9419d8d622a4de91f76b306af6aa627aa9c ]

Commit 79901317ce80 ("n_tty: Don't flush buffer when closing ldisc"),
first merged in kernel release 3.10, caused the following regression
in the Gigaset M101 driver:

Before that commit, when closing the N_TTY line discipline in
preparation to switching to N_GIGASET_M101, receive_room would be
reset to a non-zero value by the call to n_tty_flush_buffer() in
n_tty's close method. With the removal of that call, receive_room
might be left at zero, blocking data reception on the serial line.

The present patch fixes that regression by setting receive_room
to an appropriate value in the ldisc open method.

Fixes: 79901317ce80 ("n_tty: Don't flush buffer when closing ldisc")
Signed-off-by: Tilman Schmidt <tilman@imap.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/gigaset/ser-gigaset.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/isdn/gigaset/ser-gigaset.c b/drivers/isdn/gigaset/ser-gigaset.c
index 8c91fd5..3ac9c41 100644
--- a/drivers/isdn/gigaset/ser-gigaset.c
+++ b/drivers/isdn/gigaset/ser-gigaset.c
@@ -524,9 +524,18 @@ gigaset_tty_open(struct tty_struct *tty)
 	cs->hw.ser->tty = tty;
 	atomic_set(&cs->hw.ser->refcnt, 1);
 	init_completion(&cs->hw.ser->dead_cmp);
-
 	tty->disc_data = cs;
 
+	/* Set the amount of data we're willing to receive per call
+	 * from the hardware driver to half of the input buffer size
+	 * to leave some reserve.
+	 * Note: We don't do flow control towards the hardware driver.
+	 * If more data is received than will fit into the input buffer,
+	 * it will be dropped and an error will be logged. This should
+	 * never happen as the device is slow and the buffer size ample.
+	 */
+	tty->receive_room = RBUFSIZE/2;
+
 	/* OK.. Initialization of the datastructures and the HW is done.. Now
 	 * startup system and notify the LL that we are ready to run
 	 */
-- 
2.1.0


From 069e31c054eb9c130df601b12504cc5e39c9b297 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 14 Jul 2015 08:10:22 +0200
Subject: [PATCH 17/32] ipv6: lock socket in ip6_datagram_connect()

[ Upstream commit 03645a11a570d52e70631838cb786eb4253eb463 ]

ip6_datagram_connect() is doing a lot of socket changes without
socket being locked.

This looks wrong, at least for udp_lib_rehash() which could corrupt
lists because of concurrent udp_sk(sk)->udp_portaddr_hash accesses.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h    |  1 +
 net/ipv4/datagram.c | 16 ++++++++++++----
 net/ipv6/datagram.c | 20 +++++++++++++++-----
 3 files changed, 28 insertions(+), 9 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index c0c26c3..d00ebdf 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -160,6 +160,7 @@ static inline __u8 get_rtconn_flags(struct ipcm_cookie* ipc, struct sock* sk)
 }
 
 /* datagram.c */
+int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
 int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
 
 void ip4_datagram_release_cb(struct sock *sk);
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index 90c0e83..574fad9 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -20,7 +20,7 @@
 #include <net/route.h>
 #include <net/tcp_states.h>
 
-int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct sockaddr_in *usin = (struct sockaddr_in *) uaddr;
@@ -39,8 +39,6 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 
 	sk_dst_reset(sk);
 
-	lock_sock(sk);
-
 	oif = sk->sk_bound_dev_if;
 	saddr = inet->inet_saddr;
 	if (ipv4_is_multicast(usin->sin_addr.s_addr)) {
@@ -82,9 +80,19 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	sk_dst_set(sk, &rt->dst);
 	err = 0;
 out:
-	release_sock(sk);
 	return err;
 }
+EXPORT_SYMBOL(__ip4_datagram_connect);
+
+int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+{
+	int res;
+
+	lock_sock(sk);
+	res = __ip4_datagram_connect(sk, uaddr, addr_len);
+	release_sock(sk);
+	return res;
+}
 EXPORT_SYMBOL(ip4_datagram_connect);
 
 /* Because UDP xmit path can manipulate sk_dst_cache without holding
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 11e3945..e069aeb2 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -40,7 +40,7 @@ static bool ipv6_mapped_addr_any(const struct in6_addr *a)
 	return ipv6_addr_v4mapped(a) && (a->s6_addr32[3] == 0);
 }
 
-int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+static int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
 	struct sockaddr_in6	*usin = (struct sockaddr_in6 *) uaddr;
 	struct inet_sock	*inet = inet_sk(sk);
@@ -56,7 +56,7 @@ int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	if (usin->sin6_family == AF_INET) {
 		if (__ipv6_only_sock(sk))
 			return -EAFNOSUPPORT;
-		err = ip4_datagram_connect(sk, uaddr, addr_len);
+		err = __ip4_datagram_connect(sk, uaddr, addr_len);
 		goto ipv4_connected;
 	}
 
@@ -98,9 +98,9 @@ int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 		sin.sin_addr.s_addr = daddr->s6_addr32[3];
 		sin.sin_port = usin->sin6_port;
 
-		err = ip4_datagram_connect(sk,
-					   (struct sockaddr *) &sin,
-					   sizeof(sin));
+		err = __ip4_datagram_connect(sk,
+					     (struct sockaddr *) &sin,
+					     sizeof(sin));
 
 ipv4_connected:
 		if (err)
@@ -204,6 +204,16 @@ out:
 	fl6_sock_release(flowlabel);
 	return err;
 }
+
+int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+{
+	int res;
+
+	lock_sock(sk);
+	res = __ip6_datagram_connect(sk, uaddr, addr_len);
+	release_sock(sk);
+	return res;
+}
 EXPORT_SYMBOL_GPL(ip6_datagram_connect);
 
 int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr *uaddr,
-- 
2.1.0


From 75d9fbc7e42fe45d9c5f40b6d7ef8a89ea1278e4 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Wed, 15 Jul 2015 21:52:51 +0200
Subject: [PATCH 18/32] bonding: fix destruction of bond with devices different
 from arphrd_ether

[ Upstream commit 06f6d1094aa0992432b1e2a0920b0ee86ccd83bf ]

When the bonding is being unloaded and the netdevice notifier is
unregistered it executes NETDEV_UNREGISTER for each device which should
remove the bond's proc entry but if the device enslaved is not of
ARPHRD_ETHER type and is in front of the bonding, it may execute
bond_release_and_destroy() first which would release the last slave and
destroy the bond device leaving the proc entry and thus we will get the
following error (with dynamic debug on for bond_netdev_event to see the
events order):
[  908.963051] eql: event: 9
[  908.963052] eql: IFF_SLAVE
[  908.963054] eql: event: 2
[  908.963056] eql: IFF_SLAVE
[  908.963058] eql: event: 6
[  908.963059] eql: IFF_SLAVE
[  908.963110] bond0: Releasing active interface eql
[  908.976168] bond0: Destroying bond bond0
[  908.976266] bond0 (unregistering): Released all slaves
[  908.984097] ------------[ cut here ]------------
[  908.984107] WARNING: CPU: 0 PID: 1787 at fs/proc/generic.c:575
remove_proc_entry+0x112/0x160()
[  908.984110] remove_proc_entry: removing non-empty directory
'net/bonding', leaking at least 'bond0'
[  908.984111] Modules linked in: bonding(-) eql(O) 9p nfsd auth_rpcgss
oid_registry nfs_acl nfs lockd grace fscache sunrpc crct10dif_pclmul
crc32_pclmul crc32c_intel ghash_clmulni_intel ppdev qxl drm_kms_helper
snd_hda_codec_generic aesni_intel ttm aes_x86_64 glue_helper pcspkr lrw
gf128mul ablk_helper cryptd snd_hda_intel virtio_console snd_hda_codec
psmouse serio_raw snd_hwdep snd_hda_core 9pnet_virtio 9pnet evdev joydev
drm virtio_balloon snd_pcm snd_timer snd soundcore i2c_piix4 i2c_core
pvpanic acpi_cpufreq parport_pc parport processor thermal_sys button
autofs4 ext4 crc16 mbcache jbd2 hid_generic usbhid hid sg sr_mod cdrom
ata_generic virtio_blk virtio_net floppy ata_piix e1000 libata ehci_pci
virtio_pci scsi_mod uhci_hcd ehci_hcd virtio_ring virtio usbcore
usb_common [last unloaded: bonding]

[  908.984168] CPU: 0 PID: 1787 Comm: rmmod Tainted: G        W  O
4.2.0-rc2+ #8
[  908.984170] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
[  908.984172]  0000000000000000 ffffffff81732d41 ffffffff81525b34
ffff8800358dfda8
[  908.984175]  ffffffff8106c521 ffff88003595af78 ffff88003595af40
ffff88003e3a4280
[  908.984178]  ffffffffa058d040 0000000000000000 ffffffff8106c59a
ffffffff8172ebd0
[  908.984181] Call Trace:
[  908.984188]  [<ffffffff81525b34>] ? dump_stack+0x40/0x50
[  908.984193]  [<ffffffff8106c521>] ? warn_slowpath_common+0x81/0xb0
[  908.984196]  [<ffffffff8106c59a>] ? warn_slowpath_fmt+0x4a/0x50
[  908.984199]  [<ffffffff81218352>] ? remove_proc_entry+0x112/0x160
[  908.984205]  [<ffffffffa05850e6>] ? bond_destroy_proc_dir+0x26/0x30
[bonding]
[  908.984208]  [<ffffffffa057540e>] ? bond_net_exit+0x8e/0xa0 [bonding]
[  908.984217]  [<ffffffff8142f407>] ? ops_exit_list.isra.4+0x37/0x70
[  908.984225]  [<ffffffff8142f52d>] ?
unregister_pernet_operations+0x8d/0xd0
[  908.984228]  [<ffffffff8142f58d>] ?
unregister_pernet_subsys+0x1d/0x30
[  908.984232]  [<ffffffffa0585269>] ? bonding_exit+0x23/0xdba [bonding]
[  908.984236]  [<ffffffff810e28ba>] ? SyS_delete_module+0x18a/0x250
[  908.984241]  [<ffffffff81086f99>] ? task_work_run+0x89/0xc0
[  908.984244]  [<ffffffff8152b732>] ?
entry_SYSCALL_64_fastpath+0x16/0x75
[  908.984247] ---[ end trace 7c006ed4abbef24b ]---

Thus remove the proc entry manually if bond_release_and_destroy() is
used. Because of the checks in bond_remove_proc_entry() it's not a
problem for a bond device to change namespaces (the bug fixed by the
Fixes commit) but since commit
f9399814927ad ("bonding: Don't allow bond devices to change network
namespaces.") that can't happen anyway.

Reported-by: Carol Soto <clsoto@linux.vnet.ibm.com>
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Fixes: a64d49c3dd50 ("bonding: Manage /proc/net/bonding/ entries from
                      the netdev events")
Tested-by: Carol L Soto <clsoto@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 1cc06c0..f32d50a 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1805,6 +1805,7 @@ static int  bond_release_and_destroy(struct net_device *bond_dev,
 		bond_dev->priv_flags |= IFF_DISABLE_NETPOLL;
 		netdev_info(bond_dev, "Destroying bond %s\n",
 			    bond_dev->name);
+		bond_remove_proc_entry(bond);
 		unregister_netdevice(bond_dev);
 	}
 	return ret;
-- 
2.1.0


From bceb01c7a04d77ae5874b1b0cc2b07e3fdaf93a5 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Mon, 20 Jul 2015 17:55:38 +0800
Subject: [PATCH 19/32] Revert "sit: Add gro callbacks to sit_offload"

[ Upstream commit fdbf5b097bbd9693a86c0b8bfdd071a9a2117cfc ]

This patch reverts 19424e052fb44da2f00d1a868cbb51f3e9f4bbb5 ("sit:
Add gro callbacks to sit_offload") because it generates packets
that cannot be handled even by our own GSO.

Reported-by: Wolfgang Walter <linux@stwm.de>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_offload.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 01e12d0..bfd5990 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -292,8 +292,6 @@ static struct packet_offload ipv6_packet_offload __read_mostly = {
 static const struct net_offload sit_offload = {
 	.callbacks = {
 		.gso_segment	= ipv6_gso_segment,
-		.gro_receive	= ipv6_gro_receive,
-		.gro_complete	= ipv6_gro_complete,
 	},
 };
 
-- 
2.1.0


From 2c2e1ff66a699a34c0d2eaab42d128577f0bf750 Mon Sep 17 00:00:00 2001
From: dingtianhong <dingtianhong@huawei.com>
Date: Thu, 16 Jul 2015 16:30:02 +0800
Subject: [PATCH 20/32] bonding: correct the MAC address for "follow"
 fail_over_mac policy

[ Upstream commit a951bc1e6ba58f11df5ed5ddc41311e10f5fd20b ]

The "follow" fail_over_mac policy is useful for multiport devices that
either become confused or incur a performance penalty when multiple
ports are programmed with the same MAC address, but the same MAC
address still may happened by this steps for this policy:

1) echo +eth0 > /sys/class/net/bond0/bonding/slaves
   bond0 has the same mac address with eth0, it is MAC1.

2) echo +eth1 > /sys/class/net/bond0/bonding/slaves
   eth1 is backup, eth1 has MAC2.

3) ifconfig eth0 down
   eth1 became active slave, bond will swap MAC for eth0 and eth1,
   so eth1 has MAC1, and eth0 has MAC2.

4) ifconfig eth1 down
   there is no active slave, and eth1 still has MAC1, eth2 has MAC2.

5) ifconfig eth0 up
   the eth0 became active slave again, the bond set eth0 to MAC1.

Something wrong here, then if you set eth1 up, the eth0 and eth1 will have the same
MAC address, it will break this policy for ACTIVE_BACKUP mode.

This patch will fix this problem by finding the old active slave and
swap them MAC address before change active slave.

Signed-off-by: Ding Tianhong <dingtianhong@huawei.com>
Tested-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index f32d50a..081dd70 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -622,6 +622,23 @@ static void bond_set_dev_addr(struct net_device *bond_dev,
 	call_netdevice_notifiers(NETDEV_CHANGEADDR, bond_dev);
 }
 
+static struct slave *bond_get_old_active(struct bonding *bond,
+					 struct slave *new_active)
+{
+	struct slave *slave;
+	struct list_head *iter;
+
+	bond_for_each_slave(bond, slave, iter) {
+		if (slave == new_active)
+			continue;
+
+		if (ether_addr_equal(bond->dev->dev_addr, slave->dev->dev_addr))
+			return slave;
+	}
+
+	return NULL;
+}
+
 /* bond_do_fail_over_mac
  *
  * Perform special MAC address swapping for fail_over_mac settings
@@ -649,6 +666,9 @@ static void bond_do_fail_over_mac(struct bonding *bond,
 		if (!new_active)
 			return;
 
+		if (!old_active)
+			old_active = bond_get_old_active(bond, new_active);
+
 		if (old_active) {
 			ether_addr_copy(tmp_mac, new_active->dev->dev_addr);
 			ether_addr_copy(saddr.sa_data,
-- 
2.1.0


From c89918f14242a37327ec7a88ba036efe5e589b3e Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 17 Jul 2015 22:38:43 +0200
Subject: [PATCH 21/32] sched: cls_bpf: fix panic on filter replace

[ Upstream commit f6bfc46da6292b630ba389592123f0dd02066172 ]

The following test case causes a NULL pointer dereference in cls_bpf:

  FOO="1,6 0 0 4294967295,"
  tc filter add dev foo parent 1: bpf bytecode "$FOO" flowid 1:1 action ok
  tc filter replace dev foo parent 1: pref 49152 handle 0x1 \
            bpf bytecode "$FOO" flowid 1:1 action drop

The problem is that commit 1f947bf151e9 ("net: sched: rcu'ify cls_bpf")
accidentally swapped the arguments of list_replace_rcu(), the old
element needs to be the first argument and the new element the second.

Fixes: 1f947bf151e9 ("net: sched: rcu'ify cls_bpf")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.r.fastabend@intel.com>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_bpf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index eed49d1..d923add 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -282,7 +282,7 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
 		goto errout;
 
 	if (oldprog) {
-		list_replace_rcu(&prog->link, &oldprog->link);
+		list_replace_rcu(&oldprog->link, &prog->link);
 		tcf_unbind_filter(tp, &oldprog->res);
 		call_rcu(&oldprog->rcu, __cls_bpf_delete_prog);
 	} else {
-- 
2.1.0


From cddc5ab6b1cc775e37eb5914cf8d487dcbf456c7 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 17 Jul 2015 22:38:45 +0200
Subject: [PATCH 22/32] sched: cls_flow: fix panic on filter replace

[ Upstream commit 32b2f4b196b37695fdb42b31afcbc15399d6ef91 ]

The following test case causes a NULL pointer dereference in cls_flow:

  tc filter add dev foo parent 1: handle 0x1 flow hash keys dst action ok
  tc filter replace dev foo parent 1: pref 49152 handle 0x1 \
            flow hash keys mark action drop

To be more precise, actually two different panics are fixed, the first
occurs because tcf_exts_init() is not called on the newly allocated
filter when we do a replace. And the second panic uncovered after that
happens since the arguments of list_replace_rcu() are swapped, the old
element needs to be the first argument and the new element the second.

Fixes: 70da9f0bf999 ("net: sched: cls_flow use RCU")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_flow.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index 4ac515f..81a94b2 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -419,6 +419,8 @@ static int flow_change(struct net *net, struct sk_buff *in_skb,
 	if (!fnew)
 		goto err2;
 
+	tcf_exts_init(&fnew->exts, TCA_FLOW_ACT, TCA_FLOW_POLICE);
+
 	fold = (struct flow_filter *)*arg;
 	if (fold) {
 		err = -EINVAL;
@@ -483,7 +485,6 @@ static int flow_change(struct net *net, struct sk_buff *in_skb,
 		fnew->mask  = ~0U;
 		fnew->tp = tp;
 		get_random_bytes(&fnew->hashrnd, 4);
-		tcf_exts_init(&fnew->exts, TCA_FLOW_ACT, TCA_FLOW_POLICE);
 	}
 
 	fnew->perturb_timer.function = flow_perturbation;
@@ -523,7 +524,7 @@ static int flow_change(struct net *net, struct sk_buff *in_skb,
 	if (*arg == 0)
 		list_add_tail_rcu(&fnew->list, &head->filters);
 	else
-		list_replace_rcu(&fnew->list, &fold->list);
+		list_replace_rcu(&fold->list, &fnew->list);
 
 	*arg = (unsigned long)fnew;
 
-- 
2.1.0


From 6af4ef164fd5658e96d1312b1d917b0b334510ec Mon Sep 17 00:00:00 2001
From: Edward Hyunkoo Jee <edjee@google.com>
Date: Tue, 21 Jul 2015 09:43:59 +0200
Subject: [PATCH 23/32] inet: frags: fix defragmented packet's IP header for
 af_packet

[ Upstream commit 0848f6428ba3a2e42db124d41ac6f548655735bf ]

When ip_frag_queue() computes positions, it assumes that the passed
sk_buff does not contain L2 headers.

However, when PACKET_FANOUT_FLAG_DEFRAG is used, IP reassembly
functions can be called on outgoing packets that contain L2 headers.

Also, IPv4 checksum is not corrected after reassembly.

Fixes: 7736d33f4262 ("packet: Add pre-defragmentation support for ipv4 fanouts.")
Signed-off-by: Edward Hyunkoo Jee <edjee@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Jerry Chu <hkchu@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_fragment.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index b48e03cd6..95160318 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -342,7 +342,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 	ihl = ip_hdrlen(skb);
 
 	/* Determine the position of this fragment. */
-	end = offset + skb->len - ihl;
+	end = offset + skb->len - skb_network_offset(skb) - ihl;
 	err = -EINVAL;
 
 	/* Is this the final fragment? */
@@ -372,7 +372,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 		goto err;
 
 	err = -ENOMEM;
-	if (pskb_pull(skb, ihl) == NULL)
+	if (!pskb_pull(skb, skb_network_offset(skb) + ihl))
 		goto err;
 
 	err = pskb_trim_rcsum(skb, end - offset);
@@ -612,6 +612,9 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 	iph->frag_off = qp->q.max_size ? htons(IP_DF) : 0;
 	iph->tot_len = htons(len);
 	iph->tos |= ecn;
+
+	ip_send_check(iph);
+
 	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMOKS);
 	qp->q.fragments = NULL;
 	qp->q.fragments_tail = NULL;
-- 
2.1.0


From 33a3b9efa3318dda6e1e4abf742e1f6e433531dd Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 21 Jul 2015 16:33:50 +0200
Subject: [PATCH 24/32] netlink: don't hold mutex in rcu callback when
 releasing mmapd ring

[ Upstream commit 0470eb99b4721586ccac954faac3fa4472da0845 ]

Kirill A. Shutemov says:

This simple test-case trigers few locking asserts in kernel:

int main(int argc, char **argv)
{
        unsigned int block_size = 16 * 4096;
        struct nl_mmap_req req = {
                .nm_block_size          = block_size,
                .nm_block_nr            = 64,
                .nm_frame_size          = 16384,
                .nm_frame_nr            = 64 * block_size / 16384,
        };
        unsigned int ring_size;
	int fd;

	fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_GENERIC);
        if (setsockopt(fd, SOL_NETLINK, NETLINK_RX_RING, &req, sizeof(req)) < 0)
                exit(1);
        if (setsockopt(fd, SOL_NETLINK, NETLINK_TX_RING, &req, sizeof(req)) < 0)
                exit(1);

	ring_size = req.nm_block_nr * req.nm_block_size;
	mmap(NULL, 2 * ring_size, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0);
	return 0;
}

+++ exited with 0 +++
BUG: sleeping function called from invalid context at /home/kas/git/public/linux-mm/kernel/locking/mutex.c:616
in_atomic(): 1, irqs_disabled(): 0, pid: 1, name: init
3 locks held by init/1:
 #0:  (reboot_mutex){+.+...}, at: [<ffffffff81080959>] SyS_reboot+0xa9/0x220
 #1:  ((reboot_notifier_list).rwsem){.+.+..}, at: [<ffffffff8107f379>] __blocking_notifier_call_chain+0x39/0x70
 #2:  (rcu_callback){......}, at: [<ffffffff810d32e0>] rcu_do_batch.isra.49+0x160/0x10c0
Preemption disabled at:[<ffffffff8145365f>] __delay+0xf/0x20

CPU: 1 PID: 1 Comm: init Not tainted 4.1.0-00009-gbddf4c4818e0 #253
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS Debian-1.8.2-1 04/01/2014
 ffff88017b3d8000 ffff88027bc03c38 ffffffff81929ceb 0000000000000102
 0000000000000000 ffff88027bc03c68 ffffffff81085a9d 0000000000000002
 ffffffff81ca2a20 0000000000000268 0000000000000000 ffff88027bc03c98
Call Trace:
 <IRQ>  [<ffffffff81929ceb>] dump_stack+0x4f/0x7b
 [<ffffffff81085a9d>] ___might_sleep+0x16d/0x270
 [<ffffffff81085bed>] __might_sleep+0x4d/0x90
 [<ffffffff8192e96f>] mutex_lock_nested+0x2f/0x430
 [<ffffffff81932fed>] ? _raw_spin_unlock_irqrestore+0x5d/0x80
 [<ffffffff81464143>] ? __this_cpu_preempt_check+0x13/0x20
 [<ffffffff8182fc3d>] netlink_set_ring+0x1ed/0x350
 [<ffffffff8182e000>] ? netlink_undo_bind+0x70/0x70
 [<ffffffff8182fe20>] netlink_sock_destruct+0x80/0x150
 [<ffffffff817e484d>] __sk_free+0x1d/0x160
 [<ffffffff817e49a9>] sk_free+0x19/0x20
[..]

Cong Wang says:

We can't hold mutex lock in a rcu callback, [..]

Thomas Graf says:

The socket should be dead at this point. It might be simpler to
add a netlink_release_ring() function which doesn't require
locking at all.

Reported-by: "Kirill A. Shutemov" <kirill@shutemov.name>
Diagnosed-by: Cong Wang <cwang@twopensource.com>
Suggested-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 79 ++++++++++++++++++++++++++++--------------------
 1 file changed, 47 insertions(+), 32 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index c82b2e3..6ffd1eb 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -366,25 +366,52 @@ err1:
 	return NULL;
 }
 
+
+static void
+__netlink_set_ring(struct sock *sk, struct nl_mmap_req *req, bool tx_ring, void **pg_vec,
+		   unsigned int order)
+{
+	struct netlink_sock *nlk = nlk_sk(sk);
+	struct sk_buff_head *queue;
+	struct netlink_ring *ring;
+
+	queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue;
+	ring  = tx_ring ? &nlk->tx_ring : &nlk->rx_ring;
+
+	spin_lock_bh(&queue->lock);
+
+	ring->frame_max		= req->nm_frame_nr - 1;
+	ring->head		= 0;
+	ring->frame_size	= req->nm_frame_size;
+	ring->pg_vec_pages	= req->nm_block_size / PAGE_SIZE;
+
+	swap(ring->pg_vec_len, req->nm_block_nr);
+	swap(ring->pg_vec_order, order);
+	swap(ring->pg_vec, pg_vec);
+
+	__skb_queue_purge(queue);
+	spin_unlock_bh(&queue->lock);
+
+	WARN_ON(atomic_read(&nlk->mapped));
+
+	if (pg_vec)
+		free_pg_vec(pg_vec, order, req->nm_block_nr);
+}
+
 static int netlink_set_ring(struct sock *sk, struct nl_mmap_req *req,
-			    bool closing, bool tx_ring)
+			    bool tx_ring)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
 	struct netlink_ring *ring;
-	struct sk_buff_head *queue;
 	void **pg_vec = NULL;
 	unsigned int order = 0;
-	int err;
 
 	ring  = tx_ring ? &nlk->tx_ring : &nlk->rx_ring;
-	queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue;
 
-	if (!closing) {
-		if (atomic_read(&nlk->mapped))
-			return -EBUSY;
-		if (atomic_read(&ring->pending))
-			return -EBUSY;
-	}
+	if (atomic_read(&nlk->mapped))
+		return -EBUSY;
+	if (atomic_read(&ring->pending))
+		return -EBUSY;
 
 	if (req->nm_block_nr) {
 		if (ring->pg_vec != NULL)
@@ -416,31 +443,19 @@ static int netlink_set_ring(struct sock *sk, struct nl_mmap_req *req,
 			return -EINVAL;
 	}
 
-	err = -EBUSY;
 	mutex_lock(&nlk->pg_vec_lock);
-	if (closing || atomic_read(&nlk->mapped) == 0) {
-		err = 0;
-		spin_lock_bh(&queue->lock);
-
-		ring->frame_max		= req->nm_frame_nr - 1;
-		ring->head		= 0;
-		ring->frame_size	= req->nm_frame_size;
-		ring->pg_vec_pages	= req->nm_block_size / PAGE_SIZE;
-
-		swap(ring->pg_vec_len, req->nm_block_nr);
-		swap(ring->pg_vec_order, order);
-		swap(ring->pg_vec, pg_vec);
-
-		__skb_queue_purge(queue);
-		spin_unlock_bh(&queue->lock);
-
-		WARN_ON(atomic_read(&nlk->mapped));
+	if (atomic_read(&nlk->mapped) == 0) {
+		__netlink_set_ring(sk, req, tx_ring, pg_vec, order);
+		mutex_unlock(&nlk->pg_vec_lock);
+		return 0;
 	}
+
 	mutex_unlock(&nlk->pg_vec_lock);
 
 	if (pg_vec)
 		free_pg_vec(pg_vec, order, req->nm_block_nr);
-	return err;
+
+	return -EBUSY;
 }
 
 static void netlink_mm_open(struct vm_area_struct *vma)
@@ -909,10 +924,10 @@ static void netlink_sock_destruct(struct sock *sk)
 
 		memset(&req, 0, sizeof(req));
 		if (nlk->rx_ring.pg_vec)
-			netlink_set_ring(sk, &req, true, false);
+			__netlink_set_ring(sk, &req, false, NULL, 0);
 		memset(&req, 0, sizeof(req));
 		if (nlk->tx_ring.pg_vec)
-			netlink_set_ring(sk, &req, true, true);
+			__netlink_set_ring(sk, &req, true, NULL, 0);
 	}
 #endif /* CONFIG_NETLINK_MMAP */
 
@@ -2163,7 +2178,7 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 			return -EINVAL;
 		if (copy_from_user(&req, optval, sizeof(req)))
 			return -EFAULT;
-		err = netlink_set_ring(sk, &req, false,
+		err = netlink_set_ring(sk, &req,
 				       optname == NETLINK_TX_RING);
 		break;
 	}
-- 
2.1.0


From 064bf4924b87d153d99b0afaf4e0f2d7d95c5751 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Wed, 22 Jul 2015 13:03:40 +0200
Subject: [PATCH 25/32] bridge: netlink: fix slave_changelink/br_setport race
 conditions

[ Upstream commit 963ad94853000ab100f5ff19eea80095660d41b4 ]

Since slave_changelink support was added there have been a few race
conditions when using br_setport() since some of the port functions it
uses require the bridge lock. It is very easy to trigger a lockup due to
some internal spin_lock() usage without bh disabled, also it's possible to
get the bridge into an inconsistent state.

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Fixes: 3ac636b8591c ("bridge: implement rtnl_link_ops->slave_changelink")
Reviewed-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_netlink.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index e5ec470..3659f90 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -464,9 +464,17 @@ static int br_port_slave_changelink(struct net_device *brdev,
 				    struct nlattr *tb[],
 				    struct nlattr *data[])
 {
+	struct net_bridge *br = netdev_priv(brdev);
+	int ret;
+
 	if (!data)
 		return 0;
-	return br_setport(br_port_get_rtnl(dev), data);
+
+	spin_lock_bh(&br->lock);
+	ret = br_setport(br_port_get_rtnl(dev), data);
+	spin_unlock_bh(&br->lock);
+
+	return ret;
 }
 
 static int br_port_fill_slave_info(struct sk_buff *skb,
-- 
2.1.0


From b994909618ac305515f0bb96a91c24033271859a Mon Sep 17 00:00:00 2001
From: Jack Morgenstein <jackm@dev.mellanox.co.il>
Date: Wed, 22 Jul 2015 16:53:47 +0300
Subject: [PATCH 26/32] net/mlx4_core: Fix wrong index in propagating port
 change event to VFs

[ Upstream commit 1c1bf34951e8d17941bf708d1901c47e81b15d55 ]

The port-change event processing in procedure mlx4_eq_int() uses "slave"
as the vf_oper array index. Since the value of "slave" is the PF function
index, the result is that the PF link state is used for deciding to
propagate the event for all the VFs. The VF link state should be used,
so the VF function index should be used here.

Fixes: 948e306d7d64 ('net/mlx4: Add VF link state support')
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/eq.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index 49290a4..af67e7d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -568,7 +568,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 							continue;
 						mlx4_dbg(dev, "%s: Sending MLX4_PORT_CHANGE_SUBTYPE_DOWN to slave: %d, port:%d\n",
 							 __func__, i, port);
-						s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state;
+						s_info = &priv->mfunc.master.vf_oper[i].vport[port].state;
 						if (IFLA_VF_LINK_STATE_AUTO == s_info->link_state) {
 							eqe->event.port_change.port =
 								cpu_to_be32(
@@ -601,7 +601,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 							continue;
 						if (i == mlx4_master_func_num(dev))
 							continue;
-						s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state;
+						s_info = &priv->mfunc.master.vf_oper[i].vport[port].state;
 						if (IFLA_VF_LINK_STATE_AUTO == s_info->link_state) {
 							eqe->event.port_change.port =
 								cpu_to_be32(
-- 
2.1.0


From a5752582562aad04f18608580cd209d3f82afcac Mon Sep 17 00:00:00 2001
From: Lars Westerhoff <lars.westerhoff@newtec.eu>
Date: Tue, 28 Jul 2015 01:32:21 +0300
Subject: [PATCH 27/32] packet: missing dev_put() in packet_do_bind()

[ Upstream commit 158cd4af8dedbda0d612d448c724c715d0dda649 ]

When binding a PF_PACKET socket, the use count of the bound interface is
always increased with dev_hold in dev_get_by_{index,name}.  However,
when rebound with the same protocol and device as in the previous bind
the use count of the interface was not decreased.  Ultimately, this
caused the deletion of the interface to fail with the following message:

unregister_netdevice: waiting for dummy0 to become free. Usage count = 1

This patch moves the dev_put out of the conditional part that was only
executed when either the protocol or device changed on a bind.

Fixes: 902fefb82ef7 ('packet: improve socket create/bind latency in some cases')
Signed-off-by: Lars Westerhoff <lars.westerhoff@newtec.eu>
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 5dcfe05..bf60977 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2645,7 +2645,7 @@ static int packet_release(struct socket *sock)
 static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
 {
 	struct packet_sock *po = pkt_sk(sk);
-	const struct net_device *dev_curr;
+	struct net_device *dev_curr;
 	__be16 proto_curr;
 	bool need_rehook;
 
@@ -2669,15 +2669,13 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
 
 		po->num = proto;
 		po->prot_hook.type = proto;
-
-		if (po->prot_hook.dev)
-			dev_put(po->prot_hook.dev);
-
 		po->prot_hook.dev = dev;
 
 		po->ifindex = dev ? dev->ifindex : 0;
 		packet_cached_dev_assign(po, dev);
 	}
+	if (dev_curr)
+		dev_put(dev_curr);
 
 	if (proto == 0 || !need_rehook)
 		goto out_unlock;
-- 
2.1.0


From 5ec22dd1fe7dfd6a65ed6ad9983301ba8ea2f529 Mon Sep 17 00:00:00 2001
From: Alexander Drozdov <al.drozdov@gmail.com>
Date: Tue, 28 Jul 2015 13:57:01 +0300
Subject: [PATCH 28/32] packet: tpacket_snd(): fix signed/unsigned comparison

[ Upstream commit dbd46ab412b8fb395f2b0ff6f6a7eec9df311550 ]

tpacket_fill_skb() can return a negative value (-errno) which
is stored in tp_len variable. In that case the following
condition will be (but shouldn't be) true:

tp_len > dev->mtu + dev->hard_header_len

as dev->mtu and dev->hard_header_len are both unsigned.

That may lead to just returning an incorrect EMSGSIZE errno
to the user.

Fixes: 52f1454f629fa ("packet: allow to transmit +4 byte in TX_RING slot for VLAN case")
Signed-off-by: Alexander Drozdov <al.drozdov@gmail.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index bf60977..785256f 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2274,7 +2274,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 
 		tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto,
 					  addr, hlen);
-		if (tp_len > dev->mtu + dev->hard_header_len) {
+		if (likely(tp_len >= 0) &&
+		    tp_len > dev->mtu + dev->hard_header_len) {
 			struct ethhdr *ehdr;
 			/* Earlier code assumed this would be a VLAN pkt,
 			 * double-check this now that we have the actual
-- 
2.1.0


From d74e371dc25d352c4dd9446df2bf46dd80cf0f71 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 29 Jul 2015 23:35:25 +0200
Subject: [PATCH 29/32] net: sched: fix refcount imbalance in actions

[ Upstream commit 28e6b67f0b292f557468c139085303b15f1a678f ]

Since commit 55334a5db5cd ("net_sched: act: refuse to remove bound action
outside"), we end up with a wrong reference count for a tc action.

Test case 1:

  FOO="1,6 0 0 4294967295,"
  BAR="1,6 0 0 4294967294,"
  tc filter add dev foo parent 1: bpf bytecode "$FOO" flowid 1:1 \
     action bpf bytecode "$FOO"
  tc actions show action bpf
    action order 0: bpf bytecode '1,6 0 0 4294967295' default-action pipe
    index 1 ref 1 bind 1
  tc actions replace action bpf bytecode "$BAR" index 1
  tc actions show action bpf
    action order 0: bpf bytecode '1,6 0 0 4294967294' default-action pipe
    index 1 ref 2 bind 1
  tc actions replace action bpf bytecode "$FOO" index 1
  tc actions show action bpf
    action order 0: bpf bytecode '1,6 0 0 4294967295' default-action pipe
    index 1 ref 3 bind 1

Test case 2:

  FOO="1,6 0 0 4294967295,"
  tc filter add dev foo parent 1: bpf bytecode "$FOO" flowid 1:1 action ok
  tc actions show action gact
    action order 0: gact action pass
    random type none pass val 0
     index 1 ref 1 bind 1
  tc actions add action drop index 1
    RTNETLINK answers: File exists [...]
  tc actions show action gact
    action order 0: gact action pass
     random type none pass val 0
     index 1 ref 2 bind 1
  tc actions add action drop index 1
    RTNETLINK answers: File exists [...]
  tc actions show action gact
    action order 0: gact action pass
     random type none pass val 0
     index 1 ref 3 bind 1

What happens is that in tcf_hash_check(), we check tcf_common for a given
index and increase tcfc_refcnt and conditionally tcfc_bindcnt when we've
found an existing action. Now there are the following cases:

  1) We do a late binding of an action. In that case, we leave the
     tcfc_refcnt/tcfc_bindcnt increased and are done with the ->init()
     handler. This is correctly handeled.

  2) We replace the given action, or we try to add one without replacing
     and find out that the action at a specific index already exists
     (thus, we go out with error in that case).

In case of 2), we have to undo the reference count increase from
tcf_hash_check() in the tcf_hash_check() function. Currently, we fail to
do so because of the 'tcfc_bindcnt > 0' check which bails out early with
an -EPERM error.

Now, while commit 55334a5db5cd prevents 'tc actions del action ...' on an
already classifier-bound action to drop the reference count (which could
then become negative, wrap around etc), this restriction only accounts for
invocations outside a specific action's ->init() handler.

One possible solution would be to add a flag thus we possibly trigger
the -EPERM ony in situations where it is indeed relevant.

After the patch, above test cases have correct reference count again.

Fixes: 55334a5db5cd ("net_sched: act: refuse to remove bound action outside")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Cong Wang <cwang@twopensource.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/act_api.h |  8 +++++++-
 net/sched/act_api.c   | 11 ++++++-----
 2 files changed, 13 insertions(+), 6 deletions(-)

diff --git a/include/net/act_api.h b/include/net/act_api.h
index 3ee4c92..931738b 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -99,7 +99,6 @@ struct tc_action_ops {
 
 int tcf_hash_search(struct tc_action *a, u32 index);
 void tcf_hash_destroy(struct tc_action *a);
-int tcf_hash_release(struct tc_action *a, int bind);
 u32 tcf_hash_new_index(struct tcf_hashinfo *hinfo);
 int tcf_hash_check(u32 index, struct tc_action *a, int bind);
 int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a,
@@ -107,6 +106,13 @@ int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a,
 void tcf_hash_cleanup(struct tc_action *a, struct nlattr *est);
 void tcf_hash_insert(struct tc_action *a);
 
+int __tcf_hash_release(struct tc_action *a, bool bind, bool strict);
+
+static inline int tcf_hash_release(struct tc_action *a, bool bind)
+{
+	return __tcf_hash_release(a, bind, false);
+}
+
 int tcf_register_action(struct tc_action_ops *a, unsigned int mask);
 int tcf_unregister_action(struct tc_action_ops *a);
 int tcf_action_destroy(struct list_head *actions, int bind);
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 3d43e49..f8d9c2a 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -45,7 +45,7 @@ void tcf_hash_destroy(struct tc_action *a)
 }
 EXPORT_SYMBOL(tcf_hash_destroy);
 
-int tcf_hash_release(struct tc_action *a, int bind)
+int __tcf_hash_release(struct tc_action *a, bool bind, bool strict)
 {
 	struct tcf_common *p = a->priv;
 	int ret = 0;
@@ -53,7 +53,7 @@ int tcf_hash_release(struct tc_action *a, int bind)
 	if (p) {
 		if (bind)
 			p->tcfc_bindcnt--;
-		else if (p->tcfc_bindcnt > 0)
+		else if (strict && p->tcfc_bindcnt > 0)
 			return -EPERM;
 
 		p->tcfc_refcnt--;
@@ -64,9 +64,10 @@ int tcf_hash_release(struct tc_action *a, int bind)
 			ret = 1;
 		}
 	}
+
 	return ret;
 }
-EXPORT_SYMBOL(tcf_hash_release);
+EXPORT_SYMBOL(__tcf_hash_release);
 
 static int tcf_dump_walker(struct sk_buff *skb, struct netlink_callback *cb,
 			   struct tc_action *a)
@@ -136,7 +137,7 @@ static int tcf_del_walker(struct sk_buff *skb, struct tc_action *a)
 		head = &hinfo->htab[tcf_hash(i, hinfo->hmask)];
 		hlist_for_each_entry_safe(p, n, head, tcfc_head) {
 			a->priv = p;
-			ret = tcf_hash_release(a, 0);
+			ret = __tcf_hash_release(a, false, true);
 			if (ret == ACT_P_DELETED) {
 				module_put(a->ops->owner);
 				n_i++;
@@ -413,7 +414,7 @@ int tcf_action_destroy(struct list_head *actions, int bind)
 	int ret = 0;
 
 	list_for_each_entry_safe(a, tmp, actions, list) {
-		ret = tcf_hash_release(a, bind);
+		ret = __tcf_hash_release(a, bind, true);
 		if (ret == ACT_P_DELETED)
 			module_put(a->ops->owner);
 		else if (ret < 0)
-- 
2.1.0


From 2a3460186f37862fc69bc4b003c0fd936a942f2f Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Sat, 1 Aug 2015 15:33:26 +0300
Subject: [PATCH 30/32] rds: fix an integer overflow test in
 rds_info_getsockopt()

[ Upstream commit 468b732b6f76b138c0926eadf38ac88467dcd271 ]

"len" is a signed integer.  We check that len is not negative, so it
goes from zero to INT_MAX.  PAGE_SIZE is unsigned long so the comparison
is type promoted to unsigned long.  ULONG_MAX - 4095 is a higher than
INT_MAX so the condition can never be true.

I don't know if this is harmful but it seems safe to limit "len" to
INT_MAX - 4095.

Fixes: a8c879a7ee98 ('RDS: Info and stats')
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/info.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/rds/info.c b/net/rds/info.c
index 9a6b4f6..140a44a 100644
--- a/net/rds/info.c
+++ b/net/rds/info.c
@@ -176,7 +176,7 @@ int rds_info_getsockopt(struct socket *sock, int optname, char __user *optval,
 
 	/* check for all kinds of wrapping and the like */
 	start = (unsigned long)optval;
-	if (len < 0 || len + PAGE_SIZE - 1 < len || start + len < start) {
+	if (len < 0 || len > INT_MAX - PAGE_SIZE + 1 || start + len < start) {
 		ret = -EINVAL;
 		goto out;
 	}
-- 
2.1.0


From 1466a93cd95381d9cab3e994a88f0ba56ccd4fd1 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 1 Aug 2015 12:14:33 +0200
Subject: [PATCH 31/32] udp: fix dst races with multicast early demux
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 10e2eb878f3ca07ac2f05fa5ca5e6c4c9174a27a ]

Multicast dst are not cached. They carry DST_NOCACHE.

As mentioned in commit f8864972126899 ("ipv4: fix dst race in
sk_dst_get()"), these dst need special care before caching them
into a socket.

Caching them is allowed only if their refcnt was not 0, ie we
must use atomic_inc_not_zero()

Also, we must use READ_ONCE() to fetch sk->sk_rx_dst, as mentioned
in commit d0c294c53a771 ("tcp: prevent fetching dst twice in early demux
code")

Fixes: 421b3885bf6d ("udp: ipv4: Add udp early demux")
Tested-by: Gregory Hoggarth <Gregory.Hoggarth@alliedtelesis.co.nz>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Gregory Hoggarth <Gregory.Hoggarth@alliedtelesis.co.nz>
Reported-by: Alex Gartrell <agartrell@fb.com>
Cc: Michal Kubeček <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index c5e3194..4ea9753 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1983,12 +1983,19 @@ void udp_v4_early_demux(struct sk_buff *skb)
 
 	skb->sk = sk;
 	skb->destructor = sock_efree;
-	dst = sk->sk_rx_dst;
+	dst = READ_ONCE(sk->sk_rx_dst);
 
 	if (dst)
 		dst = dst_check(dst, 0);
-	if (dst)
-		skb_dst_set_noref(skb, dst);
+	if (dst) {
+		/* DST_NOCACHE can not be used without taking a reference */
+		if (dst->flags & DST_NOCACHE) {
+			if (likely(atomic_inc_not_zero(&dst->__refcnt)))
+				skb_dst_set(skb, dst);
+		} else {
+			skb_dst_set_noref(skb, dst);
+		}
+	}
 }
 
 int udp_rcv(struct sk_buff *skb)
-- 
2.1.0


From abda36edc37aa66ff9cbec740366598b144ab27f Mon Sep 17 00:00:00 2001
From: Ivan Vecera <ivecera@redhat.com>
Date: Thu, 6 Aug 2015 22:48:23 +0200
Subject: [PATCH 32/32] bna: fix interrupts storm caused by erroneous packets

[ Upstream commit ade4dc3e616e33c80d7e62855fe1b6f9895bc7c3 ]

The commit "e29aa33 bna: Enable Multi Buffer RX" moved packets counter
increment from the beginning of the NAPI processing loop after the check
for erroneous packets so they are never accounted. This counter is used
to inform firmware about number of processed completions (packets).
As these packets are never acked the firmware fires IRQs for them again
and again.

Fixes: e29aa33 ("bna: Enable Multi Buffer RX")
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Acked-by: Rasesh Mody <rasesh.mody@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/brocade/bna/bnad.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index c3861de..d864614 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -674,6 +674,7 @@ bnad_cq_process(struct bnad *bnad, struct bna_ccb *ccb, int budget)
 			if (!next_cmpl->valid)
 				break;
 		}
+		packets++;
 
 		/* TODO: BNA_CQ_EF_LOCAL ? */
 		if (unlikely(flags & (BNA_CQ_EF_MAC_ERROR |
@@ -690,7 +691,6 @@ bnad_cq_process(struct bnad *bnad, struct bna_ccb *ccb, int budget)
 		else
 			bnad_cq_setup_skb_frags(rcb, skb, sop_ci, nvecs, len);
 
-		packets++;
 		rcb->rxq->rx_packets++;
 		rcb->rxq->rx_bytes += totlen;
 		ccb->bytes_per_intr += totlen;
-- 
2.1.0


[-- Attachment #5: net_41.mbox --]
[-- Type: Application/Octet-Stream, Size: 111930 bytes --]

From 8c2854df13fbdfb163bc66939d6d09bb0ca306f6 Mon Sep 17 00:00:00 2001
From: Angga <Hermin.Anggawijaya@alliedtelesis.co.nz>
Date: Fri, 3 Jul 2015 14:40:52 +1200
Subject: [PATCH 01/46] ipv6: Make MLD packets to only be processed locally

[ Upstream commit 4c938d22c88a9ddccc8c55a85e0430e9c62b1ac5 ]

Before commit daad151263cf ("ipv6: Make ipv6_is_mld() inline and use it
from ip6_mc_input().") MLD packets were only processed locally. After the
change, a copy of MLD packet goes through ip6_mr_input, causing
MRT6MSG_NOCACHE message to be generated to user space.

Make MLD packet only processed locally.

Fixes: daad151263cf ("ipv6: Make ipv6_is_mld() inline and use it from ip6_mc_input().")
Signed-off-by: Hermin Anggawijaya <hermin.anggawijaya@alliedtelesis.co.nz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_input.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index f2e464e..57990c9 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -331,10 +331,10 @@ int ip6_mc_input(struct sk_buff *skb)
 				if (offset < 0)
 					goto out;
 
-				if (!ipv6_is_mld(skb, nexthdr, offset))
-					goto out;
+				if (ipv6_is_mld(skb, nexthdr, offset))
+					deliver = true;
 
-				deliver = true;
+				goto out;
 			}
 			/* unknown RA - process it normally */
 		}
-- 
2.1.0


From b8c2c9a2ae175da385649f0855b9b9fb03b6a799 Mon Sep 17 00:00:00 2001
From: Phil Sutter <phil@nwl.cc>
Date: Mon, 6 Jul 2015 15:51:20 +0200
Subject: [PATCH 02/46] rhashtable: fix for resize events during table walk

[ Upstream commit 142b942a75cb10ede1b42bf85368d41449ab4e3b ]

If rhashtable_walk_next detects a resize operation in progress, it jumps
to the new table and continues walking that one. But it misses to drop
the reference to it's current item, leading it to continue traversing
the new table's bucket in which the current item is sorted into, and
after reaching that bucket's end continues traversing the new table's
second bucket instead of the first one, thereby potentially missing
items.

This fixes the rhashtable runtime test for me. Bug probably introduced
by Herbert Xu's patch eddee5ba ("rhashtable: Fix walker behaviour during
rehash") although not explicitly tested.

Fixes: eddee5ba ("rhashtable: Fix walker behaviour during rehash")
Signed-off-by: Phil Sutter <phil@nwl.cc>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 lib/rhashtable.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 8609378..cf910e4 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -612,6 +612,8 @@ next:
 		iter->skip = 0;
 	}
 
+	iter->p = NULL;
+
 	/* Ensure we see any new tables. */
 	smp_rmb();
 
@@ -622,8 +624,6 @@ next:
 		return ERR_PTR(-EAGAIN);
 	}
 
-	iter->p = NULL;
-
 out:
 
 	return obj;
-- 
2.1.0


From 1ab639a7e8ab4f2263a5fdd611b33e0b9aff6b09 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 6 Jul 2015 17:13:26 +0200
Subject: [PATCH 03/46] net: graceful exit from netif_alloc_netdev_queues()

[ Upstream commit d339727c2b1a10f25e6636670ab6e1841170e328 ]

User space can crash kernel with

ip link add ifb10 numtxqueues 100000 type ifb

We must replace a BUG_ON() by proper test and return -EINVAL for
crazy values.

Fixes: 60877a32bce00 ("net: allow large number of tx queues")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index aa82f9a..4723914 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6297,7 +6297,8 @@ static int netif_alloc_netdev_queues(struct net_device *dev)
 	struct netdev_queue *tx;
 	size_t sz = count * sizeof(*tx);
 
-	BUG_ON(count < 1 || count > 0xffff);
+	if (count < 1 || count > 0xffff)
+		return -EINVAL;
 
 	tx = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
 	if (!tx) {
-- 
2.1.0


From fa72557a85e0032a819bcd857de185da10799dd4 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Mon, 6 Jul 2015 17:25:10 +0200
Subject: [PATCH 04/46] Revert "dev: set iflink to 0 for virtual interfaces"

[ Upstream commit 95ec655bc465ccb2a3329d4aff9a45e3c8188db5 ]

This reverts commit e1622baf54df8cc958bf29d71de5ad545ea7d93c.

The side effect of this commit is to add a '@NONE' after each virtual
interface name with a 'ip link'. It may break existing scripts.

Reported-by: Olivier Hartkopp <socketcan@hartkopp.net>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Tested-by: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 4723914..877ec57 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -672,10 +672,6 @@ int dev_get_iflink(const struct net_device *dev)
 	if (dev->netdev_ops && dev->netdev_ops->ndo_get_iflink)
 		return dev->netdev_ops->ndo_get_iflink(dev);
 
-	/* If dev->rtnl_link_ops is set, it's a virtual interface. */
-	if (dev->rtnl_link_ops)
-		return 0;
-
 	return dev->ifindex;
 }
 EXPORT_SYMBOL(dev_get_iflink);
-- 
2.1.0


From 75cead319911eab1b9813c55274b391128329d9b Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Tue, 7 Jul 2015 00:07:52 +0200
Subject: [PATCH 05/46] rtnetlink: verify IFLA_VF_INFO attributes before
 passing them to driver

[ Upstream commit 4f7d2cdfdde71ffe962399b7020c674050329423 ]

Jason Gunthorpe reported that since commit c02db8c6290b ("rtnetlink: make
SR-IOV VF interface symmetric"), we don't verify IFLA_VF_INFO attributes
anymore with respect to their policy, that is, ifla_vfinfo_policy[].

Before, they were part of ifla_policy[], but they have been nested since
placed under IFLA_VFINFO_LIST, that contains the attribute IFLA_VF_INFO,
which is another nested attribute for the actual VF attributes such as
IFLA_VF_MAC, IFLA_VF_VLAN, etc.

Despite the policy being split out from ifla_policy[] in this commit,
it's never applied anywhere. nla_for_each_nested() only does basic nla_ok()
testing for struct nlattr, but it doesn't know about the data context and
their requirements.

Fix, on top of Jason's initial work, does 1) parsing of the attributes
with the right policy, and 2) using the resulting parsed attribute table
from 1) instead of the nla_for_each_nested() loop (just like we used to
do when still part of ifla_policy[]).

Reference: http://thread.gmane.org/gmane.linux.network/368913
Fixes: c02db8c6290b ("rtnetlink: make SR-IOV VF interface symmetric")
Reported-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Cc: Chris Wright <chrisw@sous-sol.org>
Cc: Sucheta Chakraborty <sucheta.chakraborty@qlogic.com>
Cc: Greg Rose <gregory.v.rose@intel.com>
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Cc: Rony Efraim <ronye@mellanox.com>
Cc: Vlad Zolotarov <vladz@cloudius-systems.com>
Cc: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Cc: Thomas Graf <tgraf@suug.ch>
Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Vlad Zolotarov <vladz@cloudius-systems.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 187 ++++++++++++++++++++++++++-------------------------
 1 file changed, 96 insertions(+), 91 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 8de3682..fe95cb7 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1287,10 +1287,6 @@ static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
 	[IFLA_INFO_SLAVE_DATA]	= { .type = NLA_NESTED },
 };
 
-static const struct nla_policy ifla_vfinfo_policy[IFLA_VF_INFO_MAX+1] = {
-	[IFLA_VF_INFO]		= { .type = NLA_NESTED },
-};
-
 static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = {
 	[IFLA_VF_MAC]		= { .len = sizeof(struct ifla_vf_mac) },
 	[IFLA_VF_VLAN]		= { .len = sizeof(struct ifla_vf_vlan) },
@@ -1437,96 +1433,98 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[])
 	return 0;
 }
 
-static int do_setvfinfo(struct net_device *dev, struct nlattr *attr)
+static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
 {
-	int rem, err = -EINVAL;
-	struct nlattr *vf;
 	const struct net_device_ops *ops = dev->netdev_ops;
+	int err = -EINVAL;
 
-	nla_for_each_nested(vf, attr, rem) {
-		switch (nla_type(vf)) {
-		case IFLA_VF_MAC: {
-			struct ifla_vf_mac *ivm;
-			ivm = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_mac)
-				err = ops->ndo_set_vf_mac(dev, ivm->vf,
-							  ivm->mac);
-			break;
-		}
-		case IFLA_VF_VLAN: {
-			struct ifla_vf_vlan *ivv;
-			ivv = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_vlan)
-				err = ops->ndo_set_vf_vlan(dev, ivv->vf,
-							   ivv->vlan,
-							   ivv->qos);
-			break;
-		}
-		case IFLA_VF_TX_RATE: {
-			struct ifla_vf_tx_rate *ivt;
-			struct ifla_vf_info ivf;
-			ivt = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_get_vf_config)
-				err = ops->ndo_get_vf_config(dev, ivt->vf,
-							     &ivf);
-			if (err)
-				break;
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_rate)
-				err = ops->ndo_set_vf_rate(dev, ivt->vf,
-							   ivf.min_tx_rate,
-							   ivt->rate);
-			break;
-		}
-		case IFLA_VF_RATE: {
-			struct ifla_vf_rate *ivt;
-			ivt = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_rate)
-				err = ops->ndo_set_vf_rate(dev, ivt->vf,
-							   ivt->min_tx_rate,
-							   ivt->max_tx_rate);
-			break;
-		}
-		case IFLA_VF_SPOOFCHK: {
-			struct ifla_vf_spoofchk *ivs;
-			ivs = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_spoofchk)
-				err = ops->ndo_set_vf_spoofchk(dev, ivs->vf,
-							       ivs->setting);
-			break;
-		}
-		case IFLA_VF_LINK_STATE: {
-			struct ifla_vf_link_state *ivl;
-			ivl = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_link_state)
-				err = ops->ndo_set_vf_link_state(dev, ivl->vf,
-								 ivl->link_state);
-			break;
-		}
-		case IFLA_VF_RSS_QUERY_EN: {
-			struct ifla_vf_rss_query_en *ivrssq_en;
+	if (tb[IFLA_VF_MAC]) {
+		struct ifla_vf_mac *ivm = nla_data(tb[IFLA_VF_MAC]);
 
-			ivrssq_en = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_rss_query_en)
-				err = ops->ndo_set_vf_rss_query_en(dev,
-							    ivrssq_en->vf,
-							    ivrssq_en->setting);
-			break;
-		}
-		default:
-			err = -EINVAL;
-			break;
-		}
-		if (err)
-			break;
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_mac)
+			err = ops->ndo_set_vf_mac(dev, ivm->vf,
+						  ivm->mac);
+		if (err < 0)
+			return err;
+	}
+
+	if (tb[IFLA_VF_VLAN]) {
+		struct ifla_vf_vlan *ivv = nla_data(tb[IFLA_VF_VLAN]);
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_vlan)
+			err = ops->ndo_set_vf_vlan(dev, ivv->vf, ivv->vlan,
+						   ivv->qos);
+		if (err < 0)
+			return err;
+	}
+
+	if (tb[IFLA_VF_TX_RATE]) {
+		struct ifla_vf_tx_rate *ivt = nla_data(tb[IFLA_VF_TX_RATE]);
+		struct ifla_vf_info ivf;
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_get_vf_config)
+			err = ops->ndo_get_vf_config(dev, ivt->vf, &ivf);
+		if (err < 0)
+			return err;
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_rate)
+			err = ops->ndo_set_vf_rate(dev, ivt->vf,
+						   ivf.min_tx_rate,
+						   ivt->rate);
+		if (err < 0)
+			return err;
+	}
+
+	if (tb[IFLA_VF_RATE]) {
+		struct ifla_vf_rate *ivt = nla_data(tb[IFLA_VF_RATE]);
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_rate)
+			err = ops->ndo_set_vf_rate(dev, ivt->vf,
+						   ivt->min_tx_rate,
+						   ivt->max_tx_rate);
+		if (err < 0)
+			return err;
 	}
+
+	if (tb[IFLA_VF_SPOOFCHK]) {
+		struct ifla_vf_spoofchk *ivs = nla_data(tb[IFLA_VF_SPOOFCHK]);
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_spoofchk)
+			err = ops->ndo_set_vf_spoofchk(dev, ivs->vf,
+						       ivs->setting);
+		if (err < 0)
+			return err;
+	}
+
+	if (tb[IFLA_VF_LINK_STATE]) {
+		struct ifla_vf_link_state *ivl = nla_data(tb[IFLA_VF_LINK_STATE]);
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_link_state)
+			err = ops->ndo_set_vf_link_state(dev, ivl->vf,
+							 ivl->link_state);
+		if (err < 0)
+			return err;
+	}
+
+	if (tb[IFLA_VF_RSS_QUERY_EN]) {
+		struct ifla_vf_rss_query_en *ivrssq_en;
+
+		err = -EOPNOTSUPP;
+		ivrssq_en = nla_data(tb[IFLA_VF_RSS_QUERY_EN]);
+		if (ops->ndo_set_vf_rss_query_en)
+			err = ops->ndo_set_vf_rss_query_en(dev, ivrssq_en->vf,
+							   ivrssq_en->setting);
+		if (err < 0)
+			return err;
+	}
+
 	return err;
 }
 
@@ -1722,14 +1720,21 @@ static int do_setlink(const struct sk_buff *skb,
 	}
 
 	if (tb[IFLA_VFINFO_LIST]) {
+		struct nlattr *vfinfo[IFLA_VF_MAX + 1];
 		struct nlattr *attr;
 		int rem;
+
 		nla_for_each_nested(attr, tb[IFLA_VFINFO_LIST], rem) {
-			if (nla_type(attr) != IFLA_VF_INFO) {
+			if (nla_type(attr) != IFLA_VF_INFO ||
+			    nla_len(attr) < NLA_HDRLEN) {
 				err = -EINVAL;
 				goto errout;
 			}
-			err = do_setvfinfo(dev, attr);
+			err = nla_parse_nested(vfinfo, IFLA_VF_MAX, attr,
+					       ifla_vf_policy);
+			if (err < 0)
+				goto errout;
+			err = do_setvfinfo(dev, vfinfo);
 			if (err < 0)
 				goto errout;
 			status |= DO_SETLINK_NOTIFY;
-- 
2.1.0


From e2205c42c1e82d357f7c5007f1507e0b9f341092 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timo=20Ter=C3=A4s?= <timo.teras@iki.fi>
Date: Tue, 7 Jul 2015 08:34:13 +0300
Subject: [PATCH 06/46] ip_tunnel: fix ipv4 pmtu check to honor inner ip header
 df
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit fc24f2b2094366da8786f59f2606307e934cea17 ]

Frag needed should be sent only if the inner header asked
to not fragment. Currently fragmentation is broken if the
tunnel has df set, but df was not asked in the original
packet. The tunnel's df needs to be still checked to update
internally the pmtu cache.

Commit 23a3647bc4f93bac broke it, and this commit fixes
the ipv4 df check back to the way it was.

Fixes: 23a3647bc4f93bac ("ip_tunnels: Use skb-len to PMTU check.")
Cc: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: Timo Teräs <timo.teras@iki.fi>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_tunnel.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 4c2c3ba..626d9e5 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -586,7 +586,8 @@ int ip_tunnel_encap(struct sk_buff *skb, struct ip_tunnel *t,
 EXPORT_SYMBOL(ip_tunnel_encap);
 
 static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
-			    struct rtable *rt, __be16 df)
+			    struct rtable *rt, __be16 df,
+			    const struct iphdr *inner_iph)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	int pkt_size = skb->len - tunnel->hlen - dev->hard_header_len;
@@ -603,7 +604,8 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
 
 	if (skb->protocol == htons(ETH_P_IP)) {
 		if (!skb_is_gso(skb) &&
-		    (df & htons(IP_DF)) && mtu < pkt_size) {
+		    (inner_iph->frag_off & htons(IP_DF)) &&
+		    mtu < pkt_size) {
 			memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
 			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
 			return -E2BIG;
@@ -737,7 +739,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		goto tx_error;
 	}
 
-	if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off)) {
+	if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off, inner_iph)) {
 		ip_rt_put(rt);
 		goto tx_error;
 	}
-- 
2.1.0


From b663e59e521c92aec57078e512f54fa6cabe998a Mon Sep 17 00:00:00 2001
From: Stephen Smalley <sds@tycho.nsa.gov>
Date: Tue, 7 Jul 2015 09:43:45 -0400
Subject: [PATCH 07/46] net/tipc: initialize security state for new connection
 socket

[ Upstream commit fdd75ea8df370f206a8163786e7470c1277a5064 ]

Calling connect() with an AF_TIPC socket would trigger a series
of error messages from SELinux along the lines of:
SELinux: Invalid class 0
type=AVC msg=audit(1434126658.487:34500): avc:  denied  { <unprintable> }
  for pid=292 comm="kworker/u16:5" scontext=system_u:system_r:kernel_t:s0
  tcontext=system_u:object_r:unlabeled_t:s0 tclass=<unprintable>
  permissive=0

This was due to a failure to initialize the security state of the new
connection sock by the tipc code, leaving it with junk in the security
class field and an unlabeled secid.  Add a call to security_sk_clone()
to inherit the security state from the parent socket.

Reported-by: Tim Shearer <tim.shearer@overturenetworks.com>
Signed-off-by: Stephen Smalley <sds@tycho.nsa.gov>
Acked-by: Paul Moore <paul@paul-moore.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/socket.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index f485600..20cc6df 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2009,6 +2009,7 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags)
 	res = tipc_sk_create(sock_net(sock->sk), new_sock, 0, 1);
 	if (res)
 		goto exit;
+	security_sk_clone(sock->sk, new_sock->sk);
 
 	new_sk = new_sock->sk;
 	new_tsock = tipc_sk(new_sk);
-- 
2.1.0


From b5e30ebfbf8c2b93970492ab66be1778b3114332 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <razor@blackwall.org>
Date: Tue, 7 Jul 2015 15:55:56 +0200
Subject: [PATCH 08/46] bridge: mdb: zero out the local br_ip variable before
 use

[ Upstream commit f1158b74e54f2e2462ba5e2f45a118246d9d5b43 ]

Since commit b0e9a30dd669 ("bridge: Add vlan id to multicast groups")
there's a check in br_ip_equal() for a matching vlan id, but the mdb
functions were not modified to use (or at least zero it) so when an
entry was added it would have a garbage vlan id (from the local br_ip
variable in __br_mdb_add/del) and this would prevent it from being
matched and also deleted. So zero out the whole local ip var to protect
ourselves from future changes and also to fix the current bug, since
there's no vlan id support in the mdb uapi - use always vlan id 0.
Example before patch:
root@debian:~# bridge mdb add dev br0 port eth1 grp 239.0.0.1 permanent
root@debian:~# bridge mdb
dev br0 port eth1 grp 239.0.0.1 permanent
root@debian:~# bridge mdb del dev br0 port eth1 grp 239.0.0.1 permanent
RTNETLINK answers: Invalid argument

After patch:
root@debian:~# bridge mdb add dev br0 port eth1 grp 239.0.0.1 permanent
root@debian:~# bridge mdb
dev br0 port eth1 grp 239.0.0.1 permanent
root@debian:~# bridge mdb del dev br0 port eth1 grp 239.0.0.1 permanent
root@debian:~# bridge mdb

Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Fixes: b0e9a30dd669 ("bridge: Add vlan id to multicast groups")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_mdb.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index e29ad70..cc00066 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -371,6 +371,7 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br,
 	if (!p || p->br != br || p->state == BR_STATE_DISABLED)
 		return -EINVAL;
 
+	memset(&ip, 0, sizeof(ip));
 	ip.proto = entry->addr.proto;
 	if (ip.proto == htons(ETH_P_IP))
 		ip.u.ip4 = entry->addr.u.ip4;
@@ -417,6 +418,7 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry)
 	if (!netif_running(br->dev) || br->multicast_disabled)
 		return -EINVAL;
 
+	memset(&ip, 0, sizeof(ip));
 	ip.proto = entry->addr.proto;
 	if (ip.proto == htons(ETH_P_IP)) {
 		if (timer_pending(&br->ip4_other_query.timer))
-- 
2.1.0


From fe98c4431957e308595cc5af799cb9f86c0875d1 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Wed, 8 Jul 2015 21:42:11 +0200
Subject: [PATCH 09/46] net: pktgen: fix race between pktgen_thread_worker()
 and kthread_stop()

[ Upstream commit fecdf8be2d91e04b0a9a4f79ff06499a36f5d14f ]

pktgen_thread_worker() is obviously racy, kthread_stop() can come
between the kthread_should_stop() check and set_current_state().

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Reported-by: Jan Stancek <jstancek@redhat.com>
Reported-by: Marcelo Leitner <mleitner@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/pktgen.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 508155b..043ea186 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -3490,8 +3490,10 @@ static int pktgen_thread_worker(void *arg)
 	pktgen_rem_thread(t);
 
 	/* Wait for kthread_stop */
-	while (!kthread_should_stop()) {
+	for (;;) {
 		set_current_state(TASK_INTERRUPTIBLE);
+		if (kthread_should_stop())
+			break;
 		schedule();
 	}
 	__set_current_state(TASK_RUNNING);
-- 
2.1.0


From 15d50c4f295d8403f6fd818391e04b2c4f3e9637 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 9 Jul 2015 18:56:07 +0200
Subject: [PATCH 10/46] bridge: fix potential crash in __netdev_pick_tx()

[ Upstream commit a7d35f9d73e9ffa74a02304b817e579eec632f67 ]

Commit c29390c6dfee ("xps: must clear sender_cpu before forwarding")
fixed an issue in normal forward path, caused by sender_cpu & napi_id
skb fields being an union.

Bridge is another point where skb can be forwarded, so we need
the same cure.

Bug triggers if packet was received on a NIC using skb_mark_napi_id()

Fixes: 2bd82484bb4c ("xps: fix xps for stacked devices")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Bob Liu <bob.liu@oracle.com>
Tested-by: Bob Liu <bob.liu@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_forward.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index e97572b..0ff6e1b 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -42,6 +42,7 @@ int br_dev_queue_push_xmit(struct sock *sk, struct sk_buff *skb)
 	} else {
 		skb_push(skb, ETH_HLEN);
 		br_drop_fake_rtable(skb);
+		skb_sender_cpu_clear(skb);
 		dev_queue_xmit(skb);
 	}
 
-- 
2.1.0


From 7bb85c2bd072511dd095c3c8ecbe063064ba2c5f Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Thu, 9 Jul 2015 09:59:09 +0300
Subject: [PATCH 11/46] net: do not process device backlog during
 unregistration

[ Upstream commit e9e4dd3267d0c5234c5c0f47440456b10875dec9 ]

commit 381c759d9916 ("ipv4: Avoid crashing in ip_error")
fixes a problem where processed packet comes from device
with destroyed inetdev (dev->ip_ptr). This is not expected
because inetdev_destroy is called in NETDEV_UNREGISTER
phase and packets should not be processed after
dev_close_many() and synchronize_net(). Above fix is still
required because inetdev_destroy can be called for other
reasons. But it shows the real problem: backlog can keep
packets for long time and they do not hold reference to
device. Such packets are then delivered to upper levels
at the same time when device is unregistered.
Calling flush_backlog after NETDEV_UNREGISTER_FINAL still
accounts all packets from backlog but before that some packets
continue to be delivered to upper levels long after the
synchronize_net call which is supposed to wait the last
ones. Also, as Eric pointed out, processed packets, mostly
from other devices, can continue to add new packets to backlog.

Fix the problem by moving flush_backlog early, after the
device driver is stopped and before the synchronize_net() call.
Then use netif_running check to make sure we do not add more
packets to backlog. We have to do it in enqueue_to_backlog
context when the local IRQ is disabled. As result, after the
flush_backlog and synchronize_net sequence all packets
should be accounted.

Thanks to Eric W. Biederman for the test script and his
valuable feedback!

Reported-by: Vittorio Gambaletta <linuxbugs@vittgam.net>
Fixes: 6e583ce5242f ("net: eliminate refcounting in backlog queue")
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 877ec57..cb49e01 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3337,6 +3337,8 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
 	local_irq_save(flags);
 
 	rps_lock(sd);
+	if (!netif_running(skb->dev))
+		goto drop;
 	qlen = skb_queue_len(&sd->input_pkt_queue);
 	if (qlen <= netdev_max_backlog && !skb_flow_limit(skb, qlen)) {
 		if (qlen) {
@@ -3358,6 +3360,7 @@ enqueue:
 		goto enqueue;
 	}
 
+drop:
 	sd->dropped++;
 	rps_unlock(sd);
 
@@ -6023,6 +6026,7 @@ static void rollback_registered_many(struct list_head *head)
 		unlist_netdevice(dev);
 
 		dev->reg_state = NETREG_UNREGISTERING;
+		on_each_cpu(flush_backlog, dev, 1);
 	}
 
 	synchronize_net();
@@ -6647,8 +6651,6 @@ void netdev_run_todo(void)
 
 		dev->reg_state = NETREG_UNREGISTERED;
 
-		on_each_cpu(flush_backlog, dev, 1);
-
 		netdev_wait_allrefs(dev);
 
 		/* paranoia */
-- 
2.1.0


From c979c0e11800c79634b6b9d33ddb8f4cc03c81fa Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Thu, 9 Jul 2015 09:59:10 +0300
Subject: [PATCH 12/46] net: call rcu_read_lock early in process_backlog

[ Upstream commit 2c17d27c36dcce2b6bf689f41a46b9e909877c21 ]

Incoming packet should be either in backlog queue or
in RCU read-side section. Otherwise, the final sequence of
flush_backlog() and synchronize_net() may miss packets
that can run without device reference:

CPU 1                  CPU 2
                       skb->dev: no reference
                       process_backlog:__skb_dequeue
                       process_backlog:local_irq_enable

on_each_cpu for
flush_backlog =>       IPI(hardirq): flush_backlog
                       - packet not found in backlog

                       CPU delayed ...
synchronize_net
- no ongoing RCU
read-side sections

netdev_run_todo,
rcu_barrier: no
ongoing callbacks
                       __netif_receive_skb_core:rcu_read_lock
                       - too late
free dev
                       process packet for freed dev

Fixes: 6e583ce5242f ("net: eliminate refcounting in backlog queue")
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 30 +++++++++++++++---------------
 1 file changed, 15 insertions(+), 15 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index cb49e01..a42b232 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3666,8 +3666,6 @@ static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc)
 
 	pt_prev = NULL;
 
-	rcu_read_lock();
-
 another_round:
 	skb->skb_iif = skb->dev->ifindex;
 
@@ -3677,7 +3675,7 @@ another_round:
 	    skb->protocol == cpu_to_be16(ETH_P_8021AD)) {
 		skb = skb_vlan_untag(skb);
 		if (unlikely(!skb))
-			goto unlock;
+			goto out;
 	}
 
 #ifdef CONFIG_NET_CLS_ACT
@@ -3707,7 +3705,7 @@ skip_taps:
 	if (static_key_false(&ingress_needed)) {
 		skb = handle_ing(skb, &pt_prev, &ret, orig_dev);
 		if (!skb)
-			goto unlock;
+			goto out;
 	}
 
 	skb->tc_verd = 0;
@@ -3724,7 +3722,7 @@ ncls:
 		if (vlan_do_receive(&skb))
 			goto another_round;
 		else if (unlikely(!skb))
-			goto unlock;
+			goto out;
 	}
 
 	rx_handler = rcu_dereference(skb->dev->rx_handler);
@@ -3736,7 +3734,7 @@ ncls:
 		switch (rx_handler(&skb)) {
 		case RX_HANDLER_CONSUMED:
 			ret = NET_RX_SUCCESS;
-			goto unlock;
+			goto out;
 		case RX_HANDLER_ANOTHER:
 			goto another_round;
 		case RX_HANDLER_EXACT:
@@ -3790,8 +3788,7 @@ drop:
 		ret = NET_RX_DROP;
 	}
 
-unlock:
-	rcu_read_unlock();
+out:
 	return ret;
 }
 
@@ -3822,29 +3819,30 @@ static int __netif_receive_skb(struct sk_buff *skb)
 
 static int netif_receive_skb_internal(struct sk_buff *skb)
 {
+	int ret;
+
 	net_timestamp_check(netdev_tstamp_prequeue, skb);
 
 	if (skb_defer_rx_timestamp(skb))
 		return NET_RX_SUCCESS;
 
+	rcu_read_lock();
+
 #ifdef CONFIG_RPS
 	if (static_key_false(&rps_needed)) {
 		struct rps_dev_flow voidflow, *rflow = &voidflow;
-		int cpu, ret;
-
-		rcu_read_lock();
-
-		cpu = get_rps_cpu(skb->dev, skb, &rflow);
+		int cpu = get_rps_cpu(skb->dev, skb, &rflow);
 
 		if (cpu >= 0) {
 			ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
 			rcu_read_unlock();
 			return ret;
 		}
-		rcu_read_unlock();
 	}
 #endif
-	return __netif_receive_skb(skb);
+	ret = __netif_receive_skb(skb);
+	rcu_read_unlock();
+	return ret;
 }
 
 /**
@@ -4389,8 +4387,10 @@ static int process_backlog(struct napi_struct *napi, int quota)
 		struct sk_buff *skb;
 
 		while ((skb = __skb_dequeue(&sd->process_queue))) {
+			rcu_read_lock();
 			local_irq_enable();
 			__netif_receive_skb(skb);
+			rcu_read_unlock();
 			local_irq_disable();
 			input_queue_head_incr(sd);
 			if (++work >= quota) {
-- 
2.1.0


From 9648a7edaa4326282fef3dbb8de9756d8edbfd0a Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Sun, 12 Jul 2015 01:20:55 +0300
Subject: [PATCH 13/46] net/xen-netback: off by one in BUG_ON() condition

[ Upstream commit 50c2e4dd6749725338621fff456b26d3a592259f ]

The > should be >=.  I also added spaces around the '-' operations so
the code is a little more consistent and matches the condition better.

Fixes: f53c3fe8dad7 ('xen-netback: Introduce TX grant mapping')
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netback/netback.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 0d25943..0866c5d 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -1571,13 +1571,13 @@ static inline void xenvif_tx_dealloc_action(struct xenvif_queue *queue)
 		smp_rmb();
 
 		while (dc != dp) {
-			BUG_ON(gop - queue->tx_unmap_ops > MAX_PENDING_REQS);
+			BUG_ON(gop - queue->tx_unmap_ops >= MAX_PENDING_REQS);
 			pending_idx =
 				queue->dealloc_ring[pending_index(dc++)];
 
-			pending_idx_release[gop-queue->tx_unmap_ops] =
+			pending_idx_release[gop - queue->tx_unmap_ops] =
 				pending_idx;
-			queue->pages_to_unmap[gop-queue->tx_unmap_ops] =
+			queue->pages_to_unmap[gop - queue->tx_unmap_ops] =
 				queue->mmap_pages[pending_idx];
 			gnttab_set_unmap_op(gop,
 					    idx_to_kaddr(queue, pending_idx),
-- 
2.1.0


From d015db1b0649539f4473113aec24589a84c49dda Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Mon, 13 Jul 2015 16:04:13 +0800
Subject: [PATCH 14/46] net: Clone skb before setting peeked flag

[ Upstream commit 738ac1ebb96d02e0d23bc320302a6ea94c612dec ]

Shared skbs must not be modified and this is crucial for broadcast
and/or multicast paths where we use it as an optimisation to avoid
unnecessary cloning.

The function skb_recv_datagram breaks this rule by setting peeked
without cloning the skb first.  This causes funky races which leads
to double-free.

This patch fixes this by cloning the skb and replacing the skb
in the list when setting skb->peeked.

Fixes: a59322be07c9 ("[UDP]: Only increment counter on first peek/recv")
Reported-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/datagram.c | 41 ++++++++++++++++++++++++++++++++++++++---
 1 file changed, 38 insertions(+), 3 deletions(-)

diff --git a/net/core/datagram.c b/net/core/datagram.c
index b80fb91..4e9a3f6 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -131,6 +131,35 @@ out_noerr:
 	goto out;
 }
 
+static int skb_set_peeked(struct sk_buff *skb)
+{
+	struct sk_buff *nskb;
+
+	if (skb->peeked)
+		return 0;
+
+	/* We have to unshare an skb before modifying it. */
+	if (!skb_shared(skb))
+		goto done;
+
+	nskb = skb_clone(skb, GFP_ATOMIC);
+	if (!nskb)
+		return -ENOMEM;
+
+	skb->prev->next = nskb;
+	skb->next->prev = nskb;
+	nskb->prev = skb->prev;
+	nskb->next = skb->next;
+
+	consume_skb(skb);
+	skb = nskb;
+
+done:
+	skb->peeked = 1;
+
+	return 0;
+}
+
 /**
  *	__skb_recv_datagram - Receive a datagram skbuff
  *	@sk: socket
@@ -165,7 +194,9 @@ out_noerr:
 struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
 				    int *peeked, int *off, int *err)
 {
+	struct sk_buff_head *queue = &sk->sk_receive_queue;
 	struct sk_buff *skb, *last;
+	unsigned long cpu_flags;
 	long timeo;
 	/*
 	 * Caller is allowed not to check sk->sk_err before skb_recv_datagram()
@@ -184,8 +215,6 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
 		 * Look at current nfs client by the way...
 		 * However, this function was correct in any case. 8)
 		 */
-		unsigned long cpu_flags;
-		struct sk_buff_head *queue = &sk->sk_receive_queue;
 		int _off = *off;
 
 		last = (struct sk_buff *)queue;
@@ -199,7 +228,11 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
 					_off -= skb->len;
 					continue;
 				}
-				skb->peeked = 1;
+
+				error = skb_set_peeked(skb);
+				if (error)
+					goto unlock_err;
+
 				atomic_inc(&skb->users);
 			} else
 				__skb_unlink(skb, queue);
@@ -223,6 +256,8 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
 
 	return NULL;
 
+unlock_err:
+	spin_unlock_irqrestore(&queue->lock, cpu_flags);
 no_packet:
 	*err = error;
 	return NULL;
-- 
2.1.0


From cf2492918d52dee5f35b16cbba65d7000ff35ce2 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Mon, 13 Jul 2015 20:01:42 +0800
Subject: [PATCH 15/46] net: Fix skb csum races when peeking

[ Upstream commit 89c22d8c3b278212eef6a8cc66b570bc840a6f5a ]

When we calculate the checksum on the recv path, we store the
result in the skb as an optimisation in case we need the checksum
again down the line.

This is in fact bogus for the MSG_PEEK case as this is done without
any locking.  So multiple threads can peek and then store the result
to the same skb, potentially resulting in bogus skb states.

This patch fixes this by only storing the result if the skb is not
shared.  This preserves the optimisations for the few cases where
it can be done safely due to locking or other reasons, e.g., SIOCINQ.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/datagram.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/net/core/datagram.c b/net/core/datagram.c
index 4e9a3f6..4967262 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -657,7 +657,8 @@ __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len)
 		    !skb->csum_complete_sw)
 			netdev_rx_csum_fault(skb->dev);
 	}
-	skb->csum_valid = !sum;
+	if (!skb_shared(skb))
+		skb->csum_valid = !sum;
 	return sum;
 }
 EXPORT_SYMBOL(__skb_checksum_complete_head);
@@ -677,11 +678,13 @@ __sum16 __skb_checksum_complete(struct sk_buff *skb)
 			netdev_rx_csum_fault(skb->dev);
 	}
 
-	/* Save full packet checksum */
-	skb->csum = csum;
-	skb->ip_summed = CHECKSUM_COMPLETE;
-	skb->csum_complete_sw = 1;
-	skb->csum_valid = !sum;
+	if (!skb_shared(skb)) {
+		/* Save full packet checksum */
+		skb->csum = csum;
+		skb->ip_summed = CHECKSUM_COMPLETE;
+		skb->csum_complete_sw = 1;
+		skb->csum_valid = !sum;
+	}
 
 	return sum;
 }
-- 
2.1.0


From e2d3e7bcf6679da22c3a68837c4b3c78db3ec110 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Tue, 4 Aug 2015 15:42:47 +0800
Subject: [PATCH 16/46] net: Fix skb_set_peeked use-after-free bug

[ Upstream commit a0a2a6602496a45ae838a96db8b8173794b5d398 ]

The commit 738ac1ebb96d02e0d23bc320302a6ea94c612dec ("net: Clone
skb before setting peeked flag") introduced a use-after-free bug
in skb_recv_datagram.  This is because skb_set_peeked may create
a new skb and free the existing one.  As it stands the caller will
continue to use the old freed skb.

This patch fixes it by making skb_set_peeked return the new skb
(or the old one if unchanged).

Fixes: 738ac1ebb96d ("net: Clone skb before setting peeked flag")
Reported-by: Brenden Blanco <bblanco@plumgrid.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Tested-by: Brenden Blanco <bblanco@plumgrid.com>
Reviewed-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/datagram.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/net/core/datagram.c b/net/core/datagram.c
index 4967262..617088a 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -131,12 +131,12 @@ out_noerr:
 	goto out;
 }
 
-static int skb_set_peeked(struct sk_buff *skb)
+static struct sk_buff *skb_set_peeked(struct sk_buff *skb)
 {
 	struct sk_buff *nskb;
 
 	if (skb->peeked)
-		return 0;
+		return skb;
 
 	/* We have to unshare an skb before modifying it. */
 	if (!skb_shared(skb))
@@ -144,7 +144,7 @@ static int skb_set_peeked(struct sk_buff *skb)
 
 	nskb = skb_clone(skb, GFP_ATOMIC);
 	if (!nskb)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	skb->prev->next = nskb;
 	skb->next->prev = nskb;
@@ -157,7 +157,7 @@ static int skb_set_peeked(struct sk_buff *skb)
 done:
 	skb->peeked = 1;
 
-	return 0;
+	return skb;
 }
 
 /**
@@ -229,8 +229,9 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
 					continue;
 				}
 
-				error = skb_set_peeked(skb);
-				if (error)
+				skb = skb_set_peeked(skb);
+				error = PTR_ERR(skb);
+				if (IS_ERR(skb))
 					goto unlock_err;
 
 				atomic_inc(&skb->users);
-- 
2.1.0


From f82e3fd078652a9b64f6b129d5b8eddb76481093 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Mon, 13 Jul 2015 06:36:19 -0700
Subject: [PATCH 17/46] bridge: mdb: fix double add notification

[ Upstream commit 5ebc784625ea68a9570d1f70557e7932988cd1b4 ]

Since the mdb add/del code was introduced there have been 2 br_mdb_notify
calls when doing br_mdb_add() resulting in 2 notifications on each add.

Example:
 Command: bridge mdb add dev br0 port eth1 grp 239.0.0.1 permanent
 Before patch:
 root@debian:~# bridge monitor all
 [MDB]dev br0 port eth1 grp 239.0.0.1 permanent
 [MDB]dev br0 port eth1 grp 239.0.0.1 permanent

 After patch:
 root@debian:~# bridge monitor all
 [MDB]dev br0 port eth1 grp 239.0.0.1 permanent

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Fixes: cfd567543590 ("bridge: add support of adding and deleting mdb entries")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_mdb.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index cc00066..d1f910c 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -348,7 +348,6 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
 		return -ENOMEM;
 	rcu_assign_pointer(*pp, p);
 
-	br_mdb_notify(br->dev, port, group, RTM_NEWMDB);
 	return 0;
 }
 
-- 
2.1.0


From 8e96bd6de5d8c4acd2faeb9b950bd2ff42a8275a Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Mon, 13 Jul 2015 12:30:07 -0700
Subject: [PATCH 18/46] fq_codel: fix a use-after-free

[ Upstream commit 052cbda41fdc243a8d40cce7ab3a6327b4b2887e ]

Fixes: 25331d6ce42b ("net: sched: implement qstat helper routines")
Cc: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Cong Wang <cwang@twopensource.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_fq_codel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index c244c45b..9291598 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -162,10 +162,10 @@ static unsigned int fq_codel_drop(struct Qdisc *sch)
 	skb = dequeue_head(flow);
 	len = qdisc_pkt_len(skb);
 	q->backlogs[idx] -= len;
-	kfree_skb(skb);
 	sch->q.qlen--;
 	qdisc_qstats_drop(sch);
 	qdisc_qstats_backlog_dec(sch, skb);
+	kfree_skb(skb);
 	flow->dropped++;
 	return idx;
 }
-- 
2.1.0


From d4657581d01faad94a50b03f31bbe33c3b6dcb14 Mon Sep 17 00:00:00 2001
From: Tilman Schmidt <tilman@imap.cc>
Date: Tue, 14 Jul 2015 00:37:13 +0200
Subject: [PATCH 19/46] isdn/gigaset: reset tty->receive_room when attaching
 ser_gigaset

[ Upstream commit fd98e9419d8d622a4de91f76b306af6aa627aa9c ]

Commit 79901317ce80 ("n_tty: Don't flush buffer when closing ldisc"),
first merged in kernel release 3.10, caused the following regression
in the Gigaset M101 driver:

Before that commit, when closing the N_TTY line discipline in
preparation to switching to N_GIGASET_M101, receive_room would be
reset to a non-zero value by the call to n_tty_flush_buffer() in
n_tty's close method. With the removal of that call, receive_room
might be left at zero, blocking data reception on the serial line.

The present patch fixes that regression by setting receive_room
to an appropriate value in the ldisc open method.

Fixes: 79901317ce80 ("n_tty: Don't flush buffer when closing ldisc")
Signed-off-by: Tilman Schmidt <tilman@imap.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/gigaset/ser-gigaset.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/isdn/gigaset/ser-gigaset.c b/drivers/isdn/gigaset/ser-gigaset.c
index 8c91fd5..3ac9c41 100644
--- a/drivers/isdn/gigaset/ser-gigaset.c
+++ b/drivers/isdn/gigaset/ser-gigaset.c
@@ -524,9 +524,18 @@ gigaset_tty_open(struct tty_struct *tty)
 	cs->hw.ser->tty = tty;
 	atomic_set(&cs->hw.ser->refcnt, 1);
 	init_completion(&cs->hw.ser->dead_cmp);
-
 	tty->disc_data = cs;
 
+	/* Set the amount of data we're willing to receive per call
+	 * from the hardware driver to half of the input buffer size
+	 * to leave some reserve.
+	 * Note: We don't do flow control towards the hardware driver.
+	 * If more data is received than will fit into the input buffer,
+	 * it will be dropped and an error will be logged. This should
+	 * never happen as the device is slow and the buffer size ample.
+	 */
+	tty->receive_room = RBUFSIZE/2;
+
 	/* OK.. Initialization of the datastructures and the HW is done.. Now
 	 * startup system and notify the LL that we are ready to run
 	 */
-- 
2.1.0


From a5802a78d70219bb1f2e5f6726486e3834b1270d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 14 Jul 2015 08:10:22 +0200
Subject: [PATCH 20/46] ipv6: lock socket in ip6_datagram_connect()

[ Upstream commit 03645a11a570d52e70631838cb786eb4253eb463 ]

ip6_datagram_connect() is doing a lot of socket changes without
socket being locked.

This looks wrong, at least for udp_lib_rehash() which could corrupt
lists because of concurrent udp_sk(sk)->udp_portaddr_hash accesses.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h    |  1 +
 net/ipv4/datagram.c | 16 ++++++++++++----
 net/ipv6/datagram.c | 20 +++++++++++++++-----
 3 files changed, 28 insertions(+), 9 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index d14af7e..f41fc49 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -161,6 +161,7 @@ static inline __u8 get_rtconn_flags(struct ipcm_cookie* ipc, struct sock* sk)
 }
 
 /* datagram.c */
+int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
 int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
 
 void ip4_datagram_release_cb(struct sock *sk);
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index 90c0e83..574fad9 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -20,7 +20,7 @@
 #include <net/route.h>
 #include <net/tcp_states.h>
 
-int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct sockaddr_in *usin = (struct sockaddr_in *) uaddr;
@@ -39,8 +39,6 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 
 	sk_dst_reset(sk);
 
-	lock_sock(sk);
-
 	oif = sk->sk_bound_dev_if;
 	saddr = inet->inet_saddr;
 	if (ipv4_is_multicast(usin->sin_addr.s_addr)) {
@@ -82,9 +80,19 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	sk_dst_set(sk, &rt->dst);
 	err = 0;
 out:
-	release_sock(sk);
 	return err;
 }
+EXPORT_SYMBOL(__ip4_datagram_connect);
+
+int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+{
+	int res;
+
+	lock_sock(sk);
+	res = __ip4_datagram_connect(sk, uaddr, addr_len);
+	release_sock(sk);
+	return res;
+}
 EXPORT_SYMBOL(ip4_datagram_connect);
 
 /* Because UDP xmit path can manipulate sk_dst_cache without holding
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 62d908e..b10a889 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -40,7 +40,7 @@ static bool ipv6_mapped_addr_any(const struct in6_addr *a)
 	return ipv6_addr_v4mapped(a) && (a->s6_addr32[3] == 0);
 }
 
-int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+static int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
 	struct sockaddr_in6	*usin = (struct sockaddr_in6 *) uaddr;
 	struct inet_sock	*inet = inet_sk(sk);
@@ -56,7 +56,7 @@ int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	if (usin->sin6_family == AF_INET) {
 		if (__ipv6_only_sock(sk))
 			return -EAFNOSUPPORT;
-		err = ip4_datagram_connect(sk, uaddr, addr_len);
+		err = __ip4_datagram_connect(sk, uaddr, addr_len);
 		goto ipv4_connected;
 	}
 
@@ -98,9 +98,9 @@ int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 		sin.sin_addr.s_addr = daddr->s6_addr32[3];
 		sin.sin_port = usin->sin6_port;
 
-		err = ip4_datagram_connect(sk,
-					   (struct sockaddr *) &sin,
-					   sizeof(sin));
+		err = __ip4_datagram_connect(sk,
+					     (struct sockaddr *) &sin,
+					     sizeof(sin));
 
 ipv4_connected:
 		if (err)
@@ -204,6 +204,16 @@ out:
 	fl6_sock_release(flowlabel);
 	return err;
 }
+
+int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+{
+	int res;
+
+	lock_sock(sk);
+	res = __ip6_datagram_connect(sk, uaddr, addr_len);
+	release_sock(sk);
+	return res;
+}
 EXPORT_SYMBOL_GPL(ip6_datagram_connect);
 
 int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr *uaddr,
-- 
2.1.0


From 1c0df6bdc731f7692a1fafd9c606135ba714e7c6 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Wed, 15 Jul 2015 21:52:51 +0200
Subject: [PATCH 21/46] bonding: fix destruction of bond with devices different
 from arphrd_ether

[ Upstream commit 06f6d1094aa0992432b1e2a0920b0ee86ccd83bf ]

When the bonding is being unloaded and the netdevice notifier is
unregistered it executes NETDEV_UNREGISTER for each device which should
remove the bond's proc entry but if the device enslaved is not of
ARPHRD_ETHER type and is in front of the bonding, it may execute
bond_release_and_destroy() first which would release the last slave and
destroy the bond device leaving the proc entry and thus we will get the
following error (with dynamic debug on for bond_netdev_event to see the
events order):
[  908.963051] eql: event: 9
[  908.963052] eql: IFF_SLAVE
[  908.963054] eql: event: 2
[  908.963056] eql: IFF_SLAVE
[  908.963058] eql: event: 6
[  908.963059] eql: IFF_SLAVE
[  908.963110] bond0: Releasing active interface eql
[  908.976168] bond0: Destroying bond bond0
[  908.976266] bond0 (unregistering): Released all slaves
[  908.984097] ------------[ cut here ]------------
[  908.984107] WARNING: CPU: 0 PID: 1787 at fs/proc/generic.c:575
remove_proc_entry+0x112/0x160()
[  908.984110] remove_proc_entry: removing non-empty directory
'net/bonding', leaking at least 'bond0'
[  908.984111] Modules linked in: bonding(-) eql(O) 9p nfsd auth_rpcgss
oid_registry nfs_acl nfs lockd grace fscache sunrpc crct10dif_pclmul
crc32_pclmul crc32c_intel ghash_clmulni_intel ppdev qxl drm_kms_helper
snd_hda_codec_generic aesni_intel ttm aes_x86_64 glue_helper pcspkr lrw
gf128mul ablk_helper cryptd snd_hda_intel virtio_console snd_hda_codec
psmouse serio_raw snd_hwdep snd_hda_core 9pnet_virtio 9pnet evdev joydev
drm virtio_balloon snd_pcm snd_timer snd soundcore i2c_piix4 i2c_core
pvpanic acpi_cpufreq parport_pc parport processor thermal_sys button
autofs4 ext4 crc16 mbcache jbd2 hid_generic usbhid hid sg sr_mod cdrom
ata_generic virtio_blk virtio_net floppy ata_piix e1000 libata ehci_pci
virtio_pci scsi_mod uhci_hcd ehci_hcd virtio_ring virtio usbcore
usb_common [last unloaded: bonding]

[  908.984168] CPU: 0 PID: 1787 Comm: rmmod Tainted: G        W  O
4.2.0-rc2+ #8
[  908.984170] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
[  908.984172]  0000000000000000 ffffffff81732d41 ffffffff81525b34
ffff8800358dfda8
[  908.984175]  ffffffff8106c521 ffff88003595af78 ffff88003595af40
ffff88003e3a4280
[  908.984178]  ffffffffa058d040 0000000000000000 ffffffff8106c59a
ffffffff8172ebd0
[  908.984181] Call Trace:
[  908.984188]  [<ffffffff81525b34>] ? dump_stack+0x40/0x50
[  908.984193]  [<ffffffff8106c521>] ? warn_slowpath_common+0x81/0xb0
[  908.984196]  [<ffffffff8106c59a>] ? warn_slowpath_fmt+0x4a/0x50
[  908.984199]  [<ffffffff81218352>] ? remove_proc_entry+0x112/0x160
[  908.984205]  [<ffffffffa05850e6>] ? bond_destroy_proc_dir+0x26/0x30
[bonding]
[  908.984208]  [<ffffffffa057540e>] ? bond_net_exit+0x8e/0xa0 [bonding]
[  908.984217]  [<ffffffff8142f407>] ? ops_exit_list.isra.4+0x37/0x70
[  908.984225]  [<ffffffff8142f52d>] ?
unregister_pernet_operations+0x8d/0xd0
[  908.984228]  [<ffffffff8142f58d>] ?
unregister_pernet_subsys+0x1d/0x30
[  908.984232]  [<ffffffffa0585269>] ? bonding_exit+0x23/0xdba [bonding]
[  908.984236]  [<ffffffff810e28ba>] ? SyS_delete_module+0x18a/0x250
[  908.984241]  [<ffffffff81086f99>] ? task_work_run+0x89/0xc0
[  908.984244]  [<ffffffff8152b732>] ?
entry_SYSCALL_64_fastpath+0x16/0x75
[  908.984247] ---[ end trace 7c006ed4abbef24b ]---

Thus remove the proc entry manually if bond_release_and_destroy() is
used. Because of the checks in bond_remove_proc_entry() it's not a
problem for a bond device to change namespaces (the bug fixed by the
Fixes commit) but since commit
f9399814927ad ("bonding: Don't allow bond devices to change network
namespaces.") that can't happen anyway.

Reported-by: Carol Soto <clsoto@linux.vnet.ibm.com>
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Fixes: a64d49c3dd50 ("bonding: Manage /proc/net/bonding/ entries from
                      the netdev events")
Tested-by: Carol L Soto <clsoto@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index d5fe5d5..6a4e523 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1902,6 +1902,7 @@ static int  bond_release_and_destroy(struct net_device *bond_dev,
 		bond_dev->priv_flags |= IFF_DISABLE_NETPOLL;
 		netdev_info(bond_dev, "Destroying bond %s\n",
 			    bond_dev->name);
+		bond_remove_proc_entry(bond);
 		unregister_netdevice(bond_dev);
 	}
 	return ret;
-- 
2.1.0


From 69200c77f33e23a81609bc618659a4859c188a98 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Mon, 20 Jul 2015 17:55:38 +0800
Subject: [PATCH 22/46] Revert "sit: Add gro callbacks to sit_offload"

[ Upstream commit fdbf5b097bbd9693a86c0b8bfdd071a9a2117cfc ]

This patch reverts 19424e052fb44da2f00d1a868cbb51f3e9f4bbb5 ("sit:
Add gro callbacks to sit_offload") because it generates packets
that cannot be handled even by our own GSO.

Reported-by: Wolfgang Walter <linux@stwm.de>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_offload.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index e893cd1..08b6204 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -292,8 +292,6 @@ static struct packet_offload ipv6_packet_offload __read_mostly = {
 static const struct net_offload sit_offload = {
 	.callbacks = {
 		.gso_segment	= ipv6_gso_segment,
-		.gro_receive	= ipv6_gro_receive,
-		.gro_complete	= ipv6_gro_complete,
 	},
 };
 
-- 
2.1.0


From 0479ad88a4eb6dd0d05a5712ff1d489fc27feaa4 Mon Sep 17 00:00:00 2001
From: dingtianhong <dingtianhong@huawei.com>
Date: Thu, 16 Jul 2015 16:30:02 +0800
Subject: [PATCH 23/46] bonding: correct the MAC address for "follow"
 fail_over_mac policy

[ Upstream commit a951bc1e6ba58f11df5ed5ddc41311e10f5fd20b ]

The "follow" fail_over_mac policy is useful for multiport devices that
either become confused or incur a performance penalty when multiple
ports are programmed with the same MAC address, but the same MAC
address still may happened by this steps for this policy:

1) echo +eth0 > /sys/class/net/bond0/bonding/slaves
   bond0 has the same mac address with eth0, it is MAC1.

2) echo +eth1 > /sys/class/net/bond0/bonding/slaves
   eth1 is backup, eth1 has MAC2.

3) ifconfig eth0 down
   eth1 became active slave, bond will swap MAC for eth0 and eth1,
   so eth1 has MAC1, and eth0 has MAC2.

4) ifconfig eth1 down
   there is no active slave, and eth1 still has MAC1, eth2 has MAC2.

5) ifconfig eth0 up
   the eth0 became active slave again, the bond set eth0 to MAC1.

Something wrong here, then if you set eth1 up, the eth0 and eth1 will have the same
MAC address, it will break this policy for ACTIVE_BACKUP mode.

This patch will fix this problem by finding the old active slave and
swap them MAC address before change active slave.

Signed-off-by: Ding Tianhong <dingtianhong@huawei.com>
Tested-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 6a4e523..16d87bf 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -625,6 +625,23 @@ static void bond_set_dev_addr(struct net_device *bond_dev,
 	call_netdevice_notifiers(NETDEV_CHANGEADDR, bond_dev);
 }
 
+static struct slave *bond_get_old_active(struct bonding *bond,
+					 struct slave *new_active)
+{
+	struct slave *slave;
+	struct list_head *iter;
+
+	bond_for_each_slave(bond, slave, iter) {
+		if (slave == new_active)
+			continue;
+
+		if (ether_addr_equal(bond->dev->dev_addr, slave->dev->dev_addr))
+			return slave;
+	}
+
+	return NULL;
+}
+
 /* bond_do_fail_over_mac
  *
  * Perform special MAC address swapping for fail_over_mac settings
@@ -652,6 +669,9 @@ static void bond_do_fail_over_mac(struct bonding *bond,
 		if (!new_active)
 			return;
 
+		if (!old_active)
+			old_active = bond_get_old_active(bond, new_active);
+
 		if (old_active) {
 			ether_addr_copy(tmp_mac, new_active->dev->dev_addr);
 			ether_addr_copy(saddr.sa_data,
-- 
2.1.0


From 6fef6e2a4f97d67ea0c20473d228e755e3f96a21 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 17 Jul 2015 22:38:43 +0200
Subject: [PATCH 24/46] sched: cls_bpf: fix panic on filter replace

[ Upstream commit f6bfc46da6292b630ba389592123f0dd02066172 ]

The following test case causes a NULL pointer dereference in cls_bpf:

  FOO="1,6 0 0 4294967295,"
  tc filter add dev foo parent 1: bpf bytecode "$FOO" flowid 1:1 action ok
  tc filter replace dev foo parent 1: pref 49152 handle 0x1 \
            bpf bytecode "$FOO" flowid 1:1 action drop

The problem is that commit 1f947bf151e9 ("net: sched: rcu'ify cls_bpf")
accidentally swapped the arguments of list_replace_rcu(), the old
element needs to be the first argument and the new element the second.

Fixes: 1f947bf151e9 ("net: sched: rcu'ify cls_bpf")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.r.fastabend@intel.com>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_bpf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 91bd9c1..c0b86f2 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -364,7 +364,7 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
 		goto errout;
 
 	if (oldprog) {
-		list_replace_rcu(&prog->link, &oldprog->link);
+		list_replace_rcu(&oldprog->link, &prog->link);
 		tcf_unbind_filter(tp, &oldprog->res);
 		call_rcu(&oldprog->rcu, __cls_bpf_delete_prog);
 	} else {
-- 
2.1.0


From 8c2111406c9cc807767ecc64ae29a409cf486c94 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 17 Jul 2015 22:38:45 +0200
Subject: [PATCH 25/46] sched: cls_flow: fix panic on filter replace

[ Upstream commit 32b2f4b196b37695fdb42b31afcbc15399d6ef91 ]

The following test case causes a NULL pointer dereference in cls_flow:

  tc filter add dev foo parent 1: handle 0x1 flow hash keys dst action ok
  tc filter replace dev foo parent 1: pref 49152 handle 0x1 \
            flow hash keys mark action drop

To be more precise, actually two different panics are fixed, the first
occurs because tcf_exts_init() is not called on the newly allocated
filter when we do a replace. And the second panic uncovered after that
happens since the arguments of list_replace_rcu() are swapped, the old
element needs to be the first argument and the new element the second.

Fixes: 70da9f0bf999 ("net: sched: cls_flow use RCU")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_flow.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index a620c4e..75df923 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -419,6 +419,8 @@ static int flow_change(struct net *net, struct sk_buff *in_skb,
 	if (!fnew)
 		goto err2;
 
+	tcf_exts_init(&fnew->exts, TCA_FLOW_ACT, TCA_FLOW_POLICE);
+
 	fold = (struct flow_filter *)*arg;
 	if (fold) {
 		err = -EINVAL;
@@ -480,7 +482,6 @@ static int flow_change(struct net *net, struct sk_buff *in_skb,
 		fnew->mask  = ~0U;
 		fnew->tp = tp;
 		get_random_bytes(&fnew->hashrnd, 4);
-		tcf_exts_init(&fnew->exts, TCA_FLOW_ACT, TCA_FLOW_POLICE);
 	}
 
 	fnew->perturb_timer.function = flow_perturbation;
@@ -520,7 +521,7 @@ static int flow_change(struct net *net, struct sk_buff *in_skb,
 	if (*arg == 0)
 		list_add_tail_rcu(&fnew->list, &head->filters);
 	else
-		list_replace_rcu(&fnew->list, &fold->list);
+		list_replace_rcu(&fold->list, &fnew->list);
 
 	*arg = (unsigned long)fnew;
 
-- 
2.1.0


From fe0e0574a708320517330ca57865f1d4d2530cfc Mon Sep 17 00:00:00 2001
From: Edward Hyunkoo Jee <edjee@google.com>
Date: Tue, 21 Jul 2015 09:43:59 +0200
Subject: [PATCH 26/46] inet: frags: fix defragmented packet's IP header for
 af_packet

[ Upstream commit 0848f6428ba3a2e42db124d41ac6f548655735bf ]

When ip_frag_queue() computes positions, it assumes that the passed
sk_buff does not contain L2 headers.

However, when PACKET_FANOUT_FLAG_DEFRAG is used, IP reassembly
functions can be called on outgoing packets that contain L2 headers.

Also, IPv4 checksum is not corrected after reassembly.

Fixes: 7736d33f4262 ("packet: Add pre-defragmentation support for ipv4 fanouts.")
Signed-off-by: Edward Hyunkoo Jee <edjee@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Jerry Chu <hkchu@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_fragment.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index cc1da6d..cae22a1 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -342,7 +342,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 	ihl = ip_hdrlen(skb);
 
 	/* Determine the position of this fragment. */
-	end = offset + skb->len - ihl;
+	end = offset + skb->len - skb_network_offset(skb) - ihl;
 	err = -EINVAL;
 
 	/* Is this the final fragment? */
@@ -372,7 +372,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 		goto err;
 
 	err = -ENOMEM;
-	if (!pskb_pull(skb, ihl))
+	if (!pskb_pull(skb, skb_network_offset(skb) + ihl))
 		goto err;
 
 	err = pskb_trim_rcsum(skb, end - offset);
@@ -613,6 +613,9 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 	iph->frag_off = qp->q.max_size ? htons(IP_DF) : 0;
 	iph->tot_len = htons(len);
 	iph->tos |= ecn;
+
+	ip_send_check(iph);
+
 	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMOKS);
 	qp->q.fragments = NULL;
 	qp->q.fragments_tail = NULL;
-- 
2.1.0


From 5dfcd4a0749d9d421ec04dedf37d9f07a0c22f3a Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 21 Jul 2015 16:33:50 +0200
Subject: [PATCH 27/46] netlink: don't hold mutex in rcu callback when
 releasing mmapd ring

[ Upstream commit 0470eb99b4721586ccac954faac3fa4472da0845 ]

Kirill A. Shutemov says:

This simple test-case trigers few locking asserts in kernel:

int main(int argc, char **argv)
{
        unsigned int block_size = 16 * 4096;
        struct nl_mmap_req req = {
                .nm_block_size          = block_size,
                .nm_block_nr            = 64,
                .nm_frame_size          = 16384,
                .nm_frame_nr            = 64 * block_size / 16384,
        };
        unsigned int ring_size;
	int fd;

	fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_GENERIC);
        if (setsockopt(fd, SOL_NETLINK, NETLINK_RX_RING, &req, sizeof(req)) < 0)
                exit(1);
        if (setsockopt(fd, SOL_NETLINK, NETLINK_TX_RING, &req, sizeof(req)) < 0)
                exit(1);

	ring_size = req.nm_block_nr * req.nm_block_size;
	mmap(NULL, 2 * ring_size, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0);
	return 0;
}

+++ exited with 0 +++
BUG: sleeping function called from invalid context at /home/kas/git/public/linux-mm/kernel/locking/mutex.c:616
in_atomic(): 1, irqs_disabled(): 0, pid: 1, name: init
3 locks held by init/1:
 #0:  (reboot_mutex){+.+...}, at: [<ffffffff81080959>] SyS_reboot+0xa9/0x220
 #1:  ((reboot_notifier_list).rwsem){.+.+..}, at: [<ffffffff8107f379>] __blocking_notifier_call_chain+0x39/0x70
 #2:  (rcu_callback){......}, at: [<ffffffff810d32e0>] rcu_do_batch.isra.49+0x160/0x10c0
Preemption disabled at:[<ffffffff8145365f>] __delay+0xf/0x20

CPU: 1 PID: 1 Comm: init Not tainted 4.1.0-00009-gbddf4c4818e0 #253
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS Debian-1.8.2-1 04/01/2014
 ffff88017b3d8000 ffff88027bc03c38 ffffffff81929ceb 0000000000000102
 0000000000000000 ffff88027bc03c68 ffffffff81085a9d 0000000000000002
 ffffffff81ca2a20 0000000000000268 0000000000000000 ffff88027bc03c98
Call Trace:
 <IRQ>  [<ffffffff81929ceb>] dump_stack+0x4f/0x7b
 [<ffffffff81085a9d>] ___might_sleep+0x16d/0x270
 [<ffffffff81085bed>] __might_sleep+0x4d/0x90
 [<ffffffff8192e96f>] mutex_lock_nested+0x2f/0x430
 [<ffffffff81932fed>] ? _raw_spin_unlock_irqrestore+0x5d/0x80
 [<ffffffff81464143>] ? __this_cpu_preempt_check+0x13/0x20
 [<ffffffff8182fc3d>] netlink_set_ring+0x1ed/0x350
 [<ffffffff8182e000>] ? netlink_undo_bind+0x70/0x70
 [<ffffffff8182fe20>] netlink_sock_destruct+0x80/0x150
 [<ffffffff817e484d>] __sk_free+0x1d/0x160
 [<ffffffff817e49a9>] sk_free+0x19/0x20
[..]

Cong Wang says:

We can't hold mutex lock in a rcu callback, [..]

Thomas Graf says:

The socket should be dead at this point. It might be simpler to
add a netlink_release_ring() function which doesn't require
locking at all.

Reported-by: "Kirill A. Shutemov" <kirill@shutemov.name>
Diagnosed-by: Cong Wang <cwang@twopensource.com>
Suggested-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 79 ++++++++++++++++++++++++++++--------------------
 1 file changed, 47 insertions(+), 32 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index bf6e766..ea5ed7a 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -355,25 +355,52 @@ err1:
 	return NULL;
 }
 
+
+static void
+__netlink_set_ring(struct sock *sk, struct nl_mmap_req *req, bool tx_ring, void **pg_vec,
+		   unsigned int order)
+{
+	struct netlink_sock *nlk = nlk_sk(sk);
+	struct sk_buff_head *queue;
+	struct netlink_ring *ring;
+
+	queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue;
+	ring  = tx_ring ? &nlk->tx_ring : &nlk->rx_ring;
+
+	spin_lock_bh(&queue->lock);
+
+	ring->frame_max		= req->nm_frame_nr - 1;
+	ring->head		= 0;
+	ring->frame_size	= req->nm_frame_size;
+	ring->pg_vec_pages	= req->nm_block_size / PAGE_SIZE;
+
+	swap(ring->pg_vec_len, req->nm_block_nr);
+	swap(ring->pg_vec_order, order);
+	swap(ring->pg_vec, pg_vec);
+
+	__skb_queue_purge(queue);
+	spin_unlock_bh(&queue->lock);
+
+	WARN_ON(atomic_read(&nlk->mapped));
+
+	if (pg_vec)
+		free_pg_vec(pg_vec, order, req->nm_block_nr);
+}
+
 static int netlink_set_ring(struct sock *sk, struct nl_mmap_req *req,
-			    bool closing, bool tx_ring)
+			    bool tx_ring)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
 	struct netlink_ring *ring;
-	struct sk_buff_head *queue;
 	void **pg_vec = NULL;
 	unsigned int order = 0;
-	int err;
 
 	ring  = tx_ring ? &nlk->tx_ring : &nlk->rx_ring;
-	queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue;
 
-	if (!closing) {
-		if (atomic_read(&nlk->mapped))
-			return -EBUSY;
-		if (atomic_read(&ring->pending))
-			return -EBUSY;
-	}
+	if (atomic_read(&nlk->mapped))
+		return -EBUSY;
+	if (atomic_read(&ring->pending))
+		return -EBUSY;
 
 	if (req->nm_block_nr) {
 		if (ring->pg_vec != NULL)
@@ -405,31 +432,19 @@ static int netlink_set_ring(struct sock *sk, struct nl_mmap_req *req,
 			return -EINVAL;
 	}
 
-	err = -EBUSY;
 	mutex_lock(&nlk->pg_vec_lock);
-	if (closing || atomic_read(&nlk->mapped) == 0) {
-		err = 0;
-		spin_lock_bh(&queue->lock);
-
-		ring->frame_max		= req->nm_frame_nr - 1;
-		ring->head		= 0;
-		ring->frame_size	= req->nm_frame_size;
-		ring->pg_vec_pages	= req->nm_block_size / PAGE_SIZE;
-
-		swap(ring->pg_vec_len, req->nm_block_nr);
-		swap(ring->pg_vec_order, order);
-		swap(ring->pg_vec, pg_vec);
-
-		__skb_queue_purge(queue);
-		spin_unlock_bh(&queue->lock);
-
-		WARN_ON(atomic_read(&nlk->mapped));
+	if (atomic_read(&nlk->mapped) == 0) {
+		__netlink_set_ring(sk, req, tx_ring, pg_vec, order);
+		mutex_unlock(&nlk->pg_vec_lock);
+		return 0;
 	}
+
 	mutex_unlock(&nlk->pg_vec_lock);
 
 	if (pg_vec)
 		free_pg_vec(pg_vec, order, req->nm_block_nr);
-	return err;
+
+	return -EBUSY;
 }
 
 static void netlink_mm_open(struct vm_area_struct *vma)
@@ -898,10 +913,10 @@ static void netlink_sock_destruct(struct sock *sk)
 
 		memset(&req, 0, sizeof(req));
 		if (nlk->rx_ring.pg_vec)
-			netlink_set_ring(sk, &req, true, false);
+			__netlink_set_ring(sk, &req, false, NULL, 0);
 		memset(&req, 0, sizeof(req));
 		if (nlk->tx_ring.pg_vec)
-			netlink_set_ring(sk, &req, true, true);
+			__netlink_set_ring(sk, &req, true, NULL, 0);
 	}
 #endif /* CONFIG_NETLINK_MMAP */
 
@@ -2197,7 +2212,7 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 			return -EINVAL;
 		if (copy_from_user(&req, optval, sizeof(req)))
 			return -EFAULT;
-		err = netlink_set_ring(sk, &req, false,
+		err = netlink_set_ring(sk, &req,
 				       optname == NETLINK_TX_RING);
 		break;
 	}
-- 
2.1.0


From c8a958d63443e2d143d1710ee437c17438fd12e5 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Wed, 15 Jul 2015 15:26:19 +0300
Subject: [PATCH 28/46] virtio_net: don't require ANY_LAYOUT with VERSION_1

[ Upstream commit 75993300d008f418ee2569a632185fc1d7d50674 ]

ANY_LAYOUT is a compatibility feature. It's implied
for VERSION_1 devices, and non-transitional devices
might not offer it. Change code to behave accordingly.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 63c7810..7fbca37 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1828,7 +1828,8 @@ static int virtnet_probe(struct virtio_device *vdev)
 	else
 		vi->hdr_len = sizeof(struct virtio_net_hdr);
 
-	if (virtio_has_feature(vdev, VIRTIO_F_ANY_LAYOUT))
+	if (virtio_has_feature(vdev, VIRTIO_F_ANY_LAYOUT) ||
+	    virtio_has_feature(vdev, VIRTIO_F_VERSION_1))
 		vi->any_header_sg = true;
 
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ))
-- 
2.1.0


From d5df2abc93d5027ec62fb714d6bb9b14bed65548 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Wed, 22 Jul 2015 13:03:40 +0200
Subject: [PATCH 29/46] bridge: netlink: fix slave_changelink/br_setport race
 conditions

[ Upstream commit 963ad94853000ab100f5ff19eea80095660d41b4 ]

Since slave_changelink support was added there have been a few race
conditions when using br_setport() since some of the port functions it
uses require the bridge lock. It is very easy to trigger a lockup due to
some internal spin_lock() usage without bh disabled, also it's possible to
get the bridge into an inconsistent state.

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Fixes: 3ac636b8591c ("bridge: implement rtnl_link_ops->slave_changelink")
Reviewed-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_netlink.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 4b5c236..20e06a9 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -711,9 +711,17 @@ static int br_port_slave_changelink(struct net_device *brdev,
 				    struct nlattr *tb[],
 				    struct nlattr *data[])
 {
+	struct net_bridge *br = netdev_priv(brdev);
+	int ret;
+
 	if (!data)
 		return 0;
-	return br_setport(br_port_get_rtnl(dev), data);
+
+	spin_lock_bh(&br->lock);
+	ret = br_setport(br_port_get_rtnl(dev), data);
+	spin_unlock_bh(&br->lock);
+
+	return ret;
 }
 
 static int br_port_fill_slave_info(struct sk_buff *skb,
-- 
2.1.0


From 8002540aec64b57e8a2a93adf4ad893b085f9ae6 Mon Sep 17 00:00:00 2001
From: Jack Morgenstein <jackm@dev.mellanox.co.il>
Date: Wed, 22 Jul 2015 16:53:47 +0300
Subject: [PATCH 30/46] net/mlx4_core: Fix wrong index in propagating port
 change event to VFs

[ Upstream commit 1c1bf34951e8d17941bf708d1901c47e81b15d55 ]

The port-change event processing in procedure mlx4_eq_int() uses "slave"
as the vf_oper array index. Since the value of "slave" is the PF function
index, the result is that the PF link state is used for deciding to
propagate the event for all the VFs. The VF link state should be used,
so the VF function index should be used here.

Fixes: 948e306d7d64 ('net/mlx4: Add VF link state support')
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/eq.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index 2619c9f..983b1d5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -573,7 +573,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 							continue;
 						mlx4_dbg(dev, "%s: Sending MLX4_PORT_CHANGE_SUBTYPE_DOWN to slave: %d, port:%d\n",
 							 __func__, i, port);
-						s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state;
+						s_info = &priv->mfunc.master.vf_oper[i].vport[port].state;
 						if (IFLA_VF_LINK_STATE_AUTO == s_info->link_state) {
 							eqe->event.port_change.port =
 								cpu_to_be32(
@@ -608,7 +608,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 							continue;
 						if (i == mlx4_master_func_num(dev))
 							continue;
-						s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state;
+						s_info = &priv->mfunc.master.vf_oper[i].vport[port].state;
 						if (IFLA_VF_LINK_STATE_AUTO == s_info->link_state) {
 							eqe->event.port_change.port =
 								cpu_to_be32(
-- 
2.1.0


From 9df9bb9ae0c1579a4e6e63fc6ebfb7d1e0a16ebb Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@redhat.com>
Date: Mon, 27 Jul 2015 13:08:06 -0700
Subject: [PATCH 31/46] fib_trie: Drop unnecessary calls to leaf_pull_suffix

[ Upstream commit 1513069edcf8dd86cfd8d5daef482b97d6b93df6 ]

It was reported that update_suffix was taking a long time on systems where
a large number of leaves were attached to a single node.  As it turns out
fib_table_flush was calling update_suffix for each leaf that didn't have all
of the aliases stripped from it.  As a result, on this large node removing
one leaf would result in us calling update_suffix for every other leaf on
the node.

The fix is to just remove the calls to leaf_pull_suffix since they are
redundant as we already have a call in resize that will go through and
update the suffix length for the node before we exit out of
fib_table_flush or fib_table_flush_external.

Reported-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Tested-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_trie.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 09b62e1..210ceca 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1780,8 +1780,6 @@ void fib_table_flush_external(struct fib_table *tb)
 		if (hlist_empty(&n->leaf)) {
 			put_child_root(pn, n->key, NULL);
 			node_free(n);
-		} else {
-			leaf_pull_suffix(pn, n);
 		}
 	}
 }
@@ -1852,8 +1850,6 @@ int fib_table_flush(struct fib_table *tb)
 		if (hlist_empty(&n->leaf)) {
 			put_child_root(pn, n->key, NULL);
 			node_free(n);
-		} else {
-			leaf_pull_suffix(pn, n);
 		}
 	}
 
-- 
2.1.0


From 9119c5bc8f4ef473506590477e0dc196c2bc496d Mon Sep 17 00:00:00 2001
From: Lars Westerhoff <lars.westerhoff@newtec.eu>
Date: Tue, 28 Jul 2015 01:32:21 +0300
Subject: [PATCH 32/46] packet: missing dev_put() in packet_do_bind()

[ Upstream commit 158cd4af8dedbda0d612d448c724c715d0dda649 ]

When binding a PF_PACKET socket, the use count of the bound interface is
always increased with dev_hold in dev_get_by_{index,name}.  However,
when rebound with the same protocol and device as in the previous bind
the use count of the interface was not decreased.  Ultimately, this
caused the deletion of the interface to fail with the following message:

unregister_netdevice: waiting for dummy0 to become free. Usage count = 1

This patch moves the dev_put out of the conditional part that was only
executed when either the protocol or device changed on a bind.

Fixes: 902fefb82ef7 ('packet: improve socket create/bind latency in some cases')
Signed-off-by: Lars Westerhoff <lars.westerhoff@newtec.eu>
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index fe1610d..733ef5a 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2688,7 +2688,7 @@ static int packet_release(struct socket *sock)
 static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
 {
 	struct packet_sock *po = pkt_sk(sk);
-	const struct net_device *dev_curr;
+	struct net_device *dev_curr;
 	__be16 proto_curr;
 	bool need_rehook;
 
@@ -2712,15 +2712,13 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
 
 		po->num = proto;
 		po->prot_hook.type = proto;
-
-		if (po->prot_hook.dev)
-			dev_put(po->prot_hook.dev);
-
 		po->prot_hook.dev = dev;
 
 		po->ifindex = dev ? dev->ifindex : 0;
 		packet_cached_dev_assign(po, dev);
 	}
+	if (dev_curr)
+		dev_put(dev_curr);
 
 	if (proto == 0 || !need_rehook)
 		goto out_unlock;
-- 
2.1.0


From dbd3501b0f680161110947cb7ba49b308a2d182e Mon Sep 17 00:00:00 2001
From: Alexander Drozdov <al.drozdov@gmail.com>
Date: Tue, 28 Jul 2015 13:57:01 +0300
Subject: [PATCH 33/46] packet: tpacket_snd(): fix signed/unsigned comparison

[ Upstream commit dbd46ab412b8fb395f2b0ff6f6a7eec9df311550 ]

tpacket_fill_skb() can return a negative value (-errno) which
is stored in tp_len variable. In that case the following
condition will be (but shouldn't be) true:

tp_len > dev->mtu + dev->hard_header_len

as dev->mtu and dev->hard_header_len are both unsigned.

That may lead to just returning an incorrect EMSGSIZE errno
to the user.

Fixes: 52f1454f629fa ("packet: allow to transmit +4 byte in TX_RING slot for VLAN case")
Signed-off-by: Alexander Drozdov <al.drozdov@gmail.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 733ef5a..e1ea5d4 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2307,7 +2307,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 		}
 		tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto,
 					  addr, hlen);
-		if (tp_len > dev->mtu + dev->hard_header_len) {
+		if (likely(tp_len >= 0) &&
+		    tp_len > dev->mtu + dev->hard_header_len) {
 			struct ethhdr *ehdr;
 			/* Earlier code assumed this would be a VLAN pkt,
 			 * double-check this now that we have the actual
-- 
2.1.0


From 9f07a1825bac3efa34dcb2d50944377edcf39d38 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 29 Jul 2015 18:40:56 +0200
Subject: [PATCH 34/46] act_bpf: fix memory leaks when replacing bpf programs

[ Upstream commit f4eaed28c7834fc049c754f63e6988bbd73778d9 ]

We currently trigger multiple memory leaks when replacing bpf
actions, besides others:

  comm "tc", pid 1909, jiffies 4294851310 (age 1602.796s)
  hex dump (first 32 bytes):
    01 00 00 00 03 00 00 00 00 00 00 00 00 00 00 00  ................
    18 b0 98 6d 00 88 ff ff 00 00 00 00 00 00 00 00  ...m............
  backtrace:
    [<ffffffff817e623e>] kmemleak_alloc+0x4e/0xb0
    [<ffffffff8120a22d>] __vmalloc_node_range+0x1bd/0x2c0
    [<ffffffff8120a37a>] __vmalloc+0x4a/0x50
    [<ffffffff811a8d0a>] bpf_prog_alloc+0x3a/0xa0
    [<ffffffff816c0684>] bpf_prog_create+0x44/0xa0
    [<ffffffffa09ba4eb>] tcf_bpf_init+0x28b/0x3c0 [act_bpf]
    [<ffffffff816d7001>] tcf_action_init_1+0x191/0x1b0
    [<ffffffff816d70a2>] tcf_action_init+0x82/0xf0
    [<ffffffff816d4d12>] tcf_exts_validate+0xb2/0xc0
    [<ffffffffa09b5838>] cls_bpf_modify_existing+0x98/0x340 [cls_bpf]
    [<ffffffffa09b5cd6>] cls_bpf_change+0x1a6/0x274 [cls_bpf]
    [<ffffffff816d56e5>] tc_ctl_tfilter+0x335/0x910
    [<ffffffff816b9145>] rtnetlink_rcv_msg+0x95/0x240
    [<ffffffff816df34f>] netlink_rcv_skb+0xaf/0xc0
    [<ffffffff816b909e>] rtnetlink_rcv+0x2e/0x40
    [<ffffffff816deaaf>] netlink_unicast+0xef/0x1b0

Issue is that the old content from tcf_bpf is allocated and needs
to be released when we replace it. We seem to do that since the
beginning of act_bpf on the filter and insns, later on the name as
well.

Example test case, after patch:

  # FOO="1,6 0 0 4294967295,"
  # BAR="1,6 0 0 4294967294,"
  # tc actions add action bpf bytecode "$FOO" index 2
  # tc actions show action bpf
   action order 0: bpf bytecode '1,6 0 0 4294967295' default-action pipe
   index 2 ref 1 bind 0
  # tc actions replace action bpf bytecode "$BAR" index 2
  # tc actions show action bpf
   action order 0: bpf bytecode '1,6 0 0 4294967294' default-action pipe
   index 2 ref 1 bind 0
  # tc actions replace action bpf bytecode "$FOO" index 2
  # tc actions show action bpf
   action order 0: bpf bytecode '1,6 0 0 4294967295' default-action pipe
   index 2 ref 1 bind 0
  # tc actions del action bpf index 2
  [...]
  # echo "scan" > /sys/kernel/debug/kmemleak
  # cat /sys/kernel/debug/kmemleak | grep "comm \"tc\"" | wc -l
  0

Fixes: d23b8ad8ab23 ("tc: add BPF based action")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_bpf.c | 50 +++++++++++++++++++++++++++++++++++---------------
 1 file changed, 35 insertions(+), 15 deletions(-)

diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index dc6a2d3..521ffca 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -27,9 +27,10 @@
 struct tcf_bpf_cfg {
 	struct bpf_prog *filter;
 	struct sock_filter *bpf_ops;
-	char *bpf_name;
+	const char *bpf_name;
 	u32 bpf_fd;
 	u16 bpf_num_ops;
+	bool is_ebpf;
 };
 
 static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act,
@@ -200,6 +201,7 @@ static int tcf_bpf_init_from_ops(struct nlattr **tb, struct tcf_bpf_cfg *cfg)
 	cfg->bpf_ops = bpf_ops;
 	cfg->bpf_num_ops = bpf_num_ops;
 	cfg->filter = fp;
+	cfg->is_ebpf = false;
 
 	return 0;
 }
@@ -234,18 +236,40 @@ static int tcf_bpf_init_from_efd(struct nlattr **tb, struct tcf_bpf_cfg *cfg)
 	cfg->bpf_fd = bpf_fd;
 	cfg->bpf_name = name;
 	cfg->filter = fp;
+	cfg->is_ebpf = true;
 
 	return 0;
 }
 
+static void tcf_bpf_cfg_cleanup(const struct tcf_bpf_cfg *cfg)
+{
+	if (cfg->is_ebpf)
+		bpf_prog_put(cfg->filter);
+	else
+		bpf_prog_destroy(cfg->filter);
+
+	kfree(cfg->bpf_ops);
+	kfree(cfg->bpf_name);
+}
+
+static void tcf_bpf_prog_fill_cfg(const struct tcf_bpf *prog,
+				  struct tcf_bpf_cfg *cfg)
+{
+	cfg->is_ebpf = tcf_bpf_is_ebpf(prog);
+	cfg->filter = prog->filter;
+
+	cfg->bpf_ops = prog->bpf_ops;
+	cfg->bpf_name = prog->bpf_name;
+}
+
 static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 			struct nlattr *est, struct tc_action *act,
 			int replace, int bind)
 {
 	struct nlattr *tb[TCA_ACT_BPF_MAX + 1];
+	struct tcf_bpf_cfg cfg, old;
 	struct tc_act_bpf *parm;
 	struct tcf_bpf *prog;
-	struct tcf_bpf_cfg cfg;
 	bool is_bpf, is_ebpf;
 	int ret;
 
@@ -294,6 +318,9 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 	prog = to_bpf(act);
 	spin_lock_bh(&prog->tcf_lock);
 
+	if (ret != ACT_P_CREATED)
+		tcf_bpf_prog_fill_cfg(prog, &old);
+
 	prog->bpf_ops = cfg.bpf_ops;
 	prog->bpf_name = cfg.bpf_name;
 
@@ -309,29 +336,22 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 
 	if (ret == ACT_P_CREATED)
 		tcf_hash_insert(act);
+	else
+		tcf_bpf_cfg_cleanup(&old);
 
 	return ret;
 
 destroy_fp:
-	if (is_ebpf)
-		bpf_prog_put(cfg.filter);
-	else
-		bpf_prog_destroy(cfg.filter);
-
-	kfree(cfg.bpf_ops);
-	kfree(cfg.bpf_name);
-
+	tcf_bpf_cfg_cleanup(&cfg);
 	return ret;
 }
 
 static void tcf_bpf_cleanup(struct tc_action *act, int bind)
 {
-	const struct tcf_bpf *prog = act->priv;
+	struct tcf_bpf_cfg tmp;
 
-	if (tcf_bpf_is_ebpf(prog))
-		bpf_prog_put(prog->filter);
-	else
-		bpf_prog_destroy(prog->filter);
+	tcf_bpf_prog_fill_cfg(act->priv, &tmp);
+	tcf_bpf_cfg_cleanup(&tmp);
 }
 
 static struct tc_action_ops act_bpf_ops __read_mostly = {
-- 
2.1.0


From a376fa38ddfa431270ed3127873550282d677fe7 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 29 Jul 2015 23:35:25 +0200
Subject: [PATCH 35/46] net: sched: fix refcount imbalance in actions

[ Upstream commit 28e6b67f0b292f557468c139085303b15f1a678f ]

Since commit 55334a5db5cd ("net_sched: act: refuse to remove bound action
outside"), we end up with a wrong reference count for a tc action.

Test case 1:

  FOO="1,6 0 0 4294967295,"
  BAR="1,6 0 0 4294967294,"
  tc filter add dev foo parent 1: bpf bytecode "$FOO" flowid 1:1 \
     action bpf bytecode "$FOO"
  tc actions show action bpf
    action order 0: bpf bytecode '1,6 0 0 4294967295' default-action pipe
    index 1 ref 1 bind 1
  tc actions replace action bpf bytecode "$BAR" index 1
  tc actions show action bpf
    action order 0: bpf bytecode '1,6 0 0 4294967294' default-action pipe
    index 1 ref 2 bind 1
  tc actions replace action bpf bytecode "$FOO" index 1
  tc actions show action bpf
    action order 0: bpf bytecode '1,6 0 0 4294967295' default-action pipe
    index 1 ref 3 bind 1

Test case 2:

  FOO="1,6 0 0 4294967295,"
  tc filter add dev foo parent 1: bpf bytecode "$FOO" flowid 1:1 action ok
  tc actions show action gact
    action order 0: gact action pass
    random type none pass val 0
     index 1 ref 1 bind 1
  tc actions add action drop index 1
    RTNETLINK answers: File exists [...]
  tc actions show action gact
    action order 0: gact action pass
     random type none pass val 0
     index 1 ref 2 bind 1
  tc actions add action drop index 1
    RTNETLINK answers: File exists [...]
  tc actions show action gact
    action order 0: gact action pass
     random type none pass val 0
     index 1 ref 3 bind 1

What happens is that in tcf_hash_check(), we check tcf_common for a given
index and increase tcfc_refcnt and conditionally tcfc_bindcnt when we've
found an existing action. Now there are the following cases:

  1) We do a late binding of an action. In that case, we leave the
     tcfc_refcnt/tcfc_bindcnt increased and are done with the ->init()
     handler. This is correctly handeled.

  2) We replace the given action, or we try to add one without replacing
     and find out that the action at a specific index already exists
     (thus, we go out with error in that case).

In case of 2), we have to undo the reference count increase from
tcf_hash_check() in the tcf_hash_check() function. Currently, we fail to
do so because of the 'tcfc_bindcnt > 0' check which bails out early with
an -EPERM error.

Now, while commit 55334a5db5cd prevents 'tc actions del action ...' on an
already classifier-bound action to drop the reference count (which could
then become negative, wrap around etc), this restriction only accounts for
invocations outside a specific action's ->init() handler.

One possible solution would be to add a flag thus we possibly trigger
the -EPERM ony in situations where it is indeed relevant.

After the patch, above test cases have correct reference count again.

Fixes: 55334a5db5cd ("net_sched: act: refuse to remove bound action outside")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Cong Wang <cwang@twopensource.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/act_api.h |  8 +++++++-
 net/sched/act_api.c   | 11 ++++++-----
 2 files changed, 13 insertions(+), 6 deletions(-)

diff --git a/include/net/act_api.h b/include/net/act_api.h
index 3ee4c92..931738b 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -99,7 +99,6 @@ struct tc_action_ops {
 
 int tcf_hash_search(struct tc_action *a, u32 index);
 void tcf_hash_destroy(struct tc_action *a);
-int tcf_hash_release(struct tc_action *a, int bind);
 u32 tcf_hash_new_index(struct tcf_hashinfo *hinfo);
 int tcf_hash_check(u32 index, struct tc_action *a, int bind);
 int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a,
@@ -107,6 +106,13 @@ int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a,
 void tcf_hash_cleanup(struct tc_action *a, struct nlattr *est);
 void tcf_hash_insert(struct tc_action *a);
 
+int __tcf_hash_release(struct tc_action *a, bool bind, bool strict);
+
+static inline int tcf_hash_release(struct tc_action *a, bool bind)
+{
+	return __tcf_hash_release(a, bind, false);
+}
+
 int tcf_register_action(struct tc_action_ops *a, unsigned int mask);
 int tcf_unregister_action(struct tc_action_ops *a);
 int tcf_action_destroy(struct list_head *actions, int bind);
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 3d43e49..f8d9c2a 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -45,7 +45,7 @@ void tcf_hash_destroy(struct tc_action *a)
 }
 EXPORT_SYMBOL(tcf_hash_destroy);
 
-int tcf_hash_release(struct tc_action *a, int bind)
+int __tcf_hash_release(struct tc_action *a, bool bind, bool strict)
 {
 	struct tcf_common *p = a->priv;
 	int ret = 0;
@@ -53,7 +53,7 @@ int tcf_hash_release(struct tc_action *a, int bind)
 	if (p) {
 		if (bind)
 			p->tcfc_bindcnt--;
-		else if (p->tcfc_bindcnt > 0)
+		else if (strict && p->tcfc_bindcnt > 0)
 			return -EPERM;
 
 		p->tcfc_refcnt--;
@@ -64,9 +64,10 @@ int tcf_hash_release(struct tc_action *a, int bind)
 			ret = 1;
 		}
 	}
+
 	return ret;
 }
-EXPORT_SYMBOL(tcf_hash_release);
+EXPORT_SYMBOL(__tcf_hash_release);
 
 static int tcf_dump_walker(struct sk_buff *skb, struct netlink_callback *cb,
 			   struct tc_action *a)
@@ -136,7 +137,7 @@ static int tcf_del_walker(struct sk_buff *skb, struct tc_action *a)
 		head = &hinfo->htab[tcf_hash(i, hinfo->hmask)];
 		hlist_for_each_entry_safe(p, n, head, tcfc_head) {
 			a->priv = p;
-			ret = tcf_hash_release(a, 0);
+			ret = __tcf_hash_release(a, false, true);
 			if (ret == ACT_P_DELETED) {
 				module_put(a->ops->owner);
 				n_i++;
@@ -413,7 +414,7 @@ int tcf_action_destroy(struct list_head *actions, int bind)
 	int ret = 0;
 
 	list_for_each_entry_safe(a, tmp, actions, list) {
-		ret = tcf_hash_release(a, bind);
+		ret = __tcf_hash_release(a, bind, true);
 		if (ret == ACT_P_DELETED)
 			module_put(a->ops->owner);
 		else if (ret < 0)
-- 
2.1.0


From 40df9588f4415a976f1b67f344757d26f157e4f8 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Sun, 2 Aug 2015 19:29:16 +0200
Subject: [PATCH 36/46] rocker: free netdevice during netdevice removal

[ Upstream commit 1ebd47efa4e17391dfac8caa349c6a8d35f996d1 ]

When removing a port's netdevice in 'rocker_remove_ports', we should
also free the allocated 'net_device' structure. Do that by calling
'free_netdev' after unregistering it.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Fixes: 4b8ac9660af ("rocker: introduce rocker switch driver")
Acked-by: Scott Feldman <sfeldma@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/rocker/rocker.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c
index cf98cc9..73b6fc2 100644
--- a/drivers/net/ethernet/rocker/rocker.c
+++ b/drivers/net/ethernet/rocker/rocker.c
@@ -4587,6 +4587,7 @@ static void rocker_remove_ports(struct rocker *rocker)
 		rocker_port = rocker->ports[i];
 		rocker_port_ig_tbl(rocker_port, ROCKER_OP_FLAG_REMOVE);
 		unregister_netdev(rocker_port->dev);
+		free_netdev(rocker_port->dev);
 	}
 	kfree(rocker->ports);
 }
-- 
2.1.0


From b2c177c64de1f863de832da667ef6f626ccddb48 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Sat, 1 Aug 2015 15:33:26 +0300
Subject: [PATCH 37/46] rds: fix an integer overflow test in
 rds_info_getsockopt()

[ Upstream commit 468b732b6f76b138c0926eadf38ac88467dcd271 ]

"len" is a signed integer.  We check that len is not negative, so it
goes from zero to INT_MAX.  PAGE_SIZE is unsigned long so the comparison
is type promoted to unsigned long.  ULONG_MAX - 4095 is a higher than
INT_MAX so the condition can never be true.

I don't know if this is harmful but it seems safe to limit "len" to
INT_MAX - 4095.

Fixes: a8c879a7ee98 ('RDS: Info and stats')
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/info.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/rds/info.c b/net/rds/info.c
index 9a6b4f6..140a44a 100644
--- a/net/rds/info.c
+++ b/net/rds/info.c
@@ -176,7 +176,7 @@ int rds_info_getsockopt(struct socket *sock, int optname, char __user *optval,
 
 	/* check for all kinds of wrapping and the like */
 	start = (unsigned long)optval;
-	if (len < 0 || len + PAGE_SIZE - 1 < len || start + len < start) {
+	if (len < 0 || len > INT_MAX - PAGE_SIZE + 1 || start + len < start) {
 		ret = -EINVAL;
 		goto out;
 	}
-- 
2.1.0


From 346f0535765909d0f5fda364f365e05f8e602879 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 1 Aug 2015 12:14:33 +0200
Subject: [PATCH 38/46] udp: fix dst races with multicast early demux
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 10e2eb878f3ca07ac2f05fa5ca5e6c4c9174a27a ]

Multicast dst are not cached. They carry DST_NOCACHE.

As mentioned in commit f8864972126899 ("ipv4: fix dst race in
sk_dst_get()"), these dst need special care before caching them
into a socket.

Caching them is allowed only if their refcnt was not 0, ie we
must use atomic_inc_not_zero()

Also, we must use READ_ONCE() to fetch sk->sk_rx_dst, as mentioned
in commit d0c294c53a771 ("tcp: prevent fetching dst twice in early demux
code")

Fixes: 421b3885bf6d ("udp: ipv4: Add udp early demux")
Tested-by: Gregory Hoggarth <Gregory.Hoggarth@alliedtelesis.co.nz>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Gregory Hoggarth <Gregory.Hoggarth@alliedtelesis.co.nz>
Reported-by: Alex Gartrell <agartrell@fb.com>
Cc: Michal Kubeček <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 83aa604..1b8c5ba 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1995,12 +1995,19 @@ void udp_v4_early_demux(struct sk_buff *skb)
 
 	skb->sk = sk;
 	skb->destructor = sock_efree;
-	dst = sk->sk_rx_dst;
+	dst = READ_ONCE(sk->sk_rx_dst);
 
 	if (dst)
 		dst = dst_check(dst, 0);
-	if (dst)
-		skb_dst_set_noref(skb, dst);
+	if (dst) {
+		/* DST_NOCACHE can not be used without taking a reference */
+		if (dst->flags & DST_NOCACHE) {
+			if (likely(atomic_inc_not_zero(&dst->__refcnt)))
+				skb_dst_set(skb, dst);
+		} else {
+			skb_dst_set_noref(skb, dst);
+		}
+	}
 }
 
 int udp_rcv(struct sk_buff *skb)
-- 
2.1.0


From 469e1ebf7f9f83516cd805f0a8f2392d1b8298a3 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Tue, 4 Aug 2015 19:06:32 +0200
Subject: [PATCH 39/46] bridge: netlink: account for the IFLA_BRPORT_PROXYARP
 attribute size and policy

[ Upstream commit 355b9f9df1f0311f20087350aee8ad96eedca8a9 ]

The attribute size wasn't accounted for in the get_slave_size() callback
(br_port_get_slave_size) when it was introduced, so fix it now. Also add
a policy entry for it in br_port_policy.

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Fixes: 958501163ddd ("bridge: Add support for IEEE 802.11 Proxy ARP")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_netlink.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 20e06a9..95ef032 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -112,6 +112,7 @@ static inline size_t br_port_info_size(void)
 		+ nla_total_size(1)	/* IFLA_BRPORT_FAST_LEAVE */
 		+ nla_total_size(1)	/* IFLA_BRPORT_LEARNING */
 		+ nla_total_size(1)	/* IFLA_BRPORT_UNICAST_FLOOD */
+		+ nla_total_size(1)	/* IFLA_BRPORT_PROXYARP */
 		+ 0;
 }
 
@@ -504,6 +505,7 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = {
 	[IFLA_BRPORT_FAST_LEAVE]= { .type = NLA_U8 },
 	[IFLA_BRPORT_LEARNING]	= { .type = NLA_U8 },
 	[IFLA_BRPORT_UNICAST_FLOOD] = { .type = NLA_U8 },
+	[IFLA_BRPORT_PROXYARP]	= { .type = NLA_U8 },
 };
 
 /* Change the state of the port and notify spanning tree */
-- 
2.1.0


From 7cea8ba728e377145ddb3c0c449beca792171109 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Tue, 4 Aug 2015 19:06:33 +0200
Subject: [PATCH 40/46] bridge: netlink: account for the
 IFLA_BRPORT_PROXYARP_WIFI attribute size and policy

[ Upstream commit 786c2077ec8e9eab37a88fc14aac4309a8061e18 ]

The attribute size wasn't accounted for in the get_slave_size() callback
(br_port_get_slave_size) when it was introduced, so fix it now. Also add
a policy entry for it in br_port_policy.

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Fixes: 842a9ae08a25 ("bridge: Extend Proxy ARP design to allow optional rules for Wi-Fi")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_netlink.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 95ef032..a7559ef 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -113,6 +113,7 @@ static inline size_t br_port_info_size(void)
 		+ nla_total_size(1)	/* IFLA_BRPORT_LEARNING */
 		+ nla_total_size(1)	/* IFLA_BRPORT_UNICAST_FLOOD */
 		+ nla_total_size(1)	/* IFLA_BRPORT_PROXYARP */
+		+ nla_total_size(1)	/* IFLA_BRPORT_PROXYARP_WIFI */
 		+ 0;
 }
 
@@ -506,6 +507,7 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = {
 	[IFLA_BRPORT_LEARNING]	= { .type = NLA_U8 },
 	[IFLA_BRPORT_UNICAST_FLOOD] = { .type = NLA_U8 },
 	[IFLA_BRPORT_PROXYARP]	= { .type = NLA_U8 },
+	[IFLA_BRPORT_PROXYARP_WIFI] = { .type = NLA_U8 },
 };
 
 /* Change the state of the port and notify spanning tree */
-- 
2.1.0


From 61c226cb391165314b5ee42cc6f72bc9b29bc897 Mon Sep 17 00:00:00 2001
From: Ivan Vecera <ivecera@redhat.com>
Date: Thu, 6 Aug 2015 22:48:23 +0200
Subject: [PATCH 41/46] bna: fix interrupts storm caused by erroneous packets

[ Upstream commit ade4dc3e616e33c80d7e62855fe1b6f9895bc7c3 ]

The commit "e29aa33 bna: Enable Multi Buffer RX" moved packets counter
increment from the beginning of the NAPI processing loop after the check
for erroneous packets so they are never accounted. This counter is used
to inform firmware about number of processed completions (packets).
As these packets are never acked the firmware fires IRQs for them again
and again.

Fixes: e29aa33 ("bna: Enable Multi Buffer RX")
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Acked-by: Rasesh Mody <rasesh.mody@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/brocade/bna/bnad.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index caae6cb..a1c30ee 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -675,6 +675,7 @@ bnad_cq_process(struct bnad *bnad, struct bna_ccb *ccb, int budget)
 			if (!next_cmpl->valid)
 				break;
 		}
+		packets++;
 
 		/* TODO: BNA_CQ_EF_LOCAL ? */
 		if (unlikely(flags & (BNA_CQ_EF_MAC_ERROR |
@@ -691,7 +692,6 @@ bnad_cq_process(struct bnad *bnad, struct bna_ccb *ccb, int budget)
 		else
 			bnad_cq_setup_skb_frags(rcb, skb, sop_ci, nvecs, len);
 
-		packets++;
 		rcb->rxq->rx_packets++;
 		rcb->rxq->rx_bytes += totlen;
 		ccb->bytes_per_intr += totlen;
-- 
2.1.0


From a4f50b7501f98b5e76e695bb3f8c892429082f90 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 7 Aug 2015 00:26:41 +0200
Subject: [PATCH 42/46] netlink: make sure -EBUSY won't escape from
 netlink_insert

[ Upstream commit 4e7c1330689e27556de407d3fdadc65ffff5eb12 ]

Linus reports the following deadlock on rtnl_mutex; triggered only
once so far (extract):

[12236.694209] NetworkManager  D 0000000000013b80     0  1047      1 0x00000000
[12236.694218]  ffff88003f902640 0000000000000000 ffffffff815d15a9 0000000000000018
[12236.694224]  ffff880119538000 ffff88003f902640 ffffffff81a8ff84 00000000ffffffff
[12236.694230]  ffffffff81a8ff88 ffff880119c47f00 ffffffff815d133a ffffffff81a8ff80
[12236.694235] Call Trace:
[12236.694250]  [<ffffffff815d15a9>] ? schedule_preempt_disabled+0x9/0x10
[12236.694257]  [<ffffffff815d133a>] ? schedule+0x2a/0x70
[12236.694263]  [<ffffffff815d15a9>] ? schedule_preempt_disabled+0x9/0x10
[12236.694271]  [<ffffffff815d2c3f>] ? __mutex_lock_slowpath+0x7f/0xf0
[12236.694280]  [<ffffffff815d2cc6>] ? mutex_lock+0x16/0x30
[12236.694291]  [<ffffffff814f1f90>] ? rtnetlink_rcv+0x10/0x30
[12236.694299]  [<ffffffff8150ce3b>] ? netlink_unicast+0xfb/0x180
[12236.694309]  [<ffffffff814f5ad3>] ? rtnl_getlink+0x113/0x190
[12236.694319]  [<ffffffff814f202a>] ? rtnetlink_rcv_msg+0x7a/0x210
[12236.694331]  [<ffffffff8124565c>] ? sock_has_perm+0x5c/0x70
[12236.694339]  [<ffffffff814f1fb0>] ? rtnetlink_rcv+0x30/0x30
[12236.694346]  [<ffffffff8150d62c>] ? netlink_rcv_skb+0x9c/0xc0
[12236.694354]  [<ffffffff814f1f9f>] ? rtnetlink_rcv+0x1f/0x30
[12236.694360]  [<ffffffff8150ce3b>] ? netlink_unicast+0xfb/0x180
[12236.694367]  [<ffffffff8150d344>] ? netlink_sendmsg+0x484/0x5d0
[12236.694376]  [<ffffffff810a236f>] ? __wake_up+0x2f/0x50
[12236.694387]  [<ffffffff814cad23>] ? sock_sendmsg+0x33/0x40
[12236.694396]  [<ffffffff814cb05e>] ? ___sys_sendmsg+0x22e/0x240
[12236.694405]  [<ffffffff814cab75>] ? ___sys_recvmsg+0x135/0x1a0
[12236.694415]  [<ffffffff811a9d12>] ? eventfd_write+0x82/0x210
[12236.694423]  [<ffffffff811a0f9e>] ? fsnotify+0x32e/0x4c0
[12236.694429]  [<ffffffff8108cb70>] ? wake_up_q+0x60/0x60
[12236.694434]  [<ffffffff814cba09>] ? __sys_sendmsg+0x39/0x70
[12236.694440]  [<ffffffff815d4797>] ? entry_SYSCALL_64_fastpath+0x12/0x6a

It seems so far plausible that the recursive call into rtnetlink_rcv()
looks suspicious. One way, where this could trigger is that the senders
NETLINK_CB(skb).portid was wrongly 0 (which is rtnetlink socket), so
the rtnl_getlink() request's answer would be sent to the kernel instead
to the actual user process, thus grabbing rtnl_mutex() twice.

One theory would be that netlink_autobind() triggered via netlink_sendmsg()
internally overwrites the -EBUSY error to 0, but where it is wrongly
originating from __netlink_insert() instead. That would reset the
socket's portid to 0, which is then filled into NETLINK_CB(skb).portid
later on. As commit d470e3b483dc ("[NETLINK]: Fix two socket hashing bugs.")
also puts it, -EBUSY should not be propagated from netlink_insert().

It looks like it's very unlikely to reproduce. We need to trigger the
rhashtable_insert_rehash() handler under a situation where rehashing
currently occurs (one /rare/ way would be to hit ht->elasticity limits
while not filled enough to expand the hashtable, but that would rather
require a specifically crafted bind() sequence with knowledge about
destination slots, seems unlikely). It probably makes sense to guard
__netlink_insert() in any case and remap that error. It was suggested
that EOVERFLOW might be better than an already overloaded ENOMEM.

Reference: http://thread.gmane.org/gmane.linux.network/372676
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index ea5ed7a..4856d97 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1094,6 +1094,11 @@ static int netlink_insert(struct sock *sk, u32 portid)
 
 	err = __netlink_insert(table, sk);
 	if (err) {
+		/* In case the hashtable backend returns with -EBUSY
+		 * from here, it must not escape to the caller.
+		 */
+		if (unlikely(err == -EBUSY))
+			err = -EOVERFLOW;
 		if (err == -EEXIST)
 			err = -EADDRINUSE;
 		nlk_sk(sk)->portid = 0;
-- 
2.1.0


From 538c509b7f2287f77363c6410216160d082dba22 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 10 Aug 2015 15:07:34 -0700
Subject: [PATCH 43/46] inet: fix possible request socket leak

[ Upstream commit 3257d8b12f954c462d29de6201664a846328a522 ]

In commit b357a364c57c9 ("inet: fix possible panic in
reqsk_queue_unlink()"), I missed fact that tcp_check_req()
can return the listener socket in one case, and that we must
release the request socket refcount or we leak it.

Tested:

 Following packetdrill test template shows the issue

0     socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+0    setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+0    bind(3, ..., ...) = 0
+0    listen(3, 1) = 0

+0    < S 0:0(0) win 2920 <mss 1460,sackOK,nop,nop>
+0    > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK>
+.002 < . 1:1(0) ack 21 win 2920
+0    > R 21:21(0)

Fixes: b357a364c57c9 ("inet: fix possible panic in reqsk_queue_unlink()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c | 2 +-
 net/ipv6/tcp_ipv6.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index fc1c658..441ca6f 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1348,7 +1348,7 @@ static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
 	req = inet_csk_search_req(sk, th->source, iph->saddr, iph->daddr);
 	if (req) {
 		nsk = tcp_check_req(sk, skb, req, false);
-		if (!nsk)
+		if (!nsk || nsk == sk)
 			reqsk_put(req);
 		return nsk;
 	}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 3adffb3..e541d68 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -946,7 +946,7 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk, struct sk_buff *skb)
 				   &ipv6_hdr(skb)->daddr, tcp_v6_iif(skb));
 	if (req) {
 		nsk = tcp_check_req(sk, skb, req, false);
-		if (!nsk)
+		if (!nsk || nsk == sk)
 			reqsk_put(req);
 		return nsk;
 	}
-- 
2.1.0


From 5712cc9fa64a51b05baa1fa1e7a56e911ad47e3e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 10 Aug 2015 09:09:13 -0700
Subject: [PATCH 44/46] inet: fix races with reqsk timers

[ Upstream commit 2235f2ac75fd2501c251b0b699a9632e80239a6d ]

reqsk_queue_destroy() and reqsk_queue_unlink() should use
del_timer_sync() instead of del_timer() before calling reqsk_put(),
otherwise we could free a req still used by another cpu.

But before doing so, reqsk_queue_destroy() must release syn_wait_lock
spinlock or risk a dead lock, as reqsk_timer_handler() might
need to take this same spinlock from reqsk_queue_unlink() (called from
inet_csk_reqsk_queue_drop())

Fixes: fa76ce7328b2 ("inet: get rid of central tcp/dccp listener timer")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/request_sock.c         | 8 +++++++-
 net/ipv4/inet_connection_sock.c | 2 +-
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/core/request_sock.c b/net/core/request_sock.c
index 87b22c0..b42f0e2 100644
--- a/net/core/request_sock.c
+++ b/net/core/request_sock.c
@@ -103,10 +103,16 @@ void reqsk_queue_destroy(struct request_sock_queue *queue)
 			spin_lock_bh(&queue->syn_wait_lock);
 			while ((req = lopt->syn_table[i]) != NULL) {
 				lopt->syn_table[i] = req->dl_next;
+				/* Because of following del_timer_sync(),
+				 * we must release the spinlock here
+				 * or risk a dead lock.
+				 */
+				spin_unlock_bh(&queue->syn_wait_lock);
 				atomic_inc(&lopt->qlen_dec);
-				if (del_timer(&req->rsk_timer))
+				if (del_timer_sync(&req->rsk_timer))
 					reqsk_put(req);
 				reqsk_put(req);
+				spin_lock_bh(&queue->syn_wait_lock);
 			}
 			spin_unlock_bh(&queue->syn_wait_lock);
 		}
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 8976ca4..b27fc40 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -584,7 +584,7 @@ static bool reqsk_queue_unlink(struct request_sock_queue *queue,
 	}
 
 	spin_unlock(&queue->syn_wait_lock);
-	if (del_timer(&req->rsk_timer))
+	if (del_timer_sync(&req->rsk_timer))
 		reqsk_put(req);
 	return found;
 }
-- 
2.1.0


From 6f5087e42a1d9b2ebb7340eeea948b9524e54862 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Sat, 8 Aug 2015 12:58:57 -0700
Subject: [PATCH 45/46] net: dsa: Do not override PHY interface if already
 configured

[ Upstream commit 211c504a444710b1d8ce3431ac19f2578602ca27 ]

In case we need to divert reads/writes using the slave MII bus, we may have
already fetched a valid PHY interface property from Device Tree, and that
mode is used by the PHY driver to make configuration decisions.

If we could not fetch the "phy-mode" property, we will assign p->phy_interface
to PHY_INTERFACE_MODE_NA, such that we can actually check for that condition as
to whether or not we should override the interface value.

Fixes: 19334920eaf7 ("net: dsa: Set valid phy interface type")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/slave.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 827cda56..57978c5 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -732,7 +732,8 @@ static int dsa_slave_phy_connect(struct dsa_slave_priv *p,
 		return -ENODEV;
 
 	/* Use already configured phy mode */
-	p->phy_interface = p->phy->interface;
+	if (p->phy_interface == PHY_INTERFACE_MODE_NA)
+		p->phy_interface = p->phy->interface;
 	phy_connect_direct(slave_dev, p->phy, dsa_slave_adjust_link,
 			   p->phy_interface);
 
-- 
2.1.0


From 75eefed4fed0fd630556144eedcfed7e017ca96a Mon Sep 17 00:00:00 2001
From: Andy Whitcroft <apw@canonical.com>
Date: Thu, 13 Aug 2015 20:49:01 +0100
Subject: [PATCH 46/46] ipv4: off-by-one in continuation handling in
 /proc/net/route

[ Upstream commit 25b97c016b26039982daaa2c11d83979f93b71ab ]

When generating /proc/net/route we emit a header followed by a line for
each route.  When a short read is performed we will restart this process
based on the open file descriptor.  When calculating the start point we
fail to take into account that the 0th entry is the header.  This leads
us to skip the first entry when doing a continuation read.

This can be easily seen with the comparison below:

  while read l; do echo "$l"; done </proc/net/route >A
  cat /proc/net/route >B
  diff -bu A B | grep '^[+-]'

On my example machine I have approximatly 10KB of route output.  There we
see the very first non-title element is lost in the while read case,
and an entry around the 8K mark in the cat case:

  +wlan0 00000000 02021EAC 0003 0 0 400 00000000 0 0 0
  -tun1  00C0AC0A 00000000 0001 0 0 950 00C0FFFF 0 0 0

Fix up the off-by-one when reaquiring position on continuation.

Fixes: 8be33e955cb9 ("fib_trie: Fib walk rcu should take a tnode and key instead of a trie and a leaf")
BugLink: http://bugs.launchpad.net/bugs/1483440
Acked-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: Andy Whitcroft <apw@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_trie.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 210ceca..0ca933d 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -2453,7 +2453,7 @@ static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter,
 		key = l->key + 1;
 		iter->pos++;
 
-		if (pos-- <= 0)
+		if (--pos <= 0)
 			break;
 
 		l = NULL;
-- 
2.1.0

Re: [PATCHES] Networking

[Jiri Slaby]

On 08/27/2015, 08:05 AM, David Miller wrote:
> Please queue up the following networking bug fixes for v3.12, v3.14, v3.18,
> and v4.1 -stable, respectively.

Great, applied to 3.12. Thanks!

-- 
js
suse labs

Re: [PATCHES] Networking

[Luis Henriques]

Hi David,

On Wed, Aug 26, 2015 at 11:05:12PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v3.12, v3.14, v3.18,
> and v4.1 -stable, respectively.
> 
> Thanks!

While going through these patches to pick those applicable to the 3.16
kernel, I believe I found an issue with the backport of 1c1bf34951e8
("net/mlx4_core: Fix wrong index in propagating port change event to
VFs") into 3.14.

The 2nd hunk has the following:

@@ -583,7 +583,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 					for (i = 0; i < dev->num_slaves; i++) {
 						if (i == mlx4_master_func_num(dev))
 							continue;
-						s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state;
+						s_info = &priv->mfunc.master.vf_oper[slave].vport[i].state;

It should be:

-						s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state;
+						s_info = &priv->mfunc.master.vf_oper[i].vport[port].state;

(the 'slave' index should be changed by 'i', not 'port').

Cheers,
--
Lu�s

Re: [PATCHES] Networking

[David Miller]

From: Luis Henriques <luis.henriques@canonical.com>
Date: Thu, 27 Aug 2015 14:35:57 +0100

> Hi David,
> 
> On Wed, Aug 26, 2015 at 11:05:12PM -0700, David Miller wrote:
>> 
>> Please queue up the following networking bug fixes for v3.12, v3.14, v3.18,
>> and v4.1 -stable, respectively.
>> 
>> Thanks!
> 
> While going through these patches to pick those applicable to the 3.16
> kernel, I believe I found an issue with the backport of 1c1bf34951e8
> ("net/mlx4_core: Fix wrong index in propagating port change event to
> VFs") into 3.14.
> 
> The 2nd hunk has the following:
> 
> @@ -583,7 +583,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
>  					for (i = 0; i < dev->num_slaves; i++) {
>  						if (i == mlx4_master_func_num(dev))
>  							continue;
> -						s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state;
> +						s_info = &priv->mfunc.master.vf_oper[slave].vport[i].state;
> 
> It should be:
> 
> -						s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state;
> +						s_info = &priv->mfunc.master.vf_oper[i].vport[port].state;
> 
> (the 'slave' index should be changed by 'i', not 'port').

Sorry, you are definitely correct.  I hope the v3.14 -stable maintain
catches this, thanks!

Re: [PATCHES] Networking

[Greg KH]

On Wed, Aug 26, 2015 at 11:05:12PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v3.12, v3.14, v3.18,
> and v4.1 -stable, respectively.
> 
> Thanks!




Sorry for the long delay, my fault, now queued up, thanks.

greg k-h

Re: [PATCHES] Networking

[Greg KH]

On Thu, Aug 27, 2015 at 09:34:44AM -0700, David Miller wrote:
> From: Luis Henriques <luis.henriques@canonical.com>
> Date: Thu, 27 Aug 2015 14:35:57 +0100
> 
> > Hi David,
> > 
> > On Wed, Aug 26, 2015 at 11:05:12PM -0700, David Miller wrote:
> >> 
> >> Please queue up the following networking bug fixes for v3.12, v3.14, v3.18,
> >> and v4.1 -stable, respectively.
> >> 
> >> Thanks!
> > 
> > While going through these patches to pick those applicable to the 3.16
> > kernel, I believe I found an issue with the backport of 1c1bf34951e8
> > ("net/mlx4_core: Fix wrong index in propagating port change event to
> > VFs") into 3.14.
> > 
> > The 2nd hunk has the following:
> > 
> > @@ -583,7 +583,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
> >  					for (i = 0; i < dev->num_slaves; i++) {
> >  						if (i == mlx4_master_func_num(dev))
> >  							continue;
> > -						s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state;
> > +						s_info = &priv->mfunc.master.vf_oper[slave].vport[i].state;
> > 
> > It should be:
> > 
> > -						s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state;
> > +						s_info = &priv->mfunc.master.vf_oper[i].vport[port].state;
> > 
> > (the 'slave' index should be changed by 'i', not 'port').
> 
> Sorry, you are definitely correct.  I hope the v3.14 -stable maintain
> catches this, thanks!

Now fixed, thanks.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 117 bytes --]


Please queue up the following networking bug fixes for v3.14, v3.18,
v4.1, and v4.2 -stable, respectively.

Thanks!

[-- Attachment #2: net_314.mbox --]
[-- Type: Application/Octet-Stream, Size: 24549 bytes --]

From 64a1954f6811ea50b5fc7477d1ac43cb8bd054b5 Mon Sep 17 00:00:00 2001
From: huaibin Wang <huaibin.wang@6wind.com>
Date: Tue, 25 Aug 2015 16:20:34 +0200
Subject: [PATCH 1/8] ip6_gre: release cached dst on tunnel removal

[ Upstream commit d4257295ba1b389c693b79de857a96e4b7cd8ac0 ]

When a tunnel is deleted, the cached dst entry should be released.

This problem may prevent the removal of a netns (seen with a x-netns IPv6
gre tunnel):
  unregister_netdevice: waiting for lo to become free. Usage count = 3

CC: Dmitry Kozlov <xeb@mail.ru>
Fixes: c12b395a4664 ("gre: Support GRE over IPv6")
Signed-off-by: huaibin Wang <huaibin.wang@6wind.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 4a230b1..baffa3b 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -357,6 +357,7 @@ static void ip6gre_tunnel_uninit(struct net_device *dev)
 	struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
 
 	ip6gre_tunnel_unlink(ign, netdev_priv(dev));
+	ip6_tnl_dst_reset(netdev_priv(dev));
 	dev_put(dev);
 }
 
-- 
2.1.0


From 85f774be138b8b06c2fbd88cfdaabc1899ee9704 Mon Sep 17 00:00:00 2001
From: Eugene Shatokhin <eugene.shatokhin@rosalab.ru>
Date: Mon, 24 Aug 2015 23:13:42 +0300
Subject: [PATCH 2/8] usbnet: Get EVENT_NO_RUNTIME_PM bit before it is cleared

[ Upstream commit f50791ac1aca1ac1b0370d62397b43e9f831421a ]

It is needed to check EVENT_NO_RUNTIME_PM bit of dev->flags in
usbnet_stop(), but its value should be read before it is cleared
when dev->flags is set to 0.

The problem was spotted and the fix was provided by
Oliver Neukum <oneukum@suse.de>.

Signed-off-by: Eugene Shatokhin <eugene.shatokhin@rosalab.ru>
Acked-by: Oliver Neukum <oneukum@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/usbnet.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index f9e96c4..23dc131 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -778,7 +778,7 @@ int usbnet_stop (struct net_device *net)
 {
 	struct usbnet		*dev = netdev_priv(net);
 	struct driver_info	*info = dev->driver_info;
-	int			retval, pm;
+	int			retval, pm, mpn;
 
 	clear_bit(EVENT_DEV_OPEN, &dev->flags);
 	netif_stop_queue (net);
@@ -809,6 +809,8 @@ int usbnet_stop (struct net_device *net)
 
 	usbnet_purge_paused_rxq(dev);
 
+	mpn = !test_and_clear_bit(EVENT_NO_RUNTIME_PM, &dev->flags);
+
 	/* deferred work (task, timer, softirq) must also stop.
 	 * can't flush_scheduled_work() until we drop rtnl (later),
 	 * else workers could deadlock; so make workers a NOP.
@@ -819,8 +821,7 @@ int usbnet_stop (struct net_device *net)
 	if (!pm)
 		usb_autopm_put_interface(dev->intf);
 
-	if (info->manage_power &&
-	    !test_and_clear_bit(EVENT_NO_RUNTIME_PM, &dev->flags))
+	if (info->manage_power && mpn)
 		info->manage_power(dev, 0);
 	else
 		usb_autopm_put_interface(dev->intf);
-- 
2.1.0


From 43fdbd6841747b2f924c2a108f70c24871c7f858 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 3 Sep 2015 00:29:07 +0200
Subject: [PATCH 3/8] ipv6: fix exthdrs offload registration in out_rt path

[ Upstream commit e41b0bedba0293b9e1e8d1e8ed553104b9693656 ]

We previously register IPPROTO_ROUTING offload under inet6_add_offload(),
but in error path, we try to unregister it with inet_del_offload(). This
doesn't seem correct, it should actually be inet6_del_offload(), also
ipv6_exthdrs_offload_exit() from that commit seems rather incorrect (it
also uses rthdr_offload twice), but it got removed entirely later on.

Fixes: 3336288a9fea ("ipv6: Switch to using new offload infrastructure.")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/exthdrs_offload.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/exthdrs_offload.c b/net/ipv6/exthdrs_offload.c
index 447a7fb..f5e2ba1 100644
--- a/net/ipv6/exthdrs_offload.c
+++ b/net/ipv6/exthdrs_offload.c
@@ -36,6 +36,6 @@ out:
 	return ret;
 
 out_rt:
-	inet_del_offload(&rthdr_offload, IPPROTO_ROUTING);
+	inet6_del_offload(&rthdr_offload, IPPROTO_ROUTING);
 	goto out;
 }
-- 
2.1.0


From 311ab9d79c1add43ad8e76e4562d9132b1c9759c Mon Sep 17 00:00:00 2001
From: Richard Laing <richard.laing@alliedtelesis.co.nz>
Date: Thu, 3 Sep 2015 13:52:31 +1200
Subject: [PATCH 4/8] net/ipv6: Correct PIM6 mrt_lock handling

[ Upstream commit 25b4a44c19c83d98e8c0807a7ede07c1f28eab8b ]

In the IPv6 multicast routing code the mrt_lock was not being released
correctly in the MFC iterator, as a result adding or deleting a MIF would
cause a hang because the mrt_lock could not be acquired.

This fix is a copy of the code for the IPv4 case and ensures that the lock
is released correctly.

Signed-off-by: Richard Laing <richard.laing@alliedtelesis.co.nz>
Acked-by: Cong Wang <cwang@twopensource.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6mr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 8737400..821d8df 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -552,7 +552,7 @@ static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v)
 
 	if (it->cache == &mrt->mfc6_unres_queue)
 		spin_unlock_bh(&mfc_unres_lock);
-	else if (it->cache == mrt->mfc6_cache_array)
+	else if (it->cache == &mrt->mfc6_cache_array[it->ct])
 		read_unlock(&mrt_lock);
 }
 
-- 
2.1.0


From 63be25ac5910449798b3e545431d4d8babaf8ec3 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 10 Sep 2015 20:05:46 +0200
Subject: [PATCH 5/8] netlink, mmap: transform mmap skb into full skb on taps

[ Upstream commit 1853c949646005b5959c483becde86608f548f24 ]

Ken-ichirou reported that running netlink in mmap mode for receive in
combination with nlmon will throw a NULL pointer dereference in
__kfree_skb() on nlmon_xmit(), in my case I can also trigger an "unable
to handle kernel paging request". The problem is the skb_clone() in
__netlink_deliver_tap_skb() for skbs that are mmaped.

I.e. the cloned skb doesn't have a destructor, whereas the mmap netlink
skb has it pointed to netlink_skb_destructor(), set in the handler
netlink_ring_setup_skb(). There, skb->head is being set to NULL, so
that in such cases, __kfree_skb() doesn't perform a skb_release_data()
via skb_release_all(), where skb->head is possibly being freed through
kfree(head) into slab allocator, although netlink mmap skb->head points
to the mmap buffer. Similarly, the same has to be done also for large
netlink skbs where the data area is vmalloced. Therefore, as discussed,
make a copy for these rather rare cases for now. This fixes the issue
on my and Ken-ichirou's test-cases.

Reference: http://thread.gmane.org/gmane.linux.network/371129
Fixes: bcbde0d449ed ("net: netlink: virtual tap device management")
Reported-by: Ken-ichirou MATSUZAWA <chamaken@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Ken-ichirou MATSUZAWA <chamaken@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 30 +++++++++++++++++++++++-------
 net/netlink/af_netlink.h |  9 +++++++++
 2 files changed, 32 insertions(+), 7 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index a0b0ea9..28119f6 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -115,6 +115,24 @@ static inline struct hlist_head *nl_portid_hashfn(struct nl_portid_hash *hash, u
 	return &hash->table[jhash_1word(portid, hash->rnd) & hash->mask];
 }
 
+static struct sk_buff *netlink_to_full_skb(const struct sk_buff *skb,
+					   gfp_t gfp_mask)
+{
+	unsigned int len = skb_end_offset(skb);
+	struct sk_buff *new;
+
+	new = alloc_skb(len, gfp_mask);
+	if (new == NULL)
+		return NULL;
+
+	NETLINK_CB(new).portid = NETLINK_CB(skb).portid;
+	NETLINK_CB(new).dst_group = NETLINK_CB(skb).dst_group;
+	NETLINK_CB(new).creds = NETLINK_CB(skb).creds;
+
+	memcpy(skb_put(new, len), skb->data, len);
+	return new;
+}
+
 int netlink_add_tap(struct netlink_tap *nt)
 {
 	if (unlikely(nt->dev->type != ARPHRD_NETLINK))
@@ -199,7 +217,11 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb,
 	int ret = -ENOMEM;
 
 	dev_hold(dev);
-	nskb = skb_clone(skb, GFP_ATOMIC);
+
+	if (netlink_skb_is_mmaped(skb) || is_vmalloc_addr(skb->head))
+		nskb = netlink_to_full_skb(skb, GFP_ATOMIC);
+	else
+		nskb = skb_clone(skb, GFP_ATOMIC);
 	if (nskb) {
 		nskb->dev = dev;
 		nskb->protocol = htons((u16) sk->sk_protocol);
@@ -271,11 +293,6 @@ static void netlink_rcv_wake(struct sock *sk)
 }
 
 #ifdef CONFIG_NETLINK_MMAP
-static bool netlink_skb_is_mmaped(const struct sk_buff *skb)
-{
-	return NETLINK_CB(skb).flags & NETLINK_SKB_MMAPED;
-}
-
 static bool netlink_rx_is_mmaped(struct sock *sk)
 {
 	return nlk_sk(sk)->rx_ring.pg_vec != NULL;
@@ -812,7 +829,6 @@ static void netlink_ring_set_copied(struct sock *sk, struct sk_buff *skb)
 }
 
 #else /* CONFIG_NETLINK_MMAP */
-#define netlink_skb_is_mmaped(skb)	false
 #define netlink_rx_is_mmaped(sk)	false
 #define netlink_tx_is_mmaped(sk)	false
 #define netlink_mmap			sock_no_mmap
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index acbd774..dcc89c7 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -65,6 +65,15 @@ struct nl_portid_hash {
 	u32			rnd;
 };
 
+static inline bool netlink_skb_is_mmaped(const struct sk_buff *skb)
+{
+#ifdef CONFIG_NETLINK_MMAP
+	return NETLINK_CB(skb).flags & NETLINK_SKB_MMAPED;
+#else
+	return false;
+#endif /* CONFIG_NETLINK_MMAP */
+}
+
 struct netlink_table {
 	struct nl_portid_hash	hash;
 	struct hlist_head	mc_list;
-- 
2.1.0


From 4d926a5772e7c840bfce1a43d52e243ab57135a1 Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Thu, 10 Sep 2015 17:31:15 -0300
Subject: [PATCH 6/8] sctp: fix race on protocol/netns initialization

[ Upstream commit 8e2d61e0aed2b7c4ecb35844fe07e0b2b762dee4 ]

Consider sctp module is unloaded and is being requested because an user
is creating a sctp socket.

During initialization, sctp will add the new protocol type and then
initialize pernet subsys:

        status = sctp_v4_protosw_init();
        if (status)
                goto err_protosw_init;

        status = sctp_v6_protosw_init();
        if (status)
                goto err_v6_protosw_init;

        status = register_pernet_subsys(&sctp_net_ops);

The problem is that after those calls to sctp_v{4,6}_protosw_init(), it
is possible for userspace to create SCTP sockets like if the module is
already fully loaded. If that happens, one of the possible effects is
that we will have readers for net->sctp.local_addr_list list earlier
than expected and sctp_net_init() does not take precautions while
dealing with that list, leading to a potential panic but not limited to
that, as sctp_sock_init() will copy a bunch of blank/partially
initialized values from net->sctp.

The race happens like this:

     CPU 0                           |  CPU 1
  socket()                           |
   __sock_create                     | socket()
    inet_create                      |  __sock_create
     list_for_each_entry_rcu(        |
        answer, &inetsw[sock->type], |
        list) {                      |   inet_create
      /* no hits */                  |
     if (unlikely(err)) {            |
      ...                            |
      request_module()               |
      /* socket creation is blocked  |
       * the module is fully loaded  |
       */                            |
       sctp_init                     |
        sctp_v4_protosw_init         |
         inet_register_protosw       |
          list_add_rcu(&p->list,     |
                       last_perm);   |
                                     |  list_for_each_entry_rcu(
                                     |     answer, &inetsw[sock->type],
        sctp_v6_protosw_init         |     list) {
                                     |     /* hit, so assumes protocol
                                     |      * is already loaded
                                     |      */
                                     |  /* socket creation continues
                                     |   * before netns is initialized
                                     |   */
        register_pernet_subsys       |

Simply inverting the initialization order between
register_pernet_subsys() and sctp_v4_protosw_init() is not possible
because register_pernet_subsys() will create a control sctp socket, so
the protocol must be already visible by then. Deferring the socket
creation to a work-queue is not good specially because we loose the
ability to handle its errors.

So, as suggested by Vlad, the fix is to split netns initialization in
two moments: defaults and control socket, so that the defaults are
already loaded by when we register the protocol, while control socket
initialization is kept at the same moment it is today.

Fixes: 4db67e808640 ("sctp: Make the address lists per network namespace")
Signed-off-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/protocol.c | 64 ++++++++++++++++++++++++++++++++++-------------------
 1 file changed, 41 insertions(+), 23 deletions(-)

diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index a62a215..1237a23 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -1167,7 +1167,7 @@ static void sctp_v4_del_protocol(void)
 	unregister_inetaddr_notifier(&sctp_inetaddr_notifier);
 }
 
-static int __net_init sctp_net_init(struct net *net)
+static int __net_init sctp_defaults_init(struct net *net)
 {
 	int status;
 
@@ -1260,12 +1260,6 @@ static int __net_init sctp_net_init(struct net *net)
 
 	sctp_dbg_objcnt_init(net);
 
-	/* Initialize the control inode/socket for handling OOTB packets.  */
-	if ((status = sctp_ctl_sock_init(net))) {
-		pr_err("Failed to initialize the SCTP control sock\n");
-		goto err_ctl_sock_init;
-	}
-
 	/* Initialize the local address list. */
 	INIT_LIST_HEAD(&net->sctp.local_addr_list);
 	spin_lock_init(&net->sctp.local_addr_lock);
@@ -1281,9 +1275,6 @@ static int __net_init sctp_net_init(struct net *net)
 
 	return 0;
 
-err_ctl_sock_init:
-	sctp_dbg_objcnt_exit(net);
-	sctp_proc_exit(net);
 err_init_proc:
 	cleanup_sctp_mibs(net);
 err_init_mibs:
@@ -1292,15 +1283,12 @@ err_sysctl_register:
 	return status;
 }
 
-static void __net_exit sctp_net_exit(struct net *net)
+static void __net_exit sctp_defaults_exit(struct net *net)
 {
 	/* Free the local address list */
 	sctp_free_addr_wq(net);
 	sctp_free_local_addr_list(net);
 
-	/* Free the control endpoint.  */
-	inet_ctl_sock_destroy(net->sctp.ctl_sock);
-
 	sctp_dbg_objcnt_exit(net);
 
 	sctp_proc_exit(net);
@@ -1308,9 +1296,32 @@ static void __net_exit sctp_net_exit(struct net *net)
 	sctp_sysctl_net_unregister(net);
 }
 
-static struct pernet_operations sctp_net_ops = {
-	.init = sctp_net_init,
-	.exit = sctp_net_exit,
+static struct pernet_operations sctp_defaults_ops = {
+	.init = sctp_defaults_init,
+	.exit = sctp_defaults_exit,
+};
+
+static int __net_init sctp_ctrlsock_init(struct net *net)
+{
+	int status;
+
+	/* Initialize the control inode/socket for handling OOTB packets.  */
+	status = sctp_ctl_sock_init(net);
+	if (status)
+		pr_err("Failed to initialize the SCTP control sock\n");
+
+	return status;
+}
+
+static void __net_init sctp_ctrlsock_exit(struct net *net)
+{
+	/* Free the control endpoint.  */
+	inet_ctl_sock_destroy(net->sctp.ctl_sock);
+}
+
+static struct pernet_operations sctp_ctrlsock_ops = {
+	.init = sctp_ctrlsock_init,
+	.exit = sctp_ctrlsock_exit,
 };
 
 /* Initialize the universe into something sensible.  */
@@ -1444,8 +1455,11 @@ static __init int sctp_init(void)
 	sctp_v4_pf_init();
 	sctp_v6_pf_init();
 
-	status = sctp_v4_protosw_init();
+	status = register_pernet_subsys(&sctp_defaults_ops);
+	if (status)
+		goto err_register_defaults;
 
+	status = sctp_v4_protosw_init();
 	if (status)
 		goto err_protosw_init;
 
@@ -1453,9 +1467,9 @@ static __init int sctp_init(void)
 	if (status)
 		goto err_v6_protosw_init;
 
-	status = register_pernet_subsys(&sctp_net_ops);
+	status = register_pernet_subsys(&sctp_ctrlsock_ops);
 	if (status)
-		goto err_register_pernet_subsys;
+		goto err_register_ctrlsock;
 
 	status = sctp_v4_add_protocol();
 	if (status)
@@ -1471,12 +1485,14 @@ out:
 err_v6_add_protocol:
 	sctp_v4_del_protocol();
 err_add_protocol:
-	unregister_pernet_subsys(&sctp_net_ops);
-err_register_pernet_subsys:
+	unregister_pernet_subsys(&sctp_ctrlsock_ops);
+err_register_ctrlsock:
 	sctp_v6_protosw_exit();
 err_v6_protosw_init:
 	sctp_v4_protosw_exit();
 err_protosw_init:
+	unregister_pernet_subsys(&sctp_defaults_ops);
+err_register_defaults:
 	sctp_v4_pf_exit();
 	sctp_v6_pf_exit();
 	sctp_sysctl_unregister();
@@ -1509,12 +1525,14 @@ static __exit void sctp_exit(void)
 	sctp_v6_del_protocol();
 	sctp_v4_del_protocol();
 
-	unregister_pernet_subsys(&sctp_net_ops);
+	unregister_pernet_subsys(&sctp_ctrlsock_ops);
 
 	/* Free protosw registrations */
 	sctp_v6_protosw_exit();
 	sctp_v4_protosw_exit();
 
+	unregister_pernet_subsys(&sctp_defaults_ops);
+
 	/* Unregister with socket layer. */
 	sctp_v6_pf_exit();
 	sctp_v4_pf_exit();
-- 
2.1.0


From c746e0a10bd5da46f589bdaffa17575ba14df439 Mon Sep 17 00:00:00 2001
From: Jesse Gross <jesse@nicira.com>
Date: Mon, 21 Sep 2015 20:21:20 -0700
Subject: [PATCH 7/8] openvswitch: Zero flows on allocation.

[ Upstream commit ae5f2fb1d51fa128a460bcfbe3c56d7ab8bf6a43 ]

When support for megaflows was introduced, OVS needed to start
installing flows with a mask applied to them. Since masking is an
expensive operation, OVS also had an optimization that would only
take the parts of the flow keys that were covered by a non-zero
mask. The values stored in the remaining pieces should not matter
because they are masked out.

While this works fine for the purposes of matching (which must always
look at the mask), serialization to netlink can be problematic. Since
the flow and the mask are serialized separately, the uninitialized
portions of the flow can be encoded with whatever values happen to be
present.

In terms of functionality, this has little effect since these fields
will be masked out by definition. However, it leaks kernel memory to
userspace, which is a potential security vulnerability. It is also
possible that other code paths could look at the masked key and get
uninitialized data, although this does not currently appear to be an
issue in practice.

This removes the mask optimization for flows that are being installed.
This was always intended to be the case as the mask optimizations were
really targetting per-packet flow operations.

Fixes: 03f0d916 ("openvswitch: Mega flow implementation")
Signed-off-by: Jesse Gross <jesse@nicira.com>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/datapath.c   |  2 +-
 net/openvswitch/flow_table.c | 21 ++++++++++++---------
 net/openvswitch/flow_table.h |  2 +-
 3 files changed, 14 insertions(+), 11 deletions(-)

diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 270b77d..8bb1a5a 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -803,7 +803,7 @@ static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info)
 		if (IS_ERR(acts))
 			goto error;
 
-		ovs_flow_mask_key(&masked_key, &key, &mask);
+		ovs_flow_mask_key(&masked_key, &key, true, &mask);
 		error = ovs_nla_copy_actions(a[OVS_FLOW_ATTR_ACTIONS],
 					     &masked_key, 0, &acts);
 		if (error) {
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index 3c268b3..4877d5a 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -55,18 +55,21 @@ static u16 range_n_bytes(const struct sw_flow_key_range *range)
 }
 
 void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
-		       const struct sw_flow_mask *mask)
+		       bool full, const struct sw_flow_mask *mask)
 {
-	const long *m = (long *)((u8 *)&mask->key + mask->range.start);
-	const long *s = (long *)((u8 *)src + mask->range.start);
-	long *d = (long *)((u8 *)dst + mask->range.start);
+	int start = full ? 0 : mask->range.start;
+	int len = full ? sizeof *dst : range_n_bytes(&mask->range);
+	const long *m = (const long *)((const u8 *)&mask->key + start);
+	const long *s = (const long *)((const u8 *)src + start);
+	long *d = (long *)((u8 *)dst + start);
 	int i;
 
-	/* The memory outside of the 'mask->range' are not set since
-	 * further operations on 'dst' only uses contents within
-	 * 'mask->range'.
+	/* If 'full' is true then all of 'dst' is fully initialized. Otherwise,
+	 * if 'full' is false the memory outside of the 'mask->range' is left
+	 * uninitialized. This can be used as an optimization when further
+	 * operations on 'dst' only use contents within 'mask->range'.
 	 */
-	for (i = 0; i < range_n_bytes(&mask->range); i += sizeof(long))
+	for (i = 0; i < len; i += sizeof(long))
 		*d++ = *s++ & *m++;
 }
 
@@ -436,7 +439,7 @@ static struct sw_flow *masked_flow_lookup(struct table_instance *ti,
 	u32 hash;
 	struct sw_flow_key masked_key;
 
-	ovs_flow_mask_key(&masked_key, unmasked, mask);
+	ovs_flow_mask_key(&masked_key, unmasked, false, mask);
 	hash = flow_hash(&masked_key, key_start, key_end);
 	head = find_bucket(ti, hash);
 	hlist_for_each_entry_rcu(flow, head, hash_node[ti->node_ver]) {
diff --git a/net/openvswitch/flow_table.h b/net/openvswitch/flow_table.h
index baaeb10..82e64a9 100644
--- a/net/openvswitch/flow_table.h
+++ b/net/openvswitch/flow_table.h
@@ -79,5 +79,5 @@ bool ovs_flow_cmp_unmasked_key(const struct sw_flow *flow,
 			       struct sw_flow_match *match);
 
 void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
-		       const struct sw_flow_mask *mask);
+		       bool full, const struct sw_flow_mask *mask);
 #endif /* flow_table.h */
-- 
2.1.0


From 6c4dea7ae27cd5e42bf2176211070c6846893129 Mon Sep 17 00:00:00 2001
From: Wilson Kok <wkok@cumulusnetworks.com>
Date: Tue, 22 Sep 2015 21:40:22 -0700
Subject: [PATCH 8/8] fib_rules: fix fib rule dumps across multiple skbs

[ Upstream commit 41fc014332d91ee90c32840bf161f9685b7fbf2b ]

dump_rules returns skb length and not error.
But when family == AF_UNSPEC, the caller of dump_rules
assumes that it returns an error. Hence, when family == AF_UNSPEC,
we continue trying to dump on -EMSGSIZE errors resulting in
incorrect dump idx carried between skbs belonging to the same dump.
This results in fib rule dump always only dumping rules that fit
into the first skb.

This patch fixes dump_rules to return error so that we exit correctly
and idx is correctly maintained between skbs that are part of the
same dump.

Signed-off-by: Wilson Kok <wkok@cumulusnetworks.com>
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/fib_rules.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 185c341..aeedc3a 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -621,15 +621,17 @@ static int dump_rules(struct sk_buff *skb, struct netlink_callback *cb,
 {
 	int idx = 0;
 	struct fib_rule *rule;
+	int err = 0;
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(rule, &ops->rules_list, list) {
 		if (idx < cb->args[1])
 			goto skip;
 
-		if (fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid,
-				     cb->nlh->nlmsg_seq, RTM_NEWRULE,
-				     NLM_F_MULTI, ops) < 0)
+		err = fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid,
+				       cb->nlh->nlmsg_seq, RTM_NEWRULE,
+				       NLM_F_MULTI, ops);
+		if (err)
 			break;
 skip:
 		idx++;
@@ -638,7 +640,7 @@ skip:
 	cb->args[1] = idx;
 	rules_ops_put(ops);
 
-	return skb->len;
+	return err;
 }
 
 static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb)
@@ -654,7 +656,9 @@ static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb)
 		if (ops == NULL)
 			return -EAFNOSUPPORT;
 
-		return dump_rules(skb, cb, ops);
+		dump_rules(skb, cb, ops);
+
+		return skb->len;
 	}
 
 	rcu_read_lock();
-- 
2.1.0


[-- Attachment #3: net_318.mbox --]
[-- Type: Application/Octet-Stream, Size: 32017 bytes --]

From 786c86281cef8a44a3a49db9bcbb4dd04039c802 Mon Sep 17 00:00:00 2001
From: huaibin Wang <huaibin.wang@6wind.com>
Date: Tue, 25 Aug 2015 16:20:34 +0200
Subject: [PATCH 01/12] ip6_gre: release cached dst on tunnel removal

[ Upstream commit d4257295ba1b389c693b79de857a96e4b7cd8ac0 ]

When a tunnel is deleted, the cached dst entry should be released.

This problem may prevent the removal of a netns (seen with a x-netns IPv6
gre tunnel):
  unregister_netdevice: waiting for lo to become free. Usage count = 3

CC: Dmitry Kozlov <xeb@mail.ru>
Fixes: c12b395a4664 ("gre: Support GRE over IPv6")
Signed-off-by: huaibin Wang <huaibin.wang@6wind.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 0e32d2e..fe85d46 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -361,6 +361,7 @@ static void ip6gre_tunnel_uninit(struct net_device *dev)
 	struct ip6gre_net *ign = net_generic(t->net, ip6gre_net_id);
 
 	ip6gre_tunnel_unlink(ign, t);
+	ip6_tnl_dst_reset(t);
 	dev_put(dev);
 }
 
-- 
2.1.0


From 330448ee09755fa2a746e2165a59ea971a7179d5 Mon Sep 17 00:00:00 2001
From: Eugene Shatokhin <eugene.shatokhin@rosalab.ru>
Date: Mon, 24 Aug 2015 23:13:42 +0300
Subject: [PATCH 02/12] usbnet: Get EVENT_NO_RUNTIME_PM bit before it is
 cleared

[ Upstream commit f50791ac1aca1ac1b0370d62397b43e9f831421a ]

It is needed to check EVENT_NO_RUNTIME_PM bit of dev->flags in
usbnet_stop(), but its value should be read before it is cleared
when dev->flags is set to 0.

The problem was spotted and the fix was provided by
Oliver Neukum <oneukum@suse.de>.

Signed-off-by: Eugene Shatokhin <eugene.shatokhin@rosalab.ru>
Acked-by: Oliver Neukum <oneukum@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/usbnet.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index e7ed251..7a59893 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -779,7 +779,7 @@ int usbnet_stop (struct net_device *net)
 {
 	struct usbnet		*dev = netdev_priv(net);
 	struct driver_info	*info = dev->driver_info;
-	int			retval, pm;
+	int			retval, pm, mpn;
 
 	clear_bit(EVENT_DEV_OPEN, &dev->flags);
 	netif_stop_queue (net);
@@ -810,6 +810,8 @@ int usbnet_stop (struct net_device *net)
 
 	usbnet_purge_paused_rxq(dev);
 
+	mpn = !test_and_clear_bit(EVENT_NO_RUNTIME_PM, &dev->flags);
+
 	/* deferred work (task, timer, softirq) must also stop.
 	 * can't flush_scheduled_work() until we drop rtnl (later),
 	 * else workers could deadlock; so make workers a NOP.
@@ -820,8 +822,7 @@ int usbnet_stop (struct net_device *net)
 	if (!pm)
 		usb_autopm_put_interface(dev->intf);
 
-	if (info->manage_power &&
-	    !test_and_clear_bit(EVENT_NO_RUNTIME_PM, &dev->flags))
+	if (info->manage_power && mpn)
 		info->manage_power(dev, 0);
 	else
 		usb_autopm_put_interface(dev->intf);
-- 
2.1.0


From aaa82c63e101e99c4efa2537695c260a2245f1d7 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 3 Sep 2015 00:29:07 +0200
Subject: [PATCH 03/12] ipv6: fix exthdrs offload registration in out_rt path

[ Upstream commit e41b0bedba0293b9e1e8d1e8ed553104b9693656 ]

We previously register IPPROTO_ROUTING offload under inet6_add_offload(),
but in error path, we try to unregister it with inet_del_offload(). This
doesn't seem correct, it should actually be inet6_del_offload(), also
ipv6_exthdrs_offload_exit() from that commit seems rather incorrect (it
also uses rthdr_offload twice), but it got removed entirely later on.

Fixes: 3336288a9fea ("ipv6: Switch to using new offload infrastructure.")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/exthdrs_offload.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/exthdrs_offload.c b/net/ipv6/exthdrs_offload.c
index 447a7fb..f5e2ba1 100644
--- a/net/ipv6/exthdrs_offload.c
+++ b/net/ipv6/exthdrs_offload.c
@@ -36,6 +36,6 @@ out:
 	return ret;
 
 out_rt:
-	inet_del_offload(&rthdr_offload, IPPROTO_ROUTING);
+	inet6_del_offload(&rthdr_offload, IPPROTO_ROUTING);
 	goto out;
 }
-- 
2.1.0


From f86594cbe2531cc440b9270d7714e178c1af4d17 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Wed, 2 Sep 2015 17:24:14 +0800
Subject: [PATCH 04/12] net: fec: clear receive interrupts before processing a
 packet

[ Upstream commit ed63f1dcd5788d36f942fbcce350742385e3e18c ]

The patch just to re-submit the patch "db3421c114cfa6326" because the
patch "4d494cdc92b3b9a0" remove the change.

Clear any pending receive interrupt before we process a pending packet.
This helps to avoid any spurious interrupts being raised after we have
fully cleaned the receive ring, while still allowing an interrupt to be
raised if we receive another packet.

The position of this is critical: we must do this prior to reading the
next packet status to avoid potentially dropping an interrupt when a
packet is still pending.

Acked-by: Fugang Duan <B38611@freescale.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 96ba23e..56fa3d5 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -1390,6 +1390,7 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
 		if ((status & BD_ENET_RX_LAST) == 0)
 			netdev_err(ndev, "rcv is not +last\n");
 
+		writel(FEC_ENET_RXF, fep->hwp + FEC_IEVENT);
 
 		/* Check for errors. */
 		if (status & (BD_ENET_RX_LG | BD_ENET_RX_SH | BD_ENET_RX_NO |
-- 
2.1.0


From d9b0ef90d9eeddb96d72a0a75799a6f1f768b188 Mon Sep 17 00:00:00 2001
From: Atsushi Nemoto <nemoto@toshiba-tops.co.jp>
Date: Wed, 2 Sep 2015 17:49:29 +0900
Subject: [PATCH 05/12] net: eth: altera: fix napi poll_list corruption

[ Upstream commit 4548a697e4969d695047cebd6d9af5e2f6cc728e ]

tse_poll() calls __napi_complete() with irq enabled.  This leads napi
poll_list corruption and may stop all napi drivers working.
Use napi_complete() instead of __napi_complete().

Signed-off-by: Atsushi Nemoto <nemoto@toshiba-tops.co.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/altera/altera_tse_main.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c
index 4efc435..2eb6404 100644
--- a/drivers/net/ethernet/altera/altera_tse_main.c
+++ b/drivers/net/ethernet/altera/altera_tse_main.c
@@ -501,8 +501,7 @@ static int tse_poll(struct napi_struct *napi, int budget)
 	if (rxcomplete >= budget || txcomplete > 0)
 		return rxcomplete;
 
-	napi_gro_flush(napi, false);
-	__napi_complete(napi);
+	napi_complete(napi);
 
 	netdev_dbg(priv->dev,
 		   "NAPI Complete, did %d packets with budget %d\n",
-- 
2.1.0


From 97aa79a462e1f64861eb6bb75f2220bfaa4bb780 Mon Sep 17 00:00:00 2001
From: Richard Laing <richard.laing@alliedtelesis.co.nz>
Date: Thu, 3 Sep 2015 13:52:31 +1200
Subject: [PATCH 06/12] net/ipv6: Correct PIM6 mrt_lock handling

[ Upstream commit 25b4a44c19c83d98e8c0807a7ede07c1f28eab8b ]

In the IPv6 multicast routing code the mrt_lock was not being released
correctly in the MFC iterator, as a result adding or deleting a MIF would
cause a hang because the mrt_lock could not be acquired.

This fix is a copy of the code for the IPv4 case and ensures that the lock
is released correctly.

Signed-off-by: Richard Laing <richard.laing@alliedtelesis.co.nz>
Acked-by: Cong Wang <cwang@twopensource.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6mr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 1a01d79..0d58542 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -552,7 +552,7 @@ static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v)
 
 	if (it->cache == &mrt->mfc6_unres_queue)
 		spin_unlock_bh(&mfc_unres_lock);
-	else if (it->cache == mrt->mfc6_cache_array)
+	else if (it->cache == &mrt->mfc6_cache_array[it->ct])
 		read_unlock(&mrt_lock);
 }
 
-- 
2.1.0


From bd2de867630d2850e344828be1517e3cf1c1354f Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 8 Sep 2015 20:06:41 -0700
Subject: [PATCH 07/12] net: dsa: bcm_sf2: Fix 64-bits register writes

[ Upstream commit 03679a14739a0d4c14b52ba65a69ff553bfba73b ]

The macro to write 64-bits quantities to the 32-bits register swapped
the value and offsets arguments, we want to preserve the ordering of the
arguments with respect to how writel() is implemented for instance:
value first, offset/base second.

Fixes: 246d7f773c13 ("net: dsa: add Broadcom SF2 switch driver")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/bcm_sf2.h b/drivers/net/dsa/bcm_sf2.h
index ee9f650..3ecfda8 100644
--- a/drivers/net/dsa/bcm_sf2.h
+++ b/drivers/net/dsa/bcm_sf2.h
@@ -110,8 +110,8 @@ static inline u64 name##_readq(struct bcm_sf2_priv *priv, u32 off)	\
 	spin_unlock(&priv->indir_lock);					\
 	return (u64)indir << 32 | dir;					\
 }									\
-static inline void name##_writeq(struct bcm_sf2_priv *priv, u32 off,	\
-							u64 val)	\
+static inline void name##_writeq(struct bcm_sf2_priv *priv, u64 val,	\
+							u32 off)	\
 {									\
 	spin_lock(&priv->indir_lock);					\
 	reg_writel(priv, upper_32_bits(val), REG_DIR_DATA_WRITE);	\
-- 
2.1.0


From 1b44705be0bc71eb59e380b31fa824a4e7d607de Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 10 Sep 2015 20:05:46 +0200
Subject: [PATCH 08/12] netlink, mmap: transform mmap skb into full skb on taps

[ Upstream commit 1853c949646005b5959c483becde86608f548f24 ]

Ken-ichirou reported that running netlink in mmap mode for receive in
combination with nlmon will throw a NULL pointer dereference in
__kfree_skb() on nlmon_xmit(), in my case I can also trigger an "unable
to handle kernel paging request". The problem is the skb_clone() in
__netlink_deliver_tap_skb() for skbs that are mmaped.

I.e. the cloned skb doesn't have a destructor, whereas the mmap netlink
skb has it pointed to netlink_skb_destructor(), set in the handler
netlink_ring_setup_skb(). There, skb->head is being set to NULL, so
that in such cases, __kfree_skb() doesn't perform a skb_release_data()
via skb_release_all(), where skb->head is possibly being freed through
kfree(head) into slab allocator, although netlink mmap skb->head points
to the mmap buffer. Similarly, the same has to be done also for large
netlink skbs where the data area is vmalloced. Therefore, as discussed,
make a copy for these rather rare cases for now. This fixes the issue
on my and Ken-ichirou's test-cases.

Reference: http://thread.gmane.org/gmane.linux.network/371129
Fixes: bcbde0d449ed ("net: netlink: virtual tap device management")
Reported-by: Ken-ichirou MATSUZAWA <chamaken@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Ken-ichirou MATSUZAWA <chamaken@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 30 +++++++++++++++++++++++-------
 net/netlink/af_netlink.h |  9 +++++++++
 2 files changed, 32 insertions(+), 7 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index c82b2e3..da0b73a 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -133,6 +133,24 @@ static inline u32 netlink_group_mask(u32 group)
 	return group ? 1 << (group - 1) : 0;
 }
 
+static struct sk_buff *netlink_to_full_skb(const struct sk_buff *skb,
+					   gfp_t gfp_mask)
+{
+	unsigned int len = skb_end_offset(skb);
+	struct sk_buff *new;
+
+	new = alloc_skb(len, gfp_mask);
+	if (new == NULL)
+		return NULL;
+
+	NETLINK_CB(new).portid = NETLINK_CB(skb).portid;
+	NETLINK_CB(new).dst_group = NETLINK_CB(skb).dst_group;
+	NETLINK_CB(new).creds = NETLINK_CB(skb).creds;
+
+	memcpy(skb_put(new, len), skb->data, len);
+	return new;
+}
+
 int netlink_add_tap(struct netlink_tap *nt)
 {
 	if (unlikely(nt->dev->type != ARPHRD_NETLINK))
@@ -215,7 +233,11 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb,
 	int ret = -ENOMEM;
 
 	dev_hold(dev);
-	nskb = skb_clone(skb, GFP_ATOMIC);
+
+	if (netlink_skb_is_mmaped(skb) || is_vmalloc_addr(skb->head))
+		nskb = netlink_to_full_skb(skb, GFP_ATOMIC);
+	else
+		nskb = skb_clone(skb, GFP_ATOMIC);
 	if (nskb) {
 		nskb->dev = dev;
 		nskb->protocol = htons((u16) sk->sk_protocol);
@@ -287,11 +309,6 @@ static void netlink_rcv_wake(struct sock *sk)
 }
 
 #ifdef CONFIG_NETLINK_MMAP
-static bool netlink_skb_is_mmaped(const struct sk_buff *skb)
-{
-	return NETLINK_CB(skb).flags & NETLINK_SKB_MMAPED;
-}
-
 static bool netlink_rx_is_mmaped(struct sock *sk)
 {
 	return nlk_sk(sk)->rx_ring.pg_vec != NULL;
@@ -828,7 +845,6 @@ static void netlink_ring_set_copied(struct sock *sk, struct sk_buff *skb)
 }
 
 #else /* CONFIG_NETLINK_MMAP */
-#define netlink_skb_is_mmaped(skb)	false
 #define netlink_rx_is_mmaped(sk)	false
 #define netlink_tx_is_mmaped(sk)	false
 #define netlink_mmap			sock_no_mmap
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index b20a173..3951874 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -57,6 +57,15 @@ static inline struct netlink_sock *nlk_sk(struct sock *sk)
 	return container_of(sk, struct netlink_sock, sk);
 }
 
+static inline bool netlink_skb_is_mmaped(const struct sk_buff *skb)
+{
+#ifdef CONFIG_NETLINK_MMAP
+	return NETLINK_CB(skb).flags & NETLINK_SKB_MMAPED;
+#else
+	return false;
+#endif /* CONFIG_NETLINK_MMAP */
+}
+
 struct netlink_table {
 	struct rhashtable	hash;
 	struct hlist_head	mc_list;
-- 
2.1.0


From fd90cd689a1a8d3c28b03ab1e4e5ed5c8fbdd0f7 Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Thu, 10 Sep 2015 17:31:15 -0300
Subject: [PATCH 09/12] sctp: fix race on protocol/netns initialization

[ Upstream commit 8e2d61e0aed2b7c4ecb35844fe07e0b2b762dee4 ]

Consider sctp module is unloaded and is being requested because an user
is creating a sctp socket.

During initialization, sctp will add the new protocol type and then
initialize pernet subsys:

        status = sctp_v4_protosw_init();
        if (status)
                goto err_protosw_init;

        status = sctp_v6_protosw_init();
        if (status)
                goto err_v6_protosw_init;

        status = register_pernet_subsys(&sctp_net_ops);

The problem is that after those calls to sctp_v{4,6}_protosw_init(), it
is possible for userspace to create SCTP sockets like if the module is
already fully loaded. If that happens, one of the possible effects is
that we will have readers for net->sctp.local_addr_list list earlier
than expected and sctp_net_init() does not take precautions while
dealing with that list, leading to a potential panic but not limited to
that, as sctp_sock_init() will copy a bunch of blank/partially
initialized values from net->sctp.

The race happens like this:

     CPU 0                           |  CPU 1
  socket()                           |
   __sock_create                     | socket()
    inet_create                      |  __sock_create
     list_for_each_entry_rcu(        |
        answer, &inetsw[sock->type], |
        list) {                      |   inet_create
      /* no hits */                  |
     if (unlikely(err)) {            |
      ...                            |
      request_module()               |
      /* socket creation is blocked  |
       * the module is fully loaded  |
       */                            |
       sctp_init                     |
        sctp_v4_protosw_init         |
         inet_register_protosw       |
          list_add_rcu(&p->list,     |
                       last_perm);   |
                                     |  list_for_each_entry_rcu(
                                     |     answer, &inetsw[sock->type],
        sctp_v6_protosw_init         |     list) {
                                     |     /* hit, so assumes protocol
                                     |      * is already loaded
                                     |      */
                                     |  /* socket creation continues
                                     |   * before netns is initialized
                                     |   */
        register_pernet_subsys       |

Simply inverting the initialization order between
register_pernet_subsys() and sctp_v4_protosw_init() is not possible
because register_pernet_subsys() will create a control sctp socket, so
the protocol must be already visible by then. Deferring the socket
creation to a work-queue is not good specially because we loose the
ability to handle its errors.

So, as suggested by Vlad, the fix is to split netns initialization in
two moments: defaults and control socket, so that the defaults are
already loaded by when we register the protocol, while control socket
initialization is kept at the same moment it is today.

Fixes: 4db67e808640 ("sctp: Make the address lists per network namespace")
Signed-off-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/protocol.c | 64 ++++++++++++++++++++++++++++++++++-------------------
 1 file changed, 41 insertions(+), 23 deletions(-)

diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 8f34b27..143c4eb 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -1166,7 +1166,7 @@ static void sctp_v4_del_protocol(void)
 	unregister_inetaddr_notifier(&sctp_inetaddr_notifier);
 }
 
-static int __net_init sctp_net_init(struct net *net)
+static int __net_init sctp_defaults_init(struct net *net)
 {
 	int status;
 
@@ -1259,12 +1259,6 @@ static int __net_init sctp_net_init(struct net *net)
 
 	sctp_dbg_objcnt_init(net);
 
-	/* Initialize the control inode/socket for handling OOTB packets.  */
-	if ((status = sctp_ctl_sock_init(net))) {
-		pr_err("Failed to initialize the SCTP control sock\n");
-		goto err_ctl_sock_init;
-	}
-
 	/* Initialize the local address list. */
 	INIT_LIST_HEAD(&net->sctp.local_addr_list);
 	spin_lock_init(&net->sctp.local_addr_lock);
@@ -1280,9 +1274,6 @@ static int __net_init sctp_net_init(struct net *net)
 
 	return 0;
 
-err_ctl_sock_init:
-	sctp_dbg_objcnt_exit(net);
-	sctp_proc_exit(net);
 err_init_proc:
 	cleanup_sctp_mibs(net);
 err_init_mibs:
@@ -1291,15 +1282,12 @@ err_sysctl_register:
 	return status;
 }
 
-static void __net_exit sctp_net_exit(struct net *net)
+static void __net_exit sctp_defaults_exit(struct net *net)
 {
 	/* Free the local address list */
 	sctp_free_addr_wq(net);
 	sctp_free_local_addr_list(net);
 
-	/* Free the control endpoint.  */
-	inet_ctl_sock_destroy(net->sctp.ctl_sock);
-
 	sctp_dbg_objcnt_exit(net);
 
 	sctp_proc_exit(net);
@@ -1307,9 +1295,32 @@ static void __net_exit sctp_net_exit(struct net *net)
 	sctp_sysctl_net_unregister(net);
 }
 
-static struct pernet_operations sctp_net_ops = {
-	.init = sctp_net_init,
-	.exit = sctp_net_exit,
+static struct pernet_operations sctp_defaults_ops = {
+	.init = sctp_defaults_init,
+	.exit = sctp_defaults_exit,
+};
+
+static int __net_init sctp_ctrlsock_init(struct net *net)
+{
+	int status;
+
+	/* Initialize the control inode/socket for handling OOTB packets.  */
+	status = sctp_ctl_sock_init(net);
+	if (status)
+		pr_err("Failed to initialize the SCTP control sock\n");
+
+	return status;
+}
+
+static void __net_init sctp_ctrlsock_exit(struct net *net)
+{
+	/* Free the control endpoint.  */
+	inet_ctl_sock_destroy(net->sctp.ctl_sock);
+}
+
+static struct pernet_operations sctp_ctrlsock_ops = {
+	.init = sctp_ctrlsock_init,
+	.exit = sctp_ctrlsock_exit,
 };
 
 /* Initialize the universe into something sensible.  */
@@ -1443,8 +1454,11 @@ static __init int sctp_init(void)
 	sctp_v4_pf_init();
 	sctp_v6_pf_init();
 
-	status = sctp_v4_protosw_init();
+	status = register_pernet_subsys(&sctp_defaults_ops);
+	if (status)
+		goto err_register_defaults;
 
+	status = sctp_v4_protosw_init();
 	if (status)
 		goto err_protosw_init;
 
@@ -1452,9 +1466,9 @@ static __init int sctp_init(void)
 	if (status)
 		goto err_v6_protosw_init;
 
-	status = register_pernet_subsys(&sctp_net_ops);
+	status = register_pernet_subsys(&sctp_ctrlsock_ops);
 	if (status)
-		goto err_register_pernet_subsys;
+		goto err_register_ctrlsock;
 
 	status = sctp_v4_add_protocol();
 	if (status)
@@ -1470,12 +1484,14 @@ out:
 err_v6_add_protocol:
 	sctp_v4_del_protocol();
 err_add_protocol:
-	unregister_pernet_subsys(&sctp_net_ops);
-err_register_pernet_subsys:
+	unregister_pernet_subsys(&sctp_ctrlsock_ops);
+err_register_ctrlsock:
 	sctp_v6_protosw_exit();
 err_v6_protosw_init:
 	sctp_v4_protosw_exit();
 err_protosw_init:
+	unregister_pernet_subsys(&sctp_defaults_ops);
+err_register_defaults:
 	sctp_v4_pf_exit();
 	sctp_v6_pf_exit();
 	sctp_sysctl_unregister();
@@ -1508,12 +1524,14 @@ static __exit void sctp_exit(void)
 	sctp_v6_del_protocol();
 	sctp_v4_del_protocol();
 
-	unregister_pernet_subsys(&sctp_net_ops);
+	unregister_pernet_subsys(&sctp_ctrlsock_ops);
 
 	/* Free protosw registrations */
 	sctp_v6_protosw_exit();
 	sctp_v4_protosw_exit();
 
+	unregister_pernet_subsys(&sctp_defaults_ops);
+
 	/* Unregister with socket layer. */
 	sctp_v6_pf_exit();
 	sctp_v4_pf_exit();
-- 
2.1.0


From a6c5aeb519e0cae934a0aff1c9195bd2f522f006 Mon Sep 17 00:00:00 2001
From: Jesse Gross <jesse@nicira.com>
Date: Mon, 21 Sep 2015 20:21:20 -0700
Subject: [PATCH 10/12] openvswitch: Zero flows on allocation.

[ Upstream commit ae5f2fb1d51fa128a460bcfbe3c56d7ab8bf6a43 ]

When support for megaflows was introduced, OVS needed to start
installing flows with a mask applied to them. Since masking is an
expensive operation, OVS also had an optimization that would only
take the parts of the flow keys that were covered by a non-zero
mask. The values stored in the remaining pieces should not matter
because they are masked out.

While this works fine for the purposes of matching (which must always
look at the mask), serialization to netlink can be problematic. Since
the flow and the mask are serialized separately, the uninitialized
portions of the flow can be encoded with whatever values happen to be
present.

In terms of functionality, this has little effect since these fields
will be masked out by definition. However, it leaks kernel memory to
userspace, which is a potential security vulnerability. It is also
possible that other code paths could look at the masked key and get
uninitialized data, although this does not currently appear to be an
issue in practice.

This removes the mask optimization for flows that are being installed.
This was always intended to be the case as the mask optimizations were
really targetting per-packet flow operations.

Fixes: 03f0d916 ("openvswitch: Mega flow implementation")
Signed-off-by: Jesse Gross <jesse@nicira.com>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/datapath.c   |  4 ++--
 net/openvswitch/flow_table.c | 23 ++++++++++++-----------
 net/openvswitch/flow_table.h |  2 +-
 3 files changed, 15 insertions(+), 14 deletions(-)

diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 28213df..acf6b2e 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -834,7 +834,7 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	if (error)
 		goto err_kfree_flow;
 
-	ovs_flow_mask_key(&new_flow->key, &new_flow->unmasked_key, &mask);
+	ovs_flow_mask_key(&new_flow->key, &new_flow->unmasked_key, true, &mask);
 
 	/* Validate actions. */
 	acts = ovs_nla_alloc_flow_actions(nla_len(a[OVS_FLOW_ATTR_ACTIONS]));
@@ -949,7 +949,7 @@ static struct sw_flow_actions *get_flow_actions(const struct nlattr *a,
 	if (IS_ERR(acts))
 		return acts;
 
-	ovs_flow_mask_key(&masked_key, key, mask);
+	ovs_flow_mask_key(&masked_key, key, true, mask);
 	error = ovs_nla_copy_actions(a, &masked_key, 0, &acts);
 	if (error) {
 		OVS_NLERR("Flow actions may not be safe on all matching packets.\n");
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index cf2d853..740041a 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -56,20 +56,21 @@ static u16 range_n_bytes(const struct sw_flow_key_range *range)
 }
 
 void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
-		       const struct sw_flow_mask *mask)
+		       bool full, const struct sw_flow_mask *mask)
 {
-	const long *m = (const long *)((const u8 *)&mask->key +
-				mask->range.start);
-	const long *s = (const long *)((const u8 *)src +
-				mask->range.start);
-	long *d = (long *)((u8 *)dst + mask->range.start);
+	int start = full ? 0 : mask->range.start;
+	int len = full ? sizeof *dst : range_n_bytes(&mask->range);
+	const long *m = (const long *)((const u8 *)&mask->key + start);
+	const long *s = (const long *)((const u8 *)src + start);
+	long *d = (long *)((u8 *)dst + start);
 	int i;
 
-	/* The memory outside of the 'mask->range' are not set since
-	 * further operations on 'dst' only uses contents within
-	 * 'mask->range'.
+	/* If 'full' is true then all of 'dst' is fully initialized. Otherwise,
+	 * if 'full' is false the memory outside of the 'mask->range' is left
+	 * uninitialized. This can be used as an optimization when further
+	 * operations on 'dst' only use contents within 'mask->range'.
 	 */
-	for (i = 0; i < range_n_bytes(&mask->range); i += sizeof(long))
+	for (i = 0; i < len; i += sizeof(long))
 		*d++ = *s++ & *m++;
 }
 
@@ -418,7 +419,7 @@ static struct sw_flow *masked_flow_lookup(struct table_instance *ti,
 	u32 hash;
 	struct sw_flow_key masked_key;
 
-	ovs_flow_mask_key(&masked_key, unmasked, mask);
+	ovs_flow_mask_key(&masked_key, unmasked, false, mask);
 	hash = flow_hash(&masked_key, key_start, key_end);
 	head = find_bucket(ti, hash);
 	hlist_for_each_entry_rcu(flow, head, hash_node[ti->node_ver]) {
diff --git a/net/openvswitch/flow_table.h b/net/openvswitch/flow_table.h
index 5918bff..2f0cf20 100644
--- a/net/openvswitch/flow_table.h
+++ b/net/openvswitch/flow_table.h
@@ -82,5 +82,5 @@ bool ovs_flow_cmp_unmasked_key(const struct sw_flow *flow,
 			       struct sw_flow_match *match);
 
 void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
-		       const struct sw_flow_mask *mask);
+		       bool full, const struct sw_flow_mask *mask);
 #endif /* flow_table.h */
-- 
2.1.0


From 9149d5def926efb3c3a4e6bc66d3b3f60591ddbe Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 23 Sep 2015 14:00:21 -0700
Subject: [PATCH 11/12] tcp: add proper TS val into RST packets

[ Upstream commit 675ee231d960af2af3606b4480324e26797eb010 ]

RST packets sent on behalf of TCP connections with TS option (RFC 7323
TCP timestamps) have incorrect TS val (set to 0), but correct TS ecr.

A > B: Flags [S], seq 0, win 65535, options [mss 1000,nop,nop,TS val 100
ecr 0], length 0
B > A: Flags [S.], seq 2444755794, ack 1, win 28960, options [mss
1460,nop,nop,TS val 7264344 ecr 100], length 0
A > B: Flags [.], ack 1, win 65535, options [nop,nop,TS val 110 ecr
7264344], length 0

B > A: Flags [R.], seq 1, ack 1, win 28960, options [nop,nop,TS val 0
ecr 110], length 0

We need to call skb_mstamp_get() to get proper TS val,
derived from skb->skb_mstamp

Note that RFC 1323 was advocating to not send TS option in RST segment,
but RFC 7323 recommends the opposite :

  Once TSopt has been successfully negotiated, that is both <SYN> and
  <SYN,ACK> contain TSopt, the TSopt MUST be sent in every non-<RST>
  segment for the duration of the connection, and SHOULD be sent in an
  <RST> segment (see Section 5.2 for details)

Note this RFC recommends to send TS val = 0, but we believe it is
premature : We do not know if all TCP stacks are properly
handling the receive side :

   When an <RST> segment is
   received, it MUST NOT be subjected to the PAWS check by verifying an
   acceptable value in SEG.TSval, and information from the Timestamps
   option MUST NOT be used to update connection state information.
   SEG.TSecr MAY be used to provide stricter <RST> acceptance checks.

In 5 years, if/when all TCP stack are RFC 7323 ready, we might consider
to decide to send TS val = 0, if it buys something.

Fixes: 7faee5c0d514 ("tcp: remove TCP_SKB_CB(skb)->when")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index dc9f925..9c7d8887 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2798,6 +2798,7 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority)
 	skb_reserve(skb, MAX_TCP_HEADER);
 	tcp_init_nondata_skb(skb, tcp_acceptable_seq(sk),
 			     TCPHDR_ACK | TCPHDR_RST);
+	skb_mstamp_get(&skb->skb_mstamp);
 	/* Send it off. */
 	if (tcp_transmit_skb(sk, skb, 0, priority))
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED);
-- 
2.1.0


From 374d3782e0297a83a398ddad1a67eac606720e22 Mon Sep 17 00:00:00 2001
From: Wilson Kok <wkok@cumulusnetworks.com>
Date: Tue, 22 Sep 2015 21:40:22 -0700
Subject: [PATCH 12/12] fib_rules: fix fib rule dumps across multiple skbs

[ Upstream commit 41fc014332d91ee90c32840bf161f9685b7fbf2b ]

dump_rules returns skb length and not error.
But when family == AF_UNSPEC, the caller of dump_rules
assumes that it returns an error. Hence, when family == AF_UNSPEC,
we continue trying to dump on -EMSGSIZE errors resulting in
incorrect dump idx carried between skbs belonging to the same dump.
This results in fib rule dump always only dumping rules that fit
into the first skb.

This patch fixes dump_rules to return error so that we exit correctly
and idx is correctly maintained between skbs that are part of the
same dump.

Signed-off-by: Wilson Kok <wkok@cumulusnetworks.com>
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/fib_rules.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 185c341..aeedc3a 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -621,15 +621,17 @@ static int dump_rules(struct sk_buff *skb, struct netlink_callback *cb,
 {
 	int idx = 0;
 	struct fib_rule *rule;
+	int err = 0;
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(rule, &ops->rules_list, list) {
 		if (idx < cb->args[1])
 			goto skip;
 
-		if (fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid,
-				     cb->nlh->nlmsg_seq, RTM_NEWRULE,
-				     NLM_F_MULTI, ops) < 0)
+		err = fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid,
+				       cb->nlh->nlmsg_seq, RTM_NEWRULE,
+				       NLM_F_MULTI, ops);
+		if (err)
 			break;
 skip:
 		idx++;
@@ -638,7 +640,7 @@ skip:
 	cb->args[1] = idx;
 	rules_ops_put(ops);
 
-	return skb->len;
+	return err;
 }
 
 static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb)
@@ -654,7 +656,9 @@ static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb)
 		if (ops == NULL)
 			return -EAFNOSUPPORT;
 
-		return dump_rules(skb, cb, ops);
+		dump_rules(skb, cb, ops);
+
+		return skb->len;
 	}
 
 	rcu_read_lock();
-- 
2.1.0


[-- Attachment #4: net_41.mbox --]
[-- Type: Application/Octet-Stream, Size: 85559 bytes --]

From 923462db2683c5e46dcf038528097c7f0e5b83d3 Mon Sep 17 00:00:00 2001
From: huaibin Wang <huaibin.wang@6wind.com>
Date: Tue, 25 Aug 2015 16:20:34 +0200
Subject: [PATCH 01/28] ip6_gre: release cached dst on tunnel removal

[ Upstream commit d4257295ba1b389c693b79de857a96e4b7cd8ac0 ]

When a tunnel is deleted, the cached dst entry should be released.

This problem may prevent the removal of a netns (seen with a x-netns IPv6
gre tunnel):
  unregister_netdevice: waiting for lo to become free. Usage count = 3

CC: Dmitry Kozlov <xeb@mail.ru>
Fixes: c12b395a4664 ("gre: Support GRE over IPv6")
Signed-off-by: huaibin Wang <huaibin.wang@6wind.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index a38d3ac..69f4f68 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -361,6 +361,7 @@ static void ip6gre_tunnel_uninit(struct net_device *dev)
 	struct ip6gre_net *ign = net_generic(t->net, ip6gre_net_id);
 
 	ip6gre_tunnel_unlink(ign, t);
+	ip6_tnl_dst_reset(t);
 	dev_put(dev);
 }
 
-- 
2.1.0


From 9615a90e16e4dc465ccb8d0b0a6d5aae9f3ddfe0 Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Tue, 25 Aug 2015 20:22:35 -0300
Subject: [PATCH 02/28] vxlan: re-ignore EADDRINUSE from igmp_join

[ Upstream commit bef0057b7ba881d5ae67eec876df7a26fe672a59 ]

Before 56ef9c909b40[1] it used to ignore all errors from igmp_join().
That commit enhanced that and made it error out whatever error happened
with igmp_join(), but that's not good because when using multicast
groups vxlan will try to join it multiple times if the socket is reused
and then the 2nd and further attempts will fail with EADDRINUSE.

As we don't track to which groups the socket is already subscribed, it's
okay to just ignore that error.

Fixes: 56ef9c909b40 ("vxlan: Move socket initialization to within rtnl scope")
Reported-by: John Nielsen <lists@jnielsen.net>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 21a0fbf..0085b8d 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2212,6 +2212,8 @@ static int vxlan_open(struct net_device *dev)
 
 	if (vxlan_addr_multicast(&vxlan->default_dst.remote_ip)) {
 		ret = vxlan_igmp_join(vxlan);
+		if (ret == -EADDRINUSE)
+			ret = 0;
 		if (ret) {
 			vxlan_sock_release(vs);
 			return ret;
-- 
2.1.0


From 50829ec4c515b379721304dbcf0e3d6288f56761 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Tue, 25 Aug 2015 16:38:12 -0700
Subject: [PATCH 03/28] cls_u32: complete the check for non-forced case in
 u32_destroy()

[ Upstream commit a6c1aea044e490da3e59124ec55991fe316818d5 ]

In commit 1e052be69d04 ("net_sched: destroy proto tp when all filters are gone")
I added a check in u32_destroy() to see if all real filters are gone
for each tp, however, that is only done for root_ht, same is needed
for others.

This can be reproduced by the following tc commands:

tc filter add dev eth0 parent 1:0 prio 5 handle 15: protocol ip u32 divisor 256
tc filter add dev eth0 protocol ip parent 1: prio 5 handle 15:2:2 u32
ht 15:2: match ip src 10.0.0.2 flowid 1:10
tc filter add dev eth0 protocol ip parent 1: prio 5 handle 15:2:3 u32
ht 15:2: match ip src 10.0.0.3 flowid 1:10

Fixes: 1e052be69d04 ("net_sched: destroy proto tp when all filters are gone")
Reported-by: Akshat Kakkar <akshat.1984@gmail.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Cong Wang <cwang@twopensource.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_u32.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index cab9e9b..4fbb674 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -490,6 +490,19 @@ static bool u32_destroy(struct tcf_proto *tp, bool force)
 					return false;
 			}
 		}
+
+		if (tp_c->refcnt > 1)
+			return false;
+
+		if (tp_c->refcnt == 1) {
+			struct tc_u_hnode *ht;
+
+			for (ht = rtnl_dereference(tp_c->hlist);
+			     ht;
+			     ht = rtnl_dereference(ht->next))
+				if (!ht_empty(ht))
+					return false;
+		}
 	}
 
 	if (root_ht && --root_ht->refcnt == 0)
-- 
2.1.0


From 917a5220ce98d3e0c96899d5d926631ee09fc50b Mon Sep 17 00:00:00 2001
From: Eugene Shatokhin <eugene.shatokhin@rosalab.ru>
Date: Mon, 24 Aug 2015 23:13:42 +0300
Subject: [PATCH 04/28] usbnet: Get EVENT_NO_RUNTIME_PM bit before it is
 cleared

[ Upstream commit f50791ac1aca1ac1b0370d62397b43e9f831421a ]

It is needed to check EVENT_NO_RUNTIME_PM bit of dev->flags in
usbnet_stop(), but its value should be read before it is cleared
when dev->flags is set to 0.

The problem was spotted and the fix was provided by
Oliver Neukum <oneukum@suse.de>.

Signed-off-by: Eugene Shatokhin <eugene.shatokhin@rosalab.ru>
Acked-by: Oliver Neukum <oneukum@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/usbnet.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 3c86b10..e049857 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -778,7 +778,7 @@ int usbnet_stop (struct net_device *net)
 {
 	struct usbnet		*dev = netdev_priv(net);
 	struct driver_info	*info = dev->driver_info;
-	int			retval, pm;
+	int			retval, pm, mpn;
 
 	clear_bit(EVENT_DEV_OPEN, &dev->flags);
 	netif_stop_queue (net);
@@ -809,6 +809,8 @@ int usbnet_stop (struct net_device *net)
 
 	usbnet_purge_paused_rxq(dev);
 
+	mpn = !test_and_clear_bit(EVENT_NO_RUNTIME_PM, &dev->flags);
+
 	/* deferred work (task, timer, softirq) must also stop.
 	 * can't flush_scheduled_work() until we drop rtnl (later),
 	 * else workers could deadlock; so make workers a NOP.
@@ -819,8 +821,7 @@ int usbnet_stop (struct net_device *net)
 	if (!pm)
 		usb_autopm_put_interface(dev->intf);
 
-	if (info->manage_power &&
-	    !test_and_clear_bit(EVENT_NO_RUNTIME_PM, &dev->flags))
+	if (info->manage_power && mpn)
 		info->manage_power(dev, 0);
 	else
 		usb_autopm_put_interface(dev->intf);
-- 
2.1.0


From 4ae73f6fa9d42d42bfa762d48e7d80c6120f58ad Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 2 Sep 2015 14:00:36 +0200
Subject: [PATCH 05/28] sock, diag: fix panic in sock_diag_put_filterinfo

[ Upstream commit b382c08656000c12a146723a153b85b13a855b49 ]

diag socket's sock_diag_put_filterinfo() dumps classic BPF programs
upon request to user space (ss -0 -b). However, native eBPF programs
attached to sockets (SO_ATTACH_BPF) cannot be dumped with this method:

Their orig_prog is always NULL. However, sock_diag_put_filterinfo()
unconditionally tries to access its filter length resp. wants to copy
the filter insns from there. Internal cBPF to eBPF transformations
attached to sockets don't have this issue, as orig_prog state is kept.

It's currently only used by packet sockets. If we would want to add
native eBPF support in the future, this needs to be done through
a different attribute than PACKET_DIAG_FILTER to not confuse possible
user space disassemblers that work on diag data.

Fixes: 89aa075832b0 ("net: sock: allow eBPF programs to be attached to sockets")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock_diag.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index 74dddf8..556ecf96 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -86,6 +86,9 @@ int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk,
 		goto out;
 
 	fprog = filter->prog->orig_prog;
+	if (!fprog)
+		goto out;
+
 	flen = bpf_classic_proglen(fprog);
 
 	attr = nla_reserve(skb, attrtype, flen);
-- 
2.1.0


From 82918a07fe222feea4ebe2dca23f7c0a3c1eb874 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 3 Sep 2015 00:29:07 +0200
Subject: [PATCH 06/28] ipv6: fix exthdrs offload registration in out_rt path

[ Upstream commit e41b0bedba0293b9e1e8d1e8ed553104b9693656 ]

We previously register IPPROTO_ROUTING offload under inet6_add_offload(),
but in error path, we try to unregister it with inet_del_offload(). This
doesn't seem correct, it should actually be inet6_del_offload(), also
ipv6_exthdrs_offload_exit() from that commit seems rather incorrect (it
also uses rthdr_offload twice), but it got removed entirely later on.

Fixes: 3336288a9fea ("ipv6: Switch to using new offload infrastructure.")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/exthdrs_offload.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/exthdrs_offload.c b/net/ipv6/exthdrs_offload.c
index 447a7fb..f5e2ba1 100644
--- a/net/ipv6/exthdrs_offload.c
+++ b/net/ipv6/exthdrs_offload.c
@@ -36,6 +36,6 @@ out:
 	return ret;
 
 out_rt:
-	inet_del_offload(&rthdr_offload, IPPROTO_ROUTING);
+	inet6_del_offload(&rthdr_offload, IPPROTO_ROUTING);
 	goto out;
 }
-- 
2.1.0


From dd222d5ded20452f5d1db209dce7b7babf54be5a Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Wed, 2 Sep 2015 17:24:14 +0800
Subject: [PATCH 07/28] net: fec: clear receive interrupts before processing a
 packet

[ Upstream commit ed63f1dcd5788d36f942fbcce350742385e3e18c ]

The patch just to re-submit the patch "db3421c114cfa6326" because the
patch "4d494cdc92b3b9a0" remove the change.

Clear any pending receive interrupt before we process a pending packet.
This helps to avoid any spurious interrupts being raised after we have
fully cleaned the receive ring, while still allowing an interrupt to be
raised if we receive another packet.

The position of this is critical: we must do this prior to reading the
next packet status to avoid potentially dropping an interrupt when a
packet is still pending.

Acked-by: Fugang Duan <B38611@freescale.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 66d47e4..570390b 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -1396,6 +1396,7 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
 		if ((status & BD_ENET_RX_LAST) == 0)
 			netdev_err(ndev, "rcv is not +last\n");
 
+		writel(FEC_ENET_RXF, fep->hwp + FEC_IEVENT);
 
 		/* Check for errors. */
 		if (status & (BD_ENET_RX_LG | BD_ENET_RX_SH | BD_ENET_RX_NO |
-- 
2.1.0


From e12b93d0d23f3cb4dd68d099408f4c953f0e1347 Mon Sep 17 00:00:00 2001
From: Atsushi Nemoto <nemoto@toshiba-tops.co.jp>
Date: Wed, 2 Sep 2015 17:49:29 +0900
Subject: [PATCH 08/28] net: eth: altera: fix napi poll_list corruption

[ Upstream commit 4548a697e4969d695047cebd6d9af5e2f6cc728e ]

tse_poll() calls __napi_complete() with irq enabled.  This leads napi
poll_list corruption and may stop all napi drivers working.
Use napi_complete() instead of __napi_complete().

Signed-off-by: Atsushi Nemoto <nemoto@toshiba-tops.co.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/altera/altera_tse_main.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c
index da48e66..8207877 100644
--- a/drivers/net/ethernet/altera/altera_tse_main.c
+++ b/drivers/net/ethernet/altera/altera_tse_main.c
@@ -511,8 +511,7 @@ static int tse_poll(struct napi_struct *napi, int budget)
 
 	if (rxcomplete < budget) {
 
-		napi_gro_flush(napi, false);
-		__napi_complete(napi);
+		napi_complete(napi);
 
 		netdev_dbg(priv->dev,
 			   "NAPI Complete, did %d packets with budget %d\n",
-- 
2.1.0


From d8be124bd7a68ccd82c3522c4a3d132c66ffc328 Mon Sep 17 00:00:00 2001
From: Richard Laing <richard.laing@alliedtelesis.co.nz>
Date: Thu, 3 Sep 2015 13:52:31 +1200
Subject: [PATCH 09/28] net/ipv6: Correct PIM6 mrt_lock handling

[ Upstream commit 25b4a44c19c83d98e8c0807a7ede07c1f28eab8b ]

In the IPv6 multicast routing code the mrt_lock was not being released
correctly in the MFC iterator, as a result adding or deleting a MIF would
cause a hang because the mrt_lock could not be acquired.

This fix is a copy of the code for the IPv4 case and ensures that the lock
is released correctly.

Signed-off-by: Richard Laing <richard.laing@alliedtelesis.co.nz>
Acked-by: Cong Wang <cwang@twopensource.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6mr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 74ceb73..5f36266 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -550,7 +550,7 @@ static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v)
 
 	if (it->cache == &mrt->mfc6_unres_queue)
 		spin_unlock_bh(&mfc_unres_lock);
-	else if (it->cache == mrt->mfc6_cache_array)
+	else if (it->cache == &mrt->mfc6_cache_array[it->ct])
 		read_unlock(&mrt_lock);
 }
 
-- 
2.1.0


From 3ba957b71c4b6de20048dba028556cd4aeee3aec Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Sat, 5 Sep 2015 13:07:27 -0700
Subject: [PATCH 10/28] net: dsa: bcm_sf2: Fix ageing conditions and operation

[ Upstream commit 39797a279d62972cd914ef580fdfacb13e508bf8 ]

The comparison check between cur_hw_state and hw_state is currently
invalid because cur_hw_state is right shifted by G_MISTP_SHIFT, while
hw_state is not, so we end-up comparing bits 2:0 with bits 7:5, which is
going to cause an additional aging to occur. Fix this by not shifting
cur_hw_state while reading it, but instead, mask the value with the
appropriately shitfted bitmask.

The other problem with the fast-ageing process is that we did not set
the EN_AGE_DYNAMIC bit to request the ageing to occur for dynamically
learned MAC addresses. Finally, write back 0 to the FAST_AGE_CTRL
register to avoid leaving spurious bits sets from one operation to the
other.

Fixes: 12f460f23423 ("net: dsa: bcm_sf2: add HW bridging support")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index cedb572..f24c4fe 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -417,7 +417,7 @@ static int bcm_sf2_sw_fast_age_port(struct dsa_switch  *ds, int port)
 	core_writel(priv, port, CORE_FAST_AGE_PORT);
 
 	reg = core_readl(priv, CORE_FAST_AGE_CTRL);
-	reg |= EN_AGE_PORT | FAST_AGE_STR_DONE;
+	reg |= EN_AGE_PORT | EN_AGE_DYNAMIC | FAST_AGE_STR_DONE;
 	core_writel(priv, reg, CORE_FAST_AGE_CTRL);
 
 	do {
@@ -431,6 +431,8 @@ static int bcm_sf2_sw_fast_age_port(struct dsa_switch  *ds, int port)
 	if (!timeout)
 		return -ETIMEDOUT;
 
+	core_writel(priv, 0, CORE_FAST_AGE_CTRL);
+
 	return 0;
 }
 
@@ -506,7 +508,7 @@ static int bcm_sf2_sw_br_set_stp_state(struct dsa_switch *ds, int port,
 	u32 reg;
 
 	reg = core_readl(priv, CORE_G_PCTL_PORT(port));
-	cur_hw_state = reg >> G_MISTP_STATE_SHIFT;
+	cur_hw_state = reg & (G_MISTP_STATE_MASK << G_MISTP_STATE_SHIFT);
 
 	switch (state) {
 	case BR_STATE_DISABLED:
@@ -530,10 +532,12 @@ static int bcm_sf2_sw_br_set_stp_state(struct dsa_switch *ds, int port,
 	}
 
 	/* Fast-age ARL entries if we are moving a port from Learning or
-	 * Forwarding state to Disabled, Blocking or Listening state
+	 * Forwarding (cur_hw_state) state to Disabled, Blocking or Listening
+	 * state (hw_state)
 	 */
 	if (cur_hw_state != hw_state) {
-		if (cur_hw_state & 4 && !(hw_state & 4)) {
+		if (cur_hw_state >= G_MISTP_LEARN_STATE &&
+		    hw_state <= G_MISTP_LISTEN_STATE) {
 			ret = bcm_sf2_sw_fast_age_port(ds, port);
 			if (ret) {
 				pr_err("%s: fast-ageing failed\n", __func__);
-- 
2.1.0


From 54ae54b11332d089dc4d9ad989bbf63428d49641 Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Tue, 8 Sep 2015 10:53:04 -0700
Subject: [PATCH 11/28] ipv6: fix multipath route replace error recovery

[ Upstream commit 6b9ea5a64ed5eeb3f68f2e6fcce0ed1179801d1e ]

Problem:
The ecmp route replace support for ipv6 in the kernel, deletes the
existing ecmp route too early, ie when it installs the first nexthop.
If there is an error in installing the subsequent nexthops, its too late
to recover the already deleted existing route leaving the fib
in an inconsistent state.

This patch reduces the possibility of this by doing the following:
a) Changes the existing multipath route add code to a two stage process:
  build rt6_infos + insert them
	ip6_route_add rt6_info creation code is moved into
	ip6_route_info_create.
b) This ensures that most errors are caught during building rt6_infos
  and we fail early
c) Separates multipath add and del code. Because add needs the special
  two stage mode in a) and delete essentially does not care.
d) In any event if the code fails during inserting a route again, a
  warning is printed (This should be unlikely)

Before the patch:
$ip -6 route show
3000:1000:1000:1000::2 via fe80::202:ff:fe00:b dev swp49s0 metric 1024
3000:1000:1000:1000::2 via fe80::202:ff:fe00:d dev swp49s1 metric 1024
3000:1000:1000:1000::2 via fe80::202:ff:fe00:f dev swp49s2 metric 1024

/* Try replacing the route with a duplicate nexthop */
$ip -6 route change 3000:1000:1000:1000::2/128 nexthop via
fe80::202:ff:fe00:b dev swp49s0 nexthop via fe80::202:ff:fe00:d dev
swp49s1 nexthop via fe80::202:ff:fe00:d dev swp49s1
RTNETLINK answers: File exists

$ip -6 route show
/* previously added ecmp route 3000:1000:1000:1000::2 dissappears from
 * kernel */

After the patch:
$ip -6 route show
3000:1000:1000:1000::2 via fe80::202:ff:fe00:b dev swp49s0 metric 1024
3000:1000:1000:1000::2 via fe80::202:ff:fe00:d dev swp49s1 metric 1024
3000:1000:1000:1000::2 via fe80::202:ff:fe00:f dev swp49s2 metric 1024

/* Try replacing the route with a duplicate nexthop */
$ip -6 route change 3000:1000:1000:1000::2/128 nexthop via
fe80::202:ff:fe00:b dev swp49s0 nexthop via fe80::202:ff:fe00:d dev
swp49s1 nexthop via fe80::202:ff:fe00:d dev swp49s1
RTNETLINK answers: File exists

$ip -6 route show
3000:1000:1000:1000::2 via fe80::202:ff:fe00:b dev swp49s0 metric 1024
3000:1000:1000:1000::2 via fe80::202:ff:fe00:d dev swp49s1 metric 1024
3000:1000:1000:1000::2 via fe80::202:ff:fe00:f dev swp49s2 metric 1024

Fixes: 27596472473a ("ipv6: fix ECMP route replacement")
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Reviewed-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 201 ++++++++++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 175 insertions(+), 26 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index c73ae50..f371fef 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1515,7 +1515,7 @@ static int ip6_convert_metrics(struct mx6_config *mxc,
 	return -EINVAL;
 }
 
-int ip6_route_add(struct fib6_config *cfg)
+int ip6_route_info_create(struct fib6_config *cfg, struct rt6_info **rt_ret)
 {
 	int err;
 	struct net *net = cfg->fc_nlinfo.nl_net;
@@ -1523,7 +1523,6 @@ int ip6_route_add(struct fib6_config *cfg)
 	struct net_device *dev = NULL;
 	struct inet6_dev *idev = NULL;
 	struct fib6_table *table;
-	struct mx6_config mxc = { .mx = NULL, };
 	int addr_type;
 
 	if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128)
@@ -1719,6 +1718,32 @@ install_route:
 
 	cfg->fc_nlinfo.nl_net = dev_net(dev);
 
+	*rt_ret = rt;
+
+	return 0;
+out:
+	if (dev)
+		dev_put(dev);
+	if (idev)
+		in6_dev_put(idev);
+	if (rt)
+		dst_free(&rt->dst);
+
+	*rt_ret = NULL;
+
+	return err;
+}
+
+int ip6_route_add(struct fib6_config *cfg)
+{
+	struct mx6_config mxc = { .mx = NULL, };
+	struct rt6_info *rt = NULL;
+	int err;
+
+	err = ip6_route_info_create(cfg, &rt);
+	if (err)
+		goto out;
+
 	err = ip6_convert_metrics(&mxc, cfg);
 	if (err)
 		goto out;
@@ -1726,14 +1751,12 @@ install_route:
 	err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, &mxc);
 
 	kfree(mxc.mx);
+
 	return err;
 out:
-	if (dev)
-		dev_put(dev);
-	if (idev)
-		in6_dev_put(idev);
 	if (rt)
 		dst_free(&rt->dst);
+
 	return err;
 }
 
@@ -2496,19 +2519,78 @@ errout:
 	return err;
 }
 
-static int ip6_route_multipath(struct fib6_config *cfg, int add)
+struct rt6_nh {
+	struct rt6_info *rt6_info;
+	struct fib6_config r_cfg;
+	struct mx6_config mxc;
+	struct list_head next;
+};
+
+static void ip6_print_replace_route_err(struct list_head *rt6_nh_list)
+{
+	struct rt6_nh *nh;
+
+	list_for_each_entry(nh, rt6_nh_list, next) {
+		pr_warn("IPV6: multipath route replace failed (check consistency of installed routes): %pI6 nexthop %pI6 ifi %d\n",
+		        &nh->r_cfg.fc_dst, &nh->r_cfg.fc_gateway,
+		        nh->r_cfg.fc_ifindex);
+	}
+}
+
+static int ip6_route_info_append(struct list_head *rt6_nh_list,
+				 struct rt6_info *rt, struct fib6_config *r_cfg)
+{
+	struct rt6_nh *nh;
+	struct rt6_info *rtnh;
+	int err = -EEXIST;
+
+	list_for_each_entry(nh, rt6_nh_list, next) {
+		/* check if rt6_info already exists */
+		rtnh = nh->rt6_info;
+
+		if (rtnh->dst.dev == rt->dst.dev &&
+		    rtnh->rt6i_idev == rt->rt6i_idev &&
+		    ipv6_addr_equal(&rtnh->rt6i_gateway,
+				    &rt->rt6i_gateway))
+			return err;
+	}
+
+	nh = kzalloc(sizeof(*nh), GFP_KERNEL);
+	if (!nh)
+		return -ENOMEM;
+	nh->rt6_info = rt;
+	err = ip6_convert_metrics(&nh->mxc, r_cfg);
+	if (err) {
+		kfree(nh);
+		return err;
+	}
+	memcpy(&nh->r_cfg, r_cfg, sizeof(*r_cfg));
+	list_add_tail(&nh->next, rt6_nh_list);
+
+	return 0;
+}
+
+static int ip6_route_multipath_add(struct fib6_config *cfg)
 {
 	struct fib6_config r_cfg;
 	struct rtnexthop *rtnh;
+	struct rt6_info *rt;
+	struct rt6_nh *err_nh;
+	struct rt6_nh *nh, *nh_safe;
 	int remaining;
 	int attrlen;
-	int err = 0, last_err = 0;
+	int err = 1;
+	int nhn = 0;
+	int replace = (cfg->fc_nlinfo.nlh &&
+		       (cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_REPLACE));
+	LIST_HEAD(rt6_nh_list);
 
 	remaining = cfg->fc_mp_len;
-beginning:
 	rtnh = (struct rtnexthop *)cfg->fc_mp;
 
-	/* Parse a Multipath Entry */
+	/* Parse a Multipath Entry and build a list (rt6_nh_list) of
+	 * rt6_info structs per nexthop
+	 */
 	while (rtnh_ok(rtnh, remaining)) {
 		memcpy(&r_cfg, cfg, sizeof(*cfg));
 		if (rtnh->rtnh_ifindex)
@@ -2524,22 +2606,32 @@ beginning:
 				r_cfg.fc_flags |= RTF_GATEWAY;
 			}
 		}
-		err = add ? ip6_route_add(&r_cfg) : ip6_route_del(&r_cfg);
+
+		err = ip6_route_info_create(&r_cfg, &rt);
+		if (err)
+			goto cleanup;
+
+		err = ip6_route_info_append(&rt6_nh_list, rt, &r_cfg);
 		if (err) {
-			last_err = err;
-			/* If we are trying to remove a route, do not stop the
-			 * loop when ip6_route_del() fails (because next hop is
-			 * already gone), we should try to remove all next hops.
-			 */
-			if (add) {
-				/* If add fails, we should try to delete all
-				 * next hops that have been already added.
-				 */
-				add = 0;
-				remaining = cfg->fc_mp_len - remaining;
-				goto beginning;
-			}
+			dst_free(&rt->dst);
+			goto cleanup;
+		}
+
+		rtnh = rtnh_next(rtnh, &remaining);
+	}
+
+	err_nh = NULL;
+	list_for_each_entry(nh, &rt6_nh_list, next) {
+		err = __ip6_ins_rt(nh->rt6_info, &cfg->fc_nlinfo, &nh->mxc);
+		/* nh->rt6_info is used or freed at this point, reset to NULL*/
+		nh->rt6_info = NULL;
+		if (err) {
+			if (replace && nhn)
+				ip6_print_replace_route_err(&rt6_nh_list);
+			err_nh = nh;
+			goto add_errout;
 		}
+
 		/* Because each route is added like a single route we remove
 		 * these flags after the first nexthop: if there is a collision,
 		 * we have already failed to add the first nexthop:
@@ -2549,6 +2641,63 @@ beginning:
 		 */
 		cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL |
 						     NLM_F_REPLACE);
+		nhn++;
+	}
+
+	goto cleanup;
+
+add_errout:
+	/* Delete routes that were already added */
+	list_for_each_entry(nh, &rt6_nh_list, next) {
+		if (err_nh == nh)
+			break;
+		ip6_route_del(&nh->r_cfg);
+	}
+
+cleanup:
+	list_for_each_entry_safe(nh, nh_safe, &rt6_nh_list, next) {
+		if (nh->rt6_info)
+			dst_free(&nh->rt6_info->dst);
+		if (nh->mxc.mx)
+			kfree(nh->mxc.mx);
+		list_del(&nh->next);
+		kfree(nh);
+	}
+
+	return err;
+}
+
+static int ip6_route_multipath_del(struct fib6_config *cfg)
+{
+	struct fib6_config r_cfg;
+	struct rtnexthop *rtnh;
+	int remaining;
+	int attrlen;
+	int err = 1, last_err = 0;
+
+	remaining = cfg->fc_mp_len;
+	rtnh = (struct rtnexthop *)cfg->fc_mp;
+
+	/* Parse a Multipath Entry */
+	while (rtnh_ok(rtnh, remaining)) {
+		memcpy(&r_cfg, cfg, sizeof(*cfg));
+		if (rtnh->rtnh_ifindex)
+			r_cfg.fc_ifindex = rtnh->rtnh_ifindex;
+
+		attrlen = rtnh_attrlen(rtnh);
+		if (attrlen > 0) {
+			struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
+
+			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
+			if (nla) {
+				nla_memcpy(&r_cfg.fc_gateway, nla, 16);
+				r_cfg.fc_flags |= RTF_GATEWAY;
+			}
+		}
+		err = ip6_route_del(&r_cfg);
+		if (err)
+			last_err = err;
+
 		rtnh = rtnh_next(rtnh, &remaining);
 	}
 
@@ -2565,7 +2714,7 @@ static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh)
 		return err;
 
 	if (cfg.fc_mp)
-		return ip6_route_multipath(&cfg, 0);
+		return ip6_route_multipath_del(&cfg);
 	else
 		return ip6_route_del(&cfg);
 }
@@ -2580,7 +2729,7 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh)
 		return err;
 
 	if (cfg.fc_mp)
-		return ip6_route_multipath(&cfg, 1);
+		return ip6_route_multipath_add(&cfg);
 	else
 		return ip6_route_add(&cfg);
 }
-- 
2.1.0


From 9ebe12001cb76d9b47fe0fab691980fe8e1e7c25 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 8 Sep 2015 20:06:41 -0700
Subject: [PATCH 12/28] net: dsa: bcm_sf2: Fix 64-bits register writes

[ Upstream commit 03679a14739a0d4c14b52ba65a69ff553bfba73b ]

The macro to write 64-bits quantities to the 32-bits register swapped
the value and offsets arguments, we want to preserve the ordering of the
arguments with respect to how writel() is implemented for instance:
value first, offset/base second.

Fixes: 246d7f773c13 ("net: dsa: add Broadcom SF2 switch driver")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/bcm_sf2.h b/drivers/net/dsa/bcm_sf2.h
index 22e2ebf..789d7b7 100644
--- a/drivers/net/dsa/bcm_sf2.h
+++ b/drivers/net/dsa/bcm_sf2.h
@@ -112,8 +112,8 @@ static inline u64 name##_readq(struct bcm_sf2_priv *priv, u32 off)	\
 	spin_unlock(&priv->indir_lock);					\
 	return (u64)indir << 32 | dir;					\
 }									\
-static inline void name##_writeq(struct bcm_sf2_priv *priv, u32 off,	\
-							u64 val)	\
+static inline void name##_writeq(struct bcm_sf2_priv *priv, u64 val,	\
+							u32 off)	\
 {									\
 	spin_lock(&priv->indir_lock);					\
 	reg_writel(priv, upper_32_bits(val), REG_DIR_DATA_WRITE);	\
-- 
2.1.0


From 3179751dd88c387d12fe607b111fde3f3ecf5a02 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 10 Sep 2015 20:05:46 +0200
Subject: [PATCH 13/28] netlink, mmap: transform mmap skb into full skb on taps

[ Upstream commit 1853c949646005b5959c483becde86608f548f24 ]

Ken-ichirou reported that running netlink in mmap mode for receive in
combination with nlmon will throw a NULL pointer dereference in
__kfree_skb() on nlmon_xmit(), in my case I can also trigger an "unable
to handle kernel paging request". The problem is the skb_clone() in
__netlink_deliver_tap_skb() for skbs that are mmaped.

I.e. the cloned skb doesn't have a destructor, whereas the mmap netlink
skb has it pointed to netlink_skb_destructor(), set in the handler
netlink_ring_setup_skb(). There, skb->head is being set to NULL, so
that in such cases, __kfree_skb() doesn't perform a skb_release_data()
via skb_release_all(), where skb->head is possibly being freed through
kfree(head) into slab allocator, although netlink mmap skb->head points
to the mmap buffer. Similarly, the same has to be done also for large
netlink skbs where the data area is vmalloced. Therefore, as discussed,
make a copy for these rather rare cases for now. This fixes the issue
on my and Ken-ichirou's test-cases.

Reference: http://thread.gmane.org/gmane.linux.network/371129
Fixes: bcbde0d449ed ("net: netlink: virtual tap device management")
Reported-by: Ken-ichirou MATSUZAWA <chamaken@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Ken-ichirou MATSUZAWA <chamaken@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 30 +++++++++++++++++++++++-------
 net/netlink/af_netlink.h |  9 +++++++++
 2 files changed, 32 insertions(+), 7 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index bf6e766..ca08ffb 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -123,6 +123,24 @@ static inline u32 netlink_group_mask(u32 group)
 	return group ? 1 << (group - 1) : 0;
 }
 
+static struct sk_buff *netlink_to_full_skb(const struct sk_buff *skb,
+					   gfp_t gfp_mask)
+{
+	unsigned int len = skb_end_offset(skb);
+	struct sk_buff *new;
+
+	new = alloc_skb(len, gfp_mask);
+	if (new == NULL)
+		return NULL;
+
+	NETLINK_CB(new).portid = NETLINK_CB(skb).portid;
+	NETLINK_CB(new).dst_group = NETLINK_CB(skb).dst_group;
+	NETLINK_CB(new).creds = NETLINK_CB(skb).creds;
+
+	memcpy(skb_put(new, len), skb->data, len);
+	return new;
+}
+
 int netlink_add_tap(struct netlink_tap *nt)
 {
 	if (unlikely(nt->dev->type != ARPHRD_NETLINK))
@@ -204,7 +222,11 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb,
 	int ret = -ENOMEM;
 
 	dev_hold(dev);
-	nskb = skb_clone(skb, GFP_ATOMIC);
+
+	if (netlink_skb_is_mmaped(skb) || is_vmalloc_addr(skb->head))
+		nskb = netlink_to_full_skb(skb, GFP_ATOMIC);
+	else
+		nskb = skb_clone(skb, GFP_ATOMIC);
 	if (nskb) {
 		nskb->dev = dev;
 		nskb->protocol = htons((u16) sk->sk_protocol);
@@ -276,11 +298,6 @@ static void netlink_rcv_wake(struct sock *sk)
 }
 
 #ifdef CONFIG_NETLINK_MMAP
-static bool netlink_skb_is_mmaped(const struct sk_buff *skb)
-{
-	return NETLINK_CB(skb).flags & NETLINK_SKB_MMAPED;
-}
-
 static bool netlink_rx_is_mmaped(struct sock *sk)
 {
 	return nlk_sk(sk)->rx_ring.pg_vec != NULL;
@@ -817,7 +834,6 @@ static void netlink_ring_set_copied(struct sock *sk, struct sk_buff *skb)
 }
 
 #else /* CONFIG_NETLINK_MMAP */
-#define netlink_skb_is_mmaped(skb)	false
 #define netlink_rx_is_mmaped(sk)	false
 #define netlink_tx_is_mmaped(sk)	false
 #define netlink_mmap			sock_no_mmap
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index 8900840..df9a060 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -59,6 +59,15 @@ static inline struct netlink_sock *nlk_sk(struct sock *sk)
 	return container_of(sk, struct netlink_sock, sk);
 }
 
+static inline bool netlink_skb_is_mmaped(const struct sk_buff *skb)
+{
+#ifdef CONFIG_NETLINK_MMAP
+	return NETLINK_CB(skb).flags & NETLINK_SKB_MMAPED;
+#else
+	return false;
+#endif /* CONFIG_NETLINK_MMAP */
+}
+
 struct netlink_table {
 	struct rhashtable	hash;
 	struct hlist_head	mc_list;
-- 
2.1.0


From 8d895660866bca3fd683e2cdc331b651f855f6d2 Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Thu, 10 Sep 2015 17:31:15 -0300
Subject: [PATCH 14/28] sctp: fix race on protocol/netns initialization

[ Upstream commit 8e2d61e0aed2b7c4ecb35844fe07e0b2b762dee4 ]

Consider sctp module is unloaded and is being requested because an user
is creating a sctp socket.

During initialization, sctp will add the new protocol type and then
initialize pernet subsys:

        status = sctp_v4_protosw_init();
        if (status)
                goto err_protosw_init;

        status = sctp_v6_protosw_init();
        if (status)
                goto err_v6_protosw_init;

        status = register_pernet_subsys(&sctp_net_ops);

The problem is that after those calls to sctp_v{4,6}_protosw_init(), it
is possible for userspace to create SCTP sockets like if the module is
already fully loaded. If that happens, one of the possible effects is
that we will have readers for net->sctp.local_addr_list list earlier
than expected and sctp_net_init() does not take precautions while
dealing with that list, leading to a potential panic but not limited to
that, as sctp_sock_init() will copy a bunch of blank/partially
initialized values from net->sctp.

The race happens like this:

     CPU 0                           |  CPU 1
  socket()                           |
   __sock_create                     | socket()
    inet_create                      |  __sock_create
     list_for_each_entry_rcu(        |
        answer, &inetsw[sock->type], |
        list) {                      |   inet_create
      /* no hits */                  |
     if (unlikely(err)) {            |
      ...                            |
      request_module()               |
      /* socket creation is blocked  |
       * the module is fully loaded  |
       */                            |
       sctp_init                     |
        sctp_v4_protosw_init         |
         inet_register_protosw       |
          list_add_rcu(&p->list,     |
                       last_perm);   |
                                     |  list_for_each_entry_rcu(
                                     |     answer, &inetsw[sock->type],
        sctp_v6_protosw_init         |     list) {
                                     |     /* hit, so assumes protocol
                                     |      * is already loaded
                                     |      */
                                     |  /* socket creation continues
                                     |   * before netns is initialized
                                     |   */
        register_pernet_subsys       |

Simply inverting the initialization order between
register_pernet_subsys() and sctp_v4_protosw_init() is not possible
because register_pernet_subsys() will create a control sctp socket, so
the protocol must be already visible by then. Deferring the socket
creation to a work-queue is not good specially because we loose the
ability to handle its errors.

So, as suggested by Vlad, the fix is to split netns initialization in
two moments: defaults and control socket, so that the defaults are
already loaded by when we register the protocol, while control socket
initialization is kept at the same moment it is today.

Fixes: 4db67e808640 ("sctp: Make the address lists per network namespace")
Signed-off-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/protocol.c | 64 ++++++++++++++++++++++++++++++++++-------------------
 1 file changed, 41 insertions(+), 23 deletions(-)

diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 53b7acd..e13c3c3 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -1166,7 +1166,7 @@ static void sctp_v4_del_protocol(void)
 	unregister_inetaddr_notifier(&sctp_inetaddr_notifier);
 }
 
-static int __net_init sctp_net_init(struct net *net)
+static int __net_init sctp_defaults_init(struct net *net)
 {
 	int status;
 
@@ -1259,12 +1259,6 @@ static int __net_init sctp_net_init(struct net *net)
 
 	sctp_dbg_objcnt_init(net);
 
-	/* Initialize the control inode/socket for handling OOTB packets.  */
-	if ((status = sctp_ctl_sock_init(net))) {
-		pr_err("Failed to initialize the SCTP control sock\n");
-		goto err_ctl_sock_init;
-	}
-
 	/* Initialize the local address list. */
 	INIT_LIST_HEAD(&net->sctp.local_addr_list);
 	spin_lock_init(&net->sctp.local_addr_lock);
@@ -1280,9 +1274,6 @@ static int __net_init sctp_net_init(struct net *net)
 
 	return 0;
 
-err_ctl_sock_init:
-	sctp_dbg_objcnt_exit(net);
-	sctp_proc_exit(net);
 err_init_proc:
 	cleanup_sctp_mibs(net);
 err_init_mibs:
@@ -1291,15 +1282,12 @@ err_sysctl_register:
 	return status;
 }
 
-static void __net_exit sctp_net_exit(struct net *net)
+static void __net_exit sctp_defaults_exit(struct net *net)
 {
 	/* Free the local address list */
 	sctp_free_addr_wq(net);
 	sctp_free_local_addr_list(net);
 
-	/* Free the control endpoint.  */
-	inet_ctl_sock_destroy(net->sctp.ctl_sock);
-
 	sctp_dbg_objcnt_exit(net);
 
 	sctp_proc_exit(net);
@@ -1307,9 +1295,32 @@ static void __net_exit sctp_net_exit(struct net *net)
 	sctp_sysctl_net_unregister(net);
 }
 
-static struct pernet_operations sctp_net_ops = {
-	.init = sctp_net_init,
-	.exit = sctp_net_exit,
+static struct pernet_operations sctp_defaults_ops = {
+	.init = sctp_defaults_init,
+	.exit = sctp_defaults_exit,
+};
+
+static int __net_init sctp_ctrlsock_init(struct net *net)
+{
+	int status;
+
+	/* Initialize the control inode/socket for handling OOTB packets.  */
+	status = sctp_ctl_sock_init(net);
+	if (status)
+		pr_err("Failed to initialize the SCTP control sock\n");
+
+	return status;
+}
+
+static void __net_init sctp_ctrlsock_exit(struct net *net)
+{
+	/* Free the control endpoint.  */
+	inet_ctl_sock_destroy(net->sctp.ctl_sock);
+}
+
+static struct pernet_operations sctp_ctrlsock_ops = {
+	.init = sctp_ctrlsock_init,
+	.exit = sctp_ctrlsock_exit,
 };
 
 /* Initialize the universe into something sensible.  */
@@ -1442,8 +1453,11 @@ static __init int sctp_init(void)
 	sctp_v4_pf_init();
 	sctp_v6_pf_init();
 
-	status = sctp_v4_protosw_init();
+	status = register_pernet_subsys(&sctp_defaults_ops);
+	if (status)
+		goto err_register_defaults;
 
+	status = sctp_v4_protosw_init();
 	if (status)
 		goto err_protosw_init;
 
@@ -1451,9 +1465,9 @@ static __init int sctp_init(void)
 	if (status)
 		goto err_v6_protosw_init;
 
-	status = register_pernet_subsys(&sctp_net_ops);
+	status = register_pernet_subsys(&sctp_ctrlsock_ops);
 	if (status)
-		goto err_register_pernet_subsys;
+		goto err_register_ctrlsock;
 
 	status = sctp_v4_add_protocol();
 	if (status)
@@ -1469,12 +1483,14 @@ out:
 err_v6_add_protocol:
 	sctp_v4_del_protocol();
 err_add_protocol:
-	unregister_pernet_subsys(&sctp_net_ops);
-err_register_pernet_subsys:
+	unregister_pernet_subsys(&sctp_ctrlsock_ops);
+err_register_ctrlsock:
 	sctp_v6_protosw_exit();
 err_v6_protosw_init:
 	sctp_v4_protosw_exit();
 err_protosw_init:
+	unregister_pernet_subsys(&sctp_defaults_ops);
+err_register_defaults:
 	sctp_v4_pf_exit();
 	sctp_v6_pf_exit();
 	sctp_sysctl_unregister();
@@ -1507,12 +1523,14 @@ static __exit void sctp_exit(void)
 	sctp_v6_del_protocol();
 	sctp_v4_del_protocol();
 
-	unregister_pernet_subsys(&sctp_net_ops);
+	unregister_pernet_subsys(&sctp_ctrlsock_ops);
 
 	/* Free protosw registrations */
 	sctp_v6_protosw_exit();
 	sctp_v4_protosw_exit();
 
+	unregister_pernet_subsys(&sctp_defaults_ops);
+
 	/* Unregister with socket layer. */
 	sctp_v6_pf_exit();
 	sctp_v4_pf_exit();
-- 
2.1.0


From 902fd2280ee30d1be55739643704d79d8c92b1ac Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Linus=20L=C3=BCssing?= <linus.luessing@c0d3.blue>
Date: Fri, 11 Sep 2015 18:39:48 +0200
Subject: [PATCH 15/28] bridge: fix igmpv3 / mldv2 report parsing
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit c2d4fbd2163e607915cc05798ce7fb7f31117cc1 ]

With the newly introduced helper functions the skb pulling is hidden in
the checksumming function - and undone before returning to the caller.

The IGMPv3 and MLDv2 report parsing functions in the bridge still
assumed that the skb is pointing to the beginning of the IGMP/MLD
message while it is now kept at the beginning of the IPv4/6 header,
breaking the message parsing and creating packet loss.

Fixing this by taking the offset between IP and IGMP/MLD header into
account, too.

Fixes: 9afd85c9e455 ("net: Export IGMP/MLD message validation code")
Reported-by: Tobias Powalowski <tobias.powalowski@googlemail.com>
Tested-by: Tobias Powalowski <tobias.powalowski@googlemail.com>
Signed-off-by: Linus Lüssing <linus.luessing@c0d3.blue>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index ff667e1..9ba383f 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -980,7 +980,7 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br,
 
 	ih = igmpv3_report_hdr(skb);
 	num = ntohs(ih->ngrec);
-	len = sizeof(*ih);
+	len = skb_transport_offset(skb) + sizeof(*ih);
 
 	for (i = 0; i < num; i++) {
 		len += sizeof(*grec);
@@ -1035,7 +1035,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br,
 
 	icmp6h = icmp6_hdr(skb);
 	num = ntohs(icmp6h->icmp6_dataun.un_data16[1]);
-	len = sizeof(*icmp6h);
+	len = skb_transport_offset(skb) + sizeof(*icmp6h);
 
 	for (i = 0; i < num; i++) {
 		__be16 *nsrcs, _nsrcs;
-- 
2.1.0


From 3b10baa848d5421e7300e629dd1d47dc5d5cf7e5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 15 Sep 2015 18:29:47 -0700
Subject: [PATCH 16/28] net/mlx4_en: really allow to change RSS key

[ Upsteam commit 4671fc6d47e0a0108fe24a4d830347d6a6ef4aa7 ]

When changing rss key, we do not want to overwrite user provided key
by the one provided by netdev_rss_key_fill(), which is the host random
key generated at boot time.

Fixes: 947cbb0ac242 ("net/mlx4_en: Support for configurable RSS hash function")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Eyal Perry <eyalpe@mellanox.com>
CC: Amir Vadai <amirv@mellanox.com>
Acked-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_rx.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index eab4e08..80aac20 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -1256,8 +1256,6 @@ int mlx4_en_config_rss_steer(struct mlx4_en_priv *priv)
 		rss_context->hash_fn = MLX4_RSS_HASH_TOP;
 		memcpy(rss_context->rss_key, priv->rss_key,
 		       MLX4_EN_RSS_KEY_SIZE);
-		netdev_rss_key_fill(rss_context->rss_key,
-				    MLX4_EN_RSS_KEY_SIZE);
 	} else {
 		en_err(priv, "Unknown RSS hash function requested\n");
 		err = -EINVAL;
-- 
2.1.0


From 550e098bd3241e02a60ee1d513e01dfa58a2cd16 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Fri, 18 Sep 2015 13:41:09 +0300
Subject: [PATCH 17/28] macvtap: fix TUNSETSNDBUF values > 64k

[ Upstream commit 3ea79249e81e5ed051f2e6480cbde896d99046e8 ]

Upon TUNSETSNDBUF,  macvtap reads the requested sndbuf size into
a local variable u.
commit 39ec7de7092b ("macvtap: fix uninitialized access on
TUNSETIFF") changed its type to u16 (which is the right thing to
do for all other macvtap ioctls), breaking all values > 64k.

The value of TUNSETSNDBUF is actually a signed 32 bit integer, so
the right thing to do is to read it into an int.

Cc: David S. Miller <davem@davemloft.net>
Fixes: 39ec7de7092b ("macvtap: fix uninitialized access on TUNSETIFF")
Reported-by: Mark A. Peloquin
Bisected-by: Matthew Rosato <mjrosato@linux.vnet.ibm.com>
Reported-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by:  Matthew Rosato <mjrosato@linux.vnet.ibm.com>
Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macvtap.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 8c350c5..58858c5 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -1054,10 +1054,10 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd,
 		return 0;
 
 	case TUNSETSNDBUF:
-		if (get_user(u, up))
+		if (get_user(s, sp))
 			return -EFAULT;
 
-		q->sk.sk_sndbuf = u;
+		q->sk.sk_sndbuf = s;
 		return 0;
 
 	case TUNGETVNETHDRSZ:
-- 
2.1.0


From b934f9581fe4db0923ee82f633ab8efab675e2e0 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Fri, 18 Sep 2015 19:16:50 +0800
Subject: [PATCH 18/28] netlink: Fix autobind race condition that leads to zero
 port ID

[ Upstream commit 1f770c0a09da855a2b51af6d19de97fb955eca85 ]

The commit c0bb07df7d981e4091432754e30c9c720e2c0c78 ("netlink:
Reset portid after netlink_insert failure") introduced a race
condition where if two threads try to autobind the same socket
one of them may end up with a zero port ID.  This led to kernel
deadlocks that were observed by multiple people.

This patch reverts that commit and instead fixes it by introducing
a separte rhash_portid variable so that the real portid is only set
after the socket has been successfully hashed.

Fixes: c0bb07df7d98 ("netlink: Reset portid after netlink_insert failure")
Reported-by: Tejun Heo <tj@kernel.org>
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 12 +++++++-----
 net/netlink/af_netlink.h |  1 +
 2 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index ca08ffb..7d20abe 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1002,7 +1002,7 @@ static inline int netlink_compare(struct rhashtable_compare_arg *arg,
 	const struct netlink_compare_arg *x = arg->key;
 	const struct netlink_sock *nlk = ptr;
 
-	return nlk->portid != x->portid ||
+	return nlk->rhash_portid != x->portid ||
 	       !net_eq(sock_net(&nlk->sk), read_pnet(&x->pnet));
 }
 
@@ -1028,7 +1028,7 @@ static int __netlink_insert(struct netlink_table *table, struct sock *sk)
 {
 	struct netlink_compare_arg arg;
 
-	netlink_compare_arg_init(&arg, sock_net(sk), nlk_sk(sk)->portid);
+	netlink_compare_arg_init(&arg, sock_net(sk), nlk_sk(sk)->rhash_portid);
 	return rhashtable_lookup_insert_key(&table->hash, &arg,
 					    &nlk_sk(sk)->node,
 					    netlink_rhashtable_params);
@@ -1090,17 +1090,19 @@ static int netlink_insert(struct sock *sk, u32 portid)
 	    unlikely(atomic_read(&table->hash.nelems) >= UINT_MAX))
 		goto err;
 
-	nlk_sk(sk)->portid = portid;
+	nlk_sk(sk)->rhash_portid = portid;
 	sock_hold(sk);
 
 	err = __netlink_insert(table, sk);
 	if (err) {
 		if (err == -EEXIST)
 			err = -EADDRINUSE;
-		nlk_sk(sk)->portid = 0;
 		sock_put(sk);
+		goto err;
 	}
 
+	nlk_sk(sk)->portid = portid;
+
 err:
 	release_sock(sk);
 	return err;
@@ -3147,7 +3149,7 @@ static inline u32 netlink_hash(const void *data, u32 len, u32 seed)
 	const struct netlink_sock *nlk = data;
 	struct netlink_compare_arg arg;
 
-	netlink_compare_arg_init(&arg, sock_net(&nlk->sk), nlk->portid);
+	netlink_compare_arg_init(&arg, sock_net(&nlk->sk), nlk->rhash_portid);
 	return jhash2((u32 *)&arg, netlink_compare_arg_len / sizeof(u32), seed);
 }
 
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index df9a060..80b2b75 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -25,6 +25,7 @@ struct netlink_ring {
 struct netlink_sock {
 	/* struct sock has to be the first member of netlink_sock */
 	struct sock		sk;
+	u32			rhash_portid;
 	u32			portid;
 	u32			dst_portid;
 	u32			dst_group;
-- 
2.1.0


From 403b09ea207341e05c877f101098f3667c232117 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Tue, 22 Sep 2015 11:38:56 +0800
Subject: [PATCH 19/28] netlink: Replace rhash_portid with bound

[ Upstream commit da314c9923fed553a007785a901fd395b7eb6c19 ]

On Mon, Sep 21, 2015 at 02:20:22PM -0400, Tejun Heo wrote:
>
> store_release and load_acquire are different from the usual memory
> barriers and can't be paired this way.  You have to pair store_release
> and load_acquire.  Besides, it isn't a particularly good idea to

OK I've decided to drop the acquire/release helpers as they don't
help us at all and simply pessimises the code by using full memory
barriers (on some architectures) where only a write or read barrier
is needed.

> depend on memory barriers embedded in other data structures like the
> above.  Here, especially, rhashtable_insert() would have write barrier
> *before* the entry is hashed not necessarily *after*, which means that
> in the above case, a socket which appears to have set bound to a
> reader might not visible when the reader tries to look up the socket
> on the hashtable.

But you are right we do need an explicit write barrier here to
ensure that the hashing is visible.

> There's no reason to be overly smart here.  This isn't a crazy hot
> path, write barriers tend to be very cheap, store_release more so.
> Please just do smp_store_release() and note what it's paired with.

It's not about being overly smart.  It's about actually understanding
what's going on with the code.  I've seen too many instances of
people simply sprinkling synchronisation primitives around without
any knowledge of what is happening underneath, which is just a recipe
for creating hard-to-debug races.

> > @@ -1539,7 +1546,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
> >  		}
> >  	}
> >
> > -	if (!nlk->portid) {
> > +	if (!nlk->bound) {
>
> I don't think you can skip load_acquire here just because this is the
> second deref of the variable.  That doesn't change anything.  Race
> condition could still happen between the first and second tests and
> skipping the second would lead to the same kind of bug.

The reason this one is OK is because we do not use nlk->portid or
try to get nlk from the hash table before we return to user-space.

However, there is a real bug here that none of these acquire/release
helpers discovered.  The two bound tests here used to be a single
one.  Now that they are separate it is entirely possible for another
thread to come in the middle and bind the socket.  So we need to
repeat the portid check in order to maintain consistency.

> > @@ -1587,7 +1594,7 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr,
> >  	    !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
> >  		return -EPERM;
> >
> > -	if (!nlk->portid)
> > +	if (!nlk->bound)
>
> Don't we need load_acquire here too?  Is this path holding a lock
> which makes that unnecessary?

Ditto.

---8<---
The commit 1f770c0a09da855a2b51af6d19de97fb955eca85 ("netlink:
Fix autobind race condition that leads to zero port ID") created
some new races that can occur due to inconcsistencies between the
two port IDs.

Tejun is right that a barrier is unavoidable.  Therefore I am
reverting to the original patch that used a boolean to indicate
that a user netlink socket has been bound.

Barriers have been added where necessary to ensure that a valid
portid and the hashed socket is visible.

I have also changed netlink_insert to only return EBUSY if the
socket is bound to a portid different to the requested one.  This
combined with only reading nlk->bound once in netlink_bind fixes
a race where two threads that bind the socket at the same time
with different port IDs may both succeed.

Fixes: 1f770c0a09da ("netlink: Fix autobind race condition that leads to zero port ID")
Reported-by: Tejun Heo <tj@kernel.org>
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Nacked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 39 ++++++++++++++++++++++++++++-----------
 net/netlink/af_netlink.h |  2 +-
 2 files changed, 29 insertions(+), 12 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 7d20abe..7d824ac 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1002,7 +1002,7 @@ static inline int netlink_compare(struct rhashtable_compare_arg *arg,
 	const struct netlink_compare_arg *x = arg->key;
 	const struct netlink_sock *nlk = ptr;
 
-	return nlk->rhash_portid != x->portid ||
+	return nlk->portid != x->portid ||
 	       !net_eq(sock_net(&nlk->sk), read_pnet(&x->pnet));
 }
 
@@ -1028,7 +1028,7 @@ static int __netlink_insert(struct netlink_table *table, struct sock *sk)
 {
 	struct netlink_compare_arg arg;
 
-	netlink_compare_arg_init(&arg, sock_net(sk), nlk_sk(sk)->rhash_portid);
+	netlink_compare_arg_init(&arg, sock_net(sk), nlk_sk(sk)->portid);
 	return rhashtable_lookup_insert_key(&table->hash, &arg,
 					    &nlk_sk(sk)->node,
 					    netlink_rhashtable_params);
@@ -1081,8 +1081,8 @@ static int netlink_insert(struct sock *sk, u32 portid)
 
 	lock_sock(sk);
 
-	err = -EBUSY;
-	if (nlk_sk(sk)->portid)
+	err = nlk_sk(sk)->portid == portid ? 0 : -EBUSY;
+	if (nlk_sk(sk)->bound)
 		goto err;
 
 	err = -ENOMEM;
@@ -1090,7 +1090,7 @@ static int netlink_insert(struct sock *sk, u32 portid)
 	    unlikely(atomic_read(&table->hash.nelems) >= UINT_MAX))
 		goto err;
 
-	nlk_sk(sk)->rhash_portid = portid;
+	nlk_sk(sk)->portid = portid;
 	sock_hold(sk);
 
 	err = __netlink_insert(table, sk);
@@ -1101,7 +1101,9 @@ static int netlink_insert(struct sock *sk, u32 portid)
 		goto err;
 	}
 
-	nlk_sk(sk)->portid = portid;
+	/* We need to ensure that the socket is hashed and visible. */
+	smp_wmb();
+	nlk_sk(sk)->bound = portid;
 
 err:
 	release_sock(sk);
@@ -1482,6 +1484,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 	struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr;
 	int err;
 	long unsigned int groups = nladdr->nl_groups;
+	bool bound;
 
 	if (addr_len < sizeof(struct sockaddr_nl))
 		return -EINVAL;
@@ -1498,9 +1501,14 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 			return err;
 	}
 
-	if (nlk->portid)
+	bound = nlk->bound;
+	if (bound) {
+		/* Ensure nlk->portid is up-to-date. */
+		smp_rmb();
+
 		if (nladdr->nl_pid != nlk->portid)
 			return -EINVAL;
+	}
 
 	if (nlk->netlink_bind && groups) {
 		int group;
@@ -1516,7 +1524,10 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 		}
 	}
 
-	if (!nlk->portid) {
+	/* No need for barriers here as we return to user-space without
+	 * using any of the bound attributes.
+	 */
+	if (!bound) {
 		err = nladdr->nl_pid ?
 			netlink_insert(sk, nladdr->nl_pid) :
 			netlink_autobind(sock);
@@ -1564,7 +1575,10 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr,
 	    !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
 		return -EPERM;
 
-	if (!nlk->portid)
+	/* No need for barriers here as we return to user-space without
+	 * using any of the bound attributes.
+	 */
+	if (!nlk->bound)
 		err = netlink_autobind(sock);
 
 	if (err == 0) {
@@ -2321,10 +2335,13 @@ static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 		dst_group = nlk->dst_group;
 	}
 
-	if (!nlk->portid) {
+	if (!nlk->bound) {
 		err = netlink_autobind(sock);
 		if (err)
 			goto out;
+	} else {
+		/* Ensure nlk is hashed and visible. */
+		smp_rmb();
 	}
 
 	/* It's a really convoluted way for userland to ask for mmaped
@@ -3149,7 +3166,7 @@ static inline u32 netlink_hash(const void *data, u32 len, u32 seed)
 	const struct netlink_sock *nlk = data;
 	struct netlink_compare_arg arg;
 
-	netlink_compare_arg_init(&arg, sock_net(&nlk->sk), nlk->rhash_portid);
+	netlink_compare_arg_init(&arg, sock_net(&nlk->sk), nlk->portid);
 	return jhash2((u32 *)&arg, netlink_compare_arg_len / sizeof(u32), seed);
 }
 
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index 80b2b75..14437d9 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -25,7 +25,6 @@ struct netlink_ring {
 struct netlink_sock {
 	/* struct sock has to be the first member of netlink_sock */
 	struct sock		sk;
-	u32			rhash_portid;
 	u32			portid;
 	u32			dst_portid;
 	u32			dst_group;
@@ -36,6 +35,7 @@ struct netlink_sock {
 	unsigned long		state;
 	size_t			max_recvmsg_len;
 	wait_queue_head_t	wait;
+	bool			bound;
 	bool			cb_running;
 	struct netlink_callback	cb;
 	struct mutex		*cb_mutex;
-- 
2.1.0


From 336f32fe105e34e610d5b7d46c147ba01d24fec9 Mon Sep 17 00:00:00 2001
From: Jesse Gross <jesse@nicira.com>
Date: Mon, 21 Sep 2015 20:21:20 -0700
Subject: [PATCH 20/28] openvswitch: Zero flows on allocation.

[ Upstream commit ae5f2fb1d51fa128a460bcfbe3c56d7ab8bf6a43 ]

When support for megaflows was introduced, OVS needed to start
installing flows with a mask applied to them. Since masking is an
expensive operation, OVS also had an optimization that would only
take the parts of the flow keys that were covered by a non-zero
mask. The values stored in the remaining pieces should not matter
because they are masked out.

While this works fine for the purposes of matching (which must always
look at the mask), serialization to netlink can be problematic. Since
the flow and the mask are serialized separately, the uninitialized
portions of the flow can be encoded with whatever values happen to be
present.

In terms of functionality, this has little effect since these fields
will be masked out by definition. However, it leaks kernel memory to
userspace, which is a potential security vulnerability. It is also
possible that other code paths could look at the masked key and get
uninitialized data, although this does not currently appear to be an
issue in practice.

This removes the mask optimization for flows that are being installed.
This was always intended to be the case as the mask optimizations were
really targetting per-packet flow operations.

Fixes: 03f0d916 ("openvswitch: Mega flow implementation")
Signed-off-by: Jesse Gross <jesse@nicira.com>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/datapath.c   |  4 ++--
 net/openvswitch/flow_table.c | 23 ++++++++++++-----------
 net/openvswitch/flow_table.h |  2 +-
 3 files changed, 15 insertions(+), 14 deletions(-)

diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 096c627..27e1496 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -906,7 +906,7 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	if (error)
 		goto err_kfree_flow;
 
-	ovs_flow_mask_key(&new_flow->key, &key, &mask);
+	ovs_flow_mask_key(&new_flow->key, &key, true, &mask);
 
 	/* Extract flow identifier. */
 	error = ovs_nla_get_identifier(&new_flow->id, a[OVS_FLOW_ATTR_UFID],
@@ -1033,7 +1033,7 @@ static struct sw_flow_actions *get_flow_actions(const struct nlattr *a,
 	struct sw_flow_key masked_key;
 	int error;
 
-	ovs_flow_mask_key(&masked_key, key, mask);
+	ovs_flow_mask_key(&masked_key, key, true, mask);
 	error = ovs_nla_copy_actions(a, &masked_key, &acts, log);
 	if (error) {
 		OVS_NLERR(log,
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index 4613df8..aa34951 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -56,20 +56,21 @@ static u16 range_n_bytes(const struct sw_flow_key_range *range)
 }
 
 void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
-		       const struct sw_flow_mask *mask)
+		       bool full, const struct sw_flow_mask *mask)
 {
-	const long *m = (const long *)((const u8 *)&mask->key +
-				mask->range.start);
-	const long *s = (const long *)((const u8 *)src +
-				mask->range.start);
-	long *d = (long *)((u8 *)dst + mask->range.start);
+	int start = full ? 0 : mask->range.start;
+	int len = full ? sizeof *dst : range_n_bytes(&mask->range);
+	const long *m = (const long *)((const u8 *)&mask->key + start);
+	const long *s = (const long *)((const u8 *)src + start);
+	long *d = (long *)((u8 *)dst + start);
 	int i;
 
-	/* The memory outside of the 'mask->range' are not set since
-	 * further operations on 'dst' only uses contents within
-	 * 'mask->range'.
+	/* If 'full' is true then all of 'dst' is fully initialized. Otherwise,
+	 * if 'full' is false the memory outside of the 'mask->range' is left
+	 * uninitialized. This can be used as an optimization when further
+	 * operations on 'dst' only use contents within 'mask->range'.
 	 */
-	for (i = 0; i < range_n_bytes(&mask->range); i += sizeof(long))
+	for (i = 0; i < len; i += sizeof(long))
 		*d++ = *s++ & *m++;
 }
 
@@ -473,7 +474,7 @@ static struct sw_flow *masked_flow_lookup(struct table_instance *ti,
 	u32 hash;
 	struct sw_flow_key masked_key;
 
-	ovs_flow_mask_key(&masked_key, unmasked, mask);
+	ovs_flow_mask_key(&masked_key, unmasked, false, mask);
 	hash = flow_hash(&masked_key, &mask->range);
 	head = find_bucket(ti, hash);
 	hlist_for_each_entry_rcu(flow, head, flow_table.node[ti->node_ver]) {
diff --git a/net/openvswitch/flow_table.h b/net/openvswitch/flow_table.h
index 616eda1..2dd9900 100644
--- a/net/openvswitch/flow_table.h
+++ b/net/openvswitch/flow_table.h
@@ -86,5 +86,5 @@ struct sw_flow *ovs_flow_tbl_lookup_ufid(struct flow_table *,
 bool ovs_flow_cmp(const struct sw_flow *, const struct sw_flow_match *);
 
 void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
-		       const struct sw_flow_mask *mask);
+		       bool full, const struct sw_flow_mask *mask);
 #endif /* flow_table.h */
-- 
2.1.0


From f702441c691d47fa63f69da6b69f041b2b6f3261 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 23 Sep 2015 14:00:21 -0700
Subject: [PATCH 21/28] tcp: add proper TS val into RST packets

[ Upstream commit 675ee231d960af2af3606b4480324e26797eb010 ]

RST packets sent on behalf of TCP connections with TS option (RFC 7323
TCP timestamps) have incorrect TS val (set to 0), but correct TS ecr.

A > B: Flags [S], seq 0, win 65535, options [mss 1000,nop,nop,TS val 100
ecr 0], length 0
B > A: Flags [S.], seq 2444755794, ack 1, win 28960, options [mss
1460,nop,nop,TS val 7264344 ecr 100], length 0
A > B: Flags [.], ack 1, win 65535, options [nop,nop,TS val 110 ecr
7264344], length 0

B > A: Flags [R.], seq 1, ack 1, win 28960, options [nop,nop,TS val 0
ecr 110], length 0

We need to call skb_mstamp_get() to get proper TS val,
derived from skb->skb_mstamp

Note that RFC 1323 was advocating to not send TS option in RST segment,
but RFC 7323 recommends the opposite :

  Once TSopt has been successfully negotiated, that is both <SYN> and
  <SYN,ACK> contain TSopt, the TSopt MUST be sent in every non-<RST>
  segment for the duration of the connection, and SHOULD be sent in an
  <RST> segment (see Section 5.2 for details)

Note this RFC recommends to send TS val = 0, but we believe it is
premature : We do not know if all TCP stacks are properly
handling the receive side :

   When an <RST> segment is
   received, it MUST NOT be subjected to the PAWS check by verifying an
   acceptable value in SEG.TSval, and information from the Timestamps
   option MUST NOT be used to update connection state information.
   SEG.TSecr MAY be used to provide stricter <RST> acceptance checks.

In 5 years, if/when all TCP stack are RFC 7323 ready, we might consider
to decide to send TS val = 0, if it buys something.

Fixes: 7faee5c0d514 ("tcp: remove TCP_SKB_CB(skb)->when")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index a369e8a..986440b 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2893,6 +2893,7 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority)
 	skb_reserve(skb, MAX_TCP_HEADER);
 	tcp_init_nondata_skb(skb, tcp_acceptable_seq(sk),
 			     TCPHDR_ACK | TCPHDR_RST);
+	skb_mstamp_get(&skb->skb_mstamp);
 	/* Send it off. */
 	if (tcp_transmit_skb(sk, skb, 0, priority))
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED);
-- 
2.1.0


From 8563bea6b79e1c25773944d6c5276cb8e72f2084 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Tue, 22 Sep 2015 17:01:11 -0700
Subject: [PATCH 22/28] net: revert "net_sched: move tp->root allocation into
 fw_init()"

[ Upstream commit d8aecb10115497f6cdf841df8c88ebb3ba25fa28 ]

fw filter uses tp->root==NULL to check if it is the old method,
so it doesn't need allocation at all in this case. This patch
reverts the offending commit and adds some comments for old
method to make it obvious.

Fixes: 33f8b9ecdb15 ("net_sched: move tp->root allocation into fw_init()")
Reported-by: Akshat Kakkar <akshat.1984@gmail.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_fw.c | 30 +++++++++++++++---------------
 1 file changed, 15 insertions(+), 15 deletions(-)

diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c
index 715e01e..f23a3b6 100644
--- a/net/sched/cls_fw.c
+++ b/net/sched/cls_fw.c
@@ -33,7 +33,6 @@
 
 struct fw_head {
 	u32			mask;
-	bool			mask_set;
 	struct fw_filter __rcu	*ht[HTSIZE];
 	struct rcu_head		rcu;
 };
@@ -84,7 +83,7 @@ static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 			}
 		}
 	} else {
-		/* old method */
+		/* Old method: classify the packet using its skb mark. */
 		if (id && (TC_H_MAJ(id) == 0 ||
 			   !(TC_H_MAJ(id ^ tp->q->handle)))) {
 			res->classid = id;
@@ -114,14 +113,9 @@ static unsigned long fw_get(struct tcf_proto *tp, u32 handle)
 
 static int fw_init(struct tcf_proto *tp)
 {
-	struct fw_head *head;
-
-	head = kzalloc(sizeof(struct fw_head), GFP_KERNEL);
-	if (head == NULL)
-		return -ENOBUFS;
-
-	head->mask_set = false;
-	rcu_assign_pointer(tp->root, head);
+	/* We don't allocate fw_head here, because in the old method
+	 * we don't need it at all.
+	 */
 	return 0;
 }
 
@@ -252,7 +246,7 @@ static int fw_change(struct net *net, struct sk_buff *in_skb,
 	int err;
 
 	if (!opt)
-		return handle ? -EINVAL : 0;
+		return handle ? -EINVAL : 0; /* Succeed if it is old method. */
 
 	err = nla_parse_nested(tb, TCA_FW_MAX, opt, fw_policy);
 	if (err < 0)
@@ -302,11 +296,17 @@ static int fw_change(struct net *net, struct sk_buff *in_skb,
 	if (!handle)
 		return -EINVAL;
 
-	if (!head->mask_set) {
-		head->mask = 0xFFFFFFFF;
+	if (!head) {
+		u32 mask = 0xFFFFFFFF;
 		if (tb[TCA_FW_MASK])
-			head->mask = nla_get_u32(tb[TCA_FW_MASK]);
-		head->mask_set = true;
+			mask = nla_get_u32(tb[TCA_FW_MASK]);
+
+		head = kzalloc(sizeof(*head), GFP_KERNEL);
+		if (!head)
+			return -ENOBUFS;
+		head->mask = mask;
+
+		rcu_assign_pointer(tp->root, head);
 	}
 
 	f = kzalloc(sizeof(struct fw_filter), GFP_KERNEL);
-- 
2.1.0


From 5d9dfb608531d4b95b8d000652d4ced4bd3adf41 Mon Sep 17 00:00:00 2001
From: Wilson Kok <wkok@cumulusnetworks.com>
Date: Tue, 22 Sep 2015 21:40:22 -0700
Subject: [PATCH 23/28] fib_rules: fix fib rule dumps across multiple skbs

[ Upstream commit 41fc014332d91ee90c32840bf161f9685b7fbf2b ]

dump_rules returns skb length and not error.
But when family == AF_UNSPEC, the caller of dump_rules
assumes that it returns an error. Hence, when family == AF_UNSPEC,
we continue trying to dump on -EMSGSIZE errors resulting in
incorrect dump idx carried between skbs belonging to the same dump.
This results in fib rule dump always only dumping rules that fit
into the first skb.

This patch fixes dump_rules to return error so that we exit correctly
and idx is correctly maintained between skbs that are part of the
same dump.

Signed-off-by: Wilson Kok <wkok@cumulusnetworks.com>
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/fib_rules.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 9a12668..0ad144f 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -615,15 +615,17 @@ static int dump_rules(struct sk_buff *skb, struct netlink_callback *cb,
 {
 	int idx = 0;
 	struct fib_rule *rule;
+	int err = 0;
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(rule, &ops->rules_list, list) {
 		if (idx < cb->args[1])
 			goto skip;
 
-		if (fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid,
-				     cb->nlh->nlmsg_seq, RTM_NEWRULE,
-				     NLM_F_MULTI, ops) < 0)
+		err = fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid,
+				       cb->nlh->nlmsg_seq, RTM_NEWRULE,
+				       NLM_F_MULTI, ops);
+		if (err)
 			break;
 skip:
 		idx++;
@@ -632,7 +634,7 @@ skip:
 	cb->args[1] = idx;
 	rules_ops_put(ops);
 
-	return skb->len;
+	return err;
 }
 
 static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb)
@@ -648,7 +650,9 @@ static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb)
 		if (ops == NULL)
 			return -EAFNOSUPPORT;
 
-		return dump_rules(skb, cb, ops);
+		dump_rules(skb, cb, ops);
+
+		return skb->len;
 	}
 
 	rcu_read_lock();
-- 
2.1.0


From a682bd590e9fe3284054df5cf5ca5f2e82065042 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Mon, 20 Jul 2015 17:49:55 -0700
Subject: [PATCH 24/28] net: dsa: bcm_sf2: Do not override speed settings

[ Upstream d2eac98f7d1b950b762a7eca05a9ce0ea1d878d2 in net-next tree,
  will be pushed to Linus very soon. ]

The SF2 driver currently overrides speed settings for its port
configured using a fixed PHY, this is both unnecessary and incorrect,
because we keep feedback to the hardware parameters that we read from
the PHY device, which in the case of a fixed PHY cannot possibly change
speed.

This is a required change to allow the fixed PHY code to allow
registering a PHY with a link configured as DOWN by default and avoid
some sort of circular dependency where we require the link_update
callback to run to program the hardware, and we then utilize the fixed
PHY parameters to program the hardware with the same settings.

Fixes: 246d7f773c13 ("net: dsa: add Broadcom SF2 switch driver")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2.c | 18 +-----------------
 1 file changed, 1 insertion(+), 17 deletions(-)

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index f24c4fe..db9ebbc 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -893,15 +893,11 @@ static void bcm_sf2_sw_fixed_link_update(struct dsa_switch *ds, int port,
 					 struct fixed_phy_status *status)
 {
 	struct bcm_sf2_priv *priv = ds_to_priv(ds);
-	u32 duplex, pause, speed;
+	u32 duplex, pause;
 	u32 reg;
 
 	duplex = core_readl(priv, CORE_DUPSTS);
 	pause = core_readl(priv, CORE_PAUSESTS);
-	speed = core_readl(priv, CORE_SPDSTS);
-
-	speed >>= (port * SPDSTS_SHIFT);
-	speed &= SPDSTS_MASK;
 
 	status->link = 0;
 
@@ -929,18 +925,6 @@ static void bcm_sf2_sw_fixed_link_update(struct dsa_switch *ds, int port,
 		reg &= ~LINK_STS;
 	core_writel(priv, reg, CORE_STS_OVERRIDE_GMIIP_PORT(port));
 
-	switch (speed) {
-	case SPDSTS_10:
-		status->speed = SPEED_10;
-		break;
-	case SPDSTS_100:
-		status->speed = SPEED_100;
-		break;
-	case SPDSTS_1000:
-		status->speed = SPEED_1000;
-		break;
-	}
-
 	if ((pause & (1 << port)) &&
 	    (pause & (1 << (port + PAUSESTS_TX_PAUSE_SHIFT)))) {
 		status->asym_pause = 1;
-- 
2.1.0


From 426e5e860e4d076992943ec7837c1234f7384a67 Mon Sep 17 00:00:00 2001
From: Stas Sergeev <stsp@list.ru>
Date: Mon, 20 Jul 2015 17:49:56 -0700
Subject: [PATCH 25/28] net: phy: fixed_phy: handle link-down case

[ Upstream 868a4215be9a6d80548ccb74763b883dc99d32a2 in net-next tree,
  will be pushed to Linus very soon. ]

fixed_phy_register() currently hardcodes the fixed PHY link to 1, and
expects to find a "speed" parameter to provide correct information
towards the fixed PHY consumer.

In a subsequent change, where we allow "managed" (e.g: (RS)GMII in-band
status auto-negotiation) fixed PHYs, none of these parameters can be
provided since they will be auto-negotiated, hence, we just provide a
zero-initialized fixed_phy_status to fixed_phy_register() which makes it
fail when we call fixed_phy_update_regs() since status.speed = 0 which
makes us hit the "default" label and error out.

Without this change, we would also see potentially inconsistent
speed/duplex parameters for fixed PHYs when the link is DOWN.

CC: netdev@vger.kernel.org
CC: linux-kernel@vger.kernel.org
Signed-off-by: Stas Sergeev <stsp@users.sourceforge.net>
[florian: add more background to why this is correct and desirable]
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/fixed_phy.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c
index 1960b46..479b93f 100644
--- a/drivers/net/phy/fixed_phy.c
+++ b/drivers/net/phy/fixed_phy.c
@@ -52,6 +52,10 @@ static int fixed_phy_update_regs(struct fixed_phy *fp)
 	u16 lpagb = 0;
 	u16 lpa = 0;
 
+	if (!fp->status.link)
+		goto done;
+	bmsr |= BMSR_LSTATUS | BMSR_ANEGCOMPLETE;
+
 	if (fp->status.duplex) {
 		bmcr |= BMCR_FULLDPLX;
 
@@ -96,15 +100,13 @@ static int fixed_phy_update_regs(struct fixed_phy *fp)
 		}
 	}
 
-	if (fp->status.link)
-		bmsr |= BMSR_LSTATUS | BMSR_ANEGCOMPLETE;
-
 	if (fp->status.pause)
 		lpa |= LPA_PAUSE_CAP;
 
 	if (fp->status.asym_pause)
 		lpa |= LPA_PAUSE_ASYM;
 
+done:
 	fp->regs[MII_PHYSID1] = 0;
 	fp->regs[MII_PHYSID2] = 0;
 
-- 
2.1.0


From a231920c27e977bd8f6ca5fc909b6de42f6ec5b3 Mon Sep 17 00:00:00 2001
From: Stas Sergeev <stsp@list.ru>
Date: Mon, 20 Jul 2015 17:49:57 -0700
Subject: [PATCH 26/28] of_mdio: add new DT property 'managed' to specify the
 PHY management type

[ Upstream commit 4cba5c2103657d43d0886e4cff8004d95a3d0def in net-next tree,
  will be pushed to Linus very soon. ]

Currently the PHY management type is selected by the MAC driver arbitrary.
The decision is based on the presence of the "fixed-link" node and on a
will of the driver's authors.
This caused a regression recently, when mvneta driver suddenly started
to use the in-band status for auto-negotiation on fixed links.
It appears the auto-negotiation may not work when expected by the MAC driver.
Sebastien Rannou explains:
<< Yes, I confirm that my HW does not generate an in-band status. AFAIK, it's
a PHY that aggregates 4xSGMIIs to 1xQSGMII ; the MAC side of the PHY (with
inband status) is connected to the switch through QSGMII, and in this context
we are on the media side of the PHY. >>
https://lkml.org/lkml/2015/7/10/206

This patch introduces the new string property 'managed' that allows
the user to set the management type explicitly.
The supported values are:
"auto" - default. Uses either MDIO or nothing, depending on the presence
of the fixed-link node
"in-band-status" - use in-band status

Signed-off-by: Stas Sergeev <stsp@users.sourceforge.net>

CC: Rob Herring <robh+dt@kernel.org>
CC: Pawel Moll <pawel.moll@arm.com>
CC: Mark Rutland <mark.rutland@arm.com>
CC: Ian Campbell <ijc+devicetree@hellion.org.uk>
CC: Kumar Gala <galak@codeaurora.org>
CC: Florian Fainelli <f.fainelli@gmail.com>
CC: Grant Likely <grant.likely@linaro.org>
CC: devicetree@vger.kernel.org
CC: linux-kernel@vger.kernel.org
CC: netdev@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/devicetree/bindings/net/ethernet.txt |  4 ++++
 drivers/of/of_mdio.c                               | 19 +++++++++++++++++--
 2 files changed, 21 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/ethernet.txt b/Documentation/devicetree/bindings/net/ethernet.txt
index 41b3f3f..5d88f37 100644
--- a/Documentation/devicetree/bindings/net/ethernet.txt
+++ b/Documentation/devicetree/bindings/net/ethernet.txt
@@ -25,7 +25,11 @@ The following properties are common to the Ethernet controllers:
   flow control thresholds.
 - tx-fifo-depth: the size of the controller's transmit fifo in bytes. This
   is used for components that can have configurable fifo sizes.
+- managed: string, specifies the PHY management type. Supported values are:
+  "auto", "in-band-status". "auto" is the default, it usess MDIO for
+  management if fixed-link is not specified.
 
 Child nodes of the Ethernet controller are typically the individual PHY devices
 connected via the MDIO bus (sometimes the MDIO bus controller is separate).
 They are described in the phy.txt file in this same directory.
+For non-MDIO PHY management see fixed-link.txt.
diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c
index 0c06448..bec8ec2 100644
--- a/drivers/of/of_mdio.c
+++ b/drivers/of/of_mdio.c
@@ -263,7 +263,8 @@ EXPORT_SYMBOL(of_phy_attach);
 bool of_phy_is_fixed_link(struct device_node *np)
 {
 	struct device_node *dn;
-	int len;
+	int len, err;
+	const char *managed;
 
 	/* New binding */
 	dn = of_get_child_by_name(np, "fixed-link");
@@ -272,6 +273,10 @@ bool of_phy_is_fixed_link(struct device_node *np)
 		return true;
 	}
 
+	err = of_property_read_string(np, "managed", &managed);
+	if (err == 0 && strcmp(managed, "auto") != 0)
+		return true;
+
 	/* Old binding */
 	if (of_get_property(np, "fixed-link", &len) &&
 	    len == (5 * sizeof(__be32)))
@@ -286,8 +291,18 @@ int of_phy_register_fixed_link(struct device_node *np)
 	struct fixed_phy_status status = {};
 	struct device_node *fixed_link_node;
 	const __be32 *fixed_link_prop;
-	int len;
+	int len, err;
 	struct phy_device *phy;
+	const char *managed;
+
+	err = of_property_read_string(np, "managed", &managed);
+	if (err == 0) {
+		if (strcmp(managed, "in-band-status") == 0) {
+			/* status is zeroed, namely its .link member */
+			phy = fixed_phy_register(PHY_POLL, &status, np);
+			return IS_ERR(phy) ? PTR_ERR(phy) : 0;
+		}
+	}
 
 	/* New binding */
 	fixed_link_node = of_get_child_by_name(np, "fixed-link");
-- 
2.1.0


From f2a50cea6256782e375a44ba02d39441307433ff Mon Sep 17 00:00:00 2001
From: Stas Sergeev <stsp@list.ru>
Date: Mon, 20 Jul 2015 17:49:58 -0700
Subject: [PATCH 27/28] mvneta: use inband status only when explicitly enabled

[ Upstream commit f8af8e6eb95093d5ce5ebcc52bd1929b0433e172 in net-next tree,
  will be pushed to Linus very soon. ]

The commit 898b2970e2c9 ("mvneta: implement SGMII-based in-band link state
signaling") implemented the link parameters auto-negotiation unconditionally.
Unfortunately it appears that some HW that implements SGMII protocol,
doesn't generate the inband status, so it is not possible to auto-negotiate
anything with such HW.

This patch enables the auto-negotiation only if explicitly requested with
the 'managed' DT property.

This patch fixes the following regression:
https://lkml.org/lkml/2015/7/8/865

Signed-off-by: Stas Sergeev <stsp@users.sourceforge.net>

CC: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
CC: netdev@vger.kernel.org
CC: linux-kernel@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 74d0389..4d608f0 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -3029,8 +3029,8 @@ static int mvneta_probe(struct platform_device *pdev)
 	const char *dt_mac_addr;
 	char hw_mac_addr[ETH_ALEN];
 	const char *mac_from;
+	const char *managed;
 	int phy_mode;
-	int fixed_phy = 0;
 	int err;
 
 	/* Our multiqueue support is not complete, so for now, only
@@ -3064,7 +3064,6 @@ static int mvneta_probe(struct platform_device *pdev)
 			dev_err(&pdev->dev, "cannot register fixed PHY\n");
 			goto err_free_irq;
 		}
-		fixed_phy = 1;
 
 		/* In the case of a fixed PHY, the DT node associated
 		 * to the PHY is the Ethernet MAC DT node.
@@ -3088,8 +3087,10 @@ static int mvneta_probe(struct platform_device *pdev)
 	pp = netdev_priv(dev);
 	pp->phy_node = phy_node;
 	pp->phy_interface = phy_mode;
-	pp->use_inband_status = (phy_mode == PHY_INTERFACE_MODE_SGMII) &&
-				fixed_phy;
+
+	err = of_property_read_string(dn, "managed", &managed);
+	pp->use_inband_status = (err == 0 &&
+				 strcmp(managed, "in-band-status") == 0);
 
 	pp->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(pp->clk)) {
-- 
2.1.0


From b5eae410ec845978d1cffab6eae27d7ab28c9fcf Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 7 Aug 2015 00:26:41 +0200
Subject: [PATCH 28/28] netlink: make sure -EBUSY won't escape from
 netlink_insert

[ Upstream commit 4e7c1330689e27556de407d3fdadc65ffff5eb12 ]

Linus reports the following deadlock on rtnl_mutex; triggered only
once so far (extract):

[12236.694209] NetworkManager  D 0000000000013b80     0  1047      1 0x00000000
[12236.694218]  ffff88003f902640 0000000000000000 ffffffff815d15a9 0000000000000018
[12236.694224]  ffff880119538000 ffff88003f902640 ffffffff81a8ff84 00000000ffffffff
[12236.694230]  ffffffff81a8ff88 ffff880119c47f00 ffffffff815d133a ffffffff81a8ff80
[12236.694235] Call Trace:
[12236.694250]  [<ffffffff815d15a9>] ? schedule_preempt_disabled+0x9/0x10
[12236.694257]  [<ffffffff815d133a>] ? schedule+0x2a/0x70
[12236.694263]  [<ffffffff815d15a9>] ? schedule_preempt_disabled+0x9/0x10
[12236.694271]  [<ffffffff815d2c3f>] ? __mutex_lock_slowpath+0x7f/0xf0
[12236.694280]  [<ffffffff815d2cc6>] ? mutex_lock+0x16/0x30
[12236.694291]  [<ffffffff814f1f90>] ? rtnetlink_rcv+0x10/0x30
[12236.694299]  [<ffffffff8150ce3b>] ? netlink_unicast+0xfb/0x180
[12236.694309]  [<ffffffff814f5ad3>] ? rtnl_getlink+0x113/0x190
[12236.694319]  [<ffffffff814f202a>] ? rtnetlink_rcv_msg+0x7a/0x210
[12236.694331]  [<ffffffff8124565c>] ? sock_has_perm+0x5c/0x70
[12236.694339]  [<ffffffff814f1fb0>] ? rtnetlink_rcv+0x30/0x30
[12236.694346]  [<ffffffff8150d62c>] ? netlink_rcv_skb+0x9c/0xc0
[12236.694354]  [<ffffffff814f1f9f>] ? rtnetlink_rcv+0x1f/0x30
[12236.694360]  [<ffffffff8150ce3b>] ? netlink_unicast+0xfb/0x180
[12236.694367]  [<ffffffff8150d344>] ? netlink_sendmsg+0x484/0x5d0
[12236.694376]  [<ffffffff810a236f>] ? __wake_up+0x2f/0x50
[12236.694387]  [<ffffffff814cad23>] ? sock_sendmsg+0x33/0x40
[12236.694396]  [<ffffffff814cb05e>] ? ___sys_sendmsg+0x22e/0x240
[12236.694405]  [<ffffffff814cab75>] ? ___sys_recvmsg+0x135/0x1a0
[12236.694415]  [<ffffffff811a9d12>] ? eventfd_write+0x82/0x210
[12236.694423]  [<ffffffff811a0f9e>] ? fsnotify+0x32e/0x4c0
[12236.694429]  [<ffffffff8108cb70>] ? wake_up_q+0x60/0x60
[12236.694434]  [<ffffffff814cba09>] ? __sys_sendmsg+0x39/0x70
[12236.694440]  [<ffffffff815d4797>] ? entry_SYSCALL_64_fastpath+0x12/0x6a

It seems so far plausible that the recursive call into rtnetlink_rcv()
looks suspicious. One way, where this could trigger is that the senders
NETLINK_CB(skb).portid was wrongly 0 (which is rtnetlink socket), so
the rtnl_getlink() request's answer would be sent to the kernel instead
to the actual user process, thus grabbing rtnl_mutex() twice.

One theory would be that netlink_autobind() triggered via netlink_sendmsg()
internally overwrites the -EBUSY error to 0, but where it is wrongly
originating from __netlink_insert() instead. That would reset the
socket's portid to 0, which is then filled into NETLINK_CB(skb).portid
later on. As commit d470e3b483dc ("[NETLINK]: Fix two socket hashing bugs.")
also puts it, -EBUSY should not be propagated from netlink_insert().

It looks like it's very unlikely to reproduce. We need to trigger the
rhashtable_insert_rehash() handler under a situation where rehashing
currently occurs (one /rare/ way would be to hit ht->elasticity limits
while not filled enough to expand the hashtable, but that would rather
require a specifically crafted bind() sequence with knowledge about
destination slots, seems unlikely). It probably makes sense to guard
__netlink_insert() in any case and remap that error. It was suggested
that EOVERFLOW might be better than an already overloaded ENOMEM.

Reference: http://thread.gmane.org/gmane.linux.network/372676
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 7d824ac..c87bcf9 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1095,6 +1095,11 @@ static int netlink_insert(struct sock *sk, u32 portid)
 
 	err = __netlink_insert(table, sk);
 	if (err) {
+		/* In case the hashtable backend returns with -EBUSY
+		 * from here, it must not escape to the caller.
+		 */
+		if (unlikely(err == -EBUSY))
+			err = -EOVERFLOW;
 		if (err == -EEXIST)
 			err = -EADDRINUSE;
 		sock_put(sk);
-- 
2.1.0


[-- Attachment #5: net_42.mbox --]
[-- Type: Application/Octet-Stream, Size: 97439 bytes --]

From 42f257d5d3dfb28aeb3bdaf1b885d428a9ab7284 Mon Sep 17 00:00:00 2001
From: Mark Salter <msalter@redhat.com>
Date: Tue, 1 Sep 2015 09:36:05 -0400
Subject: [PATCH 01/30] phylib: fix device deletion order in
 mdiobus_unregister()

[ Upstream commit b6c6aedcbcbacd7b0cb4b64ed5ac835bc1c60a03 ]

commit 8b63ec1837fa ("phylib: Make PHYs children of their MDIO bus, not
the bus' parent.") uncovered a problem in mdiobus_unregister() which
leads to this warning when I reboot an APM Mustang (arm64) platform:

  WARNING: CPU: 7 PID: 4239 at fs/sysfs/group.c:224 sysfs_remove_group+0xa0/0xa4()
  sysfs group fffffe0000e07a10 not found for kobject 'xgene-mii-eth0:03'
  ...
  CPU: 7 PID: 4239 Comm: reboot Tainted: G            E   4.2.0-0.18.el7.test15.aarch64 #1
  Hardware name: AppliedMicro Mustang/Mustang, BIOS 1.1.0 Aug 26 2015
  Call Trace:
  [<fffffe000009739c>] dump_backtrace+0x0/0x170
  [<fffffe000009752c>] show_stack+0x20/0x2c
  [<fffffe00007436f0>] dump_stack+0x78/0x9c
  [<fffffe00000c2cb4>] warn_slowpath_common+0xa0/0xd8
  [<fffffe00000c2d60>] warn_slowpath_fmt+0x74/0x88
  [<fffffe0000293d3c>] sysfs_remove_group+0x9c/0xa4
  [<fffffe00004a8bac>] dpm_sysfs_remove+0x5c/0x70
  [<fffffe000049b388>] device_del+0x44/0x208
  [<fffffe000049b578>] device_unregister+0x2c/0x7c
  [<fffffe000050dc68>] mdiobus_unregister+0x48/0x94
  [<fffffe000052afd0>] xgene_enet_mdio_remove+0x28/0x44
  [<fffffe000052d3f0>] xgene_enet_remove+0xd0/0xd8
  [<fffffe000052d424>] xgene_enet_shutdown+0x2c/0x3c
  [<fffffe00004a204c>] platform_drv_shutdown+0x24/0x40
  [<fffffe000049d4f4>] device_shutdown+0xf0/0x1b4
  [<fffffe00000e31ec>] kernel_restart_prepare+0x40/0x4c
  [<fffffe00000e32f8>] kernel_restart+0x1c/0x80
  [<fffffe00000e3670>] SyS_reboot+0x17c/0x250

The problem is that mdiobus_unregister() deletes the bus device before
unregistering the phy devices on the bus. This wasn't a problem before
because the phys were not children of the bus:

  /sys/devices/platform/APMC0D05:00/net/eth0/xgene-mii-eth0:03
  /sys/devices/platform/APMC0D05:00/net/eth0/xgene-mii-eth0

But now that they are:

  /sys/devices/platform/APMC0D05:00/net/eth0/xgene-mii-eth0/xgene-mii-eth0:03

when mdiobus_unregister deletes the bus device, the phy subdirs are
removed from sysfs also. So when the phys are unregistered afterward,
we get the warning. This patch changes the order so that phys are
unregistered before the bus device is deleted.

Fixes: 8b63ec1837fa ("phylib: Make PHYs children of their MDIO bus, not the bus' parent.")
Signed-off-by: Mark Salter <msalter@redhat.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Tested-by: Mark Langsdorf <mlangsdo@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mdio_bus.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index 46a14cb..02a4615 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -303,12 +303,12 @@ void mdiobus_unregister(struct mii_bus *bus)
 	BUG_ON(bus->state != MDIOBUS_REGISTERED);
 	bus->state = MDIOBUS_UNREGISTERED;
 
-	device_del(&bus->dev);
 	for (i = 0; i < PHY_MAX_ADDR; i++) {
 		if (bus->phy_map[i])
 			device_unregister(&bus->phy_map[i]->dev);
 		bus->phy_map[i] = NULL;
 	}
+	device_del(&bus->dev);
 }
 EXPORT_SYMBOL(mdiobus_unregister);
 
-- 
2.1.0


From 12fa777b0629951d79d36c3f5899a35eb91f828b Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 2 Sep 2015 14:00:36 +0200
Subject: [PATCH 02/30] sock, diag: fix panic in sock_diag_put_filterinfo

[ Upstream commit b382c08656000c12a146723a153b85b13a855b49 ]

diag socket's sock_diag_put_filterinfo() dumps classic BPF programs
upon request to user space (ss -0 -b). However, native eBPF programs
attached to sockets (SO_ATTACH_BPF) cannot be dumped with this method:

Their orig_prog is always NULL. However, sock_diag_put_filterinfo()
unconditionally tries to access its filter length resp. wants to copy
the filter insns from there. Internal cBPF to eBPF transformations
attached to sockets don't have this issue, as orig_prog state is kept.

It's currently only used by packet sockets. If we would want to add
native eBPF support in the future, this needs to be done through
a different attribute than PACKET_DIAG_FILTER to not confuse possible
user space disassemblers that work on diag data.

Fixes: 89aa075832b0 ("net: sock: allow eBPF programs to be attached to sockets")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock_diag.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index d79866c..817622f 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -90,6 +90,9 @@ int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk,
 		goto out;
 
 	fprog = filter->prog->orig_prog;
+	if (!fprog)
+		goto out;
+
 	flen = bpf_classic_proglen(fprog);
 
 	attr = nla_reserve(skb, attrtype, flen);
-- 
2.1.0


From 6f8f9135005900cd00365273df66da12130fa0bc Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 3 Sep 2015 00:29:07 +0200
Subject: [PATCH 03/30] ipv6: fix exthdrs offload registration in out_rt path

[ Upstream commit e41b0bedba0293b9e1e8d1e8ed553104b9693656 ]

We previously register IPPROTO_ROUTING offload under inet6_add_offload(),
but in error path, we try to unregister it with inet_del_offload(). This
doesn't seem correct, it should actually be inet6_del_offload(), also
ipv6_exthdrs_offload_exit() from that commit seems rather incorrect (it
also uses rthdr_offload twice), but it got removed entirely later on.

Fixes: 3336288a9fea ("ipv6: Switch to using new offload infrastructure.")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/exthdrs_offload.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/exthdrs_offload.c b/net/ipv6/exthdrs_offload.c
index 447a7fb..f5e2ba1 100644
--- a/net/ipv6/exthdrs_offload.c
+++ b/net/ipv6/exthdrs_offload.c
@@ -36,6 +36,6 @@ out:
 	return ret;
 
 out_rt:
-	inet_del_offload(&rthdr_offload, IPPROTO_ROUTING);
+	inet6_del_offload(&rthdr_offload, IPPROTO_ROUTING);
 	goto out;
 }
-- 
2.1.0


From 8bd68ca93e602c06d66eee5f7f87f36bcf8e74a8 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Wed, 2 Sep 2015 17:24:14 +0800
Subject: [PATCH 04/30] net: fec: clear receive interrupts before processing a
 packet

[ Upstream commit ed63f1dcd5788d36f942fbcce350742385e3e18c ]

The patch just to re-submit the patch "db3421c114cfa6326" because the
patch "4d494cdc92b3b9a0" remove the change.

Clear any pending receive interrupt before we process a pending packet.
This helps to avoid any spurious interrupts being raised after we have
fully cleaned the receive ring, while still allowing an interrupt to be
raised if we receive another packet.

The position of this is critical: we must do this prior to reading the
next packet status to avoid potentially dropping an interrupt when a
packet is still pending.

Acked-by: Fugang Duan <B38611@freescale.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index b349e6f..de63266d 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -1402,6 +1402,7 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
 		if ((status & BD_ENET_RX_LAST) == 0)
 			netdev_err(ndev, "rcv is not +last\n");
 
+		writel(FEC_ENET_RXF, fep->hwp + FEC_IEVENT);
 
 		/* Check for errors. */
 		if (status & (BD_ENET_RX_LG | BD_ENET_RX_SH | BD_ENET_RX_NO |
-- 
2.1.0


From f8b294e6c916632036f06ec27f5f8f50ffd025ac Mon Sep 17 00:00:00 2001
From: Atsushi Nemoto <nemoto@toshiba-tops.co.jp>
Date: Wed, 2 Sep 2015 17:49:29 +0900
Subject: [PATCH 05/30] net: eth: altera: fix napi poll_list corruption

[ Upstream commit 4548a697e4969d695047cebd6d9af5e2f6cc728e ]

tse_poll() calls __napi_complete() with irq enabled.  This leads napi
poll_list corruption and may stop all napi drivers working.
Use napi_complete() instead of __napi_complete().

Signed-off-by: Atsushi Nemoto <nemoto@toshiba-tops.co.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/altera/altera_tse_main.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c
index da48e66..8207877 100644
--- a/drivers/net/ethernet/altera/altera_tse_main.c
+++ b/drivers/net/ethernet/altera/altera_tse_main.c
@@ -511,8 +511,7 @@ static int tse_poll(struct napi_struct *napi, int budget)
 
 	if (rxcomplete < budget) {
 
-		napi_gro_flush(napi, false);
-		__napi_complete(napi);
+		napi_complete(napi);
 
 		netdev_dbg(priv->dev,
 			   "NAPI Complete, did %d packets with budget %d\n",
-- 
2.1.0


From 29e43d1c1ee9ed0292e2bf235fb6150984acc410 Mon Sep 17 00:00:00 2001
From: Richard Laing <richard.laing@alliedtelesis.co.nz>
Date: Thu, 3 Sep 2015 13:52:31 +1200
Subject: [PATCH 06/30] net/ipv6: Correct PIM6 mrt_lock handling

[ Upstream commit 25b4a44c19c83d98e8c0807a7ede07c1f28eab8b ]

In the IPv6 multicast routing code the mrt_lock was not being released
correctly in the MFC iterator, as a result adding or deleting a MIF would
cause a hang because the mrt_lock could not be acquired.

This fix is a copy of the code for the IPv4 case and ensures that the lock
is released correctly.

Signed-off-by: Richard Laing <richard.laing@alliedtelesis.co.nz>
Acked-by: Cong Wang <cwang@twopensource.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6mr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 74ceb73..5f36266 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -550,7 +550,7 @@ static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v)
 
 	if (it->cache == &mrt->mfc6_unres_queue)
 		spin_unlock_bh(&mfc_unres_lock);
-	else if (it->cache == mrt->mfc6_cache_array)
+	else if (it->cache == &mrt->mfc6_cache_array[it->ct])
 		read_unlock(&mrt_lock);
 }
 
-- 
2.1.0


From 8ef957156771e81b37d25a8227a2534414f28b5b Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Sat, 5 Sep 2015 13:07:27 -0700
Subject: [PATCH 07/30] net: dsa: bcm_sf2: Fix ageing conditions and operation

[ Upstream commit 39797a279d62972cd914ef580fdfacb13e508bf8 ]

The comparison check between cur_hw_state and hw_state is currently
invalid because cur_hw_state is right shifted by G_MISTP_SHIFT, while
hw_state is not, so we end-up comparing bits 2:0 with bits 7:5, which is
going to cause an additional aging to occur. Fix this by not shifting
cur_hw_state while reading it, but instead, mask the value with the
appropriately shitfted bitmask.

The other problem with the fast-ageing process is that we did not set
the EN_AGE_DYNAMIC bit to request the ageing to occur for dynamically
learned MAC addresses. Finally, write back 0 to the FAST_AGE_CTRL
register to avoid leaving spurious bits sets from one operation to the
other.

Fixes: 12f460f23423 ("net: dsa: bcm_sf2: add HW bridging support")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 079897b..691caea 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -418,7 +418,7 @@ static int bcm_sf2_sw_fast_age_port(struct dsa_switch  *ds, int port)
 	core_writel(priv, port, CORE_FAST_AGE_PORT);
 
 	reg = core_readl(priv, CORE_FAST_AGE_CTRL);
-	reg |= EN_AGE_PORT | FAST_AGE_STR_DONE;
+	reg |= EN_AGE_PORT | EN_AGE_DYNAMIC | FAST_AGE_STR_DONE;
 	core_writel(priv, reg, CORE_FAST_AGE_CTRL);
 
 	do {
@@ -432,6 +432,8 @@ static int bcm_sf2_sw_fast_age_port(struct dsa_switch  *ds, int port)
 	if (!timeout)
 		return -ETIMEDOUT;
 
+	core_writel(priv, 0, CORE_FAST_AGE_CTRL);
+
 	return 0;
 }
 
@@ -507,7 +509,7 @@ static int bcm_sf2_sw_br_set_stp_state(struct dsa_switch *ds, int port,
 	u32 reg;
 
 	reg = core_readl(priv, CORE_G_PCTL_PORT(port));
-	cur_hw_state = reg >> G_MISTP_STATE_SHIFT;
+	cur_hw_state = reg & (G_MISTP_STATE_MASK << G_MISTP_STATE_SHIFT);
 
 	switch (state) {
 	case BR_STATE_DISABLED:
@@ -531,10 +533,12 @@ static int bcm_sf2_sw_br_set_stp_state(struct dsa_switch *ds, int port,
 	}
 
 	/* Fast-age ARL entries if we are moving a port from Learning or
-	 * Forwarding state to Disabled, Blocking or Listening state
+	 * Forwarding (cur_hw_state) state to Disabled, Blocking or Listening
+	 * state (hw_state)
 	 */
 	if (cur_hw_state != hw_state) {
-		if (cur_hw_state & 4 && !(hw_state & 4)) {
+		if (cur_hw_state >= G_MISTP_LEARN_STATE &&
+		    hw_state <= G_MISTP_LISTEN_STATE) {
 			ret = bcm_sf2_sw_fast_age_port(ds, port);
 			if (ret) {
 				pr_err("%s: fast-ageing failed\n", __func__);
-- 
2.1.0


From e2a239cf73304bd8c7b3c71a91de8d6137bca80d Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Tue, 8 Sep 2015 10:53:04 -0700
Subject: [PATCH 08/30] ipv6: fix multipath route replace error recovery

[ Upstream commit 6b9ea5a64ed5eeb3f68f2e6fcce0ed1179801d1e ]

Problem:
The ecmp route replace support for ipv6 in the kernel, deletes the
existing ecmp route too early, ie when it installs the first nexthop.
If there is an error in installing the subsequent nexthops, its too late
to recover the already deleted existing route leaving the fib
in an inconsistent state.

This patch reduces the possibility of this by doing the following:
a) Changes the existing multipath route add code to a two stage process:
  build rt6_infos + insert them
	ip6_route_add rt6_info creation code is moved into
	ip6_route_info_create.
b) This ensures that most errors are caught during building rt6_infos
  and we fail early
c) Separates multipath add and del code. Because add needs the special
  two stage mode in a) and delete essentially does not care.
d) In any event if the code fails during inserting a route again, a
  warning is printed (This should be unlikely)

Before the patch:
$ip -6 route show
3000:1000:1000:1000::2 via fe80::202:ff:fe00:b dev swp49s0 metric 1024
3000:1000:1000:1000::2 via fe80::202:ff:fe00:d dev swp49s1 metric 1024
3000:1000:1000:1000::2 via fe80::202:ff:fe00:f dev swp49s2 metric 1024

/* Try replacing the route with a duplicate nexthop */
$ip -6 route change 3000:1000:1000:1000::2/128 nexthop via
fe80::202:ff:fe00:b dev swp49s0 nexthop via fe80::202:ff:fe00:d dev
swp49s1 nexthop via fe80::202:ff:fe00:d dev swp49s1
RTNETLINK answers: File exists

$ip -6 route show
/* previously added ecmp route 3000:1000:1000:1000::2 dissappears from
 * kernel */

After the patch:
$ip -6 route show
3000:1000:1000:1000::2 via fe80::202:ff:fe00:b dev swp49s0 metric 1024
3000:1000:1000:1000::2 via fe80::202:ff:fe00:d dev swp49s1 metric 1024
3000:1000:1000:1000::2 via fe80::202:ff:fe00:f dev swp49s2 metric 1024

/* Try replacing the route with a duplicate nexthop */
$ip -6 route change 3000:1000:1000:1000::2/128 nexthop via
fe80::202:ff:fe00:b dev swp49s0 nexthop via fe80::202:ff:fe00:d dev
swp49s1 nexthop via fe80::202:ff:fe00:d dev swp49s1
RTNETLINK answers: File exists

$ip -6 route show
3000:1000:1000:1000::2 via fe80::202:ff:fe00:b dev swp49s0 metric 1024
3000:1000:1000:1000::2 via fe80::202:ff:fe00:d dev swp49s1 metric 1024
3000:1000:1000:1000::2 via fe80::202:ff:fe00:f dev swp49s2 metric 1024

Fixes: 27596472473a ("ipv6: fix ECMP route replacement")
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Reviewed-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 201 ++++++++++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 175 insertions(+), 26 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index d155864..00b64d4 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1727,7 +1727,7 @@ static int ip6_convert_metrics(struct mx6_config *mxc,
 	return -EINVAL;
 }
 
-int ip6_route_add(struct fib6_config *cfg)
+int ip6_route_info_create(struct fib6_config *cfg, struct rt6_info **rt_ret)
 {
 	int err;
 	struct net *net = cfg->fc_nlinfo.nl_net;
@@ -1735,7 +1735,6 @@ int ip6_route_add(struct fib6_config *cfg)
 	struct net_device *dev = NULL;
 	struct inet6_dev *idev = NULL;
 	struct fib6_table *table;
-	struct mx6_config mxc = { .mx = NULL, };
 	int addr_type;
 
 	if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128)
@@ -1941,6 +1940,32 @@ install_route:
 
 	cfg->fc_nlinfo.nl_net = dev_net(dev);
 
+	*rt_ret = rt;
+
+	return 0;
+out:
+	if (dev)
+		dev_put(dev);
+	if (idev)
+		in6_dev_put(idev);
+	if (rt)
+		dst_free(&rt->dst);
+
+	*rt_ret = NULL;
+
+	return err;
+}
+
+int ip6_route_add(struct fib6_config *cfg)
+{
+	struct mx6_config mxc = { .mx = NULL, };
+	struct rt6_info *rt = NULL;
+	int err;
+
+	err = ip6_route_info_create(cfg, &rt);
+	if (err)
+		goto out;
+
 	err = ip6_convert_metrics(&mxc, cfg);
 	if (err)
 		goto out;
@@ -1948,14 +1973,12 @@ install_route:
 	err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, &mxc);
 
 	kfree(mxc.mx);
+
 	return err;
 out:
-	if (dev)
-		dev_put(dev);
-	if (idev)
-		in6_dev_put(idev);
 	if (rt)
 		dst_free(&rt->dst);
+
 	return err;
 }
 
@@ -2727,19 +2750,78 @@ errout:
 	return err;
 }
 
-static int ip6_route_multipath(struct fib6_config *cfg, int add)
+struct rt6_nh {
+	struct rt6_info *rt6_info;
+	struct fib6_config r_cfg;
+	struct mx6_config mxc;
+	struct list_head next;
+};
+
+static void ip6_print_replace_route_err(struct list_head *rt6_nh_list)
+{
+	struct rt6_nh *nh;
+
+	list_for_each_entry(nh, rt6_nh_list, next) {
+		pr_warn("IPV6: multipath route replace failed (check consistency of installed routes): %pI6 nexthop %pI6 ifi %d\n",
+		        &nh->r_cfg.fc_dst, &nh->r_cfg.fc_gateway,
+		        nh->r_cfg.fc_ifindex);
+	}
+}
+
+static int ip6_route_info_append(struct list_head *rt6_nh_list,
+				 struct rt6_info *rt, struct fib6_config *r_cfg)
+{
+	struct rt6_nh *nh;
+	struct rt6_info *rtnh;
+	int err = -EEXIST;
+
+	list_for_each_entry(nh, rt6_nh_list, next) {
+		/* check if rt6_info already exists */
+		rtnh = nh->rt6_info;
+
+		if (rtnh->dst.dev == rt->dst.dev &&
+		    rtnh->rt6i_idev == rt->rt6i_idev &&
+		    ipv6_addr_equal(&rtnh->rt6i_gateway,
+				    &rt->rt6i_gateway))
+			return err;
+	}
+
+	nh = kzalloc(sizeof(*nh), GFP_KERNEL);
+	if (!nh)
+		return -ENOMEM;
+	nh->rt6_info = rt;
+	err = ip6_convert_metrics(&nh->mxc, r_cfg);
+	if (err) {
+		kfree(nh);
+		return err;
+	}
+	memcpy(&nh->r_cfg, r_cfg, sizeof(*r_cfg));
+	list_add_tail(&nh->next, rt6_nh_list);
+
+	return 0;
+}
+
+static int ip6_route_multipath_add(struct fib6_config *cfg)
 {
 	struct fib6_config r_cfg;
 	struct rtnexthop *rtnh;
+	struct rt6_info *rt;
+	struct rt6_nh *err_nh;
+	struct rt6_nh *nh, *nh_safe;
 	int remaining;
 	int attrlen;
-	int err = 0, last_err = 0;
+	int err = 1;
+	int nhn = 0;
+	int replace = (cfg->fc_nlinfo.nlh &&
+		       (cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_REPLACE));
+	LIST_HEAD(rt6_nh_list);
 
 	remaining = cfg->fc_mp_len;
-beginning:
 	rtnh = (struct rtnexthop *)cfg->fc_mp;
 
-	/* Parse a Multipath Entry */
+	/* Parse a Multipath Entry and build a list (rt6_nh_list) of
+	 * rt6_info structs per nexthop
+	 */
 	while (rtnh_ok(rtnh, remaining)) {
 		memcpy(&r_cfg, cfg, sizeof(*cfg));
 		if (rtnh->rtnh_ifindex)
@@ -2755,22 +2837,32 @@ beginning:
 				r_cfg.fc_flags |= RTF_GATEWAY;
 			}
 		}
-		err = add ? ip6_route_add(&r_cfg) : ip6_route_del(&r_cfg);
+
+		err = ip6_route_info_create(&r_cfg, &rt);
+		if (err)
+			goto cleanup;
+
+		err = ip6_route_info_append(&rt6_nh_list, rt, &r_cfg);
 		if (err) {
-			last_err = err;
-			/* If we are trying to remove a route, do not stop the
-			 * loop when ip6_route_del() fails (because next hop is
-			 * already gone), we should try to remove all next hops.
-			 */
-			if (add) {
-				/* If add fails, we should try to delete all
-				 * next hops that have been already added.
-				 */
-				add = 0;
-				remaining = cfg->fc_mp_len - remaining;
-				goto beginning;
-			}
+			dst_free(&rt->dst);
+			goto cleanup;
+		}
+
+		rtnh = rtnh_next(rtnh, &remaining);
+	}
+
+	err_nh = NULL;
+	list_for_each_entry(nh, &rt6_nh_list, next) {
+		err = __ip6_ins_rt(nh->rt6_info, &cfg->fc_nlinfo, &nh->mxc);
+		/* nh->rt6_info is used or freed at this point, reset to NULL*/
+		nh->rt6_info = NULL;
+		if (err) {
+			if (replace && nhn)
+				ip6_print_replace_route_err(&rt6_nh_list);
+			err_nh = nh;
+			goto add_errout;
 		}
+
 		/* Because each route is added like a single route we remove
 		 * these flags after the first nexthop: if there is a collision,
 		 * we have already failed to add the first nexthop:
@@ -2780,6 +2872,63 @@ beginning:
 		 */
 		cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL |
 						     NLM_F_REPLACE);
+		nhn++;
+	}
+
+	goto cleanup;
+
+add_errout:
+	/* Delete routes that were already added */
+	list_for_each_entry(nh, &rt6_nh_list, next) {
+		if (err_nh == nh)
+			break;
+		ip6_route_del(&nh->r_cfg);
+	}
+
+cleanup:
+	list_for_each_entry_safe(nh, nh_safe, &rt6_nh_list, next) {
+		if (nh->rt6_info)
+			dst_free(&nh->rt6_info->dst);
+		if (nh->mxc.mx)
+			kfree(nh->mxc.mx);
+		list_del(&nh->next);
+		kfree(nh);
+	}
+
+	return err;
+}
+
+static int ip6_route_multipath_del(struct fib6_config *cfg)
+{
+	struct fib6_config r_cfg;
+	struct rtnexthop *rtnh;
+	int remaining;
+	int attrlen;
+	int err = 1, last_err = 0;
+
+	remaining = cfg->fc_mp_len;
+	rtnh = (struct rtnexthop *)cfg->fc_mp;
+
+	/* Parse a Multipath Entry */
+	while (rtnh_ok(rtnh, remaining)) {
+		memcpy(&r_cfg, cfg, sizeof(*cfg));
+		if (rtnh->rtnh_ifindex)
+			r_cfg.fc_ifindex = rtnh->rtnh_ifindex;
+
+		attrlen = rtnh_attrlen(rtnh);
+		if (attrlen > 0) {
+			struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
+
+			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
+			if (nla) {
+				nla_memcpy(&r_cfg.fc_gateway, nla, 16);
+				r_cfg.fc_flags |= RTF_GATEWAY;
+			}
+		}
+		err = ip6_route_del(&r_cfg);
+		if (err)
+			last_err = err;
+
 		rtnh = rtnh_next(rtnh, &remaining);
 	}
 
@@ -2796,7 +2945,7 @@ static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh)
 		return err;
 
 	if (cfg.fc_mp)
-		return ip6_route_multipath(&cfg, 0);
+		return ip6_route_multipath_del(&cfg);
 	else
 		return ip6_route_del(&cfg);
 }
@@ -2811,7 +2960,7 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh)
 		return err;
 
 	if (cfg.fc_mp)
-		return ip6_route_multipath(&cfg, 1);
+		return ip6_route_multipath_add(&cfg);
 	else
 		return ip6_route_add(&cfg);
 }
-- 
2.1.0


From fc01b1b13b865133352c866fbed764f4f619fa98 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 8 Sep 2015 20:06:41 -0700
Subject: [PATCH 09/30] net: dsa: bcm_sf2: Fix 64-bits register writes

[ Upstream commit 03679a14739a0d4c14b52ba65a69ff553bfba73b ]

The macro to write 64-bits quantities to the 32-bits register swapped
the value and offsets arguments, we want to preserve the ordering of the
arguments with respect to how writel() is implemented for instance:
value first, offset/base second.

Fixes: 246d7f773c13 ("net: dsa: add Broadcom SF2 switch driver")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/bcm_sf2.h b/drivers/net/dsa/bcm_sf2.h
index 22e2ebf..789d7b7 100644
--- a/drivers/net/dsa/bcm_sf2.h
+++ b/drivers/net/dsa/bcm_sf2.h
@@ -112,8 +112,8 @@ static inline u64 name##_readq(struct bcm_sf2_priv *priv, u32 off)	\
 	spin_unlock(&priv->indir_lock);					\
 	return (u64)indir << 32 | dir;					\
 }									\
-static inline void name##_writeq(struct bcm_sf2_priv *priv, u32 off,	\
-							u64 val)	\
+static inline void name##_writeq(struct bcm_sf2_priv *priv, u64 val,	\
+							u32 off)	\
 {									\
 	spin_lock(&priv->indir_lock);					\
 	reg_writel(priv, upper_32_bits(val), REG_DIR_DATA_WRITE);	\
-- 
2.1.0


From b92b169ab9398c5be10a41ab908ff9ecee1c9457 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 10 Sep 2015 20:05:46 +0200
Subject: [PATCH 10/30] netlink, mmap: transform mmap skb into full skb on taps

[ Upstream commit 1853c949646005b5959c483becde86608f548f24 ]

Ken-ichirou reported that running netlink in mmap mode for receive in
combination with nlmon will throw a NULL pointer dereference in
__kfree_skb() on nlmon_xmit(), in my case I can also trigger an "unable
to handle kernel paging request". The problem is the skb_clone() in
__netlink_deliver_tap_skb() for skbs that are mmaped.

I.e. the cloned skb doesn't have a destructor, whereas the mmap netlink
skb has it pointed to netlink_skb_destructor(), set in the handler
netlink_ring_setup_skb(). There, skb->head is being set to NULL, so
that in such cases, __kfree_skb() doesn't perform a skb_release_data()
via skb_release_all(), where skb->head is possibly being freed through
kfree(head) into slab allocator, although netlink mmap skb->head points
to the mmap buffer. Similarly, the same has to be done also for large
netlink skbs where the data area is vmalloced. Therefore, as discussed,
make a copy for these rather rare cases for now. This fixes the issue
on my and Ken-ichirou's test-cases.

Reference: http://thread.gmane.org/gmane.linux.network/371129
Fixes: bcbde0d449ed ("net: netlink: virtual tap device management")
Reported-by: Ken-ichirou MATSUZAWA <chamaken@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Ken-ichirou MATSUZAWA <chamaken@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 30 +++++++++++++++++++++++-------
 net/netlink/af_netlink.h |  9 +++++++++
 2 files changed, 32 insertions(+), 7 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index a774985..bbd5d43 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -124,6 +124,24 @@ static inline u32 netlink_group_mask(u32 group)
 	return group ? 1 << (group - 1) : 0;
 }
 
+static struct sk_buff *netlink_to_full_skb(const struct sk_buff *skb,
+					   gfp_t gfp_mask)
+{
+	unsigned int len = skb_end_offset(skb);
+	struct sk_buff *new;
+
+	new = alloc_skb(len, gfp_mask);
+	if (new == NULL)
+		return NULL;
+
+	NETLINK_CB(new).portid = NETLINK_CB(skb).portid;
+	NETLINK_CB(new).dst_group = NETLINK_CB(skb).dst_group;
+	NETLINK_CB(new).creds = NETLINK_CB(skb).creds;
+
+	memcpy(skb_put(new, len), skb->data, len);
+	return new;
+}
+
 int netlink_add_tap(struct netlink_tap *nt)
 {
 	if (unlikely(nt->dev->type != ARPHRD_NETLINK))
@@ -205,7 +223,11 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb,
 	int ret = -ENOMEM;
 
 	dev_hold(dev);
-	nskb = skb_clone(skb, GFP_ATOMIC);
+
+	if (netlink_skb_is_mmaped(skb) || is_vmalloc_addr(skb->head))
+		nskb = netlink_to_full_skb(skb, GFP_ATOMIC);
+	else
+		nskb = skb_clone(skb, GFP_ATOMIC);
 	if (nskb) {
 		nskb->dev = dev;
 		nskb->protocol = htons((u16) sk->sk_protocol);
@@ -278,11 +300,6 @@ static void netlink_rcv_wake(struct sock *sk)
 }
 
 #ifdef CONFIG_NETLINK_MMAP
-static bool netlink_skb_is_mmaped(const struct sk_buff *skb)
-{
-	return NETLINK_CB(skb).flags & NETLINK_SKB_MMAPED;
-}
-
 static bool netlink_rx_is_mmaped(struct sock *sk)
 {
 	return nlk_sk(sk)->rx_ring.pg_vec != NULL;
@@ -834,7 +851,6 @@ static void netlink_ring_set_copied(struct sock *sk, struct sk_buff *skb)
 }
 
 #else /* CONFIG_NETLINK_MMAP */
-#define netlink_skb_is_mmaped(skb)	false
 #define netlink_rx_is_mmaped(sk)	false
 #define netlink_tx_is_mmaped(sk)	false
 #define netlink_mmap			sock_no_mmap
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index 8900840..df9a060 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -59,6 +59,15 @@ static inline struct netlink_sock *nlk_sk(struct sock *sk)
 	return container_of(sk, struct netlink_sock, sk);
 }
 
+static inline bool netlink_skb_is_mmaped(const struct sk_buff *skb)
+{
+#ifdef CONFIG_NETLINK_MMAP
+	return NETLINK_CB(skb).flags & NETLINK_SKB_MMAPED;
+#else
+	return false;
+#endif /* CONFIG_NETLINK_MMAP */
+}
+
 struct netlink_table {
 	struct rhashtable	hash;
 	struct hlist_head	mc_list;
-- 
2.1.0


From 3c78d3e283f1e8bb0b27dcd4ffc672f59fb887bb Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Thu, 10 Sep 2015 17:31:15 -0300
Subject: [PATCH 11/30] sctp: fix race on protocol/netns initialization

[ Upstream commit 8e2d61e0aed2b7c4ecb35844fe07e0b2b762dee4 ]

Consider sctp module is unloaded and is being requested because an user
is creating a sctp socket.

During initialization, sctp will add the new protocol type and then
initialize pernet subsys:

        status = sctp_v4_protosw_init();
        if (status)
                goto err_protosw_init;

        status = sctp_v6_protosw_init();
        if (status)
                goto err_v6_protosw_init;

        status = register_pernet_subsys(&sctp_net_ops);

The problem is that after those calls to sctp_v{4,6}_protosw_init(), it
is possible for userspace to create SCTP sockets like if the module is
already fully loaded. If that happens, one of the possible effects is
that we will have readers for net->sctp.local_addr_list list earlier
than expected and sctp_net_init() does not take precautions while
dealing with that list, leading to a potential panic but not limited to
that, as sctp_sock_init() will copy a bunch of blank/partially
initialized values from net->sctp.

The race happens like this:

     CPU 0                           |  CPU 1
  socket()                           |
   __sock_create                     | socket()
    inet_create                      |  __sock_create
     list_for_each_entry_rcu(        |
        answer, &inetsw[sock->type], |
        list) {                      |   inet_create
      /* no hits */                  |
     if (unlikely(err)) {            |
      ...                            |
      request_module()               |
      /* socket creation is blocked  |
       * the module is fully loaded  |
       */                            |
       sctp_init                     |
        sctp_v4_protosw_init         |
         inet_register_protosw       |
          list_add_rcu(&p->list,     |
                       last_perm);   |
                                     |  list_for_each_entry_rcu(
                                     |     answer, &inetsw[sock->type],
        sctp_v6_protosw_init         |     list) {
                                     |     /* hit, so assumes protocol
                                     |      * is already loaded
                                     |      */
                                     |  /* socket creation continues
                                     |   * before netns is initialized
                                     |   */
        register_pernet_subsys       |

Simply inverting the initialization order between
register_pernet_subsys() and sctp_v4_protosw_init() is not possible
because register_pernet_subsys() will create a control sctp socket, so
the protocol must be already visible by then. Deferring the socket
creation to a work-queue is not good specially because we loose the
ability to handle its errors.

So, as suggested by Vlad, the fix is to split netns initialization in
two moments: defaults and control socket, so that the defaults are
already loaded by when we register the protocol, while control socket
initialization is kept at the same moment it is today.

Fixes: 4db67e808640 ("sctp: Make the address lists per network namespace")
Signed-off-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/protocol.c | 64 ++++++++++++++++++++++++++++++++++-------------------
 1 file changed, 41 insertions(+), 23 deletions(-)

diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 59e8035..3ac604f 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -1166,7 +1166,7 @@ static void sctp_v4_del_protocol(void)
 	unregister_inetaddr_notifier(&sctp_inetaddr_notifier);
 }
 
-static int __net_init sctp_net_init(struct net *net)
+static int __net_init sctp_defaults_init(struct net *net)
 {
 	int status;
 
@@ -1259,12 +1259,6 @@ static int __net_init sctp_net_init(struct net *net)
 
 	sctp_dbg_objcnt_init(net);
 
-	/* Initialize the control inode/socket for handling OOTB packets.  */
-	if ((status = sctp_ctl_sock_init(net))) {
-		pr_err("Failed to initialize the SCTP control sock\n");
-		goto err_ctl_sock_init;
-	}
-
 	/* Initialize the local address list. */
 	INIT_LIST_HEAD(&net->sctp.local_addr_list);
 	spin_lock_init(&net->sctp.local_addr_lock);
@@ -1280,9 +1274,6 @@ static int __net_init sctp_net_init(struct net *net)
 
 	return 0;
 
-err_ctl_sock_init:
-	sctp_dbg_objcnt_exit(net);
-	sctp_proc_exit(net);
 err_init_proc:
 	cleanup_sctp_mibs(net);
 err_init_mibs:
@@ -1291,15 +1282,12 @@ err_sysctl_register:
 	return status;
 }
 
-static void __net_exit sctp_net_exit(struct net *net)
+static void __net_exit sctp_defaults_exit(struct net *net)
 {
 	/* Free the local address list */
 	sctp_free_addr_wq(net);
 	sctp_free_local_addr_list(net);
 
-	/* Free the control endpoint.  */
-	inet_ctl_sock_destroy(net->sctp.ctl_sock);
-
 	sctp_dbg_objcnt_exit(net);
 
 	sctp_proc_exit(net);
@@ -1307,9 +1295,32 @@ static void __net_exit sctp_net_exit(struct net *net)
 	sctp_sysctl_net_unregister(net);
 }
 
-static struct pernet_operations sctp_net_ops = {
-	.init = sctp_net_init,
-	.exit = sctp_net_exit,
+static struct pernet_operations sctp_defaults_ops = {
+	.init = sctp_defaults_init,
+	.exit = sctp_defaults_exit,
+};
+
+static int __net_init sctp_ctrlsock_init(struct net *net)
+{
+	int status;
+
+	/* Initialize the control inode/socket for handling OOTB packets.  */
+	status = sctp_ctl_sock_init(net);
+	if (status)
+		pr_err("Failed to initialize the SCTP control sock\n");
+
+	return status;
+}
+
+static void __net_init sctp_ctrlsock_exit(struct net *net)
+{
+	/* Free the control endpoint.  */
+	inet_ctl_sock_destroy(net->sctp.ctl_sock);
+}
+
+static struct pernet_operations sctp_ctrlsock_ops = {
+	.init = sctp_ctrlsock_init,
+	.exit = sctp_ctrlsock_exit,
 };
 
 /* Initialize the universe into something sensible.  */
@@ -1442,8 +1453,11 @@ static __init int sctp_init(void)
 	sctp_v4_pf_init();
 	sctp_v6_pf_init();
 
-	status = sctp_v4_protosw_init();
+	status = register_pernet_subsys(&sctp_defaults_ops);
+	if (status)
+		goto err_register_defaults;
 
+	status = sctp_v4_protosw_init();
 	if (status)
 		goto err_protosw_init;
 
@@ -1451,9 +1465,9 @@ static __init int sctp_init(void)
 	if (status)
 		goto err_v6_protosw_init;
 
-	status = register_pernet_subsys(&sctp_net_ops);
+	status = register_pernet_subsys(&sctp_ctrlsock_ops);
 	if (status)
-		goto err_register_pernet_subsys;
+		goto err_register_ctrlsock;
 
 	status = sctp_v4_add_protocol();
 	if (status)
@@ -1469,12 +1483,14 @@ out:
 err_v6_add_protocol:
 	sctp_v4_del_protocol();
 err_add_protocol:
-	unregister_pernet_subsys(&sctp_net_ops);
-err_register_pernet_subsys:
+	unregister_pernet_subsys(&sctp_ctrlsock_ops);
+err_register_ctrlsock:
 	sctp_v6_protosw_exit();
 err_v6_protosw_init:
 	sctp_v4_protosw_exit();
 err_protosw_init:
+	unregister_pernet_subsys(&sctp_defaults_ops);
+err_register_defaults:
 	sctp_v4_pf_exit();
 	sctp_v6_pf_exit();
 	sctp_sysctl_unregister();
@@ -1507,12 +1523,14 @@ static __exit void sctp_exit(void)
 	sctp_v6_del_protocol();
 	sctp_v4_del_protocol();
 
-	unregister_pernet_subsys(&sctp_net_ops);
+	unregister_pernet_subsys(&sctp_ctrlsock_ops);
 
 	/* Free protosw registrations */
 	sctp_v6_protosw_exit();
 	sctp_v4_protosw_exit();
 
+	unregister_pernet_subsys(&sctp_defaults_ops);
+
 	/* Unregister with socket layer. */
 	sctp_v6_pf_exit();
 	sctp_v4_pf_exit();
-- 
2.1.0


From 1e7617b8ab80e76f4a7dd09f0198f9b9008e8691 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Linus=20L=C3=BCssing?= <linus.luessing@c0d3.blue>
Date: Fri, 11 Sep 2015 18:39:48 +0200
Subject: [PATCH 12/30] bridge: fix igmpv3 / mldv2 report parsing
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit c2d4fbd2163e607915cc05798ce7fb7f31117cc1 ]

With the newly introduced helper functions the skb pulling is hidden in
the checksumming function - and undone before returning to the caller.

The IGMPv3 and MLDv2 report parsing functions in the bridge still
assumed that the skb is pointing to the beginning of the IGMP/MLD
message while it is now kept at the beginning of the IPv4/6 header,
breaking the message parsing and creating packet loss.

Fixing this by taking the offset between IP and IGMP/MLD header into
account, too.

Fixes: 9afd85c9e455 ("net: Export IGMP/MLD message validation code")
Reported-by: Tobias Powalowski <tobias.powalowski@googlemail.com>
Tested-by: Tobias Powalowski <tobias.powalowski@googlemail.com>
Signed-off-by: Linus Lüssing <linus.luessing@c0d3.blue>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 1285eaf..03cdb9e 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -991,7 +991,7 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br,
 
 	ih = igmpv3_report_hdr(skb);
 	num = ntohs(ih->ngrec);
-	len = sizeof(*ih);
+	len = skb_transport_offset(skb) + sizeof(*ih);
 
 	for (i = 0; i < num; i++) {
 		len += sizeof(*grec);
@@ -1052,7 +1052,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br,
 
 	icmp6h = icmp6_hdr(skb);
 	num = ntohs(icmp6h->icmp6_dataun.un_data16[1]);
-	len = sizeof(*icmp6h);
+	len = skb_transport_offset(skb) + sizeof(*icmp6h);
 
 	for (i = 0; i < num; i++) {
 		__be16 *nsrcs, _nsrcs;
-- 
2.1.0


From e34419618ff3b9f9b191f847fa92a09939c36d77 Mon Sep 17 00:00:00 2001
From: Simon Guinot <simon.guinot@sequanux.org>
Date: Tue, 15 Sep 2015 22:41:21 +0200
Subject: [PATCH 13/30] net: mvneta: fix DMA buffer unmapping in mvneta_rx()

[ Upstream commit daf158d0d544cec80b7b30deff8cfc59a6e17610 ]

This patch fixes a regression introduced by the commit a84e32894191
("net: mvneta: fix refilling for Rx DMA buffers"). Due to this commit
the newly allocated Rx buffers are DMA-unmapped in place of those passed
to the networking stack. Obviously, this causes data corruptions.

This patch fixes the issue by ensuring that the right Rx buffers are
DMA-unmapped.

Reported-by: Oren Laskin <oren@igneous.io>
Signed-off-by: Simon Guinot <simon.guinot@sequanux.org>
Fixes: a84e32894191 ("net: mvneta: fix refilling for Rx DMA buffers")
Cc: <stable@vger.kernel.org> # v3.8+
Tested-by: Oren Laskin <oren@igneous.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 62e48bc..03e052a 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -1479,6 +1479,7 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo,
 		struct mvneta_rx_desc *rx_desc = mvneta_rxq_next_desc_get(rxq);
 		struct sk_buff *skb;
 		unsigned char *data;
+		dma_addr_t phys_addr;
 		u32 rx_status;
 		int rx_bytes, err;
 
@@ -1486,6 +1487,7 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo,
 		rx_status = rx_desc->status;
 		rx_bytes = rx_desc->data_size - (ETH_FCS_LEN + MVNETA_MH_SIZE);
 		data = (unsigned char *)rx_desc->buf_cookie;
+		phys_addr = rx_desc->buf_phys_addr;
 
 		if (!mvneta_rxq_desc_is_first_last(rx_status) ||
 		    (rx_status & MVNETA_RXD_ERR_SUMMARY)) {
@@ -1534,7 +1536,7 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo,
 		if (!skb)
 			goto err_drop_frame;
 
-		dma_unmap_single(dev->dev.parent, rx_desc->buf_phys_addr,
+		dma_unmap_single(dev->dev.parent, phys_addr,
 				 MVNETA_RX_BUF_SIZE(pp->pkt_size), DMA_FROM_DEVICE);
 
 		rcvd_pkts++;
-- 
2.1.0


From ff98428008fee09e3552c7f8fc6b0e08a955d048 Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Tue, 15 Sep 2015 14:44:29 -0700
Subject: [PATCH 14/30] rtnetlink: catch -EOPNOTSUPP errors from
 ndo_bridge_getlink

[ Upstream commit d64f69b0373a7d0bcec8b5da7712977518a8f42b ]

problem reported:
	kernel 4.1.3
	------------
	# bridge vlan
	port	vlan ids
	eth0	 1 PVID Egress Untagged
	 	90
	 	91
	 	92
	 	93
	 	94
	 	95
	 	96
	 	97
	 	98
	 	99
	 	100

	vmbr0	 1 PVID Egress Untagged
	 	94

	kernel 4.2
	-----------
	# bridge vlan
	port	vlan ids

ndo_bridge_getlink can return -EOPNOTSUPP when an interfaces
ndo_bridge_getlink op is set to switchdev_port_bridge_getlink
and CONFIG_SWITCHDEV is not defined. This today can happen to
bond, rocker and team devices. This patch adds -EOPNOTSUPP
checks after calls to ndo_bridge_getlink.

Fixes: 85fdb956726ff2a ("switchdev: cut over to new switchdev_port_bridge_getlink")
Reported-by: Alexandre DERUMIER <aderumier@odiso.com>
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 26 ++++++++++++++++----------
 1 file changed, 16 insertions(+), 10 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index dc004b1..0861018 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3021,6 +3021,7 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb)
 	u32 portid = NETLINK_CB(cb->skb).portid;
 	u32 seq = cb->nlh->nlmsg_seq;
 	u32 filter_mask = 0;
+	int err;
 
 	if (nlmsg_len(cb->nlh) > sizeof(struct ifinfomsg)) {
 		struct nlattr *extfilt;
@@ -3041,20 +3042,25 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb)
 		struct net_device *br_dev = netdev_master_upper_dev_get(dev);
 
 		if (br_dev && br_dev->netdev_ops->ndo_bridge_getlink) {
-			if (idx >= cb->args[0] &&
-			    br_dev->netdev_ops->ndo_bridge_getlink(
-				    skb, portid, seq, dev, filter_mask,
-				    NLM_F_MULTI) < 0)
-				break;
+			if (idx >= cb->args[0]) {
+				err = br_dev->netdev_ops->ndo_bridge_getlink(
+						skb, portid, seq, dev,
+						filter_mask, NLM_F_MULTI);
+				if (err < 0 && err != -EOPNOTSUPP)
+					break;
+			}
 			idx++;
 		}
 
 		if (ops->ndo_bridge_getlink) {
-			if (idx >= cb->args[0] &&
-			    ops->ndo_bridge_getlink(skb, portid, seq, dev,
-						    filter_mask,
-						    NLM_F_MULTI) < 0)
-				break;
+			if (idx >= cb->args[0]) {
+				err = ops->ndo_bridge_getlink(skb, portid,
+							      seq, dev,
+							      filter_mask,
+							      NLM_F_MULTI);
+				if (err < 0 && err != -EOPNOTSUPP)
+					break;
+			}
 			idx++;
 		}
 	}
-- 
2.1.0


From 5d11d899f25b20905c2ea21c46ef8c3ddf54e57a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 15 Sep 2015 18:29:47 -0700
Subject: [PATCH 15/30] net/mlx4_en: really allow to change RSS key

[ Upsteam commit 4671fc6d47e0a0108fe24a4d830347d6a6ef4aa7 ]

When changing rss key, we do not want to overwrite user provided key
by the one provided by netdev_rss_key_fill(), which is the host random
key generated at boot time.

Fixes: 947cbb0ac242 ("net/mlx4_en: Support for configurable RSS hash function")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Eyal Perry <eyalpe@mellanox.com>
CC: Amir Vadai <amirv@mellanox.com>
Acked-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_rx.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 9c145dd..4f95fa7 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -1250,8 +1250,6 @@ int mlx4_en_config_rss_steer(struct mlx4_en_priv *priv)
 		rss_context->hash_fn = MLX4_RSS_HASH_TOP;
 		memcpy(rss_context->rss_key, priv->rss_key,
 		       MLX4_EN_RSS_KEY_SIZE);
-		netdev_rss_key_fill(rss_context->rss_key,
-				    MLX4_EN_RSS_KEY_SIZE);
 	} else {
 		en_err(priv, "Unknown RSS hash function requested\n");
 		err = -EINVAL;
-- 
2.1.0


From c8fb6c89a432b7055eed2fce946bc660a2c6f498 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Fri, 18 Sep 2015 13:41:09 +0300
Subject: [PATCH 16/30] macvtap: fix TUNSETSNDBUF values > 64k

[ Upstream commit 3ea79249e81e5ed051f2e6480cbde896d99046e8 ]

Upon TUNSETSNDBUF,  macvtap reads the requested sndbuf size into
a local variable u.
commit 39ec7de7092b ("macvtap: fix uninitialized access on
TUNSETIFF") changed its type to u16 (which is the right thing to
do for all other macvtap ioctls), breaking all values > 64k.

The value of TUNSETSNDBUF is actually a signed 32 bit integer, so
the right thing to do is to read it into an int.

Cc: David S. Miller <davem@davemloft.net>
Fixes: 39ec7de7092b ("macvtap: fix uninitialized access on TUNSETIFF")
Reported-by: Mark A. Peloquin
Bisected-by: Matthew Rosato <mjrosato@linux.vnet.ibm.com>
Reported-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by:  Matthew Rosato <mjrosato@linux.vnet.ibm.com>
Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macvtap.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index edd7734..248478c 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -1111,10 +1111,10 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd,
 		return 0;
 
 	case TUNSETSNDBUF:
-		if (get_user(u, up))
+		if (get_user(s, sp))
 			return -EFAULT;
 
-		q->sk.sk_sndbuf = u;
+		q->sk.sk_sndbuf = s;
 		return 0;
 
 	case TUNGETVNETHDRSZ:
-- 
2.1.0


From 22bed6544249fa903260a5fea28202db990bfa39 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Fri, 18 Sep 2015 19:16:50 +0800
Subject: [PATCH 17/30] netlink: Fix autobind race condition that leads to zero
 port ID

[ Upstream commit 1f770c0a09da855a2b51af6d19de97fb955eca85 ]

The commit c0bb07df7d981e4091432754e30c9c720e2c0c78 ("netlink:
Reset portid after netlink_insert failure") introduced a race
condition where if two threads try to autobind the same socket
one of them may end up with a zero port ID.  This led to kernel
deadlocks that were observed by multiple people.

This patch reverts that commit and instead fixes it by introducing
a separte rhash_portid variable so that the real portid is only set
after the socket has been successfully hashed.

Fixes: c0bb07df7d98 ("netlink: Reset portid after netlink_insert failure")
Reported-by: Tejun Heo <tj@kernel.org>
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 12 +++++++-----
 net/netlink/af_netlink.h |  1 +
 2 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index bbd5d43..42de385 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1019,7 +1019,7 @@ static inline int netlink_compare(struct rhashtable_compare_arg *arg,
 	const struct netlink_compare_arg *x = arg->key;
 	const struct netlink_sock *nlk = ptr;
 
-	return nlk->portid != x->portid ||
+	return nlk->rhash_portid != x->portid ||
 	       !net_eq(sock_net(&nlk->sk), read_pnet(&x->pnet));
 }
 
@@ -1045,7 +1045,7 @@ static int __netlink_insert(struct netlink_table *table, struct sock *sk)
 {
 	struct netlink_compare_arg arg;
 
-	netlink_compare_arg_init(&arg, sock_net(sk), nlk_sk(sk)->portid);
+	netlink_compare_arg_init(&arg, sock_net(sk), nlk_sk(sk)->rhash_portid);
 	return rhashtable_lookup_insert_key(&table->hash, &arg,
 					    &nlk_sk(sk)->node,
 					    netlink_rhashtable_params);
@@ -1107,7 +1107,7 @@ static int netlink_insert(struct sock *sk, u32 portid)
 	    unlikely(atomic_read(&table->hash.nelems) >= UINT_MAX))
 		goto err;
 
-	nlk_sk(sk)->portid = portid;
+	nlk_sk(sk)->rhash_portid = portid;
 	sock_hold(sk);
 
 	err = __netlink_insert(table, sk);
@@ -1119,10 +1119,12 @@ static int netlink_insert(struct sock *sk, u32 portid)
 			err = -EOVERFLOW;
 		if (err == -EEXIST)
 			err = -EADDRINUSE;
-		nlk_sk(sk)->portid = 0;
 		sock_put(sk);
+		goto err;
 	}
 
+	nlk_sk(sk)->portid = portid;
+
 err:
 	release_sock(sk);
 	return err;
@@ -3233,7 +3235,7 @@ static inline u32 netlink_hash(const void *data, u32 len, u32 seed)
 	const struct netlink_sock *nlk = data;
 	struct netlink_compare_arg arg;
 
-	netlink_compare_arg_init(&arg, sock_net(&nlk->sk), nlk->portid);
+	netlink_compare_arg_init(&arg, sock_net(&nlk->sk), nlk->rhash_portid);
 	return jhash2((u32 *)&arg, netlink_compare_arg_len / sizeof(u32), seed);
 }
 
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index df9a060..80b2b75 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -25,6 +25,7 @@ struct netlink_ring {
 struct netlink_sock {
 	/* struct sock has to be the first member of netlink_sock */
 	struct sock		sk;
+	u32			rhash_portid;
 	u32			portid;
 	u32			dst_portid;
 	u32			dst_group;
-- 
2.1.0


From a5c5dea26e50fcfc2b4553c78df875555f5a20ff Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Tue, 22 Sep 2015 11:38:56 +0800
Subject: [PATCH 18/30] netlink: Replace rhash_portid with bound

[ Upstream commit da314c9923fed553a007785a901fd395b7eb6c19 ]

On Mon, Sep 21, 2015 at 02:20:22PM -0400, Tejun Heo wrote:
>
> store_release and load_acquire are different from the usual memory
> barriers and can't be paired this way.  You have to pair store_release
> and load_acquire.  Besides, it isn't a particularly good idea to

OK I've decided to drop the acquire/release helpers as they don't
help us at all and simply pessimises the code by using full memory
barriers (on some architectures) where only a write or read barrier
is needed.

> depend on memory barriers embedded in other data structures like the
> above.  Here, especially, rhashtable_insert() would have write barrier
> *before* the entry is hashed not necessarily *after*, which means that
> in the above case, a socket which appears to have set bound to a
> reader might not visible when the reader tries to look up the socket
> on the hashtable.

But you are right we do need an explicit write barrier here to
ensure that the hashing is visible.

> There's no reason to be overly smart here.  This isn't a crazy hot
> path, write barriers tend to be very cheap, store_release more so.
> Please just do smp_store_release() and note what it's paired with.

It's not about being overly smart.  It's about actually understanding
what's going on with the code.  I've seen too many instances of
people simply sprinkling synchronisation primitives around without
any knowledge of what is happening underneath, which is just a recipe
for creating hard-to-debug races.

> > @@ -1539,7 +1546,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
> >  		}
> >  	}
> >
> > -	if (!nlk->portid) {
> > +	if (!nlk->bound) {
>
> I don't think you can skip load_acquire here just because this is the
> second deref of the variable.  That doesn't change anything.  Race
> condition could still happen between the first and second tests and
> skipping the second would lead to the same kind of bug.

The reason this one is OK is because we do not use nlk->portid or
try to get nlk from the hash table before we return to user-space.

However, there is a real bug here that none of these acquire/release
helpers discovered.  The two bound tests here used to be a single
one.  Now that they are separate it is entirely possible for another
thread to come in the middle and bind the socket.  So we need to
repeat the portid check in order to maintain consistency.

> > @@ -1587,7 +1594,7 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr,
> >  	    !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
> >  		return -EPERM;
> >
> > -	if (!nlk->portid)
> > +	if (!nlk->bound)
>
> Don't we need load_acquire here too?  Is this path holding a lock
> which makes that unnecessary?

Ditto.

---8<---
The commit 1f770c0a09da855a2b51af6d19de97fb955eca85 ("netlink:
Fix autobind race condition that leads to zero port ID") created
some new races that can occur due to inconcsistencies between the
two port IDs.

Tejun is right that a barrier is unavoidable.  Therefore I am
reverting to the original patch that used a boolean to indicate
that a user netlink socket has been bound.

Barriers have been added where necessary to ensure that a valid
portid and the hashed socket is visible.

I have also changed netlink_insert to only return EBUSY if the
socket is bound to a portid different to the requested one.  This
combined with only reading nlk->bound once in netlink_bind fixes
a race where two threads that bind the socket at the same time
with different port IDs may both succeed.

Fixes: 1f770c0a09da ("netlink: Fix autobind race condition that leads to zero port ID")
Reported-by: Tejun Heo <tj@kernel.org>
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Nacked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 39 ++++++++++++++++++++++++++++-----------
 net/netlink/af_netlink.h |  2 +-
 2 files changed, 29 insertions(+), 12 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 42de385..0857f72 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1019,7 +1019,7 @@ static inline int netlink_compare(struct rhashtable_compare_arg *arg,
 	const struct netlink_compare_arg *x = arg->key;
 	const struct netlink_sock *nlk = ptr;
 
-	return nlk->rhash_portid != x->portid ||
+	return nlk->portid != x->portid ||
 	       !net_eq(sock_net(&nlk->sk), read_pnet(&x->pnet));
 }
 
@@ -1045,7 +1045,7 @@ static int __netlink_insert(struct netlink_table *table, struct sock *sk)
 {
 	struct netlink_compare_arg arg;
 
-	netlink_compare_arg_init(&arg, sock_net(sk), nlk_sk(sk)->rhash_portid);
+	netlink_compare_arg_init(&arg, sock_net(sk), nlk_sk(sk)->portid);
 	return rhashtable_lookup_insert_key(&table->hash, &arg,
 					    &nlk_sk(sk)->node,
 					    netlink_rhashtable_params);
@@ -1098,8 +1098,8 @@ static int netlink_insert(struct sock *sk, u32 portid)
 
 	lock_sock(sk);
 
-	err = -EBUSY;
-	if (nlk_sk(sk)->portid)
+	err = nlk_sk(sk)->portid == portid ? 0 : -EBUSY;
+	if (nlk_sk(sk)->bound)
 		goto err;
 
 	err = -ENOMEM;
@@ -1107,7 +1107,7 @@ static int netlink_insert(struct sock *sk, u32 portid)
 	    unlikely(atomic_read(&table->hash.nelems) >= UINT_MAX))
 		goto err;
 
-	nlk_sk(sk)->rhash_portid = portid;
+	nlk_sk(sk)->portid = portid;
 	sock_hold(sk);
 
 	err = __netlink_insert(table, sk);
@@ -1123,7 +1123,9 @@ static int netlink_insert(struct sock *sk, u32 portid)
 		goto err;
 	}
 
-	nlk_sk(sk)->portid = portid;
+	/* We need to ensure that the socket is hashed and visible. */
+	smp_wmb();
+	nlk_sk(sk)->bound = portid;
 
 err:
 	release_sock(sk);
@@ -1509,6 +1511,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 	struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr;
 	int err;
 	long unsigned int groups = nladdr->nl_groups;
+	bool bound;
 
 	if (addr_len < sizeof(struct sockaddr_nl))
 		return -EINVAL;
@@ -1525,9 +1528,14 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 			return err;
 	}
 
-	if (nlk->portid)
+	bound = nlk->bound;
+	if (bound) {
+		/* Ensure nlk->portid is up-to-date. */
+		smp_rmb();
+
 		if (nladdr->nl_pid != nlk->portid)
 			return -EINVAL;
+	}
 
 	if (nlk->netlink_bind && groups) {
 		int group;
@@ -1543,7 +1551,10 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 		}
 	}
 
-	if (!nlk->portid) {
+	/* No need for barriers here as we return to user-space without
+	 * using any of the bound attributes.
+	 */
+	if (!bound) {
 		err = nladdr->nl_pid ?
 			netlink_insert(sk, nladdr->nl_pid) :
 			netlink_autobind(sock);
@@ -1591,7 +1602,10 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr,
 	    !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
 		return -EPERM;
 
-	if (!nlk->portid)
+	/* No need for barriers here as we return to user-space without
+	 * using any of the bound attributes.
+	 */
+	if (!nlk->bound)
 		err = netlink_autobind(sock);
 
 	if (err == 0) {
@@ -2409,10 +2423,13 @@ static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 		dst_group = nlk->dst_group;
 	}
 
-	if (!nlk->portid) {
+	if (!nlk->bound) {
 		err = netlink_autobind(sock);
 		if (err)
 			goto out;
+	} else {
+		/* Ensure nlk is hashed and visible. */
+		smp_rmb();
 	}
 
 	/* It's a really convoluted way for userland to ask for mmaped
@@ -3235,7 +3252,7 @@ static inline u32 netlink_hash(const void *data, u32 len, u32 seed)
 	const struct netlink_sock *nlk = data;
 	struct netlink_compare_arg arg;
 
-	netlink_compare_arg_init(&arg, sock_net(&nlk->sk), nlk->rhash_portid);
+	netlink_compare_arg_init(&arg, sock_net(&nlk->sk), nlk->portid);
 	return jhash2((u32 *)&arg, netlink_compare_arg_len / sizeof(u32), seed);
 }
 
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index 80b2b75..14437d9 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -25,7 +25,6 @@ struct netlink_ring {
 struct netlink_sock {
 	/* struct sock has to be the first member of netlink_sock */
 	struct sock		sk;
-	u32			rhash_portid;
 	u32			portid;
 	u32			dst_portid;
 	u32			dst_group;
@@ -36,6 +35,7 @@ struct netlink_sock {
 	unsigned long		state;
 	size_t			max_recvmsg_len;
 	wait_queue_head_t	wait;
+	bool			bound;
 	bool			cb_running;
 	struct netlink_callback	cb;
 	struct mutex		*cb_mutex;
-- 
2.1.0


From 4cdf5359b8226ba9c1ce1a4ded955d2adf035fdb Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Mon, 21 Sep 2015 21:42:59 +0100
Subject: [PATCH 19/30] net: dsa: actually force the speed on the CPU port

[ Upstream commit 53adc9e83028d9e35b6408231ebaf62a94a16e4d ]

Commit 54d792f257c6 ("net: dsa: Centralise global and port setup
code into mv88e6xxx.") merged in the 4.2 merge window broke the link
speed forcing for the CPU port of Marvell DSA switches.  The original
code was:

        /* MAC Forcing register: don't force link, speed, duplex
         * or flow control state to any particular values on physical
         * ports, but force the CPU port and all DSA ports to 1000 Mb/s
         * full duplex.
         */
        if (dsa_is_cpu_port(ds, p) || ds->dsa_port_mask & (1 << p))
                REG_WRITE(addr, 0x01, 0x003e);
        else
                REG_WRITE(addr, 0x01, 0x0003);

but the new code does a read-modify-write:

                reg = _mv88e6xxx_reg_read(ds, REG_PORT(port), PORT_PCS_CTRL);
                if (dsa_is_cpu_port(ds, port) ||
                    ds->dsa_port_mask & (1 << port)) {
                        reg |= PORT_PCS_CTRL_FORCE_LINK |
                                PORT_PCS_CTRL_LINK_UP |
                                PORT_PCS_CTRL_DUPLEX_FULL |
                                PORT_PCS_CTRL_FORCE_DUPLEX;
                        if (mv88e6xxx_6065_family(ds))
                                reg |= PORT_PCS_CTRL_100;
                        else
                                reg |= PORT_PCS_CTRL_1000;

The link speed in the PCS control register is a two bit field.  Forcing
the link speed in this way doesn't ensure that the bit field is set to
the correct value - on the hardware I have here, the speed bitfield
remains set to 0x03, resulting in the speed not being forced to gigabit.

We must clear both bits before forcing the link speed.

Fixes: 54d792f257c6 ("net: dsa: Centralise global and port setup code into mv88e6xxx.")
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Acked-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c
index 5613424..26ec2fb 100644
--- a/drivers/net/dsa/mv88e6xxx.c
+++ b/drivers/net/dsa/mv88e6xxx.c
@@ -1387,6 +1387,7 @@ static int mv88e6xxx_setup_port(struct dsa_switch *ds, int port)
 		reg = _mv88e6xxx_reg_read(ds, REG_PORT(port), PORT_PCS_CTRL);
 		if (dsa_is_cpu_port(ds, port) ||
 		    ds->dsa_port_mask & (1 << port)) {
+			reg &= ~PORT_PCS_CTRL_UNFORCED;
 			reg |= PORT_PCS_CTRL_FORCE_LINK |
 				PORT_PCS_CTRL_LINK_UP |
 				PORT_PCS_CTRL_DUPLEX_FULL |
-- 
2.1.0


From a5cbaca9e02496bc3850e4d057c667d98d87a7c7 Mon Sep 17 00:00:00 2001
From: Jesse Gross <jesse@nicira.com>
Date: Mon, 21 Sep 2015 20:21:20 -0700
Subject: [PATCH 20/30] openvswitch: Zero flows on allocation.

[ Upstream commit ae5f2fb1d51fa128a460bcfbe3c56d7ab8bf6a43 ]

When support for megaflows was introduced, OVS needed to start
installing flows with a mask applied to them. Since masking is an
expensive operation, OVS also had an optimization that would only
take the parts of the flow keys that were covered by a non-zero
mask. The values stored in the remaining pieces should not matter
because they are masked out.

While this works fine for the purposes of matching (which must always
look at the mask), serialization to netlink can be problematic. Since
the flow and the mask are serialized separately, the uninitialized
portions of the flow can be encoded with whatever values happen to be
present.

In terms of functionality, this has little effect since these fields
will be masked out by definition. However, it leaks kernel memory to
userspace, which is a potential security vulnerability. It is also
possible that other code paths could look at the masked key and get
uninitialized data, although this does not currently appear to be an
issue in practice.

This removes the mask optimization for flows that are being installed.
This was always intended to be the case as the mask optimizations were
really targetting per-packet flow operations.

Fixes: 03f0d916 ("openvswitch: Mega flow implementation")
Signed-off-by: Jesse Gross <jesse@nicira.com>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/datapath.c   |  4 ++--
 net/openvswitch/flow_table.c | 23 ++++++++++++-----------
 net/openvswitch/flow_table.h |  2 +-
 3 files changed, 15 insertions(+), 14 deletions(-)

diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index ff8c4a4..ff332d1 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -920,7 +920,7 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	if (error)
 		goto err_kfree_flow;
 
-	ovs_flow_mask_key(&new_flow->key, &key, &mask);
+	ovs_flow_mask_key(&new_flow->key, &key, true, &mask);
 
 	/* Extract flow identifier. */
 	error = ovs_nla_get_identifier(&new_flow->id, a[OVS_FLOW_ATTR_UFID],
@@ -1047,7 +1047,7 @@ static struct sw_flow_actions *get_flow_actions(const struct nlattr *a,
 	struct sw_flow_key masked_key;
 	int error;
 
-	ovs_flow_mask_key(&masked_key, key, mask);
+	ovs_flow_mask_key(&masked_key, key, true, mask);
 	error = ovs_nla_copy_actions(a, &masked_key, &acts, log);
 	if (error) {
 		OVS_NLERR(log,
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index 6552394..b5c3bba 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -56,20 +56,21 @@ static u16 range_n_bytes(const struct sw_flow_key_range *range)
 }
 
 void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
-		       const struct sw_flow_mask *mask)
+		       bool full, const struct sw_flow_mask *mask)
 {
-	const long *m = (const long *)((const u8 *)&mask->key +
-				mask->range.start);
-	const long *s = (const long *)((const u8 *)src +
-				mask->range.start);
-	long *d = (long *)((u8 *)dst + mask->range.start);
+	int start = full ? 0 : mask->range.start;
+	int len = full ? sizeof *dst : range_n_bytes(&mask->range);
+	const long *m = (const long *)((const u8 *)&mask->key + start);
+	const long *s = (const long *)((const u8 *)src + start);
+	long *d = (long *)((u8 *)dst + start);
 	int i;
 
-	/* The memory outside of the 'mask->range' are not set since
-	 * further operations on 'dst' only uses contents within
-	 * 'mask->range'.
+	/* If 'full' is true then all of 'dst' is fully initialized. Otherwise,
+	 * if 'full' is false the memory outside of the 'mask->range' is left
+	 * uninitialized. This can be used as an optimization when further
+	 * operations on 'dst' only use contents within 'mask->range'.
 	 */
-	for (i = 0; i < range_n_bytes(&mask->range); i += sizeof(long))
+	for (i = 0; i < len; i += sizeof(long))
 		*d++ = *s++ & *m++;
 }
 
@@ -473,7 +474,7 @@ static struct sw_flow *masked_flow_lookup(struct table_instance *ti,
 	u32 hash;
 	struct sw_flow_key masked_key;
 
-	ovs_flow_mask_key(&masked_key, unmasked, mask);
+	ovs_flow_mask_key(&masked_key, unmasked, false, mask);
 	hash = flow_hash(&masked_key, &mask->range);
 	head = find_bucket(ti, hash);
 	hlist_for_each_entry_rcu(flow, head, flow_table.node[ti->node_ver]) {
diff --git a/net/openvswitch/flow_table.h b/net/openvswitch/flow_table.h
index 616eda1..2dd9900 100644
--- a/net/openvswitch/flow_table.h
+++ b/net/openvswitch/flow_table.h
@@ -86,5 +86,5 @@ struct sw_flow *ovs_flow_tbl_lookup_ufid(struct flow_table *,
 bool ovs_flow_cmp(const struct sw_flow *, const struct sw_flow_match *);
 
 void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
-		       const struct sw_flow_mask *mask);
+		       bool full, const struct sw_flow_mask *mask);
 #endif /* flow_table.h */
-- 
2.1.0


From fe62699d2210be635242035461ab5636bc87d5d4 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 23 Sep 2015 14:00:21 -0700
Subject: [PATCH 21/30] tcp: add proper TS val into RST packets

[ Upstream commit 675ee231d960af2af3606b4480324e26797eb010 ]

RST packets sent on behalf of TCP connections with TS option (RFC 7323
TCP timestamps) have incorrect TS val (set to 0), but correct TS ecr.

A > B: Flags [S], seq 0, win 65535, options [mss 1000,nop,nop,TS val 100
ecr 0], length 0
B > A: Flags [S.], seq 2444755794, ack 1, win 28960, options [mss
1460,nop,nop,TS val 7264344 ecr 100], length 0
A > B: Flags [.], ack 1, win 65535, options [nop,nop,TS val 110 ecr
7264344], length 0

B > A: Flags [R.], seq 1, ack 1, win 28960, options [nop,nop,TS val 0
ecr 110], length 0

We need to call skb_mstamp_get() to get proper TS val,
derived from skb->skb_mstamp

Note that RFC 1323 was advocating to not send TS option in RST segment,
but RFC 7323 recommends the opposite :

  Once TSopt has been successfully negotiated, that is both <SYN> and
  <SYN,ACK> contain TSopt, the TSopt MUST be sent in every non-<RST>
  segment for the duration of the connection, and SHOULD be sent in an
  <RST> segment (see Section 5.2 for details)

Note this RFC recommends to send TS val = 0, but we believe it is
premature : We do not know if all TCP stacks are properly
handling the receive side :

   When an <RST> segment is
   received, it MUST NOT be subjected to the PAWS check by verifying an
   acceptable value in SEG.TSval, and information from the Timestamps
   option MUST NOT be used to update connection state information.
   SEG.TSecr MAY be used to provide stricter <RST> acceptance checks.

In 5 years, if/when all TCP stack are RFC 7323 ready, we might consider
to decide to send TS val = 0, if it buys something.

Fixes: 7faee5c0d514 ("tcp: remove TCP_SKB_CB(skb)->when")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index b1c218d..b7dedd9 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2898,6 +2898,7 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority)
 	skb_reserve(skb, MAX_TCP_HEADER);
 	tcp_init_nondata_skb(skb, tcp_acceptable_seq(sk),
 			     TCPHDR_ACK | TCPHDR_RST);
+	skb_mstamp_get(&skb->skb_mstamp);
 	/* Send it off. */
 	if (tcp_transmit_skb(sk, skb, 0, priority))
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED);
-- 
2.1.0


From 5829d2eafe497437bda2ef310a1eaa4be5783306 Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw2@infradead.org>
Date: Wed, 23 Sep 2015 19:45:08 +0100
Subject: [PATCH 22/30] Fix AF_PACKET ABI breakage in 4.2

[ Upstream commit d3869efe7a8a2298516d9af4f91487cf486ca945 ]

Commit 7d82410950aa ("virtio: add explicit big-endian support to memory
accessors") accidentally changed the virtio_net header used by
AF_PACKET with PACKET_VNET_HDR from host-endian to big-endian.

Since virtio_legacy_is_little_endian() is a very long identifier,
define a vio_le macro and use that throughout the code instead of the
hard-coded 'false' for little-endian.

This restores the ABI to match 4.1 and earlier kernels, and makes my
test program work again.

Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 32 +++++++++++++++++---------------
 1 file changed, 17 insertions(+), 15 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index ed458b3..7851b12 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -229,6 +229,8 @@ struct packet_skb_cb {
 	} sa;
 };
 
+#define vio_le() virtio_legacy_is_little_endian()
+
 #define PACKET_SKB_CB(__skb)	((struct packet_skb_cb *)((__skb)->cb))
 
 #define GET_PBDQC_FROM_RB(x)	((struct tpacket_kbdq_core *)(&(x)->prb_bdqc))
@@ -2561,15 +2563,15 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 			goto out_unlock;
 
 		if ((vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) &&
-		    (__virtio16_to_cpu(false, vnet_hdr.csum_start) +
-		     __virtio16_to_cpu(false, vnet_hdr.csum_offset) + 2 >
-		      __virtio16_to_cpu(false, vnet_hdr.hdr_len)))
-			vnet_hdr.hdr_len = __cpu_to_virtio16(false,
-				 __virtio16_to_cpu(false, vnet_hdr.csum_start) +
-				__virtio16_to_cpu(false, vnet_hdr.csum_offset) + 2);
+		    (__virtio16_to_cpu(vio_le(), vnet_hdr.csum_start) +
+		     __virtio16_to_cpu(vio_le(), vnet_hdr.csum_offset) + 2 >
+		      __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len)))
+			vnet_hdr.hdr_len = __cpu_to_virtio16(vio_le(),
+				 __virtio16_to_cpu(vio_le(), vnet_hdr.csum_start) +
+				__virtio16_to_cpu(vio_le(), vnet_hdr.csum_offset) + 2);
 
 		err = -EINVAL;
-		if (__virtio16_to_cpu(false, vnet_hdr.hdr_len) > len)
+		if (__virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len) > len)
 			goto out_unlock;
 
 		if (vnet_hdr.gso_type != VIRTIO_NET_HDR_GSO_NONE) {
@@ -2612,7 +2614,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	hlen = LL_RESERVED_SPACE(dev);
 	tlen = dev->needed_tailroom;
 	skb = packet_alloc_skb(sk, hlen + tlen, hlen, len,
-			       __virtio16_to_cpu(false, vnet_hdr.hdr_len),
+			       __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len),
 			       msg->msg_flags & MSG_DONTWAIT, &err);
 	if (skb == NULL)
 		goto out_unlock;
@@ -2659,8 +2661,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 
 	if (po->has_vnet_hdr) {
 		if (vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
-			u16 s = __virtio16_to_cpu(false, vnet_hdr.csum_start);
-			u16 o = __virtio16_to_cpu(false, vnet_hdr.csum_offset);
+			u16 s = __virtio16_to_cpu(vio_le(), vnet_hdr.csum_start);
+			u16 o = __virtio16_to_cpu(vio_le(), vnet_hdr.csum_offset);
 			if (!skb_partial_csum_set(skb, s, o)) {
 				err = -EINVAL;
 				goto out_free;
@@ -2668,7 +2670,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		}
 
 		skb_shinfo(skb)->gso_size =
-			__virtio16_to_cpu(false, vnet_hdr.gso_size);
+			__virtio16_to_cpu(vio_le(), vnet_hdr.gso_size);
 		skb_shinfo(skb)->gso_type = gso_type;
 
 		/* Header must be checked, and gso_segs computed. */
@@ -3042,9 +3044,9 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 
 			/* This is a hint as to how much should be linear. */
 			vnet_hdr.hdr_len =
-				__cpu_to_virtio16(false, skb_headlen(skb));
+				__cpu_to_virtio16(vio_le(), skb_headlen(skb));
 			vnet_hdr.gso_size =
-				__cpu_to_virtio16(false, sinfo->gso_size);
+				__cpu_to_virtio16(vio_le(), sinfo->gso_size);
 			if (sinfo->gso_type & SKB_GSO_TCPV4)
 				vnet_hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
 			else if (sinfo->gso_type & SKB_GSO_TCPV6)
@@ -3062,9 +3064,9 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 
 		if (skb->ip_summed == CHECKSUM_PARTIAL) {
 			vnet_hdr.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
-			vnet_hdr.csum_start = __cpu_to_virtio16(false,
+			vnet_hdr.csum_start = __cpu_to_virtio16(vio_le(),
 					  skb_checksum_start_offset(skb));
-			vnet_hdr.csum_offset = __cpu_to_virtio16(false,
+			vnet_hdr.csum_offset = __cpu_to_virtio16(vio_le(),
 							 skb->csum_offset);
 		} else if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
 			vnet_hdr.flags = VIRTIO_NET_HDR_F_DATA_VALID;
-- 
2.1.0


From 13d563e7a1dc1c5e656285161b3862edab52112a Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Tue, 22 Sep 2015 17:01:11 -0700
Subject: [PATCH 23/30] net: revert "net_sched: move tp->root allocation into
 fw_init()"

[ Upstream commit d8aecb10115497f6cdf841df8c88ebb3ba25fa28 ]

fw filter uses tp->root==NULL to check if it is the old method,
so it doesn't need allocation at all in this case. This patch
reverts the offending commit and adds some comments for old
method to make it obvious.

Fixes: 33f8b9ecdb15 ("net_sched: move tp->root allocation into fw_init()")
Reported-by: Akshat Kakkar <akshat.1984@gmail.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_fw.c | 30 +++++++++++++++---------------
 1 file changed, 15 insertions(+), 15 deletions(-)

diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c
index 715e01e..f23a3b6 100644
--- a/net/sched/cls_fw.c
+++ b/net/sched/cls_fw.c
@@ -33,7 +33,6 @@
 
 struct fw_head {
 	u32			mask;
-	bool			mask_set;
 	struct fw_filter __rcu	*ht[HTSIZE];
 	struct rcu_head		rcu;
 };
@@ -84,7 +83,7 @@ static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 			}
 		}
 	} else {
-		/* old method */
+		/* Old method: classify the packet using its skb mark. */
 		if (id && (TC_H_MAJ(id) == 0 ||
 			   !(TC_H_MAJ(id ^ tp->q->handle)))) {
 			res->classid = id;
@@ -114,14 +113,9 @@ static unsigned long fw_get(struct tcf_proto *tp, u32 handle)
 
 static int fw_init(struct tcf_proto *tp)
 {
-	struct fw_head *head;
-
-	head = kzalloc(sizeof(struct fw_head), GFP_KERNEL);
-	if (head == NULL)
-		return -ENOBUFS;
-
-	head->mask_set = false;
-	rcu_assign_pointer(tp->root, head);
+	/* We don't allocate fw_head here, because in the old method
+	 * we don't need it at all.
+	 */
 	return 0;
 }
 
@@ -252,7 +246,7 @@ static int fw_change(struct net *net, struct sk_buff *in_skb,
 	int err;
 
 	if (!opt)
-		return handle ? -EINVAL : 0;
+		return handle ? -EINVAL : 0; /* Succeed if it is old method. */
 
 	err = nla_parse_nested(tb, TCA_FW_MAX, opt, fw_policy);
 	if (err < 0)
@@ -302,11 +296,17 @@ static int fw_change(struct net *net, struct sk_buff *in_skb,
 	if (!handle)
 		return -EINVAL;
 
-	if (!head->mask_set) {
-		head->mask = 0xFFFFFFFF;
+	if (!head) {
+		u32 mask = 0xFFFFFFFF;
 		if (tb[TCA_FW_MASK])
-			head->mask = nla_get_u32(tb[TCA_FW_MASK]);
-		head->mask_set = true;
+			mask = nla_get_u32(tb[TCA_FW_MASK]);
+
+		head = kzalloc(sizeof(*head), GFP_KERNEL);
+		if (!head)
+			return -ENOBUFS;
+		head->mask = mask;
+
+		rcu_assign_pointer(tp->root, head);
 	}
 
 	f = kzalloc(sizeof(struct fw_filter), GFP_KERNEL);
-- 
2.1.0


From 7a084c0513beddf19a13b4b29a53c2bd8e1511b7 Mon Sep 17 00:00:00 2001
From: Wilson Kok <wkok@cumulusnetworks.com>
Date: Tue, 22 Sep 2015 21:40:22 -0700
Subject: [PATCH 24/30] fib_rules: fix fib rule dumps across multiple skbs

[ Upstream commit 41fc014332d91ee90c32840bf161f9685b7fbf2b ]

dump_rules returns skb length and not error.
But when family == AF_UNSPEC, the caller of dump_rules
assumes that it returns an error. Hence, when family == AF_UNSPEC,
we continue trying to dump on -EMSGSIZE errors resulting in
incorrect dump idx carried between skbs belonging to the same dump.
This results in fib rule dump always only dumping rules that fit
into the first skb.

This patch fixes dump_rules to return error so that we exit correctly
and idx is correctly maintained between skbs that are part of the
same dump.

Signed-off-by: Wilson Kok <wkok@cumulusnetworks.com>
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/fib_rules.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 9a12668..0ad144f 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -615,15 +615,17 @@ static int dump_rules(struct sk_buff *skb, struct netlink_callback *cb,
 {
 	int idx = 0;
 	struct fib_rule *rule;
+	int err = 0;
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(rule, &ops->rules_list, list) {
 		if (idx < cb->args[1])
 			goto skip;
 
-		if (fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid,
-				     cb->nlh->nlmsg_seq, RTM_NEWRULE,
-				     NLM_F_MULTI, ops) < 0)
+		err = fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid,
+				       cb->nlh->nlmsg_seq, RTM_NEWRULE,
+				       NLM_F_MULTI, ops);
+		if (err)
 			break;
 skip:
 		idx++;
@@ -632,7 +634,7 @@ skip:
 	cb->args[1] = idx;
 	rules_ops_put(ops);
 
-	return skb->len;
+	return err;
 }
 
 static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb)
@@ -648,7 +650,9 @@ static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb)
 		if (ops == NULL)
 			return -EAFNOSUPPORT;
 
-		return dump_rules(skb, cb, ops);
+		dump_rules(skb, cb, ops);
+
+		return skb->len;
 	}
 
 	rcu_read_lock();
-- 
2.1.0


From e3dc378e623e1a12f3ff19e19310b7b8571b910a Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Thu, 24 Sep 2015 12:54:01 +0200
Subject: [PATCH 25/30] ppp: fix lockdep splat in ppp_dev_uninit()

[ Upstream commit 58a89ecaca53736aa465170530acea4f8be34ab4 ]

ppp_dev_uninit() locks all_ppp_mutex while under rtnl mutex protection.
ppp_create_interface() must then lock these mutexes in that same order
to avoid possible deadlock.

[  120.880011] ======================================================
[  120.880011] [ INFO: possible circular locking dependency detected ]
[  120.880011] 4.2.0 #1 Not tainted
[  120.880011] -------------------------------------------------------
[  120.880011] ppp-apitest/15827 is trying to acquire lock:
[  120.880011]  (&pn->all_ppp_mutex){+.+.+.}, at: [<ffffffffa0145f56>] ppp_dev_uninit+0x64/0xb0 [ppp_generic]
[  120.880011]
[  120.880011] but task is already holding lock:
[  120.880011]  (rtnl_mutex){+.+.+.}, at: [<ffffffff812e4255>] rtnl_lock+0x12/0x14
[  120.880011]
[  120.880011] which lock already depends on the new lock.
[  120.880011]
[  120.880011]
[  120.880011] the existing dependency chain (in reverse order) is:
[  120.880011]
[  120.880011] -> #1 (rtnl_mutex){+.+.+.}:
[  120.880011]        [<ffffffff81073a6f>] lock_acquire+0xcf/0x10e
[  120.880011]        [<ffffffff813ab18a>] mutex_lock_nested+0x56/0x341
[  120.880011]        [<ffffffff812e4255>] rtnl_lock+0x12/0x14
[  120.880011]        [<ffffffff812d9d94>] register_netdev+0x11/0x27
[  120.880011]        [<ffffffffa0147b17>] ppp_ioctl+0x289/0xc98 [ppp_generic]
[  120.880011]        [<ffffffff8113b367>] do_vfs_ioctl+0x4ea/0x532
[  120.880011]        [<ffffffff8113b3fd>] SyS_ioctl+0x4e/0x7d
[  120.880011]        [<ffffffff813ad7d7>] entry_SYSCALL_64_fastpath+0x12/0x6f
[  120.880011]
[  120.880011] -> #0 (&pn->all_ppp_mutex){+.+.+.}:
[  120.880011]        [<ffffffff8107334e>] __lock_acquire+0xb07/0xe76
[  120.880011]        [<ffffffff81073a6f>] lock_acquire+0xcf/0x10e
[  120.880011]        [<ffffffff813ab18a>] mutex_lock_nested+0x56/0x341
[  120.880011]        [<ffffffffa0145f56>] ppp_dev_uninit+0x64/0xb0 [ppp_generic]
[  120.880011]        [<ffffffff812d5263>] rollback_registered_many+0x19e/0x252
[  120.880011]        [<ffffffff812d5381>] rollback_registered+0x29/0x38
[  120.880011]        [<ffffffff812d53fa>] unregister_netdevice_queue+0x6a/0x77
[  120.880011]        [<ffffffffa0146a94>] ppp_release+0x42/0x79 [ppp_generic]
[  120.880011]        [<ffffffff8112d9f6>] __fput+0xec/0x192
[  120.880011]        [<ffffffff8112dacc>] ____fput+0x9/0xb
[  120.880011]        [<ffffffff8105447a>] task_work_run+0x66/0x80
[  120.880011]        [<ffffffff81001801>] prepare_exit_to_usermode+0x8c/0xa7
[  120.880011]        [<ffffffff81001900>] syscall_return_slowpath+0xe4/0x104
[  120.880011]        [<ffffffff813ad931>] int_ret_from_sys_call+0x25/0x9f
[  120.880011]
[  120.880011] other info that might help us debug this:
[  120.880011]
[  120.880011]  Possible unsafe locking scenario:
[  120.880011]
[  120.880011]        CPU0                    CPU1
[  120.880011]        ----                    ----
[  120.880011]   lock(rtnl_mutex);
[  120.880011]                                lock(&pn->all_ppp_mutex);
[  120.880011]                                lock(rtnl_mutex);
[  120.880011]   lock(&pn->all_ppp_mutex);
[  120.880011]
[  120.880011]  *** DEADLOCK ***

Fixes: 8cb775bc0a34 ("ppp: fix device unregistration upon netns deletion")
Reported-by: Sedat Dilek <sedat.dilek@gmail.com>
Tested-by: Sedat Dilek <sedat.dilek@gmail.com>
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/ppp_generic.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index fa8f504..487be20 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -2742,6 +2742,7 @@ static struct ppp *ppp_create_interface(struct net *net, int unit,
 	 */
 	dev_net_set(dev, net);
 
+	rtnl_lock();
 	mutex_lock(&pn->all_ppp_mutex);
 
 	if (unit < 0) {
@@ -2772,7 +2773,7 @@ static struct ppp *ppp_create_interface(struct net *net, int unit,
 	ppp->file.index = unit;
 	sprintf(dev->name, "ppp%d", unit);
 
-	ret = register_netdev(dev);
+	ret = register_netdevice(dev);
 	if (ret != 0) {
 		unit_put(&pn->units_idr, unit);
 		netdev_err(ppp->dev, "PPP: couldn't register device %s (%d)\n",
@@ -2784,6 +2785,7 @@ static struct ppp *ppp_create_interface(struct net *net, int unit,
 
 	atomic_inc(&ppp_unit_count);
 	mutex_unlock(&pn->all_ppp_mutex);
+	rtnl_unlock();
 
 	*retp = 0;
 	return ppp;
-- 
2.1.0


From d82d92e35535ebaafef4bad60493d1e2873fd7a9 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Mon, 20 Jul 2015 17:49:55 -0700
Subject: [PATCH 26/30] net: dsa: bcm_sf2: Do not override speed settings

[ Upstream d2eac98f7d1b950b762a7eca05a9ce0ea1d878d2 in net-next tree,
  will be pushed to Linus very soon. ]

The SF2 driver currently overrides speed settings for its port
configured using a fixed PHY, this is both unnecessary and incorrect,
because we keep feedback to the hardware parameters that we read from
the PHY device, which in the case of a fixed PHY cannot possibly change
speed.

This is a required change to allow the fixed PHY code to allow
registering a PHY with a link configured as DOWN by default and avoid
some sort of circular dependency where we require the link_update
callback to run to program the hardware, and we then utilize the fixed
PHY parameters to program the hardware with the same settings.

Fixes: 246d7f773c13 ("net: dsa: add Broadcom SF2 switch driver")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2.c | 18 +-----------------
 1 file changed, 1 insertion(+), 17 deletions(-)

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 691caea..9d56515 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -905,15 +905,11 @@ static void bcm_sf2_sw_fixed_link_update(struct dsa_switch *ds, int port,
 					 struct fixed_phy_status *status)
 {
 	struct bcm_sf2_priv *priv = ds_to_priv(ds);
-	u32 duplex, pause, speed;
+	u32 duplex, pause;
 	u32 reg;
 
 	duplex = core_readl(priv, CORE_DUPSTS);
 	pause = core_readl(priv, CORE_PAUSESTS);
-	speed = core_readl(priv, CORE_SPDSTS);
-
-	speed >>= (port * SPDSTS_SHIFT);
-	speed &= SPDSTS_MASK;
 
 	status->link = 0;
 
@@ -948,18 +944,6 @@ static void bcm_sf2_sw_fixed_link_update(struct dsa_switch *ds, int port,
 		reg &= ~LINK_STS;
 	core_writel(priv, reg, CORE_STS_OVERRIDE_GMIIP_PORT(port));
 
-	switch (speed) {
-	case SPDSTS_10:
-		status->speed = SPEED_10;
-		break;
-	case SPDSTS_100:
-		status->speed = SPEED_100;
-		break;
-	case SPDSTS_1000:
-		status->speed = SPEED_1000;
-		break;
-	}
-
 	if ((pause & (1 << port)) &&
 	    (pause & (1 << (port + PAUSESTS_TX_PAUSE_SHIFT)))) {
 		status->asym_pause = 1;
-- 
2.1.0


From 7b3713db16ac51ad80d855bb96dddf44e77df24d Mon Sep 17 00:00:00 2001
From: Stas Sergeev <stsp@list.ru>
Date: Mon, 20 Jul 2015 17:49:56 -0700
Subject: [PATCH 27/30] net: phy: fixed_phy: handle link-down case

[ Upstream 868a4215be9a6d80548ccb74763b883dc99d32a2 in net-next tree,
  will be pushed to Linus very soon. ]

fixed_phy_register() currently hardcodes the fixed PHY link to 1, and
expects to find a "speed" parameter to provide correct information
towards the fixed PHY consumer.

In a subsequent change, where we allow "managed" (e.g: (RS)GMII in-band
status auto-negotiation) fixed PHYs, none of these parameters can be
provided since they will be auto-negotiated, hence, we just provide a
zero-initialized fixed_phy_status to fixed_phy_register() which makes it
fail when we call fixed_phy_update_regs() since status.speed = 0 which
makes us hit the "default" label and error out.

Without this change, we would also see potentially inconsistent
speed/duplex parameters for fixed PHYs when the link is DOWN.

CC: netdev@vger.kernel.org
CC: linux-kernel@vger.kernel.org
Signed-off-by: Stas Sergeev <stsp@users.sourceforge.net>
[florian: add more background to why this is correct and desirable]
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/fixed_phy.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c
index d7a6524..99d9bc1 100644
--- a/drivers/net/phy/fixed_phy.c
+++ b/drivers/net/phy/fixed_phy.c
@@ -52,6 +52,10 @@ static int fixed_phy_update_regs(struct fixed_phy *fp)
 	u16 lpagb = 0;
 	u16 lpa = 0;
 
+	if (!fp->status.link)
+		goto done;
+	bmsr |= BMSR_LSTATUS | BMSR_ANEGCOMPLETE;
+
 	if (fp->status.duplex) {
 		bmcr |= BMCR_FULLDPLX;
 
@@ -96,15 +100,13 @@ static int fixed_phy_update_regs(struct fixed_phy *fp)
 		}
 	}
 
-	if (fp->status.link)
-		bmsr |= BMSR_LSTATUS | BMSR_ANEGCOMPLETE;
-
 	if (fp->status.pause)
 		lpa |= LPA_PAUSE_CAP;
 
 	if (fp->status.asym_pause)
 		lpa |= LPA_PAUSE_ASYM;
 
+done:
 	fp->regs[MII_PHYSID1] = 0;
 	fp->regs[MII_PHYSID2] = 0;
 
-- 
2.1.0


From dec98dd4bf6107f1de79668119a3434ff12b04e4 Mon Sep 17 00:00:00 2001
From: Stas Sergeev <stsp@list.ru>
Date: Mon, 20 Jul 2015 17:49:57 -0700
Subject: [PATCH 28/30] of_mdio: add new DT property 'managed' to specify the
 PHY management type

[ Upstream commit 4cba5c2103657d43d0886e4cff8004d95a3d0def in net-next tree,
  will be pushed to Linus very soon. ]

Currently the PHY management type is selected by the MAC driver arbitrary.
The decision is based on the presence of the "fixed-link" node and on a
will of the driver's authors.
This caused a regression recently, when mvneta driver suddenly started
to use the in-band status for auto-negotiation on fixed links.
It appears the auto-negotiation may not work when expected by the MAC driver.
Sebastien Rannou explains:
<< Yes, I confirm that my HW does not generate an in-band status. AFAIK, it's
a PHY that aggregates 4xSGMIIs to 1xQSGMII ; the MAC side of the PHY (with
inband status) is connected to the switch through QSGMII, and in this context
we are on the media side of the PHY. >>
https://lkml.org/lkml/2015/7/10/206

This patch introduces the new string property 'managed' that allows
the user to set the management type explicitly.
The supported values are:
"auto" - default. Uses either MDIO or nothing, depending on the presence
of the fixed-link node
"in-band-status" - use in-band status

Signed-off-by: Stas Sergeev <stsp@users.sourceforge.net>

CC: Rob Herring <robh+dt@kernel.org>
CC: Pawel Moll <pawel.moll@arm.com>
CC: Mark Rutland <mark.rutland@arm.com>
CC: Ian Campbell <ijc+devicetree@hellion.org.uk>
CC: Kumar Gala <galak@codeaurora.org>
CC: Florian Fainelli <f.fainelli@gmail.com>
CC: Grant Likely <grant.likely@linaro.org>
CC: devicetree@vger.kernel.org
CC: linux-kernel@vger.kernel.org
CC: netdev@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/devicetree/bindings/net/ethernet.txt |  4 ++++
 drivers/of/of_mdio.c                               | 19 +++++++++++++++++--
 2 files changed, 21 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/ethernet.txt b/Documentation/devicetree/bindings/net/ethernet.txt
index 41b3f3f..5d88f37 100644
--- a/Documentation/devicetree/bindings/net/ethernet.txt
+++ b/Documentation/devicetree/bindings/net/ethernet.txt
@@ -25,7 +25,11 @@ The following properties are common to the Ethernet controllers:
   flow control thresholds.
 - tx-fifo-depth: the size of the controller's transmit fifo in bytes. This
   is used for components that can have configurable fifo sizes.
+- managed: string, specifies the PHY management type. Supported values are:
+  "auto", "in-band-status". "auto" is the default, it usess MDIO for
+  management if fixed-link is not specified.
 
 Child nodes of the Ethernet controller are typically the individual PHY devices
 connected via the MDIO bus (sometimes the MDIO bus controller is separate).
 They are described in the phy.txt file in this same directory.
+For non-MDIO PHY management see fixed-link.txt.
diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c
index fdc60db..7c8c23c 100644
--- a/drivers/of/of_mdio.c
+++ b/drivers/of/of_mdio.c
@@ -266,7 +266,8 @@ EXPORT_SYMBOL(of_phy_attach);
 bool of_phy_is_fixed_link(struct device_node *np)
 {
 	struct device_node *dn;
-	int len;
+	int len, err;
+	const char *managed;
 
 	/* New binding */
 	dn = of_get_child_by_name(np, "fixed-link");
@@ -275,6 +276,10 @@ bool of_phy_is_fixed_link(struct device_node *np)
 		return true;
 	}
 
+	err = of_property_read_string(np, "managed", &managed);
+	if (err == 0 && strcmp(managed, "auto") != 0)
+		return true;
+
 	/* Old binding */
 	if (of_get_property(np, "fixed-link", &len) &&
 	    len == (5 * sizeof(__be32)))
@@ -289,8 +294,18 @@ int of_phy_register_fixed_link(struct device_node *np)
 	struct fixed_phy_status status = {};
 	struct device_node *fixed_link_node;
 	const __be32 *fixed_link_prop;
-	int len;
+	int len, err;
 	struct phy_device *phy;
+	const char *managed;
+
+	err = of_property_read_string(np, "managed", &managed);
+	if (err == 0) {
+		if (strcmp(managed, "in-band-status") == 0) {
+			/* status is zeroed, namely its .link member */
+			phy = fixed_phy_register(PHY_POLL, &status, np);
+			return IS_ERR(phy) ? PTR_ERR(phy) : 0;
+		}
+	}
 
 	/* New binding */
 	fixed_link_node = of_get_child_by_name(np, "fixed-link");
-- 
2.1.0


From d47cfb643b75954ad54341ee63369c59cd3bd670 Mon Sep 17 00:00:00 2001
From: Stas Sergeev <stsp@list.ru>
Date: Mon, 20 Jul 2015 17:49:58 -0700
Subject: [PATCH 29/30] mvneta: use inband status only when explicitly enabled

[ Upstream commit f8af8e6eb95093d5ce5ebcc52bd1929b0433e172 in net-next tree,
  will be pushed to Linus very soon. ]

The commit 898b2970e2c9 ("mvneta: implement SGMII-based in-band link state
signaling") implemented the link parameters auto-negotiation unconditionally.
Unfortunately it appears that some HW that implements SGMII protocol,
doesn't generate the inband status, so it is not possible to auto-negotiate
anything with such HW.

This patch enables the auto-negotiation only if explicitly requested with
the 'managed' DT property.

This patch fixes the following regression:
https://lkml.org/lkml/2015/7/8/865

Signed-off-by: Stas Sergeev <stsp@users.sourceforge.net>

CC: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
CC: netdev@vger.kernel.org
CC: linux-kernel@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 03e052a..09ec32e 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -3029,8 +3029,8 @@ static int mvneta_probe(struct platform_device *pdev)
 	const char *dt_mac_addr;
 	char hw_mac_addr[ETH_ALEN];
 	const char *mac_from;
+	const char *managed;
 	int phy_mode;
-	int fixed_phy = 0;
 	int err;
 
 	/* Our multiqueue support is not complete, so for now, only
@@ -3064,7 +3064,6 @@ static int mvneta_probe(struct platform_device *pdev)
 			dev_err(&pdev->dev, "cannot register fixed PHY\n");
 			goto err_free_irq;
 		}
-		fixed_phy = 1;
 
 		/* In the case of a fixed PHY, the DT node associated
 		 * to the PHY is the Ethernet MAC DT node.
@@ -3088,8 +3087,10 @@ static int mvneta_probe(struct platform_device *pdev)
 	pp = netdev_priv(dev);
 	pp->phy_node = phy_node;
 	pp->phy_interface = phy_mode;
-	pp->use_inband_status = (phy_mode == PHY_INTERFACE_MODE_SGMII) &&
-				fixed_phy;
+
+	err = of_property_read_string(dn, "managed", &managed);
+	pp->use_inband_status = (err == 0 &&
+				 strcmp(managed, "in-band-status") == 0);
 
 	pp->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(pp->clk)) {
-- 
2.1.0


From a80c11e7e00b9cfacb5d0ff49404636c9b114082 Mon Sep 17 00:00:00 2001
From: Carol L Soto <clsoto@linux.vnet.ibm.com>
Date: Thu, 27 Aug 2015 14:43:25 -0500
Subject: [PATCH 30/30] net/mlx4_core: Capping number of requested MSIXs to
 MAX_MSIX

[ Upstream commit 9293267a3e2a7a2555d8ddc8f9301525e5b03b1b ]

We currently manage IRQs in pool_bm which is a bit field
of MAX_MSIX bits. Thus, allocating more than MAX_MSIX
interrupts can't be managed in pool_bm.
Fixing this by capping number of requested MSIXs to
MAX_MSIX.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Carol L Soto <clsoto@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/main.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 29c2a01..a408977 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -2654,9 +2654,14 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev)
 
 	if (msi_x) {
 		int nreq = dev->caps.num_ports * num_online_cpus() + 1;
+		bool shared_ports = false;
 
 		nreq = min_t(int, dev->caps.num_eqs - dev->caps.reserved_eqs,
 			     nreq);
+		if (nreq > MAX_MSIX) {
+			nreq = MAX_MSIX;
+			shared_ports = true;
+		}
 
 		entries = kcalloc(nreq, sizeof *entries, GFP_KERNEL);
 		if (!entries)
@@ -2679,6 +2684,9 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev)
 		bitmap_zero(priv->eq_table.eq[MLX4_EQ_ASYNC].actv_ports.ports,
 			    dev->caps.num_ports);
 
+		if (MLX4_IS_LEGACY_EQ_MODE(dev->caps))
+			shared_ports = true;
+
 		for (i = 0; i < dev->caps.num_comp_vectors + 1; i++) {
 			if (i == MLX4_EQ_ASYNC)
 				continue;
@@ -2686,7 +2694,7 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev)
 			priv->eq_table.eq[i].irq =
 				entries[i + 1 - !!(i > MLX4_EQ_ASYNC)].vector;
 
-			if (MLX4_IS_LEGACY_EQ_MODE(dev->caps)) {
+			if (shared_ports) {
 				bitmap_fill(priv->eq_table.eq[i].actv_ports.ports,
 					    dev->caps.num_ports);
 				/* We don't set affinity hint when there
-- 
2.1.0

Re: [PATCHES] Networking

[Greg KH]

On Mon, Sep 28, 2015 at 09:54:08PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v3.14, v3.18,
> v4.1, and v4.2 -stable, respectively.

ALl now queued up for 3.14, 4.1, and 4.2, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 113 bytes --]


Please queue up the following networking bug fixes for 3.14, 3.18, 4.1,
and 4.2 -stable, respectively.

Thanks!

[-- Attachment #2: net_314.mbox --]
[-- Type: Application/Octet-Stream, Size: 22500 bytes --]

From 0f454ae2609f3008ed33b9330a502f5737a9b263 Mon Sep 17 00:00:00 2001
From: Alexander Couzens <lynxis@fe80.eu>
Date: Mon, 28 Sep 2015 11:32:42 +0200
Subject: [PATCH 01/11] l2tp: protect tunnel->del_work by ref_count

[ Upstream commit 06a15f51cf3618e32a73871ee6a547ef7fd902b5 ]

There is a small chance that tunnel_free() is called before tunnel->del_work scheduled
resulting in a zero pointer dereference.

Signed-off-by: Alexander Couzens <lynxis@fe80.eu>
Acked-by: James Chapman <jchapman@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c |   11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 85d9d94..3679bd6 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1435,7 +1435,7 @@ static void l2tp_tunnel_del_work(struct work_struct *work)
 	tunnel = container_of(work, struct l2tp_tunnel, del_work);
 	sk = l2tp_tunnel_sock_lookup(tunnel);
 	if (!sk)
-		return;
+		goto out;
 
 	sock = sk->sk_socket;
 
@@ -1456,6 +1456,8 @@ static void l2tp_tunnel_del_work(struct work_struct *work)
 	}
 
 	l2tp_tunnel_sock_put(sk);
+out:
+	l2tp_tunnel_dec_refcount(tunnel);
 }
 
 /* Create a socket for the tunnel, if one isn't set up by
@@ -1785,8 +1787,13 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_create);
  */
 int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel)
 {
+	l2tp_tunnel_inc_refcount(tunnel);
 	l2tp_tunnel_closeall(tunnel);
-	return (false == queue_work(l2tp_wq, &tunnel->del_work));
+	if (false == queue_work(l2tp_wq, &tunnel->del_work)) {
+		l2tp_tunnel_dec_refcount(tunnel);
+		return 1;
+	}
+	return 0;
 }
 EXPORT_SYMBOL_GPL(l2tp_tunnel_delete);
 
-- 
1.7.10.4


From 43831e267880844c1ee627049073cb82a8082c47 Mon Sep 17 00:00:00 2001
From: Aaron Conole <aconole@bytheb.org>
Date: Sat, 26 Sep 2015 18:50:42 -0400
Subject: [PATCH 02/11] af_unix: Convert the unix_sk macro to an inline
 function for type safety

[ Upstream commit 4613012db1d911f80897f9446a49de817b2c4c47 ]

As suggested by Eric Dumazet this change replaces the
#define with a static inline function to enjoy
complaints by the compiler when misusing the API.

Signed-off-by: Aaron Conole <aconole@bytheb.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/af_unix.h |    6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index a175ba4..dfe4ddf 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -64,7 +64,11 @@ struct unix_sock {
 #define UNIX_GC_MAYBE_CYCLE	1
 	struct socket_wq	peer_wq;
 };
-#define unix_sk(__sk) ((struct unix_sock *)__sk)
+
+static inline struct unix_sock *unix_sk(struct sock *sk)
+{
+	return (struct unix_sock *)sk;
+}
 
 #define peer_wait peer_wq.wait
 
-- 
1.7.10.4


From db633e0d3684b515c52673c33093bfa7446d3b36 Mon Sep 17 00:00:00 2001
From: Aaron Conole <aconole@bytheb.org>
Date: Sat, 26 Sep 2015 18:50:43 -0400
Subject: [PATCH 03/11] af_unix: return data from multiple SKBs on recv() with
 MSG_PEEK flag

[ Upstream commit 9f389e35674f5b086edd70ed524ca0f287259725 ]

AF_UNIX sockets now return multiple skbs from recv() when MSG_PEEK flag
is set.

This is referenced in kernel bugzilla #12323 @
https://bugzilla.kernel.org/show_bug.cgi?id=12323

As described both in the BZ and lkml thread @
http://lkml.org/lkml/2008/1/8/444 calling recv() with MSG_PEEK on an
AF_UNIX socket only reads a single skb, where the desired effect is
to return as much skb data has been queued, until hitting the recv
buffer size (whichever comes first).

The modified MSG_PEEK path will now move to the next skb in the tree
and jump to the again: label, rather than following the natural loop
structure. This requires duplicating some of the loop head actions.

This was tested using the python socketpair python code attached to
the bugzilla issue.

Signed-off-by: Aaron Conole <aconole@bytheb.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c |   14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 4757f1c..7c7c19d 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2064,8 +2064,20 @@ again:
 			if (UNIXCB(skb).fp)
 				siocb->scm->fp = scm_fp_dup(UNIXCB(skb).fp);
 
-			sk_peek_offset_fwd(sk, chunk);
+			if (skip) {
+				sk_peek_offset_fwd(sk, chunk);
+				skip -= chunk;
+			}
+
+			if (UNIXCB(skb).fp)
+				break;
 
+			last = skb;
+			unix_state_lock(sk);
+			skb = skb_peek_next(skb, &sk->sk_receive_queue);
+			if (skb)
+				goto again;
+			unix_state_unlock(sk);
 			break;
 		}
 	} while (size);
-- 
1.7.10.4


From 32b32540d4f7ff9f7aac0f9fd2de78b58b6d47fd Mon Sep 17 00:00:00 2001
From: Andrey Vagin <avagin@openvz.org>
Date: Fri, 2 Oct 2015 00:05:36 +0300
Subject: [PATCH 04/11] net/unix: fix logic about sk_peek_offset

[ Upstream commit e9193d60d363e4dff75ff6d43a48f22be26d59c7 ]

Now send with MSG_PEEK can return data from multiple SKBs.

Unfortunately we take into account the peek offset for each skb,
that is wrong. We need to apply the peek offset only once.

In addition, the peek offset should be used only if MSG_PEEK is set.

Cc: "David S. Miller" <davem@davemloft.net> (maintainer:NETWORKING
Cc: Eric Dumazet <edumazet@google.com> (commit_signer:1/14=7%)
Cc: Aaron Conole <aconole@bytheb.org>
Fixes: 9f389e35674f ("af_unix: return data from multiple SKBs on recv() with MSG_PEEK flag")
Signed-off-by: Andrey Vagin <avagin@openvz.org>
Tested-by: Aaron Conole <aconole@bytheb.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c |   12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 7c7c19d..4affedb 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1956,6 +1956,11 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 		goto out;
 	}
 
+	if (flags & MSG_PEEK)
+		skip = sk_peek_offset(sk, flags);
+	else
+		skip = 0;
+
 	do {
 		int chunk;
 		struct sk_buff *skb, *last;
@@ -2002,7 +2007,6 @@ again:
 			break;
 		}
 
-		skip = sk_peek_offset(sk, flags);
 		while (skip >= unix_skb_len(skb)) {
 			skip -= unix_skb_len(skb);
 			last = skb;
@@ -2064,14 +2068,12 @@ again:
 			if (UNIXCB(skb).fp)
 				siocb->scm->fp = scm_fp_dup(UNIXCB(skb).fp);
 
-			if (skip) {
-				sk_peek_offset_fwd(sk, chunk);
-				skip -= chunk;
-			}
+			sk_peek_offset_fwd(sk, chunk);
 
 			if (UNIXCB(skb).fp)
 				break;
 
+			skip = 0;
 			last = skb;
 			unix_state_lock(sk);
 			skb = skb_peek_next(skb, &sk->sk_receive_queue);
-- 
1.7.10.4


From 34c90af59caf72880708240448835f42e5049e71 Mon Sep 17 00:00:00 2001
From: Pravin B Shelar <pshelar@nicira.com>
Date: Tue, 22 Sep 2015 12:57:53 -0700
Subject: [PATCH 05/11] skbuff: Fix skb checksum flag on skb pull

[ Upstream commit 6ae459bdaaeebc632b16e54dcbabb490c6931d61 ]

VXLAN device can receive skb with checksum partial. But the checksum
offset could be in outer header which is pulled on receive. This results
in negative checksum offset for the skb. Such skb can cause the assert
failure in skb_checksum_help(). Following patch fixes the bug by setting
checksum-none while pulling outer header.

Following is the kernel panic msg from old kernel hitting the bug.

------------[ cut here ]------------
kernel BUG at net/core/dev.c:1906!
RIP: 0010:[<ffffffff81518034>] skb_checksum_help+0x144/0x150
Call Trace:
<IRQ>
[<ffffffffa0164c28>] queue_userspace_packet+0x408/0x470 [openvswitch]
[<ffffffffa016614d>] ovs_dp_upcall+0x5d/0x60 [openvswitch]
[<ffffffffa0166236>] ovs_dp_process_packet_with_key+0xe6/0x100 [openvswitch]
[<ffffffffa016629b>] ovs_dp_process_received_packet+0x4b/0x80 [openvswitch]
[<ffffffffa016c51a>] ovs_vport_receive+0x2a/0x30 [openvswitch]
[<ffffffffa0171383>] vxlan_rcv+0x53/0x60 [openvswitch]
[<ffffffffa01734cb>] vxlan_udp_encap_recv+0x8b/0xf0 [openvswitch]
[<ffffffff8157addc>] udp_queue_rcv_skb+0x2dc/0x3b0
[<ffffffff8157b56f>] __udp4_lib_rcv+0x1cf/0x6c0
[<ffffffff8157ba7a>] udp_rcv+0x1a/0x20
[<ffffffff8154fdbd>] ip_local_deliver_finish+0xdd/0x280
[<ffffffff81550128>] ip_local_deliver+0x88/0x90
[<ffffffff8154fa7d>] ip_rcv_finish+0x10d/0x370
[<ffffffff81550365>] ip_rcv+0x235/0x300
[<ffffffff8151ba1d>] __netif_receive_skb+0x55d/0x620
[<ffffffff8151c360>] netif_receive_skb+0x80/0x90
[<ffffffff81459935>] virtnet_poll+0x555/0x6f0
[<ffffffff8151cd04>] net_rx_action+0x134/0x290
[<ffffffff810683d8>] __do_softirq+0xa8/0x210
[<ffffffff8162fe6c>] call_softirq+0x1c/0x30
[<ffffffff810161a5>] do_softirq+0x65/0xa0
[<ffffffff810687be>] irq_exit+0x8e/0xb0
[<ffffffff81630733>] do_IRQ+0x63/0xe0
[<ffffffff81625f2e>] common_interrupt+0x6e/0x6e

Reported-by: Anupam Chanda <achanda@vmware.com>
Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
Acked-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h |    3 +++
 1 file changed, 3 insertions(+)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index ab31337..fa9d612 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2347,6 +2347,9 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb,
 {
 	if (skb->ip_summed == CHECKSUM_COMPLETE)
 		skb->csum = csum_sub(skb->csum, csum_partial(start, len, 0));
+	else if (skb->ip_summed == CHECKSUM_PARTIAL &&
+		 skb_checksum_start_offset(skb) <= len)
+		skb->ip_summed = CHECKSUM_NONE;
 }
 
 unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len);
-- 
1.7.10.4


From cea16ceb6b47d0ece3691bcdb5e5cbd090d06b4e Mon Sep 17 00:00:00 2001
From: Pravin B Shelar <pshelar@nicira.com>
Date: Mon, 28 Sep 2015 17:24:25 -0700
Subject: [PATCH 06/11] skbuff: Fix skb checksum partial check.

[ Upstream commit 31b33dfb0a144469dd805514c9e63f4993729a48 ]

Earlier patch 6ae459bda tried to detect void ckecksum partial
skb by comparing pull length to checksum offset. But it does
not work for all cases since checksum-offset depends on
updates to skb->data.

Following patch fixes it by validating checksum start offset
after skb-data pointer is updated. Negative value of checksum
offset start means there is no need to checksum.

Fixes: 6ae459bda ("skbuff: Fix skb checksum flag on skb pull")
Reported-by: Andrew Vagin <avagin@odin.com>
Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h |    2 +-
 net/core/skbuff.c      |    9 +++++----
 2 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index fa9d612..d8bec47 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2348,7 +2348,7 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb,
 	if (skb->ip_summed == CHECKSUM_COMPLETE)
 		skb->csum = csum_sub(skb->csum, csum_partial(start, len, 0));
 	else if (skb->ip_summed == CHECKSUM_PARTIAL &&
-		 skb_checksum_start_offset(skb) <= len)
+		 skb_checksum_start_offset(skb) < 0)
 		skb->ip_summed = CHECKSUM_NONE;
 }
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 8207f8d..366f7ff 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2862,11 +2862,12 @@ EXPORT_SYMBOL(skb_append_datato_frags);
  */
 unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len)
 {
+	unsigned char *data = skb->data;
+
 	BUG_ON(len > skb->len);
-	skb->len -= len;
-	BUG_ON(skb->len < skb->data_len);
-	skb_postpull_rcsum(skb, skb->data, len);
-	return skb->data += len;
+	__skb_pull(skb, len);
+	skb_postpull_rcsum(skb, data, len);
+	return skb->data;
 }
 EXPORT_SYMBOL_GPL(skb_pull_rcsum);
 
-- 
1.7.10.4


From 64680967401557d6432ad2a92f1aba512cb6c2a3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 29 Sep 2015 18:52:25 -0700
Subject: [PATCH 07/11] net: add pfmemalloc check in sk_add_backlog()

[ Upstream commit c7c49b8fde26b74277188bdc6c9dca38db6fa35b ]

Greg reported crashes hitting the following check in __sk_backlog_rcv()

	BUG_ON(!sock_flag(sk, SOCK_MEMALLOC));

The pfmemalloc bit is currently checked in sk_filter().

This works correctly for TCP, because sk_filter() is ran in
tcp_v[46]_rcv() before hitting the prequeue or backlog checks.

For UDP or other protocols, this does not work, because the sk_filter()
is ran from sock_queue_rcv_skb(), which might be called _after_ backlog
queuing if socket is owned by user by the time packet is processed by
softirq handler.

Fixes: b4b9e35585089 ("netvm: set PF_MEMALLOC as appropriate during SKB processing")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Greg Thelen <gthelen@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h |    8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/include/net/sock.h b/include/net/sock.h
index 0c79a74..ff4f825 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -805,6 +805,14 @@ static inline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *s
 	if (sk_rcvqueues_full(sk, skb, limit))
 		return -ENOBUFS;
 
+	/*
+	 * If the skb was allocated from pfmemalloc reserves, only
+	 * allow SOCK_MEMALLOC sockets to use it as this socket is
+	 * helping free memory
+	 */
+	if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC))
+		return -ENOMEM;
+
 	__sk_add_backlog(sk, skb);
 	sk->sk_backlog.len += skb->truesize;
 	return 0;
-- 
1.7.10.4


From 5a0fa430bfe636ecfa662185b283b8dd3c5f234a Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Wed, 30 Sep 2015 11:45:33 +0200
Subject: [PATCH 08/11] ppp: don't override sk->sk_state in pppoe_flush_dev()

[ Upstream commit e6740165b8f7f06d8caee0fceab3fb9d790a6fed ]

Since commit 2b018d57ff18 ("pppoe: drop PPPOX_ZOMBIEs in pppoe_release"),
pppoe_release() calls dev_put(po->pppoe_dev) if sk is in the
PPPOX_ZOMBIE state. But pppoe_flush_dev() can set sk->sk_state to
PPPOX_ZOMBIE _and_ reset po->pppoe_dev to NULL. This leads to the
following oops:

[  570.140800] BUG: unable to handle kernel NULL pointer dereference at 00000000000004e0
[  570.142931] IP: [<ffffffffa018c701>] pppoe_release+0x50/0x101 [pppoe]
[  570.144601] PGD 3d119067 PUD 3dbc1067 PMD 0
[  570.144601] Oops: 0000 [#1] SMP
[  570.144601] Modules linked in: l2tp_ppp l2tp_netlink l2tp_core ip6_udp_tunnel udp_tunnel pppoe pppox ppp_generic slhc loop crc32c_intel ghash_clmulni_intel jitterentropy_rng sha256_generic hmac drbg ansi_cprng aesni_intel aes_x86_64 ablk_helper cryptd lrw gf128mul glue_helper acpi_cpufreq evdev serio_raw processor button ext4 crc16 mbcache jbd2 virtio_net virtio_blk virtio_pci virtio_ring virtio
[  570.144601] CPU: 1 PID: 15738 Comm: ppp-apitest Not tainted 4.2.0 #1
[  570.144601] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Debian-1.8.2-1 04/01/2014
[  570.144601] task: ffff88003d30d600 ti: ffff880036b60000 task.ti: ffff880036b60000
[  570.144601] RIP: 0010:[<ffffffffa018c701>]  [<ffffffffa018c701>] pppoe_release+0x50/0x101 [pppoe]
[  570.144601] RSP: 0018:ffff880036b63e08  EFLAGS: 00010202
[  570.144601] RAX: 0000000000000000 RBX: ffff880034340000 RCX: 0000000000000206
[  570.144601] RDX: 0000000000000006 RSI: ffff88003d30dd20 RDI: ffff88003d30dd20
[  570.144601] RBP: ffff880036b63e28 R08: 0000000000000001 R09: 0000000000000000
[  570.144601] R10: 00007ffee9b50420 R11: ffff880034340078 R12: ffff8800387ec780
[  570.144601] R13: ffff8800387ec7b0 R14: ffff88003e222aa0 R15: ffff8800387ec7b0
[  570.144601] FS:  00007f5672f48700(0000) GS:ffff88003fc80000(0000) knlGS:0000000000000000
[  570.144601] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  570.144601] CR2: 00000000000004e0 CR3: 0000000037f7e000 CR4: 00000000000406a0
[  570.144601] Stack:
[  570.144601]  ffffffffa018f240 ffff8800387ec780 ffffffffa018f240 ffff8800387ec7b0
[  570.144601]  ffff880036b63e48 ffffffff812caabe ffff880039e4e000 0000000000000008
[  570.144601]  ffff880036b63e58 ffffffff812cabad ffff880036b63ea8 ffffffff811347f5
[  570.144601] Call Trace:
[  570.144601]  [<ffffffff812caabe>] sock_release+0x1a/0x75
[  570.144601]  [<ffffffff812cabad>] sock_close+0xd/0x11
[  570.144601]  [<ffffffff811347f5>] __fput+0xff/0x1a5
[  570.144601]  [<ffffffff811348cb>] ____fput+0x9/0xb
[  570.144601]  [<ffffffff81056682>] task_work_run+0x66/0x90
[  570.144601]  [<ffffffff8100189e>] prepare_exit_to_usermode+0x8c/0xa7
[  570.144601]  [<ffffffff81001a26>] syscall_return_slowpath+0x16d/0x19b
[  570.144601]  [<ffffffff813babb1>] int_ret_from_sys_call+0x25/0x9f
[  570.144601] Code: 48 8b 83 c8 01 00 00 a8 01 74 12 48 89 df e8 8b 27 14 e1 b8 f7 ff ff ff e9 b7 00 00 00 8a 43 12 a8 0b 74 1c 48 8b 83 a8 04 00 00 <48> 8b 80 e0 04 00 00 65 ff 08 48 c7 83 a8 04 00 00 00 00 00 00
[  570.144601] RIP  [<ffffffffa018c701>] pppoe_release+0x50/0x101 [pppoe]
[  570.144601]  RSP <ffff880036b63e08>
[  570.144601] CR2: 00000000000004e0
[  570.200518] ---[ end trace 46956baf17349563 ]---

pppoe_flush_dev() has no reason to override sk->sk_state with
PPPOX_ZOMBIE. pppox_unbind_sock() already sets sk->sk_state to
PPPOX_DEAD, which is the correct state given that sk is unbound and
po->pppoe_dev is NULL.

Fixes: 2b018d57ff18 ("pppoe: drop PPPOX_ZOMBIEs in pppoe_release")
Tested-by: Oleksii Berezhniak <core@irc.lg.ua>
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pppoe.c |    1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 6c9c16d..f606b5b 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -313,7 +313,6 @@ static void pppoe_flush_dev(struct net_device *dev)
 			if (po->pppoe_dev == dev &&
 			    sk->sk_state & (PPPOX_CONNECTED | PPPOX_BOUND | PPPOX_ZOMBIE)) {
 				pppox_unbind_sock(sk);
-				sk->sk_state = PPPOX_ZOMBIE;
 				sk->sk_state_change(sk);
 				po->pppoe_dev = NULL;
 				dev_put(dev);
-- 
1.7.10.4


From f210707c3390550adf050dc1de8d757f3dc53b4b Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Wed, 14 Oct 2015 01:09:40 -0700
Subject: [PATCH 09/11] ethtool: Use kcalloc instead of kmalloc for
 ethtool_get_strings

[ Upstream commit 077cb37fcf6f00a45f375161200b5ee0cd4e937b ]

It seems that kernel memory can leak into userspace by a
kmalloc, ethtool_get_strings, then copy_to_user sequence.

Avoid this by using kcalloc to zero fill the copied buffer.

Signed-off-by: Joe Perches <joe@perches.com>
Acked-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/ethtool.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 30071de..0b39ab6 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -1080,7 +1080,7 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr)
 
 	gstrings.len = ret;
 
-	data = kmalloc(gstrings.len * ETH_GSTRING_LEN, GFP_USER);
+	data = kcalloc(gstrings.len, ETH_GSTRING_LEN, GFP_USER);
 	if (!data)
 		return -ENOMEM;
 
-- 
1.7.10.4


From 51a584416ca3aeca30b26275e3b8dd4efd409c66 Mon Sep 17 00:00:00 2001
From: Michel Stam <m.stam@fugro.nl>
Date: Thu, 2 Oct 2014 10:22:02 +0200
Subject: [PATCH 10/11] asix: Don't reset PHY on if_up for ASIX 88772

[ Upstream commit 3cc81d85ee01e5a0b7ea2f4190e2ed1165f53c31 ]

I've noticed every time the interface is set to 'up,', the kernel
reports that the link speed is set to 100 Mbps/Full Duplex, even
when ethtool is used to set autonegotiation to 'off', half
duplex, 10 Mbps.
It can be tested by:
 ifconfig eth0 down
 ethtool -s eth0 autoneg off speed 10 duplex half
 ifconfig eth0 up

Then checking 'dmesg' for the link speed.

Signed-off-by: Michel Stam <m.stam@fugro.nl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/asix_devices.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c
index 5d19409..2c05f6c 100644
--- a/drivers/net/usb/asix_devices.c
+++ b/drivers/net/usb/asix_devices.c
@@ -890,7 +890,7 @@ static const struct driver_info ax88772_info = {
 	.unbind = ax88772_unbind,
 	.status = asix_status,
 	.link_reset = ax88772_link_reset,
-	.reset = ax88772_reset,
+	.reset = ax88772_link_reset,
 	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR | FLAG_MULTI_PACKET,
 	.rx_fixup = asix_rx_fixup_common,
 	.tx_fixup = asix_tx_fixup,
-- 
1.7.10.4


From ddb5bd995e0f9ee4e327eb9d78517b45eebd34eb Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Date: Thu, 6 Nov 2014 15:49:41 +0000
Subject: [PATCH 11/11] asix: Do full reset during ax88772_bind

[ Upstream commit 436c2a5036b6ffe813310df2cf327d3b69be0734 ]

commit 3cc81d85ee01 ("asix: Don't reset PHY on if_up for ASIX 88772")
causes the ethernet on Arndale to no longer function. This appears to
be because the Arndale ethernet requires a full reset before it will
function correctly, however simply reverting the above patch causes
problems with ethtool settings getting reset.

It seems the problem is that the ethernet is not properly reset during
bind, and indeed the code in ax88772_bind that resets the device is a
very small subset of the actual ax88772_reset function. This patch uses
ax88772_reset in place of the existing reset code in ax88772_bind which
removes some code duplication and fixes the ethernet on Arndale.

It is still possible that the original patch causes some issues with
suspend and resume but that seems like a separate issue and I haven't
had a chance to test that yet.

Signed-off-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Tested-by: Riku Voipio <riku.voipio@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/asix_devices.c |   14 +-------------
 1 file changed, 1 insertion(+), 13 deletions(-)

diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c
index 2c05f6c..816d511 100644
--- a/drivers/net/usb/asix_devices.c
+++ b/drivers/net/usb/asix_devices.c
@@ -465,19 +465,7 @@ static int ax88772_bind(struct usbnet *dev, struct usb_interface *intf)
 		return ret;
 	}
 
-	ret = asix_sw_reset(dev, AX_SWRESET_IPPD | AX_SWRESET_PRL);
-	if (ret < 0)
-		return ret;
-
-	msleep(150);
-
-	ret = asix_sw_reset(dev, AX_SWRESET_CLEAR);
-	if (ret < 0)
-		return ret;
-
-	msleep(150);
-
-	ret = asix_sw_reset(dev, embd_phy ? AX_SWRESET_IPRL : AX_SWRESET_PRTE);
+	ax88772_reset(dev);
 
 	/* Read PHYID register *AFTER* the PHY was reset properly */
 	phyid = asix_get_phyid(dev);
-- 
1.7.10.4


[-- Attachment #3: net_318.mbox --]
[-- Type: Application/Octet-Stream, Size: 24472 bytes --]

From b795b660c1ca51921243173f2b9c6a26bf16e923 Mon Sep 17 00:00:00 2001
From: Alexander Couzens <lynxis@fe80.eu>
Date: Mon, 28 Sep 2015 11:32:42 +0200
Subject: [PATCH 01/11] l2tp: protect tunnel->del_work by ref_count

[ Upstream commit 06a15f51cf3618e32a73871ee6a547ef7fd902b5 ]

There is a small chance that tunnel_free() is called before tunnel->del_work scheduled
resulting in a zero pointer dereference.

Signed-off-by: Alexander Couzens <lynxis@fe80.eu>
Acked-by: James Chapman <jchapman@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c |   11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 895348e..508154a 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1319,7 +1319,7 @@ static void l2tp_tunnel_del_work(struct work_struct *work)
 	tunnel = container_of(work, struct l2tp_tunnel, del_work);
 	sk = l2tp_tunnel_sock_lookup(tunnel);
 	if (!sk)
-		return;
+		goto out;
 
 	sock = sk->sk_socket;
 
@@ -1340,6 +1340,8 @@ static void l2tp_tunnel_del_work(struct work_struct *work)
 	}
 
 	l2tp_tunnel_sock_put(sk);
+out:
+	l2tp_tunnel_dec_refcount(tunnel);
 }
 
 /* Create a socket for the tunnel, if one isn't set up by
@@ -1639,8 +1641,13 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_create);
  */
 int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel)
 {
+	l2tp_tunnel_inc_refcount(tunnel);
 	l2tp_tunnel_closeall(tunnel);
-	return (false == queue_work(l2tp_wq, &tunnel->del_work));
+	if (false == queue_work(l2tp_wq, &tunnel->del_work)) {
+		l2tp_tunnel_dec_refcount(tunnel);
+		return 1;
+	}
+	return 0;
 }
 EXPORT_SYMBOL_GPL(l2tp_tunnel_delete);
 
-- 
1.7.10.4


From 92fe703b6367dbc0627aa3865cc674a6b7b7f4e3 Mon Sep 17 00:00:00 2001
From: Aaron Conole <aconole@bytheb.org>
Date: Sat, 26 Sep 2015 18:50:42 -0400
Subject: [PATCH 02/11] af_unix: Convert the unix_sk macro to an inline
 function for type safety

[ Upstream commit 4613012db1d911f80897f9446a49de817b2c4c47 ]

As suggested by Eric Dumazet this change replaces the
#define with a static inline function to enjoy
complaints by the compiler when misusing the API.

Signed-off-by: Aaron Conole <aconole@bytheb.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/af_unix.h |    6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index a175ba4..dfe4ddf 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -64,7 +64,11 @@ struct unix_sock {
 #define UNIX_GC_MAYBE_CYCLE	1
 	struct socket_wq	peer_wq;
 };
-#define unix_sk(__sk) ((struct unix_sock *)__sk)
+
+static inline struct unix_sock *unix_sk(struct sock *sk)
+{
+	return (struct unix_sock *)sk;
+}
 
 #define peer_wait peer_wq.wait
 
-- 
1.7.10.4


From cc7a9dd024992e616446b465233515d79b4b1286 Mon Sep 17 00:00:00 2001
From: Aaron Conole <aconole@bytheb.org>
Date: Sat, 26 Sep 2015 18:50:43 -0400
Subject: [PATCH 03/11] af_unix: return data from multiple SKBs on recv() with
 MSG_PEEK flag

[ Upstream commit 9f389e35674f5b086edd70ed524ca0f287259725 ]

AF_UNIX sockets now return multiple skbs from recv() when MSG_PEEK flag
is set.

This is referenced in kernel bugzilla #12323 @
https://bugzilla.kernel.org/show_bug.cgi?id=12323

As described both in the BZ and lkml thread @
http://lkml.org/lkml/2008/1/8/444 calling recv() with MSG_PEEK on an
AF_UNIX socket only reads a single skb, where the desired effect is
to return as much skb data has been queued, until hitting the recv
buffer size (whichever comes first).

The modified MSG_PEEK path will now move to the next skb in the tree
and jump to the again: label, rather than following the natural loop
structure. This requires duplicating some of the loop head actions.

This was tested using the python socketpair python code attached to
the bugzilla issue.

Signed-off-by: Aaron Conole <aconole@bytheb.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c |   14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 8232118..30a705e 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2070,8 +2070,20 @@ again:
 			if (UNIXCB(skb).fp)
 				siocb->scm->fp = scm_fp_dup(UNIXCB(skb).fp);
 
-			sk_peek_offset_fwd(sk, chunk);
+			if (skip) {
+				sk_peek_offset_fwd(sk, chunk);
+				skip -= chunk;
+			}
+
+			if (UNIXCB(skb).fp)
+				break;
 
+			last = skb;
+			unix_state_lock(sk);
+			skb = skb_peek_next(skb, &sk->sk_receive_queue);
+			if (skb)
+				goto again;
+			unix_state_unlock(sk);
 			break;
 		}
 	} while (size);
-- 
1.7.10.4


From d691cd9811aabd05d57bb77ff7f2f5be1c2f91d3 Mon Sep 17 00:00:00 2001
From: Andrey Vagin <avagin@openvz.org>
Date: Fri, 2 Oct 2015 00:05:36 +0300
Subject: [PATCH 04/11] net/unix: fix logic about sk_peek_offset

[ Upstream commit e9193d60d363e4dff75ff6d43a48f22be26d59c7 ]

Now send with MSG_PEEK can return data from multiple SKBs.

Unfortunately we take into account the peek offset for each skb,
that is wrong. We need to apply the peek offset only once.

In addition, the peek offset should be used only if MSG_PEEK is set.

Cc: "David S. Miller" <davem@davemloft.net> (maintainer:NETWORKING
Cc: Eric Dumazet <edumazet@google.com> (commit_signer:1/14=7%)
Cc: Aaron Conole <aconole@bytheb.org>
Fixes: 9f389e35674f ("af_unix: return data from multiple SKBs on recv() with MSG_PEEK flag")
Signed-off-by: Andrey Vagin <avagin@openvz.org>
Tested-by: Aaron Conole <aconole@bytheb.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c |   12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 30a705e..2ae4a59 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1962,6 +1962,11 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 		goto out;
 	}
 
+	if (flags & MSG_PEEK)
+		skip = sk_peek_offset(sk, flags);
+	else
+		skip = 0;
+
 	do {
 		int chunk;
 		struct sk_buff *skb, *last;
@@ -2008,7 +2013,6 @@ again:
 			break;
 		}
 
-		skip = sk_peek_offset(sk, flags);
 		while (skip >= unix_skb_len(skb)) {
 			skip -= unix_skb_len(skb);
 			last = skb;
@@ -2070,14 +2074,12 @@ again:
 			if (UNIXCB(skb).fp)
 				siocb->scm->fp = scm_fp_dup(UNIXCB(skb).fp);
 
-			if (skip) {
-				sk_peek_offset_fwd(sk, chunk);
-				skip -= chunk;
-			}
+			sk_peek_offset_fwd(sk, chunk);
 
 			if (UNIXCB(skb).fp)
 				break;
 
+			skip = 0;
 			last = skb;
 			unix_state_lock(sk);
 			skb = skb_peek_next(skb, &sk->sk_receive_queue);
-- 
1.7.10.4


From 061169413944310357505f0450f8ec920e0f7bb9 Mon Sep 17 00:00:00 2001
From: Pravin B Shelar <pshelar@nicira.com>
Date: Tue, 22 Sep 2015 12:57:53 -0700
Subject: [PATCH 05/11] skbuff: Fix skb checksum flag on skb pull

[ Upstream commit 6ae459bdaaeebc632b16e54dcbabb490c6931d61 ]

VXLAN device can receive skb with checksum partial. But the checksum
offset could be in outer header which is pulled on receive. This results
in negative checksum offset for the skb. Such skb can cause the assert
failure in skb_checksum_help(). Following patch fixes the bug by setting
checksum-none while pulling outer header.

Following is the kernel panic msg from old kernel hitting the bug.

------------[ cut here ]------------
kernel BUG at net/core/dev.c:1906!
RIP: 0010:[<ffffffff81518034>] skb_checksum_help+0x144/0x150
Call Trace:
<IRQ>
[<ffffffffa0164c28>] queue_userspace_packet+0x408/0x470 [openvswitch]
[<ffffffffa016614d>] ovs_dp_upcall+0x5d/0x60 [openvswitch]
[<ffffffffa0166236>] ovs_dp_process_packet_with_key+0xe6/0x100 [openvswitch]
[<ffffffffa016629b>] ovs_dp_process_received_packet+0x4b/0x80 [openvswitch]
[<ffffffffa016c51a>] ovs_vport_receive+0x2a/0x30 [openvswitch]
[<ffffffffa0171383>] vxlan_rcv+0x53/0x60 [openvswitch]
[<ffffffffa01734cb>] vxlan_udp_encap_recv+0x8b/0xf0 [openvswitch]
[<ffffffff8157addc>] udp_queue_rcv_skb+0x2dc/0x3b0
[<ffffffff8157b56f>] __udp4_lib_rcv+0x1cf/0x6c0
[<ffffffff8157ba7a>] udp_rcv+0x1a/0x20
[<ffffffff8154fdbd>] ip_local_deliver_finish+0xdd/0x280
[<ffffffff81550128>] ip_local_deliver+0x88/0x90
[<ffffffff8154fa7d>] ip_rcv_finish+0x10d/0x370
[<ffffffff81550365>] ip_rcv+0x235/0x300
[<ffffffff8151ba1d>] __netif_receive_skb+0x55d/0x620
[<ffffffff8151c360>] netif_receive_skb+0x80/0x90
[<ffffffff81459935>] virtnet_poll+0x555/0x6f0
[<ffffffff8151cd04>] net_rx_action+0x134/0x290
[<ffffffff810683d8>] __do_softirq+0xa8/0x210
[<ffffffff8162fe6c>] call_softirq+0x1c/0x30
[<ffffffff810161a5>] do_softirq+0x65/0xa0
[<ffffffff810687be>] irq_exit+0x8e/0xb0
[<ffffffff81630733>] do_IRQ+0x63/0xe0
[<ffffffff81625f2e>] common_interrupt+0x6e/0x6e

Reported-by: Anupam Chanda <achanda@vmware.com>
Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
Acked-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h |    3 +++
 1 file changed, 3 insertions(+)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 522d837..603b5da 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2549,6 +2549,9 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb,
 {
 	if (skb->ip_summed == CHECKSUM_COMPLETE)
 		skb->csum = csum_sub(skb->csum, csum_partial(start, len, 0));
+	else if (skb->ip_summed == CHECKSUM_PARTIAL &&
+		 skb_checksum_start_offset(skb) <= len)
+		skb->ip_summed = CHECKSUM_NONE;
 }
 
 unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len);
-- 
1.7.10.4


From 64635e1ae296039d50c8a43945e03fd8d2b1b8e7 Mon Sep 17 00:00:00 2001
From: Pravin B Shelar <pshelar@nicira.com>
Date: Mon, 28 Sep 2015 17:24:25 -0700
Subject: [PATCH 06/11] skbuff: Fix skb checksum partial check.

[ Upstream commit 31b33dfb0a144469dd805514c9e63f4993729a48 ]

Earlier patch 6ae459bda tried to detect void ckecksum partial
skb by comparing pull length to checksum offset. But it does
not work for all cases since checksum-offset depends on
updates to skb->data.

Following patch fixes it by validating checksum start offset
after skb-data pointer is updated. Negative value of checksum
offset start means there is no need to checksum.

Fixes: 6ae459bda ("skbuff: Fix skb checksum flag on skb pull")
Reported-by: Andrew Vagin <avagin@odin.com>
Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h |    2 +-
 net/core/skbuff.c      |    9 +++++----
 2 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 603b5da..3b57c67 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2550,7 +2550,7 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb,
 	if (skb->ip_summed == CHECKSUM_COMPLETE)
 		skb->csum = csum_sub(skb->csum, csum_partial(start, len, 0));
 	else if (skb->ip_summed == CHECKSUM_PARTIAL &&
-		 skb_checksum_start_offset(skb) <= len)
+		 skb_checksum_start_offset(skb) < 0)
 		skb->ip_summed = CHECKSUM_NONE;
 }
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 72400a1..ea0bcc4 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2881,11 +2881,12 @@ EXPORT_SYMBOL(skb_append_datato_frags);
  */
 unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len)
 {
+	unsigned char *data = skb->data;
+
 	BUG_ON(len > skb->len);
-	skb->len -= len;
-	BUG_ON(skb->len < skb->data_len);
-	skb_postpull_rcsum(skb, skb->data, len);
-	return skb->data += len;
+	__skb_pull(skb, len);
+	skb_postpull_rcsum(skb, data, len);
+	return skb->data;
 }
 EXPORT_SYMBOL_GPL(skb_pull_rcsum);
 
-- 
1.7.10.4


From efa02bc48615d45c926299f97abeca03eba0173f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 29 Sep 2015 18:52:25 -0700
Subject: [PATCH 07/11] net: add pfmemalloc check in sk_add_backlog()

[ Upstream commit c7c49b8fde26b74277188bdc6c9dca38db6fa35b ]

Greg reported crashes hitting the following check in __sk_backlog_rcv()

	BUG_ON(!sock_flag(sk, SOCK_MEMALLOC));

The pfmemalloc bit is currently checked in sk_filter().

This works correctly for TCP, because sk_filter() is ran in
tcp_v[46]_rcv() before hitting the prequeue or backlog checks.

For UDP or other protocols, this does not work, because the sk_filter()
is ran from sock_queue_rcv_skb(), which might be called _after_ backlog
queuing if socket is owned by user by the time packet is processed by
softirq handler.

Fixes: b4b9e35585089 ("netvm: set PF_MEMALLOC as appropriate during SKB processing")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Greg Thelen <gthelen@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h |    8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/include/net/sock.h b/include/net/sock.h
index 4406dbe..a098ce3 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -819,6 +819,14 @@ static inline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *s
 	if (sk_rcvqueues_full(sk, limit))
 		return -ENOBUFS;
 
+	/*
+	 * If the skb was allocated from pfmemalloc reserves, only
+	 * allow SOCK_MEMALLOC sockets to use it as this socket is
+	 * helping free memory
+	 */
+	if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC))
+		return -ENOMEM;
+
 	__sk_add_backlog(sk, skb);
 	sk->sk_backlog.len += skb->truesize;
 	return 0;
-- 
1.7.10.4


From fdc38458c23c70f54fbf57c2877b5bbb3d06a813 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Wed, 30 Sep 2015 11:45:33 +0200
Subject: [PATCH 08/11] ppp: don't override sk->sk_state in pppoe_flush_dev()

[ Upstream commit e6740165b8f7f06d8caee0fceab3fb9d790a6fed ]

Since commit 2b018d57ff18 ("pppoe: drop PPPOX_ZOMBIEs in pppoe_release"),
pppoe_release() calls dev_put(po->pppoe_dev) if sk is in the
PPPOX_ZOMBIE state. But pppoe_flush_dev() can set sk->sk_state to
PPPOX_ZOMBIE _and_ reset po->pppoe_dev to NULL. This leads to the
following oops:

[  570.140800] BUG: unable to handle kernel NULL pointer dereference at 00000000000004e0
[  570.142931] IP: [<ffffffffa018c701>] pppoe_release+0x50/0x101 [pppoe]
[  570.144601] PGD 3d119067 PUD 3dbc1067 PMD 0
[  570.144601] Oops: 0000 [#1] SMP
[  570.144601] Modules linked in: l2tp_ppp l2tp_netlink l2tp_core ip6_udp_tunnel udp_tunnel pppoe pppox ppp_generic slhc loop crc32c_intel ghash_clmulni_intel jitterentropy_rng sha256_generic hmac drbg ansi_cprng aesni_intel aes_x86_64 ablk_helper cryptd lrw gf128mul glue_helper acpi_cpufreq evdev serio_raw processor button ext4 crc16 mbcache jbd2 virtio_net virtio_blk virtio_pci virtio_ring virtio
[  570.144601] CPU: 1 PID: 15738 Comm: ppp-apitest Not tainted 4.2.0 #1
[  570.144601] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Debian-1.8.2-1 04/01/2014
[  570.144601] task: ffff88003d30d600 ti: ffff880036b60000 task.ti: ffff880036b60000
[  570.144601] RIP: 0010:[<ffffffffa018c701>]  [<ffffffffa018c701>] pppoe_release+0x50/0x101 [pppoe]
[  570.144601] RSP: 0018:ffff880036b63e08  EFLAGS: 00010202
[  570.144601] RAX: 0000000000000000 RBX: ffff880034340000 RCX: 0000000000000206
[  570.144601] RDX: 0000000000000006 RSI: ffff88003d30dd20 RDI: ffff88003d30dd20
[  570.144601] RBP: ffff880036b63e28 R08: 0000000000000001 R09: 0000000000000000
[  570.144601] R10: 00007ffee9b50420 R11: ffff880034340078 R12: ffff8800387ec780
[  570.144601] R13: ffff8800387ec7b0 R14: ffff88003e222aa0 R15: ffff8800387ec7b0
[  570.144601] FS:  00007f5672f48700(0000) GS:ffff88003fc80000(0000) knlGS:0000000000000000
[  570.144601] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  570.144601] CR2: 00000000000004e0 CR3: 0000000037f7e000 CR4: 00000000000406a0
[  570.144601] Stack:
[  570.144601]  ffffffffa018f240 ffff8800387ec780 ffffffffa018f240 ffff8800387ec7b0
[  570.144601]  ffff880036b63e48 ffffffff812caabe ffff880039e4e000 0000000000000008
[  570.144601]  ffff880036b63e58 ffffffff812cabad ffff880036b63ea8 ffffffff811347f5
[  570.144601] Call Trace:
[  570.144601]  [<ffffffff812caabe>] sock_release+0x1a/0x75
[  570.144601]  [<ffffffff812cabad>] sock_close+0xd/0x11
[  570.144601]  [<ffffffff811347f5>] __fput+0xff/0x1a5
[  570.144601]  [<ffffffff811348cb>] ____fput+0x9/0xb
[  570.144601]  [<ffffffff81056682>] task_work_run+0x66/0x90
[  570.144601]  [<ffffffff8100189e>] prepare_exit_to_usermode+0x8c/0xa7
[  570.144601]  [<ffffffff81001a26>] syscall_return_slowpath+0x16d/0x19b
[  570.144601]  [<ffffffff813babb1>] int_ret_from_sys_call+0x25/0x9f
[  570.144601] Code: 48 8b 83 c8 01 00 00 a8 01 74 12 48 89 df e8 8b 27 14 e1 b8 f7 ff ff ff e9 b7 00 00 00 8a 43 12 a8 0b 74 1c 48 8b 83 a8 04 00 00 <48> 8b 80 e0 04 00 00 65 ff 08 48 c7 83 a8 04 00 00 00 00 00 00
[  570.144601] RIP  [<ffffffffa018c701>] pppoe_release+0x50/0x101 [pppoe]
[  570.144601]  RSP <ffff880036b63e08>
[  570.144601] CR2: 00000000000004e0
[  570.200518] ---[ end trace 46956baf17349563 ]---

pppoe_flush_dev() has no reason to override sk->sk_state with
PPPOX_ZOMBIE. pppox_unbind_sock() already sets sk->sk_state to
PPPOX_DEAD, which is the correct state given that sk is unbound and
po->pppoe_dev is NULL.

Fixes: 2b018d57ff18 ("pppoe: drop PPPOX_ZOMBIEs in pppoe_release")
Tested-by: Oleksii Berezhniak <core@irc.lg.ua>
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pppoe.c |    1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 6c9c16d..f606b5b 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -313,7 +313,6 @@ static void pppoe_flush_dev(struct net_device *dev)
 			if (po->pppoe_dev == dev &&
 			    sk->sk_state & (PPPOX_CONNECTED | PPPOX_BOUND | PPPOX_ZOMBIE)) {
 				pppox_unbind_sock(sk);
-				sk->sk_state = PPPOX_ZOMBIE;
 				sk->sk_state_change(sk);
 				po->pppoe_dev = NULL;
 				dev_put(dev);
-- 
1.7.10.4


From 3b8b9f1c757b578dfeeb44ca99f5f984241a2761 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Date: Fri, 2 Oct 2015 13:18:22 +0300
Subject: [PATCH 09/11] ovs: do not allocate memory from offline numa node

[ Upstream commit 598c12d0ba6de9060f04999746eb1e015774044b ]

When openvswitch tries allocate memory from offline numa node 0:
stats = kmem_cache_alloc_node(flow_stats_cache, GFP_KERNEL | __GFP_ZERO, 0)
It catches VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES || !node_online(nid))
[ replaced with VM_WARN_ON(!node_online(nid)) recently ] in linux/gfp.h
This patch disables numa affinity in this case.

Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/flow_table.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index cf2d853..199b2e7 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -89,7 +89,8 @@ struct sw_flow *ovs_flow_alloc(void)
 
 	/* Initialize the default stat node. */
 	stats = kmem_cache_alloc_node(flow_stats_cache,
-				      GFP_KERNEL | __GFP_ZERO, 0);
+				      GFP_KERNEL | __GFP_ZERO,
+				      node_online(0) ? 0 : NUMA_NO_NODE);
 	if (!stats)
 		goto err;
 
-- 
1.7.10.4


From d0e6b3cb49f27c8bad0f3ba0a4434895738f52c7 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Wed, 14 Oct 2015 01:09:40 -0700
Subject: [PATCH 10/11] ethtool: Use kcalloc instead of kmalloc for
 ethtool_get_strings

[ Upstream commit 077cb37fcf6f00a45f375161200b5ee0cd4e937b ]

It seems that kernel memory can leak into userspace by a
kmalloc, ethtool_get_strings, then copy_to_user sequence.

Avoid this by using kcalloc to zero fill the copied buffer.

Signed-off-by: Joe Perches <joe@perches.com>
Acked-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/ethtool.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 06dfb29..14bb158 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -1257,7 +1257,7 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr)
 
 	gstrings.len = ret;
 
-	data = kmalloc(gstrings.len * ETH_GSTRING_LEN, GFP_USER);
+	data = kcalloc(gstrings.len, ETH_GSTRING_LEN, GFP_USER);
 	if (!data)
 		return -ENOMEM;
 
-- 
1.7.10.4


From 0934f7c701336608a59bde5e694d8fb30f8fab6b Mon Sep 17 00:00:00 2001
From: "Arad, Ronen" <ronen.arad@intel.com>
Date: Thu, 15 Oct 2015 01:55:17 -0700
Subject: [PATCH 11/11] netlink: Trim skb to alloc size to avoid MSG_TRUNC

[ Upstream commit db65a3aaf29ecce2e34271d52e8d2336b97bd9fe ]

netlink_dump() allocates skb based on the calculated min_dump_alloc or
a per socket max_recvmsg_len.
min_alloc_size is maximum space required for any single netdev
attributes as calculated by rtnl_calcit().
max_recvmsg_len tracks the user provided buffer to netlink_recvmsg.
It is capped at 16KiB.
The intention is to avoid small allocations and to minimize the number
of calls required to obtain dump information for all net devices.

netlink_dump packs as many small messages as could fit within an skb
that was sized for the largest single netdev information. The actual
space available within an skb is larger than what is requested. It could
be much larger and up to near 2x with align to next power of 2 approach.

Allowing netlink_dump to use all the space available within the
allocated skb increases the buffer size a user has to provide to avoid
truncaion (i.e. MSG_TRUNG flag set).

It was observed that with many VLANs configured on at least one netdev,
a larger buffer of near 64KiB was necessary to avoid "Message truncated"
error in "ip link" or "bridge [-c[ompressvlans]] vlan show" when
min_alloc_size was only little over 32KiB.

This patch trims skb to allocated size in order to allow the user to
avoid truncation with more reasonable buffer size.

Signed-off-by: Ronen Arad <ronen.arad@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c |   34 ++++++++++++++++++++++------------
 1 file changed, 22 insertions(+), 12 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 6ffd1eb..327c000 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2615,6 +2615,7 @@ static int netlink_dump(struct sock *sk)
 	struct sk_buff *skb = NULL;
 	struct nlmsghdr *nlh;
 	int len, err = -ENOBUFS;
+	int alloc_min_size;
 	int alloc_size;
 
 	mutex_lock(nlk->cb_mutex);
@@ -2623,9 +2624,6 @@ static int netlink_dump(struct sock *sk)
 		goto errout_skb;
 	}
 
-	cb = &nlk->cb;
-	alloc_size = max_t(int, cb->min_dump_alloc, NLMSG_GOODSIZE);
-
 	if (!netlink_rx_is_mmaped(sk) &&
 	    atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
 		goto errout_skb;
@@ -2635,23 +2633,35 @@ static int netlink_dump(struct sock *sk)
 	 * to reduce number of system calls on dump operations, if user
 	 * ever provided a big enough buffer.
 	 */
-	if (alloc_size < nlk->max_recvmsg_len) {
-		skb = netlink_alloc_skb(sk,
-					nlk->max_recvmsg_len,
-					nlk->portid,
+	cb = &nlk->cb;
+	alloc_min_size = max_t(int, cb->min_dump_alloc, NLMSG_GOODSIZE);
+
+	if (alloc_min_size < nlk->max_recvmsg_len) {
+		alloc_size = nlk->max_recvmsg_len;
+		skb = netlink_alloc_skb(sk, alloc_size, nlk->portid,
 					GFP_KERNEL |
 					__GFP_NOWARN |
 					__GFP_NORETRY);
-		/* available room should be exact amount to avoid MSG_TRUNC */
-		if (skb)
-			skb_reserve(skb, skb_tailroom(skb) -
-					 nlk->max_recvmsg_len);
 	}
-	if (!skb)
+	if (!skb) {
+		alloc_size = alloc_min_size;
 		skb = netlink_alloc_skb(sk, alloc_size, nlk->portid,
 					GFP_KERNEL);
+	}
 	if (!skb)
 		goto errout_skb;
+
+	/* Trim skb to allocated size. User is expected to provide buffer as
+	 * large as max(min_dump_alloc, 16KiB (mac_recvmsg_len capped at
+	 * netlink_recvmsg())). dump will pack as many smaller messages as
+	 * could fit within the allocated skb. skb is typically allocated
+	 * with larger space than required (could be as much as near 2x the
+	 * requested size with align to next power of 2 approach). Allowing
+	 * dump to use the excess space makes it difficult for a user to have a
+	 * reasonable static buffer based on the expected largest dump of a
+	 * single netdev. The outcome is MSG_TRUNC error.
+	 */
+	skb_reserve(skb, skb_tailroom(skb) - alloc_size);
 	netlink_skb_set_owner_r(skb, sk);
 
 	len = cb->dump(skb, cb);
-- 
1.7.10.4


[-- Attachment #4: net_41.mbox --]
[-- Type: Application/Octet-Stream, Size: 37768 bytes --]

From d1719fc2cba61a28fedd0114fc1178eb00879f82 Mon Sep 17 00:00:00 2001
From: Ivan Mikhaylov <ivan@ru.ibm.com>
Date: Fri, 25 Sep 2015 11:52:27 +0400
Subject: [PATCH 01/18] net/ibm/emac: bump version numbers for correct work
 with ethtool

[ Upstream commit 661dfc65f7981481ba2e31aaa702371e82336e56 ]

The size of the MAC register dump used to be the size specified by the
reg property in the device tree.  Userland has no good way of finding
out that size, and it was not specified consistently for each MAC type,
so ethtool would end up printing junk at the end of the register dump
if the device tree didn't match the size it assumed.

Using the new version numbers indicates unambiguously that the size of
the MAC register dump is dependent only on the MAC type.

Fixes: 5369c71f7ca2 ("net/ibm/emac: fix size of emac dump memory areas")
Signed-off-by: Ivan Mikhaylov <ivan@ru.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ibm/emac/core.h |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/ibm/emac/core.h b/drivers/net/ethernet/ibm/emac/core.h
index 28df374..ac02c67 100644
--- a/drivers/net/ethernet/ibm/emac/core.h
+++ b/drivers/net/ethernet/ibm/emac/core.h
@@ -460,8 +460,8 @@ struct emac_ethtool_regs_subhdr {
 	u32 index;
 };
 
-#define EMAC_ETHTOOL_REGS_VER		0
-#define EMAC4_ETHTOOL_REGS_VER		1
-#define EMAC4SYNC_ETHTOOL_REGS_VER	2
+#define EMAC_ETHTOOL_REGS_VER		3
+#define EMAC4_ETHTOOL_REGS_VER		4
+#define EMAC4SYNC_ETHTOOL_REGS_VER	5
 
 #endif /* __IBM_NEWEMAC_CORE_H */
-- 
1.7.10.4


From aef7765f232f215a31a0d04a389da9ef5fb404ba Mon Sep 17 00:00:00 2001
From: Alexander Couzens <lynxis@fe80.eu>
Date: Mon, 28 Sep 2015 11:32:42 +0200
Subject: [PATCH 02/18] l2tp: protect tunnel->del_work by ref_count

[ Upstream commit 06a15f51cf3618e32a73871ee6a547ef7fd902b5 ]

There is a small chance that tunnel_free() is called before tunnel->del_work scheduled
resulting in a zero pointer dereference.

Signed-off-by: Alexander Couzens <lynxis@fe80.eu>
Acked-by: James Chapman <jchapman@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c |   11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index a29a504..e3db498 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1319,7 +1319,7 @@ static void l2tp_tunnel_del_work(struct work_struct *work)
 	tunnel = container_of(work, struct l2tp_tunnel, del_work);
 	sk = l2tp_tunnel_sock_lookup(tunnel);
 	if (!sk)
-		return;
+		goto out;
 
 	sock = sk->sk_socket;
 
@@ -1340,6 +1340,8 @@ static void l2tp_tunnel_del_work(struct work_struct *work)
 	}
 
 	l2tp_tunnel_sock_put(sk);
+out:
+	l2tp_tunnel_dec_refcount(tunnel);
 }
 
 /* Create a socket for the tunnel, if one isn't set up by
@@ -1639,8 +1641,13 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_create);
  */
 int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel)
 {
+	l2tp_tunnel_inc_refcount(tunnel);
 	l2tp_tunnel_closeall(tunnel);
-	return (false == queue_work(l2tp_wq, &tunnel->del_work));
+	if (false == queue_work(l2tp_wq, &tunnel->del_work)) {
+		l2tp_tunnel_dec_refcount(tunnel);
+		return 1;
+	}
+	return 0;
 }
 EXPORT_SYMBOL_GPL(l2tp_tunnel_delete);
 
-- 
1.7.10.4


From ef5ffafba408c6625bf7918e89a217f3f76fc27d Mon Sep 17 00:00:00 2001
From: Pravin B Shelar <pshelar@nicira.com>
Date: Tue, 22 Sep 2015 12:57:53 -0700
Subject: [PATCH 03/18] skbuff: Fix skb checksum flag on skb pull

[ Upstream commit 6ae459bdaaeebc632b16e54dcbabb490c6931d61 ]

VXLAN device can receive skb with checksum partial. But the checksum
offset could be in outer header which is pulled on receive. This results
in negative checksum offset for the skb. Such skb can cause the assert
failure in skb_checksum_help(). Following patch fixes the bug by setting
checksum-none while pulling outer header.

Following is the kernel panic msg from old kernel hitting the bug.

------------[ cut here ]------------
kernel BUG at net/core/dev.c:1906!
RIP: 0010:[<ffffffff81518034>] skb_checksum_help+0x144/0x150
Call Trace:
<IRQ>
[<ffffffffa0164c28>] queue_userspace_packet+0x408/0x470 [openvswitch]
[<ffffffffa016614d>] ovs_dp_upcall+0x5d/0x60 [openvswitch]
[<ffffffffa0166236>] ovs_dp_process_packet_with_key+0xe6/0x100 [openvswitch]
[<ffffffffa016629b>] ovs_dp_process_received_packet+0x4b/0x80 [openvswitch]
[<ffffffffa016c51a>] ovs_vport_receive+0x2a/0x30 [openvswitch]
[<ffffffffa0171383>] vxlan_rcv+0x53/0x60 [openvswitch]
[<ffffffffa01734cb>] vxlan_udp_encap_recv+0x8b/0xf0 [openvswitch]
[<ffffffff8157addc>] udp_queue_rcv_skb+0x2dc/0x3b0
[<ffffffff8157b56f>] __udp4_lib_rcv+0x1cf/0x6c0
[<ffffffff8157ba7a>] udp_rcv+0x1a/0x20
[<ffffffff8154fdbd>] ip_local_deliver_finish+0xdd/0x280
[<ffffffff81550128>] ip_local_deliver+0x88/0x90
[<ffffffff8154fa7d>] ip_rcv_finish+0x10d/0x370
[<ffffffff81550365>] ip_rcv+0x235/0x300
[<ffffffff8151ba1d>] __netif_receive_skb+0x55d/0x620
[<ffffffff8151c360>] netif_receive_skb+0x80/0x90
[<ffffffff81459935>] virtnet_poll+0x555/0x6f0
[<ffffffff8151cd04>] net_rx_action+0x134/0x290
[<ffffffff810683d8>] __do_softirq+0xa8/0x210
[<ffffffff8162fe6c>] call_softirq+0x1c/0x30
[<ffffffff810161a5>] do_softirq+0x65/0xa0
[<ffffffff810687be>] irq_exit+0x8e/0xb0
[<ffffffff81630733>] do_IRQ+0x63/0xe0
[<ffffffff81625f2e>] common_interrupt+0x6e/0x6e

Reported-by: Anupam Chanda <achanda@vmware.com>
Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
Acked-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h |    3 +++
 1 file changed, 3 insertions(+)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index eb1c55b..7f04271 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2588,6 +2588,9 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb,
 {
 	if (skb->ip_summed == CHECKSUM_COMPLETE)
 		skb->csum = csum_sub(skb->csum, csum_partial(start, len, 0));
+	else if (skb->ip_summed == CHECKSUM_PARTIAL &&
+		 skb_checksum_start_offset(skb) <= len)
+		skb->ip_summed = CHECKSUM_NONE;
 }
 
 unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len);
-- 
1.7.10.4


From fdde5ed58c4069c59c924357b524fe5c8a5ced50 Mon Sep 17 00:00:00 2001
From: Pravin B Shelar <pshelar@nicira.com>
Date: Mon, 28 Sep 2015 17:24:25 -0700
Subject: [PATCH 04/18] skbuff: Fix skb checksum partial check.

[ Upstream commit 31b33dfb0a144469dd805514c9e63f4993729a48 ]

Earlier patch 6ae459bda tried to detect void ckecksum partial
skb by comparing pull length to checksum offset. But it does
not work for all cases since checksum-offset depends on
updates to skb->data.

Following patch fixes it by validating checksum start offset
after skb-data pointer is updated. Negative value of checksum
offset start means there is no need to checksum.

Fixes: 6ae459bda ("skbuff: Fix skb checksum flag on skb pull")
Reported-by: Andrew Vagin <avagin@odin.com>
Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h |    2 +-
 net/core/skbuff.c      |    9 +++++----
 2 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 7f04271..4307e20 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2589,7 +2589,7 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb,
 	if (skb->ip_summed == CHECKSUM_COMPLETE)
 		skb->csum = csum_sub(skb->csum, csum_partial(start, len, 0));
 	else if (skb->ip_summed == CHECKSUM_PARTIAL &&
-		 skb_checksum_start_offset(skb) <= len)
+		 skb_checksum_start_offset(skb) < 0)
 		skb->ip_summed = CHECKSUM_NONE;
 }
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index a2e4e47..075d2e7 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2976,11 +2976,12 @@ EXPORT_SYMBOL(skb_append_datato_frags);
  */
 unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len)
 {
+	unsigned char *data = skb->data;
+
 	BUG_ON(len > skb->len);
-	skb->len -= len;
-	BUG_ON(skb->len < skb->data_len);
-	skb_postpull_rcsum(skb, skb->data, len);
-	return skb->data += len;
+	__skb_pull(skb, len);
+	skb_postpull_rcsum(skb, data, len);
+	return skb->data;
 }
 EXPORT_SYMBOL_GPL(skb_pull_rcsum);
 
-- 
1.7.10.4


From 04a294c3b8f0730f2faab5b488c67c831b08514b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 13 Aug 2015 15:44:51 -0700
Subject: [PATCH 05/18] inet: fix potential deadlock in reqsk_queue_unlink()

[ Upstream commit 83fccfc3940c4a2db90fd7e7079f5b465cd8c6af ]

When replacing del_timer() with del_timer_sync(), I introduced
a deadlock condition :

reqsk_queue_unlink() is called from inet_csk_reqsk_queue_drop()

inet_csk_reqsk_queue_drop() can be called from many contexts,
one being the timer handler itself (reqsk_timer_handler()).

In this case, del_timer_sync() loops forever.

Simple fix is to test if timer is pending.

Fixes: 2235f2ac75fd ("inet: fix races with reqsk timers")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/inet_connection_sock.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index b27fc40..e664706 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -584,7 +584,7 @@ static bool reqsk_queue_unlink(struct request_sock_queue *queue,
 	}
 
 	spin_unlock(&queue->syn_wait_lock);
-	if (del_timer_sync(&req->rsk_timer))
+	if (timer_pending(&req->rsk_timer) && del_timer_sync(&req->rsk_timer))
 		reqsk_put(req);
 	return found;
 }
-- 
1.7.10.4


From c8f4f24903c6ea5b7728c8aa2438cae9d16c4e84 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 19 Sep 2015 09:48:04 -0700
Subject: [PATCH 06/18] inet: fix races in reqsk_queue_hash_req()

[ Upstream commit 29c6852602e259d2c1882f320b29d5c3fec0de04 ]

Before allowing lockless LISTEN processing, we need to make
sure to arm the SYN_RECV timer before the req socket is visible
in hash tables.

Also, req->rsk_hash should be written before we set rsk_refcnt
to a non zero value.

Fixes: fa76ce7328b2 ("inet: get rid of central tcp/dccp listener timer")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Ying Cai <ycai@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/inet_connection_sock.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index e664706..390f61d 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -676,20 +676,20 @@ void reqsk_queue_hash_req(struct request_sock_queue *queue,
 	req->num_timeout = 0;
 	req->sk = NULL;
 
+	setup_timer(&req->rsk_timer, reqsk_timer_handler, (unsigned long)req);
+	mod_timer_pinned(&req->rsk_timer, jiffies + timeout);
+	req->rsk_hash = hash;
+
 	/* before letting lookups find us, make sure all req fields
 	 * are committed to memory and refcnt initialized.
 	 */
 	smp_wmb();
 	atomic_set(&req->rsk_refcnt, 2);
-	setup_timer(&req->rsk_timer, reqsk_timer_handler, (unsigned long)req);
-	req->rsk_hash = hash;
 
 	spin_lock(&queue->syn_wait_lock);
 	req->dl_next = lopt->syn_table[hash];
 	lopt->syn_table[hash] = req;
 	spin_unlock(&queue->syn_wait_lock);
-
-	mod_timer_pinned(&req->rsk_timer, jiffies + timeout);
 }
 EXPORT_SYMBOL(reqsk_queue_hash_req);
 
-- 
1.7.10.4


From d7d44194b15d8cfeb67aafaad0070573ef41bacd Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 29 Sep 2015 18:52:25 -0700
Subject: [PATCH 07/18] net: add pfmemalloc check in sk_add_backlog()

[ Upstream commit c7c49b8fde26b74277188bdc6c9dca38db6fa35b ]

Greg reported crashes hitting the following check in __sk_backlog_rcv()

	BUG_ON(!sock_flag(sk, SOCK_MEMALLOC));

The pfmemalloc bit is currently checked in sk_filter().

This works correctly for TCP, because sk_filter() is ran in
tcp_v[46]_rcv() before hitting the prequeue or backlog checks.

For UDP or other protocols, this does not work, because the sk_filter()
is ran from sock_queue_rcv_skb(), which might be called _after_ backlog
queuing if socket is owned by user by the time packet is processed by
softirq handler.

Fixes: b4b9e35585089 ("netvm: set PF_MEMALLOC as appropriate during SKB processing")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Greg Thelen <gthelen@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h |    8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/include/net/sock.h b/include/net/sock.h
index 3a4898e..ed01a01 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -826,6 +826,14 @@ static inline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *s
 	if (sk_rcvqueues_full(sk, limit))
 		return -ENOBUFS;
 
+	/*
+	 * If the skb was allocated from pfmemalloc reserves, only
+	 * allow SOCK_MEMALLOC sockets to use it as this socket is
+	 * helping free memory
+	 */
+	if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC))
+		return -ENOMEM;
+
 	__sk_add_backlog(sk, skb);
 	sk->sk_backlog.len += skb->truesize;
 	return 0;
-- 
1.7.10.4


From f5ae53e9f44696fc67d7817848addd822ed8e71b Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Wed, 30 Sep 2015 11:45:33 +0200
Subject: [PATCH 08/18] ppp: don't override sk->sk_state in pppoe_flush_dev()

[ Upstream commit e6740165b8f7f06d8caee0fceab3fb9d790a6fed ]

Since commit 2b018d57ff18 ("pppoe: drop PPPOX_ZOMBIEs in pppoe_release"),
pppoe_release() calls dev_put(po->pppoe_dev) if sk is in the
PPPOX_ZOMBIE state. But pppoe_flush_dev() can set sk->sk_state to
PPPOX_ZOMBIE _and_ reset po->pppoe_dev to NULL. This leads to the
following oops:

[  570.140800] BUG: unable to handle kernel NULL pointer dereference at 00000000000004e0
[  570.142931] IP: [<ffffffffa018c701>] pppoe_release+0x50/0x101 [pppoe]
[  570.144601] PGD 3d119067 PUD 3dbc1067 PMD 0
[  570.144601] Oops: 0000 [#1] SMP
[  570.144601] Modules linked in: l2tp_ppp l2tp_netlink l2tp_core ip6_udp_tunnel udp_tunnel pppoe pppox ppp_generic slhc loop crc32c_intel ghash_clmulni_intel jitterentropy_rng sha256_generic hmac drbg ansi_cprng aesni_intel aes_x86_64 ablk_helper cryptd lrw gf128mul glue_helper acpi_cpufreq evdev serio_raw processor button ext4 crc16 mbcache jbd2 virtio_net virtio_blk virtio_pci virtio_ring virtio
[  570.144601] CPU: 1 PID: 15738 Comm: ppp-apitest Not tainted 4.2.0 #1
[  570.144601] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Debian-1.8.2-1 04/01/2014
[  570.144601] task: ffff88003d30d600 ti: ffff880036b60000 task.ti: ffff880036b60000
[  570.144601] RIP: 0010:[<ffffffffa018c701>]  [<ffffffffa018c701>] pppoe_release+0x50/0x101 [pppoe]
[  570.144601] RSP: 0018:ffff880036b63e08  EFLAGS: 00010202
[  570.144601] RAX: 0000000000000000 RBX: ffff880034340000 RCX: 0000000000000206
[  570.144601] RDX: 0000000000000006 RSI: ffff88003d30dd20 RDI: ffff88003d30dd20
[  570.144601] RBP: ffff880036b63e28 R08: 0000000000000001 R09: 0000000000000000
[  570.144601] R10: 00007ffee9b50420 R11: ffff880034340078 R12: ffff8800387ec780
[  570.144601] R13: ffff8800387ec7b0 R14: ffff88003e222aa0 R15: ffff8800387ec7b0
[  570.144601] FS:  00007f5672f48700(0000) GS:ffff88003fc80000(0000) knlGS:0000000000000000
[  570.144601] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  570.144601] CR2: 00000000000004e0 CR3: 0000000037f7e000 CR4: 00000000000406a0
[  570.144601] Stack:
[  570.144601]  ffffffffa018f240 ffff8800387ec780 ffffffffa018f240 ffff8800387ec7b0
[  570.144601]  ffff880036b63e48 ffffffff812caabe ffff880039e4e000 0000000000000008
[  570.144601]  ffff880036b63e58 ffffffff812cabad ffff880036b63ea8 ffffffff811347f5
[  570.144601] Call Trace:
[  570.144601]  [<ffffffff812caabe>] sock_release+0x1a/0x75
[  570.144601]  [<ffffffff812cabad>] sock_close+0xd/0x11
[  570.144601]  [<ffffffff811347f5>] __fput+0xff/0x1a5
[  570.144601]  [<ffffffff811348cb>] ____fput+0x9/0xb
[  570.144601]  [<ffffffff81056682>] task_work_run+0x66/0x90
[  570.144601]  [<ffffffff8100189e>] prepare_exit_to_usermode+0x8c/0xa7
[  570.144601]  [<ffffffff81001a26>] syscall_return_slowpath+0x16d/0x19b
[  570.144601]  [<ffffffff813babb1>] int_ret_from_sys_call+0x25/0x9f
[  570.144601] Code: 48 8b 83 c8 01 00 00 a8 01 74 12 48 89 df e8 8b 27 14 e1 b8 f7 ff ff ff e9 b7 00 00 00 8a 43 12 a8 0b 74 1c 48 8b 83 a8 04 00 00 <48> 8b 80 e0 04 00 00 65 ff 08 48 c7 83 a8 04 00 00 00 00 00 00
[  570.144601] RIP  [<ffffffffa018c701>] pppoe_release+0x50/0x101 [pppoe]
[  570.144601]  RSP <ffff880036b63e08>
[  570.144601] CR2: 00000000000004e0
[  570.200518] ---[ end trace 46956baf17349563 ]---

pppoe_flush_dev() has no reason to override sk->sk_state with
PPPOX_ZOMBIE. pppox_unbind_sock() already sets sk->sk_state to
PPPOX_DEAD, which is the correct state given that sk is unbound and
po->pppoe_dev is NULL.

Fixes: 2b018d57ff18 ("pppoe: drop PPPOX_ZOMBIEs in pppoe_release")
Tested-by: Oleksii Berezhniak <core@irc.lg.ua>
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pppoe.c |    1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index b62a5e3..db2c3cd 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -313,7 +313,6 @@ static void pppoe_flush_dev(struct net_device *dev)
 			if (po->pppoe_dev == dev &&
 			    sk->sk_state & (PPPOX_CONNECTED | PPPOX_BOUND | PPPOX_ZOMBIE)) {
 				pppox_unbind_sock(sk);
-				sk->sk_state = PPPOX_ZOMBIE;
 				sk->sk_state_change(sk);
 				po->pppoe_dev = NULL;
 				dev_put(dev);
-- 
1.7.10.4


From d972c794a087582cb43f81d22c91ed4e4ef608a5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 1 Oct 2015 05:39:26 -0700
Subject: [PATCH 09/18] inet: fix race in reqsk_queue_unlink()

[ Upstream commit 2306c704ce280c97a60d1f45333b822b40281dea ]

reqsk_timer_handler() tests if icsk_accept_queue.listen_opt
is NULL at its beginning.

By the time it calls inet_csk_reqsk_queue_drop() and
reqsk_queue_unlink(), listener might have been closed and
inet_csk_listen_stop() had called reqsk_queue_yank_acceptq()
which sets icsk_accept_queue.listen_opt to NULL

We therefore need to correctly check listen_opt being NULL
after holding syn_wait_lock for proper synchronization.

Fixes: fa76ce7328b2 ("inet: get rid of central tcp/dccp listener timer")
Fixes: b357a364c57c ("inet: fix possible panic in reqsk_queue_unlink()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/inet_connection_sock.c |   19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 390f61d..4d2bc8c 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -568,21 +568,22 @@ EXPORT_SYMBOL(inet_rtx_syn_ack);
 static bool reqsk_queue_unlink(struct request_sock_queue *queue,
 			       struct request_sock *req)
 {
-	struct listen_sock *lopt = queue->listen_opt;
 	struct request_sock **prev;
+	struct listen_sock *lopt;
 	bool found = false;
 
 	spin_lock(&queue->syn_wait_lock);
-
-	for (prev = &lopt->syn_table[req->rsk_hash]; *prev != NULL;
-	     prev = &(*prev)->dl_next) {
-		if (*prev == req) {
-			*prev = req->dl_next;
-			found = true;
-			break;
+	lopt = queue->listen_opt;
+	if (lopt) {
+		for (prev = &lopt->syn_table[req->rsk_hash]; *prev != NULL;
+		     prev = &(*prev)->dl_next) {
+			if (*prev == req) {
+				*prev = req->dl_next;
+				found = true;
+				break;
+			}
 		}
 	}
-
 	spin_unlock(&queue->syn_wait_lock);
 	if (timer_pending(&req->rsk_timer) && del_timer_sync(&req->rsk_timer))
 		reqsk_put(req);
-- 
1.7.10.4


From 29ff9ee800cbde1cc4f1f54443b3924c43591906 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 2 Oct 2015 12:06:03 +0200
Subject: [PATCH 10/18] bpf: fix panic in SO_GET_FILTER with native ebpf
 programs

[ Upstream commit 93d08b6966cf730ea669d4d98f43627597077153 ]

When sockets have a native eBPF program attached through
setsockopt(sk, SOL_SOCKET, SO_ATTACH_BPF, ...), and then try to
dump these over getsockopt(sk, SOL_SOCKET, SO_GET_FILTER, ...),
the following panic appears:

  [49904.178642] BUG: unable to handle kernel NULL pointer dereference at (null)
  [49904.178762] IP: [<ffffffff81610fd9>] sk_get_filter+0x39/0x90
  [49904.182000] PGD 86fc9067 PUD 531a1067 PMD 0
  [49904.185196] Oops: 0000 [#1] SMP
  [...]
  [49904.224677] Call Trace:
  [49904.226090]  [<ffffffff815e3d49>] sock_getsockopt+0x319/0x740
  [49904.227535]  [<ffffffff812f59e3>] ? sock_has_perm+0x63/0x70
  [49904.228953]  [<ffffffff815e2fc8>] ? release_sock+0x108/0x150
  [49904.230380]  [<ffffffff812f5a43>] ? selinux_socket_getsockopt+0x23/0x30
  [49904.231788]  [<ffffffff815dff36>] SyS_getsockopt+0xa6/0xc0
  [49904.233267]  [<ffffffff8171b9ae>] entry_SYSCALL_64_fastpath+0x12/0x71

The underlying issue is the very same as in commit b382c0865600
("sock, diag: fix panic in sock_diag_put_filterinfo"), that is,
native eBPF programs don't store an original program since this
is only needed in cBPF ones.

However, sk_get_filter() wasn't updated to test for this at the
time when eBPF could be attached. Just throw an error to the user
to indicate that eBPF cannot be dumped over this interface.
That way, it can also be known that a program _is_ attached (as
opposed to just return 0), and a different (future) method needs
to be consulted for a dump.

Fixes: 89aa075832b0 ("net: sock: allow eBPF programs to be attached to sockets")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/filter.c |    6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index bf831a8..0fa2613 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1526,9 +1526,13 @@ int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf,
 		goto out;
 
 	/* We're copying the filter that has been originally attached,
-	 * so no conversion/decode needed anymore.
+	 * so no conversion/decode needed anymore. eBPF programs that
+	 * have no original program cannot be dumped through this.
 	 */
+	ret = -EACCES;
 	fprog = filter->prog->orig_prog;
+	if (!fprog)
+		goto out;
 
 	ret = fprog->len;
 	if (!len)
-- 
1.7.10.4


From 0ddb32e825e246d685c527ca025d0903d837d847 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Date: Fri, 2 Oct 2015 13:18:22 +0300
Subject: [PATCH 11/18] ovs: do not allocate memory from offline numa node

[ Upstream commit 598c12d0ba6de9060f04999746eb1e015774044b ]

When openvswitch tries allocate memory from offline numa node 0:
stats = kmem_cache_alloc_node(flow_stats_cache, GFP_KERNEL | __GFP_ZERO, 0)
It catches VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES || !node_online(nid))
[ replaced with VM_WARN_ON(!node_online(nid)) recently ] in linux/gfp.h
This patch disables numa affinity in this case.

Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/flow_table.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index aa34951..eed5622 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -92,7 +92,8 @@ struct sw_flow *ovs_flow_alloc(void)
 
 	/* Initialize the default stat node. */
 	stats = kmem_cache_alloc_node(flow_stats_cache,
-				      GFP_KERNEL | __GFP_ZERO, 0);
+				      GFP_KERNEL | __GFP_ZERO,
+				      node_online(0) ? 0 : NUMA_NO_NODE);
 	if (!stats)
 		goto err;
 
-- 
1.7.10.4


From ab801beaf1bcb1966b53125b24f1764407dd3250 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Tue, 6 Oct 2015 17:23:47 -0700
Subject: [PATCH 12/18] act_mirred: clear sender cpu before sending to tx

[ Upstream commit d40496a56430eac0d330378816954619899fe303 ]

Similar to commit c29390c6dfee ("xps: must clear sender_cpu before forwarding")
the skb->sender_cpu needs to be cleared when moving from Rx
Tx, otherwise kernel could crash.

Fixes: 2bd82484bb4c ("xps: fix xps for stacked devices")
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <cwang@twopensource.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_mirred.c |    1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 3f63cea..844dd85 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -166,6 +166,7 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
 
 	skb2->skb_iif = skb->dev->ifindex;
 	skb2->dev = dev;
+	skb_sender_cpu_clear(skb2);
 	err = dev_queue_xmit(skb2);
 
 out:
-- 
1.7.10.4


From bb254f2764e6ba490b9e5fcb2ea00c6be02deeb2 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Wed, 14 Oct 2015 01:09:40 -0700
Subject: [PATCH 13/18] ethtool: Use kcalloc instead of kmalloc for
 ethtool_get_strings

[ Upstream commit 077cb37fcf6f00a45f375161200b5ee0cd4e937b ]

It seems that kernel memory can leak into userspace by a
kmalloc, ethtool_get_strings, then copy_to_user sequence.

Avoid this by using kcalloc to zero fill the copied buffer.

Signed-off-by: Joe Perches <joe@perches.com>
Acked-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/ethtool.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 1d00b89..4a68247 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -1273,7 +1273,7 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr)
 
 	gstrings.len = ret;
 
-	data = kmalloc(gstrings.len * ETH_GSTRING_LEN, GFP_USER);
+	data = kcalloc(gstrings.len, ETH_GSTRING_LEN, GFP_USER);
 	if (!data)
 		return -ENOMEM;
 
-- 
1.7.10.4


From 173f34826985b5dd75d7d2d0c8b8894c5141ffef Mon Sep 17 00:00:00 2001
From: Jon Paul Maloy <jon.maloy@ericsson.com>
Date: Wed, 14 Oct 2015 09:23:18 -0400
Subject: [PATCH 14/18] tipc: move fragment importance field to new header
 position

[ Upstream commit dde4b5ae65de659b9ec64bafdde0430459fcb495 ]

In commit e3eea1eb47a ("tipc: clean up handling of message priorities")
we introduced a field in the packet header for keeping track of the
priority of fragments, since this value is not present in the specified
protocol header. Since the value so far only is used at the transmitting
end of the link, we have not yet officially defined it as part of the
protocol.

Unfortunately, the field we use for keeping this value, bits 13-15 in
in word 5, has turned out to be a poor choice; it is already used by the
broadcast protocol for carrying the 'network id' field of the sending
node. Since packet fragments also need to be transported across the
broadcast protocol, the risk of conflict is obvious, and we see this
happen when we use network identities larger than 2^13-1. This has
escaped our testing because we have so far only been using small network
id values.

We now move this field to bits 0-2 in word 9, a field that is guaranteed
to be unused by all involved protocols.

Fixes: e3eea1eb47a ("tipc: clean up handling of message priorities")
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/msg.h |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/tipc/msg.h b/net/tipc/msg.h
index e1d3595e..4cbb0fb 100644
--- a/net/tipc/msg.h
+++ b/net/tipc/msg.h
@@ -353,7 +353,7 @@ static inline void msg_set_seqno(struct tipc_msg *m, u32 n)
 static inline u32 msg_importance(struct tipc_msg *m)
 {
 	if (unlikely(msg_user(m) == MSG_FRAGMENTER))
-		return msg_bits(m, 5, 13, 0x7);
+		return msg_bits(m, 9, 0, 0x7);
 	if (likely(msg_isdata(m) && !msg_errcode(m)))
 		return msg_user(m);
 	return TIPC_SYSTEM_IMPORTANCE;
@@ -362,7 +362,7 @@ static inline u32 msg_importance(struct tipc_msg *m)
 static inline void msg_set_importance(struct tipc_msg *m, u32 i)
 {
 	if (unlikely(msg_user(m) == MSG_FRAGMENTER))
-		msg_set_bits(m, 5, 13, 0x7, i);
+		msg_set_bits(m, 9, 0, 0x7, i);
 	else if (likely(i < TIPC_SYSTEM_IMPORTANCE))
 		msg_set_user(m, i);
 	else
-- 
1.7.10.4


From 82ed1372a2af6f0b1282770ff1e1f1c7bc67a370 Mon Sep 17 00:00:00 2001
From: "Arad, Ronen" <ronen.arad@intel.com>
Date: Thu, 15 Oct 2015 01:55:17 -0700
Subject: [PATCH 15/18] netlink: Trim skb to alloc size to avoid MSG_TRUNC

[ Upstream commit db65a3aaf29ecce2e34271d52e8d2336b97bd9fe ]

netlink_dump() allocates skb based on the calculated min_dump_alloc or
a per socket max_recvmsg_len.
min_alloc_size is maximum space required for any single netdev
attributes as calculated by rtnl_calcit().
max_recvmsg_len tracks the user provided buffer to netlink_recvmsg.
It is capped at 16KiB.
The intention is to avoid small allocations and to minimize the number
of calls required to obtain dump information for all net devices.

netlink_dump packs as many small messages as could fit within an skb
that was sized for the largest single netdev information. The actual
space available within an skb is larger than what is requested. It could
be much larger and up to near 2x with align to next power of 2 approach.

Allowing netlink_dump to use all the space available within the
allocated skb increases the buffer size a user has to provide to avoid
truncaion (i.e. MSG_TRUNG flag set).

It was observed that with many VLANs configured on at least one netdev,
a larger buffer of near 64KiB was necessary to avoid "Message truncated"
error in "ip link" or "bridge [-c[ompressvlans]] vlan show" when
min_alloc_size was only little over 32KiB.

This patch trims skb to allocated size in order to allow the user to
avoid truncation with more reasonable buffer size.

Signed-off-by: Ronen Arad <ronen.arad@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c |   34 ++++++++++++++++++++++------------
 1 file changed, 22 insertions(+), 12 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 980121e..d139c43 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2683,6 +2683,7 @@ static int netlink_dump(struct sock *sk)
 	struct sk_buff *skb = NULL;
 	struct nlmsghdr *nlh;
 	int len, err = -ENOBUFS;
+	int alloc_min_size;
 	int alloc_size;
 
 	mutex_lock(nlk->cb_mutex);
@@ -2691,9 +2692,6 @@ static int netlink_dump(struct sock *sk)
 		goto errout_skb;
 	}
 
-	cb = &nlk->cb;
-	alloc_size = max_t(int, cb->min_dump_alloc, NLMSG_GOODSIZE);
-
 	if (!netlink_rx_is_mmaped(sk) &&
 	    atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
 		goto errout_skb;
@@ -2703,23 +2701,35 @@ static int netlink_dump(struct sock *sk)
 	 * to reduce number of system calls on dump operations, if user
 	 * ever provided a big enough buffer.
 	 */
-	if (alloc_size < nlk->max_recvmsg_len) {
-		skb = netlink_alloc_skb(sk,
-					nlk->max_recvmsg_len,
-					nlk->portid,
+	cb = &nlk->cb;
+	alloc_min_size = max_t(int, cb->min_dump_alloc, NLMSG_GOODSIZE);
+
+	if (alloc_min_size < nlk->max_recvmsg_len) {
+		alloc_size = nlk->max_recvmsg_len;
+		skb = netlink_alloc_skb(sk, alloc_size, nlk->portid,
 					GFP_KERNEL |
 					__GFP_NOWARN |
 					__GFP_NORETRY);
-		/* available room should be exact amount to avoid MSG_TRUNC */
-		if (skb)
-			skb_reserve(skb, skb_tailroom(skb) -
-					 nlk->max_recvmsg_len);
 	}
-	if (!skb)
+	if (!skb) {
+		alloc_size = alloc_min_size;
 		skb = netlink_alloc_skb(sk, alloc_size, nlk->portid,
 					GFP_KERNEL);
+	}
 	if (!skb)
 		goto errout_skb;
+
+	/* Trim skb to allocated size. User is expected to provide buffer as
+	 * large as max(min_dump_alloc, 16KiB (mac_recvmsg_len capped at
+	 * netlink_recvmsg())). dump will pack as many smaller messages as
+	 * could fit within the allocated skb. skb is typically allocated
+	 * with larger space than required (could be as much as near 2x the
+	 * requested size with align to next power of 2 approach). Allowing
+	 * dump to use the excess space makes it difficult for a user to have a
+	 * reasonable static buffer based on the expected largest dump of a
+	 * single netdev. The outcome is MSG_TRUNC error.
+	 */
+	skb_reserve(skb, skb_tailroom(skb) - alloc_size);
 	netlink_skb_set_owner_r(skb, sk);
 
 	len = cb->dump(skb, cb);
-- 
1.7.10.4


From f7893178be86e56ba69240363adfafb53039f118 Mon Sep 17 00:00:00 2001
From: Aaron Conole <aconole@bytheb.org>
Date: Sat, 26 Sep 2015 18:50:42 -0400
Subject: [PATCH 16/18] af_unix: Convert the unix_sk macro to an inline
 function for type safety

[ Upstream commit 4613012db1d911f80897f9446a49de817b2c4c47 ]

As suggested by Eric Dumazet this change replaces the
#define with a static inline function to enjoy
complaints by the compiler when misusing the API.

Signed-off-by: Aaron Conole <aconole@bytheb.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/af_unix.h |    6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index a175ba4..dfe4ddf 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -64,7 +64,11 @@ struct unix_sock {
 #define UNIX_GC_MAYBE_CYCLE	1
 	struct socket_wq	peer_wq;
 };
-#define unix_sk(__sk) ((struct unix_sock *)__sk)
+
+static inline struct unix_sock *unix_sk(struct sock *sk)
+{
+	return (struct unix_sock *)sk;
+}
 
 #define peer_wait peer_wq.wait
 
-- 
1.7.10.4


From 2eab2ebd93d9bad17c97736c9b737793361140d7 Mon Sep 17 00:00:00 2001
From: Aaron Conole <aconole@bytheb.org>
Date: Sat, 26 Sep 2015 18:50:43 -0400
Subject: [PATCH 17/18] af_unix: return data from multiple SKBs on recv() with
 MSG_PEEK flag

[ Upstream commit 9f389e35674f5b086edd70ed524ca0f287259725 ]

AF_UNIX sockets now return multiple skbs from recv() when MSG_PEEK flag
is set.

This is referenced in kernel bugzilla #12323 @
https://bugzilla.kernel.org/show_bug.cgi?id=12323

As described both in the BZ and lkml thread @
http://lkml.org/lkml/2008/1/8/444 calling recv() with MSG_PEEK on an
AF_UNIX socket only reads a single skb, where the desired effect is
to return as much skb data has been queued, until hitting the recv
buffer size (whichever comes first).

The modified MSG_PEEK path will now move to the next skb in the tree
and jump to the again: label, rather than following the natural loop
structure. This requires duplicating some of the loop head actions.

This was tested using the python socketpair python code attached to
the bugzilla issue.

Signed-off-by: Aaron Conole <aconole@bytheb.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c |   14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 0643059..5650154 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2046,8 +2046,20 @@ again:
 			if (UNIXCB(skb).fp)
 				scm.fp = scm_fp_dup(UNIXCB(skb).fp);
 
-			sk_peek_offset_fwd(sk, chunk);
+			if (skip) {
+				sk_peek_offset_fwd(sk, chunk);
+				skip -= chunk;
+			}
+
+			if (UNIXCB(skb).fp)
+				break;
 
+			last = skb;
+			unix_state_lock(sk);
+			skb = skb_peek_next(skb, &sk->sk_receive_queue);
+			if (skb)
+				goto again;
+			unix_state_unlock(sk);
 			break;
 		}
 	} while (size);
-- 
1.7.10.4


From ae0542285aa492f52c605b5d5589d66a1f1671b3 Mon Sep 17 00:00:00 2001
From: Andrey Vagin <avagin@openvz.org>
Date: Fri, 2 Oct 2015 00:05:36 +0300
Subject: [PATCH 18/18] net/unix: fix logic about sk_peek_offset

[ Upstream commit e9193d60d363e4dff75ff6d43a48f22be26d59c7 ]

Now send with MSG_PEEK can return data from multiple SKBs.

Unfortunately we take into account the peek offset for each skb,
that is wrong. We need to apply the peek offset only once.

In addition, the peek offset should be used only if MSG_PEEK is set.

Cc: "David S. Miller" <davem@davemloft.net> (maintainer:NETWORKING
Cc: Eric Dumazet <edumazet@google.com> (commit_signer:1/14=7%)
Cc: Aaron Conole <aconole@bytheb.org>
Fixes: 9f389e35674f ("af_unix: return data from multiple SKBs on recv() with MSG_PEEK flag")
Signed-off-by: Andrey Vagin <avagin@openvz.org>
Tested-by: Aaron Conole <aconole@bytheb.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c |   12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 5650154..76e6669 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1938,6 +1938,11 @@ static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg,
 		goto out;
 	}
 
+	if (flags & MSG_PEEK)
+		skip = sk_peek_offset(sk, flags);
+	else
+		skip = 0;
+
 	do {
 		int chunk;
 		struct sk_buff *skb, *last;
@@ -1984,7 +1989,6 @@ again:
 			break;
 		}
 
-		skip = sk_peek_offset(sk, flags);
 		while (skip >= unix_skb_len(skb)) {
 			skip -= unix_skb_len(skb);
 			last = skb;
@@ -2046,14 +2050,12 @@ again:
 			if (UNIXCB(skb).fp)
 				scm.fp = scm_fp_dup(UNIXCB(skb).fp);
 
-			if (skip) {
-				sk_peek_offset_fwd(sk, chunk);
-				skip -= chunk;
-			}
+			sk_peek_offset_fwd(sk, chunk);
 
 			if (UNIXCB(skb).fp)
 				break;
 
+			skip = 0;
 			last = skb;
 			unix_state_lock(sk);
 			skb = skb_peek_next(skb, &sk->sk_receive_queue);
-- 
1.7.10.4


[-- Attachment #5: net_42.mbox --]
[-- Type: Application/Octet-Stream, Size: 41782 bytes --]

From be261d994d7fab3b79f40cb2e9e431d300e853fe Mon Sep 17 00:00:00 2001
From: Ivan Mikhaylov <ivan@ru.ibm.com>
Date: Fri, 25 Sep 2015 11:52:27 +0400
Subject: [PATCH 01/20] net/ibm/emac: bump version numbers for correct work
 with ethtool

[ Upstream commit 661dfc65f7981481ba2e31aaa702371e82336e56 ]

The size of the MAC register dump used to be the size specified by the
reg property in the device tree.  Userland has no good way of finding
out that size, and it was not specified consistently for each MAC type,
so ethtool would end up printing junk at the end of the register dump
if the device tree didn't match the size it assumed.

Using the new version numbers indicates unambiguously that the size of
the MAC register dump is dependent only on the MAC type.

Fixes: 5369c71f7ca2 ("net/ibm/emac: fix size of emac dump memory areas")
Signed-off-by: Ivan Mikhaylov <ivan@ru.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ibm/emac/core.h |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/ibm/emac/core.h b/drivers/net/ethernet/ibm/emac/core.h
index 28df374..ac02c67 100644
--- a/drivers/net/ethernet/ibm/emac/core.h
+++ b/drivers/net/ethernet/ibm/emac/core.h
@@ -460,8 +460,8 @@ struct emac_ethtool_regs_subhdr {
 	u32 index;
 };
 
-#define EMAC_ETHTOOL_REGS_VER		0
-#define EMAC4_ETHTOOL_REGS_VER		1
-#define EMAC4SYNC_ETHTOOL_REGS_VER	2
+#define EMAC_ETHTOOL_REGS_VER		3
+#define EMAC4_ETHTOOL_REGS_VER		4
+#define EMAC4SYNC_ETHTOOL_REGS_VER	5
 
 #endif /* __IBM_NEWEMAC_CORE_H */
-- 
1.7.10.4


From d76890bbb8619c034f5008c49048f0ba24521258 Mon Sep 17 00:00:00 2001
From: Alexander Couzens <lynxis@fe80.eu>
Date: Mon, 28 Sep 2015 11:32:42 +0200
Subject: [PATCH 02/20] l2tp: protect tunnel->del_work by ref_count

[ Upstream commit 06a15f51cf3618e32a73871ee6a547ef7fd902b5 ]

There is a small chance that tunnel_free() is called before tunnel->del_work scheduled
resulting in a zero pointer dereference.

Signed-off-by: Alexander Couzens <lynxis@fe80.eu>
Acked-by: James Chapman <jchapman@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c |   11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index f6b090d..afca2eb 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1319,7 +1319,7 @@ static void l2tp_tunnel_del_work(struct work_struct *work)
 	tunnel = container_of(work, struct l2tp_tunnel, del_work);
 	sk = l2tp_tunnel_sock_lookup(tunnel);
 	if (!sk)
-		return;
+		goto out;
 
 	sock = sk->sk_socket;
 
@@ -1341,6 +1341,8 @@ static void l2tp_tunnel_del_work(struct work_struct *work)
 	}
 
 	l2tp_tunnel_sock_put(sk);
+out:
+	l2tp_tunnel_dec_refcount(tunnel);
 }
 
 /* Create a socket for the tunnel, if one isn't set up by
@@ -1636,8 +1638,13 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_create);
  */
 int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel)
 {
+	l2tp_tunnel_inc_refcount(tunnel);
 	l2tp_tunnel_closeall(tunnel);
-	return (false == queue_work(l2tp_wq, &tunnel->del_work));
+	if (false == queue_work(l2tp_wq, &tunnel->del_work)) {
+		l2tp_tunnel_dec_refcount(tunnel);
+		return 1;
+	}
+	return 0;
 }
 EXPORT_SYMBOL_GPL(l2tp_tunnel_delete);
 
-- 
1.7.10.4


From bf9e4ed11d69aac78162529d2f199ad62e689acc Mon Sep 17 00:00:00 2001
From: Aaron Conole <aconole@bytheb.org>
Date: Sat, 26 Sep 2015 18:50:42 -0400
Subject: [PATCH 03/20] af_unix: Convert the unix_sk macro to an inline
 function for type safety

[ Upstream commit 4613012db1d911f80897f9446a49de817b2c4c47 ]

As suggested by Eric Dumazet this change replaces the
#define with a static inline function to enjoy
complaints by the compiler when misusing the API.

Signed-off-by: Aaron Conole <aconole@bytheb.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/af_unix.h |    6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index 4a167b3..cb1b9bb 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -63,7 +63,11 @@ struct unix_sock {
 #define UNIX_GC_MAYBE_CYCLE	1
 	struct socket_wq	peer_wq;
 };
-#define unix_sk(__sk) ((struct unix_sock *)__sk)
+
+static inline struct unix_sock *unix_sk(struct sock *sk)
+{
+	return (struct unix_sock *)sk;
+}
 
 #define peer_wait peer_wq.wait
 
-- 
1.7.10.4


From ed06cb0f10edf95d142d0ccb3b0f8970295d354d Mon Sep 17 00:00:00 2001
From: Aaron Conole <aconole@bytheb.org>
Date: Sat, 26 Sep 2015 18:50:43 -0400
Subject: [PATCH 04/20] af_unix: return data from multiple SKBs on recv() with
 MSG_PEEK flag

[ Upstream commit 9f389e35674f5b086edd70ed524ca0f287259725 ]

AF_UNIX sockets now return multiple skbs from recv() when MSG_PEEK flag
is set.

This is referenced in kernel bugzilla #12323 @
https://bugzilla.kernel.org/show_bug.cgi?id=12323

As described both in the BZ and lkml thread @
http://lkml.org/lkml/2008/1/8/444 calling recv() with MSG_PEEK on an
AF_UNIX socket only reads a single skb, where the desired effect is
to return as much skb data has been queued, until hitting the recv
buffer size (whichever comes first).

The modified MSG_PEEK path will now move to the next skb in the tree
and jump to the again: label, rather than following the natural loop
structure. This requires duplicating some of the loop head actions.

This was tested using the python socketpair python code attached to
the bugzilla issue.

Signed-off-by: Aaron Conole <aconole@bytheb.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c |   15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 03ee4d3..ef31b40 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2179,8 +2179,21 @@ unlock:
 			if (UNIXCB(skb).fp)
 				scm.fp = scm_fp_dup(UNIXCB(skb).fp);
 
-			sk_peek_offset_fwd(sk, chunk);
+			if (skip) {
+				sk_peek_offset_fwd(sk, chunk);
+				skip -= chunk;
+			}
 
+			if (UNIXCB(skb).fp)
+				break;
+
+			last = skb;
+			last_len = skb->len;
+			unix_state_lock(sk);
+			skb = skb_peek_next(skb, &sk->sk_receive_queue);
+			if (skb)
+				goto again;
+			unix_state_unlock(sk);
 			break;
 		}
 	} while (size);
-- 
1.7.10.4


From 99e4bf81ede85e9f0c2848f14bfbdb31e7e51653 Mon Sep 17 00:00:00 2001
From: Andrey Vagin <avagin@openvz.org>
Date: Fri, 2 Oct 2015 00:05:36 +0300
Subject: [PATCH 05/20] net/unix: fix logic about sk_peek_offset

[ Upstream commit e9193d60d363e4dff75ff6d43a48f22be26d59c7 ]

Now send with MSG_PEEK can return data from multiple SKBs.

Unfortunately we take into account the peek offset for each skb,
that is wrong. We need to apply the peek offset only once.

In addition, the peek offset should be used only if MSG_PEEK is set.

Cc: "David S. Miller" <davem@davemloft.net> (maintainer:NETWORKING
Cc: Eric Dumazet <edumazet@google.com> (commit_signer:1/14=7%)
Cc: Aaron Conole <aconole@bytheb.org>
Fixes: 9f389e35674f ("af_unix: return data from multiple SKBs on recv() with MSG_PEEK flag")
Signed-off-by: Andrey Vagin <avagin@openvz.org>
Tested-by: Aaron Conole <aconole@bytheb.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c |   12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index ef31b40..94f6582 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2064,6 +2064,11 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state)
 		goto out;
 	}
 
+	if (flags & MSG_PEEK)
+		skip = sk_peek_offset(sk, flags);
+	else
+		skip = 0;
+
 	do {
 		int chunk;
 		struct sk_buff *skb, *last;
@@ -2112,7 +2117,6 @@ unlock:
 			break;
 		}
 
-		skip = sk_peek_offset(sk, flags);
 		while (skip >= unix_skb_len(skb)) {
 			skip -= unix_skb_len(skb);
 			last = skb;
@@ -2179,14 +2183,12 @@ unlock:
 			if (UNIXCB(skb).fp)
 				scm.fp = scm_fp_dup(UNIXCB(skb).fp);
 
-			if (skip) {
-				sk_peek_offset_fwd(sk, chunk);
-				skip -= chunk;
-			}
+			sk_peek_offset_fwd(sk, chunk);
 
 			if (UNIXCB(skb).fp)
 				break;
 
+			skip = 0;
 			last = skb;
 			last_len = skb->len;
 			unix_state_lock(sk);
-- 
1.7.10.4


From b41a7da45e90266a70b541a5cb242e598d296b09 Mon Sep 17 00:00:00 2001
From: Pravin B Shelar <pshelar@nicira.com>
Date: Tue, 22 Sep 2015 12:57:53 -0700
Subject: [PATCH 06/20] skbuff: Fix skb checksum flag on skb pull

[ Upstream commit 6ae459bdaaeebc632b16e54dcbabb490c6931d61 ]

VXLAN device can receive skb with checksum partial. But the checksum
offset could be in outer header which is pulled on receive. This results
in negative checksum offset for the skb. Such skb can cause the assert
failure in skb_checksum_help(). Following patch fixes the bug by setting
checksum-none while pulling outer header.

Following is the kernel panic msg from old kernel hitting the bug.

------------[ cut here ]------------
kernel BUG at net/core/dev.c:1906!
RIP: 0010:[<ffffffff81518034>] skb_checksum_help+0x144/0x150
Call Trace:
<IRQ>
[<ffffffffa0164c28>] queue_userspace_packet+0x408/0x470 [openvswitch]
[<ffffffffa016614d>] ovs_dp_upcall+0x5d/0x60 [openvswitch]
[<ffffffffa0166236>] ovs_dp_process_packet_with_key+0xe6/0x100 [openvswitch]
[<ffffffffa016629b>] ovs_dp_process_received_packet+0x4b/0x80 [openvswitch]
[<ffffffffa016c51a>] ovs_vport_receive+0x2a/0x30 [openvswitch]
[<ffffffffa0171383>] vxlan_rcv+0x53/0x60 [openvswitch]
[<ffffffffa01734cb>] vxlan_udp_encap_recv+0x8b/0xf0 [openvswitch]
[<ffffffff8157addc>] udp_queue_rcv_skb+0x2dc/0x3b0
[<ffffffff8157b56f>] __udp4_lib_rcv+0x1cf/0x6c0
[<ffffffff8157ba7a>] udp_rcv+0x1a/0x20
[<ffffffff8154fdbd>] ip_local_deliver_finish+0xdd/0x280
[<ffffffff81550128>] ip_local_deliver+0x88/0x90
[<ffffffff8154fa7d>] ip_rcv_finish+0x10d/0x370
[<ffffffff81550365>] ip_rcv+0x235/0x300
[<ffffffff8151ba1d>] __netif_receive_skb+0x55d/0x620
[<ffffffff8151c360>] netif_receive_skb+0x80/0x90
[<ffffffff81459935>] virtnet_poll+0x555/0x6f0
[<ffffffff8151cd04>] net_rx_action+0x134/0x290
[<ffffffff810683d8>] __do_softirq+0xa8/0x210
[<ffffffff8162fe6c>] call_softirq+0x1c/0x30
[<ffffffff810161a5>] do_softirq+0x65/0xa0
[<ffffffff810687be>] irq_exit+0x8e/0xb0
[<ffffffff81630733>] do_IRQ+0x63/0xe0
[<ffffffff81625f2e>] common_interrupt+0x6e/0x6e

Reported-by: Anupam Chanda <achanda@vmware.com>
Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
Acked-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h |    3 +++
 1 file changed, 3 insertions(+)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 9b88536..e2ee6a7 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2601,6 +2601,9 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb,
 {
 	if (skb->ip_summed == CHECKSUM_COMPLETE)
 		skb->csum = csum_sub(skb->csum, csum_partial(start, len, 0));
+	else if (skb->ip_summed == CHECKSUM_PARTIAL &&
+		 skb_checksum_start_offset(skb) <= len)
+		skb->ip_summed = CHECKSUM_NONE;
 }
 
 unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len);
-- 
1.7.10.4


From 5d56583dc44aae8f96931ab7fb800dbfbc141e07 Mon Sep 17 00:00:00 2001
From: Pravin B Shelar <pshelar@nicira.com>
Date: Mon, 28 Sep 2015 17:24:25 -0700
Subject: [PATCH 07/20] skbuff: Fix skb checksum partial check.

[ Upstream commit 31b33dfb0a144469dd805514c9e63f4993729a48 ]

Earlier patch 6ae459bda tried to detect void ckecksum partial
skb by comparing pull length to checksum offset. But it does
not work for all cases since checksum-offset depends on
updates to skb->data.

Following patch fixes it by validating checksum start offset
after skb-data pointer is updated. Negative value of checksum
offset start means there is no need to checksum.

Fixes: 6ae459bda ("skbuff: Fix skb checksum flag on skb pull")
Reported-by: Andrew Vagin <avagin@odin.com>
Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h |    2 +-
 net/core/skbuff.c      |    9 +++++----
 2 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index e2ee6a7..2751588 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2602,7 +2602,7 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb,
 	if (skb->ip_summed == CHECKSUM_COMPLETE)
 		skb->csum = csum_sub(skb->csum, csum_partial(start, len, 0));
 	else if (skb->ip_summed == CHECKSUM_PARTIAL &&
-		 skb_checksum_start_offset(skb) <= len)
+		 skb_checksum_start_offset(skb) < 0)
 		skb->ip_summed = CHECKSUM_NONE;
 }
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 7b84330..7bfa187 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2958,11 +2958,12 @@ EXPORT_SYMBOL_GPL(skb_append_pagefrags);
  */
 unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len)
 {
+	unsigned char *data = skb->data;
+
 	BUG_ON(len > skb->len);
-	skb->len -= len;
-	BUG_ON(skb->len < skb->data_len);
-	skb_postpull_rcsum(skb, skb->data, len);
-	return skb->data += len;
+	__skb_pull(skb, len);
+	skb_postpull_rcsum(skb, data, len);
+	return skb->data;
 }
 EXPORT_SYMBOL_GPL(skb_pull_rcsum);
 
-- 
1.7.10.4


From b028d7f989b21622f3b7721b7a0b2c2410e85d11 Mon Sep 17 00:00:00 2001
From: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Date: Tue, 29 Sep 2015 14:17:54 -0400
Subject: [PATCH 08/20] net: dsa: fix preparation of a port STP update

[ Upstream commit 57a47532c4312159935c98b7f1cf0e62296b9171 ]

Because of the default 0 value of ret in dsa_slave_port_attr_set, a
driver may return -EOPNOTSUPP from the commit phase of a STP state,
which triggers a WARN() from switchdev.

This happened on a 6185 switch which does not support hardware bridging.

Fixes: 3563606258cf ("switchdev: convert STP update to switchdev attr set")
Reported-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/slave.c |   11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 35c47dd..25dbb91 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -348,12 +348,17 @@ static int dsa_slave_stp_update(struct net_device *dev, u8 state)
 static int dsa_slave_port_attr_set(struct net_device *dev,
 				   struct switchdev_attr *attr)
 {
-	int ret = 0;
+	struct dsa_slave_priv *p = netdev_priv(dev);
+	struct dsa_switch *ds = p->parent;
+	int ret;
 
 	switch (attr->id) {
 	case SWITCHDEV_ATTR_PORT_STP_STATE:
-		if (attr->trans == SWITCHDEV_TRANS_COMMIT)
-			ret = dsa_slave_stp_update(dev, attr->u.stp_state);
+		if (attr->trans == SWITCHDEV_TRANS_PREPARE)
+			ret = ds->drv->port_stp_update ? 0 : -EOPNOTSUPP;
+		else
+			ret = ds->drv->port_stp_update(ds, p->port,
+						       attr->u.stp_state);
 		break;
 	default:
 		ret = -EOPNOTSUPP;
-- 
1.7.10.4


From 1d9625c1ea80d1faf74434badf62a17bb71fcb6f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 19 Sep 2015 09:48:04 -0700
Subject: [PATCH 09/20] inet: fix races in reqsk_queue_hash_req()

[ Upstream commit 29c6852602e259d2c1882f320b29d5c3fec0de04 ]

Before allowing lockless LISTEN processing, we need to make
sure to arm the SYN_RECV timer before the req socket is visible
in hash tables.

Also, req->rsk_hash should be written before we set rsk_refcnt
to a non zero value.

Fixes: fa76ce7328b2 ("inet: get rid of central tcp/dccp listener timer")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Ying Cai <ycai@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/inet_connection_sock.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 1349571..7bb9c39 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -685,20 +685,20 @@ void reqsk_queue_hash_req(struct request_sock_queue *queue,
 	req->num_timeout = 0;
 	req->sk = NULL;
 
+	setup_timer(&req->rsk_timer, reqsk_timer_handler, (unsigned long)req);
+	mod_timer_pinned(&req->rsk_timer, jiffies + timeout);
+	req->rsk_hash = hash;
+
 	/* before letting lookups find us, make sure all req fields
 	 * are committed to memory and refcnt initialized.
 	 */
 	smp_wmb();
 	atomic_set(&req->rsk_refcnt, 2);
-	setup_timer(&req->rsk_timer, reqsk_timer_handler, (unsigned long)req);
-	req->rsk_hash = hash;
 
 	spin_lock(&queue->syn_wait_lock);
 	req->dl_next = lopt->syn_table[hash];
 	lopt->syn_table[hash] = req;
 	spin_unlock(&queue->syn_wait_lock);
-
-	mod_timer_pinned(&req->rsk_timer, jiffies + timeout);
 }
 EXPORT_SYMBOL(reqsk_queue_hash_req);
 
-- 
1.7.10.4


From 34207b9dfc25351e761133ffdd2824890e32073a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 29 Sep 2015 18:52:25 -0700
Subject: [PATCH 10/20] net: add pfmemalloc check in sk_add_backlog()

[ Upstream commit c7c49b8fde26b74277188bdc6c9dca38db6fa35b ]

Greg reported crashes hitting the following check in __sk_backlog_rcv()

	BUG_ON(!sock_flag(sk, SOCK_MEMALLOC));

The pfmemalloc bit is currently checked in sk_filter().

This works correctly for TCP, because sk_filter() is ran in
tcp_v[46]_rcv() before hitting the prequeue or backlog checks.

For UDP or other protocols, this does not work, because the sk_filter()
is ran from sock_queue_rcv_skb(), which might be called _after_ backlog
queuing if socket is owned by user by the time packet is processed by
softirq handler.

Fixes: b4b9e35585089 ("netvm: set PF_MEMALLOC as appropriate during SKB processing")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Greg Thelen <gthelen@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h |    8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/include/net/sock.h b/include/net/sock.h
index f21f070..4ca4c3f 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -826,6 +826,14 @@ static inline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *s
 	if (sk_rcvqueues_full(sk, limit))
 		return -ENOBUFS;
 
+	/*
+	 * If the skb was allocated from pfmemalloc reserves, only
+	 * allow SOCK_MEMALLOC sockets to use it as this socket is
+	 * helping free memory
+	 */
+	if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC))
+		return -ENOMEM;
+
 	__sk_add_backlog(sk, skb);
 	sk->sk_backlog.len += skb->truesize;
 	return 0;
-- 
1.7.10.4


From 34c2c7c6ef8ed5279b7aa193ca4401cf8631e9d2 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Wed, 30 Sep 2015 11:45:33 +0200
Subject: [PATCH 11/20] ppp: don't override sk->sk_state in pppoe_flush_dev()

[ Upstream commit e6740165b8f7f06d8caee0fceab3fb9d790a6fed ]

Since commit 2b018d57ff18 ("pppoe: drop PPPOX_ZOMBIEs in pppoe_release"),
pppoe_release() calls dev_put(po->pppoe_dev) if sk is in the
PPPOX_ZOMBIE state. But pppoe_flush_dev() can set sk->sk_state to
PPPOX_ZOMBIE _and_ reset po->pppoe_dev to NULL. This leads to the
following oops:

[  570.140800] BUG: unable to handle kernel NULL pointer dereference at 00000000000004e0
[  570.142931] IP: [<ffffffffa018c701>] pppoe_release+0x50/0x101 [pppoe]
[  570.144601] PGD 3d119067 PUD 3dbc1067 PMD 0
[  570.144601] Oops: 0000 [#1] SMP
[  570.144601] Modules linked in: l2tp_ppp l2tp_netlink l2tp_core ip6_udp_tunnel udp_tunnel pppoe pppox ppp_generic slhc loop crc32c_intel ghash_clmulni_intel jitterentropy_rng sha256_generic hmac drbg ansi_cprng aesni_intel aes_x86_64 ablk_helper cryptd lrw gf128mul glue_helper acpi_cpufreq evdev serio_raw processor button ext4 crc16 mbcache jbd2 virtio_net virtio_blk virtio_pci virtio_ring virtio
[  570.144601] CPU: 1 PID: 15738 Comm: ppp-apitest Not tainted 4.2.0 #1
[  570.144601] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Debian-1.8.2-1 04/01/2014
[  570.144601] task: ffff88003d30d600 ti: ffff880036b60000 task.ti: ffff880036b60000
[  570.144601] RIP: 0010:[<ffffffffa018c701>]  [<ffffffffa018c701>] pppoe_release+0x50/0x101 [pppoe]
[  570.144601] RSP: 0018:ffff880036b63e08  EFLAGS: 00010202
[  570.144601] RAX: 0000000000000000 RBX: ffff880034340000 RCX: 0000000000000206
[  570.144601] RDX: 0000000000000006 RSI: ffff88003d30dd20 RDI: ffff88003d30dd20
[  570.144601] RBP: ffff880036b63e28 R08: 0000000000000001 R09: 0000000000000000
[  570.144601] R10: 00007ffee9b50420 R11: ffff880034340078 R12: ffff8800387ec780
[  570.144601] R13: ffff8800387ec7b0 R14: ffff88003e222aa0 R15: ffff8800387ec7b0
[  570.144601] FS:  00007f5672f48700(0000) GS:ffff88003fc80000(0000) knlGS:0000000000000000
[  570.144601] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  570.144601] CR2: 00000000000004e0 CR3: 0000000037f7e000 CR4: 00000000000406a0
[  570.144601] Stack:
[  570.144601]  ffffffffa018f240 ffff8800387ec780 ffffffffa018f240 ffff8800387ec7b0
[  570.144601]  ffff880036b63e48 ffffffff812caabe ffff880039e4e000 0000000000000008
[  570.144601]  ffff880036b63e58 ffffffff812cabad ffff880036b63ea8 ffffffff811347f5
[  570.144601] Call Trace:
[  570.144601]  [<ffffffff812caabe>] sock_release+0x1a/0x75
[  570.144601]  [<ffffffff812cabad>] sock_close+0xd/0x11
[  570.144601]  [<ffffffff811347f5>] __fput+0xff/0x1a5
[  570.144601]  [<ffffffff811348cb>] ____fput+0x9/0xb
[  570.144601]  [<ffffffff81056682>] task_work_run+0x66/0x90
[  570.144601]  [<ffffffff8100189e>] prepare_exit_to_usermode+0x8c/0xa7
[  570.144601]  [<ffffffff81001a26>] syscall_return_slowpath+0x16d/0x19b
[  570.144601]  [<ffffffff813babb1>] int_ret_from_sys_call+0x25/0x9f
[  570.144601] Code: 48 8b 83 c8 01 00 00 a8 01 74 12 48 89 df e8 8b 27 14 e1 b8 f7 ff ff ff e9 b7 00 00 00 8a 43 12 a8 0b 74 1c 48 8b 83 a8 04 00 00 <48> 8b 80 e0 04 00 00 65 ff 08 48 c7 83 a8 04 00 00 00 00 00 00
[  570.144601] RIP  [<ffffffffa018c701>] pppoe_release+0x50/0x101 [pppoe]
[  570.144601]  RSP <ffff880036b63e08>
[  570.144601] CR2: 00000000000004e0
[  570.200518] ---[ end trace 46956baf17349563 ]---

pppoe_flush_dev() has no reason to override sk->sk_state with
PPPOX_ZOMBIE. pppox_unbind_sock() already sets sk->sk_state to
PPPOX_DEAD, which is the correct state given that sk is unbound and
po->pppoe_dev is NULL.

Fixes: 2b018d57ff18 ("pppoe: drop PPPOX_ZOMBIEs in pppoe_release")
Tested-by: Oleksii Berezhniak <core@irc.lg.ua>
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pppoe.c |    1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 3837ae3..2ed7506 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -313,7 +313,6 @@ static void pppoe_flush_dev(struct net_device *dev)
 			if (po->pppoe_dev == dev &&
 			    sk->sk_state & (PPPOX_CONNECTED | PPPOX_BOUND | PPPOX_ZOMBIE)) {
 				pppox_unbind_sock(sk);
-				sk->sk_state = PPPOX_ZOMBIE;
 				sk->sk_state_change(sk);
 				po->pppoe_dev = NULL;
 				dev_put(dev);
-- 
1.7.10.4


From d96e9f3dd117d780769c65807df0a251566a3615 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 1 Oct 2015 05:39:26 -0700
Subject: [PATCH 12/20] inet: fix race in reqsk_queue_unlink()

[ Upstream commit 2306c704ce280c97a60d1f45333b822b40281dea ]

reqsk_timer_handler() tests if icsk_accept_queue.listen_opt
is NULL at its beginning.

By the time it calls inet_csk_reqsk_queue_drop() and
reqsk_queue_unlink(), listener might have been closed and
inet_csk_listen_stop() had called reqsk_queue_yank_acceptq()
which sets icsk_accept_queue.listen_opt to NULL

We therefore need to correctly check listen_opt being NULL
after holding syn_wait_lock for proper synchronization.

Fixes: fa76ce7328b2 ("inet: get rid of central tcp/dccp listener timer")
Fixes: b357a364c57c ("inet: fix possible panic in reqsk_queue_unlink()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/inet_connection_sock.c |   19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 7bb9c39..61b45a1 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -577,21 +577,22 @@ EXPORT_SYMBOL(inet_rtx_syn_ack);
 static bool reqsk_queue_unlink(struct request_sock_queue *queue,
 			       struct request_sock *req)
 {
-	struct listen_sock *lopt = queue->listen_opt;
 	struct request_sock **prev;
+	struct listen_sock *lopt;
 	bool found = false;
 
 	spin_lock(&queue->syn_wait_lock);
-
-	for (prev = &lopt->syn_table[req->rsk_hash]; *prev != NULL;
-	     prev = &(*prev)->dl_next) {
-		if (*prev == req) {
-			*prev = req->dl_next;
-			found = true;
-			break;
+	lopt = queue->listen_opt;
+	if (lopt) {
+		for (prev = &lopt->syn_table[req->rsk_hash]; *prev != NULL;
+		     prev = &(*prev)->dl_next) {
+			if (*prev == req) {
+				*prev = req->dl_next;
+				found = true;
+				break;
+			}
 		}
 	}
-
 	spin_unlock(&queue->syn_wait_lock);
 	if (timer_pending(&req->rsk_timer) && del_timer_sync(&req->rsk_timer))
 		reqsk_put(req);
-- 
1.7.10.4


From 2b4663cc3eff93245d71a7a611a6760a526ca309 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 2 Oct 2015 12:06:03 +0200
Subject: [PATCH 13/20] bpf: fix panic in SO_GET_FILTER with native ebpf
 programs

[ Upstream commit 93d08b6966cf730ea669d4d98f43627597077153 ]

When sockets have a native eBPF program attached through
setsockopt(sk, SOL_SOCKET, SO_ATTACH_BPF, ...), and then try to
dump these over getsockopt(sk, SOL_SOCKET, SO_GET_FILTER, ...),
the following panic appears:

  [49904.178642] BUG: unable to handle kernel NULL pointer dereference at (null)
  [49904.178762] IP: [<ffffffff81610fd9>] sk_get_filter+0x39/0x90
  [49904.182000] PGD 86fc9067 PUD 531a1067 PMD 0
  [49904.185196] Oops: 0000 [#1] SMP
  [...]
  [49904.224677] Call Trace:
  [49904.226090]  [<ffffffff815e3d49>] sock_getsockopt+0x319/0x740
  [49904.227535]  [<ffffffff812f59e3>] ? sock_has_perm+0x63/0x70
  [49904.228953]  [<ffffffff815e2fc8>] ? release_sock+0x108/0x150
  [49904.230380]  [<ffffffff812f5a43>] ? selinux_socket_getsockopt+0x23/0x30
  [49904.231788]  [<ffffffff815dff36>] SyS_getsockopt+0xa6/0xc0
  [49904.233267]  [<ffffffff8171b9ae>] entry_SYSCALL_64_fastpath+0x12/0x71

The underlying issue is the very same as in commit b382c0865600
("sock, diag: fix panic in sock_diag_put_filterinfo"), that is,
native eBPF programs don't store an original program since this
is only needed in cBPF ones.

However, sk_get_filter() wasn't updated to test for this at the
time when eBPF could be attached. Just throw an error to the user
to indicate that eBPF cannot be dumped over this interface.
That way, it can also be known that a program _is_ attached (as
opposed to just return 0), and a different (future) method needs
to be consulted for a dump.

Fixes: 89aa075832b0 ("net: sock: allow eBPF programs to be attached to sockets")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/filter.c |    6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index be3098f..4c74ae9 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1701,9 +1701,13 @@ int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf,
 		goto out;
 
 	/* We're copying the filter that has been originally attached,
-	 * so no conversion/decode needed anymore.
+	 * so no conversion/decode needed anymore. eBPF programs that
+	 * have no original program cannot be dumped through this.
 	 */
+	ret = -EACCES;
 	fprog = filter->prog->orig_prog;
+	if (!fprog)
+		goto out;
 
 	ret = fprog->len;
 	if (!len)
-- 
1.7.10.4


From 58e4bf2d98fcd7ea3f8a69adc458557c40372255 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Date: Fri, 2 Oct 2015 13:18:22 +0300
Subject: [PATCH 14/20] ovs: do not allocate memory from offline numa node

[ Upstream commit 598c12d0ba6de9060f04999746eb1e015774044b ]

When openvswitch tries allocate memory from offline numa node 0:
stats = kmem_cache_alloc_node(flow_stats_cache, GFP_KERNEL | __GFP_ZERO, 0)
It catches VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES || !node_online(nid))
[ replaced with VM_WARN_ON(!node_online(nid)) recently ] in linux/gfp.h
This patch disables numa affinity in this case.

Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/flow_table.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index b5c3bba..af08e6f 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -92,7 +92,8 @@ struct sw_flow *ovs_flow_alloc(void)
 
 	/* Initialize the default stat node. */
 	stats = kmem_cache_alloc_node(flow_stats_cache,
-				      GFP_KERNEL | __GFP_ZERO, 0);
+				      GFP_KERNEL | __GFP_ZERO,
+				      node_online(0) ? 0 : NUMA_NO_NODE);
 	if (!stats)
 		goto err;
 
-- 
1.7.10.4


From a0ed131dc4f7a2ad36fd557d5bcdd7b342039510 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Tue, 6 Oct 2015 17:23:47 -0700
Subject: [PATCH 15/20] act_mirred: clear sender cpu before sending to tx

[ Upstream commit d40496a56430eac0d330378816954619899fe303 ]

Similar to commit c29390c6dfee ("xps: must clear sender_cpu before forwarding")
the skb->sender_cpu needs to be cleared when moving from Rx
Tx, otherwise kernel could crash.

Fixes: 2bd82484bb4c ("xps: fix xps for stacked devices")
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <cwang@twopensource.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_mirred.c |    1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 2685450..b176819 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -168,6 +168,7 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
 
 	skb2->skb_iif = skb->dev->ifindex;
 	skb2->dev = dev;
+	skb_sender_cpu_clear(skb2);
 	err = dev_queue_xmit(skb2);
 
 out:
-- 
1.7.10.4


From 13e6622f10625bb19934a2572cf2685903ee5168 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@plumgrid.com>
Date: Tue, 6 Oct 2015 20:46:07 -0700
Subject: [PATCH 16/20] bpf: clear sender_cpu before xmit

[ Upstream commit 6bf0577374cfb6c2301dbf4934a4f23ad3d72763 ]

Similar to commit c29390c6dfee ("xps: must clear sender_cpu before forwarding")
the skb->sender_cpu needs to be cleared before xmit.

Fixes: 3896d655f4d4 ("bpf: introduce bpf_clone_redirect() helper")
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/filter.c |    1 +
 1 file changed, 1 insertion(+)

diff --git a/net/core/filter.c b/net/core/filter.c
index 4c74ae9..8dcdd86 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1412,6 +1412,7 @@ static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5)
 		return dev_forward_skb(dev, skb2);
 
 	skb2->dev = dev;
+	skb_sender_cpu_clear(skb2);
 	return dev_queue_xmit(skb2);
 }
 
-- 
1.7.10.4


From d318c3c901f7e32f11cfd7f6828a33bd1d853321 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Mon, 12 Oct 2015 11:02:08 -0500
Subject: [PATCH 17/20] ipv6: Don't call with rt6_uncached_list_flush_dev

[ Upstream commit e332bc67cf5e5e5b71a1aec9750d0791aac65183 ]

As originally written rt6_uncached_list_flush_dev makes no sense when
called with dev == NULL as it attempts to flush all uncached routes
regardless of network namespace when dev == NULL.  Which is simply
incorrect behavior.

Furthermore at the point rt6_ifdown is called with dev == NULL no more
network devices exist in the network namespace so even if the code in
rt6_uncached_list_flush_dev were to attempt something sensible it
would be meaningless.

Therefore remove support in rt6_uncached_list_flush_dev for handling
network devices where dev == NULL, and only call rt6_uncached_list_flush_dev
 when rt6_ifdown is called with a network device.

Fixes: 8d0b94afdca8 ("ipv6: Keep track of DST_NOCACHE routes in case of iface down/unregister")
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Reviewed-by: Martin KaFai Lau <kafai@fb.com>
Tested-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c |   12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 00b64d4..dd6ebba 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -139,6 +139,9 @@ static void rt6_uncached_list_flush_dev(struct net *net, struct net_device *dev)
 	struct net_device *loopback_dev = net->loopback_dev;
 	int cpu;
 
+	if (dev == loopback_dev)
+		return;
+
 	for_each_possible_cpu(cpu) {
 		struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu);
 		struct rt6_info *rt;
@@ -148,14 +151,12 @@ static void rt6_uncached_list_flush_dev(struct net *net, struct net_device *dev)
 			struct inet6_dev *rt_idev = rt->rt6i_idev;
 			struct net_device *rt_dev = rt->dst.dev;
 
-			if (rt_idev && (rt_idev->dev == dev || !dev) &&
-			    rt_idev->dev != loopback_dev) {
+			if (rt_idev->dev == dev) {
 				rt->rt6i_idev = in6_dev_get(loopback_dev);
 				in6_dev_put(rt_idev);
 			}
 
-			if (rt_dev && (rt_dev == dev || !dev) &&
-			    rt_dev != loopback_dev) {
+			if (rt_dev == dev) {
 				rt->dst.dev = loopback_dev;
 				dev_hold(rt->dst.dev);
 				dev_put(rt_dev);
@@ -2577,7 +2578,8 @@ void rt6_ifdown(struct net *net, struct net_device *dev)
 
 	fib6_clean_all(net, fib6_ifdown, &adn);
 	icmp6_clean_all(fib6_ifdown, &adn);
-	rt6_uncached_list_flush_dev(net, dev);
+	if (dev)
+		rt6_uncached_list_flush_dev(net, dev);
 }
 
 struct rt6_mtu_change_arg {
-- 
1.7.10.4


From b10e900b269cdb6c1d7e816fc515f791ccbdbffd Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Wed, 14 Oct 2015 01:09:40 -0700
Subject: [PATCH 18/20] ethtool: Use kcalloc instead of kmalloc for
 ethtool_get_strings

[ Upstream commit 077cb37fcf6f00a45f375161200b5ee0cd4e937b ]

It seems that kernel memory can leak into userspace by a
kmalloc, ethtool_get_strings, then copy_to_user sequence.

Avoid this by using kcalloc to zero fill the copied buffer.

Signed-off-by: Joe Perches <joe@perches.com>
Acked-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/ethtool.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index b495ab1..29edf74 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -1284,7 +1284,7 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr)
 
 	gstrings.len = ret;
 
-	data = kmalloc(gstrings.len * ETH_GSTRING_LEN, GFP_USER);
+	data = kcalloc(gstrings.len, ETH_GSTRING_LEN, GFP_USER);
 	if (!data)
 		return -ENOMEM;
 
-- 
1.7.10.4


From 211b7f420dd72366e55cce872e1375f8b22ee284 Mon Sep 17 00:00:00 2001
From: Jon Paul Maloy <jon.maloy@ericsson.com>
Date: Wed, 14 Oct 2015 09:23:18 -0400
Subject: [PATCH 19/20] tipc: move fragment importance field to new header
 position

[ Upstream commit dde4b5ae65de659b9ec64bafdde0430459fcb495 ]

In commit e3eea1eb47a ("tipc: clean up handling of message priorities")
we introduced a field in the packet header for keeping track of the
priority of fragments, since this value is not present in the specified
protocol header. Since the value so far only is used at the transmitting
end of the link, we have not yet officially defined it as part of the
protocol.

Unfortunately, the field we use for keeping this value, bits 13-15 in
in word 5, has turned out to be a poor choice; it is already used by the
broadcast protocol for carrying the 'network id' field of the sending
node. Since packet fragments also need to be transported across the
broadcast protocol, the risk of conflict is obvious, and we see this
happen when we use network identities larger than 2^13-1. This has
escaped our testing because we have so far only been using small network
id values.

We now move this field to bits 0-2 in word 9, a field that is guaranteed
to be unused by all involved protocols.

Fixes: e3eea1eb47a ("tipc: clean up handling of message priorities")
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/msg.h |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/tipc/msg.h b/net/tipc/msg.h
index 19c45fb..49f9a96 100644
--- a/net/tipc/msg.h
+++ b/net/tipc/msg.h
@@ -357,7 +357,7 @@ static inline u32 msg_importance(struct tipc_msg *m)
 	if (likely((usr <= TIPC_CRITICAL_IMPORTANCE) && !msg_errcode(m)))
 		return usr;
 	if ((usr == MSG_FRAGMENTER) || (usr == MSG_BUNDLER))
-		return msg_bits(m, 5, 13, 0x7);
+		return msg_bits(m, 9, 0, 0x7);
 	return TIPC_SYSTEM_IMPORTANCE;
 }
 
@@ -366,7 +366,7 @@ static inline void msg_set_importance(struct tipc_msg *m, u32 i)
 	int usr = msg_user(m);
 
 	if (likely((usr == MSG_FRAGMENTER) || (usr == MSG_BUNDLER)))
-		msg_set_bits(m, 5, 13, 0x7, i);
+		msg_set_bits(m, 9, 0, 0x7, i);
 	else if (i < TIPC_SYSTEM_IMPORTANCE)
 		msg_set_user(m, i);
 	else
-- 
1.7.10.4


From 2c12b92ce32a5c183cbdac7e250d03b3effd8fb6 Mon Sep 17 00:00:00 2001
From: "Arad, Ronen" <ronen.arad@intel.com>
Date: Thu, 15 Oct 2015 01:55:17 -0700
Subject: [PATCH 20/20] netlink: Trim skb to alloc size to avoid MSG_TRUNC

[ Upstream commit db65a3aaf29ecce2e34271d52e8d2336b97bd9fe ]

netlink_dump() allocates skb based on the calculated min_dump_alloc or
a per socket max_recvmsg_len.
min_alloc_size is maximum space required for any single netdev
attributes as calculated by rtnl_calcit().
max_recvmsg_len tracks the user provided buffer to netlink_recvmsg.
It is capped at 16KiB.
The intention is to avoid small allocations and to minimize the number
of calls required to obtain dump information for all net devices.

netlink_dump packs as many small messages as could fit within an skb
that was sized for the largest single netdev information. The actual
space available within an skb is larger than what is requested. It could
be much larger and up to near 2x with align to next power of 2 approach.

Allowing netlink_dump to use all the space available within the
allocated skb increases the buffer size a user has to provide to avoid
truncaion (i.e. MSG_TRUNG flag set).

It was observed that with many VLANs configured on at least one netdev,
a larger buffer of near 64KiB was necessary to avoid "Message truncated"
error in "ip link" or "bridge [-c[ompressvlans]] vlan show" when
min_alloc_size was only little over 32KiB.

This patch trims skb to allocated size in order to allow the user to
avoid truncation with more reasonable buffer size.

Signed-off-by: Ronen Arad <ronen.arad@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c |   34 ++++++++++++++++++++++------------
 1 file changed, 22 insertions(+), 12 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 0857f72..a133d16 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2750,6 +2750,7 @@ static int netlink_dump(struct sock *sk)
 	struct sk_buff *skb = NULL;
 	struct nlmsghdr *nlh;
 	int len, err = -ENOBUFS;
+	int alloc_min_size;
 	int alloc_size;
 
 	mutex_lock(nlk->cb_mutex);
@@ -2758,9 +2759,6 @@ static int netlink_dump(struct sock *sk)
 		goto errout_skb;
 	}
 
-	cb = &nlk->cb;
-	alloc_size = max_t(int, cb->min_dump_alloc, NLMSG_GOODSIZE);
-
 	if (!netlink_rx_is_mmaped(sk) &&
 	    atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
 		goto errout_skb;
@@ -2770,23 +2768,35 @@ static int netlink_dump(struct sock *sk)
 	 * to reduce number of system calls on dump operations, if user
 	 * ever provided a big enough buffer.
 	 */
-	if (alloc_size < nlk->max_recvmsg_len) {
-		skb = netlink_alloc_skb(sk,
-					nlk->max_recvmsg_len,
-					nlk->portid,
+	cb = &nlk->cb;
+	alloc_min_size = max_t(int, cb->min_dump_alloc, NLMSG_GOODSIZE);
+
+	if (alloc_min_size < nlk->max_recvmsg_len) {
+		alloc_size = nlk->max_recvmsg_len;
+		skb = netlink_alloc_skb(sk, alloc_size, nlk->portid,
 					GFP_KERNEL |
 					__GFP_NOWARN |
 					__GFP_NORETRY);
-		/* available room should be exact amount to avoid MSG_TRUNC */
-		if (skb)
-			skb_reserve(skb, skb_tailroom(skb) -
-					 nlk->max_recvmsg_len);
 	}
-	if (!skb)
+	if (!skb) {
+		alloc_size = alloc_min_size;
 		skb = netlink_alloc_skb(sk, alloc_size, nlk->portid,
 					GFP_KERNEL);
+	}
 	if (!skb)
 		goto errout_skb;
+
+	/* Trim skb to allocated size. User is expected to provide buffer as
+	 * large as max(min_dump_alloc, 16KiB (mac_recvmsg_len capped at
+	 * netlink_recvmsg())). dump will pack as many smaller messages as
+	 * could fit within the allocated skb. skb is typically allocated
+	 * with larger space than required (could be as much as near 2x the
+	 * requested size with align to next power of 2 approach). Allowing
+	 * dump to use the excess space makes it difficult for a user to have a
+	 * reasonable static buffer based on the expected largest dump of a
+	 * single netdev. The outcome is MSG_TRUNC error.
+	 */
+	skb_reserve(skb, skb_tailroom(skb) - alloc_size);
 	netlink_skb_set_owner_r(skb, sk);
 
 	len = cb->dump(skb, cb);
-- 
1.7.10.4

Re: [PATCHES] Networking

[Greg KH]

On Tue, Oct 20, 2015 at 08:51:10PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for 3.14, 3.18, 4.1,
> and 4.2 -stable, respectively.

All queued up for the stable trees I manage, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 108 bytes --]


Please queue up the following bug fixes to 4.3.x, 4.2.x, 4.1.x, and
3.18.x -stable, respectively.

Thanks!

[-- Attachment #2: net_43.mbox --]
[-- Type: Application/Octet-Stream, Size: 45935 bytes --]

From 212f263930ebc1020ad12dd0fa52a058592709e8 Mon Sep 17 00:00:00 2001
From: Jon Paul Maloy <jon.maloy@ericsson.com>
Date: Wed, 28 Oct 2015 13:09:53 -0400
Subject: [PATCH 01/17] tipc: linearize arriving NAME_DISTR and LINK_PROTO
 buffers

[ Upstream commit 5cbb28a4bf65c7e4daa6c25b651fed8eb888c620 ]

Testing of the new UDP bearer has revealed that reception of
NAME_DISTRIBUTOR, LINK_PROTOCOL/RESET and LINK_PROTOCOL/ACTIVATE
message buffers is not prepared for the case that those may be
non-linear.

We now linearize all such buffers before they are delivered up to the
generic reception layer.

In order for the commit to apply cleanly to 'net' and 'stable', we do
the change in the function tipc_udp_recv() for now. Later, we will post
a commit to 'net-next' moving the linearization to generic code, in
tipc_named_rcv() and tipc_link_proto_rcv().

Fixes: commit d0f91938bede ("tipc: add ip/udp media type")
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/udp_media.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index 6e648d9..cd7c5f1 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -48,6 +48,7 @@
 #include <linux/tipc_netlink.h>
 #include "core.h"
 #include "bearer.h"
+#include "msg.h"
 
 /* IANA assigned UDP port */
 #define UDP_PORT_DEFAULT	6118
@@ -222,6 +223,10 @@ static int tipc_udp_recv(struct sock *sk, struct sk_buff *skb)
 {
 	struct udp_bearer *ub;
 	struct tipc_bearer *b;
+	int usr = msg_user(buf_msg(skb));
+
+	if ((usr == LINK_PROTOCOL) || (usr == NAME_DISTRIBUTOR))
+		skb_linearize(skb);
 
 	ub = rcu_dereference_sk_user_data(sk);
 	if (!ub) {
-- 
2.4.1


From a04db8659b41413b9ef6751b1487c96f4fe5c8c1 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 29 Oct 2015 18:11:35 -0700
Subject: [PATCH 02/17] net: bcmgenet: Software reset EPHY after power on

[ Upstream commit 5dbebbb44a6ad94aab2cd1a46f7676f255403f64 ]

The EPHY on GENET v1->v3 is extremely finicky, and will show occasional
failures based on the timing and reset sequence, ranging from duplicate
packets, to extremely high latencies.

Perform an additional software reset, and re-configuration to make sure it is
in a consistent and working state.

Fixes: 6ac3ce8295e6 ("net: bcmgenet: Remove excessive PHY reset")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c |  4 +++-
 drivers/net/ethernet/broadcom/genet/bcmgenet.h |  1 +
 drivers/net/ethernet/broadcom/genet/bcmmii.c   | 18 ++++++++++++++++++
 3 files changed, 22 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 1805541..5e3cd76 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -907,8 +907,10 @@ static void bcmgenet_power_up(struct bcmgenet_priv *priv,
 	}
 
 	bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
-	if (mode == GENET_POWER_PASSIVE)
+	if (mode == GENET_POWER_PASSIVE) {
 		bcmgenet_phy_power_set(priv->dev, true);
+		bcmgenet_mii_reset(priv->dev);
+	}
 }
 
 /* ioctl handle special commands that are not present in ethtool. */
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 7299d10..c739f7e 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -674,6 +674,7 @@ int bcmgenet_mii_init(struct net_device *dev);
 int bcmgenet_mii_config(struct net_device *dev);
 int bcmgenet_mii_probe(struct net_device *dev);
 void bcmgenet_mii_exit(struct net_device *dev);
+void bcmgenet_mii_reset(struct net_device *dev);
 void bcmgenet_phy_power_set(struct net_device *dev, bool enable);
 void bcmgenet_mii_setup(struct net_device *dev);
 
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index c8affad..8bdfe53 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -163,6 +163,7 @@ void bcmgenet_mii_setup(struct net_device *dev)
 	phy_print_status(phydev);
 }
 
+
 static int bcmgenet_fixed_phy_link_update(struct net_device *dev,
 					  struct fixed_phy_status *status)
 {
@@ -172,6 +173,22 @@ static int bcmgenet_fixed_phy_link_update(struct net_device *dev,
 	return 0;
 }
 
+/* Perform a voluntary PHY software reset, since the EPHY is very finicky about
+ * not doing it and will start corrupting packets
+ */
+void bcmgenet_mii_reset(struct net_device *dev)
+{
+	struct bcmgenet_priv *priv = netdev_priv(dev);
+
+	if (GENET_IS_V4(priv))
+		return;
+
+	if (priv->phydev) {
+		phy_init_hw(priv->phydev);
+		phy_start_aneg(priv->phydev);
+	}
+}
+
 void bcmgenet_phy_power_set(struct net_device *dev, bool enable)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
@@ -214,6 +231,7 @@ static void bcmgenet_internal_phy_setup(struct net_device *dev)
 	reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);
 	reg |= EXT_PWR_DN_EN_LD;
 	bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
+	bcmgenet_mii_reset(dev);
 }
 
 static void bcmgenet_moca_phy_setup(struct bcmgenet_priv *priv)
-- 
2.4.1


From 667672b33d13d71b92244bbd410f0a4122afa428 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Fri, 30 Oct 2015 10:23:33 +0200
Subject: [PATCH 03/17] ipv4: fix to not remove local route on link down

[ Upstream commit 4f823defdd5b106a5e89745ee8b163c71855de1e ]

When fib_netdev_event calls fib_disable_ip on NETDEV_DOWN event
we should not delete the local routes if the local address
is still present. The confusion comes from the fact that both
fib_netdev_event and fib_inetaddr_event use the NETDEV_DOWN
constant. Fix it by returning back the variable 'force'.

Steps to reproduce:
modprobe dummy
ifconfig dummy0 192.168.168.1 up
ifconfig dummy0 down
ip route list table local | grep dummy | grep host
local 192.168.168.1 dev dummy0  proto kernel  scope host  src 192.168.168.1

Fixes: 8a3d03166f19 ("net: track link-status of ipv4 nexthops")
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_fib.h     |  2 +-
 net/ipv4/fib_frontend.c  | 13 +++++++------
 net/ipv4/fib_semantics.c | 11 ++++++++---
 3 files changed, 16 insertions(+), 10 deletions(-)

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 727d6e9..965fa5b 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -317,7 +317,7 @@ void fib_flush_external(struct net *net);
 
 /* Exported by fib_semantics.c */
 int ip_fib_check_default(__be32 gw, struct net_device *dev);
-int fib_sync_down_dev(struct net_device *dev, unsigned long event);
+int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force);
 int fib_sync_down_addr(struct net *net, __be32 local);
 int fib_sync_up(struct net_device *dev, unsigned int nh_flags);
 void fib_select_multipath(struct fib_result *res);
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 690bcbc..457b2cd 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1110,9 +1110,10 @@ static void nl_fib_lookup_exit(struct net *net)
 	net->ipv4.fibnl = NULL;
 }
 
-static void fib_disable_ip(struct net_device *dev, unsigned long event)
+static void fib_disable_ip(struct net_device *dev, unsigned long event,
+			   bool force)
 {
-	if (fib_sync_down_dev(dev, event))
+	if (fib_sync_down_dev(dev, event, force))
 		fib_flush(dev_net(dev));
 	rt_cache_flush(dev_net(dev));
 	arp_ifdown(dev);
@@ -1140,7 +1141,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event,
 			/* Last address was deleted from this interface.
 			 * Disable IP.
 			 */
-			fib_disable_ip(dev, event);
+			fib_disable_ip(dev, event, true);
 		} else {
 			rt_cache_flush(dev_net(dev));
 		}
@@ -1157,7 +1158,7 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo
 	unsigned int flags;
 
 	if (event == NETDEV_UNREGISTER) {
-		fib_disable_ip(dev, event);
+		fib_disable_ip(dev, event, true);
 		rt_flush_dev(dev);
 		return NOTIFY_DONE;
 	}
@@ -1178,14 +1179,14 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo
 		rt_cache_flush(net);
 		break;
 	case NETDEV_DOWN:
-		fib_disable_ip(dev, event);
+		fib_disable_ip(dev, event, false);
 		break;
 	case NETDEV_CHANGE:
 		flags = dev_get_flags(dev);
 		if (flags & (IFF_RUNNING | IFF_LOWER_UP))
 			fib_sync_up(dev, RTNH_F_LINKDOWN);
 		else
-			fib_sync_down_dev(dev, event);
+			fib_sync_down_dev(dev, event, false);
 		/* fall through */
 	case NETDEV_CHANGEMTU:
 		rt_cache_flush(net);
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 064bd3c..2aa5b5e 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1281,7 +1281,13 @@ int fib_sync_down_addr(struct net *net, __be32 local)
 	return ret;
 }
 
-int fib_sync_down_dev(struct net_device *dev, unsigned long event)
+/* Event              force Flags           Description
+ * NETDEV_CHANGE      0     LINKDOWN        Carrier OFF, not for scope host
+ * NETDEV_DOWN        0     LINKDOWN|DEAD   Link down, not for scope host
+ * NETDEV_DOWN        1     LINKDOWN|DEAD   Last address removed
+ * NETDEV_UNREGISTER  1     LINKDOWN|DEAD   Device removed
+ */
+int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force)
 {
 	int ret = 0;
 	int scope = RT_SCOPE_NOWHERE;
@@ -1290,8 +1296,7 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event)
 	struct hlist_head *head = &fib_info_devhash[hash];
 	struct fib_nh *nh;
 
-	if (event == NETDEV_UNREGISTER ||
-	    event == NETDEV_DOWN)
+	if (force)
 		scope = -1;
 
 	hlist_for_each_entry(nh, head, nh_hash) {
-- 
2.4.1


From 79c1b779621a34487aaf8a7fa1e499c04fff5c79 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Fri, 30 Oct 2015 10:23:34 +0200
Subject: [PATCH 04/17] ipv4: update RTNH_F_LINKDOWN flag on UP event

[ Upstream commit c9b3292eeb52c6834e972eb5b8fe38914771ed12 ]

When nexthop is part of multipath route we should clear the
LINKDOWN flag when link goes UP or when first address is added.
This is needed because we always set LINKDOWN flag when DEAD flag
was set but now on UP the nexthop is not dead anymore. Examples when
LINKDOWN bit can be forgotten when no NETDEV_CHANGE is delivered:

- link goes down (LINKDOWN is set), then link goes UP and device
shows carrier OK but LINKDOWN remains set

- last address is deleted (LINKDOWN is set), then address is
added and device shows carrier OK but LINKDOWN remains set

Steps to reproduce:
modprobe dummy
ifconfig dummy0 192.168.168.1 up

here add a multipath route where one nexthop is for dummy0:

ip route add 1.2.3.4 nexthop dummy0 nexthop SOME_OTHER_DEVICE
ifconfig dummy0 down
ifconfig dummy0 up

now ip route shows nexthop that is not dead. Now set the sysctl var:

echo 1 > /proc/sys/net/ipv4/conf/dummy0/ignore_routes_with_linkdown

now ip route will show a dead nexthop because the forgotten
RTNH_F_LINKDOWN is propagated as RTNH_F_DEAD.

Fixes: 8a3d03166f19 ("net: track link-status of ipv4 nexthops")
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_semantics.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 2aa5b5e..e966f85 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1445,6 +1445,13 @@ int fib_sync_up(struct net_device *dev, unsigned int nh_flags)
 	if (!(dev->flags & IFF_UP))
 		return 0;
 
+	if (nh_flags & RTNH_F_DEAD) {
+		unsigned int flags = dev_get_flags(dev);
+
+		if (flags & (IFF_RUNNING | IFF_LOWER_UP))
+			nh_flags |= RTNH_F_LINKDOWN;
+	}
+
 	prev_fi = NULL;
 	hash = fib_devindex_hashfn(dev->ifindex);
 	head = &fib_info_devhash[hash];
-- 
2.4.1


From 22c6a0b8732f4b426f64f18ca9097288cd996a64 Mon Sep 17 00:00:00 2001
From: Phil Reid <preid@electromag.com.au>
Date: Fri, 30 Oct 2015 16:43:55 +0800
Subject: [PATCH 05/17] stmmac: Correctly report PTP capabilities.

[ Upstream commit e6dbe1eb2db0d7a14991c06278dd3030c45fb825 ]

priv->hwts_*_en indicate if timestamping is enabled/disabled at run
time. But  priv->dma_cap.time_stamp  and priv->dma_cap.atime_stamp
indicates HW is support for PTPv1/PTPv2.

Signed-off-by: Phil Reid <preid@electromag.com.au>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index 771cda2..2e51b81 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -721,10 +721,13 @@ static int stmmac_get_ts_info(struct net_device *dev,
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
 
-	if ((priv->hwts_tx_en) && (priv->hwts_rx_en)) {
+	if ((priv->dma_cap.time_stamp || priv->dma_cap.atime_stamp)) {
 
-		info->so_timestamping = SOF_TIMESTAMPING_TX_HARDWARE |
+		info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
+					SOF_TIMESTAMPING_TX_HARDWARE |
+					SOF_TIMESTAMPING_RX_SOFTWARE |
 					SOF_TIMESTAMPING_RX_HARDWARE |
+					SOF_TIMESTAMPING_SOFTWARE |
 					SOF_TIMESTAMPING_RAW_HARDWARE;
 
 		if (priv->ptp_clock)
-- 
2.4.1


From 27cc4a97a3cdcb3b3daa126667d4e86c9b014909 Mon Sep 17 00:00:00 2001
From: Ani Sinha <ani@arista.com>
Date: Fri, 30 Oct 2015 16:54:31 -0700
Subject: [PATCH 06/17] ipmr: fix possible race resulting from improper usage
 of IP_INC_STATS_BH() in preemptible context.

[ Upstream commit 44f49dd8b5a606870a1f21101522a0f9c4414784 ]

Fixes the following kernel BUG :

BUG: using __this_cpu_add() in preemptible [00000000] code: bash/2758
caller is __this_cpu_preempt_check+0x13/0x15
CPU: 0 PID: 2758 Comm: bash Tainted: P           O   3.18.19 #2
 ffffffff8170eaca ffff880110d1b788 ffffffff81482b2a 0000000000000000
 0000000000000000 ffff880110d1b7b8 ffffffff812010ae ffff880007cab800
 ffff88001a060800 ffff88013a899108 ffff880108b84240 ffff880110d1b7c8
Call Trace:
[<ffffffff81482b2a>] dump_stack+0x52/0x80
[<ffffffff812010ae>] check_preemption_disabled+0xce/0xe1
[<ffffffff812010d4>] __this_cpu_preempt_check+0x13/0x15
[<ffffffff81419d60>] ipmr_queue_xmit+0x647/0x70c
[<ffffffff8141a154>] ip_mr_forward+0x32f/0x34e
[<ffffffff8141af76>] ip_mroute_setsockopt+0xe03/0x108c
[<ffffffff810553fc>] ? get_parent_ip+0x11/0x42
[<ffffffff810e6974>] ? pollwake+0x4d/0x51
[<ffffffff81058ac0>] ? default_wake_function+0x0/0xf
[<ffffffff810553fc>] ? get_parent_ip+0x11/0x42
[<ffffffff810613d9>] ? __wake_up_common+0x45/0x77
[<ffffffff81486ea9>] ? _raw_spin_unlock_irqrestore+0x1d/0x32
[<ffffffff810618bc>] ? __wake_up_sync_key+0x4a/0x53
[<ffffffff8139a519>] ? sock_def_readable+0x71/0x75
[<ffffffff813dd226>] do_ip_setsockopt+0x9d/0xb55
[<ffffffff81429818>] ? unix_seqpacket_sendmsg+0x3f/0x41
[<ffffffff813963fe>] ? sock_sendmsg+0x6d/0x86
[<ffffffff813959d4>] ? sockfd_lookup_light+0x12/0x5d
[<ffffffff8139650a>] ? SyS_sendto+0xf3/0x11b
[<ffffffff810d5738>] ? new_sync_read+0x82/0xaa
[<ffffffff813ddd19>] compat_ip_setsockopt+0x3b/0x99
[<ffffffff813fb24a>] compat_raw_setsockopt+0x11/0x32
[<ffffffff81399052>] compat_sock_common_setsockopt+0x18/0x1f
[<ffffffff813c4d05>] compat_SyS_setsockopt+0x1a9/0x1cf
[<ffffffff813c4149>] compat_SyS_socketcall+0x180/0x1e3
[<ffffffff81488ea1>] cstar_dispatch+0x7/0x1e

Signed-off-by: Ani Sinha <ani@arista.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ipmr.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 866ee89..8e8203d 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1682,8 +1682,8 @@ static inline int ipmr_forward_finish(struct sock *sk, struct sk_buff *skb)
 {
 	struct ip_options *opt = &(IPCB(skb)->opt);
 
-	IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS);
-	IP_ADD_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTOCTETS, skb->len);
+	IP_INC_STATS(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS);
+	IP_ADD_STATS(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTOCTETS, skb->len);
 
 	if (unlikely(opt->optlen))
 		ip_forward_options(skb);
@@ -1745,7 +1745,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
 		 * to blackhole.
 		 */
 
-		IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
+		IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
 		ip_rt_put(rt);
 		goto out_free;
 	}
-- 
2.4.1


From 217a7af11532c12fc19168231216160cbf92adc8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Sun, 1 Nov 2015 01:34:50 +0100
Subject: [PATCH 07/17] qmi_wwan: fix entry for HP lt4112 LTE/HSPA+ Gobi 4G
 Module
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 70910791731b5956171e1bfcad707766b8e18fee ]

The lt4112 is a HP branded Huawei me906e modem. Like other Huawei
modems, it does not have a fixed interface to function mapping.
Instead it uses a Huawei specific scheme: functions are mapped by
subclass and protocol.

However, the HP vendor ID is used for modems from many different
manufacturers using different schemes, so we cannot apply a generic
vendor rule like we do for the Huawei vendor ID.

Replace the previous lt4112 entry pointing to an arbitrary interface
number with a device specific subclass + protocol match.

Reported-and-tested-by: Muri Nicanor <muri+libqmi@immerda.ch>
Tested-by: Martin Hauke <mardnh@gmx.de>
Fixes: bb2bdeb83fb1 ("qmi_wwan: Add support for HP lt4112 LTE/HSPA+ Gobi 4G Modem")
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 2a7c1be..1ba1fdc 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -539,6 +539,10 @@ static const struct usb_device_id products[] = {
 					      USB_CDC_PROTO_NONE),
 		.driver_info        = (unsigned long)&qmi_wwan_info,
 	},
+	{	/* HP lt4112 LTE/HSPA+ Gobi 4G Module (Huawei me906e) */
+		USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x581d, USB_CLASS_VENDOR_SPEC, 1, 7),
+		.driver_info = (unsigned long)&qmi_wwan_info,
+	},
 
 	/* 3. Combined interface devices matching on interface number */
 	{QMI_FIXED_INTF(0x0408, 0xea42, 4)},	/* Yota / Megafon M100-1 */
@@ -791,7 +795,6 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x413c, 0x81a9, 8)},	/* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */
 	{QMI_FIXED_INTF(0x413c, 0x81b1, 8)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card */
 	{QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)},	/* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */
-	{QMI_FIXED_INTF(0x03f0, 0x581d, 4)},	/* HP lt4112 LTE/HSPA+ Gobi 4G Module (Huawei me906e) */
 
 	/* 4. Gobi 1000 devices */
 	{QMI_GOBI1K_DEVICE(0x05c6, 0x9212)},	/* Acer Gobi Modem Device */
-- 
2.4.1


From 8d81dd753b8725645da63cf78c8d280c27e414a3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 2 Nov 2015 17:08:19 -0800
Subject: [PATCH 08/17] sit: fix sit0 percpu double allocations

[ Upstream commit 4ece9009774596ee3df0acba65a324b7ea79387c ]

sit0 device allocates its percpu storage twice :
- One time in ipip6_tunnel_init()
- One time in ipip6_fb_tunnel_init()

Thus we leak 48 bytes per possible cpu per network namespace dismantle.

ipip6_fb_tunnel_init() can be much simpler and does not
return an error, and should be called after register_netdev()

Note that ipip6_tunnel_clone_6rd() also needs to be called
after register_netdev() (calling ipip6_tunnel_init())

Fixes: ebe084aafb7e ("sit: Use ipip6_tunnel_init as the ndo_init function.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 26 ++++----------------------
 1 file changed, 4 insertions(+), 22 deletions(-)

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 94428fd..dcccae8 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1394,34 +1394,20 @@ static int ipip6_tunnel_init(struct net_device *dev)
 	return 0;
 }
 
-static int __net_init ipip6_fb_tunnel_init(struct net_device *dev)
+static void __net_init ipip6_fb_tunnel_init(struct net_device *dev)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	struct iphdr *iph = &tunnel->parms.iph;
 	struct net *net = dev_net(dev);
 	struct sit_net *sitn = net_generic(net, sit_net_id);
 
-	tunnel->dev = dev;
-	tunnel->net = dev_net(dev);
-
 	iph->version		= 4;
 	iph->protocol		= IPPROTO_IPV6;
 	iph->ihl		= 5;
 	iph->ttl		= 64;
 
-	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
-	if (!dev->tstats)
-		return -ENOMEM;
-
-	tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst);
-	if (!tunnel->dst_cache) {
-		free_percpu(dev->tstats);
-		return -ENOMEM;
-	}
-
 	dev_hold(dev);
 	rcu_assign_pointer(sitn->tunnels_wc[0], tunnel);
-	return 0;
 }
 
 static int ipip6_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -1831,23 +1817,19 @@ static int __net_init sit_init_net(struct net *net)
 	 */
 	sitn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL;
 
-	err = ipip6_fb_tunnel_init(sitn->fb_tunnel_dev);
-	if (err)
-		goto err_dev_free;
-
-	ipip6_tunnel_clone_6rd(sitn->fb_tunnel_dev, sitn);
 	err = register_netdev(sitn->fb_tunnel_dev);
 	if (err)
 		goto err_reg_dev;
 
+	ipip6_tunnel_clone_6rd(sitn->fb_tunnel_dev, sitn);
+	ipip6_fb_tunnel_init(sitn->fb_tunnel_dev);
+
 	t = netdev_priv(sitn->fb_tunnel_dev);
 
 	strcpy(t->parms.name, sitn->fb_tunnel_dev->name);
 	return 0;
 
 err_reg_dev:
-	dev_put(sitn->fb_tunnel_dev);
-err_dev_free:
 	ipip6_dev_free(sitn->fb_tunnel_dev);
 err_alloc_dev:
 	return err;
-- 
2.4.1


From 03ebc93ed50c5d98c9f86b5831f537a408935d83 Mon Sep 17 00:00:00 2001
From: Martin Habets <mhabets@solarflare.com>
Date: Mon, 2 Nov 2015 12:51:31 +0000
Subject: [PATCH 09/17] sfc: push partner queue for skb->xmit_more

[ Upstream commit b2663a4f30e85ec606b806f5135413e6d5c78d1e ]

When the IP stack passes SKBs the sfc driver puts them in 2 different TX
queues (called partners), one for checksummed and one for not checksummed.
If the SKB has xmit_more set the driver will delay pushing the work to the
NIC.

When later it does decide to push the buffers this patch ensures it also
pushes the partner queue, if that also has any delayed work. Before this
fix the work in the partner queue would be left for a long time and cause
a netdev watchdog.

Fixes: 70b33fb ("sfc: add support for skb->xmit_more")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Martin Habets <mhabets@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/ef10.c       |  4 +++-
 drivers/net/ethernet/sfc/farch.c      |  4 +++-
 drivers/net/ethernet/sfc/net_driver.h |  2 ++
 drivers/net/ethernet/sfc/tx.c         | 30 ++++++++++++++++++++++++++++--
 4 files changed, 36 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index ff649eb..286cc6b 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -1849,7 +1849,9 @@ static void efx_ef10_tx_write(struct efx_tx_queue *tx_queue)
 	unsigned int write_ptr;
 	efx_qword_t *txd;
 
-	BUG_ON(tx_queue->write_count == tx_queue->insert_count);
+	tx_queue->xmit_more_available = false;
+	if (unlikely(tx_queue->write_count == tx_queue->insert_count))
+		return;
 
 	do {
 		write_ptr = tx_queue->write_count & tx_queue->ptr_mask;
diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c
index f08266f..5a1c5a8 100644
--- a/drivers/net/ethernet/sfc/farch.c
+++ b/drivers/net/ethernet/sfc/farch.c
@@ -321,7 +321,9 @@ void efx_farch_tx_write(struct efx_tx_queue *tx_queue)
 	unsigned write_ptr;
 	unsigned old_write_count = tx_queue->write_count;
 
-	BUG_ON(tx_queue->write_count == tx_queue->insert_count);
+	tx_queue->xmit_more_available = false;
+	if (unlikely(tx_queue->write_count == tx_queue->insert_count))
+		return;
 
 	do {
 		write_ptr = tx_queue->write_count & tx_queue->ptr_mask;
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index c530e1c..24038ef 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -219,6 +219,7 @@ struct efx_tx_buffer {
  * @tso_packets: Number of packets via the TSO xmit path
  * @pushes: Number of times the TX push feature has been used
  * @pio_packets: Number of times the TX PIO feature has been used
+ * @xmit_more_available: Are any packets waiting to be pushed to the NIC
  * @empty_read_count: If the completion path has seen the queue as empty
  *	and the transmission path has not yet checked this, the value of
  *	@read_count bitwise-added to %EFX_EMPTY_COUNT_VALID; otherwise 0.
@@ -253,6 +254,7 @@ struct efx_tx_queue {
 	unsigned int tso_packets;
 	unsigned int pushes;
 	unsigned int pio_packets;
+	bool xmit_more_available;
 	/* Statistics to supplement MAC stats */
 	unsigned long tx_packets;
 
diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c
index 1833a01..67f6afa 100644
--- a/drivers/net/ethernet/sfc/tx.c
+++ b/drivers/net/ethernet/sfc/tx.c
@@ -431,8 +431,20 @@ finish_packet:
 	efx_tx_maybe_stop_queue(tx_queue);
 
 	/* Pass off to hardware */
-	if (!skb->xmit_more || netif_xmit_stopped(tx_queue->core_txq))
+	if (!skb->xmit_more || netif_xmit_stopped(tx_queue->core_txq)) {
+		struct efx_tx_queue *txq2 = efx_tx_queue_partner(tx_queue);
+
+		/* There could be packets left on the partner queue if those
+		 * SKBs had skb->xmit_more set. If we do not push those they
+		 * could be left for a long time and cause a netdev watchdog.
+		 */
+		if (txq2->xmit_more_available)
+			efx_nic_push_buffers(txq2);
+
 		efx_nic_push_buffers(tx_queue);
+	} else {
+		tx_queue->xmit_more_available = skb->xmit_more;
+	}
 
 	tx_queue->tx_packets++;
 
@@ -722,6 +734,7 @@ void efx_init_tx_queue(struct efx_tx_queue *tx_queue)
 	tx_queue->read_count = 0;
 	tx_queue->old_read_count = 0;
 	tx_queue->empty_read_count = 0 | EFX_EMPTY_COUNT_VALID;
+	tx_queue->xmit_more_available = false;
 
 	/* Set up TX descriptor ring */
 	efx_nic_init_tx(tx_queue);
@@ -747,6 +760,7 @@ void efx_fini_tx_queue(struct efx_tx_queue *tx_queue)
 
 		++tx_queue->read_count;
 	}
+	tx_queue->xmit_more_available = false;
 	netdev_tx_reset_queue(tx_queue->core_txq);
 }
 
@@ -1302,8 +1316,20 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue,
 	efx_tx_maybe_stop_queue(tx_queue);
 
 	/* Pass off to hardware */
-	if (!skb->xmit_more || netif_xmit_stopped(tx_queue->core_txq))
+	if (!skb->xmit_more || netif_xmit_stopped(tx_queue->core_txq)) {
+		struct efx_tx_queue *txq2 = efx_tx_queue_partner(tx_queue);
+
+		/* There could be packets left on the partner queue if those
+		 * SKBs had skb->xmit_more set. If we do not push those they
+		 * could be left for a long time and cause a netdev watchdog.
+		 */
+		if (txq2->xmit_more_available)
+			efx_nic_push_buffers(txq2);
+
 		efx_nic_push_buffers(tx_queue);
+	} else {
+		tx_queue->xmit_more_available = skb->xmit_more;
+	}
 
 	tx_queue->tso_bursts++;
 	return NETDEV_TX_OK;
-- 
2.4.1


From 80a7f5cf508c8054c3196e1110efecf5e842f698 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 2 Nov 2015 07:50:07 -0800
Subject: [PATCH 10/17] net: avoid NULL deref in inet_ctl_sock_destroy()

[ Upstream commit 8fa677d2706d325d71dab91bf6e6512c05214e37 ]

Under low memory conditions, tcp_sk_init() and icmp_sk_init()
can both iterate on all possible cpus and call inet_ctl_sock_destroy(),
with eventual NULL pointer.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_common.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/net/inet_common.h b/include/net/inet_common.h
index 279f835..109e3ee 100644
--- a/include/net/inet_common.h
+++ b/include/net/inet_common.h
@@ -41,7 +41,8 @@ int inet_recv_error(struct sock *sk, struct msghdr *msg, int len,
 
 static inline void inet_ctl_sock_destroy(struct sock *sk)
 {
-	sock_release(sk->sk_socket);
+	if (sk)
+		sock_release(sk->sk_socket);
 }
 
 #endif
-- 
2.4.1


From 4cc1b5dbe087a8b3ab518164fa90c9ab4d63e923 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Wed, 4 Nov 2015 14:47:53 +0100
Subject: [PATCH 11/17] ipv6: clean up dev_snmp6 proc entry when we fail to
 initialize inet6_dev

[ Upstream commit 2a189f9e57650e9f310ddf4aad75d66c1233a064 ]

In ipv6_add_dev, when addrconf_sysctl_register fails, we do not clean up
the dev_snmp6 entry that we have already registered for this device.
Call snmp6_unregister_dev in this case.

Fixes: a317a2f19da7d ("ipv6: fail early when creating netdev named all or default")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 36b85bd..dd00828 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -417,6 +417,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
 	if (err) {
 		ipv6_mc_destroy_dev(ndev);
 		del_timer(&ndev->regen_timer);
+		snmp6_unregister_dev(ndev);
 		goto err_release;
 	}
 	/* protected by rtnl_lock */
-- 
2.4.1


From 31aa0cfdfddba6e487aec78ff1f8fffb8bc3015d Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Tue, 3 Nov 2015 14:32:57 -0800
Subject: [PATCH 12/17] ipv4: disable BH when changing ip local port range

[ Upstream commit 4ee3bd4a8c7463cdef0b82ebc33fc94a9170a7e0 ]

This fixes the following lockdep warning:

 [ INFO: inconsistent lock state ]
 4.3.0-rc7+ #1197 Not tainted
 ---------------------------------
 inconsistent {IN-SOFTIRQ-R} -> {SOFTIRQ-ON-W} usage.
 sysctl/1019 [HC0[0]:SC0[0]:HE1:SE1] takes:
  (&(&net->ipv4.ip_local_ports.lock)->seqcount){+.+-..}, at: [<ffffffff81921de7>] ipv4_local_port_range+0xb4/0x12a
 {IN-SOFTIRQ-R} state was registered at:
   [<ffffffff810bd682>] __lock_acquire+0x2f6/0xdf0
   [<ffffffff810be6d5>] lock_acquire+0x11c/0x1a4
   [<ffffffff818e599c>] inet_get_local_port_range+0x4e/0xae
   [<ffffffff8166e8e3>] udp_flow_src_port.constprop.40+0x23/0x116
   [<ffffffff81671cb9>] vxlan_xmit_one+0x219/0xa6a
   [<ffffffff81672f75>] vxlan_xmit+0xa6b/0xaa5
   [<ffffffff817f2deb>] dev_hard_start_xmit+0x2ae/0x465
   [<ffffffff817f35ed>] __dev_queue_xmit+0x531/0x633
   [<ffffffff817f3702>] dev_queue_xmit_sk+0x13/0x15
   [<ffffffff818004a5>] neigh_resolve_output+0x12f/0x14d
   [<ffffffff81959cfa>] ip6_finish_output2+0x344/0x39f
   [<ffffffff8195bf58>] ip6_finish_output+0x88/0x8e
   [<ffffffff8195bfef>] ip6_output+0x91/0xe5
   [<ffffffff819792ae>] dst_output_sk+0x47/0x4c
   [<ffffffff81979392>] NF_HOOK_THRESH.constprop.30+0x38/0x82
   [<ffffffff8197981e>] mld_sendpack+0x189/0x266
   [<ffffffff8197b28b>] mld_ifc_timer_expire+0x1ef/0x223
   [<ffffffff810de581>] call_timer_fn+0xfb/0x28c
   [<ffffffff810ded1e>] run_timer_softirq+0x1c7/0x1f1

Fixes: b8f1a55639e6 ("udp: Add function to make source port for UDP tunnels")
Cc: Tom Herbert <tom@herbertland.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/sysctl_net_ipv4.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 894da3a..ade7737 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -48,14 +48,14 @@ static void set_local_port_range(struct net *net, int range[2])
 {
 	bool same_parity = !((range[0] ^ range[1]) & 1);
 
-	write_seqlock(&net->ipv4.ip_local_ports.lock);
+	write_seqlock_bh(&net->ipv4.ip_local_ports.lock);
 	if (same_parity && !net->ipv4.ip_local_ports.warned) {
 		net->ipv4.ip_local_ports.warned = true;
 		pr_err_ratelimited("ip_local_port_range: prefer different parity for start/end values.\n");
 	}
 	net->ipv4.ip_local_ports.range[0] = range[0];
 	net->ipv4.ip_local_ports.range[1] = range[1];
-	write_sequnlock(&net->ipv4.ip_local_ports.lock);
+	write_sequnlock_bh(&net->ipv4.ip_local_ports.lock);
 }
 
 /* Validate changes from /proc interface. */
-- 
2.4.1


From d04ea27f9dfc17ef6f031fd001b818b1ac70141d Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Tue, 3 Nov 2015 15:59:28 -0800
Subject: [PATCH 13/17] net: Fix prefsrc lookups

[ Upstream commit e1b8d903c6c3862160d2d5036806a94786c8fc4e ]

A bug report (https://bugzilla.kernel.org/show_bug.cgi?id=107071) noted
that the follwoing ip command is failing with v4.3:

    $ ip route add 10.248.5.0/24 dev bond0.250 table vlan_250 src 10.248.5.154
    RTNETLINK answers: Invalid argument

021dd3b8a142d changed the lookup of the given preferred source address to
use the table id passed in, but this assumes the local entries are in the
given table which is not necessarily true for non-VRF use cases. When
validating the preferred source fallback to the local table on failure.

Fixes: 021dd3b8a142d ("net: Add routes to the table associated with the device")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_semantics.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index e966f85..ef5892f 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -864,14 +864,21 @@ static bool fib_valid_prefsrc(struct fib_config *cfg, __be32 fib_prefsrc)
 	if (cfg->fc_type != RTN_LOCAL || !cfg->fc_dst ||
 	    fib_prefsrc != cfg->fc_dst) {
 		u32 tb_id = cfg->fc_table;
+		int rc;
 
 		if (tb_id == RT_TABLE_MAIN)
 			tb_id = RT_TABLE_LOCAL;
 
-		if (inet_addr_type_table(cfg->fc_nlinfo.nl_net,
-					 fib_prefsrc, tb_id) != RTN_LOCAL) {
-			return false;
+		rc = inet_addr_type_table(cfg->fc_nlinfo.nl_net,
+					  fib_prefsrc, tb_id);
+
+		if (rc != RTN_LOCAL && tb_id != RT_TABLE_LOCAL) {
+			rc = inet_addr_type_table(cfg->fc_nlinfo.nl_net,
+						  fib_prefsrc, RT_TABLE_LOCAL);
 		}
+
+		if (rc != RTN_LOCAL)
+			return false;
 	}
 	return true;
 }
-- 
2.4.1


From 79f11d5fe0fd0547c8b1d03166e70f2f6ffae8a8 Mon Sep 17 00:00:00 2001
From: Tobias Klauser <tklauser@distanz.ch>
Date: Wed, 4 Nov 2015 13:49:49 +0100
Subject: [PATCH 14/17] tun_dst: Fix potential NULL dereference

[ Upstream commit f63ce5b6fa5e9a0faf7a0e1ef2993a502878c78a ]

In tun_dst_unclone() the return value of skb_metadata_dst() is checked
for being NULL after it is dereferenced. Fix this by moving the
dereference after the NULL check.

Found by the Coverity scanner (CID 1338068).

Fixes: fc4099f17240 ("openvswitch: Fix egress tunnel info.")
Cc: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst_metadata.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h
index ce00971..6816f0f 100644
--- a/include/net/dst_metadata.h
+++ b/include/net/dst_metadata.h
@@ -63,12 +63,13 @@ static inline struct metadata_dst *tun_rx_dst(int md_size)
 static inline struct metadata_dst *tun_dst_unclone(struct sk_buff *skb)
 {
 	struct metadata_dst *md_dst = skb_metadata_dst(skb);
-	int md_size = md_dst->u.tun_info.options_len;
+	int md_size;
 	struct metadata_dst *new_md;
 
 	if (!md_dst)
 		return ERR_PTR(-EINVAL);
 
+	md_size = md_dst->u.tun_info.options_len;
 	new_md = metadata_dst_alloc(md_size, GFP_ATOMIC);
 	if (!new_md)
 		return ERR_PTR(-ENOMEM);
-- 
2.4.1


From 4a75ef6f762c85d73a76a9466672cf66965d82e2 Mon Sep 17 00:00:00 2001
From: Francesco Ruggeri <fruggeri@aristanetworks.com>
Date: Thu, 5 Nov 2015 08:16:14 -0800
Subject: [PATCH 15/17] packet: race condition in packet_bind

[ Upstream commit 30f7ea1c2b5f5fb7462c5ae44fe2e40cb2d6a474 ]

There is a race conditions between packet_notifier and packet_bind{_spkt}.

It happens if packet_notifier(NETDEV_UNREGISTER) executes between the
time packet_bind{_spkt} takes a reference on the new netdevice and the
time packet_do_bind sets po->ifindex.
In this case the notification can be missed.
If this happens during a dev_change_net_namespace this can result in the
netdevice to be moved to the new namespace while the packet_sock in the
old namespace still holds a reference on it. When the netdevice is later
deleted in the new namespace the deletion hangs since the packet_sock
is not found in the new namespace' &net->packet.sklist.
It can be reproduced with the script below.

This patch makes packet_do_bind check again for the presence of the
netdevice in the packet_sock's namespace after the synchronize_net
in unregister_prot_hook.
More in general it also uses the rcu lock for the duration of the bind
to stop dev_change_net_namespace/rollback_registered_many from
going past the synchronize_net following unlist_netdevice, so that
no NETDEV_UNREGISTER notifications can happen on the new netdevice
while the bind is executing. In order to do this some code from
packet_bind{_spkt} is consolidated into packet_do_dev.

import socket, os, time, sys
proto=7
realDev='em1'
vlanId=400
if len(sys.argv) > 1:
   vlanId=int(sys.argv[1])
dev='vlan%d' % vlanId

os.system('taskset -p 0x10 %d' % os.getpid())

s = socket.socket(socket.PF_PACKET, socket.SOCK_RAW, proto)
os.system('ip link add link %s name %s type vlan id %d' %
          (realDev, dev, vlanId))
os.system('ip netns add dummy')

pid=os.fork()

if pid == 0:
   # dev should be moved while packet_do_bind is in synchronize net
   os.system('taskset -p 0x20000 %d' % os.getpid())
   os.system('ip link set %s netns dummy' % dev)
   os.system('ip netns exec dummy ip link del %s' % dev)
   s.close()
   sys.exit(0)

time.sleep(.004)
try:
   s.bind(('%s' % dev, proto+1))
except:
   print 'Could not bind socket'
   s.close()
   os.system('ip netns del dummy')
   sys.exit(0)

os.waitpid(pid, 0)
s.close()
os.system('ip netns del dummy')
sys.exit(0)

Signed-off-by: Francesco Ruggeri <fruggeri@arista.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 80 +++++++++++++++++++++++++++++++-------------------
 1 file changed, 49 insertions(+), 31 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index aa4b15c..27b2898 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2903,22 +2903,40 @@ static int packet_release(struct socket *sock)
  *	Attach a packet hook.
  */
 
-static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
+static int packet_do_bind(struct sock *sk, const char *name, int ifindex,
+			  __be16 proto)
 {
 	struct packet_sock *po = pkt_sk(sk);
 	struct net_device *dev_curr;
 	__be16 proto_curr;
 	bool need_rehook;
+	struct net_device *dev = NULL;
+	int ret = 0;
+	bool unlisted = false;
 
-	if (po->fanout) {
-		if (dev)
-			dev_put(dev);
-
+	if (po->fanout)
 		return -EINVAL;
-	}
 
 	lock_sock(sk);
 	spin_lock(&po->bind_lock);
+	rcu_read_lock();
+
+	if (name) {
+		dev = dev_get_by_name_rcu(sock_net(sk), name);
+		if (!dev) {
+			ret = -ENODEV;
+			goto out_unlock;
+		}
+	} else if (ifindex) {
+		dev = dev_get_by_index_rcu(sock_net(sk), ifindex);
+		if (!dev) {
+			ret = -ENODEV;
+			goto out_unlock;
+		}
+	}
+
+	if (dev)
+		dev_hold(dev);
 
 	proto_curr = po->prot_hook.type;
 	dev_curr = po->prot_hook.dev;
@@ -2926,14 +2944,29 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
 	need_rehook = proto_curr != proto || dev_curr != dev;
 
 	if (need_rehook) {
-		unregister_prot_hook(sk, true);
+		if (po->running) {
+			rcu_read_unlock();
+			__unregister_prot_hook(sk, true);
+			rcu_read_lock();
+			dev_curr = po->prot_hook.dev;
+			if (dev)
+				unlisted = !dev_get_by_index_rcu(sock_net(sk),
+								 dev->ifindex);
+		}
 
 		po->num = proto;
 		po->prot_hook.type = proto;
-		po->prot_hook.dev = dev;
 
-		po->ifindex = dev ? dev->ifindex : 0;
-		packet_cached_dev_assign(po, dev);
+		if (unlikely(unlisted)) {
+			dev_put(dev);
+			po->prot_hook.dev = NULL;
+			po->ifindex = -1;
+			packet_cached_dev_reset(po);
+		} else {
+			po->prot_hook.dev = dev;
+			po->ifindex = dev ? dev->ifindex : 0;
+			packet_cached_dev_assign(po, dev);
+		}
 	}
 	if (dev_curr)
 		dev_put(dev_curr);
@@ -2941,7 +2974,7 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
 	if (proto == 0 || !need_rehook)
 		goto out_unlock;
 
-	if (!dev || (dev->flags & IFF_UP)) {
+	if (!unlisted && (!dev || (dev->flags & IFF_UP))) {
 		register_prot_hook(sk);
 	} else {
 		sk->sk_err = ENETDOWN;
@@ -2950,9 +2983,10 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
 	}
 
 out_unlock:
+	rcu_read_unlock();
 	spin_unlock(&po->bind_lock);
 	release_sock(sk);
-	return 0;
+	return ret;
 }
 
 /*
@@ -2964,8 +2998,6 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr,
 {
 	struct sock *sk = sock->sk;
 	char name[15];
-	struct net_device *dev;
-	int err = -ENODEV;
 
 	/*
 	 *	Check legality
@@ -2975,19 +3007,13 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr,
 		return -EINVAL;
 	strlcpy(name, uaddr->sa_data, sizeof(name));
 
-	dev = dev_get_by_name(sock_net(sk), name);
-	if (dev)
-		err = packet_do_bind(sk, dev, pkt_sk(sk)->num);
-	return err;
+	return packet_do_bind(sk, name, 0, pkt_sk(sk)->num);
 }
 
 static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 {
 	struct sockaddr_ll *sll = (struct sockaddr_ll *)uaddr;
 	struct sock *sk = sock->sk;
-	struct net_device *dev = NULL;
-	int err;
-
 
 	/*
 	 *	Check legality
@@ -2998,16 +3024,8 @@ static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len
 	if (sll->sll_family != AF_PACKET)
 		return -EINVAL;
 
-	if (sll->sll_ifindex) {
-		err = -ENODEV;
-		dev = dev_get_by_index(sock_net(sk), sll->sll_ifindex);
-		if (dev == NULL)
-			goto out;
-	}
-	err = packet_do_bind(sk, dev, sll->sll_protocol ? : pkt_sk(sk)->num);
-
-out:
-	return err;
+	return packet_do_bind(sk, NULL, sll->sll_ifindex,
+			      sll->sll_protocol ? : pkt_sk(sk)->num);
 }
 
 static struct proto packet_proto = {
-- 
2.4.1


From b84e1a71f9b380b8fe8843e5af4c72cad640a1dc Mon Sep 17 00:00:00 2001
From: Jay Vosburgh <jay.vosburgh@canonical.com>
Date: Fri, 6 Nov 2015 17:23:23 -0800
Subject: [PATCH 16/17] bonding: fix panic on non-ARPHRD_ETHER enslave failure

[ Upstream commit 40baec225765c54eefa870530dd613bad9829bb7 ]

Since commit 7d5cd2ce529b, when bond_enslave fails on devices that
are not ARPHRD_ETHER, if needed, it resets the bonding device back to
ARPHRD_ETHER by calling ether_setup.

	Unfortunately, ether_setup clobbers dev->flags, clearing IFF_UP
if the bond device is up, leaving it in a quasi-down state without
having actually gone through dev_close.  For bonding, if any periodic
work queue items are active (miimon, arp_interval, etc), those will
remain running, as they are stopped by bond_close.  At this point, if
the bonding module is unloaded or the bond is deleted, the system will
panic when the work function is called.

	This panic is resolved by calling dev_close on the bond itself
prior to calling ether_setup.

Cc: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Fixes: 7d5cd2ce5292 ("bonding: correctly handle bonding type change on enslave failure")
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 771a449..bcd7bdd 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1749,6 +1749,7 @@ err_undo_flags:
 					    slave_dev->dev_addr))
 			eth_hw_addr_random(bond_dev);
 		if (bond_dev->type != ARPHRD_ETHER) {
+			dev_close(bond_dev);
 			ether_setup(bond_dev);
 			bond_dev->flags |= IFF_MASTER;
 			bond_dev->priv_flags &= ~IFF_TX_SKB_SHARING;
-- 
2.4.1


From b019533c6926b5dd5a7b1d6f8cb8616b51e39297 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 9 Nov 2015 17:51:23 -0800
Subject: [PATCH 17/17] net: fix a race in dst_release()

[ Upstream commit d69bbf88c8d0b367cf3e3a052f6daadf630ee566 ]

Only cpu seeing dst refcount going to 0 can safely
dereference dst->flags.

Otherwise an other cpu might already have freed the dst.

Fixes: 27b75c95f10d ("net: avoid RCU for NOCACHE dst")
Reported-by: Greg Thelen <gthelen@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dst.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/dst.c b/net/core/dst.c
index 0771c8c..d6a5a0b 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -306,7 +306,7 @@ void dst_release(struct dst_entry *dst)
 		if (unlikely(newrefcnt < 0))
 			net_warn_ratelimited("%s: dst:%p refcnt:%d\n",
 					     __func__, dst, newrefcnt);
-		if (unlikely(dst->flags & DST_NOCACHE) && !newrefcnt)
+		if (!newrefcnt && unlikely(dst->flags & DST_NOCACHE))
 			call_rcu(&dst->rcu_head, dst_destroy_rcu);
 	}
 }
-- 
2.4.1


[-- Attachment #3: net_42.mbox --]
[-- Type: Application/Octet-Stream, Size: 71031 bytes --]

From 98949e7c168b5bff3429d8c1e02f1c3d0720fea5 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Mon, 19 Oct 2015 13:16:49 +0300
Subject: [PATCH 01/30] irda: precedence bug in irlmp_seq_hb_idx()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 50010c20597d14667eff0fdb628309986f195230 ]

This is decrementing the pointer, instead of the value stored in the
pointer.  KASan detects it as an out of bounds reference.

Reported-by: "Berry Cheng 程君(成淼)" <chengmiao.cj@alibaba-inc.com>
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/irda/irlmp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/irda/irlmp.c b/net/irda/irlmp.c
index a26c401..4396459 100644
--- a/net/irda/irlmp.c
+++ b/net/irda/irlmp.c
@@ -1839,7 +1839,7 @@ static void *irlmp_seq_hb_idx(struct irlmp_iter_state *iter, loff_t *off)
 	for (element = hashbin_get_first(iter->hashbin);
 	     element != NULL;
 	     element = hashbin_get_next(iter->hashbin)) {
-		if (!off || *off-- == 0) {
+		if (!off || (*off)-- == 0) {
 			/* NB: hashbin left locked */
 			return element;
 		}
-- 
2.4.1


From 0e5fb773f251d5f3429a6bbc60b262ff65638590 Mon Sep 17 00:00:00 2001
From: Jon Paul Maloy <jon.maloy@ericsson.com>
Date: Mon, 19 Oct 2015 11:33:00 -0400
Subject: [PATCH 02/30] tipc: allow non-linear first fragment buffer

[ Upstream commit 45c8b7b175ceb2d542e0fe15247377bf3bce29ec ]

The current code for message reassembly is erroneously assuming that
the the first arriving fragment buffer always is linear, and then goes
ahead resetting the fragment list of that buffer in anticipation of
more arriving fragments.

However, if the buffer already happens to be non-linear, we will
inadvertently drop the already attached fragment list, and later
on trig a BUG() in __pskb_pull_tail().

We see this happen when running fragmented TIPC multicast across UDP,
something made possible since
commit d0f91938bede ("tipc: add ip/udp media type")

We fix this by not resetting the fragment list when the buffer is non-
linear, and by initiatlizing our private fragment list tail pointer to
the tail of the existing fragment list.

Fixes: commit d0f91938bede ("tipc: add ip/udp media type")
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/msg.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index 08b4cc7..b3a3931 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -121,7 +121,7 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf)
 {
 	struct sk_buff *head = *headbuf;
 	struct sk_buff *frag = *buf;
-	struct sk_buff *tail;
+	struct sk_buff *tail = NULL;
 	struct tipc_msg *msg;
 	u32 fragid;
 	int delta;
@@ -141,9 +141,15 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf)
 		if (unlikely(skb_unclone(frag, GFP_ATOMIC)))
 			goto err;
 		head = *headbuf = frag;
-		skb_frag_list_init(head);
-		TIPC_SKB_CB(head)->tail = NULL;
 		*buf = NULL;
+		TIPC_SKB_CB(head)->tail = NULL;
+		if (skb_is_nonlinear(head)) {
+			skb_walk_frags(head, tail) {
+				TIPC_SKB_CB(head)->tail = tail;
+			}
+		} else {
+			skb_frag_list_init(head);
+		}
 		return 0;
 	}
 
-- 
2.4.1


From cf0634da1037b05a3860af534ef0c384cb85d9c8 Mon Sep 17 00:00:00 2001
From: Renato Westphal <renatowestphal@gmail.com>
Date: Mon, 19 Oct 2015 18:51:34 -0200
Subject: [PATCH 03/30] tcp: remove improper preemption check in
 tcp_xmit_probe_skb()

[ Upstream commit e2e8009ff72ad2a795b67785f3238af152146368 ]

Commit e520af48c7e5a introduced the following bug when setting the
TCP_REPAIR sockoption:

[ 2860.657036] BUG: using __this_cpu_add() in preemptible [00000000] code: daemon/12164
[ 2860.657045] caller is __this_cpu_preempt_check+0x13/0x20
[ 2860.657049] CPU: 1 PID: 12164 Comm: daemon Not tainted 4.2.3 #1
[ 2860.657051] Hardware name: Dell Inc. PowerEdge R210 II/0JP7TR, BIOS 2.0.5 03/13/2012
[ 2860.657054]  ffffffff81c7f071 ffff880231e9fdf8 ffffffff8185d765 0000000000000002
[ 2860.657058]  0000000000000001 ffff880231e9fe28 ffffffff8146ed91 ffff880231e9fe18
[ 2860.657062]  ffffffff81cd1a5d ffff88023534f200 ffff8800b9811000 ffff880231e9fe38
[ 2860.657065] Call Trace:
[ 2860.657072]  [<ffffffff8185d765>] dump_stack+0x4f/0x7b
[ 2860.657075]  [<ffffffff8146ed91>] check_preemption_disabled+0xe1/0xf0
[ 2860.657078]  [<ffffffff8146edd3>] __this_cpu_preempt_check+0x13/0x20
[ 2860.657082]  [<ffffffff817e0bc7>] tcp_xmit_probe_skb+0xc7/0x100
[ 2860.657085]  [<ffffffff817e1e2d>] tcp_send_window_probe+0x2d/0x30
[ 2860.657089]  [<ffffffff817d1d8c>] do_tcp_setsockopt.isra.29+0x74c/0x830
[ 2860.657093]  [<ffffffff817d1e9c>] tcp_setsockopt+0x2c/0x30
[ 2860.657097]  [<ffffffff81767b74>] sock_common_setsockopt+0x14/0x20
[ 2860.657100]  [<ffffffff817669e1>] SyS_setsockopt+0x71/0xc0
[ 2860.657104]  [<ffffffff81865172>] entry_SYSCALL_64_fastpath+0x16/0x75

Since tcp_xmit_probe_skb() can be called from process context, use
NET_INC_STATS() instead of NET_INC_STATS_BH().

Fixes: e520af48c7e5 ("tcp: add TCPWinProbe and TCPKeepAlive SNMP counters")
Signed-off-by: Renato Westphal <renatow@taghos.com.br>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index b7dedd9..747a4c4 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3406,7 +3406,7 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent, int mib)
 	 */
 	tcp_init_nondata_skb(skb, tp->snd_una - !urgent, TCPHDR_ACK);
 	skb_mstamp_get(&skb->skb_mstamp);
-	NET_INC_STATS_BH(sock_net(sk), mib);
+	NET_INC_STATS(sock_net(sk), mib);
 	return tcp_transmit_skb(sk, skb, 0, GFP_ATOMIC);
 }
 
-- 
2.4.1


From 8edc7f6a43876a6f3f0b58e0c3969ed33bb87c9d Mon Sep 17 00:00:00 2001
From: David Herrmann <dh.herrmann@gmail.com>
Date: Wed, 21 Oct 2015 11:47:43 +0200
Subject: [PATCH 04/30] netlink: fix locking around NETLINK_LIST_MEMBERSHIPS

[ Upstream commit 47191d65b647af5eb5c82ede70ed4c24b1e93ef4 ]

Currently, NETLINK_LIST_MEMBERSHIPS grabs the netlink table while copying
the membership state to user-space. However, grabing the netlink table is
effectively a write_lock_irq(), and as such we should not be triggering
page-faults in the critical section.

This can be easily reproduced by the following snippet:
    int s = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
    void *p = mmap(0, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANON, -1, 0);
    int r = getsockopt(s, 0x10e, 9, p, (void*)((char*)p + 4092));

This should work just fine, but currently triggers EFAULT and a possible
WARN_ON below handle_mm_fault().

Fix this by reducing locking of NETLINK_LIST_MEMBERSHIPS to a read-side
lock. The write-lock was overkill in the first place, and the read-lock
allows page-faults just fine.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index a133d16..8b158f7 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2346,7 +2346,7 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname,
 		int pos, idx, shift;
 
 		err = 0;
-		netlink_table_grab();
+		netlink_lock_table();
 		for (pos = 0; pos * 8 < nlk->ngroups; pos += sizeof(u32)) {
 			if (len - pos < sizeof(u32))
 				break;
@@ -2361,7 +2361,7 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname,
 		}
 		if (put_user(ALIGN(nlk->ngroups / 8, sizeof(u32)), optlen))
 			err = -EFAULT;
-		netlink_table_ungrab();
+		netlink_unlock_table();
 		break;
 	}
 	default:
-- 
2.4.1


From 8291449450b3360e9cbeffb7526130ccc567955c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Thu, 22 Oct 2015 14:15:58 +0200
Subject: [PATCH 05/30] qmi_wwan: add Sierra Wireless MC74xx/EM74xx
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 0db65fcfcded76fe4f74e3ca9f4e2baf67b683ef ]

New device IDs shamelessly lifted from the vendor driver.

Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 64a60af..8f1738c 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -765,6 +765,10 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1199, 0x9056, 8)},	/* Sierra Wireless Modem */
 	{QMI_FIXED_INTF(0x1199, 0x9057, 8)},
 	{QMI_FIXED_INTF(0x1199, 0x9061, 8)},	/* Sierra Wireless Modem */
+	{QMI_FIXED_INTF(0x1199, 0x9070, 8)},	/* Sierra Wireless MC74xx/EM74xx */
+	{QMI_FIXED_INTF(0x1199, 0x9070, 10)},	/* Sierra Wireless MC74xx/EM74xx */
+	{QMI_FIXED_INTF(0x1199, 0x9071, 8)},	/* Sierra Wireless MC74xx/EM74xx */
+	{QMI_FIXED_INTF(0x1199, 0x9071, 10)},	/* Sierra Wireless MC74xx/EM74xx */
 	{QMI_FIXED_INTF(0x1bbb, 0x011e, 4)},	/* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */
 	{QMI_FIXED_INTF(0x1bbb, 0x0203, 2)},	/* Alcatel L800MA */
 	{QMI_FIXED_INTF(0x2357, 0x0201, 4)},	/* TP-LINK HSUPA Modem MA180 */
-- 
2.4.1


From 94fdcdeebd0d0982176879f19779168edf60a9e0 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Fri, 23 Oct 2015 00:57:05 -0400
Subject: [PATCH 06/30] macvtap: unbreak receiving of gro skb with frag list

[ Upstream commit f23d538bc24a83c16127c2eb82c9cf1adc2b5149 ]

We don't have fraglist support in TAP_FEATURES. This will lead
software segmentation of gro skb with frag list. Fixes by having
frag list support in TAP_FEATURES.

With this patch single session of netperf receiving were restored from
about 5Gb/s to about 12Gb/s on mlx4.

Fixes a567dd6252 ("macvtap: simplify usage of tap_features")
Cc: Vlad Yasevich <vyasevic@redhat.com>
Cc: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macvtap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 248478c..197c939 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -137,7 +137,7 @@ static const struct proto_ops macvtap_socket_ops;
 #define TUN_OFFLOADS (NETIF_F_HW_CSUM | NETIF_F_TSO_ECN | NETIF_F_TSO | \
 		      NETIF_F_TSO6 | NETIF_F_UFO)
 #define RX_OFFLOADS (NETIF_F_GRO | NETIF_F_LRO)
-#define TAP_FEATURES (NETIF_F_GSO | NETIF_F_SG)
+#define TAP_FEATURES (NETIF_F_GSO | NETIF_F_SG | NETIF_F_FRAGLIST)
 
 static struct macvlan_dev *macvtap_get_vlan_rcu(const struct net_device *dev)
 {
-- 
2.4.1


From 1250cab846970cbf1b77325ba5d3205b4c0546d3 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Thu, 22 Oct 2015 16:57:10 +0200
Subject: [PATCH 07/30] ppp: fix pppoe_dev deletion condition in
 pppoe_release()

[ Upstream commit 1acea4f6ce1b1c0941438aca75dd2e5c6b09db60 ]

We can't rely on PPPOX_ZOMBIE to decide whether to clear po->pppoe_dev.
PPPOX_ZOMBIE can be set by pppoe_disc_rcv() even when po->pppoe_dev is
NULL. So we have no guarantee that (sk->sk_state & PPPOX_ZOMBIE) implies
(po->pppoe_dev != NULL).
Since we're releasing a PPPoE socket, we want to release the pppoe_dev
if it exists and reset sk_state to PPPOX_DEAD, no matter the previous
value of sk_state. So we can just check for po->pppoe_dev and avoid any
assumption on sk->sk_state.

Fixes: 2b018d57ff18 ("pppoe: drop PPPOX_ZOMBIEs in pppoe_release")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pppoe.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 2ed7506..5e0b432 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -589,7 +589,7 @@ static int pppoe_release(struct socket *sock)
 
 	po = pppox_sk(sk);
 
-	if (sk->sk_state & (PPPOX_CONNECTED | PPPOX_BOUND | PPPOX_ZOMBIE)) {
+	if (po->pppoe_dev) {
 		dev_put(po->pppoe_dev);
 		po->pppoe_dev = NULL;
 	}
-- 
2.4.1


From 0d534bfa01efdda374e32273c3682094ded2ace8 Mon Sep 17 00:00:00 2001
From: "Lendacky, Thomas" <Thomas.Lendacky@amd.com>
Date: Wed, 21 Oct 2015 15:37:05 -0500
Subject: [PATCH 08/30] amd-xgbe: Use wmb before updating current descriptor
 count

[ Upstream commit 20a41fba679d665cdae2808e2b9cae97c073351f ]

The code currently uses the lightweight dma_wmb barrier before updating
the current descriptor count. Under heavy load, the Tx cleanup routine
was seeing the updated current descriptor count before the updated
descriptor information. As a result, the Tx descriptor was being cleaned
up before it was used because it was not "owned" by the hardware yet,
resulting in a Tx queue hang.

Using the wmb barrier insures that the descriptor is updated before the
descriptor counter preventing the Tx queue hang. For extra insurance,
the Tx cleanup routine is changed to grab the current decriptor count on
entry and uses that initial value in the processing loop rather than
trying to chase the current value.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Tested-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe-dev.c | 2 +-
 drivers/net/ethernet/amd/xgbe/xgbe-drv.c | 4 +++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
index a4473d8..e9ab8b9 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
@@ -1595,7 +1595,7 @@ static void xgbe_dev_xmit(struct xgbe_channel *channel)
 				  packet->rdesc_count, 1);
 
 	/* Make sure ownership is written to the descriptor */
-	dma_wmb();
+	wmb();
 
 	ring->cur = cur_index + 1;
 	if (!packet->skb->xmit_more ||
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index aae9d5e..d2b77d9 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -1807,6 +1807,7 @@ static int xgbe_tx_poll(struct xgbe_channel *channel)
 	struct netdev_queue *txq;
 	int processed = 0;
 	unsigned int tx_packets = 0, tx_bytes = 0;
+	unsigned int cur;
 
 	DBGPR("-->xgbe_tx_poll\n");
 
@@ -1814,10 +1815,11 @@ static int xgbe_tx_poll(struct xgbe_channel *channel)
 	if (!ring)
 		return 0;
 
+	cur = ring->cur;
 	txq = netdev_get_tx_queue(netdev, channel->queue_index);
 
 	while ((processed < XGBE_TX_DESC_MAX_PROC) &&
-	       (ring->dirty != ring->cur)) {
+	       (ring->dirty != cur)) {
 		rdata = XGBE_GET_DESC_DATA(ring, ring->dirty);
 		rdesc = rdata->rdesc;
 
-- 
2.4.1


From a4ded16560af78b57fae335afcadef15021e4760 Mon Sep 17 00:00:00 2001
From: "Lendacky, Thomas" <Thomas.Lendacky@amd.com>
Date: Mon, 26 Oct 2015 17:13:54 -0500
Subject: [PATCH 09/30] amd-xgbe: Fix race between access of desc and desc
 index

[ Upstream commit 20986ed826cbb36bb8f2d77f872e3c52d8d30647 ]

During Tx cleanup it's still possible for the descriptor data to be
read ahead of the descriptor index. A memory barrier is required between
the read of the descriptor index and the start of the Tx cleanup loop.
This allows a change to a lighter-weight barrier in the Tx transmit
routine just before updating the current descriptor index.

Since the memory barrier does result in extra overhead on arm64, keep
the previous change to not chase the current descriptor value. This
prevents the execution of the barrier for each loop performed.

Suggested-by: Alexander Duyck <alexander.duyck@gmail.com>
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe-dev.c | 2 +-
 drivers/net/ethernet/amd/xgbe/xgbe-drv.c | 4 ++++
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
index e9ab8b9..f672dba 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
@@ -1595,7 +1595,7 @@ static void xgbe_dev_xmit(struct xgbe_channel *channel)
 				  packet->rdesc_count, 1);
 
 	/* Make sure ownership is written to the descriptor */
-	wmb();
+	smp_wmb();
 
 	ring->cur = cur_index + 1;
 	if (!packet->skb->xmit_more ||
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index d2b77d9..dde0486 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -1816,6 +1816,10 @@ static int xgbe_tx_poll(struct xgbe_channel *channel)
 		return 0;
 
 	cur = ring->cur;
+
+	/* Be sure we get ring->cur before accessing descriptor data */
+	smp_rmb();
+
 	txq = netdev_get_tx_queue(netdev, channel->queue_index);
 
 	while ((processed < XGBE_TX_DESC_MAX_PROC) &&
-- 
2.4.1


From 484dacbfaba57f4089f19647b859aab053919568 Mon Sep 17 00:00:00 2001
From: Fabio Estevam <fabio.estevam@freescale.com>
Date: Wed, 12 Aug 2015 12:10:23 -0300
Subject: [PATCH 10/30] net: fec: Remove unneeded use of IS_ERR_VALUE() macro

[ Upstream commit b0c6ce24911fcb64715de9569f0f7b4f54d1d045 ]

There is no need to use the IS_ERR_VALUE() macro for checking
the return value from pm_runtime_* functions.

Just do a simple negative test instead.

The semantic patch that makes this change is available
in scripts/coccinelle/api/pm_runtime.cocci.

Signed-off-by: Fabio Estevam <fabio.estevam@freescale.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_main.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index de63266d..bee2765 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -1775,7 +1775,7 @@ static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 	int ret = 0;
 
 	ret = pm_runtime_get_sync(dev);
-	if (IS_ERR_VALUE(ret))
+	if (ret < 0)
 		return ret;
 
 	fep->mii_timeout = 0;
@@ -1814,7 +1814,7 @@ static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 	int ret = 0;
 
 	ret = pm_runtime_get_sync(dev);
-	if (IS_ERR_VALUE(ret))
+	if (ret < 0)
 		return ret;
 
 	fep->mii_timeout = 0;
@@ -2866,7 +2866,7 @@ fec_enet_open(struct net_device *ndev)
 	int ret;
 
 	ret = pm_runtime_get_sync(&fep->pdev->dev);
-	if (IS_ERR_VALUE(ret))
+	if (ret < 0)
 		return ret;
 
 	pinctrl_pm_select_default_state(&fep->pdev->dev);
-- 
2.4.1


From 556f7b32d62433fd8035afac93173df9f4617f79 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 24 Oct 2015 05:47:44 -0700
Subject: [PATCH 11/30] ipv6: gre: support SIT encapsulation

[ Upstream commit 7e3b6e7423d5f994257c1de88e06b509673fdbcf ]

gre_gso_segment() chokes if SIT frames were aggregated by GRO engine.

Fixes: 61c1db7fae21e ("ipv6: sit: add GSO/TSO support")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/gre_offload.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index 5aa46d4..5a8ee32 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -36,7 +36,8 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 				  SKB_GSO_TCP_ECN |
 				  SKB_GSO_GRE |
 				  SKB_GSO_GRE_CSUM |
-				  SKB_GSO_IPIP)))
+				  SKB_GSO_IPIP |
+				  SKB_GSO_SIT)))
 		goto out;
 
 	if (!skb->encapsulation)
-- 
2.4.1


From befb5893c325a6d031f49969a6db8f32ad10a1b9 Mon Sep 17 00:00:00 2001
From: "Maciej S. Szmigiero" <mail@maciej.szmigiero.name>
Date: Thu, 3 Sep 2015 21:38:30 +0200
Subject: [PATCH 12/30] net: fec: normalize return value of
 pm_runtime_get_sync() in MDIO write

[ Upstream commit 42ea4457aea7aaeddf0c0b06724f297608f5e9d2 ]

If fec MDIO write method succeeds its return value comes from
call to pm_runtime_get_sync().
But pm_runtime_get_sync() can also return 1.

In case of Micrel KSZ9031 PHY this value will then
be returned along the call chain of phy_write() ->
ksz9031_extended_write() -> ksz9031_center_flp_timing() ->
ksz9031_config_init() -> phy_init_hw() -> phy_attach_direct() ->
phy_connect_direct().

Then phy_connect() will cast it into a pointer using ERR_PTR(),
which then fec_enet_mii_probe() will try to dereference
resulting in an oops.

Fix it by normalizing return value of pm_runtime_get_sync()
to be zero if positive in MDIO write method.

Fixes: 8fff755e9f8d ("net: fec: Ensure clocks are enabled while using mdio bus")
Signed-off-by: Maciej Szmigiero <mail@maciej.szmigiero.name>
Acked-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_main.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index bee2765..5d1dde3 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -1811,11 +1811,13 @@ static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 	struct fec_enet_private *fep = bus->priv;
 	struct device *dev = &fep->pdev->dev;
 	unsigned long time_left;
-	int ret = 0;
+	int ret;
 
 	ret = pm_runtime_get_sync(dev);
 	if (ret < 0)
 		return ret;
+	else
+		ret = 0;
 
 	fep->mii_timeout = 0;
 	reinit_completion(&fep->mdio_done);
-- 
2.4.1


From 30510ca202993f08074e60a0be3613aa897794da Mon Sep 17 00:00:00 2001
From: Alexander Duyck <aduyck@mirantis.com>
Date: Tue, 27 Oct 2015 15:06:45 -0700
Subject: [PATCH 13/30] fib_trie: leaf_walk_rcu should not compute key if key
 is less than pn->key

[ Upstream commit c2229fe1430d4e1c70e36520229dd64a87802b20 ]

We were computing the child index in cases where the key value we were
looking for was actually less than the base key of the tnode.  As a result
we were getting incorrect index values that would cause us to skip over
some children.

To fix this I have added a test that will force us to use child index 0 if
the key we are looking for is less than the key of the current tnode.

Fixes: 8be33e955cb9 ("fib_trie: Fib walk rcu should take a tnode and key instead of a trie and a leaf")
Reported-by: Brian Rak <brak@gameservers.com>
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_trie.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index b0c6258..ea3aedb 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1561,7 +1561,7 @@ static struct key_vector *leaf_walk_rcu(struct key_vector **tn, t_key key)
 	do {
 		/* record parent and next child index */
 		pn = n;
-		cindex = key ? get_index(key, pn) : 0;
+		cindex = (key > pn->key) ? get_index(key, pn) : 0;
 
 		if (cindex >> pn->bits)
 			break;
-- 
2.4.1


From 92113af88c34bee689654f9c5f694a6d0c41c1e0 Mon Sep 17 00:00:00 2001
From: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Date: Mon, 26 Oct 2015 12:46:37 -0400
Subject: [PATCH 14/30] RDS-TCP: Recover correctly from pskb_pull()/pksb_trim()
 failure in rds_tcp_data_recv

[ Upstream commit 8ce675ff39b9958d1c10f86cf58e357efaafc856 ]

Either of pskb_pull() or pskb_trim() may fail under low memory conditions.
If rds_tcp_data_recv() ignores such failures, the application will
receive corrupted data because the skb has not been correctly
carved to the RDS datagram size.

Avoid this by handling pskb_pull/pskb_trim failure in the same
manner as the skb_clone failure: bail out of rds_tcp_data_recv(), and
retry via the deferred call to rds_send_worker() that gets set up on
ENOMEM from rds_tcp_read_sock()

Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/tcp_recv.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c
index fbc5ef8..27a9921 100644
--- a/net/rds/tcp_recv.c
+++ b/net/rds/tcp_recv.c
@@ -214,8 +214,15 @@ static int rds_tcp_data_recv(read_descriptor_t *desc, struct sk_buff *skb,
 			}
 
 			to_copy = min(tc->t_tinc_data_rem, left);
-			pskb_pull(clone, offset);
-			pskb_trim(clone, to_copy);
+			if (!pskb_pull(clone, offset) ||
+			    pskb_trim(clone, to_copy)) {
+				pr_warn("rds_tcp_data_recv: pull/trim failed "
+					"left %zu data_rem %zu skb_len %d\n",
+					left, tc->t_tinc_data_rem, skb->len);
+				kfree_skb(clone);
+				desc->error = -ENOMEM;
+				goto out;
+			}
 			skb_queue_tail(&tinc->ti_skb_list, clone);
 
 			rdsdebug("skb %p data %p len %d off %u to_copy %zu -> "
-- 
2.4.1


From fb8a8bc61c791e6940e35a2364f19a4ce5115982 Mon Sep 17 00:00:00 2001
From: Carol L Soto <clsoto@linux.vnet.ibm.com>
Date: Tue, 27 Oct 2015 17:36:20 +0200
Subject: [PATCH 15/30] net/mlx4: Copy/set only sizeof struct mlx4_eqe bytes

[ Upstream commit c02b05011fadf8e409e41910217ca689f2fc9d91 ]

When doing memcpy/memset of EQEs, we should use sizeof struct
mlx4_eqe as the base size and not caps.eqe_size which could be bigger.

If caps.eqe_size is bigger than the struct mlx4_eqe then we corrupt
data in the master context.

When using a 64 byte stride, the memcpy copied over 63 bytes to the
slave_eq structure.  This resulted in copying over the entire eqe of
interest, including its ownership bit -- and also 31 bytes of garbage
into the next WQE in the slave EQ -- which did NOT include the ownership
bit (and therefore had no impact).

However, once the stride is increased to 128, we are overwriting the
ownership bits of *three* eqes in the slave_eq struct.  This results
in an incorrect ownership bit for those eqes, which causes the eq to
seem to be full. The issue therefore surfaced only once 128-byte EQEs
started being used in SRIOV and (overarchitectures that have 128/256
byte cache-lines such as PPC) - e.g after commit 77507aa249ae
"net/mlx4_core: Enable CQE/EQE stride support".

Fixes: 08ff32352d6f ('mlx4: 64-byte CQE/EQE support')
Signed-off-by: Carol L Soto <clsoto@linux.vnet.ibm.com>
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/cmd.c | 2 +-
 drivers/net/ethernet/mellanox/mlx4/eq.c  | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 0a32020..2177e56 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -2398,7 +2398,7 @@ int mlx4_multi_func_init(struct mlx4_dev *dev)
 			}
 		}
 
-		memset(&priv->mfunc.master.cmd_eqe, 0, dev->caps.eqe_size);
+		memset(&priv->mfunc.master.cmd_eqe, 0, sizeof(struct mlx4_eqe));
 		priv->mfunc.master.cmd_eqe.type = MLX4_EVENT_TYPE_CMD;
 		INIT_WORK(&priv->mfunc.master.comm_work,
 			  mlx4_master_comm_channel);
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index 8e81e53..ad8f95d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -196,7 +196,7 @@ static void slave_event(struct mlx4_dev *dev, u8 slave, struct mlx4_eqe *eqe)
 		return;
 	}
 
-	memcpy(s_eqe, eqe, dev->caps.eqe_size - 1);
+	memcpy(s_eqe, eqe, sizeof(struct mlx4_eqe) - 1);
 	s_eqe->slave_id = slave;
 	/* ensure all information is written before setting the ownersip bit */
 	dma_wmb();
-- 
2.4.1


From bc6615c152f490763e66ba0fd3350a5a067ffd09 Mon Sep 17 00:00:00 2001
From: Jon Paul Maloy <jon.maloy@ericsson.com>
Date: Wed, 28 Oct 2015 13:09:53 -0400
Subject: [PATCH 16/30] tipc: linearize arriving NAME_DISTR and LINK_PROTO
 buffers

[ Upstream commit 5cbb28a4bf65c7e4daa6c25b651fed8eb888c620 ]

Testing of the new UDP bearer has revealed that reception of
NAME_DISTRIBUTOR, LINK_PROTOCOL/RESET and LINK_PROTOCOL/ACTIVATE
message buffers is not prepared for the case that those may be
non-linear.

We now linearize all such buffers before they are delivered up to the
generic reception layer.

In order for the commit to apply cleanly to 'net' and 'stable', we do
the change in the function tipc_udp_recv() for now. Later, we will post
a commit to 'net-next' moving the linearization to generic code, in
tipc_named_rcv() and tipc_link_proto_rcv().

Fixes: commit d0f91938bede ("tipc: add ip/udp media type")
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/udp_media.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index 66deebc..f8dfee5 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -48,6 +48,7 @@
 #include <linux/tipc_netlink.h>
 #include "core.h"
 #include "bearer.h"
+#include "msg.h"
 
 /* IANA assigned UDP port */
 #define UDP_PORT_DEFAULT	6118
@@ -216,6 +217,10 @@ static int tipc_udp_recv(struct sock *sk, struct sk_buff *skb)
 {
 	struct udp_bearer *ub;
 	struct tipc_bearer *b;
+	int usr = msg_user(buf_msg(skb));
+
+	if ((usr == LINK_PROTOCOL) || (usr == NAME_DISTRIBUTOR))
+		skb_linearize(skb);
 
 	ub = rcu_dereference_sk_user_data(sk);
 	if (!ub) {
-- 
2.4.1


From 3bd23d90ce393d1cf776b2a4a541def02be08f4c Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Fri, 30 Oct 2015 10:23:33 +0200
Subject: [PATCH 17/30] ipv4: fix to not remove local route on link down

[ Upstream commit 4f823defdd5b106a5e89745ee8b163c71855de1e ]

When fib_netdev_event calls fib_disable_ip on NETDEV_DOWN event
we should not delete the local routes if the local address
is still present. The confusion comes from the fact that both
fib_netdev_event and fib_inetaddr_event use the NETDEV_DOWN
constant. Fix it by returning back the variable 'force'.

Steps to reproduce:
modprobe dummy
ifconfig dummy0 192.168.168.1 up
ifconfig dummy0 down
ip route list table local | grep dummy | grep host
local 192.168.168.1 dev dummy0  proto kernel  scope host  src 192.168.168.1

Fixes: 8a3d03166f19 ("net: track link-status of ipv4 nexthops")
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_fib.h     |  2 +-
 net/ipv4/fib_frontend.c  | 13 +++++++------
 net/ipv4/fib_semantics.c | 11 ++++++++---
 3 files changed, 16 insertions(+), 10 deletions(-)

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 5fa643b..ff6d78f 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -306,7 +306,7 @@ void fib_flush_external(struct net *net);
 
 /* Exported by fib_semantics.c */
 int ip_fib_check_default(__be32 gw, struct net_device *dev);
-int fib_sync_down_dev(struct net_device *dev, unsigned long event);
+int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force);
 int fib_sync_down_addr(struct net *net, __be32 local);
 int fib_sync_up(struct net_device *dev, unsigned int nh_flags);
 void fib_select_multipath(struct fib_result *res);
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 6bbc549..d7116cf 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1063,9 +1063,10 @@ static void nl_fib_lookup_exit(struct net *net)
 	net->ipv4.fibnl = NULL;
 }
 
-static void fib_disable_ip(struct net_device *dev, unsigned long event)
+static void fib_disable_ip(struct net_device *dev, unsigned long event,
+			   bool force)
 {
-	if (fib_sync_down_dev(dev, event))
+	if (fib_sync_down_dev(dev, event, force))
 		fib_flush(dev_net(dev));
 	rt_cache_flush(dev_net(dev));
 	arp_ifdown(dev);
@@ -1093,7 +1094,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event,
 			/* Last address was deleted from this interface.
 			 * Disable IP.
 			 */
-			fib_disable_ip(dev, event);
+			fib_disable_ip(dev, event, true);
 		} else {
 			rt_cache_flush(dev_net(dev));
 		}
@@ -1110,7 +1111,7 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo
 	unsigned int flags;
 
 	if (event == NETDEV_UNREGISTER) {
-		fib_disable_ip(dev, event);
+		fib_disable_ip(dev, event, true);
 		rt_flush_dev(dev);
 		return NOTIFY_DONE;
 	}
@@ -1131,14 +1132,14 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo
 		rt_cache_flush(net);
 		break;
 	case NETDEV_DOWN:
-		fib_disable_ip(dev, event);
+		fib_disable_ip(dev, event, false);
 		break;
 	case NETDEV_CHANGE:
 		flags = dev_get_flags(dev);
 		if (flags & (IFF_RUNNING | IFF_LOWER_UP))
 			fib_sync_up(dev, RTNH_F_LINKDOWN);
 		else
-			fib_sync_down_dev(dev, event);
+			fib_sync_down_dev(dev, event, false);
 		/* fall through */
 	case NETDEV_CHANGEMTU:
 		rt_cache_flush(net);
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 3a06586..fadf7b2 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1132,7 +1132,13 @@ int fib_sync_down_addr(struct net *net, __be32 local)
 	return ret;
 }
 
-int fib_sync_down_dev(struct net_device *dev, unsigned long event)
+/* Event              force Flags           Description
+ * NETDEV_CHANGE      0     LINKDOWN        Carrier OFF, not for scope host
+ * NETDEV_DOWN        0     LINKDOWN|DEAD   Link down, not for scope host
+ * NETDEV_DOWN        1     LINKDOWN|DEAD   Last address removed
+ * NETDEV_UNREGISTER  1     LINKDOWN|DEAD   Device removed
+ */
+int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force)
 {
 	int ret = 0;
 	int scope = RT_SCOPE_NOWHERE;
@@ -1141,8 +1147,7 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event)
 	struct hlist_head *head = &fib_info_devhash[hash];
 	struct fib_nh *nh;
 
-	if (event == NETDEV_UNREGISTER ||
-	    event == NETDEV_DOWN)
+	if (force)
 		scope = -1;
 
 	hlist_for_each_entry(nh, head, nh_hash) {
-- 
2.4.1


From d628fc9d637ad3c158401d1ff5d508a0df2b1df1 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Fri, 30 Oct 2015 10:23:34 +0200
Subject: [PATCH 18/30] ipv4: update RTNH_F_LINKDOWN flag on UP event

[ Upstream commit c9b3292eeb52c6834e972eb5b8fe38914771ed12 ]

When nexthop is part of multipath route we should clear the
LINKDOWN flag when link goes UP or when first address is added.
This is needed because we always set LINKDOWN flag when DEAD flag
was set but now on UP the nexthop is not dead anymore. Examples when
LINKDOWN bit can be forgotten when no NETDEV_CHANGE is delivered:

- link goes down (LINKDOWN is set), then link goes UP and device
shows carrier OK but LINKDOWN remains set

- last address is deleted (LINKDOWN is set), then address is
added and device shows carrier OK but LINKDOWN remains set

Steps to reproduce:
modprobe dummy
ifconfig dummy0 192.168.168.1 up

here add a multipath route where one nexthop is for dummy0:

ip route add 1.2.3.4 nexthop dummy0 nexthop SOME_OTHER_DEVICE
ifconfig dummy0 down
ifconfig dummy0 up

now ip route shows nexthop that is not dead. Now set the sysctl var:

echo 1 > /proc/sys/net/ipv4/conf/dummy0/ignore_routes_with_linkdown

now ip route will show a dead nexthop because the forgotten
RTNH_F_LINKDOWN is propagated as RTNH_F_DEAD.

Fixes: 8a3d03166f19 ("net: track link-status of ipv4 nexthops")
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_semantics.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index fadf7b2..71bad5c 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1296,6 +1296,13 @@ int fib_sync_up(struct net_device *dev, unsigned int nh_flags)
 	if (!(dev->flags & IFF_UP))
 		return 0;
 
+	if (nh_flags & RTNH_F_DEAD) {
+		unsigned int flags = dev_get_flags(dev);
+
+		if (flags & (IFF_RUNNING | IFF_LOWER_UP))
+			nh_flags |= RTNH_F_LINKDOWN;
+	}
+
 	prev_fi = NULL;
 	hash = fib_devindex_hashfn(dev->ifindex);
 	head = &fib_info_devhash[hash];
-- 
2.4.1


From adcf739992f9df748bf744c7f46b56753c061045 Mon Sep 17 00:00:00 2001
From: Phil Reid <preid@electromag.com.au>
Date: Fri, 30 Oct 2015 16:43:55 +0800
Subject: [PATCH 19/30] stmmac: Correctly report PTP capabilities.

[ Upstream commit e6dbe1eb2db0d7a14991c06278dd3030c45fb825 ]

priv->hwts_*_en indicate if timestamping is enabled/disabled at run
time. But  priv->dma_cap.time_stamp  and priv->dma_cap.atime_stamp
indicates HW is support for PTPv1/PTPv2.

Signed-off-by: Phil Reid <preid@electromag.com.au>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index 771cda2..2e51b81 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -721,10 +721,13 @@ static int stmmac_get_ts_info(struct net_device *dev,
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
 
-	if ((priv->hwts_tx_en) && (priv->hwts_rx_en)) {
+	if ((priv->dma_cap.time_stamp || priv->dma_cap.atime_stamp)) {
 
-		info->so_timestamping = SOF_TIMESTAMPING_TX_HARDWARE |
+		info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
+					SOF_TIMESTAMPING_TX_HARDWARE |
+					SOF_TIMESTAMPING_RX_SOFTWARE |
 					SOF_TIMESTAMPING_RX_HARDWARE |
+					SOF_TIMESTAMPING_SOFTWARE |
 					SOF_TIMESTAMPING_RAW_HARDWARE;
 
 		if (priv->ptp_clock)
-- 
2.4.1


From 5138a56979f9ef950ca86eb82a1e71c449d7ec27 Mon Sep 17 00:00:00 2001
From: Ani Sinha <ani@arista.com>
Date: Fri, 30 Oct 2015 16:54:31 -0700
Subject: [PATCH 20/30] ipmr: fix possible race resulting from improper usage
 of IP_INC_STATS_BH() in preemptible context.

[ Upstream commit 44f49dd8b5a606870a1f21101522a0f9c4414784 ]

Fixes the following kernel BUG :

BUG: using __this_cpu_add() in preemptible [00000000] code: bash/2758
caller is __this_cpu_preempt_check+0x13/0x15
CPU: 0 PID: 2758 Comm: bash Tainted: P           O   3.18.19 #2
 ffffffff8170eaca ffff880110d1b788 ffffffff81482b2a 0000000000000000
 0000000000000000 ffff880110d1b7b8 ffffffff812010ae ffff880007cab800
 ffff88001a060800 ffff88013a899108 ffff880108b84240 ffff880110d1b7c8
Call Trace:
[<ffffffff81482b2a>] dump_stack+0x52/0x80
[<ffffffff812010ae>] check_preemption_disabled+0xce/0xe1
[<ffffffff812010d4>] __this_cpu_preempt_check+0x13/0x15
[<ffffffff81419d60>] ipmr_queue_xmit+0x647/0x70c
[<ffffffff8141a154>] ip_mr_forward+0x32f/0x34e
[<ffffffff8141af76>] ip_mroute_setsockopt+0xe03/0x108c
[<ffffffff810553fc>] ? get_parent_ip+0x11/0x42
[<ffffffff810e6974>] ? pollwake+0x4d/0x51
[<ffffffff81058ac0>] ? default_wake_function+0x0/0xf
[<ffffffff810553fc>] ? get_parent_ip+0x11/0x42
[<ffffffff810613d9>] ? __wake_up_common+0x45/0x77
[<ffffffff81486ea9>] ? _raw_spin_unlock_irqrestore+0x1d/0x32
[<ffffffff810618bc>] ? __wake_up_sync_key+0x4a/0x53
[<ffffffff8139a519>] ? sock_def_readable+0x71/0x75
[<ffffffff813dd226>] do_ip_setsockopt+0x9d/0xb55
[<ffffffff81429818>] ? unix_seqpacket_sendmsg+0x3f/0x41
[<ffffffff813963fe>] ? sock_sendmsg+0x6d/0x86
[<ffffffff813959d4>] ? sockfd_lookup_light+0x12/0x5d
[<ffffffff8139650a>] ? SyS_sendto+0xf3/0x11b
[<ffffffff810d5738>] ? new_sync_read+0x82/0xaa
[<ffffffff813ddd19>] compat_ip_setsockopt+0x3b/0x99
[<ffffffff813fb24a>] compat_raw_setsockopt+0x11/0x32
[<ffffffff81399052>] compat_sock_common_setsockopt+0x18/0x1f
[<ffffffff813c4d05>] compat_SyS_setsockopt+0x1a9/0x1cf
[<ffffffff813c4149>] compat_SyS_socketcall+0x180/0x1e3
[<ffffffff81488ea1>] cstar_dispatch+0x7/0x1e

Signed-off-by: Ani Sinha <ani@arista.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ipmr.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 3a2c016..df28693 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1683,8 +1683,8 @@ static inline int ipmr_forward_finish(struct sock *sk, struct sk_buff *skb)
 {
 	struct ip_options *opt = &(IPCB(skb)->opt);
 
-	IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS);
-	IP_ADD_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTOCTETS, skb->len);
+	IP_INC_STATS(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS);
+	IP_ADD_STATS(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTOCTETS, skb->len);
 
 	if (unlikely(opt->optlen))
 		ip_forward_options(skb);
@@ -1746,7 +1746,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
 		 * to blackhole.
 		 */
 
-		IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
+		IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
 		ip_rt_put(rt);
 		goto out_free;
 	}
-- 
2.4.1


From 221fb6930424ebdb2e936716703629d233daef2f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Sun, 1 Nov 2015 01:34:50 +0100
Subject: [PATCH 21/30] qmi_wwan: fix entry for HP lt4112 LTE/HSPA+ Gobi 4G
 Module
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 70910791731b5956171e1bfcad707766b8e18fee ]

The lt4112 is a HP branded Huawei me906e modem. Like other Huawei
modems, it does not have a fixed interface to function mapping.
Instead it uses a Huawei specific scheme: functions are mapped by
subclass and protocol.

However, the HP vendor ID is used for modems from many different
manufacturers using different schemes, so we cannot apply a generic
vendor rule like we do for the Huawei vendor ID.

Replace the previous lt4112 entry pointing to an arbitrary interface
number with a device specific subclass + protocol match.

Reported-and-tested-by: Muri Nicanor <muri+libqmi@immerda.ch>
Tested-by: Martin Hauke <mardnh@gmx.de>
Fixes: bb2bdeb83fb1 ("qmi_wwan: Add support for HP lt4112 LTE/HSPA+ Gobi 4G Modem")
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 8f1738c..6ee6c15 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -539,6 +539,10 @@ static const struct usb_device_id products[] = {
 					      USB_CDC_PROTO_NONE),
 		.driver_info        = (unsigned long)&qmi_wwan_info,
 	},
+	{	/* HP lt4112 LTE/HSPA+ Gobi 4G Module (Huawei me906e) */
+		USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x581d, USB_CLASS_VENDOR_SPEC, 1, 7),
+		.driver_info = (unsigned long)&qmi_wwan_info,
+	},
 
 	/* 3. Combined interface devices matching on interface number */
 	{QMI_FIXED_INTF(0x0408, 0xea42, 4)},	/* Yota / Megafon M100-1 */
@@ -790,7 +794,6 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x413c, 0x81a8, 8)},	/* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card */
 	{QMI_FIXED_INTF(0x413c, 0x81a9, 8)},	/* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */
 	{QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)},	/* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */
-	{QMI_FIXED_INTF(0x03f0, 0x581d, 4)},	/* HP lt4112 LTE/HSPA+ Gobi 4G Module (Huawei me906e) */
 
 	/* 4. Gobi 1000 devices */
 	{QMI_GOBI1K_DEVICE(0x05c6, 0x9212)},	/* Acer Gobi Modem Device */
-- 
2.4.1


From d33da04d65aa3ba1c16723f8e6e2041417eddb0a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 2 Nov 2015 17:08:19 -0800
Subject: [PATCH 22/30] sit: fix sit0 percpu double allocations

[ Upstream commit 4ece9009774596ee3df0acba65a324b7ea79387c ]

sit0 device allocates its percpu storage twice :
- One time in ipip6_tunnel_init()
- One time in ipip6_fb_tunnel_init()

Thus we leak 48 bytes per possible cpu per network namespace dismantle.

ipip6_fb_tunnel_init() can be much simpler and does not
return an error, and should be called after register_netdev()

Note that ipip6_tunnel_clone_6rd() also needs to be called
after register_netdev() (calling ipip6_tunnel_init())

Fixes: ebe084aafb7e ("sit: Use ipip6_tunnel_init as the ndo_init function.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 26 ++++----------------------
 1 file changed, 4 insertions(+), 22 deletions(-)

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index ac35a28..85c4b2f 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1394,34 +1394,20 @@ static int ipip6_tunnel_init(struct net_device *dev)
 	return 0;
 }
 
-static int __net_init ipip6_fb_tunnel_init(struct net_device *dev)
+static void __net_init ipip6_fb_tunnel_init(struct net_device *dev)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	struct iphdr *iph = &tunnel->parms.iph;
 	struct net *net = dev_net(dev);
 	struct sit_net *sitn = net_generic(net, sit_net_id);
 
-	tunnel->dev = dev;
-	tunnel->net = dev_net(dev);
-
 	iph->version		= 4;
 	iph->protocol		= IPPROTO_IPV6;
 	iph->ihl		= 5;
 	iph->ttl		= 64;
 
-	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
-	if (!dev->tstats)
-		return -ENOMEM;
-
-	tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst);
-	if (!tunnel->dst_cache) {
-		free_percpu(dev->tstats);
-		return -ENOMEM;
-	}
-
 	dev_hold(dev);
 	rcu_assign_pointer(sitn->tunnels_wc[0], tunnel);
-	return 0;
 }
 
 static int ipip6_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -1831,23 +1817,19 @@ static int __net_init sit_init_net(struct net *net)
 	 */
 	sitn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL;
 
-	err = ipip6_fb_tunnel_init(sitn->fb_tunnel_dev);
-	if (err)
-		goto err_dev_free;
-
-	ipip6_tunnel_clone_6rd(sitn->fb_tunnel_dev, sitn);
 	err = register_netdev(sitn->fb_tunnel_dev);
 	if (err)
 		goto err_reg_dev;
 
+	ipip6_tunnel_clone_6rd(sitn->fb_tunnel_dev, sitn);
+	ipip6_fb_tunnel_init(sitn->fb_tunnel_dev);
+
 	t = netdev_priv(sitn->fb_tunnel_dev);
 
 	strcpy(t->parms.name, sitn->fb_tunnel_dev->name);
 	return 0;
 
 err_reg_dev:
-	dev_put(sitn->fb_tunnel_dev);
-err_dev_free:
 	ipip6_dev_free(sitn->fb_tunnel_dev);
 err_alloc_dev:
 	return err;
-- 
2.4.1


From c903be329f0820a8267a7826bec3eb547712e386 Mon Sep 17 00:00:00 2001
From: Martin Habets <mhabets@solarflare.com>
Date: Mon, 2 Nov 2015 12:51:31 +0000
Subject: [PATCH 23/30] sfc: push partner queue for skb->xmit_more

[ Upstream commit b2663a4f30e85ec606b806f5135413e6d5c78d1e ]

When the IP stack passes SKBs the sfc driver puts them in 2 different TX
queues (called partners), one for checksummed and one for not checksummed.
If the SKB has xmit_more set the driver will delay pushing the work to the
NIC.

When later it does decide to push the buffers this patch ensures it also
pushes the partner queue, if that also has any delayed work. Before this
fix the work in the partner queue would be left for a long time and cause
a netdev watchdog.

Fixes: 70b33fb ("sfc: add support for skb->xmit_more")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Martin Habets <mhabets@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/ef10.c       |  4 +++-
 drivers/net/ethernet/sfc/farch.c      |  4 +++-
 drivers/net/ethernet/sfc/net_driver.h |  2 ++
 drivers/net/ethernet/sfc/tx.c         | 30 ++++++++++++++++++++++++++++--
 4 files changed, 36 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index b1a4ea2..4dd18f4 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -1809,7 +1809,9 @@ static void efx_ef10_tx_write(struct efx_tx_queue *tx_queue)
 	unsigned int write_ptr;
 	efx_qword_t *txd;
 
-	BUG_ON(tx_queue->write_count == tx_queue->insert_count);
+	tx_queue->xmit_more_available = false;
+	if (unlikely(tx_queue->write_count == tx_queue->insert_count))
+		return;
 
 	do {
 		write_ptr = tx_queue->write_count & tx_queue->ptr_mask;
diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c
index f08266f..5a1c5a8 100644
--- a/drivers/net/ethernet/sfc/farch.c
+++ b/drivers/net/ethernet/sfc/farch.c
@@ -321,7 +321,9 @@ void efx_farch_tx_write(struct efx_tx_queue *tx_queue)
 	unsigned write_ptr;
 	unsigned old_write_count = tx_queue->write_count;
 
-	BUG_ON(tx_queue->write_count == tx_queue->insert_count);
+	tx_queue->xmit_more_available = false;
+	if (unlikely(tx_queue->write_count == tx_queue->insert_count))
+		return;
 
 	do {
 		write_ptr = tx_queue->write_count & tx_queue->ptr_mask;
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index 47d1e3a..b8e8ce1 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -219,6 +219,7 @@ struct efx_tx_buffer {
  * @tso_packets: Number of packets via the TSO xmit path
  * @pushes: Number of times the TX push feature has been used
  * @pio_packets: Number of times the TX PIO feature has been used
+ * @xmit_more_available: Are any packets waiting to be pushed to the NIC
  * @empty_read_count: If the completion path has seen the queue as empty
  *	and the transmission path has not yet checked this, the value of
  *	@read_count bitwise-added to %EFX_EMPTY_COUNT_VALID; otherwise 0.
@@ -253,6 +254,7 @@ struct efx_tx_queue {
 	unsigned int tso_packets;
 	unsigned int pushes;
 	unsigned int pio_packets;
+	bool xmit_more_available;
 	/* Statistics to supplement MAC stats */
 	unsigned long tx_packets;
 
diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c
index 1833a01..67f6afa 100644
--- a/drivers/net/ethernet/sfc/tx.c
+++ b/drivers/net/ethernet/sfc/tx.c
@@ -431,8 +431,20 @@ finish_packet:
 	efx_tx_maybe_stop_queue(tx_queue);
 
 	/* Pass off to hardware */
-	if (!skb->xmit_more || netif_xmit_stopped(tx_queue->core_txq))
+	if (!skb->xmit_more || netif_xmit_stopped(tx_queue->core_txq)) {
+		struct efx_tx_queue *txq2 = efx_tx_queue_partner(tx_queue);
+
+		/* There could be packets left on the partner queue if those
+		 * SKBs had skb->xmit_more set. If we do not push those they
+		 * could be left for a long time and cause a netdev watchdog.
+		 */
+		if (txq2->xmit_more_available)
+			efx_nic_push_buffers(txq2);
+
 		efx_nic_push_buffers(tx_queue);
+	} else {
+		tx_queue->xmit_more_available = skb->xmit_more;
+	}
 
 	tx_queue->tx_packets++;
 
@@ -722,6 +734,7 @@ void efx_init_tx_queue(struct efx_tx_queue *tx_queue)
 	tx_queue->read_count = 0;
 	tx_queue->old_read_count = 0;
 	tx_queue->empty_read_count = 0 | EFX_EMPTY_COUNT_VALID;
+	tx_queue->xmit_more_available = false;
 
 	/* Set up TX descriptor ring */
 	efx_nic_init_tx(tx_queue);
@@ -747,6 +760,7 @@ void efx_fini_tx_queue(struct efx_tx_queue *tx_queue)
 
 		++tx_queue->read_count;
 	}
+	tx_queue->xmit_more_available = false;
 	netdev_tx_reset_queue(tx_queue->core_txq);
 }
 
@@ -1302,8 +1316,20 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue,
 	efx_tx_maybe_stop_queue(tx_queue);
 
 	/* Pass off to hardware */
-	if (!skb->xmit_more || netif_xmit_stopped(tx_queue->core_txq))
+	if (!skb->xmit_more || netif_xmit_stopped(tx_queue->core_txq)) {
+		struct efx_tx_queue *txq2 = efx_tx_queue_partner(tx_queue);
+
+		/* There could be packets left on the partner queue if those
+		 * SKBs had skb->xmit_more set. If we do not push those they
+		 * could be left for a long time and cause a netdev watchdog.
+		 */
+		if (txq2->xmit_more_available)
+			efx_nic_push_buffers(txq2);
+
 		efx_nic_push_buffers(tx_queue);
+	} else {
+		tx_queue->xmit_more_available = skb->xmit_more;
+	}
 
 	tx_queue->tso_bursts++;
 	return NETDEV_TX_OK;
-- 
2.4.1


From 7a3bbb7395cc2fa708521e7a78bb75dc94cf1353 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 2 Nov 2015 07:50:07 -0800
Subject: [PATCH 24/30] net: avoid NULL deref in inet_ctl_sock_destroy()

[ Upstream commit 8fa677d2706d325d71dab91bf6e6512c05214e37 ]

Under low memory conditions, tcp_sk_init() and icmp_sk_init()
can both iterate on all possible cpus and call inet_ctl_sock_destroy(),
with eventual NULL pointer.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_common.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/net/inet_common.h b/include/net/inet_common.h
index 279f835..109e3ee 100644
--- a/include/net/inet_common.h
+++ b/include/net/inet_common.h
@@ -41,7 +41,8 @@ int inet_recv_error(struct sock *sk, struct msghdr *msg, int len,
 
 static inline void inet_ctl_sock_destroy(struct sock *sk)
 {
-	sock_release(sk->sk_socket);
+	if (sk)
+		sock_release(sk->sk_socket);
 }
 
 #endif
-- 
2.4.1


From d144a38bdaf2c3eeb3478fed0beba4ba5ce550ea Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Wed, 4 Nov 2015 14:47:53 +0100
Subject: [PATCH 25/30] ipv6: clean up dev_snmp6 proc entry when we fail to
 initialize inet6_dev

[ Upstream commit 2a189f9e57650e9f310ddf4aad75d66c1233a064 ]

In ipv6_add_dev, when addrconf_sysctl_register fails, we do not clean up
the dev_snmp6 entry that we have already registered for this device.
Call snmp6_unregister_dev in this case.

Fixes: a317a2f19da7d ("ipv6: fail early when creating netdev named all or default")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 21c2c81..c8c1fea 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -411,6 +411,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
 	if (err) {
 		ipv6_mc_destroy_dev(ndev);
 		del_timer(&ndev->regen_timer);
+		snmp6_unregister_dev(ndev);
 		goto err_release;
 	}
 	/* protected by rtnl_lock */
-- 
2.4.1


From 2d5bc150dfddc081c3d49e15afd8bf36ccc445bd Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Tue, 3 Nov 2015 14:32:57 -0800
Subject: [PATCH 26/30] ipv4: disable BH when changing ip local port range

[ Upstream commit 4ee3bd4a8c7463cdef0b82ebc33fc94a9170a7e0 ]

This fixes the following lockdep warning:

 [ INFO: inconsistent lock state ]
 4.3.0-rc7+ #1197 Not tainted
 ---------------------------------
 inconsistent {IN-SOFTIRQ-R} -> {SOFTIRQ-ON-W} usage.
 sysctl/1019 [HC0[0]:SC0[0]:HE1:SE1] takes:
  (&(&net->ipv4.ip_local_ports.lock)->seqcount){+.+-..}, at: [<ffffffff81921de7>] ipv4_local_port_range+0xb4/0x12a
 {IN-SOFTIRQ-R} state was registered at:
   [<ffffffff810bd682>] __lock_acquire+0x2f6/0xdf0
   [<ffffffff810be6d5>] lock_acquire+0x11c/0x1a4
   [<ffffffff818e599c>] inet_get_local_port_range+0x4e/0xae
   [<ffffffff8166e8e3>] udp_flow_src_port.constprop.40+0x23/0x116
   [<ffffffff81671cb9>] vxlan_xmit_one+0x219/0xa6a
   [<ffffffff81672f75>] vxlan_xmit+0xa6b/0xaa5
   [<ffffffff817f2deb>] dev_hard_start_xmit+0x2ae/0x465
   [<ffffffff817f35ed>] __dev_queue_xmit+0x531/0x633
   [<ffffffff817f3702>] dev_queue_xmit_sk+0x13/0x15
   [<ffffffff818004a5>] neigh_resolve_output+0x12f/0x14d
   [<ffffffff81959cfa>] ip6_finish_output2+0x344/0x39f
   [<ffffffff8195bf58>] ip6_finish_output+0x88/0x8e
   [<ffffffff8195bfef>] ip6_output+0x91/0xe5
   [<ffffffff819792ae>] dst_output_sk+0x47/0x4c
   [<ffffffff81979392>] NF_HOOK_THRESH.constprop.30+0x38/0x82
   [<ffffffff8197981e>] mld_sendpack+0x189/0x266
   [<ffffffff8197b28b>] mld_ifc_timer_expire+0x1ef/0x223
   [<ffffffff810de581>] call_timer_fn+0xfb/0x28c
   [<ffffffff810ded1e>] run_timer_softirq+0x1c7/0x1f1

Fixes: b8f1a55639e6 ("udp: Add function to make source port for UDP tunnels")
Cc: Tom Herbert <tom@herbertland.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/sysctl_net_ipv4.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 0330ab2..a1442c5 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -47,14 +47,14 @@ static void set_local_port_range(struct net *net, int range[2])
 {
 	bool same_parity = !((range[0] ^ range[1]) & 1);
 
-	write_seqlock(&net->ipv4.ip_local_ports.lock);
+	write_seqlock_bh(&net->ipv4.ip_local_ports.lock);
 	if (same_parity && !net->ipv4.ip_local_ports.warned) {
 		net->ipv4.ip_local_ports.warned = true;
 		pr_err_ratelimited("ip_local_port_range: prefer different parity for start/end values.\n");
 	}
 	net->ipv4.ip_local_ports.range[0] = range[0];
 	net->ipv4.ip_local_ports.range[1] = range[1];
-	write_sequnlock(&net->ipv4.ip_local_ports.lock);
+	write_sequnlock_bh(&net->ipv4.ip_local_ports.lock);
 }
 
 /* Validate changes from /proc interface. */
-- 
2.4.1


From a014f0e1b0481e67532cfaf6216f21c5aaf6c767 Mon Sep 17 00:00:00 2001
From: Francesco Ruggeri <fruggeri@aristanetworks.com>
Date: Thu, 5 Nov 2015 08:16:14 -0800
Subject: [PATCH 27/30] packet: race condition in packet_bind

[ Upstream commit 30f7ea1c2b5f5fb7462c5ae44fe2e40cb2d6a474 ]

There is a race conditions between packet_notifier and packet_bind{_spkt}.

It happens if packet_notifier(NETDEV_UNREGISTER) executes between the
time packet_bind{_spkt} takes a reference on the new netdevice and the
time packet_do_bind sets po->ifindex.
In this case the notification can be missed.
If this happens during a dev_change_net_namespace this can result in the
netdevice to be moved to the new namespace while the packet_sock in the
old namespace still holds a reference on it. When the netdevice is later
deleted in the new namespace the deletion hangs since the packet_sock
is not found in the new namespace' &net->packet.sklist.
It can be reproduced with the script below.

This patch makes packet_do_bind check again for the presence of the
netdevice in the packet_sock's namespace after the synchronize_net
in unregister_prot_hook.
More in general it also uses the rcu lock for the duration of the bind
to stop dev_change_net_namespace/rollback_registered_many from
going past the synchronize_net following unlist_netdevice, so that
no NETDEV_UNREGISTER notifications can happen on the new netdevice
while the bind is executing. In order to do this some code from
packet_bind{_spkt} is consolidated into packet_do_dev.

import socket, os, time, sys
proto=7
realDev='em1'
vlanId=400
if len(sys.argv) > 1:
   vlanId=int(sys.argv[1])
dev='vlan%d' % vlanId

os.system('taskset -p 0x10 %d' % os.getpid())

s = socket.socket(socket.PF_PACKET, socket.SOCK_RAW, proto)
os.system('ip link add link %s name %s type vlan id %d' %
          (realDev, dev, vlanId))
os.system('ip netns add dummy')

pid=os.fork()

if pid == 0:
   # dev should be moved while packet_do_bind is in synchronize net
   os.system('taskset -p 0x20000 %d' % os.getpid())
   os.system('ip link set %s netns dummy' % dev)
   os.system('ip netns exec dummy ip link del %s' % dev)
   s.close()
   sys.exit(0)

time.sleep(.004)
try:
   s.bind(('%s' % dev, proto+1))
except:
   print 'Could not bind socket'
   s.close()
   os.system('ip netns del dummy')
   sys.exit(0)

os.waitpid(pid, 0)
s.close()
os.system('ip netns del dummy')
sys.exit(0)

Signed-off-by: Francesco Ruggeri <fruggeri@arista.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 80 +++++++++++++++++++++++++++++++-------------------
 1 file changed, 49 insertions(+), 31 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 7851b12..71cb085 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2784,22 +2784,40 @@ static int packet_release(struct socket *sock)
  *	Attach a packet hook.
  */
 
-static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
+static int packet_do_bind(struct sock *sk, const char *name, int ifindex,
+			  __be16 proto)
 {
 	struct packet_sock *po = pkt_sk(sk);
 	struct net_device *dev_curr;
 	__be16 proto_curr;
 	bool need_rehook;
+	struct net_device *dev = NULL;
+	int ret = 0;
+	bool unlisted = false;
 
-	if (po->fanout) {
-		if (dev)
-			dev_put(dev);
-
+	if (po->fanout)
 		return -EINVAL;
-	}
 
 	lock_sock(sk);
 	spin_lock(&po->bind_lock);
+	rcu_read_lock();
+
+	if (name) {
+		dev = dev_get_by_name_rcu(sock_net(sk), name);
+		if (!dev) {
+			ret = -ENODEV;
+			goto out_unlock;
+		}
+	} else if (ifindex) {
+		dev = dev_get_by_index_rcu(sock_net(sk), ifindex);
+		if (!dev) {
+			ret = -ENODEV;
+			goto out_unlock;
+		}
+	}
+
+	if (dev)
+		dev_hold(dev);
 
 	proto_curr = po->prot_hook.type;
 	dev_curr = po->prot_hook.dev;
@@ -2807,14 +2825,29 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
 	need_rehook = proto_curr != proto || dev_curr != dev;
 
 	if (need_rehook) {
-		unregister_prot_hook(sk, true);
+		if (po->running) {
+			rcu_read_unlock();
+			__unregister_prot_hook(sk, true);
+			rcu_read_lock();
+			dev_curr = po->prot_hook.dev;
+			if (dev)
+				unlisted = !dev_get_by_index_rcu(sock_net(sk),
+								 dev->ifindex);
+		}
 
 		po->num = proto;
 		po->prot_hook.type = proto;
-		po->prot_hook.dev = dev;
 
-		po->ifindex = dev ? dev->ifindex : 0;
-		packet_cached_dev_assign(po, dev);
+		if (unlikely(unlisted)) {
+			dev_put(dev);
+			po->prot_hook.dev = NULL;
+			po->ifindex = -1;
+			packet_cached_dev_reset(po);
+		} else {
+			po->prot_hook.dev = dev;
+			po->ifindex = dev ? dev->ifindex : 0;
+			packet_cached_dev_assign(po, dev);
+		}
 	}
 	if (dev_curr)
 		dev_put(dev_curr);
@@ -2822,7 +2855,7 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
 	if (proto == 0 || !need_rehook)
 		goto out_unlock;
 
-	if (!dev || (dev->flags & IFF_UP)) {
+	if (!unlisted && (!dev || (dev->flags & IFF_UP))) {
 		register_prot_hook(sk);
 	} else {
 		sk->sk_err = ENETDOWN;
@@ -2831,9 +2864,10 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
 	}
 
 out_unlock:
+	rcu_read_unlock();
 	spin_unlock(&po->bind_lock);
 	release_sock(sk);
-	return 0;
+	return ret;
 }
 
 /*
@@ -2845,8 +2879,6 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr,
 {
 	struct sock *sk = sock->sk;
 	char name[15];
-	struct net_device *dev;
-	int err = -ENODEV;
 
 	/*
 	 *	Check legality
@@ -2856,19 +2888,13 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr,
 		return -EINVAL;
 	strlcpy(name, uaddr->sa_data, sizeof(name));
 
-	dev = dev_get_by_name(sock_net(sk), name);
-	if (dev)
-		err = packet_do_bind(sk, dev, pkt_sk(sk)->num);
-	return err;
+	return packet_do_bind(sk, name, 0, pkt_sk(sk)->num);
 }
 
 static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 {
 	struct sockaddr_ll *sll = (struct sockaddr_ll *)uaddr;
 	struct sock *sk = sock->sk;
-	struct net_device *dev = NULL;
-	int err;
-
 
 	/*
 	 *	Check legality
@@ -2879,16 +2905,8 @@ static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len
 	if (sll->sll_family != AF_PACKET)
 		return -EINVAL;
 
-	if (sll->sll_ifindex) {
-		err = -ENODEV;
-		dev = dev_get_by_index(sock_net(sk), sll->sll_ifindex);
-		if (dev == NULL)
-			goto out;
-	}
-	err = packet_do_bind(sk, dev, sll->sll_protocol ? : pkt_sk(sk)->num);
-
-out:
-	return err;
+	return packet_do_bind(sk, NULL, sll->sll_ifindex,
+			      sll->sll_protocol ? : pkt_sk(sk)->num);
 }
 
 static struct proto packet_proto = {
-- 
2.4.1


From 8f06702fe50e1cbdee845c6f4acc611b0c0072af Mon Sep 17 00:00:00 2001
From: Jay Vosburgh <jay.vosburgh@canonical.com>
Date: Fri, 6 Nov 2015 17:23:23 -0800
Subject: [PATCH 28/30] bonding: fix panic on non-ARPHRD_ETHER enslave failure

[ Upstream commit 40baec225765c54eefa870530dd613bad9829bb7 ]

Since commit 7d5cd2ce529b, when bond_enslave fails on devices that
are not ARPHRD_ETHER, if needed, it resets the bonding device back to
ARPHRD_ETHER by calling ether_setup.

	Unfortunately, ether_setup clobbers dev->flags, clearing IFF_UP
if the bond device is up, leaving it in a quasi-down state without
having actually gone through dev_close.  For bonding, if any periodic
work queue items are active (miimon, arp_interval, etc), those will
remain running, as they are stopped by bond_close.  At this point, if
the bonding module is unloaded or the bond is deleted, the system will
panic when the work function is called.

	This panic is resolved by calling dev_close on the bond itself
prior to calling ether_setup.

Cc: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Fixes: 7d5cd2ce5292 ("bonding: correctly handle bonding type change on enslave failure")
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index a98dd4f..cbbb1c9 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1751,6 +1751,7 @@ err_undo_flags:
 					    slave_dev->dev_addr))
 			eth_hw_addr_random(bond_dev);
 		if (bond_dev->type != ARPHRD_ETHER) {
+			dev_close(bond_dev);
 			ether_setup(bond_dev);
 			bond_dev->flags |= IFF_MASTER;
 			bond_dev->priv_flags &= ~IFF_TX_SKB_SHARING;
-- 
2.4.1


From 05ba54fff106bc121f98f80ffec075b88a41f3dc Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 9 Nov 2015 17:51:23 -0800
Subject: [PATCH 29/30] net: fix a race in dst_release()

[ Upstream commit d69bbf88c8d0b367cf3e3a052f6daadf630ee566 ]

Only cpu seeing dst refcount going to 0 can safely
dereference dst->flags.

Otherwise an other cpu might already have freed the dst.

Fixes: 27b75c95f10d ("net: avoid RCU for NOCACHE dst")
Reported-by: Greg Thelen <gthelen@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dst.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/dst.c b/net/core/dst.c
index 002144be..cc4a086 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -287,7 +287,7 @@ void dst_release(struct dst_entry *dst)
 		if (unlikely(newrefcnt < 0))
 			net_warn_ratelimited("%s: dst:%p refcnt:%d\n",
 					     __func__, dst, newrefcnt);
-		if (unlikely(dst->flags & DST_NOCACHE) && !newrefcnt)
+		if (!newrefcnt && unlikely(dst->flags & DST_NOCACHE))
 			call_rcu(&dst->rcu_head, dst_destroy_rcu);
 	}
 }
-- 
2.4.1


From 996a2780b8c9cbe691df7c0ce7aab1cdde9dbd4c Mon Sep 17 00:00:00 2001
From: Sasha Levin <sasha.levin@oracle.com>
Date: Tue, 8 Sep 2015 10:53:40 -0400
Subject: [PATCH 30/30] RDS: verify the underlying transport exists before
 creating a connection

[ Upstream commit 74e98eb085889b0d2d4908f59f6e00026063014f ]

There was no verification that an underlying transport exists when creating
a connection, this would cause dereferencing a NULL ptr.

It might happen on sockets that weren't properly bound before attempting to
send a message, which will cause a NULL ptr deref:

[135546.047719] kasan: GPF could be caused by NULL-ptr deref or user memory accessgeneral protection fault: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC KASAN
[135546.051270] Modules linked in:
[135546.051781] CPU: 4 PID: 15650 Comm: trinity-c4 Not tainted 4.2.0-next-20150902-sasha-00041-gbaa1222-dirty #2527
[135546.053217] task: ffff8800835bc000 ti: ffff8800bc708000 task.ti: ffff8800bc708000
[135546.054291] RIP: __rds_conn_create (net/rds/connection.c:194)
[135546.055666] RSP: 0018:ffff8800bc70fab0  EFLAGS: 00010202
[135546.056457] RAX: dffffc0000000000 RBX: 0000000000000f2c RCX: ffff8800835bc000
[135546.057494] RDX: 0000000000000007 RSI: ffff8800835bccd8 RDI: 0000000000000038
[135546.058530] RBP: ffff8800bc70fb18 R08: 0000000000000001 R09: 0000000000000000
[135546.059556] R10: ffffed014d7a3a23 R11: ffffed014d7a3a21 R12: 0000000000000000
[135546.060614] R13: 0000000000000001 R14: ffff8801ec3d0000 R15: 0000000000000000
[135546.061668] FS:  00007faad4ffb700(0000) GS:ffff880252000000(0000) knlGS:0000000000000000
[135546.062836] CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[135546.063682] CR2: 000000000000846a CR3: 000000009d137000 CR4: 00000000000006a0
[135546.064723] Stack:
[135546.065048]  ffffffffafe2055c ffffffffafe23fc1 ffffed00493097bf ffff8801ec3d0008
[135546.066247]  0000000000000000 00000000000000d0 0000000000000000 ac194a24c0586342
[135546.067438]  1ffff100178e1f78 ffff880320581b00 ffff8800bc70fdd0 ffff880320581b00
[135546.068629] Call Trace:
[135546.069028] ? __rds_conn_create (include/linux/rcupdate.h:856 net/rds/connection.c:134)
[135546.069989] ? rds_message_copy_from_user (net/rds/message.c:298)
[135546.071021] rds_conn_create_outgoing (net/rds/connection.c:278)
[135546.071981] rds_sendmsg (net/rds/send.c:1058)
[135546.072858] ? perf_trace_lock (include/trace/events/lock.h:38)
[135546.073744] ? lockdep_init (kernel/locking/lockdep.c:3298)
[135546.074577] ? rds_send_drop_to (net/rds/send.c:976)
[135546.075508] ? __might_fault (./arch/x86/include/asm/current.h:14 mm/memory.c:3795)
[135546.076349] ? __might_fault (mm/memory.c:3795)
[135546.077179] ? rds_send_drop_to (net/rds/send.c:976)
[135546.078114] sock_sendmsg (net/socket.c:611 net/socket.c:620)
[135546.078856] SYSC_sendto (net/socket.c:1657)
[135546.079596] ? SYSC_connect (net/socket.c:1628)
[135546.080510] ? trace_dump_stack (kernel/trace/trace.c:1926)
[135546.081397] ? ring_buffer_unlock_commit (kernel/trace/ring_buffer.c:2479 kernel/trace/ring_buffer.c:2558 kernel/trace/ring_buffer.c:2674)
[135546.082390] ? trace_buffer_unlock_commit (kernel/trace/trace.c:1749)
[135546.083410] ? trace_event_raw_event_sys_enter (include/trace/events/syscalls.h:16)
[135546.084481] ? do_audit_syscall_entry (include/trace/events/syscalls.h:16)
[135546.085438] ? trace_buffer_unlock_commit (kernel/trace/trace.c:1749)
[135546.085515] rds_ib_laddr_check(): addr 36.74.25.172 ret -99 node type -1

Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/connection.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/rds/connection.c b/net/rds/connection.c
index da6da57..9d66705 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -187,6 +187,12 @@ new_conn:
 		}
 	}
 
+	if (trans == NULL) {
+		kmem_cache_free(rds_conn_slab, conn);
+		conn = ERR_PTR(-ENODEV);
+		goto out;
+	}
+
 	conn->c_trans = trans;
 
 	ret = trans->conn_alloc(conn, gfp);
-- 
2.4.1


[-- Attachment #4: net_41.mbox --]
[-- Type: Application/Octet-Stream, Size: 50878 bytes --]

From e8003c567592cb70fa56c5a384e2be8e6e8f3997 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Mon, 19 Oct 2015 13:16:49 +0300
Subject: [PATCH 01/22] irda: precedence bug in irlmp_seq_hb_idx()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 50010c20597d14667eff0fdb628309986f195230 ]

This is decrementing the pointer, instead of the value stored in the
pointer.  KASan detects it as an out of bounds reference.

Reported-by: "Berry Cheng 程君(成淼)" <chengmiao.cj@alibaba-inc.com>
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/irda/irlmp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/irda/irlmp.c b/net/irda/irlmp.c
index a26c401..4396459 100644
--- a/net/irda/irlmp.c
+++ b/net/irda/irlmp.c
@@ -1839,7 +1839,7 @@ static void *irlmp_seq_hb_idx(struct irlmp_iter_state *iter, loff_t *off)
 	for (element = hashbin_get_first(iter->hashbin);
 	     element != NULL;
 	     element = hashbin_get_next(iter->hashbin)) {
-		if (!off || *off-- == 0) {
+		if (!off || (*off)-- == 0) {
 			/* NB: hashbin left locked */
 			return element;
 		}
-- 
2.4.1


From 579522bc1f5bbd8b3fd059cb061f0221a71bf3f4 Mon Sep 17 00:00:00 2001
From: Jon Paul Maloy <jon.maloy@ericsson.com>
Date: Mon, 19 Oct 2015 11:33:00 -0400
Subject: [PATCH 02/22] tipc: allow non-linear first fragment buffer

[ Upstream commit 45c8b7b175ceb2d542e0fe15247377bf3bce29ec ]

The current code for message reassembly is erroneously assuming that
the the first arriving fragment buffer always is linear, and then goes
ahead resetting the fragment list of that buffer in anticipation of
more arriving fragments.

However, if the buffer already happens to be non-linear, we will
inadvertently drop the already attached fragment list, and later
on trig a BUG() in __pskb_pull_tail().

We see this happen when running fragmented TIPC multicast across UDP,
something made possible since
commit d0f91938bede ("tipc: add ip/udp media type")

We fix this by not resetting the fragment list when the buffer is non-
linear, and by initiatlizing our private fragment list tail pointer to
the tail of the existing fragment list.

Fixes: commit d0f91938bede ("tipc: add ip/udp media type")
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/msg.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index c3e96e8..e933314 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -121,7 +121,7 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf)
 {
 	struct sk_buff *head = *headbuf;
 	struct sk_buff *frag = *buf;
-	struct sk_buff *tail;
+	struct sk_buff *tail = NULL;
 	struct tipc_msg *msg;
 	u32 fragid;
 	int delta;
@@ -141,9 +141,15 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf)
 		if (unlikely(skb_unclone(frag, GFP_ATOMIC)))
 			goto err;
 		head = *headbuf = frag;
-		skb_frag_list_init(head);
-		TIPC_SKB_CB(head)->tail = NULL;
 		*buf = NULL;
+		TIPC_SKB_CB(head)->tail = NULL;
+		if (skb_is_nonlinear(head)) {
+			skb_walk_frags(head, tail) {
+				TIPC_SKB_CB(head)->tail = tail;
+			}
+		} else {
+			skb_frag_list_init(head);
+		}
 		return 0;
 	}
 
-- 
2.4.1


From a98d52f3ee1168d37accdc5ab2f2bd7cdb15406b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Thu, 22 Oct 2015 14:15:58 +0200
Subject: [PATCH 03/22] qmi_wwan: add Sierra Wireless MC74xx/EM74xx
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 0db65fcfcded76fe4f74e3ca9f4e2baf67b683ef ]

New device IDs shamelessly lifted from the vendor driver.

Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index f603f36..4e0470d 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -764,6 +764,10 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1199, 0x9056, 8)},	/* Sierra Wireless Modem */
 	{QMI_FIXED_INTF(0x1199, 0x9057, 8)},
 	{QMI_FIXED_INTF(0x1199, 0x9061, 8)},	/* Sierra Wireless Modem */
+	{QMI_FIXED_INTF(0x1199, 0x9070, 8)},	/* Sierra Wireless MC74xx/EM74xx */
+	{QMI_FIXED_INTF(0x1199, 0x9070, 10)},	/* Sierra Wireless MC74xx/EM74xx */
+	{QMI_FIXED_INTF(0x1199, 0x9071, 8)},	/* Sierra Wireless MC74xx/EM74xx */
+	{QMI_FIXED_INTF(0x1199, 0x9071, 10)},	/* Sierra Wireless MC74xx/EM74xx */
 	{QMI_FIXED_INTF(0x1bbb, 0x011e, 4)},	/* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */
 	{QMI_FIXED_INTF(0x1bbb, 0x0203, 2)},	/* Alcatel L800MA */
 	{QMI_FIXED_INTF(0x2357, 0x0201, 4)},	/* TP-LINK HSUPA Modem MA180 */
-- 
2.4.1


From 143e60985cf6b76a3a6710cd0ecc27b118807893 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Fri, 23 Oct 2015 00:57:05 -0400
Subject: [PATCH 04/22] macvtap: unbreak receiving of gro skb with frag list

[ Upstream commit f23d538bc24a83c16127c2eb82c9cf1adc2b5149 ]

We don't have fraglist support in TAP_FEATURES. This will lead
software segmentation of gro skb with frag list. Fixes by having
frag list support in TAP_FEATURES.

With this patch single session of netperf receiving were restored from
about 5Gb/s to about 12Gb/s on mlx4.

Fixes a567dd6252 ("macvtap: simplify usage of tap_features")
Cc: Vlad Yasevich <vyasevic@redhat.com>
Cc: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macvtap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 58858c5..4dba5fb 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -82,7 +82,7 @@ static const struct proto_ops macvtap_socket_ops;
 #define TUN_OFFLOADS (NETIF_F_HW_CSUM | NETIF_F_TSO_ECN | NETIF_F_TSO | \
 		      NETIF_F_TSO6 | NETIF_F_UFO)
 #define RX_OFFLOADS (NETIF_F_GRO | NETIF_F_LRO)
-#define TAP_FEATURES (NETIF_F_GSO | NETIF_F_SG)
+#define TAP_FEATURES (NETIF_F_GSO | NETIF_F_SG | NETIF_F_FRAGLIST)
 
 static struct macvlan_dev *macvtap_get_vlan_rcu(const struct net_device *dev)
 {
-- 
2.4.1


From 47848c855a8a26b84e5c2619c6aea814fe181ad9 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Thu, 22 Oct 2015 16:57:10 +0200
Subject: [PATCH 05/22] ppp: fix pppoe_dev deletion condition in
 pppoe_release()

[ Upstream commit 1acea4f6ce1b1c0941438aca75dd2e5c6b09db60 ]

We can't rely on PPPOX_ZOMBIE to decide whether to clear po->pppoe_dev.
PPPOX_ZOMBIE can be set by pppoe_disc_rcv() even when po->pppoe_dev is
NULL. So we have no guarantee that (sk->sk_state & PPPOX_ZOMBIE) implies
(po->pppoe_dev != NULL).
Since we're releasing a PPPoE socket, we want to release the pppoe_dev
if it exists and reset sk_state to PPPOX_DEAD, no matter the previous
value of sk_state. So we can just check for po->pppoe_dev and avoid any
assumption on sk->sk_state.

Fixes: 2b018d57ff18 ("pppoe: drop PPPOX_ZOMBIEs in pppoe_release")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pppoe.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index db2c3cd..ab33262 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -589,7 +589,7 @@ static int pppoe_release(struct socket *sock)
 
 	po = pppox_sk(sk);
 
-	if (sk->sk_state & (PPPOX_CONNECTED | PPPOX_BOUND | PPPOX_ZOMBIE)) {
+	if (po->pppoe_dev) {
 		dev_put(po->pppoe_dev);
 		po->pppoe_dev = NULL;
 	}
-- 
2.4.1


From b26b582760604b73b57701c29375c464e7ba8ac7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 24 Oct 2015 05:47:44 -0700
Subject: [PATCH 06/22] ipv6: gre: support SIT encapsulation

[ Upstream commit 7e3b6e7423d5f994257c1de88e06b509673fdbcf ]

gre_gso_segment() chokes if SIT frames were aggregated by GRO engine.

Fixes: 61c1db7fae21e ("ipv6: sit: add GSO/TSO support")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/gre_offload.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index 5aa46d4..5a8ee32 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -36,7 +36,8 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 				  SKB_GSO_TCP_ECN |
 				  SKB_GSO_GRE |
 				  SKB_GSO_GRE_CSUM |
-				  SKB_GSO_IPIP)))
+				  SKB_GSO_IPIP |
+				  SKB_GSO_SIT)))
 		goto out;
 
 	if (!skb->encapsulation)
-- 
2.4.1


From 7b4116dd564d2b36d145e66b9b76d88661029018 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <aduyck@mirantis.com>
Date: Tue, 27 Oct 2015 15:06:45 -0700
Subject: [PATCH 07/22] fib_trie: leaf_walk_rcu should not compute key if key
 is less than pn->key

[ Upstream commit c2229fe1430d4e1c70e36520229dd64a87802b20 ]

We were computing the child index in cases where the key value we were
looking for was actually less than the base key of the tnode.  As a result
we were getting incorrect index values that would cause us to skip over
some children.

To fix this I have added a test that will force us to use child index 0 if
the key we are looking for is less than the key of the current tnode.

Fixes: 8be33e955cb9 ("fib_trie: Fib walk rcu should take a tnode and key instead of a trie and a leaf")
Reported-by: Brian Rak <brak@gameservers.com>
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_trie.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 0ca933d..93b8029 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1547,7 +1547,7 @@ static struct key_vector *leaf_walk_rcu(struct key_vector **tn, t_key key)
 	do {
 		/* record parent and next child index */
 		pn = n;
-		cindex = key ? get_index(key, pn) : 0;
+		cindex = (key > pn->key) ? get_index(key, pn) : 0;
 
 		if (cindex >> pn->bits)
 			break;
-- 
2.4.1


From fdb3cd7c03ba7039e8c8be96fdfa847ccfc6d4fa Mon Sep 17 00:00:00 2001
From: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Date: Mon, 26 Oct 2015 12:46:37 -0400
Subject: [PATCH 08/22] RDS-TCP: Recover correctly from pskb_pull()/pksb_trim()
 failure in rds_tcp_data_recv

[ Upstream commit 8ce675ff39b9958d1c10f86cf58e357efaafc856 ]

Either of pskb_pull() or pskb_trim() may fail under low memory conditions.
If rds_tcp_data_recv() ignores such failures, the application will
receive corrupted data because the skb has not been correctly
carved to the RDS datagram size.

Avoid this by handling pskb_pull/pskb_trim failure in the same
manner as the skb_clone failure: bail out of rds_tcp_data_recv(), and
retry via the deferred call to rds_send_worker() that gets set up on
ENOMEM from rds_tcp_read_sock()

Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/tcp_recv.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c
index fbc5ef8..27a9921 100644
--- a/net/rds/tcp_recv.c
+++ b/net/rds/tcp_recv.c
@@ -214,8 +214,15 @@ static int rds_tcp_data_recv(read_descriptor_t *desc, struct sk_buff *skb,
 			}
 
 			to_copy = min(tc->t_tinc_data_rem, left);
-			pskb_pull(clone, offset);
-			pskb_trim(clone, to_copy);
+			if (!pskb_pull(clone, offset) ||
+			    pskb_trim(clone, to_copy)) {
+				pr_warn("rds_tcp_data_recv: pull/trim failed "
+					"left %zu data_rem %zu skb_len %d\n",
+					left, tc->t_tinc_data_rem, skb->len);
+				kfree_skb(clone);
+				desc->error = -ENOMEM;
+				goto out;
+			}
 			skb_queue_tail(&tinc->ti_skb_list, clone);
 
 			rdsdebug("skb %p data %p len %d off %u to_copy %zu -> "
-- 
2.4.1


From cf6bf07e8fa7f37f4e110b7a9100d0598b596add Mon Sep 17 00:00:00 2001
From: Carol L Soto <clsoto@linux.vnet.ibm.com>
Date: Tue, 27 Oct 2015 17:36:20 +0200
Subject: [PATCH 09/22] net/mlx4: Copy/set only sizeof struct mlx4_eqe bytes

[ Upstream commit c02b05011fadf8e409e41910217ca689f2fc9d91 ]

When doing memcpy/memset of EQEs, we should use sizeof struct
mlx4_eqe as the base size and not caps.eqe_size which could be bigger.

If caps.eqe_size is bigger than the struct mlx4_eqe then we corrupt
data in the master context.

When using a 64 byte stride, the memcpy copied over 63 bytes to the
slave_eq structure.  This resulted in copying over the entire eqe of
interest, including its ownership bit -- and also 31 bytes of garbage
into the next WQE in the slave EQ -- which did NOT include the ownership
bit (and therefore had no impact).

However, once the stride is increased to 128, we are overwriting the
ownership bits of *three* eqes in the slave_eq struct.  This results
in an incorrect ownership bit for those eqes, which causes the eq to
seem to be full. The issue therefore surfaced only once 128-byte EQEs
started being used in SRIOV and (overarchitectures that have 128/256
byte cache-lines such as PPC) - e.g after commit 77507aa249ae
"net/mlx4_core: Enable CQE/EQE stride support".

Fixes: 08ff32352d6f ('mlx4: 64-byte CQE/EQE support')
Signed-off-by: Carol L Soto <clsoto@linux.vnet.ibm.com>
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/cmd.c | 2 +-
 drivers/net/ethernet/mellanox/mlx4/eq.c  | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 529ef05..3756e45 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -2382,7 +2382,7 @@ int mlx4_multi_func_init(struct mlx4_dev *dev)
 			}
 		}
 
-		memset(&priv->mfunc.master.cmd_eqe, 0, dev->caps.eqe_size);
+		memset(&priv->mfunc.master.cmd_eqe, 0, sizeof(struct mlx4_eqe));
 		priv->mfunc.master.cmd_eqe.type = MLX4_EVENT_TYPE_CMD;
 		INIT_WORK(&priv->mfunc.master.comm_work,
 			  mlx4_master_comm_channel);
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index 983b1d5..337811d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -185,7 +185,7 @@ static void slave_event(struct mlx4_dev *dev, u8 slave, struct mlx4_eqe *eqe)
 		return;
 	}
 
-	memcpy(s_eqe, eqe, dev->caps.eqe_size - 1);
+	memcpy(s_eqe, eqe, sizeof(struct mlx4_eqe) - 1);
 	s_eqe->slave_id = slave;
 	/* ensure all information is written before setting the ownersip bit */
 	dma_wmb();
-- 
2.4.1


From 7b6c8453ebcd69e7ce7daf562b555953f68b5b5b Mon Sep 17 00:00:00 2001
From: Jon Paul Maloy <jon.maloy@ericsson.com>
Date: Wed, 28 Oct 2015 13:09:53 -0400
Subject: [PATCH 10/22] tipc: linearize arriving NAME_DISTR and LINK_PROTO
 buffers

[ Upstream commit 5cbb28a4bf65c7e4daa6c25b651fed8eb888c620 ]

Testing of the new UDP bearer has revealed that reception of
NAME_DISTRIBUTOR, LINK_PROTOCOL/RESET and LINK_PROTOCOL/ACTIVATE
message buffers is not prepared for the case that those may be
non-linear.

We now linearize all such buffers before they are delivered up to the
generic reception layer.

In order for the commit to apply cleanly to 'net' and 'stable', we do
the change in the function tipc_udp_recv() for now. Later, we will post
a commit to 'net-next' moving the linearization to generic code, in
tipc_named_rcv() and tipc_link_proto_rcv().

Fixes: commit d0f91938bede ("tipc: add ip/udp media type")
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/udp_media.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index 66deebc..f8dfee5 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -48,6 +48,7 @@
 #include <linux/tipc_netlink.h>
 #include "core.h"
 #include "bearer.h"
+#include "msg.h"
 
 /* IANA assigned UDP port */
 #define UDP_PORT_DEFAULT	6118
@@ -216,6 +217,10 @@ static int tipc_udp_recv(struct sock *sk, struct sk_buff *skb)
 {
 	struct udp_bearer *ub;
 	struct tipc_bearer *b;
+	int usr = msg_user(buf_msg(skb));
+
+	if ((usr == LINK_PROTOCOL) || (usr == NAME_DISTRIBUTOR))
+		skb_linearize(skb);
 
 	ub = rcu_dereference_sk_user_data(sk);
 	if (!ub) {
-- 
2.4.1


From 25543d5411d47272ddeb02445c42e1dd47b002fc Mon Sep 17 00:00:00 2001
From: Phil Reid <preid@electromag.com.au>
Date: Fri, 30 Oct 2015 16:43:55 +0800
Subject: [PATCH 11/22] stmmac: Correctly report PTP capabilities.

[ Upstream commit e6dbe1eb2db0d7a14991c06278dd3030c45fb825 ]

priv->hwts_*_en indicate if timestamping is enabled/disabled at run
time. But  priv->dma_cap.time_stamp  and priv->dma_cap.atime_stamp
indicates HW is support for PTPv1/PTPv2.

Signed-off-by: Phil Reid <preid@electromag.com.au>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index 771cda2..2e51b81 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -721,10 +721,13 @@ static int stmmac_get_ts_info(struct net_device *dev,
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
 
-	if ((priv->hwts_tx_en) && (priv->hwts_rx_en)) {
+	if ((priv->dma_cap.time_stamp || priv->dma_cap.atime_stamp)) {
 
-		info->so_timestamping = SOF_TIMESTAMPING_TX_HARDWARE |
+		info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
+					SOF_TIMESTAMPING_TX_HARDWARE |
+					SOF_TIMESTAMPING_RX_SOFTWARE |
 					SOF_TIMESTAMPING_RX_HARDWARE |
+					SOF_TIMESTAMPING_SOFTWARE |
 					SOF_TIMESTAMPING_RAW_HARDWARE;
 
 		if (priv->ptp_clock)
-- 
2.4.1


From c5d0de5264e2423df02e64d9ada00066b80564e8 Mon Sep 17 00:00:00 2001
From: Ani Sinha <ani@arista.com>
Date: Fri, 30 Oct 2015 16:54:31 -0700
Subject: [PATCH 12/22] ipmr: fix possible race resulting from improper usage
 of IP_INC_STATS_BH() in preemptible context.

[ Upstream commit 44f49dd8b5a606870a1f21101522a0f9c4414784 ]

Fixes the following kernel BUG :

BUG: using __this_cpu_add() in preemptible [00000000] code: bash/2758
caller is __this_cpu_preempt_check+0x13/0x15
CPU: 0 PID: 2758 Comm: bash Tainted: P           O   3.18.19 #2
 ffffffff8170eaca ffff880110d1b788 ffffffff81482b2a 0000000000000000
 0000000000000000 ffff880110d1b7b8 ffffffff812010ae ffff880007cab800
 ffff88001a060800 ffff88013a899108 ffff880108b84240 ffff880110d1b7c8
Call Trace:
[<ffffffff81482b2a>] dump_stack+0x52/0x80
[<ffffffff812010ae>] check_preemption_disabled+0xce/0xe1
[<ffffffff812010d4>] __this_cpu_preempt_check+0x13/0x15
[<ffffffff81419d60>] ipmr_queue_xmit+0x647/0x70c
[<ffffffff8141a154>] ip_mr_forward+0x32f/0x34e
[<ffffffff8141af76>] ip_mroute_setsockopt+0xe03/0x108c
[<ffffffff810553fc>] ? get_parent_ip+0x11/0x42
[<ffffffff810e6974>] ? pollwake+0x4d/0x51
[<ffffffff81058ac0>] ? default_wake_function+0x0/0xf
[<ffffffff810553fc>] ? get_parent_ip+0x11/0x42
[<ffffffff810613d9>] ? __wake_up_common+0x45/0x77
[<ffffffff81486ea9>] ? _raw_spin_unlock_irqrestore+0x1d/0x32
[<ffffffff810618bc>] ? __wake_up_sync_key+0x4a/0x53
[<ffffffff8139a519>] ? sock_def_readable+0x71/0x75
[<ffffffff813dd226>] do_ip_setsockopt+0x9d/0xb55
[<ffffffff81429818>] ? unix_seqpacket_sendmsg+0x3f/0x41
[<ffffffff813963fe>] ? sock_sendmsg+0x6d/0x86
[<ffffffff813959d4>] ? sockfd_lookup_light+0x12/0x5d
[<ffffffff8139650a>] ? SyS_sendto+0xf3/0x11b
[<ffffffff810d5738>] ? new_sync_read+0x82/0xaa
[<ffffffff813ddd19>] compat_ip_setsockopt+0x3b/0x99
[<ffffffff813fb24a>] compat_raw_setsockopt+0x11/0x32
[<ffffffff81399052>] compat_sock_common_setsockopt+0x18/0x1f
[<ffffffff813c4d05>] compat_SyS_setsockopt+0x1a9/0x1cf
[<ffffffff813c4149>] compat_SyS_socketcall+0x180/0x1e3
[<ffffffff81488ea1>] cstar_dispatch+0x7/0x1e

Signed-off-by: Ani Sinha <ani@arista.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ipmr.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 3a2c016..df28693 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1683,8 +1683,8 @@ static inline int ipmr_forward_finish(struct sock *sk, struct sk_buff *skb)
 {
 	struct ip_options *opt = &(IPCB(skb)->opt);
 
-	IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS);
-	IP_ADD_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTOCTETS, skb->len);
+	IP_INC_STATS(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS);
+	IP_ADD_STATS(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTOCTETS, skb->len);
 
 	if (unlikely(opt->optlen))
 		ip_forward_options(skb);
@@ -1746,7 +1746,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
 		 * to blackhole.
 		 */
 
-		IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
+		IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
 		ip_rt_put(rt);
 		goto out_free;
 	}
-- 
2.4.1


From 0b38d043bf5155129cdf60c21d1bf0c8165a32dc Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Sun, 1 Nov 2015 01:34:50 +0100
Subject: [PATCH 13/22] qmi_wwan: fix entry for HP lt4112 LTE/HSPA+ Gobi 4G
 Module
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 70910791731b5956171e1bfcad707766b8e18fee ]

The lt4112 is a HP branded Huawei me906e modem. Like other Huawei
modems, it does not have a fixed interface to function mapping.
Instead it uses a Huawei specific scheme: functions are mapped by
subclass and protocol.

However, the HP vendor ID is used for modems from many different
manufacturers using different schemes, so we cannot apply a generic
vendor rule like we do for the Huawei vendor ID.

Replace the previous lt4112 entry pointing to an arbitrary interface
number with a device specific subclass + protocol match.

Reported-and-tested-by: Muri Nicanor <muri+libqmi@immerda.ch>
Tested-by: Martin Hauke <mardnh@gmx.de>
Fixes: bb2bdeb83fb1 ("qmi_wwan: Add support for HP lt4112 LTE/HSPA+ Gobi 4G Modem")
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 4e0470d..7a95383 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -539,6 +539,10 @@ static const struct usb_device_id products[] = {
 					      USB_CDC_PROTO_NONE),
 		.driver_info        = (unsigned long)&qmi_wwan_info,
 	},
+	{	/* HP lt4112 LTE/HSPA+ Gobi 4G Module (Huawei me906e) */
+		USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x581d, USB_CLASS_VENDOR_SPEC, 1, 7),
+		.driver_info = (unsigned long)&qmi_wwan_info,
+	},
 
 	/* 3. Combined interface devices matching on interface number */
 	{QMI_FIXED_INTF(0x0408, 0xea42, 4)},	/* Yota / Megafon M100-1 */
@@ -788,7 +792,6 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x413c, 0x81a4, 8)},	/* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */
 	{QMI_FIXED_INTF(0x413c, 0x81a8, 8)},	/* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card */
 	{QMI_FIXED_INTF(0x413c, 0x81a9, 8)},	/* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */
-	{QMI_FIXED_INTF(0x03f0, 0x581d, 4)},	/* HP lt4112 LTE/HSPA+ Gobi 4G Module (Huawei me906e) */
 
 	/* 4. Gobi 1000 devices */
 	{QMI_GOBI1K_DEVICE(0x05c6, 0x9212)},	/* Acer Gobi Modem Device */
-- 
2.4.1


From 11c092c2bf13ce8e6c01c35225b5cb5d76e93637 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 2 Nov 2015 17:08:19 -0800
Subject: [PATCH 14/22] sit: fix sit0 percpu double allocations

[ Upstream commit 4ece9009774596ee3df0acba65a324b7ea79387c ]

sit0 device allocates its percpu storage twice :
- One time in ipip6_tunnel_init()
- One time in ipip6_fb_tunnel_init()

Thus we leak 48 bytes per possible cpu per network namespace dismantle.

ipip6_fb_tunnel_init() can be much simpler and does not
return an error, and should be called after register_netdev()

Note that ipip6_tunnel_clone_6rd() also needs to be called
after register_netdev() (calling ipip6_tunnel_init())

Fixes: ebe084aafb7e ("sit: Use ipip6_tunnel_init as the ndo_init function.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 26 ++++----------------------
 1 file changed, 4 insertions(+), 22 deletions(-)

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index ac35a28..85c4b2f 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1394,34 +1394,20 @@ static int ipip6_tunnel_init(struct net_device *dev)
 	return 0;
 }
 
-static int __net_init ipip6_fb_tunnel_init(struct net_device *dev)
+static void __net_init ipip6_fb_tunnel_init(struct net_device *dev)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	struct iphdr *iph = &tunnel->parms.iph;
 	struct net *net = dev_net(dev);
 	struct sit_net *sitn = net_generic(net, sit_net_id);
 
-	tunnel->dev = dev;
-	tunnel->net = dev_net(dev);
-
 	iph->version		= 4;
 	iph->protocol		= IPPROTO_IPV6;
 	iph->ihl		= 5;
 	iph->ttl		= 64;
 
-	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
-	if (!dev->tstats)
-		return -ENOMEM;
-
-	tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst);
-	if (!tunnel->dst_cache) {
-		free_percpu(dev->tstats);
-		return -ENOMEM;
-	}
-
 	dev_hold(dev);
 	rcu_assign_pointer(sitn->tunnels_wc[0], tunnel);
-	return 0;
 }
 
 static int ipip6_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -1831,23 +1817,19 @@ static int __net_init sit_init_net(struct net *net)
 	 */
 	sitn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL;
 
-	err = ipip6_fb_tunnel_init(sitn->fb_tunnel_dev);
-	if (err)
-		goto err_dev_free;
-
-	ipip6_tunnel_clone_6rd(sitn->fb_tunnel_dev, sitn);
 	err = register_netdev(sitn->fb_tunnel_dev);
 	if (err)
 		goto err_reg_dev;
 
+	ipip6_tunnel_clone_6rd(sitn->fb_tunnel_dev, sitn);
+	ipip6_fb_tunnel_init(sitn->fb_tunnel_dev);
+
 	t = netdev_priv(sitn->fb_tunnel_dev);
 
 	strcpy(t->parms.name, sitn->fb_tunnel_dev->name);
 	return 0;
 
 err_reg_dev:
-	dev_put(sitn->fb_tunnel_dev);
-err_dev_free:
 	ipip6_dev_free(sitn->fb_tunnel_dev);
 err_alloc_dev:
 	return err;
-- 
2.4.1


From 62009af8f36728b1a90392ead043ddef49e00b49 Mon Sep 17 00:00:00 2001
From: Martin Habets <mhabets@solarflare.com>
Date: Mon, 2 Nov 2015 12:51:31 +0000
Subject: [PATCH 15/22] sfc: push partner queue for skb->xmit_more

[ Upstream commit b2663a4f30e85ec606b806f5135413e6d5c78d1e ]

When the IP stack passes SKBs the sfc driver puts them in 2 different TX
queues (called partners), one for checksummed and one for not checksummed.
If the SKB has xmit_more set the driver will delay pushing the work to the
NIC.

When later it does decide to push the buffers this patch ensures it also
pushes the partner queue, if that also has any delayed work. Before this
fix the work in the partner queue would be left for a long time and cause
a netdev watchdog.

Fixes: 70b33fb ("sfc: add support for skb->xmit_more")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Martin Habets <mhabets@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/ef10.c       |  4 +++-
 drivers/net/ethernet/sfc/farch.c      |  4 +++-
 drivers/net/ethernet/sfc/net_driver.h |  2 ++
 drivers/net/ethernet/sfc/tx.c         | 30 ++++++++++++++++++++++++++++--
 4 files changed, 36 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index fbb6cfa..feca46e 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -1344,7 +1344,9 @@ static void efx_ef10_tx_write(struct efx_tx_queue *tx_queue)
 	unsigned int write_ptr;
 	efx_qword_t *txd;
 
-	BUG_ON(tx_queue->write_count == tx_queue->insert_count);
+	tx_queue->xmit_more_available = false;
+	if (unlikely(tx_queue->write_count == tx_queue->insert_count))
+		return;
 
 	do {
 		write_ptr = tx_queue->write_count & tx_queue->ptr_mask;
diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c
index bb89e96..6d4e004 100644
--- a/drivers/net/ethernet/sfc/farch.c
+++ b/drivers/net/ethernet/sfc/farch.c
@@ -319,7 +319,9 @@ void efx_farch_tx_write(struct efx_tx_queue *tx_queue)
 	unsigned write_ptr;
 	unsigned old_write_count = tx_queue->write_count;
 
-	BUG_ON(tx_queue->write_count == tx_queue->insert_count);
+	tx_queue->xmit_more_available = false;
+	if (unlikely(tx_queue->write_count == tx_queue->insert_count))
+		return;
 
 	do {
 		write_ptr = tx_queue->write_count & tx_queue->ptr_mask;
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index 325dd94..0bdef4a 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -218,6 +218,7 @@ struct efx_tx_buffer {
  * @tso_packets: Number of packets via the TSO xmit path
  * @pushes: Number of times the TX push feature has been used
  * @pio_packets: Number of times the TX PIO feature has been used
+ * @xmit_more_available: Are any packets waiting to be pushed to the NIC
  * @empty_read_count: If the completion path has seen the queue as empty
  *	and the transmission path has not yet checked this, the value of
  *	@read_count bitwise-added to %EFX_EMPTY_COUNT_VALID; otherwise 0.
@@ -250,6 +251,7 @@ struct efx_tx_queue {
 	unsigned int tso_packets;
 	unsigned int pushes;
 	unsigned int pio_packets;
+	bool xmit_more_available;
 	/* Statistics to supplement MAC stats */
 	unsigned long tx_packets;
 
diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c
index aaf2987..e70edc3 100644
--- a/drivers/net/ethernet/sfc/tx.c
+++ b/drivers/net/ethernet/sfc/tx.c
@@ -431,8 +431,20 @@ finish_packet:
 	efx_tx_maybe_stop_queue(tx_queue);
 
 	/* Pass off to hardware */
-	if (!skb->xmit_more || netif_xmit_stopped(tx_queue->core_txq))
+	if (!skb->xmit_more || netif_xmit_stopped(tx_queue->core_txq)) {
+		struct efx_tx_queue *txq2 = efx_tx_queue_partner(tx_queue);
+
+		/* There could be packets left on the partner queue if those
+		 * SKBs had skb->xmit_more set. If we do not push those they
+		 * could be left for a long time and cause a netdev watchdog.
+		 */
+		if (txq2->xmit_more_available)
+			efx_nic_push_buffers(txq2);
+
 		efx_nic_push_buffers(tx_queue);
+	} else {
+		tx_queue->xmit_more_available = skb->xmit_more;
+	}
 
 	tx_queue->tx_packets++;
 
@@ -721,6 +733,7 @@ void efx_init_tx_queue(struct efx_tx_queue *tx_queue)
 	tx_queue->read_count = 0;
 	tx_queue->old_read_count = 0;
 	tx_queue->empty_read_count = 0 | EFX_EMPTY_COUNT_VALID;
+	tx_queue->xmit_more_available = false;
 
 	/* Set up TX descriptor ring */
 	efx_nic_init_tx(tx_queue);
@@ -746,6 +759,7 @@ void efx_fini_tx_queue(struct efx_tx_queue *tx_queue)
 
 		++tx_queue->read_count;
 	}
+	tx_queue->xmit_more_available = false;
 	netdev_tx_reset_queue(tx_queue->core_txq);
 }
 
@@ -1301,8 +1315,20 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue,
 	efx_tx_maybe_stop_queue(tx_queue);
 
 	/* Pass off to hardware */
-	if (!skb->xmit_more || netif_xmit_stopped(tx_queue->core_txq))
+	if (!skb->xmit_more || netif_xmit_stopped(tx_queue->core_txq)) {
+		struct efx_tx_queue *txq2 = efx_tx_queue_partner(tx_queue);
+
+		/* There could be packets left on the partner queue if those
+		 * SKBs had skb->xmit_more set. If we do not push those they
+		 * could be left for a long time and cause a netdev watchdog.
+		 */
+		if (txq2->xmit_more_available)
+			efx_nic_push_buffers(txq2);
+
 		efx_nic_push_buffers(tx_queue);
+	} else {
+		tx_queue->xmit_more_available = skb->xmit_more;
+	}
 
 	tx_queue->tso_bursts++;
 	return NETDEV_TX_OK;
-- 
2.4.1


From 424d45bf9efe356732528dee1edf485983714f2a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 2 Nov 2015 07:50:07 -0800
Subject: [PATCH 16/22] net: avoid NULL deref in inet_ctl_sock_destroy()

[ Upstream commit 8fa677d2706d325d71dab91bf6e6512c05214e37 ]

Under low memory conditions, tcp_sk_init() and icmp_sk_init()
can both iterate on all possible cpus and call inet_ctl_sock_destroy(),
with eventual NULL pointer.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_common.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/net/inet_common.h b/include/net/inet_common.h
index 4a92423..82669da 100644
--- a/include/net/inet_common.h
+++ b/include/net/inet_common.h
@@ -41,7 +41,8 @@ int inet_recv_error(struct sock *sk, struct msghdr *msg, int len,
 
 static inline void inet_ctl_sock_destroy(struct sock *sk)
 {
-	sk_release_kernel(sk);
+	if (sk)
+		sk_release_kernel(sk);
 }
 
 #endif
-- 
2.4.1


From 7c114178cbc084b61a723f84e9fae14779be1ecd Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Wed, 4 Nov 2015 14:47:53 +0100
Subject: [PATCH 17/22] ipv6: clean up dev_snmp6 proc entry when we fail to
 initialize inet6_dev

[ Upstream commit 2a189f9e57650e9f310ddf4aad75d66c1233a064 ]

In ipv6_add_dev, when addrconf_sysctl_register fails, we do not clean up
the dev_snmp6 entry that we have already registered for this device.
Call snmp6_unregister_dev in this case.

Fixes: a317a2f19da7d ("ipv6: fail early when creating netdev named all or default")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 37b70e8..fd3aa61 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -411,6 +411,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
 	if (err) {
 		ipv6_mc_destroy_dev(ndev);
 		del_timer(&ndev->regen_timer);
+		snmp6_unregister_dev(ndev);
 		goto err_release;
 	}
 	/* protected by rtnl_lock */
-- 
2.4.1


From cd3269621fed898f14989389367690b86fd78f1e Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Tue, 3 Nov 2015 14:32:57 -0800
Subject: [PATCH 18/22] ipv4: disable BH when changing ip local port range

[ Upstream commit 4ee3bd4a8c7463cdef0b82ebc33fc94a9170a7e0 ]

This fixes the following lockdep warning:

 [ INFO: inconsistent lock state ]
 4.3.0-rc7+ #1197 Not tainted
 ---------------------------------
 inconsistent {IN-SOFTIRQ-R} -> {SOFTIRQ-ON-W} usage.
 sysctl/1019 [HC0[0]:SC0[0]:HE1:SE1] takes:
  (&(&net->ipv4.ip_local_ports.lock)->seqcount){+.+-..}, at: [<ffffffff81921de7>] ipv4_local_port_range+0xb4/0x12a
 {IN-SOFTIRQ-R} state was registered at:
   [<ffffffff810bd682>] __lock_acquire+0x2f6/0xdf0
   [<ffffffff810be6d5>] lock_acquire+0x11c/0x1a4
   [<ffffffff818e599c>] inet_get_local_port_range+0x4e/0xae
   [<ffffffff8166e8e3>] udp_flow_src_port.constprop.40+0x23/0x116
   [<ffffffff81671cb9>] vxlan_xmit_one+0x219/0xa6a
   [<ffffffff81672f75>] vxlan_xmit+0xa6b/0xaa5
   [<ffffffff817f2deb>] dev_hard_start_xmit+0x2ae/0x465
   [<ffffffff817f35ed>] __dev_queue_xmit+0x531/0x633
   [<ffffffff817f3702>] dev_queue_xmit_sk+0x13/0x15
   [<ffffffff818004a5>] neigh_resolve_output+0x12f/0x14d
   [<ffffffff81959cfa>] ip6_finish_output2+0x344/0x39f
   [<ffffffff8195bf58>] ip6_finish_output+0x88/0x8e
   [<ffffffff8195bfef>] ip6_output+0x91/0xe5
   [<ffffffff819792ae>] dst_output_sk+0x47/0x4c
   [<ffffffff81979392>] NF_HOOK_THRESH.constprop.30+0x38/0x82
   [<ffffffff8197981e>] mld_sendpack+0x189/0x266
   [<ffffffff8197b28b>] mld_ifc_timer_expire+0x1ef/0x223
   [<ffffffff810de581>] call_timer_fn+0xfb/0x28c
   [<ffffffff810ded1e>] run_timer_softirq+0x1c7/0x1f1

Fixes: b8f1a55639e6 ("udp: Add function to make source port for UDP tunnels")
Cc: Tom Herbert <tom@herbertland.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/sysctl_net_ipv4.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index c3852a7..f0e8297 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -45,10 +45,10 @@ static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
 /* Update system visible IP port range */
 static void set_local_port_range(struct net *net, int range[2])
 {
-	write_seqlock(&net->ipv4.ip_local_ports.lock);
+	write_seqlock_bh(&net->ipv4.ip_local_ports.lock);
 	net->ipv4.ip_local_ports.range[0] = range[0];
 	net->ipv4.ip_local_ports.range[1] = range[1];
-	write_sequnlock(&net->ipv4.ip_local_ports.lock);
+	write_sequnlock_bh(&net->ipv4.ip_local_ports.lock);
 }
 
 /* Validate changes from /proc interface. */
-- 
2.4.1


From 75c6770b2f0798d2fafb324fe2c01c8f9f6befe0 Mon Sep 17 00:00:00 2001
From: Francesco Ruggeri <fruggeri@aristanetworks.com>
Date: Thu, 5 Nov 2015 08:16:14 -0800
Subject: [PATCH 19/22] packet: race condition in packet_bind

[ Upstream commit 30f7ea1c2b5f5fb7462c5ae44fe2e40cb2d6a474 ]

There is a race conditions between packet_notifier and packet_bind{_spkt}.

It happens if packet_notifier(NETDEV_UNREGISTER) executes between the
time packet_bind{_spkt} takes a reference on the new netdevice and the
time packet_do_bind sets po->ifindex.
In this case the notification can be missed.
If this happens during a dev_change_net_namespace this can result in the
netdevice to be moved to the new namespace while the packet_sock in the
old namespace still holds a reference on it. When the netdevice is later
deleted in the new namespace the deletion hangs since the packet_sock
is not found in the new namespace' &net->packet.sklist.
It can be reproduced with the script below.

This patch makes packet_do_bind check again for the presence of the
netdevice in the packet_sock's namespace after the synchronize_net
in unregister_prot_hook.
More in general it also uses the rcu lock for the duration of the bind
to stop dev_change_net_namespace/rollback_registered_many from
going past the synchronize_net following unlist_netdevice, so that
no NETDEV_UNREGISTER notifications can happen on the new netdevice
while the bind is executing. In order to do this some code from
packet_bind{_spkt} is consolidated into packet_do_dev.

import socket, os, time, sys
proto=7
realDev='em1'
vlanId=400
if len(sys.argv) > 1:
   vlanId=int(sys.argv[1])
dev='vlan%d' % vlanId

os.system('taskset -p 0x10 %d' % os.getpid())

s = socket.socket(socket.PF_PACKET, socket.SOCK_RAW, proto)
os.system('ip link add link %s name %s type vlan id %d' %
          (realDev, dev, vlanId))
os.system('ip netns add dummy')

pid=os.fork()

if pid == 0:
   # dev should be moved while packet_do_bind is in synchronize net
   os.system('taskset -p 0x20000 %d' % os.getpid())
   os.system('ip link set %s netns dummy' % dev)
   os.system('ip netns exec dummy ip link del %s' % dev)
   s.close()
   sys.exit(0)

time.sleep(.004)
try:
   s.bind(('%s' % dev, proto+1))
except:
   print 'Could not bind socket'
   s.close()
   os.system('ip netns del dummy')
   sys.exit(0)

os.waitpid(pid, 0)
s.close()
os.system('ip netns del dummy')
sys.exit(0)

Signed-off-by: Francesco Ruggeri <fruggeri@arista.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 80 +++++++++++++++++++++++++++++++-------------------
 1 file changed, 49 insertions(+), 31 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index e1ea5d4..686e601 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2686,22 +2686,40 @@ static int packet_release(struct socket *sock)
  *	Attach a packet hook.
  */
 
-static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
+static int packet_do_bind(struct sock *sk, const char *name, int ifindex,
+			  __be16 proto)
 {
 	struct packet_sock *po = pkt_sk(sk);
 	struct net_device *dev_curr;
 	__be16 proto_curr;
 	bool need_rehook;
+	struct net_device *dev = NULL;
+	int ret = 0;
+	bool unlisted = false;
 
-	if (po->fanout) {
-		if (dev)
-			dev_put(dev);
-
+	if (po->fanout)
 		return -EINVAL;
-	}
 
 	lock_sock(sk);
 	spin_lock(&po->bind_lock);
+	rcu_read_lock();
+
+	if (name) {
+		dev = dev_get_by_name_rcu(sock_net(sk), name);
+		if (!dev) {
+			ret = -ENODEV;
+			goto out_unlock;
+		}
+	} else if (ifindex) {
+		dev = dev_get_by_index_rcu(sock_net(sk), ifindex);
+		if (!dev) {
+			ret = -ENODEV;
+			goto out_unlock;
+		}
+	}
+
+	if (dev)
+		dev_hold(dev);
 
 	proto_curr = po->prot_hook.type;
 	dev_curr = po->prot_hook.dev;
@@ -2709,14 +2727,29 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
 	need_rehook = proto_curr != proto || dev_curr != dev;
 
 	if (need_rehook) {
-		unregister_prot_hook(sk, true);
+		if (po->running) {
+			rcu_read_unlock();
+			__unregister_prot_hook(sk, true);
+			rcu_read_lock();
+			dev_curr = po->prot_hook.dev;
+			if (dev)
+				unlisted = !dev_get_by_index_rcu(sock_net(sk),
+								 dev->ifindex);
+		}
 
 		po->num = proto;
 		po->prot_hook.type = proto;
-		po->prot_hook.dev = dev;
 
-		po->ifindex = dev ? dev->ifindex : 0;
-		packet_cached_dev_assign(po, dev);
+		if (unlikely(unlisted)) {
+			dev_put(dev);
+			po->prot_hook.dev = NULL;
+			po->ifindex = -1;
+			packet_cached_dev_reset(po);
+		} else {
+			po->prot_hook.dev = dev;
+			po->ifindex = dev ? dev->ifindex : 0;
+			packet_cached_dev_assign(po, dev);
+		}
 	}
 	if (dev_curr)
 		dev_put(dev_curr);
@@ -2724,7 +2757,7 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
 	if (proto == 0 || !need_rehook)
 		goto out_unlock;
 
-	if (!dev || (dev->flags & IFF_UP)) {
+	if (!unlisted && (!dev || (dev->flags & IFF_UP))) {
 		register_prot_hook(sk);
 	} else {
 		sk->sk_err = ENETDOWN;
@@ -2733,9 +2766,10 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
 	}
 
 out_unlock:
+	rcu_read_unlock();
 	spin_unlock(&po->bind_lock);
 	release_sock(sk);
-	return 0;
+	return ret;
 }
 
 /*
@@ -2747,8 +2781,6 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr,
 {
 	struct sock *sk = sock->sk;
 	char name[15];
-	struct net_device *dev;
-	int err = -ENODEV;
 
 	/*
 	 *	Check legality
@@ -2758,19 +2790,13 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr,
 		return -EINVAL;
 	strlcpy(name, uaddr->sa_data, sizeof(name));
 
-	dev = dev_get_by_name(sock_net(sk), name);
-	if (dev)
-		err = packet_do_bind(sk, dev, pkt_sk(sk)->num);
-	return err;
+	return packet_do_bind(sk, name, 0, pkt_sk(sk)->num);
 }
 
 static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 {
 	struct sockaddr_ll *sll = (struct sockaddr_ll *)uaddr;
 	struct sock *sk = sock->sk;
-	struct net_device *dev = NULL;
-	int err;
-
 
 	/*
 	 *	Check legality
@@ -2781,16 +2807,8 @@ static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len
 	if (sll->sll_family != AF_PACKET)
 		return -EINVAL;
 
-	if (sll->sll_ifindex) {
-		err = -ENODEV;
-		dev = dev_get_by_index(sock_net(sk), sll->sll_ifindex);
-		if (dev == NULL)
-			goto out;
-	}
-	err = packet_do_bind(sk, dev, sll->sll_protocol ? : pkt_sk(sk)->num);
-
-out:
-	return err;
+	return packet_do_bind(sk, NULL, sll->sll_ifindex,
+			      sll->sll_protocol ? : pkt_sk(sk)->num);
 }
 
 static struct proto packet_proto = {
-- 
2.4.1


From fbc9209519d50bfa591405ebe61161bde8027bc2 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 9 Nov 2015 17:51:23 -0800
Subject: [PATCH 20/22] net: fix a race in dst_release()

[ Upstream commit d69bbf88c8d0b367cf3e3a052f6daadf630ee566 ]

Only cpu seeing dst refcount going to 0 can safely
dereference dst->flags.

Otherwise an other cpu might already have freed the dst.

Fixes: 27b75c95f10d ("net: avoid RCU for NOCACHE dst")
Reported-by: Greg Thelen <gthelen@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dst.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/dst.c b/net/core/dst.c
index e956ce6..f8db403 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -285,7 +285,7 @@ void dst_release(struct dst_entry *dst)
 
 		newrefcnt = atomic_dec_return(&dst->__refcnt);
 		WARN_ON(newrefcnt < 0);
-		if (unlikely(dst->flags & DST_NOCACHE) && !newrefcnt)
+		if (!newrefcnt && unlikely(dst->flags & DST_NOCACHE))
 			call_rcu(&dst->rcu_head, dst_destroy_rcu);
 	}
 }
-- 
2.4.1


From 8ffd1e43f749b05c366c2e5ba0bb93fa2e7e17dd Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Wed, 5 Aug 2015 10:34:04 +0800
Subject: [PATCH 21/22] virtio-net: drop NETIF_F_FRAGLIST

[ Upstream commit 48900cb6af4282fa0fb6ff4d72a81aa3dadb5c39 ]

virtio declares support for NETIF_F_FRAGLIST, but assumes
that there are at most MAX_SKB_FRAGS + 2 fragments which isn't
always true with a fraglist.

A longer fraglist in the skb will make the call to skb_to_sgvec overflow
the sg array, leading to memory corruption.

Drop NETIF_F_FRAGLIST so we only get what we can handle.

Cc: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 7fbca37..237f8e5 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1756,9 +1756,9 @@ static int virtnet_probe(struct virtio_device *vdev)
 	/* Do we support "hardware" checksums? */
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_CSUM)) {
 		/* This opens up the world of extra features. */
-		dev->hw_features |= NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST;
+		dev->hw_features |= NETIF_F_HW_CSUM | NETIF_F_SG;
 		if (csum)
-			dev->features |= NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST;
+			dev->features |= NETIF_F_HW_CSUM | NETIF_F_SG;
 
 		if (virtio_has_feature(vdev, VIRTIO_NET_F_GSO)) {
 			dev->hw_features |= NETIF_F_TSO | NETIF_F_UFO
-- 
2.4.1


From 4662423179e2716f43cdeedbe2d39f80dc70bbb9 Mon Sep 17 00:00:00 2001
From: Sasha Levin <sasha.levin@oracle.com>
Date: Tue, 8 Sep 2015 10:53:40 -0400
Subject: [PATCH 22/22] RDS: verify the underlying transport exists before
 creating a connection

[ Upstream commit 74e98eb085889b0d2d4908f59f6e00026063014f ]

There was no verification that an underlying transport exists when creating
a connection, this would cause dereferencing a NULL ptr.

It might happen on sockets that weren't properly bound before attempting to
send a message, which will cause a NULL ptr deref:

[135546.047719] kasan: GPF could be caused by NULL-ptr deref or user memory accessgeneral protection fault: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC KASAN
[135546.051270] Modules linked in:
[135546.051781] CPU: 4 PID: 15650 Comm: trinity-c4 Not tainted 4.2.0-next-20150902-sasha-00041-gbaa1222-dirty #2527
[135546.053217] task: ffff8800835bc000 ti: ffff8800bc708000 task.ti: ffff8800bc708000
[135546.054291] RIP: __rds_conn_create (net/rds/connection.c:194)
[135546.055666] RSP: 0018:ffff8800bc70fab0  EFLAGS: 00010202
[135546.056457] RAX: dffffc0000000000 RBX: 0000000000000f2c RCX: ffff8800835bc000
[135546.057494] RDX: 0000000000000007 RSI: ffff8800835bccd8 RDI: 0000000000000038
[135546.058530] RBP: ffff8800bc70fb18 R08: 0000000000000001 R09: 0000000000000000
[135546.059556] R10: ffffed014d7a3a23 R11: ffffed014d7a3a21 R12: 0000000000000000
[135546.060614] R13: 0000000000000001 R14: ffff8801ec3d0000 R15: 0000000000000000
[135546.061668] FS:  00007faad4ffb700(0000) GS:ffff880252000000(0000) knlGS:0000000000000000
[135546.062836] CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[135546.063682] CR2: 000000000000846a CR3: 000000009d137000 CR4: 00000000000006a0
[135546.064723] Stack:
[135546.065048]  ffffffffafe2055c ffffffffafe23fc1 ffffed00493097bf ffff8801ec3d0008
[135546.066247]  0000000000000000 00000000000000d0 0000000000000000 ac194a24c0586342
[135546.067438]  1ffff100178e1f78 ffff880320581b00 ffff8800bc70fdd0 ffff880320581b00
[135546.068629] Call Trace:
[135546.069028] ? __rds_conn_create (include/linux/rcupdate.h:856 net/rds/connection.c:134)
[135546.069989] ? rds_message_copy_from_user (net/rds/message.c:298)
[135546.071021] rds_conn_create_outgoing (net/rds/connection.c:278)
[135546.071981] rds_sendmsg (net/rds/send.c:1058)
[135546.072858] ? perf_trace_lock (include/trace/events/lock.h:38)
[135546.073744] ? lockdep_init (kernel/locking/lockdep.c:3298)
[135546.074577] ? rds_send_drop_to (net/rds/send.c:976)
[135546.075508] ? __might_fault (./arch/x86/include/asm/current.h:14 mm/memory.c:3795)
[135546.076349] ? __might_fault (mm/memory.c:3795)
[135546.077179] ? rds_send_drop_to (net/rds/send.c:976)
[135546.078114] sock_sendmsg (net/socket.c:611 net/socket.c:620)
[135546.078856] SYSC_sendto (net/socket.c:1657)
[135546.079596] ? SYSC_connect (net/socket.c:1628)
[135546.080510] ? trace_dump_stack (kernel/trace/trace.c:1926)
[135546.081397] ? ring_buffer_unlock_commit (kernel/trace/ring_buffer.c:2479 kernel/trace/ring_buffer.c:2558 kernel/trace/ring_buffer.c:2674)
[135546.082390] ? trace_buffer_unlock_commit (kernel/trace/trace.c:1749)
[135546.083410] ? trace_event_raw_event_sys_enter (include/trace/events/syscalls.h:16)
[135546.084481] ? do_audit_syscall_entry (include/trace/events/syscalls.h:16)
[135546.085438] ? trace_buffer_unlock_commit (kernel/trace/trace.c:1749)
[135546.085515] rds_ib_laddr_check(): addr 36.74.25.172 ret -99 node type -1

Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/connection.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/rds/connection.c b/net/rds/connection.c
index da6da57..9d66705 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -187,6 +187,12 @@ new_conn:
 		}
 	}
 
+	if (trans == NULL) {
+		kmem_cache_free(rds_conn_slab, conn);
+		conn = ERR_PTR(-ENODEV);
+		goto out;
+	}
+
 	conn->c_trans = trans;
 
 	ret = trans->conn_alloc(conn, gfp);
-- 
2.4.1


[-- Attachment #5: net_318.mbox --]
[-- Type: Application/Octet-Stream, Size: 45587 bytes --]

From 59f48b97a3c0d41f603167a149d96e2d39d8b8cc Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Mon, 19 Oct 2015 13:16:49 +0300
Subject: [PATCH 01/19] irda: precedence bug in irlmp_seq_hb_idx()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 50010c20597d14667eff0fdb628309986f195230 ]

This is decrementing the pointer, instead of the value stored in the
pointer.  KASan detects it as an out of bounds reference.

Reported-by: "Berry Cheng 程君(成淼)" <chengmiao.cj@alibaba-inc.com>
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/irda/irlmp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/irda/irlmp.c b/net/irda/irlmp.c
index a5f28d4..c3a939d7 100644
--- a/net/irda/irlmp.c
+++ b/net/irda/irlmp.c
@@ -1877,7 +1877,7 @@ static void *irlmp_seq_hb_idx(struct irlmp_iter_state *iter, loff_t *off)
 	for (element = hashbin_get_first(iter->hashbin);
 	     element != NULL;
 	     element = hashbin_get_next(iter->hashbin)) {
-		if (!off || *off-- == 0) {
+		if (!off || (*off)-- == 0) {
 			/* NB: hashbin left locked */
 			return element;
 		}
-- 
2.4.1


From a5d898a41607194c9d459e0b0972832292a906f6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Thu, 22 Oct 2015 14:15:58 +0200
Subject: [PATCH 02/19] qmi_wwan: add Sierra Wireless MC74xx/EM74xx
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 0db65fcfcded76fe4f74e3ca9f4e2baf67b683ef ]

New device IDs shamelessly lifted from the vendor driver.

Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index b8a82b8..f5a0e10 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -760,6 +760,10 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1199, 0x9056, 8)},	/* Sierra Wireless Modem */
 	{QMI_FIXED_INTF(0x1199, 0x9057, 8)},
 	{QMI_FIXED_INTF(0x1199, 0x9061, 8)},	/* Sierra Wireless Modem */
+	{QMI_FIXED_INTF(0x1199, 0x9070, 8)},	/* Sierra Wireless MC74xx/EM74xx */
+	{QMI_FIXED_INTF(0x1199, 0x9070, 10)},	/* Sierra Wireless MC74xx/EM74xx */
+	{QMI_FIXED_INTF(0x1199, 0x9071, 8)},	/* Sierra Wireless MC74xx/EM74xx */
+	{QMI_FIXED_INTF(0x1199, 0x9071, 10)},	/* Sierra Wireless MC74xx/EM74xx */
 	{QMI_FIXED_INTF(0x1bbb, 0x011e, 4)},	/* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */
 	{QMI_FIXED_INTF(0x1bbb, 0x0203, 2)},	/* Alcatel L800MA */
 	{QMI_FIXED_INTF(0x2357, 0x0201, 4)},	/* TP-LINK HSUPA Modem MA180 */
-- 
2.4.1


From cb399f9f796167bddb108e1329fc22d04b575ece Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Fri, 23 Oct 2015 00:57:05 -0400
Subject: [PATCH 03/19] macvtap: unbreak receiving of gro skb with frag list

[ Upstream commit f23d538bc24a83c16127c2eb82c9cf1adc2b5149 ]

We don't have fraglist support in TAP_FEATURES. This will lead
software segmentation of gro skb with frag list. Fixes by having
frag list support in TAP_FEATURES.

With this patch single session of netperf receiving were restored from
about 5Gb/s to about 12Gb/s on mlx4.

Fixes a567dd6252 ("macvtap: simplify usage of tap_features")
Cc: Vlad Yasevich <vyasevic@redhat.com>
Cc: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macvtap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 91d0c6a..91120f0 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -68,7 +68,7 @@ static const struct proto_ops macvtap_socket_ops;
 #define TUN_OFFLOADS (NETIF_F_HW_CSUM | NETIF_F_TSO_ECN | NETIF_F_TSO | \
 		      NETIF_F_TSO6)
 #define RX_OFFLOADS (NETIF_F_GRO | NETIF_F_LRO)
-#define TAP_FEATURES (NETIF_F_GSO | NETIF_F_SG)
+#define TAP_FEATURES (NETIF_F_GSO | NETIF_F_SG | NETIF_F_FRAGLIST)
 
 static struct macvlan_dev *macvtap_get_vlan_rcu(const struct net_device *dev)
 {
-- 
2.4.1


From a5c2f93ba7a0bd24502f6b6766257a4e5424e8d6 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Thu, 22 Oct 2015 16:57:10 +0200
Subject: [PATCH 04/19] ppp: fix pppoe_dev deletion condition in
 pppoe_release()

[ Upstream commit 1acea4f6ce1b1c0941438aca75dd2e5c6b09db60 ]

We can't rely on PPPOX_ZOMBIE to decide whether to clear po->pppoe_dev.
PPPOX_ZOMBIE can be set by pppoe_disc_rcv() even when po->pppoe_dev is
NULL. So we have no guarantee that (sk->sk_state & PPPOX_ZOMBIE) implies
(po->pppoe_dev != NULL).
Since we're releasing a PPPoE socket, we want to release the pppoe_dev
if it exists and reset sk_state to PPPOX_DEAD, no matter the previous
value of sk_state. So we can just check for po->pppoe_dev and avoid any
assumption on sk->sk_state.

Fixes: 2b018d57ff18 ("pppoe: drop PPPOX_ZOMBIEs in pppoe_release")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pppoe.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 6c9c16d..c4406bd 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -570,7 +570,7 @@ static int pppoe_release(struct socket *sock)
 
 	po = pppox_sk(sk);
 
-	if (sk->sk_state & (PPPOX_CONNECTED | PPPOX_BOUND | PPPOX_ZOMBIE)) {
+	if (po->pppoe_dev) {
 		dev_put(po->pppoe_dev);
 		po->pppoe_dev = NULL;
 	}
-- 
2.4.1


From 9123864cc857ab2d0780b7bf24892d36ba024fc5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 24 Oct 2015 05:47:44 -0700
Subject: [PATCH 05/19] ipv6: gre: support SIT encapsulation

[ Upstream commit 7e3b6e7423d5f994257c1de88e06b509673fdbcf ]

gre_gso_segment() chokes if SIT frames were aggregated by GRO engine.

Fixes: 61c1db7fae21e ("ipv6: sit: add GSO/TSO support")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/gre_offload.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index 51973dd..abc50b4 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -36,7 +36,8 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 				  SKB_GSO_TCP_ECN |
 				  SKB_GSO_GRE |
 				  SKB_GSO_GRE_CSUM |
-				  SKB_GSO_IPIP)))
+				  SKB_GSO_IPIP |
+				  SKB_GSO_SIT)))
 		goto out;
 
 	if (!skb->encapsulation)
-- 
2.4.1


From 1a11964c7e43b07eabe98d7484c0ad750c7c0b77 Mon Sep 17 00:00:00 2001
From: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Date: Mon, 26 Oct 2015 12:46:37 -0400
Subject: [PATCH 06/19] RDS-TCP: Recover correctly from pskb_pull()/pksb_trim()
 failure in rds_tcp_data_recv

[ Upstream commit 8ce675ff39b9958d1c10f86cf58e357efaafc856 ]

Either of pskb_pull() or pskb_trim() may fail under low memory conditions.
If rds_tcp_data_recv() ignores such failures, the application will
receive corrupted data because the skb has not been correctly
carved to the RDS datagram size.

Avoid this by handling pskb_pull/pskb_trim failure in the same
manner as the skb_clone failure: bail out of rds_tcp_data_recv(), and
retry via the deferred call to rds_send_worker() that gets set up on
ENOMEM from rds_tcp_read_sock()

Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/tcp_recv.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c
index 9ae6e0a..2dd88db 100644
--- a/net/rds/tcp_recv.c
+++ b/net/rds/tcp_recv.c
@@ -234,8 +234,15 @@ static int rds_tcp_data_recv(read_descriptor_t *desc, struct sk_buff *skb,
 			}
 
 			to_copy = min(tc->t_tinc_data_rem, left);
-			pskb_pull(clone, offset);
-			pskb_trim(clone, to_copy);
+			if (!pskb_pull(clone, offset) ||
+			    pskb_trim(clone, to_copy)) {
+				pr_warn("rds_tcp_data_recv: pull/trim failed "
+					"left %zu data_rem %zu skb_len %d\n",
+					left, tc->t_tinc_data_rem, skb->len);
+				kfree_skb(clone);
+				desc->error = -ENOMEM;
+				goto out;
+			}
 			skb_queue_tail(&tinc->ti_skb_list, clone);
 
 			rdsdebug("skb %p data %p len %d off %u to_copy %zu -> "
-- 
2.4.1


From 12eddfbbb4e1269cd3b8a2e6ef9bf1eb4ce977ce Mon Sep 17 00:00:00 2001
From: Carol L Soto <clsoto@linux.vnet.ibm.com>
Date: Tue, 27 Oct 2015 17:36:20 +0200
Subject: [PATCH 07/19] net/mlx4: Copy/set only sizeof struct mlx4_eqe bytes

[ Upstream commit c02b05011fadf8e409e41910217ca689f2fc9d91 ]

When doing memcpy/memset of EQEs, we should use sizeof struct
mlx4_eqe as the base size and not caps.eqe_size which could be bigger.

If caps.eqe_size is bigger than the struct mlx4_eqe then we corrupt
data in the master context.

When using a 64 byte stride, the memcpy copied over 63 bytes to the
slave_eq structure.  This resulted in copying over the entire eqe of
interest, including its ownership bit -- and also 31 bytes of garbage
into the next WQE in the slave EQ -- which did NOT include the ownership
bit (and therefore had no impact).

However, once the stride is increased to 128, we are overwriting the
ownership bits of *three* eqes in the slave_eq struct.  This results
in an incorrect ownership bit for those eqes, which causes the eq to
seem to be full. The issue therefore surfaced only once 128-byte EQEs
started being used in SRIOV and (overarchitectures that have 128/256
byte cache-lines such as PPC) - e.g after commit 77507aa249ae
"net/mlx4_core: Enable CQE/EQE stride support".

Fixes: 08ff32352d6f ('mlx4: 64-byte CQE/EQE support')
Signed-off-by: Carol L Soto <clsoto@linux.vnet.ibm.com>
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/cmd.c | 2 +-
 drivers/net/ethernet/mellanox/mlx4/eq.c  | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 61ebb03..2a6b149 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -2047,7 +2047,7 @@ int mlx4_multi_func_init(struct mlx4_dev *dev)
 			spin_lock_init(&s_state->lock);
 		}
 
-		memset(&priv->mfunc.master.cmd_eqe, 0, dev->caps.eqe_size);
+		memset(&priv->mfunc.master.cmd_eqe, 0, sizeof(struct mlx4_eqe));
 		priv->mfunc.master.cmd_eqe.type = MLX4_EVENT_TYPE_CMD;
 		INIT_WORK(&priv->mfunc.master.comm_work,
 			  mlx4_master_comm_channel);
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index af67e7d..11ef2c2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -185,7 +185,7 @@ static void slave_event(struct mlx4_dev *dev, u8 slave, struct mlx4_eqe *eqe)
 		return;
 	}
 
-	memcpy(s_eqe, eqe, dev->caps.eqe_size - 1);
+	memcpy(s_eqe, eqe, sizeof(struct mlx4_eqe) - 1);
 	s_eqe->slave_id = slave;
 	/* ensure all information is written before setting the ownersip bit */
 	wmb();
-- 
2.4.1


From b4739e303288c1f2db35d20570feb7b8882432e8 Mon Sep 17 00:00:00 2001
From: Phil Reid <preid@electromag.com.au>
Date: Fri, 30 Oct 2015 16:43:55 +0800
Subject: [PATCH 08/19] stmmac: Correctly report PTP capabilities.

[ Upstream commit e6dbe1eb2db0d7a14991c06278dd3030c45fb825 ]

priv->hwts_*_en indicate if timestamping is enabled/disabled at run
time. But  priv->dma_cap.time_stamp  and priv->dma_cap.atime_stamp
indicates HW is support for PTPv1/PTPv2.

Signed-off-by: Phil Reid <preid@electromag.com.au>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index 3a08a1f..11edb2c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -721,10 +721,13 @@ static int stmmac_get_ts_info(struct net_device *dev,
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
 
-	if ((priv->hwts_tx_en) && (priv->hwts_rx_en)) {
+	if ((priv->dma_cap.time_stamp || priv->dma_cap.atime_stamp)) {
 
-		info->so_timestamping = SOF_TIMESTAMPING_TX_HARDWARE |
+		info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
+					SOF_TIMESTAMPING_TX_HARDWARE |
+					SOF_TIMESTAMPING_RX_SOFTWARE |
 					SOF_TIMESTAMPING_RX_HARDWARE |
+					SOF_TIMESTAMPING_SOFTWARE |
 					SOF_TIMESTAMPING_RAW_HARDWARE;
 
 		if (priv->ptp_clock)
-- 
2.4.1


From 203df1bf66a366c15e8ee7bd3b5d5e35a60ae8a6 Mon Sep 17 00:00:00 2001
From: Ani Sinha <ani@arista.com>
Date: Fri, 30 Oct 2015 16:54:31 -0700
Subject: [PATCH 09/19] ipmr: fix possible race resulting from improper usage
 of IP_INC_STATS_BH() in preemptible context.

[ Upstream commit 44f49dd8b5a606870a1f21101522a0f9c4414784 ]

Fixes the following kernel BUG :

BUG: using __this_cpu_add() in preemptible [00000000] code: bash/2758
caller is __this_cpu_preempt_check+0x13/0x15
CPU: 0 PID: 2758 Comm: bash Tainted: P           O   3.18.19 #2
 ffffffff8170eaca ffff880110d1b788 ffffffff81482b2a 0000000000000000
 0000000000000000 ffff880110d1b7b8 ffffffff812010ae ffff880007cab800
 ffff88001a060800 ffff88013a899108 ffff880108b84240 ffff880110d1b7c8
Call Trace:
[<ffffffff81482b2a>] dump_stack+0x52/0x80
[<ffffffff812010ae>] check_preemption_disabled+0xce/0xe1
[<ffffffff812010d4>] __this_cpu_preempt_check+0x13/0x15
[<ffffffff81419d60>] ipmr_queue_xmit+0x647/0x70c
[<ffffffff8141a154>] ip_mr_forward+0x32f/0x34e
[<ffffffff8141af76>] ip_mroute_setsockopt+0xe03/0x108c
[<ffffffff810553fc>] ? get_parent_ip+0x11/0x42
[<ffffffff810e6974>] ? pollwake+0x4d/0x51
[<ffffffff81058ac0>] ? default_wake_function+0x0/0xf
[<ffffffff810553fc>] ? get_parent_ip+0x11/0x42
[<ffffffff810613d9>] ? __wake_up_common+0x45/0x77
[<ffffffff81486ea9>] ? _raw_spin_unlock_irqrestore+0x1d/0x32
[<ffffffff810618bc>] ? __wake_up_sync_key+0x4a/0x53
[<ffffffff8139a519>] ? sock_def_readable+0x71/0x75
[<ffffffff813dd226>] do_ip_setsockopt+0x9d/0xb55
[<ffffffff81429818>] ? unix_seqpacket_sendmsg+0x3f/0x41
[<ffffffff813963fe>] ? sock_sendmsg+0x6d/0x86
[<ffffffff813959d4>] ? sockfd_lookup_light+0x12/0x5d
[<ffffffff8139650a>] ? SyS_sendto+0xf3/0x11b
[<ffffffff810d5738>] ? new_sync_read+0x82/0xaa
[<ffffffff813ddd19>] compat_ip_setsockopt+0x3b/0x99
[<ffffffff813fb24a>] compat_raw_setsockopt+0x11/0x32
[<ffffffff81399052>] compat_sock_common_setsockopt+0x18/0x1f
[<ffffffff813c4d05>] compat_SyS_setsockopt+0x1a9/0x1cf
[<ffffffff813c4149>] compat_SyS_socketcall+0x180/0x1e3
[<ffffffff81488ea1>] cstar_dispatch+0x7/0x1e

Signed-off-by: Ani Sinha <ani@arista.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ipmr.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index c803458..a1fc97a 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1674,8 +1674,8 @@ static inline int ipmr_forward_finish(struct sk_buff *skb)
 {
 	struct ip_options *opt = &(IPCB(skb)->opt);
 
-	IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS);
-	IP_ADD_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTOCTETS, skb->len);
+	IP_INC_STATS(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS);
+	IP_ADD_STATS(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTOCTETS, skb->len);
 
 	if (unlikely(opt->optlen))
 		ip_forward_options(skb);
@@ -1737,7 +1737,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
 		 * to blackhole.
 		 */
 
-		IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
+		IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
 		ip_rt_put(rt);
 		goto out_free;
 	}
-- 
2.4.1


From a7e1f1ca2ceb427ba0c3edb9b8a69c8fb4a5ab24 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Sun, 1 Nov 2015 01:34:50 +0100
Subject: [PATCH 10/19] qmi_wwan: fix entry for HP lt4112 LTE/HSPA+ Gobi 4G
 Module
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 70910791731b5956171e1bfcad707766b8e18fee ]

The lt4112 is a HP branded Huawei me906e modem. Like other Huawei
modems, it does not have a fixed interface to function mapping.
Instead it uses a Huawei specific scheme: functions are mapped by
subclass and protocol.

However, the HP vendor ID is used for modems from many different
manufacturers using different schemes, so we cannot apply a generic
vendor rule like we do for the Huawei vendor ID.

Replace the previous lt4112 entry pointing to an arbitrary interface
number with a device specific subclass + protocol match.

Reported-and-tested-by: Muri Nicanor <muri+libqmi@immerda.ch>
Tested-by: Martin Hauke <mardnh@gmx.de>
Fixes: bb2bdeb83fb1 ("qmi_wwan: Add support for HP lt4112 LTE/HSPA+ Gobi 4G Modem")
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index f5a0e10..2d91050 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -535,6 +535,10 @@ static const struct usb_device_id products[] = {
 					      USB_CDC_PROTO_NONE),
 		.driver_info        = (unsigned long)&qmi_wwan_info,
 	},
+	{	/* HP lt4112 LTE/HSPA+ Gobi 4G Module (Huawei me906e) */
+		USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x581d, USB_CLASS_VENDOR_SPEC, 1, 7),
+		.driver_info = (unsigned long)&qmi_wwan_info,
+	},
 
 	/* 3. Combined interface devices matching on interface number */
 	{QMI_FIXED_INTF(0x0408, 0xea42, 4)},	/* Yota / Megafon M100-1 */
@@ -784,7 +788,6 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x413c, 0x81a4, 8)},	/* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */
 	{QMI_FIXED_INTF(0x413c, 0x81a8, 8)},	/* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card */
 	{QMI_FIXED_INTF(0x413c, 0x81a9, 8)},	/* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */
-	{QMI_FIXED_INTF(0x03f0, 0x581d, 4)},	/* HP lt4112 LTE/HSPA+ Gobi 4G Module (Huawei me906e) */
 
 	/* 4. Gobi 1000 devices */
 	{QMI_GOBI1K_DEVICE(0x05c6, 0x9212)},	/* Acer Gobi Modem Device */
-- 
2.4.1


From 6ff4f988a6122d0f7cb4cf8463c03a2e4b8dc9fb Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 2 Nov 2015 17:08:19 -0800
Subject: [PATCH 11/19] sit: fix sit0 percpu double allocations

[ Upstream commit 4ece9009774596ee3df0acba65a324b7ea79387c ]

sit0 device allocates its percpu storage twice :
- One time in ipip6_tunnel_init()
- One time in ipip6_fb_tunnel_init()

Thus we leak 48 bytes per possible cpu per network namespace dismantle.

ipip6_fb_tunnel_init() can be much simpler and does not
return an error, and should be called after register_netdev()

Note that ipip6_tunnel_clone_6rd() also needs to be called
after register_netdev() (calling ipip6_tunnel_init())

Fixes: ebe084aafb7e ("sit: Use ipip6_tunnel_init as the ndo_init function.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 25 ++++---------------------
 1 file changed, 4 insertions(+), 21 deletions(-)

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index a24557a..2cbfad9 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1394,34 +1394,20 @@ static int ipip6_tunnel_init(struct net_device *dev)
 	return 0;
 }
 
-static int __net_init ipip6_fb_tunnel_init(struct net_device *dev)
+static void __net_init ipip6_fb_tunnel_init(struct net_device *dev)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	struct iphdr *iph = &tunnel->parms.iph;
 	struct net *net = dev_net(dev);
 	struct sit_net *sitn = net_generic(net, sit_net_id);
 
-	tunnel->dev = dev;
-	tunnel->net = dev_net(dev);
-
 	iph->version		= 4;
 	iph->protocol		= IPPROTO_IPV6;
 	iph->ihl		= 5;
 	iph->ttl		= 64;
 
-	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
-	if (!dev->tstats)
-		return -ENOMEM;
-
-	tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst);
-	if (!tunnel->dst_cache) {
-		free_percpu(dev->tstats);
-		return -ENOMEM;
-	}
-
 	dev_hold(dev);
 	rcu_assign_pointer(sitn->tunnels_wc[0], tunnel);
-	return 0;
 }
 
 static int ipip6_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -1831,23 +1817,20 @@ static int __net_init sit_init_net(struct net *net)
 	 */
 	sitn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL;
 
-	err = ipip6_fb_tunnel_init(sitn->fb_tunnel_dev);
-	if (err)
-		goto err_dev_free;
-
 	ipip6_tunnel_clone_6rd(sitn->fb_tunnel_dev, sitn);
 
 	if ((err = register_netdev(sitn->fb_tunnel_dev)))
 		goto err_reg_dev;
 
+	ipip6_tunnel_clone_6rd(sitn->fb_tunnel_dev, sitn);
+	ipip6_fb_tunnel_init(sitn->fb_tunnel_dev);
+
 	t = netdev_priv(sitn->fb_tunnel_dev);
 
 	strcpy(t->parms.name, sitn->fb_tunnel_dev->name);
 	return 0;
 
 err_reg_dev:
-	dev_put(sitn->fb_tunnel_dev);
-err_dev_free:
 	ipip6_dev_free(sitn->fb_tunnel_dev);
 err_alloc_dev:
 	return err;
-- 
2.4.1


From 6cc8f0df78e1c91a5785d267e2cbfe16ef7613d3 Mon Sep 17 00:00:00 2001
From: Martin Habets <mhabets@solarflare.com>
Date: Mon, 2 Nov 2015 12:51:31 +0000
Subject: [PATCH 12/19] sfc: push partner queue for skb->xmit_more

[ Upstream commit b2663a4f30e85ec606b806f5135413e6d5c78d1e ]

When the IP stack passes SKBs the sfc driver puts them in 2 different TX
queues (called partners), one for checksummed and one for not checksummed.
If the SKB has xmit_more set the driver will delay pushing the work to the
NIC.

When later it does decide to push the buffers this patch ensures it also
pushes the partner queue, if that also has any delayed work. Before this
fix the work in the partner queue would be left for a long time and cause
a netdev watchdog.

Fixes: 70b33fb ("sfc: add support for skb->xmit_more")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Martin Habets <mhabets@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/ef10.c       |  4 +++-
 drivers/net/ethernet/sfc/farch.c      |  4 +++-
 drivers/net/ethernet/sfc/net_driver.h |  2 ++
 drivers/net/ethernet/sfc/tx.c         | 30 ++++++++++++++++++++++++++++--
 4 files changed, 36 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index a77f05c..63ec209 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -1344,7 +1344,9 @@ static void efx_ef10_tx_write(struct efx_tx_queue *tx_queue)
 	unsigned int write_ptr;
 	efx_qword_t *txd;
 
-	BUG_ON(tx_queue->write_count == tx_queue->insert_count);
+	tx_queue->xmit_more_available = false;
+	if (unlikely(tx_queue->write_count == tx_queue->insert_count))
+		return;
 
 	do {
 		write_ptr = tx_queue->write_count & tx_queue->ptr_mask;
diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c
index 6859437..b70b865 100644
--- a/drivers/net/ethernet/sfc/farch.c
+++ b/drivers/net/ethernet/sfc/farch.c
@@ -316,7 +316,9 @@ void efx_farch_tx_write(struct efx_tx_queue *tx_queue)
 	unsigned write_ptr;
 	unsigned old_write_count = tx_queue->write_count;
 
-	BUG_ON(tx_queue->write_count == tx_queue->insert_count);
+	tx_queue->xmit_more_available = false;
+	if (unlikely(tx_queue->write_count == tx_queue->insert_count))
+		return;
 
 	do {
 		write_ptr = tx_queue->write_count & tx_queue->ptr_mask;
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index 9ede320..eda39c8 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -218,6 +218,7 @@ struct efx_tx_buffer {
  * @tso_packets: Number of packets via the TSO xmit path
  * @pushes: Number of times the TX push feature has been used
  * @pio_packets: Number of times the TX PIO feature has been used
+ * @xmit_more_available: Are any packets waiting to be pushed to the NIC
  * @empty_read_count: If the completion path has seen the queue as empty
  *	and the transmission path has not yet checked this, the value of
  *	@read_count bitwise-added to %EFX_EMPTY_COUNT_VALID; otherwise 0.
@@ -250,6 +251,7 @@ struct efx_tx_queue {
 	unsigned int tso_packets;
 	unsigned int pushes;
 	unsigned int pio_packets;
+	bool xmit_more_available;
 	/* Statistics to supplement MAC stats */
 	unsigned long tx_packets;
 
diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c
index aaf2987..e70edc3 100644
--- a/drivers/net/ethernet/sfc/tx.c
+++ b/drivers/net/ethernet/sfc/tx.c
@@ -431,8 +431,20 @@ finish_packet:
 	efx_tx_maybe_stop_queue(tx_queue);
 
 	/* Pass off to hardware */
-	if (!skb->xmit_more || netif_xmit_stopped(tx_queue->core_txq))
+	if (!skb->xmit_more || netif_xmit_stopped(tx_queue->core_txq)) {
+		struct efx_tx_queue *txq2 = efx_tx_queue_partner(tx_queue);
+
+		/* There could be packets left on the partner queue if those
+		 * SKBs had skb->xmit_more set. If we do not push those they
+		 * could be left for a long time and cause a netdev watchdog.
+		 */
+		if (txq2->xmit_more_available)
+			efx_nic_push_buffers(txq2);
+
 		efx_nic_push_buffers(tx_queue);
+	} else {
+		tx_queue->xmit_more_available = skb->xmit_more;
+	}
 
 	tx_queue->tx_packets++;
 
@@ -721,6 +733,7 @@ void efx_init_tx_queue(struct efx_tx_queue *tx_queue)
 	tx_queue->read_count = 0;
 	tx_queue->old_read_count = 0;
 	tx_queue->empty_read_count = 0 | EFX_EMPTY_COUNT_VALID;
+	tx_queue->xmit_more_available = false;
 
 	/* Set up TX descriptor ring */
 	efx_nic_init_tx(tx_queue);
@@ -746,6 +759,7 @@ void efx_fini_tx_queue(struct efx_tx_queue *tx_queue)
 
 		++tx_queue->read_count;
 	}
+	tx_queue->xmit_more_available = false;
 	netdev_tx_reset_queue(tx_queue->core_txq);
 }
 
@@ -1301,8 +1315,20 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue,
 	efx_tx_maybe_stop_queue(tx_queue);
 
 	/* Pass off to hardware */
-	if (!skb->xmit_more || netif_xmit_stopped(tx_queue->core_txq))
+	if (!skb->xmit_more || netif_xmit_stopped(tx_queue->core_txq)) {
+		struct efx_tx_queue *txq2 = efx_tx_queue_partner(tx_queue);
+
+		/* There could be packets left on the partner queue if those
+		 * SKBs had skb->xmit_more set. If we do not push those they
+		 * could be left for a long time and cause a netdev watchdog.
+		 */
+		if (txq2->xmit_more_available)
+			efx_nic_push_buffers(txq2);
+
 		efx_nic_push_buffers(tx_queue);
+	} else {
+		tx_queue->xmit_more_available = skb->xmit_more;
+	}
 
 	tx_queue->tso_bursts++;
 	return NETDEV_TX_OK;
-- 
2.4.1


From abd719aef574ea05ad9229af96d8f6bc97161d6b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 2 Nov 2015 07:50:07 -0800
Subject: [PATCH 13/19] net: avoid NULL deref in inet_ctl_sock_destroy()

[ Upstream commit 8fa677d2706d325d71dab91bf6e6512c05214e37 ]

Under low memory conditions, tcp_sk_init() and icmp_sk_init()
can both iterate on all possible cpus and call inet_ctl_sock_destroy(),
with eventual NULL pointer.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_common.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/net/inet_common.h b/include/net/inet_common.h
index b2828a0..a7d812d 100644
--- a/include/net/inet_common.h
+++ b/include/net/inet_common.h
@@ -42,7 +42,8 @@ int inet_recv_error(struct sock *sk, struct msghdr *msg, int len,
 
 static inline void inet_ctl_sock_destroy(struct sock *sk)
 {
-	sk_release_kernel(sk);
+	if (sk)
+		sk_release_kernel(sk);
 }
 
 #endif
-- 
2.4.1


From aaef929fc9c6ca401f5b548ba29b6223890aaa4e Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Wed, 4 Nov 2015 14:47:53 +0100
Subject: [PATCH 14/19] ipv6: clean up dev_snmp6 proc entry when we fail to
 initialize inet6_dev

[ Upstream commit 2a189f9e57650e9f310ddf4aad75d66c1233a064 ]

In ipv6_add_dev, when addrconf_sysctl_register fails, we do not clean up
the dev_snmp6 entry that we have already registered for this device.
Call snmp6_unregister_dev in this case.

Fixes: a317a2f19da7d ("ipv6: fail early when creating netdev named all or default")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 17a0258..3c321c2 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -396,6 +396,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
 	if (err) {
 		ipv6_mc_destroy_dev(ndev);
 		del_timer(&ndev->regen_timer);
+		snmp6_unregister_dev(ndev);
 		goto err_release;
 	}
 	/* protected by rtnl_lock */
-- 
2.4.1


From 33f97a151d83ea6435c95030367fe57d39a6abf2 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Tue, 3 Nov 2015 14:32:57 -0800
Subject: [PATCH 15/19] ipv4: disable BH when changing ip local port range

[ Upstream commit 4ee3bd4a8c7463cdef0b82ebc33fc94a9170a7e0 ]

This fixes the following lockdep warning:

 [ INFO: inconsistent lock state ]
 4.3.0-rc7+ #1197 Not tainted
 ---------------------------------
 inconsistent {IN-SOFTIRQ-R} -> {SOFTIRQ-ON-W} usage.
 sysctl/1019 [HC0[0]:SC0[0]:HE1:SE1] takes:
  (&(&net->ipv4.ip_local_ports.lock)->seqcount){+.+-..}, at: [<ffffffff81921de7>] ipv4_local_port_range+0xb4/0x12a
 {IN-SOFTIRQ-R} state was registered at:
   [<ffffffff810bd682>] __lock_acquire+0x2f6/0xdf0
   [<ffffffff810be6d5>] lock_acquire+0x11c/0x1a4
   [<ffffffff818e599c>] inet_get_local_port_range+0x4e/0xae
   [<ffffffff8166e8e3>] udp_flow_src_port.constprop.40+0x23/0x116
   [<ffffffff81671cb9>] vxlan_xmit_one+0x219/0xa6a
   [<ffffffff81672f75>] vxlan_xmit+0xa6b/0xaa5
   [<ffffffff817f2deb>] dev_hard_start_xmit+0x2ae/0x465
   [<ffffffff817f35ed>] __dev_queue_xmit+0x531/0x633
   [<ffffffff817f3702>] dev_queue_xmit_sk+0x13/0x15
   [<ffffffff818004a5>] neigh_resolve_output+0x12f/0x14d
   [<ffffffff81959cfa>] ip6_finish_output2+0x344/0x39f
   [<ffffffff8195bf58>] ip6_finish_output+0x88/0x8e
   [<ffffffff8195bfef>] ip6_output+0x91/0xe5
   [<ffffffff819792ae>] dst_output_sk+0x47/0x4c
   [<ffffffff81979392>] NF_HOOK_THRESH.constprop.30+0x38/0x82
   [<ffffffff8197981e>] mld_sendpack+0x189/0x266
   [<ffffffff8197b28b>] mld_ifc_timer_expire+0x1ef/0x223
   [<ffffffff810de581>] call_timer_fn+0xfb/0x28c
   [<ffffffff810ded1e>] run_timer_softirq+0x1c7/0x1f1

Fixes: b8f1a55639e6 ("udp: Add function to make source port for UDP tunnels")
Cc: Tom Herbert <tom@herbertland.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/sysctl_net_ipv4.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index b3c53c8..633cd34 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -45,10 +45,10 @@ static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
 /* Update system visible IP port range */
 static void set_local_port_range(struct net *net, int range[2])
 {
-	write_seqlock(&net->ipv4.ip_local_ports.lock);
+	write_seqlock_bh(&net->ipv4.ip_local_ports.lock);
 	net->ipv4.ip_local_ports.range[0] = range[0];
 	net->ipv4.ip_local_ports.range[1] = range[1];
-	write_sequnlock(&net->ipv4.ip_local_ports.lock);
+	write_sequnlock_bh(&net->ipv4.ip_local_ports.lock);
 }
 
 /* Validate changes from /proc interface. */
-- 
2.4.1


From e4d94a0c565466da05847577ecac7e08d3098a4d Mon Sep 17 00:00:00 2001
From: Francesco Ruggeri <fruggeri@aristanetworks.com>
Date: Thu, 5 Nov 2015 08:16:14 -0800
Subject: [PATCH 16/19] packet: race condition in packet_bind

[ Upstream commit 30f7ea1c2b5f5fb7462c5ae44fe2e40cb2d6a474 ]

There is a race conditions between packet_notifier and packet_bind{_spkt}.

It happens if packet_notifier(NETDEV_UNREGISTER) executes between the
time packet_bind{_spkt} takes a reference on the new netdevice and the
time packet_do_bind sets po->ifindex.
In this case the notification can be missed.
If this happens during a dev_change_net_namespace this can result in the
netdevice to be moved to the new namespace while the packet_sock in the
old namespace still holds a reference on it. When the netdevice is later
deleted in the new namespace the deletion hangs since the packet_sock
is not found in the new namespace' &net->packet.sklist.
It can be reproduced with the script below.

This patch makes packet_do_bind check again for the presence of the
netdevice in the packet_sock's namespace after the synchronize_net
in unregister_prot_hook.
More in general it also uses the rcu lock for the duration of the bind
to stop dev_change_net_namespace/rollback_registered_many from
going past the synchronize_net following unlist_netdevice, so that
no NETDEV_UNREGISTER notifications can happen on the new netdevice
while the bind is executing. In order to do this some code from
packet_bind{_spkt} is consolidated into packet_do_dev.

import socket, os, time, sys
proto=7
realDev='em1'
vlanId=400
if len(sys.argv) > 1:
   vlanId=int(sys.argv[1])
dev='vlan%d' % vlanId

os.system('taskset -p 0x10 %d' % os.getpid())

s = socket.socket(socket.PF_PACKET, socket.SOCK_RAW, proto)
os.system('ip link add link %s name %s type vlan id %d' %
          (realDev, dev, vlanId))
os.system('ip netns add dummy')

pid=os.fork()

if pid == 0:
   # dev should be moved while packet_do_bind is in synchronize net
   os.system('taskset -p 0x20000 %d' % os.getpid())
   os.system('ip link set %s netns dummy' % dev)
   os.system('ip netns exec dummy ip link del %s' % dev)
   s.close()
   sys.exit(0)

time.sleep(.004)
try:
   s.bind(('%s' % dev, proto+1))
except:
   print 'Could not bind socket'
   s.close()
   os.system('ip netns del dummy')
   sys.exit(0)

os.waitpid(pid, 0)
s.close()
os.system('ip netns del dummy')
sys.exit(0)

Signed-off-by: Francesco Ruggeri <fruggeri@arista.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 80 +++++++++++++++++++++++++++++++-------------------
 1 file changed, 49 insertions(+), 31 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index bf60977..bd4145b 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2642,22 +2642,40 @@ static int packet_release(struct socket *sock)
  *	Attach a packet hook.
  */
 
-static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
+static int packet_do_bind(struct sock *sk, const char *name, int ifindex,
+			  __be16 proto)
 {
 	struct packet_sock *po = pkt_sk(sk);
 	struct net_device *dev_curr;
 	__be16 proto_curr;
 	bool need_rehook;
+	struct net_device *dev = NULL;
+	int ret = 0;
+	bool unlisted = false;
 
-	if (po->fanout) {
-		if (dev)
-			dev_put(dev);
-
+	if (po->fanout)
 		return -EINVAL;
-	}
 
 	lock_sock(sk);
 	spin_lock(&po->bind_lock);
+	rcu_read_lock();
+
+	if (name) {
+		dev = dev_get_by_name_rcu(sock_net(sk), name);
+		if (!dev) {
+			ret = -ENODEV;
+			goto out_unlock;
+		}
+	} else if (ifindex) {
+		dev = dev_get_by_index_rcu(sock_net(sk), ifindex);
+		if (!dev) {
+			ret = -ENODEV;
+			goto out_unlock;
+		}
+	}
+
+	if (dev)
+		dev_hold(dev);
 
 	proto_curr = po->prot_hook.type;
 	dev_curr = po->prot_hook.dev;
@@ -2665,14 +2683,29 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
 	need_rehook = proto_curr != proto || dev_curr != dev;
 
 	if (need_rehook) {
-		unregister_prot_hook(sk, true);
+		if (po->running) {
+			rcu_read_unlock();
+			__unregister_prot_hook(sk, true);
+			rcu_read_lock();
+			dev_curr = po->prot_hook.dev;
+			if (dev)
+				unlisted = !dev_get_by_index_rcu(sock_net(sk),
+								 dev->ifindex);
+		}
 
 		po->num = proto;
 		po->prot_hook.type = proto;
-		po->prot_hook.dev = dev;
 
-		po->ifindex = dev ? dev->ifindex : 0;
-		packet_cached_dev_assign(po, dev);
+		if (unlikely(unlisted)) {
+			dev_put(dev);
+			po->prot_hook.dev = NULL;
+			po->ifindex = -1;
+			packet_cached_dev_reset(po);
+		} else {
+			po->prot_hook.dev = dev;
+			po->ifindex = dev ? dev->ifindex : 0;
+			packet_cached_dev_assign(po, dev);
+		}
 	}
 	if (dev_curr)
 		dev_put(dev_curr);
@@ -2680,7 +2713,7 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
 	if (proto == 0 || !need_rehook)
 		goto out_unlock;
 
-	if (!dev || (dev->flags & IFF_UP)) {
+	if (!unlisted && (!dev || (dev->flags & IFF_UP))) {
 		register_prot_hook(sk);
 	} else {
 		sk->sk_err = ENETDOWN;
@@ -2689,9 +2722,10 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
 	}
 
 out_unlock:
+	rcu_read_unlock();
 	spin_unlock(&po->bind_lock);
 	release_sock(sk);
-	return 0;
+	return ret;
 }
 
 /*
@@ -2703,8 +2737,6 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr,
 {
 	struct sock *sk = sock->sk;
 	char name[15];
-	struct net_device *dev;
-	int err = -ENODEV;
 
 	/*
 	 *	Check legality
@@ -2714,19 +2746,13 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr,
 		return -EINVAL;
 	strlcpy(name, uaddr->sa_data, sizeof(name));
 
-	dev = dev_get_by_name(sock_net(sk), name);
-	if (dev)
-		err = packet_do_bind(sk, dev, pkt_sk(sk)->num);
-	return err;
+	return packet_do_bind(sk, name, 0, pkt_sk(sk)->num);
 }
 
 static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 {
 	struct sockaddr_ll *sll = (struct sockaddr_ll *)uaddr;
 	struct sock *sk = sock->sk;
-	struct net_device *dev = NULL;
-	int err;
-
 
 	/*
 	 *	Check legality
@@ -2737,16 +2763,8 @@ static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len
 	if (sll->sll_family != AF_PACKET)
 		return -EINVAL;
 
-	if (sll->sll_ifindex) {
-		err = -ENODEV;
-		dev = dev_get_by_index(sock_net(sk), sll->sll_ifindex);
-		if (dev == NULL)
-			goto out;
-	}
-	err = packet_do_bind(sk, dev, sll->sll_protocol ? : pkt_sk(sk)->num);
-
-out:
-	return err;
+	return packet_do_bind(sk, NULL, sll->sll_ifindex,
+			      sll->sll_protocol ? : pkt_sk(sk)->num);
 }
 
 static struct proto packet_proto = {
-- 
2.4.1


From 8c68d54a89133b51a2d18c62af7d6363701caa33 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 9 Nov 2015 17:51:23 -0800
Subject: [PATCH 17/19] net: fix a race in dst_release()

[ Upstream commit d69bbf88c8d0b367cf3e3a052f6daadf630ee566 ]

Only cpu seeing dst refcount going to 0 can safely
dereference dst->flags.

Otherwise an other cpu might already have freed the dst.

Fixes: 27b75c95f10d ("net: avoid RCU for NOCACHE dst")
Reported-by: Greg Thelen <gthelen@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dst.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/dst.c b/net/core/dst.c
index a028409..a80e923 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -285,7 +285,7 @@ void dst_release(struct dst_entry *dst)
 
 		newrefcnt = atomic_dec_return(&dst->__refcnt);
 		WARN_ON(newrefcnt < 0);
-		if (unlikely(dst->flags & DST_NOCACHE) && !newrefcnt)
+		if (!newrefcnt && unlikely(dst->flags & DST_NOCACHE))
 			call_rcu(&dst->rcu_head, dst_destroy_rcu);
 	}
 }
-- 
2.4.1


From 7a9f9c8d8b5e2821f0393b587c139d6f657ee02d Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Wed, 5 Aug 2015 10:34:04 +0800
Subject: [PATCH 18/19] virtio-net: drop NETIF_F_FRAGLIST

[ Upstream commit 48900cb6af4282fa0fb6ff4d72a81aa3dadb5c39 ]

virtio declares support for NETIF_F_FRAGLIST, but assumes
that there are at most MAX_SKB_FRAGS + 2 fragments which isn't
always true with a fraglist.

A longer fraglist in the skb will make the call to skb_to_sgvec overflow
the sg array, leading to memory corruption.

Drop NETIF_F_FRAGLIST so we only get what we can handle.

Cc: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 484ecce..ce2a299 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1746,9 +1746,9 @@ static int virtnet_probe(struct virtio_device *vdev)
 	/* Do we support "hardware" checksums? */
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_CSUM)) {
 		/* This opens up the world of extra features. */
-		dev->hw_features |= NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST;
+		dev->hw_features |= NETIF_F_HW_CSUM | NETIF_F_SG;
 		if (csum)
-			dev->features |= NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST;
+			dev->features |= NETIF_F_HW_CSUM | NETIF_F_SG;
 
 		if (virtio_has_feature(vdev, VIRTIO_NET_F_GSO)) {
 			dev->hw_features |= NETIF_F_TSO
-- 
2.4.1


From 1dbf4da718197ded8db2ae1863687717909b025d Mon Sep 17 00:00:00 2001
From: Sasha Levin <sasha.levin@oracle.com>
Date: Tue, 8 Sep 2015 10:53:40 -0400
Subject: [PATCH 19/19] RDS: verify the underlying transport exists before
 creating a connection

[ Upstream commit 74e98eb085889b0d2d4908f59f6e00026063014f ]

There was no verification that an underlying transport exists when creating
a connection, this would cause dereferencing a NULL ptr.

It might happen on sockets that weren't properly bound before attempting to
send a message, which will cause a NULL ptr deref:

[135546.047719] kasan: GPF could be caused by NULL-ptr deref or user memory accessgeneral protection fault: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC KASAN
[135546.051270] Modules linked in:
[135546.051781] CPU: 4 PID: 15650 Comm: trinity-c4 Not tainted 4.2.0-next-20150902-sasha-00041-gbaa1222-dirty #2527
[135546.053217] task: ffff8800835bc000 ti: ffff8800bc708000 task.ti: ffff8800bc708000
[135546.054291] RIP: __rds_conn_create (net/rds/connection.c:194)
[135546.055666] RSP: 0018:ffff8800bc70fab0  EFLAGS: 00010202
[135546.056457] RAX: dffffc0000000000 RBX: 0000000000000f2c RCX: ffff8800835bc000
[135546.057494] RDX: 0000000000000007 RSI: ffff8800835bccd8 RDI: 0000000000000038
[135546.058530] RBP: ffff8800bc70fb18 R08: 0000000000000001 R09: 0000000000000000
[135546.059556] R10: ffffed014d7a3a23 R11: ffffed014d7a3a21 R12: 0000000000000000
[135546.060614] R13: 0000000000000001 R14: ffff8801ec3d0000 R15: 0000000000000000
[135546.061668] FS:  00007faad4ffb700(0000) GS:ffff880252000000(0000) knlGS:0000000000000000
[135546.062836] CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[135546.063682] CR2: 000000000000846a CR3: 000000009d137000 CR4: 00000000000006a0
[135546.064723] Stack:
[135546.065048]  ffffffffafe2055c ffffffffafe23fc1 ffffed00493097bf ffff8801ec3d0008
[135546.066247]  0000000000000000 00000000000000d0 0000000000000000 ac194a24c0586342
[135546.067438]  1ffff100178e1f78 ffff880320581b00 ffff8800bc70fdd0 ffff880320581b00
[135546.068629] Call Trace:
[135546.069028] ? __rds_conn_create (include/linux/rcupdate.h:856 net/rds/connection.c:134)
[135546.069989] ? rds_message_copy_from_user (net/rds/message.c:298)
[135546.071021] rds_conn_create_outgoing (net/rds/connection.c:278)
[135546.071981] rds_sendmsg (net/rds/send.c:1058)
[135546.072858] ? perf_trace_lock (include/trace/events/lock.h:38)
[135546.073744] ? lockdep_init (kernel/locking/lockdep.c:3298)
[135546.074577] ? rds_send_drop_to (net/rds/send.c:976)
[135546.075508] ? __might_fault (./arch/x86/include/asm/current.h:14 mm/memory.c:3795)
[135546.076349] ? __might_fault (mm/memory.c:3795)
[135546.077179] ? rds_send_drop_to (net/rds/send.c:976)
[135546.078114] sock_sendmsg (net/socket.c:611 net/socket.c:620)
[135546.078856] SYSC_sendto (net/socket.c:1657)
[135546.079596] ? SYSC_connect (net/socket.c:1628)
[135546.080510] ? trace_dump_stack (kernel/trace/trace.c:1926)
[135546.081397] ? ring_buffer_unlock_commit (kernel/trace/ring_buffer.c:2479 kernel/trace/ring_buffer.c:2558 kernel/trace/ring_buffer.c:2674)
[135546.082390] ? trace_buffer_unlock_commit (kernel/trace/trace.c:1749)
[135546.083410] ? trace_event_raw_event_sys_enter (include/trace/events/syscalls.h:16)
[135546.084481] ? do_audit_syscall_entry (include/trace/events/syscalls.h:16)
[135546.085438] ? trace_buffer_unlock_commit (kernel/trace/trace.c:1749)
[135546.085515] rds_ib_laddr_check(): addr 36.74.25.172 ret -99 node type -1

Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/connection.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/rds/connection.c b/net/rds/connection.c
index 378c3a6..f5fb7d6 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -183,6 +183,12 @@ static struct rds_connection *__rds_conn_create(__be32 laddr, __be32 faddr,
 		}
 	}
 
+	if (trans == NULL) {
+		kmem_cache_free(rds_conn_slab, conn);
+		conn = ERR_PTR(-ENODEV);
+		goto out;
+	}
+
 	conn->c_trans = trans;
 
 	ret = trans->conn_alloc(conn, gfp);
-- 
2.4.1

Re: [PATCHES] Networking

[Jiri Slaby]

On 11/13/2015, 10:38 PM, David Miller wrote:
> 
> Please queue up the following bug fixes to 4.3.x, 4.2.x, 4.1.x, and
> 3.18.x -stable, respectively.

Hi,

it looks like 3.18 backport of 4ece9009774596ee3df0acba65a324b7ea79387c
is missing removal of ipip6_tunnel_clone_6rd call, right?

thanks,
-- 
js
suse labs

Re: [PATCHES] Networking

[David Miller]

From: Jiri Slaby <jslaby@suse.cz>
Date: Sat, 14 Nov 2015 16:59:34 +0100

> On 11/13/2015, 10:38 PM, David Miller wrote:
>> 
>> Please queue up the following bug fixes to 4.3.x, 4.2.x, 4.1.x, and
>> 3.18.x -stable, respectively.
> 
> Hi,
> 
> it looks like 3.18 backport of 4ece9009774596ee3df0acba65a324b7ea79387c
> is missing removal of ipip6_tunnel_clone_6rd call, right?

Indeed, good catch.

The following should be more correct:

====================
>From 7cc46fa7d5de9f253615f887522a18bb621737dc Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 2 Nov 2015 17:08:19 -0800
Subject: [PATCH] sit: fix sit0 percpu double allocations

[ Upstream commit 4ece9009774596ee3df0acba65a324b7ea79387c ]

sit0 device allocates its percpu storage twice :
- One time in ipip6_tunnel_init()
- One time in ipip6_fb_tunnel_init()

Thus we leak 48 bytes per possible cpu per network namespace dismantle.

ipip6_fb_tunnel_init() can be much simpler and does not
return an error, and should be called after register_netdev()

Note that ipip6_tunnel_clone_6rd() also needs to be called
after register_netdev() (calling ipip6_tunnel_init())

Fixes: ebe084aafb7e ("sit: Use ipip6_tunnel_init as the ndo_init function.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 27 ++++-----------------------
 1 file changed, 4 insertions(+), 23 deletions(-)

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index a24557a..45eae1e 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1394,34 +1394,20 @@ static int ipip6_tunnel_init(struct net_device *dev)
 	return 0;
 }
 
-static int __net_init ipip6_fb_tunnel_init(struct net_device *dev)
+static void __net_init ipip6_fb_tunnel_init(struct net_device *dev)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	struct iphdr *iph = &tunnel->parms.iph;
 	struct net *net = dev_net(dev);
 	struct sit_net *sitn = net_generic(net, sit_net_id);
 
-	tunnel->dev = dev;
-	tunnel->net = dev_net(dev);
-
 	iph->version		= 4;
 	iph->protocol		= IPPROTO_IPV6;
 	iph->ihl		= 5;
 	iph->ttl		= 64;
 
-	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
-	if (!dev->tstats)
-		return -ENOMEM;
-
-	tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst);
-	if (!tunnel->dst_cache) {
-		free_percpu(dev->tstats);
-		return -ENOMEM;
-	}
-
 	dev_hold(dev);
 	rcu_assign_pointer(sitn->tunnels_wc[0], tunnel);
-	return 0;
 }
 
 static int ipip6_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -1831,23 +1817,18 @@ static int __net_init sit_init_net(struct net *net)
 	 */
 	sitn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL;
 
-	err = ipip6_fb_tunnel_init(sitn->fb_tunnel_dev);
-	if (err)
-		goto err_dev_free;
-
-	ipip6_tunnel_clone_6rd(sitn->fb_tunnel_dev, sitn);
-
 	if ((err = register_netdev(sitn->fb_tunnel_dev)))
 		goto err_reg_dev;
 
+	ipip6_tunnel_clone_6rd(sitn->fb_tunnel_dev, sitn);
+	ipip6_fb_tunnel_init(sitn->fb_tunnel_dev);
+
 	t = netdev_priv(sitn->fb_tunnel_dev);
 
 	strcpy(t->parms.name, sitn->fb_tunnel_dev->name);
 	return 0;
 
 err_reg_dev:
-	dev_put(sitn->fb_tunnel_dev);
-err_dev_free:
 	ipip6_dev_free(sitn->fb_tunnel_dev);
 err_alloc_dev:
 	return err;
-- 
2.1.0

Re: [PATCHES] Networking

[Greg KH]

On Fri, Nov 13, 2015 at 04:38:08PM -0500, David Miller wrote:
> 
> Please queue up the following bug fixes to 4.3.x, 4.2.x, 4.1.x, and
> 3.18.x -stable, respectively.

All queued up, thanks for these.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 112 bytes --]


Please queue up the following networking bug fixes for 3.18, 4.1, 4.2,
and 4.3 -stable, respectively.

Thanks!

[-- Attachment #2: net_318.mbox --]
[-- Type: Application/Octet-Stream, Size: 83293 bytes --]

From 7c242d9a871f5c9962d8b3a140712faab5dc3512 Mon Sep 17 00:00:00 2001
From: Rainer Weikusat <rweikusat@mobileactivedefense.com>
Date: Fri, 20 Nov 2015 22:07:23 +0000
Subject: [PATCH 01/23] unix: avoid use-after-free in ep_remove_wait_queue

[ Upstream commit 7d267278a9ece963d77eefec61630223fce08c6c ]

Rainer Weikusat <rweikusat@mobileactivedefense.com> writes:
An AF_UNIX datagram socket being the client in an n:1 association with
some server socket is only allowed to send messages to the server if the
receive queue of this socket contains at most sk_max_ack_backlog
datagrams. This implies that prospective writers might be forced to go
to sleep despite none of the message presently enqueued on the server
receive queue were sent by them. In order to ensure that these will be
woken up once space becomes again available, the present unix_dgram_poll
routine does a second sock_poll_wait call with the peer_wait wait queue
of the server socket as queue argument (unix_dgram_recvmsg does a wake
up on this queue after a datagram was received). This is inherently
problematic because the server socket is only guaranteed to remain alive
for as long as the client still holds a reference to it. In case the
connection is dissolved via connect or by the dead peer detection logic
in unix_dgram_sendmsg, the server socket may be freed despite "the
polling mechanism" (in particular, epoll) still has a pointer to the
corresponding peer_wait queue. There's no way to forcibly deregister a
wait queue with epoll.

Based on an idea by Jason Baron, the patch below changes the code such
that a wait_queue_t belonging to the client socket is enqueued on the
peer_wait queue of the server whenever the peer receive queue full
condition is detected by either a sendmsg or a poll. A wake up on the
peer queue is then relayed to the ordinary wait queue of the client
socket via wake function. The connection to the peer wait queue is again
dissolved if either a wake up is about to be relayed or the client
socket reconnects or a dead peer is detected or the client socket is
itself closed. This enables removing the second sock_poll_wait from
unix_dgram_poll, thus avoiding the use-after-free, while still ensuring
that no blocked writer sleeps forever.

Signed-off-by: Rainer Weikusat <rweikusat@mobileactivedefense.com>
Fixes: ec0d215f9420 ("af_unix: fix 'poll for write'/connected DGRAM sockets")
Reviewed-by: Jason Baron <jbaron@akamai.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/af_unix.h |   1 +
 net/unix/af_unix.c    | 183 ++++++++++++++++++++++++++++++++++++++++++++------
 2 files changed, 165 insertions(+), 19 deletions(-)

diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index a175ba4..cb4a728 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -63,6 +63,7 @@ struct unix_sock {
 #define UNIX_GC_CANDIDATE	0
 #define UNIX_GC_MAYBE_CYCLE	1
 	struct socket_wq	peer_wq;
+	wait_queue_t		peer_wake;
 };
 #define unix_sk(__sk) ((struct unix_sock *)__sk)
 
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 8232118..b11562e 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -316,6 +316,118 @@ found:
 	return s;
 }
 
+/* Support code for asymmetrically connected dgram sockets
+ *
+ * If a datagram socket is connected to a socket not itself connected
+ * to the first socket (eg, /dev/log), clients may only enqueue more
+ * messages if the present receive queue of the server socket is not
+ * "too large". This means there's a second writeability condition
+ * poll and sendmsg need to test. The dgram recv code will do a wake
+ * up on the peer_wait wait queue of a socket upon reception of a
+ * datagram which needs to be propagated to sleeping would-be writers
+ * since these might not have sent anything so far. This can't be
+ * accomplished via poll_wait because the lifetime of the server
+ * socket might be less than that of its clients if these break their
+ * association with it or if the server socket is closed while clients
+ * are still connected to it and there's no way to inform "a polling
+ * implementation" that it should let go of a certain wait queue
+ *
+ * In order to propagate a wake up, a wait_queue_t of the client
+ * socket is enqueued on the peer_wait queue of the server socket
+ * whose wake function does a wake_up on the ordinary client socket
+ * wait queue. This connection is established whenever a write (or
+ * poll for write) hit the flow control condition and broken when the
+ * association to the server socket is dissolved or after a wake up
+ * was relayed.
+ */
+
+static int unix_dgram_peer_wake_relay(wait_queue_t *q, unsigned mode, int flags,
+				      void *key)
+{
+	struct unix_sock *u;
+	wait_queue_head_t *u_sleep;
+
+	u = container_of(q, struct unix_sock, peer_wake);
+
+	__remove_wait_queue(&unix_sk(u->peer_wake.private)->peer_wait,
+			    q);
+	u->peer_wake.private = NULL;
+
+	/* relaying can only happen while the wq still exists */
+	u_sleep = sk_sleep(&u->sk);
+	if (u_sleep)
+		wake_up_interruptible_poll(u_sleep, key);
+
+	return 0;
+}
+
+static int unix_dgram_peer_wake_connect(struct sock *sk, struct sock *other)
+{
+	struct unix_sock *u, *u_other;
+	int rc;
+
+	u = unix_sk(sk);
+	u_other = unix_sk(other);
+	rc = 0;
+	spin_lock(&u_other->peer_wait.lock);
+
+	if (!u->peer_wake.private) {
+		u->peer_wake.private = other;
+		__add_wait_queue(&u_other->peer_wait, &u->peer_wake);
+
+		rc = 1;
+	}
+
+	spin_unlock(&u_other->peer_wait.lock);
+	return rc;
+}
+
+static void unix_dgram_peer_wake_disconnect(struct sock *sk,
+					    struct sock *other)
+{
+	struct unix_sock *u, *u_other;
+
+	u = unix_sk(sk);
+	u_other = unix_sk(other);
+	spin_lock(&u_other->peer_wait.lock);
+
+	if (u->peer_wake.private == other) {
+		__remove_wait_queue(&u_other->peer_wait, &u->peer_wake);
+		u->peer_wake.private = NULL;
+	}
+
+	spin_unlock(&u_other->peer_wait.lock);
+}
+
+static void unix_dgram_peer_wake_disconnect_wakeup(struct sock *sk,
+						   struct sock *other)
+{
+	unix_dgram_peer_wake_disconnect(sk, other);
+	wake_up_interruptible_poll(sk_sleep(sk),
+				   POLLOUT |
+				   POLLWRNORM |
+				   POLLWRBAND);
+}
+
+/* preconditions:
+ *	- unix_peer(sk) == other
+ *	- association is stable
+ */
+static int unix_dgram_peer_wake_me(struct sock *sk, struct sock *other)
+{
+	int connected;
+
+	connected = unix_dgram_peer_wake_connect(sk, other);
+
+	if (unix_recvq_full(other))
+		return 1;
+
+	if (connected)
+		unix_dgram_peer_wake_disconnect(sk, other);
+
+	return 0;
+}
+
 static inline int unix_writable(struct sock *sk)
 {
 	return (atomic_read(&sk->sk_wmem_alloc) << 2) <= sk->sk_sndbuf;
@@ -420,6 +532,8 @@ static void unix_release_sock(struct sock *sk, int embrion)
 			skpair->sk_state_change(skpair);
 			sk_wake_async(skpair, SOCK_WAKE_WAITD, POLL_HUP);
 		}
+
+		unix_dgram_peer_wake_disconnect(sk, skpair);
 		sock_put(skpair); /* It may now die */
 		unix_peer(sk) = NULL;
 	}
@@ -653,6 +767,7 @@ static struct sock *unix_create1(struct net *net, struct socket *sock)
 	INIT_LIST_HEAD(&u->link);
 	mutex_init(&u->readlock); /* single task reading lock */
 	init_waitqueue_head(&u->peer_wait);
+	init_waitqueue_func_entry(&u->peer_wake, unix_dgram_peer_wake_relay);
 	unix_insert_socket(unix_sockets_unbound(sk), sk);
 out:
 	if (sk == NULL)
@@ -1020,6 +1135,8 @@ restart:
 	if (unix_peer(sk)) {
 		struct sock *old_peer = unix_peer(sk);
 		unix_peer(sk) = other;
+		unix_dgram_peer_wake_disconnect_wakeup(sk, old_peer);
+
 		unix_state_double_unlock(sk, other);
 
 		if (other != old_peer)
@@ -1459,6 +1576,7 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	struct scm_cookie tmp_scm;
 	int max_level;
 	int data_len = 0;
+	int sk_locked;
 
 	if (NULL == siocb->scm)
 		siocb->scm = &tmp_scm;
@@ -1540,12 +1658,14 @@ restart:
 		goto out_free;
 	}
 
+	sk_locked = 0;
 	unix_state_lock(other);
+restart_locked:
 	err = -EPERM;
 	if (!unix_may_send(sk, other))
 		goto out_unlock;
 
-	if (sock_flag(other, SOCK_DEAD)) {
+	if (unlikely(sock_flag(other, SOCK_DEAD))) {
 		/*
 		 *	Check with 1003.1g - what should
 		 *	datagram error
@@ -1553,10 +1673,14 @@ restart:
 		unix_state_unlock(other);
 		sock_put(other);
 
+		if (!sk_locked)
+			unix_state_lock(sk);
+
 		err = 0;
-		unix_state_lock(sk);
 		if (unix_peer(sk) == other) {
 			unix_peer(sk) = NULL;
+			unix_dgram_peer_wake_disconnect_wakeup(sk, other);
+
 			unix_state_unlock(sk);
 
 			unix_dgram_disconnected(sk, other);
@@ -1582,21 +1706,38 @@ restart:
 			goto out_unlock;
 	}
 
-	if (unix_peer(other) != sk && unix_recvq_full(other)) {
-		if (!timeo) {
-			err = -EAGAIN;
-			goto out_unlock;
+	if (unlikely(unix_peer(other) != sk && unix_recvq_full(other))) {
+		if (timeo) {
+			timeo = unix_wait_for_peer(other, timeo);
+
+			err = sock_intr_errno(timeo);
+			if (signal_pending(current))
+				goto out_free;
+
+			goto restart;
 		}
 
-		timeo = unix_wait_for_peer(other, timeo);
+		if (!sk_locked) {
+			unix_state_unlock(other);
+			unix_state_double_lock(sk, other);
+		}
 
-		err = sock_intr_errno(timeo);
-		if (signal_pending(current))
-			goto out_free;
+		if (unix_peer(sk) != other ||
+		    unix_dgram_peer_wake_me(sk, other)) {
+			err = -EAGAIN;
+			sk_locked = 1;
+			goto out_unlock;
+		}
 
-		goto restart;
+		if (!sk_locked) {
+			sk_locked = 1;
+			goto restart_locked;
+		}
 	}
 
+	if (unlikely(sk_locked))
+		unix_state_unlock(sk);
+
 	if (sock_flag(other, SOCK_RCVTSTAMP))
 		__net_timestamp(skb);
 	maybe_add_creds(skb, sock, other);
@@ -1610,6 +1751,8 @@ restart:
 	return len;
 
 out_unlock:
+	if (sk_locked)
+		unix_state_unlock(sk);
 	unix_state_unlock(other);
 out_free:
 	kfree_skb(skb);
@@ -2255,14 +2398,16 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock,
 		return mask;
 
 	writable = unix_writable(sk);
-	other = unix_peer_get(sk);
-	if (other) {
-		if (unix_peer(other) != sk) {
-			sock_poll_wait(file, &unix_sk(other)->peer_wait, wait);
-			if (unix_recvq_full(other))
-				writable = 0;
-		}
-		sock_put(other);
+	if (writable) {
+		unix_state_lock(sk);
+
+		other = unix_peer(sk);
+		if (other && unix_peer(other) != sk &&
+		    unix_recvq_full(other) &&
+		    unix_dgram_peer_wake_me(sk, other))
+			writable = 0;
+
+		unix_state_unlock(sk);
 	}
 
 	if (writable)
-- 
2.4.1


From 4c317c260868f448f5467535535a246c5a83b08b Mon Sep 17 00:00:00 2001
From: Kamal Mostafa <kamal@canonical.com>
Date: Wed, 11 Nov 2015 14:24:27 -0800
Subject: [PATCH 02/23] tools/net: Use include/uapi with __EXPORTED_HEADERS__

[ Upstream commit d7475de58575c904818efa369c82e88c6648ce2e ]

Use the local uapi headers to keep in sync with "recently" added #define's
(e.g. SKF_AD_VLAN_TPID).  Refactored CFLAGS, and bpf_asm doesn't need -I.

Fixes: 3f356385e8a4 ("filter: bpf_asm: add minimal bpf asm tool")
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/net/Makefile | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/tools/net/Makefile b/tools/net/Makefile
index ee577ea..ddf8880 100644
--- a/tools/net/Makefile
+++ b/tools/net/Makefile
@@ -4,6 +4,9 @@ CC = gcc
 LEX = flex
 YACC = bison
 
+CFLAGS += -Wall -O2
+CFLAGS += -D__EXPORTED_HEADERS__ -I../../include/uapi -I../../include
+
 %.yacc.c: %.y
 	$(YACC) -o $@ -d $<
 
@@ -12,15 +15,13 @@ YACC = bison
 
 all : bpf_jit_disasm bpf_dbg bpf_asm
 
-bpf_jit_disasm : CFLAGS = -Wall -O2 -DPACKAGE='bpf_jit_disasm'
+bpf_jit_disasm : CFLAGS += -DPACKAGE='bpf_jit_disasm'
 bpf_jit_disasm : LDLIBS = -lopcodes -lbfd -ldl
 bpf_jit_disasm : bpf_jit_disasm.o
 
-bpf_dbg : CFLAGS = -Wall -O2
 bpf_dbg : LDLIBS = -lreadline
 bpf_dbg : bpf_dbg.o
 
-bpf_asm : CFLAGS = -Wall -O2 -I.
 bpf_asm : LDLIBS =
 bpf_asm : bpf_asm.o bpf_exp.yacc.o bpf_exp.lex.o
 bpf_exp.lex.o : bpf_exp.yacc.c
-- 
2.4.1


From 1add2a51ec1e0dd0e66b7b5d5594f120f1305748 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 11 Nov 2015 23:25:40 +0100
Subject: [PATCH 03/23] packet: do skb_probe_transport_header when we actually
 have data

[ Upstream commit efdfa2f7848f64517008136fb41f53c4a1faf93a ]

In tpacket_fill_skb() commit c1aad275b029 ("packet: set transport
header before doing xmit") and later on 40893fd0fd4e ("net: switch
to use skb_probe_transport_header()") was probing for a transport
header on the skb from a ring buffer slot, but at a time, where
the skb has _not even_ been filled with data yet. So that call into
the flow dissector is pretty useless. Lets do it after we've set
up the skb frags.

Fixes: c1aad275b029 ("packet: set transport header before doing xmit")
Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index bf60977..0a6868e 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2117,8 +2117,6 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 	skb_reserve(skb, hlen);
 	skb_reset_network_header(skb);
 
-	if (!packet_use_direct_xmit(po))
-		skb_probe_transport_header(skb, 0);
 	if (unlikely(po->tp_tx_has_off)) {
 		int off_min, off_max, off;
 		off_min = po->tp_hdrlen - sizeof(struct sockaddr_ll);
@@ -2202,6 +2200,9 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 		len = ((to_write > len_max) ? len_max : to_write);
 	}
 
+	if (!packet_use_direct_xmit(po))
+		skb_probe_transport_header(skb, 0);
+
 	return tp_len;
 }
 
-- 
2.4.1


From da661e19afc5895926fb2f9c8df503efee596dbf Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 11 Nov 2015 23:25:41 +0100
Subject: [PATCH 04/23] packet: always probe for transport header

[ Upstream commit 8fd6c80d9dd938ca338c70698533a7e304752846 ]

We concluded that the skb_probe_transport_header() should better be
called unconditionally. Avoiding the call into the flow dissector has
also not really much to do with the direct xmit mode.

While it seems that only virtio_net code makes use of GSO from non
RX/TX ring packet socket paths, we should probe for a transport header
nevertheless before they hit devices.

Reference: http://thread.gmane.org/gmane.linux.network/386173/
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 0a6868e..9ac51b5 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2200,8 +2200,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 		len = ((to_write > len_max) ? len_max : to_write);
 	}
 
-	if (!packet_use_direct_xmit(po))
-		skb_probe_transport_header(skb, 0);
+	skb_probe_transport_header(skb, 0);
 
 	return tp_len;
 }
@@ -2538,8 +2537,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		len += vnet_hdr_len;
 	}
 
-	if (!packet_use_direct_xmit(po))
-		skb_probe_transport_header(skb, reserve);
+	skb_probe_transport_header(skb, reserve);
+
 	if (unlikely(extra_len == 4))
 		skb->no_fcs = 1;
 
-- 
2.4.1


From 2a5cdc54f4969a5f67ed03db014ef80f61d3d407 Mon Sep 17 00:00:00 2001
From: Alexander Drozdov <al.drozdov@gmail.com>
Date: Tue, 28 Jul 2015 13:57:01 +0300
Subject: [PATCH 05/23] packet: tpacket_snd(): fix signed/unsigned comparison

[ Upstream commit dbd46ab412b8fb395f2b0ff6f6a7eec9df311550 ]

tpacket_fill_skb() can return a negative value (-errno) which
is stored in tp_len variable. In that case the following
condition will be (but shouldn't be) true:

tp_len > dev->mtu + dev->hard_header_len

as dev->mtu and dev->hard_header_len are both unsigned.

That may lead to just returning an incorrect EMSGSIZE errno
to the user.

Fixes: 52f1454f629fa ("packet: allow to transmit +4 byte in TX_RING slot for VLAN case")
Signed-off-by: Alexander Drozdov <al.drozdov@gmail.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 9ac51b5..40df7cd 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2274,7 +2274,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 
 		tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto,
 					  addr, hlen);
-		if (tp_len > dev->mtu + dev->hard_header_len) {
+		if (likely(tp_len >= 0) &&
+		    tp_len > dev->mtu + dev->hard_header_len) {
 			struct ethhdr *ehdr;
 			/* Earlier code assumed this would be a VLAN pkt,
 			 * double-check this now that we have the actual
-- 
2.4.1


From 81073407a1ed4ae3964838074284d25563c8b833 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 11 Nov 2015 23:25:42 +0100
Subject: [PATCH 06/23] packet: only allow extra vlan len on ethernet devices

[ Upstream commit 3c70c132488794e2489ab045559b0ce0afcf17de ]

Packet sockets can be used by various net devices and are not
really restricted to ARPHRD_ETHER device types. However, when
currently checking for the extra 4 bytes that can be transmitted
in VLAN case, our assumption is that we generally probe on
ARPHRD_ETHER devices. Therefore, before looking into Ethernet
header, check the device type first.

This also fixes the issue where non-ARPHRD_ETHER devices could
have no dev->hard_header_len in TX_RING SOCK_RAW case, and thus
the check would test unfilled linear part of the skb (instead
of non-linear).

Fixes: 57f89bfa2140 ("network: Allow af_packet to transmit +4 bytes for VLAN packets.")
Fixes: 52f1454f629f ("packet: allow to transmit +4 byte in TX_RING slot for VLAN case")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 60 +++++++++++++++++++++-----------------------------
 1 file changed, 25 insertions(+), 35 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 40df7cd..8670ffb 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1507,6 +1507,20 @@ static void fanout_release(struct sock *sk)
 	mutex_unlock(&fanout_mutex);
 }
 
+static bool packet_extra_vlan_len_allowed(const struct net_device *dev,
+					  struct sk_buff *skb)
+{
+	/* Earlier code assumed this would be a VLAN pkt, double-check
+	 * this now that we have the actual packet in hand. We can only
+	 * do this check on Ethernet devices.
+	 */
+	if (unlikely(dev->type != ARPHRD_ETHER))
+		return false;
+
+	skb_reset_mac_header(skb);
+	return likely(eth_hdr(skb)->h_proto == htons(ETH_P_8021Q));
+}
+
 static const struct proto_ops packet_ops;
 
 static const struct proto_ops packet_ops_spkt;
@@ -1668,18 +1682,10 @@ retry:
 		goto retry;
 	}
 
-	if (len > (dev->mtu + dev->hard_header_len + extra_len)) {
-		/* Earlier code assumed this would be a VLAN pkt,
-		 * double-check this now that we have the actual
-		 * packet in hand.
-		 */
-		struct ethhdr *ehdr;
-		skb_reset_mac_header(skb);
-		ehdr = eth_hdr(skb);
-		if (ehdr->h_proto != htons(ETH_P_8021Q)) {
-			err = -EMSGSIZE;
-			goto out_unlock;
-		}
+	if (len > (dev->mtu + dev->hard_header_len + extra_len) &&
+	    !packet_extra_vlan_len_allowed(dev, skb)) {
+		err = -EMSGSIZE;
+		goto out_unlock;
 	}
 
 	skb->protocol = proto;
@@ -2275,18 +2281,10 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 		tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto,
 					  addr, hlen);
 		if (likely(tp_len >= 0) &&
-		    tp_len > dev->mtu + dev->hard_header_len) {
-			struct ethhdr *ehdr;
-			/* Earlier code assumed this would be a VLAN pkt,
-			 * double-check this now that we have the actual
-			 * packet in hand.
-			 */
+		    tp_len > dev->mtu + dev->hard_header_len &&
+		    !packet_extra_vlan_len_allowed(dev, skb))
+			tp_len = -EMSGSIZE;
 
-			skb_reset_mac_header(skb);
-			ehdr = eth_hdr(skb);
-			if (ehdr->h_proto != htons(ETH_P_8021Q))
-				tp_len = -EMSGSIZE;
-		}
 		if (unlikely(tp_len < 0)) {
 			if (po->tp_loss) {
 				__packet_set_status(po, ph,
@@ -2498,18 +2496,10 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 
 	sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags);
 
-	if (!gso_type && (len > dev->mtu + reserve + extra_len)) {
-		/* Earlier code assumed this would be a VLAN pkt,
-		 * double-check this now that we have the actual
-		 * packet in hand.
-		 */
-		struct ethhdr *ehdr;
-		skb_reset_mac_header(skb);
-		ehdr = eth_hdr(skb);
-		if (ehdr->h_proto != htons(ETH_P_8021Q)) {
-			err = -EMSGSIZE;
-			goto out_free;
-		}
+	if (!gso_type && (len > dev->mtu + reserve + extra_len) &&
+	    !packet_extra_vlan_len_allowed(dev, skb)) {
+		err = -EMSGSIZE;
+		goto out_free;
 	}
 
 	skb->protocol = proto;
-- 
2.4.1


From 12bad87e4020abac47c7d198e4142c28dcee0552 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 11 Nov 2015 23:25:43 +0100
Subject: [PATCH 07/23] packet: infer protocol from ethernet header if unset

[ Upstream commit c72219b75fde768efccf7666342282fab7f9e4e7 ]

In case no struct sockaddr_ll has been passed to packet
socket's sendmsg() when doing a TX_RING flush run, then
skb->protocol is set to po->num instead, which is the protocol
passed via socket(2)/bind(2).

Applications only xmitting can go the path of allocating the
socket as socket(PF_PACKET, <mode>, 0) and do a bind(2) on the
TX_RING with sll_protocol of 0. That way, register_prot_hook()
is neither called on creation nor on bind time, which saves
cycles when there's no interest in capturing anyway.

That leaves us however with po->num 0 instead and therefore
the TX_RING flush run sets skb->protocol to 0 as well. Eric
reported that this leads to problems when using tools like
trafgen over bonding device. I.e. the bonding's hash function
could invoke the kernel's flow dissector, which depends on
skb->protocol being properly set. In the current situation, all
the traffic is then directed to a single slave.

Fix it up by inferring skb->protocol from the Ethernet header
when not set and we have ARPHRD_ETHER device type. This is only
done in case of SOCK_RAW and where we have a dev->hard_header_len
length. In case of ARPHRD_ETHER devices, this is guaranteed to
cover ETH_HLEN, and therefore being accessed on the skb after
the skb_store_bits().

Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 8670ffb..81dfc66 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2087,6 +2087,15 @@ static void tpacket_destruct_skb(struct sk_buff *skb)
 	sock_wfree(skb);
 }
 
+static void tpacket_set_protocol(const struct net_device *dev,
+				 struct sk_buff *skb)
+{
+	if (dev->type == ARPHRD_ETHER) {
+		skb_reset_mac_header(skb);
+		skb->protocol = eth_hdr(skb)->h_proto;
+	}
+}
+
 static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 		void *frame, struct net_device *dev, int size_max,
 		__be16 proto, unsigned char *addr, int hlen)
@@ -2172,6 +2181,8 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 				dev->hard_header_len);
 		if (unlikely(err))
 			return err;
+		if (!skb->protocol)
+			tpacket_set_protocol(dev, skb);
 
 		data += dev->hard_header_len;
 		to_write -= dev->hard_header_len;
-- 
2.4.1


From 3a8d03f8a6c29869dc01f464529e42354b383961 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 11 Nov 2015 23:25:44 +0100
Subject: [PATCH 08/23] packet: fix tpacket_snd max frame len

[ Upstream commit 5cfb4c8d05b4409c4044cb9c05b19705c1d9818b ]

Since it's introduction in commit 69e3c75f4d54 ("net: TX_RING and
packet mmap"), TX_RING could be used from SOCK_DGRAM and SOCK_RAW
side. When used with SOCK_DGRAM only, the size_max > dev->mtu +
reserve check should have reserve as 0, but currently, this is
unconditionally set (in it's original form as dev->hard_header_len).

I think this is not correct since tpacket_fill_skb() would then
take dev->mtu and dev->hard_header_len into account for SOCK_DGRAM,
the extra VLAN_HLEN could be possible in both cases. Presumably, the
reserve code was copied from packet_snd(), but later on missed the
check. Make it similar as we have it in packet_snd().

Fixes: 69e3c75f4d54 ("net: TX_RING and packet mmap")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 81dfc66..cb62daf 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2263,12 +2263,13 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 	if (unlikely(!(dev->flags & IFF_UP)))
 		goto out_put;
 
-	reserve = dev->hard_header_len + VLAN_HLEN;
+	if (po->sk.sk_socket->type == SOCK_RAW)
+		reserve = dev->hard_header_len;
 	size_max = po->tx_ring.frame_size
 		- (po->tp_hdrlen - sizeof(struct sockaddr_ll));
 
-	if (size_max > dev->mtu + reserve)
-		size_max = dev->mtu + reserve;
+	if (size_max > dev->mtu + reserve + VLAN_HLEN)
+		size_max = dev->mtu + reserve + VLAN_HLEN;
 
 	do {
 		ph = packet_current_frame(po, &po->tx_ring,
@@ -2292,7 +2293,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 		tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto,
 					  addr, hlen);
 		if (likely(tp_len >= 0) &&
-		    tp_len > dev->mtu + dev->hard_header_len &&
+		    tp_len > dev->mtu + reserve &&
 		    !packet_extra_vlan_len_allowed(dev, skb))
 			tp_len = -EMSGSIZE;
 
-- 
2.4.1


From c2e34c5d0ffc482fcd229e73c47a452e06c40854 Mon Sep 17 00:00:00 2001
From: lucien <lucien.xin@gmail.com>
Date: Thu, 12 Nov 2015 13:07:07 +0800
Subject: [PATCH 09/23] sctp: translate host order to network order when
 setting a hmacid

[ Upstream commit ed5a377d87dc4c87fb3e1f7f698cba38cd893103 ]

now sctp auth cannot work well when setting a hmacid manually, which
is caused by that we didn't use the network order for hmacid, so fix
it by adding the transformation in sctp_auth_ep_set_hmacs.

even we set hmacid with the network order in userspace, it still
can't work, because of this condition in sctp_auth_ep_set_hmacs():

		if (id > SCTP_AUTH_HMAC_ID_MAX)
			return -EOPNOTSUPP;

so this wasn't working before and thus it won't break compatibility.

Fixes: 65b07e5d0d09 ("[SCTP]: API updates to suport SCTP-AUTH extensions.")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/auth.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sctp/auth.c b/net/sctp/auth.c
index fb7976a..603c3bb 100644
--- a/net/sctp/auth.c
+++ b/net/sctp/auth.c
@@ -800,8 +800,8 @@ int sctp_auth_ep_set_hmacs(struct sctp_endpoint *ep,
 	if (!has_sha1)
 		return -EINVAL;
 
-	memcpy(ep->auth_hmacs_list->hmac_ids, &hmacs->shmac_idents[0],
-		hmacs->shmac_num_idents * sizeof(__u16));
+	for (i = 0; i < hmacs->shmac_num_idents; i++)
+		ep->auth_hmacs_list->hmac_ids[i] = htons(hmacs->shmac_idents[i]);
 	ep->auth_hmacs_list->param_hdr.length = htons(sizeof(sctp_paramhdr_t) +
 				hmacs->shmac_num_idents * sizeof(__u16));
 	return 0;
-- 
2.4.1


From e467d6fac3b48f1c3bbdd702a4612d224ce858e5 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Thu, 12 Nov 2015 17:35:58 +0100
Subject: [PATCH 10/23] ip_tunnel: disable preemption when updating per-cpu
 tstats

[ Upstream commit b4fe85f9c9146f60457e9512fb6055e69e6a7a65 ]

Drivers like vxlan use the recently introduced
udp_tunnel_xmit_skb/udp_tunnel6_xmit_skb APIs. udp_tunnel6_xmit_skb
makes use of ip6tunnel_xmit, and ip6tunnel_xmit, after sending the
packet, updates the struct stats using the usual
u64_stats_update_begin/end calls on this_cpu_ptr(dev->tstats).
udp_tunnel_xmit_skb makes use of iptunnel_xmit, which doesn't touch
tstats, so drivers like vxlan, immediately after, call
iptunnel_xmit_stats, which does the same thing - calls
u64_stats_update_begin/end on this_cpu_ptr(dev->tstats).

While vxlan is probably fine (I don't know?), calling a similar function
from, say, an unbound workqueue, on a fully preemptable kernel causes
real issues:

[  188.434537] BUG: using smp_processor_id() in preemptible [00000000] code: kworker/u8:0/6
[  188.435579] caller is debug_smp_processor_id+0x17/0x20
[  188.435583] CPU: 0 PID: 6 Comm: kworker/u8:0 Not tainted 4.2.6 #2
[  188.435607] Call Trace:
[  188.435611]  [<ffffffff8234e936>] dump_stack+0x4f/0x7b
[  188.435615]  [<ffffffff81915f3d>] check_preemption_disabled+0x19d/0x1c0
[  188.435619]  [<ffffffff81915f77>] debug_smp_processor_id+0x17/0x20

The solution would be to protect the whole
this_cpu_ptr(dev->tstats)/u64_stats_update_begin/end blocks with
disabling preemption and then reenabling it.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_tunnel.h | 3 ++-
 include/net/ip_tunnels.h | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index a5593da..ef95576 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -79,11 +79,12 @@ static inline void ip6tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 	err = ip6_local_out(skb);
 
 	if (net_xmit_eval(err) == 0) {
-		struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
+		struct pcpu_sw_netstats *tstats = get_cpu_ptr(dev->tstats);
 		u64_stats_update_begin(&tstats->syncp);
 		tstats->tx_bytes += pkt_len;
 		tstats->tx_packets++;
 		u64_stats_update_end(&tstats->syncp);
+		put_cpu_ptr(tstats);
 	} else {
 		stats->tx_errors++;
 		stats->tx_aborted_errors++;
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 5bc6ede..a3f2f80 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -186,12 +186,13 @@ static inline void iptunnel_xmit_stats(int err,
 				       struct pcpu_sw_netstats __percpu *stats)
 {
 	if (err > 0) {
-		struct pcpu_sw_netstats *tstats = this_cpu_ptr(stats);
+		struct pcpu_sw_netstats *tstats = get_cpu_ptr(stats);
 
 		u64_stats_update_begin(&tstats->syncp);
 		tstats->tx_bytes += err;
 		tstats->tx_packets++;
 		u64_stats_update_end(&tstats->syncp);
+		put_cpu_ptr(tstats);
 	} else if (err < 0) {
 		err_stats->tx_errors++;
 		err_stats->tx_aborted_errors++;
-- 
2.4.1


From e6195ff76c36e4a2d3173b8e05158da10c8d6985 Mon Sep 17 00:00:00 2001
From: Neil Horman <nhorman@tuxdriver.com>
Date: Mon, 16 Nov 2015 13:09:10 -0500
Subject: [PATCH 11/23] snmp: Remove duplicate OUTMCAST stat increment

[ Upstream commit 41033f029e393a64e81966cbe34d66c6cf8a2e7e ]

the OUTMCAST stat is double incremented, getting bumped once in the mcast code
itself, and again in the common ip output path.  Remove the mcast bump, as its
not needed

Validated by the reporter, with good results

Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Reported-by: Claus Jensen <claus.jensen@microsemi.com>
CC: Claus Jensen <claus.jensen@microsemi.com>
CC: David Miller <davem@davemloft.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/mcast.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index ed2c4e4..5aedf76 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1652,7 +1652,6 @@ out:
 	if (!err) {
 		ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT);
 		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
-		IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, payload_len);
 	} else {
 		IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
 	}
@@ -2015,7 +2014,6 @@ out:
 	if (!err) {
 		ICMP6MSGOUT_INC_STATS(net, idev, type);
 		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
-		IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, full_len);
 	} else
 		IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
 
-- 
2.4.1


From f9b3ee630a8c8b5151d3ec759b9feae119d4cf43 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Wed, 18 Nov 2015 21:13:07 +0100
Subject: [PATCH 12/23] net: qmi_wwan: add XS Stick W100-2 from 4G Systems
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 68242a5a1e2edce39b069385cbafb82304eac0f1 ]

Thomas reports
"
4gsystems sells two total different LTE-surfsticks under the same name.
..
The newer version of XS Stick W100 is from "omega"
..
Under windows the driver switches to the same ID, and uses MI03\6 for
network and MI01\6 for modem.
..
echo "1c9e 9b01" > /sys/bus/usb/drivers/qmi_wwan/new_id
echo "1c9e 9b01" > /sys/bus/usb-serial/drivers/option1/new_id

T:  Bus=01 Lev=01 Prnt=01 Port=03 Cnt=01 Dev#=  4 Spd=480 MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1c9e ProdID=9b01 Rev=02.32
S:  Manufacturer=USB Modem
S:  Product=USB Modem
S:  SerialNumber=
C:  #Ifs= 5 Cfg#= 1 Atr=80 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
I:  If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
I:  If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
I:  If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
I:  If#= 4 Alt= 0 #EPs= 2 Cls=08(stor.) Sub=06 Prot=50 Driver=usb-storage

Now all important things are there:

wwp0s29f7u2i3 (net), ttyUSB2 (at), cdc-wdm0 (qmi), ttyUSB1 (at)

There is also ttyUSB0, but it is not usable, at least not for at.

The device works well with qmi and ModemManager-NetworkManager.
"

Reported-by: Thomas Schäfer <tschaefer@t-online.de>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index b8a82b8..24f47fd 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -766,6 +766,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x2357, 0x9000, 4)},	/* TP-LINK MA260 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)},	/* Telit LE920 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1201, 2)},	/* Telit LE920 */
+	{QMI_FIXED_INTF(0x1c9e, 0x9b01, 3)},	/* XS Stick W100-2 from 4G Systems */
 	{QMI_FIXED_INTF(0x0b3c, 0xc000, 4)},	/* Olivetti Olicard 100 */
 	{QMI_FIXED_INTF(0x0b3c, 0xc001, 4)},	/* Olivetti Olicard 120 */
 	{QMI_FIXED_INTF(0x0b3c, 0xc002, 4)},	/* Olivetti Olicard 140 */
-- 
2.4.1


From f5cdc7c2e935e9a1508dc3f3b205e7180df5cea8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 18 Nov 2015 12:40:13 -0800
Subject: [PATCH 13/23] tcp: md5: fix lockdep annotation

[ Upstream commit 1b8e6a01e19f001e9f93b39c32387961c91ed3cc ]

When a passive TCP is created, we eventually call tcp_md5_do_add()
with sk pointing to the child. It is not owner by the user yet (we
will add this socket into listener accept queue a bit later anyway)

But we do own the spinlock, so amend the lockdep annotation to avoid
following splat :

[ 8451.090932] net/ipv4/tcp_ipv4.c:923 suspicious rcu_dereference_protected() usage!
[ 8451.090932]
[ 8451.090932] other info that might help us debug this:
[ 8451.090932]
[ 8451.090934]
[ 8451.090934] rcu_scheduler_active = 1, debug_locks = 1
[ 8451.090936] 3 locks held by socket_sockopt_/214795:
[ 8451.090936]  #0:  (rcu_read_lock){.+.+..}, at: [<ffffffff855c6ac1>] __netif_receive_skb_core+0x151/0xe90
[ 8451.090947]  #1:  (rcu_read_lock){.+.+..}, at: [<ffffffff85618143>] ip_local_deliver_finish+0x43/0x2b0
[ 8451.090952]  #2:  (slock-AF_INET){+.-...}, at: [<ffffffff855acda5>] sk_clone_lock+0x1c5/0x500
[ 8451.090958]
[ 8451.090958] stack backtrace:
[ 8451.090960] CPU: 7 PID: 214795 Comm: socket_sockopt_

[ 8451.091215] Call Trace:
[ 8451.091216]  <IRQ>  [<ffffffff856fb29c>] dump_stack+0x55/0x76
[ 8451.091229]  [<ffffffff85123b5b>] lockdep_rcu_suspicious+0xeb/0x110
[ 8451.091235]  [<ffffffff8564544f>] tcp_md5_do_add+0x1bf/0x1e0
[ 8451.091239]  [<ffffffff85645751>] tcp_v4_syn_recv_sock+0x1f1/0x4c0
[ 8451.091242]  [<ffffffff85642b27>] ? tcp_v4_md5_hash_skb+0x167/0x190
[ 8451.091246]  [<ffffffff85647c78>] tcp_check_req+0x3c8/0x500
[ 8451.091249]  [<ffffffff856451ae>] ? tcp_v4_inbound_md5_hash+0x11e/0x190
[ 8451.091253]  [<ffffffff85647170>] tcp_v4_rcv+0x3c0/0x9f0
[ 8451.091256]  [<ffffffff85618143>] ? ip_local_deliver_finish+0x43/0x2b0
[ 8451.091260]  [<ffffffff856181b6>] ip_local_deliver_finish+0xb6/0x2b0
[ 8451.091263]  [<ffffffff85618143>] ? ip_local_deliver_finish+0x43/0x2b0
[ 8451.091267]  [<ffffffff85618d38>] ip_local_deliver+0x48/0x80
[ 8451.091270]  [<ffffffff85618510>] ip_rcv_finish+0x160/0x700
[ 8451.091273]  [<ffffffff8561900e>] ip_rcv+0x29e/0x3d0
[ 8451.091277]  [<ffffffff855c74b7>] __netif_receive_skb_core+0xb47/0xe90

Fixes: a8afca0329988 ("tcp: md5: protects md5sig_info with RCU")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a5fdfe9..6cd9f69 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -959,7 +959,8 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
 	}
 
 	md5sig = rcu_dereference_protected(tp->md5sig_info,
-					   sock_owned_by_user(sk));
+					   sock_owned_by_user(sk) ||
+					   lockdep_is_held(&sk->sk_lock.slock));
 	if (!md5sig) {
 		md5sig = kmalloc(sizeof(*md5sig), gfp);
 		if (!md5sig)
-- 
2.4.1


From ee56324ce74d5b66df0bf44701634732ddbd0959 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 18 Nov 2015 21:03:33 -0800
Subject: [PATCH 14/23] tcp: fix potential huge kmalloc() calls in TCP_REPAIR

[ Upstream commit 5d4c9bfbabdb1d497f21afd81501e5c54b0c85d9 ]

tcp_send_rcvq() is used for re-injecting data into tcp receive queue.

Problems :

- No check against size is performed, allowed user to fool kernel in
  attempting very large memory allocations, eventually triggering
  OOM when memory is fragmented.

- In case of fault during the copy we do not return correct errno.

Lets use alloc_skb_with_frags() to cook optimal skbs.

Fixes: 292e8d8c8538 ("tcp: Move rcvq sending to tcp_input.c")
Fixes: c0e88ff0f256 ("tcp: Repair socket queues")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 22 +++++++++++++++++++---
 1 file changed, 19 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 6f46cde..aa16715 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4356,19 +4356,34 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int
 int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
 {
 	struct sk_buff *skb;
+	int err = -ENOMEM;
+	int data_len = 0;
 	bool fragstolen;
 
 	if (size == 0)
 		return 0;
 
-	skb = alloc_skb(size, sk->sk_allocation);
+	if (size > PAGE_SIZE) {
+		int npages = min_t(size_t, size >> PAGE_SHIFT, MAX_SKB_FRAGS);
+
+		data_len = npages << PAGE_SHIFT;
+		size = data_len + (size & ~PAGE_MASK);
+	}
+	skb = alloc_skb_with_frags(size - data_len, data_len,
+				   PAGE_ALLOC_COSTLY_ORDER,
+				   &err, sk->sk_allocation);
 	if (!skb)
 		goto err;
 
+	skb_put(skb, size - data_len);
+	skb->data_len = data_len;
+	skb->len = size;
+
 	if (tcp_try_rmem_schedule(sk, skb, skb->truesize))
 		goto err_free;
 
-	if (memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size))
+	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, size);
+	if (err)
 		goto err_free;
 
 	TCP_SKB_CB(skb)->seq = tcp_sk(sk)->rcv_nxt;
@@ -4384,7 +4399,8 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
 err_free:
 	kfree_skb(skb);
 err:
-	return -ENOMEM;
+	return err;
+
 }
 
 static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
-- 
2.4.1


From f52f4692c6cf5f3523c8142106e39e4d18292d36 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 26 Nov 2015 08:18:14 -0800
Subject: [PATCH 15/23] tcp: initialize tp->copied_seq in case of cross SYN
 connection

[ Upstream commit 142a2e7ece8d8ac0e818eb2c91f99ca894730e2a ]

Dmitry provided a syzkaller (http://github.com/google/syzkaller)
generated program that triggers the WARNING at
net/ipv4/tcp.c:1729 in tcp_recvmsg() :

WARN_ON(tp->copied_seq != tp->rcv_nxt &&
        !(flags & (MSG_PEEK | MSG_TRUNC)));

His program is specifically attempting a Cross SYN TCP exchange,
that we support (for the pleasure of hackers ?), but it looks we
lack proper tcp->copied_seq initialization.

Thanks again Dmitry for your report and testings.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Tested-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index aa16715..0c96055 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5540,6 +5540,7 @@ discard:
 		}
 
 		tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
+		tp->copied_seq = tp->rcv_nxt;
 		tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1;
 
 		/* RFC1323: The window in SYN & SYN/ACK segments is
-- 
2.4.1


From 1d26a5197c10ea419524fa731e456398e99cea42 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 20 Nov 2015 00:11:56 +0100
Subject: [PATCH 16/23] net, scm: fix PaX detected msg_controllen overflow in
 scm_detach_fds

[ Upstream commit 6900317f5eff0a7070c5936e5383f589e0de7a09 ]

David and HacKurx reported a following/similar size overflow triggered
in a grsecurity kernel, thanks to PaX's gcc size overflow plugin:

(Already fixed in later grsecurity versions by Brad and PaX Team.)

[ 1002.296137] PAX: size overflow detected in function scm_detach_fds net/core/scm.c:314
               cicus.202_127 min, count: 4, decl: msg_controllen; num: 0; context: msghdr;
[ 1002.296145] CPU: 0 PID: 3685 Comm: scm_rights_recv Not tainted 4.2.3-grsec+ #7
[ 1002.296149] Hardware name: Apple Inc. MacBookAir5,1/Mac-66F35F19FE2A0D05, [...]
[ 1002.296153]  ffffffff81c27366 0000000000000000 ffffffff81c27375 ffffc90007843aa8
[ 1002.296162]  ffffffff818129ba 0000000000000000 ffffffff81c27366 ffffc90007843ad8
[ 1002.296169]  ffffffff8121f838 fffffffffffffffc fffffffffffffffc ffffc90007843e60
[ 1002.296176] Call Trace:
[ 1002.296190]  [<ffffffff818129ba>] dump_stack+0x45/0x57
[ 1002.296200]  [<ffffffff8121f838>] report_size_overflow+0x38/0x60
[ 1002.296209]  [<ffffffff816a979e>] scm_detach_fds+0x2ce/0x300
[ 1002.296220]  [<ffffffff81791899>] unix_stream_read_generic+0x609/0x930
[ 1002.296228]  [<ffffffff81791c9f>] unix_stream_recvmsg+0x4f/0x60
[ 1002.296236]  [<ffffffff8178dc00>] ? unix_set_peek_off+0x50/0x50
[ 1002.296243]  [<ffffffff8168fac7>] sock_recvmsg+0x47/0x60
[ 1002.296248]  [<ffffffff81691522>] ___sys_recvmsg+0xe2/0x1e0
[ 1002.296257]  [<ffffffff81693496>] __sys_recvmsg+0x46/0x80
[ 1002.296263]  [<ffffffff816934fc>] SyS_recvmsg+0x2c/0x40
[ 1002.296271]  [<ffffffff8181a3ab>] entry_SYSCALL_64_fastpath+0x12/0x85

Further investigation showed that this can happen when an *odd* number of
fds are being passed over AF_UNIX sockets.

In these cases CMSG_LEN(i * sizeof(int)) and CMSG_SPACE(i * sizeof(int)),
where i is the number of successfully passed fds, differ by 4 bytes due
to the extra CMSG_ALIGN() padding in CMSG_SPACE() to an 8 byte boundary
on 64 bit. The padding is used to align subsequent cmsg headers in the
control buffer.

When the control buffer passed in from the receiver side *lacks* these 4
bytes (e.g. due to buggy/wrong API usage), then msg->msg_controllen will
overflow in scm_detach_fds():

  int cmlen = CMSG_LEN(i * sizeof(int));  <--- cmlen w/o tail-padding
  err = put_user(SOL_SOCKET, &cm->cmsg_level);
  if (!err)
    err = put_user(SCM_RIGHTS, &cm->cmsg_type);
  if (!err)
    err = put_user(cmlen, &cm->cmsg_len);
  if (!err) {
    cmlen = CMSG_SPACE(i * sizeof(int));  <--- cmlen w/ 4 byte extra tail-padding
    msg->msg_control += cmlen;
    msg->msg_controllen -= cmlen;         <--- iff no tail-padding space here ...
  }                                            ... wrap-around

F.e. it will wrap to a length of 18446744073709551612 bytes in case the
receiver passed in msg->msg_controllen of 20 bytes, and the sender
properly transferred 1 fd to the receiver, so that its CMSG_LEN results
in 20 bytes and CMSG_SPACE in 24 bytes.

In case of MSG_CMSG_COMPAT (scm_detach_fds_compat()), I haven't seen an
issue in my tests as alignment seems always on 4 byte boundary. Same
should be in case of native 32 bit, where we end up with 4 byte boundaries
as well.

In practice, passing msg->msg_controllen of 20 to recvmsg() while receiving
a single fd would mean that on successful return, msg->msg_controllen is
being set by the kernel to 24 bytes instead, thus more than the input
buffer advertised. It could f.e. become an issue if such application later
on zeroes or copies the control buffer based on the returned msg->msg_controllen
elsewhere.

Maximum number of fds we can send is a hard upper limit SCM_MAX_FD (253).

Going over the code, it seems like msg->msg_controllen is not being read
after scm_detach_fds() in scm_recv() anymore by the kernel, good!

Relevant recvmsg() handler are unix_dgram_recvmsg() (unix_seqpacket_recvmsg())
and unix_stream_recvmsg(). Both return back to their recvmsg() caller,
and ___sys_recvmsg() places the updated length, that is, new msg_control -
old msg_control pointer into msg->msg_controllen (hence the 24 bytes seen
in the example).

Long time ago, Wei Yongjun fixed something related in commit 1ac70e7ad24a
("[NET]: Fix function put_cmsg() which may cause usr application memory
overflow").

RFC3542, section 20.2. says:

  The fields shown as "XX" are possible padding, between the cmsghdr
  structure and the data, and between the data and the next cmsghdr
  structure, if required by the implementation. While sending an
  application may or may not include padding at the end of last
  ancillary data in msg_controllen and implementations must accept both
  as valid. On receiving a portable application must provide space for
  padding at the end of the last ancillary data as implementations may
  copy out the padding at the end of the control message buffer and
  include it in the received msg_controllen. When recvmsg() is called
  if msg_controllen is too small for all the ancillary data items
  including any trailing padding after the last item an implementation
  may set MSG_CTRUNC.

Since we didn't place MSG_CTRUNC for already quite a long time, just do
the same as in 1ac70e7ad24a to avoid an overflow.

Btw, even man-page author got this wrong :/ See db939c9b26e9 ("cmsg.3: Fix
error in SCM_RIGHTS code sample"). Some people must have copied this (?),
thus it got triggered in the wild (reported several times during boot by
David and HacKurx).

No Fixes tag this time as pre 2002 (that is, pre history tree).

Reported-by: David Sterba <dave@jikos.cz>
Reported-by: HacKurx <hackurx@gmail.com>
Cc: PaX Team <pageexec@freemail.hu>
Cc: Emese Revfy <re.emese@gmail.com>
Cc: Brad Spengler <spender@grsecurity.net>
Cc: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Cc: Eric Dumazet <edumazet@google.com>
Reviewed-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/scm.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/core/scm.c b/net/core/scm.c
index b442e7e..d30eb05 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -306,6 +306,8 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
 			err = put_user(cmlen, &cm->cmsg_len);
 		if (!err) {
 			cmlen = CMSG_SPACE(i*sizeof(int));
+			if (msg->msg_controllen < cmlen)
+				cmlen = msg->msg_controllen;
 			msg->msg_control += cmlen;
 			msg->msg_controllen -= cmlen;
 		}
-- 
2.4.1


From 5069ce31b1d84fe1078a375d9640afaad9ca5239 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Fri, 20 Nov 2015 13:54:19 +0100
Subject: [PATCH 17/23] net: ipmr: fix static mfc/dev leaks on table
 destruction

[ Upstream commit 0e615e9601a15efeeb8942cf7cd4dadba0c8c5a7 ]

When destroying an mrt table the static mfc entries and the static
devices are kept, which leads to devices that can never be destroyed
(because of refcnt taken) and leaked memory, for example:
unreferenced object 0xffff880034c144c0 (size 192):
  comm "mfc-broken", pid 4777, jiffies 4320349055 (age 46001.964s)
  hex dump (first 32 bytes):
    98 53 f0 34 00 88 ff ff 98 53 f0 34 00 88 ff ff  .S.4.....S.4....
    ef 0a 0a 14 01 02 03 04 00 00 00 00 01 00 00 00  ................
  backtrace:
    [<ffffffff815c1b9e>] kmemleak_alloc+0x4e/0xb0
    [<ffffffff811ea6e0>] kmem_cache_alloc+0x190/0x300
    [<ffffffff815931cb>] ip_mroute_setsockopt+0x5cb/0x910
    [<ffffffff8153d575>] do_ip_setsockopt.isra.11+0x105/0xff0
    [<ffffffff8153e490>] ip_setsockopt+0x30/0xa0
    [<ffffffff81564e13>] raw_setsockopt+0x33/0x90
    [<ffffffff814d1e14>] sock_common_setsockopt+0x14/0x20
    [<ffffffff814d0b51>] SyS_setsockopt+0x71/0xc0
    [<ffffffff815cdbf6>] entry_SYSCALL_64_fastpath+0x16/0x7a
    [<ffffffffffffffff>] 0xffffffffffffffff

Make sure that everything is cleaned on netns destruction.

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Reviewed-by: Cong Wang <cwang@twopensource.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ipmr.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index c803458..abc7dbd 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -136,7 +136,7 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
 			      struct mfc_cache *c, struct rtmsg *rtm);
 static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc,
 				 int cmd);
-static void mroute_clean_tables(struct mr_table *mrt);
+static void mroute_clean_tables(struct mr_table *mrt, bool all);
 static void ipmr_expire_process(unsigned long arg);
 
 #ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
@@ -348,7 +348,7 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id)
 static void ipmr_free_table(struct mr_table *mrt)
 {
 	del_timer_sync(&mrt->ipmr_expire_timer);
-	mroute_clean_tables(mrt);
+	mroute_clean_tables(mrt, true);
 	kfree(mrt);
 }
 
@@ -1201,7 +1201,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
  *	Close the multicast socket, and clear the vif tables etc
  */
 
-static void mroute_clean_tables(struct mr_table *mrt)
+static void mroute_clean_tables(struct mr_table *mrt, bool all)
 {
 	int i;
 	LIST_HEAD(list);
@@ -1210,8 +1210,9 @@ static void mroute_clean_tables(struct mr_table *mrt)
 	/* Shut down all active vif entries */
 
 	for (i = 0; i < mrt->maxvif; i++) {
-		if (!(mrt->vif_table[i].flags & VIFF_STATIC))
-			vif_delete(mrt, i, 0, &list);
+		if (!all && (mrt->vif_table[i].flags & VIFF_STATIC))
+			continue;
+		vif_delete(mrt, i, 0, &list);
 	}
 	unregister_netdevice_many(&list);
 
@@ -1219,7 +1220,7 @@ static void mroute_clean_tables(struct mr_table *mrt)
 
 	for (i = 0; i < MFC_LINES; i++) {
 		list_for_each_entry_safe(c, next, &mrt->mfc_cache_array[i], list) {
-			if (c->mfc_flags & MFC_STATIC)
+			if (!all && (c->mfc_flags & MFC_STATIC))
 				continue;
 			list_del_rcu(&c->list);
 			mroute_netlink_event(mrt, c, RTM_DELROUTE);
@@ -1254,7 +1255,7 @@ static void mrtsock_destruct(struct sock *sk)
 						    NETCONFA_IFINDEX_ALL,
 						    net->ipv4.devconf_all);
 			RCU_INIT_POINTER(mrt->mroute_sk, NULL);
-			mroute_clean_tables(mrt);
+			mroute_clean_tables(mrt, false);
 		}
 	}
 	rtnl_unlock();
-- 
2.4.1


From 9864bb362cb834d256d014ec56af69499e11f987 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Fri, 20 Nov 2015 13:54:20 +0100
Subject: [PATCH 18/23] net: ip6mr: fix static mfc/dev leaks on table
 destruction

[ Upstream commit 4c6980462f32b4f282c5d8e5f7ea8070e2937725 ]

Similar to ipv4, when destroying an mrt table the static mfc entries and
the static devices are kept, which leads to devices that can never be
destroyed (because of refcnt taken) and leaked memory. Make sure that
everything is cleaned up on netns destruction.

Fixes: 8229efdaef1e ("netns: ip6mr: enable namespace support in ipv6 multicast forwarding code")
CC: Benjamin Thery <benjamin.thery@bull.net>
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Reviewed-by: Cong Wang <cwang@twopensource.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6mr.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 0d58542..4ca7cdd 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -120,7 +120,7 @@ static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc,
 			      int cmd);
 static int ip6mr_rtm_dumproute(struct sk_buff *skb,
 			       struct netlink_callback *cb);
-static void mroute_clean_tables(struct mr6_table *mrt);
+static void mroute_clean_tables(struct mr6_table *mrt, bool all);
 static void ipmr_expire_process(unsigned long arg);
 
 #ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES
@@ -337,7 +337,7 @@ static struct mr6_table *ip6mr_new_table(struct net *net, u32 id)
 static void ip6mr_free_table(struct mr6_table *mrt)
 {
 	del_timer(&mrt->ipmr_expire_timer);
-	mroute_clean_tables(mrt);
+	mroute_clean_tables(mrt, true);
 	kfree(mrt);
 }
 
@@ -1540,7 +1540,7 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt,
  *	Close the multicast socket, and clear the vif tables etc
  */
 
-static void mroute_clean_tables(struct mr6_table *mrt)
+static void mroute_clean_tables(struct mr6_table *mrt, bool all)
 {
 	int i;
 	LIST_HEAD(list);
@@ -1550,8 +1550,9 @@ static void mroute_clean_tables(struct mr6_table *mrt)
 	 *	Shut down all active vif entries
 	 */
 	for (i = 0; i < mrt->maxvif; i++) {
-		if (!(mrt->vif6_table[i].flags & VIFF_STATIC))
-			mif6_delete(mrt, i, &list);
+		if (!all && (mrt->vif6_table[i].flags & VIFF_STATIC))
+			continue;
+		mif6_delete(mrt, i, &list);
 	}
 	unregister_netdevice_many(&list);
 
@@ -1560,7 +1561,7 @@ static void mroute_clean_tables(struct mr6_table *mrt)
 	 */
 	for (i = 0; i < MFC6_LINES; i++) {
 		list_for_each_entry_safe(c, next, &mrt->mfc6_cache_array[i], list) {
-			if (c->mfc_flags & MFC_STATIC)
+			if (!all && (c->mfc_flags & MFC_STATIC))
 				continue;
 			write_lock_bh(&mrt_lock);
 			list_del(&c->list);
@@ -1623,7 +1624,7 @@ int ip6mr_sk_done(struct sock *sk)
 						     net->ipv6.devconf_all);
 			write_unlock_bh(&mrt_lock);
 
-			mroute_clean_tables(mrt);
+			mroute_clean_tables(mrt, false);
 			err = 0;
 			break;
 		}
-- 
2.4.1


From 09cc45c483d72782e9216fc50ee6fe70d959118e Mon Sep 17 00:00:00 2001
From: Aaro Koskinen <aaro.koskinen@iki.fi>
Date: Sun, 22 Nov 2015 01:08:54 +0200
Subject: [PATCH 19/23] broadcom: fix PHY_ID_BCM5481 entry in the id table

[ Upstream commit 3c25a860d17b7378822f35d8c9141db9507e3beb ]

Commit fcb26ec5b18d ("broadcom: move all PHY_ID's to header")
updated broadcom_tbl to use PHY_IDs, but incorrectly replaced 0x0143bca0
with PHY_ID_BCM5482 (making a duplicate entry, and completely omitting
the original). Fix that.

Fixes: fcb26ec5b18d ("broadcom: move all PHY_ID's to header")
Signed-off-by: Aaro Koskinen <aaro.koskinen@iki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/broadcom.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c
index 854f2c9..64860c0 100644
--- a/drivers/net/phy/broadcom.c
+++ b/drivers/net/phy/broadcom.c
@@ -674,7 +674,7 @@ static struct mdio_device_id __maybe_unused broadcom_tbl[] = {
 	{ PHY_ID_BCM5421, 0xfffffff0 },
 	{ PHY_ID_BCM5461, 0xfffffff0 },
 	{ PHY_ID_BCM5464, 0xfffffff0 },
-	{ PHY_ID_BCM5482, 0xfffffff0 },
+	{ PHY_ID_BCM5481, 0xfffffff0 },
 	{ PHY_ID_BCM5482, 0xfffffff0 },
 	{ PHY_ID_BCM50610, 0xfffffff0 },
 	{ PHY_ID_BCM50610M, 0xfffffff0 },
-- 
2.4.1


From c720f326a09fffa78c2b714d62e6e78d6ed2904f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Michal=20Kube=C4=8Dek?= <mkubecek@suse.cz>
Date: Tue, 24 Nov 2015 15:07:11 +0100
Subject: [PATCH 20/23] ipv6: distinguish frag queues by device for multicast
 and link-local packets

[ Upstream commit 264640fc2c5f4f913db5c73fa3eb1ead2c45e9d7 ]

If a fragmented multicast packet is received on an ethernet device which
has an active macvlan on top of it, each fragment is duplicated and
received both on the underlying device and the macvlan. If some
fragments for macvlan are processed before the whole packet for the
underlying device is reassembled, the "overlapping fragments" test in
ip6_frag_queue() discards the whole fragment queue.

To resolve this, add device ifindex to the search key and require it to
match reassembling multicast packets and packets to link-local
addresses.

Note: similar patch has been already submitted by Yoshifuji Hideaki in

  http://patchwork.ozlabs.org/patch/220979/

but got lost and forgotten for some reason.

Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h                      |  1 +
 net/ipv6/netfilter/nf_conntrack_reasm.c |  5 +++--
 net/ipv6/reassembly.c                   | 10 +++++++---
 3 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 4292929..bc56e8a 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -490,6 +490,7 @@ struct ip6_create_arg {
 	u32 user;
 	const struct in6_addr *src;
 	const struct in6_addr *dst;
+	int iif;
 	u8 ecn;
 };
 
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 6f187c8..d235ed7 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -190,7 +190,7 @@ static void nf_ct_frag6_expire(unsigned long data)
 /* Creation primitives. */
 static inline struct frag_queue *fq_find(struct net *net, __be32 id,
 					 u32 user, struct in6_addr *src,
-					 struct in6_addr *dst, u8 ecn)
+					 struct in6_addr *dst, int iif, u8 ecn)
 {
 	struct inet_frag_queue *q;
 	struct ip6_create_arg arg;
@@ -200,6 +200,7 @@ static inline struct frag_queue *fq_find(struct net *net, __be32 id,
 	arg.user = user;
 	arg.src = src;
 	arg.dst = dst;
+	arg.iif = iif;
 	arg.ecn = ecn;
 
 	local_bh_disable();
@@ -603,7 +604,7 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user)
 	fhdr = (struct frag_hdr *)skb_transport_header(clone);
 
 	fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr,
-		     ip6_frag_ecn(hdr));
+		     skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
 	if (fq == NULL) {
 		pr_debug("Can't find and can't create new queue\n");
 		goto ret_orig;
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 1a157ca..28e72f3 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -108,7 +108,10 @@ bool ip6_frag_match(const struct inet_frag_queue *q, const void *a)
 	return	fq->id == arg->id &&
 		fq->user == arg->user &&
 		ipv6_addr_equal(&fq->saddr, arg->src) &&
-		ipv6_addr_equal(&fq->daddr, arg->dst);
+		ipv6_addr_equal(&fq->daddr, arg->dst) &&
+		(arg->iif == fq->iif ||
+		 !(ipv6_addr_type(arg->dst) & (IPV6_ADDR_MULTICAST |
+					       IPV6_ADDR_LINKLOCAL)));
 }
 EXPORT_SYMBOL(ip6_frag_match);
 
@@ -180,7 +183,7 @@ static void ip6_frag_expire(unsigned long data)
 
 static __inline__ struct frag_queue *
 fq_find(struct net *net, __be32 id, const struct in6_addr *src,
-	const struct in6_addr *dst, u8 ecn)
+	const struct in6_addr *dst, int iif, u8 ecn)
 {
 	struct inet_frag_queue *q;
 	struct ip6_create_arg arg;
@@ -190,6 +193,7 @@ fq_find(struct net *net, __be32 id, const struct in6_addr *src,
 	arg.user = IP6_DEFRAG_LOCAL_DELIVER;
 	arg.src = src;
 	arg.dst = dst;
+	arg.iif = iif;
 	arg.ecn = ecn;
 
 	hash = inet6_hash_frag(id, src, dst);
@@ -550,7 +554,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 	}
 
 	fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr,
-		     ip6_frag_ecn(hdr));
+		     skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
 	if (fq != NULL) {
 		int ret;
 
-- 
2.4.1


From fbb52b8201993be2e0fbe9af7c44ba1c04f9ab3f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 29 Nov 2015 19:37:57 -0800
Subject: [PATCH 21/23] ipv6: add complete rcu protection around np->opt

[ Upstream commit 45f6fad84cc305103b28d73482b344d7f5b76f39 ]

This patch addresses multiple problems :

UDP/RAW sendmsg() need to get a stable struct ipv6_txoptions
while socket is not locked : Other threads can change np->opt
concurrently. Dmitry posted a syzkaller
(http://github.com/google/syzkaller) program desmonstrating
use-after-free.

Starting with TCP/DCCP lockless listeners, tcp_v6_syn_recv_sock()
and dccp_v6_request_recv_sock() also need to use RCU protection
to dereference np->opt once (before calling ipv6_dup_options())

This patch adds full RCU protection to np->opt

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ipv6.h             |  2 +-
 include/net/ipv6.h               | 21 ++++++++++++++++++++-
 net/dccp/ipv6.c                  | 33 +++++++++++++++++++++------------
 net/ipv6/af_inet6.c              | 13 +++++++++----
 net/ipv6/datagram.c              |  4 +++-
 net/ipv6/exthdrs.c               |  3 ++-
 net/ipv6/inet6_connection_sock.c | 11 ++++++++---
 net/ipv6/ipv6_sockglue.c         | 36 ++++++++++++++++++++++++------------
 net/ipv6/raw.c                   |  8 ++++++--
 net/ipv6/syncookies.c            |  2 +-
 net/ipv6/tcp_ipv6.c              | 28 +++++++++++++++++-----------
 net/ipv6/udp.c                   |  8 ++++++--
 net/l2tp/l2tp_ip6.c              |  8 ++++++--
 13 files changed, 124 insertions(+), 53 deletions(-)

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index ff56053..2725b03 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -212,7 +212,7 @@ struct ipv6_pinfo {
 	struct ipv6_ac_socklist	*ipv6_ac_list;
 	struct ipv6_fl_socklist __rcu *ipv6_fl_list;
 
-	struct ipv6_txoptions	*opt;
+	struct ipv6_txoptions __rcu	*opt;
 	struct sk_buff		*pktoptions;
 	struct sk_buff		*rxpmtu;
 	struct {
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index bc56e8a..a5169a4 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -207,6 +207,7 @@ extern rwlock_t ip6_ra_lock;
  */
 
 struct ipv6_txoptions {
+	atomic_t		refcnt;
 	/* Length of this structure */
 	int			tot_len;
 
@@ -219,7 +220,7 @@ struct ipv6_txoptions {
 	struct ipv6_opt_hdr	*dst0opt;
 	struct ipv6_rt_hdr	*srcrt;	/* Routing Header */
 	struct ipv6_opt_hdr	*dst1opt;
-
+	struct rcu_head		rcu;
 	/* Option buffer, as read by IPV6_PKTOPTIONS, starts here. */
 };
 
@@ -252,6 +253,24 @@ struct ipv6_fl_socklist {
 	struct rcu_head			rcu;
 };
 
+static inline struct ipv6_txoptions *txopt_get(const struct ipv6_pinfo *np)
+{
+	struct ipv6_txoptions *opt;
+
+	rcu_read_lock();
+	opt = rcu_dereference(np->opt);
+	if (opt && !atomic_inc_not_zero(&opt->refcnt))
+		opt = NULL;
+	rcu_read_unlock();
+	return opt;
+}
+
+static inline void txopt_put(struct ipv6_txoptions *opt)
+{
+	if (opt && atomic_dec_and_test(&opt->refcnt))
+		kfree_rcu(opt, rcu);
+}
+
 struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label);
 struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space,
 					 struct ip6_flowlabel *fl,
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 6bcaa33..7bcb223 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -238,7 +238,9 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req)
 	security_req_classify_flow(req, flowi6_to_flowi(&fl6));
 
 
-	final_p = fl6_update_dst(&fl6, np->opt, &final);
+	rcu_read_lock();
+	final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final);
+	rcu_read_unlock();
 
 	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
@@ -255,7 +257,10 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req)
 							 &ireq->ir_v6_loc_addr,
 							 &ireq->ir_v6_rmt_addr);
 		fl6.daddr = ireq->ir_v6_rmt_addr;
-		err = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass);
+		rcu_read_lock();
+		err = ip6_xmit(sk, skb, &fl6, rcu_dereference(np->opt),
+			       np->tclass);
+		rcu_read_unlock();
 		err = net_xmit_eval(err);
 	}
 
@@ -450,6 +455,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
 	struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
+	struct ipv6_txoptions *opt;
 	struct inet_sock *newinet;
 	struct dccp6_sock *newdp6;
 	struct sock *newsk;
@@ -573,13 +579,15 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
 	 * Yes, keeping reference count would be much more clever, but we make
 	 * one more one thing there: reattach optmem to newsk.
 	 */
-	if (np->opt != NULL)
-		newnp->opt = ipv6_dup_options(newsk, np->opt);
-
+	opt = rcu_dereference(np->opt);
+	if (opt) {
+		opt = ipv6_dup_options(newsk, opt);
+		RCU_INIT_POINTER(newnp->opt, opt);
+	}
 	inet_csk(newsk)->icsk_ext_hdr_len = 0;
-	if (newnp->opt != NULL)
-		inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen +
-						     newnp->opt->opt_flen);
+	if (opt)
+		inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen +
+						    opt->opt_flen;
 
 	dccp_sync_mss(newsk, dst_mtu(dst));
 
@@ -832,6 +840,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct dccp_sock *dp = dccp_sk(sk);
 	struct in6_addr *saddr = NULL, *final_p, final;
+	struct ipv6_txoptions *opt;
 	struct flowi6 fl6;
 	struct dst_entry *dst;
 	int addr_type;
@@ -933,7 +942,8 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	fl6.fl6_sport = inet->inet_sport;
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
-	final_p = fl6_update_dst(&fl6, np->opt, &final);
+	opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+	final_p = fl6_update_dst(&fl6, opt, &final);
 
 	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
@@ -953,9 +963,8 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	__ip6_dst_store(sk, dst, NULL, NULL);
 
 	icsk->icsk_ext_hdr_len = 0;
-	if (np->opt != NULL)
-		icsk->icsk_ext_hdr_len = (np->opt->opt_flen +
-					  np->opt->opt_nflen);
+	if (opt)
+		icsk->icsk_ext_hdr_len = opt->opt_flen + opt->opt_nflen;
 
 	inet->inet_dport = usin->sin6_port;
 
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index e8c4400..05417c3 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -425,9 +425,11 @@ void inet6_destroy_sock(struct sock *sk)
 
 	/* Free tx options */
 
-	opt = xchg(&np->opt, NULL);
-	if (opt != NULL)
-		sock_kfree_s(sk, opt, opt->tot_len);
+	opt = xchg((__force struct ipv6_txoptions **)&np->opt, NULL);
+	if (opt) {
+		atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+		txopt_put(opt);
+	}
 }
 EXPORT_SYMBOL_GPL(inet6_destroy_sock);
 
@@ -656,7 +658,10 @@ int inet6_sk_rebuild_header(struct sock *sk)
 		fl6.fl6_sport = inet->inet_sport;
 		security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
-		final_p = fl6_update_dst(&fl6, np->opt, &final);
+		rcu_read_lock();
+		final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt),
+					 &final);
+		rcu_read_unlock();
 
 		dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
 		if (IS_ERR(dst)) {
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index e069aeb2..9e3b0b6 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -167,8 +167,10 @@ ipv4_connected:
 
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
-	opt = flowlabel ? flowlabel->opt : np->opt;
+	rcu_read_lock();
+	opt = flowlabel ? flowlabel->opt : rcu_dereference(np->opt);
 	final_p = fl6_update_dst(&fl6, opt, &final);
+	rcu_read_unlock();
 
 	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
 	err = 0;
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index bfde361..4f08a0f 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -727,6 +727,7 @@ ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt)
 			*((char **)&opt2->dst1opt) += dif;
 		if (opt2->srcrt)
 			*((char **)&opt2->srcrt) += dif;
+		atomic_set(&opt2->refcnt, 1);
 	}
 	return opt2;
 }
@@ -790,7 +791,7 @@ ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt,
 		return ERR_PTR(-ENOBUFS);
 
 	memset(opt2, 0, tot_len);
-
+	atomic_set(&opt2->refcnt, 1);
 	opt2->tot_len = tot_len;
 	p = (char *)(opt2 + 1);
 
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 29b3220..6cc516c 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -77,7 +77,9 @@ struct dst_entry *inet6_csk_route_req(struct sock *sk,
 	memset(fl6, 0, sizeof(*fl6));
 	fl6->flowi6_proto = IPPROTO_TCP;
 	fl6->daddr = ireq->ir_v6_rmt_addr;
-	final_p = fl6_update_dst(fl6, np->opt, &final);
+	rcu_read_lock();
+	final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
+	rcu_read_unlock();
 	fl6->saddr = ireq->ir_v6_loc_addr;
 	fl6->flowi6_oif = ireq->ir_iif;
 	fl6->flowi6_mark = ireq->ir_mark;
@@ -208,7 +210,9 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk,
 	fl6->fl6_dport = inet->inet_dport;
 	security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
 
-	final_p = fl6_update_dst(fl6, np->opt, &final);
+	rcu_read_lock();
+	final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
+	rcu_read_unlock();
 
 	dst = __inet6_csk_dst_check(sk, np->dst_cookie);
 	if (!dst) {
@@ -241,7 +245,8 @@ int inet6_csk_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl_unused
 	/* Restore final destination back after routing done */
 	fl6.daddr = sk->sk_v6_daddr;
 
-	res = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass);
+	res = ip6_xmit(sk, skb, &fl6, rcu_dereference(np->opt),
+		       np->tclass);
 	rcu_read_unlock();
 	return res;
 }
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index e1a9583..f81fcc0 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -110,10 +110,12 @@ struct ipv6_txoptions *ipv6_update_options(struct sock *sk,
 			icsk->icsk_ext_hdr_len = opt->opt_flen + opt->opt_nflen;
 			icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie);
 		}
-		opt = xchg(&inet6_sk(sk)->opt, opt);
+		opt = xchg((__force struct ipv6_txoptions **)&inet6_sk(sk)->opt,
+			   opt);
 	} else {
 		spin_lock(&sk->sk_dst_lock);
-		opt = xchg(&inet6_sk(sk)->opt, opt);
+		opt = xchg((__force struct ipv6_txoptions **)&inet6_sk(sk)->opt,
+			   opt);
 		spin_unlock(&sk->sk_dst_lock);
 	}
 	sk_dst_reset(sk);
@@ -213,9 +215,12 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 				sk->sk_socket->ops = &inet_dgram_ops;
 				sk->sk_family = PF_INET;
 			}
-			opt = xchg(&np->opt, NULL);
-			if (opt)
-				sock_kfree_s(sk, opt, opt->tot_len);
+			opt = xchg((__force struct ipv6_txoptions **)&np->opt,
+				   NULL);
+			if (opt) {
+				atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+				txopt_put(opt);
+			}
 			pktopt = xchg(&np->pktoptions, NULL);
 			kfree_skb(pktopt);
 
@@ -385,7 +390,8 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 		if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW))
 			break;
 
-		opt = ipv6_renew_options(sk, np->opt, optname,
+		opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+		opt = ipv6_renew_options(sk, opt, optname,
 					 (struct ipv6_opt_hdr __user *)optval,
 					 optlen);
 		if (IS_ERR(opt)) {
@@ -414,8 +420,10 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 		retv = 0;
 		opt = ipv6_update_options(sk, opt);
 sticky_done:
-		if (opt)
-			sock_kfree_s(sk, opt, opt->tot_len);
+		if (opt) {
+			atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+			txopt_put(opt);
+		}
 		break;
 	}
 
@@ -468,6 +476,7 @@ sticky_done:
 			break;
 
 		memset(opt, 0, sizeof(*opt));
+		atomic_set(&opt->refcnt, 1);
 		opt->tot_len = sizeof(*opt) + optlen;
 		retv = -EFAULT;
 		if (copy_from_user(opt+1, optval, optlen))
@@ -484,8 +493,10 @@ update:
 		retv = 0;
 		opt = ipv6_update_options(sk, opt);
 done:
-		if (opt)
-			sock_kfree_s(sk, opt, opt->tot_len);
+		if (opt) {
+			atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+			txopt_put(opt);
+		}
 		break;
 	}
 	case IPV6_UNICAST_HOPS:
@@ -1092,10 +1103,11 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 	case IPV6_RTHDR:
 	case IPV6_DSTOPTS:
 	{
+		struct ipv6_txoptions *opt;
 
 		lock_sock(sk);
-		len = ipv6_getsockopt_sticky(sk, np->opt,
-					     optname, optval, len);
+		opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+		len = ipv6_getsockopt_sticky(sk, opt, optname, optval, len);
 		release_sock(sk);
 		/* check if ipv6_getsockopt_sticky() returns err code */
 		if (len < 0)
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 896af88..a66a67d 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -735,6 +735,7 @@ static int rawv6_probe_proto_opt(struct flowi6 *fl6, struct msghdr *msg)
 static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 		   struct msghdr *msg, size_t len)
 {
+	struct ipv6_txoptions *opt_to_free = NULL;
 	struct ipv6_txoptions opt_space;
 	DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
 	struct in6_addr *daddr, *final_p, final;
@@ -840,8 +841,10 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 		if (!(opt->opt_nflen|opt->opt_flen))
 			opt = NULL;
 	}
-	if (opt == NULL)
-		opt = np->opt;
+	if (!opt) {
+		opt = txopt_get(np);
+		opt_to_free = opt;
+	}
 	if (flowlabel)
 		opt = fl6_merge_options(&opt_space, flowlabel, opt);
 	opt = ipv6_fixup_options(&opt_space, opt);
@@ -902,6 +905,7 @@ done:
 	dst_release(dst);
 out:
 	fl6_sock_release(flowlabel);
+	txopt_put(opt_to_free);
 	return err < 0 ? err : len;
 do_confirm:
 	dst_confirm(dst);
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 2f25cb6..aa96993 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -241,7 +241,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 		memset(&fl6, 0, sizeof(fl6));
 		fl6.flowi6_proto = IPPROTO_TCP;
 		fl6.daddr = ireq->ir_v6_rmt_addr;
-		final_p = fl6_update_dst(&fl6, np->opt, &final);
+		final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final);
 		fl6.saddr = ireq->ir_v6_loc_addr;
 		fl6.flowi6_oif = sk->sk_bound_dev_if;
 		fl6.flowi6_mark = ireq->ir_mark;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index a3f9f11..26feadd 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -134,6 +134,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct in6_addr *saddr = NULL, *final_p, final;
+	struct ipv6_txoptions *opt;
 	struct rt6_info *rt;
 	struct flowi6 fl6;
 	struct dst_entry *dst;
@@ -253,7 +254,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	fl6.fl6_dport = usin->sin6_port;
 	fl6.fl6_sport = inet->inet_sport;
 
-	final_p = fl6_update_dst(&fl6, np->opt, &final);
+	opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+	final_p = fl6_update_dst(&fl6, opt, &final);
 
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
@@ -282,9 +284,9 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 		tcp_fetch_timewait_stamp(sk, dst);
 
 	icsk->icsk_ext_hdr_len = 0;
-	if (np->opt)
-		icsk->icsk_ext_hdr_len = (np->opt->opt_flen +
-					  np->opt->opt_nflen);
+	if (opt)
+		icsk->icsk_ext_hdr_len = opt->opt_flen +
+					 opt->opt_nflen;
 
 	tp->rx_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
 
@@ -501,7 +503,8 @@ static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst,
 			fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));
 
 		skb_set_queue_mapping(skb, queue_mapping);
-		err = ip6_xmit(sk, skb, fl6, np->opt, np->tclass);
+		err = ip6_xmit(sk, skb, fl6, rcu_dereference(np->opt),
+			       np->tclass);
 		err = net_xmit_eval(err);
 	}
 
@@ -1052,6 +1055,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	struct inet_request_sock *ireq;
 	struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
 	struct tcp6_sock *newtcp6sk;
+	struct ipv6_txoptions *opt;
 	struct inet_sock *newinet;
 	struct tcp_sock *newtp;
 	struct sock *newsk;
@@ -1191,13 +1195,15 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	   but we make one more one thing there: reattach optmem
 	   to newsk.
 	 */
-	if (np->opt)
-		newnp->opt = ipv6_dup_options(newsk, np->opt);
-
+	opt = rcu_dereference(np->opt);
+	if (opt) {
+		opt = ipv6_dup_options(newsk, opt);
+		RCU_INIT_POINTER(newnp->opt, opt);
+	}
 	inet_csk(newsk)->icsk_ext_hdr_len = 0;
-	if (newnp->opt)
-		inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen +
-						     newnp->opt->opt_flen);
+	if (opt)
+		inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen +
+						    opt->opt_flen;
 
 	tcp_sync_mss(newsk, dst_mtu(dst));
 	newtp->advmss = dst_metric_advmss(dst);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index dd530f0..a5ce705 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1082,6 +1082,7 @@ int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 	DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
 	struct in6_addr *daddr, *final_p, final;
 	struct ipv6_txoptions *opt = NULL;
+	struct ipv6_txoptions *opt_to_free = NULL;
 	struct ip6_flowlabel *flowlabel = NULL;
 	struct flowi6 fl6;
 	struct dst_entry *dst;
@@ -1234,8 +1235,10 @@ do_udp_sendmsg:
 			opt = NULL;
 		connected = 0;
 	}
-	if (opt == NULL)
-		opt = np->opt;
+	if (!opt) {
+		opt = txopt_get(np);
+		opt_to_free = opt;
+	}
 	if (flowlabel)
 		opt = fl6_merge_options(&opt_space, flowlabel, opt);
 	opt = ipv6_fixup_options(&opt_space, opt);
@@ -1329,6 +1332,7 @@ do_append_data:
 out:
 	dst_release(dst);
 	fl6_sock_release(flowlabel);
+	txopt_put(opt_to_free);
 	if (!err)
 		return len;
 	/*
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 0edb263..3865882 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -487,6 +487,7 @@ static int l2tp_ip6_sendmsg(struct kiocb *iocb, struct sock *sk,
 	DECLARE_SOCKADDR(struct sockaddr_l2tpip6 *, lsa, msg->msg_name);
 	struct in6_addr *daddr, *final_p, final;
 	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct ipv6_txoptions *opt_to_free = NULL;
 	struct ipv6_txoptions *opt = NULL;
 	struct ip6_flowlabel *flowlabel = NULL;
 	struct dst_entry *dst = NULL;
@@ -576,8 +577,10 @@ static int l2tp_ip6_sendmsg(struct kiocb *iocb, struct sock *sk,
 			opt = NULL;
 	}
 
-	if (opt == NULL)
-		opt = np->opt;
+	if (!opt) {
+		opt = txopt_get(np);
+		opt_to_free = opt;
+	}
 	if (flowlabel)
 		opt = fl6_merge_options(&opt_space, flowlabel, opt);
 	opt = ipv6_fixup_options(&opt_space, opt);
@@ -632,6 +635,7 @@ done:
 	dst_release(dst);
 out:
 	fl6_sock_release(flowlabel);
+	txopt_put(opt_to_free);
 
 	return err < 0 ? err : len;
 
-- 
2.4.1


From 16fd8938cc04d5e56e7ad83d2b79e1c176a53d12 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <koct9i@gmail.com>
Date: Tue, 1 Dec 2015 01:14:48 +0300
Subject: [PATCH 22/23] net/neighbour: fix crash at dumping device-agnostic
 proxy entries

[ Upstream commit 6adc5fd6a142c6e2c80574c1db0c7c17dedaa42e ]

Proxy entries could have null pointer to net-device.

Signed-off-by: Konstantin Khlebnikov <koct9i@gmail.com>
Fixes: 84920c1420e2 ("net: Allow ipv6 proxies and arp proxies be shown with iproute2")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 2b0d99d..0478423 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2263,7 +2263,7 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn,
 	ndm->ndm_pad2    = 0;
 	ndm->ndm_flags	 = pn->flags | NTF_PROXY;
 	ndm->ndm_type	 = RTN_UNICAST;
-	ndm->ndm_ifindex = pn->dev->ifindex;
+	ndm->ndm_ifindex = pn->dev ? pn->dev->ifindex : 0;
 	ndm->ndm_state	 = NUD_NONE;
 
 	if (nla_put(skb, NDA_DST, tbl->key_len, pn->key))
@@ -2337,7 +2337,7 @@ static int pneigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
 		if (h > s_h)
 			s_idx = 0;
 		for (n = tbl->phash_buckets[h], idx = 0; n; n = n->next) {
-			if (dev_net(n->dev) != net)
+			if (pneigh_net(n) != net)
 				continue;
 			if (idx < s_idx)
 				goto next;
-- 
2.4.1


From 98cc05e3c6c475a1c5f329e7d76fd81e0054f62a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 1 Dec 2015 07:20:07 -0800
Subject: [PATCH 23/23] ipv6: sctp: implement sctp_v6_destroy_sock()

[ Upstream commit 602dd62dfbda3e63a2d6a3cbde953ebe82bf5087 ]

Dmitry Vyukov reported a memory leak using IPV6 SCTP sockets.

We need to call inet6_destroy_sock() to properly release
inet6 specific fields.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 99e640c..fb082aa 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -7393,6 +7393,13 @@ struct proto sctp_prot = {
 
 #if IS_ENABLED(CONFIG_IPV6)
 
+#include <net/transp_v6.h>
+static void sctp_v6_destroy_sock(struct sock *sk)
+{
+	sctp_destroy_sock(sk);
+	inet6_destroy_sock(sk);
+}
+
 struct proto sctpv6_prot = {
 	.name		= "SCTPv6",
 	.owner		= THIS_MODULE,
@@ -7402,7 +7409,7 @@ struct proto sctpv6_prot = {
 	.accept		= sctp_accept,
 	.ioctl		= sctp_ioctl,
 	.init		= sctp_init_sock,
-	.destroy	= sctp_destroy_sock,
+	.destroy	= sctp_v6_destroy_sock,
 	.shutdown	= sctp_shutdown,
 	.setsockopt	= sctp_setsockopt,
 	.getsockopt	= sctp_getsockopt,
-- 
2.4.1


[-- Attachment #3: net_41.mbox --]
[-- Type: Application/Octet-Stream, Size: 96593 bytes --]

From 52e9f9c82c084b07a5db10b1b9b425da19c7acc1 Mon Sep 17 00:00:00 2001
From: Rainer Weikusat <rweikusat@mobileactivedefense.com>
Date: Fri, 20 Nov 2015 22:07:23 +0000
Subject: [PATCH 01/26] unix: avoid use-after-free in ep_remove_wait_queue

[ Upstream commit 7d267278a9ece963d77eefec61630223fce08c6c ]

Rainer Weikusat <rweikusat@mobileactivedefense.com> writes:
An AF_UNIX datagram socket being the client in an n:1 association with
some server socket is only allowed to send messages to the server if the
receive queue of this socket contains at most sk_max_ack_backlog
datagrams. This implies that prospective writers might be forced to go
to sleep despite none of the message presently enqueued on the server
receive queue were sent by them. In order to ensure that these will be
woken up once space becomes again available, the present unix_dgram_poll
routine does a second sock_poll_wait call with the peer_wait wait queue
of the server socket as queue argument (unix_dgram_recvmsg does a wake
up on this queue after a datagram was received). This is inherently
problematic because the server socket is only guaranteed to remain alive
for as long as the client still holds a reference to it. In case the
connection is dissolved via connect or by the dead peer detection logic
in unix_dgram_sendmsg, the server socket may be freed despite "the
polling mechanism" (in particular, epoll) still has a pointer to the
corresponding peer_wait queue. There's no way to forcibly deregister a
wait queue with epoll.

Based on an idea by Jason Baron, the patch below changes the code such
that a wait_queue_t belonging to the client socket is enqueued on the
peer_wait queue of the server whenever the peer receive queue full
condition is detected by either a sendmsg or a poll. A wake up on the
peer queue is then relayed to the ordinary wait queue of the client
socket via wake function. The connection to the peer wait queue is again
dissolved if either a wake up is about to be relayed or the client
socket reconnects or a dead peer is detected or the client socket is
itself closed. This enables removing the second sock_poll_wait from
unix_dgram_poll, thus avoiding the use-after-free, while still ensuring
that no blocked writer sleeps forever.

Signed-off-by: Rainer Weikusat <rweikusat@mobileactivedefense.com>
Fixes: ec0d215f9420 ("af_unix: fix 'poll for write'/connected DGRAM sockets")
Reviewed-by: Jason Baron <jbaron@akamai.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/af_unix.h |   1 +
 net/unix/af_unix.c    | 183 ++++++++++++++++++++++++++++++++++++++++++++------
 2 files changed, 165 insertions(+), 19 deletions(-)

diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index dfe4ddf..e830c3d 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -63,6 +63,7 @@ struct unix_sock {
 #define UNIX_GC_CANDIDATE	0
 #define UNIX_GC_MAYBE_CYCLE	1
 	struct socket_wq	peer_wq;
+	wait_queue_t		peer_wake;
 };
 
 static inline struct unix_sock *unix_sk(struct sock *sk)
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 76e6669..1975fd8 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -316,6 +316,118 @@ found:
 	return s;
 }
 
+/* Support code for asymmetrically connected dgram sockets
+ *
+ * If a datagram socket is connected to a socket not itself connected
+ * to the first socket (eg, /dev/log), clients may only enqueue more
+ * messages if the present receive queue of the server socket is not
+ * "too large". This means there's a second writeability condition
+ * poll and sendmsg need to test. The dgram recv code will do a wake
+ * up on the peer_wait wait queue of a socket upon reception of a
+ * datagram which needs to be propagated to sleeping would-be writers
+ * since these might not have sent anything so far. This can't be
+ * accomplished via poll_wait because the lifetime of the server
+ * socket might be less than that of its clients if these break their
+ * association with it or if the server socket is closed while clients
+ * are still connected to it and there's no way to inform "a polling
+ * implementation" that it should let go of a certain wait queue
+ *
+ * In order to propagate a wake up, a wait_queue_t of the client
+ * socket is enqueued on the peer_wait queue of the server socket
+ * whose wake function does a wake_up on the ordinary client socket
+ * wait queue. This connection is established whenever a write (or
+ * poll for write) hit the flow control condition and broken when the
+ * association to the server socket is dissolved or after a wake up
+ * was relayed.
+ */
+
+static int unix_dgram_peer_wake_relay(wait_queue_t *q, unsigned mode, int flags,
+				      void *key)
+{
+	struct unix_sock *u;
+	wait_queue_head_t *u_sleep;
+
+	u = container_of(q, struct unix_sock, peer_wake);
+
+	__remove_wait_queue(&unix_sk(u->peer_wake.private)->peer_wait,
+			    q);
+	u->peer_wake.private = NULL;
+
+	/* relaying can only happen while the wq still exists */
+	u_sleep = sk_sleep(&u->sk);
+	if (u_sleep)
+		wake_up_interruptible_poll(u_sleep, key);
+
+	return 0;
+}
+
+static int unix_dgram_peer_wake_connect(struct sock *sk, struct sock *other)
+{
+	struct unix_sock *u, *u_other;
+	int rc;
+
+	u = unix_sk(sk);
+	u_other = unix_sk(other);
+	rc = 0;
+	spin_lock(&u_other->peer_wait.lock);
+
+	if (!u->peer_wake.private) {
+		u->peer_wake.private = other;
+		__add_wait_queue(&u_other->peer_wait, &u->peer_wake);
+
+		rc = 1;
+	}
+
+	spin_unlock(&u_other->peer_wait.lock);
+	return rc;
+}
+
+static void unix_dgram_peer_wake_disconnect(struct sock *sk,
+					    struct sock *other)
+{
+	struct unix_sock *u, *u_other;
+
+	u = unix_sk(sk);
+	u_other = unix_sk(other);
+	spin_lock(&u_other->peer_wait.lock);
+
+	if (u->peer_wake.private == other) {
+		__remove_wait_queue(&u_other->peer_wait, &u->peer_wake);
+		u->peer_wake.private = NULL;
+	}
+
+	spin_unlock(&u_other->peer_wait.lock);
+}
+
+static void unix_dgram_peer_wake_disconnect_wakeup(struct sock *sk,
+						   struct sock *other)
+{
+	unix_dgram_peer_wake_disconnect(sk, other);
+	wake_up_interruptible_poll(sk_sleep(sk),
+				   POLLOUT |
+				   POLLWRNORM |
+				   POLLWRBAND);
+}
+
+/* preconditions:
+ *	- unix_peer(sk) == other
+ *	- association is stable
+ */
+static int unix_dgram_peer_wake_me(struct sock *sk, struct sock *other)
+{
+	int connected;
+
+	connected = unix_dgram_peer_wake_connect(sk, other);
+
+	if (unix_recvq_full(other))
+		return 1;
+
+	if (connected)
+		unix_dgram_peer_wake_disconnect(sk, other);
+
+	return 0;
+}
+
 static inline int unix_writable(struct sock *sk)
 {
 	return (atomic_read(&sk->sk_wmem_alloc) << 2) <= sk->sk_sndbuf;
@@ -420,6 +532,8 @@ static void unix_release_sock(struct sock *sk, int embrion)
 			skpair->sk_state_change(skpair);
 			sk_wake_async(skpair, SOCK_WAKE_WAITD, POLL_HUP);
 		}
+
+		unix_dgram_peer_wake_disconnect(sk, skpair);
 		sock_put(skpair); /* It may now die */
 		unix_peer(sk) = NULL;
 	}
@@ -648,6 +762,7 @@ static struct sock *unix_create1(struct net *net, struct socket *sock)
 	INIT_LIST_HEAD(&u->link);
 	mutex_init(&u->readlock); /* single task reading lock */
 	init_waitqueue_head(&u->peer_wait);
+	init_waitqueue_func_entry(&u->peer_wake, unix_dgram_peer_wake_relay);
 	unix_insert_socket(unix_sockets_unbound(sk), sk);
 out:
 	if (sk == NULL)
@@ -1015,6 +1130,8 @@ restart:
 	if (unix_peer(sk)) {
 		struct sock *old_peer = unix_peer(sk);
 		unix_peer(sk) = other;
+		unix_dgram_peer_wake_disconnect_wakeup(sk, old_peer);
+
 		unix_state_double_unlock(sk, other);
 
 		if (other != old_peer)
@@ -1453,6 +1570,7 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 	struct scm_cookie scm;
 	int max_level;
 	int data_len = 0;
+	int sk_locked;
 
 	wait_for_unix_gc();
 	err = scm_send(sock, msg, &scm, false);
@@ -1532,12 +1650,14 @@ restart:
 		goto out_free;
 	}
 
+	sk_locked = 0;
 	unix_state_lock(other);
+restart_locked:
 	err = -EPERM;
 	if (!unix_may_send(sk, other))
 		goto out_unlock;
 
-	if (sock_flag(other, SOCK_DEAD)) {
+	if (unlikely(sock_flag(other, SOCK_DEAD))) {
 		/*
 		 *	Check with 1003.1g - what should
 		 *	datagram error
@@ -1545,10 +1665,14 @@ restart:
 		unix_state_unlock(other);
 		sock_put(other);
 
+		if (!sk_locked)
+			unix_state_lock(sk);
+
 		err = 0;
-		unix_state_lock(sk);
 		if (unix_peer(sk) == other) {
 			unix_peer(sk) = NULL;
+			unix_dgram_peer_wake_disconnect_wakeup(sk, other);
+
 			unix_state_unlock(sk);
 
 			unix_dgram_disconnected(sk, other);
@@ -1574,21 +1698,38 @@ restart:
 			goto out_unlock;
 	}
 
-	if (unix_peer(other) != sk && unix_recvq_full(other)) {
-		if (!timeo) {
-			err = -EAGAIN;
-			goto out_unlock;
+	if (unlikely(unix_peer(other) != sk && unix_recvq_full(other))) {
+		if (timeo) {
+			timeo = unix_wait_for_peer(other, timeo);
+
+			err = sock_intr_errno(timeo);
+			if (signal_pending(current))
+				goto out_free;
+
+			goto restart;
 		}
 
-		timeo = unix_wait_for_peer(other, timeo);
+		if (!sk_locked) {
+			unix_state_unlock(other);
+			unix_state_double_lock(sk, other);
+		}
 
-		err = sock_intr_errno(timeo);
-		if (signal_pending(current))
-			goto out_free;
+		if (unix_peer(sk) != other ||
+		    unix_dgram_peer_wake_me(sk, other)) {
+			err = -EAGAIN;
+			sk_locked = 1;
+			goto out_unlock;
+		}
 
-		goto restart;
+		if (!sk_locked) {
+			sk_locked = 1;
+			goto restart_locked;
+		}
 	}
 
+	if (unlikely(sk_locked))
+		unix_state_unlock(sk);
+
 	if (sock_flag(other, SOCK_RCVTSTAMP))
 		__net_timestamp(skb);
 	maybe_add_creds(skb, sock, other);
@@ -1602,6 +1743,8 @@ restart:
 	return len;
 
 out_unlock:
+	if (sk_locked)
+		unix_state_unlock(sk);
 	unix_state_unlock(other);
 out_free:
 	kfree_skb(skb);
@@ -2245,14 +2388,16 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock,
 		return mask;
 
 	writable = unix_writable(sk);
-	other = unix_peer_get(sk);
-	if (other) {
-		if (unix_peer(other) != sk) {
-			sock_poll_wait(file, &unix_sk(other)->peer_wait, wait);
-			if (unix_recvq_full(other))
-				writable = 0;
-		}
-		sock_put(other);
+	if (writable) {
+		unix_state_lock(sk);
+
+		other = unix_peer(sk);
+		if (other && unix_peer(other) != sk &&
+		    unix_recvq_full(other) &&
+		    unix_dgram_peer_wake_me(sk, other))
+			writable = 0;
+
+		unix_state_unlock(sk);
 	}
 
 	if (writable)
-- 
2.4.1


From ef3a10fb9d2cc82cbd2d66bfc1c19ffbd027e0bb Mon Sep 17 00:00:00 2001
From: Kamal Mostafa <kamal@canonical.com>
Date: Wed, 11 Nov 2015 14:24:27 -0800
Subject: [PATCH 02/26] tools/net: Use include/uapi with __EXPORTED_HEADERS__

[ Upstream commit d7475de58575c904818efa369c82e88c6648ce2e ]

Use the local uapi headers to keep in sync with "recently" added #define's
(e.g. SKF_AD_VLAN_TPID).  Refactored CFLAGS, and bpf_asm doesn't need -I.

Fixes: 3f356385e8a4 ("filter: bpf_asm: add minimal bpf asm tool")
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/net/Makefile | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/tools/net/Makefile b/tools/net/Makefile
index ee577ea..ddf8880 100644
--- a/tools/net/Makefile
+++ b/tools/net/Makefile
@@ -4,6 +4,9 @@ CC = gcc
 LEX = flex
 YACC = bison
 
+CFLAGS += -Wall -O2
+CFLAGS += -D__EXPORTED_HEADERS__ -I../../include/uapi -I../../include
+
 %.yacc.c: %.y
 	$(YACC) -o $@ -d $<
 
@@ -12,15 +15,13 @@ YACC = bison
 
 all : bpf_jit_disasm bpf_dbg bpf_asm
 
-bpf_jit_disasm : CFLAGS = -Wall -O2 -DPACKAGE='bpf_jit_disasm'
+bpf_jit_disasm : CFLAGS += -DPACKAGE='bpf_jit_disasm'
 bpf_jit_disasm : LDLIBS = -lopcodes -lbfd -ldl
 bpf_jit_disasm : bpf_jit_disasm.o
 
-bpf_dbg : CFLAGS = -Wall -O2
 bpf_dbg : LDLIBS = -lreadline
 bpf_dbg : bpf_dbg.o
 
-bpf_asm : CFLAGS = -Wall -O2 -I.
 bpf_asm : LDLIBS =
 bpf_asm : bpf_asm.o bpf_exp.yacc.o bpf_exp.lex.o
 bpf_exp.lex.o : bpf_exp.yacc.c
-- 
2.4.1


From e87cb0b0a67f28e45f222bfc6098c139874e4152 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 11 Nov 2015 23:25:40 +0100
Subject: [PATCH 03/26] packet: do skb_probe_transport_header when we actually
 have data

[ Upstream commit efdfa2f7848f64517008136fb41f53c4a1faf93a ]

In tpacket_fill_skb() commit c1aad275b029 ("packet: set transport
header before doing xmit") and later on 40893fd0fd4e ("net: switch
to use skb_probe_transport_header()") was probing for a transport
header on the skb from a ring buffer slot, but at a time, where
the skb has _not even_ been filled with data yet. So that call into
the flow dissector is pretty useless. Lets do it after we've set
up the skb frags.

Fixes: c1aad275b029 ("packet: set transport header before doing xmit")
Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 686e601..16a8b37 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2151,8 +2151,6 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 	skb_reserve(skb, hlen);
 	skb_reset_network_header(skb);
 
-	if (!packet_use_direct_xmit(po))
-		skb_probe_transport_header(skb, 0);
 	if (unlikely(po->tp_tx_has_off)) {
 		int off_min, off_max, off;
 		off_min = po->tp_hdrlen - sizeof(struct sockaddr_ll);
@@ -2232,6 +2230,9 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 		len = ((to_write > len_max) ? len_max : to_write);
 	}
 
+	if (!packet_use_direct_xmit(po))
+		skb_probe_transport_header(skb, 0);
+
 	return tp_len;
 }
 
-- 
2.4.1


From 5126f386276510bc7718663f79da3a6844940ea7 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 11 Nov 2015 23:25:41 +0100
Subject: [PATCH 04/26] packet: always probe for transport header

[ Upstream commit 8fd6c80d9dd938ca338c70698533a7e304752846 ]

We concluded that the skb_probe_transport_header() should better be
called unconditionally. Avoiding the call into the flow dissector has
also not really much to do with the direct xmit mode.

While it seems that only virtio_net code makes use of GSO from non
RX/TX ring packet socket paths, we should probe for a transport header
nevertheless before they hit devices.

Reference: http://thread.gmane.org/gmane.linux.network/386173/
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 16a8b37..313119c 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2230,8 +2230,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 		len = ((to_write > len_max) ? len_max : to_write);
 	}
 
-	if (!packet_use_direct_xmit(po))
-		skb_probe_transport_header(skb, 0);
+	skb_probe_transport_header(skb, 0);
 
 	return tp_len;
 }
@@ -2583,8 +2582,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		len += vnet_hdr_len;
 	}
 
-	if (!packet_use_direct_xmit(po))
-		skb_probe_transport_header(skb, reserve);
+	skb_probe_transport_header(skb, reserve);
+
 	if (unlikely(extra_len == 4))
 		skb->no_fcs = 1;
 
-- 
2.4.1


From e60dfaba288b160759d0a28919c3129f68618218 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 11 Nov 2015 23:25:42 +0100
Subject: [PATCH 05/26] packet: only allow extra vlan len on ethernet devices

[ Upstream commit 3c70c132488794e2489ab045559b0ce0afcf17de ]

Packet sockets can be used by various net devices and are not
really restricted to ARPHRD_ETHER device types. However, when
currently checking for the extra 4 bytes that can be transmitted
in VLAN case, our assumption is that we generally probe on
ARPHRD_ETHER devices. Therefore, before looking into Ethernet
header, check the device type first.

This also fixes the issue where non-ARPHRD_ETHER devices could
have no dev->hard_header_len in TX_RING SOCK_RAW case, and thus
the check would test unfilled linear part of the skb (instead
of non-linear).

Fixes: 57f89bfa2140 ("network: Allow af_packet to transmit +4 bytes for VLAN packets.")
Fixes: 52f1454f629f ("packet: allow to transmit +4 byte in TX_RING slot for VLAN case")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 60 +++++++++++++++++++++-----------------------------
 1 file changed, 25 insertions(+), 35 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 313119c..36ece6f 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1524,6 +1524,20 @@ static void fanout_release(struct sock *sk)
 	mutex_unlock(&fanout_mutex);
 }
 
+static bool packet_extra_vlan_len_allowed(const struct net_device *dev,
+					  struct sk_buff *skb)
+{
+	/* Earlier code assumed this would be a VLAN pkt, double-check
+	 * this now that we have the actual packet in hand. We can only
+	 * do this check on Ethernet devices.
+	 */
+	if (unlikely(dev->type != ARPHRD_ETHER))
+		return false;
+
+	skb_reset_mac_header(skb);
+	return likely(eth_hdr(skb)->h_proto == htons(ETH_P_8021Q));
+}
+
 static const struct proto_ops packet_ops;
 
 static const struct proto_ops packet_ops_spkt;
@@ -1685,18 +1699,10 @@ retry:
 		goto retry;
 	}
 
-	if (len > (dev->mtu + dev->hard_header_len + extra_len)) {
-		/* Earlier code assumed this would be a VLAN pkt,
-		 * double-check this now that we have the actual
-		 * packet in hand.
-		 */
-		struct ethhdr *ehdr;
-		skb_reset_mac_header(skb);
-		ehdr = eth_hdr(skb);
-		if (ehdr->h_proto != htons(ETH_P_8021Q)) {
-			err = -EMSGSIZE;
-			goto out_unlock;
-		}
+	if (len > (dev->mtu + dev->hard_header_len + extra_len) &&
+	    !packet_extra_vlan_len_allowed(dev, skb)) {
+		err = -EMSGSIZE;
+		goto out_unlock;
 	}
 
 	skb->protocol = proto;
@@ -2308,18 +2314,10 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 		tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto,
 					  addr, hlen);
 		if (likely(tp_len >= 0) &&
-		    tp_len > dev->mtu + dev->hard_header_len) {
-			struct ethhdr *ehdr;
-			/* Earlier code assumed this would be a VLAN pkt,
-			 * double-check this now that we have the actual
-			 * packet in hand.
-			 */
+		    tp_len > dev->mtu + dev->hard_header_len &&
+		    !packet_extra_vlan_len_allowed(dev, skb))
+			tp_len = -EMSGSIZE;
 
-			skb_reset_mac_header(skb);
-			ehdr = eth_hdr(skb);
-			if (ehdr->h_proto != htons(ETH_P_8021Q))
-				tp_len = -EMSGSIZE;
-		}
 		if (unlikely(tp_len < 0)) {
 			if (po->tp_loss) {
 				__packet_set_status(po, ph,
@@ -2540,18 +2538,10 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 
 	sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags);
 
-	if (!gso_type && (len > dev->mtu + reserve + extra_len)) {
-		/* Earlier code assumed this would be a VLAN pkt,
-		 * double-check this now that we have the actual
-		 * packet in hand.
-		 */
-		struct ethhdr *ehdr;
-		skb_reset_mac_header(skb);
-		ehdr = eth_hdr(skb);
-		if (ehdr->h_proto != htons(ETH_P_8021Q)) {
-			err = -EMSGSIZE;
-			goto out_free;
-		}
+	if (!gso_type && (len > dev->mtu + reserve + extra_len) &&
+	    !packet_extra_vlan_len_allowed(dev, skb)) {
+		err = -EMSGSIZE;
+		goto out_free;
 	}
 
 	skb->protocol = proto;
-- 
2.4.1


From cadb1e319d6698f99d8559c50174c8479a233033 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 11 Nov 2015 23:25:43 +0100
Subject: [PATCH 06/26] packet: infer protocol from ethernet header if unset

[ Upstream commit c72219b75fde768efccf7666342282fab7f9e4e7 ]

In case no struct sockaddr_ll has been passed to packet
socket's sendmsg() when doing a TX_RING flush run, then
skb->protocol is set to po->num instead, which is the protocol
passed via socket(2)/bind(2).

Applications only xmitting can go the path of allocating the
socket as socket(PF_PACKET, <mode>, 0) and do a bind(2) on the
TX_RING with sll_protocol of 0. That way, register_prot_hook()
is neither called on creation nor on bind time, which saves
cycles when there's no interest in capturing anyway.

That leaves us however with po->num 0 instead and therefore
the TX_RING flush run sets skb->protocol to 0 as well. Eric
reported that this leads to problems when using tools like
trafgen over bonding device. I.e. the bonding's hash function
could invoke the kernel's flow dissector, which depends on
skb->protocol being properly set. In the current situation, all
the traffic is then directed to a single slave.

Fix it up by inferring skb->protocol from the Ethernet header
when not set and we have ARPHRD_ETHER device type. This is only
done in case of SOCK_RAW and where we have a dev->hard_header_len
length. In case of ARPHRD_ETHER devices, this is guaranteed to
cover ETH_HLEN, and therefore being accessed on the skb after
the skb_store_bits().

Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 36ece6f..2d83124 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2121,6 +2121,15 @@ static bool ll_header_truncated(const struct net_device *dev, int len)
 	return false;
 }
 
+static void tpacket_set_protocol(const struct net_device *dev,
+				 struct sk_buff *skb)
+{
+	if (dev->type == ARPHRD_ETHER) {
+		skb_reset_mac_header(skb);
+		skb->protocol = eth_hdr(skb)->h_proto;
+	}
+}
+
 static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 		void *frame, struct net_device *dev, int size_max,
 		__be16 proto, unsigned char *addr, int hlen)
@@ -2202,6 +2211,8 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 				dev->hard_header_len);
 		if (unlikely(err))
 			return err;
+		if (!skb->protocol)
+			tpacket_set_protocol(dev, skb);
 
 		data += dev->hard_header_len;
 		to_write -= dev->hard_header_len;
-- 
2.4.1


From 4a3ccd6a25c83e2a184e465ef62d7a9e4dae9024 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 11 Nov 2015 23:25:44 +0100
Subject: [PATCH 07/26] packet: fix tpacket_snd max frame len

[ Upstream commit 5cfb4c8d05b4409c4044cb9c05b19705c1d9818b ]

Since it's introduction in commit 69e3c75f4d54 ("net: TX_RING and
packet mmap"), TX_RING could be used from SOCK_DGRAM and SOCK_RAW
side. When used with SOCK_DGRAM only, the size_max > dev->mtu +
reserve check should have reserve as 0, but currently, this is
unconditionally set (in it's original form as dev->hard_header_len).

I think this is not correct since tpacket_fill_skb() would then
take dev->mtu and dev->hard_header_len into account for SOCK_DGRAM,
the extra VLAN_HLEN could be possible in both cases. Presumably, the
reserve code was copied from packet_snd(), but later on missed the
check. Make it similar as we have it in packet_snd().

Fixes: 69e3c75f4d54 ("net: TX_RING and packet mmap")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 2d83124..ebc39e6 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2293,12 +2293,13 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 	if (unlikely(!(dev->flags & IFF_UP)))
 		goto out_put;
 
-	reserve = dev->hard_header_len + VLAN_HLEN;
+	if (po->sk.sk_socket->type == SOCK_RAW)
+		reserve = dev->hard_header_len;
 	size_max = po->tx_ring.frame_size
 		- (po->tp_hdrlen - sizeof(struct sockaddr_ll));
 
-	if (size_max > dev->mtu + reserve)
-		size_max = dev->mtu + reserve;
+	if (size_max > dev->mtu + reserve + VLAN_HLEN)
+		size_max = dev->mtu + reserve + VLAN_HLEN;
 
 	do {
 		ph = packet_current_frame(po, &po->tx_ring,
@@ -2325,7 +2326,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 		tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto,
 					  addr, hlen);
 		if (likely(tp_len >= 0) &&
-		    tp_len > dev->mtu + dev->hard_header_len &&
+		    tp_len > dev->mtu + reserve &&
 		    !packet_extra_vlan_len_allowed(dev, skb))
 			tp_len = -EMSGSIZE;
 
-- 
2.4.1


From 343ed7e573ba1b74599c602fcb885ea205b2fc34 Mon Sep 17 00:00:00 2001
From: lucien <lucien.xin@gmail.com>
Date: Thu, 12 Nov 2015 13:07:07 +0800
Subject: [PATCH 08/26] sctp: translate host order to network order when
 setting a hmacid

[ Upstream commit ed5a377d87dc4c87fb3e1f7f698cba38cd893103 ]

now sctp auth cannot work well when setting a hmacid manually, which
is caused by that we didn't use the network order for hmacid, so fix
it by adding the transformation in sctp_auth_ep_set_hmacs.

even we set hmacid with the network order in userspace, it still
can't work, because of this condition in sctp_auth_ep_set_hmacs():

		if (id > SCTP_AUTH_HMAC_ID_MAX)
			return -EOPNOTSUPP;

so this wasn't working before and thus it won't break compatibility.

Fixes: 65b07e5d0d09 ("[SCTP]: API updates to suport SCTP-AUTH extensions.")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/auth.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sctp/auth.c b/net/sctp/auth.c
index 4f15b7d..1543e39 100644
--- a/net/sctp/auth.c
+++ b/net/sctp/auth.c
@@ -809,8 +809,8 @@ int sctp_auth_ep_set_hmacs(struct sctp_endpoint *ep,
 	if (!has_sha1)
 		return -EINVAL;
 
-	memcpy(ep->auth_hmacs_list->hmac_ids, &hmacs->shmac_idents[0],
-		hmacs->shmac_num_idents * sizeof(__u16));
+	for (i = 0; i < hmacs->shmac_num_idents; i++)
+		ep->auth_hmacs_list->hmac_ids[i] = htons(hmacs->shmac_idents[i]);
 	ep->auth_hmacs_list->param_hdr.length = htons(sizeof(sctp_paramhdr_t) +
 				hmacs->shmac_num_idents * sizeof(__u16));
 	return 0;
-- 
2.4.1


From 19478f73760e789ae70cd246d9c6aff87774d479 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Thu, 12 Nov 2015 17:35:58 +0100
Subject: [PATCH 09/26] ip_tunnel: disable preemption when updating per-cpu
 tstats

[ Upstream commit b4fe85f9c9146f60457e9512fb6055e69e6a7a65 ]

Drivers like vxlan use the recently introduced
udp_tunnel_xmit_skb/udp_tunnel6_xmit_skb APIs. udp_tunnel6_xmit_skb
makes use of ip6tunnel_xmit, and ip6tunnel_xmit, after sending the
packet, updates the struct stats using the usual
u64_stats_update_begin/end calls on this_cpu_ptr(dev->tstats).
udp_tunnel_xmit_skb makes use of iptunnel_xmit, which doesn't touch
tstats, so drivers like vxlan, immediately after, call
iptunnel_xmit_stats, which does the same thing - calls
u64_stats_update_begin/end on this_cpu_ptr(dev->tstats).

While vxlan is probably fine (I don't know?), calling a similar function
from, say, an unbound workqueue, on a fully preemptable kernel causes
real issues:

[  188.434537] BUG: using smp_processor_id() in preemptible [00000000] code: kworker/u8:0/6
[  188.435579] caller is debug_smp_processor_id+0x17/0x20
[  188.435583] CPU: 0 PID: 6 Comm: kworker/u8:0 Not tainted 4.2.6 #2
[  188.435607] Call Trace:
[  188.435611]  [<ffffffff8234e936>] dump_stack+0x4f/0x7b
[  188.435615]  [<ffffffff81915f3d>] check_preemption_disabled+0x19d/0x1c0
[  188.435619]  [<ffffffff81915f77>] debug_smp_processor_id+0x17/0x20

The solution would be to protect the whole
this_cpu_ptr(dev->tstats)/u64_stats_update_begin/end blocks with
disabling preemption and then reenabling it.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_tunnel.h | 3 ++-
 include/net/ip_tunnels.h | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index b8529aa..b0f7445 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -83,11 +83,12 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb,
 	err = ip6_local_out_sk(sk, skb);
 
 	if (net_xmit_eval(err) == 0) {
-		struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
+		struct pcpu_sw_netstats *tstats = get_cpu_ptr(dev->tstats);
 		u64_stats_update_begin(&tstats->syncp);
 		tstats->tx_bytes += pkt_len;
 		tstats->tx_packets++;
 		u64_stats_update_end(&tstats->syncp);
+		put_cpu_ptr(tstats);
 	} else {
 		stats->tx_errors++;
 		stats->tx_aborted_errors++;
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index d8214cb..9c2897e 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -207,12 +207,13 @@ static inline void iptunnel_xmit_stats(int err,
 				       struct pcpu_sw_netstats __percpu *stats)
 {
 	if (err > 0) {
-		struct pcpu_sw_netstats *tstats = this_cpu_ptr(stats);
+		struct pcpu_sw_netstats *tstats = get_cpu_ptr(stats);
 
 		u64_stats_update_begin(&tstats->syncp);
 		tstats->tx_bytes += err;
 		tstats->tx_packets++;
 		u64_stats_update_end(&tstats->syncp);
+		put_cpu_ptr(tstats);
 	} else if (err < 0) {
 		err_stats->tx_errors++;
 		err_stats->tx_aborted_errors++;
-- 
2.4.1


From 31bef771ad862f6acc3205416f7bdfc7ca3da12d Mon Sep 17 00:00:00 2001
From: Neil Horman <nhorman@tuxdriver.com>
Date: Mon, 16 Nov 2015 13:09:10 -0500
Subject: [PATCH 10/26] snmp: Remove duplicate OUTMCAST stat increment

[ Upstream commit 41033f029e393a64e81966cbe34d66c6cf8a2e7e ]

the OUTMCAST stat is double incremented, getting bumped once in the mcast code
itself, and again in the common ip output path.  Remove the mcast bump, as its
not needed

Validated by the reporter, with good results

Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Reported-by: Claus Jensen <claus.jensen@microsemi.com>
CC: Claus Jensen <claus.jensen@microsemi.com>
CC: David Miller <davem@davemloft.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/mcast.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 083b292..41e3b5e 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1651,7 +1651,6 @@ out:
 	if (!err) {
 		ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT);
 		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
-		IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, payload_len);
 	} else {
 		IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
 	}
@@ -2014,7 +2013,6 @@ out:
 	if (!err) {
 		ICMP6MSGOUT_INC_STATS(net, idev, type);
 		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
-		IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, full_len);
 	} else
 		IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
 
-- 
2.4.1


From d36c2376c2fa9d959e761ad554387e15bb71036c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Wed, 18 Nov 2015 21:13:07 +0100
Subject: [PATCH 11/26] net: qmi_wwan: add XS Stick W100-2 from 4G Systems
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 68242a5a1e2edce39b069385cbafb82304eac0f1 ]

Thomas reports
"
4gsystems sells two total different LTE-surfsticks under the same name.
..
The newer version of XS Stick W100 is from "omega"
..
Under windows the driver switches to the same ID, and uses MI03\6 for
network and MI01\6 for modem.
..
echo "1c9e 9b01" > /sys/bus/usb/drivers/qmi_wwan/new_id
echo "1c9e 9b01" > /sys/bus/usb-serial/drivers/option1/new_id

T:  Bus=01 Lev=01 Prnt=01 Port=03 Cnt=01 Dev#=  4 Spd=480 MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1c9e ProdID=9b01 Rev=02.32
S:  Manufacturer=USB Modem
S:  Product=USB Modem
S:  SerialNumber=
C:  #Ifs= 5 Cfg#= 1 Atr=80 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
I:  If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
I:  If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
I:  If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
I:  If#= 4 Alt= 0 #EPs= 2 Cls=08(stor.) Sub=06 Prot=50 Driver=usb-storage

Now all important things are there:

wwp0s29f7u2i3 (net), ttyUSB2 (at), cdc-wdm0 (qmi), ttyUSB1 (at)

There is also ttyUSB0, but it is not usable, at least not for at.

The device works well with qmi and ModemManager-NetworkManager.
"

Reported-by: Thomas Schäfer <tschaefer@t-online.de>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 4e0470d..71190dc 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -774,6 +774,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x2357, 0x9000, 4)},	/* TP-LINK MA260 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)},	/* Telit LE920 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1201, 2)},	/* Telit LE920 */
+	{QMI_FIXED_INTF(0x1c9e, 0x9b01, 3)},	/* XS Stick W100-2 from 4G Systems */
 	{QMI_FIXED_INTF(0x0b3c, 0xc000, 4)},	/* Olivetti Olicard 100 */
 	{QMI_FIXED_INTF(0x0b3c, 0xc001, 4)},	/* Olivetti Olicard 120 */
 	{QMI_FIXED_INTF(0x0b3c, 0xc002, 4)},	/* Olivetti Olicard 140 */
-- 
2.4.1


From 16a11a50ac4f185f0edbfe29047e18f3cbdc8bf9 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 18 Nov 2015 12:40:13 -0800
Subject: [PATCH 12/26] tcp: md5: fix lockdep annotation

[ Upstream commit 1b8e6a01e19f001e9f93b39c32387961c91ed3cc ]

When a passive TCP is created, we eventually call tcp_md5_do_add()
with sk pointing to the child. It is not owner by the user yet (we
will add this socket into listener accept queue a bit later anyway)

But we do own the spinlock, so amend the lockdep annotation to avoid
following splat :

[ 8451.090932] net/ipv4/tcp_ipv4.c:923 suspicious rcu_dereference_protected() usage!
[ 8451.090932]
[ 8451.090932] other info that might help us debug this:
[ 8451.090932]
[ 8451.090934]
[ 8451.090934] rcu_scheduler_active = 1, debug_locks = 1
[ 8451.090936] 3 locks held by socket_sockopt_/214795:
[ 8451.090936]  #0:  (rcu_read_lock){.+.+..}, at: [<ffffffff855c6ac1>] __netif_receive_skb_core+0x151/0xe90
[ 8451.090947]  #1:  (rcu_read_lock){.+.+..}, at: [<ffffffff85618143>] ip_local_deliver_finish+0x43/0x2b0
[ 8451.090952]  #2:  (slock-AF_INET){+.-...}, at: [<ffffffff855acda5>] sk_clone_lock+0x1c5/0x500
[ 8451.090958]
[ 8451.090958] stack backtrace:
[ 8451.090960] CPU: 7 PID: 214795 Comm: socket_sockopt_

[ 8451.091215] Call Trace:
[ 8451.091216]  <IRQ>  [<ffffffff856fb29c>] dump_stack+0x55/0x76
[ 8451.091229]  [<ffffffff85123b5b>] lockdep_rcu_suspicious+0xeb/0x110
[ 8451.091235]  [<ffffffff8564544f>] tcp_md5_do_add+0x1bf/0x1e0
[ 8451.091239]  [<ffffffff85645751>] tcp_v4_syn_recv_sock+0x1f1/0x4c0
[ 8451.091242]  [<ffffffff85642b27>] ? tcp_v4_md5_hash_skb+0x167/0x190
[ 8451.091246]  [<ffffffff85647c78>] tcp_check_req+0x3c8/0x500
[ 8451.091249]  [<ffffffff856451ae>] ? tcp_v4_inbound_md5_hash+0x11e/0x190
[ 8451.091253]  [<ffffffff85647170>] tcp_v4_rcv+0x3c0/0x9f0
[ 8451.091256]  [<ffffffff85618143>] ? ip_local_deliver_finish+0x43/0x2b0
[ 8451.091260]  [<ffffffff856181b6>] ip_local_deliver_finish+0xb6/0x2b0
[ 8451.091263]  [<ffffffff85618143>] ? ip_local_deliver_finish+0x43/0x2b0
[ 8451.091267]  [<ffffffff85618d38>] ip_local_deliver+0x48/0x80
[ 8451.091270]  [<ffffffff85618510>] ip_rcv_finish+0x160/0x700
[ 8451.091273]  [<ffffffff8561900e>] ip_rcv+0x29e/0x3d0
[ 8451.091277]  [<ffffffff855c74b7>] __netif_receive_skb_core+0xb47/0xe90

Fixes: a8afca0329988 ("tcp: md5: protects md5sig_info with RCU")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 441ca6f..88203e7 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -922,7 +922,8 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
 	}
 
 	md5sig = rcu_dereference_protected(tp->md5sig_info,
-					   sock_owned_by_user(sk));
+					   sock_owned_by_user(sk) ||
+					   lockdep_is_held(&sk->sk_lock.slock));
 	if (!md5sig) {
 		md5sig = kmalloc(sizeof(*md5sig), gfp);
 		if (!md5sig)
-- 
2.4.1


From 36198366b533871e8796a4a9e0c6e0de7d017b04 Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Wed, 18 Nov 2015 18:17:30 -0800
Subject: [PATCH 13/26] tcp: disable Fast Open on timeouts after handshake

[ Upstream commit 0e45f4da5981895e885dd72fe912a3f8e32bae73 ]

Some middle-boxes black-hole the data after the Fast Open handshake
(https://www.ietf.org/proceedings/94/slides/slides-94-tcpm-13.pdf).
The exact reason is unknown. The work-around is to disable Fast Open
temporarily after multiple recurring timeouts with few or no data
delivered in the established state.

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Christoph Paasch <cpaasch@apple.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_timer.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 8c65dc1..c8f9785 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -176,6 +176,18 @@ static int tcp_write_timeout(struct sock *sk)
 		syn_set = true;
 	} else {
 		if (retransmits_timed_out(sk, sysctl_tcp_retries1, 0, 0)) {
+			/* Some middle-boxes may black-hole Fast Open _after_
+			 * the handshake. Therefore we conservatively disable
+			 * Fast Open on this path on recurring timeouts with
+			 * few or zero bytes acked after Fast Open.
+			 */
+			if (tp->syn_data_acked &&
+			    tp->bytes_acked <= tp->rx_opt.mss_clamp) {
+				tcp_fastopen_cache_set(sk, 0, NULL, true, 0);
+				if (icsk->icsk_retransmits == sysctl_tcp_retries1)
+					NET_INC_STATS_BH(sock_net(sk),
+							 LINUX_MIB_TCPFASTOPENACTIVEFAIL);
+			}
 			/* Black hole detection */
 			tcp_mtu_probing(icsk, sk);
 
-- 
2.4.1


From 77dce63294f13dc8ff12d1417b93aaf80f764f1d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 18 Nov 2015 21:03:33 -0800
Subject: [PATCH 14/26] tcp: fix potential huge kmalloc() calls in TCP_REPAIR

[ Upstream commit 5d4c9bfbabdb1d497f21afd81501e5c54b0c85d9 ]

tcp_send_rcvq() is used for re-injecting data into tcp receive queue.

Problems :

- No check against size is performed, allowed user to fool kernel in
  attempting very large memory allocations, eventually triggering
  OOM when memory is fragmented.

- In case of fault during the copy we do not return correct errno.

Lets use alloc_skb_with_frags() to cook optimal skbs.

Fixes: 292e8d8c8538 ("tcp: Move rcvq sending to tcp_input.c")
Fixes: c0e88ff0f256 ("tcp: Repair socket queues")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 22 +++++++++++++++++++---
 1 file changed, 19 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index c9ab964..7b1fc95 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4438,19 +4438,34 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int
 int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
 {
 	struct sk_buff *skb;
+	int err = -ENOMEM;
+	int data_len = 0;
 	bool fragstolen;
 
 	if (size == 0)
 		return 0;
 
-	skb = alloc_skb(size, sk->sk_allocation);
+	if (size > PAGE_SIZE) {
+		int npages = min_t(size_t, size >> PAGE_SHIFT, MAX_SKB_FRAGS);
+
+		data_len = npages << PAGE_SHIFT;
+		size = data_len + (size & ~PAGE_MASK);
+	}
+	skb = alloc_skb_with_frags(size - data_len, data_len,
+				   PAGE_ALLOC_COSTLY_ORDER,
+				   &err, sk->sk_allocation);
 	if (!skb)
 		goto err;
 
+	skb_put(skb, size - data_len);
+	skb->data_len = data_len;
+	skb->len = size;
+
 	if (tcp_try_rmem_schedule(sk, skb, skb->truesize))
 		goto err_free;
 
-	if (memcpy_from_msg(skb_put(skb, size), msg, size))
+	err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size);
+	if (err)
 		goto err_free;
 
 	TCP_SKB_CB(skb)->seq = tcp_sk(sk)->rcv_nxt;
@@ -4466,7 +4481,8 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
 err_free:
 	kfree_skb(skb);
 err:
-	return -ENOMEM;
+	return err;
+
 }
 
 static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
-- 
2.4.1


From 58b66513bb8135193c2a3e0dce4afdec229eeb97 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 26 Nov 2015 08:18:14 -0800
Subject: [PATCH 15/26] tcp: initialize tp->copied_seq in case of cross SYN
 connection

[ Upstream commit 142a2e7ece8d8ac0e818eb2c91f99ca894730e2a ]

Dmitry provided a syzkaller (http://github.com/google/syzkaller)
generated program that triggers the WARNING at
net/ipv4/tcp.c:1729 in tcp_recvmsg() :

WARN_ON(tp->copied_seq != tp->rcv_nxt &&
        !(flags & (MSG_PEEK | MSG_TRUNC)));

His program is specifically attempting a Cross SYN TCP exchange,
that we support (for the pleasure of hackers ?), but it looks we
lack proper tcp->copied_seq initialization.

Thanks again Dmitry for your report and testings.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Tested-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 7b1fc95..87463c8 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5638,6 +5638,7 @@ discard:
 		}
 
 		tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
+		tp->copied_seq = tp->rcv_nxt;
 		tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1;
 
 		/* RFC1323: The window in SYN & SYN/ACK segments is
-- 
2.4.1


From 3bbf94f5d1b83545d64c3caa81c83d3aad104a9c Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 20 Nov 2015 00:11:56 +0100
Subject: [PATCH 16/26] net, scm: fix PaX detected msg_controllen overflow in
 scm_detach_fds

[ Upstream commit 6900317f5eff0a7070c5936e5383f589e0de7a09 ]

David and HacKurx reported a following/similar size overflow triggered
in a grsecurity kernel, thanks to PaX's gcc size overflow plugin:

(Already fixed in later grsecurity versions by Brad and PaX Team.)

[ 1002.296137] PAX: size overflow detected in function scm_detach_fds net/core/scm.c:314
               cicus.202_127 min, count: 4, decl: msg_controllen; num: 0; context: msghdr;
[ 1002.296145] CPU: 0 PID: 3685 Comm: scm_rights_recv Not tainted 4.2.3-grsec+ #7
[ 1002.296149] Hardware name: Apple Inc. MacBookAir5,1/Mac-66F35F19FE2A0D05, [...]
[ 1002.296153]  ffffffff81c27366 0000000000000000 ffffffff81c27375 ffffc90007843aa8
[ 1002.296162]  ffffffff818129ba 0000000000000000 ffffffff81c27366 ffffc90007843ad8
[ 1002.296169]  ffffffff8121f838 fffffffffffffffc fffffffffffffffc ffffc90007843e60
[ 1002.296176] Call Trace:
[ 1002.296190]  [<ffffffff818129ba>] dump_stack+0x45/0x57
[ 1002.296200]  [<ffffffff8121f838>] report_size_overflow+0x38/0x60
[ 1002.296209]  [<ffffffff816a979e>] scm_detach_fds+0x2ce/0x300
[ 1002.296220]  [<ffffffff81791899>] unix_stream_read_generic+0x609/0x930
[ 1002.296228]  [<ffffffff81791c9f>] unix_stream_recvmsg+0x4f/0x60
[ 1002.296236]  [<ffffffff8178dc00>] ? unix_set_peek_off+0x50/0x50
[ 1002.296243]  [<ffffffff8168fac7>] sock_recvmsg+0x47/0x60
[ 1002.296248]  [<ffffffff81691522>] ___sys_recvmsg+0xe2/0x1e0
[ 1002.296257]  [<ffffffff81693496>] __sys_recvmsg+0x46/0x80
[ 1002.296263]  [<ffffffff816934fc>] SyS_recvmsg+0x2c/0x40
[ 1002.296271]  [<ffffffff8181a3ab>] entry_SYSCALL_64_fastpath+0x12/0x85

Further investigation showed that this can happen when an *odd* number of
fds are being passed over AF_UNIX sockets.

In these cases CMSG_LEN(i * sizeof(int)) and CMSG_SPACE(i * sizeof(int)),
where i is the number of successfully passed fds, differ by 4 bytes due
to the extra CMSG_ALIGN() padding in CMSG_SPACE() to an 8 byte boundary
on 64 bit. The padding is used to align subsequent cmsg headers in the
control buffer.

When the control buffer passed in from the receiver side *lacks* these 4
bytes (e.g. due to buggy/wrong API usage), then msg->msg_controllen will
overflow in scm_detach_fds():

  int cmlen = CMSG_LEN(i * sizeof(int));  <--- cmlen w/o tail-padding
  err = put_user(SOL_SOCKET, &cm->cmsg_level);
  if (!err)
    err = put_user(SCM_RIGHTS, &cm->cmsg_type);
  if (!err)
    err = put_user(cmlen, &cm->cmsg_len);
  if (!err) {
    cmlen = CMSG_SPACE(i * sizeof(int));  <--- cmlen w/ 4 byte extra tail-padding
    msg->msg_control += cmlen;
    msg->msg_controllen -= cmlen;         <--- iff no tail-padding space here ...
  }                                            ... wrap-around

F.e. it will wrap to a length of 18446744073709551612 bytes in case the
receiver passed in msg->msg_controllen of 20 bytes, and the sender
properly transferred 1 fd to the receiver, so that its CMSG_LEN results
in 20 bytes and CMSG_SPACE in 24 bytes.

In case of MSG_CMSG_COMPAT (scm_detach_fds_compat()), I haven't seen an
issue in my tests as alignment seems always on 4 byte boundary. Same
should be in case of native 32 bit, where we end up with 4 byte boundaries
as well.

In practice, passing msg->msg_controllen of 20 to recvmsg() while receiving
a single fd would mean that on successful return, msg->msg_controllen is
being set by the kernel to 24 bytes instead, thus more than the input
buffer advertised. It could f.e. become an issue if such application later
on zeroes or copies the control buffer based on the returned msg->msg_controllen
elsewhere.

Maximum number of fds we can send is a hard upper limit SCM_MAX_FD (253).

Going over the code, it seems like msg->msg_controllen is not being read
after scm_detach_fds() in scm_recv() anymore by the kernel, good!

Relevant recvmsg() handler are unix_dgram_recvmsg() (unix_seqpacket_recvmsg())
and unix_stream_recvmsg(). Both return back to their recvmsg() caller,
and ___sys_recvmsg() places the updated length, that is, new msg_control -
old msg_control pointer into msg->msg_controllen (hence the 24 bytes seen
in the example).

Long time ago, Wei Yongjun fixed something related in commit 1ac70e7ad24a
("[NET]: Fix function put_cmsg() which may cause usr application memory
overflow").

RFC3542, section 20.2. says:

  The fields shown as "XX" are possible padding, between the cmsghdr
  structure and the data, and between the data and the next cmsghdr
  structure, if required by the implementation. While sending an
  application may or may not include padding at the end of last
  ancillary data in msg_controllen and implementations must accept both
  as valid. On receiving a portable application must provide space for
  padding at the end of the last ancillary data as implementations may
  copy out the padding at the end of the control message buffer and
  include it in the received msg_controllen. When recvmsg() is called
  if msg_controllen is too small for all the ancillary data items
  including any trailing padding after the last item an implementation
  may set MSG_CTRUNC.

Since we didn't place MSG_CTRUNC for already quite a long time, just do
the same as in 1ac70e7ad24a to avoid an overflow.

Btw, even man-page author got this wrong :/ See db939c9b26e9 ("cmsg.3: Fix
error in SCM_RIGHTS code sample"). Some people must have copied this (?),
thus it got triggered in the wild (reported several times during boot by
David and HacKurx).

No Fixes tag this time as pre 2002 (that is, pre history tree).

Reported-by: David Sterba <dave@jikos.cz>
Reported-by: HacKurx <hackurx@gmail.com>
Cc: PaX Team <pageexec@freemail.hu>
Cc: Emese Revfy <re.emese@gmail.com>
Cc: Brad Spengler <spender@grsecurity.net>
Cc: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Cc: Eric Dumazet <edumazet@google.com>
Reviewed-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/scm.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/core/scm.c b/net/core/scm.c
index 3b6899b..8a1741b 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -305,6 +305,8 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
 			err = put_user(cmlen, &cm->cmsg_len);
 		if (!err) {
 			cmlen = CMSG_SPACE(i*sizeof(int));
+			if (msg->msg_controllen < cmlen)
+				cmlen = msg->msg_controllen;
 			msg->msg_control += cmlen;
 			msg->msg_controllen -= cmlen;
 		}
-- 
2.4.1


From bc2a32a21580cb4a3f807a00e7355f365ec2f969 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Fri, 20 Nov 2015 13:54:19 +0100
Subject: [PATCH 17/26] net: ipmr: fix static mfc/dev leaks on table
 destruction

[ Upstream commit 0e615e9601a15efeeb8942cf7cd4dadba0c8c5a7 ]

When destroying an mrt table the static mfc entries and the static
devices are kept, which leads to devices that can never be destroyed
(because of refcnt taken) and leaked memory, for example:
unreferenced object 0xffff880034c144c0 (size 192):
  comm "mfc-broken", pid 4777, jiffies 4320349055 (age 46001.964s)
  hex dump (first 32 bytes):
    98 53 f0 34 00 88 ff ff 98 53 f0 34 00 88 ff ff  .S.4.....S.4....
    ef 0a 0a 14 01 02 03 04 00 00 00 00 01 00 00 00  ................
  backtrace:
    [<ffffffff815c1b9e>] kmemleak_alloc+0x4e/0xb0
    [<ffffffff811ea6e0>] kmem_cache_alloc+0x190/0x300
    [<ffffffff815931cb>] ip_mroute_setsockopt+0x5cb/0x910
    [<ffffffff8153d575>] do_ip_setsockopt.isra.11+0x105/0xff0
    [<ffffffff8153e490>] ip_setsockopt+0x30/0xa0
    [<ffffffff81564e13>] raw_setsockopt+0x33/0x90
    [<ffffffff814d1e14>] sock_common_setsockopt+0x14/0x20
    [<ffffffff814d0b51>] SyS_setsockopt+0x71/0xc0
    [<ffffffff815cdbf6>] entry_SYSCALL_64_fastpath+0x16/0x7a
    [<ffffffffffffffff>] 0xffffffffffffffff

Make sure that everything is cleaned on netns destruction.

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Reviewed-by: Cong Wang <cwang@twopensource.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ipmr.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index df28693..c3bfebd 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -134,7 +134,7 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
 			      struct mfc_cache *c, struct rtmsg *rtm);
 static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc,
 				 int cmd);
-static void mroute_clean_tables(struct mr_table *mrt);
+static void mroute_clean_tables(struct mr_table *mrt, bool all);
 static void ipmr_expire_process(unsigned long arg);
 
 #ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
@@ -351,7 +351,7 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id)
 static void ipmr_free_table(struct mr_table *mrt)
 {
 	del_timer_sync(&mrt->ipmr_expire_timer);
-	mroute_clean_tables(mrt);
+	mroute_clean_tables(mrt, true);
 	kfree(mrt);
 }
 
@@ -1209,7 +1209,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
  *	Close the multicast socket, and clear the vif tables etc
  */
 
-static void mroute_clean_tables(struct mr_table *mrt)
+static void mroute_clean_tables(struct mr_table *mrt, bool all)
 {
 	int i;
 	LIST_HEAD(list);
@@ -1218,8 +1218,9 @@ static void mroute_clean_tables(struct mr_table *mrt)
 	/* Shut down all active vif entries */
 
 	for (i = 0; i < mrt->maxvif; i++) {
-		if (!(mrt->vif_table[i].flags & VIFF_STATIC))
-			vif_delete(mrt, i, 0, &list);
+		if (!all && (mrt->vif_table[i].flags & VIFF_STATIC))
+			continue;
+		vif_delete(mrt, i, 0, &list);
 	}
 	unregister_netdevice_many(&list);
 
@@ -1227,7 +1228,7 @@ static void mroute_clean_tables(struct mr_table *mrt)
 
 	for (i = 0; i < MFC_LINES; i++) {
 		list_for_each_entry_safe(c, next, &mrt->mfc_cache_array[i], list) {
-			if (c->mfc_flags & MFC_STATIC)
+			if (!all && (c->mfc_flags & MFC_STATIC))
 				continue;
 			list_del_rcu(&c->list);
 			mroute_netlink_event(mrt, c, RTM_DELROUTE);
@@ -1262,7 +1263,7 @@ static void mrtsock_destruct(struct sock *sk)
 						    NETCONFA_IFINDEX_ALL,
 						    net->ipv4.devconf_all);
 			RCU_INIT_POINTER(mrt->mroute_sk, NULL);
-			mroute_clean_tables(mrt);
+			mroute_clean_tables(mrt, false);
 		}
 	}
 	rtnl_unlock();
-- 
2.4.1


From 9fc21885648e14fbc1a5a782998c0e8b37840306 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Fri, 20 Nov 2015 13:54:20 +0100
Subject: [PATCH 18/26] net: ip6mr: fix static mfc/dev leaks on table
 destruction

[ Upstream commit 4c6980462f32b4f282c5d8e5f7ea8070e2937725 ]

Similar to ipv4, when destroying an mrt table the static mfc entries and
the static devices are kept, which leads to devices that can never be
destroyed (because of refcnt taken) and leaked memory. Make sure that
everything is cleaned up on netns destruction.

Fixes: 8229efdaef1e ("netns: ip6mr: enable namespace support in ipv6 multicast forwarding code")
CC: Benjamin Thery <benjamin.thery@bull.net>
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Reviewed-by: Cong Wang <cwang@twopensource.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6mr.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 5f36266..a7aef4b 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -118,7 +118,7 @@ static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc,
 			      int cmd);
 static int ip6mr_rtm_dumproute(struct sk_buff *skb,
 			       struct netlink_callback *cb);
-static void mroute_clean_tables(struct mr6_table *mrt);
+static void mroute_clean_tables(struct mr6_table *mrt, bool all);
 static void ipmr_expire_process(unsigned long arg);
 
 #ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES
@@ -335,7 +335,7 @@ static struct mr6_table *ip6mr_new_table(struct net *net, u32 id)
 static void ip6mr_free_table(struct mr6_table *mrt)
 {
 	del_timer_sync(&mrt->ipmr_expire_timer);
-	mroute_clean_tables(mrt);
+	mroute_clean_tables(mrt, true);
 	kfree(mrt);
 }
 
@@ -1543,7 +1543,7 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt,
  *	Close the multicast socket, and clear the vif tables etc
  */
 
-static void mroute_clean_tables(struct mr6_table *mrt)
+static void mroute_clean_tables(struct mr6_table *mrt, bool all)
 {
 	int i;
 	LIST_HEAD(list);
@@ -1553,8 +1553,9 @@ static void mroute_clean_tables(struct mr6_table *mrt)
 	 *	Shut down all active vif entries
 	 */
 	for (i = 0; i < mrt->maxvif; i++) {
-		if (!(mrt->vif6_table[i].flags & VIFF_STATIC))
-			mif6_delete(mrt, i, &list);
+		if (!all && (mrt->vif6_table[i].flags & VIFF_STATIC))
+			continue;
+		mif6_delete(mrt, i, &list);
 	}
 	unregister_netdevice_many(&list);
 
@@ -1563,7 +1564,7 @@ static void mroute_clean_tables(struct mr6_table *mrt)
 	 */
 	for (i = 0; i < MFC6_LINES; i++) {
 		list_for_each_entry_safe(c, next, &mrt->mfc6_cache_array[i], list) {
-			if (c->mfc_flags & MFC_STATIC)
+			if (!all && (c->mfc_flags & MFC_STATIC))
 				continue;
 			write_lock_bh(&mrt_lock);
 			list_del(&c->list);
@@ -1626,7 +1627,7 @@ int ip6mr_sk_done(struct sock *sk)
 						     net->ipv6.devconf_all);
 			write_unlock_bh(&mrt_lock);
 
-			mroute_clean_tables(mrt);
+			mroute_clean_tables(mrt, false);
 			err = 0;
 			break;
 		}
-- 
2.4.1


From da785b62ca9b54f2216e07521a517d599e984962 Mon Sep 17 00:00:00 2001
From: Aaro Koskinen <aaro.koskinen@iki.fi>
Date: Sun, 22 Nov 2015 01:08:54 +0200
Subject: [PATCH 19/26] broadcom: fix PHY_ID_BCM5481 entry in the id table

[ Upstream commit 3c25a860d17b7378822f35d8c9141db9507e3beb ]

Commit fcb26ec5b18d ("broadcom: move all PHY_ID's to header")
updated broadcom_tbl to use PHY_IDs, but incorrectly replaced 0x0143bca0
with PHY_ID_BCM5482 (making a duplicate entry, and completely omitting
the original). Fix that.

Fixes: fcb26ec5b18d ("broadcom: move all PHY_ID's to header")
Signed-off-by: Aaro Koskinen <aaro.koskinen@iki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/broadcom.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c
index 9c71295..85e64044 100644
--- a/drivers/net/phy/broadcom.c
+++ b/drivers/net/phy/broadcom.c
@@ -675,7 +675,7 @@ static struct mdio_device_id __maybe_unused broadcom_tbl[] = {
 	{ PHY_ID_BCM5461, 0xfffffff0 },
 	{ PHY_ID_BCM54616S, 0xfffffff0 },
 	{ PHY_ID_BCM5464, 0xfffffff0 },
-	{ PHY_ID_BCM5482, 0xfffffff0 },
+	{ PHY_ID_BCM5481, 0xfffffff0 },
 	{ PHY_ID_BCM5482, 0xfffffff0 },
 	{ PHY_ID_BCM50610, 0xfffffff0 },
 	{ PHY_ID_BCM50610M, 0xfffffff0 },
-- 
2.4.1


From c0081fbfd50a8218611ef6a7a1543ed0c1a6d3e6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Michal=20Kube=C4=8Dek?= <mkubecek@suse.cz>
Date: Tue, 24 Nov 2015 15:07:11 +0100
Subject: [PATCH 20/26] ipv6: distinguish frag queues by device for multicast
 and link-local packets

[ Upstream commit 264640fc2c5f4f913db5c73fa3eb1ead2c45e9d7 ]

If a fragmented multicast packet is received on an ethernet device which
has an active macvlan on top of it, each fragment is duplicated and
received both on the underlying device and the macvlan. If some
fragments for macvlan are processed before the whole packet for the
underlying device is reassembled, the "overlapping fragments" test in
ip6_frag_queue() discards the whole fragment queue.

To resolve this, add device ifindex to the search key and require it to
match reassembling multicast packets and packets to link-local
addresses.

Note: similar patch has been already submitted by Yoshifuji Hideaki in

  http://patchwork.ozlabs.org/patch/220979/

but got lost and forgotten for some reason.

Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h                      |  1 +
 net/ipv6/netfilter/nf_conntrack_reasm.c |  5 +++--
 net/ipv6/reassembly.c                   | 10 +++++++---
 3 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index eec8ad3..ab8ebd3 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -488,6 +488,7 @@ struct ip6_create_arg {
 	u32 user;
 	const struct in6_addr *src;
 	const struct in6_addr *dst;
+	int iif;
 	u8 ecn;
 };
 
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 6f187c8..d235ed7 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -190,7 +190,7 @@ static void nf_ct_frag6_expire(unsigned long data)
 /* Creation primitives. */
 static inline struct frag_queue *fq_find(struct net *net, __be32 id,
 					 u32 user, struct in6_addr *src,
-					 struct in6_addr *dst, u8 ecn)
+					 struct in6_addr *dst, int iif, u8 ecn)
 {
 	struct inet_frag_queue *q;
 	struct ip6_create_arg arg;
@@ -200,6 +200,7 @@ static inline struct frag_queue *fq_find(struct net *net, __be32 id,
 	arg.user = user;
 	arg.src = src;
 	arg.dst = dst;
+	arg.iif = iif;
 	arg.ecn = ecn;
 
 	local_bh_disable();
@@ -603,7 +604,7 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user)
 	fhdr = (struct frag_hdr *)skb_transport_header(clone);
 
 	fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr,
-		     ip6_frag_ecn(hdr));
+		     skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
 	if (fq == NULL) {
 		pr_debug("Can't find and can't create new queue\n");
 		goto ret_orig;
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 8ffa2c8..9d1f6a2 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -108,7 +108,10 @@ bool ip6_frag_match(const struct inet_frag_queue *q, const void *a)
 	return	fq->id == arg->id &&
 		fq->user == arg->user &&
 		ipv6_addr_equal(&fq->saddr, arg->src) &&
-		ipv6_addr_equal(&fq->daddr, arg->dst);
+		ipv6_addr_equal(&fq->daddr, arg->dst) &&
+		(arg->iif == fq->iif ||
+		 !(ipv6_addr_type(arg->dst) & (IPV6_ADDR_MULTICAST |
+					       IPV6_ADDR_LINKLOCAL)));
 }
 EXPORT_SYMBOL(ip6_frag_match);
 
@@ -180,7 +183,7 @@ static void ip6_frag_expire(unsigned long data)
 
 static struct frag_queue *
 fq_find(struct net *net, __be32 id, const struct in6_addr *src,
-	const struct in6_addr *dst, u8 ecn)
+	const struct in6_addr *dst, int iif, u8 ecn)
 {
 	struct inet_frag_queue *q;
 	struct ip6_create_arg arg;
@@ -190,6 +193,7 @@ fq_find(struct net *net, __be32 id, const struct in6_addr *src,
 	arg.user = IP6_DEFRAG_LOCAL_DELIVER;
 	arg.src = src;
 	arg.dst = dst;
+	arg.iif = iif;
 	arg.ecn = ecn;
 
 	hash = inet6_hash_frag(id, src, dst);
@@ -551,7 +555,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 	}
 
 	fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr,
-		     ip6_frag_ecn(hdr));
+		     skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
 	if (fq) {
 		int ret;
 
-- 
2.4.1


From 9fe1e6b2e6a567fa28de0ecbcbc6114a4b4608c4 Mon Sep 17 00:00:00 2001
From: Quentin Casasnovas <quentin.casasnovas@oracle.com>
Date: Tue, 24 Nov 2015 17:13:21 -0500
Subject: [PATCH 21/26] RDS: fix race condition when sending a message on
 unbound socket

[ Upstream commit 8c7188b23474cca017b3ef354c4a58456f68303a ]

Sasha's found a NULL pointer dereference in the RDS connection code when
sending a message to an apparently unbound socket.  The problem is caused
by the code checking if the socket is bound in rds_sendmsg(), which checks
the rs_bound_addr field without taking a lock on the socket.  This opens a
race where rs_bound_addr is temporarily set but where the transport is not
in rds_bind(), leading to a NULL pointer dereference when trying to
dereference 'trans' in __rds_conn_create().

Vegard wrote a reproducer for this issue, so kindly ask him to share if
you're interested.

I cannot reproduce the NULL pointer dereference using Vegard's reproducer
with this patch, whereas I could without.

Complete earlier incomplete fix to CVE-2015-6937:

  74e98eb08588 ("RDS: verify the underlying transport exists before creating a connection")

Cc: David S. Miller <davem@davemloft.net>
Cc: stable@vger.kernel.org

Reviewed-by: Vegard Nossum <vegard.nossum@oracle.com>
Reviewed-by: Sasha Levin <sasha.levin@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: Quentin Casasnovas <quentin.casasnovas@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/connection.c | 6 ------
 net/rds/send.c       | 4 +++-
 2 files changed, 3 insertions(+), 7 deletions(-)

diff --git a/net/rds/connection.c b/net/rds/connection.c
index 9d66705..da6da57 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -187,12 +187,6 @@ new_conn:
 		}
 	}
 
-	if (trans == NULL) {
-		kmem_cache_free(rds_conn_slab, conn);
-		conn = ERR_PTR(-ENODEV);
-		goto out;
-	}
-
 	conn->c_trans = trans;
 
 	ret = trans->conn_alloc(conn, gfp);
diff --git a/net/rds/send.c b/net/rds/send.c
index e9430f5..7b30c0f 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -986,11 +986,13 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 		release_sock(sk);
 	}
 
-	/* racing with another thread binding seems ok here */
+	lock_sock(sk);
 	if (daddr == 0 || rs->rs_bound_addr == 0) {
+		release_sock(sk);
 		ret = -ENOTCONN; /* XXX not a great errno */
 		goto out;
 	}
+	release_sock(sk);
 
 	/* size of rm including all sgs */
 	ret = rds_rm_size(msg, payload_len);
-- 
2.4.1


From 1182988535dd93cfc71bdb39202c733ce3974f36 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Mon, 30 Nov 2015 13:02:56 +0100
Subject: [PATCH 22/26] bpf, array: fix heap out-of-bounds access when updating
 elements

[ Upstream commit fbca9d2d35c6ef1b323fae75cc9545005ba25097 ]

During own review but also reported by Dmitry's syzkaller [1] it has been
noticed that we trigger a heap out-of-bounds access on eBPF array maps
when updating elements. This happens with each map whose map->value_size
(specified during map creation time) is not multiple of 8 bytes.

In array_map_alloc(), elem_size is round_up(attr->value_size, 8) and
used to align array map slots for faster access. However, in function
array_map_update_elem(), we update the element as ...

memcpy(array->value + array->elem_size * index, value, array->elem_size);

... where we access 'value' out-of-bounds, since it was allocated from
map_update_elem() from syscall side as kmalloc(map->value_size, GFP_USER)
and later on copied through copy_from_user(value, uvalue, map->value_size).
Thus, up to 7 bytes, we can access out-of-bounds.

Same could happen from within an eBPF program, where in worst case we
access beyond an eBPF program's designated stack.

Since 1be7f75d1668 ("bpf: enable non-root eBPF programs") didn't hit an
official release yet, it only affects priviledged users.

In case of array_map_lookup_elem(), the verifier prevents eBPF programs
from accessing beyond map->value_size through check_map_access(). Also
from syscall side map_lookup_elem() only copies map->value_size back to
user, so nothing could leak.

  [1] http://github.com/google/syzkaller

Fixes: 28fbcfa08d8e ("bpf: add array type of eBPF maps")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/arraymap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 8a66165..1c1b8ab 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -109,7 +109,7 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value,
 		/* all elements already exist */
 		return -EEXIST;
 
-	memcpy(array->value + array->elem_size * index, value, array->elem_size);
+	memcpy(array->value + array->elem_size * index, value, map->value_size);
 	return 0;
 }
 
-- 
2.4.1


From d2033f7385494211f197d9ff53d8682a03bfec95 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 29 Nov 2015 19:37:57 -0800
Subject: [PATCH 23/26] ipv6: add complete rcu protection around np->opt

[ Upstream commit 45f6fad84cc305103b28d73482b344d7f5b76f39 ]

This patch addresses multiple problems :

UDP/RAW sendmsg() need to get a stable struct ipv6_txoptions
while socket is not locked : Other threads can change np->opt
concurrently. Dmitry posted a syzkaller
(http://github.com/google/syzkaller) program desmonstrating
use-after-free.

Starting with TCP/DCCP lockless listeners, tcp_v6_syn_recv_sock()
and dccp_v6_request_recv_sock() also need to use RCU protection
to dereference np->opt once (before calling ipv6_dup_options())

This patch adds full RCU protection to np->opt

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ipv6.h             |  2 +-
 include/net/ipv6.h               | 21 ++++++++++++++++++++-
 net/dccp/ipv6.c                  | 33 +++++++++++++++++++++------------
 net/ipv6/af_inet6.c              | 13 +++++++++----
 net/ipv6/datagram.c              |  4 +++-
 net/ipv6/exthdrs.c               |  3 ++-
 net/ipv6/inet6_connection_sock.c | 11 ++++++++---
 net/ipv6/ipv6_sockglue.c         | 33 ++++++++++++++++++++++-----------
 net/ipv6/raw.c                   |  8 ++++++--
 net/ipv6/syncookies.c            |  2 +-
 net/ipv6/tcp_ipv6.c              | 28 +++++++++++++++++-----------
 net/ipv6/udp.c                   |  8 ++++++--
 net/l2tp/l2tp_ip6.c              |  8 ++++++--
 13 files changed, 122 insertions(+), 52 deletions(-)

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 82806c6..e4b4649 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -224,7 +224,7 @@ struct ipv6_pinfo {
 	struct ipv6_ac_socklist	*ipv6_ac_list;
 	struct ipv6_fl_socklist __rcu *ipv6_fl_list;
 
-	struct ipv6_txoptions	*opt;
+	struct ipv6_txoptions __rcu	*opt;
 	struct sk_buff		*pktoptions;
 	struct sk_buff		*rxpmtu;
 	struct inet6_cork	cork;
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index ab8ebd3..df555ec 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -205,6 +205,7 @@ extern rwlock_t ip6_ra_lock;
  */
 
 struct ipv6_txoptions {
+	atomic_t		refcnt;
 	/* Length of this structure */
 	int			tot_len;
 
@@ -217,7 +218,7 @@ struct ipv6_txoptions {
 	struct ipv6_opt_hdr	*dst0opt;
 	struct ipv6_rt_hdr	*srcrt;	/* Routing Header */
 	struct ipv6_opt_hdr	*dst1opt;
-
+	struct rcu_head		rcu;
 	/* Option buffer, as read by IPV6_PKTOPTIONS, starts here. */
 };
 
@@ -250,6 +251,24 @@ struct ipv6_fl_socklist {
 	struct rcu_head			rcu;
 };
 
+static inline struct ipv6_txoptions *txopt_get(const struct ipv6_pinfo *np)
+{
+	struct ipv6_txoptions *opt;
+
+	rcu_read_lock();
+	opt = rcu_dereference(np->opt);
+	if (opt && !atomic_inc_not_zero(&opt->refcnt))
+		opt = NULL;
+	rcu_read_unlock();
+	return opt;
+}
+
+static inline void txopt_put(struct ipv6_txoptions *opt)
+{
+	if (opt && atomic_dec_and_test(&opt->refcnt))
+		kfree_rcu(opt, rcu);
+}
+
 struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label);
 struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space,
 					 struct ip6_flowlabel *fl,
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 5165571..a049050 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -202,7 +202,9 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req)
 	security_req_classify_flow(req, flowi6_to_flowi(&fl6));
 
 
-	final_p = fl6_update_dst(&fl6, np->opt, &final);
+	rcu_read_lock();
+	final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final);
+	rcu_read_unlock();
 
 	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
@@ -219,7 +221,10 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req)
 							 &ireq->ir_v6_loc_addr,
 							 &ireq->ir_v6_rmt_addr);
 		fl6.daddr = ireq->ir_v6_rmt_addr;
-		err = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass);
+		rcu_read_lock();
+		err = ip6_xmit(sk, skb, &fl6, rcu_dereference(np->opt),
+			       np->tclass);
+		rcu_read_unlock();
 		err = net_xmit_eval(err);
 	}
 
@@ -415,6 +420,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
 	struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
+	struct ipv6_txoptions *opt;
 	struct inet_sock *newinet;
 	struct dccp6_sock *newdp6;
 	struct sock *newsk;
@@ -534,13 +540,15 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
 	 * Yes, keeping reference count would be much more clever, but we make
 	 * one more one thing there: reattach optmem to newsk.
 	 */
-	if (np->opt != NULL)
-		newnp->opt = ipv6_dup_options(newsk, np->opt);
-
+	opt = rcu_dereference(np->opt);
+	if (opt) {
+		opt = ipv6_dup_options(newsk, opt);
+		RCU_INIT_POINTER(newnp->opt, opt);
+	}
 	inet_csk(newsk)->icsk_ext_hdr_len = 0;
-	if (newnp->opt != NULL)
-		inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen +
-						     newnp->opt->opt_flen);
+	if (opt)
+		inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen +
+						    opt->opt_flen;
 
 	dccp_sync_mss(newsk, dst_mtu(dst));
 
@@ -793,6 +801,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct dccp_sock *dp = dccp_sk(sk);
 	struct in6_addr *saddr = NULL, *final_p, final;
+	struct ipv6_txoptions *opt;
 	struct flowi6 fl6;
 	struct dst_entry *dst;
 	int addr_type;
@@ -892,7 +901,8 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	fl6.fl6_sport = inet->inet_sport;
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
-	final_p = fl6_update_dst(&fl6, np->opt, &final);
+	opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+	final_p = fl6_update_dst(&fl6, opt, &final);
 
 	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
@@ -912,9 +922,8 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	__ip6_dst_store(sk, dst, NULL, NULL);
 
 	icsk->icsk_ext_hdr_len = 0;
-	if (np->opt != NULL)
-		icsk->icsk_ext_hdr_len = (np->opt->opt_flen +
-					  np->opt->opt_nflen);
+	if (opt)
+		icsk->icsk_ext_hdr_len = opt->opt_flen + opt->opt_nflen;
 
 	inet->inet_dport = usin->sin6_port;
 
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index eef63b3..2d044d2 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -425,9 +425,11 @@ void inet6_destroy_sock(struct sock *sk)
 
 	/* Free tx options */
 
-	opt = xchg(&np->opt, NULL);
-	if (opt)
-		sock_kfree_s(sk, opt, opt->tot_len);
+	opt = xchg((__force struct ipv6_txoptions **)&np->opt, NULL);
+	if (opt) {
+		atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+		txopt_put(opt);
+	}
 }
 EXPORT_SYMBOL_GPL(inet6_destroy_sock);
 
@@ -656,7 +658,10 @@ int inet6_sk_rebuild_header(struct sock *sk)
 		fl6.fl6_sport = inet->inet_sport;
 		security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
-		final_p = fl6_update_dst(&fl6, np->opt, &final);
+		rcu_read_lock();
+		final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt),
+					 &final);
+		rcu_read_unlock();
 
 		dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
 		if (IS_ERR(dst)) {
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index b10a889..13ca4cf 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -167,8 +167,10 @@ ipv4_connected:
 
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
-	opt = flowlabel ? flowlabel->opt : np->opt;
+	rcu_read_lock();
+	opt = flowlabel ? flowlabel->opt : rcu_dereference(np->opt);
 	final_p = fl6_update_dst(&fl6, opt, &final);
+	rcu_read_unlock();
 
 	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
 	err = 0;
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index a7bbbe4..adbd695 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -727,6 +727,7 @@ ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt)
 			*((char **)&opt2->dst1opt) += dif;
 		if (opt2->srcrt)
 			*((char **)&opt2->srcrt) += dif;
+		atomic_set(&opt2->refcnt, 1);
 	}
 	return opt2;
 }
@@ -790,7 +791,7 @@ ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt,
 		return ERR_PTR(-ENOBUFS);
 
 	memset(opt2, 0, tot_len);
-
+	atomic_set(&opt2->refcnt, 1);
 	opt2->tot_len = tot_len;
 	p = (char *)(opt2 + 1);
 
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 6927f3f..9beed30 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -77,7 +77,9 @@ struct dst_entry *inet6_csk_route_req(struct sock *sk,
 	memset(fl6, 0, sizeof(*fl6));
 	fl6->flowi6_proto = IPPROTO_TCP;
 	fl6->daddr = ireq->ir_v6_rmt_addr;
-	final_p = fl6_update_dst(fl6, np->opt, &final);
+	rcu_read_lock();
+	final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
+	rcu_read_unlock();
 	fl6->saddr = ireq->ir_v6_loc_addr;
 	fl6->flowi6_oif = ireq->ir_iif;
 	fl6->flowi6_mark = ireq->ir_mark;
@@ -207,7 +209,9 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk,
 	fl6->fl6_dport = inet->inet_dport;
 	security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
 
-	final_p = fl6_update_dst(fl6, np->opt, &final);
+	rcu_read_lock();
+	final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
+	rcu_read_unlock();
 
 	dst = __inet6_csk_dst_check(sk, np->dst_cookie);
 	if (!dst) {
@@ -240,7 +244,8 @@ int inet6_csk_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl_unused
 	/* Restore final destination back after routing done */
 	fl6.daddr = sk->sk_v6_daddr;
 
-	res = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass);
+	res = ip6_xmit(sk, skb, &fl6, rcu_dereference(np->opt),
+		       np->tclass);
 	rcu_read_unlock();
 	return res;
 }
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 63e6956..4449ad1 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -111,7 +111,8 @@ struct ipv6_txoptions *ipv6_update_options(struct sock *sk,
 			icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie);
 		}
 	}
-	opt = xchg(&inet6_sk(sk)->opt, opt);
+	opt = xchg((__force struct ipv6_txoptions **)&inet6_sk(sk)->opt,
+		   opt);
 	sk_dst_reset(sk);
 
 	return opt;
@@ -231,9 +232,12 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 				sk->sk_socket->ops = &inet_dgram_ops;
 				sk->sk_family = PF_INET;
 			}
-			opt = xchg(&np->opt, NULL);
-			if (opt)
-				sock_kfree_s(sk, opt, opt->tot_len);
+			opt = xchg((__force struct ipv6_txoptions **)&np->opt,
+				   NULL);
+			if (opt) {
+				atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+				txopt_put(opt);
+			}
 			pktopt = xchg(&np->pktoptions, NULL);
 			kfree_skb(pktopt);
 
@@ -403,7 +407,8 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 		if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW))
 			break;
 
-		opt = ipv6_renew_options(sk, np->opt, optname,
+		opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+		opt = ipv6_renew_options(sk, opt, optname,
 					 (struct ipv6_opt_hdr __user *)optval,
 					 optlen);
 		if (IS_ERR(opt)) {
@@ -432,8 +437,10 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 		retv = 0;
 		opt = ipv6_update_options(sk, opt);
 sticky_done:
-		if (opt)
-			sock_kfree_s(sk, opt, opt->tot_len);
+		if (opt) {
+			atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+			txopt_put(opt);
+		}
 		break;
 	}
 
@@ -486,6 +493,7 @@ sticky_done:
 			break;
 
 		memset(opt, 0, sizeof(*opt));
+		atomic_set(&opt->refcnt, 1);
 		opt->tot_len = sizeof(*opt) + optlen;
 		retv = -EFAULT;
 		if (copy_from_user(opt+1, optval, optlen))
@@ -502,8 +510,10 @@ update:
 		retv = 0;
 		opt = ipv6_update_options(sk, opt);
 done:
-		if (opt)
-			sock_kfree_s(sk, opt, opt->tot_len);
+		if (opt) {
+			atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+			txopt_put(opt);
+		}
 		break;
 	}
 	case IPV6_UNICAST_HOPS:
@@ -1110,10 +1120,11 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 	case IPV6_RTHDR:
 	case IPV6_DSTOPTS:
 	{
+		struct ipv6_txoptions *opt;
 
 		lock_sock(sk);
-		len = ipv6_getsockopt_sticky(sk, np->opt,
-					     optname, optval, len);
+		opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+		len = ipv6_getsockopt_sticky(sk, opt, optname, optval, len);
 		release_sock(sk);
 		/* check if ipv6_getsockopt_sticky() returns err code */
 		if (len < 0)
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 8072bd4..2c639ae 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -731,6 +731,7 @@ static int raw6_getfrag(void *from, char *to, int offset, int len, int odd,
 
 static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 {
+	struct ipv6_txoptions *opt_to_free = NULL;
 	struct ipv6_txoptions opt_space;
 	DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
 	struct in6_addr *daddr, *final_p, final;
@@ -837,8 +838,10 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		if (!(opt->opt_nflen|opt->opt_flen))
 			opt = NULL;
 	}
-	if (!opt)
-		opt = np->opt;
+	if (!opt) {
+		opt = txopt_get(np);
+		opt_to_free = opt;
+		}
 	if (flowlabel)
 		opt = fl6_merge_options(&opt_space, flowlabel, opt);
 	opt = ipv6_fixup_options(&opt_space, opt);
@@ -901,6 +904,7 @@ done:
 	dst_release(dst);
 out:
 	fl6_sock_release(flowlabel);
+	txopt_put(opt_to_free);
 	return err < 0 ? err : len;
 do_confirm:
 	dst_confirm(dst);
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 21bc2eb..a4cf004 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -242,7 +242,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 		memset(&fl6, 0, sizeof(fl6));
 		fl6.flowi6_proto = IPPROTO_TCP;
 		fl6.daddr = ireq->ir_v6_rmt_addr;
-		final_p = fl6_update_dst(&fl6, np->opt, &final);
+		final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final);
 		fl6.saddr = ireq->ir_v6_loc_addr;
 		fl6.flowi6_oif = sk->sk_bound_dev_if;
 		fl6.flowi6_mark = ireq->ir_mark;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index e541d68..cfb27f5 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -121,6 +121,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct in6_addr *saddr = NULL, *final_p, final;
+	struct ipv6_txoptions *opt;
 	struct rt6_info *rt;
 	struct flowi6 fl6;
 	struct dst_entry *dst;
@@ -237,7 +238,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	fl6.fl6_dport = usin->sin6_port;
 	fl6.fl6_sport = inet->inet_sport;
 
-	final_p = fl6_update_dst(&fl6, np->opt, &final);
+	opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+	final_p = fl6_update_dst(&fl6, opt, &final);
 
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
@@ -266,9 +268,9 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 		tcp_fetch_timewait_stamp(sk, dst);
 
 	icsk->icsk_ext_hdr_len = 0;
-	if (np->opt)
-		icsk->icsk_ext_hdr_len = (np->opt->opt_flen +
-					  np->opt->opt_nflen);
+	if (opt)
+		icsk->icsk_ext_hdr_len = opt->opt_flen +
+					 opt->opt_nflen;
 
 	tp->rx_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
 
@@ -464,7 +466,8 @@ static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst,
 			fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));
 
 		skb_set_queue_mapping(skb, queue_mapping);
-		err = ip6_xmit(sk, skb, fl6, np->opt, np->tclass);
+		err = ip6_xmit(sk, skb, fl6, rcu_dereference(np->opt),
+			       np->tclass);
 		err = net_xmit_eval(err);
 	}
 
@@ -994,6 +997,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	struct inet_request_sock *ireq;
 	struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
 	struct tcp6_sock *newtcp6sk;
+	struct ipv6_txoptions *opt;
 	struct inet_sock *newinet;
 	struct tcp_sock *newtp;
 	struct sock *newsk;
@@ -1129,13 +1133,15 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	   but we make one more one thing there: reattach optmem
 	   to newsk.
 	 */
-	if (np->opt)
-		newnp->opt = ipv6_dup_options(newsk, np->opt);
-
+	opt = rcu_dereference(np->opt);
+	if (opt) {
+		opt = ipv6_dup_options(newsk, opt);
+		RCU_INIT_POINTER(newnp->opt, opt);
+	}
 	inet_csk(newsk)->icsk_ext_hdr_len = 0;
-	if (newnp->opt)
-		inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen +
-						     newnp->opt->opt_flen);
+	if (opt)
+		inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen +
+						    opt->opt_flen;
 
 	tcp_ca_openreq_child(newsk, dst);
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index e51fc3e..7333f35 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1107,6 +1107,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
 	struct in6_addr *daddr, *final_p, final;
 	struct ipv6_txoptions *opt = NULL;
+	struct ipv6_txoptions *opt_to_free = NULL;
 	struct ip6_flowlabel *flowlabel = NULL;
 	struct flowi6 fl6;
 	struct dst_entry *dst;
@@ -1260,8 +1261,10 @@ do_udp_sendmsg:
 			opt = NULL;
 		connected = 0;
 	}
-	if (!opt)
-		opt = np->opt;
+	if (!opt) {
+		opt = txopt_get(np);
+		opt_to_free = opt;
+	}
 	if (flowlabel)
 		opt = fl6_merge_options(&opt_space, flowlabel, opt);
 	opt = ipv6_fixup_options(&opt_space, opt);
@@ -1370,6 +1373,7 @@ release_dst:
 out:
 	dst_release(dst);
 	fl6_sock_release(flowlabel);
+	txopt_put(opt_to_free);
 	if (!err)
 		return len;
 	/*
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index d1ded37..0ce9da9 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -486,6 +486,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	DECLARE_SOCKADDR(struct sockaddr_l2tpip6 *, lsa, msg->msg_name);
 	struct in6_addr *daddr, *final_p, final;
 	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct ipv6_txoptions *opt_to_free = NULL;
 	struct ipv6_txoptions *opt = NULL;
 	struct ip6_flowlabel *flowlabel = NULL;
 	struct dst_entry *dst = NULL;
@@ -575,8 +576,10 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 			opt = NULL;
 	}
 
-	if (opt == NULL)
-		opt = np->opt;
+	if (!opt) {
+		opt = txopt_get(np);
+		opt_to_free = opt;
+	}
 	if (flowlabel)
 		opt = fl6_merge_options(&opt_space, flowlabel, opt);
 	opt = ipv6_fixup_options(&opt_space, opt);
@@ -631,6 +634,7 @@ done:
 	dst_release(dst);
 out:
 	fl6_sock_release(flowlabel);
+	txopt_put(opt_to_free);
 
 	return err < 0 ? err : len;
 
-- 
2.4.1


From c1ab8e4c93f9a2417ada3aba0bfaad4c334f5e34 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <koct9i@gmail.com>
Date: Tue, 1 Dec 2015 01:14:48 +0300
Subject: [PATCH 24/26] net/neighbour: fix crash at dumping device-agnostic
 proxy entries

[ Upstream commit 6adc5fd6a142c6e2c80574c1db0c7c17dedaa42e ]

Proxy entries could have null pointer to net-device.

Signed-off-by: Konstantin Khlebnikov <koct9i@gmail.com>
Fixes: 84920c1420e2 ("net: Allow ipv6 proxies and arp proxies be shown with iproute2")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 2237c1b..d6e8cfc 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2207,7 +2207,7 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn,
 	ndm->ndm_pad2    = 0;
 	ndm->ndm_flags	 = pn->flags | NTF_PROXY;
 	ndm->ndm_type	 = RTN_UNICAST;
-	ndm->ndm_ifindex = pn->dev->ifindex;
+	ndm->ndm_ifindex = pn->dev ? pn->dev->ifindex : 0;
 	ndm->ndm_state	 = NUD_NONE;
 
 	if (nla_put(skb, NDA_DST, tbl->key_len, pn->key))
@@ -2282,7 +2282,7 @@ static int pneigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
 		if (h > s_h)
 			s_idx = 0;
 		for (n = tbl->phash_buckets[h], idx = 0; n; n = n->next) {
-			if (dev_net(n->dev) != net)
+			if (pneigh_net(n) != net)
 				continue;
 			if (idx < s_idx)
 				goto next;
-- 
2.4.1


From 702a741580d73f3c39b842931127832c2150ac2a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 1 Dec 2015 07:20:07 -0800
Subject: [PATCH 25/26] ipv6: sctp: implement sctp_v6_destroy_sock()

[ Upstream commit 602dd62dfbda3e63a2d6a3cbde953ebe82bf5087 ]

Dmitry Vyukov reported a memory leak using IPV6 SCTP sockets.

We need to call inet6_destroy_sock() to properly release
inet6 specific fields.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 5f6c4e6..66d7960 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -7387,6 +7387,13 @@ struct proto sctp_prot = {
 
 #if IS_ENABLED(CONFIG_IPV6)
 
+#include <net/transp_v6.h>
+static void sctp_v6_destroy_sock(struct sock *sk)
+{
+	sctp_destroy_sock(sk);
+	inet6_destroy_sock(sk);
+}
+
 struct proto sctpv6_prot = {
 	.name		= "SCTPv6",
 	.owner		= THIS_MODULE,
@@ -7396,7 +7403,7 @@ struct proto sctpv6_prot = {
 	.accept		= sctp_accept,
 	.ioctl		= sctp_ioctl,
 	.init		= sctp_init_sock,
-	.destroy	= sctp_destroy_sock,
+	.destroy	= sctp_v6_destroy_sock,
 	.shutdown	= sctp_shutdown,
 	.setsockopt	= sctp_setsockopt,
 	.getsockopt	= sctp_getsockopt,
-- 
2.4.1


From 62c39bfdff3ccadc0c406066aee3e0e6733148e8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 1 Dec 2015 20:08:51 -0800
Subject: [PATCH 26/26] net_sched: fix qdisc_tree_decrease_qlen() races

[ Upstream commit 4eaf3b84f2881c9c028f1d5e76c52ab575fe3a66 ]

qdisc_tree_decrease_qlen() suffers from two problems on multiqueue
devices.

One problem is that it updates sch->q.qlen and sch->qstats.drops
on the mq/mqprio root qdisc, while it should not : Daniele
reported underflows errors :
[  681.774821] PAX: sch->q.qlen: 0 n: 1
[  681.774825] PAX: size overflow detected in function qdisc_tree_decrease_qlen net/sched/sch_api.c:769 cicus.693_49 min, count: 72, decl: qlen; num: 0; context: sk_buff_head;
[  681.774954] CPU: 2 PID: 19 Comm: ksoftirqd/2 Tainted: G           O    4.2.6.201511282239-1-grsec #1
[  681.774955] Hardware name: ASUSTeK COMPUTER INC. X302LJ/X302LJ, BIOS X302LJ.202 03/05/2015
[  681.774956]  ffffffffa9a04863 0000000000000000 0000000000000000 ffffffffa990ff7c
[  681.774959]  ffffc90000d3bc38 ffffffffa95d2810 0000000000000007 ffffffffa991002b
[  681.774960]  ffffc90000d3bc68 ffffffffa91a44f4 0000000000000001 0000000000000001
[  681.774962] Call Trace:
[  681.774967]  [<ffffffffa95d2810>] dump_stack+0x4c/0x7f
[  681.774970]  [<ffffffffa91a44f4>] report_size_overflow+0x34/0x50
[  681.774972]  [<ffffffffa94d17e2>] qdisc_tree_decrease_qlen+0x152/0x160
[  681.774976]  [<ffffffffc02694b1>] fq_codel_dequeue+0x7b1/0x820 [sch_fq_codel]
[  681.774978]  [<ffffffffc02680a0>] ? qdisc_peek_dequeued+0xa0/0xa0 [sch_fq_codel]
[  681.774980]  [<ffffffffa94cd92d>] __qdisc_run+0x4d/0x1d0
[  681.774983]  [<ffffffffa949b2b2>] net_tx_action+0xc2/0x160
[  681.774985]  [<ffffffffa90664c1>] __do_softirq+0xf1/0x200
[  681.774987]  [<ffffffffa90665ee>] run_ksoftirqd+0x1e/0x30
[  681.774989]  [<ffffffffa90896b0>] smpboot_thread_fn+0x150/0x260
[  681.774991]  [<ffffffffa9089560>] ? sort_range+0x40/0x40
[  681.774992]  [<ffffffffa9085fe4>] kthread+0xe4/0x100
[  681.774994]  [<ffffffffa9085f00>] ? kthread_worker_fn+0x170/0x170
[  681.774995]  [<ffffffffa95d8d1e>] ret_from_fork+0x3e/0x70

mq/mqprio have their own ways to report qlen/drops by folding stats on
all their queues, with appropriate locking.

A second problem is that qdisc_tree_decrease_qlen() calls qdisc_lookup()
without proper locking : concurrent qdisc updates could corrupt the list
that qdisc_match_from_root() parses to find a qdisc given its handle.

Fix first problem adding a TCQ_F_NOPARENT qdisc flag that
qdisc_tree_decrease_qlen() can use to abort its tree traversal,
as soon as it meets a mq/mqprio qdisc children.

Second problem can be fixed by RCU protection.
Qdisc are already freed after RCU grace period, so qdisc_list_add() and
qdisc_list_del() simply have to use appropriate rcu list variants.

A future patch will add a per struct netdev_queue list anchor, so that
qdisc_tree_decrease_qlen() can have more efficient lookups.

Reported-by: Daniele Fucini <dfucini@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Cong Wang <cwang@twopensource.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h |  3 +++
 net/sched/sch_api.c       | 27 ++++++++++++++++++---------
 net/sched/sch_generic.c   |  2 +-
 net/sched/sch_mq.c        |  4 ++--
 net/sched/sch_mqprio.c    |  4 ++--
 5 files changed, 26 insertions(+), 14 deletions(-)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 6d778ef..080b657 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -61,6 +61,9 @@ struct Qdisc {
 				      */
 #define TCQ_F_WARN_NONWC	(1 << 16)
 #define TCQ_F_CPUSTATS		0x20 /* run using percpu statistics */
+#define TCQ_F_NOPARENT		0x40 /* root of its hierarchy :
+				      * qdisc_tree_decrease_qlen() should stop.
+				      */
 	u32			limit;
 	const struct Qdisc_ops	*ops;
 	struct qdisc_size_table	__rcu *stab;
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 1e1c89e..d4b6f36 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -253,7 +253,8 @@ int qdisc_set_default(const char *name)
 }
 
 /* We know handle. Find qdisc among all qdisc's attached to device
-   (root qdisc, all its children, children of children etc.)
+ * (root qdisc, all its children, children of children etc.)
+ * Note: caller either uses rtnl or rcu_read_lock()
  */
 
 static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle)
@@ -264,7 +265,7 @@ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle)
 	    root->handle == handle)
 		return root;
 
-	list_for_each_entry(q, &root->list, list) {
+	list_for_each_entry_rcu(q, &root->list, list) {
 		if (q->handle == handle)
 			return q;
 	}
@@ -277,15 +278,18 @@ void qdisc_list_add(struct Qdisc *q)
 		struct Qdisc *root = qdisc_dev(q)->qdisc;
 
 		WARN_ON_ONCE(root == &noop_qdisc);
-		list_add_tail(&q->list, &root->list);
+		ASSERT_RTNL();
+		list_add_tail_rcu(&q->list, &root->list);
 	}
 }
 EXPORT_SYMBOL(qdisc_list_add);
 
 void qdisc_list_del(struct Qdisc *q)
 {
-	if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS))
-		list_del(&q->list);
+	if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) {
+		ASSERT_RTNL();
+		list_del_rcu(&q->list);
+	}
 }
 EXPORT_SYMBOL(qdisc_list_del);
 
@@ -750,14 +754,18 @@ void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
 	if (n == 0)
 		return;
 	drops = max_t(int, n, 0);
+	rcu_read_lock();
 	while ((parentid = sch->parent)) {
 		if (TC_H_MAJ(parentid) == TC_H_MAJ(TC_H_INGRESS))
-			return;
+			break;
 
+		if (sch->flags & TCQ_F_NOPARENT)
+			break;
+		/* TODO: perform the search on a per txq basis */
 		sch = qdisc_lookup(qdisc_dev(sch), TC_H_MAJ(parentid));
 		if (sch == NULL) {
-			WARN_ON(parentid != TC_H_ROOT);
-			return;
+			WARN_ON_ONCE(parentid != TC_H_ROOT);
+			break;
 		}
 		cops = sch->ops->cl_ops;
 		if (cops->qlen_notify) {
@@ -768,6 +776,7 @@ void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
 		sch->q.qlen -= n;
 		__qdisc_qstats_drop(sch, drops);
 	}
+	rcu_read_unlock();
 }
 EXPORT_SYMBOL(qdisc_tree_decrease_qlen);
 
@@ -941,7 +950,7 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue,
 		}
 		lockdep_set_class(qdisc_lock(sch), &qdisc_tx_lock);
 		if (!netif_is_multiqueue(dev))
-			sch->flags |= TCQ_F_ONETXQUEUE;
+			sch->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
 	}
 
 	sch->handle = handle;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 6efca30..b453270 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -743,7 +743,7 @@ static void attach_one_default_qdisc(struct net_device *dev,
 			return;
 		}
 		if (!netif_is_multiqueue(dev))
-			qdisc->flags |= TCQ_F_ONETXQUEUE;
+			qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
 	}
 	dev_queue->qdisc_sleeping = qdisc;
 }
diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
index f3cbaec..3e82f04 100644
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -63,7 +63,7 @@ static int mq_init(struct Qdisc *sch, struct nlattr *opt)
 		if (qdisc == NULL)
 			goto err;
 		priv->qdiscs[ntx] = qdisc;
-		qdisc->flags |= TCQ_F_ONETXQUEUE;
+		qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
 	}
 
 	sch->flags |= TCQ_F_MQROOT;
@@ -156,7 +156,7 @@ static int mq_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new,
 
 	*old = dev_graft_qdisc(dev_queue, new);
 	if (new)
-		new->flags |= TCQ_F_ONETXQUEUE;
+		new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
 	if (dev->flags & IFF_UP)
 		dev_activate(dev);
 	return 0;
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index 3811a74..ad70ecf 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -132,7 +132,7 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt)
 			goto err;
 		}
 		priv->qdiscs[i] = qdisc;
-		qdisc->flags |= TCQ_F_ONETXQUEUE;
+		qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
 	}
 
 	/* If the mqprio options indicate that hardware should own
@@ -209,7 +209,7 @@ static int mqprio_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new,
 	*old = dev_graft_qdisc(dev_queue, new);
 
 	if (new)
-		new->flags |= TCQ_F_ONETXQUEUE;
+		new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
 
 	if (dev->flags & IFF_UP)
 		dev_activate(dev);
-- 
2.4.1


[-- Attachment #4: net_42.mbox --]
[-- Type: Application/Octet-Stream, Size: 122630 bytes --]

From 0fd118097a0c34dec4fdd39716ce644de9d36bcd Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Tue, 10 Nov 2015 16:23:15 +0100
Subject: [PATCH 01/37] af-unix: fix use-after-free with concurrent readers
 while splicing

[ Upstream commit 73ed5d25dce0354ea381d6dc93005c3085fae03d ]

During splicing an af-unix socket to a pipe we have to drop all
af-unix socket locks. While doing so we allow another reader to enter
unix_stream_read_generic which can read, copy and finally free another
skb. If exactly this skb is just in process of being spliced we get a
use-after-free report by kasan.

First, we must make sure to not have a free while the skb is used during
the splice operation. We simply increment its use counter before unlocking
the reader lock.

Stream sockets have the nice characteristic that we don't care about
zero length writes and they never reach the peer socket's queue. That
said, we can take the UNIXCB.consumed field as the indicator if the
skb was already freed from the socket's receive queue. If the skb was
fully consumed after we locked the reader side again we know it has been
dropped by a second reader. We indicate a short read to user space and
abort the current splice operation.

This bug has been found with syzkaller
(http://github.com/google/syzkaller) by Dmitry Vyukov.

Fixes: 2b514574f7e8 ("net: af_unix: implement splice for stream af_unix sockets")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 94f6582..a5afe41 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -440,6 +440,7 @@ static void unix_release_sock(struct sock *sk, int embrion)
 		if (state == TCP_LISTEN)
 			unix_release_sock(skb->sk, 1);
 		/* passed fds are erased in the kfree_skb hook	      */
+		UNIXCB(skb).consumed = skb->len;
 		kfree_skb(skb);
 	}
 
@@ -2071,6 +2072,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state)
 
 	do {
 		int chunk;
+		bool drop_skb;
 		struct sk_buff *skb, *last;
 
 		unix_state_lock(sk);
@@ -2151,7 +2153,11 @@ unlock:
 		}
 
 		chunk = min_t(unsigned int, unix_skb_len(skb) - skip, size);
+		skb_get(skb);
 		chunk = state->recv_actor(skb, skip, chunk, state);
+		drop_skb = !unix_skb_len(skb);
+		/* skb is only safe to use if !drop_skb */
+		consume_skb(skb);
 		if (chunk < 0) {
 			if (copied == 0)
 				copied = -EFAULT;
@@ -2160,6 +2166,18 @@ unlock:
 		copied += chunk;
 		size -= chunk;
 
+		if (drop_skb) {
+			/* the skb was touched by a concurrent reader;
+			 * we should not expect anything from this skb
+			 * anymore and assume it invalid - we can be
+			 * sure it was dropped from the socket queue
+			 *
+			 * let's report a short read
+			 */
+			err = 0;
+			break;
+		}
+
 		/* Mark read part of skb as used */
 		if (!(flags & MSG_PEEK)) {
 			UNIXCB(skb).consumed += chunk;
-- 
2.1.0


From 1d24912c692fae2c2903feee18abfa4ed02ee4a3 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Mon, 16 Nov 2015 16:25:56 +0100
Subject: [PATCH 02/37] af_unix: don't append consumed skbs to sk_receive_queue

[ Upstream commit 8844f97238ca6c1ca92a5d6c69f53efd361a266f ]

In case multiple writes to a unix stream socket race we could end up in a
situation where we pre-allocate a new skb for use in unix_stream_sendpage
but have to free it again in the locked section because another skb
has been appended meanwhile, which we must use. Accidentally we didn't
clear the pointer after consuming it and so we touched freed memory
while appending it to the sk_receive_queue. So, clear the pointer after
consuming the skb.

This bug has been found with syzkaller
(http://github.com/google/syzkaller) by Dmitry Vyukov.

Fixes: 869e7c62486e ("net: af_unix: implement stream sendpage support")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index a5afe41..3e2ca39 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1799,6 +1799,7 @@ alloc_skb:
 		 * this - does no harm
 		 */
 		consume_skb(newskb);
+		newskb = NULL;
 	}
 
 	if (skb_append_pagefrags(skb, page, offset, size)) {
-- 
2.1.0


From 2607ebe2281295959ca39d65f07c2bdacd2afe55 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Tue, 17 Nov 2015 15:10:59 +0100
Subject: [PATCH 03/37] af_unix: take receive queue lock while appending new
 skb

[ Upstream commit a3a116e04cc6a94d595ead4e956ab1bc1d2f4746 ]

While possibly in future we don't necessarily need to use
sk_buff_head.lock this is a rather larger change, as it affects the
af_unix fd garbage collector, diag and socket cleanups. This is too much
for a stable patch.

For the time being grab sk_buff_head.lock without disabling bh and irqs,
so don't use locked skb_queue_tail.

Fixes: 869e7c62486e ("net: af_unix: implement stream sendpage support")
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Reported-by: Eric Dumazet <edumazet@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 3e2ca39..42ab2cc 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1812,8 +1812,11 @@ alloc_skb:
 	skb->truesize += size;
 	atomic_add(size, &sk->sk_wmem_alloc);
 
-	if (newskb)
+	if (newskb) {
+		spin_lock(&other->sk_receive_queue.lock);
 		__skb_queue_tail(&other->sk_receive_queue, newskb);
+		spin_unlock(&other->sk_receive_queue.lock);
+	}
 
 	unix_state_unlock(other);
 	mutex_unlock(&unix_sk(other)->readlock);
-- 
2.1.0


From 918a9490949ffc1a920d695c2d5f5f83c87906de Mon Sep 17 00:00:00 2001
From: Rainer Weikusat <rweikusat@mobileactivedefense.com>
Date: Fri, 20 Nov 2015 22:07:23 +0000
Subject: [PATCH 04/37] unix: avoid use-after-free in ep_remove_wait_queue

[ Upstream commit 7d267278a9ece963d77eefec61630223fce08c6c ]

Rainer Weikusat <rweikusat@mobileactivedefense.com> writes:
An AF_UNIX datagram socket being the client in an n:1 association with
some server socket is only allowed to send messages to the server if the
receive queue of this socket contains at most sk_max_ack_backlog
datagrams. This implies that prospective writers might be forced to go
to sleep despite none of the message presently enqueued on the server
receive queue were sent by them. In order to ensure that these will be
woken up once space becomes again available, the present unix_dgram_poll
routine does a second sock_poll_wait call with the peer_wait wait queue
of the server socket as queue argument (unix_dgram_recvmsg does a wake
up on this queue after a datagram was received). This is inherently
problematic because the server socket is only guaranteed to remain alive
for as long as the client still holds a reference to it. In case the
connection is dissolved via connect or by the dead peer detection logic
in unix_dgram_sendmsg, the server socket may be freed despite "the
polling mechanism" (in particular, epoll) still has a pointer to the
corresponding peer_wait queue. There's no way to forcibly deregister a
wait queue with epoll.

Based on an idea by Jason Baron, the patch below changes the code such
that a wait_queue_t belonging to the client socket is enqueued on the
peer_wait queue of the server whenever the peer receive queue full
condition is detected by either a sendmsg or a poll. A wake up on the
peer queue is then relayed to the ordinary wait queue of the client
socket via wake function. The connection to the peer wait queue is again
dissolved if either a wake up is about to be relayed or the client
socket reconnects or a dead peer is detected or the client socket is
itself closed. This enables removing the second sock_poll_wait from
unix_dgram_poll, thus avoiding the use-after-free, while still ensuring
that no blocked writer sleeps forever.

Signed-off-by: Rainer Weikusat <rweikusat@mobileactivedefense.com>
Fixes: ec0d215f9420 ("af_unix: fix 'poll for write'/connected DGRAM sockets")
Reviewed-by: Jason Baron <jbaron@akamai.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/af_unix.h |   1 +
 net/unix/af_unix.c    | 183 ++++++++++++++++++++++++++++++++++++++++++++------
 2 files changed, 165 insertions(+), 19 deletions(-)

diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index cb1b9bb..49c7683 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -62,6 +62,7 @@ struct unix_sock {
 #define UNIX_GC_CANDIDATE	0
 #define UNIX_GC_MAYBE_CYCLE	1
 	struct socket_wq	peer_wq;
+	wait_queue_t		peer_wake;
 };
 
 static inline struct unix_sock *unix_sk(struct sock *sk)
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 42ab2cc..153b2f2 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -326,6 +326,118 @@ found:
 	return s;
 }
 
+/* Support code for asymmetrically connected dgram sockets
+ *
+ * If a datagram socket is connected to a socket not itself connected
+ * to the first socket (eg, /dev/log), clients may only enqueue more
+ * messages if the present receive queue of the server socket is not
+ * "too large". This means there's a second writeability condition
+ * poll and sendmsg need to test. The dgram recv code will do a wake
+ * up on the peer_wait wait queue of a socket upon reception of a
+ * datagram which needs to be propagated to sleeping would-be writers
+ * since these might not have sent anything so far. This can't be
+ * accomplished via poll_wait because the lifetime of the server
+ * socket might be less than that of its clients if these break their
+ * association with it or if the server socket is closed while clients
+ * are still connected to it and there's no way to inform "a polling
+ * implementation" that it should let go of a certain wait queue
+ *
+ * In order to propagate a wake up, a wait_queue_t of the client
+ * socket is enqueued on the peer_wait queue of the server socket
+ * whose wake function does a wake_up on the ordinary client socket
+ * wait queue. This connection is established whenever a write (or
+ * poll for write) hit the flow control condition and broken when the
+ * association to the server socket is dissolved or after a wake up
+ * was relayed.
+ */
+
+static int unix_dgram_peer_wake_relay(wait_queue_t *q, unsigned mode, int flags,
+				      void *key)
+{
+	struct unix_sock *u;
+	wait_queue_head_t *u_sleep;
+
+	u = container_of(q, struct unix_sock, peer_wake);
+
+	__remove_wait_queue(&unix_sk(u->peer_wake.private)->peer_wait,
+			    q);
+	u->peer_wake.private = NULL;
+
+	/* relaying can only happen while the wq still exists */
+	u_sleep = sk_sleep(&u->sk);
+	if (u_sleep)
+		wake_up_interruptible_poll(u_sleep, key);
+
+	return 0;
+}
+
+static int unix_dgram_peer_wake_connect(struct sock *sk, struct sock *other)
+{
+	struct unix_sock *u, *u_other;
+	int rc;
+
+	u = unix_sk(sk);
+	u_other = unix_sk(other);
+	rc = 0;
+	spin_lock(&u_other->peer_wait.lock);
+
+	if (!u->peer_wake.private) {
+		u->peer_wake.private = other;
+		__add_wait_queue(&u_other->peer_wait, &u->peer_wake);
+
+		rc = 1;
+	}
+
+	spin_unlock(&u_other->peer_wait.lock);
+	return rc;
+}
+
+static void unix_dgram_peer_wake_disconnect(struct sock *sk,
+					    struct sock *other)
+{
+	struct unix_sock *u, *u_other;
+
+	u = unix_sk(sk);
+	u_other = unix_sk(other);
+	spin_lock(&u_other->peer_wait.lock);
+
+	if (u->peer_wake.private == other) {
+		__remove_wait_queue(&u_other->peer_wait, &u->peer_wake);
+		u->peer_wake.private = NULL;
+	}
+
+	spin_unlock(&u_other->peer_wait.lock);
+}
+
+static void unix_dgram_peer_wake_disconnect_wakeup(struct sock *sk,
+						   struct sock *other)
+{
+	unix_dgram_peer_wake_disconnect(sk, other);
+	wake_up_interruptible_poll(sk_sleep(sk),
+				   POLLOUT |
+				   POLLWRNORM |
+				   POLLWRBAND);
+}
+
+/* preconditions:
+ *	- unix_peer(sk) == other
+ *	- association is stable
+ */
+static int unix_dgram_peer_wake_me(struct sock *sk, struct sock *other)
+{
+	int connected;
+
+	connected = unix_dgram_peer_wake_connect(sk, other);
+
+	if (unix_recvq_full(other))
+		return 1;
+
+	if (connected)
+		unix_dgram_peer_wake_disconnect(sk, other);
+
+	return 0;
+}
+
 static inline int unix_writable(struct sock *sk)
 {
 	return (atomic_read(&sk->sk_wmem_alloc) << 2) <= sk->sk_sndbuf;
@@ -430,6 +542,8 @@ static void unix_release_sock(struct sock *sk, int embrion)
 			skpair->sk_state_change(skpair);
 			sk_wake_async(skpair, SOCK_WAKE_WAITD, POLL_HUP);
 		}
+
+		unix_dgram_peer_wake_disconnect(sk, skpair);
 		sock_put(skpair); /* It may now die */
 		unix_peer(sk) = NULL;
 	}
@@ -665,6 +779,7 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern)
 	INIT_LIST_HEAD(&u->link);
 	mutex_init(&u->readlock); /* single task reading lock */
 	init_waitqueue_head(&u->peer_wait);
+	init_waitqueue_func_entry(&u->peer_wake, unix_dgram_peer_wake_relay);
 	unix_insert_socket(unix_sockets_unbound(sk), sk);
 out:
 	if (sk == NULL)
@@ -1032,6 +1147,8 @@ restart:
 	if (unix_peer(sk)) {
 		struct sock *old_peer = unix_peer(sk);
 		unix_peer(sk) = other;
+		unix_dgram_peer_wake_disconnect_wakeup(sk, old_peer);
+
 		unix_state_double_unlock(sk, other);
 
 		if (other != old_peer)
@@ -1471,6 +1588,7 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 	struct scm_cookie scm;
 	int max_level;
 	int data_len = 0;
+	int sk_locked;
 
 	wait_for_unix_gc();
 	err = scm_send(sock, msg, &scm, false);
@@ -1549,12 +1667,14 @@ restart:
 		goto out_free;
 	}
 
+	sk_locked = 0;
 	unix_state_lock(other);
+restart_locked:
 	err = -EPERM;
 	if (!unix_may_send(sk, other))
 		goto out_unlock;
 
-	if (sock_flag(other, SOCK_DEAD)) {
+	if (unlikely(sock_flag(other, SOCK_DEAD))) {
 		/*
 		 *	Check with 1003.1g - what should
 		 *	datagram error
@@ -1562,10 +1682,14 @@ restart:
 		unix_state_unlock(other);
 		sock_put(other);
 
+		if (!sk_locked)
+			unix_state_lock(sk);
+
 		err = 0;
-		unix_state_lock(sk);
 		if (unix_peer(sk) == other) {
 			unix_peer(sk) = NULL;
+			unix_dgram_peer_wake_disconnect_wakeup(sk, other);
+
 			unix_state_unlock(sk);
 
 			unix_dgram_disconnected(sk, other);
@@ -1591,21 +1715,38 @@ restart:
 			goto out_unlock;
 	}
 
-	if (unix_peer(other) != sk && unix_recvq_full(other)) {
-		if (!timeo) {
-			err = -EAGAIN;
-			goto out_unlock;
+	if (unlikely(unix_peer(other) != sk && unix_recvq_full(other))) {
+		if (timeo) {
+			timeo = unix_wait_for_peer(other, timeo);
+
+			err = sock_intr_errno(timeo);
+			if (signal_pending(current))
+				goto out_free;
+
+			goto restart;
 		}
 
-		timeo = unix_wait_for_peer(other, timeo);
+		if (!sk_locked) {
+			unix_state_unlock(other);
+			unix_state_double_lock(sk, other);
+		}
 
-		err = sock_intr_errno(timeo);
-		if (signal_pending(current))
-			goto out_free;
+		if (unix_peer(sk) != other ||
+		    unix_dgram_peer_wake_me(sk, other)) {
+			err = -EAGAIN;
+			sk_locked = 1;
+			goto out_unlock;
+		}
 
-		goto restart;
+		if (!sk_locked) {
+			sk_locked = 1;
+			goto restart_locked;
+		}
 	}
 
+	if (unlikely(sk_locked))
+		unix_state_unlock(sk);
+
 	if (sock_flag(other, SOCK_RCVTSTAMP))
 		__net_timestamp(skb);
 	maybe_add_creds(skb, sock, other);
@@ -1619,6 +1760,8 @@ restart:
 	return len;
 
 out_unlock:
+	if (sk_locked)
+		unix_state_unlock(sk);
 	unix_state_unlock(other);
 out_free:
 	kfree_skb(skb);
@@ -2475,14 +2618,16 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock,
 		return mask;
 
 	writable = unix_writable(sk);
-	other = unix_peer_get(sk);
-	if (other) {
-		if (unix_peer(other) != sk) {
-			sock_poll_wait(file, &unix_sk(other)->peer_wait, wait);
-			if (unix_recvq_full(other))
-				writable = 0;
-		}
-		sock_put(other);
+	if (writable) {
+		unix_state_lock(sk);
+
+		other = unix_peer(sk);
+		if (other && unix_peer(other) != sk &&
+		    unix_recvq_full(other) &&
+		    unix_dgram_peer_wake_me(sk, other))
+			writable = 0;
+
+		unix_state_unlock(sk);
 	}
 
 	if (writable)
-- 
2.1.0


From da5d960dbf4f1746d0055d668c5439e4bacbb5d9 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Thu, 26 Nov 2015 12:08:18 +0100
Subject: [PATCH 05/37] af-unix: passcred support for sendpage

[ Upstream commit 9490f886b192964796285907d777ff00fba1fa0f ]

sendpage did not care about credentials at all. This could lead to
situations in which because of fd passing between processes we could
append data to skbs with different scm data. It is illegal to splice those
skbs together. Instead we have to allocate a new skb and if requested
fill out the scm details.

Fixes: 869e7c62486ec ("net: af_unix: implement stream sendpage support")
Reported-by: Al Viro <viro@zeniv.linux.org.uk>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c | 79 +++++++++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 64 insertions(+), 15 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 153b2f2..128b098 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1550,6 +1550,14 @@ static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool sen
 	return err;
 }
 
+static bool unix_passcred_enabled(const struct socket *sock,
+				  const struct sock *other)
+{
+	return test_bit(SOCK_PASSCRED, &sock->flags) ||
+	       !other->sk_socket ||
+	       test_bit(SOCK_PASSCRED, &other->sk_socket->flags);
+}
+
 /*
  * Some apps rely on write() giving SCM_CREDENTIALS
  * We include credentials if source or destination socket
@@ -1560,14 +1568,41 @@ static void maybe_add_creds(struct sk_buff *skb, const struct socket *sock,
 {
 	if (UNIXCB(skb).pid)
 		return;
-	if (test_bit(SOCK_PASSCRED, &sock->flags) ||
-	    !other->sk_socket ||
-	    test_bit(SOCK_PASSCRED, &other->sk_socket->flags)) {
+	if (unix_passcred_enabled(sock, other)) {
 		UNIXCB(skb).pid  = get_pid(task_tgid(current));
 		current_uid_gid(&UNIXCB(skb).uid, &UNIXCB(skb).gid);
 	}
 }
 
+static int maybe_init_creds(struct scm_cookie *scm,
+			    struct socket *socket,
+			    const struct sock *other)
+{
+	int err;
+	struct msghdr msg = { .msg_controllen = 0 };
+
+	err = scm_send(socket, &msg, scm, false);
+	if (err)
+		return err;
+
+	if (unix_passcred_enabled(socket, other)) {
+		scm->pid = get_pid(task_tgid(current));
+		current_uid_gid(&scm->creds.uid, &scm->creds.gid);
+	}
+	return err;
+}
+
+static bool unix_skb_scm_eq(struct sk_buff *skb,
+			    struct scm_cookie *scm)
+{
+	const struct unix_skb_parms *u = &UNIXCB(skb);
+
+	return u->pid == scm->pid &&
+	       uid_eq(u->uid, scm->creds.uid) &&
+	       gid_eq(u->gid, scm->creds.gid) &&
+	       unix_secdata_eq(scm, skb);
+}
+
 /*
  *	Send AF_UNIX data.
  */
@@ -1883,8 +1918,10 @@ out_err:
 static ssize_t unix_stream_sendpage(struct socket *socket, struct page *page,
 				    int offset, size_t size, int flags)
 {
-	int err = 0;
-	bool send_sigpipe = true;
+	int err;
+	bool send_sigpipe = false;
+	bool init_scm = true;
+	struct scm_cookie scm;
 	struct sock *other, *sk = socket->sk;
 	struct sk_buff *skb, *newskb = NULL, *tail = NULL;
 
@@ -1902,7 +1939,7 @@ alloc_skb:
 		newskb = sock_alloc_send_pskb(sk, 0, 0, flags & MSG_DONTWAIT,
 					      &err, 0);
 		if (!newskb)
-			return err;
+			goto err;
 	}
 
 	/* we must acquire readlock as we modify already present
@@ -1911,12 +1948,12 @@ alloc_skb:
 	err = mutex_lock_interruptible(&unix_sk(other)->readlock);
 	if (err) {
 		err = flags & MSG_DONTWAIT ? -EAGAIN : -ERESTARTSYS;
-		send_sigpipe = false;
 		goto err;
 	}
 
 	if (sk->sk_shutdown & SEND_SHUTDOWN) {
 		err = -EPIPE;
+		send_sigpipe = true;
 		goto err_unlock;
 	}
 
@@ -1925,17 +1962,27 @@ alloc_skb:
 	if (sock_flag(other, SOCK_DEAD) ||
 	    other->sk_shutdown & RCV_SHUTDOWN) {
 		err = -EPIPE;
+		send_sigpipe = true;
 		goto err_state_unlock;
 	}
 
+	if (init_scm) {
+		err = maybe_init_creds(&scm, socket, other);
+		if (err)
+			goto err_state_unlock;
+		init_scm = false;
+	}
+
 	skb = skb_peek_tail(&other->sk_receive_queue);
 	if (tail && tail == skb) {
 		skb = newskb;
-	} else if (!skb) {
-		if (newskb)
+	} else if (!skb || !unix_skb_scm_eq(skb, &scm)) {
+		if (newskb) {
 			skb = newskb;
-		else
+		} else {
+			tail = skb;
 			goto alloc_skb;
+		}
 	} else if (newskb) {
 		/* this is fast path, we don't necessarily need to
 		 * call to kfree_skb even though with newskb == NULL
@@ -1956,6 +2003,9 @@ alloc_skb:
 	atomic_add(size, &sk->sk_wmem_alloc);
 
 	if (newskb) {
+		err = unix_scm_to_skb(&scm, skb, false);
+		if (err)
+			goto err_state_unlock;
 		spin_lock(&other->sk_receive_queue.lock);
 		__skb_queue_tail(&other->sk_receive_queue, newskb);
 		spin_unlock(&other->sk_receive_queue.lock);
@@ -1965,7 +2015,7 @@ alloc_skb:
 	mutex_unlock(&unix_sk(other)->readlock);
 
 	other->sk_data_ready(other);
-
+	scm_destroy(&scm);
 	return size;
 
 err_state_unlock:
@@ -1976,6 +2026,8 @@ err:
 	kfree_skb(newskb);
 	if (send_sigpipe && !(flags & MSG_NOSIGNAL))
 		send_sig(SIGPIPE, current, 0);
+	if (!init_scm)
+		scm_destroy(&scm);
 	return err;
 }
 
@@ -2279,10 +2331,7 @@ unlock:
 
 		if (check_creds) {
 			/* Never glue messages from different writers */
-			if ((UNIXCB(skb).pid  != scm.pid) ||
-			    !uid_eq(UNIXCB(skb).uid, scm.creds.uid) ||
-			    !gid_eq(UNIXCB(skb).gid, scm.creds.gid) ||
-			    !unix_secdata_eq(&scm, skb))
+			if (!unix_skb_scm_eq(skb, &scm))
 				break;
 		} else if (test_bit(SOCK_PASSCRED, &sock->flags)) {
 			/* Copy credentials */
-- 
2.1.0


From 17a04262d29701d1aae327645916a427deb79636 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 11 Nov 2015 11:51:06 -0800
Subject: [PATCH 06/37] ipv6: Avoid creating RTF_CACHE from a rt that is not
 managed by fib6 tree

[ Upstream commit 0d3f6d297bfb7af24d0508460fdb3d1ec4903fa3 ]

The original bug report:
https://bugzilla.redhat.com/show_bug.cgi?id=1272571

The setup has a IPv4 GRE tunnel running in a IPSec.  The bug
happens when ndisc starts sending router solicitation at the gre
interface.  The simplified oops stack is like:

__lock_acquire+0x1b2/0x1c30
lock_acquire+0xb9/0x140
_raw_write_lock_bh+0x3f/0x50
__ip6_ins_rt+0x2e/0x60
ip6_ins_rt+0x49/0x50
~~~~~~~~
__ip6_rt_update_pmtu.part.54+0x145/0x250
ip6_rt_update_pmtu+0x2e/0x40
~~~~~~~~
ip_tunnel_xmit+0x1f1/0xf40
__gre_xmit+0x7a/0x90
ipgre_xmit+0x15a/0x220
dev_hard_start_xmit+0x2bd/0x480
__dev_queue_xmit+0x696/0x730
dev_queue_xmit+0x10/0x20
neigh_direct_output+0x11/0x20
ip6_finish_output2+0x21f/0x770
ip6_finish_output+0xa7/0x1d0
ip6_output+0x56/0x190
~~~~~~~~
ndisc_send_skb+0x1d9/0x400
ndisc_send_rs+0x88/0xc0
~~~~~~~~

The rt passed to ip6_rt_update_pmtu() is created by
icmp6_dst_alloc() and it is not managed by the fib6 tree,
so its rt6i_table == NULL.  When __ip6_rt_update_pmtu() creates
a RTF_CACHE clone, the newly created clone also has rt6i_table == NULL
and it causes the ip6_ins_rt() oops.

During pmtu update, we only want to create a RTF_CACHE clone
from a rt which is currently managed (or owned) by the
fib6 tree.  It means either rt->rt6i_node != NULL or
rt is a RTF_PCPU clone.

It is worth to note that rt6i_table may not be NULL even it is
not (yet) managed by the fib6 tree (e.g. addrconf_dst_alloc()).
Hence, rt6i_node is a better check instead of rt6i_table.

Fixes: 45e4fd26683c ("ipv6: Only create RTF_CACHE routes after encountering pmtu")
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Reported-by: Chris Siebenmann <cks-rhbugzilla@cs.toronto.edu>
Cc: Chris Siebenmann <cks-rhbugzilla@cs.toronto.edu>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index dd6ebba..5533cb4 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1326,6 +1326,12 @@ static void rt6_do_update_pmtu(struct rt6_info *rt, u32 mtu)
 	rt6_update_expires(rt, net->ipv6.sysctl.ip6_rt_mtu_expires);
 }
 
+static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt)
+{
+	return !(rt->rt6i_flags & RTF_CACHE) &&
+		(rt->rt6i_flags & RTF_PCPU || rt->rt6i_node);
+}
+
 static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
 				 const struct ipv6hdr *iph, u32 mtu)
 {
@@ -1339,7 +1345,7 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
 	if (mtu >= dst_mtu(dst))
 		return;
 
-	if (rt6->rt6i_flags & RTF_CACHE) {
+	if (!rt6_cache_allowed_for_pmtu(rt6)) {
 		rt6_do_update_pmtu(rt6, mtu);
 	} else {
 		const struct in6_addr *daddr, *saddr;
-- 
2.1.0


From f9cbc9ca6507dbe0f472cf4fcb0c407b0883c2ed Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 11 Nov 2015 11:51:07 -0800
Subject: [PATCH 07/37] ipv6: Check expire on DST_NOCACHE route

[ Upstream commit 5973fb1e245086071bf71994c8b54d99526ded03 ]

Since the expires of the DST_NOCACHE rt can be set during
the ip6_rt_update_pmtu(), we also need to consider the expires
value when doing ip6_dst_check().

This patches creates __rt6_check_expired() to only
check the expire value (if one exists) of the current rt.

In rt6_dst_from_check(), it adds __rt6_check_expired() as
one of the condition check.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 5533cb4..fcb239b 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -401,6 +401,14 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
 	}
 }
 
+static bool __rt6_check_expired(const struct rt6_info *rt)
+{
+	if (rt->rt6i_flags & RTF_EXPIRES)
+		return time_after(jiffies, rt->dst.expires);
+	else
+		return false;
+}
+
 static bool rt6_check_expired(const struct rt6_info *rt)
 {
 	if (rt->rt6i_flags & RTF_EXPIRES) {
@@ -1255,7 +1263,8 @@ static struct dst_entry *rt6_check(struct rt6_info *rt, u32 cookie)
 
 static struct dst_entry *rt6_dst_from_check(struct rt6_info *rt, u32 cookie)
 {
-	if (rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK &&
+	if (!__rt6_check_expired(rt) &&
+	    rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK &&
 	    rt6_check((struct rt6_info *)(rt->dst.from), cookie))
 		return &rt->dst;
 	else
-- 
2.1.0


From 340d0787b0972ef4147101bf5e55b823d8df5757 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 11 Nov 2015 11:51:08 -0800
Subject: [PATCH 08/37] ipv6: Check rt->dst.from for the DST_NOCACHE route

[ Upstrem commit 02bcf4e082e4dc634409a6a6cb7def8806d6e5e6 ]

All DST_NOCACHE rt6_info used to have rt->dst.from set to
its parent.

After commit 8e3d5be73681 ("ipv6: Avoid double dst_free"),
DST_NOCACHE is also set to rt6_info which does not have
a parent (i.e. rt->dst.from is NULL).

This patch catches the rt->dst.from == NULL case.

Fixes: 8e3d5be73681 ("ipv6: Avoid double dst_free")
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h | 3 ++-
 net/ipv6/route.c      | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 3b76849..75a888c 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -165,7 +165,8 @@ static inline void rt6_update_expires(struct rt6_info *rt0, int timeout)
 
 static inline u32 rt6_get_cookie(const struct rt6_info *rt)
 {
-	if (rt->rt6i_flags & RTF_PCPU || unlikely(rt->dst.flags & DST_NOCACHE))
+	if (rt->rt6i_flags & RTF_PCPU ||
+	    (unlikely(rt->dst.flags & DST_NOCACHE) && rt->dst.from))
 		rt = (struct rt6_info *)(rt->dst.from);
 
 	return rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index fcb239b..8478719 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1284,7 +1284,8 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
 
 	rt6_dst_from_metrics_check(rt);
 
-	if ((rt->rt6i_flags & RTF_PCPU) || unlikely(dst->flags & DST_NOCACHE))
+	if (rt->rt6i_flags & RTF_PCPU ||
+	    (unlikely(dst->flags & DST_NOCACHE) && rt->dst.from))
 		return rt6_dst_from_check(rt, cookie);
 	else
 		return rt6_check(rt, cookie);
-- 
2.1.0


From 40acbe3e895c5d0ece424eaeb01a021068a36e10 Mon Sep 17 00:00:00 2001
From: Kamal Mostafa <kamal@canonical.com>
Date: Wed, 11 Nov 2015 14:24:27 -0800
Subject: [PATCH 09/37] tools/net: Use include/uapi with __EXPORTED_HEADERS__

[ Upstream commit d7475de58575c904818efa369c82e88c6648ce2e ]

Use the local uapi headers to keep in sync with "recently" added #define's
(e.g. SKF_AD_VLAN_TPID).  Refactored CFLAGS, and bpf_asm doesn't need -I.

Fixes: 3f356385e8a4 ("filter: bpf_asm: add minimal bpf asm tool")
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/net/Makefile | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/tools/net/Makefile b/tools/net/Makefile
index ee577ea..ddf8880 100644
--- a/tools/net/Makefile
+++ b/tools/net/Makefile
@@ -4,6 +4,9 @@ CC = gcc
 LEX = flex
 YACC = bison
 
+CFLAGS += -Wall -O2
+CFLAGS += -D__EXPORTED_HEADERS__ -I../../include/uapi -I../../include
+
 %.yacc.c: %.y
 	$(YACC) -o $@ -d $<
 
@@ -12,15 +15,13 @@ YACC = bison
 
 all : bpf_jit_disasm bpf_dbg bpf_asm
 
-bpf_jit_disasm : CFLAGS = -Wall -O2 -DPACKAGE='bpf_jit_disasm'
+bpf_jit_disasm : CFLAGS += -DPACKAGE='bpf_jit_disasm'
 bpf_jit_disasm : LDLIBS = -lopcodes -lbfd -ldl
 bpf_jit_disasm : bpf_jit_disasm.o
 
-bpf_dbg : CFLAGS = -Wall -O2
 bpf_dbg : LDLIBS = -lreadline
 bpf_dbg : bpf_dbg.o
 
-bpf_asm : CFLAGS = -Wall -O2 -I.
 bpf_asm : LDLIBS =
 bpf_asm : bpf_asm.o bpf_exp.yacc.o bpf_exp.lex.o
 bpf_exp.lex.o : bpf_exp.yacc.c
-- 
2.1.0


From a034f79d2acef0a3542c281c704b6ee172380bc6 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 11 Nov 2015 23:25:40 +0100
Subject: [PATCH 10/37] packet: do skb_probe_transport_header when we actually
 have data

[ Upstream commit efdfa2f7848f64517008136fb41f53c4a1faf93a ]

In tpacket_fill_skb() commit c1aad275b029 ("packet: set transport
header before doing xmit") and later on 40893fd0fd4e ("net: switch
to use skb_probe_transport_header()") was probing for a transport
header on the skb from a ring buffer slot, but at a time, where
the skb has _not even_ been filled with data yet. So that call into
the flow dissector is pretty useless. Lets do it after we've set
up the skb frags.

Fixes: c1aad275b029 ("packet: set transport header before doing xmit")
Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 71cb085..ff4586f 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2249,8 +2249,6 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 	skb_reserve(skb, hlen);
 	skb_reset_network_header(skb);
 
-	if (!packet_use_direct_xmit(po))
-		skb_probe_transport_header(skb, 0);
 	if (unlikely(po->tp_tx_has_off)) {
 		int off_min, off_max, off;
 		off_min = po->tp_hdrlen - sizeof(struct sockaddr_ll);
@@ -2330,6 +2328,9 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 		len = ((to_write > len_max) ? len_max : to_write);
 	}
 
+	if (!packet_use_direct_xmit(po))
+		skb_probe_transport_header(skb, 0);
+
 	return tp_len;
 }
 
-- 
2.1.0


From 1cae18b3f25c63298e4807e5c636bb45e9a53da9 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 11 Nov 2015 23:25:41 +0100
Subject: [PATCH 11/37] packet: always probe for transport header

[ Upstream commit 8fd6c80d9dd938ca338c70698533a7e304752846 ]

We concluded that the skb_probe_transport_header() should better be
called unconditionally. Avoiding the call into the flow dissector has
also not really much to do with the direct xmit mode.

While it seems that only virtio_net code makes use of GSO from non
RX/TX ring packet socket paths, we should probe for a transport header
nevertheless before they hit devices.

Reference: http://thread.gmane.org/gmane.linux.network/386173/
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index ff4586f..5b1eadb 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2328,8 +2328,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 		len = ((to_write > len_max) ? len_max : to_write);
 	}
 
-	if (!packet_use_direct_xmit(po))
-		skb_probe_transport_header(skb, 0);
+	skb_probe_transport_header(skb, 0);
 
 	return tp_len;
 }
@@ -2681,8 +2680,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		len += vnet_hdr_len;
 	}
 
-	if (!packet_use_direct_xmit(po))
-		skb_probe_transport_header(skb, reserve);
+	skb_probe_transport_header(skb, reserve);
+
 	if (unlikely(extra_len == 4))
 		skb->no_fcs = 1;
 
-- 
2.1.0


From a98eb2ff39373be45cc5e07efe8917fd664f4065 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 11 Nov 2015 23:25:42 +0100
Subject: [PATCH 12/37] packet: only allow extra vlan len on ethernet devices

[ Upstream commit 3c70c132488794e2489ab045559b0ce0afcf17de ]

Packet sockets can be used by various net devices and are not
really restricted to ARPHRD_ETHER device types. However, when
currently checking for the extra 4 bytes that can be transmitted
in VLAN case, our assumption is that we generally probe on
ARPHRD_ETHER devices. Therefore, before looking into Ethernet
header, check the device type first.

This also fixes the issue where non-ARPHRD_ETHER devices could
have no dev->hard_header_len in TX_RING SOCK_RAW case, and thus
the check would test unfilled linear part of the skb (instead
of non-linear).

Fixes: 57f89bfa2140 ("network: Allow af_packet to transmit +4 bytes for VLAN packets.")
Fixes: 52f1454f629f ("packet: allow to transmit +4 byte in TX_RING slot for VLAN case")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 60 +++++++++++++++++++++-----------------------------
 1 file changed, 25 insertions(+), 35 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 5b1eadb..4710f22 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1622,6 +1622,20 @@ static void fanout_release(struct sock *sk)
 		kfree_rcu(po->rollover, rcu);
 }
 
+static bool packet_extra_vlan_len_allowed(const struct net_device *dev,
+					  struct sk_buff *skb)
+{
+	/* Earlier code assumed this would be a VLAN pkt, double-check
+	 * this now that we have the actual packet in hand. We can only
+	 * do this check on Ethernet devices.
+	 */
+	if (unlikely(dev->type != ARPHRD_ETHER))
+		return false;
+
+	skb_reset_mac_header(skb);
+	return likely(eth_hdr(skb)->h_proto == htons(ETH_P_8021Q));
+}
+
 static const struct proto_ops packet_ops;
 
 static const struct proto_ops packet_ops_spkt;
@@ -1783,18 +1797,10 @@ retry:
 		goto retry;
 	}
 
-	if (len > (dev->mtu + dev->hard_header_len + extra_len)) {
-		/* Earlier code assumed this would be a VLAN pkt,
-		 * double-check this now that we have the actual
-		 * packet in hand.
-		 */
-		struct ethhdr *ehdr;
-		skb_reset_mac_header(skb);
-		ehdr = eth_hdr(skb);
-		if (ehdr->h_proto != htons(ETH_P_8021Q)) {
-			err = -EMSGSIZE;
-			goto out_unlock;
-		}
+	if (len > (dev->mtu + dev->hard_header_len + extra_len) &&
+	    !packet_extra_vlan_len_allowed(dev, skb)) {
+		err = -EMSGSIZE;
+		goto out_unlock;
 	}
 
 	skb->protocol = proto;
@@ -2406,18 +2412,10 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 		tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto,
 					  addr, hlen);
 		if (likely(tp_len >= 0) &&
-		    tp_len > dev->mtu + dev->hard_header_len) {
-			struct ethhdr *ehdr;
-			/* Earlier code assumed this would be a VLAN pkt,
-			 * double-check this now that we have the actual
-			 * packet in hand.
-			 */
+		    tp_len > dev->mtu + dev->hard_header_len &&
+		    !packet_extra_vlan_len_allowed(dev, skb))
+			tp_len = -EMSGSIZE;
 
-			skb_reset_mac_header(skb);
-			ehdr = eth_hdr(skb);
-			if (ehdr->h_proto != htons(ETH_P_8021Q))
-				tp_len = -EMSGSIZE;
-		}
 		if (unlikely(tp_len < 0)) {
 			if (po->tp_loss) {
 				__packet_set_status(po, ph,
@@ -2638,18 +2636,10 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 
 	sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags);
 
-	if (!gso_type && (len > dev->mtu + reserve + extra_len)) {
-		/* Earlier code assumed this would be a VLAN pkt,
-		 * double-check this now that we have the actual
-		 * packet in hand.
-		 */
-		struct ethhdr *ehdr;
-		skb_reset_mac_header(skb);
-		ehdr = eth_hdr(skb);
-		if (ehdr->h_proto != htons(ETH_P_8021Q)) {
-			err = -EMSGSIZE;
-			goto out_free;
-		}
+	if (!gso_type && (len > dev->mtu + reserve + extra_len) &&
+	    !packet_extra_vlan_len_allowed(dev, skb)) {
+		err = -EMSGSIZE;
+		goto out_free;
 	}
 
 	skb->protocol = proto;
-- 
2.1.0


From 97c2fd875f74faa9b79b712908992746d257c97b Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 11 Nov 2015 23:25:43 +0100
Subject: [PATCH 13/37] packet: infer protocol from ethernet header if unset

[ Upstream commit c72219b75fde768efccf7666342282fab7f9e4e7 ]

In case no struct sockaddr_ll has been passed to packet
socket's sendmsg() when doing a TX_RING flush run, then
skb->protocol is set to po->num instead, which is the protocol
passed via socket(2)/bind(2).

Applications only xmitting can go the path of allocating the
socket as socket(PF_PACKET, <mode>, 0) and do a bind(2) on the
TX_RING with sll_protocol of 0. That way, register_prot_hook()
is neither called on creation nor on bind time, which saves
cycles when there's no interest in capturing anyway.

That leaves us however with po->num 0 instead and therefore
the TX_RING flush run sets skb->protocol to 0 as well. Eric
reported that this leads to problems when using tools like
trafgen over bonding device. I.e. the bonding's hash function
could invoke the kernel's flow dissector, which depends on
skb->protocol being properly set. In the current situation, all
the traffic is then directed to a single slave.

Fix it up by inferring skb->protocol from the Ethernet header
when not set and we have ARPHRD_ETHER device type. This is only
done in case of SOCK_RAW and where we have a dev->hard_header_len
length. In case of ARPHRD_ETHER devices, this is guaranteed to
cover ETH_HLEN, and therefore being accessed on the skb after
the skb_store_bits().

Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 4710f22..ecad899 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2219,6 +2219,15 @@ static bool ll_header_truncated(const struct net_device *dev, int len)
 	return false;
 }
 
+static void tpacket_set_protocol(const struct net_device *dev,
+				 struct sk_buff *skb)
+{
+	if (dev->type == ARPHRD_ETHER) {
+		skb_reset_mac_header(skb);
+		skb->protocol = eth_hdr(skb)->h_proto;
+	}
+}
+
 static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 		void *frame, struct net_device *dev, int size_max,
 		__be16 proto, unsigned char *addr, int hlen)
@@ -2300,6 +2309,8 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 				dev->hard_header_len);
 		if (unlikely(err))
 			return err;
+		if (!skb->protocol)
+			tpacket_set_protocol(dev, skb);
 
 		data += dev->hard_header_len;
 		to_write -= dev->hard_header_len;
-- 
2.1.0


From 89e7a93e5747abb845ad058cdf7d1bb374d656b1 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 11 Nov 2015 23:25:44 +0100
Subject: [PATCH 14/37] packet: fix tpacket_snd max frame len

[ Upstream commit 5cfb4c8d05b4409c4044cb9c05b19705c1d9818b ]

Since it's introduction in commit 69e3c75f4d54 ("net: TX_RING and
packet mmap"), TX_RING could be used from SOCK_DGRAM and SOCK_RAW
side. When used with SOCK_DGRAM only, the size_max > dev->mtu +
reserve check should have reserve as 0, but currently, this is
unconditionally set (in it's original form as dev->hard_header_len).

I think this is not correct since tpacket_fill_skb() would then
take dev->mtu and dev->hard_header_len into account for SOCK_DGRAM,
the extra VLAN_HLEN could be possible in both cases. Presumably, the
reserve code was copied from packet_snd(), but later on missed the
check. Make it similar as we have it in packet_snd().

Fixes: 69e3c75f4d54 ("net: TX_RING and packet mmap")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index ecad899..71d671c 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2391,12 +2391,13 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 	if (unlikely(!(dev->flags & IFF_UP)))
 		goto out_put;
 
-	reserve = dev->hard_header_len + VLAN_HLEN;
+	if (po->sk.sk_socket->type == SOCK_RAW)
+		reserve = dev->hard_header_len;
 	size_max = po->tx_ring.frame_size
 		- (po->tp_hdrlen - sizeof(struct sockaddr_ll));
 
-	if (size_max > dev->mtu + reserve)
-		size_max = dev->mtu + reserve;
+	if (size_max > dev->mtu + reserve + VLAN_HLEN)
+		size_max = dev->mtu + reserve + VLAN_HLEN;
 
 	do {
 		ph = packet_current_frame(po, &po->tx_ring,
@@ -2423,7 +2424,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 		tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto,
 					  addr, hlen);
 		if (likely(tp_len >= 0) &&
-		    tp_len > dev->mtu + dev->hard_header_len &&
+		    tp_len > dev->mtu + reserve &&
 		    !packet_extra_vlan_len_allowed(dev, skb))
 			tp_len = -EMSGSIZE;
 
-- 
2.1.0


From 147ba7b20131040aa8f8256667a6a719818058fd Mon Sep 17 00:00:00 2001
From: lucien <lucien.xin@gmail.com>
Date: Thu, 12 Nov 2015 13:07:07 +0800
Subject: [PATCH 15/37] sctp: translate host order to network order when
 setting a hmacid

[ Upstream commit ed5a377d87dc4c87fb3e1f7f698cba38cd893103 ]

now sctp auth cannot work well when setting a hmacid manually, which
is caused by that we didn't use the network order for hmacid, so fix
it by adding the transformation in sctp_auth_ep_set_hmacs.

even we set hmacid with the network order in userspace, it still
can't work, because of this condition in sctp_auth_ep_set_hmacs():

		if (id > SCTP_AUTH_HMAC_ID_MAX)
			return -EOPNOTSUPP;

so this wasn't working before and thus it won't break compatibility.

Fixes: 65b07e5d0d09 ("[SCTP]: API updates to suport SCTP-AUTH extensions.")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/auth.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sctp/auth.c b/net/sctp/auth.c
index 4f15b7d..1543e39 100644
--- a/net/sctp/auth.c
+++ b/net/sctp/auth.c
@@ -809,8 +809,8 @@ int sctp_auth_ep_set_hmacs(struct sctp_endpoint *ep,
 	if (!has_sha1)
 		return -EINVAL;
 
-	memcpy(ep->auth_hmacs_list->hmac_ids, &hmacs->shmac_idents[0],
-		hmacs->shmac_num_idents * sizeof(__u16));
+	for (i = 0; i < hmacs->shmac_num_idents; i++)
+		ep->auth_hmacs_list->hmac_ids[i] = htons(hmacs->shmac_idents[i]);
 	ep->auth_hmacs_list->param_hdr.length = htons(sizeof(sctp_paramhdr_t) +
 				hmacs->shmac_num_idents * sizeof(__u16));
 	return 0;
-- 
2.1.0


From a7ff2e38b473647c6b05c6e9c25165e0f1a6651c Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Thu, 12 Nov 2015 19:35:29 +0200
Subject: [PATCH 16/37] net/mlx4_core: Fix sleeping while holding spinlock at
 rem_slave_counters

[ Upstream commit f5adbfee72282bb1f456d52b04adacd4fe6ac502 ]

When cleaning slave's counter resources, we hold a spinlock that
protects the slave's counters list. As part of the clean, we call
__mlx4_clear_if_stat which calls mlx4_alloc_cmd_mailbox which is a
sleepable function.

In order to fix this issue, hold the spinlock, and copy all counter
indices into a temporary array, and release the spinlock. Afterwards,
iterate over this array and free every counter. Repeat this scenario
until the original list is empty (a new counter might have been added
while releasing the counters from the temporary array).

Fixes: b72ca7e96acf ("net/mlx4_core: Reset counters data when freed")
Reported-by: Moni Shoua <monis@mellanox.com>
Tested-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlx4/resource_tracker.c  | 39 +++++++++++++++-------
 1 file changed, 27 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 731423c..8bead97 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -4934,26 +4934,41 @@ static void rem_slave_counters(struct mlx4_dev *dev, int slave)
 	struct res_counter *counter;
 	struct res_counter *tmp;
 	int err;
-	int index;
+	int *counters_arr = NULL;
+	int i, j;
 
 	err = move_all_busy(dev, slave, RES_COUNTER);
 	if (err)
 		mlx4_warn(dev, "rem_slave_counters: Could not move all counters - too busy for slave %d\n",
 			  slave);
 
-	spin_lock_irq(mlx4_tlock(dev));
-	list_for_each_entry_safe(counter, tmp, counter_list, com.list) {
-		if (counter->com.owner == slave) {
-			index = counter->com.res_id;
-			rb_erase(&counter->com.node,
-				 &tracker->res_tree[RES_COUNTER]);
-			list_del(&counter->com.list);
-			kfree(counter);
-			__mlx4_counter_free(dev, index);
+	counters_arr = kmalloc_array(dev->caps.max_counters,
+				     sizeof(*counters_arr), GFP_KERNEL);
+	if (!counters_arr)
+		return;
+
+	do {
+		i = 0;
+		j = 0;
+		spin_lock_irq(mlx4_tlock(dev));
+		list_for_each_entry_safe(counter, tmp, counter_list, com.list) {
+			if (counter->com.owner == slave) {
+				counters_arr[i++] = counter->com.res_id;
+				rb_erase(&counter->com.node,
+					 &tracker->res_tree[RES_COUNTER]);
+				list_del(&counter->com.list);
+				kfree(counter);
+			}
+		}
+		spin_unlock_irq(mlx4_tlock(dev));
+
+		while (j < i) {
+			__mlx4_counter_free(dev, counters_arr[j++]);
 			mlx4_release_resource(dev, slave, RES_COUNTER, 1, 0);
 		}
-	}
-	spin_unlock_irq(mlx4_tlock(dev));
+	} while (i);
+
+	kfree(counters_arr);
 }
 
 static void rem_slave_xrcdns(struct mlx4_dev *dev, int slave)
-- 
2.1.0


From dd68d7f48af24378d4b88918bee9089b2c0467cb Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Thu, 12 Nov 2015 17:35:58 +0100
Subject: [PATCH 17/37] ip_tunnel: disable preemption when updating per-cpu
 tstats

[ Upstream commit b4fe85f9c9146f60457e9512fb6055e69e6a7a65 ]

Drivers like vxlan use the recently introduced
udp_tunnel_xmit_skb/udp_tunnel6_xmit_skb APIs. udp_tunnel6_xmit_skb
makes use of ip6tunnel_xmit, and ip6tunnel_xmit, after sending the
packet, updates the struct stats using the usual
u64_stats_update_begin/end calls on this_cpu_ptr(dev->tstats).
udp_tunnel_xmit_skb makes use of iptunnel_xmit, which doesn't touch
tstats, so drivers like vxlan, immediately after, call
iptunnel_xmit_stats, which does the same thing - calls
u64_stats_update_begin/end on this_cpu_ptr(dev->tstats).

While vxlan is probably fine (I don't know?), calling a similar function
from, say, an unbound workqueue, on a fully preemptable kernel causes
real issues:

[  188.434537] BUG: using smp_processor_id() in preemptible [00000000] code: kworker/u8:0/6
[  188.435579] caller is debug_smp_processor_id+0x17/0x20
[  188.435583] CPU: 0 PID: 6 Comm: kworker/u8:0 Not tainted 4.2.6 #2
[  188.435607] Call Trace:
[  188.435611]  [<ffffffff8234e936>] dump_stack+0x4f/0x7b
[  188.435615]  [<ffffffff81915f3d>] check_preemption_disabled+0x19d/0x1c0
[  188.435619]  [<ffffffff81915f77>] debug_smp_processor_id+0x17/0x20

The solution would be to protect the whole
this_cpu_ptr(dev->tstats)/u64_stats_update_begin/end blocks with
disabling preemption and then reenabling it.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_tunnel.h | 3 ++-
 include/net/ip_tunnels.h | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index b8529aa..b0f7445 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -83,11 +83,12 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb,
 	err = ip6_local_out_sk(sk, skb);
 
 	if (net_xmit_eval(err) == 0) {
-		struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
+		struct pcpu_sw_netstats *tstats = get_cpu_ptr(dev->tstats);
 		u64_stats_update_begin(&tstats->syncp);
 		tstats->tx_bytes += pkt_len;
 		tstats->tx_packets++;
 		u64_stats_update_end(&tstats->syncp);
+		put_cpu_ptr(tstats);
 	} else {
 		stats->tx_errors++;
 		stats->tx_aborted_errors++;
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index d8214cb..9c2897e 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -207,12 +207,13 @@ static inline void iptunnel_xmit_stats(int err,
 				       struct pcpu_sw_netstats __percpu *stats)
 {
 	if (err > 0) {
-		struct pcpu_sw_netstats *tstats = this_cpu_ptr(stats);
+		struct pcpu_sw_netstats *tstats = get_cpu_ptr(stats);
 
 		u64_stats_update_begin(&tstats->syncp);
 		tstats->tx_bytes += err;
 		tstats->tx_packets++;
 		u64_stats_update_end(&tstats->syncp);
+		put_cpu_ptr(tstats);
 	} else if (err < 0) {
 		err_stats->tx_errors++;
 		err_stats->tx_aborted_errors++;
-- 
2.1.0


From 52964ecb13dcfb471ae4209e04a0e9cd18aa9cbb Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dragos@endocode.com>
Date: Mon, 16 Nov 2015 10:52:48 +0100
Subject: [PATCH 18/37] net: switchdev: fix return code of fdb_dump stub

[ Upstream commit 24cb7055a3066634a0f3fa0cd6a4780652905d35 ]

rtnl_fdb_dump always expects an index to be returned by the ndo_fdb_dump op,
but when CONFIG_NET_SWITCHDEV is off, it returns an error.

Fix that by returning the given unmodified idx.

A similar fix was 0890cf6cb6ab ("switchdev: fix return value of
switchdev_port_fdb_dump in case of error") but for the CONFIG_NET_SWITCHDEV=y
case.

Fixes: 45d4122ca7cd ("switchdev: add support for fdb add/del/dump via switchdev_port_obj ops.")
Signed-off-by: Dragos Tatulea <dragos@endocode.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/switchdev.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index d5671f1..0b91979 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -268,7 +268,7 @@ static inline int switchdev_port_fdb_dump(struct sk_buff *skb,
 					  struct net_device *filter_dev,
 					  int idx)
 {
-	return -EOPNOTSUPP;
+       return idx;
 }
 
 #endif
-- 
2.1.0


From 673a57ec4f0f21fea3ddd2f330374546dc2c6b38 Mon Sep 17 00:00:00 2001
From: Pavel Fedin <p.fedin@samsung.com>
Date: Mon, 16 Nov 2015 17:51:34 +0300
Subject: [PATCH 19/37] net: thunder: Check for driver data in nicvf_remove()

[ Upstream commit 7750130d93decff06120df0d8ea024ff8a038a21 ]

In some cases the crash is caused by nicvf_remove() being called from
outside. For example, if we try to feed the device to vfio after the
probe has failed for some reason. So, move the check to better place.

Signed-off-by: Pavel Fedin <p.fedin@samsung.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/thunder/nicvf_main.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 3b90afb..6f2a748 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -1325,7 +1325,12 @@ err_disable_device:
 static void nicvf_remove(struct pci_dev *pdev)
 {
 	struct net_device *netdev = pci_get_drvdata(pdev);
-	struct nicvf *nic = netdev_priv(netdev);
+	struct nicvf *nic;
+
+	if (!netdev)
+		return;
+
+	nic = netdev_priv(netdev);
 
 	unregister_netdev(netdev);
 	nicvf_unregister_interrupts(nic);
-- 
2.1.0


From 4c72e38e5a02a52c33bc4c613082c8c0aaca8a8c Mon Sep 17 00:00:00 2001
From: Neil Horman <nhorman@tuxdriver.com>
Date: Mon, 16 Nov 2015 13:09:10 -0500
Subject: [PATCH 20/37] snmp: Remove duplicate OUTMCAST stat increment

[ Upstream commit 41033f029e393a64e81966cbe34d66c6cf8a2e7e ]

the OUTMCAST stat is double incremented, getting bumped once in the mcast code
itself, and again in the common ip output path.  Remove the mcast bump, as its
not needed

Validated by the reporter, with good results

Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Reported-by: Claus Jensen <claus.jensen@microsemi.com>
CC: Claus Jensen <claus.jensen@microsemi.com>
CC: David Miller <davem@davemloft.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/mcast.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 083b292..41e3b5e 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1651,7 +1651,6 @@ out:
 	if (!err) {
 		ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT);
 		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
-		IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, payload_len);
 	} else {
 		IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
 	}
@@ -2014,7 +2013,6 @@ out:
 	if (!err) {
 		ICMP6MSGOUT_INC_STATS(net, idev, type);
 		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
-		IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, full_len);
 	} else
 		IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
 
-- 
2.1.0


From ec69f679b948f8a51cfeacf9ea5abc5a61b5cbb2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Wed, 18 Nov 2015 21:13:07 +0100
Subject: [PATCH 21/37] net: qmi_wwan: add XS Stick W100-2 from 4G Systems
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 68242a5a1e2edce39b069385cbafb82304eac0f1 ]

Thomas reports
"
4gsystems sells two total different LTE-surfsticks under the same name.
..
The newer version of XS Stick W100 is from "omega"
..
Under windows the driver switches to the same ID, and uses MI03\6 for
network and MI01\6 for modem.
..
echo "1c9e 9b01" > /sys/bus/usb/drivers/qmi_wwan/new_id
echo "1c9e 9b01" > /sys/bus/usb-serial/drivers/option1/new_id

T:  Bus=01 Lev=01 Prnt=01 Port=03 Cnt=01 Dev#=  4 Spd=480 MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1c9e ProdID=9b01 Rev=02.32
S:  Manufacturer=USB Modem
S:  Product=USB Modem
S:  SerialNumber=
C:  #Ifs= 5 Cfg#= 1 Atr=80 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
I:  If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
I:  If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
I:  If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
I:  If#= 4 Alt= 0 #EPs= 2 Cls=08(stor.) Sub=06 Prot=50 Driver=usb-storage

Now all important things are there:

wwp0s29f7u2i3 (net), ttyUSB2 (at), cdc-wdm0 (qmi), ttyUSB1 (at)

There is also ttyUSB0, but it is not usable, at least not for at.

The device works well with qmi and ModemManager-NetworkManager.
"

Reported-by: Thomas Schäfer <tschaefer@t-online.de>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 8f1738c..de27f51 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -775,6 +775,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x2357, 0x9000, 4)},	/* TP-LINK MA260 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)},	/* Telit LE920 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1201, 2)},	/* Telit LE920 */
+	{QMI_FIXED_INTF(0x1c9e, 0x9b01, 3)},	/* XS Stick W100-2 from 4G Systems */
 	{QMI_FIXED_INTF(0x0b3c, 0xc000, 4)},	/* Olivetti Olicard 100 */
 	{QMI_FIXED_INTF(0x0b3c, 0xc001, 4)},	/* Olivetti Olicard 120 */
 	{QMI_FIXED_INTF(0x0b3c, 0xc002, 4)},	/* Olivetti Olicard 140 */
-- 
2.1.0


From 20eb0f0537467a8452ae6a53a4ca9bb150660e0a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 18 Nov 2015 12:40:13 -0800
Subject: [PATCH 22/37] tcp: md5: fix lockdep annotation

[ Upstream commit 1b8e6a01e19f001e9f93b39c32387961c91ed3cc ]

When a passive TCP is created, we eventually call tcp_md5_do_add()
with sk pointing to the child. It is not owner by the user yet (we
will add this socket into listener accept queue a bit later anyway)

But we do own the spinlock, so amend the lockdep annotation to avoid
following splat :

[ 8451.090932] net/ipv4/tcp_ipv4.c:923 suspicious rcu_dereference_protected() usage!
[ 8451.090932]
[ 8451.090932] other info that might help us debug this:
[ 8451.090932]
[ 8451.090934]
[ 8451.090934] rcu_scheduler_active = 1, debug_locks = 1
[ 8451.090936] 3 locks held by socket_sockopt_/214795:
[ 8451.090936]  #0:  (rcu_read_lock){.+.+..}, at: [<ffffffff855c6ac1>] __netif_receive_skb_core+0x151/0xe90
[ 8451.090947]  #1:  (rcu_read_lock){.+.+..}, at: [<ffffffff85618143>] ip_local_deliver_finish+0x43/0x2b0
[ 8451.090952]  #2:  (slock-AF_INET){+.-...}, at: [<ffffffff855acda5>] sk_clone_lock+0x1c5/0x500
[ 8451.090958]
[ 8451.090958] stack backtrace:
[ 8451.090960] CPU: 7 PID: 214795 Comm: socket_sockopt_

[ 8451.091215] Call Trace:
[ 8451.091216]  <IRQ>  [<ffffffff856fb29c>] dump_stack+0x55/0x76
[ 8451.091229]  [<ffffffff85123b5b>] lockdep_rcu_suspicious+0xeb/0x110
[ 8451.091235]  [<ffffffff8564544f>] tcp_md5_do_add+0x1bf/0x1e0
[ 8451.091239]  [<ffffffff85645751>] tcp_v4_syn_recv_sock+0x1f1/0x4c0
[ 8451.091242]  [<ffffffff85642b27>] ? tcp_v4_md5_hash_skb+0x167/0x190
[ 8451.091246]  [<ffffffff85647c78>] tcp_check_req+0x3c8/0x500
[ 8451.091249]  [<ffffffff856451ae>] ? tcp_v4_inbound_md5_hash+0x11e/0x190
[ 8451.091253]  [<ffffffff85647170>] tcp_v4_rcv+0x3c0/0x9f0
[ 8451.091256]  [<ffffffff85618143>] ? ip_local_deliver_finish+0x43/0x2b0
[ 8451.091260]  [<ffffffff856181b6>] ip_local_deliver_finish+0xb6/0x2b0
[ 8451.091263]  [<ffffffff85618143>] ? ip_local_deliver_finish+0x43/0x2b0
[ 8451.091267]  [<ffffffff85618d38>] ip_local_deliver+0x48/0x80
[ 8451.091270]  [<ffffffff85618510>] ip_rcv_finish+0x160/0x700
[ 8451.091273]  [<ffffffff8561900e>] ip_rcv+0x29e/0x3d0
[ 8451.091277]  [<ffffffff855c74b7>] __netif_receive_skb_core+0xb47/0xe90

Fixes: a8afca0329988 ("tcp: md5: protects md5sig_info with RCU")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 0ea2e1c..569c638 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -922,7 +922,8 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
 	}
 
 	md5sig = rcu_dereference_protected(tp->md5sig_info,
-					   sock_owned_by_user(sk));
+					   sock_owned_by_user(sk) ||
+					   lockdep_is_held(&sk->sk_lock.slock));
 	if (!md5sig) {
 		md5sig = kmalloc(sizeof(*md5sig), gfp);
 		if (!md5sig)
-- 
2.1.0


From dd711f463bb9faafe25f9ab98af1656655137441 Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Wed, 18 Nov 2015 18:17:30 -0800
Subject: [PATCH 23/37] tcp: disable Fast Open on timeouts after handshake

[ Upstream commit 0e45f4da5981895e885dd72fe912a3f8e32bae73 ]

Some middle-boxes black-hole the data after the Fast Open handshake
(https://www.ietf.org/proceedings/94/slides/slides-94-tcpm-13.pdf).
The exact reason is unknown. The work-around is to disable Fast Open
temporarily after multiple recurring timeouts with few or no data
delivered in the established state.

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Christoph Paasch <cpaasch@apple.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_timer.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 5b752f5..1e63c8f 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -176,6 +176,18 @@ static int tcp_write_timeout(struct sock *sk)
 		syn_set = true;
 	} else {
 		if (retransmits_timed_out(sk, sysctl_tcp_retries1, 0, 0)) {
+			/* Some middle-boxes may black-hole Fast Open _after_
+			 * the handshake. Therefore we conservatively disable
+			 * Fast Open on this path on recurring timeouts with
+			 * few or zero bytes acked after Fast Open.
+			 */
+			if (tp->syn_data_acked &&
+			    tp->bytes_acked <= tp->rx_opt.mss_clamp) {
+				tcp_fastopen_cache_set(sk, 0, NULL, true, 0);
+				if (icsk->icsk_retransmits == sysctl_tcp_retries1)
+					NET_INC_STATS_BH(sock_net(sk),
+							 LINUX_MIB_TCPFASTOPENACTIVEFAIL);
+			}
 			/* Black hole detection */
 			tcp_mtu_probing(icsk, sk);
 
-- 
2.1.0


From 6abdc9f3582b7d7878480648bf185e9aad6a8fb0 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 18 Nov 2015 21:03:33 -0800
Subject: [PATCH 24/37] tcp: fix potential huge kmalloc() calls in TCP_REPAIR

[ Upstream commit 5d4c9bfbabdb1d497f21afd81501e5c54b0c85d9 ]

tcp_send_rcvq() is used for re-injecting data into tcp receive queue.

Problems :

- No check against size is performed, allowed user to fool kernel in
  attempting very large memory allocations, eventually triggering
  OOM when memory is fragmented.

- In case of fault during the copy we do not return correct errno.

Lets use alloc_skb_with_frags() to cook optimal skbs.

Fixes: 292e8d8c8538 ("tcp: Move rcvq sending to tcp_input.c")
Fixes: c0e88ff0f256 ("tcp: Repair socket queues")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 22 +++++++++++++++++++---
 1 file changed, 19 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 728f5b3..c990105 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4434,19 +4434,34 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int
 int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
 {
 	struct sk_buff *skb;
+	int err = -ENOMEM;
+	int data_len = 0;
 	bool fragstolen;
 
 	if (size == 0)
 		return 0;
 
-	skb = alloc_skb(size, sk->sk_allocation);
+	if (size > PAGE_SIZE) {
+		int npages = min_t(size_t, size >> PAGE_SHIFT, MAX_SKB_FRAGS);
+
+		data_len = npages << PAGE_SHIFT;
+		size = data_len + (size & ~PAGE_MASK);
+	}
+	skb = alloc_skb_with_frags(size - data_len, data_len,
+				   PAGE_ALLOC_COSTLY_ORDER,
+				   &err, sk->sk_allocation);
 	if (!skb)
 		goto err;
 
+	skb_put(skb, size - data_len);
+	skb->data_len = data_len;
+	skb->len = size;
+
 	if (tcp_try_rmem_schedule(sk, skb, skb->truesize))
 		goto err_free;
 
-	if (memcpy_from_msg(skb_put(skb, size), msg, size))
+	err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size);
+	if (err)
 		goto err_free;
 
 	TCP_SKB_CB(skb)->seq = tcp_sk(sk)->rcv_nxt;
@@ -4462,7 +4477,8 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
 err_free:
 	kfree_skb(skb);
 err:
-	return -ENOMEM;
+	return err;
+
 }
 
 static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
-- 
2.1.0


From 9f5bbd968c4fea392d92d486adfccb588f963d68 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 26 Nov 2015 08:18:14 -0800
Subject: [PATCH 25/37] tcp: initialize tp->copied_seq in case of cross SYN
 connection

[ Upstream commit 142a2e7ece8d8ac0e818eb2c91f99ca894730e2a ]

Dmitry provided a syzkaller (http://github.com/google/syzkaller)
generated program that triggers the WARNING at
net/ipv4/tcp.c:1729 in tcp_recvmsg() :

WARN_ON(tp->copied_seq != tp->rcv_nxt &&
        !(flags & (MSG_PEEK | MSG_TRUNC)));

His program is specifically attempting a Cross SYN TCP exchange,
that we support (for the pleasure of hackers ?), but it looks we
lack proper tcp->copied_seq initialization.

Thanks again Dmitry for your report and testings.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Tested-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index c990105..77730b4 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5636,6 +5636,7 @@ discard:
 		}
 
 		tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
+		tp->copied_seq = tp->rcv_nxt;
 		tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1;
 
 		/* RFC1323: The window in SYN & SYN/ACK segments is
-- 
2.1.0


From eae7ab74ca54ad3593c52b6ded2717cd31d2a74d Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 20 Nov 2015 00:11:56 +0100
Subject: [PATCH 26/37] net, scm: fix PaX detected msg_controllen overflow in
 scm_detach_fds

[ Upstream commit 6900317f5eff0a7070c5936e5383f589e0de7a09 ]

David and HacKurx reported a following/similar size overflow triggered
in a grsecurity kernel, thanks to PaX's gcc size overflow plugin:

(Already fixed in later grsecurity versions by Brad and PaX Team.)

[ 1002.296137] PAX: size overflow detected in function scm_detach_fds net/core/scm.c:314
               cicus.202_127 min, count: 4, decl: msg_controllen; num: 0; context: msghdr;
[ 1002.296145] CPU: 0 PID: 3685 Comm: scm_rights_recv Not tainted 4.2.3-grsec+ #7
[ 1002.296149] Hardware name: Apple Inc. MacBookAir5,1/Mac-66F35F19FE2A0D05, [...]
[ 1002.296153]  ffffffff81c27366 0000000000000000 ffffffff81c27375 ffffc90007843aa8
[ 1002.296162]  ffffffff818129ba 0000000000000000 ffffffff81c27366 ffffc90007843ad8
[ 1002.296169]  ffffffff8121f838 fffffffffffffffc fffffffffffffffc ffffc90007843e60
[ 1002.296176] Call Trace:
[ 1002.296190]  [<ffffffff818129ba>] dump_stack+0x45/0x57
[ 1002.296200]  [<ffffffff8121f838>] report_size_overflow+0x38/0x60
[ 1002.296209]  [<ffffffff816a979e>] scm_detach_fds+0x2ce/0x300
[ 1002.296220]  [<ffffffff81791899>] unix_stream_read_generic+0x609/0x930
[ 1002.296228]  [<ffffffff81791c9f>] unix_stream_recvmsg+0x4f/0x60
[ 1002.296236]  [<ffffffff8178dc00>] ? unix_set_peek_off+0x50/0x50
[ 1002.296243]  [<ffffffff8168fac7>] sock_recvmsg+0x47/0x60
[ 1002.296248]  [<ffffffff81691522>] ___sys_recvmsg+0xe2/0x1e0
[ 1002.296257]  [<ffffffff81693496>] __sys_recvmsg+0x46/0x80
[ 1002.296263]  [<ffffffff816934fc>] SyS_recvmsg+0x2c/0x40
[ 1002.296271]  [<ffffffff8181a3ab>] entry_SYSCALL_64_fastpath+0x12/0x85

Further investigation showed that this can happen when an *odd* number of
fds are being passed over AF_UNIX sockets.

In these cases CMSG_LEN(i * sizeof(int)) and CMSG_SPACE(i * sizeof(int)),
where i is the number of successfully passed fds, differ by 4 bytes due
to the extra CMSG_ALIGN() padding in CMSG_SPACE() to an 8 byte boundary
on 64 bit. The padding is used to align subsequent cmsg headers in the
control buffer.

When the control buffer passed in from the receiver side *lacks* these 4
bytes (e.g. due to buggy/wrong API usage), then msg->msg_controllen will
overflow in scm_detach_fds():

  int cmlen = CMSG_LEN(i * sizeof(int));  <--- cmlen w/o tail-padding
  err = put_user(SOL_SOCKET, &cm->cmsg_level);
  if (!err)
    err = put_user(SCM_RIGHTS, &cm->cmsg_type);
  if (!err)
    err = put_user(cmlen, &cm->cmsg_len);
  if (!err) {
    cmlen = CMSG_SPACE(i * sizeof(int));  <--- cmlen w/ 4 byte extra tail-padding
    msg->msg_control += cmlen;
    msg->msg_controllen -= cmlen;         <--- iff no tail-padding space here ...
  }                                            ... wrap-around

F.e. it will wrap to a length of 18446744073709551612 bytes in case the
receiver passed in msg->msg_controllen of 20 bytes, and the sender
properly transferred 1 fd to the receiver, so that its CMSG_LEN results
in 20 bytes and CMSG_SPACE in 24 bytes.

In case of MSG_CMSG_COMPAT (scm_detach_fds_compat()), I haven't seen an
issue in my tests as alignment seems always on 4 byte boundary. Same
should be in case of native 32 bit, where we end up with 4 byte boundaries
as well.

In practice, passing msg->msg_controllen of 20 to recvmsg() while receiving
a single fd would mean that on successful return, msg->msg_controllen is
being set by the kernel to 24 bytes instead, thus more than the input
buffer advertised. It could f.e. become an issue if such application later
on zeroes or copies the control buffer based on the returned msg->msg_controllen
elsewhere.

Maximum number of fds we can send is a hard upper limit SCM_MAX_FD (253).

Going over the code, it seems like msg->msg_controllen is not being read
after scm_detach_fds() in scm_recv() anymore by the kernel, good!

Relevant recvmsg() handler are unix_dgram_recvmsg() (unix_seqpacket_recvmsg())
and unix_stream_recvmsg(). Both return back to their recvmsg() caller,
and ___sys_recvmsg() places the updated length, that is, new msg_control -
old msg_control pointer into msg->msg_controllen (hence the 24 bytes seen
in the example).

Long time ago, Wei Yongjun fixed something related in commit 1ac70e7ad24a
("[NET]: Fix function put_cmsg() which may cause usr application memory
overflow").

RFC3542, section 20.2. says:

  The fields shown as "XX" are possible padding, between the cmsghdr
  structure and the data, and between the data and the next cmsghdr
  structure, if required by the implementation. While sending an
  application may or may not include padding at the end of last
  ancillary data in msg_controllen and implementations must accept both
  as valid. On receiving a portable application must provide space for
  padding at the end of the last ancillary data as implementations may
  copy out the padding at the end of the control message buffer and
  include it in the received msg_controllen. When recvmsg() is called
  if msg_controllen is too small for all the ancillary data items
  including any trailing padding after the last item an implementation
  may set MSG_CTRUNC.

Since we didn't place MSG_CTRUNC for already quite a long time, just do
the same as in 1ac70e7ad24a to avoid an overflow.

Btw, even man-page author got this wrong :/ See db939c9b26e9 ("cmsg.3: Fix
error in SCM_RIGHTS code sample"). Some people must have copied this (?),
thus it got triggered in the wild (reported several times during boot by
David and HacKurx).

No Fixes tag this time as pre 2002 (that is, pre history tree).

Reported-by: David Sterba <dave@jikos.cz>
Reported-by: HacKurx <hackurx@gmail.com>
Cc: PaX Team <pageexec@freemail.hu>
Cc: Emese Revfy <re.emese@gmail.com>
Cc: Brad Spengler <spender@grsecurity.net>
Cc: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Cc: Eric Dumazet <edumazet@google.com>
Reviewed-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/scm.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/core/scm.c b/net/core/scm.c
index 3b6899b..8a1741b 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -305,6 +305,8 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
 			err = put_user(cmlen, &cm->cmsg_len);
 		if (!err) {
 			cmlen = CMSG_SPACE(i*sizeof(int));
+			if (msg->msg_controllen < cmlen)
+				cmlen = msg->msg_controllen;
 			msg->msg_control += cmlen;
 			msg->msg_controllen -= cmlen;
 		}
-- 
2.1.0


From 7aa12b718983d04b4ced5c7649504f0307f2c82e Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Fri, 20 Nov 2015 13:54:19 +0100
Subject: [PATCH 27/37] net: ipmr: fix static mfc/dev leaks on table
 destruction

[ Upstream commit 0e615e9601a15efeeb8942cf7cd4dadba0c8c5a7 ]

When destroying an mrt table the static mfc entries and the static
devices are kept, which leads to devices that can never be destroyed
(because of refcnt taken) and leaked memory, for example:
unreferenced object 0xffff880034c144c0 (size 192):
  comm "mfc-broken", pid 4777, jiffies 4320349055 (age 46001.964s)
  hex dump (first 32 bytes):
    98 53 f0 34 00 88 ff ff 98 53 f0 34 00 88 ff ff  .S.4.....S.4....
    ef 0a 0a 14 01 02 03 04 00 00 00 00 01 00 00 00  ................
  backtrace:
    [<ffffffff815c1b9e>] kmemleak_alloc+0x4e/0xb0
    [<ffffffff811ea6e0>] kmem_cache_alloc+0x190/0x300
    [<ffffffff815931cb>] ip_mroute_setsockopt+0x5cb/0x910
    [<ffffffff8153d575>] do_ip_setsockopt.isra.11+0x105/0xff0
    [<ffffffff8153e490>] ip_setsockopt+0x30/0xa0
    [<ffffffff81564e13>] raw_setsockopt+0x33/0x90
    [<ffffffff814d1e14>] sock_common_setsockopt+0x14/0x20
    [<ffffffff814d0b51>] SyS_setsockopt+0x71/0xc0
    [<ffffffff815cdbf6>] entry_SYSCALL_64_fastpath+0x16/0x7a
    [<ffffffffffffffff>] 0xffffffffffffffff

Make sure that everything is cleaned on netns destruction.

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Reviewed-by: Cong Wang <cwang@twopensource.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ipmr.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index df28693..c3bfebd 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -134,7 +134,7 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
 			      struct mfc_cache *c, struct rtmsg *rtm);
 static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc,
 				 int cmd);
-static void mroute_clean_tables(struct mr_table *mrt);
+static void mroute_clean_tables(struct mr_table *mrt, bool all);
 static void ipmr_expire_process(unsigned long arg);
 
 #ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
@@ -351,7 +351,7 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id)
 static void ipmr_free_table(struct mr_table *mrt)
 {
 	del_timer_sync(&mrt->ipmr_expire_timer);
-	mroute_clean_tables(mrt);
+	mroute_clean_tables(mrt, true);
 	kfree(mrt);
 }
 
@@ -1209,7 +1209,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
  *	Close the multicast socket, and clear the vif tables etc
  */
 
-static void mroute_clean_tables(struct mr_table *mrt)
+static void mroute_clean_tables(struct mr_table *mrt, bool all)
 {
 	int i;
 	LIST_HEAD(list);
@@ -1218,8 +1218,9 @@ static void mroute_clean_tables(struct mr_table *mrt)
 	/* Shut down all active vif entries */
 
 	for (i = 0; i < mrt->maxvif; i++) {
-		if (!(mrt->vif_table[i].flags & VIFF_STATIC))
-			vif_delete(mrt, i, 0, &list);
+		if (!all && (mrt->vif_table[i].flags & VIFF_STATIC))
+			continue;
+		vif_delete(mrt, i, 0, &list);
 	}
 	unregister_netdevice_many(&list);
 
@@ -1227,7 +1228,7 @@ static void mroute_clean_tables(struct mr_table *mrt)
 
 	for (i = 0; i < MFC_LINES; i++) {
 		list_for_each_entry_safe(c, next, &mrt->mfc_cache_array[i], list) {
-			if (c->mfc_flags & MFC_STATIC)
+			if (!all && (c->mfc_flags & MFC_STATIC))
 				continue;
 			list_del_rcu(&c->list);
 			mroute_netlink_event(mrt, c, RTM_DELROUTE);
@@ -1262,7 +1263,7 @@ static void mrtsock_destruct(struct sock *sk)
 						    NETCONFA_IFINDEX_ALL,
 						    net->ipv4.devconf_all);
 			RCU_INIT_POINTER(mrt->mroute_sk, NULL);
-			mroute_clean_tables(mrt);
+			mroute_clean_tables(mrt, false);
 		}
 	}
 	rtnl_unlock();
-- 
2.1.0


From bbd383a3ea991780cfc41fb89b063d4a6b5f0c23 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Fri, 20 Nov 2015 13:54:20 +0100
Subject: [PATCH 28/37] net: ip6mr: fix static mfc/dev leaks on table
 destruction

[ Upstream commit 4c6980462f32b4f282c5d8e5f7ea8070e2937725 ]

Similar to ipv4, when destroying an mrt table the static mfc entries and
the static devices are kept, which leads to devices that can never be
destroyed (because of refcnt taken) and leaked memory. Make sure that
everything is cleaned up on netns destruction.

Fixes: 8229efdaef1e ("netns: ip6mr: enable namespace support in ipv6 multicast forwarding code")
CC: Benjamin Thery <benjamin.thery@bull.net>
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Reviewed-by: Cong Wang <cwang@twopensource.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6mr.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 5f36266..a7aef4b 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -118,7 +118,7 @@ static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc,
 			      int cmd);
 static int ip6mr_rtm_dumproute(struct sk_buff *skb,
 			       struct netlink_callback *cb);
-static void mroute_clean_tables(struct mr6_table *mrt);
+static void mroute_clean_tables(struct mr6_table *mrt, bool all);
 static void ipmr_expire_process(unsigned long arg);
 
 #ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES
@@ -335,7 +335,7 @@ static struct mr6_table *ip6mr_new_table(struct net *net, u32 id)
 static void ip6mr_free_table(struct mr6_table *mrt)
 {
 	del_timer_sync(&mrt->ipmr_expire_timer);
-	mroute_clean_tables(mrt);
+	mroute_clean_tables(mrt, true);
 	kfree(mrt);
 }
 
@@ -1543,7 +1543,7 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt,
  *	Close the multicast socket, and clear the vif tables etc
  */
 
-static void mroute_clean_tables(struct mr6_table *mrt)
+static void mroute_clean_tables(struct mr6_table *mrt, bool all)
 {
 	int i;
 	LIST_HEAD(list);
@@ -1553,8 +1553,9 @@ static void mroute_clean_tables(struct mr6_table *mrt)
 	 *	Shut down all active vif entries
 	 */
 	for (i = 0; i < mrt->maxvif; i++) {
-		if (!(mrt->vif6_table[i].flags & VIFF_STATIC))
-			mif6_delete(mrt, i, &list);
+		if (!all && (mrt->vif6_table[i].flags & VIFF_STATIC))
+			continue;
+		mif6_delete(mrt, i, &list);
 	}
 	unregister_netdevice_many(&list);
 
@@ -1563,7 +1564,7 @@ static void mroute_clean_tables(struct mr6_table *mrt)
 	 */
 	for (i = 0; i < MFC6_LINES; i++) {
 		list_for_each_entry_safe(c, next, &mrt->mfc6_cache_array[i], list) {
-			if (c->mfc_flags & MFC_STATIC)
+			if (!all && (c->mfc_flags & MFC_STATIC))
 				continue;
 			write_lock_bh(&mrt_lock);
 			list_del(&c->list);
@@ -1626,7 +1627,7 @@ int ip6mr_sk_done(struct sock *sk)
 						     net->ipv6.devconf_all);
 			write_unlock_bh(&mrt_lock);
 
-			mroute_clean_tables(mrt);
+			mroute_clean_tables(mrt, false);
 			err = 0;
 			break;
 		}
-- 
2.1.0


From a683fe9e6bd517c1e0af74a4e6af434c932524e4 Mon Sep 17 00:00:00 2001
From: Aaro Koskinen <aaro.koskinen@iki.fi>
Date: Sun, 22 Nov 2015 01:08:54 +0200
Subject: [PATCH 29/37] broadcom: fix PHY_ID_BCM5481 entry in the id table

[ Upstream commit 3c25a860d17b7378822f35d8c9141db9507e3beb ]

Commit fcb26ec5b18d ("broadcom: move all PHY_ID's to header")
updated broadcom_tbl to use PHY_IDs, but incorrectly replaced 0x0143bca0
with PHY_ID_BCM5482 (making a duplicate entry, and completely omitting
the original). Fix that.

Fixes: fcb26ec5b18d ("broadcom: move all PHY_ID's to header")
Signed-off-by: Aaro Koskinen <aaro.koskinen@iki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/broadcom.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c
index 9c71295..85e64044 100644
--- a/drivers/net/phy/broadcom.c
+++ b/drivers/net/phy/broadcom.c
@@ -675,7 +675,7 @@ static struct mdio_device_id __maybe_unused broadcom_tbl[] = {
 	{ PHY_ID_BCM5461, 0xfffffff0 },
 	{ PHY_ID_BCM54616S, 0xfffffff0 },
 	{ PHY_ID_BCM5464, 0xfffffff0 },
-	{ PHY_ID_BCM5482, 0xfffffff0 },
+	{ PHY_ID_BCM5481, 0xfffffff0 },
 	{ PHY_ID_BCM5482, 0xfffffff0 },
 	{ PHY_ID_BCM50610, 0xfffffff0 },
 	{ PHY_ID_BCM50610M, 0xfffffff0 },
-- 
2.1.0


From 26d430e69b1a190683cf3ff5feed35e81e13d621 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Michal=20Kube=C4=8Dek?= <mkubecek@suse.cz>
Date: Tue, 24 Nov 2015 15:07:11 +0100
Subject: [PATCH 30/37] ipv6: distinguish frag queues by device for multicast
 and link-local packets

[ Upstream commit 264640fc2c5f4f913db5c73fa3eb1ead2c45e9d7 ]

If a fragmented multicast packet is received on an ethernet device which
has an active macvlan on top of it, each fragment is duplicated and
received both on the underlying device and the macvlan. If some
fragments for macvlan are processed before the whole packet for the
underlying device is reassembled, the "overlapping fragments" test in
ip6_frag_queue() discards the whole fragment queue.

To resolve this, add device ifindex to the search key and require it to
match reassembling multicast packets and packets to link-local
addresses.

Note: similar patch has been already submitted by Yoshifuji Hideaki in

  http://patchwork.ozlabs.org/patch/220979/

but got lost and forgotten for some reason.

Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h                      |  1 +
 net/ipv6/netfilter/nf_conntrack_reasm.c |  5 +++--
 net/ipv6/reassembly.c                   | 10 +++++++---
 3 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 82dbdb0..13aecd1 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -490,6 +490,7 @@ struct ip6_create_arg {
 	u32 user;
 	const struct in6_addr *src;
 	const struct in6_addr *dst;
+	int iif;
 	u8 ecn;
 };
 
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 6d02498..2a4682c 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -190,7 +190,7 @@ static void nf_ct_frag6_expire(unsigned long data)
 /* Creation primitives. */
 static inline struct frag_queue *fq_find(struct net *net, __be32 id,
 					 u32 user, struct in6_addr *src,
-					 struct in6_addr *dst, u8 ecn)
+					 struct in6_addr *dst, int iif, u8 ecn)
 {
 	struct inet_frag_queue *q;
 	struct ip6_create_arg arg;
@@ -200,6 +200,7 @@ static inline struct frag_queue *fq_find(struct net *net, __be32 id,
 	arg.user = user;
 	arg.src = src;
 	arg.dst = dst;
+	arg.iif = iif;
 	arg.ecn = ecn;
 
 	local_bh_disable();
@@ -603,7 +604,7 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user)
 	fhdr = (struct frag_hdr *)skb_transport_header(clone);
 
 	fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr,
-		     ip6_frag_ecn(hdr));
+		     skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
 	if (fq == NULL) {
 		pr_debug("Can't find and can't create new queue\n");
 		goto ret_orig;
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index f1159bb..04013a9 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -108,7 +108,10 @@ bool ip6_frag_match(const struct inet_frag_queue *q, const void *a)
 	return	fq->id == arg->id &&
 		fq->user == arg->user &&
 		ipv6_addr_equal(&fq->saddr, arg->src) &&
-		ipv6_addr_equal(&fq->daddr, arg->dst);
+		ipv6_addr_equal(&fq->daddr, arg->dst) &&
+		(arg->iif == fq->iif ||
+		 !(ipv6_addr_type(arg->dst) & (IPV6_ADDR_MULTICAST |
+					       IPV6_ADDR_LINKLOCAL)));
 }
 EXPORT_SYMBOL(ip6_frag_match);
 
@@ -180,7 +183,7 @@ static void ip6_frag_expire(unsigned long data)
 
 static struct frag_queue *
 fq_find(struct net *net, __be32 id, const struct in6_addr *src,
-	const struct in6_addr *dst, u8 ecn)
+	const struct in6_addr *dst, int iif, u8 ecn)
 {
 	struct inet_frag_queue *q;
 	struct ip6_create_arg arg;
@@ -190,6 +193,7 @@ fq_find(struct net *net, __be32 id, const struct in6_addr *src,
 	arg.user = IP6_DEFRAG_LOCAL_DELIVER;
 	arg.src = src;
 	arg.dst = dst;
+	arg.iif = iif;
 	arg.ecn = ecn;
 
 	hash = inet6_hash_frag(id, src, dst);
@@ -551,7 +555,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 	}
 
 	fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr,
-		     ip6_frag_ecn(hdr));
+		     skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
 	if (fq) {
 		int ret;
 
-- 
2.1.0


From 30493fb29bc5af48ee13b44fde0e09e25ee2d38e Mon Sep 17 00:00:00 2001
From: Quentin Casasnovas <quentin.casasnovas@oracle.com>
Date: Tue, 24 Nov 2015 17:13:21 -0500
Subject: [PATCH 31/37] RDS: fix race condition when sending a message on
 unbound socket

[ Upstream commit 8c7188b23474cca017b3ef354c4a58456f68303a ]

Sasha's found a NULL pointer dereference in the RDS connection code when
sending a message to an apparently unbound socket.  The problem is caused
by the code checking if the socket is bound in rds_sendmsg(), which checks
the rs_bound_addr field without taking a lock on the socket.  This opens a
race where rs_bound_addr is temporarily set but where the transport is not
in rds_bind(), leading to a NULL pointer dereference when trying to
dereference 'trans' in __rds_conn_create().

Vegard wrote a reproducer for this issue, so kindly ask him to share if
you're interested.

I cannot reproduce the NULL pointer dereference using Vegard's reproducer
with this patch, whereas I could without.

Complete earlier incomplete fix to CVE-2015-6937:

  74e98eb08588 ("RDS: verify the underlying transport exists before creating a connection")

Cc: David S. Miller <davem@davemloft.net>
Cc: stable@vger.kernel.org

Reviewed-by: Vegard Nossum <vegard.nossum@oracle.com>
Reviewed-by: Sasha Levin <sasha.levin@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: Quentin Casasnovas <quentin.casasnovas@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/connection.c | 6 ------
 net/rds/send.c       | 4 +++-
 2 files changed, 3 insertions(+), 7 deletions(-)

diff --git a/net/rds/connection.c b/net/rds/connection.c
index 9d66705..da6da57 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -187,12 +187,6 @@ new_conn:
 		}
 	}
 
-	if (trans == NULL) {
-		kmem_cache_free(rds_conn_slab, conn);
-		conn = ERR_PTR(-ENODEV);
-		goto out;
-	}
-
 	conn->c_trans = trans;
 
 	ret = trans->conn_alloc(conn, gfp);
diff --git a/net/rds/send.c b/net/rds/send.c
index e9430f5..7b30c0f 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -986,11 +986,13 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 		release_sock(sk);
 	}
 
-	/* racing with another thread binding seems ok here */
+	lock_sock(sk);
 	if (daddr == 0 || rs->rs_bound_addr == 0) {
+		release_sock(sk);
 		ret = -ENOTCONN; /* XXX not a great errno */
 		goto out;
 	}
+	release_sock(sk);
 
 	/* size of rm including all sgs */
 	ret = rds_rm_size(msg, payload_len);
-- 
2.1.0


From 89399541540e210498d755d37b6c2477818e6aff Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Mon, 30 Nov 2015 13:02:56 +0100
Subject: [PATCH 32/37] bpf, array: fix heap out-of-bounds access when updating
 elements

[ Upstream commit fbca9d2d35c6ef1b323fae75cc9545005ba25097 ]

During own review but also reported by Dmitry's syzkaller [1] it has been
noticed that we trigger a heap out-of-bounds access on eBPF array maps
when updating elements. This happens with each map whose map->value_size
(specified during map creation time) is not multiple of 8 bytes.

In array_map_alloc(), elem_size is round_up(attr->value_size, 8) and
used to align array map slots for faster access. However, in function
array_map_update_elem(), we update the element as ...

memcpy(array->value + array->elem_size * index, value, array->elem_size);

... where we access 'value' out-of-bounds, since it was allocated from
map_update_elem() from syscall side as kmalloc(map->value_size, GFP_USER)
and later on copied through copy_from_user(value, uvalue, map->value_size).
Thus, up to 7 bytes, we can access out-of-bounds.

Same could happen from within an eBPF program, where in worst case we
access beyond an eBPF program's designated stack.

Since 1be7f75d1668 ("bpf: enable non-root eBPF programs") didn't hit an
official release yet, it only affects priviledged users.

In case of array_map_lookup_elem(), the verifier prevents eBPF programs
from accessing beyond map->value_size through check_map_access(). Also
from syscall side map_lookup_elem() only copies map->value_size back to
user, so nothing could leak.

  [1] http://github.com/google/syzkaller

Fixes: 28fbcfa08d8e ("bpf: add array type of eBPF maps")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/arraymap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index cb31229..34265a1 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -104,7 +104,7 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value,
 		/* all elements already exist */
 		return -EEXIST;
 
-	memcpy(array->value + array->elem_size * index, value, array->elem_size);
+	memcpy(array->value + array->elem_size * index, value, map->value_size);
 	return 0;
 }
 
-- 
2.1.0


From 88a52cf2de740c4c77684c2f74e6c58a004c1f45 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 29 Nov 2015 19:37:57 -0800
Subject: [PATCH 33/37] ipv6: add complete rcu protection around np->opt

[ Upstream commit 45f6fad84cc305103b28d73482b344d7f5b76f39 ]

This patch addresses multiple problems :

UDP/RAW sendmsg() need to get a stable struct ipv6_txoptions
while socket is not locked : Other threads can change np->opt
concurrently. Dmitry posted a syzkaller
(http://github.com/google/syzkaller) program desmonstrating
use-after-free.

Starting with TCP/DCCP lockless listeners, tcp_v6_syn_recv_sock()
and dccp_v6_request_recv_sock() also need to use RCU protection
to dereference np->opt once (before calling ipv6_dup_options())

This patch adds full RCU protection to np->opt

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ipv6.h             |  2 +-
 include/net/ipv6.h               | 21 ++++++++++++++++++++-
 net/dccp/ipv6.c                  | 33 +++++++++++++++++++++------------
 net/ipv6/af_inet6.c              | 13 +++++++++----
 net/ipv6/datagram.c              |  4 +++-
 net/ipv6/exthdrs.c               |  3 ++-
 net/ipv6/inet6_connection_sock.c | 11 ++++++++---
 net/ipv6/ipv6_sockglue.c         | 33 ++++++++++++++++++++++-----------
 net/ipv6/raw.c                   |  8 ++++++--
 net/ipv6/syncookies.c            |  2 +-
 net/ipv6/tcp_ipv6.c              | 28 +++++++++++++++++-----------
 net/ipv6/udp.c                   |  8 ++++++--
 net/l2tp/l2tp_ip6.c              |  8 ++++++--
 13 files changed, 122 insertions(+), 52 deletions(-)

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 82806c6..e4b4649 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -224,7 +224,7 @@ struct ipv6_pinfo {
 	struct ipv6_ac_socklist	*ipv6_ac_list;
 	struct ipv6_fl_socklist __rcu *ipv6_fl_list;
 
-	struct ipv6_txoptions	*opt;
+	struct ipv6_txoptions __rcu	*opt;
 	struct sk_buff		*pktoptions;
 	struct sk_buff		*rxpmtu;
 	struct inet6_cork	cork;
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 13aecd1..177a896 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -205,6 +205,7 @@ extern rwlock_t ip6_ra_lock;
  */
 
 struct ipv6_txoptions {
+	atomic_t		refcnt;
 	/* Length of this structure */
 	int			tot_len;
 
@@ -217,7 +218,7 @@ struct ipv6_txoptions {
 	struct ipv6_opt_hdr	*dst0opt;
 	struct ipv6_rt_hdr	*srcrt;	/* Routing Header */
 	struct ipv6_opt_hdr	*dst1opt;
-
+	struct rcu_head		rcu;
 	/* Option buffer, as read by IPV6_PKTOPTIONS, starts here. */
 };
 
@@ -252,6 +253,24 @@ struct ipv6_fl_socklist {
 	struct rcu_head			rcu;
 };
 
+static inline struct ipv6_txoptions *txopt_get(const struct ipv6_pinfo *np)
+{
+	struct ipv6_txoptions *opt;
+
+	rcu_read_lock();
+	opt = rcu_dereference(np->opt);
+	if (opt && !atomic_inc_not_zero(&opt->refcnt))
+		opt = NULL;
+	rcu_read_unlock();
+	return opt;
+}
+
+static inline void txopt_put(struct ipv6_txoptions *opt)
+{
+	if (opt && atomic_dec_and_test(&opt->refcnt))
+		kfree_rcu(opt, rcu);
+}
+
 struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label);
 struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space,
 					 struct ip6_flowlabel *fl,
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 5165571..a049050 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -202,7 +202,9 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req)
 	security_req_classify_flow(req, flowi6_to_flowi(&fl6));
 
 
-	final_p = fl6_update_dst(&fl6, np->opt, &final);
+	rcu_read_lock();
+	final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final);
+	rcu_read_unlock();
 
 	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
@@ -219,7 +221,10 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req)
 							 &ireq->ir_v6_loc_addr,
 							 &ireq->ir_v6_rmt_addr);
 		fl6.daddr = ireq->ir_v6_rmt_addr;
-		err = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass);
+		rcu_read_lock();
+		err = ip6_xmit(sk, skb, &fl6, rcu_dereference(np->opt),
+			       np->tclass);
+		rcu_read_unlock();
 		err = net_xmit_eval(err);
 	}
 
@@ -415,6 +420,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
 	struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
+	struct ipv6_txoptions *opt;
 	struct inet_sock *newinet;
 	struct dccp6_sock *newdp6;
 	struct sock *newsk;
@@ -534,13 +540,15 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
 	 * Yes, keeping reference count would be much more clever, but we make
 	 * one more one thing there: reattach optmem to newsk.
 	 */
-	if (np->opt != NULL)
-		newnp->opt = ipv6_dup_options(newsk, np->opt);
-
+	opt = rcu_dereference(np->opt);
+	if (opt) {
+		opt = ipv6_dup_options(newsk, opt);
+		RCU_INIT_POINTER(newnp->opt, opt);
+	}
 	inet_csk(newsk)->icsk_ext_hdr_len = 0;
-	if (newnp->opt != NULL)
-		inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen +
-						     newnp->opt->opt_flen);
+	if (opt)
+		inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen +
+						    opt->opt_flen;
 
 	dccp_sync_mss(newsk, dst_mtu(dst));
 
@@ -793,6 +801,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct dccp_sock *dp = dccp_sk(sk);
 	struct in6_addr *saddr = NULL, *final_p, final;
+	struct ipv6_txoptions *opt;
 	struct flowi6 fl6;
 	struct dst_entry *dst;
 	int addr_type;
@@ -892,7 +901,8 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	fl6.fl6_sport = inet->inet_sport;
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
-	final_p = fl6_update_dst(&fl6, np->opt, &final);
+	opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+	final_p = fl6_update_dst(&fl6, opt, &final);
 
 	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
@@ -912,9 +922,8 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	__ip6_dst_store(sk, dst, NULL, NULL);
 
 	icsk->icsk_ext_hdr_len = 0;
-	if (np->opt != NULL)
-		icsk->icsk_ext_hdr_len = (np->opt->opt_flen +
-					  np->opt->opt_nflen);
+	if (opt)
+		icsk->icsk_ext_hdr_len = opt->opt_flen + opt->opt_nflen;
 
 	inet->inet_dport = usin->sin6_port;
 
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 7de52b6..d87519e 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -426,9 +426,11 @@ void inet6_destroy_sock(struct sock *sk)
 
 	/* Free tx options */
 
-	opt = xchg(&np->opt, NULL);
-	if (opt)
-		sock_kfree_s(sk, opt, opt->tot_len);
+	opt = xchg((__force struct ipv6_txoptions **)&np->opt, NULL);
+	if (opt) {
+		atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+		txopt_put(opt);
+	}
 }
 EXPORT_SYMBOL_GPL(inet6_destroy_sock);
 
@@ -657,7 +659,10 @@ int inet6_sk_rebuild_header(struct sock *sk)
 		fl6.fl6_sport = inet->inet_sport;
 		security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
-		final_p = fl6_update_dst(&fl6, np->opt, &final);
+		rcu_read_lock();
+		final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt),
+					 &final);
+		rcu_read_unlock();
 
 		dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
 		if (IS_ERR(dst)) {
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index b10a889..13ca4cf 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -167,8 +167,10 @@ ipv4_connected:
 
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
-	opt = flowlabel ? flowlabel->opt : np->opt;
+	rcu_read_lock();
+	opt = flowlabel ? flowlabel->opt : rcu_dereference(np->opt);
 	final_p = fl6_update_dst(&fl6, opt, &final);
+	rcu_read_unlock();
 
 	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
 	err = 0;
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index a7bbbe4..adbd695 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -727,6 +727,7 @@ ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt)
 			*((char **)&opt2->dst1opt) += dif;
 		if (opt2->srcrt)
 			*((char **)&opt2->srcrt) += dif;
+		atomic_set(&opt2->refcnt, 1);
 	}
 	return opt2;
 }
@@ -790,7 +791,7 @@ ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt,
 		return ERR_PTR(-ENOBUFS);
 
 	memset(opt2, 0, tot_len);
-
+	atomic_set(&opt2->refcnt, 1);
 	opt2->tot_len = tot_len;
 	p = (char *)(opt2 + 1);
 
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 6927f3f..9beed30 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -77,7 +77,9 @@ struct dst_entry *inet6_csk_route_req(struct sock *sk,
 	memset(fl6, 0, sizeof(*fl6));
 	fl6->flowi6_proto = IPPROTO_TCP;
 	fl6->daddr = ireq->ir_v6_rmt_addr;
-	final_p = fl6_update_dst(fl6, np->opt, &final);
+	rcu_read_lock();
+	final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
+	rcu_read_unlock();
 	fl6->saddr = ireq->ir_v6_loc_addr;
 	fl6->flowi6_oif = ireq->ir_iif;
 	fl6->flowi6_mark = ireq->ir_mark;
@@ -207,7 +209,9 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk,
 	fl6->fl6_dport = inet->inet_dport;
 	security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
 
-	final_p = fl6_update_dst(fl6, np->opt, &final);
+	rcu_read_lock();
+	final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
+	rcu_read_unlock();
 
 	dst = __inet6_csk_dst_check(sk, np->dst_cookie);
 	if (!dst) {
@@ -240,7 +244,8 @@ int inet6_csk_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl_unused
 	/* Restore final destination back after routing done */
 	fl6.daddr = sk->sk_v6_daddr;
 
-	res = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass);
+	res = ip6_xmit(sk, skb, &fl6, rcu_dereference(np->opt),
+		       np->tclass);
 	rcu_read_unlock();
 	return res;
 }
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 63e6956..4449ad1 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -111,7 +111,8 @@ struct ipv6_txoptions *ipv6_update_options(struct sock *sk,
 			icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie);
 		}
 	}
-	opt = xchg(&inet6_sk(sk)->opt, opt);
+	opt = xchg((__force struct ipv6_txoptions **)&inet6_sk(sk)->opt,
+		   opt);
 	sk_dst_reset(sk);
 
 	return opt;
@@ -231,9 +232,12 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 				sk->sk_socket->ops = &inet_dgram_ops;
 				sk->sk_family = PF_INET;
 			}
-			opt = xchg(&np->opt, NULL);
-			if (opt)
-				sock_kfree_s(sk, opt, opt->tot_len);
+			opt = xchg((__force struct ipv6_txoptions **)&np->opt,
+				   NULL);
+			if (opt) {
+				atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+				txopt_put(opt);
+			}
 			pktopt = xchg(&np->pktoptions, NULL);
 			kfree_skb(pktopt);
 
@@ -403,7 +407,8 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 		if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW))
 			break;
 
-		opt = ipv6_renew_options(sk, np->opt, optname,
+		opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+		opt = ipv6_renew_options(sk, opt, optname,
 					 (struct ipv6_opt_hdr __user *)optval,
 					 optlen);
 		if (IS_ERR(opt)) {
@@ -432,8 +437,10 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 		retv = 0;
 		opt = ipv6_update_options(sk, opt);
 sticky_done:
-		if (opt)
-			sock_kfree_s(sk, opt, opt->tot_len);
+		if (opt) {
+			atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+			txopt_put(opt);
+		}
 		break;
 	}
 
@@ -486,6 +493,7 @@ sticky_done:
 			break;
 
 		memset(opt, 0, sizeof(*opt));
+		atomic_set(&opt->refcnt, 1);
 		opt->tot_len = sizeof(*opt) + optlen;
 		retv = -EFAULT;
 		if (copy_from_user(opt+1, optval, optlen))
@@ -502,8 +510,10 @@ update:
 		retv = 0;
 		opt = ipv6_update_options(sk, opt);
 done:
-		if (opt)
-			sock_kfree_s(sk, opt, opt->tot_len);
+		if (opt) {
+			atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+			txopt_put(opt);
+		}
 		break;
 	}
 	case IPV6_UNICAST_HOPS:
@@ -1110,10 +1120,11 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 	case IPV6_RTHDR:
 	case IPV6_DSTOPTS:
 	{
+		struct ipv6_txoptions *opt;
 
 		lock_sock(sk);
-		len = ipv6_getsockopt_sticky(sk, np->opt,
-					     optname, optval, len);
+		opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+		len = ipv6_getsockopt_sticky(sk, opt, optname, optval, len);
 		release_sock(sk);
 		/* check if ipv6_getsockopt_sticky() returns err code */
 		if (len < 0)
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index ca4700c..92d5329 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -731,6 +731,7 @@ static int raw6_getfrag(void *from, char *to, int offset, int len, int odd,
 
 static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 {
+	struct ipv6_txoptions *opt_to_free = NULL;
 	struct ipv6_txoptions opt_space;
 	DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
 	struct in6_addr *daddr, *final_p, final;
@@ -837,8 +838,10 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		if (!(opt->opt_nflen|opt->opt_flen))
 			opt = NULL;
 	}
-	if (!opt)
-		opt = np->opt;
+	if (!opt) {
+		opt = txopt_get(np);
+		opt_to_free = opt;
+		}
 	if (flowlabel)
 		opt = fl6_merge_options(&opt_space, flowlabel, opt);
 	opt = ipv6_fixup_options(&opt_space, opt);
@@ -904,6 +907,7 @@ done:
 	dst_release(dst);
 out:
 	fl6_sock_release(flowlabel);
+	txopt_put(opt_to_free);
 	return err < 0 ? err : len;
 do_confirm:
 	dst_confirm(dst);
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 0909f4e..f30bfdc 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -225,7 +225,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 		memset(&fl6, 0, sizeof(fl6));
 		fl6.flowi6_proto = IPPROTO_TCP;
 		fl6.daddr = ireq->ir_v6_rmt_addr;
-		final_p = fl6_update_dst(&fl6, np->opt, &final);
+		final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final);
 		fl6.saddr = ireq->ir_v6_loc_addr;
 		fl6.flowi6_oif = sk->sk_bound_dev_if;
 		fl6.flowi6_mark = ireq->ir_mark;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 7a6cea5..45e473e 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -120,6 +120,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct in6_addr *saddr = NULL, *final_p, final;
+	struct ipv6_txoptions *opt;
 	struct flowi6 fl6;
 	struct dst_entry *dst;
 	int addr_type;
@@ -235,7 +236,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	fl6.fl6_dport = usin->sin6_port;
 	fl6.fl6_sport = inet->inet_sport;
 
-	final_p = fl6_update_dst(&fl6, np->opt, &final);
+	opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+	final_p = fl6_update_dst(&fl6, opt, &final);
 
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
@@ -263,9 +265,9 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 		tcp_fetch_timewait_stamp(sk, dst);
 
 	icsk->icsk_ext_hdr_len = 0;
-	if (np->opt)
-		icsk->icsk_ext_hdr_len = (np->opt->opt_flen +
-					  np->opt->opt_nflen);
+	if (opt)
+		icsk->icsk_ext_hdr_len = opt->opt_flen +
+					 opt->opt_nflen;
 
 	tp->rx_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
 
@@ -461,7 +463,8 @@ static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst,
 			fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));
 
 		skb_set_queue_mapping(skb, queue_mapping);
-		err = ip6_xmit(sk, skb, fl6, np->opt, np->tclass);
+		err = ip6_xmit(sk, skb, fl6, rcu_dereference(np->opt),
+			       np->tclass);
 		err = net_xmit_eval(err);
 	}
 
@@ -991,6 +994,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	struct inet_request_sock *ireq;
 	struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
 	struct tcp6_sock *newtcp6sk;
+	struct ipv6_txoptions *opt;
 	struct inet_sock *newinet;
 	struct tcp_sock *newtp;
 	struct sock *newsk;
@@ -1126,13 +1130,15 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	   but we make one more one thing there: reattach optmem
 	   to newsk.
 	 */
-	if (np->opt)
-		newnp->opt = ipv6_dup_options(newsk, np->opt);
-
+	opt = rcu_dereference(np->opt);
+	if (opt) {
+		opt = ipv6_dup_options(newsk, opt);
+		RCU_INIT_POINTER(newnp->opt, opt);
+	}
 	inet_csk(newsk)->icsk_ext_hdr_len = 0;
-	if (newnp->opt)
-		inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen +
-						     newnp->opt->opt_flen);
+	if (opt)
+		inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen +
+						    opt->opt_flen;
 
 	tcp_ca_openreq_child(newsk, dst);
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index e51fc3e..7333f35 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1107,6 +1107,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
 	struct in6_addr *daddr, *final_p, final;
 	struct ipv6_txoptions *opt = NULL;
+	struct ipv6_txoptions *opt_to_free = NULL;
 	struct ip6_flowlabel *flowlabel = NULL;
 	struct flowi6 fl6;
 	struct dst_entry *dst;
@@ -1260,8 +1261,10 @@ do_udp_sendmsg:
 			opt = NULL;
 		connected = 0;
 	}
-	if (!opt)
-		opt = np->opt;
+	if (!opt) {
+		opt = txopt_get(np);
+		opt_to_free = opt;
+	}
 	if (flowlabel)
 		opt = fl6_merge_options(&opt_space, flowlabel, opt);
 	opt = ipv6_fixup_options(&opt_space, opt);
@@ -1370,6 +1373,7 @@ release_dst:
 out:
 	dst_release(dst);
 	fl6_sock_release(flowlabel);
+	txopt_put(opt_to_free);
 	if (!err)
 		return len;
 	/*
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index d1ded37..0ce9da9 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -486,6 +486,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	DECLARE_SOCKADDR(struct sockaddr_l2tpip6 *, lsa, msg->msg_name);
 	struct in6_addr *daddr, *final_p, final;
 	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct ipv6_txoptions *opt_to_free = NULL;
 	struct ipv6_txoptions *opt = NULL;
 	struct ip6_flowlabel *flowlabel = NULL;
 	struct dst_entry *dst = NULL;
@@ -575,8 +576,10 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 			opt = NULL;
 	}
 
-	if (opt == NULL)
-		opt = np->opt;
+	if (!opt) {
+		opt = txopt_get(np);
+		opt_to_free = opt;
+	}
 	if (flowlabel)
 		opt = fl6_merge_options(&opt_space, flowlabel, opt);
 	opt = ipv6_fixup_options(&opt_space, opt);
@@ -631,6 +634,7 @@ done:
 	dst_release(dst);
 out:
 	fl6_sock_release(flowlabel);
+	txopt_put(opt_to_free);
 
 	return err < 0 ? err : len;
 
-- 
2.1.0


From 265b1a0aef414f7ded963f97f93b217901bf5d35 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <koct9i@gmail.com>
Date: Tue, 1 Dec 2015 01:14:48 +0300
Subject: [PATCH 34/37] net/neighbour: fix crash at dumping device-agnostic
 proxy entries

[ Upstream commit 6adc5fd6a142c6e2c80574c1db0c7c17dedaa42e ]

Proxy entries could have null pointer to net-device.

Signed-off-by: Konstantin Khlebnikov <koct9i@gmail.com>
Fixes: 84920c1420e2 ("net: Allow ipv6 proxies and arp proxies be shown with iproute2")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 84195da..ecdb171 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2210,7 +2210,7 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn,
 	ndm->ndm_pad2    = 0;
 	ndm->ndm_flags	 = pn->flags | NTF_PROXY;
 	ndm->ndm_type	 = RTN_UNICAST;
-	ndm->ndm_ifindex = pn->dev->ifindex;
+	ndm->ndm_ifindex = pn->dev ? pn->dev->ifindex : 0;
 	ndm->ndm_state	 = NUD_NONE;
 
 	if (nla_put(skb, NDA_DST, tbl->key_len, pn->key))
@@ -2285,7 +2285,7 @@ static int pneigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
 		if (h > s_h)
 			s_idx = 0;
 		for (n = tbl->phash_buckets[h], idx = 0; n; n = n->next) {
-			if (dev_net(n->dev) != net)
+			if (pneigh_net(n) != net)
 				continue;
 			if (idx < s_idx)
 				goto next;
-- 
2.1.0


From ab005ac72d13e866c39f2589b0499ae78b091116 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 1 Dec 2015 07:20:07 -0800
Subject: [PATCH 35/37] ipv6: sctp: implement sctp_v6_destroy_sock()

[ Upstream commit 602dd62dfbda3e63a2d6a3cbde953ebe82bf5087 ]

Dmitry Vyukov reported a memory leak using IPV6 SCTP sockets.

We need to call inet6_destroy_sock() to properly release
inet6 specific fields.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 17bef01..3ec88be 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -7375,6 +7375,13 @@ struct proto sctp_prot = {
 
 #if IS_ENABLED(CONFIG_IPV6)
 
+#include <net/transp_v6.h>
+static void sctp_v6_destroy_sock(struct sock *sk)
+{
+	sctp_destroy_sock(sk);
+	inet6_destroy_sock(sk);
+}
+
 struct proto sctpv6_prot = {
 	.name		= "SCTPv6",
 	.owner		= THIS_MODULE,
@@ -7384,7 +7391,7 @@ struct proto sctpv6_prot = {
 	.accept		= sctp_accept,
 	.ioctl		= sctp_ioctl,
 	.init		= sctp_init_sock,
-	.destroy	= sctp_destroy_sock,
+	.destroy	= sctp_v6_destroy_sock,
 	.shutdown	= sctp_shutdown,
 	.setsockopt	= sctp_setsockopt,
 	.getsockopt	= sctp_getsockopt,
-- 
2.1.0


From 04b53c85122a9889c07dcae0d9aaa1f8491425b8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 1 Dec 2015 20:08:51 -0800
Subject: [PATCH 36/37] net_sched: fix qdisc_tree_decrease_qlen() races

[ Upstream commit 4eaf3b84f2881c9c028f1d5e76c52ab575fe3a66 ]

qdisc_tree_decrease_qlen() suffers from two problems on multiqueue
devices.

One problem is that it updates sch->q.qlen and sch->qstats.drops
on the mq/mqprio root qdisc, while it should not : Daniele
reported underflows errors :
[  681.774821] PAX: sch->q.qlen: 0 n: 1
[  681.774825] PAX: size overflow detected in function qdisc_tree_decrease_qlen net/sched/sch_api.c:769 cicus.693_49 min, count: 72, decl: qlen; num: 0; context: sk_buff_head;
[  681.774954] CPU: 2 PID: 19 Comm: ksoftirqd/2 Tainted: G           O    4.2.6.201511282239-1-grsec #1
[  681.774955] Hardware name: ASUSTeK COMPUTER INC. X302LJ/X302LJ, BIOS X302LJ.202 03/05/2015
[  681.774956]  ffffffffa9a04863 0000000000000000 0000000000000000 ffffffffa990ff7c
[  681.774959]  ffffc90000d3bc38 ffffffffa95d2810 0000000000000007 ffffffffa991002b
[  681.774960]  ffffc90000d3bc68 ffffffffa91a44f4 0000000000000001 0000000000000001
[  681.774962] Call Trace:
[  681.774967]  [<ffffffffa95d2810>] dump_stack+0x4c/0x7f
[  681.774970]  [<ffffffffa91a44f4>] report_size_overflow+0x34/0x50
[  681.774972]  [<ffffffffa94d17e2>] qdisc_tree_decrease_qlen+0x152/0x160
[  681.774976]  [<ffffffffc02694b1>] fq_codel_dequeue+0x7b1/0x820 [sch_fq_codel]
[  681.774978]  [<ffffffffc02680a0>] ? qdisc_peek_dequeued+0xa0/0xa0 [sch_fq_codel]
[  681.774980]  [<ffffffffa94cd92d>] __qdisc_run+0x4d/0x1d0
[  681.774983]  [<ffffffffa949b2b2>] net_tx_action+0xc2/0x160
[  681.774985]  [<ffffffffa90664c1>] __do_softirq+0xf1/0x200
[  681.774987]  [<ffffffffa90665ee>] run_ksoftirqd+0x1e/0x30
[  681.774989]  [<ffffffffa90896b0>] smpboot_thread_fn+0x150/0x260
[  681.774991]  [<ffffffffa9089560>] ? sort_range+0x40/0x40
[  681.774992]  [<ffffffffa9085fe4>] kthread+0xe4/0x100
[  681.774994]  [<ffffffffa9085f00>] ? kthread_worker_fn+0x170/0x170
[  681.774995]  [<ffffffffa95d8d1e>] ret_from_fork+0x3e/0x70

mq/mqprio have their own ways to report qlen/drops by folding stats on
all their queues, with appropriate locking.

A second problem is that qdisc_tree_decrease_qlen() calls qdisc_lookup()
without proper locking : concurrent qdisc updates could corrupt the list
that qdisc_match_from_root() parses to find a qdisc given its handle.

Fix first problem adding a TCQ_F_NOPARENT qdisc flag that
qdisc_tree_decrease_qlen() can use to abort its tree traversal,
as soon as it meets a mq/mqprio qdisc children.

Second problem can be fixed by RCU protection.
Qdisc are already freed after RCU grace period, so qdisc_list_add() and
qdisc_list_del() simply have to use appropriate rcu list variants.

A future patch will add a per struct netdev_queue list anchor, so that
qdisc_tree_decrease_qlen() can have more efficient lookups.

Reported-by: Daniele Fucini <dfucini@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Cong Wang <cwang@twopensource.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h |  3 +++
 net/sched/sch_api.c       | 27 ++++++++++++++++++---------
 net/sched/sch_generic.c   |  2 +-
 net/sched/sch_mq.c        |  4 ++--
 net/sched/sch_mqprio.c    |  4 ++--
 5 files changed, 26 insertions(+), 14 deletions(-)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 2738f6f..49dda38 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -61,6 +61,9 @@ struct Qdisc {
 				      */
 #define TCQ_F_WARN_NONWC	(1 << 16)
 #define TCQ_F_CPUSTATS		0x20 /* run using percpu statistics */
+#define TCQ_F_NOPARENT		0x40 /* root of its hierarchy :
+				      * qdisc_tree_decrease_qlen() should stop.
+				      */
 	u32			limit;
 	const struct Qdisc_ops	*ops;
 	struct qdisc_size_table	__rcu *stab;
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index f06aa01..1a0aa2a 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -253,7 +253,8 @@ int qdisc_set_default(const char *name)
 }
 
 /* We know handle. Find qdisc among all qdisc's attached to device
-   (root qdisc, all its children, children of children etc.)
+ * (root qdisc, all its children, children of children etc.)
+ * Note: caller either uses rtnl or rcu_read_lock()
  */
 
 static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle)
@@ -264,7 +265,7 @@ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle)
 	    root->handle == handle)
 		return root;
 
-	list_for_each_entry(q, &root->list, list) {
+	list_for_each_entry_rcu(q, &root->list, list) {
 		if (q->handle == handle)
 			return q;
 	}
@@ -277,15 +278,18 @@ void qdisc_list_add(struct Qdisc *q)
 		struct Qdisc *root = qdisc_dev(q)->qdisc;
 
 		WARN_ON_ONCE(root == &noop_qdisc);
-		list_add_tail(&q->list, &root->list);
+		ASSERT_RTNL();
+		list_add_tail_rcu(&q->list, &root->list);
 	}
 }
 EXPORT_SYMBOL(qdisc_list_add);
 
 void qdisc_list_del(struct Qdisc *q)
 {
-	if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS))
-		list_del(&q->list);
+	if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) {
+		ASSERT_RTNL();
+		list_del_rcu(&q->list);
+	}
 }
 EXPORT_SYMBOL(qdisc_list_del);
 
@@ -750,14 +754,18 @@ void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
 	if (n == 0)
 		return;
 	drops = max_t(int, n, 0);
+	rcu_read_lock();
 	while ((parentid = sch->parent)) {
 		if (TC_H_MAJ(parentid) == TC_H_MAJ(TC_H_INGRESS))
-			return;
+			break;
 
+		if (sch->flags & TCQ_F_NOPARENT)
+			break;
+		/* TODO: perform the search on a per txq basis */
 		sch = qdisc_lookup(qdisc_dev(sch), TC_H_MAJ(parentid));
 		if (sch == NULL) {
-			WARN_ON(parentid != TC_H_ROOT);
-			return;
+			WARN_ON_ONCE(parentid != TC_H_ROOT);
+			break;
 		}
 		cops = sch->ops->cl_ops;
 		if (cops->qlen_notify) {
@@ -768,6 +776,7 @@ void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
 		sch->q.qlen -= n;
 		__qdisc_qstats_drop(sch, drops);
 	}
+	rcu_read_unlock();
 }
 EXPORT_SYMBOL(qdisc_tree_decrease_qlen);
 
@@ -941,7 +950,7 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue,
 		}
 		lockdep_set_class(qdisc_lock(sch), &qdisc_tx_lock);
 		if (!netif_is_multiqueue(dev))
-			sch->flags |= TCQ_F_ONETXQUEUE;
+			sch->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
 	}
 
 	sch->handle = handle;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 6efca30..b453270 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -743,7 +743,7 @@ static void attach_one_default_qdisc(struct net_device *dev,
 			return;
 		}
 		if (!netif_is_multiqueue(dev))
-			qdisc->flags |= TCQ_F_ONETXQUEUE;
+			qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
 	}
 	dev_queue->qdisc_sleeping = qdisc;
 }
diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
index f3cbaec..3e82f04 100644
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -63,7 +63,7 @@ static int mq_init(struct Qdisc *sch, struct nlattr *opt)
 		if (qdisc == NULL)
 			goto err;
 		priv->qdiscs[ntx] = qdisc;
-		qdisc->flags |= TCQ_F_ONETXQUEUE;
+		qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
 	}
 
 	sch->flags |= TCQ_F_MQROOT;
@@ -156,7 +156,7 @@ static int mq_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new,
 
 	*old = dev_graft_qdisc(dev_queue, new);
 	if (new)
-		new->flags |= TCQ_F_ONETXQUEUE;
+		new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
 	if (dev->flags & IFF_UP)
 		dev_activate(dev);
 	return 0;
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index 3811a74..ad70ecf 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -132,7 +132,7 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt)
 			goto err;
 		}
 		priv->qdiscs[i] = qdisc;
-		qdisc->flags |= TCQ_F_ONETXQUEUE;
+		qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
 	}
 
 	/* If the mqprio options indicate that hardware should own
@@ -209,7 +209,7 @@ static int mqprio_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new,
 	*old = dev_graft_qdisc(dev_queue, new);
 
 	if (new)
-		new->flags |= TCQ_F_ONETXQUEUE;
+		new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
 
 	if (dev->flags & IFF_UP)
 		dev_activate(dev);
-- 
2.1.0


From 1be90963346785f5a081544af299f7a7e4de8a6a Mon Sep 17 00:00:00 2001
From: Andrej Ota <andrej@ota.si>
Date: Thu, 15 Oct 2015 00:14:37 +0200
Subject: [PATCH 37/37] via-rhine: fix VLAN receive handling regression.

[ Upstream commit 5f715c097965c0ad037f64393d0b95c50287775b ]

Because eth_type_trans() consumes ethernet header worth of bytes, a call
to read TCI from end of packet using rhine_rx_vlan_tag() no longer works
as it's reading from an invalid offset.

Tested to be working on PCEngines Alix board.

Fixes: 810f19bcb862 ("via-rhine: add consistent memory barrier in vlan receive code.")
Signed-off-by: Andrej Ota <andrej@ota.si>
Acked-by: Francois Romieu <romieu@fr.zoreil.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/via/via-rhine.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c
index a832637..2b7550c 100644
--- a/drivers/net/ethernet/via/via-rhine.c
+++ b/drivers/net/ethernet/via/via-rhine.c
@@ -2134,10 +2134,11 @@ static int rhine_rx(struct net_device *dev, int limit)
 			}
 
 			skb_put(skb, pkt_len);
-			skb->protocol = eth_type_trans(skb, dev);
 
 			rhine_rx_vlan_tag(skb, desc, data_size);
 
+			skb->protocol = eth_type_trans(skb, dev);
+
 			netif_receive_skb(skb);
 
 			u64_stats_update_begin(&rp->rx_stats.syncp);
-- 
2.1.0


[-- Attachment #5: net_43.mbox --]
[-- Type: Application/Octet-Stream, Size: 143618 bytes --]

From 19900d0bd94181ffa4d2130b5d6afcc6aef805e1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?fran=C3=A7ois=20romieu?= <romieu@fr.zoreil.com>
Date: Wed, 11 Nov 2015 23:35:18 +0100
Subject: [PATCH 01/43] r8169: fix kasan reported skb use-after-free.

[ Upstream commit 39174291d8e8acfd1113214a943263aaa03c57c8 ]

Signed-off-by: Francois Romieu <romieu@fr.zoreil.com>
Reported-by: Dave Jones <davej@codemonkey.org.uk>
Fixes: d7d2d89d4b0af ("r8169: Add software counter for multicast packages")
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Corinna Vinschen <vinschen@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index b4f2123..79ef799 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -7429,15 +7429,15 @@ process_pkt:
 
 			rtl8169_rx_vlan_tag(desc, skb);
 
+			if (skb->pkt_type == PACKET_MULTICAST)
+				dev->stats.multicast++;
+
 			napi_gro_receive(&tp->napi, skb);
 
 			u64_stats_update_begin(&tp->rx_stats.syncp);
 			tp->rx_stats.packets++;
 			tp->rx_stats.bytes += pkt_size;
 			u64_stats_update_end(&tp->rx_stats.syncp);
-
-			if (skb->pkt_type == PACKET_MULTICAST)
-				dev->stats.multicast++;
 		}
 release_descriptor:
 		desc->opts2 = 0;
-- 
2.1.0


From 16e46199ccdb834330ed801019d6b96077291d7c Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Tue, 10 Nov 2015 16:23:15 +0100
Subject: [PATCH 02/43] af-unix: fix use-after-free with concurrent readers
 while splicing

[ Upstream commit 73ed5d25dce0354ea381d6dc93005c3085fae03d ]

During splicing an af-unix socket to a pipe we have to drop all
af-unix socket locks. While doing so we allow another reader to enter
unix_stream_read_generic which can read, copy and finally free another
skb. If exactly this skb is just in process of being spliced we get a
use-after-free report by kasan.

First, we must make sure to not have a free while the skb is used during
the splice operation. We simply increment its use counter before unlocking
the reader lock.

Stream sockets have the nice characteristic that we don't care about
zero length writes and they never reach the peer socket's queue. That
said, we can take the UNIXCB.consumed field as the indicator if the
skb was already freed from the socket's receive queue. If the skb was
fully consumed after we locked the reader side again we know it has been
dropped by a second reader. We indicate a short read to user space and
abort the current splice operation.

This bug has been found with syzkaller
(http://github.com/google/syzkaller) by Dmitry Vyukov.

Fixes: 2b514574f7e8 ("net: af_unix: implement splice for stream af_unix sockets")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 94f6582..a5afe41 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -440,6 +440,7 @@ static void unix_release_sock(struct sock *sk, int embrion)
 		if (state == TCP_LISTEN)
 			unix_release_sock(skb->sk, 1);
 		/* passed fds are erased in the kfree_skb hook	      */
+		UNIXCB(skb).consumed = skb->len;
 		kfree_skb(skb);
 	}
 
@@ -2071,6 +2072,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state)
 
 	do {
 		int chunk;
+		bool drop_skb;
 		struct sk_buff *skb, *last;
 
 		unix_state_lock(sk);
@@ -2151,7 +2153,11 @@ unlock:
 		}
 
 		chunk = min_t(unsigned int, unix_skb_len(skb) - skip, size);
+		skb_get(skb);
 		chunk = state->recv_actor(skb, skip, chunk, state);
+		drop_skb = !unix_skb_len(skb);
+		/* skb is only safe to use if !drop_skb */
+		consume_skb(skb);
 		if (chunk < 0) {
 			if (copied == 0)
 				copied = -EFAULT;
@@ -2160,6 +2166,18 @@ unlock:
 		copied += chunk;
 		size -= chunk;
 
+		if (drop_skb) {
+			/* the skb was touched by a concurrent reader;
+			 * we should not expect anything from this skb
+			 * anymore and assume it invalid - we can be
+			 * sure it was dropped from the socket queue
+			 *
+			 * let's report a short read
+			 */
+			err = 0;
+			break;
+		}
+
 		/* Mark read part of skb as used */
 		if (!(flags & MSG_PEEK)) {
 			UNIXCB(skb).consumed += chunk;
-- 
2.1.0


From 75262dbd214a2a628aa333d51531b9e64fd7dc7e Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Mon, 16 Nov 2015 16:25:56 +0100
Subject: [PATCH 03/43] af_unix: don't append consumed skbs to sk_receive_queue

[ Upstream commit 8844f97238ca6c1ca92a5d6c69f53efd361a266f ]

In case multiple writes to a unix stream socket race we could end up in a
situation where we pre-allocate a new skb for use in unix_stream_sendpage
but have to free it again in the locked section because another skb
has been appended meanwhile, which we must use. Accidentally we didn't
clear the pointer after consuming it and so we touched freed memory
while appending it to the sk_receive_queue. So, clear the pointer after
consuming the skb.

This bug has been found with syzkaller
(http://github.com/google/syzkaller) by Dmitry Vyukov.

Fixes: 869e7c62486e ("net: af_unix: implement stream sendpage support")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index a5afe41..3e2ca39 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1799,6 +1799,7 @@ alloc_skb:
 		 * this - does no harm
 		 */
 		consume_skb(newskb);
+		newskb = NULL;
 	}
 
 	if (skb_append_pagefrags(skb, page, offset, size)) {
-- 
2.1.0


From faa83c6e01f8604c385c4e0ccc7ca1da591100a5 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Tue, 17 Nov 2015 15:10:59 +0100
Subject: [PATCH 04/43] af_unix: take receive queue lock while appending new
 skb

[ Upstream commit a3a116e04cc6a94d595ead4e956ab1bc1d2f4746 ]

While possibly in future we don't necessarily need to use
sk_buff_head.lock this is a rather larger change, as it affects the
af_unix fd garbage collector, diag and socket cleanups. This is too much
for a stable patch.

For the time being grab sk_buff_head.lock without disabling bh and irqs,
so don't use locked skb_queue_tail.

Fixes: 869e7c62486e ("net: af_unix: implement stream sendpage support")
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Reported-by: Eric Dumazet <edumazet@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 3e2ca39..42ab2cc 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1812,8 +1812,11 @@ alloc_skb:
 	skb->truesize += size;
 	atomic_add(size, &sk->sk_wmem_alloc);
 
-	if (newskb)
+	if (newskb) {
+		spin_lock(&other->sk_receive_queue.lock);
 		__skb_queue_tail(&other->sk_receive_queue, newskb);
+		spin_unlock(&other->sk_receive_queue.lock);
+	}
 
 	unix_state_unlock(other);
 	mutex_unlock(&unix_sk(other)->readlock);
-- 
2.1.0


From a46b9d2bac864f3ef6b21eb96864ddd88794222d Mon Sep 17 00:00:00 2001
From: Rainer Weikusat <rweikusat@mobileactivedefense.com>
Date: Fri, 20 Nov 2015 22:07:23 +0000
Subject: [PATCH 05/43] unix: avoid use-after-free in ep_remove_wait_queue

[ Upstream commit 7d267278a9ece963d77eefec61630223fce08c6c ]

Rainer Weikusat <rweikusat@mobileactivedefense.com> writes:
An AF_UNIX datagram socket being the client in an n:1 association with
some server socket is only allowed to send messages to the server if the
receive queue of this socket contains at most sk_max_ack_backlog
datagrams. This implies that prospective writers might be forced to go
to sleep despite none of the message presently enqueued on the server
receive queue were sent by them. In order to ensure that these will be
woken up once space becomes again available, the present unix_dgram_poll
routine does a second sock_poll_wait call with the peer_wait wait queue
of the server socket as queue argument (unix_dgram_recvmsg does a wake
up on this queue after a datagram was received). This is inherently
problematic because the server socket is only guaranteed to remain alive
for as long as the client still holds a reference to it. In case the
connection is dissolved via connect or by the dead peer detection logic
in unix_dgram_sendmsg, the server socket may be freed despite "the
polling mechanism" (in particular, epoll) still has a pointer to the
corresponding peer_wait queue. There's no way to forcibly deregister a
wait queue with epoll.

Based on an idea by Jason Baron, the patch below changes the code such
that a wait_queue_t belonging to the client socket is enqueued on the
peer_wait queue of the server whenever the peer receive queue full
condition is detected by either a sendmsg or a poll. A wake up on the
peer queue is then relayed to the ordinary wait queue of the client
socket via wake function. The connection to the peer wait queue is again
dissolved if either a wake up is about to be relayed or the client
socket reconnects or a dead peer is detected or the client socket is
itself closed. This enables removing the second sock_poll_wait from
unix_dgram_poll, thus avoiding the use-after-free, while still ensuring
that no blocked writer sleeps forever.

Signed-off-by: Rainer Weikusat <rweikusat@mobileactivedefense.com>
Fixes: ec0d215f9420 ("af_unix: fix 'poll for write'/connected DGRAM sockets")
Reviewed-by: Jason Baron <jbaron@akamai.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/af_unix.h |   1 +
 net/unix/af_unix.c    | 183 ++++++++++++++++++++++++++++++++++++++++++++------
 2 files changed, 165 insertions(+), 19 deletions(-)

diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index b36d837..2a91a05 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -62,6 +62,7 @@ struct unix_sock {
 #define UNIX_GC_CANDIDATE	0
 #define UNIX_GC_MAYBE_CYCLE	1
 	struct socket_wq	peer_wq;
+	wait_queue_t		peer_wake;
 };
 
 static inline struct unix_sock *unix_sk(const struct sock *sk)
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 42ab2cc..153b2f2 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -326,6 +326,118 @@ found:
 	return s;
 }
 
+/* Support code for asymmetrically connected dgram sockets
+ *
+ * If a datagram socket is connected to a socket not itself connected
+ * to the first socket (eg, /dev/log), clients may only enqueue more
+ * messages if the present receive queue of the server socket is not
+ * "too large". This means there's a second writeability condition
+ * poll and sendmsg need to test. The dgram recv code will do a wake
+ * up on the peer_wait wait queue of a socket upon reception of a
+ * datagram which needs to be propagated to sleeping would-be writers
+ * since these might not have sent anything so far. This can't be
+ * accomplished via poll_wait because the lifetime of the server
+ * socket might be less than that of its clients if these break their
+ * association with it or if the server socket is closed while clients
+ * are still connected to it and there's no way to inform "a polling
+ * implementation" that it should let go of a certain wait queue
+ *
+ * In order to propagate a wake up, a wait_queue_t of the client
+ * socket is enqueued on the peer_wait queue of the server socket
+ * whose wake function does a wake_up on the ordinary client socket
+ * wait queue. This connection is established whenever a write (or
+ * poll for write) hit the flow control condition and broken when the
+ * association to the server socket is dissolved or after a wake up
+ * was relayed.
+ */
+
+static int unix_dgram_peer_wake_relay(wait_queue_t *q, unsigned mode, int flags,
+				      void *key)
+{
+	struct unix_sock *u;
+	wait_queue_head_t *u_sleep;
+
+	u = container_of(q, struct unix_sock, peer_wake);
+
+	__remove_wait_queue(&unix_sk(u->peer_wake.private)->peer_wait,
+			    q);
+	u->peer_wake.private = NULL;
+
+	/* relaying can only happen while the wq still exists */
+	u_sleep = sk_sleep(&u->sk);
+	if (u_sleep)
+		wake_up_interruptible_poll(u_sleep, key);
+
+	return 0;
+}
+
+static int unix_dgram_peer_wake_connect(struct sock *sk, struct sock *other)
+{
+	struct unix_sock *u, *u_other;
+	int rc;
+
+	u = unix_sk(sk);
+	u_other = unix_sk(other);
+	rc = 0;
+	spin_lock(&u_other->peer_wait.lock);
+
+	if (!u->peer_wake.private) {
+		u->peer_wake.private = other;
+		__add_wait_queue(&u_other->peer_wait, &u->peer_wake);
+
+		rc = 1;
+	}
+
+	spin_unlock(&u_other->peer_wait.lock);
+	return rc;
+}
+
+static void unix_dgram_peer_wake_disconnect(struct sock *sk,
+					    struct sock *other)
+{
+	struct unix_sock *u, *u_other;
+
+	u = unix_sk(sk);
+	u_other = unix_sk(other);
+	spin_lock(&u_other->peer_wait.lock);
+
+	if (u->peer_wake.private == other) {
+		__remove_wait_queue(&u_other->peer_wait, &u->peer_wake);
+		u->peer_wake.private = NULL;
+	}
+
+	spin_unlock(&u_other->peer_wait.lock);
+}
+
+static void unix_dgram_peer_wake_disconnect_wakeup(struct sock *sk,
+						   struct sock *other)
+{
+	unix_dgram_peer_wake_disconnect(sk, other);
+	wake_up_interruptible_poll(sk_sleep(sk),
+				   POLLOUT |
+				   POLLWRNORM |
+				   POLLWRBAND);
+}
+
+/* preconditions:
+ *	- unix_peer(sk) == other
+ *	- association is stable
+ */
+static int unix_dgram_peer_wake_me(struct sock *sk, struct sock *other)
+{
+	int connected;
+
+	connected = unix_dgram_peer_wake_connect(sk, other);
+
+	if (unix_recvq_full(other))
+		return 1;
+
+	if (connected)
+		unix_dgram_peer_wake_disconnect(sk, other);
+
+	return 0;
+}
+
 static inline int unix_writable(struct sock *sk)
 {
 	return (atomic_read(&sk->sk_wmem_alloc) << 2) <= sk->sk_sndbuf;
@@ -430,6 +542,8 @@ static void unix_release_sock(struct sock *sk, int embrion)
 			skpair->sk_state_change(skpair);
 			sk_wake_async(skpair, SOCK_WAKE_WAITD, POLL_HUP);
 		}
+
+		unix_dgram_peer_wake_disconnect(sk, skpair);
 		sock_put(skpair); /* It may now die */
 		unix_peer(sk) = NULL;
 	}
@@ -665,6 +779,7 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern)
 	INIT_LIST_HEAD(&u->link);
 	mutex_init(&u->readlock); /* single task reading lock */
 	init_waitqueue_head(&u->peer_wait);
+	init_waitqueue_func_entry(&u->peer_wake, unix_dgram_peer_wake_relay);
 	unix_insert_socket(unix_sockets_unbound(sk), sk);
 out:
 	if (sk == NULL)
@@ -1032,6 +1147,8 @@ restart:
 	if (unix_peer(sk)) {
 		struct sock *old_peer = unix_peer(sk);
 		unix_peer(sk) = other;
+		unix_dgram_peer_wake_disconnect_wakeup(sk, old_peer);
+
 		unix_state_double_unlock(sk, other);
 
 		if (other != old_peer)
@@ -1471,6 +1588,7 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 	struct scm_cookie scm;
 	int max_level;
 	int data_len = 0;
+	int sk_locked;
 
 	wait_for_unix_gc();
 	err = scm_send(sock, msg, &scm, false);
@@ -1549,12 +1667,14 @@ restart:
 		goto out_free;
 	}
 
+	sk_locked = 0;
 	unix_state_lock(other);
+restart_locked:
 	err = -EPERM;
 	if (!unix_may_send(sk, other))
 		goto out_unlock;
 
-	if (sock_flag(other, SOCK_DEAD)) {
+	if (unlikely(sock_flag(other, SOCK_DEAD))) {
 		/*
 		 *	Check with 1003.1g - what should
 		 *	datagram error
@@ -1562,10 +1682,14 @@ restart:
 		unix_state_unlock(other);
 		sock_put(other);
 
+		if (!sk_locked)
+			unix_state_lock(sk);
+
 		err = 0;
-		unix_state_lock(sk);
 		if (unix_peer(sk) == other) {
 			unix_peer(sk) = NULL;
+			unix_dgram_peer_wake_disconnect_wakeup(sk, other);
+
 			unix_state_unlock(sk);
 
 			unix_dgram_disconnected(sk, other);
@@ -1591,21 +1715,38 @@ restart:
 			goto out_unlock;
 	}
 
-	if (unix_peer(other) != sk && unix_recvq_full(other)) {
-		if (!timeo) {
-			err = -EAGAIN;
-			goto out_unlock;
+	if (unlikely(unix_peer(other) != sk && unix_recvq_full(other))) {
+		if (timeo) {
+			timeo = unix_wait_for_peer(other, timeo);
+
+			err = sock_intr_errno(timeo);
+			if (signal_pending(current))
+				goto out_free;
+
+			goto restart;
 		}
 
-		timeo = unix_wait_for_peer(other, timeo);
+		if (!sk_locked) {
+			unix_state_unlock(other);
+			unix_state_double_lock(sk, other);
+		}
 
-		err = sock_intr_errno(timeo);
-		if (signal_pending(current))
-			goto out_free;
+		if (unix_peer(sk) != other ||
+		    unix_dgram_peer_wake_me(sk, other)) {
+			err = -EAGAIN;
+			sk_locked = 1;
+			goto out_unlock;
+		}
 
-		goto restart;
+		if (!sk_locked) {
+			sk_locked = 1;
+			goto restart_locked;
+		}
 	}
 
+	if (unlikely(sk_locked))
+		unix_state_unlock(sk);
+
 	if (sock_flag(other, SOCK_RCVTSTAMP))
 		__net_timestamp(skb);
 	maybe_add_creds(skb, sock, other);
@@ -1619,6 +1760,8 @@ restart:
 	return len;
 
 out_unlock:
+	if (sk_locked)
+		unix_state_unlock(sk);
 	unix_state_unlock(other);
 out_free:
 	kfree_skb(skb);
@@ -2475,14 +2618,16 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock,
 		return mask;
 
 	writable = unix_writable(sk);
-	other = unix_peer_get(sk);
-	if (other) {
-		if (unix_peer(other) != sk) {
-			sock_poll_wait(file, &unix_sk(other)->peer_wait, wait);
-			if (unix_recvq_full(other))
-				writable = 0;
-		}
-		sock_put(other);
+	if (writable) {
+		unix_state_lock(sk);
+
+		other = unix_peer(sk);
+		if (other && unix_peer(other) != sk &&
+		    unix_recvq_full(other) &&
+		    unix_dgram_peer_wake_me(sk, other))
+			writable = 0;
+
+		unix_state_unlock(sk);
 	}
 
 	if (writable)
-- 
2.1.0


From 8a029a6b8df3a955bd24253ce77cfc93834ce71f Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Thu, 26 Nov 2015 12:08:18 +0100
Subject: [PATCH 06/43] af-unix: passcred support for sendpage

[ Upstream commit 9490f886b192964796285907d777ff00fba1fa0f ]

sendpage did not care about credentials at all. This could lead to
situations in which because of fd passing between processes we could
append data to skbs with different scm data. It is illegal to splice those
skbs together. Instead we have to allocate a new skb and if requested
fill out the scm details.

Fixes: 869e7c62486ec ("net: af_unix: implement stream sendpage support")
Reported-by: Al Viro <viro@zeniv.linux.org.uk>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c | 79 +++++++++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 64 insertions(+), 15 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 153b2f2..128b098 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1550,6 +1550,14 @@ static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool sen
 	return err;
 }
 
+static bool unix_passcred_enabled(const struct socket *sock,
+				  const struct sock *other)
+{
+	return test_bit(SOCK_PASSCRED, &sock->flags) ||
+	       !other->sk_socket ||
+	       test_bit(SOCK_PASSCRED, &other->sk_socket->flags);
+}
+
 /*
  * Some apps rely on write() giving SCM_CREDENTIALS
  * We include credentials if source or destination socket
@@ -1560,14 +1568,41 @@ static void maybe_add_creds(struct sk_buff *skb, const struct socket *sock,
 {
 	if (UNIXCB(skb).pid)
 		return;
-	if (test_bit(SOCK_PASSCRED, &sock->flags) ||
-	    !other->sk_socket ||
-	    test_bit(SOCK_PASSCRED, &other->sk_socket->flags)) {
+	if (unix_passcred_enabled(sock, other)) {
 		UNIXCB(skb).pid  = get_pid(task_tgid(current));
 		current_uid_gid(&UNIXCB(skb).uid, &UNIXCB(skb).gid);
 	}
 }
 
+static int maybe_init_creds(struct scm_cookie *scm,
+			    struct socket *socket,
+			    const struct sock *other)
+{
+	int err;
+	struct msghdr msg = { .msg_controllen = 0 };
+
+	err = scm_send(socket, &msg, scm, false);
+	if (err)
+		return err;
+
+	if (unix_passcred_enabled(socket, other)) {
+		scm->pid = get_pid(task_tgid(current));
+		current_uid_gid(&scm->creds.uid, &scm->creds.gid);
+	}
+	return err;
+}
+
+static bool unix_skb_scm_eq(struct sk_buff *skb,
+			    struct scm_cookie *scm)
+{
+	const struct unix_skb_parms *u = &UNIXCB(skb);
+
+	return u->pid == scm->pid &&
+	       uid_eq(u->uid, scm->creds.uid) &&
+	       gid_eq(u->gid, scm->creds.gid) &&
+	       unix_secdata_eq(scm, skb);
+}
+
 /*
  *	Send AF_UNIX data.
  */
@@ -1883,8 +1918,10 @@ out_err:
 static ssize_t unix_stream_sendpage(struct socket *socket, struct page *page,
 				    int offset, size_t size, int flags)
 {
-	int err = 0;
-	bool send_sigpipe = true;
+	int err;
+	bool send_sigpipe = false;
+	bool init_scm = true;
+	struct scm_cookie scm;
 	struct sock *other, *sk = socket->sk;
 	struct sk_buff *skb, *newskb = NULL, *tail = NULL;
 
@@ -1902,7 +1939,7 @@ alloc_skb:
 		newskb = sock_alloc_send_pskb(sk, 0, 0, flags & MSG_DONTWAIT,
 					      &err, 0);
 		if (!newskb)
-			return err;
+			goto err;
 	}
 
 	/* we must acquire readlock as we modify already present
@@ -1911,12 +1948,12 @@ alloc_skb:
 	err = mutex_lock_interruptible(&unix_sk(other)->readlock);
 	if (err) {
 		err = flags & MSG_DONTWAIT ? -EAGAIN : -ERESTARTSYS;
-		send_sigpipe = false;
 		goto err;
 	}
 
 	if (sk->sk_shutdown & SEND_SHUTDOWN) {
 		err = -EPIPE;
+		send_sigpipe = true;
 		goto err_unlock;
 	}
 
@@ -1925,17 +1962,27 @@ alloc_skb:
 	if (sock_flag(other, SOCK_DEAD) ||
 	    other->sk_shutdown & RCV_SHUTDOWN) {
 		err = -EPIPE;
+		send_sigpipe = true;
 		goto err_state_unlock;
 	}
 
+	if (init_scm) {
+		err = maybe_init_creds(&scm, socket, other);
+		if (err)
+			goto err_state_unlock;
+		init_scm = false;
+	}
+
 	skb = skb_peek_tail(&other->sk_receive_queue);
 	if (tail && tail == skb) {
 		skb = newskb;
-	} else if (!skb) {
-		if (newskb)
+	} else if (!skb || !unix_skb_scm_eq(skb, &scm)) {
+		if (newskb) {
 			skb = newskb;
-		else
+		} else {
+			tail = skb;
 			goto alloc_skb;
+		}
 	} else if (newskb) {
 		/* this is fast path, we don't necessarily need to
 		 * call to kfree_skb even though with newskb == NULL
@@ -1956,6 +2003,9 @@ alloc_skb:
 	atomic_add(size, &sk->sk_wmem_alloc);
 
 	if (newskb) {
+		err = unix_scm_to_skb(&scm, skb, false);
+		if (err)
+			goto err_state_unlock;
 		spin_lock(&other->sk_receive_queue.lock);
 		__skb_queue_tail(&other->sk_receive_queue, newskb);
 		spin_unlock(&other->sk_receive_queue.lock);
@@ -1965,7 +2015,7 @@ alloc_skb:
 	mutex_unlock(&unix_sk(other)->readlock);
 
 	other->sk_data_ready(other);
-
+	scm_destroy(&scm);
 	return size;
 
 err_state_unlock:
@@ -1976,6 +2026,8 @@ err:
 	kfree_skb(newskb);
 	if (send_sigpipe && !(flags & MSG_NOSIGNAL))
 		send_sig(SIGPIPE, current, 0);
+	if (!init_scm)
+		scm_destroy(&scm);
 	return err;
 }
 
@@ -2279,10 +2331,7 @@ unlock:
 
 		if (check_creds) {
 			/* Never glue messages from different writers */
-			if ((UNIXCB(skb).pid  != scm.pid) ||
-			    !uid_eq(UNIXCB(skb).uid, scm.creds.uid) ||
-			    !gid_eq(UNIXCB(skb).gid, scm.creds.gid) ||
-			    !unix_secdata_eq(&scm, skb))
+			if (!unix_skb_scm_eq(skb, &scm))
 				break;
 		} else if (test_bit(SOCK_PASSCRED, &sock->flags)) {
 			/* Copy credentials */
-- 
2.1.0


From 6f61ebb821b04690a54ae998160cb758dbaa7f9b Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 11 Nov 2015 11:51:06 -0800
Subject: [PATCH 07/43] ipv6: Avoid creating RTF_CACHE from a rt that is not
 managed by fib6 tree

[ Upstream commit 0d3f6d297bfb7af24d0508460fdb3d1ec4903fa3 ]

The original bug report:
https://bugzilla.redhat.com/show_bug.cgi?id=1272571

The setup has a IPv4 GRE tunnel running in a IPSec.  The bug
happens when ndisc starts sending router solicitation at the gre
interface.  The simplified oops stack is like:

__lock_acquire+0x1b2/0x1c30
lock_acquire+0xb9/0x140
_raw_write_lock_bh+0x3f/0x50
__ip6_ins_rt+0x2e/0x60
ip6_ins_rt+0x49/0x50
~~~~~~~~
__ip6_rt_update_pmtu.part.54+0x145/0x250
ip6_rt_update_pmtu+0x2e/0x40
~~~~~~~~
ip_tunnel_xmit+0x1f1/0xf40
__gre_xmit+0x7a/0x90
ipgre_xmit+0x15a/0x220
dev_hard_start_xmit+0x2bd/0x480
__dev_queue_xmit+0x696/0x730
dev_queue_xmit+0x10/0x20
neigh_direct_output+0x11/0x20
ip6_finish_output2+0x21f/0x770
ip6_finish_output+0xa7/0x1d0
ip6_output+0x56/0x190
~~~~~~~~
ndisc_send_skb+0x1d9/0x400
ndisc_send_rs+0x88/0xc0
~~~~~~~~

The rt passed to ip6_rt_update_pmtu() is created by
icmp6_dst_alloc() and it is not managed by the fib6 tree,
so its rt6i_table == NULL.  When __ip6_rt_update_pmtu() creates
a RTF_CACHE clone, the newly created clone also has rt6i_table == NULL
and it causes the ip6_ins_rt() oops.

During pmtu update, we only want to create a RTF_CACHE clone
from a rt which is currently managed (or owned) by the
fib6 tree.  It means either rt->rt6i_node != NULL or
rt is a RTF_PCPU clone.

It is worth to note that rt6i_table may not be NULL even it is
not (yet) managed by the fib6 tree (e.g. addrconf_dst_alloc()).
Hence, rt6i_node is a better check instead of rt6i_table.

Fixes: 45e4fd26683c ("ipv6: Only create RTF_CACHE routes after encountering pmtu")
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Reported-by: Chris Siebenmann <cks-rhbugzilla@cs.toronto.edu>
Cc: Chris Siebenmann <cks-rhbugzilla@cs.toronto.edu>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 946880a..711ec7a 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1340,6 +1340,12 @@ static void rt6_do_update_pmtu(struct rt6_info *rt, u32 mtu)
 	rt6_update_expires(rt, net->ipv6.sysctl.ip6_rt_mtu_expires);
 }
 
+static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt)
+{
+	return !(rt->rt6i_flags & RTF_CACHE) &&
+		(rt->rt6i_flags & RTF_PCPU || rt->rt6i_node);
+}
+
 static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
 				 const struct ipv6hdr *iph, u32 mtu)
 {
@@ -1353,7 +1359,7 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
 	if (mtu >= dst_mtu(dst))
 		return;
 
-	if (rt6->rt6i_flags & RTF_CACHE) {
+	if (!rt6_cache_allowed_for_pmtu(rt6)) {
 		rt6_do_update_pmtu(rt6, mtu);
 	} else {
 		const struct in6_addr *daddr, *saddr;
-- 
2.1.0


From 36e5325023d53e603ce46bfcd55587f164850102 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 11 Nov 2015 11:51:07 -0800
Subject: [PATCH 08/43] ipv6: Check expire on DST_NOCACHE route

[ Upstream commit 5973fb1e245086071bf71994c8b54d99526ded03 ]

Since the expires of the DST_NOCACHE rt can be set during
the ip6_rt_update_pmtu(), we also need to consider the expires
value when doing ip6_dst_check().

This patches creates __rt6_check_expired() to only
check the expire value (if one exists) of the current rt.

In rt6_dst_from_check(), it adds __rt6_check_expired() as
one of the condition check.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 711ec7a..ea892c1 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -403,6 +403,14 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
 	}
 }
 
+static bool __rt6_check_expired(const struct rt6_info *rt)
+{
+	if (rt->rt6i_flags & RTF_EXPIRES)
+		return time_after(jiffies, rt->dst.expires);
+	else
+		return false;
+}
+
 static bool rt6_check_expired(const struct rt6_info *rt)
 {
 	if (rt->rt6i_flags & RTF_EXPIRES) {
@@ -1270,7 +1278,8 @@ static struct dst_entry *rt6_check(struct rt6_info *rt, u32 cookie)
 
 static struct dst_entry *rt6_dst_from_check(struct rt6_info *rt, u32 cookie)
 {
-	if (rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK &&
+	if (!__rt6_check_expired(rt) &&
+	    rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK &&
 	    rt6_check((struct rt6_info *)(rt->dst.from), cookie))
 		return &rt->dst;
 	else
-- 
2.1.0


From 037104a8ac4a3509ee800cfa124897600c9483e7 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 11 Nov 2015 11:51:08 -0800
Subject: [PATCH 09/43] ipv6: Check rt->dst.from for the DST_NOCACHE route

[ Upstrem commit 02bcf4e082e4dc634409a6a6cb7def8806d6e5e6 ]

All DST_NOCACHE rt6_info used to have rt->dst.from set to
its parent.

After commit 8e3d5be73681 ("ipv6: Avoid double dst_free"),
DST_NOCACHE is also set to rt6_info which does not have
a parent (i.e. rt->dst.from is NULL).

This patch catches the rt->dst.from == NULL case.

Fixes: 8e3d5be73681 ("ipv6: Avoid double dst_free")
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h | 3 ++-
 net/ipv6/route.c      | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index aaf9700..fb961a5 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -167,7 +167,8 @@ static inline void rt6_update_expires(struct rt6_info *rt0, int timeout)
 
 static inline u32 rt6_get_cookie(const struct rt6_info *rt)
 {
-	if (rt->rt6i_flags & RTF_PCPU || unlikely(rt->dst.flags & DST_NOCACHE))
+	if (rt->rt6i_flags & RTF_PCPU ||
+	    (unlikely(rt->dst.flags & DST_NOCACHE) && rt->dst.from))
 		rt = (struct rt6_info *)(rt->dst.from);
 
 	return rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index ea892c1..d377326 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1299,7 +1299,8 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
 
 	rt6_dst_from_metrics_check(rt);
 
-	if ((rt->rt6i_flags & RTF_PCPU) || unlikely(dst->flags & DST_NOCACHE))
+	if (rt->rt6i_flags & RTF_PCPU ||
+	    (unlikely(dst->flags & DST_NOCACHE) && rt->dst.from))
 		return rt6_dst_from_check(rt, cookie);
 	else
 		return rt6_check(rt, cookie);
-- 
2.1.0


From bbecfdcd08494929d0cde9176346d51007fb77ed Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Fri, 27 Nov 2015 18:17:05 +0100
Subject: [PATCH 10/43] Revert "ipv6: ndisc: inherit metadata dst when creating
 ndisc requests"

[ Upstream commit 304d888b29cf96f1dd53511ee686499cd8cdf249 ]

This reverts commit ab450605b35caa768ca33e86db9403229bf42be4.

In IPv6, we cannot inherit the dst of the original dst. ndisc packets
are IPv6 packets and may take another route than the original packet.

This patch breaks the following scenario: a packet comes from eth0 and
is forwarded through vxlan1. The encapsulated packet triggers an NS
which cannot be sent because of the wrong route.

CC: Jiri Benc <jbenc@redhat.com>
CC: Thomas Graf <tgraf@suug.ch>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ndisc.h |  3 +--
 net/ipv6/addrconf.c |  2 +-
 net/ipv6/ndisc.c    | 10 +++-------
 net/ipv6/route.c    |  2 +-
 4 files changed, 6 insertions(+), 11 deletions(-)

diff --git a/include/net/ndisc.h b/include/net/ndisc.h
index aba5695..b3a7751 100644
--- a/include/net/ndisc.h
+++ b/include/net/ndisc.h
@@ -182,8 +182,7 @@ int ndisc_rcv(struct sk_buff *skb);
 
 void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh,
 		   const struct in6_addr *solicit,
-		   const struct in6_addr *daddr, const struct in6_addr *saddr,
-		   struct sk_buff *oskb);
+		   const struct in6_addr *daddr, const struct in6_addr *saddr);
 
 void ndisc_send_rs(struct net_device *dev,
 		   const struct in6_addr *saddr, const struct in6_addr *daddr);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index dd00828..3939dd2 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3628,7 +3628,7 @@ static void addrconf_dad_work(struct work_struct *w)
 
 	/* send a neighbour solicitation for our addr */
 	addrconf_addr_solict_mult(&ifp->addr, &mcaddr);
-	ndisc_send_ns(ifp->idev->dev, NULL, &ifp->addr, &mcaddr, &in6addr_any, NULL);
+	ndisc_send_ns(ifp->idev->dev, NULL, &ifp->addr, &mcaddr, &in6addr_any);
 out:
 	in6_ifa_put(ifp);
 	rtnl_unlock();
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 64a7135..9ad46cd 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -553,8 +553,7 @@ static void ndisc_send_unsol_na(struct net_device *dev)
 
 void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh,
 		   const struct in6_addr *solicit,
-		   const struct in6_addr *daddr, const struct in6_addr *saddr,
-		   struct sk_buff *oskb)
+		   const struct in6_addr *daddr, const struct in6_addr *saddr)
 {
 	struct sk_buff *skb;
 	struct in6_addr addr_buf;
@@ -590,9 +589,6 @@ void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh,
 		ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR,
 				       dev->dev_addr);
 
-	if (!(dev->priv_flags & IFF_XMIT_DST_RELEASE) && oskb)
-		skb_dst_copy(skb, oskb);
-
 	ndisc_send_skb(skb, daddr, saddr);
 }
 
@@ -679,12 +675,12 @@ static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb)
 				  "%s: trying to ucast probe in NUD_INVALID: %pI6\n",
 				  __func__, target);
 		}
-		ndisc_send_ns(dev, neigh, target, target, saddr, skb);
+		ndisc_send_ns(dev, neigh, target, target, saddr);
 	} else if ((probes -= NEIGH_VAR(neigh->parms, APP_PROBES)) < 0) {
 		neigh_app_ns(neigh);
 	} else {
 		addrconf_addr_solict_mult(target, &mcaddr);
-		ndisc_send_ns(dev, NULL, target, &mcaddr, saddr, skb);
+		ndisc_send_ns(dev, NULL, target, &mcaddr, saddr);
 	}
 }
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index d377326..fd0e674 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -546,7 +546,7 @@ static void rt6_probe_deferred(struct work_struct *w)
 		container_of(w, struct __rt6_probe_work, work);
 
 	addrconf_addr_solict_mult(&work->target, &mcaddr);
-	ndisc_send_ns(work->dev, NULL, &work->target, &mcaddr, NULL, NULL);
+	ndisc_send_ns(work->dev, NULL, &work->target, &mcaddr, NULL);
 	dev_put(work->dev);
 	kfree(work);
 }
-- 
2.1.0


From 3855e07a82c0180d9110ac03d84405f9ecc79866 Mon Sep 17 00:00:00 2001
From: Kamal Mostafa <kamal@canonical.com>
Date: Wed, 11 Nov 2015 14:24:27 -0800
Subject: [PATCH 11/43] tools/net: Use include/uapi with __EXPORTED_HEADERS__

[ Upstream commit d7475de58575c904818efa369c82e88c6648ce2e ]

Use the local uapi headers to keep in sync with "recently" added #define's
(e.g. SKF_AD_VLAN_TPID).  Refactored CFLAGS, and bpf_asm doesn't need -I.

Fixes: 3f356385e8a4 ("filter: bpf_asm: add minimal bpf asm tool")
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/net/Makefile | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/tools/net/Makefile b/tools/net/Makefile
index ee577ea..ddf8880 100644
--- a/tools/net/Makefile
+++ b/tools/net/Makefile
@@ -4,6 +4,9 @@ CC = gcc
 LEX = flex
 YACC = bison
 
+CFLAGS += -Wall -O2
+CFLAGS += -D__EXPORTED_HEADERS__ -I../../include/uapi -I../../include
+
 %.yacc.c: %.y
 	$(YACC) -o $@ -d $<
 
@@ -12,15 +15,13 @@ YACC = bison
 
 all : bpf_jit_disasm bpf_dbg bpf_asm
 
-bpf_jit_disasm : CFLAGS = -Wall -O2 -DPACKAGE='bpf_jit_disasm'
+bpf_jit_disasm : CFLAGS += -DPACKAGE='bpf_jit_disasm'
 bpf_jit_disasm : LDLIBS = -lopcodes -lbfd -ldl
 bpf_jit_disasm : bpf_jit_disasm.o
 
-bpf_dbg : CFLAGS = -Wall -O2
 bpf_dbg : LDLIBS = -lreadline
 bpf_dbg : bpf_dbg.o
 
-bpf_asm : CFLAGS = -Wall -O2 -I.
 bpf_asm : LDLIBS =
 bpf_asm : bpf_asm.o bpf_exp.yacc.o bpf_exp.lex.o
 bpf_exp.lex.o : bpf_exp.yacc.c
-- 
2.1.0


From 00e7c45712e9d826a2908cdfb4d15581f825e47d Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 11 Nov 2015 23:25:40 +0100
Subject: [PATCH 12/43] packet: do skb_probe_transport_header when we actually
 have data

[ Upstream commit efdfa2f7848f64517008136fb41f53c4a1faf93a ]

In tpacket_fill_skb() commit c1aad275b029 ("packet: set transport
header before doing xmit") and later on 40893fd0fd4e ("net: switch
to use skb_probe_transport_header()") was probing for a transport
header on the skb from a ring buffer slot, but at a time, where
the skb has _not even_ been filled with data yet. So that call into
the flow dissector is pretty useless. Lets do it after we've set
up the skb frags.

Fixes: c1aad275b029 ("packet: set transport header before doing xmit")
Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 27b2898..be038c9 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2368,8 +2368,6 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 	skb_reserve(skb, hlen);
 	skb_reset_network_header(skb);
 
-	if (!packet_use_direct_xmit(po))
-		skb_probe_transport_header(skb, 0);
 	if (unlikely(po->tp_tx_has_off)) {
 		int off_min, off_max, off;
 		off_min = po->tp_hdrlen - sizeof(struct sockaddr_ll);
@@ -2449,6 +2447,9 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 		len = ((to_write > len_max) ? len_max : to_write);
 	}
 
+	if (!packet_use_direct_xmit(po))
+		skb_probe_transport_header(skb, 0);
+
 	return tp_len;
 }
 
-- 
2.1.0


From 995afa88f27c706e0daf329f6fb07398414f2334 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 11 Nov 2015 23:25:41 +0100
Subject: [PATCH 13/43] packet: always probe for transport header

[ Upstream commit 8fd6c80d9dd938ca338c70698533a7e304752846 ]

We concluded that the skb_probe_transport_header() should better be
called unconditionally. Avoiding the call into the flow dissector has
also not really much to do with the direct xmit mode.

While it seems that only virtio_net code makes use of GSO from non
RX/TX ring packet socket paths, we should probe for a transport header
nevertheless before they hit devices.

Reference: http://thread.gmane.org/gmane.linux.network/386173/
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index be038c9..3059f51 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2447,8 +2447,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 		len = ((to_write > len_max) ? len_max : to_write);
 	}
 
-	if (!packet_use_direct_xmit(po))
-		skb_probe_transport_header(skb, 0);
+	skb_probe_transport_header(skb, 0);
 
 	return tp_len;
 }
@@ -2800,8 +2799,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		len += vnet_hdr_len;
 	}
 
-	if (!packet_use_direct_xmit(po))
-		skb_probe_transport_header(skb, reserve);
+	skb_probe_transport_header(skb, reserve);
+
 	if (unlikely(extra_len == 4))
 		skb->no_fcs = 1;
 
-- 
2.1.0


From 85df0fab1bfabd5a88b9d53a09d34df51672282a Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 11 Nov 2015 23:25:42 +0100
Subject: [PATCH 14/43] packet: only allow extra vlan len on ethernet devices

[ Upstream commit 3c70c132488794e2489ab045559b0ce0afcf17de ]

Packet sockets can be used by various net devices and are not
really restricted to ARPHRD_ETHER device types. However, when
currently checking for the extra 4 bytes that can be transmitted
in VLAN case, our assumption is that we generally probe on
ARPHRD_ETHER devices. Therefore, before looking into Ethernet
header, check the device type first.

This also fixes the issue where non-ARPHRD_ETHER devices could
have no dev->hard_header_len in TX_RING SOCK_RAW case, and thus
the check would test unfilled linear part of the skb (instead
of non-linear).

Fixes: 57f89bfa2140 ("network: Allow af_packet to transmit +4 bytes for VLAN packets.")
Fixes: 52f1454f629f ("packet: allow to transmit +4 byte in TX_RING slot for VLAN case")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 60 +++++++++++++++++++++-----------------------------
 1 file changed, 25 insertions(+), 35 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 3059f51..6e3cd2f 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1741,6 +1741,20 @@ static void fanout_release(struct sock *sk)
 		kfree_rcu(po->rollover, rcu);
 }
 
+static bool packet_extra_vlan_len_allowed(const struct net_device *dev,
+					  struct sk_buff *skb)
+{
+	/* Earlier code assumed this would be a VLAN pkt, double-check
+	 * this now that we have the actual packet in hand. We can only
+	 * do this check on Ethernet devices.
+	 */
+	if (unlikely(dev->type != ARPHRD_ETHER))
+		return false;
+
+	skb_reset_mac_header(skb);
+	return likely(eth_hdr(skb)->h_proto == htons(ETH_P_8021Q));
+}
+
 static const struct proto_ops packet_ops;
 
 static const struct proto_ops packet_ops_spkt;
@@ -1902,18 +1916,10 @@ retry:
 		goto retry;
 	}
 
-	if (len > (dev->mtu + dev->hard_header_len + extra_len)) {
-		/* Earlier code assumed this would be a VLAN pkt,
-		 * double-check this now that we have the actual
-		 * packet in hand.
-		 */
-		struct ethhdr *ehdr;
-		skb_reset_mac_header(skb);
-		ehdr = eth_hdr(skb);
-		if (ehdr->h_proto != htons(ETH_P_8021Q)) {
-			err = -EMSGSIZE;
-			goto out_unlock;
-		}
+	if (len > (dev->mtu + dev->hard_header_len + extra_len) &&
+	    !packet_extra_vlan_len_allowed(dev, skb)) {
+		err = -EMSGSIZE;
+		goto out_unlock;
 	}
 
 	skb->protocol = proto;
@@ -2525,18 +2531,10 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 		tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto,
 					  addr, hlen);
 		if (likely(tp_len >= 0) &&
-		    tp_len > dev->mtu + dev->hard_header_len) {
-			struct ethhdr *ehdr;
-			/* Earlier code assumed this would be a VLAN pkt,
-			 * double-check this now that we have the actual
-			 * packet in hand.
-			 */
+		    tp_len > dev->mtu + dev->hard_header_len &&
+		    !packet_extra_vlan_len_allowed(dev, skb))
+			tp_len = -EMSGSIZE;
 
-			skb_reset_mac_header(skb);
-			ehdr = eth_hdr(skb);
-			if (ehdr->h_proto != htons(ETH_P_8021Q))
-				tp_len = -EMSGSIZE;
-		}
 		if (unlikely(tp_len < 0)) {
 			if (po->tp_loss) {
 				__packet_set_status(po, ph,
@@ -2757,18 +2755,10 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 
 	sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags);
 
-	if (!gso_type && (len > dev->mtu + reserve + extra_len)) {
-		/* Earlier code assumed this would be a VLAN pkt,
-		 * double-check this now that we have the actual
-		 * packet in hand.
-		 */
-		struct ethhdr *ehdr;
-		skb_reset_mac_header(skb);
-		ehdr = eth_hdr(skb);
-		if (ehdr->h_proto != htons(ETH_P_8021Q)) {
-			err = -EMSGSIZE;
-			goto out_free;
-		}
+	if (!gso_type && (len > dev->mtu + reserve + extra_len) &&
+	    !packet_extra_vlan_len_allowed(dev, skb)) {
+		err = -EMSGSIZE;
+		goto out_free;
 	}
 
 	skb->protocol = proto;
-- 
2.1.0


From 3862137bdee867b99ade815a3c4d966ab223ac6d Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 11 Nov 2015 23:25:43 +0100
Subject: [PATCH 15/43] packet: infer protocol from ethernet header if unset

[ Upstream commit c72219b75fde768efccf7666342282fab7f9e4e7 ]

In case no struct sockaddr_ll has been passed to packet
socket's sendmsg() when doing a TX_RING flush run, then
skb->protocol is set to po->num instead, which is the protocol
passed via socket(2)/bind(2).

Applications only xmitting can go the path of allocating the
socket as socket(PF_PACKET, <mode>, 0) and do a bind(2) on the
TX_RING with sll_protocol of 0. That way, register_prot_hook()
is neither called on creation nor on bind time, which saves
cycles when there's no interest in capturing anyway.

That leaves us however with po->num 0 instead and therefore
the TX_RING flush run sets skb->protocol to 0 as well. Eric
reported that this leads to problems when using tools like
trafgen over bonding device. I.e. the bonding's hash function
could invoke the kernel's flow dissector, which depends on
skb->protocol being properly set. In the current situation, all
the traffic is then directed to a single slave.

Fix it up by inferring skb->protocol from the Ethernet header
when not set and we have ARPHRD_ETHER device type. This is only
done in case of SOCK_RAW and where we have a dev->hard_header_len
length. In case of ARPHRD_ETHER devices, this is guaranteed to
cover ETH_HLEN, and therefore being accessed on the skb after
the skb_store_bits().

Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 6e3cd2f..45d4196 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2338,6 +2338,15 @@ static bool ll_header_truncated(const struct net_device *dev, int len)
 	return false;
 }
 
+static void tpacket_set_protocol(const struct net_device *dev,
+				 struct sk_buff *skb)
+{
+	if (dev->type == ARPHRD_ETHER) {
+		skb_reset_mac_header(skb);
+		skb->protocol = eth_hdr(skb)->h_proto;
+	}
+}
+
 static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 		void *frame, struct net_device *dev, int size_max,
 		__be16 proto, unsigned char *addr, int hlen)
@@ -2419,6 +2428,8 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 				dev->hard_header_len);
 		if (unlikely(err))
 			return err;
+		if (!skb->protocol)
+			tpacket_set_protocol(dev, skb);
 
 		data += dev->hard_header_len;
 		to_write -= dev->hard_header_len;
-- 
2.1.0


From c5cde0ccf91927c87fd06b86d39d580a9244fb57 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 11 Nov 2015 23:25:44 +0100
Subject: [PATCH 16/43] packet: fix tpacket_snd max frame len

[ Upstream commit 5cfb4c8d05b4409c4044cb9c05b19705c1d9818b ]

Since it's introduction in commit 69e3c75f4d54 ("net: TX_RING and
packet mmap"), TX_RING could be used from SOCK_DGRAM and SOCK_RAW
side. When used with SOCK_DGRAM only, the size_max > dev->mtu +
reserve check should have reserve as 0, but currently, this is
unconditionally set (in it's original form as dev->hard_header_len).

I think this is not correct since tpacket_fill_skb() would then
take dev->mtu and dev->hard_header_len into account for SOCK_DGRAM,
the extra VLAN_HLEN could be possible in both cases. Presumably, the
reserve code was copied from packet_snd(), but later on missed the
check. Make it similar as we have it in packet_snd().

Fixes: 69e3c75f4d54 ("net: TX_RING and packet mmap")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 45d4196..4695a36 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2510,12 +2510,13 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 	if (unlikely(!(dev->flags & IFF_UP)))
 		goto out_put;
 
-	reserve = dev->hard_header_len + VLAN_HLEN;
+	if (po->sk.sk_socket->type == SOCK_RAW)
+		reserve = dev->hard_header_len;
 	size_max = po->tx_ring.frame_size
 		- (po->tp_hdrlen - sizeof(struct sockaddr_ll));
 
-	if (size_max > dev->mtu + reserve)
-		size_max = dev->mtu + reserve;
+	if (size_max > dev->mtu + reserve + VLAN_HLEN)
+		size_max = dev->mtu + reserve + VLAN_HLEN;
 
 	do {
 		ph = packet_current_frame(po, &po->tx_ring,
@@ -2542,7 +2543,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 		tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto,
 					  addr, hlen);
 		if (likely(tp_len >= 0) &&
-		    tp_len > dev->mtu + dev->hard_header_len &&
+		    tp_len > dev->mtu + reserve &&
 		    !packet_extra_vlan_len_allowed(dev, skb))
 			tp_len = -EMSGSIZE;
 
-- 
2.1.0


From 93d8395a99eefdd3b470cf9c04e947c6cb8bb85a Mon Sep 17 00:00:00 2001
From: lucien <lucien.xin@gmail.com>
Date: Thu, 12 Nov 2015 13:07:07 +0800
Subject: [PATCH 17/43] sctp: translate host order to network order when
 setting a hmacid

[ Upstream commit ed5a377d87dc4c87fb3e1f7f698cba38cd893103 ]

now sctp auth cannot work well when setting a hmacid manually, which
is caused by that we didn't use the network order for hmacid, so fix
it by adding the transformation in sctp_auth_ep_set_hmacs.

even we set hmacid with the network order in userspace, it still
can't work, because of this condition in sctp_auth_ep_set_hmacs():

		if (id > SCTP_AUTH_HMAC_ID_MAX)
			return -EOPNOTSUPP;

so this wasn't working before and thus it won't break compatibility.

Fixes: 65b07e5d0d09 ("[SCTP]: API updates to suport SCTP-AUTH extensions.")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/auth.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sctp/auth.c b/net/sctp/auth.c
index 4f15b7d..1543e39 100644
--- a/net/sctp/auth.c
+++ b/net/sctp/auth.c
@@ -809,8 +809,8 @@ int sctp_auth_ep_set_hmacs(struct sctp_endpoint *ep,
 	if (!has_sha1)
 		return -EINVAL;
 
-	memcpy(ep->auth_hmacs_list->hmac_ids, &hmacs->shmac_idents[0],
-		hmacs->shmac_num_idents * sizeof(__u16));
+	for (i = 0; i < hmacs->shmac_num_idents; i++)
+		ep->auth_hmacs_list->hmac_ids[i] = htons(hmacs->shmac_idents[i]);
 	ep->auth_hmacs_list->param_hdr.length = htons(sizeof(sctp_paramhdr_t) +
 				hmacs->shmac_num_idents * sizeof(__u16));
 	return 0;
-- 
2.1.0


From d53e3dbdedfaa2e1e0fd8b37a5e34b0df8a295c5 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Thu, 12 Nov 2015 19:35:26 +0200
Subject: [PATCH 18/43] net/mlx5e: Added self loopback prevention

[ Upstream commit 66189961e986e53ae39822898fc2ce88f44c61bb ]

Prevent outgoing multicast frames from looping back to the RX queue.

By introducing new HW capability self_lb_en_modifiable, which indicates
the support to modify self_lb_en bit in modify_tir command.

When this capability is set we can prevent TIRs from sending back
loopback multicast traffic to their own RQs, by "refreshing TIRs" with
modify_tir command, on every time new channels (SQs/RQs) are created at
device open.
This is needed since TIRs are static and only allocated once on driver
load, and the loopback decision is under their responsibility.

Fixes issues of the kind:
"IPv6: eth2: IPv6 duplicate address fe80::e61d:2dff:fe5c:f2e9 detected!"
The issue is seen since the IPv6 solicitations multicast messages are
loopedback and the network stack thinks they are coming from another host.

Fixes: 5c50368f3831 ("net/mlx5e: Light-weight netdev open/stop")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 56 ++++++++++++++++++++++-
 include/linux/mlx5/mlx5_ifc.h                     | 24 ++++++----
 2 files changed, 68 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 59874d6..443632d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1332,6 +1332,42 @@ static int mlx5e_modify_tir_lro(struct mlx5e_priv *priv, int tt)
 	return err;
 }
 
+static int mlx5e_refresh_tir_self_loopback_enable(struct mlx5_core_dev *mdev,
+						  u32 tirn)
+{
+	void *in;
+	int inlen;
+	int err;
+
+	inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
+	in = mlx5_vzalloc(inlen);
+	if (!in)
+		return -ENOMEM;
+
+	MLX5_SET(modify_tir_in, in, bitmask.self_lb_en, 1);
+
+	err = mlx5_core_modify_tir(mdev, tirn, in, inlen);
+
+	kvfree(in);
+
+	return err;
+}
+
+static int mlx5e_refresh_tirs_self_loopback_enable(struct mlx5e_priv *priv)
+{
+	int err;
+	int i;
+
+	for (i = 0; i < MLX5E_NUM_TT; i++) {
+		err = mlx5e_refresh_tir_self_loopback_enable(priv->mdev,
+							     priv->tirn[i]);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 static int mlx5e_set_dev_port_mtu(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -1367,13 +1403,20 @@ int mlx5e_open_locked(struct net_device *netdev)
 
 	err = mlx5e_set_dev_port_mtu(netdev);
 	if (err)
-		return err;
+		goto err_clear_state_opened_flag;
 
 	err = mlx5e_open_channels(priv);
 	if (err) {
 		netdev_err(netdev, "%s: mlx5e_open_channels failed, %d\n",
 			   __func__, err);
-		return err;
+		goto err_clear_state_opened_flag;
+	}
+
+	err = mlx5e_refresh_tirs_self_loopback_enable(priv);
+	if (err) {
+		netdev_err(netdev, "%s: mlx5e_refresh_tirs_self_loopback_enable failed, %d\n",
+			   __func__, err);
+		goto err_close_channels;
 	}
 
 	mlx5e_update_carrier(priv);
@@ -1382,6 +1425,12 @@ int mlx5e_open_locked(struct net_device *netdev)
 	schedule_delayed_work(&priv->update_stats_work, 0);
 
 	return 0;
+
+err_close_channels:
+	mlx5e_close_channels(priv);
+err_clear_state_opened_flag:
+	clear_bit(MLX5E_STATE_OPENED, &priv->state);
+	return err;
 }
 
 static int mlx5e_open(struct net_device *netdev)
@@ -1899,6 +1948,9 @@ static int mlx5e_check_required_hca_cap(struct mlx5_core_dev *mdev)
 			       "Not creating net device, some required device capabilities are missing\n");
 		return -ENOTSUPP;
 	}
+	if (!MLX5_CAP_ETH(mdev, self_lb_en_modifiable))
+		mlx5_core_warn(mdev, "Self loop back prevention is not supported\n");
+
 	return 0;
 }
 
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index dd20974..1565324 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -453,26 +453,28 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits {
 	u8         lro_cap[0x1];
 	u8         lro_psh_flag[0x1];
 	u8         lro_time_stamp[0x1];
-	u8         reserved_0[0x6];
+	u8         reserved_0[0x3];
+	u8         self_lb_en_modifiable[0x1];
+	u8         reserved_1[0x2];
 	u8         max_lso_cap[0x5];
-	u8         reserved_1[0x4];
+	u8         reserved_2[0x4];
 	u8         rss_ind_tbl_cap[0x4];
-	u8         reserved_2[0x3];
+	u8         reserved_3[0x3];
 	u8         tunnel_lso_const_out_ip_id[0x1];
-	u8         reserved_3[0x2];
+	u8         reserved_4[0x2];
 	u8         tunnel_statless_gre[0x1];
 	u8         tunnel_stateless_vxlan[0x1];
 
-	u8         reserved_4[0x20];
+	u8         reserved_5[0x20];
 
-	u8         reserved_5[0x10];
+	u8         reserved_6[0x10];
 	u8         lro_min_mss_size[0x10];
 
-	u8         reserved_6[0x120];
+	u8         reserved_7[0x120];
 
 	u8         lro_timer_supported_periods[4][0x20];
 
-	u8         reserved_7[0x600];
+	u8         reserved_8[0x600];
 };
 
 struct mlx5_ifc_roce_cap_bits {
@@ -4051,9 +4053,11 @@ struct mlx5_ifc_modify_tis_in_bits {
 };
 
 struct mlx5_ifc_modify_tir_bitmask_bits {
-	u8	   reserved[0x20];
+	u8	   reserved_0[0x20];
 
-	u8         reserved1[0x1f];
+	u8         reserved_1[0x1b];
+	u8         self_lb_en[0x1];
+	u8         reserved_2[0x3];
 	u8         lro[0x1];
 };
 
-- 
2.1.0


From 752f833f18bc5af0d0f5172cbeb554cf9b836311 Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Thu, 12 Nov 2015 19:35:29 +0200
Subject: [PATCH 19/43] net/mlx4_core: Fix sleeping while holding spinlock at
 rem_slave_counters

[ Upstream commit f5adbfee72282bb1f456d52b04adacd4fe6ac502 ]

When cleaning slave's counter resources, we hold a spinlock that
protects the slave's counters list. As part of the clean, we call
__mlx4_clear_if_stat which calls mlx4_alloc_cmd_mailbox which is a
sleepable function.

In order to fix this issue, hold the spinlock, and copy all counter
indices into a temporary array, and release the spinlock. Afterwards,
iterate over this array and free every counter. Repeat this scenario
until the original list is empty (a new counter might have been added
while releasing the counters from the temporary array).

Fixes: b72ca7e96acf ("net/mlx4_core: Reset counters data when freed")
Reported-by: Moni Shoua <monis@mellanox.com>
Tested-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlx4/resource_tracker.c  | 39 +++++++++++++++-------
 1 file changed, 27 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 731423c..8bead97 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -4934,26 +4934,41 @@ static void rem_slave_counters(struct mlx4_dev *dev, int slave)
 	struct res_counter *counter;
 	struct res_counter *tmp;
 	int err;
-	int index;
+	int *counters_arr = NULL;
+	int i, j;
 
 	err = move_all_busy(dev, slave, RES_COUNTER);
 	if (err)
 		mlx4_warn(dev, "rem_slave_counters: Could not move all counters - too busy for slave %d\n",
 			  slave);
 
-	spin_lock_irq(mlx4_tlock(dev));
-	list_for_each_entry_safe(counter, tmp, counter_list, com.list) {
-		if (counter->com.owner == slave) {
-			index = counter->com.res_id;
-			rb_erase(&counter->com.node,
-				 &tracker->res_tree[RES_COUNTER]);
-			list_del(&counter->com.list);
-			kfree(counter);
-			__mlx4_counter_free(dev, index);
+	counters_arr = kmalloc_array(dev->caps.max_counters,
+				     sizeof(*counters_arr), GFP_KERNEL);
+	if (!counters_arr)
+		return;
+
+	do {
+		i = 0;
+		j = 0;
+		spin_lock_irq(mlx4_tlock(dev));
+		list_for_each_entry_safe(counter, tmp, counter_list, com.list) {
+			if (counter->com.owner == slave) {
+				counters_arr[i++] = counter->com.res_id;
+				rb_erase(&counter->com.node,
+					 &tracker->res_tree[RES_COUNTER]);
+				list_del(&counter->com.list);
+				kfree(counter);
+			}
+		}
+		spin_unlock_irq(mlx4_tlock(dev));
+
+		while (j < i) {
+			__mlx4_counter_free(dev, counters_arr[j++]);
 			mlx4_release_resource(dev, slave, RES_COUNTER, 1, 0);
 		}
-	}
-	spin_unlock_irq(mlx4_tlock(dev));
+	} while (i);
+
+	kfree(counters_arr);
 }
 
 static void rem_slave_xrcdns(struct mlx4_dev *dev, int slave)
-- 
2.1.0


From 30de3861d01de70551c41529a9933cc2d3221c7b Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Thu, 12 Nov 2015 17:35:58 +0100
Subject: [PATCH 20/43] ip_tunnel: disable preemption when updating per-cpu
 tstats

[ Upstream commit b4fe85f9c9146f60457e9512fb6055e69e6a7a65 ]

Drivers like vxlan use the recently introduced
udp_tunnel_xmit_skb/udp_tunnel6_xmit_skb APIs. udp_tunnel6_xmit_skb
makes use of ip6tunnel_xmit, and ip6tunnel_xmit, after sending the
packet, updates the struct stats using the usual
u64_stats_update_begin/end calls on this_cpu_ptr(dev->tstats).
udp_tunnel_xmit_skb makes use of iptunnel_xmit, which doesn't touch
tstats, so drivers like vxlan, immediately after, call
iptunnel_xmit_stats, which does the same thing - calls
u64_stats_update_begin/end on this_cpu_ptr(dev->tstats).

While vxlan is probably fine (I don't know?), calling a similar function
from, say, an unbound workqueue, on a fully preemptable kernel causes
real issues:

[  188.434537] BUG: using smp_processor_id() in preemptible [00000000] code: kworker/u8:0/6
[  188.435579] caller is debug_smp_processor_id+0x17/0x20
[  188.435583] CPU: 0 PID: 6 Comm: kworker/u8:0 Not tainted 4.2.6 #2
[  188.435607] Call Trace:
[  188.435611]  [<ffffffff8234e936>] dump_stack+0x4f/0x7b
[  188.435615]  [<ffffffff81915f3d>] check_preemption_disabled+0x19d/0x1c0
[  188.435619]  [<ffffffff81915f77>] debug_smp_processor_id+0x17/0x20

The solution would be to protect the whole
this_cpu_ptr(dev->tstats)/u64_stats_update_begin/end blocks with
disabling preemption and then reenabling it.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_tunnel.h | 3 ++-
 include/net/ip_tunnels.h | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index fa915fa..d49a8f8 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -90,11 +90,12 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb,
 	err = ip6_local_out_sk(sk, skb);
 
 	if (net_xmit_eval(err) == 0) {
-		struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
+		struct pcpu_sw_netstats *tstats = get_cpu_ptr(dev->tstats);
 		u64_stats_update_begin(&tstats->syncp);
 		tstats->tx_bytes += pkt_len;
 		tstats->tx_packets++;
 		u64_stats_update_end(&tstats->syncp);
+		put_cpu_ptr(tstats);
 	} else {
 		stats->tx_errors++;
 		stats->tx_aborted_errors++;
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index f6dafec..62a750a 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -287,12 +287,13 @@ static inline void iptunnel_xmit_stats(int err,
 				       struct pcpu_sw_netstats __percpu *stats)
 {
 	if (err > 0) {
-		struct pcpu_sw_netstats *tstats = this_cpu_ptr(stats);
+		struct pcpu_sw_netstats *tstats = get_cpu_ptr(stats);
 
 		u64_stats_update_begin(&tstats->syncp);
 		tstats->tx_bytes += err;
 		tstats->tx_packets++;
 		u64_stats_update_end(&tstats->syncp);
+		put_cpu_ptr(tstats);
 	} else if (err < 0) {
 		err_stats->tx_errors++;
 		err_stats->tx_aborted_errors++;
-- 
2.1.0


From b532a633740a46806a53d618634ff1169c5e9a4b Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dragos@endocode.com>
Date: Mon, 16 Nov 2015 10:52:48 +0100
Subject: [PATCH 21/43] net: switchdev: fix return code of fdb_dump stub

[ Upstream commit 24cb7055a3066634a0f3fa0cd6a4780652905d35 ]

rtnl_fdb_dump always expects an index to be returned by the ndo_fdb_dump op,
but when CONFIG_NET_SWITCHDEV is off, it returns an error.

Fix that by returning the given unmodified idx.

A similar fix was 0890cf6cb6ab ("switchdev: fix return value of
switchdev_port_fdb_dump in case of error") but for the CONFIG_NET_SWITCHDEV=y
case.

Fixes: 45d4122ca7cd ("switchdev: add support for fdb add/del/dump via switchdev_port_obj ops.")
Signed-off-by: Dragos Tatulea <dragos@endocode.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/switchdev.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index 319baab..731c40e 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -272,7 +272,7 @@ static inline int switchdev_port_fdb_dump(struct sk_buff *skb,
 					  struct net_device *filter_dev,
 					  int idx)
 {
-	return -EOPNOTSUPP;
+       return idx;
 }
 
 static inline void switchdev_port_fwd_mark_set(struct net_device *dev,
-- 
2.1.0


From 06416634e5b57f33854a5905bdf87ddc68f99ff4 Mon Sep 17 00:00:00 2001
From: Pavel Fedin <p.fedin@samsung.com>
Date: Mon, 16 Nov 2015 17:51:34 +0300
Subject: [PATCH 22/43] net: thunder: Check for driver data in nicvf_remove()

[ Upstream commit 7750130d93decff06120df0d8ea024ff8a038a21 ]

In some cases the crash is caused by nicvf_remove() being called from
outside. For example, if we try to feed the device to vfio after the
probe has failed for some reason. So, move the check to better place.

Signed-off-by: Pavel Fedin <p.fedin@samsung.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/thunder/nicvf_main.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index a937772..7f709cb 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -1583,8 +1583,14 @@ err_disable_device:
 static void nicvf_remove(struct pci_dev *pdev)
 {
 	struct net_device *netdev = pci_get_drvdata(pdev);
-	struct nicvf *nic = netdev_priv(netdev);
-	struct net_device *pnetdev = nic->pnicvf->netdev;
+	struct nicvf *nic;
+	struct net_device *pnetdev;
+
+	if (!netdev)
+		return;
+
+	nic = netdev_priv(netdev);
+	pnetdev = nic->pnicvf->netdev;
 
 	/* Check if this Qset is assigned to different VF.
 	 * If yes, clean primary and all secondary Qsets.
-- 
2.1.0


From fba5174af82c781b154aa5ffcc0fad2229767ec5 Mon Sep 17 00:00:00 2001
From: Neil Horman <nhorman@tuxdriver.com>
Date: Mon, 16 Nov 2015 13:09:10 -0500
Subject: [PATCH 23/43] snmp: Remove duplicate OUTMCAST stat increment

[ Upstream commit 41033f029e393a64e81966cbe34d66c6cf8a2e7e ]

the OUTMCAST stat is double incremented, getting bumped once in the mcast code
itself, and again in the common ip output path.  Remove the mcast bump, as its
not needed

Validated by the reporter, with good results

Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Reported-by: Claus Jensen <claus.jensen@microsemi.com>
CC: Claus Jensen <claus.jensen@microsemi.com>
CC: David Miller <davem@davemloft.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/mcast.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 083b292..41e3b5e 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1651,7 +1651,6 @@ out:
 	if (!err) {
 		ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT);
 		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
-		IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, payload_len);
 	} else {
 		IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
 	}
@@ -2014,7 +2013,6 @@ out:
 	if (!err) {
 		ICMP6MSGOUT_INC_STATS(net, idev, type);
 		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
-		IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, full_len);
 	} else
 		IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
 
-- 
2.1.0


From 677298fd534e16274c8859e7658e57864bddb2a9 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 18 Nov 2015 16:40:19 +0100
Subject: [PATCH 24/43] net/ip6_tunnel: fix dst leak

[ Upstream commit 206b49500df558dbc15d8836b09f6397ec5ed8bb ]

the commit cdf3464e6c6b ("ipv6: Fix dst_entry refcnt bugs in ip6_tunnel")
introduced percpu storage for ip6_tunnel dst cache, but while clearing
such cache it used raw_cpu_ptr to walk the per cpu entries, so cached
dst on non current cpu are not actually reset.

This patch replaces raw_cpu_ptr with per_cpu_ptr, properly cleaning
such storage.

Fixes: cdf3464e6c6b ("ipv6: Fix dst_entry refcnt bugs in ip6_tunnel")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index eabffbb..137fca4 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -177,7 +177,7 @@ void ip6_tnl_dst_reset(struct ip6_tnl *t)
 	int i;
 
 	for_each_possible_cpu(i)
-		ip6_tnl_per_cpu_dst_set(raw_cpu_ptr(t->dst_cache), NULL);
+		ip6_tnl_per_cpu_dst_set(per_cpu_ptr(t->dst_cache, i), NULL);
 }
 EXPORT_SYMBOL_GPL(ip6_tnl_dst_reset);
 
-- 
2.1.0


From 1451e186dddbd12331cbbd82cd1ec4df6207d598 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Wed, 18 Nov 2015 21:13:07 +0100
Subject: [PATCH 25/43] net: qmi_wwan: add XS Stick W100-2 from 4G Systems
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 68242a5a1e2edce39b069385cbafb82304eac0f1 ]

Thomas reports
"
4gsystems sells two total different LTE-surfsticks under the same name.
..
The newer version of XS Stick W100 is from "omega"
..
Under windows the driver switches to the same ID, and uses MI03\6 for
network and MI01\6 for modem.
..
echo "1c9e 9b01" > /sys/bus/usb/drivers/qmi_wwan/new_id
echo "1c9e 9b01" > /sys/bus/usb-serial/drivers/option1/new_id

T:  Bus=01 Lev=01 Prnt=01 Port=03 Cnt=01 Dev#=  4 Spd=480 MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1c9e ProdID=9b01 Rev=02.32
S:  Manufacturer=USB Modem
S:  Product=USB Modem
S:  SerialNumber=
C:  #Ifs= 5 Cfg#= 1 Atr=80 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
I:  If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
I:  If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
I:  If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
I:  If#= 4 Alt= 0 #EPs= 2 Cls=08(stor.) Sub=06 Prot=50 Driver=usb-storage

Now all important things are there:

wwp0s29f7u2i3 (net), ttyUSB2 (at), cdc-wdm0 (qmi), ttyUSB1 (at)

There is also ttyUSB0, but it is not usable, at least not for at.

The device works well with qmi and ModemManager-NetworkManager.
"

Reported-by: Thomas Schäfer <tschaefer@t-online.de>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 2a7c1be..66e0853 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -775,6 +775,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x2357, 0x9000, 4)},	/* TP-LINK MA260 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)},	/* Telit LE920 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1201, 2)},	/* Telit LE920 */
+	{QMI_FIXED_INTF(0x1c9e, 0x9b01, 3)},	/* XS Stick W100-2 from 4G Systems */
 	{QMI_FIXED_INTF(0x0b3c, 0xc000, 4)},	/* Olivetti Olicard 100 */
 	{QMI_FIXED_INTF(0x0b3c, 0xc001, 4)},	/* Olivetti Olicard 120 */
 	{QMI_FIXED_INTF(0x0b3c, 0xc002, 4)},	/* Olivetti Olicard 140 */
-- 
2.1.0


From c137397256ef9502cfba4de0fa77f850ed0ad7a6 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 18 Nov 2015 12:40:13 -0800
Subject: [PATCH 26/43] tcp: md5: fix lockdep annotation

[ Upstream commit 1b8e6a01e19f001e9f93b39c32387961c91ed3cc ]

When a passive TCP is created, we eventually call tcp_md5_do_add()
with sk pointing to the child. It is not owner by the user yet (we
will add this socket into listener accept queue a bit later anyway)

But we do own the spinlock, so amend the lockdep annotation to avoid
following splat :

[ 8451.090932] net/ipv4/tcp_ipv4.c:923 suspicious rcu_dereference_protected() usage!
[ 8451.090932]
[ 8451.090932] other info that might help us debug this:
[ 8451.090932]
[ 8451.090934]
[ 8451.090934] rcu_scheduler_active = 1, debug_locks = 1
[ 8451.090936] 3 locks held by socket_sockopt_/214795:
[ 8451.090936]  #0:  (rcu_read_lock){.+.+..}, at: [<ffffffff855c6ac1>] __netif_receive_skb_core+0x151/0xe90
[ 8451.090947]  #1:  (rcu_read_lock){.+.+..}, at: [<ffffffff85618143>] ip_local_deliver_finish+0x43/0x2b0
[ 8451.090952]  #2:  (slock-AF_INET){+.-...}, at: [<ffffffff855acda5>] sk_clone_lock+0x1c5/0x500
[ 8451.090958]
[ 8451.090958] stack backtrace:
[ 8451.090960] CPU: 7 PID: 214795 Comm: socket_sockopt_

[ 8451.091215] Call Trace:
[ 8451.091216]  <IRQ>  [<ffffffff856fb29c>] dump_stack+0x55/0x76
[ 8451.091229]  [<ffffffff85123b5b>] lockdep_rcu_suspicious+0xeb/0x110
[ 8451.091235]  [<ffffffff8564544f>] tcp_md5_do_add+0x1bf/0x1e0
[ 8451.091239]  [<ffffffff85645751>] tcp_v4_syn_recv_sock+0x1f1/0x4c0
[ 8451.091242]  [<ffffffff85642b27>] ? tcp_v4_md5_hash_skb+0x167/0x190
[ 8451.091246]  [<ffffffff85647c78>] tcp_check_req+0x3c8/0x500
[ 8451.091249]  [<ffffffff856451ae>] ? tcp_v4_inbound_md5_hash+0x11e/0x190
[ 8451.091253]  [<ffffffff85647170>] tcp_v4_rcv+0x3c0/0x9f0
[ 8451.091256]  [<ffffffff85618143>] ? ip_local_deliver_finish+0x43/0x2b0
[ 8451.091260]  [<ffffffff856181b6>] ip_local_deliver_finish+0xb6/0x2b0
[ 8451.091263]  [<ffffffff85618143>] ? ip_local_deliver_finish+0x43/0x2b0
[ 8451.091267]  [<ffffffff85618d38>] ip_local_deliver+0x48/0x80
[ 8451.091270]  [<ffffffff85618510>] ip_rcv_finish+0x160/0x700
[ 8451.091273]  [<ffffffff8561900e>] ip_rcv+0x29e/0x3d0
[ 8451.091277]  [<ffffffff855c74b7>] __netif_receive_skb_core+0xb47/0xe90

Fixes: a8afca0329988 ("tcp: md5: protects md5sig_info with RCU")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 93898e0..a7739c8 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -922,7 +922,8 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
 	}
 
 	md5sig = rcu_dereference_protected(tp->md5sig_info,
-					   sock_owned_by_user(sk));
+					   sock_owned_by_user(sk) ||
+					   lockdep_is_held(&sk->sk_lock.slock));
 	if (!md5sig) {
 		md5sig = kmalloc(sizeof(*md5sig), gfp);
 		if (!md5sig)
-- 
2.1.0


From 9a9201e594f1e328a927ea12f672a3541b03d797 Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Wed, 18 Nov 2015 18:17:30 -0800
Subject: [PATCH 27/43] tcp: disable Fast Open on timeouts after handshake

[ Upstream commit 0e45f4da5981895e885dd72fe912a3f8e32bae73 ]

Some middle-boxes black-hole the data after the Fast Open handshake
(https://www.ietf.org/proceedings/94/slides/slides-94-tcpm-13.pdf).
The exact reason is unknown. The work-around is to disable Fast Open
temporarily after multiple recurring timeouts with few or no data
delivered in the established state.

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Christoph Paasch <cpaasch@apple.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_timer.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 7149ebc..04f0a05 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -176,6 +176,18 @@ static int tcp_write_timeout(struct sock *sk)
 		syn_set = true;
 	} else {
 		if (retransmits_timed_out(sk, sysctl_tcp_retries1, 0, 0)) {
+			/* Some middle-boxes may black-hole Fast Open _after_
+			 * the handshake. Therefore we conservatively disable
+			 * Fast Open on this path on recurring timeouts with
+			 * few or zero bytes acked after Fast Open.
+			 */
+			if (tp->syn_data_acked &&
+			    tp->bytes_acked <= tp->rx_opt.mss_clamp) {
+				tcp_fastopen_cache_set(sk, 0, NULL, true, 0);
+				if (icsk->icsk_retransmits == sysctl_tcp_retries1)
+					NET_INC_STATS_BH(sock_net(sk),
+							 LINUX_MIB_TCPFASTOPENACTIVEFAIL);
+			}
 			/* Black hole detection */
 			tcp_mtu_probing(icsk, sk);
 
-- 
2.1.0


From fc6c61249dd9e249b96291b83c0751b441cda8de Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 18 Nov 2015 21:03:33 -0800
Subject: [PATCH 28/43] tcp: fix potential huge kmalloc() calls in TCP_REPAIR

[ Upstream commit 5d4c9bfbabdb1d497f21afd81501e5c54b0c85d9 ]

tcp_send_rcvq() is used for re-injecting data into tcp receive queue.

Problems :

- No check against size is performed, allowed user to fool kernel in
  attempting very large memory allocations, eventually triggering
  OOM when memory is fragmented.

- In case of fault during the copy we do not return correct errno.

Lets use alloc_skb_with_frags() to cook optimal skbs.

Fixes: 292e8d8c8538 ("tcp: Move rcvq sending to tcp_input.c")
Fixes: c0e88ff0f256 ("tcp: Repair socket queues")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 22 +++++++++++++++++++---
 1 file changed, 19 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a8f515b..cc6bd43 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4457,19 +4457,34 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int
 int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
 {
 	struct sk_buff *skb;
+	int err = -ENOMEM;
+	int data_len = 0;
 	bool fragstolen;
 
 	if (size == 0)
 		return 0;
 
-	skb = alloc_skb(size, sk->sk_allocation);
+	if (size > PAGE_SIZE) {
+		int npages = min_t(size_t, size >> PAGE_SHIFT, MAX_SKB_FRAGS);
+
+		data_len = npages << PAGE_SHIFT;
+		size = data_len + (size & ~PAGE_MASK);
+	}
+	skb = alloc_skb_with_frags(size - data_len, data_len,
+				   PAGE_ALLOC_COSTLY_ORDER,
+				   &err, sk->sk_allocation);
 	if (!skb)
 		goto err;
 
+	skb_put(skb, size - data_len);
+	skb->data_len = data_len;
+	skb->len = size;
+
 	if (tcp_try_rmem_schedule(sk, skb, skb->truesize))
 		goto err_free;
 
-	if (memcpy_from_msg(skb_put(skb, size), msg, size))
+	err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size);
+	if (err)
 		goto err_free;
 
 	TCP_SKB_CB(skb)->seq = tcp_sk(sk)->rcv_nxt;
@@ -4485,7 +4500,8 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
 err_free:
 	kfree_skb(skb);
 err:
-	return -ENOMEM;
+	return err;
+
 }
 
 static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
-- 
2.1.0


From 419ee3eb1d6dea668f00ee440c670f8f479f8216 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 26 Nov 2015 08:18:14 -0800
Subject: [PATCH 29/43] tcp: initialize tp->copied_seq in case of cross SYN
 connection

[ Upstream commit 142a2e7ece8d8ac0e818eb2c91f99ca894730e2a ]

Dmitry provided a syzkaller (http://github.com/google/syzkaller)
generated program that triggers the WARNING at
net/ipv4/tcp.c:1729 in tcp_recvmsg() :

WARN_ON(tp->copied_seq != tp->rcv_nxt &&
        !(flags & (MSG_PEEK | MSG_TRUNC)));

His program is specifically attempting a Cross SYN TCP exchange,
that we support (for the pleasure of hackers ?), but it looks we
lack proper tcp->copied_seq initialization.

Thanks again Dmitry for your report and testings.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Tested-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index cc6bd43..0a2b61d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5659,6 +5659,7 @@ discard:
 		}
 
 		tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
+		tp->copied_seq = tp->rcv_nxt;
 		tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1;
 
 		/* RFC1323: The window in SYN & SYN/ACK segments is
-- 
2.1.0


From 4d8baf23458211113b2b4aaac26d715a1cfa9a4f Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 20 Nov 2015 00:11:56 +0100
Subject: [PATCH 30/43] net, scm: fix PaX detected msg_controllen overflow in
 scm_detach_fds

[ Upstream commit 6900317f5eff0a7070c5936e5383f589e0de7a09 ]

David and HacKurx reported a following/similar size overflow triggered
in a grsecurity kernel, thanks to PaX's gcc size overflow plugin:

(Already fixed in later grsecurity versions by Brad and PaX Team.)

[ 1002.296137] PAX: size overflow detected in function scm_detach_fds net/core/scm.c:314
               cicus.202_127 min, count: 4, decl: msg_controllen; num: 0; context: msghdr;
[ 1002.296145] CPU: 0 PID: 3685 Comm: scm_rights_recv Not tainted 4.2.3-grsec+ #7
[ 1002.296149] Hardware name: Apple Inc. MacBookAir5,1/Mac-66F35F19FE2A0D05, [...]
[ 1002.296153]  ffffffff81c27366 0000000000000000 ffffffff81c27375 ffffc90007843aa8
[ 1002.296162]  ffffffff818129ba 0000000000000000 ffffffff81c27366 ffffc90007843ad8
[ 1002.296169]  ffffffff8121f838 fffffffffffffffc fffffffffffffffc ffffc90007843e60
[ 1002.296176] Call Trace:
[ 1002.296190]  [<ffffffff818129ba>] dump_stack+0x45/0x57
[ 1002.296200]  [<ffffffff8121f838>] report_size_overflow+0x38/0x60
[ 1002.296209]  [<ffffffff816a979e>] scm_detach_fds+0x2ce/0x300
[ 1002.296220]  [<ffffffff81791899>] unix_stream_read_generic+0x609/0x930
[ 1002.296228]  [<ffffffff81791c9f>] unix_stream_recvmsg+0x4f/0x60
[ 1002.296236]  [<ffffffff8178dc00>] ? unix_set_peek_off+0x50/0x50
[ 1002.296243]  [<ffffffff8168fac7>] sock_recvmsg+0x47/0x60
[ 1002.296248]  [<ffffffff81691522>] ___sys_recvmsg+0xe2/0x1e0
[ 1002.296257]  [<ffffffff81693496>] __sys_recvmsg+0x46/0x80
[ 1002.296263]  [<ffffffff816934fc>] SyS_recvmsg+0x2c/0x40
[ 1002.296271]  [<ffffffff8181a3ab>] entry_SYSCALL_64_fastpath+0x12/0x85

Further investigation showed that this can happen when an *odd* number of
fds are being passed over AF_UNIX sockets.

In these cases CMSG_LEN(i * sizeof(int)) and CMSG_SPACE(i * sizeof(int)),
where i is the number of successfully passed fds, differ by 4 bytes due
to the extra CMSG_ALIGN() padding in CMSG_SPACE() to an 8 byte boundary
on 64 bit. The padding is used to align subsequent cmsg headers in the
control buffer.

When the control buffer passed in from the receiver side *lacks* these 4
bytes (e.g. due to buggy/wrong API usage), then msg->msg_controllen will
overflow in scm_detach_fds():

  int cmlen = CMSG_LEN(i * sizeof(int));  <--- cmlen w/o tail-padding
  err = put_user(SOL_SOCKET, &cm->cmsg_level);
  if (!err)
    err = put_user(SCM_RIGHTS, &cm->cmsg_type);
  if (!err)
    err = put_user(cmlen, &cm->cmsg_len);
  if (!err) {
    cmlen = CMSG_SPACE(i * sizeof(int));  <--- cmlen w/ 4 byte extra tail-padding
    msg->msg_control += cmlen;
    msg->msg_controllen -= cmlen;         <--- iff no tail-padding space here ...
  }                                            ... wrap-around

F.e. it will wrap to a length of 18446744073709551612 bytes in case the
receiver passed in msg->msg_controllen of 20 bytes, and the sender
properly transferred 1 fd to the receiver, so that its CMSG_LEN results
in 20 bytes and CMSG_SPACE in 24 bytes.

In case of MSG_CMSG_COMPAT (scm_detach_fds_compat()), I haven't seen an
issue in my tests as alignment seems always on 4 byte boundary. Same
should be in case of native 32 bit, where we end up with 4 byte boundaries
as well.

In practice, passing msg->msg_controllen of 20 to recvmsg() while receiving
a single fd would mean that on successful return, msg->msg_controllen is
being set by the kernel to 24 bytes instead, thus more than the input
buffer advertised. It could f.e. become an issue if such application later
on zeroes or copies the control buffer based on the returned msg->msg_controllen
elsewhere.

Maximum number of fds we can send is a hard upper limit SCM_MAX_FD (253).

Going over the code, it seems like msg->msg_controllen is not being read
after scm_detach_fds() in scm_recv() anymore by the kernel, good!

Relevant recvmsg() handler are unix_dgram_recvmsg() (unix_seqpacket_recvmsg())
and unix_stream_recvmsg(). Both return back to their recvmsg() caller,
and ___sys_recvmsg() places the updated length, that is, new msg_control -
old msg_control pointer into msg->msg_controllen (hence the 24 bytes seen
in the example).

Long time ago, Wei Yongjun fixed something related in commit 1ac70e7ad24a
("[NET]: Fix function put_cmsg() which may cause usr application memory
overflow").

RFC3542, section 20.2. says:

  The fields shown as "XX" are possible padding, between the cmsghdr
  structure and the data, and between the data and the next cmsghdr
  structure, if required by the implementation. While sending an
  application may or may not include padding at the end of last
  ancillary data in msg_controllen and implementations must accept both
  as valid. On receiving a portable application must provide space for
  padding at the end of the last ancillary data as implementations may
  copy out the padding at the end of the control message buffer and
  include it in the received msg_controllen. When recvmsg() is called
  if msg_controllen is too small for all the ancillary data items
  including any trailing padding after the last item an implementation
  may set MSG_CTRUNC.

Since we didn't place MSG_CTRUNC for already quite a long time, just do
the same as in 1ac70e7ad24a to avoid an overflow.

Btw, even man-page author got this wrong :/ See db939c9b26e9 ("cmsg.3: Fix
error in SCM_RIGHTS code sample"). Some people must have copied this (?),
thus it got triggered in the wild (reported several times during boot by
David and HacKurx).

No Fixes tag this time as pre 2002 (that is, pre history tree).

Reported-by: David Sterba <dave@jikos.cz>
Reported-by: HacKurx <hackurx@gmail.com>
Cc: PaX Team <pageexec@freemail.hu>
Cc: Emese Revfy <re.emese@gmail.com>
Cc: Brad Spengler <spender@grsecurity.net>
Cc: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Cc: Eric Dumazet <edumazet@google.com>
Reviewed-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/scm.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/core/scm.c b/net/core/scm.c
index 3b6899b..8a1741b 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -305,6 +305,8 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
 			err = put_user(cmlen, &cm->cmsg_len);
 		if (!err) {
 			cmlen = CMSG_SPACE(i*sizeof(int));
+			if (msg->msg_controllen < cmlen)
+				cmlen = msg->msg_controllen;
 			msg->msg_control += cmlen;
 			msg->msg_controllen -= cmlen;
 		}
-- 
2.1.0


From fd10116065e9a7bde6eb70f3f69c5e9ec2722e2e Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Fri, 20 Nov 2015 13:54:19 +0100
Subject: [PATCH 31/43] net: ipmr: fix static mfc/dev leaks on table
 destruction

[ Upstream commit 0e615e9601a15efeeb8942cf7cd4dadba0c8c5a7 ]

When destroying an mrt table the static mfc entries and the static
devices are kept, which leads to devices that can never be destroyed
(because of refcnt taken) and leaked memory, for example:
unreferenced object 0xffff880034c144c0 (size 192):
  comm "mfc-broken", pid 4777, jiffies 4320349055 (age 46001.964s)
  hex dump (first 32 bytes):
    98 53 f0 34 00 88 ff ff 98 53 f0 34 00 88 ff ff  .S.4.....S.4....
    ef 0a 0a 14 01 02 03 04 00 00 00 00 01 00 00 00  ................
  backtrace:
    [<ffffffff815c1b9e>] kmemleak_alloc+0x4e/0xb0
    [<ffffffff811ea6e0>] kmem_cache_alloc+0x190/0x300
    [<ffffffff815931cb>] ip_mroute_setsockopt+0x5cb/0x910
    [<ffffffff8153d575>] do_ip_setsockopt.isra.11+0x105/0xff0
    [<ffffffff8153e490>] ip_setsockopt+0x30/0xa0
    [<ffffffff81564e13>] raw_setsockopt+0x33/0x90
    [<ffffffff814d1e14>] sock_common_setsockopt+0x14/0x20
    [<ffffffff814d0b51>] SyS_setsockopt+0x71/0xc0
    [<ffffffff815cdbf6>] entry_SYSCALL_64_fastpath+0x16/0x7a
    [<ffffffffffffffff>] 0xffffffffffffffff

Make sure that everything is cleaned on netns destruction.

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Reviewed-by: Cong Wang <cwang@twopensource.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ipmr.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 8e8203d..ef7e2c4 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -134,7 +134,7 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
 			      struct mfc_cache *c, struct rtmsg *rtm);
 static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc,
 				 int cmd);
-static void mroute_clean_tables(struct mr_table *mrt);
+static void mroute_clean_tables(struct mr_table *mrt, bool all);
 static void ipmr_expire_process(unsigned long arg);
 
 #ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
@@ -350,7 +350,7 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id)
 static void ipmr_free_table(struct mr_table *mrt)
 {
 	del_timer_sync(&mrt->ipmr_expire_timer);
-	mroute_clean_tables(mrt);
+	mroute_clean_tables(mrt, true);
 	kfree(mrt);
 }
 
@@ -1208,7 +1208,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
  *	Close the multicast socket, and clear the vif tables etc
  */
 
-static void mroute_clean_tables(struct mr_table *mrt)
+static void mroute_clean_tables(struct mr_table *mrt, bool all)
 {
 	int i;
 	LIST_HEAD(list);
@@ -1217,8 +1217,9 @@ static void mroute_clean_tables(struct mr_table *mrt)
 	/* Shut down all active vif entries */
 
 	for (i = 0; i < mrt->maxvif; i++) {
-		if (!(mrt->vif_table[i].flags & VIFF_STATIC))
-			vif_delete(mrt, i, 0, &list);
+		if (!all && (mrt->vif_table[i].flags & VIFF_STATIC))
+			continue;
+		vif_delete(mrt, i, 0, &list);
 	}
 	unregister_netdevice_many(&list);
 
@@ -1226,7 +1227,7 @@ static void mroute_clean_tables(struct mr_table *mrt)
 
 	for (i = 0; i < MFC_LINES; i++) {
 		list_for_each_entry_safe(c, next, &mrt->mfc_cache_array[i], list) {
-			if (c->mfc_flags & MFC_STATIC)
+			if (!all && (c->mfc_flags & MFC_STATIC))
 				continue;
 			list_del_rcu(&c->list);
 			mroute_netlink_event(mrt, c, RTM_DELROUTE);
@@ -1261,7 +1262,7 @@ static void mrtsock_destruct(struct sock *sk)
 						    NETCONFA_IFINDEX_ALL,
 						    net->ipv4.devconf_all);
 			RCU_INIT_POINTER(mrt->mroute_sk, NULL);
-			mroute_clean_tables(mrt);
+			mroute_clean_tables(mrt, false);
 		}
 	}
 	rtnl_unlock();
-- 
2.1.0


From 6fea7a6bf9a832ea306a816204984e2244000784 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Fri, 20 Nov 2015 13:54:20 +0100
Subject: [PATCH 32/43] net: ip6mr: fix static mfc/dev leaks on table
 destruction

[ Upstream commit 4c6980462f32b4f282c5d8e5f7ea8070e2937725 ]

Similar to ipv4, when destroying an mrt table the static mfc entries and
the static devices are kept, which leads to devices that can never be
destroyed (because of refcnt taken) and leaked memory. Make sure that
everything is cleaned up on netns destruction.

Fixes: 8229efdaef1e ("netns: ip6mr: enable namespace support in ipv6 multicast forwarding code")
CC: Benjamin Thery <benjamin.thery@bull.net>
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Reviewed-by: Cong Wang <cwang@twopensource.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6mr.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 0e004cc..35eee72 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -118,7 +118,7 @@ static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc,
 			      int cmd);
 static int ip6mr_rtm_dumproute(struct sk_buff *skb,
 			       struct netlink_callback *cb);
-static void mroute_clean_tables(struct mr6_table *mrt);
+static void mroute_clean_tables(struct mr6_table *mrt, bool all);
 static void ipmr_expire_process(unsigned long arg);
 
 #ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES
@@ -334,7 +334,7 @@ static struct mr6_table *ip6mr_new_table(struct net *net, u32 id)
 static void ip6mr_free_table(struct mr6_table *mrt)
 {
 	del_timer_sync(&mrt->ipmr_expire_timer);
-	mroute_clean_tables(mrt);
+	mroute_clean_tables(mrt, true);
 	kfree(mrt);
 }
 
@@ -1542,7 +1542,7 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt,
  *	Close the multicast socket, and clear the vif tables etc
  */
 
-static void mroute_clean_tables(struct mr6_table *mrt)
+static void mroute_clean_tables(struct mr6_table *mrt, bool all)
 {
 	int i;
 	LIST_HEAD(list);
@@ -1552,8 +1552,9 @@ static void mroute_clean_tables(struct mr6_table *mrt)
 	 *	Shut down all active vif entries
 	 */
 	for (i = 0; i < mrt->maxvif; i++) {
-		if (!(mrt->vif6_table[i].flags & VIFF_STATIC))
-			mif6_delete(mrt, i, &list);
+		if (!all && (mrt->vif6_table[i].flags & VIFF_STATIC))
+			continue;
+		mif6_delete(mrt, i, &list);
 	}
 	unregister_netdevice_many(&list);
 
@@ -1562,7 +1563,7 @@ static void mroute_clean_tables(struct mr6_table *mrt)
 	 */
 	for (i = 0; i < MFC6_LINES; i++) {
 		list_for_each_entry_safe(c, next, &mrt->mfc6_cache_array[i], list) {
-			if (c->mfc_flags & MFC_STATIC)
+			if (!all && (c->mfc_flags & MFC_STATIC))
 				continue;
 			write_lock_bh(&mrt_lock);
 			list_del(&c->list);
@@ -1625,7 +1626,7 @@ int ip6mr_sk_done(struct sock *sk)
 						     net->ipv6.devconf_all);
 			write_unlock_bh(&mrt_lock);
 
-			mroute_clean_tables(mrt);
+			mroute_clean_tables(mrt, false);
 			err = 0;
 			break;
 		}
-- 
2.1.0


From 46b15261453a821e3d33889189715d61c4fb0af2 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Sat, 21 Nov 2015 19:46:19 +0100
Subject: [PATCH 33/43] vrf: fix double free and memory corruption on
 register_netdevice failure

[ Upstream commit 7f109f7cc37108cba7243bc832988525b0d85909 ]

When vrf's ->newlink is called, if register_netdevice() fails then it
does free_netdev(), but that's also done by rtnl_newlink() so a second
free happens and memory gets corrupted, to reproduce execute the
following line a couple of times (1 - 5 usually is enough):
$ for i in `seq 1 5`; do ip link add vrf: type vrf table 1; done;
This works because we fail in register_netdevice() because of the wrong
name "vrf:".

And here's a trace of one crash:
[   28.792157] ------------[ cut here ]------------
[   28.792407] kernel BUG at fs/namei.c:246!
[   28.792608] invalid opcode: 0000 [#1] SMP
[   28.793240] Modules linked in: vrf nfsd auth_rpcgss oid_registry
nfs_acl nfs lockd grace sunrpc crct10dif_pclmul crc32_pclmul
crc32c_intel qxl drm_kms_helper ttm drm aesni_intel aes_x86_64 psmouse
glue_helper lrw evdev gf128mul i2c_piix4 ablk_helper cryptd ppdev
parport_pc parport serio_raw pcspkr virtio_balloon virtio_console
i2c_core acpi_cpufreq button 9pnet_virtio 9p 9pnet fscache ipv6 autofs4
ext4 crc16 mbcache jbd2 virtio_blk virtio_net sg sr_mod cdrom
ata_generic ehci_pci uhci_hcd ehci_hcd e1000 usbcore usb_common ata_piix
libata virtio_pci virtio_ring virtio scsi_mod floppy
[   28.796016] CPU: 0 PID: 1148 Comm: ld-linux-x86-64 Not tainted
4.4.0-rc1+ #24
[   28.796016] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996),
BIOS 1.8.1-20150318_183358- 04/01/2014
[   28.796016] task: ffff8800352561c0 ti: ffff88003592c000 task.ti:
ffff88003592c000
[   28.796016] RIP: 0010:[<ffffffff812187b3>]  [<ffffffff812187b3>]
putname+0x43/0x60
[   28.796016] RSP: 0018:ffff88003592fe88  EFLAGS: 00010246
[   28.796016] RAX: 0000000000000000 RBX: ffff8800352561c0 RCX:
0000000000000001
[   28.796016] RDX: 0000000000000000 RSI: 0000000000000000 RDI:
ffff88003784f000
[   28.796016] RBP: ffff88003592ff08 R08: 0000000000000001 R09:
0000000000000000
[   28.796016] R10: 0000000000000000 R11: 0000000000000001 R12:
0000000000000000
[   28.796016] R13: 000000000000047c R14: ffff88003784f000 R15:
ffff8800358c4a00
[   28.796016] FS:  0000000000000000(0000) GS:ffff88003fc00000(0000)
knlGS:0000000000000000
[   28.796016] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   28.796016] CR2: 00007ffd583bc2d9 CR3: 0000000035a99000 CR4:
00000000000406f0
[   28.796016] Stack:
[   28.796016]  ffffffff8121045d ffffffff812102d3 ffff8800352561c0
ffff880035a91660
[   28.796016]  ffff8800008a9880 0000000000000000 ffffffff81a49940
00ffffff81218684
[   28.796016]  ffff8800352561c0 000000000000047c 0000000000000000
ffff880035b36d80
[   28.796016] Call Trace:
[   28.796016]  [<ffffffff8121045d>] ?
do_execveat_common.isra.34+0x74d/0x930
[   28.796016]  [<ffffffff812102d3>] ?
do_execveat_common.isra.34+0x5c3/0x930
[   28.796016]  [<ffffffff8121066c>] do_execve+0x2c/0x30
[   28.796016]  [<ffffffff810939a0>]
call_usermodehelper_exec_async+0xf0/0x140
[   28.796016]  [<ffffffff810938b0>] ? umh_complete+0x40/0x40
[   28.796016]  [<ffffffff815cb1af>] ret_from_fork+0x3f/0x70
[   28.796016] Code: 48 8d 47 1c 48 89 e5 53 48 8b 37 48 89 fb 48 39 c6
74 1a 48 8b 3d 7e e9 8f 00 e8 49 fa fc ff 48 89 df e8 f1 01 fd ff 5b 5d
f3 c3 <0f> 0b 48 89 fe 48 8b 3d 61 e9 8f 00 e8 2c fa fc ff 5b 5d eb e9
[   28.796016] RIP  [<ffffffff812187b3>] putname+0x43/0x60
[   28.796016]  RSP <ffff88003592fe88>

Fixes: 193125dbd8eb ("net: Introduce VRF device driver")
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Acked-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 15 ++-------------
 1 file changed, 2 insertions(+), 13 deletions(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 488c6f5..c9e309c 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -581,7 +581,6 @@ static int vrf_newlink(struct net *src_net, struct net_device *dev,
 {
 	struct net_vrf *vrf = netdev_priv(dev);
 	struct net_vrf_dev *vrf_ptr;
-	int err;
 
 	if (!data || !data[IFLA_VRF_TABLE])
 		return -EINVAL;
@@ -590,26 +589,16 @@ static int vrf_newlink(struct net *src_net, struct net_device *dev,
 
 	dev->priv_flags |= IFF_VRF_MASTER;
 
-	err = -ENOMEM;
 	vrf_ptr = kmalloc(sizeof(*dev->vrf_ptr), GFP_KERNEL);
 	if (!vrf_ptr)
-		goto out_fail;
+		return -ENOMEM;
 
 	vrf_ptr->ifindex = dev->ifindex;
 	vrf_ptr->tb_id = vrf->tb_id;
 
-	err = register_netdevice(dev);
-	if (err < 0)
-		goto out_fail;
-
 	rcu_assign_pointer(dev->vrf_ptr, vrf_ptr);
 
-	return 0;
-
-out_fail:
-	kfree(vrf_ptr);
-	free_netdev(dev);
-	return err;
+	return register_netdev(dev);
 }
 
 static size_t vrf_nl_getsize(const struct net_device *dev)
-- 
2.1.0


From 3ac4063f990a9e106c8971d60e1b430518fb5cec Mon Sep 17 00:00:00 2001
From: Aaro Koskinen <aaro.koskinen@iki.fi>
Date: Sun, 22 Nov 2015 01:08:54 +0200
Subject: [PATCH 34/43] broadcom: fix PHY_ID_BCM5481 entry in the id table

[ Upstream commit 3c25a860d17b7378822f35d8c9141db9507e3beb ]

Commit fcb26ec5b18d ("broadcom: move all PHY_ID's to header")
updated broadcom_tbl to use PHY_IDs, but incorrectly replaced 0x0143bca0
with PHY_ID_BCM5482 (making a duplicate entry, and completely omitting
the original). Fix that.

Fixes: fcb26ec5b18d ("broadcom: move all PHY_ID's to header")
Signed-off-by: Aaro Koskinen <aaro.koskinen@iki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/broadcom.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c
index 9c71295..85e64044 100644
--- a/drivers/net/phy/broadcom.c
+++ b/drivers/net/phy/broadcom.c
@@ -675,7 +675,7 @@ static struct mdio_device_id __maybe_unused broadcom_tbl[] = {
 	{ PHY_ID_BCM5461, 0xfffffff0 },
 	{ PHY_ID_BCM54616S, 0xfffffff0 },
 	{ PHY_ID_BCM5464, 0xfffffff0 },
-	{ PHY_ID_BCM5482, 0xfffffff0 },
+	{ PHY_ID_BCM5481, 0xfffffff0 },
 	{ PHY_ID_BCM5482, 0xfffffff0 },
 	{ PHY_ID_BCM50610, 0xfffffff0 },
 	{ PHY_ID_BCM50610M, 0xfffffff0 },
-- 
2.1.0


From d71b7cd7146378b31252e33a23ad693b6d461ed8 Mon Sep 17 00:00:00 2001
From: Ying Xue <ying.xue@windriver.com>
Date: Tue, 24 Nov 2015 13:57:57 +0800
Subject: [PATCH 35/43] tipc: fix error handling of expanding buffer headroom

[ Upstream commit 7098356baca723513e97ca0020df4e18bc353be3 ]

Coverity says:

*** CID 1338065:  Error handling issues  (CHECKED_RETURN)
/net/tipc/udp_media.c: 162 in tipc_udp_send_msg()
156     	struct udp_media_addr *dst = (struct udp_media_addr *)&dest->value;
157     	struct udp_media_addr *src = (struct udp_media_addr *)&b->addr.value;
158     	struct sk_buff *clone;
159     	struct rtable *rt;
160
161     	if (skb_headroom(skb) < UDP_MIN_HEADROOM)
>>>     CID 1338065:  Error handling issues  (CHECKED_RETURN)
>>>     Calling "pskb_expand_head" without checking return value (as is done elsewhere 51 out of 56 times).
162     		pskb_expand_head(skb, UDP_MIN_HEADROOM, 0, GFP_ATOMIC);
163
164     	clone = skb_clone(skb, GFP_ATOMIC);
165     	skb_set_inner_protocol(clone, htons(ETH_P_TIPC));
166     	ub = rcu_dereference_rtnl(b->media_ptr);
167     	if (!ub) {

When expanding buffer headroom over udp tunnel with pskb_expand_head(),
it's unfortunate that we don't check its return value. As a result, if
the function returns an error code due to the lack of memory, it may
cause unpredictable consequence as we unconditionally consider that
it's always successful.

Fixes: e53567948f82 ("tipc: conditionally expand buffer headroom over udp tunnel")
Reported-by: <scan-admin@coverity.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/udp_media.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index cd7c5f1..86f2e7c 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -159,8 +159,11 @@ static int tipc_udp_send_msg(struct net *net, struct sk_buff *skb,
 	struct sk_buff *clone;
 	struct rtable *rt;
 
-	if (skb_headroom(skb) < UDP_MIN_HEADROOM)
-		pskb_expand_head(skb, UDP_MIN_HEADROOM, 0, GFP_ATOMIC);
+	if (skb_headroom(skb) < UDP_MIN_HEADROOM) {
+		err = pskb_expand_head(skb, UDP_MIN_HEADROOM, 0, GFP_ATOMIC);
+		if (err)
+			goto tx_error;
+	}
 
 	clone = skb_clone(skb, GFP_ATOMIC);
 	skb_set_inner_protocol(clone, htons(ETH_P_TIPC));
-- 
2.1.0


From d26834684ff963259ed7fd9e19c816ed71d7bf61 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Michal=20Kube=C4=8Dek?= <mkubecek@suse.cz>
Date: Tue, 24 Nov 2015 15:07:11 +0100
Subject: [PATCH 36/43] ipv6: distinguish frag queues by device for multicast
 and link-local packets

[ Upstream commit 264640fc2c5f4f913db5c73fa3eb1ead2c45e9d7 ]

If a fragmented multicast packet is received on an ethernet device which
has an active macvlan on top of it, each fragment is duplicated and
received both on the underlying device and the macvlan. If some
fragments for macvlan are processed before the whole packet for the
underlying device is reassembled, the "overlapping fragments" test in
ip6_frag_queue() discards the whole fragment queue.

To resolve this, add device ifindex to the search key and require it to
match reassembling multicast packets and packets to link-local
addresses.

Note: similar patch has been already submitted by Yoshifuji Hideaki in

  http://patchwork.ozlabs.org/patch/220979/

but got lost and forgotten for some reason.

Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h                      |  1 +
 net/ipv6/netfilter/nf_conntrack_reasm.c |  5 +++--
 net/ipv6/reassembly.c                   | 10 +++++++---
 3 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 711cca4..1b63717 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -490,6 +490,7 @@ struct ip6_create_arg {
 	u32 user;
 	const struct in6_addr *src;
 	const struct in6_addr *dst;
+	int iif;
 	u8 ecn;
 };
 
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index c7196ad..dc50143 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -190,7 +190,7 @@ static void nf_ct_frag6_expire(unsigned long data)
 /* Creation primitives. */
 static inline struct frag_queue *fq_find(struct net *net, __be32 id,
 					 u32 user, struct in6_addr *src,
-					 struct in6_addr *dst, u8 ecn)
+					 struct in6_addr *dst, int iif, u8 ecn)
 {
 	struct inet_frag_queue *q;
 	struct ip6_create_arg arg;
@@ -200,6 +200,7 @@ static inline struct frag_queue *fq_find(struct net *net, __be32 id,
 	arg.user = user;
 	arg.src = src;
 	arg.dst = dst;
+	arg.iif = iif;
 	arg.ecn = ecn;
 
 	local_bh_disable();
@@ -603,7 +604,7 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user)
 	fhdr = (struct frag_hdr *)skb_transport_header(clone);
 
 	fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr,
-		     ip6_frag_ecn(hdr));
+		     skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
 	if (fq == NULL) {
 		pr_debug("Can't find and can't create new queue\n");
 		goto ret_orig;
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index f1159bb..04013a9 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -108,7 +108,10 @@ bool ip6_frag_match(const struct inet_frag_queue *q, const void *a)
 	return	fq->id == arg->id &&
 		fq->user == arg->user &&
 		ipv6_addr_equal(&fq->saddr, arg->src) &&
-		ipv6_addr_equal(&fq->daddr, arg->dst);
+		ipv6_addr_equal(&fq->daddr, arg->dst) &&
+		(arg->iif == fq->iif ||
+		 !(ipv6_addr_type(arg->dst) & (IPV6_ADDR_MULTICAST |
+					       IPV6_ADDR_LINKLOCAL)));
 }
 EXPORT_SYMBOL(ip6_frag_match);
 
@@ -180,7 +183,7 @@ static void ip6_frag_expire(unsigned long data)
 
 static struct frag_queue *
 fq_find(struct net *net, __be32 id, const struct in6_addr *src,
-	const struct in6_addr *dst, u8 ecn)
+	const struct in6_addr *dst, int iif, u8 ecn)
 {
 	struct inet_frag_queue *q;
 	struct ip6_create_arg arg;
@@ -190,6 +193,7 @@ fq_find(struct net *net, __be32 id, const struct in6_addr *src,
 	arg.user = IP6_DEFRAG_LOCAL_DELIVER;
 	arg.src = src;
 	arg.dst = dst;
+	arg.iif = iif;
 	arg.ecn = ecn;
 
 	hash = inet6_hash_frag(id, src, dst);
@@ -551,7 +555,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 	}
 
 	fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr,
-		     ip6_frag_ecn(hdr));
+		     skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
 	if (fq) {
 		int ret;
 
-- 
2.1.0


From a9bb7b65ac7cd16bafc5cbd4ebb182ce5bbcb488 Mon Sep 17 00:00:00 2001
From: Quentin Casasnovas <quentin.casasnovas@oracle.com>
Date: Tue, 24 Nov 2015 17:13:21 -0500
Subject: [PATCH 37/43] RDS: fix race condition when sending a message on
 unbound socket

[ Upstream commit 8c7188b23474cca017b3ef354c4a58456f68303a ]

Sasha's found a NULL pointer dereference in the RDS connection code when
sending a message to an apparently unbound socket.  The problem is caused
by the code checking if the socket is bound in rds_sendmsg(), which checks
the rs_bound_addr field without taking a lock on the socket.  This opens a
race where rs_bound_addr is temporarily set but where the transport is not
in rds_bind(), leading to a NULL pointer dereference when trying to
dereference 'trans' in __rds_conn_create().

Vegard wrote a reproducer for this issue, so kindly ask him to share if
you're interested.

I cannot reproduce the NULL pointer dereference using Vegard's reproducer
with this patch, whereas I could without.

Complete earlier incomplete fix to CVE-2015-6937:

  74e98eb08588 ("RDS: verify the underlying transport exists before creating a connection")

Cc: David S. Miller <davem@davemloft.net>
Cc: stable@vger.kernel.org

Reviewed-by: Vegard Nossum <vegard.nossum@oracle.com>
Reviewed-by: Sasha Levin <sasha.levin@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: Quentin Casasnovas <quentin.casasnovas@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/connection.c | 6 ------
 net/rds/send.c       | 4 +++-
 2 files changed, 3 insertions(+), 7 deletions(-)

diff --git a/net/rds/connection.c b/net/rds/connection.c
index 49adeef..9b2de5e 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -190,12 +190,6 @@ new_conn:
 		}
 	}
 
-	if (trans == NULL) {
-		kmem_cache_free(rds_conn_slab, conn);
-		conn = ERR_PTR(-ENODEV);
-		goto out;
-	}
-
 	conn->c_trans = trans;
 
 	ret = trans->conn_alloc(conn, gfp);
diff --git a/net/rds/send.c b/net/rds/send.c
index 4df61a5..859de6f 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -1009,11 +1009,13 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 		release_sock(sk);
 	}
 
-	/* racing with another thread binding seems ok here */
+	lock_sock(sk);
 	if (daddr == 0 || rs->rs_bound_addr == 0) {
+		release_sock(sk);
 		ret = -ENOTCONN; /* XXX not a great errno */
 		goto out;
 	}
+	release_sock(sk);
 
 	if (payload_len > rds_sk_sndbuf(rs)) {
 		ret = -EMSGSIZE;
-- 
2.1.0


From f6c7967f25e8220913bedf596c260c379dab5341 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Mon, 30 Nov 2015 13:02:56 +0100
Subject: [PATCH 38/43] bpf, array: fix heap out-of-bounds access when updating
 elements

[ Upstream commit fbca9d2d35c6ef1b323fae75cc9545005ba25097 ]

During own review but also reported by Dmitry's syzkaller [1] it has been
noticed that we trigger a heap out-of-bounds access on eBPF array maps
when updating elements. This happens with each map whose map->value_size
(specified during map creation time) is not multiple of 8 bytes.

In array_map_alloc(), elem_size is round_up(attr->value_size, 8) and
used to align array map slots for faster access. However, in function
array_map_update_elem(), we update the element as ...

memcpy(array->value + array->elem_size * index, value, array->elem_size);

... where we access 'value' out-of-bounds, since it was allocated from
map_update_elem() from syscall side as kmalloc(map->value_size, GFP_USER)
and later on copied through copy_from_user(value, uvalue, map->value_size).
Thus, up to 7 bytes, we can access out-of-bounds.

Same could happen from within an eBPF program, where in worst case we
access beyond an eBPF program's designated stack.

Since 1be7f75d1668 ("bpf: enable non-root eBPF programs") didn't hit an
official release yet, it only affects priviledged users.

In case of array_map_lookup_elem(), the verifier prevents eBPF programs
from accessing beyond map->value_size through check_map_access(). Also
from syscall side map_lookup_elem() only copies map->value_size back to
user, so nothing could leak.

  [1] http://github.com/google/syzkaller

Fixes: 28fbcfa08d8e ("bpf: add array type of eBPF maps")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/arraymap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 29ace10..7a0decf 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -104,7 +104,7 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value,
 		/* all elements already exist */
 		return -EEXIST;
 
-	memcpy(array->value + array->elem_size * index, value, array->elem_size);
+	memcpy(array->value + array->elem_size * index, value, map->value_size);
 	return 0;
 }
 
-- 
2.1.0


From 5c3c67ba34c640fa3d93ff4e0506cb5826619de2 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 29 Nov 2015 19:37:57 -0800
Subject: [PATCH 39/43] ipv6: add complete rcu protection around np->opt

[ Upstream commit 45f6fad84cc305103b28d73482b344d7f5b76f39 ]

This patch addresses multiple problems :

UDP/RAW sendmsg() need to get a stable struct ipv6_txoptions
while socket is not locked : Other threads can change np->opt
concurrently. Dmitry posted a syzkaller
(http://github.com/google/syzkaller) program desmonstrating
use-after-free.

Starting with TCP/DCCP lockless listeners, tcp_v6_syn_recv_sock()
and dccp_v6_request_recv_sock() also need to use RCU protection
to dereference np->opt once (before calling ipv6_dup_options())

This patch adds full RCU protection to np->opt

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ipv6.h             |  2 +-
 include/net/ipv6.h               | 21 ++++++++++++++++++++-
 net/dccp/ipv6.c                  | 33 +++++++++++++++++++++------------
 net/ipv6/af_inet6.c              | 13 +++++++++----
 net/ipv6/datagram.c              |  4 +++-
 net/ipv6/exthdrs.c               |  3 ++-
 net/ipv6/inet6_connection_sock.c | 11 ++++++++---
 net/ipv6/ipv6_sockglue.c         | 33 ++++++++++++++++++++++-----------
 net/ipv6/raw.c                   |  8 ++++++--
 net/ipv6/syncookies.c            |  2 +-
 net/ipv6/tcp_ipv6.c              | 28 +++++++++++++++++-----------
 net/ipv6/udp.c                   |  8 ++++++--
 net/l2tp/l2tp_ip6.c              |  8 ++++++--
 13 files changed, 122 insertions(+), 52 deletions(-)

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index f1f32af..3e4ff3f 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -227,7 +227,7 @@ struct ipv6_pinfo {
 	struct ipv6_ac_socklist	*ipv6_ac_list;
 	struct ipv6_fl_socklist __rcu *ipv6_fl_list;
 
-	struct ipv6_txoptions	*opt;
+	struct ipv6_txoptions __rcu	*opt;
 	struct sk_buff		*pktoptions;
 	struct sk_buff		*rxpmtu;
 	struct inet6_cork	cork;
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 1b63717..b14e158 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -205,6 +205,7 @@ extern rwlock_t ip6_ra_lock;
  */
 
 struct ipv6_txoptions {
+	atomic_t		refcnt;
 	/* Length of this structure */
 	int			tot_len;
 
@@ -217,7 +218,7 @@ struct ipv6_txoptions {
 	struct ipv6_opt_hdr	*dst0opt;
 	struct ipv6_rt_hdr	*srcrt;	/* Routing Header */
 	struct ipv6_opt_hdr	*dst1opt;
-
+	struct rcu_head		rcu;
 	/* Option buffer, as read by IPV6_PKTOPTIONS, starts here. */
 };
 
@@ -252,6 +253,24 @@ struct ipv6_fl_socklist {
 	struct rcu_head			rcu;
 };
 
+static inline struct ipv6_txoptions *txopt_get(const struct ipv6_pinfo *np)
+{
+	struct ipv6_txoptions *opt;
+
+	rcu_read_lock();
+	opt = rcu_dereference(np->opt);
+	if (opt && !atomic_inc_not_zero(&opt->refcnt))
+		opt = NULL;
+	rcu_read_unlock();
+	return opt;
+}
+
+static inline void txopt_put(struct ipv6_txoptions *opt)
+{
+	if (opt && atomic_dec_and_test(&opt->refcnt))
+		kfree_rcu(opt, rcu);
+}
+
 struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label);
 struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space,
 					 struct ip6_flowlabel *fl,
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 5165571..a049050 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -202,7 +202,9 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req)
 	security_req_classify_flow(req, flowi6_to_flowi(&fl6));
 
 
-	final_p = fl6_update_dst(&fl6, np->opt, &final);
+	rcu_read_lock();
+	final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final);
+	rcu_read_unlock();
 
 	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
@@ -219,7 +221,10 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req)
 							 &ireq->ir_v6_loc_addr,
 							 &ireq->ir_v6_rmt_addr);
 		fl6.daddr = ireq->ir_v6_rmt_addr;
-		err = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass);
+		rcu_read_lock();
+		err = ip6_xmit(sk, skb, &fl6, rcu_dereference(np->opt),
+			       np->tclass);
+		rcu_read_unlock();
 		err = net_xmit_eval(err);
 	}
 
@@ -415,6 +420,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
 	struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
+	struct ipv6_txoptions *opt;
 	struct inet_sock *newinet;
 	struct dccp6_sock *newdp6;
 	struct sock *newsk;
@@ -534,13 +540,15 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
 	 * Yes, keeping reference count would be much more clever, but we make
 	 * one more one thing there: reattach optmem to newsk.
 	 */
-	if (np->opt != NULL)
-		newnp->opt = ipv6_dup_options(newsk, np->opt);
-
+	opt = rcu_dereference(np->opt);
+	if (opt) {
+		opt = ipv6_dup_options(newsk, opt);
+		RCU_INIT_POINTER(newnp->opt, opt);
+	}
 	inet_csk(newsk)->icsk_ext_hdr_len = 0;
-	if (newnp->opt != NULL)
-		inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen +
-						     newnp->opt->opt_flen);
+	if (opt)
+		inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen +
+						    opt->opt_flen;
 
 	dccp_sync_mss(newsk, dst_mtu(dst));
 
@@ -793,6 +801,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct dccp_sock *dp = dccp_sk(sk);
 	struct in6_addr *saddr = NULL, *final_p, final;
+	struct ipv6_txoptions *opt;
 	struct flowi6 fl6;
 	struct dst_entry *dst;
 	int addr_type;
@@ -892,7 +901,8 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	fl6.fl6_sport = inet->inet_sport;
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
-	final_p = fl6_update_dst(&fl6, np->opt, &final);
+	opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+	final_p = fl6_update_dst(&fl6, opt, &final);
 
 	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
@@ -912,9 +922,8 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	__ip6_dst_store(sk, dst, NULL, NULL);
 
 	icsk->icsk_ext_hdr_len = 0;
-	if (np->opt != NULL)
-		icsk->icsk_ext_hdr_len = (np->opt->opt_flen +
-					  np->opt->opt_nflen);
+	if (opt)
+		icsk->icsk_ext_hdr_len = opt->opt_flen + opt->opt_nflen;
 
 	inet->inet_dport = usin->sin6_port;
 
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 44bb66b..38d66dd 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -428,9 +428,11 @@ void inet6_destroy_sock(struct sock *sk)
 
 	/* Free tx options */
 
-	opt = xchg(&np->opt, NULL);
-	if (opt)
-		sock_kfree_s(sk, opt, opt->tot_len);
+	opt = xchg((__force struct ipv6_txoptions **)&np->opt, NULL);
+	if (opt) {
+		atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+		txopt_put(opt);
+	}
 }
 EXPORT_SYMBOL_GPL(inet6_destroy_sock);
 
@@ -659,7 +661,10 @@ int inet6_sk_rebuild_header(struct sock *sk)
 		fl6.fl6_sport = inet->inet_sport;
 		security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
-		final_p = fl6_update_dst(&fl6, np->opt, &final);
+		rcu_read_lock();
+		final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt),
+					 &final);
+		rcu_read_unlock();
 
 		dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
 		if (IS_ERR(dst)) {
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 9aadd57..a42a673 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -167,8 +167,10 @@ ipv4_connected:
 
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
-	opt = flowlabel ? flowlabel->opt : np->opt;
+	rcu_read_lock();
+	opt = flowlabel ? flowlabel->opt : rcu_dereference(np->opt);
 	final_p = fl6_update_dst(&fl6, opt, &final);
+	rcu_read_unlock();
 
 	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
 	err = 0;
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index ce203b0..ea7c4d6 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -727,6 +727,7 @@ ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt)
 			*((char **)&opt2->dst1opt) += dif;
 		if (opt2->srcrt)
 			*((char **)&opt2->srcrt) += dif;
+		atomic_set(&opt2->refcnt, 1);
 	}
 	return opt2;
 }
@@ -790,7 +791,7 @@ ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt,
 		return ERR_PTR(-ENOBUFS);
 
 	memset(opt2, 0, tot_len);
-
+	atomic_set(&opt2->refcnt, 1);
 	opt2->tot_len = tot_len;
 	p = (char *)(opt2 + 1);
 
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 6927f3f..9beed30 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -77,7 +77,9 @@ struct dst_entry *inet6_csk_route_req(struct sock *sk,
 	memset(fl6, 0, sizeof(*fl6));
 	fl6->flowi6_proto = IPPROTO_TCP;
 	fl6->daddr = ireq->ir_v6_rmt_addr;
-	final_p = fl6_update_dst(fl6, np->opt, &final);
+	rcu_read_lock();
+	final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
+	rcu_read_unlock();
 	fl6->saddr = ireq->ir_v6_loc_addr;
 	fl6->flowi6_oif = ireq->ir_iif;
 	fl6->flowi6_mark = ireq->ir_mark;
@@ -207,7 +209,9 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk,
 	fl6->fl6_dport = inet->inet_dport;
 	security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
 
-	final_p = fl6_update_dst(fl6, np->opt, &final);
+	rcu_read_lock();
+	final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
+	rcu_read_unlock();
 
 	dst = __inet6_csk_dst_check(sk, np->dst_cookie);
 	if (!dst) {
@@ -240,7 +244,8 @@ int inet6_csk_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl_unused
 	/* Restore final destination back after routing done */
 	fl6.daddr = sk->sk_v6_daddr;
 
-	res = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass);
+	res = ip6_xmit(sk, skb, &fl6, rcu_dereference(np->opt),
+		       np->tclass);
 	rcu_read_unlock();
 	return res;
 }
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 63e6956..4449ad1 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -111,7 +111,8 @@ struct ipv6_txoptions *ipv6_update_options(struct sock *sk,
 			icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie);
 		}
 	}
-	opt = xchg(&inet6_sk(sk)->opt, opt);
+	opt = xchg((__force struct ipv6_txoptions **)&inet6_sk(sk)->opt,
+		   opt);
 	sk_dst_reset(sk);
 
 	return opt;
@@ -231,9 +232,12 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 				sk->sk_socket->ops = &inet_dgram_ops;
 				sk->sk_family = PF_INET;
 			}
-			opt = xchg(&np->opt, NULL);
-			if (opt)
-				sock_kfree_s(sk, opt, opt->tot_len);
+			opt = xchg((__force struct ipv6_txoptions **)&np->opt,
+				   NULL);
+			if (opt) {
+				atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+				txopt_put(opt);
+			}
 			pktopt = xchg(&np->pktoptions, NULL);
 			kfree_skb(pktopt);
 
@@ -403,7 +407,8 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 		if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW))
 			break;
 
-		opt = ipv6_renew_options(sk, np->opt, optname,
+		opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+		opt = ipv6_renew_options(sk, opt, optname,
 					 (struct ipv6_opt_hdr __user *)optval,
 					 optlen);
 		if (IS_ERR(opt)) {
@@ -432,8 +437,10 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 		retv = 0;
 		opt = ipv6_update_options(sk, opt);
 sticky_done:
-		if (opt)
-			sock_kfree_s(sk, opt, opt->tot_len);
+		if (opt) {
+			atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+			txopt_put(opt);
+		}
 		break;
 	}
 
@@ -486,6 +493,7 @@ sticky_done:
 			break;
 
 		memset(opt, 0, sizeof(*opt));
+		atomic_set(&opt->refcnt, 1);
 		opt->tot_len = sizeof(*opt) + optlen;
 		retv = -EFAULT;
 		if (copy_from_user(opt+1, optval, optlen))
@@ -502,8 +510,10 @@ update:
 		retv = 0;
 		opt = ipv6_update_options(sk, opt);
 done:
-		if (opt)
-			sock_kfree_s(sk, opt, opt->tot_len);
+		if (opt) {
+			atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+			txopt_put(opt);
+		}
 		break;
 	}
 	case IPV6_UNICAST_HOPS:
@@ -1110,10 +1120,11 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 	case IPV6_RTHDR:
 	case IPV6_DSTOPTS:
 	{
+		struct ipv6_txoptions *opt;
 
 		lock_sock(sk);
-		len = ipv6_getsockopt_sticky(sk, np->opt,
-					     optname, optval, len);
+		opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+		len = ipv6_getsockopt_sticky(sk, opt, optname, optval, len);
 		release_sock(sk);
 		/* check if ipv6_getsockopt_sticky() returns err code */
 		if (len < 0)
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index fdbada156..fe97729 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -732,6 +732,7 @@ static int raw6_getfrag(void *from, char *to, int offset, int len, int odd,
 
 static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 {
+	struct ipv6_txoptions *opt_to_free = NULL;
 	struct ipv6_txoptions opt_space;
 	DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
 	struct in6_addr *daddr, *final_p, final;
@@ -838,8 +839,10 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		if (!(opt->opt_nflen|opt->opt_flen))
 			opt = NULL;
 	}
-	if (!opt)
-		opt = np->opt;
+	if (!opt) {
+		opt = txopt_get(np);
+		opt_to_free = opt;
+		}
 	if (flowlabel)
 		opt = fl6_merge_options(&opt_space, flowlabel, opt);
 	opt = ipv6_fixup_options(&opt_space, opt);
@@ -905,6 +908,7 @@ done:
 	dst_release(dst);
 out:
 	fl6_sock_release(flowlabel);
+	txopt_put(opt_to_free);
 	return err < 0 ? err : len;
 do_confirm:
 	dst_confirm(dst);
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 0909f4e..f30bfdc 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -225,7 +225,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 		memset(&fl6, 0, sizeof(fl6));
 		fl6.flowi6_proto = IPPROTO_TCP;
 		fl6.daddr = ireq->ir_v6_rmt_addr;
-		final_p = fl6_update_dst(&fl6, np->opt, &final);
+		final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final);
 		fl6.saddr = ireq->ir_v6_loc_addr;
 		fl6.flowi6_oif = sk->sk_bound_dev_if;
 		fl6.flowi6_mark = ireq->ir_mark;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 97d9314..9e9b77b 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -120,6 +120,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct in6_addr *saddr = NULL, *final_p, final;
+	struct ipv6_txoptions *opt;
 	struct flowi6 fl6;
 	struct dst_entry *dst;
 	int addr_type;
@@ -235,7 +236,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	fl6.fl6_dport = usin->sin6_port;
 	fl6.fl6_sport = inet->inet_sport;
 
-	final_p = fl6_update_dst(&fl6, np->opt, &final);
+	opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+	final_p = fl6_update_dst(&fl6, opt, &final);
 
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
@@ -263,9 +265,9 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 		tcp_fetch_timewait_stamp(sk, dst);
 
 	icsk->icsk_ext_hdr_len = 0;
-	if (np->opt)
-		icsk->icsk_ext_hdr_len = (np->opt->opt_flen +
-					  np->opt->opt_nflen);
+	if (opt)
+		icsk->icsk_ext_hdr_len = opt->opt_flen +
+					 opt->opt_nflen;
 
 	tp->rx_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
 
@@ -461,7 +463,8 @@ static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst,
 			fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));
 
 		skb_set_queue_mapping(skb, queue_mapping);
-		err = ip6_xmit(sk, skb, fl6, np->opt, np->tclass);
+		err = ip6_xmit(sk, skb, fl6, rcu_dereference(np->opt),
+			       np->tclass);
 		err = net_xmit_eval(err);
 	}
 
@@ -991,6 +994,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	struct inet_request_sock *ireq;
 	struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
 	struct tcp6_sock *newtcp6sk;
+	struct ipv6_txoptions *opt;
 	struct inet_sock *newinet;
 	struct tcp_sock *newtp;
 	struct sock *newsk;
@@ -1126,13 +1130,15 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	   but we make one more one thing there: reattach optmem
 	   to newsk.
 	 */
-	if (np->opt)
-		newnp->opt = ipv6_dup_options(newsk, np->opt);
-
+	opt = rcu_dereference(np->opt);
+	if (opt) {
+		opt = ipv6_dup_options(newsk, opt);
+		RCU_INIT_POINTER(newnp->opt, opt);
+	}
 	inet_csk(newsk)->icsk_ext_hdr_len = 0;
-	if (newnp->opt)
-		inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen +
-						     newnp->opt->opt_flen);
+	if (opt)
+		inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen +
+						    opt->opt_flen;
 
 	tcp_ca_openreq_child(newsk, dst);
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 0aba654..8379fc2 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1107,6 +1107,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
 	struct in6_addr *daddr, *final_p, final;
 	struct ipv6_txoptions *opt = NULL;
+	struct ipv6_txoptions *opt_to_free = NULL;
 	struct ip6_flowlabel *flowlabel = NULL;
 	struct flowi6 fl6;
 	struct dst_entry *dst;
@@ -1260,8 +1261,10 @@ do_udp_sendmsg:
 			opt = NULL;
 		connected = 0;
 	}
-	if (!opt)
-		opt = np->opt;
+	if (!opt) {
+		opt = txopt_get(np);
+		opt_to_free = opt;
+	}
 	if (flowlabel)
 		opt = fl6_merge_options(&opt_space, flowlabel, opt);
 	opt = ipv6_fixup_options(&opt_space, opt);
@@ -1370,6 +1373,7 @@ release_dst:
 out:
 	dst_release(dst);
 	fl6_sock_release(flowlabel);
+	txopt_put(opt_to_free);
 	if (!err)
 		return len;
 	/*
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index d1ded37..0ce9da9 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -486,6 +486,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	DECLARE_SOCKADDR(struct sockaddr_l2tpip6 *, lsa, msg->msg_name);
 	struct in6_addr *daddr, *final_p, final;
 	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct ipv6_txoptions *opt_to_free = NULL;
 	struct ipv6_txoptions *opt = NULL;
 	struct ip6_flowlabel *flowlabel = NULL;
 	struct dst_entry *dst = NULL;
@@ -575,8 +576,10 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 			opt = NULL;
 	}
 
-	if (opt == NULL)
-		opt = np->opt;
+	if (!opt) {
+		opt = txopt_get(np);
+		opt_to_free = opt;
+	}
 	if (flowlabel)
 		opt = fl6_merge_options(&opt_space, flowlabel, opt);
 	opt = ipv6_fixup_options(&opt_space, opt);
@@ -631,6 +634,7 @@ done:
 	dst_release(dst);
 out:
 	fl6_sock_release(flowlabel);
+	txopt_put(opt_to_free);
 
 	return err < 0 ? err : len;
 
-- 
2.1.0


From 42b4973eefcdcfc62b49c61f50f9f1e81ae6a615 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <koct9i@gmail.com>
Date: Tue, 1 Dec 2015 01:14:48 +0300
Subject: [PATCH 40/43] net/neighbour: fix crash at dumping device-agnostic
 proxy entries

[ Upstream commit 6adc5fd6a142c6e2c80574c1db0c7c17dedaa42e ]

Proxy entries could have null pointer to net-device.

Signed-off-by: Konstantin Khlebnikov <koct9i@gmail.com>
Fixes: 84920c1420e2 ("net: Allow ipv6 proxies and arp proxies be shown with iproute2")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 2b515ba..c169bba 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2215,7 +2215,7 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn,
 	ndm->ndm_pad2    = 0;
 	ndm->ndm_flags	 = pn->flags | NTF_PROXY;
 	ndm->ndm_type	 = RTN_UNICAST;
-	ndm->ndm_ifindex = pn->dev->ifindex;
+	ndm->ndm_ifindex = pn->dev ? pn->dev->ifindex : 0;
 	ndm->ndm_state	 = NUD_NONE;
 
 	if (nla_put(skb, NDA_DST, tbl->key_len, pn->key))
@@ -2290,7 +2290,7 @@ static int pneigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
 		if (h > s_h)
 			s_idx = 0;
 		for (n = tbl->phash_buckets[h], idx = 0; n; n = n->next) {
-			if (dev_net(n->dev) != net)
+			if (pneigh_net(n) != net)
 				continue;
 			if (idx < s_idx)
 				goto next;
-- 
2.1.0


From f7391ce93c846664fb548ff4054edc165e7a5442 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 1 Dec 2015 07:20:07 -0800
Subject: [PATCH 41/43] ipv6: sctp: implement sctp_v6_destroy_sock()

[ Upstream commit 602dd62dfbda3e63a2d6a3cbde953ebe82bf5087 ]

Dmitry Vyukov reported a memory leak using IPV6 SCTP sockets.

We need to call inet6_destroy_sock() to properly release
inet6 specific fields.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 17bef01..3ec88be 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -7375,6 +7375,13 @@ struct proto sctp_prot = {
 
 #if IS_ENABLED(CONFIG_IPV6)
 
+#include <net/transp_v6.h>
+static void sctp_v6_destroy_sock(struct sock *sk)
+{
+	sctp_destroy_sock(sk);
+	inet6_destroy_sock(sk);
+}
+
 struct proto sctpv6_prot = {
 	.name		= "SCTPv6",
 	.owner		= THIS_MODULE,
@@ -7384,7 +7391,7 @@ struct proto sctpv6_prot = {
 	.accept		= sctp_accept,
 	.ioctl		= sctp_ioctl,
 	.init		= sctp_init_sock,
-	.destroy	= sctp_destroy_sock,
+	.destroy	= sctp_v6_destroy_sock,
 	.shutdown	= sctp_shutdown,
 	.setsockopt	= sctp_setsockopt,
 	.getsockopt	= sctp_getsockopt,
-- 
2.1.0


From c391cc510c3cf6b5a8dd57fbc1de26b4b28bd7e0 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 1 Dec 2015 18:33:36 +0100
Subject: [PATCH 42/43] openvswitch: fix hangup on vxlan/gre/geneve device
 deletion

[ Upstream commit 13175303024c8f4cd09e51079a8fcbbe572111ec ]

Each openvswitch tunnel vport (vxlan,gre,geneve) holds a reference
to the underlying tunnel device, but never released it when such
device is deleted.
Deleting the underlying device via the ip tool cause the kernel to
hangup in the netdev_wait_allrefs() loop.
This commit ensure that on device unregistration dp_detach_port_notify()
is called for all vports that hold the device reference, properly
releasing it.

Fixes: 614732eaa12d ("openvswitch: Use regular VXLAN net_device device")
Fixes: b2acd1dc3949 ("openvswitch: Use regular GRE net_device instead of vport")
Fixes: 6b001e682e90 ("openvswitch: Use Geneve device.")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Flavio Leitner <fbl@sysclose.org>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/dp_notify.c    | 2 +-
 net/openvswitch/vport-netdev.c | 8 ++++++--
 2 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/net/openvswitch/dp_notify.c b/net/openvswitch/dp_notify.c
index a7a80a6..653d073 100644
--- a/net/openvswitch/dp_notify.c
+++ b/net/openvswitch/dp_notify.c
@@ -58,7 +58,7 @@ void ovs_dp_notify_wq(struct work_struct *work)
 			struct hlist_node *n;
 
 			hlist_for_each_entry_safe(vport, n, &dp->ports[i], dp_hash_node) {
-				if (vport->ops->type != OVS_VPORT_TYPE_NETDEV)
+				if (vport->ops->type == OVS_VPORT_TYPE_INTERNAL)
 					continue;
 
 				if (!(vport->dev->priv_flags & IFF_OVS_DATAPATH))
diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c
index f7e8dcc..ac14c48 100644
--- a/net/openvswitch/vport-netdev.c
+++ b/net/openvswitch/vport-netdev.c
@@ -180,9 +180,13 @@ void ovs_netdev_tunnel_destroy(struct vport *vport)
 	if (vport->dev->priv_flags & IFF_OVS_DATAPATH)
 		ovs_netdev_detach_dev(vport);
 
-	/* Early release so we can unregister the device */
+	/* We can be invoked by both explicit vport deletion and
+	 * underlying netdev deregistration; delete the link only
+	 * if it's not already shutting down.
+	 */
+	if (vport->dev->reg_state == NETREG_REGISTERED)
+		rtnl_delete_link(vport->dev);
 	dev_put(vport->dev);
-	rtnl_delete_link(vport->dev);
 	vport->dev = NULL;
 	rtnl_unlock();
 
-- 
2.1.0


From d6c39cbd9479fcce790b2381042c9405fc170384 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 1 Dec 2015 20:08:51 -0800
Subject: [PATCH 43/43] net_sched: fix qdisc_tree_decrease_qlen() races

[ Upstream commit 4eaf3b84f2881c9c028f1d5e76c52ab575fe3a66 ]

qdisc_tree_decrease_qlen() suffers from two problems on multiqueue
devices.

One problem is that it updates sch->q.qlen and sch->qstats.drops
on the mq/mqprio root qdisc, while it should not : Daniele
reported underflows errors :
[  681.774821] PAX: sch->q.qlen: 0 n: 1
[  681.774825] PAX: size overflow detected in function qdisc_tree_decrease_qlen net/sched/sch_api.c:769 cicus.693_49 min, count: 72, decl: qlen; num: 0; context: sk_buff_head;
[  681.774954] CPU: 2 PID: 19 Comm: ksoftirqd/2 Tainted: G           O    4.2.6.201511282239-1-grsec #1
[  681.774955] Hardware name: ASUSTeK COMPUTER INC. X302LJ/X302LJ, BIOS X302LJ.202 03/05/2015
[  681.774956]  ffffffffa9a04863 0000000000000000 0000000000000000 ffffffffa990ff7c
[  681.774959]  ffffc90000d3bc38 ffffffffa95d2810 0000000000000007 ffffffffa991002b
[  681.774960]  ffffc90000d3bc68 ffffffffa91a44f4 0000000000000001 0000000000000001
[  681.774962] Call Trace:
[  681.774967]  [<ffffffffa95d2810>] dump_stack+0x4c/0x7f
[  681.774970]  [<ffffffffa91a44f4>] report_size_overflow+0x34/0x50
[  681.774972]  [<ffffffffa94d17e2>] qdisc_tree_decrease_qlen+0x152/0x160
[  681.774976]  [<ffffffffc02694b1>] fq_codel_dequeue+0x7b1/0x820 [sch_fq_codel]
[  681.774978]  [<ffffffffc02680a0>] ? qdisc_peek_dequeued+0xa0/0xa0 [sch_fq_codel]
[  681.774980]  [<ffffffffa94cd92d>] __qdisc_run+0x4d/0x1d0
[  681.774983]  [<ffffffffa949b2b2>] net_tx_action+0xc2/0x160
[  681.774985]  [<ffffffffa90664c1>] __do_softirq+0xf1/0x200
[  681.774987]  [<ffffffffa90665ee>] run_ksoftirqd+0x1e/0x30
[  681.774989]  [<ffffffffa90896b0>] smpboot_thread_fn+0x150/0x260
[  681.774991]  [<ffffffffa9089560>] ? sort_range+0x40/0x40
[  681.774992]  [<ffffffffa9085fe4>] kthread+0xe4/0x100
[  681.774994]  [<ffffffffa9085f00>] ? kthread_worker_fn+0x170/0x170
[  681.774995]  [<ffffffffa95d8d1e>] ret_from_fork+0x3e/0x70

mq/mqprio have their own ways to report qlen/drops by folding stats on
all their queues, with appropriate locking.

A second problem is that qdisc_tree_decrease_qlen() calls qdisc_lookup()
without proper locking : concurrent qdisc updates could corrupt the list
that qdisc_match_from_root() parses to find a qdisc given its handle.

Fix first problem adding a TCQ_F_NOPARENT qdisc flag that
qdisc_tree_decrease_qlen() can use to abort its tree traversal,
as soon as it meets a mq/mqprio qdisc children.

Second problem can be fixed by RCU protection.
Qdisc are already freed after RCU grace period, so qdisc_list_add() and
qdisc_list_del() simply have to use appropriate rcu list variants.

A future patch will add a per struct netdev_queue list anchor, so that
qdisc_tree_decrease_qlen() can have more efficient lookups.

Reported-by: Daniele Fucini <dfucini@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Cong Wang <cwang@twopensource.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h |  3 +++
 net/sched/sch_api.c       | 27 ++++++++++++++++++---------
 net/sched/sch_generic.c   |  2 +-
 net/sched/sch_mq.c        |  4 ++--
 net/sched/sch_mqprio.c    |  4 ++--
 5 files changed, 26 insertions(+), 14 deletions(-)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 444faa8..f1ad8f8 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -61,6 +61,9 @@ struct Qdisc {
 				      */
 #define TCQ_F_WARN_NONWC	(1 << 16)
 #define TCQ_F_CPUSTATS		0x20 /* run using percpu statistics */
+#define TCQ_F_NOPARENT		0x40 /* root of its hierarchy :
+				      * qdisc_tree_decrease_qlen() should stop.
+				      */
 	u32			limit;
 	const struct Qdisc_ops	*ops;
 	struct qdisc_size_table	__rcu *stab;
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index f43c8f3..7ec667d 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -253,7 +253,8 @@ int qdisc_set_default(const char *name)
 }
 
 /* We know handle. Find qdisc among all qdisc's attached to device
-   (root qdisc, all its children, children of children etc.)
+ * (root qdisc, all its children, children of children etc.)
+ * Note: caller either uses rtnl or rcu_read_lock()
  */
 
 static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle)
@@ -264,7 +265,7 @@ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle)
 	    root->handle == handle)
 		return root;
 
-	list_for_each_entry(q, &root->list, list) {
+	list_for_each_entry_rcu(q, &root->list, list) {
 		if (q->handle == handle)
 			return q;
 	}
@@ -277,15 +278,18 @@ void qdisc_list_add(struct Qdisc *q)
 		struct Qdisc *root = qdisc_dev(q)->qdisc;
 
 		WARN_ON_ONCE(root == &noop_qdisc);
-		list_add_tail(&q->list, &root->list);
+		ASSERT_RTNL();
+		list_add_tail_rcu(&q->list, &root->list);
 	}
 }
 EXPORT_SYMBOL(qdisc_list_add);
 
 void qdisc_list_del(struct Qdisc *q)
 {
-	if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS))
-		list_del(&q->list);
+	if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) {
+		ASSERT_RTNL();
+		list_del_rcu(&q->list);
+	}
 }
 EXPORT_SYMBOL(qdisc_list_del);
 
@@ -750,14 +754,18 @@ void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
 	if (n == 0)
 		return;
 	drops = max_t(int, n, 0);
+	rcu_read_lock();
 	while ((parentid = sch->parent)) {
 		if (TC_H_MAJ(parentid) == TC_H_MAJ(TC_H_INGRESS))
-			return;
+			break;
 
+		if (sch->flags & TCQ_F_NOPARENT)
+			break;
+		/* TODO: perform the search on a per txq basis */
 		sch = qdisc_lookup(qdisc_dev(sch), TC_H_MAJ(parentid));
 		if (sch == NULL) {
-			WARN_ON(parentid != TC_H_ROOT);
-			return;
+			WARN_ON_ONCE(parentid != TC_H_ROOT);
+			break;
 		}
 		cops = sch->ops->cl_ops;
 		if (cops->qlen_notify) {
@@ -768,6 +776,7 @@ void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
 		sch->q.qlen -= n;
 		__qdisc_qstats_drop(sch, drops);
 	}
+	rcu_read_unlock();
 }
 EXPORT_SYMBOL(qdisc_tree_decrease_qlen);
 
@@ -941,7 +950,7 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue,
 		}
 		lockdep_set_class(qdisc_lock(sch), &qdisc_tx_lock);
 		if (!netif_is_multiqueue(dev))
-			sch->flags |= TCQ_F_ONETXQUEUE;
+			sch->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
 	}
 
 	sch->handle = handle;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index cb5d4ad..e82a1ad 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -737,7 +737,7 @@ static void attach_one_default_qdisc(struct net_device *dev,
 		return;
 	}
 	if (!netif_is_multiqueue(dev))
-		qdisc->flags |= TCQ_F_ONETXQUEUE;
+		qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
 	dev_queue->qdisc_sleeping = qdisc;
 }
 
diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
index f3cbaec..3e82f04 100644
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -63,7 +63,7 @@ static int mq_init(struct Qdisc *sch, struct nlattr *opt)
 		if (qdisc == NULL)
 			goto err;
 		priv->qdiscs[ntx] = qdisc;
-		qdisc->flags |= TCQ_F_ONETXQUEUE;
+		qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
 	}
 
 	sch->flags |= TCQ_F_MQROOT;
@@ -156,7 +156,7 @@ static int mq_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new,
 
 	*old = dev_graft_qdisc(dev_queue, new);
 	if (new)
-		new->flags |= TCQ_F_ONETXQUEUE;
+		new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
 	if (dev->flags & IFF_UP)
 		dev_activate(dev);
 	return 0;
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index 3811a74..ad70ecf 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -132,7 +132,7 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt)
 			goto err;
 		}
 		priv->qdiscs[i] = qdisc;
-		qdisc->flags |= TCQ_F_ONETXQUEUE;
+		qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
 	}
 
 	/* If the mqprio options indicate that hardware should own
@@ -209,7 +209,7 @@ static int mqprio_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new,
 	*old = dev_graft_qdisc(dev_queue, new);
 
 	if (new)
-		new->flags |= TCQ_F_ONETXQUEUE;
+		new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
 
 	if (dev->flags & IFF_UP)
 		dev_activate(dev);
-- 
2.1.0

Re: [PATCHES] Networking

[Greg KH]

On Thu, Dec 10, 2015 at 02:37:58PM -0500, David Miller wrote:
> 
> Please queue up the following networking bug fixes for 3.18, 4.1, 4.2,
> and 4.3 -stable, respectively.

All queued up now, thanks.

Note, this is going to be the last 4.2-stable kernel release, so no need
to do any more networking stable patches for it.

thanks again,

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 102 bytes --]


Please queue up the following bug fixes for 3.18.x, 4.1.x, and
4.3.x -stable, respectively.

Thanks!

[-- Attachment #2: net_318.mbox --]
[-- Type: Application/Octet-Stream, Size: 32638 bytes --]

From 3e5546bb864b08b6b73701a8602a58a51c3d6dba Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Thu, 3 Dec 2015 17:21:50 +0100
Subject: [PATCH 01/16] gre6: allow to update all parameters via rtnl

[ Upstream commit 6a61d4dbf4f54b5683e0f1e58d873cecca7cb977 ]

Parameters were updated only if the kernel was unable to find the tunnel
with the new parameters, ie only if core pamareters were updated (keys,
addr, link, type).
Now it's possible to update ttl, hoplimit, flowinfo and flags.

Fixes: c12b395a4664 ("gre: Support GRE over IPv6")
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 28d7a24..25cd22c 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1563,13 +1563,11 @@ static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[],
 			return -EEXIST;
 	} else {
 		t = nt;
-
-		ip6gre_tunnel_unlink(ign, t);
-		ip6gre_tnl_change(t, &p, !tb[IFLA_MTU]);
-		ip6gre_tunnel_link(ign, t);
-		netdev_state_change(dev);
 	}
 
+	ip6gre_tunnel_unlink(ign, t);
+	ip6gre_tnl_change(t, &p, !tb[IFLA_MTU]);
+	ip6gre_tunnel_link(ign, t);
 	return 0;
 }
 
-- 
2.4.1


From bb71a28815f5a4ddaa086965e4c24774d571d801 Mon Sep 17 00:00:00 2001
From: Pavel Machek <pavel@ucw.cz>
Date: Fri, 4 Dec 2015 09:50:00 +0100
Subject: [PATCH 02/16] atl1c: Improve driver not to do order 4 GFP_ATOMIC
 allocation

[ Upstream commit f2a3771ae8aca879c32336c76ad05a017629bae2 ]

atl1c driver is doing order-4 allocation with GFP_ATOMIC
priority. That often breaks  networking after resume. Switch to
GFP_KERNEL. Still not ideal, but should be significantly better.

atl1c_setup_ring_resources() is called from .open() function, and
already uses GFP_KERNEL, so this change is safe.

Signed-off-by: Pavel Machek <pavel@ucw.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/atheros/atl1c/atl1c_main.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index 72fb86b..067f2cb 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -1014,13 +1014,12 @@ static int atl1c_setup_ring_resources(struct atl1c_adapter *adapter)
 		sizeof(struct atl1c_recv_ret_status) * rx_desc_count +
 		8 * 4;
 
-	ring_header->desc = pci_alloc_consistent(pdev, ring_header->size,
-				&ring_header->dma);
+	ring_header->desc = dma_zalloc_coherent(&pdev->dev, ring_header->size,
+						&ring_header->dma, GFP_KERNEL);
 	if (unlikely(!ring_header->desc)) {
-		dev_err(&pdev->dev, "pci_alloc_consistend failed\n");
+		dev_err(&pdev->dev, "could not get memory for DMA buffer\n");
 		goto err_nomem;
 	}
-	memset(ring_header->desc, 0, ring_header->size);
 	/* init TPD ring */
 
 	tpd_ring[0].dma = roundup(ring_header->dma, 8);
-- 
2.4.1


From c045ea423c3eb0da851b2e70c6612fad57fdabf4 Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Fri, 4 Dec 2015 15:14:03 -0200
Subject: [PATCH 03/16] sctp: use the same clock as if sock source timestamps
 were on

[ Upstream commit cb5e173ed7c03a0d4630ce68a95a186cce3cc872 ]

SCTP echoes a cookie o INIT ACK chunks that contains a timestamp, for
detecting stale cookies. This cookie is echoed back to the server by the
client and then that timestamp is checked.

Thing is, if the listening socket is using packet timestamping, the
cookie is encoded with ktime_get() value and checked against
ktime_get_real(), as done by __net_timestamp().

The fix is to sctp also use ktime_get_real(), so we can compare bananas
with bananas later no matter if packet timestamping was enabled or not.

Fixes: 52db882f3fc2 ("net: sctp: migrate cookie life from timeval to ktime")
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sm_make_chunk.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 371a152..642c115 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -1652,7 +1652,7 @@ static sctp_cookie_param_t *sctp_pack_cookie(const struct sctp_endpoint *ep,
 
 	/* Set an expiration time for the cookie.  */
 	cookie->c.expiration = ktime_add(asoc->cookie_life,
-					 ktime_get());
+					 ktime_get_real());
 
 	/* Copy the peer's init packet.  */
 	memcpy(&cookie->c.peer_init[0], init_chunk->chunk_hdr,
@@ -1780,7 +1780,7 @@ no_hmac:
 	if (sock_flag(ep->base.sk, SOCK_TIMESTAMP))
 		kt = skb_get_ktime(skb);
 	else
-		kt = ktime_get();
+		kt = ktime_get_real();
 
 	if (!asoc && ktime_before(bear_cookie->expiration, kt)) {
 		/*
-- 
2.4.1


From ecabc55d2cbab6c4172e5dc89a0196c561af4491 Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Fri, 4 Dec 2015 15:14:04 -0200
Subject: [PATCH 04/16] sctp: update the netstamp_needed counter when copying
 sockets

[ Upstream commit 01ce63c90170283a9855d1db4fe81934dddce648 ]

Dmitry Vyukov reported that SCTP was triggering a WARN on socket destroy
related to disabling sock timestamp.

When SCTP accepts an association or peel one off, it copies sock flags
but forgot to call net_enable_timestamp() if a packet timestamping flag
was copied, leading to extra calls to net_disable_timestamp() whenever
such clones were closed.

The fix is to call net_enable_timestamp() whenever we copy a sock with
that flag on, like tcp does.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h | 2 ++
 net/core/sock.c    | 2 --
 net/sctp/socket.c  | 3 +++
 3 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index a098ce3..bc50326 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -715,6 +715,8 @@ enum sock_flags {
 	SOCK_SELECT_ERR_QUEUE, /* Wake select on error queue */
 };
 
+#define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))
+
 static inline void sock_copy_flags(struct sock *nsk, struct sock *osk)
 {
 	nsk->sk_flags = osk->sk_flags;
diff --git a/net/core/sock.c b/net/core/sock.c
index 1e5130d..1c4fe8b 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -422,8 +422,6 @@ static void sock_warn_obsolete_bsdism(const char *name)
 	}
 }
 
-#define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))
-
 static void sock_disable_timestamp(struct sock *sk, unsigned long flags)
 {
 	if (sk->sk_flags & flags) {
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index fb082aa..3f4d09d 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -7213,6 +7213,9 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk,
 	newinet->mc_ttl = 1;
 	newinet->mc_index = 0;
 	newinet->mc_list = NULL;
+
+	if (newsk->sk_flags & SK_FLAGS_TIMESTAMP)
+		net_enable_timestamp();
 }
 
 static inline void sctp_copy_descendant(struct sock *sk_to,
-- 
2.4.1


From 6e4acecf56135744b7d9bedbaf2546fc199856b7 Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Fri, 4 Dec 2015 15:14:05 -0200
Subject: [PATCH 05/16] sctp: also copy sk_tsflags when copying the socket

[ Upstream commit 50a5ffb1ef535e3c6989711c51b5d61b543a3b45 ]

As we are keeping timestamps on when copying the socket, we also have to
copy sk_tsflags.

This is needed since b9f40e21ef42 ("net-timestamp: move timestamp flags
out of sk_flags").

Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 3f4d09d..4130c1b 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -7181,6 +7181,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk,
 	newsk->sk_type = sk->sk_type;
 	newsk->sk_bound_dev_if = sk->sk_bound_dev_if;
 	newsk->sk_flags = sk->sk_flags;
+	newsk->sk_tsflags = sk->sk_tsflags;
 	newsk->sk_no_check_tx = sk->sk_no_check_tx;
 	newsk->sk_no_check_rx = sk->sk_no_check_rx;
 	newsk->sk_reuse = sk->sk_reuse;
-- 
2.4.1


From 564838f6c14065e36e3fadefe6438a1631f25846 Mon Sep 17 00:00:00 2001
From: Stefan Wahren <stefan.wahren@i2se.com>
Date: Fri, 4 Dec 2015 16:29:10 +0100
Subject: [PATCH 06/16] net: qca_spi: fix transmit queue timeout handling

[ Upstream commit ed7d42e24effbd3681e909711a7a2119a85e9217 ]

In case of a tx queue timeout every transmit is blocked until the
QCA7000 resets himself and triggers a sync which makes the driver
flushs the tx ring. So avoid this blocking situation by triggering
the sync immediately after the timeout. Waking the queue doesn't
make sense in this situation.

Signed-off-by: Stefan Wahren <stefan.wahren@i2se.com>
Fixes: 291ab06ecf67 ("net: qualcomm: new Ethernet over SPI driver for QCA7000")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qualcomm/qca_spi.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c
index 2c811f6..f77b589 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.c
+++ b/drivers/net/ethernet/qualcomm/qca_spi.c
@@ -737,9 +737,8 @@ qcaspi_netdev_tx_timeout(struct net_device *dev)
 	netdev_info(qca->net_dev, "Transmit timeout at %ld, latency %ld\n",
 		    jiffies, jiffies - dev->trans_start);
 	qca->net_dev->stats.tx_errors++;
-	/* wake the queue if there is room */
-	if (qcaspi_tx_ring_has_space(&qca->txr))
-		netif_wake_queue(dev);
+	/* Trigger tx queue flush and QCA7000 reset */
+	qca->sync = QCASPI_SYNC_UNKNOWN;
 }
 
 static int
-- 
2.4.1


From 7280c7ceed331db91a11ecb2a702068793acff21 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 9 Dec 2015 07:25:06 -0800
Subject: [PATCH 07/16] ipv6: sctp: clone options to avoid use after free

[ Upstream commit 9470e24f35ab81574da54e69df90c1eb4a96b43f ]

SCTP is lacking proper np->opt cloning at accept() time.

TCP and DCCP use ipv6_dup_options() helper, do the same
in SCTP.

We might later factorize this code in a common helper to avoid
future mistakes.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ipv6.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 0e4198e..3267a5c 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -634,6 +634,7 @@ static struct sock *sctp_v6_create_accept_sk(struct sock *sk,
 	struct sock *newsk;
 	struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
 	struct sctp6_sock *newsctp6sk;
+	struct ipv6_txoptions *opt;
 
 	newsk = sk_alloc(sock_net(sk), PF_INET6, GFP_KERNEL, sk->sk_prot);
 	if (!newsk)
@@ -653,6 +654,13 @@ static struct sock *sctp_v6_create_accept_sk(struct sock *sk,
 
 	memcpy(newnp, np, sizeof(struct ipv6_pinfo));
 
+	rcu_read_lock();
+	opt = rcu_dereference(np->opt);
+	if (opt)
+		opt = ipv6_dup_options(newsk, opt);
+	RCU_INIT_POINTER(newnp->opt, opt);
+	rcu_read_unlock();
+
 	/* Initialize sk's sport, dport, rcv_saddr and daddr for getsockname()
 	 * and getpeername().
 	 */
-- 
2.4.1


From c68b97e0e6f2f5eafaa0cbffd50c6339f33f5a22 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Mon, 14 Dec 2015 22:03:39 +0100
Subject: [PATCH 08/16] net: add validation for the socket syscall protocol
 argument
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 79462ad02e861803b3840cc782248c7359451cd9 ]

郭永刚 reported that one could simply crash the kernel as root by
using a simple program:

	int socket_fd;
	struct sockaddr_in addr;
	addr.sin_port = 0;
	addr.sin_addr.s_addr = INADDR_ANY;
	addr.sin_family = 10;

	socket_fd = socket(10,3,0x40000000);
	connect(socket_fd , &addr,16);

AF_INET, AF_INET6 sockets actually only support 8-bit protocol
identifiers. inet_sock's skc_protocol field thus is sized accordingly,
thus larger protocol identifiers simply cut off the higher bits and
store a zero in the protocol fields.

This could lead to e.g. NULL function pointer because as a result of
the cut off inet_num is zero and we call down to inet_autobind, which
is NULL for raw sockets.

kernel: Call Trace:
kernel:  [<ffffffff816db90e>] ? inet_autobind+0x2e/0x70
kernel:  [<ffffffff816db9a4>] inet_dgram_connect+0x54/0x80
kernel:  [<ffffffff81645069>] SYSC_connect+0xd9/0x110
kernel:  [<ffffffff810ac51b>] ? ptrace_notify+0x5b/0x80
kernel:  [<ffffffff810236d8>] ? syscall_trace_enter_phase2+0x108/0x200
kernel:  [<ffffffff81645e0e>] SyS_connect+0xe/0x10
kernel:  [<ffffffff81779515>] tracesys_phase2+0x84/0x89

I found no particular commit which introduced this problem.

CVE: CVE-2015-8543
Cc: Cong Wang <cwang@twopensource.com>
Reported-by: 郭永刚 <guoyonggang@360.cn>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h     | 1 +
 net/ax25/af_ax25.c     | 3 +++
 net/decnet/af_decnet.c | 3 +++
 net/ipv4/af_inet.c     | 3 +++
 net/ipv6/af_inet6.c    | 3 +++
 net/irda/af_irda.c     | 3 +++
 6 files changed, 16 insertions(+)

diff --git a/include/net/sock.h b/include/net/sock.h
index bc50326..2b12e04 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -379,6 +379,7 @@ struct sock {
 				sk_no_check_rx : 1,
 				sk_userlocks : 4,
 				sk_protocol  : 8,
+#define SK_PROTOCOL_MAX U8_MAX
 				sk_type      : 16;
 	kmemcheck_bitfield_end(flags);
 	int			sk_wmem_queued;
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index c35c3f4..1428c3f 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -806,6 +806,9 @@ static int ax25_create(struct net *net, struct socket *sock, int protocol,
 	struct sock *sk;
 	ax25_cb *ax25;
 
+	if (protocol < 0 || protocol > SK_PROTOCOL_MAX)
+		return -EINVAL;
+
 	if (!net_eq(net, &init_net))
 		return -EAFNOSUPPORT;
 
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 25733d5..2aeeb4f 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -678,6 +678,9 @@ static int dn_create(struct net *net, struct socket *sock, int protocol,
 {
 	struct sock *sk;
 
+	if (protocol < 0 || protocol > SK_PROTOCOL_MAX)
+		return -EINVAL;
+
 	if (!net_eq(net, &init_net))
 		return -EAFNOSUPPORT;
 
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 9a17357..6cf020e 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -259,6 +259,9 @@ static int inet_create(struct net *net, struct socket *sock, int protocol,
 	int try_loading_module = 0;
 	int err;
 
+	if (protocol < 0 || protocol >= IPPROTO_MAX)
+		return -EINVAL;
+
 	sock->state = SS_UNCONNECTED;
 
 	/* Look for the requested type/protocol pair. */
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 05417c3..ad95905 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -109,6 +109,9 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol,
 	int try_loading_module = 0;
 	int err;
 
+	if (protocol < 0 || protocol >= IPPROTO_MAX)
+		return -EINVAL;
+
 	/* Look for the requested type/protocol pair. */
 lookup_protocol:
 	err = -ESOCKTNOSUPPORT;
diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index 3f3a6cb..b3f6ec0 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -1100,6 +1100,9 @@ static int irda_create(struct net *net, struct socket *sock, int protocol,
 
 	IRDA_DEBUG(2, "%s()\n", __func__);
 
+	if (protocol < 0 || protocol > SK_PROTOCOL_MAX)
+		return -EINVAL;
+
 	if (net != &init_net)
 		return -EAFNOSUPPORT;
 
-- 
2.4.1


From 176194f6f059ec6d5ad489a68060ebe8057fdbbc Mon Sep 17 00:00:00 2001
From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Date: Fri, 4 Dec 2015 01:45:40 +0300
Subject: [PATCH 09/16] sh_eth: fix kernel oops in skb_put()

[ Upstream commit 248be83dcb3feb3f6332eb3d010a016402138484 ]

In a low memory situation the following kernel oops occurs:

Unable to handle kernel NULL pointer dereference at virtual address 00000050
pgd = 8490c000
[00000050] *pgd=4651e831, *pte=00000000, *ppte=00000000
Internal error: Oops: 17 [#1] PREEMPT ARM
Modules linked in:
CPU: 0    Not tainted  (3.4-at16 #9)
PC is at skb_put+0x10/0x98
LR is at sh_eth_poll+0x2c8/0xa10
pc : [<8035f780>]    lr : [<8028bf50>]    psr: 60000113
sp : 84eb1a90  ip : 84eb1ac8  fp : 84eb1ac4
r10: 0000003f  r9 : 000005ea  r8 : 00000000
r7 : 00000000  r6 : 940453b0  r5 : 00030000  r4 : 9381b180
r3 : 00000000  r2 : 00000000  r1 : 000005ea  r0 : 00000000
Flags: nZCv  IRQs on  FIQs on  Mode SVC_32  ISA ARM  Segment user
Control: 10c53c7d  Table: 4248c059  DAC: 00000015
Process klogd (pid: 2046, stack limit = 0x84eb02e8)
[...]

This is  because netdev_alloc_skb() fails and 'mdp->rx_skbuff[entry]' is left
NULL but sh_eth_rx() later  uses it without checking.  Add such check...

Reported-by: Yasushi SHOJI <yashi@atmark-techno.com>
Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/sh_eth.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index b5db6b3..b474dbf 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -1417,6 +1417,7 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota)
 		if (mdp->cd->shift_rd0)
 			desc_status >>= 16;
 
+		skb = mdp->rx_skbuff[entry];
 		if (desc_status & (RD_RFS1 | RD_RFS2 | RD_RFS3 | RD_RFS4 |
 				   RD_RFS5 | RD_RFS6 | RD_RFS10)) {
 			ndev->stats.rx_errors++;
@@ -1432,12 +1433,11 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota)
 				ndev->stats.rx_missed_errors++;
 			if (desc_status & RD_RFS10)
 				ndev->stats.rx_over_errors++;
-		} else {
+		} else	if (skb) {
 			if (!mdp->cd->hw_swap)
 				sh_eth_soft_swap(
 					phys_to_virt(ALIGN(rxdesc->addr, 4)),
 					pkt_len + 2);
-			skb = mdp->rx_skbuff[entry];
 			mdp->rx_skbuff[entry] = NULL;
 			if (mdp->cd->rpadir)
 				skb_reserve(skb, NET_IP_ALIGN);
-- 
2.4.1


From 9148e98d916c3b359968b29adc7860587aa426e5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 14 Dec 2015 14:08:53 -0800
Subject: [PATCH 10/16] net: fix IP early demux races

[ Upstream commit 5037e9ef9454917b047f9f3a19b4dd179fbf7cd4 ]

David Wilder reported crashes caused by dst reuse.

<quote David>
  I am seeing a crash on a distro V4.2.3 kernel caused by a double
  release of a dst_entry.  In ipv4_dst_destroy() the call to
  list_empty() finds a poisoned next pointer, indicating the dst_entry
  has already been removed from the list and freed. The crash occurs
  18 to 24 hours into a run of a network stress exerciser.
</quote>

Thanks to his detailed report and analysis, we were able to understand
the core issue.

IP early demux can associate a dst to skb, after a lookup in TCP/UDP
sockets.

When socket cache is not properly set, we want to store into
sk->sk_dst_cache the dst for future IP early demux lookups,
by acquiring a stable refcount on the dst.

Problem is this acquisition is simply using an atomic_inc(),
which works well, unless the dst was queued for destruction from
dst_release() noticing dst refcount went to zero, if DST_NOCACHE
was set on dst.

We need to make sure current refcount is not zero before incrementing
it, or risk double free as David reported.

This patch, being a stable candidate, adds two new helpers, and use
them only from IP early demux problematic paths.

It might be possible to merge in net-next skb_dst_force() and
skb_dst_force_safe(), but I prefer having the smallest patch for stable
kernels : Maybe some skb_dst_force() callers do not expect skb->dst
can suddenly be cleared.

Can probably be backported back to linux-3.6 kernels

Reported-by: David J. Wilder <dwilder@us.ibm.com>
Tested-by: David J. Wilder <dwilder@us.ibm.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst.h   | 33 +++++++++++++++++++++++++++++++++
 include/net/sock.h  |  2 +-
 net/ipv4/tcp_ipv4.c |  5 ++---
 net/ipv6/tcp_ipv6.c |  3 +--
 4 files changed, 37 insertions(+), 6 deletions(-)

diff --git a/include/net/dst.h b/include/net/dst.h
index 0fb99a2..182b812 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -312,6 +312,39 @@ static inline void skb_dst_force(struct sk_buff *skb)
 	}
 }
 
+/**
+ * dst_hold_safe - Take a reference on a dst if possible
+ * @dst: pointer to dst entry
+ *
+ * This helper returns false if it could not safely
+ * take a reference on a dst.
+ */
+static inline bool dst_hold_safe(struct dst_entry *dst)
+{
+	if (dst->flags & DST_NOCACHE)
+		return atomic_inc_not_zero(&dst->__refcnt);
+	dst_hold(dst);
+	return true;
+}
+
+/**
+ * skb_dst_force_safe - makes sure skb dst is refcounted
+ * @skb: buffer
+ *
+ * If dst is not yet refcounted and not destroyed, grab a ref on it.
+ */
+static inline void skb_dst_force_safe(struct sk_buff *skb)
+{
+	if (skb_dst_is_noref(skb)) {
+		struct dst_entry *dst = skb_dst(skb);
+
+		if (!dst_hold_safe(dst))
+			dst = NULL;
+
+		skb->_skb_refdst = (unsigned long)dst;
+	}
+}
+
 
 /**
  *	__skb_tunnel_rx - prepare skb for rx reinsert
diff --git a/include/net/sock.h b/include/net/sock.h
index 2b12e04..a40bc8c 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -792,7 +792,7 @@ void sk_stream_write_space(struct sock *sk);
 static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb)
 {
 	/* dont let skb dst not refcounted, we are going to leave rcu lock */
-	skb_dst_force(skb);
+	skb_dst_force_safe(skb);
 
 	if (!sk->sk_backlog.tail)
 		sk->sk_backlog.head = skb;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 6cd9f69..5d53902 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1553,7 +1553,7 @@ bool tcp_prequeue(struct sock *sk, struct sk_buff *skb)
 	if (likely(sk->sk_rx_dst))
 		skb_dst_drop(skb);
 	else
-		skb_dst_force(skb);
+		skb_dst_force_safe(skb);
 
 	__skb_queue_tail(&tp->ucopy.prequeue, skb);
 	tp->ucopy.memory += skb->truesize;
@@ -1758,8 +1758,7 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
 
-	if (dst) {
-		dst_hold(dst);
+	if (dst && dst_hold_safe(dst)) {
 		sk->sk_rx_dst = dst;
 		inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
 	}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 26feadd..b5a4ac8 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -93,10 +93,9 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
 
-	if (dst) {
+	if (dst && dst_hold_safe(dst)) {
 		const struct rt6_info *rt = (const struct rt6_info *)dst;
 
-		dst_hold(dst);
 		sk->sk_rx_dst = dst;
 		inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
 		if (rt->rt6i_node)
-- 
2.4.1


From 7a44d80f9835c5381e7edbd0897a8c7c7616c9ad Mon Sep 17 00:00:00 2001
From: Vlad Yasevich <vyasevich@gmail.com>
Date: Mon, 16 Nov 2015 15:43:44 -0500
Subject: [PATCH 11/16] vlan: Fix untag operations of stacked vlans with
 REORDER_HEADER off

[ Upstream commit a6e18ff111701b4ff6947605bfbe9594ec42a6e8 ]

When we have multiple stacked vlan devices all of which have
turned off REORDER_HEADER flag, the untag operation does not
locate the ethernet addresses correctly for nested vlans.
The reason is that in case of REORDER_HEADER flag being off,
the outer vlan headers are put back and the mac_len is adjusted
to account for the presense of the header.  Then, the subsequent
untag operation, for the next level vlan, always use VLAN_ETH_HLEN
to locate the begining of the ethernet header and that ends up
being a multiple of 4 bytes short of the actuall beginning
of the mac header (the multiple depending on the how many vlan
encapsulations ethere are).

As a reslult, if there are multiple levles of vlan devices
with REODER_HEADER being off, the recevied packets end up
being dropped.

To solve this, we use skb->mac_len as the offset.  The value
is always set on receive path and starts out as a ETH_HLEN.
The value is also updated when the vlan header manupations occur
so we know it will be correct.

Signed-off-by: Vladislav Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index ea0bcc4..7c7b2c0 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4108,7 +4108,8 @@ static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb)
 		return NULL;
 	}
 
-	memmove(skb->data - ETH_HLEN, skb->data - VLAN_ETH_HLEN, 2 * ETH_ALEN);
+	memmove(skb->data - ETH_HLEN, skb->data - skb->mac_len,
+		2 * ETH_ALEN);
 	skb->mac_header += VLAN_HLEN;
 	return skb;
 }
-- 
2.4.1


From ad94844e58f626e019f48c1290db27998935130c Mon Sep 17 00:00:00 2001
From: Vlad Yasevich <vyasevich@gmail.com>
Date: Mon, 14 Dec 2015 17:44:10 -0500
Subject: [PATCH 12/16] skbuff: Fix offset error in skb_reorder_vlan_header

[ Upstream commit f654861569872d10dcb79d9d7ca219b316f94ff0 ]

skb_reorder_vlan_header is called after the vlan header has
been pulled.  As a result the offset of the begining of
the mac header has been incrased by 4 bytes (VLAN_HLEN).
When moving the mac addresses, include this incrase in
the offset calcualation so that the mac addresses are
copied correctly.

Fixes: a6e18ff1117 (vlan: Fix untag operations of stacked vlans with REORDER_HEADER off)
CC: Nicolas Dichtel <nicolas.dichtel@6wind.com>
CC: Patrick McHardy <kaber@trash.net>
Signed-off-by: Vladislav Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 7c7b2c0..e9d5556 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4108,7 +4108,7 @@ static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb)
 		return NULL;
 	}
 
-	memmove(skb->data - ETH_HLEN, skb->data - skb->mac_len,
+	memmove(skb->data - ETH_HLEN, skb->data - skb->mac_len - VLAN_HLEN,
 		2 * ETH_ALEN);
 	skb->mac_header += VLAN_HLEN;
 	return skb;
-- 
2.4.1


From a1c89970d52edd564e7d0e2d74d70e309ef7ccb9 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Mon, 14 Dec 2015 13:48:36 -0800
Subject: [PATCH 13/16] pptp: verify sockaddr_len in pptp_bind() and
 pptp_connect()

[ Upstream commit 09ccfd238e5a0e670d8178cf50180ea81ae09ae1 ]

Reported-by: Dmitry Vyukov <dvyukov@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pptp.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index 1dc628f..0710214 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -420,6 +420,9 @@ static int pptp_bind(struct socket *sock, struct sockaddr *uservaddr,
 	struct pptp_opt *opt = &po->proto.pptp;
 	int error = 0;
 
+	if (sockaddr_len < sizeof(struct sockaddr_pppox))
+		return -EINVAL;
+
 	lock_sock(sk);
 
 	opt->src_addr = sp->sa_addr.pptp;
@@ -441,6 +444,9 @@ static int pptp_connect(struct socket *sock, struct sockaddr *uservaddr,
 	struct flowi4 fl4;
 	int error = 0;
 
+	if (sockaddr_len < sizeof(struct sockaddr_pppox))
+		return -EINVAL;
+
 	if (sp->sa_protocol != PX_PROTO_PPTP)
 		return -EINVAL;
 
-- 
2.4.1


From b114934ecc31b981bd0be12cbb3d4bd9a0f2888f Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 15 Dec 2015 15:39:08 -0500
Subject: [PATCH 14/16] bluetooth: Validate socket address length in
 sco_sock_bind().

[ Upstream commit 5233252fce714053f0151680933571a2da9cbfb4 ]

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bluetooth/sco.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 7ee9e4a..b3ef78a 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -520,6 +520,9 @@ static int sco_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_le
 	if (!addr || addr->sa_family != AF_BLUETOOTH)
 		return -EINVAL;
 
+	if (addr_len < sizeof(struct sockaddr_sco))
+		return -EINVAL;
+
 	lock_sock(sk);
 
 	if (sk->sk_state != BT_OPEN) {
-- 
2.4.1


From 1f5796c606937bf1e0b4aacfe2c48f5b18c64a94 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Tue, 15 Dec 2015 21:01:53 +0100
Subject: [PATCH 15/16] fou: clean up socket with kfree_rcu

[ Upstream commit 3036facbb7be3a169e35be3b271162b0fa564a2d ]

fou->udp_offloads is managed by RCU. As it is actually included inside
the fou sockets, we cannot let the memory go out of scope before a grace
period. We either can synchronize_rcu or switch over to kfree_rcu to
manage the sockets. kfree_rcu seems appropriate as it is used by vxlan
and geneve.

Fixes: 23461551c00628c ("fou: Support for foo-over-udp RX path")
Cc: Tom Herbert <tom@herbertland.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fou.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 606c520..8ce8e82 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -25,6 +25,7 @@ struct fou {
 	u16 port;
 	struct udp_offload udp_offloads;
 	struct list_head list;
+	struct rcu_head rcu;
 };
 
 struct fou_cfg {
@@ -287,7 +288,7 @@ static void fou_release(struct fou *fou)
 
 	sock_release(sock);
 
-	kfree(fou);
+	kfree_rcu(fou, rcu);
 }
 
 static int fou_encap_init(struct sock *sk, struct fou *fou, struct fou_cfg *cfg)
-- 
2.4.1


From 92b0c7beee483158e48963a562875f6b0c671543 Mon Sep 17 00:00:00 2001
From: Rainer Weikusat <rweikusat@mobileactivedefense.com>
Date: Wed, 16 Dec 2015 20:09:25 +0000
Subject: [PATCH 16/16] af_unix: Revert 'lock_interruptible' in stream receive
 code

[ Upstream commit 3822b5c2fc62e3de8a0f33806ff279fb7df92432 ]

With b3ca9b02b00704053a38bfe4c31dbbb9c13595d0, the AF_UNIX SOCK_STREAM
receive code was changed from using mutex_lock(&u->readlock) to
mutex_lock_interruptible(&u->readlock) to prevent signals from being
delayed for an indefinite time if a thread sleeping on the mutex
happened to be selected for handling the signal. But this was never a
problem with the stream receive code (as opposed to its datagram
counterpart) as that never went to sleep waiting for new messages with the
mutex held and thus, wouldn't cause secondary readers to block on the
mutex waiting for the sleeping primary reader. As the interruptible
locking makes the code more complicated in exchange for no benefit,
change it back to using mutex_lock.

Signed-off-by: Rainer Weikusat <rweikusat@mobileactivedefense.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c | 13 +++----------
 1 file changed, 3 insertions(+), 10 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 2ae4a59..7834e32 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1953,14 +1953,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 		memset(&tmp_scm, 0, sizeof(tmp_scm));
 	}
 
-	err = mutex_lock_interruptible(&u->readlock);
-	if (unlikely(err)) {
-		/* recvmsg() in non blocking mode is supposed to return -EAGAIN
-		 * sk_rcvtimeo is not honored by mutex_lock_interruptible()
-		 */
-		err = noblock ? -EAGAIN : -ERESTARTSYS;
-		goto out;
-	}
+	mutex_lock(&u->readlock);
 
 	if (flags & MSG_PEEK)
 		skip = sk_peek_offset(sk, flags);
@@ -2001,12 +1994,12 @@ again:
 
 			timeo = unix_stream_data_wait(sk, timeo, last);
 
-			if (signal_pending(current)
-			    ||  mutex_lock_interruptible(&u->readlock)) {
+			if (signal_pending(current)) {
 				err = sock_intr_errno(timeo);
 				goto out;
 			}
 
+			mutex_lock(&u->readlock);
 			continue;
  unlock:
 			unix_state_unlock(sk);
-- 
2.4.1


[-- Attachment #3: net_41.mbox --]
[-- Type: Application/Octet-Stream, Size: 56001 bytes --]

From 48d4d2a30ac1581d685d99be33573a1d4397f09d Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Thu, 3 Dec 2015 16:49:32 +0100
Subject: [PATCH 01/27] pppoe: fix memory corruption in padt work structure

[ Upstream commit fe53985aaac83d516b38358d4f39921d9942a0e2 ]

pppoe_connect() mustn't touch the padt_work field of pppoe sockets
because that work could be already pending.

[   21.473147] BUG: unable to handle kernel NULL pointer dereference at 00000004
[   21.474523] IP: [<c1043177>] process_one_work+0x29/0x31c
[   21.475164] *pde = 00000000
[   21.475513] Oops: 0000 [#1] SMP
[   21.475910] Modules linked in: pppoe pppox ppp_generic slhc crc32c_intel aesni_intel virtio_net xts aes_i586 lrw gf128mul ablk_helper cryptd evdev acpi_cpufreq processor serio_raw button ext4 crc16 mbcache jbd2 virtio_blk virtio_pci virtio_ring virtio
[   21.476168] CPU: 2 PID: 164 Comm: kworker/2:2 Not tainted 4.4.0-rc1 #1
[   21.476168] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Debian-1.8.2-1 04/01/2014
[   21.476168] task: f5f83c00 ti: f5e28000 task.ti: f5e28000
[   21.476168] EIP: 0060:[<c1043177>] EFLAGS: 00010046 CPU: 2
[   21.476168] EIP is at process_one_work+0x29/0x31c
[   21.484082] EAX: 00000000 EBX: f678b2a0 ECX: 00000004 EDX: 00000000
[   21.484082] ESI: f6c69940 EDI: f5e29ef0 EBP: f5e29f0c ESP: f5e29edc
[   21.484082]  DS: 007b ES: 007b FS: 00d8 GS: 0000 SS: 0068
[   21.484082] CR0: 80050033 CR2: 000000a4 CR3: 317ad000 CR4: 00040690
[   21.484082] Stack:
[   21.484082]  00000000 f6c69950 00000000 f6c69940 c0042338 f5e29f0c c1327945 00000000
[   21.484082]  00000008 f678b2a0 f6c69940 f678b2b8 f5e29f30 c1043984 f5f83c00 f6c69970
[   21.484082]  f678b2a0 c10437d3 f6775e80 f678b2a0 c10437d3 f5e29fac c1047059 f5e29f74
[   21.484082] Call Trace:
[   21.484082]  [<c1327945>] ? _raw_spin_lock_irq+0x28/0x30
[   21.484082]  [<c1043984>] worker_thread+0x1b1/0x244
[   21.484082]  [<c10437d3>] ? rescuer_thread+0x229/0x229
[   21.484082]  [<c10437d3>] ? rescuer_thread+0x229/0x229
[   21.484082]  [<c1047059>] kthread+0x8f/0x94
[   21.484082]  [<c1327a32>] ? _raw_spin_unlock_irq+0x22/0x26
[   21.484082]  [<c1327ee9>] ret_from_kernel_thread+0x21/0x38
[   21.484082]  [<c1046fca>] ? kthread_parkme+0x19/0x19
[   21.496082] Code: 5d c3 55 89 e5 57 56 53 89 c3 83 ec 24 89 d0 89 55 e0 8d 7d e4 e8 6c d8 ff ff b9 04 00 00 00 89 45 d8 8b 43 24 89 45 dc 8b 45 d8 <8b> 40 04 8b 80 e0 00 00 00 c1 e8 05 24 01 88 45 d7 8b 45 e0 8d
[   21.496082] EIP: [<c1043177>] process_one_work+0x29/0x31c SS:ESP 0068:f5e29edc
[   21.496082] CR2: 0000000000000004
[   21.496082] ---[ end trace e362cc9cf10dae89 ]---

Reported-by: Andrew <nitr0@seti.kr.ua>
Fixes: 287f3a943fef ("pppoe: Use workqueue to die properly when a PADT is received")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pppoe.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index ab33262..9c8fabe 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -568,6 +568,9 @@ static int pppoe_create(struct net *net, struct socket *sock)
 	sk->sk_family		= PF_PPPOX;
 	sk->sk_protocol		= PX_PROTO_OE;
 
+	INIT_WORK(&pppox_sk(sk)->proto.pppoe.padt_work,
+		  pppoe_unbind_sock_work);
+
 	return 0;
 }
 
@@ -632,8 +635,6 @@ static int pppoe_connect(struct socket *sock, struct sockaddr *uservaddr,
 
 	lock_sock(sk);
 
-	INIT_WORK(&po->proto.pppoe.padt_work, pppoe_unbind_sock_work);
-
 	error = -EINVAL;
 	if (sp->sa_protocol != PX_PROTO_OE)
 		goto end;
@@ -663,8 +664,13 @@ static int pppoe_connect(struct socket *sock, struct sockaddr *uservaddr,
 			po->pppoe_dev = NULL;
 		}
 
-		memset(sk_pppox(po) + 1, 0,
-		       sizeof(struct pppox_sock) - sizeof(struct sock));
+		po->pppoe_ifindex = 0;
+		memset(&po->pppoe_pa, 0, sizeof(po->pppoe_pa));
+		memset(&po->pppoe_relay, 0, sizeof(po->pppoe_relay));
+		memset(&po->chan, 0, sizeof(po->chan));
+		po->next = NULL;
+		po->num = 0;
+
 		sk->sk_state = PPPOX_NONE;
 	}
 
-- 
2.4.1


From 9c364c9f03ced8416b7ff87489f364c332434b76 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Thu, 3 Dec 2015 17:21:50 +0100
Subject: [PATCH 02/27] gre6: allow to update all parameters via rtnl

[ Upstream commit 6a61d4dbf4f54b5683e0f1e58d873cecca7cb977 ]

Parameters were updated only if the kernel was unable to find the tunnel
with the new parameters, ie only if core pamareters were updated (keys,
addr, link, type).
Now it's possible to update ttl, hoplimit, flowinfo and flags.

Fixes: c12b395a4664 ("gre: Support GRE over IPv6")
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 69f4f68..76be7d3 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1553,13 +1553,11 @@ static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[],
 			return -EEXIST;
 	} else {
 		t = nt;
-
-		ip6gre_tunnel_unlink(ign, t);
-		ip6gre_tnl_change(t, &p, !tb[IFLA_MTU]);
-		ip6gre_tunnel_link(ign, t);
-		netdev_state_change(dev);
 	}
 
+	ip6gre_tunnel_unlink(ign, t);
+	ip6gre_tnl_change(t, &p, !tb[IFLA_MTU]);
+	ip6gre_tunnel_link(ign, t);
 	return 0;
 }
 
-- 
2.4.1


From f3bc73a1014e8360b5e0602fd051ad5a63c8db18 Mon Sep 17 00:00:00 2001
From: Pavel Machek <pavel@ucw.cz>
Date: Fri, 4 Dec 2015 09:50:00 +0100
Subject: [PATCH 03/27] atl1c: Improve driver not to do order 4 GFP_ATOMIC
 allocation

[ Upstream commit f2a3771ae8aca879c32336c76ad05a017629bae2 ]

atl1c driver is doing order-4 allocation with GFP_ATOMIC
priority. That often breaks  networking after resume. Switch to
GFP_KERNEL. Still not ideal, but should be significantly better.

atl1c_setup_ring_resources() is called from .open() function, and
already uses GFP_KERNEL, so this change is safe.

Signed-off-by: Pavel Machek <pavel@ucw.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/atheros/atl1c/atl1c_main.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index 932bd18..6e9036a 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -1014,13 +1014,12 @@ static int atl1c_setup_ring_resources(struct atl1c_adapter *adapter)
 		sizeof(struct atl1c_recv_ret_status) * rx_desc_count +
 		8 * 4;
 
-	ring_header->desc = pci_alloc_consistent(pdev, ring_header->size,
-				&ring_header->dma);
+	ring_header->desc = dma_zalloc_coherent(&pdev->dev, ring_header->size,
+						&ring_header->dma, GFP_KERNEL);
 	if (unlikely(!ring_header->desc)) {
-		dev_err(&pdev->dev, "pci_alloc_consistend failed\n");
+		dev_err(&pdev->dev, "could not get memory for DMA buffer\n");
 		goto err_nomem;
 	}
-	memset(ring_header->desc, 0, ring_header->size);
 	/* init TPD ring */
 
 	tpd_ring[0].dma = roundup(ring_header->dma, 8);
-- 
2.4.1


From dddf53406242f708b8fcee1ab3c6b3da3676aef7 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Fri, 4 Dec 2015 14:15:08 +0100
Subject: [PATCH 04/27] ipv6: keep existing flags when setting IFA_F_OPTIMISTIC
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 9a1ec4612c9bfc94d4185e3459055a37a685e575 ]

Commit 64236f3f3d74 ("ipv6: introduce IFA_F_STABLE_PRIVACY flag")
failed to update the setting of the IFA_F_OPTIMISTIC flag, causing
the IFA_F_STABLE_PRIVACY flag to be lost if IFA_F_OPTIMISTIC is set.

Cc: Erik Kline <ek@google.com>
Cc: Fernando Gont <fgont@si6networks.com>
Cc: Lorenzo Colitti <lorenzo@google.com>
Cc: YOSHIFUJI Hideaki/吉藤英明 <hideaki.yoshifuji@miraclelinux.com>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Fixes: 64236f3f3d74 ("ipv6: introduce IFA_F_STABLE_PRIVACY flag")
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index fd3aa61..9d067b3 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -2384,7 +2384,7 @@ ok:
 #ifdef CONFIG_IPV6_OPTIMISTIC_DAD
 			if (in6_dev->cnf.optimistic_dad &&
 			    !net->ipv6.devconf_all->forwarding && sllao)
-				addr_flags = IFA_F_OPTIMISTIC;
+				addr_flags |= IFA_F_OPTIMISTIC;
 #endif
 
 			/* Do not allow to create too much of autoconfigured
-- 
2.4.1


From cbb6b471e7ba425248e01ff6933ff6808acd507f Mon Sep 17 00:00:00 2001
From: Jiri Benc <jbenc@redhat.com>
Date: Fri, 4 Dec 2015 13:54:03 +0100
Subject: [PATCH 05/27] vxlan: fix incorrect RCO bit in VXLAN header

[ Upstream commit c5fb8caaf91ea6a92920cf24db10cfc94d58de0f ]

Commit 3511494ce2f3d ("vxlan: Group Policy extension") changed definition of
VXLAN_HF_RCO from 0x00200000 to BIT(24). This is obviously incorrect. It's
also in violation with the RFC draft.

Fixes: 3511494ce2f3d ("vxlan: Group Policy extension")
Cc: Thomas Graf <tgraf@suug.ch>
Cc: Tom Herbert <therbert@google.com>
Signed-off-by: Jiri Benc <jbenc@redhat.com>
Acked-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/vxlan.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 0082b5d..7ef9272 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -78,7 +78,7 @@ struct vxlanhdr {
 };
 
 /* VXLAN header flags. */
-#define VXLAN_HF_RCO BIT(24)
+#define VXLAN_HF_RCO BIT(21)
 #define VXLAN_HF_VNI BIT(27)
 #define VXLAN_HF_GBP BIT(31)
 
-- 
2.4.1


From 6cef4300a9c3e96cb4ed4796eccd10e485251213 Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Fri, 4 Dec 2015 15:14:03 -0200
Subject: [PATCH 06/27] sctp: use the same clock as if sock source timestamps
 were on

[ Upstream commit cb5e173ed7c03a0d4630ce68a95a186cce3cc872 ]

SCTP echoes a cookie o INIT ACK chunks that contains a timestamp, for
detecting stale cookies. This cookie is echoed back to the server by the
client and then that timestamp is checked.

Thing is, if the listening socket is using packet timestamping, the
cookie is encoded with ktime_get() value and checked against
ktime_get_real(), as done by __net_timestamp().

The fix is to sctp also use ktime_get_real(), so we can compare bananas
with bananas later no matter if packet timestamping was enabled or not.

Fixes: 52db882f3fc2 ("net: sctp: migrate cookie life from timeval to ktime")
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sm_make_chunk.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 06320c8..83a07d4 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -1652,7 +1652,7 @@ static sctp_cookie_param_t *sctp_pack_cookie(const struct sctp_endpoint *ep,
 
 	/* Set an expiration time for the cookie.  */
 	cookie->c.expiration = ktime_add(asoc->cookie_life,
-					 ktime_get());
+					 ktime_get_real());
 
 	/* Copy the peer's init packet.  */
 	memcpy(&cookie->c.peer_init[0], init_chunk->chunk_hdr,
@@ -1780,7 +1780,7 @@ no_hmac:
 	if (sock_flag(ep->base.sk, SOCK_TIMESTAMP))
 		kt = skb_get_ktime(skb);
 	else
-		kt = ktime_get();
+		kt = ktime_get_real();
 
 	if (!asoc && ktime_before(bear_cookie->expiration, kt)) {
 		/*
-- 
2.4.1


From f409c06b4c99ae48ae53fe0a3ab9817da700e3bd Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Fri, 4 Dec 2015 15:14:04 -0200
Subject: [PATCH 07/27] sctp: update the netstamp_needed counter when copying
 sockets

[ Upstream commit 01ce63c90170283a9855d1db4fe81934dddce648 ]

Dmitry Vyukov reported that SCTP was triggering a WARN on socket destroy
related to disabling sock timestamp.

When SCTP accepts an association or peel one off, it copies sock flags
but forgot to call net_enable_timestamp() if a packet timestamping flag
was copied, leading to extra calls to net_disable_timestamp() whenever
such clones were closed.

The fix is to call net_enable_timestamp() whenever we copy a sock with
that flag on, like tcp does.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h | 2 ++
 net/core/sock.c    | 2 --
 net/sctp/socket.c  | 3 +++
 3 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index ed01a01..ec468b0 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -722,6 +722,8 @@ enum sock_flags {
 	SOCK_SELECT_ERR_QUEUE, /* Wake select on error queue */
 };
 
+#define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))
+
 static inline void sock_copy_flags(struct sock *nsk, struct sock *osk)
 {
 	nsk->sk_flags = osk->sk_flags;
diff --git a/net/core/sock.c b/net/core/sock.c
index dc30dc5..6c5aab3 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -421,8 +421,6 @@ static void sock_warn_obsolete_bsdism(const char *name)
 	}
 }
 
-#define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))
-
 static void sock_disable_timestamp(struct sock *sk, unsigned long flags)
 {
 	if (sk->sk_flags & flags) {
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 66d7960..3a1cb52 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -7207,6 +7207,9 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk,
 	newinet->mc_ttl = 1;
 	newinet->mc_index = 0;
 	newinet->mc_list = NULL;
+
+	if (newsk->sk_flags & SK_FLAGS_TIMESTAMP)
+		net_enable_timestamp();
 }
 
 static inline void sctp_copy_descendant(struct sock *sk_to,
-- 
2.4.1


From cf6622009a33807c8e708266626728c6a0234974 Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Fri, 4 Dec 2015 15:14:05 -0200
Subject: [PATCH 08/27] sctp: also copy sk_tsflags when copying the socket

[ Upstream commit 50a5ffb1ef535e3c6989711c51b5d61b543a3b45 ]

As we are keeping timestamps on when copying the socket, we also have to
copy sk_tsflags.

This is needed since b9f40e21ef42 ("net-timestamp: move timestamp flags
out of sk_flags").

Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 3a1cb52..a63c2c8 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -7175,6 +7175,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk,
 	newsk->sk_type = sk->sk_type;
 	newsk->sk_bound_dev_if = sk->sk_bound_dev_if;
 	newsk->sk_flags = sk->sk_flags;
+	newsk->sk_tsflags = sk->sk_tsflags;
 	newsk->sk_no_check_tx = sk->sk_no_check_tx;
 	newsk->sk_no_check_rx = sk->sk_no_check_rx;
 	newsk->sk_reuse = sk->sk_reuse;
-- 
2.4.1


From afc8be4cc599b8de64114b1a356b7f099337e1c2 Mon Sep 17 00:00:00 2001
From: Stefan Wahren <stefan.wahren@i2se.com>
Date: Fri, 4 Dec 2015 16:29:10 +0100
Subject: [PATCH 09/27] net: qca_spi: fix transmit queue timeout handling

[ Upstream commit ed7d42e24effbd3681e909711a7a2119a85e9217 ]

In case of a tx queue timeout every transmit is blocked until the
QCA7000 resets himself and triggers a sync which makes the driver
flushs the tx ring. So avoid this blocking situation by triggering
the sync immediately after the timeout. Waking the queue doesn't
make sense in this situation.

Signed-off-by: Stefan Wahren <stefan.wahren@i2se.com>
Fixes: 291ab06ecf67 ("net: qualcomm: new Ethernet over SPI driver for QCA7000")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qualcomm/qca_spi.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c
index 6af028d..97e4df9 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.c
+++ b/drivers/net/ethernet/qualcomm/qca_spi.c
@@ -736,9 +736,8 @@ qcaspi_netdev_tx_timeout(struct net_device *dev)
 	netdev_info(qca->net_dev, "Transmit timeout at %ld, latency %ld\n",
 		    jiffies, jiffies - dev->trans_start);
 	qca->net_dev->stats.tx_errors++;
-	/* wake the queue if there is room */
-	if (qcaspi_tx_ring_has_space(&qca->txr))
-		netif_wake_queue(dev);
+	/* Trigger tx queue flush and QCA7000 reset */
+	qca->sync = QCASPI_SYNC_UNKNOWN;
 }
 
 static int
-- 
2.4.1


From d800091c09eb71edb0cbc8d9f8d916aa35b5af56 Mon Sep 17 00:00:00 2001
From: Peter Wu <peter@lekensteyn.nl>
Date: Tue, 8 Dec 2015 12:17:42 +0100
Subject: [PATCH 10/27] r8152: fix lockup when runtime PM is enabled

[ Upstream commit 90186af404ada5a47b875bf3c16d0b02bb023ea0 ]

When an interface is brought up which was previously suspended (via
runtime PM), it would hang. This happens because napi_disable is called
before napi_enable.

Solve this by avoiding napi_enable in the resume during open function
(netif_running is true when open is called, IFF_UP is set after a
successful open; netif_running is false when close is called, but IFF_UP
is then still set).

While at it, remove WORK_ENABLE check from rtl8152_open (introduced with
the original change) because it cannot happen:

 - After this patch, runtime resume will not set it during rtl8152_open.
 - When link is up, rtl8152_open is not called.
 - When link is down during system/auto suspend/resume, it is not set.

Fixes: 41cec84cf285 ("r8152: don't enable napi before rx ready")
Link: https://lkml.kernel.org/r/20151205105912.GA1766@al
Signed-off-by: Peter Wu <peter@lekensteyn.nl>
Acked-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 21 +++------------------
 1 file changed, 3 insertions(+), 18 deletions(-)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index aafa1a1..ce6fad1 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -3006,17 +3006,6 @@ static int rtl8152_open(struct net_device *netdev)
 
 	mutex_lock(&tp->control);
 
-	/* The WORK_ENABLE may be set when autoresume occurs */
-	if (test_bit(WORK_ENABLE, &tp->flags)) {
-		clear_bit(WORK_ENABLE, &tp->flags);
-		usb_kill_urb(tp->intr_urb);
-		cancel_delayed_work_sync(&tp->schedule);
-
-		/* disable the tx/rx, if the workqueue has enabled them. */
-		if (netif_carrier_ok(netdev))
-			tp->rtl_ops.disable(tp);
-	}
-
 	tp->rtl_ops.up(tp);
 
 	rtl8152_set_speed(tp, AUTONEG_ENABLE,
@@ -3063,12 +3052,6 @@ static int rtl8152_close(struct net_device *netdev)
 	} else {
 		mutex_lock(&tp->control);
 
-		/* The autosuspend may have been enabled and wouldn't
-		 * be disable when autoresume occurs, because the
-		 * netif_running() would be false.
-		 */
-		rtl_runtime_suspend_enable(tp, false);
-
 		tp->rtl_ops.down(tp);
 
 		mutex_unlock(&tp->control);
@@ -3369,7 +3352,7 @@ static int rtl8152_resume(struct usb_interface *intf)
 		netif_device_attach(tp->netdev);
 	}
 
-	if (netif_running(tp->netdev)) {
+	if (netif_running(tp->netdev) && tp->netdev->flags & IFF_UP) {
 		if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
 			rtl_runtime_suspend_enable(tp, false);
 			clear_bit(SELECTIVE_SUSPEND, &tp->flags);
@@ -3387,6 +3370,8 @@ static int rtl8152_resume(struct usb_interface *intf)
 		}
 		usb_submit_urb(tp->intr_urb, GFP_KERNEL);
 	} else if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
+		if (tp->netdev->flags & IFF_UP)
+			rtl_runtime_suspend_enable(tp, false);
 		clear_bit(SELECTIVE_SUSPEND, &tp->flags);
 	}
 
-- 
2.4.1


From 2cafec0bfcd7d0f58a7d8d9b0c4ae7a43e186b64 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 9 Dec 2015 07:25:06 -0800
Subject: [PATCH 11/27] ipv6: sctp: clone options to avoid use after free

[ Upstream commit 9470e24f35ab81574da54e69df90c1eb4a96b43f ]

SCTP is lacking proper np->opt cloning at accept() time.

TCP and DCCP use ipv6_dup_options() helper, do the same
in SCTP.

We might later factorize this code in a common helper to avoid
future mistakes.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ipv6.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 0e4198e..3267a5c 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -634,6 +634,7 @@ static struct sock *sctp_v6_create_accept_sk(struct sock *sk,
 	struct sock *newsk;
 	struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
 	struct sctp6_sock *newsctp6sk;
+	struct ipv6_txoptions *opt;
 
 	newsk = sk_alloc(sock_net(sk), PF_INET6, GFP_KERNEL, sk->sk_prot);
 	if (!newsk)
@@ -653,6 +654,13 @@ static struct sock *sctp_v6_create_accept_sk(struct sock *sk,
 
 	memcpy(newnp, np, sizeof(struct ipv6_pinfo));
 
+	rcu_read_lock();
+	opt = rcu_dereference(np->opt);
+	if (opt)
+		opt = ipv6_dup_options(newsk, opt);
+	RCU_INIT_POINTER(newnp->opt, opt);
+	rcu_read_unlock();
+
 	/* Initialize sk's sport, dport, rcv_saddr and daddr for getsockname()
 	 * and getpeername().
 	 */
-- 
2.4.1


From 9f6e9dfda8c6a72ce814cd6d149e01d30a2724ae Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Mon, 14 Dec 2015 22:03:39 +0100
Subject: [PATCH 12/27] net: add validation for the socket syscall protocol
 argument
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 79462ad02e861803b3840cc782248c7359451cd9 ]

郭永刚 reported that one could simply crash the kernel as root by
using a simple program:

	int socket_fd;
	struct sockaddr_in addr;
	addr.sin_port = 0;
	addr.sin_addr.s_addr = INADDR_ANY;
	addr.sin_family = 10;

	socket_fd = socket(10,3,0x40000000);
	connect(socket_fd , &addr,16);

AF_INET, AF_INET6 sockets actually only support 8-bit protocol
identifiers. inet_sock's skc_protocol field thus is sized accordingly,
thus larger protocol identifiers simply cut off the higher bits and
store a zero in the protocol fields.

This could lead to e.g. NULL function pointer because as a result of
the cut off inet_num is zero and we call down to inet_autobind, which
is NULL for raw sockets.

kernel: Call Trace:
kernel:  [<ffffffff816db90e>] ? inet_autobind+0x2e/0x70
kernel:  [<ffffffff816db9a4>] inet_dgram_connect+0x54/0x80
kernel:  [<ffffffff81645069>] SYSC_connect+0xd9/0x110
kernel:  [<ffffffff810ac51b>] ? ptrace_notify+0x5b/0x80
kernel:  [<ffffffff810236d8>] ? syscall_trace_enter_phase2+0x108/0x200
kernel:  [<ffffffff81645e0e>] SyS_connect+0xe/0x10
kernel:  [<ffffffff81779515>] tracesys_phase2+0x84/0x89

I found no particular commit which introduced this problem.

CVE: CVE-2015-8543
Cc: Cong Wang <cwang@twopensource.com>
Reported-by: 郭永刚 <guoyonggang@360.cn>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h     | 1 +
 net/ax25/af_ax25.c     | 3 +++
 net/decnet/af_decnet.c | 3 +++
 net/ipv4/af_inet.c     | 3 +++
 net/ipv6/af_inet6.c    | 3 +++
 net/irda/af_irda.c     | 3 +++
 6 files changed, 16 insertions(+)

diff --git a/include/net/sock.h b/include/net/sock.h
index ec468b0..f581324 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -386,6 +386,7 @@ struct sock {
 				sk_no_check_rx : 1,
 				sk_userlocks : 4,
 				sk_protocol  : 8,
+#define SK_PROTOCOL_MAX U8_MAX
 				sk_type      : 16;
 	kmemcheck_bitfield_end(flags);
 	int			sk_wmem_queued;
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 330c1f4..a64884b 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -806,6 +806,9 @@ static int ax25_create(struct net *net, struct socket *sock, int protocol,
 	struct sock *sk;
 	ax25_cb *ax25;
 
+	if (protocol < 0 || protocol > SK_PROTOCOL_MAX)
+		return -EINVAL;
+
 	if (!net_eq(net, &init_net))
 		return -EAFNOSUPPORT;
 
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 754484b..2783c53 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -678,6 +678,9 @@ static int dn_create(struct net *net, struct socket *sock, int protocol,
 {
 	struct sock *sk;
 
+	if (protocol < 0 || protocol > SK_PROTOCOL_MAX)
+		return -EINVAL;
+
 	if (!net_eq(net, &init_net))
 		return -EAFNOSUPPORT;
 
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index a5aa54e..0cc98b1 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -259,6 +259,9 @@ static int inet_create(struct net *net, struct socket *sock, int protocol,
 	int try_loading_module = 0;
 	int err;
 
+	if (protocol < 0 || protocol >= IPPROTO_MAX)
+		return -EINVAL;
+
 	sock->state = SS_UNCONNECTED;
 
 	/* Look for the requested type/protocol pair. */
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 2d044d2..bad62fa 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -109,6 +109,9 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol,
 	int try_loading_module = 0;
 	int err;
 
+	if (protocol < 0 || protocol >= IPPROTO_MAX)
+		return -EINVAL;
+
 	/* Look for the requested type/protocol pair. */
 lookup_protocol:
 	err = -ESOCKTNOSUPPORT;
diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index ee0ea25..9a1edcd 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -1086,6 +1086,9 @@ static int irda_create(struct net *net, struct socket *sock, int protocol,
 	struct sock *sk;
 	struct irda_sock *self;
 
+	if (protocol < 0 || protocol > SK_PROTOCOL_MAX)
+		return -EINVAL;
+
 	if (net != &init_net)
 		return -EAFNOSUPPORT;
 
-- 
2.4.1


From f79aaefa9b09e0181c32c0670e9619c2fe82a3c3 Mon Sep 17 00:00:00 2001
From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Date: Fri, 4 Dec 2015 01:45:40 +0300
Subject: [PATCH 13/27] sh_eth: fix kernel oops in skb_put()

[ Upstream commit 248be83dcb3feb3f6332eb3d010a016402138484 ]

In a low memory situation the following kernel oops occurs:

Unable to handle kernel NULL pointer dereference at virtual address 00000050
pgd = 8490c000
[00000050] *pgd=4651e831, *pte=00000000, *ppte=00000000
Internal error: Oops: 17 [#1] PREEMPT ARM
Modules linked in:
CPU: 0    Not tainted  (3.4-at16 #9)
PC is at skb_put+0x10/0x98
LR is at sh_eth_poll+0x2c8/0xa10
pc : [<8035f780>]    lr : [<8028bf50>]    psr: 60000113
sp : 84eb1a90  ip : 84eb1ac8  fp : 84eb1ac4
r10: 0000003f  r9 : 000005ea  r8 : 00000000
r7 : 00000000  r6 : 940453b0  r5 : 00030000  r4 : 9381b180
r3 : 00000000  r2 : 00000000  r1 : 000005ea  r0 : 00000000
Flags: nZCv  IRQs on  FIQs on  Mode SVC_32  ISA ARM  Segment user
Control: 10c53c7d  Table: 4248c059  DAC: 00000015
Process klogd (pid: 2046, stack limit = 0x84eb02e8)
[...]

This is  because netdev_alloc_skb() fails and 'mdp->rx_skbuff[entry]' is left
NULL but sh_eth_rx() later  uses it without checking.  Add such check...

Reported-by: Yasushi SHOJI <yashi@atmark-techno.com>
Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/sh_eth.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 7fb244f..13463c4 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -1481,6 +1481,7 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota)
 		if (mdp->cd->shift_rd0)
 			desc_status >>= 16;
 
+		skb = mdp->rx_skbuff[entry];
 		if (desc_status & (RD_RFS1 | RD_RFS2 | RD_RFS3 | RD_RFS4 |
 				   RD_RFS5 | RD_RFS6 | RD_RFS10)) {
 			ndev->stats.rx_errors++;
@@ -1496,12 +1497,11 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota)
 				ndev->stats.rx_missed_errors++;
 			if (desc_status & RD_RFS10)
 				ndev->stats.rx_over_errors++;
-		} else {
+		} else	if (skb) {
 			if (!mdp->cd->hw_swap)
 				sh_eth_soft_swap(
 					phys_to_virt(ALIGN(rxdesc->addr, 4)),
 					pkt_len + 2);
-			skb = mdp->rx_skbuff[entry];
 			mdp->rx_skbuff[entry] = NULL;
 			if (mdp->cd->rpadir)
 				skb_reserve(skb, NET_IP_ALIGN);
-- 
2.4.1


From a9bc7ddf928398ad03ef74251d4fa100b597d0cd Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 14 Dec 2015 14:08:53 -0800
Subject: [PATCH 14/27] net: fix IP early demux races

[ Upstream commit 5037e9ef9454917b047f9f3a19b4dd179fbf7cd4 ]

David Wilder reported crashes caused by dst reuse.

<quote David>
  I am seeing a crash on a distro V4.2.3 kernel caused by a double
  release of a dst_entry.  In ipv4_dst_destroy() the call to
  list_empty() finds a poisoned next pointer, indicating the dst_entry
  has already been removed from the list and freed. The crash occurs
  18 to 24 hours into a run of a network stress exerciser.
</quote>

Thanks to his detailed report and analysis, we were able to understand
the core issue.

IP early demux can associate a dst to skb, after a lookup in TCP/UDP
sockets.

When socket cache is not properly set, we want to store into
sk->sk_dst_cache the dst for future IP early demux lookups,
by acquiring a stable refcount on the dst.

Problem is this acquisition is simply using an atomic_inc(),
which works well, unless the dst was queued for destruction from
dst_release() noticing dst refcount went to zero, if DST_NOCACHE
was set on dst.

We need to make sure current refcount is not zero before incrementing
it, or risk double free as David reported.

This patch, being a stable candidate, adds two new helpers, and use
them only from IP early demux problematic paths.

It might be possible to merge in net-next skb_dst_force() and
skb_dst_force_safe(), but I prefer having the smallest patch for stable
kernels : Maybe some skb_dst_force() callers do not expect skb->dst
can suddenly be cleared.

Can probably be backported back to linux-3.6 kernels

Reported-by: David J. Wilder <dwilder@us.ibm.com>
Tested-by: David J. Wilder <dwilder@us.ibm.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst.h   | 33 +++++++++++++++++++++++++++++++++
 include/net/sock.h  |  2 +-
 net/ipv4/tcp_ipv4.c |  5 ++---
 net/ipv6/tcp_ipv6.c |  3 +--
 4 files changed, 37 insertions(+), 6 deletions(-)

diff --git a/include/net/dst.h b/include/net/dst.h
index 0fb99a2..182b812 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -312,6 +312,39 @@ static inline void skb_dst_force(struct sk_buff *skb)
 	}
 }
 
+/**
+ * dst_hold_safe - Take a reference on a dst if possible
+ * @dst: pointer to dst entry
+ *
+ * This helper returns false if it could not safely
+ * take a reference on a dst.
+ */
+static inline bool dst_hold_safe(struct dst_entry *dst)
+{
+	if (dst->flags & DST_NOCACHE)
+		return atomic_inc_not_zero(&dst->__refcnt);
+	dst_hold(dst);
+	return true;
+}
+
+/**
+ * skb_dst_force_safe - makes sure skb dst is refcounted
+ * @skb: buffer
+ *
+ * If dst is not yet refcounted and not destroyed, grab a ref on it.
+ */
+static inline void skb_dst_force_safe(struct sk_buff *skb)
+{
+	if (skb_dst_is_noref(skb)) {
+		struct dst_entry *dst = skb_dst(skb);
+
+		if (!dst_hold_safe(dst))
+			dst = NULL;
+
+		skb->_skb_refdst = (unsigned long)dst;
+	}
+}
+
 
 /**
  *	__skb_tunnel_rx - prepare skb for rx reinsert
diff --git a/include/net/sock.h b/include/net/sock.h
index f581324..4c4b21c 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -799,7 +799,7 @@ void sk_stream_write_space(struct sock *sk);
 static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb)
 {
 	/* dont let skb dst not refcounted, we are going to leave rcu lock */
-	skb_dst_force(skb);
+	skb_dst_force_safe(skb);
 
 	if (!sk->sk_backlog.tail)
 		sk->sk_backlog.head = skb;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 88203e7..cd18c3d 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1509,7 +1509,7 @@ bool tcp_prequeue(struct sock *sk, struct sk_buff *skb)
 	if (likely(sk->sk_rx_dst))
 		skb_dst_drop(skb);
 	else
-		skb_dst_force(skb);
+		skb_dst_force_safe(skb);
 
 	__skb_queue_tail(&tp->ucopy.prequeue, skb);
 	tp->ucopy.memory += skb->truesize;
@@ -1714,8 +1714,7 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
 
-	if (dst) {
-		dst_hold(dst);
+	if (dst && dst_hold_safe(dst)) {
 		sk->sk_rx_dst = dst;
 		inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
 	}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index cfb27f5..c1938ad 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -93,10 +93,9 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
 
-	if (dst) {
+	if (dst && dst_hold_safe(dst)) {
 		const struct rt6_info *rt = (const struct rt6_info *)dst;
 
-		dst_hold(dst);
 		sk->sk_rx_dst = dst;
 		inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
 		if (rt->rt6i_node)
-- 
2.4.1


From 022f65bcbcc5872edc4014c51c4d6ed59cc03a82 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Mon, 14 Dec 2015 13:48:36 -0800
Subject: [PATCH 15/27] pptp: verify sockaddr_len in pptp_bind() and
 pptp_connect()

[ Upstream commit 09ccfd238e5a0e670d8178cf50180ea81ae09ae1 ]

Reported-by: Dmitry Vyukov <dvyukov@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pptp.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index e3bfbd4d..0bacabf 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -420,6 +420,9 @@ static int pptp_bind(struct socket *sock, struct sockaddr *uservaddr,
 	struct pptp_opt *opt = &po->proto.pptp;
 	int error = 0;
 
+	if (sockaddr_len < sizeof(struct sockaddr_pppox))
+		return -EINVAL;
+
 	lock_sock(sk);
 
 	opt->src_addr = sp->sa_addr.pptp;
@@ -441,6 +444,9 @@ static int pptp_connect(struct socket *sock, struct sockaddr *uservaddr,
 	struct flowi4 fl4;
 	int error = 0;
 
+	if (sockaddr_len < sizeof(struct sockaddr_pppox))
+		return -EINVAL;
+
 	if (sp->sa_protocol != PX_PROTO_PPTP)
 		return -EINVAL;
 
-- 
2.4.1


From ea8c5b8e54b5ec81dc0734e3bf1dbec9ac8a85b4 Mon Sep 17 00:00:00 2001
From: Vlad Yasevich <vyasevich@gmail.com>
Date: Mon, 16 Nov 2015 15:43:44 -0500
Subject: [PATCH 16/27] vlan: Fix untag operations of stacked vlans with
 REORDER_HEADER off

[ Upstream commit a6e18ff111701b4ff6947605bfbe9594ec42a6e8 ]

When we have multiple stacked vlan devices all of which have
turned off REORDER_HEADER flag, the untag operation does not
locate the ethernet addresses correctly for nested vlans.
The reason is that in case of REORDER_HEADER flag being off,
the outer vlan headers are put back and the mac_len is adjusted
to account for the presense of the header.  Then, the subsequent
untag operation, for the next level vlan, always use VLAN_ETH_HLEN
to locate the begining of the ethernet header and that ends up
being a multiple of 4 bytes short of the actuall beginning
of the mac header (the multiple depending on the how many vlan
encapsulations ethere are).

As a reslult, if there are multiple levles of vlan devices
with REODER_HEADER being off, the recevied packets end up
being dropped.

To solve this, we use skb->mac_len as the offset.  The value
is always set on receive path and starts out as a ETH_HLEN.
The value is also updated when the vlan header manupations occur
so we know it will be correct.

Signed-off-by: Vladislav Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 075d2e7..13ddacb 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4200,7 +4200,8 @@ static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb)
 		return NULL;
 	}
 
-	memmove(skb->data - ETH_HLEN, skb->data - VLAN_ETH_HLEN, 2 * ETH_ALEN);
+	memmove(skb->data - ETH_HLEN, skb->data - skb->mac_len,
+		2 * ETH_ALEN);
 	skb->mac_header += VLAN_HLEN;
 	return skb;
 }
-- 
2.4.1


From 29dde177f41f87bc202c7ddee3dcb483d43bd9b2 Mon Sep 17 00:00:00 2001
From: Vlad Yasevich <vyasevich@gmail.com>
Date: Mon, 14 Dec 2015 17:44:10 -0500
Subject: [PATCH 17/27] skbuff: Fix offset error in skb_reorder_vlan_header

[ Upstream commit f654861569872d10dcb79d9d7ca219b316f94ff0 ]

skb_reorder_vlan_header is called after the vlan header has
been pulled.  As a result the offset of the begining of
the mac header has been incrased by 4 bytes (VLAN_HLEN).
When moving the mac addresses, include this incrase in
the offset calcualation so that the mac addresses are
copied correctly.

Fixes: a6e18ff1117 (vlan: Fix untag operations of stacked vlans with REORDER_HEADER off)
CC: Nicolas Dichtel <nicolas.dichtel@6wind.com>
CC: Patrick McHardy <kaber@trash.net>
Signed-off-by: Vladislav Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 13ddacb..f3f7d0a 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4200,7 +4200,7 @@ static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb)
 		return NULL;
 	}
 
-	memmove(skb->data - ETH_HLEN, skb->data - skb->mac_len,
+	memmove(skb->data - ETH_HLEN, skb->data - skb->mac_len - VLAN_HLEN,
 		2 * ETH_ALEN);
 	skb->mac_header += VLAN_HLEN;
 	return skb;
-- 
2.4.1


From e02ee3b9ee88574601e01f9dfc3d64bd57376dce Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Wed, 16 Dec 2015 23:39:04 -0800
Subject: [PATCH 18/27] net: check both type and procotol for tcp sockets

[ Upstream commit ac5cc977991d2dce85fc734a6c71ddb33f6fe3c1 ]

Dmitry reported the following out-of-bound access:

Call Trace:
 [<ffffffff816cec2e>] __asan_report_load4_noabort+0x3e/0x40
mm/kasan/report.c:294
 [<ffffffff84affb14>] sock_setsockopt+0x1284/0x13d0 net/core/sock.c:880
 [<     inline     >] SYSC_setsockopt net/socket.c:1746
 [<ffffffff84aed7ee>] SyS_setsockopt+0x1fe/0x240 net/socket.c:1729
 [<ffffffff85c18c76>] entry_SYSCALL_64_fastpath+0x16/0x7a
arch/x86/entry/entry_64.S:185

This is because we mistake a raw socket as a tcp socket.
We should check both sk->sk_type and sk->sk_protocol to ensure
it is a tcp socket.

Willem points out __skb_complete_tx_timestamp() needs to fix as well.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 3 ++-
 net/core/sock.c   | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index f3f7d0a..2e5fcda 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3661,7 +3661,8 @@ static void __skb_complete_tx_timestamp(struct sk_buff *skb,
 	serr->ee.ee_info = tstype;
 	if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) {
 		serr->ee.ee_data = skb_shinfo(skb)->tskey;
-		if (sk->sk_protocol == IPPROTO_TCP)
+		if (sk->sk_protocol == IPPROTO_TCP &&
+		    sk->sk_type == SOCK_STREAM)
 			serr->ee.ee_data -= sk->sk_tskey;
 	}
 
diff --git a/net/core/sock.c b/net/core/sock.c
index 6c5aab3..47fc8bb 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -859,7 +859,8 @@ set_rcvbuf:
 
 		if (val & SOF_TIMESTAMPING_OPT_ID &&
 		    !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) {
-			if (sk->sk_protocol == IPPROTO_TCP) {
+			if (sk->sk_protocol == IPPROTO_TCP &&
+			    sk->sk_type == SOCK_STREAM) {
 				if (sk->sk_state != TCP_ESTABLISHED) {
 					ret = -EINVAL;
 					break;
-- 
2.4.1


From 0616c328fb6ad7bf5411806eb04496f67afed2d8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 15 Dec 2015 09:43:12 -0800
Subject: [PATCH 19/27] net_sched: make qdisc_tree_decrease_qlen() work for non
 mq

[ Upstream commit 225734de70cd0a9e0b978f3583a4a87939271d5e ]

Stas Nichiporovich reported a regression in his HFSC qdisc setup
on a non multi queue device.

It turns out I mistakenly added a TCQ_F_NOPARENT flag on all qdisc
allocated in qdisc_create() for non multi queue devices, which was
rather buggy. I was clearly mislead by the TCQ_F_ONETXQUEUE that is
also set here for no good reason, since it only matters for the root
qdisc.

Fixes: 4eaf3b84f288 ("net_sched: fix qdisc_tree_decrease_qlen() races")
Reported-by: Stas Nichiporovich <stasn77@gmail.com>
Tested-by: Stas Nichiporovich <stasn77@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_api.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index d4b6f36..68c599a 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -950,7 +950,7 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue,
 		}
 		lockdep_set_class(qdisc_lock(sch), &qdisc_tx_lock);
 		if (!netif_is_multiqueue(dev))
-			sch->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
+			sch->flags |= TCQ_F_ONETXQUEUE;
 	}
 
 	sch->handle = handle;
-- 
2.4.1


From f87ec41133606fe888a13be2c1b8c58420413586 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 15 Dec 2015 15:39:08 -0500
Subject: [PATCH 20/27] bluetooth: Validate socket address length in
 sco_sock_bind().

[ Upstream commit 5233252fce714053f0151680933571a2da9cbfb4 ]

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bluetooth/sco.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 4322c83..8611bc7 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -520,6 +520,9 @@ static int sco_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_le
 	if (!addr || addr->sa_family != AF_BLUETOOTH)
 		return -EINVAL;
 
+	if (addr_len < sizeof(struct sockaddr_sco))
+		return -EINVAL;
+
 	lock_sock(sk);
 
 	if (sk->sk_state != BT_OPEN) {
-- 
2.4.1


From b245d8fcf8d145006f7542d06346e24457a8bb11 Mon Sep 17 00:00:00 2001
From: "tadeusz.struk@intel.com" <tadeusz.struk@intel.com>
Date: Tue, 15 Dec 2015 10:46:17 -0800
Subject: [PATCH 21/27] net: fix uninitialized variable issue

[ Upstream commit 130ed5d105dde141e7fe60d5440aa53e0a84f13b ]

msg_iocb needs to be initialized on the recv/recvfrom path.
Otherwise afalg will wrongly interpret it as an async call.

Cc: stable@vger.kernel.org
Reported-by: Harald Freudenberger <freude@linux.vnet.ibm.com>
Signed-off-by: Tadeusz Struk <tadeusz.struk@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/socket.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/socket.c b/net/socket.c
index 884e329..dcbfa86 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1705,6 +1705,7 @@ SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size,
 	msg.msg_name = addr ? (struct sockaddr *)&address : NULL;
 	/* We assume all kernel code knows the size of sockaddr_storage */
 	msg.msg_namelen = 0;
+	msg.msg_iocb = NULL;
 	if (sock->file->f_flags & O_NONBLOCK)
 		flags |= MSG_DONTWAIT;
 	err = sock_recvmsg(sock, &msg, iov_iter_count(&msg.msg_iter), flags);
-- 
2.4.1


From 2fae64c2f5327c64fc015726e22cee5e166e0f1e Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Tue, 15 Dec 2015 22:59:12 +0100
Subject: [PATCH 22/27] ipv6: automatically enable stable privacy mode if
 stable_secret set
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 9b29c6962b70f232cde4076b1020191e1be0889d ]

Bjørn reported that while we switch all interfaces to privacy stable mode
when setting the secret, we don't set this mode for new interfaces. This
does not make sense, so change this behaviour.

Fixes: 622c81d57b392cc ("ipv6: generation of stable privacy addresses for link-local and autoconf")
Reported-by: Bjørn Mork <bjorn@mork.no>
Cc: Bjørn Mork <bjorn@mork.no>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 9d067b3..a2d6850 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -343,6 +343,12 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
 	setup_timer(&ndev->rs_timer, addrconf_rs_timer,
 		    (unsigned long)ndev);
 	memcpy(&ndev->cnf, dev_net(dev)->ipv6.devconf_dflt, sizeof(ndev->cnf));
+
+	if (ndev->cnf.stable_secret.initialized)
+		ndev->addr_gen_mode = IN6_ADDR_GEN_MODE_STABLE_PRIVACY;
+	else
+		ndev->addr_gen_mode = IN6_ADDR_GEN_MODE_EUI64;
+
 	ndev->cnf.mtu6 = dev->mtu;
 	ndev->cnf.sysctl = NULL;
 	ndev->nd_parms = neigh_parms_alloc(dev, &nd_tbl);
-- 
2.4.1


From 5f3a25c2845dd12c5362acf5fb593434a6c576c2 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Wed, 16 Dec 2015 18:13:14 +0800
Subject: [PATCH 23/27] rhashtable: Enforce minimum size on initial hash table

[ Upstream commit 3a324606bbabfc30084ce9d08169910773ba9a92 ]

William Hua <william.hua@canonical.com> wrote:
>
> I wasn't aware there was an enforced minimum size. I simply set the
> nelem_hint in the rhastable_params struct to 1, expecting it to grow as
> needed. This caused a segfault afterwards when trying to insert an
> element.

OK we're doing the size computation before we enforce the limit
on min_size.

---8<---
We need to do the initial hash table size computation after we
have obtained the correct min_size/max_size parameters.  Otherwise
we may end up with a hash table whose size is outside the allowed
envelope.

Fixes: a998f712f77e ("rhashtable: Round up/down min/max_size to...")
Reported-by: William Hua <william.hua@canonical.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 lib/rhashtable.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index cf910e4..4ff003e 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -730,9 +730,6 @@ int rhashtable_init(struct rhashtable *ht,
 	if (params->nulls_base && params->nulls_base < (1U << RHT_BASE_SHIFT))
 		return -EINVAL;
 
-	if (params->nelem_hint)
-		size = rounded_hashtable_size(params);
-
 	memset(ht, 0, sizeof(*ht));
 	mutex_init(&ht->mutex);
 	spin_lock_init(&ht->lock);
@@ -752,6 +749,9 @@ int rhashtable_init(struct rhashtable *ht,
 
 	ht->p.min_size = max(ht->p.min_size, HASH_MIN_SIZE);
 
+	if (params->nelem_hint)
+		size = rounded_hashtable_size(&ht->p);
+
 	/* The maximum (not average) chain length grows with the
 	 * size of the hash table, at a rate of (log N)/(log log N).
 	 * The value of 16 is selected so that even if the hash
-- 
2.4.1


From dcb94c2aa33f05711030a9468e3e05c52a3c5e7d Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Tue, 15 Dec 2015 21:01:53 +0100
Subject: [PATCH 24/27] fou: clean up socket with kfree_rcu

[ Upstream commit 3036facbb7be3a169e35be3b271162b0fa564a2d ]

fou->udp_offloads is managed by RCU. As it is actually included inside
the fou sockets, we cannot let the memory go out of scope before a grace
period. We either can synchronize_rcu or switch over to kfree_rcu to
manage the sockets. kfree_rcu seems appropriate as it is used by vxlan
and geneve.

Fixes: 23461551c00628c ("fou: Support for foo-over-udp RX path")
Cc: Tom Herbert <tom@herbertland.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fou.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 34968cd..4b67937 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -24,6 +24,7 @@ struct fou {
 	u16 type;
 	struct udp_offload udp_offloads;
 	struct list_head list;
+	struct rcu_head rcu;
 };
 
 #define FOU_F_REMCSUM_NOPARTIAL BIT(0)
@@ -421,7 +422,7 @@ static void fou_release(struct fou *fou)
 	list_del(&fou->list);
 	udp_tunnel_sock_release(sock);
 
-	kfree(fou);
+	kfree_rcu(fou, rcu);
 }
 
 static int fou_encap_init(struct sock *sk, struct fou *fou, struct fou_cfg *cfg)
-- 
2.4.1


From d50694e31e850f666c0962b7a85149278d5ff6c9 Mon Sep 17 00:00:00 2001
From: Rainer Weikusat <rweikusat@mobileactivedefense.com>
Date: Wed, 16 Dec 2015 20:09:25 +0000
Subject: [PATCH 25/27] af_unix: Revert 'lock_interruptible' in stream receive
 code

[ Upstream commit 3822b5c2fc62e3de8a0f33806ff279fb7df92432 ]

With b3ca9b02b00704053a38bfe4c31dbbb9c13595d0, the AF_UNIX SOCK_STREAM
receive code was changed from using mutex_lock(&u->readlock) to
mutex_lock_interruptible(&u->readlock) to prevent signals from being
delayed for an indefinite time if a thread sleeping on the mutex
happened to be selected for handling the signal. But this was never a
problem with the stream receive code (as opposed to its datagram
counterpart) as that never went to sleep waiting for new messages with the
mutex held and thus, wouldn't cause secondary readers to block on the
mutex waiting for the sleeping primary reader. As the interruptible
locking makes the code more complicated in exchange for no benefit,
change it back to using mutex_lock.

Signed-off-by: Rainer Weikusat <rweikusat@mobileactivedefense.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c | 13 +++----------
 1 file changed, 3 insertions(+), 10 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 1975fd8..a398f62 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2072,14 +2072,7 @@ static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg,
 
 	memset(&scm, 0, sizeof(scm));
 
-	err = mutex_lock_interruptible(&u->readlock);
-	if (unlikely(err)) {
-		/* recvmsg() in non blocking mode is supposed to return -EAGAIN
-		 * sk_rcvtimeo is not honored by mutex_lock_interruptible()
-		 */
-		err = noblock ? -EAGAIN : -ERESTARTSYS;
-		goto out;
-	}
+	mutex_lock(&u->readlock);
 
 	if (flags & MSG_PEEK)
 		skip = sk_peek_offset(sk, flags);
@@ -2120,12 +2113,12 @@ again:
 
 			timeo = unix_stream_data_wait(sk, timeo, last);
 
-			if (signal_pending(current)
-			    ||  mutex_lock_interruptible(&u->readlock)) {
+			if (signal_pending(current)) {
 				err = sock_intr_errno(timeo);
 				goto out;
 			}
 
+			mutex_lock(&u->readlock);
 			continue;
  unlock:
 			unix_state_unlock(sk);
-- 
2.4.1


From a1f879cd8e6a83ce3b8c0e563c9d5a01b55093ff Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 16 Dec 2015 13:53:10 -0800
Subject: [PATCH 26/27] tcp: restore fastopen with no data in SYN packet

[ Upstream commit 07e100f984975cb0417a7d5e626d0409efbad478 ]

Yuchung tracked a regression caused by commit 57be5bdad759 ("ip: convert
tcp_sendmsg() to iov_iter primitives") for TCP Fast Open.

Some Fast Open users do not actually add any data in the SYN packet.

Fixes: 57be5bdad759 ("ip: convert tcp_sendmsg() to iov_iter primitives")
Reported-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 23 ++++++++++++-----------
 1 file changed, 12 insertions(+), 11 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 986440b..1ea4322 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3143,7 +3143,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_fastopen_request *fo = tp->fastopen_req;
-	int syn_loss = 0, space, err = 0, copied;
+	int syn_loss = 0, space, err = 0;
 	unsigned long last_syn_loss = 0;
 	struct sk_buff *syn_data;
 
@@ -3181,17 +3181,18 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 		goto fallback;
 	syn_data->ip_summed = CHECKSUM_PARTIAL;
 	memcpy(syn_data->cb, syn->cb, sizeof(syn->cb));
-	copied = copy_from_iter(skb_put(syn_data, space), space,
-				&fo->data->msg_iter);
-	if (unlikely(!copied)) {
-		kfree_skb(syn_data);
-		goto fallback;
-	}
-	if (copied != space) {
-		skb_trim(syn_data, copied);
-		space = copied;
+	if (space) {
+		int copied = copy_from_iter(skb_put(syn_data, space), space,
+					    &fo->data->msg_iter);
+		if (unlikely(!copied)) {
+			kfree_skb(syn_data);
+			goto fallback;
+		}
+		if (copied != space) {
+			skb_trim(syn_data, copied);
+			space = copied;
+		}
 	}
-
 	/* No more data pending in inet_wait_for_connect() */
 	if (space == fo->size)
 		fo->data = NULL;
-- 
2.4.1


From 980f5aa371963e9c2ea5aaa0cb9106c97f1f46cf Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Wed, 16 Dec 2015 16:45:54 +0800
Subject: [PATCH 27/27] rhashtable: Fix walker list corruption

[ Upstream commit c6ff5268293ef98e48a99597e765ffc417e39fa5 ]

The commit ba7c95ea3870fe7b847466d39a049ab6f156aa2c ("rhashtable:
Fix sleeping inside RCU critical section in walk_stop") introduced
a new spinlock for the walker list.  However, it did not convert
all existing users of the list over to the new spin lock.  Some
continued to use the old mutext for this purpose.  This obviously
led to corruption of the list.

The fix is to use the spin lock everywhere where we touch the list.

This also allows us to do rcu_rad_lock before we take the lock in
rhashtable_walk_start.  With the old mutex this would've deadlocked
but it's safe with the new spin lock.

Fixes: ba7c95ea3870 ("rhashtable: Fix sleeping inside RCU...")
Reported-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 lib/rhashtable.c | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 4ff003e..5b17447 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -506,10 +506,11 @@ int rhashtable_walk_init(struct rhashtable *ht, struct rhashtable_iter *iter)
 	if (!iter->walker)
 		return -ENOMEM;
 
-	mutex_lock(&ht->mutex);
-	iter->walker->tbl = rht_dereference(ht->tbl, ht);
+	spin_lock(&ht->lock);
+	iter->walker->tbl =
+		rcu_dereference_protected(ht->tbl, lockdep_is_held(&ht->lock));
 	list_add(&iter->walker->list, &iter->walker->tbl->walkers);
-	mutex_unlock(&ht->mutex);
+	spin_unlock(&ht->lock);
 
 	return 0;
 }
@@ -523,10 +524,10 @@ EXPORT_SYMBOL_GPL(rhashtable_walk_init);
  */
 void rhashtable_walk_exit(struct rhashtable_iter *iter)
 {
-	mutex_lock(&iter->ht->mutex);
+	spin_lock(&iter->ht->lock);
 	if (iter->walker->tbl)
 		list_del(&iter->walker->list);
-	mutex_unlock(&iter->ht->mutex);
+	spin_unlock(&iter->ht->lock);
 	kfree(iter->walker);
 }
 EXPORT_SYMBOL_GPL(rhashtable_walk_exit);
@@ -550,14 +551,12 @@ int rhashtable_walk_start(struct rhashtable_iter *iter)
 {
 	struct rhashtable *ht = iter->ht;
 
-	mutex_lock(&ht->mutex);
+	rcu_read_lock();
 
+	spin_lock(&ht->lock);
 	if (iter->walker->tbl)
 		list_del(&iter->walker->list);
-
-	rcu_read_lock();
-
-	mutex_unlock(&ht->mutex);
+	spin_unlock(&ht->lock);
 
 	if (!iter->walker->tbl) {
 		iter->walker->tbl = rht_dereference_rcu(ht->tbl, ht);
-- 
2.4.1


[-- Attachment #4: net_43.mbox --]
[-- Type: Application/Octet-Stream, Size: 72084 bytes --]

From 14b602561ad208203fb04a8eb3df052ad2c6551a Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Thu, 3 Dec 2015 16:49:32 +0100
Subject: [PATCH 01/34] pppoe: fix memory corruption in padt work structure

[ Upstream commit fe53985aaac83d516b38358d4f39921d9942a0e2 ]

pppoe_connect() mustn't touch the padt_work field of pppoe sockets
because that work could be already pending.

[   21.473147] BUG: unable to handle kernel NULL pointer dereference at 00000004
[   21.474523] IP: [<c1043177>] process_one_work+0x29/0x31c
[   21.475164] *pde = 00000000
[   21.475513] Oops: 0000 [#1] SMP
[   21.475910] Modules linked in: pppoe pppox ppp_generic slhc crc32c_intel aesni_intel virtio_net xts aes_i586 lrw gf128mul ablk_helper cryptd evdev acpi_cpufreq processor serio_raw button ext4 crc16 mbcache jbd2 virtio_blk virtio_pci virtio_ring virtio
[   21.476168] CPU: 2 PID: 164 Comm: kworker/2:2 Not tainted 4.4.0-rc1 #1
[   21.476168] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Debian-1.8.2-1 04/01/2014
[   21.476168] task: f5f83c00 ti: f5e28000 task.ti: f5e28000
[   21.476168] EIP: 0060:[<c1043177>] EFLAGS: 00010046 CPU: 2
[   21.476168] EIP is at process_one_work+0x29/0x31c
[   21.484082] EAX: 00000000 EBX: f678b2a0 ECX: 00000004 EDX: 00000000
[   21.484082] ESI: f6c69940 EDI: f5e29ef0 EBP: f5e29f0c ESP: f5e29edc
[   21.484082]  DS: 007b ES: 007b FS: 00d8 GS: 0000 SS: 0068
[   21.484082] CR0: 80050033 CR2: 000000a4 CR3: 317ad000 CR4: 00040690
[   21.484082] Stack:
[   21.484082]  00000000 f6c69950 00000000 f6c69940 c0042338 f5e29f0c c1327945 00000000
[   21.484082]  00000008 f678b2a0 f6c69940 f678b2b8 f5e29f30 c1043984 f5f83c00 f6c69970
[   21.484082]  f678b2a0 c10437d3 f6775e80 f678b2a0 c10437d3 f5e29fac c1047059 f5e29f74
[   21.484082] Call Trace:
[   21.484082]  [<c1327945>] ? _raw_spin_lock_irq+0x28/0x30
[   21.484082]  [<c1043984>] worker_thread+0x1b1/0x244
[   21.484082]  [<c10437d3>] ? rescuer_thread+0x229/0x229
[   21.484082]  [<c10437d3>] ? rescuer_thread+0x229/0x229
[   21.484082]  [<c1047059>] kthread+0x8f/0x94
[   21.484082]  [<c1327a32>] ? _raw_spin_unlock_irq+0x22/0x26
[   21.484082]  [<c1327ee9>] ret_from_kernel_thread+0x21/0x38
[   21.484082]  [<c1046fca>] ? kthread_parkme+0x19/0x19
[   21.496082] Code: 5d c3 55 89 e5 57 56 53 89 c3 83 ec 24 89 d0 89 55 e0 8d 7d e4 e8 6c d8 ff ff b9 04 00 00 00 89 45 d8 8b 43 24 89 45 dc 8b 45 d8 <8b> 40 04 8b 80 e0 00 00 00 c1 e8 05 24 01 88 45 d7 8b 45 e0 8d
[   21.496082] EIP: [<c1043177>] process_one_work+0x29/0x31c SS:ESP 0068:f5e29edc
[   21.496082] CR2: 0000000000000004
[   21.496082] ---[ end trace e362cc9cf10dae89 ]---

Reported-by: Andrew <nitr0@seti.kr.ua>
Fixes: 287f3a943fef ("pppoe: Use workqueue to die properly when a PADT is received")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pppoe.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 5e0b432..0a37f84 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -568,6 +568,9 @@ static int pppoe_create(struct net *net, struct socket *sock, int kern)
 	sk->sk_family		= PF_PPPOX;
 	sk->sk_protocol		= PX_PROTO_OE;
 
+	INIT_WORK(&pppox_sk(sk)->proto.pppoe.padt_work,
+		  pppoe_unbind_sock_work);
+
 	return 0;
 }
 
@@ -632,8 +635,6 @@ static int pppoe_connect(struct socket *sock, struct sockaddr *uservaddr,
 
 	lock_sock(sk);
 
-	INIT_WORK(&po->proto.pppoe.padt_work, pppoe_unbind_sock_work);
-
 	error = -EINVAL;
 	if (sp->sa_protocol != PX_PROTO_OE)
 		goto end;
@@ -663,8 +664,13 @@ static int pppoe_connect(struct socket *sock, struct sockaddr *uservaddr,
 			po->pppoe_dev = NULL;
 		}
 
-		memset(sk_pppox(po) + 1, 0,
-		       sizeof(struct pppox_sock) - sizeof(struct sock));
+		po->pppoe_ifindex = 0;
+		memset(&po->pppoe_pa, 0, sizeof(po->pppoe_pa));
+		memset(&po->pppoe_relay, 0, sizeof(po->pppoe_relay));
+		memset(&po->chan, 0, sizeof(po->chan));
+		po->next = NULL;
+		po->num = 0;
+
 		sk->sk_state = PPPOX_NONE;
 	}
 
-- 
2.4.1


From 2d5925b5a6011084d1fac6b8d8625ddbcb7d95a6 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Thu, 3 Dec 2015 17:21:50 +0100
Subject: [PATCH 02/34] gre6: allow to update all parameters via rtnl

[ Upstream commit 6a61d4dbf4f54b5683e0f1e58d873cecca7cb977 ]

Parameters were updated only if the kernel was unable to find the tunnel
with the new parameters, ie only if core pamareters were updated (keys,
addr, link, type).
Now it's possible to update ttl, hoplimit, flowinfo and flags.

Fixes: c12b395a4664 ("gre: Support GRE over IPv6")
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 3c7b931..e5ea177 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1571,13 +1571,11 @@ static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[],
 			return -EEXIST;
 	} else {
 		t = nt;
-
-		ip6gre_tunnel_unlink(ign, t);
-		ip6gre_tnl_change(t, &p, !tb[IFLA_MTU]);
-		ip6gre_tunnel_link(ign, t);
-		netdev_state_change(dev);
 	}
 
+	ip6gre_tunnel_unlink(ign, t);
+	ip6gre_tnl_change(t, &p, !tb[IFLA_MTU]);
+	ip6gre_tunnel_link(ign, t);
 	return 0;
 }
 
-- 
2.4.1


From 3960bc911e092832dac3f9a42b435d2ec566e412 Mon Sep 17 00:00:00 2001
From: Pavel Machek <pavel@ucw.cz>
Date: Fri, 4 Dec 2015 09:50:00 +0100
Subject: [PATCH 03/34] atl1c: Improve driver not to do order 4 GFP_ATOMIC
 allocation

[ Upstream commit f2a3771ae8aca879c32336c76ad05a017629bae2 ]

atl1c driver is doing order-4 allocation with GFP_ATOMIC
priority. That often breaks  networking after resume. Switch to
GFP_KERNEL. Still not ideal, but should be significantly better.

atl1c_setup_ring_resources() is called from .open() function, and
already uses GFP_KERNEL, so this change is safe.

Signed-off-by: Pavel Machek <pavel@ucw.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/atheros/atl1c/atl1c_main.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index 2795d6d..8b5988e 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -1016,13 +1016,12 @@ static int atl1c_setup_ring_resources(struct atl1c_adapter *adapter)
 		sizeof(struct atl1c_recv_ret_status) * rx_desc_count +
 		8 * 4;
 
-	ring_header->desc = pci_alloc_consistent(pdev, ring_header->size,
-				&ring_header->dma);
+	ring_header->desc = dma_zalloc_coherent(&pdev->dev, ring_header->size,
+						&ring_header->dma, GFP_KERNEL);
 	if (unlikely(!ring_header->desc)) {
-		dev_err(&pdev->dev, "pci_alloc_consistend failed\n");
+		dev_err(&pdev->dev, "could not get memory for DMA buffer\n");
 		goto err_nomem;
 	}
-	memset(ring_header->desc, 0, ring_header->size);
 	/* init TPD ring */
 
 	tpd_ring[0].dma = roundup(ring_header->dma, 8);
-- 
2.4.1


From cf2265157f68424a83d74a70962781c0470d3e83 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Fri, 4 Dec 2015 14:15:08 +0100
Subject: [PATCH 04/34] ipv6: keep existing flags when setting IFA_F_OPTIMISTIC
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 9a1ec4612c9bfc94d4185e3459055a37a685e575 ]

Commit 64236f3f3d74 ("ipv6: introduce IFA_F_STABLE_PRIVACY flag")
failed to update the setting of the IFA_F_OPTIMISTIC flag, causing
the IFA_F_STABLE_PRIVACY flag to be lost if IFA_F_OPTIMISTIC is set.

Cc: Erik Kline <ek@google.com>
Cc: Fernando Gont <fgont@si6networks.com>
Cc: Lorenzo Colitti <lorenzo@google.com>
Cc: YOSHIFUJI Hideaki/吉藤英明 <hideaki.yoshifuji@miraclelinux.com>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Fixes: 64236f3f3d74 ("ipv6: introduce IFA_F_STABLE_PRIVACY flag")
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 3939dd2..ff873c8 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -2453,7 +2453,7 @@ ok:
 #ifdef CONFIG_IPV6_OPTIMISTIC_DAD
 			if (in6_dev->cnf.optimistic_dad &&
 			    !net->ipv6.devconf_all->forwarding && sllao)
-				addr_flags = IFA_F_OPTIMISTIC;
+				addr_flags |= IFA_F_OPTIMISTIC;
 #endif
 
 			/* Do not allow to create too much of autoconfigured
-- 
2.4.1


From e37caf36e65b943cb28ce6ce2d7bfb3c406ec277 Mon Sep 17 00:00:00 2001
From: Jiri Benc <jbenc@redhat.com>
Date: Fri, 4 Dec 2015 13:54:03 +0100
Subject: [PATCH 05/34] vxlan: fix incorrect RCO bit in VXLAN header

[ Upstream commit c5fb8caaf91ea6a92920cf24db10cfc94d58de0f ]

Commit 3511494ce2f3d ("vxlan: Group Policy extension") changed definition of
VXLAN_HF_RCO from 0x00200000 to BIT(24). This is obviously incorrect. It's
also in violation with the RFC draft.

Fixes: 3511494ce2f3d ("vxlan: Group Policy extension")
Cc: Thomas Graf <tgraf@suug.ch>
Cc: Tom Herbert <therbert@google.com>
Signed-off-by: Jiri Benc <jbenc@redhat.com>
Acked-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/vxlan.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 480a319..f4a4972 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -79,7 +79,7 @@ struct vxlanhdr {
 };
 
 /* VXLAN header flags. */
-#define VXLAN_HF_RCO BIT(24)
+#define VXLAN_HF_RCO BIT(21)
 #define VXLAN_HF_VNI BIT(27)
 #define VXLAN_HF_GBP BIT(31)
 
-- 
2.4.1


From f7804be938a80839063eae490106d196281c763b Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Fri, 4 Dec 2015 15:14:03 -0200
Subject: [PATCH 06/34] sctp: use the same clock as if sock source timestamps
 were on

[ Upstream commit cb5e173ed7c03a0d4630ce68a95a186cce3cc872 ]

SCTP echoes a cookie o INIT ACK chunks that contains a timestamp, for
detecting stale cookies. This cookie is echoed back to the server by the
client and then that timestamp is checked.

Thing is, if the listening socket is using packet timestamping, the
cookie is encoded with ktime_get() value and checked against
ktime_get_real(), as done by __net_timestamp().

The fix is to sctp also use ktime_get_real(), so we can compare bananas
with bananas later no matter if packet timestamping was enabled or not.

Fixes: 52db882f3fc2 ("net: sctp: migrate cookie life from timeval to ktime")
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sm_make_chunk.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 7954c52..8d67d72 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -1652,7 +1652,7 @@ static sctp_cookie_param_t *sctp_pack_cookie(const struct sctp_endpoint *ep,
 
 	/* Set an expiration time for the cookie.  */
 	cookie->c.expiration = ktime_add(asoc->cookie_life,
-					 ktime_get());
+					 ktime_get_real());
 
 	/* Copy the peer's init packet.  */
 	memcpy(&cookie->c.peer_init[0], init_chunk->chunk_hdr,
@@ -1780,7 +1780,7 @@ no_hmac:
 	if (sock_flag(ep->base.sk, SOCK_TIMESTAMP))
 		kt = skb_get_ktime(skb);
 	else
-		kt = ktime_get();
+		kt = ktime_get_real();
 
 	if (!asoc && ktime_before(bear_cookie->expiration, kt)) {
 		/*
-- 
2.4.1


From 46ad18aad09a087729289c5e5f57c86d1aab8d56 Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Fri, 4 Dec 2015 15:14:04 -0200
Subject: [PATCH 07/34] sctp: update the netstamp_needed counter when copying
 sockets

[ Upstream commit 01ce63c90170283a9855d1db4fe81934dddce648 ]

Dmitry Vyukov reported that SCTP was triggering a WARN on socket destroy
related to disabling sock timestamp.

When SCTP accepts an association or peel one off, it copies sock flags
but forgot to call net_enable_timestamp() if a packet timestamping flag
was copied, leading to extra calls to net_disable_timestamp() whenever
such clones were closed.

The fix is to call net_enable_timestamp() whenever we copy a sock with
that flag on, like tcp does.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h | 2 ++
 net/core/sock.c    | 2 --
 net/sctp/socket.c  | 3 +++
 3 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index e237170..492855d 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -724,6 +724,8 @@ enum sock_flags {
 	SOCK_SELECT_ERR_QUEUE, /* Wake select on error queue */
 };
 
+#define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))
+
 static inline void sock_copy_flags(struct sock *nsk, struct sock *osk)
 {
 	nsk->sk_flags = osk->sk_flags;
diff --git a/net/core/sock.c b/net/core/sock.c
index 3307c02..d7a7fc5 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -422,8 +422,6 @@ static void sock_warn_obsolete_bsdism(const char *name)
 	}
 }
 
-#define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))
-
 static void sock_disable_timestamp(struct sock *sk, unsigned long flags)
 {
 	if (sk->sk_flags & flags) {
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 3ec88be..f19a67c 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -7195,6 +7195,9 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk,
 	newinet->mc_ttl = 1;
 	newinet->mc_index = 0;
 	newinet->mc_list = NULL;
+
+	if (newsk->sk_flags & SK_FLAGS_TIMESTAMP)
+		net_enable_timestamp();
 }
 
 static inline void sctp_copy_descendant(struct sock *sk_to,
-- 
2.4.1


From 0081745cc115ec4147644b9ed464efc1bff5846e Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Fri, 4 Dec 2015 15:14:05 -0200
Subject: [PATCH 08/34] sctp: also copy sk_tsflags when copying the socket

[ Upstream commit 50a5ffb1ef535e3c6989711c51b5d61b543a3b45 ]

As we are keeping timestamps on when copying the socket, we also have to
copy sk_tsflags.

This is needed since b9f40e21ef42 ("net-timestamp: move timestamp flags
out of sk_flags").

Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index f19a67c..84b1b50 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -7163,6 +7163,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk,
 	newsk->sk_type = sk->sk_type;
 	newsk->sk_bound_dev_if = sk->sk_bound_dev_if;
 	newsk->sk_flags = sk->sk_flags;
+	newsk->sk_tsflags = sk->sk_tsflags;
 	newsk->sk_no_check_tx = sk->sk_no_check_tx;
 	newsk->sk_no_check_rx = sk->sk_no_check_rx;
 	newsk->sk_reuse = sk->sk_reuse;
-- 
2.4.1


From f1cf5767d87c24f3e9c7a780651230cc34485c39 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Sat, 5 Dec 2015 13:01:50 +0100
Subject: [PATCH 09/34] net: cdc_mbim: add "NDP to end" quirk for Huawei E3372
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit f8c0cfa5eca902d388c0b57c7ca29a1ff2e6d8c6 ]

The Huawei E3372 (12d1:157d) needs this quirk in MBIM mode
as well. Allow this by forcing the NTB to contain only a
single NDP, and add a device specific entry for this ID.

Due to the way Huawei use device IDs, this might be applied
to other modems as well.  It is assumed that those modems
will be based on the same firmware and will need this quirk
too.  If not, it will still not harm normal usage, although
multiplexing performance could be impacted.

Cc: Enrico Mioso <mrkiko.rs@gmail.com>
Reported-by: Sami Farin <hvtaifwkbgefbaei@gmail.com>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Acked-By: Enrico Mioso <mrkiko.rs@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_mbim.c | 26 +++++++++++++++++++++++++-
 drivers/net/usb/cdc_ncm.c  | 10 +++++++++-
 2 files changed, 34 insertions(+), 2 deletions(-)

diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c
index efc18e0..b6ea6ff 100644
--- a/drivers/net/usb/cdc_mbim.c
+++ b/drivers/net/usb/cdc_mbim.c
@@ -158,7 +158,7 @@ static int cdc_mbim_bind(struct usbnet *dev, struct usb_interface *intf)
 	if (!cdc_ncm_comm_intf_is_mbim(intf->cur_altsetting))
 		goto err;
 
-	ret = cdc_ncm_bind_common(dev, intf, data_altsetting, 0);
+	ret = cdc_ncm_bind_common(dev, intf, data_altsetting, dev->driver_info->data);
 	if (ret)
 		goto err;
 
@@ -582,6 +582,26 @@ static const struct driver_info cdc_mbim_info_zlp = {
 	.tx_fixup = cdc_mbim_tx_fixup,
 };
 
+/* The spefication explicitly allows NDPs to be placed anywhere in the
+ * frame, but some devices fail unless the NDP is placed after the IP
+ * packets.  Using the CDC_NCM_FLAG_NDP_TO_END flags to force this
+ * behaviour.
+ *
+ * Note: The current implementation of this feature restricts each NTB
+ * to a single NDP, implying that multiplexed sessions cannot share an
+ * NTB. This might affect performace for multiplexed sessions.
+ */
+static const struct driver_info cdc_mbim_info_ndp_to_end = {
+	.description = "CDC MBIM",
+	.flags = FLAG_NO_SETINT | FLAG_MULTI_PACKET | FLAG_WWAN,
+	.bind = cdc_mbim_bind,
+	.unbind = cdc_mbim_unbind,
+	.manage_power = cdc_mbim_manage_power,
+	.rx_fixup = cdc_mbim_rx_fixup,
+	.tx_fixup = cdc_mbim_tx_fixup,
+	.data = CDC_NCM_FLAG_NDP_TO_END,
+};
+
 static const struct usb_device_id mbim_devs[] = {
 	/* This duplicate NCM entry is intentional. MBIM devices can
 	 * be disguised as NCM by default, and this is necessary to
@@ -597,6 +617,10 @@ static const struct usb_device_id mbim_devs[] = {
 	{ USB_VENDOR_AND_INTERFACE_INFO(0x0bdb, USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE),
 	  .driver_info = (unsigned long)&cdc_mbim_info,
 	},
+	/* Huawei E3372 fails unless NDP comes after the IP packets */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x12d1, 0x157d, USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE),
+	  .driver_info = (unsigned long)&cdc_mbim_info_ndp_to_end,
+	},
 	/* default entry */
 	{ USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE),
 	  .driver_info = (unsigned long)&cdc_mbim_info_zlp,
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index db40175..fa41a6d 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -1006,10 +1006,18 @@ static struct usb_cdc_ncm_ndp16 *cdc_ncm_ndp(struct cdc_ncm_ctx *ctx, struct sk_
 	* NTH16 header as we would normally do. NDP isn't written to the SKB yet, and
 	* the wNdpIndex field in the header is actually not consistent with reality. It will be later.
 	*/
-	if (ctx->drvflags & CDC_NCM_FLAG_NDP_TO_END)
+	if (ctx->drvflags & CDC_NCM_FLAG_NDP_TO_END) {
 		if (ctx->delayed_ndp16->dwSignature == sign)
 			return ctx->delayed_ndp16;
 
+		/* We can only push a single NDP to the end. Return
+		 * NULL to send what we've already got and queue this
+		 * skb for later.
+		 */
+		else if (ctx->delayed_ndp16->dwSignature)
+			return NULL;
+	}
+
 	/* follow the chain of NDPs, looking for a match */
 	while (ndpoffset) {
 		ndp16 = (struct usb_cdc_ncm_ndp16 *)(skb->data + ndpoffset);
-- 
2.4.1


From 9ae2d6c090172e8f1782af19b10679f15bd42350 Mon Sep 17 00:00:00 2001
From: Stefan Wahren <stefan.wahren@i2se.com>
Date: Fri, 4 Dec 2015 16:29:10 +0100
Subject: [PATCH 10/34] net: qca_spi: fix transmit queue timeout handling

[ Upstream commit ed7d42e24effbd3681e909711a7a2119a85e9217 ]

In case of a tx queue timeout every transmit is blocked until the
QCA7000 resets himself and triggers a sync which makes the driver
flushs the tx ring. So avoid this blocking situation by triggering
the sync immediately after the timeout. Waking the queue doesn't
make sense in this situation.

Signed-off-by: Stefan Wahren <stefan.wahren@i2se.com>
Fixes: 291ab06ecf67 ("net: qualcomm: new Ethernet over SPI driver for QCA7000")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qualcomm/qca_spi.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c
index 2f87909..60ccc29 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.c
+++ b/drivers/net/ethernet/qualcomm/qca_spi.c
@@ -736,9 +736,8 @@ qcaspi_netdev_tx_timeout(struct net_device *dev)
 	netdev_info(qca->net_dev, "Transmit timeout at %ld, latency %ld\n",
 		    jiffies, jiffies - dev->trans_start);
 	qca->net_dev->stats.tx_errors++;
-	/* wake the queue if there is room */
-	if (qcaspi_tx_ring_has_space(&qca->txr))
-		netif_wake_queue(dev);
+	/* Trigger tx queue flush and QCA7000 reset */
+	qca->sync = QCASPI_SYNC_UNKNOWN;
 }
 
 static int
-- 
2.4.1


From 43979766bb4c6f2e2c549793e0e659b22fb3c6de Mon Sep 17 00:00:00 2001
From: Peter Wu <peter@lekensteyn.nl>
Date: Tue, 8 Dec 2015 12:17:42 +0100
Subject: [PATCH 11/34] r8152: fix lockup when runtime PM is enabled

[ Upstream commit 90186af404ada5a47b875bf3c16d0b02bb023ea0 ]

When an interface is brought up which was previously suspended (via
runtime PM), it would hang. This happens because napi_disable is called
before napi_enable.

Solve this by avoiding napi_enable in the resume during open function
(netif_running is true when open is called, IFF_UP is set after a
successful open; netif_running is false when close is called, but IFF_UP
is then still set).

While at it, remove WORK_ENABLE check from rtl8152_open (introduced with
the original change) because it cannot happen:

 - After this patch, runtime resume will not set it during rtl8152_open.
 - When link is up, rtl8152_open is not called.
 - When link is down during system/auto suspend/resume, it is not set.

Fixes: 41cec84cf285 ("r8152: don't enable napi before rx ready")
Link: https://lkml.kernel.org/r/20151205105912.GA1766@al
Signed-off-by: Peter Wu <peter@lekensteyn.nl>
Acked-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 21 +++------------------
 1 file changed, 3 insertions(+), 18 deletions(-)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index d9427ca..2e32c41 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -3067,17 +3067,6 @@ static int rtl8152_open(struct net_device *netdev)
 
 	mutex_lock(&tp->control);
 
-	/* The WORK_ENABLE may be set when autoresume occurs */
-	if (test_bit(WORK_ENABLE, &tp->flags)) {
-		clear_bit(WORK_ENABLE, &tp->flags);
-		usb_kill_urb(tp->intr_urb);
-		cancel_delayed_work_sync(&tp->schedule);
-
-		/* disable the tx/rx, if the workqueue has enabled them. */
-		if (netif_carrier_ok(netdev))
-			tp->rtl_ops.disable(tp);
-	}
-
 	tp->rtl_ops.up(tp);
 
 	rtl8152_set_speed(tp, AUTONEG_ENABLE,
@@ -3124,12 +3113,6 @@ static int rtl8152_close(struct net_device *netdev)
 	} else {
 		mutex_lock(&tp->control);
 
-		/* The autosuspend may have been enabled and wouldn't
-		 * be disable when autoresume occurs, because the
-		 * netif_running() would be false.
-		 */
-		rtl_runtime_suspend_enable(tp, false);
-
 		tp->rtl_ops.down(tp);
 
 		mutex_unlock(&tp->control);
@@ -3512,7 +3495,7 @@ static int rtl8152_resume(struct usb_interface *intf)
 		netif_device_attach(tp->netdev);
 	}
 
-	if (netif_running(tp->netdev)) {
+	if (netif_running(tp->netdev) && tp->netdev->flags & IFF_UP) {
 		if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
 			rtl_runtime_suspend_enable(tp, false);
 			clear_bit(SELECTIVE_SUSPEND, &tp->flags);
@@ -3532,6 +3515,8 @@ static int rtl8152_resume(struct usb_interface *intf)
 		}
 		usb_submit_urb(tp->intr_urb, GFP_KERNEL);
 	} else if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
+		if (tp->netdev->flags & IFF_UP)
+			rtl_runtime_suspend_enable(tp, false);
 		clear_bit(SELECTIVE_SUSPEND, &tp->flags);
 	}
 
-- 
2.4.1


From bc386e51daba6547cb14ac06baf1f56c9274abde Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 9 Dec 2015 07:25:06 -0800
Subject: [PATCH 12/34] ipv6: sctp: clone options to avoid use after free

[ Upstream commit 9470e24f35ab81574da54e69df90c1eb4a96b43f ]

SCTP is lacking proper np->opt cloning at accept() time.

TCP and DCCP use ipv6_dup_options() helper, do the same
in SCTP.

We might later factorize this code in a common helper to avoid
future mistakes.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ipv6.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index e917d27..40677cf 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -635,6 +635,7 @@ static struct sock *sctp_v6_create_accept_sk(struct sock *sk,
 	struct sock *newsk;
 	struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
 	struct sctp6_sock *newsctp6sk;
+	struct ipv6_txoptions *opt;
 
 	newsk = sk_alloc(sock_net(sk), PF_INET6, GFP_KERNEL, sk->sk_prot, 0);
 	if (!newsk)
@@ -654,6 +655,13 @@ static struct sock *sctp_v6_create_accept_sk(struct sock *sk,
 
 	memcpy(newnp, np, sizeof(struct ipv6_pinfo));
 
+	rcu_read_lock();
+	opt = rcu_dereference(np->opt);
+	if (opt)
+		opt = ipv6_dup_options(newsk, opt);
+	RCU_INIT_POINTER(newnp->opt, opt);
+	rcu_read_unlock();
+
 	/* Initialize sk's sport, dport, rcv_saddr and daddr for getsockname()
 	 * and getpeername().
 	 */
-- 
2.4.1


From 15287a6a3cbca306a66640e371b2684e50a22565 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Wed, 9 Dec 2015 19:56:31 +0100
Subject: [PATCH 13/34] phy: micrel: Fix finding PHY properties in MAC node.

[ Upstream commit 651df2183543bc92f5dbcf99cd9e236ead0bc4c5 ]

commit 8b63ec1837fa ("phylib: Make PHYs children of their MDIO bus,
not the bus' parent.")  changed the parenting of PHY devices, making
them a child of the MDIO bus, instead of the MAC device. This broken
the Micrel PHY driver which has a deprecated feature of allowing PHY
properties to be placed into the MAC node.

In order to find the MAC node, we need to walk up the tree of devices
until we find one with an OF node attached.

Reported-by: Dinh Nguyen <dinguyen@opensource.altera.com>
Suggested-by: David Daney <david.daney@cavium.com>
Acked-by: David Daney <david.daney@cavium.com>
Fixes: 8b63ec1837fa ("phylib: Make PHYs children of their MDIO bus, not the bus' parent.")
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Tested-by: Dinh Nguyen <dinguyen@opensource.altera.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/micrel.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index cf6312f..e13ad6c 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -339,9 +339,18 @@ static int ksz9021_config_init(struct phy_device *phydev)
 {
 	const struct device *dev = &phydev->dev;
 	const struct device_node *of_node = dev->of_node;
+	const struct device *dev_walker;
 
-	if (!of_node && dev->parent->of_node)
-		of_node = dev->parent->of_node;
+	/* The Micrel driver has a deprecated option to place phy OF
+	 * properties in the MAC node. Walk up the tree of devices to
+	 * find a device with an OF node.
+	 */
+	dev_walker = &phydev->dev;
+	do {
+		of_node = dev_walker->of_node;
+		dev_walker = dev_walker->parent;
+
+	} while (!of_node && dev_walker);
 
 	if (of_node) {
 		ksz9021_load_values_from_of(phydev, of_node,
-- 
2.4.1


From 73e71dcb1df404661314ec7cb9aa27d209407d70 Mon Sep 17 00:00:00 2001
From: Joe Stringer <joe@ovn.org>
Date: Wed, 9 Dec 2015 14:07:39 -0800
Subject: [PATCH 14/34] openvswitch: Fix helper reference leak

[ Upstream commit 2f3ab9f9fc23811188b9d07d86e4d99ffee887f4 ]

If the actions (re)allocation fails, or the actions list is larger than the
maximum size, and the conntrack action is the last action when these
problems are hit, then references to helper modules may be leaked. Fix
the issue.

Fixes: cae3a2627520 ("openvswitch: Allow attaching helpers to ct action")
Signed-off-by: Joe Stringer <joe@ovn.org>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/conntrack.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 5009582..a808b0f 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -53,6 +53,8 @@ struct ovs_conntrack_info {
 	struct md_labels labels;
 };
 
+static void __ovs_ct_free_action(struct ovs_conntrack_info *ct_info);
+
 static u16 key_to_nfproto(const struct sw_flow_key *key)
 {
 	switch (ntohs(key->eth.type)) {
@@ -708,7 +710,7 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr,
 	nf_conntrack_get(&ct_info.ct->ct_general);
 	return 0;
 err_free_ct:
-	nf_conntrack_free(ct_info.ct);
+	__ovs_ct_free_action(&ct_info);
 	return err;
 }
 
@@ -750,6 +752,11 @@ void ovs_ct_free_action(const struct nlattr *a)
 {
 	struct ovs_conntrack_info *ct_info = nla_data(a);
 
+	__ovs_ct_free_action(ct_info);
+}
+
+static void __ovs_ct_free_action(struct ovs_conntrack_info *ct_info)
+{
 	if (ct_info->helper)
 		module_put(ct_info->helper->me);
 	if (ct_info->ct)
-- 
2.4.1


From 7539fb022a74bb9b69fe5ad9125b899b83001a6d Mon Sep 17 00:00:00 2001
From: Joe Stringer <joe@ovn.org>
Date: Wed, 9 Dec 2015 14:07:40 -0800
Subject: [PATCH 15/34] openvswitch: Respect conntrack zone even if invalid

[ Upstream commit d110986c5ddb1caf576e8576044c0c831e3e7fa4 ]

If userspace executes ct(zone=1), and the connection tracker determines
that the packet is invalid, then the ct_zone flow key field is populated
with the default zone rather than the zone that was specified. Even
though connection tracking failed, this field should be updated with the
value that the action specified. Fix the issue.

Fixes: 7f8a436eaa2c ("openvswitch: Add conntrack action")
Signed-off-by: Joe Stringer <joe@ovn.org>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/conntrack.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index a808b0f..cad8c4b 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -143,6 +143,7 @@ static void __ovs_ct_update_key(struct sw_flow_key *key, u8 state,
  * previously sent the packet to conntrack via the ct action.
  */
 static void ovs_ct_update_key(const struct sk_buff *skb,
+			      const struct ovs_conntrack_info *info,
 			      struct sw_flow_key *key, bool post_ct)
 {
 	const struct nf_conntrack_zone *zone = &nf_ct_zone_dflt;
@@ -160,13 +161,15 @@ static void ovs_ct_update_key(const struct sk_buff *skb,
 		zone = nf_ct_zone(ct);
 	} else if (post_ct) {
 		state = OVS_CS_F_TRACKED | OVS_CS_F_INVALID;
+		if (info)
+			zone = &info->zone;
 	}
 	__ovs_ct_update_key(key, state, zone, ct);
 }
 
 void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key)
 {
-	ovs_ct_update_key(skb, key, false);
+	ovs_ct_update_key(skb, NULL, key, false);
 }
 
 int ovs_ct_put_key(const struct sw_flow_key *key, struct sk_buff *skb)
@@ -420,7 +423,7 @@ static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key,
 		}
 	}
 
-	ovs_ct_update_key(skb, key, true);
+	ovs_ct_update_key(skb, info, key, true);
 
 	return 0;
 }
-- 
2.4.1


From 9226d3bc36e0da4f99f5fe9138f46e34b631fda8 Mon Sep 17 00:00:00 2001
From: stephen hemminger <stephen@networkplumber.org>
Date: Thu, 10 Dec 2015 09:14:20 -0800
Subject: [PATCH 16/34] uapi: export ila.h

[ Upstream commit f7fc6bc414121954c45c5f18b70e2a8717d0d5b4 ]

The file ila.h used for lightweight tunnels is being used by iproute2
but is not exported yet.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/Kbuild | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index f7b2db4..7fc5733 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -186,6 +186,7 @@ header-y += if_tunnel.h
 header-y += if_vlan.h
 header-y += if_x25.h
 header-y += igmp.h
+header-y += ila.h
 header-y += in6.h
 header-y += inet_diag.h
 header-y += in.h
-- 
2.4.1


From 204ce70323cdcff523324a2dd02f3a4fa2c01754 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Mon, 14 Dec 2015 22:03:39 +0100
Subject: [PATCH 17/34] net: add validation for the socket syscall protocol
 argument
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 79462ad02e861803b3840cc782248c7359451cd9 ]

郭永刚 reported that one could simply crash the kernel as root by
using a simple program:

	int socket_fd;
	struct sockaddr_in addr;
	addr.sin_port = 0;
	addr.sin_addr.s_addr = INADDR_ANY;
	addr.sin_family = 10;

	socket_fd = socket(10,3,0x40000000);
	connect(socket_fd , &addr,16);

AF_INET, AF_INET6 sockets actually only support 8-bit protocol
identifiers. inet_sock's skc_protocol field thus is sized accordingly,
thus larger protocol identifiers simply cut off the higher bits and
store a zero in the protocol fields.

This could lead to e.g. NULL function pointer because as a result of
the cut off inet_num is zero and we call down to inet_autobind, which
is NULL for raw sockets.

kernel: Call Trace:
kernel:  [<ffffffff816db90e>] ? inet_autobind+0x2e/0x70
kernel:  [<ffffffff816db9a4>] inet_dgram_connect+0x54/0x80
kernel:  [<ffffffff81645069>] SYSC_connect+0xd9/0x110
kernel:  [<ffffffff810ac51b>] ? ptrace_notify+0x5b/0x80
kernel:  [<ffffffff810236d8>] ? syscall_trace_enter_phase2+0x108/0x200
kernel:  [<ffffffff81645e0e>] SyS_connect+0xe/0x10
kernel:  [<ffffffff81779515>] tracesys_phase2+0x84/0x89

I found no particular commit which introduced this problem.

CVE: CVE-2015-8543
Cc: Cong Wang <cwang@twopensource.com>
Reported-by: 郭永刚 <guoyonggang@360.cn>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h     | 1 +
 net/ax25/af_ax25.c     | 3 +++
 net/decnet/af_decnet.c | 3 +++
 net/ipv4/af_inet.c     | 3 +++
 net/ipv6/af_inet6.c    | 3 +++
 net/irda/af_irda.c     | 3 +++
 6 files changed, 16 insertions(+)

diff --git a/include/net/sock.h b/include/net/sock.h
index 492855d..7ae032e 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -387,6 +387,7 @@ struct sock {
 				sk_no_check_rx : 1,
 				sk_userlocks : 4,
 				sk_protocol  : 8,
+#define SK_PROTOCOL_MAX U8_MAX
 				sk_type      : 16;
 	kmemcheck_bitfield_end(flags);
 	int			sk_wmem_queued;
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index ae3a47f..fbd0acf 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -805,6 +805,9 @@ static int ax25_create(struct net *net, struct socket *sock, int protocol,
 	struct sock *sk;
 	ax25_cb *ax25;
 
+	if (protocol < 0 || protocol > SK_PROTOCOL_MAX)
+		return -EINVAL;
+
 	if (!net_eq(net, &init_net))
 		return -EAFNOSUPPORT;
 
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 675cf94..6feddca 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -678,6 +678,9 @@ static int dn_create(struct net *net, struct socket *sock, int protocol,
 {
 	struct sock *sk;
 
+	if (protocol < 0 || protocol > SK_PROTOCOL_MAX)
+		return -EINVAL;
+
 	if (!net_eq(net, &init_net))
 		return -EAFNOSUPPORT;
 
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 1d0c3ad..4b16cf3 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -261,6 +261,9 @@ static int inet_create(struct net *net, struct socket *sock, int protocol,
 	int try_loading_module = 0;
 	int err;
 
+	if (protocol < 0 || protocol >= IPPROTO_MAX)
+		return -EINVAL;
+
 	sock->state = SS_UNCONNECTED;
 
 	/* Look for the requested type/protocol pair. */
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 38d66dd..df095ee 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -109,6 +109,9 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol,
 	int try_loading_module = 0;
 	int err;
 
+	if (protocol < 0 || protocol >= IPPROTO_MAX)
+		return -EINVAL;
+
 	/* Look for the requested type/protocol pair. */
 lookup_protocol:
 	err = -ESOCKTNOSUPPORT;
diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index fae6822..25f63a8 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -1086,6 +1086,9 @@ static int irda_create(struct net *net, struct socket *sock, int protocol,
 	struct sock *sk;
 	struct irda_sock *self;
 
+	if (protocol < 0 || protocol > SK_PROTOCOL_MAX)
+		return -EINVAL;
+
 	if (net != &init_net)
 		return -EAFNOSUPPORT;
 
-- 
2.4.1


From 3b1d8cc00ea00bb6451a2db42b98179e109ac291 Mon Sep 17 00:00:00 2001
From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Date: Fri, 4 Dec 2015 01:45:40 +0300
Subject: [PATCH 18/34] sh_eth: fix kernel oops in skb_put()

[ Upstream commit 248be83dcb3feb3f6332eb3d010a016402138484 ]

In a low memory situation the following kernel oops occurs:

Unable to handle kernel NULL pointer dereference at virtual address 00000050
pgd = 8490c000
[00000050] *pgd=4651e831, *pte=00000000, *ppte=00000000
Internal error: Oops: 17 [#1] PREEMPT ARM
Modules linked in:
CPU: 0    Not tainted  (3.4-at16 #9)
PC is at skb_put+0x10/0x98
LR is at sh_eth_poll+0x2c8/0xa10
pc : [<8035f780>]    lr : [<8028bf50>]    psr: 60000113
sp : 84eb1a90  ip : 84eb1ac8  fp : 84eb1ac4
r10: 0000003f  r9 : 000005ea  r8 : 00000000
r7 : 00000000  r6 : 940453b0  r5 : 00030000  r4 : 9381b180
r3 : 00000000  r2 : 00000000  r1 : 000005ea  r0 : 00000000
Flags: nZCv  IRQs on  FIQs on  Mode SVC_32  ISA ARM  Segment user
Control: 10c53c7d  Table: 4248c059  DAC: 00000015
Process klogd (pid: 2046, stack limit = 0x84eb02e8)
[...]

This is  because netdev_alloc_skb() fails and 'mdp->rx_skbuff[entry]' is left
NULL but sh_eth_rx() later  uses it without checking.  Add such check...

Reported-by: Yasushi SHOJI <yashi@atmark-techno.com>
Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/sh_eth.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index a484d8b..f3cbf90c 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -1481,6 +1481,7 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota)
 		if (mdp->cd->shift_rd0)
 			desc_status >>= 16;
 
+		skb = mdp->rx_skbuff[entry];
 		if (desc_status & (RD_RFS1 | RD_RFS2 | RD_RFS3 | RD_RFS4 |
 				   RD_RFS5 | RD_RFS6 | RD_RFS10)) {
 			ndev->stats.rx_errors++;
@@ -1496,12 +1497,11 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota)
 				ndev->stats.rx_missed_errors++;
 			if (desc_status & RD_RFS10)
 				ndev->stats.rx_over_errors++;
-		} else {
+		} else	if (skb) {
 			if (!mdp->cd->hw_swap)
 				sh_eth_soft_swap(
 					phys_to_virt(ALIGN(rxdesc->addr, 4)),
 					pkt_len + 2);
-			skb = mdp->rx_skbuff[entry];
 			mdp->rx_skbuff[entry] = NULL;
 			if (mdp->cd->rpadir)
 				skb_reserve(skb, NET_IP_ALIGN);
-- 
2.4.1


From 864f5d3880ba7e9e3d11f8ba725f29b7f45ae508 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 14 Dec 2015 14:08:53 -0800
Subject: [PATCH 19/34] net: fix IP early demux races

[ Upstream commit 5037e9ef9454917b047f9f3a19b4dd179fbf7cd4 ]

David Wilder reported crashes caused by dst reuse.

<quote David>
  I am seeing a crash on a distro V4.2.3 kernel caused by a double
  release of a dst_entry.  In ipv4_dst_destroy() the call to
  list_empty() finds a poisoned next pointer, indicating the dst_entry
  has already been removed from the list and freed. The crash occurs
  18 to 24 hours into a run of a network stress exerciser.
</quote>

Thanks to his detailed report and analysis, we were able to understand
the core issue.

IP early demux can associate a dst to skb, after a lookup in TCP/UDP
sockets.

When socket cache is not properly set, we want to store into
sk->sk_dst_cache the dst for future IP early demux lookups,
by acquiring a stable refcount on the dst.

Problem is this acquisition is simply using an atomic_inc(),
which works well, unless the dst was queued for destruction from
dst_release() noticing dst refcount went to zero, if DST_NOCACHE
was set on dst.

We need to make sure current refcount is not zero before incrementing
it, or risk double free as David reported.

This patch, being a stable candidate, adds two new helpers, and use
them only from IP early demux problematic paths.

It might be possible to merge in net-next skb_dst_force() and
skb_dst_force_safe(), but I prefer having the smallest patch for stable
kernels : Maybe some skb_dst_force() callers do not expect skb->dst
can suddenly be cleared.

Can probably be backported back to linux-3.6 kernels

Reported-by: David J. Wilder <dwilder@us.ibm.com>
Tested-by: David J. Wilder <dwilder@us.ibm.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst.h   | 33 +++++++++++++++++++++++++++++++++
 include/net/sock.h  |  2 +-
 net/ipv4/tcp_ipv4.c |  5 ++---
 net/ipv6/tcp_ipv6.c |  3 +--
 4 files changed, 37 insertions(+), 6 deletions(-)

diff --git a/include/net/dst.h b/include/net/dst.h
index 9261d92..e7fa2e2 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -322,6 +322,39 @@ static inline void skb_dst_force(struct sk_buff *skb)
 	}
 }
 
+/**
+ * dst_hold_safe - Take a reference on a dst if possible
+ * @dst: pointer to dst entry
+ *
+ * This helper returns false if it could not safely
+ * take a reference on a dst.
+ */
+static inline bool dst_hold_safe(struct dst_entry *dst)
+{
+	if (dst->flags & DST_NOCACHE)
+		return atomic_inc_not_zero(&dst->__refcnt);
+	dst_hold(dst);
+	return true;
+}
+
+/**
+ * skb_dst_force_safe - makes sure skb dst is refcounted
+ * @skb: buffer
+ *
+ * If dst is not yet refcounted and not destroyed, grab a ref on it.
+ */
+static inline void skb_dst_force_safe(struct sk_buff *skb)
+{
+	if (skb_dst_is_noref(skb)) {
+		struct dst_entry *dst = skb_dst(skb);
+
+		if (!dst_hold_safe(dst))
+			dst = NULL;
+
+		skb->_skb_refdst = (unsigned long)dst;
+	}
+}
+
 
 /**
  *	__skb_tunnel_rx - prepare skb for rx reinsert
diff --git a/include/net/sock.h b/include/net/sock.h
index 7ae032e..bca709a 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -801,7 +801,7 @@ void sk_stream_write_space(struct sock *sk);
 static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb)
 {
 	/* dont let skb dst not refcounted, we are going to leave rcu lock */
-	skb_dst_force(skb);
+	skb_dst_force_safe(skb);
 
 	if (!sk->sk_backlog.tail)
 		sk->sk_backlog.head = skb;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a7739c8..d77be28 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1509,7 +1509,7 @@ bool tcp_prequeue(struct sock *sk, struct sk_buff *skb)
 	if (likely(sk->sk_rx_dst))
 		skb_dst_drop(skb);
 	else
-		skb_dst_force(skb);
+		skb_dst_force_safe(skb);
 
 	__skb_queue_tail(&tp->ucopy.prequeue, skb);
 	tp->ucopy.memory += skb->truesize;
@@ -1710,8 +1710,7 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
 
-	if (dst) {
-		dst_hold(dst);
+	if (dst && dst_hold_safe(dst)) {
 		sk->sk_rx_dst = dst;
 		inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
 	}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 9e9b77b..8935dc1 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -93,10 +93,9 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
 
-	if (dst) {
+	if (dst && dst_hold_safe(dst)) {
 		const struct rt6_info *rt = (const struct rt6_info *)dst;
 
-		dst_hold(dst);
 		sk->sk_rx_dst = dst;
 		inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
 		inet6_sk(sk)->rx_dst_cookie = rt6_get_cookie(rt);
-- 
2.4.1


From 68743b8922086a882bf9ea135221a3a2229ca6be Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Mon, 14 Dec 2015 13:48:36 -0800
Subject: [PATCH 20/34] pptp: verify sockaddr_len in pptp_bind() and
 pptp_connect()

[ Upstream commit 09ccfd238e5a0e670d8178cf50180ea81ae09ae1 ]

Reported-by: Dmitry Vyukov <dvyukov@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pptp.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index 686f37d..b910cae 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -418,6 +418,9 @@ static int pptp_bind(struct socket *sock, struct sockaddr *uservaddr,
 	struct pptp_opt *opt = &po->proto.pptp;
 	int error = 0;
 
+	if (sockaddr_len < sizeof(struct sockaddr_pppox))
+		return -EINVAL;
+
 	lock_sock(sk);
 
 	opt->src_addr = sp->sa_addr.pptp;
@@ -439,6 +442,9 @@ static int pptp_connect(struct socket *sock, struct sockaddr *uservaddr,
 	struct flowi4 fl4;
 	int error = 0;
 
+	if (sockaddr_len < sizeof(struct sockaddr_pppox))
+		return -EINVAL;
+
 	if (sp->sa_protocol != PX_PROTO_PPTP)
 		return -EINVAL;
 
-- 
2.4.1


From a745f3ea43700db573910f2231d87a0d0f82e03b Mon Sep 17 00:00:00 2001
From: Vlad Yasevich <vyasevich@gmail.com>
Date: Mon, 16 Nov 2015 15:43:44 -0500
Subject: [PATCH 21/34] vlan: Fix untag operations of stacked vlans with
 REORDER_HEADER off

[ Upstream commit a6e18ff111701b4ff6947605bfbe9594ec42a6e8 ]

When we have multiple stacked vlan devices all of which have
turned off REORDER_HEADER flag, the untag operation does not
locate the ethernet addresses correctly for nested vlans.
The reason is that in case of REORDER_HEADER flag being off,
the outer vlan headers are put back and the mac_len is adjusted
to account for the presense of the header.  Then, the subsequent
untag operation, for the next level vlan, always use VLAN_ETH_HLEN
to locate the begining of the ethernet header and that ends up
being a multiple of 4 bytes short of the actuall beginning
of the mac header (the multiple depending on the how many vlan
encapsulations ethere are).

As a reslult, if there are multiple levles of vlan devices
with REODER_HEADER being off, the recevied packets end up
being dropped.

To solve this, we use skb->mac_len as the offset.  The value
is always set on receive path and starts out as a ETH_HLEN.
The value is also updated when the vlan header manupations occur
so we know it will be correct.

Signed-off-by: Vladislav Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index fab4599..160193f 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4268,7 +4268,8 @@ static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb)
 		return NULL;
 	}
 
-	memmove(skb->data - ETH_HLEN, skb->data - VLAN_ETH_HLEN, 2 * ETH_ALEN);
+	memmove(skb->data - ETH_HLEN, skb->data - skb->mac_len,
+		2 * ETH_ALEN);
 	skb->mac_header += VLAN_HLEN;
 	return skb;
 }
-- 
2.4.1


From 3555f4b7a44fb052205049353ebf858291ae722d Mon Sep 17 00:00:00 2001
From: Vlad Yasevich <vyasevich@gmail.com>
Date: Mon, 14 Dec 2015 17:44:10 -0500
Subject: [PATCH 22/34] skbuff: Fix offset error in skb_reorder_vlan_header

[ Upstream commit f654861569872d10dcb79d9d7ca219b316f94ff0 ]

skb_reorder_vlan_header is called after the vlan header has
been pulled.  As a result the offset of the begining of
the mac header has been incrased by 4 bytes (VLAN_HLEN).
When moving the mac addresses, include this incrase in
the offset calcualation so that the mac addresses are
copied correctly.

Fixes: a6e18ff1117 (vlan: Fix untag operations of stacked vlans with REORDER_HEADER off)
CC: Nicolas Dichtel <nicolas.dichtel@6wind.com>
CC: Patrick McHardy <kaber@trash.net>
Signed-off-by: Vladislav Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 160193f..1883d28 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4268,7 +4268,7 @@ static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb)
 		return NULL;
 	}
 
-	memmove(skb->data - ETH_HLEN, skb->data - skb->mac_len,
+	memmove(skb->data - ETH_HLEN, skb->data - skb->mac_len - VLAN_HLEN,
 		2 * ETH_ALEN);
 	skb->mac_header += VLAN_HLEN;
 	return skb;
-- 
2.4.1


From ed74e375974b73498576c5e5305f0e1c0445e4f9 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Wed, 16 Dec 2015 23:39:04 -0800
Subject: [PATCH 23/34] net: check both type and procotol for tcp sockets

[ Upstream commit ac5cc977991d2dce85fc734a6c71ddb33f6fe3c1 ]

Dmitry reported the following out-of-bound access:

Call Trace:
 [<ffffffff816cec2e>] __asan_report_load4_noabort+0x3e/0x40
mm/kasan/report.c:294
 [<ffffffff84affb14>] sock_setsockopt+0x1284/0x13d0 net/core/sock.c:880
 [<     inline     >] SYSC_setsockopt net/socket.c:1746
 [<ffffffff84aed7ee>] SyS_setsockopt+0x1fe/0x240 net/socket.c:1729
 [<ffffffff85c18c76>] entry_SYSCALL_64_fastpath+0x16/0x7a
arch/x86/entry/entry_64.S:185

This is because we mistake a raw socket as a tcp socket.
We should check both sk->sk_type and sk->sk_protocol to ensure
it is a tcp socket.

Willem points out __skb_complete_tx_timestamp() needs to fix as well.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 3 ++-
 net/core/sock.c   | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 1883d28..1c1f87c 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3643,7 +3643,8 @@ static void __skb_complete_tx_timestamp(struct sk_buff *skb,
 	serr->ee.ee_info = tstype;
 	if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) {
 		serr->ee.ee_data = skb_shinfo(skb)->tskey;
-		if (sk->sk_protocol == IPPROTO_TCP)
+		if (sk->sk_protocol == IPPROTO_TCP &&
+		    sk->sk_type == SOCK_STREAM)
 			serr->ee.ee_data -= sk->sk_tskey;
 	}
 
diff --git a/net/core/sock.c b/net/core/sock.c
index d7a7fc5..dbbda99 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -860,7 +860,8 @@ set_rcvbuf:
 
 		if (val & SOF_TIMESTAMPING_OPT_ID &&
 		    !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) {
-			if (sk->sk_protocol == IPPROTO_TCP) {
+			if (sk->sk_protocol == IPPROTO_TCP &&
+			    sk->sk_type == SOCK_STREAM) {
 				if (sk->sk_state != TCP_ESTABLISHED) {
 					ret = -EINVAL;
 					break;
-- 
2.4.1


From b5b6dd8ecd8cbbc029b0eaf3acc077c61d2a5611 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 15 Dec 2015 09:43:12 -0800
Subject: [PATCH 24/34] net_sched: make qdisc_tree_decrease_qlen() work for non
 mq

[ Upstream commit 225734de70cd0a9e0b978f3583a4a87939271d5e ]

Stas Nichiporovich reported a regression in his HFSC qdisc setup
on a non multi queue device.

It turns out I mistakenly added a TCQ_F_NOPARENT flag on all qdisc
allocated in qdisc_create() for non multi queue devices, which was
rather buggy. I was clearly mislead by the TCQ_F_ONETXQUEUE that is
also set here for no good reason, since it only matters for the root
qdisc.

Fixes: 4eaf3b84f288 ("net_sched: fix qdisc_tree_decrease_qlen() races")
Reported-by: Stas Nichiporovich <stasn77@gmail.com>
Tested-by: Stas Nichiporovich <stasn77@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_api.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 7ec667d..b5c2cf2 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -950,7 +950,7 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue,
 		}
 		lockdep_set_class(qdisc_lock(sch), &qdisc_tx_lock);
 		if (!netif_is_multiqueue(dev))
-			sch->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
+			sch->flags |= TCQ_F_ONETXQUEUE;
 	}
 
 	sch->handle = handle;
-- 
2.4.1


From a7ace68f6ce8e50a6c828595e1672c037f40c36a Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 15 Dec 2015 15:39:08 -0500
Subject: [PATCH 25/34] bluetooth: Validate socket address length in
 sco_sock_bind().

[ Upstream commit 5233252fce714053f0151680933571a2da9cbfb4 ]

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bluetooth/sco.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index f315c8d..15cb6c5 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -519,6 +519,9 @@ static int sco_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_le
 	if (!addr || addr->sa_family != AF_BLUETOOTH)
 		return -EINVAL;
 
+	if (addr_len < sizeof(struct sockaddr_sco))
+		return -EINVAL;
+
 	lock_sock(sk);
 
 	if (sk->sk_state != BT_OPEN) {
-- 
2.4.1


From 0d4975246467f450ce902e9dc442d647eb7ad516 Mon Sep 17 00:00:00 2001
From: "tadeusz.struk@intel.com" <tadeusz.struk@intel.com>
Date: Tue, 15 Dec 2015 10:46:17 -0800
Subject: [PATCH 26/34] net: fix uninitialized variable issue

[ Upstream commit 130ed5d105dde141e7fe60d5440aa53e0a84f13b ]

msg_iocb needs to be initialized on the recv/recvfrom path.
Otherwise afalg will wrongly interpret it as an async call.

Cc: stable@vger.kernel.org
Reported-by: Harald Freudenberger <freude@linux.vnet.ibm.com>
Signed-off-by: Tadeusz Struk <tadeusz.struk@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/socket.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/socket.c b/net/socket.c
index 9963a0b..f3fbe17 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1702,6 +1702,7 @@ SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size,
 	msg.msg_name = addr ? (struct sockaddr *)&address : NULL;
 	/* We assume all kernel code knows the size of sockaddr_storage */
 	msg.msg_namelen = 0;
+	msg.msg_iocb = NULL;
 	if (sock->file->f_flags & O_NONBLOCK)
 		flags |= MSG_DONTWAIT;
 	err = sock_recvmsg(sock, &msg, iov_iter_count(&msg.msg_iter), flags);
-- 
2.4.1


From 055a98ed38bb76ad811feec778f287e47d20bf41 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Tue, 15 Dec 2015 22:59:12 +0100
Subject: [PATCH 27/34] ipv6: automatically enable stable privacy mode if
 stable_secret set
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 9b29c6962b70f232cde4076b1020191e1be0889d ]

Bjørn reported that while we switch all interfaces to privacy stable mode
when setting the secret, we don't set this mode for new interfaces. This
does not make sense, so change this behaviour.

Fixes: 622c81d57b392cc ("ipv6: generation of stable privacy addresses for link-local and autoconf")
Reported-by: Bjørn Mork <bjorn@mork.no>
Cc: Bjørn Mork <bjorn@mork.no>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index ff873c8..ddd3511 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -349,6 +349,12 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
 	setup_timer(&ndev->rs_timer, addrconf_rs_timer,
 		    (unsigned long)ndev);
 	memcpy(&ndev->cnf, dev_net(dev)->ipv6.devconf_dflt, sizeof(ndev->cnf));
+
+	if (ndev->cnf.stable_secret.initialized)
+		ndev->addr_gen_mode = IN6_ADDR_GEN_MODE_STABLE_PRIVACY;
+	else
+		ndev->addr_gen_mode = IN6_ADDR_GEN_MODE_EUI64;
+
 	ndev->cnf.mtu6 = dev->mtu;
 	ndev->cnf.sysctl = NULL;
 	ndev->nd_parms = neigh_parms_alloc(dev, &nd_tbl);
-- 
2.4.1


From e7763d6d443faf1a4a4026d3e8e98843784606c2 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 15 Dec 2015 20:56:44 -0800
Subject: [PATCH 28/34] inet: tcp: fix inetpeer_set_addr_v4()

[ Upstream commit 887dc9f2cef6e98dcccf807da5e6faf4f60ba483 ]

David Ahern added a vif field in the a4 part of inetpeer_addr struct.

This broke IPv4 TCP fast open client side and more generally tcp metrics
cache, because inetpeer_addr_cmp() is now comparing two u32 instead of
one.

inetpeer_set_addr_v4() needs to properly init vif field, otherwise
the comparison result depends on uninitialized data.

Fixes: 192132b9a034 ("net: Add support for VRFs to inetpeer cache")
Reported-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inetpeer.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index 4a6009d..235c781 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -78,6 +78,7 @@ void inet_initpeers(void) __init;
 static inline void inetpeer_set_addr_v4(struct inetpeer_addr *iaddr, __be32 ip)
 {
 	iaddr->a4.addr = ip;
+	iaddr->a4.vif = 0;
 	iaddr->family = AF_INET;
 }
 
-- 
2.4.1


From dc6f25bdfbf1027db505506d8795fef1234f342c Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Wed, 16 Dec 2015 18:13:14 +0800
Subject: [PATCH 29/34] rhashtable: Enforce minimum size on initial hash table

[ Upstream commit 3a324606bbabfc30084ce9d08169910773ba9a92 ]

William Hua <william.hua@canonical.com> wrote:
>
> I wasn't aware there was an enforced minimum size. I simply set the
> nelem_hint in the rhastable_params struct to 1, expecting it to grow as
> needed. This caused a segfault afterwards when trying to insert an
> element.

OK we're doing the size computation before we enforce the limit
on min_size.

---8<---
We need to do the initial hash table size computation after we
have obtained the correct min_size/max_size parameters.  Otherwise
we may end up with a hash table whose size is outside the allowed
envelope.

Fixes: a998f712f77e ("rhashtable: Round up/down min/max_size to...")
Reported-by: William Hua <william.hua@canonical.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 lib/rhashtable.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index a54ff89..d2daf67e 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -723,9 +723,6 @@ int rhashtable_init(struct rhashtable *ht,
 	if (params->nulls_base && params->nulls_base < (1U << RHT_BASE_SHIFT))
 		return -EINVAL;
 
-	if (params->nelem_hint)
-		size = rounded_hashtable_size(params);
-
 	memset(ht, 0, sizeof(*ht));
 	mutex_init(&ht->mutex);
 	spin_lock_init(&ht->lock);
@@ -745,6 +742,9 @@ int rhashtable_init(struct rhashtable *ht,
 
 	ht->p.min_size = max(ht->p.min_size, HASH_MIN_SIZE);
 
+	if (params->nelem_hint)
+		size = rounded_hashtable_size(&ht->p);
+
 	/* The maximum (not average) chain length grows with the
 	 * size of the hash table, at a rate of (log N)/(log log N).
 	 * The value of 16 is selected so that even if the hash
-- 
2.4.1


From b91eef0e59aebcdaceb9bfeb61aafe0a345d2d81 Mon Sep 17 00:00:00 2001
From: Hamish Martin <hamish.martin@alliedtelesis.co.nz>
Date: Tue, 15 Dec 2015 14:14:50 +1300
Subject: [PATCH 30/34] gianfar: Don't enable RX Filer if not supported

[ Upstream commit 7bff47da1ee23d00d1257905f2944c29594f799d ]

After commit 15bf176db1fb ("gianfar: Don't enable the Filer w/o the
Parser"), 'TSEC' model controllers (for example as seen on MPC8541E)
always have 8 bytes stripped from the front of received frames.
Only 'eTSEC' gianfar controllers have the RX Filer capability (amongst
other enhancements). Previously this was treated as always enabled
for both 'TSEC' and 'eTSEC' controllers.
In commit 15bf176db1fb ("gianfar: Don't enable the Filer w/o the Parser")
a subtle change was made to the setting of 'uses_rxfcb' to effectively
always set it (since 'rx_filer_enable' was always true). This had the
side-effect of always stripping 8 bytes from the front of received frames
on 'TSEC' type controllers.

We now only enable the RX Filer capability on controller types that
support it, thereby avoiding the issue for 'TSEC' type controllers.

Reviewed-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Reviewed-by: Mark Tomlinson <mark.tomlinson@alliedtelesis.co.nz>
Signed-off-by: Hamish Martin <hamish.martin@alliedtelesis.co.nz>
Reviewed-by: Claudiu Manoil <claudiu.manoil@freescale.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/gianfar.c | 8 +++++---
 drivers/net/ethernet/freescale/gianfar.h | 1 +
 2 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index ce38d26..bcb933e 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -894,7 +894,8 @@ static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev)
 				     FSL_GIANFAR_DEV_HAS_VLAN |
 				     FSL_GIANFAR_DEV_HAS_MAGIC_PACKET |
 				     FSL_GIANFAR_DEV_HAS_EXTENDED_HASH |
-				     FSL_GIANFAR_DEV_HAS_TIMER;
+				     FSL_GIANFAR_DEV_HAS_TIMER |
+				     FSL_GIANFAR_DEV_HAS_RX_FILER;
 
 	err = of_property_read_string(np, "phy-connection-type", &ctype);
 
@@ -1393,8 +1394,9 @@ static int gfar_probe(struct platform_device *ofdev)
 		priv->rx_queue[i]->rxic = DEFAULT_RXIC;
 	}
 
-	/* always enable rx filer */
-	priv->rx_filer_enable = 1;
+	/* Always enable rx filer if available */
+	priv->rx_filer_enable =
+	    (priv->device_flags & FSL_GIANFAR_DEV_HAS_RX_FILER) ? 1 : 0;
 	/* Enable most messages by default */
 	priv->msg_enable = (NETIF_MSG_IFUP << 1 ) - 1;
 	/* use pritority h/w tx queue scheduling for single queue devices */
diff --git a/drivers/net/ethernet/freescale/gianfar.h b/drivers/net/ethernet/freescale/gianfar.h
index 8c19948..3755372 100644
--- a/drivers/net/ethernet/freescale/gianfar.h
+++ b/drivers/net/ethernet/freescale/gianfar.h
@@ -917,6 +917,7 @@ struct gfar {
 #define FSL_GIANFAR_DEV_HAS_BD_STASHING		0x00000200
 #define FSL_GIANFAR_DEV_HAS_BUF_STASHING	0x00000400
 #define FSL_GIANFAR_DEV_HAS_TIMER		0x00000800
+#define FSL_GIANFAR_DEV_HAS_RX_FILER		0x00002000
 
 #if (MAXGROUPS == 2)
 #define DEFAULT_MAPPING 	0xAA
-- 
2.4.1


From e8fcabcaa1cc5d503b1dd7d94d9bb83e13610e96 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Tue, 15 Dec 2015 21:01:53 +0100
Subject: [PATCH 31/34] fou: clean up socket with kfree_rcu

[ Upstream commit 3036facbb7be3a169e35be3b271162b0fa564a2d ]

fou->udp_offloads is managed by RCU. As it is actually included inside
the fou sockets, we cannot let the memory go out of scope before a grace
period. We either can synchronize_rcu or switch over to kfree_rcu to
manage the sockets. kfree_rcu seems appropriate as it is used by vxlan
and geneve.

Fixes: 23461551c00628c ("fou: Support for foo-over-udp RX path")
Cc: Tom Herbert <tom@herbertland.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fou.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index e0fcbbb..bd903fe 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -24,6 +24,7 @@ struct fou {
 	u16 type;
 	struct udp_offload udp_offloads;
 	struct list_head list;
+	struct rcu_head rcu;
 };
 
 #define FOU_F_REMCSUM_NOPARTIAL BIT(0)
@@ -417,7 +418,7 @@ static void fou_release(struct fou *fou)
 	list_del(&fou->list);
 	udp_tunnel_sock_release(sock);
 
-	kfree(fou);
+	kfree_rcu(fou, rcu);
 }
 
 static int fou_encap_init(struct sock *sk, struct fou *fou, struct fou_cfg *cfg)
-- 
2.4.1


From 99450d55526ae8c64f343738542527c42e30ff78 Mon Sep 17 00:00:00 2001
From: Rainer Weikusat <rweikusat@mobileactivedefense.com>
Date: Wed, 16 Dec 2015 20:09:25 +0000
Subject: [PATCH 32/34] af_unix: Revert 'lock_interruptible' in stream receive
 code

[ Upstream commit 3822b5c2fc62e3de8a0f33806ff279fb7df92432 ]

With b3ca9b02b00704053a38bfe4c31dbbb9c13595d0, the AF_UNIX SOCK_STREAM
receive code was changed from using mutex_lock(&u->readlock) to
mutex_lock_interruptible(&u->readlock) to prevent signals from being
delayed for an indefinite time if a thread sleeping on the mutex
happened to be selected for handling the signal. But this was never a
problem with the stream receive code (as opposed to its datagram
counterpart) as that never went to sleep waiting for new messages with the
mutex held and thus, wouldn't cause secondary readers to block on the
mutex waiting for the sleeping primary reader. As the interruptible
locking makes the code more complicated in exchange for no benefit,
change it back to using mutex_lock.

Signed-off-by: Rainer Weikusat <rweikusat@mobileactivedefense.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c | 13 +++----------
 1 file changed, 3 insertions(+), 10 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 128b098..0fc6dba 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2255,14 +2255,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state)
 	/* Lock the socket to prevent queue disordering
 	 * while sleeps in memcpy_tomsg
 	 */
-	err = mutex_lock_interruptible(&u->readlock);
-	if (unlikely(err)) {
-		/* recvmsg() in non blocking mode is supposed to return -EAGAIN
-		 * sk_rcvtimeo is not honored by mutex_lock_interruptible()
-		 */
-		err = noblock ? -EAGAIN : -ERESTARTSYS;
-		goto out;
-	}
+	mutex_lock(&u->readlock);
 
 	if (flags & MSG_PEEK)
 		skip = sk_peek_offset(sk, flags);
@@ -2306,12 +2299,12 @@ again:
 			timeo = unix_stream_data_wait(sk, timeo, last,
 						      last_len);
 
-			if (signal_pending(current) ||
-			    mutex_lock_interruptible(&u->readlock)) {
+			if (signal_pending(current)) {
 				err = sock_intr_errno(timeo);
 				goto out;
 			}
 
+			mutex_lock(&u->readlock);
 			continue;
 unlock:
 			unix_state_unlock(sk);
-- 
2.4.1


From dc9c6c2fb77bda57cc2b06d2a2b1d1befd3819fc Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 16 Dec 2015 13:53:10 -0800
Subject: [PATCH 33/34] tcp: restore fastopen with no data in SYN packet

[ Upstream commit 07e100f984975cb0417a7d5e626d0409efbad478 ]

Yuchung tracked a regression caused by commit 57be5bdad759 ("ip: convert
tcp_sendmsg() to iov_iter primitives") for TCP Fast Open.

Some Fast Open users do not actually add any data in the SYN packet.

Fixes: 57be5bdad759 ("ip: convert tcp_sendmsg() to iov_iter primitives")
Reported-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 23 ++++++++++++-----------
 1 file changed, 12 insertions(+), 11 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 3dbee0d..c958596 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3147,7 +3147,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_fastopen_request *fo = tp->fastopen_req;
-	int syn_loss = 0, space, err = 0, copied;
+	int syn_loss = 0, space, err = 0;
 	unsigned long last_syn_loss = 0;
 	struct sk_buff *syn_data;
 
@@ -3185,17 +3185,18 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 		goto fallback;
 	syn_data->ip_summed = CHECKSUM_PARTIAL;
 	memcpy(syn_data->cb, syn->cb, sizeof(syn->cb));
-	copied = copy_from_iter(skb_put(syn_data, space), space,
-				&fo->data->msg_iter);
-	if (unlikely(!copied)) {
-		kfree_skb(syn_data);
-		goto fallback;
-	}
-	if (copied != space) {
-		skb_trim(syn_data, copied);
-		space = copied;
+	if (space) {
+		int copied = copy_from_iter(skb_put(syn_data, space), space,
+					    &fo->data->msg_iter);
+		if (unlikely(!copied)) {
+			kfree_skb(syn_data);
+			goto fallback;
+		}
+		if (copied != space) {
+			skb_trim(syn_data, copied);
+			space = copied;
+		}
 	}
-
 	/* No more data pending in inet_wait_for_connect() */
 	if (space == fo->size)
 		fo->data = NULL;
-- 
2.4.1


From 51a41cd14356285e5e69c7657c55061a92e7ed79 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Wed, 16 Dec 2015 16:45:54 +0800
Subject: [PATCH 34/34] rhashtable: Fix walker list corruption

[ Upstream commit c6ff5268293ef98e48a99597e765ffc417e39fa5 ]

The commit ba7c95ea3870fe7b847466d39a049ab6f156aa2c ("rhashtable:
Fix sleeping inside RCU critical section in walk_stop") introduced
a new spinlock for the walker list.  However, it did not convert
all existing users of the list over to the new spin lock.  Some
continued to use the old mutext for this purpose.  This obviously
led to corruption of the list.

The fix is to use the spin lock everywhere where we touch the list.

This also allows us to do rcu_rad_lock before we take the lock in
rhashtable_walk_start.  With the old mutex this would've deadlocked
but it's safe with the new spin lock.

Fixes: ba7c95ea3870 ("rhashtable: Fix sleeping inside RCU...")
Reported-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 lib/rhashtable.c | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index d2daf67e..aa388a7 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -503,10 +503,11 @@ int rhashtable_walk_init(struct rhashtable *ht, struct rhashtable_iter *iter)
 	if (!iter->walker)
 		return -ENOMEM;
 
-	mutex_lock(&ht->mutex);
-	iter->walker->tbl = rht_dereference(ht->tbl, ht);
+	spin_lock(&ht->lock);
+	iter->walker->tbl =
+		rcu_dereference_protected(ht->tbl, lockdep_is_held(&ht->lock));
 	list_add(&iter->walker->list, &iter->walker->tbl->walkers);
-	mutex_unlock(&ht->mutex);
+	spin_unlock(&ht->lock);
 
 	return 0;
 }
@@ -520,10 +521,10 @@ EXPORT_SYMBOL_GPL(rhashtable_walk_init);
  */
 void rhashtable_walk_exit(struct rhashtable_iter *iter)
 {
-	mutex_lock(&iter->ht->mutex);
+	spin_lock(&iter->ht->lock);
 	if (iter->walker->tbl)
 		list_del(&iter->walker->list);
-	mutex_unlock(&iter->ht->mutex);
+	spin_unlock(&iter->ht->lock);
 	kfree(iter->walker);
 }
 EXPORT_SYMBOL_GPL(rhashtable_walk_exit);
@@ -547,14 +548,12 @@ int rhashtable_walk_start(struct rhashtable_iter *iter)
 {
 	struct rhashtable *ht = iter->ht;
 
-	mutex_lock(&ht->mutex);
+	rcu_read_lock();
 
+	spin_lock(&ht->lock);
 	if (iter->walker->tbl)
 		list_del(&iter->walker->list);
-
-	rcu_read_lock();
-
-	mutex_unlock(&ht->mutex);
+	spin_unlock(&ht->lock);
 
 	if (!iter->walker->tbl) {
 		iter->walker->tbl = rht_dereference_rcu(ht->tbl, ht);
-- 
2.4.1

Re: [PATCHES] Networking

[Greg KH]

On Tue, Dec 22, 2015 at 04:51:57PM -0500, David Miller wrote:
> 
> Please queue up the following bug fixes for 3.18.x, 4.1.x, and
> 4.3.x -stable, respectively.
> 
> Thanks!

Thanks for the patches, now queued up to the trees I care about.

greg k-h

Re: [PATCHES] Networking

[Josh Boyer]

On Tue, Jan 19, 2016 at 12:20 AM, Greg KH <greg@kroah.com> wrote:
> On Tue, Dec 22, 2015 at 04:51:57PM -0500, David Miller wrote:
>>
>> Please queue up the following bug fixes for 3.18.x, 4.1.x, and
>> 4.3.x -stable, respectively.
>>
>> Thanks!
>
> Thanks for the patches, now queued up to the trees I care about.

Hi Greg.  Looks like you only queued up patches in the 3.10 and 3.14
trees.  Does that mean you aren't going to do another 4.3.y release?
You have patches sitting in the queue from Dave's last set, and you
didn't add these so I'm confused.

josh

Re: [PATCHES] Networking

[Josh Boyer]

On Tue, Jan 19, 2016 at 7:00 AM, Josh Boyer <jwboyer@fedoraproject.org> wrote:
> On Tue, Jan 19, 2016 at 12:20 AM, Greg KH <greg@kroah.com> wrote:
>> On Tue, Dec 22, 2015 at 04:51:57PM -0500, David Miller wrote:
>>>
>>> Please queue up the following bug fixes for 3.18.x, 4.1.x, and
>>> 4.3.x -stable, respectively.
>>>
>>> Thanks!
>>
>> Thanks for the patches, now queued up to the trees I care about.
>
> Hi Greg.  Looks like you only queued up patches in the 3.10 and 3.14
> trees.  Does that mean you aren't going to do another 4.3.y release?
> You have patches sitting in the queue from Dave's last set, and you
> didn't add these so I'm confused.

OK, I am confused and I sorted it out sort of.  The patches in
stable-queue/queue-4.3 are this set, not the previous set.  My mistake
and my apologies.

I am still curious if 4.3.y is going to get another release though
given 4.4.1 should be coming out relatively soon.

josh

Re: [PATCHES] Networking

[Greg KH]

On Tue, Jan 19, 2016 at 08:29:48AM -0500, Josh Boyer wrote:
> On Tue, Jan 19, 2016 at 7:00 AM, Josh Boyer <jwboyer@fedoraproject.org> wrote:
> > On Tue, Jan 19, 2016 at 12:20 AM, Greg KH <greg@kroah.com> wrote:
> >> On Tue, Dec 22, 2015 at 04:51:57PM -0500, David Miller wrote:
> >>>
> >>> Please queue up the following bug fixes for 3.18.x, 4.1.x, and
> >>> 4.3.x -stable, respectively.
> >>>
> >>> Thanks!
> >>
> >> Thanks for the patches, now queued up to the trees I care about.
> >
> > Hi Greg.  Looks like you only queued up patches in the 3.10 and 3.14
> > trees.  Does that mean you aren't going to do another 4.3.y release?
> > You have patches sitting in the queue from Dave's last set, and you
> > didn't add these so I'm confused.
> 
> OK, I am confused and I sorted it out sort of.  The patches in
> stable-queue/queue-4.3 are this set, not the previous set.  My mistake
> and my apologies.
> 
> I am still curious if 4.3.y is going to get another release though
> given 4.4.1 should be coming out relatively soon.

4.4.1 can't come out until 4.5-rc1 is out, so yes, I'll be doing at
least one more 4.3.y release, if not a few more.

thanks,

greg k-h

Re: [PATCHES] Networking

[Josh Boyer]

On Tue, Jan 19, 2016 at 12:39 PM, Greg KH <greg@kroah.com> wrote:
> On Tue, Jan 19, 2016 at 08:29:48AM -0500, Josh Boyer wrote:
>> On Tue, Jan 19, 2016 at 7:00 AM, Josh Boyer <jwboyer@fedoraproject.org> wrote:
>> > On Tue, Jan 19, 2016 at 12:20 AM, Greg KH <greg@kroah.com> wrote:
>> >> On Tue, Dec 22, 2015 at 04:51:57PM -0500, David Miller wrote:
>> >>>
>> >>> Please queue up the following bug fixes for 3.18.x, 4.1.x, and
>> >>> 4.3.x -stable, respectively.
>> >>>
>> >>> Thanks!
>> >>
>> >> Thanks for the patches, now queued up to the trees I care about.
>> >
>> > Hi Greg.  Looks like you only queued up patches in the 3.10 and 3.14
>> > trees.  Does that mean you aren't going to do another 4.3.y release?
>> > You have patches sitting in the queue from Dave's last set, and you
>> > didn't add these so I'm confused.
>>
>> OK, I am confused and I sorted it out sort of.  The patches in
>> stable-queue/queue-4.3 are this set, not the previous set.  My mistake
>> and my apologies.
>>
>> I am still curious if 4.3.y is going to get another release though
>> given 4.4.1 should be coming out relatively soon.
>
> 4.4.1 can't come out until 4.5-rc1 is out, so yes, I'll be doing at
> least one more 4.3.y release, if not a few more.

Thanks.  Good to know.

josh

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 120 bytes --]


Please queue up the following networking bug fixes for 4.4.x, 4.3.1, 4.1.x, and
3.18.x -stable, respectively.

Thanks!

[-- Attachment #2: net_44.mbox --]
[-- Type: Application/Octet-Stream, Size: 69799 bytes --]

From cabe7ee5a4d4b1addcd6c85f3755e6912e536b16 Mon Sep 17 00:00:00 2001
From: willy tarreau <w@1wt.eu>
Date: Sun, 10 Jan 2016 07:54:56 +0100
Subject: [PATCH 01/24] unix: properly account for FDs passed over unix sockets

[ Upstream commit 712f4aad406bb1ed67f3f98d04c044191f0ff593 ]

It is possible for a process to allocate and accumulate far more FDs than
the process' limit by sending them over a unix socket then closing them
to keep the process' fd count low.

This change addresses this problem by keeping track of the number of FDs
in flight per user and preventing non-privileged processes from having
more FDs in flight than their configured FD limit.

Reported-by: socketpair@gmail.com
Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Mitigates: CVE-2013-4312 (Linux 2.0+)
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/sched.h |  1 +
 net/unix/af_unix.c    | 24 ++++++++++++++++++++----
 net/unix/garbage.c    | 13 ++++++++-----
 3 files changed, 29 insertions(+), 9 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index fa39434..21a6e96 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -830,6 +830,7 @@ struct user_struct {
 	unsigned long mq_bytes;	/* How many bytes can be allocated to mqueue? */
 #endif
 	unsigned long locked_shm; /* How many pages of mlocked shm ? */
+	unsigned long unix_inflight;	/* How many files in flight in unix sockets */
 
 #ifdef CONFIG_KEYS
 	struct key *uid_keyring;	/* UID specific keyring */
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index ef05cd9..e3f85bc 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1513,6 +1513,21 @@ static void unix_destruct_scm(struct sk_buff *skb)
 	sock_wfree(skb);
 }
 
+/*
+ * The "user->unix_inflight" variable is protected by the garbage
+ * collection lock, and we just read it locklessly here. If you go
+ * over the limit, there might be a tiny race in actually noticing
+ * it across threads. Tough.
+ */
+static inline bool too_many_unix_fds(struct task_struct *p)
+{
+	struct user_struct *user = current_user();
+
+	if (unlikely(user->unix_inflight > task_rlimit(p, RLIMIT_NOFILE)))
+		return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN);
+	return false;
+}
+
 #define MAX_RECURSION_LEVEL 4
 
 static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
@@ -1521,6 +1536,9 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
 	unsigned char max_level = 0;
 	int unix_sock_count = 0;
 
+	if (too_many_unix_fds(current))
+		return -ETOOMANYREFS;
+
 	for (i = scm->fp->count - 1; i >= 0; i--) {
 		struct sock *sk = unix_get_socket(scm->fp->fp[i]);
 
@@ -1542,10 +1560,8 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
 	if (!UNIXCB(skb).fp)
 		return -ENOMEM;
 
-	if (unix_sock_count) {
-		for (i = scm->fp->count - 1; i >= 0; i--)
-			unix_inflight(scm->fp->fp[i]);
-	}
+	for (i = scm->fp->count - 1; i >= 0; i--)
+		unix_inflight(scm->fp->fp[i]);
 	return max_level;
 }
 
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index a73a226..8fcdc22 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -120,11 +120,11 @@ void unix_inflight(struct file *fp)
 {
 	struct sock *s = unix_get_socket(fp);
 
+	spin_lock(&unix_gc_lock);
+
 	if (s) {
 		struct unix_sock *u = unix_sk(s);
 
-		spin_lock(&unix_gc_lock);
-
 		if (atomic_long_inc_return(&u->inflight) == 1) {
 			BUG_ON(!list_empty(&u->link));
 			list_add_tail(&u->link, &gc_inflight_list);
@@ -132,25 +132,28 @@ void unix_inflight(struct file *fp)
 			BUG_ON(list_empty(&u->link));
 		}
 		unix_tot_inflight++;
-		spin_unlock(&unix_gc_lock);
 	}
+	fp->f_cred->user->unix_inflight++;
+	spin_unlock(&unix_gc_lock);
 }
 
 void unix_notinflight(struct file *fp)
 {
 	struct sock *s = unix_get_socket(fp);
 
+	spin_lock(&unix_gc_lock);
+
 	if (s) {
 		struct unix_sock *u = unix_sk(s);
 
-		spin_lock(&unix_gc_lock);
 		BUG_ON(list_empty(&u->link));
 
 		if (atomic_long_dec_and_test(&u->inflight))
 			list_del_init(&u->link);
 		unix_tot_inflight--;
-		spin_unlock(&unix_gc_lock);
 	}
+	fp->f_cred->user->unix_inflight--;
+	spin_unlock(&unix_gc_lock);
 }
 
 static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *),
-- 
2.1.0


From 57e347bd3d41655a6a844983b4b738915572bf58 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Thu, 7 Jan 2016 11:26:53 +0100
Subject: [PATCH 02/24] vxlan: fix test which detect duplicate vxlan iface

[ Upstream commit 07b9b37c227cb8d88d478b4a9c5634fee514ede1 ]

When a vxlan interface is created, the driver checks that there is not
another vxlan interface with the same properties. To do this, it checks
the existing vxlan udp socket. Since commit 1c51a9159dde, the creation of
the vxlan socket is done only when the interface is set up, thus it breaks
that test.

Example:
$ ip l a vxlan10 type vxlan id 10 group 239.0.0.10 dev eth0 dstport 0
$ ip l a vxlan11 type vxlan id 10 group 239.0.0.10 dev eth0 dstport 0
$ ip -br l | grep vxlan
vxlan10          DOWN           f2:55:1c:6a:fb:00 <BROADCAST,MULTICAST>
vxlan11          DOWN           7a:cb:b9:38:59:0d <BROADCAST,MULTICAST>

Instead of checking sockets, let's loop over the vxlan iface list.

Fixes: 1c51a9159dde ("vxlan: fix race caused by dropping rtnl_unlock")
Reported-by: Thomas Faivre <thomas.faivre@6wind.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index ba363ce..405a7b6 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2751,7 +2751,7 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 			       struct vxlan_config *conf)
 {
 	struct vxlan_net *vn = net_generic(src_net, vxlan_net_id);
-	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_dev *vxlan = netdev_priv(dev), *tmp;
 	struct vxlan_rdst *dst = &vxlan->default_dst;
 	unsigned short needed_headroom = ETH_HLEN;
 	int err;
@@ -2817,9 +2817,15 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 	if (!vxlan->cfg.age_interval)
 		vxlan->cfg.age_interval = FDB_AGE_DEFAULT;
 
-	if (vxlan_find_vni(src_net, conf->vni, use_ipv6 ? AF_INET6 : AF_INET,
-			   vxlan->cfg.dst_port, vxlan->flags))
+	list_for_each_entry(tmp, &vn->vxlan_list, next) {
+		if (tmp->cfg.vni == conf->vni &&
+		    (tmp->default_dst.remote_ip.sa.sa_family == AF_INET6 ||
+		     tmp->cfg.saddr.sa.sa_family == AF_INET6) == use_ipv6 &&
+		    tmp->cfg.dst_port == vxlan->cfg.dst_port &&
+		    (tmp->flags & VXLAN_F_RCV_FLAGS) ==
+		    (vxlan->flags & VXLAN_F_RCV_FLAGS))
 		return -EEXIST;
+	}
 
 	dev->ethtool_ops = &vxlan_ethtool_ops;
 
-- 
2.1.0


From c471f16ed19665aa872674fe0d61a2e99082e1d9 Mon Sep 17 00:00:00 2001
From: Sasha Levin <sasha.levin@oracle.com>
Date: Thu, 7 Jan 2016 14:52:43 -0500
Subject: [PATCH 03/24] net: sctp: prevent writes to cookie_hmac_alg from
 accessing invalid memory

[ Upstream commit 320f1a4a175e7cd5d3f006f92b4d4d3e2cbb7bb5 ]

proc_dostring() needs an initialized destination string, while the one
provided in proc_sctp_do_hmac_alg() contains stack garbage.

Thus, writing to cookie_hmac_alg would strlen() that garbage and end up
accessing invalid memory.

Fixes: 3c68198e7 ("sctp: Make hmac algorithm selection for cookie generation dynamic")
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sysctl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index 26d50c5..3e0fc51 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -320,7 +320,7 @@ static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write,
 	struct ctl_table tbl;
 	bool changed = false;
 	char *none = "none";
-	char tmp[8];
+	char tmp[8] = {0};
 	int ret;
 
 	memset(&tbl, 0, sizeof(struct ctl_table));
-- 
2.1.0


From 56af53dace5fcb19a63c352434490ba0a080448d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 8 Jan 2016 09:35:51 -0800
Subject: [PATCH 04/24] ipv6: tcp: add rcu locking in tcp_v6_send_synack()

[ Upstream commit 3e4006f0b86a5ae5eb0e8215f9a9e1db24506977 ]

When first SYNACK is sent, we already hold rcu_read_lock(), but this
is not true if a SYNACK is retransmitted, as a timer (soft) interrupt
does not hold rcu_read_lock()

Fixes: 45f6fad84cc30 ("ipv6: add complete rcu protection around np->opt")
Reported-by: Dave Jones <davej@codemonkey.org.uk>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/tcp_ipv6.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 6b8a8a9..bd100b4 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -462,8 +462,10 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
 		if (np->repflow && ireq->pktopts)
 			fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));
 
+		rcu_read_lock();
 		err = ip6_xmit(sk, skb, fl6, rcu_dereference(np->opt),
 			       np->tclass);
+		rcu_read_unlock();
 		err = net_xmit_eval(err);
 	}
 
-- 
2.1.0


From a5083e3ca664868194859f8bd77267b0ea8569a0 Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Mon, 11 Jan 2016 13:42:43 -0500
Subject: [PATCH 05/24] tcp_yeah: don't set ssthresh below 2

[ Upstream commit 83d15e70c4d8909d722c0d64747d8fb42e38a48f ]

For tcp_yeah, use an ssthresh floor of 2, the same floor used by Reno
and CUBIC, per RFC 5681 (equation 4).

tcp_yeah_ssthresh() was sometimes returning a 0 or negative ssthresh
value if the intended reduction is as big or bigger than the current
cwnd. Congestion control modules should never return a zero or
negative ssthresh. A zero ssthresh generally results in a zero cwnd,
causing the connection to stall. A negative ssthresh value will be
interpreted as a u32 and will set a target cwnd for PRR near 4
billion.

Oleksandr Natalenko reported that a system using tcp_yeah with ECN
could see a warning about a prior_cwnd of 0 in
tcp_cwnd_reduction(). Testing verified that this was due to
tcp_yeah_ssthresh() misbehaving in this way.

Reported-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_yeah.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c
index 17d3566..3e6a472 100644
--- a/net/ipv4/tcp_yeah.c
+++ b/net/ipv4/tcp_yeah.c
@@ -219,7 +219,7 @@ static u32 tcp_yeah_ssthresh(struct sock *sk)
 	yeah->fast_count = 0;
 	yeah->reno_count = max(yeah->reno_count>>1, 2U);
 
-	return tp->snd_cwnd - reduction;
+	return max_t(int, tp->snd_cwnd - reduction, 2);
 }
 
 static struct tcp_congestion_ops tcp_yeah __read_mostly = {
-- 
2.1.0


From 5f90e6bd5f61dad892a6cf44e663ea33512fc4fe Mon Sep 17 00:00:00 2001
From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Sun, 10 Jan 2016 11:47:01 -0500
Subject: [PATCH 06/24] sched,cls_flower: set key address type when present

[ Upstream commit 66530bdf85eb1d72a0c399665e09a2c2298501c6 ]

only when user space passes the addresses should we consider their
presence

Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_flower.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 5769294..95b0212 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -252,23 +252,28 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
 	fl_set_key_val(tb, key->eth.src, TCA_FLOWER_KEY_ETH_SRC,
 		       mask->eth.src, TCA_FLOWER_KEY_ETH_SRC_MASK,
 		       sizeof(key->eth.src));
+
 	fl_set_key_val(tb, &key->basic.n_proto, TCA_FLOWER_KEY_ETH_TYPE,
 		       &mask->basic.n_proto, TCA_FLOWER_UNSPEC,
 		       sizeof(key->basic.n_proto));
+
 	if (key->basic.n_proto == htons(ETH_P_IP) ||
 	    key->basic.n_proto == htons(ETH_P_IPV6)) {
 		fl_set_key_val(tb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO,
 			       &mask->basic.ip_proto, TCA_FLOWER_UNSPEC,
 			       sizeof(key->basic.ip_proto));
 	}
-	if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
+
+	if (tb[TCA_FLOWER_KEY_IPV4_SRC] || tb[TCA_FLOWER_KEY_IPV4_DST]) {
+		key->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
 		fl_set_key_val(tb, &key->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC,
 			       &mask->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC_MASK,
 			       sizeof(key->ipv4.src));
 		fl_set_key_val(tb, &key->ipv4.dst, TCA_FLOWER_KEY_IPV4_DST,
 			       &mask->ipv4.dst, TCA_FLOWER_KEY_IPV4_DST_MASK,
 			       sizeof(key->ipv4.dst));
-	} else if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
+	} else if (tb[TCA_FLOWER_KEY_IPV6_SRC] || tb[TCA_FLOWER_KEY_IPV6_DST]) {
+		key->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
 		fl_set_key_val(tb, &key->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC,
 			       &mask->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC_MASK,
 			       sizeof(key->ipv6.src));
@@ -276,6 +281,7 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
 			       &mask->ipv6.dst, TCA_FLOWER_KEY_IPV6_DST_MASK,
 			       sizeof(key->ipv6.dst));
 	}
+
 	if (key->basic.ip_proto == IPPROTO_TCP) {
 		fl_set_key_val(tb, &key->tp.src, TCA_FLOWER_KEY_TCP_SRC,
 			       &mask->tp.src, TCA_FLOWER_UNSPEC,
-- 
2.1.0


From f9f7772a8172511a3767e4990347489f66c28350 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Sun, 10 Jan 2016 21:38:44 -0800
Subject: [PATCH 07/24] net: pktgen: fix null ptr deref in skb allocation

[ Upstream commit 3de03596dfeee48bc803c1d1a6daf60a459929f3 ]

Fix possible null pointer dereference that may occur when calling
skb_reserve() on a null skb.

Fixes: 879c7220e82 ("net: pktgen: Observe needed_headroom of the device")
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/pktgen.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index de8d5cc..4da4d51 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -2787,7 +2787,9 @@ static struct sk_buff *pktgen_alloc_skb(struct net_device *dev,
 	} else {
 		 skb = __netdev_alloc_skb(dev, size, GFP_NOWAIT);
 	}
-	skb_reserve(skb, LL_RESERVED_SPACE(dev));
+
+	if (likely(skb))
+		skb_reserve(skb, LL_RESERVED_SPACE(dev));
 
 	return skb;
 }
-- 
2.1.0


From f7d7785849aeae8974a44fa71bb52c2439d8a89c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Michal=20Kube=C4=8Dek?= <mkubecek@suse.cz>
Date: Mon, 11 Jan 2016 07:50:30 +0100
Subject: [PATCH 08/24] udp: disallow UFO for sockets with SO_NO_CHECK option

[ Upstream commit 40ba330227ad00b8c0cdf2f425736ff9549cc423 ]

Commit acf8dd0a9d0b ("udp: only allow UFO for packets from SOCK_DGRAM
sockets") disallows UFO for packets sent from raw sockets. We need to do
the same also for SOCK_DGRAM sockets with SO_NO_CHECK options, even if
for a bit different reason: while such socket would override the
CHECKSUM_PARTIAL set by ip_ufo_append_data(), gso_size is still set and
bad offloading flags warning is triggered in __skb_gso_segment().

In the IPv6 case, SO_NO_CHECK option is ignored but we need to disallow
UFO for packets sent by sockets with UDP_NO_CHECK6_TX option.

Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Tested-by: Shannon Nelson <shannon.nelson@intel.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_output.c  | 2 +-
 net/ipv6/ip6_output.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 4233cbe..36ac9f3 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -921,7 +921,7 @@ static int __ip_append_data(struct sock *sk,
 	if (((length > mtu) || (skb && skb_is_gso(skb))) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
 	    (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len &&
-	    (sk->sk_type == SOCK_DGRAM)) {
+	    (sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx) {
 		err = ip_ufo_append_data(sk, queue, getfrag, from, length,
 					 hh_len, fragheaderlen, transhdrlen,
 					 maxfraglen, flags);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index e6a7bd15..6473889 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1353,7 +1353,7 @@ emsgsize:
 	     (skb && skb_is_gso(skb))) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
 	    (rt->dst.dev->features & NETIF_F_UFO) &&
-	    (sk->sk_type == SOCK_DGRAM)) {
+	    (sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk)) {
 		err = ip6_ufo_append_data(sk, queue, getfrag, from, length,
 					  hh_len, fragheaderlen,
 					  transhdrlen, mtu, flags, fl6);
-- 
2.1.0


From 1b0d871681390842140fdc765885e8a4faeae671 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <koct9i@gmail.com>
Date: Fri, 8 Jan 2016 15:21:46 +0300
Subject: [PATCH 09/24] net: preserve IP control block during GSO segmentation

[ Upstream commit 9207f9d45b0ad071baa128e846d7e7ed85016df3 ]

Skb_gso_segment() uses skb control block during segmentation.
This patch adds 32-bytes room for previous control block which
will be copied into all resulting segments.

This patch fixes kernel crash during fragmenting forwarded packets.
Fragmentation requires valid IP CB in skb for clearing ip options.
Also patch removes custom save/restore in ovs code, now it's redundant.

Signed-off-by: Konstantin Khlebnikov <koct9i@gmail.com>
Link: http://lkml.kernel.org/r/CALYGNiP-0MZ-FExV2HutTvE9U-QQtkKSoE--KN=JQE5STYsjAA@mail.gmail.com
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h     | 3 ++-
 net/core/dev.c             | 5 +++++
 net/ipv4/ip_output.c       | 1 +
 net/openvswitch/datapath.c | 5 +----
 net/xfrm/xfrm_output.c     | 2 ++
 5 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 4355129..9147f9f 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3446,7 +3446,8 @@ struct skb_gso_cb {
 	int	encap_level;
 	__u16	csum_start;
 };
-#define SKB_GSO_CB(skb) ((struct skb_gso_cb *)(skb)->cb)
+#define SKB_SGO_CB_OFFSET	32
+#define SKB_GSO_CB(skb) ((struct skb_gso_cb *)((skb)->cb + SKB_SGO_CB_OFFSET))
 
 static inline int skb_tnl_header_len(const struct sk_buff *inner_skb)
 {
diff --git a/net/core/dev.c b/net/core/dev.c
index ae00b89..7f00f24 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2542,6 +2542,8 @@ static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path)
  *
  *	It may return NULL if the skb requires no segmentation.  This is
  *	only possible when GSO is used for verifying header integrity.
+ *
+ *	Segmentation preserves SKB_SGO_CB_OFFSET bytes of previous skb cb.
  */
 struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
 				  netdev_features_t features, bool tx_path)
@@ -2556,6 +2558,9 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
 			return ERR_PTR(err);
 	}
 
+	BUILD_BUG_ON(SKB_SGO_CB_OFFSET +
+		     sizeof(*SKB_GSO_CB(skb)) > sizeof(skb->cb));
+
 	SKB_GSO_CB(skb)->mac_offset = skb_headroom(skb);
 	SKB_GSO_CB(skb)->encap_level = 0;
 
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 36ac9f3..49f0285 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -240,6 +240,7 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk,
 	 * from host network stack.
 	 */
 	features = netif_skb_features(skb);
+	BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET);
 	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
 	if (IS_ERR_OR_NULL(segs)) {
 		kfree_skb(skb);
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 91a8b00..deadfda 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -336,12 +336,10 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
 	unsigned short gso_type = skb_shinfo(skb)->gso_type;
 	struct sw_flow_key later_key;
 	struct sk_buff *segs, *nskb;
-	struct ovs_skb_cb ovs_cb;
 	int err;
 
-	ovs_cb = *OVS_CB(skb);
+	BUILD_BUG_ON(sizeof(*OVS_CB(skb)) > SKB_SGO_CB_OFFSET);
 	segs = __skb_gso_segment(skb, NETIF_F_SG, false);
-	*OVS_CB(skb) = ovs_cb;
 	if (IS_ERR(segs))
 		return PTR_ERR(segs);
 	if (segs == NULL)
@@ -359,7 +357,6 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
 	/* Queue all of the segments. */
 	skb = segs;
 	do {
-		*OVS_CB(skb) = ovs_cb;
 		if (gso_type & SKB_GSO_UDP && skb != segs)
 			key = &later_key;
 
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index cc3676e..ff4a91f 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -167,6 +167,8 @@ static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb
 {
 	struct sk_buff *segs;
 
+	BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET);
+	BUILD_BUG_ON(sizeof(*IP6CB(skb)) > SKB_SGO_CB_OFFSET);
 	segs = skb_gso_segment(skb, 0);
 	kfree_skb(skb);
 	if (IS_ERR(segs))
-- 
2.1.0


From 9c02d9daabfad26028ee09265997a53c1c618eda Mon Sep 17 00:00:00 2001
From: Karl Heiss <kheiss@gmail.com>
Date: Mon, 11 Jan 2016 08:28:43 -0500
Subject: [PATCH 10/24] bonding: Prevent IPv6 link local address on enslaved
 devices

[ Upstream commit 03d84a5f83a67e692af00a3d3901e7820e3e84d5 ]

Commit 1f718f0f4f97 ("bonding: populate neighbour's private on enslave")
undoes the fix provided by commit c2edacf80e15 ("bonding / ipv6: no addrconf
for slaves separately from master") by effectively setting the slave flag
after the slave has been opened.  If the slave comes up quickly enough, it
will go through the IPv6 addrconf before the slave flag has been set and
will get a link local IPv6 address.

In order to ensure that addrconf knows to ignore the slave devices on state
change, set IFF_SLAVE before dev_open() during bonding enslavement.

Fixes: 1f718f0f4f97 ("bonding: populate neighbour's private on enslave")
Signed-off-by: Karl Heiss <kheiss@gmail.com>
Signed-off-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Reviewed-by: Jarod Wilson <jarod@redhat.com>
Signed-off-by: Andy Gospodarek <gospo@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 9e0f8a7..f1692e4 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1207,7 +1207,6 @@ static int bond_master_upper_dev_link(struct net_device *bond_dev,
 	err = netdev_master_upper_dev_link_private(slave_dev, bond_dev, slave);
 	if (err)
 		return err;
-	slave_dev->flags |= IFF_SLAVE;
 	rtmsg_ifinfo(RTM_NEWLINK, slave_dev, IFF_SLAVE, GFP_KERNEL);
 	return 0;
 }
@@ -1465,6 +1464,9 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 		}
 	}
 
+	/* set slave flag before open to prevent IPv6 addrconf */
+	slave_dev->flags |= IFF_SLAVE;
+
 	/* open the slave since the application closed it */
 	res = dev_open(slave_dev);
 	if (res) {
@@ -1725,6 +1727,7 @@ err_close:
 	dev_close(slave_dev);
 
 err_restore_mac:
+	slave_dev->flags &= ~IFF_SLAVE;
 	if (!bond->params.fail_over_mac ||
 	    BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
 		/* XXX TODO - fom follow mode needs to change master's
-- 
2.1.0


From 403be417be21060b6af1465fa97f27a0b4030e15 Mon Sep 17 00:00:00 2001
From: Lars Persson <lars.persson@axis.com>
Date: Tue, 12 Jan 2016 15:28:13 +0100
Subject: [PATCH 11/24] dwc_eth_qos: Fix dma address for multi-fragment skbs

[ Upstream commit d461873272169a3fc3a8d155d7b1c92e9d97b419 ]

The offset inside the fragment was not used for the dma address and
silent data corruption resulted because TSO makes the checksum match.

Fixes: 077742dac2c7 ("dwc_eth_qos: Add support for Synopsys DWC Ethernet QoS")
Signed-off-by: Lars Persson <larper@axis.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/synopsys/dwc_eth_qos.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/synopsys/dwc_eth_qos.c b/drivers/net/ethernet/synopsys/dwc_eth_qos.c
index 9066d7a..f96c6b3 100644
--- a/drivers/net/ethernet/synopsys/dwc_eth_qos.c
+++ b/drivers/net/ethernet/synopsys/dwc_eth_qos.c
@@ -2107,7 +2107,7 @@ static int dwceqos_tx_frags(struct sk_buff *skb, struct net_local *lp,
 			dd = &lp->tx_descs[lp->tx_next];
 
 			/* Set DMA Descriptor fields */
-			dd->des0 = dma_handle;
+			dd->des0 = dma_handle + consumed_size;
 			dd->des1 = 0;
 			dd->des2 = dma_size;
 
-- 
2.1.0


From b8a814ce0b48c26e18553f5b0b7d08f4025f5824 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 12 Jan 2016 08:58:00 -0800
Subject: [PATCH 12/24] phonet: properly unshare skbs in phonet_rcv()

[ Upstream commit 7aaed57c5c2890634cfadf725173c7c68ea4cb4f ]

Ivaylo Dimitrov reported a regression caused by commit 7866a621043f
("dev: add per net_device packet type chains").

skb->dev becomes NULL and we crash in __netif_receive_skb_core().

Before above commit, different kind of bugs or corruptions could happen
without major crash.

But the root cause is that phonet_rcv() can queue skb without checking
if skb is shared or not.

Many thanks to Ivaylo Dimitrov for his help, diagnosis and tests.

Reported-by: Ivaylo Dimitrov <ivo.g.dimitrov.75@gmail.com>
Tested-by: Ivaylo Dimitrov <ivo.g.dimitrov.75@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Remi Denis-Courmont <courmisch@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/phonet/af_phonet.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c
index 10d42f3..f925753 100644
--- a/net/phonet/af_phonet.c
+++ b/net/phonet/af_phonet.c
@@ -377,6 +377,10 @@ static int phonet_rcv(struct sk_buff *skb, struct net_device *dev,
 	struct sockaddr_pn sa;
 	u16 len;
 
+	skb = skb_share_check(skb, GFP_ATOMIC);
+	if (!skb)
+		return NET_RX_DROP;
+
 	/* check we have at least a full Phonet header */
 	if (!pskb_pull(skb, sizeof(struct phonethdr)))
 		goto out;
-- 
2.1.0


From 72f7d308e39152a3a30a8ea9b4af53ed0fd40fbf Mon Sep 17 00:00:00 2001
From: Rabin Vincent <rabin@rab.in>
Date: Tue, 12 Jan 2016 20:17:08 +0100
Subject: [PATCH 13/24] net: bpf: reject invalid shifts

[ Upstream commit 229394e8e62a4191d592842cf67e80c62a492937 ]

On ARM64, a BUG() is triggered in the eBPF JIT if a filter with a
constant shift that can't be encoded in the immediate field of the
UBFM/SBFM instructions is passed to the JIT.  Since these shifts
amounts, which are negative or >= regsize, are invalid, reject them in
the eBPF verifier and the classic BPF filter checker, for all
architectures.

Signed-off-by: Rabin Vincent <rabin@rab.in>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c | 10 ++++++++++
 net/core/filter.c     |  5 +++++
 2 files changed, 15 insertions(+)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index a7945d1..d1d3e8f 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1121,6 +1121,16 @@ static int check_alu_op(struct verifier_env *env, struct bpf_insn *insn)
 			return -EINVAL;
 		}
 
+		if ((opcode == BPF_LSH || opcode == BPF_RSH ||
+		     opcode == BPF_ARSH) && BPF_SRC(insn->code) == BPF_K) {
+			int size = BPF_CLASS(insn->code) == BPF_ALU64 ? 64 : 32;
+
+			if (insn->imm < 0 || insn->imm >= size) {
+				verbose("invalid shift %d\n", insn->imm);
+				return -EINVAL;
+			}
+		}
+
 		/* pattern match 'bpf_add Rx, imm' instruction */
 		if (opcode == BPF_ADD && BPF_CLASS(insn->code) == BPF_ALU64 &&
 		    regs[insn->dst_reg].type == FRAME_PTR &&
diff --git a/net/core/filter.c b/net/core/filter.c
index 672eefb..37157c4 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -777,6 +777,11 @@ static int bpf_check_classic(const struct sock_filter *filter,
 			if (ftest->k == 0)
 				return -EINVAL;
 			break;
+		case BPF_ALU | BPF_LSH | BPF_K:
+		case BPF_ALU | BPF_RSH | BPF_K:
+			if (ftest->k >= 32)
+				return -EINVAL;
+			break;
 		case BPF_LD | BPF_MEM:
 		case BPF_LDX | BPF_MEM:
 		case BPF_ST:
-- 
2.1.0


From 13f48a5c8f1d903381225081425ed1160360de64 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 15 Jan 2016 04:56:56 -0800
Subject: [PATCH 14/24] ipv6: update skb->csum when CE mark is propagated

[ Upstream commit 34ae6a1aa0540f0f781dd265366036355fdc8930 ]

When a tunnel decapsulates the outer header, it has to comply
with RFC 6080 and eventually propagate CE mark into inner header.

It turns out IP6_ECN_set_ce() does not correctly update skb->csum
for CHECKSUM_COMPLETE packets, triggering infamous "hw csum failure"
messages and stack traces.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_ecn.h       | 19 ++++++++++++++++---
 net/ipv6/xfrm6_mode_tunnel.c |  2 +-
 2 files changed, 17 insertions(+), 4 deletions(-)

diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h
index 84b2083..0dc0a51 100644
--- a/include/net/inet_ecn.h
+++ b/include/net/inet_ecn.h
@@ -111,11 +111,24 @@ static inline void ipv4_copy_dscp(unsigned int dscp, struct iphdr *inner)
 
 struct ipv6hdr;
 
-static inline int IP6_ECN_set_ce(struct ipv6hdr *iph)
+/* Note:
+ * IP_ECN_set_ce() has to tweak IPV4 checksum when setting CE,
+ * meaning both changes have no effect on skb->csum if/when CHECKSUM_COMPLETE
+ * In IPv6 case, no checksum compensates the change in IPv6 header,
+ * so we have to update skb->csum.
+ */
+static inline int IP6_ECN_set_ce(struct sk_buff *skb, struct ipv6hdr *iph)
 {
+	__be32 from, to;
+
 	if (INET_ECN_is_not_ect(ipv6_get_dsfield(iph)))
 		return 0;
-	*(__be32*)iph |= htonl(INET_ECN_CE << 20);
+
+	from = *(__be32 *)iph;
+	to = from | htonl(INET_ECN_CE << 20);
+	*(__be32 *)iph = to;
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		skb->csum = csum_add(csum_sub(skb->csum, from), to);
 	return 1;
 }
 
@@ -142,7 +155,7 @@ static inline int INET_ECN_set_ce(struct sk_buff *skb)
 	case cpu_to_be16(ETH_P_IPV6):
 		if (skb_network_header(skb) + sizeof(struct ipv6hdr) <=
 		    skb_tail_pointer(skb))
-			return IP6_ECN_set_ce(ipv6_hdr(skb));
+			return IP6_ECN_set_ce(skb, ipv6_hdr(skb));
 		break;
 	}
 
diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c
index f7fbdba..372855e 100644
--- a/net/ipv6/xfrm6_mode_tunnel.c
+++ b/net/ipv6/xfrm6_mode_tunnel.c
@@ -23,7 +23,7 @@ static inline void ipip6_ecn_decapsulate(struct sk_buff *skb)
 	struct ipv6hdr *inner_iph = ipipv6_hdr(skb);
 
 	if (INET_ECN_is_ce(XFRM_MODE_SKB_CB(skb)->tos))
-		IP6_ECN_set_ce(inner_iph);
+		IP6_ECN_set_ce(skb, inner_iph);
 }
 
 /* Add encapsulation header.
-- 
2.1.0


From e9d5822ae2d1ce1ca1fb388b06b618991a52e899 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Fri, 15 Jan 2016 19:03:54 +0100
Subject: [PATCH 15/24] bridge: fix lockdep addr_list_lock false positive splat

[ Upstream commit c6894dec8ea9ae05747124dce98b3b5c2e69b168 ]

After promisc mode management was introduced a bridge device could do
dev_set_promiscuity from its ndo_change_rx_flags() callback which in
turn can be called after the bridge's addr_list_lock has been taken
(e.g. by dev_uc_add). This causes a false positive lockdep splat because
the port interfaces' addr_list_lock is taken when br_manage_promisc()
runs after the bridge's addr list lock was already taken.
To remove the false positive introduce a custom bridge addr_list_lock
class and set it on bridge init.
A simple way to reproduce this is with the following:
$ brctl addbr br0
$ ip l add l br0 br0.100 type vlan id 100
$ ip l set br0 up
$ ip l set br0.100 up
$ echo 1 > /sys/class/net/br0/bridge/vlan_filtering
$ brctl addif br0 eth0
Splat:
[   43.684325] =============================================
[   43.684485] [ INFO: possible recursive locking detected ]
[   43.684636] 4.4.0-rc8+ #54 Not tainted
[   43.684755] ---------------------------------------------
[   43.684906] brctl/1187 is trying to acquire lock:
[   43.685047]  (_xmit_ETHER){+.....}, at: [<ffffffff8150169e>] dev_set_rx_mode+0x1e/0x40
[   43.685460]  but task is already holding lock:
[   43.685618]  (_xmit_ETHER){+.....}, at: [<ffffffff815072a7>] dev_uc_add+0x27/0x80
[   43.686015]  other info that might help us debug this:
[   43.686316]  Possible unsafe locking scenario:

[   43.686743]        CPU0
[   43.686967]        ----
[   43.687197]   lock(_xmit_ETHER);
[   43.687544]   lock(_xmit_ETHER);
[   43.687886] *** DEADLOCK ***

[   43.688438]  May be due to missing lock nesting notation

[   43.688882] 2 locks held by brctl/1187:
[   43.689134]  #0:  (rtnl_mutex){+.+.+.}, at: [<ffffffff81510317>] rtnl_lock+0x17/0x20
[   43.689852]  #1:  (_xmit_ETHER){+.....}, at: [<ffffffff815072a7>] dev_uc_add+0x27/0x80
[   43.690575] stack backtrace:
[   43.690970] CPU: 0 PID: 1187 Comm: brctl Not tainted 4.4.0-rc8+ #54
[   43.691270] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.8.1-20150318_183358- 04/01/2014
[   43.691770]  ffffffff826a25c0 ffff8800369fb8e0 ffffffff81360ceb ffffffff826a25c0
[   43.692425]  ffff8800369fb9b8 ffffffff810d0466 ffff8800369fb968 ffffffff81537139
[   43.693071]  ffff88003a08c880 0000000000000000 00000000ffffffff 0000000002080020
[   43.693709] Call Trace:
[   43.693931]  [<ffffffff81360ceb>] dump_stack+0x4b/0x70
[   43.694199]  [<ffffffff810d0466>] __lock_acquire+0x1e46/0x1e90
[   43.694483]  [<ffffffff81537139>] ? netlink_broadcast_filtered+0x139/0x3e0
[   43.694789]  [<ffffffff8153b5da>] ? nlmsg_notify+0x5a/0xc0
[   43.695064]  [<ffffffff810d10f5>] lock_acquire+0xe5/0x1f0
[   43.695340]  [<ffffffff8150169e>] ? dev_set_rx_mode+0x1e/0x40
[   43.695623]  [<ffffffff815edea5>] _raw_spin_lock_bh+0x45/0x80
[   43.695901]  [<ffffffff8150169e>] ? dev_set_rx_mode+0x1e/0x40
[   43.696180]  [<ffffffff8150169e>] dev_set_rx_mode+0x1e/0x40
[   43.696460]  [<ffffffff8150189c>] dev_set_promiscuity+0x3c/0x50
[   43.696750]  [<ffffffffa0586845>] br_port_set_promisc+0x25/0x50 [bridge]
[   43.697052]  [<ffffffffa05869aa>] br_manage_promisc+0x8a/0xe0 [bridge]
[   43.697348]  [<ffffffffa05826ee>] br_dev_change_rx_flags+0x1e/0x20 [bridge]
[   43.697655]  [<ffffffff81501532>] __dev_set_promiscuity+0x132/0x1f0
[   43.697943]  [<ffffffff81501672>] __dev_set_rx_mode+0x82/0x90
[   43.698223]  [<ffffffff815072de>] dev_uc_add+0x5e/0x80
[   43.698498]  [<ffffffffa05b3c62>] vlan_device_event+0x542/0x650 [8021q]
[   43.698798]  [<ffffffff8109886d>] notifier_call_chain+0x5d/0x80
[   43.699083]  [<ffffffff810988b6>] raw_notifier_call_chain+0x16/0x20
[   43.699374]  [<ffffffff814f456e>] call_netdevice_notifiers_info+0x6e/0x80
[   43.699678]  [<ffffffff814f4596>] call_netdevice_notifiers+0x16/0x20
[   43.699973]  [<ffffffffa05872be>] br_add_if+0x47e/0x4c0 [bridge]
[   43.700259]  [<ffffffffa058801e>] add_del_if+0x6e/0x80 [bridge]
[   43.700548]  [<ffffffffa0588b5f>] br_dev_ioctl+0xaf/0xc0 [bridge]
[   43.700836]  [<ffffffff8151a7ac>] dev_ifsioc+0x30c/0x3c0
[   43.701106]  [<ffffffff8151aac9>] dev_ioctl+0xf9/0x6f0
[   43.701379]  [<ffffffff81254345>] ? mntput_no_expire+0x5/0x450
[   43.701665]  [<ffffffff812543ee>] ? mntput_no_expire+0xae/0x450
[   43.701947]  [<ffffffff814d7b02>] sock_do_ioctl+0x42/0x50
[   43.702219]  [<ffffffff814d8175>] sock_ioctl+0x1e5/0x290
[   43.702500]  [<ffffffff81242d0b>] do_vfs_ioctl+0x2cb/0x5c0
[   43.702771]  [<ffffffff81243079>] SyS_ioctl+0x79/0x90
[   43.703033]  [<ffffffff815eebb6>] entry_SYSCALL_64_fastpath+0x16/0x7a

CC: Vlad Yasevich <vyasevic@redhat.com>
CC: Stephen Hemminger <stephen@networkplumber.org>
CC: Bridge list <bridge@lists.linux-foundation.org>
CC: Andy Gospodarek <gospo@cumulusnetworks.com>
CC: Roopa Prabhu <roopa@cumulusnetworks.com>
Fixes: 2796d0c648c9 ("bridge: Automatically manage port promiscuous mode.")
Reported-by: Andy Gospodarek <gospo@cumulusnetworks.com>
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_device.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 5e88d3e..2c8095a 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -28,6 +28,8 @@
 const struct nf_br_ops __rcu *nf_br_ops __read_mostly;
 EXPORT_SYMBOL_GPL(nf_br_ops);
 
+static struct lock_class_key bridge_netdev_addr_lock_key;
+
 /* net device transmit always called with BH disabled */
 netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 {
@@ -87,6 +89,11 @@ out:
 	return NETDEV_TX_OK;
 }
 
+static void br_set_lockdep_class(struct net_device *dev)
+{
+	lockdep_set_class(&dev->addr_list_lock, &bridge_netdev_addr_lock_key);
+}
+
 static int br_dev_init(struct net_device *dev)
 {
 	struct net_bridge *br = netdev_priv(dev);
@@ -99,6 +106,7 @@ static int br_dev_init(struct net_device *dev)
 	err = br_vlan_init(br);
 	if (err)
 		free_percpu(br->stats);
+	br_set_lockdep_class(dev);
 
 	return err;
 }
-- 
2.1.0


From b7e440fe34b750c57ff05d6e14e3ca3942e0d00e Mon Sep 17 00:00:00 2001
From: Doron Tsur <doront@mellanox.com>
Date: Sun, 17 Jan 2016 11:25:47 +0200
Subject: [PATCH 16/24] net/mlx5_core: Fix trimming down IRQ number

[ Upstream commit 0b6e26ce89391327d955a756a7823272238eb867 ]

With several ConnectX-4 cards installed on a server, one may receive
irqn > 255 from the kernel API, which we mistakenly trim to 8bit.

This causes EQ creation failure with the following stack trace:
[<ffffffff812a11f4>] dump_stack+0x48/0x64
[<ffffffff810ace21>] __setup_irq+0x3a1/0x4f0
[<ffffffff810ad7e0>] request_threaded_irq+0x120/0x180
[<ffffffffa0923660>] ? mlx5_eq_int+0x450/0x450 [mlx5_core]
[<ffffffffa0922f64>] mlx5_create_map_eq+0x1e4/0x2b0 [mlx5_core]
[<ffffffffa091de01>] alloc_comp_eqs+0xb1/0x180 [mlx5_core]
[<ffffffffa091ea99>] mlx5_dev_init+0x5e9/0x6e0 [mlx5_core]
[<ffffffffa091ec29>] init_one+0x99/0x1c0 [mlx5_core]
[<ffffffff812e2afc>] local_pci_probe+0x4c/0xa0

Fixing it by changing of the irqn type from u8 to unsigned int to
support values > 255

Fixes: 61d0e73e0a5a ('net/mlx5_core: Use the the real irqn in eq->irqn')
Reported-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Doron Tsur <doront@mellanox.com>
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/mlx5/cq.c                   | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 6 +++---
 drivers/net/ethernet/mellanox/mlx5/core/main.c    | 3 ++-
 include/linux/mlx5/cq.h                           | 2 +-
 include/linux/mlx5/driver.h                       | 5 +++--
 5 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index 3dfd287..92ddae1 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -756,7 +756,7 @@ struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev,
 	int uninitialized_var(index);
 	int uninitialized_var(inlen);
 	int cqe_size;
-	int irqn;
+	unsigned int irqn;
 	int eqn;
 	int err;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 1e52db3..1203d89 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -746,7 +746,7 @@ static int mlx5e_create_cq(struct mlx5e_channel *c,
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5_core_cq *mcq = &cq->mcq;
 	int eqn_not_used;
-	int irqn;
+	unsigned int irqn;
 	int err;
 	u32 i;
 
@@ -800,7 +800,7 @@ static int mlx5e_enable_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
 	void *in;
 	void *cqc;
 	int inlen;
-	int irqn_not_used;
+	unsigned int irqn_not_used;
 	int eqn;
 	int err;
 
@@ -1504,7 +1504,7 @@ static int mlx5e_create_drop_cq(struct mlx5e_priv *priv,
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5_core_cq *mcq = &cq->mcq;
 	int eqn_not_used;
-	int irqn;
+	unsigned int irqn;
 	int err;
 
 	err = mlx5_cqwq_create(mdev, &param->wq, param->cqc, &cq->wq,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 4ac8d4cc..6cf6d93 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -568,7 +568,8 @@ static void mlx5_irq_clear_affinity_hints(struct mlx5_core_dev *mdev)
 		mlx5_irq_clear_affinity_hint(mdev, i);
 }
 
-int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, int *irqn)
+int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn,
+		    unsigned int *irqn)
 {
 	struct mlx5_eq_table *table = &dev->priv.eq_table;
 	struct mlx5_eq *eq, *n;
diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h
index abc4767..b2c9fad 100644
--- a/include/linux/mlx5/cq.h
+++ b/include/linux/mlx5/cq.h
@@ -45,7 +45,7 @@ struct mlx5_core_cq {
 	atomic_t		refcount;
 	struct completion	free;
 	unsigned		vector;
-	int			irqn;
+	unsigned int		irqn;
 	void (*comp)		(struct mlx5_core_cq *);
 	void (*event)		(struct mlx5_core_cq *, enum mlx5_event);
 	struct mlx5_uar	       *uar;
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 5c857f2..af3efd9 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -303,7 +303,7 @@ struct mlx5_eq {
 	u32			cons_index;
 	struct mlx5_buf		buf;
 	int			size;
-	u8			irqn;
+	unsigned int		irqn;
 	u8			eqn;
 	int			nent;
 	u64			mask;
@@ -762,7 +762,8 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
 int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
 int mlx5_start_eqs(struct mlx5_core_dev *dev);
 int mlx5_stop_eqs(struct mlx5_core_dev *dev);
-int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, int *irqn);
+int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn,
+		    unsigned int *irqn);
 int mlx5_core_attach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn);
 int mlx5_core_detach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn);
 
-- 
2.1.0


From c3e0d33b8934b5eb8809d9f29bf8ca439e80d0ee Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Mon, 18 Jan 2016 17:30:22 +0200
Subject: [PATCH 17/24] team: Replace rcu_read_lock with a mutex in
 team_vlan_rx_kill_vid

[ Upstream commit 60a6531bfe49555581ccd65f66a350cc5693fcde ]

We can't be within an RCU read-side critical section when deleting
VLANs, as underlying drivers might sleep during the hardware operation.
Therefore, replace the RCU critical section with a mutex. This is
consistent with team_vlan_rx_add_vid.

Fixes: 3d249d4ca7d0 ("net: introduce ethernet teaming device")
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 651d35e..59fefca 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1845,10 +1845,10 @@ static int team_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid)
 	struct team *team = netdev_priv(dev);
 	struct team_port *port;
 
-	rcu_read_lock();
-	list_for_each_entry_rcu(port, &team->port_list, list)
+	mutex_lock(&team->lock);
+	list_for_each_entry(port, &team->port_list, list)
 		vlan_vid_del(port->dev, proto, vid);
-	rcu_read_unlock();
+	mutex_unlock(&team->lock);
 
 	return 0;
 }
-- 
2.1.0


From b7cfe3e689e0446097a483284e8d40da79f32454 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Thu, 14 Jan 2016 15:28:19 +0100
Subject: [PATCH 18/24] batman-adv: Avoid recursive call_rcu for
 batadv_bla_claim

[ Upstream commit 63b399272294e7a939cde41792dca38c549f0484 ]

The batadv_claim_free_ref function uses call_rcu to delay the free of the
batadv_bla_claim object until no (already started) rcu_read_lock is enabled
anymore. This makes sure that no context is still trying to access the
object which should be removed. But batadv_bla_claim also contains a
reference to backbone_gw which must be removed.

The reference drop of backbone_gw was done in the call_rcu function
batadv_claim_free_rcu but should actually be done in the
batadv_claim_release function to avoid nested call_rcus. This is important
because rcu_barrier (e.g. batadv_softif_free or batadv_exit) will not
detect the inner call_rcu as relevant for its execution. Otherwise this
barrier will most likely be inserted in the queue before the callback of
the first call_rcu was executed. The caller of rcu_barrier will therefore
continue to run before the inner call_rcu callback finished.

Fixes: 23721387c409 ("batman-adv: add basic bridge loop avoidance code")
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Acked-by: Simon Wunderlich <sw@simonwunderlich.de>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>
Signed-off-by: Antonio Quartulli <a@unstable.cc>
---
 net/batman-adv/bridge_loop_avoidance.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c
index 191a702..f5d2fe5 100644
--- a/net/batman-adv/bridge_loop_avoidance.c
+++ b/net/batman-adv/bridge_loop_avoidance.c
@@ -127,21 +127,17 @@ batadv_backbone_gw_free_ref(struct batadv_bla_backbone_gw *backbone_gw)
 }
 
 /* finally deinitialize the claim */
-static void batadv_claim_free_rcu(struct rcu_head *rcu)
+static void batadv_claim_release(struct batadv_bla_claim *claim)
 {
-	struct batadv_bla_claim *claim;
-
-	claim = container_of(rcu, struct batadv_bla_claim, rcu);
-
 	batadv_backbone_gw_free_ref(claim->backbone_gw);
-	kfree(claim);
+	kfree_rcu(claim, rcu);
 }
 
 /* free a claim, call claim_free_rcu if its the last reference */
 static void batadv_claim_free_ref(struct batadv_bla_claim *claim)
 {
 	if (atomic_dec_and_test(&claim->refcount))
-		call_rcu(&claim->rcu, batadv_claim_free_rcu);
+		batadv_claim_release(claim);
 }
 
 /**
-- 
2.1.0


From 6903d460344b2f9f12bf07f623349a2658a3b4c8 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Tue, 5 Jan 2016 12:06:19 +0100
Subject: [PATCH 19/24] batman-adv: Avoid recursive call_rcu for batadv_nc_node

[ Upstream commit 44e8e7e91d6c7c7ab19688750f7257292640d1a0 ]

The batadv_nc_node_free_ref function uses call_rcu to delay the free of the
batadv_nc_node object until no (already started) rcu_read_lock is enabled
anymore. This makes sure that no context is still trying to access the
object which should be removed. But batadv_nc_node also contains a
reference to orig_node which must be removed.

The reference drop of orig_node was done in the call_rcu function
batadv_nc_node_free_rcu but should actually be done in the
batadv_nc_node_release function to avoid nested call_rcus. This is
important because rcu_barrier (e.g. batadv_softif_free or batadv_exit) will
not detect the inner call_rcu as relevant for its execution. Otherwise this
barrier will most likely be inserted in the queue before the callback of
the first call_rcu was executed. The caller of rcu_barrier will therefore
continue to run before the inner call_rcu callback finished.

Fixes: d56b1705e28c ("batman-adv: network coding - detect coding nodes and remove these after timeout")
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>
Signed-off-by: Antonio Quartulli <a@unstable.cc>
---
 net/batman-adv/network-coding.c | 19 ++++++++-----------
 1 file changed, 8 insertions(+), 11 deletions(-)

diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c
index f5276be..d0956f7 100644
--- a/net/batman-adv/network-coding.c
+++ b/net/batman-adv/network-coding.c
@@ -203,28 +203,25 @@ void batadv_nc_init_orig(struct batadv_orig_node *orig_node)
 }
 
 /**
- * batadv_nc_node_free_rcu - rcu callback to free an nc node and remove
- *  its refcount on the orig_node
- * @rcu: rcu pointer of the nc node
+ * batadv_nc_node_release - release nc_node from lists and queue for free after
+ *  rcu grace period
+ * @nc_node: the nc node to free
  */
-static void batadv_nc_node_free_rcu(struct rcu_head *rcu)
+static void batadv_nc_node_release(struct batadv_nc_node *nc_node)
 {
-	struct batadv_nc_node *nc_node;
-
-	nc_node = container_of(rcu, struct batadv_nc_node, rcu);
 	batadv_orig_node_free_ref(nc_node->orig_node);
-	kfree(nc_node);
+	kfree_rcu(nc_node, rcu);
 }
 
 /**
- * batadv_nc_node_free_ref - decrements the nc node refcounter and possibly
- * frees it
+ * batadv_nc_node_free_ref - decrement the nc node refcounter and possibly
+ *  release it
  * @nc_node: the nc node to free
  */
 static void batadv_nc_node_free_ref(struct batadv_nc_node *nc_node)
 {
 	if (atomic_dec_and_test(&nc_node->refcount))
-		call_rcu(&nc_node->rcu, batadv_nc_node_free_rcu);
+		batadv_nc_node_release(nc_node);
 }
 
 /**
-- 
2.1.0


From 9b49a1b1a38d3ff42511dfc2deef50539cc1730d Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Tue, 5 Jan 2016 12:06:21 +0100
Subject: [PATCH 20/24] batman-adv: Drop immediate batadv_orig_ifinfo free
 function

[ Upstream commit deed96605f5695cb945e0b3d79429581857a2b9d ]

It is not allowed to free the memory of an object which is part of a list
which is protected by rcu-read-side-critical sections without making sure
that no other context is accessing the object anymore. This usually happens
by removing the references to this object and then waiting until the rcu
grace period is over and no one (allowedly) accesses it anymore.

But the _now functions ignore this completely. They free the object
directly even when a different context still tries to access it. This has
to be avoided and thus these functions must be removed and all functions
have to use batadv_orig_ifinfo_free_ref.

Fixes: 7351a4822d42 ("batman-adv: split out router from orig_node")
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>
Signed-off-by: Antonio Quartulli <a@unstable.cc>
---
 net/batman-adv/originator.c | 59 ++++++++++++++++++++++++---------------------
 1 file changed, 31 insertions(+), 28 deletions(-)

diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index 7486df9..a072894 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -553,76 +553,79 @@ static void batadv_orig_ifinfo_free_rcu(struct rcu_head *rcu)
 }
 
 /**
- * batadv_orig_ifinfo_free_ref - decrement the refcounter and possibly free
- *  the orig_ifinfo (without rcu callback)
+ * batadv_orig_ifinfo_free_ref - decrement the refcounter and possibly release
+ *  the orig_ifinfo
  * @orig_ifinfo: the orig_ifinfo object to release
  */
-static void
-batadv_orig_ifinfo_free_ref_now(struct batadv_orig_ifinfo *orig_ifinfo)
+void batadv_orig_ifinfo_free_ref(struct batadv_orig_ifinfo *orig_ifinfo)
 {
 	if (atomic_dec_and_test(&orig_ifinfo->refcount))
-		batadv_orig_ifinfo_free_rcu(&orig_ifinfo->rcu);
+		call_rcu(&orig_ifinfo->rcu, batadv_orig_ifinfo_free_rcu);
 }
 
 /**
- * batadv_orig_ifinfo_free_ref - decrement the refcounter and possibly free
- *  the orig_ifinfo
- * @orig_ifinfo: the orig_ifinfo object to release
+ * batadv_orig_node_free_rcu - free the orig_node
+ * @rcu: rcu pointer of the orig_node
  */
-void batadv_orig_ifinfo_free_ref(struct batadv_orig_ifinfo *orig_ifinfo)
+static void batadv_orig_node_free_rcu(struct rcu_head *rcu)
 {
-	if (atomic_dec_and_test(&orig_ifinfo->refcount))
-		call_rcu(&orig_ifinfo->rcu, batadv_orig_ifinfo_free_rcu);
+	struct batadv_orig_node *orig_node;
+
+	orig_node = container_of(rcu, struct batadv_orig_node, rcu);
+
+	batadv_mcast_purge_orig(orig_node);
+
+	batadv_frag_purge_orig(orig_node, NULL);
+
+	if (orig_node->bat_priv->bat_algo_ops->bat_orig_free)
+		orig_node->bat_priv->bat_algo_ops->bat_orig_free(orig_node);
+
+	kfree(orig_node->tt_buff);
+	kfree(orig_node);
 }
 
-static void batadv_orig_node_free_rcu(struct rcu_head *rcu)
+/**
+ * batadv_orig_node_release - release orig_node from lists and queue for
+ *  free after rcu grace period
+ * @orig_node: the orig node to free
+ */
+static void batadv_orig_node_release(struct batadv_orig_node *orig_node)
 {
 	struct hlist_node *node_tmp;
 	struct batadv_neigh_node *neigh_node;
-	struct batadv_orig_node *orig_node;
 	struct batadv_orig_ifinfo *orig_ifinfo;
 
-	orig_node = container_of(rcu, struct batadv_orig_node, rcu);
-
 	spin_lock_bh(&orig_node->neigh_list_lock);
 
 	/* for all neighbors towards this originator ... */
 	hlist_for_each_entry_safe(neigh_node, node_tmp,
 				  &orig_node->neigh_list, list) {
 		hlist_del_rcu(&neigh_node->list);
-		batadv_neigh_node_free_ref_now(neigh_node);
+		batadv_neigh_node_free_ref(neigh_node);
 	}
 
 	hlist_for_each_entry_safe(orig_ifinfo, node_tmp,
 				  &orig_node->ifinfo_list, list) {
 		hlist_del_rcu(&orig_ifinfo->list);
-		batadv_orig_ifinfo_free_ref_now(orig_ifinfo);
+		batadv_orig_ifinfo_free_ref(orig_ifinfo);
 	}
 	spin_unlock_bh(&orig_node->neigh_list_lock);
 
-	batadv_mcast_purge_orig(orig_node);
-
 	/* Free nc_nodes */
 	batadv_nc_purge_orig(orig_node->bat_priv, orig_node, NULL);
 
-	batadv_frag_purge_orig(orig_node, NULL);
-
-	if (orig_node->bat_priv->bat_algo_ops->bat_orig_free)
-		orig_node->bat_priv->bat_algo_ops->bat_orig_free(orig_node);
-
-	kfree(orig_node->tt_buff);
-	kfree(orig_node);
+	call_rcu(&orig_node->rcu, batadv_orig_node_free_rcu);
 }
 
 /**
  * batadv_orig_node_free_ref - decrement the orig node refcounter and possibly
- * schedule an rcu callback for freeing it
+ *  release it
  * @orig_node: the orig node to free
  */
 void batadv_orig_node_free_ref(struct batadv_orig_node *orig_node)
 {
 	if (atomic_dec_and_test(&orig_node->refcount))
-		call_rcu(&orig_node->rcu, batadv_orig_node_free_rcu);
+		batadv_orig_node_release(orig_node);
 }
 
 /**
-- 
2.1.0


From bea68018ba807bc6560992d550c141784d8fc069 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Tue, 5 Jan 2016 12:06:22 +0100
Subject: [PATCH 21/24] batman-adv: Drop immediate batadv_neigh_node free
 function

[ Upstream commit 2baa753c276f27f8e844637561ad597867aa6fb6 ]

It is not allowed to free the memory of an object which is part of a list
which is protected by rcu-read-side-critical sections without making sure
that no other context is accessing the object anymore. This usually happens
by removing the references to this object and then waiting until the rcu
grace period is over and no one (allowedly) accesses it anymore.

But the _now functions ignore this completely. They free the object
directly even when a different context still tries to access it. This has
to be avoided and thus these functions must be removed and all functions
have to use batadv_neigh_node_free_ref.

Fixes: 89652331c00f ("batman-adv: split tq information in neigh_node struct")
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>
Signed-off-by: Antonio Quartulli <a@unstable.cc>
---
 net/batman-adv/originator.c | 33 ++++++++++-----------------------
 1 file changed, 10 insertions(+), 23 deletions(-)

diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index a072894..a8e68eb 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -229,20 +229,8 @@ static void batadv_neigh_node_free_rcu(struct rcu_head *rcu)
 }
 
 /**
- * batadv_neigh_node_free_ref_now - decrement the neighbors refcounter
- *  and possibly free it (without rcu callback)
- * @neigh_node: neigh neighbor to free
- */
-static void
-batadv_neigh_node_free_ref_now(struct batadv_neigh_node *neigh_node)
-{
-	if (atomic_dec_and_test(&neigh_node->refcount))
-		batadv_neigh_node_free_rcu(&neigh_node->rcu);
-}
-
-/**
  * batadv_neigh_node_free_ref - decrement the neighbors refcounter
- *  and possibly free it
+ *  and possibly release it
  * @neigh_node: neigh neighbor to free
  */
 void batadv_neigh_node_free_ref(struct batadv_neigh_node *neigh_node)
@@ -532,24 +520,23 @@ out:
 }
 
 /**
- * batadv_orig_ifinfo_free_rcu - free the orig_ifinfo object
- * @rcu: rcu pointer of the orig_ifinfo object
+ * batadv_orig_ifinfo_release - release orig_ifinfo from lists and queue for
+ *  free after rcu grace period
+ * @orig_ifinfo: the orig_ifinfo object to release
  */
-static void batadv_orig_ifinfo_free_rcu(struct rcu_head *rcu)
+static void batadv_orig_ifinfo_release(struct batadv_orig_ifinfo *orig_ifinfo)
 {
-	struct batadv_orig_ifinfo *orig_ifinfo;
 	struct batadv_neigh_node *router;
 
-	orig_ifinfo = container_of(rcu, struct batadv_orig_ifinfo, rcu);
-
 	if (orig_ifinfo->if_outgoing != BATADV_IF_DEFAULT)
-		batadv_hardif_free_ref_now(orig_ifinfo->if_outgoing);
+		batadv_hardif_free_ref(orig_ifinfo->if_outgoing);
 
 	/* this is the last reference to this object */
 	router = rcu_dereference_protected(orig_ifinfo->router, true);
 	if (router)
-		batadv_neigh_node_free_ref_now(router);
-	kfree(orig_ifinfo);
+		batadv_neigh_node_free_ref(router);
+
+	kfree_rcu(orig_ifinfo, rcu);
 }
 
 /**
@@ -560,7 +547,7 @@ static void batadv_orig_ifinfo_free_rcu(struct rcu_head *rcu)
 void batadv_orig_ifinfo_free_ref(struct batadv_orig_ifinfo *orig_ifinfo)
 {
 	if (atomic_dec_and_test(&orig_ifinfo->refcount))
-		call_rcu(&orig_ifinfo->rcu, batadv_orig_ifinfo_free_rcu);
+		batadv_orig_ifinfo_release(orig_ifinfo);
 }
 
 /**
-- 
2.1.0


From c01e3bc244234ab0b99746dc056a2edbbd6a7474 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Tue, 5 Jan 2016 12:06:24 +0100
Subject: [PATCH 22/24] batman-adv: Drop immediate neigh_ifinfo free function

[ Upstream commit ae3e1e36e3cb6c686a7a2725af20ca86aa46d62a ]

It is not allowed to free the memory of an object which is part of a list
which is protected by rcu-read-side-critical sections without making sure
that no other context is accessing the object anymore. This usually happens
by removing the references to this object and then waiting until the rcu
grace period is over and no one (allowedly) accesses it anymore.

But the _now functions ignore this completely. They free the object
directly even when a different context still tries to access it. This has
to be avoided and thus these functions must be removed and all functions
have to use batadv_neigh_ifinfo_free_ref.

Fixes: 89652331c00f ("batman-adv: split tq information in neigh_node struct")
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>
Signed-off-by: Antonio Quartulli <a@unstable.cc>
---
 net/batman-adv/originator.c | 34 ++++++++++------------------------
 1 file changed, 10 insertions(+), 24 deletions(-)

diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index a8e68eb..0c27f07 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -163,42 +163,28 @@ err:
 }
 
 /**
- * batadv_neigh_ifinfo_free_rcu - free the neigh_ifinfo object
- * @rcu: rcu pointer of the neigh_ifinfo object
- */
-static void batadv_neigh_ifinfo_free_rcu(struct rcu_head *rcu)
-{
-	struct batadv_neigh_ifinfo *neigh_ifinfo;
-
-	neigh_ifinfo = container_of(rcu, struct batadv_neigh_ifinfo, rcu);
-
-	if (neigh_ifinfo->if_outgoing != BATADV_IF_DEFAULT)
-		batadv_hardif_free_ref_now(neigh_ifinfo->if_outgoing);
-
-	kfree(neigh_ifinfo);
-}
-
-/**
- * batadv_neigh_ifinfo_free_now - decrement the refcounter and possibly free
- *  the neigh_ifinfo (without rcu callback)
+ * batadv_neigh_ifinfo_release - release neigh_ifinfo from lists and queue for
+ *  free after rcu grace period
  * @neigh_ifinfo: the neigh_ifinfo object to release
  */
 static void
-batadv_neigh_ifinfo_free_ref_now(struct batadv_neigh_ifinfo *neigh_ifinfo)
+batadv_neigh_ifinfo_release(struct batadv_neigh_ifinfo *neigh_ifinfo)
 {
-	if (atomic_dec_and_test(&neigh_ifinfo->refcount))
-		batadv_neigh_ifinfo_free_rcu(&neigh_ifinfo->rcu);
+	if (neigh_ifinfo->if_outgoing != BATADV_IF_DEFAULT)
+		batadv_hardif_free_ref(neigh_ifinfo->if_outgoing);
+
+	kfree_rcu(neigh_ifinfo, rcu);
 }
 
 /**
- * batadv_neigh_ifinfo_free_ref - decrement the refcounter and possibly free
+ * batadv_neigh_ifinfo_free_ref - decrement the refcounter and possibly release
  *  the neigh_ifinfo
  * @neigh_ifinfo: the neigh_ifinfo object to release
  */
 void batadv_neigh_ifinfo_free_ref(struct batadv_neigh_ifinfo *neigh_ifinfo)
 {
 	if (atomic_dec_and_test(&neigh_ifinfo->refcount))
-		call_rcu(&neigh_ifinfo->rcu, batadv_neigh_ifinfo_free_rcu);
+		batadv_neigh_ifinfo_release(neigh_ifinfo);
 }
 
 /**
@@ -217,7 +203,7 @@ static void batadv_neigh_node_free_rcu(struct rcu_head *rcu)
 
 	hlist_for_each_entry_safe(neigh_ifinfo, node_tmp,
 				  &neigh_node->ifinfo_list, list) {
-		batadv_neigh_ifinfo_free_ref_now(neigh_ifinfo);
+		batadv_neigh_ifinfo_free_ref(neigh_ifinfo);
 	}
 
 	if (bao->bat_neigh_free)
-- 
2.1.0


From 946b8972661dbcece8373e5651665fad10e1cb1e Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Tue, 5 Jan 2016 12:06:25 +0100
Subject: [PATCH 23/24] batman-adv: Drop immediate batadv_hard_iface free
 function

[ Upstream commit b4d922cfc9c08318eeb77d53b7633740e6b0efb0 ]

It is not allowed to free the memory of an object which is part of a list
which is protected by rcu-read-side-critical sections without making sure
that no other context is accessing the object anymore. This usually happens
by removing the references to this object and then waiting until the rcu
grace period is over and no one (allowedly) accesses it anymore.

But the _now functions ignore this completely. They free the object
directly even when a different context still tries to access it. This has
to be avoided and thus these functions must be removed and all functions
have to use batadv_hardif_free_ref.

Fixes: 89652331c00f ("batman-adv: split tq information in neigh_node struct")
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>
Signed-off-by: Antonio Quartulli <a@unstable.cc>
---
 net/batman-adv/hard-interface.h | 12 ------------
 net/batman-adv/originator.c     | 14 +++++++-------
 2 files changed, 7 insertions(+), 19 deletions(-)

diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h
index 5a31420..7b12ea8 100644
--- a/net/batman-adv/hard-interface.h
+++ b/net/batman-adv/hard-interface.h
@@ -75,18 +75,6 @@ batadv_hardif_free_ref(struct batadv_hard_iface *hard_iface)
 		call_rcu(&hard_iface->rcu, batadv_hardif_free_rcu);
 }
 
-/**
- * batadv_hardif_free_ref_now - decrement the hard interface refcounter and
- *  possibly free it (without rcu callback)
- * @hard_iface: the hard interface to free
- */
-static inline void
-batadv_hardif_free_ref_now(struct batadv_hard_iface *hard_iface)
-{
-	if (atomic_dec_and_test(&hard_iface->refcount))
-		batadv_hardif_free_rcu(&hard_iface->rcu);
-}
-
 static inline struct batadv_hard_iface *
 batadv_primary_if_get_selected(struct batadv_priv *bat_priv)
 {
diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index 0c27f07..d9d2cee 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -189,16 +189,16 @@ void batadv_neigh_ifinfo_free_ref(struct batadv_neigh_ifinfo *neigh_ifinfo)
 
 /**
  * batadv_neigh_node_free_rcu - free the neigh_node
- * @rcu: rcu pointer of the neigh_node
+ * batadv_neigh_node_release - release neigh_node from lists and queue for
+ *  free after rcu grace period
+ * @neigh_node: neigh neighbor to free
  */
-static void batadv_neigh_node_free_rcu(struct rcu_head *rcu)
+static void batadv_neigh_node_release(struct batadv_neigh_node *neigh_node)
 {
 	struct hlist_node *node_tmp;
-	struct batadv_neigh_node *neigh_node;
 	struct batadv_neigh_ifinfo *neigh_ifinfo;
 	struct batadv_algo_ops *bao;
 
-	neigh_node = container_of(rcu, struct batadv_neigh_node, rcu);
 	bao = neigh_node->orig_node->bat_priv->bat_algo_ops;
 
 	hlist_for_each_entry_safe(neigh_ifinfo, node_tmp,
@@ -209,9 +209,9 @@ static void batadv_neigh_node_free_rcu(struct rcu_head *rcu)
 	if (bao->bat_neigh_free)
 		bao->bat_neigh_free(neigh_node);
 
-	batadv_hardif_free_ref_now(neigh_node->if_incoming);
+	batadv_hardif_free_ref(neigh_node->if_incoming);
 
-	kfree(neigh_node);
+	kfree_rcu(neigh_node, rcu);
 }
 
 /**
@@ -222,7 +222,7 @@ static void batadv_neigh_node_free_rcu(struct rcu_head *rcu)
 void batadv_neigh_node_free_ref(struct batadv_neigh_node *neigh_node)
 {
 	if (atomic_dec_and_test(&neigh_node->refcount))
-		call_rcu(&neigh_node->rcu, batadv_neigh_node_free_rcu);
+		batadv_neigh_node_release(neigh_node);
 }
 
 /**
-- 
2.1.0


From 4605c9771c036e0b3f1b39e89573220ea0ebbea8 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Tue, 5 Jan 2016 12:06:20 +0100
Subject: [PATCH 24/24] batman-adv: Drop immediate orig_node free function

[ Upstream commit 42eff6a617e23b691f8e4467f4687ed7245a92db ]

It is not allowed to free the memory of an object which is part of a list
which is protected by rcu-read-side-critical sections without making sure
that no other context is accessing the object anymore. This usually happens
by removing the references to this object and then waiting until the rcu
grace period is over and no one (allowedly) accesses it anymore.

But the _now functions ignore this completely. They free the object
directly even when a different context still tries to access it. This has
to be avoided and thus these functions must be removed and all functions
have to use batadv_orig_node_free_ref.

Fixes: 72822225bd41 ("batman-adv: Fix rcu_barrier() miss due to double call_rcu() in TT code")
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>
Signed-off-by: Antonio Quartulli <a@unstable.cc>
---
 net/batman-adv/originator.c        | 11 -----------
 net/batman-adv/originator.h        |  1 -
 net/batman-adv/translation-table.c | 28 +++++++++++++---------------
 3 files changed, 13 insertions(+), 27 deletions(-)

diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index d9d2cee..17851d3 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -601,17 +601,6 @@ void batadv_orig_node_free_ref(struct batadv_orig_node *orig_node)
 		batadv_orig_node_release(orig_node);
 }
 
-/**
- * batadv_orig_node_free_ref_now - decrement the orig node refcounter and
- * possibly free it (without rcu callback)
- * @orig_node: the orig node to free
- */
-void batadv_orig_node_free_ref_now(struct batadv_orig_node *orig_node)
-{
-	if (atomic_dec_and_test(&orig_node->refcount))
-		batadv_orig_node_free_rcu(&orig_node->rcu);
-}
-
 void batadv_originator_free(struct batadv_priv *bat_priv)
 {
 	struct batadv_hashtable *hash = bat_priv->orig_hash;
diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h
index fa18f9b..a5c3788 100644
--- a/net/batman-adv/originator.h
+++ b/net/batman-adv/originator.h
@@ -38,7 +38,6 @@ int batadv_originator_init(struct batadv_priv *bat_priv);
 void batadv_originator_free(struct batadv_priv *bat_priv);
 void batadv_purge_orig_ref(struct batadv_priv *bat_priv);
 void batadv_orig_node_free_ref(struct batadv_orig_node *orig_node);
-void batadv_orig_node_free_ref_now(struct batadv_orig_node *orig_node);
 struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv,
 					      const u8 *addr);
 struct batadv_neigh_node *
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index 76f19ba..83b0ca2 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -240,20 +240,6 @@ int batadv_tt_global_hash_count(struct batadv_priv *bat_priv,
 	return count;
 }
 
-static void batadv_tt_orig_list_entry_free_rcu(struct rcu_head *rcu)
-{
-	struct batadv_tt_orig_list_entry *orig_entry;
-
-	orig_entry = container_of(rcu, struct batadv_tt_orig_list_entry, rcu);
-
-	/* We are in an rcu callback here, therefore we cannot use
-	 * batadv_orig_node_free_ref() and its call_rcu():
-	 * An rcu_barrier() wouldn't wait for that to finish
-	 */
-	batadv_orig_node_free_ref_now(orig_entry->orig_node);
-	kfree(orig_entry);
-}
-
 /**
  * batadv_tt_local_size_mod - change the size by v of the local table identified
  *  by vid
@@ -349,13 +335,25 @@ static void batadv_tt_global_size_dec(struct batadv_orig_node *orig_node,
 	batadv_tt_global_size_mod(orig_node, vid, -1);
 }
 
+/**
+ * batadv_tt_orig_list_entry_release - release tt orig entry from lists and
+ *  queue for free after rcu grace period
+ * @orig_entry: tt orig entry to be free'd
+ */
+static void
+batadv_tt_orig_list_entry_release(struct batadv_tt_orig_list_entry *orig_entry)
+{
+	batadv_orig_node_free_ref(orig_entry->orig_node);
+	kfree_rcu(orig_entry, rcu);
+}
+
 static void
 batadv_tt_orig_list_entry_free_ref(struct batadv_tt_orig_list_entry *orig_entry)
 {
 	if (!atomic_dec_and_test(&orig_entry->refcount))
 		return;
 
-	call_rcu(&orig_entry->rcu, batadv_tt_orig_list_entry_free_rcu);
+	batadv_tt_orig_list_entry_release(orig_entry);
 }
 
 /**
-- 
2.1.0


[-- Attachment #3: net_43.mbox --]
[-- Type: Application/Octet-Stream, Size: 120439 bytes --]

From eedc46a8a69a945aae20ff58efdc851496082b26 Mon Sep 17 00:00:00 2001
From: Simon Horman <simon.horman@netronome.com>
Date: Fri, 18 Dec 2015 19:43:15 +0900
Subject: [PATCH 01/40] openvswitch: correct encoding of set tunnel action
 attributes

[ Upstream commit e905eabc90a5b787d8708df164543ee295bea5f2 ]

In a set action tunnel attributes should be encoded in a
nested action.

I noticed this because ovs-dpctl was reporting an error
when dumping flows due to the incorrect encoding of tunnel attributes
in a set action.

Fixes: fc4099f17240 ("openvswitch: Fix egress tunnel info.")
Signed-off-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/flow_netlink.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 38536c1..4563511 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -2382,7 +2382,9 @@ static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb)
 		if (!start)
 			return -EMSGSIZE;
 
-		err = ovs_nla_put_tunnel_info(skb, tun_info);
+		err =  ipv4_tun_to_nlattr(skb, &tun_info->key,
+					  ip_tunnel_info_opts(tun_info),
+					  tun_info->options_len);
 		if (err)
 			return err;
 		nla_nest_end(skb, start);
-- 
2.1.0


From 401cb36391a7fdbc3366d4d2f2da2ba980a01c9c Mon Sep 17 00:00:00 2001
From: Vijay Pandurangan <vijayp@vijayp.ca>
Date: Fri, 18 Dec 2015 14:34:59 -0500
Subject: [PATCH 02/40] =?UTF-8?q?veth:=20don=E2=80=99t=20modify=20ip=5Fsum?=
 =?UTF-8?q?med;=20doing=20so=20treats=20packets=20with=20bad=20checksums?=
 =?UTF-8?q?=20as=20good.?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit ce8c839b74e3017996fad4e1b7ba2e2625ede82f ]

Packets that arrive from real hardware devices have ip_summed ==
CHECKSUM_UNNECESSARY if the hardware verified the checksums, or
CHECKSUM_NONE if the packet is bad or it was unable to verify it. The
current version of veth will replace CHECKSUM_NONE with
CHECKSUM_UNNECESSARY, which causes corrupt packets routed from hardware to
a veth device to be delivered to the application. This caused applications
at Twitter to receive corrupt data when network hardware was corrupting
packets.

We believe this was added as an optimization to skip computing and
verifying checksums for communication between containers. However, locally
generated packets have ip_summed == CHECKSUM_PARTIAL, so the code as
written does nothing for them. As far as we can tell, after removing this
code, these packets are transmitted from one stack to another unmodified
(tcpdump shows invalid checksums on both sides, as expected), and they are
delivered correctly to applications. We didn’t test every possible network
configuration, but we tried a few common ones such as bridging containers,
using NAT between the host and a container, and routing from hardware
devices to containers. We have effectively deployed this in production at
Twitter (by disabling RX checksum offloading on veth devices).

This code dates back to the first version of the driver, commit
<e314dbdc1c0dc6a548ecf> ("[NET]: Virtual ethernet device driver"), so I
suspect this bug occurred mostly because the driver API has evolved
significantly since then. Commit <0b7967503dc97864f283a> ("net/veth: Fix
packet checksumming") (in December 2010) fixed this for packets that get
created locally and sent to hardware devices, by not changing
CHECKSUM_PARTIAL. However, the same issue still occurs for packets coming
in from hardware devices.

Co-authored-by: Evan Jones <ej@evanjones.ca>
Signed-off-by: Evan Jones <ej@evanjones.ca>
Cc: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Cc: Phil Sutter <phil@nwl.cc>
Cc: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Cc: netdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Vijay Pandurangan <vijayp@vijayp.ca>
Acked-by: Cong Wang <cwang@twopensource.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/veth.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 0ef4a5a..ba21d07 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -117,12 +117,6 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 		kfree_skb(skb);
 		goto drop;
 	}
-	/* don't change ip_summed == CHECKSUM_PARTIAL, as that
-	 * will cause bad checksum on forwarded packets
-	 */
-	if (skb->ip_summed == CHECKSUM_NONE &&
-	    rcv->features & NETIF_F_RXCSUM)
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
 
 	if (likely(dev_forward_skb(rcv, skb) == NET_RX_SUCCESS)) {
 		struct pcpu_vstats *stats = this_cpu_ptr(dev->vstats);
-- 
2.1.0


From 695293225adc27ec92edffb3ea0038508704e9e0 Mon Sep 17 00:00:00 2001
From: Andrey Ryabinin <aryabinin@virtuozzo.com>
Date: Mon, 21 Dec 2015 12:54:45 +0300
Subject: [PATCH 03/40] ipv6/addrlabel: fix ip6addrlbl_get()

[ Upstream commit e459dfeeb64008b2d23bdf600f03b3605dbb8152 ]

ip6addrlbl_get() has never worked. If ip6addrlbl_hold() succeeded,
ip6addrlbl_get() will exit with '-ESRCH'. If ip6addrlbl_hold() failed,
ip6addrlbl_get() will use about to be free ip6addrlbl_entry pointer.

Fix this by inverting ip6addrlbl_hold() check.

Fixes: 2a8cc6c89039 ("[IPV6] ADDRCONF: Support RFC3484 configurable address selection policy table.")
Signed-off-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
Reviewed-by: Cong Wang <cwang@twopensource.com>
Acked-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrlabel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index 882124e..a8f6986 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -552,7 +552,7 @@ static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 
 	rcu_read_lock();
 	p = __ipv6_addr_label(net, addr, ipv6_addr_type(addr), ifal->ifal_index);
-	if (p && ip6addrlbl_hold(p))
+	if (p && !ip6addrlbl_hold(p))
 		p = NULL;
 	lseq = ip6addrlbl_table.seq;
 	rcu_read_unlock();
-- 
2.1.0


From ff3c5475a54a92fa06a44bd3870cb00b2a3bbd1c Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Mon, 21 Dec 2015 10:55:45 -0800
Subject: [PATCH 04/40] addrconf: always initialize sysctl table data

[ Upstream commit 5449a5ca9bc27dd51a462de7ca0b1cd861cd2bd0 ]

When sysctl performs restrict writes, it allows to write from
a middle position of a sysctl file, which requires us to initialize
the table data before calling proc_dostring() for the write case.

Fixes: 3d1bec99320d ("ipv6: introduce secret_stable to ipv6_devconf")
Reported-by: Sasha Levin <sasha.levin@oracle.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Tested-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index ddd3511..5462bfd 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5349,13 +5349,10 @@ static int addrconf_sysctl_stable_secret(struct ctl_table *ctl, int write,
 		goto out;
 	}
 
-	if (!write) {
-		err = snprintf(str, sizeof(str), "%pI6",
-			       &secret->secret);
-		if (err >= sizeof(str)) {
-			err = -EIO;
-			goto out;
-		}
+	err = snprintf(str, sizeof(str), "%pI6", &secret->secret);
+	if (err >= sizeof(str)) {
+		err = -EIO;
+		goto out;
 	}
 
 	err = proc_dostring(&lctl, write, buffer, lenp, ppos);
-- 
2.1.0


From ed763a94d746dc42499fb46e71a4befe17e75c25 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Wed, 23 Dec 2015 13:42:43 +0100
Subject: [PATCH 05/40] net: cdc_ncm: avoid changing RX/TX buffers on MTU
 changes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 1dfddff5fcd869fcab0c52fafae099dfa435a935 ]

NCM buffer sizes are negotiated with the device independently of
the network device MTU.  The RX buffers are allocated by the
usbnet framework based on the rx_urb_size value set by cdc_ncm. A
single RX buffer can hold a number of MTU sized packets.

The default usbnet change_mtu ndo only modifies rx_urb_size if it
is equal to hard_mtu.  And the cdc_ncm driver will set rx_urb_size
and hard_mtu independently of each other, based on dwNtbInMaxSize
and dwNtbOutMaxSize respectively. It was therefore assumed that
usbnet_change_mtu() would never touch rx_urb_size.  This failed to
consider the case where dwNtbInMaxSize and dwNtbOutMaxSize happens
to be equal.

Fix by implementing an NCM specific change_mtu ndo, modifying the
netdev MTU without touching the buffer size settings.

Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_mbim.c  |  2 +-
 drivers/net/usb/cdc_ncm.c   | 31 +++++++++++++++++++++++++++++++
 include/linux/usb/cdc_ncm.h |  1 +
 3 files changed, 33 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c
index b6ea6ff..d87b4ac 100644
--- a/drivers/net/usb/cdc_mbim.c
+++ b/drivers/net/usb/cdc_mbim.c
@@ -100,7 +100,7 @@ static const struct net_device_ops cdc_mbim_netdev_ops = {
 	.ndo_stop             = usbnet_stop,
 	.ndo_start_xmit       = usbnet_start_xmit,
 	.ndo_tx_timeout       = usbnet_tx_timeout,
-	.ndo_change_mtu       = usbnet_change_mtu,
+	.ndo_change_mtu       = cdc_ncm_change_mtu,
 	.ndo_set_mac_address  = eth_mac_addr,
 	.ndo_validate_addr    = eth_validate_addr,
 	.ndo_vlan_rx_add_vid  = cdc_mbim_rx_add_vid,
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index fa41a6d..e278a7a 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -41,6 +41,7 @@
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/ctype.h>
+#include <linux/etherdevice.h>
 #include <linux/ethtool.h>
 #include <linux/workqueue.h>
 #include <linux/mii.h>
@@ -689,6 +690,33 @@ static void cdc_ncm_free(struct cdc_ncm_ctx *ctx)
 	kfree(ctx);
 }
 
+/* we need to override the usbnet change_mtu ndo for two reasons:
+ *  - respect the negotiated maximum datagram size
+ *  - avoid unwanted changes to rx and tx buffers
+ */
+int cdc_ncm_change_mtu(struct net_device *net, int new_mtu)
+{
+	struct usbnet *dev = netdev_priv(net);
+	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
+	int maxmtu = ctx->max_datagram_size - cdc_ncm_eth_hlen(dev);
+
+	if (new_mtu <= 0 || new_mtu > maxmtu)
+		return -EINVAL;
+	net->mtu = new_mtu;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cdc_ncm_change_mtu);
+
+static const struct net_device_ops cdc_ncm_netdev_ops = {
+	.ndo_open	     = usbnet_open,
+	.ndo_stop	     = usbnet_stop,
+	.ndo_start_xmit	     = usbnet_start_xmit,
+	.ndo_tx_timeout	     = usbnet_tx_timeout,
+	.ndo_change_mtu	     = cdc_ncm_change_mtu,
+	.ndo_set_mac_address = eth_mac_addr,
+	.ndo_validate_addr   = eth_validate_addr,
+};
+
 int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting, int drvflags)
 {
 	const struct usb_cdc_union_desc *union_desc = NULL;
@@ -874,6 +902,9 @@ advance:
 	/* add our sysfs attrs */
 	dev->net->sysfs_groups[0] = &cdc_ncm_sysfs_attr_group;
 
+	/* must handle MTU changes */
+	dev->net->netdev_ops = &cdc_ncm_netdev_ops;
+
 	return 0;
 
 error2:
diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h
index 1f6526c..3a375d0 100644
--- a/include/linux/usb/cdc_ncm.h
+++ b/include/linux/usb/cdc_ncm.h
@@ -138,6 +138,7 @@ struct cdc_ncm_ctx {
 };
 
 u8 cdc_ncm_select_altsetting(struct usb_interface *intf);
+int cdc_ncm_change_mtu(struct net_device *net, int new_mtu);
 int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting, int drvflags);
 void cdc_ncm_unbind(struct usbnet *dev, struct usb_interface *intf);
 struct sk_buff *cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign);
-- 
2.1.0


From db54a8c1aedc4867ae3b854a097ce5a187795897 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 29 Dec 2015 17:49:25 +0800
Subject: [PATCH 06/40] sctp: sctp should release assoc when
 sctp_make_abort_user return NULL in sctp_close

[ Upstream commit 068d8bd338e855286aea54e70d1c101569284b21 ]

In sctp_close, sctp_make_abort_user may return NULL because of memory
allocation failure. If this happens, it will bypass any state change
and never free the assoc. The assoc has no chance to be freed and it
will be kept in memory with the state it had even after the socket is
closed by sctp_close().

So if sctp_make_abort_user fails to allocate memory, we should abort
the asoc via sctp_primitive_ABORT as well. Just like the annotation in
sctp_sf_cookie_wait_prm_abort and sctp_sf_do_9_1_prm_abort said,
"Even if we can't send the ABORT due to low memory delete the TCB.
This is a departure from our typical NOMEM handling".

But then the chunk is NULL (low memory) and the SCTP_CMD_REPLY cmd would
dereference the chunk pointer, and system crash. So we should add
SCTP_CMD_REPLY cmd only when the chunk is not NULL, just like other
places where it adds SCTP_CMD_REPLY cmd.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sm_statefuns.c | 6 ++++--
 net/sctp/socket.c       | 3 +--
 2 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index d7eaa73..c89586e 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -4829,7 +4829,8 @@ sctp_disposition_t sctp_sf_do_9_1_prm_abort(
 
 	retval = SCTP_DISPOSITION_CONSUME;
 
-	sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort));
+	if (abort)
+		sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort));
 
 	/* Even if we can't send the ABORT due to low memory delete the
 	 * TCB.  This is a departure from our typical NOMEM handling.
@@ -4966,7 +4967,8 @@ sctp_disposition_t sctp_sf_cookie_wait_prm_abort(
 			SCTP_TO(SCTP_EVENT_TIMEOUT_T1_INIT));
 	retval = SCTP_DISPOSITION_CONSUME;
 
-	sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort));
+	if (abort)
+		sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort));
 
 	sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE,
 			SCTP_STATE(SCTP_STATE_CLOSED));
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 84b1b50..9dee804 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1513,8 +1513,7 @@ static void sctp_close(struct sock *sk, long timeout)
 			struct sctp_chunk *chunk;
 
 			chunk = sctp_make_abort_user(asoc, NULL, 0);
-			if (chunk)
-				sctp_primitive_ABORT(net, asoc, chunk);
+			sctp_primitive_ABORT(net, asoc, chunk);
 		} else
 			sctp_primitive_SHUTDOWN(net, asoc, NULL);
 	}
-- 
2.1.0


From 1ec9e235143f7688b5c67f8b1f21c41aa3d7c096 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 31 Dec 2015 14:26:33 +0100
Subject: [PATCH 07/40] connector: bump skb->users before callback invocation

[ Upstream commit 55285bf09427c5abf43ee1d54e892f352092b1f1 ]

Dmitry reports memleak with syskaller program.
Problem is that connector bumps skb usecount but might not invoke callback.

So move skb_get to where we invoke the callback.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/connector/connector.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c
index 30f5228..c19e7fc 100644
--- a/drivers/connector/connector.c
+++ b/drivers/connector/connector.c
@@ -178,26 +178,21 @@ static int cn_call_callback(struct sk_buff *skb)
  *
  * It checks skb, netlink header and msg sizes, and calls callback helper.
  */
-static void cn_rx_skb(struct sk_buff *__skb)
+static void cn_rx_skb(struct sk_buff *skb)
 {
 	struct nlmsghdr *nlh;
-	struct sk_buff *skb;
 	int len, err;
 
-	skb = skb_get(__skb);
-
 	if (skb->len >= NLMSG_HDRLEN) {
 		nlh = nlmsg_hdr(skb);
 		len = nlmsg_len(nlh);
 
 		if (len < (int)sizeof(struct cn_msg) ||
 		    skb->len < nlh->nlmsg_len ||
-		    len > CONNECTOR_MAX_MSG_SIZE) {
-			kfree_skb(skb);
+		    len > CONNECTOR_MAX_MSG_SIZE)
 			return;
-		}
 
-		err = cn_call_callback(skb);
+		err = cn_call_callback(skb_get(skb));
 		if (err < 0)
 			kfree_skb(skb);
 	}
-- 
2.1.0


From e3b4828390f23167a210accea6f6655621177ae9 Mon Sep 17 00:00:00 2001
From: Rainer Weikusat <rweikusat@mobileactivedefense.com>
Date: Sun, 3 Jan 2016 18:56:38 +0000
Subject: [PATCH 08/40] af_unix: Fix splice-bind deadlock

[ Upstream commit c845acb324aa85a39650a14e7696982ceea75dc1 ]

On 2015/11/06, Dmitry Vyukov reported a deadlock involving the splice
system call and AF_UNIX sockets,

http://lists.openwall.net/netdev/2015/11/06/24

The situation was analyzed as

(a while ago) A: socketpair()
B: splice() from a pipe to /mnt/regular_file
	does sb_start_write() on /mnt
C: try to freeze /mnt
	wait for B to finish with /mnt
A: bind() try to bind our socket to /mnt/new_socket_name
	lock our socket, see it not bound yet
	decide that it needs to create something in /mnt
	try to do sb_start_write() on /mnt, block (it's
	waiting for C).
D: splice() from the same pipe to our socket
	lock the pipe, see that socket is connected
	try to lock the socket, block waiting for A
B:	get around to actually feeding a chunk from
	pipe to file, try to lock the pipe.  Deadlock.

on 2015/11/10 by Al Viro,

http://lists.openwall.net/netdev/2015/11/10/4

The patch fixes this by removing the kern_path_create related code from
unix_mknod and executing it as part of unix_bind prior acquiring the
readlock of the socket in question. This means that A (as used above)
will sb_start_write on /mnt before it acquires the readlock, hence, it
won't indirectly block B which first did a sb_start_write and then
waited for a thread trying to acquire the readlock. Consequently, A
being blocked by C waiting for B won't cause a deadlock anymore
(effectively, both A and B acquire two locks in opposite order in the
situation described above).

Dmitry Vyukov(<dvyukov@google.com>) tested the original patch.

Signed-off-by: Rainer Weikusat <rweikusat@mobileactivedefense.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c | 66 +++++++++++++++++++++++++++++++++---------------------
 1 file changed, 40 insertions(+), 26 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 0fc6dba..0e7bf2b 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -952,32 +952,20 @@ fail:
 	return NULL;
 }
 
-static int unix_mknod(const char *sun_path, umode_t mode, struct path *res)
+static int unix_mknod(struct dentry *dentry, struct path *path, umode_t mode,
+		      struct path *res)
 {
-	struct dentry *dentry;
-	struct path path;
-	int err = 0;
-	/*
-	 * Get the parent directory, calculate the hash for last
-	 * component.
-	 */
-	dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0);
-	err = PTR_ERR(dentry);
-	if (IS_ERR(dentry))
-		return err;
+	int err;
 
-	/*
-	 * All right, let's create it.
-	 */
-	err = security_path_mknod(&path, dentry, mode, 0);
+	err = security_path_mknod(path, dentry, mode, 0);
 	if (!err) {
-		err = vfs_mknod(d_inode(path.dentry), dentry, mode, 0);
+		err = vfs_mknod(d_inode(path->dentry), dentry, mode, 0);
 		if (!err) {
-			res->mnt = mntget(path.mnt);
+			res->mnt = mntget(path->mnt);
 			res->dentry = dget(dentry);
 		}
 	}
-	done_path_create(&path, dentry);
+
 	return err;
 }
 
@@ -988,10 +976,12 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	struct unix_sock *u = unix_sk(sk);
 	struct sockaddr_un *sunaddr = (struct sockaddr_un *)uaddr;
 	char *sun_path = sunaddr->sun_path;
-	int err;
+	int err, name_err;
 	unsigned int hash;
 	struct unix_address *addr;
 	struct hlist_head *list;
+	struct path path;
+	struct dentry *dentry;
 
 	err = -EINVAL;
 	if (sunaddr->sun_family != AF_UNIX)
@@ -1007,14 +997,34 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		goto out;
 	addr_len = err;
 
+	name_err = 0;
+	dentry = NULL;
+	if (sun_path[0]) {
+		/* Get the parent directory, calculate the hash for last
+		 * component.
+		 */
+		dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0);
+
+		if (IS_ERR(dentry)) {
+			/* delay report until after 'already bound' check */
+			name_err = PTR_ERR(dentry);
+			dentry = NULL;
+		}
+	}
+
 	err = mutex_lock_interruptible(&u->readlock);
 	if (err)
-		goto out;
+		goto out_path;
 
 	err = -EINVAL;
 	if (u->addr)
 		goto out_up;
 
+	if (name_err) {
+		err = name_err == -EEXIST ? -EADDRINUSE : name_err;
+		goto out_up;
+	}
+
 	err = -ENOMEM;
 	addr = kmalloc(sizeof(*addr)+addr_len, GFP_KERNEL);
 	if (!addr)
@@ -1025,11 +1035,11 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	addr->hash = hash ^ sk->sk_type;
 	atomic_set(&addr->refcnt, 1);
 
-	if (sun_path[0]) {
-		struct path path;
+	if (dentry) {
+		struct path u_path;
 		umode_t mode = S_IFSOCK |
 		       (SOCK_INODE(sock)->i_mode & ~current_umask());
-		err = unix_mknod(sun_path, mode, &path);
+		err = unix_mknod(dentry, &path, mode, &u_path);
 		if (err) {
 			if (err == -EEXIST)
 				err = -EADDRINUSE;
@@ -1037,9 +1047,9 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 			goto out_up;
 		}
 		addr->hash = UNIX_HASH_SIZE;
-		hash = d_backing_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE-1);
+		hash = d_backing_inode(dentry)->i_ino & (UNIX_HASH_SIZE - 1);
 		spin_lock(&unix_table_lock);
-		u->path = path;
+		u->path = u_path;
 		list = &unix_socket_table[hash];
 	} else {
 		spin_lock(&unix_table_lock);
@@ -1062,6 +1072,10 @@ out_unlock:
 	spin_unlock(&unix_table_lock);
 out_up:
 	mutex_unlock(&u->readlock);
+out_path:
+	if (dentry)
+		done_path_create(&path, dentry);
+
 out:
 	return err;
 }
-- 
2.1.0


From 5bd335ad4325029262c321436fd83f9d2f9310f6 Mon Sep 17 00:00:00 2001
From: willy tarreau <w@1wt.eu>
Date: Sun, 10 Jan 2016 07:54:56 +0100
Subject: [PATCH 09/40] unix: properly account for FDs passed over unix sockets

[ Upstream commit 712f4aad406bb1ed67f3f98d04c044191f0ff593 ]

It is possible for a process to allocate and accumulate far more FDs than
the process' limit by sending them over a unix socket then closing them
to keep the process' fd count low.

This change addresses this problem by keeping track of the number of FDs
in flight per user and preventing non-privileged processes from having
more FDs in flight than their configured FD limit.

Reported-by: socketpair@gmail.com
Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Mitigates: CVE-2013-4312 (Linux 2.0+)
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/sched.h |  1 +
 net/unix/af_unix.c    | 24 ++++++++++++++++++++----
 net/unix/garbage.c    | 13 ++++++++-----
 3 files changed, 29 insertions(+), 9 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index b7b9501..f477e87 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -830,6 +830,7 @@ struct user_struct {
 	unsigned long mq_bytes;	/* How many bytes can be allocated to mqueue? */
 #endif
 	unsigned long locked_shm; /* How many pages of mlocked shm ? */
+	unsigned long unix_inflight;	/* How many files in flight in unix sockets */
 
 #ifdef CONFIG_KEYS
 	struct key *uid_keyring;	/* UID specific keyring */
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 0e7bf2b..7926de1 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1512,6 +1512,21 @@ static void unix_destruct_scm(struct sk_buff *skb)
 	sock_wfree(skb);
 }
 
+/*
+ * The "user->unix_inflight" variable is protected by the garbage
+ * collection lock, and we just read it locklessly here. If you go
+ * over the limit, there might be a tiny race in actually noticing
+ * it across threads. Tough.
+ */
+static inline bool too_many_unix_fds(struct task_struct *p)
+{
+	struct user_struct *user = current_user();
+
+	if (unlikely(user->unix_inflight > task_rlimit(p, RLIMIT_NOFILE)))
+		return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN);
+	return false;
+}
+
 #define MAX_RECURSION_LEVEL 4
 
 static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
@@ -1520,6 +1535,9 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
 	unsigned char max_level = 0;
 	int unix_sock_count = 0;
 
+	if (too_many_unix_fds(current))
+		return -ETOOMANYREFS;
+
 	for (i = scm->fp->count - 1; i >= 0; i--) {
 		struct sock *sk = unix_get_socket(scm->fp->fp[i]);
 
@@ -1541,10 +1559,8 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
 	if (!UNIXCB(skb).fp)
 		return -ENOMEM;
 
-	if (unix_sock_count) {
-		for (i = scm->fp->count - 1; i >= 0; i--)
-			unix_inflight(scm->fp->fp[i]);
-	}
+	for (i = scm->fp->count - 1; i >= 0; i--)
+		unix_inflight(scm->fp->fp[i]);
 	return max_level;
 }
 
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index a73a226..8fcdc22 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -120,11 +120,11 @@ void unix_inflight(struct file *fp)
 {
 	struct sock *s = unix_get_socket(fp);
 
+	spin_lock(&unix_gc_lock);
+
 	if (s) {
 		struct unix_sock *u = unix_sk(s);
 
-		spin_lock(&unix_gc_lock);
-
 		if (atomic_long_inc_return(&u->inflight) == 1) {
 			BUG_ON(!list_empty(&u->link));
 			list_add_tail(&u->link, &gc_inflight_list);
@@ -132,25 +132,28 @@ void unix_inflight(struct file *fp)
 			BUG_ON(list_empty(&u->link));
 		}
 		unix_tot_inflight++;
-		spin_unlock(&unix_gc_lock);
 	}
+	fp->f_cred->user->unix_inflight++;
+	spin_unlock(&unix_gc_lock);
 }
 
 void unix_notinflight(struct file *fp)
 {
 	struct sock *s = unix_get_socket(fp);
 
+	spin_lock(&unix_gc_lock);
+
 	if (s) {
 		struct unix_sock *u = unix_sk(s);
 
-		spin_lock(&unix_gc_lock);
 		BUG_ON(list_empty(&u->link));
 
 		if (atomic_long_dec_and_test(&u->inflight))
 			list_del_init(&u->link);
 		unix_tot_inflight--;
-		spin_unlock(&unix_gc_lock);
 	}
+	fp->f_cred->user->unix_inflight--;
+	spin_unlock(&unix_gc_lock);
 }
 
 static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *),
-- 
2.1.0


From c9da36e7ac35987b4fe153ad473a186d1fb53ef6 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Tue, 5 Jan 2016 10:46:00 +0100
Subject: [PATCH 10/40] bridge: Only call /sbin/bridge-stp for the initial
 network namespace

[ Upstream commit ff62198553e43cdffa9d539f6165d3e83f8a42bc ]

[I stole this patch from Eric Biederman. He wrote:]

> There is no defined mechanism to pass network namespace information
> into /sbin/bridge-stp therefore don't even try to invoke it except
> for bridge devices in the initial network namespace.
>
> It is possible for unprivileged users to cause /sbin/bridge-stp to be
> invoked for any network device name which if /sbin/bridge-stp does not
> guard against unreasonable arguments or being invoked twice on the
> same network device could cause problems.

[Hannes: changed patch using netns_eq]

Cc: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_stp_if.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
index 4ca449a..49d8d28 100644
--- a/net/bridge/br_stp_if.c
+++ b/net/bridge/br_stp_if.c
@@ -130,7 +130,10 @@ static void br_stp_start(struct net_bridge *br)
 	char *envp[] = { NULL };
 	struct net_bridge_port *p;
 
-	r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC);
+	if (net_eq(dev_net(br->dev), &init_net))
+		r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC);
+	else
+		r = -ENOENT;
 
 	spin_lock_bh(&br->lock);
 
-- 
2.1.0


From b024b6ad652514fe2baf71668633b17aada5ebf3 Mon Sep 17 00:00:00 2001
From: Rabin Vincent <rabin@rab.in>
Date: Tue, 5 Jan 2016 16:23:07 +0100
Subject: [PATCH 11/40] net: filter: make JITs zero A for SKF_AD_ALU_XOR_X

[ Upstream commit 55795ef5469290f89f04e12e662ded604909e462 ]

The SKF_AD_ALU_XOR_X ancillary is not like the other ancillary data
instructions since it XORs A with X while all the others replace A with
some loaded value.  All the BPF JITs fail to clear A if this is used as
the first instruction in a filter.  This was found using american fuzzy
lop.

Add a helper to determine if A needs to be cleared given the first
instruction in a filter, and use this in the JITs.  Except for ARM, the
rest have only been compile-tested.

Fixes: 3480593131e0 ("net: filter: get rid of BPF_S_* enum")
Signed-off-by: Rabin Vincent <rabin@rab.in>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/arm/net/bpf_jit_32.c       | 16 +---------------
 arch/mips/net/bpf_jit.c         | 16 +---------------
 arch/powerpc/net/bpf_jit_comp.c | 13 ++-----------
 arch/sparc/net/bpf_jit_comp.c   | 17 ++---------------
 include/linux/filter.h          | 19 +++++++++++++++++++
 5 files changed, 25 insertions(+), 56 deletions(-)

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index b8efb8c..4d25fd0 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -182,19 +182,6 @@ static inline int mem_words_used(struct jit_ctx *ctx)
 	return fls(ctx->seen & SEEN_MEM);
 }
 
-static inline bool is_load_to_a(u16 inst)
-{
-	switch (inst) {
-	case BPF_LD | BPF_W | BPF_LEN:
-	case BPF_LD | BPF_W | BPF_ABS:
-	case BPF_LD | BPF_H | BPF_ABS:
-	case BPF_LD | BPF_B | BPF_ABS:
-		return true;
-	default:
-		return false;
-	}
-}
-
 static void jit_fill_hole(void *area, unsigned int size)
 {
 	u32 *ptr;
@@ -206,7 +193,6 @@ static void jit_fill_hole(void *area, unsigned int size)
 static void build_prologue(struct jit_ctx *ctx)
 {
 	u16 reg_set = saved_regs(ctx);
-	u16 first_inst = ctx->skf->insns[0].code;
 	u16 off;
 
 #ifdef CONFIG_FRAME_POINTER
@@ -236,7 +222,7 @@ static void build_prologue(struct jit_ctx *ctx)
 		emit(ARM_MOV_I(r_X, 0), ctx);
 
 	/* do not leak kernel data to userspace */
-	if ((first_inst != (BPF_RET | BPF_K)) && !(is_load_to_a(first_inst)))
+	if (bpf_needs_clear_a(&ctx->skf->insns[0]))
 		emit(ARM_MOV_I(r_A, 0), ctx);
 
 	/* stack space for the BPF_MEM words */
diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c
index 0c4a133..26e947d 100644
--- a/arch/mips/net/bpf_jit.c
+++ b/arch/mips/net/bpf_jit.c
@@ -521,19 +521,6 @@ static inline u16 align_sp(unsigned int num)
 	return num;
 }
 
-static bool is_load_to_a(u16 inst)
-{
-	switch (inst) {
-	case BPF_LD | BPF_W | BPF_LEN:
-	case BPF_LD | BPF_W | BPF_ABS:
-	case BPF_LD | BPF_H | BPF_ABS:
-	case BPF_LD | BPF_B | BPF_ABS:
-		return true;
-	default:
-		return false;
-	}
-}
-
 static void save_bpf_jit_regs(struct jit_ctx *ctx, unsigned offset)
 {
 	int i = 0, real_off = 0;
@@ -614,7 +601,6 @@ static unsigned int get_stack_depth(struct jit_ctx *ctx)
 
 static void build_prologue(struct jit_ctx *ctx)
 {
-	u16 first_inst = ctx->skf->insns[0].code;
 	int sp_off;
 
 	/* Calculate the total offset for the stack pointer */
@@ -641,7 +627,7 @@ static void build_prologue(struct jit_ctx *ctx)
 		emit_jit_reg_move(r_X, r_zero, ctx);
 
 	/* Do not leak kernel data to userspace */
-	if ((first_inst != (BPF_RET | BPF_K)) && !(is_load_to_a(first_inst)))
+	if (bpf_needs_clear_a(&ctx->skf->insns[0]))
 		emit_jit_reg_move(r_A, r_zero, ctx);
 }
 
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 17cea18..264c473 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -78,18 +78,9 @@ static void bpf_jit_build_prologue(struct bpf_prog *fp, u32 *image,
 		PPC_LI(r_X, 0);
 	}
 
-	switch (filter[0].code) {
-	case BPF_RET | BPF_K:
-	case BPF_LD | BPF_W | BPF_LEN:
-	case BPF_LD | BPF_W | BPF_ABS:
-	case BPF_LD | BPF_H | BPF_ABS:
-	case BPF_LD | BPF_B | BPF_ABS:
-		/* first instruction sets A register (or is RET 'constant') */
-		break;
-	default:
-		/* make sure we dont leak kernel information to user */
+	/* make sure we dont leak kernel information to user */
+	if (bpf_needs_clear_a(&filter[0]))
 		PPC_LI(r_A, 0);
-	}
 }
 
 static void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c
index f8b9f71..17e71d2 100644
--- a/arch/sparc/net/bpf_jit_comp.c
+++ b/arch/sparc/net/bpf_jit_comp.c
@@ -420,22 +420,9 @@ void bpf_jit_compile(struct bpf_prog *fp)
 		}
 		emit_reg_move(O7, r_saved_O7);
 
-		switch (filter[0].code) {
-		case BPF_RET | BPF_K:
-		case BPF_LD | BPF_W | BPF_LEN:
-		case BPF_LD | BPF_W | BPF_ABS:
-		case BPF_LD | BPF_H | BPF_ABS:
-		case BPF_LD | BPF_B | BPF_ABS:
-			/* The first instruction sets the A register (or is
-			 * a "RET 'constant'")
-			 */
-			break;
-		default:
-			/* Make sure we dont leak kernel information to the
-			 * user.
-			 */
+		/* Make sure we dont leak kernel information to the user. */
+		if (bpf_needs_clear_a(&filter[0]))
 			emit_clear(r_A); /* A = 0 */
-		}
 
 		for (i = 0; i < flen; i++) {
 			unsigned int K = filter[i].k;
diff --git a/include/linux/filter.h b/include/linux/filter.h
index fa2cab9..d42a5b8 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -459,6 +459,25 @@ static inline void bpf_jit_free(struct bpf_prog *fp)
 
 #define BPF_ANC		BIT(15)
 
+static inline bool bpf_needs_clear_a(const struct sock_filter *first)
+{
+	switch (first->code) {
+	case BPF_RET | BPF_K:
+	case BPF_LD | BPF_W | BPF_LEN:
+		return false;
+
+	case BPF_LD | BPF_W | BPF_ABS:
+	case BPF_LD | BPF_H | BPF_ABS:
+	case BPF_LD | BPF_B | BPF_ABS:
+		if (first->k == SKF_AD_OFF + SKF_AD_ALU_XOR_X)
+			return true;
+		return false;
+
+	default:
+		return true;
+	}
+}
+
 static inline u16 bpf_anc_helper(const struct sock_filter *ftest)
 {
 	BUG_ON(ftest->code & BPF_ANC);
-- 
2.1.0


From 5f7994a8b4d5dd62a1ff38e9c8491d062088e791 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Tue, 5 Jan 2016 09:11:36 -0800
Subject: [PATCH 12/40] net: sched: fix missing free per cpu on qstats

[ Upstream commit 73c20a8b7245273125cfe92c4b46e6fdb568a801 ]

When a qdisc is using per cpu stats (currently just the ingress
qdisc) only the bstats are being freed. This also free's the qstats.

Fixes: b0ab6f92752b9f9d8 ("net: sched: enable per cpu qstats")
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_generic.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index e82a1ad..16bc83b 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -658,8 +658,10 @@ static void qdisc_rcu_free(struct rcu_head *head)
 {
 	struct Qdisc *qdisc = container_of(head, struct Qdisc, rcu_head);
 
-	if (qdisc_is_percpu_stats(qdisc))
+	if (qdisc_is_percpu_stats(qdisc)) {
 		free_percpu(qdisc->cpu_bstats);
+		free_percpu(qdisc->cpu_qstats);
+	}
 
 	kfree((char *) qdisc - qdisc->padded);
 }
-- 
2.1.0


From 71a2504bfa54a157365fb7a9da6ad40e98da6d34 Mon Sep 17 00:00:00 2001
From: Francesco Ruggeri <fruggeri@aristanetworks.com>
Date: Wed, 6 Jan 2016 00:18:48 -0800
Subject: [PATCH 13/40] net: possible use after free in dst_release

[ Upstream commit 07a5d38453599052aff0877b16bb9c1585f08609 ]

dst_release should not access dst->flags after decrementing
__refcnt to 0. The dst_entry may be in dst_busy_list and
dst_gc_task may dst_destroy it before dst_release gets a chance
to access dst->flags.

Fixes: d69bbf88c8d0 ("net: fix a race in dst_release()")
Fixes: 27b75c95f10d ("net: avoid RCU for NOCACHE dst")
Signed-off-by: Francesco Ruggeri <fruggeri@arista.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dst.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/dst.c b/net/core/dst.c
index d6a5a0b..8852021 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -301,12 +301,13 @@ void dst_release(struct dst_entry *dst)
 {
 	if (dst) {
 		int newrefcnt;
+		unsigned short nocache = dst->flags & DST_NOCACHE;
 
 		newrefcnt = atomic_dec_return(&dst->__refcnt);
 		if (unlikely(newrefcnt < 0))
 			net_warn_ratelimited("%s: dst:%p refcnt:%d\n",
 					     __func__, dst, newrefcnt);
-		if (!newrefcnt && unlikely(dst->flags & DST_NOCACHE))
+		if (!newrefcnt && unlikely(nocache))
 			call_rcu(&dst->rcu_head, dst_destroy_rcu);
 	}
 }
-- 
2.1.0


From fe94d13d943c2501cd61c7e061cb3d55689e1222 Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Wed, 6 Jan 2016 12:42:38 -0800
Subject: [PATCH 14/40] tcp: fix zero cwnd in tcp_cwnd_reduction

[ Upstream commit 8b8a321ff72c785ed5e8b4cf6eda20b35d427390 ]

Patch 3759824da87b ("tcp: PRR uses CRB mode by default and SS mode
conditionally") introduced a bug that cwnd may become 0 when both
inflight and sndcnt are 0 (cwnd = inflight + sndcnt). This may lead
to a div-by-zero if the connection starts another cwnd reduction
phase by setting tp->prior_cwnd to the current cwnd (0) in
tcp_init_cwnd_reduction().

To prevent this we skip PRR operation when nothing is acked or
sacked. Then cwnd must be positive in all cases as long as ssthresh
is positive:

1) The proportional reduction mode
   inflight > ssthresh > 0

2) The reduction bound mode
  a) inflight == ssthresh > 0

  b) inflight < ssthresh
     sndcnt > 0 since newly_acked_sacked > 0 and inflight < ssthresh

Therefore in all cases inflight and sndcnt can not both be 0.
We check invalid tp->prior_cwnd to avoid potential div0 bugs.

In reality this bug is triggered only with a sequence of less common
events.  For example, the connection is terminating an ECN-triggered
cwnd reduction with an inflight 0, then it receives reordered/old
ACKs or DSACKs from prior transmission (which acks nothing). Or the
connection is in fast recovery stage that marks everything lost,
but fails to retransmit due to local issues, then receives data
packets from other end which acks nothing.

Fixes: 3759824da87b ("tcp: PRR uses CRB mode by default and SS mode conditionally")
Reported-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 0a2b61d..064f1a0 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2525,6 +2525,9 @@ static void tcp_cwnd_reduction(struct sock *sk, const int prior_unsacked,
 	int newly_acked_sacked = prior_unsacked -
 				 (tp->packets_out - tp->sacked_out);
 
+	if (newly_acked_sacked <= 0 || WARN_ON_ONCE(!tp->prior_cwnd))
+		return;
+
 	tp->prr_delivered += newly_acked_sacked;
 	if (delta < 0) {
 		u64 dividend = (u64)tp->snd_ssthresh * tp->prr_delivered +
-- 
2.1.0


From 1c1773db926fb64d7833d3a130f738f2ffc96e21 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Thu, 7 Jan 2016 11:26:53 +0100
Subject: [PATCH 15/40] vxlan: fix test which detect duplicate vxlan iface

[ Upstream commit 07b9b37c227cb8d88d478b4a9c5634fee514ede1 ]

When a vxlan interface is created, the driver checks that there is not
another vxlan interface with the same properties. To do this, it checks
the existing vxlan udp socket. Since commit 1c51a9159dde, the creation of
the vxlan socket is done only when the interface is set up, thus it breaks
that test.

Example:
$ ip l a vxlan10 type vxlan id 10 group 239.0.0.10 dev eth0 dstport 0
$ ip l a vxlan11 type vxlan id 10 group 239.0.0.10 dev eth0 dstport 0
$ ip -br l | grep vxlan
vxlan10          DOWN           f2:55:1c:6a:fb:00 <BROADCAST,MULTICAST>
vxlan11          DOWN           7a:cb:b9:38:59:0d <BROADCAST,MULTICAST>

Instead of checking sockets, let's loop over the vxlan iface list.

Fixes: 1c51a9159dde ("vxlan: fix race caused by dropping rtnl_unlock")
Reported-by: Thomas Faivre <thomas.faivre@6wind.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index c1587ec..40b5f8a 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2660,7 +2660,7 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 			       struct vxlan_config *conf)
 {
 	struct vxlan_net *vn = net_generic(src_net, vxlan_net_id);
-	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_dev *vxlan = netdev_priv(dev), *tmp;
 	struct vxlan_rdst *dst = &vxlan->default_dst;
 	int err;
 	bool use_ipv6 = false;
@@ -2725,9 +2725,15 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 	if (!vxlan->cfg.age_interval)
 		vxlan->cfg.age_interval = FDB_AGE_DEFAULT;
 
-	if (vxlan_find_vni(src_net, conf->vni, use_ipv6 ? AF_INET6 : AF_INET,
-			   vxlan->cfg.dst_port, vxlan->flags))
+	list_for_each_entry(tmp, &vn->vxlan_list, next) {
+		if (tmp->cfg.vni == conf->vni &&
+		    (tmp->default_dst.remote_ip.sa.sa_family == AF_INET6 ||
+		     tmp->cfg.saddr.sa.sa_family == AF_INET6) == use_ipv6 &&
+		    tmp->cfg.dst_port == vxlan->cfg.dst_port &&
+		    (tmp->flags & VXLAN_F_RCV_FLAGS) ==
+		    (vxlan->flags & VXLAN_F_RCV_FLAGS))
 		return -EEXIST;
+	}
 
 	dev->ethtool_ops = &vxlan_ethtool_ops;
 
-- 
2.1.0


From b69d761f6900518fb90d29488fac8f5dbdace722 Mon Sep 17 00:00:00 2001
From: Sasha Levin <sasha.levin@oracle.com>
Date: Thu, 7 Jan 2016 14:52:43 -0500
Subject: [PATCH 16/40] net: sctp: prevent writes to cookie_hmac_alg from
 accessing invalid memory

[ Upstream commit 320f1a4a175e7cd5d3f006f92b4d4d3e2cbb7bb5 ]

proc_dostring() needs an initialized destination string, while the one
provided in proc_sctp_do_hmac_alg() contains stack garbage.

Thus, writing to cookie_hmac_alg would strlen() that garbage and end up
accessing invalid memory.

Fixes: 3c68198e7 ("sctp: Make hmac algorithm selection for cookie generation dynamic")
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sysctl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index 26d50c5..3e0fc51 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -320,7 +320,7 @@ static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write,
 	struct ctl_table tbl;
 	bool changed = false;
 	char *none = "none";
-	char tmp[8];
+	char tmp[8] = {0};
 	int ret;
 
 	memset(&tbl, 0, sizeof(struct ctl_table));
-- 
2.1.0


From 188bfdb897f70e010491b2ea67edda334162b2cb Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 8 Jan 2016 09:35:51 -0800
Subject: [PATCH 17/40] ipv6: tcp: add rcu locking in tcp_v6_send_synack()

[ Upstream commit 3e4006f0b86a5ae5eb0e8215f9a9e1db24506977 ]

When first SYNACK is sent, we already hold rcu_read_lock(), but this
is not true if a SYNACK is retransmitted, as a timer (soft) interrupt
does not hold rcu_read_lock()

Fixes: 45f6fad84cc30 ("ipv6: add complete rcu protection around np->opt")
Reported-by: Dave Jones <davej@codemonkey.org.uk>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/tcp_ipv6.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 8935dc1..a71fb26 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -462,8 +462,10 @@ static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst,
 			fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));
 
 		skb_set_queue_mapping(skb, queue_mapping);
+		rcu_read_lock();
 		err = ip6_xmit(sk, skb, fl6, rcu_dereference(np->opt),
 			       np->tclass);
+		rcu_read_unlock();
 		err = net_xmit_eval(err);
 	}
 
-- 
2.1.0


From 4e3c6e834edb6f3a725178b3df0e96074158b81a Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Mon, 11 Jan 2016 13:42:43 -0500
Subject: [PATCH 18/40] tcp_yeah: don't set ssthresh below 2

[ Upstream commit 83d15e70c4d8909d722c0d64747d8fb42e38a48f ]

For tcp_yeah, use an ssthresh floor of 2, the same floor used by Reno
and CUBIC, per RFC 5681 (equation 4).

tcp_yeah_ssthresh() was sometimes returning a 0 or negative ssthresh
value if the intended reduction is as big or bigger than the current
cwnd. Congestion control modules should never return a zero or
negative ssthresh. A zero ssthresh generally results in a zero cwnd,
causing the connection to stall. A negative ssthresh value will be
interpreted as a u32 and will set a target cwnd for PRR near 4
billion.

Oleksandr Natalenko reported that a system using tcp_yeah with ECN
could see a warning about a prior_cwnd of 0 in
tcp_cwnd_reduction(). Testing verified that this was due to
tcp_yeah_ssthresh() misbehaving in this way.

Reported-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_yeah.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c
index 17d3566..3e6a472 100644
--- a/net/ipv4/tcp_yeah.c
+++ b/net/ipv4/tcp_yeah.c
@@ -219,7 +219,7 @@ static u32 tcp_yeah_ssthresh(struct sock *sk)
 	yeah->fast_count = 0;
 	yeah->reno_count = max(yeah->reno_count>>1, 2U);
 
-	return tp->snd_cwnd - reduction;
+	return max_t(int, tp->snd_cwnd - reduction, 2);
 }
 
 static struct tcp_congestion_ops tcp_yeah __read_mostly = {
-- 
2.1.0


From 4a82e7184457f63a48ee38760eb84133a275595f Mon Sep 17 00:00:00 2001
From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Sun, 10 Jan 2016 11:47:01 -0500
Subject: [PATCH 19/40] sched,cls_flower: set key address type when present

[ Upstream commit 66530bdf85eb1d72a0c399665e09a2c2298501c6 ]

only when user space passes the addresses should we consider their
presence

Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_flower.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 5769294..95b0212 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -252,23 +252,28 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
 	fl_set_key_val(tb, key->eth.src, TCA_FLOWER_KEY_ETH_SRC,
 		       mask->eth.src, TCA_FLOWER_KEY_ETH_SRC_MASK,
 		       sizeof(key->eth.src));
+
 	fl_set_key_val(tb, &key->basic.n_proto, TCA_FLOWER_KEY_ETH_TYPE,
 		       &mask->basic.n_proto, TCA_FLOWER_UNSPEC,
 		       sizeof(key->basic.n_proto));
+
 	if (key->basic.n_proto == htons(ETH_P_IP) ||
 	    key->basic.n_proto == htons(ETH_P_IPV6)) {
 		fl_set_key_val(tb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO,
 			       &mask->basic.ip_proto, TCA_FLOWER_UNSPEC,
 			       sizeof(key->basic.ip_proto));
 	}
-	if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
+
+	if (tb[TCA_FLOWER_KEY_IPV4_SRC] || tb[TCA_FLOWER_KEY_IPV4_DST]) {
+		key->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
 		fl_set_key_val(tb, &key->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC,
 			       &mask->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC_MASK,
 			       sizeof(key->ipv4.src));
 		fl_set_key_val(tb, &key->ipv4.dst, TCA_FLOWER_KEY_IPV4_DST,
 			       &mask->ipv4.dst, TCA_FLOWER_KEY_IPV4_DST_MASK,
 			       sizeof(key->ipv4.dst));
-	} else if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
+	} else if (tb[TCA_FLOWER_KEY_IPV6_SRC] || tb[TCA_FLOWER_KEY_IPV6_DST]) {
+		key->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
 		fl_set_key_val(tb, &key->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC,
 			       &mask->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC_MASK,
 			       sizeof(key->ipv6.src));
@@ -276,6 +281,7 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
 			       &mask->ipv6.dst, TCA_FLOWER_KEY_IPV6_DST_MASK,
 			       sizeof(key->ipv6.dst));
 	}
+
 	if (key->basic.ip_proto == IPPROTO_TCP) {
 		fl_set_key_val(tb, &key->tp.src, TCA_FLOWER_KEY_TCP_SRC,
 			       &mask->tp.src, TCA_FLOWER_UNSPEC,
-- 
2.1.0


From e435b8ab8e45a6a80754763c0faf207ff974a5f0 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Sun, 10 Jan 2016 21:38:44 -0800
Subject: [PATCH 20/40] net: pktgen: fix null ptr deref in skb allocation

[ Upstream commit 3de03596dfeee48bc803c1d1a6daf60a459929f3 ]

Fix possible null pointer dereference that may occur when calling
skb_reserve() on a null skb.

Fixes: 879c7220e82 ("net: pktgen: Observe needed_headroom of the device")
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/pktgen.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index de8d5cc..4da4d51 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -2787,7 +2787,9 @@ static struct sk_buff *pktgen_alloc_skb(struct net_device *dev,
 	} else {
 		 skb = __netdev_alloc_skb(dev, size, GFP_NOWAIT);
 	}
-	skb_reserve(skb, LL_RESERVED_SPACE(dev));
+
+	if (likely(skb))
+		skb_reserve(skb, LL_RESERVED_SPACE(dev));
 
 	return skb;
 }
-- 
2.1.0


From abd3a1448ae9330d22f7fd1883fca6b407f1222a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Michal=20Kube=C4=8Dek?= <mkubecek@suse.cz>
Date: Mon, 11 Jan 2016 07:50:30 +0100
Subject: [PATCH 21/40] udp: disallow UFO for sockets with SO_NO_CHECK option

[ Upstream commit 40ba330227ad00b8c0cdf2f425736ff9549cc423 ]

Commit acf8dd0a9d0b ("udp: only allow UFO for packets from SOCK_DGRAM
sockets") disallows UFO for packets sent from raw sockets. We need to do
the same also for SOCK_DGRAM sockets with SO_NO_CHECK options, even if
for a bit different reason: while such socket would override the
CHECKSUM_PARTIAL set by ip_ufo_append_data(), gso_size is still set and
bad offloading flags warning is triggered in __skb_gso_segment().

In the IPv6 case, SO_NO_CHECK option is ignored but we need to disallow
UFO for packets sent by sockets with UDP_NO_CHECK6_TX option.

Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Tested-by: Shannon Nelson <shannon.nelson@intel.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_output.c  | 2 +-
 net/ipv6/ip6_output.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 0138fad..314f26e 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -918,7 +918,7 @@ static int __ip_append_data(struct sock *sk,
 	if (((length > mtu) || (skb && skb_is_gso(skb))) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
 	    (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len &&
-	    (sk->sk_type == SOCK_DGRAM)) {
+	    (sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx) {
 		err = ip_ufo_append_data(sk, queue, getfrag, from, length,
 					 hh_len, fragheaderlen, transhdrlen,
 					 maxfraglen, flags);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index f84ec4e..fb7973a 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1345,7 +1345,7 @@ emsgsize:
 	     (skb && skb_is_gso(skb))) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
 	    (rt->dst.dev->features & NETIF_F_UFO) &&
-	    (sk->sk_type == SOCK_DGRAM)) {
+	    (sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk)) {
 		err = ip6_ufo_append_data(sk, queue, getfrag, from, length,
 					  hh_len, fragheaderlen,
 					  transhdrlen, mtu, flags, fl6);
-- 
2.1.0


From 85e6b0b5f5d5e9e75051a9e7c6871b53ef09d84d Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <koct9i@gmail.com>
Date: Fri, 8 Jan 2016 15:21:46 +0300
Subject: [PATCH 22/40] net: preserve IP control block during GSO segmentation

[ Upstream commit 9207f9d45b0ad071baa128e846d7e7ed85016df3 ]

Skb_gso_segment() uses skb control block during segmentation.
This patch adds 32-bytes room for previous control block which
will be copied into all resulting segments.

This patch fixes kernel crash during fragmenting forwarded packets.
Fragmentation requires valid IP CB in skb for clearing ip options.
Also patch removes custom save/restore in ovs code, now it's redundant.

Signed-off-by: Konstantin Khlebnikov <koct9i@gmail.com>
Link: http://lkml.kernel.org/r/CALYGNiP-0MZ-FExV2HutTvE9U-QQtkKSoE--KN=JQE5STYsjAA@mail.gmail.com
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h     | 3 ++-
 net/core/dev.c             | 5 +++++
 net/ipv4/ip_output.c       | 1 +
 net/openvswitch/datapath.c | 5 +----
 net/xfrm/xfrm_output.c     | 2 ++
 5 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 4398411..23ce309 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3437,7 +3437,8 @@ struct skb_gso_cb {
 	int	encap_level;
 	__u16	csum_start;
 };
-#define SKB_GSO_CB(skb) ((struct skb_gso_cb *)(skb)->cb)
+#define SKB_SGO_CB_OFFSET	32
+#define SKB_GSO_CB(skb) ((struct skb_gso_cb *)((skb)->cb + SKB_SGO_CB_OFFSET))
 
 static inline int skb_tnl_header_len(const struct sk_buff *inner_skb)
 {
diff --git a/net/core/dev.c b/net/core/dev.c
index c14748d..6369c45 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2539,6 +2539,8 @@ static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path)
  *
  *	It may return NULL if the skb requires no segmentation.  This is
  *	only possible when GSO is used for verifying header integrity.
+ *
+ *	Segmentation preserves SKB_SGO_CB_OFFSET bytes of previous skb cb.
  */
 struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
 				  netdev_features_t features, bool tx_path)
@@ -2553,6 +2555,9 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
 			return ERR_PTR(err);
 	}
 
+	BUILD_BUG_ON(SKB_SGO_CB_OFFSET +
+		     sizeof(*SKB_GSO_CB(skb)) > sizeof(skb->cb));
+
 	SKB_GSO_CB(skb)->mac_offset = skb_headroom(skb);
 	SKB_GSO_CB(skb)->encap_level = 0;
 
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 314f26e..b945f1e 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -240,6 +240,7 @@ static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb,
 	 * from host network stack.
 	 */
 	features = netif_skb_features(skb);
+	BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET);
 	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
 	if (IS_ERR_OR_NULL(segs)) {
 		kfree_skb(skb);
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index c5d08ee..6e9a222 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -337,12 +337,10 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
 	unsigned short gso_type = skb_shinfo(skb)->gso_type;
 	struct sw_flow_key later_key;
 	struct sk_buff *segs, *nskb;
-	struct ovs_skb_cb ovs_cb;
 	int err;
 
-	ovs_cb = *OVS_CB(skb);
+	BUILD_BUG_ON(sizeof(*OVS_CB(skb)) > SKB_SGO_CB_OFFSET);
 	segs = __skb_gso_segment(skb, NETIF_F_SG, false);
-	*OVS_CB(skb) = ovs_cb;
 	if (IS_ERR(segs))
 		return PTR_ERR(segs);
 	if (segs == NULL)
@@ -360,7 +358,6 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
 	/* Queue all of the segments. */
 	skb = segs;
 	do {
-		*OVS_CB(skb) = ovs_cb;
 		if (gso_type & SKB_GSO_UDP && skb != segs)
 			key = &later_key;
 
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 68ada2c..443f78c 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -165,6 +165,8 @@ static int xfrm_output_gso(struct sock *sk, struct sk_buff *skb)
 {
 	struct sk_buff *segs;
 
+	BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET);
+	BUILD_BUG_ON(sizeof(*IP6CB(skb)) > SKB_SGO_CB_OFFSET);
 	segs = skb_gso_segment(skb, 0);
 	kfree_skb(skb);
 	if (IS_ERR(segs))
-- 
2.1.0


From 9b3d913cf20be89f0c38d8318075f0aa7b260d53 Mon Sep 17 00:00:00 2001
From: Karl Heiss <kheiss@gmail.com>
Date: Mon, 11 Jan 2016 08:28:43 -0500
Subject: [PATCH 23/40] bonding: Prevent IPv6 link local address on enslaved
 devices

[ Upstream commit 03d84a5f83a67e692af00a3d3901e7820e3e84d5 ]

Commit 1f718f0f4f97 ("bonding: populate neighbour's private on enslave")
undoes the fix provided by commit c2edacf80e15 ("bonding / ipv6: no addrconf
for slaves separately from master") by effectively setting the slave flag
after the slave has been opened.  If the slave comes up quickly enough, it
will go through the IPv6 addrconf before the slave flag has been set and
will get a link local IPv6 address.

In order to ensure that addrconf knows to ignore the slave devices on state
change, set IFF_SLAVE before dev_open() during bonding enslavement.

Fixes: 1f718f0f4f97 ("bonding: populate neighbour's private on enslave")
Signed-off-by: Karl Heiss <kheiss@gmail.com>
Signed-off-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Reviewed-by: Jarod Wilson <jarod@redhat.com>
Signed-off-by: Andy Gospodarek <gospo@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index bcd7bdd..509440c 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1207,7 +1207,6 @@ static int bond_master_upper_dev_link(struct net_device *bond_dev,
 	err = netdev_master_upper_dev_link_private(slave_dev, bond_dev, slave);
 	if (err)
 		return err;
-	slave_dev->flags |= IFF_SLAVE;
 	rtmsg_ifinfo(RTM_NEWLINK, slave_dev, IFF_SLAVE, GFP_KERNEL);
 	return 0;
 }
@@ -1465,6 +1464,9 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 		}
 	}
 
+	/* set slave flag before open to prevent IPv6 addrconf */
+	slave_dev->flags |= IFF_SLAVE;
+
 	/* open the slave since the application closed it */
 	res = dev_open(slave_dev);
 	if (res) {
@@ -1725,6 +1727,7 @@ err_close:
 	dev_close(slave_dev);
 
 err_restore_mac:
+	slave_dev->flags &= ~IFF_SLAVE;
 	if (!bond->params.fail_over_mac ||
 	    BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
 		/* XXX TODO - fom follow mode needs to change master's
-- 
2.1.0


From d65bd7ec0866c5ceb80991322d011d2d40fea368 Mon Sep 17 00:00:00 2001
From: Lars Persson <lars.persson@axis.com>
Date: Tue, 12 Jan 2016 15:28:13 +0100
Subject: [PATCH 24/40] dwc_eth_qos: Fix dma address for multi-fragment skbs

[ Upstream commit d461873272169a3fc3a8d155d7b1c92e9d97b419 ]

The offset inside the fragment was not used for the dma address and
silent data corruption resulted because TSO makes the checksum match.

Fixes: 077742dac2c7 ("dwc_eth_qos: Add support for Synopsys DWC Ethernet QoS")
Signed-off-by: Lars Persson <larper@axis.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/synopsys/dwc_eth_qos.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/synopsys/dwc_eth_qos.c b/drivers/net/ethernet/synopsys/dwc_eth_qos.c
index 85b3326..37640e1 100644
--- a/drivers/net/ethernet/synopsys/dwc_eth_qos.c
+++ b/drivers/net/ethernet/synopsys/dwc_eth_qos.c
@@ -2107,7 +2107,7 @@ static int dwceqos_tx_frags(struct sk_buff *skb, struct net_local *lp,
 			dd = &lp->tx_descs[lp->tx_next];
 
 			/* Set DMA Descriptor fields */
-			dd->des0 = dma_handle;
+			dd->des0 = dma_handle + consumed_size;
 			dd->des1 = 0;
 			dd->des2 = dma_size;
 
-- 
2.1.0


From 87f125ea6d18de4c11ff76cb1678dfae6e60dd88 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 12 Jan 2016 08:58:00 -0800
Subject: [PATCH 25/40] phonet: properly unshare skbs in phonet_rcv()

[ Upstream commit 7aaed57c5c2890634cfadf725173c7c68ea4cb4f ]

Ivaylo Dimitrov reported a regression caused by commit 7866a621043f
("dev: add per net_device packet type chains").

skb->dev becomes NULL and we crash in __netif_receive_skb_core().

Before above commit, different kind of bugs or corruptions could happen
without major crash.

But the root cause is that phonet_rcv() can queue skb without checking
if skb is shared or not.

Many thanks to Ivaylo Dimitrov for his help, diagnosis and tests.

Reported-by: Ivaylo Dimitrov <ivo.g.dimitrov.75@gmail.com>
Tested-by: Ivaylo Dimitrov <ivo.g.dimitrov.75@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Remi Denis-Courmont <courmisch@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/phonet/af_phonet.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c
index 10d42f3..f925753 100644
--- a/net/phonet/af_phonet.c
+++ b/net/phonet/af_phonet.c
@@ -377,6 +377,10 @@ static int phonet_rcv(struct sk_buff *skb, struct net_device *dev,
 	struct sockaddr_pn sa;
 	u16 len;
 
+	skb = skb_share_check(skb, GFP_ATOMIC);
+	if (!skb)
+		return NET_RX_DROP;
+
 	/* check we have at least a full Phonet header */
 	if (!pskb_pull(skb, sizeof(struct phonethdr)))
 		goto out;
-- 
2.1.0


From bd5d62832b90629e00231acee8e436d467949d4e Mon Sep 17 00:00:00 2001
From: Rabin Vincent <rabin@rab.in>
Date: Tue, 12 Jan 2016 20:17:08 +0100
Subject: [PATCH 26/40] net: bpf: reject invalid shifts

[ Upstream commit 229394e8e62a4191d592842cf67e80c62a492937 ]

On ARM64, a BUG() is triggered in the eBPF JIT if a filter with a
constant shift that can't be encoded in the immediate field of the
UBFM/SBFM instructions is passed to the JIT.  Since these shifts
amounts, which are negative or >= regsize, are invalid, reject them in
the eBPF verifier and the classic BPF filter checker, for all
architectures.

Signed-off-by: Rabin Vincent <rabin@rab.in>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c | 10 ++++++++++
 net/core/filter.c     |  5 +++++
 2 files changed, 15 insertions(+)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index b074b23..36c6efe 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1058,6 +1058,16 @@ static int check_alu_op(struct reg_state *regs, struct bpf_insn *insn)
 			return -EINVAL;
 		}
 
+		if ((opcode == BPF_LSH || opcode == BPF_RSH ||
+		     opcode == BPF_ARSH) && BPF_SRC(insn->code) == BPF_K) {
+			int size = BPF_CLASS(insn->code) == BPF_ALU64 ? 64 : 32;
+
+			if (insn->imm < 0 || insn->imm >= size) {
+				verbose("invalid shift %d\n", insn->imm);
+				return -EINVAL;
+			}
+		}
+
 		/* pattern match 'bpf_add Rx, imm' instruction */
 		if (opcode == BPF_ADD && BPF_CLASS(insn->code) == BPF_ALU64 &&
 		    regs[insn->dst_reg].type == FRAME_PTR &&
diff --git a/net/core/filter.c b/net/core/filter.c
index bb18c36..49b4487 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -781,6 +781,11 @@ static int bpf_check_classic(const struct sock_filter *filter,
 			if (ftest->k == 0)
 				return -EINVAL;
 			break;
+		case BPF_ALU | BPF_LSH | BPF_K:
+		case BPF_ALU | BPF_RSH | BPF_K:
+			if (ftest->k >= 32)
+				return -EINVAL;
+			break;
 		case BPF_LD | BPF_MEM:
 		case BPF_LDX | BPF_MEM:
 		case BPF_ST:
-- 
2.1.0


From a01ae1d4ef72c130d4d5d6e19dc96f38c8b889b5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 15 Jan 2016 04:56:56 -0800
Subject: [PATCH 27/40] ipv6: update skb->csum when CE mark is propagated

[ Upstream commit 34ae6a1aa0540f0f781dd265366036355fdc8930 ]

When a tunnel decapsulates the outer header, it has to comply
with RFC 6080 and eventually propagate CE mark into inner header.

It turns out IP6_ECN_set_ce() does not correctly update skb->csum
for CHECKSUM_COMPLETE packets, triggering infamous "hw csum failure"
messages and stack traces.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_ecn.h       | 19 ++++++++++++++++---
 net/ipv6/xfrm6_mode_tunnel.c |  2 +-
 2 files changed, 17 insertions(+), 4 deletions(-)

diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h
index 84b2083..0dc0a51 100644
--- a/include/net/inet_ecn.h
+++ b/include/net/inet_ecn.h
@@ -111,11 +111,24 @@ static inline void ipv4_copy_dscp(unsigned int dscp, struct iphdr *inner)
 
 struct ipv6hdr;
 
-static inline int IP6_ECN_set_ce(struct ipv6hdr *iph)
+/* Note:
+ * IP_ECN_set_ce() has to tweak IPV4 checksum when setting CE,
+ * meaning both changes have no effect on skb->csum if/when CHECKSUM_COMPLETE
+ * In IPv6 case, no checksum compensates the change in IPv6 header,
+ * so we have to update skb->csum.
+ */
+static inline int IP6_ECN_set_ce(struct sk_buff *skb, struct ipv6hdr *iph)
 {
+	__be32 from, to;
+
 	if (INET_ECN_is_not_ect(ipv6_get_dsfield(iph)))
 		return 0;
-	*(__be32*)iph |= htonl(INET_ECN_CE << 20);
+
+	from = *(__be32 *)iph;
+	to = from | htonl(INET_ECN_CE << 20);
+	*(__be32 *)iph = to;
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		skb->csum = csum_add(csum_sub(skb->csum, from), to);
 	return 1;
 }
 
@@ -142,7 +155,7 @@ static inline int INET_ECN_set_ce(struct sk_buff *skb)
 	case cpu_to_be16(ETH_P_IPV6):
 		if (skb_network_header(skb) + sizeof(struct ipv6hdr) <=
 		    skb_tail_pointer(skb))
-			return IP6_ECN_set_ce(ipv6_hdr(skb));
+			return IP6_ECN_set_ce(skb, ipv6_hdr(skb));
 		break;
 	}
 
diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c
index f7fbdba..372855e 100644
--- a/net/ipv6/xfrm6_mode_tunnel.c
+++ b/net/ipv6/xfrm6_mode_tunnel.c
@@ -23,7 +23,7 @@ static inline void ipip6_ecn_decapsulate(struct sk_buff *skb)
 	struct ipv6hdr *inner_iph = ipipv6_hdr(skb);
 
 	if (INET_ECN_is_ce(XFRM_MODE_SKB_CB(skb)->tos))
-		IP6_ECN_set_ce(inner_iph);
+		IP6_ECN_set_ce(skb, inner_iph);
 }
 
 /* Add encapsulation header.
-- 
2.1.0


From 9ebd79537635078c83c3b781842df69b40e4675e Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Fri, 15 Jan 2016 19:03:54 +0100
Subject: [PATCH 28/40] bridge: fix lockdep addr_list_lock false positive splat

[ Upstream commit c6894dec8ea9ae05747124dce98b3b5c2e69b168 ]

After promisc mode management was introduced a bridge device could do
dev_set_promiscuity from its ndo_change_rx_flags() callback which in
turn can be called after the bridge's addr_list_lock has been taken
(e.g. by dev_uc_add). This causes a false positive lockdep splat because
the port interfaces' addr_list_lock is taken when br_manage_promisc()
runs after the bridge's addr list lock was already taken.
To remove the false positive introduce a custom bridge addr_list_lock
class and set it on bridge init.
A simple way to reproduce this is with the following:
$ brctl addbr br0
$ ip l add l br0 br0.100 type vlan id 100
$ ip l set br0 up
$ ip l set br0.100 up
$ echo 1 > /sys/class/net/br0/bridge/vlan_filtering
$ brctl addif br0 eth0
Splat:
[   43.684325] =============================================
[   43.684485] [ INFO: possible recursive locking detected ]
[   43.684636] 4.4.0-rc8+ #54 Not tainted
[   43.684755] ---------------------------------------------
[   43.684906] brctl/1187 is trying to acquire lock:
[   43.685047]  (_xmit_ETHER){+.....}, at: [<ffffffff8150169e>] dev_set_rx_mode+0x1e/0x40
[   43.685460]  but task is already holding lock:
[   43.685618]  (_xmit_ETHER){+.....}, at: [<ffffffff815072a7>] dev_uc_add+0x27/0x80
[   43.686015]  other info that might help us debug this:
[   43.686316]  Possible unsafe locking scenario:

[   43.686743]        CPU0
[   43.686967]        ----
[   43.687197]   lock(_xmit_ETHER);
[   43.687544]   lock(_xmit_ETHER);
[   43.687886] *** DEADLOCK ***

[   43.688438]  May be due to missing lock nesting notation

[   43.688882] 2 locks held by brctl/1187:
[   43.689134]  #0:  (rtnl_mutex){+.+.+.}, at: [<ffffffff81510317>] rtnl_lock+0x17/0x20
[   43.689852]  #1:  (_xmit_ETHER){+.....}, at: [<ffffffff815072a7>] dev_uc_add+0x27/0x80
[   43.690575] stack backtrace:
[   43.690970] CPU: 0 PID: 1187 Comm: brctl Not tainted 4.4.0-rc8+ #54
[   43.691270] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.8.1-20150318_183358- 04/01/2014
[   43.691770]  ffffffff826a25c0 ffff8800369fb8e0 ffffffff81360ceb ffffffff826a25c0
[   43.692425]  ffff8800369fb9b8 ffffffff810d0466 ffff8800369fb968 ffffffff81537139
[   43.693071]  ffff88003a08c880 0000000000000000 00000000ffffffff 0000000002080020
[   43.693709] Call Trace:
[   43.693931]  [<ffffffff81360ceb>] dump_stack+0x4b/0x70
[   43.694199]  [<ffffffff810d0466>] __lock_acquire+0x1e46/0x1e90
[   43.694483]  [<ffffffff81537139>] ? netlink_broadcast_filtered+0x139/0x3e0
[   43.694789]  [<ffffffff8153b5da>] ? nlmsg_notify+0x5a/0xc0
[   43.695064]  [<ffffffff810d10f5>] lock_acquire+0xe5/0x1f0
[   43.695340]  [<ffffffff8150169e>] ? dev_set_rx_mode+0x1e/0x40
[   43.695623]  [<ffffffff815edea5>] _raw_spin_lock_bh+0x45/0x80
[   43.695901]  [<ffffffff8150169e>] ? dev_set_rx_mode+0x1e/0x40
[   43.696180]  [<ffffffff8150169e>] dev_set_rx_mode+0x1e/0x40
[   43.696460]  [<ffffffff8150189c>] dev_set_promiscuity+0x3c/0x50
[   43.696750]  [<ffffffffa0586845>] br_port_set_promisc+0x25/0x50 [bridge]
[   43.697052]  [<ffffffffa05869aa>] br_manage_promisc+0x8a/0xe0 [bridge]
[   43.697348]  [<ffffffffa05826ee>] br_dev_change_rx_flags+0x1e/0x20 [bridge]
[   43.697655]  [<ffffffff81501532>] __dev_set_promiscuity+0x132/0x1f0
[   43.697943]  [<ffffffff81501672>] __dev_set_rx_mode+0x82/0x90
[   43.698223]  [<ffffffff815072de>] dev_uc_add+0x5e/0x80
[   43.698498]  [<ffffffffa05b3c62>] vlan_device_event+0x542/0x650 [8021q]
[   43.698798]  [<ffffffff8109886d>] notifier_call_chain+0x5d/0x80
[   43.699083]  [<ffffffff810988b6>] raw_notifier_call_chain+0x16/0x20
[   43.699374]  [<ffffffff814f456e>] call_netdevice_notifiers_info+0x6e/0x80
[   43.699678]  [<ffffffff814f4596>] call_netdevice_notifiers+0x16/0x20
[   43.699973]  [<ffffffffa05872be>] br_add_if+0x47e/0x4c0 [bridge]
[   43.700259]  [<ffffffffa058801e>] add_del_if+0x6e/0x80 [bridge]
[   43.700548]  [<ffffffffa0588b5f>] br_dev_ioctl+0xaf/0xc0 [bridge]
[   43.700836]  [<ffffffff8151a7ac>] dev_ifsioc+0x30c/0x3c0
[   43.701106]  [<ffffffff8151aac9>] dev_ioctl+0xf9/0x6f0
[   43.701379]  [<ffffffff81254345>] ? mntput_no_expire+0x5/0x450
[   43.701665]  [<ffffffff812543ee>] ? mntput_no_expire+0xae/0x450
[   43.701947]  [<ffffffff814d7b02>] sock_do_ioctl+0x42/0x50
[   43.702219]  [<ffffffff814d8175>] sock_ioctl+0x1e5/0x290
[   43.702500]  [<ffffffff81242d0b>] do_vfs_ioctl+0x2cb/0x5c0
[   43.702771]  [<ffffffff81243079>] SyS_ioctl+0x79/0x90
[   43.703033]  [<ffffffff815eebb6>] entry_SYSCALL_64_fastpath+0x16/0x7a

CC: Vlad Yasevich <vyasevic@redhat.com>
CC: Stephen Hemminger <stephen@networkplumber.org>
CC: Bridge list <bridge@lists.linux-foundation.org>
CC: Andy Gospodarek <gospo@cumulusnetworks.com>
CC: Roopa Prabhu <roopa@cumulusnetworks.com>
Fixes: 2796d0c648c9 ("bridge: Automatically manage port promiscuous mode.")
Reported-by: Andy Gospodarek <gospo@cumulusnetworks.com>
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_device.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 6ed2feb..9780603 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -28,6 +28,8 @@
 const struct nf_br_ops __rcu *nf_br_ops __read_mostly;
 EXPORT_SYMBOL_GPL(nf_br_ops);
 
+static struct lock_class_key bridge_netdev_addr_lock_key;
+
 /* net device transmit always called with BH disabled */
 netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 {
@@ -87,6 +89,11 @@ out:
 	return NETDEV_TX_OK;
 }
 
+static void br_set_lockdep_class(struct net_device *dev)
+{
+	lockdep_set_class(&dev->addr_list_lock, &bridge_netdev_addr_lock_key);
+}
+
 static int br_dev_init(struct net_device *dev)
 {
 	struct net_bridge *br = netdev_priv(dev);
@@ -99,6 +106,7 @@ static int br_dev_init(struct net_device *dev)
 	err = br_vlan_init(br);
 	if (err)
 		free_percpu(br->stats);
+	br_set_lockdep_class(dev);
 
 	return err;
 }
-- 
2.1.0


From 3985280b860b74c82dad84a018cff5f945c51ae9 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben@decadent.org.uk>
Date: Sun, 1 Nov 2015 16:21:24 +0000
Subject: [PATCH 29/40] isdn_ppp: Add checks for allocation failure in
 isdn_ppp_open()

[ Upstream commit 0baa57d8dc32db78369d8b5176ef56c5e2e18ab3 ]

Compile-tested only.

Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/i4l/isdn_ppp.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/isdn/i4l/isdn_ppp.c b/drivers/isdn/i4l/isdn_ppp.c
index c4198fa..86f9abe 100644
--- a/drivers/isdn/i4l/isdn_ppp.c
+++ b/drivers/isdn/i4l/isdn_ppp.c
@@ -301,6 +301,8 @@ isdn_ppp_open(int min, struct file *file)
 	is->compflags = 0;
 
 	is->reset = isdn_ppp_ccp_reset_alloc(is);
+	if (!is->reset)
+		return -ENOMEM;
 
 	is->lp = NULL;
 	is->mp_seqno = 0;       /* MP sequence number */
@@ -320,6 +322,10 @@ isdn_ppp_open(int min, struct file *file)
 	 * VJ header compression init
 	 */
 	is->slcomp = slhc_init(16, 16);	/* not necessary for 2. link in bundle */
+	if (!is->slcomp) {
+		isdn_ppp_ccp_reset_free(is);
+		return -ENOMEM;
+	}
 #endif
 #ifdef CONFIG_IPPP_FILTER
 	is->pass_filter = NULL;
-- 
2.1.0


From 1be145750f85302530e0b6504eff623dc9d93a35 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben@decadent.org.uk>
Date: Sun, 1 Nov 2015 16:22:53 +0000
Subject: [PATCH 30/40] ppp, slip: Validate VJ compression slot parameters
 completely
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 4ab42d78e37a294ac7bc56901d563c642e03c4ae ]

Currently slhc_init() treats out-of-range values of rslots and tslots
as equivalent to 0, except that if tslots is too large it will
dereference a null pointer (CVE-2015-7799).

Add a range-check at the top of the function and make it return an
ERR_PTR() on error instead of NULL.  Change the callers accordingly.

Compile-tested only.

Reported-by: 郭永刚 <guoyonggang@360.cn>
References: http://article.gmane.org/gmane.comp.security.oss.general/17908
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/i4l/isdn_ppp.c   | 10 ++++------
 drivers/net/ppp/ppp_generic.c |  6 ++----
 drivers/net/slip/slhc.c       | 12 ++++++++----
 drivers/net/slip/slip.c       |  2 +-
 4 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/drivers/isdn/i4l/isdn_ppp.c b/drivers/isdn/i4l/isdn_ppp.c
index 86f9abe..9c1e8ad 100644
--- a/drivers/isdn/i4l/isdn_ppp.c
+++ b/drivers/isdn/i4l/isdn_ppp.c
@@ -322,9 +322,9 @@ isdn_ppp_open(int min, struct file *file)
 	 * VJ header compression init
 	 */
 	is->slcomp = slhc_init(16, 16);	/* not necessary for 2. link in bundle */
-	if (!is->slcomp) {
+	if (IS_ERR(is->slcomp)) {
 		isdn_ppp_ccp_reset_free(is);
-		return -ENOMEM;
+		return PTR_ERR(is->slcomp);
 	}
 #endif
 #ifdef CONFIG_IPPP_FILTER
@@ -573,10 +573,8 @@ isdn_ppp_ioctl(int min, struct file *file, unsigned int cmd, unsigned long arg)
 			is->maxcid = val;
 #ifdef CONFIG_ISDN_PPP_VJ
 			sltmp = slhc_init(16, val);
-			if (!sltmp) {
-				printk(KERN_ERR "ippp, can't realloc slhc struct\n");
-				return -ENOMEM;
-			}
+			if (IS_ERR(sltmp))
+				return PTR_ERR(sltmp);
 			if (is->slcomp)
 				slhc_free(is->slcomp);
 			is->slcomp = sltmp;
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index ed00446..9a863c6 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -721,10 +721,8 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 			val &= 0xffff;
 		}
 		vj = slhc_init(val2+1, val+1);
-		if (!vj) {
-			netdev_err(ppp->dev,
-				   "PPP: no memory (VJ compressor)\n");
-			err = -ENOMEM;
+		if (IS_ERR(vj)) {
+			err = PTR_ERR(vj);
 			break;
 		}
 		ppp_lock(ppp);
diff --git a/drivers/net/slip/slhc.c b/drivers/net/slip/slhc.c
index 079f7ad..27ed252 100644
--- a/drivers/net/slip/slhc.c
+++ b/drivers/net/slip/slhc.c
@@ -84,8 +84,9 @@ static long decode(unsigned char **cpp);
 static unsigned char * put16(unsigned char *cp, unsigned short x);
 static unsigned short pull16(unsigned char **cpp);
 
-/* Initialize compression data structure
+/* Allocate compression data structure
  *	slots must be in range 0 to 255 (zero meaning no compression)
+ * Returns pointer to structure or ERR_PTR() on error.
  */
 struct slcompress *
 slhc_init(int rslots, int tslots)
@@ -94,11 +95,14 @@ slhc_init(int rslots, int tslots)
 	register struct cstate *ts;
 	struct slcompress *comp;
 
+	if (rslots < 0 || rslots > 255 || tslots < 0 || tslots > 255)
+		return ERR_PTR(-EINVAL);
+
 	comp = kzalloc(sizeof(struct slcompress), GFP_KERNEL);
 	if (! comp)
 		goto out_fail;
 
-	if ( rslots > 0  &&  rslots < 256 ) {
+	if (rslots > 0) {
 		size_t rsize = rslots * sizeof(struct cstate);
 		comp->rstate = kzalloc(rsize, GFP_KERNEL);
 		if (! comp->rstate)
@@ -106,7 +110,7 @@ slhc_init(int rslots, int tslots)
 		comp->rslot_limit = rslots - 1;
 	}
 
-	if ( tslots > 0  &&  tslots < 256 ) {
+	if (tslots > 0) {
 		size_t tsize = tslots * sizeof(struct cstate);
 		comp->tstate = kzalloc(tsize, GFP_KERNEL);
 		if (! comp->tstate)
@@ -141,7 +145,7 @@ out_free2:
 out_free:
 	kfree(comp);
 out_fail:
-	return NULL;
+	return ERR_PTR(-ENOMEM);
 }
 
 
diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c
index 05387b1..a17d86a 100644
--- a/drivers/net/slip/slip.c
+++ b/drivers/net/slip/slip.c
@@ -164,7 +164,7 @@ static int sl_alloc_bufs(struct slip *sl, int mtu)
 	if (cbuff == NULL)
 		goto err_exit;
 	slcomp = slhc_init(16, 16);
-	if (slcomp == NULL)
+	if (IS_ERR(slcomp))
 		goto err_exit;
 #endif
 	spin_lock_bh(&sl->lock);
-- 
2.1.0


From 29e1664018cb9bd294067b7296d8afa9f9039ab9 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Thu, 14 Jan 2016 15:28:19 +0100
Subject: [PATCH 31/40] batman-adv: Avoid recursive call_rcu for
 batadv_bla_claim

[ Upstream commit 63b399272294e7a939cde41792dca38c549f0484 ]

The batadv_claim_free_ref function uses call_rcu to delay the free of the
batadv_bla_claim object until no (already started) rcu_read_lock is enabled
anymore. This makes sure that no context is still trying to access the
object which should be removed. But batadv_bla_claim also contains a
reference to backbone_gw which must be removed.

The reference drop of backbone_gw was done in the call_rcu function
batadv_claim_free_rcu but should actually be done in the
batadv_claim_release function to avoid nested call_rcus. This is important
because rcu_barrier (e.g. batadv_softif_free or batadv_exit) will not
detect the inner call_rcu as relevant for its execution. Otherwise this
barrier will most likely be inserted in the queue before the callback of
the first call_rcu was executed. The caller of rcu_barrier will therefore
continue to run before the inner call_rcu callback finished.

Fixes: 23721387c409 ("batman-adv: add basic bridge loop avoidance code")
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Acked-by: Simon Wunderlich <sw@simonwunderlich.de>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>
Signed-off-by: Antonio Quartulli <a@unstable.cc>
---
 net/batman-adv/bridge_loop_avoidance.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c
index 191a702..f5d2fe5 100644
--- a/net/batman-adv/bridge_loop_avoidance.c
+++ b/net/batman-adv/bridge_loop_avoidance.c
@@ -127,21 +127,17 @@ batadv_backbone_gw_free_ref(struct batadv_bla_backbone_gw *backbone_gw)
 }
 
 /* finally deinitialize the claim */
-static void batadv_claim_free_rcu(struct rcu_head *rcu)
+static void batadv_claim_release(struct batadv_bla_claim *claim)
 {
-	struct batadv_bla_claim *claim;
-
-	claim = container_of(rcu, struct batadv_bla_claim, rcu);
-
 	batadv_backbone_gw_free_ref(claim->backbone_gw);
-	kfree(claim);
+	kfree_rcu(claim, rcu);
 }
 
 /* free a claim, call claim_free_rcu if its the last reference */
 static void batadv_claim_free_ref(struct batadv_bla_claim *claim)
 {
 	if (atomic_dec_and_test(&claim->refcount))
-		call_rcu(&claim->rcu, batadv_claim_free_rcu);
+		batadv_claim_release(claim);
 }
 
 /**
-- 
2.1.0


From 29acc573810146d0995c56f7823191be4f08d625 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Tue, 5 Jan 2016 12:06:19 +0100
Subject: [PATCH 32/40] batman-adv: Avoid recursive call_rcu for batadv_nc_node

[ Upstream commit 44e8e7e91d6c7c7ab19688750f7257292640d1a0 ]

The batadv_nc_node_free_ref function uses call_rcu to delay the free of the
batadv_nc_node object until no (already started) rcu_read_lock is enabled
anymore. This makes sure that no context is still trying to access the
object which should be removed. But batadv_nc_node also contains a
reference to orig_node which must be removed.

The reference drop of orig_node was done in the call_rcu function
batadv_nc_node_free_rcu but should actually be done in the
batadv_nc_node_release function to avoid nested call_rcus. This is
important because rcu_barrier (e.g. batadv_softif_free or batadv_exit) will
not detect the inner call_rcu as relevant for its execution. Otherwise this
barrier will most likely be inserted in the queue before the callback of
the first call_rcu was executed. The caller of rcu_barrier will therefore
continue to run before the inner call_rcu callback finished.

Fixes: d56b1705e28c ("batman-adv: network coding - detect coding nodes and remove these after timeout")
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>
Signed-off-by: Antonio Quartulli <a@unstable.cc>
---
 net/batman-adv/network-coding.c | 19 ++++++++-----------
 1 file changed, 8 insertions(+), 11 deletions(-)

diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c
index f5276be..d0956f7 100644
--- a/net/batman-adv/network-coding.c
+++ b/net/batman-adv/network-coding.c
@@ -203,28 +203,25 @@ void batadv_nc_init_orig(struct batadv_orig_node *orig_node)
 }
 
 /**
- * batadv_nc_node_free_rcu - rcu callback to free an nc node and remove
- *  its refcount on the orig_node
- * @rcu: rcu pointer of the nc node
+ * batadv_nc_node_release - release nc_node from lists and queue for free after
+ *  rcu grace period
+ * @nc_node: the nc node to free
  */
-static void batadv_nc_node_free_rcu(struct rcu_head *rcu)
+static void batadv_nc_node_release(struct batadv_nc_node *nc_node)
 {
-	struct batadv_nc_node *nc_node;
-
-	nc_node = container_of(rcu, struct batadv_nc_node, rcu);
 	batadv_orig_node_free_ref(nc_node->orig_node);
-	kfree(nc_node);
+	kfree_rcu(nc_node, rcu);
 }
 
 /**
- * batadv_nc_node_free_ref - decrements the nc node refcounter and possibly
- * frees it
+ * batadv_nc_node_free_ref - decrement the nc node refcounter and possibly
+ *  release it
  * @nc_node: the nc node to free
  */
 static void batadv_nc_node_free_ref(struct batadv_nc_node *nc_node)
 {
 	if (atomic_dec_and_test(&nc_node->refcount))
-		call_rcu(&nc_node->rcu, batadv_nc_node_free_rcu);
+		batadv_nc_node_release(nc_node);
 }
 
 /**
-- 
2.1.0


From 7161d429e9deb0e8d5c5507cd74b21c9a08ad245 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Tue, 5 Jan 2016 12:06:21 +0100
Subject: [PATCH 33/40] batman-adv: Drop immediate batadv_orig_ifinfo free
 function

[ Upstream commit deed96605f5695cb945e0b3d79429581857a2b9d ]

It is not allowed to free the memory of an object which is part of a list
which is protected by rcu-read-side-critical sections without making sure
that no other context is accessing the object anymore. This usually happens
by removing the references to this object and then waiting until the rcu
grace period is over and no one (allowedly) accesses it anymore.

But the _now functions ignore this completely. They free the object
directly even when a different context still tries to access it. This has
to be avoided and thus these functions must be removed and all functions
have to use batadv_orig_ifinfo_free_ref.

Fixes: 7351a4822d42 ("batman-adv: split out router from orig_node")
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>
Signed-off-by: Antonio Quartulli <a@unstable.cc>
---
 net/batman-adv/originator.c | 59 ++++++++++++++++++++++++---------------------
 1 file changed, 31 insertions(+), 28 deletions(-)

diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index 7486df9..a072894 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -553,76 +553,79 @@ static void batadv_orig_ifinfo_free_rcu(struct rcu_head *rcu)
 }
 
 /**
- * batadv_orig_ifinfo_free_ref - decrement the refcounter and possibly free
- *  the orig_ifinfo (without rcu callback)
+ * batadv_orig_ifinfo_free_ref - decrement the refcounter and possibly release
+ *  the orig_ifinfo
  * @orig_ifinfo: the orig_ifinfo object to release
  */
-static void
-batadv_orig_ifinfo_free_ref_now(struct batadv_orig_ifinfo *orig_ifinfo)
+void batadv_orig_ifinfo_free_ref(struct batadv_orig_ifinfo *orig_ifinfo)
 {
 	if (atomic_dec_and_test(&orig_ifinfo->refcount))
-		batadv_orig_ifinfo_free_rcu(&orig_ifinfo->rcu);
+		call_rcu(&orig_ifinfo->rcu, batadv_orig_ifinfo_free_rcu);
 }
 
 /**
- * batadv_orig_ifinfo_free_ref - decrement the refcounter and possibly free
- *  the orig_ifinfo
- * @orig_ifinfo: the orig_ifinfo object to release
+ * batadv_orig_node_free_rcu - free the orig_node
+ * @rcu: rcu pointer of the orig_node
  */
-void batadv_orig_ifinfo_free_ref(struct batadv_orig_ifinfo *orig_ifinfo)
+static void batadv_orig_node_free_rcu(struct rcu_head *rcu)
 {
-	if (atomic_dec_and_test(&orig_ifinfo->refcount))
-		call_rcu(&orig_ifinfo->rcu, batadv_orig_ifinfo_free_rcu);
+	struct batadv_orig_node *orig_node;
+
+	orig_node = container_of(rcu, struct batadv_orig_node, rcu);
+
+	batadv_mcast_purge_orig(orig_node);
+
+	batadv_frag_purge_orig(orig_node, NULL);
+
+	if (orig_node->bat_priv->bat_algo_ops->bat_orig_free)
+		orig_node->bat_priv->bat_algo_ops->bat_orig_free(orig_node);
+
+	kfree(orig_node->tt_buff);
+	kfree(orig_node);
 }
 
-static void batadv_orig_node_free_rcu(struct rcu_head *rcu)
+/**
+ * batadv_orig_node_release - release orig_node from lists and queue for
+ *  free after rcu grace period
+ * @orig_node: the orig node to free
+ */
+static void batadv_orig_node_release(struct batadv_orig_node *orig_node)
 {
 	struct hlist_node *node_tmp;
 	struct batadv_neigh_node *neigh_node;
-	struct batadv_orig_node *orig_node;
 	struct batadv_orig_ifinfo *orig_ifinfo;
 
-	orig_node = container_of(rcu, struct batadv_orig_node, rcu);
-
 	spin_lock_bh(&orig_node->neigh_list_lock);
 
 	/* for all neighbors towards this originator ... */
 	hlist_for_each_entry_safe(neigh_node, node_tmp,
 				  &orig_node->neigh_list, list) {
 		hlist_del_rcu(&neigh_node->list);
-		batadv_neigh_node_free_ref_now(neigh_node);
+		batadv_neigh_node_free_ref(neigh_node);
 	}
 
 	hlist_for_each_entry_safe(orig_ifinfo, node_tmp,
 				  &orig_node->ifinfo_list, list) {
 		hlist_del_rcu(&orig_ifinfo->list);
-		batadv_orig_ifinfo_free_ref_now(orig_ifinfo);
+		batadv_orig_ifinfo_free_ref(orig_ifinfo);
 	}
 	spin_unlock_bh(&orig_node->neigh_list_lock);
 
-	batadv_mcast_purge_orig(orig_node);
-
 	/* Free nc_nodes */
 	batadv_nc_purge_orig(orig_node->bat_priv, orig_node, NULL);
 
-	batadv_frag_purge_orig(orig_node, NULL);
-
-	if (orig_node->bat_priv->bat_algo_ops->bat_orig_free)
-		orig_node->bat_priv->bat_algo_ops->bat_orig_free(orig_node);
-
-	kfree(orig_node->tt_buff);
-	kfree(orig_node);
+	call_rcu(&orig_node->rcu, batadv_orig_node_free_rcu);
 }
 
 /**
  * batadv_orig_node_free_ref - decrement the orig node refcounter and possibly
- * schedule an rcu callback for freeing it
+ *  release it
  * @orig_node: the orig node to free
  */
 void batadv_orig_node_free_ref(struct batadv_orig_node *orig_node)
 {
 	if (atomic_dec_and_test(&orig_node->refcount))
-		call_rcu(&orig_node->rcu, batadv_orig_node_free_rcu);
+		batadv_orig_node_release(orig_node);
 }
 
 /**
-- 
2.1.0


From 4343b3c0f6804f2192d20e22f923e46ad01ddb66 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Tue, 5 Jan 2016 12:06:22 +0100
Subject: [PATCH 34/40] batman-adv: Drop immediate batadv_neigh_node free
 function

[ Upstream commit 2baa753c276f27f8e844637561ad597867aa6fb6 ]

It is not allowed to free the memory of an object which is part of a list
which is protected by rcu-read-side-critical sections without making sure
that no other context is accessing the object anymore. This usually happens
by removing the references to this object and then waiting until the rcu
grace period is over and no one (allowedly) accesses it anymore.

But the _now functions ignore this completely. They free the object
directly even when a different context still tries to access it. This has
to be avoided and thus these functions must be removed and all functions
have to use batadv_neigh_node_free_ref.

Fixes: 89652331c00f ("batman-adv: split tq information in neigh_node struct")
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>
Signed-off-by: Antonio Quartulli <a@unstable.cc>
---
 net/batman-adv/originator.c | 33 ++++++++++-----------------------
 1 file changed, 10 insertions(+), 23 deletions(-)

diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index a072894..a8e68eb 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -229,20 +229,8 @@ static void batadv_neigh_node_free_rcu(struct rcu_head *rcu)
 }
 
 /**
- * batadv_neigh_node_free_ref_now - decrement the neighbors refcounter
- *  and possibly free it (without rcu callback)
- * @neigh_node: neigh neighbor to free
- */
-static void
-batadv_neigh_node_free_ref_now(struct batadv_neigh_node *neigh_node)
-{
-	if (atomic_dec_and_test(&neigh_node->refcount))
-		batadv_neigh_node_free_rcu(&neigh_node->rcu);
-}
-
-/**
  * batadv_neigh_node_free_ref - decrement the neighbors refcounter
- *  and possibly free it
+ *  and possibly release it
  * @neigh_node: neigh neighbor to free
  */
 void batadv_neigh_node_free_ref(struct batadv_neigh_node *neigh_node)
@@ -532,24 +520,23 @@ out:
 }
 
 /**
- * batadv_orig_ifinfo_free_rcu - free the orig_ifinfo object
- * @rcu: rcu pointer of the orig_ifinfo object
+ * batadv_orig_ifinfo_release - release orig_ifinfo from lists and queue for
+ *  free after rcu grace period
+ * @orig_ifinfo: the orig_ifinfo object to release
  */
-static void batadv_orig_ifinfo_free_rcu(struct rcu_head *rcu)
+static void batadv_orig_ifinfo_release(struct batadv_orig_ifinfo *orig_ifinfo)
 {
-	struct batadv_orig_ifinfo *orig_ifinfo;
 	struct batadv_neigh_node *router;
 
-	orig_ifinfo = container_of(rcu, struct batadv_orig_ifinfo, rcu);
-
 	if (orig_ifinfo->if_outgoing != BATADV_IF_DEFAULT)
-		batadv_hardif_free_ref_now(orig_ifinfo->if_outgoing);
+		batadv_hardif_free_ref(orig_ifinfo->if_outgoing);
 
 	/* this is the last reference to this object */
 	router = rcu_dereference_protected(orig_ifinfo->router, true);
 	if (router)
-		batadv_neigh_node_free_ref_now(router);
-	kfree(orig_ifinfo);
+		batadv_neigh_node_free_ref(router);
+
+	kfree_rcu(orig_ifinfo, rcu);
 }
 
 /**
@@ -560,7 +547,7 @@ static void batadv_orig_ifinfo_free_rcu(struct rcu_head *rcu)
 void batadv_orig_ifinfo_free_ref(struct batadv_orig_ifinfo *orig_ifinfo)
 {
 	if (atomic_dec_and_test(&orig_ifinfo->refcount))
-		call_rcu(&orig_ifinfo->rcu, batadv_orig_ifinfo_free_rcu);
+		batadv_orig_ifinfo_release(orig_ifinfo);
 }
 
 /**
-- 
2.1.0


From 85e73fc9b13f34d5457234d8e541258d1e8299ff Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Tue, 5 Jan 2016 12:06:24 +0100
Subject: [PATCH 35/40] batman-adv: Drop immediate neigh_ifinfo free function

[ Upstream commit ae3e1e36e3cb6c686a7a2725af20ca86aa46d62a ]

It is not allowed to free the memory of an object which is part of a list
which is protected by rcu-read-side-critical sections without making sure
that no other context is accessing the object anymore. This usually happens
by removing the references to this object and then waiting until the rcu
grace period is over and no one (allowedly) accesses it anymore.

But the _now functions ignore this completely. They free the object
directly even when a different context still tries to access it. This has
to be avoided and thus these functions must be removed and all functions
have to use batadv_neigh_ifinfo_free_ref.

Fixes: 89652331c00f ("batman-adv: split tq information in neigh_node struct")
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>
Signed-off-by: Antonio Quartulli <a@unstable.cc>
---
 net/batman-adv/originator.c | 34 ++++++++++------------------------
 1 file changed, 10 insertions(+), 24 deletions(-)

diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index a8e68eb..0c27f07 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -163,42 +163,28 @@ err:
 }
 
 /**
- * batadv_neigh_ifinfo_free_rcu - free the neigh_ifinfo object
- * @rcu: rcu pointer of the neigh_ifinfo object
- */
-static void batadv_neigh_ifinfo_free_rcu(struct rcu_head *rcu)
-{
-	struct batadv_neigh_ifinfo *neigh_ifinfo;
-
-	neigh_ifinfo = container_of(rcu, struct batadv_neigh_ifinfo, rcu);
-
-	if (neigh_ifinfo->if_outgoing != BATADV_IF_DEFAULT)
-		batadv_hardif_free_ref_now(neigh_ifinfo->if_outgoing);
-
-	kfree(neigh_ifinfo);
-}
-
-/**
- * batadv_neigh_ifinfo_free_now - decrement the refcounter and possibly free
- *  the neigh_ifinfo (without rcu callback)
+ * batadv_neigh_ifinfo_release - release neigh_ifinfo from lists and queue for
+ *  free after rcu grace period
  * @neigh_ifinfo: the neigh_ifinfo object to release
  */
 static void
-batadv_neigh_ifinfo_free_ref_now(struct batadv_neigh_ifinfo *neigh_ifinfo)
+batadv_neigh_ifinfo_release(struct batadv_neigh_ifinfo *neigh_ifinfo)
 {
-	if (atomic_dec_and_test(&neigh_ifinfo->refcount))
-		batadv_neigh_ifinfo_free_rcu(&neigh_ifinfo->rcu);
+	if (neigh_ifinfo->if_outgoing != BATADV_IF_DEFAULT)
+		batadv_hardif_free_ref(neigh_ifinfo->if_outgoing);
+
+	kfree_rcu(neigh_ifinfo, rcu);
 }
 
 /**
- * batadv_neigh_ifinfo_free_ref - decrement the refcounter and possibly free
+ * batadv_neigh_ifinfo_free_ref - decrement the refcounter and possibly release
  *  the neigh_ifinfo
  * @neigh_ifinfo: the neigh_ifinfo object to release
  */
 void batadv_neigh_ifinfo_free_ref(struct batadv_neigh_ifinfo *neigh_ifinfo)
 {
 	if (atomic_dec_and_test(&neigh_ifinfo->refcount))
-		call_rcu(&neigh_ifinfo->rcu, batadv_neigh_ifinfo_free_rcu);
+		batadv_neigh_ifinfo_release(neigh_ifinfo);
 }
 
 /**
@@ -217,7 +203,7 @@ static void batadv_neigh_node_free_rcu(struct rcu_head *rcu)
 
 	hlist_for_each_entry_safe(neigh_ifinfo, node_tmp,
 				  &neigh_node->ifinfo_list, list) {
-		batadv_neigh_ifinfo_free_ref_now(neigh_ifinfo);
+		batadv_neigh_ifinfo_free_ref(neigh_ifinfo);
 	}
 
 	if (bao->bat_neigh_free)
-- 
2.1.0


From 94b6a83a0339007eb425a9a075e45521256e321a Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Tue, 5 Jan 2016 12:06:25 +0100
Subject: [PATCH 36/40] batman-adv: Drop immediate batadv_hard_iface free
 function

[ Upstream commit b4d922cfc9c08318eeb77d53b7633740e6b0efb0 ]

It is not allowed to free the memory of an object which is part of a list
which is protected by rcu-read-side-critical sections without making sure
that no other context is accessing the object anymore. This usually happens
by removing the references to this object and then waiting until the rcu
grace period is over and no one (allowedly) accesses it anymore.

But the _now functions ignore this completely. They free the object
directly even when a different context still tries to access it. This has
to be avoided and thus these functions must be removed and all functions
have to use batadv_hardif_free_ref.

Fixes: 89652331c00f ("batman-adv: split tq information in neigh_node struct")
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>
Signed-off-by: Antonio Quartulli <a@unstable.cc>
---
 net/batman-adv/hard-interface.h | 12 ------------
 net/batman-adv/originator.c     | 14 +++++++-------
 2 files changed, 7 insertions(+), 19 deletions(-)

diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h
index 5a31420..7b12ea8 100644
--- a/net/batman-adv/hard-interface.h
+++ b/net/batman-adv/hard-interface.h
@@ -75,18 +75,6 @@ batadv_hardif_free_ref(struct batadv_hard_iface *hard_iface)
 		call_rcu(&hard_iface->rcu, batadv_hardif_free_rcu);
 }
 
-/**
- * batadv_hardif_free_ref_now - decrement the hard interface refcounter and
- *  possibly free it (without rcu callback)
- * @hard_iface: the hard interface to free
- */
-static inline void
-batadv_hardif_free_ref_now(struct batadv_hard_iface *hard_iface)
-{
-	if (atomic_dec_and_test(&hard_iface->refcount))
-		batadv_hardif_free_rcu(&hard_iface->rcu);
-}
-
 static inline struct batadv_hard_iface *
 batadv_primary_if_get_selected(struct batadv_priv *bat_priv)
 {
diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index 0c27f07..d9d2cee 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -189,16 +189,16 @@ void batadv_neigh_ifinfo_free_ref(struct batadv_neigh_ifinfo *neigh_ifinfo)
 
 /**
  * batadv_neigh_node_free_rcu - free the neigh_node
- * @rcu: rcu pointer of the neigh_node
+ * batadv_neigh_node_release - release neigh_node from lists and queue for
+ *  free after rcu grace period
+ * @neigh_node: neigh neighbor to free
  */
-static void batadv_neigh_node_free_rcu(struct rcu_head *rcu)
+static void batadv_neigh_node_release(struct batadv_neigh_node *neigh_node)
 {
 	struct hlist_node *node_tmp;
-	struct batadv_neigh_node *neigh_node;
 	struct batadv_neigh_ifinfo *neigh_ifinfo;
 	struct batadv_algo_ops *bao;
 
-	neigh_node = container_of(rcu, struct batadv_neigh_node, rcu);
 	bao = neigh_node->orig_node->bat_priv->bat_algo_ops;
 
 	hlist_for_each_entry_safe(neigh_ifinfo, node_tmp,
@@ -209,9 +209,9 @@ static void batadv_neigh_node_free_rcu(struct rcu_head *rcu)
 	if (bao->bat_neigh_free)
 		bao->bat_neigh_free(neigh_node);
 
-	batadv_hardif_free_ref_now(neigh_node->if_incoming);
+	batadv_hardif_free_ref(neigh_node->if_incoming);
 
-	kfree(neigh_node);
+	kfree_rcu(neigh_node, rcu);
 }
 
 /**
@@ -222,7 +222,7 @@ static void batadv_neigh_node_free_rcu(struct rcu_head *rcu)
 void batadv_neigh_node_free_ref(struct batadv_neigh_node *neigh_node)
 {
 	if (atomic_dec_and_test(&neigh_node->refcount))
-		call_rcu(&neigh_node->rcu, batadv_neigh_node_free_rcu);
+		batadv_neigh_node_release(neigh_node);
 }
 
 /**
-- 
2.1.0


From 3ff976eec8860c138ce61225ac0cd02ac1b8cd4a Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Tue, 5 Jan 2016 12:06:20 +0100
Subject: [PATCH 37/40] batman-adv: Drop immediate orig_node free function

[ Upstream commit 42eff6a617e23b691f8e4467f4687ed7245a92db ]

It is not allowed to free the memory of an object which is part of a list
which is protected by rcu-read-side-critical sections without making sure
that no other context is accessing the object anymore. This usually happens
by removing the references to this object and then waiting until the rcu
grace period is over and no one (allowedly) accesses it anymore.

But the _now functions ignore this completely. They free the object
directly even when a different context still tries to access it. This has
to be avoided and thus these functions must be removed and all functions
have to use batadv_orig_node_free_ref.

Fixes: 72822225bd41 ("batman-adv: Fix rcu_barrier() miss due to double call_rcu() in TT code")
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>
Signed-off-by: Antonio Quartulli <a@unstable.cc>
---
 net/batman-adv/originator.c        | 11 -----------
 net/batman-adv/originator.h        |  1 -
 net/batman-adv/translation-table.c | 28 +++++++++++++---------------
 3 files changed, 13 insertions(+), 27 deletions(-)

diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index d9d2cee..17851d3 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -601,17 +601,6 @@ void batadv_orig_node_free_ref(struct batadv_orig_node *orig_node)
 		batadv_orig_node_release(orig_node);
 }
 
-/**
- * batadv_orig_node_free_ref_now - decrement the orig node refcounter and
- * possibly free it (without rcu callback)
- * @orig_node: the orig node to free
- */
-void batadv_orig_node_free_ref_now(struct batadv_orig_node *orig_node)
-{
-	if (atomic_dec_and_test(&orig_node->refcount))
-		batadv_orig_node_free_rcu(&orig_node->rcu);
-}
-
 void batadv_originator_free(struct batadv_priv *bat_priv)
 {
 	struct batadv_hashtable *hash = bat_priv->orig_hash;
diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h
index fa18f9b..a5c3788 100644
--- a/net/batman-adv/originator.h
+++ b/net/batman-adv/originator.h
@@ -38,7 +38,6 @@ int batadv_originator_init(struct batadv_priv *bat_priv);
 void batadv_originator_free(struct batadv_priv *bat_priv);
 void batadv_purge_orig_ref(struct batadv_priv *bat_priv);
 void batadv_orig_node_free_ref(struct batadv_orig_node *orig_node);
-void batadv_orig_node_free_ref_now(struct batadv_orig_node *orig_node);
 struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv,
 					      const u8 *addr);
 struct batadv_neigh_node *
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index 4228b10..900e94b 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -238,20 +238,6 @@ int batadv_tt_global_hash_count(struct batadv_priv *bat_priv,
 	return count;
 }
 
-static void batadv_tt_orig_list_entry_free_rcu(struct rcu_head *rcu)
-{
-	struct batadv_tt_orig_list_entry *orig_entry;
-
-	orig_entry = container_of(rcu, struct batadv_tt_orig_list_entry, rcu);
-
-	/* We are in an rcu callback here, therefore we cannot use
-	 * batadv_orig_node_free_ref() and its call_rcu():
-	 * An rcu_barrier() wouldn't wait for that to finish
-	 */
-	batadv_orig_node_free_ref_now(orig_entry->orig_node);
-	kfree(orig_entry);
-}
-
 /**
  * batadv_tt_local_size_mod - change the size by v of the local table identified
  *  by vid
@@ -347,13 +333,25 @@ static void batadv_tt_global_size_dec(struct batadv_orig_node *orig_node,
 	batadv_tt_global_size_mod(orig_node, vid, -1);
 }
 
+/**
+ * batadv_tt_orig_list_entry_release - release tt orig entry from lists and
+ *  queue for free after rcu grace period
+ * @orig_entry: tt orig entry to be free'd
+ */
+static void
+batadv_tt_orig_list_entry_release(struct batadv_tt_orig_list_entry *orig_entry)
+{
+	batadv_orig_node_free_ref(orig_entry->orig_node);
+	kfree_rcu(orig_entry, rcu);
+}
+
 static void
 batadv_tt_orig_list_entry_free_ref(struct batadv_tt_orig_list_entry *orig_entry)
 {
 	if (!atomic_dec_and_test(&orig_entry->refcount))
 		return;
 
-	call_rcu(&orig_entry->rcu, batadv_tt_orig_list_entry_free_rcu);
+	batadv_tt_orig_list_entry_release(orig_entry);
 }
 
 /**
-- 
2.1.0


From ab392cb5b77ed28c8b7edd5c7fa5d22f7e535fc4 Mon Sep 17 00:00:00 2001
From: Doron Tsur <doront@mellanox.com>
Date: Sun, 17 Jan 2016 11:25:47 +0200
Subject: [PATCH 38/40] net/mlx5_core: Fix trimming down IRQ number

[ Upstream commit 0b6e26ce89391327d955a756a7823272238eb867 ]

With several ConnectX-4 cards installed on a server, one may receive
irqn > 255 from the kernel API, which we mistakenly trim to 8bit.

This causes EQ creation failure with the following stack trace:
[<ffffffff812a11f4>] dump_stack+0x48/0x64
[<ffffffff810ace21>] __setup_irq+0x3a1/0x4f0
[<ffffffff810ad7e0>] request_threaded_irq+0x120/0x180
[<ffffffffa0923660>] ? mlx5_eq_int+0x450/0x450 [mlx5_core]
[<ffffffffa0922f64>] mlx5_create_map_eq+0x1e4/0x2b0 [mlx5_core]
[<ffffffffa091de01>] alloc_comp_eqs+0xb1/0x180 [mlx5_core]
[<ffffffffa091ea99>] mlx5_dev_init+0x5e9/0x6e0 [mlx5_core]
[<ffffffffa091ec29>] init_one+0x99/0x1c0 [mlx5_core]
[<ffffffff812e2afc>] local_pci_probe+0x4c/0xa0

Fixing it by changing of the irqn type from u8 to unsigned int to
support values > 255

Fixes: 61d0e73e0a5a ('net/mlx5_core: Use the the real irqn in eq->irqn')
Reported-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Doron Tsur <doront@mellanox.com>
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/mlx5/cq.c                   | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 6 +++---
 drivers/net/ethernet/mellanox/mlx5/core/main.c    | 3 ++-
 include/linux/mlx5/cq.h                           | 2 +-
 include/linux/mlx5/driver.h                       | 5 +++--
 5 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index 2d0dbbf..558c1e7 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -756,7 +756,7 @@ struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev,
 	int uninitialized_var(index);
 	int uninitialized_var(inlen);
 	int cqe_size;
-	int irqn;
+	unsigned int irqn;
 	int eqn;
 	int err;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 443632d..394744b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -746,7 +746,7 @@ static int mlx5e_create_cq(struct mlx5e_channel *c,
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5_core_cq *mcq = &cq->mcq;
 	int eqn_not_used;
-	int irqn;
+	unsigned int irqn;
 	int err;
 	u32 i;
 
@@ -800,7 +800,7 @@ static int mlx5e_enable_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
 	void *in;
 	void *cqc;
 	int inlen;
-	int irqn_not_used;
+	unsigned int irqn_not_used;
 	int eqn;
 	int err;
 
@@ -1498,7 +1498,7 @@ static int mlx5e_create_drop_cq(struct mlx5e_priv *priv,
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5_core_cq *mcq = &cq->mcq;
 	int eqn_not_used;
-	int irqn;
+	unsigned int irqn;
 	int err;
 
 	err = mlx5_cqwq_create(mdev, &param->wq, param->cqc, &cq->wq,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 03aabdd..af9593b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -520,7 +520,8 @@ static void mlx5_irq_clear_affinity_hints(struct mlx5_core_dev *mdev)
 		mlx5_irq_clear_affinity_hint(mdev, i);
 }
 
-int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, int *irqn)
+int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn,
+		    unsigned int *irqn)
 {
 	struct mlx5_eq_table *table = &dev->priv.eq_table;
 	struct mlx5_eq *eq, *n;
diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h
index abc4767..b2c9fad 100644
--- a/include/linux/mlx5/cq.h
+++ b/include/linux/mlx5/cq.h
@@ -45,7 +45,7 @@ struct mlx5_core_cq {
 	atomic_t		refcount;
 	struct completion	free;
 	unsigned		vector;
-	int			irqn;
+	unsigned int		irqn;
 	void (*comp)		(struct mlx5_core_cq *);
 	void (*event)		(struct mlx5_core_cq *, enum mlx5_event);
 	struct mlx5_uar	       *uar;
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 8b6d6f2..2b013dc 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -303,7 +303,7 @@ struct mlx5_eq {
 	u32			cons_index;
 	struct mlx5_buf		buf;
 	int			size;
-	u8			irqn;
+	unsigned int		irqn;
 	u8			eqn;
 	int			nent;
 	u64			mask;
@@ -738,7 +738,8 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
 int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
 int mlx5_start_eqs(struct mlx5_core_dev *dev);
 int mlx5_stop_eqs(struct mlx5_core_dev *dev);
-int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, int *irqn);
+int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn,
+		    unsigned int *irqn);
 int mlx5_core_attach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn);
 int mlx5_core_detach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn);
 
-- 
2.1.0


From ec3e28632be5cab8d687b1bc7b162e4970cfb664 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Mon, 18 Jan 2016 17:30:22 +0200
Subject: [PATCH 39/40] team: Replace rcu_read_lock with a mutex in
 team_vlan_rx_kill_vid

[ Upstream commit 60a6531bfe49555581ccd65f66a350cc5693fcde ]

We can't be within an RCU read-side critical section when deleting
VLANs, as underlying drivers might sleep during the hardware operation.
Therefore, replace the RCU critical section with a mutex. This is
consistent with team_vlan_rx_add_vid.

Fixes: 3d249d4ca7d0 ("net: introduce ethernet teaming device")
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 651d35e..59fefca 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1845,10 +1845,10 @@ static int team_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid)
 	struct team *team = netdev_priv(dev);
 	struct team_port *port;
 
-	rcu_read_lock();
-	list_for_each_entry_rcu(port, &team->port_list, list)
+	mutex_lock(&team->lock);
+	list_for_each_entry(port, &team->port_list, list)
 		vlan_vid_del(port->dev, proto, vid);
-	rcu_read_unlock();
+	mutex_unlock(&team->lock);
 
 	return 0;
 }
-- 
2.1.0


From 6e8c4e029d8184715d94859469d304a5b60eae13 Mon Sep 17 00:00:00 2001
From: Dan Streetman <dan.streetman@canonical.com>
Date: Thu, 29 Oct 2015 09:51:16 -0400
Subject: [PATCH 40/40] xfrm: dst_entries_init() per-net dst_ops

[ Upstream commit a8a572a6b5f2a79280d6e302cb3c1cb1fbaeb3e8 ]

Remove the dst_entries_init/destroy calls for xfrm4 and xfrm6 dst_ops
templates; their dst_entries counters will never be used.  Move the
xfrm dst_ops initialization from the common xfrm/xfrm_policy.c to
xfrm4/xfrm4_policy.c and xfrm6/xfrm6_policy.c, and call dst_entries_init
and dst_entries_destroy for each net namespace.

The ipv4 and ipv6 xfrms each create dst_ops template, and perform
dst_entries_init on the templates.  The template values are copied to each
net namespace's xfrm.xfrm*_dst_ops.  The problem there is the dst_ops
pcpuc_entries field is a percpu counter and cannot be used correctly by
simply copying it to another object.

The result of this is a very subtle bug; changes to the dst entries
counter from one net namespace may sometimes get applied to a different
net namespace dst entries counter.  This is because of how the percpu
counter works; it has a main count field as well as a pointer to the
percpu variables.  Each net namespace maintains its own main count
variable, but all point to one set of percpu variables.  When any net
namespace happens to change one of the percpu variables to outside its
small batch range, its count is moved to the net namespace's main count
variable.  So with multiple net namespaces operating concurrently, the
dst_ops entries counter can stray from the actual value that it should
be; if counts are consistently moved from one net namespace to another
(which my testing showed is likely), then one net namespace winds up
with a negative dst_ops count while another winds up with a continually
increasing count, eventually reaching its gc_thresh limit, which causes
all new traffic on the net namespace to fail with -ENOBUFS.

Signed-off-by: Dan Streetman <dan.streetman@canonical.com>
Signed-off-by: Dan Streetman <ddstreet@ieee.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/ipv4/xfrm4_policy.c | 46 +++++++++++++++++++++++++++++++++---------
 net/ipv6/xfrm6_policy.c | 53 +++++++++++++++++++++++++++++++++++--------------
 net/xfrm/xfrm_policy.c  | 38 -----------------------------------
 3 files changed, 75 insertions(+), 62 deletions(-)

diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index c10a9ee..126ff90 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -236,7 +236,7 @@ static void xfrm4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
 	xfrm_dst_ifdown(dst, dev);
 }
 
-static struct dst_ops xfrm4_dst_ops = {
+static struct dst_ops xfrm4_dst_ops_template = {
 	.family =		AF_INET,
 	.gc =			xfrm4_garbage_collect,
 	.update_pmtu =		xfrm4_update_pmtu,
@@ -250,7 +250,7 @@ static struct dst_ops xfrm4_dst_ops = {
 
 static struct xfrm_policy_afinfo xfrm4_policy_afinfo = {
 	.family = 		AF_INET,
-	.dst_ops =		&xfrm4_dst_ops,
+	.dst_ops =		&xfrm4_dst_ops_template,
 	.dst_lookup =		xfrm4_dst_lookup,
 	.get_saddr =		xfrm4_get_saddr,
 	.decode_session =	_decode_session4,
@@ -272,7 +272,7 @@ static struct ctl_table xfrm4_policy_table[] = {
 	{ }
 };
 
-static int __net_init xfrm4_net_init(struct net *net)
+static int __net_init xfrm4_net_sysctl_init(struct net *net)
 {
 	struct ctl_table *table;
 	struct ctl_table_header *hdr;
@@ -300,7 +300,7 @@ err_alloc:
 	return -ENOMEM;
 }
 
-static void __net_exit xfrm4_net_exit(struct net *net)
+static void __net_exit xfrm4_net_sysctl_exit(struct net *net)
 {
 	struct ctl_table *table;
 
@@ -312,12 +312,44 @@ static void __net_exit xfrm4_net_exit(struct net *net)
 	if (!net_eq(net, &init_net))
 		kfree(table);
 }
+#else /* CONFIG_SYSCTL */
+static int inline xfrm4_net_sysctl_init(struct net *net)
+{
+	return 0;
+}
+
+static void inline xfrm4_net_sysctl_exit(struct net *net)
+{
+}
+#endif
+
+static int __net_init xfrm4_net_init(struct net *net)
+{
+	int ret;
+
+	memcpy(&net->xfrm.xfrm4_dst_ops, &xfrm4_dst_ops_template,
+	       sizeof(xfrm4_dst_ops_template));
+	ret = dst_entries_init(&net->xfrm.xfrm4_dst_ops);
+	if (ret)
+		return ret;
+
+	ret = xfrm4_net_sysctl_init(net);
+	if (ret)
+		dst_entries_destroy(&net->xfrm.xfrm4_dst_ops);
+
+	return ret;
+}
+
+static void __net_exit xfrm4_net_exit(struct net *net)
+{
+	xfrm4_net_sysctl_exit(net);
+	dst_entries_destroy(&net->xfrm.xfrm4_dst_ops);
+}
 
 static struct pernet_operations __net_initdata xfrm4_net_ops = {
 	.init	= xfrm4_net_init,
 	.exit	= xfrm4_net_exit,
 };
-#endif
 
 static void __init xfrm4_policy_init(void)
 {
@@ -326,13 +358,9 @@ static void __init xfrm4_policy_init(void)
 
 void __init xfrm4_init(void)
 {
-	dst_entries_init(&xfrm4_dst_ops);
-
 	xfrm4_state_init();
 	xfrm4_policy_init();
 	xfrm4_protocol_init();
-#ifdef CONFIG_SYSCTL
 	register_pernet_subsys(&xfrm4_net_ops);
-#endif
 }
 
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index da55e0c..d51a18d 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -281,7 +281,7 @@ static void xfrm6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
 	xfrm_dst_ifdown(dst, dev);
 }
 
-static struct dst_ops xfrm6_dst_ops = {
+static struct dst_ops xfrm6_dst_ops_template = {
 	.family =		AF_INET6,
 	.gc =			xfrm6_garbage_collect,
 	.update_pmtu =		xfrm6_update_pmtu,
@@ -295,7 +295,7 @@ static struct dst_ops xfrm6_dst_ops = {
 
 static struct xfrm_policy_afinfo xfrm6_policy_afinfo = {
 	.family =		AF_INET6,
-	.dst_ops =		&xfrm6_dst_ops,
+	.dst_ops =		&xfrm6_dst_ops_template,
 	.dst_lookup =		xfrm6_dst_lookup,
 	.get_saddr =		xfrm6_get_saddr,
 	.decode_session =	_decode_session6,
@@ -327,7 +327,7 @@ static struct ctl_table xfrm6_policy_table[] = {
 	{ }
 };
 
-static int __net_init xfrm6_net_init(struct net *net)
+static int __net_init xfrm6_net_sysctl_init(struct net *net)
 {
 	struct ctl_table *table;
 	struct ctl_table_header *hdr;
@@ -355,7 +355,7 @@ err_alloc:
 	return -ENOMEM;
 }
 
-static void __net_exit xfrm6_net_exit(struct net *net)
+static void __net_exit xfrm6_net_sysctl_exit(struct net *net)
 {
 	struct ctl_table *table;
 
@@ -367,24 +367,52 @@ static void __net_exit xfrm6_net_exit(struct net *net)
 	if (!net_eq(net, &init_net))
 		kfree(table);
 }
+#else /* CONFIG_SYSCTL */
+static int inline xfrm6_net_sysctl_init(struct net *net)
+{
+	return 0;
+}
+
+static void inline xfrm6_net_sysctl_exit(struct net *net)
+{
+}
+#endif
+
+static int __net_init xfrm6_net_init(struct net *net)
+{
+	int ret;
+
+	memcpy(&net->xfrm.xfrm6_dst_ops, &xfrm6_dst_ops_template,
+	       sizeof(xfrm6_dst_ops_template));
+	ret = dst_entries_init(&net->xfrm.xfrm6_dst_ops);
+	if (ret)
+		return ret;
+
+	ret = xfrm6_net_sysctl_init(net);
+	if (ret)
+		dst_entries_destroy(&net->xfrm.xfrm6_dst_ops);
+
+	return ret;
+}
+
+static void __net_exit xfrm6_net_exit(struct net *net)
+{
+	xfrm6_net_sysctl_exit(net);
+	dst_entries_destroy(&net->xfrm.xfrm6_dst_ops);
+}
 
 static struct pernet_operations xfrm6_net_ops = {
 	.init	= xfrm6_net_init,
 	.exit	= xfrm6_net_exit,
 };
-#endif
 
 int __init xfrm6_init(void)
 {
 	int ret;
 
-	dst_entries_init(&xfrm6_dst_ops);
-
 	ret = xfrm6_policy_init();
-	if (ret) {
-		dst_entries_destroy(&xfrm6_dst_ops);
+	if (ret)
 		goto out;
-	}
 	ret = xfrm6_state_init();
 	if (ret)
 		goto out_policy;
@@ -393,9 +421,7 @@ int __init xfrm6_init(void)
 	if (ret)
 		goto out_state;
 
-#ifdef CONFIG_SYSCTL
 	register_pernet_subsys(&xfrm6_net_ops);
-#endif
 out:
 	return ret;
 out_state:
@@ -407,11 +433,8 @@ out_policy:
 
 void xfrm6_fini(void)
 {
-#ifdef CONFIG_SYSCTL
 	unregister_pernet_subsys(&xfrm6_net_ops);
-#endif
 	xfrm6_protocol_fini();
 	xfrm6_policy_fini();
 	xfrm6_state_fini();
-	dst_entries_destroy(&xfrm6_dst_ops);
 }
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 94af3d0..bacd30b 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2807,7 +2807,6 @@ static struct neighbour *xfrm_neigh_lookup(const struct dst_entry *dst,
 
 int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo)
 {
-	struct net *net;
 	int err = 0;
 	if (unlikely(afinfo == NULL))
 		return -EINVAL;
@@ -2838,26 +2837,6 @@ int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo)
 	}
 	spin_unlock(&xfrm_policy_afinfo_lock);
 
-	rtnl_lock();
-	for_each_net(net) {
-		struct dst_ops *xfrm_dst_ops;
-
-		switch (afinfo->family) {
-		case AF_INET:
-			xfrm_dst_ops = &net->xfrm.xfrm4_dst_ops;
-			break;
-#if IS_ENABLED(CONFIG_IPV6)
-		case AF_INET6:
-			xfrm_dst_ops = &net->xfrm.xfrm6_dst_ops;
-			break;
-#endif
-		default:
-			BUG();
-		}
-		*xfrm_dst_ops = *afinfo->dst_ops;
-	}
-	rtnl_unlock();
-
 	return err;
 }
 EXPORT_SYMBOL(xfrm_policy_register_afinfo);
@@ -2893,22 +2872,6 @@ int xfrm_policy_unregister_afinfo(struct xfrm_policy_afinfo *afinfo)
 }
 EXPORT_SYMBOL(xfrm_policy_unregister_afinfo);
 
-static void __net_init xfrm_dst_ops_init(struct net *net)
-{
-	struct xfrm_policy_afinfo *afinfo;
-
-	rcu_read_lock();
-	afinfo = rcu_dereference(xfrm_policy_afinfo[AF_INET]);
-	if (afinfo)
-		net->xfrm.xfrm4_dst_ops = *afinfo->dst_ops;
-#if IS_ENABLED(CONFIG_IPV6)
-	afinfo = rcu_dereference(xfrm_policy_afinfo[AF_INET6]);
-	if (afinfo)
-		net->xfrm.xfrm6_dst_ops = *afinfo->dst_ops;
-#endif
-	rcu_read_unlock();
-}
-
 static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void *ptr)
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
@@ -3057,7 +3020,6 @@ static int __net_init xfrm_net_init(struct net *net)
 	rv = xfrm_policy_init(net);
 	if (rv < 0)
 		goto out_policy;
-	xfrm_dst_ops_init(net);
 	rv = xfrm_sysctl_init(net);
 	if (rv < 0)
 		goto out_sysctl;
-- 
2.1.0


[-- Attachment #4: net_41.mbox --]
[-- Type: Application/Octet-Stream, Size: 122371 bytes --]

From 280bbc0164022d700967ac1da20d48c14bcc545b Mon Sep 17 00:00:00 2001
From: Vijay Pandurangan <vijayp@vijayp.ca>
Date: Fri, 18 Dec 2015 14:34:59 -0500
Subject: [PATCH 01/39] =?UTF-8?q?veth:=20don=E2=80=99t=20modify=20ip=5Fsum?=
 =?UTF-8?q?med;=20doing=20so=20treats=20packets=20with=20bad=20checksums?=
 =?UTF-8?q?=20as=20good.?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit ce8c839b74e3017996fad4e1b7ba2e2625ede82f ]

Packets that arrive from real hardware devices have ip_summed ==
CHECKSUM_UNNECESSARY if the hardware verified the checksums, or
CHECKSUM_NONE if the packet is bad or it was unable to verify it. The
current version of veth will replace CHECKSUM_NONE with
CHECKSUM_UNNECESSARY, which causes corrupt packets routed from hardware to
a veth device to be delivered to the application. This caused applications
at Twitter to receive corrupt data when network hardware was corrupting
packets.

We believe this was added as an optimization to skip computing and
verifying checksums for communication between containers. However, locally
generated packets have ip_summed == CHECKSUM_PARTIAL, so the code as
written does nothing for them. As far as we can tell, after removing this
code, these packets are transmitted from one stack to another unmodified
(tcpdump shows invalid checksums on both sides, as expected), and they are
delivered correctly to applications. We didn’t test every possible network
configuration, but we tried a few common ones such as bridging containers,
using NAT between the host and a container, and routing from hardware
devices to containers. We have effectively deployed this in production at
Twitter (by disabling RX checksum offloading on veth devices).

This code dates back to the first version of the driver, commit
<e314dbdc1c0dc6a548ecf> ("[NET]: Virtual ethernet device driver"), so I
suspect this bug occurred mostly because the driver API has evolved
significantly since then. Commit <0b7967503dc97864f283a> ("net/veth: Fix
packet checksumming") (in December 2010) fixed this for packets that get
created locally and sent to hardware devices, by not changing
CHECKSUM_PARTIAL. However, the same issue still occurs for packets coming
in from hardware devices.

Co-authored-by: Evan Jones <ej@evanjones.ca>
Signed-off-by: Evan Jones <ej@evanjones.ca>
Cc: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Cc: Phil Sutter <phil@nwl.cc>
Cc: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Cc: netdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Vijay Pandurangan <vijayp@vijayp.ca>
Acked-by: Cong Wang <cwang@twopensource.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/veth.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index c8186ff..2e61a79 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -117,12 +117,6 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 		kfree_skb(skb);
 		goto drop;
 	}
-	/* don't change ip_summed == CHECKSUM_PARTIAL, as that
-	 * will cause bad checksum on forwarded packets
-	 */
-	if (skb->ip_summed == CHECKSUM_NONE &&
-	    rcv->features & NETIF_F_RXCSUM)
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
 
 	if (likely(dev_forward_skb(rcv, skb) == NET_RX_SUCCESS)) {
 		struct pcpu_vstats *stats = this_cpu_ptr(dev->vstats);
-- 
2.1.0


From b9d86035732193ccbb3ba20d9810da058d16ff75 Mon Sep 17 00:00:00 2001
From: Andrey Ryabinin <aryabinin@virtuozzo.com>
Date: Mon, 21 Dec 2015 12:54:45 +0300
Subject: [PATCH 02/39] ipv6/addrlabel: fix ip6addrlbl_get()

[ Upstream commit e459dfeeb64008b2d23bdf600f03b3605dbb8152 ]

ip6addrlbl_get() has never worked. If ip6addrlbl_hold() succeeded,
ip6addrlbl_get() will exit with '-ESRCH'. If ip6addrlbl_hold() failed,
ip6addrlbl_get() will use about to be free ip6addrlbl_entry pointer.

Fix this by inverting ip6addrlbl_hold() check.

Fixes: 2a8cc6c89039 ("[IPV6] ADDRCONF: Support RFC3484 configurable address selection policy table.")
Signed-off-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
Reviewed-by: Cong Wang <cwang@twopensource.com>
Acked-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrlabel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index 882124e..a8f6986 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -552,7 +552,7 @@ static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 
 	rcu_read_lock();
 	p = __ipv6_addr_label(net, addr, ipv6_addr_type(addr), ifal->ifal_index);
-	if (p && ip6addrlbl_hold(p))
+	if (p && !ip6addrlbl_hold(p))
 		p = NULL;
 	lseq = ip6addrlbl_table.seq;
 	rcu_read_unlock();
-- 
2.1.0


From 695f8c5103eaf31288cc5d3107a79ad9ed3db660 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Mon, 21 Dec 2015 10:55:45 -0800
Subject: [PATCH 03/39] addrconf: always initialize sysctl table data

[ Upstream commit 5449a5ca9bc27dd51a462de7ca0b1cd861cd2bd0 ]

When sysctl performs restrict writes, it allows to write from
a middle position of a sysctl file, which requires us to initialize
the table data before calling proc_dostring() for the write case.

Fixes: 3d1bec99320d ("ipv6: introduce secret_stable to ipv6_devconf")
Reported-by: Sasha Levin <sasha.levin@oracle.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Tested-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index a2d6850..f4795b0 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5267,13 +5267,10 @@ static int addrconf_sysctl_stable_secret(struct ctl_table *ctl, int write,
 		goto out;
 	}
 
-	if (!write) {
-		err = snprintf(str, sizeof(str), "%pI6",
-			       &secret->secret);
-		if (err >= sizeof(str)) {
-			err = -EIO;
-			goto out;
-		}
+	err = snprintf(str, sizeof(str), "%pI6", &secret->secret);
+	if (err >= sizeof(str)) {
+		err = -EIO;
+		goto out;
 	}
 
 	err = proc_dostring(&lctl, write, buffer, lenp, ppos);
-- 
2.1.0


From 920fe6792a149dbbd443a5eaa8cbac246f4a24df Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Wed, 23 Dec 2015 13:42:43 +0100
Subject: [PATCH 04/39] net: cdc_ncm: avoid changing RX/TX buffers on MTU
 changes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 1dfddff5fcd869fcab0c52fafae099dfa435a935 ]

NCM buffer sizes are negotiated with the device independently of
the network device MTU.  The RX buffers are allocated by the
usbnet framework based on the rx_urb_size value set by cdc_ncm. A
single RX buffer can hold a number of MTU sized packets.

The default usbnet change_mtu ndo only modifies rx_urb_size if it
is equal to hard_mtu.  And the cdc_ncm driver will set rx_urb_size
and hard_mtu independently of each other, based on dwNtbInMaxSize
and dwNtbOutMaxSize respectively. It was therefore assumed that
usbnet_change_mtu() would never touch rx_urb_size.  This failed to
consider the case where dwNtbInMaxSize and dwNtbOutMaxSize happens
to be equal.

Fix by implementing an NCM specific change_mtu ndo, modifying the
netdev MTU without touching the buffer size settings.

Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_mbim.c  |  2 +-
 drivers/net/usb/cdc_ncm.c   | 31 +++++++++++++++++++++++++++++++
 include/linux/usb/cdc_ncm.h |  1 +
 3 files changed, 33 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c
index e4b7a47..5efaa9a 100644
--- a/drivers/net/usb/cdc_mbim.c
+++ b/drivers/net/usb/cdc_mbim.c
@@ -100,7 +100,7 @@ static const struct net_device_ops cdc_mbim_netdev_ops = {
 	.ndo_stop             = usbnet_stop,
 	.ndo_start_xmit       = usbnet_start_xmit,
 	.ndo_tx_timeout       = usbnet_tx_timeout,
-	.ndo_change_mtu       = usbnet_change_mtu,
+	.ndo_change_mtu       = cdc_ncm_change_mtu,
 	.ndo_set_mac_address  = eth_mac_addr,
 	.ndo_validate_addr    = eth_validate_addr,
 	.ndo_vlan_rx_add_vid  = cdc_mbim_rx_add_vid,
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 8067b8f..0b481c3 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -41,6 +41,7 @@
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/ctype.h>
+#include <linux/etherdevice.h>
 #include <linux/ethtool.h>
 #include <linux/workqueue.h>
 #include <linux/mii.h>
@@ -687,6 +688,33 @@ static void cdc_ncm_free(struct cdc_ncm_ctx *ctx)
 	kfree(ctx);
 }
 
+/* we need to override the usbnet change_mtu ndo for two reasons:
+ *  - respect the negotiated maximum datagram size
+ *  - avoid unwanted changes to rx and tx buffers
+ */
+int cdc_ncm_change_mtu(struct net_device *net, int new_mtu)
+{
+	struct usbnet *dev = netdev_priv(net);
+	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
+	int maxmtu = ctx->max_datagram_size - cdc_ncm_eth_hlen(dev);
+
+	if (new_mtu <= 0 || new_mtu > maxmtu)
+		return -EINVAL;
+	net->mtu = new_mtu;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cdc_ncm_change_mtu);
+
+static const struct net_device_ops cdc_ncm_netdev_ops = {
+	.ndo_open	     = usbnet_open,
+	.ndo_stop	     = usbnet_stop,
+	.ndo_start_xmit	     = usbnet_start_xmit,
+	.ndo_tx_timeout	     = usbnet_tx_timeout,
+	.ndo_change_mtu	     = cdc_ncm_change_mtu,
+	.ndo_set_mac_address = eth_mac_addr,
+	.ndo_validate_addr   = eth_validate_addr,
+};
+
 int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting)
 {
 	const struct usb_cdc_union_desc *union_desc = NULL;
@@ -861,6 +889,9 @@ advance:
 	/* add our sysfs attrs */
 	dev->net->sysfs_groups[0] = &cdc_ncm_sysfs_attr_group;
 
+	/* must handle MTU changes */
+	dev->net->netdev_ops = &cdc_ncm_netdev_ops;
+
 	return 0;
 
 error2:
diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h
index 7c9b484..e7827ae 100644
--- a/include/linux/usb/cdc_ncm.h
+++ b/include/linux/usb/cdc_ncm.h
@@ -133,6 +133,7 @@ struct cdc_ncm_ctx {
 };
 
 u8 cdc_ncm_select_altsetting(struct usb_interface *intf);
+int cdc_ncm_change_mtu(struct net_device *net, int new_mtu);
 int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting);
 void cdc_ncm_unbind(struct usbnet *dev, struct usb_interface *intf);
 struct sk_buff *cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign);
-- 
2.1.0


From 7c14cf9434452f74cf28c7f99f6907bf75072bce Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 29 Dec 2015 17:49:25 +0800
Subject: [PATCH 05/39] sctp: sctp should release assoc when
 sctp_make_abort_user return NULL in sctp_close

[ Upstream commit 068d8bd338e855286aea54e70d1c101569284b21 ]

In sctp_close, sctp_make_abort_user may return NULL because of memory
allocation failure. If this happens, it will bypass any state change
and never free the assoc. The assoc has no chance to be freed and it
will be kept in memory with the state it had even after the socket is
closed by sctp_close().

So if sctp_make_abort_user fails to allocate memory, we should abort
the asoc via sctp_primitive_ABORT as well. Just like the annotation in
sctp_sf_cookie_wait_prm_abort and sctp_sf_do_9_1_prm_abort said,
"Even if we can't send the ABORT due to low memory delete the TCB.
This is a departure from our typical NOMEM handling".

But then the chunk is NULL (low memory) and the SCTP_CMD_REPLY cmd would
dereference the chunk pointer, and system crash. So we should add
SCTP_CMD_REPLY cmd only when the chunk is not NULL, just like other
places where it adds SCTP_CMD_REPLY cmd.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sm_statefuns.c | 6 ++++--
 net/sctp/socket.c       | 3 +--
 2 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 3ee27b7..e6bb98e 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -4829,7 +4829,8 @@ sctp_disposition_t sctp_sf_do_9_1_prm_abort(
 
 	retval = SCTP_DISPOSITION_CONSUME;
 
-	sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort));
+	if (abort)
+		sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort));
 
 	/* Even if we can't send the ABORT due to low memory delete the
 	 * TCB.  This is a departure from our typical NOMEM handling.
@@ -4966,7 +4967,8 @@ sctp_disposition_t sctp_sf_cookie_wait_prm_abort(
 			SCTP_TO(SCTP_EVENT_TIMEOUT_T1_INIT));
 	retval = SCTP_DISPOSITION_CONSUME;
 
-	sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort));
+	if (abort)
+		sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort));
 
 	sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE,
 			SCTP_STATE(SCTP_STATE_CLOSED));
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index a63c2c8..76e6ec6 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1513,8 +1513,7 @@ static void sctp_close(struct sock *sk, long timeout)
 			struct sctp_chunk *chunk;
 
 			chunk = sctp_make_abort_user(asoc, NULL, 0);
-			if (chunk)
-				sctp_primitive_ABORT(net, asoc, chunk);
+			sctp_primitive_ABORT(net, asoc, chunk);
 		} else
 			sctp_primitive_SHUTDOWN(net, asoc, NULL);
 	}
-- 
2.1.0


From 4b14fb3c5b97286e6de4b3a015532c4b6c1773b7 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 31 Dec 2015 14:26:33 +0100
Subject: [PATCH 06/39] connector: bump skb->users before callback invocation

[ Upstream commit 55285bf09427c5abf43ee1d54e892f352092b1f1 ]

Dmitry reports memleak with syskaller program.
Problem is that connector bumps skb usecount but might not invoke callback.

So move skb_get to where we invoke the callback.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/connector/connector.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c
index 30f5228..c19e7fc 100644
--- a/drivers/connector/connector.c
+++ b/drivers/connector/connector.c
@@ -178,26 +178,21 @@ static int cn_call_callback(struct sk_buff *skb)
  *
  * It checks skb, netlink header and msg sizes, and calls callback helper.
  */
-static void cn_rx_skb(struct sk_buff *__skb)
+static void cn_rx_skb(struct sk_buff *skb)
 {
 	struct nlmsghdr *nlh;
-	struct sk_buff *skb;
 	int len, err;
 
-	skb = skb_get(__skb);
-
 	if (skb->len >= NLMSG_HDRLEN) {
 		nlh = nlmsg_hdr(skb);
 		len = nlmsg_len(nlh);
 
 		if (len < (int)sizeof(struct cn_msg) ||
 		    skb->len < nlh->nlmsg_len ||
-		    len > CONNECTOR_MAX_MSG_SIZE) {
-			kfree_skb(skb);
+		    len > CONNECTOR_MAX_MSG_SIZE)
 			return;
-		}
 
-		err = cn_call_callback(skb);
+		err = cn_call_callback(skb_get(skb));
 		if (err < 0)
 			kfree_skb(skb);
 	}
-- 
2.1.0


From f977bb1a8fc62ba9672b38e4d4f0790a7b49c582 Mon Sep 17 00:00:00 2001
From: willy tarreau <w@1wt.eu>
Date: Sun, 10 Jan 2016 07:54:56 +0100
Subject: [PATCH 07/39] unix: properly account for FDs passed over unix sockets

[ Upstream commit 712f4aad406bb1ed67f3f98d04c044191f0ff593 ]

It is possible for a process to allocate and accumulate far more FDs than
the process' limit by sending them over a unix socket then closing them
to keep the process' fd count low.

This change addresses this problem by keeping track of the number of FDs
in flight per user and preventing non-privileged processes from having
more FDs in flight than their configured FD limit.

Reported-by: socketpair@gmail.com
Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Mitigates: CVE-2013-4312 (Linux 2.0+)
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/sched.h |  1 +
 net/unix/af_unix.c    | 24 ++++++++++++++++++++----
 net/unix/garbage.c    | 13 ++++++++-----
 3 files changed, 29 insertions(+), 9 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 61f4f2d..9128b4e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -802,6 +802,7 @@ struct user_struct {
 	unsigned long mq_bytes;	/* How many bytes can be allocated to mqueue? */
 #endif
 	unsigned long locked_shm; /* How many pages of mlocked shm ? */
+	unsigned long unix_inflight;	/* How many files in flight in unix sockets */
 
 #ifdef CONFIG_KEYS
 	struct key *uid_keyring;	/* UID specific keyring */
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index a398f62..cb3a01a 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1481,6 +1481,21 @@ static void unix_destruct_scm(struct sk_buff *skb)
 	sock_wfree(skb);
 }
 
+/*
+ * The "user->unix_inflight" variable is protected by the garbage
+ * collection lock, and we just read it locklessly here. If you go
+ * over the limit, there might be a tiny race in actually noticing
+ * it across threads. Tough.
+ */
+static inline bool too_many_unix_fds(struct task_struct *p)
+{
+	struct user_struct *user = current_user();
+
+	if (unlikely(user->unix_inflight > task_rlimit(p, RLIMIT_NOFILE)))
+		return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN);
+	return false;
+}
+
 #define MAX_RECURSION_LEVEL 4
 
 static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
@@ -1489,6 +1504,9 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
 	unsigned char max_level = 0;
 	int unix_sock_count = 0;
 
+	if (too_many_unix_fds(current))
+		return -ETOOMANYREFS;
+
 	for (i = scm->fp->count - 1; i >= 0; i--) {
 		struct sock *sk = unix_get_socket(scm->fp->fp[i]);
 
@@ -1510,10 +1528,8 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
 	if (!UNIXCB(skb).fp)
 		return -ENOMEM;
 
-	if (unix_sock_count) {
-		for (i = scm->fp->count - 1; i >= 0; i--)
-			unix_inflight(scm->fp->fp[i]);
-	}
+	for (i = scm->fp->count - 1; i >= 0; i--)
+		unix_inflight(scm->fp->fp[i]);
 	return max_level;
 }
 
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index a73a226..8fcdc22 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -120,11 +120,11 @@ void unix_inflight(struct file *fp)
 {
 	struct sock *s = unix_get_socket(fp);
 
+	spin_lock(&unix_gc_lock);
+
 	if (s) {
 		struct unix_sock *u = unix_sk(s);
 
-		spin_lock(&unix_gc_lock);
-
 		if (atomic_long_inc_return(&u->inflight) == 1) {
 			BUG_ON(!list_empty(&u->link));
 			list_add_tail(&u->link, &gc_inflight_list);
@@ -132,25 +132,28 @@ void unix_inflight(struct file *fp)
 			BUG_ON(list_empty(&u->link));
 		}
 		unix_tot_inflight++;
-		spin_unlock(&unix_gc_lock);
 	}
+	fp->f_cred->user->unix_inflight++;
+	spin_unlock(&unix_gc_lock);
 }
 
 void unix_notinflight(struct file *fp)
 {
 	struct sock *s = unix_get_socket(fp);
 
+	spin_lock(&unix_gc_lock);
+
 	if (s) {
 		struct unix_sock *u = unix_sk(s);
 
-		spin_lock(&unix_gc_lock);
 		BUG_ON(list_empty(&u->link));
 
 		if (atomic_long_dec_and_test(&u->inflight))
 			list_del_init(&u->link);
 		unix_tot_inflight--;
-		spin_unlock(&unix_gc_lock);
 	}
+	fp->f_cred->user->unix_inflight--;
+	spin_unlock(&unix_gc_lock);
 }
 
 static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *),
-- 
2.1.0


From 53b014d9c53d5184bee575e35d1812a9b5f38fda Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Tue, 5 Jan 2016 10:46:00 +0100
Subject: [PATCH 08/39] bridge: Only call /sbin/bridge-stp for the initial
 network namespace

[ Upstream commit ff62198553e43cdffa9d539f6165d3e83f8a42bc ]

[I stole this patch from Eric Biederman. He wrote:]

> There is no defined mechanism to pass network namespace information
> into /sbin/bridge-stp therefore don't even try to invoke it except
> for bridge devices in the initial network namespace.
>
> It is possible for unprivileged users to cause /sbin/bridge-stp to be
> invoked for any network device name which if /sbin/bridge-stp does not
> guard against unreasonable arguments or being invoked twice on the
> same network device could cause problems.

[Hannes: changed patch using netns_eq]

Cc: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_stp_if.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
index 7832d07..ce658ab 100644
--- a/net/bridge/br_stp_if.c
+++ b/net/bridge/br_stp_if.c
@@ -128,7 +128,10 @@ static void br_stp_start(struct net_bridge *br)
 	char *argv[] = { BR_STP_PROG, br->dev->name, "start", NULL };
 	char *envp[] = { NULL };
 
-	r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC);
+	if (net_eq(dev_net(br->dev), &init_net))
+		r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC);
+	else
+		r = -ENOENT;
 
 	spin_lock_bh(&br->lock);
 
-- 
2.1.0


From fe1b8c7e714c766321bb2a4aa2a88ccbf3bdf185 Mon Sep 17 00:00:00 2001
From: Rabin Vincent <rabin@rab.in>
Date: Tue, 5 Jan 2016 16:23:07 +0100
Subject: [PATCH 09/39] net: filter: make JITs zero A for SKF_AD_ALU_XOR_X

[ Upstream commit 55795ef5469290f89f04e12e662ded604909e462 ]

The SKF_AD_ALU_XOR_X ancillary is not like the other ancillary data
instructions since it XORs A with X while all the others replace A with
some loaded value.  All the BPF JITs fail to clear A if this is used as
the first instruction in a filter.  This was found using american fuzzy
lop.

Add a helper to determine if A needs to be cleared given the first
instruction in a filter, and use this in the JITs.  Except for ARM, the
rest have only been compile-tested.

Fixes: 3480593131e0 ("net: filter: get rid of BPF_S_* enum")
Signed-off-by: Rabin Vincent <rabin@rab.in>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/arm/net/bpf_jit_32.c       | 16 +---------------
 arch/mips/net/bpf_jit.c         | 16 +---------------
 arch/powerpc/net/bpf_jit_comp.c | 13 ++-----------
 arch/sparc/net/bpf_jit_comp.c   | 17 ++---------------
 include/linux/filter.h          | 19 +++++++++++++++++++
 5 files changed, 25 insertions(+), 56 deletions(-)

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index e0e2358..5fe949b 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -162,19 +162,6 @@ static inline int mem_words_used(struct jit_ctx *ctx)
 	return fls(ctx->seen & SEEN_MEM);
 }
 
-static inline bool is_load_to_a(u16 inst)
-{
-	switch (inst) {
-	case BPF_LD | BPF_W | BPF_LEN:
-	case BPF_LD | BPF_W | BPF_ABS:
-	case BPF_LD | BPF_H | BPF_ABS:
-	case BPF_LD | BPF_B | BPF_ABS:
-		return true;
-	default:
-		return false;
-	}
-}
-
 static void jit_fill_hole(void *area, unsigned int size)
 {
 	u32 *ptr;
@@ -186,7 +173,6 @@ static void jit_fill_hole(void *area, unsigned int size)
 static void build_prologue(struct jit_ctx *ctx)
 {
 	u16 reg_set = saved_regs(ctx);
-	u16 first_inst = ctx->skf->insns[0].code;
 	u16 off;
 
 #ifdef CONFIG_FRAME_POINTER
@@ -216,7 +202,7 @@ static void build_prologue(struct jit_ctx *ctx)
 		emit(ARM_MOV_I(r_X, 0), ctx);
 
 	/* do not leak kernel data to userspace */
-	if ((first_inst != (BPF_RET | BPF_K)) && !(is_load_to_a(first_inst)))
+	if (bpf_needs_clear_a(&ctx->skf->insns[0]))
 		emit(ARM_MOV_I(r_A, 0), ctx);
 
 	/* stack space for the BPF_MEM words */
diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c
index e23fdf2..d6d27d5 100644
--- a/arch/mips/net/bpf_jit.c
+++ b/arch/mips/net/bpf_jit.c
@@ -556,19 +556,6 @@ static inline u16 align_sp(unsigned int num)
 	return num;
 }
 
-static bool is_load_to_a(u16 inst)
-{
-	switch (inst) {
-	case BPF_LD | BPF_W | BPF_LEN:
-	case BPF_LD | BPF_W | BPF_ABS:
-	case BPF_LD | BPF_H | BPF_ABS:
-	case BPF_LD | BPF_B | BPF_ABS:
-		return true;
-	default:
-		return false;
-	}
-}
-
 static void save_bpf_jit_regs(struct jit_ctx *ctx, unsigned offset)
 {
 	int i = 0, real_off = 0;
@@ -686,7 +673,6 @@ static unsigned int get_stack_depth(struct jit_ctx *ctx)
 
 static void build_prologue(struct jit_ctx *ctx)
 {
-	u16 first_inst = ctx->skf->insns[0].code;
 	int sp_off;
 
 	/* Calculate the total offset for the stack pointer */
@@ -700,7 +686,7 @@ static void build_prologue(struct jit_ctx *ctx)
 		emit_jit_reg_move(r_X, r_zero, ctx);
 
 	/* Do not leak kernel data to userspace */
-	if ((first_inst != (BPF_RET | BPF_K)) && !(is_load_to_a(first_inst)))
+	if (bpf_needs_clear_a(&ctx->skf->insns[0]))
 		emit_jit_reg_move(r_A, r_zero, ctx);
 }
 
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 17cea18..264c473 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -78,18 +78,9 @@ static void bpf_jit_build_prologue(struct bpf_prog *fp, u32 *image,
 		PPC_LI(r_X, 0);
 	}
 
-	switch (filter[0].code) {
-	case BPF_RET | BPF_K:
-	case BPF_LD | BPF_W | BPF_LEN:
-	case BPF_LD | BPF_W | BPF_ABS:
-	case BPF_LD | BPF_H | BPF_ABS:
-	case BPF_LD | BPF_B | BPF_ABS:
-		/* first instruction sets A register (or is RET 'constant') */
-		break;
-	default:
-		/* make sure we dont leak kernel information to user */
+	/* make sure we dont leak kernel information to user */
+	if (bpf_needs_clear_a(&filter[0]))
 		PPC_LI(r_A, 0);
-	}
 }
 
 static void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c
index 7931eee..8109e92 100644
--- a/arch/sparc/net/bpf_jit_comp.c
+++ b/arch/sparc/net/bpf_jit_comp.c
@@ -420,22 +420,9 @@ void bpf_jit_compile(struct bpf_prog *fp)
 		}
 		emit_reg_move(O7, r_saved_O7);
 
-		switch (filter[0].code) {
-		case BPF_RET | BPF_K:
-		case BPF_LD | BPF_W | BPF_LEN:
-		case BPF_LD | BPF_W | BPF_ABS:
-		case BPF_LD | BPF_H | BPF_ABS:
-		case BPF_LD | BPF_B | BPF_ABS:
-			/* The first instruction sets the A register (or is
-			 * a "RET 'constant'")
-			 */
-			break;
-		default:
-			/* Make sure we dont leak kernel information to the
-			 * user.
-			 */
+		/* Make sure we dont leak kernel information to the user. */
+		if (bpf_needs_clear_a(&filter[0]))
 			emit_clear(r_A); /* A = 0 */
-		}
 
 		for (i = 0; i < flen; i++) {
 			unsigned int K = filter[i].k;
diff --git a/include/linux/filter.h b/include/linux/filter.h
index fa11b3a..1ce6e10 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -428,6 +428,25 @@ static inline void bpf_jit_free(struct bpf_prog *fp)
 
 #define BPF_ANC		BIT(15)
 
+static inline bool bpf_needs_clear_a(const struct sock_filter *first)
+{
+	switch (first->code) {
+	case BPF_RET | BPF_K:
+	case BPF_LD | BPF_W | BPF_LEN:
+		return false;
+
+	case BPF_LD | BPF_W | BPF_ABS:
+	case BPF_LD | BPF_H | BPF_ABS:
+	case BPF_LD | BPF_B | BPF_ABS:
+		if (first->k == SKF_AD_OFF + SKF_AD_ALU_XOR_X)
+			return true;
+		return false;
+
+	default:
+		return true;
+	}
+}
+
 static inline u16 bpf_anc_helper(const struct sock_filter *ftest)
 {
 	BUG_ON(ftest->code & BPF_ANC);
-- 
2.1.0


From a323157913b9f64ee8f68c5bb7aef934d2e6ef48 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Tue, 5 Jan 2016 09:11:36 -0800
Subject: [PATCH 10/39] net: sched: fix missing free per cpu on qstats

[ Upstream commit 73c20a8b7245273125cfe92c4b46e6fdb568a801 ]

When a qdisc is using per cpu stats (currently just the ingress
qdisc) only the bstats are being freed. This also free's the qstats.

Fixes: b0ab6f92752b9f9d8 ("net: sched: enable per cpu qstats")
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_generic.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index b453270..3c6f6b77 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -666,8 +666,10 @@ static void qdisc_rcu_free(struct rcu_head *head)
 {
 	struct Qdisc *qdisc = container_of(head, struct Qdisc, rcu_head);
 
-	if (qdisc_is_percpu_stats(qdisc))
+	if (qdisc_is_percpu_stats(qdisc)) {
 		free_percpu(qdisc->cpu_bstats);
+		free_percpu(qdisc->cpu_qstats);
+	}
 
 	kfree((char *) qdisc - qdisc->padded);
 }
-- 
2.1.0


From 651e6465df47c6336e6744a82e0a1badebb3f4cc Mon Sep 17 00:00:00 2001
From: Francesco Ruggeri <fruggeri@aristanetworks.com>
Date: Wed, 6 Jan 2016 00:18:48 -0800
Subject: [PATCH 11/39] net: possible use after free in dst_release

[ Upstream commit 07a5d38453599052aff0877b16bb9c1585f08609 ]

dst_release should not access dst->flags after decrementing
__refcnt to 0. The dst_entry may be in dst_busy_list and
dst_gc_task may dst_destroy it before dst_release gets a chance
to access dst->flags.

Fixes: d69bbf88c8d0 ("net: fix a race in dst_release()")
Fixes: 27b75c95f10d ("net: avoid RCU for NOCACHE dst")
Signed-off-by: Francesco Ruggeri <fruggeri@arista.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dst.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/dst.c b/net/core/dst.c
index f8db403..540066c 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -282,10 +282,11 @@ void dst_release(struct dst_entry *dst)
 {
 	if (dst) {
 		int newrefcnt;
+		unsigned short nocache = dst->flags & DST_NOCACHE;
 
 		newrefcnt = atomic_dec_return(&dst->__refcnt);
 		WARN_ON(newrefcnt < 0);
-		if (!newrefcnt && unlikely(dst->flags & DST_NOCACHE))
+		if (!newrefcnt && unlikely(nocache))
 			call_rcu(&dst->rcu_head, dst_destroy_rcu);
 	}
 }
-- 
2.1.0


From 7ccfbdc41a177afdf64f1d22d7053a0b406d088f Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Thu, 7 Jan 2016 11:26:53 +0100
Subject: [PATCH 12/39] vxlan: fix test which detect duplicate vxlan iface

[ Upstream commit 07b9b37c227cb8d88d478b4a9c5634fee514ede1 ]

When a vxlan interface is created, the driver checks that there is not
another vxlan interface with the same properties. To do this, it checks
the existing vxlan udp socket. Since commit 1c51a9159dde, the creation of
the vxlan socket is done only when the interface is set up, thus it breaks
that test.

Example:
$ ip l a vxlan10 type vxlan id 10 group 239.0.0.10 dev eth0 dstport 0
$ ip l a vxlan11 type vxlan id 10 group 239.0.0.10 dev eth0 dstport 0
$ ip -br l | grep vxlan
vxlan10          DOWN           f2:55:1c:6a:fb:00 <BROADCAST,MULTICAST>
vxlan11          DOWN           7a:cb:b9:38:59:0d <BROADCAST,MULTICAST>

Instead of checking sockets, let's loop over the vxlan iface list.

Fixes: 1c51a9159dde ("vxlan: fix race caused by dropping rtnl_unlock")
Reported-by: Thomas Faivre <thomas.faivre@6wind.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 0085b8d..940f78e 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2581,7 +2581,7 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev,
 			 struct nlattr *tb[], struct nlattr *data[])
 {
 	struct vxlan_net *vn = net_generic(src_net, vxlan_net_id);
-	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_dev *vxlan = netdev_priv(dev), *tmp;
 	struct vxlan_rdst *dst = &vxlan->default_dst;
 	__u32 vni;
 	int err;
@@ -2714,9 +2714,13 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev,
 	if (data[IFLA_VXLAN_REMCSUM_NOPARTIAL])
 		vxlan->flags |= VXLAN_F_REMCSUM_NOPARTIAL;
 
-	if (vxlan_find_vni(src_net, vni, use_ipv6 ? AF_INET6 : AF_INET,
-			   vxlan->dst_port, vxlan->flags)) {
-		pr_info("duplicate VNI %u\n", vni);
+	list_for_each_entry(tmp, &vn->vxlan_list, next) {
+		if (tmp->default_dst.remote_vni == vni &&
+		    (tmp->default_dst.remote_ip.sa.sa_family == AF_INET6 ||
+		     tmp->saddr.sa.sa_family == AF_INET6) == use_ipv6 &&
+		    tmp->dst_port == vxlan->dst_port &&
+		    (tmp->flags & VXLAN_F_RCV_FLAGS) ==
+		    (vxlan->flags & VXLAN_F_RCV_FLAGS))
 		return -EEXIST;
 	}
 
-- 
2.1.0


From 95c34fece8119372533aaf890ac9fb769f576af2 Mon Sep 17 00:00:00 2001
From: Sasha Levin <sasha.levin@oracle.com>
Date: Thu, 7 Jan 2016 14:52:43 -0500
Subject: [PATCH 13/39] net: sctp: prevent writes to cookie_hmac_alg from
 accessing invalid memory

[ Upstream commit 320f1a4a175e7cd5d3f006f92b4d4d3e2cbb7bb5 ]

proc_dostring() needs an initialized destination string, while the one
provided in proc_sctp_do_hmac_alg() contains stack garbage.

Thus, writing to cookie_hmac_alg would strlen() that garbage and end up
accessing invalid memory.

Fixes: 3c68198e7 ("sctp: Make hmac algorithm selection for cookie generation dynamic")
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sysctl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index 26d50c5..3e0fc51 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -320,7 +320,7 @@ static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write,
 	struct ctl_table tbl;
 	bool changed = false;
 	char *none = "none";
-	char tmp[8];
+	char tmp[8] = {0};
 	int ret;
 
 	memset(&tbl, 0, sizeof(struct ctl_table));
-- 
2.1.0


From f28fb9dcd62bb72cafdf27236df99108e6081202 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 8 Jan 2016 09:35:51 -0800
Subject: [PATCH 14/39] ipv6: tcp: add rcu locking in tcp_v6_send_synack()

[ Upstream commit 3e4006f0b86a5ae5eb0e8215f9a9e1db24506977 ]

When first SYNACK is sent, we already hold rcu_read_lock(), but this
is not true if a SYNACK is retransmitted, as a timer (soft) interrupt
does not hold rcu_read_lock()

Fixes: 45f6fad84cc30 ("ipv6: add complete rcu protection around np->opt")
Reported-by: Dave Jones <davej@codemonkey.org.uk>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/tcp_ipv6.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index c1938ad..c1147ac 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -465,8 +465,10 @@ static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst,
 			fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));
 
 		skb_set_queue_mapping(skb, queue_mapping);
+		rcu_read_lock();
 		err = ip6_xmit(sk, skb, fl6, rcu_dereference(np->opt),
 			       np->tclass);
+		rcu_read_unlock();
 		err = net_xmit_eval(err);
 	}
 
-- 
2.1.0


From 75001d6df9aed1838ce0f9f3c3e837449a242dc0 Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Mon, 11 Jan 2016 13:42:43 -0500
Subject: [PATCH 15/39] tcp_yeah: don't set ssthresh below 2

[ Upstream commit 83d15e70c4d8909d722c0d64747d8fb42e38a48f ]

For tcp_yeah, use an ssthresh floor of 2, the same floor used by Reno
and CUBIC, per RFC 5681 (equation 4).

tcp_yeah_ssthresh() was sometimes returning a 0 or negative ssthresh
value if the intended reduction is as big or bigger than the current
cwnd. Congestion control modules should never return a zero or
negative ssthresh. A zero ssthresh generally results in a zero cwnd,
causing the connection to stall. A negative ssthresh value will be
interpreted as a u32 and will set a target cwnd for PRR near 4
billion.

Oleksandr Natalenko reported that a system using tcp_yeah with ECN
could see a warning about a prior_cwnd of 0 in
tcp_cwnd_reduction(). Testing verified that this was due to
tcp_yeah_ssthresh() misbehaving in this way.

Reported-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_yeah.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c
index 17d3566..3e6a472 100644
--- a/net/ipv4/tcp_yeah.c
+++ b/net/ipv4/tcp_yeah.c
@@ -219,7 +219,7 @@ static u32 tcp_yeah_ssthresh(struct sock *sk)
 	yeah->fast_count = 0;
 	yeah->reno_count = max(yeah->reno_count>>1, 2U);
 
-	return tp->snd_cwnd - reduction;
+	return max_t(int, tp->snd_cwnd - reduction, 2);
 }
 
 static struct tcp_congestion_ops tcp_yeah __read_mostly = {
-- 
2.1.0


From 905d5cb4f5072363212c4646df024929fa69182c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Michal=20Kube=C4=8Dek?= <mkubecek@suse.cz>
Date: Mon, 11 Jan 2016 07:50:30 +0100
Subject: [PATCH 16/39] udp: disallow UFO for sockets with SO_NO_CHECK option

[ Upstream commit 40ba330227ad00b8c0cdf2f425736ff9549cc423 ]

Commit acf8dd0a9d0b ("udp: only allow UFO for packets from SOCK_DGRAM
sockets") disallows UFO for packets sent from raw sockets. We need to do
the same also for SOCK_DGRAM sockets with SO_NO_CHECK options, even if
for a bit different reason: while such socket would override the
CHECKSUM_PARTIAL set by ip_ufo_append_data(), gso_size is still set and
bad offloading flags warning is triggered in __skb_gso_segment().

In the IPv6 case, SO_NO_CHECK option is ignored but we need to disallow
UFO for packets sent by sockets with UDP_NO_CHECK6_TX option.

Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Tested-by: Shannon Nelson <shannon.nelson@intel.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_output.c  | 2 +-
 net/ipv6/ip6_output.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index c65b93a..fe16f41 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -893,7 +893,7 @@ static int __ip_append_data(struct sock *sk,
 	if (((length > mtu) || (skb && skb_is_gso(skb))) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
 	    (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len &&
-	    (sk->sk_type == SOCK_DGRAM)) {
+	    (sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx) {
 		err = ip_ufo_append_data(sk, queue, getfrag, from, length,
 					 hh_len, fragheaderlen, transhdrlen,
 					 maxfraglen, flags);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index bc09cb9..f50228b 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1329,7 +1329,7 @@ emsgsize:
 	     (skb && skb_is_gso(skb))) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
 	    (rt->dst.dev->features & NETIF_F_UFO) &&
-	    (sk->sk_type == SOCK_DGRAM)) {
+	    (sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk)) {
 		err = ip6_ufo_append_data(sk, queue, getfrag, from, length,
 					  hh_len, fragheaderlen,
 					  transhdrlen, mtu, flags, rt);
-- 
2.1.0


From 5d585ccac68e5140ba8d07d49566a9a7963a6134 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <koct9i@gmail.com>
Date: Fri, 8 Jan 2016 15:21:46 +0300
Subject: [PATCH 17/39] net: preserve IP control block during GSO segmentation

[ Upstream commit 9207f9d45b0ad071baa128e846d7e7ed85016df3 ]

Skb_gso_segment() uses skb control block during segmentation.
This patch adds 32-bytes room for previous control block which
will be copied into all resulting segments.

This patch fixes kernel crash during fragmenting forwarded packets.
Fragmentation requires valid IP CB in skb for clearing ip options.
Also patch removes custom save/restore in ovs code, now it's redundant.

Signed-off-by: Konstantin Khlebnikov <koct9i@gmail.com>
Link: http://lkml.kernel.org/r/CALYGNiP-0MZ-FExV2HutTvE9U-QQtkKSoE--KN=JQE5STYsjAA@mail.gmail.com
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h     | 3 ++-
 net/core/dev.c             | 5 +++++
 net/ipv4/ip_output.c       | 1 +
 net/openvswitch/datapath.c | 5 +----
 net/xfrm/xfrm_output.c     | 2 ++
 5 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 4307e20..1f17abe 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3320,7 +3320,8 @@ struct skb_gso_cb {
 	int	encap_level;
 	__u16	csum_start;
 };
-#define SKB_GSO_CB(skb) ((struct skb_gso_cb *)(skb)->cb)
+#define SKB_SGO_CB_OFFSET	32
+#define SKB_GSO_CB(skb) ((struct skb_gso_cb *)((skb)->cb + SKB_SGO_CB_OFFSET))
 
 static inline int skb_tnl_header_len(const struct sk_buff *inner_skb)
 {
diff --git a/net/core/dev.c b/net/core/dev.c
index a42b232..185a339 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2479,6 +2479,8 @@ static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path)
  *
  *	It may return NULL if the skb requires no segmentation.  This is
  *	only possible when GSO is used for verifying header integrity.
+ *
+ *	Segmentation preserves SKB_SGO_CB_OFFSET bytes of previous skb cb.
  */
 struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
 				  netdev_features_t features, bool tx_path)
@@ -2493,6 +2495,9 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
 			return ERR_PTR(err);
 	}
 
+	BUILD_BUG_ON(SKB_SGO_CB_OFFSET +
+		     sizeof(*SKB_GSO_CB(skb)) > sizeof(skb->cb));
+
 	SKB_GSO_CB(skb)->mac_offset = skb_headroom(skb);
 	SKB_GSO_CB(skb)->encap_level = 0;
 
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index fe16f41..51573f8 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -235,6 +235,7 @@ static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb)
 	 * from host network stack.
 	 */
 	features = netif_skb_features(skb);
+	BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET);
 	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
 	if (IS_ERR_OR_NULL(segs)) {
 		kfree_skb(skb);
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 27e1496..b3fe02a 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -337,12 +337,10 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
 	unsigned short gso_type = skb_shinfo(skb)->gso_type;
 	struct sw_flow_key later_key;
 	struct sk_buff *segs, *nskb;
-	struct ovs_skb_cb ovs_cb;
 	int err;
 
-	ovs_cb = *OVS_CB(skb);
+	BUILD_BUG_ON(sizeof(*OVS_CB(skb)) > SKB_SGO_CB_OFFSET);
 	segs = __skb_gso_segment(skb, NETIF_F_SG, false);
-	*OVS_CB(skb) = ovs_cb;
 	if (IS_ERR(segs))
 		return PTR_ERR(segs);
 	if (segs == NULL)
@@ -360,7 +358,6 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
 	/* Queue all of the segments. */
 	skb = segs;
 	do {
-		*OVS_CB(skb) = ovs_cb;
 		if (gso_type & SKB_GSO_UDP && skb != segs)
 			key = &later_key;
 
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index fbcedbe..5097dce 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -153,6 +153,8 @@ static int xfrm_output_gso(struct sock *sk, struct sk_buff *skb)
 {
 	struct sk_buff *segs;
 
+	BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET);
+	BUILD_BUG_ON(sizeof(*IP6CB(skb)) > SKB_SGO_CB_OFFSET);
 	segs = skb_gso_segment(skb, 0);
 	kfree_skb(skb);
 	if (IS_ERR(segs))
-- 
2.1.0


From 0064fb4327730b6f1a3002d7430108b7a6fa8e5d Mon Sep 17 00:00:00 2001
From: Karl Heiss <kheiss@gmail.com>
Date: Mon, 11 Jan 2016 08:28:43 -0500
Subject: [PATCH 18/39] bonding: Prevent IPv6 link local address on enslaved
 devices

[ Upstream commit 03d84a5f83a67e692af00a3d3901e7820e3e84d5 ]

Commit 1f718f0f4f97 ("bonding: populate neighbour's private on enslave")
undoes the fix provided by commit c2edacf80e15 ("bonding / ipv6: no addrconf
for slaves separately from master") by effectively setting the slave flag
after the slave has been opened.  If the slave comes up quickly enough, it
will go through the IPv6 addrconf before the slave flag has been set and
will get a link local IPv6 address.

In order to ensure that addrconf knows to ignore the slave devices on state
change, set IFF_SLAVE before dev_open() during bonding enslavement.

Fixes: 1f718f0f4f97 ("bonding: populate neighbour's private on enslave")
Signed-off-by: Karl Heiss <kheiss@gmail.com>
Signed-off-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Reviewed-by: Jarod Wilson <jarod@redhat.com>
Signed-off-by: Andy Gospodarek <gospo@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 16d87bf..72ba774 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1194,7 +1194,6 @@ static int bond_master_upper_dev_link(struct net_device *bond_dev,
 	err = netdev_master_upper_dev_link_private(slave_dev, bond_dev, slave);
 	if (err)
 		return err;
-	slave_dev->flags |= IFF_SLAVE;
 	rtmsg_ifinfo(RTM_NEWLINK, slave_dev, IFF_SLAVE, GFP_KERNEL);
 	return 0;
 }
@@ -1452,6 +1451,9 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 		}
 	}
 
+	/* set slave flag before open to prevent IPv6 addrconf */
+	slave_dev->flags |= IFF_SLAVE;
+
 	/* open the slave since the application closed it */
 	res = dev_open(slave_dev);
 	if (res) {
@@ -1712,6 +1714,7 @@ err_close:
 	dev_close(slave_dev);
 
 err_restore_mac:
+	slave_dev->flags &= ~IFF_SLAVE;
 	if (!bond->params.fail_over_mac ||
 	    BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
 		/* XXX TODO - fom follow mode needs to change master's
-- 
2.1.0


From 0a9f2019ba2c5602e33d3dbf8611e9917c79a3e6 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 12 Jan 2016 08:58:00 -0800
Subject: [PATCH 19/39] phonet: properly unshare skbs in phonet_rcv()

[ Upstream commit 7aaed57c5c2890634cfadf725173c7c68ea4cb4f ]

Ivaylo Dimitrov reported a regression caused by commit 7866a621043f
("dev: add per net_device packet type chains").

skb->dev becomes NULL and we crash in __netif_receive_skb_core().

Before above commit, different kind of bugs or corruptions could happen
without major crash.

But the root cause is that phonet_rcv() can queue skb without checking
if skb is shared or not.

Many thanks to Ivaylo Dimitrov for his help, diagnosis and tests.

Reported-by: Ivaylo Dimitrov <ivo.g.dimitrov.75@gmail.com>
Tested-by: Ivaylo Dimitrov <ivo.g.dimitrov.75@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Remi Denis-Courmont <courmisch@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/phonet/af_phonet.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c
index 32ab87d..11d0b29 100644
--- a/net/phonet/af_phonet.c
+++ b/net/phonet/af_phonet.c
@@ -377,6 +377,10 @@ static int phonet_rcv(struct sk_buff *skb, struct net_device *dev,
 	struct sockaddr_pn sa;
 	u16 len;
 
+	skb = skb_share_check(skb, GFP_ATOMIC);
+	if (!skb)
+		return NET_RX_DROP;
+
 	/* check we have at least a full Phonet header */
 	if (!pskb_pull(skb, sizeof(struct phonethdr)))
 		goto out;
-- 
2.1.0


From 79c4c85bd9795eb6bb49923164cd0aef09a593d5 Mon Sep 17 00:00:00 2001
From: Rabin Vincent <rabin@rab.in>
Date: Tue, 12 Jan 2016 20:17:08 +0100
Subject: [PATCH 20/39] net: bpf: reject invalid shifts

[ Upstream commit 229394e8e62a4191d592842cf67e80c62a492937 ]

On ARM64, a BUG() is triggered in the eBPF JIT if a filter with a
constant shift that can't be encoded in the immediate field of the
UBFM/SBFM instructions is passed to the JIT.  Since these shifts
amounts, which are negative or >= regsize, are invalid, reject them in
the eBPF verifier and the classic BPF filter checker, for all
architectures.

Signed-off-by: Rabin Vincent <rabin@rab.in>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c | 10 ++++++++++
 net/core/filter.c     |  5 +++++
 2 files changed, 15 insertions(+)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 47dcd3a..141d562 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1019,6 +1019,16 @@ static int check_alu_op(struct reg_state *regs, struct bpf_insn *insn)
 			return -EINVAL;
 		}
 
+		if ((opcode == BPF_LSH || opcode == BPF_RSH ||
+		     opcode == BPF_ARSH) && BPF_SRC(insn->code) == BPF_K) {
+			int size = BPF_CLASS(insn->code) == BPF_ALU64 ? 64 : 32;
+
+			if (insn->imm < 0 || insn->imm >= size) {
+				verbose("invalid shift %d\n", insn->imm);
+				return -EINVAL;
+			}
+		}
+
 		/* pattern match 'bpf_add Rx, imm' instruction */
 		if (opcode == BPF_ADD && BPF_CLASS(insn->code) == BPF_ALU64 &&
 		    regs[insn->dst_reg].type == FRAME_PTR &&
diff --git a/net/core/filter.c b/net/core/filter.c
index 0fa2613..238bb3f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -775,6 +775,11 @@ int bpf_check_classic(const struct sock_filter *filter, unsigned int flen)
 			if (ftest->k == 0)
 				return -EINVAL;
 			break;
+		case BPF_ALU | BPF_LSH | BPF_K:
+		case BPF_ALU | BPF_RSH | BPF_K:
+			if (ftest->k >= 32)
+				return -EINVAL;
+			break;
 		case BPF_LD | BPF_MEM:
 		case BPF_LDX | BPF_MEM:
 		case BPF_ST:
-- 
2.1.0


From ccff5d1166b857799270e2a69c47b9c52609a0c6 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 15 Jan 2016 04:56:56 -0800
Subject: [PATCH 21/39] ipv6: update skb->csum when CE mark is propagated

[ Upstream commit 34ae6a1aa0540f0f781dd265366036355fdc8930 ]

When a tunnel decapsulates the outer header, it has to comply
with RFC 6080 and eventually propagate CE mark into inner header.

It turns out IP6_ECN_set_ce() does not correctly update skb->csum
for CHECKSUM_COMPLETE packets, triggering infamous "hw csum failure"
messages and stack traces.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_ecn.h       | 19 ++++++++++++++++---
 net/ipv6/xfrm6_mode_tunnel.c |  2 +-
 2 files changed, 17 insertions(+), 4 deletions(-)

diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h
index 84b2083..0dc0a51 100644
--- a/include/net/inet_ecn.h
+++ b/include/net/inet_ecn.h
@@ -111,11 +111,24 @@ static inline void ipv4_copy_dscp(unsigned int dscp, struct iphdr *inner)
 
 struct ipv6hdr;
 
-static inline int IP6_ECN_set_ce(struct ipv6hdr *iph)
+/* Note:
+ * IP_ECN_set_ce() has to tweak IPV4 checksum when setting CE,
+ * meaning both changes have no effect on skb->csum if/when CHECKSUM_COMPLETE
+ * In IPv6 case, no checksum compensates the change in IPv6 header,
+ * so we have to update skb->csum.
+ */
+static inline int IP6_ECN_set_ce(struct sk_buff *skb, struct ipv6hdr *iph)
 {
+	__be32 from, to;
+
 	if (INET_ECN_is_not_ect(ipv6_get_dsfield(iph)))
 		return 0;
-	*(__be32*)iph |= htonl(INET_ECN_CE << 20);
+
+	from = *(__be32 *)iph;
+	to = from | htonl(INET_ECN_CE << 20);
+	*(__be32 *)iph = to;
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		skb->csum = csum_add(csum_sub(skb->csum, from), to);
 	return 1;
 }
 
@@ -142,7 +155,7 @@ static inline int INET_ECN_set_ce(struct sk_buff *skb)
 	case cpu_to_be16(ETH_P_IPV6):
 		if (skb_network_header(skb) + sizeof(struct ipv6hdr) <=
 		    skb_tail_pointer(skb))
-			return IP6_ECN_set_ce(ipv6_hdr(skb));
+			return IP6_ECN_set_ce(skb, ipv6_hdr(skb));
 		break;
 	}
 
diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c
index 901ef6f..5266ad2 100644
--- a/net/ipv6/xfrm6_mode_tunnel.c
+++ b/net/ipv6/xfrm6_mode_tunnel.c
@@ -24,7 +24,7 @@ static inline void ipip6_ecn_decapsulate(struct sk_buff *skb)
 	struct ipv6hdr *inner_iph = ipipv6_hdr(skb);
 
 	if (INET_ECN_is_ce(ipv6_get_dsfield(outer_iph)))
-		IP6_ECN_set_ce(inner_iph);
+		IP6_ECN_set_ce(skb, inner_iph);
 }
 
 /* Add encapsulation header.
-- 
2.1.0


From e5f96e519b065aad930157987f834a6dfbe3dd20 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Fri, 15 Jan 2016 19:03:54 +0100
Subject: [PATCH 22/39] bridge: fix lockdep addr_list_lock false positive splat

[ Upstream commit c6894dec8ea9ae05747124dce98b3b5c2e69b168 ]

After promisc mode management was introduced a bridge device could do
dev_set_promiscuity from its ndo_change_rx_flags() callback which in
turn can be called after the bridge's addr_list_lock has been taken
(e.g. by dev_uc_add). This causes a false positive lockdep splat because
the port interfaces' addr_list_lock is taken when br_manage_promisc()
runs after the bridge's addr list lock was already taken.
To remove the false positive introduce a custom bridge addr_list_lock
class and set it on bridge init.
A simple way to reproduce this is with the following:
$ brctl addbr br0
$ ip l add l br0 br0.100 type vlan id 100
$ ip l set br0 up
$ ip l set br0.100 up
$ echo 1 > /sys/class/net/br0/bridge/vlan_filtering
$ brctl addif br0 eth0
Splat:
[   43.684325] =============================================
[   43.684485] [ INFO: possible recursive locking detected ]
[   43.684636] 4.4.0-rc8+ #54 Not tainted
[   43.684755] ---------------------------------------------
[   43.684906] brctl/1187 is trying to acquire lock:
[   43.685047]  (_xmit_ETHER){+.....}, at: [<ffffffff8150169e>] dev_set_rx_mode+0x1e/0x40
[   43.685460]  but task is already holding lock:
[   43.685618]  (_xmit_ETHER){+.....}, at: [<ffffffff815072a7>] dev_uc_add+0x27/0x80
[   43.686015]  other info that might help us debug this:
[   43.686316]  Possible unsafe locking scenario:

[   43.686743]        CPU0
[   43.686967]        ----
[   43.687197]   lock(_xmit_ETHER);
[   43.687544]   lock(_xmit_ETHER);
[   43.687886] *** DEADLOCK ***

[   43.688438]  May be due to missing lock nesting notation

[   43.688882] 2 locks held by brctl/1187:
[   43.689134]  #0:  (rtnl_mutex){+.+.+.}, at: [<ffffffff81510317>] rtnl_lock+0x17/0x20
[   43.689852]  #1:  (_xmit_ETHER){+.....}, at: [<ffffffff815072a7>] dev_uc_add+0x27/0x80
[   43.690575] stack backtrace:
[   43.690970] CPU: 0 PID: 1187 Comm: brctl Not tainted 4.4.0-rc8+ #54
[   43.691270] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.8.1-20150318_183358- 04/01/2014
[   43.691770]  ffffffff826a25c0 ffff8800369fb8e0 ffffffff81360ceb ffffffff826a25c0
[   43.692425]  ffff8800369fb9b8 ffffffff810d0466 ffff8800369fb968 ffffffff81537139
[   43.693071]  ffff88003a08c880 0000000000000000 00000000ffffffff 0000000002080020
[   43.693709] Call Trace:
[   43.693931]  [<ffffffff81360ceb>] dump_stack+0x4b/0x70
[   43.694199]  [<ffffffff810d0466>] __lock_acquire+0x1e46/0x1e90
[   43.694483]  [<ffffffff81537139>] ? netlink_broadcast_filtered+0x139/0x3e0
[   43.694789]  [<ffffffff8153b5da>] ? nlmsg_notify+0x5a/0xc0
[   43.695064]  [<ffffffff810d10f5>] lock_acquire+0xe5/0x1f0
[   43.695340]  [<ffffffff8150169e>] ? dev_set_rx_mode+0x1e/0x40
[   43.695623]  [<ffffffff815edea5>] _raw_spin_lock_bh+0x45/0x80
[   43.695901]  [<ffffffff8150169e>] ? dev_set_rx_mode+0x1e/0x40
[   43.696180]  [<ffffffff8150169e>] dev_set_rx_mode+0x1e/0x40
[   43.696460]  [<ffffffff8150189c>] dev_set_promiscuity+0x3c/0x50
[   43.696750]  [<ffffffffa0586845>] br_port_set_promisc+0x25/0x50 [bridge]
[   43.697052]  [<ffffffffa05869aa>] br_manage_promisc+0x8a/0xe0 [bridge]
[   43.697348]  [<ffffffffa05826ee>] br_dev_change_rx_flags+0x1e/0x20 [bridge]
[   43.697655]  [<ffffffff81501532>] __dev_set_promiscuity+0x132/0x1f0
[   43.697943]  [<ffffffff81501672>] __dev_set_rx_mode+0x82/0x90
[   43.698223]  [<ffffffff815072de>] dev_uc_add+0x5e/0x80
[   43.698498]  [<ffffffffa05b3c62>] vlan_device_event+0x542/0x650 [8021q]
[   43.698798]  [<ffffffff8109886d>] notifier_call_chain+0x5d/0x80
[   43.699083]  [<ffffffff810988b6>] raw_notifier_call_chain+0x16/0x20
[   43.699374]  [<ffffffff814f456e>] call_netdevice_notifiers_info+0x6e/0x80
[   43.699678]  [<ffffffff814f4596>] call_netdevice_notifiers+0x16/0x20
[   43.699973]  [<ffffffffa05872be>] br_add_if+0x47e/0x4c0 [bridge]
[   43.700259]  [<ffffffffa058801e>] add_del_if+0x6e/0x80 [bridge]
[   43.700548]  [<ffffffffa0588b5f>] br_dev_ioctl+0xaf/0xc0 [bridge]
[   43.700836]  [<ffffffff8151a7ac>] dev_ifsioc+0x30c/0x3c0
[   43.701106]  [<ffffffff8151aac9>] dev_ioctl+0xf9/0x6f0
[   43.701379]  [<ffffffff81254345>] ? mntput_no_expire+0x5/0x450
[   43.701665]  [<ffffffff812543ee>] ? mntput_no_expire+0xae/0x450
[   43.701947]  [<ffffffff814d7b02>] sock_do_ioctl+0x42/0x50
[   43.702219]  [<ffffffff814d8175>] sock_ioctl+0x1e5/0x290
[   43.702500]  [<ffffffff81242d0b>] do_vfs_ioctl+0x2cb/0x5c0
[   43.702771]  [<ffffffff81243079>] SyS_ioctl+0x79/0x90
[   43.703033]  [<ffffffff815eebb6>] entry_SYSCALL_64_fastpath+0x16/0x7a

CC: Vlad Yasevich <vyasevic@redhat.com>
CC: Stephen Hemminger <stephen@networkplumber.org>
CC: Bridge list <bridge@lists.linux-foundation.org>
CC: Andy Gospodarek <gospo@cumulusnetworks.com>
CC: Roopa Prabhu <roopa@cumulusnetworks.com>
Fixes: 2796d0c648c9 ("bridge: Automatically manage port promiscuous mode.")
Reported-by: Andy Gospodarek <gospo@cumulusnetworks.com>
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_device.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 4ff77a1..3d6c8e2 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -28,6 +28,8 @@
 const struct nf_br_ops __rcu *nf_br_ops __read_mostly;
 EXPORT_SYMBOL_GPL(nf_br_ops);
 
+static struct lock_class_key bridge_netdev_addr_lock_key;
+
 /* net device transmit always called with BH disabled */
 netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 {
@@ -87,6 +89,11 @@ out:
 	return NETDEV_TX_OK;
 }
 
+static void br_set_lockdep_class(struct net_device *dev)
+{
+	lockdep_set_class(&dev->addr_list_lock, &bridge_netdev_addr_lock_key);
+}
+
 static int br_dev_init(struct net_device *dev)
 {
 	struct net_bridge *br = netdev_priv(dev);
@@ -99,6 +106,7 @@ static int br_dev_init(struct net_device *dev)
 	err = br_vlan_init(br);
 	if (err)
 		free_percpu(br->stats);
+	br_set_lockdep_class(dev);
 
 	return err;
 }
-- 
2.1.0


From 181884b03cfbc831836cdf8b0c4aef25040132e1 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 19 Sep 2015 09:08:34 -0700
Subject: [PATCH 23/39] tcp/dccp: fix timewait races in timer handling

[ Upstream commit ed2e923945892a8372ab70d2f61d364b0b6d9054 ]

When creating a timewait socket, we need to arm the timer before
allowing other cpus to find it. The signal allowing cpus to find
the socket is setting tw_refcnt to non zero value.

As we set tw_refcnt in __inet_twsk_hashdance(), we therefore need to
call inet_twsk_schedule() first.

This also means we need to remove tw_refcnt changes from
inet_twsk_schedule() and let the caller handle it.

Note that because we use mod_timer_pinned(), we have the guarantee
the timer wont expire before we set tw_refcnt as we run in BH context.

To make things more readable I introduced inet_twsk_reschedule() helper.

When rearming the timer, we can use mod_timer_pending() to make sure
we do not rearm a canceled timer.

Note: This bug can possibly trigger if packets of a flow can hit
multiple cpus. This does not normally happen, unless flow steering
is broken somehow. This explains this bug was spotted ~5 months after
its introduction.

A similar fix is needed for SYN_RECV sockets in reqsk_queue_hash_req(),
but will be provided in a separate patch for proper tracking.

Fixes: 789f558cfb36 ("tcp/dccp: get rid of central timewait timer")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Ying Cai <ycai@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_timewait_sock.h | 14 +++++++++++++-
 net/dccp/minisocks.c             |  4 ++--
 net/ipv4/inet_timewait_sock.c    | 16 ++++++++++------
 net/ipv4/tcp_minisocks.c         | 13 ++++++-------
 4 files changed, 31 insertions(+), 16 deletions(-)

diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h
index 360c480..95a5a77 100644
--- a/include/net/inet_timewait_sock.h
+++ b/include/net/inet_timewait_sock.h
@@ -112,7 +112,19 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk,
 void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
 			   struct inet_hashinfo *hashinfo);
 
-void inet_twsk_schedule(struct inet_timewait_sock *tw, const int timeo);
+void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo,
+			  bool rearm);
+
+static void inline inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo)
+{
+	__inet_twsk_schedule(tw, timeo, false);
+}
+
+static void inline inet_twsk_reschedule(struct inet_timewait_sock *tw, int timeo)
+{
+	__inet_twsk_schedule(tw, timeo, true);
+}
+
 void inet_twsk_deschedule(struct inet_timewait_sock *tw);
 
 void inet_twsk_purge(struct inet_hashinfo *hashinfo,
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index 30addee..838f524 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -48,8 +48,6 @@ void dccp_time_wait(struct sock *sk, int state, int timeo)
 			tw->tw_ipv6only = sk->sk_ipv6only;
 		}
 #endif
-		/* Linkage updates. */
-		__inet_twsk_hashdance(tw, sk, &dccp_hashinfo);
 
 		/* Get the TIME_WAIT timeout firing. */
 		if (timeo < rto)
@@ -60,6 +58,8 @@ void dccp_time_wait(struct sock *sk, int state, int timeo)
 			timeo = DCCP_TIMEWAIT_LEN;
 
 		inet_twsk_schedule(tw, timeo);
+		/* Linkage updates. */
+		__inet_twsk_hashdance(tw, sk, &dccp_hashinfo);
 		inet_twsk_put(tw);
 	} else {
 		/* Sorry, if we're out of memory, just CLOSE this
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 00ec8d5..bb96c1c 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -153,13 +153,15 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
 	/*
 	 * Step 2: Hash TW into tcp ehash chain.
 	 * Notes :
-	 * - tw_refcnt is set to 3 because :
+	 * - tw_refcnt is set to 4 because :
 	 * - We have one reference from bhash chain.
 	 * - We have one reference from ehash chain.
+	 * - We have one reference from timer.
+	 * - One reference for ourself (our caller will release it).
 	 * We can use atomic_set() because prior spin_lock()/spin_unlock()
 	 * committed into memory all tw fields.
 	 */
-	atomic_set(&tw->tw_refcnt, 1 + 1 + 1);
+	atomic_set(&tw->tw_refcnt, 4);
 	inet_twsk_add_node_rcu(tw, &ehead->chain);
 
 	/* Step 3: Remove SK from hash chain */
@@ -243,7 +245,7 @@ void inet_twsk_deschedule(struct inet_timewait_sock *tw)
 }
 EXPORT_SYMBOL(inet_twsk_deschedule);
 
-void inet_twsk_schedule(struct inet_timewait_sock *tw, const int timeo)
+void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm)
 {
 	/* timeout := RTO * 3.5
 	 *
@@ -271,12 +273,14 @@ void inet_twsk_schedule(struct inet_timewait_sock *tw, const int timeo)
 	 */
 
 	tw->tw_kill = timeo <= 4*HZ;
-	if (!mod_timer_pinned(&tw->tw_timer, jiffies + timeo)) {
-		atomic_inc(&tw->tw_refcnt);
+	if (!rearm) {
+		BUG_ON(mod_timer_pinned(&tw->tw_timer, jiffies + timeo));
 		atomic_inc(&tw->tw_dr->tw_count);
+	} else {
+		mod_timer_pending(&tw->tw_timer, jiffies + timeo);
 	}
 }
-EXPORT_SYMBOL_GPL(inet_twsk_schedule);
+EXPORT_SYMBOL_GPL(__inet_twsk_schedule);
 
 void inet_twsk_purge(struct inet_hashinfo *hashinfo,
 		     struct inet_timewait_death_row *twdr, int family)
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 17e7339..fec2907 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -163,9 +163,9 @@ kill_with_rst:
 		if (tcp_death_row.sysctl_tw_recycle &&
 		    tcptw->tw_ts_recent_stamp &&
 		    tcp_tw_remember_stamp(tw))
-			inet_twsk_schedule(tw, tw->tw_timeout);
+			inet_twsk_reschedule(tw, tw->tw_timeout);
 		else
-			inet_twsk_schedule(tw, TCP_TIMEWAIT_LEN);
+			inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN);
 		return TCP_TW_ACK;
 	}
 
@@ -203,7 +203,7 @@ kill:
 				return TCP_TW_SUCCESS;
 			}
 		}
-		inet_twsk_schedule(tw, TCP_TIMEWAIT_LEN);
+		inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN);
 
 		if (tmp_opt.saw_tstamp) {
 			tcptw->tw_ts_recent	  = tmp_opt.rcv_tsval;
@@ -253,7 +253,7 @@ kill:
 		 * Do not reschedule in the last case.
 		 */
 		if (paws_reject || th->ack)
-			inet_twsk_schedule(tw, TCP_TIMEWAIT_LEN);
+			inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN);
 
 		return tcp_timewait_check_oow_rate_limit(
 			tw, skb, LINUX_MIB_TCPACKSKIPPEDTIMEWAIT);
@@ -324,9 +324,6 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 		} while (0);
 #endif
 
-		/* Linkage updates. */
-		__inet_twsk_hashdance(tw, sk, &tcp_hashinfo);
-
 		/* Get the TIME_WAIT timeout firing. */
 		if (timeo < rto)
 			timeo = rto;
@@ -340,6 +337,8 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 		}
 
 		inet_twsk_schedule(tw, timeo);
+		/* Linkage updates. */
+		__inet_twsk_hashdance(tw, sk, &tcp_hashinfo);
 		inet_twsk_put(tw);
 	} else {
 		/* Sorry, if we're out of memory, just CLOSE this
-- 
2.1.0


From 16f538209644b785e25cf25395202e467978f072 Mon Sep 17 00:00:00 2001
From: Raanan Avargil <raanan.avargil@intel.com>
Date: Thu, 1 Oct 2015 04:48:53 -0700
Subject: [PATCH 24/39] tcp/dccp: fix old style declarations
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 8695a144da9e500a5a60fa34c06694346ec1048f ]

I’m using the compilation flag -Werror=old-style-declaration, which
requires that the “inline” word would come at the beginning of the code
line.

$ make drivers/net/ethernet/intel/e1000e/e1000e.ko
...
include/net/inet_timewait_sock.h:116:1: error: ‘inline’ is not at
beginning of declaration [-Werror=old-style-declaration]
static void inline inet_twsk_schedule(struct inet_timewait_sock *tw, int
timeo)

include/net/inet_timewait_sock.h:121:1: error: ‘inline’ is not at
beginning of declaration [-Werror=old-style-declaration]
static void inline inet_twsk_reschedule(struct inet_timewait_sock *tw,
int timeo)

Fixes: ed2e92394589 ("tcp/dccp: fix timewait races in timer handling")
Signed-off-by: Raanan Avargil <raanan.avargil@intel.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_timewait_sock.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h
index 95a5a77..7682cb2 100644
--- a/include/net/inet_timewait_sock.h
+++ b/include/net/inet_timewait_sock.h
@@ -115,12 +115,12 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
 void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo,
 			  bool rearm);
 
-static void inline inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo)
+static inline void inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo)
 {
 	__inet_twsk_schedule(tw, timeo, false);
 }
 
-static void inline inet_twsk_reschedule(struct inet_timewait_sock *tw, int timeo)
+static inline void inet_twsk_reschedule(struct inet_timewait_sock *tw, int timeo)
 {
 	__inet_twsk_schedule(tw, timeo, true);
 }
-- 
2.1.0


From 75cff6eb608c61f1ab707df9bdc3696b65c64b63 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben@decadent.org.uk>
Date: Sun, 1 Nov 2015 16:21:24 +0000
Subject: [PATCH 25/39] isdn_ppp: Add checks for allocation failure in
 isdn_ppp_open()

[ Upstream commit 0baa57d8dc32db78369d8b5176ef56c5e2e18ab3 ]

Compile-tested only.

Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/i4l/isdn_ppp.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/isdn/i4l/isdn_ppp.c b/drivers/isdn/i4l/isdn_ppp.c
index c4198fa..86f9abe 100644
--- a/drivers/isdn/i4l/isdn_ppp.c
+++ b/drivers/isdn/i4l/isdn_ppp.c
@@ -301,6 +301,8 @@ isdn_ppp_open(int min, struct file *file)
 	is->compflags = 0;
 
 	is->reset = isdn_ppp_ccp_reset_alloc(is);
+	if (!is->reset)
+		return -ENOMEM;
 
 	is->lp = NULL;
 	is->mp_seqno = 0;       /* MP sequence number */
@@ -320,6 +322,10 @@ isdn_ppp_open(int min, struct file *file)
 	 * VJ header compression init
 	 */
 	is->slcomp = slhc_init(16, 16);	/* not necessary for 2. link in bundle */
+	if (!is->slcomp) {
+		isdn_ppp_ccp_reset_free(is);
+		return -ENOMEM;
+	}
 #endif
 #ifdef CONFIG_IPPP_FILTER
 	is->pass_filter = NULL;
-- 
2.1.0


From 761e9104816b6f1e3aeedc838efbd54cd074abf2 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben@decadent.org.uk>
Date: Sun, 1 Nov 2015 16:22:53 +0000
Subject: [PATCH 26/39] ppp, slip: Validate VJ compression slot parameters
 completely
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 4ab42d78e37a294ac7bc56901d563c642e03c4ae ]

Currently slhc_init() treats out-of-range values of rslots and tslots
as equivalent to 0, except that if tslots is too large it will
dereference a null pointer (CVE-2015-7799).

Add a range-check at the top of the function and make it return an
ERR_PTR() on error instead of NULL.  Change the callers accordingly.

Compile-tested only.

Reported-by: 郭永刚 <guoyonggang@360.cn>
References: http://article.gmane.org/gmane.comp.security.oss.general/17908
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/i4l/isdn_ppp.c   | 10 ++++------
 drivers/net/ppp/ppp_generic.c |  6 ++----
 drivers/net/slip/slhc.c       | 12 ++++++++----
 drivers/net/slip/slip.c       |  2 +-
 4 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/drivers/isdn/i4l/isdn_ppp.c b/drivers/isdn/i4l/isdn_ppp.c
index 86f9abe..9c1e8ad 100644
--- a/drivers/isdn/i4l/isdn_ppp.c
+++ b/drivers/isdn/i4l/isdn_ppp.c
@@ -322,9 +322,9 @@ isdn_ppp_open(int min, struct file *file)
 	 * VJ header compression init
 	 */
 	is->slcomp = slhc_init(16, 16);	/* not necessary for 2. link in bundle */
-	if (!is->slcomp) {
+	if (IS_ERR(is->slcomp)) {
 		isdn_ppp_ccp_reset_free(is);
-		return -ENOMEM;
+		return PTR_ERR(is->slcomp);
 	}
 #endif
 #ifdef CONFIG_IPPP_FILTER
@@ -573,10 +573,8 @@ isdn_ppp_ioctl(int min, struct file *file, unsigned int cmd, unsigned long arg)
 			is->maxcid = val;
 #ifdef CONFIG_ISDN_PPP_VJ
 			sltmp = slhc_init(16, val);
-			if (!sltmp) {
-				printk(KERN_ERR "ippp, can't realloc slhc struct\n");
-				return -ENOMEM;
-			}
+			if (IS_ERR(sltmp))
+				return PTR_ERR(sltmp);
 			if (is->slcomp)
 				slhc_free(is->slcomp);
 			is->slcomp = sltmp;
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 9d15566..cfe49a0 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -715,10 +715,8 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 			val &= 0xffff;
 		}
 		vj = slhc_init(val2+1, val+1);
-		if (!vj) {
-			netdev_err(ppp->dev,
-				   "PPP: no memory (VJ compressor)\n");
-			err = -ENOMEM;
+		if (IS_ERR(vj)) {
+			err = PTR_ERR(vj);
 			break;
 		}
 		ppp_lock(ppp);
diff --git a/drivers/net/slip/slhc.c b/drivers/net/slip/slhc.c
index 079f7ad..27ed252 100644
--- a/drivers/net/slip/slhc.c
+++ b/drivers/net/slip/slhc.c
@@ -84,8 +84,9 @@ static long decode(unsigned char **cpp);
 static unsigned char * put16(unsigned char *cp, unsigned short x);
 static unsigned short pull16(unsigned char **cpp);
 
-/* Initialize compression data structure
+/* Allocate compression data structure
  *	slots must be in range 0 to 255 (zero meaning no compression)
+ * Returns pointer to structure or ERR_PTR() on error.
  */
 struct slcompress *
 slhc_init(int rslots, int tslots)
@@ -94,11 +95,14 @@ slhc_init(int rslots, int tslots)
 	register struct cstate *ts;
 	struct slcompress *comp;
 
+	if (rslots < 0 || rslots > 255 || tslots < 0 || tslots > 255)
+		return ERR_PTR(-EINVAL);
+
 	comp = kzalloc(sizeof(struct slcompress), GFP_KERNEL);
 	if (! comp)
 		goto out_fail;
 
-	if ( rslots > 0  &&  rslots < 256 ) {
+	if (rslots > 0) {
 		size_t rsize = rslots * sizeof(struct cstate);
 		comp->rstate = kzalloc(rsize, GFP_KERNEL);
 		if (! comp->rstate)
@@ -106,7 +110,7 @@ slhc_init(int rslots, int tslots)
 		comp->rslot_limit = rslots - 1;
 	}
 
-	if ( tslots > 0  &&  tslots < 256 ) {
+	if (tslots > 0) {
 		size_t tsize = tslots * sizeof(struct cstate);
 		comp->tstate = kzalloc(tsize, GFP_KERNEL);
 		if (! comp->tstate)
@@ -141,7 +145,7 @@ out_free2:
 out_free:
 	kfree(comp);
 out_fail:
-	return NULL;
+	return ERR_PTR(-ENOMEM);
 }
 
 
diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c
index 05387b1..a17d86a 100644
--- a/drivers/net/slip/slip.c
+++ b/drivers/net/slip/slip.c
@@ -164,7 +164,7 @@ static int sl_alloc_bufs(struct slip *sl, int mtu)
 	if (cbuff == NULL)
 		goto err_exit;
 	slcomp = slhc_init(16, 16);
-	if (slcomp == NULL)
+	if (IS_ERR(slcomp))
 		goto err_exit;
 #endif
 	spin_lock_bh(&sl->lock);
-- 
2.1.0


From 6c25b057f24b80ae602cc9ba9ec97882b26d84aa Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Thu, 14 Jan 2016 15:28:19 +0100
Subject: [PATCH 27/39] batman-adv: Avoid recursive call_rcu for
 batadv_bla_claim

[ Upstream commit 63b399272294e7a939cde41792dca38c549f0484 ]

The batadv_claim_free_ref function uses call_rcu to delay the free of the
batadv_bla_claim object until no (already started) rcu_read_lock is enabled
anymore. This makes sure that no context is still trying to access the
object which should be removed. But batadv_bla_claim also contains a
reference to backbone_gw which must be removed.

The reference drop of backbone_gw was done in the call_rcu function
batadv_claim_free_rcu but should actually be done in the
batadv_claim_release function to avoid nested call_rcus. This is important
because rcu_barrier (e.g. batadv_softif_free or batadv_exit) will not
detect the inner call_rcu as relevant for its execution. Otherwise this
barrier will most likely be inserted in the queue before the callback of
the first call_rcu was executed. The caller of rcu_barrier will therefore
continue to run before the inner call_rcu callback finished.

Fixes: 23721387c409 ("batman-adv: add basic bridge loop avoidance code")
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Acked-by: Simon Wunderlich <sw@simonwunderlich.de>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>
Signed-off-by: Antonio Quartulli <a@unstable.cc>
---
 net/batman-adv/bridge_loop_avoidance.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c
index ac4b96e..bd3357e 100644
--- a/net/batman-adv/bridge_loop_avoidance.c
+++ b/net/batman-adv/bridge_loop_avoidance.c
@@ -112,21 +112,17 @@ batadv_backbone_gw_free_ref(struct batadv_bla_backbone_gw *backbone_gw)
 }
 
 /* finally deinitialize the claim */
-static void batadv_claim_free_rcu(struct rcu_head *rcu)
+static void batadv_claim_release(struct batadv_bla_claim *claim)
 {
-	struct batadv_bla_claim *claim;
-
-	claim = container_of(rcu, struct batadv_bla_claim, rcu);
-
 	batadv_backbone_gw_free_ref(claim->backbone_gw);
-	kfree(claim);
+	kfree_rcu(claim, rcu);
 }
 
 /* free a claim, call claim_free_rcu if its the last reference */
 static void batadv_claim_free_ref(struct batadv_bla_claim *claim)
 {
 	if (atomic_dec_and_test(&claim->refcount))
-		call_rcu(&claim->rcu, batadv_claim_free_rcu);
+		batadv_claim_release(claim);
 }
 
 /**
-- 
2.1.0


From fc6f22cf4d942840dbe17cb05169f8084b985542 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Tue, 5 Jan 2016 12:06:19 +0100
Subject: [PATCH 28/39] batman-adv: Avoid recursive call_rcu for batadv_nc_node

[ Upstream commit 44e8e7e91d6c7c7ab19688750f7257292640d1a0 ]

The batadv_nc_node_free_ref function uses call_rcu to delay the free of the
batadv_nc_node object until no (already started) rcu_read_lock is enabled
anymore. This makes sure that no context is still trying to access the
object which should be removed. But batadv_nc_node also contains a
reference to orig_node which must be removed.

The reference drop of orig_node was done in the call_rcu function
batadv_nc_node_free_rcu but should actually be done in the
batadv_nc_node_release function to avoid nested call_rcus. This is
important because rcu_barrier (e.g. batadv_softif_free or batadv_exit) will
not detect the inner call_rcu as relevant for its execution. Otherwise this
barrier will most likely be inserted in the queue before the callback of
the first call_rcu was executed. The caller of rcu_barrier will therefore
continue to run before the inner call_rcu callback finished.

Fixes: d56b1705e28c ("batman-adv: network coding - detect coding nodes and remove these after timeout")
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>
Signed-off-by: Antonio Quartulli <a@unstable.cc>
---
 net/batman-adv/network-coding.c | 19 ++++++++-----------
 1 file changed, 8 insertions(+), 11 deletions(-)

diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c
index a449195c..2fbd3a6 100644
--- a/net/batman-adv/network-coding.c
+++ b/net/batman-adv/network-coding.c
@@ -175,28 +175,25 @@ void batadv_nc_init_orig(struct batadv_orig_node *orig_node)
 }
 
 /**
- * batadv_nc_node_free_rcu - rcu callback to free an nc node and remove
- *  its refcount on the orig_node
- * @rcu: rcu pointer of the nc node
+ * batadv_nc_node_release - release nc_node from lists and queue for free after
+ *  rcu grace period
+ * @nc_node: the nc node to free
  */
-static void batadv_nc_node_free_rcu(struct rcu_head *rcu)
+static void batadv_nc_node_release(struct batadv_nc_node *nc_node)
 {
-	struct batadv_nc_node *nc_node;
-
-	nc_node = container_of(rcu, struct batadv_nc_node, rcu);
 	batadv_orig_node_free_ref(nc_node->orig_node);
-	kfree(nc_node);
+	kfree_rcu(nc_node, rcu);
 }
 
 /**
- * batadv_nc_node_free_ref - decrements the nc node refcounter and possibly
- * frees it
+ * batadv_nc_node_free_ref - decrement the nc node refcounter and possibly
+ *  release it
  * @nc_node: the nc node to free
  */
 static void batadv_nc_node_free_ref(struct batadv_nc_node *nc_node)
 {
 	if (atomic_dec_and_test(&nc_node->refcount))
-		call_rcu(&nc_node->rcu, batadv_nc_node_free_rcu);
+		batadv_nc_node_release(nc_node);
 }
 
 /**
-- 
2.1.0


From ad0491891773ffe992f7efd6250b33a14dbe7ad0 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Tue, 5 Jan 2016 12:06:21 +0100
Subject: [PATCH 29/39] batman-adv: Drop immediate batadv_orig_ifinfo free
 function

[ Upstream commit deed96605f5695cb945e0b3d79429581857a2b9d ]

It is not allowed to free the memory of an object which is part of a list
which is protected by rcu-read-side-critical sections without making sure
that no other context is accessing the object anymore. This usually happens
by removing the references to this object and then waiting until the rcu
grace period is over and no one (allowedly) accesses it anymore.

But the _now functions ignore this completely. They free the object
directly even when a different context still tries to access it. This has
to be avoided and thus these functions must be removed and all functions
have to use batadv_orig_ifinfo_free_ref.

Fixes: 7351a4822d42 ("batman-adv: split out router from orig_node")
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>
Signed-off-by: Antonio Quartulli <a@unstable.cc>
---
 net/batman-adv/originator.c | 59 ++++++++++++++++++++++++---------------------
 1 file changed, 31 insertions(+), 28 deletions(-)

diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index dfae974..8327f46 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -516,76 +516,79 @@ static void batadv_orig_ifinfo_free_rcu(struct rcu_head *rcu)
 }
 
 /**
- * batadv_orig_ifinfo_free_ref - decrement the refcounter and possibly free
- *  the orig_ifinfo (without rcu callback)
+ * batadv_orig_ifinfo_free_ref - decrement the refcounter and possibly release
+ *  the orig_ifinfo
  * @orig_ifinfo: the orig_ifinfo object to release
  */
-static void
-batadv_orig_ifinfo_free_ref_now(struct batadv_orig_ifinfo *orig_ifinfo)
+void batadv_orig_ifinfo_free_ref(struct batadv_orig_ifinfo *orig_ifinfo)
 {
 	if (atomic_dec_and_test(&orig_ifinfo->refcount))
-		batadv_orig_ifinfo_free_rcu(&orig_ifinfo->rcu);
+		call_rcu(&orig_ifinfo->rcu, batadv_orig_ifinfo_free_rcu);
 }
 
 /**
- * batadv_orig_ifinfo_free_ref - decrement the refcounter and possibly free
- *  the orig_ifinfo
- * @orig_ifinfo: the orig_ifinfo object to release
+ * batadv_orig_node_free_rcu - free the orig_node
+ * @rcu: rcu pointer of the orig_node
  */
-void batadv_orig_ifinfo_free_ref(struct batadv_orig_ifinfo *orig_ifinfo)
+static void batadv_orig_node_free_rcu(struct rcu_head *rcu)
 {
-	if (atomic_dec_and_test(&orig_ifinfo->refcount))
-		call_rcu(&orig_ifinfo->rcu, batadv_orig_ifinfo_free_rcu);
+	struct batadv_orig_node *orig_node;
+
+	orig_node = container_of(rcu, struct batadv_orig_node, rcu);
+
+	batadv_mcast_purge_orig(orig_node);
+
+	batadv_frag_purge_orig(orig_node, NULL);
+
+	if (orig_node->bat_priv->bat_algo_ops->bat_orig_free)
+		orig_node->bat_priv->bat_algo_ops->bat_orig_free(orig_node);
+
+	kfree(orig_node->tt_buff);
+	kfree(orig_node);
 }
 
-static void batadv_orig_node_free_rcu(struct rcu_head *rcu)
+/**
+ * batadv_orig_node_release - release orig_node from lists and queue for
+ *  free after rcu grace period
+ * @orig_node: the orig node to free
+ */
+static void batadv_orig_node_release(struct batadv_orig_node *orig_node)
 {
 	struct hlist_node *node_tmp;
 	struct batadv_neigh_node *neigh_node;
-	struct batadv_orig_node *orig_node;
 	struct batadv_orig_ifinfo *orig_ifinfo;
 
-	orig_node = container_of(rcu, struct batadv_orig_node, rcu);
-
 	spin_lock_bh(&orig_node->neigh_list_lock);
 
 	/* for all neighbors towards this originator ... */
 	hlist_for_each_entry_safe(neigh_node, node_tmp,
 				  &orig_node->neigh_list, list) {
 		hlist_del_rcu(&neigh_node->list);
-		batadv_neigh_node_free_ref_now(neigh_node);
+		batadv_neigh_node_free_ref(neigh_node);
 	}
 
 	hlist_for_each_entry_safe(orig_ifinfo, node_tmp,
 				  &orig_node->ifinfo_list, list) {
 		hlist_del_rcu(&orig_ifinfo->list);
-		batadv_orig_ifinfo_free_ref_now(orig_ifinfo);
+		batadv_orig_ifinfo_free_ref(orig_ifinfo);
 	}
 	spin_unlock_bh(&orig_node->neigh_list_lock);
 
-	batadv_mcast_purge_orig(orig_node);
-
 	/* Free nc_nodes */
 	batadv_nc_purge_orig(orig_node->bat_priv, orig_node, NULL);
 
-	batadv_frag_purge_orig(orig_node, NULL);
-
-	if (orig_node->bat_priv->bat_algo_ops->bat_orig_free)
-		orig_node->bat_priv->bat_algo_ops->bat_orig_free(orig_node);
-
-	kfree(orig_node->tt_buff);
-	kfree(orig_node);
+	call_rcu(&orig_node->rcu, batadv_orig_node_free_rcu);
 }
 
 /**
  * batadv_orig_node_free_ref - decrement the orig node refcounter and possibly
- * schedule an rcu callback for freeing it
+ *  release it
  * @orig_node: the orig node to free
  */
 void batadv_orig_node_free_ref(struct batadv_orig_node *orig_node)
 {
 	if (atomic_dec_and_test(&orig_node->refcount))
-		call_rcu(&orig_node->rcu, batadv_orig_node_free_rcu);
+		batadv_orig_node_release(orig_node);
 }
 
 /**
-- 
2.1.0


From 52067d6122137a91d26588c104017e827d1f5929 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Tue, 5 Jan 2016 12:06:22 +0100
Subject: [PATCH 30/39] batman-adv: Drop immediate batadv_neigh_node free
 function

[ Upstream commit 2baa753c276f27f8e844637561ad597867aa6fb6 ]

It is not allowed to free the memory of an object which is part of a list
which is protected by rcu-read-side-critical sections without making sure
that no other context is accessing the object anymore. This usually happens
by removing the references to this object and then waiting until the rcu
grace period is over and no one (allowedly) accesses it anymore.

But the _now functions ignore this completely. They free the object
directly even when a different context still tries to access it. This has
to be avoided and thus these functions must be removed and all functions
have to use batadv_neigh_node_free_ref.

Fixes: 89652331c00f ("batman-adv: split tq information in neigh_node struct")
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>
Signed-off-by: Antonio Quartulli <a@unstable.cc>
---
 net/batman-adv/originator.c | 33 ++++++++++-----------------------
 1 file changed, 10 insertions(+), 23 deletions(-)

diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index 8327f46..c816c66 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -210,20 +210,8 @@ static void batadv_neigh_node_free_rcu(struct rcu_head *rcu)
 }
 
 /**
- * batadv_neigh_node_free_ref_now - decrement the neighbors refcounter
- *  and possibly free it (without rcu callback)
- * @neigh_node: neigh neighbor to free
- */
-static void
-batadv_neigh_node_free_ref_now(struct batadv_neigh_node *neigh_node)
-{
-	if (atomic_dec_and_test(&neigh_node->refcount))
-		batadv_neigh_node_free_rcu(&neigh_node->rcu);
-}
-
-/**
  * batadv_neigh_node_free_ref - decrement the neighbors refcounter
- *  and possibly free it
+ *  and possibly release it
  * @neigh_node: neigh neighbor to free
  */
 void batadv_neigh_node_free_ref(struct batadv_neigh_node *neigh_node)
@@ -495,24 +483,23 @@ batadv_neigh_node_get(const struct batadv_orig_node *orig_node,
 }
 
 /**
- * batadv_orig_ifinfo_free_rcu - free the orig_ifinfo object
- * @rcu: rcu pointer of the orig_ifinfo object
+ * batadv_orig_ifinfo_release - release orig_ifinfo from lists and queue for
+ *  free after rcu grace period
+ * @orig_ifinfo: the orig_ifinfo object to release
  */
-static void batadv_orig_ifinfo_free_rcu(struct rcu_head *rcu)
+static void batadv_orig_ifinfo_release(struct batadv_orig_ifinfo *orig_ifinfo)
 {
-	struct batadv_orig_ifinfo *orig_ifinfo;
 	struct batadv_neigh_node *router;
 
-	orig_ifinfo = container_of(rcu, struct batadv_orig_ifinfo, rcu);
-
 	if (orig_ifinfo->if_outgoing != BATADV_IF_DEFAULT)
-		batadv_hardif_free_ref_now(orig_ifinfo->if_outgoing);
+		batadv_hardif_free_ref(orig_ifinfo->if_outgoing);
 
 	/* this is the last reference to this object */
 	router = rcu_dereference_protected(orig_ifinfo->router, true);
 	if (router)
-		batadv_neigh_node_free_ref_now(router);
-	kfree(orig_ifinfo);
+		batadv_neigh_node_free_ref(router);
+
+	kfree_rcu(orig_ifinfo, rcu);
 }
 
 /**
@@ -523,7 +510,7 @@ static void batadv_orig_ifinfo_free_rcu(struct rcu_head *rcu)
 void batadv_orig_ifinfo_free_ref(struct batadv_orig_ifinfo *orig_ifinfo)
 {
 	if (atomic_dec_and_test(&orig_ifinfo->refcount))
-		call_rcu(&orig_ifinfo->rcu, batadv_orig_ifinfo_free_rcu);
+		batadv_orig_ifinfo_release(orig_ifinfo);
 }
 
 /**
-- 
2.1.0


From 663757435d69ecb18d43014ec33d4a4a53d1cccd Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Tue, 5 Jan 2016 12:06:24 +0100
Subject: [PATCH 31/39] batman-adv: Drop immediate neigh_ifinfo free function

[ Upstream commit ae3e1e36e3cb6c686a7a2725af20ca86aa46d62a ]

It is not allowed to free the memory of an object which is part of a list
which is protected by rcu-read-side-critical sections without making sure
that no other context is accessing the object anymore. This usually happens
by removing the references to this object and then waiting until the rcu
grace period is over and no one (allowedly) accesses it anymore.

But the _now functions ignore this completely. They free the object
directly even when a different context still tries to access it. This has
to be avoided and thus these functions must be removed and all functions
have to use batadv_neigh_ifinfo_free_ref.

Fixes: 89652331c00f ("batman-adv: split tq information in neigh_node struct")
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>
Signed-off-by: Antonio Quartulli <a@unstable.cc>
---
 net/batman-adv/originator.c | 34 ++++++++++------------------------
 1 file changed, 10 insertions(+), 24 deletions(-)

diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index c816c66..23db96f 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -150,42 +150,28 @@ err:
 }
 
 /**
- * batadv_neigh_ifinfo_free_rcu - free the neigh_ifinfo object
- * @rcu: rcu pointer of the neigh_ifinfo object
- */
-static void batadv_neigh_ifinfo_free_rcu(struct rcu_head *rcu)
-{
-	struct batadv_neigh_ifinfo *neigh_ifinfo;
-
-	neigh_ifinfo = container_of(rcu, struct batadv_neigh_ifinfo, rcu);
-
-	if (neigh_ifinfo->if_outgoing != BATADV_IF_DEFAULT)
-		batadv_hardif_free_ref_now(neigh_ifinfo->if_outgoing);
-
-	kfree(neigh_ifinfo);
-}
-
-/**
- * batadv_neigh_ifinfo_free_now - decrement the refcounter and possibly free
- *  the neigh_ifinfo (without rcu callback)
+ * batadv_neigh_ifinfo_release - release neigh_ifinfo from lists and queue for
+ *  free after rcu grace period
  * @neigh_ifinfo: the neigh_ifinfo object to release
  */
 static void
-batadv_neigh_ifinfo_free_ref_now(struct batadv_neigh_ifinfo *neigh_ifinfo)
+batadv_neigh_ifinfo_release(struct batadv_neigh_ifinfo *neigh_ifinfo)
 {
-	if (atomic_dec_and_test(&neigh_ifinfo->refcount))
-		batadv_neigh_ifinfo_free_rcu(&neigh_ifinfo->rcu);
+	if (neigh_ifinfo->if_outgoing != BATADV_IF_DEFAULT)
+		batadv_hardif_free_ref(neigh_ifinfo->if_outgoing);
+
+	kfree_rcu(neigh_ifinfo, rcu);
 }
 
 /**
- * batadv_neigh_ifinfo_free_ref - decrement the refcounter and possibly free
+ * batadv_neigh_ifinfo_free_ref - decrement the refcounter and possibly release
  *  the neigh_ifinfo
  * @neigh_ifinfo: the neigh_ifinfo object to release
  */
 void batadv_neigh_ifinfo_free_ref(struct batadv_neigh_ifinfo *neigh_ifinfo)
 {
 	if (atomic_dec_and_test(&neigh_ifinfo->refcount))
-		call_rcu(&neigh_ifinfo->rcu, batadv_neigh_ifinfo_free_rcu);
+		batadv_neigh_ifinfo_release(neigh_ifinfo);
 }
 
 /**
@@ -202,7 +188,7 @@ static void batadv_neigh_node_free_rcu(struct rcu_head *rcu)
 
 	hlist_for_each_entry_safe(neigh_ifinfo, node_tmp,
 				  &neigh_node->ifinfo_list, list) {
-		batadv_neigh_ifinfo_free_ref_now(neigh_ifinfo);
+		batadv_neigh_ifinfo_free_ref(neigh_ifinfo);
 	}
 	batadv_hardif_free_ref_now(neigh_node->if_incoming);
 
-- 
2.1.0


From cc9f2593205cf6563d1b214581ab4bf1f0919bc5 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Tue, 5 Jan 2016 12:06:25 +0100
Subject: [PATCH 32/39] batman-adv: Drop immediate batadv_hard_iface free
 function

[ Upstream commit b4d922cfc9c08318eeb77d53b7633740e6b0efb0 ]

It is not allowed to free the memory of an object which is part of a list
which is protected by rcu-read-side-critical sections without making sure
that no other context is accessing the object anymore. This usually happens
by removing the references to this object and then waiting until the rcu
grace period is over and no one (allowedly) accesses it anymore.

But the _now functions ignore this completely. They free the object
directly even when a different context still tries to access it. This has
to be avoided and thus these functions must be removed and all functions
have to use batadv_hardif_free_ref.

Fixes: 89652331c00f ("batman-adv: split tq information in neigh_node struct")
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>
Signed-off-by: Antonio Quartulli <a@unstable.cc>
---
 net/batman-adv/hard-interface.h | 12 ------------
 net/batman-adv/originator.c     | 16 +++++++---------
 2 files changed, 7 insertions(+), 21 deletions(-)

diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h
index 1918cd5..b6bff9c 100644
--- a/net/batman-adv/hard-interface.h
+++ b/net/batman-adv/hard-interface.h
@@ -64,18 +64,6 @@ batadv_hardif_free_ref(struct batadv_hard_iface *hard_iface)
 		call_rcu(&hard_iface->rcu, batadv_hardif_free_rcu);
 }
 
-/**
- * batadv_hardif_free_ref_now - decrement the hard interface refcounter and
- *  possibly free it (without rcu callback)
- * @hard_iface: the hard interface to free
- */
-static inline void
-batadv_hardif_free_ref_now(struct batadv_hard_iface *hard_iface)
-{
-	if (atomic_dec_and_test(&hard_iface->refcount))
-		batadv_hardif_free_rcu(&hard_iface->rcu);
-}
-
 static inline struct batadv_hard_iface *
 batadv_primary_if_get_selected(struct batadv_priv *bat_priv)
 {
diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index 23db96f..36dfa3b 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -175,24 +175,22 @@ void batadv_neigh_ifinfo_free_ref(struct batadv_neigh_ifinfo *neigh_ifinfo)
 }
 
 /**
- * batadv_neigh_node_free_rcu - free the neigh_node
- * @rcu: rcu pointer of the neigh_node
+ * batadv_neigh_node_release - release neigh_node from lists and queue for
+ *  free after rcu grace period
+ * @neigh_node: neigh neighbor to free
  */
-static void batadv_neigh_node_free_rcu(struct rcu_head *rcu)
+static void batadv_neigh_node_release(struct batadv_neigh_node *neigh_node)
 {
 	struct hlist_node *node_tmp;
-	struct batadv_neigh_node *neigh_node;
 	struct batadv_neigh_ifinfo *neigh_ifinfo;
 
-	neigh_node = container_of(rcu, struct batadv_neigh_node, rcu);
-
 	hlist_for_each_entry_safe(neigh_ifinfo, node_tmp,
 				  &neigh_node->ifinfo_list, list) {
 		batadv_neigh_ifinfo_free_ref(neigh_ifinfo);
 	}
-	batadv_hardif_free_ref_now(neigh_node->if_incoming);
+	batadv_hardif_free_ref(neigh_node->if_incoming);
 
-	kfree(neigh_node);
+	kfree_rcu(neigh_node, rcu);
 }
 
 /**
@@ -203,7 +201,7 @@ static void batadv_neigh_node_free_rcu(struct rcu_head *rcu)
 void batadv_neigh_node_free_ref(struct batadv_neigh_node *neigh_node)
 {
 	if (atomic_dec_and_test(&neigh_node->refcount))
-		call_rcu(&neigh_node->rcu, batadv_neigh_node_free_rcu);
+		batadv_neigh_node_release(neigh_node);
 }
 
 /**
-- 
2.1.0


From 755fc5e51f1edcd14fbd9add9564a043be3fbbe6 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Tue, 5 Jan 2016 12:06:20 +0100
Subject: [PATCH 33/39] batman-adv: Drop immediate orig_node free function

[ Upstream commit 42eff6a617e23b691f8e4467f4687ed7245a92db ]

It is not allowed to free the memory of an object which is part of a list
which is protected by rcu-read-side-critical sections without making sure
that no other context is accessing the object anymore. This usually happens
by removing the references to this object and then waiting until the rcu
grace period is over and no one (allowedly) accesses it anymore.

But the _now functions ignore this completely. They free the object
directly even when a different context still tries to access it. This has
to be avoided and thus these functions must be removed and all functions
have to use batadv_orig_node_free_ref.

Fixes: 72822225bd41 ("batman-adv: Fix rcu_barrier() miss due to double call_rcu() in TT code")
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>
Signed-off-by: Antonio Quartulli <a@unstable.cc>
---
 net/batman-adv/originator.c        | 11 -----------
 net/batman-adv/originator.h        |  1 -
 net/batman-adv/translation-table.c | 28 +++++++++++++---------------
 3 files changed, 13 insertions(+), 27 deletions(-)

diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index 36dfa3b..77ea1d4 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -562,17 +562,6 @@ void batadv_orig_node_free_ref(struct batadv_orig_node *orig_node)
 		batadv_orig_node_release(orig_node);
 }
 
-/**
- * batadv_orig_node_free_ref_now - decrement the orig node refcounter and
- * possibly free it (without rcu callback)
- * @orig_node: the orig node to free
- */
-void batadv_orig_node_free_ref_now(struct batadv_orig_node *orig_node)
-{
-	if (atomic_dec_and_test(&orig_node->refcount))
-		batadv_orig_node_free_rcu(&orig_node->rcu);
-}
-
 void batadv_originator_free(struct batadv_priv *bat_priv)
 {
 	struct batadv_hashtable *hash = bat_priv->orig_hash;
diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h
index aa4a436..28b751a 100644
--- a/net/batman-adv/originator.h
+++ b/net/batman-adv/originator.h
@@ -25,7 +25,6 @@ int batadv_originator_init(struct batadv_priv *bat_priv);
 void batadv_originator_free(struct batadv_priv *bat_priv);
 void batadv_purge_orig_ref(struct batadv_priv *bat_priv);
 void batadv_orig_node_free_ref(struct batadv_orig_node *orig_node);
-void batadv_orig_node_free_ref_now(struct batadv_orig_node *orig_node);
 struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv,
 					      const uint8_t *addr);
 struct batadv_neigh_node *
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index 4f2a9d2..ddd62c9 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -219,20 +219,6 @@ int batadv_tt_global_hash_count(struct batadv_priv *bat_priv,
 	return count;
 }
 
-static void batadv_tt_orig_list_entry_free_rcu(struct rcu_head *rcu)
-{
-	struct batadv_tt_orig_list_entry *orig_entry;
-
-	orig_entry = container_of(rcu, struct batadv_tt_orig_list_entry, rcu);
-
-	/* We are in an rcu callback here, therefore we cannot use
-	 * batadv_orig_node_free_ref() and its call_rcu():
-	 * An rcu_barrier() wouldn't wait for that to finish
-	 */
-	batadv_orig_node_free_ref_now(orig_entry->orig_node);
-	kfree(orig_entry);
-}
-
 /**
  * batadv_tt_local_size_mod - change the size by v of the local table identified
  *  by vid
@@ -328,13 +314,25 @@ static void batadv_tt_global_size_dec(struct batadv_orig_node *orig_node,
 	batadv_tt_global_size_mod(orig_node, vid, -1);
 }
 
+/**
+ * batadv_tt_orig_list_entry_release - release tt orig entry from lists and
+ *  queue for free after rcu grace period
+ * @orig_entry: tt orig entry to be free'd
+ */
+static void
+batadv_tt_orig_list_entry_release(struct batadv_tt_orig_list_entry *orig_entry)
+{
+	batadv_orig_node_free_ref(orig_entry->orig_node);
+	kfree_rcu(orig_entry, rcu);
+}
+
 static void
 batadv_tt_orig_list_entry_free_ref(struct batadv_tt_orig_list_entry *orig_entry)
 {
 	if (!atomic_dec_and_test(&orig_entry->refcount))
 		return;
 
-	call_rcu(&orig_entry->rcu, batadv_tt_orig_list_entry_free_rcu);
+	batadv_tt_orig_list_entry_release(orig_entry);
 }
 
 /**
-- 
2.1.0


From b6e2d2cbd65e1cf3ee3080b80ddaa940dfb6e638 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Mon, 18 Jan 2016 17:30:22 +0200
Subject: [PATCH 34/39] team: Replace rcu_read_lock with a mutex in
 team_vlan_rx_kill_vid

[ Upstream commit 60a6531bfe49555581ccd65f66a350cc5693fcde ]

We can't be within an RCU read-side critical section when deleting
VLANs, as underlying drivers might sleep during the hardware operation.
Therefore, replace the RCU critical section with a mutex. This is
consistent with team_vlan_rx_add_vid.

Fixes: 3d249d4ca7d0 ("net: introduce ethernet teaming device")
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 6928448..2b45d01 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1845,10 +1845,10 @@ static int team_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid)
 	struct team *team = netdev_priv(dev);
 	struct team_port *port;
 
-	rcu_read_lock();
-	list_for_each_entry_rcu(port, &team->port_list, list)
+	mutex_lock(&team->lock);
+	list_for_each_entry(port, &team->port_list, list)
 		vlan_vid_del(port->dev, proto, vid);
-	rcu_read_unlock();
+	mutex_unlock(&team->lock);
 
 	return 0;
 }
-- 
2.1.0


From 025adf6d6057f1f4f5364011a37211e74b77193a Mon Sep 17 00:00:00 2001
From: Karl Heiss <kheiss@gmail.com>
Date: Thu, 24 Sep 2015 12:15:07 -0400
Subject: [PATCH 35/39] sctp: Prevent soft lockup when sctp_accept() is called
 during a timeout event

[ Upstream commit 635682a14427d241bab7bbdeebb48a7d7b91638e ]

A case can occur when sctp_accept() is called by the user during
a heartbeat timeout event after the 4-way handshake.  Since
sctp_assoc_migrate() changes both assoc->base.sk and assoc->ep, the
bh_sock_lock in sctp_generate_heartbeat_event() will be taken with
the listening socket but released with the new association socket.
The result is a deadlock on any future attempts to take the listening
socket lock.

Note that this race can occur with other SCTP timeouts that take
the bh_lock_sock() in the event sctp_accept() is called.

 BUG: soft lockup - CPU#9 stuck for 67s! [swapper:0]
 ...
 RIP: 0010:[<ffffffff8152d48e>]  [<ffffffff8152d48e>] _spin_lock+0x1e/0x30
 RSP: 0018:ffff880028323b20  EFLAGS: 00000206
 RAX: 0000000000000002 RBX: ffff880028323b20 RCX: 0000000000000000
 RDX: 0000000000000000 RSI: ffff880028323be0 RDI: ffff8804632c4b48
 RBP: ffffffff8100bb93 R08: 0000000000000000 R09: 0000000000000000
 R10: ffff880610662280 R11: 0000000000000100 R12: ffff880028323aa0
 R13: ffff8804383c3880 R14: ffff880028323a90 R15: ffffffff81534225
 FS:  0000000000000000(0000) GS:ffff880028320000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0018 ES: 0018 CR0: 000000008005003b
 CR2: 00000000006df528 CR3: 0000000001a85000 CR4: 00000000000006e0
 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
 Process swapper (pid: 0, threadinfo ffff880616b70000, task ffff880616b6cab0)
 Stack:
 ffff880028323c40 ffffffffa01c2582 ffff880614cfb020 0000000000000000
 <d> 0100000000000000 00000014383a6c44 ffff8804383c3880 ffff880614e93c00
 <d> ffff880614e93c00 0000000000000000 ffff8804632c4b00 ffff8804383c38b8
 Call Trace:
 <IRQ>
 [<ffffffffa01c2582>] ? sctp_rcv+0x492/0xa10 [sctp]
 [<ffffffff8148c559>] ? nf_iterate+0x69/0xb0
 [<ffffffff814974a0>] ? ip_local_deliver_finish+0x0/0x2d0
 [<ffffffff8148c716>] ? nf_hook_slow+0x76/0x120
 [<ffffffff814974a0>] ? ip_local_deliver_finish+0x0/0x2d0
 [<ffffffff8149757d>] ? ip_local_deliver_finish+0xdd/0x2d0
 [<ffffffff81497808>] ? ip_local_deliver+0x98/0xa0
 [<ffffffff81496ccd>] ? ip_rcv_finish+0x12d/0x440
 [<ffffffff81497255>] ? ip_rcv+0x275/0x350
 [<ffffffff8145cfeb>] ? __netif_receive_skb+0x4ab/0x750
 ...

With lockdep debugging:

 =====================================
 [ BUG: bad unlock balance detected! ]
 -------------------------------------
 CslRx/12087 is trying to release lock (slock-AF_INET) at:
 [<ffffffffa01bcae0>] sctp_generate_timeout_event+0x40/0xe0 [sctp]
 but there are no more locks to release!

 other info that might help us debug this:
 2 locks held by CslRx/12087:
 #0:  (&asoc->timers[i]){+.-...}, at: [<ffffffff8108ce1f>] run_timer_softirq+0x16f/0x3e0
 #1:  (slock-AF_INET){+.-...}, at: [<ffffffffa01bcac3>] sctp_generate_timeout_event+0x23/0xe0 [sctp]

Ensure the socket taken is also the same one that is released by
saving a copy of the socket before entering the timeout event
critical section.

Signed-off-by: Karl Heiss <kheiss@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sm_sideeffect.c | 42 +++++++++++++++++++++++-------------------
 1 file changed, 23 insertions(+), 19 deletions(-)

diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index fef2acd..ecae556 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -244,12 +244,13 @@ void sctp_generate_t3_rtx_event(unsigned long peer)
 	int error;
 	struct sctp_transport *transport = (struct sctp_transport *) peer;
 	struct sctp_association *asoc = transport->asoc;
-	struct net *net = sock_net(asoc->base.sk);
+	struct sock *sk = asoc->base.sk;
+	struct net *net = sock_net(sk);
 
 	/* Check whether a task is in the sock.  */
 
-	bh_lock_sock(asoc->base.sk);
-	if (sock_owned_by_user(asoc->base.sk)) {
+	bh_lock_sock(sk);
+	if (sock_owned_by_user(sk)) {
 		pr_debug("%s: sock is busy\n", __func__);
 
 		/* Try again later.  */
@@ -272,10 +273,10 @@ void sctp_generate_t3_rtx_event(unsigned long peer)
 			   transport, GFP_ATOMIC);
 
 	if (error)
-		asoc->base.sk->sk_err = -error;
+		sk->sk_err = -error;
 
 out_unlock:
-	bh_unlock_sock(asoc->base.sk);
+	bh_unlock_sock(sk);
 	sctp_transport_put(transport);
 }
 
@@ -285,11 +286,12 @@ out_unlock:
 static void sctp_generate_timeout_event(struct sctp_association *asoc,
 					sctp_event_timeout_t timeout_type)
 {
-	struct net *net = sock_net(asoc->base.sk);
+	struct sock *sk = asoc->base.sk;
+	struct net *net = sock_net(sk);
 	int error = 0;
 
-	bh_lock_sock(asoc->base.sk);
-	if (sock_owned_by_user(asoc->base.sk)) {
+	bh_lock_sock(sk);
+	if (sock_owned_by_user(sk)) {
 		pr_debug("%s: sock is busy: timer %d\n", __func__,
 			 timeout_type);
 
@@ -312,10 +314,10 @@ static void sctp_generate_timeout_event(struct sctp_association *asoc,
 			   (void *)timeout_type, GFP_ATOMIC);
 
 	if (error)
-		asoc->base.sk->sk_err = -error;
+		sk->sk_err = -error;
 
 out_unlock:
-	bh_unlock_sock(asoc->base.sk);
+	bh_unlock_sock(sk);
 	sctp_association_put(asoc);
 }
 
@@ -365,10 +367,11 @@ void sctp_generate_heartbeat_event(unsigned long data)
 	int error = 0;
 	struct sctp_transport *transport = (struct sctp_transport *) data;
 	struct sctp_association *asoc = transport->asoc;
-	struct net *net = sock_net(asoc->base.sk);
+	struct sock *sk = asoc->base.sk;
+	struct net *net = sock_net(sk);
 
-	bh_lock_sock(asoc->base.sk);
-	if (sock_owned_by_user(asoc->base.sk)) {
+	bh_lock_sock(sk);
+	if (sock_owned_by_user(sk)) {
 		pr_debug("%s: sock is busy\n", __func__);
 
 		/* Try again later.  */
@@ -389,10 +392,10 @@ void sctp_generate_heartbeat_event(unsigned long data)
 			   transport, GFP_ATOMIC);
 
 	 if (error)
-		 asoc->base.sk->sk_err = -error;
+		sk->sk_err = -error;
 
 out_unlock:
-	bh_unlock_sock(asoc->base.sk);
+	bh_unlock_sock(sk);
 	sctp_transport_put(transport);
 }
 
@@ -403,10 +406,11 @@ void sctp_generate_proto_unreach_event(unsigned long data)
 {
 	struct sctp_transport *transport = (struct sctp_transport *) data;
 	struct sctp_association *asoc = transport->asoc;
-	struct net *net = sock_net(asoc->base.sk);
+	struct sock *sk = asoc->base.sk;
+	struct net *net = sock_net(sk);
 
-	bh_lock_sock(asoc->base.sk);
-	if (sock_owned_by_user(asoc->base.sk)) {
+	bh_lock_sock(sk);
+	if (sock_owned_by_user(sk)) {
 		pr_debug("%s: sock is busy\n", __func__);
 
 		/* Try again later.  */
@@ -427,7 +431,7 @@ void sctp_generate_proto_unreach_event(unsigned long data)
 		   asoc->state, asoc->ep, asoc, transport, GFP_ATOMIC);
 
 out_unlock:
-	bh_unlock_sock(asoc->base.sk);
+	bh_unlock_sock(sk);
 	sctp_association_put(asoc);
 }
 
-- 
2.1.0


From 386a048a2e059fa69ede10c4613c3c6d98a45a5e Mon Sep 17 00:00:00 2001
From: Wei Liu <wei.liu2@citrix.com>
Date: Thu, 10 Sep 2015 11:18:57 +0100
Subject: [PATCH 36/39] xen-netback: respect user provided max_queues

[ Upstream commit 4c82ac3c37363e8c4ded6a5fe1ec5fa756b34df3 ]

Originally that parameter was always reset to num_online_cpus during
module initialisation, which renders it useless.

The fix is to only set max_queues to num_online_cpus when user has not
provided a value.

Reported-by: Johnny Strom <johnny.strom@linuxsolutions.fi>
Signed-off-by: Wei Liu <wei.liu2@citrix.com>
Reviewed-by: David Vrabel <david.vrabel@citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netback/netback.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 0866c5d..5e5b618 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -2007,8 +2007,11 @@ static int __init netback_init(void)
 	if (!xen_domain())
 		return -ENODEV;
 
-	/* Allow as many queues as there are CPUs, by default */
-	xenvif_max_queues = num_online_cpus();
+	/* Allow as many queues as there are CPUs if user has not
+	 * specified a value.
+	 */
+	if (xenvif_max_queues == 0)
+		xenvif_max_queues = num_online_cpus();
 
 	if (fatal_skb_slots < XEN_NETBK_LEGACY_SLOTS_MAX) {
 		pr_info("fatal_skb_slots too small (%d), bump it to XEN_NETBK_LEGACY_SLOTS_MAX (%d)\n",
-- 
2.1.0


From 8e39dd20f7362085b40460e5f4930e837ab82a43 Mon Sep 17 00:00:00 2001
From: Wei Liu <wei.liu2@citrix.com>
Date: Thu, 10 Sep 2015 11:18:58 +0100
Subject: [PATCH 37/39] xen-netfront: respect user provided max_queues

[ Upstream commit 32a844056fd43dda647e1c3c6b9983bdfa04d17d ]

Originally that parameter was always reset to num_online_cpus during
module initialisation, which renders it useless.

The fix is to only set max_queues to num_online_cpus when user has not
provided a value.

Signed-off-by: Wei Liu <wei.liu2@citrix.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Reviewed-by: David Vrabel <david.vrabel@citrix.com>
Tested-by: David Vrabel <david.vrabel@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netfront.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 52f081f..2a01b68 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -2140,8 +2140,11 @@ static int __init netif_init(void)
 
 	pr_info("Initialising Xen virtual ethernet driver\n");
 
-	/* Allow as many queues as there are CPUs, by default */
-	xennet_max_queues = num_online_cpus();
+	/* Allow as many queues as there are CPUs if user has not
+	 * specified a value.
+	 */
+	if (xennet_max_queues == 0)
+		xennet_max_queues = num_online_cpus();
 
 	return xenbus_register_frontend(&netfront_driver);
 }
-- 
2.1.0


From c24734787b0b70630ebec335d0d3aac153244203 Mon Sep 17 00:00:00 2001
From: Joe Jin <joe.jin@oracle.com>
Date: Mon, 19 Oct 2015 13:37:17 +0800
Subject: [PATCH 38/39] xen-netfront: update num_queues to real created

[ Upstream commit ca88ea1247dfee094e2467a3578eaec9bdf0833a ]

Sometimes xennet_create_queues() may failed to created all requested
queues, we need to update num_queues to real created to avoid NULL
pointer dereference.

Signed-off-by: Joe Jin <joe.jin@oracle.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Wei Liu <wei.liu2@citrix.com>
Cc: Ian Campbell <ian.campbell@citrix.com>
Cc: David S. Miller <davem@davemloft.net>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netfront.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 2a01b68..fd51626 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -1710,19 +1710,19 @@ static void xennet_destroy_queues(struct netfront_info *info)
 }
 
 static int xennet_create_queues(struct netfront_info *info,
-				unsigned int num_queues)
+				unsigned int *num_queues)
 {
 	unsigned int i;
 	int ret;
 
-	info->queues = kcalloc(num_queues, sizeof(struct netfront_queue),
+	info->queues = kcalloc(*num_queues, sizeof(struct netfront_queue),
 			       GFP_KERNEL);
 	if (!info->queues)
 		return -ENOMEM;
 
 	rtnl_lock();
 
-	for (i = 0; i < num_queues; i++) {
+	for (i = 0; i < *num_queues; i++) {
 		struct netfront_queue *queue = &info->queues[i];
 
 		queue->id = i;
@@ -1732,7 +1732,7 @@ static int xennet_create_queues(struct netfront_info *info,
 		if (ret < 0) {
 			dev_warn(&info->netdev->dev,
 				 "only created %d queues\n", i);
-			num_queues = i;
+			*num_queues = i;
 			break;
 		}
 
@@ -1742,11 +1742,11 @@ static int xennet_create_queues(struct netfront_info *info,
 			napi_enable(&queue->napi);
 	}
 
-	netif_set_real_num_tx_queues(info->netdev, num_queues);
+	netif_set_real_num_tx_queues(info->netdev, *num_queues);
 
 	rtnl_unlock();
 
-	if (num_queues == 0) {
+	if (*num_queues == 0) {
 		dev_err(&info->netdev->dev, "no queues\n");
 		return -EINVAL;
 	}
@@ -1792,7 +1792,7 @@ static int talk_to_netback(struct xenbus_device *dev,
 	if (info->queues)
 		xennet_destroy_queues(info);
 
-	err = xennet_create_queues(info, num_queues);
+	err = xennet_create_queues(info, &num_queues);
 	if (err < 0)
 		goto destroy_ring;
 
-- 
2.1.0


From ce6088d3ea662862de69cf8ad5e7feeb7a4b75e7 Mon Sep 17 00:00:00 2001
From: Dan Streetman <dan.streetman@canonical.com>
Date: Thu, 29 Oct 2015 09:51:16 -0400
Subject: [PATCH 39/39] xfrm: dst_entries_init() per-net dst_ops

[ Upstream commit a8a572a6b5f2a79280d6e302cb3c1cb1fbaeb3e8 ]

Remove the dst_entries_init/destroy calls for xfrm4 and xfrm6 dst_ops
templates; their dst_entries counters will never be used.  Move the
xfrm dst_ops initialization from the common xfrm/xfrm_policy.c to
xfrm4/xfrm4_policy.c and xfrm6/xfrm6_policy.c, and call dst_entries_init
and dst_entries_destroy for each net namespace.

The ipv4 and ipv6 xfrms each create dst_ops template, and perform
dst_entries_init on the templates.  The template values are copied to each
net namespace's xfrm.xfrm*_dst_ops.  The problem there is the dst_ops
pcpuc_entries field is a percpu counter and cannot be used correctly by
simply copying it to another object.

The result of this is a very subtle bug; changes to the dst entries
counter from one net namespace may sometimes get applied to a different
net namespace dst entries counter.  This is because of how the percpu
counter works; it has a main count field as well as a pointer to the
percpu variables.  Each net namespace maintains its own main count
variable, but all point to one set of percpu variables.  When any net
namespace happens to change one of the percpu variables to outside its
small batch range, its count is moved to the net namespace's main count
variable.  So with multiple net namespaces operating concurrently, the
dst_ops entries counter can stray from the actual value that it should
be; if counts are consistently moved from one net namespace to another
(which my testing showed is likely), then one net namespace winds up
with a negative dst_ops count while another winds up with a continually
increasing count, eventually reaching its gc_thresh limit, which causes
all new traffic on the net namespace to fail with -ENOBUFS.

Signed-off-by: Dan Streetman <dan.streetman@canonical.com>
Signed-off-by: Dan Streetman <ddstreet@ieee.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/ipv4/xfrm4_policy.c | 46 +++++++++++++++++++++++++++++++++---------
 net/ipv6/xfrm6_policy.c | 53 +++++++++++++++++++++++++++++++++++--------------
 net/xfrm/xfrm_policy.c  | 38 -----------------------------------
 3 files changed, 75 insertions(+), 62 deletions(-)

diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index bff6974..7852608 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -230,7 +230,7 @@ static void xfrm4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
 	xfrm_dst_ifdown(dst, dev);
 }
 
-static struct dst_ops xfrm4_dst_ops = {
+static struct dst_ops xfrm4_dst_ops_template = {
 	.family =		AF_INET,
 	.gc =			xfrm4_garbage_collect,
 	.update_pmtu =		xfrm4_update_pmtu,
@@ -244,7 +244,7 @@ static struct dst_ops xfrm4_dst_ops = {
 
 static struct xfrm_policy_afinfo xfrm4_policy_afinfo = {
 	.family = 		AF_INET,
-	.dst_ops =		&xfrm4_dst_ops,
+	.dst_ops =		&xfrm4_dst_ops_template,
 	.dst_lookup =		xfrm4_dst_lookup,
 	.get_saddr =		xfrm4_get_saddr,
 	.decode_session =	_decode_session4,
@@ -266,7 +266,7 @@ static struct ctl_table xfrm4_policy_table[] = {
 	{ }
 };
 
-static int __net_init xfrm4_net_init(struct net *net)
+static int __net_init xfrm4_net_sysctl_init(struct net *net)
 {
 	struct ctl_table *table;
 	struct ctl_table_header *hdr;
@@ -294,7 +294,7 @@ err_alloc:
 	return -ENOMEM;
 }
 
-static void __net_exit xfrm4_net_exit(struct net *net)
+static void __net_exit xfrm4_net_sysctl_exit(struct net *net)
 {
 	struct ctl_table *table;
 
@@ -306,12 +306,44 @@ static void __net_exit xfrm4_net_exit(struct net *net)
 	if (!net_eq(net, &init_net))
 		kfree(table);
 }
+#else /* CONFIG_SYSCTL */
+static int inline xfrm4_net_sysctl_init(struct net *net)
+{
+	return 0;
+}
+
+static void inline xfrm4_net_sysctl_exit(struct net *net)
+{
+}
+#endif
+
+static int __net_init xfrm4_net_init(struct net *net)
+{
+	int ret;
+
+	memcpy(&net->xfrm.xfrm4_dst_ops, &xfrm4_dst_ops_template,
+	       sizeof(xfrm4_dst_ops_template));
+	ret = dst_entries_init(&net->xfrm.xfrm4_dst_ops);
+	if (ret)
+		return ret;
+
+	ret = xfrm4_net_sysctl_init(net);
+	if (ret)
+		dst_entries_destroy(&net->xfrm.xfrm4_dst_ops);
+
+	return ret;
+}
+
+static void __net_exit xfrm4_net_exit(struct net *net)
+{
+	xfrm4_net_sysctl_exit(net);
+	dst_entries_destroy(&net->xfrm.xfrm4_dst_ops);
+}
 
 static struct pernet_operations __net_initdata xfrm4_net_ops = {
 	.init	= xfrm4_net_init,
 	.exit	= xfrm4_net_exit,
 };
-#endif
 
 static void __init xfrm4_policy_init(void)
 {
@@ -320,13 +352,9 @@ static void __init xfrm4_policy_init(void)
 
 void __init xfrm4_init(void)
 {
-	dst_entries_init(&xfrm4_dst_ops);
-
 	xfrm4_state_init();
 	xfrm4_policy_init();
 	xfrm4_protocol_init();
-#ifdef CONFIG_SYSCTL
 	register_pernet_subsys(&xfrm4_net_ops);
-#endif
 }
 
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index f337a90..4fb94f6 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -289,7 +289,7 @@ static void xfrm6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
 	xfrm_dst_ifdown(dst, dev);
 }
 
-static struct dst_ops xfrm6_dst_ops = {
+static struct dst_ops xfrm6_dst_ops_template = {
 	.family =		AF_INET6,
 	.gc =			xfrm6_garbage_collect,
 	.update_pmtu =		xfrm6_update_pmtu,
@@ -303,7 +303,7 @@ static struct dst_ops xfrm6_dst_ops = {
 
 static struct xfrm_policy_afinfo xfrm6_policy_afinfo = {
 	.family =		AF_INET6,
-	.dst_ops =		&xfrm6_dst_ops,
+	.dst_ops =		&xfrm6_dst_ops_template,
 	.dst_lookup =		xfrm6_dst_lookup,
 	.get_saddr =		xfrm6_get_saddr,
 	.decode_session =	_decode_session6,
@@ -336,7 +336,7 @@ static struct ctl_table xfrm6_policy_table[] = {
 	{ }
 };
 
-static int __net_init xfrm6_net_init(struct net *net)
+static int __net_init xfrm6_net_sysctl_init(struct net *net)
 {
 	struct ctl_table *table;
 	struct ctl_table_header *hdr;
@@ -364,7 +364,7 @@ err_alloc:
 	return -ENOMEM;
 }
 
-static void __net_exit xfrm6_net_exit(struct net *net)
+static void __net_exit xfrm6_net_sysctl_exit(struct net *net)
 {
 	struct ctl_table *table;
 
@@ -376,24 +376,52 @@ static void __net_exit xfrm6_net_exit(struct net *net)
 	if (!net_eq(net, &init_net))
 		kfree(table);
 }
+#else /* CONFIG_SYSCTL */
+static int inline xfrm6_net_sysctl_init(struct net *net)
+{
+	return 0;
+}
+
+static void inline xfrm6_net_sysctl_exit(struct net *net)
+{
+}
+#endif
+
+static int __net_init xfrm6_net_init(struct net *net)
+{
+	int ret;
+
+	memcpy(&net->xfrm.xfrm6_dst_ops, &xfrm6_dst_ops_template,
+	       sizeof(xfrm6_dst_ops_template));
+	ret = dst_entries_init(&net->xfrm.xfrm6_dst_ops);
+	if (ret)
+		return ret;
+
+	ret = xfrm6_net_sysctl_init(net);
+	if (ret)
+		dst_entries_destroy(&net->xfrm.xfrm6_dst_ops);
+
+	return ret;
+}
+
+static void __net_exit xfrm6_net_exit(struct net *net)
+{
+	xfrm6_net_sysctl_exit(net);
+	dst_entries_destroy(&net->xfrm.xfrm6_dst_ops);
+}
 
 static struct pernet_operations xfrm6_net_ops = {
 	.init	= xfrm6_net_init,
 	.exit	= xfrm6_net_exit,
 };
-#endif
 
 int __init xfrm6_init(void)
 {
 	int ret;
 
-	dst_entries_init(&xfrm6_dst_ops);
-
 	ret = xfrm6_policy_init();
-	if (ret) {
-		dst_entries_destroy(&xfrm6_dst_ops);
+	if (ret)
 		goto out;
-	}
 	ret = xfrm6_state_init();
 	if (ret)
 		goto out_policy;
@@ -402,9 +430,7 @@ int __init xfrm6_init(void)
 	if (ret)
 		goto out_state;
 
-#ifdef CONFIG_SYSCTL
 	register_pernet_subsys(&xfrm6_net_ops);
-#endif
 out:
 	return ret;
 out_state:
@@ -416,11 +442,8 @@ out_policy:
 
 void xfrm6_fini(void)
 {
-#ifdef CONFIG_SYSCTL
 	unregister_pernet_subsys(&xfrm6_net_ops);
-#endif
 	xfrm6_protocol_fini();
 	xfrm6_policy_fini();
 	xfrm6_state_fini();
-	dst_entries_destroy(&xfrm6_dst_ops);
 }
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 638af06..4cd2076 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2806,7 +2806,6 @@ static struct neighbour *xfrm_neigh_lookup(const struct dst_entry *dst,
 
 int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo)
 {
-	struct net *net;
 	int err = 0;
 	if (unlikely(afinfo == NULL))
 		return -EINVAL;
@@ -2837,26 +2836,6 @@ int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo)
 	}
 	spin_unlock(&xfrm_policy_afinfo_lock);
 
-	rtnl_lock();
-	for_each_net(net) {
-		struct dst_ops *xfrm_dst_ops;
-
-		switch (afinfo->family) {
-		case AF_INET:
-			xfrm_dst_ops = &net->xfrm.xfrm4_dst_ops;
-			break;
-#if IS_ENABLED(CONFIG_IPV6)
-		case AF_INET6:
-			xfrm_dst_ops = &net->xfrm.xfrm6_dst_ops;
-			break;
-#endif
-		default:
-			BUG();
-		}
-		*xfrm_dst_ops = *afinfo->dst_ops;
-	}
-	rtnl_unlock();
-
 	return err;
 }
 EXPORT_SYMBOL(xfrm_policy_register_afinfo);
@@ -2892,22 +2871,6 @@ int xfrm_policy_unregister_afinfo(struct xfrm_policy_afinfo *afinfo)
 }
 EXPORT_SYMBOL(xfrm_policy_unregister_afinfo);
 
-static void __net_init xfrm_dst_ops_init(struct net *net)
-{
-	struct xfrm_policy_afinfo *afinfo;
-
-	rcu_read_lock();
-	afinfo = rcu_dereference(xfrm_policy_afinfo[AF_INET]);
-	if (afinfo)
-		net->xfrm.xfrm4_dst_ops = *afinfo->dst_ops;
-#if IS_ENABLED(CONFIG_IPV6)
-	afinfo = rcu_dereference(xfrm_policy_afinfo[AF_INET6]);
-	if (afinfo)
-		net->xfrm.xfrm6_dst_ops = *afinfo->dst_ops;
-#endif
-	rcu_read_unlock();
-}
-
 static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void *ptr)
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
@@ -3056,7 +3019,6 @@ static int __net_init xfrm_net_init(struct net *net)
 	rv = xfrm_policy_init(net);
 	if (rv < 0)
 		goto out_policy;
-	xfrm_dst_ops_init(net);
 	rv = xfrm_sysctl_init(net);
 	if (rv < 0)
 		goto out_sysctl;
-- 
2.1.0


[-- Attachment #5: net_318.mbox --]
[-- Type: Application/Octet-Stream, Size: 62825 bytes --]

From 5140e07a51274b95e96a9140b316301239f1e6a6 Mon Sep 17 00:00:00 2001
From: Vijay Pandurangan <vijayp@vijayp.ca>
Date: Fri, 18 Dec 2015 14:34:59 -0500
Subject: [PATCH 01/24] =?UTF-8?q?veth:=20don=E2=80=99t=20modify=20ip=5Fsum?=
 =?UTF-8?q?med;=20doing=20so=20treats=20packets=20with=20bad=20checksums?=
 =?UTF-8?q?=20as=20good.?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit ce8c839b74e3017996fad4e1b7ba2e2625ede82f ]

Packets that arrive from real hardware devices have ip_summed ==
CHECKSUM_UNNECESSARY if the hardware verified the checksums, or
CHECKSUM_NONE if the packet is bad or it was unable to verify it. The
current version of veth will replace CHECKSUM_NONE with
CHECKSUM_UNNECESSARY, which causes corrupt packets routed from hardware to
a veth device to be delivered to the application. This caused applications
at Twitter to receive corrupt data when network hardware was corrupting
packets.

We believe this was added as an optimization to skip computing and
verifying checksums for communication between containers. However, locally
generated packets have ip_summed == CHECKSUM_PARTIAL, so the code as
written does nothing for them. As far as we can tell, after removing this
code, these packets are transmitted from one stack to another unmodified
(tcpdump shows invalid checksums on both sides, as expected), and they are
delivered correctly to applications. We didn’t test every possible network
configuration, but we tried a few common ones such as bridging containers,
using NAT between the host and a container, and routing from hardware
devices to containers. We have effectively deployed this in production at
Twitter (by disabling RX checksum offloading on veth devices).

This code dates back to the first version of the driver, commit
<e314dbdc1c0dc6a548ecf> ("[NET]: Virtual ethernet device driver"), so I
suspect this bug occurred mostly because the driver API has evolved
significantly since then. Commit <0b7967503dc97864f283a> ("net/veth: Fix
packet checksumming") (in December 2010) fixed this for packets that get
created locally and sent to hardware devices, by not changing
CHECKSUM_PARTIAL. However, the same issue still occurs for packets coming
in from hardware devices.

Co-authored-by: Evan Jones <ej@evanjones.ca>
Signed-off-by: Evan Jones <ej@evanjones.ca>
Cc: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Cc: Phil Sutter <phil@nwl.cc>
Cc: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Cc: netdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Vijay Pandurangan <vijayp@vijayp.ca>
Acked-by: Cong Wang <cwang@twopensource.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/veth.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 8ad5965..32ce1cd 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -117,12 +117,6 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 		kfree_skb(skb);
 		goto drop;
 	}
-	/* don't change ip_summed == CHECKSUM_PARTIAL, as that
-	 * will cause bad checksum on forwarded packets
-	 */
-	if (skb->ip_summed == CHECKSUM_NONE &&
-	    rcv->features & NETIF_F_RXCSUM)
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
 
 	if (likely(dev_forward_skb(rcv, skb) == NET_RX_SUCCESS)) {
 		struct pcpu_vstats *stats = this_cpu_ptr(dev->vstats);
-- 
2.1.0


From 84064f2ed2c82ef8e4dbc7de24c35f8e75166f9e Mon Sep 17 00:00:00 2001
From: Andrey Ryabinin <aryabinin@virtuozzo.com>
Date: Mon, 21 Dec 2015 12:54:45 +0300
Subject: [PATCH 02/24] ipv6/addrlabel: fix ip6addrlbl_get()

[ Upstream commit e459dfeeb64008b2d23bdf600f03b3605dbb8152 ]

ip6addrlbl_get() has never worked. If ip6addrlbl_hold() succeeded,
ip6addrlbl_get() will exit with '-ESRCH'. If ip6addrlbl_hold() failed,
ip6addrlbl_get() will use about to be free ip6addrlbl_entry pointer.

Fix this by inverting ip6addrlbl_hold() check.

Fixes: 2a8cc6c89039 ("[IPV6] ADDRCONF: Support RFC3484 configurable address selection policy table.")
Signed-off-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
Reviewed-by: Cong Wang <cwang@twopensource.com>
Acked-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrlabel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index fd0dc47..70efbdd 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -558,7 +558,7 @@ static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 
 	rcu_read_lock();
 	p = __ipv6_addr_label(net, addr, ipv6_addr_type(addr), ifal->ifal_index);
-	if (p && ip6addrlbl_hold(p))
+	if (p && !ip6addrlbl_hold(p))
 		p = NULL;
 	lseq = ip6addrlbl_table.seq;
 	rcu_read_unlock();
-- 
2.1.0


From aa1ce726bd160f4aa1b89d4fa65d3acc14170c5c Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 29 Dec 2015 17:49:25 +0800
Subject: [PATCH 03/24] sctp: sctp should release assoc when
 sctp_make_abort_user return NULL in sctp_close

[ Upstream commit 068d8bd338e855286aea54e70d1c101569284b21 ]

In sctp_close, sctp_make_abort_user may return NULL because of memory
allocation failure. If this happens, it will bypass any state change
and never free the assoc. The assoc has no chance to be freed and it
will be kept in memory with the state it had even after the socket is
closed by sctp_close().

So if sctp_make_abort_user fails to allocate memory, we should abort
the asoc via sctp_primitive_ABORT as well. Just like the annotation in
sctp_sf_cookie_wait_prm_abort and sctp_sf_do_9_1_prm_abort said,
"Even if we can't send the ABORT due to low memory delete the TCB.
This is a departure from our typical NOMEM handling".

But then the chunk is NULL (low memory) and the SCTP_CMD_REPLY cmd would
dereference the chunk pointer, and system crash. So we should add
SCTP_CMD_REPLY cmd only when the chunk is not NULL, just like other
places where it adds SCTP_CMD_REPLY cmd.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sm_statefuns.c | 6 ++++--
 net/sctp/socket.c       | 3 +--
 2 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 3ee27b7..e6bb98e 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -4829,7 +4829,8 @@ sctp_disposition_t sctp_sf_do_9_1_prm_abort(
 
 	retval = SCTP_DISPOSITION_CONSUME;
 
-	sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort));
+	if (abort)
+		sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort));
 
 	/* Even if we can't send the ABORT due to low memory delete the
 	 * TCB.  This is a departure from our typical NOMEM handling.
@@ -4966,7 +4967,8 @@ sctp_disposition_t sctp_sf_cookie_wait_prm_abort(
 			SCTP_TO(SCTP_EVENT_TIMEOUT_T1_INIT));
 	retval = SCTP_DISPOSITION_CONSUME;
 
-	sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort));
+	if (abort)
+		sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort));
 
 	sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE,
 			SCTP_STATE(SCTP_STATE_CLOSED));
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 4130c1b..72da7d5 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1518,8 +1518,7 @@ static void sctp_close(struct sock *sk, long timeout)
 			struct sctp_chunk *chunk;
 
 			chunk = sctp_make_abort_user(asoc, NULL, 0);
-			if (chunk)
-				sctp_primitive_ABORT(net, asoc, chunk);
+			sctp_primitive_ABORT(net, asoc, chunk);
 		} else
 			sctp_primitive_SHUTDOWN(net, asoc, NULL);
 	}
-- 
2.1.0


From f987c7362d52ec928640585b494778f97e9b7ba4 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 31 Dec 2015 14:26:33 +0100
Subject: [PATCH 04/24] connector: bump skb->users before callback invocation

[ Upstream commit 55285bf09427c5abf43ee1d54e892f352092b1f1 ]

Dmitry reports memleak with syskaller program.
Problem is that connector bumps skb usecount but might not invoke callback.

So move skb_get to where we invoke the callback.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/connector/connector.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c
index f612d68..fd7430e 100644
--- a/drivers/connector/connector.c
+++ b/drivers/connector/connector.c
@@ -172,26 +172,21 @@ static int cn_call_callback(struct sk_buff *skb)
  *
  * It checks skb, netlink header and msg sizes, and calls callback helper.
  */
-static void cn_rx_skb(struct sk_buff *__skb)
+static void cn_rx_skb(struct sk_buff *skb)
 {
 	struct nlmsghdr *nlh;
-	struct sk_buff *skb;
 	int len, err;
 
-	skb = skb_get(__skb);
-
 	if (skb->len >= NLMSG_HDRLEN) {
 		nlh = nlmsg_hdr(skb);
 		len = nlmsg_len(nlh);
 
 		if (len < (int)sizeof(struct cn_msg) ||
 		    skb->len < nlh->nlmsg_len ||
-		    len > CONNECTOR_MAX_MSG_SIZE) {
-			kfree_skb(skb);
+		    len > CONNECTOR_MAX_MSG_SIZE)
 			return;
-		}
 
-		err = cn_call_callback(skb);
+		err = cn_call_callback(skb_get(skb));
 		if (err < 0)
 			kfree_skb(skb);
 	}
-- 
2.1.0


From d24a1c8a25acd6bc06ed0034bc8dedd58b537db4 Mon Sep 17 00:00:00 2001
From: willy tarreau <w@1wt.eu>
Date: Sun, 10 Jan 2016 07:54:56 +0100
Subject: [PATCH 05/24] unix: properly account for FDs passed over unix sockets

[ Upstream commit 712f4aad406bb1ed67f3f98d04c044191f0ff593 ]

It is possible for a process to allocate and accumulate far more FDs than
the process' limit by sending them over a unix socket then closing them
to keep the process' fd count low.

This change addresses this problem by keeping track of the number of FDs
in flight per user and preventing non-privileged processes from having
more FDs in flight than their configured FD limit.

Reported-by: socketpair@gmail.com
Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Mitigates: CVE-2013-4312 (Linux 2.0+)
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/sched.h |  1 +
 net/unix/af_unix.c    | 24 ++++++++++++++++++++----
 net/unix/garbage.c    | 16 ++++++++++++----
 3 files changed, 33 insertions(+), 8 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5e344bb..2a0bcc8 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -758,6 +758,7 @@ struct user_struct {
 	unsigned long mq_bytes;	/* How many bytes can be allocated to mqueue? */
 #endif
 	unsigned long locked_shm; /* How many pages of mlocked shm ? */
+	unsigned long unix_inflight;	/* How many files in flight in unix sockets */
 
 #ifdef CONFIG_KEYS
 	struct key *uid_keyring;	/* UID specific keyring */
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 7229794..20d7526 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1486,6 +1486,21 @@ static void unix_destruct_scm(struct sk_buff *skb)
 	sock_wfree(skb);
 }
 
+/*
+ * The "user->unix_inflight" variable is protected by the garbage
+ * collection lock, and we just read it locklessly here. If you go
+ * over the limit, there might be a tiny race in actually noticing
+ * it across threads. Tough.
+ */
+static inline bool too_many_unix_fds(struct task_struct *p)
+{
+	struct user_struct *user = current_user();
+
+	if (unlikely(user->unix_inflight > task_rlimit(p, RLIMIT_NOFILE)))
+		return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN);
+	return false;
+}
+
 #define MAX_RECURSION_LEVEL 4
 
 static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
@@ -1494,6 +1509,9 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
 	unsigned char max_level = 0;
 	int unix_sock_count = 0;
 
+	if (too_many_unix_fds(current))
+		return -ETOOMANYREFS;
+
 	for (i = scm->fp->count - 1; i >= 0; i--) {
 		struct sock *sk = unix_get_socket(scm->fp->fp[i]);
 
@@ -1515,10 +1533,8 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
 	if (!UNIXCB(skb).fp)
 		return -ENOMEM;
 
-	if (unix_sock_count) {
-		for (i = scm->fp->count - 1; i >= 0; i--)
-			unix_inflight(scm->fp->fp[i]);
-	}
+	for (i = scm->fp->count - 1; i >= 0; i--)
+		unix_inflight(scm->fp->fp[i]);
 	return max_level;
 }
 
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 99f7012..6247787 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -125,9 +125,12 @@ struct sock *unix_get_socket(struct file *filp)
 void unix_inflight(struct file *fp)
 {
 	struct sock *s = unix_get_socket(fp);
+
+	spin_lock(&unix_gc_lock);
+
 	if (s) {
 		struct unix_sock *u = unix_sk(s);
-		spin_lock(&unix_gc_lock);
+
 		if (atomic_long_inc_return(&u->inflight) == 1) {
 			BUG_ON(!list_empty(&u->link));
 			list_add_tail(&u->link, &gc_inflight_list);
@@ -135,22 +138,27 @@ void unix_inflight(struct file *fp)
 			BUG_ON(list_empty(&u->link));
 		}
 		unix_tot_inflight++;
-		spin_unlock(&unix_gc_lock);
 	}
+	fp->f_cred->user->unix_inflight++;
+	spin_unlock(&unix_gc_lock);
 }
 
 void unix_notinflight(struct file *fp)
 {
 	struct sock *s = unix_get_socket(fp);
+
+	spin_lock(&unix_gc_lock);
+
 	if (s) {
 		struct unix_sock *u = unix_sk(s);
-		spin_lock(&unix_gc_lock);
+
 		BUG_ON(list_empty(&u->link));
 		if (atomic_long_dec_and_test(&u->inflight))
 			list_del_init(&u->link);
 		unix_tot_inflight--;
-		spin_unlock(&unix_gc_lock);
 	}
+	fp->f_cred->user->unix_inflight--;
+	spin_unlock(&unix_gc_lock);
 }
 
 static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *),
-- 
2.1.0


From 99cc506b971342f6983e8e123266210ff18473fe Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Tue, 5 Jan 2016 10:46:00 +0100
Subject: [PATCH 06/24] bridge: Only call /sbin/bridge-stp for the initial
 network namespace

[ Upstream commit ff62198553e43cdffa9d539f6165d3e83f8a42bc ]

[I stole this patch from Eric Biederman. He wrote:]

> There is no defined mechanism to pass network namespace information
> into /sbin/bridge-stp therefore don't even try to invoke it except
> for bridge devices in the initial network namespace.
>
> It is possible for unprivileged users to cause /sbin/bridge-stp to be
> invoked for any network device name which if /sbin/bridge-stp does not
> guard against unreasonable arguments or being invoked twice on the
> same network device could cause problems.

[Hannes: changed patch using netns_eq]

Cc: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_stp_if.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
index 7832d07..ce658ab 100644
--- a/net/bridge/br_stp_if.c
+++ b/net/bridge/br_stp_if.c
@@ -128,7 +128,10 @@ static void br_stp_start(struct net_bridge *br)
 	char *argv[] = { BR_STP_PROG, br->dev->name, "start", NULL };
 	char *envp[] = { NULL };
 
-	r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC);
+	if (net_eq(dev_net(br->dev), &init_net))
+		r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC);
+	else
+		r = -ENOENT;
 
 	spin_lock_bh(&br->lock);
 
-- 
2.1.0


From 2cd76a189ed36b12845d96c81fb8200696544fc2 Mon Sep 17 00:00:00 2001
From: Rabin Vincent <rabin@rab.in>
Date: Tue, 5 Jan 2016 16:23:07 +0100
Subject: [PATCH 07/24] net: filter: make JITs zero A for SKF_AD_ALU_XOR_X

[ Upstream commit 55795ef5469290f89f04e12e662ded604909e462 ]

The SKF_AD_ALU_XOR_X ancillary is not like the other ancillary data
instructions since it XORs A with X while all the others replace A with
some loaded value.  All the BPF JITs fail to clear A if this is used as
the first instruction in a filter.  This was found using american fuzzy
lop.

Add a helper to determine if A needs to be cleared given the first
instruction in a filter, and use this in the JITs.  Except for ARM, the
rest have only been compile-tested.

Fixes: 3480593131e0 ("net: filter: get rid of BPF_S_* enum")
Signed-off-by: Rabin Vincent <rabin@rab.in>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/arm/net/bpf_jit_32.c       | 16 +---------------
 arch/mips/net/bpf_jit.c         | 16 +---------------
 arch/powerpc/net/bpf_jit_comp.c | 13 ++-----------
 arch/sparc/net/bpf_jit_comp.c   | 17 ++---------------
 include/linux/filter.h          | 19 +++++++++++++++++++
 5 files changed, 25 insertions(+), 56 deletions(-)

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index f412b53..ace4dc1 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -161,19 +161,6 @@ static inline int mem_words_used(struct jit_ctx *ctx)
 	return fls(ctx->seen & SEEN_MEM);
 }
 
-static inline bool is_load_to_a(u16 inst)
-{
-	switch (inst) {
-	case BPF_LD | BPF_W | BPF_LEN:
-	case BPF_LD | BPF_W | BPF_ABS:
-	case BPF_LD | BPF_H | BPF_ABS:
-	case BPF_LD | BPF_B | BPF_ABS:
-		return true;
-	default:
-		return false;
-	}
-}
-
 static void jit_fill_hole(void *area, unsigned int size)
 {
 	u32 *ptr;
@@ -185,7 +172,6 @@ static void jit_fill_hole(void *area, unsigned int size)
 static void build_prologue(struct jit_ctx *ctx)
 {
 	u16 reg_set = saved_regs(ctx);
-	u16 first_inst = ctx->skf->insns[0].code;
 	u16 off;
 
 #ifdef CONFIG_FRAME_POINTER
@@ -215,7 +201,7 @@ static void build_prologue(struct jit_ctx *ctx)
 		emit(ARM_MOV_I(r_X, 0), ctx);
 
 	/* do not leak kernel data to userspace */
-	if ((first_inst != (BPF_RET | BPF_K)) && !(is_load_to_a(first_inst)))
+	if (bpf_needs_clear_a(&ctx->skf->insns[0]))
 		emit(ARM_MOV_I(r_A, 0), ctx);
 
 	/* stack space for the BPF_MEM words */
diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c
index 9fd6834..9fd82f4 100644
--- a/arch/mips/net/bpf_jit.c
+++ b/arch/mips/net/bpf_jit.c
@@ -556,19 +556,6 @@ static inline u16 align_sp(unsigned int num)
 	return num;
 }
 
-static bool is_load_to_a(u16 inst)
-{
-	switch (inst) {
-	case BPF_LD | BPF_W | BPF_LEN:
-	case BPF_LD | BPF_W | BPF_ABS:
-	case BPF_LD | BPF_H | BPF_ABS:
-	case BPF_LD | BPF_B | BPF_ABS:
-		return true;
-	default:
-		return false;
-	}
-}
-
 static void save_bpf_jit_regs(struct jit_ctx *ctx, unsigned offset)
 {
 	int i = 0, real_off = 0;
@@ -690,7 +677,6 @@ static unsigned int get_stack_depth(struct jit_ctx *ctx)
 
 static void build_prologue(struct jit_ctx *ctx)
 {
-	u16 first_inst = ctx->skf->insns[0].code;
 	int sp_off;
 
 	/* Calculate the total offset for the stack pointer */
@@ -704,7 +690,7 @@ static void build_prologue(struct jit_ctx *ctx)
 		emit_jit_reg_move(r_X, r_zero, ctx);
 
 	/* Do not leak kernel data to userspace */
-	if ((first_inst != (BPF_RET | BPF_K)) && !(is_load_to_a(first_inst)))
+	if (bpf_needs_clear_a(&ctx->skf->insns[0]))
 		emit_jit_reg_move(r_A, r_zero, ctx);
 }
 
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index cbae2df..6a29085 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -78,18 +78,9 @@ static void bpf_jit_build_prologue(struct bpf_prog *fp, u32 *image,
 		PPC_LI(r_X, 0);
 	}
 
-	switch (filter[0].code) {
-	case BPF_RET | BPF_K:
-	case BPF_LD | BPF_W | BPF_LEN:
-	case BPF_LD | BPF_W | BPF_ABS:
-	case BPF_LD | BPF_H | BPF_ABS:
-	case BPF_LD | BPF_B | BPF_ABS:
-		/* first instruction sets A register (or is RET 'constant') */
-		break;
-	default:
-		/* make sure we dont leak kernel information to user */
+	/* make sure we dont leak kernel information to user */
+	if (bpf_needs_clear_a(&filter[0]))
 		PPC_LI(r_A, 0);
-	}
 }
 
 static void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c
index f33e7c7..5cf170a 100644
--- a/arch/sparc/net/bpf_jit_comp.c
+++ b/arch/sparc/net/bpf_jit_comp.c
@@ -420,22 +420,9 @@ void bpf_jit_compile(struct bpf_prog *fp)
 		}
 		emit_reg_move(O7, r_saved_O7);
 
-		switch (filter[0].code) {
-		case BPF_RET | BPF_K:
-		case BPF_LD | BPF_W | BPF_LEN:
-		case BPF_LD | BPF_W | BPF_ABS:
-		case BPF_LD | BPF_H | BPF_ABS:
-		case BPF_LD | BPF_B | BPF_ABS:
-			/* The first instruction sets the A register (or is
-			 * a "RET 'constant'")
-			 */
-			break;
-		default:
-			/* Make sure we dont leak kernel information to the
-			 * user.
-			 */
+		/* Make sure we dont leak kernel information to the user. */
+		if (bpf_needs_clear_a(&filter[0]))
 			emit_clear(r_A); /* A = 0 */
-		}
 
 		for (i = 0; i < flen; i++) {
 			unsigned int K = filter[i].k;
diff --git a/include/linux/filter.h b/include/linux/filter.h
index ca95abd..c80b1a9 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -427,6 +427,25 @@ static inline void bpf_jit_free(struct bpf_prog *fp)
 
 #define BPF_ANC		BIT(15)
 
+static inline bool bpf_needs_clear_a(const struct sock_filter *first)
+{
+	switch (first->code) {
+	case BPF_RET | BPF_K:
+	case BPF_LD | BPF_W | BPF_LEN:
+		return false;
+
+	case BPF_LD | BPF_W | BPF_ABS:
+	case BPF_LD | BPF_H | BPF_ABS:
+	case BPF_LD | BPF_B | BPF_ABS:
+		if (first->k == SKF_AD_OFF + SKF_AD_ALU_XOR_X)
+			return true;
+		return false;
+
+	default:
+		return true;
+	}
+}
+
 static inline u16 bpf_anc_helper(const struct sock_filter *ftest)
 {
 	BUG_ON(ftest->code & BPF_ANC);
-- 
2.1.0


From 40406822c9c19ca7658257e5e730976b8ce912da Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Tue, 5 Jan 2016 09:11:36 -0800
Subject: [PATCH 08/24] net: sched: fix missing free per cpu on qstats

[ Upstream commit 73c20a8b7245273125cfe92c4b46e6fdb568a801 ]

When a qdisc is using per cpu stats (currently just the ingress
qdisc) only the bstats are being freed. This also free's the qstats.

Fixes: b0ab6f92752b9f9d8 ("net: sched: enable per cpu qstats")
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_generic.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 6efca30..507edcf 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -666,8 +666,10 @@ static void qdisc_rcu_free(struct rcu_head *head)
 {
 	struct Qdisc *qdisc = container_of(head, struct Qdisc, rcu_head);
 
-	if (qdisc_is_percpu_stats(qdisc))
+	if (qdisc_is_percpu_stats(qdisc)) {
 		free_percpu(qdisc->cpu_bstats);
+		free_percpu(qdisc->cpu_qstats);
+	}
 
 	kfree((char *) qdisc - qdisc->padded);
 }
-- 
2.1.0


From 48eafb48f05ca20965c8a8c6a354bf65830996de Mon Sep 17 00:00:00 2001
From: Francesco Ruggeri <fruggeri@aristanetworks.com>
Date: Wed, 6 Jan 2016 00:18:48 -0800
Subject: [PATCH 09/24] net: possible use after free in dst_release

[ Upstream commit 07a5d38453599052aff0877b16bb9c1585f08609 ]

dst_release should not access dst->flags after decrementing
__refcnt to 0. The dst_entry may be in dst_busy_list and
dst_gc_task may dst_destroy it before dst_release gets a chance
to access dst->flags.

Fixes: d69bbf88c8d0 ("net: fix a race in dst_release()")
Fixes: 27b75c95f10d ("net: avoid RCU for NOCACHE dst")
Signed-off-by: Francesco Ruggeri <fruggeri@arista.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dst.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/dst.c b/net/core/dst.c
index a80e923..57746a1 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -282,10 +282,11 @@ void dst_release(struct dst_entry *dst)
 {
 	if (dst) {
 		int newrefcnt;
+		unsigned short nocache = dst->flags & DST_NOCACHE;
 
 		newrefcnt = atomic_dec_return(&dst->__refcnt);
 		WARN_ON(newrefcnt < 0);
-		if (!newrefcnt && unlikely(dst->flags & DST_NOCACHE))
+		if (!newrefcnt && unlikely(nocache))
 			call_rcu(&dst->rcu_head, dst_destroy_rcu);
 	}
 }
-- 
2.1.0


From f6a9194bfd5c4ffbd2a52f4fedcd56bd339f4edc Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Thu, 7 Jan 2016 11:26:53 +0100
Subject: [PATCH 10/24] vxlan: fix test which detect duplicate vxlan iface

[ Upstream commit 07b9b37c227cb8d88d478b4a9c5634fee514ede1 ]

When a vxlan interface is created, the driver checks that there is not
another vxlan interface with the same properties. To do this, it checks
the existing vxlan udp socket. Since commit 1c51a9159dde, the creation of
the vxlan socket is done only when the interface is set up, thus it breaks
that test.

Example:
$ ip l a vxlan10 type vxlan id 10 group 239.0.0.10 dev eth0 dstport 0
$ ip l a vxlan11 type vxlan id 10 group 239.0.0.10 dev eth0 dstport 0
$ ip -br l | grep vxlan
vxlan10          DOWN           f2:55:1c:6a:fb:00 <BROADCAST,MULTICAST>
vxlan11          DOWN           7a:cb:b9:38:59:0d <BROADCAST,MULTICAST>

Instead of checking sockets, let's loop over the vxlan iface list.

Fixes: 1c51a9159dde ("vxlan: fix race caused by dropping rtnl_unlock")
Reported-by: Thomas Faivre <thomas.faivre@6wind.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 12 ++++++++----
 include/net/vxlan.h |  5 +++++
 2 files changed, 13 insertions(+), 4 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 2826c55..59282dd 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2433,7 +2433,7 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
 			 struct nlattr *tb[], struct nlattr *data[])
 {
 	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
-	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_dev *vxlan = netdev_priv(dev), *tmp;
 	struct vxlan_rdst *dst = &vxlan->default_dst;
 	__u32 vni;
 	int err;
@@ -2554,9 +2554,13 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
 	    nla_get_u8(data[IFLA_VXLAN_UDP_ZERO_CSUM6_RX]))
 		vxlan->flags |= VXLAN_F_UDP_ZERO_CSUM6_RX;
 
-	if (vxlan_find_vni(net, vni, use_ipv6 ? AF_INET6 : AF_INET,
-			   vxlan->dst_port)) {
-		pr_info("duplicate VNI %u\n", vni);
+	list_for_each_entry(tmp, &vn->vxlan_list, next) {
+		if (tmp->default_dst.remote_vni == vni &&
+		    (tmp->default_dst.remote_ip.sa.sa_family == AF_INET6 ||
+		     tmp->saddr.sa.sa_family == AF_INET6) == use_ipv6 &&
+		    tmp->dst_port == vxlan->dst_port &&
+		    (tmp->flags & VXLAN_F_RCV_FLAGS) ==
+		    (vxlan->flags & VXLAN_F_RCV_FLAGS))
 		return -EEXIST;
 	}
 
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 903461a..2f3572f 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -43,6 +43,11 @@ struct vxlan_sock {
 #define VXLAN_F_UDP_ZERO_CSUM6_TX	0x80
 #define VXLAN_F_UDP_ZERO_CSUM6_RX	0x100
 
+/* Flags that are used in the receive path. These flags must match in
+ * order for a socket to be shareable
+ */
+#define VXLAN_F_RCV_FLAGS		VXLAN_F_UDP_ZERO_CSUM6_RX
+					 
 struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
 				  vxlan_rcv_t *rcv, void *data,
 				  bool no_share, u32 flags);
-- 
2.1.0


From 586ab7a6fdbaed7ec6e85c1310135a6675b7e962 Mon Sep 17 00:00:00 2001
From: Sasha Levin <sasha.levin@oracle.com>
Date: Thu, 7 Jan 2016 14:52:43 -0500
Subject: [PATCH 11/24] net: sctp: prevent writes to cookie_hmac_alg from
 accessing invalid memory

[ Upstream commit 320f1a4a175e7cd5d3f006f92b4d4d3e2cbb7bb5 ]

proc_dostring() needs an initialized destination string, while the one
provided in proc_sctp_do_hmac_alg() contains stack garbage.

Thus, writing to cookie_hmac_alg would strlen() that garbage and end up
accessing invalid memory.

Fixes: 3c68198e7 ("sctp: Make hmac algorithm selection for cookie generation dynamic")
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sysctl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index 2e9ada1..5b6e757 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -324,7 +324,7 @@ static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write,
 	struct ctl_table tbl;
 	bool changed = false;
 	char *none = "none";
-	char tmp[8];
+	char tmp[8] = {0};
 	int ret;
 
 	memset(&tbl, 0, sizeof(struct ctl_table));
-- 
2.1.0


From 6fcac4abbc902e119f35a2b54cb5d5c56d68cf1a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 8 Jan 2016 09:35:51 -0800
Subject: [PATCH 12/24] ipv6: tcp: add rcu locking in tcp_v6_send_synack()

[ Upstream commit 3e4006f0b86a5ae5eb0e8215f9a9e1db24506977 ]

When first SYNACK is sent, we already hold rcu_read_lock(), but this
is not true if a SYNACK is retransmitted, as a timer (soft) interrupt
does not hold rcu_read_lock()

Fixes: 45f6fad84cc30 ("ipv6: add complete rcu protection around np->opt")
Reported-by: Dave Jones <davej@codemonkey.org.uk>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/tcp_ipv6.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index b5a4ac8..78d1806 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -502,8 +502,10 @@ static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst,
 			fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));
 
 		skb_set_queue_mapping(skb, queue_mapping);
+		rcu_read_lock();
 		err = ip6_xmit(sk, skb, fl6, rcu_dereference(np->opt),
 			       np->tclass);
+		rcu_read_unlock();
 		err = net_xmit_eval(err);
 	}
 
-- 
2.1.0


From 981f2b8610d04d2db4fa14aabe3a630ef6556461 Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Mon, 11 Jan 2016 13:42:43 -0500
Subject: [PATCH 13/24] tcp_yeah: don't set ssthresh below 2

[ Upstream commit 83d15e70c4d8909d722c0d64747d8fb42e38a48f ]

For tcp_yeah, use an ssthresh floor of 2, the same floor used by Reno
and CUBIC, per RFC 5681 (equation 4).

tcp_yeah_ssthresh() was sometimes returning a 0 or negative ssthresh
value if the intended reduction is as big or bigger than the current
cwnd. Congestion control modules should never return a zero or
negative ssthresh. A zero ssthresh generally results in a zero cwnd,
causing the connection to stall. A negative ssthresh value will be
interpreted as a u32 and will set a target cwnd for PRR near 4
billion.

Oleksandr Natalenko reported that a system using tcp_yeah with ECN
could see a warning about a prior_cwnd of 0 in
tcp_cwnd_reduction(). Testing verified that this was due to
tcp_yeah_ssthresh() misbehaving in this way.

Reported-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_yeah.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c
index cd72732..25a2297 100644
--- a/net/ipv4/tcp_yeah.c
+++ b/net/ipv4/tcp_yeah.c
@@ -219,7 +219,7 @@ static u32 tcp_yeah_ssthresh(struct sock *sk)
 	yeah->fast_count = 0;
 	yeah->reno_count = max(yeah->reno_count>>1, 2U);
 
-	return tp->snd_cwnd - reduction;
+	return max_t(int, tp->snd_cwnd - reduction, 2);
 }
 
 static struct tcp_congestion_ops tcp_yeah __read_mostly = {
-- 
2.1.0


From 715bfbb3cf9cbbc4010426899a205e9ecd2a12a0 Mon Sep 17 00:00:00 2001
From: Karl Heiss <kheiss@gmail.com>
Date: Mon, 11 Jan 2016 08:28:43 -0500
Subject: [PATCH 14/24] bonding: Prevent IPv6 link local address on enslaved
 devices

[ Upstream commit 03d84a5f83a67e692af00a3d3901e7820e3e84d5 ]

Commit 1f718f0f4f97 ("bonding: populate neighbour's private on enslave")
undoes the fix provided by commit c2edacf80e15 ("bonding / ipv6: no addrconf
for slaves separately from master") by effectively setting the slave flag
after the slave has been opened.  If the slave comes up quickly enough, it
will go through the IPv6 addrconf before the slave flag has been set and
will get a link local IPv6 address.

In order to ensure that addrconf knows to ignore the slave devices on state
change, set IFF_SLAVE before dev_open() during bonding enslavement.

Fixes: 1f718f0f4f97 ("bonding: populate neighbour's private on enslave")
Signed-off-by: Karl Heiss <kheiss@gmail.com>
Signed-off-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Reviewed-by: Jarod Wilson <jarod@redhat.com>
Signed-off-by: Andy Gospodarek <gospo@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 081dd70..566054c 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1154,7 +1154,6 @@ static int bond_master_upper_dev_link(struct net_device *bond_dev,
 	err = netdev_master_upper_dev_link_private(slave_dev, bond_dev, slave);
 	if (err)
 		return err;
-	slave_dev->flags |= IFF_SLAVE;
 	rtmsg_ifinfo(RTM_NEWLINK, slave_dev, IFF_SLAVE, GFP_KERNEL);
 	return 0;
 }
@@ -1362,6 +1361,9 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 		}
 	}
 
+	/* set slave flag before open to prevent IPv6 addrconf */
+	slave_dev->flags |= IFF_SLAVE;
+
 	/* open the slave since the application closed it */
 	res = dev_open(slave_dev);
 	if (res) {
@@ -1615,6 +1617,7 @@ err_close:
 	dev_close(slave_dev);
 
 err_restore_mac:
+	slave_dev->flags &= ~IFF_SLAVE;
 	if (!bond->params.fail_over_mac ||
 	    BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
 		/* XXX TODO - fom follow mode needs to change master's
-- 
2.1.0


From b9ee143fb9124f71cd048f7eadfb6b91609e7d58 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 12 Jan 2016 08:58:00 -0800
Subject: [PATCH 15/24] phonet: properly unshare skbs in phonet_rcv()

[ Upstream commit 7aaed57c5c2890634cfadf725173c7c68ea4cb4f ]

Ivaylo Dimitrov reported a regression caused by commit 7866a621043f
("dev: add per net_device packet type chains").

skb->dev becomes NULL and we crash in __netif_receive_skb_core().

Before above commit, different kind of bugs or corruptions could happen
without major crash.

But the root cause is that phonet_rcv() can queue skb without checking
if skb is shared or not.

Many thanks to Ivaylo Dimitrov for his help, diagnosis and tests.

Reported-by: Ivaylo Dimitrov <ivo.g.dimitrov.75@gmail.com>
Tested-by: Ivaylo Dimitrov <ivo.g.dimitrov.75@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Remi Denis-Courmont <courmisch@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/phonet/af_phonet.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c
index 5a940db..f022922 100644
--- a/net/phonet/af_phonet.c
+++ b/net/phonet/af_phonet.c
@@ -377,6 +377,10 @@ static int phonet_rcv(struct sk_buff *skb, struct net_device *dev,
 	struct sockaddr_pn sa;
 	u16 len;
 
+	skb = skb_share_check(skb, GFP_ATOMIC);
+	if (!skb)
+		return NET_RX_DROP;
+
 	/* check we have at least a full Phonet header */
 	if (!pskb_pull(skb, sizeof(struct phonethdr)))
 		goto out;
-- 
2.1.0


From f05eb57de8cda97185f08df36eeca00aa490ea4c Mon Sep 17 00:00:00 2001
From: Rabin Vincent <rabin@rab.in>
Date: Tue, 12 Jan 2016 20:17:08 +0100
Subject: [PATCH 16/24] net: bpf: reject invalid shifts

[ Upstream commit 229394e8e62a4191d592842cf67e80c62a492937 ]

On ARM64, a BUG() is triggered in the eBPF JIT if a filter with a
constant shift that can't be encoded in the immediate field of the
UBFM/SBFM instructions is passed to the JIT.  Since these shifts
amounts, which are negative or >= regsize, are invalid, reject them in
the eBPF verifier and the classic BPF filter checker, for all
architectures.

Signed-off-by: Rabin Vincent <rabin@rab.in>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c | 10 ++++++++++
 net/core/filter.c     |  5 +++++
 2 files changed, 15 insertions(+)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 055ae6a..67f5f17 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1025,6 +1025,16 @@ static int check_alu_op(struct reg_state *regs, struct bpf_insn *insn)
 			return -EINVAL;
 		}
 
+		if ((opcode == BPF_LSH || opcode == BPF_RSH ||
+		     opcode == BPF_ARSH) && BPF_SRC(insn->code) == BPF_K) {
+			int size = BPF_CLASS(insn->code) == BPF_ALU64 ? 64 : 32;
+
+			if (insn->imm < 0 || insn->imm >= size) {
+				verbose("invalid shift %d\n", insn->imm);
+				return -EINVAL;
+			}
+		}
+
 		/* pattern match 'bpf_add Rx, imm' instruction */
 		if (opcode == BPF_ADD && BPF_CLASS(insn->code) == BPF_ALU64 &&
 		    regs[insn->dst_reg].type == FRAME_PTR &&
diff --git a/net/core/filter.c b/net/core/filter.c
index 647b122..e6cde173 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -728,6 +728,11 @@ int bpf_check_classic(const struct sock_filter *filter, unsigned int flen)
 			if (ftest->k == 0)
 				return -EINVAL;
 			break;
+		case BPF_ALU | BPF_LSH | BPF_K:
+		case BPF_ALU | BPF_RSH | BPF_K:
+			if (ftest->k >= 32)
+				return -EINVAL;
+			break;
 		case BPF_LD | BPF_MEM:
 		case BPF_LDX | BPF_MEM:
 		case BPF_ST:
-- 
2.1.0


From 56203ff50f061ca52e86ae9de55dadf6c1410d61 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 15 Jan 2016 04:56:56 -0800
Subject: [PATCH 17/24] ipv6: update skb->csum when CE mark is propagated

[ Upstream commit 34ae6a1aa0540f0f781dd265366036355fdc8930 ]

When a tunnel decapsulates the outer header, it has to comply
with RFC 6080 and eventually propagate CE mark into inner header.

It turns out IP6_ECN_set_ce() does not correctly update skb->csum
for CHECKSUM_COMPLETE packets, triggering infamous "hw csum failure"
messages and stack traces.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_ecn.h       | 19 ++++++++++++++++---
 net/ipv6/xfrm6_mode_tunnel.c |  2 +-
 2 files changed, 17 insertions(+), 4 deletions(-)

diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h
index 84b2083..0dc0a51 100644
--- a/include/net/inet_ecn.h
+++ b/include/net/inet_ecn.h
@@ -111,11 +111,24 @@ static inline void ipv4_copy_dscp(unsigned int dscp, struct iphdr *inner)
 
 struct ipv6hdr;
 
-static inline int IP6_ECN_set_ce(struct ipv6hdr *iph)
+/* Note:
+ * IP_ECN_set_ce() has to tweak IPV4 checksum when setting CE,
+ * meaning both changes have no effect on skb->csum if/when CHECKSUM_COMPLETE
+ * In IPv6 case, no checksum compensates the change in IPv6 header,
+ * so we have to update skb->csum.
+ */
+static inline int IP6_ECN_set_ce(struct sk_buff *skb, struct ipv6hdr *iph)
 {
+	__be32 from, to;
+
 	if (INET_ECN_is_not_ect(ipv6_get_dsfield(iph)))
 		return 0;
-	*(__be32*)iph |= htonl(INET_ECN_CE << 20);
+
+	from = *(__be32 *)iph;
+	to = from | htonl(INET_ECN_CE << 20);
+	*(__be32 *)iph = to;
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		skb->csum = csum_add(csum_sub(skb->csum, from), to);
 	return 1;
 }
 
@@ -142,7 +155,7 @@ static inline int INET_ECN_set_ce(struct sk_buff *skb)
 	case cpu_to_be16(ETH_P_IPV6):
 		if (skb_network_header(skb) + sizeof(struct ipv6hdr) <=
 		    skb_tail_pointer(skb))
-			return IP6_ECN_set_ce(ipv6_hdr(skb));
+			return IP6_ECN_set_ce(skb, ipv6_hdr(skb));
 		break;
 	}
 
diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c
index 901ef6f..5266ad2 100644
--- a/net/ipv6/xfrm6_mode_tunnel.c
+++ b/net/ipv6/xfrm6_mode_tunnel.c
@@ -24,7 +24,7 @@ static inline void ipip6_ecn_decapsulate(struct sk_buff *skb)
 	struct ipv6hdr *inner_iph = ipipv6_hdr(skb);
 
 	if (INET_ECN_is_ce(ipv6_get_dsfield(outer_iph)))
-		IP6_ECN_set_ce(inner_iph);
+		IP6_ECN_set_ce(skb, inner_iph);
 }
 
 /* Add encapsulation header.
-- 
2.1.0


From 4504757da0e2ac31490772e5b77ef30d83efb5d7 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben@decadent.org.uk>
Date: Sun, 1 Nov 2015 16:21:24 +0000
Subject: [PATCH 18/24] isdn_ppp: Add checks for allocation failure in
 isdn_ppp_open()

[ Upstream commit 0baa57d8dc32db78369d8b5176ef56c5e2e18ab3 ]

Compile-tested only.

Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/i4l/isdn_ppp.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/isdn/i4l/isdn_ppp.c b/drivers/isdn/i4l/isdn_ppp.c
index c4198fa..86f9abe 100644
--- a/drivers/isdn/i4l/isdn_ppp.c
+++ b/drivers/isdn/i4l/isdn_ppp.c
@@ -301,6 +301,8 @@ isdn_ppp_open(int min, struct file *file)
 	is->compflags = 0;
 
 	is->reset = isdn_ppp_ccp_reset_alloc(is);
+	if (!is->reset)
+		return -ENOMEM;
 
 	is->lp = NULL;
 	is->mp_seqno = 0;       /* MP sequence number */
@@ -320,6 +322,10 @@ isdn_ppp_open(int min, struct file *file)
 	 * VJ header compression init
 	 */
 	is->slcomp = slhc_init(16, 16);	/* not necessary for 2. link in bundle */
+	if (!is->slcomp) {
+		isdn_ppp_ccp_reset_free(is);
+		return -ENOMEM;
+	}
 #endif
 #ifdef CONFIG_IPPP_FILTER
 	is->pass_filter = NULL;
-- 
2.1.0


From 4dcf66b6da01284a379307ee558fe76cd4f00e19 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben@decadent.org.uk>
Date: Sun, 1 Nov 2015 16:22:53 +0000
Subject: [PATCH 19/24] ppp, slip: Validate VJ compression slot parameters
 completely
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 4ab42d78e37a294ac7bc56901d563c642e03c4ae ]

Currently slhc_init() treats out-of-range values of rslots and tslots
as equivalent to 0, except that if tslots is too large it will
dereference a null pointer (CVE-2015-7799).

Add a range-check at the top of the function and make it return an
ERR_PTR() on error instead of NULL.  Change the callers accordingly.

Compile-tested only.

Reported-by: 郭永刚 <guoyonggang@360.cn>
References: http://article.gmane.org/gmane.comp.security.oss.general/17908
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/i4l/isdn_ppp.c   | 10 ++++------
 drivers/net/ppp/ppp_generic.c |  6 ++----
 drivers/net/slip/slhc.c       | 12 ++++++++----
 drivers/net/slip/slip.c       |  2 +-
 4 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/drivers/isdn/i4l/isdn_ppp.c b/drivers/isdn/i4l/isdn_ppp.c
index 86f9abe..9c1e8ad 100644
--- a/drivers/isdn/i4l/isdn_ppp.c
+++ b/drivers/isdn/i4l/isdn_ppp.c
@@ -322,9 +322,9 @@ isdn_ppp_open(int min, struct file *file)
 	 * VJ header compression init
 	 */
 	is->slcomp = slhc_init(16, 16);	/* not necessary for 2. link in bundle */
-	if (!is->slcomp) {
+	if (IS_ERR(is->slcomp)) {
 		isdn_ppp_ccp_reset_free(is);
-		return -ENOMEM;
+		return PTR_ERR(is->slcomp);
 	}
 #endif
 #ifdef CONFIG_IPPP_FILTER
@@ -573,10 +573,8 @@ isdn_ppp_ioctl(int min, struct file *file, unsigned int cmd, unsigned long arg)
 			is->maxcid = val;
 #ifdef CONFIG_ISDN_PPP_VJ
 			sltmp = slhc_init(16, val);
-			if (!sltmp) {
-				printk(KERN_ERR "ippp, can't realloc slhc struct\n");
-				return -ENOMEM;
-			}
+			if (IS_ERR(sltmp))
+				return PTR_ERR(sltmp);
 			if (is->slcomp)
 				slhc_free(is->slcomp);
 			is->slcomp = sltmp;
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 6d6c20c..fc7b3d76 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -713,10 +713,8 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 			val &= 0xffff;
 		}
 		vj = slhc_init(val2+1, val+1);
-		if (!vj) {
-			netdev_err(ppp->dev,
-				   "PPP: no memory (VJ compressor)\n");
-			err = -ENOMEM;
+		if (IS_ERR(vj)) {
+			err = PTR_ERR(vj);
 			break;
 		}
 		ppp_lock(ppp);
diff --git a/drivers/net/slip/slhc.c b/drivers/net/slip/slhc.c
index 079f7ad..27ed252 100644
--- a/drivers/net/slip/slhc.c
+++ b/drivers/net/slip/slhc.c
@@ -84,8 +84,9 @@ static long decode(unsigned char **cpp);
 static unsigned char * put16(unsigned char *cp, unsigned short x);
 static unsigned short pull16(unsigned char **cpp);
 
-/* Initialize compression data structure
+/* Allocate compression data structure
  *	slots must be in range 0 to 255 (zero meaning no compression)
+ * Returns pointer to structure or ERR_PTR() on error.
  */
 struct slcompress *
 slhc_init(int rslots, int tslots)
@@ -94,11 +95,14 @@ slhc_init(int rslots, int tslots)
 	register struct cstate *ts;
 	struct slcompress *comp;
 
+	if (rslots < 0 || rslots > 255 || tslots < 0 || tslots > 255)
+		return ERR_PTR(-EINVAL);
+
 	comp = kzalloc(sizeof(struct slcompress), GFP_KERNEL);
 	if (! comp)
 		goto out_fail;
 
-	if ( rslots > 0  &&  rslots < 256 ) {
+	if (rslots > 0) {
 		size_t rsize = rslots * sizeof(struct cstate);
 		comp->rstate = kzalloc(rsize, GFP_KERNEL);
 		if (! comp->rstate)
@@ -106,7 +110,7 @@ slhc_init(int rslots, int tslots)
 		comp->rslot_limit = rslots - 1;
 	}
 
-	if ( tslots > 0  &&  tslots < 256 ) {
+	if (tslots > 0) {
 		size_t tsize = tslots * sizeof(struct cstate);
 		comp->tstate = kzalloc(tsize, GFP_KERNEL);
 		if (! comp->tstate)
@@ -141,7 +145,7 @@ out_free2:
 out_free:
 	kfree(comp);
 out_fail:
-	return NULL;
+	return ERR_PTR(-ENOMEM);
 }
 
 
diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c
index 05387b1..a17d86a 100644
--- a/drivers/net/slip/slip.c
+++ b/drivers/net/slip/slip.c
@@ -164,7 +164,7 @@ static int sl_alloc_bufs(struct slip *sl, int mtu)
 	if (cbuff == NULL)
 		goto err_exit;
 	slcomp = slhc_init(16, 16);
-	if (slcomp == NULL)
+	if (IS_ERR(slcomp))
 		goto err_exit;
 #endif
 	spin_lock_bh(&sl->lock);
-- 
2.1.0


From 6bfe93ae59358f02193033b835dea14ea6b6d1d1 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Mon, 18 Jan 2016 17:30:22 +0200
Subject: [PATCH 20/24] team: Replace rcu_read_lock with a mutex in
 team_vlan_rx_kill_vid

[ Upstream commit 60a6531bfe49555581ccd65f66a350cc5693fcde ]

We can't be within an RCU read-side critical section when deleting
VLANs, as underlying drivers might sleep during the hardware operation.
Therefore, replace the RCU critical section with a mutex. This is
consistent with team_vlan_rx_add_vid.

Fixes: 3d249d4ca7d0 ("net: introduce ethernet teaming device")
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index ebc95a3..16c5803 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1848,10 +1848,10 @@ static int team_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid)
 	struct team *team = netdev_priv(dev);
 	struct team_port *port;
 
-	rcu_read_lock();
-	list_for_each_entry_rcu(port, &team->port_list, list)
+	mutex_lock(&team->lock);
+	list_for_each_entry(port, &team->port_list, list)
 		vlan_vid_del(port->dev, proto, vid);
-	rcu_read_unlock();
+	mutex_unlock(&team->lock);
 
 	return 0;
 }
-- 
2.1.0


From 3f55370371541f9234c3f0fdeee7b3adeb3cf85a Mon Sep 17 00:00:00 2001
From: Wei Liu <wei.liu2@citrix.com>
Date: Thu, 10 Sep 2015 11:18:57 +0100
Subject: [PATCH 21/24] xen-netback: respect user provided max_queues

[ Upstream commit 4c82ac3c37363e8c4ded6a5fe1ec5fa756b34df3 ]

Originally that parameter was always reset to num_online_cpus during
module initialisation, which renders it useless.

The fix is to only set max_queues to num_online_cpus when user has not
provided a value.

Reported-by: Johnny Strom <johnny.strom@linuxsolutions.fi>
Signed-off-by: Wei Liu <wei.liu2@citrix.com>
Reviewed-by: David Vrabel <david.vrabel@citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netback/netback.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index c39aace..63f9413 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -2185,8 +2185,11 @@ static int __init netback_init(void)
 	if (!xen_domain())
 		return -ENODEV;
 
-	/* Allow as many queues as there are CPUs, by default */
-	xenvif_max_queues = num_online_cpus();
+	/* Allow as many queues as there are CPUs if user has not
+	 * specified a value.
+	 */
+	if (xenvif_max_queues == 0)
+		xenvif_max_queues = num_online_cpus();
 
 	if (fatal_skb_slots < XEN_NETBK_LEGACY_SLOTS_MAX) {
 		pr_info("fatal_skb_slots too small (%d), bump it to XEN_NETBK_LEGACY_SLOTS_MAX (%d)\n",
-- 
2.1.0


From 39cfcfc0374336f3c15993f6f3ae4e43d7b6b502 Mon Sep 17 00:00:00 2001
From: Wei Liu <wei.liu2@citrix.com>
Date: Thu, 10 Sep 2015 11:18:58 +0100
Subject: [PATCH 22/24] xen-netfront: respect user provided max_queues

[ Upstream commit 32a844056fd43dda647e1c3c6b9983bdfa04d17d ]

Originally that parameter was always reset to num_online_cpus during
module initialisation, which renders it useless.

The fix is to only set max_queues to num_online_cpus when user has not
provided a value.

Signed-off-by: Wei Liu <wei.liu2@citrix.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Reviewed-by: David Vrabel <david.vrabel@citrix.com>
Tested-by: David Vrabel <david.vrabel@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netfront.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 2a64f28..2ab55b7 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -2351,8 +2351,11 @@ static int __init netif_init(void)
 
 	pr_info("Initialising Xen virtual ethernet driver\n");
 
-	/* Allow as many queues as there are CPUs, by default */
-	xennet_max_queues = num_online_cpus();
+	/* Allow as many queues as there are CPUs if user has not
+	 * specified a value.
+	 */
+	if (xennet_max_queues == 0)
+		xennet_max_queues = num_online_cpus();
 
 	return xenbus_register_frontend(&netfront_driver);
 }
-- 
2.1.0


From 7f331b214ef45a10f2fef44f9c03acd10b4fe883 Mon Sep 17 00:00:00 2001
From: Joe Jin <joe.jin@oracle.com>
Date: Mon, 19 Oct 2015 13:37:17 +0800
Subject: [PATCH 23/24] xen-netfront: update num_queues to real created

[ Upstream commit ca88ea1247dfee094e2467a3578eaec9bdf0833a ]

Sometimes xennet_create_queues() may failed to created all requested
queues, we need to update num_queues to real created to avoid NULL
pointer dereference.

Signed-off-by: Joe Jin <joe.jin@oracle.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Wei Liu <wei.liu2@citrix.com>
Cc: Ian Campbell <ian.campbell@citrix.com>
Cc: David S. Miller <davem@davemloft.net>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netfront.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 2ab55b7..8f45be1 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -1792,19 +1792,19 @@ static void xennet_destroy_queues(struct netfront_info *info)
 }
 
 static int xennet_create_queues(struct netfront_info *info,
-				unsigned int num_queues)
+				unsigned int *num_queues)
 {
 	unsigned int i;
 	int ret;
 
-	info->queues = kcalloc(num_queues, sizeof(struct netfront_queue),
+	info->queues = kcalloc(*num_queues, sizeof(struct netfront_queue),
 			       GFP_KERNEL);
 	if (!info->queues)
 		return -ENOMEM;
 
 	rtnl_lock();
 
-	for (i = 0; i < num_queues; i++) {
+	for (i = 0; i < *num_queues; i++) {
 		struct netfront_queue *queue = &info->queues[i];
 
 		queue->id = i;
@@ -1814,7 +1814,7 @@ static int xennet_create_queues(struct netfront_info *info,
 		if (ret < 0) {
 			dev_warn(&info->netdev->dev,
 				 "only created %d queues\n", i);
-			num_queues = i;
+			*num_queues = i;
 			break;
 		}
 
@@ -1824,11 +1824,11 @@ static int xennet_create_queues(struct netfront_info *info,
 			napi_enable(&queue->napi);
 	}
 
-	netif_set_real_num_tx_queues(info->netdev, num_queues);
+	netif_set_real_num_tx_queues(info->netdev, *num_queues);
 
 	rtnl_unlock();
 
-	if (num_queues == 0) {
+	if (*num_queues == 0) {
 		dev_err(&info->netdev->dev, "no queues\n");
 		return -EINVAL;
 	}
@@ -1874,7 +1874,7 @@ static int talk_to_netback(struct xenbus_device *dev,
 	if (info->queues)
 		xennet_destroy_queues(info);
 
-	err = xennet_create_queues(info, num_queues);
+	err = xennet_create_queues(info, &num_queues);
 	if (err < 0)
 		goto destroy_ring;
 
-- 
2.1.0


From 9b6adc4ed29162d0267b19f696f4632286a23ea0 Mon Sep 17 00:00:00 2001
From: Dan Streetman <dan.streetman@canonical.com>
Date: Thu, 29 Oct 2015 09:51:16 -0400
Subject: [PATCH 24/24] xfrm: dst_entries_init() per-net dst_ops

[ Upstream commit a8a572a6b5f2a79280d6e302cb3c1cb1fbaeb3e8 ]

Remove the dst_entries_init/destroy calls for xfrm4 and xfrm6 dst_ops
templates; their dst_entries counters will never be used.  Move the
xfrm dst_ops initialization from the common xfrm/xfrm_policy.c to
xfrm4/xfrm4_policy.c and xfrm6/xfrm6_policy.c, and call dst_entries_init
and dst_entries_destroy for each net namespace.

The ipv4 and ipv6 xfrms each create dst_ops template, and perform
dst_entries_init on the templates.  The template values are copied to each
net namespace's xfrm.xfrm*_dst_ops.  The problem there is the dst_ops
pcpuc_entries field is a percpu counter and cannot be used correctly by
simply copying it to another object.

The result of this is a very subtle bug; changes to the dst entries
counter from one net namespace may sometimes get applied to a different
net namespace dst entries counter.  This is because of how the percpu
counter works; it has a main count field as well as a pointer to the
percpu variables.  Each net namespace maintains its own main count
variable, but all point to one set of percpu variables.  When any net
namespace happens to change one of the percpu variables to outside its
small batch range, its count is moved to the net namespace's main count
variable.  So with multiple net namespaces operating concurrently, the
dst_ops entries counter can stray from the actual value that it should
be; if counts are consistently moved from one net namespace to another
(which my testing showed is likely), then one net namespace winds up
with a negative dst_ops count while another winds up with a continually
increasing count, eventually reaching its gc_thresh limit, which causes
all new traffic on the net namespace to fail with -ENOBUFS.

Signed-off-by: Dan Streetman <dan.streetman@canonical.com>
Signed-off-by: Dan Streetman <ddstreet@ieee.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/ipv4/xfrm4_policy.c | 46 +++++++++++++++++++++++++++++++++---------
 net/ipv6/xfrm6_policy.c | 53 +++++++++++++++++++++++++++++++++++--------------
 net/xfrm/xfrm_policy.c  | 38 -----------------------------------
 3 files changed, 75 insertions(+), 62 deletions(-)

diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 6156f68..94fc16d 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -230,7 +230,7 @@ static void xfrm4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
 	xfrm_dst_ifdown(dst, dev);
 }
 
-static struct dst_ops xfrm4_dst_ops = {
+static struct dst_ops xfrm4_dst_ops_template = {
 	.family =		AF_INET,
 	.protocol =		cpu_to_be16(ETH_P_IP),
 	.gc =			xfrm4_garbage_collect,
@@ -245,7 +245,7 @@ static struct dst_ops xfrm4_dst_ops = {
 
 static struct xfrm_policy_afinfo xfrm4_policy_afinfo = {
 	.family = 		AF_INET,
-	.dst_ops =		&xfrm4_dst_ops,
+	.dst_ops =		&xfrm4_dst_ops_template,
 	.dst_lookup =		xfrm4_dst_lookup,
 	.get_saddr =		xfrm4_get_saddr,
 	.decode_session =	_decode_session4,
@@ -267,7 +267,7 @@ static struct ctl_table xfrm4_policy_table[] = {
 	{ }
 };
 
-static int __net_init xfrm4_net_init(struct net *net)
+static int __net_init xfrm4_net_sysctl_init(struct net *net)
 {
 	struct ctl_table *table;
 	struct ctl_table_header *hdr;
@@ -295,7 +295,7 @@ err_alloc:
 	return -ENOMEM;
 }
 
-static void __net_exit xfrm4_net_exit(struct net *net)
+static void __net_exit xfrm4_net_sysctl_exit(struct net *net)
 {
 	struct ctl_table *table;
 
@@ -307,12 +307,44 @@ static void __net_exit xfrm4_net_exit(struct net *net)
 	if (!net_eq(net, &init_net))
 		kfree(table);
 }
+#else /* CONFIG_SYSCTL */
+static int inline xfrm4_net_sysctl_init(struct net *net)
+{
+	return 0;
+}
+
+static void inline xfrm4_net_sysctl_exit(struct net *net)
+{
+}
+#endif
+
+static int __net_init xfrm4_net_init(struct net *net)
+{
+	int ret;
+
+	memcpy(&net->xfrm.xfrm4_dst_ops, &xfrm4_dst_ops_template,
+	       sizeof(xfrm4_dst_ops_template));
+	ret = dst_entries_init(&net->xfrm.xfrm4_dst_ops);
+	if (ret)
+		return ret;
+
+	ret = xfrm4_net_sysctl_init(net);
+	if (ret)
+		dst_entries_destroy(&net->xfrm.xfrm4_dst_ops);
+
+	return ret;
+}
+
+static void __net_exit xfrm4_net_exit(struct net *net)
+{
+	xfrm4_net_sysctl_exit(net);
+	dst_entries_destroy(&net->xfrm.xfrm4_dst_ops);
+}
 
 static struct pernet_operations __net_initdata xfrm4_net_ops = {
 	.init	= xfrm4_net_init,
 	.exit	= xfrm4_net_exit,
 };
-#endif
 
 static void __init xfrm4_policy_init(void)
 {
@@ -321,13 +353,9 @@ static void __init xfrm4_policy_init(void)
 
 void __init xfrm4_init(void)
 {
-	dst_entries_init(&xfrm4_dst_ops);
-
 	xfrm4_state_init();
 	xfrm4_policy_init();
 	xfrm4_protocol_init();
-#ifdef CONFIG_SYSCTL
 	register_pernet_subsys(&xfrm4_net_ops);
-#endif
 }
 
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 5f98364..d2425ce 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -284,7 +284,7 @@ static void xfrm6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
 	xfrm_dst_ifdown(dst, dev);
 }
 
-static struct dst_ops xfrm6_dst_ops = {
+static struct dst_ops xfrm6_dst_ops_template = {
 	.family =		AF_INET6,
 	.protocol =		cpu_to_be16(ETH_P_IPV6),
 	.gc =			xfrm6_garbage_collect,
@@ -299,7 +299,7 @@ static struct dst_ops xfrm6_dst_ops = {
 
 static struct xfrm_policy_afinfo xfrm6_policy_afinfo = {
 	.family =		AF_INET6,
-	.dst_ops =		&xfrm6_dst_ops,
+	.dst_ops =		&xfrm6_dst_ops_template,
 	.dst_lookup =		xfrm6_dst_lookup,
 	.get_saddr =		xfrm6_get_saddr,
 	.decode_session =	_decode_session6,
@@ -332,7 +332,7 @@ static struct ctl_table xfrm6_policy_table[] = {
 	{ }
 };
 
-static int __net_init xfrm6_net_init(struct net *net)
+static int __net_init xfrm6_net_sysctl_init(struct net *net)
 {
 	struct ctl_table *table;
 	struct ctl_table_header *hdr;
@@ -360,7 +360,7 @@ err_alloc:
 	return -ENOMEM;
 }
 
-static void __net_exit xfrm6_net_exit(struct net *net)
+static void __net_exit xfrm6_net_sysctl_exit(struct net *net)
 {
 	struct ctl_table *table;
 
@@ -372,24 +372,52 @@ static void __net_exit xfrm6_net_exit(struct net *net)
 	if (!net_eq(net, &init_net))
 		kfree(table);
 }
+#else /* CONFIG_SYSCTL */
+static int inline xfrm6_net_sysctl_init(struct net *net)
+{
+	return 0;
+}
+
+static void inline xfrm6_net_sysctl_exit(struct net *net)
+{
+}
+#endif
+
+static int __net_init xfrm6_net_init(struct net *net)
+{
+	int ret;
+
+	memcpy(&net->xfrm.xfrm6_dst_ops, &xfrm6_dst_ops_template,
+	       sizeof(xfrm6_dst_ops_template));
+	ret = dst_entries_init(&net->xfrm.xfrm6_dst_ops);
+	if (ret)
+		return ret;
+
+	ret = xfrm6_net_sysctl_init(net);
+	if (ret)
+		dst_entries_destroy(&net->xfrm.xfrm6_dst_ops);
+
+	return ret;
+}
+
+static void __net_exit xfrm6_net_exit(struct net *net)
+{
+	xfrm6_net_sysctl_exit(net);
+	dst_entries_destroy(&net->xfrm.xfrm6_dst_ops);
+}
 
 static struct pernet_operations xfrm6_net_ops = {
 	.init	= xfrm6_net_init,
 	.exit	= xfrm6_net_exit,
 };
-#endif
 
 int __init xfrm6_init(void)
 {
 	int ret;
 
-	dst_entries_init(&xfrm6_dst_ops);
-
 	ret = xfrm6_policy_init();
-	if (ret) {
-		dst_entries_destroy(&xfrm6_dst_ops);
+	if (ret)
 		goto out;
-	}
 	ret = xfrm6_state_init();
 	if (ret)
 		goto out_policy;
@@ -398,9 +426,7 @@ int __init xfrm6_init(void)
 	if (ret)
 		goto out_state;
 
-#ifdef CONFIG_SYSCTL
 	register_pernet_subsys(&xfrm6_net_ops);
-#endif
 out:
 	return ret;
 out_state:
@@ -412,11 +438,8 @@ out_policy:
 
 void xfrm6_fini(void)
 {
-#ifdef CONFIG_SYSCTL
 	unregister_pernet_subsys(&xfrm6_net_ops);
-#endif
 	xfrm6_protocol_fini();
 	xfrm6_policy_fini();
 	xfrm6_state_fini();
-	dst_entries_destroy(&xfrm6_dst_ops);
 }
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index f62fd2c..4769382 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2801,7 +2801,6 @@ static struct neighbour *xfrm_neigh_lookup(const struct dst_entry *dst,
 
 int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo)
 {
-	struct net *net;
 	int err = 0;
 	if (unlikely(afinfo == NULL))
 		return -EINVAL;
@@ -2832,26 +2831,6 @@ int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo)
 	}
 	spin_unlock(&xfrm_policy_afinfo_lock);
 
-	rtnl_lock();
-	for_each_net(net) {
-		struct dst_ops *xfrm_dst_ops;
-
-		switch (afinfo->family) {
-		case AF_INET:
-			xfrm_dst_ops = &net->xfrm.xfrm4_dst_ops;
-			break;
-#if IS_ENABLED(CONFIG_IPV6)
-		case AF_INET6:
-			xfrm_dst_ops = &net->xfrm.xfrm6_dst_ops;
-			break;
-#endif
-		default:
-			BUG();
-		}
-		*xfrm_dst_ops = *afinfo->dst_ops;
-	}
-	rtnl_unlock();
-
 	return err;
 }
 EXPORT_SYMBOL(xfrm_policy_register_afinfo);
@@ -2887,22 +2866,6 @@ int xfrm_policy_unregister_afinfo(struct xfrm_policy_afinfo *afinfo)
 }
 EXPORT_SYMBOL(xfrm_policy_unregister_afinfo);
 
-static void __net_init xfrm_dst_ops_init(struct net *net)
-{
-	struct xfrm_policy_afinfo *afinfo;
-
-	rcu_read_lock();
-	afinfo = rcu_dereference(xfrm_policy_afinfo[AF_INET]);
-	if (afinfo)
-		net->xfrm.xfrm4_dst_ops = *afinfo->dst_ops;
-#if IS_ENABLED(CONFIG_IPV6)
-	afinfo = rcu_dereference(xfrm_policy_afinfo[AF_INET6]);
-	if (afinfo)
-		net->xfrm.xfrm6_dst_ops = *afinfo->dst_ops;
-#endif
-	rcu_read_unlock();
-}
-
 static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void *ptr)
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
@@ -3050,7 +3013,6 @@ static int __net_init xfrm_net_init(struct net *net)
 	rv = xfrm_policy_init(net);
 	if (rv < 0)
 		goto out_policy;
-	xfrm_dst_ops_init(net);
 	rv = xfrm_sysctl_init(net);
 	if (rv < 0)
 		goto out_sysctl;
-- 
2.1.0

Re: [PATCHES] Networking

[Greg KH]

On Tue, Jan 26, 2016 at 06:00:44PM -0800, David Miller wrote:
> 
> Please queue up the following networking bug fixes for 4.4.x, 4.3.1, 4.1.x, and
> 3.18.x -stable, respectively.

All queued up now, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 93 bytes --]


Please queue up the following bug fixes for 4.1.x and 4.4.x -stable,
respectively.

Thanks!

[-- Attachment #2: net_41.mbox --]
[-- Type: Application/Octet-Stream, Size: 95022 bytes --]

From 75230205ba83c6938ab4b4d3f7cabccda29d8436 Mon Sep 17 00:00:00 2001
From: Ursula Braun <ursula.braun@de.ibm.com>
Date: Tue, 19 Jan 2016 10:41:33 +0100
Subject: [PATCH 01/34] af_iucv: Validate socket address length in
 iucv_sock_bind()

[ Upstream commit 52a82e23b9f2a9e1d429c5207f8575784290d008 ]

Signed-off-by: Ursula Braun <ursula.braun@de.ibm.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Reviewed-by: Evgeny Cherkashin <Eugene.Crosser@ru.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/iucv/af_iucv.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 6daa52a..123f6f9 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -709,6 +709,9 @@ static int iucv_sock_bind(struct socket *sock, struct sockaddr *addr,
 	if (!addr || addr->sa_family != AF_IUCV)
 		return -EINVAL;
 
+	if (addr_len < sizeof(struct sockaddr_iucv))
+		return -EINVAL;
+
 	lock_sock(sk);
 	if (sk->sk_state != IUCV_OPEN) {
 		err = -EBADFD;
-- 
2.4.1


From 3f585b16ac9c4aa592528dac16f3155ce5ad20cb Mon Sep 17 00:00:00 2001
From: Manfred Rudigier <Manfred.Rudigier@omicron.at>
Date: Wed, 20 Jan 2016 11:22:28 +0100
Subject: [PATCH 02/34] net: dp83640: Fix tx timestamp overflow handling.

[ Upstream commit 81e8f2e930fe76b9814c71b9d87c30760b5eb705 ]

PHY status frames are not reliable, the PHY may not be able to send them
during heavy receive traffic. This overflow condition is signaled by the
PHY in the next status frame, but the driver did not make use of it.
Instead it always reported wrong tx timestamps to user space after an
overflow happened because it assigned newly received tx timestamps to old
packets in the queue.

This commit fixes this issue by clearing the tx timestamp queue every time
an overflow happens, so that no timestamps are delivered for overflow
packets. This way time stamping will continue correctly after an overflow.

Signed-off-by: Manfred Rudigier <manfred.rudigier@omicron.at>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/dp83640.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index 00cb41e..c56cf0b 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -833,6 +833,11 @@ static void decode_rxts(struct dp83640_private *dp83640,
 	struct skb_shared_hwtstamps *shhwtstamps = NULL;
 	struct sk_buff *skb;
 	unsigned long flags;
+	u8 overflow;
+
+	overflow = (phy_rxts->ns_hi >> 14) & 0x3;
+	if (overflow)
+		pr_debug("rx timestamp queue overflow, count %d\n", overflow);
 
 	spin_lock_irqsave(&dp83640->rx_lock, flags);
 
@@ -875,6 +880,7 @@ static void decode_txts(struct dp83640_private *dp83640,
 	struct skb_shared_hwtstamps shhwtstamps;
 	struct sk_buff *skb;
 	u64 ns;
+	u8 overflow;
 
 	/* We must already have the skb that triggered this. */
 
@@ -884,6 +890,17 @@ static void decode_txts(struct dp83640_private *dp83640,
 		pr_debug("have timestamp but tx_queue empty\n");
 		return;
 	}
+
+	overflow = (phy_txts->ns_hi >> 14) & 0x3;
+	if (overflow) {
+		pr_debug("tx timestamp queue overflow, count %d\n", overflow);
+		while (skb) {
+			skb_complete_tx_timestamp(skb, NULL);
+			skb = skb_dequeue(&dp83640->tx_queue);
+		}
+		return;
+	}
+
 	ns = phy2txts(phy_txts);
 	memset(&shhwtstamps, 0, sizeof(shhwtstamps));
 	shhwtstamps.hwtstamp = ns_to_ktime(ns);
-- 
2.4.1


From 41340b951894aedff9adce10fe01bfd80c9b144f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 21 Jan 2016 08:02:54 -0800
Subject: [PATCH 03/34] tcp: fix NULL deref in tcp_v4_send_ack()

[ Upstream commit e62a123b8ef7c5dc4db2c16383d506860ad21b47 ]

Neal reported crashes with this stack trace :

 RIP: 0010:[<ffffffff8c57231b>] tcp_v4_send_ack+0x41/0x20f
...
 CR2: 0000000000000018 CR3: 000000044005c000 CR4: 00000000001427e0
...
  [<ffffffff8c57258e>] tcp_v4_reqsk_send_ack+0xa5/0xb4
  [<ffffffff8c1a7caa>] tcp_check_req+0x2ea/0x3e0
  [<ffffffff8c19e420>] tcp_rcv_state_process+0x850/0x2500
  [<ffffffff8c1a6d21>] tcp_v4_do_rcv+0x141/0x330
  [<ffffffff8c56cdb2>] sk_backlog_rcv+0x21/0x30
  [<ffffffff8c098bbd>] tcp_recvmsg+0x75d/0xf90
  [<ffffffff8c0a8700>] inet_recvmsg+0x80/0xa0
  [<ffffffff8c17623e>] sock_aio_read+0xee/0x110
  [<ffffffff8c066fcf>] do_sync_read+0x6f/0xa0
  [<ffffffff8c0673a1>] SyS_read+0x1e1/0x290
  [<ffffffff8c5ca262>] system_call_fastpath+0x16/0x1b

The problem here is the skb we provide to tcp_v4_send_ack() had to
be parked in the backlog of a new TCP fastopen child because this child
was owned by the user at the time an out of window packet arrived.

Before queuing a packet, TCP has to set skb->dev to NULL as the device
could disappear before packet is removed from the queue.

Fix this issue by using the net pointer provided by the socket (being a
timewait or a request socket).

IPv6 is immune to the bug : tcp_v6_send_response() already gets the net
pointer from the socket if provided.

Fixes: 168a8f58059a ("tcp: TCP Fast Open Server - main code path")
Reported-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jerry Chu <hkchu@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index cd18c3d..13b92d5 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -705,7 +705,8 @@ release_sk1:
    outside socket context is ugly, certainly. What can I do?
  */
 
-static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
+static void tcp_v4_send_ack(struct net *net,
+			    struct sk_buff *skb, u32 seq, u32 ack,
 			    u32 win, u32 tsval, u32 tsecr, int oif,
 			    struct tcp_md5sig_key *key,
 			    int reply_flags, u8 tos)
@@ -720,7 +721,6 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
 			];
 	} rep;
 	struct ip_reply_arg arg;
-	struct net *net = dev_net(skb_dst(skb)->dev);
 
 	memset(&rep.th, 0, sizeof(struct tcphdr));
 	memset(&arg, 0, sizeof(arg));
@@ -782,7 +782,8 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
 	struct inet_timewait_sock *tw = inet_twsk(sk);
 	struct tcp_timewait_sock *tcptw = tcp_twsk(sk);
 
-	tcp_v4_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
+	tcp_v4_send_ack(sock_net(sk), skb,
+			tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
 			tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
 			tcp_time_stamp + tcptw->tw_ts_offset,
 			tcptw->tw_ts_recent,
@@ -801,8 +802,10 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
 	/* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV
 	 * sk->sk_state == TCP_SYN_RECV -> for Fast Open.
 	 */
-	tcp_v4_send_ack(skb, (sk->sk_state == TCP_LISTEN) ?
-			tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt,
+	u32 seq = (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 :
+					     tcp_sk(sk)->snd_nxt;
+
+	tcp_v4_send_ack(sock_net(sk), skb, seq,
 			tcp_rsk(req)->rcv_nxt, req->rcv_wnd,
 			tcp_time_stamp,
 			req->ts_recent,
-- 
2.4.1


From a8b19ec2254fd7c4d9c9d32b6bbcfdb7a5ad50ad Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 24 Jan 2016 13:53:50 -0800
Subject: [PATCH 04/34] af_unix: fix struct pid memory leak

[ Upstream commit fa0dc04df259ba2df3ce1920e9690c7842f8fa4b ]

Dmitry reported a struct pid leak detected by a syzkaller program.

Bug happens in unix_stream_recvmsg() when we break the loop when a
signal is pending, without properly releasing scm.

Fixes: b3ca9b02b007 ("net: fix multithreaded signal handling in unix recv routines")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Rainer Weikusat <rweikusat@mobileactivedefense.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index cb3a01a..c741d83 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2131,6 +2131,7 @@ again:
 
 			if (signal_pending(current)) {
 				err = sock_intr_errno(timeo);
+				scm_destroy(&scm);
 				goto out;
 			}
 
-- 
2.4.1


From 8f077a7a428d457c12a10f0fc1cfd15d57651c59 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Fri, 22 Jan 2016 01:39:43 +0100
Subject: [PATCH 05/34] pptp: fix illegal memory access caused by multiple
 bind()s

[ Upstream commit 9a368aff9cb370298fa02feeffa861f2db497c18 ]

Several times already this has been reported as kasan reports caused by
syzkaller and trinity and people always looked at RCU races, but it is
much more simple. :)

In case we bind a pptp socket multiple times, we simply add it to
the callid_sock list but don't remove the old binding. Thus the old
socket stays in the bucket with unused call_id indexes and doesn't get
cleaned up. This causes various forms of kasan reports which were hard
to pinpoint.

Simply don't allow multiple binds and correct error handling in
pptp_bind. Also keep sk_state bits in place in pptp_connect.

Fixes: 00959ade36acad ("PPTP: PPP over IPv4 (Point-to-Point Tunneling Protocol)")
Cc: Dmitry Kozlov <xeb@mail.ru>
Cc: Sasha Levin <sasha.levin@oracle.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Dave Jones <davej@codemonkey.org.uk>
Reported-by: Dave Jones <davej@codemonkey.org.uk>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pptp.c | 34 ++++++++++++++++++++++++----------
 1 file changed, 24 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index 0bacabf..b35199c 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -131,24 +131,27 @@ static int lookup_chan_dst(u16 call_id, __be32 d_addr)
 	return i < MAX_CALLID;
 }
 
-static int add_chan(struct pppox_sock *sock)
+static int add_chan(struct pppox_sock *sock,
+		    struct pptp_addr *sa)
 {
 	static int call_id;
 
 	spin_lock(&chan_lock);
-	if (!sock->proto.pptp.src_addr.call_id)	{
+	if (!sa->call_id)	{
 		call_id = find_next_zero_bit(callid_bitmap, MAX_CALLID, call_id + 1);
 		if (call_id == MAX_CALLID) {
 			call_id = find_next_zero_bit(callid_bitmap, MAX_CALLID, 1);
 			if (call_id == MAX_CALLID)
 				goto out_err;
 		}
-		sock->proto.pptp.src_addr.call_id = call_id;
-	} else if (test_bit(sock->proto.pptp.src_addr.call_id, callid_bitmap))
+		sa->call_id = call_id;
+	} else if (test_bit(sa->call_id, callid_bitmap)) {
 		goto out_err;
+	}
 
-	set_bit(sock->proto.pptp.src_addr.call_id, callid_bitmap);
-	rcu_assign_pointer(callid_sock[sock->proto.pptp.src_addr.call_id], sock);
+	sock->proto.pptp.src_addr = *sa;
+	set_bit(sa->call_id, callid_bitmap);
+	rcu_assign_pointer(callid_sock[sa->call_id], sock);
 	spin_unlock(&chan_lock);
 
 	return 0;
@@ -417,7 +420,6 @@ static int pptp_bind(struct socket *sock, struct sockaddr *uservaddr,
 	struct sock *sk = sock->sk;
 	struct sockaddr_pppox *sp = (struct sockaddr_pppox *) uservaddr;
 	struct pppox_sock *po = pppox_sk(sk);
-	struct pptp_opt *opt = &po->proto.pptp;
 	int error = 0;
 
 	if (sockaddr_len < sizeof(struct sockaddr_pppox))
@@ -425,10 +427,22 @@ static int pptp_bind(struct socket *sock, struct sockaddr *uservaddr,
 
 	lock_sock(sk);
 
-	opt->src_addr = sp->sa_addr.pptp;
-	if (add_chan(po))
+	if (sk->sk_state & PPPOX_DEAD) {
+		error = -EALREADY;
+		goto out;
+	}
+
+	if (sk->sk_state & PPPOX_BOUND) {
 		error = -EBUSY;
+		goto out;
+	}
+
+	if (add_chan(po, &sp->sa_addr.pptp))
+		error = -EBUSY;
+	else
+		sk->sk_state |= PPPOX_BOUND;
 
+out:
 	release_sock(sk);
 	return error;
 }
@@ -499,7 +513,7 @@ static int pptp_connect(struct socket *sock, struct sockaddr *uservaddr,
 	}
 
 	opt->dst_addr = sp->sa_addr.pptp;
-	sk->sk_state = PPPOX_CONNECTED;
+	sk->sk_state |= PPPOX_CONNECTED;
 
  end:
 	release_sock(sk);
-- 
2.4.1


From 943b170d487203b94394c0990ab4c5fea903395e Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Fri, 22 Jan 2016 18:29:49 -0200
Subject: [PATCH 06/34] sctp: allow setting SCTP_SACK_IMMEDIATELY by the
 application

[ Upstream commit 27f7ed2b11d42ab6d796e96533c2076ec220affc ]

This patch extends commit b93d6471748d ("sctp: implement the sender side
for SACK-IMMEDIATELY extension") as it didn't white list
SCTP_SACK_IMMEDIATELY on sctp_msghdr_parse(), causing it to be
understood as an invalid flag and returning -EINVAL to the application.

Note that the actual handling of the flag is already there in
sctp_datamsg_from_user().

https://tools.ietf.org/html/rfc7053#section-7

Fixes: b93d6471748d ("sctp: implement the sender side for SACK-IMMEDIATELY extension")
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 76e6ec6..1b80f20 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -6653,6 +6653,7 @@ static int sctp_msghdr_parse(const struct msghdr *msg, sctp_cmsgs_t *cmsgs)
 
 			if (cmsgs->srinfo->sinfo_flags &
 			    ~(SCTP_UNORDERED | SCTP_ADDR_OVER |
+			      SCTP_SACK_IMMEDIATELY |
 			      SCTP_ABORT | SCTP_EOF))
 				return -EINVAL;
 			break;
@@ -6676,6 +6677,7 @@ static int sctp_msghdr_parse(const struct msghdr *msg, sctp_cmsgs_t *cmsgs)
 
 			if (cmsgs->sinfo->snd_flags &
 			    ~(SCTP_UNORDERED | SCTP_ADDR_OVER |
+			      SCTP_SACK_IMMEDIATELY |
 			      SCTP_ABORT | SCTP_EOF))
 				return -EINVAL;
 			break;
-- 
2.4.1


From 2316e82d255a6110c35afb7cbbf0d01d08f083c2 Mon Sep 17 00:00:00 2001
From: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
Date: Wed, 27 Jan 2016 11:35:59 +0100
Subject: [PATCH 07/34] tipc: fix connection abort during subscription cancel

[ Upstream commit 4d5cfcba2f6ec494d8810b9e3c0a7b06255c8067 ]

In 'commit 7fe8097cef5f ("tipc: fix nullpointer bug when subscribing
to events")', we terminate the connection if the subscription
creation fails.
In the same commit, the subscription creation result was based on
the value of the subscription pointer (set in the function) instead
of the return code.

Unfortunately, the same function tipc_subscrp_create() handles
subscription cancel request. For a subscription cancellation request,
the subscription pointer cannot be set. Thus if a subscriber has
several subscriptions and cancels any of them, the connection is
terminated.

In this commit, we terminate the connection based on the return value
of tipc_subscrp_create().
Fixes: commit 7fe8097cef5f ("tipc: fix nullpointer bug when subscribing to events")

Reviewed-by:  Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/subscr.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c
index 1c147c8..948f316 100644
--- a/net/tipc/subscr.c
+++ b/net/tipc/subscr.c
@@ -302,11 +302,10 @@ static void subscr_conn_msg_event(struct net *net, int conid,
 	struct tipc_net *tn = net_generic(net, tipc_net_id);
 
 	spin_lock_bh(&subscriber->lock);
-	subscr_subscribe(net, (struct tipc_subscr *)buf, subscriber, &sub);
-	if (sub)
-		tipc_nametbl_subscribe(sub);
-	else
+	if (subscr_subscribe(net, (struct tipc_subscr *)buf, subscriber, &sub))
 		tipc_conn_terminate(tn->topsrv, subscriber->conid);
+	else
+		tipc_nametbl_subscribe(sub);
 	spin_unlock_bh(&subscriber->lock);
 }
 
-- 
2.4.1


From b407fdbb44b3bad4a99f495f1436306230bd86dc Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 27 Jan 2016 15:16:43 +0100
Subject: [PATCH 08/34] switchdev: Require RTNL mutex to be held when sending
 FDB notifications

[ Upstream commit 4f2c6ae5c64c353fb1b0425e4747e5603feadba1 ]

When switchdev drivers process FDB notifications from the underlying
device they resolve the netdev to which the entry points to and notify
the bridge using the switchdev notifier.

However, since the RTNL mutex is not held there is nothing preventing
the netdev from disappearing in the middle, which will cause
br_switchdev_event() to dereference a non-existing netdev.

Make switchdev drivers hold the lock at the beginning of the
notification processing session and release it once it ends, after
notifying the bridge.

Also, remove switchdev_mutex and fdb_lock, as they are no longer needed
when RTNL mutex is held.

Fixes: 03bf0c281234 ("switchdev: introduce switchdev notifier")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/rocker/rocker.c |  2 ++
 net/bridge/br.c                      |  3 +--
 net/switchdev/switchdev.c            | 15 ++++++++-------
 3 files changed, 11 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c
index 73b6fc2..4fedf7f 100644
--- a/drivers/net/ethernet/rocker/rocker.c
+++ b/drivers/net/ethernet/rocker/rocker.c
@@ -3384,12 +3384,14 @@ static void rocker_port_fdb_learn_work(struct work_struct *work)
 	info.addr = lw->addr;
 	info.vid = lw->vid;
 
+	rtnl_lock();
 	if (learned && removing)
 		call_netdev_switch_notifiers(NETDEV_SWITCH_FDB_DEL,
 					     lw->dev, &info.info);
 	else if (learned && !removing)
 		call_netdev_switch_notifiers(NETDEV_SWITCH_FDB_ADD,
 					     lw->dev, &info.info);
+	rtnl_unlock();
 
 	kfree(work);
 }
diff --git a/net/bridge/br.c b/net/bridge/br.c
index 02c24cf..c72e01c 100644
--- a/net/bridge/br.c
+++ b/net/bridge/br.c
@@ -121,6 +121,7 @@ static struct notifier_block br_device_notifier = {
 	.notifier_call = br_device_event
 };
 
+/* called with RTNL */
 static int br_netdev_switch_event(struct notifier_block *unused,
 				  unsigned long event, void *ptr)
 {
@@ -130,7 +131,6 @@ static int br_netdev_switch_event(struct notifier_block *unused,
 	struct netdev_switch_notifier_fdb_info *fdb_info;
 	int err = NOTIFY_DONE;
 
-	rtnl_lock();
 	p = br_port_get_rtnl(dev);
 	if (!p)
 		goto out;
@@ -155,7 +155,6 @@ static int br_netdev_switch_event(struct notifier_block *unused,
 	}
 
 out:
-	rtnl_unlock();
 	return err;
 }
 
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index 055453d..a8dbe80 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -15,6 +15,7 @@
 #include <linux/mutex.h>
 #include <linux/notifier.h>
 #include <linux/netdevice.h>
+#include <linux/rtnetlink.h>
 #include <net/ip_fib.h>
 #include <net/switchdev.h>
 
@@ -64,7 +65,6 @@ int netdev_switch_port_stp_update(struct net_device *dev, u8 state)
 }
 EXPORT_SYMBOL_GPL(netdev_switch_port_stp_update);
 
-static DEFINE_MUTEX(netdev_switch_mutex);
 static RAW_NOTIFIER_HEAD(netdev_switch_notif_chain);
 
 /**
@@ -79,9 +79,9 @@ int register_netdev_switch_notifier(struct notifier_block *nb)
 {
 	int err;
 
-	mutex_lock(&netdev_switch_mutex);
+	rtnl_lock();
 	err = raw_notifier_chain_register(&netdev_switch_notif_chain, nb);
-	mutex_unlock(&netdev_switch_mutex);
+	rtnl_unlock();
 	return err;
 }
 EXPORT_SYMBOL_GPL(register_netdev_switch_notifier);
@@ -97,9 +97,9 @@ int unregister_netdev_switch_notifier(struct notifier_block *nb)
 {
 	int err;
 
-	mutex_lock(&netdev_switch_mutex);
+	rtnl_lock();
 	err = raw_notifier_chain_unregister(&netdev_switch_notif_chain, nb);
-	mutex_unlock(&netdev_switch_mutex);
+	rtnl_unlock();
 	return err;
 }
 EXPORT_SYMBOL_GPL(unregister_netdev_switch_notifier);
@@ -113,16 +113,17 @@ EXPORT_SYMBOL_GPL(unregister_netdev_switch_notifier);
  *	Call all network notifier blocks. This should be called by driver
  *	when it needs to propagate hardware event.
  *	Return values are same as for atomic_notifier_call_chain().
+ *	rtnl_lock must be held.
  */
 int call_netdev_switch_notifiers(unsigned long val, struct net_device *dev,
 				 struct netdev_switch_notifier_info *info)
 {
 	int err;
 
+	ASSERT_RTNL();
+
 	info->dev = dev;
-	mutex_lock(&netdev_switch_mutex);
 	err = raw_notifier_call_chain(&netdev_switch_notif_chain, val, info);
-	mutex_unlock(&netdev_switch_mutex);
 	return err;
 }
 EXPORT_SYMBOL_GPL(call_netdev_switch_notifiers);
-- 
2.4.1


From bdd9c26852c741ff12b2a563b76f6cb5accfdc61 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 27 Jan 2016 10:52:43 -0800
Subject: [PATCH 09/34] tcp: beware of alignments in tcp_get_info()

[ Upstream commit ff5d749772018602c47509bdc0093ff72acd82ec ]

With some combinations of user provided flags in netlink command,
it is possible to call tcp_get_info() with a buffer that is not 8-bytes
aligned.

It does matter on some arches, so we need to use put_unaligned() to
store the u64 fields.

Current iproute2 package does not trigger this particular issue.

Fixes: 0df48c26d841 ("tcp: add tcpi_bytes_acked to tcp_info")
Fixes: 977cb0ecf82e ("tcp: add pacing_rate information into tcp_info")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index bb2ce74..b5f4f5c 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -279,6 +279,7 @@
 
 #include <asm/uaccess.h>
 #include <asm/ioctls.h>
+#include <asm/unaligned.h>
 #include <net/busy_poll.h>
 
 int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;
@@ -2603,6 +2604,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	u32 now = tcp_time_stamp;
 	unsigned int start;
+	u64 rate64;
 	u32 rate;
 
 	memset(info, 0, sizeof(*info));
@@ -2665,15 +2667,17 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	info->tcpi_total_retrans = tp->total_retrans;
 
 	rate = READ_ONCE(sk->sk_pacing_rate);
-	info->tcpi_pacing_rate = rate != ~0U ? rate : ~0ULL;
+	rate64 = rate != ~0U ? rate : ~0ULL;
+	put_unaligned(rate64, &info->tcpi_pacing_rate);
 
 	rate = READ_ONCE(sk->sk_max_pacing_rate);
-	info->tcpi_max_pacing_rate = rate != ~0U ? rate : ~0ULL;
+	rate64 = rate != ~0U ? rate : ~0ULL;
+	put_unaligned(rate64, &info->tcpi_max_pacing_rate);
 
 	do {
 		start = u64_stats_fetch_begin_irq(&tp->syncp);
-		info->tcpi_bytes_acked = tp->bytes_acked;
-		info->tcpi_bytes_received = tp->bytes_received;
+		put_unaligned(tp->bytes_acked, &info->tcpi_bytes_acked);
+		put_unaligned(tp->bytes_received, &info->tcpi_bytes_received);
 	} while (u64_stats_fetch_retry_irq(&tp->syncp, start));
 }
 EXPORT_SYMBOL_GPL(tcp_get_info);
-- 
2.4.1


From 0822b6e3c189f8c47979ff58e6fbf37dc309ca36 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 29 Jan 2016 12:30:19 +0100
Subject: [PATCH 10/34] ipv6: enforce flowi6_oif usage in ip6_dst_lookup_tail()

[ Upstream commit 6f21c96a78b835259546d8f3fb4edff0f651d478 ]

The current implementation of ip6_dst_lookup_tail basically
ignore the egress ifindex match: if the saddr is set,
ip6_route_output() purposefully ignores flowi6_oif, due
to the commit d46a9d678e4c ("net: ipv6: Dont add RT6_LOOKUP_F_IFACE
flag if saddr set"), if the saddr is 'any' the first route lookup
in ip6_dst_lookup_tail fails, but upon failure a second lookup will
be performed with saddr set, thus ignoring the ifindex constraint.

This commit adds an output route lookup function variant, which
allows the caller to specify lookup flags, and modify
ip6_dst_lookup_tail() to enforce the ifindex match on the second
lookup via said helper.

ip6_route_output() becames now a static inline function build on
top of ip6_route_output_flags(); as a side effect, out-of-tree
modules need now a GPL license to access the output route lookup
functionality.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_route.h | 12 ++++++++++--
 net/ipv6/ip6_output.c   |  6 +++++-
 net/ipv6/route.c        |  8 +++-----
 3 files changed, 18 insertions(+), 8 deletions(-)

diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 5e19206..388dea4 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -64,8 +64,16 @@ static inline bool rt6_need_strict(const struct in6_addr *daddr)
 
 void ip6_route_input(struct sk_buff *skb);
 
-struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk,
-				   struct flowi6 *fl6);
+struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk,
+					 struct flowi6 *fl6, int flags);
+
+static inline struct dst_entry *ip6_route_output(struct net *net,
+						 const struct sock *sk,
+						 struct flowi6 *fl6)
+{
+	return ip6_route_output_flags(net, sk, fl6, 0);
+}
+
 struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6,
 				   int flags);
 
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index f50228b..36b9ac4 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -885,6 +885,7 @@ static int ip6_dst_lookup_tail(struct sock *sk,
 	struct rt6_info *rt;
 #endif
 	int err;
+	int flags = 0;
 
 	/* The correct way to handle this would be to do
 	 * ip6_route_get_saddr, and then ip6_route_output; however,
@@ -916,10 +917,13 @@ static int ip6_dst_lookup_tail(struct sock *sk,
 			dst_release(*dst);
 			*dst = NULL;
 		}
+
+		if (fl6->flowi6_oif)
+			flags |= RT6_LOOKUP_F_IFACE;
 	}
 
 	if (!*dst)
-		*dst = ip6_route_output(net, sk, fl6);
+		*dst = ip6_route_output_flags(net, sk, fl6, flags);
 
 	err = (*dst)->error;
 	if (err)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index f371fef..fe70bd6 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1030,11 +1030,9 @@ static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table
 	return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, flags);
 }
 
-struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk,
-				    struct flowi6 *fl6)
+struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk,
+					 struct flowi6 *fl6, int flags)
 {
-	int flags = 0;
-
 	fl6->flowi6_iif = LOOPBACK_IFINDEX;
 
 	if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr))
@@ -1047,7 +1045,7 @@ struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk,
 
 	return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_output);
 }
-EXPORT_SYMBOL(ip6_route_output);
+EXPORT_SYMBOL_GPL(ip6_route_output_flags);
 
 struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_orig)
 {
-- 
2.4.1


From 4ab8d66399bd0c3bf51742376f753f9fe45d13a7 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 29 Jan 2016 12:30:20 +0100
Subject: [PATCH 11/34] ipv6/udp: use sticky pktinfo egress ifindex on
 connect()

[ Upstream commit 1cdda91871470f15e79375991bd2eddc6e86ddb1 ]

Currently, the egress interface index specified via IPV6_PKTINFO
is ignored by __ip6_datagram_connect(), so that RFC 3542 section 6.7
can be subverted when the user space application calls connect()
before sendmsg().
Fix it by initializing properly flowi6_oif in connect() before
performing the route lookup.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/datagram.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 13ca4cf..8e6cb3f 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -162,6 +162,9 @@ ipv4_connected:
 	fl6.fl6_dport = inet->inet_dport;
 	fl6.fl6_sport = inet->inet_sport;
 
+	if (!fl6.flowi6_oif)
+		fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
+
 	if (!fl6.flowi6_oif && (addr_type&IPV6_ADDR_MULTICAST))
 		fl6.flowi6_oif = np->mcast_oif;
 
-- 
2.4.1


From b47c8e84f58cb28628f8b685e2179c3a58375cb8 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Thu, 30 Jul 2015 14:28:42 +0800
Subject: [PATCH 12/34] net/ipv6: add sysctl option accept_ra_min_hop_limit

[ Upstream commit 8013d1d7eafb0589ca766db6b74026f76b7f5cb4 ]

Commit 6fd99094de2b ("ipv6: Don't reduce hop limit for an interface")
disabled accept hop limit from RA if it is smaller than the current hop
limit for security stuff. But this behavior kind of break the RFC definition.

RFC 4861, 6.3.4.  Processing Received Router Advertisements
   A Router Advertisement field (e.g., Cur Hop Limit, Reachable Time,
   and Retrans Timer) may contain a value denoting that it is
   unspecified.  In such cases, the parameter should be ignored and the
   host should continue using whatever value it is already using.

   If the received Cur Hop Limit value is non-zero, the host SHOULD set
   its CurHopLimit variable to the received value.

So add sysctl option accept_ra_min_hop_limit to let user choose the minimum
hop limit value they can accept from RA. And set default to 1 to meet RFC
standards.

Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Acked-by: YOSHIFUJI Hideaki <hideaki.yoshifuji@miraclelinux.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt |  8 ++++++++
 include/linux/ipv6.h                   |  1 +
 include/uapi/linux/ipv6.h              |  2 ++
 net/ipv6/addrconf.c                    | 10 ++++++++++
 net/ipv6/ndisc.c                       | 16 +++++++---------
 5 files changed, 28 insertions(+), 9 deletions(-)

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 071fb18..07fad3d 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1321,6 +1321,14 @@ accept_ra_from_local - BOOLEAN
 	   disabled if accept_ra_from_local is disabled
                on a specific interface.
 
+accept_ra_min_hop_limit - INTEGER
+	Minimum hop limit Information in Router Advertisement.
+
+	Hop limit Information in Router Advertisement less than this
+	variable shall be ignored.
+
+	Default: 1
+
 accept_ra_pinfo - BOOLEAN
 	Learn Prefix Information in Router Advertisement.
 
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index e4b4649..01c2592 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -29,6 +29,7 @@ struct ipv6_devconf {
 	__s32		max_desync_factor;
 	__s32		max_addresses;
 	__s32		accept_ra_defrtr;
+	__s32		accept_ra_min_hop_limit;
 	__s32		accept_ra_pinfo;
 #ifdef CONFIG_IPV6_ROUTER_PREF
 	__s32		accept_ra_rtr_pref;
diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h
index 5efa54a..80f3b74 100644
--- a/include/uapi/linux/ipv6.h
+++ b/include/uapi/linux/ipv6.h
@@ -171,6 +171,8 @@ enum {
 	DEVCONF_USE_OPTIMISTIC,
 	DEVCONF_ACCEPT_RA_MTU,
 	DEVCONF_STABLE_SECRET,
+	DEVCONF_USE_OIF_ADDRS_ONLY,
+	DEVCONF_ACCEPT_RA_MIN_HOP_LIMIT,
 	DEVCONF_MAX
 };
 
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index f4795b0..28c4bc5 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -195,6 +195,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
 	.max_addresses		= IPV6_MAX_ADDRESSES,
 	.accept_ra_defrtr	= 1,
 	.accept_ra_from_local	= 0,
+	.accept_ra_min_hop_limit= 1,
 	.accept_ra_pinfo	= 1,
 #ifdef CONFIG_IPV6_ROUTER_PREF
 	.accept_ra_rtr_pref	= 1,
@@ -236,6 +237,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
 	.max_addresses		= IPV6_MAX_ADDRESSES,
 	.accept_ra_defrtr	= 1,
 	.accept_ra_from_local	= 0,
+	.accept_ra_min_hop_limit= 1,
 	.accept_ra_pinfo	= 1,
 #ifdef CONFIG_IPV6_ROUTER_PREF
 	.accept_ra_rtr_pref	= 1,
@@ -4565,6 +4567,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
 	array[DEVCONF_MAX_DESYNC_FACTOR] = cnf->max_desync_factor;
 	array[DEVCONF_MAX_ADDRESSES] = cnf->max_addresses;
 	array[DEVCONF_ACCEPT_RA_DEFRTR] = cnf->accept_ra_defrtr;
+	array[DEVCONF_ACCEPT_RA_MIN_HOP_LIMIT] = cnf->accept_ra_min_hop_limit;
 	array[DEVCONF_ACCEPT_RA_PINFO] = cnf->accept_ra_pinfo;
 #ifdef CONFIG_IPV6_ROUTER_PREF
 	array[DEVCONF_ACCEPT_RA_RTR_PREF] = cnf->accept_ra_rtr_pref;
@@ -5458,6 +5461,13 @@ static struct addrconf_sysctl_table
 			.proc_handler	= proc_dointvec,
 		},
 		{
+			.procname	= "accept_ra_min_hop_limit",
+			.data		= &ipv6_devconf.accept_ra_min_hop_limit,
+			.maxlen		= sizeof(int),
+			.mode		= 0644,
+			.proc_handler	= proc_dointvec,
+		},
+		{
 			.procname	= "accept_ra_pinfo",
 			.data		= &ipv6_devconf.accept_ra_pinfo,
 			.maxlen		= sizeof(int),
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 96f153c..abb0bdd 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1225,18 +1225,16 @@ static void ndisc_router_discovery(struct sk_buff *skb)
 
 	if (rt)
 		rt6_set_expires(rt, jiffies + (HZ * lifetime));
-	if (ra_msg->icmph.icmp6_hop_limit) {
-		/* Only set hop_limit on the interface if it is higher than
-		 * the current hop_limit.
-		 */
-		if (in6_dev->cnf.hop_limit < ra_msg->icmph.icmp6_hop_limit) {
+	if (in6_dev->cnf.accept_ra_min_hop_limit < 256 &&
+	    ra_msg->icmph.icmp6_hop_limit) {
+		if (in6_dev->cnf.accept_ra_min_hop_limit <= ra_msg->icmph.icmp6_hop_limit) {
 			in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit;
+			if (rt)
+				dst_metric_set(&rt->dst, RTAX_HOPLIMIT,
+					       ra_msg->icmph.icmp6_hop_limit);
 		} else {
-			ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than current\n");
+			ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than minimum\n");
 		}
-		if (rt)
-			dst_metric_set(&rt->dst, RTAX_HOPLIMIT,
-				       ra_msg->icmph.icmp6_hop_limit);
 	}
 
 skip_defrtr:
-- 
2.4.1


From 4f0cc857de55aaac5e791f341c1d3b22ef55bbff Mon Sep 17 00:00:00 2001
From: "subashab@codeaurora.org" <subashab@codeaurora.org>
Date: Tue, 2 Feb 2016 02:11:10 +0000
Subject: [PATCH 13/34] ipv6: addrconf: Fix recursive spin lock call

[ Upstream commit 16186a82de1fdd868255448274e64ae2616e2640 ]

A rcu stall with the following backtrace was seen on a system with
forwarding, optimistic_dad and use_optimistic set. To reproduce,
set these flags and allow ipv6 autoconf.

This occurs because the device write_lock is acquired while already
holding the read_lock. Back trace below -

INFO: rcu_preempt self-detected stall on CPU { 1}  (t=2100 jiffies
 g=3992 c=3991 q=4471)
<6> Task dump for CPU 1:
<2> kworker/1:0     R  running task    12168    15   2 0x00000002
<2> Workqueue: ipv6_addrconf addrconf_dad_work
<6> Call trace:
<2> [<ffffffc000084da8>] el1_irq+0x68/0xdc
<2> [<ffffffc000cc4e0c>] _raw_write_lock_bh+0x20/0x30
<2> [<ffffffc000bc5dd8>] __ipv6_dev_ac_inc+0x64/0x1b4
<2> [<ffffffc000bcbd2c>] addrconf_join_anycast+0x9c/0xc4
<2> [<ffffffc000bcf9f0>] __ipv6_ifa_notify+0x160/0x29c
<2> [<ffffffc000bcfb7c>] ipv6_ifa_notify+0x50/0x70
<2> [<ffffffc000bd035c>] addrconf_dad_work+0x314/0x334
<2> [<ffffffc0000b64c8>] process_one_work+0x244/0x3fc
<2> [<ffffffc0000b7324>] worker_thread+0x2f8/0x418
<2> [<ffffffc0000bb40c>] kthread+0xe0/0xec

v2: do addrconf_dad_kick inside read lock and then acquire write
lock for ipv6_ifa_notify as suggested by Eric

Fixes: 7fd2561e4ebdd ("net: ipv6: Add a sysctl to make optimistic
addresses useful candidates")

Cc: Eric Dumazet <edumazet@google.com>
Cc: Erik Kline <ek@google.com>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 28c4bc5..fcfbd05 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3423,6 +3423,7 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
 {
 	struct inet6_dev *idev = ifp->idev;
 	struct net_device *dev = idev->dev;
+	bool notify = false;
 
 	addrconf_join_solict(dev, &ifp->addr);
 
@@ -3468,7 +3469,7 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
 			/* Because optimistic nodes can use this address,
 			 * notify listeners. If DAD fails, RTM_DELADDR is sent.
 			 */
-			ipv6_ifa_notify(RTM_NEWADDR, ifp);
+			notify = true;
 		}
 	}
 
@@ -3476,6 +3477,8 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
 out:
 	spin_unlock(&ifp->lock);
 	read_unlock_bh(&idev->lock);
+	if (notify)
+		ipv6_ifa_notify(RTM_NEWADDR, ifp);
 }
 
 static void addrconf_dad_start(struct inet6_ifaddr *ifp)
-- 
2.4.1


From 61b970c511fb87bebd773bdf7606dddabf564ffd Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 2 Feb 2016 17:55:01 -0800
Subject: [PATCH 14/34] ipv6: fix a lockdep splat

[ Upstream commit 44c3d0c1c0a880354e9de5d94175742e2c7c9683 ]

Silence lockdep false positive about rcu_dereference() being
used in the wrong context.

First one should use rcu_dereference_protected() as we own the spinlock.

Second one should be a normal assignation, as no barrier is needed.

Fixes: 18367681a10bd ("ipv6 flowlabel: Convert np->ipv6_fl_list to RCU.")
Reported-by: Dave Jones <davej@codemonkey.org.uk>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_flowlabel.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index d491125..db939e4 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -540,12 +540,13 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
 		}
 		spin_lock_bh(&ip6_sk_fl_lock);
 		for (sflp = &np->ipv6_fl_list;
-		     (sfl = rcu_dereference(*sflp)) != NULL;
+		     (sfl = rcu_dereference_protected(*sflp,
+						      lockdep_is_held(&ip6_sk_fl_lock))) != NULL;
 		     sflp = &sfl->next) {
 			if (sfl->fl->label == freq.flr_label) {
 				if (freq.flr_label == (np->flow_label&IPV6_FLOWLABEL_MASK))
 					np->flow_label &= ~IPV6_FLOWLABEL_MASK;
-				*sflp = rcu_dereference(sfl->next);
+				*sflp = sfl->next;
 				spin_unlock_bh(&ip6_sk_fl_lock);
 				fl_release(sfl->fl);
 				kfree_rcu(sfl, rcu);
-- 
2.4.1


From 1bf445552ac764132b27d611f2f367061ac11a10 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Wed, 3 Feb 2016 02:11:03 +0100
Subject: [PATCH 15/34] unix: correctly track in-flight fds in sending process
 user_struct

[ Upstream commit 415e3d3e90ce9e18727e8843ae343eda5a58fad6 ]

The commit referenced in the Fixes tag incorrectly accounted the number
of in-flight fds over a unix domain socket to the original opener
of the file-descriptor. This allows another process to arbitrary
deplete the original file-openers resource limit for the maximum of
open files. Instead the sending processes and its struct cred should
be credited.

To do so, we add a reference counted struct user_struct pointer to the
scm_fp_list and use it to account for the number of inflight unix fds.

Fixes: 712f4aad406bb1 ("unix: properly account for FDs passed over unix sockets")
Reported-by: David Herrmann <dh.herrmann@gmail.com>
Cc: David Herrmann <dh.herrmann@gmail.com>
Cc: Willy Tarreau <w@1wt.eu>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/af_unix.h | 4 ++--
 include/net/scm.h     | 1 +
 net/core/scm.c        | 7 +++++++
 net/unix/af_unix.c    | 4 ++--
 net/unix/garbage.c    | 8 ++++----
 5 files changed, 16 insertions(+), 8 deletions(-)

diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index e830c3d..7bb69c9 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -6,8 +6,8 @@
 #include <linux/mutex.h>
 #include <net/sock.h>
 
-void unix_inflight(struct file *fp);
-void unix_notinflight(struct file *fp);
+void unix_inflight(struct user_struct *user, struct file *fp);
+void unix_notinflight(struct user_struct *user, struct file *fp);
 void unix_gc(void);
 void wait_for_unix_gc(void);
 struct sock *unix_get_socket(struct file *filp);
diff --git a/include/net/scm.h b/include/net/scm.h
index 262532d..59fa93c 100644
--- a/include/net/scm.h
+++ b/include/net/scm.h
@@ -21,6 +21,7 @@ struct scm_creds {
 struct scm_fp_list {
 	short			count;
 	short			max;
+	struct user_struct	*user;
 	struct file		*fp[SCM_MAX_FD];
 };
 
diff --git a/net/core/scm.c b/net/core/scm.c
index 8a1741b..dce0acb 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -87,6 +87,7 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp)
 		*fplp = fpl;
 		fpl->count = 0;
 		fpl->max = SCM_MAX_FD;
+		fpl->user = NULL;
 	}
 	fpp = &fpl->fp[fpl->count];
 
@@ -107,6 +108,10 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp)
 		*fpp++ = file;
 		fpl->count++;
 	}
+
+	if (!fpl->user)
+		fpl->user = get_uid(current_user());
+
 	return num;
 }
 
@@ -119,6 +124,7 @@ void __scm_destroy(struct scm_cookie *scm)
 		scm->fp = NULL;
 		for (i=fpl->count-1; i>=0; i--)
 			fput(fpl->fp[i]);
+		free_uid(fpl->user);
 		kfree(fpl);
 	}
 }
@@ -336,6 +342,7 @@ struct scm_fp_list *scm_fp_dup(struct scm_fp_list *fpl)
 		for (i = 0; i < fpl->count; i++)
 			get_file(fpl->fp[i]);
 		new_fpl->max = new_fpl->count;
+		new_fpl->user = get_uid(fpl->user);
 	}
 	return new_fpl;
 }
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index c741d83..d644042 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1464,7 +1464,7 @@ static void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb)
 	UNIXCB(skb).fp = NULL;
 
 	for (i = scm->fp->count-1; i >= 0; i--)
-		unix_notinflight(scm->fp->fp[i]);
+		unix_notinflight(scm->fp->user, scm->fp->fp[i]);
 }
 
 static void unix_destruct_scm(struct sk_buff *skb)
@@ -1529,7 +1529,7 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
 		return -ENOMEM;
 
 	for (i = scm->fp->count - 1; i >= 0; i--)
-		unix_inflight(scm->fp->fp[i]);
+		unix_inflight(scm->fp->user, scm->fp->fp[i]);
 	return max_level;
 }
 
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 8fcdc22..6a0d485 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -116,7 +116,7 @@ struct sock *unix_get_socket(struct file *filp)
  * descriptor if it is for an AF_UNIX socket.
  */
 
-void unix_inflight(struct file *fp)
+void unix_inflight(struct user_struct *user, struct file *fp)
 {
 	struct sock *s = unix_get_socket(fp);
 
@@ -133,11 +133,11 @@ void unix_inflight(struct file *fp)
 		}
 		unix_tot_inflight++;
 	}
-	fp->f_cred->user->unix_inflight++;
+	user->unix_inflight++;
 	spin_unlock(&unix_gc_lock);
 }
 
-void unix_notinflight(struct file *fp)
+void unix_notinflight(struct user_struct *user, struct file *fp)
 {
 	struct sock *s = unix_get_socket(fp);
 
@@ -152,7 +152,7 @@ void unix_notinflight(struct file *fp)
 			list_del_init(&u->link);
 		unix_tot_inflight--;
 	}
-	fp->f_cred->user->unix_inflight--;
+	user->unix_inflight--;
 	spin_unlock(&unix_gc_lock);
 }
 
-- 
2.4.1


From 88ad25c59ee9a8a1227d56649506eba1719e6312 Mon Sep 17 00:00:00 2001
From: Hans Westgaard Ry <hans.westgaard.ry@oracle.com>
Date: Wed, 3 Feb 2016 09:26:57 +0100
Subject: [PATCH 16/34] net:Add sysctl_max_skb_frags
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 5f74f82ea34c0da80ea0b49192bb5ea06e063593 ]

Devices may have limits on the number of fragments in an skb they support.
Current codebase uses a constant as maximum for number of fragments one
skb can hold and use.
When enabling scatter/gather and running traffic with many small messages
the codebase uses the maximum number of fragments and may thereby violate
the max for certain devices.
The patch introduces a global variable as max number of fragments.

Signed-off-by: Hans Westgaard Ry <hans.westgaard.ry@oracle.com>
Reviewed-by: Håkon Bugge <haakon.bugge@oracle.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h     |  1 +
 net/core/skbuff.c          |  2 ++
 net/core/sysctl_net_core.c | 10 ++++++++++
 net/ipv4/tcp.c             |  4 ++--
 4 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 1f17abe..6633b0c 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -203,6 +203,7 @@ struct sk_buff;
 #else
 #define MAX_SKB_FRAGS (65536/PAGE_SIZE + 1)
 #endif
+extern int sysctl_max_skb_frags;
 
 typedef struct skb_frag_struct skb_frag_t;
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 2e5fcda..c9793c6 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -79,6 +79,8 @@
 
 struct kmem_cache *skbuff_head_cache __read_mostly;
 static struct kmem_cache *skbuff_fclone_cache __read_mostly;
+int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS;
+EXPORT_SYMBOL(sysctl_max_skb_frags);
 
 /**
  *	skb_panic - private function for out-of-line support
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 95b6139..a6beb7b 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -26,6 +26,7 @@ static int zero = 0;
 static int one = 1;
 static int min_sndbuf = SOCK_MIN_SNDBUF;
 static int min_rcvbuf = SOCK_MIN_RCVBUF;
+static int max_skb_frags = MAX_SKB_FRAGS;
 
 static int net_msg_warn;	/* Unused, but still a sysctl */
 
@@ -392,6 +393,15 @@ static struct ctl_table net_core_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+	{
+		.procname	= "max_skb_frags",
+		.data		= &sysctl_max_skb_frags,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &one,
+		.extra2		= &max_skb_frags,
+	},
 	{ }
 };
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index b5f4f5c..19d385a 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -922,7 +922,7 @@ new_segment:
 
 		i = skb_shinfo(skb)->nr_frags;
 		can_coalesce = skb_can_coalesce(skb, i, page, offset);
-		if (!can_coalesce && i >= MAX_SKB_FRAGS) {
+		if (!can_coalesce && i >= sysctl_max_skb_frags) {
 			tcp_mark_push(tp, skb);
 			goto new_segment;
 		}
@@ -1188,7 +1188,7 @@ new_segment:
 
 			if (!skb_can_coalesce(skb, i, pfrag->page,
 					      pfrag->offset)) {
-				if (i == MAX_SKB_FRAGS || !sg) {
+				if (i == sysctl_max_skb_frags || !sg) {
 					tcp_mark_push(tp, skb);
 					goto new_segment;
 				}
-- 
2.4.1


From d8aa3c292681b63f6aa0ee1ebd2c130832b9917b Mon Sep 17 00:00:00 2001
From: Siva Reddy Kallam <siva.kallam@broadcom.com>
Date: Wed, 3 Feb 2016 14:09:38 +0530
Subject: [PATCH 17/34] tg3: Fix for tg3 transmit queue 0 timed out when too
 many gso_segs

[ Upstream commit b7d987295c74500b733a0ba07f9a9bcc4074fa83 ]

tg3_tso_bug() can hit a condition where the entire tx ring is not big
enough to segment the GSO packet. For example, if MSS is very small,
gso_segs can exceed the tx ring size. When we hit the condition, it
will cause tx timeout.

tg3_tso_bug() is called to handle TSO and DMA hardware bugs.
For TSO bugs, if tg3_tso_bug() cannot succeed, we have to drop the packet.
For DMA bugs, we can still fall back to linearize the SKB and let the
hardware transmit the TSO packet.

This patch adds a function tg3_tso_bug_gso_check() to check if there
are enough tx descriptors for GSO before calling tg3_tso_bug().
The caller will then handle the error appropriately - drop or
lineraize the SKB.

v2: Corrected patch description to avoid confusion.

Signed-off-by: Siva Reddy Kallam <siva.kallam@broadcom.com>
Signed-off-by: Michael Chan <mchan@broadcom.com>
Acked-by: Prashant Sreedharan <prashant@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/tg3.c | 25 +++++++++++++++++++------
 1 file changed, 19 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 0d8af5b..d541520 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -7833,6 +7833,14 @@ static int tigon3_dma_hwbug_workaround(struct tg3_napi *tnapi,
 	return ret;
 }
 
+static bool tg3_tso_bug_gso_check(struct tg3_napi *tnapi, struct sk_buff *skb)
+{
+	/* Check if we will never have enough descriptors,
+	 * as gso_segs can be more than current ring size
+	 */
+	return skb_shinfo(skb)->gso_segs < tnapi->tx_pending / 3;
+}
+
 static netdev_tx_t tg3_start_xmit(struct sk_buff *, struct net_device *);
 
 /* Use GSO to workaround all TSO packets that meet HW bug conditions
@@ -7936,14 +7944,19 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		 * vlan encapsulated.
 		 */
 		if (skb->protocol == htons(ETH_P_8021Q) ||
-		    skb->protocol == htons(ETH_P_8021AD))
-			return tg3_tso_bug(tp, tnapi, txq, skb);
+		    skb->protocol == htons(ETH_P_8021AD)) {
+			if (tg3_tso_bug_gso_check(tnapi, skb))
+				return tg3_tso_bug(tp, tnapi, txq, skb);
+			goto drop;
+		}
 
 		if (!skb_is_gso_v6(skb)) {
 			if (unlikely((ETH_HLEN + hdr_len) > 80) &&
-			    tg3_flag(tp, TSO_BUG))
-				return tg3_tso_bug(tp, tnapi, txq, skb);
-
+			    tg3_flag(tp, TSO_BUG)) {
+				if (tg3_tso_bug_gso_check(tnapi, skb))
+					return tg3_tso_bug(tp, tnapi, txq, skb);
+				goto drop;
+			}
 			ip_csum = iph->check;
 			ip_tot_len = iph->tot_len;
 			iph->check = 0;
@@ -8075,7 +8088,7 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (would_hit_hwbug) {
 		tg3_tx_skb_unmap(tnapi, tnapi->tx_prod, i);
 
-		if (mss) {
+		if (mss && tg3_tso_bug_gso_check(tnapi, skb)) {
 			/* If it's a TSO packet, do GSO instead of
 			 * allocating and copying to a large linear SKB
 			 */
-- 
2.4.1


From 89e06932ea735e5bca99fdeee29e446d0c013c0c Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 3 Feb 2016 23:33:30 +0800
Subject: [PATCH 18/34] sctp: translate network order to host order when users
 get a hmacid

[ Upstream commit 7a84bd46647ff181eb2659fdc99590e6f16e501d ]

Commit ed5a377d87dc ("sctp: translate host order to network order when
setting a hmacid") corrected the hmacid byte-order when setting a hmacid.
but the same issue also exists on getting a hmacid.

We fix it by changing hmacids to host order when users get them with
getsockopt.

Fixes: Commit ed5a377d87dc ("sctp: translate host order to network order when setting a hmacid")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 1b80f20..3c58330 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -5555,6 +5555,7 @@ static int sctp_getsockopt_hmac_ident(struct sock *sk, int len,
 	struct sctp_hmac_algo_param *hmacs;
 	__u16 data_len = 0;
 	u32 num_idents;
+	int i;
 
 	if (!ep->auth_enable)
 		return -EACCES;
@@ -5572,8 +5573,12 @@ static int sctp_getsockopt_hmac_ident(struct sock *sk, int len,
 		return -EFAULT;
 	if (put_user(num_idents, &p->shmac_num_idents))
 		return -EFAULT;
-	if (copy_to_user(p->shmac_idents, hmacs->hmac_ids, data_len))
-		return -EFAULT;
+	for (i = 0; i < num_idents; i++) {
+		__u16 hmacid = ntohs(hmacs->hmac_ids[i]);
+
+		if (copy_to_user(&p->shmac_idents[i], &hmacid, sizeof(__u16)))
+			return -EFAULT;
+	}
 	return 0;
 }
 
-- 
2.4.1


From d21955e438460e31e6d35d891c7f3120ad66b47c Mon Sep 17 00:00:00 2001
From: Alexander Duyck <aduyck@mirantis.com>
Date: Tue, 9 Feb 2016 02:49:54 -0800
Subject: [PATCH 19/34] flow_dissector: Fix unaligned access in
 __skb_flow_dissector when used by eth_get_headlen

[ Upstream commit 461547f3158978c180d74484d58e82be9b8e7357, since
  we lack the flow dissector flags in this release we guard the
  flow label access using a test on 'skb' being NULL ]

This patch fixes an issue with unaligned accesses when using
eth_get_headlen on a page that was DMA aligned instead of being IP aligned.
The fact is when trying to check the length we don't need to be looking at
the flow label so we can reorder the checks to first check if we are
supposed to gather the flow label and then make the call to actually get
it.

v2:  Updated path so that either STOP_AT_FLOW_LABEL or KEY_FLOW_LABEL can
     cause us to check for the flow label.

Reported-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/flow_dissector.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 2c35c02..f96d2ca 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -113,7 +113,6 @@ ip:
 	case htons(ETH_P_IPV6): {
 		const struct ipv6hdr *iph;
 		struct ipv6hdr _iph;
-		__be32 flow_label;
 
 ipv6:
 		iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph);
@@ -130,8 +129,9 @@ ipv6:
 		flow->src = (__force __be32)ipv6_addr_hash(&iph->saddr);
 		flow->dst = (__force __be32)ipv6_addr_hash(&iph->daddr);
 
-		flow_label = ip6_flowlabel(iph);
-		if (flow_label) {
+		if (skb && ip6_flowlabel(iph)) {
+			__be32 flow_label = ip6_flowlabel(iph);
+
 			/* Awesome, IPv6 packet has a flow label so we can
 			 * use that to represent the ports without any
 			 * further dissection.
-- 
2.4.1


From 4126e8100d4a4c11497e098545a99acbf5483f8a Mon Sep 17 00:00:00 2001
From: Alexander Duyck <aduyck@mirantis.com>
Date: Tue, 9 Feb 2016 06:14:43 -0800
Subject: [PATCH 20/34] net: Copy inner L3 and L4 headers as unaligned on GRE
 TEB

[ Upstream commit 78565208d73ca9b654fb9a6b142214d52eeedfd1 ]

This patch corrects the unaligned accesses seen on GRE TEB tunnels when
generating hash keys.  Specifically what this patch does is make it so that
we force the use of skb_copy_bits when the GRE inner headers will be
unaligned due to NET_IP_ALIGNED being a non-zero value.

Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Acked-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/flow_dissector.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index f96d2ca..3556791 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -233,6 +233,13 @@ ipv6:
 					return false;
 				proto = eth->h_proto;
 				nhoff += sizeof(*eth);
+
+				/* Cap headers that we access via pointers at the
+				 * end of the Ethernet header as our maximum alignment
+				 * at that point is only 2 bytes.
+				 */
+				if (NET_IP_ALIGN)
+					hlen = nhoff;
 			}
 			goto again;
 		}
-- 
2.4.1


From 2fab3b421ef1a12bd4a24eff8b6fdc5a78e3f594 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 10 Feb 2016 16:47:11 +0100
Subject: [PATCH 21/34] bpf: fix branch offset adjustment on backjumps after
 patching ctx expansion

[ Upstream commit a1b14d27ed0965838350f1377ff97c93ee383492 ]

When ctx access is used, the kernel often needs to expand/rewrite
instructions, so after that patching, branch offsets have to be
adjusted for both forward and backward jumps in the new eBPF program,
but for backward jumps it fails to account the delta. Meaning, for
example, if the expansion happens exactly on the insn that sits at
the jump target, it doesn't fix up the back jump offset.

Analysis on what the check in adjust_branches() is currently doing:

  /* adjust offset of jmps if necessary */
  if (i < pos && i + insn->off + 1 > pos)
    insn->off += delta;
  else if (i > pos && i + insn->off + 1 < pos)
    insn->off -= delta;

First condition (forward jumps):

  Before:                         After:

  insns[0]                        insns[0]
  insns[1] <--- i/insn            insns[1] <--- i/insn
  insns[2] <--- pos               insns[P] <--- pos
  insns[3]                        insns[P]  `------| delta
  insns[4] <--- target_X          insns[P]   `-----|
  insns[5]                        insns[3]
                                  insns[4] <--- target_X
                                  insns[5]

First case is if we cross pos-boundary and the jump instruction was
before pos. This is handeled correctly. I.e. if i == pos, then this
would mean our jump that we currently check was the patchlet itself
that we just injected. Since such patchlets are self-contained and
have no awareness of any insns before or after the patched one, the
delta is correctly not adjusted. Also, for the second condition in
case of i + insn->off + 1 == pos, means we jump to that newly patched
instruction, so no offset adjustment are needed. That part is correct.

Second condition (backward jumps):

  Before:                         After:

  insns[0]                        insns[0]
  insns[1] <--- target_X          insns[1] <--- target_X
  insns[2] <--- pos <-- target_Y  insns[P] <--- pos <-- target_Y
  insns[3]                        insns[P]  `------| delta
  insns[4] <--- i/insn            insns[P]   `-----|
  insns[5]                        insns[3]
                                  insns[4] <--- i/insn
                                  insns[5]

Second interesting case is where we cross pos-boundary and the jump
instruction was after pos. Backward jump with i == pos would be
impossible and pose a bug somewhere in the patchlet, so the first
condition checking i > pos is okay only by itself. However, i +
insn->off + 1 < pos does not always work as intended to trigger the
adjustment. It works when jump targets would be far off where the
delta wouldn't matter. But, for example, where the fixed insn->off
before pointed to pos (target_Y), it now points to pos + delta, so
that additional room needs to be taken into account for the check.
This means that i) both tests here need to be adjusted into pos + delta,
and ii) for the second condition, the test needs to be <= as pos
itself can be a target in the backjump, too.

Fixes: 9bac3d6d548e ("bpf: allow extended BPF programs access skb fields")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 141d562..6582410 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1944,7 +1944,7 @@ static void adjust_branches(struct bpf_prog *prog, int pos, int delta)
 		/* adjust offset of jmps if necessary */
 		if (i < pos && i + insn->off + 1 > pos)
 			insn->off += delta;
-		else if (i > pos && i + insn->off + 1 < pos)
+		else if (i > pos + delta && i + insn->off + 1 <= pos + delta)
 			insn->off -= delta;
 	}
 }
-- 
2.4.1


From e8b38a5db8a2b0f6d5480af6594ed4365235d82f Mon Sep 17 00:00:00 2001
From: Jay Vosburgh <jay.vosburgh@canonical.com>
Date: Tue, 2 Feb 2016 13:35:56 -0800
Subject: [PATCH 22/34] bonding: Fix ARP monitor validation

[ Upstream commit 21a75f0915dde8674708b39abfcda113911c49b1 ]

The current logic in bond_arp_rcv will accept an incoming ARP for
validation if (a) the receiving slave is either "active" (which includes
the currently active slave, or the current ARP slave) or, (b) there is a
currently active slave, and it has received an ARP since it became active.
For case (b), the receiving slave isn't the currently active slave, and is
receiving the original broadcast ARP request, not an ARP reply from the
target.

	This logic can fail if there is no currently active slave.  In
this situation, the ARP probe logic cycles through all slaves, assigning
each in turn as the "current_arp_slave" for one arp_interval, then setting
that one as "active," and sending an ARP probe from that slave.  The
current logic expects the ARP reply to arrive on the sending
current_arp_slave, however, due to switch FDB updating delays, the reply
may be directed to another slave.

	This can arise if the bonding slaves and switch are working, but
the ARP target is not responding.  When the ARP target recovers, a
condition may result wherein the ARP target host replies faster than the
switch can update its forwarding table, causing each ARP reply to be sent
to the previous current_arp_slave.  This will never pass the logic in
bond_arp_rcv, as neither of the above conditions (a) or (b) are met.

	Some experimentation on a LAN shows ARP reply round trips in the
200 usec range, but my available switches never update their FDB in less
than 4000 usec.

	This patch changes the logic in bond_arp_rcv to additionally
accept an ARP reply for validation on any slave if there is a current ARP
slave and it sent an ARP probe during the previous arp_interval.

Fixes: aeea64ac717a ("bonding: don't trust arp requests unless active slave really works")
Cc: Veaceslav Falico <vfalico@gmail.com>
Cc: Andy Gospodarek <gospo@cumulusnetworks.com>
Signed-off-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 39 ++++++++++++++++++++++++++++-----------
 1 file changed, 28 insertions(+), 11 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 72ba774..bd744e3 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -214,6 +214,8 @@ static void bond_uninit(struct net_device *bond_dev);
 static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev,
 						struct rtnl_link_stats64 *stats);
 static void bond_slave_arr_handler(struct work_struct *work);
+static bool bond_time_in_interval(struct bonding *bond, unsigned long last_act,
+				  int mod);
 
 /*---------------------------- General routines -----------------------------*/
 
@@ -2397,7 +2399,7 @@ int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond,
 		 struct slave *slave)
 {
 	struct arphdr *arp = (struct arphdr *)skb->data;
-	struct slave *curr_active_slave;
+	struct slave *curr_active_slave, *curr_arp_slave;
 	unsigned char *arp_ptr;
 	__be32 sip, tip;
 	int alen, is_arp = skb->protocol == __cpu_to_be16(ETH_P_ARP);
@@ -2444,26 +2446,41 @@ int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond,
 		     &sip, &tip);
 
 	curr_active_slave = rcu_dereference(bond->curr_active_slave);
+	curr_arp_slave = rcu_dereference(bond->current_arp_slave);
 
-	/* Backup slaves won't see the ARP reply, but do come through
-	 * here for each ARP probe (so we swap the sip/tip to validate
-	 * the probe).  In a "redundant switch, common router" type of
-	 * configuration, the ARP probe will (hopefully) travel from
-	 * the active, through one switch, the router, then the other
-	 * switch before reaching the backup.
+	/* We 'trust' the received ARP enough to validate it if:
+	 *
+	 * (a) the slave receiving the ARP is active (which includes the
+	 * current ARP slave, if any), or
+	 *
+	 * (b) the receiving slave isn't active, but there is a currently
+	 * active slave and it received valid arp reply(s) after it became
+	 * the currently active slave, or
+	 *
+	 * (c) there is an ARP slave that sent an ARP during the prior ARP
+	 * interval, and we receive an ARP reply on any slave.  We accept
+	 * these because switch FDB update delays may deliver the ARP
+	 * reply to a slave other than the sender of the ARP request.
 	 *
-	 * We 'trust' the arp requests if there is an active slave and
-	 * it received valid arp reply(s) after it became active. This
-	 * is done to avoid endless looping when we can't reach the
+	 * Note: for (b), backup slaves are receiving the broadcast ARP
+	 * request, not a reply.  This request passes from the sending
+	 * slave through the L2 switch(es) to the receiving slave.  Since
+	 * this is checking the request, sip/tip are swapped for
+	 * validation.
+	 *
+	 * This is done to avoid endless looping when we can't reach the
 	 * arp_ip_target and fool ourselves with our own arp requests.
 	 */
-
 	if (bond_is_active_slave(slave))
 		bond_validate_arp(bond, slave, sip, tip);
 	else if (curr_active_slave &&
 		 time_after(slave_last_rx(bond, curr_active_slave),
 			    curr_active_slave->last_link_up))
 		bond_validate_arp(bond, slave, tip, sip);
+	else if (curr_arp_slave && (arp->ar_op == htons(ARPOP_REPLY)) &&
+		 bond_time_in_interval(bond,
+				       dev_trans_start(curr_arp_slave->dev), 1))
+		bond_validate_arp(bond, slave, sip, tip);
 
 out_unlock:
 	if (arp != (struct arphdr *)skb->data)
-- 
2.4.1


From b3410b06fb9b7ea3bb4fc85940387c01507f8119 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 4 Feb 2016 06:23:28 -0800
Subject: [PATCH 23/34] ipv4: fix memory leaks in ip_cmsg_send() callers

[ Upstream commit 919483096bfe75dda338e98d56da91a263746a0a ]

Dmitry reported memory leaks of IP options allocated in
ip_cmsg_send() when/if this function returns an error.

Callers are responsible for the freeing.

Many thanks to Dmitry for the report and diagnostic.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_sockglue.c | 2 ++
 net/ipv4/ping.c        | 4 +++-
 net/ipv4/raw.c         | 4 +++-
 net/ipv4/udp.c         | 4 +++-
 4 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 6ddde89..b6c7bde 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -249,6 +249,8 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc,
 		switch (cmsg->cmsg_type) {
 		case IP_RETOPTS:
 			err = cmsg->cmsg_len - CMSG_ALIGN(sizeof(struct cmsghdr));
+
+			/* Our caller is responsible for freeing ipc->opt */
 			err = ip_options_get(net, &ipc->opt, CMSG_DATA(cmsg),
 					     err < 40 ? err : 40);
 			if (err)
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 05ff44b..f6ee0d5 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -745,8 +745,10 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	if (msg->msg_controllen) {
 		err = ip_cmsg_send(sock_net(sk), msg, &ipc, false);
-		if (err)
+		if (unlikely(err)) {
+			kfree(ipc.opt);
 			return err;
+		}
 		if (ipc.opt)
 			free = 1;
 	}
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 561cd4b..c77aac7 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -543,8 +543,10 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	if (msg->msg_controllen) {
 		err = ip_cmsg_send(sock_net(sk), msg, &ipc, false);
-		if (err)
+		if (unlikely(err)) {
+			kfree(ipc.opt);
 			goto out;
+		}
 		if (ipc.opt)
 			free = 1;
 	}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 1b8c5ba..a390174 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -963,8 +963,10 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	if (msg->msg_controllen) {
 		err = ip_cmsg_send(sock_net(sk), msg, &ipc,
 				   sk->sk_family == AF_INET6);
-		if (err)
+		if (unlikely(err)) {
+			kfree(ipc.opt);
 			return err;
+		}
 		if (ipc.opt)
 			free = 1;
 		connected = 0;
-- 
2.4.1


From 631df6b90c7eeff42da24023f4ba3ebc2cab2296 Mon Sep 17 00:00:00 2001
From: Rainer Weikusat <rweikusat@mobileactivedefense.com>
Date: Thu, 11 Feb 2016 19:37:27 +0000
Subject: [PATCH 24/34] af_unix: Guard against other == sk in
 unix_dgram_sendmsg

[ Upstream commit a5527dda344fff0514b7989ef7a755729769daa1 ]

The unix_dgram_sendmsg routine use the following test

if (unlikely(unix_peer(other) != sk && unix_recvq_full(other))) {

to determine if sk and other are in an n:1 association (either
established via connect or by using sendto to send messages to an
unrelated socket identified by address). This isn't correct as the
specified address could have been bound to the sending socket itself or
because this socket could have been connected to itself by the time of
the unix_peer_get but disconnected before the unix_state_lock(other). In
both cases, the if-block would be entered despite other == sk which
might either block the sender unintentionally or lead to trying to unlock
the same spin lock twice for a non-blocking send. Add a other != sk
check to guard against this.

Fixes: 7d267278a9ec ("unix: avoid use-after-free in ep_remove_wait_queue")
Reported-By: Philipp Hahn <pmhahn@pmhahn.de>
Signed-off-by: Rainer Weikusat <rweikusat@mobileactivedefense.com>
Tested-by: Philipp Hahn <pmhahn@pmhahn.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index d644042..535a642 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1714,7 +1714,12 @@ restart_locked:
 			goto out_unlock;
 	}
 
-	if (unlikely(unix_peer(other) != sk && unix_recvq_full(other))) {
+	/* other == sk && unix_peer(other) != sk if
+	 * - unix_peer(sk) == NULL, destination address bound to sk
+	 * - unix_peer(sk) == sk by time of get but disconnected before lock
+	 */
+	if (other != sk &&
+	    unlikely(unix_peer(other) != sk && unix_recvq_full(other))) {
 		if (timeo) {
 			timeo = unix_wait_for_peer(other, timeo);
 
-- 
2.4.1


From 08bde5fe438f572f92b5869ecfa27abd192d9926 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Fri, 12 Feb 2016 16:42:14 +0100
Subject: [PATCH 25/34] qmi_wwan: add "4G LTE usb-modem U901"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit aac8d3c282e024c344c5b86dc1eab7af88bb9716 ]

Thomas reports:

T:  Bus=01 Lev=01 Prnt=01 Port=03 Cnt=01 Dev#=  4 Spd=480 MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=05c6 ProdID=6001 Rev=00.00
S:  Manufacturer=USB Modem
S:  Product=USB Modem
S:  SerialNumber=1234567890ABCDEF
C:  #Ifs= 5 Cfg#= 1 Atr=e0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
I:  If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
I:  If#= 2 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
I:  If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
I:  If#= 4 Alt= 0 #EPs= 2 Cls=08(stor.) Sub=06 Prot=50 Driver=usb-storage

Reported-by: Thomas Schäfer <tschaefer@t-online.de>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 71190dc..cffb252 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -542,6 +542,7 @@ static const struct usb_device_id products[] = {
 
 	/* 3. Combined interface devices matching on interface number */
 	{QMI_FIXED_INTF(0x0408, 0xea42, 4)},	/* Yota / Megafon M100-1 */
+	{QMI_FIXED_INTF(0x05c6, 0x6001, 3)},	/* 4G LTE usb-modem U901 */
 	{QMI_FIXED_INTF(0x05c6, 0x7000, 0)},
 	{QMI_FIXED_INTF(0x05c6, 0x7001, 1)},
 	{QMI_FIXED_INTF(0x05c6, 0x7002, 1)},
-- 
2.4.1


From 8e1208d15c594fd8c8380d31ec0c48a90c457401 Mon Sep 17 00:00:00 2001
From: Amir Vadai <amir@vadai.me>
Date: Wed, 17 Feb 2016 17:24:22 +0200
Subject: [PATCH 26/34] net/mlx4_en: Count HW buffer overrun only once

[ Upstream commit 281e8b2fdf8e4ef366b899453cae50e09b577ada ]

RdropOvflw counts overrun of HW buffer, therefore should
be used for rx_fifo_errors only.

Currently RdropOvflw counter is mistakenly also set into
rx_missed_errors and rx_over_errors too, which makes the
device total dropped packets accounting to show wrong results.

Fix that. Use it for rx_fifo_errors only.

Fixes: c27a02cd94d6 ('mlx4_en: Add driver for Mellanox ConnectX 10GbE NIC')
Signed-off-by: Amir Vadai <amir@vadai.me>
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_port.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c
index 0a56f01..760a8b3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c
@@ -223,11 +223,11 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
 	stats->collisions = 0;
 	stats->rx_dropped = be32_to_cpu(mlx4_en_stats->RDROP);
 	stats->rx_length_errors = be32_to_cpu(mlx4_en_stats->RdropLength);
-	stats->rx_over_errors = be32_to_cpu(mlx4_en_stats->RdropOvflw);
+	stats->rx_over_errors = 0;
 	stats->rx_crc_errors = be32_to_cpu(mlx4_en_stats->RCRC);
 	stats->rx_frame_errors = 0;
 	stats->rx_fifo_errors = be32_to_cpu(mlx4_en_stats->RdropOvflw);
-	stats->rx_missed_errors = be32_to_cpu(mlx4_en_stats->RdropOvflw);
+	stats->rx_missed_errors = 0;
 	stats->tx_aborted_errors = 0;
 	stats->tx_carrier_errors = 0;
 	stats->tx_fifo_errors = 0;
-- 
2.4.1


From 860101bf000a6d18cb5ae385a6b8041c173cd0c6 Mon Sep 17 00:00:00 2001
From: Eugenia Emantayev <eugenia@mellanox.com>
Date: Wed, 17 Feb 2016 17:24:23 +0200
Subject: [PATCH 27/34] net/mlx4_en: Choose time-stamping shift value according
 to HW frequency

[ Upstream commit 31c128b66e5b28f468076e4f3ca3025c35342041 ]

Previously, the shift value used for time-stamping was constant and didn't
depend on the HW chip frequency. Change that to take the frequency into account
and calculate the maximal value in cycles per wraparound of ten seconds. This
time slot was chosen since it gives a good accuracy in time synchronization.

Algorithm for shift value calculation:
 * Round up the maximal value in cycles to nearest power of two

 * Calculate maximal multiplier by division of all 64 bits set
   to above result

 * Then, invert the function clocksource_khz2mult() to get the shift from
   maximal mult value

Fixes: ec693d47010e ('net/mlx4_en: Add HW timestamping (TS) support')
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Reviewed-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_clock.c | 25 +++++++++++++++++++------
 1 file changed, 19 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_clock.c b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
index 8a083d7..dae2ebb 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
@@ -236,6 +236,24 @@ static const struct ptp_clock_info mlx4_en_ptp_clock_info = {
 	.enable		= mlx4_en_phc_enable,
 };
 
+#define MLX4_EN_WRAP_AROUND_SEC	10ULL
+
+/* This function calculates the max shift that enables the user range
+ * of MLX4_EN_WRAP_AROUND_SEC values in the cycles register.
+ */
+static u32 freq_to_shift(u16 freq)
+{
+	u32 freq_khz = freq * 1000;
+	u64 max_val_cycles = freq_khz * 1000 * MLX4_EN_WRAP_AROUND_SEC;
+	u64 max_val_cycles_rounded = is_power_of_2(max_val_cycles + 1) ?
+		max_val_cycles : roundup_pow_of_two(max_val_cycles) - 1;
+	/* calculate max possible multiplier in order to fit in 64bit */
+	u64 max_mul = div_u64(0xffffffffffffffffULL, max_val_cycles_rounded);
+
+	/* This comes from the reverse of clocksource_khz2mult */
+	return ilog2(div_u64(max_mul * freq_khz, 1000000));
+}
+
 void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev)
 {
 	struct mlx4_dev *dev = mdev->dev;
@@ -247,12 +265,7 @@ void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev)
 	memset(&mdev->cycles, 0, sizeof(mdev->cycles));
 	mdev->cycles.read = mlx4_en_read_clock;
 	mdev->cycles.mask = CLOCKSOURCE_MASK(48);
-	/* Using shift to make calculation more accurate. Since current HW
-	 * clock frequency is 427 MHz, and cycles are given using a 48 bits
-	 * register, the biggest shift when calculating using u64, is 14
-	 * (max_cycles * multiplier < 2^64)
-	 */
-	mdev->cycles.shift = 14;
+	mdev->cycles.shift = freq_to_shift(dev->caps.hca_core_clock);
 	mdev->cycles.mult =
 		clocksource_khz2mult(1000 * dev->caps.hca_core_clock, mdev->cycles.shift);
 	mdev->nominal_c_mult = mdev->cycles.mult;
-- 
2.4.1


From 46edd100765589d9a783ccff96423b785e501aca Mon Sep 17 00:00:00 2001
From: Eugenia Emantayev <eugenia@mellanox.com>
Date: Wed, 17 Feb 2016 17:24:27 +0200
Subject: [PATCH 28/34] net/mlx4_en: Avoid changing dev->features directly in
 run-time

[ Upstream commit 925ab1aa9394bbaeac47ee5b65d3fdf0fb8135cf ]

It's forbidden to manually change dev->features in run-time. Currently, this is
done in the driver to make sure that GSO_UDP_TUNNEL is advertized only when
VXLAN tunnel is set. However, since the stack actually does features intersection
with hw_enc_features, we can safely revert to advertizing features early when
registering the netdevice.

Fixes: f4a1edd56120 ('net/mlx4_en: Advertize encapsulation offloads [...]')
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index a5a0b84..e918959 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2330,8 +2330,6 @@ out:
 	/* set offloads */
 	priv->dev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_RXCSUM |
 				      NETIF_F_TSO | NETIF_F_GSO_UDP_TUNNEL;
-	priv->dev->hw_features |= NETIF_F_GSO_UDP_TUNNEL;
-	priv->dev->features    |= NETIF_F_GSO_UDP_TUNNEL;
 }
 
 static void mlx4_en_del_vxlan_offloads(struct work_struct *work)
@@ -2342,8 +2340,6 @@ static void mlx4_en_del_vxlan_offloads(struct work_struct *work)
 	/* unset offloads */
 	priv->dev->hw_enc_features &= ~(NETIF_F_IP_CSUM | NETIF_F_RXCSUM |
 				      NETIF_F_TSO | NETIF_F_GSO_UDP_TUNNEL);
-	priv->dev->hw_features &= ~NETIF_F_GSO_UDP_TUNNEL;
-	priv->dev->features    &= ~NETIF_F_GSO_UDP_TUNNEL;
 
 	ret = mlx4_SET_PORT_VXLAN(priv->mdev->dev, priv->port,
 				  VXLAN_STEER_BY_OUTER_MAC, 0);
@@ -2940,6 +2936,11 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 		priv->rss_hash_fn = ETH_RSS_HASH_TOP;
 	}
 
+	if (mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) {
+		dev->hw_features |= NETIF_F_GSO_UDP_TUNNEL;
+		dev->features    |= NETIF_F_GSO_UDP_TUNNEL;
+	}
+
 	mdev->pndev[port] = dev;
 	mdev->upper[port] = NULL;
 
-- 
2.4.1


From 446b8f5e12e2b12b3c06eb2814332a1820b3c8fa Mon Sep 17 00:00:00 2001
From: Mark Tomlinson <mark.tomlinson@alliedtelesis.co.nz>
Date: Mon, 15 Feb 2016 16:24:44 +1300
Subject: [PATCH 29/34] l2tp: Fix error creating L2TP tunnels

[ Upstream commit 853effc55b0f975abd6d318cca486a9c1b67e10f ]

A previous commit (33f72e6) added notification via netlink for tunnels
when created/modified/deleted. If the notification returned an error,
this error was returned from the tunnel function. If there were no
listeners, the error code ESRCH was returned, even though having no
listeners is not an error. Other calls to this and other similar
notification functions either ignore the error code, or filter ESRCH.
This patch checks for ESRCH and does not flag this as an error.

Reviewed-by: Hamish Martin <hamish.martin@alliedtelesis.co.nz>
Signed-off-by: Mark Tomlinson <mark.tomlinson@alliedtelesis.co.nz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_netlink.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index 9e13c2f..fe92a08 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -124,8 +124,13 @@ static int l2tp_tunnel_notify(struct genl_family *family,
 	ret = l2tp_nl_tunnel_send(msg, info->snd_portid, info->snd_seq,
 				  NLM_F_ACK, tunnel, cmd);
 
-	if (ret >= 0)
-		return genlmsg_multicast_allns(family, msg, 0,	0, GFP_ATOMIC);
+	if (ret >= 0) {
+		ret = genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC);
+		/* We don't care if no one is listening */
+		if (ret == -ESRCH)
+			ret = 0;
+		return ret;
+	}
 
 	nlmsg_free(msg);
 
@@ -147,8 +152,13 @@ static int l2tp_session_notify(struct genl_family *family,
 	ret = l2tp_nl_session_send(msg, info->snd_portid, info->snd_seq,
 				   NLM_F_ACK, session, cmd);
 
-	if (ret >= 0)
-		return genlmsg_multicast_allns(family, msg, 0,	0, GFP_ATOMIC);
+	if (ret >= 0) {
+		ret = genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC);
+		/* We don't care if no one is listening */
+		if (ret == -ESRCH)
+			ret = 0;
+		return ret;
+	}
 
 	nlmsg_free(msg);
 
-- 
2.4.1


From 47428bcfddd944e0c2d5b048de440dc96ecf8b0f Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Mon, 15 Feb 2016 17:01:10 +0100
Subject: [PATCH 30/34] pppoe: fix reference counting in PPPoE proxy

[ Upstream commit 29e73269aa4d36f92b35610c25f8b01c789b0dc8 ]

Drop reference on the relay_po socket when __pppoe_xmit() succeeds.
This is already handled correctly in the error path.

Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pppoe.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 9c8fabe..d1c4bc1 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -395,6 +395,8 @@ static int pppoe_rcv_core(struct sock *sk, struct sk_buff *skb)
 
 		if (!__pppoe_xmit(sk_pppox(relay_po), skb))
 			goto abort_put;
+
+		sock_put(sk_pppox(relay_po));
 	} else {
 		if (sock_queue_rcv_skb(sk, skb))
 			goto abort_kfree;
-- 
2.4.1


From 6fa83f7aa46ec6035c1c41f19e63833ecdcd49ca Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 18 Feb 2016 21:21:19 +0800
Subject: [PATCH 31/34] route: check and remove route cache when we get route

[ Upstream commit deed49df7390d5239024199e249190328f1651e7 ]

Since the gc of ipv4 route was removed, the route cached would has
no chance to be removed, and even it has been timeout, it still could
be used, cause no code to check it's expires.

Fix this issue by checking  and removing route cache when we get route.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_fib.h |  1 +
 net/ipv4/route.c     | 77 ++++++++++++++++++++++++++++++++++++++++++----------
 2 files changed, 64 insertions(+), 14 deletions(-)

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 54271ed..13f1a97 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -59,6 +59,7 @@ struct fib_nh_exception {
 	struct rtable __rcu		*fnhe_rth_input;
 	struct rtable __rcu		*fnhe_rth_output;
 	unsigned long			fnhe_stamp;
+	struct rcu_head			rcu;
 };
 
 struct fnhe_hash_bucket {
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index f45f2a1..1d3cdb4d 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -125,6 +125,7 @@ static int ip_rt_mtu_expires __read_mostly	= 10 * 60 * HZ;
 static int ip_rt_min_pmtu __read_mostly		= 512 + 20 + 20;
 static int ip_rt_min_advmss __read_mostly	= 256;
 
+static int ip_rt_gc_timeout __read_mostly	= RT_GC_TIMEOUT;
 /*
  *	Interface to generic destination cache.
  */
@@ -753,7 +754,7 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
 				struct fib_nh *nh = &FIB_RES_NH(res);
 
 				update_or_create_fnhe(nh, fl4->daddr, new_gw,
-						      0, 0);
+						0, jiffies + ip_rt_gc_timeout);
 			}
 			if (kill_route)
 				rt->dst.obsolete = DST_OBSOLETE_KILL;
@@ -1538,6 +1539,36 @@ static void ip_handle_martian_source(struct net_device *dev,
 #endif
 }
 
+static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
+{
+	struct fnhe_hash_bucket *hash;
+	struct fib_nh_exception *fnhe, __rcu **fnhe_p;
+	u32 hval = fnhe_hashfun(daddr);
+
+	spin_lock_bh(&fnhe_lock);
+
+	hash = rcu_dereference_protected(nh->nh_exceptions,
+					 lockdep_is_held(&fnhe_lock));
+	hash += hval;
+
+	fnhe_p = &hash->chain;
+	fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock));
+	while (fnhe) {
+		if (fnhe->fnhe_daddr == daddr) {
+			rcu_assign_pointer(*fnhe_p, rcu_dereference_protected(
+				fnhe->fnhe_next, lockdep_is_held(&fnhe_lock)));
+			fnhe_flush_routes(fnhe);
+			kfree_rcu(fnhe, rcu);
+			break;
+		}
+		fnhe_p = &fnhe->fnhe_next;
+		fnhe = rcu_dereference_protected(fnhe->fnhe_next,
+						 lockdep_is_held(&fnhe_lock));
+	}
+
+	spin_unlock_bh(&fnhe_lock);
+}
+
 /* called in rcu_read_lock() section */
 static int __mkroute_input(struct sk_buff *skb,
 			   const struct fib_result *res,
@@ -1592,11 +1623,20 @@ static int __mkroute_input(struct sk_buff *skb,
 
 	fnhe = find_exception(&FIB_RES_NH(*res), daddr);
 	if (do_cache) {
-		if (fnhe)
+		if (fnhe) {
 			rth = rcu_dereference(fnhe->fnhe_rth_input);
-		else
-			rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
+			if (rth && rth->dst.expires &&
+			    time_after(jiffies, rth->dst.expires)) {
+				ip_del_fnhe(&FIB_RES_NH(*res), daddr);
+				fnhe = NULL;
+			} else {
+				goto rt_cache;
+			}
+		}
+
+		rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
 
+rt_cache:
 		if (rt_cache_valid(rth)) {
 			skb_dst_set_noref(skb, &rth->dst);
 			goto out;
@@ -1945,19 +1985,29 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 		struct fib_nh *nh = &FIB_RES_NH(*res);
 
 		fnhe = find_exception(nh, fl4->daddr);
-		if (fnhe)
+		if (fnhe) {
 			prth = &fnhe->fnhe_rth_output;
-		else {
-			if (unlikely(fl4->flowi4_flags &
-				     FLOWI_FLAG_KNOWN_NH &&
-				     !(nh->nh_gw &&
-				       nh->nh_scope == RT_SCOPE_LINK))) {
-				do_cache = false;
-				goto add;
+			rth = rcu_dereference(*prth);
+			if (rth && rth->dst.expires &&
+			    time_after(jiffies, rth->dst.expires)) {
+				ip_del_fnhe(nh, fl4->daddr);
+				fnhe = NULL;
+			} else {
+				goto rt_cache;
 			}
-			prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
 		}
+
+		if (unlikely(fl4->flowi4_flags &
+			     FLOWI_FLAG_KNOWN_NH &&
+			     !(nh->nh_gw &&
+			       nh->nh_scope == RT_SCOPE_LINK))) {
+			do_cache = false;
+			goto add;
+		}
+		prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
 		rth = rcu_dereference(*prth);
+
+rt_cache:
 		if (rt_cache_valid(rth)) {
 			dst_hold(&rth->dst);
 			return rth;
@@ -2504,7 +2554,6 @@ void ip_rt_multicast_event(struct in_device *in_dev)
 }
 
 #ifdef CONFIG_SYSCTL
-static int ip_rt_gc_timeout __read_mostly	= RT_GC_TIMEOUT;
 static int ip_rt_gc_interval __read_mostly  = 60 * HZ;
 static int ip_rt_gc_min_interval __read_mostly	= HZ / 2;
 static int ip_rt_gc_elasticity __read_mostly	= 8;
-- 
2.4.1


From 1f3ccbd82112896b6d775fa9988296e65a84ec83 Mon Sep 17 00:00:00 2001
From: Anton Protopopov <a.s.protopopov@gmail.com>
Date: Tue, 16 Feb 2016 21:43:16 -0500
Subject: [PATCH 32/34] rtnl: RTM_GETNETCONF: fix wrong return value

[ Upstream commit a97eb33ff225f34a8124774b3373fd244f0e83ce ]

An error response from a RTM_GETNETCONF request can return the positive
error value EINVAL in the struct nlmsgerr that can mislead userspace.

Signed-off-by: Anton Protopopov <a.s.protopopov@gmail.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/devinet.c  | 2 +-
 net/ipv6/addrconf.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 419d23c..280d46f 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1839,7 +1839,7 @@ static int inet_netconf_get_devconf(struct sk_buff *in_skb,
 	if (err < 0)
 		goto errout;
 
-	err = EINVAL;
+	err = -EINVAL;
 	if (!tb[NETCONFA_IFINDEX])
 		goto errout;
 
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index fcfbd05..f555f4f 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -569,7 +569,7 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb,
 	if (err < 0)
 		goto errout;
 
-	err = EINVAL;
+	err = -EINVAL;
 	if (!tb[NETCONFA_IFINDEX])
 		goto errout;
 
-- 
2.4.1


From 23a177abe9bc1f608dde418c1b3f8a8ac73f0abe Mon Sep 17 00:00:00 2001
From: "Dmitry V. Levin" <ldv@altlinux.org>
Date: Fri, 19 Feb 2016 04:27:48 +0300
Subject: [PATCH 33/34] unix_diag: fix incorrect sign extension in
 unix_lookup_by_ino

[ Upstream commit b5f0549231ffb025337be5a625b0ff9f52b016f0 ]

The value passed by unix_diag_get_exact to unix_lookup_by_ino has type
__u32, but unix_lookup_by_ino's argument ino has type int, which is not
a problem yet.
However, when ino is compared with sock_i_ino return value of type
unsigned long, ino is sign extended to signed long, and this results
to incorrect comparison on 64-bit architectures for inode numbers
greater than INT_MAX.

This bug was found by strace test suite.

Fixes: 5d3cae8bc39d ("unix_diag: Dumping exact socket core")
Signed-off-by: Dmitry V. Levin <ldv@altlinux.org>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/diag.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/unix/diag.c b/net/unix/diag.c
index c512f64..4d96797 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -220,7 +220,7 @@ done:
 	return skb->len;
 }
 
-static struct sock *unix_lookup_by_ino(int ino)
+static struct sock *unix_lookup_by_ino(unsigned int ino)
 {
 	int i;
 	struct sock *sk;
-- 
2.4.1


From 79eb6ee61e06f1b95b25365401c6bccbe012cf51 Mon Sep 17 00:00:00 2001
From: Neil Horman <nhorman@tuxdriver.com>
Date: Thu, 18 Feb 2016 16:10:57 -0500
Subject: [PATCH 34/34] sctp: Fix port hash table size computation

[ Upstream commit d9749fb5942f51555dc9ce1ac0dbb1806960a975 ]

Dmitry Vyukov noted recently that the sctp_port_hashtable had an error in
its size computation, observing that the current method never guaranteed
that the hashsize (measured in number of entries) would be a power of two,
which the input hash function for that table requires.  The root cause of
the problem is that two values need to be computed (one, the allocation
order of the storage requries, as passed to __get_free_pages, and two the
number of entries for the hash table).  Both need to be ^2, but for
different reasons, and the existing code is simply computing one order
value, and using it as the basis for both, which is wrong (i.e. it assumes
that ((1<<order)*PAGE_SIZE)/sizeof(bucket) is still ^2 when its not).

To fix this, we change the logic slightly.  We start by computing a goal
allocation order (which is limited by the maximum size hash table we want
to support.  Then we attempt to allocate that size table, decreasing the
order until a successful allocation is made.  Then, with the resultant
successful order we compute the number of buckets that hash table supports,
which we then round down to the nearest power of two, giving us the number
of entries the table actually supports.

I've tested this locally here, using non-debug and spinlock-debug kernels,
and the number of entries in the hashtable consistently work out to be
powers of two in all cases.

Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
CC: Dmitry Vyukov <dvyukov@google.com>
CC: Vladislav Yasevich <vyasevich@gmail.com>
CC: "David S. Miller" <davem@davemloft.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/protocol.c | 47 ++++++++++++++++++++++++++++++++++++++---------
 1 file changed, 38 insertions(+), 9 deletions(-)

diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index e13c3c3..9d134ab 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -60,6 +60,8 @@
 #include <net/inet_common.h>
 #include <net/inet_ecn.h>
 
+#define MAX_SCTP_PORT_HASH_ENTRIES (64 * 1024)
+
 /* Global data structures. */
 struct sctp_globals sctp_globals __read_mostly;
 
@@ -1332,6 +1334,8 @@ static __init int sctp_init(void)
 	unsigned long limit;
 	int max_share;
 	int order;
+	int num_entries;
+	int max_entry_order;
 
 	sock_skb_cb_check_size(sizeof(struct sctp_ulpevent));
 
@@ -1384,14 +1388,24 @@ static __init int sctp_init(void)
 
 	/* Size and allocate the association hash table.
 	 * The methodology is similar to that of the tcp hash tables.
+	 * Though not identical.  Start by getting a goal size
 	 */
 	if (totalram_pages >= (128 * 1024))
 		goal = totalram_pages >> (22 - PAGE_SHIFT);
 	else
 		goal = totalram_pages >> (24 - PAGE_SHIFT);
 
-	for (order = 0; (1UL << order) < goal; order++)
-		;
+	/* Then compute the page order for said goal */
+	order = get_order(goal);
+
+	/* Now compute the required page order for the maximum sized table we
+	 * want to create
+	 */
+	max_entry_order = get_order(MAX_SCTP_PORT_HASH_ENTRIES *
+				    sizeof(struct sctp_bind_hashbucket));
+
+	/* Limit the page order by that maximum hash table size */
+	order = min(order, max_entry_order);
 
 	do {
 		sctp_assoc_hashsize = (1UL << order) * PAGE_SIZE /
@@ -1425,27 +1439,42 @@ static __init int sctp_init(void)
 		INIT_HLIST_HEAD(&sctp_ep_hashtable[i].chain);
 	}
 
-	/* Allocate and initialize the SCTP port hash table.  */
+	/* Allocate and initialize the SCTP port hash table.
+	 * Note that order is initalized to start at the max sized
+	 * table we want to support.  If we can't get that many pages
+	 * reduce the order and try again
+	 */
 	do {
-		sctp_port_hashsize = (1UL << order) * PAGE_SIZE /
-					sizeof(struct sctp_bind_hashbucket);
-		if ((sctp_port_hashsize > (64 * 1024)) && order > 0)
-			continue;
 		sctp_port_hashtable = (struct sctp_bind_hashbucket *)
 			__get_free_pages(GFP_ATOMIC|__GFP_NOWARN, order);
 	} while (!sctp_port_hashtable && --order > 0);
+
 	if (!sctp_port_hashtable) {
 		pr_err("Failed bind hash alloc\n");
 		status = -ENOMEM;
 		goto err_bhash_alloc;
 	}
+
+	/* Now compute the number of entries that will fit in the
+	 * port hash space we allocated
+	 */
+	num_entries = (1UL << order) * PAGE_SIZE /
+		      sizeof(struct sctp_bind_hashbucket);
+
+	/* And finish by rounding it down to the nearest power of two
+	 * this wastes some memory of course, but its needed because
+	 * the hash function operates based on the assumption that
+	 * that the number of entries is a power of two
+	 */
+	sctp_port_hashsize = rounddown_pow_of_two(num_entries);
+
 	for (i = 0; i < sctp_port_hashsize; i++) {
 		spin_lock_init(&sctp_port_hashtable[i].lock);
 		INIT_HLIST_HEAD(&sctp_port_hashtable[i].chain);
 	}
 
-	pr_info("Hash tables configured (established %d bind %d)\n",
-		sctp_assoc_hashsize, sctp_port_hashsize);
+	pr_info("Hash tables configured (established %d bind %d/%d)\n",
+		sctp_assoc_hashsize, sctp_port_hashsize, num_entries);
 
 	sctp_sysctl_register();
 
-- 
2.4.1


[-- Attachment #3: net_44.mbox --]
[-- Type: Application/Octet-Stream, Size: 132632 bytes --]

From 9fa527a0fe2f2df2665ac7aaa28bc0d75ff779ea Mon Sep 17 00:00:00 2001
From: Ursula Braun <ursula.braun@de.ibm.com>
Date: Tue, 19 Jan 2016 10:41:33 +0100
Subject: [PATCH 01/47] af_iucv: Validate socket address length in
 iucv_sock_bind()

[ Upstream commit 52a82e23b9f2a9e1d429c5207f8575784290d008 ]

Signed-off-by: Ursula Braun <ursula.braun@de.ibm.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Reviewed-by: Evgeny Cherkashin <Eugene.Crosser@ru.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/iucv/af_iucv.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 435608c..20ab7b2 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -708,6 +708,9 @@ static int iucv_sock_bind(struct socket *sock, struct sockaddr *addr,
 	if (!addr || addr->sa_family != AF_IUCV)
 		return -EINVAL;
 
+	if (addr_len < sizeof(struct sockaddr_iucv))
+		return -EINVAL;
+
 	lock_sock(sk);
 	if (sk->sk_state != IUCV_OPEN) {
 		err = -EBADFD;
-- 
2.1.0


From 68931e770f545953e63fb17c847fd6299a05daa8 Mon Sep 17 00:00:00 2001
From: Jesse Gross <jesse@kernel.org>
Date: Wed, 20 Jan 2016 17:59:49 -0800
Subject: [PATCH 02/47] gro: Make GRO aware of lightweight tunnels.

[ Upstream commit ce87fc6ce3f9f4488546187e3757cf666d9d4a2a ]

GRO is currently not aware of tunnel metadata generated by lightweight
tunnels and stored in the dst. This leads to two possible problems:
 * Incorrectly merging two frames that have different metadata.
 * Leaking of allocated metadata from merged frames.

This avoids those problems by comparing the tunnel information before
merging, similar to how we handle other metadata (such as vlan tags),
and releasing any state when we are done.

Reported-by: John <john.phillips5@hpe.com>
Fixes: 2e15ea39 ("ip_gre: Add support to collect tunnel metadata.")
Signed-off-by: Jesse Gross <jesse@kernel.org>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst_metadata.h | 18 ++++++++++++++++++
 net/core/dev.c             |  7 +++++--
 2 files changed, 23 insertions(+), 2 deletions(-)

diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h
index 6816f0f..30a56ab 100644
--- a/include/net/dst_metadata.h
+++ b/include/net/dst_metadata.h
@@ -44,6 +44,24 @@ static inline bool skb_valid_dst(const struct sk_buff *skb)
 	return dst && !(dst->flags & DST_METADATA);
 }
 
+static inline int skb_metadata_dst_cmp(const struct sk_buff *skb_a,
+				       const struct sk_buff *skb_b)
+{
+	const struct metadata_dst *a, *b;
+
+	if (!(skb_a->_skb_refdst | skb_b->_skb_refdst))
+		return 0;
+
+	a = (const struct metadata_dst *) skb_dst(skb_a);
+	b = (const struct metadata_dst *) skb_dst(skb_b);
+
+	if (!a != !b || a->u.tun_info.options_len != b->u.tun_info.options_len)
+		return 1;
+
+	return memcmp(&a->u.tun_info, &b->u.tun_info,
+		      sizeof(a->u.tun_info) + a->u.tun_info.options_len);
+}
+
 struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags);
 struct metadata_dst __percpu *metadata_dst_alloc_percpu(u8 optslen, gfp_t flags);
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 7f00f24..7dc137f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4145,6 +4145,7 @@ static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb)
 
 		diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev;
 		diffs |= p->vlan_tci ^ skb->vlan_tci;
+		diffs |= skb_metadata_dst_cmp(p, skb);
 		if (maclen == ETH_HLEN)
 			diffs |= compare_ether_header(skb_mac_header(p),
 						      skb_mac_header(skb));
@@ -4342,10 +4343,12 @@ static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
 		break;
 
 	case GRO_MERGED_FREE:
-		if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD)
+		if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) {
+			skb_dst_drop(skb);
 			kmem_cache_free(skbuff_head_cache, skb);
-		else
+		} else {
 			__kfree_skb(skb);
+		}
 		break;
 
 	case GRO_HELD:
-- 
2.1.0


From 16fee63d42a89481c5d435ef51fb7e4d89a3184a Mon Sep 17 00:00:00 2001
From: Manfred Rudigier <Manfred.Rudigier@omicron.at>
Date: Wed, 20 Jan 2016 11:22:28 +0100
Subject: [PATCH 03/47] net: dp83640: Fix tx timestamp overflow handling.

[ Upstream commit 81e8f2e930fe76b9814c71b9d87c30760b5eb705 ]

PHY status frames are not reliable, the PHY may not be able to send them
during heavy receive traffic. This overflow condition is signaled by the
PHY in the next status frame, but the driver did not make use of it.
Instead it always reported wrong tx timestamps to user space after an
overflow happened because it assigned newly received tx timestamps to old
packets in the queue.

This commit fixes this issue by clearing the tx timestamp queue every time
an overflow happens, so that no timestamps are delivered for overflow
packets. This way time stamping will continue correctly after an overflow.

Signed-off-by: Manfred Rudigier <manfred.rudigier@omicron.at>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/dp83640.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index 47b7117..e6cefd0 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -845,6 +845,11 @@ static void decode_rxts(struct dp83640_private *dp83640,
 	struct skb_shared_hwtstamps *shhwtstamps = NULL;
 	struct sk_buff *skb;
 	unsigned long flags;
+	u8 overflow;
+
+	overflow = (phy_rxts->ns_hi >> 14) & 0x3;
+	if (overflow)
+		pr_debug("rx timestamp queue overflow, count %d\n", overflow);
 
 	spin_lock_irqsave(&dp83640->rx_lock, flags);
 
@@ -887,6 +892,7 @@ static void decode_txts(struct dp83640_private *dp83640,
 	struct skb_shared_hwtstamps shhwtstamps;
 	struct sk_buff *skb;
 	u64 ns;
+	u8 overflow;
 
 	/* We must already have the skb that triggered this. */
 
@@ -896,6 +902,17 @@ static void decode_txts(struct dp83640_private *dp83640,
 		pr_debug("have timestamp but tx_queue empty\n");
 		return;
 	}
+
+	overflow = (phy_txts->ns_hi >> 14) & 0x3;
+	if (overflow) {
+		pr_debug("tx timestamp queue overflow, count %d\n", overflow);
+		while (skb) {
+			skb_complete_tx_timestamp(skb, NULL);
+			skb = skb_dequeue(&dp83640->tx_queue);
+		}
+		return;
+	}
+
 	ns = phy2txts(phy_txts);
 	memset(&shhwtstamps, 0, sizeof(shhwtstamps));
 	shhwtstamps.hwtstamp = ns_to_ktime(ns);
-- 
2.1.0


From e7b24525edb7de3eedd2df4e5b7e40d0d04dc971 Mon Sep 17 00:00:00 2001
From: Jesse Gross <jesse@kernel.org>
Date: Wed, 20 Jan 2016 16:22:47 -0800
Subject: [PATCH 04/47] tunnels: Allow IPv6 UDP checksums to be correctly
 controlled.

[ Upstream commit 35e2d1152b22eae99c961affbe85374bef05a775 ]

When configuring checksums on UDP tunnels, the flags are different
for IPv4 vs. IPv6 (and reversed). However, when lightweight tunnels
are enabled the flags used are always the IPv4 versions, which are
ignored in the IPv6 code paths. This uses the correct IPv6 flags, so
checksums can be controlled appropriately.

Fixes: a725e514 ("vxlan: metadata based tunneling for IPv6")
Fixes: abe492b4 ("geneve: UDP checksum configuration via netlink")
Signed-off-by: Jesse Gross <jesse@kernel.org>
Acked-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 23 ++++++++++++++++-------
 1 file changed, 16 insertions(+), 7 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 405a7b6..e0fcda4 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1984,11 +1984,6 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 				     vxlan->cfg.port_max, true);
 
 	if (info) {
-		if (info->key.tun_flags & TUNNEL_CSUM)
-			flags |= VXLAN_F_UDP_CSUM;
-		else
-			flags &= ~VXLAN_F_UDP_CSUM;
-
 		ttl = info->key.ttl;
 		tos = info->key.tos;
 
@@ -2003,8 +1998,15 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 			goto drop;
 		sk = vxlan->vn4_sock->sock->sk;
 
-		if (info && (info->key.tun_flags & TUNNEL_DONT_FRAGMENT))
-			df = htons(IP_DF);
+		if (info) {
+			if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT)
+				df = htons(IP_DF);
+
+			if (info->key.tun_flags & TUNNEL_CSUM)
+				flags |= VXLAN_F_UDP_CSUM;
+			else
+				flags &= ~VXLAN_F_UDP_CSUM;
+		}
 
 		memset(&fl4, 0, sizeof(fl4));
 		fl4.flowi4_oif = rdst ? rdst->remote_ifindex : 0;
@@ -2102,6 +2104,13 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 			return;
 		}
 
+		if (info) {
+			if (info->key.tun_flags & TUNNEL_CSUM)
+				flags &= ~VXLAN_F_UDP_ZERO_CSUM6_TX;
+			else
+				flags |= VXLAN_F_UDP_ZERO_CSUM6_TX;
+		}
+
 		ttl = ttl ? : ip6_dst_hoplimit(ndst);
 		err = vxlan6_xmit_skb(ndst, sk, skb, dev, &saddr, &dst->sin6.sin6_addr,
 				      0, ttl, src_port, dst_port, htonl(vni << 8), md,
-- 
2.1.0


From 30b7b7dd18f55b33cf35027ce67975ddc2d7fd02 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 17 Feb 2016 19:30:01 +0100
Subject: [PATCH 05/47] lwt: fix rx checksum setting for lwt devices tunneling
 over ipv6

[ Upstream commit c868ee7063bdb53f3ef9eac7bcec84960980b471 ]

the commit 35e2d1152b22 ("tunnels: Allow IPv6 UDP checksums to be
correctly controlled.") changed the default xmit checksum setting
for lwt vxlan/geneve ipv6 tunnels, so that now the checksum is not
set into external UDP header.
This commit changes the rx checksum setting for both lwt vxlan/geneve
devices created by openvswitch accordingly, so that lwt over ipv6
tunnel pairs are again able to communicate with default values.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Jiri Benc <jbenc@redhat.com>
Acked-by: Jesse Gross <jesse@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/vport-vxlan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index 1605691..d933cb8 100644
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -90,7 +90,7 @@ static struct vport *vxlan_tnl_create(const struct vport_parms *parms)
 	int err;
 	struct vxlan_config conf = {
 		.no_share = true,
-		.flags = VXLAN_F_COLLECT_METADATA,
+		.flags = VXLAN_F_COLLECT_METADATA | VXLAN_F_UDP_ZERO_CSUM6_RX,
 	};
 
 	if (!options) {
-- 
2.1.0


From 5f7ba02e2e587ae13897a45b7c8fcfe3a9efd627 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 21 Jan 2016 08:02:54 -0800
Subject: [PATCH 06/47] tcp: fix NULL deref in tcp_v4_send_ack()

[ Upstream commit e62a123b8ef7c5dc4db2c16383d506860ad21b47 ]

Neal reported crashes with this stack trace :

 RIP: 0010:[<ffffffff8c57231b>] tcp_v4_send_ack+0x41/0x20f
...
 CR2: 0000000000000018 CR3: 000000044005c000 CR4: 00000000001427e0
...
  [<ffffffff8c57258e>] tcp_v4_reqsk_send_ack+0xa5/0xb4
  [<ffffffff8c1a7caa>] tcp_check_req+0x2ea/0x3e0
  [<ffffffff8c19e420>] tcp_rcv_state_process+0x850/0x2500
  [<ffffffff8c1a6d21>] tcp_v4_do_rcv+0x141/0x330
  [<ffffffff8c56cdb2>] sk_backlog_rcv+0x21/0x30
  [<ffffffff8c098bbd>] tcp_recvmsg+0x75d/0xf90
  [<ffffffff8c0a8700>] inet_recvmsg+0x80/0xa0
  [<ffffffff8c17623e>] sock_aio_read+0xee/0x110
  [<ffffffff8c066fcf>] do_sync_read+0x6f/0xa0
  [<ffffffff8c0673a1>] SyS_read+0x1e1/0x290
  [<ffffffff8c5ca262>] system_call_fastpath+0x16/0x1b

The problem here is the skb we provide to tcp_v4_send_ack() had to
be parked in the backlog of a new TCP fastopen child because this child
was owned by the user at the time an out of window packet arrived.

Before queuing a packet, TCP has to set skb->dev to NULL as the device
could disappear before packet is removed from the queue.

Fix this issue by using the net pointer provided by the socket (being a
timewait or a request socket).

IPv6 is immune to the bug : tcp_v6_send_response() already gets the net
pointer from the socket if provided.

Fixes: 168a8f58059a ("tcp: TCP Fast Open Server - main code path")
Reported-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jerry Chu <hkchu@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index d8841a2..4627717 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -705,7 +705,8 @@ release_sk1:
    outside socket context is ugly, certainly. What can I do?
  */
 
-static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
+static void tcp_v4_send_ack(struct net *net,
+			    struct sk_buff *skb, u32 seq, u32 ack,
 			    u32 win, u32 tsval, u32 tsecr, int oif,
 			    struct tcp_md5sig_key *key,
 			    int reply_flags, u8 tos)
@@ -720,7 +721,6 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
 			];
 	} rep;
 	struct ip_reply_arg arg;
-	struct net *net = dev_net(skb_dst(skb)->dev);
 
 	memset(&rep.th, 0, sizeof(struct tcphdr));
 	memset(&arg, 0, sizeof(arg));
@@ -782,7 +782,8 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
 	struct inet_timewait_sock *tw = inet_twsk(sk);
 	struct tcp_timewait_sock *tcptw = tcp_twsk(sk);
 
-	tcp_v4_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
+	tcp_v4_send_ack(sock_net(sk), skb,
+			tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
 			tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
 			tcp_time_stamp + tcptw->tw_ts_offset,
 			tcptw->tw_ts_recent,
@@ -801,8 +802,10 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
 	/* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV
 	 * sk->sk_state == TCP_SYN_RECV -> for Fast Open.
 	 */
-	tcp_v4_send_ack(skb, (sk->sk_state == TCP_LISTEN) ?
-			tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt,
+	u32 seq = (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 :
+					     tcp_sk(sk)->snd_nxt;
+
+	tcp_v4_send_ack(sock_net(sk), skb, seq,
 			tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd,
 			tcp_time_stamp,
 			req->ts_recent,
-- 
2.1.0


From 7ff516ac42dc47146116c5698685d342a2c293cc Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 24 Jan 2016 13:53:50 -0800
Subject: [PATCH 07/47] af_unix: fix struct pid memory leak

[ Upstream commit fa0dc04df259ba2df3ce1920e9690c7842f8fa4b ]

Dmitry reported a struct pid leak detected by a syzkaller program.

Bug happens in unix_stream_recvmsg() when we break the loop when a
signal is pending, without properly releasing scm.

Fixes: b3ca9b02b007 ("net: fix multithreaded signal handling in unix recv routines")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Rainer Weikusat <rweikusat@mobileactivedefense.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index e3f85bc..775855e 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2332,6 +2332,7 @@ again:
 
 			if (signal_pending(current)) {
 				err = sock_intr_errno(timeo);
+				scm_destroy(&scm);
 				goto out;
 			}
 
-- 
2.1.0


From 494c9dd2cd0ee53d2d914219d91a062b3c355da3 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Fri, 22 Jan 2016 01:39:43 +0100
Subject: [PATCH 08/47] pptp: fix illegal memory access caused by multiple
 bind()s

[ Upstream commit 9a368aff9cb370298fa02feeffa861f2db497c18 ]

Several times already this has been reported as kasan reports caused by
syzkaller and trinity and people always looked at RCU races, but it is
much more simple. :)

In case we bind a pptp socket multiple times, we simply add it to
the callid_sock list but don't remove the old binding. Thus the old
socket stays in the bucket with unused call_id indexes and doesn't get
cleaned up. This causes various forms of kasan reports which were hard
to pinpoint.

Simply don't allow multiple binds and correct error handling in
pptp_bind. Also keep sk_state bits in place in pptp_connect.

Fixes: 00959ade36acad ("PPTP: PPP over IPv4 (Point-to-Point Tunneling Protocol)")
Cc: Dmitry Kozlov <xeb@mail.ru>
Cc: Sasha Levin <sasha.levin@oracle.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Dave Jones <davej@codemonkey.org.uk>
Reported-by: Dave Jones <davej@codemonkey.org.uk>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pptp.c | 34 ++++++++++++++++++++++++----------
 1 file changed, 24 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index 597c53e..f7e8c79 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -129,24 +129,27 @@ static int lookup_chan_dst(u16 call_id, __be32 d_addr)
 	return i < MAX_CALLID;
 }
 
-static int add_chan(struct pppox_sock *sock)
+static int add_chan(struct pppox_sock *sock,
+		    struct pptp_addr *sa)
 {
 	static int call_id;
 
 	spin_lock(&chan_lock);
-	if (!sock->proto.pptp.src_addr.call_id)	{
+	if (!sa->call_id)	{
 		call_id = find_next_zero_bit(callid_bitmap, MAX_CALLID, call_id + 1);
 		if (call_id == MAX_CALLID) {
 			call_id = find_next_zero_bit(callid_bitmap, MAX_CALLID, 1);
 			if (call_id == MAX_CALLID)
 				goto out_err;
 		}
-		sock->proto.pptp.src_addr.call_id = call_id;
-	} else if (test_bit(sock->proto.pptp.src_addr.call_id, callid_bitmap))
+		sa->call_id = call_id;
+	} else if (test_bit(sa->call_id, callid_bitmap)) {
 		goto out_err;
+	}
 
-	set_bit(sock->proto.pptp.src_addr.call_id, callid_bitmap);
-	rcu_assign_pointer(callid_sock[sock->proto.pptp.src_addr.call_id], sock);
+	sock->proto.pptp.src_addr = *sa;
+	set_bit(sa->call_id, callid_bitmap);
+	rcu_assign_pointer(callid_sock[sa->call_id], sock);
 	spin_unlock(&chan_lock);
 
 	return 0;
@@ -416,7 +419,6 @@ static int pptp_bind(struct socket *sock, struct sockaddr *uservaddr,
 	struct sock *sk = sock->sk;
 	struct sockaddr_pppox *sp = (struct sockaddr_pppox *) uservaddr;
 	struct pppox_sock *po = pppox_sk(sk);
-	struct pptp_opt *opt = &po->proto.pptp;
 	int error = 0;
 
 	if (sockaddr_len < sizeof(struct sockaddr_pppox))
@@ -424,10 +426,22 @@ static int pptp_bind(struct socket *sock, struct sockaddr *uservaddr,
 
 	lock_sock(sk);
 
-	opt->src_addr = sp->sa_addr.pptp;
-	if (add_chan(po))
+	if (sk->sk_state & PPPOX_DEAD) {
+		error = -EALREADY;
+		goto out;
+	}
+
+	if (sk->sk_state & PPPOX_BOUND) {
 		error = -EBUSY;
+		goto out;
+	}
+
+	if (add_chan(po, &sp->sa_addr.pptp))
+		error = -EBUSY;
+	else
+		sk->sk_state |= PPPOX_BOUND;
 
+out:
 	release_sock(sk);
 	return error;
 }
@@ -498,7 +512,7 @@ static int pptp_connect(struct socket *sock, struct sockaddr *uservaddr,
 	}
 
 	opt->dst_addr = sp->sa_addr.pptp;
-	sk->sk_state = PPPOX_CONNECTED;
+	sk->sk_state |= PPPOX_CONNECTED;
 
  end:
 	release_sock(sk);
-- 
2.1.0


From 1bf3c1dcb5a1cabf2d76c7e6e99f46d396dd5f53 Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Fri, 22 Jan 2016 18:29:49 -0200
Subject: [PATCH 09/47] sctp: allow setting SCTP_SACK_IMMEDIATELY by the
 application

[ Upstream commit 27f7ed2b11d42ab6d796e96533c2076ec220affc ]

This patch extends commit b93d6471748d ("sctp: implement the sender side
for SACK-IMMEDIATELY extension") as it didn't white list
SCTP_SACK_IMMEDIATELY on sctp_msghdr_parse(), causing it to be
understood as an invalid flag and returning -EINVAL to the application.

Note that the actual handling of the flag is already there in
sctp_datamsg_from_user().

https://tools.ietf.org/html/rfc7053#section-7

Fixes: b93d6471748d ("sctp: implement the sender side for SACK-IMMEDIATELY extension")
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index ef1d90f..06a9cfb 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -6640,6 +6640,7 @@ static int sctp_msghdr_parse(const struct msghdr *msg, sctp_cmsgs_t *cmsgs)
 
 			if (cmsgs->srinfo->sinfo_flags &
 			    ~(SCTP_UNORDERED | SCTP_ADDR_OVER |
+			      SCTP_SACK_IMMEDIATELY |
 			      SCTP_ABORT | SCTP_EOF))
 				return -EINVAL;
 			break;
@@ -6663,6 +6664,7 @@ static int sctp_msghdr_parse(const struct msghdr *msg, sctp_cmsgs_t *cmsgs)
 
 			if (cmsgs->sinfo->snd_flags &
 			    ~(SCTP_UNORDERED | SCTP_ADDR_OVER |
+			      SCTP_SACK_IMMEDIATELY |
 			      SCTP_ABORT | SCTP_EOF))
 				return -EINVAL;
 			break;
-- 
2.1.0


From 592d9e5b6987a271ebb95f53eaac9e53c3f4969f Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Sun, 24 Jan 2016 09:22:05 +0000
Subject: [PATCH 10/47] net: dsa: fix mv88e6xxx switches

[ Upstream commit db0e51afa481088e6396f11e02018d64113a6578 ]

Since commit 76e398a62712 ("net: dsa: use switchdev obj for VLAN add/del
ops"), the Marvell 88E6xxx switch has been unable to pass traffic
between ports - any received traffic is discarded by the switch.
Taking a port out of bridge mode and configuring a vlan on it also the
port to start passing traffic.

With the debugfs files re-instated to allow debug of this issue by
comparing the register settings between the working and non-working
case, the reason becomes clear:

     GLOBAL GLOBAL2 SERDES   0    1    2    3    4    5    6
- 7:  1111    707f    2001     2    2    2    2    2    0    2
+ 7:  1111    707f    2001     1    1    1    1    1    0    1

Register 7 for the ports is the default vlan tag register, and in the
non-working setup, it has been set to 2, despite vlan 2 not being
configured.  This causes the switch to drop all packets coming in to
these ports.  The working setup has the default vlan tag register set
to 1, which is the default vlan when none is configured.

Inspection of the code reveals why.  The code prior to this commit
was:

-		for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) {
...
-			if (!err && vlan->flags & BRIDGE_VLAN_INFO_PVID)
-				err = ds->drv->port_pvid_set(ds, p->port, vid);

but the new code is:

+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) {
...
+	}
...
+	if (pvid)
+		err = _mv88e6xxx_port_pvid_set(ds, port, vid);

This causes the new code to always set the default vlan to one higher
than the old code.

Fix this.

Fixes: 76e398a62712 ("net: dsa: use switchdev obj for VLAN add/del ops")
Cc: <stable@vger.kernel.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c
index b06dba0..2dea39b 100644
--- a/drivers/net/dsa/mv88e6xxx.c
+++ b/drivers/net/dsa/mv88e6xxx.c
@@ -1519,7 +1519,7 @@ int mv88e6xxx_port_vlan_add(struct dsa_switch *ds, int port,
 
 	/* no PVID with ranges, otherwise it's a bug */
 	if (pvid)
-		err = _mv88e6xxx_port_pvid_set(ds, port, vid);
+		err = _mv88e6xxx_port_pvid_set(ds, port, vlan->vid_end);
 unlock:
 	mutex_unlock(&ps->smi_mutex);
 
-- 
2.1.0


From d4ad57cc78bcb85d96445d00083c9f8f1f61d29d Mon Sep 17 00:00:00 2001
From: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
Date: Wed, 27 Jan 2016 11:35:59 +0100
Subject: [PATCH 11/47] tipc: fix connection abort during subscription cancel

[ Upstream commit 4d5cfcba2f6ec494d8810b9e3c0a7b06255c8067 ]

In 'commit 7fe8097cef5f ("tipc: fix nullpointer bug when subscribing
to events")', we terminate the connection if the subscription
creation fails.
In the same commit, the subscription creation result was based on
the value of the subscription pointer (set in the function) instead
of the return code.

Unfortunately, the same function tipc_subscrp_create() handles
subscription cancel request. For a subscription cancellation request,
the subscription pointer cannot be set. Thus if a subscriber has
several subscriptions and cancels any of them, the connection is
terminated.

In this commit, we terminate the connection based on the return value
of tipc_subscrp_create().
Fixes: commit 7fe8097cef5f ("tipc: fix nullpointer bug when subscribing to events")

Reviewed-by:  Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/subscr.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c
index 350cca3..69ee2ee 100644
--- a/net/tipc/subscr.c
+++ b/net/tipc/subscr.c
@@ -289,15 +289,14 @@ static void tipc_subscrb_rcv_cb(struct net *net, int conid,
 				struct sockaddr_tipc *addr, void *usr_data,
 				void *buf, size_t len)
 {
-	struct tipc_subscriber *subscriber = usr_data;
+	struct tipc_subscriber *subscrb = usr_data;
 	struct tipc_subscription *sub = NULL;
 	struct tipc_net *tn = net_generic(net, tipc_net_id);
 
-	tipc_subscrp_create(net, (struct tipc_subscr *)buf, subscriber, &sub);
-	if (sub)
-		tipc_nametbl_subscribe(sub);
-	else
-		tipc_conn_terminate(tn->topsrv, subscriber->conid);
+	if (tipc_subscrp_create(net, (struct tipc_subscr *)buf, subscrb, &sub))
+		return tipc_conn_terminate(tn->topsrv, subscrb->conid);
+
+	tipc_nametbl_subscribe(sub);
 }
 
 /* Handle one request to establish a new subscriber */
-- 
2.1.0


From e867177d0385fd90f5daba0f6b459cf4a3f8d300 Mon Sep 17 00:00:00 2001
From: Joe Stringer <joe@ovn.org>
Date: Fri, 22 Jan 2016 15:49:12 -0800
Subject: [PATCH 12/47] inet: frag: Always orphan skbs inside ip_defrag()

[ Upstream commit 8282f27449bf15548cb82c77b6e04ee0ab827bdc ]

Later parts of the stack (including fragmentation) expect that there is
never a socket attached to frag in a frag_list, however this invariant
was not enforced on all defrag paths. This could lead to the
BUG_ON(skb->sk) during ip_do_fragment(), as per the call stack at the
end of this commit message.

While the call could be added to openvswitch to fix this particular
error, the head and tail of the frags list are already orphaned
indirectly inside ip_defrag(), so it seems like the remaining fragments
should all be orphaned in all circumstances.

kernel BUG at net/ipv4/ip_output.c:586!
[...]
Call Trace:
 <IRQ>
 [<ffffffffa0205270>] ? do_output.isra.29+0x1b0/0x1b0 [openvswitch]
 [<ffffffffa02167a7>] ovs_fragment+0xcc/0x214 [openvswitch]
 [<ffffffff81667830>] ? dst_discard_out+0x20/0x20
 [<ffffffff81667810>] ? dst_ifdown+0x80/0x80
 [<ffffffffa0212072>] ? find_bucket.isra.2+0x62/0x70 [openvswitch]
 [<ffffffff810e0ba5>] ? mod_timer_pending+0x65/0x210
 [<ffffffff810b732b>] ? __lock_acquire+0x3db/0x1b90
 [<ffffffffa03205a2>] ? nf_conntrack_in+0x252/0x500 [nf_conntrack]
 [<ffffffff810b63c4>] ? __lock_is_held+0x54/0x70
 [<ffffffffa02051a3>] do_output.isra.29+0xe3/0x1b0 [openvswitch]
 [<ffffffffa0206411>] do_execute_actions+0xe11/0x11f0 [openvswitch]
 [<ffffffff810b63c4>] ? __lock_is_held+0x54/0x70
 [<ffffffffa0206822>] ovs_execute_actions+0x32/0xd0 [openvswitch]
 [<ffffffffa020b505>] ovs_dp_process_packet+0x85/0x140 [openvswitch]
 [<ffffffff810b63c4>] ? __lock_is_held+0x54/0x70
 [<ffffffffa02068a2>] ovs_execute_actions+0xb2/0xd0 [openvswitch]
 [<ffffffffa020b505>] ovs_dp_process_packet+0x85/0x140 [openvswitch]
 [<ffffffffa0215019>] ? ovs_ct_get_labels+0x49/0x80 [openvswitch]
 [<ffffffffa0213a1d>] ovs_vport_receive+0x5d/0xa0 [openvswitch]
 [<ffffffff810b732b>] ? __lock_acquire+0x3db/0x1b90
 [<ffffffff810b732b>] ? __lock_acquire+0x3db/0x1b90
 [<ffffffff810b732b>] ? __lock_acquire+0x3db/0x1b90
 [<ffffffffa0214895>] ? internal_dev_xmit+0x5/0x140 [openvswitch]
 [<ffffffffa02148fc>] internal_dev_xmit+0x6c/0x140 [openvswitch]
 [<ffffffffa0214895>] ? internal_dev_xmit+0x5/0x140 [openvswitch]
 [<ffffffff81660299>] dev_hard_start_xmit+0x2b9/0x5e0
 [<ffffffff8165fc21>] ? netif_skb_features+0xd1/0x1f0
 [<ffffffff81660f20>] __dev_queue_xmit+0x800/0x930
 [<ffffffff81660770>] ? __dev_queue_xmit+0x50/0x930
 [<ffffffff810b53f1>] ? mark_held_locks+0x71/0x90
 [<ffffffff81669876>] ? neigh_resolve_output+0x106/0x220
 [<ffffffff81661060>] dev_queue_xmit+0x10/0x20
 [<ffffffff816698e8>] neigh_resolve_output+0x178/0x220
 [<ffffffff816a8e6f>] ? ip_finish_output2+0x1ff/0x590
 [<ffffffff816a8e6f>] ip_finish_output2+0x1ff/0x590
 [<ffffffff816a8cee>] ? ip_finish_output2+0x7e/0x590
 [<ffffffff816a9a31>] ip_do_fragment+0x831/0x8a0
 [<ffffffff816a8c70>] ? ip_copy_metadata+0x1b0/0x1b0
 [<ffffffff816a9ae3>] ip_fragment.constprop.49+0x43/0x80
 [<ffffffff816a9c9c>] ip_finish_output+0x17c/0x340
 [<ffffffff8169a6f4>] ? nf_hook_slow+0xe4/0x190
 [<ffffffff816ab4c0>] ip_output+0x70/0x110
 [<ffffffff816a9b20>] ? ip_fragment.constprop.49+0x80/0x80
 [<ffffffff816aa9f9>] ip_local_out+0x39/0x70
 [<ffffffff816abf89>] ip_send_skb+0x19/0x40
 [<ffffffff816abfe3>] ip_push_pending_frames+0x33/0x40
 [<ffffffff816df21a>] icmp_push_reply+0xea/0x120
 [<ffffffff816df93d>] icmp_reply.constprop.23+0x1ed/0x230
 [<ffffffff816df9ce>] icmp_echo.part.21+0x4e/0x50
 [<ffffffff810b63c4>] ? __lock_is_held+0x54/0x70
 [<ffffffff810d5f9e>] ? rcu_read_lock_held+0x5e/0x70
 [<ffffffff816dfa06>] icmp_echo+0x36/0x70
 [<ffffffff816e0d11>] icmp_rcv+0x271/0x450
 [<ffffffff816a4ca7>] ip_local_deliver_finish+0x127/0x3a0
 [<ffffffff816a4bc1>] ? ip_local_deliver_finish+0x41/0x3a0
 [<ffffffff816a5160>] ip_local_deliver+0x60/0xd0
 [<ffffffff816a4b80>] ? ip_rcv_finish+0x560/0x560
 [<ffffffff816a46fd>] ip_rcv_finish+0xdd/0x560
 [<ffffffff816a5453>] ip_rcv+0x283/0x3e0
 [<ffffffff810b6302>] ? match_held_lock+0x192/0x200
 [<ffffffff816a4620>] ? inet_del_offload+0x40/0x40
 [<ffffffff8165d062>] __netif_receive_skb_core+0x392/0xae0
 [<ffffffff8165e68e>] ? process_backlog+0x8e/0x230
 [<ffffffff810b53f1>] ? mark_held_locks+0x71/0x90
 [<ffffffff8165d7c8>] __netif_receive_skb+0x18/0x60
 [<ffffffff8165e678>] process_backlog+0x78/0x230
 [<ffffffff8165e6dd>] ? process_backlog+0xdd/0x230
 [<ffffffff8165e355>] net_rx_action+0x155/0x400
 [<ffffffff8106b48c>] __do_softirq+0xcc/0x420
 [<ffffffff816a8e87>] ? ip_finish_output2+0x217/0x590
 [<ffffffff8178e78c>] do_softirq_own_stack+0x1c/0x30
 <EOI>
 [<ffffffff8106b88e>] do_softirq+0x4e/0x60
 [<ffffffff8106b948>] __local_bh_enable_ip+0xa8/0xb0
 [<ffffffff816a8eb0>] ip_finish_output2+0x240/0x590
 [<ffffffff816a9a31>] ? ip_do_fragment+0x831/0x8a0
 [<ffffffff816a9a31>] ip_do_fragment+0x831/0x8a0
 [<ffffffff816a8c70>] ? ip_copy_metadata+0x1b0/0x1b0
 [<ffffffff816a9ae3>] ip_fragment.constprop.49+0x43/0x80
 [<ffffffff816a9c9c>] ip_finish_output+0x17c/0x340
 [<ffffffff8169a6f4>] ? nf_hook_slow+0xe4/0x190
 [<ffffffff816ab4c0>] ip_output+0x70/0x110
 [<ffffffff816a9b20>] ? ip_fragment.constprop.49+0x80/0x80
 [<ffffffff816aa9f9>] ip_local_out+0x39/0x70
 [<ffffffff816abf89>] ip_send_skb+0x19/0x40
 [<ffffffff816abfe3>] ip_push_pending_frames+0x33/0x40
 [<ffffffff816d55d3>] raw_sendmsg+0x7d3/0xc30
 [<ffffffff810b732b>] ? __lock_acquire+0x3db/0x1b90
 [<ffffffff816e7557>] ? inet_sendmsg+0xc7/0x1d0
 [<ffffffff810b63c4>] ? __lock_is_held+0x54/0x70
 [<ffffffff816e759a>] inet_sendmsg+0x10a/0x1d0
 [<ffffffff816e7495>] ? inet_sendmsg+0x5/0x1d0
 [<ffffffff8163e398>] sock_sendmsg+0x38/0x50
 [<ffffffff8163ec5f>] ___sys_sendmsg+0x25f/0x270
 [<ffffffff811aadad>] ? handle_mm_fault+0x8dd/0x1320
 [<ffffffff8178c147>] ? _raw_spin_unlock+0x27/0x40
 [<ffffffff810529b2>] ? __do_page_fault+0x1e2/0x460
 [<ffffffff81204886>] ? __fget_light+0x66/0x90
 [<ffffffff8163f8e2>] __sys_sendmsg+0x42/0x80
 [<ffffffff8163f932>] SyS_sendmsg+0x12/0x20
 [<ffffffff8178cb17>] entry_SYSCALL_64_fastpath+0x12/0x6f
Code: 00 00 44 89 e0 e9 7c fb ff ff 4c 89 ff e8 e7 e7 ff ff 41 8b 9d 80 00 00 00 2b 5d d4 89 d8 c1 f8 03 0f b7 c0 e9 33 ff ff f
 66 66 66 2e 0f 1f 84 00 00 00 00 00 66 66 66 66 90 55 48
RIP  [<ffffffff816a9a92>] ip_do_fragment+0x892/0x8a0
 RSP <ffff88006d603170>

Fixes: 7f8a436eaa2c ("openvswitch: Add conntrack action")
Signed-off-by: Joe Stringer <joe@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_fragment.c              | 1 +
 net/ipv4/netfilter/nf_defrag_ipv4.c | 2 --
 2 files changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 1fe55ae..b8a0607d 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -661,6 +661,7 @@ int ip_defrag(struct net *net, struct sk_buff *skb, u32 user)
 	struct ipq *qp;
 
 	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMREQDS);
+	skb_orphan(skb);
 
 	/* Lookup (or create) queue header */
 	qp = ip_find(net, ip_hdr(skb), user, vif);
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index 6fb869f6..a04dee5 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -27,8 +27,6 @@ static int nf_ct_ipv4_gather_frags(struct net *net, struct sk_buff *skb,
 {
 	int err;
 
-	skb_orphan(skb);
-
 	local_bh_disable();
 	err = ip_defrag(net, skb, user);
 	local_bh_enable();
-- 
2.1.0


From c416cebf49e48078c5f65855b703373df486e2c7 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 27 Jan 2016 15:16:43 +0100
Subject: [PATCH 13/47] switchdev: Require RTNL mutex to be held when sending
 FDB notifications

[ Upstream commit 4f2c6ae5c64c353fb1b0425e4747e5603feadba1 ]

When switchdev drivers process FDB notifications from the underlying
device they resolve the netdev to which the entry points to and notify
the bridge using the switchdev notifier.

However, since the RTNL mutex is not held there is nothing preventing
the netdev from disappearing in the middle, which will cause
br_switchdev_event() to dereference a non-existing netdev.

Make switchdev drivers hold the lock at the beginning of the
notification processing session and release it once it ends, after
notifying the bridge.

Also, remove switchdev_mutex and fdb_lock, as they are no longer needed
when RTNL mutex is held.

Fixes: 03bf0c281234 ("switchdev: introduce switchdev notifier")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c |  3 +++
 drivers/net/ethernet/rocker/rocker.c                     |  2 ++
 net/bridge/br.c                                          |  3 +--
 net/switchdev/switchdev.c                                | 15 ++++++++-------
 4 files changed, 14 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 617fb22..7dbeafa 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -45,6 +45,7 @@
 #include <linux/if_bridge.h>
 #include <linux/workqueue.h>
 #include <linux/jiffies.h>
+#include <linux/rtnetlink.h>
 #include <net/switchdev.h>
 
 #include "spectrum.h"
@@ -812,6 +813,7 @@ static void mlxsw_sp_fdb_notify_work(struct work_struct *work)
 
 	mlxsw_sp = container_of(work, struct mlxsw_sp, fdb_notify.dw.work);
 
+	rtnl_lock();
 	do {
 		mlxsw_reg_sfn_pack(sfn_pl);
 		err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(sfn), sfn_pl);
@@ -824,6 +826,7 @@ static void mlxsw_sp_fdb_notify_work(struct work_struct *work)
 			mlxsw_sp_fdb_notify_rec_process(mlxsw_sp, sfn_pl, i);
 
 	} while (num_rec);
+	rtnl_unlock();
 
 	kfree(sfn_pl);
 	mlxsw_sp_fdb_notify_work_schedule(mlxsw_sp);
diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c
index e9f2349..52ec3d6 100644
--- a/drivers/net/ethernet/rocker/rocker.c
+++ b/drivers/net/ethernet/rocker/rocker.c
@@ -3531,12 +3531,14 @@ static void rocker_port_fdb_learn_work(struct work_struct *work)
 	info.addr = lw->addr;
 	info.vid = lw->vid;
 
+	rtnl_lock();
 	if (learned && removing)
 		call_switchdev_notifiers(SWITCHDEV_FDB_DEL,
 					 lw->rocker_port->dev, &info.info);
 	else if (learned && !removing)
 		call_switchdev_notifiers(SWITCHDEV_FDB_ADD,
 					 lw->rocker_port->dev, &info.info);
+	rtnl_unlock();
 
 	rocker_port_kfree(lw->trans, work);
 }
diff --git a/net/bridge/br.c b/net/bridge/br.c
index a1abe49..3addc05 100644
--- a/net/bridge/br.c
+++ b/net/bridge/br.c
@@ -121,6 +121,7 @@ static struct notifier_block br_device_notifier = {
 	.notifier_call = br_device_event
 };
 
+/* called with RTNL */
 static int br_switchdev_event(struct notifier_block *unused,
 			      unsigned long event, void *ptr)
 {
@@ -130,7 +131,6 @@ static int br_switchdev_event(struct notifier_block *unused,
 	struct switchdev_notifier_fdb_info *fdb_info;
 	int err = NOTIFY_DONE;
 
-	rtnl_lock();
 	p = br_port_get_rtnl(dev);
 	if (!p)
 		goto out;
@@ -155,7 +155,6 @@ static int br_switchdev_event(struct notifier_block *unused,
 	}
 
 out:
-	rtnl_unlock();
 	return err;
 }
 
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index f34e535..d5d7132 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -20,6 +20,7 @@
 #include <linux/list.h>
 #include <linux/workqueue.h>
 #include <linux/if_vlan.h>
+#include <linux/rtnetlink.h>
 #include <net/ip_fib.h>
 #include <net/switchdev.h>
 
@@ -565,7 +566,6 @@ int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj,
 }
 EXPORT_SYMBOL_GPL(switchdev_port_obj_dump);
 
-static DEFINE_MUTEX(switchdev_mutex);
 static RAW_NOTIFIER_HEAD(switchdev_notif_chain);
 
 /**
@@ -580,9 +580,9 @@ int register_switchdev_notifier(struct notifier_block *nb)
 {
 	int err;
 
-	mutex_lock(&switchdev_mutex);
+	rtnl_lock();
 	err = raw_notifier_chain_register(&switchdev_notif_chain, nb);
-	mutex_unlock(&switchdev_mutex);
+	rtnl_unlock();
 	return err;
 }
 EXPORT_SYMBOL_GPL(register_switchdev_notifier);
@@ -598,9 +598,9 @@ int unregister_switchdev_notifier(struct notifier_block *nb)
 {
 	int err;
 
-	mutex_lock(&switchdev_mutex);
+	rtnl_lock();
 	err = raw_notifier_chain_unregister(&switchdev_notif_chain, nb);
-	mutex_unlock(&switchdev_mutex);
+	rtnl_unlock();
 	return err;
 }
 EXPORT_SYMBOL_GPL(unregister_switchdev_notifier);
@@ -614,16 +614,17 @@ EXPORT_SYMBOL_GPL(unregister_switchdev_notifier);
  *	Call all network notifier blocks. This should be called by driver
  *	when it needs to propagate hardware event.
  *	Return values are same as for atomic_notifier_call_chain().
+ *	rtnl_lock must be held.
  */
 int call_switchdev_notifiers(unsigned long val, struct net_device *dev,
 			     struct switchdev_notifier_info *info)
 {
 	int err;
 
+	ASSERT_RTNL();
+
 	info->dev = dev;
-	mutex_lock(&switchdev_mutex);
 	err = raw_notifier_call_chain(&switchdev_notif_chain, val, info);
-	mutex_unlock(&switchdev_mutex);
 	return err;
 }
 EXPORT_SYMBOL_GPL(call_switchdev_notifiers);
-- 
2.1.0


From 9f1b1e47c8aacb370028b6f4ef7a2bc95e081b31 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 27 Jan 2016 10:52:43 -0800
Subject: [PATCH 14/47] tcp: beware of alignments in tcp_get_info()

[ Upstream commit ff5d749772018602c47509bdc0093ff72acd82ec ]

With some combinations of user provided flags in netlink command,
it is possible to call tcp_get_info() with a buffer that is not 8-bytes
aligned.

It does matter on some arches, so we need to use put_unaligned() to
store the u64 fields.

Current iproute2 package does not trigger this particular issue.

Fixes: 0df48c26d841 ("tcp: add tcpi_bytes_acked to tcp_info")
Fixes: 977cb0ecf82e ("tcp: add pacing_rate information into tcp_info")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index c82cca1..9c1241e 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -279,6 +279,7 @@
 
 #include <asm/uaccess.h>
 #include <asm/ioctls.h>
+#include <asm/unaligned.h>
 #include <net/busy_poll.h>
 
 int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;
@@ -2637,6 +2638,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	u32 now = tcp_time_stamp;
 	unsigned int start;
+	u64 rate64;
 	u32 rate;
 
 	memset(info, 0, sizeof(*info));
@@ -2702,15 +2704,17 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	info->tcpi_total_retrans = tp->total_retrans;
 
 	rate = READ_ONCE(sk->sk_pacing_rate);
-	info->tcpi_pacing_rate = rate != ~0U ? rate : ~0ULL;
+	rate64 = rate != ~0U ? rate : ~0ULL;
+	put_unaligned(rate64, &info->tcpi_pacing_rate);
 
 	rate = READ_ONCE(sk->sk_max_pacing_rate);
-	info->tcpi_max_pacing_rate = rate != ~0U ? rate : ~0ULL;
+	rate64 = rate != ~0U ? rate : ~0ULL;
+	put_unaligned(rate64, &info->tcpi_max_pacing_rate);
 
 	do {
 		start = u64_stats_fetch_begin_irq(&tp->syncp);
-		info->tcpi_bytes_acked = tp->bytes_acked;
-		info->tcpi_bytes_received = tp->bytes_received;
+		put_unaligned(tp->bytes_acked, &info->tcpi_bytes_acked);
+		put_unaligned(tp->bytes_received, &info->tcpi_bytes_received);
 	} while (u64_stats_fetch_retry_irq(&tp->syncp, start));
 	info->tcpi_segs_out = tp->segs_out;
 	info->tcpi_segs_in = tp->segs_in;
-- 
2.1.0


From b31af060afe04db01a3c374264801351589b75e8 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 29 Jan 2016 12:30:19 +0100
Subject: [PATCH 15/47] ipv6: enforce flowi6_oif usage in ip6_dst_lookup_tail()

[ Upstream commit 6f21c96a78b835259546d8f3fb4edff0f651d478 ]

The current implementation of ip6_dst_lookup_tail basically
ignore the egress ifindex match: if the saddr is set,
ip6_route_output() purposefully ignores flowi6_oif, due
to the commit d46a9d678e4c ("net: ipv6: Dont add RT6_LOOKUP_F_IFACE
flag if saddr set"), if the saddr is 'any' the first route lookup
in ip6_dst_lookup_tail fails, but upon failure a second lookup will
be performed with saddr set, thus ignoring the ifindex constraint.

This commit adds an output route lookup function variant, which
allows the caller to specify lookup flags, and modify
ip6_dst_lookup_tail() to enforce the ifindex match on the second
lookup via said helper.

ip6_route_output() becames now a static inline function build on
top of ip6_route_output_flags(); as a side effect, out-of-tree
modules need now a GPL license to access the output route lookup
functionality.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_route.h | 12 ++++++++++--
 net/ipv6/ip6_output.c   |  6 +++++-
 net/ipv6/route.c        |  7 +++----
 3 files changed, 18 insertions(+), 7 deletions(-)

diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 877f682..295d291 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -64,8 +64,16 @@ static inline bool rt6_need_strict(const struct in6_addr *daddr)
 
 void ip6_route_input(struct sk_buff *skb);
 
-struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk,
-				   struct flowi6 *fl6);
+struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk,
+					 struct flowi6 *fl6, int flags);
+
+static inline struct dst_entry *ip6_route_output(struct net *net,
+						 const struct sock *sk,
+						 struct flowi6 *fl6)
+{
+	return ip6_route_output_flags(net, sk, fl6, 0);
+}
+
 struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6,
 				   int flags);
 
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 6473889..31144c4 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -909,6 +909,7 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk,
 	struct rt6_info *rt;
 #endif
 	int err;
+	int flags = 0;
 
 	/* The correct way to handle this would be to do
 	 * ip6_route_get_saddr, and then ip6_route_output; however,
@@ -940,10 +941,13 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk,
 			dst_release(*dst);
 			*dst = NULL;
 		}
+
+		if (fl6->flowi6_oif)
+			flags |= RT6_LOOKUP_F_IFACE;
 	}
 
 	if (!*dst)
-		*dst = ip6_route_output(net, sk, fl6);
+		*dst = ip6_route_output_flags(net, sk, fl6, flags);
 
 	err = (*dst)->error;
 	if (err)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 826e6aa..3f164d3 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1174,11 +1174,10 @@ static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table
 	return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, flags);
 }
 
-struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk,
-				    struct flowi6 *fl6)
+struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk,
+					 struct flowi6 *fl6, int flags)
 {
 	struct dst_entry *dst;
-	int flags = 0;
 	bool any_src;
 
 	dst = l3mdev_rt6_dst_by_oif(net, fl6);
@@ -1199,7 +1198,7 @@ struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk,
 
 	return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_output);
 }
-EXPORT_SYMBOL(ip6_route_output);
+EXPORT_SYMBOL_GPL(ip6_route_output_flags);
 
 struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_orig)
 {
-- 
2.1.0


From cdde8a05ab4c9384596dfc6c67e04a75296c55cb Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 29 Jan 2016 12:30:20 +0100
Subject: [PATCH 16/47] ipv6/udp: use sticky pktinfo egress ifindex on
 connect()

[ Upstream commit 1cdda91871470f15e79375991bd2eddc6e86ddb1 ]

Currently, the egress interface index specified via IPV6_PKTINFO
is ignored by __ip6_datagram_connect(), so that RFC 3542 section 6.7
can be subverted when the user space application calls connect()
before sendmsg().
Fix it by initializing properly flowi6_oif in connect() before
performing the route lookup.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/datagram.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 517c55b..4281621 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -162,6 +162,9 @@ ipv4_connected:
 	fl6.fl6_dport = inet->inet_dport;
 	fl6.fl6_sport = inet->inet_sport;
 
+	if (!fl6.flowi6_oif)
+		fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
+
 	if (!fl6.flowi6_oif && (addr_type&IPV6_ADDR_MULTICAST))
 		fl6.flowi6_oif = np->mcast_oif;
 
-- 
2.1.0


From 0ec365e650c3f9af9af4233aac389cba1b8ebdfa Mon Sep 17 00:00:00 2001
From: "subashab@codeaurora.org" <subashab@codeaurora.org>
Date: Tue, 2 Feb 2016 02:11:10 +0000
Subject: [PATCH 17/47] ipv6: addrconf: Fix recursive spin lock call

[ Upstream commit 16186a82de1fdd868255448274e64ae2616e2640 ]

A rcu stall with the following backtrace was seen on a system with
forwarding, optimistic_dad and use_optimistic set. To reproduce,
set these flags and allow ipv6 autoconf.

This occurs because the device write_lock is acquired while already
holding the read_lock. Back trace below -

INFO: rcu_preempt self-detected stall on CPU { 1}  (t=2100 jiffies
 g=3992 c=3991 q=4471)
<6> Task dump for CPU 1:
<2> kworker/1:0     R  running task    12168    15   2 0x00000002
<2> Workqueue: ipv6_addrconf addrconf_dad_work
<6> Call trace:
<2> [<ffffffc000084da8>] el1_irq+0x68/0xdc
<2> [<ffffffc000cc4e0c>] _raw_write_lock_bh+0x20/0x30
<2> [<ffffffc000bc5dd8>] __ipv6_dev_ac_inc+0x64/0x1b4
<2> [<ffffffc000bcbd2c>] addrconf_join_anycast+0x9c/0xc4
<2> [<ffffffc000bcf9f0>] __ipv6_ifa_notify+0x160/0x29c
<2> [<ffffffc000bcfb7c>] ipv6_ifa_notify+0x50/0x70
<2> [<ffffffc000bd035c>] addrconf_dad_work+0x314/0x334
<2> [<ffffffc0000b64c8>] process_one_work+0x244/0x3fc
<2> [<ffffffc0000b7324>] worker_thread+0x2f8/0x418
<2> [<ffffffc0000bb40c>] kthread+0xe0/0xec

v2: do addrconf_dad_kick inside read lock and then acquire write
lock for ipv6_ifa_notify as suggested by Eric

Fixes: 7fd2561e4ebdd ("net: ipv6: Add a sysctl to make optimistic
addresses useful candidates")

Cc: Eric Dumazet <edumazet@google.com>
Cc: Erik Kline <ek@google.com>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 1f21087..828ab28 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3506,6 +3506,7 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
 {
 	struct inet6_dev *idev = ifp->idev;
 	struct net_device *dev = idev->dev;
+	bool notify = false;
 
 	addrconf_join_solict(dev, &ifp->addr);
 
@@ -3551,7 +3552,7 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
 			/* Because optimistic nodes can use this address,
 			 * notify listeners. If DAD fails, RTM_DELADDR is sent.
 			 */
-			ipv6_ifa_notify(RTM_NEWADDR, ifp);
+			notify = true;
 		}
 	}
 
@@ -3559,6 +3560,8 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
 out:
 	spin_unlock(&ifp->lock);
 	read_unlock_bh(&idev->lock);
+	if (notify)
+		ipv6_ifa_notify(RTM_NEWADDR, ifp);
 }
 
 static void addrconf_dad_start(struct inet6_ifaddr *ifp)
-- 
2.1.0


From 8dd81b32c8f18c1e2791b4a60262e83041af4566 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 2 Feb 2016 17:55:01 -0800
Subject: [PATCH 18/47] ipv6: fix a lockdep splat

[ Upstream commit 44c3d0c1c0a880354e9de5d94175742e2c7c9683 ]

Silence lockdep false positive about rcu_dereference() being
used in the wrong context.

First one should use rcu_dereference_protected() as we own the spinlock.

Second one should be a normal assignation, as no barrier is needed.

Fixes: 18367681a10bd ("ipv6 flowlabel: Convert np->ipv6_fl_list to RCU.")
Reported-by: Dave Jones <davej@codemonkey.org.uk>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_flowlabel.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 1f9ebe3..dc2db4f 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -540,12 +540,13 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
 		}
 		spin_lock_bh(&ip6_sk_fl_lock);
 		for (sflp = &np->ipv6_fl_list;
-		     (sfl = rcu_dereference(*sflp)) != NULL;
+		     (sfl = rcu_dereference_protected(*sflp,
+						      lockdep_is_held(&ip6_sk_fl_lock))) != NULL;
 		     sflp = &sfl->next) {
 			if (sfl->fl->label == freq.flr_label) {
 				if (freq.flr_label == (np->flow_label&IPV6_FLOWLABEL_MASK))
 					np->flow_label &= ~IPV6_FLOWLABEL_MASK;
-				*sflp = rcu_dereference(sfl->next);
+				*sflp = sfl->next;
 				spin_unlock_bh(&ip6_sk_fl_lock);
 				fl_release(sfl->fl);
 				kfree_rcu(sfl, rcu);
-- 
2.1.0


From 15ddbc126c8e92959e261f49ca9f9be7385ac1e7 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Wed, 3 Feb 2016 02:11:03 +0100
Subject: [PATCH 19/47] unix: correctly track in-flight fds in sending process
 user_struct

[ Upstream commit 415e3d3e90ce9e18727e8843ae343eda5a58fad6 ]

The commit referenced in the Fixes tag incorrectly accounted the number
of in-flight fds over a unix domain socket to the original opener
of the file-descriptor. This allows another process to arbitrary
deplete the original file-openers resource limit for the maximum of
open files. Instead the sending processes and its struct cred should
be credited.

To do so, we add a reference counted struct user_struct pointer to the
scm_fp_list and use it to account for the number of inflight unix fds.

Fixes: 712f4aad406bb1 ("unix: properly account for FDs passed over unix sockets")
Reported-by: David Herrmann <dh.herrmann@gmail.com>
Cc: David Herrmann <dh.herrmann@gmail.com>
Cc: Willy Tarreau <w@1wt.eu>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/af_unix.h | 4 ++--
 include/net/scm.h     | 1 +
 net/core/scm.c        | 7 +++++++
 net/unix/af_unix.c    | 4 ++--
 net/unix/garbage.c    | 8 ++++----
 5 files changed, 16 insertions(+), 8 deletions(-)

diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index 2a91a05..9b4c418 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -6,8 +6,8 @@
 #include <linux/mutex.h>
 #include <net/sock.h>
 
-void unix_inflight(struct file *fp);
-void unix_notinflight(struct file *fp);
+void unix_inflight(struct user_struct *user, struct file *fp);
+void unix_notinflight(struct user_struct *user, struct file *fp);
 void unix_gc(void);
 void wait_for_unix_gc(void);
 struct sock *unix_get_socket(struct file *filp);
diff --git a/include/net/scm.h b/include/net/scm.h
index 262532d..59fa93c 100644
--- a/include/net/scm.h
+++ b/include/net/scm.h
@@ -21,6 +21,7 @@ struct scm_creds {
 struct scm_fp_list {
 	short			count;
 	short			max;
+	struct user_struct	*user;
 	struct file		*fp[SCM_MAX_FD];
 };
 
diff --git a/net/core/scm.c b/net/core/scm.c
index 8a1741b..dce0acb 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -87,6 +87,7 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp)
 		*fplp = fpl;
 		fpl->count = 0;
 		fpl->max = SCM_MAX_FD;
+		fpl->user = NULL;
 	}
 	fpp = &fpl->fp[fpl->count];
 
@@ -107,6 +108,10 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp)
 		*fpp++ = file;
 		fpl->count++;
 	}
+
+	if (!fpl->user)
+		fpl->user = get_uid(current_user());
+
 	return num;
 }
 
@@ -119,6 +124,7 @@ void __scm_destroy(struct scm_cookie *scm)
 		scm->fp = NULL;
 		for (i=fpl->count-1; i>=0; i--)
 			fput(fpl->fp[i]);
+		free_uid(fpl->user);
 		kfree(fpl);
 	}
 }
@@ -336,6 +342,7 @@ struct scm_fp_list *scm_fp_dup(struct scm_fp_list *fpl)
 		for (i = 0; i < fpl->count; i++)
 			get_file(fpl->fp[i]);
 		new_fpl->max = new_fpl->count;
+		new_fpl->user = get_uid(fpl->user);
 	}
 	return new_fpl;
 }
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 775855e..6de41c3 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1496,7 +1496,7 @@ static void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb)
 	UNIXCB(skb).fp = NULL;
 
 	for (i = scm->fp->count-1; i >= 0; i--)
-		unix_notinflight(scm->fp->fp[i]);
+		unix_notinflight(scm->fp->user, scm->fp->fp[i]);
 }
 
 static void unix_destruct_scm(struct sk_buff *skb)
@@ -1561,7 +1561,7 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
 		return -ENOMEM;
 
 	for (i = scm->fp->count - 1; i >= 0; i--)
-		unix_inflight(scm->fp->fp[i]);
+		unix_inflight(scm->fp->user, scm->fp->fp[i]);
 	return max_level;
 }
 
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 8fcdc22..6a0d485 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -116,7 +116,7 @@ struct sock *unix_get_socket(struct file *filp)
  * descriptor if it is for an AF_UNIX socket.
  */
 
-void unix_inflight(struct file *fp)
+void unix_inflight(struct user_struct *user, struct file *fp)
 {
 	struct sock *s = unix_get_socket(fp);
 
@@ -133,11 +133,11 @@ void unix_inflight(struct file *fp)
 		}
 		unix_tot_inflight++;
 	}
-	fp->f_cred->user->unix_inflight++;
+	user->unix_inflight++;
 	spin_unlock(&unix_gc_lock);
 }
 
-void unix_notinflight(struct file *fp)
+void unix_notinflight(struct user_struct *user, struct file *fp)
 {
 	struct sock *s = unix_get_socket(fp);
 
@@ -152,7 +152,7 @@ void unix_notinflight(struct file *fp)
 			list_del_init(&u->link);
 		unix_tot_inflight--;
 	}
-	fp->f_cred->user->unix_inflight--;
+	user->unix_inflight--;
 	spin_unlock(&unix_gc_lock);
 }
 
-- 
2.1.0


From ae6b0d02de1a9931012e1ef12e688a4c3997daa3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 2 Feb 2016 19:31:12 -0800
Subject: [PATCH 20/47] tcp: do not drop syn_recv on all icmp reports

[ Upstream commit 9cf7490360bf2c46a16b7525f899e4970c5fc144 ]

Petr Novopashenniy reported that ICMP redirects on SYN_RECV sockets
were leading to RST.

This is of course incorrect.

A specific list of ICMP messages should be able to drop a SYN_RECV.

For instance, a REDIRECT on SYN_RECV shall be ignored, as we do
not hold a dst per SYN_RECV pseudo request.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=111751
Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table")
Reported-by: Petr Novopashenniy <pety@rusnet.ru>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h   |  2 +-
 net/ipv4/tcp_ipv4.c | 11 ++++++++---
 net/ipv6/tcp_ipv6.c |  5 +++--
 3 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index f80e74c..414d822 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -449,7 +449,7 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th);
 
 void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb);
 void tcp_v4_mtu_reduced(struct sock *sk);
-void tcp_req_err(struct sock *sk, u32 seq);
+void tcp_req_err(struct sock *sk, u32 seq, bool abort);
 int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb);
 struct sock *tcp_create_openreq_child(const struct sock *sk,
 				      struct request_sock *req,
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 4627717..f66696c 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -312,7 +312,7 @@ static void do_redirect(struct sk_buff *skb, struct sock *sk)
 
 
 /* handle ICMP messages on TCP_NEW_SYN_RECV request sockets */
-void tcp_req_err(struct sock *sk, u32 seq)
+void tcp_req_err(struct sock *sk, u32 seq, bool abort)
 {
 	struct request_sock *req = inet_reqsk(sk);
 	struct net *net = sock_net(sk);
@@ -324,7 +324,7 @@ void tcp_req_err(struct sock *sk, u32 seq)
 
 	if (seq != tcp_rsk(req)->snt_isn) {
 		NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
-	} else {
+	} else if (abort) {
 		/*
 		 * Still in SYN_RECV, just remove it silently.
 		 * There is no good way to pass the error to the newly
@@ -384,7 +384,12 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 	}
 	seq = ntohl(th->seq);
 	if (sk->sk_state == TCP_NEW_SYN_RECV)
-		return tcp_req_err(sk, seq);
+		return tcp_req_err(sk, seq,
+				  type == ICMP_PARAMETERPROB ||
+				  type == ICMP_TIME_EXCEEDED ||
+				  (type == ICMP_DEST_UNREACH &&
+				   (code == ICMP_NET_UNREACH ||
+				    code == ICMP_HOST_UNREACH)));
 
 	bh_lock_sock(sk);
 	/* If too many ICMPs get dropped on busy
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index bd100b4..aea071e 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -328,6 +328,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	struct tcp_sock *tp;
 	__u32 seq, snd_una;
 	struct sock *sk;
+	bool fatal;
 	int err;
 
 	sk = __inet6_lookup_established(net, &tcp_hashinfo,
@@ -346,8 +347,9 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		return;
 	}
 	seq = ntohl(th->seq);
+	fatal = icmpv6_err_convert(type, code, &err);
 	if (sk->sk_state == TCP_NEW_SYN_RECV)
-		return tcp_req_err(sk, seq);
+		return tcp_req_err(sk, seq, fatal);
 
 	bh_lock_sock(sk);
 	if (sock_owned_by_user(sk) && type != ICMPV6_PKT_TOOBIG)
@@ -401,7 +403,6 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		goto out;
 	}
 
-	icmpv6_err_convert(type, code, &err);
 
 	/* Might be for an request_sock */
 	switch (sk->sk_state) {
-- 
2.1.0


From 06fd34194441c30fb8f8fc53846ebc2292b46893 Mon Sep 17 00:00:00 2001
From: Hans Westgaard Ry <hans.westgaard.ry@oracle.com>
Date: Wed, 3 Feb 2016 09:26:57 +0100
Subject: [PATCH 21/47] net:Add sysctl_max_skb_frags
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 5f74f82ea34c0da80ea0b49192bb5ea06e063593 ]

Devices may have limits on the number of fragments in an skb they support.
Current codebase uses a constant as maximum for number of fragments one
skb can hold and use.
When enabling scatter/gather and running traffic with many small messages
the codebase uses the maximum number of fragments and may thereby violate
the max for certain devices.
The patch introduces a global variable as max number of fragments.

Signed-off-by: Hans Westgaard Ry <hans.westgaard.ry@oracle.com>
Reviewed-by: Håkon Bugge <haakon.bugge@oracle.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h     |  1 +
 net/core/skbuff.c          |  2 ++
 net/core/sysctl_net_core.c | 10 ++++++++++
 net/ipv4/tcp.c             |  4 ++--
 4 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 9147f9f..75f136a 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -219,6 +219,7 @@ struct sk_buff;
 #else
 #define MAX_SKB_FRAGS (65536/PAGE_SIZE + 1)
 #endif
+extern int sysctl_max_skb_frags;
 
 typedef struct skb_frag_struct skb_frag_t;
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index b2df375..5bf88f5 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -79,6 +79,8 @@
 
 struct kmem_cache *skbuff_head_cache __read_mostly;
 static struct kmem_cache *skbuff_fclone_cache __read_mostly;
+int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS;
+EXPORT_SYMBOL(sysctl_max_skb_frags);
 
 /**
  *	skb_panic - private function for out-of-line support
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 95b6139..a6beb7b 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -26,6 +26,7 @@ static int zero = 0;
 static int one = 1;
 static int min_sndbuf = SOCK_MIN_SNDBUF;
 static int min_rcvbuf = SOCK_MIN_RCVBUF;
+static int max_skb_frags = MAX_SKB_FRAGS;
 
 static int net_msg_warn;	/* Unused, but still a sysctl */
 
@@ -392,6 +393,15 @@ static struct ctl_table net_core_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+	{
+		.procname	= "max_skb_frags",
+		.data		= &sysctl_max_skb_frags,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &one,
+		.extra2		= &max_skb_frags,
+	},
 	{ }
 };
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 9c1241e..036a76b 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -939,7 +939,7 @@ new_segment:
 
 		i = skb_shinfo(skb)->nr_frags;
 		can_coalesce = skb_can_coalesce(skb, i, page, offset);
-		if (!can_coalesce && i >= MAX_SKB_FRAGS) {
+		if (!can_coalesce && i >= sysctl_max_skb_frags) {
 			tcp_mark_push(tp, skb);
 			goto new_segment;
 		}
@@ -1212,7 +1212,7 @@ new_segment:
 
 			if (!skb_can_coalesce(skb, i, pfrag->page,
 					      pfrag->offset)) {
-				if (i == MAX_SKB_FRAGS || !sg) {
+				if (i == sysctl_max_skb_frags || !sg) {
 					tcp_mark_push(tp, skb);
 					goto new_segment;
 				}
-- 
2.1.0


From cd62a6368231e29455f2c44bf772403b5d1bdb11 Mon Sep 17 00:00:00 2001
From: Siva Reddy Kallam <siva.kallam@broadcom.com>
Date: Wed, 3 Feb 2016 14:09:38 +0530
Subject: [PATCH 22/47] tg3: Fix for tg3 transmit queue 0 timed out when too
 many gso_segs

[ Upstream commit b7d987295c74500b733a0ba07f9a9bcc4074fa83 ]

tg3_tso_bug() can hit a condition where the entire tx ring is not big
enough to segment the GSO packet. For example, if MSS is very small,
gso_segs can exceed the tx ring size. When we hit the condition, it
will cause tx timeout.

tg3_tso_bug() is called to handle TSO and DMA hardware bugs.
For TSO bugs, if tg3_tso_bug() cannot succeed, we have to drop the packet.
For DMA bugs, we can still fall back to linearize the SKB and let the
hardware transmit the TSO packet.

This patch adds a function tg3_tso_bug_gso_check() to check if there
are enough tx descriptors for GSO before calling tg3_tso_bug().
The caller will then handle the error appropriately - drop or
lineraize the SKB.

v2: Corrected patch description to avoid confusion.

Signed-off-by: Siva Reddy Kallam <siva.kallam@broadcom.com>
Signed-off-by: Michael Chan <mchan@broadcom.com>
Acked-by: Prashant Sreedharan <prashant@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/tg3.c | 25 +++++++++++++++++++------
 1 file changed, 19 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 79789d8..ca5ac5d 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -7833,6 +7833,14 @@ static int tigon3_dma_hwbug_workaround(struct tg3_napi *tnapi,
 	return ret;
 }
 
+static bool tg3_tso_bug_gso_check(struct tg3_napi *tnapi, struct sk_buff *skb)
+{
+	/* Check if we will never have enough descriptors,
+	 * as gso_segs can be more than current ring size
+	 */
+	return skb_shinfo(skb)->gso_segs < tnapi->tx_pending / 3;
+}
+
 static netdev_tx_t tg3_start_xmit(struct sk_buff *, struct net_device *);
 
 /* Use GSO to workaround all TSO packets that meet HW bug conditions
@@ -7936,14 +7944,19 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		 * vlan encapsulated.
 		 */
 		if (skb->protocol == htons(ETH_P_8021Q) ||
-		    skb->protocol == htons(ETH_P_8021AD))
-			return tg3_tso_bug(tp, tnapi, txq, skb);
+		    skb->protocol == htons(ETH_P_8021AD)) {
+			if (tg3_tso_bug_gso_check(tnapi, skb))
+				return tg3_tso_bug(tp, tnapi, txq, skb);
+			goto drop;
+		}
 
 		if (!skb_is_gso_v6(skb)) {
 			if (unlikely((ETH_HLEN + hdr_len) > 80) &&
-			    tg3_flag(tp, TSO_BUG))
-				return tg3_tso_bug(tp, tnapi, txq, skb);
-
+			    tg3_flag(tp, TSO_BUG)) {
+				if (tg3_tso_bug_gso_check(tnapi, skb))
+					return tg3_tso_bug(tp, tnapi, txq, skb);
+				goto drop;
+			}
 			ip_csum = iph->check;
 			ip_tot_len = iph->tot_len;
 			iph->check = 0;
@@ -8075,7 +8088,7 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (would_hit_hwbug) {
 		tg3_tx_skb_unmap(tnapi, tnapi->tx_prod, i);
 
-		if (mss) {
+		if (mss && tg3_tso_bug_gso_check(tnapi, skb)) {
 			/* If it's a TSO packet, do GSO instead of
 			 * allocating and copying to a large linear SKB
 			 */
-- 
2.1.0


From 0090d03ed7a0851f00eade59eed8bbba4b0e164c Mon Sep 17 00:00:00 2001
From: Sandeep Pillai <sanpilla@cisco.com>
Date: Wed, 3 Feb 2016 14:40:44 +0530
Subject: [PATCH 23/47] enic: increment devcmd2 result ring in case of timeout

[ Upstream commit ca7f41a4957b872577807169bd7464b36aae9b9c ]

Firmware posts the devcmd result in result ring. In case of timeout, driver
does not increment the current result pointer and firmware could post the
result after timeout has occurred. During next devcmd, driver would be
reading the result of previous devcmd.

Fix this by incrementing result even in case of timeout.

Fixes: 373fb0873d43 ("enic: add devcmd2")
Signed-off-by: Sandeep Pillai <sanpilla@cisco.com>
Signed-off-by: Govindarajulu Varadarajan <_govind@gmx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cisco/enic/enic.h     |  2 +-
 drivers/net/ethernet/cisco/enic/vnic_dev.c | 19 ++++++++++++-------
 2 files changed, 13 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/cisco/enic/enic.h b/drivers/net/ethernet/cisco/enic/enic.h
index 1671fa3..7ba6d53 100644
--- a/drivers/net/ethernet/cisco/enic/enic.h
+++ b/drivers/net/ethernet/cisco/enic/enic.h
@@ -33,7 +33,7 @@
 
 #define DRV_NAME		"enic"
 #define DRV_DESCRIPTION		"Cisco VIC Ethernet NIC Driver"
-#define DRV_VERSION		"2.3.0.12"
+#define DRV_VERSION		"2.3.0.20"
 #define DRV_COPYRIGHT		"Copyright 2008-2013 Cisco Systems, Inc"
 
 #define ENIC_BARS_MAX		6
diff --git a/drivers/net/ethernet/cisco/enic/vnic_dev.c b/drivers/net/ethernet/cisco/enic/vnic_dev.c
index 1ffd105..1fdf5fe 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_dev.c
+++ b/drivers/net/ethernet/cisco/enic/vnic_dev.c
@@ -298,7 +298,8 @@ static int _vnic_dev_cmd2(struct vnic_dev *vdev, enum vnic_devcmd_cmd cmd,
 			  int wait)
 {
 	struct devcmd2_controller *dc2c = vdev->devcmd2;
-	struct devcmd2_result *result = dc2c->result + dc2c->next_result;
+	struct devcmd2_result *result;
+	u8 color;
 	unsigned int i;
 	int delay, err;
 	u32 fetch_index, new_posted;
@@ -336,13 +337,17 @@ static int _vnic_dev_cmd2(struct vnic_dev *vdev, enum vnic_devcmd_cmd cmd,
 	if (dc2c->cmd_ring[posted].flags & DEVCMD2_FNORESULT)
 		return 0;
 
+	result = dc2c->result + dc2c->next_result;
+	color = dc2c->color;
+
+	dc2c->next_result++;
+	if (dc2c->next_result == dc2c->result_size) {
+		dc2c->next_result = 0;
+		dc2c->color = dc2c->color ? 0 : 1;
+	}
+
 	for (delay = 0; delay < wait; delay++) {
-		if (result->color == dc2c->color) {
-			dc2c->next_result++;
-			if (dc2c->next_result == dc2c->result_size) {
-				dc2c->next_result = 0;
-				dc2c->color = dc2c->color ? 0 : 1;
-			}
+		if (result->color == color) {
 			if (result->error) {
 				err = result->error;
 				if (err != ERR_ECMDUNKNOWN ||
-- 
2.1.0


From 055c0a822bdeca4b0ebdc7a34d91e9cef3ad1ad0 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 3 Feb 2016 23:33:30 +0800
Subject: [PATCH 24/47] sctp: translate network order to host order when users
 get a hmacid

[ Upstream commit 7a84bd46647ff181eb2659fdc99590e6f16e501d ]

Commit ed5a377d87dc ("sctp: translate host order to network order when
setting a hmacid") corrected the hmacid byte-order when setting a hmacid.
but the same issue also exists on getting a hmacid.

We fix it by changing hmacids to host order when users get them with
getsockopt.

Fixes: Commit ed5a377d87dc ("sctp: translate host order to network order when setting a hmacid")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 06a9cfb..be1489f 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -5542,6 +5542,7 @@ static int sctp_getsockopt_hmac_ident(struct sock *sk, int len,
 	struct sctp_hmac_algo_param *hmacs;
 	__u16 data_len = 0;
 	u32 num_idents;
+	int i;
 
 	if (!ep->auth_enable)
 		return -EACCES;
@@ -5559,8 +5560,12 @@ static int sctp_getsockopt_hmac_ident(struct sock *sk, int len,
 		return -EFAULT;
 	if (put_user(num_idents, &p->shmac_num_idents))
 		return -EFAULT;
-	if (copy_to_user(p->shmac_idents, hmacs->hmac_ids, data_len))
-		return -EFAULT;
+	for (i = 0; i < num_idents; i++) {
+		__u16 hmacid = ntohs(hmacs->hmac_ids[i]);
+
+		if (copy_to_user(&p->shmac_idents[i], &hmacid, sizeof(__u16)))
+			return -EFAULT;
+	}
 	return 0;
 }
 
-- 
2.1.0


From 163cc5d252e42abbab2d8a7780f028483e49b720 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <aduyck@mirantis.com>
Date: Tue, 9 Feb 2016 06:14:43 -0800
Subject: [PATCH 25/47] net: Copy inner L3 and L4 headers as unaligned on GRE
 TEB

[ Upstream commit 78565208d73ca9b654fb9a6b142214d52eeedfd1 ]

This patch corrects the unaligned accesses seen on GRE TEB tunnels when
generating hash keys.  Specifically what this patch does is make it so that
we force the use of skb_copy_bits when the GRE inner headers will be
unaligned due to NET_IP_ALIGNED being a non-zero value.

Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Acked-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/flow_dissector.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index d79699c..b258f45 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -396,6 +396,13 @@ ip_proto_again:
 				goto out_bad;
 			proto = eth->h_proto;
 			nhoff += sizeof(*eth);
+
+			/* Cap headers that we access via pointers at the
+			 * end of the Ethernet header as our maximum alignment
+			 * at that point is only 2 bytes.
+			 */
+			if (NET_IP_ALIGN)
+				hlen = nhoff;
 		}
 
 		key_control->flags |= FLOW_DIS_ENCAPSULATION;
-- 
2.1.0


From 14850edd12f32fba006d23109fe5739e2483cc93 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <aduyck@mirantis.com>
Date: Tue, 9 Feb 2016 02:49:54 -0800
Subject: [PATCH 26/47] flow_dissector: Fix unaligned access in
 __skb_flow_dissector when used by eth_get_headlen

[ Upstream commit 461547f3158978c180d74484d58e82be9b8e7357 ]

This patch fixes an issue with unaligned accesses when using
eth_get_headlen on a page that was DMA aligned instead of being IP aligned.
The fact is when trying to check the length we don't need to be looking at
the flow label so we can reorder the checks to first check if we are
supposed to gather the flow label and then make the call to actually get
it.

v2:  Updated path so that either STOP_AT_FLOW_LABEL or KEY_FLOW_LABEL can
     cause us to check for the flow label.

Reported-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/flow_dissector.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index b258f45..12e7003 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -208,7 +208,6 @@ ip:
 	case htons(ETH_P_IPV6): {
 		const struct ipv6hdr *iph;
 		struct ipv6hdr _iph;
-		__be32 flow_label;
 
 ipv6:
 		iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph);
@@ -230,8 +229,12 @@ ipv6:
 			key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
 		}
 
-		flow_label = ip6_flowlabel(iph);
-		if (flow_label) {
+		if ((dissector_uses_key(flow_dissector,
+					FLOW_DISSECTOR_KEY_FLOW_LABEL) ||
+		     (flags & FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL)) &&
+		    ip6_flowlabel(iph)) {
+			__be32 flow_label = ip6_flowlabel(iph);
+
 			if (dissector_uses_key(flow_dissector,
 					       FLOW_DISSECTOR_KEY_FLOW_LABEL)) {
 				key_tags = skb_flow_dissector_target(flow_dissector,
-- 
2.1.0


From fd0a139b8c2f871c6baf9221aadaaab1f9e2b097 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 10 Feb 2016 16:47:11 +0100
Subject: [PATCH 27/47] bpf: fix branch offset adjustment on backjumps after
 patching ctx expansion

[ Upstream commit a1b14d27ed0965838350f1377ff97c93ee383492 ]

When ctx access is used, the kernel often needs to expand/rewrite
instructions, so after that patching, branch offsets have to be
adjusted for both forward and backward jumps in the new eBPF program,
but for backward jumps it fails to account the delta. Meaning, for
example, if the expansion happens exactly on the insn that sits at
the jump target, it doesn't fix up the back jump offset.

Analysis on what the check in adjust_branches() is currently doing:

  /* adjust offset of jmps if necessary */
  if (i < pos && i + insn->off + 1 > pos)
    insn->off += delta;
  else if (i > pos && i + insn->off + 1 < pos)
    insn->off -= delta;

First condition (forward jumps):

  Before:                         After:

  insns[0]                        insns[0]
  insns[1] <--- i/insn            insns[1] <--- i/insn
  insns[2] <--- pos               insns[P] <--- pos
  insns[3]                        insns[P]  `------| delta
  insns[4] <--- target_X          insns[P]   `-----|
  insns[5]                        insns[3]
                                  insns[4] <--- target_X
                                  insns[5]

First case is if we cross pos-boundary and the jump instruction was
before pos. This is handeled correctly. I.e. if i == pos, then this
would mean our jump that we currently check was the patchlet itself
that we just injected. Since such patchlets are self-contained and
have no awareness of any insns before or after the patched one, the
delta is correctly not adjusted. Also, for the second condition in
case of i + insn->off + 1 == pos, means we jump to that newly patched
instruction, so no offset adjustment are needed. That part is correct.

Second condition (backward jumps):

  Before:                         After:

  insns[0]                        insns[0]
  insns[1] <--- target_X          insns[1] <--- target_X
  insns[2] <--- pos <-- target_Y  insns[P] <--- pos <-- target_Y
  insns[3]                        insns[P]  `------| delta
  insns[4] <--- i/insn            insns[P]   `-----|
  insns[5]                        insns[3]
                                  insns[4] <--- i/insn
                                  insns[5]

Second interesting case is where we cross pos-boundary and the jump
instruction was after pos. Backward jump with i == pos would be
impossible and pose a bug somewhere in the patchlet, so the first
condition checking i > pos is okay only by itself. However, i +
insn->off + 1 < pos does not always work as intended to trigger the
adjustment. It works when jump targets would be far off where the
delta wouldn't matter. But, for example, where the fixed insn->off
before pointed to pos (target_Y), it now points to pos + delta, so
that additional room needs to be taken into account for the check.
This means that i) both tests here need to be adjusted into pos + delta,
and ii) for the second condition, the test needs to be <= as pos
itself can be a target in the backjump, too.

Fixes: 9bac3d6d548e ("bpf: allow extended BPF programs access skb fields")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index d1d3e8f..2e7f7ab 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2082,7 +2082,7 @@ static void adjust_branches(struct bpf_prog *prog, int pos, int delta)
 		/* adjust offset of jmps if necessary */
 		if (i < pos && i + insn->off + 1 > pos)
 			insn->off += delta;
-		else if (i > pos && i + insn->off + 1 < pos)
+		else if (i > pos + delta && i + insn->off + 1 <= pos + delta)
 			insn->off -= delta;
 	}
 }
-- 
2.1.0


From 818792e44f5178cd8199768e0750e28201549d8c Mon Sep 17 00:00:00 2001
From: Jay Vosburgh <jay.vosburgh@canonical.com>
Date: Tue, 2 Feb 2016 13:35:56 -0800
Subject: [PATCH 28/47] bonding: Fix ARP monitor validation

[ Upstream commit 21a75f0915dde8674708b39abfcda113911c49b1 ]

The current logic in bond_arp_rcv will accept an incoming ARP for
validation if (a) the receiving slave is either "active" (which includes
the currently active slave, or the current ARP slave) or, (b) there is a
currently active slave, and it has received an ARP since it became active.
For case (b), the receiving slave isn't the currently active slave, and is
receiving the original broadcast ARP request, not an ARP reply from the
target.

	This logic can fail if there is no currently active slave.  In
this situation, the ARP probe logic cycles through all slaves, assigning
each in turn as the "current_arp_slave" for one arp_interval, then setting
that one as "active," and sending an ARP probe from that slave.  The
current logic expects the ARP reply to arrive on the sending
current_arp_slave, however, due to switch FDB updating delays, the reply
may be directed to another slave.

	This can arise if the bonding slaves and switch are working, but
the ARP target is not responding.  When the ARP target recovers, a
condition may result wherein the ARP target host replies faster than the
switch can update its forwarding table, causing each ARP reply to be sent
to the previous current_arp_slave.  This will never pass the logic in
bond_arp_rcv, as neither of the above conditions (a) or (b) are met.

	Some experimentation on a LAN shows ARP reply round trips in the
200 usec range, but my available switches never update their FDB in less
than 4000 usec.

	This patch changes the logic in bond_arp_rcv to additionally
accept an ARP reply for validation on any slave if there is a current ARP
slave and it sent an ARP probe during the previous arp_interval.

Fixes: aeea64ac717a ("bonding: don't trust arp requests unless active slave really works")
Cc: Veaceslav Falico <vfalico@gmail.com>
Cc: Andy Gospodarek <gospo@cumulusnetworks.com>
Signed-off-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 39 ++++++++++++++++++++++++++++-----------
 1 file changed, 28 insertions(+), 11 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index f1692e4..28bbca0 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -214,6 +214,8 @@ static void bond_uninit(struct net_device *bond_dev);
 static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev,
 						struct rtnl_link_stats64 *stats);
 static void bond_slave_arr_handler(struct work_struct *work);
+static bool bond_time_in_interval(struct bonding *bond, unsigned long last_act,
+				  int mod);
 
 /*---------------------------- General routines -----------------------------*/
 
@@ -2418,7 +2420,7 @@ int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond,
 		 struct slave *slave)
 {
 	struct arphdr *arp = (struct arphdr *)skb->data;
-	struct slave *curr_active_slave;
+	struct slave *curr_active_slave, *curr_arp_slave;
 	unsigned char *arp_ptr;
 	__be32 sip, tip;
 	int alen, is_arp = skb->protocol == __cpu_to_be16(ETH_P_ARP);
@@ -2465,26 +2467,41 @@ int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond,
 		     &sip, &tip);
 
 	curr_active_slave = rcu_dereference(bond->curr_active_slave);
+	curr_arp_slave = rcu_dereference(bond->current_arp_slave);
 
-	/* Backup slaves won't see the ARP reply, but do come through
-	 * here for each ARP probe (so we swap the sip/tip to validate
-	 * the probe).  In a "redundant switch, common router" type of
-	 * configuration, the ARP probe will (hopefully) travel from
-	 * the active, through one switch, the router, then the other
-	 * switch before reaching the backup.
+	/* We 'trust' the received ARP enough to validate it if:
+	 *
+	 * (a) the slave receiving the ARP is active (which includes the
+	 * current ARP slave, if any), or
+	 *
+	 * (b) the receiving slave isn't active, but there is a currently
+	 * active slave and it received valid arp reply(s) after it became
+	 * the currently active slave, or
+	 *
+	 * (c) there is an ARP slave that sent an ARP during the prior ARP
+	 * interval, and we receive an ARP reply on any slave.  We accept
+	 * these because switch FDB update delays may deliver the ARP
+	 * reply to a slave other than the sender of the ARP request.
 	 *
-	 * We 'trust' the arp requests if there is an active slave and
-	 * it received valid arp reply(s) after it became active. This
-	 * is done to avoid endless looping when we can't reach the
+	 * Note: for (b), backup slaves are receiving the broadcast ARP
+	 * request, not a reply.  This request passes from the sending
+	 * slave through the L2 switch(es) to the receiving slave.  Since
+	 * this is checking the request, sip/tip are swapped for
+	 * validation.
+	 *
+	 * This is done to avoid endless looping when we can't reach the
 	 * arp_ip_target and fool ourselves with our own arp requests.
 	 */
-
 	if (bond_is_active_slave(slave))
 		bond_validate_arp(bond, slave, sip, tip);
 	else if (curr_active_slave &&
 		 time_after(slave_last_rx(bond, curr_active_slave),
 			    curr_active_slave->last_link_up))
 		bond_validate_arp(bond, slave, tip, sip);
+	else if (curr_arp_slave && (arp->ar_op == htons(ARPOP_REPLY)) &&
+		 bond_time_in_interval(bond,
+				       dev_trans_start(curr_arp_slave->dev), 1))
+		bond_validate_arp(bond, slave, sip, tip);
 
 out_unlock:
 	if (arp != (struct arphdr *)skb->data)
-- 
2.1.0


From 2a1f86f784469fedb786b863458330e8e910e852 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 4 Feb 2016 06:23:28 -0800
Subject: [PATCH 29/47] ipv4: fix memory leaks in ip_cmsg_send() callers

[ Upstream commit 919483096bfe75dda338e98d56da91a263746a0a ]

Dmitry reported memory leaks of IP options allocated in
ip_cmsg_send() when/if this function returns an error.

Callers are responsible for the freeing.

Many thanks to Dmitry for the report and diagnostic.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_sockglue.c | 2 ++
 net/ipv4/ping.c        | 4 +++-
 net/ipv4/raw.c         | 4 +++-
 net/ipv4/udp.c         | 4 +++-
 4 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 5f73a7c..a501242 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -249,6 +249,8 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc,
 		switch (cmsg->cmsg_type) {
 		case IP_RETOPTS:
 			err = cmsg->cmsg_len - CMSG_ALIGN(sizeof(struct cmsghdr));
+
+			/* Our caller is responsible for freeing ipc->opt */
 			err = ip_options_get(net, &ipc->opt, CMSG_DATA(cmsg),
 					     err < 40 ? err : 40);
 			if (err)
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index e89094a..aa67e0e 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -746,8 +746,10 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	if (msg->msg_controllen) {
 		err = ip_cmsg_send(sock_net(sk), msg, &ipc, false);
-		if (err)
+		if (unlikely(err)) {
+			kfree(ipc.opt);
 			return err;
+		}
 		if (ipc.opt)
 			free = 1;
 	}
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index bc35f18..7113bae 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -547,8 +547,10 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	if (msg->msg_controllen) {
 		err = ip_cmsg_send(net, msg, &ipc, false);
-		if (err)
+		if (unlikely(err)) {
+			kfree(ipc.opt);
 			goto out;
+		}
 		if (ipc.opt)
 			free = 1;
 	}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index c438908..7f8ab46 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -966,8 +966,10 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	if (msg->msg_controllen) {
 		err = ip_cmsg_send(sock_net(sk), msg, &ipc,
 				   sk->sk_family == AF_INET6);
-		if (err)
+		if (unlikely(err)) {
+			kfree(ipc.opt);
 			return err;
+		}
 		if (ipc.opt)
 			free = 1;
 		connected = 0;
-- 
2.1.0


From 1e6d3be5ae45d16befd733df388714902da15f94 Mon Sep 17 00:00:00 2001
From: Rainer Weikusat <rweikusat@mobileactivedefense.com>
Date: Mon, 8 Feb 2016 18:47:19 +0000
Subject: [PATCH 30/47] af_unix: Don't set err in unix_stream_read_generic
 unless there was an error

[ Upstream commit 1b92ee3d03af6643df395300ba7748f19ecdb0c5 ]

The present unix_stream_read_generic contains various code sequences of
the form

err = -EDISASTER;
if (<test>)
	goto out;

This has the unfortunate side effect of possibly causing the error code
to bleed through to the final

out:
	return copied ? : err;

and then to be wrongly returned if no data was copied because the caller
didn't supply a data buffer, as demonstrated by the program available at

http://pad.lv/1540731

Change it such that err is only set if an error condition was detected.

Fixes: 3822b5c2fc62 ("af_unix: Revert 'lock_interruptible' in stream receive code")
Reported-by: Joseph Salisbury <joseph.salisbury@canonical.com>
Signed-off-by: Rainer Weikusat <rweikusat@mobileactivedefense.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 6de41c3..265412c 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2270,13 +2270,15 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state)
 	size_t size = state->size;
 	unsigned int last_len;
 
-	err = -EINVAL;
-	if (sk->sk_state != TCP_ESTABLISHED)
+	if (unlikely(sk->sk_state != TCP_ESTABLISHED)) {
+		err = -EINVAL;
 		goto out;
+	}
 
-	err = -EOPNOTSUPP;
-	if (flags & MSG_OOB)
+	if (unlikely(flags & MSG_OOB)) {
+		err = -EOPNOTSUPP;
 		goto out;
+	}
 
 	target = sock_rcvlowat(sk, flags & MSG_WAITALL, size);
 	timeo = sock_rcvtimeo(sk, noblock);
@@ -2322,9 +2324,11 @@ again:
 				goto unlock;
 
 			unix_state_unlock(sk);
-			err = -EAGAIN;
-			if (!timeo)
+			if (!timeo) {
+				err = -EAGAIN;
 				break;
+			}
+
 			mutex_unlock(&u->readlock);
 
 			timeo = unix_stream_data_wait(sk, timeo, last,
-- 
2.1.0


From dcd51b905bfc941f1ffea3322e97bb8a20db8a5d Mon Sep 17 00:00:00 2001
From: Rainer Weikusat <rweikusat@mobileactivedefense.com>
Date: Thu, 11 Feb 2016 19:37:27 +0000
Subject: [PATCH 31/47] af_unix: Guard against other == sk in
 unix_dgram_sendmsg

[ Upstream commit a5527dda344fff0514b7989ef7a755729769daa1 ]

The unix_dgram_sendmsg routine use the following test

if (unlikely(unix_peer(other) != sk && unix_recvq_full(other))) {

to determine if sk and other are in an n:1 association (either
established via connect or by using sendto to send messages to an
unrelated socket identified by address). This isn't correct as the
specified address could have been bound to the sending socket itself or
because this socket could have been connected to itself by the time of
the unix_peer_get but disconnected before the unix_state_lock(other). In
both cases, the if-block would be entered despite other == sk which
might either block the sender unintentionally or lead to trying to unlock
the same spin lock twice for a non-blocking send. Add a other != sk
check to guard against this.

Fixes: 7d267278a9ec ("unix: avoid use-after-free in ep_remove_wait_queue")
Reported-By: Philipp Hahn <pmhahn@pmhahn.de>
Signed-off-by: Rainer Weikusat <rweikusat@mobileactivedefense.com>
Tested-by: Philipp Hahn <pmhahn@pmhahn.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 265412c..898a53a 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1781,7 +1781,12 @@ restart_locked:
 			goto out_unlock;
 	}
 
-	if (unlikely(unix_peer(other) != sk && unix_recvq_full(other))) {
+	/* other == sk && unix_peer(other) != sk if
+	 * - unix_peer(sk) == NULL, destination address bound to sk
+	 * - unix_peer(sk) == sk by time of get but disconnected before lock
+	 */
+	if (other != sk &&
+	    unlikely(unix_peer(other) != sk && unix_recvq_full(other))) {
 		if (timeo) {
 			timeo = unix_wait_for_peer(other, timeo);
 
-- 
2.1.0


From aba4bbb881ef85776da744260e8f1d24c75722d6 Mon Sep 17 00:00:00 2001
From: Jon Paul Maloy <jon.maloy@ericsson.com>
Date: Wed, 10 Feb 2016 16:14:57 -0500
Subject: [PATCH 32/47] tipc: fix premature addition of node to lookup table

[ Upstream commit d5c91fb72f1652ea3026925240a0998a42ddb16b ]

In commit 5266698661401a ("tipc: let broadcast packet reception
use new link receive function") we introduced a new per-node
broadcast reception link instance. This link is created at the
moment the node itself is created. Unfortunately, the allocation
is done after the node instance has already been added to the node
lookup hash table. This creates a potential race condition, where
arriving broadcast packets are able to find and access the node
before it has been fully initialized, and before the above mentioned
link has been created. The result is occasional crashes in the function
tipc_bcast_rcv(), which is trying to access the not-yet existing link.

We fix this by deferring the addition of the node instance until after
it has been fully initialized in the function tipc_node_create().

Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/node.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/tipc/node.c b/net/tipc/node.c
index 20cddec..3926b56 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -168,12 +168,6 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr, u16 capabilities)
 	skb_queue_head_init(&n_ptr->bc_entry.inputq1);
 	__skb_queue_head_init(&n_ptr->bc_entry.arrvq);
 	skb_queue_head_init(&n_ptr->bc_entry.inputq2);
-	hlist_add_head_rcu(&n_ptr->hash, &tn->node_htable[tipc_hashfn(addr)]);
-	list_for_each_entry_rcu(temp_node, &tn->node_list, list) {
-		if (n_ptr->addr < temp_node->addr)
-			break;
-	}
-	list_add_tail_rcu(&n_ptr->list, &temp_node->list);
 	n_ptr->state = SELF_DOWN_PEER_LEAVING;
 	n_ptr->signature = INVALID_NODE_SIG;
 	n_ptr->active_links[0] = INVALID_BEARER_ID;
@@ -193,6 +187,12 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr, u16 capabilities)
 	tipc_node_get(n_ptr);
 	setup_timer(&n_ptr->timer, tipc_node_timeout, (unsigned long)n_ptr);
 	n_ptr->keepalive_intv = U32_MAX;
+	hlist_add_head_rcu(&n_ptr->hash, &tn->node_htable[tipc_hashfn(addr)]);
+	list_for_each_entry_rcu(temp_node, &tn->node_list, list) {
+		if (n_ptr->addr < temp_node->addr)
+			break;
+	}
+	list_add_tail_rcu(&n_ptr->list, &temp_node->list);
 exit:
 	spin_unlock_bh(&tn->node_list_lock);
 	return n_ptr;
-- 
2.1.0


From 9db218fa06f9917a7e852089e7d2b9513af31f2a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 11 Feb 2016 22:50:29 -0800
Subject: [PATCH 33/47] tcp: md5: release request socket instead of listener

[ Upstream commit 729235554d805c63e5e274fcc6a98e71015dd847 ]

If tcp_v4_inbound_md5_hash() returns an error, we must release
the refcount on the request socket, not on the listener.

The bug was added for IPv4 only.

Fixes: 079096f103fac ("tcp/dccp: install syn_recv requests into ehash table")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index f66696c..bfcddee 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1597,8 +1597,10 @@ process:
 		struct sock *nsk = NULL;
 
 		sk = req->rsk_listener;
-		if (tcp_v4_inbound_md5_hash(sk, skb))
-			goto discard_and_relse;
+		if (unlikely(tcp_v4_inbound_md5_hash(sk, skb))) {
+			reqsk_put(req);
+			goto discard_it;
+		}
 		if (likely(sk->sk_state == TCP_LISTEN)) {
 			nsk = tcp_check_req(sk, skb, req, false);
 		} else {
-- 
2.1.0


From f3eddbd11f221643b1f33beca572d06f6c883da0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Fri, 12 Feb 2016 16:42:14 +0100
Subject: [PATCH 34/47] qmi_wwan: add "4G LTE usb-modem U901"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit aac8d3c282e024c344c5b86dc1eab7af88bb9716 ]

Thomas reports:

T:  Bus=01 Lev=01 Prnt=01 Port=03 Cnt=01 Dev#=  4 Spd=480 MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=05c6 ProdID=6001 Rev=00.00
S:  Manufacturer=USB Modem
S:  Product=USB Modem
S:  SerialNumber=1234567890ABCDEF
C:  #Ifs= 5 Cfg#= 1 Atr=e0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
I:  If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
I:  If#= 2 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
I:  If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
I:  If#= 4 Alt= 0 #EPs= 2 Cls=08(stor.) Sub=06 Prot=50 Driver=usb-storage

Reported-by: Thomas Schäfer <tschaefer@t-online.de>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 5fccc5a..982e0acd 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -492,6 +492,7 @@ static const struct usb_device_id products[] = {
 
 	/* 3. Combined interface devices matching on interface number */
 	{QMI_FIXED_INTF(0x0408, 0xea42, 4)},	/* Yota / Megafon M100-1 */
+	{QMI_FIXED_INTF(0x05c6, 0x6001, 3)},	/* 4G LTE usb-modem U901 */
 	{QMI_FIXED_INTF(0x05c6, 0x7000, 0)},
 	{QMI_FIXED_INTF(0x05c6, 0x7001, 1)},
 	{QMI_FIXED_INTF(0x05c6, 0x7002, 1)},
-- 
2.1.0


From ae637d7ca4d9df02a5438870066f40de97746eea Mon Sep 17 00:00:00 2001
From: Amir Vadai <amir@vadai.me>
Date: Wed, 17 Feb 2016 17:24:22 +0200
Subject: [PATCH 35/47] net/mlx4_en: Count HW buffer overrun only once

[ Upstream commit 281e8b2fdf8e4ef366b899453cae50e09b577ada ]

RdropOvflw counts overrun of HW buffer, therefore should
be used for rx_fifo_errors only.

Currently RdropOvflw counter is mistakenly also set into
rx_missed_errors and rx_over_errors too, which makes the
device total dropped packets accounting to show wrong results.

Fix that. Use it for rx_fifo_errors only.

Fixes: c27a02cd94d6 ('mlx4_en: Add driver for Mellanox ConnectX 10GbE NIC')
Signed-off-by: Amir Vadai <amir@vadai.me>
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_port.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c
index ee99e67..3904b5f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c
@@ -238,11 +238,11 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
 	stats->collisions = 0;
 	stats->rx_dropped = be32_to_cpu(mlx4_en_stats->RDROP);
 	stats->rx_length_errors = be32_to_cpu(mlx4_en_stats->RdropLength);
-	stats->rx_over_errors = be32_to_cpu(mlx4_en_stats->RdropOvflw);
+	stats->rx_over_errors = 0;
 	stats->rx_crc_errors = be32_to_cpu(mlx4_en_stats->RCRC);
 	stats->rx_frame_errors = 0;
 	stats->rx_fifo_errors = be32_to_cpu(mlx4_en_stats->RdropOvflw);
-	stats->rx_missed_errors = be32_to_cpu(mlx4_en_stats->RdropOvflw);
+	stats->rx_missed_errors = 0;
 	stats->tx_aborted_errors = 0;
 	stats->tx_carrier_errors = 0;
 	stats->tx_fifo_errors = 0;
-- 
2.1.0


From b5fcfba41470bc264d1d750efd01f0ed104c37da Mon Sep 17 00:00:00 2001
From: Eugenia Emantayev <eugenia@mellanox.com>
Date: Wed, 17 Feb 2016 17:24:23 +0200
Subject: [PATCH 36/47] net/mlx4_en: Choose time-stamping shift value according
 to HW frequency

[ Upstream commit 31c128b66e5b28f468076e4f3ca3025c35342041 ]

Previously, the shift value used for time-stamping was constant and didn't
depend on the HW chip frequency. Change that to take the frequency into account
and calculate the maximal value in cycles per wraparound of ten seconds. This
time slot was chosen since it gives a good accuracy in time synchronization.

Algorithm for shift value calculation:
 * Round up the maximal value in cycles to nearest power of two

 * Calculate maximal multiplier by division of all 64 bits set
   to above result

 * Then, invert the function clocksource_khz2mult() to get the shift from
   maximal mult value

Fixes: ec693d47010e ('net/mlx4_en: Add HW timestamping (TS) support')
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Reviewed-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_clock.c | 25 +++++++++++++++++++------
 1 file changed, 19 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_clock.c b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
index 038f9ce..1494997 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
@@ -236,6 +236,24 @@ static const struct ptp_clock_info mlx4_en_ptp_clock_info = {
 	.enable		= mlx4_en_phc_enable,
 };
 
+#define MLX4_EN_WRAP_AROUND_SEC	10ULL
+
+/* This function calculates the max shift that enables the user range
+ * of MLX4_EN_WRAP_AROUND_SEC values in the cycles register.
+ */
+static u32 freq_to_shift(u16 freq)
+{
+	u32 freq_khz = freq * 1000;
+	u64 max_val_cycles = freq_khz * 1000 * MLX4_EN_WRAP_AROUND_SEC;
+	u64 max_val_cycles_rounded = is_power_of_2(max_val_cycles + 1) ?
+		max_val_cycles : roundup_pow_of_two(max_val_cycles) - 1;
+	/* calculate max possible multiplier in order to fit in 64bit */
+	u64 max_mul = div_u64(0xffffffffffffffffULL, max_val_cycles_rounded);
+
+	/* This comes from the reverse of clocksource_khz2mult */
+	return ilog2(div_u64(max_mul * freq_khz, 1000000));
+}
+
 void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev)
 {
 	struct mlx4_dev *dev = mdev->dev;
@@ -254,12 +272,7 @@ void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev)
 	memset(&mdev->cycles, 0, sizeof(mdev->cycles));
 	mdev->cycles.read = mlx4_en_read_clock;
 	mdev->cycles.mask = CLOCKSOURCE_MASK(48);
-	/* Using shift to make calculation more accurate. Since current HW
-	 * clock frequency is 427 MHz, and cycles are given using a 48 bits
-	 * register, the biggest shift when calculating using u64, is 14
-	 * (max_cycles * multiplier < 2^64)
-	 */
-	mdev->cycles.shift = 14;
+	mdev->cycles.shift = freq_to_shift(dev->caps.hca_core_clock);
 	mdev->cycles.mult =
 		clocksource_khz2mult(1000 * dev->caps.hca_core_clock, mdev->cycles.shift);
 	mdev->nominal_c_mult = mdev->cycles.mult;
-- 
2.1.0


From 2681336d558086688fb81760a2294c5c298e60dd Mon Sep 17 00:00:00 2001
From: Eugenia Emantayev <eugenia@mellanox.com>
Date: Wed, 17 Feb 2016 17:24:27 +0200
Subject: [PATCH 37/47] net/mlx4_en: Avoid changing dev->features directly in
 run-time

[ Upstream commit 925ab1aa9394bbaeac47ee5b65d3fdf0fb8135cf ]

It's forbidden to manually change dev->features in run-time. Currently, this is
done in the driver to make sure that GSO_UDP_TUNNEL is advertized only when
VXLAN tunnel is set. However, since the stack actually does features intersection
with hw_enc_features, we can safely revert to advertizing features early when
registering the netdevice.

Fixes: f4a1edd56120 ('net/mlx4_en: Advertize encapsulation offloads [...]')
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 7869f97..67e9633 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2381,8 +2381,6 @@ out:
 	/* set offloads */
 	priv->dev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_RXCSUM |
 				      NETIF_F_TSO | NETIF_F_GSO_UDP_TUNNEL;
-	priv->dev->hw_features |= NETIF_F_GSO_UDP_TUNNEL;
-	priv->dev->features    |= NETIF_F_GSO_UDP_TUNNEL;
 }
 
 static void mlx4_en_del_vxlan_offloads(struct work_struct *work)
@@ -2393,8 +2391,6 @@ static void mlx4_en_del_vxlan_offloads(struct work_struct *work)
 	/* unset offloads */
 	priv->dev->hw_enc_features &= ~(NETIF_F_IP_CSUM | NETIF_F_RXCSUM |
 				      NETIF_F_TSO | NETIF_F_GSO_UDP_TUNNEL);
-	priv->dev->hw_features &= ~NETIF_F_GSO_UDP_TUNNEL;
-	priv->dev->features    &= ~NETIF_F_GSO_UDP_TUNNEL;
 
 	ret = mlx4_SET_PORT_VXLAN(priv->mdev->dev, priv->port,
 				  VXLAN_STEER_BY_OUTER_MAC, 0);
@@ -3020,6 +3016,11 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 		priv->rss_hash_fn = ETH_RSS_HASH_TOP;
 	}
 
+	if (mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) {
+		dev->hw_features |= NETIF_F_GSO_UDP_TUNNEL;
+		dev->features    |= NETIF_F_GSO_UDP_TUNNEL;
+	}
+
 	mdev->pndev[port] = dev;
 	mdev->upper[port] = NULL;
 
-- 
2.1.0


From 679b435ba7247a4ade026c9fadf0bd3444907fbd Mon Sep 17 00:00:00 2001
From: Mark Tomlinson <mark.tomlinson@alliedtelesis.co.nz>
Date: Mon, 15 Feb 2016 16:24:44 +1300
Subject: [PATCH 38/47] l2tp: Fix error creating L2TP tunnels

[ Upstream commit 853effc55b0f975abd6d318cca486a9c1b67e10f ]

A previous commit (33f72e6) added notification via netlink for tunnels
when created/modified/deleted. If the notification returned an error,
this error was returned from the tunnel function. If there were no
listeners, the error code ESRCH was returned, even though having no
listeners is not an error. Other calls to this and other similar
notification functions either ignore the error code, or filter ESRCH.
This patch checks for ESRCH and does not flag this as an error.

Reviewed-by: Hamish Martin <hamish.martin@alliedtelesis.co.nz>
Signed-off-by: Mark Tomlinson <mark.tomlinson@alliedtelesis.co.nz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_netlink.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index f93c5be..2caaa84 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -124,8 +124,13 @@ static int l2tp_tunnel_notify(struct genl_family *family,
 	ret = l2tp_nl_tunnel_send(msg, info->snd_portid, info->snd_seq,
 				  NLM_F_ACK, tunnel, cmd);
 
-	if (ret >= 0)
-		return genlmsg_multicast_allns(family, msg, 0,	0, GFP_ATOMIC);
+	if (ret >= 0) {
+		ret = genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC);
+		/* We don't care if no one is listening */
+		if (ret == -ESRCH)
+			ret = 0;
+		return ret;
+	}
 
 	nlmsg_free(msg);
 
@@ -147,8 +152,13 @@ static int l2tp_session_notify(struct genl_family *family,
 	ret = l2tp_nl_session_send(msg, info->snd_portid, info->snd_seq,
 				   NLM_F_ACK, session, cmd);
 
-	if (ret >= 0)
-		return genlmsg_multicast_allns(family, msg, 0,	0, GFP_ATOMIC);
+	if (ret >= 0) {
+		ret = genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC);
+		/* We don't care if no one is listening */
+		if (ret == -ESRCH)
+			ret = 0;
+		return ret;
+	}
 
 	nlmsg_free(msg);
 
-- 
2.1.0


From af71da691d72f8d4dff2c6ee2f478635d8c1db0a Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Mon, 15 Feb 2016 17:01:10 +0100
Subject: [PATCH 39/47] pppoe: fix reference counting in PPPoE proxy

[ Upstream commit 29e73269aa4d36f92b35610c25f8b01c789b0dc8 ]

Drop reference on the relay_po socket when __pppoe_xmit() succeeds.
This is already handled correctly in the error path.

Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pppoe.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 0a37f84..4e0068e7 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -395,6 +395,8 @@ static int pppoe_rcv_core(struct sock *sk, struct sk_buff *skb)
 
 		if (!__pppoe_xmit(sk_pppox(relay_po), skb))
 			goto abort_put;
+
+		sock_put(sk_pppox(relay_po));
 	} else {
 		if (sock_queue_rcv_skb(sk, skb))
 			goto abort_kfree;
-- 
2.1.0


From 11253bc76ca428cf57d2ef3fcd198eff79359d24 Mon Sep 17 00:00:00 2001
From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Thu, 18 Feb 2016 07:38:04 -0500
Subject: [PATCH 40/47] net_sched fix: reclassification needs to consider ether
 protocol changes

[ Upstream commit 619fe32640b4b01f370574d50344ae0f62689816 ]

actions could change the etherproto in particular with ethernet
tunnelled data. Typically such actions, after peeling the outer header,
will ask for the packet to be  reclassified. We then need to restart
the classification with the new proto header.

Example setup used to catch this:
sudo tc qdisc add dev $ETH ingress
sudo $TC filter add dev $ETH parent ffff: pref 1 protocol 802.1Q \
u32 match u32 0 0 flowid 1:1 \
action  vlan pop reclassify

Fixes: 3b3ae880266d ("net: sched: consolidate tc_classify{,_compat}")
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_api.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index b5c2cf2..af1acf0 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1852,6 +1852,7 @@ reset:
 	}
 
 	tp = old_tp;
+	protocol = tc_skb_protocol(skb);
 	goto reclassify;
 #endif
 }
-- 
2.1.0


From 92e994dc73307d98080ee684259182eb300dc552 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 18 Feb 2016 21:21:19 +0800
Subject: [PATCH 41/47] route: check and remove route cache when we get route

[ Upstream commit deed49df7390d5239024199e249190328f1651e7 ]

Since the gc of ipv4 route was removed, the route cached would has
no chance to be removed, and even it has been timeout, it still could
be used, cause no code to check it's expires.

Fix this issue by checking  and removing route cache when we get route.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_fib.h |  1 +
 net/ipv4/route.c     | 77 ++++++++++++++++++++++++++++++++++++++++++----------
 2 files changed, 64 insertions(+), 14 deletions(-)

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 9f4df68..3f98233 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -61,6 +61,7 @@ struct fib_nh_exception {
 	struct rtable __rcu		*fnhe_rth_input;
 	struct rtable __rcu		*fnhe_rth_output;
 	unsigned long			fnhe_stamp;
+	struct rcu_head			rcu;
 };
 
 struct fnhe_hash_bucket {
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 85f184e..02c6229 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -129,6 +129,7 @@ static int ip_rt_mtu_expires __read_mostly	= 10 * 60 * HZ;
 static int ip_rt_min_pmtu __read_mostly		= 512 + 20 + 20;
 static int ip_rt_min_advmss __read_mostly	= 256;
 
+static int ip_rt_gc_timeout __read_mostly	= RT_GC_TIMEOUT;
 /*
  *	Interface to generic destination cache.
  */
@@ -755,7 +756,7 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
 				struct fib_nh *nh = &FIB_RES_NH(res);
 
 				update_or_create_fnhe(nh, fl4->daddr, new_gw,
-						      0, 0);
+						0, jiffies + ip_rt_gc_timeout);
 			}
 			if (kill_route)
 				rt->dst.obsolete = DST_OBSOLETE_KILL;
@@ -1556,6 +1557,36 @@ static void ip_handle_martian_source(struct net_device *dev,
 #endif
 }
 
+static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
+{
+	struct fnhe_hash_bucket *hash;
+	struct fib_nh_exception *fnhe, __rcu **fnhe_p;
+	u32 hval = fnhe_hashfun(daddr);
+
+	spin_lock_bh(&fnhe_lock);
+
+	hash = rcu_dereference_protected(nh->nh_exceptions,
+					 lockdep_is_held(&fnhe_lock));
+	hash += hval;
+
+	fnhe_p = &hash->chain;
+	fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock));
+	while (fnhe) {
+		if (fnhe->fnhe_daddr == daddr) {
+			rcu_assign_pointer(*fnhe_p, rcu_dereference_protected(
+				fnhe->fnhe_next, lockdep_is_held(&fnhe_lock)));
+			fnhe_flush_routes(fnhe);
+			kfree_rcu(fnhe, rcu);
+			break;
+		}
+		fnhe_p = &fnhe->fnhe_next;
+		fnhe = rcu_dereference_protected(fnhe->fnhe_next,
+						 lockdep_is_held(&fnhe_lock));
+	}
+
+	spin_unlock_bh(&fnhe_lock);
+}
+
 /* called in rcu_read_lock() section */
 static int __mkroute_input(struct sk_buff *skb,
 			   const struct fib_result *res,
@@ -1609,11 +1640,20 @@ static int __mkroute_input(struct sk_buff *skb,
 
 	fnhe = find_exception(&FIB_RES_NH(*res), daddr);
 	if (do_cache) {
-		if (fnhe)
+		if (fnhe) {
 			rth = rcu_dereference(fnhe->fnhe_rth_input);
-		else
-			rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
+			if (rth && rth->dst.expires &&
+			    time_after(jiffies, rth->dst.expires)) {
+				ip_del_fnhe(&FIB_RES_NH(*res), daddr);
+				fnhe = NULL;
+			} else {
+				goto rt_cache;
+			}
+		}
+
+		rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
 
+rt_cache:
 		if (rt_cache_valid(rth)) {
 			skb_dst_set_noref(skb, &rth->dst);
 			goto out;
@@ -2014,19 +2054,29 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 		struct fib_nh *nh = &FIB_RES_NH(*res);
 
 		fnhe = find_exception(nh, fl4->daddr);
-		if (fnhe)
+		if (fnhe) {
 			prth = &fnhe->fnhe_rth_output;
-		else {
-			if (unlikely(fl4->flowi4_flags &
-				     FLOWI_FLAG_KNOWN_NH &&
-				     !(nh->nh_gw &&
-				       nh->nh_scope == RT_SCOPE_LINK))) {
-				do_cache = false;
-				goto add;
+			rth = rcu_dereference(*prth);
+			if (rth && rth->dst.expires &&
+			    time_after(jiffies, rth->dst.expires)) {
+				ip_del_fnhe(nh, fl4->daddr);
+				fnhe = NULL;
+			} else {
+				goto rt_cache;
 			}
-			prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
 		}
+
+		if (unlikely(fl4->flowi4_flags &
+			     FLOWI_FLAG_KNOWN_NH &&
+			     !(nh->nh_gw &&
+			       nh->nh_scope == RT_SCOPE_LINK))) {
+			do_cache = false;
+			goto add;
+		}
+		prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
 		rth = rcu_dereference(*prth);
+
+rt_cache:
 		if (rt_cache_valid(rth)) {
 			dst_hold(&rth->dst);
 			return rth;
@@ -2569,7 +2619,6 @@ void ip_rt_multicast_event(struct in_device *in_dev)
 }
 
 #ifdef CONFIG_SYSCTL
-static int ip_rt_gc_timeout __read_mostly	= RT_GC_TIMEOUT;
 static int ip_rt_gc_interval __read_mostly  = 60 * HZ;
 static int ip_rt_gc_min_interval __read_mostly	= HZ / 2;
 static int ip_rt_gc_elasticity __read_mostly	= 8;
-- 
2.1.0


From e7b45041b74baa3aea88b9ef6e2db8c4ed9b7e24 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 18 Feb 2016 05:39:18 -0800
Subject: [PATCH 42/47] tcp/dccp: fix another race at listener dismantle

[ Upstream commit 7716682cc58e305e22207d5bb315f26af6b1e243 ]

Ilya reported following lockdep splat:

kernel: =========================
kernel: [ BUG: held lock freed! ]
kernel: 4.5.0-rc1-ceph-00026-g5e0a311 #1 Not tainted
kernel: -------------------------
kernel: swapper/5/0 is freeing memory
ffff880035c9d200-ffff880035c9dbff, with a lock still held there!
kernel: (&(&queue->rskq_lock)->rlock){+.-...}, at:
[<ffffffff816f6a88>] inet_csk_reqsk_queue_add+0x28/0xa0
kernel: 4 locks held by swapper/5/0:
kernel: #0:  (rcu_read_lock){......}, at: [<ffffffff8169ef6b>]
netif_receive_skb_internal+0x4b/0x1f0
kernel: #1:  (rcu_read_lock){......}, at: [<ffffffff816e977f>]
ip_local_deliver_finish+0x3f/0x380
kernel: #2:  (slock-AF_INET){+.-...}, at: [<ffffffff81685ffb>]
sk_clone_lock+0x19b/0x440
kernel: #3:  (&(&queue->rskq_lock)->rlock){+.-...}, at:
[<ffffffff816f6a88>] inet_csk_reqsk_queue_add+0x28/0xa0

To properly fix this issue, inet_csk_reqsk_queue_add() needs
to return to its callers if the child as been queued
into accept queue.

We also need to make sure listener is still there before
calling sk->sk_data_ready(), by holding a reference on it,
since the reference carried by the child can disappear as
soon as the child is put on accept queue.

Reported-by: Ilya Dryomov <idryomov@gmail.com>
Fixes: ebb516af60e1 ("tcp/dccp: fix race at listener dismantle phase")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_connection_sock.h |  5 +++--
 net/dccp/ipv4.c                    | 14 +++++++-------
 net/dccp/ipv6.c                    | 14 +++++++-------
 net/ipv4/inet_connection_sock.c    | 14 +++++++-------
 net/ipv4/tcp_ipv4.c                | 14 +++++++-------
 net/ipv6/tcp_ipv6.c                | 14 +++++++-------
 6 files changed, 38 insertions(+), 37 deletions(-)

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 481fe1c..49dcad4 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -270,8 +270,9 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
 					    struct sock *newsk,
 					    const struct request_sock *req);
 
-void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req,
-			      struct sock *child);
+struct sock *inet_csk_reqsk_queue_add(struct sock *sk,
+				      struct request_sock *req,
+				      struct sock *child);
 void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req,
 				   unsigned long timeout);
 struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child,
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 5684e14..902d606 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -824,26 +824,26 @@ lookup:
 
 	if (sk->sk_state == DCCP_NEW_SYN_RECV) {
 		struct request_sock *req = inet_reqsk(sk);
-		struct sock *nsk = NULL;
+		struct sock *nsk;
 
 		sk = req->rsk_listener;
-		if (likely(sk->sk_state == DCCP_LISTEN)) {
-			nsk = dccp_check_req(sk, skb, req);
-		} else {
+		if (unlikely(sk->sk_state != DCCP_LISTEN)) {
 			inet_csk_reqsk_queue_drop_and_put(sk, req);
 			goto lookup;
 		}
+		sock_hold(sk);
+		nsk = dccp_check_req(sk, skb, req);
 		if (!nsk) {
 			reqsk_put(req);
-			goto discard_it;
+			goto discard_and_relse;
 		}
 		if (nsk == sk) {
-			sock_hold(sk);
 			reqsk_put(req);
 		} else if (dccp_child_process(sk, nsk, skb)) {
 			dccp_v4_ctl_send_reset(sk, skb);
-			goto discard_it;
+			goto discard_and_relse;
 		} else {
+			sock_put(sk);
 			return 0;
 		}
 	}
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 9c6d050..b8608b7 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -691,26 +691,26 @@ lookup:
 
 	if (sk->sk_state == DCCP_NEW_SYN_RECV) {
 		struct request_sock *req = inet_reqsk(sk);
-		struct sock *nsk = NULL;
+		struct sock *nsk;
 
 		sk = req->rsk_listener;
-		if (likely(sk->sk_state == DCCP_LISTEN)) {
-			nsk = dccp_check_req(sk, skb, req);
-		} else {
+		if (unlikely(sk->sk_state != DCCP_LISTEN)) {
 			inet_csk_reqsk_queue_drop_and_put(sk, req);
 			goto lookup;
 		}
+		sock_hold(sk);
+		nsk = dccp_check_req(sk, skb, req);
 		if (!nsk) {
 			reqsk_put(req);
-			goto discard_it;
+			goto discard_and_relse;
 		}
 		if (nsk == sk) {
-			sock_hold(sk);
 			reqsk_put(req);
 		} else if (dccp_child_process(sk, nsk, skb)) {
 			dccp_v6_ctl_send_reset(sk, skb);
-			goto discard_it;
+			goto discard_and_relse;
 		} else {
+			sock_put(sk);
 			return 0;
 		}
 	}
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 46b9c88..6414891 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -789,14 +789,16 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req,
 	reqsk_put(req);
 }
 
-void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req,
-			      struct sock *child)
+struct sock *inet_csk_reqsk_queue_add(struct sock *sk,
+				      struct request_sock *req,
+				      struct sock *child)
 {
 	struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
 
 	spin_lock(&queue->rskq_lock);
 	if (unlikely(sk->sk_state != TCP_LISTEN)) {
 		inet_child_forget(sk, req, child);
+		child = NULL;
 	} else {
 		req->sk = child;
 		req->dl_next = NULL;
@@ -808,6 +810,7 @@ void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req,
 		sk_acceptq_added(sk);
 	}
 	spin_unlock(&queue->rskq_lock);
+	return child;
 }
 EXPORT_SYMBOL(inet_csk_reqsk_queue_add);
 
@@ -817,11 +820,8 @@ struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child,
 	if (own_req) {
 		inet_csk_reqsk_queue_drop(sk, req);
 		reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req);
-		inet_csk_reqsk_queue_add(sk, req, child);
-		/* Warning: caller must not call reqsk_put(req);
-		 * child stole last reference on it.
-		 */
-		return child;
+		if (inet_csk_reqsk_queue_add(sk, req, child))
+			return child;
 	}
 	/* Too bad, another child took ownership of the request, undo. */
 	bh_unlock_sock(child);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index bfcddee..8c7e631 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1594,30 +1594,30 @@ process:
 
 	if (sk->sk_state == TCP_NEW_SYN_RECV) {
 		struct request_sock *req = inet_reqsk(sk);
-		struct sock *nsk = NULL;
+		struct sock *nsk;
 
 		sk = req->rsk_listener;
 		if (unlikely(tcp_v4_inbound_md5_hash(sk, skb))) {
 			reqsk_put(req);
 			goto discard_it;
 		}
-		if (likely(sk->sk_state == TCP_LISTEN)) {
-			nsk = tcp_check_req(sk, skb, req, false);
-		} else {
+		if (unlikely(sk->sk_state != TCP_LISTEN)) {
 			inet_csk_reqsk_queue_drop_and_put(sk, req);
 			goto lookup;
 		}
+		sock_hold(sk);
+		nsk = tcp_check_req(sk, skb, req, false);
 		if (!nsk) {
 			reqsk_put(req);
-			goto discard_it;
+			goto discard_and_relse;
 		}
 		if (nsk == sk) {
-			sock_hold(sk);
 			reqsk_put(req);
 		} else if (tcp_child_process(sk, nsk, skb)) {
 			tcp_v4_send_reset(nsk, skb);
-			goto discard_it;
+			goto discard_and_relse;
 		} else {
+			sock_put(sk);
 			return 0;
 		}
 	}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index aea071e..b8d4056 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1388,7 +1388,7 @@ process:
 
 	if (sk->sk_state == TCP_NEW_SYN_RECV) {
 		struct request_sock *req = inet_reqsk(sk);
-		struct sock *nsk = NULL;
+		struct sock *nsk;
 
 		sk = req->rsk_listener;
 		tcp_v6_fill_cb(skb, hdr, th);
@@ -1396,24 +1396,24 @@ process:
 			reqsk_put(req);
 			goto discard_it;
 		}
-		if (likely(sk->sk_state == TCP_LISTEN)) {
-			nsk = tcp_check_req(sk, skb, req, false);
-		} else {
+		if (unlikely(sk->sk_state != TCP_LISTEN)) {
 			inet_csk_reqsk_queue_drop_and_put(sk, req);
 			goto lookup;
 		}
+		sock_hold(sk);
+		nsk = tcp_check_req(sk, skb, req, false);
 		if (!nsk) {
 			reqsk_put(req);
-			goto discard_it;
+			goto discard_and_relse;
 		}
 		if (nsk == sk) {
-			sock_hold(sk);
 			reqsk_put(req);
 			tcp_v6_restore_cb(skb);
 		} else if (tcp_child_process(sk, nsk, skb)) {
 			tcp_v6_send_reset(nsk, skb);
-			goto discard_it;
+			goto discard_and_relse;
 		} else {
+			sock_put(sk);
 			return 0;
 		}
 	}
-- 
2.1.0


From 21f96ea490128efda867db9e12de77a77981eb7c Mon Sep 17 00:00:00 2001
From: Phil Sutter <phil@nwl.cc>
Date: Wed, 17 Feb 2016 15:37:43 +0100
Subject: [PATCH 43/47] IFF_NO_QUEUE: Fix for drivers not calling ether_setup()

[ Upstream commit a813104d923339144078939175faf4e66aca19b4 ]

My implementation around IFF_NO_QUEUE driver flag assumed that leaving
tx_queue_len untouched (specifically: not setting it to zero) by drivers
would make it possible to assign a regular qdisc to them without having
to worry about setting tx_queue_len to a useful value. This was only
partially true: I overlooked that some drivers don't call ether_setup()
and therefore not initialize tx_queue_len to the default value of 1000.
Consequently, removing the workarounds in place for that case in qdisc
implementations which cared about it (namely, pfifo, bfifo, gred, htb,
plug and sfb) leads to problems with these specific interface types and
qdiscs.

Luckily, there's already a sanitization point for drivers setting
tx_queue_len to zero, which can be reused to assign the fallback value
most qdisc implementations used, which is 1.

Fixes: 348e3435cbefa ("net: sched: drop all special handling of tx_queue_len == 0")
Tested-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 7dc137f..9efbdb3 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7128,8 +7128,10 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM;
 	setup(dev);
 
-	if (!dev->tx_queue_len)
+	if (!dev->tx_queue_len) {
 		dev->priv_flags |= IFF_NO_QUEUE;
+		dev->tx_queue_len = 1;
+	}
 
 	dev->num_tx_queues = txqs;
 	dev->real_num_tx_queues = txqs;
-- 
2.1.0


From 3405709a2458bd74386630981b23bbe4f152f7e2 Mon Sep 17 00:00:00 2001
From: Anton Protopopov <a.s.protopopov@gmail.com>
Date: Tue, 16 Feb 2016 21:43:16 -0500
Subject: [PATCH 44/47] rtnl: RTM_GETNETCONF: fix wrong return value

[ Upstream commit a97eb33ff225f34a8124774b3373fd244f0e83ce ]

An error response from a RTM_GETNETCONF request can return the positive
error value EINVAL in the struct nlmsgerr that can mislead userspace.

Signed-off-by: Anton Protopopov <a.s.protopopov@gmail.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/devinet.c  | 2 +-
 net/ipv6/addrconf.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index cebd9d3..f6303b1 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1847,7 +1847,7 @@ static int inet_netconf_get_devconf(struct sk_buff *in_skb,
 	if (err < 0)
 		goto errout;
 
-	err = EINVAL;
+	err = -EINVAL;
 	if (!tb[NETCONFA_IFINDEX])
 		goto errout;
 
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 828ab28..e8d3da0 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -583,7 +583,7 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb,
 	if (err < 0)
 		goto errout;
 
-	err = EINVAL;
+	err = -EINVAL;
 	if (!tb[NETCONFA_IFINDEX])
 		goto errout;
 
-- 
2.1.0


From 7bb4e9fb668efb3ccac5308ad53e77e31be84a16 Mon Sep 17 00:00:00 2001
From: Insu Yun <wuninsu@gmail.com>
Date: Wed, 17 Feb 2016 11:47:35 -0500
Subject: [PATCH 45/47] tipc: unlock in error path

[ Upstream commit b53ce3e7d407aa4196877a48b8601181162ab158 ]

tipc_bcast_unlock need to be unlocked in error path.

Signed-off-by: Insu Yun <wuninsu@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/bcast.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c
index 9dc239d..92e367a 100644
--- a/net/tipc/bcast.c
+++ b/net/tipc/bcast.c
@@ -399,8 +399,10 @@ int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg)
 
 	hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family,
 			  NLM_F_MULTI, TIPC_NL_LINK_GET);
-	if (!hdr)
+	if (!hdr) {
+		tipc_bcast_unlock(net);
 		return -EMSGSIZE;
+	}
 
 	attrs = nla_nest_start(msg->skb, TIPC_NLA_LINK);
 	if (!attrs)
-- 
2.1.0


From 94405f52f00d5cea3e612251df468c39afa0a690 Mon Sep 17 00:00:00 2001
From: "Dmitry V. Levin" <ldv@altlinux.org>
Date: Fri, 19 Feb 2016 04:27:48 +0300
Subject: [PATCH 46/47] unix_diag: fix incorrect sign extension in
 unix_lookup_by_ino

[ Upstream commit b5f0549231ffb025337be5a625b0ff9f52b016f0 ]

The value passed by unix_diag_get_exact to unix_lookup_by_ino has type
__u32, but unix_lookup_by_ino's argument ino has type int, which is not
a problem yet.
However, when ino is compared with sock_i_ino return value of type
unsigned long, ino is sign extended to signed long, and this results
to incorrect comparison on 64-bit architectures for inode numbers
greater than INT_MAX.

This bug was found by strace test suite.

Fixes: 5d3cae8bc39d ("unix_diag: Dumping exact socket core")
Signed-off-by: Dmitry V. Levin <ldv@altlinux.org>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/diag.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/unix/diag.c b/net/unix/diag.c
index c512f64..4d96797 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -220,7 +220,7 @@ done:
 	return skb->len;
 }
 
-static struct sock *unix_lookup_by_ino(int ino)
+static struct sock *unix_lookup_by_ino(unsigned int ino)
 {
 	int i;
 	struct sock *sk;
-- 
2.1.0


From 7175e22c21a1a420ea72caca518146f43ec4e29e Mon Sep 17 00:00:00 2001
From: Neil Horman <nhorman@tuxdriver.com>
Date: Thu, 18 Feb 2016 16:10:57 -0500
Subject: [PATCH 47/47] sctp: Fix port hash table size computation

[ Upstream commit d9749fb5942f51555dc9ce1ac0dbb1806960a975 ]

Dmitry Vyukov noted recently that the sctp_port_hashtable had an error in
its size computation, observing that the current method never guaranteed
that the hashsize (measured in number of entries) would be a power of two,
which the input hash function for that table requires.  The root cause of
the problem is that two values need to be computed (one, the allocation
order of the storage requries, as passed to __get_free_pages, and two the
number of entries for the hash table).  Both need to be ^2, but for
different reasons, and the existing code is simply computing one order
value, and using it as the basis for both, which is wrong (i.e. it assumes
that ((1<<order)*PAGE_SIZE)/sizeof(bucket) is still ^2 when its not).

To fix this, we change the logic slightly.  We start by computing a goal
allocation order (which is limited by the maximum size hash table we want
to support.  Then we attempt to allocate that size table, decreasing the
order until a successful allocation is made.  Then, with the resultant
successful order we compute the number of buckets that hash table supports,
which we then round down to the nearest power of two, giving us the number
of entries the table actually supports.

I've tested this locally here, using non-debug and spinlock-debug kernels,
and the number of entries in the hashtable consistently work out to be
powers of two in all cases.

Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
CC: Dmitry Vyukov <dvyukov@google.com>
CC: Vladislav Yasevich <vyasevich@gmail.com>
CC: "David S. Miller" <davem@davemloft.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/protocol.c | 43 ++++++++++++++++++++++++++++++++++++-------
 1 file changed, 36 insertions(+), 7 deletions(-)

diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 3d9ea9a..8b4ff31 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -60,6 +60,8 @@
 #include <net/inet_common.h>
 #include <net/inet_ecn.h>
 
+#define MAX_SCTP_PORT_HASH_ENTRIES (64 * 1024)
+
 /* Global data structures. */
 struct sctp_globals sctp_globals __read_mostly;
 
@@ -1352,6 +1354,8 @@ static __init int sctp_init(void)
 	unsigned long limit;
 	int max_share;
 	int order;
+	int num_entries;
+	int max_entry_order;
 
 	sock_skb_cb_check_size(sizeof(struct sctp_ulpevent));
 
@@ -1404,14 +1408,24 @@ static __init int sctp_init(void)
 
 	/* Size and allocate the association hash table.
 	 * The methodology is similar to that of the tcp hash tables.
+	 * Though not identical.  Start by getting a goal size
 	 */
 	if (totalram_pages >= (128 * 1024))
 		goal = totalram_pages >> (22 - PAGE_SHIFT);
 	else
 		goal = totalram_pages >> (24 - PAGE_SHIFT);
 
-	for (order = 0; (1UL << order) < goal; order++)
-		;
+	/* Then compute the page order for said goal */
+	order = get_order(goal);
+
+	/* Now compute the required page order for the maximum sized table we
+	 * want to create
+	 */
+	max_entry_order = get_order(MAX_SCTP_PORT_HASH_ENTRIES *
+				    sizeof(struct sctp_bind_hashbucket));
+
+	/* Limit the page order by that maximum hash table size */
+	order = min(order, max_entry_order);
 
 	do {
 		sctp_assoc_hashsize = (1UL << order) * PAGE_SIZE /
@@ -1445,20 +1459,35 @@ static __init int sctp_init(void)
 		INIT_HLIST_HEAD(&sctp_ep_hashtable[i].chain);
 	}
 
-	/* Allocate and initialize the SCTP port hash table.  */
+	/* Allocate and initialize the SCTP port hash table.
+	 * Note that order is initalized to start at the max sized
+	 * table we want to support.  If we can't get that many pages
+	 * reduce the order and try again
+	 */
 	do {
-		sctp_port_hashsize = (1UL << order) * PAGE_SIZE /
-					sizeof(struct sctp_bind_hashbucket);
-		if ((sctp_port_hashsize > (64 * 1024)) && order > 0)
-			continue;
 		sctp_port_hashtable = (struct sctp_bind_hashbucket *)
 			__get_free_pages(GFP_ATOMIC|__GFP_NOWARN, order);
 	} while (!sctp_port_hashtable && --order > 0);
+
 	if (!sctp_port_hashtable) {
 		pr_err("Failed bind hash alloc\n");
 		status = -ENOMEM;
 		goto err_bhash_alloc;
 	}
+
+	/* Now compute the number of entries that will fit in the
+	 * port hash space we allocated
+	 */
+	num_entries = (1UL << order) * PAGE_SIZE /
+		      sizeof(struct sctp_bind_hashbucket);
+
+	/* And finish by rounding it down to the nearest power of two
+	 * this wastes some memory of course, but its needed because
+	 * the hash function operates based on the assumption that
+	 * that the number of entries is a power of two
+	 */
+	sctp_port_hashsize = rounddown_pow_of_two(num_entries);
+
 	for (i = 0; i < sctp_port_hashsize; i++) {
 		spin_lock_init(&sctp_port_hashtable[i].lock);
 		INIT_HLIST_HEAD(&sctp_port_hashtable[i].chain);
-- 
2.1.0

Re: [PATCHES] Networking

[Greg KH]

On Mon, Feb 29, 2016 at 04:56:15PM -0500, David Miller wrote:
> 
> Please queue up the following bug fixes for 4.1.x and 4.4.x -stable,
> respectively.

All now applied for 4.4.y, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 95 bytes --]


Please queue up the following bug fixes for 4.1, 4.4, and 4.5 -stable,
respectively.

Thanks!

[-- Attachment #2: net_41.mbox --]
[-- Type: Application/Octet-Stream, Size: 90994 bytes --]

From 0453a88450c9f076daafffbb79344cf68f2c6a4a Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Date: Sun, 21 Feb 2016 10:12:39 +0300
Subject: [PATCH 01/37] tcp: convert cached rtt from usec to jiffies when
 feeding initial rto

[ Upstream commit 9bdfb3b79e61c60e1a3e2dc05ad164528afa6b8a ]

Currently it's converted into msecs, thus HZ=1000 intact.

Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Fixes: 740b0f1841f6 ("tcp: switch rtt estimations to usec resolution")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_metrics.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index a51d63a..9c840c5 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -566,7 +566,7 @@ reset:
 	 */
 	if (crtt > tp->srtt_us) {
 		/* Set RTO like tcp_rtt_estimator(), but from cached RTT. */
-		crtt /= 8 * USEC_PER_MSEC;
+		crtt /= 8 * USEC_PER_SEC / HZ;
 		inet_csk(sk)->icsk_rto = crtt + max(2 * crtt, tcp_rto_min(sk));
 	} else if (tp->srtt_us == 0) {
 		/* RFC6298: 5.7 We've failed to get a valid RTT sample from
-- 
2.1.0


From ea5e0a1c25b1d6110fdc9d454faadc14e9f0534f Mon Sep 17 00:00:00 2001
From: Bernie Harris <bernie.harris@alliedtelesis.co.nz>
Date: Mon, 22 Feb 2016 12:58:05 +1300
Subject: [PATCH 02/37] tunnel: Clear IPCB(skb)->opt before dst_link_failure
 called

[ Upstream commit 5146d1f151122e868e594c7b45115d64825aee5f ]

IPCB may contain data from previous layers (in the observed case the
qdisc layer). In the observed scenario, the data was misinterpreted as
ip header options, which later caused the ihl to be set to an invalid
value (<5). This resulted in an infinite loop in the mips implementation
of ip_fast_csum.

This patch clears IPCB(skb)->opt before dst_link_failure can be called for
various types of tunnels. This change only applies to encapsulated ipv4
packets.

The code introduced in 11c21a30 which clears all of IPCB has been removed
to be consistent with these changes, and instead the opt field is cleared
unconditionally in ip_tunnel_xmit. The change in ip_tunnel_xmit applies to
SIT, GRE, and IPIP tunnels.

The relevant vti, l2tp, and pptp functions already contain similar code for
clearing the IPCB.

Signed-off-by: Bernie Harris <bernie.harris@alliedtelesis.co.nz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_tunnel.c  | 3 ++-
 net/ipv4/udp_tunnel.c | 2 ++
 net/ipv6/ip6_gre.c    | 2 ++
 net/ipv6/ip6_tunnel.c | 2 ++
 4 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 626d9e5..35080a7 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -652,6 +652,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
 	connected = (tunnel->parms.iph.daddr != 0);
 
+	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+
 	dst = tnl_params->daddr;
 	if (dst == 0) {
 		/* NBMA tunnel */
@@ -749,7 +751,6 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 				tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
 			tunnel->err_count--;
 
-			memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
 			dst_link_failure(skb);
 		} else
 			tunnel->err_count = 0;
diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c
index 6bb98cc..7b534ac 100644
--- a/net/ipv4/udp_tunnel.c
+++ b/net/ipv4/udp_tunnel.c
@@ -90,6 +90,8 @@ int udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb,
 	uh->source = src_port;
 	uh->len = htons(skb->len);
 
+	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+
 	udp_set_csum(nocheck, skb, src, dst, skb->len);
 
 	return iptunnel_xmit(sk, rt, skb, src, dst, IPPROTO_UDP,
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 76be7d3..b1311da 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -783,6 +783,8 @@ static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev)
 	__u32 mtu;
 	int err;
 
+	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+
 	if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
 		encap_limit = t->parms.encap_limit;
 
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 5cafd92..6fd0f96 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1124,6 +1124,8 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	u8 tproto;
 	int err;
 
+	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+
 	tproto = ACCESS_ONCE(t->parms.proto);
 	if (tproto != IPPROTO_IPIP && tproto != 0)
 		return -1;
-- 
2.1.0


From 4dd9a3e85d48acfbbfca991adb49a716f04f443c Mon Sep 17 00:00:00 2001
From: Diego Viola <diego.viola@gmail.com>
Date: Tue, 23 Feb 2016 12:04:04 -0300
Subject: [PATCH 03/37] net: jme: fix suspend/resume on JMC260

[ Upstream commit ee50c130c82175eaa0820c96b6d3763928af2241 ]

The JMC260 network card fails to suspend/resume because the call to
jme_start_irq() was too early, moving the call to jme_start_irq() after
the call to jme_reset_link() makes it work.

Prior this change suspend/resume would fail unless /sys/power/pm_async=0
was explicitly specified.

Relevant bug report: https://bugzilla.kernel.org/show_bug.cgi?id=112351

Signed-off-by: Diego Viola <diego.viola@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/jme.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c
index 6e9a792..32d240b 100644
--- a/drivers/net/ethernet/jme.c
+++ b/drivers/net/ethernet/jme.c
@@ -3316,13 +3316,14 @@ jme_resume(struct device *dev)
 		jme_reset_phy_processor(jme);
 	jme_phy_calibration(jme);
 	jme_phy_setEA(jme);
-	jme_start_irq(jme);
 	netif_device_attach(netdev);
 
 	atomic_inc(&jme->link_changing);
 
 	jme_reset_link(jme);
 
+	jme_start_irq(jme);
+
 	return 0;
 }
 
-- 
2.1.0


From 6ecc2f6118e0e11c14b2a008f3cb14f66ada325a Mon Sep 17 00:00:00 2001
From: Stefan Wahren <stefan.wahren@i2se.com>
Date: Tue, 23 Feb 2016 19:23:23 +0000
Subject: [PATCH 04/37] net: qca_spi: Don't clear IFF_BROADCAST

[ Upstream commit 2b70bad23c89b121a3e4a00f8968d14ebb78887d ]

Currently qcaspi_netdev_setup accidentally clears IFF_BROADCAST.
So fix this by keeping the flags from ether_setup.

Reported-by: Michael Heimpold <michael.heimpold@i2se.com>
Signed-off-by: Stefan Wahren <stefan.wahren@i2se.com>
Fixes: 291ab06ecf67 (net: qualcomm: new Ethernet over SPI driver for QCA7000)
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qualcomm/qca_spi.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c
index 97e4df9..412715c 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.c
+++ b/drivers/net/ethernet/qualcomm/qca_spi.c
@@ -811,7 +811,6 @@ qcaspi_netdev_setup(struct net_device *dev)
 	dev->netdev_ops = &qcaspi_netdev_ops;
 	qcaspi_set_ethtool_ops(dev);
 	dev->watchdog_timeo = QCASPI_TX_TIMEOUT;
-	dev->flags = IFF_MULTICAST;
 	dev->tx_queue_len = 100;
 
 	qca = netdev_priv(dev);
-- 
2.1.0


From 474072364f93409b33fd5ed0da04fea16dd1685a Mon Sep 17 00:00:00 2001
From: Stefan Wahren <stefan.wahren@i2se.com>
Date: Tue, 23 Feb 2016 19:23:24 +0000
Subject: [PATCH 05/37] net: qca_spi: clear IFF_TX_SKB_SHARING

[ Upstream commit a4690afeb0d2d7ba4d60dfa98a89f3bb1ce60ecd ]

ether_setup sets IFF_TX_SKB_SHARING but this is not supported by
qca_spi as it modifies the skb on xmit.

Signed-off-by: Stefan Wahren <stefan.wahren@i2se.com>
Fixes: 291ab06ecf67 (net: qualcomm: new Ethernet over SPI driver for QCA7000)
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qualcomm/qca_spi.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c
index 412715c..cba4186 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.c
+++ b/drivers/net/ethernet/qualcomm/qca_spi.c
@@ -811,6 +811,7 @@ qcaspi_netdev_setup(struct net_device *dev)
 	dev->netdev_ops = &qcaspi_netdev_ops;
 	qcaspi_set_ethtool_ops(dev);
 	dev->watchdog_timeo = QCASPI_TX_TIMEOUT;
+	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	dev->tx_queue_len = 100;
 
 	qca = netdev_priv(dev);
-- 
2.1.0


From 11e1ec0b421ea1506947dae8b99624c87528c20c Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 28 Feb 2016 10:03:51 +0800
Subject: [PATCH 06/37] sctp: lack the check for ports in sctp_v6_cmp_addr

[ Upstream commit 40b4f0fd74e46c017814618d67ec9127ff20f157 ]

As the member .cmp_addr of sctp_af_inet6, sctp_v6_cmp_addr should also check
the port of addresses, just like sctp_v4_cmp_addr, cause it's invoked by
sctp_cmp_addr_exact().

Now sctp_v6_cmp_addr just check the port when two addresses have different
family, and lack the port check for two ipv6 addresses. that will make
sctp_hash_cmp() cannot work well.

so fix it by adding ports comparison in sctp_v6_cmp_addr().

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ipv6.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 3267a5c..18361cb 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -519,6 +519,8 @@ static int sctp_v6_cmp_addr(const union sctp_addr *addr1,
 		}
 		return 0;
 	}
+	if (addr1->v6.sin6_port != addr2->v6.sin6_port)
+		return 0;
 	if (!ipv6_addr_equal(&addr1->v6.sin6_addr, &addr2->v6.sin6_addr))
 		return 0;
 	/* If this is a linklocal address, compare the scope_id. */
-- 
2.1.0


From 7b749fabbb65e2b1b41a3b457fa4445fe9f7dc85 Mon Sep 17 00:00:00 2001
From: Benjamin Poirier <bpoirier@suse.com>
Date: Mon, 29 Feb 2016 15:03:33 -0800
Subject: [PATCH 07/37] mld, igmp: Fix reserved tailroom calculation

[ Upstream commit 1837b2e2bcd23137766555a63867e649c0b637f0 ]

The current reserved_tailroom calculation fails to take hlen and tlen into
account.

skb:
[__hlen__|__data____________|__tlen___|__extra__]
^                                               ^
head                                            skb_end_offset

In this representation, hlen + data + tlen is the size passed to alloc_skb.
"extra" is the extra space made available in __alloc_skb because of
rounding up by kmalloc. We can reorder the representation like so:

[__hlen__|__data____________|__extra__|__tlen___]
^                                               ^
head                                            skb_end_offset

The maximum space available for ip headers and payload without
fragmentation is min(mtu, data + extra). Therefore,
reserved_tailroom
= data + extra + tlen - min(mtu, data + extra)
= skb_end_offset - hlen - min(mtu, skb_end_offset - hlen - tlen)
= skb_tailroom - min(mtu, skb_tailroom - tlen) ; after skb_reserve(hlen)

Compare the second line to the current expression:
reserved_tailroom = skb_end_offset - min(mtu, skb_end_offset)
and we can see that hlen and tlen are not taken into account.

The min() in the third line can be expanded into:
if mtu < skb_tailroom - tlen:
	reserved_tailroom = skb_tailroom - mtu
else:
	reserved_tailroom = tlen

Depending on hlen, tlen, mtu and the number of multicast address records,
the current code may output skbs that have less tailroom than
dev->needed_tailroom or it may output more skbs than needed because not all
space available is used.

Fixes: 4c672e4b ("ipv6: mld: fix add_grhead skb_over_panic for devs with large MTUs")
Signed-off-by: Benjamin Poirier <bpoirier@suse.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 24 ++++++++++++++++++++++++
 net/ipv4/igmp.c        |  3 +--
 net/ipv6/mcast.c       |  3 +--
 3 files changed, 26 insertions(+), 4 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 6633b0c..ca2e26a 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1781,6 +1781,30 @@ static inline void skb_reserve(struct sk_buff *skb, int len)
 	skb->tail += len;
 }
 
+/**
+ *	skb_tailroom_reserve - adjust reserved_tailroom
+ *	@skb: buffer to alter
+ *	@mtu: maximum amount of headlen permitted
+ *	@needed_tailroom: minimum amount of reserved_tailroom
+ *
+ *	Set reserved_tailroom so that headlen can be as large as possible but
+ *	not larger than mtu and tailroom cannot be smaller than
+ *	needed_tailroom.
+ *	The required headroom should already have been reserved before using
+ *	this function.
+ */
+static inline void skb_tailroom_reserve(struct sk_buff *skb, unsigned int mtu,
+					unsigned int needed_tailroom)
+{
+	SKB_LINEAR_ASSERT(skb);
+	if (mtu < skb_tailroom(skb) - needed_tailroom)
+		/* use at most mtu */
+		skb->reserved_tailroom = skb_tailroom(skb) - mtu;
+	else
+		/* use up to all available space */
+		skb->reserved_tailroom = needed_tailroom;
+}
+
 #define ENCAP_TYPE_ETHER	0
 #define ENCAP_TYPE_IPPROTO	1
 
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index a3a697f..218abf9 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -353,9 +353,8 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu)
 	skb_dst_set(skb, &rt->dst);
 	skb->dev = dev;
 
-	skb->reserved_tailroom = skb_end_offset(skb) -
-				 min(mtu, skb_end_offset(skb));
 	skb_reserve(skb, hlen);
+	skb_tailroom_reserve(skb, mtu, tlen);
 
 	skb_reset_network_header(skb);
 	pip = ip_hdr(skb);
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 41e3b5e..9a63110 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1574,9 +1574,8 @@ static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu)
 		return NULL;
 
 	skb->priority = TC_PRIO_CONTROL;
-	skb->reserved_tailroom = skb_end_offset(skb) -
-				 min(mtu, skb_end_offset(skb));
 	skb_reserve(skb, hlen);
+	skb_tailroom_reserve(skb, mtu, tlen);
 
 	if (__ipv6_get_lladdr(idev, &addr_buf, IFA_F_TENTATIVE)) {
 		/* <draft-ietf-magma-mld-source-05.txt>:
-- 
2.1.0


From 12b54c913ce847e777fd1b07803936ebd5d367c2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Tue, 1 Mar 2016 14:31:02 +0100
Subject: [PATCH 08/37] qmi_wwan: add Sierra Wireless EM74xx device ID
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit bf13c94ccb33c3182efc92ce4989506a0f541243 ]

The MC74xx and EM74xx modules use different IDs by default, according
to the Lenovo EM7455 driver for Windows.

Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index cffb252..8677c6a 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -767,8 +767,10 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1199, 0x9061, 8)},	/* Sierra Wireless Modem */
 	{QMI_FIXED_INTF(0x1199, 0x9070, 8)},	/* Sierra Wireless MC74xx/EM74xx */
 	{QMI_FIXED_INTF(0x1199, 0x9070, 10)},	/* Sierra Wireless MC74xx/EM74xx */
-	{QMI_FIXED_INTF(0x1199, 0x9071, 8)},	/* Sierra Wireless MC74xx/EM74xx */
-	{QMI_FIXED_INTF(0x1199, 0x9071, 10)},	/* Sierra Wireless MC74xx/EM74xx */
+	{QMI_FIXED_INTF(0x1199, 0x9071, 8)},	/* Sierra Wireless MC74xx */
+	{QMI_FIXED_INTF(0x1199, 0x9071, 10)},	/* Sierra Wireless MC74xx */
+	{QMI_FIXED_INTF(0x1199, 0x9079, 8)},	/* Sierra Wireless EM74xx */
+	{QMI_FIXED_INTF(0x1199, 0x9079, 10)},	/* Sierra Wireless EM74xx */
 	{QMI_FIXED_INTF(0x1bbb, 0x011e, 4)},	/* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */
 	{QMI_FIXED_INTF(0x1bbb, 0x0203, 2)},	/* Alcatel L800MA */
 	{QMI_FIXED_INTF(0x2357, 0x0201, 4)},	/* TP-LINK HSUPA Modem MA180 */
-- 
2.1.0


From d84532d1e4d977eda55c59b505b18a285db4bb0b Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 1 Mar 2016 16:15:16 +0100
Subject: [PATCH 09/37] ipv6: re-enable fragment header matching in
 ipv6_find_hdr

[ Upstream commit 5d150a985520bbe3cb2aa1ceef24a7e32f20c15f ]

When ipv6_find_hdr is used to find a fragment header
(caller specifies target NEXTHDR_FRAGMENT) we erronously return
-ENOENT for all fragments with nonzero offset.

Before commit 9195bb8e381d, when target was specified, we did not
enter the exthdr walk loop as nexthdr == target so this used to work.

Now we do (so we can skip empty route headers). When we then stumble upon
a frag with nonzero frag_off we must return -ENOENT ("header not found")
only if the caller did not specifically request NEXTHDR_FRAGMENT.

This allows nfables exthdr expression to match ipv6 fragments, e.g. via

nft add rule ip6 filter input frag frag-off gt 0

Fixes: 9195bb8e381d ("ipv6: improve ipv6_find_hdr() to skip empty routing headers")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/exthdrs_core.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c
index 5c5d23e..9508a20 100644
--- a/net/ipv6/exthdrs_core.c
+++ b/net/ipv6/exthdrs_core.c
@@ -257,7 +257,11 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
 						*fragoff = _frag_off;
 					return hp->nexthdr;
 				}
-				return -ENOENT;
+				if (!found)
+					return -ENOENT;
+				if (fragoff)
+					*fragoff = _frag_off;
+				break;
 			}
 			hdrlen = 8;
 		} else if (nexthdr == NEXTHDR_AUTH) {
-- 
2.1.0


From bec097ac90ae1f6e5c935810c2c6d561c02c42a2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Thu, 3 Mar 2016 22:20:53 +0100
Subject: [PATCH 10/37] cdc_ncm: toggle altsetting to force reset before setup
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 48906f62c96cc2cd35753e59310cb70eb08cc6a5 ]

Some devices will silently fail setup unless they are reset first.
This is necessary even if the data interface is already in
altsetting 0, which it will be when the device is probed for the
first time.  Briefly toggling the altsetting forces a function
reset regardless of the initial state.

This fixes a setup problem observed on a number of Huawei devices,
appearing to operate in NTB-32 mode even if we explicitly set them
to NTB-16 mode.

Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ncm.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 0b481c3..5db25e4 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -843,7 +843,11 @@ advance:
 
 	iface_no = ctx->data->cur_altsetting->desc.bInterfaceNumber;
 
-	/* reset data interface */
+	/* Reset data interface. Some devices will not reset properly
+	 * unless they are configured first.  Toggle the altsetting to
+	 * force a reset
+	 */
+	usb_set_interface(dev->udev, iface_no, data_altsetting);
 	temp = usb_set_interface(dev->udev, iface_no, 0);
 	if (temp) {
 		dev_dbg(&intf->dev, "set interface failed\n");
-- 
2.1.0


From 5189276fe9834fe6bf5eba31d9d45ed7f8409d8e Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.com>
Date: Mon, 7 Mar 2016 11:31:10 +0100
Subject: [PATCH 11/37] usbnet: cleanup after bind() in probe()

[ Upstream commit 1666984c8625b3db19a9abc298931d35ab7bc64b ]

In case bind() works, but a later error forces bailing
in probe() in error cases work and a timer may be scheduled.
They must be killed. This fixes an error case related to
the double free reported in
http://www.spinics.net/lists/netdev/msg367669.html
and needs to go on top of Linus' fix to cdc-ncm.

Signed-off-by: Oliver Neukum <ONeukum@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/usbnet.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index e049857..edbb2f3 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -1754,6 +1754,13 @@ out3:
 	if (info->unbind)
 		info->unbind (dev, udev);
 out1:
+	/* subdrivers must undo all they did in bind() if they
+	 * fail it, but we may fail later and a deferred kevent
+	 * may trigger an error resubmitting itself and, worse,
+	 * schedule a timer. So we kill it all just in case.
+	 */
+	cancel_work_sync(&dev->kevent);
+	del_timer_sync(&dev->delay);
 	free_netdev(net);
 out:
 	return status;
-- 
2.1.0


From 76b5ae98f50d069862cfb874fc10386d869ef1a8 Mon Sep 17 00:00:00 2001
From: Bill Sommerfeld <wsommerfeld@google.com>
Date: Fri, 4 Mar 2016 14:47:21 -0800
Subject: [PATCH 12/37] udp6: fix UDP/IPv6 encap resubmit path

[ Upstream commit 59dca1d8a6725a121dae6c452de0b2611d5865dc ]

IPv4 interprets a negative return value from a protocol handler as a
request to redispatch to a new protocol.  In contrast, IPv6 interprets a
negative value as an error, and interprets a positive value as a request
for redispatch.

UDP for IPv6 was unaware of this difference.  Change __udp6_lib_rcv() to
return a positive value for redispatch.  Note that the socket's
encap_rcv hook still needs to return a negative value to request
dispatch, and in the case of IPv6 packets, adjust IP6CB(skb)->nhoff to
identify the byte containing the next protocol.

Signed-off-by: Bill Sommerfeld <wsommerfeld@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/udp.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 7333f35..d28b2a1 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -913,11 +913,9 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 		ret = udpv6_queue_rcv_skb(sk, skb);
 		sock_put(sk);
 
-		/* a return value > 0 means to resubmit the input, but
-		 * it wants the return to be -protocol, or 0
-		 */
+		/* a return value > 0 means to resubmit the input */
 		if (ret > 0)
-			return -ret;
+			return ret;
 
 		return 0;
 	}
-- 
2.1.0


From cb9f0a4fff910ec4438762866358d24de10d37e2 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 9 Mar 2016 21:58:32 -0500
Subject: [PATCH 13/37] net: validate variable length ll headers

[ Upstream commit 2793a23aacbd754dbbb5cb75093deb7e4103bace ]

Netdevice parameter hard_header_len is variously interpreted both as
an upper and lower bound on link layer header length. The field is
used as upper bound when reserving room at allocation, as lower bound
when validating user input in PF_PACKET.

Clarify the definition to be maximum header length. For validation
of untrusted headers, add an optional validate member to header_ops.

Allow bypassing of validation by passing CAP_SYS_RAWIO, for instance
for deliberate testing of corrupt input. In this case, pad trailing
bytes, as some device drivers expect completely initialized headers.

See also http://comments.gmane.org/gmane.linux.network/401064

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 21 ++++++++++++++++++++-
 1 file changed, 20 insertions(+), 1 deletion(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 05b9a69..6c86c7e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -265,6 +265,7 @@ struct header_ops {
 	void	(*cache_update)(struct hh_cache *hh,
 				const struct net_device *dev,
 				const unsigned char *haddr);
+	bool	(*validate)(const char *ll_header, unsigned int len);
 };
 
 /* These flag bits are private to the generic network queueing
@@ -1372,7 +1373,7 @@ enum netdev_priv_flags {
  *	@dma:		DMA channel
  *	@mtu:		Interface MTU value
  *	@type:		Interface hardware type
- *	@hard_header_len: Hardware header length
+ *	@hard_header_len: Maximum hardware header length.
  *
  *	@needed_headroom: Extra headroom the hardware may need, but not in all
  *			  cases can this be guaranteed
@@ -2416,6 +2417,24 @@ static inline int dev_parse_header(const struct sk_buff *skb,
 	return dev->header_ops->parse(skb, haddr);
 }
 
+/* ll_header must have at least hard_header_len allocated */
+static inline bool dev_validate_header(const struct net_device *dev,
+				       char *ll_header, int len)
+{
+	if (likely(len >= dev->hard_header_len))
+		return true;
+
+	if (capable(CAP_SYS_RAWIO)) {
+		memset(ll_header + len, 0, dev->hard_header_len - len);
+		return true;
+	}
+
+	if (dev->header_ops && dev->header_ops->validate)
+		return dev->header_ops->validate(ll_header, len);
+
+	return false;
+}
+
 typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr, int len);
 int register_gifconf(unsigned int family, gifconf_func_t *gifconf);
 static inline int unregister_gifconf(unsigned int family)
-- 
2.1.0


From 7d3b5b537bb26f2357cf8260b820408255e5311d Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 9 Mar 2016 21:58:33 -0500
Subject: [PATCH 14/37] ax25: add link layer header validation function

[ Upstream commit ea47781c26510e5d97f80f9aceafe9065bd5e3aa ]

As variable length protocol, AX25 fails link layer header validation
tests based on a minimum length. header_ops.validate allows protocols
to validate headers that are shorter than hard_header_len. Implement
this callback for AX25.

See also http://comments.gmane.org/gmane.linux.network/401064

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ax25/ax25_ip.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/net/ax25/ax25_ip.c b/net/ax25/ax25_ip.c
index 7c646bb..98d206b 100644
--- a/net/ax25/ax25_ip.c
+++ b/net/ax25/ax25_ip.c
@@ -229,8 +229,23 @@ netdev_tx_t ax25_ip_xmit(struct sk_buff *skb)
 }
 #endif
 
+static bool ax25_validate_header(const char *header, unsigned int len)
+{
+	ax25_digi digi;
+
+	if (!len)
+		return false;
+
+	if (header[0])
+		return true;
+
+	return ax25_addr_parse(header + 1, len - 1, NULL, NULL, &digi, NULL,
+			       NULL);
+}
+
 const struct header_ops ax25_header_ops = {
 	.create = ax25_hard_header,
+	.validate = ax25_validate_header,
 };
 
 EXPORT_SYMBOL(ax25_header_ops);
-- 
2.1.0


From 139b7e33a08abc58fb336b9bd6f384b22e6b8b25 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 9 Mar 2016 21:58:34 -0500
Subject: [PATCH 15/37] packet: validate variable length ll headers

[ Upstream commit 9ed988cd591500c040b2a6257bc68543e08ceeef ]

Replace link layer header validation check ll_header_truncate with
more generic dev_validate_header.

Validation based on hard_header_len incorrectly drops valid packets
in variable length protocols, such as AX25. dev_validate_header
calls header_ops.validate for such protocols to ensure correctness
below hard_header_len.

See also http://comments.gmane.org/gmane.linux.network/401064

Fixes 9c7077622dd9 ("packet: make packet_snd fail on len smaller than l2 header")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 37 ++++++++++++++++---------------------
 1 file changed, 16 insertions(+), 21 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index ebc39e6..68a04847 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1699,6 +1699,10 @@ retry:
 		goto retry;
 	}
 
+	if (!dev_validate_header(dev, skb->data, len)) {
+		err = -EINVAL;
+		goto out_unlock;
+	}
 	if (len > (dev->mtu + dev->hard_header_len + extra_len) &&
 	    !packet_extra_vlan_len_allowed(dev, skb)) {
 		err = -EMSGSIZE;
@@ -2109,18 +2113,6 @@ static void tpacket_destruct_skb(struct sk_buff *skb)
 	sock_wfree(skb);
 }
 
-static bool ll_header_truncated(const struct net_device *dev, int len)
-{
-	/* net device doesn't like empty head */
-	if (unlikely(len <= dev->hard_header_len)) {
-		net_warn_ratelimited("%s: packet size is too short (%d <= %d)\n",
-				     current->comm, len, dev->hard_header_len);
-		return true;
-	}
-
-	return false;
-}
-
 static void tpacket_set_protocol(const struct net_device *dev,
 				 struct sk_buff *skb)
 {
@@ -2203,19 +2195,19 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 		if (unlikely(err < 0))
 			return -EINVAL;
 	} else if (dev->hard_header_len) {
-		if (ll_header_truncated(dev, tp_len))
-			return -EINVAL;
+		int hdrlen = min_t(int, dev->hard_header_len, tp_len);
 
 		skb_push(skb, dev->hard_header_len);
-		err = skb_store_bits(skb, 0, data,
-				dev->hard_header_len);
+		err = skb_store_bits(skb, 0, data, hdrlen);
 		if (unlikely(err))
 			return err;
+		if (!dev_validate_header(dev, skb->data, hdrlen))
+			return -EINVAL;
 		if (!skb->protocol)
 			tpacket_set_protocol(dev, skb);
 
-		data += dev->hard_header_len;
-		to_write -= dev->hard_header_len;
+		data += hdrlen;
+		to_write -= hdrlen;
 	}
 
 	offset = offset_in_page(data);
@@ -2538,9 +2530,6 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		offset = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, len);
 		if (unlikely(offset < 0))
 			goto out_free;
-	} else {
-		if (ll_header_truncated(dev, len))
-			goto out_free;
 	}
 
 	/* Returns -EFAULT on error */
@@ -2548,6 +2537,12 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	if (err)
 		goto out_free;
 
+	if (sock->type == SOCK_RAW &&
+	    !dev_validate_header(dev, skb->data, len)) {
+		err = -EINVAL;
+		goto out_free;
+	}
+
 	sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags);
 
 	if (!gso_type && (len > dev->mtu + reserve + extra_len) &&
-- 
2.1.0


From 4a6095feda011d45f55507e6db65fb5a1dc0eff1 Mon Sep 17 00:00:00 2001
From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Date: Tue, 8 Mar 2016 01:36:28 +0300
Subject: [PATCH 16/37] sh_eth: fix NULL pointer dereference in
 sh_eth_ring_format()

[ Upstream commit c1b7fca65070bfadca94dd53a4e6b71cd4f69715 ]

In a low memory situation, if netdev_alloc_skb() fails on a first RX ring
loop iteration  in sh_eth_ring_format(), 'rxdesc' is still NULL.  Avoid
kernel oops by adding the 'rxdesc' check after the loop.

Reported-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/sh_eth.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 13463c4..51eff9f 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -1173,7 +1173,8 @@ static void sh_eth_ring_format(struct net_device *ndev)
 	mdp->dirty_rx = (u32) (i - mdp->num_rx_ring);
 
 	/* Mark the last entry as wrapping the ring. */
-	rxdesc->status |= cpu_to_edmac(mdp, RD_RDEL);
+	if (rxdesc)
+		rxdesc->status |= cpu_to_edmac(mdp, RD_RDEL);
 
 	memset(mdp->tx_ring, 0, tx_ringsize);
 
-- 
2.1.0


From 30bd2f7d4e5ab2605a65d55b9e6140e7ceed44c5 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Tue, 8 Mar 2016 15:18:54 -0500
Subject: [PATCH 17/37] macvtap: always pass ethernet header in linear

[ Upstream commit 8e2ad4113ce4671686740f808ff2795395c39eef ]

The stack expects link layer headers in the skb linear section.
Macvtap can create skbs with llheader in frags in edge cases:
when (IFF_VNET_HDR is off or vnet_hdr.hdr_len < ETH_HLEN) and
prepad + len > PAGE_SIZE and vnet_hdr.flags has no or bad csum.

Add checks to ensure linear is always at least ETH_HLEN.
At this point, len is already ensured to be >= ETH_HLEN.

For backwards compatiblity, rounds up short vnet_hdr.hdr_len.
This differs from tap and packet, which return an error.

Fixes b9fb9ee07e67 ("macvtap: add GSO/csum offload support")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macvtap.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 4dba5fb..2b212f3 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -710,6 +710,8 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 			macvtap16_to_cpu(q, vnet_hdr.hdr_len) : GOODCOPY_LEN;
 		if (copylen > good_linear)
 			copylen = good_linear;
+		else if (copylen < ETH_HLEN)
+			copylen = ETH_HLEN;
 		linear = copylen;
 		i = *from;
 		iov_iter_advance(&i, copylen);
@@ -719,10 +721,11 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 
 	if (!zerocopy) {
 		copylen = len;
-		if (macvtap16_to_cpu(q, vnet_hdr.hdr_len) > good_linear)
+		linear = macvtap16_to_cpu(q, vnet_hdr.hdr_len);
+		if (linear > good_linear)
 			linear = good_linear;
-		else
-			linear = macvtap16_to_cpu(q, vnet_hdr.hdr_len);
+		else if (linear < ETH_HLEN)
+			linear = ETH_HLEN;
 	}
 
 	skb = macvtap_alloc_skb(&q->sk, MACVTAP_RESERVE, copylen,
-- 
2.1.0


From 6cd2ffcb74a3a58209456c1f1dfd97af8ecf899a Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sun, 13 Mar 2016 23:28:00 -0400
Subject: [PATCH 18/37] ipv4: Don't do expensive useless work during inetdev
 destroy.

[ Upstream commit fbd40ea0180a2d328c5adc61414dc8bab9335ce2 ]

When an inetdev is destroyed, every address assigned to the interface
is removed.  And in this scenerio we do two pointless things which can
be very expensive if the number of assigned interfaces is large:

1) Address promotion.  We are deleting all addresses, so there is no
   point in doing this.

2) A full nf conntrack table purge for every address.  We only need to
   do this once, as is already caught by the existing
   masq_dev_notifier so masq_inet_event() can skip this.

Reported-by: Solar Designer <solar@openwall.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Tested-by: Cyrill Gorcunov <gorcunov@openvz.org>
---
 net/ipv4/devinet.c                          |  4 ++++
 net/ipv4/fib_frontend.c                     |  4 ++++
 net/ipv4/netfilter/nf_nat_masquerade_ipv4.c | 12 ++++++++++--
 3 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 280d46f..a57056d 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -334,6 +334,9 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
 
 	ASSERT_RTNL();
 
+	if (in_dev->dead)
+		goto no_promotions;
+
 	/* 1. Deleting primary ifaddr forces deletion all secondaries
 	 * unless alias promotion is set
 	 **/
@@ -380,6 +383,7 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
 			fib_del_ifaddr(ifa, ifa1);
 	}
 
+no_promotions:
 	/* 2. Unlink it */
 
 	*ifap = ifa1->ifa_next;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 872494e..8776636 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -876,6 +876,9 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim)
 		subnet = 1;
 	}
 
+	if (in_dev->dead)
+		goto no_promotions;
+
 	/* Deletion is more complicated than add.
 	 * We should take care of not to delete too much :-)
 	 *
@@ -951,6 +954,7 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim)
 		}
 	}
 
+no_promotions:
 	if (!(ok & BRD_OK))
 		fib_magic(RTM_DELROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim);
 	if (subnet && ifa->ifa_prefixlen < 31) {
diff --git a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
index c6eb421..ea91058 100644
--- a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
@@ -108,10 +108,18 @@ static int masq_inet_event(struct notifier_block *this,
 			   unsigned long event,
 			   void *ptr)
 {
-	struct net_device *dev = ((struct in_ifaddr *)ptr)->ifa_dev->dev;
+	struct in_device *idev = ((struct in_ifaddr *)ptr)->ifa_dev;
 	struct netdev_notifier_info info;
 
-	netdev_notifier_info_init(&info, dev);
+	/* The masq_dev_notifier will catch the case of the device going
+	 * down.  So if the inetdev is dead and being destroyed we have
+	 * no work to do.  Otherwise this is an individual address removal
+	 * and we have to perform the flush.
+	 */
+	if (idev->dead)
+		return NOTIFY_DONE;
+
+	netdev_notifier_info_init(&info, idev->dev);
 	return masq_device_event(this, event, &info);
 }
 
-- 
2.1.0


From 16ce73fe85c889df52a4d8fa4298c939ed5a28b0 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 14 Mar 2016 09:56:35 -0300
Subject: [PATCH 19/37] net: Fix use after free in the recvmmsg exit path

[ Upstream commit 34b88a68f26a75e4fded796f1a49c40f82234b7d ]

The syzkaller fuzzer hit the following use-after-free:

  Call Trace:
   [<ffffffff8175ea0e>] __asan_report_load8_noabort+0x3e/0x40 mm/kasan/report.c:295
   [<ffffffff851cc31a>] __sys_recvmmsg+0x6fa/0x7f0 net/socket.c:2261
   [<     inline     >] SYSC_recvmmsg net/socket.c:2281
   [<ffffffff851cc57f>] SyS_recvmmsg+0x16f/0x180 net/socket.c:2270
   [<ffffffff86332bb6>] entry_SYSCALL_64_fastpath+0x16/0x7a
  arch/x86/entry/entry_64.S:185

And, as Dmitry rightly assessed, that is because we can drop the
reference and then touch it when the underlying recvmsg calls return
some packets and then hit an error, which will make recvmmsg to set
sock->sk->sk_err, oops, fix it.

Reported-and-Tested-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Kostya Serebryany <kcc@google.com>
Cc: Sasha Levin <sasha.levin@oracle.com>
Fixes: a2e2725541fa ("net: Introduce recvmmsg socket syscall")
http://lkml.kernel.org/r/20160122211644.GC2470@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/socket.c | 38 +++++++++++++++++++-------------------
 1 file changed, 19 insertions(+), 19 deletions(-)

diff --git a/net/socket.c b/net/socket.c
index dcbfa86..e66e4f3 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2247,31 +2247,31 @@ int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
 			break;
 	}
 
-out_put:
-	fput_light(sock->file, fput_needed);
-
 	if (err == 0)
-		return datagrams;
+		goto out_put;
 
-	if (datagrams != 0) {
+	if (datagrams == 0) {
+		datagrams = err;
+		goto out_put;
+	}
+
+	/*
+	 * We may return less entries than requested (vlen) if the
+	 * sock is non block and there aren't enough datagrams...
+	 */
+	if (err != -EAGAIN) {
 		/*
-		 * We may return less entries than requested (vlen) if the
-		 * sock is non block and there aren't enough datagrams...
+		 * ... or  if recvmsg returns an error after we
+		 * received some datagrams, where we record the
+		 * error to return on the next call or if the
+		 * app asks about it using getsockopt(SO_ERROR).
 		 */
-		if (err != -EAGAIN) {
-			/*
-			 * ... or  if recvmsg returns an error after we
-			 * received some datagrams, where we record the
-			 * error to return on the next call or if the
-			 * app asks about it using getsockopt(SO_ERROR).
-			 */
-			sock->sk->sk_err = -err;
-		}
-
-		return datagrams;
+		sock->sk->sk_err = -err;
 	}
+out_put:
+	fput_light(sock->file, fput_needed);
 
-	return err;
+	return datagrams;
 }
 
 SYSCALL_DEFINE5(recvmmsg, int, fd, struct mmsghdr __user *, mmsg,
-- 
2.1.0


From 80be7069f5edcdf5f98fea8ef3efcc05131da318 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 14 Mar 2016 15:18:34 +0100
Subject: [PATCH 20/37] mlx4: add missing braces in verify_qp_parameters

[ Upstream commit baefd7015cdb304ce6c94f9679d0486c71954766 ]

The implementation of QP paravirtualization back in linux-3.7 included
some code that looks very dubious, and gcc-6 has grown smart enough
to warn about it:

drivers/net/ethernet/mellanox/mlx4/resource_tracker.c: In function 'verify_qp_parameters':
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c:3154:5: error: statement is indented as if it were guarded by... [-Werror=misleading-indentation]
     if (optpar & MLX4_QP_OPTPAR_ALT_ADDR_PATH) {
     ^~
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c:3144:4: note: ...this 'if' clause, but it is not
    if (slave != mlx4_master_func_num(dev))

>From looking at the context, I'm reasonably sure that the indentation
is correct but that it should have contained curly braces from the
start, as the update_gid() function in the same patch correctly does.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Fixes: 54679e148287 ("mlx4: Implement QP paravirtualization and maintain phys_pkey_cache for smp_snoop")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/resource_tracker.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index bafe218..e662ab3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -2960,7 +2960,7 @@ static int verify_qp_parameters(struct mlx4_dev *dev,
 		case QP_TRANS_RTS2RTS:
 		case QP_TRANS_SQD2SQD:
 		case QP_TRANS_SQD2RTS:
-			if (slave != mlx4_master_func_num(dev))
+			if (slave != mlx4_master_func_num(dev)) {
 				if (optpar & MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH) {
 					port = (qp_ctx->pri_path.sched_queue >> 6 & 1) + 1;
 					if (dev->caps.port_mask[port] != MLX4_PORT_TYPE_IB)
@@ -2979,6 +2979,7 @@ static int verify_qp_parameters(struct mlx4_dev *dev,
 					if (qp_ctx->alt_path.mgid_index >= num_gids)
 						return -EINVAL;
 				}
+			}
 			break;
 		default:
 			break;
-- 
2.1.0


From 3ac3a8e6e96f641dc730ec9f5822b65df677ac20 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 14 Mar 2016 15:18:35 +0100
Subject: [PATCH 21/37] farsync: fix off-by-one bug in fst_add_one

[ Upstream commit e725a66c0202b5f36c2f9d59d26a65c53bbf21f7 ]

gcc-6 finds an out of bounds access in the fst_add_one function
when calculating the end of the mmio area:

drivers/net/wan/farsync.c: In function 'fst_add_one':
drivers/net/wan/farsync.c:418:53: error: index 2 denotes an offset greater than size of 'u8[2][8192] {aka unsigned char[2][8192]}' [-Werror=array-bounds]
 #define BUF_OFFSET(X)   (BFM_BASE + offsetof(struct buf_window, X))
                                                     ^
include/linux/compiler-gcc.h:158:21: note: in definition of macro '__compiler_offsetof'
  __builtin_offsetof(a, b)
                     ^
drivers/net/wan/farsync.c:418:37: note: in expansion of macro 'offsetof'
 #define BUF_OFFSET(X)   (BFM_BASE + offsetof(struct buf_window, X))
                                     ^~~~~~~~
drivers/net/wan/farsync.c:2519:36: note: in expansion of macro 'BUF_OFFSET'
                                  + BUF_OFFSET ( txBuffer[i][NUM_TX_BUFFER][0]);
                                    ^~~~~~~~~~

The warning is correct, but not critical because this appears
to be a write-only variable that is set by each WAN driver but
never accessed afterwards.

I'm taking the minimal fix here, using the correct pointer by
pointing 'mem_end' to the last byte inside of the register area
as all other WAN drivers do, rather than the first byte outside of
it. An alternative would be to just remove the mem_end member
entirely.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wan/farsync.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wan/farsync.c b/drivers/net/wan/farsync.c
index 44541dbc..69b994f 100644
--- a/drivers/net/wan/farsync.c
+++ b/drivers/net/wan/farsync.c
@@ -2516,7 +2516,7 @@ fst_add_one(struct pci_dev *pdev, const struct pci_device_id *ent)
                 dev->mem_start   = card->phys_mem
                                  + BUF_OFFSET ( txBuffer[i][0][0]);
                 dev->mem_end     = card->phys_mem
-                                 + BUF_OFFSET ( txBuffer[i][NUM_TX_BUFFER][0]);
+                                 + BUF_OFFSET ( txBuffer[i][NUM_TX_BUFFER - 1][LEN_RX_BUFFER - 1]);
                 dev->base_addr   = card->pci_conf;
                 dev->irq         = card->irq;
 
-- 
2.1.0


From 46d120c4f55bc5864281af63c3f27a4b7993588e Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 14 Mar 2016 15:18:36 +0100
Subject: [PATCH 22/37] ath9k: fix buffer overrun for ar9287

[ Upstream commit 83d6f1f15f8cce844b0a131cbc63e444620e48b5 ]

Code that was added back in 2.6.38 has an obvious overflow
when accessing a static array, and at the time it was added
only a code comment was put in front of it as a reminder
to have it reviewed properly.

This has not happened, but gcc-6 now points to the specific
overflow:

drivers/net/wireless/ath/ath9k/eeprom.c: In function 'ath9k_hw_get_gain_boundaries_pdadcs':
drivers/net/wireless/ath/ath9k/eeprom.c:483:44: error: array subscript is above array bounds [-Werror=array-bounds]
     maxPwrT4[i] = data_9287[idxL].pwrPdg[i][4];
                   ~~~~~~~~~~~~~~~~~~~~~~~~~^~~

It turns out that the correct array length exists in the local
'intercepts' variable of this function, so we can just use that
instead of hardcoding '4', so this patch changes all three
instances to use that variable. The other two instances were
already correct, but it's more consistent this way.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Fixes: 940cd2c12ebf ("ath9k_hw: merge the ar9287 version of ath9k_hw_get_gain_boundaries_pdadcs")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wireless/ath/ath9k/eeprom.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/eeprom.c b/drivers/net/wireless/ath/ath9k/eeprom.c
index cc81482..113a43f 100644
--- a/drivers/net/wireless/ath/ath9k/eeprom.c
+++ b/drivers/net/wireless/ath/ath9k/eeprom.c
@@ -403,10 +403,9 @@ void ath9k_hw_get_gain_boundaries_pdadcs(struct ath_hw *ah,
 
 	if (match) {
 		if (AR_SREV_9287(ah)) {
-			/* FIXME: array overrun? */
 			for (i = 0; i < numXpdGains; i++) {
 				minPwrT4[i] = data_9287[idxL].pwrPdg[i][0];
-				maxPwrT4[i] = data_9287[idxL].pwrPdg[i][4];
+				maxPwrT4[i] = data_9287[idxL].pwrPdg[i][intercepts - 1];
 				ath9k_hw_fill_vpd_table(minPwrT4[i], maxPwrT4[i],
 						data_9287[idxL].pwrPdg[i],
 						data_9287[idxL].vpdPdg[i],
@@ -416,7 +415,7 @@ void ath9k_hw_get_gain_boundaries_pdadcs(struct ath_hw *ah,
 		} else if (eeprom_4k) {
 			for (i = 0; i < numXpdGains; i++) {
 				minPwrT4[i] = data_4k[idxL].pwrPdg[i][0];
-				maxPwrT4[i] = data_4k[idxL].pwrPdg[i][4];
+				maxPwrT4[i] = data_4k[idxL].pwrPdg[i][intercepts - 1];
 				ath9k_hw_fill_vpd_table(minPwrT4[i], maxPwrT4[i],
 						data_4k[idxL].pwrPdg[i],
 						data_4k[idxL].vpdPdg[i],
@@ -426,7 +425,7 @@ void ath9k_hw_get_gain_boundaries_pdadcs(struct ath_hw *ah,
 		} else {
 			for (i = 0; i < numXpdGains; i++) {
 				minPwrT4[i] = data_def[idxL].pwrPdg[i][0];
-				maxPwrT4[i] = data_def[idxL].pwrPdg[i][4];
+				maxPwrT4[i] = data_def[idxL].pwrPdg[i][intercepts - 1];
 				ath9k_hw_fill_vpd_table(minPwrT4[i], maxPwrT4[i],
 						data_def[idxL].pwrPdg[i],
 						data_def[idxL].vpdPdg[i],
-- 
2.1.0


From df8791ab3698aaf56572db876327c01a15e891d3 Mon Sep 17 00:00:00 2001
From: Dmitri Epshtein <dima@marvell.com>
Date: Sat, 12 Mar 2016 18:44:18 +0100
Subject: [PATCH 23/37] net: mvneta: enable change MAC address when interface
 is up

[ Upstream commit 928b6519afeb2a5e2dc61154380b545ed66c476a ]

Function eth_prepare_mac_addr_change() is called as part of MAC
address change. This function check if interface is running.
To enable change MAC address when interface is running:
IFF_LIVE_ADDR_CHANGE flag must be set to dev->priv_flags field

Fixes: c5aff18204da ("net: mvneta: driver for Marvell Armada 370/XP
network unit")
Cc: stable@vger.kernel.org
Signed-off-by: Dmitri Epshtein <dima@marvell.com>
Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index e07afc6..e4c0796 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -3157,7 +3157,7 @@ static int mvneta_probe(struct platform_device *pdev)
 	dev->features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO;
 	dev->hw_features |= dev->features;
 	dev->vlan_features |= dev->features;
-	dev->priv_flags |= IFF_UNICAST_FLT;
+	dev->priv_flags |= IFF_UNICAST_FLT | IFF_LIVE_ADDR_CHANGE;
 	dev->gso_max_segs = MVNETA_MAX_TSO_SEGS;
 
 	err = register_netdev(dev);
-- 
2.1.0


From 3622da12798095a568229e8c6b2bae0fd99c7ed5 Mon Sep 17 00:00:00 2001
From: Manish Chopra <manish.chopra@qlogic.com>
Date: Tue, 15 Mar 2016 07:13:45 -0400
Subject: [PATCH 24/37] qlge: Fix receive packets drop.

[ Upstream commit 2c9a266afefe137bff06bbe0fc48b4d3b3cb348c ]

When running small packets [length < 256 bytes] traffic, packets were
being dropped due to invalid data in those packets which were
delivered by the driver upto the stack. Using pci_dma_sync_single_for_cpu
ensures copying latest and updated data into skb from the receive buffer.

Signed-off-by: Sony Chacko <sony.chacko@qlogic.com>
Signed-off-by: Manish Chopra <manish.chopra@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qlge/qlge_main.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
index 25800a1..b915de0 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
@@ -1648,7 +1648,18 @@ static void ql_process_mac_rx_skb(struct ql_adapter *qdev,
 		return;
 	}
 	skb_reserve(new_skb, NET_IP_ALIGN);
+
+	pci_dma_sync_single_for_cpu(qdev->pdev,
+				    dma_unmap_addr(sbq_desc, mapaddr),
+				    dma_unmap_len(sbq_desc, maplen),
+				    PCI_DMA_FROMDEVICE);
+
 	memcpy(skb_put(new_skb, length), skb->data, length);
+
+	pci_dma_sync_single_for_device(qdev->pdev,
+				       dma_unmap_addr(sbq_desc, mapaddr),
+				       dma_unmap_len(sbq_desc, maplen),
+				       PCI_DMA_FROMDEVICE);
 	skb = new_skb;
 
 	/* Frame error, so drop the packet. */
-- 
2.1.0


From 3957b00cf071d1313ee75f942ada2c7acf1c1e26 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 17 Mar 2016 11:57:06 -0700
Subject: [PATCH 25/37] net: bcmgenet: fix dma api length mismatch

[ Upstream commit eee577232203842b4dcadb7ab477a298479633ed ]

When un-mapping skb->data in __bcmgenet_tx_reclaim(),
we must use the length that was used in original dma_map_single(),
instead of skb->len that might be bigger (includes the frags)

We simply can store skb_len into tx_cb_ptr->dma_len and use it
at unmap time.

Fixes: 1c1008c793fa ("net: bcmgenet: add main driver file")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 6043734..a9fcac0 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -1048,7 +1048,7 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
 			dev->stats.tx_bytes += tx_cb_ptr->skb->len;
 			dma_unmap_single(&dev->dev,
 					 dma_unmap_addr(tx_cb_ptr, dma_addr),
-					 tx_cb_ptr->skb->len,
+					 dma_unmap_len(tx_cb_ptr, dma_len),
 					 DMA_TO_DEVICE);
 			bcmgenet_free_cb(tx_cb_ptr);
 		} else if (dma_unmap_addr(tx_cb_ptr, dma_addr)) {
@@ -1159,7 +1159,7 @@ static int bcmgenet_xmit_single(struct net_device *dev,
 	}
 
 	dma_unmap_addr_set(tx_cb_ptr, dma_addr, mapping);
-	dma_unmap_len_set(tx_cb_ptr, dma_len, skb->len);
+	dma_unmap_len_set(tx_cb_ptr, dma_len, skb_len);
 	length_status = (skb_len << DMA_BUFLENGTH_SHIFT) | dma_desc_flags |
 			(priv->hw_params->qtag_mask << DMA_TX_QTAG_SHIFT) |
 			DMA_TX_APPEND_CRC;
-- 
2.1.0


From cd473b7c4da235da1720671c2e422f509521544e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 17 Mar 2016 17:23:36 -0700
Subject: [PATCH 26/37] bonding: fix bond_get_stats()

[ Upstream commit fe30937b65354c7fec244caebbdaae68e28ca797 ]

bond_get_stats() can be called from rtnetlink (with RTNL held)
or from /proc/net/dev seq handler (with RCU held)

The logic added in commit 5f0c5f73e5ef ("bonding: make global bonding
stats more reliable") kind of assumed only one cpu could run there.

If multiple threads are reading /proc/net/dev, stats can be really
messed up after a while.

A second problem is that some fields are 32bit, so we need to properly
handle the wrap around problem.

Given that RTNL is not always held, we need to use
bond_for_each_slave_rcu().

Fixes: 5f0c5f73e5ef ("bonding: make global bonding stats more reliable")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Andy Gospodarek <gospo@cumulusnetworks.com>
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Cc: Veaceslav Falico <vfalico@gmail.com>
Reviewed-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 65 ++++++++++++++++++++++-------------------
 include/net/bonding.h           |  1 +
 2 files changed, 36 insertions(+), 30 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index bd744e3..9ba92e2 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3246,6 +3246,30 @@ static int bond_close(struct net_device *bond_dev)
 	return 0;
 }
 
+/* fold stats, assuming all rtnl_link_stats64 fields are u64, but
+ * that some drivers can provide 32bit values only.
+ */
+static void bond_fold_stats(struct rtnl_link_stats64 *_res,
+			    const struct rtnl_link_stats64 *_new,
+			    const struct rtnl_link_stats64 *_old)
+{
+	const u64 *new = (const u64 *)_new;
+	const u64 *old = (const u64 *)_old;
+	u64 *res = (u64 *)_res;
+	int i;
+
+	for (i = 0; i < sizeof(*_res) / sizeof(u64); i++) {
+		u64 nv = new[i];
+		u64 ov = old[i];
+
+		/* detects if this particular field is 32bit only */
+		if (((nv | ov) >> 32) == 0)
+			res[i] += (u32)nv - (u32)ov;
+		else
+			res[i] += nv - ov;
+	}
+}
+
 static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev,
 						struct rtnl_link_stats64 *stats)
 {
@@ -3254,43 +3278,23 @@ static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev,
 	struct list_head *iter;
 	struct slave *slave;
 
+	spin_lock(&bond->stats_lock);
 	memcpy(stats, &bond->bond_stats, sizeof(*stats));
 
-	bond_for_each_slave(bond, slave, iter) {
-		const struct rtnl_link_stats64 *sstats =
+	rcu_read_lock();
+	bond_for_each_slave_rcu(bond, slave, iter) {
+		const struct rtnl_link_stats64 *new =
 			dev_get_stats(slave->dev, &temp);
-		struct rtnl_link_stats64 *pstats = &slave->slave_stats;
-
-		stats->rx_packets +=  sstats->rx_packets - pstats->rx_packets;
-		stats->rx_bytes += sstats->rx_bytes - pstats->rx_bytes;
-		stats->rx_errors += sstats->rx_errors - pstats->rx_errors;
-		stats->rx_dropped += sstats->rx_dropped - pstats->rx_dropped;
-
-		stats->tx_packets += sstats->tx_packets - pstats->tx_packets;;
-		stats->tx_bytes += sstats->tx_bytes - pstats->tx_bytes;
-		stats->tx_errors += sstats->tx_errors - pstats->tx_errors;
-		stats->tx_dropped += sstats->tx_dropped - pstats->tx_dropped;
-
-		stats->multicast += sstats->multicast - pstats->multicast;
-		stats->collisions += sstats->collisions - pstats->collisions;
-
-		stats->rx_length_errors += sstats->rx_length_errors - pstats->rx_length_errors;
-		stats->rx_over_errors += sstats->rx_over_errors - pstats->rx_over_errors;
-		stats->rx_crc_errors += sstats->rx_crc_errors - pstats->rx_crc_errors;
-		stats->rx_frame_errors += sstats->rx_frame_errors - pstats->rx_frame_errors;
-		stats->rx_fifo_errors += sstats->rx_fifo_errors - pstats->rx_fifo_errors;
-		stats->rx_missed_errors += sstats->rx_missed_errors - pstats->rx_missed_errors;
-
-		stats->tx_aborted_errors += sstats->tx_aborted_errors - pstats->tx_aborted_errors;
-		stats->tx_carrier_errors += sstats->tx_carrier_errors - pstats->tx_carrier_errors;
-		stats->tx_fifo_errors += sstats->tx_fifo_errors - pstats->tx_fifo_errors;
-		stats->tx_heartbeat_errors += sstats->tx_heartbeat_errors - pstats->tx_heartbeat_errors;
-		stats->tx_window_errors += sstats->tx_window_errors - pstats->tx_window_errors;
+
+		bond_fold_stats(stats, new, &slave->slave_stats);
 
 		/* save off the slave stats for the next run */
-		memcpy(pstats, sstats, sizeof(*sstats));
+		memcpy(&slave->slave_stats, new, sizeof(*new));
 	}
+	rcu_read_unlock();
+
 	memcpy(&bond->bond_stats, stats, sizeof(*stats));
+	spin_unlock(&bond->stats_lock);
 
 	return stats;
 }
@@ -4102,6 +4106,7 @@ void bond_setup(struct net_device *bond_dev)
 	struct bonding *bond = netdev_priv(bond_dev);
 
 	spin_lock_init(&bond->mode_lock);
+	spin_lock_init(&bond->stats_lock);
 	bond->params = bonding_defaults;
 
 	/* Initialize pointers */
diff --git a/include/net/bonding.h b/include/net/bonding.h
index 78ed135..5cba8f3 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -211,6 +211,7 @@ struct bonding {
 	 * ALB mode (6) - to sync the use and modifications of its hash table
 	 */
 	spinlock_t mode_lock;
+	spinlock_t stats_lock;
 	u8	 send_peer_notif;
 	u8       igmp_retrans;
 #ifdef CONFIG_PROC_FS
-- 
2.1.0


From aa3ee03e9eb0af95ce1ec081a9618ec3aa150bb5 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 22 Mar 2016 09:19:38 +0100
Subject: [PATCH 27/37] ipv4: fix broadcast packets reception

[ Upstream commit ad0ea1989cc4d5905941d0a9e62c63ad6d859cef ]

Currently, ingress ipv4 broadcast datagrams are dropped since,
in udp_v4_early_demux(), ip_check_mc_rcu() is invoked even on
bcast packets.

This patch addresses the issue, invoking ip_check_mc_rcu()
only for mcast packets.

Fixes: 6e5403093261 ("ipv4/udp: Verify multicast group is ours in upd_v4_early_demux()")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index a390174..031752e 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1979,10 +1979,14 @@ void udp_v4_early_demux(struct sk_buff *skb)
 		if (!in_dev)
 			return;
 
-		ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr,
-				       iph->protocol);
-		if (!ours)
-			return;
+		/* we are supposed to accept bcast packets */
+		if (skb->pkt_type == PACKET_MULTICAST) {
+			ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr,
+					       iph->protocol);
+			if (!ours)
+				return;
+		}
+
 		sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr,
 						   uh->source, iph->saddr, dif);
 	} else if (skb->pkt_type == PACKET_HOST) {
-- 
2.1.0


From f1de124492d13aa964fdf8563a60dab54ac0bf82 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Wed, 23 Mar 2016 16:38:55 +0100
Subject: [PATCH 28/37] ppp: take reference on channels netns

[ Upstream commit 1f461dcdd296eecedaffffc6bae2bfa90bd7eb89 ]

Let channels hold a reference on their network namespace.
Some channel types, like ppp_async and ppp_synctty, can have their
userspace controller running in a different namespace. Therefore they
can't rely on them to preclude their netns from being removed from
under them.

==================================================================
BUG: KASAN: use-after-free in ppp_unregister_channel+0x372/0x3a0 at
addr ffff880064e217e0
Read of size 8 by task syz-executor/11581
=============================================================================
BUG net_namespace (Not tainted): kasan: bad access detected
-----------------------------------------------------------------------------

Disabling lock debugging due to kernel taint
INFO: Allocated in copy_net_ns+0x6b/0x1a0 age=92569 cpu=3 pid=6906
[<      none      >] ___slab_alloc+0x4c7/0x500 kernel/mm/slub.c:2440
[<      none      >] __slab_alloc+0x4c/0x90 kernel/mm/slub.c:2469
[<     inline     >] slab_alloc_node kernel/mm/slub.c:2532
[<     inline     >] slab_alloc kernel/mm/slub.c:2574
[<      none      >] kmem_cache_alloc+0x23a/0x2b0 kernel/mm/slub.c:2579
[<     inline     >] kmem_cache_zalloc kernel/include/linux/slab.h:597
[<     inline     >] net_alloc kernel/net/core/net_namespace.c:325
[<      none      >] copy_net_ns+0x6b/0x1a0 kernel/net/core/net_namespace.c:360
[<      none      >] create_new_namespaces+0x2f6/0x610 kernel/kernel/nsproxy.c:95
[<      none      >] copy_namespaces+0x297/0x320 kernel/kernel/nsproxy.c:150
[<      none      >] copy_process.part.35+0x1bf4/0x5760 kernel/kernel/fork.c:1451
[<     inline     >] copy_process kernel/kernel/fork.c:1274
[<      none      >] _do_fork+0x1bc/0xcb0 kernel/kernel/fork.c:1723
[<     inline     >] SYSC_clone kernel/kernel/fork.c:1832
[<      none      >] SyS_clone+0x37/0x50 kernel/kernel/fork.c:1826
[<      none      >] entry_SYSCALL_64_fastpath+0x16/0x7a kernel/arch/x86/entry/entry_64.S:185

INFO: Freed in net_drop_ns+0x67/0x80 age=575 cpu=2 pid=2631
[<      none      >] __slab_free+0x1fc/0x320 kernel/mm/slub.c:2650
[<     inline     >] slab_free kernel/mm/slub.c:2805
[<      none      >] kmem_cache_free+0x2a0/0x330 kernel/mm/slub.c:2814
[<     inline     >] net_free kernel/net/core/net_namespace.c:341
[<      none      >] net_drop_ns+0x67/0x80 kernel/net/core/net_namespace.c:348
[<      none      >] cleanup_net+0x4e5/0x600 kernel/net/core/net_namespace.c:448
[<      none      >] process_one_work+0x794/0x1440 kernel/kernel/workqueue.c:2036
[<      none      >] worker_thread+0xdb/0xfc0 kernel/kernel/workqueue.c:2170
[<      none      >] kthread+0x23f/0x2d0 kernel/drivers/block/aoe/aoecmd.c:1303
[<      none      >] ret_from_fork+0x3f/0x70 kernel/arch/x86/entry/entry_64.S:468
INFO: Slab 0xffffea0001938800 objects=3 used=0 fp=0xffff880064e20000
flags=0x5fffc0000004080
INFO: Object 0xffff880064e20000 @offset=0 fp=0xffff880064e24200

CPU: 1 PID: 11581 Comm: syz-executor Tainted: G    B           4.4.0+
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS
rel-1.8.2-0-g33fbe13 by qemu-project.org 04/01/2014
 00000000ffffffff ffff8800662c7790 ffffffff8292049d ffff88003e36a300
 ffff880064e20000 ffff880064e20000 ffff8800662c77c0 ffffffff816f2054
 ffff88003e36a300 ffffea0001938800 ffff880064e20000 0000000000000000
Call Trace:
 [<     inline     >] __dump_stack kernel/lib/dump_stack.c:15
 [<ffffffff8292049d>] dump_stack+0x6f/0xa2 kernel/lib/dump_stack.c:50
 [<ffffffff816f2054>] print_trailer+0xf4/0x150 kernel/mm/slub.c:654
 [<ffffffff816f875f>] object_err+0x2f/0x40 kernel/mm/slub.c:661
 [<     inline     >] print_address_description kernel/mm/kasan/report.c:138
 [<ffffffff816fb0c5>] kasan_report_error+0x215/0x530 kernel/mm/kasan/report.c:236
 [<     inline     >] kasan_report kernel/mm/kasan/report.c:259
 [<ffffffff816fb4de>] __asan_report_load8_noabort+0x3e/0x40 kernel/mm/kasan/report.c:280
 [<     inline     >] ? ppp_pernet kernel/include/linux/compiler.h:218
 [<ffffffff83ad71b2>] ? ppp_unregister_channel+0x372/0x3a0 kernel/drivers/net/ppp/ppp_generic.c:2392
 [<     inline     >] ppp_pernet kernel/include/linux/compiler.h:218
 [<ffffffff83ad71b2>] ppp_unregister_channel+0x372/0x3a0 kernel/drivers/net/ppp/ppp_generic.c:2392
 [<     inline     >] ? ppp_pernet kernel/drivers/net/ppp/ppp_generic.c:293
 [<ffffffff83ad6f26>] ? ppp_unregister_channel+0xe6/0x3a0 kernel/drivers/net/ppp/ppp_generic.c:2392
 [<ffffffff83ae18f3>] ppp_asynctty_close+0xa3/0x130 kernel/drivers/net/ppp/ppp_async.c:241
 [<ffffffff83ae1850>] ? async_lcp_peek+0x5b0/0x5b0 kernel/drivers/net/ppp/ppp_async.c:1000
 [<ffffffff82c33239>] tty_ldisc_close.isra.1+0x99/0xe0 kernel/drivers/tty/tty_ldisc.c:478
 [<ffffffff82c332c0>] tty_ldisc_kill+0x40/0x170 kernel/drivers/tty/tty_ldisc.c:744
 [<ffffffff82c34943>] tty_ldisc_release+0x1b3/0x260 kernel/drivers/tty/tty_ldisc.c:772
 [<ffffffff82c1ef21>] tty_release+0xac1/0x13e0 kernel/drivers/tty/tty_io.c:1901
 [<ffffffff82c1e460>] ? release_tty+0x320/0x320 kernel/drivers/tty/tty_io.c:1688
 [<ffffffff8174de36>] __fput+0x236/0x780 kernel/fs/file_table.c:208
 [<ffffffff8174e405>] ____fput+0x15/0x20 kernel/fs/file_table.c:244
 [<ffffffff813595ab>] task_work_run+0x16b/0x200 kernel/kernel/task_work.c:115
 [<     inline     >] exit_task_work kernel/include/linux/task_work.h:21
 [<ffffffff81307105>] do_exit+0x8b5/0x2c60 kernel/kernel/exit.c:750
 [<ffffffff813fdd20>] ? debug_check_no_locks_freed+0x290/0x290 kernel/kernel/locking/lockdep.c:4123
 [<ffffffff81306850>] ? mm_update_next_owner+0x6f0/0x6f0 kernel/kernel/exit.c:357
 [<ffffffff813215e6>] ? __dequeue_signal+0x136/0x470 kernel/kernel/signal.c:550
 [<ffffffff8132067b>] ? recalc_sigpending_tsk+0x13b/0x180 kernel/kernel/signal.c:145
 [<ffffffff81309628>] do_group_exit+0x108/0x330 kernel/kernel/exit.c:880
 [<ffffffff8132b9d4>] get_signal+0x5e4/0x14f0 kernel/kernel/signal.c:2307
 [<     inline     >] ? kretprobe_table_lock kernel/kernel/kprobes.c:1113
 [<ffffffff8151d355>] ? kprobe_flush_task+0xb5/0x450 kernel/kernel/kprobes.c:1158
 [<ffffffff8115f7d3>] do_signal+0x83/0x1c90 kernel/arch/x86/kernel/signal.c:712
 [<ffffffff8151d2a0>] ? recycle_rp_inst+0x310/0x310 kernel/include/linux/list.h:655
 [<ffffffff8115f750>] ? setup_sigcontext+0x780/0x780 kernel/arch/x86/kernel/signal.c:165
 [<ffffffff81380864>] ? finish_task_switch+0x424/0x5f0 kernel/kernel/sched/core.c:2692
 [<     inline     >] ? finish_lock_switch kernel/kernel/sched/sched.h:1099
 [<ffffffff81380560>] ? finish_task_switch+0x120/0x5f0 kernel/kernel/sched/core.c:2678
 [<     inline     >] ? context_switch kernel/kernel/sched/core.c:2807
 [<ffffffff85d794e9>] ? __schedule+0x919/0x1bd0 kernel/kernel/sched/core.c:3283
 [<ffffffff81003901>] exit_to_usermode_loop+0xf1/0x1a0 kernel/arch/x86/entry/common.c:247
 [<     inline     >] prepare_exit_to_usermode kernel/arch/x86/entry/common.c:282
 [<ffffffff810062ef>] syscall_return_slowpath+0x19f/0x210 kernel/arch/x86/entry/common.c:344
 [<ffffffff85d88022>] int_ret_from_sys_call+0x25/0x9f kernel/arch/x86/entry/entry_64.S:281
Memory state around the buggy address:
 ffff880064e21680: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff880064e21700: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff880064e21780: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                                                       ^
 ffff880064e21800: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff880064e21880: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
==================================================================

Fixes: 273ec51dd7ce ("net: ppp_generic - introduce net-namespace functionality v2")
Reported-by: Baozeng Ding <sploving1@gmail.com>
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Reviewed-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/ppp_generic.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index cfe49a0..922263a 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -2244,7 +2244,7 @@ int ppp_register_net_channel(struct net *net, struct ppp_channel *chan)
 
 	pch->ppp = NULL;
 	pch->chan = chan;
-	pch->chan_net = net;
+	pch->chan_net = get_net(net);
 	chan->ppp = pch;
 	init_ppp_file(&pch->file, CHANNEL);
 	pch->file.hdrlen = chan->hdrlen;
@@ -2341,6 +2341,8 @@ ppp_unregister_channel(struct ppp_channel *chan)
 	spin_lock_bh(&pn->all_channels_lock);
 	list_del(&pch->list);
 	spin_unlock_bh(&pn->all_channels_lock);
+	put_net(pch->chan_net);
+	pch->chan_net = NULL;
 
 	pch->file.dead = 1;
 	wake_up_interruptible(&pch->file.rwait);
-- 
2.1.0


From 1acfd745eb284c488770b40ac157037a3767630b Mon Sep 17 00:00:00 2001
From: "subashab@codeaurora.org" <subashab@codeaurora.org>
Date: Wed, 23 Mar 2016 22:39:50 -0600
Subject: [PATCH 29/37] xfrm: Fix crash observed during device unregistration
 and decryption

[ Upstream commit 071d36bf21bcc837be00cea55bcef8d129e7f609 ]

A crash is observed when a decrypted packet is processed in receive
path. get_rps_cpus() tries to dereference the skb->dev fields but it
appears that the device is freed from the poison pattern.

[<ffffffc000af58ec>] get_rps_cpu+0x94/0x2f0
[<ffffffc000af5f94>] netif_rx_internal+0x140/0x1cc
[<ffffffc000af6094>] netif_rx+0x74/0x94
[<ffffffc000bc0b6c>] xfrm_input+0x754/0x7d0
[<ffffffc000bc0bf8>] xfrm_input_resume+0x10/0x1c
[<ffffffc000ba6eb8>] esp_input_done+0x20/0x30
[<ffffffc0000b64c8>] process_one_work+0x244/0x3fc
[<ffffffc0000b7324>] worker_thread+0x2f8/0x418
[<ffffffc0000bb40c>] kthread+0xe0/0xec

-013|get_rps_cpu(
     |    dev = 0xFFFFFFC08B688000,
     |    skb = 0xFFFFFFC0C76AAC00 -> (
     |      dev = 0xFFFFFFC08B688000 -> (
     |        name =
"......................................................
     |        name_hlist = (next = 0xAAAAAAAAAAAAAAAA, pprev =
0xAAAAAAAAAAA

Following are the sequence of events observed -

- Encrypted packet in receive path from netdevice is queued
- Encrypted packet queued for decryption (asynchronous)
- Netdevice brought down and freed
- Packet is decrypted and returned through callback in esp_input_done
- Packet is queued again for process in network stack using netif_rx

Since the device appears to have been freed, the dereference of
skb->dev in get_rps_cpus() leads to an unhandled page fault
exception.

Fix this by holding on to device reference when queueing packets
asynchronously and releasing the reference on call back return.

v2: Make the change generic to xfrm as mentioned by Steffen and
update the title to xfrm

Suggested-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Jerome Stanislaus <jeromes@codeaurora.org>
Signed-off-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/xfrm/xfrm_input.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index b58286e..cbaf52c 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -292,12 +292,15 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 		XFRM_SKB_CB(skb)->seq.input.hi = seq_hi;
 
 		skb_dst_force(skb);
+		dev_hold(skb->dev);
 
 		nexthdr = x->type->input(x, skb);
 
 		if (nexthdr == -EINPROGRESS)
 			return 0;
 resume:
+		dev_put(skb->dev);
+
 		spin_lock(&x->lock);
 		if (nexthdr <= 0) {
 			if (nexthdr == -EBADMSG) {
-- 
2.1.0


From 56e39508abe5148f0dd1f8d68f1598317e7a5b04 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Mon, 28 Mar 2016 22:38:16 +0200
Subject: [PATCH 30/37] qmi_wwan: add "D-Link DWM-221 B1" device id
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit e84810c7b85a2d7897797b3ad3e879168a8e032a ]

Thomas reports:
"Windows:

00 diagnostics
01 modem
02 at-port
03 nmea
04 nic

Linux:

T:  Bus=02 Lev=01 Prnt=01 Port=03 Cnt=01 Dev#=  4 Spd=480 MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=2001 ProdID=7e19 Rev=02.32
S:  Manufacturer=Mobile Connect
S:  Product=Mobile Connect
S:  SerialNumber=0123456789ABCDEF
C:  #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
I:  If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
I:  If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
I:  If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
I:  If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
I:  If#= 5 Alt= 0 #EPs= 2 Cls=08(stor.) Sub=06 Prot=50 Driver=usb-storage"

Reported-by: Thomas Schäfer <tschaefer@t-online.de>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 8677c6a..8153e97 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -749,6 +749,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x19d2, 0x1426, 2)},	/* ZTE MF91 */
 	{QMI_FIXED_INTF(0x19d2, 0x1428, 2)},	/* Telewell TW-LTE 4G v2 */
 	{QMI_FIXED_INTF(0x19d2, 0x2002, 4)},	/* ZTE (Vodafone) K3765-Z */
+	{QMI_FIXED_INTF(0x2001, 0x7e19, 4)},	/* D-Link DWM-221 B1 */
 	{QMI_FIXED_INTF(0x0f3d, 0x68a2, 8)},    /* Sierra Wireless MC7700 */
 	{QMI_FIXED_INTF(0x114f, 0x68a2, 8)},    /* Sierra Wireless MC7750 */
 	{QMI_FIXED_INTF(0x1199, 0x68a2, 8)},	/* Sierra Wireless MC7710 in QMI mode */
-- 
2.1.0


From b17fcfeeb52e377b1c0d12a60ac985d6e1a38857 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 29 Mar 2016 08:43:41 -0700
Subject: [PATCH 31/37] ipv6: udp: fix UDP_MIB_IGNOREDMULTI updates

[ Upstream commit 2d4212261fdf13e29728ddb5ea9d60c342cc92b5 ]

IPv6 counters updates use a different macro than IPv4.

Fixes: 36cbb2452cbaf ("udp: Increment UDP_MIB_IGNOREDMULTI for arriving unmatched multicasts")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Rick Jones <rick.jones2@hp.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/udp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index d28b2a1..1173557 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -834,8 +834,8 @@ start_lookup:
 		flush_stack(stack, count, skb, count - 1);
 	} else {
 		if (!inner_flushed)
-			UDP_INC_STATS_BH(net, UDP_MIB_IGNOREDMULTI,
-					 proto == IPPROTO_UDPLITE);
+			UDP6_INC_STATS_BH(net, UDP_MIB_IGNOREDMULTI,
+					  proto == IPPROTO_UDPLITE);
 		consume_skb(skb);
 	}
 	return 0;
-- 
2.1.0


From b7a1bb18f79dd5c19a6443b13328c4e2255c7599 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Thu, 31 Mar 2016 18:10:31 +0200
Subject: [PATCH 32/37] rtnl: fix msg size calculation in if_nlmsg_size()

[ Upstream commit c57c7a95da842807b475b823ed2e5435c42cb3b0 ]

Size of the attribute IFLA_PHYS_PORT_NAME was missing.

Fixes: db24a9044ee1 ("net: add support for phys_port_name")
CC: David Ahern <dsahern@gmail.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index fe95cb7..6fa719c 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -884,7 +884,8 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + rtnl_link_get_size(dev) /* IFLA_LINKINFO */
 	       + rtnl_link_get_af_size(dev) /* IFLA_AF_SPEC */
 	       + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_PORT_ID */
-	       + nla_total_size(MAX_PHYS_ITEM_ID_LEN); /* IFLA_PHYS_SWITCH_ID */
+	       + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_SWITCH_ID */
+	       + nla_total_size(IFNAMSIZ); /* IFLA_PHYS_PORT_NAME */
 }
 
 static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev)
-- 
2.1.0


From dd99745e3506b6bf381e32b50421dcf414e1b35b Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 31 Mar 2016 02:13:18 +0200
Subject: [PATCH 33/37] tun, bpf: fix suspicious RCU usage in tun_{attach,
 detach}_filter

[ Upstream commit 5a5abb1fa3b05dd6aa821525832644c1e7d2905f ]

Sasha Levin reported a suspicious rcu_dereference_protected() warning
found while fuzzing with trinity that is similar to this one:

  [   52.765684] net/core/filter.c:2262 suspicious rcu_dereference_protected() usage!
  [   52.765688] other info that might help us debug this:
  [   52.765695] rcu_scheduler_active = 1, debug_locks = 1
  [   52.765701] 1 lock held by a.out/1525:
  [   52.765704]  #0:  (rtnl_mutex){+.+.+.}, at: [<ffffffff816a64b7>] rtnl_lock+0x17/0x20
  [   52.765721] stack backtrace:
  [   52.765728] CPU: 1 PID: 1525 Comm: a.out Not tainted 4.5.0+ #264
  [...]
  [   52.765768] Call Trace:
  [   52.765775]  [<ffffffff813e488d>] dump_stack+0x85/0xc8
  [   52.765784]  [<ffffffff810f2fa5>] lockdep_rcu_suspicious+0xd5/0x110
  [   52.765792]  [<ffffffff816afdc2>] sk_detach_filter+0x82/0x90
  [   52.765801]  [<ffffffffa0883425>] tun_detach_filter+0x35/0x90 [tun]
  [   52.765810]  [<ffffffffa0884ed4>] __tun_chr_ioctl+0x354/0x1130 [tun]
  [   52.765818]  [<ffffffff8136fed0>] ? selinux_file_ioctl+0x130/0x210
  [   52.765827]  [<ffffffffa0885ce3>] tun_chr_ioctl+0x13/0x20 [tun]
  [   52.765834]  [<ffffffff81260ea6>] do_vfs_ioctl+0x96/0x690
  [   52.765843]  [<ffffffff81364af3>] ? security_file_ioctl+0x43/0x60
  [   52.765850]  [<ffffffff81261519>] SyS_ioctl+0x79/0x90
  [   52.765858]  [<ffffffff81003ba2>] do_syscall_64+0x62/0x140
  [   52.765866]  [<ffffffff817d563f>] entry_SYSCALL64_slow_path+0x25/0x25

Same can be triggered with PROVE_RCU (+ PROVE_RCU_REPEATEDLY) enabled
from tun_attach_filter() when user space calls ioctl(tun_fd, TUN{ATTACH,
DETACH}FILTER, ...) for adding/removing a BPF filter on tap devices.

Since the fix in f91ff5b9ff52 ("net: sk_{detach|attach}_filter() rcu
fixes") sk_attach_filter()/sk_detach_filter() now dereferences the
filter with rcu_dereference_protected(), checking whether socket lock
is held in control path.

Since its introduction in 994051625981 ("tun: socket filter support"),
tap filters are managed under RTNL lock from __tun_chr_ioctl(). Thus the
sock_owned_by_user(sk) doesn't apply in this specific case and therefore
triggers the false positive.

Extend the BPF API with __sk_attach_filter()/__sk_detach_filter() pair
that is used by tap filters and pass in lockdep_rtnl_is_held() for the
rcu_dereference_protected() checks instead.

Reported-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c      |  8 +++++---
 include/linux/filter.h |  3 +++
 net/core/filter.c      | 33 +++++++++++++++++++++------------
 3 files changed, 29 insertions(+), 15 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index e470ae5..6a70fc3 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -570,7 +570,8 @@ static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filte
 
 	/* Re-attach the filter to persist device */
 	if (!skip_filter && (tun->filter_attached == true)) {
-		err = sk_attach_filter(&tun->fprog, tfile->socket.sk);
+		err = __sk_attach_filter(&tun->fprog, tfile->socket.sk,
+					 lockdep_rtnl_is_held());
 		if (!err)
 			goto out;
 	}
@@ -1760,7 +1761,7 @@ static void tun_detach_filter(struct tun_struct *tun, int n)
 
 	for (i = 0; i < n; i++) {
 		tfile = rtnl_dereference(tun->tfiles[i]);
-		sk_detach_filter(tfile->socket.sk);
+		__sk_detach_filter(tfile->socket.sk, lockdep_rtnl_is_held());
 	}
 
 	tun->filter_attached = false;
@@ -1773,7 +1774,8 @@ static int tun_attach_filter(struct tun_struct *tun)
 
 	for (i = 0; i < tun->numqueues; i++) {
 		tfile = rtnl_dereference(tun->tfiles[i]);
-		ret = sk_attach_filter(&tun->fprog, tfile->socket.sk);
+		ret = __sk_attach_filter(&tun->fprog, tfile->socket.sk,
+					 lockdep_rtnl_is_held());
 		if (ret) {
 			tun_detach_filter(tun, i);
 			return ret;
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 1ce6e10..61c8118 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -381,8 +381,11 @@ int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog);
 void bpf_prog_destroy(struct bpf_prog *fp);
 
 int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk);
+int __sk_attach_filter(struct sock_fprog *fprog, struct sock *sk,
+		       bool locked);
 int sk_attach_bpf(u32 ufd, struct sock *sk);
 int sk_detach_filter(struct sock *sk);
+int __sk_detach_filter(struct sock *sk, bool locked);
 
 int bpf_check_classic(const struct sock_filter *filter, unsigned int flen);
 int sk_get_filter(struct sock *sk, struct sock_filter __user *filter,
diff --git a/net/core/filter.c b/net/core/filter.c
index 238bb3f..1f675c1 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1070,7 +1070,8 @@ void bpf_prog_destroy(struct bpf_prog *fp)
 }
 EXPORT_SYMBOL_GPL(bpf_prog_destroy);
 
-static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk)
+static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk,
+			    bool locked)
 {
 	struct sk_filter *fp, *old_fp;
 
@@ -1086,10 +1087,8 @@ static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk)
 		return -ENOMEM;
 	}
 
-	old_fp = rcu_dereference_protected(sk->sk_filter,
-					   sock_owned_by_user(sk));
+	old_fp = rcu_dereference_protected(sk->sk_filter, locked);
 	rcu_assign_pointer(sk->sk_filter, fp);
-
 	if (old_fp)
 		sk_filter_uncharge(sk, old_fp);
 
@@ -1106,7 +1105,8 @@ static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk)
  * occurs or there is insufficient memory for the filter a negative
  * errno code is returned. On success the return is zero.
  */
-int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
+int __sk_attach_filter(struct sock_fprog *fprog, struct sock *sk,
+		       bool locked)
 {
 	unsigned int fsize = bpf_classic_proglen(fprog);
 	unsigned int bpf_fsize = bpf_prog_size(fprog->len);
@@ -1144,7 +1144,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 	if (IS_ERR(prog))
 		return PTR_ERR(prog);
 
-	err = __sk_attach_prog(prog, sk);
+	err = __sk_attach_prog(prog, sk, locked);
 	if (err < 0) {
 		__bpf_prog_release(prog);
 		return err;
@@ -1152,7 +1152,12 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(sk_attach_filter);
+EXPORT_SYMBOL_GPL(__sk_attach_filter);
+
+int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
+{
+	return __sk_attach_filter(fprog, sk, sock_owned_by_user(sk));
+}
 
 int sk_attach_bpf(u32 ufd, struct sock *sk)
 {
@@ -1171,7 +1176,7 @@ int sk_attach_bpf(u32 ufd, struct sock *sk)
 		return -EINVAL;
 	}
 
-	err = __sk_attach_prog(prog, sk);
+	err = __sk_attach_prog(prog, sk, sock_owned_by_user(sk));
 	if (err < 0) {
 		bpf_prog_put(prog);
 		return err;
@@ -1497,7 +1502,7 @@ static int __init register_sk_filter_ops(void)
 }
 late_initcall(register_sk_filter_ops);
 
-int sk_detach_filter(struct sock *sk)
+int __sk_detach_filter(struct sock *sk, bool locked)
 {
 	int ret = -ENOENT;
 	struct sk_filter *filter;
@@ -1505,8 +1510,7 @@ int sk_detach_filter(struct sock *sk)
 	if (sock_flag(sk, SOCK_FILTER_LOCKED))
 		return -EPERM;
 
-	filter = rcu_dereference_protected(sk->sk_filter,
-					   sock_owned_by_user(sk));
+	filter = rcu_dereference_protected(sk->sk_filter, locked);
 	if (filter) {
 		RCU_INIT_POINTER(sk->sk_filter, NULL);
 		sk_filter_uncharge(sk, filter);
@@ -1515,7 +1519,12 @@ int sk_detach_filter(struct sock *sk)
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(sk_detach_filter);
+EXPORT_SYMBOL_GPL(__sk_detach_filter);
+
+int sk_detach_filter(struct sock *sk)
+{
+	return __sk_detach_filter(sk, sock_owned_by_user(sk));
+}
 
 int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf,
 		  unsigned int len)
-- 
2.1.0


From 8ff03714dae35f125708f13ebb4a2af56680a0c2 Mon Sep 17 00:00:00 2001
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Sun, 3 Apr 2016 22:09:23 +0800
Subject: [PATCH 34/37] ipv4: l2tp: fix a potential issue in l2tp_ip_recv

[ Upstream commit 5745b8232e942abd5e16e85fa9b27cc21324acf0 ]

pskb_may_pull() can change skb->data, so we have to load ptr/optr at the
right place.

Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ip.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 7964993..44ee068 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -123,12 +123,11 @@ static int l2tp_ip_recv(struct sk_buff *skb)
 	struct l2tp_tunnel *tunnel = NULL;
 	int length;
 
-	/* Point to L2TP header */
-	optr = ptr = skb->data;
-
 	if (!pskb_may_pull(skb, 4))
 		goto discard;
 
+	/* Point to L2TP header */
+	optr = ptr = skb->data;
 	session_id = ntohl(*((__be32 *) ptr));
 	ptr += 4;
 
@@ -156,6 +155,9 @@ static int l2tp_ip_recv(struct sk_buff *skb)
 		if (!pskb_may_pull(skb, length))
 			goto discard;
 
+		/* Point to L2TP header */
+		optr = ptr = skb->data;
+		ptr += 4;
 		pr_debug("%s: ip recv\n", tunnel->name);
 		print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length);
 	}
-- 
2.1.0


From 868b047701eb7201cee82ebfffddcbce138108f7 Mon Sep 17 00:00:00 2001
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Sun, 3 Apr 2016 22:09:24 +0800
Subject: [PATCH 35/37] ipv6: l2tp: fix a potential issue in l2tp_ip6_recv

[ Upstream commit be447f305494e019dfc37ea4cdf3b0e4200b4eba ]

pskb_may_pull() can change skb->data, so we have to load ptr/optr at the
right place.

Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ip6.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 0ce9da9..36f8fa2 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -135,12 +135,11 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
 	struct l2tp_tunnel *tunnel = NULL;
 	int length;
 
-	/* Point to L2TP header */
-	optr = ptr = skb->data;
-
 	if (!pskb_may_pull(skb, 4))
 		goto discard;
 
+	/* Point to L2TP header */
+	optr = ptr = skb->data;
 	session_id = ntohl(*((__be32 *) ptr));
 	ptr += 4;
 
@@ -168,6 +167,9 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
 		if (!pskb_may_pull(skb, length))
 			goto discard;
 
+		/* Point to L2TP header */
+		optr = ptr = skb->data;
+		ptr += 4;
 		pr_debug("%s: ip recv\n", tunnel->name);
 		print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length);
 	}
-- 
2.1.0


From b82ea80bba65523327d64cbabaa02de81ba799fc Mon Sep 17 00:00:00 2001
From: Thadeu Lima de Souza Cascardo <cascardo@redhat.com>
Date: Fri, 1 Apr 2016 17:17:50 -0300
Subject: [PATCH 36/37] ip6_tunnel: set rtnl_link_ops before calling
 register_netdevice

[ Upstream commit b6ee376cb0b7fb4e7e07d6cd248bd40436fb9ba6 ]

When creating an ip6tnl tunnel with ip tunnel, rtnl_link_ops is not set
before ip6_tnl_create2 is called. When register_netdevice is called, there
is no linkinfo attribute in the NEWLINK message because of that.

Setting rtnl_link_ops before calling register_netdevice fixes that.

Fixes: 0b112457229d ("ip6tnl: add support of link creation via rtnl")
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@redhat.com>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 6fd0f96..c7c2c33 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -284,12 +284,12 @@ static int ip6_tnl_create2(struct net_device *dev)
 
 	t = netdev_priv(dev);
 
+	dev->rtnl_link_ops = &ip6_link_ops;
 	err = register_netdevice(dev);
 	if (err < 0)
 		goto out;
 
 	strcpy(t->parms.name, dev->name);
-	dev->rtnl_link_ops = &ip6_link_ops;
 
 	dev_hold(dev);
 	ip6_tnl_link(ip6n, t);
-- 
2.1.0


From a463c14f09c02e73496a1335c3076e9ef48faa43 Mon Sep 17 00:00:00 2001
From: Jakub Sitnicki <jkbs@redhat.com>
Date: Tue, 5 Apr 2016 18:41:08 +0200
Subject: [PATCH 37/37] ipv6: Count in extension headers in skb->network_header

[ Upstream commit 3ba3458fb9c050718b95275a3310b74415e767e2 ]

When sending a UDPv6 message longer than MTU, account for the length
of fragmentable IPv6 extension headers in skb->network_header offset.
Same as we do in alloc_new_skb path in __ip6_append_data().

This ensures that later on __ip6_make_skb() will make space in
headroom for fragmentable extension headers:

	/* move skb->data to ip header from ext header */
	if (skb->data < skb_network_header(skb))
		__skb_pull(skb, skb_network_offset(skb));

Prevents a splat due to skb_under_panic:

skbuff: skb_under_panic: text:ffffffff8143397b len:2126 put:14 \
head:ffff880005bacf50 data:ffff880005bacf4a tail:0x48 end:0xc0 dev:lo
------------[ cut here ]------------
kernel BUG at net/core/skbuff.c:104!
invalid opcode: 0000 [#1] KASAN
CPU: 0 PID: 160 Comm: reproducer Not tainted 4.6.0-rc2 #65
[...]
Call Trace:
 [<ffffffff813eb7b9>] skb_push+0x79/0x80
 [<ffffffff8143397b>] eth_header+0x2b/0x100
 [<ffffffff8141e0d0>] neigh_resolve_output+0x210/0x310
 [<ffffffff814eab77>] ip6_finish_output2+0x4a7/0x7c0
 [<ffffffff814efe3a>] ip6_output+0x16a/0x280
 [<ffffffff815440c1>] ip6_local_out+0xb1/0xf0
 [<ffffffff814f1115>] ip6_send_skb+0x45/0xd0
 [<ffffffff81518836>] udp_v6_send_skb+0x246/0x5d0
 [<ffffffff8151985e>] udpv6_sendmsg+0xa6e/0x1090
[...]

Reported-by: Ji Jianwen <jiji@redhat.com>
Signed-off-by: Jakub Sitnicki <jkbs@redhat.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_output.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 06bf401..23e6fd0 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1066,9 +1066,8 @@ static inline int ip6_ufo_append_data(struct sock *sk,
 			int getfrag(void *from, char *to, int offset, int len,
 			int odd, struct sk_buff *skb),
 			void *from, int length, int hh_len, int fragheaderlen,
-			int transhdrlen, int mtu, unsigned int flags,
-			struct rt6_info *rt)
-
+			int exthdrlen, int transhdrlen, int mtu,
+			unsigned int flags, struct rt6_info *rt)
 {
 	struct sk_buff *skb;
 	struct frag_hdr fhdr;
@@ -1093,7 +1092,7 @@ static inline int ip6_ufo_append_data(struct sock *sk,
 		skb_put(skb, fragheaderlen + transhdrlen);
 
 		/* initialize network header pointer */
-		skb_reset_network_header(skb);
+		skb_set_network_header(skb, exthdrlen);
 
 		/* initialize protocol header pointer */
 		skb->transport_header = skb->network_header + fragheaderlen;
@@ -1338,7 +1337,7 @@ emsgsize:
 	    (rt->dst.dev->features & NETIF_F_UFO) &&
 	    (sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk)) {
 		err = ip6_ufo_append_data(sk, queue, getfrag, from, length,
-					  hh_len, fragheaderlen,
+					  hh_len, fragheaderlen, exthdrlen,
 					  transhdrlen, mtu, flags, rt);
 		if (err)
 			goto error;
-- 
2.1.0


[-- Attachment #3: net_44.mbox --]
[-- Type: Application/Octet-Stream, Size: 143988 bytes --]

From de885979963fbb5c950a2cbb00249d248f793995 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Date: Sun, 21 Feb 2016 10:12:39 +0300
Subject: [PATCH 01/56] tcp: convert cached rtt from usec to jiffies when
 feeding initial rto

[ Upstream commit 9bdfb3b79e61c60e1a3e2dc05ad164528afa6b8a ]

Currently it's converted into msecs, thus HZ=1000 intact.

Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Fixes: 740b0f1841f6 ("tcp: switch rtt estimations to usec resolution")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_metrics.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index c8cbc2b..a726d78 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -550,7 +550,7 @@ reset:
 	 */
 	if (crtt > tp->srtt_us) {
 		/* Set RTO like tcp_rtt_estimator(), but from cached RTT. */
-		crtt /= 8 * USEC_PER_MSEC;
+		crtt /= 8 * USEC_PER_SEC / HZ;
 		inet_csk(sk)->icsk_rto = crtt + max(2 * crtt, tcp_rto_min(sk));
 	} else if (tp->srtt_us == 0) {
 		/* RFC6298: 5.7 We've failed to get a valid RTT sample from
-- 
2.1.0


From 1d9a9a3a97075b1bdbbf52f9cee6a2656a1aea5f Mon Sep 17 00:00:00 2001
From: Bernie Harris <bernie.harris@alliedtelesis.co.nz>
Date: Mon, 22 Feb 2016 12:58:05 +1300
Subject: [PATCH 02/56] tunnel: Clear IPCB(skb)->opt before dst_link_failure
 called

[ Upstream commit 5146d1f151122e868e594c7b45115d64825aee5f ]

IPCB may contain data from previous layers (in the observed case the
qdisc layer). In the observed scenario, the data was misinterpreted as
ip header options, which later caused the ihl to be set to an invalid
value (<5). This resulted in an infinite loop in the mips implementation
of ip_fast_csum.

This patch clears IPCB(skb)->opt before dst_link_failure can be called for
various types of tunnels. This change only applies to encapsulated ipv4
packets.

The code introduced in 11c21a30 which clears all of IPCB has been removed
to be consistent with these changes, and instead the opt field is cleared
unconditionally in ip_tunnel_xmit. The change in ip_tunnel_xmit applies to
SIT, GRE, and IPIP tunnels.

The relevant vti, l2tp, and pptp functions already contain similar code for
clearing the IPCB.

Signed-off-by: Bernie Harris <bernie.harris@alliedtelesis.co.nz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_tunnel.c  | 3 ++-
 net/ipv4/udp_tunnel.c | 2 ++
 net/ipv6/ip6_gre.c    | 2 ++
 net/ipv6/ip6_tunnel.c | 2 ++
 4 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index cbb51f3..ce30c8b 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -663,6 +663,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
 	connected = (tunnel->parms.iph.daddr != 0);
 
+	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+
 	dst = tnl_params->daddr;
 	if (dst == 0) {
 		/* NBMA tunnel */
@@ -760,7 +762,6 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 				tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
 			tunnel->err_count--;
 
-			memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
 			dst_link_failure(skb);
 		} else
 			tunnel->err_count = 0;
diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c
index aba4286..280a9bd 100644
--- a/net/ipv4/udp_tunnel.c
+++ b/net/ipv4/udp_tunnel.c
@@ -89,6 +89,8 @@ int udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb,
 	uh->source = src_port;
 	uh->len = htons(skb->len);
 
+	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+
 	udp_set_csum(nocheck, skb, src, dst, skb->len);
 
 	return iptunnel_xmit(sk, rt, skb, src, dst, IPPROTO_UDP,
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index e5ea177..4650c68 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -778,6 +778,8 @@ static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev)
 	__u32 mtu;
 	int err;
 
+	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+
 	if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
 		encap_limit = t->parms.encap_limit;
 
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 137fca4..6c5dfec 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1180,6 +1180,8 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	u8 tproto;
 	int err;
 
+	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+
 	tproto = ACCESS_ONCE(t->parms.proto);
 	if (tproto != IPPROTO_IPIP && tproto != 0)
 		return -1;
-- 
2.1.0


From 7b716c407658787322d55c49dd5d607d1ead43e4 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Mon, 22 Feb 2016 18:43:25 +0100
Subject: [PATCH 03/56] ipv4: only create late gso-skb if skb is already set up
 with CHECKSUM_PARTIAL

[ Upstream commit a8c4a2522a0808c5c2143612909717d1115c40cf ]

Otherwise we break the contract with GSO to only pass CHECKSUM_PARTIAL
skbs down. This can easily happen with UDP+IPv4 sockets with the first
MSG_MORE write smaller than the MTU, second write is a sendfile.

Returning -EOPNOTSUPP lets the callers fall back into normal sendmsg path,
were we calculate the checksum manually during copying.

Commit d749c9cbffd6 ("ipv4: no CHECKSUM_PARTIAL on MSG_MORE corked
sockets") started to exposes this bug.

Fixes: d749c9cbffd6 ("ipv4: no CHECKSUM_PARTIAL on MSG_MORE corked sockets")
Reported-by: Jiri Benc <jbenc@redhat.com>
Cc: Jiri Benc <jbenc@redhat.com>
Reported-by: Wakko Warner <wakko@animx.eu.org>
Cc: Wakko Warner <wakko@animx.eu.org>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_output.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 49f0285..f2ad521 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1237,13 +1237,16 @@ ssize_t	ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
 	if (!skb)
 		return -EINVAL;
 
-	cork->length += size;
 	if ((size + skb->len > mtu) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
 	    (rt->dst.dev->features & NETIF_F_UFO)) {
+		if (skb->ip_summed != CHECKSUM_PARTIAL)
+			return -EOPNOTSUPP;
+
 		skb_shinfo(skb)->gso_size = mtu - fragheaderlen;
 		skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
 	}
+	cork->length += size;
 
 	while (size > 0) {
 		if (skb_is_gso(skb)) {
-- 
2.1.0


From c3f97f54d35d1e06179f28afcfdb201d380904aa Mon Sep 17 00:00:00 2001
From: Diego Viola <diego.viola@gmail.com>
Date: Tue, 23 Feb 2016 12:04:04 -0300
Subject: [PATCH 04/56] net: jme: fix suspend/resume on JMC260

[ Upstream commit ee50c130c82175eaa0820c96b6d3763928af2241 ]

The JMC260 network card fails to suspend/resume because the call to
jme_start_irq() was too early, moving the call to jme_start_irq() after
the call to jme_reset_link() makes it work.

Prior this change suspend/resume would fail unless /sys/power/pm_async=0
was explicitly specified.

Relevant bug report: https://bugzilla.kernel.org/show_bug.cgi?id=112351

Signed-off-by: Diego Viola <diego.viola@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/jme.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c
index 060dd39..973dade 100644
--- a/drivers/net/ethernet/jme.c
+++ b/drivers/net/ethernet/jme.c
@@ -3312,13 +3312,14 @@ jme_resume(struct device *dev)
 		jme_reset_phy_processor(jme);
 	jme_phy_calibration(jme);
 	jme_phy_setEA(jme);
-	jme_start_irq(jme);
 	netif_device_attach(netdev);
 
 	atomic_inc(&jme->link_changing);
 
 	jme_reset_link(jme);
 
+	jme_start_irq(jme);
+
 	return 0;
 }
 
-- 
2.1.0


From a39e7dc0d4005e47a6ec8e58de77abd6c254c64f Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Tue, 23 Feb 2016 10:10:26 -0800
Subject: [PATCH 05/56] net: vrf: Remove direct access to skb->data

[ Upstream commit 65c38aa653c14df49e19faad74bd375f36e61c57 ]

Nik pointed that the VRF driver should be using skb_header_pointer
instead of accessing skb->data and bits beyond directly which can
be garbage.

Fixes: 35402e313663 ("net: Add IPv6 support to VRF device")
Cc: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 0a242b2..903bda4 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -114,20 +114,23 @@ static struct dst_ops vrf_dst_ops = {
 #if IS_ENABLED(CONFIG_IPV6)
 static bool check_ipv6_frame(const struct sk_buff *skb)
 {
-	const struct ipv6hdr *ipv6h = (struct ipv6hdr *)skb->data;
-	size_t hlen = sizeof(*ipv6h);
+	const struct ipv6hdr *ipv6h;
+	struct ipv6hdr _ipv6h;
 	bool rc = true;
 
-	if (skb->len < hlen)
+	ipv6h = skb_header_pointer(skb, 0, sizeof(_ipv6h), &_ipv6h);
+	if (!ipv6h)
 		goto out;
 
 	if (ipv6h->nexthdr == NEXTHDR_ICMP) {
 		const struct icmp6hdr *icmph;
+		struct icmp6hdr _icmph;
 
-		if (skb->len < hlen + sizeof(*icmph))
+		icmph = skb_header_pointer(skb, sizeof(_ipv6h),
+					   sizeof(_icmph), &_icmph);
+		if (!icmph)
 			goto out;
 
-		icmph = (struct icmp6hdr *)(skb->data + sizeof(*ipv6h));
 		switch (icmph->icmp6_type) {
 		case NDISC_ROUTER_SOLICITATION:
 		case NDISC_ROUTER_ADVERTISEMENT:
-- 
2.1.0


From 833cca2bcd768783928bf538d77094dcdfe29034 Mon Sep 17 00:00:00 2001
From: Stefan Wahren <stefan.wahren@i2se.com>
Date: Tue, 23 Feb 2016 19:23:23 +0000
Subject: [PATCH 06/56] net: qca_spi: Don't clear IFF_BROADCAST

[ Upstream commit 2b70bad23c89b121a3e4a00f8968d14ebb78887d ]

Currently qcaspi_netdev_setup accidentally clears IFF_BROADCAST.
So fix this by keeping the flags from ether_setup.

Reported-by: Michael Heimpold <michael.heimpold@i2se.com>
Signed-off-by: Stefan Wahren <stefan.wahren@i2se.com>
Fixes: 291ab06ecf67 (net: qualcomm: new Ethernet over SPI driver for QCA7000)
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qualcomm/qca_spi.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c
index 689a4a5..f2ee3e5f 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.c
+++ b/drivers/net/ethernet/qualcomm/qca_spi.c
@@ -811,7 +811,6 @@ qcaspi_netdev_setup(struct net_device *dev)
 	dev->netdev_ops = &qcaspi_netdev_ops;
 	qcaspi_set_ethtool_ops(dev);
 	dev->watchdog_timeo = QCASPI_TX_TIMEOUT;
-	dev->flags = IFF_MULTICAST;
 	dev->tx_queue_len = 100;
 
 	qca = netdev_priv(dev);
-- 
2.1.0


From da10634ea8bc9cac8ccbcd4798323f9d2c520833 Mon Sep 17 00:00:00 2001
From: Stefan Wahren <stefan.wahren@i2se.com>
Date: Tue, 23 Feb 2016 19:23:24 +0000
Subject: [PATCH 07/56] net: qca_spi: clear IFF_TX_SKB_SHARING

[ Upstream commit a4690afeb0d2d7ba4d60dfa98a89f3bb1ce60ecd ]

ether_setup sets IFF_TX_SKB_SHARING but this is not supported by
qca_spi as it modifies the skb on xmit.

Signed-off-by: Stefan Wahren <stefan.wahren@i2se.com>
Fixes: 291ab06ecf67 (net: qualcomm: new Ethernet over SPI driver for QCA7000)
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qualcomm/qca_spi.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c
index f2ee3e5f..1ef0393 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.c
+++ b/drivers/net/ethernet/qualcomm/qca_spi.c
@@ -811,6 +811,7 @@ qcaspi_netdev_setup(struct net_device *dev)
 	dev->netdev_ops = &qcaspi_netdev_ops;
 	qcaspi_set_ethtool_ops(dev);
 	dev->watchdog_timeo = QCASPI_TX_TIMEOUT;
+	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	dev->tx_queue_len = 100;
 
 	qca = netdev_priv(dev);
-- 
2.1.0


From 1e75210559970855c909e59a3b19b7428ad1999a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Linus=20L=C3=BCssing?= <linus.luessing@c0d3.blue>
Date: Wed, 24 Feb 2016 04:21:42 +0100
Subject: [PATCH 08/56] net: fix bridge multicast packet checksum validation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 9b368814b336b0a1a479135eb2815edbc00efd3c ]

We need to update the skb->csum after pulling the skb, otherwise
an unnecessary checksum (re)computation can ocure for IGMP/MLD packets
in the bridge code. Additionally this fixes the following splats for
network devices / bridge ports with support for and enabled RX checksum
offloading:

[...]
[   43.986968] eth0: hw csum failure
[   43.990344] CPU: 3 PID: 0 Comm: swapper/3 Not tainted 4.4.0 #2
[   43.996193] Hardware name: BCM2709
[   43.999647] [<800204e0>] (unwind_backtrace) from [<8001cf14>] (show_stack+0x10/0x14)
[   44.007432] [<8001cf14>] (show_stack) from [<801ab614>] (dump_stack+0x80/0x90)
[   44.014695] [<801ab614>] (dump_stack) from [<802e4548>] (__skb_checksum_complete+0x6c/0xac)
[   44.023090] [<802e4548>] (__skb_checksum_complete) from [<803a055c>] (ipv6_mc_validate_checksum+0x104/0x178)
[   44.032959] [<803a055c>] (ipv6_mc_validate_checksum) from [<802e111c>] (skb_checksum_trimmed+0x130/0x188)
[   44.042565] [<802e111c>] (skb_checksum_trimmed) from [<803a06e8>] (ipv6_mc_check_mld+0x118/0x338)
[   44.051501] [<803a06e8>] (ipv6_mc_check_mld) from [<803b2c98>] (br_multicast_rcv+0x5dc/0xd00)
[   44.060077] [<803b2c98>] (br_multicast_rcv) from [<803aa510>] (br_handle_frame_finish+0xac/0x51c)
[...]

Fixes: 9afd85c9e455 ("net: Export IGMP/MLD message validation code")
Reported-by: Álvaro Fernández Rojas <noltari@gmail.com>
Signed-off-by: Linus Lüssing <linus.luessing@c0d3.blue>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 17 +++++++++++++++++
 net/core/skbuff.c      | 22 ++++++++++++++++++++--
 2 files changed, 37 insertions(+), 2 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 75f136a..d84c593 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2724,6 +2724,23 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb,
 
 unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len);
 
+static inline void skb_postpush_rcsum(struct sk_buff *skb,
+				      const void *start, unsigned int len)
+{
+	/* For performing the reverse operation to skb_postpull_rcsum(),
+	 * we can instead of ...
+	 *
+	 *   skb->csum = csum_add(skb->csum, csum_partial(start, len, 0));
+	 *
+	 * ... just use this equivalent version here to save a few
+	 * instructions. Feeding csum of 0 in csum_partial() and later
+	 * on adding skb->csum is equivalent to feed skb->csum in the
+	 * first place.
+	 */
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		skb->csum = csum_partial(start, len, skb->csum);
+}
+
 /**
  *	pskb_trim_rcsum - trim received skb and update checksum
  *	@skb: buffer to trim
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 5bf88f5..8616d11 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2948,6 +2948,24 @@ int skb_append_pagefrags(struct sk_buff *skb, struct page *page,
 EXPORT_SYMBOL_GPL(skb_append_pagefrags);
 
 /**
+ *	skb_push_rcsum - push skb and update receive checksum
+ *	@skb: buffer to update
+ *	@len: length of data pulled
+ *
+ *	This function performs an skb_push on the packet and updates
+ *	the CHECKSUM_COMPLETE checksum.  It should be used on
+ *	receive path processing instead of skb_push unless you know
+ *	that the checksum difference is zero (e.g., a valid IP header)
+ *	or you are setting ip_summed to CHECKSUM_NONE.
+ */
+static unsigned char *skb_push_rcsum(struct sk_buff *skb, unsigned len)
+{
+	skb_push(skb, len);
+	skb_postpush_rcsum(skb, skb->data, len);
+	return skb->data;
+}
+
+/**
  *	skb_pull_rcsum - pull skb and update receive checksum
  *	@skb: buffer to update
  *	@len: length of data pulled
@@ -4084,9 +4102,9 @@ struct sk_buff *skb_checksum_trimmed(struct sk_buff *skb,
 	if (!pskb_may_pull(skb_chk, offset))
 		goto err;
 
-	__skb_pull(skb_chk, offset);
+	skb_pull_rcsum(skb_chk, offset);
 	ret = skb_chkf(skb_chk);
-	__skb_push(skb_chk, offset);
+	skb_push_rcsum(skb_chk, offset);
 
 	if (ret)
 		goto err;
-- 
2.1.0


From 13d08314d28473268aa646183efead95590cc76b Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 28 Feb 2016 10:03:51 +0800
Subject: [PATCH 09/56] sctp: lack the check for ports in sctp_v6_cmp_addr

[ Upstream commit 40b4f0fd74e46c017814618d67ec9127ff20f157 ]

As the member .cmp_addr of sctp_af_inet6, sctp_v6_cmp_addr should also check
the port of addresses, just like sctp_v4_cmp_addr, cause it's invoked by
sctp_cmp_addr_exact().

Now sctp_v6_cmp_addr just check the port when two addresses have different
family, and lack the port check for two ipv6 addresses. that will make
sctp_hash_cmp() cannot work well.

so fix it by adding ports comparison in sctp_v6_cmp_addr().

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ipv6.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index ec52912..ce46f1c 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -526,6 +526,8 @@ static int sctp_v6_cmp_addr(const union sctp_addr *addr1,
 		}
 		return 0;
 	}
+	if (addr1->v6.sin6_port != addr2->v6.sin6_port)
+		return 0;
 	if (!ipv6_addr_equal(&addr1->v6.sin6_addr, &addr2->v6.sin6_addr))
 		return 0;
 	/* If this is a linklocal address, compare the scope_id. */
-- 
2.1.0


From bf68d39769c2b1adde8f2a02969693019044d0eb Mon Sep 17 00:00:00 2001
From: Benjamin Poirier <bpoirier@suse.com>
Date: Mon, 29 Feb 2016 15:03:33 -0800
Subject: [PATCH 10/56] mld, igmp: Fix reserved tailroom calculation

[ Upstream commit 1837b2e2bcd23137766555a63867e649c0b637f0 ]

The current reserved_tailroom calculation fails to take hlen and tlen into
account.

skb:
[__hlen__|__data____________|__tlen___|__extra__]
^                                               ^
head                                            skb_end_offset

In this representation, hlen + data + tlen is the size passed to alloc_skb.
"extra" is the extra space made available in __alloc_skb because of
rounding up by kmalloc. We can reorder the representation like so:

[__hlen__|__data____________|__extra__|__tlen___]
^                                               ^
head                                            skb_end_offset

The maximum space available for ip headers and payload without
fragmentation is min(mtu, data + extra). Therefore,
reserved_tailroom
= data + extra + tlen - min(mtu, data + extra)
= skb_end_offset - hlen - min(mtu, skb_end_offset - hlen - tlen)
= skb_tailroom - min(mtu, skb_tailroom - tlen) ; after skb_reserve(hlen)

Compare the second line to the current expression:
reserved_tailroom = skb_end_offset - min(mtu, skb_end_offset)
and we can see that hlen and tlen are not taken into account.

The min() in the third line can be expanded into:
if mtu < skb_tailroom - tlen:
	reserved_tailroom = skb_tailroom - mtu
else:
	reserved_tailroom = tlen

Depending on hlen, tlen, mtu and the number of multicast address records,
the current code may output skbs that have less tailroom than
dev->needed_tailroom or it may output more skbs than needed because not all
space available is used.

Fixes: 4c672e4b ("ipv6: mld: fix add_grhead skb_over_panic for devs with large MTUs")
Signed-off-by: Benjamin Poirier <bpoirier@suse.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 24 ++++++++++++++++++++++++
 net/ipv4/igmp.c        |  3 +--
 net/ipv6/mcast.c       |  3 +--
 3 files changed, 26 insertions(+), 4 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index d84c593..4fde618 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1908,6 +1908,30 @@ static inline void skb_reserve(struct sk_buff *skb, int len)
 	skb->tail += len;
 }
 
+/**
+ *	skb_tailroom_reserve - adjust reserved_tailroom
+ *	@skb: buffer to alter
+ *	@mtu: maximum amount of headlen permitted
+ *	@needed_tailroom: minimum amount of reserved_tailroom
+ *
+ *	Set reserved_tailroom so that headlen can be as large as possible but
+ *	not larger than mtu and tailroom cannot be smaller than
+ *	needed_tailroom.
+ *	The required headroom should already have been reserved before using
+ *	this function.
+ */
+static inline void skb_tailroom_reserve(struct sk_buff *skb, unsigned int mtu,
+					unsigned int needed_tailroom)
+{
+	SKB_LINEAR_ASSERT(skb);
+	if (mtu < skb_tailroom(skb) - needed_tailroom)
+		/* use at most mtu */
+		skb->reserved_tailroom = skb_tailroom(skb) - mtu;
+	else
+		/* use up to all available space */
+		skb->reserved_tailroom = needed_tailroom;
+}
+
 #define ENCAP_TYPE_ETHER	0
 #define ENCAP_TYPE_IPPROTO	1
 
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 05e4cba..b3086cf 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -356,9 +356,8 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu)
 	skb_dst_set(skb, &rt->dst);
 	skb->dev = dev;
 
-	skb->reserved_tailroom = skb_end_offset(skb) -
-				 min(mtu, skb_end_offset(skb));
 	skb_reserve(skb, hlen);
+	skb_tailroom_reserve(skb, mtu, tlen);
 
 	skb_reset_network_header(skb);
 	pip = ip_hdr(skb);
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 5ee56d0..d64ee7e 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1574,9 +1574,8 @@ static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu)
 		return NULL;
 
 	skb->priority = TC_PRIO_CONTROL;
-	skb->reserved_tailroom = skb_end_offset(skb) -
-				 min(mtu, skb_end_offset(skb));
 	skb_reserve(skb, hlen);
+	skb_tailroom_reserve(skb, mtu, tlen);
 
 	if (__ipv6_get_lladdr(idev, &addr_buf, IFA_F_TENTATIVE)) {
 		/* <draft-ietf-magma-mld-source-05.txt>:
-- 
2.1.0


From e4bcc002f7d57b7d186b3fb2111a6253a800d675 Mon Sep 17 00:00:00 2001
From: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
Date: Tue, 1 Mar 2016 11:07:09 +0100
Subject: [PATCH 11/56] tipc: Revert "tipc: use existing sk_write_queue for
 outgoing packet chain"

[ Upstream commit f214fc402967e1bc94ad7f39faa03db5813d6849 ]

reverts commit 94153e36e709e ("tipc: use existing sk_write_queue for
outgoing packet chain")

In Commit 94153e36e709e, we assume that we fill & empty the socket's
sk_write_queue within the same lock_sock() session.

This is not true if the link is congested. During congestion, the
socket lock is released while we wait for the congestion to cease.
This implementation causes a nullptr exception, if the user space
program has several threads accessing the same socket descriptor.

Consider two threads of the same program performing the following:
     Thread1                                  Thread2
--------------------                    ----------------------
Enter tipc_sendmsg()                    Enter tipc_sendmsg()
lock_sock()                             lock_sock()
Enter tipc_link_xmit(), ret=ELINKCONG   spin on socket lock..
sk_wait_event()                             :
release_sock()                          grab socket lock
    :                                   Enter tipc_link_xmit(), ret=0
    :                                   release_sock()
Wakeup after congestion
lock_sock()
skb = skb_peek(pktchain);
!! TIPC_SKB_CB(skb)->wakeup_pending = tsk->link_cong;

In this case, the second thread transmits the buffers belonging to
both thread1 and thread2 successfully. When the first thread wakeup
after the congestion it assumes that the pktchain is intact and
operates on the skb's in it, which leads to the following exception:

[2102.439969] BUG: unable to handle kernel NULL pointer dereference at 00000000000000d0
[2102.440074] IP: [<ffffffffa005f330>] __tipc_link_xmit+0x2b0/0x4d0 [tipc]
[2102.440074] PGD 3fa3f067 PUD 3fa6b067 PMD 0
[2102.440074] Oops: 0000 [#1] SMP
[2102.440074] CPU: 2 PID: 244 Comm: sender Not tainted 3.12.28 #1
[2102.440074] RIP: 0010:[<ffffffffa005f330>]  [<ffffffffa005f330>] __tipc_link_xmit+0x2b0/0x4d0 [tipc]
[...]
[2102.440074] Call Trace:
[2102.440074]  [<ffffffff8163f0b9>] ? schedule+0x29/0x70
[2102.440074]  [<ffffffffa006a756>] ? tipc_node_unlock+0x46/0x170 [tipc]
[2102.440074]  [<ffffffffa005f761>] tipc_link_xmit+0x51/0xf0 [tipc]
[2102.440074]  [<ffffffffa006d8ae>] tipc_send_stream+0x11e/0x4f0 [tipc]
[2102.440074]  [<ffffffff8106b150>] ? __wake_up_sync+0x20/0x20
[2102.440074]  [<ffffffffa006dc9c>] tipc_send_packet+0x1c/0x20 [tipc]
[2102.440074]  [<ffffffff81502478>] sock_sendmsg+0xa8/0xd0
[2102.440074]  [<ffffffff81507895>] ? release_sock+0x145/0x170
[2102.440074]  [<ffffffff815030d8>] ___sys_sendmsg+0x3d8/0x3e0
[2102.440074]  [<ffffffff816426ae>] ? _raw_spin_unlock+0xe/0x10
[2102.440074]  [<ffffffff81115c2a>] ? handle_mm_fault+0x6ca/0x9d0
[2102.440074]  [<ffffffff8107dd65>] ? set_next_entity+0x85/0xa0
[2102.440074]  [<ffffffff816426de>] ? _raw_spin_unlock_irq+0xe/0x20
[2102.440074]  [<ffffffff8107463c>] ? finish_task_switch+0x5c/0xc0
[2102.440074]  [<ffffffff8163ea8c>] ? __schedule+0x34c/0x950
[2102.440074]  [<ffffffff81504e12>] __sys_sendmsg+0x42/0x80
[2102.440074]  [<ffffffff81504e62>] SyS_sendmsg+0x12/0x20
[2102.440074]  [<ffffffff8164aed2>] system_call_fastpath+0x16/0x1b

In this commit, we maintain the skb list always in the stack.

Signed-off-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/socket.c | 33 +++++++++++++++++++--------------
 1 file changed, 19 insertions(+), 14 deletions(-)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index b53246f..e53003c 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -673,7 +673,7 @@ static int tipc_sendmcast(struct  socket *sock, struct tipc_name_seq *seq,
 	struct tipc_sock *tsk = tipc_sk(sk);
 	struct net *net = sock_net(sk);
 	struct tipc_msg *mhdr = &tsk->phdr;
-	struct sk_buff_head *pktchain = &sk->sk_write_queue;
+	struct sk_buff_head pktchain;
 	struct iov_iter save = msg->msg_iter;
 	uint mtu;
 	int rc;
@@ -687,14 +687,16 @@ static int tipc_sendmcast(struct  socket *sock, struct tipc_name_seq *seq,
 	msg_set_nameupper(mhdr, seq->upper);
 	msg_set_hdr_sz(mhdr, MCAST_H_SIZE);
 
+	skb_queue_head_init(&pktchain);
+
 new_mtu:
 	mtu = tipc_bcast_get_mtu(net);
-	rc = tipc_msg_build(mhdr, msg, 0, dsz, mtu, pktchain);
+	rc = tipc_msg_build(mhdr, msg, 0, dsz, mtu, &pktchain);
 	if (unlikely(rc < 0))
 		return rc;
 
 	do {
-		rc = tipc_bcast_xmit(net, pktchain);
+		rc = tipc_bcast_xmit(net, &pktchain);
 		if (likely(!rc))
 			return dsz;
 
@@ -704,7 +706,7 @@ new_mtu:
 			if (!rc)
 				continue;
 		}
-		__skb_queue_purge(pktchain);
+		__skb_queue_purge(&pktchain);
 		if (rc == -EMSGSIZE) {
 			msg->msg_iter = save;
 			goto new_mtu;
@@ -863,7 +865,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz)
 	struct net *net = sock_net(sk);
 	struct tipc_msg *mhdr = &tsk->phdr;
 	u32 dnode, dport;
-	struct sk_buff_head *pktchain = &sk->sk_write_queue;
+	struct sk_buff_head pktchain;
 	struct sk_buff *skb;
 	struct tipc_name_seq *seq;
 	struct iov_iter save;
@@ -924,17 +926,18 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz)
 		msg_set_hdr_sz(mhdr, BASIC_H_SIZE);
 	}
 
+	skb_queue_head_init(&pktchain);
 	save = m->msg_iter;
 new_mtu:
 	mtu = tipc_node_get_mtu(net, dnode, tsk->portid);
-	rc = tipc_msg_build(mhdr, m, 0, dsz, mtu, pktchain);
+	rc = tipc_msg_build(mhdr, m, 0, dsz, mtu, &pktchain);
 	if (rc < 0)
 		return rc;
 
 	do {
-		skb = skb_peek(pktchain);
+		skb = skb_peek(&pktchain);
 		TIPC_SKB_CB(skb)->wakeup_pending = tsk->link_cong;
-		rc = tipc_node_xmit(net, pktchain, dnode, tsk->portid);
+		rc = tipc_node_xmit(net, &pktchain, dnode, tsk->portid);
 		if (likely(!rc)) {
 			if (sock->state != SS_READY)
 				sock->state = SS_CONNECTING;
@@ -946,7 +949,7 @@ new_mtu:
 			if (!rc)
 				continue;
 		}
-		__skb_queue_purge(pktchain);
+		__skb_queue_purge(&pktchain);
 		if (rc == -EMSGSIZE) {
 			m->msg_iter = save;
 			goto new_mtu;
@@ -1016,7 +1019,7 @@ static int __tipc_send_stream(struct socket *sock, struct msghdr *m, size_t dsz)
 	struct net *net = sock_net(sk);
 	struct tipc_sock *tsk = tipc_sk(sk);
 	struct tipc_msg *mhdr = &tsk->phdr;
-	struct sk_buff_head *pktchain = &sk->sk_write_queue;
+	struct sk_buff_head pktchain;
 	DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
 	u32 portid = tsk->portid;
 	int rc = -EINVAL;
@@ -1044,17 +1047,19 @@ static int __tipc_send_stream(struct socket *sock, struct msghdr *m, size_t dsz)
 
 	timeo = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT);
 	dnode = tsk_peer_node(tsk);
+	skb_queue_head_init(&pktchain);
 
 next:
 	save = m->msg_iter;
 	mtu = tsk->max_pkt;
 	send = min_t(uint, dsz - sent, TIPC_MAX_USER_MSG_SIZE);
-	rc = tipc_msg_build(mhdr, m, sent, send, mtu, pktchain);
+	rc = tipc_msg_build(mhdr, m, sent, send, mtu, &pktchain);
 	if (unlikely(rc < 0))
 		return rc;
+
 	do {
 		if (likely(!tsk_conn_cong(tsk))) {
-			rc = tipc_node_xmit(net, pktchain, dnode, portid);
+			rc = tipc_node_xmit(net, &pktchain, dnode, portid);
 			if (likely(!rc)) {
 				tsk->sent_unacked++;
 				sent += send;
@@ -1063,7 +1068,7 @@ next:
 				goto next;
 			}
 			if (rc == -EMSGSIZE) {
-				__skb_queue_purge(pktchain);
+				__skb_queue_purge(&pktchain);
 				tsk->max_pkt = tipc_node_get_mtu(net, dnode,
 								 portid);
 				m->msg_iter = save;
@@ -1077,7 +1082,7 @@ next:
 		rc = tipc_wait_for_sndpkt(sock, &timeo);
 	} while (!rc);
 
-	__skb_queue_purge(pktchain);
+	__skb_queue_purge(&pktchain);
 	return sent ? sent : rc;
 }
 
-- 
2.1.0


From 38df1d74cf2599fa7fab72db4ab13526e76dd83b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Tue, 1 Mar 2016 14:31:02 +0100
Subject: [PATCH 12/56] qmi_wwan: add Sierra Wireless EM74xx device ID
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit bf13c94ccb33c3182efc92ce4989506a0f541243 ]

The MC74xx and EM74xx modules use different IDs by default, according
to the Lenovo EM7455 driver for Windows.

Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 982e0acd..df77467 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -718,8 +718,10 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1199, 0x9061, 8)},	/* Sierra Wireless Modem */
 	{QMI_FIXED_INTF(0x1199, 0x9070, 8)},	/* Sierra Wireless MC74xx/EM74xx */
 	{QMI_FIXED_INTF(0x1199, 0x9070, 10)},	/* Sierra Wireless MC74xx/EM74xx */
-	{QMI_FIXED_INTF(0x1199, 0x9071, 8)},	/* Sierra Wireless MC74xx/EM74xx */
-	{QMI_FIXED_INTF(0x1199, 0x9071, 10)},	/* Sierra Wireless MC74xx/EM74xx */
+	{QMI_FIXED_INTF(0x1199, 0x9071, 8)},	/* Sierra Wireless MC74xx */
+	{QMI_FIXED_INTF(0x1199, 0x9071, 10)},	/* Sierra Wireless MC74xx */
+	{QMI_FIXED_INTF(0x1199, 0x9079, 8)},	/* Sierra Wireless EM74xx */
+	{QMI_FIXED_INTF(0x1199, 0x9079, 10)},	/* Sierra Wireless EM74xx */
 	{QMI_FIXED_INTF(0x1bbb, 0x011e, 4)},	/* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */
 	{QMI_FIXED_INTF(0x1bbb, 0x0203, 2)},	/* Alcatel L800MA */
 	{QMI_FIXED_INTF(0x2357, 0x0201, 4)},	/* TP-LINK HSUPA Modem MA180 */
-- 
2.1.0


From c754bfdd7123895f10d7692d526e450741433479 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 1 Mar 2016 16:15:16 +0100
Subject: [PATCH 13/56] ipv6: re-enable fragment header matching in
 ipv6_find_hdr

[ Upstream commit 5d150a985520bbe3cb2aa1ceef24a7e32f20c15f ]

When ipv6_find_hdr is used to find a fragment header
(caller specifies target NEXTHDR_FRAGMENT) we erronously return
-ENOENT for all fragments with nonzero offset.

Before commit 9195bb8e381d, when target was specified, we did not
enter the exthdr walk loop as nexthdr == target so this used to work.

Now we do (so we can skip empty route headers). When we then stumble upon
a frag with nonzero frag_off we must return -ENOENT ("header not found")
only if the caller did not specifically request NEXTHDR_FRAGMENT.

This allows nfables exthdr expression to match ipv6 fragments, e.g. via

nft add rule ip6 filter input frag frag-off gt 0

Fixes: 9195bb8e381d ("ipv6: improve ipv6_find_hdr() to skip empty routing headers")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/exthdrs_core.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c
index 5c5d23e..9508a20 100644
--- a/net/ipv6/exthdrs_core.c
+++ b/net/ipv6/exthdrs_core.c
@@ -257,7 +257,11 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
 						*fragoff = _frag_off;
 					return hp->nexthdr;
 				}
-				return -ENOENT;
+				if (!found)
+					return -ENOENT;
+				if (fragoff)
+					*fragoff = _frag_off;
+				break;
 			}
 			hdrlen = 8;
 		} else if (nexthdr == NEXTHDR_AUTH) {
-- 
2.1.0


From 957ce5000fb04671c9554b7cd0f82763ea2e0dd5 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 2 Mar 2016 02:32:08 +0100
Subject: [PATCH 14/56] vxlan: fix missing options_len update on RX with
 collect metadata

[ Upstream commit 4024fcf70556311521e7b6cf79fa50e16f31013a ]

When signalling to metadata consumers that the metadata_dst entry
carries additional GBP extension data for vxlan (TUNNEL_VXLAN_OPT),
the dst's vxlan_metadata information is populated, but options_len
is left to zero. F.e. in ovs, ovs_flow_key_extract() checks for
options_len before extracting the data through ip_tunnel_info_opts_get().

Geneve uses ip_tunnel_info_opts_set() helper in receive path, which
sets options_len internally, vxlan however uses ip_tunnel_info_opts(),
so when filling vxlan_metadata, we do need to update options_len.

Fixes: 4c22279848c5 ("ip-tunnel: Use API to access tunnel metadata options.")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index e0fcda4..3c0df70 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1306,8 +1306,10 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 		gbp = (struct vxlanhdr_gbp *)vxh;
 		md->gbp = ntohs(gbp->policy_id);
 
-		if (tun_dst)
+		if (tun_dst) {
 			tun_dst->u.tun_info.key.tun_flags |= TUNNEL_VXLAN_OPT;
+			tun_dst->u.tun_info.options_len = sizeof(*md);
+		}
 
 		if (gbp->dont_learn)
 			md->gbp |= VXLAN_GBP_DONT_LEARN;
-- 
2.1.0


From 8a1c0e2b385932cbd4161be97ed26bd21701e82f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Thu, 3 Mar 2016 22:20:53 +0100
Subject: [PATCH 15/56] cdc_ncm: toggle altsetting to force reset before setup
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 48906f62c96cc2cd35753e59310cb70eb08cc6a5 ]

Some devices will silently fail setup unless they are reset first.
This is necessary even if the data interface is already in
altsetting 0, which it will be when the device is probed for the
first time.  Briefly toggling the altsetting forces a function
reset regardless of the initial state.

This fixes a setup problem observed on a number of Huawei devices,
appearing to operate in NTB-32 mode even if we explicitly set them
to NTB-16 mode.

Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ncm.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index e8a1144..8c2bb77 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -794,7 +794,11 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_
 
 	iface_no = ctx->data->cur_altsetting->desc.bInterfaceNumber;
 
-	/* reset data interface */
+	/* Reset data interface. Some devices will not reset properly
+	 * unless they are configured first.  Toggle the altsetting to
+	 * force a reset
+	 */
+	usb_set_interface(dev->udev, iface_no, data_altsetting);
 	temp = usb_set_interface(dev->udev, iface_no, 0);
 	if (temp) {
 		dev_dbg(&intf->dev, "set interface failed\n");
-- 
2.1.0


From e7480c68b67aa644589da04caf4ebeb71e21a3e9 Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.com>
Date: Mon, 7 Mar 2016 11:31:10 +0100
Subject: [PATCH 16/56] usbnet: cleanup after bind() in probe()

[ Upstream commit 1666984c8625b3db19a9abc298931d35ab7bc64b ]

In case bind() works, but a later error forces bailing
in probe() in error cases work and a timer may be scheduled.
They must be killed. This fixes an error case related to
the double free reported in
http://www.spinics.net/lists/netdev/msg367669.html
and needs to go on top of Linus' fix to cdc-ncm.

Signed-off-by: Oliver Neukum <ONeukum@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/usbnet.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 0744bf2..c2ea4e5 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -1766,6 +1766,13 @@ out3:
 	if (info->unbind)
 		info->unbind (dev, udev);
 out1:
+	/* subdrivers must undo all they did in bind() if they
+	 * fail it, but we may fail later and a deferred kevent
+	 * may trigger an error resubmitting itself and, worse,
+	 * schedule a timer. So we kill it all just in case.
+	 */
+	cancel_work_sync(&dev->kevent);
+	del_timer_sync(&dev->delay);
 	free_netdev(net);
 out:
 	return status;
-- 
2.1.0


From a77d746c5680fc9ee7dafc31a37dda2564dacdd0 Mon Sep 17 00:00:00 2001
From: Bill Sommerfeld <wsommerfeld@google.com>
Date: Fri, 4 Mar 2016 14:47:21 -0800
Subject: [PATCH 17/56] udp6: fix UDP/IPv6 encap resubmit path

[ Upstream commit 59dca1d8a6725a121dae6c452de0b2611d5865dc ]

IPv4 interprets a negative return value from a protocol handler as a
request to redispatch to a new protocol.  In contrast, IPv6 interprets a
negative value as an error, and interprets a positive value as a request
for redispatch.

UDP for IPv6 was unaware of this difference.  Change __udp6_lib_rcv() to
return a positive value for redispatch.  Note that the socket's
encap_rcv hook still needs to return a negative value to request
dispatch, and in the case of IPv6 packets, adjust IP6CB(skb)->nhoff to
identify the byte containing the next protocol.

Signed-off-by: Bill Sommerfeld <wsommerfeld@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/udp.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 9da3287..1e293a5 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -916,11 +916,9 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 		ret = udpv6_queue_rcv_skb(sk, skb);
 		sock_put(sk);
 
-		/* a return value > 0 means to resubmit the input, but
-		 * it wants the return to be -protocol, or 0
-		 */
+		/* a return value > 0 means to resubmit the input */
 		if (ret > 0)
-			return -ret;
+			return ret;
 
 		return 0;
 	}
-- 
2.1.0


From 9e689bc819a6bb49ae2ade70bb332051f2492ec6 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 6 Mar 2016 09:29:21 -0800
Subject: [PATCH 18/56] tcp: fix tcpi_segs_in after connection establishment

[ Upstream commit a9d99ce28ed359d68cf6f3c1a69038aefedf6d6a ]

If final packet (ACK) of 3WHS is lost, it appears we do not properly
account the following incoming segment into tcpi_segs_in

While we are at it, starts segs_in with one, to count the SYN packet.

We do not yet count number of SYN we received for a request sock, we
might add this someday.

packetdrill script showing proper behavior after fix :

// Tests tcpi_segs_in when 3rd packet (ACK) of 3WHS is lost
0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
   +0 bind(3, ..., ...) = 0
   +0 listen(3, 1) = 0

   +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop>
   +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK>
+.020 < P. 1:1001(1000) ack 1 win 32792

   +0 accept(3, ..., ...) = 4

+.000 %{ assert tcpi_segs_in == 2, 'tcpi_segs_in=%d' % tcpi_segs_in }%

Fixes: 2efd055c53c06 ("tcp: add tcpi_segs_in and tcpi_segs_out to tcp_info")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_minisocks.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index ac6b196..9475a27 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -458,7 +458,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 
 		newtp->rcv_wup = newtp->copied_seq =
 		newtp->rcv_nxt = treq->rcv_isn + 1;
-		newtp->segs_in = 0;
+		newtp->segs_in = 1;
 
 		newtp->snd_sml = newtp->snd_una =
 		newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1;
@@ -818,6 +818,7 @@ int tcp_child_process(struct sock *parent, struct sock *child,
 	int ret = 0;
 	int state = child->sk_state;
 
+	tcp_sk(child)->segs_in += max_t(u16, 1, skb_shinfo(skb)->gso_segs);
 	if (!sock_owned_by_user(child)) {
 		ret = tcp_rcv_state_process(child, skb);
 		/* Wakeup parent, send SIGIO */
-- 
2.1.0


From 05225f8ff251f8b4e36dfa334f0b1e2e441f573f Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Mon, 7 Mar 2016 19:36:44 +0100
Subject: [PATCH 19/56] ppp: release rtnl mutex when interface creation fails

[ Upstream commit 6faac63a6986f29ef39827f460edd3a5ba64ad5c ]

Add missing rtnl_unlock() in the error path of ppp_create_interface().

Fixes: 58a89ecaca53 ("ppp: fix lockdep splat in ppp_dev_uninit()")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/ppp_generic.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 9a863c6..40b303e 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -2803,6 +2803,7 @@ static struct ppp *ppp_create_interface(struct net *net, int unit,
 
 out2:
 	mutex_unlock(&pn->all_ppp_mutex);
+	rtnl_unlock();
 	free_netdev(dev);
 out1:
 	*retp = ret;
-- 
2.1.0


From 5b27270ee02d1ff73770db29e437a5593342308b Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 9 Mar 2016 21:58:32 -0500
Subject: [PATCH 20/56] net: validate variable length ll headers

[ Upstream commit 2793a23aacbd754dbbb5cb75093deb7e4103bace ]

Netdevice parameter hard_header_len is variously interpreted both as
an upper and lower bound on link layer header length. The field is
used as upper bound when reserving room at allocation, as lower bound
when validating user input in PF_PACKET.

Clarify the definition to be maximum header length. For validation
of untrusted headers, add an optional validate member to header_ops.

Allow bypassing of validation by passing CAP_SYS_RAWIO, for instance
for deliberate testing of corrupt input. In this case, pad trailing
bytes, as some device drivers expect completely initialized headers.

See also http://comments.gmane.org/gmane.linux.network/401064

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 22 ++++++++++++++++++++--
 1 file changed, 20 insertions(+), 2 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 3143c84..04c068e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -265,6 +265,7 @@ struct header_ops {
 	void	(*cache_update)(struct hh_cache *hh,
 				const struct net_device *dev,
 				const unsigned char *haddr);
+	bool	(*validate)(const char *ll_header, unsigned int len);
 };
 
 /* These flag bits are private to the generic network queueing
@@ -1398,8 +1399,7 @@ enum netdev_priv_flags {
  *	@dma:		DMA channel
  *	@mtu:		Interface MTU value
  *	@type:		Interface hardware type
- *	@hard_header_len: Hardware header length, which means that this is the
- *			  minimum size of a packet.
+ *	@hard_header_len: Maximum hardware header length.
  *
  *	@needed_headroom: Extra headroom the hardware may need, but not in all
  *			  cases can this be guaranteed
@@ -2493,6 +2493,24 @@ static inline int dev_parse_header(const struct sk_buff *skb,
 	return dev->header_ops->parse(skb, haddr);
 }
 
+/* ll_header must have at least hard_header_len allocated */
+static inline bool dev_validate_header(const struct net_device *dev,
+				       char *ll_header, int len)
+{
+	if (likely(len >= dev->hard_header_len))
+		return true;
+
+	if (capable(CAP_SYS_RAWIO)) {
+		memset(ll_header + len, 0, dev->hard_header_len - len);
+		return true;
+	}
+
+	if (dev->header_ops && dev->header_ops->validate)
+		return dev->header_ops->validate(ll_header, len);
+
+	return false;
+}
+
 typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr, int len);
 int register_gifconf(unsigned int family, gifconf_func_t *gifconf);
 static inline int unregister_gifconf(unsigned int family)
-- 
2.1.0


From 93c377f1baf7ba365a3a76c09c5c5f3800dadafa Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 9 Mar 2016 21:58:33 -0500
Subject: [PATCH 21/56] ax25: add link layer header validation function

[ Upstream commit ea47781c26510e5d97f80f9aceafe9065bd5e3aa ]

As variable length protocol, AX25 fails link layer header validation
tests based on a minimum length. header_ops.validate allows protocols
to validate headers that are shorter than hard_header_len. Implement
this callback for AX25.

See also http://comments.gmane.org/gmane.linux.network/401064

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ax25/ax25_ip.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/net/ax25/ax25_ip.c b/net/ax25/ax25_ip.c
index b563a3f..2fa3be9 100644
--- a/net/ax25/ax25_ip.c
+++ b/net/ax25/ax25_ip.c
@@ -228,8 +228,23 @@ netdev_tx_t ax25_ip_xmit(struct sk_buff *skb)
 }
 #endif
 
+static bool ax25_validate_header(const char *header, unsigned int len)
+{
+	ax25_digi digi;
+
+	if (!len)
+		return false;
+
+	if (header[0])
+		return true;
+
+	return ax25_addr_parse(header + 1, len - 1, NULL, NULL, &digi, NULL,
+			       NULL);
+}
+
 const struct header_ops ax25_header_ops = {
 	.create = ax25_hard_header,
+	.validate = ax25_validate_header,
 };
 
 EXPORT_SYMBOL(ax25_header_ops);
-- 
2.1.0


From c4198ee27feaa0f5e8c0a53f7d0886691d4a54df Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 9 Mar 2016 21:58:34 -0500
Subject: [PATCH 22/56] packet: validate variable length ll headers

[ Upstream commit 9ed988cd591500c040b2a6257bc68543e08ceeef ]

Replace link layer header validation check ll_header_truncate with
more generic dev_validate_header.

Validation based on hard_header_len incorrectly drops valid packets
in variable length protocols, such as AX25. dev_validate_header
calls header_ops.validate for such protocols to ensure correctness
below hard_header_len.

See also http://comments.gmane.org/gmane.linux.network/401064

Fixes 9c7077622dd9 ("packet: make packet_snd fail on len smaller than l2 header")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 37 ++++++++++++++++---------------------
 1 file changed, 16 insertions(+), 21 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 992396a..da1ae0e1 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1916,6 +1916,10 @@ retry:
 		goto retry;
 	}
 
+	if (!dev_validate_header(dev, skb->data, len)) {
+		err = -EINVAL;
+		goto out_unlock;
+	}
 	if (len > (dev->mtu + dev->hard_header_len + extra_len) &&
 	    !packet_extra_vlan_len_allowed(dev, skb)) {
 		err = -EMSGSIZE;
@@ -2326,18 +2330,6 @@ static void tpacket_destruct_skb(struct sk_buff *skb)
 	sock_wfree(skb);
 }
 
-static bool ll_header_truncated(const struct net_device *dev, int len)
-{
-	/* net device doesn't like empty head */
-	if (unlikely(len < dev->hard_header_len)) {
-		net_warn_ratelimited("%s: packet size is too short (%d < %d)\n",
-				     current->comm, len, dev->hard_header_len);
-		return true;
-	}
-
-	return false;
-}
-
 static void tpacket_set_protocol(const struct net_device *dev,
 				 struct sk_buff *skb)
 {
@@ -2420,19 +2412,19 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 		if (unlikely(err < 0))
 			return -EINVAL;
 	} else if (dev->hard_header_len) {
-		if (ll_header_truncated(dev, tp_len))
-			return -EINVAL;
+		int hdrlen = min_t(int, dev->hard_header_len, tp_len);
 
 		skb_push(skb, dev->hard_header_len);
-		err = skb_store_bits(skb, 0, data,
-				dev->hard_header_len);
+		err = skb_store_bits(skb, 0, data, hdrlen);
 		if (unlikely(err))
 			return err;
+		if (!dev_validate_header(dev, skb->data, hdrlen))
+			return -EINVAL;
 		if (!skb->protocol)
 			tpacket_set_protocol(dev, skb);
 
-		data += dev->hard_header_len;
-		to_write -= dev->hard_header_len;
+		data += hdrlen;
+		to_write -= hdrlen;
 	}
 
 	offset = offset_in_page(data);
@@ -2763,9 +2755,6 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		offset = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, len);
 		if (unlikely(offset < 0))
 			goto out_free;
-	} else {
-		if (ll_header_truncated(dev, len))
-			goto out_free;
 	}
 
 	/* Returns -EFAULT on error */
@@ -2773,6 +2762,12 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	if (err)
 		goto out_free;
 
+	if (sock->type == SOCK_RAW &&
+	    !dev_validate_header(dev, skb->data, len)) {
+		err = -EINVAL;
+		goto out_free;
+	}
+
 	sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags);
 
 	if (!gso_type && (len > dev->mtu + reserve + extra_len) &&
-- 
2.1.0


From 6bfa54ac92785068e81437fc4cacdba30b098466 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@fb.com>
Date: Wed, 9 Mar 2016 20:02:33 -0800
Subject: [PATCH 23/56] bpf: avoid copying junk bytes in bpf_get_current_comm()

[ Upstream commit cdc4e47da8f4c32eeb6b2061a8a834f4362a12b7 ]

Lots of places in the kernel use memcpy(buf, comm, TASK_COMM_LEN); but
the result is typically passed to print("%s", buf) and extra bytes
after zero don't cause any harm.
In bpf the result of bpf_get_current_comm() is used as the part of
map key and was causing spurious hash map mismatches.
Use strlcpy() to guarantee zero-terminated string.
bpf verifier checks that output buffer is zero-initialized,
so even for short task names the output buffer don't have junk bytes.
Note it's not a security concern, since kprobe+bpf is root only.

Fixes: ffeedafbf023 ("bpf: introduce current->pid, tgid, uid, gid, comm accessors")
Reported-by: Tobias Waldekranz <tobias@waldekranz.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/helpers.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 4504ca6..50da680 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -166,7 +166,7 @@ static u64 bpf_get_current_comm(u64 r1, u64 size, u64 r3, u64 r4, u64 r5)
 	if (!task)
 		return -EINVAL;
 
-	memcpy(buf, task->comm, min_t(size_t, size, sizeof(task->comm)));
+	strlcpy(buf, task->comm, min_t(size_t, size, sizeof(task->comm)));
 	return 0;
 }
 
-- 
2.1.0


From 1b49d4f9624010412c90fd63e668fb19beadae63 Mon Sep 17 00:00:00 2001
From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Date: Tue, 8 Mar 2016 01:36:28 +0300
Subject: [PATCH 24/56] sh_eth: fix NULL pointer dereference in
 sh_eth_ring_format()

[ Upstream commit c1b7fca65070bfadca94dd53a4e6b71cd4f69715 ]

In a low memory situation, if netdev_alloc_skb() fails on a first RX ring
loop iteration  in sh_eth_ring_format(), 'rxdesc' is still NULL.  Avoid
kernel oops by adding the 'rxdesc' check after the loop.

Reported-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/sh_eth.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 6a8fc0f..a1702f4 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -1212,7 +1212,8 @@ static void sh_eth_ring_format(struct net_device *ndev)
 	mdp->dirty_rx = (u32) (i - mdp->num_rx_ring);
 
 	/* Mark the last entry as wrapping the ring. */
-	rxdesc->status |= cpu_to_edmac(mdp, RD_RDLE);
+	if (rxdesc)
+		rxdesc->status |= cpu_to_edmac(mdp, RD_RDLE);
 
 	memset(mdp->tx_ring, 0, tx_ringsize);
 
-- 
2.1.0


From 54bbc993591f09805a0262694d8fb85483113031 Mon Sep 17 00:00:00 2001
From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Date: Tue, 8 Mar 2016 01:37:09 +0300
Subject: [PATCH 25/56] sh_eth: advance 'rxdesc' later in sh_eth_ring_format()

[ Upstream commit d0ba913488dc8c55d1880f5ed34f096dc45fb05d ]

Iff dma_map_single() fails, 'rxdesc'  should point  to the last filled RX
descriptor, so  that it can be marked as the last one, however the driver
would have  already  advanced it by that time. In order to fix that, only
fill  an RX descriptor  once all the data for it is ready.

Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/sh_eth.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index a1702f4..36fc942 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -1185,11 +1185,8 @@ static void sh_eth_ring_format(struct net_device *ndev)
 			break;
 		sh_eth_set_receive_align(skb);
 
-		/* RX descriptor */
-		rxdesc = &mdp->rx_ring[i];
 		/* The size of the buffer is a multiple of 32 bytes. */
 		buf_len = ALIGN(mdp->rx_buf_sz, 32);
-		rxdesc->len = cpu_to_edmac(mdp, buf_len << 16);
 		dma_addr = dma_map_single(&ndev->dev, skb->data, buf_len,
 					  DMA_FROM_DEVICE);
 		if (dma_mapping_error(&ndev->dev, dma_addr)) {
@@ -1197,6 +1194,10 @@ static void sh_eth_ring_format(struct net_device *ndev)
 			break;
 		}
 		mdp->rx_skbuff[i] = skb;
+
+		/* RX descriptor */
+		rxdesc = &mdp->rx_ring[i];
+		rxdesc->len = cpu_to_edmac(mdp, buf_len << 16);
 		rxdesc->addr = cpu_to_edmac(mdp, dma_addr);
 		rxdesc->status = cpu_to_edmac(mdp, RD_RACT | RD_RFP);
 
-- 
2.1.0


From 16e3aa2629140bdc5c93eb4a3d8780b2ec0db8d8 Mon Sep 17 00:00:00 2001
From: Rajesh Borundia <rajesh.borundia@qlogic.com>
Date: Tue, 8 Mar 2016 02:39:57 -0500
Subject: [PATCH 26/56] qlcnic: Remove unnecessary usage of atomic_t

[ Upstream commit 5bf93251cee1fb66141d1d2eaff86e04a9397bdf ]

o atomic_t usage is incorrect as we are not implementing
any atomicity.

Signed-off-by: Rajesh Borundia <rajesh.borundia@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qlcnic/qlcnic.h         | 2 +-
 drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c | 9 ++++-----
 2 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
index 46bbea8..d18667b 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
@@ -1099,7 +1099,7 @@ struct qlcnic_mailbox {
 	unsigned long		status;
 	spinlock_t		queue_lock;	/* Mailbox queue lock */
 	spinlock_t		aen_lock;	/* Mailbox response/AEN lock */
-	atomic_t		rsp_status;
+	u32			rsp_status;
 	u32			num_cmds;
 };
 
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
index 37a731b..e3d1bb7 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
@@ -491,7 +491,7 @@ irqreturn_t qlcnic_83xx_clear_legacy_intr(struct qlcnic_adapter *adapter)
 
 static inline void qlcnic_83xx_notify_mbx_response(struct qlcnic_mailbox *mbx)
 {
-	atomic_set(&mbx->rsp_status, QLC_83XX_MBX_RESPONSE_ARRIVED);
+	mbx->rsp_status = QLC_83XX_MBX_RESPONSE_ARRIVED;
 	complete(&mbx->completion);
 }
 
@@ -510,7 +510,7 @@ static void qlcnic_83xx_poll_process_aen(struct qlcnic_adapter *adapter)
 	if (event &  QLCNIC_MBX_ASYNC_EVENT) {
 		__qlcnic_83xx_process_aen(adapter);
 	} else {
-		if (atomic_read(&mbx->rsp_status) != rsp_status)
+		if (mbx->rsp_status != rsp_status)
 			qlcnic_83xx_notify_mbx_response(mbx);
 	}
 out:
@@ -1023,7 +1023,7 @@ static void qlcnic_83xx_process_aen(struct qlcnic_adapter *adapter)
 		if (event &  QLCNIC_MBX_ASYNC_EVENT) {
 			__qlcnic_83xx_process_aen(adapter);
 		} else {
-			if (atomic_read(&mbx->rsp_status) != rsp_status)
+			if (mbx->rsp_status != rsp_status)
 				qlcnic_83xx_notify_mbx_response(mbx);
 		}
 	}
@@ -4050,7 +4050,6 @@ static void qlcnic_83xx_mailbox_worker(struct work_struct *work)
 	struct qlcnic_adapter *adapter = mbx->adapter;
 	const struct qlcnic_mbx_ops *mbx_ops = mbx->ops;
 	struct device *dev = &adapter->pdev->dev;
-	atomic_t *rsp_status = &mbx->rsp_status;
 	struct list_head *head = &mbx->cmd_q;
 	struct qlcnic_hardware_context *ahw;
 	struct qlcnic_cmd_args *cmd = NULL;
@@ -4063,7 +4062,7 @@ static void qlcnic_83xx_mailbox_worker(struct work_struct *work)
 			return;
 		}
 
-		atomic_set(rsp_status, QLC_83XX_MBX_RESPONSE_WAIT);
+		mbx->rsp_status = QLC_83XX_MBX_RESPONSE_WAIT;
 
 		spin_lock(&mbx->queue_lock);
 
-- 
2.1.0


From 1818551e488a86eb3a30ba6c42480285d6738951 Mon Sep 17 00:00:00 2001
From: Rajesh Borundia <rajesh.borundia@qlogic.com>
Date: Tue, 8 Mar 2016 02:39:58 -0500
Subject: [PATCH 27/56] qlcnic: Fix mailbox completion handling during spurious
 interrupt

[ Upstream commit 819bfe764dceec2f6b4551768453f374b4c60443 ]

o While the driver is in the middle of a MB completion processing
and it receives a spurious MB interrupt, it is mistaken as a good MB
completion interrupt leading to premature completion of the next MB
request. Fix the driver to guard against this by checking the current
state of MB processing and ignore the spurious interrupt.
Also added a stats counter to record this condition.

Signed-off-by: Rajesh Borundia <rajesh.borundia@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qlcnic/qlcnic.h         |  1 +
 drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c | 15 +++++++++++----
 drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c |  3 ++-
 3 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
index d18667b..55007f1 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
@@ -566,6 +566,7 @@ struct qlcnic_adapter_stats {
 	u64  tx_dma_map_error;
 	u64  spurious_intr;
 	u64  mac_filter_limit_overrun;
+	u64  mbx_spurious_intr;
 };
 
 /*
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
index e3d1bb7..f9640d5ce 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
@@ -2338,9 +2338,9 @@ static void qlcnic_83xx_handle_link_aen(struct qlcnic_adapter *adapter,
 
 static irqreturn_t qlcnic_83xx_handle_aen(int irq, void *data)
 {
+	u32 mask, resp, event, rsp_status = QLC_83XX_MBX_RESPONSE_ARRIVED;
 	struct qlcnic_adapter *adapter = data;
 	struct qlcnic_mailbox *mbx;
-	u32 mask, resp, event;
 	unsigned long flags;
 
 	mbx = adapter->ahw->mailbox;
@@ -2350,10 +2350,14 @@ static irqreturn_t qlcnic_83xx_handle_aen(int irq, void *data)
 		goto out;
 
 	event = readl(QLCNIC_MBX_FW(adapter->ahw, 0));
-	if (event &  QLCNIC_MBX_ASYNC_EVENT)
+	if (event &  QLCNIC_MBX_ASYNC_EVENT) {
 		__qlcnic_83xx_process_aen(adapter);
-	else
-		qlcnic_83xx_notify_mbx_response(mbx);
+	} else {
+		if (mbx->rsp_status != rsp_status)
+			qlcnic_83xx_notify_mbx_response(mbx);
+		else
+			adapter->stats.mbx_spurious_intr++;
+	}
 
 out:
 	mask = QLCRDX(adapter->ahw, QLCNIC_DEF_INT_MASK);
@@ -4053,6 +4057,7 @@ static void qlcnic_83xx_mailbox_worker(struct work_struct *work)
 	struct list_head *head = &mbx->cmd_q;
 	struct qlcnic_hardware_context *ahw;
 	struct qlcnic_cmd_args *cmd = NULL;
+	unsigned long flags;
 
 	ahw = adapter->ahw;
 
@@ -4062,7 +4067,9 @@ static void qlcnic_83xx_mailbox_worker(struct work_struct *work)
 			return;
 		}
 
+		spin_lock_irqsave(&mbx->aen_lock, flags);
 		mbx->rsp_status = QLC_83XX_MBX_RESPONSE_WAIT;
+		spin_unlock_irqrestore(&mbx->aen_lock, flags);
 
 		spin_lock(&mbx->queue_lock);
 
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
index 494e810..0a2318c 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
@@ -59,7 +59,8 @@ static const struct qlcnic_stats qlcnic_gstrings_stats[] = {
 	 QLC_OFF(stats.mac_filter_limit_overrun)},
 	{"spurious intr", QLC_SIZEOF(stats.spurious_intr),
 	 QLC_OFF(stats.spurious_intr)},
-
+	{"mbx spurious intr", QLC_SIZEOF(stats.mbx_spurious_intr),
+	 QLC_OFF(stats.mbx_spurious_intr)},
 };
 
 static const char qlcnic_device_gstrings_stats[][ETH_GSTRING_LEN] = {
-- 
2.1.0


From f8ccb3799fa86838e591ecd1b31fe0eade762a5f Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Tue, 8 Mar 2016 15:18:54 -0500
Subject: [PATCH 28/56] macvtap: always pass ethernet header in linear

[ Upstream commit 8e2ad4113ce4671686740f808ff2795395c39eef ]

The stack expects link layer headers in the skb linear section.
Macvtap can create skbs with llheader in frags in edge cases:
when (IFF_VNET_HDR is off or vnet_hdr.hdr_len < ETH_HLEN) and
prepad + len > PAGE_SIZE and vnet_hdr.flags has no or bad csum.

Add checks to ensure linear is always at least ETH_HLEN.
At this point, len is already ensured to be >= ETH_HLEN.

For backwards compatiblity, rounds up short vnet_hdr.hdr_len.
This differs from tap and packet, which return an error.

Fixes b9fb9ee07e67 ("macvtap: add GSO/csum offload support")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macvtap.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 0fc5219..159a687 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -760,6 +760,8 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 			macvtap16_to_cpu(q, vnet_hdr.hdr_len) : GOODCOPY_LEN;
 		if (copylen > good_linear)
 			copylen = good_linear;
+		else if (copylen < ETH_HLEN)
+			copylen = ETH_HLEN;
 		linear = copylen;
 		i = *from;
 		iov_iter_advance(&i, copylen);
@@ -769,10 +771,11 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 
 	if (!zerocopy) {
 		copylen = len;
-		if (macvtap16_to_cpu(q, vnet_hdr.hdr_len) > good_linear)
+		linear = macvtap16_to_cpu(q, vnet_hdr.hdr_len);
+		if (linear > good_linear)
 			linear = good_linear;
-		else
-			linear = macvtap16_to_cpu(q, vnet_hdr.hdr_len);
+		else if (linear < ETH_HLEN)
+			linear = ETH_HLEN;
 	}
 
 	skb = macvtap_alloc_skb(&q->sk, MACVTAP_RESERVE, copylen,
-- 
2.1.0


From ebd3e7aad0605a7864da202b01bc40ae51adf793 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Tue, 8 Mar 2016 12:59:33 -0800
Subject: [PATCH 29/56] mlxsw: spectrum: Check requested ageing time is valid

[ Upstream commit 869f63a4d28144c03c8f4a4c0d1e8f31f8c11a10 ]

Commit c62987bbd8a1 ("bridge: push bridge setting ageing_time down to
switchdev") added a check for minimum and maximum ageing time, but this
breaks existing behaviour where one can set ageing time to 0 for a
non-learning bridge.

Push this check down to the driver and allow the check in the bridge
layer to be removed. Currently ageing time 0 is refused by the driver,
but we can later add support for this functionality.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h           | 2 ++
 drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c | 9 +++++++--
 2 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 4365c8b..605f641 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -61,6 +61,8 @@ struct mlxsw_sp {
 #define MLXSW_SP_DEFAULT_LEARNING_INTERVAL 100
 		unsigned int interval; /* ms */
 	} fdb_notify;
+#define MLXSW_SP_MIN_AGEING_TIME 10
+#define MLXSW_SP_MAX_AGEING_TIME 1000000
 #define MLXSW_SP_DEFAULT_AGEING_TIME 300
 	u32 ageing_time;
 	struct {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 7dbeafa..d4c4c2b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -232,8 +232,13 @@ static int mlxsw_sp_port_attr_br_ageing_set(struct mlxsw_sp_port *mlxsw_sp_port,
 	unsigned long ageing_jiffies = clock_t_to_jiffies(ageing_clock_t);
 	u32 ageing_time = jiffies_to_msecs(ageing_jiffies) / 1000;
 
-	if (switchdev_trans_ph_prepare(trans))
-		return 0;
+	if (switchdev_trans_ph_prepare(trans)) {
+		if (ageing_time < MLXSW_SP_MIN_AGEING_TIME ||
+		    ageing_time > MLXSW_SP_MAX_AGEING_TIME)
+			return -ERANGE;
+		else
+			return 0;
+	}
 
 	return mlxsw_sp_ageing_set(mlxsw_sp, ageing_time);
 }
-- 
2.1.0


From 5a4c66e220c95c4f87ab9604aab43bee524ed1d5 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Tue, 8 Mar 2016 12:59:34 -0800
Subject: [PATCH 30/56] rocker: set FDB cleanup timer according to lowest
 ageing time

[ Upstream commit 88de1cd457e5cb664d6d437e2ea4750d089165f5 ]

In rocker, ageing time is a per-port attribute, so the next time the FDB
cleanup timer fires should be set according to the lowest ageing time.

This will later allow us to delete the BR_MIN_AGEING_TIME macro, which was
added to guarantee minimum ageing time in the bridge layer, thereby breaking
existing behavior.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/rocker/rocker.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c
index 52ec3d6..2b34622 100644
--- a/drivers/net/ethernet/rocker/rocker.c
+++ b/drivers/net/ethernet/rocker/rocker.c
@@ -239,6 +239,7 @@ struct rocker {
 	struct {
 		u64 id;
 	} hw;
+	unsigned long ageing_time;
 	spinlock_t cmd_ring_lock;		/* for cmd ring accesses */
 	struct rocker_dma_ring_info cmd_ring;
 	struct rocker_dma_ring_info event_ring;
@@ -3704,7 +3705,7 @@ static void rocker_fdb_cleanup(unsigned long data)
 	struct rocker_port *rocker_port;
 	struct rocker_fdb_tbl_entry *entry;
 	struct hlist_node *tmp;
-	unsigned long next_timer = jiffies + BR_MIN_AGEING_TIME;
+	unsigned long next_timer = jiffies + rocker->ageing_time;
 	unsigned long expires;
 	unsigned long lock_flags;
 	int flags = ROCKER_OP_FLAG_NOWAIT | ROCKER_OP_FLAG_REMOVE |
@@ -4367,8 +4368,12 @@ static int rocker_port_bridge_ageing_time(struct rocker_port *rocker_port,
 					  struct switchdev_trans *trans,
 					  u32 ageing_time)
 {
+	struct rocker *rocker = rocker_port->rocker;
+
 	if (!switchdev_trans_ph_prepare(trans)) {
 		rocker_port->ageing_time = clock_t_to_jiffies(ageing_time);
+		if (rocker_port->ageing_time < rocker->ageing_time)
+			rocker->ageing_time = rocker_port->ageing_time;
 		mod_timer(&rocker_port->rocker->fdb_cleanup_timer, jiffies);
 	}
 
@@ -5206,10 +5211,13 @@ static int rocker_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto err_init_tbls;
 	}
 
+	rocker->ageing_time = BR_DEFAULT_AGEING_TIME;
 	setup_timer(&rocker->fdb_cleanup_timer, rocker_fdb_cleanup,
 		    (unsigned long) rocker);
 	mod_timer(&rocker->fdb_cleanup_timer, jiffies);
 
+	rocker->ageing_time = BR_DEFAULT_AGEING_TIME;
+
 	err = rocker_probe_ports(rocker);
 	if (err) {
 		dev_err(&pdev->dev, "failed to probe ports\n");
-- 
2.1.0


From c41734d5ca344948f492c5e669729b704667e7ae Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <shemming@brocade.com>
Date: Tue, 8 Mar 2016 12:59:35 -0800
Subject: [PATCH 31/56] bridge: allow zero ageing time

[ Upstream commit 4c656c13b254d598e83e586b7b4d36a2043dad85 ]

This fixes a regression in the bridge ageing time caused by:
commit c62987bbd8a1 ("bridge: push bridge setting ageing_time down to switchdev")

There are users of Linux bridge which use the feature that if ageing time
is set to 0 it causes entries to never expire. See:
  https://www.linuxfoundation.org/collaborate/workgroups/networking/bridge

For a pure software bridge, it is unnecessary for the code to have
arbitrary restrictions on what values are allowable.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_bridge.h |  4 ----
 net/bridge/br_stp.c       | 11 ++++++++---
 2 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
index a338a688..dcb89e3 100644
--- a/include/linux/if_bridge.h
+++ b/include/linux/if_bridge.h
@@ -46,10 +46,6 @@ struct br_ip_list {
 #define BR_LEARNING_SYNC	BIT(9)
 #define BR_PROXYARP_WIFI	BIT(10)
 
-/* values as per ieee8021QBridgeFdbAgingTime */
-#define BR_MIN_AGEING_TIME	(10 * HZ)
-#define BR_MAX_AGEING_TIME	(1000000 * HZ)
-
 #define BR_DEFAULT_AGEING_TIME	(300 * HZ)
 
 extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __user *));
diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c
index 5f3f645..0e658f4 100644
--- a/net/bridge/br_stp.c
+++ b/net/bridge/br_stp.c
@@ -567,6 +567,14 @@ int br_set_max_age(struct net_bridge *br, unsigned long val)
 
 }
 
+/* Set time interval that dynamic forwarding entries live
+ * For pure software bridge, allow values outside the 802.1
+ * standard specification for special cases:
+ *  0 - entry never ages (all permanant)
+ *  1 - entry disappears (no persistance)
+ *
+ * Offloaded switch entries maybe more restrictive
+ */
 int br_set_ageing_time(struct net_bridge *br, u32 ageing_time)
 {
 	struct switchdev_attr attr = {
@@ -577,9 +585,6 @@ int br_set_ageing_time(struct net_bridge *br, u32 ageing_time)
 	unsigned long t = clock_t_to_jiffies(ageing_time);
 	int err;
 
-	if (t < BR_MIN_AGEING_TIME || t > BR_MAX_AGEING_TIME)
-		return -ERANGE;
-
 	err = switchdev_port_attr_set(br->dev, &attr);
 	if (err)
 		return err;
-- 
2.1.0


From 61f0af28181ea639fb9385e65242abbb61f19a02 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sun, 13 Mar 2016 23:28:00 -0400
Subject: [PATCH 32/56] ipv4: Don't do expensive useless work during inetdev
 destroy.

[ Upstream commit fbd40ea0180a2d328c5adc61414dc8bab9335ce2 ]

When an inetdev is destroyed, every address assigned to the interface
is removed.  And in this scenerio we do two pointless things which can
be very expensive if the number of assigned interfaces is large:

1) Address promotion.  We are deleting all addresses, so there is no
   point in doing this.

2) A full nf conntrack table purge for every address.  We only need to
   do this once, as is already caught by the existing
   masq_dev_notifier so masq_inet_event() can skip this.

Reported-by: Solar Designer <solar@openwall.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Tested-by: Cyrill Gorcunov <gorcunov@openvz.org>
---
 net/ipv4/devinet.c                          |  4 ++++
 net/ipv4/fib_frontend.c                     |  4 ++++
 net/ipv4/netfilter/nf_nat_masquerade_ipv4.c | 12 ++++++++++--
 3 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index f6303b1..0212591 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -334,6 +334,9 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
 
 	ASSERT_RTNL();
 
+	if (in_dev->dead)
+		goto no_promotions;
+
 	/* 1. Deleting primary ifaddr forces deletion all secondaries
 	 * unless alias promotion is set
 	 **/
@@ -380,6 +383,7 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
 			fib_del_ifaddr(ifa, ifa1);
 	}
 
+no_promotions:
 	/* 2. Unlink it */
 
 	*ifap = ifa1->ifa_next;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 4734475..21add55 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -922,6 +922,9 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim)
 		subnet = 1;
 	}
 
+	if (in_dev->dead)
+		goto no_promotions;
+
 	/* Deletion is more complicated than add.
 	 * We should take care of not to delete too much :-)
 	 *
@@ -997,6 +1000,7 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim)
 		}
 	}
 
+no_promotions:
 	if (!(ok & BRD_OK))
 		fib_magic(RTM_DELROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim);
 	if (subnet && ifa->ifa_prefixlen < 31) {
diff --git a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
index c6eb421..ea91058 100644
--- a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
@@ -108,10 +108,18 @@ static int masq_inet_event(struct notifier_block *this,
 			   unsigned long event,
 			   void *ptr)
 {
-	struct net_device *dev = ((struct in_ifaddr *)ptr)->ifa_dev->dev;
+	struct in_device *idev = ((struct in_ifaddr *)ptr)->ifa_dev;
 	struct netdev_notifier_info info;
 
-	netdev_notifier_info_init(&info, dev);
+	/* The masq_dev_notifier will catch the case of the device going
+	 * down.  So if the inetdev is dead and being destroyed we have
+	 * no work to do.  Otherwise this is an individual address removal
+	 * and we have to perform the flush.
+	 */
+	if (idev->dead)
+		return NOTIFY_DONE;
+
+	netdev_notifier_info_init(&info, idev->dev);
 	return masq_device_event(this, event, &info);
 }
 
-- 
2.1.0


From be6d4498b0363c62e839cfde081e4fdc6e035602 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 14 Mar 2016 09:56:35 -0300
Subject: [PATCH 33/56] net: Fix use after free in the recvmmsg exit path

[ Upstream commit 34b88a68f26a75e4fded796f1a49c40f82234b7d ]

The syzkaller fuzzer hit the following use-after-free:

  Call Trace:
   [<ffffffff8175ea0e>] __asan_report_load8_noabort+0x3e/0x40 mm/kasan/report.c:295
   [<ffffffff851cc31a>] __sys_recvmmsg+0x6fa/0x7f0 net/socket.c:2261
   [<     inline     >] SYSC_recvmmsg net/socket.c:2281
   [<ffffffff851cc57f>] SyS_recvmmsg+0x16f/0x180 net/socket.c:2270
   [<ffffffff86332bb6>] entry_SYSCALL_64_fastpath+0x16/0x7a
  arch/x86/entry/entry_64.S:185

And, as Dmitry rightly assessed, that is because we can drop the
reference and then touch it when the underlying recvmsg calls return
some packets and then hit an error, which will make recvmmsg to set
sock->sk->sk_err, oops, fix it.

Reported-and-Tested-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Kostya Serebryany <kcc@google.com>
Cc: Sasha Levin <sasha.levin@oracle.com>
Fixes: a2e2725541fa ("net: Introduce recvmmsg socket syscall")
http://lkml.kernel.org/r/20160122211644.GC2470@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/socket.c | 38 +++++++++++++++++++-------------------
 1 file changed, 19 insertions(+), 19 deletions(-)

diff --git a/net/socket.c b/net/socket.c
index d730ef9..263b334 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2238,31 +2238,31 @@ int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
 			break;
 	}
 
-out_put:
-	fput_light(sock->file, fput_needed);
-
 	if (err == 0)
-		return datagrams;
+		goto out_put;
 
-	if (datagrams != 0) {
+	if (datagrams == 0) {
+		datagrams = err;
+		goto out_put;
+	}
+
+	/*
+	 * We may return less entries than requested (vlen) if the
+	 * sock is non block and there aren't enough datagrams...
+	 */
+	if (err != -EAGAIN) {
 		/*
-		 * We may return less entries than requested (vlen) if the
-		 * sock is non block and there aren't enough datagrams...
+		 * ... or  if recvmsg returns an error after we
+		 * received some datagrams, where we record the
+		 * error to return on the next call or if the
+		 * app asks about it using getsockopt(SO_ERROR).
 		 */
-		if (err != -EAGAIN) {
-			/*
-			 * ... or  if recvmsg returns an error after we
-			 * received some datagrams, where we record the
-			 * error to return on the next call or if the
-			 * app asks about it using getsockopt(SO_ERROR).
-			 */
-			sock->sk->sk_err = -err;
-		}
-
-		return datagrams;
+		sock->sk->sk_err = -err;
 	}
+out_put:
+	fput_light(sock->file, fput_needed);
 
-	return err;
+	return datagrams;
 }
 
 SYSCALL_DEFINE5(recvmmsg, int, fd, struct mmsghdr __user *, mmsg,
-- 
2.1.0


From ff849beb9ccb7e26f87402ab5e3036dd38a9e14a Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 14 Mar 2016 15:18:34 +0100
Subject: [PATCH 34/56] mlx4: add missing braces in verify_qp_parameters

[ Upstream commit baefd7015cdb304ce6c94f9679d0486c71954766 ]

The implementation of QP paravirtualization back in linux-3.7 included
some code that looks very dubious, and gcc-6 has grown smart enough
to warn about it:

drivers/net/ethernet/mellanox/mlx4/resource_tracker.c: In function 'verify_qp_parameters':
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c:3154:5: error: statement is indented as if it were guarded by... [-Werror=misleading-indentation]
     if (optpar & MLX4_QP_OPTPAR_ALT_ADDR_PATH) {
     ^~
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c:3144:4: note: ...this 'if' clause, but it is not
    if (slave != mlx4_master_func_num(dev))

>From looking at the context, I'm reasonably sure that the indentation
is correct but that it should have contained curly braces from the
start, as the update_gid() function in the same patch correctly does.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Fixes: 54679e148287 ("mlx4: Implement QP paravirtualization and maintain phys_pkey_cache for smp_snoop")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/resource_tracker.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index cad6c44..d314d96 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -3132,7 +3132,7 @@ static int verify_qp_parameters(struct mlx4_dev *dev,
 		case QP_TRANS_RTS2RTS:
 		case QP_TRANS_SQD2SQD:
 		case QP_TRANS_SQD2RTS:
-			if (slave != mlx4_master_func_num(dev))
+			if (slave != mlx4_master_func_num(dev)) {
 				if (optpar & MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH) {
 					port = (qp_ctx->pri_path.sched_queue >> 6 & 1) + 1;
 					if (dev->caps.port_mask[port] != MLX4_PORT_TYPE_IB)
@@ -3151,6 +3151,7 @@ static int verify_qp_parameters(struct mlx4_dev *dev,
 					if (qp_ctx->alt_path.mgid_index >= num_gids)
 						return -EINVAL;
 				}
+			}
 			break;
 		default:
 			break;
-- 
2.1.0


From 43258d8391f21ab6ce800ddd2d8c64047bb6a892 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 14 Mar 2016 15:18:35 +0100
Subject: [PATCH 35/56] farsync: fix off-by-one bug in fst_add_one

[ Upstream commit e725a66c0202b5f36c2f9d59d26a65c53bbf21f7 ]

gcc-6 finds an out of bounds access in the fst_add_one function
when calculating the end of the mmio area:

drivers/net/wan/farsync.c: In function 'fst_add_one':
drivers/net/wan/farsync.c:418:53: error: index 2 denotes an offset greater than size of 'u8[2][8192] {aka unsigned char[2][8192]}' [-Werror=array-bounds]
 #define BUF_OFFSET(X)   (BFM_BASE + offsetof(struct buf_window, X))
                                                     ^
include/linux/compiler-gcc.h:158:21: note: in definition of macro '__compiler_offsetof'
  __builtin_offsetof(a, b)
                     ^
drivers/net/wan/farsync.c:418:37: note: in expansion of macro 'offsetof'
 #define BUF_OFFSET(X)   (BFM_BASE + offsetof(struct buf_window, X))
                                     ^~~~~~~~
drivers/net/wan/farsync.c:2519:36: note: in expansion of macro 'BUF_OFFSET'
                                  + BUF_OFFSET ( txBuffer[i][NUM_TX_BUFFER][0]);
                                    ^~~~~~~~~~

The warning is correct, but not critical because this appears
to be a write-only variable that is set by each WAN driver but
never accessed afterwards.

I'm taking the minimal fix here, using the correct pointer by
pointing 'mem_end' to the last byte inside of the register area
as all other WAN drivers do, rather than the first byte outside of
it. An alternative would be to just remove the mem_end member
entirely.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wan/farsync.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wan/farsync.c b/drivers/net/wan/farsync.c
index 44541dbc..69b994f 100644
--- a/drivers/net/wan/farsync.c
+++ b/drivers/net/wan/farsync.c
@@ -2516,7 +2516,7 @@ fst_add_one(struct pci_dev *pdev, const struct pci_device_id *ent)
                 dev->mem_start   = card->phys_mem
                                  + BUF_OFFSET ( txBuffer[i][0][0]);
                 dev->mem_end     = card->phys_mem
-                                 + BUF_OFFSET ( txBuffer[i][NUM_TX_BUFFER][0]);
+                                 + BUF_OFFSET ( txBuffer[i][NUM_TX_BUFFER - 1][LEN_RX_BUFFER - 1]);
                 dev->base_addr   = card->pci_conf;
                 dev->irq         = card->irq;
 
-- 
2.1.0


From 2f1b669b9e57ca47b3feb971224c617ca208c53e Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 14 Mar 2016 15:18:36 +0100
Subject: [PATCH 36/56] ath9k: fix buffer overrun for ar9287

[ Upstream commit 83d6f1f15f8cce844b0a131cbc63e444620e48b5 ]

Code that was added back in 2.6.38 has an obvious overflow
when accessing a static array, and at the time it was added
only a code comment was put in front of it as a reminder
to have it reviewed properly.

This has not happened, but gcc-6 now points to the specific
overflow:

drivers/net/wireless/ath/ath9k/eeprom.c: In function 'ath9k_hw_get_gain_boundaries_pdadcs':
drivers/net/wireless/ath/ath9k/eeprom.c:483:44: error: array subscript is above array bounds [-Werror=array-bounds]
     maxPwrT4[i] = data_9287[idxL].pwrPdg[i][4];
                   ~~~~~~~~~~~~~~~~~~~~~~~~~^~~

It turns out that the correct array length exists in the local
'intercepts' variable of this function, so we can just use that
instead of hardcoding '4', so this patch changes all three
instances to use that variable. The other two instances were
already correct, but it's more consistent this way.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Fixes: 940cd2c12ebf ("ath9k_hw: merge the ar9287 version of ath9k_hw_get_gain_boundaries_pdadcs")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wireless/ath/ath9k/eeprom.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/eeprom.c b/drivers/net/wireless/ath/ath9k/eeprom.c
index cc81482..113a43f 100644
--- a/drivers/net/wireless/ath/ath9k/eeprom.c
+++ b/drivers/net/wireless/ath/ath9k/eeprom.c
@@ -403,10 +403,9 @@ void ath9k_hw_get_gain_boundaries_pdadcs(struct ath_hw *ah,
 
 	if (match) {
 		if (AR_SREV_9287(ah)) {
-			/* FIXME: array overrun? */
 			for (i = 0; i < numXpdGains; i++) {
 				minPwrT4[i] = data_9287[idxL].pwrPdg[i][0];
-				maxPwrT4[i] = data_9287[idxL].pwrPdg[i][4];
+				maxPwrT4[i] = data_9287[idxL].pwrPdg[i][intercepts - 1];
 				ath9k_hw_fill_vpd_table(minPwrT4[i], maxPwrT4[i],
 						data_9287[idxL].pwrPdg[i],
 						data_9287[idxL].vpdPdg[i],
@@ -416,7 +415,7 @@ void ath9k_hw_get_gain_boundaries_pdadcs(struct ath_hw *ah,
 		} else if (eeprom_4k) {
 			for (i = 0; i < numXpdGains; i++) {
 				minPwrT4[i] = data_4k[idxL].pwrPdg[i][0];
-				maxPwrT4[i] = data_4k[idxL].pwrPdg[i][4];
+				maxPwrT4[i] = data_4k[idxL].pwrPdg[i][intercepts - 1];
 				ath9k_hw_fill_vpd_table(minPwrT4[i], maxPwrT4[i],
 						data_4k[idxL].pwrPdg[i],
 						data_4k[idxL].vpdPdg[i],
@@ -426,7 +425,7 @@ void ath9k_hw_get_gain_boundaries_pdadcs(struct ath_hw *ah,
 		} else {
 			for (i = 0; i < numXpdGains; i++) {
 				minPwrT4[i] = data_def[idxL].pwrPdg[i][0];
-				maxPwrT4[i] = data_def[idxL].pwrPdg[i][4];
+				maxPwrT4[i] = data_def[idxL].pwrPdg[i][intercepts - 1];
 				ath9k_hw_fill_vpd_table(minPwrT4[i], maxPwrT4[i],
 						data_def[idxL].pwrPdg[i],
 						data_def[idxL].vpdPdg[i],
-- 
2.1.0


From dbeb94738951b5bf1454ee809be80b77d77feb18 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Mon, 14 Mar 2016 21:17:16 +0100
Subject: [PATCH 37/56] ppp: ensure file->private_data can't be overridden

[ Upstream commit e8e56ffd9d2973398b60ece1f1bebb8d67b4d032 ]

Locking ppp_mutex must be done before dereferencing file->private_data,
otherwise it could be modified before ppp_unattached_ioctl() takes the
lock. This could lead ppp_unattached_ioctl() to override ->private_data,
thus leaking reference to the ppp_file previously pointed to.

v2: lock all ppp_ioctl() instead of just checking private_data in
    ppp_unattached_ioctl(), to avoid ambiguous behaviour.

Fixes: f3ff8a4d80e8 ("ppp: push BKL down into the driver")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/ppp_generic.c | 31 +++++++++++++++++--------------
 1 file changed, 17 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 40b303e..35e8b5a 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -567,7 +567,7 @@ static int get_filter(void __user *arg, struct sock_filter **p)
 
 static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
-	struct ppp_file *pf = file->private_data;
+	struct ppp_file *pf;
 	struct ppp *ppp;
 	int err = -EFAULT, val, val2, i;
 	struct ppp_idle idle;
@@ -577,9 +577,14 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	void __user *argp = (void __user *)arg;
 	int __user *p = argp;
 
-	if (!pf)
-		return ppp_unattached_ioctl(current->nsproxy->net_ns,
-					pf, file, cmd, arg);
+	mutex_lock(&ppp_mutex);
+
+	pf = file->private_data;
+	if (!pf) {
+		err = ppp_unattached_ioctl(current->nsproxy->net_ns,
+					   pf, file, cmd, arg);
+		goto out;
+	}
 
 	if (cmd == PPPIOCDETACH) {
 		/*
@@ -594,7 +599,6 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		 * this fd and reopening /dev/ppp.
 		 */
 		err = -EINVAL;
-		mutex_lock(&ppp_mutex);
 		if (pf->kind == INTERFACE) {
 			ppp = PF_TO_PPP(pf);
 			rtnl_lock();
@@ -608,15 +612,13 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		} else
 			pr_warn("PPPIOCDETACH file->f_count=%ld\n",
 				atomic_long_read(&file->f_count));
-		mutex_unlock(&ppp_mutex);
-		return err;
+		goto out;
 	}
 
 	if (pf->kind == CHANNEL) {
 		struct channel *pch;
 		struct ppp_channel *chan;
 
-		mutex_lock(&ppp_mutex);
 		pch = PF_TO_CHANNEL(pf);
 
 		switch (cmd) {
@@ -638,17 +640,16 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 				err = chan->ops->ioctl(chan, cmd, arg);
 			up_read(&pch->chan_sem);
 		}
-		mutex_unlock(&ppp_mutex);
-		return err;
+		goto out;
 	}
 
 	if (pf->kind != INTERFACE) {
 		/* can't happen */
 		pr_err("PPP: not interface or channel??\n");
-		return -EINVAL;
+		err = -EINVAL;
+		goto out;
 	}
 
-	mutex_lock(&ppp_mutex);
 	ppp = PF_TO_PPP(pf);
 	switch (cmd) {
 	case PPPIOCSMRU:
@@ -823,7 +824,10 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	default:
 		err = -ENOTTY;
 	}
+
+out:
 	mutex_unlock(&ppp_mutex);
+
 	return err;
 }
 
@@ -836,7 +840,6 @@ static int ppp_unattached_ioctl(struct net *net, struct ppp_file *pf,
 	struct ppp_net *pn;
 	int __user *p = (int __user *)arg;
 
-	mutex_lock(&ppp_mutex);
 	switch (cmd) {
 	case PPPIOCNEWUNIT:
 		/* Create a new ppp unit */
@@ -886,7 +889,7 @@ static int ppp_unattached_ioctl(struct net *net, struct ppp_file *pf,
 	default:
 		err = -ENOTTY;
 	}
-	mutex_unlock(&ppp_mutex);
+
 	return err;
 }
 
-- 
2.1.0


From 154ea89b1a862f06087d4e896ae192060a2324ac Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 16 Mar 2016 22:52:15 -0700
Subject: [PATCH 38/56] tcp/dccp: remove obsolete WARN_ON() in icmp handlers

[ Upstream commit e316ea62e3203d524ff0239a40c56d3a39ad1b5c ]

Now SYN_RECV request sockets are installed in ehash table, an ICMP
handler can find a request socket while another cpu handles an incoming
packet transforming this SYN_RECV request socket into an ESTABLISHED
socket.

We need to remove the now obsolete WARN_ON(req->sk), since req->sk
is set when a new child is created and added into listener accept queue.

If this race happens, the ICMP will do nothing special.

Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Ben Lazarus <blazarus@google.com>
Reported-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ipv4.c     | 2 --
 net/ipv4/tcp_ipv4.c | 2 --
 2 files changed, 4 deletions(-)

diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 902d606..8be8f27 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -204,8 +204,6 @@ void dccp_req_err(struct sock *sk, u64 seq)
 	 * ICMPs are not backlogged, hence we cannot get an established
 	 * socket here.
 	 */
-	WARN_ON(req->sk);
-
 	if (!between48(seq, dccp_rsk(req)->dreq_iss, dccp_rsk(req)->dreq_gss)) {
 		NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
 	} else {
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 8c7e631..048418b 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -320,8 +320,6 @@ void tcp_req_err(struct sock *sk, u32 seq, bool abort)
 	/* ICMPs are not backlogged, hence we cannot get
 	 * an established socket here.
 	 */
-	WARN_ON(req->sk);
-
 	if (seq != tcp_rsk(req)->snt_isn) {
 		NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
 	} else if (abort) {
-- 
2.1.0


From 0697ea5567a4f327befa3cbb219c01fa6aea0247 Mon Sep 17 00:00:00 2001
From: Manish Chopra <manish.chopra@qlogic.com>
Date: Tue, 15 Mar 2016 07:13:45 -0400
Subject: [PATCH 39/56] qlge: Fix receive packets drop.

[ Upstream commit 2c9a266afefe137bff06bbe0fc48b4d3b3cb348c ]

When running small packets [length < 256 bytes] traffic, packets were
being dropped due to invalid data in those packets which were
delivered by the driver upto the stack. Using pci_dma_sync_single_for_cpu
ensures copying latest and updated data into skb from the receive buffer.

Signed-off-by: Sony Chacko <sony.chacko@qlogic.com>
Signed-off-by: Manish Chopra <manish.chopra@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qlge/qlge_main.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
index 9979764..b28e73e 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
@@ -1648,7 +1648,18 @@ static void ql_process_mac_rx_skb(struct ql_adapter *qdev,
 		return;
 	}
 	skb_reserve(new_skb, NET_IP_ALIGN);
+
+	pci_dma_sync_single_for_cpu(qdev->pdev,
+				    dma_unmap_addr(sbq_desc, mapaddr),
+				    dma_unmap_len(sbq_desc, maplen),
+				    PCI_DMA_FROMDEVICE);
+
 	memcpy(skb_put(new_skb, length), skb->data, length);
+
+	pci_dma_sync_single_for_device(qdev->pdev,
+				       dma_unmap_addr(sbq_desc, mapaddr),
+				       dma_unmap_len(sbq_desc, maplen),
+				       PCI_DMA_FROMDEVICE);
 	skb = new_skb;
 
 	/* Frame error, so drop the packet. */
-- 
2.1.0


From eb4d3c42c207cdbe880e93674ff2dd3a8d9945f2 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 17 Mar 2016 11:57:06 -0700
Subject: [PATCH 40/56] net: bcmgenet: fix dma api length mismatch

[ Upstream commit eee577232203842b4dcadb7ab477a298479633ed ]

When un-mapping skb->data in __bcmgenet_tx_reclaim(),
we must use the length that was used in original dma_map_single(),
instead of skb->len that might be bigger (includes the frags)

We simply can store skb_len into tx_cb_ptr->dma_len and use it
at unmap time.

Fixes: 1c1008c793fa ("net: bcmgenet: add main driver file")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 17f017a..0fb3f8d 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -1197,7 +1197,7 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
 			dev->stats.tx_bytes += tx_cb_ptr->skb->len;
 			dma_unmap_single(&dev->dev,
 					 dma_unmap_addr(tx_cb_ptr, dma_addr),
-					 tx_cb_ptr->skb->len,
+					 dma_unmap_len(tx_cb_ptr, dma_len),
 					 DMA_TO_DEVICE);
 			bcmgenet_free_cb(tx_cb_ptr);
 		} else if (dma_unmap_addr(tx_cb_ptr, dma_addr)) {
@@ -1308,7 +1308,7 @@ static int bcmgenet_xmit_single(struct net_device *dev,
 	}
 
 	dma_unmap_addr_set(tx_cb_ptr, dma_addr, mapping);
-	dma_unmap_len_set(tx_cb_ptr, dma_len, skb->len);
+	dma_unmap_len_set(tx_cb_ptr, dma_len, skb_len);
 	length_status = (skb_len << DMA_BUFLENGTH_SHIFT) | dma_desc_flags |
 			(priv->hw_params->qtag_mask << DMA_TX_QTAG_SHIFT) |
 			DMA_TX_APPEND_CRC;
-- 
2.1.0


From 06b405b6abf8bd9af21b60ff597110017b8ce552 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 17 Mar 2016 17:23:36 -0700
Subject: [PATCH 41/56] bonding: fix bond_get_stats()

[ Upstream commit fe30937b65354c7fec244caebbdaae68e28ca797 ]

bond_get_stats() can be called from rtnetlink (with RTNL held)
or from /proc/net/dev seq handler (with RCU held)

The logic added in commit 5f0c5f73e5ef ("bonding: make global bonding
stats more reliable") kind of assumed only one cpu could run there.

If multiple threads are reading /proc/net/dev, stats can be really
messed up after a while.

A second problem is that some fields are 32bit, so we need to properly
handle the wrap around problem.

Given that RTNL is not always held, we need to use
bond_for_each_slave_rcu().

Fixes: 5f0c5f73e5ef ("bonding: make global bonding stats more reliable")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Andy Gospodarek <gospo@cumulusnetworks.com>
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Cc: Veaceslav Falico <vfalico@gmail.com>
Reviewed-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 65 ++++++++++++++++++++++-------------------
 include/net/bonding.h           |  1 +
 2 files changed, 36 insertions(+), 30 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 28bbca0..b3d70a7 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3260,6 +3260,30 @@ static int bond_close(struct net_device *bond_dev)
 	return 0;
 }
 
+/* fold stats, assuming all rtnl_link_stats64 fields are u64, but
+ * that some drivers can provide 32bit values only.
+ */
+static void bond_fold_stats(struct rtnl_link_stats64 *_res,
+			    const struct rtnl_link_stats64 *_new,
+			    const struct rtnl_link_stats64 *_old)
+{
+	const u64 *new = (const u64 *)_new;
+	const u64 *old = (const u64 *)_old;
+	u64 *res = (u64 *)_res;
+	int i;
+
+	for (i = 0; i < sizeof(*_res) / sizeof(u64); i++) {
+		u64 nv = new[i];
+		u64 ov = old[i];
+
+		/* detects if this particular field is 32bit only */
+		if (((nv | ov) >> 32) == 0)
+			res[i] += (u32)nv - (u32)ov;
+		else
+			res[i] += nv - ov;
+	}
+}
+
 static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev,
 						struct rtnl_link_stats64 *stats)
 {
@@ -3268,43 +3292,23 @@ static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev,
 	struct list_head *iter;
 	struct slave *slave;
 
+	spin_lock(&bond->stats_lock);
 	memcpy(stats, &bond->bond_stats, sizeof(*stats));
 
-	bond_for_each_slave(bond, slave, iter) {
-		const struct rtnl_link_stats64 *sstats =
+	rcu_read_lock();
+	bond_for_each_slave_rcu(bond, slave, iter) {
+		const struct rtnl_link_stats64 *new =
 			dev_get_stats(slave->dev, &temp);
-		struct rtnl_link_stats64 *pstats = &slave->slave_stats;
-
-		stats->rx_packets +=  sstats->rx_packets - pstats->rx_packets;
-		stats->rx_bytes += sstats->rx_bytes - pstats->rx_bytes;
-		stats->rx_errors += sstats->rx_errors - pstats->rx_errors;
-		stats->rx_dropped += sstats->rx_dropped - pstats->rx_dropped;
-
-		stats->tx_packets += sstats->tx_packets - pstats->tx_packets;;
-		stats->tx_bytes += sstats->tx_bytes - pstats->tx_bytes;
-		stats->tx_errors += sstats->tx_errors - pstats->tx_errors;
-		stats->tx_dropped += sstats->tx_dropped - pstats->tx_dropped;
-
-		stats->multicast += sstats->multicast - pstats->multicast;
-		stats->collisions += sstats->collisions - pstats->collisions;
-
-		stats->rx_length_errors += sstats->rx_length_errors - pstats->rx_length_errors;
-		stats->rx_over_errors += sstats->rx_over_errors - pstats->rx_over_errors;
-		stats->rx_crc_errors += sstats->rx_crc_errors - pstats->rx_crc_errors;
-		stats->rx_frame_errors += sstats->rx_frame_errors - pstats->rx_frame_errors;
-		stats->rx_fifo_errors += sstats->rx_fifo_errors - pstats->rx_fifo_errors;
-		stats->rx_missed_errors += sstats->rx_missed_errors - pstats->rx_missed_errors;
-
-		stats->tx_aborted_errors += sstats->tx_aborted_errors - pstats->tx_aborted_errors;
-		stats->tx_carrier_errors += sstats->tx_carrier_errors - pstats->tx_carrier_errors;
-		stats->tx_fifo_errors += sstats->tx_fifo_errors - pstats->tx_fifo_errors;
-		stats->tx_heartbeat_errors += sstats->tx_heartbeat_errors - pstats->tx_heartbeat_errors;
-		stats->tx_window_errors += sstats->tx_window_errors - pstats->tx_window_errors;
+
+		bond_fold_stats(stats, new, &slave->slave_stats);
 
 		/* save off the slave stats for the next run */
-		memcpy(pstats, sstats, sizeof(*sstats));
+		memcpy(&slave->slave_stats, new, sizeof(*new));
 	}
+	rcu_read_unlock();
+
 	memcpy(&bond->bond_stats, stats, sizeof(*stats));
+	spin_unlock(&bond->stats_lock);
 
 	return stats;
 }
@@ -4118,6 +4122,7 @@ void bond_setup(struct net_device *bond_dev)
 	struct bonding *bond = netdev_priv(bond_dev);
 
 	spin_lock_init(&bond->mode_lock);
+	spin_lock_init(&bond->stats_lock);
 	bond->params = bonding_defaults;
 
 	/* Initialize pointers */
diff --git a/include/net/bonding.h b/include/net/bonding.h
index c1740a2..93abe5f 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -214,6 +214,7 @@ struct bonding {
 	 * ALB mode (6) - to sync the use and modifications of its hash table
 	 */
 	spinlock_t mode_lock;
+	spinlock_t stats_lock;
 	u8	 send_peer_notif;
 	u8       igmp_retrans;
 #ifdef CONFIG_PROC_FS
-- 
2.1.0


From c9de6cb3d493567ea85cabf606f8c037c317fcb8 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 22 Mar 2016 09:19:38 +0100
Subject: [PATCH 42/56] ipv4: fix broadcast packets reception

[ Upstream commit ad0ea1989cc4d5905941d0a9e62c63ad6d859cef ]

Currently, ingress ipv4 broadcast datagrams are dropped since,
in udp_v4_early_demux(), ip_check_mc_rcu() is invoked even on
bcast packets.

This patch addresses the issue, invoking ip_check_mc_rcu()
only for mcast packets.

Fixes: 6e5403093261 ("ipv4/udp: Verify multicast group is ours in upd_v4_early_demux()")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 7f8ab46..21fbb54 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1990,10 +1990,14 @@ void udp_v4_early_demux(struct sk_buff *skb)
 		if (!in_dev)
 			return;
 
-		ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr,
-				       iph->protocol);
-		if (!ours)
-			return;
+		/* we are supposed to accept bcast packets */
+		if (skb->pkt_type == PACKET_MULTICAST) {
+			ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr,
+					       iph->protocol);
+			if (!ours)
+				return;
+		}
+
 		sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr,
 						   uh->source, iph->saddr, dif);
 	} else if (skb->pkt_type == PACKET_HOST) {
-- 
2.1.0


From e3256b7b1b3135197d92a3d69734665f5c7d8dec Mon Sep 17 00:00:00 2001
From: Lance Richardson <lrichard@redhat.com>
Date: Tue, 22 Mar 2016 14:56:57 -0400
Subject: [PATCH 43/56] ipv4: initialize flowi4_flags before calling
 fib_lookup()

[ Upstream commit 4cfc86f3dae6ca38ed49cdd78f458a03d4d87992 ]

Field fl4.flowi4_flags is not initialized in fib_compute_spec_dst()
before calling fib_lookup(), which means fib_table_lookup() is
using non-deterministic data at this line:

	if (!(flp->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF)) {

Fix by initializing the entire fl4 structure, which will prevent
similar issues as fields are added in the future by ensuring that
all fields are initialized to zero unless explicitly initialized
to another value.

Fixes: 58189ca7b2741 ("net: Fix vti use case with oif in dst lookups")
Suggested-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: Lance Richardson <lrichard@redhat.com>
Acked-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_frontend.c | 16 +++++++---------
 1 file changed, 7 insertions(+), 9 deletions(-)

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 21add55..8a9246d 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -280,7 +280,6 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb)
 	struct in_device *in_dev;
 	struct fib_result res;
 	struct rtable *rt;
-	struct flowi4 fl4;
 	struct net *net;
 	int scope;
 
@@ -296,14 +295,13 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb)
 
 	scope = RT_SCOPE_UNIVERSE;
 	if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) {
-		fl4.flowi4_oif = 0;
-		fl4.flowi4_iif = LOOPBACK_IFINDEX;
-		fl4.daddr = ip_hdr(skb)->saddr;
-		fl4.saddr = 0;
-		fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);
-		fl4.flowi4_scope = scope;
-		fl4.flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0;
-		fl4.flowi4_tun_key.tun_id = 0;
+		struct flowi4 fl4 = {
+			.flowi4_iif = LOOPBACK_IFINDEX,
+			.daddr = ip_hdr(skb)->saddr,
+			.flowi4_tos = RT_TOS(ip_hdr(skb)->tos),
+			.flowi4_scope = scope,
+			.flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0,
+		};
 		if (!fib_lookup(net, &fl4, &res, 0))
 			return FIB_RES_PREFSRC(net, res);
 	} else {
-- 
2.1.0


From dbc67ea0189456f81e0a43494332347f697c0cb9 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Wed, 23 Mar 2016 16:38:55 +0100
Subject: [PATCH 44/56] ppp: take reference on channels netns

[ Upstream commit 1f461dcdd296eecedaffffc6bae2bfa90bd7eb89 ]

Let channels hold a reference on their network namespace.
Some channel types, like ppp_async and ppp_synctty, can have their
userspace controller running in a different namespace. Therefore they
can't rely on them to preclude their netns from being removed from
under them.

==================================================================
BUG: KASAN: use-after-free in ppp_unregister_channel+0x372/0x3a0 at
addr ffff880064e217e0
Read of size 8 by task syz-executor/11581
=============================================================================
BUG net_namespace (Not tainted): kasan: bad access detected
-----------------------------------------------------------------------------

Disabling lock debugging due to kernel taint
INFO: Allocated in copy_net_ns+0x6b/0x1a0 age=92569 cpu=3 pid=6906
[<      none      >] ___slab_alloc+0x4c7/0x500 kernel/mm/slub.c:2440
[<      none      >] __slab_alloc+0x4c/0x90 kernel/mm/slub.c:2469
[<     inline     >] slab_alloc_node kernel/mm/slub.c:2532
[<     inline     >] slab_alloc kernel/mm/slub.c:2574
[<      none      >] kmem_cache_alloc+0x23a/0x2b0 kernel/mm/slub.c:2579
[<     inline     >] kmem_cache_zalloc kernel/include/linux/slab.h:597
[<     inline     >] net_alloc kernel/net/core/net_namespace.c:325
[<      none      >] copy_net_ns+0x6b/0x1a0 kernel/net/core/net_namespace.c:360
[<      none      >] create_new_namespaces+0x2f6/0x610 kernel/kernel/nsproxy.c:95
[<      none      >] copy_namespaces+0x297/0x320 kernel/kernel/nsproxy.c:150
[<      none      >] copy_process.part.35+0x1bf4/0x5760 kernel/kernel/fork.c:1451
[<     inline     >] copy_process kernel/kernel/fork.c:1274
[<      none      >] _do_fork+0x1bc/0xcb0 kernel/kernel/fork.c:1723
[<     inline     >] SYSC_clone kernel/kernel/fork.c:1832
[<      none      >] SyS_clone+0x37/0x50 kernel/kernel/fork.c:1826
[<      none      >] entry_SYSCALL_64_fastpath+0x16/0x7a kernel/arch/x86/entry/entry_64.S:185

INFO: Freed in net_drop_ns+0x67/0x80 age=575 cpu=2 pid=2631
[<      none      >] __slab_free+0x1fc/0x320 kernel/mm/slub.c:2650
[<     inline     >] slab_free kernel/mm/slub.c:2805
[<      none      >] kmem_cache_free+0x2a0/0x330 kernel/mm/slub.c:2814
[<     inline     >] net_free kernel/net/core/net_namespace.c:341
[<      none      >] net_drop_ns+0x67/0x80 kernel/net/core/net_namespace.c:348
[<      none      >] cleanup_net+0x4e5/0x600 kernel/net/core/net_namespace.c:448
[<      none      >] process_one_work+0x794/0x1440 kernel/kernel/workqueue.c:2036
[<      none      >] worker_thread+0xdb/0xfc0 kernel/kernel/workqueue.c:2170
[<      none      >] kthread+0x23f/0x2d0 kernel/drivers/block/aoe/aoecmd.c:1303
[<      none      >] ret_from_fork+0x3f/0x70 kernel/arch/x86/entry/entry_64.S:468
INFO: Slab 0xffffea0001938800 objects=3 used=0 fp=0xffff880064e20000
flags=0x5fffc0000004080
INFO: Object 0xffff880064e20000 @offset=0 fp=0xffff880064e24200

CPU: 1 PID: 11581 Comm: syz-executor Tainted: G    B           4.4.0+
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS
rel-1.8.2-0-g33fbe13 by qemu-project.org 04/01/2014
 00000000ffffffff ffff8800662c7790 ffffffff8292049d ffff88003e36a300
 ffff880064e20000 ffff880064e20000 ffff8800662c77c0 ffffffff816f2054
 ffff88003e36a300 ffffea0001938800 ffff880064e20000 0000000000000000
Call Trace:
 [<     inline     >] __dump_stack kernel/lib/dump_stack.c:15
 [<ffffffff8292049d>] dump_stack+0x6f/0xa2 kernel/lib/dump_stack.c:50
 [<ffffffff816f2054>] print_trailer+0xf4/0x150 kernel/mm/slub.c:654
 [<ffffffff816f875f>] object_err+0x2f/0x40 kernel/mm/slub.c:661
 [<     inline     >] print_address_description kernel/mm/kasan/report.c:138
 [<ffffffff816fb0c5>] kasan_report_error+0x215/0x530 kernel/mm/kasan/report.c:236
 [<     inline     >] kasan_report kernel/mm/kasan/report.c:259
 [<ffffffff816fb4de>] __asan_report_load8_noabort+0x3e/0x40 kernel/mm/kasan/report.c:280
 [<     inline     >] ? ppp_pernet kernel/include/linux/compiler.h:218
 [<ffffffff83ad71b2>] ? ppp_unregister_channel+0x372/0x3a0 kernel/drivers/net/ppp/ppp_generic.c:2392
 [<     inline     >] ppp_pernet kernel/include/linux/compiler.h:218
 [<ffffffff83ad71b2>] ppp_unregister_channel+0x372/0x3a0 kernel/drivers/net/ppp/ppp_generic.c:2392
 [<     inline     >] ? ppp_pernet kernel/drivers/net/ppp/ppp_generic.c:293
 [<ffffffff83ad6f26>] ? ppp_unregister_channel+0xe6/0x3a0 kernel/drivers/net/ppp/ppp_generic.c:2392
 [<ffffffff83ae18f3>] ppp_asynctty_close+0xa3/0x130 kernel/drivers/net/ppp/ppp_async.c:241
 [<ffffffff83ae1850>] ? async_lcp_peek+0x5b0/0x5b0 kernel/drivers/net/ppp/ppp_async.c:1000
 [<ffffffff82c33239>] tty_ldisc_close.isra.1+0x99/0xe0 kernel/drivers/tty/tty_ldisc.c:478
 [<ffffffff82c332c0>] tty_ldisc_kill+0x40/0x170 kernel/drivers/tty/tty_ldisc.c:744
 [<ffffffff82c34943>] tty_ldisc_release+0x1b3/0x260 kernel/drivers/tty/tty_ldisc.c:772
 [<ffffffff82c1ef21>] tty_release+0xac1/0x13e0 kernel/drivers/tty/tty_io.c:1901
 [<ffffffff82c1e460>] ? release_tty+0x320/0x320 kernel/drivers/tty/tty_io.c:1688
 [<ffffffff8174de36>] __fput+0x236/0x780 kernel/fs/file_table.c:208
 [<ffffffff8174e405>] ____fput+0x15/0x20 kernel/fs/file_table.c:244
 [<ffffffff813595ab>] task_work_run+0x16b/0x200 kernel/kernel/task_work.c:115
 [<     inline     >] exit_task_work kernel/include/linux/task_work.h:21
 [<ffffffff81307105>] do_exit+0x8b5/0x2c60 kernel/kernel/exit.c:750
 [<ffffffff813fdd20>] ? debug_check_no_locks_freed+0x290/0x290 kernel/kernel/locking/lockdep.c:4123
 [<ffffffff81306850>] ? mm_update_next_owner+0x6f0/0x6f0 kernel/kernel/exit.c:357
 [<ffffffff813215e6>] ? __dequeue_signal+0x136/0x470 kernel/kernel/signal.c:550
 [<ffffffff8132067b>] ? recalc_sigpending_tsk+0x13b/0x180 kernel/kernel/signal.c:145
 [<ffffffff81309628>] do_group_exit+0x108/0x330 kernel/kernel/exit.c:880
 [<ffffffff8132b9d4>] get_signal+0x5e4/0x14f0 kernel/kernel/signal.c:2307
 [<     inline     >] ? kretprobe_table_lock kernel/kernel/kprobes.c:1113
 [<ffffffff8151d355>] ? kprobe_flush_task+0xb5/0x450 kernel/kernel/kprobes.c:1158
 [<ffffffff8115f7d3>] do_signal+0x83/0x1c90 kernel/arch/x86/kernel/signal.c:712
 [<ffffffff8151d2a0>] ? recycle_rp_inst+0x310/0x310 kernel/include/linux/list.h:655
 [<ffffffff8115f750>] ? setup_sigcontext+0x780/0x780 kernel/arch/x86/kernel/signal.c:165
 [<ffffffff81380864>] ? finish_task_switch+0x424/0x5f0 kernel/kernel/sched/core.c:2692
 [<     inline     >] ? finish_lock_switch kernel/kernel/sched/sched.h:1099
 [<ffffffff81380560>] ? finish_task_switch+0x120/0x5f0 kernel/kernel/sched/core.c:2678
 [<     inline     >] ? context_switch kernel/kernel/sched/core.c:2807
 [<ffffffff85d794e9>] ? __schedule+0x919/0x1bd0 kernel/kernel/sched/core.c:3283
 [<ffffffff81003901>] exit_to_usermode_loop+0xf1/0x1a0 kernel/arch/x86/entry/common.c:247
 [<     inline     >] prepare_exit_to_usermode kernel/arch/x86/entry/common.c:282
 [<ffffffff810062ef>] syscall_return_slowpath+0x19f/0x210 kernel/arch/x86/entry/common.c:344
 [<ffffffff85d88022>] int_ret_from_sys_call+0x25/0x9f kernel/arch/x86/entry/entry_64.S:281
Memory state around the buggy address:
 ffff880064e21680: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff880064e21700: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff880064e21780: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                                                       ^
 ffff880064e21800: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff880064e21880: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
==================================================================

Fixes: 273ec51dd7ce ("net: ppp_generic - introduce net-namespace functionality v2")
Reported-by: Baozeng Ding <sploving1@gmail.com>
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Reviewed-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/ppp_generic.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 35e8b5a..174e06e 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -2293,7 +2293,7 @@ int ppp_register_net_channel(struct net *net, struct ppp_channel *chan)
 
 	pch->ppp = NULL;
 	pch->chan = chan;
-	pch->chan_net = net;
+	pch->chan_net = get_net(net);
 	chan->ppp = pch;
 	init_ppp_file(&pch->file, CHANNEL);
 	pch->file.hdrlen = chan->hdrlen;
@@ -2390,6 +2390,8 @@ ppp_unregister_channel(struct ppp_channel *chan)
 	spin_lock_bh(&pn->all_channels_lock);
 	list_del(&pch->list);
 	spin_unlock_bh(&pn->all_channels_lock);
+	put_net(pch->chan_net);
+	pch->chan_net = NULL;
 
 	pch->file.dead = 1;
 	wake_up_interruptible(&pch->file.rwait);
-- 
2.1.0


From 192346f134faccd0bdf417d359985f5e525d8379 Mon Sep 17 00:00:00 2001
From: "subashab@codeaurora.org" <subashab@codeaurora.org>
Date: Wed, 23 Mar 2016 22:39:50 -0600
Subject: [PATCH 45/56] xfrm: Fix crash observed during device unregistration
 and decryption

[ Upstream commit 071d36bf21bcc837be00cea55bcef8d129e7f609 ]

A crash is observed when a decrypted packet is processed in receive
path. get_rps_cpus() tries to dereference the skb->dev fields but it
appears that the device is freed from the poison pattern.

[<ffffffc000af58ec>] get_rps_cpu+0x94/0x2f0
[<ffffffc000af5f94>] netif_rx_internal+0x140/0x1cc
[<ffffffc000af6094>] netif_rx+0x74/0x94
[<ffffffc000bc0b6c>] xfrm_input+0x754/0x7d0
[<ffffffc000bc0bf8>] xfrm_input_resume+0x10/0x1c
[<ffffffc000ba6eb8>] esp_input_done+0x20/0x30
[<ffffffc0000b64c8>] process_one_work+0x244/0x3fc
[<ffffffc0000b7324>] worker_thread+0x2f8/0x418
[<ffffffc0000bb40c>] kthread+0xe0/0xec

-013|get_rps_cpu(
     |    dev = 0xFFFFFFC08B688000,
     |    skb = 0xFFFFFFC0C76AAC00 -> (
     |      dev = 0xFFFFFFC08B688000 -> (
     |        name =
"......................................................
     |        name_hlist = (next = 0xAAAAAAAAAAAAAAAA, pprev =
0xAAAAAAAAAAA

Following are the sequence of events observed -

- Encrypted packet in receive path from netdevice is queued
- Encrypted packet queued for decryption (asynchronous)
- Netdevice brought down and freed
- Packet is decrypted and returned through callback in esp_input_done
- Packet is queued again for process in network stack using netif_rx

Since the device appears to have been freed, the dereference of
skb->dev in get_rps_cpus() leads to an unhandled page fault
exception.

Fix this by holding on to device reference when queueing packets
asynchronously and releasing the reference on call back return.

v2: Make the change generic to xfrm as mentioned by Steffen and
update the title to xfrm

Suggested-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Jerome Stanislaus <jeromes@codeaurora.org>
Signed-off-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/xfrm/xfrm_input.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index ad7f5b3..1c4ad47 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -292,12 +292,15 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 		XFRM_SKB_CB(skb)->seq.input.hi = seq_hi;
 
 		skb_dst_force(skb);
+		dev_hold(skb->dev);
 
 		nexthdr = x->type->input(x, skb);
 
 		if (nexthdr == -EINPROGRESS)
 			return 0;
 resume:
+		dev_put(skb->dev);
+
 		spin_lock(&x->lock);
 		if (nexthdr <= 0) {
 			if (nexthdr == -EBADMSG) {
-- 
2.1.0


From e7ac15057b9dcbe1222771cbc0c68813506a32c8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Mon, 28 Mar 2016 22:38:16 +0200
Subject: [PATCH 46/56] qmi_wwan: add "D-Link DWM-221 B1" device id
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit e84810c7b85a2d7897797b3ad3e879168a8e032a ]

Thomas reports:
"Windows:

00 diagnostics
01 modem
02 at-port
03 nmea
04 nic

Linux:

T:  Bus=02 Lev=01 Prnt=01 Port=03 Cnt=01 Dev#=  4 Spd=480 MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=2001 ProdID=7e19 Rev=02.32
S:  Manufacturer=Mobile Connect
S:  Product=Mobile Connect
S:  SerialNumber=0123456789ABCDEF
C:  #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
I:  If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
I:  If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
I:  If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
I:  If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
I:  If#= 5 Alt= 0 #EPs= 2 Cls=08(stor.) Sub=06 Prot=50 Driver=usb-storage"

Reported-by: Thomas Schäfer <tschaefer@t-online.de>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index df77467..a34f491 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -699,6 +699,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x19d2, 0x1426, 2)},	/* ZTE MF91 */
 	{QMI_FIXED_INTF(0x19d2, 0x1428, 2)},	/* Telewell TW-LTE 4G v2 */
 	{QMI_FIXED_INTF(0x19d2, 0x2002, 4)},	/* ZTE (Vodafone) K3765-Z */
+	{QMI_FIXED_INTF(0x2001, 0x7e19, 4)},	/* D-Link DWM-221 B1 */
 	{QMI_FIXED_INTF(0x0f3d, 0x68a2, 8)},    /* Sierra Wireless MC7700 */
 	{QMI_FIXED_INTF(0x114f, 0x68a2, 8)},    /* Sierra Wireless MC7750 */
 	{QMI_FIXED_INTF(0x1199, 0x68a2, 8)},	/* Sierra Wireless MC7710 in QMI mode */
-- 
2.1.0


From ec7f908ae22a131f117e90811c835c3cd8ed2c30 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 29 Mar 2016 08:43:41 -0700
Subject: [PATCH 47/56] ipv6: udp: fix UDP_MIB_IGNOREDMULTI updates

[ Upstream commit 2d4212261fdf13e29728ddb5ea9d60c342cc92b5 ]

IPv6 counters updates use a different macro than IPv4.

Fixes: 36cbb2452cbaf ("udp: Increment UDP_MIB_IGNOREDMULTI for arriving unmatched multicasts")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Rick Jones <rick.jones2@hp.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/udp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 1e293a5..6665e1a 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -837,8 +837,8 @@ start_lookup:
 		flush_stack(stack, count, skb, count - 1);
 	} else {
 		if (!inner_flushed)
-			UDP_INC_STATS_BH(net, UDP_MIB_IGNOREDMULTI,
-					 proto == IPPROTO_UDPLITE);
+			UDP6_INC_STATS_BH(net, UDP_MIB_IGNOREDMULTI,
+					  proto == IPPROTO_UDPLITE);
 		consume_skb(skb);
 	}
 	return 0;
-- 
2.1.0


From b5af4fd60e99bed8902b8c44548cbfcf9092c22b Mon Sep 17 00:00:00 2001
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Tue, 29 Mar 2016 18:48:08 +0800
Subject: [PATCH 48/56] bridge: Allow set bridge ageing time when switchdev
 disabled

[ Upstream commit 5e263f712691615fb802f06c98d7638c378f5d11 ]

When NET_SWITCHDEV=n, switchdev_port_attr_set will return -EOPNOTSUPP,
we should ignore this error code and continue to set the ageing time.

Fixes: c62987bbd8a1 ("bridge: push bridge setting ageing_time down to switchdev")
Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Acked-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_stp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c
index 0e658f4..eff69cb 100644
--- a/net/bridge/br_stp.c
+++ b/net/bridge/br_stp.c
@@ -586,7 +586,7 @@ int br_set_ageing_time(struct net_bridge *br, u32 ageing_time)
 	int err;
 
 	err = switchdev_port_attr_set(br->dev, &attr);
-	if (err)
+	if (err && err != -EOPNOTSUPP)
 		return err;
 
 	br->ageing_time = t;
-- 
2.1.0


From d93bd509709669d3e9077a7cc60f9133c854156b Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Thu, 31 Mar 2016 18:10:31 +0200
Subject: [PATCH 49/56] rtnl: fix msg size calculation in if_nlmsg_size()

[ Upstream commit c57c7a95da842807b475b823ed2e5435c42cb3b0 ]

Size of the attribute IFLA_PHYS_PORT_NAME was missing.

Fixes: db24a9044ee1 ("net: add support for phys_port_name")
CC: David Ahern <dsahern@gmail.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 34ba7a0..ca966f7 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -905,6 +905,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + rtnl_link_get_af_size(dev, ext_filter_mask) /* IFLA_AF_SPEC */
 	       + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_PORT_ID */
 	       + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_SWITCH_ID */
+	       + nla_total_size(IFNAMSIZ) /* IFLA_PHYS_PORT_NAME */
 	       + nla_total_size(1); /* IFLA_PROTO_DOWN */
 
 }
-- 
2.1.0


From ba41b79cefe9a7bd0f6b4a40dcd6c4ed4af06dfd Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 31 Mar 2016 02:13:18 +0200
Subject: [PATCH 50/56] tun, bpf: fix suspicious RCU usage in tun_{attach,
 detach}_filter

[ Upstream commit 5a5abb1fa3b05dd6aa821525832644c1e7d2905f ]

Sasha Levin reported a suspicious rcu_dereference_protected() warning
found while fuzzing with trinity that is similar to this one:

  [   52.765684] net/core/filter.c:2262 suspicious rcu_dereference_protected() usage!
  [   52.765688] other info that might help us debug this:
  [   52.765695] rcu_scheduler_active = 1, debug_locks = 1
  [   52.765701] 1 lock held by a.out/1525:
  [   52.765704]  #0:  (rtnl_mutex){+.+.+.}, at: [<ffffffff816a64b7>] rtnl_lock+0x17/0x20
  [   52.765721] stack backtrace:
  [   52.765728] CPU: 1 PID: 1525 Comm: a.out Not tainted 4.5.0+ #264
  [...]
  [   52.765768] Call Trace:
  [   52.765775]  [<ffffffff813e488d>] dump_stack+0x85/0xc8
  [   52.765784]  [<ffffffff810f2fa5>] lockdep_rcu_suspicious+0xd5/0x110
  [   52.765792]  [<ffffffff816afdc2>] sk_detach_filter+0x82/0x90
  [   52.765801]  [<ffffffffa0883425>] tun_detach_filter+0x35/0x90 [tun]
  [   52.765810]  [<ffffffffa0884ed4>] __tun_chr_ioctl+0x354/0x1130 [tun]
  [   52.765818]  [<ffffffff8136fed0>] ? selinux_file_ioctl+0x130/0x210
  [   52.765827]  [<ffffffffa0885ce3>] tun_chr_ioctl+0x13/0x20 [tun]
  [   52.765834]  [<ffffffff81260ea6>] do_vfs_ioctl+0x96/0x690
  [   52.765843]  [<ffffffff81364af3>] ? security_file_ioctl+0x43/0x60
  [   52.765850]  [<ffffffff81261519>] SyS_ioctl+0x79/0x90
  [   52.765858]  [<ffffffff81003ba2>] do_syscall_64+0x62/0x140
  [   52.765866]  [<ffffffff817d563f>] entry_SYSCALL64_slow_path+0x25/0x25

Same can be triggered with PROVE_RCU (+ PROVE_RCU_REPEATEDLY) enabled
from tun_attach_filter() when user space calls ioctl(tun_fd, TUN{ATTACH,
DETACH}FILTER, ...) for adding/removing a BPF filter on tap devices.

Since the fix in f91ff5b9ff52 ("net: sk_{detach|attach}_filter() rcu
fixes") sk_attach_filter()/sk_detach_filter() now dereferences the
filter with rcu_dereference_protected(), checking whether socket lock
is held in control path.

Since its introduction in 994051625981 ("tun: socket filter support"),
tap filters are managed under RTNL lock from __tun_chr_ioctl(). Thus the
sock_owned_by_user(sk) doesn't apply in this specific case and therefore
triggers the false positive.

Extend the BPF API with __sk_attach_filter()/__sk_detach_filter() pair
that is used by tap filters and pass in lockdep_rtnl_is_held() for the
rcu_dereference_protected() checks instead.

Reported-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c      |  8 +++++---
 include/linux/filter.h |  4 ++++
 net/core/filter.c      | 33 +++++++++++++++++++++------------
 3 files changed, 30 insertions(+), 15 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index f0db770..9bc7b0c 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -621,7 +621,8 @@ static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filte
 
 	/* Re-attach the filter to persist device */
 	if (!skip_filter && (tun->filter_attached == true)) {
-		err = sk_attach_filter(&tun->fprog, tfile->socket.sk);
+		err = __sk_attach_filter(&tun->fprog, tfile->socket.sk,
+					 lockdep_rtnl_is_held());
 		if (!err)
 			goto out;
 	}
@@ -1804,7 +1805,7 @@ static void tun_detach_filter(struct tun_struct *tun, int n)
 
 	for (i = 0; i < n; i++) {
 		tfile = rtnl_dereference(tun->tfiles[i]);
-		sk_detach_filter(tfile->socket.sk);
+		__sk_detach_filter(tfile->socket.sk, lockdep_rtnl_is_held());
 	}
 
 	tun->filter_attached = false;
@@ -1817,7 +1818,8 @@ static int tun_attach_filter(struct tun_struct *tun)
 
 	for (i = 0; i < tun->numqueues; i++) {
 		tfile = rtnl_dereference(tun->tfiles[i]);
-		ret = sk_attach_filter(&tun->fprog, tfile->socket.sk);
+		ret = __sk_attach_filter(&tun->fprog, tfile->socket.sk,
+					 lockdep_rtnl_is_held());
 		if (ret) {
 			tun_detach_filter(tun, i);
 			return ret;
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 5972ffe..5110d42 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -446,8 +446,12 @@ int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog,
 void bpf_prog_destroy(struct bpf_prog *fp);
 
 int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk);
+int __sk_attach_filter(struct sock_fprog *fprog, struct sock *sk,
+		       bool locked);
 int sk_attach_bpf(u32 ufd, struct sock *sk);
 int sk_detach_filter(struct sock *sk);
+int __sk_detach_filter(struct sock *sk, bool locked);
+
 int sk_get_filter(struct sock *sk, struct sock_filter __user *filter,
 		  unsigned int len);
 
diff --git a/net/core/filter.c b/net/core/filter.c
index 37157c4..f393a22 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1139,7 +1139,8 @@ void bpf_prog_destroy(struct bpf_prog *fp)
 }
 EXPORT_SYMBOL_GPL(bpf_prog_destroy);
 
-static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk)
+static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk,
+			    bool locked)
 {
 	struct sk_filter *fp, *old_fp;
 
@@ -1155,10 +1156,8 @@ static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk)
 		return -ENOMEM;
 	}
 
-	old_fp = rcu_dereference_protected(sk->sk_filter,
-					   sock_owned_by_user(sk));
+	old_fp = rcu_dereference_protected(sk->sk_filter, locked);
 	rcu_assign_pointer(sk->sk_filter, fp);
-
 	if (old_fp)
 		sk_filter_uncharge(sk, old_fp);
 
@@ -1175,7 +1174,8 @@ static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk)
  * occurs or there is insufficient memory for the filter a negative
  * errno code is returned. On success the return is zero.
  */
-int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
+int __sk_attach_filter(struct sock_fprog *fprog, struct sock *sk,
+		       bool locked)
 {
 	unsigned int fsize = bpf_classic_proglen(fprog);
 	unsigned int bpf_fsize = bpf_prog_size(fprog->len);
@@ -1213,7 +1213,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 	if (IS_ERR(prog))
 		return PTR_ERR(prog);
 
-	err = __sk_attach_prog(prog, sk);
+	err = __sk_attach_prog(prog, sk, locked);
 	if (err < 0) {
 		__bpf_prog_release(prog);
 		return err;
@@ -1221,7 +1221,12 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(sk_attach_filter);
+EXPORT_SYMBOL_GPL(__sk_attach_filter);
+
+int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
+{
+	return __sk_attach_filter(fprog, sk, sock_owned_by_user(sk));
+}
 
 int sk_attach_bpf(u32 ufd, struct sock *sk)
 {
@@ -1240,7 +1245,7 @@ int sk_attach_bpf(u32 ufd, struct sock *sk)
 		return -EINVAL;
 	}
 
-	err = __sk_attach_prog(prog, sk);
+	err = __sk_attach_prog(prog, sk, sock_owned_by_user(sk));
 	if (err < 0) {
 		bpf_prog_put(prog);
 		return err;
@@ -1913,7 +1918,7 @@ static int __init register_sk_filter_ops(void)
 }
 late_initcall(register_sk_filter_ops);
 
-int sk_detach_filter(struct sock *sk)
+int __sk_detach_filter(struct sock *sk, bool locked)
 {
 	int ret = -ENOENT;
 	struct sk_filter *filter;
@@ -1921,8 +1926,7 @@ int sk_detach_filter(struct sock *sk)
 	if (sock_flag(sk, SOCK_FILTER_LOCKED))
 		return -EPERM;
 
-	filter = rcu_dereference_protected(sk->sk_filter,
-					   sock_owned_by_user(sk));
+	filter = rcu_dereference_protected(sk->sk_filter, locked);
 	if (filter) {
 		RCU_INIT_POINTER(sk->sk_filter, NULL);
 		sk_filter_uncharge(sk, filter);
@@ -1931,7 +1935,12 @@ int sk_detach_filter(struct sock *sk)
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(sk_detach_filter);
+EXPORT_SYMBOL_GPL(__sk_detach_filter);
+
+int sk_detach_filter(struct sock *sk)
+{
+	return __sk_detach_filter(sk, sock_owned_by_user(sk));
+}
 
 int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf,
 		  unsigned int len)
-- 
2.1.0


From 5c6e46ed7e261e007378f295bb5fa95646f3b01d Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Fri, 8 Apr 2016 13:26:48 +0800
Subject: [PATCH 51/56] tuntap: restore default qdisc

[ Upstream commit 016adb7260f481168c03e09f785184d6d5278894 ]

After commit f84bb1eac027 ("net: fix IFF_NO_QUEUE for drivers using
alloc_netdev"), default qdisc was changed to noqueue because
tuntap does not set tx_queue_len during .setup(). This patch restores
default qdisc by setting tx_queue_len in tun_setup().

Fixes: f84bb1eac027 ("net: fix IFF_NO_QUEUE for drivers using alloc_netdev")
Cc: Phil Sutter <phil@nwl.cc>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 9bc7b0c..2d186bd 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1001,7 +1001,6 @@ static void tun_net_init(struct net_device *dev)
 		/* Zero header length */
 		dev->type = ARPHRD_NONE;
 		dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST;
-		dev->tx_queue_len = TUN_READQ_SIZE;  /* We prefer our own queue length */
 		break;
 
 	case IFF_TAP:
@@ -1013,7 +1012,6 @@ static void tun_net_init(struct net_device *dev)
 
 		eth_hw_addr_random(dev);
 
-		dev->tx_queue_len = TUN_READQ_SIZE;  /* We prefer our own queue length */
 		break;
 	}
 }
@@ -1464,6 +1462,8 @@ static void tun_setup(struct net_device *dev)
 
 	dev->ethtool_ops = &tun_ethtool_ops;
 	dev->destructor = tun_free_netdev;
+	/* We prefer our own queue length */
+	dev->tx_queue_len = TUN_READQ_SIZE;
 }
 
 /* Trivial set of netlink ops to allow deleting tun or tap
-- 
2.1.0


From a0c3ba23c231dca5b0acb5b9e2ad25744446646e Mon Sep 17 00:00:00 2001
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Sun, 3 Apr 2016 22:09:23 +0800
Subject: [PATCH 52/56] ipv4: l2tp: fix a potential issue in l2tp_ip_recv

[ Upstream commit 5745b8232e942abd5e16e85fa9b27cc21324acf0 ]

pskb_may_pull() can change skb->data, so we have to load ptr/optr at the
right place.

Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ip.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index ec22078..42de4cc 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -123,12 +123,11 @@ static int l2tp_ip_recv(struct sk_buff *skb)
 	struct l2tp_tunnel *tunnel = NULL;
 	int length;
 
-	/* Point to L2TP header */
-	optr = ptr = skb->data;
-
 	if (!pskb_may_pull(skb, 4))
 		goto discard;
 
+	/* Point to L2TP header */
+	optr = ptr = skb->data;
 	session_id = ntohl(*((__be32 *) ptr));
 	ptr += 4;
 
@@ -156,6 +155,9 @@ static int l2tp_ip_recv(struct sk_buff *skb)
 		if (!pskb_may_pull(skb, length))
 			goto discard;
 
+		/* Point to L2TP header */
+		optr = ptr = skb->data;
+		ptr += 4;
 		pr_debug("%s: ip recv\n", tunnel->name);
 		print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length);
 	}
-- 
2.1.0


From b3397ab4c28e9aa76f687a5e96919ed399e5643a Mon Sep 17 00:00:00 2001
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Sun, 3 Apr 2016 22:09:24 +0800
Subject: [PATCH 53/56] ipv6: l2tp: fix a potential issue in l2tp_ip6_recv

[ Upstream commit be447f305494e019dfc37ea4cdf3b0e4200b4eba ]

pskb_may_pull() can change skb->data, so we have to load ptr/optr at the
right place.

Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ip6.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index a2c8747..9ee4ddb 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -135,12 +135,11 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
 	struct l2tp_tunnel *tunnel = NULL;
 	int length;
 
-	/* Point to L2TP header */
-	optr = ptr = skb->data;
-
 	if (!pskb_may_pull(skb, 4))
 		goto discard;
 
+	/* Point to L2TP header */
+	optr = ptr = skb->data;
 	session_id = ntohl(*((__be32 *) ptr));
 	ptr += 4;
 
@@ -168,6 +167,9 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
 		if (!pskb_may_pull(skb, length))
 			goto discard;
 
+		/* Point to L2TP header */
+		optr = ptr = skb->data;
+		ptr += 4;
 		pr_debug("%s: ip recv\n", tunnel->name);
 		print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length);
 	}
-- 
2.1.0


From fe7a4f20ddbefed1552af73a56ce3febd5689c86 Mon Sep 17 00:00:00 2001
From: Thadeu Lima de Souza Cascardo <cascardo@redhat.com>
Date: Fri, 1 Apr 2016 17:17:50 -0300
Subject: [PATCH 54/56] ip6_tunnel: set rtnl_link_ops before calling
 register_netdevice

[ Upstream commit b6ee376cb0b7fb4e7e07d6cd248bd40436fb9ba6 ]

When creating an ip6tnl tunnel with ip tunnel, rtnl_link_ops is not set
before ip6_tnl_create2 is called. When register_netdevice is called, there
is no linkinfo attribute in the NEWLINK message because of that.

Setting rtnl_link_ops before calling register_netdevice fixes that.

Fixes: 0b112457229d ("ip6tnl: add support of link creation via rtnl")
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@redhat.com>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 6c5dfec..3991b21 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -343,12 +343,12 @@ static int ip6_tnl_create2(struct net_device *dev)
 
 	t = netdev_priv(dev);
 
+	dev->rtnl_link_ops = &ip6_link_ops;
 	err = register_netdevice(dev);
 	if (err < 0)
 		goto out;
 
 	strcpy(t->parms.name, dev->name);
-	dev->rtnl_link_ops = &ip6_link_ops;
 
 	dev_hold(dev);
 	ip6_tnl_link(ip6n, t);
-- 
2.1.0


From 750c7e0168d2890a2d98e6ae37ecf8be40d9715b Mon Sep 17 00:00:00 2001
From: Jakub Sitnicki <jkbs@redhat.com>
Date: Tue, 5 Apr 2016 18:41:08 +0200
Subject: [PATCH 55/56] ipv6: Count in extension headers in skb->network_header

[ Upstream commit 3ba3458fb9c050718b95275a3310b74415e767e2 ]

When sending a UDPv6 message longer than MTU, account for the length
of fragmentable IPv6 extension headers in skb->network_header offset.
Same as we do in alloc_new_skb path in __ip6_append_data().

This ensures that later on __ip6_make_skb() will make space in
headroom for fragmentable extension headers:

	/* move skb->data to ip header from ext header */
	if (skb->data < skb_network_header(skb))
		__skb_pull(skb, skb_network_offset(skb));

Prevents a splat due to skb_under_panic:

skbuff: skb_under_panic: text:ffffffff8143397b len:2126 put:14 \
head:ffff880005bacf50 data:ffff880005bacf4a tail:0x48 end:0xc0 dev:lo
------------[ cut here ]------------
kernel BUG at net/core/skbuff.c:104!
invalid opcode: 0000 [#1] KASAN
CPU: 0 PID: 160 Comm: reproducer Not tainted 4.6.0-rc2 #65
[...]
Call Trace:
 [<ffffffff813eb7b9>] skb_push+0x79/0x80
 [<ffffffff8143397b>] eth_header+0x2b/0x100
 [<ffffffff8141e0d0>] neigh_resolve_output+0x210/0x310
 [<ffffffff814eab77>] ip6_finish_output2+0x4a7/0x7c0
 [<ffffffff814efe3a>] ip6_output+0x16a/0x280
 [<ffffffff815440c1>] ip6_local_out+0xb1/0xf0
 [<ffffffff814f1115>] ip6_send_skb+0x45/0xd0
 [<ffffffff81518836>] udp_v6_send_skb+0x246/0x5d0
 [<ffffffff8151985e>] udpv6_sendmsg+0xa6e/0x1090
[...]

Reported-by: Ji Jianwen <jiji@redhat.com>
Signed-off-by: Jakub Sitnicki <jkbs@redhat.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_output.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 31144c4..a175152 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1091,8 +1091,8 @@ static inline int ip6_ufo_append_data(struct sock *sk,
 			int getfrag(void *from, char *to, int offset, int len,
 			int odd, struct sk_buff *skb),
 			void *from, int length, int hh_len, int fragheaderlen,
-			int transhdrlen, int mtu, unsigned int flags,
-			const struct flowi6 *fl6)
+			int exthdrlen, int transhdrlen, int mtu,
+			unsigned int flags, const struct flowi6 *fl6)
 
 {
 	struct sk_buff *skb;
@@ -1117,7 +1117,7 @@ static inline int ip6_ufo_append_data(struct sock *sk,
 		skb_put(skb, fragheaderlen + transhdrlen);
 
 		/* initialize network header pointer */
-		skb_reset_network_header(skb);
+		skb_set_network_header(skb, exthdrlen);
 
 		/* initialize protocol header pointer */
 		skb->transport_header = skb->network_header + fragheaderlen;
@@ -1359,7 +1359,7 @@ emsgsize:
 	    (rt->dst.dev->features & NETIF_F_UFO) &&
 	    (sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk)) {
 		err = ip6_ufo_append_data(sk, queue, getfrag, from, length,
-					  hh_len, fragheaderlen,
+					  hh_len, fragheaderlen, exthdrlen,
 					  transhdrlen, mtu, flags, fl6);
 		if (err)
 			goto error;
-- 
2.1.0


From bdea26cc21b6d4f71c46da142b12e55dc9b26133 Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Thu, 7 Apr 2016 21:28:38 -0700
Subject: [PATCH 56/56] mpls: find_outdev: check for err ptr in addition to
 NULL check

[ Upstream commit 94a57f1f8a9de90ab4b0f8748361ff8be706c80c ]

find_outdev calls inet{,6}_fib_lookup_dev() or dev_get_by_index() to
find the output device. In case of an error, inet{,6}_fib_lookup_dev()
returns error pointer and dev_get_by_index() returns NULL. But the function
only checks for NULL and thus can end up calling dev_put on an ERR_PTR.
This patch adds an additional check for err ptr after the NULL check.

Before: Trying to add an mpls route with no oif from user, no available
path to 10.1.1.8 and no default route:
$ip -f mpls route add 100 as 200 via inet 10.1.1.8
[  822.337195] BUG: unable to handle kernel NULL pointer dereference at
00000000000003a3
[  822.340033] IP: [<ffffffff8148781e>] mpls_nh_assign_dev+0x10b/0x182
[  822.340033] PGD 1db38067 PUD 1de9e067 PMD 0
[  822.340033] Oops: 0000 [#1] SMP
[  822.340033] Modules linked in:
[  822.340033] CPU: 0 PID: 11148 Comm: ip Not tainted 4.5.0-rc7+ #54
[  822.340033] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996),
BIOS rel-1.7.5.1-0-g8936dbb-20141113_115728-nilsson.home.kraxel.org
04/01/2014
[  822.340033] task: ffff88001db82580 ti: ffff88001dad4000 task.ti:
ffff88001dad4000
[  822.340033] RIP: 0010:[<ffffffff8148781e>]  [<ffffffff8148781e>]
mpls_nh_assign_dev+0x10b/0x182
[  822.340033] RSP: 0018:ffff88001dad7a88  EFLAGS: 00010282
[  822.340033] RAX: ffffffffffffff9b RBX: ffffffffffffff9b RCX:
0000000000000002
[  822.340033] RDX: 00000000ffffff9b RSI: 0000000000000008 RDI:
0000000000000000
[  822.340033] RBP: ffff88001ddc9ea0 R08: ffff88001e9f1768 R09:
0000000000000000
[  822.340033] R10: ffff88001d9c1100 R11: ffff88001e3c89f0 R12:
ffffffff8187e0c0
[  822.340033] R13: ffffffff8187e0c0 R14: ffff88001ddc9e80 R15:
0000000000000004
[  822.340033] FS:  00007ff9ed798700(0000) GS:ffff88001fc00000(0000)
knlGS:0000000000000000
[  822.340033] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  822.340033] CR2: 00000000000003a3 CR3: 000000001de89000 CR4:
00000000000006f0
[  822.340033] Stack:
[  822.340033]  0000000000000000 0000000100000000 0000000000000000
0000000000000000
[  822.340033]  0000000000000000 0801010a00000000 0000000000000000
0000000000000000
[  822.340033]  0000000000000004 ffffffff8148749b ffffffff8187e0c0
000000000000001c
[  822.340033] Call Trace:
[  822.340033]  [<ffffffff8148749b>] ? mpls_rt_alloc+0x2b/0x3e
[  822.340033]  [<ffffffff81488e66>] ? mpls_rtm_newroute+0x358/0x3e2
[  822.340033]  [<ffffffff810e7bbc>] ? get_page+0x5/0xa
[  822.340033]  [<ffffffff813b7d94>] ? rtnetlink_rcv_msg+0x17e/0x191
[  822.340033]  [<ffffffff8111794e>] ? __kmalloc_track_caller+0x8c/0x9e
[  822.340033]  [<ffffffff813c9393>] ?
rht_key_hashfn.isra.20.constprop.57+0x14/0x1f
[  822.340033]  [<ffffffff813b7c16>] ? __rtnl_unlock+0xc/0xc
[  822.340033]  [<ffffffff813cb794>] ? netlink_rcv_skb+0x36/0x82
[  822.340033]  [<ffffffff813b4507>] ? rtnetlink_rcv+0x1f/0x28
[  822.340033]  [<ffffffff813cb2b1>] ? netlink_unicast+0x106/0x189
[  822.340033]  [<ffffffff813cb5b3>] ? netlink_sendmsg+0x27f/0x2c8
[  822.340033]  [<ffffffff81392ede>] ? sock_sendmsg_nosec+0x10/0x1b
[  822.340033]  [<ffffffff81393df1>] ? ___sys_sendmsg+0x182/0x1e3
[  822.340033]  [<ffffffff810e4f35>] ?
__alloc_pages_nodemask+0x11c/0x1e4
[  822.340033]  [<ffffffff8110619c>] ? PageAnon+0x5/0xd
[  822.340033]  [<ffffffff811062fe>] ? __page_set_anon_rmap+0x45/0x52
[  822.340033]  [<ffffffff810e7bbc>] ? get_page+0x5/0xa
[  822.340033]  [<ffffffff810e85ab>] ? __lru_cache_add+0x1a/0x3a
[  822.340033]  [<ffffffff81087ea9>] ? current_kernel_time64+0x9/0x30
[  822.340033]  [<ffffffff813940c4>] ? __sys_sendmsg+0x3c/0x5a
[  822.340033]  [<ffffffff8148f597>] ?
entry_SYSCALL_64_fastpath+0x12/0x6a
[  822.340033] Code: 83 08 04 00 00 65 ff 00 48 8b 3c 24 e8 40 7c f2 ff
eb 13 48 c7 c3 9f ff ff ff eb 0f 89 ce e8 f1 ae f1 ff 48 89 c3 48 85 db
74 15 <48> 8b 83 08 04 00 00 65 ff 08 48 81 fb 00 f0 ff ff 76 0d eb 07
[  822.340033] RIP  [<ffffffff8148781e>] mpls_nh_assign_dev+0x10b/0x182
[  822.340033]  RSP <ffff88001dad7a88>
[  822.340033] CR2: 00000000000003a3
[  822.435363] ---[ end trace 98cc65e6f6b8bf11 ]---

After patch:
$ip -f mpls route add 100 as 200 via inet 10.1.1.8
RTNETLINK answers: Network is unreachable

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Reported-by: David Miller <davem@davemloft.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mpls/af_mpls.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index c32fc41..881bc20 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -518,6 +518,9 @@ static struct net_device *find_outdev(struct net *net,
 	if (!dev)
 		return ERR_PTR(-ENODEV);
 
+	if (IS_ERR(dev))
+		return dev;
+
 	/* The caller is holding rtnl anyways, so release the dev reference */
 	dev_put(dev);
 
-- 
2.1.0


[-- Attachment #4: net_45.mbox --]
[-- Type: Application/Octet-Stream, Size: 107010 bytes --]

From b11b31ff9c74e22642184f0f5a42ceb29853441e Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 9 Mar 2016 21:58:32 -0500
Subject: [PATCH 01/40] net: validate variable length ll headers

[ Upstream commit 2793a23aacbd754dbbb5cb75093deb7e4103bace ]

Netdevice parameter hard_header_len is variously interpreted both as
an upper and lower bound on link layer header length. The field is
used as upper bound when reserving room at allocation, as lower bound
when validating user input in PF_PACKET.

Clarify the definition to be maximum header length. For validation
of untrusted headers, add an optional validate member to header_ops.

Allow bypassing of validation by passing CAP_SYS_RAWIO, for instance
for deliberate testing of corrupt input. In this case, pad trailing
bytes, as some device drivers expect completely initialized headers.

See also http://comments.gmane.org/gmane.linux.network/401064

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 22 ++++++++++++++++++++--
 1 file changed, 20 insertions(+), 2 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5440b7b..6d1d8f4 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -267,6 +267,7 @@ struct header_ops {
 	void	(*cache_update)(struct hh_cache *hh,
 				const struct net_device *dev,
 				const unsigned char *haddr);
+	bool	(*validate)(const char *ll_header, unsigned int len);
 };
 
 /* These flag bits are private to the generic network queueing
@@ -1420,8 +1421,7 @@ enum netdev_priv_flags {
  *	@dma:		DMA channel
  *	@mtu:		Interface MTU value
  *	@type:		Interface hardware type
- *	@hard_header_len: Hardware header length, which means that this is the
- *			  minimum size of a packet.
+ *	@hard_header_len: Maximum hardware header length.
  *
  *	@needed_headroom: Extra headroom the hardware may need, but not in all
  *			  cases can this be guaranteed
@@ -2627,6 +2627,24 @@ static inline int dev_parse_header(const struct sk_buff *skb,
 	return dev->header_ops->parse(skb, haddr);
 }
 
+/* ll_header must have at least hard_header_len allocated */
+static inline bool dev_validate_header(const struct net_device *dev,
+				       char *ll_header, int len)
+{
+	if (likely(len >= dev->hard_header_len))
+		return true;
+
+	if (capable(CAP_SYS_RAWIO)) {
+		memset(ll_header + len, 0, dev->hard_header_len - len);
+		return true;
+	}
+
+	if (dev->header_ops && dev->header_ops->validate)
+		return dev->header_ops->validate(ll_header, len);
+
+	return false;
+}
+
 typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr, int len);
 int register_gifconf(unsigned int family, gifconf_func_t *gifconf);
 static inline int unregister_gifconf(unsigned int family)
-- 
2.1.0


From 41171c456b3ac590e4890516be6a714dfad1efc6 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 9 Mar 2016 21:58:33 -0500
Subject: [PATCH 02/40] ax25: add link layer header validation function

[ Upstream commit ea47781c26510e5d97f80f9aceafe9065bd5e3aa ]

As variable length protocol, AX25 fails link layer header validation
tests based on a minimum length. header_ops.validate allows protocols
to validate headers that are shorter than hard_header_len. Implement
this callback for AX25.

See also http://comments.gmane.org/gmane.linux.network/401064

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ax25/ax25_ip.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/net/ax25/ax25_ip.c b/net/ax25/ax25_ip.c
index b563a3f..2fa3be9 100644
--- a/net/ax25/ax25_ip.c
+++ b/net/ax25/ax25_ip.c
@@ -228,8 +228,23 @@ netdev_tx_t ax25_ip_xmit(struct sk_buff *skb)
 }
 #endif
 
+static bool ax25_validate_header(const char *header, unsigned int len)
+{
+	ax25_digi digi;
+
+	if (!len)
+		return false;
+
+	if (header[0])
+		return true;
+
+	return ax25_addr_parse(header + 1, len - 1, NULL, NULL, &digi, NULL,
+			       NULL);
+}
+
 const struct header_ops ax25_header_ops = {
 	.create = ax25_hard_header,
+	.validate = ax25_validate_header,
 };
 
 EXPORT_SYMBOL(ax25_header_ops);
-- 
2.1.0


From 6784fea17ef28e907de6cfc563dc66838997ff1f Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 9 Mar 2016 21:58:34 -0500
Subject: [PATCH 03/40] packet: validate variable length ll headers

[ Upstream commit 9ed988cd591500c040b2a6257bc68543e08ceeef ]

Replace link layer header validation check ll_header_truncate with
more generic dev_validate_header.

Validation based on hard_header_len incorrectly drops valid packets
in variable length protocols, such as AX25. dev_validate_header
calls header_ops.validate for such protocols to ensure correctness
below hard_header_len.

See also http://comments.gmane.org/gmane.linux.network/401064

Fixes 9c7077622dd9 ("packet: make packet_snd fail on len smaller than l2 header")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 37 ++++++++++++++++---------------------
 1 file changed, 16 insertions(+), 21 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 992396a..da1ae0e1 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1916,6 +1916,10 @@ retry:
 		goto retry;
 	}
 
+	if (!dev_validate_header(dev, skb->data, len)) {
+		err = -EINVAL;
+		goto out_unlock;
+	}
 	if (len > (dev->mtu + dev->hard_header_len + extra_len) &&
 	    !packet_extra_vlan_len_allowed(dev, skb)) {
 		err = -EMSGSIZE;
@@ -2326,18 +2330,6 @@ static void tpacket_destruct_skb(struct sk_buff *skb)
 	sock_wfree(skb);
 }
 
-static bool ll_header_truncated(const struct net_device *dev, int len)
-{
-	/* net device doesn't like empty head */
-	if (unlikely(len < dev->hard_header_len)) {
-		net_warn_ratelimited("%s: packet size is too short (%d < %d)\n",
-				     current->comm, len, dev->hard_header_len);
-		return true;
-	}
-
-	return false;
-}
-
 static void tpacket_set_protocol(const struct net_device *dev,
 				 struct sk_buff *skb)
 {
@@ -2420,19 +2412,19 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 		if (unlikely(err < 0))
 			return -EINVAL;
 	} else if (dev->hard_header_len) {
-		if (ll_header_truncated(dev, tp_len))
-			return -EINVAL;
+		int hdrlen = min_t(int, dev->hard_header_len, tp_len);
 
 		skb_push(skb, dev->hard_header_len);
-		err = skb_store_bits(skb, 0, data,
-				dev->hard_header_len);
+		err = skb_store_bits(skb, 0, data, hdrlen);
 		if (unlikely(err))
 			return err;
+		if (!dev_validate_header(dev, skb->data, hdrlen))
+			return -EINVAL;
 		if (!skb->protocol)
 			tpacket_set_protocol(dev, skb);
 
-		data += dev->hard_header_len;
-		to_write -= dev->hard_header_len;
+		data += hdrlen;
+		to_write -= hdrlen;
 	}
 
 	offset = offset_in_page(data);
@@ -2763,9 +2755,6 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		offset = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, len);
 		if (unlikely(offset < 0))
 			goto out_free;
-	} else {
-		if (ll_header_truncated(dev, len))
-			goto out_free;
 	}
 
 	/* Returns -EFAULT on error */
@@ -2773,6 +2762,12 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	if (err)
 		goto out_free;
 
+	if (sock->type == SOCK_RAW &&
+	    !dev_validate_header(dev, skb->data, len)) {
+		err = -EINVAL;
+		goto out_free;
+	}
+
 	sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags);
 
 	if (!gso_type && (len > dev->mtu + reserve + extra_len) &&
-- 
2.1.0


From 8f34a56c082bb870f80c0c78df324813993196eb Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@fb.com>
Date: Wed, 9 Mar 2016 20:02:33 -0800
Subject: [PATCH 04/40] bpf: avoid copying junk bytes in bpf_get_current_comm()

[ Upstream commit cdc4e47da8f4c32eeb6b2061a8a834f4362a12b7 ]

Lots of places in the kernel use memcpy(buf, comm, TASK_COMM_LEN); but
the result is typically passed to print("%s", buf) and extra bytes
after zero don't cause any harm.
In bpf the result of bpf_get_current_comm() is used as the part of
map key and was causing spurious hash map mismatches.
Use strlcpy() to guarantee zero-terminated string.
bpf verifier checks that output buffer is zero-initialized,
so even for short task names the output buffer don't have junk bytes.
Note it's not a security concern, since kprobe+bpf is root only.

Fixes: ffeedafbf023 ("bpf: introduce current->pid, tgid, uid, gid, comm accessors")
Reported-by: Tobias Waldekranz <tobias@waldekranz.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/helpers.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 4504ca6..50da680 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -166,7 +166,7 @@ static u64 bpf_get_current_comm(u64 r1, u64 size, u64 r3, u64 r4, u64 r5)
 	if (!task)
 		return -EINVAL;
 
-	memcpy(buf, task->comm, min_t(size_t, size, sizeof(task->comm)));
+	strlcpy(buf, task->comm, min_t(size_t, size, sizeof(task->comm)));
 	return 0;
 }
 
-- 
2.1.0


From e799cf407ee79ff534dbf8ea892383e58c2c6766 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <narmstrong@baylibre.com>
Date: Tue, 8 Mar 2016 10:36:20 +0100
Subject: [PATCH 05/40] net: dsa: Fix cleanup resources upon module removal

[ Upstream commit 04761890a7cec6a1ff9aafd909004da4fe8059db ]

The initial commit badly merged into the dsa_resume method instead
of the dsa_remove_dst method.
As consequence, the dst->master_netdev->dsa_ptr is not set to NULL on
removal and re-bind of the dsa device fails with error -17.

Fixes: b0dc635d923c ("net: dsa: cleanup resources upon module removal ")
Signed-off-by: Neil Armstrong <narmstrong@baylibre.com>
Acked-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/dsa.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index fa4daba..d8fb47f 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -935,6 +935,14 @@ static void dsa_remove_dst(struct dsa_switch_tree *dst)
 {
 	int i;
 
+	dst->master_netdev->dsa_ptr = NULL;
+
+	/* If we used a tagging format that doesn't have an ethertype
+	 * field, make sure that all packets from this point get sent
+	 * without the tag and go through the regular receive path.
+	 */
+	wmb();
+
 	for (i = 0; i < dst->pd->nr_chips; i++) {
 		struct dsa_switch *ds = dst->ds[i];
 
@@ -988,14 +996,6 @@ static int dsa_suspend(struct device *d)
 	struct dsa_switch_tree *dst = platform_get_drvdata(pdev);
 	int i, ret = 0;
 
-	dst->master_netdev->dsa_ptr = NULL;
-
-	/* If we used a tagging format that doesn't have an ethertype
-	 * field, make sure that all packets from this point get sent
-	 * without the tag and go through the regular receive path.
-	 */
-	wmb();
-
 	for (i = 0; i < dst->pd->nr_chips; i++) {
 		struct dsa_switch *ds = dst->ds[i];
 
-- 
2.1.0


From 8e4928acde26a9ebdcb2302cd2726606d8b187c4 Mon Sep 17 00:00:00 2001
From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Date: Tue, 8 Mar 2016 01:36:28 +0300
Subject: [PATCH 06/40] sh_eth: fix NULL pointer dereference in
 sh_eth_ring_format()

[ Upstream commit c1b7fca65070bfadca94dd53a4e6b71cd4f69715 ]

In a low memory situation, if netdev_alloc_skb() fails on a first RX ring
loop iteration  in sh_eth_ring_format(), 'rxdesc' is still NULL.  Avoid
kernel oops by adding the 'rxdesc' check after the loop.

Reported-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/sh_eth.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 7384499..b5ec8bf 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -1163,7 +1163,8 @@ static void sh_eth_ring_format(struct net_device *ndev)
 	mdp->dirty_rx = (u32) (i - mdp->num_rx_ring);
 
 	/* Mark the last entry as wrapping the ring. */
-	rxdesc->status |= cpu_to_le32(RD_RDLE);
+	if (rxdesc)
+		rxdesc->status |= cpu_to_le32(RD_RDLE);
 
 	memset(mdp->tx_ring, 0, tx_ringsize);
 
-- 
2.1.0


From 45d6ebd11dcaeef1282e3f578c9b47bf893121ac Mon Sep 17 00:00:00 2001
From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Date: Tue, 8 Mar 2016 01:37:09 +0300
Subject: [PATCH 07/40] sh_eth: advance 'rxdesc' later in sh_eth_ring_format()

[ Upstream commit d0ba913488dc8c55d1880f5ed34f096dc45fb05d ]

Iff dma_map_single() fails, 'rxdesc'  should point  to the last filled RX
descriptor, so  that it can be marked as the last one, however the driver
would have  already  advanced it by that time. In order to fix that, only
fill  an RX descriptor  once all the data for it is ready.

Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/sh_eth.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index b5ec8bf..01f6d5b 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -1136,11 +1136,8 @@ static void sh_eth_ring_format(struct net_device *ndev)
 			break;
 		sh_eth_set_receive_align(skb);
 
-		/* RX descriptor */
-		rxdesc = &mdp->rx_ring[i];
 		/* The size of the buffer is a multiple of 32 bytes. */
 		buf_len = ALIGN(mdp->rx_buf_sz, 32);
-		rxdesc->len = cpu_to_le32(buf_len << 16);
 		dma_addr = dma_map_single(&ndev->dev, skb->data, buf_len,
 					  DMA_FROM_DEVICE);
 		if (dma_mapping_error(&ndev->dev, dma_addr)) {
@@ -1148,6 +1145,10 @@ static void sh_eth_ring_format(struct net_device *ndev)
 			break;
 		}
 		mdp->rx_skbuff[i] = skb;
+
+		/* RX descriptor */
+		rxdesc = &mdp->rx_ring[i];
+		rxdesc->len = cpu_to_le32(buf_len << 16);
 		rxdesc->addr = cpu_to_le32(dma_addr);
 		rxdesc->status = cpu_to_le32(RD_RACT | RD_RFP);
 
-- 
2.1.0


From 44c81344e141f3d3e9c2309e4e688026c4384fd5 Mon Sep 17 00:00:00 2001
From: Rajesh Borundia <rajesh.borundia@qlogic.com>
Date: Tue, 8 Mar 2016 02:39:57 -0500
Subject: [PATCH 08/40] qlcnic: Remove unnecessary usage of atomic_t

[ Upstream commit 5bf93251cee1fb66141d1d2eaff86e04a9397bdf ]

o atomic_t usage is incorrect as we are not implementing
any atomicity.

Signed-off-by: Rajesh Borundia <rajesh.borundia@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qlcnic/qlcnic.h         | 2 +-
 drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c | 9 ++++-----
 2 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
index 46bbea8..d18667b 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
@@ -1099,7 +1099,7 @@ struct qlcnic_mailbox {
 	unsigned long		status;
 	spinlock_t		queue_lock;	/* Mailbox queue lock */
 	spinlock_t		aen_lock;	/* Mailbox response/AEN lock */
-	atomic_t		rsp_status;
+	u32			rsp_status;
 	u32			num_cmds;
 };
 
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
index 37a731b..e3d1bb7 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
@@ -491,7 +491,7 @@ irqreturn_t qlcnic_83xx_clear_legacy_intr(struct qlcnic_adapter *adapter)
 
 static inline void qlcnic_83xx_notify_mbx_response(struct qlcnic_mailbox *mbx)
 {
-	atomic_set(&mbx->rsp_status, QLC_83XX_MBX_RESPONSE_ARRIVED);
+	mbx->rsp_status = QLC_83XX_MBX_RESPONSE_ARRIVED;
 	complete(&mbx->completion);
 }
 
@@ -510,7 +510,7 @@ static void qlcnic_83xx_poll_process_aen(struct qlcnic_adapter *adapter)
 	if (event &  QLCNIC_MBX_ASYNC_EVENT) {
 		__qlcnic_83xx_process_aen(adapter);
 	} else {
-		if (atomic_read(&mbx->rsp_status) != rsp_status)
+		if (mbx->rsp_status != rsp_status)
 			qlcnic_83xx_notify_mbx_response(mbx);
 	}
 out:
@@ -1023,7 +1023,7 @@ static void qlcnic_83xx_process_aen(struct qlcnic_adapter *adapter)
 		if (event &  QLCNIC_MBX_ASYNC_EVENT) {
 			__qlcnic_83xx_process_aen(adapter);
 		} else {
-			if (atomic_read(&mbx->rsp_status) != rsp_status)
+			if (mbx->rsp_status != rsp_status)
 				qlcnic_83xx_notify_mbx_response(mbx);
 		}
 	}
@@ -4050,7 +4050,6 @@ static void qlcnic_83xx_mailbox_worker(struct work_struct *work)
 	struct qlcnic_adapter *adapter = mbx->adapter;
 	const struct qlcnic_mbx_ops *mbx_ops = mbx->ops;
 	struct device *dev = &adapter->pdev->dev;
-	atomic_t *rsp_status = &mbx->rsp_status;
 	struct list_head *head = &mbx->cmd_q;
 	struct qlcnic_hardware_context *ahw;
 	struct qlcnic_cmd_args *cmd = NULL;
@@ -4063,7 +4062,7 @@ static void qlcnic_83xx_mailbox_worker(struct work_struct *work)
 			return;
 		}
 
-		atomic_set(rsp_status, QLC_83XX_MBX_RESPONSE_WAIT);
+		mbx->rsp_status = QLC_83XX_MBX_RESPONSE_WAIT;
 
 		spin_lock(&mbx->queue_lock);
 
-- 
2.1.0


From 8653d6b279a09b74a16049aef73d2df65c17b9bd Mon Sep 17 00:00:00 2001
From: Rajesh Borundia <rajesh.borundia@qlogic.com>
Date: Tue, 8 Mar 2016 02:39:58 -0500
Subject: [PATCH 09/40] qlcnic: Fix mailbox completion handling during spurious
 interrupt

[ Upstream commit 819bfe764dceec2f6b4551768453f374b4c60443 ]

o While the driver is in the middle of a MB completion processing
and it receives a spurious MB interrupt, it is mistaken as a good MB
completion interrupt leading to premature completion of the next MB
request. Fix the driver to guard against this by checking the current
state of MB processing and ignore the spurious interrupt.
Also added a stats counter to record this condition.

Signed-off-by: Rajesh Borundia <rajesh.borundia@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qlcnic/qlcnic.h         |  1 +
 drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c | 15 +++++++++++----
 drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c |  3 ++-
 3 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
index d18667b..55007f1 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
@@ -566,6 +566,7 @@ struct qlcnic_adapter_stats {
 	u64  tx_dma_map_error;
 	u64  spurious_intr;
 	u64  mac_filter_limit_overrun;
+	u64  mbx_spurious_intr;
 };
 
 /*
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
index e3d1bb7..f9640d5ce 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
@@ -2338,9 +2338,9 @@ static void qlcnic_83xx_handle_link_aen(struct qlcnic_adapter *adapter,
 
 static irqreturn_t qlcnic_83xx_handle_aen(int irq, void *data)
 {
+	u32 mask, resp, event, rsp_status = QLC_83XX_MBX_RESPONSE_ARRIVED;
 	struct qlcnic_adapter *adapter = data;
 	struct qlcnic_mailbox *mbx;
-	u32 mask, resp, event;
 	unsigned long flags;
 
 	mbx = adapter->ahw->mailbox;
@@ -2350,10 +2350,14 @@ static irqreturn_t qlcnic_83xx_handle_aen(int irq, void *data)
 		goto out;
 
 	event = readl(QLCNIC_MBX_FW(adapter->ahw, 0));
-	if (event &  QLCNIC_MBX_ASYNC_EVENT)
+	if (event &  QLCNIC_MBX_ASYNC_EVENT) {
 		__qlcnic_83xx_process_aen(adapter);
-	else
-		qlcnic_83xx_notify_mbx_response(mbx);
+	} else {
+		if (mbx->rsp_status != rsp_status)
+			qlcnic_83xx_notify_mbx_response(mbx);
+		else
+			adapter->stats.mbx_spurious_intr++;
+	}
 
 out:
 	mask = QLCRDX(adapter->ahw, QLCNIC_DEF_INT_MASK);
@@ -4053,6 +4057,7 @@ static void qlcnic_83xx_mailbox_worker(struct work_struct *work)
 	struct list_head *head = &mbx->cmd_q;
 	struct qlcnic_hardware_context *ahw;
 	struct qlcnic_cmd_args *cmd = NULL;
+	unsigned long flags;
 
 	ahw = adapter->ahw;
 
@@ -4062,7 +4067,9 @@ static void qlcnic_83xx_mailbox_worker(struct work_struct *work)
 			return;
 		}
 
+		spin_lock_irqsave(&mbx->aen_lock, flags);
 		mbx->rsp_status = QLC_83XX_MBX_RESPONSE_WAIT;
+		spin_unlock_irqrestore(&mbx->aen_lock, flags);
 
 		spin_lock(&mbx->queue_lock);
 
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
index 494e810..0a2318c 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
@@ -59,7 +59,8 @@ static const struct qlcnic_stats qlcnic_gstrings_stats[] = {
 	 QLC_OFF(stats.mac_filter_limit_overrun)},
 	{"spurious intr", QLC_SIZEOF(stats.spurious_intr),
 	 QLC_OFF(stats.spurious_intr)},
-
+	{"mbx spurious intr", QLC_SIZEOF(stats.mbx_spurious_intr),
+	 QLC_OFF(stats.mbx_spurious_intr)},
 };
 
 static const char qlcnic_device_gstrings_stats[][ETH_GSTRING_LEN] = {
-- 
2.1.0


From 99dc03ec465651678dc616be8c71f33b6b667e40 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Tue, 8 Mar 2016 15:18:54 -0500
Subject: [PATCH 10/40] macvtap: always pass ethernet header in linear

[ Upstream commit 8e2ad4113ce4671686740f808ff2795395c39eef ]

The stack expects link layer headers in the skb linear section.
Macvtap can create skbs with llheader in frags in edge cases:
when (IFF_VNET_HDR is off or vnet_hdr.hdr_len < ETH_HLEN) and
prepad + len > PAGE_SIZE and vnet_hdr.flags has no or bad csum.

Add checks to ensure linear is always at least ETH_HLEN.
At this point, len is already ensured to be >= ETH_HLEN.

For backwards compatiblity, rounds up short vnet_hdr.hdr_len.
This differs from tap and packet, which return an error.

Fixes b9fb9ee07e67 ("macvtap: add GSO/csum offload support")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macvtap.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index d636d05..95394ed 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -760,6 +760,8 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 			macvtap16_to_cpu(q, vnet_hdr.hdr_len) : GOODCOPY_LEN;
 		if (copylen > good_linear)
 			copylen = good_linear;
+		else if (copylen < ETH_HLEN)
+			copylen = ETH_HLEN;
 		linear = copylen;
 		i = *from;
 		iov_iter_advance(&i, copylen);
@@ -769,10 +771,11 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 
 	if (!zerocopy) {
 		copylen = len;
-		if (macvtap16_to_cpu(q, vnet_hdr.hdr_len) > good_linear)
+		linear = macvtap16_to_cpu(q, vnet_hdr.hdr_len);
+		if (linear > good_linear)
 			linear = good_linear;
-		else
-			linear = macvtap16_to_cpu(q, vnet_hdr.hdr_len);
+		else if (linear < ETH_HLEN)
+			linear = ETH_HLEN;
 	}
 
 	skb = macvtap_alloc_skb(&q->sk, MACVTAP_RESERVE, copylen,
-- 
2.1.0


From 0b535a2211090e26e91dca4333a280e22b6a220f Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Tue, 8 Mar 2016 12:59:33 -0800
Subject: [PATCH 11/40] mlxsw: spectrum: Check requested ageing time is valid

[ Upstream commit 869f63a4d28144c03c8f4a4c0d1e8f31f8c11a10 ]

Commit c62987bbd8a1 ("bridge: push bridge setting ageing_time down to
switchdev") added a check for minimum and maximum ageing time, but this
breaks existing behaviour where one can set ageing time to 0 for a
non-learning bridge.

Push this check down to the driver and allow the check in the bridge
layer to be removed. Currently ageing time 0 is refused by the driver,
but we can later add support for this functionality.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h           | 2 ++
 drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c | 9 +++++++--
 2 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 3b89ed2..65a115f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -118,6 +118,8 @@ struct mlxsw_sp {
 #define MLXSW_SP_DEFAULT_LEARNING_INTERVAL 100
 		unsigned int interval; /* ms */
 	} fdb_notify;
+#define MLXSW_SP_MIN_AGEING_TIME 10
+#define MLXSW_SP_MAX_AGEING_TIME 1000000
 #define MLXSW_SP_DEFAULT_AGEING_TIME 300
 	u32 ageing_time;
 	struct mlxsw_sp_upper master_bridge;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 7b56098..e1c74ef 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -311,8 +311,13 @@ static int mlxsw_sp_port_attr_br_ageing_set(struct mlxsw_sp_port *mlxsw_sp_port,
 	unsigned long ageing_jiffies = clock_t_to_jiffies(ageing_clock_t);
 	u32 ageing_time = jiffies_to_msecs(ageing_jiffies) / 1000;
 
-	if (switchdev_trans_ph_prepare(trans))
-		return 0;
+	if (switchdev_trans_ph_prepare(trans)) {
+		if (ageing_time < MLXSW_SP_MIN_AGEING_TIME ||
+		    ageing_time > MLXSW_SP_MAX_AGEING_TIME)
+			return -ERANGE;
+		else
+			return 0;
+	}
 
 	return mlxsw_sp_ageing_set(mlxsw_sp, ageing_time);
 }
-- 
2.1.0


From 1d1bb7d3e13f3d4345150a30462bee14f8fb83ae Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Tue, 8 Mar 2016 12:59:34 -0800
Subject: [PATCH 12/40] rocker: set FDB cleanup timer according to lowest
 ageing time

[ Upstream commit 88de1cd457e5cb664d6d437e2ea4750d089165f5 ]

In rocker, ageing time is a per-port attribute, so the next time the FDB
cleanup timer fires should be set according to the lowest ageing time.

This will later allow us to delete the BR_MIN_AGEING_TIME macro, which was
added to guarantee minimum ageing time in the bridge layer, thereby breaking
existing behavior.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/rocker/rocker.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c
index 166a7fc..f39e719 100644
--- a/drivers/net/ethernet/rocker/rocker.c
+++ b/drivers/net/ethernet/rocker/rocker.c
@@ -239,6 +239,7 @@ struct rocker {
 	struct {
 		u64 id;
 	} hw;
+	unsigned long ageing_time;
 	spinlock_t cmd_ring_lock;		/* for cmd ring accesses */
 	struct rocker_dma_ring_info cmd_ring;
 	struct rocker_dma_ring_info event_ring;
@@ -3704,7 +3705,7 @@ static void rocker_fdb_cleanup(unsigned long data)
 	struct rocker_port *rocker_port;
 	struct rocker_fdb_tbl_entry *entry;
 	struct hlist_node *tmp;
-	unsigned long next_timer = jiffies + BR_MIN_AGEING_TIME;
+	unsigned long next_timer = jiffies + rocker->ageing_time;
 	unsigned long expires;
 	unsigned long lock_flags;
 	int flags = ROCKER_OP_FLAG_NOWAIT | ROCKER_OP_FLAG_REMOVE |
@@ -4367,8 +4368,12 @@ static int rocker_port_bridge_ageing_time(struct rocker_port *rocker_port,
 					  struct switchdev_trans *trans,
 					  u32 ageing_time)
 {
+	struct rocker *rocker = rocker_port->rocker;
+
 	if (!switchdev_trans_ph_prepare(trans)) {
 		rocker_port->ageing_time = clock_t_to_jiffies(ageing_time);
+		if (rocker_port->ageing_time < rocker->ageing_time)
+			rocker->ageing_time = rocker_port->ageing_time;
 		mod_timer(&rocker_port->rocker->fdb_cleanup_timer, jiffies);
 	}
 
@@ -5206,10 +5211,13 @@ static int rocker_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto err_init_tbls;
 	}
 
+	rocker->ageing_time = BR_DEFAULT_AGEING_TIME;
 	setup_timer(&rocker->fdb_cleanup_timer, rocker_fdb_cleanup,
 		    (unsigned long) rocker);
 	mod_timer(&rocker->fdb_cleanup_timer, jiffies);
 
+	rocker->ageing_time = BR_DEFAULT_AGEING_TIME;
+
 	err = rocker_probe_ports(rocker);
 	if (err) {
 		dev_err(&pdev->dev, "failed to probe ports\n");
-- 
2.1.0


From d5e5c4ceb02be87c2e6ee07eddbef14fd17d5a02 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <shemming@brocade.com>
Date: Tue, 8 Mar 2016 12:59:35 -0800
Subject: [PATCH 13/40] bridge: allow zero ageing time

[ Upstream commit 4c656c13b254d598e83e586b7b4d36a2043dad85 ]

This fixes a regression in the bridge ageing time caused by:
commit c62987bbd8a1 ("bridge: push bridge setting ageing_time down to switchdev")

There are users of Linux bridge which use the feature that if ageing time
is set to 0 it causes entries to never expire. See:
  https://www.linuxfoundation.org/collaborate/workgroups/networking/bridge

For a pure software bridge, it is unnecessary for the code to have
arbitrary restrictions on what values are allowable.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_bridge.h |  4 ----
 net/bridge/br_stp.c       | 11 ++++++++---
 2 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
index a338a688..dcb89e3 100644
--- a/include/linux/if_bridge.h
+++ b/include/linux/if_bridge.h
@@ -46,10 +46,6 @@ struct br_ip_list {
 #define BR_LEARNING_SYNC	BIT(9)
 #define BR_PROXYARP_WIFI	BIT(10)
 
-/* values as per ieee8021QBridgeFdbAgingTime */
-#define BR_MIN_AGEING_TIME	(10 * HZ)
-#define BR_MAX_AGEING_TIME	(1000000 * HZ)
-
 #define BR_DEFAULT_AGEING_TIME	(300 * HZ)
 
 extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __user *));
diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c
index b3cca12..8b5898a 100644
--- a/net/bridge/br_stp.c
+++ b/net/bridge/br_stp.c
@@ -568,6 +568,14 @@ int br_set_max_age(struct net_bridge *br, unsigned long val)
 
 }
 
+/* Set time interval that dynamic forwarding entries live
+ * For pure software bridge, allow values outside the 802.1
+ * standard specification for special cases:
+ *  0 - entry never ages (all permanant)
+ *  1 - entry disappears (no persistance)
+ *
+ * Offloaded switch entries maybe more restrictive
+ */
 int br_set_ageing_time(struct net_bridge *br, u32 ageing_time)
 {
 	struct switchdev_attr attr = {
@@ -579,9 +587,6 @@ int br_set_ageing_time(struct net_bridge *br, u32 ageing_time)
 	unsigned long t = clock_t_to_jiffies(ageing_time);
 	int err;
 
-	if (t < BR_MIN_AGEING_TIME || t > BR_MAX_AGEING_TIME)
-		return -ERANGE;
-
 	err = switchdev_port_attr_set(br->dev, &attr);
 	if (err)
 		return err;
-- 
2.1.0


From e51c1f052b8d440bb637ef459c54612fb107d0a5 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sun, 13 Mar 2016 23:28:00 -0400
Subject: [PATCH 14/40] ipv4: Don't do expensive useless work during inetdev
 destroy.

[ Upstream commit fbd40ea0180a2d328c5adc61414dc8bab9335ce2 ]

When an inetdev is destroyed, every address assigned to the interface
is removed.  And in this scenerio we do two pointless things which can
be very expensive if the number of assigned interfaces is large:

1) Address promotion.  We are deleting all addresses, so there is no
   point in doing this.

2) A full nf conntrack table purge for every address.  We only need to
   do this once, as is already caught by the existing
   masq_dev_notifier so masq_inet_event() can skip this.

Reported-by: Solar Designer <solar@openwall.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Tested-by: Cyrill Gorcunov <gorcunov@openvz.org>
---
 net/ipv4/devinet.c                          |  4 ++++
 net/ipv4/fib_frontend.c                     |  4 ++++
 net/ipv4/netfilter/nf_nat_masquerade_ipv4.c | 12 ++++++++++--
 3 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index f6303b1..0212591 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -334,6 +334,9 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
 
 	ASSERT_RTNL();
 
+	if (in_dev->dead)
+		goto no_promotions;
+
 	/* 1. Deleting primary ifaddr forces deletion all secondaries
 	 * unless alias promotion is set
 	 **/
@@ -380,6 +383,7 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
 			fib_del_ifaddr(ifa, ifa1);
 	}
 
+no_promotions:
 	/* 2. Unlink it */
 
 	*ifap = ifa1->ifa_next;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 4734475..21add55 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -922,6 +922,9 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim)
 		subnet = 1;
 	}
 
+	if (in_dev->dead)
+		goto no_promotions;
+
 	/* Deletion is more complicated than add.
 	 * We should take care of not to delete too much :-)
 	 *
@@ -997,6 +1000,7 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim)
 		}
 	}
 
+no_promotions:
 	if (!(ok & BRD_OK))
 		fib_magic(RTM_DELROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim);
 	if (subnet && ifa->ifa_prefixlen < 31) {
diff --git a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
index c6eb421..ea91058 100644
--- a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
@@ -108,10 +108,18 @@ static int masq_inet_event(struct notifier_block *this,
 			   unsigned long event,
 			   void *ptr)
 {
-	struct net_device *dev = ((struct in_ifaddr *)ptr)->ifa_dev->dev;
+	struct in_device *idev = ((struct in_ifaddr *)ptr)->ifa_dev;
 	struct netdev_notifier_info info;
 
-	netdev_notifier_info_init(&info, dev);
+	/* The masq_dev_notifier will catch the case of the device going
+	 * down.  So if the inetdev is dead and being destroyed we have
+	 * no work to do.  Otherwise this is an individual address removal
+	 * and we have to perform the flush.
+	 */
+	if (idev->dead)
+		return NOTIFY_DONE;
+
+	netdev_notifier_info_init(&info, idev->dev);
 	return masq_device_event(this, event, &info);
 }
 
-- 
2.1.0


From 5b7ea86c02820216a3ba565ea6a9260cd8d35da2 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 14 Mar 2016 09:56:35 -0300
Subject: [PATCH 15/40] net: Fix use after free in the recvmmsg exit path

[ Upstream commit 34b88a68f26a75e4fded796f1a49c40f82234b7d ]

The syzkaller fuzzer hit the following use-after-free:

  Call Trace:
   [<ffffffff8175ea0e>] __asan_report_load8_noabort+0x3e/0x40 mm/kasan/report.c:295
   [<ffffffff851cc31a>] __sys_recvmmsg+0x6fa/0x7f0 net/socket.c:2261
   [<     inline     >] SYSC_recvmmsg net/socket.c:2281
   [<ffffffff851cc57f>] SyS_recvmmsg+0x16f/0x180 net/socket.c:2270
   [<ffffffff86332bb6>] entry_SYSCALL_64_fastpath+0x16/0x7a
  arch/x86/entry/entry_64.S:185

And, as Dmitry rightly assessed, that is because we can drop the
reference and then touch it when the underlying recvmsg calls return
some packets and then hit an error, which will make recvmmsg to set
sock->sk->sk_err, oops, fix it.

Reported-and-Tested-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Kostya Serebryany <kcc@google.com>
Cc: Sasha Levin <sasha.levin@oracle.com>
Fixes: a2e2725541fa ("net: Introduce recvmmsg socket syscall")
http://lkml.kernel.org/r/20160122211644.GC2470@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/socket.c | 38 +++++++++++++++++++-------------------
 1 file changed, 19 insertions(+), 19 deletions(-)

diff --git a/net/socket.c b/net/socket.c
index c044d1e..db13ae8 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2240,31 +2240,31 @@ int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
 		cond_resched();
 	}
 
-out_put:
-	fput_light(sock->file, fput_needed);
-
 	if (err == 0)
-		return datagrams;
+		goto out_put;
 
-	if (datagrams != 0) {
+	if (datagrams == 0) {
+		datagrams = err;
+		goto out_put;
+	}
+
+	/*
+	 * We may return less entries than requested (vlen) if the
+	 * sock is non block and there aren't enough datagrams...
+	 */
+	if (err != -EAGAIN) {
 		/*
-		 * We may return less entries than requested (vlen) if the
-		 * sock is non block and there aren't enough datagrams...
+		 * ... or  if recvmsg returns an error after we
+		 * received some datagrams, where we record the
+		 * error to return on the next call or if the
+		 * app asks about it using getsockopt(SO_ERROR).
 		 */
-		if (err != -EAGAIN) {
-			/*
-			 * ... or  if recvmsg returns an error after we
-			 * received some datagrams, where we record the
-			 * error to return on the next call or if the
-			 * app asks about it using getsockopt(SO_ERROR).
-			 */
-			sock->sk->sk_err = -err;
-		}
-
-		return datagrams;
+		sock->sk->sk_err = -err;
 	}
+out_put:
+	fput_light(sock->file, fput_needed);
 
-	return err;
+	return datagrams;
 }
 
 SYSCALL_DEFINE5(recvmmsg, int, fd, struct mmsghdr __user *, mmsg,
-- 
2.1.0


From d3e28edb850434ceb8e327a9dea1edea7303084a Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 14 Mar 2016 15:18:34 +0100
Subject: [PATCH 16/40] mlx4: add missing braces in verify_qp_parameters

[ Upstream commit baefd7015cdb304ce6c94f9679d0486c71954766 ]

The implementation of QP paravirtualization back in linux-3.7 included
some code that looks very dubious, and gcc-6 has grown smart enough
to warn about it:

drivers/net/ethernet/mellanox/mlx4/resource_tracker.c: In function 'verify_qp_parameters':
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c:3154:5: error: statement is indented as if it were guarded by... [-Werror=misleading-indentation]
     if (optpar & MLX4_QP_OPTPAR_ALT_ADDR_PATH) {
     ^~
drivers/net/ethernet/mellanox/mlx4/resource_tracker.c:3144:4: note: ...this 'if' clause, but it is not
    if (slave != mlx4_master_func_num(dev))

>From looking at the context, I'm reasonably sure that the indentation
is correct but that it should have contained curly braces from the
start, as the update_gid() function in the same patch correctly does.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Fixes: 54679e148287 ("mlx4: Implement QP paravirtualization and maintain phys_pkey_cache for smp_snoop")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/resource_tracker.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 25ce1b0..cd9b2b2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -3141,7 +3141,7 @@ static int verify_qp_parameters(struct mlx4_dev *dev,
 		case QP_TRANS_RTS2RTS:
 		case QP_TRANS_SQD2SQD:
 		case QP_TRANS_SQD2RTS:
-			if (slave != mlx4_master_func_num(dev))
+			if (slave != mlx4_master_func_num(dev)) {
 				if (optpar & MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH) {
 					port = (qp_ctx->pri_path.sched_queue >> 6 & 1) + 1;
 					if (dev->caps.port_mask[port] != MLX4_PORT_TYPE_IB)
@@ -3160,6 +3160,7 @@ static int verify_qp_parameters(struct mlx4_dev *dev,
 					if (qp_ctx->alt_path.mgid_index >= num_gids)
 						return -EINVAL;
 				}
+			}
 			break;
 		default:
 			break;
-- 
2.1.0


From 5ac1554f66685aa520314b1b95cdd53392b23f3d Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 14 Mar 2016 15:18:35 +0100
Subject: [PATCH 17/40] farsync: fix off-by-one bug in fst_add_one

[ Upstream commit e725a66c0202b5f36c2f9d59d26a65c53bbf21f7 ]

gcc-6 finds an out of bounds access in the fst_add_one function
when calculating the end of the mmio area:

drivers/net/wan/farsync.c: In function 'fst_add_one':
drivers/net/wan/farsync.c:418:53: error: index 2 denotes an offset greater than size of 'u8[2][8192] {aka unsigned char[2][8192]}' [-Werror=array-bounds]
 #define BUF_OFFSET(X)   (BFM_BASE + offsetof(struct buf_window, X))
                                                     ^
include/linux/compiler-gcc.h:158:21: note: in definition of macro '__compiler_offsetof'
  __builtin_offsetof(a, b)
                     ^
drivers/net/wan/farsync.c:418:37: note: in expansion of macro 'offsetof'
 #define BUF_OFFSET(X)   (BFM_BASE + offsetof(struct buf_window, X))
                                     ^~~~~~~~
drivers/net/wan/farsync.c:2519:36: note: in expansion of macro 'BUF_OFFSET'
                                  + BUF_OFFSET ( txBuffer[i][NUM_TX_BUFFER][0]);
                                    ^~~~~~~~~~

The warning is correct, but not critical because this appears
to be a write-only variable that is set by each WAN driver but
never accessed afterwards.

I'm taking the minimal fix here, using the correct pointer by
pointing 'mem_end' to the last byte inside of the register area
as all other WAN drivers do, rather than the first byte outside of
it. An alternative would be to just remove the mem_end member
entirely.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wan/farsync.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wan/farsync.c b/drivers/net/wan/farsync.c
index 44541dbc..69b994f 100644
--- a/drivers/net/wan/farsync.c
+++ b/drivers/net/wan/farsync.c
@@ -2516,7 +2516,7 @@ fst_add_one(struct pci_dev *pdev, const struct pci_device_id *ent)
                 dev->mem_start   = card->phys_mem
                                  + BUF_OFFSET ( txBuffer[i][0][0]);
                 dev->mem_end     = card->phys_mem
-                                 + BUF_OFFSET ( txBuffer[i][NUM_TX_BUFFER][0]);
+                                 + BUF_OFFSET ( txBuffer[i][NUM_TX_BUFFER - 1][LEN_RX_BUFFER - 1]);
                 dev->base_addr   = card->pci_conf;
                 dev->irq         = card->irq;
 
-- 
2.1.0


From 78d30accfedec73d21a7d9dfb37834fa8aca570a Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 14 Mar 2016 15:18:36 +0100
Subject: [PATCH 18/40] ath9k: fix buffer overrun for ar9287

[ Upstream commit 83d6f1f15f8cce844b0a131cbc63e444620e48b5 ]

Code that was added back in 2.6.38 has an obvious overflow
when accessing a static array, and at the time it was added
only a code comment was put in front of it as a reminder
to have it reviewed properly.

This has not happened, but gcc-6 now points to the specific
overflow:

drivers/net/wireless/ath/ath9k/eeprom.c: In function 'ath9k_hw_get_gain_boundaries_pdadcs':
drivers/net/wireless/ath/ath9k/eeprom.c:483:44: error: array subscript is above array bounds [-Werror=array-bounds]
     maxPwrT4[i] = data_9287[idxL].pwrPdg[i][4];
                   ~~~~~~~~~~~~~~~~~~~~~~~~~^~~

It turns out that the correct array length exists in the local
'intercepts' variable of this function, so we can just use that
instead of hardcoding '4', so this patch changes all three
instances to use that variable. The other two instances were
already correct, but it's more consistent this way.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Fixes: 940cd2c12ebf ("ath9k_hw: merge the ar9287 version of ath9k_hw_get_gain_boundaries_pdadcs")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wireless/ath/ath9k/eeprom.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/eeprom.c b/drivers/net/wireless/ath/ath9k/eeprom.c
index 73fb423..a794157 100644
--- a/drivers/net/wireless/ath/ath9k/eeprom.c
+++ b/drivers/net/wireless/ath/ath9k/eeprom.c
@@ -477,10 +477,9 @@ void ath9k_hw_get_gain_boundaries_pdadcs(struct ath_hw *ah,
 
 	if (match) {
 		if (AR_SREV_9287(ah)) {
-			/* FIXME: array overrun? */
 			for (i = 0; i < numXpdGains; i++) {
 				minPwrT4[i] = data_9287[idxL].pwrPdg[i][0];
-				maxPwrT4[i] = data_9287[idxL].pwrPdg[i][4];
+				maxPwrT4[i] = data_9287[idxL].pwrPdg[i][intercepts - 1];
 				ath9k_hw_fill_vpd_table(minPwrT4[i], maxPwrT4[i],
 						data_9287[idxL].pwrPdg[i],
 						data_9287[idxL].vpdPdg[i],
@@ -490,7 +489,7 @@ void ath9k_hw_get_gain_boundaries_pdadcs(struct ath_hw *ah,
 		} else if (eeprom_4k) {
 			for (i = 0; i < numXpdGains; i++) {
 				minPwrT4[i] = data_4k[idxL].pwrPdg[i][0];
-				maxPwrT4[i] = data_4k[idxL].pwrPdg[i][4];
+				maxPwrT4[i] = data_4k[idxL].pwrPdg[i][intercepts - 1];
 				ath9k_hw_fill_vpd_table(minPwrT4[i], maxPwrT4[i],
 						data_4k[idxL].pwrPdg[i],
 						data_4k[idxL].vpdPdg[i],
@@ -500,7 +499,7 @@ void ath9k_hw_get_gain_boundaries_pdadcs(struct ath_hw *ah,
 		} else {
 			for (i = 0; i < numXpdGains; i++) {
 				minPwrT4[i] = data_def[idxL].pwrPdg[i][0];
-				maxPwrT4[i] = data_def[idxL].pwrPdg[i][4];
+				maxPwrT4[i] = data_def[idxL].pwrPdg[i][intercepts - 1];
 				ath9k_hw_fill_vpd_table(minPwrT4[i], maxPwrT4[i],
 						data_def[idxL].pwrPdg[i],
 						data_def[idxL].vpdPdg[i],
-- 
2.1.0


From e57848e853f6b0f021ec37c547e9f540511affe2 Mon Sep 17 00:00:00 2001
From: Gregory CLEMENT <gregory.clement@free-electrons.com>
Date: Sat, 12 Mar 2016 18:44:17 +0100
Subject: [PATCH 19/40] net: mvneta: Fix spinlock usage

[ Upstream commit 1c2722a975fdb8c90bc6ba8570b7fb62db4e2e9c ]

In the previous patch, the spinlock was not initialized. While it didn't
cause any trouble yet it could be a problem to use it uninitialized.

The most annoying part was the critical section protected by the spinlock
in mvneta_stop(). Some of the functions could sleep as pointed when
activated CONFIG_DEBUG_ATOMIC_SLEEP. Actually, in mvneta_stop() we only
need to protect the is_stopped flagged, indeed the code of the notifier
for CPU online is protected by the same spinlock, so when we get the
lock, the notifer work is done.

Reported-by: Patrick Uiterwijk <patrick@puiterwijk.org>
Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index b0ae69f..8dc7df2 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -3070,17 +3070,17 @@ static int mvneta_stop(struct net_device *dev)
 	struct mvneta_port *pp = netdev_priv(dev);
 
 	/* Inform that we are stopping so we don't want to setup the
-	 * driver for new CPUs in the notifiers
+	 * driver for new CPUs in the notifiers. The code of the
+	 * notifier for CPU online is protected by the same spinlock,
+	 * so when we get the lock, the notifer work is done.
 	 */
 	spin_lock(&pp->lock);
 	pp->is_stopped = true;
+	spin_unlock(&pp->lock);
+
 	mvneta_stop_dev(pp);
 	mvneta_mdio_remove(pp);
 	unregister_cpu_notifier(&pp->cpu_notifier);
-	/* Now that the notifier are unregistered, we can release le
-	 * lock
-	 */
-	spin_unlock(&pp->lock);
 	on_each_cpu(mvneta_percpu_disable, pp, true);
 	free_percpu_irq(dev->irq, pp->ports);
 	mvneta_cleanup_rxqs(pp);
@@ -3612,6 +3612,7 @@ static int mvneta_probe(struct platform_device *pdev)
 	dev->ethtool_ops = &mvneta_eth_tool_ops;
 
 	pp = netdev_priv(dev);
+	spin_lock_init(&pp->lock);
 	pp->phy_node = phy_node;
 	pp->phy_interface = phy_mode;
 
-- 
2.1.0


From c34311aa1385e43d966a157d546f11155ec3cfe1 Mon Sep 17 00:00:00 2001
From: Dmitri Epshtein <dima@marvell.com>
Date: Sat, 12 Mar 2016 18:44:18 +0100
Subject: [PATCH 20/40] net: mvneta: enable change MAC address when interface
 is up

[ Upstream commit 928b6519afeb2a5e2dc61154380b545ed66c476a ]

Function eth_prepare_mac_addr_change() is called as part of MAC
address change. This function check if interface is running.
To enable change MAC address when interface is running:
IFF_LIVE_ADDR_CHANGE flag must be set to dev->priv_flags field

Fixes: c5aff18204da ("net: mvneta: driver for Marvell Armada 370/XP
network unit")
Cc: stable@vger.kernel.org
Signed-off-by: Dmitri Epshtein <dima@marvell.com>
Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 8dc7df2..2ee05ce 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -3721,7 +3721,7 @@ static int mvneta_probe(struct platform_device *pdev)
 	dev->features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO;
 	dev->hw_features |= dev->features;
 	dev->vlan_features |= dev->features;
-	dev->priv_flags |= IFF_UNICAST_FLT;
+	dev->priv_flags |= IFF_UNICAST_FLT | IFF_LIVE_ADDR_CHANGE;
 	dev->gso_max_segs = MVNETA_MAX_TSO_SEGS;
 
 	err = register_netdev(dev);
-- 
2.1.0


From d37726c5ea6f0f3013ce93b0e3c8bc62b78a6f3f Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Mon, 14 Mar 2016 21:17:16 +0100
Subject: [PATCH 21/40] ppp: ensure file->private_data can't be overridden

[ Upstream commit e8e56ffd9d2973398b60ece1f1bebb8d67b4d032 ]

Locking ppp_mutex must be done before dereferencing file->private_data,
otherwise it could be modified before ppp_unattached_ioctl() takes the
lock. This could lead ppp_unattached_ioctl() to override ->private_data,
thus leaking reference to the ppp_file previously pointed to.

v2: lock all ppp_ioctl() instead of just checking private_data in
    ppp_unattached_ioctl(), to avoid ambiguous behaviour.

Fixes: f3ff8a4d80e8 ("ppp: push BKL down into the driver")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/ppp_generic.c | 31 +++++++++++++++++--------------
 1 file changed, 17 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index d61da9ec..8c8eedb 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -575,7 +575,7 @@ static int get_filter(void __user *arg, struct sock_filter **p)
 
 static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
-	struct ppp_file *pf = file->private_data;
+	struct ppp_file *pf;
 	struct ppp *ppp;
 	int err = -EFAULT, val, val2, i;
 	struct ppp_idle idle;
@@ -585,9 +585,14 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	void __user *argp = (void __user *)arg;
 	int __user *p = argp;
 
-	if (!pf)
-		return ppp_unattached_ioctl(current->nsproxy->net_ns,
-					pf, file, cmd, arg);
+	mutex_lock(&ppp_mutex);
+
+	pf = file->private_data;
+	if (!pf) {
+		err = ppp_unattached_ioctl(current->nsproxy->net_ns,
+					   pf, file, cmd, arg);
+		goto out;
+	}
 
 	if (cmd == PPPIOCDETACH) {
 		/*
@@ -602,7 +607,6 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		 * this fd and reopening /dev/ppp.
 		 */
 		err = -EINVAL;
-		mutex_lock(&ppp_mutex);
 		if (pf->kind == INTERFACE) {
 			ppp = PF_TO_PPP(pf);
 			rtnl_lock();
@@ -616,15 +620,13 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		} else
 			pr_warn("PPPIOCDETACH file->f_count=%ld\n",
 				atomic_long_read(&file->f_count));
-		mutex_unlock(&ppp_mutex);
-		return err;
+		goto out;
 	}
 
 	if (pf->kind == CHANNEL) {
 		struct channel *pch;
 		struct ppp_channel *chan;
 
-		mutex_lock(&ppp_mutex);
 		pch = PF_TO_CHANNEL(pf);
 
 		switch (cmd) {
@@ -646,17 +648,16 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 				err = chan->ops->ioctl(chan, cmd, arg);
 			up_read(&pch->chan_sem);
 		}
-		mutex_unlock(&ppp_mutex);
-		return err;
+		goto out;
 	}
 
 	if (pf->kind != INTERFACE) {
 		/* can't happen */
 		pr_err("PPP: not interface or channel??\n");
-		return -EINVAL;
+		err = -EINVAL;
+		goto out;
 	}
 
-	mutex_lock(&ppp_mutex);
 	ppp = PF_TO_PPP(pf);
 	switch (cmd) {
 	case PPPIOCSMRU:
@@ -831,7 +832,10 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	default:
 		err = -ENOTTY;
 	}
+
+out:
 	mutex_unlock(&ppp_mutex);
+
 	return err;
 }
 
@@ -844,7 +848,6 @@ static int ppp_unattached_ioctl(struct net *net, struct ppp_file *pf,
 	struct ppp_net *pn;
 	int __user *p = (int __user *)arg;
 
-	mutex_lock(&ppp_mutex);
 	switch (cmd) {
 	case PPPIOCNEWUNIT:
 		/* Create a new ppp unit */
@@ -894,7 +897,7 @@ static int ppp_unattached_ioctl(struct net *net, struct ppp_file *pf,
 	default:
 		err = -ENOTTY;
 	}
-	mutex_unlock(&ppp_mutex);
+
 	return err;
 }
 
-- 
2.1.0


From e4655f22f92ca89cfd7a925aeb6ed14d62682580 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 16 Mar 2016 22:52:15 -0700
Subject: [PATCH 22/40] tcp/dccp: remove obsolete WARN_ON() in icmp handlers

[ Upstream commit e316ea62e3203d524ff0239a40c56d3a39ad1b5c ]

Now SYN_RECV request sockets are installed in ehash table, an ICMP
handler can find a request socket while another cpu handles an incoming
packet transforming this SYN_RECV request socket into an ESTABLISHED
socket.

We need to remove the now obsolete WARN_ON(req->sk), since req->sk
is set when a new child is created and added into listener accept queue.

If this race happens, the ICMP will do nothing special.

Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Ben Lazarus <blazarus@google.com>
Reported-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ipv4.c     | 2 --
 net/ipv4/tcp_ipv4.c | 2 --
 2 files changed, 4 deletions(-)

diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 902d606..8be8f27 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -204,8 +204,6 @@ void dccp_req_err(struct sock *sk, u64 seq)
 	 * ICMPs are not backlogged, hence we cannot get an established
 	 * socket here.
 	 */
-	WARN_ON(req->sk);
-
 	if (!between48(seq, dccp_rsk(req)->dreq_iss, dccp_rsk(req)->dreq_gss)) {
 		NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
 	} else {
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 487ac67..a7b1a90 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -319,8 +319,6 @@ void tcp_req_err(struct sock *sk, u32 seq, bool abort)
 	/* ICMPs are not backlogged, hence we cannot get
 	 * an established socket here.
 	 */
-	WARN_ON(req->sk);
-
 	if (seq != tcp_rsk(req)->snt_isn) {
 		NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
 	} else if (abort) {
-- 
2.1.0


From 2ea31adf540c6a0402eabb1bc21fb39796b70123 Mon Sep 17 00:00:00 2001
From: Manish Chopra <manish.chopra@qlogic.com>
Date: Tue, 15 Mar 2016 07:13:45 -0400
Subject: [PATCH 23/40] qlge: Fix receive packets drop.

[ Upstream commit 2c9a266afefe137bff06bbe0fc48b4d3b3cb348c ]

When running small packets [length < 256 bytes] traffic, packets were
being dropped due to invalid data in those packets which were
delivered by the driver upto the stack. Using pci_dma_sync_single_for_cpu
ensures copying latest and updated data into skb from the receive buffer.

Signed-off-by: Sony Chacko <sony.chacko@qlogic.com>
Signed-off-by: Manish Chopra <manish.chopra@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qlge/qlge_main.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
index 9979764..b28e73e 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
@@ -1648,7 +1648,18 @@ static void ql_process_mac_rx_skb(struct ql_adapter *qdev,
 		return;
 	}
 	skb_reserve(new_skb, NET_IP_ALIGN);
+
+	pci_dma_sync_single_for_cpu(qdev->pdev,
+				    dma_unmap_addr(sbq_desc, mapaddr),
+				    dma_unmap_len(sbq_desc, maplen),
+				    PCI_DMA_FROMDEVICE);
+
 	memcpy(skb_put(new_skb, length), skb->data, length);
+
+	pci_dma_sync_single_for_device(qdev->pdev,
+				       dma_unmap_addr(sbq_desc, mapaddr),
+				       dma_unmap_len(sbq_desc, maplen),
+				       PCI_DMA_FROMDEVICE);
 	skb = new_skb;
 
 	/* Frame error, so drop the packet. */
-- 
2.1.0


From 85e29d1ffd559facb2fe87b7d63d766c1a131df3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 17 Mar 2016 11:57:06 -0700
Subject: [PATCH 24/40] net: bcmgenet: fix dma api length mismatch

[ Upstream commit eee577232203842b4dcadb7ab477a298479633ed ]

When un-mapping skb->data in __bcmgenet_tx_reclaim(),
we must use the length that was used in original dma_map_single(),
instead of skb->len that might be bigger (includes the frags)

We simply can store skb_len into tx_cb_ptr->dma_len and use it
at unmap time.

Fixes: 1c1008c793fa ("net: bcmgenet: add main driver file")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index d7e01a7..6746fd0 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -1197,7 +1197,7 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
 			dev->stats.tx_bytes += tx_cb_ptr->skb->len;
 			dma_unmap_single(&dev->dev,
 					 dma_unmap_addr(tx_cb_ptr, dma_addr),
-					 tx_cb_ptr->skb->len,
+					 dma_unmap_len(tx_cb_ptr, dma_len),
 					 DMA_TO_DEVICE);
 			bcmgenet_free_cb(tx_cb_ptr);
 		} else if (dma_unmap_addr(tx_cb_ptr, dma_addr)) {
@@ -1308,7 +1308,7 @@ static int bcmgenet_xmit_single(struct net_device *dev,
 	}
 
 	dma_unmap_addr_set(tx_cb_ptr, dma_addr, mapping);
-	dma_unmap_len_set(tx_cb_ptr, dma_len, skb->len);
+	dma_unmap_len_set(tx_cb_ptr, dma_len, skb_len);
 	length_status = (skb_len << DMA_BUFLENGTH_SHIFT) | dma_desc_flags |
 			(priv->hw_params->qtag_mask << DMA_TX_QTAG_SHIFT) |
 			DMA_TX_APPEND_CRC;
-- 
2.1.0


From ac06666da24fe556bb551d8163e97f7f37bccc94 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 17 Mar 2016 17:23:36 -0700
Subject: [PATCH 25/40] bonding: fix bond_get_stats()

[ Upstream commit fe30937b65354c7fec244caebbdaae68e28ca797 ]

bond_get_stats() can be called from rtnetlink (with RTNL held)
or from /proc/net/dev seq handler (with RCU held)

The logic added in commit 5f0c5f73e5ef ("bonding: make global bonding
stats more reliable") kind of assumed only one cpu could run there.

If multiple threads are reading /proc/net/dev, stats can be really
messed up after a while.

A second problem is that some fields are 32bit, so we need to properly
handle the wrap around problem.

Given that RTNL is not always held, we need to use
bond_for_each_slave_rcu().

Fixes: 5f0c5f73e5ef ("bonding: make global bonding stats more reliable")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Andy Gospodarek <gospo@cumulusnetworks.com>
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Cc: Veaceslav Falico <vfalico@gmail.com>
Reviewed-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 65 ++++++++++++++++++++++-------------------
 include/net/bonding.h           |  1 +
 2 files changed, 36 insertions(+), 30 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index b7f1a99..5ec8195 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3308,6 +3308,30 @@ static int bond_close(struct net_device *bond_dev)
 	return 0;
 }
 
+/* fold stats, assuming all rtnl_link_stats64 fields are u64, but
+ * that some drivers can provide 32bit values only.
+ */
+static void bond_fold_stats(struct rtnl_link_stats64 *_res,
+			    const struct rtnl_link_stats64 *_new,
+			    const struct rtnl_link_stats64 *_old)
+{
+	const u64 *new = (const u64 *)_new;
+	const u64 *old = (const u64 *)_old;
+	u64 *res = (u64 *)_res;
+	int i;
+
+	for (i = 0; i < sizeof(*_res) / sizeof(u64); i++) {
+		u64 nv = new[i];
+		u64 ov = old[i];
+
+		/* detects if this particular field is 32bit only */
+		if (((nv | ov) >> 32) == 0)
+			res[i] += (u32)nv - (u32)ov;
+		else
+			res[i] += nv - ov;
+	}
+}
+
 static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev,
 						struct rtnl_link_stats64 *stats)
 {
@@ -3316,43 +3340,23 @@ static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev,
 	struct list_head *iter;
 	struct slave *slave;
 
+	spin_lock(&bond->stats_lock);
 	memcpy(stats, &bond->bond_stats, sizeof(*stats));
 
-	bond_for_each_slave(bond, slave, iter) {
-		const struct rtnl_link_stats64 *sstats =
+	rcu_read_lock();
+	bond_for_each_slave_rcu(bond, slave, iter) {
+		const struct rtnl_link_stats64 *new =
 			dev_get_stats(slave->dev, &temp);
-		struct rtnl_link_stats64 *pstats = &slave->slave_stats;
-
-		stats->rx_packets +=  sstats->rx_packets - pstats->rx_packets;
-		stats->rx_bytes += sstats->rx_bytes - pstats->rx_bytes;
-		stats->rx_errors += sstats->rx_errors - pstats->rx_errors;
-		stats->rx_dropped += sstats->rx_dropped - pstats->rx_dropped;
-
-		stats->tx_packets += sstats->tx_packets - pstats->tx_packets;;
-		stats->tx_bytes += sstats->tx_bytes - pstats->tx_bytes;
-		stats->tx_errors += sstats->tx_errors - pstats->tx_errors;
-		stats->tx_dropped += sstats->tx_dropped - pstats->tx_dropped;
-
-		stats->multicast += sstats->multicast - pstats->multicast;
-		stats->collisions += sstats->collisions - pstats->collisions;
-
-		stats->rx_length_errors += sstats->rx_length_errors - pstats->rx_length_errors;
-		stats->rx_over_errors += sstats->rx_over_errors - pstats->rx_over_errors;
-		stats->rx_crc_errors += sstats->rx_crc_errors - pstats->rx_crc_errors;
-		stats->rx_frame_errors += sstats->rx_frame_errors - pstats->rx_frame_errors;
-		stats->rx_fifo_errors += sstats->rx_fifo_errors - pstats->rx_fifo_errors;
-		stats->rx_missed_errors += sstats->rx_missed_errors - pstats->rx_missed_errors;
-
-		stats->tx_aborted_errors += sstats->tx_aborted_errors - pstats->tx_aborted_errors;
-		stats->tx_carrier_errors += sstats->tx_carrier_errors - pstats->tx_carrier_errors;
-		stats->tx_fifo_errors += sstats->tx_fifo_errors - pstats->tx_fifo_errors;
-		stats->tx_heartbeat_errors += sstats->tx_heartbeat_errors - pstats->tx_heartbeat_errors;
-		stats->tx_window_errors += sstats->tx_window_errors - pstats->tx_window_errors;
+
+		bond_fold_stats(stats, new, &slave->slave_stats);
 
 		/* save off the slave stats for the next run */
-		memcpy(pstats, sstats, sizeof(*sstats));
+		memcpy(&slave->slave_stats, new, sizeof(*new));
 	}
+	rcu_read_unlock();
+
 	memcpy(&bond->bond_stats, stats, sizeof(*stats));
+	spin_unlock(&bond->stats_lock);
 
 	return stats;
 }
@@ -4166,6 +4170,7 @@ void bond_setup(struct net_device *bond_dev)
 	struct bonding *bond = netdev_priv(bond_dev);
 
 	spin_lock_init(&bond->mode_lock);
+	spin_lock_init(&bond->stats_lock);
 	bond->params = bonding_defaults;
 
 	/* Initialize pointers */
diff --git a/include/net/bonding.h b/include/net/bonding.h
index ee6c520..791800d 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -215,6 +215,7 @@ struct bonding {
 	 * ALB mode (6) - to sync the use and modifications of its hash table
 	 */
 	spinlock_t mode_lock;
+	spinlock_t stats_lock;
 	u8	 send_peer_notif;
 	u8       igmp_retrans;
 #ifdef CONFIG_PROC_FS
-- 
2.1.0


From fbfba94effed131b4ca7458416e198fae4dcf778 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 22 Mar 2016 09:19:38 +0100
Subject: [PATCH 26/40] ipv4: fix broadcast packets reception

[ Upstream commit ad0ea1989cc4d5905941d0a9e62c63ad6d859cef ]

Currently, ingress ipv4 broadcast datagrams are dropped since,
in udp_v4_early_demux(), ip_check_mc_rcu() is invoked even on
bcast packets.

This patch addresses the issue, invoking ip_check_mc_rcu()
only for mcast packets.

Fixes: 6e5403093261 ("ipv4/udp: Verify multicast group is ours in upd_v4_early_demux()")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 95d2f19..eb8933b 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2082,10 +2082,14 @@ void udp_v4_early_demux(struct sk_buff *skb)
 		if (!in_dev)
 			return;
 
-		ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr,
-				       iph->protocol);
-		if (!ours)
-			return;
+		/* we are supposed to accept bcast packets */
+		if (skb->pkt_type == PACKET_MULTICAST) {
+			ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr,
+					       iph->protocol);
+			if (!ours)
+				return;
+		}
+
 		sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr,
 						   uh->source, iph->saddr, dif);
 	} else if (skb->pkt_type == PACKET_HOST) {
-- 
2.1.0


From d42bc3e0e870023844bf7390eee963917e8c9ac9 Mon Sep 17 00:00:00 2001
From: Lance Richardson <lrichard@redhat.com>
Date: Tue, 22 Mar 2016 14:56:57 -0400
Subject: [PATCH 27/40] ipv4: initialize flowi4_flags before calling
 fib_lookup()

[ Upstream commit 4cfc86f3dae6ca38ed49cdd78f458a03d4d87992 ]

Field fl4.flowi4_flags is not initialized in fib_compute_spec_dst()
before calling fib_lookup(), which means fib_table_lookup() is
using non-deterministic data at this line:

	if (!(flp->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF)) {

Fix by initializing the entire fl4 structure, which will prevent
similar issues as fields are added in the future by ensuring that
all fields are initialized to zero unless explicitly initialized
to another value.

Fixes: 58189ca7b2741 ("net: Fix vti use case with oif in dst lookups")
Suggested-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: Lance Richardson <lrichard@redhat.com>
Acked-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_frontend.c | 16 +++++++---------
 1 file changed, 7 insertions(+), 9 deletions(-)

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 21add55..8a9246d 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -280,7 +280,6 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb)
 	struct in_device *in_dev;
 	struct fib_result res;
 	struct rtable *rt;
-	struct flowi4 fl4;
 	struct net *net;
 	int scope;
 
@@ -296,14 +295,13 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb)
 
 	scope = RT_SCOPE_UNIVERSE;
 	if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) {
-		fl4.flowi4_oif = 0;
-		fl4.flowi4_iif = LOOPBACK_IFINDEX;
-		fl4.daddr = ip_hdr(skb)->saddr;
-		fl4.saddr = 0;
-		fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);
-		fl4.flowi4_scope = scope;
-		fl4.flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0;
-		fl4.flowi4_tun_key.tun_id = 0;
+		struct flowi4 fl4 = {
+			.flowi4_iif = LOOPBACK_IFINDEX,
+			.daddr = ip_hdr(skb)->saddr,
+			.flowi4_tos = RT_TOS(ip_hdr(skb)->tos),
+			.flowi4_scope = scope,
+			.flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0,
+		};
 		if (!fib_lookup(net, &fl4, &res, 0))
 			return FIB_RES_PREFSRC(net, res);
 	} else {
-- 
2.1.0


From 38d17b690b8ed1606c4c568a9e6d03a8e41c2058 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Wed, 23 Mar 2016 16:38:55 +0100
Subject: [PATCH 28/40] ppp: take reference on channels netns

[ Upstream commit 1f461dcdd296eecedaffffc6bae2bfa90bd7eb89 ]

Let channels hold a reference on their network namespace.
Some channel types, like ppp_async and ppp_synctty, can have their
userspace controller running in a different namespace. Therefore they
can't rely on them to preclude their netns from being removed from
under them.

==================================================================
BUG: KASAN: use-after-free in ppp_unregister_channel+0x372/0x3a0 at
addr ffff880064e217e0
Read of size 8 by task syz-executor/11581
=============================================================================
BUG net_namespace (Not tainted): kasan: bad access detected
-----------------------------------------------------------------------------

Disabling lock debugging due to kernel taint
INFO: Allocated in copy_net_ns+0x6b/0x1a0 age=92569 cpu=3 pid=6906
[<      none      >] ___slab_alloc+0x4c7/0x500 kernel/mm/slub.c:2440
[<      none      >] __slab_alloc+0x4c/0x90 kernel/mm/slub.c:2469
[<     inline     >] slab_alloc_node kernel/mm/slub.c:2532
[<     inline     >] slab_alloc kernel/mm/slub.c:2574
[<      none      >] kmem_cache_alloc+0x23a/0x2b0 kernel/mm/slub.c:2579
[<     inline     >] kmem_cache_zalloc kernel/include/linux/slab.h:597
[<     inline     >] net_alloc kernel/net/core/net_namespace.c:325
[<      none      >] copy_net_ns+0x6b/0x1a0 kernel/net/core/net_namespace.c:360
[<      none      >] create_new_namespaces+0x2f6/0x610 kernel/kernel/nsproxy.c:95
[<      none      >] copy_namespaces+0x297/0x320 kernel/kernel/nsproxy.c:150
[<      none      >] copy_process.part.35+0x1bf4/0x5760 kernel/kernel/fork.c:1451
[<     inline     >] copy_process kernel/kernel/fork.c:1274
[<      none      >] _do_fork+0x1bc/0xcb0 kernel/kernel/fork.c:1723
[<     inline     >] SYSC_clone kernel/kernel/fork.c:1832
[<      none      >] SyS_clone+0x37/0x50 kernel/kernel/fork.c:1826
[<      none      >] entry_SYSCALL_64_fastpath+0x16/0x7a kernel/arch/x86/entry/entry_64.S:185

INFO: Freed in net_drop_ns+0x67/0x80 age=575 cpu=2 pid=2631
[<      none      >] __slab_free+0x1fc/0x320 kernel/mm/slub.c:2650
[<     inline     >] slab_free kernel/mm/slub.c:2805
[<      none      >] kmem_cache_free+0x2a0/0x330 kernel/mm/slub.c:2814
[<     inline     >] net_free kernel/net/core/net_namespace.c:341
[<      none      >] net_drop_ns+0x67/0x80 kernel/net/core/net_namespace.c:348
[<      none      >] cleanup_net+0x4e5/0x600 kernel/net/core/net_namespace.c:448
[<      none      >] process_one_work+0x794/0x1440 kernel/kernel/workqueue.c:2036
[<      none      >] worker_thread+0xdb/0xfc0 kernel/kernel/workqueue.c:2170
[<      none      >] kthread+0x23f/0x2d0 kernel/drivers/block/aoe/aoecmd.c:1303
[<      none      >] ret_from_fork+0x3f/0x70 kernel/arch/x86/entry/entry_64.S:468
INFO: Slab 0xffffea0001938800 objects=3 used=0 fp=0xffff880064e20000
flags=0x5fffc0000004080
INFO: Object 0xffff880064e20000 @offset=0 fp=0xffff880064e24200

CPU: 1 PID: 11581 Comm: syz-executor Tainted: G    B           4.4.0+
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS
rel-1.8.2-0-g33fbe13 by qemu-project.org 04/01/2014
 00000000ffffffff ffff8800662c7790 ffffffff8292049d ffff88003e36a300
 ffff880064e20000 ffff880064e20000 ffff8800662c77c0 ffffffff816f2054
 ffff88003e36a300 ffffea0001938800 ffff880064e20000 0000000000000000
Call Trace:
 [<     inline     >] __dump_stack kernel/lib/dump_stack.c:15
 [<ffffffff8292049d>] dump_stack+0x6f/0xa2 kernel/lib/dump_stack.c:50
 [<ffffffff816f2054>] print_trailer+0xf4/0x150 kernel/mm/slub.c:654
 [<ffffffff816f875f>] object_err+0x2f/0x40 kernel/mm/slub.c:661
 [<     inline     >] print_address_description kernel/mm/kasan/report.c:138
 [<ffffffff816fb0c5>] kasan_report_error+0x215/0x530 kernel/mm/kasan/report.c:236
 [<     inline     >] kasan_report kernel/mm/kasan/report.c:259
 [<ffffffff816fb4de>] __asan_report_load8_noabort+0x3e/0x40 kernel/mm/kasan/report.c:280
 [<     inline     >] ? ppp_pernet kernel/include/linux/compiler.h:218
 [<ffffffff83ad71b2>] ? ppp_unregister_channel+0x372/0x3a0 kernel/drivers/net/ppp/ppp_generic.c:2392
 [<     inline     >] ppp_pernet kernel/include/linux/compiler.h:218
 [<ffffffff83ad71b2>] ppp_unregister_channel+0x372/0x3a0 kernel/drivers/net/ppp/ppp_generic.c:2392
 [<     inline     >] ? ppp_pernet kernel/drivers/net/ppp/ppp_generic.c:293
 [<ffffffff83ad6f26>] ? ppp_unregister_channel+0xe6/0x3a0 kernel/drivers/net/ppp/ppp_generic.c:2392
 [<ffffffff83ae18f3>] ppp_asynctty_close+0xa3/0x130 kernel/drivers/net/ppp/ppp_async.c:241
 [<ffffffff83ae1850>] ? async_lcp_peek+0x5b0/0x5b0 kernel/drivers/net/ppp/ppp_async.c:1000
 [<ffffffff82c33239>] tty_ldisc_close.isra.1+0x99/0xe0 kernel/drivers/tty/tty_ldisc.c:478
 [<ffffffff82c332c0>] tty_ldisc_kill+0x40/0x170 kernel/drivers/tty/tty_ldisc.c:744
 [<ffffffff82c34943>] tty_ldisc_release+0x1b3/0x260 kernel/drivers/tty/tty_ldisc.c:772
 [<ffffffff82c1ef21>] tty_release+0xac1/0x13e0 kernel/drivers/tty/tty_io.c:1901
 [<ffffffff82c1e460>] ? release_tty+0x320/0x320 kernel/drivers/tty/tty_io.c:1688
 [<ffffffff8174de36>] __fput+0x236/0x780 kernel/fs/file_table.c:208
 [<ffffffff8174e405>] ____fput+0x15/0x20 kernel/fs/file_table.c:244
 [<ffffffff813595ab>] task_work_run+0x16b/0x200 kernel/kernel/task_work.c:115
 [<     inline     >] exit_task_work kernel/include/linux/task_work.h:21
 [<ffffffff81307105>] do_exit+0x8b5/0x2c60 kernel/kernel/exit.c:750
 [<ffffffff813fdd20>] ? debug_check_no_locks_freed+0x290/0x290 kernel/kernel/locking/lockdep.c:4123
 [<ffffffff81306850>] ? mm_update_next_owner+0x6f0/0x6f0 kernel/kernel/exit.c:357
 [<ffffffff813215e6>] ? __dequeue_signal+0x136/0x470 kernel/kernel/signal.c:550
 [<ffffffff8132067b>] ? recalc_sigpending_tsk+0x13b/0x180 kernel/kernel/signal.c:145
 [<ffffffff81309628>] do_group_exit+0x108/0x330 kernel/kernel/exit.c:880
 [<ffffffff8132b9d4>] get_signal+0x5e4/0x14f0 kernel/kernel/signal.c:2307
 [<     inline     >] ? kretprobe_table_lock kernel/kernel/kprobes.c:1113
 [<ffffffff8151d355>] ? kprobe_flush_task+0xb5/0x450 kernel/kernel/kprobes.c:1158
 [<ffffffff8115f7d3>] do_signal+0x83/0x1c90 kernel/arch/x86/kernel/signal.c:712
 [<ffffffff8151d2a0>] ? recycle_rp_inst+0x310/0x310 kernel/include/linux/list.h:655
 [<ffffffff8115f750>] ? setup_sigcontext+0x780/0x780 kernel/arch/x86/kernel/signal.c:165
 [<ffffffff81380864>] ? finish_task_switch+0x424/0x5f0 kernel/kernel/sched/core.c:2692
 [<     inline     >] ? finish_lock_switch kernel/kernel/sched/sched.h:1099
 [<ffffffff81380560>] ? finish_task_switch+0x120/0x5f0 kernel/kernel/sched/core.c:2678
 [<     inline     >] ? context_switch kernel/kernel/sched/core.c:2807
 [<ffffffff85d794e9>] ? __schedule+0x919/0x1bd0 kernel/kernel/sched/core.c:3283
 [<ffffffff81003901>] exit_to_usermode_loop+0xf1/0x1a0 kernel/arch/x86/entry/common.c:247
 [<     inline     >] prepare_exit_to_usermode kernel/arch/x86/entry/common.c:282
 [<ffffffff810062ef>] syscall_return_slowpath+0x19f/0x210 kernel/arch/x86/entry/common.c:344
 [<ffffffff85d88022>] int_ret_from_sys_call+0x25/0x9f kernel/arch/x86/entry/entry_64.S:281
Memory state around the buggy address:
 ffff880064e21680: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff880064e21700: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff880064e21780: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                                                       ^
 ffff880064e21800: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff880064e21880: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
==================================================================

Fixes: 273ec51dd7ce ("net: ppp_generic - introduce net-namespace functionality v2")
Reported-by: Baozeng Ding <sploving1@gmail.com>
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Reviewed-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/ppp_generic.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 8c8eedb..aafe237 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -2307,7 +2307,7 @@ int ppp_register_net_channel(struct net *net, struct ppp_channel *chan)
 
 	pch->ppp = NULL;
 	pch->chan = chan;
-	pch->chan_net = net;
+	pch->chan_net = get_net(net);
 	chan->ppp = pch;
 	init_ppp_file(&pch->file, CHANNEL);
 	pch->file.hdrlen = chan->hdrlen;
@@ -2404,6 +2404,8 @@ ppp_unregister_channel(struct ppp_channel *chan)
 	spin_lock_bh(&pn->all_channels_lock);
 	list_del(&pch->list);
 	spin_unlock_bh(&pn->all_channels_lock);
+	put_net(pch->chan_net);
+	pch->chan_net = NULL;
 
 	pch->file.dead = 1;
 	wake_up_interruptible(&pch->file.rwait);
-- 
2.1.0


From e818add1673cf3144ac607169e2c0e181c1476a8 Mon Sep 17 00:00:00 2001
From: "subashab@codeaurora.org" <subashab@codeaurora.org>
Date: Wed, 23 Mar 2016 22:39:50 -0600
Subject: [PATCH 29/40] xfrm: Fix crash observed during device unregistration
 and decryption

[ Upstream commit 071d36bf21bcc837be00cea55bcef8d129e7f609 ]

A crash is observed when a decrypted packet is processed in receive
path. get_rps_cpus() tries to dereference the skb->dev fields but it
appears that the device is freed from the poison pattern.

[<ffffffc000af58ec>] get_rps_cpu+0x94/0x2f0
[<ffffffc000af5f94>] netif_rx_internal+0x140/0x1cc
[<ffffffc000af6094>] netif_rx+0x74/0x94
[<ffffffc000bc0b6c>] xfrm_input+0x754/0x7d0
[<ffffffc000bc0bf8>] xfrm_input_resume+0x10/0x1c
[<ffffffc000ba6eb8>] esp_input_done+0x20/0x30
[<ffffffc0000b64c8>] process_one_work+0x244/0x3fc
[<ffffffc0000b7324>] worker_thread+0x2f8/0x418
[<ffffffc0000bb40c>] kthread+0xe0/0xec

-013|get_rps_cpu(
     |    dev = 0xFFFFFFC08B688000,
     |    skb = 0xFFFFFFC0C76AAC00 -> (
     |      dev = 0xFFFFFFC08B688000 -> (
     |        name =
"......................................................
     |        name_hlist = (next = 0xAAAAAAAAAAAAAAAA, pprev =
0xAAAAAAAAAAA

Following are the sequence of events observed -

- Encrypted packet in receive path from netdevice is queued
- Encrypted packet queued for decryption (asynchronous)
- Netdevice brought down and freed
- Packet is decrypted and returned through callback in esp_input_done
- Packet is queued again for process in network stack using netif_rx

Since the device appears to have been freed, the dereference of
skb->dev in get_rps_cpus() leads to an unhandled page fault
exception.

Fix this by holding on to device reference when queueing packets
asynchronously and releasing the reference on call back return.

v2: Make the change generic to xfrm as mentioned by Steffen and
update the title to xfrm

Suggested-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Jerome Stanislaus <jeromes@codeaurora.org>
Signed-off-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/xfrm/xfrm_input.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index ad7f5b3..1c4ad47 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -292,12 +292,15 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 		XFRM_SKB_CB(skb)->seq.input.hi = seq_hi;
 
 		skb_dst_force(skb);
+		dev_hold(skb->dev);
 
 		nexthdr = x->type->input(x, skb);
 
 		if (nexthdr == -EINPROGRESS)
 			return 0;
 resume:
+		dev_put(skb->dev);
+
 		spin_lock(&x->lock);
 		if (nexthdr <= 0) {
 			if (nexthdr == -EBADMSG) {
-- 
2.1.0


From 3c5699597c51c5bbe70a224549e6fe85b51ecd11 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Mon, 28 Mar 2016 22:38:16 +0200
Subject: [PATCH 30/40] qmi_wwan: add "D-Link DWM-221 B1" device id
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit e84810c7b85a2d7897797b3ad3e879168a8e032a ]

Thomas reports:
"Windows:

00 diagnostics
01 modem
02 at-port
03 nmea
04 nic

Linux:

T:  Bus=02 Lev=01 Prnt=01 Port=03 Cnt=01 Dev#=  4 Spd=480 MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=2001 ProdID=7e19 Rev=02.32
S:  Manufacturer=Mobile Connect
S:  Product=Mobile Connect
S:  SerialNumber=0123456789ABCDEF
C:  #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
I:  If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
I:  If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
I:  If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
I:  If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
I:  If#= 5 Alt= 0 #EPs= 2 Cls=08(stor.) Sub=06 Prot=50 Driver=usb-storage"

Reported-by: Thomas Schäfer <tschaefer@t-online.de>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index a3a4ccf..1232a8c6 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -844,6 +844,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x19d2, 0x1426, 2)},	/* ZTE MF91 */
 	{QMI_FIXED_INTF(0x19d2, 0x1428, 2)},	/* Telewell TW-LTE 4G v2 */
 	{QMI_FIXED_INTF(0x19d2, 0x2002, 4)},	/* ZTE (Vodafone) K3765-Z */
+	{QMI_FIXED_INTF(0x2001, 0x7e19, 4)},	/* D-Link DWM-221 B1 */
 	{QMI_FIXED_INTF(0x0f3d, 0x68a2, 8)},    /* Sierra Wireless MC7700 */
 	{QMI_FIXED_INTF(0x114f, 0x68a2, 8)},    /* Sierra Wireless MC7750 */
 	{QMI_FIXED_INTF(0x1199, 0x68a2, 8)},	/* Sierra Wireless MC7710 in QMI mode */
-- 
2.1.0


From 06dacaed2c6b2246e5c81ec5c7a10fefd81fd96f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 29 Mar 2016 08:43:41 -0700
Subject: [PATCH 31/40] ipv6: udp: fix UDP_MIB_IGNOREDMULTI updates

[ Upstream commit 2d4212261fdf13e29728ddb5ea9d60c342cc92b5 ]

IPv6 counters updates use a different macro than IPv4.

Fixes: 36cbb2452cbaf ("udp: Increment UDP_MIB_IGNOREDMULTI for arriving unmatched multicasts")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Rick Jones <rick.jones2@hp.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/udp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 422dd01..6794120 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -883,8 +883,8 @@ start_lookup:
 		flush_stack(stack, count, skb, count - 1);
 	} else {
 		if (!inner_flushed)
-			UDP_INC_STATS_BH(net, UDP_MIB_IGNOREDMULTI,
-					 proto == IPPROTO_UDPLITE);
+			UDP6_INC_STATS_BH(net, UDP_MIB_IGNOREDMULTI,
+					  proto == IPPROTO_UDPLITE);
 		consume_skb(skb);
 	}
 	return 0;
-- 
2.1.0


From d7d708f20a8b36b96a9e2a502a25689fe38162bf Mon Sep 17 00:00:00 2001
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Tue, 29 Mar 2016 18:48:08 +0800
Subject: [PATCH 32/40] bridge: Allow set bridge ageing time when switchdev
 disabled

[ Upstream commit 5e263f712691615fb802f06c98d7638c378f5d11 ]

When NET_SWITCHDEV=n, switchdev_port_attr_set will return -EOPNOTSUPP,
we should ignore this error code and continue to set the ageing time.

Fixes: c62987bbd8a1 ("bridge: push bridge setting ageing_time down to switchdev")
Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Acked-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_stp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c
index 8b5898a..e2670c5 100644
--- a/net/bridge/br_stp.c
+++ b/net/bridge/br_stp.c
@@ -588,7 +588,7 @@ int br_set_ageing_time(struct net_bridge *br, u32 ageing_time)
 	int err;
 
 	err = switchdev_port_attr_set(br->dev, &attr);
-	if (err)
+	if (err && err != -EOPNOTSUPP)
 		return err;
 
 	br->ageing_time = t;
-- 
2.1.0


From 8dfe8bb5176ba36071ba7f563e153b74921207bd Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Thu, 31 Mar 2016 18:10:31 +0200
Subject: [PATCH 33/40] rtnl: fix msg size calculation in if_nlmsg_size()

[ Upstream commit c57c7a95da842807b475b823ed2e5435c42cb3b0 ]

Size of the attribute IFLA_PHYS_PORT_NAME was missing.

Fixes: db24a9044ee1 ("net: add support for phys_port_name")
CC: David Ahern <dsahern@gmail.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 8261d95..215e613 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -905,6 +905,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + rtnl_link_get_af_size(dev, ext_filter_mask) /* IFLA_AF_SPEC */
 	       + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_PORT_ID */
 	       + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_SWITCH_ID */
+	       + nla_total_size(IFNAMSIZ) /* IFLA_PHYS_PORT_NAME */
 	       + nla_total_size(1); /* IFLA_PROTO_DOWN */
 
 }
-- 
2.1.0


From bbbd63bdd231491993277de2debafc92d4d861ef Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 31 Mar 2016 02:13:18 +0200
Subject: [PATCH 34/40] tun, bpf: fix suspicious RCU usage in tun_{attach,
 detach}_filter

[ Upstream commit 5a5abb1fa3b05dd6aa821525832644c1e7d2905f ]

Sasha Levin reported a suspicious rcu_dereference_protected() warning
found while fuzzing with trinity that is similar to this one:

  [   52.765684] net/core/filter.c:2262 suspicious rcu_dereference_protected() usage!
  [   52.765688] other info that might help us debug this:
  [   52.765695] rcu_scheduler_active = 1, debug_locks = 1
  [   52.765701] 1 lock held by a.out/1525:
  [   52.765704]  #0:  (rtnl_mutex){+.+.+.}, at: [<ffffffff816a64b7>] rtnl_lock+0x17/0x20
  [   52.765721] stack backtrace:
  [   52.765728] CPU: 1 PID: 1525 Comm: a.out Not tainted 4.5.0+ #264
  [...]
  [   52.765768] Call Trace:
  [   52.765775]  [<ffffffff813e488d>] dump_stack+0x85/0xc8
  [   52.765784]  [<ffffffff810f2fa5>] lockdep_rcu_suspicious+0xd5/0x110
  [   52.765792]  [<ffffffff816afdc2>] sk_detach_filter+0x82/0x90
  [   52.765801]  [<ffffffffa0883425>] tun_detach_filter+0x35/0x90 [tun]
  [   52.765810]  [<ffffffffa0884ed4>] __tun_chr_ioctl+0x354/0x1130 [tun]
  [   52.765818]  [<ffffffff8136fed0>] ? selinux_file_ioctl+0x130/0x210
  [   52.765827]  [<ffffffffa0885ce3>] tun_chr_ioctl+0x13/0x20 [tun]
  [   52.765834]  [<ffffffff81260ea6>] do_vfs_ioctl+0x96/0x690
  [   52.765843]  [<ffffffff81364af3>] ? security_file_ioctl+0x43/0x60
  [   52.765850]  [<ffffffff81261519>] SyS_ioctl+0x79/0x90
  [   52.765858]  [<ffffffff81003ba2>] do_syscall_64+0x62/0x140
  [   52.765866]  [<ffffffff817d563f>] entry_SYSCALL64_slow_path+0x25/0x25

Same can be triggered with PROVE_RCU (+ PROVE_RCU_REPEATEDLY) enabled
from tun_attach_filter() when user space calls ioctl(tun_fd, TUN{ATTACH,
DETACH}FILTER, ...) for adding/removing a BPF filter on tap devices.

Since the fix in f91ff5b9ff52 ("net: sk_{detach|attach}_filter() rcu
fixes") sk_attach_filter()/sk_detach_filter() now dereferences the
filter with rcu_dereference_protected(), checking whether socket lock
is held in control path.

Since its introduction in 994051625981 ("tun: socket filter support"),
tap filters are managed under RTNL lock from __tun_chr_ioctl(). Thus the
sock_owned_by_user(sk) doesn't apply in this specific case and therefore
triggers the false positive.

Extend the BPF API with __sk_attach_filter()/__sk_detach_filter() pair
that is used by tap filters and pass in lockdep_rtnl_is_held() for the
rcu_dereference_protected() checks instead.

Reported-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c      |  8 +++++---
 include/linux/filter.h |  4 ++++
 net/core/filter.c      | 33 +++++++++++++++++++++------------
 3 files changed, 30 insertions(+), 15 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 88bb8cc..9131927 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -621,7 +621,8 @@ static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filte
 
 	/* Re-attach the filter to persist device */
 	if (!skip_filter && (tun->filter_attached == true)) {
-		err = sk_attach_filter(&tun->fprog, tfile->socket.sk);
+		err = __sk_attach_filter(&tun->fprog, tfile->socket.sk,
+					 lockdep_rtnl_is_held());
 		if (!err)
 			goto out;
 	}
@@ -1807,7 +1808,7 @@ static void tun_detach_filter(struct tun_struct *tun, int n)
 
 	for (i = 0; i < n; i++) {
 		tfile = rtnl_dereference(tun->tfiles[i]);
-		sk_detach_filter(tfile->socket.sk);
+		__sk_detach_filter(tfile->socket.sk, lockdep_rtnl_is_held());
 	}
 
 	tun->filter_attached = false;
@@ -1820,7 +1821,8 @@ static int tun_attach_filter(struct tun_struct *tun)
 
 	for (i = 0; i < tun->numqueues; i++) {
 		tfile = rtnl_dereference(tun->tfiles[i]);
-		ret = sk_attach_filter(&tun->fprog, tfile->socket.sk);
+		ret = __sk_attach_filter(&tun->fprog, tfile->socket.sk,
+					 lockdep_rtnl_is_held());
 		if (ret) {
 			tun_detach_filter(tun, i);
 			return ret;
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 43aa1f8..a51a536 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -465,10 +465,14 @@ int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog,
 void bpf_prog_destroy(struct bpf_prog *fp);
 
 int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk);
+int __sk_attach_filter(struct sock_fprog *fprog, struct sock *sk,
+		       bool locked);
 int sk_attach_bpf(u32 ufd, struct sock *sk);
 int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk);
 int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk);
 int sk_detach_filter(struct sock *sk);
+int __sk_detach_filter(struct sock *sk, bool locked);
+
 int sk_get_filter(struct sock *sk, struct sock_filter __user *filter,
 		  unsigned int len);
 
diff --git a/net/core/filter.c b/net/core/filter.c
index bba502f..fb2951c 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1147,7 +1147,8 @@ void bpf_prog_destroy(struct bpf_prog *fp)
 }
 EXPORT_SYMBOL_GPL(bpf_prog_destroy);
 
-static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk)
+static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk,
+			    bool locked)
 {
 	struct sk_filter *fp, *old_fp;
 
@@ -1163,10 +1164,8 @@ static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk)
 		return -ENOMEM;
 	}
 
-	old_fp = rcu_dereference_protected(sk->sk_filter,
-					   sock_owned_by_user(sk));
+	old_fp = rcu_dereference_protected(sk->sk_filter, locked);
 	rcu_assign_pointer(sk->sk_filter, fp);
-
 	if (old_fp)
 		sk_filter_uncharge(sk, old_fp);
 
@@ -1245,7 +1244,8 @@ struct bpf_prog *__get_filter(struct sock_fprog *fprog, struct sock *sk)
  * occurs or there is insufficient memory for the filter a negative
  * errno code is returned. On success the return is zero.
  */
-int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
+int __sk_attach_filter(struct sock_fprog *fprog, struct sock *sk,
+		       bool locked)
 {
 	struct bpf_prog *prog = __get_filter(fprog, sk);
 	int err;
@@ -1253,7 +1253,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 	if (IS_ERR(prog))
 		return PTR_ERR(prog);
 
-	err = __sk_attach_prog(prog, sk);
+	err = __sk_attach_prog(prog, sk, locked);
 	if (err < 0) {
 		__bpf_prog_release(prog);
 		return err;
@@ -1261,7 +1261,12 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(sk_attach_filter);
+EXPORT_SYMBOL_GPL(__sk_attach_filter);
+
+int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
+{
+	return __sk_attach_filter(fprog, sk, sock_owned_by_user(sk));
+}
 
 int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 {
@@ -1307,7 +1312,7 @@ int sk_attach_bpf(u32 ufd, struct sock *sk)
 	if (IS_ERR(prog))
 		return PTR_ERR(prog);
 
-	err = __sk_attach_prog(prog, sk);
+	err = __sk_attach_prog(prog, sk, sock_owned_by_user(sk));
 	if (err < 0) {
 		bpf_prog_put(prog);
 		return err;
@@ -2105,7 +2110,7 @@ static int __init register_sk_filter_ops(void)
 }
 late_initcall(register_sk_filter_ops);
 
-int sk_detach_filter(struct sock *sk)
+int __sk_detach_filter(struct sock *sk, bool locked)
 {
 	int ret = -ENOENT;
 	struct sk_filter *filter;
@@ -2113,8 +2118,7 @@ int sk_detach_filter(struct sock *sk)
 	if (sock_flag(sk, SOCK_FILTER_LOCKED))
 		return -EPERM;
 
-	filter = rcu_dereference_protected(sk->sk_filter,
-					   sock_owned_by_user(sk));
+	filter = rcu_dereference_protected(sk->sk_filter, locked);
 	if (filter) {
 		RCU_INIT_POINTER(sk->sk_filter, NULL);
 		sk_filter_uncharge(sk, filter);
@@ -2123,7 +2127,12 @@ int sk_detach_filter(struct sock *sk)
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(sk_detach_filter);
+EXPORT_SYMBOL_GPL(__sk_detach_filter);
+
+int sk_detach_filter(struct sock *sk)
+{
+	return __sk_detach_filter(sk, sock_owned_by_user(sk));
+}
 
 int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf,
 		  unsigned int len)
-- 
2.1.0


From ac88c6a08919f5143793c1282edab6efee83f572 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Fri, 8 Apr 2016 13:26:48 +0800
Subject: [PATCH 35/40] tuntap: restore default qdisc

[ Upstream commit 016adb7260f481168c03e09f785184d6d5278894 ]

After commit f84bb1eac027 ("net: fix IFF_NO_QUEUE for drivers using
alloc_netdev"), default qdisc was changed to noqueue because
tuntap does not set tx_queue_len during .setup(). This patch restores
default qdisc by setting tx_queue_len in tun_setup().

Fixes: f84bb1eac027 ("net: fix IFF_NO_QUEUE for drivers using alloc_netdev")
Cc: Phil Sutter <phil@nwl.cc>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 9131927..81ecc2e 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1001,7 +1001,6 @@ static void tun_net_init(struct net_device *dev)
 		/* Zero header length */
 		dev->type = ARPHRD_NONE;
 		dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST;
-		dev->tx_queue_len = TUN_READQ_SIZE;  /* We prefer our own queue length */
 		break;
 
 	case IFF_TAP:
@@ -1013,7 +1012,6 @@ static void tun_net_init(struct net_device *dev)
 
 		eth_hw_addr_random(dev);
 
-		dev->tx_queue_len = TUN_READQ_SIZE;  /* We prefer our own queue length */
 		break;
 	}
 }
@@ -1467,6 +1465,8 @@ static void tun_setup(struct net_device *dev)
 
 	dev->ethtool_ops = &tun_ethtool_ops;
 	dev->destructor = tun_free_netdev;
+	/* We prefer our own queue length */
+	dev->tx_queue_len = TUN_READQ_SIZE;
 }
 
 /* Trivial set of netlink ops to allow deleting tun or tap
-- 
2.1.0


From 944783d127c194622ae43c1b6badf3894c4c7eac Mon Sep 17 00:00:00 2001
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Sun, 3 Apr 2016 22:09:23 +0800
Subject: [PATCH 36/40] ipv4: l2tp: fix a potential issue in l2tp_ip_recv

[ Upstream commit 5745b8232e942abd5e16e85fa9b27cc21324acf0 ]

pskb_may_pull() can change skb->data, so we have to load ptr/optr at the
right place.

Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ip.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index ec22078..42de4cc 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -123,12 +123,11 @@ static int l2tp_ip_recv(struct sk_buff *skb)
 	struct l2tp_tunnel *tunnel = NULL;
 	int length;
 
-	/* Point to L2TP header */
-	optr = ptr = skb->data;
-
 	if (!pskb_may_pull(skb, 4))
 		goto discard;
 
+	/* Point to L2TP header */
+	optr = ptr = skb->data;
 	session_id = ntohl(*((__be32 *) ptr));
 	ptr += 4;
 
@@ -156,6 +155,9 @@ static int l2tp_ip_recv(struct sk_buff *skb)
 		if (!pskb_may_pull(skb, length))
 			goto discard;
 
+		/* Point to L2TP header */
+		optr = ptr = skb->data;
+		ptr += 4;
 		pr_debug("%s: ip recv\n", tunnel->name);
 		print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length);
 	}
-- 
2.1.0


From f261b3c9701897fc8203b5a4a206960a22ff66d1 Mon Sep 17 00:00:00 2001
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Sun, 3 Apr 2016 22:09:24 +0800
Subject: [PATCH 37/40] ipv6: l2tp: fix a potential issue in l2tp_ip6_recv

[ Upstream commit be447f305494e019dfc37ea4cdf3b0e4200b4eba ]

pskb_may_pull() can change skb->data, so we have to load ptr/optr at the
right place.

Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ip6.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index a2c8747..9ee4ddb 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -135,12 +135,11 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
 	struct l2tp_tunnel *tunnel = NULL;
 	int length;
 
-	/* Point to L2TP header */
-	optr = ptr = skb->data;
-
 	if (!pskb_may_pull(skb, 4))
 		goto discard;
 
+	/* Point to L2TP header */
+	optr = ptr = skb->data;
 	session_id = ntohl(*((__be32 *) ptr));
 	ptr += 4;
 
@@ -168,6 +167,9 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
 		if (!pskb_may_pull(skb, length))
 			goto discard;
 
+		/* Point to L2TP header */
+		optr = ptr = skb->data;
+		ptr += 4;
 		pr_debug("%s: ip recv\n", tunnel->name);
 		print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length);
 	}
-- 
2.1.0


From 749a5113eadbef431abd959f0eb0e4dd05ee3a47 Mon Sep 17 00:00:00 2001
From: Thadeu Lima de Souza Cascardo <cascardo@redhat.com>
Date: Fri, 1 Apr 2016 17:17:50 -0300
Subject: [PATCH 38/40] ip6_tunnel: set rtnl_link_ops before calling
 register_netdevice

[ Upstream commit b6ee376cb0b7fb4e7e07d6cd248bd40436fb9ba6 ]

When creating an ip6tnl tunnel with ip tunnel, rtnl_link_ops is not set
before ip6_tnl_create2 is called. When register_netdevice is called, there
is no linkinfo attribute in the NEWLINK message because of that.

Setting rtnl_link_ops before calling register_netdevice fixes that.

Fixes: 0b112457229d ("ip6tnl: add support of link creation via rtnl")
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@redhat.com>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 6c5dfec..3991b21 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -343,12 +343,12 @@ static int ip6_tnl_create2(struct net_device *dev)
 
 	t = netdev_priv(dev);
 
+	dev->rtnl_link_ops = &ip6_link_ops;
 	err = register_netdevice(dev);
 	if (err < 0)
 		goto out;
 
 	strcpy(t->parms.name, dev->name);
-	dev->rtnl_link_ops = &ip6_link_ops;
 
 	dev_hold(dev);
 	ip6_tnl_link(ip6n, t);
-- 
2.1.0


From 855a4c0b572e09ce011b2bf39b66863de5bf1360 Mon Sep 17 00:00:00 2001
From: Jakub Sitnicki <jkbs@redhat.com>
Date: Tue, 5 Apr 2016 18:41:08 +0200
Subject: [PATCH 39/40] ipv6: Count in extension headers in skb->network_header

[ Upstream commit 3ba3458fb9c050718b95275a3310b74415e767e2 ]

When sending a UDPv6 message longer than MTU, account for the length
of fragmentable IPv6 extension headers in skb->network_header offset.
Same as we do in alloc_new_skb path in __ip6_append_data().

This ensures that later on __ip6_make_skb() will make space in
headroom for fragmentable extension headers:

	/* move skb->data to ip header from ext header */
	if (skb->data < skb_network_header(skb))
		__skb_pull(skb, skb_network_offset(skb));

Prevents a splat due to skb_under_panic:

skbuff: skb_under_panic: text:ffffffff8143397b len:2126 put:14 \
head:ffff880005bacf50 data:ffff880005bacf4a tail:0x48 end:0xc0 dev:lo
------------[ cut here ]------------
kernel BUG at net/core/skbuff.c:104!
invalid opcode: 0000 [#1] KASAN
CPU: 0 PID: 160 Comm: reproducer Not tainted 4.6.0-rc2 #65
[...]
Call Trace:
 [<ffffffff813eb7b9>] skb_push+0x79/0x80
 [<ffffffff8143397b>] eth_header+0x2b/0x100
 [<ffffffff8141e0d0>] neigh_resolve_output+0x210/0x310
 [<ffffffff814eab77>] ip6_finish_output2+0x4a7/0x7c0
 [<ffffffff814efe3a>] ip6_output+0x16a/0x280
 [<ffffffff815440c1>] ip6_local_out+0xb1/0xf0
 [<ffffffff814f1115>] ip6_send_skb+0x45/0xd0
 [<ffffffff81518836>] udp_v6_send_skb+0x246/0x5d0
 [<ffffffff8151985e>] udpv6_sendmsg+0xa6e/0x1090
[...]

Reported-by: Ji Jianwen <jiji@redhat.com>
Signed-off-by: Jakub Sitnicki <jkbs@redhat.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_output.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index a163102..2a6606c 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1091,8 +1091,8 @@ static inline int ip6_ufo_append_data(struct sock *sk,
 			int getfrag(void *from, char *to, int offset, int len,
 			int odd, struct sk_buff *skb),
 			void *from, int length, int hh_len, int fragheaderlen,
-			int transhdrlen, int mtu, unsigned int flags,
-			const struct flowi6 *fl6)
+			int exthdrlen, int transhdrlen, int mtu,
+			unsigned int flags, const struct flowi6 *fl6)
 
 {
 	struct sk_buff *skb;
@@ -1117,7 +1117,7 @@ static inline int ip6_ufo_append_data(struct sock *sk,
 		skb_put(skb, fragheaderlen + transhdrlen);
 
 		/* initialize network header pointer */
-		skb_reset_network_header(skb);
+		skb_set_network_header(skb, exthdrlen);
 
 		/* initialize protocol header pointer */
 		skb->transport_header = skb->network_header + fragheaderlen;
@@ -1359,7 +1359,7 @@ emsgsize:
 	    (rt->dst.dev->features & NETIF_F_UFO) &&
 	    (sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk)) {
 		err = ip6_ufo_append_data(sk, queue, getfrag, from, length,
-					  hh_len, fragheaderlen,
+					  hh_len, fragheaderlen, exthdrlen,
 					  transhdrlen, mtu, flags, fl6);
 		if (err)
 			goto error;
-- 
2.1.0


From 26b12c2008d2bd5c8cb01e4d153afd04b49e4501 Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Thu, 7 Apr 2016 21:28:38 -0700
Subject: [PATCH 40/40] mpls: find_outdev: check for err ptr in addition to
 NULL check

[ Upstream commit 94a57f1f8a9de90ab4b0f8748361ff8be706c80c ]

find_outdev calls inet{,6}_fib_lookup_dev() or dev_get_by_index() to
find the output device. In case of an error, inet{,6}_fib_lookup_dev()
returns error pointer and dev_get_by_index() returns NULL. But the function
only checks for NULL and thus can end up calling dev_put on an ERR_PTR.
This patch adds an additional check for err ptr after the NULL check.

Before: Trying to add an mpls route with no oif from user, no available
path to 10.1.1.8 and no default route:
$ip -f mpls route add 100 as 200 via inet 10.1.1.8
[  822.337195] BUG: unable to handle kernel NULL pointer dereference at
00000000000003a3
[  822.340033] IP: [<ffffffff8148781e>] mpls_nh_assign_dev+0x10b/0x182
[  822.340033] PGD 1db38067 PUD 1de9e067 PMD 0
[  822.340033] Oops: 0000 [#1] SMP
[  822.340033] Modules linked in:
[  822.340033] CPU: 0 PID: 11148 Comm: ip Not tainted 4.5.0-rc7+ #54
[  822.340033] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996),
BIOS rel-1.7.5.1-0-g8936dbb-20141113_115728-nilsson.home.kraxel.org
04/01/2014
[  822.340033] task: ffff88001db82580 ti: ffff88001dad4000 task.ti:
ffff88001dad4000
[  822.340033] RIP: 0010:[<ffffffff8148781e>]  [<ffffffff8148781e>]
mpls_nh_assign_dev+0x10b/0x182
[  822.340033] RSP: 0018:ffff88001dad7a88  EFLAGS: 00010282
[  822.340033] RAX: ffffffffffffff9b RBX: ffffffffffffff9b RCX:
0000000000000002
[  822.340033] RDX: 00000000ffffff9b RSI: 0000000000000008 RDI:
0000000000000000
[  822.340033] RBP: ffff88001ddc9ea0 R08: ffff88001e9f1768 R09:
0000000000000000
[  822.340033] R10: ffff88001d9c1100 R11: ffff88001e3c89f0 R12:
ffffffff8187e0c0
[  822.340033] R13: ffffffff8187e0c0 R14: ffff88001ddc9e80 R15:
0000000000000004
[  822.340033] FS:  00007ff9ed798700(0000) GS:ffff88001fc00000(0000)
knlGS:0000000000000000
[  822.340033] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  822.340033] CR2: 00000000000003a3 CR3: 000000001de89000 CR4:
00000000000006f0
[  822.340033] Stack:
[  822.340033]  0000000000000000 0000000100000000 0000000000000000
0000000000000000
[  822.340033]  0000000000000000 0801010a00000000 0000000000000000
0000000000000000
[  822.340033]  0000000000000004 ffffffff8148749b ffffffff8187e0c0
000000000000001c
[  822.340033] Call Trace:
[  822.340033]  [<ffffffff8148749b>] ? mpls_rt_alloc+0x2b/0x3e
[  822.340033]  [<ffffffff81488e66>] ? mpls_rtm_newroute+0x358/0x3e2
[  822.340033]  [<ffffffff810e7bbc>] ? get_page+0x5/0xa
[  822.340033]  [<ffffffff813b7d94>] ? rtnetlink_rcv_msg+0x17e/0x191
[  822.340033]  [<ffffffff8111794e>] ? __kmalloc_track_caller+0x8c/0x9e
[  822.340033]  [<ffffffff813c9393>] ?
rht_key_hashfn.isra.20.constprop.57+0x14/0x1f
[  822.340033]  [<ffffffff813b7c16>] ? __rtnl_unlock+0xc/0xc
[  822.340033]  [<ffffffff813cb794>] ? netlink_rcv_skb+0x36/0x82
[  822.340033]  [<ffffffff813b4507>] ? rtnetlink_rcv+0x1f/0x28
[  822.340033]  [<ffffffff813cb2b1>] ? netlink_unicast+0x106/0x189
[  822.340033]  [<ffffffff813cb5b3>] ? netlink_sendmsg+0x27f/0x2c8
[  822.340033]  [<ffffffff81392ede>] ? sock_sendmsg_nosec+0x10/0x1b
[  822.340033]  [<ffffffff81393df1>] ? ___sys_sendmsg+0x182/0x1e3
[  822.340033]  [<ffffffff810e4f35>] ?
__alloc_pages_nodemask+0x11c/0x1e4
[  822.340033]  [<ffffffff8110619c>] ? PageAnon+0x5/0xd
[  822.340033]  [<ffffffff811062fe>] ? __page_set_anon_rmap+0x45/0x52
[  822.340033]  [<ffffffff810e7bbc>] ? get_page+0x5/0xa
[  822.340033]  [<ffffffff810e85ab>] ? __lru_cache_add+0x1a/0x3a
[  822.340033]  [<ffffffff81087ea9>] ? current_kernel_time64+0x9/0x30
[  822.340033]  [<ffffffff813940c4>] ? __sys_sendmsg+0x3c/0x5a
[  822.340033]  [<ffffffff8148f597>] ?
entry_SYSCALL_64_fastpath+0x12/0x6a
[  822.340033] Code: 83 08 04 00 00 65 ff 00 48 8b 3c 24 e8 40 7c f2 ff
eb 13 48 c7 c3 9f ff ff ff eb 0f 89 ce e8 f1 ae f1 ff 48 89 c3 48 85 db
74 15 <48> 8b 83 08 04 00 00 65 ff 08 48 81 fb 00 f0 ff ff 76 0d eb 07
[  822.340033] RIP  [<ffffffff8148781e>] mpls_nh_assign_dev+0x10b/0x182
[  822.340033]  RSP <ffff88001dad7a88>
[  822.340033] CR2: 00000000000003a3
[  822.435363] ---[ end trace 98cc65e6f6b8bf11 ]---

After patch:
$ip -f mpls route add 100 as 200 via inet 10.1.1.8
RTNETLINK answers: Network is unreachable

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Reported-by: David Miller <davem@davemloft.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mpls/af_mpls.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index b18c5ed..0b80a71 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -543,6 +543,9 @@ static struct net_device *find_outdev(struct net *net,
 	if (!dev)
 		return ERR_PTR(-ENODEV);
 
+	if (IS_ERR(dev))
+		return dev;
+
 	/* The caller is holding rtnl anyways, so release the dev reference */
 	dev_put(dev);
 
-- 
2.1.0

Re: [PATCHES] Networking

[Greg KH]

On Fri, Apr 15, 2016 at 12:45:04AM -0400, David Miller wrote:
> 
> Please queue up the following bug fixes for 4.1, 4.4, and 4.5 -stable,
> respectively.

Thanks for these, I've queued up the 4.4 and 4.5-stable ones now.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 112 bytes --]


Please queue up the following networking bug fixes for 4.1.x, 4.4.x, and 4.5.x -stable,
respectively.

Thanks!

[-- Attachment #2: net_41.mbox --]
[-- Type: Application/Octet-Stream, Size: 80887 bytes --]

From fdd70115c477d43b2168906014ef1f59c6cd1738 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 13 May 2016 18:33:41 +0200
Subject: [PATCH 01/26] net/route: enforce hoplimit max value

[ Upstream commit 626abd59e51d4d8c6367e03aae252a8aa759ac78 ]

Currently, when creating or updating a route, no check is performed
in both ipv4 and ipv6 code to the hoplimit value.

The caller can i.e. set hoplimit to 256, and when such route will
 be used, packets will be sent with hoplimit/ttl equal to 0.

This commit adds checks for the RTAX_HOPLIMIT value, in both ipv4
ipv6 route code, substituting any value greater than 255 with 255.

This is consistent with what is currently done for ADVMSS and MTU
in the ipv4 code.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_semantics.c | 2 ++
 net/ipv6/route.c         | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 8d695b6..9ab4d02 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -855,6 +855,8 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 					val = 65535 - 40;
 				if (type == RTAX_MTU && val > 65535 - 15)
 					val = 65535 - 15;
+				if (type == RTAX_HOPLIMIT && val > 255)
+					val = 255;
 				fi->fib_metrics[type - 1] = val;
 			}
 		}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index fe70bd6..a960ffe 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1499,6 +1499,8 @@ static int ip6_convert_metrics(struct mx6_config *mxc,
 			} else {
 				val = nla_get_u32(nla);
 			}
+			if (type == RTAX_HOPLIMIT && val > 255)
+				val = 255;
 
 			mp[type - 1] = val;
 			__set_bit(type - 1, mxc->mx_valid);
-- 
2.4.1


From 9d530b3e8a74e1fd99d9d13353963823c652c46d Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sun, 10 Apr 2016 23:01:30 -0400
Subject: [PATCH 02/26] decnet: Do not build routes to devices without decnet
 private data.

[ Upstream commit a36a0d4008488fa545c74445d69eaf56377d5d4e ]

In particular, make sure we check for decnet private presence
for loopback devices.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/decnet/dn_route.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index 03227ff..76d3bf70 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -1036,10 +1036,13 @@ source_ok:
 	if (!fld.daddr) {
 		fld.daddr = fld.saddr;
 
-		err = -EADDRNOTAVAIL;
 		if (dev_out)
 			dev_put(dev_out);
+		err = -EINVAL;
 		dev_out = init_net.loopback_dev;
+		if (!dev_out->dn_ptr)
+			goto out;
+		err = -EADDRNOTAVAIL;
 		dev_hold(dev_out);
 		if (!fld.daddr) {
 			fld.daddr =
@@ -1112,6 +1115,8 @@ source_ok:
 		if (dev_out == NULL)
 			goto out;
 		dn_db = rcu_dereference_raw(dev_out->dn_ptr);
+		if (!dn_db)
+			goto e_inval;
 		/* Possible improvement - check all devices for local addr */
 		if (dn_dev_islocal(dev_out, fld.daddr)) {
 			dev_put(dev_out);
@@ -1153,6 +1158,8 @@ select_source:
 			dev_put(dev_out);
 		dev_out = init_net.loopback_dev;
 		dev_hold(dev_out);
+		if (!dev_out->dn_ptr)
+			goto e_inval;
 		fld.flowidn_oif = dev_out->ifindex;
 		if (res.fi)
 			dn_fib_info_put(res.fi);
-- 
2.4.1


From a5058d7f1c7f785db49554e0265e1792c937287c Mon Sep 17 00:00:00 2001
From: Chris Friesen <chris.friesen@windriver.com>
Date: Fri, 8 Apr 2016 15:21:30 -0600
Subject: [PATCH 03/26] route: do not cache fib route info on local routes with
 oif

[ Upstream commit d6d5e999e5df67f8ec20b6be45e2229455ee3699 ]

For local routes that require a particular output interface we do not want
to cache the result.  Caching the result causes incorrect behaviour when
there are multiple source addresses on the interface.  The end result
being that if the intended recipient is waiting on that interface for the
packet he won't receive it because it will be delivered on the loopback
interface and the IP_PKTINFO ipi_ifindex will be set to the loopback
interface as well.

This can be tested by running a program such as "dhcp_release" which
attempts to inject a packet on a particular interface so that it is
received by another program on the same board.  The receiving process
should see an IP_PKTINFO ipi_ifndex value of the source interface
(e.g., eth1) instead of the loopback interface (e.g., lo).  The packet
will still appear on the loopback interface in tcpdump but the important
aspect is that the CMSG info is correct.

Sample dhcp_release command line:

   dhcp_release eth1 192.168.204.222 02:11:33:22:44:66

Signed-off-by: Allain Legacy <allain.legacy@windriver.com>
Signed off-by: Chris Friesen <chris.friesen@windriver.com>
Reviewed-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 1d3cdb4d..eb1d983 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1976,6 +1976,18 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 		 */
 		if (fi && res->prefixlen < 4)
 			fi = NULL;
+	} else if ((type == RTN_LOCAL) && (orig_oif != 0) &&
+		   (orig_oif != dev_out->ifindex)) {
+		/* For local routes that require a particular output interface
+		 * we do not want to cache the result.  Caching the result
+		 * causes incorrect behaviour when there are multiple source
+		 * addresses on the interface, the end result being that if the
+		 * intended recipient is waiting on that interface for the
+		 * packet he won't receive it because it will be delivered on
+		 * the loopback interface and the IP_PKTINFO ipi_ifindex will
+		 * be set to the loopback interface as well.
+		 */
+		fi = NULL;
 	}
 
 	fnhe = NULL;
-- 
2.4.1


From 1aad6731a3368615ca81fa4191385edd4a2ddcdc Mon Sep 17 00:00:00 2001
From: Mathias Krause <minipli@googlemail.com>
Date: Sun, 10 Apr 2016 12:52:28 +0200
Subject: [PATCH 04/26] packet: fix heap info leak in PACKET_DIAG_MCLIST
 sock_diag interface

[ Upstream commit 309cf37fe2a781279b7675d4bb7173198e532867 ]

Because we miss to wipe the remainder of i->addr[] in packet_mc_add(),
pdiag_put_mclist() leaks uninitialized heap bytes via the
PACKET_DIAG_MCLIST netlink attribute.

Fix this by explicitly memset(0)ing the remaining bytes in i->addr[].

Fixes: eea68e2f1a00 ("packet: Report socket mclist info via diag module")
Signed-off-by: Mathias Krause <minipli@googlemail.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Acked-by: Pavel Emelyanov <xemul@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index ebc39e6..66c95e6 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3212,6 +3212,7 @@ static int packet_mc_add(struct sock *sk, struct packet_mreq_max *mreq)
 	i->ifindex = mreq->mr_ifindex;
 	i->alen = mreq->mr_alen;
 	memcpy(i->addr, mreq->mr_address, i->alen);
+	memset(i->addr + i->alen, 0, sizeof(i->addr) - i->alen);
 	i->count = 1;
 	i->next = po->mclist;
 	po->mclist = i;
-- 
2.4.1


From 7c7e307c3ac004ae11f10343fb20b728eb40e87c Mon Sep 17 00:00:00 2001
From: Lars Persson <lars.persson@axis.com>
Date: Tue, 12 Apr 2016 08:45:52 +0200
Subject: [PATCH 05/26] net: sched: do not requeue a NULL skb

[ Upstream commit 3dcd493fbebfd631913df6e2773cc295d3bf7d22 ]

A failure in validate_xmit_skb_list() triggered an unconditional call
to dev_requeue_skb with skb=NULL. This slowly grows the queue
discipline's qlen count until all traffic through the queue stops.

We take the optimistic approach and continue running the queue after a
failure since it is unknown if later packets also will fail in the
validate path.

Fixes: 55a93b3ea780 ("qdisc: validate skb without holding lock")
Signed-off-by: Lars Persson <larper@axis.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_generic.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 3c6f6b77..9821e6d 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -159,12 +159,15 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
 	if (validate)
 		skb = validate_xmit_skb_list(skb, dev);
 
-	if (skb) {
+	if (likely(skb)) {
 		HARD_TX_LOCK(dev, txq, smp_processor_id());
 		if (!netif_xmit_frozen_or_stopped(txq))
 			skb = dev_hard_start_xmit(skb, dev, txq, &ret);
 
 		HARD_TX_UNLOCK(dev, txq);
+	} else {
+		spin_lock(root_lock);
+		return qdisc_qlen(q);
 	}
 	spin_lock(root_lock);
 
-- 
2.4.1


From 2f38270241053cb89b335a62d1984830c0b00761 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@fb.com>
Date: Tue, 12 Apr 2016 10:26:19 -0700
Subject: [PATCH 06/26] bpf/verifier: reject invalid LD_ABS | BPF_DW
 instruction

[ Upstream commit d82bccc69041a51f7b7b9b4a36db0772f4cdba21 ]

verifier must check for reserved size bits in instruction opcode and
reject BPF_LD | BPF_ABS | BPF_DW and BPF_LD | BPF_IND | BPF_DW instructions,
otherwise interpreter will WARN_RATELIMIT on them during execution.

Fixes: ddd872bc3098 ("bpf: verifier: add checks for BPF_ABS | BPF_IND instructions")
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 6582410..dd16d19 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1227,6 +1227,7 @@ static int check_ld_abs(struct verifier_env *env, struct bpf_insn *insn)
 	}
 
 	if (insn->dst_reg != BPF_REG_0 || insn->off != 0 ||
+	    BPF_SIZE(insn->code) == BPF_DW ||
 	    (mode == BPF_ABS && insn->src_reg != BPF_REG_0)) {
 		verbose("BPF_LD_ABS uses reserved fields\n");
 		return -EINVAL;
-- 
2.4.1


From 55e28ce5330e3a7aee8edba8a4ea9b2edba96f53 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Sat, 20 Feb 2016 00:29:30 +0100
Subject: [PATCH 07/26] net: use skb_postpush_rcsum instead of own
 implementations

[ Upstream commit 6b83d28a55a891a9d70fc61ccb1c138e47dcbe74,
  skb_postpush_rcsum() added from commit
  f8ffad69c9f8b8dfb0b633425d4ef4d2493ba61a ]

Replace individual implementations with the recently introduced
skb_postpush_rcsum() helper.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Tom Herbert <tom@herbertland.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h         | 17 +++++++++++++++++
 net/core/skbuff.c              |  4 +---
 net/ipv6/reassembly.c          |  6 ++----
 net/openvswitch/actions.c      |  6 ++----
 net/openvswitch/vport-netdev.c |  2 +-
 net/openvswitch/vport.h        |  7 -------
 6 files changed, 23 insertions(+), 19 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 6633b0c..e055fa0 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2596,6 +2596,23 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb,
 
 unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len);
 
+static inline void skb_postpush_rcsum(struct sk_buff *skb,
+				      const void *start, unsigned int len)
+{
+	/* For performing the reverse operation to skb_postpull_rcsum(),
+	 * we can instead of ...
+	 *
+	 *   skb->csum = csum_add(skb->csum, csum_partial(start, len, 0));
+	 *
+	 * ... just use this equivalent version here to save a few
+	 * instructions. Feeding csum of 0 in csum_partial() and later
+	 * on adding skb->csum is equivalent to feed skb->csum in the
+	 * first place.
+	 */
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		skb->csum = csum_partial(start, len, skb->csum);
+}
+
 /**
  *	pskb_trim_rcsum - trim received skb and update checksum
  *	@skb: buffer to trim
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index c9793c6..605674a 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4347,9 +4347,7 @@ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci)
 		skb->mac_len += VLAN_HLEN;
 		__skb_pull(skb, offset);
 
-		if (skb->ip_summed == CHECKSUM_COMPLETE)
-			skb->csum = csum_add(skb->csum, csum_partial(skb->data
-					+ (2 * ETH_ALEN), VLAN_HLEN, 0));
+		skb_postpush_rcsum(skb, skb->data + (2 * ETH_ALEN), VLAN_HLEN);
 	}
 	__vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci);
 	return 0;
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 9d1f6a2..cf829f4 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -496,10 +496,8 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
 	IP6CB(head)->flags |= IP6SKB_FRAGMENTED;
 
 	/* Yes, and fold redundant checksum back. 8) */
-	if (head->ip_summed == CHECKSUM_COMPLETE)
-		head->csum = csum_partial(skb_network_header(head),
-					  skb_network_header_len(head),
-					  head->csum);
+	skb_postpush_rcsum(head, skb_network_header(head),
+			   skb_network_header_len(head));
 
 	rcu_read_lock();
 	IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS);
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index b491c1c..aa8072b 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -140,9 +140,7 @@ static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key,
 	new_mpls_lse = (__be32 *)skb_mpls_header(skb);
 	*new_mpls_lse = mpls->mpls_lse;
 
-	if (skb->ip_summed == CHECKSUM_COMPLETE)
-		skb->csum = csum_add(skb->csum, csum_partial(new_mpls_lse,
-							     MPLS_HLEN, 0));
+	skb_postpush_rcsum(skb, new_mpls_lse, MPLS_HLEN);
 
 	hdr = eth_hdr(skb);
 	hdr->h_proto = mpls->mpls_ethertype;
@@ -266,7 +264,7 @@ static int set_eth_addr(struct sk_buff *skb, struct sw_flow_key *flow_key,
 	ether_addr_copy_masked(eth_hdr(skb)->h_dest, key->eth_dst,
 			       mask->eth_dst);
 
-	ovs_skb_postpush_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
+	skb_postpush_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
 
 	ether_addr_copy(flow_key->eth.src, eth_hdr(skb)->h_source);
 	ether_addr_copy(flow_key->eth.dst, eth_hdr(skb)->h_dest);
diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c
index 33e6d6e..eece71d 100644
--- a/net/openvswitch/vport-netdev.c
+++ b/net/openvswitch/vport-netdev.c
@@ -52,7 +52,7 @@ static void netdev_port_receive(struct vport *vport, struct sk_buff *skb)
 		return;
 
 	skb_push(skb, ETH_HLEN);
-	ovs_skb_postpush_rcsum(skb, skb->data, ETH_HLEN);
+	skb_postpush_rcsum(skb, skb->data, ETH_HLEN);
 
 	ovs_vport_receive(vport, skb, NULL);
 	return;
diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h
index bc85331..cb4cd12 100644
--- a/net/openvswitch/vport.h
+++ b/net/openvswitch/vport.h
@@ -228,13 +228,6 @@ static inline struct vport *vport_from_priv(void *priv)
 void ovs_vport_receive(struct vport *, struct sk_buff *,
 		       const struct ovs_tunnel_info *);
 
-static inline void ovs_skb_postpush_rcsum(struct sk_buff *skb,
-				      const void *start, unsigned int len)
-{
-	if (skb->ip_summed == CHECKSUM_COMPLETE)
-		skb->csum = csum_add(skb->csum, csum_partial(start, len, 0));
-}
-
 int ovs_vport_ops_register(struct vport_ops *ops);
 void ovs_vport_ops_unregister(struct vport_ops *ops);
 
-- 
2.4.1


From 9a7daa8b08ebc88e9302c1d8afa7f4e63bf0390a Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Sat, 16 Apr 2016 02:27:58 +0200
Subject: [PATCH 08/26] vlan: pull on __vlan_insert_tag error path and fix csum
 correction

[ Upstream commit 9241e2df4fbc648a92ea0752918e05c26255649e ]

When __vlan_insert_tag() fails from skb_vlan_push() path due to the
skb_cow_head(), we need to undo the __skb_push() in the error path
as well that was done earlier to move skb->data pointer to mac header.

Moreover, I noticed that when in the non-error path the __skb_pull()
is done and the original offset to mac header was non-zero, we fixup
from a wrong skb->data offset in the checksum complete processing.

So the skb_postpush_rcsum() really needs to be done before __skb_pull()
where skb->data still points to the mac header start and thus operates
under the same conditions as in __vlan_insert_tag().

Fixes: 93515d53b133 ("net: move vlan pop/push functions into common code")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 605674a..0d890d0 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4341,13 +4341,16 @@ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci)
 		__skb_push(skb, offset);
 		err = __vlan_insert_tag(skb, skb->vlan_proto,
 					skb_vlan_tag_get(skb));
-		if (err)
+		if (err) {
+			__skb_pull(skb, offset);
 			return err;
+		}
+
 		skb->protocol = skb->vlan_proto;
 		skb->mac_len += VLAN_HLEN;
-		__skb_pull(skb, offset);
 
 		skb_postpush_rcsum(skb, skb->data + (2 * ETH_ALEN), VLAN_HLEN);
+		__skb_pull(skb, offset);
 	}
 	__vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci);
 	return 0;
-- 
2.4.1


From f0ed267a298bef4440eaaaa70e535826bad007ca Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben@decadent.org.uk>
Date: Wed, 20 Apr 2016 23:23:08 +0100
Subject: [PATCH 09/26] atl2: Disable unimplemented scatter/gather feature

[ Upstream commit f43bfaeddc79effbf3d0fcb53ca477cca66f3db8 ]

atl2 includes NETIF_F_SG in hw_features even though it has no support
for non-linear skbs.  This bug was originally harmless since the
driver does not claim to implement checksum offload and that used to
be a requirement for SG.

Now that SG and checksum offload are independent features, if you
explicitly enable SG *and* use one of the rare protocols that can use
SG without checkusm offload, this potentially leaks sensitive
information (before you notice that it just isn't working).  Therefore
this obscure bug has been designated CVE-2016-2117.

Reported-by: Justin Yackoski <jyackoski@crypto-nite.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Fixes: ec5f06156423 ("net: Kill link between CSUM and SG features.")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/atheros/atlx/atl2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c
index 46a5353..972ee64 100644
--- a/drivers/net/ethernet/atheros/atlx/atl2.c
+++ b/drivers/net/ethernet/atheros/atlx/atl2.c
@@ -1412,7 +1412,7 @@ static int atl2_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	err = -EIO;
 
-	netdev->hw_features = NETIF_F_SG | NETIF_F_HW_VLAN_CTAG_RX;
+	netdev->hw_features = NETIF_F_HW_VLAN_CTAG_RX;
 	netdev->features |= (NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX);
 
 	/* Init PHY as early as possible due to power saving issue  */
-- 
2.4.1


From dbcb9a725cc5b785c05ccbe8d01976602e47995f Mon Sep 17 00:00:00 2001
From: Simon Horman <simon.horman@netronome.com>
Date: Thu, 21 Apr 2016 11:49:15 +1000
Subject: [PATCH 10/26] openvswitch: use flow protocol when recalculating ipv6
 checksums

[ Upstream commit b4f70527f052b0c00be4d7cac562baa75b212df5 ]

When using masked actions the ipv6_proto field of an action
to set IPv6 fields may be zero rather than the prevailing protocol
which will result in skipping checksum recalculation.

This patch resolves the problem by relying on the protocol
in the flow key rather than that in the set field action.

Fixes: 83d2b9ba1abc ("net: openvswitch: Support masked set actions.")
Cc: Jarno Rajahalme <jrajahalme@nicira.com>
Signed-off-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/actions.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index aa8072b..8011404 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -439,7 +439,7 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key,
 		mask_ipv6_addr(saddr, key->ipv6_src, mask->ipv6_src, masked);
 
 		if (unlikely(memcmp(saddr, masked, sizeof(masked)))) {
-			set_ipv6_addr(skb, key->ipv6_proto, saddr, masked,
+			set_ipv6_addr(skb, flow_key->ip.proto, saddr, masked,
 				      true);
 			memcpy(&flow_key->ipv6.addr.src, masked,
 			       sizeof(flow_key->ipv6.addr.src));
@@ -461,7 +461,7 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key,
 							     NULL, &flags)
 					       != NEXTHDR_ROUTING);
 
-			set_ipv6_addr(skb, key->ipv6_proto, daddr, masked,
+			set_ipv6_addr(skb, flow_key->ip.proto, daddr, masked,
 				      recalc_csum);
 			memcpy(&flow_key->ipv6.addr.dst, masked,
 			       sizeof(flow_key->ipv6.addr.dst));
-- 
2.4.1


From 38415d46de887691ef73cf12f1ebb795ef1ec707 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 21 Apr 2016 22:23:31 +0200
Subject: [PATCH 11/26] ipv4/fib: don't warn when primary address is missing if
 in_dev is dead

[ Upstream commit 391a20333b8393ef2e13014e6e59d192c5594471 ]

After commit fbd40ea0180a ("ipv4: Don't do expensive useless work
during inetdev destroy.") when deleting an interface,
fib_del_ifaddr() can be executed without any primary address
present on the dead interface.

The above is safe, but triggers some "bug: prim == NULL" warnings.

This commit avoids warning if the in_dev is dead

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_frontend.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 872494e..80094f8 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -861,7 +861,11 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim)
 	if (ifa->ifa_flags & IFA_F_SECONDARY) {
 		prim = inet_ifa_byprefix(in_dev, any, ifa->ifa_mask);
 		if (!prim) {
-			pr_warn("%s: bug: prim == NULL\n", __func__);
+			/* if the device has been deleted, we don't perform
+			 * address promotion
+			 */
+			if (!in_dev->dead)
+				pr_warn("%s: bug: prim == NULL\n", __func__);
 			return;
 		}
 		if (iprim && iprim != prim) {
-- 
2.4.1


From 08c19b563dc088d9b69e7d572c25e2463e85b5dd Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 23 Apr 2016 11:35:46 -0700
Subject: [PATCH 12/26] net/mlx4_en: fix spurious timestamping callbacks

[ Upstream commit fc96256c906362e845d848d0f6a6354450059e81 ]

When multiple skb are TX-completed in a row, we might incorrectly keep
a timestamp of a prior skb and cause extra work.

Fixes: ec693d47010e8 ("net/mlx4_en: Add HW timestamping (TS) support")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_tx.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index c10d98f..a1b4301 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -400,7 +400,6 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev,
 	u32 packets = 0;
 	u32 bytes = 0;
 	int factor = priv->cqe_factor;
-	u64 timestamp = 0;
 	int done = 0;
 	int budget = priv->tx_work_limit;
 	u32 last_nr_txbb;
@@ -440,9 +439,12 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev,
 		new_index = be16_to_cpu(cqe->wqe_index) & size_mask;
 
 		do {
+			u64 timestamp = 0;
+
 			txbbs_skipped += last_nr_txbb;
 			ring_index = (ring_index + last_nr_txbb) & size_mask;
-			if (ring->tx_info[ring_index].ts_requested)
+
+			if (unlikely(ring->tx_info[ring_index].ts_requested))
 				timestamp = mlx4_en_get_cqe_ts(cqe);
 
 			/* free next descriptor */
-- 
2.4.1


From fd47c84676ef57ab3420a4ed7da406ccb3e14020 Mon Sep 17 00:00:00 2001
From: Jann Horn <jannh@google.com>
Date: Tue, 26 Apr 2016 22:26:26 +0200
Subject: [PATCH 13/26] bpf: fix double-fdput in replace_map_fd_with_map_ptr()

[ Upstream commit 8358b02bf67d3a5d8a825070e1aa73f25fb2e4c7 ]

When bpf(BPF_PROG_LOAD, ...) was invoked with a BPF program whose bytecode
references a non-map file descriptor as a map file descriptor, the error
handling code called fdput() twice instead of once (in __bpf_map_get() and
in replace_map_fd_with_map_ptr()). If the file descriptor table of the
current task is shared, this causes f_count to be decremented too much,
allowing the struct file to be freed while it is still in use
(use-after-free). This can be exploited to gain root privileges by an
unprivileged user.

This bug was introduced in
commit 0246e64d9a5f ("bpf: handle pseudo BPF_LD_IMM64 insn"), but is only
exploitable since
commit 1be7f75d1668 ("bpf: enable non-root eBPF programs") because
previously, CAP_SYS_ADMIN was required to reach the vulnerable code.

(posted publicly according to request by maintainer)

Signed-off-by: Jann Horn <jannh@google.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index dd16d19..efd143d 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1865,7 +1865,6 @@ static int replace_map_fd_with_map_ptr(struct verifier_env *env)
 			if (IS_ERR(map)) {
 				verbose("fd %d is not pointing to valid bpf_map\n",
 					insn->imm);
-				fdput(f);
 				return PTR_ERR(map);
 			}
 
-- 
2.4.1


From fa573ee6c8a2ca7b34adcce9023ecc32dc17871b Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Thu, 25 Feb 2016 14:55:00 -0800
Subject: [PATCH 14/26] net_sched: introduce qdisc_replace() helper

[ Upstream commit 86a7996cc8a078793670d82ed97d5a99bb4e8496 ]

Remove nearly duplicated code and prepare for the following patch.

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h | 17 +++++++++++++++++
 net/sched/sch_cbq.c       |  7 +------
 net/sched/sch_drr.c       |  6 +-----
 net/sched/sch_dsmark.c    |  8 +-------
 net/sched/sch_hfsc.c      |  6 +-----
 net/sched/sch_htb.c       |  9 +--------
 net/sched/sch_multiq.c    |  8 +-------
 net/sched/sch_netem.c     | 10 +---------
 net/sched/sch_prio.c      |  8 +-------
 net/sched/sch_qfq.c       |  6 +-----
 net/sched/sch_red.c       |  7 +------
 net/sched/sch_sfb.c       |  7 +------
 net/sched/sch_tbf.c       |  8 +-------
 13 files changed, 29 insertions(+), 78 deletions(-)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 080b657..1fb8a5b 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -691,6 +691,23 @@ static inline void qdisc_reset_queue(struct Qdisc *sch)
 	sch->qstats.backlog = 0;
 }
 
+static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new,
+					  struct Qdisc **pold)
+{
+	struct Qdisc *old;
+
+	sch_tree_lock(sch);
+	old = *pold;
+	*pold = new;
+	if (old != NULL) {
+		qdisc_tree_decrease_qlen(old, old->q.qlen);
+		qdisc_reset(old);
+	}
+	sch_tree_unlock(sch);
+
+	return old;
+}
+
 static inline unsigned int __qdisc_queue_drop(struct Qdisc *sch,
 					      struct sk_buff_head *list)
 {
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index beeb75f..17ad79e 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1624,13 +1624,8 @@ static int cbq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 			new->reshape_fail = cbq_reshape_fail;
 #endif
 	}
-	sch_tree_lock(sch);
-	*old = cl->q;
-	cl->q = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
 
+	*old = qdisc_replace(sch, new, &cl->q);
 	return 0;
 }
 
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index 3387060..d4b3f82 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -226,11 +226,7 @@ static int drr_graft_class(struct Qdisc *sch, unsigned long arg,
 			new = &noop_qdisc;
 	}
 
-	sch_tree_lock(sch);
-	drr_purge_queue(cl);
-	*old = cl->qdisc;
-	cl->qdisc = new;
-	sch_tree_unlock(sch);
+	*old = qdisc_replace(sch, new, &cl->qdisc);
 	return 0;
 }
 
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index 66700a6..d2084e7 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -67,13 +67,7 @@ static int dsmark_graft(struct Qdisc *sch, unsigned long arg,
 			new = &noop_qdisc;
 	}
 
-	sch_tree_lock(sch);
-	*old = p->q;
-	p->q = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
-
+	*old = qdisc_replace(sch, new, &p->q);
 	return 0;
 }
 
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index e6c7416..134f7d2 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1215,11 +1215,7 @@ hfsc_graft_class(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 			new = &noop_qdisc;
 	}
 
-	sch_tree_lock(sch);
-	hfsc_purge_queue(sch, cl);
-	*old = cl->qdisc;
-	cl->qdisc = new;
-	sch_tree_unlock(sch);
+	*old = qdisc_replace(sch, new, &cl->qdisc);
 	return 0;
 }
 
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index f1acb0f..520ffe9 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1165,14 +1165,7 @@ static int htb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 				     cl->common.classid)) == NULL)
 		return -ENOBUFS;
 
-	sch_tree_lock(sch);
-	*old = cl->un.leaf.q;
-	cl->un.leaf.q = new;
-	if (*old != NULL) {
-		qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-		qdisc_reset(*old);
-	}
-	sch_tree_unlock(sch);
+	*old = qdisc_replace(sch, new, &cl->un.leaf.q);
 	return 0;
 }
 
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index 42dd218..f36ff83 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -303,13 +303,7 @@ static int multiq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 	if (new == NULL)
 		new = &noop_qdisc;
 
-	sch_tree_lock(sch);
-	*old = q->queues[band];
-	q->queues[band] = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
-
+	*old = qdisc_replace(sch, new, &q->queues[band]);
 	return 0;
 }
 
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 956ead2..8d56016 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -1037,15 +1037,7 @@ static int netem_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 {
 	struct netem_sched_data *q = qdisc_priv(sch);
 
-	sch_tree_lock(sch);
-	*old = q->qdisc;
-	q->qdisc = new;
-	if (*old) {
-		qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-		qdisc_reset(*old);
-	}
-	sch_tree_unlock(sch);
-
+	*old = qdisc_replace(sch, new, &q->qdisc);
 	return 0;
 }
 
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index 8e5cd34..a677f543a 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -268,13 +268,7 @@ static int prio_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 	if (new == NULL)
 		new = &noop_qdisc;
 
-	sch_tree_lock(sch);
-	*old = q->queues[band];
-	q->queues[band] = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
-
+	*old = qdisc_replace(sch, new, &q->queues[band]);
 	return 0;
 }
 
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 3ec7e88..6fea320 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -619,11 +619,7 @@ static int qfq_graft_class(struct Qdisc *sch, unsigned long arg,
 			new = &noop_qdisc;
 	}
 
-	sch_tree_lock(sch);
-	qfq_purge_queue(cl);
-	*old = cl->qdisc;
-	cl->qdisc = new;
-	sch_tree_unlock(sch);
+	*old = qdisc_replace(sch, new, &cl->qdisc);
 	return 0;
 }
 
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 6c0534c..d5abcee 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -313,12 +313,7 @@ static int red_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 	if (new == NULL)
 		new = &noop_qdisc;
 
-	sch_tree_lock(sch);
-	*old = q->qdisc;
-	q->qdisc = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
+	*old = qdisc_replace(sch, new, &q->qdisc);
 	return 0;
 }
 
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index 5819dd8..fa7f0a3 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -614,12 +614,7 @@ static int sfb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 	if (new == NULL)
 		new = &noop_qdisc;
 
-	sch_tree_lock(sch);
-	*old = q->qdisc;
-	q->qdisc = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
+	*old = qdisc_replace(sch, new, &q->qdisc);
 	return 0;
 }
 
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index a4afde1..56a1aef 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -502,13 +502,7 @@ static int tbf_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 	if (new == NULL)
 		new = &noop_qdisc;
 
-	sch_tree_lock(sch);
-	*old = q->qdisc;
-	q->qdisc = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
-
+	*old = qdisc_replace(sch, new, &q->qdisc);
 	return 0;
 }
 
-- 
2.4.1


From aba5cf6fe5e853df4af4b7915a94b48c6c96f5bf Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Thu, 25 Feb 2016 14:55:01 -0800
Subject: [PATCH 15/26] net_sched: update hierarchical backlog too

[ Upstream commit 2ccccf5fb43ff62b2b96cc58d95fc0b3596516e4 ]

When the bottom qdisc decides to, for example, drop some packet,
it calls qdisc_tree_decrease_qlen() to update the queue length
for all its ancestors, we need to update the backlog too to
keep the stats on root qdisc accurate.

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/codel.h       |  4 ++++
 include/net/sch_generic.h |  5 +++--
 net/sched/sch_api.c       |  8 +++++---
 net/sched/sch_cbq.c       |  5 +++--
 net/sched/sch_choke.c     |  6 ++++--
 net/sched/sch_codel.c     | 10 ++++++----
 net/sched/sch_drr.c       |  3 ++-
 net/sched/sch_fq.c        |  4 +++-
 net/sched/sch_fq_codel.c  | 17 ++++++++++++-----
 net/sched/sch_hfsc.c      |  3 ++-
 net/sched/sch_hhf.c       | 10 +++++++---
 net/sched/sch_htb.c       | 10 ++++++----
 net/sched/sch_multiq.c    |  8 +++++---
 net/sched/sch_netem.c     |  3 ++-
 net/sched/sch_pie.c       |  5 +++--
 net/sched/sch_prio.c      |  7 ++++---
 net/sched/sch_qfq.c       |  3 ++-
 net/sched/sch_red.c       |  3 ++-
 net/sched/sch_sfb.c       |  3 ++-
 net/sched/sch_sfq.c       | 16 +++++++++-------
 net/sched/sch_tbf.c       |  7 +++++--
 21 files changed, 91 insertions(+), 49 deletions(-)

diff --git a/include/net/codel.h b/include/net/codel.h
index 1e18005..0ee7610 100644
--- a/include/net/codel.h
+++ b/include/net/codel.h
@@ -160,11 +160,13 @@ struct codel_vars {
  * struct codel_stats - contains codel shared variables and stats
  * @maxpacket:	largest packet we've seen so far
  * @drop_count:	temp count of dropped packets in dequeue()
+ * @drop_len:	bytes of dropped packets in dequeue()
  * ecn_mark:	number of packets we ECN marked instead of dropping
  */
 struct codel_stats {
 	u32		maxpacket;
 	u32		drop_count;
+	u32		drop_len;
 	u32		ecn_mark;
 };
 
@@ -301,6 +303,7 @@ static struct sk_buff *codel_dequeue(struct Qdisc *sch,
 								  vars->rec_inv_sqrt);
 					goto end;
 				}
+				stats->drop_len += qdisc_pkt_len(skb);
 				qdisc_drop(skb, sch);
 				stats->drop_count++;
 				skb = dequeue_func(vars, sch);
@@ -323,6 +326,7 @@ static struct sk_buff *codel_dequeue(struct Qdisc *sch,
 		if (params->ecn && INET_ECN_set_ce(skb)) {
 			stats->ecn_mark++;
 		} else {
+			stats->drop_len += qdisc_pkt_len(skb);
 			qdisc_drop(skb, sch);
 			stats->drop_count++;
 
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 1fb8a5b..530bdca 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -395,7 +395,8 @@ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue,
 			      struct Qdisc *qdisc);
 void qdisc_reset(struct Qdisc *qdisc);
 void qdisc_destroy(struct Qdisc *qdisc);
-void qdisc_tree_decrease_qlen(struct Qdisc *qdisc, unsigned int n);
+void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, unsigned int n,
+			       unsigned int len);
 struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 			  const struct Qdisc_ops *ops);
 struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue,
@@ -700,7 +701,7 @@ static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new,
 	old = *pold;
 	*pold = new;
 	if (old != NULL) {
-		qdisc_tree_decrease_qlen(old, old->q.qlen);
+		qdisc_tree_reduce_backlog(old, old->q.qlen, old->qstats.backlog);
 		qdisc_reset(old);
 	}
 	sch_tree_unlock(sch);
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 68c599a..c244a49 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -744,14 +744,15 @@ static u32 qdisc_alloc_handle(struct net_device *dev)
 	return 0;
 }
 
-void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
+void qdisc_tree_reduce_backlog(struct Qdisc *sch, unsigned int n,
+			       unsigned int len)
 {
 	const struct Qdisc_class_ops *cops;
 	unsigned long cl;
 	u32 parentid;
 	int drops;
 
-	if (n == 0)
+	if (n == 0 && len == 0)
 		return;
 	drops = max_t(int, n, 0);
 	rcu_read_lock();
@@ -774,11 +775,12 @@ void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
 			cops->put(sch, cl);
 		}
 		sch->q.qlen -= n;
+		sch->qstats.backlog -= len;
 		__qdisc_qstats_drop(sch, drops);
 	}
 	rcu_read_unlock();
 }
-EXPORT_SYMBOL(qdisc_tree_decrease_qlen);
+EXPORT_SYMBOL(qdisc_tree_reduce_backlog);
 
 static void notify_and_destroy(struct net *net, struct sk_buff *skb,
 			       struct nlmsghdr *n, u32 clid,
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 17ad79e..f6e7a60 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1909,7 +1909,7 @@ static int cbq_delete(struct Qdisc *sch, unsigned long arg)
 {
 	struct cbq_sched_data *q = qdisc_priv(sch);
 	struct cbq_class *cl = (struct cbq_class *)arg;
-	unsigned int qlen;
+	unsigned int qlen, backlog;
 
 	if (cl->filters || cl->children || cl == &q->link)
 		return -EBUSY;
@@ -1917,8 +1917,9 @@ static int cbq_delete(struct Qdisc *sch, unsigned long arg)
 	sch_tree_lock(sch);
 
 	qlen = cl->q->q.qlen;
+	backlog = cl->q->qstats.backlog;
 	qdisc_reset(cl->q);
-	qdisc_tree_decrease_qlen(cl->q, qlen);
+	qdisc_tree_reduce_backlog(cl->q, qlen, backlog);
 
 	if (cl->next_alive)
 		cbq_deactivate_class(cl);
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index c009eb9..3f6437d 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -128,8 +128,8 @@ static void choke_drop_by_idx(struct Qdisc *sch, unsigned int idx)
 		choke_zap_tail_holes(q);
 
 	qdisc_qstats_backlog_dec(sch, skb);
+	qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(skb));
 	qdisc_drop(skb, sch);
-	qdisc_tree_decrease_qlen(sch, 1);
 	--sch->q.qlen;
 }
 
@@ -449,6 +449,7 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt)
 		old = q->tab;
 		if (old) {
 			unsigned int oqlen = sch->q.qlen, tail = 0;
+			unsigned dropped = 0;
 
 			while (q->head != q->tail) {
 				struct sk_buff *skb = q->tab[q->head];
@@ -460,11 +461,12 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt)
 					ntab[tail++] = skb;
 					continue;
 				}
+				dropped += qdisc_pkt_len(skb);
 				qdisc_qstats_backlog_dec(sch, skb);
 				--sch->q.qlen;
 				qdisc_drop(skb, sch);
 			}
-			qdisc_tree_decrease_qlen(sch, oqlen - sch->q.qlen);
+			qdisc_tree_reduce_backlog(sch, oqlen - sch->q.qlen, dropped);
 			q->head = 0;
 			q->tail = tail;
 		}
diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c
index 7a0bdb1..9a9068d 100644
--- a/net/sched/sch_codel.c
+++ b/net/sched/sch_codel.c
@@ -79,12 +79,13 @@ static struct sk_buff *codel_qdisc_dequeue(struct Qdisc *sch)
 
 	skb = codel_dequeue(sch, &q->params, &q->vars, &q->stats, dequeue);
 
-	/* We cant call qdisc_tree_decrease_qlen() if our qlen is 0,
+	/* We cant call qdisc_tree_reduce_backlog() if our qlen is 0,
 	 * or HTB crashes. Defer it for next round.
 	 */
 	if (q->stats.drop_count && sch->q.qlen) {
-		qdisc_tree_decrease_qlen(sch, q->stats.drop_count);
+		qdisc_tree_reduce_backlog(sch, q->stats.drop_count, q->stats.drop_len);
 		q->stats.drop_count = 0;
+		q->stats.drop_len = 0;
 	}
 	if (skb)
 		qdisc_bstats_update(sch, skb);
@@ -115,7 +116,7 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct codel_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_CODEL_MAX + 1];
-	unsigned int qlen;
+	unsigned int qlen, dropped = 0;
 	int err;
 
 	if (!opt)
@@ -149,10 +150,11 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt)
 	while (sch->q.qlen > sch->limit) {
 		struct sk_buff *skb = __skb_dequeue(&sch->q);
 
+		dropped += qdisc_pkt_len(skb);
 		qdisc_qstats_backlog_dec(sch, skb);
 		qdisc_drop(skb, sch);
 	}
-	qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen);
+	qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped);
 
 	sch_tree_unlock(sch);
 	return 0;
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index d4b3f82..e599803 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -53,9 +53,10 @@ static struct drr_class *drr_find_class(struct Qdisc *sch, u32 classid)
 static void drr_purge_queue(struct drr_class *cl)
 {
 	unsigned int len = cl->qdisc->q.qlen;
+	unsigned int backlog = cl->qdisc->qstats.backlog;
 
 	qdisc_reset(cl->qdisc);
-	qdisc_tree_decrease_qlen(cl->qdisc, len);
+	qdisc_tree_reduce_backlog(cl->qdisc, len, backlog);
 }
 
 static const struct nla_policy drr_policy[TCA_DRR_MAX + 1] = {
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index f377702..4816778 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -659,6 +659,7 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt)
 	struct fq_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_FQ_MAX + 1];
 	int err, drop_count = 0;
+	unsigned drop_len = 0;
 	u32 fq_log;
 
 	if (!opt)
@@ -733,10 +734,11 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt)
 
 		if (!skb)
 			break;
+		drop_len += qdisc_pkt_len(skb);
 		kfree_skb(skb);
 		drop_count++;
 	}
-	qdisc_tree_decrease_qlen(sch, drop_count);
+	qdisc_tree_reduce_backlog(sch, drop_count, drop_len);
 
 	sch_tree_unlock(sch);
 	return err;
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 9291598..96971c7 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -173,7 +173,7 @@ static unsigned int fq_codel_drop(struct Qdisc *sch)
 static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 {
 	struct fq_codel_sched_data *q = qdisc_priv(sch);
-	unsigned int idx;
+	unsigned int idx, prev_backlog;
 	struct fq_codel_flow *flow;
 	int uninitialized_var(ret);
 
@@ -201,6 +201,7 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	if (++sch->q.qlen <= sch->limit)
 		return NET_XMIT_SUCCESS;
 
+	prev_backlog = sch->qstats.backlog;
 	q->drop_overlimit++;
 	/* Return Congestion Notification only if we dropped a packet
 	 * from this flow.
@@ -209,7 +210,7 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		return NET_XMIT_CN;
 
 	/* As we dropped a packet, better let upper stack know this */
-	qdisc_tree_decrease_qlen(sch, 1);
+	qdisc_tree_reduce_backlog(sch, 1, prev_backlog - sch->qstats.backlog);
 	return NET_XMIT_SUCCESS;
 }
 
@@ -239,6 +240,7 @@ static struct sk_buff *fq_codel_dequeue(struct Qdisc *sch)
 	struct fq_codel_flow *flow;
 	struct list_head *head;
 	u32 prev_drop_count, prev_ecn_mark;
+	unsigned int prev_backlog;
 
 begin:
 	head = &q->new_flows;
@@ -257,6 +259,7 @@ begin:
 
 	prev_drop_count = q->cstats.drop_count;
 	prev_ecn_mark = q->cstats.ecn_mark;
+	prev_backlog = sch->qstats.backlog;
 
 	skb = codel_dequeue(sch, &q->cparams, &flow->cvars, &q->cstats,
 			    dequeue);
@@ -274,12 +277,14 @@ begin:
 	}
 	qdisc_bstats_update(sch, skb);
 	flow->deficit -= qdisc_pkt_len(skb);
-	/* We cant call qdisc_tree_decrease_qlen() if our qlen is 0,
+	/* We cant call qdisc_tree_reduce_backlog() if our qlen is 0,
 	 * or HTB crashes. Defer it for next round.
 	 */
 	if (q->cstats.drop_count && sch->q.qlen) {
-		qdisc_tree_decrease_qlen(sch, q->cstats.drop_count);
+		qdisc_tree_reduce_backlog(sch, q->cstats.drop_count,
+					  q->cstats.drop_len);
 		q->cstats.drop_count = 0;
+		q->cstats.drop_len = 0;
 	}
 	return skb;
 }
@@ -347,11 +352,13 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt)
 	while (sch->q.qlen > sch->limit) {
 		struct sk_buff *skb = fq_codel_dequeue(sch);
 
+		q->cstats.drop_len += qdisc_pkt_len(skb);
 		kfree_skb(skb);
 		q->cstats.drop_count++;
 	}
-	qdisc_tree_decrease_qlen(sch, q->cstats.drop_count);
+	qdisc_tree_reduce_backlog(sch, q->cstats.drop_count, q->cstats.drop_len);
 	q->cstats.drop_count = 0;
+	q->cstats.drop_len = 0;
 
 	sch_tree_unlock(sch);
 	return 0;
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 134f7d2..d3e21da 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -895,9 +895,10 @@ static void
 hfsc_purge_queue(struct Qdisc *sch, struct hfsc_class *cl)
 {
 	unsigned int len = cl->qdisc->q.qlen;
+	unsigned int backlog = cl->qdisc->qstats.backlog;
 
 	qdisc_reset(cl->qdisc);
-	qdisc_tree_decrease_qlen(cl->qdisc, len);
+	qdisc_tree_reduce_backlog(cl->qdisc, len, backlog);
 }
 
 static void
diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c
index 15d3aab..792c6f3 100644
--- a/net/sched/sch_hhf.c
+++ b/net/sched/sch_hhf.c
@@ -390,6 +390,7 @@ static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	struct hhf_sched_data *q = qdisc_priv(sch);
 	enum wdrr_bucket_idx idx;
 	struct wdrr_bucket *bucket;
+	unsigned int prev_backlog;
 
 	idx = hhf_classify(skb, sch);
 
@@ -417,6 +418,7 @@ static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	if (++sch->q.qlen <= sch->limit)
 		return NET_XMIT_SUCCESS;
 
+	prev_backlog = sch->qstats.backlog;
 	q->drop_overlimit++;
 	/* Return Congestion Notification only if we dropped a packet from this
 	 * bucket.
@@ -425,7 +427,7 @@ static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		return NET_XMIT_CN;
 
 	/* As we dropped a packet, better let upper stack know this. */
-	qdisc_tree_decrease_qlen(sch, 1);
+	qdisc_tree_reduce_backlog(sch, 1, prev_backlog - sch->qstats.backlog);
 	return NET_XMIT_SUCCESS;
 }
 
@@ -535,7 +537,7 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct hhf_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_HHF_MAX + 1];
-	unsigned int qlen;
+	unsigned int qlen, prev_backlog;
 	int err;
 	u64 non_hh_quantum;
 	u32 new_quantum = q->quantum;
@@ -585,12 +587,14 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt)
 	}
 
 	qlen = sch->q.qlen;
+	prev_backlog = sch->qstats.backlog;
 	while (sch->q.qlen > sch->limit) {
 		struct sk_buff *skb = hhf_dequeue(sch);
 
 		kfree_skb(skb);
 	}
-	qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen);
+	qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen,
+				  prev_backlog - sch->qstats.backlog);
 
 	sch_tree_unlock(sch);
 	return 0;
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 520ffe9..6b118b1 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1267,7 +1267,6 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg)
 {
 	struct htb_sched *q = qdisc_priv(sch);
 	struct htb_class *cl = (struct htb_class *)arg;
-	unsigned int qlen;
 	struct Qdisc *new_q = NULL;
 	int last_child = 0;
 
@@ -1287,9 +1286,11 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg)
 	sch_tree_lock(sch);
 
 	if (!cl->level) {
-		qlen = cl->un.leaf.q->q.qlen;
+		unsigned int qlen = cl->un.leaf.q->q.qlen;
+		unsigned int backlog = cl->un.leaf.q->qstats.backlog;
+
 		qdisc_reset(cl->un.leaf.q);
-		qdisc_tree_decrease_qlen(cl->un.leaf.q, qlen);
+		qdisc_tree_reduce_backlog(cl->un.leaf.q, qlen, backlog);
 	}
 
 	/* delete from hash and active; remainder in destroy_class */
@@ -1423,10 +1424,11 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 		sch_tree_lock(sch);
 		if (parent && !parent->level) {
 			unsigned int qlen = parent->un.leaf.q->q.qlen;
+			unsigned int backlog = parent->un.leaf.q->qstats.backlog;
 
 			/* turn parent into inner node */
 			qdisc_reset(parent->un.leaf.q);
-			qdisc_tree_decrease_qlen(parent->un.leaf.q, qlen);
+			qdisc_tree_reduce_backlog(parent->un.leaf.q, qlen, backlog);
 			qdisc_destroy(parent->un.leaf.q);
 			if (parent->prio_activity)
 				htb_deactivate(q, parent);
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index f36ff83..23437d6 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -218,7 +218,8 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt)
 		if (q->queues[i] != &noop_qdisc) {
 			struct Qdisc *child = q->queues[i];
 			q->queues[i] = &noop_qdisc;
-			qdisc_tree_decrease_qlen(child, child->q.qlen);
+			qdisc_tree_reduce_backlog(child, child->q.qlen,
+						  child->qstats.backlog);
 			qdisc_destroy(child);
 		}
 	}
@@ -238,8 +239,9 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt)
 				q->queues[i] = child;
 
 				if (old != &noop_qdisc) {
-					qdisc_tree_decrease_qlen(old,
-								 old->q.qlen);
+					qdisc_tree_reduce_backlog(old,
+								  old->q.qlen,
+								  old->qstats.backlog);
 					qdisc_destroy(old);
 				}
 				sch_tree_unlock(sch);
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 8d56016..cc00329 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -598,7 +598,8 @@ deliver:
 				if (unlikely(err != NET_XMIT_SUCCESS)) {
 					if (net_xmit_drop_count(err)) {
 						qdisc_qstats_drop(sch);
-						qdisc_tree_decrease_qlen(sch, 1);
+						qdisc_tree_reduce_backlog(sch, 1,
+									  qdisc_pkt_len(skb));
 					}
 				}
 				goto tfifo_dequeue;
diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c
index b783a44..71ae3b9 100644
--- a/net/sched/sch_pie.c
+++ b/net/sched/sch_pie.c
@@ -183,7 +183,7 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct pie_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_PIE_MAX + 1];
-	unsigned int qlen;
+	unsigned int qlen, dropped = 0;
 	int err;
 
 	if (!opt)
@@ -232,10 +232,11 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt)
 	while (sch->q.qlen > sch->limit) {
 		struct sk_buff *skb = __skb_dequeue(&sch->q);
 
+		dropped += qdisc_pkt_len(skb);
 		qdisc_qstats_backlog_dec(sch, skb);
 		qdisc_drop(skb, sch);
 	}
-	qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen);
+	qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped);
 
 	sch_tree_unlock(sch);
 	return 0;
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index a677f543a..e671b1a 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -191,7 +191,7 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt)
 		struct Qdisc *child = q->queues[i];
 		q->queues[i] = &noop_qdisc;
 		if (child != &noop_qdisc) {
-			qdisc_tree_decrease_qlen(child, child->q.qlen);
+			qdisc_tree_reduce_backlog(child, child->q.qlen, child->qstats.backlog);
 			qdisc_destroy(child);
 		}
 	}
@@ -210,8 +210,9 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt)
 				q->queues[i] = child;
 
 				if (old != &noop_qdisc) {
-					qdisc_tree_decrease_qlen(old,
-								 old->q.qlen);
+					qdisc_tree_reduce_backlog(old,
+								  old->q.qlen,
+								  old->qstats.backlog);
 					qdisc_destroy(old);
 				}
 				sch_tree_unlock(sch);
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 6fea320..e2b8fd4 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -221,9 +221,10 @@ static struct qfq_class *qfq_find_class(struct Qdisc *sch, u32 classid)
 static void qfq_purge_queue(struct qfq_class *cl)
 {
 	unsigned int len = cl->qdisc->q.qlen;
+	unsigned int backlog = cl->qdisc->qstats.backlog;
 
 	qdisc_reset(cl->qdisc);
-	qdisc_tree_decrease_qlen(cl->qdisc, len);
+	qdisc_tree_reduce_backlog(cl->qdisc, len, backlog);
 }
 
 static const struct nla_policy qfq_policy[TCA_QFQ_MAX + 1] = {
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index d5abcee..8c0508c 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -210,7 +210,8 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt)
 	q->flags = ctl->flags;
 	q->limit = ctl->limit;
 	if (child) {
-		qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen);
+		qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen,
+					  q->qdisc->qstats.backlog);
 		qdisc_destroy(q->qdisc);
 		q->qdisc = child;
 	}
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index fa7f0a3..e1d634e 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -518,7 +518,8 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt)
 
 	sch_tree_lock(sch);
 
-	qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen);
+	qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen,
+				  q->qdisc->qstats.backlog);
 	qdisc_destroy(q->qdisc);
 	q->qdisc = child;
 
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index b877140..4417fb2 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -369,7 +369,7 @@ static int
 sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 {
 	struct sfq_sched_data *q = qdisc_priv(sch);
-	unsigned int hash;
+	unsigned int hash, dropped;
 	sfq_index x, qlen;
 	struct sfq_slot *slot;
 	int uninitialized_var(ret);
@@ -484,7 +484,7 @@ enqueue:
 		return NET_XMIT_SUCCESS;
 
 	qlen = slot->qlen;
-	sfq_drop(sch);
+	dropped = sfq_drop(sch);
 	/* Return Congestion Notification only if we dropped a packet
 	 * from this flow.
 	 */
@@ -492,7 +492,7 @@ enqueue:
 		return NET_XMIT_CN;
 
 	/* As we dropped a packet, better let upper stack know this */
-	qdisc_tree_decrease_qlen(sch, 1);
+	qdisc_tree_reduce_backlog(sch, 1, dropped);
 	return NET_XMIT_SUCCESS;
 }
 
@@ -560,6 +560,7 @@ static void sfq_rehash(struct Qdisc *sch)
 	struct sfq_slot *slot;
 	struct sk_buff_head list;
 	int dropped = 0;
+	unsigned int drop_len = 0;
 
 	__skb_queue_head_init(&list);
 
@@ -588,6 +589,7 @@ static void sfq_rehash(struct Qdisc *sch)
 			if (x >= SFQ_MAX_FLOWS) {
 drop:
 				qdisc_qstats_backlog_dec(sch, skb);
+				drop_len += qdisc_pkt_len(skb);
 				kfree_skb(skb);
 				dropped++;
 				continue;
@@ -617,7 +619,7 @@ drop:
 		}
 	}
 	sch->q.qlen -= dropped;
-	qdisc_tree_decrease_qlen(sch, dropped);
+	qdisc_tree_reduce_backlog(sch, dropped, drop_len);
 }
 
 static void sfq_perturbation(unsigned long arg)
@@ -641,7 +643,7 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt)
 	struct sfq_sched_data *q = qdisc_priv(sch);
 	struct tc_sfq_qopt *ctl = nla_data(opt);
 	struct tc_sfq_qopt_v1 *ctl_v1 = NULL;
-	unsigned int qlen;
+	unsigned int qlen, dropped = 0;
 	struct red_parms *p = NULL;
 
 	if (opt->nla_len < nla_attr_size(sizeof(*ctl)))
@@ -690,8 +692,8 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt)
 
 	qlen = sch->q.qlen;
 	while (sch->q.qlen > q->limit)
-		sfq_drop(sch);
-	qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen);
+		dropped += sfq_drop(sch);
+	qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped);
 
 	del_timer(&q->perturb_timer);
 	if (q->perturb_period) {
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 56a1aef..c2fbde7 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -160,6 +160,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch)
 	struct tbf_sched_data *q = qdisc_priv(sch);
 	struct sk_buff *segs, *nskb;
 	netdev_features_t features = netif_skb_features(skb);
+	unsigned int len = 0, prev_len = qdisc_pkt_len(skb);
 	int ret, nb;
 
 	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
@@ -172,6 +173,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch)
 		nskb = segs->next;
 		segs->next = NULL;
 		qdisc_skb_cb(segs)->pkt_len = segs->len;
+		len += segs->len;
 		ret = qdisc_enqueue(segs, q->qdisc);
 		if (ret != NET_XMIT_SUCCESS) {
 			if (net_xmit_drop_count(ret))
@@ -183,7 +185,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch)
 	}
 	sch->q.qlen += nb;
 	if (nb > 1)
-		qdisc_tree_decrease_qlen(sch, 1 - nb);
+		qdisc_tree_reduce_backlog(sch, 1 - nb, prev_len - len);
 	consume_skb(skb);
 	return nb > 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP;
 }
@@ -399,7 +401,8 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
 
 	sch_tree_lock(sch);
 	if (child) {
-		qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen);
+		qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen,
+					  q->qdisc->qstats.backlog);
 		qdisc_destroy(q->qdisc);
 		q->qdisc = child;
 	}
-- 
2.4.1


From d9cf6335275eb878d5440f5c871b6f107b06dcfa Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Thu, 25 Feb 2016 14:55:02 -0800
Subject: [PATCH 16/26] sch_htb: update backlog as well

[ Upstream commit 431e3a8e36a05a37126f34b41aa3a5a6456af04e ]

We saw qlen!=0 but backlog==0 on our production machine:

qdisc htb 1: dev eth0 root refcnt 2 r2q 10 default 1 direct_packets_stat 0 ver 3.17
 Sent 172680457356 bytes 222469449 pkt (dropped 0, overlimits 123575834 requeues 0)
 backlog 0b 72p requeues 0

The problem is we only count qlen for HTB qdisc but not backlog.
We need to update backlog too when we update qlen, so that we
can at least know the average packet length.

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_htb.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 6b118b1..ccff006 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -600,6 +600,7 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		htb_activate(q, cl);
 	}
 
+	qdisc_qstats_backlog_inc(sch, skb);
 	sch->q.qlen++;
 	return NET_XMIT_SUCCESS;
 }
@@ -889,6 +890,7 @@ static struct sk_buff *htb_dequeue(struct Qdisc *sch)
 ok:
 		qdisc_bstats_update(sch, skb);
 		qdisc_unthrottled(sch);
+		qdisc_qstats_backlog_dec(sch, skb);
 		sch->q.qlen--;
 		return skb;
 	}
@@ -955,6 +957,7 @@ static unsigned int htb_drop(struct Qdisc *sch)
 			unsigned int len;
 			if (cl->un.leaf.q->ops->drop &&
 			    (len = cl->un.leaf.q->ops->drop(cl->un.leaf.q))) {
+				sch->qstats.backlog -= len;
 				sch->q.qlen--;
 				if (!cl->un.leaf.q->q.qlen)
 					htb_deactivate(q, cl);
@@ -984,12 +987,12 @@ static void htb_reset(struct Qdisc *sch)
 			}
 			cl->prio_activity = 0;
 			cl->cmode = HTB_CAN_SEND;
-
 		}
 	}
 	qdisc_watchdog_cancel(&q->watchdog);
 	__skb_queue_purge(&q->direct_queue);
 	sch->q.qlen = 0;
+	sch->qstats.backlog = 0;
 	memset(q->hlevel, 0, sizeof(q->hlevel));
 	memset(q->row_mask, 0, sizeof(q->row_mask));
 	for (i = 0; i < TC_HTB_NUMPRIO; i++)
-- 
2.4.1


From 64b9c6b1c0d94bd8276d45fe591a1c8a5b5e231e Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Thu, 25 Feb 2016 14:55:03 -0800
Subject: [PATCH 17/26] sch_dsmark: update backlog as well

[ Upstream commit bdf17661f63a79c3cb4209b970b1cc39e34f7543 ]

Similarly, we need to update backlog too when we update qlen.

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_dsmark.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index d2084e7..7288dda 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -256,6 +256,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		return err;
 	}
 
+	qdisc_qstats_backlog_inc(sch, skb);
 	sch->q.qlen++;
 
 	return NET_XMIT_SUCCESS;
@@ -278,6 +279,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch)
 		return NULL;
 
 	qdisc_bstats_update(sch, skb);
+	qdisc_qstats_backlog_dec(sch, skb);
 	sch->q.qlen--;
 
 	index = skb->tc_index & (p->indices - 1);
@@ -393,6 +395,7 @@ static void dsmark_reset(struct Qdisc *sch)
 
 	pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p);
 	qdisc_reset(p->q);
+	sch->qstats.backlog = 0;
 	sch->q.qlen = 0;
 }
 
-- 
2.4.1


From 19f934fe07aa3cab290d304515cf2f0013107280 Mon Sep 17 00:00:00 2001
From: Neil Horman <nhorman@tuxdriver.com>
Date: Mon, 2 May 2016 12:20:15 -0400
Subject: [PATCH 18/26] netem: Segment GSO packets on enqueue

[ Upstream commit 6071bd1aa13ed9e41824bafad845b7b7f4df5cfd ]

This was recently reported to me, and reproduced on the latest net kernel,
when attempting to run netperf from a host that had a netem qdisc attached
to the egress interface:

[  788.073771] ---------------------[ cut here ]---------------------------
[  788.096716] WARNING: at net/core/dev.c:2253 skb_warn_bad_offload+0xcd/0xda()
[  788.129521] bnx2: caps=(0x00000001801949b3, 0x0000000000000000) len=2962
data_len=0 gso_size=1448 gso_type=1 ip_summed=3
[  788.182150] Modules linked in: sch_netem kvm_amd kvm crc32_pclmul ipmi_ssif
ghash_clmulni_intel sp5100_tco amd64_edac_mod aesni_intel lrw gf128mul
glue_helper ablk_helper edac_mce_amd cryptd pcspkr sg edac_core hpilo ipmi_si
i2c_piix4 k10temp fam15h_power hpwdt ipmi_msghandler shpchp acpi_power_meter
pcc_cpufreq nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c
sd_mod crc_t10dif crct10dif_generic mgag200 syscopyarea sysfillrect sysimgblt
i2c_algo_bit drm_kms_helper ahci ata_generic pata_acpi ttm libahci
crct10dif_pclmul pata_atiixp tg3 libata crct10dif_common drm crc32c_intel ptp
serio_raw bnx2 r8169 hpsa pps_core i2c_core mii dm_mirror dm_region_hash dm_log
dm_mod
[  788.465294] CPU: 16 PID: 0 Comm: swapper/16 Tainted: G        W
------------   3.10.0-327.el7.x86_64 #1
[  788.511521] Hardware name: HP ProLiant DL385p Gen8, BIOS A28 12/17/2012
[  788.542260]  ffff880437c036b8 f7afc56532a53db9 ffff880437c03670
ffffffff816351f1
[  788.576332]  ffff880437c036a8 ffffffff8107b200 ffff880633e74200
ffff880231674000
[  788.611943]  0000000000000001 0000000000000003 0000000000000000
ffff880437c03710
[  788.647241] Call Trace:
[  788.658817]  <IRQ>  [<ffffffff816351f1>] dump_stack+0x19/0x1b
[  788.686193]  [<ffffffff8107b200>] warn_slowpath_common+0x70/0xb0
[  788.713803]  [<ffffffff8107b29c>] warn_slowpath_fmt+0x5c/0x80
[  788.741314]  [<ffffffff812f92f3>] ? ___ratelimit+0x93/0x100
[  788.767018]  [<ffffffff81637f49>] skb_warn_bad_offload+0xcd/0xda
[  788.796117]  [<ffffffff8152950c>] skb_checksum_help+0x17c/0x190
[  788.823392]  [<ffffffffa01463a1>] netem_enqueue+0x741/0x7c0 [sch_netem]
[  788.854487]  [<ffffffff8152cb58>] dev_queue_xmit+0x2a8/0x570
[  788.880870]  [<ffffffff8156ae1d>] ip_finish_output+0x53d/0x7d0
...

The problem occurs because netem is not prepared to handle GSO packets (as it
uses skb_checksum_help in its enqueue path, which cannot manipulate these
frames).

The solution I think is to simply segment the skb in a simmilar fashion to the
way we do in __dev_queue_xmit (via validate_xmit_skb), with some minor changes.
When we decide to corrupt an skb, if the frame is GSO, we segment it, corrupt
the first segment, and enqueue the remaining ones.

tested successfully by myself on the latest net kernel, to which this applies

Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
CC: Jamal Hadi Salim <jhs@mojatatu.com>
CC: "David S. Miller" <davem@davemloft.net>
CC: netem@lists.linux-foundation.org
CC: eric.dumazet@gmail.com
CC: stephen@networkplumber.org
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_netem.c | 61 +++++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 59 insertions(+), 2 deletions(-)

diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index cc00329..80124c1 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -395,6 +395,25 @@ static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch)
 	sch->q.qlen++;
 }
 
+/* netem can't properly corrupt a megapacket (like we get from GSO), so instead
+ * when we statistically choose to corrupt one, we instead segment it, returning
+ * the first packet to be corrupted, and re-enqueue the remaining frames
+ */
+static struct sk_buff *netem_segment(struct sk_buff *skb, struct Qdisc *sch)
+{
+	struct sk_buff *segs;
+	netdev_features_t features = netif_skb_features(skb);
+
+	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+
+	if (IS_ERR_OR_NULL(segs)) {
+		qdisc_reshape_fail(skb, sch);
+		return NULL;
+	}
+	consume_skb(skb);
+	return segs;
+}
+
 /*
  * Insert one skb into qdisc.
  * Note: parent depends on return value to account for queue length.
@@ -407,7 +426,11 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	/* We don't fill cb now as skb_unshare() may invalidate it */
 	struct netem_skb_cb *cb;
 	struct sk_buff *skb2;
+	struct sk_buff *segs = NULL;
+	unsigned int len = 0, last_len, prev_len = qdisc_pkt_len(skb);
+	int nb = 0;
 	int count = 1;
+	int rc = NET_XMIT_SUCCESS;
 
 	/* Random duplication */
 	if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor))
@@ -453,10 +476,23 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	 * do it now in software before we mangle it.
 	 */
 	if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor)) {
+		if (skb_is_gso(skb)) {
+			segs = netem_segment(skb, sch);
+			if (!segs)
+				return NET_XMIT_DROP;
+		} else {
+			segs = skb;
+		}
+
+		skb = segs;
+		segs = segs->next;
+
 		if (!(skb = skb_unshare(skb, GFP_ATOMIC)) ||
 		    (skb->ip_summed == CHECKSUM_PARTIAL &&
-		     skb_checksum_help(skb)))
-			return qdisc_drop(skb, sch);
+		     skb_checksum_help(skb))) {
+			rc = qdisc_drop(skb, sch);
+			goto finish_segs;
+		}
 
 		skb->data[prandom_u32() % skb_headlen(skb)] ^=
 			1<<(prandom_u32() % 8);
@@ -516,6 +552,27 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		sch->qstats.requeues++;
 	}
 
+finish_segs:
+	if (segs) {
+		while (segs) {
+			skb2 = segs->next;
+			segs->next = NULL;
+			qdisc_skb_cb(segs)->pkt_len = segs->len;
+			last_len = segs->len;
+			rc = qdisc_enqueue(segs, sch);
+			if (rc != NET_XMIT_SUCCESS) {
+				if (net_xmit_drop_count(rc))
+					qdisc_qstats_drop(sch);
+			} else {
+				nb++;
+				len += last_len;
+			}
+			segs = skb2;
+		}
+		sch->q.qlen += nb;
+		if (nb > 1)
+			qdisc_tree_reduce_backlog(sch, 1 - nb, prev_len - len);
+	}
 	return NET_XMIT_SUCCESS;
 }
 
-- 
2.4.1


From 08b9c73b7d8e06cc9f08a242f7b555aa5d8e8b6d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 3 May 2016 16:38:53 +0200
Subject: [PATCH 19/26] net: fec: only clear a queue's work bit if the queue
 was emptied
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 1c021bb717a70aaeaa4b25c91f43c2aeddd922de ]

In the receive path a queue's work bit was cleared unconditionally even
if fec_enet_rx_queue only read out a part of the available packets from
the hardware. This resulted in not reading any packets in the next napi
turn and so packets were delayed or lost.

The obvious fix is to only clear a queue's bit when the queue was
emptied.

Fixes: 4d494cdc92b3 ("net: fec: change data structure to support multiqueue")
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Lucas Stach <l.stach@pengutronix.de>
Tested-by: Fugang Duan <fugang.duan@nxp.com>
Acked-by: Fugang Duan <fugang.duan@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_main.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 570390b..67aec18 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -1546,9 +1546,15 @@ fec_enet_rx(struct net_device *ndev, int budget)
 	struct fec_enet_private *fep = netdev_priv(ndev);
 
 	for_each_set_bit(queue_id, &fep->work_rx, FEC_ENET_MAX_RX_QS) {
-		clear_bit(queue_id, &fep->work_rx);
-		pkt_received += fec_enet_rx_queue(ndev,
+		int ret;
+
+		ret = fec_enet_rx_queue(ndev,
 					budget - pkt_received, queue_id);
+
+		if (ret < budget - pkt_received)
+			clear_bit(queue_id, &fep->work_rx);
+
+		pkt_received += ret;
 	}
 	return pkt_received;
 }
-- 
2.4.1


From e8f0966da75008940970f05e53e9cd836aa53596 Mon Sep 17 00:00:00 2001
From: Kangjie Lu <kangjielu@gmail.com>
Date: Tue, 3 May 2016 16:35:05 -0400
Subject: [PATCH 20/26] net: fix infoleak in llc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit b8670c09f37bdf2847cc44f36511a53afc6161fd ]

The stack object “info” has a total size of 12 bytes. Its last byte
is padding which is not initialized and leaked via “put_cmsg”.

Signed-off-by: Kangjie Lu <kjlu@gatech.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/llc/af_llc.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 17a8dff..c58f242 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -626,6 +626,7 @@ static void llc_cmsg_rcv(struct msghdr *msg, struct sk_buff *skb)
 	if (llc->cmsg_flags & LLC_CMSG_PKTINFO) {
 		struct llc_pktinfo info;
 
+		memset(&info, 0, sizeof(info));
 		info.lpi_ifindex = llc_sk(skb->sk)->dev->ifindex;
 		llc_pdu_decode_dsap(skb, &info.lpi_sap);
 		llc_pdu_decode_da(skb, info.lpi_mac);
-- 
2.4.1


From 4cd23b729e675f437b225791a104870cf495d3b9 Mon Sep 17 00:00:00 2001
From: Kangjie Lu <kangjielu@gmail.com>
Date: Tue, 3 May 2016 16:46:24 -0400
Subject: [PATCH 21/26] net: fix infoleak in rtnetlink
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 5f8e44741f9f216e33736ea4ec65ca9ac03036e6 ]

The stack object “map” has a total size of 32 bytes. Its last 4
bytes are padding generated by compiler. These padding bytes are
not initialized and sent out via “nla_put”.

Signed-off-by: Kangjie Lu <kjlu@gatech.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index fe95cb7..a8804c4 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1070,14 +1070,16 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 		goto nla_put_failure;
 
 	if (1) {
-		struct rtnl_link_ifmap map = {
-			.mem_start   = dev->mem_start,
-			.mem_end     = dev->mem_end,
-			.base_addr   = dev->base_addr,
-			.irq         = dev->irq,
-			.dma         = dev->dma,
-			.port        = dev->if_port,
-		};
+		struct rtnl_link_ifmap map;
+
+		memset(&map, 0, sizeof(map));
+		map.mem_start   = dev->mem_start;
+		map.mem_end     = dev->mem_end;
+		map.base_addr   = dev->base_addr;
+		map.irq         = dev->irq;
+		map.dma         = dev->dma;
+		map.port        = dev->if_port;
+
 		if (nla_put(skb, IFLA_MAP, sizeof(map), &map))
 			goto nla_put_failure;
 	}
-- 
2.4.1


From 5e55e6a5f60c05574c290394d43370c5714173d5 Mon Sep 17 00:00:00 2001
From: Daniel Jurgens <danielj@mellanox.com>
Date: Wed, 4 May 2016 15:00:33 +0300
Subject: [PATCH 22/26] net/mlx4_en: Fix endianness bug in IPV6 csum
 calculation

[ Upstream commit 82d69203df634b4dfa765c94f60ce9482bcc44d6 ]

Use htons instead of unconditionally byte swapping nexthdr.  On a little
endian systems shifting the byte is correct behavior, but it results in
incorrect csums on big endian architectures.

Fixes: f8c6455bb04b ('net/mlx4_en: Extend checksum offloading by CHECKSUM COMPLETE')
Signed-off-by: Daniel Jurgens <danielj@mellanox.com>
Reviewed-by: Carol Soto <clsoto@us.ibm.com>
Tested-by: Carol Soto <clsoto@us.ibm.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_rx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 80aac20..f6095d2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -710,7 +710,7 @@ static int get_fixed_ipv6_csum(__wsum hw_checksum, struct sk_buff *skb,
 
 	if (ipv6h->nexthdr == IPPROTO_FRAGMENT || ipv6h->nexthdr == IPPROTO_HOPOPTS)
 		return -1;
-	hw_checksum = csum_add(hw_checksum, (__force __wsum)(ipv6h->nexthdr << 8));
+	hw_checksum = csum_add(hw_checksum, (__force __wsum)htons(ipv6h->nexthdr));
 
 	csum_pseudo_hdr = csum_partial(&ipv6h->saddr,
 				       sizeof(ipv6h->saddr) + sizeof(ipv6h->daddr), 0);
-- 
2.4.1


From bd4043f5f9bd8b47c1839738a3afa016758493aa Mon Sep 17 00:00:00 2001
From: Ian Campbell <ian.campbell@docker.com>
Date: Wed, 4 May 2016 14:21:53 +0100
Subject: [PATCH 23/26] VSOCK: do not disconnect socket when peer has shutdown
 SEND only

[ Upstream commit dedc58e067d8c379a15a8a183c5db318201295bb ]

The peer may be expecting a reply having sent a request and then done a
shutdown(SHUT_WR), so tearing down the whole socket at this point seems
wrong and breaks for me with a client which does a SHUT_WR.

Looking at other socket family's stream_recvmsg callbacks doing a shutdown
here does not seem to be the norm and removing it does not seem to have
had any adverse effects that I can see.

I'm using Stefan's RFC virtio transport patches, I'm unsure of the impact
on the vmci transport.

Signed-off-by: Ian Campbell <ian.campbell@docker.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Stefan Hajnoczi <stefanha@redhat.com>
Cc: Claudio Imbrenda <imbrenda@linux.vnet.ibm.com>
Cc: Andy King <acking@vmware.com>
Cc: Dmitry Torokhov <dtor@vmware.com>
Cc: Jorgen Hansen <jhansen@vmware.com>
Cc: Adit Ranadive <aditr@vmware.com>
Cc: netdev@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/vmw_vsock/af_vsock.c | 21 +--------------------
 1 file changed, 1 insertion(+), 20 deletions(-)

diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 2ec86e6..e1c69b2 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1794,27 +1794,8 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	else if (sk->sk_shutdown & RCV_SHUTDOWN)
 		err = 0;
 
-	if (copied > 0) {
-		/* We only do these additional bookkeeping/notification steps
-		 * if we actually copied something out of the queue pair
-		 * instead of just peeking ahead.
-		 */
-
-		if (!(flags & MSG_PEEK)) {
-			/* If the other side has shutdown for sending and there
-			 * is nothing more to read, then modify the socket
-			 * state.
-			 */
-			if (vsk->peer_shutdown & SEND_SHUTDOWN) {
-				if (vsock_stream_has_data(vsk) <= 0) {
-					sk->sk_state = SS_UNCONNECTED;
-					sock_set_flag(sk, SOCK_DONE);
-					sk->sk_state_change(sk);
-				}
-			}
-		}
+	if (copied > 0)
 		err = copied;
-	}
 
 out_wait:
 	finish_wait(sk_sleep(sk), &wait);
-- 
2.4.1


From fbf3121d82820bd0025a1b0c98f34f6a1c161ec5 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Wed, 4 May 2016 16:18:45 +0200
Subject: [PATCH 24/26] net: bridge: fix old ioctl unlocked net device walk

[ Upstream commit 31ca0458a61a502adb7ed192bf9716c6d05791a5 ]

get_bridge_ifindices() is used from the old "deviceless" bridge ioctl
calls which aren't called with rtnl held. The comment above says that it is
called with rtnl but that is not really the case.
Here's a sample output from a test ASSERT_RTNL() which I put in
get_bridge_ifindices and executed "brctl show":
[  957.422726] RTNL: assertion failed at net/bridge//br_ioctl.c (30)
[  957.422925] CPU: 0 PID: 1862 Comm: brctl Tainted: G        W  O
4.6.0-rc4+ #157
[  957.423009] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996),
BIOS 1.8.1-20150318_183358- 04/01/2014
[  957.423009]  0000000000000000 ffff880058adfdf0 ffffffff8138dec5
0000000000000400
[  957.423009]  ffffffff81ce8380 ffff880058adfe58 ffffffffa05ead32
0000000000000001
[  957.423009]  00007ffec1a444b0 0000000000000400 ffff880053c19130
0000000000008940
[  957.423009] Call Trace:
[  957.423009]  [<ffffffff8138dec5>] dump_stack+0x85/0xc0
[  957.423009]  [<ffffffffa05ead32>]
br_ioctl_deviceless_stub+0x212/0x2e0 [bridge]
[  957.423009]  [<ffffffff81515beb>] sock_ioctl+0x22b/0x290
[  957.423009]  [<ffffffff8126ba75>] do_vfs_ioctl+0x95/0x700
[  957.423009]  [<ffffffff8126c159>] SyS_ioctl+0x79/0x90
[  957.423009]  [<ffffffff8163a4c0>] entry_SYSCALL_64_fastpath+0x23/0xc1

Since it only reads bridge ifindices, we can use rcu to safely walk the net
device list. Also remove the wrong rtnl comment above.

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_ioctl.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c
index 8d423bc..f876f70 100644
--- a/net/bridge/br_ioctl.c
+++ b/net/bridge/br_ioctl.c
@@ -21,18 +21,19 @@
 #include <asm/uaccess.h>
 #include "br_private.h"
 
-/* called with RTNL */
 static int get_bridge_ifindices(struct net *net, int *indices, int num)
 {
 	struct net_device *dev;
 	int i = 0;
 
-	for_each_netdev(net, dev) {
+	rcu_read_lock();
+	for_each_netdev_rcu(net, dev) {
 		if (i >= num)
 			break;
 		if (dev->priv_flags & IFF_EBRIDGE)
 			indices[i++] = dev->ifindex;
 	}
+	rcu_read_unlock();
 
 	return i;
 }
-- 
2.4.1


From b94939152a6c6cb8c9dd6bef1b1f971b2c1bfc2a Mon Sep 17 00:00:00 2001
From: Kangjie Lu <kangjielu@gmail.com>
Date: Sun, 8 May 2016 12:10:14 -0400
Subject: [PATCH 25/26] net: fix a kernel infoleak in x25 module

[ Upstream commit 79e48650320e6fba48369fccf13fd045315b19b8 ]

Stack object "dte_facilities" is allocated in x25_rx_call_request(),
which is supposed to be initialized in x25_negotiate_facilities.
However, 5 fields (8 bytes in total) are not initialized. This
object is then copied to userland via copy_to_user, thus infoleak
occurs.

Signed-off-by: Kangjie Lu <kjlu@gatech.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/x25/x25_facilities.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/x25/x25_facilities.c b/net/x25/x25_facilities.c
index 7ecd04c..997ff7b 100644
--- a/net/x25/x25_facilities.c
+++ b/net/x25/x25_facilities.c
@@ -277,6 +277,7 @@ int x25_negotiate_facilities(struct sk_buff *skb, struct sock *sk,
 
 	memset(&theirs, 0, sizeof(theirs));
 	memcpy(new, ours, sizeof(*new));
+	memset(dte, 0, sizeof(*dte));
 
 	len = x25_parse_facilities(skb, &theirs, dte, &x25->vc_facil_mask);
 	if (len < 0)
-- 
2.4.1


From 2746dccd5b72bbf41a4938e3d44d4ba8712826ad Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 9 May 2016 20:55:16 -0700
Subject: [PATCH 26/26] tcp: refresh skb timestamp at retransmit time

[ Upstream commit 10a81980fc47e64ffac26a073139813d3f697b64 ]

In the very unlikely case __tcp_retransmit_skb() can not use the cloning
done in tcp_transmit_skb(), we need to refresh skb_mstamp before doing
the copy and transmit, otherwise TCP TS val will be an exact copy of
original transmit.

Fixes: 7faee5c0d514 ("tcp: remove TCP_SKB_CB(skb)->when")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 1ea4322..ae66c84 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2627,8 +2627,10 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 	 */
 	if (unlikely((NET_IP_ALIGN && ((unsigned long)skb->data & 3)) ||
 		     skb_headroom(skb) >= 0xFFFF)) {
-		struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER,
-						   GFP_ATOMIC);
+		struct sk_buff *nskb;
+
+		skb_mstamp_get(&skb->skb_mstamp);
+		nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC);
 		err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
 			     -ENOBUFS;
 	} else {
-- 
2.4.1


[-- Attachment #3: net_44.mbox --]
[-- Type: Application/Octet-Stream, Size: 123083 bytes --]

From cb76fe0168c41ef34ba6ecca8107a5aa16890cbf Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sun, 10 Apr 2016 23:01:30 -0400
Subject: [PATCH 01/38] decnet: Do not build routes to devices without decnet
 private data.

[ Upstream commit a36a0d4008488fa545c74445d69eaf56377d5d4e ]

In particular, make sure we check for decnet private presence
for loopback devices.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/decnet/dn_route.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index 607a14f..b1dc096 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -1034,10 +1034,13 @@ source_ok:
 	if (!fld.daddr) {
 		fld.daddr = fld.saddr;
 
-		err = -EADDRNOTAVAIL;
 		if (dev_out)
 			dev_put(dev_out);
+		err = -EINVAL;
 		dev_out = init_net.loopback_dev;
+		if (!dev_out->dn_ptr)
+			goto out;
+		err = -EADDRNOTAVAIL;
 		dev_hold(dev_out);
 		if (!fld.daddr) {
 			fld.daddr =
@@ -1110,6 +1113,8 @@ source_ok:
 		if (dev_out == NULL)
 			goto out;
 		dn_db = rcu_dereference_raw(dev_out->dn_ptr);
+		if (!dn_db)
+			goto e_inval;
 		/* Possible improvement - check all devices for local addr */
 		if (dn_dev_islocal(dev_out, fld.daddr)) {
 			dev_put(dev_out);
@@ -1151,6 +1156,8 @@ select_source:
 			dev_put(dev_out);
 		dev_out = init_net.loopback_dev;
 		dev_hold(dev_out);
+		if (!dev_out->dn_ptr)
+			goto e_inval;
 		fld.flowidn_oif = dev_out->ifindex;
 		if (res.fi)
 			dn_fib_info_put(res.fi);
-- 
2.1.0


From 0b554e9c53d5a44f7b5d06e9469c1566621f46af Mon Sep 17 00:00:00 2001
From: Chris Friesen <chris.friesen@windriver.com>
Date: Fri, 8 Apr 2016 15:21:30 -0600
Subject: [PATCH 02/38] route: do not cache fib route info on local routes with
 oif

[ Upstream commit d6d5e999e5df67f8ec20b6be45e2229455ee3699 ]

For local routes that require a particular output interface we do not want
to cache the result.  Caching the result causes incorrect behaviour when
there are multiple source addresses on the interface.  The end result
being that if the intended recipient is waiting on that interface for the
packet he won't receive it because it will be delivered on the loopback
interface and the IP_PKTINFO ipi_ifindex will be set to the loopback
interface as well.

This can be tested by running a program such as "dhcp_release" which
attempts to inject a packet on a particular interface so that it is
received by another program on the same board.  The receiving process
should see an IP_PKTINFO ipi_ifndex value of the source interface
(e.g., eth1) instead of the loopback interface (e.g., lo).  The packet
will still appear on the loopback interface in tcpdump but the important
aspect is that the CMSG info is correct.

Sample dhcp_release command line:

   dhcp_release eth1 192.168.204.222 02:11:33:22:44:66

Signed-off-by: Allain Legacy <allain.legacy@windriver.com>
Signed off-by: Chris Friesen <chris.friesen@windriver.com>
Reviewed-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 02c6229..b050cf9 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2045,6 +2045,18 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 		 */
 		if (fi && res->prefixlen < 4)
 			fi = NULL;
+	} else if ((type == RTN_LOCAL) && (orig_oif != 0) &&
+		   (orig_oif != dev_out->ifindex)) {
+		/* For local routes that require a particular output interface
+		 * we do not want to cache the result.  Caching the result
+		 * causes incorrect behaviour when there are multiple source
+		 * addresses on the interface, the end result being that if the
+		 * intended recipient is waiting on that interface for the
+		 * packet he won't receive it because it will be delivered on
+		 * the loopback interface and the IP_PKTINFO ipi_ifindex will
+		 * be set to the loopback interface as well.
+		 */
+		fi = NULL;
 	}
 
 	fnhe = NULL;
-- 
2.1.0


From 0de87011f566fca3112dfcb7629ae0fada1b8424 Mon Sep 17 00:00:00 2001
From: Mathias Krause <minipli@googlemail.com>
Date: Sun, 10 Apr 2016 12:52:28 +0200
Subject: [PATCH 03/38] packet: fix heap info leak in PACKET_DIAG_MCLIST
 sock_diag interface

[ Upstream commit 309cf37fe2a781279b7675d4bb7173198e532867 ]

Because we miss to wipe the remainder of i->addr[] in packet_mc_add(),
pdiag_put_mclist() leaks uninitialized heap bytes via the
PACKET_DIAG_MCLIST netlink attribute.

Fix this by explicitly memset(0)ing the remaining bytes in i->addr[].

Fixes: eea68e2f1a00 ("packet: Report socket mclist info via diag module")
Signed-off-by: Mathias Krause <minipli@googlemail.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Acked-by: Pavel Emelyanov <xemul@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index da1ae0e1..9cc7b51 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3436,6 +3436,7 @@ static int packet_mc_add(struct sock *sk, struct packet_mreq_max *mreq)
 	i->ifindex = mreq->mr_ifindex;
 	i->alen = mreq->mr_alen;
 	memcpy(i->addr, mreq->mr_address, i->alen);
+	memset(i->addr + i->alen, 0, sizeof(i->addr) - i->alen);
 	i->count = 1;
 	i->next = po->mclist;
 	po->mclist = i;
-- 
2.1.0


From 8f2fa1630d6f0ef24e2ec8bda4a41948a22e4fef Mon Sep 17 00:00:00 2001
From: Lars Persson <lars.persson@axis.com>
Date: Tue, 12 Apr 2016 08:45:52 +0200
Subject: [PATCH 04/38] net: sched: do not requeue a NULL skb

[ Upstream commit 3dcd493fbebfd631913df6e2773cc295d3bf7d22 ]

A failure in validate_xmit_skb_list() triggered an unconditional call
to dev_requeue_skb with skb=NULL. This slowly grows the queue
discipline's qlen count until all traffic through the queue stops.

We take the optimistic approach and continue running the queue after a
failure since it is unknown if later packets also will fail in the
validate path.

Fixes: 55a93b3ea780 ("qdisc: validate skb without holding lock")
Signed-off-by: Lars Persson <larper@axis.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_generic.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 16bc83b..aa47250 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -159,12 +159,15 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
 	if (validate)
 		skb = validate_xmit_skb_list(skb, dev);
 
-	if (skb) {
+	if (likely(skb)) {
 		HARD_TX_LOCK(dev, txq, smp_processor_id());
 		if (!netif_xmit_frozen_or_stopped(txq))
 			skb = dev_hard_start_xmit(skb, dev, txq, &ret);
 
 		HARD_TX_UNLOCK(dev, txq);
+	} else {
+		spin_lock(root_lock);
+		return qdisc_qlen(q);
 	}
 	spin_lock(root_lock);
 
-- 
2.1.0


From 5b3f42ca1141370a3d0939ce253c7e5cc8e45c57 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@fb.com>
Date: Tue, 12 Apr 2016 10:26:19 -0700
Subject: [PATCH 05/38] bpf/verifier: reject invalid LD_ABS | BPF_DW
 instruction

[ Upstream commit d82bccc69041a51f7b7b9b4a36db0772f4cdba21 ]

verifier must check for reserved size bits in instruction opcode and
reject BPF_LD | BPF_ABS | BPF_DW and BPF_LD | BPF_IND | BPF_DW instructions,
otherwise interpreter will WARN_RATELIMIT on them during execution.

Fixes: ddd872bc3098 ("bpf: verifier: add checks for BPF_ABS | BPF_IND instructions")
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 2e7f7ab..c21cb14 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1348,6 +1348,7 @@ static int check_ld_abs(struct verifier_env *env, struct bpf_insn *insn)
 	}
 
 	if (insn->dst_reg != BPF_REG_0 || insn->off != 0 ||
+	    BPF_SIZE(insn->code) == BPF_DW ||
 	    (mode == BPF_ABS && insn->src_reg != BPF_REG_0)) {
 		verbose("BPF_LD_ABS uses reserved fields\n");
 		return -EINVAL;
-- 
2.1.0


From 0d215079d8e2727a0b15d555bc406c19af631d3a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Tue, 12 Apr 2016 16:11:12 +0200
Subject: [PATCH 06/38] cdc_mbim: apply "NDP to end" quirk to all Huawei
 devices
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit c5b5343cfbc9f46af65033fa4f407d7b7d98371d ]

We now have a positive report of another Huawei device needing
this quirk: The ME906s-158 (12d1:15c1).  This is an m.2 form
factor modem with no obvious relationship to the E3372 (12d1:157d)
we already have a quirk entry for.  This is reason enough to
believe the quirk might be necessary for any number of current
and future Huawei devices.

Applying the quirk to all Huawei devices, since it is crucial
to any device affected by the firmware bug, while the impact
on non-affected devices is negligible.

The quirk can if necessary be disabled per-device by writing
N to /sys/class/net/<iface>/cdc_ncm/ndp_to_end

Reported-by: Andreas Fett <andreas.fett@secunet.com>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_mbim.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c
index bdd83d9..96a5028 100644
--- a/drivers/net/usb/cdc_mbim.c
+++ b/drivers/net/usb/cdc_mbim.c
@@ -617,8 +617,13 @@ static const struct usb_device_id mbim_devs[] = {
 	{ USB_VENDOR_AND_INTERFACE_INFO(0x0bdb, USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE),
 	  .driver_info = (unsigned long)&cdc_mbim_info,
 	},
-	/* Huawei E3372 fails unless NDP comes after the IP packets */
-	{ USB_DEVICE_AND_INTERFACE_INFO(0x12d1, 0x157d, USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE),
+
+	/* Some Huawei devices, ME906s-158 (12d1:15c1) and E3372
+	 * (12d1:157d), are known to fail unless the NDP is placed
+	 * after the IP packets.  Applying the quirk to all Huawei
+	 * devices is broader than necessary, but harmless.
+	 */
+	{ USB_VENDOR_AND_INTERFACE_INFO(0x12d1, USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE),
 	  .driver_info = (unsigned long)&cdc_mbim_info_ndp_to_end,
 	},
 	/* default entry */
-- 
2.1.0


From 70898c96761332ebb533641255e06480b35e941d Mon Sep 17 00:00:00 2001
From: Craig Gallek <kraig@google.com>
Date: Tue, 12 Apr 2016 13:11:25 -0400
Subject: [PATCH 07/38] soreuseport: fix ordering for mixed v4/v6 sockets
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit d894ba18d4e449b3a7f6eb491f16c9e02933736e ]

With the SO_REUSEPORT socket option, it is possible to create sockets
in the AF_INET and AF_INET6 domains which are bound to the same IPv4 address.
This is only possible with SO_REUSEPORT and when not using IPV6_V6ONLY on
the AF_INET6 sockets.

Prior to the commits referenced below, an incoming IPv4 packet would
always be routed to a socket of type AF_INET when this mixed-mode was used.
After those changes, the same packet would be routed to the most recently
bound socket (if this happened to be an AF_INET6 socket, it would
have an IPv4 mapped IPv6 address).

The change in behavior occurred because the recent SO_REUSEPORT optimizations
short-circuit the socket scoring logic as soon as they find a match.  They
did not take into account the scoring logic that favors AF_INET sockets
over AF_INET6 sockets in the event of a tie.

To fix this problem, this patch changes the insertion order of AF_INET
and AF_INET6 addresses in the TCP and UDP socket lists when the sockets
have SO_REUSEPORT set.  AF_INET sockets will be inserted at the head of the
list and AF_INET6 sockets with SO_REUSEPORT set will always be inserted at
the tail of the list.  This will force AF_INET sockets to always be
considered first.

Fixes: e32ea7e74727 ("soreuseport: fast reuseport UDP socket selection")
Fixes: 125e80b88687 ("soreuseport: fast reuseport TCP socket selection")

Reported-by: Maciej Żenczykowski <maze@google.com>
Signed-off-by: Craig Gallek <kraig@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rculist_nulls.h | 39 +++++++++++++++++++++++++++++++++++++++
 include/net/sock.h            |  6 +++++-
 net/ipv4/udp.c                |  9 +++++++--
 3 files changed, 51 insertions(+), 3 deletions(-)

diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h
index 1c33dd7..4ae95f7 100644
--- a/include/linux/rculist_nulls.h
+++ b/include/linux/rculist_nulls.h
@@ -98,6 +98,45 @@ static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n,
 	if (!is_a_nulls(first))
 		first->pprev = &n->next;
 }
+
+/**
+ * hlist_nulls_add_tail_rcu
+ * @n: the element to add to the hash list.
+ * @h: the list to add to.
+ *
+ * Description:
+ * Adds the specified element to the end of the specified hlist_nulls,
+ * while permitting racing traversals.  NOTE: tail insertion requires
+ * list traversal.
+ *
+ * The caller must take whatever precautions are necessary
+ * (such as holding appropriate locks) to avoid racing
+ * with another list-mutation primitive, such as hlist_nulls_add_head_rcu()
+ * or hlist_nulls_del_rcu(), running on this same list.
+ * However, it is perfectly legal to run concurrently with
+ * the _rcu list-traversal primitives, such as
+ * hlist_nulls_for_each_entry_rcu(), used to prevent memory-consistency
+ * problems on Alpha CPUs.  Regardless of the type of CPU, the
+ * list-traversal primitive must be guarded by rcu_read_lock().
+ */
+static inline void hlist_nulls_add_tail_rcu(struct hlist_nulls_node *n,
+					struct hlist_nulls_head *h)
+{
+	struct hlist_nulls_node *i, *last = NULL;
+
+	for (i = hlist_nulls_first_rcu(h); !is_a_nulls(i);
+	     i = hlist_nulls_next_rcu(i))
+		last = i;
+
+	if (last) {
+		n->next = last->next;
+		n->pprev = &last->next;
+		rcu_assign_pointer(hlist_nulls_next_rcu(last), n);
+	} else {
+		hlist_nulls_add_head_rcu(n, h);
+	}
+}
+
 /**
  * hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type
  * @tpos:	the type * to use as a loop cursor.
diff --git a/include/net/sock.h b/include/net/sock.h
index 14d3c07..7a09140 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -649,7 +649,11 @@ static inline void sk_add_node_rcu(struct sock *sk, struct hlist_head *list)
 
 static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
 {
-	hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list);
+	if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport &&
+	    sk->sk_family == AF_INET6)
+		hlist_nulls_add_tail_rcu(&sk->sk_nulls_node, list);
+	else
+		hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list);
 }
 
 static inline void sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 21fbb54..7683f1e 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -296,8 +296,13 @@ found:
 
 		hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash);
 		spin_lock(&hslot2->lock);
-		hlist_nulls_add_head_rcu(&udp_sk(sk)->udp_portaddr_node,
-					 &hslot2->head);
+		if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport &&
+			sk->sk_family == AF_INET6)
+			hlist_nulls_add_tail_rcu(&udp_sk(sk)->udp_portaddr_node,
+						 &hslot2->head);
+		else
+			hlist_nulls_add_head_rcu(&udp_sk(sk)->udp_portaddr_node,
+						 &hslot2->head);
 		hslot2->count++;
 		spin_unlock(&hslot2->lock);
 	}
-- 
2.1.0


From 0133b22bb3428caff7a1ba28970c87fad320c645 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Sat, 20 Feb 2016 00:29:30 +0100
Subject: [PATCH 08/38] net: use skb_postpush_rcsum instead of own
 implementations

[ Upstream commit 6b83d28a55a891a9d70fc61ccb1c138e47dcbe74 ]

Replace individual implementations with the recently introduced
skb_postpush_rcsum() helper.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Tom Herbert <tom@herbertland.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c              | 4 +---
 net/ipv6/reassembly.c          | 6 ++----
 net/openvswitch/actions.c      | 8 +++-----
 net/openvswitch/vport-netdev.c | 2 +-
 net/openvswitch/vport.h        | 7 -------
 5 files changed, 7 insertions(+), 20 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 8616d11..78abe11 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4433,9 +4433,7 @@ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci)
 		skb->mac_len += VLAN_HLEN;
 		__skb_pull(skb, offset);
 
-		if (skb->ip_summed == CHECKSUM_COMPLETE)
-			skb->csum = csum_add(skb->csum, csum_partial(skb->data
-					+ (2 * ETH_ALEN), VLAN_HLEN, 0));
+		skb_postpush_rcsum(skb, skb->data + (2 * ETH_ALEN), VLAN_HLEN);
 	}
 	__vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci);
 	return 0;
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 45f5ae5..a234552 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -496,10 +496,8 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
 	IP6CB(head)->flags |= IP6SKB_FRAGMENTED;
 
 	/* Yes, and fold redundant checksum back. 8) */
-	if (head->ip_summed == CHECKSUM_COMPLETE)
-		head->csum = csum_partial(skb_network_header(head),
-					  skb_network_header_len(head),
-					  head->csum);
+	skb_postpush_rcsum(head, skb_network_header(head),
+			   skb_network_header_len(head));
 
 	rcu_read_lock();
 	IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS);
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index c88d0f2..7aef0c8 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -158,9 +158,7 @@ static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key,
 	new_mpls_lse = (__be32 *)skb_mpls_header(skb);
 	*new_mpls_lse = mpls->mpls_lse;
 
-	if (skb->ip_summed == CHECKSUM_COMPLETE)
-		skb->csum = csum_add(skb->csum, csum_partial(new_mpls_lse,
-							     MPLS_HLEN, 0));
+	skb_postpush_rcsum(skb, new_mpls_lse, MPLS_HLEN);
 
 	hdr = eth_hdr(skb);
 	hdr->h_proto = mpls->mpls_ethertype;
@@ -280,7 +278,7 @@ static int set_eth_addr(struct sk_buff *skb, struct sw_flow_key *flow_key,
 	ether_addr_copy_masked(eth_hdr(skb)->h_dest, key->eth_dst,
 			       mask->eth_dst);
 
-	ovs_skb_postpush_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
+	skb_postpush_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
 
 	ether_addr_copy(flow_key->eth.src, eth_hdr(skb)->h_source);
 	ether_addr_copy(flow_key->eth.dst, eth_hdr(skb)->h_dest);
@@ -639,7 +637,7 @@ static int ovs_vport_output(struct net *net, struct sock *sk, struct sk_buff *sk
 	/* Reconstruct the MAC header.  */
 	skb_push(skb, data->l2_len);
 	memcpy(skb->data, &data->l2_data, data->l2_len);
-	ovs_skb_postpush_rcsum(skb, skb->data, data->l2_len);
+	skb_postpush_rcsum(skb, skb->data, data->l2_len);
 	skb_reset_mac_header(skb);
 
 	ovs_vport_send(vport, skb);
diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c
index 6b0190b..76fcaf1 100644
--- a/net/openvswitch/vport-netdev.c
+++ b/net/openvswitch/vport-netdev.c
@@ -58,7 +58,7 @@ static void netdev_port_receive(struct sk_buff *skb)
 		return;
 
 	skb_push(skb, ETH_HLEN);
-	ovs_skb_postpush_rcsum(skb, skb->data, ETH_HLEN);
+	skb_postpush_rcsum(skb, skb->data, ETH_HLEN);
 	ovs_vport_receive(vport, skb, skb_tunnel_info(skb));
 	return;
 error:
diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h
index 8ea3a96..6e2b62f 100644
--- a/net/openvswitch/vport.h
+++ b/net/openvswitch/vport.h
@@ -184,13 +184,6 @@ static inline struct vport *vport_from_priv(void *priv)
 int ovs_vport_receive(struct vport *, struct sk_buff *,
 		      const struct ip_tunnel_info *);
 
-static inline void ovs_skb_postpush_rcsum(struct sk_buff *skb,
-				      const void *start, unsigned int len)
-{
-	if (skb->ip_summed == CHECKSUM_COMPLETE)
-		skb->csum = csum_add(skb->csum, csum_partial(start, len, 0));
-}
-
 static inline const char *ovs_vport_name(struct vport *vport)
 {
 	return vport->dev->name;
-- 
2.1.0


From 873e6aabd6c2491981cbcb10fb691eaed07b723b Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Sat, 16 Apr 2016 02:27:58 +0200
Subject: [PATCH 09/38] vlan: pull on __vlan_insert_tag error path and fix csum
 correction

[ Upstream commit 9241e2df4fbc648a92ea0752918e05c26255649e ]

When __vlan_insert_tag() fails from skb_vlan_push() path due to the
skb_cow_head(), we need to undo the __skb_push() in the error path
as well that was done earlier to move skb->data pointer to mac header.

Moreover, I noticed that when in the non-error path the __skb_pull()
is done and the original offset to mac header was non-zero, we fixup
from a wrong skb->data offset in the checksum complete processing.

So the skb_postpush_rcsum() really needs to be done before __skb_pull()
where skb->data still points to the mac header start and thus operates
under the same conditions as in __vlan_insert_tag().

Fixes: 93515d53b133 ("net: move vlan pop/push functions into common code")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 78abe11..9835d9a 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4427,13 +4427,16 @@ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci)
 		__skb_push(skb, offset);
 		err = __vlan_insert_tag(skb, skb->vlan_proto,
 					skb_vlan_tag_get(skb));
-		if (err)
+		if (err) {
+			__skb_pull(skb, offset);
 			return err;
+		}
+
 		skb->protocol = skb->vlan_proto;
 		skb->mac_len += VLAN_HLEN;
-		__skb_pull(skb, offset);
 
 		skb_postpush_rcsum(skb, skb->data + (2 * ETH_ALEN), VLAN_HLEN);
+		__skb_pull(skb, offset);
 	}
 	__vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci);
 	return 0;
-- 
2.1.0


From 80a7215ebef0672f2b59961a4fdc98b09cd6b3f0 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben@decadent.org.uk>
Date: Wed, 20 Apr 2016 23:23:08 +0100
Subject: [PATCH 10/38] atl2: Disable unimplemented scatter/gather feature

[ Upstream commit f43bfaeddc79effbf3d0fcb53ca477cca66f3db8 ]

atl2 includes NETIF_F_SG in hw_features even though it has no support
for non-linear skbs.  This bug was originally harmless since the
driver does not claim to implement checksum offload and that used to
be a requirement for SG.

Now that SG and checksum offload are independent features, if you
explicitly enable SG *and* use one of the rare protocols that can use
SG without checkusm offload, this potentially leaks sensitive
information (before you notice that it just isn't working).  Therefore
this obscure bug has been designated CVE-2016-2117.

Reported-by: Justin Yackoski <jyackoski@crypto-nite.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Fixes: ec5f06156423 ("net: Kill link between CSUM and SG features.")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/atheros/atlx/atl2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c
index 8f76f45..2ff4658 100644
--- a/drivers/net/ethernet/atheros/atlx/atl2.c
+++ b/drivers/net/ethernet/atheros/atlx/atl2.c
@@ -1412,7 +1412,7 @@ static int atl2_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	err = -EIO;
 
-	netdev->hw_features = NETIF_F_SG | NETIF_F_HW_VLAN_CTAG_RX;
+	netdev->hw_features = NETIF_F_HW_VLAN_CTAG_RX;
 	netdev->features |= (NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX);
 
 	/* Init PHY as early as possible due to power saving issue  */
-- 
2.1.0


From 246d36c54dded704013b2cbcc2de7096f517b712 Mon Sep 17 00:00:00 2001
From: Simon Horman <simon.horman@netronome.com>
Date: Thu, 21 Apr 2016 11:49:15 +1000
Subject: [PATCH 11/38] openvswitch: use flow protocol when recalculating ipv6
 checksums

[ Upstream commit b4f70527f052b0c00be4d7cac562baa75b212df5 ]

When using masked actions the ipv6_proto field of an action
to set IPv6 fields may be zero rather than the prevailing protocol
which will result in skipping checksum recalculation.

This patch resolves the problem by relying on the protocol
in the flow key rather than that in the set field action.

Fixes: 83d2b9ba1abc ("net: openvswitch: Support masked set actions.")
Cc: Jarno Rajahalme <jrajahalme@nicira.com>
Signed-off-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/actions.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 7aef0c8..7cb8184 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -461,7 +461,7 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key,
 		mask_ipv6_addr(saddr, key->ipv6_src, mask->ipv6_src, masked);
 
 		if (unlikely(memcmp(saddr, masked, sizeof(masked)))) {
-			set_ipv6_addr(skb, key->ipv6_proto, saddr, masked,
+			set_ipv6_addr(skb, flow_key->ip.proto, saddr, masked,
 				      true);
 			memcpy(&flow_key->ipv6.addr.src, masked,
 			       sizeof(flow_key->ipv6.addr.src));
@@ -483,7 +483,7 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key,
 							     NULL, &flags)
 					       != NEXTHDR_ROUTING);
 
-			set_ipv6_addr(skb, key->ipv6_proto, daddr, masked,
+			set_ipv6_addr(skb, flow_key->ip.proto, daddr, masked,
 				      recalc_csum);
 			memcpy(&flow_key->ipv6.addr.dst, masked,
 			       sizeof(flow_key->ipv6.addr.dst));
-- 
2.1.0


From d6585c5a6934a1ce0b353a4d552d0aa6dc27e2c8 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Fri, 22 Apr 2016 00:33:03 +0300
Subject: [PATCH 12/38] net/mlx5e: Device's mtu field is u16 and not int

[ Upstream commit 046339eaab26804f52f6604877f5674f70815b26 ]

For set/query MTU port firmware commands the MTU field
is 16 bits, here I changed all the "int mtu" parameters
of the functions wrapping those firmware commands to be u16.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/mlx5/main.c                 |  4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c |  4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/port.c    | 10 +++++-----
 include/linux/mlx5/driver.h                       |  6 +++---
 4 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 721d63f..fd17443 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -405,8 +405,8 @@ static int mlx5_query_hca_port(struct ib_device *ibdev, u8 port,
 	struct mlx5_ib_dev *dev = to_mdev(ibdev);
 	struct mlx5_core_dev *mdev = dev->mdev;
 	struct mlx5_hca_vport_context *rep;
-	int max_mtu;
-	int oper_mtu;
+	u16 max_mtu;
+	u16 oper_mtu;
 	int err;
 	u8 ib_link_width_oper;
 	u8 vl_hw_cap;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 1203d89..d6a7213 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1372,7 +1372,7 @@ static int mlx5e_set_dev_port_mtu(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
-	int hw_mtu;
+	u16 hw_mtu;
 	int err;
 
 	err = mlx5_set_port_mtu(mdev, MLX5E_SW2HW_MTU(netdev->mtu), 1);
@@ -1896,7 +1896,7 @@ static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu)
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
 	bool was_opened;
-	int max_mtu;
+	u16 max_mtu;
 	int err = 0;
 
 	mlx5_query_port_max_mtu(mdev, &max_mtu, 1);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index a87e773..53a793b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -246,8 +246,8 @@ int mlx5_query_port_admin_status(struct mlx5_core_dev *dev,
 }
 EXPORT_SYMBOL_GPL(mlx5_query_port_admin_status);
 
-static void mlx5_query_port_mtu(struct mlx5_core_dev *dev, int *admin_mtu,
-				int *max_mtu, int *oper_mtu, u8 port)
+static void mlx5_query_port_mtu(struct mlx5_core_dev *dev, u16 *admin_mtu,
+				u16 *max_mtu, u16 *oper_mtu, u8 port)
 {
 	u32 in[MLX5_ST_SZ_DW(pmtu_reg)];
 	u32 out[MLX5_ST_SZ_DW(pmtu_reg)];
@@ -267,7 +267,7 @@ static void mlx5_query_port_mtu(struct mlx5_core_dev *dev, int *admin_mtu,
 		*admin_mtu = MLX5_GET(pmtu_reg, out, admin_mtu);
 }
 
-int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu, u8 port)
+int mlx5_set_port_mtu(struct mlx5_core_dev *dev, u16 mtu, u8 port)
 {
 	u32 in[MLX5_ST_SZ_DW(pmtu_reg)];
 	u32 out[MLX5_ST_SZ_DW(pmtu_reg)];
@@ -282,14 +282,14 @@ int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu, u8 port)
 }
 EXPORT_SYMBOL_GPL(mlx5_set_port_mtu);
 
-void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, int *max_mtu,
+void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, u16 *max_mtu,
 			     u8 port)
 {
 	mlx5_query_port_mtu(dev, NULL, max_mtu, NULL, port);
 }
 EXPORT_SYMBOL_GPL(mlx5_query_port_max_mtu);
 
-void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, int *oper_mtu,
+void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, u16 *oper_mtu,
 			      u8 port)
 {
 	mlx5_query_port_mtu(dev, NULL, NULL, oper_mtu, port);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index af3efd9..412aa98 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -792,9 +792,9 @@ int mlx5_set_port_admin_status(struct mlx5_core_dev *dev,
 int mlx5_query_port_admin_status(struct mlx5_core_dev *dev,
 				 enum mlx5_port_status *status);
 
-int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu, u8 port);
-void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, int *max_mtu, u8 port);
-void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, int *oper_mtu,
+int mlx5_set_port_mtu(struct mlx5_core_dev *dev, u16 mtu, u8 port);
+void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, u16 *max_mtu, u8 port);
+void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, u16 *oper_mtu,
 			      u8 port);
 
 int mlx5_query_port_vl_hw_cap(struct mlx5_core_dev *dev,
-- 
2.1.0


From 115209ebab744f7561b753682dae6d584a908f1e Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Fri, 22 Apr 2016 00:33:04 +0300
Subject: [PATCH 13/38] net/mlx5e: Fix minimum MTU

[ Upstream commit d8edd2469ace550db707798180d1c84d81f93bca ]

Minimum MTU that can be set in Connectx4 device is 68.

This fixes the case where a user wants to set invalid MTU,
the driver will fail to satisfy this request and the interface
will stay down.

It is better to report an error and continue working with old
mtu.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index d6a7213..cbd17e2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1891,22 +1891,27 @@ static int mlx5e_set_features(struct net_device *netdev,
 	return err;
 }
 
+#define MXL5_HW_MIN_MTU 64
+#define MXL5E_MIN_MTU (MXL5_HW_MIN_MTU + ETH_FCS_LEN)
+
 static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
 	bool was_opened;
 	u16 max_mtu;
+	u16 min_mtu;
 	int err = 0;
 
 	mlx5_query_port_max_mtu(mdev, &max_mtu, 1);
 
 	max_mtu = MLX5E_HW2SW_MTU(max_mtu);
+	min_mtu = MLX5E_HW2SW_MTU(MXL5E_MIN_MTU);
 
-	if (new_mtu > max_mtu) {
+	if (new_mtu > max_mtu || new_mtu < min_mtu) {
 		netdev_err(netdev,
-			   "%s: Bad MTU (%d) > (%d) Max\n",
-			   __func__, new_mtu, max_mtu);
+			   "%s: Bad MTU (%d), valid range is: [%d..%d]\n",
+			   __func__, new_mtu, min_mtu, max_mtu);
 		return -EINVAL;
 	}
 
-- 
2.1.0


From c190f5666435f75218eabe58131511dd38870c37 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 21 Apr 2016 22:23:31 +0200
Subject: [PATCH 14/38] ipv4/fib: don't warn when primary address is missing if
 in_dev is dead

[ Upstream commit 391a20333b8393ef2e13014e6e59d192c5594471 ]

After commit fbd40ea0180a ("ipv4: Don't do expensive useless work
during inetdev destroy.") when deleting an interface,
fib_del_ifaddr() can be executed without any primary address
present on the dead interface.

The above is safe, but triggers some "bug: prim == NULL" warnings.

This commit avoids warning if the in_dev is dead

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_frontend.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 8a9246d..63566ec 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -904,7 +904,11 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim)
 	if (ifa->ifa_flags & IFA_F_SECONDARY) {
 		prim = inet_ifa_byprefix(in_dev, any, ifa->ifa_mask);
 		if (!prim) {
-			pr_warn("%s: bug: prim == NULL\n", __func__);
+			/* if the device has been deleted, we don't perform
+			 * address promotion
+			 */
+			if (!in_dev->dead)
+				pr_warn("%s: bug: prim == NULL\n", __func__);
 			return;
 		}
 		if (iprim && iprim != prim) {
-- 
2.1.0


From 49c10ca6c01a16538b69913de5f28e66761d22ec Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 23 Apr 2016 11:35:46 -0700
Subject: [PATCH 15/38] net/mlx4_en: fix spurious timestamping callbacks

[ Upstream commit fc96256c906362e845d848d0f6a6354450059e81 ]

When multiple skb are TX-completed in a row, we might incorrectly keep
a timestamp of a prior skb and cause extra work.

Fixes: ec693d47010e8 ("net/mlx4_en: Add HW timestamping (TS) support")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_tx.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 4421bf5..e4019a8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -400,7 +400,6 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev,
 	u32 packets = 0;
 	u32 bytes = 0;
 	int factor = priv->cqe_factor;
-	u64 timestamp = 0;
 	int done = 0;
 	int budget = priv->tx_work_limit;
 	u32 last_nr_txbb;
@@ -440,9 +439,12 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev,
 		new_index = be16_to_cpu(cqe->wqe_index) & size_mask;
 
 		do {
+			u64 timestamp = 0;
+
 			txbbs_skipped += last_nr_txbb;
 			ring_index = (ring_index + last_nr_txbb) & size_mask;
-			if (ring->tx_info[ring_index].ts_requested)
+
+			if (unlikely(ring->tx_info[ring_index].ts_requested))
 				timestamp = mlx4_en_get_cqe_ts(cqe);
 
 			/* free next descriptor */
-- 
2.1.0


From 819f88821f45738f27c9b39468c18737fb51e00a Mon Sep 17 00:00:00 2001
From: Jann Horn <jannh@google.com>
Date: Tue, 26 Apr 2016 22:26:26 +0200
Subject: [PATCH 16/38] bpf: fix double-fdput in replace_map_fd_with_map_ptr()

[ Upstream commit 8358b02bf67d3a5d8a825070e1aa73f25fb2e4c7 ]

When bpf(BPF_PROG_LOAD, ...) was invoked with a BPF program whose bytecode
references a non-map file descriptor as a map file descriptor, the error
handling code called fdput() twice instead of once (in __bpf_map_get() and
in replace_map_fd_with_map_ptr()). If the file descriptor table of the
current task is shared, this causes f_count to be decremented too much,
allowing the struct file to be freed while it is still in use
(use-after-free). This can be exploited to gain root privileges by an
unprivileged user.

This bug was introduced in
commit 0246e64d9a5f ("bpf: handle pseudo BPF_LD_IMM64 insn"), but is only
exploitable since
commit 1be7f75d1668 ("bpf: enable non-root eBPF programs") because
previously, CAP_SYS_ADMIN was required to reach the vulnerable code.

(posted publicly according to request by maintainer)

Signed-off-by: Jann Horn <jannh@google.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c21cb14..e3798cf 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2004,7 +2004,6 @@ static int replace_map_fd_with_map_ptr(struct verifier_env *env)
 			if (IS_ERR(map)) {
 				verbose("fd %d is not pointing to valid bpf_map\n",
 					insn->imm);
-				fdput(f);
 				return PTR_ERR(map);
 			}
 
-- 
2.1.0


From 78bf12f9c68f4ba9c903807dd89c6f15f203c220 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@fb.com>
Date: Wed, 27 Apr 2016 18:56:20 -0700
Subject: [PATCH 17/38] bpf: fix refcnt overflow

[ Upstream commit 92117d8443bc5afacc8d5ba82e541946310f106e ]

On a system with >32Gbyte of phyiscal memory and infinite RLIMIT_MEMLOCK,
the malicious application may overflow 32-bit bpf program refcnt.
It's also possible to overflow map refcnt on 1Tb system.
Impose 32k hard limit which means that the same bpf program or
map cannot be shared by more than 32k processes.

Fixes: 1be7f75d1668 ("bpf: enable non-root eBPF programs")
Reported-by: Jann Horn <jannh@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/bpf.h   |  3 ++-
 kernel/bpf/inode.c    |  7 ++++---
 kernel/bpf/syscall.c  | 24 ++++++++++++++++++++----
 kernel/bpf/verifier.c | 11 +++++++----
 4 files changed, 33 insertions(+), 12 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 83d1926..67bc2da 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -165,12 +165,13 @@ void bpf_register_prog_type(struct bpf_prog_type_list *tl);
 void bpf_register_map_type(struct bpf_map_type_list *tl);
 
 struct bpf_prog *bpf_prog_get(u32 ufd);
+struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog);
 void bpf_prog_put(struct bpf_prog *prog);
 void bpf_prog_put_rcu(struct bpf_prog *prog);
 
 struct bpf_map *bpf_map_get_with_uref(u32 ufd);
 struct bpf_map *__bpf_map_get(struct fd f);
-void bpf_map_inc(struct bpf_map *map, bool uref);
+struct bpf_map *bpf_map_inc(struct bpf_map *map, bool uref);
 void bpf_map_put_with_uref(struct bpf_map *map);
 void bpf_map_put(struct bpf_map *map);
 
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 5a8a797..d1a7646 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -31,10 +31,10 @@ static void *bpf_any_get(void *raw, enum bpf_type type)
 {
 	switch (type) {
 	case BPF_TYPE_PROG:
-		atomic_inc(&((struct bpf_prog *)raw)->aux->refcnt);
+		raw = bpf_prog_inc(raw);
 		break;
 	case BPF_TYPE_MAP:
-		bpf_map_inc(raw, true);
+		raw = bpf_map_inc(raw, true);
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -277,7 +277,8 @@ static void *bpf_obj_do_get(const struct filename *pathname,
 		goto out;
 
 	raw = bpf_any_get(inode->i_private, *type);
-	touch_atime(&path);
+	if (!IS_ERR(raw))
+		touch_atime(&path);
 
 	path_put(&path);
 	return raw;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 3b39550..4e32cc9 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -181,11 +181,18 @@ struct bpf_map *__bpf_map_get(struct fd f)
 	return f.file->private_data;
 }
 
-void bpf_map_inc(struct bpf_map *map, bool uref)
+/* prog's and map's refcnt limit */
+#define BPF_MAX_REFCNT 32768
+
+struct bpf_map *bpf_map_inc(struct bpf_map *map, bool uref)
 {
-	atomic_inc(&map->refcnt);
+	if (atomic_inc_return(&map->refcnt) > BPF_MAX_REFCNT) {
+		atomic_dec(&map->refcnt);
+		return ERR_PTR(-EBUSY);
+	}
 	if (uref)
 		atomic_inc(&map->usercnt);
+	return map;
 }
 
 struct bpf_map *bpf_map_get_with_uref(u32 ufd)
@@ -197,7 +204,7 @@ struct bpf_map *bpf_map_get_with_uref(u32 ufd)
 	if (IS_ERR(map))
 		return map;
 
-	bpf_map_inc(map, true);
+	map = bpf_map_inc(map, true);
 	fdput(f);
 
 	return map;
@@ -580,6 +587,15 @@ static struct bpf_prog *__bpf_prog_get(struct fd f)
 	return f.file->private_data;
 }
 
+struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog)
+{
+	if (atomic_inc_return(&prog->aux->refcnt) > BPF_MAX_REFCNT) {
+		atomic_dec(&prog->aux->refcnt);
+		return ERR_PTR(-EBUSY);
+	}
+	return prog;
+}
+
 /* called by sockets/tracing/seccomp before attaching program to an event
  * pairs with bpf_prog_put()
  */
@@ -592,7 +608,7 @@ struct bpf_prog *bpf_prog_get(u32 ufd)
 	if (IS_ERR(prog))
 		return prog;
 
-	atomic_inc(&prog->aux->refcnt);
+	prog = bpf_prog_inc(prog);
 	fdput(f);
 
 	return prog;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index e3798cf..5a615c18 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2023,15 +2023,18 @@ static int replace_map_fd_with_map_ptr(struct verifier_env *env)
 				return -E2BIG;
 			}
 
-			/* remember this map */
-			env->used_maps[env->used_map_cnt++] = map;
-
 			/* hold the map. If the program is rejected by verifier,
 			 * the map will be released by release_maps() or it
 			 * will be used by the valid program until it's unloaded
 			 * and all maps are released in free_bpf_prog_info()
 			 */
-			bpf_map_inc(map, false);
+			map = bpf_map_inc(map, false);
+			if (IS_ERR(map)) {
+				fdput(f);
+				return PTR_ERR(map);
+			}
+			env->used_maps[env->used_map_cnt++] = map;
+
 			fdput(f);
 next_insn:
 			insn++;
-- 
2.1.0


From 4ed4f65144629b027ee7e78be78fcf8f78dca81e Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@fb.com>
Date: Wed, 27 Apr 2016 18:56:21 -0700
Subject: [PATCH 18/38] bpf: fix check_map_func_compatibility logic

[ Upstream commit 6aff67c85c9e5a4bc99e5211c1bac547936626ca ]

The commit 35578d798400 ("bpf: Implement function bpf_perf_event_read() that get the selected hardware PMU conuter")
introduced clever way to check bpf_helper<->map_type compatibility.
Later on commit a43eec304259 ("bpf: introduce bpf_perf_event_output() helper") adjusted
the logic and inadvertently broke it.
Get rid of the clever bool compare and go back to two-way check
from map and from helper perspective.

Fixes: a43eec304259 ("bpf: introduce bpf_perf_event_output() helper")
Reported-by: Jann Horn <jannh@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c | 53 +++++++++++++++++++++++++++++++--------------------
 1 file changed, 32 insertions(+), 21 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 5a615c18..2cbfba7 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -239,15 +239,6 @@ static const char * const reg_type_str[] = {
 	[CONST_IMM]		= "imm",
 };
 
-static const struct {
-	int map_type;
-	int func_id;
-} func_limit[] = {
-	{BPF_MAP_TYPE_PROG_ARRAY, BPF_FUNC_tail_call},
-	{BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_read},
-	{BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_output},
-};
-
 static void print_verifier_state(struct verifier_env *env)
 {
 	enum bpf_reg_type t;
@@ -898,24 +889,44 @@ static int check_func_arg(struct verifier_env *env, u32 regno,
 
 static int check_map_func_compatibility(struct bpf_map *map, int func_id)
 {
-	bool bool_map, bool_func;
-	int i;
-
 	if (!map)
 		return 0;
 
-	for (i = 0; i < ARRAY_SIZE(func_limit); i++) {
-		bool_map = (map->map_type == func_limit[i].map_type);
-		bool_func = (func_id == func_limit[i].func_id);
-		/* only when map & func pair match it can continue.
-		 * don't allow any other map type to be passed into
-		 * the special func;
-		 */
-		if (bool_func && bool_map != bool_func)
-			return -EINVAL;
+	/* We need a two way check, first is from map perspective ... */
+	switch (map->map_type) {
+	case BPF_MAP_TYPE_PROG_ARRAY:
+		if (func_id != BPF_FUNC_tail_call)
+			goto error;
+		break;
+	case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
+		if (func_id != BPF_FUNC_perf_event_read &&
+		    func_id != BPF_FUNC_perf_event_output)
+			goto error;
+		break;
+	default:
+		break;
+	}
+
+	/* ... and second from the function itself. */
+	switch (func_id) {
+	case BPF_FUNC_tail_call:
+		if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY)
+			goto error;
+		break;
+	case BPF_FUNC_perf_event_read:
+	case BPF_FUNC_perf_event_output:
+		if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY)
+			goto error;
+		break;
+	default:
+		break;
 	}
 
 	return 0;
+error:
+	verbose("cannot pass map_type %d into func %d\n",
+		map->map_type, func_id);
+	return -EINVAL;
 }
 
 static int check_call(struct verifier_env *env, int func_id)
-- 
2.1.0


From 68ce43525ec58ee58ed9a4376ef9563ab6fd4541 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@fb.com>
Date: Wed, 27 Apr 2016 18:56:22 -0700
Subject: [PATCH 19/38] samples/bpf: fix trace_output example

[ Upstream commit 569cc39d39385a74b23145496bca2df5ac8b2fb8 ]

llvm cannot always recognize memset as builtin function and optimize
it away, so just delete it. It was a leftover from testing
of bpf_perf_event_output() with large data structures.

Fixes: 39111695b1b8 ("samples: bpf: add bpf_perf_event_output example")
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 samples/bpf/trace_output_kern.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/samples/bpf/trace_output_kern.c b/samples/bpf/trace_output_kern.c
index 8d8d1ec..9b96f4f 100644
--- a/samples/bpf/trace_output_kern.c
+++ b/samples/bpf/trace_output_kern.c
@@ -18,7 +18,6 @@ int bpf_prog1(struct pt_regs *ctx)
 		u64 cookie;
 	} data;
 
-	memset(&data, 0, sizeof(data));
 	data.pid = bpf_get_current_pid_tgid();
 	data.cookie = 0x12345678;
 
-- 
2.1.0


From 39a68dcb61f96af1a2eaf5c5213c59524d8cf34d Mon Sep 17 00:00:00 2001
From: Tim Bingham <tbingham@akamai.com>
Date: Fri, 29 Apr 2016 13:30:23 -0400
Subject: [PATCH 20/38] net: Implement net_dbg_ratelimited() for
 CONFIG_DYNAMIC_DEBUG case

[ Upstream commit 2c94b53738549d81dc7464a32117d1f5112c64d3 ]

Prior to commit d92cff89a0c8 ("net_dbg_ratelimited: turn into no-op
when !DEBUG") the implementation of net_dbg_ratelimited() was buggy
for both the DEBUG and CONFIG_DYNAMIC_DEBUG cases.

The bug was that net_ratelimit() was being called and, despite
returning true, nothing was being printed to the console. This
resulted in messages like the following -

"net_ratelimit: %d callbacks suppressed"

with no other output nearby.

After commit d92cff89a0c8 ("net_dbg_ratelimited: turn into no-op when
!DEBUG") the bug is fixed for the DEBUG case. However, there's no
output at all for CONFIG_DYNAMIC_DEBUG case.

This patch restores debug output (if enabled) for the
CONFIG_DYNAMIC_DEBUG case.

Add a definition of net_dbg_ratelimited() for the CONFIG_DYNAMIC_DEBUG
case. The implementation takes care to check that dynamic debugging is
enabled before calling net_ratelimit().

Fixes: d92cff89a0c8 ("net_dbg_ratelimited: turn into no-op when !DEBUG")
Signed-off-by: Tim Bingham <tbingham@akamai.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/net.h | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/include/linux/net.h b/include/linux/net.h
index 0b4ac7d..25ef630 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -245,7 +245,15 @@ do {								\
 	net_ratelimited_function(pr_warn, fmt, ##__VA_ARGS__)
 #define net_info_ratelimited(fmt, ...)				\
 	net_ratelimited_function(pr_info, fmt, ##__VA_ARGS__)
-#if defined(DEBUG)
+#if defined(CONFIG_DYNAMIC_DEBUG)
+#define net_dbg_ratelimited(fmt, ...)					\
+do {									\
+	DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt);			\
+	if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT) &&	\
+	    net_ratelimit())						\
+		__dynamic_pr_debug(&descriptor, fmt, ##__VA_ARGS__);	\
+} while (0)
+#elif defined(DEBUG)
 #define net_dbg_ratelimited(fmt, ...)				\
 	net_ratelimited_function(pr_debug, fmt, ##__VA_ARGS__)
 #else
-- 
2.1.0


From 6307c02141dfeb64f96b213c19083cc642532f19 Mon Sep 17 00:00:00 2001
From: Jiri Benc <jbenc@redhat.com>
Date: Fri, 29 Apr 2016 23:31:32 +0200
Subject: [PATCH 21/38] gre: do not pull header in ICMP error processing

[ Upstream commit b7f8fe251e4609e2a437bd2c2dea01e61db6849c ]

iptunnel_pull_header expects that IP header was already pulled; with this
expectation, it pulls the tunnel header. This is not true in gre_err.
Furthermore, ipv4_update_pmtu and ipv4_redirect expect that skb->data points
to the IP header.

We cannot pull the tunnel header in this path. It's just a matter of not
calling iptunnel_pull_header - we don't need any of its effects.

Fixes: bda7bb463436 ("gre: Allow multiple protocol listener for gre protocol.")
Signed-off-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_gre.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 6145214..7dc962b 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -180,6 +180,7 @@ static __be16 tnl_flags_to_gre_flags(__be16 tflags)
 	return flags;
 }
 
+/* Fills in tpi and returns header length to be pulled. */
 static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 			    bool *csum_err)
 {
@@ -239,7 +240,7 @@ static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 				return -EINVAL;
 		}
 	}
-	return iptunnel_pull_header(skb, hdr_len, tpi->proto);
+	return hdr_len;
 }
 
 static void ipgre_err(struct sk_buff *skb, u32 info,
@@ -342,7 +343,7 @@ static void gre_err(struct sk_buff *skb, u32 info)
 	struct tnl_ptk_info tpi;
 	bool csum_err = false;
 
-	if (parse_gre_header(skb, &tpi, &csum_err)) {
+	if (parse_gre_header(skb, &tpi, &csum_err) < 0) {
 		if (!csum_err)		/* ignore csum errors. */
 			return;
 	}
@@ -420,6 +421,7 @@ static int gre_rcv(struct sk_buff *skb)
 {
 	struct tnl_ptk_info tpi;
 	bool csum_err = false;
+	int hdr_len;
 
 #ifdef CONFIG_NET_IPGRE_BROADCAST
 	if (ipv4_is_multicast(ip_hdr(skb)->daddr)) {
@@ -429,7 +431,10 @@ static int gre_rcv(struct sk_buff *skb)
 	}
 #endif
 
-	if (parse_gre_header(skb, &tpi, &csum_err) < 0)
+	hdr_len = parse_gre_header(skb, &tpi, &csum_err);
+	if (hdr_len < 0)
+		goto drop;
+	if (iptunnel_pull_header(skb, hdr_len, tpi.proto) < 0)
 		goto drop;
 
 	if (ipgre_rcv(skb, &tpi) == PACKET_RCVD)
-- 
2.1.0


From be81db68364c101805179a115a920c1a144abae8 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Thu, 25 Feb 2016 14:55:00 -0800
Subject: [PATCH 22/38] net_sched: introduce qdisc_replace() helper

[ Upstream commit 86a7996cc8a078793670d82ed97d5a99bb4e8496 ]

Remove nearly duplicated code and prepare for the following patch.

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h | 17 +++++++++++++++++
 net/sched/sch_cbq.c       |  7 +------
 net/sched/sch_drr.c       |  6 +-----
 net/sched/sch_dsmark.c    |  8 +-------
 net/sched/sch_hfsc.c      |  6 +-----
 net/sched/sch_htb.c       |  9 +--------
 net/sched/sch_multiq.c    |  8 +-------
 net/sched/sch_netem.c     | 10 +---------
 net/sched/sch_prio.c      |  8 +-------
 net/sched/sch_qfq.c       |  6 +-----
 net/sched/sch_red.c       |  7 +------
 net/sched/sch_sfb.c       |  7 +------
 net/sched/sch_tbf.c       |  8 +-------
 13 files changed, 29 insertions(+), 78 deletions(-)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index b2a8e63..4dba266 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -698,6 +698,23 @@ static inline void qdisc_reset_queue(struct Qdisc *sch)
 	sch->qstats.backlog = 0;
 }
 
+static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new,
+					  struct Qdisc **pold)
+{
+	struct Qdisc *old;
+
+	sch_tree_lock(sch);
+	old = *pold;
+	*pold = new;
+	if (old != NULL) {
+		qdisc_tree_decrease_qlen(old, old->q.qlen);
+		qdisc_reset(old);
+	}
+	sch_tree_unlock(sch);
+
+	return old;
+}
+
 static inline unsigned int __qdisc_queue_drop(struct Qdisc *sch,
 					      struct sk_buff_head *list)
 {
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index c538d9e..7f8474c 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1624,13 +1624,8 @@ static int cbq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 			new->reshape_fail = cbq_reshape_fail;
 #endif
 	}
-	sch_tree_lock(sch);
-	*old = cl->q;
-	cl->q = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
 
+	*old = qdisc_replace(sch, new, &cl->q);
 	return 0;
 }
 
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index f26bdea..c76cdd4 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -226,11 +226,7 @@ static int drr_graft_class(struct Qdisc *sch, unsigned long arg,
 			new = &noop_qdisc;
 	}
 
-	sch_tree_lock(sch);
-	drr_purge_queue(cl);
-	*old = cl->qdisc;
-	cl->qdisc = new;
-	sch_tree_unlock(sch);
+	*old = qdisc_replace(sch, new, &cl->qdisc);
 	return 0;
 }
 
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index f357f34..cfddb1c 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -73,13 +73,7 @@ static int dsmark_graft(struct Qdisc *sch, unsigned long arg,
 			new = &noop_qdisc;
 	}
 
-	sch_tree_lock(sch);
-	*old = p->q;
-	p->q = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
-
+	*old = qdisc_replace(sch, new, &p->q);
 	return 0;
 }
 
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index b7ebe2c..089f3b6 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1215,11 +1215,7 @@ hfsc_graft_class(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 			new = &noop_qdisc;
 	}
 
-	sch_tree_lock(sch);
-	hfsc_purge_queue(sch, cl);
-	*old = cl->qdisc;
-	cl->qdisc = new;
-	sch_tree_unlock(sch);
+	*old = qdisc_replace(sch, new, &cl->qdisc);
 	return 0;
 }
 
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 15ccd7f..0efbcf3 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1163,14 +1163,7 @@ static int htb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 				     cl->common.classid)) == NULL)
 		return -ENOBUFS;
 
-	sch_tree_lock(sch);
-	*old = cl->un.leaf.q;
-	cl->un.leaf.q = new;
-	if (*old != NULL) {
-		qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-		qdisc_reset(*old);
-	}
-	sch_tree_unlock(sch);
+	*old = qdisc_replace(sch, new, &cl->un.leaf.q);
 	return 0;
 }
 
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index 4e904ca..a0103a1 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -303,13 +303,7 @@ static int multiq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 	if (new == NULL)
 		new = &noop_qdisc;
 
-	sch_tree_lock(sch);
-	*old = q->queues[band];
-	q->queues[band] = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
-
+	*old = qdisc_replace(sch, new, &q->queues[band]);
 	return 0;
 }
 
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 5abd1d9..0a6ddaf 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -1037,15 +1037,7 @@ static int netem_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 {
 	struct netem_sched_data *q = qdisc_priv(sch);
 
-	sch_tree_lock(sch);
-	*old = q->qdisc;
-	q->qdisc = new;
-	if (*old) {
-		qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-		qdisc_reset(*old);
-	}
-	sch_tree_unlock(sch);
-
+	*old = qdisc_replace(sch, new, &q->qdisc);
 	return 0;
 }
 
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index ba6487f..1b4aaec 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -268,13 +268,7 @@ static int prio_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 	if (new == NULL)
 		new = &noop_qdisc;
 
-	sch_tree_lock(sch);
-	*old = q->queues[band];
-	q->queues[band] = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
-
+	*old = qdisc_replace(sch, new, &q->queues[band]);
 	return 0;
 }
 
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 3dc3a6e..b5c52ca 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -617,11 +617,7 @@ static int qfq_graft_class(struct Qdisc *sch, unsigned long arg,
 			new = &noop_qdisc;
 	}
 
-	sch_tree_lock(sch);
-	qfq_purge_queue(cl);
-	*old = cl->qdisc;
-	cl->qdisc = new;
-	sch_tree_unlock(sch);
+	*old = qdisc_replace(sch, new, &cl->qdisc);
 	return 0;
 }
 
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 6c0534c..d5abcee 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -313,12 +313,7 @@ static int red_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 	if (new == NULL)
 		new = &noop_qdisc;
 
-	sch_tree_lock(sch);
-	*old = q->qdisc;
-	q->qdisc = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
+	*old = qdisc_replace(sch, new, &q->qdisc);
 	return 0;
 }
 
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index 5bbb633..0e74e55 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -606,12 +606,7 @@ static int sfb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 	if (new == NULL)
 		new = &noop_qdisc;
 
-	sch_tree_lock(sch);
-	*old = q->qdisc;
-	q->qdisc = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
+	*old = qdisc_replace(sch, new, &q->qdisc);
 	return 0;
 }
 
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index a4afde1..56a1aef 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -502,13 +502,7 @@ static int tbf_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 	if (new == NULL)
 		new = &noop_qdisc;
 
-	sch_tree_lock(sch);
-	*old = q->qdisc;
-	q->qdisc = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
-
+	*old = qdisc_replace(sch, new, &q->qdisc);
 	return 0;
 }
 
-- 
2.1.0


From 92f03732744af97036c583a6e0f2ab519ff84bb2 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Thu, 25 Feb 2016 14:55:01 -0800
Subject: [PATCH 23/38] net_sched: update hierarchical backlog too

[ Upstream commit 2ccccf5fb43ff62b2b96cc58d95fc0b3596516e4 ]

When the bottom qdisc decides to, for example, drop some packet,
it calls qdisc_tree_decrease_qlen() to update the queue length
for all its ancestors, we need to update the backlog too to
keep the stats on root qdisc accurate.

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/codel.h       |  4 ++++
 include/net/sch_generic.h |  5 +++--
 net/sched/sch_api.c       |  8 +++++---
 net/sched/sch_cbq.c       |  5 +++--
 net/sched/sch_choke.c     |  6 ++++--
 net/sched/sch_codel.c     | 10 ++++++----
 net/sched/sch_drr.c       |  3 ++-
 net/sched/sch_fq.c        |  4 +++-
 net/sched/sch_fq_codel.c  | 17 ++++++++++++-----
 net/sched/sch_hfsc.c      |  3 ++-
 net/sched/sch_hhf.c       | 10 +++++++---
 net/sched/sch_htb.c       | 10 ++++++----
 net/sched/sch_multiq.c    |  8 +++++---
 net/sched/sch_netem.c     |  3 ++-
 net/sched/sch_pie.c       |  5 +++--
 net/sched/sch_prio.c      |  7 ++++---
 net/sched/sch_qfq.c       |  3 ++-
 net/sched/sch_red.c       |  3 ++-
 net/sched/sch_sfb.c       |  3 ++-
 net/sched/sch_sfq.c       | 16 +++++++++-------
 net/sched/sch_tbf.c       |  7 +++++--
 21 files changed, 91 insertions(+), 49 deletions(-)

diff --git a/include/net/codel.h b/include/net/codel.h
index 267e702..d168aca 100644
--- a/include/net/codel.h
+++ b/include/net/codel.h
@@ -162,12 +162,14 @@ struct codel_vars {
  * struct codel_stats - contains codel shared variables and stats
  * @maxpacket:	largest packet we've seen so far
  * @drop_count:	temp count of dropped packets in dequeue()
+ * @drop_len:	bytes of dropped packets in dequeue()
  * ecn_mark:	number of packets we ECN marked instead of dropping
  * ce_mark:	number of packets CE marked because sojourn time was above ce_threshold
  */
 struct codel_stats {
 	u32		maxpacket;
 	u32		drop_count;
+	u32		drop_len;
 	u32		ecn_mark;
 	u32		ce_mark;
 };
@@ -308,6 +310,7 @@ static struct sk_buff *codel_dequeue(struct Qdisc *sch,
 								  vars->rec_inv_sqrt);
 					goto end;
 				}
+				stats->drop_len += qdisc_pkt_len(skb);
 				qdisc_drop(skb, sch);
 				stats->drop_count++;
 				skb = dequeue_func(vars, sch);
@@ -330,6 +333,7 @@ static struct sk_buff *codel_dequeue(struct Qdisc *sch,
 		if (params->ecn && INET_ECN_set_ce(skb)) {
 			stats->ecn_mark++;
 		} else {
+			stats->drop_len += qdisc_pkt_len(skb);
 			qdisc_drop(skb, sch);
 			stats->drop_count++;
 
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 4dba266..86df083 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -396,7 +396,8 @@ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue,
 			      struct Qdisc *qdisc);
 void qdisc_reset(struct Qdisc *qdisc);
 void qdisc_destroy(struct Qdisc *qdisc);
-void qdisc_tree_decrease_qlen(struct Qdisc *qdisc, unsigned int n);
+void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, unsigned int n,
+			       unsigned int len);
 struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 			  const struct Qdisc_ops *ops);
 struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue,
@@ -707,7 +708,7 @@ static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new,
 	old = *pold;
 	*pold = new;
 	if (old != NULL) {
-		qdisc_tree_decrease_qlen(old, old->q.qlen);
+		qdisc_tree_reduce_backlog(old, old->q.qlen, old->qstats.backlog);
 		qdisc_reset(old);
 	}
 	sch_tree_unlock(sch);
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index af1acf0..95b560f 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -744,14 +744,15 @@ static u32 qdisc_alloc_handle(struct net_device *dev)
 	return 0;
 }
 
-void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
+void qdisc_tree_reduce_backlog(struct Qdisc *sch, unsigned int n,
+			       unsigned int len)
 {
 	const struct Qdisc_class_ops *cops;
 	unsigned long cl;
 	u32 parentid;
 	int drops;
 
-	if (n == 0)
+	if (n == 0 && len == 0)
 		return;
 	drops = max_t(int, n, 0);
 	rcu_read_lock();
@@ -774,11 +775,12 @@ void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
 			cops->put(sch, cl);
 		}
 		sch->q.qlen -= n;
+		sch->qstats.backlog -= len;
 		__qdisc_qstats_drop(sch, drops);
 	}
 	rcu_read_unlock();
 }
-EXPORT_SYMBOL(qdisc_tree_decrease_qlen);
+EXPORT_SYMBOL(qdisc_tree_reduce_backlog);
 
 static void notify_and_destroy(struct net *net, struct sk_buff *skb,
 			       struct nlmsghdr *n, u32 clid,
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 7f8474c..baafddf 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1909,7 +1909,7 @@ static int cbq_delete(struct Qdisc *sch, unsigned long arg)
 {
 	struct cbq_sched_data *q = qdisc_priv(sch);
 	struct cbq_class *cl = (struct cbq_class *)arg;
-	unsigned int qlen;
+	unsigned int qlen, backlog;
 
 	if (cl->filters || cl->children || cl == &q->link)
 		return -EBUSY;
@@ -1917,8 +1917,9 @@ static int cbq_delete(struct Qdisc *sch, unsigned long arg)
 	sch_tree_lock(sch);
 
 	qlen = cl->q->q.qlen;
+	backlog = cl->q->qstats.backlog;
 	qdisc_reset(cl->q);
-	qdisc_tree_decrease_qlen(cl->q, qlen);
+	qdisc_tree_reduce_backlog(cl->q, qlen, backlog);
 
 	if (cl->next_alive)
 		cbq_deactivate_class(cl);
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index 5ffb8b8..0a08c86 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -128,8 +128,8 @@ static void choke_drop_by_idx(struct Qdisc *sch, unsigned int idx)
 		choke_zap_tail_holes(q);
 
 	qdisc_qstats_backlog_dec(sch, skb);
+	qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(skb));
 	qdisc_drop(skb, sch);
-	qdisc_tree_decrease_qlen(sch, 1);
 	--sch->q.qlen;
 }
 
@@ -456,6 +456,7 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt)
 		old = q->tab;
 		if (old) {
 			unsigned int oqlen = sch->q.qlen, tail = 0;
+			unsigned dropped = 0;
 
 			while (q->head != q->tail) {
 				struct sk_buff *skb = q->tab[q->head];
@@ -467,11 +468,12 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt)
 					ntab[tail++] = skb;
 					continue;
 				}
+				dropped += qdisc_pkt_len(skb);
 				qdisc_qstats_backlog_dec(sch, skb);
 				--sch->q.qlen;
 				qdisc_drop(skb, sch);
 			}
-			qdisc_tree_decrease_qlen(sch, oqlen - sch->q.qlen);
+			qdisc_tree_reduce_backlog(sch, oqlen - sch->q.qlen, dropped);
 			q->head = 0;
 			q->tail = tail;
 		}
diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c
index 535007d..9b7e298 100644
--- a/net/sched/sch_codel.c
+++ b/net/sched/sch_codel.c
@@ -79,12 +79,13 @@ static struct sk_buff *codel_qdisc_dequeue(struct Qdisc *sch)
 
 	skb = codel_dequeue(sch, &q->params, &q->vars, &q->stats, dequeue);
 
-	/* We cant call qdisc_tree_decrease_qlen() if our qlen is 0,
+	/* We cant call qdisc_tree_reduce_backlog() if our qlen is 0,
 	 * or HTB crashes. Defer it for next round.
 	 */
 	if (q->stats.drop_count && sch->q.qlen) {
-		qdisc_tree_decrease_qlen(sch, q->stats.drop_count);
+		qdisc_tree_reduce_backlog(sch, q->stats.drop_count, q->stats.drop_len);
 		q->stats.drop_count = 0;
+		q->stats.drop_len = 0;
 	}
 	if (skb)
 		qdisc_bstats_update(sch, skb);
@@ -116,7 +117,7 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct codel_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_CODEL_MAX + 1];
-	unsigned int qlen;
+	unsigned int qlen, dropped = 0;
 	int err;
 
 	if (!opt)
@@ -156,10 +157,11 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt)
 	while (sch->q.qlen > sch->limit) {
 		struct sk_buff *skb = __skb_dequeue(&sch->q);
 
+		dropped += qdisc_pkt_len(skb);
 		qdisc_qstats_backlog_dec(sch, skb);
 		qdisc_drop(skb, sch);
 	}
-	qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen);
+	qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped);
 
 	sch_tree_unlock(sch);
 	return 0;
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index c76cdd4..d6e3ad4 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -53,9 +53,10 @@ static struct drr_class *drr_find_class(struct Qdisc *sch, u32 classid)
 static void drr_purge_queue(struct drr_class *cl)
 {
 	unsigned int len = cl->qdisc->q.qlen;
+	unsigned int backlog = cl->qdisc->qstats.backlog;
 
 	qdisc_reset(cl->qdisc);
-	qdisc_tree_decrease_qlen(cl->qdisc, len);
+	qdisc_tree_reduce_backlog(cl->qdisc, len, backlog);
 }
 
 static const struct nla_policy drr_policy[TCA_DRR_MAX + 1] = {
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 109b232..3c6a47d 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -662,6 +662,7 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt)
 	struct fq_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_FQ_MAX + 1];
 	int err, drop_count = 0;
+	unsigned drop_len = 0;
 	u32 fq_log;
 
 	if (!opt)
@@ -736,10 +737,11 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt)
 
 		if (!skb)
 			break;
+		drop_len += qdisc_pkt_len(skb);
 		kfree_skb(skb);
 		drop_count++;
 	}
-	qdisc_tree_decrease_qlen(sch, drop_count);
+	qdisc_tree_reduce_backlog(sch, drop_count, drop_len);
 
 	sch_tree_unlock(sch);
 	return err;
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 4c834e9..d3fc8f9 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -175,7 +175,7 @@ static unsigned int fq_codel_qdisc_drop(struct Qdisc *sch)
 static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 {
 	struct fq_codel_sched_data *q = qdisc_priv(sch);
-	unsigned int idx;
+	unsigned int idx, prev_backlog;
 	struct fq_codel_flow *flow;
 	int uninitialized_var(ret);
 
@@ -203,6 +203,7 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	if (++sch->q.qlen <= sch->limit)
 		return NET_XMIT_SUCCESS;
 
+	prev_backlog = sch->qstats.backlog;
 	q->drop_overlimit++;
 	/* Return Congestion Notification only if we dropped a packet
 	 * from this flow.
@@ -211,7 +212,7 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		return NET_XMIT_CN;
 
 	/* As we dropped a packet, better let upper stack know this */
-	qdisc_tree_decrease_qlen(sch, 1);
+	qdisc_tree_reduce_backlog(sch, 1, prev_backlog - sch->qstats.backlog);
 	return NET_XMIT_SUCCESS;
 }
 
@@ -241,6 +242,7 @@ static struct sk_buff *fq_codel_dequeue(struct Qdisc *sch)
 	struct fq_codel_flow *flow;
 	struct list_head *head;
 	u32 prev_drop_count, prev_ecn_mark;
+	unsigned int prev_backlog;
 
 begin:
 	head = &q->new_flows;
@@ -259,6 +261,7 @@ begin:
 
 	prev_drop_count = q->cstats.drop_count;
 	prev_ecn_mark = q->cstats.ecn_mark;
+	prev_backlog = sch->qstats.backlog;
 
 	skb = codel_dequeue(sch, &q->cparams, &flow->cvars, &q->cstats,
 			    dequeue);
@@ -276,12 +279,14 @@ begin:
 	}
 	qdisc_bstats_update(sch, skb);
 	flow->deficit -= qdisc_pkt_len(skb);
-	/* We cant call qdisc_tree_decrease_qlen() if our qlen is 0,
+	/* We cant call qdisc_tree_reduce_backlog() if our qlen is 0,
 	 * or HTB crashes. Defer it for next round.
 	 */
 	if (q->cstats.drop_count && sch->q.qlen) {
-		qdisc_tree_decrease_qlen(sch, q->cstats.drop_count);
+		qdisc_tree_reduce_backlog(sch, q->cstats.drop_count,
+					  q->cstats.drop_len);
 		q->cstats.drop_count = 0;
+		q->cstats.drop_len = 0;
 	}
 	return skb;
 }
@@ -372,11 +377,13 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt)
 	while (sch->q.qlen > sch->limit) {
 		struct sk_buff *skb = fq_codel_dequeue(sch);
 
+		q->cstats.drop_len += qdisc_pkt_len(skb);
 		kfree_skb(skb);
 		q->cstats.drop_count++;
 	}
-	qdisc_tree_decrease_qlen(sch, q->cstats.drop_count);
+	qdisc_tree_reduce_backlog(sch, q->cstats.drop_count, q->cstats.drop_len);
 	q->cstats.drop_count = 0;
+	q->cstats.drop_len = 0;
 
 	sch_tree_unlock(sch);
 	return 0;
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 089f3b6..d783d7c 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -895,9 +895,10 @@ static void
 hfsc_purge_queue(struct Qdisc *sch, struct hfsc_class *cl)
 {
 	unsigned int len = cl->qdisc->q.qlen;
+	unsigned int backlog = cl->qdisc->qstats.backlog;
 
 	qdisc_reset(cl->qdisc);
-	qdisc_tree_decrease_qlen(cl->qdisc, len);
+	qdisc_tree_reduce_backlog(cl->qdisc, len, backlog);
 }
 
 static void
diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c
index 86b04e3..13d6f83 100644
--- a/net/sched/sch_hhf.c
+++ b/net/sched/sch_hhf.c
@@ -382,6 +382,7 @@ static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	struct hhf_sched_data *q = qdisc_priv(sch);
 	enum wdrr_bucket_idx idx;
 	struct wdrr_bucket *bucket;
+	unsigned int prev_backlog;
 
 	idx = hhf_classify(skb, sch);
 
@@ -409,6 +410,7 @@ static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	if (++sch->q.qlen <= sch->limit)
 		return NET_XMIT_SUCCESS;
 
+	prev_backlog = sch->qstats.backlog;
 	q->drop_overlimit++;
 	/* Return Congestion Notification only if we dropped a packet from this
 	 * bucket.
@@ -417,7 +419,7 @@ static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		return NET_XMIT_CN;
 
 	/* As we dropped a packet, better let upper stack know this. */
-	qdisc_tree_decrease_qlen(sch, 1);
+	qdisc_tree_reduce_backlog(sch, 1, prev_backlog - sch->qstats.backlog);
 	return NET_XMIT_SUCCESS;
 }
 
@@ -527,7 +529,7 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct hhf_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_HHF_MAX + 1];
-	unsigned int qlen;
+	unsigned int qlen, prev_backlog;
 	int err;
 	u64 non_hh_quantum;
 	u32 new_quantum = q->quantum;
@@ -577,12 +579,14 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt)
 	}
 
 	qlen = sch->q.qlen;
+	prev_backlog = sch->qstats.backlog;
 	while (sch->q.qlen > sch->limit) {
 		struct sk_buff *skb = hhf_dequeue(sch);
 
 		kfree_skb(skb);
 	}
-	qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen);
+	qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen,
+				  prev_backlog - sch->qstats.backlog);
 
 	sch_tree_unlock(sch);
 	return 0;
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 0efbcf3..846a7f9 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1265,7 +1265,6 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg)
 {
 	struct htb_sched *q = qdisc_priv(sch);
 	struct htb_class *cl = (struct htb_class *)arg;
-	unsigned int qlen;
 	struct Qdisc *new_q = NULL;
 	int last_child = 0;
 
@@ -1285,9 +1284,11 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg)
 	sch_tree_lock(sch);
 
 	if (!cl->level) {
-		qlen = cl->un.leaf.q->q.qlen;
+		unsigned int qlen = cl->un.leaf.q->q.qlen;
+		unsigned int backlog = cl->un.leaf.q->qstats.backlog;
+
 		qdisc_reset(cl->un.leaf.q);
-		qdisc_tree_decrease_qlen(cl->un.leaf.q, qlen);
+		qdisc_tree_reduce_backlog(cl->un.leaf.q, qlen, backlog);
 	}
 
 	/* delete from hash and active; remainder in destroy_class */
@@ -1421,10 +1422,11 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 		sch_tree_lock(sch);
 		if (parent && !parent->level) {
 			unsigned int qlen = parent->un.leaf.q->q.qlen;
+			unsigned int backlog = parent->un.leaf.q->qstats.backlog;
 
 			/* turn parent into inner node */
 			qdisc_reset(parent->un.leaf.q);
-			qdisc_tree_decrease_qlen(parent->un.leaf.q, qlen);
+			qdisc_tree_reduce_backlog(parent->un.leaf.q, qlen, backlog);
 			qdisc_destroy(parent->un.leaf.q);
 			if (parent->prio_activity)
 				htb_deactivate(q, parent);
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index a0103a1..bcdd54b 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -218,7 +218,8 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt)
 		if (q->queues[i] != &noop_qdisc) {
 			struct Qdisc *child = q->queues[i];
 			q->queues[i] = &noop_qdisc;
-			qdisc_tree_decrease_qlen(child, child->q.qlen);
+			qdisc_tree_reduce_backlog(child, child->q.qlen,
+						  child->qstats.backlog);
 			qdisc_destroy(child);
 		}
 	}
@@ -238,8 +239,9 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt)
 				q->queues[i] = child;
 
 				if (old != &noop_qdisc) {
-					qdisc_tree_decrease_qlen(old,
-								 old->q.qlen);
+					qdisc_tree_reduce_backlog(old,
+								  old->q.qlen,
+								  old->qstats.backlog);
 					qdisc_destroy(old);
 				}
 				sch_tree_unlock(sch);
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 0a6ddaf..9640bb3 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -598,7 +598,8 @@ deliver:
 				if (unlikely(err != NET_XMIT_SUCCESS)) {
 					if (net_xmit_drop_count(err)) {
 						qdisc_qstats_drop(sch);
-						qdisc_tree_decrease_qlen(sch, 1);
+						qdisc_tree_reduce_backlog(sch, 1,
+									  qdisc_pkt_len(skb));
 					}
 				}
 				goto tfifo_dequeue;
diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c
index b783a44..71ae3b9 100644
--- a/net/sched/sch_pie.c
+++ b/net/sched/sch_pie.c
@@ -183,7 +183,7 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct pie_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_PIE_MAX + 1];
-	unsigned int qlen;
+	unsigned int qlen, dropped = 0;
 	int err;
 
 	if (!opt)
@@ -232,10 +232,11 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt)
 	while (sch->q.qlen > sch->limit) {
 		struct sk_buff *skb = __skb_dequeue(&sch->q);
 
+		dropped += qdisc_pkt_len(skb);
 		qdisc_qstats_backlog_dec(sch, skb);
 		qdisc_drop(skb, sch);
 	}
-	qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen);
+	qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped);
 
 	sch_tree_unlock(sch);
 	return 0;
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index 1b4aaec..fee1b15 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -191,7 +191,7 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt)
 		struct Qdisc *child = q->queues[i];
 		q->queues[i] = &noop_qdisc;
 		if (child != &noop_qdisc) {
-			qdisc_tree_decrease_qlen(child, child->q.qlen);
+			qdisc_tree_reduce_backlog(child, child->q.qlen, child->qstats.backlog);
 			qdisc_destroy(child);
 		}
 	}
@@ -210,8 +210,9 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt)
 				q->queues[i] = child;
 
 				if (old != &noop_qdisc) {
-					qdisc_tree_decrease_qlen(old,
-								 old->q.qlen);
+					qdisc_tree_reduce_backlog(old,
+								  old->q.qlen,
+								  old->qstats.backlog);
 					qdisc_destroy(old);
 				}
 				sch_tree_unlock(sch);
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index b5c52ca..8d2d8d9 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -220,9 +220,10 @@ static struct qfq_class *qfq_find_class(struct Qdisc *sch, u32 classid)
 static void qfq_purge_queue(struct qfq_class *cl)
 {
 	unsigned int len = cl->qdisc->q.qlen;
+	unsigned int backlog = cl->qdisc->qstats.backlog;
 
 	qdisc_reset(cl->qdisc);
-	qdisc_tree_decrease_qlen(cl->qdisc, len);
+	qdisc_tree_reduce_backlog(cl->qdisc, len, backlog);
 }
 
 static const struct nla_policy qfq_policy[TCA_QFQ_MAX + 1] = {
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index d5abcee..8c0508c 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -210,7 +210,8 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt)
 	q->flags = ctl->flags;
 	q->limit = ctl->limit;
 	if (child) {
-		qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen);
+		qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen,
+					  q->qdisc->qstats.backlog);
 		qdisc_destroy(q->qdisc);
 		q->qdisc = child;
 	}
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index 0e74e55..c696116 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -510,7 +510,8 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt)
 
 	sch_tree_lock(sch);
 
-	qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen);
+	qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen,
+				  q->qdisc->qstats.backlog);
 	qdisc_destroy(q->qdisc);
 	q->qdisc = child;
 
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 3abab53..498f0a2 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -346,7 +346,7 @@ static int
 sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 {
 	struct sfq_sched_data *q = qdisc_priv(sch);
-	unsigned int hash;
+	unsigned int hash, dropped;
 	sfq_index x, qlen;
 	struct sfq_slot *slot;
 	int uninitialized_var(ret);
@@ -461,7 +461,7 @@ enqueue:
 		return NET_XMIT_SUCCESS;
 
 	qlen = slot->qlen;
-	sfq_drop(sch);
+	dropped = sfq_drop(sch);
 	/* Return Congestion Notification only if we dropped a packet
 	 * from this flow.
 	 */
@@ -469,7 +469,7 @@ enqueue:
 		return NET_XMIT_CN;
 
 	/* As we dropped a packet, better let upper stack know this */
-	qdisc_tree_decrease_qlen(sch, 1);
+	qdisc_tree_reduce_backlog(sch, 1, dropped);
 	return NET_XMIT_SUCCESS;
 }
 
@@ -537,6 +537,7 @@ static void sfq_rehash(struct Qdisc *sch)
 	struct sfq_slot *slot;
 	struct sk_buff_head list;
 	int dropped = 0;
+	unsigned int drop_len = 0;
 
 	__skb_queue_head_init(&list);
 
@@ -565,6 +566,7 @@ static void sfq_rehash(struct Qdisc *sch)
 			if (x >= SFQ_MAX_FLOWS) {
 drop:
 				qdisc_qstats_backlog_dec(sch, skb);
+				drop_len += qdisc_pkt_len(skb);
 				kfree_skb(skb);
 				dropped++;
 				continue;
@@ -594,7 +596,7 @@ drop:
 		}
 	}
 	sch->q.qlen -= dropped;
-	qdisc_tree_decrease_qlen(sch, dropped);
+	qdisc_tree_reduce_backlog(sch, dropped, drop_len);
 }
 
 static void sfq_perturbation(unsigned long arg)
@@ -618,7 +620,7 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt)
 	struct sfq_sched_data *q = qdisc_priv(sch);
 	struct tc_sfq_qopt *ctl = nla_data(opt);
 	struct tc_sfq_qopt_v1 *ctl_v1 = NULL;
-	unsigned int qlen;
+	unsigned int qlen, dropped = 0;
 	struct red_parms *p = NULL;
 
 	if (opt->nla_len < nla_attr_size(sizeof(*ctl)))
@@ -667,8 +669,8 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt)
 
 	qlen = sch->q.qlen;
 	while (sch->q.qlen > q->limit)
-		sfq_drop(sch);
-	qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen);
+		dropped += sfq_drop(sch);
+	qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped);
 
 	del_timer(&q->perturb_timer);
 	if (q->perturb_period) {
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 56a1aef..c2fbde7 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -160,6 +160,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch)
 	struct tbf_sched_data *q = qdisc_priv(sch);
 	struct sk_buff *segs, *nskb;
 	netdev_features_t features = netif_skb_features(skb);
+	unsigned int len = 0, prev_len = qdisc_pkt_len(skb);
 	int ret, nb;
 
 	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
@@ -172,6 +173,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch)
 		nskb = segs->next;
 		segs->next = NULL;
 		qdisc_skb_cb(segs)->pkt_len = segs->len;
+		len += segs->len;
 		ret = qdisc_enqueue(segs, q->qdisc);
 		if (ret != NET_XMIT_SUCCESS) {
 			if (net_xmit_drop_count(ret))
@@ -183,7 +185,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch)
 	}
 	sch->q.qlen += nb;
 	if (nb > 1)
-		qdisc_tree_decrease_qlen(sch, 1 - nb);
+		qdisc_tree_reduce_backlog(sch, 1 - nb, prev_len - len);
 	consume_skb(skb);
 	return nb > 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP;
 }
@@ -399,7 +401,8 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
 
 	sch_tree_lock(sch);
 	if (child) {
-		qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen);
+		qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen,
+					  q->qdisc->qstats.backlog);
 		qdisc_destroy(q->qdisc);
 		q->qdisc = child;
 	}
-- 
2.1.0


From 2e51d47882393c2dc54a276324d6aa9582ddf9d5 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Thu, 25 Feb 2016 14:55:02 -0800
Subject: [PATCH 24/38] sch_htb: update backlog as well

[ Upstream commit 431e3a8e36a05a37126f34b41aa3a5a6456af04e ]

We saw qlen!=0 but backlog==0 on our production machine:

qdisc htb 1: dev eth0 root refcnt 2 r2q 10 default 1 direct_packets_stat 0 ver 3.17
 Sent 172680457356 bytes 222469449 pkt (dropped 0, overlimits 123575834 requeues 0)
 backlog 0b 72p requeues 0

The problem is we only count qlen for HTB qdisc but not backlog.
We need to update backlog too when we update qlen, so that we
can at least know the average packet length.

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_htb.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 846a7f9..87b02ed3 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -600,6 +600,7 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		htb_activate(q, cl);
 	}
 
+	qdisc_qstats_backlog_inc(sch, skb);
 	sch->q.qlen++;
 	return NET_XMIT_SUCCESS;
 }
@@ -889,6 +890,7 @@ static struct sk_buff *htb_dequeue(struct Qdisc *sch)
 ok:
 		qdisc_bstats_update(sch, skb);
 		qdisc_unthrottled(sch);
+		qdisc_qstats_backlog_dec(sch, skb);
 		sch->q.qlen--;
 		return skb;
 	}
@@ -955,6 +957,7 @@ static unsigned int htb_drop(struct Qdisc *sch)
 			unsigned int len;
 			if (cl->un.leaf.q->ops->drop &&
 			    (len = cl->un.leaf.q->ops->drop(cl->un.leaf.q))) {
+				sch->qstats.backlog -= len;
 				sch->q.qlen--;
 				if (!cl->un.leaf.q->q.qlen)
 					htb_deactivate(q, cl);
@@ -984,12 +987,12 @@ static void htb_reset(struct Qdisc *sch)
 			}
 			cl->prio_activity = 0;
 			cl->cmode = HTB_CAN_SEND;
-
 		}
 	}
 	qdisc_watchdog_cancel(&q->watchdog);
 	__skb_queue_purge(&q->direct_queue);
 	sch->q.qlen = 0;
+	sch->qstats.backlog = 0;
 	memset(q->hlevel, 0, sizeof(q->hlevel));
 	memset(q->row_mask, 0, sizeof(q->row_mask));
 	for (i = 0; i < TC_HTB_NUMPRIO; i++)
-- 
2.1.0


From 8d0a112067346307f85fa7f22568486c5d74a26f Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Thu, 25 Feb 2016 14:55:03 -0800
Subject: [PATCH 25/38] sch_dsmark: update backlog as well

[ Upstream commit bdf17661f63a79c3cb4209b970b1cc39e34f7543 ]

Similarly, we need to update backlog too when we update qlen.

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_dsmark.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index cfddb1c..d0dff0c 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -258,6 +258,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		return err;
 	}
 
+	qdisc_qstats_backlog_inc(sch, skb);
 	sch->q.qlen++;
 
 	return NET_XMIT_SUCCESS;
@@ -280,6 +281,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch)
 		return NULL;
 
 	qdisc_bstats_update(sch, skb);
+	qdisc_qstats_backlog_dec(sch, skb);
 	sch->q.qlen--;
 
 	index = skb->tc_index & (p->indices - 1);
@@ -395,6 +397,7 @@ static void dsmark_reset(struct Qdisc *sch)
 
 	pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p);
 	qdisc_reset(p->q);
+	sch->qstats.backlog = 0;
 	sch->q.qlen = 0;
 }
 
-- 
2.1.0


From c1c7e5b7364490a19e677d2504bd734e427ba63e Mon Sep 17 00:00:00 2001
From: Neil Horman <nhorman@tuxdriver.com>
Date: Mon, 2 May 2016 12:20:15 -0400
Subject: [PATCH 26/38] netem: Segment GSO packets on enqueue

[ Upstream commit 6071bd1aa13ed9e41824bafad845b7b7f4df5cfd ]

This was recently reported to me, and reproduced on the latest net kernel,
when attempting to run netperf from a host that had a netem qdisc attached
to the egress interface:

[  788.073771] ---------------------[ cut here ]---------------------------
[  788.096716] WARNING: at net/core/dev.c:2253 skb_warn_bad_offload+0xcd/0xda()
[  788.129521] bnx2: caps=(0x00000001801949b3, 0x0000000000000000) len=2962
data_len=0 gso_size=1448 gso_type=1 ip_summed=3
[  788.182150] Modules linked in: sch_netem kvm_amd kvm crc32_pclmul ipmi_ssif
ghash_clmulni_intel sp5100_tco amd64_edac_mod aesni_intel lrw gf128mul
glue_helper ablk_helper edac_mce_amd cryptd pcspkr sg edac_core hpilo ipmi_si
i2c_piix4 k10temp fam15h_power hpwdt ipmi_msghandler shpchp acpi_power_meter
pcc_cpufreq nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c
sd_mod crc_t10dif crct10dif_generic mgag200 syscopyarea sysfillrect sysimgblt
i2c_algo_bit drm_kms_helper ahci ata_generic pata_acpi ttm libahci
crct10dif_pclmul pata_atiixp tg3 libata crct10dif_common drm crc32c_intel ptp
serio_raw bnx2 r8169 hpsa pps_core i2c_core mii dm_mirror dm_region_hash dm_log
dm_mod
[  788.465294] CPU: 16 PID: 0 Comm: swapper/16 Tainted: G        W
------------   3.10.0-327.el7.x86_64 #1
[  788.511521] Hardware name: HP ProLiant DL385p Gen8, BIOS A28 12/17/2012
[  788.542260]  ffff880437c036b8 f7afc56532a53db9 ffff880437c03670
ffffffff816351f1
[  788.576332]  ffff880437c036a8 ffffffff8107b200 ffff880633e74200
ffff880231674000
[  788.611943]  0000000000000001 0000000000000003 0000000000000000
ffff880437c03710
[  788.647241] Call Trace:
[  788.658817]  <IRQ>  [<ffffffff816351f1>] dump_stack+0x19/0x1b
[  788.686193]  [<ffffffff8107b200>] warn_slowpath_common+0x70/0xb0
[  788.713803]  [<ffffffff8107b29c>] warn_slowpath_fmt+0x5c/0x80
[  788.741314]  [<ffffffff812f92f3>] ? ___ratelimit+0x93/0x100
[  788.767018]  [<ffffffff81637f49>] skb_warn_bad_offload+0xcd/0xda
[  788.796117]  [<ffffffff8152950c>] skb_checksum_help+0x17c/0x190
[  788.823392]  [<ffffffffa01463a1>] netem_enqueue+0x741/0x7c0 [sch_netem]
[  788.854487]  [<ffffffff8152cb58>] dev_queue_xmit+0x2a8/0x570
[  788.880870]  [<ffffffff8156ae1d>] ip_finish_output+0x53d/0x7d0
...

The problem occurs because netem is not prepared to handle GSO packets (as it
uses skb_checksum_help in its enqueue path, which cannot manipulate these
frames).

The solution I think is to simply segment the skb in a simmilar fashion to the
way we do in __dev_queue_xmit (via validate_xmit_skb), with some minor changes.
When we decide to corrupt an skb, if the frame is GSO, we segment it, corrupt
the first segment, and enqueue the remaining ones.

tested successfully by myself on the latest net kernel, to which this applies

Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
CC: Jamal Hadi Salim <jhs@mojatatu.com>
CC: "David S. Miller" <davem@davemloft.net>
CC: netem@lists.linux-foundation.org
CC: eric.dumazet@gmail.com
CC: stephen@networkplumber.org
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_netem.c | 61 +++++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 59 insertions(+), 2 deletions(-)

diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 9640bb3..4befe97 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -395,6 +395,25 @@ static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch)
 	sch->q.qlen++;
 }
 
+/* netem can't properly corrupt a megapacket (like we get from GSO), so instead
+ * when we statistically choose to corrupt one, we instead segment it, returning
+ * the first packet to be corrupted, and re-enqueue the remaining frames
+ */
+static struct sk_buff *netem_segment(struct sk_buff *skb, struct Qdisc *sch)
+{
+	struct sk_buff *segs;
+	netdev_features_t features = netif_skb_features(skb);
+
+	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+
+	if (IS_ERR_OR_NULL(segs)) {
+		qdisc_reshape_fail(skb, sch);
+		return NULL;
+	}
+	consume_skb(skb);
+	return segs;
+}
+
 /*
  * Insert one skb into qdisc.
  * Note: parent depends on return value to account for queue length.
@@ -407,7 +426,11 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	/* We don't fill cb now as skb_unshare() may invalidate it */
 	struct netem_skb_cb *cb;
 	struct sk_buff *skb2;
+	struct sk_buff *segs = NULL;
+	unsigned int len = 0, last_len, prev_len = qdisc_pkt_len(skb);
+	int nb = 0;
 	int count = 1;
+	int rc = NET_XMIT_SUCCESS;
 
 	/* Random duplication */
 	if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor))
@@ -453,10 +476,23 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	 * do it now in software before we mangle it.
 	 */
 	if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor)) {
+		if (skb_is_gso(skb)) {
+			segs = netem_segment(skb, sch);
+			if (!segs)
+				return NET_XMIT_DROP;
+		} else {
+			segs = skb;
+		}
+
+		skb = segs;
+		segs = segs->next;
+
 		if (!(skb = skb_unshare(skb, GFP_ATOMIC)) ||
 		    (skb->ip_summed == CHECKSUM_PARTIAL &&
-		     skb_checksum_help(skb)))
-			return qdisc_drop(skb, sch);
+		     skb_checksum_help(skb))) {
+			rc = qdisc_drop(skb, sch);
+			goto finish_segs;
+		}
 
 		skb->data[prandom_u32() % skb_headlen(skb)] ^=
 			1<<(prandom_u32() % 8);
@@ -516,6 +552,27 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		sch->qstats.requeues++;
 	}
 
+finish_segs:
+	if (segs) {
+		while (segs) {
+			skb2 = segs->next;
+			segs->next = NULL;
+			qdisc_skb_cb(segs)->pkt_len = segs->len;
+			last_len = segs->len;
+			rc = qdisc_enqueue(segs, sch);
+			if (rc != NET_XMIT_SUCCESS) {
+				if (net_xmit_drop_count(rc))
+					qdisc_qstats_drop(sch);
+			} else {
+				nb++;
+				len += last_len;
+			}
+			segs = skb2;
+		}
+		sch->q.qlen += nb;
+		if (nb > 1)
+			qdisc_tree_reduce_backlog(sch, 1 - nb, prev_len - len);
+	}
 	return NET_XMIT_SUCCESS;
 }
 
-- 
2.1.0


From 51a181c61c1d69a372bb77116501fdac7e197ae1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 3 May 2016 16:38:53 +0200
Subject: [PATCH 27/38] net: fec: only clear a queue's work bit if the queue
 was emptied
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 1c021bb717a70aaeaa4b25c91f43c2aeddd922de ]

In the receive path a queue's work bit was cleared unconditionally even
if fec_enet_rx_queue only read out a part of the available packets from
the hardware. This resulted in not reading any packets in the next napi
turn and so packets were delayed or lost.

The obvious fix is to only clear a queue's bit when the queue was
emptied.

Fixes: 4d494cdc92b3 ("net: fec: change data structure to support multiqueue")
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Lucas Stach <l.stach@pengutronix.de>
Tested-by: Fugang Duan <fugang.duan@nxp.com>
Acked-by: Fugang Duan <fugang.duan@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_main.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index b2a3220..f6147ff 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -1557,9 +1557,15 @@ fec_enet_rx(struct net_device *ndev, int budget)
 	struct fec_enet_private *fep = netdev_priv(ndev);
 
 	for_each_set_bit(queue_id, &fep->work_rx, FEC_ENET_MAX_RX_QS) {
-		clear_bit(queue_id, &fep->work_rx);
-		pkt_received += fec_enet_rx_queue(ndev,
+		int ret;
+
+		ret = fec_enet_rx_queue(ndev,
 					budget - pkt_received, queue_id);
+
+		if (ret < budget - pkt_received)
+			clear_bit(queue_id, &fep->work_rx);
+
+		pkt_received += ret;
 	}
 	return pkt_received;
 }
-- 
2.1.0


From 253265f81fbb0e86d2a718b21eed42ea5e4e5125 Mon Sep 17 00:00:00 2001
From: Kangjie Lu <kangjielu@gmail.com>
Date: Tue, 3 May 2016 16:35:05 -0400
Subject: [PATCH 28/38] net: fix infoleak in llc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit b8670c09f37bdf2847cc44f36511a53afc6161fd ]

The stack object “info” has a total size of 12 bytes. Its last byte
is padding which is not initialized and leaked via “put_cmsg”.

Signed-off-by: Kangjie Lu <kjlu@gatech.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/llc/af_llc.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 8dab4e5..bb8edb9 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -626,6 +626,7 @@ static void llc_cmsg_rcv(struct msghdr *msg, struct sk_buff *skb)
 	if (llc->cmsg_flags & LLC_CMSG_PKTINFO) {
 		struct llc_pktinfo info;
 
+		memset(&info, 0, sizeof(info));
 		info.lpi_ifindex = llc_sk(skb->sk)->dev->ifindex;
 		llc_pdu_decode_dsap(skb, &info.lpi_sap);
 		llc_pdu_decode_da(skb, info.lpi_mac);
-- 
2.1.0


From 4e1a2a4a0d66abf824b76f7f4ea35f1038b5c412 Mon Sep 17 00:00:00 2001
From: Kangjie Lu <kangjielu@gmail.com>
Date: Tue, 3 May 2016 16:46:24 -0400
Subject: [PATCH 29/38] net: fix infoleak in rtnetlink
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 5f8e44741f9f216e33736ea4ec65ca9ac03036e6 ]

The stack object “map” has a total size of 32 bytes. Its last 4
bytes are padding generated by compiler. These padding bytes are
not initialized and sent out via “nla_put”.

Signed-off-by: Kangjie Lu <kjlu@gatech.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index ca966f7..87b91ff 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1175,14 +1175,16 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb,
 
 static int rtnl_fill_link_ifmap(struct sk_buff *skb, struct net_device *dev)
 {
-	struct rtnl_link_ifmap map = {
-		.mem_start   = dev->mem_start,
-		.mem_end     = dev->mem_end,
-		.base_addr   = dev->base_addr,
-		.irq         = dev->irq,
-		.dma         = dev->dma,
-		.port        = dev->if_port,
-	};
+	struct rtnl_link_ifmap map;
+
+	memset(&map, 0, sizeof(map));
+	map.mem_start   = dev->mem_start;
+	map.mem_end     = dev->mem_end;
+	map.base_addr   = dev->base_addr;
+	map.irq         = dev->irq;
+	map.dma         = dev->dma;
+	map.port        = dev->if_port;
+
 	if (nla_put(skb, IFLA_MAP, sizeof(map), &map))
 		return -EMSGSIZE;
 
-- 
2.1.0


From c9afc28f9e83ff3a1f3c0879406cbc7141bb7244 Mon Sep 17 00:00:00 2001
From: Daniel Jurgens <danielj@mellanox.com>
Date: Wed, 4 May 2016 15:00:33 +0300
Subject: [PATCH 30/38] net/mlx4_en: Fix endianness bug in IPV6 csum
 calculation

[ Upstream commit 82d69203df634b4dfa765c94f60ce9482bcc44d6 ]

Use htons instead of unconditionally byte swapping nexthdr.  On a little
endian systems shifting the byte is correct behavior, but it results in
incorrect csums on big endian architectures.

Fixes: f8c6455bb04b ('net/mlx4_en: Extend checksum offloading by CHECKSUM COMPLETE')
Signed-off-by: Daniel Jurgens <danielj@mellanox.com>
Reviewed-by: Carol Soto <clsoto@us.ibm.com>
Tested-by: Carol Soto <clsoto@us.ibm.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_rx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index e7a5000..bbff8ec 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -704,7 +704,7 @@ static int get_fixed_ipv6_csum(__wsum hw_checksum, struct sk_buff *skb,
 
 	if (ipv6h->nexthdr == IPPROTO_FRAGMENT || ipv6h->nexthdr == IPPROTO_HOPOPTS)
 		return -1;
-	hw_checksum = csum_add(hw_checksum, (__force __wsum)(ipv6h->nexthdr << 8));
+	hw_checksum = csum_add(hw_checksum, (__force __wsum)htons(ipv6h->nexthdr));
 
 	csum_pseudo_hdr = csum_partial(&ipv6h->saddr,
 				       sizeof(ipv6h->saddr) + sizeof(ipv6h->daddr), 0);
-- 
2.1.0


From 7a747d7f2470c6472635cbab369b0954c4c52765 Mon Sep 17 00:00:00 2001
From: Ian Campbell <ian.campbell@docker.com>
Date: Wed, 4 May 2016 14:21:53 +0100
Subject: [PATCH 31/38] VSOCK: do not disconnect socket when peer has shutdown
 SEND only

[ Upstream commit dedc58e067d8c379a15a8a183c5db318201295bb ]

The peer may be expecting a reply having sent a request and then done a
shutdown(SHUT_WR), so tearing down the whole socket at this point seems
wrong and breaks for me with a client which does a SHUT_WR.

Looking at other socket family's stream_recvmsg callbacks doing a shutdown
here does not seem to be the norm and removing it does not seem to have
had any adverse effects that I can see.

I'm using Stefan's RFC virtio transport patches, I'm unsure of the impact
on the vmci transport.

Signed-off-by: Ian Campbell <ian.campbell@docker.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Stefan Hajnoczi <stefanha@redhat.com>
Cc: Claudio Imbrenda <imbrenda@linux.vnet.ibm.com>
Cc: Andy King <acking@vmware.com>
Cc: Dmitry Torokhov <dtor@vmware.com>
Cc: Jorgen Hansen <jhansen@vmware.com>
Cc: Adit Ranadive <aditr@vmware.com>
Cc: netdev@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/vmw_vsock/af_vsock.c | 21 +--------------------
 1 file changed, 1 insertion(+), 20 deletions(-)

diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 7fd1220..9b5bd6d 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1794,27 +1794,8 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	else if (sk->sk_shutdown & RCV_SHUTDOWN)
 		err = 0;
 
-	if (copied > 0) {
-		/* We only do these additional bookkeeping/notification steps
-		 * if we actually copied something out of the queue pair
-		 * instead of just peeking ahead.
-		 */
-
-		if (!(flags & MSG_PEEK)) {
-			/* If the other side has shutdown for sending and there
-			 * is nothing more to read, then modify the socket
-			 * state.
-			 */
-			if (vsk->peer_shutdown & SEND_SHUTDOWN) {
-				if (vsock_stream_has_data(vsk) <= 0) {
-					sk->sk_state = SS_UNCONNECTED;
-					sock_set_flag(sk, SOCK_DONE);
-					sk->sk_state_change(sk);
-				}
-			}
-		}
+	if (copied > 0)
 		err = copied;
-	}
 
 out_wait:
 	finish_wait(sk_sleep(sk), &wait);
-- 
2.1.0


From 8b8cca349c0cdadfcf378aba281ffd583e6a6e19 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Wed, 4 May 2016 16:18:45 +0200
Subject: [PATCH 32/38] net: bridge: fix old ioctl unlocked net device walk

[ Upstream commit 31ca0458a61a502adb7ed192bf9716c6d05791a5 ]

get_bridge_ifindices() is used from the old "deviceless" bridge ioctl
calls which aren't called with rtnl held. The comment above says that it is
called with rtnl but that is not really the case.
Here's a sample output from a test ASSERT_RTNL() which I put in
get_bridge_ifindices and executed "brctl show":
[  957.422726] RTNL: assertion failed at net/bridge//br_ioctl.c (30)
[  957.422925] CPU: 0 PID: 1862 Comm: brctl Tainted: G        W  O
4.6.0-rc4+ #157
[  957.423009] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996),
BIOS 1.8.1-20150318_183358- 04/01/2014
[  957.423009]  0000000000000000 ffff880058adfdf0 ffffffff8138dec5
0000000000000400
[  957.423009]  ffffffff81ce8380 ffff880058adfe58 ffffffffa05ead32
0000000000000001
[  957.423009]  00007ffec1a444b0 0000000000000400 ffff880053c19130
0000000000008940
[  957.423009] Call Trace:
[  957.423009]  [<ffffffff8138dec5>] dump_stack+0x85/0xc0
[  957.423009]  [<ffffffffa05ead32>]
br_ioctl_deviceless_stub+0x212/0x2e0 [bridge]
[  957.423009]  [<ffffffff81515beb>] sock_ioctl+0x22b/0x290
[  957.423009]  [<ffffffff8126ba75>] do_vfs_ioctl+0x95/0x700
[  957.423009]  [<ffffffff8126c159>] SyS_ioctl+0x79/0x90
[  957.423009]  [<ffffffff8163a4c0>] entry_SYSCALL_64_fastpath+0x23/0xc1

Since it only reads bridge ifindices, we can use rcu to safely walk the net
device list. Also remove the wrong rtnl comment above.

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_ioctl.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c
index 263b4de..60a3dbf 100644
--- a/net/bridge/br_ioctl.c
+++ b/net/bridge/br_ioctl.c
@@ -21,18 +21,19 @@
 #include <asm/uaccess.h>
 #include "br_private.h"
 
-/* called with RTNL */
 static int get_bridge_ifindices(struct net *net, int *indices, int num)
 {
 	struct net_device *dev;
 	int i = 0;
 
-	for_each_netdev(net, dev) {
+	rcu_read_lock();
+	for_each_netdev_rcu(net, dev) {
 		if (i >= num)
 			break;
 		if (dev->priv_flags & IFF_EBRIDGE)
 			indices[i++] = dev->ifindex;
 	}
+	rcu_read_unlock();
 
 	return i;
 }
-- 
2.1.0


From b8642cc0a0d626a3bec2c4b7e0c5425d28748aa4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Linus=20L=C3=BCssing?= <linus.luessing@c0d3.blue>
Date: Wed, 4 May 2016 17:25:02 +0200
Subject: [PATCH 33/38] bridge: fix igmp / mld query parsing
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 856ce5d083e14571d051301fe3c65b32b8cbe321 ]

With the newly introduced helper functions the skb pulling is hidden
in the checksumming function - and undone before returning to the
caller.

The IGMP and MLD query parsing functions in the bridge still
assumed that the skb is pointing to the beginning of the IGMP/MLD
message while it is now kept at the beginning of the IPv4/6 header.

If there is a querier somewhere else, then this either causes
the multicast snooping to stay disabled even though it could be
enabled. Or, if we have the querier enabled too, then this can
create unnecessary IGMP / MLD query messages on the link.

Fixing this by taking the offset between IP and IGMP/MLD header into
account, too.

Fixes: 9afd85c9e455 ("net: Export IGMP/MLD message validation code")
Reported-by: Simon Wunderlich <sw@simonwunderlich.de>
Signed-off-by: Linus Lüssing <linus.luessing@c0d3.blue>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 03661d9..ea98937 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1270,6 +1270,7 @@ static int br_ip4_multicast_query(struct net_bridge *br,
 	struct br_ip saddr;
 	unsigned long max_delay;
 	unsigned long now = jiffies;
+	unsigned int offset = skb_transport_offset(skb);
 	__be32 group;
 	int err = 0;
 
@@ -1280,14 +1281,14 @@ static int br_ip4_multicast_query(struct net_bridge *br,
 
 	group = ih->group;
 
-	if (skb->len == sizeof(*ih)) {
+	if (skb->len == offset + sizeof(*ih)) {
 		max_delay = ih->code * (HZ / IGMP_TIMER_SCALE);
 
 		if (!max_delay) {
 			max_delay = 10 * HZ;
 			group = 0;
 		}
-	} else if (skb->len >= sizeof(*ih3)) {
+	} else if (skb->len >= offset + sizeof(*ih3)) {
 		ih3 = igmpv3_query_hdr(skb);
 		if (ih3->nsrcs)
 			goto out;
@@ -1348,6 +1349,7 @@ static int br_ip6_multicast_query(struct net_bridge *br,
 	struct br_ip saddr;
 	unsigned long max_delay;
 	unsigned long now = jiffies;
+	unsigned int offset = skb_transport_offset(skb);
 	const struct in6_addr *group = NULL;
 	bool is_general_query;
 	int err = 0;
@@ -1357,8 +1359,8 @@ static int br_ip6_multicast_query(struct net_bridge *br,
 	    (port && port->state == BR_STATE_DISABLED))
 		goto out;
 
-	if (skb->len == sizeof(*mld)) {
-		if (!pskb_may_pull(skb, sizeof(*mld))) {
+	if (skb->len == offset + sizeof(*mld)) {
+		if (!pskb_may_pull(skb, offset + sizeof(*mld))) {
 			err = -EINVAL;
 			goto out;
 		}
@@ -1367,7 +1369,7 @@ static int br_ip6_multicast_query(struct net_bridge *br,
 		if (max_delay)
 			group = &mld->mld_mca;
 	} else {
-		if (!pskb_may_pull(skb, sizeof(*mld2q))) {
+		if (!pskb_may_pull(skb, offset + sizeof(*mld2q))) {
 			err = -EINVAL;
 			goto out;
 		}
-- 
2.1.0


From 730c48a1fbe786289815fcab07c6d96a36db14a0 Mon Sep 17 00:00:00 2001
From: Mikko Rapeli <mikko.rapeli@iki.fi>
Date: Sun, 24 Apr 2016 17:45:00 +0200
Subject: [PATCH 34/38] uapi glibc compat: fix compile errors when glibc
 net/if.h included before linux/if.h
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 4a91cb61bb995e5571098188092e296192309c77 ]

glibc's net/if.h contains copies of definitions from linux/if.h and these
conflict and cause build failures if both files are included by application
source code. Changes in uapi headers, which fixed header file dependencies to
include linux/if.h when it was needed, e.g. commit 1ffad83d, made the
net/if.h and linux/if.h incompatibilities visible as build failures for
userspace applications like iproute2 and xtables-addons.

This patch fixes compile errors when glibc net/if.h is included before
linux/if.h:

./linux/if.h:99:21: error: redeclaration of enumerator ‘IFF_NOARP’
./linux/if.h:98:23: error: redeclaration of enumerator ‘IFF_RUNNING’
./linux/if.h:97:26: error: redeclaration of enumerator ‘IFF_NOTRAILERS’
./linux/if.h:96:27: error: redeclaration of enumerator ‘IFF_POINTOPOINT’
./linux/if.h:95:24: error: redeclaration of enumerator ‘IFF_LOOPBACK’
./linux/if.h:94:21: error: redeclaration of enumerator ‘IFF_DEBUG’
./linux/if.h:93:25: error: redeclaration of enumerator ‘IFF_BROADCAST’
./linux/if.h:92:19: error: redeclaration of enumerator ‘IFF_UP’
./linux/if.h:252:8: error: redefinition of ‘struct ifconf’
./linux/if.h:203:8: error: redefinition of ‘struct ifreq’
./linux/if.h:169:8: error: redefinition of ‘struct ifmap’
./linux/if.h:107:23: error: redeclaration of enumerator ‘IFF_DYNAMIC’
./linux/if.h:106:25: error: redeclaration of enumerator ‘IFF_AUTOMEDIA’
./linux/if.h:105:23: error: redeclaration of enumerator ‘IFF_PORTSEL’
./linux/if.h:104:25: error: redeclaration of enumerator ‘IFF_MULTICAST’
./linux/if.h:103:21: error: redeclaration of enumerator ‘IFF_SLAVE’
./linux/if.h:102:22: error: redeclaration of enumerator ‘IFF_MASTER’
./linux/if.h:101:24: error: redeclaration of enumerator ‘IFF_ALLMULTI’
./linux/if.h:100:23: error: redeclaration of enumerator ‘IFF_PROMISC’

The cases where linux/if.h is included before net/if.h need a similar fix in
the glibc side, or the order of include files can be changed userspace
code as a workaround.

This change was tested in x86 userspace on Debian unstable with
scripts/headers_compile_test.sh:

$ make headers_install && \
  cd usr/include && ../../scripts/headers_compile_test.sh -l -k
...
cc -Wall -c -nostdinc -I /usr/lib/gcc/i586-linux-gnu/5/include -I /usr/lib/gcc/i586-linux-gnu/5/include-fixed -I . -I /home/mcfrisk/src/linux-2.6/usr/headers_compile_test_include.2uX2zH -I /home/mcfrisk/src/linux-2.6/usr/headers_compile_test_include.2uX2zH/i586-linux-gnu -o /dev/null ./linux/if.h_libc_before_kernel.h
PASSED libc before kernel test: ./linux/if.h

Reported-by: Jan Engelhardt <jengelh@inai.de>
Reported-by: Josh Boyer <jwboyer@fedoraproject.org>
Reported-by: Stephen Hemminger <shemming@brocade.com>
Reported-by: Waldemar Brodkorb <mail@waldemar-brodkorb.de>
Cc: Gabriel Laskar <gabriel@lse.epita.fr>
Signed-off-by: Mikko Rapeli <mikko.rapeli@iki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if.h          | 28 +++++++++++++++++++++++++
 include/uapi/linux/libc-compat.h | 44 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 72 insertions(+)

diff --git a/include/uapi/linux/if.h b/include/uapi/linux/if.h
index 9cf2394..752f5dc 100644
--- a/include/uapi/linux/if.h
+++ b/include/uapi/linux/if.h
@@ -19,14 +19,20 @@
 #ifndef _LINUX_IF_H
 #define _LINUX_IF_H
 
+#include <linux/libc-compat.h>          /* for compatibility with glibc */
 #include <linux/types.h>		/* for "__kernel_caddr_t" et al	*/
 #include <linux/socket.h>		/* for "struct sockaddr" et al	*/
 #include <linux/compiler.h>		/* for "__user" et al           */
 
+#if __UAPI_DEF_IF_IFNAMSIZ
 #define	IFNAMSIZ	16
+#endif /* __UAPI_DEF_IF_IFNAMSIZ */
 #define	IFALIASZ	256
 #include <linux/hdlc/ioctl.h>
 
+/* For glibc compatibility. An empty enum does not compile. */
+#if __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO != 0 && \
+    __UAPI_DEF_IF_NET_DEVICE_FLAGS != 0
 /**
  * enum net_device_flags - &struct net_device flags
  *
@@ -68,6 +74,8 @@
  * @IFF_ECHO: echo sent packets. Volatile.
  */
 enum net_device_flags {
+/* for compatibility with glibc net/if.h */
+#if __UAPI_DEF_IF_NET_DEVICE_FLAGS
 	IFF_UP				= 1<<0,  /* sysfs */
 	IFF_BROADCAST			= 1<<1,  /* volatile */
 	IFF_DEBUG			= 1<<2,  /* sysfs */
@@ -84,11 +92,17 @@ enum net_device_flags {
 	IFF_PORTSEL			= 1<<13, /* sysfs */
 	IFF_AUTOMEDIA			= 1<<14, /* sysfs */
 	IFF_DYNAMIC			= 1<<15, /* sysfs */
+#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS */
+#if __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO
 	IFF_LOWER_UP			= 1<<16, /* volatile */
 	IFF_DORMANT			= 1<<17, /* volatile */
 	IFF_ECHO			= 1<<18, /* volatile */
+#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO */
 };
+#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO != 0 && __UAPI_DEF_IF_NET_DEVICE_FLAGS != 0 */
 
+/* for compatibility with glibc net/if.h */
+#if __UAPI_DEF_IF_NET_DEVICE_FLAGS
 #define IFF_UP				IFF_UP
 #define IFF_BROADCAST			IFF_BROADCAST
 #define IFF_DEBUG			IFF_DEBUG
@@ -105,9 +119,13 @@ enum net_device_flags {
 #define IFF_PORTSEL			IFF_PORTSEL
 #define IFF_AUTOMEDIA			IFF_AUTOMEDIA
 #define IFF_DYNAMIC			IFF_DYNAMIC
+#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS */
+
+#if __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO
 #define IFF_LOWER_UP			IFF_LOWER_UP
 #define IFF_DORMANT			IFF_DORMANT
 #define IFF_ECHO			IFF_ECHO
+#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO */
 
 #define IFF_VOLATILE	(IFF_LOOPBACK|IFF_POINTOPOINT|IFF_BROADCAST|IFF_ECHO|\
 		IFF_MASTER|IFF_SLAVE|IFF_RUNNING|IFF_LOWER_UP|IFF_DORMANT)
@@ -166,6 +184,8 @@ enum {
  *	being very small might be worth keeping for clean configuration.
  */
 
+/* for compatibility with glibc net/if.h */
+#if __UAPI_DEF_IF_IFMAP
 struct ifmap {
 	unsigned long mem_start;
 	unsigned long mem_end;
@@ -175,6 +195,7 @@ struct ifmap {
 	unsigned char port;
 	/* 3 bytes spare */
 };
+#endif /* __UAPI_DEF_IF_IFMAP */
 
 struct if_settings {
 	unsigned int type;	/* Type of physical device or protocol */
@@ -200,6 +221,8 @@ struct if_settings {
  * remainder may be interface specific.
  */
 
+/* for compatibility with glibc net/if.h */
+#if __UAPI_DEF_IF_IFREQ
 struct ifreq {
 #define IFHWADDRLEN	6
 	union
@@ -223,6 +246,7 @@ struct ifreq {
 		struct	if_settings ifru_settings;
 	} ifr_ifru;
 };
+#endif /* __UAPI_DEF_IF_IFREQ */
 
 #define ifr_name	ifr_ifrn.ifrn_name	/* interface name 	*/
 #define ifr_hwaddr	ifr_ifru.ifru_hwaddr	/* MAC address 		*/
@@ -249,6 +273,8 @@ struct ifreq {
  * must know all networks accessible).
  */
 
+/* for compatibility with glibc net/if.h */
+#if __UAPI_DEF_IF_IFCONF
 struct ifconf  {
 	int	ifc_len;			/* size of buffer	*/
 	union {
@@ -256,6 +282,8 @@ struct ifconf  {
 		struct ifreq __user *ifcu_req;
 	} ifc_ifcu;
 };
+#endif /* __UAPI_DEF_IF_IFCONF */
+
 #define	ifc_buf	ifc_ifcu.ifcu_buf		/* buffer address	*/
 #define	ifc_req	ifc_ifcu.ifcu_req		/* array of structures	*/
 
diff --git a/include/uapi/linux/libc-compat.h b/include/uapi/linux/libc-compat.h
index 7d024ce..d5e38c7 100644
--- a/include/uapi/linux/libc-compat.h
+++ b/include/uapi/linux/libc-compat.h
@@ -51,6 +51,40 @@
 /* We have included glibc headers... */
 #if defined(__GLIBC__)
 
+/* Coordinate with glibc net/if.h header. */
+#if defined(_NET_IF_H)
+
+/* GLIBC headers included first so don't define anything
+ * that would already be defined. */
+
+#define __UAPI_DEF_IF_IFCONF 0
+#define __UAPI_DEF_IF_IFMAP 0
+#define __UAPI_DEF_IF_IFNAMSIZ 0
+#define __UAPI_DEF_IF_IFREQ 0
+/* Everything up to IFF_DYNAMIC, matches net/if.h until glibc 2.23 */
+#define __UAPI_DEF_IF_NET_DEVICE_FLAGS 0
+/* For the future if glibc adds IFF_LOWER_UP, IFF_DORMANT and IFF_ECHO */
+#ifndef __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO
+#define __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO 1
+#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO */
+
+#else /* _NET_IF_H */
+
+/* Linux headers included first, and we must define everything
+ * we need. The expectation is that glibc will check the
+ * __UAPI_DEF_* defines and adjust appropriately. */
+
+#define __UAPI_DEF_IF_IFCONF 1
+#define __UAPI_DEF_IF_IFMAP 1
+#define __UAPI_DEF_IF_IFNAMSIZ 1
+#define __UAPI_DEF_IF_IFREQ 1
+/* Everything up to IFF_DYNAMIC, matches net/if.h until glibc 2.23 */
+#define __UAPI_DEF_IF_NET_DEVICE_FLAGS 1
+/* For the future if glibc adds IFF_LOWER_UP, IFF_DORMANT and IFF_ECHO */
+#define __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO 1
+
+#endif /* _NET_IF_H */
+
 /* Coordinate with glibc netinet/in.h header. */
 #if defined(_NETINET_IN_H)
 
@@ -117,6 +151,16 @@
  * that we need. */
 #else /* !defined(__GLIBC__) */
 
+/* Definitions for if.h */
+#define __UAPI_DEF_IF_IFCONF 1
+#define __UAPI_DEF_IF_IFMAP 1
+#define __UAPI_DEF_IF_IFNAMSIZ 1
+#define __UAPI_DEF_IF_IFREQ 1
+/* Everything up to IFF_DYNAMIC, matches net/if.h until glibc 2.23 */
+#define __UAPI_DEF_IF_NET_DEVICE_FLAGS 1
+/* For the future if glibc adds IFF_LOWER_UP, IFF_DORMANT and IFF_ECHO */
+#define __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO 1
+
 /* Definitions for in.h */
 #define __UAPI_DEF_IN_ADDR		1
 #define __UAPI_DEF_IN_IPPROTO		1
-- 
2.1.0


From d67445a0033868df432fb106a0993f351d04b0cc Mon Sep 17 00:00:00 2001
From: Kangjie Lu <kangjielu@gmail.com>
Date: Sun, 8 May 2016 12:10:14 -0400
Subject: [PATCH 35/38] net: fix a kernel infoleak in x25 module

[ Upstream commit 79e48650320e6fba48369fccf13fd045315b19b8 ]

Stack object "dte_facilities" is allocated in x25_rx_call_request(),
which is supposed to be initialized in x25_negotiate_facilities.
However, 5 fields (8 bytes in total) are not initialized. This
object is then copied to userland via copy_to_user, thus infoleak
occurs.

Signed-off-by: Kangjie Lu <kjlu@gatech.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/x25/x25_facilities.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/x25/x25_facilities.c b/net/x25/x25_facilities.c
index 7ecd04c..997ff7b 100644
--- a/net/x25/x25_facilities.c
+++ b/net/x25/x25_facilities.c
@@ -277,6 +277,7 @@ int x25_negotiate_facilities(struct sk_buff *skb, struct sock *sk,
 
 	memset(&theirs, 0, sizeof(theirs));
 	memcpy(new, ours, sizeof(*new));
+	memset(dte, 0, sizeof(*dte));
 
 	len = x25_parse_facilities(skb, &theirs, dte, &x25->vc_facil_mask);
 	if (len < 0)
-- 
2.1.0


From 016c37b2c46cff277238c32c058bfdbac30a2ab9 Mon Sep 17 00:00:00 2001
From: "xypron.glpk@gmx.de" <xypron.glpk@gmx.de>
Date: Mon, 9 May 2016 00:46:18 +0200
Subject: [PATCH 36/38] net: thunderx: avoid exposing kernel stack

[ Upstream commit 161de2caf68c549c266e571ffba8e2163886fb10 ]

Reserved fields should be set to zero to avoid exposing
bits from the kernel stack.

Signed-off-by: Heinrich Schuchardt <xypron.glpk@gmx.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/thunder/nicvf_queues.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index 206b6a7..d1c217e 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -550,6 +550,7 @@ static void nicvf_rcv_queue_config(struct nicvf *nic, struct queue_set *qs,
 		nicvf_config_vlan_stripping(nic, nic->netdev->features);
 
 	/* Enable Receive queue */
+	memset(&rq_cfg, 0, sizeof(struct rq_cfg));
 	rq_cfg.ena = 1;
 	rq_cfg.tcp_ena = 0;
 	nicvf_queue_reg_write(nic, NIC_QSET_RQ_0_7_CFG, qidx, *(u64 *)&rq_cfg);
@@ -582,6 +583,7 @@ void nicvf_cmp_queue_config(struct nicvf *nic, struct queue_set *qs,
 			      qidx, (u64)(cq->dmem.phys_base));
 
 	/* Enable Completion queue */
+	memset(&cq_cfg, 0, sizeof(struct cq_cfg));
 	cq_cfg.ena = 1;
 	cq_cfg.reset = 0;
 	cq_cfg.caching = 0;
@@ -630,6 +632,7 @@ static void nicvf_snd_queue_config(struct nicvf *nic, struct queue_set *qs,
 			      qidx, (u64)(sq->dmem.phys_base));
 
 	/* Enable send queue  & set queue size */
+	memset(&sq_cfg, 0, sizeof(struct sq_cfg));
 	sq_cfg.ena = 1;
 	sq_cfg.reset = 0;
 	sq_cfg.ldwb = 0;
@@ -666,6 +669,7 @@ static void nicvf_rbdr_config(struct nicvf *nic, struct queue_set *qs,
 
 	/* Enable RBDR  & set queue size */
 	/* Buffer size should be in multiples of 128 bytes */
+	memset(&rbdr_cfg, 0, sizeof(struct rbdr_cfg));
 	rbdr_cfg.ena = 1;
 	rbdr_cfg.reset = 0;
 	rbdr_cfg.ldwb = 0;
-- 
2.1.0


From ca6ad74283e704f041ceebb4e9ea801f1a4e6151 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 9 May 2016 20:55:16 -0700
Subject: [PATCH 37/38] tcp: refresh skb timestamp at retransmit time

[ Upstream commit 10a81980fc47e64ffac26a073139813d3f697b64 ]

In the very unlikely case __tcp_retransmit_skb() can not use the cloning
done in tcp_transmit_skb(), we need to refresh skb_mstamp before doing
the copy and transmit, otherwise TCP TS val will be an exact copy of
original transmit.

Fixes: 7faee5c0d514 ("tcp: remove TCP_SKB_CB(skb)->when")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 9bfc39f..7c9883a 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2625,8 +2625,10 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 	 */
 	if (unlikely((NET_IP_ALIGN && ((unsigned long)skb->data & 3)) ||
 		     skb_headroom(skb) >= 0xFFFF)) {
-		struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER,
-						   GFP_ATOMIC);
+		struct sk_buff *nskb;
+
+		skb_mstamp_get(&skb->skb_mstamp);
+		nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC);
 		err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
 			     -ENOBUFS;
 	} else {
-- 
2.1.0


From 53ecf488ab37d209581f3987fac29cb2dac504ef Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 13 May 2016 18:33:41 +0200
Subject: [PATCH 38/38] net/route: enforce hoplimit max value

[ Upstream commit 626abd59e51d4d8c6367e03aae252a8aa759ac78 ]

Currently, when creating or updating a route, no check is performed
in both ipv4 and ipv6 code to the hoplimit value.

The caller can i.e. set hoplimit to 256, and when such route will
 be used, packets will be sent with hoplimit/ttl equal to 0.

This commit adds checks for the RTAX_HOPLIMIT value, in both ipv4
ipv6 route code, substituting any value greater than 255 with 255.

This is consistent with what is currently done for ADVMSS and MTU
in the ipv4 code.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_semantics.c | 2 ++
 net/ipv6/route.c         | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index d97268e..2b68418 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -975,6 +975,8 @@ fib_convert_metrics(struct fib_info *fi, const struct fib_config *cfg)
 			val = 65535 - 40;
 		if (type == RTAX_MTU && val > 65535 - 15)
 			val = 65535 - 15;
+		if (type == RTAX_HOPLIMIT && val > 255)
+			val = 255;
 		if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK))
 			return -EINVAL;
 		fi->fib_metrics[type - 1] = val;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 3f164d3..5af2cca 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1727,6 +1727,8 @@ static int ip6_convert_metrics(struct mx6_config *mxc,
 		} else {
 			val = nla_get_u32(nla);
 		}
+		if (type == RTAX_HOPLIMIT && val > 255)
+			val = 255;
 		if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK))
 			goto err;
 
-- 
2.1.0


[-- Attachment #4: net_45.mbox --]
[-- Type: Application/Octet-Stream, Size: 139280 bytes --]

From 316a54f283bfdd14ea3536f845dbdd7360a92dfa Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sun, 10 Apr 2016 23:01:30 -0400
Subject: [PATCH 01/42] decnet: Do not build routes to devices without decnet
 private data.

[ Upstream commit a36a0d4008488fa545c74445d69eaf56377d5d4e ]

In particular, make sure we check for decnet private presence
for loopback devices.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/decnet/dn_route.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index 607a14f..b1dc096 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -1034,10 +1034,13 @@ source_ok:
 	if (!fld.daddr) {
 		fld.daddr = fld.saddr;
 
-		err = -EADDRNOTAVAIL;
 		if (dev_out)
 			dev_put(dev_out);
+		err = -EINVAL;
 		dev_out = init_net.loopback_dev;
+		if (!dev_out->dn_ptr)
+			goto out;
+		err = -EADDRNOTAVAIL;
 		dev_hold(dev_out);
 		if (!fld.daddr) {
 			fld.daddr =
@@ -1110,6 +1113,8 @@ source_ok:
 		if (dev_out == NULL)
 			goto out;
 		dn_db = rcu_dereference_raw(dev_out->dn_ptr);
+		if (!dn_db)
+			goto e_inval;
 		/* Possible improvement - check all devices for local addr */
 		if (dn_dev_islocal(dev_out, fld.daddr)) {
 			dev_put(dev_out);
@@ -1151,6 +1156,8 @@ select_source:
 			dev_put(dev_out);
 		dev_out = init_net.loopback_dev;
 		dev_hold(dev_out);
+		if (!dev_out->dn_ptr)
+			goto e_inval;
 		fld.flowidn_oif = dev_out->ifindex;
 		if (res.fi)
 			dn_fib_info_put(res.fi);
-- 
2.1.0


From dcd21256c7f8d0f689f36115301b5047fc28c723 Mon Sep 17 00:00:00 2001
From: Chris Friesen <chris.friesen@windriver.com>
Date: Fri, 8 Apr 2016 15:21:30 -0600
Subject: [PATCH 02/42] route: do not cache fib route info on local routes with
 oif

[ Upstream commit d6d5e999e5df67f8ec20b6be45e2229455ee3699 ]

For local routes that require a particular output interface we do not want
to cache the result.  Caching the result causes incorrect behaviour when
there are multiple source addresses on the interface.  The end result
being that if the intended recipient is waiting on that interface for the
packet he won't receive it because it will be delivered on the loopback
interface and the IP_PKTINFO ipi_ifindex will be set to the loopback
interface as well.

This can be tested by running a program such as "dhcp_release" which
attempts to inject a packet on a particular interface so that it is
received by another program on the same board.  The receiving process
should see an IP_PKTINFO ipi_ifndex value of the source interface
(e.g., eth1) instead of the loopback interface (e.g., lo).  The packet
will still appear on the loopback interface in tcpdump but the important
aspect is that the CMSG info is correct.

Sample dhcp_release command line:

   dhcp_release eth1 192.168.204.222 02:11:33:22:44:66

Signed-off-by: Allain Legacy <allain.legacy@windriver.com>
Signed off-by: Chris Friesen <chris.friesen@windriver.com>
Reviewed-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 02c6229..b050cf9 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2045,6 +2045,18 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 		 */
 		if (fi && res->prefixlen < 4)
 			fi = NULL;
+	} else if ((type == RTN_LOCAL) && (orig_oif != 0) &&
+		   (orig_oif != dev_out->ifindex)) {
+		/* For local routes that require a particular output interface
+		 * we do not want to cache the result.  Caching the result
+		 * causes incorrect behaviour when there are multiple source
+		 * addresses on the interface, the end result being that if the
+		 * intended recipient is waiting on that interface for the
+		 * packet he won't receive it because it will be delivered on
+		 * the loopback interface and the IP_PKTINFO ipi_ifindex will
+		 * be set to the loopback interface as well.
+		 */
+		fi = NULL;
 	}
 
 	fnhe = NULL;
-- 
2.1.0


From 854e7cbca41681aadc923a80ead7e4a76f2d1c9d Mon Sep 17 00:00:00 2001
From: Mathias Krause <minipli@googlemail.com>
Date: Sun, 10 Apr 2016 12:52:28 +0200
Subject: [PATCH 03/42] packet: fix heap info leak in PACKET_DIAG_MCLIST
 sock_diag interface

[ Upstream commit 309cf37fe2a781279b7675d4bb7173198e532867 ]

Because we miss to wipe the remainder of i->addr[] in packet_mc_add(),
pdiag_put_mclist() leaks uninitialized heap bytes via the
PACKET_DIAG_MCLIST netlink attribute.

Fix this by explicitly memset(0)ing the remaining bytes in i->addr[].

Fixes: eea68e2f1a00 ("packet: Report socket mclist info via diag module")
Signed-off-by: Mathias Krause <minipli@googlemail.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Acked-by: Pavel Emelyanov <xemul@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index da1ae0e1..9cc7b51 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3436,6 +3436,7 @@ static int packet_mc_add(struct sock *sk, struct packet_mreq_max *mreq)
 	i->ifindex = mreq->mr_ifindex;
 	i->alen = mreq->mr_alen;
 	memcpy(i->addr, mreq->mr_address, i->alen);
+	memset(i->addr + i->alen, 0, sizeof(i->addr) - i->alen);
 	i->count = 1;
 	i->next = po->mclist;
 	po->mclist = i;
-- 
2.1.0


From 870785357e5284c95608fae874be99c0c025bcf9 Mon Sep 17 00:00:00 2001
From: Lars Persson <lars.persson@axis.com>
Date: Tue, 12 Apr 2016 08:45:52 +0200
Subject: [PATCH 04/42] net: sched: do not requeue a NULL skb

[ Upstream commit 3dcd493fbebfd631913df6e2773cc295d3bf7d22 ]

A failure in validate_xmit_skb_list() triggered an unconditional call
to dev_requeue_skb with skb=NULL. This slowly grows the queue
discipline's qlen count until all traffic through the queue stops.

We take the optimistic approach and continue running the queue after a
failure since it is unknown if later packets also will fail in the
validate path.

Fixes: 55a93b3ea780 ("qdisc: validate skb without holding lock")
Signed-off-by: Lars Persson <larper@axis.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_generic.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 16bc83b..aa47250 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -159,12 +159,15 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
 	if (validate)
 		skb = validate_xmit_skb_list(skb, dev);
 
-	if (skb) {
+	if (likely(skb)) {
 		HARD_TX_LOCK(dev, txq, smp_processor_id());
 		if (!netif_xmit_frozen_or_stopped(txq))
 			skb = dev_hard_start_xmit(skb, dev, txq, &ret);
 
 		HARD_TX_UNLOCK(dev, txq);
+	} else {
+		spin_lock(root_lock);
+		return qdisc_qlen(q);
 	}
 	spin_lock(root_lock);
 
-- 
2.1.0


From 5a6d795c1b97df107903c6d7cfa489fc62177f78 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@fb.com>
Date: Tue, 12 Apr 2016 10:26:19 -0700
Subject: [PATCH 05/42] bpf/verifier: reject invalid LD_ABS | BPF_DW
 instruction

[ Upstream commit d82bccc69041a51f7b7b9b4a36db0772f4cdba21 ]

verifier must check for reserved size bits in instruction opcode and
reject BPF_LD | BPF_ABS | BPF_DW and BPF_LD | BPF_IND | BPF_DW instructions,
otherwise interpreter will WARN_RATELIMIT on them during execution.

Fixes: ddd872bc3098 ("bpf: verifier: add checks for BPF_ABS | BPF_IND instructions")
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 2e7f7ab..c21cb14 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1348,6 +1348,7 @@ static int check_ld_abs(struct verifier_env *env, struct bpf_insn *insn)
 	}
 
 	if (insn->dst_reg != BPF_REG_0 || insn->off != 0 ||
+	    BPF_SIZE(insn->code) == BPF_DW ||
 	    (mode == BPF_ABS && insn->src_reg != BPF_REG_0)) {
 		verbose("BPF_LD_ABS uses reserved fields\n");
 		return -EINVAL;
-- 
2.1.0


From 5c65a49a870770c8b5248915926cd0cd1cb38d60 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Tue, 12 Apr 2016 16:11:12 +0200
Subject: [PATCH 06/42] cdc_mbim: apply "NDP to end" quirk to all Huawei
 devices
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit c5b5343cfbc9f46af65033fa4f407d7b7d98371d ]

We now have a positive report of another Huawei device needing
this quirk: The ME906s-158 (12d1:15c1).  This is an m.2 form
factor modem with no obvious relationship to the E3372 (12d1:157d)
we already have a quirk entry for.  This is reason enough to
believe the quirk might be necessary for any number of current
and future Huawei devices.

Applying the quirk to all Huawei devices, since it is crucial
to any device affected by the firmware bug, while the impact
on non-affected devices is negligible.

The quirk can if necessary be disabled per-device by writing
N to /sys/class/net/<iface>/cdc_ncm/ndp_to_end

Reported-by: Andreas Fett <andreas.fett@secunet.com>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_mbim.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c
index bdd83d9..96a5028 100644
--- a/drivers/net/usb/cdc_mbim.c
+++ b/drivers/net/usb/cdc_mbim.c
@@ -617,8 +617,13 @@ static const struct usb_device_id mbim_devs[] = {
 	{ USB_VENDOR_AND_INTERFACE_INFO(0x0bdb, USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE),
 	  .driver_info = (unsigned long)&cdc_mbim_info,
 	},
-	/* Huawei E3372 fails unless NDP comes after the IP packets */
-	{ USB_DEVICE_AND_INTERFACE_INFO(0x12d1, 0x157d, USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE),
+
+	/* Some Huawei devices, ME906s-158 (12d1:15c1) and E3372
+	 * (12d1:157d), are known to fail unless the NDP is placed
+	 * after the IP packets.  Applying the quirk to all Huawei
+	 * devices is broader than necessary, but harmless.
+	 */
+	{ USB_VENDOR_AND_INTERFACE_INFO(0x12d1, USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE),
 	  .driver_info = (unsigned long)&cdc_mbim_info_ndp_to_end,
 	},
 	/* default entry */
-- 
2.1.0


From 28022d1d722d9917b24bf24e7bb16f24b0d626aa Mon Sep 17 00:00:00 2001
From: Craig Gallek <kraig@google.com>
Date: Tue, 12 Apr 2016 13:11:25 -0400
Subject: [PATCH 07/42] soreuseport: fix ordering for mixed v4/v6 sockets
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit d894ba18d4e449b3a7f6eb491f16c9e02933736e ]

With the SO_REUSEPORT socket option, it is possible to create sockets
in the AF_INET and AF_INET6 domains which are bound to the same IPv4 address.
This is only possible with SO_REUSEPORT and when not using IPV6_V6ONLY on
the AF_INET6 sockets.

Prior to the commits referenced below, an incoming IPv4 packet would
always be routed to a socket of type AF_INET when this mixed-mode was used.
After those changes, the same packet would be routed to the most recently
bound socket (if this happened to be an AF_INET6 socket, it would
have an IPv4 mapped IPv6 address).

The change in behavior occurred because the recent SO_REUSEPORT optimizations
short-circuit the socket scoring logic as soon as they find a match.  They
did not take into account the scoring logic that favors AF_INET sockets
over AF_INET6 sockets in the event of a tie.

To fix this problem, this patch changes the insertion order of AF_INET
and AF_INET6 addresses in the TCP and UDP socket lists when the sockets
have SO_REUSEPORT set.  AF_INET sockets will be inserted at the head of the
list and AF_INET6 sockets with SO_REUSEPORT set will always be inserted at
the tail of the list.  This will force AF_INET sockets to always be
considered first.

Fixes: e32ea7e74727 ("soreuseport: fast reuseport UDP socket selection")
Fixes: 125e80b88687 ("soreuseport: fast reuseport TCP socket selection")

Reported-by: Maciej Żenczykowski <maze@google.com>
Signed-off-by: Craig Gallek <kraig@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rculist_nulls.h | 39 +++++++++++++++++++++++++++++++++++++++
 include/net/sock.h            |  6 +++++-
 net/ipv4/udp.c                |  9 +++++++--
 3 files changed, 51 insertions(+), 3 deletions(-)

diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h
index 1c33dd7..4ae95f7 100644
--- a/include/linux/rculist_nulls.h
+++ b/include/linux/rculist_nulls.h
@@ -98,6 +98,45 @@ static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n,
 	if (!is_a_nulls(first))
 		first->pprev = &n->next;
 }
+
+/**
+ * hlist_nulls_add_tail_rcu
+ * @n: the element to add to the hash list.
+ * @h: the list to add to.
+ *
+ * Description:
+ * Adds the specified element to the end of the specified hlist_nulls,
+ * while permitting racing traversals.  NOTE: tail insertion requires
+ * list traversal.
+ *
+ * The caller must take whatever precautions are necessary
+ * (such as holding appropriate locks) to avoid racing
+ * with another list-mutation primitive, such as hlist_nulls_add_head_rcu()
+ * or hlist_nulls_del_rcu(), running on this same list.
+ * However, it is perfectly legal to run concurrently with
+ * the _rcu list-traversal primitives, such as
+ * hlist_nulls_for_each_entry_rcu(), used to prevent memory-consistency
+ * problems on Alpha CPUs.  Regardless of the type of CPU, the
+ * list-traversal primitive must be guarded by rcu_read_lock().
+ */
+static inline void hlist_nulls_add_tail_rcu(struct hlist_nulls_node *n,
+					struct hlist_nulls_head *h)
+{
+	struct hlist_nulls_node *i, *last = NULL;
+
+	for (i = hlist_nulls_first_rcu(h); !is_a_nulls(i);
+	     i = hlist_nulls_next_rcu(i))
+		last = i;
+
+	if (last) {
+		n->next = last->next;
+		n->pprev = &last->next;
+		rcu_assign_pointer(hlist_nulls_next_rcu(last), n);
+	} else {
+		hlist_nulls_add_head_rcu(n, h);
+	}
+}
+
 /**
  * hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type
  * @tpos:	the type * to use as a loop cursor.
diff --git a/include/net/sock.h b/include/net/sock.h
index f5ea148..3c688ca 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -630,7 +630,11 @@ static inline void sk_add_node_rcu(struct sock *sk, struct hlist_head *list)
 
 static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
 {
-	hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list);
+	if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport &&
+	    sk->sk_family == AF_INET6)
+		hlist_nulls_add_tail_rcu(&sk->sk_nulls_node, list);
+	else
+		hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list);
 }
 
 static inline void sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index eb8933b..56218ff 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -339,8 +339,13 @@ found:
 
 		hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash);
 		spin_lock(&hslot2->lock);
-		hlist_nulls_add_head_rcu(&udp_sk(sk)->udp_portaddr_node,
-					 &hslot2->head);
+		if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport &&
+			sk->sk_family == AF_INET6)
+			hlist_nulls_add_tail_rcu(&udp_sk(sk)->udp_portaddr_node,
+						 &hslot2->head);
+		else
+			hlist_nulls_add_head_rcu(&udp_sk(sk)->udp_portaddr_node,
+						 &hslot2->head);
 		hslot2->count++;
 		spin_unlock(&hslot2->lock);
 	}
-- 
2.1.0


From cffda81d5d0355e1f8c8d92425b1438dddbe82bb Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Sat, 20 Feb 2016 00:29:30 +0100
Subject: [PATCH 08/42] net: use skb_postpush_rcsum instead of own
 implementations

[ Upstream commit 6b83d28a55a891a9d70fc61ccb1c138e47dcbe74 ]

Replace individual implementations with the recently introduced
skb_postpush_rcsum() helper.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Tom Herbert <tom@herbertland.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c              | 4 +---
 net/ipv6/reassembly.c          | 6 ++----
 net/openvswitch/actions.c      | 8 +++-----
 net/openvswitch/vport-netdev.c | 2 +-
 net/openvswitch/vport.h        | 7 -------
 5 files changed, 7 insertions(+), 20 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 8616d11..78abe11 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4433,9 +4433,7 @@ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci)
 		skb->mac_len += VLAN_HLEN;
 		__skb_pull(skb, offset);
 
-		if (skb->ip_summed == CHECKSUM_COMPLETE)
-			skb->csum = csum_add(skb->csum, csum_partial(skb->data
-					+ (2 * ETH_ALEN), VLAN_HLEN, 0));
+		skb_postpush_rcsum(skb, skb->data + (2 * ETH_ALEN), VLAN_HLEN);
 	}
 	__vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci);
 	return 0;
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 18f3498..e2ea311 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -496,10 +496,8 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
 	IP6CB(head)->flags |= IP6SKB_FRAGMENTED;
 
 	/* Yes, and fold redundant checksum back. 8) */
-	if (head->ip_summed == CHECKSUM_COMPLETE)
-		head->csum = csum_partial(skb_network_header(head),
-					  skb_network_header_len(head),
-					  head->csum);
+	skb_postpush_rcsum(head, skb_network_header(head),
+			   skb_network_header_len(head));
 
 	rcu_read_lock();
 	IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS);
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 2d59df5..e9dd47b 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -158,9 +158,7 @@ static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key,
 	new_mpls_lse = (__be32 *)skb_mpls_header(skb);
 	*new_mpls_lse = mpls->mpls_lse;
 
-	if (skb->ip_summed == CHECKSUM_COMPLETE)
-		skb->csum = csum_add(skb->csum, csum_partial(new_mpls_lse,
-							     MPLS_HLEN, 0));
+	skb_postpush_rcsum(skb, new_mpls_lse, MPLS_HLEN);
 
 	hdr = eth_hdr(skb);
 	hdr->h_proto = mpls->mpls_ethertype;
@@ -280,7 +278,7 @@ static int set_eth_addr(struct sk_buff *skb, struct sw_flow_key *flow_key,
 	ether_addr_copy_masked(eth_hdr(skb)->h_dest, key->eth_dst,
 			       mask->eth_dst);
 
-	ovs_skb_postpush_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
+	skb_postpush_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
 
 	ether_addr_copy(flow_key->eth.src, eth_hdr(skb)->h_source);
 	ether_addr_copy(flow_key->eth.dst, eth_hdr(skb)->h_dest);
@@ -639,7 +637,7 @@ static int ovs_vport_output(struct net *net, struct sock *sk, struct sk_buff *sk
 	/* Reconstruct the MAC header.  */
 	skb_push(skb, data->l2_len);
 	memcpy(skb->data, &data->l2_data, data->l2_len);
-	ovs_skb_postpush_rcsum(skb, skb->data, data->l2_len);
+	skb_postpush_rcsum(skb, skb->data, data->l2_len);
 	skb_reset_mac_header(skb);
 
 	ovs_vport_send(vport, skb);
diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c
index 6a6adf3..4e39723 100644
--- a/net/openvswitch/vport-netdev.c
+++ b/net/openvswitch/vport-netdev.c
@@ -58,7 +58,7 @@ static void netdev_port_receive(struct sk_buff *skb)
 		return;
 
 	skb_push(skb, ETH_HLEN);
-	ovs_skb_postpush_rcsum(skb, skb->data, ETH_HLEN);
+	skb_postpush_rcsum(skb, skb->data, ETH_HLEN);
 	ovs_vport_receive(vport, skb, skb_tunnel_info(skb));
 	return;
 error:
diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h
index c10899cb..f01f28a 100644
--- a/net/openvswitch/vport.h
+++ b/net/openvswitch/vport.h
@@ -185,13 +185,6 @@ static inline struct vport *vport_from_priv(void *priv)
 int ovs_vport_receive(struct vport *, struct sk_buff *,
 		      const struct ip_tunnel_info *);
 
-static inline void ovs_skb_postpush_rcsum(struct sk_buff *skb,
-				      const void *start, unsigned int len)
-{
-	if (skb->ip_summed == CHECKSUM_COMPLETE)
-		skb->csum = csum_add(skb->csum, csum_partial(start, len, 0));
-}
-
 static inline const char *ovs_vport_name(struct vport *vport)
 {
 	return vport->dev->name;
-- 
2.1.0


From 40e959d5f3d8b86d997874bcd1ccf2c6b3f9f999 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Sat, 16 Apr 2016 02:27:58 +0200
Subject: [PATCH 09/42] vlan: pull on __vlan_insert_tag error path and fix csum
 correction

[ Upstream commit 9241e2df4fbc648a92ea0752918e05c26255649e ]

When __vlan_insert_tag() fails from skb_vlan_push() path due to the
skb_cow_head(), we need to undo the __skb_push() in the error path
as well that was done earlier to move skb->data pointer to mac header.

Moreover, I noticed that when in the non-error path the __skb_pull()
is done and the original offset to mac header was non-zero, we fixup
from a wrong skb->data offset in the checksum complete processing.

So the skb_postpush_rcsum() really needs to be done before __skb_pull()
where skb->data still points to the mac header start and thus operates
under the same conditions as in __vlan_insert_tag().

Fixes: 93515d53b133 ("net: move vlan pop/push functions into common code")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 78abe11..9835d9a 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4427,13 +4427,16 @@ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci)
 		__skb_push(skb, offset);
 		err = __vlan_insert_tag(skb, skb->vlan_proto,
 					skb_vlan_tag_get(skb));
-		if (err)
+		if (err) {
+			__skb_pull(skb, offset);
 			return err;
+		}
+
 		skb->protocol = skb->vlan_proto;
 		skb->mac_len += VLAN_HLEN;
-		__skb_pull(skb, offset);
 
 		skb_postpush_rcsum(skb, skb->data + (2 * ETH_ALEN), VLAN_HLEN);
+		__skb_pull(skb, offset);
 	}
 	__vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci);
 	return 0;
-- 
2.1.0


From c437228e4da8c1b61d0f30d23697d93361cc01aa Mon Sep 17 00:00:00 2001
From: Joe Stringer <joe@ovn.org>
Date: Mon, 18 Apr 2016 14:51:47 -0700
Subject: [PATCH 10/42] openvswitch: Orphan skbs before IPv6 defrag

[ Upstream commit 49e261a8a21e0960a3f7ff187a453ba1c1149053 ]

This is the IPv6 counterpart to commit 8282f27449bf ("inet: frag: Always
orphan skbs inside ip_defrag()").

Prior to commit 029f7f3b8701 ("netfilter: ipv6: nf_defrag: avoid/free
clone operations"), ipv6 fragments sent to nf_ct_frag6_gather() would be
cloned (implicitly orphaning) prior to queueing for reassembly. As such,
when the IPv6 message is eventually reassembled, the skb->sk for all
fragments would be NULL. After that commit was introduced, rather than
cloning, the original skbs were queued directly without orphaning. The
end result is that all frags except for the first and last may have a
socket attached.

This commit explicitly orphans such skbs during nf_ct_frag6_gather() to
prevent BUG_ON(skb->sk) during a later call to ip6_fragment().

kernel BUG at net/ipv6/ip6_output.c:631!
[...]
Call Trace:
 <IRQ>
 [<ffffffff810be8f7>] ? __lock_acquire+0x927/0x20a0
 [<ffffffffa042c7c0>] ? do_output.isra.28+0x1b0/0x1b0 [openvswitch]
 [<ffffffff810bb8a2>] ? __lock_is_held+0x52/0x70
 [<ffffffffa042c587>] ovs_fragment+0x1f7/0x280 [openvswitch]
 [<ffffffff810bdab5>] ? mark_held_locks+0x75/0xa0
 [<ffffffff817be416>] ? _raw_spin_unlock_irqrestore+0x36/0x50
 [<ffffffff81697ea0>] ? dst_discard_out+0x20/0x20
 [<ffffffff81697e80>] ? dst_ifdown+0x80/0x80
 [<ffffffffa042c703>] do_output.isra.28+0xf3/0x1b0 [openvswitch]
 [<ffffffffa042d279>] do_execute_actions+0x709/0x12c0 [openvswitch]
 [<ffffffffa04340a4>] ? ovs_flow_stats_update+0x74/0x1e0 [openvswitch]
 [<ffffffffa04340d1>] ? ovs_flow_stats_update+0xa1/0x1e0 [openvswitch]
 [<ffffffff817be387>] ? _raw_spin_unlock+0x27/0x40
 [<ffffffffa042de75>] ovs_execute_actions+0x45/0x120 [openvswitch]
 [<ffffffffa0432d65>] ovs_dp_process_packet+0x85/0x150 [openvswitch]
 [<ffffffff817be387>] ? _raw_spin_unlock+0x27/0x40
 [<ffffffffa042def4>] ovs_execute_actions+0xc4/0x120 [openvswitch]
 [<ffffffffa0432d65>] ovs_dp_process_packet+0x85/0x150 [openvswitch]
 [<ffffffffa04337f2>] ? key_extract+0x442/0xc10 [openvswitch]
 [<ffffffffa043b26d>] ovs_vport_receive+0x5d/0xb0 [openvswitch]
 [<ffffffff810be8f7>] ? __lock_acquire+0x927/0x20a0
 [<ffffffff810be8f7>] ? __lock_acquire+0x927/0x20a0
 [<ffffffff810be8f7>] ? __lock_acquire+0x927/0x20a0
 [<ffffffff817be416>] ? _raw_spin_unlock_irqrestore+0x36/0x50
 [<ffffffffa043c11d>] internal_dev_xmit+0x6d/0x150 [openvswitch]
 [<ffffffffa043c0b5>] ? internal_dev_xmit+0x5/0x150 [openvswitch]
 [<ffffffff8168fb5f>] dev_hard_start_xmit+0x2df/0x660
 [<ffffffff8168f5ea>] ? validate_xmit_skb.isra.105.part.106+0x1a/0x2b0
 [<ffffffff81690925>] __dev_queue_xmit+0x8f5/0x950
 [<ffffffff81690080>] ? __dev_queue_xmit+0x50/0x950
 [<ffffffff810bdab5>] ? mark_held_locks+0x75/0xa0
 [<ffffffff81690990>] dev_queue_xmit+0x10/0x20
 [<ffffffff8169a418>] neigh_resolve_output+0x178/0x220
 [<ffffffff81752759>] ? ip6_finish_output2+0x219/0x7b0
 [<ffffffff81752759>] ip6_finish_output2+0x219/0x7b0
 [<ffffffff817525a5>] ? ip6_finish_output2+0x65/0x7b0
 [<ffffffff816cde2b>] ? ip_idents_reserve+0x6b/0x80
 [<ffffffff8175488f>] ? ip6_fragment+0x93f/0xc50
 [<ffffffff81754af1>] ip6_fragment+0xba1/0xc50
 [<ffffffff81752540>] ? ip6_flush_pending_frames+0x40/0x40
 [<ffffffff81754c6b>] ip6_finish_output+0xcb/0x1d0
 [<ffffffff81754dcf>] ip6_output+0x5f/0x1a0
 [<ffffffff81754ba0>] ? ip6_fragment+0xc50/0xc50
 [<ffffffff81797fbd>] ip6_local_out+0x3d/0x80
 [<ffffffff817554df>] ip6_send_skb+0x2f/0xc0
 [<ffffffff817555bd>] ip6_push_pending_frames+0x4d/0x50
 [<ffffffff817796cc>] icmpv6_push_pending_frames+0xac/0xe0
 [<ffffffff8177a4be>] icmpv6_echo_reply+0x42e/0x500
 [<ffffffff8177acbf>] icmpv6_rcv+0x4cf/0x580
 [<ffffffff81755ac7>] ip6_input_finish+0x1a7/0x690
 [<ffffffff81755925>] ? ip6_input_finish+0x5/0x690
 [<ffffffff817567a0>] ip6_input+0x30/0xa0
 [<ffffffff81755920>] ? ip6_rcv_finish+0x1a0/0x1a0
 [<ffffffff817557ce>] ip6_rcv_finish+0x4e/0x1a0
 [<ffffffff8175640f>] ipv6_rcv+0x45f/0x7c0
 [<ffffffff81755fe6>] ? ipv6_rcv+0x36/0x7c0
 [<ffffffff81755780>] ? ip6_make_skb+0x1c0/0x1c0
 [<ffffffff8168b649>] __netif_receive_skb_core+0x229/0xb80
 [<ffffffff810bdab5>] ? mark_held_locks+0x75/0xa0
 [<ffffffff8168c07f>] ? process_backlog+0x6f/0x230
 [<ffffffff8168bfb6>] __netif_receive_skb+0x16/0x70
 [<ffffffff8168c088>] process_backlog+0x78/0x230
 [<ffffffff8168c0ed>] ? process_backlog+0xdd/0x230
 [<ffffffff8168db43>] net_rx_action+0x203/0x480
 [<ffffffff810bdab5>] ? mark_held_locks+0x75/0xa0
 [<ffffffff817c156e>] __do_softirq+0xde/0x49f
 [<ffffffff81752768>] ? ip6_finish_output2+0x228/0x7b0
 [<ffffffff817c070c>] do_softirq_own_stack+0x1c/0x30
 <EOI>
 [<ffffffff8106f88b>] do_softirq.part.18+0x3b/0x40
 [<ffffffff8106f946>] __local_bh_enable_ip+0xb6/0xc0
 [<ffffffff81752791>] ip6_finish_output2+0x251/0x7b0
 [<ffffffff81754af1>] ? ip6_fragment+0xba1/0xc50
 [<ffffffff816cde2b>] ? ip_idents_reserve+0x6b/0x80
 [<ffffffff8175488f>] ? ip6_fragment+0x93f/0xc50
 [<ffffffff81754af1>] ip6_fragment+0xba1/0xc50
 [<ffffffff81752540>] ? ip6_flush_pending_frames+0x40/0x40
 [<ffffffff81754c6b>] ip6_finish_output+0xcb/0x1d0
 [<ffffffff81754dcf>] ip6_output+0x5f/0x1a0
 [<ffffffff81754ba0>] ? ip6_fragment+0xc50/0xc50
 [<ffffffff81797fbd>] ip6_local_out+0x3d/0x80
 [<ffffffff817554df>] ip6_send_skb+0x2f/0xc0
 [<ffffffff817555bd>] ip6_push_pending_frames+0x4d/0x50
 [<ffffffff81778558>] rawv6_sendmsg+0xa28/0xe30
 [<ffffffff81719097>] ? inet_sendmsg+0xc7/0x1d0
 [<ffffffff817190d6>] inet_sendmsg+0x106/0x1d0
 [<ffffffff81718fd5>] ? inet_sendmsg+0x5/0x1d0
 [<ffffffff8166d078>] sock_sendmsg+0x38/0x50
 [<ffffffff8166d4d6>] SYSC_sendto+0xf6/0x170
 [<ffffffff8100201b>] ? trace_hardirqs_on_thunk+0x1b/0x1d
 [<ffffffff8166e38e>] SyS_sendto+0xe/0x10
 [<ffffffff817bebe5>] entry_SYSCALL_64_fastpath+0x18/0xa8
Code: 06 48 83 3f 00 75 26 48 8b 87 d8 00 00 00 2b 87 d0 00 00 00 48 39 d0 72 14 8b 87 e4 00 00 00 83 f8 01 75 09 48 83 7f 18 00 74 9a <0f> 0b 41 8b 86 cc 00 00 00 49 8#
RIP  [<ffffffff8175468a>] ip6_fragment+0x73a/0xc50
 RSP <ffff880072803120>

Fixes: 029f7f3b8701 ("netfilter: ipv6: nf_defrag: avoid/free clone
operations")
Reported-by: Daniele Di Proietto <diproiettod@vmware.com>
Signed-off-by: Joe Stringer <joe@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/conntrack.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index ee6ff8f..9e5b9fc 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -320,6 +320,7 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key,
 	} else if (key->eth.type == htons(ETH_P_IPV6)) {
 		enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone;
 
+		skb_orphan(skb);
 		memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));
 		err = nf_ct_frag6_gather(net, skb, user);
 		if (err)
-- 
2.1.0


From d4db550515f68c8821c0aa03fe739d3ee3767292 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben@decadent.org.uk>
Date: Wed, 20 Apr 2016 23:23:08 +0100
Subject: [PATCH 11/42] atl2: Disable unimplemented scatter/gather feature

[ Upstream commit f43bfaeddc79effbf3d0fcb53ca477cca66f3db8 ]

atl2 includes NETIF_F_SG in hw_features even though it has no support
for non-linear skbs.  This bug was originally harmless since the
driver does not claim to implement checksum offload and that used to
be a requirement for SG.

Now that SG and checksum offload are independent features, if you
explicitly enable SG *and* use one of the rare protocols that can use
SG without checkusm offload, this potentially leaks sensitive
information (before you notice that it just isn't working).  Therefore
this obscure bug has been designated CVE-2016-2117.

Reported-by: Justin Yackoski <jyackoski@crypto-nite.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Fixes: ec5f06156423 ("net: Kill link between CSUM and SG features.")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/atheros/atlx/atl2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c
index 8f76f45..2ff4658 100644
--- a/drivers/net/ethernet/atheros/atlx/atl2.c
+++ b/drivers/net/ethernet/atheros/atlx/atl2.c
@@ -1412,7 +1412,7 @@ static int atl2_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	err = -EIO;
 
-	netdev->hw_features = NETIF_F_SG | NETIF_F_HW_VLAN_CTAG_RX;
+	netdev->hw_features = NETIF_F_HW_VLAN_CTAG_RX;
 	netdev->features |= (NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX);
 
 	/* Init PHY as early as possible due to power saving issue  */
-- 
2.1.0


From 3a5da9dbe15d365fecc9e753488a2b6c34e80431 Mon Sep 17 00:00:00 2001
From: Simon Horman <simon.horman@netronome.com>
Date: Thu, 21 Apr 2016 11:49:15 +1000
Subject: [PATCH 12/42] openvswitch: use flow protocol when recalculating ipv6
 checksums

[ Upstream commit b4f70527f052b0c00be4d7cac562baa75b212df5 ]

When using masked actions the ipv6_proto field of an action
to set IPv6 fields may be zero rather than the prevailing protocol
which will result in skipping checksum recalculation.

This patch resolves the problem by relying on the protocol
in the flow key rather than that in the set field action.

Fixes: 83d2b9ba1abc ("net: openvswitch: Support masked set actions.")
Cc: Jarno Rajahalme <jrajahalme@nicira.com>
Signed-off-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/actions.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index e9dd47b..879185f 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -461,7 +461,7 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key,
 		mask_ipv6_addr(saddr, key->ipv6_src, mask->ipv6_src, masked);
 
 		if (unlikely(memcmp(saddr, masked, sizeof(masked)))) {
-			set_ipv6_addr(skb, key->ipv6_proto, saddr, masked,
+			set_ipv6_addr(skb, flow_key->ip.proto, saddr, masked,
 				      true);
 			memcpy(&flow_key->ipv6.addr.src, masked,
 			       sizeof(flow_key->ipv6.addr.src));
@@ -483,7 +483,7 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key,
 							     NULL, &flags)
 					       != NEXTHDR_ROUTING);
 
-			set_ipv6_addr(skb, key->ipv6_proto, daddr, masked,
+			set_ipv6_addr(skb, flow_key->ip.proto, daddr, masked,
 				      recalc_csum);
 			memcpy(&flow_key->ipv6.addr.dst, masked,
 			       sizeof(flow_key->ipv6.addr.dst));
-- 
2.1.0


From 3be086f20b46dcc257e81d7a85162d4d61d3d4be Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@mellanox.com>
Date: Fri, 22 Apr 2016 00:33:00 +0300
Subject: [PATCH 13/42] net/mlx5_core: Fix soft lockup in steering error flow

[ Upstream commit c3f9bf628bc7edda298897d952f5e761137229c9 ]

In the error flow of adding flow rule to auto-grouped flow
table, we call to tree_remove_node.

tree_remove_node locks the node's parent, however the node's parent
is already locked by mlx5_add_flow_rule and this causes a deadlock.
After this patch, if we failed to add the flow rule, we unlock the
flow table before calling to tree_remove_node.

fixes: f0d22d187473 ('net/mlx5_core: Introduce flow steering autogrouped
flow table')
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Reported-by: Amir Vadai <amir@vadai.me>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 46 +++++++++--------------
 1 file changed, 17 insertions(+), 29 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 6f68dba..cc90185 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -957,33 +957,6 @@ unlock_fg:
 	return rule;
 }
 
-static struct mlx5_flow_rule *add_rule_to_auto_fg(struct mlx5_flow_table *ft,
-						  u8 match_criteria_enable,
-						  u32 *match_criteria,
-						  u32 *match_value,
-						  u8 action,
-						  u32 flow_tag,
-						  struct mlx5_flow_destination *dest)
-{
-	struct mlx5_flow_rule *rule;
-	struct mlx5_flow_group *g;
-
-	g = create_autogroup(ft, match_criteria_enable, match_criteria);
-	if (IS_ERR(g))
-		return (void *)g;
-
-	rule = add_rule_fg(g, match_value,
-			   action, flow_tag, dest);
-	if (IS_ERR(rule)) {
-		/* Remove assumes refcount > 0 and autogroup creates a group
-		 * with a refcount = 0.
-		 */
-		tree_get_node(&g->node);
-		tree_remove_node(&g->node);
-	}
-	return rule;
-}
-
 struct mlx5_flow_rule *
 mlx5_add_flow_rule(struct mlx5_flow_table *ft,
 		   u8 match_criteria_enable,
@@ -1008,8 +981,23 @@ mlx5_add_flow_rule(struct mlx5_flow_table *ft,
 				goto unlock;
 		}
 
-	rule = add_rule_to_auto_fg(ft, match_criteria_enable, match_criteria,
-				   match_value, action, flow_tag, dest);
+	g = create_autogroup(ft, match_criteria_enable, match_criteria);
+	if (IS_ERR(g)) {
+		rule = (void *)g;
+		goto unlock;
+	}
+
+	rule = add_rule_fg(g, match_value,
+			   action, flow_tag, dest);
+	if (IS_ERR(rule)) {
+		/* Remove assumes refcount > 0 and autogroup creates a group
+		 * with a refcount = 0.
+		 */
+		unlock_ref_node(&ft->node);
+		tree_get_node(&g->node);
+		tree_remove_node(&g->node);
+		return rule;
+	}
 unlock:
 	unlock_ref_node(&ft->node);
 	return rule;
-- 
2.1.0


From c0981e9fbc0cd764b8c9bc6434efccc79ba2e3ed Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Fri, 22 Apr 2016 00:33:03 +0300
Subject: [PATCH 14/42] net/mlx5e: Device's mtu field is u16 and not int

[ Upstream commit 046339eaab26804f52f6604877f5674f70815b26 ]

For set/query MTU port firmware commands the MTU field
is 16 bits, here I changed all the "int mtu" parameters
of the functions wrapping those firmware commands to be u16.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/mlx5/main.c                 |  4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c |  4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/port.c    | 10 +++++-----
 include/linux/mlx5/driver.h                       |  6 +++---
 4 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index ed9cefa..eaed31d 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -654,8 +654,8 @@ static int mlx5_query_hca_port(struct ib_device *ibdev, u8 port,
 	struct mlx5_ib_dev *dev = to_mdev(ibdev);
 	struct mlx5_core_dev *mdev = dev->mdev;
 	struct mlx5_hca_vport_context *rep;
-	int max_mtu;
-	int oper_mtu;
+	u16 max_mtu;
+	u16 oper_mtu;
 	int err;
 	u8 ib_link_width_oper;
 	u8 vl_hw_cap;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 402994b..be68996 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1393,7 +1393,7 @@ static int mlx5e_set_dev_port_mtu(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
-	int hw_mtu;
+	u16 hw_mtu;
 	int err;
 
 	err = mlx5_set_port_mtu(mdev, MLX5E_SW2HW_MTU(netdev->mtu), 1);
@@ -1911,7 +1911,7 @@ static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu)
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
 	bool was_opened;
-	int max_mtu;
+	u16 max_mtu;
 	int err = 0;
 
 	mlx5_query_port_max_mtu(mdev, &max_mtu, 1);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index a87e773..53a793b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -246,8 +246,8 @@ int mlx5_query_port_admin_status(struct mlx5_core_dev *dev,
 }
 EXPORT_SYMBOL_GPL(mlx5_query_port_admin_status);
 
-static void mlx5_query_port_mtu(struct mlx5_core_dev *dev, int *admin_mtu,
-				int *max_mtu, int *oper_mtu, u8 port)
+static void mlx5_query_port_mtu(struct mlx5_core_dev *dev, u16 *admin_mtu,
+				u16 *max_mtu, u16 *oper_mtu, u8 port)
 {
 	u32 in[MLX5_ST_SZ_DW(pmtu_reg)];
 	u32 out[MLX5_ST_SZ_DW(pmtu_reg)];
@@ -267,7 +267,7 @@ static void mlx5_query_port_mtu(struct mlx5_core_dev *dev, int *admin_mtu,
 		*admin_mtu = MLX5_GET(pmtu_reg, out, admin_mtu);
 }
 
-int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu, u8 port)
+int mlx5_set_port_mtu(struct mlx5_core_dev *dev, u16 mtu, u8 port)
 {
 	u32 in[MLX5_ST_SZ_DW(pmtu_reg)];
 	u32 out[MLX5_ST_SZ_DW(pmtu_reg)];
@@ -282,14 +282,14 @@ int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu, u8 port)
 }
 EXPORT_SYMBOL_GPL(mlx5_set_port_mtu);
 
-void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, int *max_mtu,
+void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, u16 *max_mtu,
 			     u8 port)
 {
 	mlx5_query_port_mtu(dev, NULL, max_mtu, NULL, port);
 }
 EXPORT_SYMBOL_GPL(mlx5_query_port_max_mtu);
 
-void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, int *oper_mtu,
+void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, u16 *oper_mtu,
 			      u8 port)
 {
 	mlx5_query_port_mtu(dev, NULL, NULL, oper_mtu, port);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 1e3006d..46dd88e 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -813,9 +813,9 @@ int mlx5_set_port_admin_status(struct mlx5_core_dev *dev,
 int mlx5_query_port_admin_status(struct mlx5_core_dev *dev,
 				 enum mlx5_port_status *status);
 
-int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu, u8 port);
-void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, int *max_mtu, u8 port);
-void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, int *oper_mtu,
+int mlx5_set_port_mtu(struct mlx5_core_dev *dev, u16 mtu, u8 port);
+void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, u16 *max_mtu, u8 port);
+void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, u16 *oper_mtu,
 			      u8 port);
 
 int mlx5_query_port_vl_hw_cap(struct mlx5_core_dev *dev,
-- 
2.1.0


From 3f06b1ef45eba068006f22d9f351146c5480bc3c Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Fri, 22 Apr 2016 00:33:04 +0300
Subject: [PATCH 15/42] net/mlx5e: Fix minimum MTU

[ Upstream commit d8edd2469ace550db707798180d1c84d81f93bca ]

Minimum MTU that can be set in Connectx4 device is 68.

This fixes the case where a user wants to set invalid MTU,
the driver will fail to satisfy this request and the interface
will stay down.

It is better to report an error and continue working with old
mtu.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index be68996..13232e5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1906,22 +1906,27 @@ static int mlx5e_set_features(struct net_device *netdev,
 	return err;
 }
 
+#define MXL5_HW_MIN_MTU 64
+#define MXL5E_MIN_MTU (MXL5_HW_MIN_MTU + ETH_FCS_LEN)
+
 static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
 	bool was_opened;
 	u16 max_mtu;
+	u16 min_mtu;
 	int err = 0;
 
 	mlx5_query_port_max_mtu(mdev, &max_mtu, 1);
 
 	max_mtu = MLX5E_HW2SW_MTU(max_mtu);
+	min_mtu = MLX5E_HW2SW_MTU(MXL5E_MIN_MTU);
 
-	if (new_mtu > max_mtu) {
+	if (new_mtu > max_mtu || new_mtu < min_mtu) {
 		netdev_err(netdev,
-			   "%s: Bad MTU (%d) > (%d) Max\n",
-			   __func__, new_mtu, max_mtu);
+			   "%s: Bad MTU (%d), valid range is: [%d..%d]\n",
+			   __func__, new_mtu, min_mtu, max_mtu);
 		return -EINVAL;
 	}
 
-- 
2.1.0


From b7f0ee1691ae934e14542deb514fcdfef981c6d2 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Fri, 22 Apr 2016 00:33:05 +0300
Subject: [PATCH 16/42] net/mlx5e: Use vport MTU rather than physical port MTU

[ Upstream commit cd255efff9baadd654d6160e52d17ae7c568c9d3 ]

Set and report vport MTU rather than physical MTU,
Driver will set both vport and physical port mtu and will
rely on the query of vport mtu.

SRIOV VFs have to report their MTU to their vport manager (PF),
and this will allow them to work with any MTU they need
without failing the request.

Also for some cases where the PF is not a port owner, PF can
work with MTU less than the physical port mtu if set physical
port mtu didn't take effect.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 44 ++++++++++++++++++-----
 drivers/net/ethernet/mellanox/mlx5/core/vport.c   | 40 +++++++++++++++++++++
 include/linux/mlx5/vport.h                        |  2 ++
 3 files changed, 77 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 13232e5..e293a2e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1389,24 +1389,50 @@ static int mlx5e_refresh_tirs_self_loopback_enable(struct mlx5e_priv *priv)
 	return 0;
 }
 
-static int mlx5e_set_dev_port_mtu(struct net_device *netdev)
+static int mlx5e_set_mtu(struct mlx5e_priv *priv, u16 mtu)
 {
-	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
-	u16 hw_mtu;
+	u16 hw_mtu = MLX5E_SW2HW_MTU(mtu);
 	int err;
 
-	err = mlx5_set_port_mtu(mdev, MLX5E_SW2HW_MTU(netdev->mtu), 1);
+	err = mlx5_set_port_mtu(mdev, hw_mtu, 1);
 	if (err)
 		return err;
 
-	mlx5_query_port_oper_mtu(mdev, &hw_mtu, 1);
+	/* Update vport context MTU */
+	mlx5_modify_nic_vport_mtu(mdev, hw_mtu);
+	return 0;
+}
+
+static void mlx5e_query_mtu(struct mlx5e_priv *priv, u16 *mtu)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	u16 hw_mtu = 0;
+	int err;
+
+	err = mlx5_query_nic_vport_mtu(mdev, &hw_mtu);
+	if (err || !hw_mtu) /* fallback to port oper mtu */
+		mlx5_query_port_oper_mtu(mdev, &hw_mtu, 1);
+
+	*mtu = MLX5E_HW2SW_MTU(hw_mtu);
+}
+
+static int mlx5e_set_dev_port_mtu(struct net_device *netdev)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	u16 mtu;
+	int err;
+
+	err = mlx5e_set_mtu(priv, netdev->mtu);
+	if (err)
+		return err;
 
-	if (MLX5E_HW2SW_MTU(hw_mtu) != netdev->mtu)
-		netdev_warn(netdev, "%s: Port MTU %d is different than netdev mtu %d\n",
-			    __func__, MLX5E_HW2SW_MTU(hw_mtu), netdev->mtu);
+	mlx5e_query_mtu(priv, &mtu);
+	if (mtu != netdev->mtu)
+		netdev_warn(netdev, "%s: VPort MTU %d is different than netdev mtu %d\n",
+			    __func__, mtu, netdev->mtu);
 
-	netdev->mtu = MLX5E_HW2SW_MTU(hw_mtu);
+	netdev->mtu = mtu;
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index c7398b9..6d5f56e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -196,6 +196,46 @@ int mlx5_modify_nic_vport_mac_address(struct mlx5_core_dev *mdev,
 }
 EXPORT_SYMBOL_GPL(mlx5_modify_nic_vport_mac_address);
 
+int mlx5_query_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 *mtu)
+{
+	int outlen = MLX5_ST_SZ_BYTES(query_nic_vport_context_out);
+	u32 *out;
+	int err;
+
+	out = mlx5_vzalloc(outlen);
+	if (!out)
+		return -ENOMEM;
+
+	err = mlx5_query_nic_vport_context(mdev, 0, out, outlen);
+	if (!err)
+		*mtu = MLX5_GET(query_nic_vport_context_out, out,
+				nic_vport_context.mtu);
+
+	kvfree(out);
+	return err;
+}
+EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_mtu);
+
+int mlx5_modify_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 mtu)
+{
+	int inlen = MLX5_ST_SZ_BYTES(modify_nic_vport_context_in);
+	void *in;
+	int err;
+
+	in = mlx5_vzalloc(inlen);
+	if (!in)
+		return -ENOMEM;
+
+	MLX5_SET(modify_nic_vport_context_in, in, field_select.mtu, 1);
+	MLX5_SET(modify_nic_vport_context_in, in, nic_vport_context.mtu, mtu);
+
+	err = mlx5_modify_nic_vport_context(mdev, in, inlen);
+
+	kvfree(in);
+	return err;
+}
+EXPORT_SYMBOL_GPL(mlx5_modify_nic_vport_mtu);
+
 int mlx5_query_nic_vport_mac_list(struct mlx5_core_dev *dev,
 				  u32 vport,
 				  enum mlx5_list_type list_type,
diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h
index 1237710..a3f3c71 100644
--- a/include/linux/mlx5/vport.h
+++ b/include/linux/mlx5/vport.h
@@ -45,6 +45,8 @@ int mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev,
 				     u16 vport, u8 *addr);
 int mlx5_modify_nic_vport_mac_address(struct mlx5_core_dev *dev,
 				      u16 vport, u8 *addr);
+int mlx5_query_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 *mtu);
+int mlx5_modify_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 mtu);
 int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev,
 					   u64 *system_image_guid);
 int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid);
-- 
2.1.0


From cb3ddea55ce024f032affe0280e4b1009fb98272 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 21 Apr 2016 22:23:31 +0200
Subject: [PATCH 17/42] ipv4/fib: don't warn when primary address is missing if
 in_dev is dead

[ Upstream commit 391a20333b8393ef2e13014e6e59d192c5594471 ]

After commit fbd40ea0180a ("ipv4: Don't do expensive useless work
during inetdev destroy.") when deleting an interface,
fib_del_ifaddr() can be executed without any primary address
present on the dead interface.

The above is safe, but triggers some "bug: prim == NULL" warnings.

This commit avoids warning if the in_dev is dead

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_frontend.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 8a9246d..63566ec 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -904,7 +904,11 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim)
 	if (ifa->ifa_flags & IFA_F_SECONDARY) {
 		prim = inet_ifa_byprefix(in_dev, any, ifa->ifa_mask);
 		if (!prim) {
-			pr_warn("%s: bug: prim == NULL\n", __func__);
+			/* if the device has been deleted, we don't perform
+			 * address promotion
+			 */
+			if (!in_dev->dead)
+				pr_warn("%s: bug: prim == NULL\n", __func__);
 			return;
 		}
 		if (iprim && iprim != prim) {
-- 
2.1.0


From 1d0a1105cc4399970638c99d1b313886c4d97e96 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 23 Apr 2016 11:35:46 -0700
Subject: [PATCH 18/42] net/mlx4_en: fix spurious timestamping callbacks

[ Upstream commit fc96256c906362e845d848d0f6a6354450059e81 ]

When multiple skb are TX-completed in a row, we might incorrectly keep
a timestamp of a prior skb and cause extra work.

Fixes: ec693d47010e8 ("net/mlx4_en: Add HW timestamping (TS) support")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_tx.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index e0946ab..0debb61 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -402,7 +402,6 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev,
 	u32 packets = 0;
 	u32 bytes = 0;
 	int factor = priv->cqe_factor;
-	u64 timestamp = 0;
 	int done = 0;
 	int budget = priv->tx_work_limit;
 	u32 last_nr_txbb;
@@ -442,9 +441,12 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev,
 		new_index = be16_to_cpu(cqe->wqe_index) & size_mask;
 
 		do {
+			u64 timestamp = 0;
+
 			txbbs_skipped += last_nr_txbb;
 			ring_index = (ring_index + last_nr_txbb) & size_mask;
-			if (ring->tx_info[ring_index].ts_requested)
+
+			if (unlikely(ring->tx_info[ring_index].ts_requested))
 				timestamp = mlx4_en_get_cqe_ts(cqe);
 
 			/* free next descriptor */
-- 
2.1.0


From 376c8e08e4e6ef26e5a1305421a00b64e57333e7 Mon Sep 17 00:00:00 2001
From: Jann Horn <jannh@google.com>
Date: Tue, 26 Apr 2016 22:26:26 +0200
Subject: [PATCH 19/42] bpf: fix double-fdput in replace_map_fd_with_map_ptr()

[ Upstream commit 8358b02bf67d3a5d8a825070e1aa73f25fb2e4c7 ]

When bpf(BPF_PROG_LOAD, ...) was invoked with a BPF program whose bytecode
references a non-map file descriptor as a map file descriptor, the error
handling code called fdput() twice instead of once (in __bpf_map_get() and
in replace_map_fd_with_map_ptr()). If the file descriptor table of the
current task is shared, this causes f_count to be decremented too much,
allowing the struct file to be freed while it is still in use
(use-after-free). This can be exploited to gain root privileges by an
unprivileged user.

This bug was introduced in
commit 0246e64d9a5f ("bpf: handle pseudo BPF_LD_IMM64 insn"), but is only
exploitable since
commit 1be7f75d1668 ("bpf: enable non-root eBPF programs") because
previously, CAP_SYS_ADMIN was required to reach the vulnerable code.

(posted publicly according to request by maintainer)

Signed-off-by: Jann Horn <jannh@google.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c21cb14..e3798cf 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2004,7 +2004,6 @@ static int replace_map_fd_with_map_ptr(struct verifier_env *env)
 			if (IS_ERR(map)) {
 				verbose("fd %d is not pointing to valid bpf_map\n",
 					insn->imm);
-				fdput(f);
 				return PTR_ERR(map);
 			}
 
-- 
2.1.0


From a330e28db39d584ce05fda52d96d4c15c7e45255 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@fb.com>
Date: Wed, 27 Apr 2016 18:56:20 -0700
Subject: [PATCH 20/42] bpf: fix refcnt overflow

[ Upstream commit 92117d8443bc5afacc8d5ba82e541946310f106e ]

On a system with >32Gbyte of phyiscal memory and infinite RLIMIT_MEMLOCK,
the malicious application may overflow 32-bit bpf program refcnt.
It's also possible to overflow map refcnt on 1Tb system.
Impose 32k hard limit which means that the same bpf program or
map cannot be shared by more than 32k processes.

Fixes: 1be7f75d1668 ("bpf: enable non-root eBPF programs")
Reported-by: Jann Horn <jannh@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/bpf.h   |  3 ++-
 kernel/bpf/inode.c    |  7 ++++---
 kernel/bpf/syscall.c  | 24 ++++++++++++++++++++----
 kernel/bpf/verifier.c | 11 +++++++----
 4 files changed, 33 insertions(+), 12 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 83d1926..67bc2da 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -165,12 +165,13 @@ void bpf_register_prog_type(struct bpf_prog_type_list *tl);
 void bpf_register_map_type(struct bpf_map_type_list *tl);
 
 struct bpf_prog *bpf_prog_get(u32 ufd);
+struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog);
 void bpf_prog_put(struct bpf_prog *prog);
 void bpf_prog_put_rcu(struct bpf_prog *prog);
 
 struct bpf_map *bpf_map_get_with_uref(u32 ufd);
 struct bpf_map *__bpf_map_get(struct fd f);
-void bpf_map_inc(struct bpf_map *map, bool uref);
+struct bpf_map *bpf_map_inc(struct bpf_map *map, bool uref);
 void bpf_map_put_with_uref(struct bpf_map *map);
 void bpf_map_put(struct bpf_map *map);
 
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index f2ece3c..8f94ca1 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -31,10 +31,10 @@ static void *bpf_any_get(void *raw, enum bpf_type type)
 {
 	switch (type) {
 	case BPF_TYPE_PROG:
-		atomic_inc(&((struct bpf_prog *)raw)->aux->refcnt);
+		raw = bpf_prog_inc(raw);
 		break;
 	case BPF_TYPE_MAP:
-		bpf_map_inc(raw, true);
+		raw = bpf_map_inc(raw, true);
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -297,7 +297,8 @@ static void *bpf_obj_do_get(const struct filename *pathname,
 		goto out;
 
 	raw = bpf_any_get(inode->i_private, *type);
-	touch_atime(&path);
+	if (!IS_ERR(raw))
+		touch_atime(&path);
 
 	path_put(&path);
 	return raw;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 6373970..aa5f397 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -201,11 +201,18 @@ struct bpf_map *__bpf_map_get(struct fd f)
 	return f.file->private_data;
 }
 
-void bpf_map_inc(struct bpf_map *map, bool uref)
+/* prog's and map's refcnt limit */
+#define BPF_MAX_REFCNT 32768
+
+struct bpf_map *bpf_map_inc(struct bpf_map *map, bool uref)
 {
-	atomic_inc(&map->refcnt);
+	if (atomic_inc_return(&map->refcnt) > BPF_MAX_REFCNT) {
+		atomic_dec(&map->refcnt);
+		return ERR_PTR(-EBUSY);
+	}
 	if (uref)
 		atomic_inc(&map->usercnt);
+	return map;
 }
 
 struct bpf_map *bpf_map_get_with_uref(u32 ufd)
@@ -217,7 +224,7 @@ struct bpf_map *bpf_map_get_with_uref(u32 ufd)
 	if (IS_ERR(map))
 		return map;
 
-	bpf_map_inc(map, true);
+	map = bpf_map_inc(map, true);
 	fdput(f);
 
 	return map;
@@ -600,6 +607,15 @@ static struct bpf_prog *__bpf_prog_get(struct fd f)
 	return f.file->private_data;
 }
 
+struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog)
+{
+	if (atomic_inc_return(&prog->aux->refcnt) > BPF_MAX_REFCNT) {
+		atomic_dec(&prog->aux->refcnt);
+		return ERR_PTR(-EBUSY);
+	}
+	return prog;
+}
+
 /* called by sockets/tracing/seccomp before attaching program to an event
  * pairs with bpf_prog_put()
  */
@@ -612,7 +628,7 @@ struct bpf_prog *bpf_prog_get(u32 ufd)
 	if (IS_ERR(prog))
 		return prog;
 
-	atomic_inc(&prog->aux->refcnt);
+	prog = bpf_prog_inc(prog);
 	fdput(f);
 
 	return prog;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index e3798cf..5a615c18 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2023,15 +2023,18 @@ static int replace_map_fd_with_map_ptr(struct verifier_env *env)
 				return -E2BIG;
 			}
 
-			/* remember this map */
-			env->used_maps[env->used_map_cnt++] = map;
-
 			/* hold the map. If the program is rejected by verifier,
 			 * the map will be released by release_maps() or it
 			 * will be used by the valid program until it's unloaded
 			 * and all maps are released in free_bpf_prog_info()
 			 */
-			bpf_map_inc(map, false);
+			map = bpf_map_inc(map, false);
+			if (IS_ERR(map)) {
+				fdput(f);
+				return PTR_ERR(map);
+			}
+			env->used_maps[env->used_map_cnt++] = map;
+
 			fdput(f);
 next_insn:
 			insn++;
-- 
2.1.0


From 8a8a150f6da135aa5548fa352567aa81dbdf0f31 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@fb.com>
Date: Wed, 27 Apr 2016 18:56:21 -0700
Subject: [PATCH 21/42] bpf: fix check_map_func_compatibility logic

[ Upstream commit 6aff67c85c9e5a4bc99e5211c1bac547936626ca ]

The commit 35578d798400 ("bpf: Implement function bpf_perf_event_read() that get the selected hardware PMU conuter")
introduced clever way to check bpf_helper<->map_type compatibility.
Later on commit a43eec304259 ("bpf: introduce bpf_perf_event_output() helper") adjusted
the logic and inadvertently broke it.
Get rid of the clever bool compare and go back to two-way check
from map and from helper perspective.

Fixes: a43eec304259 ("bpf: introduce bpf_perf_event_output() helper")
Reported-by: Jann Horn <jannh@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c | 53 +++++++++++++++++++++++++++++++--------------------
 1 file changed, 32 insertions(+), 21 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 5a615c18..2cbfba7 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -239,15 +239,6 @@ static const char * const reg_type_str[] = {
 	[CONST_IMM]		= "imm",
 };
 
-static const struct {
-	int map_type;
-	int func_id;
-} func_limit[] = {
-	{BPF_MAP_TYPE_PROG_ARRAY, BPF_FUNC_tail_call},
-	{BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_read},
-	{BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_output},
-};
-
 static void print_verifier_state(struct verifier_env *env)
 {
 	enum bpf_reg_type t;
@@ -898,24 +889,44 @@ static int check_func_arg(struct verifier_env *env, u32 regno,
 
 static int check_map_func_compatibility(struct bpf_map *map, int func_id)
 {
-	bool bool_map, bool_func;
-	int i;
-
 	if (!map)
 		return 0;
 
-	for (i = 0; i < ARRAY_SIZE(func_limit); i++) {
-		bool_map = (map->map_type == func_limit[i].map_type);
-		bool_func = (func_id == func_limit[i].func_id);
-		/* only when map & func pair match it can continue.
-		 * don't allow any other map type to be passed into
-		 * the special func;
-		 */
-		if (bool_func && bool_map != bool_func)
-			return -EINVAL;
+	/* We need a two way check, first is from map perspective ... */
+	switch (map->map_type) {
+	case BPF_MAP_TYPE_PROG_ARRAY:
+		if (func_id != BPF_FUNC_tail_call)
+			goto error;
+		break;
+	case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
+		if (func_id != BPF_FUNC_perf_event_read &&
+		    func_id != BPF_FUNC_perf_event_output)
+			goto error;
+		break;
+	default:
+		break;
+	}
+
+	/* ... and second from the function itself. */
+	switch (func_id) {
+	case BPF_FUNC_tail_call:
+		if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY)
+			goto error;
+		break;
+	case BPF_FUNC_perf_event_read:
+	case BPF_FUNC_perf_event_output:
+		if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY)
+			goto error;
+		break;
+	default:
+		break;
 	}
 
 	return 0;
+error:
+	verbose("cannot pass map_type %d into func %d\n",
+		map->map_type, func_id);
+	return -EINVAL;
 }
 
 static int check_call(struct verifier_env *env, int func_id)
-- 
2.1.0


From e16855f9304026b12905b93e8beac7eec608bbde Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@fb.com>
Date: Wed, 27 Apr 2016 18:56:22 -0700
Subject: [PATCH 22/42] samples/bpf: fix trace_output example

[ Upstream commit 569cc39d39385a74b23145496bca2df5ac8b2fb8 ]

llvm cannot always recognize memset as builtin function and optimize
it away, so just delete it. It was a leftover from testing
of bpf_perf_event_output() with large data structures.

Fixes: 39111695b1b8 ("samples: bpf: add bpf_perf_event_output example")
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 samples/bpf/trace_output_kern.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/samples/bpf/trace_output_kern.c b/samples/bpf/trace_output_kern.c
index 8d8d1ec..9b96f4f 100644
--- a/samples/bpf/trace_output_kern.c
+++ b/samples/bpf/trace_output_kern.c
@@ -18,7 +18,6 @@ int bpf_prog1(struct pt_regs *ctx)
 		u64 cookie;
 	} data;
 
-	memset(&data, 0, sizeof(data));
 	data.pid = bpf_get_current_pid_tgid();
 	data.cookie = 0x12345678;
 
-- 
2.1.0


From ee392d734042037f0fb547316891f584b82016ee Mon Sep 17 00:00:00 2001
From: Tim Bingham <tbingham@akamai.com>
Date: Fri, 29 Apr 2016 13:30:23 -0400
Subject: [PATCH 23/42] net: Implement net_dbg_ratelimited() for
 CONFIG_DYNAMIC_DEBUG case

[ Upstream commit 2c94b53738549d81dc7464a32117d1f5112c64d3 ]

Prior to commit d92cff89a0c8 ("net_dbg_ratelimited: turn into no-op
when !DEBUG") the implementation of net_dbg_ratelimited() was buggy
for both the DEBUG and CONFIG_DYNAMIC_DEBUG cases.

The bug was that net_ratelimit() was being called and, despite
returning true, nothing was being printed to the console. This
resulted in messages like the following -

"net_ratelimit: %d callbacks suppressed"

with no other output nearby.

After commit d92cff89a0c8 ("net_dbg_ratelimited: turn into no-op when
!DEBUG") the bug is fixed for the DEBUG case. However, there's no
output at all for CONFIG_DYNAMIC_DEBUG case.

This patch restores debug output (if enabled) for the
CONFIG_DYNAMIC_DEBUG case.

Add a definition of net_dbg_ratelimited() for the CONFIG_DYNAMIC_DEBUG
case. The implementation takes care to check that dynamic debugging is
enabled before calling net_ratelimit().

Fixes: d92cff89a0c8 ("net_dbg_ratelimited: turn into no-op when !DEBUG")
Signed-off-by: Tim Bingham <tbingham@akamai.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/net.h | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/include/linux/net.h b/include/linux/net.h
index 0b4ac7d..25ef630 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -245,7 +245,15 @@ do {								\
 	net_ratelimited_function(pr_warn, fmt, ##__VA_ARGS__)
 #define net_info_ratelimited(fmt, ...)				\
 	net_ratelimited_function(pr_info, fmt, ##__VA_ARGS__)
-#if defined(DEBUG)
+#if defined(CONFIG_DYNAMIC_DEBUG)
+#define net_dbg_ratelimited(fmt, ...)					\
+do {									\
+	DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt);			\
+	if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT) &&	\
+	    net_ratelimit())						\
+		__dynamic_pr_debug(&descriptor, fmt, ##__VA_ARGS__);	\
+} while (0)
+#elif defined(DEBUG)
 #define net_dbg_ratelimited(fmt, ...)				\
 	net_ratelimited_function(pr_debug, fmt, ##__VA_ARGS__)
 #else
-- 
2.1.0


From 2ae6918cbd023c5fcb8c3227c1a4f995ee21450d Mon Sep 17 00:00:00 2001
From: Jiri Benc <jbenc@redhat.com>
Date: Fri, 29 Apr 2016 23:31:32 +0200
Subject: [PATCH 24/42] gre: do not pull header in ICMP error processing

[ Upstream commit b7f8fe251e4609e2a437bd2c2dea01e61db6849c ]

iptunnel_pull_header expects that IP header was already pulled; with this
expectation, it pulls the tunnel header. This is not true in gre_err.
Furthermore, ipv4_update_pmtu and ipv4_redirect expect that skb->data points
to the IP header.

We cannot pull the tunnel header in this path. It's just a matter of not
calling iptunnel_pull_header - we don't need any of its effects.

Fixes: bda7bb463436 ("gre: Allow multiple protocol listener for gre protocol.")
Signed-off-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_gre.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 41ba68d..d0c1e77 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -179,6 +179,7 @@ static __be16 tnl_flags_to_gre_flags(__be16 tflags)
 	return flags;
 }
 
+/* Fills in tpi and returns header length to be pulled. */
 static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 			    bool *csum_err)
 {
@@ -238,7 +239,7 @@ static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 				return -EINVAL;
 		}
 	}
-	return iptunnel_pull_header(skb, hdr_len, tpi->proto);
+	return hdr_len;
 }
 
 static void ipgre_err(struct sk_buff *skb, u32 info,
@@ -341,7 +342,7 @@ static void gre_err(struct sk_buff *skb, u32 info)
 	struct tnl_ptk_info tpi;
 	bool csum_err = false;
 
-	if (parse_gre_header(skb, &tpi, &csum_err)) {
+	if (parse_gre_header(skb, &tpi, &csum_err) < 0) {
 		if (!csum_err)		/* ignore csum errors. */
 			return;
 	}
@@ -419,6 +420,7 @@ static int gre_rcv(struct sk_buff *skb)
 {
 	struct tnl_ptk_info tpi;
 	bool csum_err = false;
+	int hdr_len;
 
 #ifdef CONFIG_NET_IPGRE_BROADCAST
 	if (ipv4_is_multicast(ip_hdr(skb)->daddr)) {
@@ -428,7 +430,10 @@ static int gre_rcv(struct sk_buff *skb)
 	}
 #endif
 
-	if (parse_gre_header(skb, &tpi, &csum_err) < 0)
+	hdr_len = parse_gre_header(skb, &tpi, &csum_err);
+	if (hdr_len < 0)
+		goto drop;
+	if (iptunnel_pull_header(skb, hdr_len, tpi.proto) < 0)
 		goto drop;
 
 	if (ipgre_rcv(skb, &tpi) == PACKET_RCVD)
-- 
2.1.0


From 775c101824687479cc15f59457e0c8478a3d4925 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Thu, 25 Feb 2016 14:55:00 -0800
Subject: [PATCH 25/42] net_sched: introduce qdisc_replace() helper

[ Upstream commit 86a7996cc8a078793670d82ed97d5a99bb4e8496 ]

Remove nearly duplicated code and prepare for the following patch.

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h | 17 +++++++++++++++++
 net/sched/sch_cbq.c       |  7 +------
 net/sched/sch_drr.c       |  6 +-----
 net/sched/sch_dsmark.c    |  8 +-------
 net/sched/sch_hfsc.c      |  6 +-----
 net/sched/sch_htb.c       |  9 +--------
 net/sched/sch_multiq.c    |  8 +-------
 net/sched/sch_netem.c     | 10 +---------
 net/sched/sch_prio.c      |  8 +-------
 net/sched/sch_qfq.c       |  6 +-----
 net/sched/sch_red.c       |  7 +------
 net/sched/sch_sfb.c       |  7 +------
 net/sched/sch_tbf.c       |  8 +-------
 13 files changed, 29 insertions(+), 78 deletions(-)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 636a362..8fdad9f 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -707,6 +707,23 @@ static inline void qdisc_reset_queue(struct Qdisc *sch)
 	sch->qstats.backlog = 0;
 }
 
+static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new,
+					  struct Qdisc **pold)
+{
+	struct Qdisc *old;
+
+	sch_tree_lock(sch);
+	old = *pold;
+	*pold = new;
+	if (old != NULL) {
+		qdisc_tree_decrease_qlen(old, old->q.qlen);
+		qdisc_reset(old);
+	}
+	sch_tree_unlock(sch);
+
+	return old;
+}
+
 static inline unsigned int __qdisc_queue_drop(struct Qdisc *sch,
 					      struct sk_buff_head *list)
 {
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index c538d9e..7f8474c 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1624,13 +1624,8 @@ static int cbq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 			new->reshape_fail = cbq_reshape_fail;
 #endif
 	}
-	sch_tree_lock(sch);
-	*old = cl->q;
-	cl->q = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
 
+	*old = qdisc_replace(sch, new, &cl->q);
 	return 0;
 }
 
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index a1cd778..b96c9a8 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -226,11 +226,7 @@ static int drr_graft_class(struct Qdisc *sch, unsigned long arg,
 			new = &noop_qdisc;
 	}
 
-	sch_tree_lock(sch);
-	drr_purge_queue(cl);
-	*old = cl->qdisc;
-	cl->qdisc = new;
-	sch_tree_unlock(sch);
+	*old = qdisc_replace(sch, new, &cl->qdisc);
 	return 0;
 }
 
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index f357f34..cfddb1c 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -73,13 +73,7 @@ static int dsmark_graft(struct Qdisc *sch, unsigned long arg,
 			new = &noop_qdisc;
 	}
 
-	sch_tree_lock(sch);
-	*old = p->q;
-	p->q = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
-
+	*old = qdisc_replace(sch, new, &p->q);
 	return 0;
 }
 
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index b7ebe2c..089f3b6 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1215,11 +1215,7 @@ hfsc_graft_class(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 			new = &noop_qdisc;
 	}
 
-	sch_tree_lock(sch);
-	hfsc_purge_queue(sch, cl);
-	*old = cl->qdisc;
-	cl->qdisc = new;
-	sch_tree_unlock(sch);
+	*old = qdisc_replace(sch, new, &cl->qdisc);
 	return 0;
 }
 
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 15ccd7f..0efbcf3 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1163,14 +1163,7 @@ static int htb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 				     cl->common.classid)) == NULL)
 		return -ENOBUFS;
 
-	sch_tree_lock(sch);
-	*old = cl->un.leaf.q;
-	cl->un.leaf.q = new;
-	if (*old != NULL) {
-		qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-		qdisc_reset(*old);
-	}
-	sch_tree_unlock(sch);
+	*old = qdisc_replace(sch, new, &cl->un.leaf.q);
 	return 0;
 }
 
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index 4e904ca..a0103a1 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -303,13 +303,7 @@ static int multiq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 	if (new == NULL)
 		new = &noop_qdisc;
 
-	sch_tree_lock(sch);
-	*old = q->queues[band];
-	q->queues[band] = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
-
+	*old = qdisc_replace(sch, new, &q->queues[band]);
 	return 0;
 }
 
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 5abd1d9..0a6ddaf 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -1037,15 +1037,7 @@ static int netem_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 {
 	struct netem_sched_data *q = qdisc_priv(sch);
 
-	sch_tree_lock(sch);
-	*old = q->qdisc;
-	q->qdisc = new;
-	if (*old) {
-		qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-		qdisc_reset(*old);
-	}
-	sch_tree_unlock(sch);
-
+	*old = qdisc_replace(sch, new, &q->qdisc);
 	return 0;
 }
 
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index ba6487f..1b4aaec 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -268,13 +268,7 @@ static int prio_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 	if (new == NULL)
 		new = &noop_qdisc;
 
-	sch_tree_lock(sch);
-	*old = q->queues[band];
-	q->queues[band] = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
-
+	*old = qdisc_replace(sch, new, &q->queues[band]);
 	return 0;
 }
 
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 3dc3a6e..b5c52ca 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -617,11 +617,7 @@ static int qfq_graft_class(struct Qdisc *sch, unsigned long arg,
 			new = &noop_qdisc;
 	}
 
-	sch_tree_lock(sch);
-	qfq_purge_queue(cl);
-	*old = cl->qdisc;
-	cl->qdisc = new;
-	sch_tree_unlock(sch);
+	*old = qdisc_replace(sch, new, &cl->qdisc);
 	return 0;
 }
 
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 6c0534c..d5abcee 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -313,12 +313,7 @@ static int red_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 	if (new == NULL)
 		new = &noop_qdisc;
 
-	sch_tree_lock(sch);
-	*old = q->qdisc;
-	q->qdisc = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
+	*old = qdisc_replace(sch, new, &q->qdisc);
 	return 0;
 }
 
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index 5bbb633..0e74e55 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -606,12 +606,7 @@ static int sfb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 	if (new == NULL)
 		new = &noop_qdisc;
 
-	sch_tree_lock(sch);
-	*old = q->qdisc;
-	q->qdisc = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
+	*old = qdisc_replace(sch, new, &q->qdisc);
 	return 0;
 }
 
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index a4afde1..56a1aef 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -502,13 +502,7 @@ static int tbf_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 	if (new == NULL)
 		new = &noop_qdisc;
 
-	sch_tree_lock(sch);
-	*old = q->qdisc;
-	q->qdisc = new;
-	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
-	qdisc_reset(*old);
-	sch_tree_unlock(sch);
-
+	*old = qdisc_replace(sch, new, &q->qdisc);
 	return 0;
 }
 
-- 
2.1.0


From 26ff9df98b6b5800fc83a8afc47e5e17bc9060c6 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Thu, 25 Feb 2016 14:55:01 -0800
Subject: [PATCH 26/42] net_sched: update hierarchical backlog too

[ Upstream commit 2ccccf5fb43ff62b2b96cc58d95fc0b3596516e4 ]

When the bottom qdisc decides to, for example, drop some packet,
it calls qdisc_tree_decrease_qlen() to update the queue length
for all its ancestors, we need to update the backlog too to
keep the stats on root qdisc accurate.

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/codel.h       |  4 ++++
 include/net/sch_generic.h |  5 +++--
 net/sched/sch_api.c       |  8 +++++---
 net/sched/sch_cbq.c       |  5 +++--
 net/sched/sch_choke.c     |  6 ++++--
 net/sched/sch_codel.c     | 10 ++++++----
 net/sched/sch_drr.c       |  3 ++-
 net/sched/sch_fq.c        |  4 +++-
 net/sched/sch_fq_codel.c  | 17 ++++++++++++-----
 net/sched/sch_hfsc.c      |  3 ++-
 net/sched/sch_hhf.c       | 10 +++++++---
 net/sched/sch_htb.c       | 10 ++++++----
 net/sched/sch_multiq.c    |  8 +++++---
 net/sched/sch_netem.c     |  3 ++-
 net/sched/sch_pie.c       |  5 +++--
 net/sched/sch_prio.c      |  7 ++++---
 net/sched/sch_qfq.c       |  3 ++-
 net/sched/sch_red.c       |  3 ++-
 net/sched/sch_sfb.c       |  3 ++-
 net/sched/sch_sfq.c       | 16 +++++++++-------
 net/sched/sch_tbf.c       |  7 +++++--
 21 files changed, 91 insertions(+), 49 deletions(-)

diff --git a/include/net/codel.h b/include/net/codel.h
index 267e702..d168aca 100644
--- a/include/net/codel.h
+++ b/include/net/codel.h
@@ -162,12 +162,14 @@ struct codel_vars {
  * struct codel_stats - contains codel shared variables and stats
  * @maxpacket:	largest packet we've seen so far
  * @drop_count:	temp count of dropped packets in dequeue()
+ * @drop_len:	bytes of dropped packets in dequeue()
  * ecn_mark:	number of packets we ECN marked instead of dropping
  * ce_mark:	number of packets CE marked because sojourn time was above ce_threshold
  */
 struct codel_stats {
 	u32		maxpacket;
 	u32		drop_count;
+	u32		drop_len;
 	u32		ecn_mark;
 	u32		ce_mark;
 };
@@ -308,6 +310,7 @@ static struct sk_buff *codel_dequeue(struct Qdisc *sch,
 								  vars->rec_inv_sqrt);
 					goto end;
 				}
+				stats->drop_len += qdisc_pkt_len(skb);
 				qdisc_drop(skb, sch);
 				stats->drop_count++;
 				skb = dequeue_func(vars, sch);
@@ -330,6 +333,7 @@ static struct sk_buff *codel_dequeue(struct Qdisc *sch,
 		if (params->ecn && INET_ECN_set_ce(skb)) {
 			stats->ecn_mark++;
 		} else {
+			stats->drop_len += qdisc_pkt_len(skb);
 			qdisc_drop(skb, sch);
 			stats->drop_count++;
 
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 8fdad9f..e5bba89 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -396,7 +396,8 @@ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue,
 			      struct Qdisc *qdisc);
 void qdisc_reset(struct Qdisc *qdisc);
 void qdisc_destroy(struct Qdisc *qdisc);
-void qdisc_tree_decrease_qlen(struct Qdisc *qdisc, unsigned int n);
+void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, unsigned int n,
+			       unsigned int len);
 struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 			  const struct Qdisc_ops *ops);
 struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue,
@@ -716,7 +717,7 @@ static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new,
 	old = *pold;
 	*pold = new;
 	if (old != NULL) {
-		qdisc_tree_decrease_qlen(old, old->q.qlen);
+		qdisc_tree_reduce_backlog(old, old->q.qlen, old->qstats.backlog);
 		qdisc_reset(old);
 	}
 	sch_tree_unlock(sch);
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index af1acf0..95b560f 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -744,14 +744,15 @@ static u32 qdisc_alloc_handle(struct net_device *dev)
 	return 0;
 }
 
-void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
+void qdisc_tree_reduce_backlog(struct Qdisc *sch, unsigned int n,
+			       unsigned int len)
 {
 	const struct Qdisc_class_ops *cops;
 	unsigned long cl;
 	u32 parentid;
 	int drops;
 
-	if (n == 0)
+	if (n == 0 && len == 0)
 		return;
 	drops = max_t(int, n, 0);
 	rcu_read_lock();
@@ -774,11 +775,12 @@ void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
 			cops->put(sch, cl);
 		}
 		sch->q.qlen -= n;
+		sch->qstats.backlog -= len;
 		__qdisc_qstats_drop(sch, drops);
 	}
 	rcu_read_unlock();
 }
-EXPORT_SYMBOL(qdisc_tree_decrease_qlen);
+EXPORT_SYMBOL(qdisc_tree_reduce_backlog);
 
 static void notify_and_destroy(struct net *net, struct sk_buff *skb,
 			       struct nlmsghdr *n, u32 clid,
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 7f8474c..baafddf 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1909,7 +1909,7 @@ static int cbq_delete(struct Qdisc *sch, unsigned long arg)
 {
 	struct cbq_sched_data *q = qdisc_priv(sch);
 	struct cbq_class *cl = (struct cbq_class *)arg;
-	unsigned int qlen;
+	unsigned int qlen, backlog;
 
 	if (cl->filters || cl->children || cl == &q->link)
 		return -EBUSY;
@@ -1917,8 +1917,9 @@ static int cbq_delete(struct Qdisc *sch, unsigned long arg)
 	sch_tree_lock(sch);
 
 	qlen = cl->q->q.qlen;
+	backlog = cl->q->qstats.backlog;
 	qdisc_reset(cl->q);
-	qdisc_tree_decrease_qlen(cl->q, qlen);
+	qdisc_tree_reduce_backlog(cl->q, qlen, backlog);
 
 	if (cl->next_alive)
 		cbq_deactivate_class(cl);
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index 5ffb8b8..0a08c86 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -128,8 +128,8 @@ static void choke_drop_by_idx(struct Qdisc *sch, unsigned int idx)
 		choke_zap_tail_holes(q);
 
 	qdisc_qstats_backlog_dec(sch, skb);
+	qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(skb));
 	qdisc_drop(skb, sch);
-	qdisc_tree_decrease_qlen(sch, 1);
 	--sch->q.qlen;
 }
 
@@ -456,6 +456,7 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt)
 		old = q->tab;
 		if (old) {
 			unsigned int oqlen = sch->q.qlen, tail = 0;
+			unsigned dropped = 0;
 
 			while (q->head != q->tail) {
 				struct sk_buff *skb = q->tab[q->head];
@@ -467,11 +468,12 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt)
 					ntab[tail++] = skb;
 					continue;
 				}
+				dropped += qdisc_pkt_len(skb);
 				qdisc_qstats_backlog_dec(sch, skb);
 				--sch->q.qlen;
 				qdisc_drop(skb, sch);
 			}
-			qdisc_tree_decrease_qlen(sch, oqlen - sch->q.qlen);
+			qdisc_tree_reduce_backlog(sch, oqlen - sch->q.qlen, dropped);
 			q->head = 0;
 			q->tail = tail;
 		}
diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c
index 535007d..9b7e298 100644
--- a/net/sched/sch_codel.c
+++ b/net/sched/sch_codel.c
@@ -79,12 +79,13 @@ static struct sk_buff *codel_qdisc_dequeue(struct Qdisc *sch)
 
 	skb = codel_dequeue(sch, &q->params, &q->vars, &q->stats, dequeue);
 
-	/* We cant call qdisc_tree_decrease_qlen() if our qlen is 0,
+	/* We cant call qdisc_tree_reduce_backlog() if our qlen is 0,
 	 * or HTB crashes. Defer it for next round.
 	 */
 	if (q->stats.drop_count && sch->q.qlen) {
-		qdisc_tree_decrease_qlen(sch, q->stats.drop_count);
+		qdisc_tree_reduce_backlog(sch, q->stats.drop_count, q->stats.drop_len);
 		q->stats.drop_count = 0;
+		q->stats.drop_len = 0;
 	}
 	if (skb)
 		qdisc_bstats_update(sch, skb);
@@ -116,7 +117,7 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct codel_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_CODEL_MAX + 1];
-	unsigned int qlen;
+	unsigned int qlen, dropped = 0;
 	int err;
 
 	if (!opt)
@@ -156,10 +157,11 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt)
 	while (sch->q.qlen > sch->limit) {
 		struct sk_buff *skb = __skb_dequeue(&sch->q);
 
+		dropped += qdisc_pkt_len(skb);
 		qdisc_qstats_backlog_dec(sch, skb);
 		qdisc_drop(skb, sch);
 	}
-	qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen);
+	qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped);
 
 	sch_tree_unlock(sch);
 	return 0;
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index b96c9a8..a63e879 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -53,9 +53,10 @@ static struct drr_class *drr_find_class(struct Qdisc *sch, u32 classid)
 static void drr_purge_queue(struct drr_class *cl)
 {
 	unsigned int len = cl->qdisc->q.qlen;
+	unsigned int backlog = cl->qdisc->qstats.backlog;
 
 	qdisc_reset(cl->qdisc);
-	qdisc_tree_decrease_qlen(cl->qdisc, len);
+	qdisc_tree_reduce_backlog(cl->qdisc, len, backlog);
 }
 
 static const struct nla_policy drr_policy[TCA_DRR_MAX + 1] = {
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 109b232..3c6a47d 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -662,6 +662,7 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt)
 	struct fq_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_FQ_MAX + 1];
 	int err, drop_count = 0;
+	unsigned drop_len = 0;
 	u32 fq_log;
 
 	if (!opt)
@@ -736,10 +737,11 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt)
 
 		if (!skb)
 			break;
+		drop_len += qdisc_pkt_len(skb);
 		kfree_skb(skb);
 		drop_count++;
 	}
-	qdisc_tree_decrease_qlen(sch, drop_count);
+	qdisc_tree_reduce_backlog(sch, drop_count, drop_len);
 
 	sch_tree_unlock(sch);
 	return err;
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 4c834e9..d3fc8f9 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -175,7 +175,7 @@ static unsigned int fq_codel_qdisc_drop(struct Qdisc *sch)
 static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 {
 	struct fq_codel_sched_data *q = qdisc_priv(sch);
-	unsigned int idx;
+	unsigned int idx, prev_backlog;
 	struct fq_codel_flow *flow;
 	int uninitialized_var(ret);
 
@@ -203,6 +203,7 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	if (++sch->q.qlen <= sch->limit)
 		return NET_XMIT_SUCCESS;
 
+	prev_backlog = sch->qstats.backlog;
 	q->drop_overlimit++;
 	/* Return Congestion Notification only if we dropped a packet
 	 * from this flow.
@@ -211,7 +212,7 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		return NET_XMIT_CN;
 
 	/* As we dropped a packet, better let upper stack know this */
-	qdisc_tree_decrease_qlen(sch, 1);
+	qdisc_tree_reduce_backlog(sch, 1, prev_backlog - sch->qstats.backlog);
 	return NET_XMIT_SUCCESS;
 }
 
@@ -241,6 +242,7 @@ static struct sk_buff *fq_codel_dequeue(struct Qdisc *sch)
 	struct fq_codel_flow *flow;
 	struct list_head *head;
 	u32 prev_drop_count, prev_ecn_mark;
+	unsigned int prev_backlog;
 
 begin:
 	head = &q->new_flows;
@@ -259,6 +261,7 @@ begin:
 
 	prev_drop_count = q->cstats.drop_count;
 	prev_ecn_mark = q->cstats.ecn_mark;
+	prev_backlog = sch->qstats.backlog;
 
 	skb = codel_dequeue(sch, &q->cparams, &flow->cvars, &q->cstats,
 			    dequeue);
@@ -276,12 +279,14 @@ begin:
 	}
 	qdisc_bstats_update(sch, skb);
 	flow->deficit -= qdisc_pkt_len(skb);
-	/* We cant call qdisc_tree_decrease_qlen() if our qlen is 0,
+	/* We cant call qdisc_tree_reduce_backlog() if our qlen is 0,
 	 * or HTB crashes. Defer it for next round.
 	 */
 	if (q->cstats.drop_count && sch->q.qlen) {
-		qdisc_tree_decrease_qlen(sch, q->cstats.drop_count);
+		qdisc_tree_reduce_backlog(sch, q->cstats.drop_count,
+					  q->cstats.drop_len);
 		q->cstats.drop_count = 0;
+		q->cstats.drop_len = 0;
 	}
 	return skb;
 }
@@ -372,11 +377,13 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt)
 	while (sch->q.qlen > sch->limit) {
 		struct sk_buff *skb = fq_codel_dequeue(sch);
 
+		q->cstats.drop_len += qdisc_pkt_len(skb);
 		kfree_skb(skb);
 		q->cstats.drop_count++;
 	}
-	qdisc_tree_decrease_qlen(sch, q->cstats.drop_count);
+	qdisc_tree_reduce_backlog(sch, q->cstats.drop_count, q->cstats.drop_len);
 	q->cstats.drop_count = 0;
+	q->cstats.drop_len = 0;
 
 	sch_tree_unlock(sch);
 	return 0;
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 089f3b6..d783d7c 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -895,9 +895,10 @@ static void
 hfsc_purge_queue(struct Qdisc *sch, struct hfsc_class *cl)
 {
 	unsigned int len = cl->qdisc->q.qlen;
+	unsigned int backlog = cl->qdisc->qstats.backlog;
 
 	qdisc_reset(cl->qdisc);
-	qdisc_tree_decrease_qlen(cl->qdisc, len);
+	qdisc_tree_reduce_backlog(cl->qdisc, len, backlog);
 }
 
 static void
diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c
index 86b04e3..13d6f83 100644
--- a/net/sched/sch_hhf.c
+++ b/net/sched/sch_hhf.c
@@ -382,6 +382,7 @@ static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	struct hhf_sched_data *q = qdisc_priv(sch);
 	enum wdrr_bucket_idx idx;
 	struct wdrr_bucket *bucket;
+	unsigned int prev_backlog;
 
 	idx = hhf_classify(skb, sch);
 
@@ -409,6 +410,7 @@ static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	if (++sch->q.qlen <= sch->limit)
 		return NET_XMIT_SUCCESS;
 
+	prev_backlog = sch->qstats.backlog;
 	q->drop_overlimit++;
 	/* Return Congestion Notification only if we dropped a packet from this
 	 * bucket.
@@ -417,7 +419,7 @@ static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		return NET_XMIT_CN;
 
 	/* As we dropped a packet, better let upper stack know this. */
-	qdisc_tree_decrease_qlen(sch, 1);
+	qdisc_tree_reduce_backlog(sch, 1, prev_backlog - sch->qstats.backlog);
 	return NET_XMIT_SUCCESS;
 }
 
@@ -527,7 +529,7 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct hhf_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_HHF_MAX + 1];
-	unsigned int qlen;
+	unsigned int qlen, prev_backlog;
 	int err;
 	u64 non_hh_quantum;
 	u32 new_quantum = q->quantum;
@@ -577,12 +579,14 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt)
 	}
 
 	qlen = sch->q.qlen;
+	prev_backlog = sch->qstats.backlog;
 	while (sch->q.qlen > sch->limit) {
 		struct sk_buff *skb = hhf_dequeue(sch);
 
 		kfree_skb(skb);
 	}
-	qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen);
+	qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen,
+				  prev_backlog - sch->qstats.backlog);
 
 	sch_tree_unlock(sch);
 	return 0;
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 0efbcf3..846a7f9 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1265,7 +1265,6 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg)
 {
 	struct htb_sched *q = qdisc_priv(sch);
 	struct htb_class *cl = (struct htb_class *)arg;
-	unsigned int qlen;
 	struct Qdisc *new_q = NULL;
 	int last_child = 0;
 
@@ -1285,9 +1284,11 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg)
 	sch_tree_lock(sch);
 
 	if (!cl->level) {
-		qlen = cl->un.leaf.q->q.qlen;
+		unsigned int qlen = cl->un.leaf.q->q.qlen;
+		unsigned int backlog = cl->un.leaf.q->qstats.backlog;
+
 		qdisc_reset(cl->un.leaf.q);
-		qdisc_tree_decrease_qlen(cl->un.leaf.q, qlen);
+		qdisc_tree_reduce_backlog(cl->un.leaf.q, qlen, backlog);
 	}
 
 	/* delete from hash and active; remainder in destroy_class */
@@ -1421,10 +1422,11 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 		sch_tree_lock(sch);
 		if (parent && !parent->level) {
 			unsigned int qlen = parent->un.leaf.q->q.qlen;
+			unsigned int backlog = parent->un.leaf.q->qstats.backlog;
 
 			/* turn parent into inner node */
 			qdisc_reset(parent->un.leaf.q);
-			qdisc_tree_decrease_qlen(parent->un.leaf.q, qlen);
+			qdisc_tree_reduce_backlog(parent->un.leaf.q, qlen, backlog);
 			qdisc_destroy(parent->un.leaf.q);
 			if (parent->prio_activity)
 				htb_deactivate(q, parent);
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index a0103a1..bcdd54b 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -218,7 +218,8 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt)
 		if (q->queues[i] != &noop_qdisc) {
 			struct Qdisc *child = q->queues[i];
 			q->queues[i] = &noop_qdisc;
-			qdisc_tree_decrease_qlen(child, child->q.qlen);
+			qdisc_tree_reduce_backlog(child, child->q.qlen,
+						  child->qstats.backlog);
 			qdisc_destroy(child);
 		}
 	}
@@ -238,8 +239,9 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt)
 				q->queues[i] = child;
 
 				if (old != &noop_qdisc) {
-					qdisc_tree_decrease_qlen(old,
-								 old->q.qlen);
+					qdisc_tree_reduce_backlog(old,
+								  old->q.qlen,
+								  old->qstats.backlog);
 					qdisc_destroy(old);
 				}
 				sch_tree_unlock(sch);
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 0a6ddaf..9640bb3 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -598,7 +598,8 @@ deliver:
 				if (unlikely(err != NET_XMIT_SUCCESS)) {
 					if (net_xmit_drop_count(err)) {
 						qdisc_qstats_drop(sch);
-						qdisc_tree_decrease_qlen(sch, 1);
+						qdisc_tree_reduce_backlog(sch, 1,
+									  qdisc_pkt_len(skb));
 					}
 				}
 				goto tfifo_dequeue;
diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c
index b783a44..71ae3b9 100644
--- a/net/sched/sch_pie.c
+++ b/net/sched/sch_pie.c
@@ -183,7 +183,7 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct pie_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_PIE_MAX + 1];
-	unsigned int qlen;
+	unsigned int qlen, dropped = 0;
 	int err;
 
 	if (!opt)
@@ -232,10 +232,11 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt)
 	while (sch->q.qlen > sch->limit) {
 		struct sk_buff *skb = __skb_dequeue(&sch->q);
 
+		dropped += qdisc_pkt_len(skb);
 		qdisc_qstats_backlog_dec(sch, skb);
 		qdisc_drop(skb, sch);
 	}
-	qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen);
+	qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped);
 
 	sch_tree_unlock(sch);
 	return 0;
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index 1b4aaec..fee1b15 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -191,7 +191,7 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt)
 		struct Qdisc *child = q->queues[i];
 		q->queues[i] = &noop_qdisc;
 		if (child != &noop_qdisc) {
-			qdisc_tree_decrease_qlen(child, child->q.qlen);
+			qdisc_tree_reduce_backlog(child, child->q.qlen, child->qstats.backlog);
 			qdisc_destroy(child);
 		}
 	}
@@ -210,8 +210,9 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt)
 				q->queues[i] = child;
 
 				if (old != &noop_qdisc) {
-					qdisc_tree_decrease_qlen(old,
-								 old->q.qlen);
+					qdisc_tree_reduce_backlog(old,
+								  old->q.qlen,
+								  old->qstats.backlog);
 					qdisc_destroy(old);
 				}
 				sch_tree_unlock(sch);
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index b5c52ca..8d2d8d9 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -220,9 +220,10 @@ static struct qfq_class *qfq_find_class(struct Qdisc *sch, u32 classid)
 static void qfq_purge_queue(struct qfq_class *cl)
 {
 	unsigned int len = cl->qdisc->q.qlen;
+	unsigned int backlog = cl->qdisc->qstats.backlog;
 
 	qdisc_reset(cl->qdisc);
-	qdisc_tree_decrease_qlen(cl->qdisc, len);
+	qdisc_tree_reduce_backlog(cl->qdisc, len, backlog);
 }
 
 static const struct nla_policy qfq_policy[TCA_QFQ_MAX + 1] = {
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index d5abcee..8c0508c 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -210,7 +210,8 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt)
 	q->flags = ctl->flags;
 	q->limit = ctl->limit;
 	if (child) {
-		qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen);
+		qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen,
+					  q->qdisc->qstats.backlog);
 		qdisc_destroy(q->qdisc);
 		q->qdisc = child;
 	}
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index 0e74e55..c696116 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -510,7 +510,8 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt)
 
 	sch_tree_lock(sch);
 
-	qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen);
+	qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen,
+				  q->qdisc->qstats.backlog);
 	qdisc_destroy(q->qdisc);
 	q->qdisc = child;
 
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 3abab53..498f0a2 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -346,7 +346,7 @@ static int
 sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 {
 	struct sfq_sched_data *q = qdisc_priv(sch);
-	unsigned int hash;
+	unsigned int hash, dropped;
 	sfq_index x, qlen;
 	struct sfq_slot *slot;
 	int uninitialized_var(ret);
@@ -461,7 +461,7 @@ enqueue:
 		return NET_XMIT_SUCCESS;
 
 	qlen = slot->qlen;
-	sfq_drop(sch);
+	dropped = sfq_drop(sch);
 	/* Return Congestion Notification only if we dropped a packet
 	 * from this flow.
 	 */
@@ -469,7 +469,7 @@ enqueue:
 		return NET_XMIT_CN;
 
 	/* As we dropped a packet, better let upper stack know this */
-	qdisc_tree_decrease_qlen(sch, 1);
+	qdisc_tree_reduce_backlog(sch, 1, dropped);
 	return NET_XMIT_SUCCESS;
 }
 
@@ -537,6 +537,7 @@ static void sfq_rehash(struct Qdisc *sch)
 	struct sfq_slot *slot;
 	struct sk_buff_head list;
 	int dropped = 0;
+	unsigned int drop_len = 0;
 
 	__skb_queue_head_init(&list);
 
@@ -565,6 +566,7 @@ static void sfq_rehash(struct Qdisc *sch)
 			if (x >= SFQ_MAX_FLOWS) {
 drop:
 				qdisc_qstats_backlog_dec(sch, skb);
+				drop_len += qdisc_pkt_len(skb);
 				kfree_skb(skb);
 				dropped++;
 				continue;
@@ -594,7 +596,7 @@ drop:
 		}
 	}
 	sch->q.qlen -= dropped;
-	qdisc_tree_decrease_qlen(sch, dropped);
+	qdisc_tree_reduce_backlog(sch, dropped, drop_len);
 }
 
 static void sfq_perturbation(unsigned long arg)
@@ -618,7 +620,7 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt)
 	struct sfq_sched_data *q = qdisc_priv(sch);
 	struct tc_sfq_qopt *ctl = nla_data(opt);
 	struct tc_sfq_qopt_v1 *ctl_v1 = NULL;
-	unsigned int qlen;
+	unsigned int qlen, dropped = 0;
 	struct red_parms *p = NULL;
 
 	if (opt->nla_len < nla_attr_size(sizeof(*ctl)))
@@ -667,8 +669,8 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt)
 
 	qlen = sch->q.qlen;
 	while (sch->q.qlen > q->limit)
-		sfq_drop(sch);
-	qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen);
+		dropped += sfq_drop(sch);
+	qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped);
 
 	del_timer(&q->perturb_timer);
 	if (q->perturb_period) {
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 56a1aef..c2fbde7 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -160,6 +160,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch)
 	struct tbf_sched_data *q = qdisc_priv(sch);
 	struct sk_buff *segs, *nskb;
 	netdev_features_t features = netif_skb_features(skb);
+	unsigned int len = 0, prev_len = qdisc_pkt_len(skb);
 	int ret, nb;
 
 	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
@@ -172,6 +173,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch)
 		nskb = segs->next;
 		segs->next = NULL;
 		qdisc_skb_cb(segs)->pkt_len = segs->len;
+		len += segs->len;
 		ret = qdisc_enqueue(segs, q->qdisc);
 		if (ret != NET_XMIT_SUCCESS) {
 			if (net_xmit_drop_count(ret))
@@ -183,7 +185,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch)
 	}
 	sch->q.qlen += nb;
 	if (nb > 1)
-		qdisc_tree_decrease_qlen(sch, 1 - nb);
+		qdisc_tree_reduce_backlog(sch, 1 - nb, prev_len - len);
 	consume_skb(skb);
 	return nb > 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP;
 }
@@ -399,7 +401,8 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
 
 	sch_tree_lock(sch);
 	if (child) {
-		qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen);
+		qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen,
+					  q->qdisc->qstats.backlog);
 		qdisc_destroy(q->qdisc);
 		q->qdisc = child;
 	}
-- 
2.1.0


From 3535408f784028f58efde885b40ffce911fe3a9d Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Thu, 25 Feb 2016 14:55:02 -0800
Subject: [PATCH 27/42] sch_htb: update backlog as well

[ Upstream commit 431e3a8e36a05a37126f34b41aa3a5a6456af04e ]

We saw qlen!=0 but backlog==0 on our production machine:

qdisc htb 1: dev eth0 root refcnt 2 r2q 10 default 1 direct_packets_stat 0 ver 3.17
 Sent 172680457356 bytes 222469449 pkt (dropped 0, overlimits 123575834 requeues 0)
 backlog 0b 72p requeues 0

The problem is we only count qlen for HTB qdisc but not backlog.
We need to update backlog too when we update qlen, so that we
can at least know the average packet length.

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_htb.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 846a7f9..87b02ed3 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -600,6 +600,7 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		htb_activate(q, cl);
 	}
 
+	qdisc_qstats_backlog_inc(sch, skb);
 	sch->q.qlen++;
 	return NET_XMIT_SUCCESS;
 }
@@ -889,6 +890,7 @@ static struct sk_buff *htb_dequeue(struct Qdisc *sch)
 ok:
 		qdisc_bstats_update(sch, skb);
 		qdisc_unthrottled(sch);
+		qdisc_qstats_backlog_dec(sch, skb);
 		sch->q.qlen--;
 		return skb;
 	}
@@ -955,6 +957,7 @@ static unsigned int htb_drop(struct Qdisc *sch)
 			unsigned int len;
 			if (cl->un.leaf.q->ops->drop &&
 			    (len = cl->un.leaf.q->ops->drop(cl->un.leaf.q))) {
+				sch->qstats.backlog -= len;
 				sch->q.qlen--;
 				if (!cl->un.leaf.q->q.qlen)
 					htb_deactivate(q, cl);
@@ -984,12 +987,12 @@ static void htb_reset(struct Qdisc *sch)
 			}
 			cl->prio_activity = 0;
 			cl->cmode = HTB_CAN_SEND;
-
 		}
 	}
 	qdisc_watchdog_cancel(&q->watchdog);
 	__skb_queue_purge(&q->direct_queue);
 	sch->q.qlen = 0;
+	sch->qstats.backlog = 0;
 	memset(q->hlevel, 0, sizeof(q->hlevel));
 	memset(q->row_mask, 0, sizeof(q->row_mask));
 	for (i = 0; i < TC_HTB_NUMPRIO; i++)
-- 
2.1.0


From 2150631e3b7f5d489052abfad1d7a44624f0dc4c Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Thu, 25 Feb 2016 14:55:03 -0800
Subject: [PATCH 28/42] sch_dsmark: update backlog as well

[ Upstream commit bdf17661f63a79c3cb4209b970b1cc39e34f7543 ]

Similarly, we need to update backlog too when we update qlen.

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_dsmark.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index cfddb1c..d0dff0c 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -258,6 +258,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		return err;
 	}
 
+	qdisc_qstats_backlog_inc(sch, skb);
 	sch->q.qlen++;
 
 	return NET_XMIT_SUCCESS;
@@ -280,6 +281,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch)
 		return NULL;
 
 	qdisc_bstats_update(sch, skb);
+	qdisc_qstats_backlog_dec(sch, skb);
 	sch->q.qlen--;
 
 	index = skb->tc_index & (p->indices - 1);
@@ -395,6 +397,7 @@ static void dsmark_reset(struct Qdisc *sch)
 
 	pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p);
 	qdisc_reset(p->q);
+	sch->qstats.backlog = 0;
 	sch->q.qlen = 0;
 }
 
-- 
2.1.0


From e8c3ce77de97bdc1172a9bf0de97b5a3fed2f1cf Mon Sep 17 00:00:00 2001
From: Neil Horman <nhorman@tuxdriver.com>
Date: Mon, 2 May 2016 12:20:15 -0400
Subject: [PATCH 29/42] netem: Segment GSO packets on enqueue

[ Upstream commit 6071bd1aa13ed9e41824bafad845b7b7f4df5cfd ]

This was recently reported to me, and reproduced on the latest net kernel,
when attempting to run netperf from a host that had a netem qdisc attached
to the egress interface:

[  788.073771] ---------------------[ cut here ]---------------------------
[  788.096716] WARNING: at net/core/dev.c:2253 skb_warn_bad_offload+0xcd/0xda()
[  788.129521] bnx2: caps=(0x00000001801949b3, 0x0000000000000000) len=2962
data_len=0 gso_size=1448 gso_type=1 ip_summed=3
[  788.182150] Modules linked in: sch_netem kvm_amd kvm crc32_pclmul ipmi_ssif
ghash_clmulni_intel sp5100_tco amd64_edac_mod aesni_intel lrw gf128mul
glue_helper ablk_helper edac_mce_amd cryptd pcspkr sg edac_core hpilo ipmi_si
i2c_piix4 k10temp fam15h_power hpwdt ipmi_msghandler shpchp acpi_power_meter
pcc_cpufreq nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c
sd_mod crc_t10dif crct10dif_generic mgag200 syscopyarea sysfillrect sysimgblt
i2c_algo_bit drm_kms_helper ahci ata_generic pata_acpi ttm libahci
crct10dif_pclmul pata_atiixp tg3 libata crct10dif_common drm crc32c_intel ptp
serio_raw bnx2 r8169 hpsa pps_core i2c_core mii dm_mirror dm_region_hash dm_log
dm_mod
[  788.465294] CPU: 16 PID: 0 Comm: swapper/16 Tainted: G        W
------------   3.10.0-327.el7.x86_64 #1
[  788.511521] Hardware name: HP ProLiant DL385p Gen8, BIOS A28 12/17/2012
[  788.542260]  ffff880437c036b8 f7afc56532a53db9 ffff880437c03670
ffffffff816351f1
[  788.576332]  ffff880437c036a8 ffffffff8107b200 ffff880633e74200
ffff880231674000
[  788.611943]  0000000000000001 0000000000000003 0000000000000000
ffff880437c03710
[  788.647241] Call Trace:
[  788.658817]  <IRQ>  [<ffffffff816351f1>] dump_stack+0x19/0x1b
[  788.686193]  [<ffffffff8107b200>] warn_slowpath_common+0x70/0xb0
[  788.713803]  [<ffffffff8107b29c>] warn_slowpath_fmt+0x5c/0x80
[  788.741314]  [<ffffffff812f92f3>] ? ___ratelimit+0x93/0x100
[  788.767018]  [<ffffffff81637f49>] skb_warn_bad_offload+0xcd/0xda
[  788.796117]  [<ffffffff8152950c>] skb_checksum_help+0x17c/0x190
[  788.823392]  [<ffffffffa01463a1>] netem_enqueue+0x741/0x7c0 [sch_netem]
[  788.854487]  [<ffffffff8152cb58>] dev_queue_xmit+0x2a8/0x570
[  788.880870]  [<ffffffff8156ae1d>] ip_finish_output+0x53d/0x7d0
...

The problem occurs because netem is not prepared to handle GSO packets (as it
uses skb_checksum_help in its enqueue path, which cannot manipulate these
frames).

The solution I think is to simply segment the skb in a simmilar fashion to the
way we do in __dev_queue_xmit (via validate_xmit_skb), with some minor changes.
When we decide to corrupt an skb, if the frame is GSO, we segment it, corrupt
the first segment, and enqueue the remaining ones.

tested successfully by myself on the latest net kernel, to which this applies

Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
CC: Jamal Hadi Salim <jhs@mojatatu.com>
CC: "David S. Miller" <davem@davemloft.net>
CC: netem@lists.linux-foundation.org
CC: eric.dumazet@gmail.com
CC: stephen@networkplumber.org
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_netem.c | 61 +++++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 59 insertions(+), 2 deletions(-)

diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 9640bb3..4befe97 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -395,6 +395,25 @@ static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch)
 	sch->q.qlen++;
 }
 
+/* netem can't properly corrupt a megapacket (like we get from GSO), so instead
+ * when we statistically choose to corrupt one, we instead segment it, returning
+ * the first packet to be corrupted, and re-enqueue the remaining frames
+ */
+static struct sk_buff *netem_segment(struct sk_buff *skb, struct Qdisc *sch)
+{
+	struct sk_buff *segs;
+	netdev_features_t features = netif_skb_features(skb);
+
+	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+
+	if (IS_ERR_OR_NULL(segs)) {
+		qdisc_reshape_fail(skb, sch);
+		return NULL;
+	}
+	consume_skb(skb);
+	return segs;
+}
+
 /*
  * Insert one skb into qdisc.
  * Note: parent depends on return value to account for queue length.
@@ -407,7 +426,11 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	/* We don't fill cb now as skb_unshare() may invalidate it */
 	struct netem_skb_cb *cb;
 	struct sk_buff *skb2;
+	struct sk_buff *segs = NULL;
+	unsigned int len = 0, last_len, prev_len = qdisc_pkt_len(skb);
+	int nb = 0;
 	int count = 1;
+	int rc = NET_XMIT_SUCCESS;
 
 	/* Random duplication */
 	if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor))
@@ -453,10 +476,23 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	 * do it now in software before we mangle it.
 	 */
 	if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor)) {
+		if (skb_is_gso(skb)) {
+			segs = netem_segment(skb, sch);
+			if (!segs)
+				return NET_XMIT_DROP;
+		} else {
+			segs = skb;
+		}
+
+		skb = segs;
+		segs = segs->next;
+
 		if (!(skb = skb_unshare(skb, GFP_ATOMIC)) ||
 		    (skb->ip_summed == CHECKSUM_PARTIAL &&
-		     skb_checksum_help(skb)))
-			return qdisc_drop(skb, sch);
+		     skb_checksum_help(skb))) {
+			rc = qdisc_drop(skb, sch);
+			goto finish_segs;
+		}
 
 		skb->data[prandom_u32() % skb_headlen(skb)] ^=
 			1<<(prandom_u32() % 8);
@@ -516,6 +552,27 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		sch->qstats.requeues++;
 	}
 
+finish_segs:
+	if (segs) {
+		while (segs) {
+			skb2 = segs->next;
+			segs->next = NULL;
+			qdisc_skb_cb(segs)->pkt_len = segs->len;
+			last_len = segs->len;
+			rc = qdisc_enqueue(segs, sch);
+			if (rc != NET_XMIT_SUCCESS) {
+				if (net_xmit_drop_count(rc))
+					qdisc_qstats_drop(sch);
+			} else {
+				nb++;
+				len += last_len;
+			}
+			segs = skb2;
+		}
+		sch->q.qlen += nb;
+		if (nb > 1)
+			qdisc_tree_reduce_backlog(sch, 1 - nb, prev_len - len);
+	}
 	return NET_XMIT_SUCCESS;
 }
 
-- 
2.1.0


From e602f9ff2e61e0589f381ff8d4871b1f0e877569 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Tue, 3 May 2016 09:58:27 +0200
Subject: [PATCH 30/42] ipv6/ila: fix nlsize calculation for lwtunnel

[ Upstream commit 79e8dc8b80bff0bc5bbb90ca5e73044bf207c8ac ]

The handler 'ila_fill_encap_info' adds one attribute: ILA_ATTR_LOCATOR.

Fixes: 65d7ab8de582 ("net: Identifier Locator Addressing module")
CC: Tom Herbert <tom@herbertland.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ila/ila_lwt.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c
index 2ae3c4f..41f18de 100644
--- a/net/ipv6/ila/ila_lwt.c
+++ b/net/ipv6/ila/ila_lwt.c
@@ -120,8 +120,7 @@ nla_put_failure:
 
 static int ila_encap_nlsize(struct lwtunnel_state *lwtstate)
 {
-	/* No encapsulation overhead */
-	return 0;
+	return nla_total_size(sizeof(u64)); /* ILA_ATTR_LOCATOR */
 }
 
 static int ila_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b)
-- 
2.1.0


From 60efc5ac1546766518bec5b36c8cfe0ec370b52d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 3 May 2016 16:38:53 +0200
Subject: [PATCH 31/42] net: fec: only clear a queue's work bit if the queue
 was emptied
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 1c021bb717a70aaeaa4b25c91f43c2aeddd922de ]

In the receive path a queue's work bit was cleared unconditionally even
if fec_enet_rx_queue only read out a part of the available packets from
the hardware. This resulted in not reading any packets in the next napi
turn and so packets were delayed or lost.

The obvious fix is to only clear a queue's bit when the queue was
emptied.

Fixes: 4d494cdc92b3 ("net: fec: change data structure to support multiqueue")
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Lucas Stach <l.stach@pengutronix.de>
Tested-by: Fugang Duan <fugang.duan@nxp.com>
Acked-by: Fugang Duan <fugang.duan@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_main.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 41c81f6..0d6e8c1 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -1566,9 +1566,15 @@ fec_enet_rx(struct net_device *ndev, int budget)
 	struct fec_enet_private *fep = netdev_priv(ndev);
 
 	for_each_set_bit(queue_id, &fep->work_rx, FEC_ENET_MAX_RX_QS) {
-		clear_bit(queue_id, &fep->work_rx);
-		pkt_received += fec_enet_rx_queue(ndev,
+		int ret;
+
+		ret = fec_enet_rx_queue(ndev,
 					budget - pkt_received, queue_id);
+
+		if (ret < budget - pkt_received)
+			clear_bit(queue_id, &fep->work_rx);
+
+		pkt_received += ret;
 	}
 	return pkt_received;
 }
-- 
2.1.0


From 7b21280577acb9746a43b3b104fd7451bd16421f Mon Sep 17 00:00:00 2001
From: Kangjie Lu <kangjielu@gmail.com>
Date: Tue, 3 May 2016 16:35:05 -0400
Subject: [PATCH 32/42] net: fix infoleak in llc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit b8670c09f37bdf2847cc44f36511a53afc6161fd ]

The stack object “info” has a total size of 12 bytes. Its last byte
is padding which is not initialized and leaked via “put_cmsg”.

Signed-off-by: Kangjie Lu <kjlu@gatech.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/llc/af_llc.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 8dab4e5..bb8edb9 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -626,6 +626,7 @@ static void llc_cmsg_rcv(struct msghdr *msg, struct sk_buff *skb)
 	if (llc->cmsg_flags & LLC_CMSG_PKTINFO) {
 		struct llc_pktinfo info;
 
+		memset(&info, 0, sizeof(info));
 		info.lpi_ifindex = llc_sk(skb->sk)->dev->ifindex;
 		llc_pdu_decode_dsap(skb, &info.lpi_sap);
 		llc_pdu_decode_da(skb, info.lpi_mac);
-- 
2.1.0


From 843e31a9b6a1fd420ca2e811ba106bc8a2226127 Mon Sep 17 00:00:00 2001
From: Kangjie Lu <kangjielu@gmail.com>
Date: Tue, 3 May 2016 16:46:24 -0400
Subject: [PATCH 33/42] net: fix infoleak in rtnetlink
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 5f8e44741f9f216e33736ea4ec65ca9ac03036e6 ]

The stack object “map” has a total size of 32 bytes. Its last 4
bytes are padding generated by compiler. These padding bytes are
not initialized and sent out via “nla_put”.

Signed-off-by: Kangjie Lu <kjlu@gatech.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 215e613..482c371 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1176,14 +1176,16 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb,
 
 static int rtnl_fill_link_ifmap(struct sk_buff *skb, struct net_device *dev)
 {
-	struct rtnl_link_ifmap map = {
-		.mem_start   = dev->mem_start,
-		.mem_end     = dev->mem_end,
-		.base_addr   = dev->base_addr,
-		.irq         = dev->irq,
-		.dma         = dev->dma,
-		.port        = dev->if_port,
-	};
+	struct rtnl_link_ifmap map;
+
+	memset(&map, 0, sizeof(map));
+	map.mem_start   = dev->mem_start;
+	map.mem_end     = dev->mem_end;
+	map.base_addr   = dev->base_addr;
+	map.irq         = dev->irq;
+	map.dma         = dev->dma;
+	map.port        = dev->if_port;
+
 	if (nla_put(skb, IFLA_MAP, sizeof(map), &map))
 		return -EMSGSIZE;
 
-- 
2.1.0


From bc61cb96623aface2416ac2c145e907e26688365 Mon Sep 17 00:00:00 2001
From: Daniel Jurgens <danielj@mellanox.com>
Date: Wed, 4 May 2016 15:00:33 +0300
Subject: [PATCH 34/42] net/mlx4_en: Fix endianness bug in IPV6 csum
 calculation

[ Upstream commit 82d69203df634b4dfa765c94f60ce9482bcc44d6 ]

Use htons instead of unconditionally byte swapping nexthdr.  On a little
endian systems shifting the byte is correct behavior, but it results in
incorrect csums on big endian architectures.

Fixes: f8c6455bb04b ('net/mlx4_en: Extend checksum offloading by CHECKSUM COMPLETE')
Signed-off-by: Daniel Jurgens <danielj@mellanox.com>
Reviewed-by: Carol Soto <clsoto@us.ibm.com>
Tested-by: Carol Soto <clsoto@us.ibm.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_rx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 41440b2..03ef9ac 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -704,7 +704,7 @@ static int get_fixed_ipv6_csum(__wsum hw_checksum, struct sk_buff *skb,
 
 	if (ipv6h->nexthdr == IPPROTO_FRAGMENT || ipv6h->nexthdr == IPPROTO_HOPOPTS)
 		return -1;
-	hw_checksum = csum_add(hw_checksum, (__force __wsum)(ipv6h->nexthdr << 8));
+	hw_checksum = csum_add(hw_checksum, (__force __wsum)htons(ipv6h->nexthdr));
 
 	csum_pseudo_hdr = csum_partial(&ipv6h->saddr,
 				       sizeof(ipv6h->saddr) + sizeof(ipv6h->daddr), 0);
-- 
2.1.0


From e755dbe35434a332986b0acce168278f151b833a Mon Sep 17 00:00:00 2001
From: Ian Campbell <ian.campbell@docker.com>
Date: Wed, 4 May 2016 14:21:53 +0100
Subject: [PATCH 35/42] VSOCK: do not disconnect socket when peer has shutdown
 SEND only

[ Upstream commit dedc58e067d8c379a15a8a183c5db318201295bb ]

The peer may be expecting a reply having sent a request and then done a
shutdown(SHUT_WR), so tearing down the whole socket at this point seems
wrong and breaks for me with a client which does a SHUT_WR.

Looking at other socket family's stream_recvmsg callbacks doing a shutdown
here does not seem to be the norm and removing it does not seem to have
had any adverse effects that I can see.

I'm using Stefan's RFC virtio transport patches, I'm unsure of the impact
on the vmci transport.

Signed-off-by: Ian Campbell <ian.campbell@docker.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Stefan Hajnoczi <stefanha@redhat.com>
Cc: Claudio Imbrenda <imbrenda@linux.vnet.ibm.com>
Cc: Andy King <acking@vmware.com>
Cc: Dmitry Torokhov <dtor@vmware.com>
Cc: Jorgen Hansen <jhansen@vmware.com>
Cc: Adit Ranadive <aditr@vmware.com>
Cc: netdev@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/vmw_vsock/af_vsock.c | 21 +--------------------
 1 file changed, 1 insertion(+), 20 deletions(-)

diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index bbe65dc..c93e67b 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1789,27 +1789,8 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	else if (sk->sk_shutdown & RCV_SHUTDOWN)
 		err = 0;
 
-	if (copied > 0) {
-		/* We only do these additional bookkeeping/notification steps
-		 * if we actually copied something out of the queue pair
-		 * instead of just peeking ahead.
-		 */
-
-		if (!(flags & MSG_PEEK)) {
-			/* If the other side has shutdown for sending and there
-			 * is nothing more to read, then modify the socket
-			 * state.
-			 */
-			if (vsk->peer_shutdown & SEND_SHUTDOWN) {
-				if (vsock_stream_has_data(vsk) <= 0) {
-					sk->sk_state = SS_UNCONNECTED;
-					sock_set_flag(sk, SOCK_DONE);
-					sk->sk_state_change(sk);
-				}
-			}
-		}
+	if (copied > 0)
 		err = copied;
-	}
 
 out:
 	release_sock(sk);
-- 
2.1.0


From eafbce20a2496c538c90a3825712f214d40ff59a Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Wed, 4 May 2016 16:18:45 +0200
Subject: [PATCH 36/42] net: bridge: fix old ioctl unlocked net device walk

[ Upstream commit 31ca0458a61a502adb7ed192bf9716c6d05791a5 ]

get_bridge_ifindices() is used from the old "deviceless" bridge ioctl
calls which aren't called with rtnl held. The comment above says that it is
called with rtnl but that is not really the case.
Here's a sample output from a test ASSERT_RTNL() which I put in
get_bridge_ifindices and executed "brctl show":
[  957.422726] RTNL: assertion failed at net/bridge//br_ioctl.c (30)
[  957.422925] CPU: 0 PID: 1862 Comm: brctl Tainted: G        W  O
4.6.0-rc4+ #157
[  957.423009] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996),
BIOS 1.8.1-20150318_183358- 04/01/2014
[  957.423009]  0000000000000000 ffff880058adfdf0 ffffffff8138dec5
0000000000000400
[  957.423009]  ffffffff81ce8380 ffff880058adfe58 ffffffffa05ead32
0000000000000001
[  957.423009]  00007ffec1a444b0 0000000000000400 ffff880053c19130
0000000000008940
[  957.423009] Call Trace:
[  957.423009]  [<ffffffff8138dec5>] dump_stack+0x85/0xc0
[  957.423009]  [<ffffffffa05ead32>]
br_ioctl_deviceless_stub+0x212/0x2e0 [bridge]
[  957.423009]  [<ffffffff81515beb>] sock_ioctl+0x22b/0x290
[  957.423009]  [<ffffffff8126ba75>] do_vfs_ioctl+0x95/0x700
[  957.423009]  [<ffffffff8126c159>] SyS_ioctl+0x79/0x90
[  957.423009]  [<ffffffff8163a4c0>] entry_SYSCALL_64_fastpath+0x23/0xc1

Since it only reads bridge ifindices, we can use rcu to safely walk the net
device list. Also remove the wrong rtnl comment above.

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_ioctl.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c
index 263b4de..60a3dbf 100644
--- a/net/bridge/br_ioctl.c
+++ b/net/bridge/br_ioctl.c
@@ -21,18 +21,19 @@
 #include <asm/uaccess.h>
 #include "br_private.h"
 
-/* called with RTNL */
 static int get_bridge_ifindices(struct net *net, int *indices, int num)
 {
 	struct net_device *dev;
 	int i = 0;
 
-	for_each_netdev(net, dev) {
+	rcu_read_lock();
+	for_each_netdev_rcu(net, dev) {
 		if (i >= num)
 			break;
 		if (dev->priv_flags & IFF_EBRIDGE)
 			indices[i++] = dev->ifindex;
 	}
+	rcu_read_unlock();
 
 	return i;
 }
-- 
2.1.0


From cb7b0c1529bfd55cf0600b298c5467db42a67dba Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Linus=20L=C3=BCssing?= <linus.luessing@c0d3.blue>
Date: Wed, 4 May 2016 17:25:02 +0200
Subject: [PATCH 37/42] bridge: fix igmp / mld query parsing
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 856ce5d083e14571d051301fe3c65b32b8cbe321 ]

With the newly introduced helper functions the skb pulling is hidden
in the checksumming function - and undone before returning to the
caller.

The IGMP and MLD query parsing functions in the bridge still
assumed that the skb is pointing to the beginning of the IGMP/MLD
message while it is now kept at the beginning of the IPv4/6 header.

If there is a querier somewhere else, then this either causes
the multicast snooping to stay disabled even though it could be
enabled. Or, if we have the querier enabled too, then this can
create unnecessary IGMP / MLD query messages on the link.

Fixing this by taking the offset between IP and IGMP/MLD header into
account, too.

Fixes: 9afd85c9e455 ("net: Export IGMP/MLD message validation code")
Reported-by: Simon Wunderlich <sw@simonwunderlich.de>
Signed-off-by: Linus Lüssing <linus.luessing@c0d3.blue>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 03661d9..ea98937 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1270,6 +1270,7 @@ static int br_ip4_multicast_query(struct net_bridge *br,
 	struct br_ip saddr;
 	unsigned long max_delay;
 	unsigned long now = jiffies;
+	unsigned int offset = skb_transport_offset(skb);
 	__be32 group;
 	int err = 0;
 
@@ -1280,14 +1281,14 @@ static int br_ip4_multicast_query(struct net_bridge *br,
 
 	group = ih->group;
 
-	if (skb->len == sizeof(*ih)) {
+	if (skb->len == offset + sizeof(*ih)) {
 		max_delay = ih->code * (HZ / IGMP_TIMER_SCALE);
 
 		if (!max_delay) {
 			max_delay = 10 * HZ;
 			group = 0;
 		}
-	} else if (skb->len >= sizeof(*ih3)) {
+	} else if (skb->len >= offset + sizeof(*ih3)) {
 		ih3 = igmpv3_query_hdr(skb);
 		if (ih3->nsrcs)
 			goto out;
@@ -1348,6 +1349,7 @@ static int br_ip6_multicast_query(struct net_bridge *br,
 	struct br_ip saddr;
 	unsigned long max_delay;
 	unsigned long now = jiffies;
+	unsigned int offset = skb_transport_offset(skb);
 	const struct in6_addr *group = NULL;
 	bool is_general_query;
 	int err = 0;
@@ -1357,8 +1359,8 @@ static int br_ip6_multicast_query(struct net_bridge *br,
 	    (port && port->state == BR_STATE_DISABLED))
 		goto out;
 
-	if (skb->len == sizeof(*mld)) {
-		if (!pskb_may_pull(skb, sizeof(*mld))) {
+	if (skb->len == offset + sizeof(*mld)) {
+		if (!pskb_may_pull(skb, offset + sizeof(*mld))) {
 			err = -EINVAL;
 			goto out;
 		}
@@ -1367,7 +1369,7 @@ static int br_ip6_multicast_query(struct net_bridge *br,
 		if (max_delay)
 			group = &mld->mld_mca;
 	} else {
-		if (!pskb_may_pull(skb, sizeof(*mld2q))) {
+		if (!pskb_may_pull(skb, offset + sizeof(*mld2q))) {
 			err = -EINVAL;
 			goto out;
 		}
-- 
2.1.0


From 2d05f9bd84da22edc77d2cdc5af7b56f2c540774 Mon Sep 17 00:00:00 2001
From: Mikko Rapeli <mikko.rapeli@iki.fi>
Date: Sun, 24 Apr 2016 17:45:00 +0200
Subject: [PATCH 38/42] uapi glibc compat: fix compile errors when glibc
 net/if.h included before linux/if.h
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 4a91cb61bb995e5571098188092e296192309c77 ]

glibc's net/if.h contains copies of definitions from linux/if.h and these
conflict and cause build failures if both files are included by application
source code. Changes in uapi headers, which fixed header file dependencies to
include linux/if.h when it was needed, e.g. commit 1ffad83d, made the
net/if.h and linux/if.h incompatibilities visible as build failures for
userspace applications like iproute2 and xtables-addons.

This patch fixes compile errors when glibc net/if.h is included before
linux/if.h:

./linux/if.h:99:21: error: redeclaration of enumerator ‘IFF_NOARP’
./linux/if.h:98:23: error: redeclaration of enumerator ‘IFF_RUNNING’
./linux/if.h:97:26: error: redeclaration of enumerator ‘IFF_NOTRAILERS’
./linux/if.h:96:27: error: redeclaration of enumerator ‘IFF_POINTOPOINT’
./linux/if.h:95:24: error: redeclaration of enumerator ‘IFF_LOOPBACK’
./linux/if.h:94:21: error: redeclaration of enumerator ‘IFF_DEBUG’
./linux/if.h:93:25: error: redeclaration of enumerator ‘IFF_BROADCAST’
./linux/if.h:92:19: error: redeclaration of enumerator ‘IFF_UP’
./linux/if.h:252:8: error: redefinition of ‘struct ifconf’
./linux/if.h:203:8: error: redefinition of ‘struct ifreq’
./linux/if.h:169:8: error: redefinition of ‘struct ifmap’
./linux/if.h:107:23: error: redeclaration of enumerator ‘IFF_DYNAMIC’
./linux/if.h:106:25: error: redeclaration of enumerator ‘IFF_AUTOMEDIA’
./linux/if.h:105:23: error: redeclaration of enumerator ‘IFF_PORTSEL’
./linux/if.h:104:25: error: redeclaration of enumerator ‘IFF_MULTICAST’
./linux/if.h:103:21: error: redeclaration of enumerator ‘IFF_SLAVE’
./linux/if.h:102:22: error: redeclaration of enumerator ‘IFF_MASTER’
./linux/if.h:101:24: error: redeclaration of enumerator ‘IFF_ALLMULTI’
./linux/if.h:100:23: error: redeclaration of enumerator ‘IFF_PROMISC’

The cases where linux/if.h is included before net/if.h need a similar fix in
the glibc side, or the order of include files can be changed userspace
code as a workaround.

This change was tested in x86 userspace on Debian unstable with
scripts/headers_compile_test.sh:

$ make headers_install && \
  cd usr/include && ../../scripts/headers_compile_test.sh -l -k
...
cc -Wall -c -nostdinc -I /usr/lib/gcc/i586-linux-gnu/5/include -I /usr/lib/gcc/i586-linux-gnu/5/include-fixed -I . -I /home/mcfrisk/src/linux-2.6/usr/headers_compile_test_include.2uX2zH -I /home/mcfrisk/src/linux-2.6/usr/headers_compile_test_include.2uX2zH/i586-linux-gnu -o /dev/null ./linux/if.h_libc_before_kernel.h
PASSED libc before kernel test: ./linux/if.h

Reported-by: Jan Engelhardt <jengelh@inai.de>
Reported-by: Josh Boyer <jwboyer@fedoraproject.org>
Reported-by: Stephen Hemminger <shemming@brocade.com>
Reported-by: Waldemar Brodkorb <mail@waldemar-brodkorb.de>
Cc: Gabriel Laskar <gabriel@lse.epita.fr>
Signed-off-by: Mikko Rapeli <mikko.rapeli@iki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if.h          | 28 +++++++++++++++++++++++++
 include/uapi/linux/libc-compat.h | 44 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 72 insertions(+)

diff --git a/include/uapi/linux/if.h b/include/uapi/linux/if.h
index 9cf2394..752f5dc 100644
--- a/include/uapi/linux/if.h
+++ b/include/uapi/linux/if.h
@@ -19,14 +19,20 @@
 #ifndef _LINUX_IF_H
 #define _LINUX_IF_H
 
+#include <linux/libc-compat.h>          /* for compatibility with glibc */
 #include <linux/types.h>		/* for "__kernel_caddr_t" et al	*/
 #include <linux/socket.h>		/* for "struct sockaddr" et al	*/
 #include <linux/compiler.h>		/* for "__user" et al           */
 
+#if __UAPI_DEF_IF_IFNAMSIZ
 #define	IFNAMSIZ	16
+#endif /* __UAPI_DEF_IF_IFNAMSIZ */
 #define	IFALIASZ	256
 #include <linux/hdlc/ioctl.h>
 
+/* For glibc compatibility. An empty enum does not compile. */
+#if __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO != 0 && \
+    __UAPI_DEF_IF_NET_DEVICE_FLAGS != 0
 /**
  * enum net_device_flags - &struct net_device flags
  *
@@ -68,6 +74,8 @@
  * @IFF_ECHO: echo sent packets. Volatile.
  */
 enum net_device_flags {
+/* for compatibility with glibc net/if.h */
+#if __UAPI_DEF_IF_NET_DEVICE_FLAGS
 	IFF_UP				= 1<<0,  /* sysfs */
 	IFF_BROADCAST			= 1<<1,  /* volatile */
 	IFF_DEBUG			= 1<<2,  /* sysfs */
@@ -84,11 +92,17 @@ enum net_device_flags {
 	IFF_PORTSEL			= 1<<13, /* sysfs */
 	IFF_AUTOMEDIA			= 1<<14, /* sysfs */
 	IFF_DYNAMIC			= 1<<15, /* sysfs */
+#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS */
+#if __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO
 	IFF_LOWER_UP			= 1<<16, /* volatile */
 	IFF_DORMANT			= 1<<17, /* volatile */
 	IFF_ECHO			= 1<<18, /* volatile */
+#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO */
 };
+#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO != 0 && __UAPI_DEF_IF_NET_DEVICE_FLAGS != 0 */
 
+/* for compatibility with glibc net/if.h */
+#if __UAPI_DEF_IF_NET_DEVICE_FLAGS
 #define IFF_UP				IFF_UP
 #define IFF_BROADCAST			IFF_BROADCAST
 #define IFF_DEBUG			IFF_DEBUG
@@ -105,9 +119,13 @@ enum net_device_flags {
 #define IFF_PORTSEL			IFF_PORTSEL
 #define IFF_AUTOMEDIA			IFF_AUTOMEDIA
 #define IFF_DYNAMIC			IFF_DYNAMIC
+#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS */
+
+#if __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO
 #define IFF_LOWER_UP			IFF_LOWER_UP
 #define IFF_DORMANT			IFF_DORMANT
 #define IFF_ECHO			IFF_ECHO
+#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO */
 
 #define IFF_VOLATILE	(IFF_LOOPBACK|IFF_POINTOPOINT|IFF_BROADCAST|IFF_ECHO|\
 		IFF_MASTER|IFF_SLAVE|IFF_RUNNING|IFF_LOWER_UP|IFF_DORMANT)
@@ -166,6 +184,8 @@ enum {
  *	being very small might be worth keeping for clean configuration.
  */
 
+/* for compatibility with glibc net/if.h */
+#if __UAPI_DEF_IF_IFMAP
 struct ifmap {
 	unsigned long mem_start;
 	unsigned long mem_end;
@@ -175,6 +195,7 @@ struct ifmap {
 	unsigned char port;
 	/* 3 bytes spare */
 };
+#endif /* __UAPI_DEF_IF_IFMAP */
 
 struct if_settings {
 	unsigned int type;	/* Type of physical device or protocol */
@@ -200,6 +221,8 @@ struct if_settings {
  * remainder may be interface specific.
  */
 
+/* for compatibility with glibc net/if.h */
+#if __UAPI_DEF_IF_IFREQ
 struct ifreq {
 #define IFHWADDRLEN	6
 	union
@@ -223,6 +246,7 @@ struct ifreq {
 		struct	if_settings ifru_settings;
 	} ifr_ifru;
 };
+#endif /* __UAPI_DEF_IF_IFREQ */
 
 #define ifr_name	ifr_ifrn.ifrn_name	/* interface name 	*/
 #define ifr_hwaddr	ifr_ifru.ifru_hwaddr	/* MAC address 		*/
@@ -249,6 +273,8 @@ struct ifreq {
  * must know all networks accessible).
  */
 
+/* for compatibility with glibc net/if.h */
+#if __UAPI_DEF_IF_IFCONF
 struct ifconf  {
 	int	ifc_len;			/* size of buffer	*/
 	union {
@@ -256,6 +282,8 @@ struct ifconf  {
 		struct ifreq __user *ifcu_req;
 	} ifc_ifcu;
 };
+#endif /* __UAPI_DEF_IF_IFCONF */
+
 #define	ifc_buf	ifc_ifcu.ifcu_buf		/* buffer address	*/
 #define	ifc_req	ifc_ifcu.ifcu_req		/* array of structures	*/
 
diff --git a/include/uapi/linux/libc-compat.h b/include/uapi/linux/libc-compat.h
index 7d024ce..d5e38c7 100644
--- a/include/uapi/linux/libc-compat.h
+++ b/include/uapi/linux/libc-compat.h
@@ -51,6 +51,40 @@
 /* We have included glibc headers... */
 #if defined(__GLIBC__)
 
+/* Coordinate with glibc net/if.h header. */
+#if defined(_NET_IF_H)
+
+/* GLIBC headers included first so don't define anything
+ * that would already be defined. */
+
+#define __UAPI_DEF_IF_IFCONF 0
+#define __UAPI_DEF_IF_IFMAP 0
+#define __UAPI_DEF_IF_IFNAMSIZ 0
+#define __UAPI_DEF_IF_IFREQ 0
+/* Everything up to IFF_DYNAMIC, matches net/if.h until glibc 2.23 */
+#define __UAPI_DEF_IF_NET_DEVICE_FLAGS 0
+/* For the future if glibc adds IFF_LOWER_UP, IFF_DORMANT and IFF_ECHO */
+#ifndef __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO
+#define __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO 1
+#endif /* __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO */
+
+#else /* _NET_IF_H */
+
+/* Linux headers included first, and we must define everything
+ * we need. The expectation is that glibc will check the
+ * __UAPI_DEF_* defines and adjust appropriately. */
+
+#define __UAPI_DEF_IF_IFCONF 1
+#define __UAPI_DEF_IF_IFMAP 1
+#define __UAPI_DEF_IF_IFNAMSIZ 1
+#define __UAPI_DEF_IF_IFREQ 1
+/* Everything up to IFF_DYNAMIC, matches net/if.h until glibc 2.23 */
+#define __UAPI_DEF_IF_NET_DEVICE_FLAGS 1
+/* For the future if glibc adds IFF_LOWER_UP, IFF_DORMANT and IFF_ECHO */
+#define __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO 1
+
+#endif /* _NET_IF_H */
+
 /* Coordinate with glibc netinet/in.h header. */
 #if defined(_NETINET_IN_H)
 
@@ -117,6 +151,16 @@
  * that we need. */
 #else /* !defined(__GLIBC__) */
 
+/* Definitions for if.h */
+#define __UAPI_DEF_IF_IFCONF 1
+#define __UAPI_DEF_IF_IFMAP 1
+#define __UAPI_DEF_IF_IFNAMSIZ 1
+#define __UAPI_DEF_IF_IFREQ 1
+/* Everything up to IFF_DYNAMIC, matches net/if.h until glibc 2.23 */
+#define __UAPI_DEF_IF_NET_DEVICE_FLAGS 1
+/* For the future if glibc adds IFF_LOWER_UP, IFF_DORMANT and IFF_ECHO */
+#define __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO 1
+
 /* Definitions for in.h */
 #define __UAPI_DEF_IN_ADDR		1
 #define __UAPI_DEF_IN_IPPROTO		1
-- 
2.1.0


From 9b7366964e6112d0d05d7d34cb489bd709ab4319 Mon Sep 17 00:00:00 2001
From: Kangjie Lu <kangjielu@gmail.com>
Date: Sun, 8 May 2016 12:10:14 -0400
Subject: [PATCH 39/42] net: fix a kernel infoleak in x25 module

[ Upstream commit 79e48650320e6fba48369fccf13fd045315b19b8 ]

Stack object "dte_facilities" is allocated in x25_rx_call_request(),
which is supposed to be initialized in x25_negotiate_facilities.
However, 5 fields (8 bytes in total) are not initialized. This
object is then copied to userland via copy_to_user, thus infoleak
occurs.

Signed-off-by: Kangjie Lu <kjlu@gatech.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/x25/x25_facilities.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/x25/x25_facilities.c b/net/x25/x25_facilities.c
index 7ecd04c..997ff7b 100644
--- a/net/x25/x25_facilities.c
+++ b/net/x25/x25_facilities.c
@@ -277,6 +277,7 @@ int x25_negotiate_facilities(struct sk_buff *skb, struct sock *sk,
 
 	memset(&theirs, 0, sizeof(theirs));
 	memcpy(new, ours, sizeof(*new));
+	memset(dte, 0, sizeof(*dte));
 
 	len = x25_parse_facilities(skb, &theirs, dte, &x25->vc_facil_mask);
 	if (len < 0)
-- 
2.1.0


From 112399230ed373de5ccd75a68765875b2c784b17 Mon Sep 17 00:00:00 2001
From: "xypron.glpk@gmx.de" <xypron.glpk@gmx.de>
Date: Mon, 9 May 2016 00:46:18 +0200
Subject: [PATCH 40/42] net: thunderx: avoid exposing kernel stack

[ Upstream commit 161de2caf68c549c266e571ffba8e2163886fb10 ]

Reserved fields should be set to zero to avoid exposing
bits from the kernel stack.

Signed-off-by: Heinrich Schuchardt <xypron.glpk@gmx.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/thunder/nicvf_queues.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index 767347b..f50bdbf 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -519,6 +519,7 @@ static void nicvf_rcv_queue_config(struct nicvf *nic, struct queue_set *qs,
 		nicvf_config_vlan_stripping(nic, nic->netdev->features);
 
 	/* Enable Receive queue */
+	memset(&rq_cfg, 0, sizeof(struct rq_cfg));
 	rq_cfg.ena = 1;
 	rq_cfg.tcp_ena = 0;
 	nicvf_queue_reg_write(nic, NIC_QSET_RQ_0_7_CFG, qidx, *(u64 *)&rq_cfg);
@@ -551,6 +552,7 @@ void nicvf_cmp_queue_config(struct nicvf *nic, struct queue_set *qs,
 			      qidx, (u64)(cq->dmem.phys_base));
 
 	/* Enable Completion queue */
+	memset(&cq_cfg, 0, sizeof(struct cq_cfg));
 	cq_cfg.ena = 1;
 	cq_cfg.reset = 0;
 	cq_cfg.caching = 0;
@@ -599,6 +601,7 @@ static void nicvf_snd_queue_config(struct nicvf *nic, struct queue_set *qs,
 			      qidx, (u64)(sq->dmem.phys_base));
 
 	/* Enable send queue  & set queue size */
+	memset(&sq_cfg, 0, sizeof(struct sq_cfg));
 	sq_cfg.ena = 1;
 	sq_cfg.reset = 0;
 	sq_cfg.ldwb = 0;
@@ -635,6 +638,7 @@ static void nicvf_rbdr_config(struct nicvf *nic, struct queue_set *qs,
 
 	/* Enable RBDR  & set queue size */
 	/* Buffer size should be in multiples of 128 bytes */
+	memset(&rbdr_cfg, 0, sizeof(struct rbdr_cfg));
 	rbdr_cfg.ena = 1;
 	rbdr_cfg.reset = 0;
 	rbdr_cfg.ldwb = 0;
-- 
2.1.0


From c3f8a39a2ee0063d162ddc38f4aa585356c47321 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 9 May 2016 20:55:16 -0700
Subject: [PATCH 41/42] tcp: refresh skb timestamp at retransmit time

[ Upstream commit 10a81980fc47e64ffac26a073139813d3f697b64 ]

In the very unlikely case __tcp_retransmit_skb() can not use the cloning
done in tcp_transmit_skb(), we need to refresh skb_mstamp before doing
the copy and transmit, otherwise TCP TS val will be an exact copy of
original transmit.

Fixes: 7faee5c0d514 ("tcp: remove TCP_SKB_CB(skb)->when")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index fda379c..b6876f2 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2625,8 +2625,10 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 	 */
 	if (unlikely((NET_IP_ALIGN && ((unsigned long)skb->data & 3)) ||
 		     skb_headroom(skb) >= 0xFFFF)) {
-		struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER,
-						   GFP_ATOMIC);
+		struct sk_buff *nskb;
+
+		skb_mstamp_get(&skb->skb_mstamp);
+		nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC);
 		err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
 			     -ENOBUFS;
 	} else {
-- 
2.1.0


From dfabb5d0f0fbb6da837d793a9cabe71274164443 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 13 May 2016 18:33:41 +0200
Subject: [PATCH 42/42] net/route: enforce hoplimit max value

[ Upstream commit 626abd59e51d4d8c6367e03aae252a8aa759ac78 ]

Currently, when creating or updating a route, no check is performed
in both ipv4 and ipv6 code to the hoplimit value.

The caller can i.e. set hoplimit to 256, and when such route will
 be used, packets will be sent with hoplimit/ttl equal to 0.

This commit adds checks for the RTAX_HOPLIMIT value, in both ipv4
ipv6 route code, substituting any value greater than 255 with 255.

This is consistent with what is currently done for ADVMSS and MTU
in the ipv4 code.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_semantics.c | 2 ++
 net/ipv6/route.c         | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index d97268e..2b68418 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -975,6 +975,8 @@ fib_convert_metrics(struct fib_info *fi, const struct fib_config *cfg)
 			val = 65535 - 40;
 		if (type == RTAX_MTU && val > 65535 - 15)
 			val = 65535 - 15;
+		if (type == RTAX_HOPLIMIT && val > 255)
+			val = 255;
 		if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK))
 			return -EINVAL;
 		fi->fib_metrics[type - 1] = val;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index ed44663..18e29e2 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1737,6 +1737,8 @@ static int ip6_convert_metrics(struct mx6_config *mxc,
 		} else {
 			val = nla_get_u32(nla);
 		}
+		if (type == RTAX_HOPLIMIT && val > 255)
+			val = 255;
 		if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK))
 			goto err;
 
-- 
2.1.0

Re: [PATCHES] Networking

[Greg KH]

On Mon, May 16, 2016 at 12:35:13PM -0400, David Miller wrote:
> 
> Please queue up the following networking bug fixes for 4.1.x, 4.4.x, and 4.5.x -stable,
> respectively.

Many thanks, patches for 4.4.x and 4.5.x now applied, and a few
cherry-picked for 3.14 where needed.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 106 bytes --]


Please queue up the following networking bug fixes for 4.4, 4.5,
and 4.6 -stable, respectively.

Thanks!

[-- Attachment #2: net_44.mbox --]
[-- Type: Application/Octet-Stream, Size: 49457 bytes --]

From 9acbadfaed5b26014d5830c6bd8fe83746950222 Mon Sep 17 00:00:00 2001
From: Richard Alpe <richard.alpe@ericsson.com>
Date: Mon, 16 May 2016 11:14:54 +0200
Subject: [PATCH 01/19] tipc: check nl sock before parsing nested attributes

[ Upstream commit 45e093ae2830cd1264677d47ff9a95a71f5d9f9c ]

Make sure the socket for which the user is listing publication exists
before parsing the socket netlink attributes.

Prior to this patch a call without any socket caused a NULL pointer
dereference in tipc_nl_publ_dump().

Tested-and-reported-by: Baozeng Ding <sploving1@gmail.com>
Signed-off-by: Richard Alpe <richard.alpe@ericsson.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.cm>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/socket.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index e53003c..9b713e0 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2814,6 +2814,9 @@ int tipc_nl_publ_dump(struct sk_buff *skb, struct netlink_callback *cb)
 		if (err)
 			return err;
 
+		if (!attrs[TIPC_NLA_SOCK])
+			return -EINVAL;
+
 		err = nla_parse_nested(sock, TIPC_NLA_SOCK_MAX,
 				       attrs[TIPC_NLA_SOCK],
 				       tipc_nl_sock_policy);
-- 
2.1.0


From 39026e0f1350d1cf84d7319c0d6d3ae3c3a9c856 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Mon, 16 May 2016 17:28:16 +0800
Subject: [PATCH 02/19] netlink: Fix dump skb leak/double free

[ Upstream commit 92964c79b357efd980812c4de5c1fd2ec8bb5520 ]

When we free cb->skb after a dump, we do it after releasing the
lock.  This means that a new dump could have started in the time
being and we'll end up freeing their skb instead of ours.

This patch saves the skb and module before we unlock so we free
the right memory.

Fixes: 16b304f3404f ("netlink: Eliminate kmalloc in netlink dump operation.")
Reported-by: Baozeng Ding <sploving1@gmail.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 992b35f..7a5fa0c 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2784,6 +2784,7 @@ static int netlink_dump(struct sock *sk)
 	struct netlink_callback *cb;
 	struct sk_buff *skb = NULL;
 	struct nlmsghdr *nlh;
+	struct module *module;
 	int len, err = -ENOBUFS;
 	int alloc_min_size;
 	int alloc_size;
@@ -2863,9 +2864,11 @@ static int netlink_dump(struct sock *sk)
 		cb->done(cb);
 
 	nlk->cb_running = false;
+	module = cb->module;
+	skb = cb->skb;
 	mutex_unlock(nlk->cb_mutex);
-	module_put(cb->module);
-	consume_skb(cb->skb);
+	module_put(module);
+	consume_skb(skb);
 	return 0;
 
 errout_skb:
-- 
2.1.0


From 04744c3b9d15c339ace5041e3e80afc9931256b4 Mon Sep 17 00:00:00 2001
From: Richard Alpe <richard.alpe@ericsson.com>
Date: Tue, 17 May 2016 16:57:37 +0200
Subject: [PATCH 03/19] tipc: fix nametable publication field in nl compat

[ Upstream commit 03aaaa9b941e136757b55c4cf775aab6068dfd94 ]

The publication field of the old netlink API should contain the
publication key and not the publication reference.

Fixes: 44a8ae94fd55 (tipc: convert legacy nl name table dump to nl compat)
Signed-off-by: Richard Alpe <richard.alpe@ericsson.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/netlink_compat.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 1eadc95..2ed732b 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -802,7 +802,7 @@ static int tipc_nl_compat_name_table_dump(struct tipc_nl_compat_msg *msg,
 		goto out;
 
 	tipc_tlv_sprintf(msg->rep, "%-10u %s",
-			 nla_get_u32(publ[TIPC_NLA_PUBL_REF]),
+			 nla_get_u32(publ[TIPC_NLA_PUBL_KEY]),
 			 scope_str[nla_get_u32(publ[TIPC_NLA_PUBL_SCOPE])]);
 out:
 	tipc_tlv_sprintf(msg->rep, "\n");
-- 
2.1.0


From c402663dff57ff00c89541cda5df2f9a456d7f4c Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Tue, 17 May 2016 18:58:08 +0200
Subject: [PATCH 04/19] switchdev: pass pointer to fib_info instead of copy

[ Upstream commit da4ed55165d41b1073f9a476f1c18493e9bf8c8e ]

The problem is that fib_info->nh is [0] so the struct fib_info
allocation size depends on number of nexthops. If we just copy fib_info,
we do not copy the nexthops info and driver accesses memory which is not
ours.

Given the fact that fib4 does not defer operations and therefore it does
not need copy, just pass the pointer down to drivers as it was done
before.

Fixes: 850d0cbc91 ("switchdev: remove pointers from switchdev objects")
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/rocker/rocker.c | 4 ++--
 include/net/switchdev.h              | 2 +-
 net/switchdev/switchdev.c            | 6 ++----
 3 files changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c
index 2b34622..3920c3eb 100644
--- a/drivers/net/ethernet/rocker/rocker.c
+++ b/drivers/net/ethernet/rocker/rocker.c
@@ -4475,7 +4475,7 @@ static int rocker_port_obj_add(struct net_device *dev,
 		fib4 = SWITCHDEV_OBJ_IPV4_FIB(obj);
 		err = rocker_port_fib_ipv4(rocker_port, trans,
 					   htonl(fib4->dst), fib4->dst_len,
-					   &fib4->fi, fib4->tb_id, 0);
+					   fib4->fi, fib4->tb_id, 0);
 		break;
 	case SWITCHDEV_OBJ_ID_PORT_FDB:
 		err = rocker_port_fdb_add(rocker_port, trans,
@@ -4547,7 +4547,7 @@ static int rocker_port_obj_del(struct net_device *dev,
 		fib4 = SWITCHDEV_OBJ_IPV4_FIB(obj);
 		err = rocker_port_fib_ipv4(rocker_port, NULL,
 					   htonl(fib4->dst), fib4->dst_len,
-					   &fib4->fi, fib4->tb_id,
+					   fib4->fi, fib4->tb_id,
 					   ROCKER_OP_FLAG_REMOVE);
 		break;
 	case SWITCHDEV_OBJ_ID_PORT_FDB:
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index 1d22ce9..31d0e51 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -88,7 +88,7 @@ struct switchdev_obj_ipv4_fib {
 	struct switchdev_obj obj;
 	u32 dst;
 	int dst_len;
-	struct fib_info fi;
+	struct fib_info *fi;
 	u8 tos;
 	u8 type;
 	u32 nlflags;
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index d5d7132..1b58866 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -1169,6 +1169,7 @@ int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi,
 		.obj.id = SWITCHDEV_OBJ_ID_IPV4_FIB,
 		.dst = dst,
 		.dst_len = dst_len,
+		.fi = fi,
 		.tos = tos,
 		.type = type,
 		.nlflags = nlflags,
@@ -1177,8 +1178,6 @@ int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi,
 	struct net_device *dev;
 	int err = 0;
 
-	memcpy(&ipv4_fib.fi, fi, sizeof(ipv4_fib.fi));
-
 	/* Don't offload route if using custom ip rules or if
 	 * IPv4 FIB offloading has been disabled completely.
 	 */
@@ -1222,6 +1221,7 @@ int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi,
 		.obj.id = SWITCHDEV_OBJ_ID_IPV4_FIB,
 		.dst = dst,
 		.dst_len = dst_len,
+		.fi = fi,
 		.tos = tos,
 		.type = type,
 		.nlflags = 0,
@@ -1230,8 +1230,6 @@ int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi,
 	struct net_device *dev;
 	int err = 0;
 
-	memcpy(&ipv4_fib.fi, fi, sizeof(ipv4_fib.fi));
-
 	if (!(fi->fib_flags & RTNH_F_OFFLOAD))
 		return 0;
 
-- 
2.1.0


From fd43ef15206a95f71d2d49051eab64bef1bc808f Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Thu, 19 May 2016 13:36:51 +0800
Subject: [PATCH 05/19] tuntap: correctly wake up process during uninit

[ Upstream commit addf8fc4acb1cf79492ac64966f07178793cb3d7 ]

We used to check dev->reg_state against NETREG_REGISTERED after each
time we are woke up. But after commit 9e641bdcfa4e ("net-tun:
restructure tun_do_read for better sleep/wakeup efficiency"), it uses
skb_recv_datagram() which does not check dev->reg_state. This will
result if we delete a tun/tap device after a process is blocked in the
reading. The device will wait for the reference count which was held
by that process for ever.

Fixes this by using RCV_SHUTDOWN which will be checked during
sk_recv_datagram() before trying to wake up the process during uninit.

Fixes: 9e641bdcfa4e ("net-tun: restructure tun_do_read for better
sleep/wakeup efficiency")
Cc: Eric Dumazet <edumazet@google.com>
Cc: Xi Wang <xii@google.com>
Cc: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 2d186bd..111b972 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -567,11 +567,13 @@ static void tun_detach_all(struct net_device *dev)
 	for (i = 0; i < n; i++) {
 		tfile = rtnl_dereference(tun->tfiles[i]);
 		BUG_ON(!tfile);
+		tfile->socket.sk->sk_shutdown = RCV_SHUTDOWN;
 		tfile->socket.sk->sk_data_ready(tfile->socket.sk);
 		RCU_INIT_POINTER(tfile->tun, NULL);
 		--tun->numqueues;
 	}
 	list_for_each_entry(tfile, &tun->disabled, next) {
+		tfile->socket.sk->sk_shutdown = RCV_SHUTDOWN;
 		tfile->socket.sk->sk_data_ready(tfile->socket.sk);
 		RCU_INIT_POINTER(tfile->tun, NULL);
 	}
@@ -627,6 +629,7 @@ static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filte
 			goto out;
 	}
 	tfile->queue_index = tun->numqueues;
+	tfile->socket.sk->sk_shutdown &= ~RCV_SHUTDOWN;
 	rcu_assign_pointer(tfile->tun, tun);
 	rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile);
 	tun->numqueues++;
@@ -1408,9 +1411,6 @@ static ssize_t tun_do_read(struct tun_struct *tun, struct tun_file *tfile,
 	if (!iov_iter_count(to))
 		return 0;
 
-	if (tun->dev->reg_state != NETREG_REGISTERED)
-		return -EIO;
-
 	/* Read frames from queue */
 	skb = __skb_recv_datagram(tfile->socket.sk, noblock ? MSG_DONTWAIT : 0,
 				  &peeked, &off, &err);
-- 
2.1.0


From 1c25a26609d815a9f9997fa86395f2924fe28517 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 20 May 2016 17:22:48 -0500
Subject: [PATCH 06/19] bpf: Use mount_nodev not mount_ns to mount the bpf
 filesystem

[ Upstream commit e27f4a942a0ee4b84567a3c6cfa84f273e55cbb7 ]

While reviewing the filesystems that set FS_USERNS_MOUNT I spotted the
bpf filesystem.  Looking at the code I saw a broken usage of mount_ns
with current->nsproxy->mnt_ns. As the code does not acquire a
reference to the mount namespace it can not possibly be correct to
store the mount namespace on the superblock as it does.

Replace mount_ns with mount_nodev so that each mount of the bpf
filesystem returns a distinct instance, and the code is not buggy.

In discussion with Hannes Frederic Sowa it was reported that the use
of mount_ns was an attempt to have one bpf instance per mount
namespace, in an attempt to keep resources that pin resources from
hiding.  That intent simply does not work, the vfs is not built to
allow that kind of behavior.  Which means that the bpf filesystem
really is buggy both semantically and in it's implemenation as it does
not nor can it implement the original intent.

This change is userspace visible, but my experience with similar
filesystems leads me to believe nothing will break with a model of each
mount of the bpf filesystem is distinct from all others.

Fixes: b2197755b263 ("bpf: add support for persistent maps/progs")
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/inode.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index d1a7646..00f978e 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -358,7 +358,7 @@ static int bpf_fill_super(struct super_block *sb, void *data, int silent)
 static struct dentry *bpf_mount(struct file_system_type *type, int flags,
 				const char *dev_name, void *data)
 {
-	return mount_ns(type, flags, current->nsproxy->mnt_ns, bpf_fill_super);
+	return mount_nodev(type, flags, data, bpf_fill_super);
 }
 
 static struct file_system_type bpf_fs_type = {
-- 
2.1.0


From 342781347d077683790a79acd76247b211d34e12 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Thu, 19 May 2016 15:58:33 +0200
Subject: [PATCH 07/19] udp: prevent skbs lingering in tunnel socket queues

[ Upstream commit e5aed006be918af163eb397e45aa5ea6cefd5e01 ]

In case we find a socket with encapsulation enabled we should call
the encap_recv function even if just a udp header without payload is
available. The callbacks are responsible for correctly verifying and
dropping the packets.

Also, in case the header validation fails for geneve and vxlan we
shouldn't put the skb back into the socket queue, no one will pick
them up there.  Instead we can simply discard them in the respective
encap_recv functions.

Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c | 10 +++-------
 drivers/net/vxlan.c  | 10 ++--------
 net/ipv4/udp.c       |  2 +-
 net/ipv6/udp.c       |  2 +-
 4 files changed, 7 insertions(+), 17 deletions(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 58efdec..e3f939f 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -310,15 +310,15 @@ static int geneve_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 
 	/* Need Geneve and inner Ethernet header to be present */
 	if (unlikely(!pskb_may_pull(skb, GENEVE_BASE_HLEN)))
-		goto error;
+		goto drop;
 
 	/* Return packets with reserved bits set */
 	geneveh = geneve_hdr(skb);
 	if (unlikely(geneveh->ver != GENEVE_VER))
-		goto error;
+		goto drop;
 
 	if (unlikely(geneveh->proto_type != htons(ETH_P_TEB)))
-		goto error;
+		goto drop;
 
 	opts_len = geneveh->opt_len * 4;
 	if (iptunnel_pull_header(skb, GENEVE_BASE_HLEN + opts_len,
@@ -336,10 +336,6 @@ drop:
 	/* Consume bad packet */
 	kfree_skb(skb);
 	return 0;
-
-error:
-	/* Let the UDP layer deal with the skb */
-	return 1;
 }
 
 static struct socket *geneve_create_sock(struct net *net, bool ipv6,
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 3c0df70..0496f1a 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1254,7 +1254,7 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 
 	/* Need Vxlan and inner Ethernet header to be present */
 	if (!pskb_may_pull(skb, VXLAN_HLEN))
-		goto error;
+		goto drop;
 
 	vxh = (struct vxlanhdr *)(udp_hdr(skb) + 1);
 	flags = ntohl(vxh->vx_flags);
@@ -1344,13 +1344,7 @@ drop:
 bad_flags:
 	netdev_dbg(skb->dev, "invalid vxlan flags=%#x vni=%#x\n",
 		   ntohl(vxh->vx_flags), ntohl(vxh->vx_vni));
-
-error:
-	if (tun_dst)
-		dst_release((struct dst_entry *)tun_dst);
-
-	/* Return non vxlan pkt */
-	return 1;
+	goto drop;
 }
 
 static int arp_reduce(struct net_device *dev, struct sk_buff *skb)
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 21fbb54..44e1632 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1531,7 +1531,7 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 
 		/* if we're overly short, let UDP handle it */
 		encap_rcv = ACCESS_ONCE(up->encap_rcv);
-		if (skb->len > sizeof(struct udphdr) && encap_rcv) {
+		if (encap_rcv) {
 			int ret;
 
 			/* Verify checksum before giving to encap */
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 6665e1a..275af43 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -647,7 +647,7 @@ int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 
 		/* if we're overly short, let UDP handle it */
 		encap_rcv = ACCESS_ONCE(up->encap_rcv);
-		if (skb->len > sizeof(struct udphdr) && encap_rcv) {
+		if (encap_rcv) {
 			int ret;
 
 			/* Verify checksum before giving to encap */
-- 
2.1.0


From 7e37bc560d7ef0ab613faf3f36747e0768919eda Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Thu, 19 May 2016 17:26:29 +0200
Subject: [PATCH 08/19] uapi glibc compat: fix compilation when !__USE_MISC in
 glibc

[ Upstream commit f0a3fdca794d1e68ae284ef4caefe681f7c18e89 ]

These structures are defined only if __USE_MISC is set in glibc net/if.h
headers, ie when _BSD_SOURCE or _SVID_SOURCE are defined.

CC: Jan Engelhardt <jengelh@inai.de>
CC: Josh Boyer <jwboyer@fedoraproject.org>
CC: Stephen Hemminger <shemming@brocade.com>
CC: Waldemar Brodkorb <mail@waldemar-brodkorb.de>
CC: Gabriel Laskar <gabriel@lse.epita.fr>
CC: Mikko Rapeli <mikko.rapeli@iki.fi>
Fixes: 4a91cb61bb99 ("uapi glibc compat: fix compile errors when glibc net/if.h included before linux/if.h")
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/libc-compat.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/uapi/linux/libc-compat.h b/include/uapi/linux/libc-compat.h
index d5e38c7..e4f048e 100644
--- a/include/uapi/linux/libc-compat.h
+++ b/include/uapi/linux/libc-compat.h
@@ -52,7 +52,7 @@
 #if defined(__GLIBC__)
 
 /* Coordinate with glibc net/if.h header. */
-#if defined(_NET_IF_H)
+#if defined(_NET_IF_H) && defined(__USE_MISC)
 
 /* GLIBC headers included first so don't define anything
  * that would already be defined. */
-- 
2.1.0


From e0466b3a229585026d02cc800de500a01d2d40fc Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Sun, 22 May 2016 23:16:18 +0200
Subject: [PATCH 09/19] bpf, inode: disallow userns mounts

[ Upstream commit 612bacad78ba6d0a91166fc4487af114bac172a8 ]

Follow-up to commit e27f4a942a0e ("bpf: Use mount_nodev not mount_ns
to mount the bpf filesystem"), which removes the FS_USERNS_MOUNT flag.

The original idea was to have a per mountns instance instead of a
single global fs instance, but that didn't work out and we had to
switch to mount_nodev() model. The intent of that middle ground was
that we avoid users who don't play nice to create endless instances
of bpf fs which are difficult to control and discover from an admin
point of view, but at the same time it would have allowed us to be
more flexible with regard to namespaces.

Therefore, since we now did the switch to mount_nodev() as a fix
where individual instances are created, we also need to remove userns
mount flag along with it to avoid running into mentioned situation.
I don't expect any breakage at this early point in time with removing
the flag and we can revisit this later should the requirement for
this come up with future users. This and commit e27f4a942a0e have
been split to facilitate tracking should any of them run into the
unlikely case of causing a regression.

Fixes: b2197755b263 ("bpf: add support for persistent maps/progs")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/inode.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 00f978e..cb85d22 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -366,7 +366,6 @@ static struct file_system_type bpf_fs_type = {
 	.name		= "bpf",
 	.mount		= bpf_mount,
 	.kill_sb	= kill_litter_super,
-	.fs_flags	= FS_USERNS_MOUNT,
 };
 
 MODULE_ALIAS_FS("bpf");
-- 
2.1.0


From d484469c293e66bd93e0e622678d74160cc743d9 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Tue, 24 May 2016 18:53:36 +0100
Subject: [PATCH 10/19] sfc: on MC reset, clear PIO buffer linkage in TXQs

[ Upstream commit c0795bf64cba4d1b796fdc5b74b33772841ed1bb ]

Otherwise, if we fail to allocate new PIO buffers, our TXQs will try to
use the old ones, which aren't there any more.

Fixes: 183233bec810 "sfc: Allocate and link PIO buffers; map them with write-combining"
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/ef10.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index e6a084a..cbe9a33 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -619,6 +619,17 @@ fail:
 	return rc;
 }
 
+static void efx_ef10_forget_old_piobufs(struct efx_nic *efx)
+{
+	struct efx_channel *channel;
+	struct efx_tx_queue *tx_queue;
+
+	/* All our existing PIO buffers went away */
+	efx_for_each_channel(channel, efx)
+		efx_for_each_channel_tx_queue(tx_queue, channel)
+			tx_queue->piobuf = NULL;
+}
+
 #else /* !EFX_USE_PIO */
 
 static int efx_ef10_alloc_piobufs(struct efx_nic *efx, unsigned int n)
@@ -635,6 +646,10 @@ static void efx_ef10_free_piobufs(struct efx_nic *efx)
 {
 }
 
+static void efx_ef10_forget_old_piobufs(struct efx_nic *efx)
+{
+}
+
 #endif /* EFX_USE_PIO */
 
 static void efx_ef10_remove(struct efx_nic *efx)
@@ -1018,6 +1033,7 @@ static void efx_ef10_reset_mc_allocations(struct efx_nic *efx)
 	nic_data->must_realloc_vis = true;
 	nic_data->must_restore_filters = true;
 	nic_data->must_restore_piobufs = true;
+	efx_ef10_forget_old_piobufs(efx);
 	nic_data->rx_rss_context = EFX_EF10_RSS_CONTEXT_INVALID;
 
 	/* Driver-created vswitches and vports must be re-created */
-- 
2.1.0


From d74a6dabde95036fbef6740ff1f57aaf60090279 Mon Sep 17 00:00:00 2001
From: Ivan Vecera <ivecera@redhat.com>
Date: Wed, 25 May 2016 21:21:52 +0200
Subject: [PATCH 11/19] team: don't call netdev_change_features under
 team->lock

[ Upstream commit f6988cb63a4e698d8a62a1d085d263d1fcc351ea ]

The team_device_event() notifier calls team_compute_features() to fix
vlan_features under team->lock to protect team->port_list. The problem is
that subsequent __team_compute_features() calls netdev_change_features()
to propagate vlan_features to upper vlan devices while team->lock is still
taken. This can lead to deadlock when NETIF_F_LRO is modified on lower
devices or team device itself.

Example:
The team0 as active backup with eth0 and eth1 NICs. Both eth0 & eth1 are
LRO capable and LRO is enabled. Thus LRO is also enabled on team0.

The command 'ethtool -K team0 lro off' now hangs due to this deadlock:

dev_ethtool()
-> ethtool_set_features()
 -> __netdev_update_features(team)
  -> netdev_sync_lower_features()
   -> netdev_update_features(lower_1)
    -> __netdev_update_features(lower_1)
    -> netdev_features_change(lower_1)
     -> call_netdevice_notifiers(...)
      -> team_device_event(lower_1)
       -> team_compute_features(team) [TAKES team->lock]
        -> netdev_change_features(team)
         -> __netdev_update_features(team)
          -> netdev_sync_lower_features()
           -> netdev_update_features(lower_2)
            -> __netdev_update_features(lower_2)
            -> netdev_features_change(lower_2)
             -> call_netdevice_notifiers(...)
              -> team_device_event(lower_2)
               -> team_compute_features(team) [DEADLOCK]

The bug is present in team from the beginning but it appeared after the commit
fd867d5 (net/core: generic support for disabling netdev features down stack)
that adds synchronization of features with lower devices.

Fixes: fd867d5 (net/core: generic support for disabling netdev features down stack)
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 59fefca..a5f392a 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -969,7 +969,7 @@ static void team_port_disable(struct team *team,
 			    NETIF_F_FRAGLIST | NETIF_F_ALL_TSO | \
 			    NETIF_F_HIGHDMA | NETIF_F_LRO)
 
-static void __team_compute_features(struct team *team)
+static void ___team_compute_features(struct team *team)
 {
 	struct team_port *port;
 	u32 vlan_features = TEAM_VLAN_FEATURES & NETIF_F_ALL_FOR_ALL;
@@ -993,15 +993,20 @@ static void __team_compute_features(struct team *team)
 	team->dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
 	if (dst_release_flag == (IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM))
 		team->dev->priv_flags |= IFF_XMIT_DST_RELEASE;
+}
 
+static void __team_compute_features(struct team *team)
+{
+	___team_compute_features(team);
 	netdev_change_features(team->dev);
 }
 
 static void team_compute_features(struct team *team)
 {
 	mutex_lock(&team->lock);
-	__team_compute_features(team);
+	___team_compute_features(team);
 	mutex_unlock(&team->lock);
+	netdev_change_features(team->dev);
 }
 
 static int team_port_enter(struct team *team, struct team_port *port)
-- 
2.1.0


From df688a5c753ec464f63eea46da8cd34866974844 Mon Sep 17 00:00:00 2001
From: Chen Haiquan <oc@yunify.com>
Date: Fri, 27 May 2016 10:49:11 +0800
Subject: [PATCH 12/19] vxlan: Accept user specified MTU value when create new
 vxlan link

[ Upstream commit ce577668a426c6a9e2470a09dcd07fbd6e45272a ]

When create a new vxlan link, example:
  ip link add vtap mtu 1440 type vxlan vni 1 dev eth0

The argument "mtu" has no effect, because it is not set to conf->mtu. The
default value is used in vxlan_dev_configure function.

This problem was introduced by commit 0dfbdf4102b9 (vxlan: Factor out device
configuration).

Fixes: 0dfbdf4102b9 (vxlan: Factor out device configuration)
Signed-off-by:  Chen Haiquan <oc@yunify.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 0496f1a..0b24f51 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2985,6 +2985,9 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev,
 	if (data[IFLA_VXLAN_REMCSUM_NOPARTIAL])
 		conf.flags |= VXLAN_F_REMCSUM_NOPARTIAL;
 
+	if (tb[IFLA_MTU])
+		conf.mtu = nla_get_u32(tb[IFLA_MTU]);
+
 	err = vxlan_dev_configure(src_net, dev, &conf);
 	switch (err) {
 	case -ENODEV:
-- 
2.1.0


From 48818d9659bb07ecae94a1818c8e0565dfa48f08 Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Mon, 6 Jun 2016 15:07:18 -0700
Subject: [PATCH 13/19] tcp: record TLP and ER timer stats in v6 stats

[ Upstream commit ce3cf4ec0305919fc69a972f6c2b2efd35d36abc ]

The v6 tcp stats scan do not provide TLP and ER timer information
correctly like the v4 version . This patch fixes that.

Fixes: 6ba8a3b19e76 ("tcp: Tail loss probe (TLP)")
Fixes: eed530b6c676 ("tcp: early retransmit")
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/tcp_ipv6.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index b8d4056..1a1cd39 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1706,7 +1706,9 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
 	destp = ntohs(inet->inet_dport);
 	srcp  = ntohs(inet->inet_sport);
 
-	if (icsk->icsk_pending == ICSK_TIME_RETRANS) {
+	if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
+	    icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
+	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
 		timer_active	= 1;
 		timer_expires	= icsk->icsk_timeout;
 	} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
-- 
2.1.0


From 8288bbe072ab6ed953ad7cd9f7ab8b08c62c4087 Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Tue, 7 Jun 2016 19:14:17 +0900
Subject: [PATCH 14/19] bridge: Don't insert unnecessary local fdb entry on
 changing mac address

[ Upstream commit 0b148def403153a4d1565f1640356cb78ce5109f ]

The missing br_vlan_should_use() test caused creation of an unneeded
local fdb entry on changing mac address of a bridge device when there is
a vlan which is configured on a bridge port but not on the bridge
device.

Fixes: 2594e9064a57 ("bridge: vlan: add per-vlan struct and move to rhashtables")
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_fdb.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index a642bb8..09442e0 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -278,6 +278,8 @@ void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr)
 	 * change from under us.
 	 */
 	list_for_each_entry(v, &vg->vlan_list, vlist) {
+		if (!br_vlan_should_use(v))
+			continue;
 		f = __br_fdb_get(br, br->dev->dev_addr, v->vid);
 		if (f && f->is_local && !f->dst)
 			fdb_delete_local(br, NULL, f);
-- 
2.1.0


From dbc8aec29801dbe51c23e8c69773a9543ffafb92 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Wed, 8 Jun 2016 12:59:17 +0200
Subject: [PATCH 15/19] l2tp: fix configuration passed to
 setup_udp_tunnel_sock()

[ Upstream commit a5c5e2da8551eb69e5d5d09d51d526140b5db9fb ]

Unused fields of udp_cfg must be all zeros. Otherwise
setup_udp_tunnel_sock() fills ->gro_receive and ->gro_complete
callbacks with garbage, eventually resulting in panic when used by
udp_gro_receive().

[   72.694123] BUG: unable to handle kernel paging request at ffff880033f87d78
[   72.695518] IP: [<ffff880033f87d78>] 0xffff880033f87d78
[   72.696530] PGD 26e2067 PUD 26e3067 PMD 342ed063 PTE 8000000033f87163
[   72.696530] Oops: 0011 [#1] SMP KASAN
[   72.696530] Modules linked in: l2tp_ppp l2tp_netlink l2tp_core ip6_udp_tunnel udp_tunnel pptp gre pppox ppp_generic slhc crc32c_intel ghash_clmulni_intel jitterentropy_rng sha256_generic hmac drbg ansi_cprng aesni_intel evdev aes_x86_64 ablk_helper cryptd lrw gf128mul glue_helper serio_raw acpi_cpufreq button proc\
essor ext4 crc16 jbd2 mbcache virtio_blk virtio_net virtio_pci virtio_ring virtio
[   72.696530] CPU: 3 PID: 0 Comm: swapper/3 Not tainted 4.7.0-rc1 #1
[   72.696530] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Debian-1.8.2-1 04/01/2014
[   72.696530] task: ffff880035b59700 ti: ffff880035b70000 task.ti: ffff880035b70000
[   72.696530] RIP: 0010:[<ffff880033f87d78>]  [<ffff880033f87d78>] 0xffff880033f87d78
[   72.696530] RSP: 0018:ffff880035f87bc0  EFLAGS: 00010246
[   72.696530] RAX: ffffed000698f996 RBX: ffff88003326b840 RCX: ffffffff814cc823
[   72.696530] RDX: ffff88003326b840 RSI: ffff880033e48038 RDI: ffff880034c7c780
[   72.696530] RBP: ffff880035f87c18 R08: 000000000000a506 R09: 0000000000000000
[   72.696530] R10: ffff880035f87b38 R11: ffff880034b9344d R12: 00000000ebfea715
[   72.696530] R13: 0000000000000000 R14: ffff880034c7c780 R15: 0000000000000000
[   72.696530] FS:  0000000000000000(0000) GS:ffff880035f80000(0000) knlGS:0000000000000000
[   72.696530] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   72.696530] CR2: ffff880033f87d78 CR3: 0000000033c98000 CR4: 00000000000406a0
[   72.696530] Stack:
[   72.696530]  ffffffff814cc834 ffff880034b93468 0000001481416818 ffff88003326b874
[   72.696530]  ffff880034c7ccb0 ffff880033e48038 ffff88003326b840 ffff880034b93462
[   72.696530]  ffff88003326b88a ffff88003326b88c ffff880034b93468 ffff880035f87c70
[   72.696530] Call Trace:
[   72.696530]  <IRQ>
[   72.696530]  [<ffffffff814cc834>] ? udp_gro_receive+0x1c6/0x1f9
[   72.696530]  [<ffffffff814ccb1c>] udp4_gro_receive+0x2b5/0x310
[   72.696530]  [<ffffffff814d989b>] inet_gro_receive+0x4a3/0x4cd
[   72.696530]  [<ffffffff81431b32>] dev_gro_receive+0x584/0x7a3
[   72.696530]  [<ffffffff810adf7a>] ? __lock_is_held+0x29/0x64
[   72.696530]  [<ffffffff814321f7>] napi_gro_receive+0x124/0x21d
[   72.696530]  [<ffffffffa000b145>] virtnet_receive+0x8df/0x8f6 [virtio_net]
[   72.696530]  [<ffffffffa000b27e>] virtnet_poll+0x1d/0x8d [virtio_net]
[   72.696530]  [<ffffffff81431350>] net_rx_action+0x15b/0x3b9
[   72.696530]  [<ffffffff815893d6>] __do_softirq+0x216/0x546
[   72.696530]  [<ffffffff81062392>] irq_exit+0x49/0xb6
[   72.696530]  [<ffffffff81588e9a>] do_IRQ+0xe2/0xfa
[   72.696530]  [<ffffffff81587a49>] common_interrupt+0x89/0x89
[   72.696530]  <EOI>
[   72.696530]  [<ffffffff810b05df>] ? trace_hardirqs_on_caller+0x229/0x270
[   72.696530]  [<ffffffff8102b3c7>] ? default_idle+0x1c/0x2d
[   72.696530]  [<ffffffff8102b3c5>] ? default_idle+0x1a/0x2d
[   72.696530]  [<ffffffff8102bb8c>] arch_cpu_idle+0xa/0xc
[   72.696530]  [<ffffffff810a6c39>] default_idle_call+0x1a/0x1c
[   72.696530]  [<ffffffff810a6d96>] cpu_startup_entry+0x15b/0x20f
[   72.696530]  [<ffffffff81039a81>] start_secondary+0x12c/0x133
[   72.696530] Code: ff ff ff ff ff ff ff ff ff ff 7f ff ff ff ff ff ff ff 7f 00 7e f8 33 00 88 ff ff 6d 61 58 81 ff ff ff ff 5e de 0a 81 ff ff ff ff <00> 5c e2 34 00 88 ff ff 00 00 00 00 00 00 00 00 00 00 00 00 00
[   72.696530] RIP  [<ffff880033f87d78>] 0xffff880033f87d78
[   72.696530]  RSP <ffff880035f87bc0>
[   72.696530] CR2: ffff880033f87d78
[   72.696530] ---[ end trace ad7758b9a1dccf99 ]---
[   72.696530] Kernel panic - not syncing: Fatal exception in interrupt
[   72.696530] Kernel Offset: disabled
[   72.696530] ---[ end Kernel panic - not syncing: Fatal exception in interrupt

v2: use empty initialiser instead of "{ NULL }" to avoid relying on
    first field's type.

Fixes: 38fd2af24fcf ("udp: Add socket based GRO and config")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index afca2eb..ec17cbe 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1581,7 +1581,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
 	/* Mark socket as an encapsulation socket. See net/ipv4/udp.c */
 	tunnel->encap = encap;
 	if (encap == L2TP_ENCAPTYPE_UDP) {
-		struct udp_tunnel_sock_cfg udp_cfg;
+		struct udp_tunnel_sock_cfg udp_cfg = { };
 
 		udp_cfg.sk_user_data = tunnel;
 		udp_cfg.encap_type = UDP_ENCAP_L2TPINUDP;
-- 
2.1.0


From eb296f08fb6a3cbf2e72737282a07b85f341a9b1 Mon Sep 17 00:00:00 2001
From: Jakub Sitnicki <jkbs@redhat.com>
Date: Wed, 8 Jun 2016 15:13:34 +0200
Subject: [PATCH 16/19] ipv6: Skip XFRM lookup if dst_entry in socket cache is
 valid

[ Upstream commit 00bc0ef5880dc7b82f9c320dead4afaad48e47be ]

At present we perform an xfrm_lookup() for each UDPv6 message we
send. The lookup involves querying the flow cache (flow_cache_lookup)
and, in case of a cache miss, creating an XFRM bundle.

If we miss the flow cache, we can end up creating a new bundle and
deriving the path MTU (xfrm_init_pmtu) from on an already transformed
dst_entry, which we pass from the socket cache (sk->sk_dst_cache) down
to xfrm_lookup(). This can happen only if we're caching the dst_entry
in the socket, that is when we're using a connected UDP socket.

To put it another way, the path MTU shrinks each time we miss the flow
cache, which later on leads to incorrectly fragmented payload. It can
be observed with ESPv6 in transport mode:

  1) Set up a transformation and lower the MTU to trigger fragmentation
    # ip xfrm policy add dir out src ::1 dst ::1 \
      tmpl src ::1 dst ::1 proto esp spi 1
    # ip xfrm state add src ::1 dst ::1 \
      proto esp spi 1 enc 'aes' 0x0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b
    # ip link set dev lo mtu 1500

  2) Monitor the packet flow and set up an UDP sink
    # tcpdump -ni lo -ttt &
    # socat udp6-listen:12345,fork /dev/null &

  3) Send a datagram that needs fragmentation with a connected socket
    # perl -e 'print "@" x 1470 | socat - udp6:[::1]:12345
    2016/06/07 18:52:52 socat[724] E read(3, 0x555bb3d5ba00, 8192): Protocol error
    00:00:00.000000 IP6 ::1 > ::1: frag (0|1448) ESP(spi=0x00000001,seq=0x2), length 1448
    00:00:00.000014 IP6 ::1 > ::1: frag (1448|32)
    00:00:00.000050 IP6 ::1 > ::1: ESP(spi=0x00000001,seq=0x3), length 1272
    (^ ICMPv6 Parameter Problem)
    00:00:00.000022 IP6 ::1 > ::1: ESP(spi=0x00000001,seq=0x5), length 136

  4) Compare it to a non-connected socket
    # perl -e 'print "@" x 1500' | socat - udp6-sendto:[::1]:12345
    00:00:40.535488 IP6 ::1 > ::1: frag (0|1448) ESP(spi=0x00000001,seq=0x6), length 1448
    00:00:00.000010 IP6 ::1 > ::1: frag (1448|64)

What happens in step (3) is:

  1) when connecting the socket in __ip6_datagram_connect(), we
     perform an XFRM lookup, miss the flow cache, create an XFRM
     bundle, and cache the destination,

  2) afterwards, when sending the datagram, we perform an XFRM lookup,
     again, miss the flow cache (due to mismatch of flowi6_iif and
     flowi6_oif, which is an issue of its own), and recreate an XFRM
     bundle based on the cached (and already transformed) destination.

To prevent the recreation of an XFRM bundle, avoid an XFRM lookup
altogether whenever we already have a destination entry cached in the
socket. This prevents the path MTU shrinkage and brings us on par with
UDPv4.

The fix also benefits connected PINGv6 sockets, another user of
ip6_sk_dst_lookup_flow(), who also suffer messages being transformed
twice.

Joint work with Hannes Frederic Sowa.

Reported-by: Jan Tluka <jtluka@redhat.com>
Signed-off-by: Jakub Sitnicki <jkbs@redhat.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_output.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index a175152..58900c2 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1072,17 +1072,12 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
 					 const struct in6_addr *final_dst)
 {
 	struct dst_entry *dst = sk_dst_check(sk, inet6_sk(sk)->dst_cookie);
-	int err;
 
 	dst = ip6_sk_dst_check(sk, dst, fl6);
+	if (!dst)
+		dst = ip6_dst_lookup_flow(sk, fl6, final_dst);
 
-	err = ip6_dst_lookup_tail(sock_net(sk), sk, &dst, fl6);
-	if (err)
-		return ERR_PTR(err);
-	if (final_dst)
-		fl6->daddr = *final_dst;
-
-	return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
+	return dst;
 }
 EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow);
 
-- 
2.1.0


From fbaf77a0231d1067007b9fc52d01a5f5cdce2fb7 Mon Sep 17 00:00:00 2001
From: David Wragg <david@weave.works>
Date: Fri, 3 Jun 2016 18:58:13 -0400
Subject: [PATCH 17/19] vxlan: Relax MTU constraints

[ Upstream commit 72564b59ffc438ea103b0727a921aaddce766728 ]

Allow the MTU of vxlan devices without an underlying device to be set
to larger values (up to a maximum based on IP packet limits and vxlan
overhead).

Previously, their MTUs could not be set to higher than the
conventional ethernet value of 1500.  This is a very arbitrary value
in the context of vxlan, and prevented vxlan devices from being able
to take advantage of jumbo frames etc.

The default MTU remains 1500, for compatibility.

Signed-off-by: David Wragg <david@weave.works>
Acked-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 36 +++++++++++++++++++++++++-----------
 1 file changed, 25 insertions(+), 11 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 0b24f51..2f44bc5 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2364,29 +2364,43 @@ static void vxlan_set_multicast_list(struct net_device *dev)
 {
 }
 
-static int vxlan_change_mtu(struct net_device *dev, int new_mtu)
+static int __vxlan_change_mtu(struct net_device *dev,
+			      struct net_device *lowerdev,
+			      struct vxlan_rdst *dst, int new_mtu, bool strict)
 {
-	struct vxlan_dev *vxlan = netdev_priv(dev);
-	struct vxlan_rdst *dst = &vxlan->default_dst;
-	struct net_device *lowerdev;
-	int max_mtu;
+	int max_mtu = IP_MAX_MTU;
 
-	lowerdev = __dev_get_by_index(vxlan->net, dst->remote_ifindex);
-	if (lowerdev == NULL)
-		return eth_change_mtu(dev, new_mtu);
+	if (lowerdev)
+		max_mtu = lowerdev->mtu;
 
 	if (dst->remote_ip.sa.sa_family == AF_INET6)
-		max_mtu = lowerdev->mtu - VXLAN6_HEADROOM;
+		max_mtu -= VXLAN6_HEADROOM;
 	else
-		max_mtu = lowerdev->mtu - VXLAN_HEADROOM;
+		max_mtu -= VXLAN_HEADROOM;
 
-	if (new_mtu < 68 || new_mtu > max_mtu)
+	if (new_mtu < 68)
 		return -EINVAL;
 
+	if (new_mtu > max_mtu) {
+		if (strict)
+			return -EINVAL;
+
+		new_mtu = max_mtu;
+	}
+
 	dev->mtu = new_mtu;
 	return 0;
 }
 
+static int vxlan_change_mtu(struct net_device *dev, int new_mtu)
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_rdst *dst = &vxlan->default_dst;
+	struct net_device *lowerdev = __dev_get_by_index(vxlan->net,
+							 dst->remote_ifindex);
+	return __vxlan_change_mtu(dev, lowerdev, dst, new_mtu, true);
+}
+
 static int egress_ipv4_tun_info(struct net_device *dev, struct sk_buff *skb,
 				struct ip_tunnel_info *info,
 				__be16 sport, __be16 dport)
-- 
2.1.0


From ee68558badb64ae66a2952e09ce33fb79d4604a9 Mon Sep 17 00:00:00 2001
From: David Wragg <david@weave.works>
Date: Fri, 3 Jun 2016 18:58:14 -0400
Subject: [PATCH 18/19] geneve: Relax MTU constraints

[ Upstream commit 55e5bfb53cff286c1c1ff49f51325dc15c7fea63 ]

Allow the MTU of geneve devices to be set to large values, in order to
exploit underlying networks with larger frame sizes.

GENEVE does not have a fixed encapsulation overhead (an openvswitch
rule can add variable length options), so there is no relevant maximum
MTU to enforce.  A maximum of IP_MAX_MTU is used instead.
Encapsulated packets that are too big for the underlying network will
get dropped on the floor.

Signed-off-by: David Wragg <david@weave.works>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index e3f939f..240620c 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -994,6 +994,17 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
 	return geneve_xmit_skb(skb, dev, info);
 }
 
+static int geneve_change_mtu(struct net_device *dev, int new_mtu)
+{
+	/* GENEVE overhead is not fixed, so we can't enforce a more
+	 * precise max MTU.
+	 */
+	if (new_mtu < 68 || new_mtu > IP_MAX_MTU)
+		return -EINVAL;
+	dev->mtu = new_mtu;
+	return 0;
+}
+
 static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 {
 	struct ip_tunnel_info *info = skb_tunnel_info(skb);
@@ -1038,7 +1049,7 @@ static const struct net_device_ops geneve_netdev_ops = {
 	.ndo_stop		= geneve_stop,
 	.ndo_start_xmit		= geneve_xmit,
 	.ndo_get_stats64	= ip_tunnel_get_stats64,
-	.ndo_change_mtu		= eth_change_mtu,
+	.ndo_change_mtu		= geneve_change_mtu,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_fill_metadata_dst	= geneve_fill_metadata_dst,
-- 
2.1.0


From 5c306d556cf063ffbf49ed777d94c2f3a0e0faaf Mon Sep 17 00:00:00 2001
From: David Wragg <david@weave.works>
Date: Fri, 3 Jun 2016 18:58:15 -0400
Subject: [PATCH 19/19] vxlan, gre, geneve: Set a large MTU on ovs-created
 tunnel devices

[ Upstream commit 7e059158d57b79159eaf1f504825d19866ef2c42 ]

Prior to 4.3, openvswitch tunnel vports (vxlan, gre and geneve) could
transmit vxlan packets of any size, constrained only by the ability to
send out the resulting packets.  4.3 introduced netdevs corresponding
to tunnel vports.  These netdevs have an MTU, which limits the size of
a packet that can be successfully encapsulated.  The default MTU
values are low (1500 or less), which is awkwardly small in the context
of physical networks supporting jumbo frames, and leads to a
conspicuous change in behaviour for userspace.

Instead, set the MTU on openvswitch-created netdevs to be the relevant
maximum (i.e. the maximum IP packet size minus any relevant overhead),
effectively restoring the behaviour prior to 4.3.

Signed-off-by: David Wragg <david@weave.works>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c          | 18 ++++++++++++++----
 drivers/net/vxlan.c           | 11 ++++++++---
 include/net/ip_tunnels.h      |  1 +
 net/ipv4/ip_gre.c             |  8 ++++++++
 net/ipv4/ip_tunnel.c          | 20 +++++++++++++++++---
 net/openvswitch/vport-vxlan.c |  2 ++
 6 files changed, 50 insertions(+), 10 deletions(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 240620c..69e31e2 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1356,11 +1356,21 @@ struct net_device *geneve_dev_create_fb(struct net *net, const char *name,
 
 	err = geneve_configure(net, dev, &geneve_remote_unspec,
 			       0, 0, 0, htons(dst_port), true);
-	if (err) {
-		free_netdev(dev);
-		return ERR_PTR(err);
-	}
+	if (err)
+		goto err;
+
+	/* openvswitch users expect packet sizes to be unrestricted,
+	 * so set the largest MTU we can.
+	 */
+	err = geneve_change_mtu(dev, IP_MAX_MTU);
+	if (err)
+		goto err;
+
 	return dev;
+
+ err:
+	free_netdev(dev);
+	return ERR_PTR(err);
 }
 EXPORT_SYMBOL_GPL(geneve_dev_create_fb);
 
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 2f44bc5..0037809 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2776,6 +2776,7 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 	int err;
 	bool use_ipv6 = false;
 	__be16 default_port = vxlan->cfg.dst_port;
+	struct net_device *lowerdev = NULL;
 
 	vxlan->net = src_net;
 
@@ -2796,9 +2797,7 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 	}
 
 	if (conf->remote_ifindex) {
-		struct net_device *lowerdev
-			 = __dev_get_by_index(src_net, conf->remote_ifindex);
-
+		lowerdev = __dev_get_by_index(src_net, conf->remote_ifindex);
 		dst->remote_ifindex = conf->remote_ifindex;
 
 		if (!lowerdev) {
@@ -2822,6 +2821,12 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 		needed_headroom = lowerdev->hard_header_len;
 	}
 
+	if (conf->mtu) {
+		err = __vxlan_change_mtu(dev, lowerdev, dst, conf->mtu, false);
+		if (err)
+			return err;
+	}
+
 	if (use_ipv6 || conf->flags & VXLAN_F_COLLECT_METADATA)
 		needed_headroom += VXLAN6_HEADROOM;
 	else
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 62a750a..af40bc5 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -230,6 +230,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd);
 int ip_tunnel_encap(struct sk_buff *skb, struct ip_tunnel *t,
 		    u8 *protocol, struct flowi4 *fl4);
+int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict);
 int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu);
 
 struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev,
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 7dc962b..3e41840 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1247,6 +1247,14 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name,
 	err = ipgre_newlink(net, dev, tb, NULL);
 	if (err < 0)
 		goto out;
+
+	/* openvswitch users expect packet sizes to be unrestricted,
+	 * so set the largest MTU we can.
+	 */
+	err = __ip_tunnel_change_mtu(dev, IP_MAX_MTU, false);
+	if (err)
+		goto out;
+
 	return dev;
 out:
 	free_netdev(dev);
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index ce30c8b..3310ac7 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -948,17 +948,31 @@ done:
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_ioctl);
 
-int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu)
+int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	int t_hlen = tunnel->hlen + sizeof(struct iphdr);
+	int max_mtu = 0xFFF8 - dev->hard_header_len - t_hlen;
 
-	if (new_mtu < 68 ||
-	    new_mtu > 0xFFF8 - dev->hard_header_len - t_hlen)
+	if (new_mtu < 68)
 		return -EINVAL;
+
+	if (new_mtu > max_mtu) {
+		if (strict)
+			return -EINVAL;
+
+		new_mtu = max_mtu;
+	}
+
 	dev->mtu = new_mtu;
 	return 0;
 }
+EXPORT_SYMBOL_GPL(__ip_tunnel_change_mtu);
+
+int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu)
+{
+	return __ip_tunnel_change_mtu(dev, new_mtu, true);
+}
 EXPORT_SYMBOL_GPL(ip_tunnel_change_mtu);
 
 static void ip_tunnel_dev_free(struct net_device *dev)
diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index d933cb8..5eb7694 100644
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -91,6 +91,8 @@ static struct vport *vxlan_tnl_create(const struct vport_parms *parms)
 	struct vxlan_config conf = {
 		.no_share = true,
 		.flags = VXLAN_F_COLLECT_METADATA | VXLAN_F_UDP_ZERO_CSUM6_RX,
+		/* Don't restrict the packets that can be sent by MTU */
+		.mtu = IP_MAX_MTU,
 	};
 
 	if (!options) {
-- 
2.1.0


[-- Attachment #3: net_45.mbox --]
[-- Type: Application/Octet-Stream, Size: 74822 bytes --]

From 4c16f72d678eb51e87cbe08ace33c4ce6d07c35f Mon Sep 17 00:00:00 2001
From: Richard Alpe <richard.alpe@ericsson.com>
Date: Mon, 16 May 2016 11:14:54 +0200
Subject: [PATCH 01/23] tipc: check nl sock before parsing nested attributes

[ Upstream commit 45e093ae2830cd1264677d47ff9a95a71f5d9f9c ]

Make sure the socket for which the user is listing publication exists
before parsing the socket netlink attributes.

Prior to this patch a call without any socket caused a NULL pointer
dereference in tipc_nl_publ_dump().

Tested-and-reported-by: Baozeng Ding <sploving1@gmail.com>
Signed-off-by: Richard Alpe <richard.alpe@ericsson.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.cm>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/socket.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 4d420bb..ea06f91 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2814,6 +2814,9 @@ int tipc_nl_publ_dump(struct sk_buff *skb, struct netlink_callback *cb)
 		if (err)
 			return err;
 
+		if (!attrs[TIPC_NLA_SOCK])
+			return -EINVAL;
+
 		err = nla_parse_nested(sock, TIPC_NLA_SOCK_MAX,
 				       attrs[TIPC_NLA_SOCK],
 				       tipc_nl_sock_policy);
-- 
2.1.0


From 3d167c8ca6d577219d0c2ec73bff91a4edca3dec Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Mon, 16 May 2016 17:28:16 +0800
Subject: [PATCH 02/23] netlink: Fix dump skb leak/double free

[ Upstream commit 92964c79b357efd980812c4de5c1fd2ec8bb5520 ]

When we free cb->skb after a dump, we do it after releasing the
lock.  This means that a new dump could have started in the time
being and we'll end up freeing their skb instead of ours.

This patch saves the skb and module before we unlock so we free
the right memory.

Fixes: 16b304f3404f ("netlink: Eliminate kmalloc in netlink dump operation.")
Reported-by: Baozeng Ding <sploving1@gmail.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index d2bc03f..45dd5e3 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2784,6 +2784,7 @@ static int netlink_dump(struct sock *sk)
 	struct netlink_callback *cb;
 	struct sk_buff *skb = NULL;
 	struct nlmsghdr *nlh;
+	struct module *module;
 	int len, err = -ENOBUFS;
 	int alloc_min_size;
 	int alloc_size;
@@ -2864,9 +2865,11 @@ static int netlink_dump(struct sock *sk)
 		cb->done(cb);
 
 	nlk->cb_running = false;
+	module = cb->module;
+	skb = cb->skb;
 	mutex_unlock(nlk->cb_mutex);
-	module_put(cb->module);
-	consume_skb(cb->skb);
+	module_put(module);
+	consume_skb(skb);
 	return 0;
 
 errout_skb:
-- 
2.1.0


From 88080b57fdbd05b9fe9e8e5cd8b8c2973d035a3e Mon Sep 17 00:00:00 2001
From: Richard Alpe <richard.alpe@ericsson.com>
Date: Tue, 17 May 2016 16:57:37 +0200
Subject: [PATCH 03/23] tipc: fix nametable publication field in nl compat

[ Upstream commit 03aaaa9b941e136757b55c4cf775aab6068dfd94 ]

The publication field of the old netlink API should contain the
publication key and not the publication reference.

Fixes: 44a8ae94fd55 (tipc: convert legacy nl name table dump to nl compat)
Signed-off-by: Richard Alpe <richard.alpe@ericsson.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/netlink_compat.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 2c016fd..ae58a6b 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -802,7 +802,7 @@ static int tipc_nl_compat_name_table_dump(struct tipc_nl_compat_msg *msg,
 		goto out;
 
 	tipc_tlv_sprintf(msg->rep, "%-10u %s",
-			 nla_get_u32(publ[TIPC_NLA_PUBL_REF]),
+			 nla_get_u32(publ[TIPC_NLA_PUBL_KEY]),
 			 scope_str[nla_get_u32(publ[TIPC_NLA_PUBL_SCOPE])]);
 out:
 	tipc_tlv_sprintf(msg->rep, "\n");
-- 
2.1.0


From 4d7d70a3cea1410dd28ee5259e7bba8bc0e01965 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Tue, 17 May 2016 18:58:08 +0200
Subject: [PATCH 04/23] switchdev: pass pointer to fib_info instead of copy

[ Upstream commit da4ed55165d41b1073f9a476f1c18493e9bf8c8e ]

The problem is that fib_info->nh is [0] so the struct fib_info
allocation size depends on number of nexthops. If we just copy fib_info,
we do not copy the nexthops info and driver accesses memory which is not
ours.

Given the fact that fib4 does not defer operations and therefore it does
not need copy, just pass the pointer down to drivers as it was done
before.

Fixes: 850d0cbc91 ("switchdev: remove pointers from switchdev objects")
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/rocker/rocker.c | 4 ++--
 include/net/switchdev.h              | 2 +-
 net/switchdev/switchdev.c            | 6 ++----
 3 files changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c
index f39e719..4f42e58 100644
--- a/drivers/net/ethernet/rocker/rocker.c
+++ b/drivers/net/ethernet/rocker/rocker.c
@@ -4475,7 +4475,7 @@ static int rocker_port_obj_add(struct net_device *dev,
 		fib4 = SWITCHDEV_OBJ_IPV4_FIB(obj);
 		err = rocker_port_fib_ipv4(rocker_port, trans,
 					   htonl(fib4->dst), fib4->dst_len,
-					   &fib4->fi, fib4->tb_id, 0);
+					   fib4->fi, fib4->tb_id, 0);
 		break;
 	case SWITCHDEV_OBJ_ID_PORT_FDB:
 		err = rocker_port_fdb_add(rocker_port, trans,
@@ -4547,7 +4547,7 @@ static int rocker_port_obj_del(struct net_device *dev,
 		fib4 = SWITCHDEV_OBJ_IPV4_FIB(obj);
 		err = rocker_port_fib_ipv4(rocker_port, NULL,
 					   htonl(fib4->dst), fib4->dst_len,
-					   &fib4->fi, fib4->tb_id,
+					   fib4->fi, fib4->tb_id,
 					   ROCKER_OP_FLAG_REMOVE);
 		break;
 	case SWITCHDEV_OBJ_ID_PORT_FDB:
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index d451122..a75d795 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -93,7 +93,7 @@ struct switchdev_obj_ipv4_fib {
 	struct switchdev_obj obj;
 	u32 dst;
 	int dst_len;
-	struct fib_info fi;
+	struct fib_info *fi;
 	u8 tos;
 	u8 type;
 	u32 nlflags;
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index 8b5833c..002cc85 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -1182,6 +1182,7 @@ int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi,
 		.obj.id = SWITCHDEV_OBJ_ID_IPV4_FIB,
 		.dst = dst,
 		.dst_len = dst_len,
+		.fi = fi,
 		.tos = tos,
 		.type = type,
 		.nlflags = nlflags,
@@ -1190,8 +1191,6 @@ int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi,
 	struct net_device *dev;
 	int err = 0;
 
-	memcpy(&ipv4_fib.fi, fi, sizeof(ipv4_fib.fi));
-
 	/* Don't offload route if using custom ip rules or if
 	 * IPv4 FIB offloading has been disabled completely.
 	 */
@@ -1236,6 +1235,7 @@ int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi,
 		.obj.id = SWITCHDEV_OBJ_ID_IPV4_FIB,
 		.dst = dst,
 		.dst_len = dst_len,
+		.fi = fi,
 		.tos = tos,
 		.type = type,
 		.nlflags = 0,
@@ -1244,8 +1244,6 @@ int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi,
 	struct net_device *dev;
 	int err = 0;
 
-	memcpy(&ipv4_fib.fi, fi, sizeof(ipv4_fib.fi));
-
 	if (!(fi->fib_flags & RTNH_F_OFFLOAD))
 		return 0;
 
-- 
2.1.0


From 2ed951a3b9743b280b7430849d4127d2afd53616 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Thu, 19 May 2016 13:36:51 +0800
Subject: [PATCH 05/23] tuntap: correctly wake up process during uninit

[ Upstream commit addf8fc4acb1cf79492ac64966f07178793cb3d7 ]

We used to check dev->reg_state against NETREG_REGISTERED after each
time we are woke up. But after commit 9e641bdcfa4e ("net-tun:
restructure tun_do_read for better sleep/wakeup efficiency"), it uses
skb_recv_datagram() which does not check dev->reg_state. This will
result if we delete a tun/tap device after a process is blocked in the
reading. The device will wait for the reference count which was held
by that process for ever.

Fixes this by using RCV_SHUTDOWN which will be checked during
sk_recv_datagram() before trying to wake up the process during uninit.

Fixes: 9e641bdcfa4e ("net-tun: restructure tun_do_read for better
sleep/wakeup efficiency")
Cc: Eric Dumazet <edumazet@google.com>
Cc: Xi Wang <xii@google.com>
Cc: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 81ecc2e..7a38844 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -567,11 +567,13 @@ static void tun_detach_all(struct net_device *dev)
 	for (i = 0; i < n; i++) {
 		tfile = rtnl_dereference(tun->tfiles[i]);
 		BUG_ON(!tfile);
+		tfile->socket.sk->sk_shutdown = RCV_SHUTDOWN;
 		tfile->socket.sk->sk_data_ready(tfile->socket.sk);
 		RCU_INIT_POINTER(tfile->tun, NULL);
 		--tun->numqueues;
 	}
 	list_for_each_entry(tfile, &tun->disabled, next) {
+		tfile->socket.sk->sk_shutdown = RCV_SHUTDOWN;
 		tfile->socket.sk->sk_data_ready(tfile->socket.sk);
 		RCU_INIT_POINTER(tfile->tun, NULL);
 	}
@@ -627,6 +629,7 @@ static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filte
 			goto out;
 	}
 	tfile->queue_index = tun->numqueues;
+	tfile->socket.sk->sk_shutdown &= ~RCV_SHUTDOWN;
 	rcu_assign_pointer(tfile->tun, tun);
 	rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile);
 	tun->numqueues++;
@@ -1411,9 +1414,6 @@ static ssize_t tun_do_read(struct tun_struct *tun, struct tun_file *tfile,
 	if (!iov_iter_count(to))
 		return 0;
 
-	if (tun->dev->reg_state != NETREG_REGISTERED)
-		return -EIO;
-
 	/* Read frames from queue */
 	skb = __skb_recv_datagram(tfile->socket.sk, noblock ? MSG_DONTWAIT : 0,
 				  &peeked, &off, &err);
-- 
2.1.0


From 0a58328e6cf1a0ca83cd6bdf95c309e0ed0e5728 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 20 May 2016 17:22:48 -0500
Subject: [PATCH 06/23] bpf: Use mount_nodev not mount_ns to mount the bpf
 filesystem

[ Upstream commit e27f4a942a0ee4b84567a3c6cfa84f273e55cbb7 ]

While reviewing the filesystems that set FS_USERNS_MOUNT I spotted the
bpf filesystem.  Looking at the code I saw a broken usage of mount_ns
with current->nsproxy->mnt_ns. As the code does not acquire a
reference to the mount namespace it can not possibly be correct to
store the mount namespace on the superblock as it does.

Replace mount_ns with mount_nodev so that each mount of the bpf
filesystem returns a distinct instance, and the code is not buggy.

In discussion with Hannes Frederic Sowa it was reported that the use
of mount_ns was an attempt to have one bpf instance per mount
namespace, in an attempt to keep resources that pin resources from
hiding.  That intent simply does not work, the vfs is not built to
allow that kind of behavior.  Which means that the bpf filesystem
really is buggy both semantically and in it's implemenation as it does
not nor can it implement the original intent.

This change is userspace visible, but my experience with similar
filesystems leads me to believe nothing will break with a model of each
mount of the bpf filesystem is distinct from all others.

Fixes: b2197755b263 ("bpf: add support for persistent maps/progs")
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/inode.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 8f94ca1..55d9236 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -378,7 +378,7 @@ static int bpf_fill_super(struct super_block *sb, void *data, int silent)
 static struct dentry *bpf_mount(struct file_system_type *type, int flags,
 				const char *dev_name, void *data)
 {
-	return mount_ns(type, flags, current->nsproxy->mnt_ns, bpf_fill_super);
+	return mount_nodev(type, flags, data, bpf_fill_super);
 }
 
 static struct file_system_type bpf_fs_type = {
-- 
2.1.0


From c2e08d65922be8c324100e0c3ecd14694f369831 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Thu, 19 May 2016 15:58:33 +0200
Subject: [PATCH 07/23] udp: prevent skbs lingering in tunnel socket queues

[ Upstream commit e5aed006be918af163eb397e45aa5ea6cefd5e01 ]

In case we find a socket with encapsulation enabled we should call
the encap_recv function even if just a udp header without payload is
available. The callbacks are responsible for correctly verifying and
dropping the packets.

Also, in case the header validation fails for geneve and vxlan we
shouldn't put the skb back into the socket queue, no one will pick
them up there.  Instead we can simply discard them in the respective
encap_recv functions.

Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c | 10 +++-------
 drivers/net/vxlan.c  | 10 ++--------
 net/ipv4/udp.c       |  2 +-
 net/ipv6/udp.c       |  2 +-
 4 files changed, 7 insertions(+), 17 deletions(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 0bf7edd..ae67fa4 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -317,15 +317,15 @@ static int geneve_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 
 	/* Need Geneve and inner Ethernet header to be present */
 	if (unlikely(!pskb_may_pull(skb, GENEVE_BASE_HLEN)))
-		goto error;
+		goto drop;
 
 	/* Return packets with reserved bits set */
 	geneveh = geneve_hdr(skb);
 	if (unlikely(geneveh->ver != GENEVE_VER))
-		goto error;
+		goto drop;
 
 	if (unlikely(geneveh->proto_type != htons(ETH_P_TEB)))
-		goto error;
+		goto drop;
 
 	opts_len = geneveh->opt_len * 4;
 	if (iptunnel_pull_header(skb, GENEVE_BASE_HLEN + opts_len,
@@ -343,10 +343,6 @@ drop:
 	/* Consume bad packet */
 	kfree_skb(skb);
 	return 0;
-
-error:
-	/* Let the UDP layer deal with the skb */
-	return 1;
 }
 
 static struct socket *geneve_create_sock(struct net *net, bool ipv6,
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 1c32bd1..b4eb55e 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1256,7 +1256,7 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 
 	/* Need Vxlan and inner Ethernet header to be present */
 	if (!pskb_may_pull(skb, VXLAN_HLEN))
-		goto error;
+		goto drop;
 
 	vxh = (struct vxlanhdr *)(udp_hdr(skb) + 1);
 	flags = ntohl(vxh->vx_flags);
@@ -1346,13 +1346,7 @@ drop:
 bad_flags:
 	netdev_dbg(skb->dev, "invalid vxlan flags=%#x vni=%#x\n",
 		   ntohl(vxh->vx_flags), ntohl(vxh->vx_vni));
-
-error:
-	if (tun_dst)
-		dst_release((struct dst_entry *)tun_dst);
-
-	/* Return non vxlan pkt */
-	return 1;
+	goto drop;
 }
 
 static int arp_reduce(struct net_device *dev, struct sk_buff *skb)
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 56218ff..c9f3de7 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1628,7 +1628,7 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 
 		/* if we're overly short, let UDP handle it */
 		encap_rcv = ACCESS_ONCE(up->encap_rcv);
-		if (skb->len > sizeof(struct udphdr) && encap_rcv) {
+		if (encap_rcv) {
 			int ret;
 
 			/* Verify checksum before giving to encap */
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 6794120..b2e9007 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -693,7 +693,7 @@ int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 
 		/* if we're overly short, let UDP handle it */
 		encap_rcv = ACCESS_ONCE(up->encap_rcv);
-		if (skb->len > sizeof(struct udphdr) && encap_rcv) {
+		if (encap_rcv) {
 			int ret;
 
 			/* Verify checksum before giving to encap */
-- 
2.1.0


From 127cd31100d4ec4baa81edc52e3c096914732909 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Thu, 19 May 2016 17:26:29 +0200
Subject: [PATCH 08/23] uapi glibc compat: fix compilation when !__USE_MISC in
 glibc

[ Upstream commit f0a3fdca794d1e68ae284ef4caefe681f7c18e89 ]

These structures are defined only if __USE_MISC is set in glibc net/if.h
headers, ie when _BSD_SOURCE or _SVID_SOURCE are defined.

CC: Jan Engelhardt <jengelh@inai.de>
CC: Josh Boyer <jwboyer@fedoraproject.org>
CC: Stephen Hemminger <shemming@brocade.com>
CC: Waldemar Brodkorb <mail@waldemar-brodkorb.de>
CC: Gabriel Laskar <gabriel@lse.epita.fr>
CC: Mikko Rapeli <mikko.rapeli@iki.fi>
Fixes: 4a91cb61bb99 ("uapi glibc compat: fix compile errors when glibc net/if.h included before linux/if.h")
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/libc-compat.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/uapi/linux/libc-compat.h b/include/uapi/linux/libc-compat.h
index d5e38c7..e4f048e 100644
--- a/include/uapi/linux/libc-compat.h
+++ b/include/uapi/linux/libc-compat.h
@@ -52,7 +52,7 @@
 #if defined(__GLIBC__)
 
 /* Coordinate with glibc net/if.h header. */
-#if defined(_NET_IF_H)
+#if defined(_NET_IF_H) && defined(__USE_MISC)
 
 /* GLIBC headers included first so don't define anything
  * that would already be defined. */
-- 
2.1.0


From 941c478c95453efd0b9049b02be954ccffabcd50 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Sun, 22 May 2016 23:16:18 +0200
Subject: [PATCH 09/23] bpf, inode: disallow userns mounts

[ Upstream commit 612bacad78ba6d0a91166fc4487af114bac172a8 ]

Follow-up to commit e27f4a942a0e ("bpf: Use mount_nodev not mount_ns
to mount the bpf filesystem"), which removes the FS_USERNS_MOUNT flag.

The original idea was to have a per mountns instance instead of a
single global fs instance, but that didn't work out and we had to
switch to mount_nodev() model. The intent of that middle ground was
that we avoid users who don't play nice to create endless instances
of bpf fs which are difficult to control and discover from an admin
point of view, but at the same time it would have allowed us to be
more flexible with regard to namespaces.

Therefore, since we now did the switch to mount_nodev() as a fix
where individual instances are created, we also need to remove userns
mount flag along with it to avoid running into mentioned situation.
I don't expect any breakage at this early point in time with removing
the flag and we can revisit this later should the requirement for
this come up with future users. This and commit e27f4a942a0e have
been split to facilitate tracking should any of them run into the
unlikely case of causing a regression.

Fixes: b2197755b263 ("bpf: add support for persistent maps/progs")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/inode.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 55d9236..b2aefa2 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -386,7 +386,6 @@ static struct file_system_type bpf_fs_type = {
 	.name		= "bpf",
 	.mount		= bpf_mount,
 	.kill_sb	= kill_litter_super,
-	.fs_flags	= FS_USERNS_MOUNT,
 };
 
 MODULE_ALIAS_FS("bpf");
-- 
2.1.0


From 4530e543a2924f8e8348cf9ebbcaa96485016bcc Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Tue, 24 May 2016 18:53:36 +0100
Subject: [PATCH 10/23] sfc: on MC reset, clear PIO buffer linkage in TXQs

[ Upstream commit c0795bf64cba4d1b796fdc5b74b33772841ed1bb ]

Otherwise, if we fail to allocate new PIO buffers, our TXQs will try to
use the old ones, which aren't there any more.

Fixes: 183233bec810 "sfc: Allocate and link PIO buffers; map them with write-combining"
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/ef10.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 98d33d4..3be934c 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -619,6 +619,17 @@ fail:
 	return rc;
 }
 
+static void efx_ef10_forget_old_piobufs(struct efx_nic *efx)
+{
+	struct efx_channel *channel;
+	struct efx_tx_queue *tx_queue;
+
+	/* All our existing PIO buffers went away */
+	efx_for_each_channel(channel, efx)
+		efx_for_each_channel_tx_queue(tx_queue, channel)
+			tx_queue->piobuf = NULL;
+}
+
 #else /* !EFX_USE_PIO */
 
 static int efx_ef10_alloc_piobufs(struct efx_nic *efx, unsigned int n)
@@ -635,6 +646,10 @@ static void efx_ef10_free_piobufs(struct efx_nic *efx)
 {
 }
 
+static void efx_ef10_forget_old_piobufs(struct efx_nic *efx)
+{
+}
+
 #endif /* EFX_USE_PIO */
 
 static void efx_ef10_remove(struct efx_nic *efx)
@@ -1018,6 +1033,7 @@ static void efx_ef10_reset_mc_allocations(struct efx_nic *efx)
 	nic_data->must_realloc_vis = true;
 	nic_data->must_restore_filters = true;
 	nic_data->must_restore_piobufs = true;
+	efx_ef10_forget_old_piobufs(efx);
 	nic_data->rx_rss_context = EFX_EF10_RSS_CONTEXT_INVALID;
 
 	/* Driver-created vswitches and vports must be re-created */
-- 
2.1.0


From 1634ecef3560b1e4c1e8bfcaa9e8b4af2ab004b2 Mon Sep 17 00:00:00 2001
From: Ivan Vecera <ivecera@redhat.com>
Date: Wed, 25 May 2016 21:21:52 +0200
Subject: [PATCH 11/23] team: don't call netdev_change_features under
 team->lock

[ Upstream commit f6988cb63a4e698d8a62a1d085d263d1fcc351ea ]

The team_device_event() notifier calls team_compute_features() to fix
vlan_features under team->lock to protect team->port_list. The problem is
that subsequent __team_compute_features() calls netdev_change_features()
to propagate vlan_features to upper vlan devices while team->lock is still
taken. This can lead to deadlock when NETIF_F_LRO is modified on lower
devices or team device itself.

Example:
The team0 as active backup with eth0 and eth1 NICs. Both eth0 & eth1 are
LRO capable and LRO is enabled. Thus LRO is also enabled on team0.

The command 'ethtool -K team0 lro off' now hangs due to this deadlock:

dev_ethtool()
-> ethtool_set_features()
 -> __netdev_update_features(team)
  -> netdev_sync_lower_features()
   -> netdev_update_features(lower_1)
    -> __netdev_update_features(lower_1)
    -> netdev_features_change(lower_1)
     -> call_netdevice_notifiers(...)
      -> team_device_event(lower_1)
       -> team_compute_features(team) [TAKES team->lock]
        -> netdev_change_features(team)
         -> __netdev_update_features(team)
          -> netdev_sync_lower_features()
           -> netdev_update_features(lower_2)
            -> __netdev_update_features(lower_2)
            -> netdev_features_change(lower_2)
             -> call_netdevice_notifiers(...)
              -> team_device_event(lower_2)
               -> team_compute_features(team) [DEADLOCK]

The bug is present in team from the beginning but it appeared after the commit
fd867d5 (net/core: generic support for disabling netdev features down stack)
that adds synchronization of features with lower devices.

Fixes: fd867d5 (net/core: generic support for disabling netdev features down stack)
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 718ceea..800a449 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -988,7 +988,7 @@ static void team_port_disable(struct team *team,
 #define TEAM_ENC_FEATURES	(NETIF_F_HW_CSUM | NETIF_F_SG | \
 				 NETIF_F_RXCSUM | NETIF_F_ALL_TSO)
 
-static void __team_compute_features(struct team *team)
+static void ___team_compute_features(struct team *team)
 {
 	struct team_port *port;
 	u32 vlan_features = TEAM_VLAN_FEATURES & NETIF_F_ALL_FOR_ALL;
@@ -1019,15 +1019,20 @@ static void __team_compute_features(struct team *team)
 	team->dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
 	if (dst_release_flag == (IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM))
 		team->dev->priv_flags |= IFF_XMIT_DST_RELEASE;
+}
 
+static void __team_compute_features(struct team *team)
+{
+	___team_compute_features(team);
 	netdev_change_features(team->dev);
 }
 
 static void team_compute_features(struct team *team)
 {
 	mutex_lock(&team->lock);
-	__team_compute_features(team);
+	___team_compute_features(team);
 	mutex_unlock(&team->lock);
+	netdev_change_features(team->dev);
 }
 
 static int team_port_enter(struct team *team, struct team_port *port)
-- 
2.1.0


From f7eb9a795c4302592d88ae2386c5138552052ca4 Mon Sep 17 00:00:00 2001
From: Feng Tang <feng.tang@intel.com>
Date: Wed, 25 May 2016 14:49:54 +0800
Subject: [PATCH 12/23] net: alx: use custom skb allocator

[ Upstream commit 26c5f03b2ae8018418ceb25b2e6a48560e8c2f5b ]

This patch follows Eric Dumazet's commit 7b70176421 for Atheros
atl1c driver to fix one exactly same bug in alx driver, that the
network link will be lost in 1-5 minutes after the device is up.

My laptop Lenovo Y580 with Atheros AR8161 ethernet device hit the
same problem with kernel 4.4, and it will be cured by Jarod Wilson's
commit c406700c for alx driver which get merged in 4.5. But there
are still some alx devices can't function well even with Jarod's
patch, while this patch could make them work fine. More details on
	https://bugzilla.kernel.org/show_bug.cgi?id=70761

The debug shows the issue is very likely to be related with the RX
DMA address, specifically 0x...f80, if RX buffer get 0x...f80 several
times, their will be RX overflow error and device will stop working.

For kernel 4.5.0 with Jarod's patch which works fine with my
AR8161/Lennov Y580, if I made some change to the
	__netdev_alloc_skb
		--> __alloc_page_frag()
to make the allocated buffer can get an address with 0x...f80,
then the same error happens. If I make it to 0x...f40 or 0x....fc0,
everything will be still fine. So I tend to believe that the
0x..f80 address cause the silicon to behave abnormally.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=70761
Cc: Eric Dumazet <edumazet@google.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: Jarod Wilson <jarod@redhat.com>
Signed-off-by: Feng Tang <feng.tang@intel.com>
Tested-by: Ole Lukoie <olelukoie@mail.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/atheros/alx/alx.h  |  4 +++
 drivers/net/ethernet/atheros/alx/main.c | 48 ++++++++++++++++++++++++++++++++-
 2 files changed, 51 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/atheros/alx/alx.h b/drivers/net/ethernet/atheros/alx/alx.h
index 8fc93c5..d02c424 100644
--- a/drivers/net/ethernet/atheros/alx/alx.h
+++ b/drivers/net/ethernet/atheros/alx/alx.h
@@ -96,6 +96,10 @@ struct alx_priv {
 	unsigned int rx_ringsz;
 	unsigned int rxbuf_size;
 
+	struct page  *rx_page;
+	unsigned int rx_page_offset;
+	unsigned int rx_frag_size;
+
 	struct napi_struct napi;
 	struct alx_tx_queue txq;
 	struct alx_rx_queue rxq;
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index 55b118e..8611811 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -70,6 +70,35 @@ static void alx_free_txbuf(struct alx_priv *alx, int entry)
 	}
 }
 
+static struct sk_buff *alx_alloc_skb(struct alx_priv *alx, gfp_t gfp)
+{
+	struct sk_buff *skb;
+	struct page *page;
+
+	if (alx->rx_frag_size > PAGE_SIZE)
+		return __netdev_alloc_skb(alx->dev, alx->rxbuf_size, gfp);
+
+	page = alx->rx_page;
+	if (!page) {
+		alx->rx_page = page = alloc_page(gfp);
+		if (unlikely(!page))
+			return NULL;
+		alx->rx_page_offset = 0;
+	}
+
+	skb = build_skb(page_address(page) + alx->rx_page_offset,
+			alx->rx_frag_size);
+	if (likely(skb)) {
+		alx->rx_page_offset += alx->rx_frag_size;
+		if (alx->rx_page_offset >= PAGE_SIZE)
+			alx->rx_page = NULL;
+		else
+			get_page(page);
+	}
+	return skb;
+}
+
+
 static int alx_refill_rx_ring(struct alx_priv *alx, gfp_t gfp)
 {
 	struct alx_rx_queue *rxq = &alx->rxq;
@@ -86,7 +115,7 @@ static int alx_refill_rx_ring(struct alx_priv *alx, gfp_t gfp)
 	while (!cur_buf->skb && next != rxq->read_idx) {
 		struct alx_rfd *rfd = &rxq->rfd[cur];
 
-		skb = __netdev_alloc_skb(alx->dev, alx->rxbuf_size, gfp);
+		skb = alx_alloc_skb(alx, gfp);
 		if (!skb)
 			break;
 		dma = dma_map_single(&alx->hw.pdev->dev,
@@ -124,6 +153,7 @@ static int alx_refill_rx_ring(struct alx_priv *alx, gfp_t gfp)
 		alx_write_mem16(&alx->hw, ALX_RFD_PIDX, cur);
 	}
 
+
 	return count;
 }
 
@@ -592,6 +622,11 @@ static void alx_free_rings(struct alx_priv *alx)
 	kfree(alx->txq.bufs);
 	kfree(alx->rxq.bufs);
 
+	if (alx->rx_page) {
+		put_page(alx->rx_page);
+		alx->rx_page = NULL;
+	}
+
 	dma_free_coherent(&alx->hw.pdev->dev,
 			  alx->descmem.size,
 			  alx->descmem.virt,
@@ -646,6 +681,7 @@ static int alx_request_irq(struct alx_priv *alx)
 				  alx->dev->name, alx);
 		if (!err)
 			goto out;
+
 		/* fall back to legacy interrupt */
 		pci_disable_msi(alx->hw.pdev);
 	}
@@ -689,6 +725,7 @@ static int alx_init_sw(struct alx_priv *alx)
 	struct pci_dev *pdev = alx->hw.pdev;
 	struct alx_hw *hw = &alx->hw;
 	int err;
+	unsigned int head_size;
 
 	err = alx_identify_hw(alx);
 	if (err) {
@@ -704,7 +741,12 @@ static int alx_init_sw(struct alx_priv *alx)
 
 	hw->smb_timer = 400;
 	hw->mtu = alx->dev->mtu;
+
 	alx->rxbuf_size = ALX_MAX_FRAME_LEN(hw->mtu);
+	head_size = SKB_DATA_ALIGN(alx->rxbuf_size + NET_SKB_PAD) +
+		    SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+	alx->rx_frag_size = roundup_pow_of_two(head_size);
+
 	alx->tx_ringsz = 256;
 	alx->rx_ringsz = 512;
 	hw->imt = 200;
@@ -806,6 +848,7 @@ static int alx_change_mtu(struct net_device *netdev, int mtu)
 {
 	struct alx_priv *alx = netdev_priv(netdev);
 	int max_frame = ALX_MAX_FRAME_LEN(mtu);
+	unsigned int head_size;
 
 	if ((max_frame < ALX_MIN_FRAME_SIZE) ||
 	    (max_frame > ALX_MAX_FRAME_SIZE))
@@ -817,6 +860,9 @@ static int alx_change_mtu(struct net_device *netdev, int mtu)
 	netdev->mtu = mtu;
 	alx->hw.mtu = mtu;
 	alx->rxbuf_size = max(max_frame, ALX_DEF_RXBUF_SIZE);
+	head_size = SKB_DATA_ALIGN(alx->rxbuf_size + NET_SKB_PAD) +
+		    SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+	alx->rx_frag_size = roundup_pow_of_two(head_size);
 	netdev_update_features(netdev);
 	if (netif_running(netdev))
 		alx_reinit(alx);
-- 
2.1.0


From 1e794be2bc0e67f4a5075ecdd80169ced22cc25b Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Thu, 26 May 2016 00:40:23 +0200
Subject: [PATCH 13/23] net: stmmac: Fix incorrect memcpy source memory

[ Upstream commit 643d60bf575daaba93c1ac0d0e1c4b1d4ded1f75 ]

The memcpy() currently copies mdio_bus_data into new_bus->irq, which
makes no sense, since the mdio_bus_data structure contains more than
just irqs. The code was likely supposed to copy mdio_bus_data->irqs
into the new_bus->irq instead, so fix this.

Fixes: e7f4dc3536a4 ("mdio: Move allocation of interrupts into core")
Signed-off-by: Marek Vasut <marex@denx.de>
Cc: David S. Miller <davem@davemloft.net>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index efb54f3..ff15da4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -217,7 +217,7 @@ int stmmac_mdio_register(struct net_device *ndev)
 		return -ENOMEM;
 
 	if (mdio_bus_data->irqs)
-		memcpy(new_bus->irq, mdio_bus_data, sizeof(new_bus->irq));
+		memcpy(new_bus->irq, mdio_bus_data->irqs, sizeof(new_bus->irq));
 
 #ifdef CONFIG_OF
 	if (priv->device->of_node)
-- 
2.1.0


From 6132566c6400c8df6cdfd94cc504e36b8436812d Mon Sep 17 00:00:00 2001
From: Chen Haiquan <oc@yunify.com>
Date: Fri, 27 May 2016 10:49:11 +0800
Subject: [PATCH 14/23] vxlan: Accept user specified MTU value when create new
 vxlan link

[ Upstream commit ce577668a426c6a9e2470a09dcd07fbd6e45272a ]

When create a new vxlan link, example:
  ip link add vtap mtu 1440 type vxlan vni 1 dev eth0

The argument "mtu" has no effect, because it is not set to conf->mtu. The
default value is used in vxlan_dev_configure function.

This problem was introduced by commit 0dfbdf4102b9 (vxlan: Factor out device
configuration).

Fixes: 0dfbdf4102b9 (vxlan: Factor out device configuration)
Signed-off-by:  Chen Haiquan <oc@yunify.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index b4eb55e..01769b8 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -3008,6 +3008,9 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev,
 	if (data[IFLA_VXLAN_REMCSUM_NOPARTIAL])
 		conf.flags |= VXLAN_F_REMCSUM_NOPARTIAL;
 
+	if (tb[IFLA_MTU])
+		conf.mtu = nla_get_u32(tb[IFLA_MTU]);
+
 	err = vxlan_dev_configure(src_net, dev, &conf);
 	switch (err) {
 	case -ENODEV:
-- 
2.1.0


From c2e1f0f2f8a8476fde450cdf5fe70c612852b17b Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Sat, 4 Jun 2016 20:50:59 +0200
Subject: [PATCH 15/23] bpf, trace: use READ_ONCE for retrieving file ptr

[ Upstream commit 5b6c1b4d46b0dae4edea636a776d09f2064f4cd7 ]

In bpf_perf_event_read() and bpf_perf_event_output(), we must use
READ_ONCE() for fetching the struct file pointer, which could get
updated concurrently, so we must prevent the compiler from potential
refetching.

We already do this with tail calls for fetching the related bpf_prog,
but not so on stored perf events. Semantics for both are the same
with regards to updates.

Fixes: a43eec304259 ("bpf: introduce bpf_perf_event_output() helper")
Fixes: 35578d798400 ("bpf: Implement function bpf_perf_event_read() that get the selected hardware PMU conuter")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/trace/bpf_trace.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 326a75e..0586e78 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -196,7 +196,7 @@ static u64 bpf_perf_event_read(u64 r1, u64 index, u64 r3, u64 r4, u64 r5)
 	if (unlikely(index >= array->map.max_entries))
 		return -E2BIG;
 
-	file = (struct file *)array->ptrs[index];
+	file = READ_ONCE(array->ptrs[index]);
 	if (unlikely(!file))
 		return -ENOENT;
 
@@ -240,7 +240,7 @@ static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 index, u64 r4, u64 size)
 	if (unlikely(index >= array->map.max_entries))
 		return -E2BIG;
 
-	file = (struct file *)array->ptrs[index];
+	file = READ_ONCE(array->ptrs[index]);
 	if (unlikely(!file))
 		return -ENOENT;
 
-- 
2.1.0


From cb9042922d3704b63c154da0a191ea0f49a05e25 Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Mon, 6 Jun 2016 15:07:18 -0700
Subject: [PATCH 16/23] tcp: record TLP and ER timer stats in v6 stats

[ Upstream commit ce3cf4ec0305919fc69a972f6c2b2efd35d36abc ]

The v6 tcp stats scan do not provide TLP and ER timer information
correctly like the v4 version . This patch fixes that.

Fixes: 6ba8a3b19e76 ("tcp: Tail loss probe (TLP)")
Fixes: eed530b6c676 ("tcp: early retransmit")
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/tcp_ipv6.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 5c8c842..29cfab3 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1707,7 +1707,9 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
 	destp = ntohs(inet->inet_dport);
 	srcp  = ntohs(inet->inet_sport);
 
-	if (icsk->icsk_pending == ICSK_TIME_RETRANS) {
+	if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
+	    icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
+	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
 		timer_active	= 1;
 		timer_expires	= icsk->icsk_timeout;
 	} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
-- 
2.1.0


From bf8974024d96ce228cc9edfb10dc0ae82ac1f88b Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Tue, 7 Jun 2016 19:14:17 +0900
Subject: [PATCH 17/23] bridge: Don't insert unnecessary local fdb entry on
 changing mac address

[ Upstream commit 0b148def403153a4d1565f1640356cb78ce5109f ]

The missing br_vlan_should_use() test caused creation of an unneeded
local fdb entry on changing mac address of a bridge device when there is
a vlan which is configured on a bridge port but not on the bridge
device.

Fixes: 2594e9064a57 ("bridge: vlan: add per-vlan struct and move to rhashtables")
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_fdb.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index dcea4f4..c18080a 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -279,6 +279,8 @@ void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr)
 	 * change from under us.
 	 */
 	list_for_each_entry(v, &vg->vlan_list, vlist) {
+		if (!br_vlan_should_use(v))
+			continue;
 		f = __br_fdb_get(br, br->dev->dev_addr, v->vid);
 		if (f && f->is_local && !f->dst)
 			fdb_delete_local(br, NULL, f);
-- 
2.1.0


From 2986034011de8fd605488908e572b07bc05d2f70 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Wed, 8 Jun 2016 12:59:17 +0200
Subject: [PATCH 18/23] l2tp: fix configuration passed to
 setup_udp_tunnel_sock()

[ Upstream commit a5c5e2da8551eb69e5d5d09d51d526140b5db9fb ]

Unused fields of udp_cfg must be all zeros. Otherwise
setup_udp_tunnel_sock() fills ->gro_receive and ->gro_complete
callbacks with garbage, eventually resulting in panic when used by
udp_gro_receive().

[   72.694123] BUG: unable to handle kernel paging request at ffff880033f87d78
[   72.695518] IP: [<ffff880033f87d78>] 0xffff880033f87d78
[   72.696530] PGD 26e2067 PUD 26e3067 PMD 342ed063 PTE 8000000033f87163
[   72.696530] Oops: 0011 [#1] SMP KASAN
[   72.696530] Modules linked in: l2tp_ppp l2tp_netlink l2tp_core ip6_udp_tunnel udp_tunnel pptp gre pppox ppp_generic slhc crc32c_intel ghash_clmulni_intel jitterentropy_rng sha256_generic hmac drbg ansi_cprng aesni_intel evdev aes_x86_64 ablk_helper cryptd lrw gf128mul glue_helper serio_raw acpi_cpufreq button proc\
essor ext4 crc16 jbd2 mbcache virtio_blk virtio_net virtio_pci virtio_ring virtio
[   72.696530] CPU: 3 PID: 0 Comm: swapper/3 Not tainted 4.7.0-rc1 #1
[   72.696530] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Debian-1.8.2-1 04/01/2014
[   72.696530] task: ffff880035b59700 ti: ffff880035b70000 task.ti: ffff880035b70000
[   72.696530] RIP: 0010:[<ffff880033f87d78>]  [<ffff880033f87d78>] 0xffff880033f87d78
[   72.696530] RSP: 0018:ffff880035f87bc0  EFLAGS: 00010246
[   72.696530] RAX: ffffed000698f996 RBX: ffff88003326b840 RCX: ffffffff814cc823
[   72.696530] RDX: ffff88003326b840 RSI: ffff880033e48038 RDI: ffff880034c7c780
[   72.696530] RBP: ffff880035f87c18 R08: 000000000000a506 R09: 0000000000000000
[   72.696530] R10: ffff880035f87b38 R11: ffff880034b9344d R12: 00000000ebfea715
[   72.696530] R13: 0000000000000000 R14: ffff880034c7c780 R15: 0000000000000000
[   72.696530] FS:  0000000000000000(0000) GS:ffff880035f80000(0000) knlGS:0000000000000000
[   72.696530] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   72.696530] CR2: ffff880033f87d78 CR3: 0000000033c98000 CR4: 00000000000406a0
[   72.696530] Stack:
[   72.696530]  ffffffff814cc834 ffff880034b93468 0000001481416818 ffff88003326b874
[   72.696530]  ffff880034c7ccb0 ffff880033e48038 ffff88003326b840 ffff880034b93462
[   72.696530]  ffff88003326b88a ffff88003326b88c ffff880034b93468 ffff880035f87c70
[   72.696530] Call Trace:
[   72.696530]  <IRQ>
[   72.696530]  [<ffffffff814cc834>] ? udp_gro_receive+0x1c6/0x1f9
[   72.696530]  [<ffffffff814ccb1c>] udp4_gro_receive+0x2b5/0x310
[   72.696530]  [<ffffffff814d989b>] inet_gro_receive+0x4a3/0x4cd
[   72.696530]  [<ffffffff81431b32>] dev_gro_receive+0x584/0x7a3
[   72.696530]  [<ffffffff810adf7a>] ? __lock_is_held+0x29/0x64
[   72.696530]  [<ffffffff814321f7>] napi_gro_receive+0x124/0x21d
[   72.696530]  [<ffffffffa000b145>] virtnet_receive+0x8df/0x8f6 [virtio_net]
[   72.696530]  [<ffffffffa000b27e>] virtnet_poll+0x1d/0x8d [virtio_net]
[   72.696530]  [<ffffffff81431350>] net_rx_action+0x15b/0x3b9
[   72.696530]  [<ffffffff815893d6>] __do_softirq+0x216/0x546
[   72.696530]  [<ffffffff81062392>] irq_exit+0x49/0xb6
[   72.696530]  [<ffffffff81588e9a>] do_IRQ+0xe2/0xfa
[   72.696530]  [<ffffffff81587a49>] common_interrupt+0x89/0x89
[   72.696530]  <EOI>
[   72.696530]  [<ffffffff810b05df>] ? trace_hardirqs_on_caller+0x229/0x270
[   72.696530]  [<ffffffff8102b3c7>] ? default_idle+0x1c/0x2d
[   72.696530]  [<ffffffff8102b3c5>] ? default_idle+0x1a/0x2d
[   72.696530]  [<ffffffff8102bb8c>] arch_cpu_idle+0xa/0xc
[   72.696530]  [<ffffffff810a6c39>] default_idle_call+0x1a/0x1c
[   72.696530]  [<ffffffff810a6d96>] cpu_startup_entry+0x15b/0x20f
[   72.696530]  [<ffffffff81039a81>] start_secondary+0x12c/0x133
[   72.696530] Code: ff ff ff ff ff ff ff ff ff ff 7f ff ff ff ff ff ff ff 7f 00 7e f8 33 00 88 ff ff 6d 61 58 81 ff ff ff ff 5e de 0a 81 ff ff ff ff <00> 5c e2 34 00 88 ff ff 00 00 00 00 00 00 00 00 00 00 00 00 00
[   72.696530] RIP  [<ffff880033f87d78>] 0xffff880033f87d78
[   72.696530]  RSP <ffff880035f87bc0>
[   72.696530] CR2: ffff880033f87d78
[   72.696530] ---[ end trace ad7758b9a1dccf99 ]---
[   72.696530] Kernel panic - not syncing: Fatal exception in interrupt
[   72.696530] Kernel Offset: disabled
[   72.696530] ---[ end Kernel panic - not syncing: Fatal exception in interrupt

v2: use empty initialiser instead of "{ NULL }" to avoid relying on
    first field's type.

Fixes: 38fd2af24fcf ("udp: Add socket based GRO and config")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index afca2eb..ec17cbe 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1581,7 +1581,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
 	/* Mark socket as an encapsulation socket. See net/ipv4/udp.c */
 	tunnel->encap = encap;
 	if (encap == L2TP_ENCAPTYPE_UDP) {
-		struct udp_tunnel_sock_cfg udp_cfg;
+		struct udp_tunnel_sock_cfg udp_cfg = { };
 
 		udp_cfg.sk_user_data = tunnel;
 		udp_cfg.encap_type = UDP_ENCAP_L2TPINUDP;
-- 
2.1.0


From e2264cfedf777ead870797b621fea0f9f3bd6027 Mon Sep 17 00:00:00 2001
From: Jakub Sitnicki <jkbs@redhat.com>
Date: Wed, 8 Jun 2016 15:13:34 +0200
Subject: [PATCH 19/23] ipv6: Skip XFRM lookup if dst_entry in socket cache is
 valid

[ Upstream commit 00bc0ef5880dc7b82f9c320dead4afaad48e47be ]

At present we perform an xfrm_lookup() for each UDPv6 message we
send. The lookup involves querying the flow cache (flow_cache_lookup)
and, in case of a cache miss, creating an XFRM bundle.

If we miss the flow cache, we can end up creating a new bundle and
deriving the path MTU (xfrm_init_pmtu) from on an already transformed
dst_entry, which we pass from the socket cache (sk->sk_dst_cache) down
to xfrm_lookup(). This can happen only if we're caching the dst_entry
in the socket, that is when we're using a connected UDP socket.

To put it another way, the path MTU shrinks each time we miss the flow
cache, which later on leads to incorrectly fragmented payload. It can
be observed with ESPv6 in transport mode:

  1) Set up a transformation and lower the MTU to trigger fragmentation
    # ip xfrm policy add dir out src ::1 dst ::1 \
      tmpl src ::1 dst ::1 proto esp spi 1
    # ip xfrm state add src ::1 dst ::1 \
      proto esp spi 1 enc 'aes' 0x0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b
    # ip link set dev lo mtu 1500

  2) Monitor the packet flow and set up an UDP sink
    # tcpdump -ni lo -ttt &
    # socat udp6-listen:12345,fork /dev/null &

  3) Send a datagram that needs fragmentation with a connected socket
    # perl -e 'print "@" x 1470 | socat - udp6:[::1]:12345
    2016/06/07 18:52:52 socat[724] E read(3, 0x555bb3d5ba00, 8192): Protocol error
    00:00:00.000000 IP6 ::1 > ::1: frag (0|1448) ESP(spi=0x00000001,seq=0x2), length 1448
    00:00:00.000014 IP6 ::1 > ::1: frag (1448|32)
    00:00:00.000050 IP6 ::1 > ::1: ESP(spi=0x00000001,seq=0x3), length 1272
    (^ ICMPv6 Parameter Problem)
    00:00:00.000022 IP6 ::1 > ::1: ESP(spi=0x00000001,seq=0x5), length 136

  4) Compare it to a non-connected socket
    # perl -e 'print "@" x 1500' | socat - udp6-sendto:[::1]:12345
    00:00:40.535488 IP6 ::1 > ::1: frag (0|1448) ESP(spi=0x00000001,seq=0x6), length 1448
    00:00:00.000010 IP6 ::1 > ::1: frag (1448|64)

What happens in step (3) is:

  1) when connecting the socket in __ip6_datagram_connect(), we
     perform an XFRM lookup, miss the flow cache, create an XFRM
     bundle, and cache the destination,

  2) afterwards, when sending the datagram, we perform an XFRM lookup,
     again, miss the flow cache (due to mismatch of flowi6_iif and
     flowi6_oif, which is an issue of its own), and recreate an XFRM
     bundle based on the cached (and already transformed) destination.

To prevent the recreation of an XFRM bundle, avoid an XFRM lookup
altogether whenever we already have a destination entry cached in the
socket. This prevents the path MTU shrinkage and brings us on par with
UDPv4.

The fix also benefits connected PINGv6 sockets, another user of
ip6_sk_dst_lookup_flow(), who also suffer messages being transformed
twice.

Joint work with Hannes Frederic Sowa.

Reported-by: Jan Tluka <jtluka@redhat.com>
Signed-off-by: Jakub Sitnicki <jkbs@redhat.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_output.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 2a6606c..f28e940 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1072,17 +1072,12 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
 					 const struct in6_addr *final_dst)
 {
 	struct dst_entry *dst = sk_dst_check(sk, inet6_sk(sk)->dst_cookie);
-	int err;
 
 	dst = ip6_sk_dst_check(sk, dst, fl6);
+	if (!dst)
+		dst = ip6_dst_lookup_flow(sk, fl6, final_dst);
 
-	err = ip6_dst_lookup_tail(sock_net(sk), sk, &dst, fl6);
-	if (err)
-		return ERR_PTR(err);
-	if (final_dst)
-		fl6->daddr = *final_dst;
-
-	return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
+	return dst;
 }
 EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow);
 
-- 
2.1.0


From 7ecb498931aba6bde0311b1f1d778d2e05cec2dc Mon Sep 17 00:00:00 2001
From: Giuseppe CAVALLARO <peppe.cavallaro@st.com>
Date: Mon, 23 May 2016 15:17:42 +0200
Subject: [PATCH 20/23] Revert "stmmac: Fix 'eth0: No PHY found' regression"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit d7e944c8ddc0983640a9a32868fb217485d12ca2 ]

This reverts commit 88f8b1bb41c6208f81b6a480244533ded7b59493.
due to problems on GeekBox and Banana Pi M1 board when
connected to a real transceiver instead of a switch via
fixed-link.

Signed-off-by: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Gabriel Fernandez <gabriel.fernandez@linaro.org>
Cc: Andreas Färber <afaerber@suse.de>
Cc: Frank Schäfer <fschaefer.oss@googlemail.com>
Cc: Dinh Nguyen <dinh.linux@gmail.com>
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c     | 11 ++++++++++-
 drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c |  9 +--------
 2 files changed, 11 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index ff15da4..601bfb21 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -199,12 +199,21 @@ int stmmac_mdio_register(struct net_device *ndev)
 	struct stmmac_priv *priv = netdev_priv(ndev);
 	struct stmmac_mdio_bus_data *mdio_bus_data = priv->plat->mdio_bus_data;
 	int addr, found;
-	struct device_node *mdio_node = priv->plat->mdio_node;
+	struct device_node *mdio_node = NULL;
+	struct device_node *child_node = NULL;
 
 	if (!mdio_bus_data)
 		return 0;
 
 	if (IS_ENABLED(CONFIG_OF)) {
+		for_each_child_of_node(priv->device->of_node, child_node) {
+			if (of_device_is_compatible(child_node,
+						    "snps,dwmac-mdio")) {
+				mdio_node = child_node;
+				break;
+			}
+		}
+
 		if (mdio_node) {
 			netdev_dbg(ndev, "FOUND MDIO subnode\n");
 		} else {
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 4514ba7..6a52fa1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -110,7 +110,6 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac)
 	struct device_node *np = pdev->dev.of_node;
 	struct plat_stmmacenet_data *plat;
 	struct stmmac_dma_cfg *dma_cfg;
-	struct device_node *child_node = NULL;
 
 	plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL);
 	if (!plat)
@@ -141,19 +140,13 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac)
 		plat->phy_node = of_node_get(np);
 	}
 
-	for_each_child_of_node(np, child_node)
-		if (of_device_is_compatible(child_node,	"snps,dwmac-mdio")) {
-			plat->mdio_node = child_node;
-			break;
-		}
-
 	/* "snps,phy-addr" is not a standard property. Mark it as deprecated
 	 * and warn of its use. Remove this when phy node support is added.
 	 */
 	if (of_property_read_u32(np, "snps,phy-addr", &plat->phy_addr) == 0)
 		dev_warn(&pdev->dev, "snps,phy-addr property is deprecated\n");
 
-	if ((plat->phy_node && !of_phy_is_fixed_link(np)) || !plat->mdio_node)
+	if ((plat->phy_node && !of_phy_is_fixed_link(np)) || plat->phy_bus_name)
 		plat->mdio_bus_data = NULL;
 	else
 		plat->mdio_bus_data =
-- 
2.1.0


From 578c4502db915331ff1da51ddbbddacb043370a0 Mon Sep 17 00:00:00 2001
From: Giuseppe CAVALLARO <peppe.cavallaro@st.com>
Date: Mon, 23 May 2016 15:17:43 +0200
Subject: [PATCH 21/23] stmmac: fix MDIO settings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit a7657f128c279ae5796ab2ca7d04a7819f4259f0 ]

Initially the phy_bus_name was added to manipulate the
driver name but it was recently just used to manage the
fixed-link and then to take some decision at run-time.
So the patch uses the is_pseudo_fixed_link and removes
the phy_bus_name variable not necessary anymore.

The driver can manage the mdio registration by using phy-handle,
dwmac-mdio and own parameter e.g. snps,phy-addr.
This patch takes care about all these possible configurations
and fixes the mdio registration in case of there is a real
transceiver or a switch (that needs to be managed by using
fixed-link).

Signed-off-by: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Reviewed-by: Andreas Färber <afaerber@suse.de>
Tested-by: Frank Schäfer <fschaefer.oss@googlemail.com>
Cc: Gabriel Fernandez <gabriel.fernandez@linaro.org>
Cc: Dinh Nguyen <dinh.linux@gmail.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Phil Reid <preid@electromag.com.au>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c  | 11 +--
 drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c  | 19 +----
 .../net/ethernet/stmicro/stmmac/stmmac_platform.c  | 84 +++++++++++++++++-----
 3 files changed, 70 insertions(+), 44 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index c21015b..389d7d0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -271,7 +271,6 @@ static void stmmac_eee_ctrl_timer(unsigned long arg)
  */
 bool stmmac_eee_init(struct stmmac_priv *priv)
 {
-	char *phy_bus_name = priv->plat->phy_bus_name;
 	unsigned long flags;
 	bool ret = false;
 
@@ -283,7 +282,7 @@ bool stmmac_eee_init(struct stmmac_priv *priv)
 		goto out;
 
 	/* Never init EEE in case of a switch is attached */
-	if (phy_bus_name && (!strcmp(phy_bus_name, "fixed")))
+	if (priv->phydev->is_pseudo_fixed_link)
 		goto out;
 
 	/* MAC core supports the EEE feature. */
@@ -820,12 +819,8 @@ static int stmmac_init_phy(struct net_device *dev)
 		phydev = of_phy_connect(dev, priv->plat->phy_node,
 					&stmmac_adjust_link, 0, interface);
 	} else {
-		if (priv->plat->phy_bus_name)
-			snprintf(bus_id, MII_BUS_ID_SIZE, "%s-%x",
-				 priv->plat->phy_bus_name, priv->plat->bus_id);
-		else
-			snprintf(bus_id, MII_BUS_ID_SIZE, "stmmac-%x",
-				 priv->plat->bus_id);
+		snprintf(bus_id, MII_BUS_ID_SIZE, "stmmac-%x",
+			 priv->plat->bus_id);
 
 		snprintf(phy_id_fmt, MII_BUS_ID_SIZE + 3, PHY_ID_FMT, bus_id,
 			 priv->plat->phy_addr);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index 601bfb21..2fec75c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -198,29 +198,12 @@ int stmmac_mdio_register(struct net_device *ndev)
 	struct mii_bus *new_bus;
 	struct stmmac_priv *priv = netdev_priv(ndev);
 	struct stmmac_mdio_bus_data *mdio_bus_data = priv->plat->mdio_bus_data;
+	struct device_node *mdio_node = priv->plat->mdio_node;
 	int addr, found;
-	struct device_node *mdio_node = NULL;
-	struct device_node *child_node = NULL;
 
 	if (!mdio_bus_data)
 		return 0;
 
-	if (IS_ENABLED(CONFIG_OF)) {
-		for_each_child_of_node(priv->device->of_node, child_node) {
-			if (of_device_is_compatible(child_node,
-						    "snps,dwmac-mdio")) {
-				mdio_node = child_node;
-				break;
-			}
-		}
-
-		if (mdio_node) {
-			netdev_dbg(ndev, "FOUND MDIO subnode\n");
-		} else {
-			netdev_warn(ndev, "No MDIO subnode found\n");
-		}
-	}
-
 	new_bus = mdiobus_alloc();
 	if (new_bus == NULL)
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 6a52fa1..190fb6d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -96,6 +96,69 @@ static int dwmac1000_validate_ucast_entries(int ucast_entries)
 }
 
 /**
+ * stmmac_dt_phy - parse device-tree driver parameters to allocate PHY resources
+ * @plat: driver data platform structure
+ * @np: device tree node
+ * @dev: device pointer
+ * Description:
+ * The mdio bus will be allocated in case of a phy transceiver is on board;
+ * it will be NULL if the fixed-link is configured.
+ * If there is the "snps,dwmac-mdio" sub-node the mdio will be allocated
+ * in any case (for DSA, mdio must be registered even if fixed-link).
+ * The table below sums the supported configurations:
+ *	-------------------------------
+ *	snps,phy-addr	|     Y
+ *	-------------------------------
+ *	phy-handle	|     Y
+ *	-------------------------------
+ *	fixed-link	|     N
+ *	-------------------------------
+ *	snps,dwmac-mdio	|
+ *	  even if	|     Y
+ *	fixed-link	|
+ *	-------------------------------
+ *
+ * It returns 0 in case of success otherwise -ENODEV.
+ */
+static int stmmac_dt_phy(struct plat_stmmacenet_data *plat,
+			 struct device_node *np, struct device *dev)
+{
+	bool mdio = true;
+
+	/* If phy-handle property is passed from DT, use it as the PHY */
+	plat->phy_node = of_parse_phandle(np, "phy-handle", 0);
+	if (plat->phy_node)
+		dev_dbg(dev, "Found phy-handle subnode\n");
+
+	/* If phy-handle is not specified, check if we have a fixed-phy */
+	if (!plat->phy_node && of_phy_is_fixed_link(np)) {
+		if ((of_phy_register_fixed_link(np) < 0))
+			return -ENODEV;
+
+		dev_dbg(dev, "Found fixed-link subnode\n");
+		plat->phy_node = of_node_get(np);
+		mdio = false;
+	}
+
+	/* If snps,dwmac-mdio is passed from DT, always register the MDIO */
+	for_each_child_of_node(np, plat->mdio_node) {
+		if (of_device_is_compatible(plat->mdio_node, "snps,dwmac-mdio"))
+			break;
+	}
+
+	if (plat->mdio_node) {
+		dev_dbg(dev, "Found MDIO subnode\n");
+		mdio = true;
+	}
+
+	if (mdio)
+		plat->mdio_bus_data =
+			devm_kzalloc(dev, sizeof(struct stmmac_mdio_bus_data),
+				     GFP_KERNEL);
+	return 0;
+}
+
+/**
  * stmmac_probe_config_dt - parse device-tree driver parameters
  * @pdev: platform_device structure
  * @plat: driver data platform structure
@@ -129,30 +192,15 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac)
 	/* Default to phy auto-detection */
 	plat->phy_addr = -1;
 
-	/* If we find a phy-handle property, use it as the PHY */
-	plat->phy_node = of_parse_phandle(np, "phy-handle", 0);
-
-	/* If phy-handle is not specified, check if we have a fixed-phy */
-	if (!plat->phy_node && of_phy_is_fixed_link(np)) {
-		if ((of_phy_register_fixed_link(np) < 0))
-			return ERR_PTR(-ENODEV);
-
-		plat->phy_node = of_node_get(np);
-	}
-
 	/* "snps,phy-addr" is not a standard property. Mark it as deprecated
 	 * and warn of its use. Remove this when phy node support is added.
 	 */
 	if (of_property_read_u32(np, "snps,phy-addr", &plat->phy_addr) == 0)
 		dev_warn(&pdev->dev, "snps,phy-addr property is deprecated\n");
 
-	if ((plat->phy_node && !of_phy_is_fixed_link(np)) || plat->phy_bus_name)
-		plat->mdio_bus_data = NULL;
-	else
-		plat->mdio_bus_data =
-			devm_kzalloc(&pdev->dev,
-				     sizeof(struct stmmac_mdio_bus_data),
-				     GFP_KERNEL);
+	/* To Configure PHY by using all device-tree supported properties */
+	if (stmmac_dt_phy(plat, np, &pdev->dev))
+		return ERR_PTR(-ENODEV);
 
 	of_property_read_u32(np, "tx-fifo-depth", &plat->tx_fifo_size);
 
-- 
2.1.0


From 332ceed0c7f4a8b1fe36e3ffe0ccbcb33674410a Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Wed, 25 May 2016 09:35:30 -0700
Subject: [PATCH 22/23] net: vrf: Fix dst reference counting

[ Upstream commit 9ab179d83b4e31ea277a123492e419067c2f129a ]

Vivek reported a kernel exception deleting a VRF with an active
connection through it. The root cause is that the socket has a cached
reference to a dst that is destroyed. Converting the dst_destroy to
dst_release and letting proper reference counting kick in does not
work as the dst has a reference to the device which needs to be released
as well.

I talked to Hannes about this at netdev and he pointed out the ipv4 and
ipv6 dst handling has dst_ifdown for just this scenario. Rather than
continuing with the reinvented dst wheel in VRF just remove it and
leverage the ipv4 and ipv6 versions.

Fixes: 193125dbd8eb2 ("net: Introduce VRF device driver")
Fixes: 35402e3136634 ("net: Add IPv6 support to VRF device")

Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c       | 177 +++++-------------------------------------------
 include/net/ip6_route.h |   3 +
 include/net/route.h     |   3 +
 net/ipv4/route.c        |   7 +-
 net/ipv6/route.c        |   7 +-
 5 files changed, 30 insertions(+), 167 deletions(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index bdcf617..d8197f9 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -61,41 +61,6 @@ struct pcpu_dstats {
 	struct u64_stats_sync	syncp;
 };
 
-static struct dst_entry *vrf_ip_check(struct dst_entry *dst, u32 cookie)
-{
-	return dst;
-}
-
-static int vrf_ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb)
-{
-	return ip_local_out(net, sk, skb);
-}
-
-static unsigned int vrf_v4_mtu(const struct dst_entry *dst)
-{
-	/* TO-DO: return max ethernet size? */
-	return dst->dev->mtu;
-}
-
-static void vrf_dst_destroy(struct dst_entry *dst)
-{
-	/* our dst lives forever - or until the device is closed */
-}
-
-static unsigned int vrf_default_advmss(const struct dst_entry *dst)
-{
-	return 65535 - 40;
-}
-
-static struct dst_ops vrf_dst_ops = {
-	.family		= AF_INET,
-	.local_out	= vrf_ip_local_out,
-	.check		= vrf_ip_check,
-	.mtu		= vrf_v4_mtu,
-	.destroy	= vrf_dst_destroy,
-	.default_advmss	= vrf_default_advmss,
-};
-
 /* neighbor handling is done with actual device; do not want
  * to flip skb->dev for those ndisc packets. This really fails
  * for multiple next protocols (e.g., NEXTHDR_HOP). But it is
@@ -350,46 +315,6 @@ static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev)
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
-static struct dst_entry *vrf_ip6_check(struct dst_entry *dst, u32 cookie)
-{
-	return dst;
-}
-
-static struct dst_ops vrf_dst_ops6 = {
-	.family		= AF_INET6,
-	.local_out	= ip6_local_out,
-	.check		= vrf_ip6_check,
-	.mtu		= vrf_v4_mtu,
-	.destroy	= vrf_dst_destroy,
-	.default_advmss	= vrf_default_advmss,
-};
-
-static int init_dst_ops6_kmem_cachep(void)
-{
-	vrf_dst_ops6.kmem_cachep = kmem_cache_create("vrf_ip6_dst_cache",
-						     sizeof(struct rt6_info),
-						     0,
-						     SLAB_HWCACHE_ALIGN,
-						     NULL);
-
-	if (!vrf_dst_ops6.kmem_cachep)
-		return -ENOMEM;
-
-	return 0;
-}
-
-static void free_dst_ops6_kmem_cachep(void)
-{
-	kmem_cache_destroy(vrf_dst_ops6.kmem_cachep);
-}
-
-static int vrf_input6(struct sk_buff *skb)
-{
-	skb->dev->stats.rx_errors++;
-	kfree_skb(skb);
-	return 0;
-}
-
 /* modelled after ip6_finish_output2 */
 static int vrf_finish_output6(struct net *net, struct sock *sk,
 			      struct sk_buff *skb)
@@ -430,67 +355,34 @@ static int vrf_output6(struct net *net, struct sock *sk, struct sk_buff *skb)
 			    !(IP6CB(skb)->flags & IP6SKB_REROUTED));
 }
 
-static void vrf_rt6_destroy(struct net_vrf *vrf)
+static void vrf_rt6_release(struct net_vrf *vrf)
 {
-	dst_destroy(&vrf->rt6->dst);
-	free_percpu(vrf->rt6->rt6i_pcpu);
+	dst_release(&vrf->rt6->dst);
 	vrf->rt6 = NULL;
 }
 
 static int vrf_rt6_create(struct net_device *dev)
 {
 	struct net_vrf *vrf = netdev_priv(dev);
-	struct dst_entry *dst;
+	struct net *net = dev_net(dev);
 	struct rt6_info *rt6;
-	int cpu;
 	int rc = -ENOMEM;
 
-	rt6 = dst_alloc(&vrf_dst_ops6, dev, 0,
-			DST_OBSOLETE_NONE,
-			(DST_HOST | DST_NOPOLICY | DST_NOXFRM));
+	rt6 = ip6_dst_alloc(net, dev,
+			    DST_HOST | DST_NOPOLICY | DST_NOXFRM | DST_NOCACHE);
 	if (!rt6)
 		goto out;
 
-	dst = &rt6->dst;
-
-	rt6->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, GFP_KERNEL);
-	if (!rt6->rt6i_pcpu) {
-		dst_destroy(dst);
-		goto out;
-	}
-	for_each_possible_cpu(cpu) {
-		struct rt6_info **p = per_cpu_ptr(rt6->rt6i_pcpu, cpu);
-		*p =  NULL;
-	}
-
-	memset(dst + 1, 0, sizeof(*rt6) - sizeof(*dst));
-
-	INIT_LIST_HEAD(&rt6->rt6i_siblings);
-	INIT_LIST_HEAD(&rt6->rt6i_uncached);
-
-	rt6->dst.input	= vrf_input6;
 	rt6->dst.output	= vrf_output6;
-
-	rt6->rt6i_table = fib6_get_table(dev_net(dev), vrf->tb_id);
-
-	atomic_set(&rt6->dst.__refcnt, 2);
-
+	rt6->rt6i_table = fib6_get_table(net, vrf->tb_id);
+	dst_hold(&rt6->dst);
 	vrf->rt6 = rt6;
 	rc = 0;
 out:
 	return rc;
 }
 #else
-static int init_dst_ops6_kmem_cachep(void)
-{
-	return 0;
-}
-
-static void free_dst_ops6_kmem_cachep(void)
-{
-}
-
-static void vrf_rt6_destroy(struct net_vrf *vrf)
+static void vrf_rt6_release(struct net_vrf *vrf)
 {
 }
 
@@ -558,11 +450,11 @@ static int vrf_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 			    !(IPCB(skb)->flags & IPSKB_REROUTED));
 }
 
-static void vrf_rtable_destroy(struct net_vrf *vrf)
+static void vrf_rtable_release(struct net_vrf *vrf)
 {
 	struct dst_entry *dst = (struct dst_entry *)vrf->rth;
 
-	dst_destroy(dst);
+	dst_release(dst);
 	vrf->rth = NULL;
 }
 
@@ -571,22 +463,10 @@ static struct rtable *vrf_rtable_create(struct net_device *dev)
 	struct net_vrf *vrf = netdev_priv(dev);
 	struct rtable *rth;
 
-	rth = dst_alloc(&vrf_dst_ops, dev, 2,
-			DST_OBSOLETE_NONE,
-			(DST_HOST | DST_NOPOLICY | DST_NOXFRM));
+	rth = rt_dst_alloc(dev, 0, RTN_UNICAST, 1, 1, 0);
 	if (rth) {
 		rth->dst.output	= vrf_output;
-		rth->rt_genid	= rt_genid_ipv4(dev_net(dev));
-		rth->rt_flags	= 0;
-		rth->rt_type	= RTN_UNICAST;
-		rth->rt_is_input = 0;
-		rth->rt_iif	= 0;
-		rth->rt_pmtu	= 0;
-		rth->rt_gateway	= 0;
-		rth->rt_uses_gateway = 0;
 		rth->rt_table_id = vrf->tb_id;
-		INIT_LIST_HEAD(&rth->rt_uncached);
-		rth->rt_uncached_list = NULL;
 	}
 
 	return rth;
@@ -674,8 +554,8 @@ static void vrf_dev_uninit(struct net_device *dev)
 	struct net_device *port_dev;
 	struct list_head *iter;
 
-	vrf_rtable_destroy(vrf);
-	vrf_rt6_destroy(vrf);
+	vrf_rtable_release(vrf);
+	vrf_rt6_release(vrf);
 
 	netdev_for_each_lower_dev(dev, port_dev, iter)
 		vrf_del_slave(dev, port_dev);
@@ -705,7 +585,7 @@ static int vrf_dev_init(struct net_device *dev)
 	return 0;
 
 out_rth:
-	vrf_rtable_destroy(vrf);
+	vrf_rtable_release(vrf);
 out_stats:
 	free_percpu(dev->dstats);
 	dev->dstats = NULL;
@@ -738,7 +618,7 @@ static struct rtable *vrf_get_rtable(const struct net_device *dev,
 		struct net_vrf *vrf = netdev_priv(dev);
 
 		rth = vrf->rth;
-		atomic_inc(&rth->dst.__refcnt);
+		dst_hold(&rth->dst);
 	}
 
 	return rth;
@@ -789,7 +669,7 @@ static struct dst_entry *vrf_get_rt6_dst(const struct net_device *dev,
 		struct net_vrf *vrf = netdev_priv(dev);
 
 		rt = vrf->rt6;
-		atomic_inc(&rt->dst.__refcnt);
+		dst_hold(&rt->dst);
 	}
 
 	return (struct dst_entry *)rt;
@@ -926,19 +806,6 @@ static int __init vrf_init_module(void)
 {
 	int rc;
 
-	vrf_dst_ops.kmem_cachep =
-		kmem_cache_create("vrf_ip_dst_cache",
-				  sizeof(struct rtable), 0,
-				  SLAB_HWCACHE_ALIGN,
-				  NULL);
-
-	if (!vrf_dst_ops.kmem_cachep)
-		return -ENOMEM;
-
-	rc = init_dst_ops6_kmem_cachep();
-	if (rc != 0)
-		goto error2;
-
 	register_netdevice_notifier(&vrf_notifier_block);
 
 	rc = rtnl_link_register(&vrf_link_ops);
@@ -949,22 +816,10 @@ static int __init vrf_init_module(void)
 
 error:
 	unregister_netdevice_notifier(&vrf_notifier_block);
-	free_dst_ops6_kmem_cachep();
-error2:
-	kmem_cache_destroy(vrf_dst_ops.kmem_cachep);
 	return rc;
 }
 
-static void __exit vrf_cleanup_module(void)
-{
-	rtnl_link_unregister(&vrf_link_ops);
-	unregister_netdevice_notifier(&vrf_notifier_block);
-	kmem_cache_destroy(vrf_dst_ops.kmem_cachep);
-	free_dst_ops6_kmem_cachep();
-}
-
 module_init(vrf_init_module);
-module_exit(vrf_cleanup_module);
 MODULE_AUTHOR("Shrijeet Mukherjee, David Ahern");
 MODULE_DESCRIPTION("Device driver to instantiate VRF domains");
 MODULE_LICENSE("GPL");
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 295d291..54c7794 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -101,6 +101,9 @@ void fib6_force_start_gc(struct net *net);
 struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
 				    const struct in6_addr *addr, bool anycast);
 
+struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev,
+			       int flags);
+
 /*
  *	support functions for ND
  *
diff --git a/include/net/route.h b/include/net/route.h
index a3b9ef7..1587ca2 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -209,6 +209,9 @@ unsigned int inet_addr_type_dev_table(struct net *net,
 void ip_rt_multicast_event(struct in_device *);
 int ip_rt_ioctl(struct net *, unsigned int cmd, void __user *arg);
 void ip_rt_get_source(u8 *src, struct sk_buff *skb, struct rtable *rt);
+struct rtable *rt_dst_alloc(struct net_device *dev,
+			     unsigned int flags, u16 type,
+			     bool nopolicy, bool noxfrm, bool will_cache);
 
 struct in_ifaddr;
 void fib_add_ifaddr(struct in_ifaddr *);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index b050cf9..60398a9 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1438,9 +1438,9 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
 #endif
 }
 
-static struct rtable *rt_dst_alloc(struct net_device *dev,
-				   unsigned int flags, u16 type,
-				   bool nopolicy, bool noxfrm, bool will_cache)
+struct rtable *rt_dst_alloc(struct net_device *dev,
+			    unsigned int flags, u16 type,
+			    bool nopolicy, bool noxfrm, bool will_cache)
 {
 	struct rtable *rt;
 
@@ -1468,6 +1468,7 @@ static struct rtable *rt_dst_alloc(struct net_device *dev,
 
 	return rt;
 }
+EXPORT_SYMBOL(rt_dst_alloc);
 
 /* called in rcu_read_lock() section */
 static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 18e29e2..f4dd143 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -338,9 +338,9 @@ static struct rt6_info *__ip6_dst_alloc(struct net *net,
 	return rt;
 }
 
-static struct rt6_info *ip6_dst_alloc(struct net *net,
-				      struct net_device *dev,
-				      int flags)
+struct rt6_info *ip6_dst_alloc(struct net *net,
+			       struct net_device *dev,
+			       int flags)
 {
 	struct rt6_info *rt = __ip6_dst_alloc(net, dev, flags);
 
@@ -364,6 +364,7 @@ static struct rt6_info *ip6_dst_alloc(struct net *net,
 
 	return rt;
 }
+EXPORT_SYMBOL(ip6_dst_alloc);
 
 static void ip6_dst_destroy(struct dst_entry *dst)
 {
-- 
2.1.0


From cc80123cbc494f05fabf8cdbbe082506c732b1fd Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Wed, 25 May 2016 09:35:31 -0700
Subject: [PATCH 23/23] net: vrf: protect changes to private data with rcu

[ Upstream commit b0e95ccdd77591f108c938bbc702b57554a1665d ]

One cpu can be processing packets which includes using the cached route
entries in the vrf device's private data and on another cpu the device
gets deleted which releases the routes and sets the pointers in net_vrf
to NULL. This results in datapath dereferencing a NULL pointer.

Fix by protecting access to dst's with rcu.

Fixes: 193125dbd8eb ("net: Introduce VRF device driver")
Fixes: 35402e313663 ("net: Add IPv6 support to VRF device")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 68 +++++++++++++++++++++++++++++++++++++------------------
 1 file changed, 46 insertions(+), 22 deletions(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index d8197f9..bfc9feb 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -47,8 +47,8 @@
 	((struct net_device *)rcu_dereference(dev->rx_handler_data))
 
 struct net_vrf {
-	struct rtable           *rth;
-	struct rt6_info		*rt6;
+	struct rtable __rcu	*rth;
+	struct rt6_info	__rcu	*rt6;
 	u32                     tb_id;
 };
 
@@ -355,10 +355,15 @@ static int vrf_output6(struct net *net, struct sock *sk, struct sk_buff *skb)
 			    !(IP6CB(skb)->flags & IP6SKB_REROUTED));
 }
 
+/* holding rtnl */
 static void vrf_rt6_release(struct net_vrf *vrf)
 {
-	dst_release(&vrf->rt6->dst);
-	vrf->rt6 = NULL;
+	struct rt6_info *rt6 = rtnl_dereference(vrf->rt6);
+
+	rcu_assign_pointer(vrf->rt6, NULL);
+
+	if (rt6)
+		dst_release(&rt6->dst);
 }
 
 static int vrf_rt6_create(struct net_device *dev)
@@ -376,7 +381,8 @@ static int vrf_rt6_create(struct net_device *dev)
 	rt6->dst.output	= vrf_output6;
 	rt6->rt6i_table = fib6_get_table(net, vrf->tb_id);
 	dst_hold(&rt6->dst);
-	vrf->rt6 = rt6;
+	rcu_assign_pointer(vrf->rt6, rt6);
+
 	rc = 0;
 out:
 	return rc;
@@ -450,26 +456,32 @@ static int vrf_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 			    !(IPCB(skb)->flags & IPSKB_REROUTED));
 }
 
+/* holding rtnl */
 static void vrf_rtable_release(struct net_vrf *vrf)
 {
-	struct dst_entry *dst = (struct dst_entry *)vrf->rth;
+	struct rtable *rth = rtnl_dereference(vrf->rth);
+
+	rcu_assign_pointer(vrf->rth, NULL);
 
-	dst_release(dst);
-	vrf->rth = NULL;
+	if (rth)
+		dst_release(&rth->dst);
 }
 
-static struct rtable *vrf_rtable_create(struct net_device *dev)
+static int vrf_rtable_create(struct net_device *dev)
 {
 	struct net_vrf *vrf = netdev_priv(dev);
 	struct rtable *rth;
 
 	rth = rt_dst_alloc(dev, 0, RTN_UNICAST, 1, 1, 0);
-	if (rth) {
-		rth->dst.output	= vrf_output;
-		rth->rt_table_id = vrf->tb_id;
-	}
+	if (!rth)
+		return -ENOMEM;
 
-	return rth;
+	rth->dst.output = vrf_output;
+	rth->rt_table_id = vrf->tb_id;
+
+	rcu_assign_pointer(vrf->rth, rth);
+
+	return 0;
 }
 
 /**************************** device handling ********************/
@@ -573,8 +585,7 @@ static int vrf_dev_init(struct net_device *dev)
 		goto out_nomem;
 
 	/* create the default dst which points back to us */
-	vrf->rth = vrf_rtable_create(dev);
-	if (!vrf->rth)
+	if (vrf_rtable_create(dev) != 0)
 		goto out_stats;
 
 	if (vrf_rt6_create(dev) != 0)
@@ -617,8 +628,13 @@ static struct rtable *vrf_get_rtable(const struct net_device *dev,
 	if (!(fl4->flowi4_flags & FLOWI_FLAG_L3MDEV_SRC)) {
 		struct net_vrf *vrf = netdev_priv(dev);
 
-		rth = vrf->rth;
-		dst_hold(&rth->dst);
+		rcu_read_lock();
+
+		rth = rcu_dereference(vrf->rth);
+		if (likely(rth))
+			dst_hold(&rth->dst);
+
+		rcu_read_unlock();
 	}
 
 	return rth;
@@ -663,16 +679,24 @@ static int vrf_get_saddr(struct net_device *dev, struct flowi4 *fl4)
 static struct dst_entry *vrf_get_rt6_dst(const struct net_device *dev,
 					 const struct flowi6 *fl6)
 {
-	struct rt6_info *rt = NULL;
+	struct dst_entry *dst = NULL;
 
 	if (!(fl6->flowi6_flags & FLOWI_FLAG_L3MDEV_SRC)) {
 		struct net_vrf *vrf = netdev_priv(dev);
+		struct rt6_info *rt;
+
+		rcu_read_lock();
+
+		rt = rcu_dereference(vrf->rt6);
+		if (likely(rt)) {
+			dst = &rt->dst;
+			dst_hold(dst);
+		}
 
-		rt = vrf->rt6;
-		dst_hold(&rt->dst);
+		rcu_read_unlock();
 	}
 
-	return (struct dst_entry *)rt;
+	return dst;
 }
 #endif
 
-- 
2.1.0


[-- Attachment #4: net_46.mbox --]
[-- Type: Application/Octet-Stream, Size: 58099 bytes --]

From cabaa81b921626d926355d49cb365f6a8b5e02ec Mon Sep 17 00:00:00 2001
From: Richard Alpe <richard.alpe@ericsson.com>
Date: Mon, 16 May 2016 11:14:54 +0200
Subject: [PATCH 01/24] tipc: check nl sock before parsing nested attributes

[ Upstream commit 45e093ae2830cd1264677d47ff9a95a71f5d9f9c ]

Make sure the socket for which the user is listing publication exists
before parsing the socket netlink attributes.

Prior to this patch a call without any socket caused a NULL pointer
dereference in tipc_nl_publ_dump().

Tested-and-reported-by: Baozeng Ding <sploving1@gmail.com>
Signed-off-by: Richard Alpe <richard.alpe@ericsson.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.cm>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/socket.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 3eeb50a..5f80d3f 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2807,6 +2807,9 @@ int tipc_nl_publ_dump(struct sk_buff *skb, struct netlink_callback *cb)
 		if (err)
 			return err;
 
+		if (!attrs[TIPC_NLA_SOCK])
+			return -EINVAL;
+
 		err = nla_parse_nested(sock, TIPC_NLA_SOCK_MAX,
 				       attrs[TIPC_NLA_SOCK],
 				       tipc_nl_sock_policy);
-- 
2.1.0


From fbc48fa5164224b19c096ba15cc3e20fde6841e7 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Mon, 16 May 2016 17:28:16 +0800
Subject: [PATCH 02/24] netlink: Fix dump skb leak/double free

[ Upstream commit 92964c79b357efd980812c4de5c1fd2ec8bb5520 ]

When we free cb->skb after a dump, we do it after releasing the
lock.  This means that a new dump could have started in the time
being and we'll end up freeing their skb instead of ours.

This patch saves the skb and module before we unlock so we free
the right memory.

Fixes: 16b304f3404f ("netlink: Eliminate kmalloc in netlink dump operation.")
Reported-by: Baozeng Ding <sploving1@gmail.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 330ebd6..f48e3b3 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2059,6 +2059,7 @@ static int netlink_dump(struct sock *sk)
 	struct netlink_callback *cb;
 	struct sk_buff *skb = NULL;
 	struct nlmsghdr *nlh;
+	struct module *module;
 	int len, err = -ENOBUFS;
 	int alloc_min_size;
 	int alloc_size;
@@ -2134,9 +2135,11 @@ static int netlink_dump(struct sock *sk)
 		cb->done(cb);
 
 	nlk->cb_running = false;
+	module = cb->module;
+	skb = cb->skb;
 	mutex_unlock(nlk->cb_mutex);
-	module_put(cb->module);
-	consume_skb(cb->skb);
+	module_put(module);
+	consume_skb(skb);
 	return 0;
 
 errout_skb:
-- 
2.1.0


From d675e6333752a9aedeb923f0a37921736251f1ac Mon Sep 17 00:00:00 2001
From: Richard Alpe <richard.alpe@ericsson.com>
Date: Tue, 17 May 2016 16:57:37 +0200
Subject: [PATCH 03/24] tipc: fix nametable publication field in nl compat

[ Upstream commit 03aaaa9b941e136757b55c4cf775aab6068dfd94 ]

The publication field of the old netlink API should contain the
publication key and not the publication reference.

Fixes: 44a8ae94fd55 (tipc: convert legacy nl name table dump to nl compat)
Signed-off-by: Richard Alpe <richard.alpe@ericsson.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/netlink_compat.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index d7d050f..4dfc5c1 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -802,7 +802,7 @@ static int tipc_nl_compat_name_table_dump(struct tipc_nl_compat_msg *msg,
 		goto out;
 
 	tipc_tlv_sprintf(msg->rep, "%-10u %s",
-			 nla_get_u32(publ[TIPC_NLA_PUBL_REF]),
+			 nla_get_u32(publ[TIPC_NLA_PUBL_KEY]),
 			 scope_str[nla_get_u32(publ[TIPC_NLA_PUBL_SCOPE])]);
 out:
 	tipc_tlv_sprintf(msg->rep, "\n");
-- 
2.1.0


From a3ccd729be03f0c3c04c0411545fd02e3e245673 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Tue, 17 May 2016 18:58:08 +0200
Subject: [PATCH 04/24] switchdev: pass pointer to fib_info instead of copy

[ Upstream commit da4ed55165d41b1073f9a476f1c18493e9bf8c8e ]

The problem is that fib_info->nh is [0] so the struct fib_info
allocation size depends on number of nexthops. If we just copy fib_info,
we do not copy the nexthops info and driver accesses memory which is not
ours.

Given the fact that fib4 does not defer operations and therefore it does
not need copy, just pass the pointer down to drivers as it was done
before.

Fixes: 850d0cbc91 ("switchdev: remove pointers from switchdev objects")
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/rocker/rocker_ofdpa.c | 4 ++--
 include/net/switchdev.h                    | 2 +-
 net/switchdev/switchdev.c                  | 6 ++----
 3 files changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/rocker/rocker_ofdpa.c b/drivers/net/ethernet/rocker/rocker_ofdpa.c
index 0e758bc..1ca7963 100644
--- a/drivers/net/ethernet/rocker/rocker_ofdpa.c
+++ b/drivers/net/ethernet/rocker/rocker_ofdpa.c
@@ -2727,7 +2727,7 @@ static int ofdpa_port_obj_fib4_add(struct rocker_port *rocker_port,
 
 	return ofdpa_port_fib_ipv4(ofdpa_port, trans,
 				   htonl(fib4->dst), fib4->dst_len,
-				   &fib4->fi, fib4->tb_id, 0);
+				   fib4->fi, fib4->tb_id, 0);
 }
 
 static int ofdpa_port_obj_fib4_del(struct rocker_port *rocker_port,
@@ -2737,7 +2737,7 @@ static int ofdpa_port_obj_fib4_del(struct rocker_port *rocker_port,
 
 	return ofdpa_port_fib_ipv4(ofdpa_port, NULL,
 				   htonl(fib4->dst), fib4->dst_len,
-				   &fib4->fi, fib4->tb_id,
+				   fib4->fi, fib4->tb_id,
 				   OFDPA_OP_FLAG_REMOVE);
 }
 
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index 51d77b2..985619a 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -97,7 +97,7 @@ struct switchdev_obj_ipv4_fib {
 	struct switchdev_obj obj;
 	u32 dst;
 	int dst_len;
-	struct fib_info fi;
+	struct fib_info *fi;
 	u8 tos;
 	u8 type;
 	u32 nlflags;
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index b7e01d8..59658b2 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -1188,6 +1188,7 @@ int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi,
 		.obj.id = SWITCHDEV_OBJ_ID_IPV4_FIB,
 		.dst = dst,
 		.dst_len = dst_len,
+		.fi = fi,
 		.tos = tos,
 		.type = type,
 		.nlflags = nlflags,
@@ -1196,8 +1197,6 @@ int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi,
 	struct net_device *dev;
 	int err = 0;
 
-	memcpy(&ipv4_fib.fi, fi, sizeof(ipv4_fib.fi));
-
 	/* Don't offload route if using custom ip rules or if
 	 * IPv4 FIB offloading has been disabled completely.
 	 */
@@ -1242,6 +1241,7 @@ int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi,
 		.obj.id = SWITCHDEV_OBJ_ID_IPV4_FIB,
 		.dst = dst,
 		.dst_len = dst_len,
+		.fi = fi,
 		.tos = tos,
 		.type = type,
 		.nlflags = 0,
@@ -1250,8 +1250,6 @@ int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi,
 	struct net_device *dev;
 	int err = 0;
 
-	memcpy(&ipv4_fib.fi, fi, sizeof(ipv4_fib.fi));
-
 	if (!(fi->fib_flags & RTNH_F_OFFLOAD))
 		return 0;
 
-- 
2.1.0


From 8647e4e36b05f966fedaba1b614b29f32b25f100 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Wed, 18 May 2016 13:34:40 +0200
Subject: [PATCH 05/24] macsec: fix netlink attribute for key id

[ Upstream commit 1968a0b8b6ca088bc029bd99ee696f1aca4090d0 ]

In my last commit I replaced MACSEC_SA_ATTR_KEYID by
MACSEC_SA_ATTR_KEY.

Fixes: 8acca6acebd0 ("macsec: key identifier is 128 bits, not 64")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macsec.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 92eaab95..9e803bb 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -1645,7 +1645,7 @@ static int macsec_add_rxsa(struct sk_buff *skb, struct genl_info *info)
 	if (tb_sa[MACSEC_SA_ATTR_ACTIVE])
 		rx_sa->active = !!nla_get_u8(tb_sa[MACSEC_SA_ATTR_ACTIVE]);
 
-	nla_memcpy(rx_sa->key.id, tb_sa[MACSEC_SA_ATTR_KEY], MACSEC_KEYID_LEN);
+	nla_memcpy(rx_sa->key.id, tb_sa[MACSEC_SA_ATTR_KEYID], MACSEC_KEYID_LEN);
 	rx_sa->sc = rx_sc;
 	rcu_assign_pointer(rx_sc->sa[assoc_num], rx_sa);
 
@@ -1784,7 +1784,7 @@ static int macsec_add_txsa(struct sk_buff *skb, struct genl_info *info)
 		return -ENOMEM;
 	}
 
-	nla_memcpy(tx_sa->key.id, tb_sa[MACSEC_SA_ATTR_KEY], MACSEC_KEYID_LEN);
+	nla_memcpy(tx_sa->key.id, tb_sa[MACSEC_SA_ATTR_KEYID], MACSEC_KEYID_LEN);
 
 	spin_lock_bh(&tx_sa->lock);
 	tx_sa->next_pn = nla_get_u32(tb_sa[MACSEC_SA_ATTR_PN]);
-- 
2.1.0


From b03b1968745fd58822192067f6feff4303dc14df Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Thu, 19 May 2016 13:36:51 +0800
Subject: [PATCH 06/24] tuntap: correctly wake up process during uninit

[ Upstream commit addf8fc4acb1cf79492ac64966f07178793cb3d7 ]

We used to check dev->reg_state against NETREG_REGISTERED after each
time we are woke up. But after commit 9e641bdcfa4e ("net-tun:
restructure tun_do_read for better sleep/wakeup efficiency"), it uses
skb_recv_datagram() which does not check dev->reg_state. This will
result if we delete a tun/tap device after a process is blocked in the
reading. The device will wait for the reference count which was held
by that process for ever.

Fixes this by using RCV_SHUTDOWN which will be checked during
sk_recv_datagram() before trying to wake up the process during uninit.

Fixes: 9e641bdcfa4e ("net-tun: restructure tun_do_read for better
sleep/wakeup efficiency")
Cc: Eric Dumazet <edumazet@google.com>
Cc: Xi Wang <xii@google.com>
Cc: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 2c9e45f5..dda4905 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -568,11 +568,13 @@ static void tun_detach_all(struct net_device *dev)
 	for (i = 0; i < n; i++) {
 		tfile = rtnl_dereference(tun->tfiles[i]);
 		BUG_ON(!tfile);
+		tfile->socket.sk->sk_shutdown = RCV_SHUTDOWN;
 		tfile->socket.sk->sk_data_ready(tfile->socket.sk);
 		RCU_INIT_POINTER(tfile->tun, NULL);
 		--tun->numqueues;
 	}
 	list_for_each_entry(tfile, &tun->disabled, next) {
+		tfile->socket.sk->sk_shutdown = RCV_SHUTDOWN;
 		tfile->socket.sk->sk_data_ready(tfile->socket.sk);
 		RCU_INIT_POINTER(tfile->tun, NULL);
 	}
@@ -628,6 +630,7 @@ static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filte
 			goto out;
 	}
 	tfile->queue_index = tun->numqueues;
+	tfile->socket.sk->sk_shutdown &= ~RCV_SHUTDOWN;
 	rcu_assign_pointer(tfile->tun, tun);
 	rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile);
 	tun->numqueues++;
@@ -1425,9 +1428,6 @@ static ssize_t tun_do_read(struct tun_struct *tun, struct tun_file *tfile,
 	if (!iov_iter_count(to))
 		return 0;
 
-	if (tun->dev->reg_state != NETREG_REGISTERED)
-		return -EIO;
-
 	/* Read frames from queue */
 	skb = __skb_recv_datagram(tfile->socket.sk, noblock ? MSG_DONTWAIT : 0,
 				  &peeked, &off, &err);
-- 
2.1.0


From 665950547b2d2922340212d5c980e08f0fe61da2 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 20 May 2016 17:22:48 -0500
Subject: [PATCH 07/24] bpf: Use mount_nodev not mount_ns to mount the bpf
 filesystem

[ Upstream commit e27f4a942a0ee4b84567a3c6cfa84f273e55cbb7 ]

While reviewing the filesystems that set FS_USERNS_MOUNT I spotted the
bpf filesystem.  Looking at the code I saw a broken usage of mount_ns
with current->nsproxy->mnt_ns. As the code does not acquire a
reference to the mount namespace it can not possibly be correct to
store the mount namespace on the superblock as it does.

Replace mount_ns with mount_nodev so that each mount of the bpf
filesystem returns a distinct instance, and the code is not buggy.

In discussion with Hannes Frederic Sowa it was reported that the use
of mount_ns was an attempt to have one bpf instance per mount
namespace, in an attempt to keep resources that pin resources from
hiding.  That intent simply does not work, the vfs is not built to
allow that kind of behavior.  Which means that the bpf filesystem
really is buggy both semantically and in it's implemenation as it does
not nor can it implement the original intent.

This change is userspace visible, but my experience with similar
filesystems leads me to believe nothing will break with a model of each
mount of the bpf filesystem is distinct from all others.

Fixes: b2197755b263 ("bpf: add support for persistent maps/progs")
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/inode.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 8f94ca1..55d9236 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -378,7 +378,7 @@ static int bpf_fill_super(struct super_block *sb, void *data, int silent)
 static struct dentry *bpf_mount(struct file_system_type *type, int flags,
 				const char *dev_name, void *data)
 {
-	return mount_ns(type, flags, current->nsproxy->mnt_ns, bpf_fill_super);
+	return mount_nodev(type, flags, data, bpf_fill_super);
 }
 
 static struct file_system_type bpf_fs_type = {
-- 
2.1.0


From 6cd217f6fb8e3e004f2932c9ab4a78ffbf47a5fc Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Thu, 19 May 2016 15:58:33 +0200
Subject: [PATCH 08/24] udp: prevent skbs lingering in tunnel socket queues

[ Upstream commit e5aed006be918af163eb397e45aa5ea6cefd5e01 ]

In case we find a socket with encapsulation enabled we should call
the encap_recv function even if just a udp header without payload is
available. The callbacks are responsible for correctly verifying and
dropping the packets.

Also, in case the header validation fails for geneve and vxlan we
shouldn't put the skb back into the socket queue, no one will pick
them up there.  Instead we can simply discard them in the respective
encap_recv functions.

Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c | 10 +++-------
 drivers/net/vxlan.c  |  4 ++--
 net/ipv4/udp.c       |  2 +-
 net/ipv6/udp.c       |  2 +-
 4 files changed, 7 insertions(+), 11 deletions(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 7b0a644..9fcb489 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -336,15 +336,15 @@ static int geneve_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 
 	/* Need Geneve and inner Ethernet header to be present */
 	if (unlikely(!pskb_may_pull(skb, GENEVE_BASE_HLEN)))
-		goto error;
+		goto drop;
 
 	/* Return packets with reserved bits set */
 	geneveh = geneve_hdr(skb);
 	if (unlikely(geneveh->ver != GENEVE_VER))
-		goto error;
+		goto drop;
 
 	if (unlikely(geneveh->proto_type != htons(ETH_P_TEB)))
-		goto error;
+		goto drop;
 
 	gs = rcu_dereference_sk_user_data(sk);
 	if (!gs)
@@ -367,10 +367,6 @@ drop:
 	/* Consume bad packet */
 	kfree_skb(skb);
 	return 0;
-
-error:
-	/* Let the UDP layer deal with the skb */
-	return 1;
 }
 
 static struct socket *geneve_create_sock(struct net *net, bool ipv6,
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 8ac261a..9aa8678 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1262,7 +1262,7 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb)
 
 	/* Need Vxlan and inner Ethernet header to be present */
 	if (!pskb_may_pull(skb, VXLAN_HLEN))
-		return 1;
+		goto drop;
 
 	unparsed = *vxlan_hdr(skb);
 	/* VNI flag always required to be set */
@@ -1271,7 +1271,7 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb)
 			   ntohl(vxlan_hdr(skb)->vx_flags),
 			   ntohl(vxlan_hdr(skb)->vx_vni));
 		/* Return non vxlan pkt */
-		return 1;
+		goto drop;
 	}
 	unparsed.vx_flags &= ~VXLAN_HF_VNI;
 	unparsed.vx_vni &= ~VXLAN_VNI_MASK;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index a2e7f55..e9853df 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1616,7 +1616,7 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 
 		/* if we're overly short, let UDP handle it */
 		encap_rcv = ACCESS_ONCE(up->encap_rcv);
-		if (skb->len > sizeof(struct udphdr) && encap_rcv) {
+		if (encap_rcv) {
 			int ret;
 
 			/* Verify checksum before giving to encap */
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 6bc5c66..f96831d9 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -653,7 +653,7 @@ int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 
 		/* if we're overly short, let UDP handle it */
 		encap_rcv = ACCESS_ONCE(up->encap_rcv);
-		if (skb->len > sizeof(struct udphdr) && encap_rcv) {
+		if (encap_rcv) {
 			int ret;
 
 			/* Verify checksum before giving to encap */
-- 
2.1.0


From 6f533e51e9cffb6b58c155a7064117f590bf4362 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Thu, 19 May 2016 17:26:29 +0200
Subject: [PATCH 09/24] uapi glibc compat: fix compilation when !__USE_MISC in
 glibc

[ Upstream commit f0a3fdca794d1e68ae284ef4caefe681f7c18e89 ]

These structures are defined only if __USE_MISC is set in glibc net/if.h
headers, ie when _BSD_SOURCE or _SVID_SOURCE are defined.

CC: Jan Engelhardt <jengelh@inai.de>
CC: Josh Boyer <jwboyer@fedoraproject.org>
CC: Stephen Hemminger <shemming@brocade.com>
CC: Waldemar Brodkorb <mail@waldemar-brodkorb.de>
CC: Gabriel Laskar <gabriel@lse.epita.fr>
CC: Mikko Rapeli <mikko.rapeli@iki.fi>
Fixes: 4a91cb61bb99 ("uapi glibc compat: fix compile errors when glibc net/if.h included before linux/if.h")
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/libc-compat.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/uapi/linux/libc-compat.h b/include/uapi/linux/libc-compat.h
index d5e38c7..e4f048e 100644
--- a/include/uapi/linux/libc-compat.h
+++ b/include/uapi/linux/libc-compat.h
@@ -52,7 +52,7 @@
 #if defined(__GLIBC__)
 
 /* Coordinate with glibc net/if.h header. */
-#if defined(_NET_IF_H)
+#if defined(_NET_IF_H) && defined(__USE_MISC)
 
 /* GLIBC headers included first so don't define anything
  * that would already be defined. */
-- 
2.1.0


From 723b57a65a44b69b2c8514db3589214ebe7f3ff7 Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia <ezequiel@vanguardiasur.com.ar>
Date: Fri, 20 May 2016 13:21:10 -0300
Subject: [PATCH 10/24] ipv4: Fix non-initialized TTL when CONFIG_SYSCTL=n

[ Upstream commit 049bbf589ec651685205bd8ce73221fdd62345cf ]

Commit fa50d974d104 ("ipv4: Namespaceify ip_default_ttl sysctl knob")
moves the default TTL assignment, and as side-effect IPv4 TTL now
has a default value only if sysctl support is enabled (CONFIG_SYSCTL=y).

The sysctl_ip_default_ttl is fundamental for IP to work properly,
as it provides the TTL to be used as default. The defautl TTL may be
used in ip_selected_ttl, through the following flow:

  ip_select_ttl
    ip4_dst_hoplimit
      net->ipv4.sysctl_ip_default_ttl

This commit fixes the issue by assigning net->ipv4.sysctl_ip_default_ttl
in net_init_net, called during ipv4's initialization.

Without this commit, a kernel built without sysctl support will send
all IP packets with zero TTL (unless a TTL is explicitly set, e.g.
with setsockopt).

Given a similar issue might appear on the other knobs that were
namespaceify, this commit also moves them.

Fixes: fa50d974d104 ("ipv4: Namespaceify ip_default_ttl sysctl knob")
Signed-off-by: Ezequiel Garcia <ezequiel@vanguardiasur.com.ar>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/af_inet.c         | 8 ++++++++
 net/ipv4/sysctl_net_ipv4.c | 4 ----
 2 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 9e48199..7ad0e56 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1660,6 +1660,14 @@ static __net_init int inet_init_net(struct net *net)
 	 */
 	net->ipv4.ping_group_range.range[0] = make_kgid(&init_user_ns, 1);
 	net->ipv4.ping_group_range.range[1] = make_kgid(&init_user_ns, 0);
+
+	/* Default values for sysctl-controlled parameters.
+	 * We set them here, in case sysctl is not compiled.
+	 */
+	net->ipv4.sysctl_ip_default_ttl = IPDEFTTL;
+	net->ipv4.sysctl_ip_dynaddr = 0;
+	net->ipv4.sysctl_ip_early_demux = 1;
+
 	return 0;
 }
 
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 1e1fe60..03112a3 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -988,10 +988,6 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
 	if (!net->ipv4.sysctl_local_reserved_ports)
 		goto err_ports;
 
-	net->ipv4.sysctl_ip_default_ttl = IPDEFTTL;
-	net->ipv4.sysctl_ip_dynaddr = 0;
-	net->ipv4.sysctl_ip_early_demux = 1;
-
 	return 0;
 
 err_ports:
-- 
2.1.0


From 8e9b53707361aa1c0405910bd761e332cc9d90b1 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Sun, 22 May 2016 23:16:18 +0200
Subject: [PATCH 11/24] bpf, inode: disallow userns mounts

[ Upstream commit 612bacad78ba6d0a91166fc4487af114bac172a8 ]

Follow-up to commit e27f4a942a0e ("bpf: Use mount_nodev not mount_ns
to mount the bpf filesystem"), which removes the FS_USERNS_MOUNT flag.

The original idea was to have a per mountns instance instead of a
single global fs instance, but that didn't work out and we had to
switch to mount_nodev() model. The intent of that middle ground was
that we avoid users who don't play nice to create endless instances
of bpf fs which are difficult to control and discover from an admin
point of view, but at the same time it would have allowed us to be
more flexible with regard to namespaces.

Therefore, since we now did the switch to mount_nodev() as a fix
where individual instances are created, we also need to remove userns
mount flag along with it to avoid running into mentioned situation.
I don't expect any breakage at this early point in time with removing
the flag and we can revisit this later should the requirement for
this come up with future users. This and commit e27f4a942a0e have
been split to facilitate tracking should any of them run into the
unlikely case of causing a regression.

Fixes: b2197755b263 ("bpf: add support for persistent maps/progs")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/inode.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 55d9236..b2aefa2 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -386,7 +386,6 @@ static struct file_system_type bpf_fs_type = {
 	.name		= "bpf",
 	.mount		= bpf_mount,
 	.kill_sb	= kill_litter_super,
-	.fs_flags	= FS_USERNS_MOUNT,
 };
 
 MODULE_ALIAS_FS("bpf");
-- 
2.1.0


From b0a4c8cd7c81fbf48c4915f46e6b3af024aafc56 Mon Sep 17 00:00:00 2001
From: Gregory CLEMENT <gregory.clement@free-electrons.com>
Date: Tue, 24 May 2016 18:03:25 +0200
Subject: [PATCH 12/24] net: mvneta: Fix lacking spinlock initialization

[ Upstream commit 91c45e38b9478ff507e05f10151d64cd0d1aad7b ]

The spinlock used by the hwbm functions must be initialized by the
network driver. This commit fixes this lack and the following erros when
lockdep is enabled:

INFO: trying to register non-static key.
the code is fine but needs lockdep annotation.
turning off the locking correctness validator.
[<c010ff80>] (unwind_backtrace) from [<c010bd08>] (show_stack+0x10/0x14)
[<c010bd08>] (show_stack) from [<c032913c>] (dump_stack+0xb4/0xe0)
[<c032913c>] (dump_stack) from [<c01670e4>] (__lock_acquire+0x1f58/0x2060)
[<c01670e4>] (__lock_acquire) from [<c0167dec>] (lock_acquire+0xa4/0xd0)
[<c0167dec>] (lock_acquire) from [<c06f6650>] (_raw_spin_lock_irqsave+0x54/0x68)
[<c06f6650>] (_raw_spin_lock_irqsave) from [<c058e830>] (hwbm_pool_add+0x1c/0xdc)
[<c058e830>] (hwbm_pool_add) from [<c043f4e8>] (mvneta_bm_pool_use+0x338/0x490)
[<c043f4e8>] (mvneta_bm_pool_use) from [<c0443198>] (mvneta_probe+0x654/0x1284)
[<c0443198>] (mvneta_probe) from [<c03b894c>] (platform_drv_probe+0x4c/0xb0)
[<c03b894c>] (platform_drv_probe) from [<c03b7158>] (driver_probe_device+0x214/0x2c0)
[<c03b7158>] (driver_probe_device) from [<c03b72c4>] (__driver_attach+0xc0/0xc4)
[<c03b72c4>] (__driver_attach) from [<c03b5440>] (bus_for_each_dev+0x68/0x9c)
[<c03b5440>] (bus_for_each_dev) from [<c03b65b8>] (bus_add_driver+0x1a0/0x218)
[<c03b65b8>] (bus_add_driver) from [<c03b79cc>] (driver_register+0x78/0xf8)
[<c03b79cc>] (driver_register) from [<c01018f4>] (do_one_initcall+0x90/0x1dc)
[<c01018f4>] (do_one_initcall) from [<c0900de4>] (kernel_init_freeable+0x15c/0x1fc)
[<c0900de4>] (kernel_init_freeable) from [<c06eed90>] (kernel_init+0x8/0x114)
[<c06eed90>] (kernel_init) from [<c0107910>] (ret_from_fork+0x14/0x24)

Fixes: baa11ebc0c76 ("net: mvneta: Use the new hwbm framework")
Reported-by: Russell King <rmk+kernel@armlinux.org.uk>
Cc: <stable@vger.kernel.org>
Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta_bm.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/marvell/mvneta_bm.c b/drivers/net/ethernet/marvell/mvneta_bm.c
index 01fccec..466939f 100644
--- a/drivers/net/ethernet/marvell/mvneta_bm.c
+++ b/drivers/net/ethernet/marvell/mvneta_bm.c
@@ -189,6 +189,7 @@ struct mvneta_bm_pool *mvneta_bm_pool_use(struct mvneta_bm *priv, u8 pool_id,
 			SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 		hwbm_pool->construct = mvneta_bm_construct;
 		hwbm_pool->priv = new_pool;
+		spin_lock_init(&hwbm_pool->lock);
 
 		/* Create new pool */
 		err = mvneta_bm_pool_create(priv, new_pool);
-- 
2.1.0


From ec6c1400725522401fee4795384615631bda4c2a Mon Sep 17 00:00:00 2001
From: Gregory CLEMENT <gregory.clement@free-electrons.com>
Date: Tue, 24 May 2016 18:03:26 +0200
Subject: [PATCH 13/24] net: hwbm: Fix unbalanced spinlock in error case

[ Upstream commit b388fc7405e901c7d6f7817d05193c054e761815 ]

When hwbm_pool_add exited in error the spinlock was not released. This
patch fixes this issue.

Fixes: 8cb2d8bf57e6 ("net: add a hardware buffer management helper API")
Reported-by: Jean-Jacques Hiblot <jjhiblot@traphandler.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/hwbm.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/core/hwbm.c b/net/core/hwbm.c
index 941c284..2cab489 100644
--- a/net/core/hwbm.c
+++ b/net/core/hwbm.c
@@ -55,18 +55,21 @@ int hwbm_pool_add(struct hwbm_pool *bm_pool, unsigned int buf_num, gfp_t gfp)
 	spin_lock_irqsave(&bm_pool->lock, flags);
 	if (bm_pool->buf_num == bm_pool->size) {
 		pr_warn("pool already filled\n");
+		spin_unlock_irqrestore(&bm_pool->lock, flags);
 		return bm_pool->buf_num;
 	}
 
 	if (buf_num + bm_pool->buf_num > bm_pool->size) {
 		pr_warn("cannot allocate %d buffers for pool\n",
 			buf_num);
+		spin_unlock_irqrestore(&bm_pool->lock, flags);
 		return 0;
 	}
 
 	if ((buf_num + bm_pool->buf_num) < bm_pool->buf_num) {
 		pr_warn("Adding %d buffers to the %d current buffers will overflow\n",
 			buf_num,  bm_pool->buf_num);
+		spin_unlock_irqrestore(&bm_pool->lock, flags);
 		return 0;
 	}
 
-- 
2.1.0


From 5b962e172436620e5806e8a765edb1fe8c49c9bd Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Tue, 24 May 2016 18:53:36 +0100
Subject: [PATCH 14/24] sfc: on MC reset, clear PIO buffer linkage in TXQs

[ Upstream commit c0795bf64cba4d1b796fdc5b74b33772841ed1bb ]

Otherwise, if we fail to allocate new PIO buffers, our TXQs will try to
use the old ones, which aren't there any more.

Fixes: 183233bec810 "sfc: Allocate and link PIO buffers; map them with write-combining"
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/ef10.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 1681084..1f30912 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -619,6 +619,17 @@ fail:
 	return rc;
 }
 
+static void efx_ef10_forget_old_piobufs(struct efx_nic *efx)
+{
+	struct efx_channel *channel;
+	struct efx_tx_queue *tx_queue;
+
+	/* All our existing PIO buffers went away */
+	efx_for_each_channel(channel, efx)
+		efx_for_each_channel_tx_queue(tx_queue, channel)
+			tx_queue->piobuf = NULL;
+}
+
 #else /* !EFX_USE_PIO */
 
 static int efx_ef10_alloc_piobufs(struct efx_nic *efx, unsigned int n)
@@ -635,6 +646,10 @@ static void efx_ef10_free_piobufs(struct efx_nic *efx)
 {
 }
 
+static void efx_ef10_forget_old_piobufs(struct efx_nic *efx)
+{
+}
+
 #endif /* EFX_USE_PIO */
 
 static void efx_ef10_remove(struct efx_nic *efx)
@@ -1018,6 +1033,7 @@ static void efx_ef10_reset_mc_allocations(struct efx_nic *efx)
 	nic_data->must_realloc_vis = true;
 	nic_data->must_restore_filters = true;
 	nic_data->must_restore_piobufs = true;
+	efx_ef10_forget_old_piobufs(efx);
 	nic_data->rx_rss_context = EFX_EF10_RSS_CONTEXT_INVALID;
 
 	/* Driver-created vswitches and vports must be re-created */
-- 
2.1.0


From 881bcb79a55f9c34df302d59a5c63de8c669ed68 Mon Sep 17 00:00:00 2001
From: Ivan Vecera <ivecera@redhat.com>
Date: Wed, 25 May 2016 21:21:52 +0200
Subject: [PATCH 15/24] team: don't call netdev_change_features under
 team->lock

[ Upstream commit f6988cb63a4e698d8a62a1d085d263d1fcc351ea ]

The team_device_event() notifier calls team_compute_features() to fix
vlan_features under team->lock to protect team->port_list. The problem is
that subsequent __team_compute_features() calls netdev_change_features()
to propagate vlan_features to upper vlan devices while team->lock is still
taken. This can lead to deadlock when NETIF_F_LRO is modified on lower
devices or team device itself.

Example:
The team0 as active backup with eth0 and eth1 NICs. Both eth0 & eth1 are
LRO capable and LRO is enabled. Thus LRO is also enabled on team0.

The command 'ethtool -K team0 lro off' now hangs due to this deadlock:

dev_ethtool()
-> ethtool_set_features()
 -> __netdev_update_features(team)
  -> netdev_sync_lower_features()
   -> netdev_update_features(lower_1)
    -> __netdev_update_features(lower_1)
    -> netdev_features_change(lower_1)
     -> call_netdevice_notifiers(...)
      -> team_device_event(lower_1)
       -> team_compute_features(team) [TAKES team->lock]
        -> netdev_change_features(team)
         -> __netdev_update_features(team)
          -> netdev_sync_lower_features()
           -> netdev_update_features(lower_2)
            -> __netdev_update_features(lower_2)
            -> netdev_features_change(lower_2)
             -> call_netdevice_notifiers(...)
              -> team_device_event(lower_2)
               -> team_compute_features(team) [DEADLOCK]

The bug is present in team from the beginning but it appeared after the commit
fd867d5 (net/core: generic support for disabling netdev features down stack)
that adds synchronization of features with lower devices.

Fixes: fd867d5 (net/core: generic support for disabling netdev features down stack)
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index a0f64cb..2ace126 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -990,7 +990,7 @@ static void team_port_disable(struct team *team,
 #define TEAM_ENC_FEATURES	(NETIF_F_HW_CSUM | NETIF_F_SG | \
 				 NETIF_F_RXCSUM | NETIF_F_ALL_TSO)
 
-static void __team_compute_features(struct team *team)
+static void ___team_compute_features(struct team *team)
 {
 	struct team_port *port;
 	u32 vlan_features = TEAM_VLAN_FEATURES & NETIF_F_ALL_FOR_ALL;
@@ -1021,15 +1021,20 @@ static void __team_compute_features(struct team *team)
 	team->dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
 	if (dst_release_flag == (IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM))
 		team->dev->priv_flags |= IFF_XMIT_DST_RELEASE;
+}
 
+static void __team_compute_features(struct team *team)
+{
+	___team_compute_features(team);
 	netdev_change_features(team->dev);
 }
 
 static void team_compute_features(struct team *team)
 {
 	mutex_lock(&team->lock);
-	__team_compute_features(team);
+	___team_compute_features(team);
 	mutex_unlock(&team->lock);
+	netdev_change_features(team->dev);
 }
 
 static int team_port_enter(struct team *team, struct team_port *port)
-- 
2.1.0


From ed819e97fe17ed47af09dcbdacc09d568d088279 Mon Sep 17 00:00:00 2001
From: Feng Tang <feng.tang@intel.com>
Date: Wed, 25 May 2016 14:49:54 +0800
Subject: [PATCH 16/24] net: alx: use custom skb allocator

[ Upstream commit 26c5f03b2ae8018418ceb25b2e6a48560e8c2f5b ]

This patch follows Eric Dumazet's commit 7b70176421 for Atheros
atl1c driver to fix one exactly same bug in alx driver, that the
network link will be lost in 1-5 minutes after the device is up.

My laptop Lenovo Y580 with Atheros AR8161 ethernet device hit the
same problem with kernel 4.4, and it will be cured by Jarod Wilson's
commit c406700c for alx driver which get merged in 4.5. But there
are still some alx devices can't function well even with Jarod's
patch, while this patch could make them work fine. More details on
	https://bugzilla.kernel.org/show_bug.cgi?id=70761

The debug shows the issue is very likely to be related with the RX
DMA address, specifically 0x...f80, if RX buffer get 0x...f80 several
times, their will be RX overflow error and device will stop working.

For kernel 4.5.0 with Jarod's patch which works fine with my
AR8161/Lennov Y580, if I made some change to the
	__netdev_alloc_skb
		--> __alloc_page_frag()
to make the allocated buffer can get an address with 0x...f80,
then the same error happens. If I make it to 0x...f40 or 0x....fc0,
everything will be still fine. So I tend to believe that the
0x..f80 address cause the silicon to behave abnormally.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=70761
Cc: Eric Dumazet <edumazet@google.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: Jarod Wilson <jarod@redhat.com>
Signed-off-by: Feng Tang <feng.tang@intel.com>
Tested-by: Ole Lukoie <olelukoie@mail.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/atheros/alx/alx.h  |  4 +++
 drivers/net/ethernet/atheros/alx/main.c | 48 ++++++++++++++++++++++++++++++++-
 2 files changed, 51 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/atheros/alx/alx.h b/drivers/net/ethernet/atheros/alx/alx.h
index 8fc93c5..d02c424 100644
--- a/drivers/net/ethernet/atheros/alx/alx.h
+++ b/drivers/net/ethernet/atheros/alx/alx.h
@@ -96,6 +96,10 @@ struct alx_priv {
 	unsigned int rx_ringsz;
 	unsigned int rxbuf_size;
 
+	struct page  *rx_page;
+	unsigned int rx_page_offset;
+	unsigned int rx_frag_size;
+
 	struct napi_struct napi;
 	struct alx_tx_queue txq;
 	struct alx_rx_queue rxq;
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index 55b118e..8611811 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -70,6 +70,35 @@ static void alx_free_txbuf(struct alx_priv *alx, int entry)
 	}
 }
 
+static struct sk_buff *alx_alloc_skb(struct alx_priv *alx, gfp_t gfp)
+{
+	struct sk_buff *skb;
+	struct page *page;
+
+	if (alx->rx_frag_size > PAGE_SIZE)
+		return __netdev_alloc_skb(alx->dev, alx->rxbuf_size, gfp);
+
+	page = alx->rx_page;
+	if (!page) {
+		alx->rx_page = page = alloc_page(gfp);
+		if (unlikely(!page))
+			return NULL;
+		alx->rx_page_offset = 0;
+	}
+
+	skb = build_skb(page_address(page) + alx->rx_page_offset,
+			alx->rx_frag_size);
+	if (likely(skb)) {
+		alx->rx_page_offset += alx->rx_frag_size;
+		if (alx->rx_page_offset >= PAGE_SIZE)
+			alx->rx_page = NULL;
+		else
+			get_page(page);
+	}
+	return skb;
+}
+
+
 static int alx_refill_rx_ring(struct alx_priv *alx, gfp_t gfp)
 {
 	struct alx_rx_queue *rxq = &alx->rxq;
@@ -86,7 +115,7 @@ static int alx_refill_rx_ring(struct alx_priv *alx, gfp_t gfp)
 	while (!cur_buf->skb && next != rxq->read_idx) {
 		struct alx_rfd *rfd = &rxq->rfd[cur];
 
-		skb = __netdev_alloc_skb(alx->dev, alx->rxbuf_size, gfp);
+		skb = alx_alloc_skb(alx, gfp);
 		if (!skb)
 			break;
 		dma = dma_map_single(&alx->hw.pdev->dev,
@@ -124,6 +153,7 @@ static int alx_refill_rx_ring(struct alx_priv *alx, gfp_t gfp)
 		alx_write_mem16(&alx->hw, ALX_RFD_PIDX, cur);
 	}
 
+
 	return count;
 }
 
@@ -592,6 +622,11 @@ static void alx_free_rings(struct alx_priv *alx)
 	kfree(alx->txq.bufs);
 	kfree(alx->rxq.bufs);
 
+	if (alx->rx_page) {
+		put_page(alx->rx_page);
+		alx->rx_page = NULL;
+	}
+
 	dma_free_coherent(&alx->hw.pdev->dev,
 			  alx->descmem.size,
 			  alx->descmem.virt,
@@ -646,6 +681,7 @@ static int alx_request_irq(struct alx_priv *alx)
 				  alx->dev->name, alx);
 		if (!err)
 			goto out;
+
 		/* fall back to legacy interrupt */
 		pci_disable_msi(alx->hw.pdev);
 	}
@@ -689,6 +725,7 @@ static int alx_init_sw(struct alx_priv *alx)
 	struct pci_dev *pdev = alx->hw.pdev;
 	struct alx_hw *hw = &alx->hw;
 	int err;
+	unsigned int head_size;
 
 	err = alx_identify_hw(alx);
 	if (err) {
@@ -704,7 +741,12 @@ static int alx_init_sw(struct alx_priv *alx)
 
 	hw->smb_timer = 400;
 	hw->mtu = alx->dev->mtu;
+
 	alx->rxbuf_size = ALX_MAX_FRAME_LEN(hw->mtu);
+	head_size = SKB_DATA_ALIGN(alx->rxbuf_size + NET_SKB_PAD) +
+		    SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+	alx->rx_frag_size = roundup_pow_of_two(head_size);
+
 	alx->tx_ringsz = 256;
 	alx->rx_ringsz = 512;
 	hw->imt = 200;
@@ -806,6 +848,7 @@ static int alx_change_mtu(struct net_device *netdev, int mtu)
 {
 	struct alx_priv *alx = netdev_priv(netdev);
 	int max_frame = ALX_MAX_FRAME_LEN(mtu);
+	unsigned int head_size;
 
 	if ((max_frame < ALX_MIN_FRAME_SIZE) ||
 	    (max_frame > ALX_MAX_FRAME_SIZE))
@@ -817,6 +860,9 @@ static int alx_change_mtu(struct net_device *netdev, int mtu)
 	netdev->mtu = mtu;
 	alx->hw.mtu = mtu;
 	alx->rxbuf_size = max(max_frame, ALX_DEF_RXBUF_SIZE);
+	head_size = SKB_DATA_ALIGN(alx->rxbuf_size + NET_SKB_PAD) +
+		    SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+	alx->rx_frag_size = roundup_pow_of_two(head_size);
 	netdev_update_features(netdev);
 	if (netif_running(netdev))
 		alx_reinit(alx);
-- 
2.1.0


From c1430dd4ef5ac3c0a8f268610c373a7cb3eaa89e Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Thu, 26 May 2016 00:40:23 +0200
Subject: [PATCH 17/24] net: stmmac: Fix incorrect memcpy source memory

[ Upstream commit 643d60bf575daaba93c1ac0d0e1c4b1d4ded1f75 ]

The memcpy() currently copies mdio_bus_data into new_bus->irq, which
makes no sense, since the mdio_bus_data structure contains more than
just irqs. The code was likely supposed to copy mdio_bus_data->irqs
into the new_bus->irq instead, so fix this.

Fixes: e7f4dc3536a4 ("mdio: Move allocation of interrupts into core")
Signed-off-by: Marek Vasut <marex@denx.de>
Cc: David S. Miller <davem@davemloft.net>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index 06704ca..8683a21 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -209,7 +209,7 @@ int stmmac_mdio_register(struct net_device *ndev)
 		return -ENOMEM;
 
 	if (mdio_bus_data->irqs)
-		memcpy(new_bus->irq, mdio_bus_data, sizeof(new_bus->irq));
+		memcpy(new_bus->irq, mdio_bus_data->irqs, sizeof(new_bus->irq));
 
 #ifdef CONFIG_OF
 	if (priv->device->of_node)
-- 
2.1.0


From 7666f3c7b0c495698ad263374137e349b66bb945 Mon Sep 17 00:00:00 2001
From: Chen Haiquan <oc@yunify.com>
Date: Fri, 27 May 2016 10:49:11 +0800
Subject: [PATCH 18/24] vxlan: Accept user specified MTU value when create new
 vxlan link

[ Upstream commit ce577668a426c6a9e2470a09dcd07fbd6e45272a ]

When create a new vxlan link, example:
  ip link add vtap mtu 1440 type vxlan vni 1 dev eth0

The argument "mtu" has no effect, because it is not set to conf->mtu. The
default value is used in vxlan_dev_configure function.

This problem was introduced by commit 0dfbdf4102b9 (vxlan: Factor out device
configuration).

Fixes: 0dfbdf4102b9 (vxlan: Factor out device configuration)
Signed-off-by:  Chen Haiquan <oc@yunify.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 9aa8678..7e29b55 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2959,6 +2959,9 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev,
 	if (data[IFLA_VXLAN_REMCSUM_NOPARTIAL])
 		conf.flags |= VXLAN_F_REMCSUM_NOPARTIAL;
 
+	if (tb[IFLA_MTU])
+		conf.mtu = nla_get_u32(tb[IFLA_MTU]);
+
 	err = vxlan_dev_configure(src_net, dev, &conf);
 	switch (err) {
 	case -ENODEV:
-- 
2.1.0


From ca043d21a63f21dc1dda15a642dcc68599198011 Mon Sep 17 00:00:00 2001
From: Elad Kanfi <eladkan@mellanox.com>
Date: Thu, 26 May 2016 15:00:06 +0300
Subject: [PATCH 19/24] net: nps_enet: Disable interrupts before napi
 reschedule

[ Upstream commit 86651650d16a359e4142c6a8b0467c87e48c4c94 ]

Since NAPI works by shutting down event interrupts when theres
work and turning them on when theres none, the net driver must
make sure that interrupts are disabled when it reschedules polling.
By calling napi_reschedule, the driver switches to polling mode,
therefor there should be no interrupt interference.
Any received packets will be handled in nps_enet_poll by polling the HW
indication of received packet until all packets are handled.

Signed-off-by: Elad Kanfi <eladkan@mellanox.com>
Acked-by: Noam Camus <noamca@mellanox.com>
Tested-by: Alexey Brodkin <abrodkin@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ezchip/nps_enet.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ezchip/nps_enet.c b/drivers/net/ethernet/ezchip/nps_enet.c
index 085f912..06f0317 100644
--- a/drivers/net/ethernet/ezchip/nps_enet.c
+++ b/drivers/net/ethernet/ezchip/nps_enet.c
@@ -205,8 +205,10 @@ static int nps_enet_poll(struct napi_struct *napi, int budget)
 		 * re-adding ourselves to the poll list.
 		 */
 
-		if (priv->tx_skb && !tx_ctrl_ct)
+		if (priv->tx_skb && !tx_ctrl_ct) {
+			nps_enet_reg_set(priv, NPS_ENET_REG_BUF_INT_ENABLE, 0);
 			napi_reschedule(napi);
+		}
 	}
 
 	return work_done;
-- 
2.1.0


From 66aa8c4947ca7d0b4ce498c60ac117fb034aca77 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Sat, 4 Jun 2016 20:50:59 +0200
Subject: [PATCH 20/24] bpf, trace: use READ_ONCE for retrieving file ptr

[ Upstream commit 5b6c1b4d46b0dae4edea636a776d09f2064f4cd7 ]

In bpf_perf_event_read() and bpf_perf_event_output(), we must use
READ_ONCE() for fetching the struct file pointer, which could get
updated concurrently, so we must prevent the compiler from potential
refetching.

We already do this with tail calls for fetching the related bpf_prog,
but not so on stored perf events. Semantics for both are the same
with regards to updates.

Fixes: a43eec304259 ("bpf: introduce bpf_perf_event_output() helper")
Fixes: 35578d798400 ("bpf: Implement function bpf_perf_event_read() that get the selected hardware PMU conuter")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/trace/bpf_trace.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 3e4ffb3..d028941 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -194,7 +194,7 @@ static u64 bpf_perf_event_read(u64 r1, u64 index, u64 r3, u64 r4, u64 r5)
 	if (unlikely(index >= array->map.max_entries))
 		return -E2BIG;
 
-	file = (struct file *)array->ptrs[index];
+	file = READ_ONCE(array->ptrs[index]);
 	if (unlikely(!file))
 		return -ENOENT;
 
@@ -238,7 +238,7 @@ static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 index, u64 r4, u64 size)
 	if (unlikely(index >= array->map.max_entries))
 		return -E2BIG;
 
-	file = (struct file *)array->ptrs[index];
+	file = READ_ONCE(array->ptrs[index]);
 	if (unlikely(!file))
 		return -ENOENT;
 
-- 
2.1.0


From b27e8f2fb3c6381a6655e6df5e99be3f0115d6fa Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Mon, 6 Jun 2016 15:07:18 -0700
Subject: [PATCH 21/24] tcp: record TLP and ER timer stats in v6 stats

[ Upstream commit ce3cf4ec0305919fc69a972f6c2b2efd35d36abc ]

The v6 tcp stats scan do not provide TLP and ER timer information
correctly like the v4 version . This patch fixes that.

Fixes: 6ba8a3b19e76 ("tcp: Tail loss probe (TLP)")
Fixes: eed530b6c676 ("tcp: early retransmit")
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/tcp_ipv6.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index f443c6b..f6d7516 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1717,7 +1717,9 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
 	destp = ntohs(inet->inet_dport);
 	srcp  = ntohs(inet->inet_sport);
 
-	if (icsk->icsk_pending == ICSK_TIME_RETRANS) {
+	if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
+	    icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
+	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
 		timer_active	= 1;
 		timer_expires	= icsk->icsk_timeout;
 	} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
-- 
2.1.0


From 3085e6dae40c4136091f13a9477c9fcac74db14c Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Tue, 7 Jun 2016 19:14:17 +0900
Subject: [PATCH 22/24] bridge: Don't insert unnecessary local fdb entry on
 changing mac address

[ Upstream commit 0b148def403153a4d1565f1640356cb78ce5109f ]

The missing br_vlan_should_use() test caused creation of an unneeded
local fdb entry on changing mac address of a bridge device when there is
a vlan which is configured on a bridge port but not on the bridge
device.

Fixes: 2594e9064a57 ("bridge: vlan: add per-vlan struct and move to rhashtables")
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_fdb.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index dcea4f4..c18080a 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -279,6 +279,8 @@ void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr)
 	 * change from under us.
 	 */
 	list_for_each_entry(v, &vg->vlan_list, vlist) {
+		if (!br_vlan_should_use(v))
+			continue;
 		f = __br_fdb_get(br, br->dev->dev_addr, v->vid);
 		if (f && f->is_local && !f->dst)
 			fdb_delete_local(br, NULL, f);
-- 
2.1.0


From 248ca552fa581f1489698e8a7c58c327cdee8375 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Wed, 8 Jun 2016 12:59:17 +0200
Subject: [PATCH 23/24] l2tp: fix configuration passed to
 setup_udp_tunnel_sock()

[ Upstream commit a5c5e2da8551eb69e5d5d09d51d526140b5db9fb ]

Unused fields of udp_cfg must be all zeros. Otherwise
setup_udp_tunnel_sock() fills ->gro_receive and ->gro_complete
callbacks with garbage, eventually resulting in panic when used by
udp_gro_receive().

[   72.694123] BUG: unable to handle kernel paging request at ffff880033f87d78
[   72.695518] IP: [<ffff880033f87d78>] 0xffff880033f87d78
[   72.696530] PGD 26e2067 PUD 26e3067 PMD 342ed063 PTE 8000000033f87163
[   72.696530] Oops: 0011 [#1] SMP KASAN
[   72.696530] Modules linked in: l2tp_ppp l2tp_netlink l2tp_core ip6_udp_tunnel udp_tunnel pptp gre pppox ppp_generic slhc crc32c_intel ghash_clmulni_intel jitterentropy_rng sha256_generic hmac drbg ansi_cprng aesni_intel evdev aes_x86_64 ablk_helper cryptd lrw gf128mul glue_helper serio_raw acpi_cpufreq button proc\
essor ext4 crc16 jbd2 mbcache virtio_blk virtio_net virtio_pci virtio_ring virtio
[   72.696530] CPU: 3 PID: 0 Comm: swapper/3 Not tainted 4.7.0-rc1 #1
[   72.696530] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Debian-1.8.2-1 04/01/2014
[   72.696530] task: ffff880035b59700 ti: ffff880035b70000 task.ti: ffff880035b70000
[   72.696530] RIP: 0010:[<ffff880033f87d78>]  [<ffff880033f87d78>] 0xffff880033f87d78
[   72.696530] RSP: 0018:ffff880035f87bc0  EFLAGS: 00010246
[   72.696530] RAX: ffffed000698f996 RBX: ffff88003326b840 RCX: ffffffff814cc823
[   72.696530] RDX: ffff88003326b840 RSI: ffff880033e48038 RDI: ffff880034c7c780
[   72.696530] RBP: ffff880035f87c18 R08: 000000000000a506 R09: 0000000000000000
[   72.696530] R10: ffff880035f87b38 R11: ffff880034b9344d R12: 00000000ebfea715
[   72.696530] R13: 0000000000000000 R14: ffff880034c7c780 R15: 0000000000000000
[   72.696530] FS:  0000000000000000(0000) GS:ffff880035f80000(0000) knlGS:0000000000000000
[   72.696530] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   72.696530] CR2: ffff880033f87d78 CR3: 0000000033c98000 CR4: 00000000000406a0
[   72.696530] Stack:
[   72.696530]  ffffffff814cc834 ffff880034b93468 0000001481416818 ffff88003326b874
[   72.696530]  ffff880034c7ccb0 ffff880033e48038 ffff88003326b840 ffff880034b93462
[   72.696530]  ffff88003326b88a ffff88003326b88c ffff880034b93468 ffff880035f87c70
[   72.696530] Call Trace:
[   72.696530]  <IRQ>
[   72.696530]  [<ffffffff814cc834>] ? udp_gro_receive+0x1c6/0x1f9
[   72.696530]  [<ffffffff814ccb1c>] udp4_gro_receive+0x2b5/0x310
[   72.696530]  [<ffffffff814d989b>] inet_gro_receive+0x4a3/0x4cd
[   72.696530]  [<ffffffff81431b32>] dev_gro_receive+0x584/0x7a3
[   72.696530]  [<ffffffff810adf7a>] ? __lock_is_held+0x29/0x64
[   72.696530]  [<ffffffff814321f7>] napi_gro_receive+0x124/0x21d
[   72.696530]  [<ffffffffa000b145>] virtnet_receive+0x8df/0x8f6 [virtio_net]
[   72.696530]  [<ffffffffa000b27e>] virtnet_poll+0x1d/0x8d [virtio_net]
[   72.696530]  [<ffffffff81431350>] net_rx_action+0x15b/0x3b9
[   72.696530]  [<ffffffff815893d6>] __do_softirq+0x216/0x546
[   72.696530]  [<ffffffff81062392>] irq_exit+0x49/0xb6
[   72.696530]  [<ffffffff81588e9a>] do_IRQ+0xe2/0xfa
[   72.696530]  [<ffffffff81587a49>] common_interrupt+0x89/0x89
[   72.696530]  <EOI>
[   72.696530]  [<ffffffff810b05df>] ? trace_hardirqs_on_caller+0x229/0x270
[   72.696530]  [<ffffffff8102b3c7>] ? default_idle+0x1c/0x2d
[   72.696530]  [<ffffffff8102b3c5>] ? default_idle+0x1a/0x2d
[   72.696530]  [<ffffffff8102bb8c>] arch_cpu_idle+0xa/0xc
[   72.696530]  [<ffffffff810a6c39>] default_idle_call+0x1a/0x1c
[   72.696530]  [<ffffffff810a6d96>] cpu_startup_entry+0x15b/0x20f
[   72.696530]  [<ffffffff81039a81>] start_secondary+0x12c/0x133
[   72.696530] Code: ff ff ff ff ff ff ff ff ff ff 7f ff ff ff ff ff ff ff 7f 00 7e f8 33 00 88 ff ff 6d 61 58 81 ff ff ff ff 5e de 0a 81 ff ff ff ff <00> 5c e2 34 00 88 ff ff 00 00 00 00 00 00 00 00 00 00 00 00 00
[   72.696530] RIP  [<ffff880033f87d78>] 0xffff880033f87d78
[   72.696530]  RSP <ffff880035f87bc0>
[   72.696530] CR2: ffff880033f87d78
[   72.696530] ---[ end trace ad7758b9a1dccf99 ]---
[   72.696530] Kernel panic - not syncing: Fatal exception in interrupt
[   72.696530] Kernel Offset: disabled
[   72.696530] ---[ end Kernel panic - not syncing: Fatal exception in interrupt

v2: use empty initialiser instead of "{ NULL }" to avoid relying on
    first field's type.

Fixes: 38fd2af24fcf ("udp: Add socket based GRO and config")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 6edfa99..1e40dac 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1581,7 +1581,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
 	/* Mark socket as an encapsulation socket. See net/ipv4/udp.c */
 	tunnel->encap = encap;
 	if (encap == L2TP_ENCAPTYPE_UDP) {
-		struct udp_tunnel_sock_cfg udp_cfg;
+		struct udp_tunnel_sock_cfg udp_cfg = { };
 
 		udp_cfg.sk_user_data = tunnel;
 		udp_cfg.encap_type = UDP_ENCAP_L2TPINUDP;
-- 
2.1.0


From f78020eb86c96d01400b09a749dfa867e1dbc2f1 Mon Sep 17 00:00:00 2001
From: Jakub Sitnicki <jkbs@redhat.com>
Date: Wed, 8 Jun 2016 15:13:34 +0200
Subject: [PATCH 24/24] ipv6: Skip XFRM lookup if dst_entry in socket cache is
 valid

[ Upstream commit 00bc0ef5880dc7b82f9c320dead4afaad48e47be ]

At present we perform an xfrm_lookup() for each UDPv6 message we
send. The lookup involves querying the flow cache (flow_cache_lookup)
and, in case of a cache miss, creating an XFRM bundle.

If we miss the flow cache, we can end up creating a new bundle and
deriving the path MTU (xfrm_init_pmtu) from on an already transformed
dst_entry, which we pass from the socket cache (sk->sk_dst_cache) down
to xfrm_lookup(). This can happen only if we're caching the dst_entry
in the socket, that is when we're using a connected UDP socket.

To put it another way, the path MTU shrinks each time we miss the flow
cache, which later on leads to incorrectly fragmented payload. It can
be observed with ESPv6 in transport mode:

  1) Set up a transformation and lower the MTU to trigger fragmentation
    # ip xfrm policy add dir out src ::1 dst ::1 \
      tmpl src ::1 dst ::1 proto esp spi 1
    # ip xfrm state add src ::1 dst ::1 \
      proto esp spi 1 enc 'aes' 0x0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b
    # ip link set dev lo mtu 1500

  2) Monitor the packet flow and set up an UDP sink
    # tcpdump -ni lo -ttt &
    # socat udp6-listen:12345,fork /dev/null &

  3) Send a datagram that needs fragmentation with a connected socket
    # perl -e 'print "@" x 1470 | socat - udp6:[::1]:12345
    2016/06/07 18:52:52 socat[724] E read(3, 0x555bb3d5ba00, 8192): Protocol error
    00:00:00.000000 IP6 ::1 > ::1: frag (0|1448) ESP(spi=0x00000001,seq=0x2), length 1448
    00:00:00.000014 IP6 ::1 > ::1: frag (1448|32)
    00:00:00.000050 IP6 ::1 > ::1: ESP(spi=0x00000001,seq=0x3), length 1272
    (^ ICMPv6 Parameter Problem)
    00:00:00.000022 IP6 ::1 > ::1: ESP(spi=0x00000001,seq=0x5), length 136

  4) Compare it to a non-connected socket
    # perl -e 'print "@" x 1500' | socat - udp6-sendto:[::1]:12345
    00:00:40.535488 IP6 ::1 > ::1: frag (0|1448) ESP(spi=0x00000001,seq=0x6), length 1448
    00:00:00.000010 IP6 ::1 > ::1: frag (1448|64)

What happens in step (3) is:

  1) when connecting the socket in __ip6_datagram_connect(), we
     perform an XFRM lookup, miss the flow cache, create an XFRM
     bundle, and cache the destination,

  2) afterwards, when sending the datagram, we perform an XFRM lookup,
     again, miss the flow cache (due to mismatch of flowi6_iif and
     flowi6_oif, which is an issue of its own), and recreate an XFRM
     bundle based on the cached (and already transformed) destination.

To prevent the recreation of an XFRM bundle, avoid an XFRM lookup
altogether whenever we already have a destination entry cached in the
socket. This prevents the path MTU shrinkage and brings us on par with
UDPv4.

The fix also benefits connected PINGv6 sockets, another user of
ip6_sk_dst_lookup_flow(), who also suffer messages being transformed
twice.

Joint work with Hannes Frederic Sowa.

Reported-by: Jan Tluka <jtluka@redhat.com>
Signed-off-by: Jakub Sitnicki <jkbs@redhat.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_output.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index bc972e7..da88de8 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1071,17 +1071,12 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
 					 const struct in6_addr *final_dst)
 {
 	struct dst_entry *dst = sk_dst_check(sk, inet6_sk(sk)->dst_cookie);
-	int err;
 
 	dst = ip6_sk_dst_check(sk, dst, fl6);
+	if (!dst)
+		dst = ip6_dst_lookup_flow(sk, fl6, final_dst);
 
-	err = ip6_dst_lookup_tail(sock_net(sk), sk, &dst, fl6);
-	if (err)
-		return ERR_PTR(err);
-	if (final_dst)
-		fl6->daddr = *final_dst;
-
-	return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
+	return dst;
 }
 EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow);
 
-- 
2.1.0

Re: [PATCHES] Networking

[Greg KH]

On Fri, Jun 17, 2016 at 12:03:46AM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for 4.4, 4.5,
> and 4.6 -stable, respectively.

Unfortunately 4.5 is now end-of-life, but thanks for those patches
anyway, hopefully someone can use them if they depend on that tree.

I've queued up the 4.4 and 4.6 patch sets.

thanks,

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 93 bytes --]


Please queue up the following bug fixes for 4.4.x and 4.6.x -stable,
respectively.

Thanks!

[-- Attachment #2: net_44.mbox --]
[-- Type: Application/Octet-Stream, Size: 40237 bytes --]

From 4c3ba35450f6815bbb4e278ebffcd39ddf7dfdf8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 12 Jun 2016 20:01:25 -0700
Subject: [PATCH 01/14] net_sched: fix pfifo_head_drop behavior vs backlog

[ Upstream commit 6c0d54f1897d229748d4f41ef919078db6db2123 ]

When the qdisc is full, we drop a packet at the head of the queue,
queue the current skb and return NET_XMIT_CN

Now we track backlog on upper qdiscs, we need to call
qdisc_tree_reduce_backlog(), even if the qlen did not change.

Fixes: 2ccccf5fb43f ("net_sched: update hierarchical backlog too")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: WANG Cong <xiyou.wangcong@gmail.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_fifo.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c
index 2177eac..2e4bd2c 100644
--- a/net/sched/sch_fifo.c
+++ b/net/sched/sch_fifo.c
@@ -37,14 +37,18 @@ static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 
 static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 {
+	unsigned int prev_backlog;
+
 	if (likely(skb_queue_len(&sch->q) < sch->limit))
 		return qdisc_enqueue_tail(skb, sch);
 
+	prev_backlog = sch->qstats.backlog;
 	/* queue full, remove one skb to fulfill the limit */
 	__qdisc_queue_drop_head(sch, &sch->q);
 	qdisc_qstats_drop(sch);
 	qdisc_enqueue_tail(skb, sch);
 
+	qdisc_tree_reduce_backlog(sch, 0, prev_backlog - sch->qstats.backlog);
 	return NET_XMIT_CN;
 }
 
-- 
2.1.0


From 2c420e28b8fbd717e8f272da7da59a417e6a8b75 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Wed, 15 Jun 2016 11:14:53 +0200
Subject: [PATCH 02/14] net: Don't forget pr_fmt on net_dbg_ratelimited for
 CONFIG_DYNAMIC_DEBUG

[ Upstream commit daddef76c3deaaa7922f9d7b18edbf0a061215c3 ]

The implementation of net_dbg_ratelimited in the CONFIG_DYNAMIC_DEBUG
case was added with 2c94b5373 ("net: Implement net_dbg_ratelimited() for
CONFIG_DYNAMIC_DEBUG case"). The implementation strategy was to take the
usual definition of the dynamic_pr_debug macro, but alter it by adding a
call to "net_ratelimit()" in the if statement. This is, in fact, the
correct approach.

However, while doing this, the author of the commit forgot to surround
fmt by pr_fmt, resulting in unprefixed log messages appearing in the
console. So, this commit adds back the pr_fmt(fmt) invocation, making
net_dbg_ratelimited properly consistent across DEBUG, no DEBUG, and
DYNAMIC_DEBUG cases, and bringing parity with the behavior of
dynamic_pr_debug as well.

Fixes: 2c94b5373 ("net: Implement net_dbg_ratelimited() for CONFIG_DYNAMIC_DEBUG case")
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Cc: Tim Bingham <tbingham@akamai.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/net.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/linux/net.h b/include/linux/net.h
index 25ef630..c00b8d1 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -251,7 +251,8 @@ do {									\
 	DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt);			\
 	if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT) &&	\
 	    net_ratelimit())						\
-		__dynamic_pr_debug(&descriptor, fmt, ##__VA_ARGS__);	\
+		__dynamic_pr_debug(&descriptor, pr_fmt(fmt),		\
+		                   ##__VA_ARGS__);			\
 } while (0)
 #elif defined(DEBUG)
 #define net_dbg_ratelimited(fmt, ...)				\
-- 
2.1.0


From 0ba7565645b7bf5b1446bf94dfec594940999a8b Mon Sep 17 00:00:00 2001
From: Simon Horman <simon.horman@netronome.com>
Date: Thu, 16 Jun 2016 17:06:19 +0900
Subject: [PATCH 03/14] sit: correct IP protocol used in ipip6_err

[ Upstream commit d5d8760b78d0cfafe292f965f599988138b06a70 ]

Since 32b8a8e59c9c ("sit: add IPv4 over IPv4 support")
ipip6_err() may be called for packets whose IP protocol is
IPPROTO_IPIP as well as those whose IP protocol is IPPROTO_IPV6.

In the case of IPPROTO_IPIP packets the correct protocol value is not
passed to ipv4_update_pmtu() or ipv4_redirect().

This patch resolves this problem by using the IP protocol of the packet
rather than a hard-coded value. This appears to be consistent
with the usage of the protocol of a packet by icmp_socket_deliver()
the caller of ipip6_err().

I was able to exercise the redirect case by using a setup where an ICMP
redirect was received for the destination of the encapsulated packet.
However, it appears that although incorrect the protocol field is not used
in this case and thus no problem manifests.  On inspection it does not
appear that a problem will manifest in the fragmentation needed/update pmtu
case either.

In short I believe this is a cosmetic fix. None the less, the use of
IPPROTO_IPV6 seems wrong and confusing.

Reviewed-by: Dinan Gunawardena <dinan.gunawardena@netronome.com>
Signed-off-by: Simon Horman <simon.horman@netronome.com>
Acked-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index dcccae8..ba3d2f3 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -560,13 +560,13 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
 
 	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
 		ipv4_update_pmtu(skb, dev_net(skb->dev), info,
-				 t->parms.link, 0, IPPROTO_IPV6, 0);
+				 t->parms.link, 0, iph->protocol, 0);
 		err = 0;
 		goto out;
 	}
 	if (type == ICMP_REDIRECT) {
 		ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0,
-			      IPPROTO_IPV6, 0);
+			      iph->protocol, 0);
 		err = 0;
 		goto out;
 	}
-- 
2.1.0


From 7368e06d43084261a895b7d14b60480f42752d0f Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Sat, 18 Jun 2016 13:03:36 +0800
Subject: [PATCH 04/14] esp: Fix ESN generation under UDP encapsulation

[ Upstream commit 962fcef33b03395051367181a0549d29d109d9a4 ]

Blair Steven noticed that ESN in conjunction with UDP encapsulation
is broken because we set the temporary ESP header to the wrong spot.

This patch fixes this by first of all using the right spot, i.e.,
4 bytes off the real ESP header, and then saving this information
so that after encryption we can restore it properly.

Fixes: 7021b2e1cddd ("esp4: Switch to new AEAD interface")
Reported-by: Blair Steven <Blair.Steven@alliedtelesis.co.nz>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/esp4.c | 52 ++++++++++++++++++++++++++++++++--------------------
 1 file changed, 32 insertions(+), 20 deletions(-)

diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 4779374..d95631d 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -23,6 +23,11 @@ struct esp_skb_cb {
 	void *tmp;
 };
 
+struct esp_output_extra {
+	__be32 seqhi;
+	u32 esphoff;
+};
+
 #define ESP_SKB_CB(__skb) ((struct esp_skb_cb *)&((__skb)->cb[0]))
 
 static u32 esp4_get_mtu(struct xfrm_state *x, int mtu);
@@ -35,11 +40,11 @@ static u32 esp4_get_mtu(struct xfrm_state *x, int mtu);
  *
  * TODO: Use spare space in skb for this where possible.
  */
-static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int seqhilen)
+static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int extralen)
 {
 	unsigned int len;
 
-	len = seqhilen;
+	len = extralen;
 
 	len += crypto_aead_ivsize(aead);
 
@@ -57,15 +62,16 @@ static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int seqhilen)
 	return kmalloc(len, GFP_ATOMIC);
 }
 
-static inline __be32 *esp_tmp_seqhi(void *tmp)
+static inline void *esp_tmp_extra(void *tmp)
 {
-	return PTR_ALIGN((__be32 *)tmp, __alignof__(__be32));
+	return PTR_ALIGN(tmp, __alignof__(struct esp_output_extra));
 }
-static inline u8 *esp_tmp_iv(struct crypto_aead *aead, void *tmp, int seqhilen)
+
+static inline u8 *esp_tmp_iv(struct crypto_aead *aead, void *tmp, int extralen)
 {
 	return crypto_aead_ivsize(aead) ?
-	       PTR_ALIGN((u8 *)tmp + seqhilen,
-			 crypto_aead_alignmask(aead) + 1) : tmp + seqhilen;
+	       PTR_ALIGN((u8 *)tmp + extralen,
+			 crypto_aead_alignmask(aead) + 1) : tmp + extralen;
 }
 
 static inline struct aead_request *esp_tmp_req(struct crypto_aead *aead, u8 *iv)
@@ -99,7 +105,7 @@ static void esp_restore_header(struct sk_buff *skb, unsigned int offset)
 {
 	struct ip_esp_hdr *esph = (void *)(skb->data + offset);
 	void *tmp = ESP_SKB_CB(skb)->tmp;
-	__be32 *seqhi = esp_tmp_seqhi(tmp);
+	__be32 *seqhi = esp_tmp_extra(tmp);
 
 	esph->seq_no = esph->spi;
 	esph->spi = *seqhi;
@@ -107,7 +113,11 @@ static void esp_restore_header(struct sk_buff *skb, unsigned int offset)
 
 static void esp_output_restore_header(struct sk_buff *skb)
 {
-	esp_restore_header(skb, skb_transport_offset(skb) - sizeof(__be32));
+	void *tmp = ESP_SKB_CB(skb)->tmp;
+	struct esp_output_extra *extra = esp_tmp_extra(tmp);
+
+	esp_restore_header(skb, skb_transport_offset(skb) + extra->esphoff -
+				sizeof(__be32));
 }
 
 static void esp_output_done_esn(struct crypto_async_request *base, int err)
@@ -121,6 +131,7 @@ static void esp_output_done_esn(struct crypto_async_request *base, int err)
 static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 {
 	int err;
+	struct esp_output_extra *extra;
 	struct ip_esp_hdr *esph;
 	struct crypto_aead *aead;
 	struct aead_request *req;
@@ -137,8 +148,7 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 	int tfclen;
 	int nfrags;
 	int assoclen;
-	int seqhilen;
-	__be32 *seqhi;
+	int extralen;
 	__be64 seqno;
 
 	/* skb is pure payload to encrypt */
@@ -166,21 +176,21 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 	nfrags = err;
 
 	assoclen = sizeof(*esph);
-	seqhilen = 0;
+	extralen = 0;
 
 	if (x->props.flags & XFRM_STATE_ESN) {
-		seqhilen += sizeof(__be32);
-		assoclen += seqhilen;
+		extralen += sizeof(*extra);
+		assoclen += sizeof(__be32);
 	}
 
-	tmp = esp_alloc_tmp(aead, nfrags, seqhilen);
+	tmp = esp_alloc_tmp(aead, nfrags, extralen);
 	if (!tmp) {
 		err = -ENOMEM;
 		goto error;
 	}
 
-	seqhi = esp_tmp_seqhi(tmp);
-	iv = esp_tmp_iv(aead, tmp, seqhilen);
+	extra = esp_tmp_extra(tmp);
+	iv = esp_tmp_iv(aead, tmp, extralen);
 	req = esp_tmp_req(aead, iv);
 	sg = esp_req_sg(aead, req);
 
@@ -247,8 +257,10 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 	 * encryption.
 	 */
 	if ((x->props.flags & XFRM_STATE_ESN)) {
-		esph = (void *)(skb_transport_header(skb) - sizeof(__be32));
-		*seqhi = esph->spi;
+		extra->esphoff = (unsigned char *)esph -
+				 skb_transport_header(skb);
+		esph = (struct ip_esp_hdr *)((unsigned char *)esph - 4);
+		extra->seqhi = esph->spi;
 		esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.hi);
 		aead_request_set_callback(req, 0, esp_output_done_esn, skb);
 	}
@@ -445,7 +457,7 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb)
 		goto out;
 
 	ESP_SKB_CB(skb)->tmp = tmp;
-	seqhi = esp_tmp_seqhi(tmp);
+	seqhi = esp_tmp_extra(tmp);
 	iv = esp_tmp_iv(aead, tmp, seqhilen);
 	req = esp_tmp_req(aead, iv);
 	sg = esp_req_sg(aead, req);
-- 
2.1.0


From c0faa64ecef6e1c6412a94759b790957cdb2aafa Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 20 Jun 2016 15:00:43 -0700
Subject: [PATCH 05/14] netem: fix a use after free

[ Upstream commit 21de12ee5568fd1aec47890c72967abf791ac80a ]

If the packet was dropped by lower qdisc, then we must not
access it later.

Save qdisc_pkt_len(skb) in a temp variable.

Fixes: 2ccccf5fb43f ("net_sched: update hierarchical backlog too")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: WANG Cong <xiyou.wangcong@gmail.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_netem.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 4befe97..b7c29d5 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -650,14 +650,14 @@ deliver:
 #endif
 
 			if (q->qdisc) {
+				unsigned int pkt_len = qdisc_pkt_len(skb);
 				int err = qdisc_enqueue(skb, q->qdisc);
 
-				if (unlikely(err != NET_XMIT_SUCCESS)) {
-					if (net_xmit_drop_count(err)) {
-						qdisc_qstats_drop(sch);
-						qdisc_tree_reduce_backlog(sch, 1,
-									  qdisc_pkt_len(skb));
-					}
+				if (err != NET_XMIT_SUCCESS &&
+				    net_xmit_drop_count(err)) {
+					qdisc_qstats_drop(sch);
+					qdisc_tree_reduce_backlog(sch, 1,
+								  pkt_len);
 				}
 				goto tfifo_dequeue;
 			}
-- 
2.1.0


From f4406d670f66fe84b7f42f7c37e2fdf0b46e1fd1 Mon Sep 17 00:00:00 2001
From: Tom Goff <thomas.goff@ll.mit.edu>
Date: Thu, 23 Jun 2016 16:11:57 -0400
Subject: [PATCH 06/14] ipmr/ip6mr: Initialize the last assert time of mfc
 entries.

[ Upstream commit 70a0dec45174c976c64b4c8c1d0898581f759948 ]

This fixes wrong-interface signaling on 32-bit platforms for entries
created when jiffies > 2^31 + MFC_ASSERT_THRESH.

Signed-off-by: Tom Goff <thomas.goff@ll.mit.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ipmr.c  | 4 +++-
 net/ipv6/ip6mr.c | 1 +
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index c3a3835..9d1e555 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -882,8 +882,10 @@ static struct mfc_cache *ipmr_cache_alloc(void)
 {
 	struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL);
 
-	if (c)
+	if (c) {
+		c->mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1;
 		c->mfc_un.res.minvif = MAXVIFS;
+	}
 	return c;
 }
 
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index a10e771..e207cb2 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1074,6 +1074,7 @@ static struct mfc6_cache *ip6mr_cache_alloc(void)
 	struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL);
 	if (!c)
 		return NULL;
+	c->mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1;
 	c->mfc_un.res.minvif = MAXMIFS;
 	return c;
 }
-- 
2.1.0


From 0819bdaf153c03de0e8da88092cd09b9d34bf4ad Mon Sep 17 00:00:00 2001
From: daniel <daniel@dd-wrt.com>
Date: Fri, 24 Jun 2016 12:35:18 +0200
Subject: [PATCH 07/14] Bridge: Fix ipv6 mc snooping if bridge has no ipv6
 address
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 0888d5f3c0f183ea6177355752ada433d370ac89 ]

The bridge is falsly dropping ipv6 mulitcast packets if there is:
 1. No ipv6 address assigned on the brigde.
 2. No external mld querier present.
 3. The internal querier enabled.

When the bridge fails to build mld queries, because it has no
ipv6 address, it slilently returns, but keeps the local querier enabled.
This specific case causes confusing packet loss.

Ipv6 multicast snooping can only work if:
 a) An external querier is present
 OR
 b) The bridge has an ipv6 address an is capable of sending own queries

Otherwise it has to forward/flood the ipv6 multicast traffic,
because snooping cannot work.

This patch fixes the issue by adding a flag to the bridge struct that
indicates that there is currently no ipv6 address assinged to the bridge
and returns a false state for the local querier in
__br_multicast_querier_exists().

Special thanks to Linus Lüssing.

Fixes: d1d81d4c3dd8 ("bridge: check return value of ipv6_dev_get_saddr()")
Signed-off-by: Daniel Danzberger <daniel@dd-wrt.com>
Acked-by: Linus Lüssing <linus.luessing@c0d3.blue>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c |  4 ++++
 net/bridge/br_private.h   | 23 +++++++++++++++++++----
 2 files changed, 23 insertions(+), 4 deletions(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index ea98937..7173a68 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -464,8 +464,11 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br,
 	if (ipv6_dev_get_saddr(dev_net(br->dev), br->dev, &ip6h->daddr, 0,
 			       &ip6h->saddr)) {
 		kfree_skb(skb);
+		br->has_ipv6_addr = 0;
 		return NULL;
 	}
+
+	br->has_ipv6_addr = 1;
 	ipv6_eth_mc_map(&ip6h->daddr, eth->h_dest);
 
 	hopopt = (u8 *)(ip6h + 1);
@@ -1736,6 +1739,7 @@ void br_multicast_init(struct net_bridge *br)
 	br->ip6_other_query.delay_time = 0;
 	br->ip6_querier.port = NULL;
 #endif
+	br->has_ipv6_addr = 1;
 
 	spin_lock_init(&br->multicast_lock);
 	setup_timer(&br->multicast_router_timer,
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 216018c..1001a1b 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -301,6 +301,7 @@ struct net_bridge
 	u8				multicast_disabled:1;
 	u8				multicast_querier:1;
 	u8				multicast_query_use_ifaddr:1;
+	u8				has_ipv6_addr:1;
 
 	u32				hash_elasticity;
 	u32				hash_max;
@@ -574,10 +575,22 @@ static inline bool br_multicast_is_router(struct net_bridge *br)
 
 static inline bool
 __br_multicast_querier_exists(struct net_bridge *br,
-			      struct bridge_mcast_other_query *querier)
+				struct bridge_mcast_other_query *querier,
+				const bool is_ipv6)
 {
+	bool own_querier_enabled;
+
+	if (br->multicast_querier) {
+		if (is_ipv6 && !br->has_ipv6_addr)
+			own_querier_enabled = false;
+		else
+			own_querier_enabled = true;
+	} else {
+		own_querier_enabled = false;
+	}
+
 	return time_is_before_jiffies(querier->delay_time) &&
-	       (br->multicast_querier || timer_pending(&querier->timer));
+	       (own_querier_enabled || timer_pending(&querier->timer));
 }
 
 static inline bool br_multicast_querier_exists(struct net_bridge *br,
@@ -585,10 +598,12 @@ static inline bool br_multicast_querier_exists(struct net_bridge *br,
 {
 	switch (eth->h_proto) {
 	case (htons(ETH_P_IP)):
-		return __br_multicast_querier_exists(br, &br->ip4_other_query);
+		return __br_multicast_querier_exists(br,
+			&br->ip4_other_query, false);
 #if IS_ENABLED(CONFIG_IPV6)
 	case (htons(ETH_P_IPV6)):
-		return __br_multicast_querier_exists(br, &br->ip6_other_query);
+		return __br_multicast_querier_exists(br,
+			&br->ip6_other_query, true);
 #endif
 	default:
 		return false;
-- 
2.1.0


From 85f9faa9e38b94c5f9497ba9cdf223d3396565b4 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 24 Jun 2016 16:02:35 -0400
Subject: [PATCH 08/14] sock_diag: do not broadcast raw socket destruction

[ Upstream commit 9a0fee2b552b1235fb1706ae1fc664ae74573be8 ]

Diag intends to broadcast tcp_sk and udp_sk socket destruction.
Testing sk->sk_protocol for IPPROTO_TCP/IPPROTO_UDP alone is not
sufficient for this. Raw sockets can have the same type.

Add a test for sk->sk_type.

Fixes: eb4cb008529c ("sock_diag: define destruction multicast groups")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/sock_diag.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h
index fddebc6..8ff34ed1 100644
--- a/include/linux/sock_diag.h
+++ b/include/linux/sock_diag.h
@@ -35,6 +35,9 @@ enum sknetlink_groups sock_diag_destroy_group(const struct sock *sk)
 {
 	switch (sk->sk_family) {
 	case AF_INET:
+		if (sk->sk_type == SOCK_RAW)
+			return SKNLGRP_NONE;
+
 		switch (sk->sk_protocol) {
 		case IPPROTO_TCP:
 			return SKNLGRP_INET_TCP_DESTROY;
@@ -44,6 +47,9 @@ enum sknetlink_groups sock_diag_destroy_group(const struct sock *sk)
 			return SKNLGRP_NONE;
 		}
 	case AF_INET6:
+		if (sk->sk_type == SOCK_RAW)
+			return SKNLGRP_NONE;
+
 		switch (sk->sk_protocol) {
 		case IPPROTO_TCP:
 			return SKNLGRP_INET6_TCP_DESTROY;
-- 
2.1.0


From 18fee7b6c4f0cbb61658456964caa8d97ffed960 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Mon, 27 Jun 2016 21:38:11 +0200
Subject: [PATCH 09/14] bpf, perf: delay release of BPF prog after grace period

[ Upstream commit ceb56070359b7329b5678b5d95a376fcb24767be ]

Commit dead9f29ddcc ("perf: Fix race in BPF program unregister") moved
destruction of BPF program from free_event_rcu() callback to __free_event(),
which is problematic if used with tail calls: if prog A is attached as
trace event directly, but at the same time present in a tail call map used
by another trace event program elsewhere, then we need to delay destruction
via RCU grace period since it can still be in use by the program doing the
tail call (the prog first needs to be dropped from the tail call map, then
trace event with prog A attached destroyed, so we get immediate destruction).

Fixes: dead9f29ddcc ("perf: Fix race in BPF program unregister")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Cc: Jann Horn <jann@thejh.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/bpf.h  | 4 ++++
 kernel/events/core.c | 2 +-
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 67bc2da..4f6d29c 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -198,6 +198,10 @@ static inline struct bpf_prog *bpf_prog_get(u32 ufd)
 static inline void bpf_prog_put(struct bpf_prog *prog)
 {
 }
+
+static inline void bpf_prog_put_rcu(struct bpf_prog *prog)
+{
+}
 #endif /* CONFIG_BPF_SYSCALL */
 
 /* verifier prototypes for helper functions called from eBPF programs */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 95e47d2..12ecd4f 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7101,7 +7101,7 @@ static void perf_event_free_bpf_prog(struct perf_event *event)
 	prog = event->tp_event->prog;
 	if (prog) {
 		event->tp_event->prog = NULL;
-		bpf_prog_put(prog);
+		bpf_prog_put_rcu(prog);
 	}
 }
 
-- 
2.1.0


From a7db24f1dc141746d9d7e277b5b54c2cc21fe3c5 Mon Sep 17 00:00:00 2001
From: David Barroso <dbarroso@fastly.com>
Date: Tue, 28 Jun 2016 11:16:43 +0300
Subject: [PATCH 10/14] neigh: Explicitly declare RCU-bh read side critical
 section in neigh_xmit()

[ Upstream commit b560f03ddfb072bca65e9440ff0dc4f9b1d1f056 ]

neigh_xmit() expects to be called inside an RCU-bh read side critical
section, and while one of its two current callers gets this right, the
other one doesn't.

More specifically, neigh_xmit() has two callers, mpls_forward() and
mpls_output(), and while both callers call neigh_xmit() under
rcu_read_lock(), this provides sufficient protection for neigh_xmit()
only in the case of mpls_forward(), as that is always called from
softirq context and therefore doesn't need explicit BH protection,
while mpls_output() can be called from process context with softirqs
enabled.

When mpls_output() is called from process context, with softirqs
enabled, we can be preempted by a softirq at any time, and RCU-bh
considers the completion of a softirq as signaling the end of any
pending read-side critical sections, so if we do get a softirq
while we are in the part of neigh_xmit() that expects to be run inside
an RCU-bh read side critical section, we can end up with an unexpected
RCU grace period running right in the middle of that critical section,
making things go boom.

This patch fixes this impedance mismatch in the callee, by making
neigh_xmit() always take rcu_read_{,un}lock_bh() around the code that
expects to be treated as an RCU-bh read side critical section, as this
seems a safer option than fixing it in the callers.

Fixes: 4fd3d7d9e868f ("neigh: Add helper function neigh_xmit")
Signed-off-by: David Barroso <dbarroso@fastly.com>
Signed-off-by: Lennert Buytenhek <lbuytenhek@fastly.com>
Acked-by: David Ahern <dsa@cumulusnetworks.com>
Acked-by: Robert Shearman <rshearma@brocade.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index f18ae91..769cece 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2467,13 +2467,17 @@ int neigh_xmit(int index, struct net_device *dev,
 		tbl = neigh_tables[index];
 		if (!tbl)
 			goto out;
+		rcu_read_lock_bh();
 		neigh = __neigh_lookup_noref(tbl, addr, dev);
 		if (!neigh)
 			neigh = __neigh_create(tbl, addr, dev, false);
 		err = PTR_ERR(neigh);
-		if (IS_ERR(neigh))
+		if (IS_ERR(neigh)) {
+			rcu_read_unlock_bh();
 			goto out_kfree_skb;
+		}
 		err = neigh->output(neigh, skb);
+		rcu_read_unlock_bh();
 	}
 	else if (index == NEIGH_LINK_TABLE) {
 		err = dev_hard_header(skb, dev, ntohs(skb->protocol),
-- 
2.1.0


From 3cc2fa9654e6a4a9bfb09b668b043a58d336ba05 Mon Sep 17 00:00:00 2001
From: Nicolas Ferre <nicolas.ferre@atmel.com>
Date: Thu, 10 Mar 2016 16:44:32 +0100
Subject: [PATCH 11/14] net: macb: fix default configuration for GMAC on AT91

[ Upstream commit 6bdaa5e9ed39b3b3328f35d218e8ad5a99cfc4d2 ]

On AT91 SoCs, the User Register (USRIO) exposes a switch to configure the
"Reduced" or "Traditional" version of the Media Independent Interface
(RMII vs. MII or RGMII vs. GMII).
As on the older EMAC version, on GMAC, this switch is set by default to the
non-reduced type of interface, so use the existing capability and extend it to
GMII as well. We then keep the current logic in the macb_init() function.

The capabilities of sama5d2, sama5d4 and sama5d3 GEM interface are updated in
the macb_config structure to be able to properly enable them with a traditional
interface (GMII or MII).

Reported-by: Romain HENRIET <romain.henriet@l-acoustics.com>
Signed-off-by: Nicolas Ferre <nicolas.ferre@atmel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
[cyrille.pitchen@atmel.com: backported to 4.4.y]
Signed-off-by: Cyrille Pitchen <cyrille.pitchen@atmel.com>
---
 drivers/net/ethernet/cadence/macb.c | 13 +++++++------
 drivers/net/ethernet/cadence/macb.h |  2 +-
 2 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index 169059c..8d54e7b 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -2405,9 +2405,9 @@ static int macb_init(struct platform_device *pdev)
 	if (bp->phy_interface == PHY_INTERFACE_MODE_RGMII)
 		val = GEM_BIT(RGMII);
 	else if (bp->phy_interface == PHY_INTERFACE_MODE_RMII &&
-		 (bp->caps & MACB_CAPS_USRIO_DEFAULT_IS_MII))
+		 (bp->caps & MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII))
 		val = MACB_BIT(RMII);
-	else if (!(bp->caps & MACB_CAPS_USRIO_DEFAULT_IS_MII))
+	else if (!(bp->caps & MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII))
 		val = MACB_BIT(MII);
 
 	if (bp->caps & MACB_CAPS_USRIO_HAS_CLKEN)
@@ -2738,7 +2738,7 @@ static int at91ether_init(struct platform_device *pdev)
 }
 
 static const struct macb_config at91sam9260_config = {
-	.caps = MACB_CAPS_USRIO_HAS_CLKEN | MACB_CAPS_USRIO_DEFAULT_IS_MII,
+	.caps = MACB_CAPS_USRIO_HAS_CLKEN | MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII,
 	.clk_init = macb_clk_init,
 	.init = macb_init,
 };
@@ -2751,21 +2751,22 @@ static const struct macb_config pc302gem_config = {
 };
 
 static const struct macb_config sama5d2_config = {
-	.caps = 0,
+	.caps = MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII,
 	.dma_burst_length = 16,
 	.clk_init = macb_clk_init,
 	.init = macb_init,
 };
 
 static const struct macb_config sama5d3_config = {
-	.caps = MACB_CAPS_SG_DISABLED | MACB_CAPS_GIGABIT_MODE_AVAILABLE,
+	.caps = MACB_CAPS_SG_DISABLED | MACB_CAPS_GIGABIT_MODE_AVAILABLE
+	      | MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII,
 	.dma_burst_length = 16,
 	.clk_init = macb_clk_init,
 	.init = macb_init,
 };
 
 static const struct macb_config sama5d4_config = {
-	.caps = 0,
+	.caps = MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII,
 	.dma_burst_length = 4,
 	.clk_init = macb_clk_init,
 	.init = macb_init,
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index d83b0db..3f385ab 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -398,7 +398,7 @@
 /* Capability mask bits */
 #define MACB_CAPS_ISR_CLEAR_ON_WRITE		0x00000001
 #define MACB_CAPS_USRIO_HAS_CLKEN		0x00000002
-#define MACB_CAPS_USRIO_DEFAULT_IS_MII		0x00000004
+#define MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII	0x00000004
 #define MACB_CAPS_NO_GIGABIT_HALF		0x00000008
 #define MACB_CAPS_FIFO_MODE			0x10000000
 #define MACB_CAPS_GIGABIT_MODE_AVAILABLE	0x20000000
-- 
2.1.0


From 296da20dbac607e4b8088c42aca1f2053697852b Mon Sep 17 00:00:00 2001
From: Feng Tang <feng.tang@intel.com>
Date: Fri, 24 Jun 2016 15:26:05 +0800
Subject: [PATCH 12/14] net: alx: Work around the DMA RX overflow issue

[ Upstream commit 881d0327db37ad917a367c77aff1afa1ee41e0a9 ]

Note: This is a verified backported patch for stable 4.4 kernel, and it
could also be applied to 4.3/4.2/4.1/3.18/3.16

There is a problem with alx devices, that the network link will be
lost in 1-5 minutes after the device is up.

>From debugging without datasheet, we found the error always
happen when the DMA RX address is set to 0x....fc0, which is very
likely to be a HW/silicon problem.

This patch will apply rx skb with 64 bytes longer space, and if the
allocated skb has a 0x...fc0 address, it will use skb_resever(skb, 64)
to advance the address, so that the RX overflow can be avoided.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=70761
Signed-off-by: Feng Tang <feng.tang@intel.com>
Suggested-by: Eric Dumazet <edumazet@google.com>
Tested-by: Ole Lukoie <olelukoie@mail.ru>
---
 drivers/net/ethernet/atheros/alx/main.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index bd377a6..df54475 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -86,9 +86,14 @@ static int alx_refill_rx_ring(struct alx_priv *alx, gfp_t gfp)
 	while (!cur_buf->skb && next != rxq->read_idx) {
 		struct alx_rfd *rfd = &rxq->rfd[cur];
 
-		skb = __netdev_alloc_skb(alx->dev, alx->rxbuf_size, gfp);
+		skb = __netdev_alloc_skb(alx->dev, alx->rxbuf_size + 64, gfp);
 		if (!skb)
 			break;
+
+		/* Workround for the HW RX DMA overflow issue */
+		if (((unsigned long)skb->data & 0xfff) == 0xfc0)
+			skb_reserve(skb, 64);
+
 		dma = dma_map_single(&alx->hw.pdev->dev,
 				     skb->data, alx->rxbuf_size,
 				     DMA_FROM_DEVICE);
-- 
2.1.0


From ac36729a3e056ccaf48c77adcc7b47a6c63afaba Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 19 Feb 2016 23:05:25 +0100
Subject: [PATCH 13/14] bpf: try harder on clones when writing into skb

[ Upstream commit 3697649ff29e0f647565eed04b27a7779c646a22 ]

When we're dealing with clones and the area is not writeable, try
harder and get a copy via pskb_expand_head(). Replace also other
occurences in tc actions with the new skb_try_make_writable().

Reported-by: Ashhad Sheikh <ashhadsheikh394@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h |  7 +++++++
 net/core/filter.c      | 18 ++++++++++--------
 net/sched/act_csum.c   |  8 ++------
 net/sched/act_nat.c    | 18 +++++-------------
 4 files changed, 24 insertions(+), 27 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 4fde618..1716f93 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2564,6 +2564,13 @@ static inline int skb_clone_writable(const struct sk_buff *skb, unsigned int len
 	       skb_headroom(skb) + len <= skb->hdr_len;
 }
 
+static inline int skb_try_make_writable(struct sk_buff *skb,
+					unsigned int write_len)
+{
+	return skb_cloned(skb) && !skb_clone_writable(skb, write_len) &&
+	       pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
+}
+
 static inline int __skb_cow(struct sk_buff *skb, unsigned int headroom,
 			    int cloned)
 {
diff --git a/net/core/filter.c b/net/core/filter.c
index f393a22..75e9b2b 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1275,9 +1275,7 @@ static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags)
 	 */
 	if (unlikely((u32) offset > 0xffff || len > sizeof(buf)))
 		return -EFAULT;
-
-	if (unlikely(skb_cloned(skb) &&
-		     !skb_clone_writable(skb, offset + len)))
+	if (unlikely(skb_try_make_writable(skb, offset + len)))
 		return -EFAULT;
 
 	ptr = skb_header_pointer(skb, offset, len, buf);
@@ -1321,8 +1319,7 @@ static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags)
 	if (unlikely((u32) offset > 0xffff))
 		return -EFAULT;
 
-	if (unlikely(skb_cloned(skb) &&
-		     !skb_clone_writable(skb, offset + sizeof(sum))))
+	if (unlikely(skb_try_make_writable(skb, offset + sizeof(sum))))
 		return -EFAULT;
 
 	ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum);
@@ -1367,9 +1364,7 @@ static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags)
 
 	if (unlikely((u32) offset > 0xffff))
 		return -EFAULT;
-
-	if (unlikely(skb_cloned(skb) &&
-		     !skb_clone_writable(skb, offset + sizeof(sum))))
+	if (unlikely(skb_try_make_writable(skb, offset + sizeof(sum))))
 		return -EFAULT;
 
 	ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum);
@@ -1554,6 +1549,13 @@ bool bpf_helper_changes_skb_data(void *func)
 		return true;
 	if (func == bpf_skb_vlan_pop)
 		return true;
+	if (func == bpf_skb_store_bytes)
+		return true;
+	if (func == bpf_l3_csum_replace)
+		return true;
+	if (func == bpf_l4_csum_replace)
+		return true;
+
 	return false;
 }
 
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index b07c535..eeb3eb3 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -105,9 +105,7 @@ static void *tcf_csum_skb_nextlayer(struct sk_buff *skb,
 	int hl = ihl + jhl;
 
 	if (!pskb_may_pull(skb, ipl + ntkoff) || (ipl < hl) ||
-	    (skb_cloned(skb) &&
-	     !skb_clone_writable(skb, hl + ntkoff) &&
-	     pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))
+	    skb_try_make_writable(skb, hl + ntkoff))
 		return NULL;
 	else
 		return (void *)(skb_network_header(skb) + ihl);
@@ -365,9 +363,7 @@ static int tcf_csum_ipv4(struct sk_buff *skb, u32 update_flags)
 	}
 
 	if (update_flags & TCA_CSUM_UPDATE_FLAG_IPV4HDR) {
-		if (skb_cloned(skb) &&
-		    !skb_clone_writable(skb, sizeof(*iph) + ntkoff) &&
-		    pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
+		if (skb_try_make_writable(skb, sizeof(*iph) + ntkoff))
 			goto fail;
 
 		ip_send_check(ip_hdr(skb));
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index b7c4ead..27607b8 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -126,9 +126,7 @@ static int tcf_nat(struct sk_buff *skb, const struct tc_action *a,
 		addr = iph->daddr;
 
 	if (!((old_addr ^ addr) & mask)) {
-		if (skb_cloned(skb) &&
-		    !skb_clone_writable(skb, sizeof(*iph) + noff) &&
-		    pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
+		if (skb_try_make_writable(skb, sizeof(*iph) + noff))
 			goto drop;
 
 		new_addr &= mask;
@@ -156,9 +154,7 @@ static int tcf_nat(struct sk_buff *skb, const struct tc_action *a,
 		struct tcphdr *tcph;
 
 		if (!pskb_may_pull(skb, ihl + sizeof(*tcph) + noff) ||
-		    (skb_cloned(skb) &&
-		     !skb_clone_writable(skb, ihl + sizeof(*tcph) + noff) &&
-		     pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))
+		    skb_try_make_writable(skb, ihl + sizeof(*tcph) + noff))
 			goto drop;
 
 		tcph = (void *)(skb_network_header(skb) + ihl);
@@ -171,9 +167,7 @@ static int tcf_nat(struct sk_buff *skb, const struct tc_action *a,
 		struct udphdr *udph;
 
 		if (!pskb_may_pull(skb, ihl + sizeof(*udph) + noff) ||
-		    (skb_cloned(skb) &&
-		     !skb_clone_writable(skb, ihl + sizeof(*udph) + noff) &&
-		     pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))
+		    skb_try_make_writable(skb, ihl + sizeof(*udph) + noff))
 			goto drop;
 
 		udph = (void *)(skb_network_header(skb) + ihl);
@@ -213,10 +207,8 @@ static int tcf_nat(struct sk_buff *skb, const struct tc_action *a,
 		if ((old_addr ^ addr) & mask)
 			break;
 
-		if (skb_cloned(skb) &&
-		    !skb_clone_writable(skb, ihl + sizeof(*icmph) +
-					     sizeof(*iph) + noff) &&
-		    pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
+		if (skb_try_make_writable(skb, ihl + sizeof(*icmph) +
+					  sizeof(*iph) + noff))
 			goto drop;
 
 		icmph = (void *)(skb_network_header(skb) + ihl);
-- 
2.1.0


From 753f79610188e9e8a39fd1448af236bec5fb16be Mon Sep 17 00:00:00 2001
From: Basil Gunn <basil@pacabunga.com>
Date: Thu, 16 Jun 2016 09:42:30 -0700
Subject: [PATCH 14/14] AX.25: Close socket connection on session completion

[ Upstream commit 4a7d99ea1b27734558feb6833f180cd38a159940 ]

A socket connection made in ax.25 is not closed when session is
completed.  The heartbeat timer is stopped prematurely and this is
where the socket gets closed. Allow heatbeat timer to run to close
socket. Symptom occurs in kernels >= 4.2.0

Originally sent 6/15/2016. Resend with distribution list matching
scripts/maintainer.pl output.

Signed-off-by: Basil Gunn <basil@pacabunga.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ax25/af_ax25.c        | 3 ++-
 net/ax25/ax25_ds_timer.c  | 5 ++++-
 net/ax25/ax25_std_timer.c | 5 ++++-
 net/ax25/ax25_subr.c      | 3 ++-
 4 files changed, 12 insertions(+), 4 deletions(-)

diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index fbd0acf..2fdebab 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -976,7 +976,8 @@ static int ax25_release(struct socket *sock)
 			release_sock(sk);
 			ax25_disconnect(ax25, 0);
 			lock_sock(sk);
-			ax25_destroy_socket(ax25);
+			if (!sock_flag(ax25->sk, SOCK_DESTROY))
+				ax25_destroy_socket(ax25);
 			break;
 
 		case AX25_STATE_3:
diff --git a/net/ax25/ax25_ds_timer.c b/net/ax25/ax25_ds_timer.c
index 951cd57..5237dff 100644
--- a/net/ax25/ax25_ds_timer.c
+++ b/net/ax25/ax25_ds_timer.c
@@ -102,6 +102,7 @@ void ax25_ds_heartbeat_expiry(ax25_cb *ax25)
 	switch (ax25->state) {
 
 	case AX25_STATE_0:
+	case AX25_STATE_2:
 		/* Magic here: If we listen() and a new link dies before it
 		   is accepted() it isn't 'dead' so doesn't get removed. */
 		if (!sk || sock_flag(sk, SOCK_DESTROY) ||
@@ -111,6 +112,7 @@ void ax25_ds_heartbeat_expiry(ax25_cb *ax25)
 				sock_hold(sk);
 				ax25_destroy_socket(ax25);
 				bh_unlock_sock(sk);
+				/* Ungrab socket and destroy it */
 				sock_put(sk);
 			} else
 				ax25_destroy_socket(ax25);
@@ -213,7 +215,8 @@ void ax25_ds_t1_timeout(ax25_cb *ax25)
 	case AX25_STATE_2:
 		if (ax25->n2count == ax25->n2) {
 			ax25_send_control(ax25, AX25_DISC, AX25_POLLON, AX25_COMMAND);
-			ax25_disconnect(ax25, ETIMEDOUT);
+			if (!sock_flag(ax25->sk, SOCK_DESTROY))
+				ax25_disconnect(ax25, ETIMEDOUT);
 			return;
 		} else {
 			ax25->n2count++;
diff --git a/net/ax25/ax25_std_timer.c b/net/ax25/ax25_std_timer.c
index 004467c9..2c0d6ef 100644
--- a/net/ax25/ax25_std_timer.c
+++ b/net/ax25/ax25_std_timer.c
@@ -38,6 +38,7 @@ void ax25_std_heartbeat_expiry(ax25_cb *ax25)
 
 	switch (ax25->state) {
 	case AX25_STATE_0:
+	case AX25_STATE_2:
 		/* Magic here: If we listen() and a new link dies before it
 		   is accepted() it isn't 'dead' so doesn't get removed. */
 		if (!sk || sock_flag(sk, SOCK_DESTROY) ||
@@ -47,6 +48,7 @@ void ax25_std_heartbeat_expiry(ax25_cb *ax25)
 				sock_hold(sk);
 				ax25_destroy_socket(ax25);
 				bh_unlock_sock(sk);
+				/* Ungrab socket and destroy it */
 				sock_put(sk);
 			} else
 				ax25_destroy_socket(ax25);
@@ -144,7 +146,8 @@ void ax25_std_t1timer_expiry(ax25_cb *ax25)
 	case AX25_STATE_2:
 		if (ax25->n2count == ax25->n2) {
 			ax25_send_control(ax25, AX25_DISC, AX25_POLLON, AX25_COMMAND);
-			ax25_disconnect(ax25, ETIMEDOUT);
+			if (!sock_flag(ax25->sk, SOCK_DESTROY))
+				ax25_disconnect(ax25, ETIMEDOUT);
 			return;
 		} else {
 			ax25->n2count++;
diff --git a/net/ax25/ax25_subr.c b/net/ax25/ax25_subr.c
index 3b78e84..655a7d4 100644
--- a/net/ax25/ax25_subr.c
+++ b/net/ax25/ax25_subr.c
@@ -264,7 +264,8 @@ void ax25_disconnect(ax25_cb *ax25, int reason)
 {
 	ax25_clear_queues(ax25);
 
-	ax25_stop_heartbeat(ax25);
+	if (!sock_flag(ax25->sk, SOCK_DESTROY))
+		ax25_stop_heartbeat(ax25);
 	ax25_stop_t1timer(ax25);
 	ax25_stop_t2timer(ax25);
 	ax25_stop_t3timer(ax25);
-- 
2.1.0


[-- Attachment #3: net_46.mbox --]
[-- Type: Application/Octet-Stream, Size: 31585 bytes --]

From 1a273e4df9aab60957a04e8753a5e5ad83d67e8a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 12 Jun 2016 20:01:25 -0700
Subject: [PATCH 01/13] net_sched: fix pfifo_head_drop behavior vs backlog

[ Upstream commit 6c0d54f1897d229748d4f41ef919078db6db2123 ]

When the qdisc is full, we drop a packet at the head of the queue,
queue the current skb and return NET_XMIT_CN

Now we track backlog on upper qdiscs, we need to call
qdisc_tree_reduce_backlog(), even if the qlen did not change.

Fixes: 2ccccf5fb43f ("net_sched: update hierarchical backlog too")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: WANG Cong <xiyou.wangcong@gmail.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_fifo.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c
index 2177eac..2e4bd2c 100644
--- a/net/sched/sch_fifo.c
+++ b/net/sched/sch_fifo.c
@@ -37,14 +37,18 @@ static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 
 static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 {
+	unsigned int prev_backlog;
+
 	if (likely(skb_queue_len(&sch->q) < sch->limit))
 		return qdisc_enqueue_tail(skb, sch);
 
+	prev_backlog = sch->qstats.backlog;
 	/* queue full, remove one skb to fulfill the limit */
 	__qdisc_queue_drop_head(sch, &sch->q);
 	qdisc_qstats_drop(sch);
 	qdisc_enqueue_tail(skb, sch);
 
+	qdisc_tree_reduce_backlog(sch, 0, prev_backlog - sch->qstats.backlog);
 	return NET_XMIT_CN;
 }
 
-- 
2.1.0


From 73974bc838d9554d94b0d7aab4b77d884dbaefb5 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Mon, 13 Jun 2016 13:44:14 -0700
Subject: [PATCH 02/13] act_ipt: fix a bind refcnt leak

[ Upstream commit d15eccea69b96a5116169688dcc9baf6d1ce2751 ]

And avoid calling tcf_hash_check() twice.

Fixes: a57f19d30b2d ("net sched: ipt action fix late binding")
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ipt.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 8b52700..6063233 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -121,10 +121,13 @@ static int __tcf_ipt_init(struct tc_action_net *tn, struct nlattr *nla,
 	}
 
 	td = (struct xt_entry_target *)nla_data(tb[TCA_IPT_TARG]);
-	if (nla_len(tb[TCA_IPT_TARG]) < td->u.target_size)
+	if (nla_len(tb[TCA_IPT_TARG]) < td->u.target_size) {
+		if (exists)
+			tcf_hash_release(a, bind);
 		return -EINVAL;
+	}
 
-	if (!tcf_hash_check(tn, index, a, bind)) {
+	if (!exists) {
 		ret = tcf_hash_create(tn, index, est, a, sizeof(*ipt), bind,
 				      false);
 		if (ret)
-- 
2.1.0


From 8b90e1835602e1eed7e10dd9be1c361727ca914f Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Wed, 15 Jun 2016 11:14:53 +0200
Subject: [PATCH 03/13] net: Don't forget pr_fmt on net_dbg_ratelimited for
 CONFIG_DYNAMIC_DEBUG

[ Upstream commit daddef76c3deaaa7922f9d7b18edbf0a061215c3 ]

The implementation of net_dbg_ratelimited in the CONFIG_DYNAMIC_DEBUG
case was added with 2c94b5373 ("net: Implement net_dbg_ratelimited() for
CONFIG_DYNAMIC_DEBUG case"). The implementation strategy was to take the
usual definition of the dynamic_pr_debug macro, but alter it by adding a
call to "net_ratelimit()" in the if statement. This is, in fact, the
correct approach.

However, while doing this, the author of the commit forgot to surround
fmt by pr_fmt, resulting in unprefixed log messages appearing in the
console. So, this commit adds back the pr_fmt(fmt) invocation, making
net_dbg_ratelimited properly consistent across DEBUG, no DEBUG, and
DYNAMIC_DEBUG cases, and bringing parity with the behavior of
dynamic_pr_debug as well.

Fixes: 2c94b5373 ("net: Implement net_dbg_ratelimited() for CONFIG_DYNAMIC_DEBUG case")
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Cc: Tim Bingham <tbingham@akamai.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/net.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/linux/net.h b/include/linux/net.h
index f840d77..9d90efe6 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -252,7 +252,8 @@ do {									\
 	DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt);			\
 	if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT) &&	\
 	    net_ratelimit())						\
-		__dynamic_pr_debug(&descriptor, fmt, ##__VA_ARGS__);	\
+		__dynamic_pr_debug(&descriptor, pr_fmt(fmt),		\
+		                   ##__VA_ARGS__);			\
 } while (0)
 #elif defined(DEBUG)
 #define net_dbg_ratelimited(fmt, ...)				\
-- 
2.1.0


From 2180a15320a98a2026b571667a2aecf9c317eaa3 Mon Sep 17 00:00:00 2001
From: Simon Horman <simon.horman@netronome.com>
Date: Thu, 16 Jun 2016 17:06:19 +0900
Subject: [PATCH 04/13] sit: correct IP protocol used in ipip6_err

[ Upstream commit d5d8760b78d0cfafe292f965f599988138b06a70 ]

Since 32b8a8e59c9c ("sit: add IPv4 over IPv4 support")
ipip6_err() may be called for packets whose IP protocol is
IPPROTO_IPIP as well as those whose IP protocol is IPPROTO_IPV6.

In the case of IPPROTO_IPIP packets the correct protocol value is not
passed to ipv4_update_pmtu() or ipv4_redirect().

This patch resolves this problem by using the IP protocol of the packet
rather than a hard-coded value. This appears to be consistent
with the usage of the protocol of a packet by icmp_socket_deliver()
the caller of ipip6_err().

I was able to exercise the redirect case by using a setup where an ICMP
redirect was received for the destination of the encapsulated packet.
However, it appears that although incorrect the protocol field is not used
in this case and thus no problem manifests.  On inspection it does not
appear that a problem will manifest in the fragmentation needed/update pmtu
case either.

In short I believe this is a cosmetic fix. None the less, the use of
IPPROTO_IPV6 seems wrong and confusing.

Reviewed-by: Dinan Gunawardena <dinan.gunawardena@netronome.com>
Signed-off-by: Simon Horman <simon.horman@netronome.com>
Acked-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 8338430..6c53e4e 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -560,13 +560,13 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
 
 	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
 		ipv4_update_pmtu(skb, dev_net(skb->dev), info,
-				 t->parms.link, 0, IPPROTO_IPV6, 0);
+				 t->parms.link, 0, iph->protocol, 0);
 		err = 0;
 		goto out;
 	}
 	if (type == ICMP_REDIRECT) {
 		ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0,
-			      IPPROTO_IPV6, 0);
+			      iph->protocol, 0);
 		err = 0;
 		goto out;
 	}
-- 
2.1.0


From 332cba16b9b37ec7e462cded877a826d13a24e2a Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jslaby@suse.cz>
Date: Mon, 20 Jun 2016 11:36:28 +0200
Subject: [PATCH 05/13] kcm: fix /proc memory leak

[ Upstream commit d19af0a76444fde629667ecb823c0ee28f9f67d8 ]

Every open of /proc/net/kcm leaks 16 bytes of memory as is reported by
kmemleak:
unreferenced object 0xffff88059c0e3458 (size 192):
  comm "cat", pid 1401, jiffies 4294935742 (age 310.720s)
  hex dump (first 32 bytes):
    28 45 71 96 05 88 ff ff 00 10 00 00 00 00 00 00  (Eq.............
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<ffffffff8156a2de>] kmem_cache_alloc_trace+0x16e/0x230
    [<ffffffff8162a479>] seq_open+0x79/0x1d0
    [<ffffffffa0578510>] kcm_seq_open+0x0/0x30 [kcm]
    [<ffffffff8162a479>] seq_open+0x79/0x1d0
    [<ffffffff8162a8cf>] __seq_open_private+0x2f/0xa0
    [<ffffffff81712548>] seq_open_net+0x38/0xa0
...

It is caused by a missing free in the ->release path. So fix it by
providing seq_release_net as the ->release method.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Fixes: cd6e111bf5 (kcm: Add statistics and proc interfaces)
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Tom Herbert <tom@herbertland.com>
Cc: netdev@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/kcm/kcmproc.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/kcm/kcmproc.c b/net/kcm/kcmproc.c
index 7380087..fda7f47 100644
--- a/net/kcm/kcmproc.c
+++ b/net/kcm/kcmproc.c
@@ -241,6 +241,7 @@ static const struct file_operations kcm_seq_fops = {
 	.open		= kcm_seq_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
+	.release	= seq_release_net,
 };
 
 static struct kcm_seq_muxinfo kcm_seq_muxinfo = {
-- 
2.1.0


From 9c9fd590505d24a9b8ff3432d220448cf0704cb4 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Sat, 18 Jun 2016 13:03:36 +0800
Subject: [PATCH 06/13] esp: Fix ESN generation under UDP encapsulation

[ Upstream commit 962fcef33b03395051367181a0549d29d109d9a4 ]

Blair Steven noticed that ESN in conjunction with UDP encapsulation
is broken because we set the temporary ESP header to the wrong spot.

This patch fixes this by first of all using the right spot, i.e.,
4 bytes off the real ESP header, and then saving this information
so that after encryption we can restore it properly.

Fixes: 7021b2e1cddd ("esp4: Switch to new AEAD interface")
Reported-by: Blair Steven <Blair.Steven@alliedtelesis.co.nz>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/esp4.c | 52 ++++++++++++++++++++++++++++++++--------------------
 1 file changed, 32 insertions(+), 20 deletions(-)

diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 4779374..d95631d 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -23,6 +23,11 @@ struct esp_skb_cb {
 	void *tmp;
 };
 
+struct esp_output_extra {
+	__be32 seqhi;
+	u32 esphoff;
+};
+
 #define ESP_SKB_CB(__skb) ((struct esp_skb_cb *)&((__skb)->cb[0]))
 
 static u32 esp4_get_mtu(struct xfrm_state *x, int mtu);
@@ -35,11 +40,11 @@ static u32 esp4_get_mtu(struct xfrm_state *x, int mtu);
  *
  * TODO: Use spare space in skb for this where possible.
  */
-static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int seqhilen)
+static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int extralen)
 {
 	unsigned int len;
 
-	len = seqhilen;
+	len = extralen;
 
 	len += crypto_aead_ivsize(aead);
 
@@ -57,15 +62,16 @@ static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int seqhilen)
 	return kmalloc(len, GFP_ATOMIC);
 }
 
-static inline __be32 *esp_tmp_seqhi(void *tmp)
+static inline void *esp_tmp_extra(void *tmp)
 {
-	return PTR_ALIGN((__be32 *)tmp, __alignof__(__be32));
+	return PTR_ALIGN(tmp, __alignof__(struct esp_output_extra));
 }
-static inline u8 *esp_tmp_iv(struct crypto_aead *aead, void *tmp, int seqhilen)
+
+static inline u8 *esp_tmp_iv(struct crypto_aead *aead, void *tmp, int extralen)
 {
 	return crypto_aead_ivsize(aead) ?
-	       PTR_ALIGN((u8 *)tmp + seqhilen,
-			 crypto_aead_alignmask(aead) + 1) : tmp + seqhilen;
+	       PTR_ALIGN((u8 *)tmp + extralen,
+			 crypto_aead_alignmask(aead) + 1) : tmp + extralen;
 }
 
 static inline struct aead_request *esp_tmp_req(struct crypto_aead *aead, u8 *iv)
@@ -99,7 +105,7 @@ static void esp_restore_header(struct sk_buff *skb, unsigned int offset)
 {
 	struct ip_esp_hdr *esph = (void *)(skb->data + offset);
 	void *tmp = ESP_SKB_CB(skb)->tmp;
-	__be32 *seqhi = esp_tmp_seqhi(tmp);
+	__be32 *seqhi = esp_tmp_extra(tmp);
 
 	esph->seq_no = esph->spi;
 	esph->spi = *seqhi;
@@ -107,7 +113,11 @@ static void esp_restore_header(struct sk_buff *skb, unsigned int offset)
 
 static void esp_output_restore_header(struct sk_buff *skb)
 {
-	esp_restore_header(skb, skb_transport_offset(skb) - sizeof(__be32));
+	void *tmp = ESP_SKB_CB(skb)->tmp;
+	struct esp_output_extra *extra = esp_tmp_extra(tmp);
+
+	esp_restore_header(skb, skb_transport_offset(skb) + extra->esphoff -
+				sizeof(__be32));
 }
 
 static void esp_output_done_esn(struct crypto_async_request *base, int err)
@@ -121,6 +131,7 @@ static void esp_output_done_esn(struct crypto_async_request *base, int err)
 static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 {
 	int err;
+	struct esp_output_extra *extra;
 	struct ip_esp_hdr *esph;
 	struct crypto_aead *aead;
 	struct aead_request *req;
@@ -137,8 +148,7 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 	int tfclen;
 	int nfrags;
 	int assoclen;
-	int seqhilen;
-	__be32 *seqhi;
+	int extralen;
 	__be64 seqno;
 
 	/* skb is pure payload to encrypt */
@@ -166,21 +176,21 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 	nfrags = err;
 
 	assoclen = sizeof(*esph);
-	seqhilen = 0;
+	extralen = 0;
 
 	if (x->props.flags & XFRM_STATE_ESN) {
-		seqhilen += sizeof(__be32);
-		assoclen += seqhilen;
+		extralen += sizeof(*extra);
+		assoclen += sizeof(__be32);
 	}
 
-	tmp = esp_alloc_tmp(aead, nfrags, seqhilen);
+	tmp = esp_alloc_tmp(aead, nfrags, extralen);
 	if (!tmp) {
 		err = -ENOMEM;
 		goto error;
 	}
 
-	seqhi = esp_tmp_seqhi(tmp);
-	iv = esp_tmp_iv(aead, tmp, seqhilen);
+	extra = esp_tmp_extra(tmp);
+	iv = esp_tmp_iv(aead, tmp, extralen);
 	req = esp_tmp_req(aead, iv);
 	sg = esp_req_sg(aead, req);
 
@@ -247,8 +257,10 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 	 * encryption.
 	 */
 	if ((x->props.flags & XFRM_STATE_ESN)) {
-		esph = (void *)(skb_transport_header(skb) - sizeof(__be32));
-		*seqhi = esph->spi;
+		extra->esphoff = (unsigned char *)esph -
+				 skb_transport_header(skb);
+		esph = (struct ip_esp_hdr *)((unsigned char *)esph - 4);
+		extra->seqhi = esph->spi;
 		esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.hi);
 		aead_request_set_callback(req, 0, esp_output_done_esn, skb);
 	}
@@ -445,7 +457,7 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb)
 		goto out;
 
 	ESP_SKB_CB(skb)->tmp = tmp;
-	seqhi = esp_tmp_seqhi(tmp);
+	seqhi = esp_tmp_extra(tmp);
 	iv = esp_tmp_iv(aead, tmp, seqhilen);
 	req = esp_tmp_req(aead, iv);
 	sg = esp_req_sg(aead, req);
-- 
2.1.0


From f8239791d5e7b118f45be891c52be2f8e9cc795e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 20 Jun 2016 15:00:43 -0700
Subject: [PATCH 07/13] netem: fix a use after free

[ Upstream commit 21de12ee5568fd1aec47890c72967abf791ac80a ]

If the packet was dropped by lower qdisc, then we must not
access it later.

Save qdisc_pkt_len(skb) in a temp variable.

Fixes: 2ccccf5fb43f ("net_sched: update hierarchical backlog too")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: WANG Cong <xiyou.wangcong@gmail.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_netem.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 4befe97..b7c29d5 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -650,14 +650,14 @@ deliver:
 #endif
 
 			if (q->qdisc) {
+				unsigned int pkt_len = qdisc_pkt_len(skb);
 				int err = qdisc_enqueue(skb, q->qdisc);
 
-				if (unlikely(err != NET_XMIT_SUCCESS)) {
-					if (net_xmit_drop_count(err)) {
-						qdisc_qstats_drop(sch);
-						qdisc_tree_reduce_backlog(sch, 1,
-									  qdisc_pkt_len(skb));
-					}
+				if (err != NET_XMIT_SUCCESS &&
+				    net_xmit_drop_count(err)) {
+					qdisc_qstats_drop(sch);
+					qdisc_tree_reduce_backlog(sch, 1,
+								  pkt_len);
 				}
 				goto tfifo_dequeue;
 			}
-- 
2.1.0


From b4d5a6007e6b840cf47bc4a239831ddec85875a9 Mon Sep 17 00:00:00 2001
From: Tom Goff <thomas.goff@ll.mit.edu>
Date: Thu, 23 Jun 2016 16:11:57 -0400
Subject: [PATCH 08/13] ipmr/ip6mr: Initialize the last assert time of mfc
 entries.

[ Upstream commit 70a0dec45174c976c64b4c8c1d0898581f759948 ]

This fixes wrong-interface signaling on 32-bit platforms for entries
created when jiffies > 2^31 + MFC_ASSERT_THRESH.

Signed-off-by: Tom Goff <thomas.goff@ll.mit.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ipmr.c  | 4 +++-
 net/ipv6/ip6mr.c | 1 +
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 395e281..a42dd80 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -891,8 +891,10 @@ static struct mfc_cache *ipmr_cache_alloc(void)
 {
 	struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL);
 
-	if (c)
+	if (c) {
+		c->mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1;
 		c->mfc_un.res.minvif = MAXVIFS;
+	}
 	return c;
 }
 
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index a10e771..e207cb2 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1074,6 +1074,7 @@ static struct mfc6_cache *ip6mr_cache_alloc(void)
 	struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL);
 	if (!c)
 		return NULL;
+	c->mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1;
 	c->mfc_un.res.minvif = MAXMIFS;
 	return c;
 }
-- 
2.1.0


From 4435da6226d3f87ff614de00bd84414159e5e4d0 Mon Sep 17 00:00:00 2001
From: daniel <daniel@dd-wrt.com>
Date: Fri, 24 Jun 2016 12:35:18 +0200
Subject: [PATCH 09/13] Bridge: Fix ipv6 mc snooping if bridge has no ipv6
 address
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 0888d5f3c0f183ea6177355752ada433d370ac89 ]

The bridge is falsly dropping ipv6 mulitcast packets if there is:
 1. No ipv6 address assigned on the brigde.
 2. No external mld querier present.
 3. The internal querier enabled.

When the bridge fails to build mld queries, because it has no
ipv6 address, it slilently returns, but keeps the local querier enabled.
This specific case causes confusing packet loss.

Ipv6 multicast snooping can only work if:
 a) An external querier is present
 OR
 b) The bridge has an ipv6 address an is capable of sending own queries

Otherwise it has to forward/flood the ipv6 multicast traffic,
because snooping cannot work.

This patch fixes the issue by adding a flag to the bridge struct that
indicates that there is currently no ipv6 address assinged to the bridge
and returns a false state for the local querier in
__br_multicast_querier_exists().

Special thanks to Linus Lüssing.

Fixes: d1d81d4c3dd8 ("bridge: check return value of ipv6_dev_get_saddr()")
Signed-off-by: Daniel Danzberger <daniel@dd-wrt.com>
Acked-by: Linus Lüssing <linus.luessing@c0d3.blue>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c |  4 ++++
 net/bridge/br_private.h   | 23 +++++++++++++++++++----
 2 files changed, 23 insertions(+), 4 deletions(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 6852f3c..4384414 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -464,8 +464,11 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br,
 	if (ipv6_dev_get_saddr(dev_net(br->dev), br->dev, &ip6h->daddr, 0,
 			       &ip6h->saddr)) {
 		kfree_skb(skb);
+		br->has_ipv6_addr = 0;
 		return NULL;
 	}
+
+	br->has_ipv6_addr = 1;
 	ipv6_eth_mc_map(&ip6h->daddr, eth->h_dest);
 
 	hopopt = (u8 *)(ip6h + 1);
@@ -1745,6 +1748,7 @@ void br_multicast_init(struct net_bridge *br)
 	br->ip6_other_query.delay_time = 0;
 	br->ip6_querier.port = NULL;
 #endif
+	br->has_ipv6_addr = 1;
 
 	spin_lock_init(&br->multicast_lock);
 	setup_timer(&br->multicast_router_timer,
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index d9da857..f516c53 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -304,6 +304,7 @@ struct net_bridge
 	u8				multicast_disabled:1;
 	u8				multicast_querier:1;
 	u8				multicast_query_use_ifaddr:1;
+	u8				has_ipv6_addr:1;
 
 	u32				hash_elasticity;
 	u32				hash_max;
@@ -577,10 +578,22 @@ static inline bool br_multicast_is_router(struct net_bridge *br)
 
 static inline bool
 __br_multicast_querier_exists(struct net_bridge *br,
-			      struct bridge_mcast_other_query *querier)
+				struct bridge_mcast_other_query *querier,
+				const bool is_ipv6)
 {
+	bool own_querier_enabled;
+
+	if (br->multicast_querier) {
+		if (is_ipv6 && !br->has_ipv6_addr)
+			own_querier_enabled = false;
+		else
+			own_querier_enabled = true;
+	} else {
+		own_querier_enabled = false;
+	}
+
 	return time_is_before_jiffies(querier->delay_time) &&
-	       (br->multicast_querier || timer_pending(&querier->timer));
+	       (own_querier_enabled || timer_pending(&querier->timer));
 }
 
 static inline bool br_multicast_querier_exists(struct net_bridge *br,
@@ -588,10 +601,12 @@ static inline bool br_multicast_querier_exists(struct net_bridge *br,
 {
 	switch (eth->h_proto) {
 	case (htons(ETH_P_IP)):
-		return __br_multicast_querier_exists(br, &br->ip4_other_query);
+		return __br_multicast_querier_exists(br,
+			&br->ip4_other_query, false);
 #if IS_ENABLED(CONFIG_IPV6)
 	case (htons(ETH_P_IPV6)):
-		return __br_multicast_querier_exists(br, &br->ip6_other_query);
+		return __br_multicast_querier_exists(br,
+			&br->ip6_other_query, true);
 #endif
 	default:
 		return false;
-- 
2.1.0


From 2ccaf661e22a9d8521f418394a8e6e34e6edeca6 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 24 Jun 2016 16:02:35 -0400
Subject: [PATCH 10/13] sock_diag: do not broadcast raw socket destruction

[ Upstream commit 9a0fee2b552b1235fb1706ae1fc664ae74573be8 ]

Diag intends to broadcast tcp_sk and udp_sk socket destruction.
Testing sk->sk_protocol for IPPROTO_TCP/IPPROTO_UDP alone is not
sufficient for this. Raw sockets can have the same type.

Add a test for sk->sk_type.

Fixes: eb4cb008529c ("sock_diag: define destruction multicast groups")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/sock_diag.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h
index 4018b48..a0596ca0 100644
--- a/include/linux/sock_diag.h
+++ b/include/linux/sock_diag.h
@@ -36,6 +36,9 @@ enum sknetlink_groups sock_diag_destroy_group(const struct sock *sk)
 {
 	switch (sk->sk_family) {
 	case AF_INET:
+		if (sk->sk_type == SOCK_RAW)
+			return SKNLGRP_NONE;
+
 		switch (sk->sk_protocol) {
 		case IPPROTO_TCP:
 			return SKNLGRP_INET_TCP_DESTROY;
@@ -45,6 +48,9 @@ enum sknetlink_groups sock_diag_destroy_group(const struct sock *sk)
 			return SKNLGRP_NONE;
 		}
 	case AF_INET6:
+		if (sk->sk_type == SOCK_RAW)
+			return SKNLGRP_NONE;
+
 		switch (sk->sk_protocol) {
 		case IPPROTO_TCP:
 			return SKNLGRP_INET6_TCP_DESTROY;
-- 
2.1.0


From 304fbb5472ea11fbca7c9ab7b33dc1def2c6eb06 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Mon, 27 Jun 2016 21:38:11 +0200
Subject: [PATCH 11/13] bpf, perf: delay release of BPF prog after grace period

[ Upstream commit ceb56070359b7329b5678b5d95a376fcb24767be ]

Commit dead9f29ddcc ("perf: Fix race in BPF program unregister") moved
destruction of BPF program from free_event_rcu() callback to __free_event(),
which is problematic if used with tail calls: if prog A is attached as
trace event directly, but at the same time present in a tail call map used
by another trace event program elsewhere, then we need to delay destruction
via RCU grace period since it can still be in use by the program doing the
tail call (the prog first needs to be dropped from the tail call map, then
trace event with prog A attached destroyed, so we get immediate destruction).

Fixes: dead9f29ddcc ("perf: Fix race in BPF program unregister")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Cc: Jann Horn <jann@thejh.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/bpf.h  | 4 ++++
 kernel/events/core.c | 2 +-
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f1d5c5ac..ca80d58 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -229,6 +229,10 @@ static inline struct bpf_prog *bpf_prog_get(u32 ufd)
 static inline void bpf_prog_put(struct bpf_prog *prog)
 {
 }
+
+static inline void bpf_prog_put_rcu(struct bpf_prog *prog)
+{
+}
 #endif /* CONFIG_BPF_SYSCALL */
 
 /* verifier prototypes for helper functions called from eBPF programs */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index c0ded24..a69c90c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7143,7 +7143,7 @@ static void perf_event_free_bpf_prog(struct perf_event *event)
 	prog = event->tp_event->prog;
 	if (prog) {
 		event->tp_event->prog = NULL;
-		bpf_prog_put(prog);
+		bpf_prog_put_rcu(prog);
 	}
 }
 
-- 
2.1.0


From 3027594de87007252281617b59374b1cc576f7f7 Mon Sep 17 00:00:00 2001
From: David Barroso <dbarroso@fastly.com>
Date: Tue, 28 Jun 2016 11:16:43 +0300
Subject: [PATCH 12/13] neigh: Explicitly declare RCU-bh read side critical
 section in neigh_xmit()

[ Upstream commit b560f03ddfb072bca65e9440ff0dc4f9b1d1f056 ]

neigh_xmit() expects to be called inside an RCU-bh read side critical
section, and while one of its two current callers gets this right, the
other one doesn't.

More specifically, neigh_xmit() has two callers, mpls_forward() and
mpls_output(), and while both callers call neigh_xmit() under
rcu_read_lock(), this provides sufficient protection for neigh_xmit()
only in the case of mpls_forward(), as that is always called from
softirq context and therefore doesn't need explicit BH protection,
while mpls_output() can be called from process context with softirqs
enabled.

When mpls_output() is called from process context, with softirqs
enabled, we can be preempted by a softirq at any time, and RCU-bh
considers the completion of a softirq as signaling the end of any
pending read-side critical sections, so if we do get a softirq
while we are in the part of neigh_xmit() that expects to be run inside
an RCU-bh read side critical section, we can end up with an unexpected
RCU grace period running right in the middle of that critical section,
making things go boom.

This patch fixes this impedance mismatch in the callee, by making
neigh_xmit() always take rcu_read_{,un}lock_bh() around the code that
expects to be treated as an RCU-bh read side critical section, as this
seems a safer option than fixing it in the callers.

Fixes: 4fd3d7d9e868f ("neigh: Add helper function neigh_xmit")
Signed-off-by: David Barroso <dbarroso@fastly.com>
Signed-off-by: Lennert Buytenhek <lbuytenhek@fastly.com>
Acked-by: David Ahern <dsa@cumulusnetworks.com>
Acked-by: Robert Shearman <rshearma@brocade.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index f18ae91..769cece 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2467,13 +2467,17 @@ int neigh_xmit(int index, struct net_device *dev,
 		tbl = neigh_tables[index];
 		if (!tbl)
 			goto out;
+		rcu_read_lock_bh();
 		neigh = __neigh_lookup_noref(tbl, addr, dev);
 		if (!neigh)
 			neigh = __neigh_create(tbl, addr, dev, false);
 		err = PTR_ERR(neigh);
-		if (IS_ERR(neigh))
+		if (IS_ERR(neigh)) {
+			rcu_read_unlock_bh();
 			goto out_kfree_skb;
+		}
 		err = neigh->output(neigh, skb);
+		rcu_read_unlock_bh();
 	}
 	else if (index == NEIGH_LINK_TABLE) {
 		err = dev_hard_header(skb, dev, ntohs(skb->protocol),
-- 
2.1.0


From 026df289fb24b37e882ce22cbff0f00392c37ffe Mon Sep 17 00:00:00 2001
From: Basil Gunn <basil@pacabunga.com>
Date: Thu, 16 Jun 2016 09:42:30 -0700
Subject: [PATCH 13/13] AX.25: Close socket connection on session completion

[ Upstream commit 4a7d99ea1b27734558feb6833f180cd38a159940 ]

A socket connection made in ax.25 is not closed when session is
completed.  The heartbeat timer is stopped prematurely and this is
where the socket gets closed. Allow heatbeat timer to run to close
socket. Symptom occurs in kernels >= 4.2.0

Originally sent 6/15/2016. Resend with distribution list matching
scripts/maintainer.pl output.

Signed-off-by: Basil Gunn <basil@pacabunga.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ax25/af_ax25.c        | 3 ++-
 net/ax25/ax25_ds_timer.c  | 5 ++++-
 net/ax25/ax25_std_timer.c | 5 ++++-
 net/ax25/ax25_subr.c      | 3 ++-
 4 files changed, 12 insertions(+), 4 deletions(-)

diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index fbd0acf..2fdebab 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -976,7 +976,8 @@ static int ax25_release(struct socket *sock)
 			release_sock(sk);
 			ax25_disconnect(ax25, 0);
 			lock_sock(sk);
-			ax25_destroy_socket(ax25);
+			if (!sock_flag(ax25->sk, SOCK_DESTROY))
+				ax25_destroy_socket(ax25);
 			break;
 
 		case AX25_STATE_3:
diff --git a/net/ax25/ax25_ds_timer.c b/net/ax25/ax25_ds_timer.c
index 951cd57..5237dff 100644
--- a/net/ax25/ax25_ds_timer.c
+++ b/net/ax25/ax25_ds_timer.c
@@ -102,6 +102,7 @@ void ax25_ds_heartbeat_expiry(ax25_cb *ax25)
 	switch (ax25->state) {
 
 	case AX25_STATE_0:
+	case AX25_STATE_2:
 		/* Magic here: If we listen() and a new link dies before it
 		   is accepted() it isn't 'dead' so doesn't get removed. */
 		if (!sk || sock_flag(sk, SOCK_DESTROY) ||
@@ -111,6 +112,7 @@ void ax25_ds_heartbeat_expiry(ax25_cb *ax25)
 				sock_hold(sk);
 				ax25_destroy_socket(ax25);
 				bh_unlock_sock(sk);
+				/* Ungrab socket and destroy it */
 				sock_put(sk);
 			} else
 				ax25_destroy_socket(ax25);
@@ -213,7 +215,8 @@ void ax25_ds_t1_timeout(ax25_cb *ax25)
 	case AX25_STATE_2:
 		if (ax25->n2count == ax25->n2) {
 			ax25_send_control(ax25, AX25_DISC, AX25_POLLON, AX25_COMMAND);
-			ax25_disconnect(ax25, ETIMEDOUT);
+			if (!sock_flag(ax25->sk, SOCK_DESTROY))
+				ax25_disconnect(ax25, ETIMEDOUT);
 			return;
 		} else {
 			ax25->n2count++;
diff --git a/net/ax25/ax25_std_timer.c b/net/ax25/ax25_std_timer.c
index 004467c9..2c0d6ef 100644
--- a/net/ax25/ax25_std_timer.c
+++ b/net/ax25/ax25_std_timer.c
@@ -38,6 +38,7 @@ void ax25_std_heartbeat_expiry(ax25_cb *ax25)
 
 	switch (ax25->state) {
 	case AX25_STATE_0:
+	case AX25_STATE_2:
 		/* Magic here: If we listen() and a new link dies before it
 		   is accepted() it isn't 'dead' so doesn't get removed. */
 		if (!sk || sock_flag(sk, SOCK_DESTROY) ||
@@ -47,6 +48,7 @@ void ax25_std_heartbeat_expiry(ax25_cb *ax25)
 				sock_hold(sk);
 				ax25_destroy_socket(ax25);
 				bh_unlock_sock(sk);
+				/* Ungrab socket and destroy it */
 				sock_put(sk);
 			} else
 				ax25_destroy_socket(ax25);
@@ -144,7 +146,8 @@ void ax25_std_t1timer_expiry(ax25_cb *ax25)
 	case AX25_STATE_2:
 		if (ax25->n2count == ax25->n2) {
 			ax25_send_control(ax25, AX25_DISC, AX25_POLLON, AX25_COMMAND);
-			ax25_disconnect(ax25, ETIMEDOUT);
+			if (!sock_flag(ax25->sk, SOCK_DESTROY))
+				ax25_disconnect(ax25, ETIMEDOUT);
 			return;
 		} else {
 			ax25->n2count++;
diff --git a/net/ax25/ax25_subr.c b/net/ax25/ax25_subr.c
index 3b78e84..655a7d4 100644
--- a/net/ax25/ax25_subr.c
+++ b/net/ax25/ax25_subr.c
@@ -264,7 +264,8 @@ void ax25_disconnect(ax25_cb *ax25, int reason)
 {
 	ax25_clear_queues(ax25);
 
-	ax25_stop_heartbeat(ax25);
+	if (!sock_flag(ax25->sk, SOCK_DESTROY))
+		ax25_stop_heartbeat(ax25);
 	ax25_stop_t1timer(ax25);
 	ax25_stop_t2timer(ax25);
 	ax25_stop_t3timer(ax25);
-- 
2.1.0

Re: [PATCHES] Networking

[Greg KH]

On Tue, Jul 05, 2016 at 10:02:12PM -0700, David Miller wrote:
> 
> Please queue up the following bug fixes for 4.4.x and 4.6.x -stable,
> respectively.

Now applied, thanks so much for these.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 104 bytes --]


Please queue up the following networking bug fixes for 4.4.x and 4.6.x
-stable, respectively.

Thanks!

[-- Attachment #2: net_44.mbox --]
[-- Type: Application/Octet-Stream, Size: 11625 bytes --]

From 6bae1ef5b126a50a12ebf9e2eb1e57f6ca57da95 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 1 Jul 2016 16:07:50 -0400
Subject: [PATCH 1/4] packet: Use symmetric hash for PACKET_FANOUT_HASH.

[ Upstream commit eb70db8756717b90c01ccc765fdefc4dd969fc74 ]

People who use PACKET_FANOUT_HASH want a symmetric hash, meaning that
they want packets going in both directions on a flow to hash to the
same bucket.

The core kernel SKB hash became non-symmetric when the ipv6 flow label
and other entities were incorporated into the standard flow hash order
to increase entropy.

But there are no users of PACKET_FANOUT_HASH who want an assymetric
hash, they all want a symmetric one.

Therefore, use the flow dissector to compute a flat symmetric hash
over only the protocol, addresses and ports.  This hash does not get
installed into and override the normal skb hash, so this change has
no effect whatsoever on the rest of the stack.

Reported-by: Eric Leblond <eric@regit.org>
Tested-by: Eric Leblond <eric@regit.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h    |  1 +
 net/core/flow_dissector.c | 43 +++++++++++++++++++++++++++++++++++++++++++
 net/packet/af_packet.c    |  2 +-
 3 files changed, 45 insertions(+), 1 deletion(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 1716f93..b3bb990 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -982,6 +982,7 @@ __skb_set_sw_hash(struct sk_buff *skb, __u32 hash, bool is_l4)
 }
 
 void __skb_get_hash(struct sk_buff *skb);
+u32 __skb_get_hash_symmetric(struct sk_buff *skb);
 u32 skb_get_poff(const struct sk_buff *skb);
 u32 __skb_get_poff(const struct sk_buff *skb, void *data,
 		   const struct flow_keys *keys, int hlen);
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 12e7003..4ab6ead 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -662,6 +662,23 @@ void make_flow_keys_digest(struct flow_keys_digest *digest,
 }
 EXPORT_SYMBOL(make_flow_keys_digest);
 
+static struct flow_dissector flow_keys_dissector_symmetric __read_mostly;
+
+u32 __skb_get_hash_symmetric(struct sk_buff *skb)
+{
+	struct flow_keys keys;
+
+	__flow_hash_secret_init();
+
+	memset(&keys, 0, sizeof(keys));
+	__skb_flow_dissect(skb, &flow_keys_dissector_symmetric, &keys,
+			   NULL, 0, 0, 0,
+			   FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
+
+	return __flow_hash_from_keys(&keys, hashrnd);
+}
+EXPORT_SYMBOL_GPL(__skb_get_hash_symmetric);
+
 /**
  * __skb_get_hash: calculate a flow hash
  * @skb: sk_buff to calculate flow hash from
@@ -874,6 +891,29 @@ static const struct flow_dissector_key flow_keys_dissector_keys[] = {
 	},
 };
 
+static const struct flow_dissector_key flow_keys_dissector_symmetric_keys[] = {
+	{
+		.key_id = FLOW_DISSECTOR_KEY_CONTROL,
+		.offset = offsetof(struct flow_keys, control),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_BASIC,
+		.offset = offsetof(struct flow_keys, basic),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS,
+		.offset = offsetof(struct flow_keys, addrs.v4addrs),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS,
+		.offset = offsetof(struct flow_keys, addrs.v6addrs),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_PORTS,
+		.offset = offsetof(struct flow_keys, ports),
+	},
+};
+
 static const struct flow_dissector_key flow_keys_buf_dissector_keys[] = {
 	{
 		.key_id = FLOW_DISSECTOR_KEY_CONTROL,
@@ -895,6 +935,9 @@ static int __init init_default_flow_dissectors(void)
 	skb_flow_dissector_init(&flow_keys_dissector,
 				flow_keys_dissector_keys,
 				ARRAY_SIZE(flow_keys_dissector_keys));
+	skb_flow_dissector_init(&flow_keys_dissector_symmetric,
+				flow_keys_dissector_symmetric_keys,
+				ARRAY_SIZE(flow_keys_dissector_symmetric_keys));
 	skb_flow_dissector_init(&flow_keys_buf_dissector,
 				flow_keys_buf_dissector_keys,
 				ARRAY_SIZE(flow_keys_buf_dissector_keys));
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 9cc7b51..a86f26d 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1341,7 +1341,7 @@ static unsigned int fanout_demux_hash(struct packet_fanout *f,
 				      struct sk_buff *skb,
 				      unsigned int num)
 {
-	return reciprocal_scale(skb_get_hash(skb), num);
+	return reciprocal_scale(__skb_get_hash_symmetric(skb), num);
 }
 
 static unsigned int fanout_demux_lb(struct packet_fanout *f,
-- 
2.1.0


From 55bf5a98b44cee7d06f8c97eb21bbb3d33972454 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Thu, 30 Jun 2016 10:15:22 -0700
Subject: [PATCH 2/4] net_sched: fix mirrored packets checksum

[ Upstream commit 82a31b9231f02d9c1b7b290a46999d517b0d312a ]

Similar to commit 9b368814b336 ("net: fix bridge multicast packet checksum validation")
we need to fixup the checksum for CHECKSUM_COMPLETE when
pushing skb on RX path. Otherwise we get similar splats.

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Tom Herbert <tom@herbertland.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 19 +++++++++++++++++++
 net/core/skbuff.c      | 18 ------------------
 net/sched/act_mirred.c |  2 +-
 3 files changed, 20 insertions(+), 19 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index b3bb990..d443d9a 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2774,6 +2774,25 @@ static inline void skb_postpush_rcsum(struct sk_buff *skb,
 }
 
 /**
+ *	skb_push_rcsum - push skb and update receive checksum
+ *	@skb: buffer to update
+ *	@len: length of data pulled
+ *
+ *	This function performs an skb_push on the packet and updates
+ *	the CHECKSUM_COMPLETE checksum.  It should be used on
+ *	receive path processing instead of skb_push unless you know
+ *	that the checksum difference is zero (e.g., a valid IP header)
+ *	or you are setting ip_summed to CHECKSUM_NONE.
+ */
+static inline unsigned char *skb_push_rcsum(struct sk_buff *skb,
+					    unsigned int len)
+{
+	skb_push(skb, len);
+	skb_postpush_rcsum(skb, skb->data, len);
+	return skb->data;
+}
+
+/**
  *	pskb_trim_rcsum - trim received skb and update checksum
  *	@skb: buffer to trim
  *	@len: new length
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 9835d9a..4968b5d 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2948,24 +2948,6 @@ int skb_append_pagefrags(struct sk_buff *skb, struct page *page,
 EXPORT_SYMBOL_GPL(skb_append_pagefrags);
 
 /**
- *	skb_push_rcsum - push skb and update receive checksum
- *	@skb: buffer to update
- *	@len: length of data pulled
- *
- *	This function performs an skb_push on the packet and updates
- *	the CHECKSUM_COMPLETE checksum.  It should be used on
- *	receive path processing instead of skb_push unless you know
- *	that the checksum difference is zero (e.g., a valid IP header)
- *	or you are setting ip_summed to CHECKSUM_NONE.
- */
-static unsigned char *skb_push_rcsum(struct sk_buff *skb, unsigned len)
-{
-	skb_push(skb, len);
-	skb_postpush_rcsum(skb, skb->data, len);
-	return skb->data;
-}
-
-/**
  *	skb_pull_rcsum - pull skb and update receive checksum
  *	@skb: buffer to update
  *	@len: length of data pulled
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 32fcdec..e384d6a 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -170,7 +170,7 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
 
 	if (!(at & AT_EGRESS)) {
 		if (m->tcfm_ok_push)
-			skb_push(skb2, skb->mac_len);
+			skb_push_rcsum(skb2, skb->mac_len);
 	}
 
 	/* mirror is always swallowed */
-- 
2.1.0


From be202f99b803e852da49c1ad55fcd8898974167b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Sun, 3 Jul 2016 22:24:50 +0200
Subject: [PATCH 3/4] cdc_ncm: workaround for EM7455 "silent" data interface
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit c086e7096170390594c425114d98172bc9aceb8a ]

Several Lenovo users have reported problems with their Sierra
Wireless EM7455 modem. The driver has loaded successfully and
the MBIM management channel has appeared to work, including
establishing a connection to the mobile network. But no frames
have been received over the data interface.

The problem affects all EM7455 and MC7455, and is assumed to
affect other modems based on the same Qualcomm chipset and
baseband firmware.

Testing narrowed the problem down to what seems to be a
firmware timing bug during initialization. Adding a short sleep
while probing is sufficient to make the problem disappear.
Experiments have shown that 1-2 ms is too little to have any
effect, while 10-20 ms is enough to reliably succeed.

Reported-by: Stefan Armbruster <ml001@armbruster-it.de>
Reported-by: Ralph Plawetzki <ralph@purejava.org>
Reported-by: Andreas Fett <andreas.fett@secunet.com>
Reported-by: Rasmus Lerdorf <rasmus@lerdorf.com>
Reported-by: Samo Ratnik <samo.ratnik@gmail.com>
Reported-and-tested-by: Aleksander Morgado <aleksander@aleksander.es>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ncm.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 8c2bb77..a790d5f 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -809,6 +809,13 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_
 	if (cdc_ncm_init(dev))
 		goto error2;
 
+	/* Some firmwares need a pause here or they will silently fail
+	 * to set up the interface properly.  This value was decided
+	 * empirically on a Sierra Wireless MC7455 running 02.08.02.00
+	 * firmware.
+	 */
+	usleep_range(10000, 20000);
+
 	/* configure data interface */
 	temp = usb_set_interface(dev->udev, iface_no, data_altsetting);
 	if (temp) {
-- 
2.1.0


From d785e7a98355ecf6ef353ecb0a475166f8dc41b1 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Tue, 5 Jul 2016 12:10:23 -0700
Subject: [PATCH 4/4] ipv6: Fix mem leak in rt6i_pcpu

[ Upstream commit 903ce4abdf374e3365d93bcb3df56c62008835ba ]

It was first reported and reproduced by Petr (thanks!) in
https://bugzilla.kernel.org/show_bug.cgi?id=119581

free_percpu(rt->rt6i_pcpu) used to always happen in ip6_dst_destroy().

However, after fixing a deadlock bug in
commit 9c7370a166b4 ("ipv6: Fix a potential deadlock when creating pcpu rt"),
free_percpu() is not called before setting non_pcpu_rt->rt6i_pcpu to NULL.

It is worth to note that rt6i_pcpu is protected by table->tb6_lock.

kmemleak somehow did not report it.  We nailed it down by
observing the pcpu entries in /proc/vmallocinfo (first suggested
by Hannes, thanks!).

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Fixes: 9c7370a166b4 ("ipv6: Fix a potential deadlock when creating pcpu rt")
Reported-by: Petr Novopashenniy <pety@rusnet.ru>
Tested-by: Petr Novopashenniy <pety@rusnet.ru>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Cc: Petr Novopashenniy <pety@rusnet.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_fib.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 0c7e276..34cf46d 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -179,6 +179,7 @@ static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt)
 		}
 	}
 
+	free_percpu(non_pcpu_rt->rt6i_pcpu);
 	non_pcpu_rt->rt6i_pcpu = NULL;
 }
 
-- 
2.1.0


[-- Attachment #3: net_46.mbox --]
[-- Type: Application/Octet-Stream, Size: 14450 bytes --]

From 0a1f87a9420c9bbcc8c269af11bc69d6b7e50d82 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 1 Jul 2016 16:07:50 -0400
Subject: [PATCH 1/6] packet: Use symmetric hash for PACKET_FANOUT_HASH.

[ Upstream commit eb70db8756717b90c01ccc765fdefc4dd969fc74 ]

People who use PACKET_FANOUT_HASH want a symmetric hash, meaning that
they want packets going in both directions on a flow to hash to the
same bucket.

The core kernel SKB hash became non-symmetric when the ipv6 flow label
and other entities were incorporated into the standard flow hash order
to increase entropy.

But there are no users of PACKET_FANOUT_HASH who want an assymetric
hash, they all want a symmetric one.

Therefore, use the flow dissector to compute a flat symmetric hash
over only the protocol, addresses and ports.  This hash does not get
installed into and override the normal skb hash, so this change has
no effect whatsoever on the rest of the stack.

Reported-by: Eric Leblond <eric@regit.org>
Tested-by: Eric Leblond <eric@regit.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h    |  1 +
 net/core/flow_dissector.c | 43 +++++++++++++++++++++++++++++++++++++++++++
 net/packet/af_packet.c    |  2 +-
 3 files changed, 45 insertions(+), 1 deletion(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 15d0df9..c0441de 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1062,6 +1062,7 @@ __skb_set_sw_hash(struct sk_buff *skb, __u32 hash, bool is_l4)
 }
 
 void __skb_get_hash(struct sk_buff *skb);
+u32 __skb_get_hash_symmetric(struct sk_buff *skb);
 u32 skb_get_poff(const struct sk_buff *skb);
 u32 __skb_get_poff(const struct sk_buff *skb, void *data,
 		   const struct flow_keys *keys, int hlen);
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index a669dea..61ad43f 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -651,6 +651,23 @@ void make_flow_keys_digest(struct flow_keys_digest *digest,
 }
 EXPORT_SYMBOL(make_flow_keys_digest);
 
+static struct flow_dissector flow_keys_dissector_symmetric __read_mostly;
+
+u32 __skb_get_hash_symmetric(struct sk_buff *skb)
+{
+	struct flow_keys keys;
+
+	__flow_hash_secret_init();
+
+	memset(&keys, 0, sizeof(keys));
+	__skb_flow_dissect(skb, &flow_keys_dissector_symmetric, &keys,
+			   NULL, 0, 0, 0,
+			   FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
+
+	return __flow_hash_from_keys(&keys, hashrnd);
+}
+EXPORT_SYMBOL_GPL(__skb_get_hash_symmetric);
+
 /**
  * __skb_get_hash: calculate a flow hash
  * @skb: sk_buff to calculate flow hash from
@@ -868,6 +885,29 @@ static const struct flow_dissector_key flow_keys_dissector_keys[] = {
 	},
 };
 
+static const struct flow_dissector_key flow_keys_dissector_symmetric_keys[] = {
+	{
+		.key_id = FLOW_DISSECTOR_KEY_CONTROL,
+		.offset = offsetof(struct flow_keys, control),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_BASIC,
+		.offset = offsetof(struct flow_keys, basic),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS,
+		.offset = offsetof(struct flow_keys, addrs.v4addrs),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS,
+		.offset = offsetof(struct flow_keys, addrs.v6addrs),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_PORTS,
+		.offset = offsetof(struct flow_keys, ports),
+	},
+};
+
 static const struct flow_dissector_key flow_keys_buf_dissector_keys[] = {
 	{
 		.key_id = FLOW_DISSECTOR_KEY_CONTROL,
@@ -889,6 +929,9 @@ static int __init init_default_flow_dissectors(void)
 	skb_flow_dissector_init(&flow_keys_dissector,
 				flow_keys_dissector_keys,
 				ARRAY_SIZE(flow_keys_dissector_keys));
+	skb_flow_dissector_init(&flow_keys_dissector_symmetric,
+				flow_keys_dissector_symmetric_keys,
+				ARRAY_SIZE(flow_keys_dissector_symmetric_keys));
 	skb_flow_dissector_init(&flow_keys_buf_dissector,
 				flow_keys_buf_dissector_keys,
 				ARRAY_SIZE(flow_keys_buf_dissector_keys));
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 18d0bec..8012f67 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1340,7 +1340,7 @@ static unsigned int fanout_demux_hash(struct packet_fanout *f,
 				      struct sk_buff *skb,
 				      unsigned int num)
 {
-	return reciprocal_scale(skb_get_hash(skb), num);
+	return reciprocal_scale(__skb_get_hash_symmetric(skb), num);
 }
 
 static unsigned int fanout_demux_lb(struct packet_fanout *f,
-- 
2.1.0


From 177291da5b7829d8f8fdf1f81b97e0c0e03d7ece Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Thu, 30 Jun 2016 10:15:22 -0700
Subject: [PATCH 2/6] net_sched: fix mirrored packets checksum

[ Upstream commit 82a31b9231f02d9c1b7b290a46999d517b0d312a ]

Similar to commit 9b368814b336 ("net: fix bridge multicast packet checksum validation")
we need to fixup the checksum for CHECKSUM_COMPLETE when
pushing skb on RX path. Otherwise we get similar splats.

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Tom Herbert <tom@herbertland.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 19 +++++++++++++++++++
 net/core/skbuff.c      | 18 ------------------
 net/sched/act_mirred.c |  2 +-
 3 files changed, 20 insertions(+), 19 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index c0441de..794b924 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2861,6 +2861,25 @@ static inline void skb_postpush_rcsum(struct sk_buff *skb,
 }
 
 /**
+ *	skb_push_rcsum - push skb and update receive checksum
+ *	@skb: buffer to update
+ *	@len: length of data pulled
+ *
+ *	This function performs an skb_push on the packet and updates
+ *	the CHECKSUM_COMPLETE checksum.  It should be used on
+ *	receive path processing instead of skb_push unless you know
+ *	that the checksum difference is zero (e.g., a valid IP header)
+ *	or you are setting ip_summed to CHECKSUM_NONE.
+ */
+static inline unsigned char *skb_push_rcsum(struct sk_buff *skb,
+					    unsigned int len)
+{
+	skb_push(skb, len);
+	skb_postpush_rcsum(skb, skb->data, len);
+	return skb->data;
+}
+
+/**
  *	pskb_trim_rcsum - trim received skb and update checksum
  *	@skb: buffer to trim
  *	@len: new length
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index e561f9f..59bf4d7 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3016,24 +3016,6 @@ int skb_append_pagefrags(struct sk_buff *skb, struct page *page,
 EXPORT_SYMBOL_GPL(skb_append_pagefrags);
 
 /**
- *	skb_push_rcsum - push skb and update receive checksum
- *	@skb: buffer to update
- *	@len: length of data pulled
- *
- *	This function performs an skb_push on the packet and updates
- *	the CHECKSUM_COMPLETE checksum.  It should be used on
- *	receive path processing instead of skb_push unless you know
- *	that the checksum difference is zero (e.g., a valid IP header)
- *	or you are setting ip_summed to CHECKSUM_NONE.
- */
-static unsigned char *skb_push_rcsum(struct sk_buff *skb, unsigned len)
-{
-	skb_push(skb, len);
-	skb_postpush_rcsum(skb, skb->data, len);
-	return skb->data;
-}
-
-/**
  *	skb_pull_rcsum - pull skb and update receive checksum
  *	@skb: buffer to update
  *	@len: length of data pulled
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 8f3948d..934336e 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -180,7 +180,7 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
 
 	if (!(at & AT_EGRESS)) {
 		if (m->tcfm_ok_push)
-			skb_push(skb2, skb->mac_len);
+			skb_push_rcsum(skb2, skb->mac_len);
 	}
 
 	/* mirror is always swallowed */
-- 
2.1.0


From ee1d004ae1230f6d54682585cc4d072dd12ee235 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 1 Jul 2016 00:00:54 +0200
Subject: [PATCH 3/6] macsec: set actual real device for xmit when
 !protect_frames

[ Upstream commit 79c62220d74a4a3f961a2cb7320da09eebf5daf7 ]

Avoid recursions of dev_queue_xmit() to the wrong net device when
frames are unprotected, since at that time skb->dev still points to
our own macsec dev and unlike macsec_encrypt_finish() dev pointer
doesn't get updated to real underlying device.

Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Sabrina Dubroca <sd@queasysnail.net>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macsec.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 9e803bb..8f3c55d 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -2564,6 +2564,7 @@ static netdev_tx_t macsec_start_xmit(struct sk_buff *skb,
 		u64_stats_update_begin(&secy_stats->syncp);
 		secy_stats->stats.OutPktsUntagged++;
 		u64_stats_update_end(&secy_stats->syncp);
+		skb->dev = macsec->real_dev;
 		len = skb->len;
 		ret = dev_queue_xmit(skb);
 		count_tx(dev, ret, len);
-- 
2.1.0


From 79ca617ef73be3eaccca07be9f9b976664d4e97a Mon Sep 17 00:00:00 2001
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Sat, 2 Jul 2016 15:02:48 +0800
Subject: [PATCH 4/6] geneve: fix max_mtu setting

[ Upstream commit d5d5e8d55732c7c35c354e45e3b0af2795978a57 ]

For ipv6+udp+geneve encapsulation data, the max_mtu should subtract
sizeof(ipv6hdr), instead of sizeof(iphdr).

Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 9fcb489..c70e515 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1092,12 +1092,17 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
 
 static int __geneve_change_mtu(struct net_device *dev, int new_mtu, bool strict)
 {
+	struct geneve_dev *geneve = netdev_priv(dev);
 	/* The max_mtu calculation does not take account of GENEVE
 	 * options, to avoid excluding potentially valid
 	 * configurations.
 	 */
-	int max_mtu = IP_MAX_MTU - GENEVE_BASE_HLEN - sizeof(struct iphdr)
-		- dev->hard_header_len;
+	int max_mtu = IP_MAX_MTU - GENEVE_BASE_HLEN - dev->hard_header_len;
+
+	if (geneve->remote.sa.sa_family == AF_INET6)
+		max_mtu -= sizeof(struct ipv6hdr);
+	else
+		max_mtu -= sizeof(struct iphdr);
 
 	if (new_mtu < 68)
 		return -EINVAL;
-- 
2.1.0


From c34410fea02ece96658069e654203754510bc2a5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Sun, 3 Jul 2016 22:24:50 +0200
Subject: [PATCH 5/6] cdc_ncm: workaround for EM7455 "silent" data interface
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit c086e7096170390594c425114d98172bc9aceb8a ]

Several Lenovo users have reported problems with their Sierra
Wireless EM7455 modem. The driver has loaded successfully and
the MBIM management channel has appeared to work, including
establishing a connection to the mobile network. But no frames
have been received over the data interface.

The problem affects all EM7455 and MC7455, and is assumed to
affect other modems based on the same Qualcomm chipset and
baseband firmware.

Testing narrowed the problem down to what seems to be a
firmware timing bug during initialization. Adding a short sleep
while probing is sufficient to make the problem disappear.
Experiments have shown that 1-2 ms is too little to have any
effect, while 10-20 ms is enough to reliably succeed.

Reported-by: Stefan Armbruster <ml001@armbruster-it.de>
Reported-by: Ralph Plawetzki <ralph@purejava.org>
Reported-by: Andreas Fett <andreas.fett@secunet.com>
Reported-by: Rasmus Lerdorf <rasmus@lerdorf.com>
Reported-by: Samo Ratnik <samo.ratnik@gmail.com>
Reported-and-tested-by: Aleksander Morgado <aleksander@aleksander.es>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ncm.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 2fb31ed..d4425c56 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -852,6 +852,13 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_
 	if (cdc_ncm_init(dev))
 		goto error2;
 
+	/* Some firmwares need a pause here or they will silently fail
+	 * to set up the interface properly.  This value was decided
+	 * empirically on a Sierra Wireless MC7455 running 02.08.02.00
+	 * firmware.
+	 */
+	usleep_range(10000, 20000);
+
 	/* configure data interface */
 	temp = usb_set_interface(dev->udev, iface_no, data_altsetting);
 	if (temp) {
-- 
2.1.0


From 5b87bb51ed80aff7981b788d9386087a99d168ef Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Tue, 5 Jul 2016 12:10:23 -0700
Subject: [PATCH 6/6] ipv6: Fix mem leak in rt6i_pcpu

[ Upstream commit 903ce4abdf374e3365d93bcb3df56c62008835ba ]

It was first reported and reproduced by Petr (thanks!) in
https://bugzilla.kernel.org/show_bug.cgi?id=119581

free_percpu(rt->rt6i_pcpu) used to always happen in ip6_dst_destroy().

However, after fixing a deadlock bug in
commit 9c7370a166b4 ("ipv6: Fix a potential deadlock when creating pcpu rt"),
free_percpu() is not called before setting non_pcpu_rt->rt6i_pcpu to NULL.

It is worth to note that rt6i_pcpu is protected by table->tb6_lock.

kmemleak somehow did not report it.  We nailed it down by
observing the pcpu entries in /proc/vmallocinfo (first suggested
by Hannes, thanks!).

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Fixes: 9c7370a166b4 ("ipv6: Fix a potential deadlock when creating pcpu rt")
Reported-by: Petr Novopashenniy <pety@rusnet.ru>
Tested-by: Petr Novopashenniy <pety@rusnet.ru>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Cc: Petr Novopashenniy <pety@rusnet.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_fib.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index ea071fa..c26fac2 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -177,6 +177,7 @@ static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt)
 		}
 	}
 
+	free_percpu(non_pcpu_rt->rt6i_pcpu);
 	non_pcpu_rt->rt6i_pcpu = NULL;
 }
 
-- 
2.1.0

Re: [PATCHES] Networking

[Greg KH]

On Wed, Jul 13, 2016 at 02:43:00PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for 4.4.x and 4.6.x
> -stable, respectively.

Thanks, all now queued up!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 112 bytes --]


Please queue up the following networking bug fixes for 4.4.x, 4.6.x,
and 4.7.x -stable, respectively.

Thanks!

[-- Attachment #2: net_44.mbox --]
[-- Type: Text/Plain, Size: 19689 bytes --]

>From a0d876bf464ea9abeb3f74aaf6737b6bcfd650c2 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 10 Jul 2016 10:04:02 +0200
Subject: [PATCH 1/8] tcp: make challenge acks less predictable

[ Upstream commit 75ff39ccc1bd5d3c455b6822ab09e533c551f758 ]

Yue Cao claims that current host rate limiting of challenge ACKS
(RFC 5961) could leak enough information to allow a patient attacker
to hijack TCP sessions. He will soon provide details in an academic
paper.

This patch increases the default limit from 100 to 1000, and adds
some randomization so that the attacker can no longer hijack
sessions without spending a considerable amount of probes.

Based on initial analysis and patch from Linus.

Note that we also have per socket rate limiting, so it is tempting
to remove the host limit in the future.

v2: randomize the count of challenge acks per second, not the period.

Fixes: 282f23c6ee34 ("tcp: implement RFC 5961 3.2")
Reported-by: Yue Cao <ycao009@ucr.edu>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index d4c5115..05f10df 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -89,7 +89,7 @@ int sysctl_tcp_adv_win_scale __read_mostly = 1;
 EXPORT_SYMBOL(sysctl_tcp_adv_win_scale);
 
 /* rfc5961 challenge ack rate limiting */
-int sysctl_tcp_challenge_ack_limit = 100;
+int sysctl_tcp_challenge_ack_limit = 1000;
 
 int sysctl_tcp_stdurg __read_mostly;
 int sysctl_tcp_rfc1337 __read_mostly;
@@ -3427,7 +3427,7 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb)
 	static u32 challenge_timestamp;
 	static unsigned int challenge_count;
 	struct tcp_sock *tp = tcp_sk(sk);
-	u32 now;
+	u32 count, now;
 
 	/* First check our per-socket dupack rate limit. */
 	if (tcp_oow_rate_limited(sock_net(sk), skb,
@@ -3435,13 +3435,18 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb)
 				 &tp->last_oow_ack_time))
 		return;
 
-	/* Then check the check host-wide RFC 5961 rate limit. */
+	/* Then check host-wide RFC 5961 rate limit. */
 	now = jiffies / HZ;
 	if (now != challenge_timestamp) {
+		u32 half = (sysctl_tcp_challenge_ack_limit + 1) >> 1;
+
 		challenge_timestamp = now;
-		challenge_count = 0;
+		WRITE_ONCE(challenge_count, half +
+			   prandom_u32_max(sysctl_tcp_challenge_ack_limit));
 	}
-	if (++challenge_count <= sysctl_tcp_challenge_ack_limit) {
+	count = READ_ONCE(challenge_count);
+	if (count > 0) {
+		WRITE_ONCE(challenge_count, count - 1);
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPCHALLENGEACK);
 		tcp_send_ack(sk);
 	}
-- 
2.1.0


>From 308b416124e42860984b23f37dac89b5e841a630 Mon Sep 17 00:00:00 2001
From: Jason Baron <jbaron@akamai.com>
Date: Thu, 14 Jul 2016 11:38:40 -0400
Subject: [PATCH 2/8] tcp: enable per-socket rate limiting of all 'challenge
 acks'

[ Upstream commit 083ae308280d13d187512b9babe3454342a7987e ]

The per-socket rate limit for 'challenge acks' was introduced in the
context of limiting ack loops:

commit f2b2c582e824 ("tcp: mitigate ACK loops for connections as tcp_sock")

And I think it can be extended to rate limit all 'challenge acks' on a
per-socket basis.

Since we have the global tcp_challenge_ack_limit, this patch allows for
tcp_challenge_ack_limit to be set to a large value and effectively rely on
the per-socket limit, or set tcp_challenge_ack_limit to a lower value and
still prevents a single connections from consuming the entire challenge ack
quota.

It further moves in the direction of eliminating the global limit at some
point, as Eric Dumazet has suggested. This a follow-up to:
Subject: tcp: make challenge acks less predictable

Cc: Eric Dumazet <edumazet@google.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Yue Cao <ycao009@ucr.edu>
Signed-off-by: Jason Baron <jbaron@akamai.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 39 ++++++++++++++++++++++-----------------
 1 file changed, 22 insertions(+), 17 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 05f10df..12b98e2 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3390,6 +3390,23 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32
 	return flag;
 }
 
+static bool __tcp_oow_rate_limited(struct net *net, int mib_idx,
+				   u32 *last_oow_ack_time)
+{
+	if (*last_oow_ack_time) {
+		s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time);
+
+		if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) {
+			NET_INC_STATS_BH(net, mib_idx);
+			return true;	/* rate-limited: don't send yet! */
+		}
+	}
+
+	*last_oow_ack_time = tcp_time_stamp;
+
+	return false;	/* not rate-limited: go ahead, send dupack now! */
+}
+
 /* Return true if we're currently rate-limiting out-of-window ACKs and
  * thus shouldn't send a dupack right now. We rate-limit dupacks in
  * response to out-of-window SYNs or ACKs to mitigate ACK loops or DoS
@@ -3403,21 +3420,9 @@ bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb,
 	/* Data packets without SYNs are not likely part of an ACK loop. */
 	if ((TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq) &&
 	    !tcp_hdr(skb)->syn)
-		goto not_rate_limited;
-
-	if (*last_oow_ack_time) {
-		s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time);
-
-		if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) {
-			NET_INC_STATS_BH(net, mib_idx);
-			return true;	/* rate-limited: don't send yet! */
-		}
-	}
-
-	*last_oow_ack_time = tcp_time_stamp;
+		return false;
 
-not_rate_limited:
-	return false;	/* not rate-limited: go ahead, send dupack now! */
+	return __tcp_oow_rate_limited(net, mib_idx, last_oow_ack_time);
 }
 
 /* RFC 5961 7 [ACK Throttling] */
@@ -3430,9 +3435,9 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb)
 	u32 count, now;
 
 	/* First check our per-socket dupack rate limit. */
-	if (tcp_oow_rate_limited(sock_net(sk), skb,
-				 LINUX_MIB_TCPACKSKIPPEDCHALLENGE,
-				 &tp->last_oow_ack_time))
+	if (__tcp_oow_rate_limited(sock_net(sk),
+				   LINUX_MIB_TCPACKSKIPPEDCHALLENGE,
+				   &tp->last_oow_ack_time))
 		return;
 
 	/* Then check host-wide RFC 5961 rate limit. */
-- 
2.1.0


>From 9cee84ffee983b4a98838832cce4534a0b0f4b71 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Sun, 10 Jul 2016 21:11:55 +0300
Subject: [PATCH 3/8] ipv4: reject RTNH_F_DEAD and RTNH_F_LINKDOWN from user
 space

[ Upstream commit 80610229ef7b26615dbb6cb6e873709a60bacc9f ]

Vegard Nossum is reporting for a crash in fib_dump_info
when nh_dev = NULL and fib_nhs == 1:

Pid: 50, comm: netlink.exe Not tainted 4.7.0-rc5+
RIP: 0033:[<00000000602b3d18>]
RSP: 0000000062623890  EFLAGS: 00010202
RAX: 0000000000000000 RBX: 000000006261b800 RCX: 0000000000000000
RDX: 0000000000000000 RSI: 0000000000000024 RDI: 000000006245ba00
RBP: 00000000626238f0 R08: 000000000000029c R09: 0000000000000000
R10: 0000000062468038 R11: 000000006245ba00 R12: 000000006245ba00
R13: 00000000625f96c0 R14: 00000000601e16f0 R15: 0000000000000000
Kernel panic - not syncing: Kernel mode fault at addr 0x2e0, ip 0x602b3d18
CPU: 0 PID: 50 Comm: netlink.exe Not tainted 4.7.0-rc5+ #581
Stack:
 626238f0 960226a02 00000400 000000fe
 62623910 600afca7 62623970 62623a48
 62468038 00000018 00000000 00000000
Call Trace:
 [<602b3e93>] rtmsg_fib+0xd3/0x190
 [<602b6680>] fib_table_insert+0x260/0x500
 [<602b0e5d>] inet_rtm_newroute+0x4d/0x60
 [<60250def>] rtnetlink_rcv_msg+0x8f/0x270
 [<60267079>] netlink_rcv_skb+0xc9/0xe0
 [<60250d4b>] rtnetlink_rcv+0x3b/0x50
 [<60265400>] netlink_unicast+0x1a0/0x2c0
 [<60265e47>] netlink_sendmsg+0x3f7/0x470
 [<6021dc9a>] sock_sendmsg+0x3a/0x90
 [<6021e0d0>] ___sys_sendmsg+0x300/0x360
 [<6021fa64>] __sys_sendmsg+0x54/0xa0
 [<6021fac0>] SyS_sendmsg+0x10/0x20
 [<6001ea68>] handle_syscall+0x88/0x90
 [<600295fd>] userspace+0x3fd/0x500
 [<6001ac55>] fork_handler+0x85/0x90

$ addr2line -e vmlinux -i 0x602b3d18
include/linux/inetdevice.h:222
net/ipv4/fib_semantics.c:1264

Problem happens when RTNH_F_LINKDOWN is provided from user space
when creating routes that do not use the flag, catched with
netlink fuzzer.

Currently, the kernel allows user space to set both flags
to nh_flags and fib_flags but this is not intentional, the
assumption was that they are not set. Fix this by rejecting
both flags with EINVAL.

Reported-by: Vegard Nossum <vegard.nossum@oracle.com>
Fixes: 0eeb075fad73 ("net: ipv4 sysctl option to ignore routes when nexthop link is down")
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Cc: Andy Gospodarek <gospo@cumulusnetworks.com>
Cc: Dinesh Dutt <ddutt@cumulusnetworks.com>
Cc: Scott Feldman <sfeldma@gmail.com>
Reviewed-by: Andy Gospodarek <gospo@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_semantics.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 2b68418..ffe95d9 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -479,6 +479,9 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
 		if (!rtnh_ok(rtnh, remaining))
 			return -EINVAL;
 
+		if (rtnh->rtnh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN))
+			return -EINVAL;
+
 		nexthop_nh->nh_flags =
 			(cfg->fc_flags & ~0xFF) | rtnh->rtnh_flags;
 		nexthop_nh->nh_oif = rtnh->rtnh_ifindex;
@@ -1003,6 +1006,9 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 	if (fib_props[cfg->fc_type].scope > cfg->fc_scope)
 		goto err_inval;
 
+	if (cfg->fc_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN))
+		goto err_inval;
+
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	if (cfg->fc_mp) {
 		nhs = fib_count_nexthops(cfg->fc_mp, cfg->fc_mp_len);
-- 
2.1.0


>From d18b5b20c5dd68da8199dc859d711cd0af921057 Mon Sep 17 00:00:00 2001
From: Beniamino Galvani <bgalvani@redhat.com>
Date: Wed, 13 Jul 2016 18:25:08 +0200
Subject: [PATCH 4/8] bonding: set carrier off for devices created through
 netlink

[ Upstream commit 005db31d5f5f7c31cfdc43505d77eb3ca5cf8ec6 ]

Commit e826eafa65c6 ("bonding: Call netif_carrier_off after
register_netdevice") moved netif_carrier_off() from bond_init() to
bond_create(), but the latter is called only for initial default
devices and ones created through sysfs:

 $ modprobe bonding
 $ echo +bond1 > /sys/class/net/bonding_masters
 $ ip link add bond2 type bond
 $ grep "MII Status" /proc/net/bonding/*
 /proc/net/bonding/bond0:MII Status: down
 /proc/net/bonding/bond1:MII Status: down
 /proc/net/bonding/bond2:MII Status: up

Ensure that carrier is initially off also for devices created through
netlink.

Signed-off-by: Beniamino Galvani <bgalvani@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_netlink.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index db760e8..b8df0f5 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -446,7 +446,11 @@ static int bond_newlink(struct net *src_net, struct net_device *bond_dev,
 	if (err < 0)
 		return err;
 
-	return register_netdevice(bond_dev);
+	err = register_netdevice(bond_dev);
+
+	netif_carrier_off(bond_dev);
+
+	return err;
 }
 
 static size_t bond_get_size(const struct net_device *bond_dev)
-- 
2.1.0


>From a13baae73d6c93fd4bfc2802e7494a8a21da92f2 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 15 Jul 2016 15:42:52 -0700
Subject: [PATCH 5/8] net: bgmac: Fix infinite loop in bgmac_dma_tx_add()

[ Upstream commit e86663c475d384ab5f46cb5637e9b7ad08c5c505 ]

Nothing is decrementing the index "i" while we are cleaning up the
fragments we could not successful transmit.

Fixes: 9cde94506eacf ("bgmac: implement scatter/gather support")
Reported-by: coverity (CID 1352048)
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bgmac.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index 28f7610..c32f5d3 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -219,7 +219,7 @@ err_dma:
 	dma_unmap_single(dma_dev, slot->dma_addr, skb_headlen(skb),
 			 DMA_TO_DEVICE);
 
-	while (i > 0) {
+	while (i-- > 0) {
 		int index = (ring->end + i) % BGMAC_TX_RING_SLOTS;
 		struct bgmac_slot_info *slot = &ring->slots[index];
 		u32 ctl1 = le32_to_cpu(ring->cpu_base[index].ctl1);
-- 
2.1.0


>From a0a4d274c777f91ff92c0b5f509728fc71117158 Mon Sep 17 00:00:00 2001
From: Vegard Nossum <vegard.nossum@oracle.com>
Date: Sat, 23 Jul 2016 07:43:50 +0200
Subject: [PATCH 6/8] net/irda: fix NULL pointer dereference on memory
 allocation failure

[ Upstream commit d3e6952cfb7ba5f4bfa29d4803ba91f96ce1204d ]

I ran into this:

    kasan: CONFIG_KASAN_INLINE enabled
    kasan: GPF could be caused by NULL-ptr deref or user memory access
    general protection fault: 0000 [#1] PREEMPT SMP KASAN
    CPU: 2 PID: 2012 Comm: trinity-c3 Not tainted 4.7.0-rc7+ #19
    Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014
    task: ffff8800b745f2c0 ti: ffff880111740000 task.ti: ffff880111740000
    RIP: 0010:[<ffffffff82bbf066>]  [<ffffffff82bbf066>] irttp_connect_request+0x36/0x710
    RSP: 0018:ffff880111747bb8  EFLAGS: 00010286
    RAX: dffffc0000000000 RBX: 0000000000000000 RCX: 0000000069dd8358
    RDX: 0000000000000009 RSI: 0000000000000027 RDI: 0000000000000048
    RBP: ffff880111747c00 R08: 0000000000000000 R09: 0000000000000000
    R10: 0000000069dd8358 R11: 1ffffffff0759723 R12: 0000000000000000
    R13: ffff88011a7e4780 R14: 0000000000000027 R15: 0000000000000000
    FS:  00007fc738404700(0000) GS:ffff88011af00000(0000) knlGS:0000000000000000
    CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
    CR2: 00007fc737fdfb10 CR3: 0000000118087000 CR4: 00000000000006e0
    Stack:
     0000000000000200 ffff880111747bd8 ffffffff810ee611 ffff880119f1f220
     ffff880119f1f4f8 ffff880119f1f4f0 ffff88011a7e4780 ffff880119f1f232
     ffff880119f1f220 ffff880111747d58 ffffffff82bca542 0000000000000000
    Call Trace:
     [<ffffffff82bca542>] irda_connect+0x562/0x1190
     [<ffffffff825ae582>] SYSC_connect+0x202/0x2a0
     [<ffffffff825b4489>] SyS_connect+0x9/0x10
     [<ffffffff8100334c>] do_syscall_64+0x19c/0x410
     [<ffffffff83295ca5>] entry_SYSCALL64_slow_path+0x25/0x25
    Code: 41 89 ca 48 89 e5 41 57 41 56 41 55 41 54 41 89 d7 53 48 89 fb 48 83 c7 48 48 89 fa 41 89 f6 48 c1 ea 03 48 83 ec 20 4c 8b 65 10 <0f> b6 04 02 84 c0 74 08 84 c0 0f 8e 4c 04 00 00 80 7b 48 00 74
    RIP  [<ffffffff82bbf066>] irttp_connect_request+0x36/0x710
     RSP <ffff880111747bb8>
    ---[ end trace 4cda2588bc055b30 ]---

The problem is that irda_open_tsap() can fail and leave self->tsap = NULL,
and then irttp_connect_request() almost immediately dereferences it.

Cc: stable@vger.kernel.org
Signed-off-by: Vegard Nossum <vegard.nossum@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/irda/af_irda.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index 923abd6..8d2f7c9 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -1024,8 +1024,11 @@ static int irda_connect(struct socket *sock, struct sockaddr *uaddr,
 	}
 
 	/* Check if we have opened a local TSAP */
-	if (!self->tsap)
-		irda_open_tsap(self, LSAP_ANY, addr->sir_name);
+	if (!self->tsap) {
+		err = irda_open_tsap(self, LSAP_ANY, addr->sir_name);
+		if (err)
+			goto out;
+	}
 
 	/* Move to connecting socket, start sending Connect Requests */
 	sock->state = SS_CONNECTING;
-- 
2.1.0


>From e51820b246d30c8b4a29910fb9474a265d8fd75c Mon Sep 17 00:00:00 2001
From: Manish Chopra <manish.chopra@qlogic.com>
Date: Mon, 25 Jul 2016 19:07:46 +0300
Subject: [PATCH 7/8] qed: Fix setting/clearing bit in completion bitmap

[ Upstream commit 59d3f1ceb69b54569685d0c34dff16a1e0816b19 ]

Slowpath completion handling is incorrectly changing
SPQ_RING_SIZE bits instead of a single one.

Fixes: 76a9a3642a0b ("qed: fix handling of concurrent ramrods")
Signed-off-by: Manish Chopra <manish.chopra@qlogic.com>
Signed-off-by: Yuval Mintz <Yuval.Mintz@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_spq.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c
index 3dd548a..40365cb 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_spq.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c
@@ -794,13 +794,12 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn,
 			 * in a bitmap and increasing the chain consumer only
 			 * for the first successive completed entries.
 			 */
-			bitmap_set(p_spq->p_comp_bitmap, pos, SPQ_RING_SIZE);
+			__set_bit(pos, p_spq->p_comp_bitmap);
 
 			while (test_bit(p_spq->comp_bitmap_idx,
 					p_spq->p_comp_bitmap)) {
-				bitmap_clear(p_spq->p_comp_bitmap,
-					     p_spq->comp_bitmap_idx,
-					     SPQ_RING_SIZE);
+				__clear_bit(p_spq->comp_bitmap_idx,
+					    p_spq->p_comp_bitmap);
 				p_spq->comp_bitmap_idx++;
 				qed_chain_return_produced(&p_spq->chain);
 			}
-- 
2.1.0


>From 2471ebe21d69b9dcd981532d0bfddcd1197c210c Mon Sep 17 00:00:00 2001
From: Soheil Hassas Yeganeh <soheil@google.com>
Date: Fri, 29 Jul 2016 09:34:02 -0400
Subject: [PATCH 8/8] tcp: consider recv buf for the initial window scale

[ Upstream commit f626300a3e776ccc9671b0dd94698fb3aa315966 ]

tcp_select_initial_window() intends to advertise a window
scaling for the maximum possible window size. To do so,
it considers the maximum of net.ipv4.tcp_rmem[2] and
net.core.rmem_max as the only possible upper-bounds.
However, users with CAP_NET_ADMIN can use SO_RCVBUFFORCE
to set the socket's receive buffer size to values
larger than net.ipv4.tcp_rmem[2] and net.core.rmem_max.
Thus, SO_RCVBUFFORCE is effectively ignored by
tcp_select_initial_window().

To fix this, consider the maximum of net.ipv4.tcp_rmem[2],
net.core.rmem_max and socket's initial buffer space.

Fixes: b0573dea1fb3 ("[NET]: Introduce SO_{SND,RCV}BUFFORCE socket options")
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Suggested-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 7c9883a..660c967 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -239,7 +239,8 @@ void tcp_select_initial_window(int __space, __u32 mss,
 		/* Set window scaling on max possible window
 		 * See RFC1323 for an explanation of the limit to 14
 		 */
-		space = max_t(u32, sysctl_tcp_rmem[2], sysctl_rmem_max);
+		space = max_t(u32, space, sysctl_tcp_rmem[2]);
+		space = max_t(u32, space, sysctl_rmem_max);
 		space = min_t(u32, space, *window_clamp);
 		while (space > 65535 && (*rcv_wscale) < 14) {
 			space >>= 1;
-- 
2.1.0


[-- Attachment #3: net_46.mbox --]
[-- Type: Text/Plain, Size: 27698 bytes --]

>From 9509f0f1ebffa31c3864d8ab5c3fd52ee6614a99 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Tue, 5 Jul 2016 22:12:36 -0700
Subject: [PATCH 01/13] ppp: defer netns reference release for ppp channel

[ Upstream commit 205e1e255c479f3fd77446415706463b282f94e4 ]

Matt reported that we have a NULL pointer dereference
in ppp_pernet() from ppp_connect_channel(),
i.e. pch->chan_net is NULL.

This is due to that a parallel ppp_unregister_channel()
could happen while we are in ppp_connect_channel(), during
which pch->chan_net set to NULL. Since we need a reference
to net per channel, it makes sense to sync the refcnt
with the life time of the channel, therefore we should
release this reference when we destroy it.

Fixes: 1f461dcdd296 ("ppp: take reference on channels netns")
Reported-by: Matt Bennett <Matt.Bennett@alliedtelesis.co.nz>
Cc: Paul Mackerras <paulus@samba.org>
Cc: linux-ppp@vger.kernel.org
Cc: Guillaume Nault <g.nault@alphalink.fr>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Reviewed-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/ppp_generic.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index f572b31..9ab88e1 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -2404,8 +2404,6 @@ ppp_unregister_channel(struct ppp_channel *chan)
 	spin_lock_bh(&pn->all_channels_lock);
 	list_del(&pch->list);
 	spin_unlock_bh(&pn->all_channels_lock);
-	put_net(pch->chan_net);
-	pch->chan_net = NULL;
 
 	pch->file.dead = 1;
 	wake_up_interruptible(&pch->file.rwait);
@@ -2999,6 +2997,9 @@ ppp_disconnect_channel(struct channel *pch)
  */
 static void ppp_destroy_channel(struct channel *pch)
 {
+	put_net(pch->chan_net);
+	pch->chan_net = NULL;
+
 	atomic_dec(&channel_count);
 
 	if (!pch->file.dead) {
-- 
2.1.0


>From fe76d1a9b2674634d17553f8eead09c6a7f34d18 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 10 Jul 2016 10:04:02 +0200
Subject: [PATCH 02/13] tcp: make challenge acks less predictable

[ Upstream commit 75ff39ccc1bd5d3c455b6822ab09e533c551f758 ]

Yue Cao claims that current host rate limiting of challenge ACKS
(RFC 5961) could leak enough information to allow a patient attacker
to hijack TCP sessions. He will soon provide details in an academic
paper.

This patch increases the default limit from 100 to 1000, and adds
some randomization so that the attacker can no longer hijack
sessions without spending a considerable amount of probes.

Based on initial analysis and patch from Linus.

Note that we also have per socket rate limiting, so it is tempting
to remove the host limit in the future.

v2: randomize the count of challenge acks per second, not the period.

Fixes: 282f23c6ee34 ("tcp: implement RFC 5961 3.2")
Reported-by: Yue Cao <ycao009@ucr.edu>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index c124c3c..593b141 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -87,7 +87,7 @@ int sysctl_tcp_adv_win_scale __read_mostly = 1;
 EXPORT_SYMBOL(sysctl_tcp_adv_win_scale);
 
 /* rfc5961 challenge ack rate limiting */
-int sysctl_tcp_challenge_ack_limit = 100;
+int sysctl_tcp_challenge_ack_limit = 1000;
 
 int sysctl_tcp_stdurg __read_mostly;
 int sysctl_tcp_rfc1337 __read_mostly;
@@ -3460,7 +3460,7 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb)
 	static u32 challenge_timestamp;
 	static unsigned int challenge_count;
 	struct tcp_sock *tp = tcp_sk(sk);
-	u32 now;
+	u32 count, now;
 
 	/* First check our per-socket dupack rate limit. */
 	if (tcp_oow_rate_limited(sock_net(sk), skb,
@@ -3468,13 +3468,18 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb)
 				 &tp->last_oow_ack_time))
 		return;
 
-	/* Then check the check host-wide RFC 5961 rate limit. */
+	/* Then check host-wide RFC 5961 rate limit. */
 	now = jiffies / HZ;
 	if (now != challenge_timestamp) {
+		u32 half = (sysctl_tcp_challenge_ack_limit + 1) >> 1;
+
 		challenge_timestamp = now;
-		challenge_count = 0;
+		WRITE_ONCE(challenge_count, half +
+			   prandom_u32_max(sysctl_tcp_challenge_ack_limit));
 	}
-	if (++challenge_count <= sysctl_tcp_challenge_ack_limit) {
+	count = READ_ONCE(challenge_count);
+	if (count > 0) {
+		WRITE_ONCE(challenge_count, count - 1);
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPCHALLENGEACK);
 		tcp_send_ack(sk);
 	}
-- 
2.1.0


>From 26032523d8333c6ca39897f1c1eac4440443e9f6 Mon Sep 17 00:00:00 2001
From: Jason Baron <jbaron@akamai.com>
Date: Thu, 14 Jul 2016 11:38:40 -0400
Subject: [PATCH 03/13] tcp: enable per-socket rate limiting of all 'challenge
 acks'

[ Upstream commit 083ae308280d13d187512b9babe3454342a7987e ]

The per-socket rate limit for 'challenge acks' was introduced in the
context of limiting ack loops:

commit f2b2c582e824 ("tcp: mitigate ACK loops for connections as tcp_sock")

And I think it can be extended to rate limit all 'challenge acks' on a
per-socket basis.

Since we have the global tcp_challenge_ack_limit, this patch allows for
tcp_challenge_ack_limit to be set to a large value and effectively rely on
the per-socket limit, or set tcp_challenge_ack_limit to a lower value and
still prevents a single connections from consuming the entire challenge ack
quota.

It further moves in the direction of eliminating the global limit at some
point, as Eric Dumazet has suggested. This a follow-up to:
Subject: tcp: make challenge acks less predictable

Cc: Eric Dumazet <edumazet@google.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Yue Cao <ycao009@ucr.edu>
Signed-off-by: Jason Baron <jbaron@akamai.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 39 ++++++++++++++++++++++-----------------
 1 file changed, 22 insertions(+), 17 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 593b141..e2e7884 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3423,6 +3423,23 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32
 	return flag;
 }
 
+static bool __tcp_oow_rate_limited(struct net *net, int mib_idx,
+				   u32 *last_oow_ack_time)
+{
+	if (*last_oow_ack_time) {
+		s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time);
+
+		if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) {
+			NET_INC_STATS_BH(net, mib_idx);
+			return true;	/* rate-limited: don't send yet! */
+		}
+	}
+
+	*last_oow_ack_time = tcp_time_stamp;
+
+	return false;	/* not rate-limited: go ahead, send dupack now! */
+}
+
 /* Return true if we're currently rate-limiting out-of-window ACKs and
  * thus shouldn't send a dupack right now. We rate-limit dupacks in
  * response to out-of-window SYNs or ACKs to mitigate ACK loops or DoS
@@ -3436,21 +3453,9 @@ bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb,
 	/* Data packets without SYNs are not likely part of an ACK loop. */
 	if ((TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq) &&
 	    !tcp_hdr(skb)->syn)
-		goto not_rate_limited;
-
-	if (*last_oow_ack_time) {
-		s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time);
-
-		if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) {
-			NET_INC_STATS_BH(net, mib_idx);
-			return true;	/* rate-limited: don't send yet! */
-		}
-	}
-
-	*last_oow_ack_time = tcp_time_stamp;
+		return false;
 
-not_rate_limited:
-	return false;	/* not rate-limited: go ahead, send dupack now! */
+	return __tcp_oow_rate_limited(net, mib_idx, last_oow_ack_time);
 }
 
 /* RFC 5961 7 [ACK Throttling] */
@@ -3463,9 +3468,9 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb)
 	u32 count, now;
 
 	/* First check our per-socket dupack rate limit. */
-	if (tcp_oow_rate_limited(sock_net(sk), skb,
-				 LINUX_MIB_TCPACKSKIPPEDCHALLENGE,
-				 &tp->last_oow_ack_time))
+	if (__tcp_oow_rate_limited(sock_net(sk),
+				   LINUX_MIB_TCPACKSKIPPEDCHALLENGE,
+				   &tp->last_oow_ack_time))
 		return;
 
 	/* Then check host-wide RFC 5961 rate limit. */
-- 
2.1.0


>From 7f39c9a67c446fc870f511b1f2774f54a1b97ac1 Mon Sep 17 00:00:00 2001
From: Beniamino Galvani <bgalvani@redhat.com>
Date: Wed, 13 Jul 2016 18:25:08 +0200
Subject: [PATCH 04/13] bonding: set carrier off for devices created through
 netlink

[ Upstream commit 005db31d5f5f7c31cfdc43505d77eb3ca5cf8ec6 ]

Commit e826eafa65c6 ("bonding: Call netif_carrier_off after
register_netdevice") moved netif_carrier_off() from bond_init() to
bond_create(), but the latter is called only for initial default
devices and ones created through sysfs:

 $ modprobe bonding
 $ echo +bond1 > /sys/class/net/bonding_masters
 $ ip link add bond2 type bond
 $ grep "MII Status" /proc/net/bonding/*
 /proc/net/bonding/bond0:MII Status: down
 /proc/net/bonding/bond1:MII Status: down
 /proc/net/bonding/bond2:MII Status: up

Ensure that carrier is initially off also for devices created through
netlink.

Signed-off-by: Beniamino Galvani <bgalvani@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_netlink.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index db760e8..b8df0f5 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -446,7 +446,11 @@ static int bond_newlink(struct net *src_net, struct net_device *bond_dev,
 	if (err < 0)
 		return err;
 
-	return register_netdevice(bond_dev);
+	err = register_netdevice(bond_dev);
+
+	netif_carrier_off(bond_dev);
+
+	return err;
 }
 
 static size_t bond_get_size(const struct net_device *bond_dev)
-- 
2.1.0


>From a2de40b1b24b9b34cb66ccadd3ed2bb3a7ba3e33 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 15 Jul 2016 15:42:52 -0700
Subject: [PATCH 05/13] net: bgmac: Fix infinite loop in bgmac_dma_tx_add()

[ Upstream commit e86663c475d384ab5f46cb5637e9b7ad08c5c505 ]

Nothing is decrementing the index "i" while we are cleaning up the
fragments we could not successful transmit.

Fixes: 9cde94506eacf ("bgmac: implement scatter/gather support")
Reported-by: coverity (CID 1352048)
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bgmac.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index 38db2e4..832401b 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -231,7 +231,7 @@ err_dma:
 	dma_unmap_single(dma_dev, slot->dma_addr, skb_headlen(skb),
 			 DMA_TO_DEVICE);
 
-	while (i > 0) {
+	while (i-- > 0) {
 		int index = (ring->end + i) % BGMAC_TX_RING_SLOTS;
 		struct bgmac_slot_info *slot = &ring->slots[index];
 		u32 ctl1 = le32_to_cpu(ring->cpu_base[index].ctl1);
-- 
2.1.0


>From b8564b8f1c7b994d1f708237d24ecee97400cab9 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 14 Jul 2016 18:00:10 +0200
Subject: [PATCH 06/13] vlan: use a valid default mtu value for vlan over
 macsec

[ Upstream commit 18d3df3eab23796d7f852f9c6bb60962b8372ced ]

macsec can't cope with mtu frames which need vlan tag insertion, and
vlan device set the default mtu equal to the underlying dev's one.
By default vlan over macsec devices use invalid mtu, dropping
all the large packets.
This patch adds a netif helper to check if an upper vlan device
needs mtu reduction. The helper is used during vlan devices
initialization to set a valid default and during mtu updating to
forbid invalid, too bit, mtu values.
The helper currently only check if the lower dev is a macsec device,
if we get more users, we need to update only the helper (possibly
reserving an additional IFF bit).

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  7 +++++++
 net/8021q/vlan_dev.c      | 10 ++++++----
 net/8021q/vlan_netlink.c  |  7 +++++--
 3 files changed, 18 insertions(+), 6 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 78181a8..54355a7 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4156,6 +4156,13 @@ static inline void netif_keep_dst(struct net_device *dev)
 	dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM);
 }
 
+/* return true if dev can't cope with mtu frames that need vlan tag insertion */
+static inline bool netif_reduces_vlan_mtu(struct net_device *dev)
+{
+	/* TODO: reserve and use an additional IFF bit, if we get more users */
+	return dev->priv_flags & IFF_MACSEC;
+}
+
 extern struct pernet_operations __net_initdata loopback_net_ops;
 
 /* Logging, debugging and troubleshooting/diagnostic helpers. */
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index e7e6257..3a573a2 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -146,10 +146,12 @@ static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb,
 
 static int vlan_dev_change_mtu(struct net_device *dev, int new_mtu)
 {
-	/* TODO: gotta make sure the underlying layer can handle it,
-	 * maybe an IFF_VLAN_CAPABLE flag for devices?
-	 */
-	if (vlan_dev_priv(dev)->real_dev->mtu < new_mtu)
+	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
+	unsigned int max_mtu = real_dev->mtu;
+
+	if (netif_reduces_vlan_mtu(real_dev))
+		max_mtu -= VLAN_HLEN;
+	if (max_mtu < new_mtu)
 		return -ERANGE;
 
 	dev->mtu = new_mtu;
diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c
index c92b52f..1270207 100644
--- a/net/8021q/vlan_netlink.c
+++ b/net/8021q/vlan_netlink.c
@@ -118,6 +118,7 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev,
 {
 	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
 	struct net_device *real_dev;
+	unsigned int max_mtu;
 	__be16 proto;
 	int err;
 
@@ -144,9 +145,11 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev,
 	if (err < 0)
 		return err;
 
+	max_mtu = netif_reduces_vlan_mtu(real_dev) ? real_dev->mtu - VLAN_HLEN :
+						     real_dev->mtu;
 	if (!tb[IFLA_MTU])
-		dev->mtu = real_dev->mtu;
-	else if (dev->mtu > real_dev->mtu)
+		dev->mtu = max_mtu;
+	else if (dev->mtu > max_mtu)
 		return -EINVAL;
 
 	err = vlan_changelink(dev, tb, data);
-- 
2.1.0


>From ff7b8b968430b3dc6aba39c0e38bd2a8e7353fba Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Fri, 22 Jul 2016 14:56:20 +0300
Subject: [PATCH 08/13] bridge: Fix incorrect re-injection of LLDP packets

[ Upstream commit baedbe55884c003819f5c8c063ec3d2569414296 ]

Commit 8626c56c8279 ("bridge: fix potential use-after-free when hook
returns QUEUE or STOLEN verdict") caused LLDP packets arriving through a
bridge port to be re-injected to the Rx path with skb->dev set to the
bridge device, but this breaks the lldpad daemon.

The lldpad daemon opens a packet socket with protocol set to ETH_P_LLDP
for any valid device on the system, which doesn't not include soft
devices such as bridge and VLAN.

Since packet sockets (ptype_base) are processed in the Rx path after the
Rx handler, LLDP packets with skb->dev set to the bridge device never
reach the lldpad daemon.

Fix this by making the bridge's Rx handler re-inject LLDP packets with
RX_HANDLER_PASS, which effectively restores the behaviour prior to the
mentioned commit.

This means netfilter will never receive LLDP packets coming through a
bridge port, as I don't see a way in which we can have okfn() consume
the packet without breaking existing behaviour. I've already carried out
a similar fix for STP packets in commit 56fae404fb2c ("bridge: Fix
incorrect re-injection of STP packets").

Fixes: 8626c56c8279 ("bridge: fix potential use-after-free when hook returns QUEUE or STOLEN verdict")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Cc: Florian Westphal <fw@strlen.de>
Cc: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_input.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 1607977..b32f5a4 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -213,6 +213,16 @@ drop:
 }
 EXPORT_SYMBOL_GPL(br_handle_frame_finish);
 
+static void __br_handle_local_finish(struct sk_buff *skb)
+{
+	struct net_bridge_port *p = br_port_get_rcu(skb->dev);
+	u16 vid = 0;
+
+	/* check if vlan is allowed, to avoid spoofing */
+	if (p->flags & BR_LEARNING && br_should_learn(p, skb, &vid))
+		br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid, false);
+}
+
 /* note: already called with rcu_read_lock */
 static int br_handle_local_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
@@ -279,6 +289,14 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
 		case 0x01:	/* IEEE MAC (Pause) */
 			goto drop;
 
+		case 0x0E:	/* 802.1AB LLDP */
+			fwd_mask |= p->br->group_fwd_mask;
+			if (fwd_mask & (1u << dest[5]))
+				goto forward;
+			*pskb = skb;
+			__br_handle_local_finish(skb);
+			return RX_HANDLER_PASS;
+
 		default:
 			/* Allow selective forwarding for most other protocols */
 			fwd_mask |= p->br->group_fwd_mask;
-- 
2.1.0


>From d4282053091319b7eef8b622bea72df7ea1457dd Mon Sep 17 00:00:00 2001
From: Mike Manning <mmanning@brocade.com>
Date: Fri, 22 Jul 2016 18:32:11 +0100
Subject: [PATCH 09/13] net: ipv6: Always leave anycast and multicast groups on
 link down

[ Upstream commit ea06f7176413e2538d13bb85b65387d0917943d9 ]

Default kernel behavior is to delete IPv6 addresses on link
down, which entails deletion of the multicast and the
subnet-router anycast addresses. These deletions do not
happen with sysctl setting to keep global IPv6 addresses on
link down, so every link down/up causes an increment of the
anycast and multicast refcounts. These bogus refcounts may
stop these addrs from being removed on subsequent calls to
delete them. The solution is to leave the groups for the
multicast and subnet anycast on link down for the callflow
when global IPv6 addresses are kept.

Fixes: f1705ec197e7 ("net: ipv6: Make address flushing on ifdown optional")
Signed-off-by: Mike Manning <mmanning@brocade.com>
Acked-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 8ec4b30..e3fc0cd 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3563,6 +3563,10 @@ restart:
 		if (state != INET6_IFADDR_STATE_DEAD) {
 			__ipv6_ifa_notify(RTM_DELADDR, ifa);
 			inet6addr_notifier_call_chain(NETDEV_DOWN, ifa);
+		} else {
+			if (idev->cnf.forwarding)
+				addrconf_leave_anycast(ifa);
+			addrconf_leave_solict(ifa->idev, &ifa->addr);
 		}
 
 		write_lock_bh(&idev->lock);
-- 
2.1.0


>From e1d101289eddb944d1b55d05443f26ca7df1e5fa Mon Sep 17 00:00:00 2001
From: Vegard Nossum <vegard.nossum@oracle.com>
Date: Sat, 23 Jul 2016 07:43:50 +0200
Subject: [PATCH 10/13] net/irda: fix NULL pointer dereference on memory
 allocation failure

[ Upstream commit d3e6952cfb7ba5f4bfa29d4803ba91f96ce1204d ]

I ran into this:

    kasan: CONFIG_KASAN_INLINE enabled
    kasan: GPF could be caused by NULL-ptr deref or user memory access
    general protection fault: 0000 [#1] PREEMPT SMP KASAN
    CPU: 2 PID: 2012 Comm: trinity-c3 Not tainted 4.7.0-rc7+ #19
    Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014
    task: ffff8800b745f2c0 ti: ffff880111740000 task.ti: ffff880111740000
    RIP: 0010:[<ffffffff82bbf066>]  [<ffffffff82bbf066>] irttp_connect_request+0x36/0x710
    RSP: 0018:ffff880111747bb8  EFLAGS: 00010286
    RAX: dffffc0000000000 RBX: 0000000000000000 RCX: 0000000069dd8358
    RDX: 0000000000000009 RSI: 0000000000000027 RDI: 0000000000000048
    RBP: ffff880111747c00 R08: 0000000000000000 R09: 0000000000000000
    R10: 0000000069dd8358 R11: 1ffffffff0759723 R12: 0000000000000000
    R13: ffff88011a7e4780 R14: 0000000000000027 R15: 0000000000000000
    FS:  00007fc738404700(0000) GS:ffff88011af00000(0000) knlGS:0000000000000000
    CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
    CR2: 00007fc737fdfb10 CR3: 0000000118087000 CR4: 00000000000006e0
    Stack:
     0000000000000200 ffff880111747bd8 ffffffff810ee611 ffff880119f1f220
     ffff880119f1f4f8 ffff880119f1f4f0 ffff88011a7e4780 ffff880119f1f232
     ffff880119f1f220 ffff880111747d58 ffffffff82bca542 0000000000000000
    Call Trace:
     [<ffffffff82bca542>] irda_connect+0x562/0x1190
     [<ffffffff825ae582>] SYSC_connect+0x202/0x2a0
     [<ffffffff825b4489>] SyS_connect+0x9/0x10
     [<ffffffff8100334c>] do_syscall_64+0x19c/0x410
     [<ffffffff83295ca5>] entry_SYSCALL64_slow_path+0x25/0x25
    Code: 41 89 ca 48 89 e5 41 57 41 56 41 55 41 54 41 89 d7 53 48 89 fb 48 83 c7 48 48 89 fa 41 89 f6 48 c1 ea 03 48 83 ec 20 4c 8b 65 10 <0f> b6 04 02 84 c0 74 08 84 c0 0f 8e 4c 04 00 00 80 7b 48 00 74
    RIP  [<ffffffff82bbf066>] irttp_connect_request+0x36/0x710
     RSP <ffff880111747bb8>
    ---[ end trace 4cda2588bc055b30 ]---

The problem is that irda_open_tsap() can fail and leave self->tsap = NULL,
and then irttp_connect_request() almost immediately dereferences it.

Cc: stable@vger.kernel.org
Signed-off-by: Vegard Nossum <vegard.nossum@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/irda/af_irda.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index 923abd6..8d2f7c9 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -1024,8 +1024,11 @@ static int irda_connect(struct socket *sock, struct sockaddr *uaddr,
 	}
 
 	/* Check if we have opened a local TSAP */
-	if (!self->tsap)
-		irda_open_tsap(self, LSAP_ANY, addr->sir_name);
+	if (!self->tsap) {
+		err = irda_open_tsap(self, LSAP_ANY, addr->sir_name);
+		if (err)
+			goto out;
+	}
 
 	/* Move to connecting socket, start sending Connect Requests */
 	sock->state = SS_CONNECTING;
-- 
2.1.0


>From 815358664017fe5df6143e3e6431e7cb81776e08 Mon Sep 17 00:00:00 2001
From: Manish Chopra <manish.chopra@qlogic.com>
Date: Mon, 25 Jul 2016 19:07:46 +0300
Subject: [PATCH 11/13] qed: Fix setting/clearing bit in completion bitmap

[ Upstream commit 59d3f1ceb69b54569685d0c34dff16a1e0816b19 ]

Slowpath completion handling is incorrectly changing
SPQ_RING_SIZE bits instead of a single one.

Fixes: 76a9a3642a0b ("qed: fix handling of concurrent ramrods")
Signed-off-by: Manish Chopra <manish.chopra@qlogic.com>
Signed-off-by: Yuval Mintz <Yuval.Mintz@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_spq.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c
index 89469d5..40e6f6c 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_spq.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c
@@ -791,13 +791,12 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn,
 			 * in a bitmap and increasing the chain consumer only
 			 * for the first successive completed entries.
 			 */
-			bitmap_set(p_spq->p_comp_bitmap, pos, SPQ_RING_SIZE);
+			__set_bit(pos, p_spq->p_comp_bitmap);
 
 			while (test_bit(p_spq->comp_bitmap_idx,
 					p_spq->p_comp_bitmap)) {
-				bitmap_clear(p_spq->p_comp_bitmap,
-					     p_spq->comp_bitmap_idx,
-					     SPQ_RING_SIZE);
+				__clear_bit(p_spq->comp_bitmap_idx,
+					    p_spq->p_comp_bitmap);
 				p_spq->comp_bitmap_idx++;
 				qed_chain_return_produced(&p_spq->chain);
 			}
-- 
2.1.0


>From 7c8329ff8570b38edcd61066b2032cf4e4edab24 Mon Sep 17 00:00:00 2001
From: Beniamino Galvani <bgalvani@redhat.com>
Date: Tue, 26 Jul 2016 12:24:53 +0200
Subject: [PATCH 12/13] macsec: ensure rx_sa is set when validation is disabled

[ Upstream commit e3a3b626010a14fe067f163c2c43409d5afcd2a9 ]

macsec_decrypt() is not called when validation is disabled and so
macsec_skb_cb(skb)->rx_sa is not set; but it is used later in
macsec_post_decrypt(), ensure that it's always initialized.

Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver")
Signed-off-by: Beniamino Galvani <bgalvani@redhat.com>
Acked-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macsec.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 8f3c55d..f58858b 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -914,7 +914,6 @@ static struct sk_buff *macsec_decrypt(struct sk_buff *skb,
 	}
 
 	macsec_skb_cb(skb)->req = req;
-	macsec_skb_cb(skb)->rx_sa = rx_sa;
 	skb->dev = dev;
 	aead_request_set_callback(req, 0, macsec_decrypt_done, skb);
 
@@ -1141,6 +1140,8 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb)
 		}
 	}
 
+	macsec_skb_cb(skb)->rx_sa = rx_sa;
+
 	/* Disabled && !changed text => skip validation */
 	if (hdr->tci_an & MACSEC_TCI_C ||
 	    secy->validate_frames != MACSEC_VALIDATE_DISABLED)
-- 
2.1.0


>From a9dcbd02cba7ef6c20f8555edcb0b9b55469924c Mon Sep 17 00:00:00 2001
From: Soheil Hassas Yeganeh <soheil@google.com>
Date: Fri, 29 Jul 2016 09:34:02 -0400
Subject: [PATCH 13/13] tcp: consider recv buf for the initial window scale

[ Upstream commit f626300a3e776ccc9671b0dd94698fb3aa315966 ]

tcp_select_initial_window() intends to advertise a window
scaling for the maximum possible window size. To do so,
it considers the maximum of net.ipv4.tcp_rmem[2] and
net.core.rmem_max as the only possible upper-bounds.
However, users with CAP_NET_ADMIN can use SO_RCVBUFFORCE
to set the socket's receive buffer size to values
larger than net.ipv4.tcp_rmem[2] and net.core.rmem_max.
Thus, SO_RCVBUFFORCE is effectively ignored by
tcp_select_initial_window().

To fix this, consider the maximum of net.ipv4.tcp_rmem[2],
net.core.rmem_max and socket's initial buffer space.

Fixes: b0573dea1fb3 ("[NET]: Introduce SO_{SND,RCV}BUFFORCE socket options")
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Suggested-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 79a03b8..7b8e903 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -236,7 +236,8 @@ void tcp_select_initial_window(int __space, __u32 mss,
 		/* Set window scaling on max possible window
 		 * See RFC1323 for an explanation of the limit to 14
 		 */
-		space = max_t(u32, sysctl_tcp_rmem[2], sysctl_rmem_max);
+		space = max_t(u32, space, sysctl_tcp_rmem[2]);
+		space = max_t(u32, space, sysctl_rmem_max);
 		space = min_t(u32, space, *window_clamp);
 		while (space > 65535 && (*rcv_wscale) < 14) {
 			space >>= 1;
-- 
2.1.0


[-- Attachment #4: net_47.mbox --]
[-- Type: Text/Plain, Size: 24179 bytes --]

>From feff53ceeb01f37c4298612e1c84fcdfb4dcd99f Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Mon, 25 Jul 2016 18:06:12 +0200
Subject: [PATCH 01/10] udp: use sk_filter_trim_cap for udp{,6}_queue_rcv_skb

[ Upstream commit ba66bbe5480a012108958a71cff88b23dce84956 ]

After a612769774a3 ("udp: prevent bugcheck if filter truncates packet
too much"), there followed various other fixes for similar cases such
as f4979fcea7fd ("rose: limit sk_filter trim to payload").

Latter introduced a new helper sk_filter_trim_cap(), where we can pass
the trim limit directly to the socket filter handling. Make use of it
here as well with sizeof(struct udphdr) as lower cap limit and drop the
extra skb->len test in UDP's input path.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Willem de Bruijn <willemb@google.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 4 +---
 net/ipv6/udp.c | 4 +---
 2 files changed, 2 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 4aed8fc..e61f7cd 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1581,9 +1581,7 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	    udp_lib_checksum_complete(skb))
 			goto csum_error;
 
-	if (sk_filter(sk, skb))
-		goto drop;
-	if (unlikely(skb->len < sizeof(struct udphdr)))
+	if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr)))
 		goto drop;
 
 	udp_csum_pull_header(skb);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index acc09705..42a2edf 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -618,9 +618,7 @@ int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	    udp_lib_checksum_complete(skb))
 		goto csum_error;
 
-	if (sk_filter(sk, skb))
-		goto drop;
-	if (unlikely(skb->len < sizeof(struct udphdr)))
+	if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr)))
 		goto drop;
 
 	udp_csum_pull_header(skb);
-- 
2.1.0


>From f8561e442d29f3a00ab657c275f1bc68c9dab6bb Mon Sep 17 00:00:00 2001
From: Mark Bloch <markb@mellanox.com>
Date: Thu, 21 Jul 2016 11:52:55 +0300
Subject: [PATCH 02/10] net/bonding: Enforce active-backup policy for IPoIB
 bonds

[ Upstream commit 1533e77315220dc1d5ec3bd6d9fe32e2aa0a74c0 ]

When using an IPoIB bond currently only active-backup mode is a valid
use case and this commit strengthens it.

Since commit 2ab82852a270 ("net/bonding: Enable bonding to enslave
netdevices not supporting set_mac_address()") was introduced till
4.7-rc1, IPoIB didn't support the set_mac_address ndo, and hence the
fail over mac policy always applied to IPoIB bonds.

With the introduction of commit 492a7e67ff83 ("IB/IPoIB: Allow setting
the device address"), that doesn't hold and practically IPoIB bonds are
broken as of that. To fix it, lets go to fail over mac if the device
doesn't support the ndo OR this is IPoIB device.

As a by-product, this commit also prevents a stack corruption which
occurred when trying to copy 20 bytes (IPoIB) device address
to a sockaddr struct that has only 16 bytes of storage.

Signed-off-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Acked-by: Andy Gospodarek <gospo@cumulusnetworks.com>
Signed-off-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index a2afa3b..4d79819 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1422,7 +1422,16 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 		return -EINVAL;
 	}
 
-	if (slave_ops->ndo_set_mac_address == NULL) {
+	if (slave_dev->type == ARPHRD_INFINIBAND &&
+	    BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
+		netdev_warn(bond_dev, "Type (%d) supports only active-backup mode\n",
+			    slave_dev->type);
+		res = -EOPNOTSUPP;
+		goto err_undo_flags;
+	}
+
+	if (!slave_ops->ndo_set_mac_address ||
+	    slave_dev->type == ARPHRD_INFINIBAND) {
 		netdev_warn(bond_dev, "The slave device specified does not support setting the MAC address\n");
 		if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP &&
 		    bond->params.fail_over_mac != BOND_FOM_ACTIVE) {
-- 
2.1.0


>From f0e152b3f0b9ab321d69ccc7359eb7371be1d163 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Fri, 22 Jul 2016 14:56:20 +0300
Subject: [PATCH 03/10] bridge: Fix incorrect re-injection of LLDP packets

[ Upstream commit baedbe55884c003819f5c8c063ec3d2569414296 ]

Commit 8626c56c8279 ("bridge: fix potential use-after-free when hook
returns QUEUE or STOLEN verdict") caused LLDP packets arriving through a
bridge port to be re-injected to the Rx path with skb->dev set to the
bridge device, but this breaks the lldpad daemon.

The lldpad daemon opens a packet socket with protocol set to ETH_P_LLDP
for any valid device on the system, which doesn't not include soft
devices such as bridge and VLAN.

Since packet sockets (ptype_base) are processed in the Rx path after the
Rx handler, LLDP packets with skb->dev set to the bridge device never
reach the lldpad daemon.

Fix this by making the bridge's Rx handler re-inject LLDP packets with
RX_HANDLER_PASS, which effectively restores the behaviour prior to the
mentioned commit.

This means netfilter will never receive LLDP packets coming through a
bridge port, as I don't see a way in which we can have okfn() consume
the packet without breaking existing behaviour. I've already carried out
a similar fix for STP packets in commit 56fae404fb2c ("bridge: Fix
incorrect re-injection of STP packets").

Fixes: 8626c56c8279 ("bridge: fix potential use-after-free when hook returns QUEUE or STOLEN verdict")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Cc: Florian Westphal <fw@strlen.de>
Cc: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_input.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 43d2cd8..28d5ec2 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -288,6 +288,14 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
 		case 0x01:	/* IEEE MAC (Pause) */
 			goto drop;
 
+		case 0x0E:	/* 802.1AB LLDP */
+			fwd_mask |= p->br->group_fwd_mask;
+			if (fwd_mask & (1u << dest[5]))
+				goto forward;
+			*pskb = skb;
+			__br_handle_local_finish(skb);
+			return RX_HANDLER_PASS;
+
 		default:
 			/* Allow selective forwarding for most other protocols */
 			fwd_mask |= p->br->group_fwd_mask;
-- 
2.1.0


>From 0993829fe12ff067e16673660be2f799e1f842ae Mon Sep 17 00:00:00 2001
From: Mike Manning <mmanning@brocade.com>
Date: Fri, 22 Jul 2016 18:32:11 +0100
Subject: [PATCH 04/10] net: ipv6: Always leave anycast and multicast groups on
 link down

[ Upstream commit ea06f7176413e2538d13bb85b65387d0917943d9 ]

Default kernel behavior is to delete IPv6 addresses on link
down, which entails deletion of the multicast and the
subnet-router anycast addresses. These deletions do not
happen with sysctl setting to keep global IPv6 addresses on
link down, so every link down/up causes an increment of the
anycast and multicast refcounts. These bogus refcounts may
stop these addrs from being removed on subsequent calls to
delete them. The solution is to leave the groups for the
multicast and subnet anycast on link down for the callflow
when global IPv6 addresses are kept.

Fixes: f1705ec197e7 ("net: ipv6: Make address flushing on ifdown optional")
Signed-off-by: Mike Manning <mmanning@brocade.com>
Acked-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 47f837a..047c75a 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3562,6 +3562,10 @@ restart:
 		if (state != INET6_IFADDR_STATE_DEAD) {
 			__ipv6_ifa_notify(RTM_DELADDR, ifa);
 			inet6addr_notifier_call_chain(NETDEV_DOWN, ifa);
+		} else {
+			if (idev->cnf.forwarding)
+				addrconf_leave_anycast(ifa);
+			addrconf_leave_solict(ifa->idev, &ifa->addr);
 		}
 
 		write_lock_bh(&idev->lock);
-- 
2.1.0


>From 9809c8e278461bc4367e6b09018cfcf87943efe0 Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Sat, 23 Jul 2016 00:32:48 -0300
Subject: [PATCH 05/10] sctp: fix BH handling on socket backlog

[ Upstream commit eefc1b1d105ee4d2ce907833ce675f1e9599b5e3 ]

Now that the backlog processing is called with BH enabled, we have to
disable BH before taking the socket lock via bh_lock_sock() otherwise
it may dead lock:

sctp_backlog_rcv()
                bh_lock_sock(sk);

                if (sock_owned_by_user(sk)) {
                        if (sk_add_backlog(sk, skb, sk->sk_rcvbuf))
                                sctp_chunk_free(chunk);
                        else
                                backloged = 1;
                } else
                        sctp_inq_push(inqueue, chunk);

                bh_unlock_sock(sk);

while sctp_inq_push() was disabling/enabling BH, but enabling BH
triggers pending softirq, which then may try to re-lock the socket in
sctp_rcv().

[  219.187215]  <IRQ>
[  219.187217]  [<ffffffff817ca3e0>] _raw_spin_lock+0x20/0x30
[  219.187223]  [<ffffffffa041888c>] sctp_rcv+0x48c/0xba0 [sctp]
[  219.187225]  [<ffffffff816e7db2>] ? nf_iterate+0x62/0x80
[  219.187226]  [<ffffffff816f1b14>] ip_local_deliver_finish+0x94/0x1e0
[  219.187228]  [<ffffffff816f1e1f>] ip_local_deliver+0x6f/0xf0
[  219.187229]  [<ffffffff816f1a80>] ? ip_rcv_finish+0x3b0/0x3b0
[  219.187230]  [<ffffffff816f17a8>] ip_rcv_finish+0xd8/0x3b0
[  219.187232]  [<ffffffff816f2122>] ip_rcv+0x282/0x3a0
[  219.187233]  [<ffffffff810d8bb6>] ? update_curr+0x66/0x180
[  219.187235]  [<ffffffff816abac4>] __netif_receive_skb_core+0x524/0xa90
[  219.187236]  [<ffffffff810d8e00>] ? update_cfs_shares+0x30/0xf0
[  219.187237]  [<ffffffff810d557c>] ? __enqueue_entity+0x6c/0x70
[  219.187239]  [<ffffffff810dc454>] ? enqueue_entity+0x204/0xdf0
[  219.187240]  [<ffffffff816ac048>] __netif_receive_skb+0x18/0x60
[  219.187242]  [<ffffffff816ad1ce>] process_backlog+0x9e/0x140
[  219.187243]  [<ffffffff816ac8ec>] net_rx_action+0x22c/0x370
[  219.187245]  [<ffffffff817cd352>] __do_softirq+0x112/0x2e7
[  219.187247]  [<ffffffff817cc3bc>] do_softirq_own_stack+0x1c/0x30
[  219.187247]  <EOI>
[  219.187248]  [<ffffffff810aa1c8>] do_softirq.part.14+0x38/0x40
[  219.187249]  [<ffffffff810aa24d>] __local_bh_enable_ip+0x7d/0x80
[  219.187254]  [<ffffffffa0408428>] sctp_inq_push+0x68/0x80 [sctp]
[  219.187258]  [<ffffffffa04190f1>] sctp_backlog_rcv+0x151/0x1c0 [sctp]
[  219.187260]  [<ffffffff81692b07>] __release_sock+0x87/0xf0
[  219.187261]  [<ffffffff81692ba0>] release_sock+0x30/0xa0
[  219.187265]  [<ffffffffa040e46d>] sctp_accept+0x17d/0x210 [sctp]
[  219.187266]  [<ffffffff810e7510>] ? prepare_to_wait_event+0xf0/0xf0
[  219.187268]  [<ffffffff8172d52c>] inet_accept+0x3c/0x130
[  219.187269]  [<ffffffff8168d7a3>] SYSC_accept4+0x103/0x210
[  219.187271]  [<ffffffff817ca2ba>] ? _raw_spin_unlock_bh+0x1a/0x20
[  219.187272]  [<ffffffff81692bfc>] ? release_sock+0x8c/0xa0
[  219.187276]  [<ffffffffa0413e22>] ? sctp_inet_listen+0x62/0x1b0 [sctp]
[  219.187277]  [<ffffffff8168f2d0>] SyS_accept+0x10/0x20

Fixes: 860fbbc343bf ("sctp: prepare for socket backlog behavior change")
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/input.c   | 2 ++
 net/sctp/inqueue.c | 2 --
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sctp/input.c b/net/sctp/input.c
index 47cf460..f093322 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -328,6 +328,7 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb)
 		 */
 
 		sk = rcvr->sk;
+		local_bh_disable();
 		bh_lock_sock(sk);
 
 		if (sock_owned_by_user(sk)) {
@@ -339,6 +340,7 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb)
 			sctp_inq_push(inqueue, chunk);
 
 		bh_unlock_sock(sk);
+		local_bh_enable();
 
 		/* If the chunk was backloged again, don't drop refs */
 		if (backloged)
diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c
index 9d87bba..b335ffc 100644
--- a/net/sctp/inqueue.c
+++ b/net/sctp/inqueue.c
@@ -89,12 +89,10 @@ void sctp_inq_push(struct sctp_inq *q, struct sctp_chunk *chunk)
 	 * Eventually, we should clean up inqueue to not rely
 	 * on the BH related data structures.
 	 */
-	local_bh_disable();
 	list_add_tail(&chunk->list, &q->in_chunk_list);
 	if (chunk->asoc)
 		chunk->asoc->stats.ipackets++;
 	q->immediate.func(&q->immediate);
-	local_bh_enable();
 }
 
 /* Peek at the next chunk on the inqeue. */
-- 
2.1.0


>From 4e76e1c6648ac314ba982866a292dccbf93cab6c Mon Sep 17 00:00:00 2001
From: Vegard Nossum <vegard.nossum@oracle.com>
Date: Sat, 23 Jul 2016 07:43:50 +0200
Subject: [PATCH 06/10] net/irda: fix NULL pointer dereference on memory
 allocation failure

[ Upstream commit d3e6952cfb7ba5f4bfa29d4803ba91f96ce1204d ]

I ran into this:

    kasan: CONFIG_KASAN_INLINE enabled
    kasan: GPF could be caused by NULL-ptr deref or user memory access
    general protection fault: 0000 [#1] PREEMPT SMP KASAN
    CPU: 2 PID: 2012 Comm: trinity-c3 Not tainted 4.7.0-rc7+ #19
    Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014
    task: ffff8800b745f2c0 ti: ffff880111740000 task.ti: ffff880111740000
    RIP: 0010:[<ffffffff82bbf066>]  [<ffffffff82bbf066>] irttp_connect_request+0x36/0x710
    RSP: 0018:ffff880111747bb8  EFLAGS: 00010286
    RAX: dffffc0000000000 RBX: 0000000000000000 RCX: 0000000069dd8358
    RDX: 0000000000000009 RSI: 0000000000000027 RDI: 0000000000000048
    RBP: ffff880111747c00 R08: 0000000000000000 R09: 0000000000000000
    R10: 0000000069dd8358 R11: 1ffffffff0759723 R12: 0000000000000000
    R13: ffff88011a7e4780 R14: 0000000000000027 R15: 0000000000000000
    FS:  00007fc738404700(0000) GS:ffff88011af00000(0000) knlGS:0000000000000000
    CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
    CR2: 00007fc737fdfb10 CR3: 0000000118087000 CR4: 00000000000006e0
    Stack:
     0000000000000200 ffff880111747bd8 ffffffff810ee611 ffff880119f1f220
     ffff880119f1f4f8 ffff880119f1f4f0 ffff88011a7e4780 ffff880119f1f232
     ffff880119f1f220 ffff880111747d58 ffffffff82bca542 0000000000000000
    Call Trace:
     [<ffffffff82bca542>] irda_connect+0x562/0x1190
     [<ffffffff825ae582>] SYSC_connect+0x202/0x2a0
     [<ffffffff825b4489>] SyS_connect+0x9/0x10
     [<ffffffff8100334c>] do_syscall_64+0x19c/0x410
     [<ffffffff83295ca5>] entry_SYSCALL64_slow_path+0x25/0x25
    Code: 41 89 ca 48 89 e5 41 57 41 56 41 55 41 54 41 89 d7 53 48 89 fb 48 83 c7 48 48 89 fa 41 89 f6 48 c1 ea 03 48 83 ec 20 4c 8b 65 10 <0f> b6 04 02 84 c0 74 08 84 c0 0f 8e 4c 04 00 00 80 7b 48 00 74
    RIP  [<ffffffff82bbf066>] irttp_connect_request+0x36/0x710
     RSP <ffff880111747bb8>
    ---[ end trace 4cda2588bc055b30 ]---

The problem is that irda_open_tsap() can fail and leave self->tsap = NULL,
and then irttp_connect_request() almost immediately dereferences it.

Cc: stable@vger.kernel.org
Signed-off-by: Vegard Nossum <vegard.nossum@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/irda/af_irda.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index 923abd6..8d2f7c9 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -1024,8 +1024,11 @@ static int irda_connect(struct socket *sock, struct sockaddr *uaddr,
 	}
 
 	/* Check if we have opened a local TSAP */
-	if (!self->tsap)
-		irda_open_tsap(self, LSAP_ANY, addr->sir_name);
+	if (!self->tsap) {
+		err = irda_open_tsap(self, LSAP_ANY, addr->sir_name);
+		if (err)
+			goto out;
+	}
 
 	/* Move to connecting socket, start sending Connect Requests */
 	sock->state = SS_CONNECTING;
-- 
2.1.0


>From 716cc6f0afc29f7f5f1dccb8ac4ff6b08b83f425 Mon Sep 17 00:00:00 2001
From: Vegard Nossum <vegard.nossum@oracle.com>
Date: Sat, 23 Jul 2016 09:42:35 +0200
Subject: [PATCH 07/10] net/sctp: terminate rhashtable walk correctly

[ Upstream commit 5fc382d87517707ad77ea4c9c12e2a3fde2c838a ]

I was seeing a lot of these:

    BUG: sleeping function called from invalid context at mm/slab.h:388
    in_atomic(): 0, irqs_disabled(): 0, pid: 14971, name: trinity-c2
    Preemption disabled at:[<ffffffff819bcd46>] rhashtable_walk_start+0x46/0x150

     [<ffffffff81149abb>] preempt_count_add+0x1fb/0x280
     [<ffffffff83295722>] _raw_spin_lock+0x12/0x40
     [<ffffffff811aac87>] console_unlock+0x2f7/0x930
     [<ffffffff811ab5bb>] vprintk_emit+0x2fb/0x520
     [<ffffffff811aba6a>] vprintk_default+0x1a/0x20
     [<ffffffff812c171a>] printk+0x94/0xb0
     [<ffffffff811d6ed0>] print_stack_trace+0xe0/0x170
     [<ffffffff8115835e>] ___might_sleep+0x3be/0x460
     [<ffffffff81158490>] __might_sleep+0x90/0x1a0
     [<ffffffff8139b823>] kmem_cache_alloc+0x153/0x1e0
     [<ffffffff819bca1e>] rhashtable_walk_init+0xfe/0x2d0
     [<ffffffff82ec64de>] sctp_transport_walk_start+0x1e/0x60
     [<ffffffff82edd8ad>] sctp_transport_seq_start+0x4d/0x150
     [<ffffffff8143a82b>] seq_read+0x27b/0x1180
     [<ffffffff814f97fc>] proc_reg_read+0xbc/0x180
     [<ffffffff813d471b>] __vfs_read+0xdb/0x610
     [<ffffffff813d4d3a>] vfs_read+0xea/0x2d0
     [<ffffffff813d615b>] SyS_pread64+0x11b/0x150
     [<ffffffff8100334c>] do_syscall_64+0x19c/0x410
     [<ffffffff832960a5>] return_from_SYSCALL_64+0x0/0x6a
     [<ffffffffffffffff>] 0xffffffffffffffff

Apparently we always need to call rhashtable_walk_stop(), even when
rhashtable_walk_start() fails:

 * rhashtable_walk_start - Start a hash table walk
 * @iter:       Hash table iterator
 *
 * Start a hash table walk.  Note that we take the RCU lock in all
 * cases including when we return an error.  So you must always call
 * rhashtable_walk_stop to clean up.

otherwise we never call rcu_read_unlock() and we get the splat above.

Fixes: 53fa1036 ("sctp: fix some rhashtable functions using in sctp proc/diag")
See-also: 53fa1036 ("sctp: fix some rhashtable functions using in sctp proc/diag")
See-also: f2dba9c6 ("rhashtable: Introduce rhashtable_walk_*")
Cc: Xin Long <lucien.xin@gmail.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: stable@vger.kernel.org
Signed-off-by: Vegard Nossum <vegard.nossum@oracle.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 67154b8..7f5689a 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4301,6 +4301,7 @@ int sctp_transport_walk_start(struct rhashtable_iter *iter)
 
 	err = rhashtable_walk_start(iter);
 	if (err && err != -EAGAIN) {
+		rhashtable_walk_stop(iter);
 		rhashtable_walk_exit(iter);
 		return err;
 	}
-- 
2.1.0


>From a1dc5a3ce16bab0f568cbb0a68bc68da63a664ef Mon Sep 17 00:00:00 2001
From: Manish Chopra <manish.chopra@qlogic.com>
Date: Mon, 25 Jul 2016 19:07:46 +0300
Subject: [PATCH 08/10] qed: Fix setting/clearing bit in completion bitmap

[ Upstream commit 59d3f1ceb69b54569685d0c34dff16a1e0816b19 ]

Slowpath completion handling is incorrectly changing
SPQ_RING_SIZE bits instead of a single one.

Fixes: 76a9a3642a0b ("qed: fix handling of concurrent ramrods")
Signed-off-by: Manish Chopra <manish.chopra@qlogic.com>
Signed-off-by: Yuval Mintz <Yuval.Mintz@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_spq.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c
index b122f60..03601df 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_spq.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c
@@ -809,13 +809,12 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn,
 			 * in a bitmap and increasing the chain consumer only
 			 * for the first successive completed entries.
 			 */
-			bitmap_set(p_spq->p_comp_bitmap, pos, SPQ_RING_SIZE);
+			__set_bit(pos, p_spq->p_comp_bitmap);
 
 			while (test_bit(p_spq->comp_bitmap_idx,
 					p_spq->p_comp_bitmap)) {
-				bitmap_clear(p_spq->p_comp_bitmap,
-					     p_spq->comp_bitmap_idx,
-					     SPQ_RING_SIZE);
+				__clear_bit(p_spq->comp_bitmap_idx,
+					    p_spq->p_comp_bitmap);
 				p_spq->comp_bitmap_idx++;
 				qed_chain_return_produced(&p_spq->chain);
 			}
-- 
2.1.0


>From d7d53adcacbbbe2a3f6bfb4d6ea6a482e028d495 Mon Sep 17 00:00:00 2001
From: Beniamino Galvani <bgalvani@redhat.com>
Date: Tue, 26 Jul 2016 12:24:53 +0200
Subject: [PATCH 09/10] macsec: ensure rx_sa is set when validation is disabled

[ Upstream commit e3a3b626010a14fe067f163c2c43409d5afcd2a9 ]

macsec_decrypt() is not called when validation is disabled and so
macsec_skb_cb(skb)->rx_sa is not set; but it is used later in
macsec_post_decrypt(), ensure that it's always initialized.

Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver")
Signed-off-by: Beniamino Galvani <bgalvani@redhat.com>
Acked-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macsec.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 8bcd78f..a70b6c4 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -942,7 +942,6 @@ static struct sk_buff *macsec_decrypt(struct sk_buff *skb,
 	}
 
 	macsec_skb_cb(skb)->req = req;
-	macsec_skb_cb(skb)->rx_sa = rx_sa;
 	skb->dev = dev;
 	aead_request_set_callback(req, 0, macsec_decrypt_done, skb);
 
@@ -1169,6 +1168,8 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb)
 		}
 	}
 
+	macsec_skb_cb(skb)->rx_sa = rx_sa;
+
 	/* Disabled && !changed text => skip validation */
 	if (hdr->tci_an & MACSEC_TCI_C ||
 	    secy->validate_frames != MACSEC_VALIDATE_DISABLED)
-- 
2.1.0


>From fc4814047308a5d3beb2f6284ed7cfb73c032e9d Mon Sep 17 00:00:00 2001
From: Soheil Hassas Yeganeh <soheil@google.com>
Date: Fri, 29 Jul 2016 09:34:02 -0400
Subject: [PATCH 10/10] tcp: consider recv buf for the initial window scale

[ Upstream commit f626300a3e776ccc9671b0dd94698fb3aa315966 ]

tcp_select_initial_window() intends to advertise a window
scaling for the maximum possible window size. To do so,
it considers the maximum of net.ipv4.tcp_rmem[2] and
net.core.rmem_max as the only possible upper-bounds.
However, users with CAP_NET_ADMIN can use SO_RCVBUFFORCE
to set the socket's receive buffer size to values
larger than net.ipv4.tcp_rmem[2] and net.core.rmem_max.
Thus, SO_RCVBUFFORCE is effectively ignored by
tcp_select_initial_window().

To fix this, consider the maximum of net.ipv4.tcp_rmem[2],
net.core.rmem_max and socket's initial buffer space.

Fixes: b0573dea1fb3 ("[NET]: Introduce SO_{SND,RCV}BUFFORCE socket options")
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Suggested-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index e00e972..700b72c 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -236,7 +236,8 @@ void tcp_select_initial_window(int __space, __u32 mss,
 		/* Set window scaling on max possible window
 		 * See RFC1323 for an explanation of the limit to 14
 		 */
-		space = max_t(u32, sysctl_tcp_rmem[2], sysctl_rmem_max);
+		space = max_t(u32, space, sysctl_tcp_rmem[2]);
+		space = max_t(u32, space, sysctl_rmem_max);
 		space = min_t(u32, space, *window_clamp);
 		while (space > 65535 && (*rcv_wscale) < 14) {
 			space >>= 1;
-- 
2.1.0

Re: [PATCHES] Networking

[Greg KH]

On Thu, Aug 11, 2016 at 05:50:41PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for 4.4.x, 4.6.x,
> and 4.7.x -stable, respectively.
> 
> Thanks!


Thanks so much for these, all now applied.

Note, this will be the last 4.6.x kernel released, so no need to do any
more patches for that release, unless something really serious comes
along.

thanks,

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 79 bytes --]


Please queue up the following networking bug fixes for v4.7 -stable.

Thanks!

[-- Attachment #2: net_47.mbox --]
[-- Type: Text/Plain, Size: 104586 bytes --]

From ac464d5c964037be50735da8c2626f99992d6997 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 2 Aug 2016 16:12:14 +0100
Subject: [PATCH 01/31] bpf: fix method of PTR_TO_PACKET reg id generation

[ Upstream commit 1f415a74b0ca64b5bfacbb12d71ed2ec050a8cfb ]

Using per-register incrementing ID can lead to
find_good_pkt_pointers() confusing registers which
have completely different values.  Consider example:

0: (bf) r6 = r1
1: (61) r8 = *(u32 *)(r6 +76)
2: (61) r0 = *(u32 *)(r6 +80)
3: (bf) r7 = r8
4: (07) r8 += 32
5: (2d) if r8 > r0 goto pc+9
 R0=pkt_end R1=ctx R6=ctx R7=pkt(id=0,off=0,r=32) R8=pkt(id=0,off=32,r=32) R10=fp
6: (bf) r8 = r7
7: (bf) r9 = r7
8: (71) r1 = *(u8 *)(r7 +0)
9: (0f) r8 += r1
10: (71) r1 = *(u8 *)(r7 +1)
11: (0f) r9 += r1
12: (07) r8 += 32
13: (2d) if r8 > r0 goto pc+1
 R0=pkt_end R1=inv56 R6=ctx R7=pkt(id=0,off=0,r=32) R8=pkt(id=1,off=32,r=32) R9=pkt(id=1,off=0,r=32) R10=fp
14: (71) r1 = *(u8 *)(r9 +16)
15: (b7) r7 = 0
16: (bf) r0 = r7
17: (95) exit

We need to get a UNKNOWN_VALUE with imm to force id
generation so lines 0-5 make r7 a valid packet pointer.
We then read two different bytes from the packet and
add them to copies of the constructed packet pointer.
r8 (line 9) and r9 (line 11) will get the same id of 1,
independently.  When either of them is validated (line
13) - find_good_pkt_pointers() will also mark the other
as safe.  This leads to access on line 14 being mistakenly
considered safe.

Fixes: 969bf05eb3ce ("bpf: direct packet access")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index eec9f90..6d011c6 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -194,6 +194,7 @@ struct verifier_env {
 	struct verifier_state_list **explored_states; /* search pruning optimization */
 	struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */
 	u32 used_map_cnt;		/* number of used maps */
+	u32 id_gen;			/* used to generate unique reg IDs */
 	bool allow_ptr_leaks;
 };
 
@@ -1277,7 +1278,7 @@ add_imm:
 		/* dst_reg stays as pkt_ptr type and since some positive
 		 * integer value was added to the pointer, increment its 'id'
 		 */
-		dst_reg->id++;
+		dst_reg->id = ++env->id_gen;
 
 		/* something was added to pkt_ptr, set range and off to zero */
 		dst_reg->off = 0;
-- 
2.1.0


From 586e42298b0b4f821b45e4e86df567ed4cd67578 Mon Sep 17 00:00:00 2001
From: David Forster <dforster@brocade.com>
Date: Wed, 3 Aug 2016 15:13:01 +0100
Subject: [PATCH 02/31] ipv4: panic in leaf_walk_rcu due to stale node pointer

[ Upstream commit 94d9f1c5906b20053efe375b6d66610bca4b8b64 ]

Panic occurs when issuing "cat /proc/net/route" whilst
populating FIB with > 1M routes.

Use of cached node pointer in fib_route_get_idx is unsafe.

 BUG: unable to handle kernel paging request at ffffc90001630024
 IP: [<ffffffff814cf6a0>] leaf_walk_rcu+0x10/0xe0
 PGD 11b08d067 PUD 11b08e067 PMD dac4b067 PTE 0
 Oops: 0000 [#1] SMP
 Modules linked in: nfsd auth_rpcgss oid_registry nfs_acl nfs lockd grace fscac
 snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hda_core snd_hwdep virti
 acpi_cpufreq button parport_pc ppdev lp parport autofs4 ext4 crc16 mbcache jbd
tio_ring virtio floppy uhci_hcd ehci_hcd usbcore usb_common libata scsi_mod
 CPU: 1 PID: 785 Comm: cat Not tainted 4.2.0-rc8+ #4
 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2007
 task: ffff8800da1c0bc0 ti: ffff88011a05c000 task.ti: ffff88011a05c000
 RIP: 0010:[<ffffffff814cf6a0>]  [<ffffffff814cf6a0>] leaf_walk_rcu+0x10/0xe0
 RSP: 0018:ffff88011a05fda0  EFLAGS: 00010202
 RAX: ffff8800d8a40c00 RBX: ffff8800da4af940 RCX: ffff88011a05ff20
 RDX: ffffc90001630020 RSI: 0000000001013531 RDI: ffff8800da4af950
 RBP: 0000000000000000 R08: ffff8800da1f9a00 R09: 0000000000000000
 R10: ffff8800db45b7e4 R11: 0000000000000246 R12: ffff8800da4af950
 R13: ffff8800d97a74c0 R14: 0000000000000000 R15: ffff8800d97a7480
 FS:  00007fd3970e0700(0000) GS:ffff88011fd00000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
 CR2: ffffc90001630024 CR3: 000000011a7e4000 CR4: 00000000000006e0
 Stack:
  ffffffff814d00d3 0000000000000000 ffff88011a05ff20 ffff8800da1f9a00
  ffffffff811dd8b9 0000000000000800 0000000000020000 00007fd396f35000
  ffffffff811f8714 0000000000003431 ffffffff8138dce0 0000000000000f80
 Call Trace:
  [<ffffffff814d00d3>] ? fib_route_seq_start+0x93/0xc0
  [<ffffffff811dd8b9>] ? seq_read+0x149/0x380
  [<ffffffff811f8714>] ? fsnotify+0x3b4/0x500
  [<ffffffff8138dce0>] ? process_echoes+0x70/0x70
  [<ffffffff8121cfa7>] ? proc_reg_read+0x47/0x70
  [<ffffffff811bb823>] ? __vfs_read+0x23/0xd0
  [<ffffffff811bbd42>] ? rw_verify_area+0x52/0xf0
  [<ffffffff811bbe61>] ? vfs_read+0x81/0x120
  [<ffffffff811bcbc2>] ? SyS_read+0x42/0xa0
  [<ffffffff81549ab2>] ? entry_SYSCALL_64_fastpath+0x16/0x75
 Code: 48 85 c0 75 d8 f3 c3 31 c0 c3 f3 c3 66 66 66 66 66 66 2e 0f 1f 84 00 00
a 04 89 f0 33 02 44 89 c9 48 d3 e8 0f b6 4a 05 49 89
 RIP  [<ffffffff814cf6a0>] leaf_walk_rcu+0x10/0xe0
  RSP <ffff88011a05fda0>
 CR2: ffffc90001630024

Signed-off-by: Dave Forster <dforster@brocade.com>
Acked-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_trie.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index d07fc07..febca0f 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -2452,9 +2452,7 @@ struct fib_route_iter {
 static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter,
 					    loff_t pos)
 {
-	struct fib_table *tb = iter->main_tb;
 	struct key_vector *l, **tp = &iter->tnode;
-	struct trie *t;
 	t_key key;
 
 	/* use cache location of next-to-find key */
@@ -2462,8 +2460,6 @@ static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter,
 		pos -= iter->pos;
 		key = iter->key;
 	} else {
-		t = (struct trie *)tb->tb_data;
-		iter->tnode = t->kv;
 		iter->pos = 0;
 		key = 0;
 	}
@@ -2504,12 +2500,12 @@ static void *fib_route_seq_start(struct seq_file *seq, loff_t *pos)
 		return NULL;
 
 	iter->main_tb = tb;
+	t = (struct trie *)tb->tb_data;
+	iter->tnode = t->kv;
 
 	if (*pos != 0)
 		return fib_route_get_idx(iter, *pos);
 
-	t = (struct trie *)tb->tb_data;
-	iter->tnode = t->kv;
 	iter->pos = 0;
 	iter->key = 0;
 
-- 
2.1.0


From cdd3411db299037e14050acf692099c257c3d843 Mon Sep 17 00:00:00 2001
From: Lance Richardson <lrichard@redhat.com>
Date: Tue, 9 Aug 2016 15:29:42 -0400
Subject: [PATCH 03/31] vti: flush x-netns xfrm cache when vti interface is
 removed

[ Upstream commit a5d0dc810abf3d6b241777467ee1d6efb02575fc ]

When executing the script included below, the netns delete operation
hangs with the following message (repeated at 10 second intervals):

  kernel:unregister_netdevice: waiting for lo to become free. Usage count = 1

This occurs because a reference to the lo interface in the "secure" netns
is still held by a dst entry in the xfrm bundle cache in the init netns.

Address this problem by garbage collecting the tunnel netns flow cache
when a cross-namespace vti interface receives a NETDEV_DOWN notification.

A more detailed description of the problem scenario (referencing commands
in the script below):

(1) ip link add vti_test type vti local 1.1.1.1 remote 1.1.1.2 key 1

  The vti_test interface is created in the init namespace. vti_tunnel_init()
  attaches a struct ip_tunnel to the vti interface's netdev_priv(dev),
  setting the tunnel net to &init_net.

(2) ip link set vti_test netns secure

  The vti_test interface is moved to the "secure" netns. Note that
  the associated struct ip_tunnel still has tunnel->net set to &init_net.

(3) ip netns exec secure ping -c 4 -i 0.02 -I 192.168.100.1 192.168.200.1

  The first packet sent using the vti device causes xfrm_lookup() to be
  called as follows:

      dst = xfrm_lookup(tunnel->net, skb_dst(skb), fl, NULL, 0);

  Note that tunnel->net is the init namespace, while skb_dst(skb) references
  the vti_test interface in the "secure" namespace. The returned dst
  references an interface in the init namespace.

  Also note that the first parameter to xfrm_lookup() determines which flow
  cache is used to store the computed xfrm bundle, so after xfrm_lookup()
  returns there will be a cached bundle in the init namespace flow cache
  with a dst referencing a device in the "secure" namespace.

(4) ip netns del secure

  Kernel begins to delete the "secure" namespace.  At some point the
  vti_test interface is deleted, at which point dst_ifdown() changes
  the dst->dev in the cached xfrm bundle flow from vti_test to lo (still
  in the "secure" namespace however).
  Since nothing has happened to cause the init namespace's flow cache
  to be garbage collected, this dst remains attached to the flow cache,
  so the kernel loops waiting for the last reference to lo to go away.

<Begin script>
ip link add br1 type bridge
ip link set dev br1 up
ip addr add dev br1 1.1.1.1/8

ip netns add secure
ip link add vti_test type vti local 1.1.1.1 remote 1.1.1.2 key 1
ip link set vti_test netns secure
ip netns exec secure ip link set vti_test up
ip netns exec secure ip link s lo up
ip netns exec secure ip addr add dev lo 192.168.100.1/24
ip netns exec secure ip route add 192.168.200.0/24 dev vti_test
ip xfrm policy flush
ip xfrm state flush
ip xfrm policy add dir out tmpl src 1.1.1.1 dst 1.1.1.2 \
   proto esp mode tunnel mark 1
ip xfrm policy add dir in tmpl src 1.1.1.2 dst 1.1.1.1 \
   proto esp mode tunnel mark 1
ip xfrm state add src 1.1.1.1 dst 1.1.1.2 proto esp spi 1 \
   mode tunnel enc des3_ede 0x112233445566778811223344556677881122334455667788
ip xfrm state add src 1.1.1.2 dst 1.1.1.1 proto esp spi 1 \
   mode tunnel enc des3_ede 0x112233445566778811223344556677881122334455667788

ip netns exec secure ping -c 4 -i 0.02 -I 192.168.100.1 192.168.200.1

ip netns del secure
<End script>

Reported-by: Hangbin Liu <haliu@redhat.com>
Reported-by: Jan Tluka <jtluka@redhat.com>
Signed-off-by: Lance Richardson <lrichard@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_vti.c | 31 +++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index a917903..cc701fa 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -557,6 +557,33 @@ static struct rtnl_link_ops vti_link_ops __read_mostly = {
 	.get_link_net	= ip_tunnel_get_link_net,
 };
 
+static bool is_vti_tunnel(const struct net_device *dev)
+{
+	return dev->netdev_ops == &vti_netdev_ops;
+}
+
+static int vti_device_event(struct notifier_block *unused,
+			    unsigned long event, void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct ip_tunnel *tunnel = netdev_priv(dev);
+
+	if (!is_vti_tunnel(dev))
+		return NOTIFY_DONE;
+
+	switch (event) {
+	case NETDEV_DOWN:
+		if (!net_eq(tunnel->net, dev_net(dev)))
+			xfrm_garbage_collect(tunnel->net);
+		break;
+	}
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block vti_notifier_block __read_mostly = {
+	.notifier_call = vti_device_event,
+};
+
 static int __init vti_init(void)
 {
 	const char *msg;
@@ -564,6 +591,8 @@ static int __init vti_init(void)
 
 	pr_info("IPv4 over IPsec tunneling driver\n");
 
+	register_netdevice_notifier(&vti_notifier_block);
+
 	msg = "tunnel device";
 	err = register_pernet_device(&vti_net_ops);
 	if (err < 0)
@@ -596,6 +625,7 @@ xfrm_proto_ah_failed:
 xfrm_proto_esp_failed:
 	unregister_pernet_device(&vti_net_ops);
 pernet_dev_failed:
+	unregister_netdevice_notifier(&vti_notifier_block);
 	pr_err("vti init: failed to register %s\n", msg);
 	return err;
 }
@@ -607,6 +637,7 @@ static void __exit vti_fini(void)
 	xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
 	xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP);
 	unregister_pernet_device(&vti_net_ops);
+	unregister_netdevice_notifier(&vti_notifier_block);
 }
 
 module_init(vti_init);
-- 
2.1.0


From 7889c7c4ec971899856c105ee9837a7448e8a2c3 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 11 Aug 2016 21:38:37 +0200
Subject: [PATCH 04/31] bpf: fix write helpers with regards to non-linear parts

[ Upstream commit 0ed661d5a48fa6df0b50ae64d27fe759a3ce42cf ]

Fix the bpf_try_make_writable() helper and all call sites we have in BPF,
it's currently defect with regards to skbs when the write_len spans into
non-linear parts, no matter if cloned or not.

There are multiple issues at once. First, using skb_store_bits() is not
correct since even if we have a cloned skb, page frags can still be shared.
To really make them private, we need to pull them in via __pskb_pull_tail()
first, which also gets us a private head via pskb_expand_head() implicitly.

This is for helpers like bpf_skb_store_bytes(), bpf_l3_csum_replace(),
bpf_l4_csum_replace(). Really, the only thing reasonable and working here
is to call skb_ensure_writable() before any write operation. Meaning, via
pskb_may_pull() it makes sure that parts we want to access are pulled in and
if not does so plus unclones the skb implicitly. If our write_len still fits
the headlen and we're cloned and our header of the clone is not writable,
then we need to make a private copy via pskb_expand_head(). skb_store_bits()
is a bit misleading and only safe to store into non-linear data in different
contexts such as 357b40a18b04 ("[IPV6]: IPV6_CHECKSUM socket option can
corrupt kernel memory").

For above BPF helper functions, it means after fixed bpf_try_make_writable(),
we've pulled in enough, so that we operate always based on skb->data. Thus,
the call to skb_header_pointer() and skb_store_bits() becomes superfluous.
In bpf_skb_store_bytes(), the len check is unnecessary too since it can
only pass in maximum of BPF stack size, so adding offset is guaranteed to
never overflow. Also bpf_l3/4_csum_replace() helpers must test for proper
offset alignment since they use __sum16 pointer for writing resulting csum.

The remaining helpers that change skb data not discussed here yet are
bpf_skb_vlan_push(), bpf_skb_vlan_pop() and bpf_skb_change_proto(). The
vlan helpers internally call either skb_ensure_writable() (pop case) and
skb_cow_head() (push case, for head expansion), respectively. Similarly,
bpf_skb_proto_xlat() takes care to not mangle page frags.

Fixes: 608cd71a9c7c ("tc: bpf: generalize pedit action")
Fixes: 91bc4822c3d6 ("tc: bpf: add checksum helpers")
Fixes: 3697649ff29e ("bpf: try harder on clones when writing into skb")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/filter.c | 70 ++++++++++++++-----------------------------------------
 1 file changed, 18 insertions(+), 52 deletions(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index e759d90..bca32d6 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1353,54 +1353,33 @@ static inline int bpf_try_make_writable(struct sk_buff *skb,
 {
 	int err;
 
-	if (!skb_cloned(skb))
-		return 0;
-	if (skb_clone_writable(skb, write_len))
-		return 0;
-	err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
-	if (!err)
-		bpf_compute_data_end(skb);
+	err = skb_ensure_writable(skb, write_len);
+	bpf_compute_data_end(skb);
+
 	return err;
 }
 
 static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags)
 {
-	struct bpf_scratchpad *sp = this_cpu_ptr(&bpf_sp);
 	struct sk_buff *skb = (struct sk_buff *) (long) r1;
-	int offset = (int) r2;
+	unsigned int offset = (unsigned int) r2;
 	void *from = (void *) (long) r3;
 	unsigned int len = (unsigned int) r4;
 	void *ptr;
 
 	if (unlikely(flags & ~(BPF_F_RECOMPUTE_CSUM | BPF_F_INVALIDATE_HASH)))
 		return -EINVAL;
-
-	/* bpf verifier guarantees that:
-	 * 'from' pointer points to bpf program stack
-	 * 'len' bytes of it were initialized
-	 * 'len' > 0
-	 * 'skb' is a valid pointer to 'struct sk_buff'
-	 *
-	 * so check for invalid 'offset' and too large 'len'
-	 */
-	if (unlikely((u32) offset > 0xffff || len > sizeof(sp->buff)))
+	if (unlikely(offset > 0xffff))
 		return -EFAULT;
 	if (unlikely(bpf_try_make_writable(skb, offset + len)))
 		return -EFAULT;
 
-	ptr = skb_header_pointer(skb, offset, len, sp->buff);
-	if (unlikely(!ptr))
-		return -EFAULT;
-
+	ptr = skb->data + offset;
 	if (flags & BPF_F_RECOMPUTE_CSUM)
 		skb_postpull_rcsum(skb, ptr, len);
 
 	memcpy(ptr, from, len);
 
-	if (ptr == sp->buff)
-		/* skb_store_bits cannot return -EFAULT here */
-		skb_store_bits(skb, offset, ptr, len);
-
 	if (flags & BPF_F_RECOMPUTE_CSUM)
 		skb_postpush_rcsum(skb, ptr, len);
 	if (flags & BPF_F_INVALIDATE_HASH)
@@ -1423,12 +1402,12 @@ static const struct bpf_func_proto bpf_skb_store_bytes_proto = {
 static u64 bpf_skb_load_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
 {
 	const struct sk_buff *skb = (const struct sk_buff *)(unsigned long) r1;
-	int offset = (int) r2;
+	unsigned int offset = (unsigned int) r2;
 	void *to = (void *)(unsigned long) r3;
 	unsigned int len = (unsigned int) r4;
 	void *ptr;
 
-	if (unlikely((u32) offset > 0xffff))
+	if (unlikely(offset > 0xffff))
 		goto err_clear;
 
 	ptr = skb_header_pointer(skb, offset, len, to);
@@ -1456,20 +1435,17 @@ static const struct bpf_func_proto bpf_skb_load_bytes_proto = {
 static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags)
 {
 	struct sk_buff *skb = (struct sk_buff *) (long) r1;
-	int offset = (int) r2;
-	__sum16 sum, *ptr;
+	unsigned int offset = (unsigned int) r2;
+	__sum16 *ptr;
 
 	if (unlikely(flags & ~(BPF_F_HDR_FIELD_MASK)))
 		return -EINVAL;
-	if (unlikely((u32) offset > 0xffff))
-		return -EFAULT;
-	if (unlikely(bpf_try_make_writable(skb, offset + sizeof(sum))))
+	if (unlikely(offset > 0xffff || offset & 1))
 		return -EFAULT;
-
-	ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum);
-	if (unlikely(!ptr))
+	if (unlikely(bpf_try_make_writable(skb, offset + sizeof(*ptr))))
 		return -EFAULT;
 
+	ptr = (__sum16 *)(skb->data + offset);
 	switch (flags & BPF_F_HDR_FIELD_MASK) {
 	case 0:
 		if (unlikely(from != 0))
@@ -1487,10 +1463,6 @@ static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags)
 		return -EINVAL;
 	}
 
-	if (ptr == &sum)
-		/* skb_store_bits guaranteed to not return -EFAULT here */
-		skb_store_bits(skb, offset, ptr, sizeof(sum));
-
 	return 0;
 }
 
@@ -1510,20 +1482,18 @@ static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags)
 	struct sk_buff *skb = (struct sk_buff *) (long) r1;
 	bool is_pseudo = flags & BPF_F_PSEUDO_HDR;
 	bool is_mmzero = flags & BPF_F_MARK_MANGLED_0;
-	int offset = (int) r2;
-	__sum16 sum, *ptr;
+	unsigned int offset = (unsigned int) r2;
+	__sum16 *ptr;
 
 	if (unlikely(flags & ~(BPF_F_MARK_MANGLED_0 | BPF_F_PSEUDO_HDR |
 			       BPF_F_HDR_FIELD_MASK)))
 		return -EINVAL;
-	if (unlikely((u32) offset > 0xffff))
+	if (unlikely(offset > 0xffff || offset & 1))
 		return -EFAULT;
-	if (unlikely(bpf_try_make_writable(skb, offset + sizeof(sum))))
+	if (unlikely(bpf_try_make_writable(skb, offset + sizeof(*ptr))))
 		return -EFAULT;
 
-	ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum);
-	if (unlikely(!ptr))
-		return -EFAULT;
+	ptr = (__sum16 *)(skb->data + offset);
 	if (is_mmzero && !*ptr)
 		return 0;
 
@@ -1546,10 +1516,6 @@ static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags)
 
 	if (is_mmzero && !*ptr)
 		*ptr = CSUM_MANGLED_0;
-	if (ptr == &sum)
-		/* skb_store_bits guaranteed to not return -EFAULT here */
-		skb_store_bits(skb, offset, ptr, sizeof(sum));
-
 	return 0;
 }
 
-- 
2.1.0


From ca5448acf5b54b56193d53a6b5bef5080838231f Mon Sep 17 00:00:00 2001
From: Vegard Nossum <vegard.nossum@oracle.com>
Date: Fri, 12 Aug 2016 10:29:13 +0200
Subject: [PATCH 05/31] net/irda: handle iriap_register_lsap() allocation
 failure

[ Upstream commit 5ba092efc7ddff040777ae7162f1d195f513571b ]

If iriap_register_lsap() fails to allocate memory, self->lsap is
set to NULL. However, none of the callers handle the failure and
irlmp_connect_request() will happily dereference it:

    iriap_register_lsap: Unable to allocated LSAP!
    ================================================================================
    UBSAN: Undefined behaviour in net/irda/irlmp.c:378:2
    member access within null pointer of type 'struct lsap_cb'
    CPU: 1 PID: 15403 Comm: trinity-c0 Not tainted 4.8.0-rc1+ #81
    Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.3-0-ge2fc41e-prebuilt.qemu-project.org
    04/01/2014
     0000000000000000 ffff88010c7e78a8 ffffffff82344f40 0000000041b58ab3
     ffffffff84f98000 ffffffff82344e94 ffff88010c7e78d0 ffff88010c7e7880
     ffff88010630ad00 ffffffff84a5fae0 ffffffff84d3f5c0 000000000000017a
    Call Trace:
     [<ffffffff82344f40>] dump_stack+0xac/0xfc
     [<ffffffff8242f5a8>] ubsan_epilogue+0xd/0x8a
     [<ffffffff824302bf>] __ubsan_handle_type_mismatch+0x157/0x411
     [<ffffffff83b7bdbc>] irlmp_connect_request+0x7ac/0x970
     [<ffffffff83b77cc0>] iriap_connect_request+0xa0/0x160
     [<ffffffff83b77f48>] state_s_disconnect+0x88/0xd0
     [<ffffffff83b78904>] iriap_do_client_event+0x94/0x120
     [<ffffffff83b77710>] iriap_getvaluebyclass_request+0x3e0/0x6d0
     [<ffffffff83ba6ebb>] irda_find_lsap_sel+0x1eb/0x630
     [<ffffffff83ba90c8>] irda_connect+0x828/0x12d0
     [<ffffffff833c0dfb>] SYSC_connect+0x22b/0x340
     [<ffffffff833c7e09>] SyS_connect+0x9/0x10
     [<ffffffff81007bd3>] do_syscall_64+0x1b3/0x4b0
     [<ffffffff845f946a>] entry_SYSCALL64_slow_path+0x25/0x25
    ================================================================================

The bug seems to have been around since forever.

There's more problems with missing error checks in iriap_init() (and
indeed all of irda_init()), but that's a bigger problem that needs
very careful review and testing. This patch will fix the most serious
bug (as it's easily reached from unprivileged userspace).

I have tested my patch with a reproducer.

Signed-off-by: Vegard Nossum <vegard.nossum@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/irda/iriap.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/irda/iriap.c b/net/irda/iriap.c
index 4a7ae32a..1138eaf 100644
--- a/net/irda/iriap.c
+++ b/net/irda/iriap.c
@@ -185,8 +185,12 @@ struct iriap_cb *iriap_open(__u8 slsap_sel, int mode, void *priv,
 
 	self->magic = IAS_MAGIC;
 	self->mode = mode;
-	if (mode == IAS_CLIENT)
-		iriap_register_lsap(self, slsap_sel, mode);
+	if (mode == IAS_CLIENT) {
+		if (iriap_register_lsap(self, slsap_sel, mode)) {
+			kfree(self);
+			return NULL;
+		}
+	}
 
 	self->confirm = callback;
 	self->priv = priv;
-- 
2.1.0


From c93fa8978873e5a6a2e74c42ad1be6b57563d517 Mon Sep 17 00:00:00 2001
From: Vegard Nossum <vegard.nossum@oracle.com>
Date: Fri, 12 Aug 2016 09:50:51 +0200
Subject: [PATCH 06/31] net/sctp: always initialise sctp_ht_iter::start_fail

[ Upstream commit 54236ab09e9696a27baaae693c288920a26e8588 ]

sctp_transport_seq_start() does not currently clear iter->start_fail on
success, but relies on it being zero when it is allocated (by
seq_open_net()).

This can be a problem in the following sequence:

    open() // allocates iter (and implicitly sets iter->start_fail = 0)
    read()
     - iter->start() // fails and sets iter->start_fail = 1
     - iter->stop() // doesn't call sctp_transport_walk_stop() (correct)
    read() again
     - iter->start() // succeeds, but doesn't change iter->start_fail
     - iter->stop() // doesn't call sctp_transport_walk_stop() (wrong)

We should initialize sctp_ht_iter::start_fail to zero if ->start()
succeeds, otherwise it's possible that we leave an old value of 1 there,
which will cause ->stop() to not call sctp_transport_walk_stop(), which
causes all sorts of problems like not calling rcu_read_unlock() (and
preempt_enable()), eventually leading to more warnings like this:

    BUG: sleeping function called from invalid context at mm/slab.h:388
    in_atomic(): 0, irqs_disabled(): 0, pid: 16551, name: trinity-c2
    Preemption disabled at:[<ffffffff819bceb6>] rhashtable_walk_start+0x46/0x150

     [<ffffffff81149abb>] preempt_count_add+0x1fb/0x280
     [<ffffffff83295892>] _raw_spin_lock+0x12/0x40
     [<ffffffff819bceb6>] rhashtable_walk_start+0x46/0x150
     [<ffffffff82ec665f>] sctp_transport_walk_start+0x2f/0x60
     [<ffffffff82edda1d>] sctp_transport_seq_start+0x4d/0x150
     [<ffffffff81439e50>] traverse+0x170/0x850
     [<ffffffff8143aeec>] seq_read+0x7cc/0x1180
     [<ffffffff814f996c>] proc_reg_read+0xbc/0x180
     [<ffffffff813d0384>] do_loop_readv_writev+0x134/0x210
     [<ffffffff813d2a95>] do_readv_writev+0x565/0x660
     [<ffffffff813d6857>] vfs_readv+0x67/0xa0
     [<ffffffff813d6c16>] do_preadv+0x126/0x170
     [<ffffffff813d710c>] SyS_preadv+0xc/0x10
     [<ffffffff8100334c>] do_syscall_64+0x19c/0x410
     [<ffffffff83296225>] return_from_SYSCALL_64+0x0/0x6a
     [<ffffffffffffffff>] 0xffffffffffffffff

Notice that this is a subtly different stacktrace from the one in commit
5fc382d875 ("net/sctp: terminate rhashtable walk correctly").

Cc: Xin Long <lucien.xin@gmail.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Vegard Nossum <vegard.nossum@oracle.com>
Acked-By: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/proc.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sctp/proc.c b/net/sctp/proc.c
index 4cb5aed..ef8ba77 100644
--- a/net/sctp/proc.c
+++ b/net/sctp/proc.c
@@ -293,6 +293,7 @@ static void *sctp_transport_seq_start(struct seq_file *seq, loff_t *pos)
 		return ERR_PTR(err);
 	}
 
+	iter->start_fail = 0;
 	return sctp_transport_get_idx(seq_file_net(seq), &iter->hti, *pos);
 }
 
-- 
2.1.0


From d649313ee57596fa6712c33d707d87dea3f997ea Mon Sep 17 00:00:00 2001
From: Mike Manning <mmanning@brocade.com>
Date: Fri, 12 Aug 2016 12:02:38 +0100
Subject: [PATCH 07/31] net: ipv6: Do not keep IPv6 addresses when IPv6 is
 disabled

[ Upstream commit bc561632dddd5af0c4444d919f01cbf6d553aa0a ]

If IPv6 is disabled when the option is set to keep IPv6
addresses on link down, userspace is unaware of this as
there is no such indication via netlink. The solution is to
remove the IPv6 addresses in this case, which results in
netlink messages indicating removal of addresses in the
usual manner. This fix also makes the behavior consistent
with the case of having IPv6 disabled first, which stops
IPv6 addresses from being added.

Fixes: f1705ec197e7 ("net: ipv6: Make address flushing on ifdown optional")
Signed-off-by: Mike Manning <mmanning@brocade.com>
Acked-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 047c75a..355b6da 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3469,7 +3469,7 @@ static int addrconf_ifdown(struct net_device *dev, int how)
 	/* combine the user config with event to determine if permanent
 	 * addresses are to be removed from address hash table
 	 */
-	keep_addr = !(how || _keep_addr <= 0);
+	keep_addr = !(how || _keep_addr <= 0 || idev->cnf.disable_ipv6);
 
 	/* Step 2: clear hash table */
 	for (i = 0; i < IN6_ADDR_HSIZE; i++) {
@@ -3525,7 +3525,7 @@ restart:
 	/* re-combine the user config with event to determine if permanent
 	 * addresses are to be removed from the interface list
 	 */
-	keep_addr = (!how && _keep_addr > 0);
+	keep_addr = (!how && _keep_addr > 0 && !idev->cnf.disable_ipv6);
 
 	INIT_LIST_HEAD(&del_list);
 	list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) {
-- 
2.1.0


From 1304bb55632d300c260d11a216ce84d142962374 Mon Sep 17 00:00:00 2001
From: Vegard Nossum <vegard.nossum@oracle.com>
Date: Sat, 23 Jul 2016 08:15:04 +0200
Subject: [PATCH 08/31] tipc: fix NULL pointer dereference in shutdown()

[ Upstream commit d2fbdf76b85bcdfe57b8ef2ba09d20e8ada79abd ]

tipc_msg_create() can return a NULL skb and if so, we shouldn't try to
call tipc_node_xmit_skb() on it.

    general protection fault: 0000 [#1] PREEMPT SMP KASAN
    CPU: 3 PID: 30298 Comm: trinity-c0 Not tainted 4.7.0-rc7+ #19
    Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014
    task: ffff8800baf09980 ti: ffff8800595b8000 task.ti: ffff8800595b8000
    RIP: 0010:[<ffffffff830bb46b>]  [<ffffffff830bb46b>] tipc_node_xmit_skb+0x6b/0x140
    RSP: 0018:ffff8800595bfce8  EFLAGS: 00010246
    RAX: 0000000000000000 RBX: 0000000000000000 RCX: 000000003023b0e0
    RDX: 0000000000000000 RSI: dffffc0000000000 RDI: ffffffff83d12580
    RBP: ffff8800595bfd78 R08: ffffed000b2b7f32 R09: 0000000000000000
    R10: fffffbfff0759725 R11: 0000000000000000 R12: 1ffff1000b2b7f9f
    R13: ffff8800595bfd58 R14: ffffffff83d12580 R15: dffffc0000000000
    FS:  00007fcdde242700(0000) GS:ffff88011af80000(0000) knlGS:0000000000000000
    CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
    CR2: 00007fcddde1db10 CR3: 000000006874b000 CR4: 00000000000006e0
    DR0: 00007fcdde248000 DR1: 00007fcddd73d000 DR2: 00007fcdde248000
    DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000090602
    Stack:
     0000000000000018 0000000000000018 0000000041b58ab3 ffffffff83954208
     ffffffff830bb400 ffff8800595bfd30 ffffffff8309d767 0000000000000018
     0000000000000018 ffff8800595bfd78 ffffffff8309da1a 00000000810ee611
    Call Trace:
     [<ffffffff830c84a3>] tipc_shutdown+0x553/0x880
     [<ffffffff825b4a3b>] SyS_shutdown+0x14b/0x170
     [<ffffffff8100334c>] do_syscall_64+0x19c/0x410
     [<ffffffff83295ca5>] entry_SYSCALL64_slow_path+0x25/0x25
    Code: 90 00 b4 0b 83 c7 00 f1 f1 f1 f1 4c 8d 6d e0 c7 40 04 00 00 00 f4 c7 40 08 f3 f3 f3 f3 48 89 d8 48 c1 e8 03 c7 45 b4 00 00 00 00 <80> 3c 30 00 75 78 48 8d 7b 08 49 8d 75 c0 48 b8 00 00 00 00 00
    RIP  [<ffffffff830bb46b>] tipc_node_xmit_skb+0x6b/0x140
     RSP <ffff8800595bfce8>
    ---[ end trace 57b0484e351e71f1 ]---

I feel like we should maybe return -ENOMEM or -ENOBUFS, but I'm not sure
userspace is equipped to handle that. Anyway, this is better than a GPF
and looks somewhat consistent with other tipc_msg_create() callers.

Signed-off-by: Vegard Nossum <vegard.nossum@oracle.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/socket.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index c49b8df..f9f5f3c 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2180,7 +2180,8 @@ restart:
 					      TIPC_CONN_MSG, SHORT_H_SIZE,
 					      0, dnode, onode, dport, oport,
 					      TIPC_CONN_SHUTDOWN);
-			tipc_node_xmit_skb(net, skb, dnode, tsk->portid);
+			if (skb)
+				tipc_node_xmit_skb(net, skb, dnode, tsk->portid);
 		}
 		tsk->connected = 0;
 		sock->state = SS_DISCONNECTING;
-- 
2.1.0


From d6c651b75ad1be18148af6bc38bfd4722914334f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 17 Aug 2016 05:56:26 -0700
Subject: [PATCH 09/31] tcp: fix use after free in tcp_xmit_retransmit_queue()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit bb1fceca22492109be12640d49f5ea5a544c6bb4 ]

When tcp_sendmsg() allocates a fresh and empty skb, it puts it at the
tail of the write queue using tcp_add_write_queue_tail()

Then it attempts to copy user data into this fresh skb.

If the copy fails, we undo the work and remove the fresh skb.

Unfortunately, this undo lacks the change done to tp->highest_sack and
we can leave a dangling pointer (to a freed skb)

Later, tcp_xmit_retransmit_queue() can dereference this pointer and
access freed memory. For regular kernels where memory is not unmapped,
this might cause SACK bugs because tcp_highest_sack_seq() is buggy,
returning garbage instead of tp->snd_nxt, but with various debug
features like CONFIG_DEBUG_PAGEALLOC, this can crash the kernel.

This bug was found by Marco Grassi thanks to syzkaller.

Fixes: 6859d49475d4 ("[TCP]: Abstract tp->highest_sack accessing & point to next skb")
Reported-by: Marco Grassi <marco.gra@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 0bcc70f..7254051 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1522,6 +1522,8 @@ static inline void tcp_check_send_head(struct sock *sk, struct sk_buff *skb_unli
 {
 	if (sk->sk_send_head == skb_unlinked)
 		sk->sk_send_head = NULL;
+	if (tcp_sk(sk)->highest_sack == skb_unlinked)
+		tcp_sk(sk)->highest_sack = NULL;
 }
 
 static inline void tcp_init_send_head(struct sock *sk)
-- 
2.1.0


From a904ec89a39538141a0106dd490cec057ba175ba Mon Sep 17 00:00:00 2001
From: Mohamad Haj Yahia <mohamad@mellanox.com>
Date: Thu, 18 Aug 2016 21:09:04 +0300
Subject: [PATCH 10/31] net/mlx5: Fix pci error recovery flow

[ Upstream commit 1061c90f524963a0a90e7d2f9a6bfa666458af51 ]

When PCI error is detected we should save the state of the pci prior to
disabling it.

Also when receiving pci slot reset call we need to verify that the
device is responsive.

Fixes: 89d44f0a6c73 ('net/mlx5_core: Add pci error handlers to mlx5_core
driver')
Signed-off-by: Mohamad Haj Yahia <mohamad@mellanox.com>

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 59 +++++++++++++-------------
 1 file changed, 29 insertions(+), 30 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 6695893..e782d0f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1392,36 +1392,12 @@ static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev,
 	dev_info(&pdev->dev, "%s was called\n", __func__);
 	mlx5_enter_error_state(dev);
 	mlx5_unload_one(dev, priv);
+	pci_save_state(pdev);
 	mlx5_pci_disable_device(dev);
 	return state == pci_channel_io_perm_failure ?
 		PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_NEED_RESET;
 }
 
-static pci_ers_result_t mlx5_pci_slot_reset(struct pci_dev *pdev)
-{
-	struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
-	int err = 0;
-
-	dev_info(&pdev->dev, "%s was called\n", __func__);
-
-	err = mlx5_pci_enable_device(dev);
-	if (err) {
-		dev_err(&pdev->dev, "%s: mlx5_pci_enable_device failed with error code: %d\n"
-			, __func__, err);
-		return PCI_ERS_RESULT_DISCONNECT;
-	}
-	pci_set_master(pdev);
-	pci_set_power_state(pdev, PCI_D0);
-	pci_restore_state(pdev);
-
-	return err ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED;
-}
-
-void mlx5_disable_device(struct mlx5_core_dev *dev)
-{
-	mlx5_pci_err_detected(dev->pdev, 0);
-}
-
 /* wait for the device to show vital signs by waiting
  * for the health counter to start counting.
  */
@@ -1449,21 +1425,44 @@ static int wait_vital(struct pci_dev *pdev)
 	return -ETIMEDOUT;
 }
 
-static void mlx5_pci_resume(struct pci_dev *pdev)
+static pci_ers_result_t mlx5_pci_slot_reset(struct pci_dev *pdev)
 {
 	struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
-	struct mlx5_priv *priv = &dev->priv;
 	int err;
 
 	dev_info(&pdev->dev, "%s was called\n", __func__);
 
-	pci_save_state(pdev);
-	err = wait_vital(pdev);
+	err = mlx5_pci_enable_device(dev);
 	if (err) {
+		dev_err(&pdev->dev, "%s: mlx5_pci_enable_device failed with error code: %d\n"
+			, __func__, err);
+		return PCI_ERS_RESULT_DISCONNECT;
+	}
+
+	pci_set_master(pdev);
+	pci_restore_state(pdev);
+
+	if (wait_vital(pdev)) {
 		dev_err(&pdev->dev, "%s: wait_vital timed out\n", __func__);
-		return;
+		return PCI_ERS_RESULT_DISCONNECT;
 	}
 
+	return PCI_ERS_RESULT_RECOVERED;
+}
+
+void mlx5_disable_device(struct mlx5_core_dev *dev)
+{
+	mlx5_pci_err_detected(dev->pdev, 0);
+}
+
+static void mlx5_pci_resume(struct pci_dev *pdev)
+{
+	struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
+	struct mlx5_priv *priv = &dev->priv;
+	int err;
+
+	dev_info(&pdev->dev, "%s was called\n", __func__);
+
 	err = mlx5_load_one(dev, priv);
 	if (err)
 		dev_err(&pdev->dev, "%s: mlx5_load_one failed with error code: %d\n"
-- 
2.1.0


From 9136473f16ce95a07f0939fbddb37960fe5caa53 Mon Sep 17 00:00:00 2001
From: Paul Blakey <paulb@mellanox.com>
Date: Thu, 18 Aug 2016 21:09:05 +0300
Subject: [PATCH 11/31] net/mlx5: Added missing check of msg length in
 verifying its signature

[ Upstream commit 2c0f8ce1b584a4d7b8ff53140d21dfed99834940 ]

Set and verify signature calculates the signature for each of the
mailbox nodes, even for those that are unused (from cache). Added
a missing length check to set and verify only those which are used.

While here, also moved the setting of msg's nodes token to where we
already go over them. This saves a pass because checksum is disabled,
and the only useful thing remaining that set signature does is setting
the token.

Fixes: e126ba97dba9 ('mlx5: Add driver for Mellanox Connect-IB
adapters')
Signed-off-by: Paul Blakey <paulb@mellanox.com>

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 85 +++++++++++++++++----------
 1 file changed, 54 insertions(+), 31 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index d6e2a1c..c2ec01a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -143,13 +143,14 @@ static struct mlx5_cmd_layout *get_inst(struct mlx5_cmd *cmd, int idx)
 	return cmd->cmd_buf + (idx << cmd->log_stride);
 }
 
-static u8 xor8_buf(void *buf, int len)
+static u8 xor8_buf(void *buf, size_t offset, int len)
 {
 	u8 *ptr = buf;
 	u8 sum = 0;
 	int i;
+	int end = len + offset;
 
-	for (i = 0; i < len; i++)
+	for (i = offset; i < end; i++)
 		sum ^= ptr[i];
 
 	return sum;
@@ -157,41 +158,49 @@ static u8 xor8_buf(void *buf, int len)
 
 static int verify_block_sig(struct mlx5_cmd_prot_block *block)
 {
-	if (xor8_buf(block->rsvd0, sizeof(*block) - sizeof(block->data) - 1) != 0xff)
+	size_t rsvd0_off = offsetof(struct mlx5_cmd_prot_block, rsvd0);
+	int xor_len = sizeof(*block) - sizeof(block->data) - 1;
+
+	if (xor8_buf(block, rsvd0_off, xor_len) != 0xff)
 		return -EINVAL;
 
-	if (xor8_buf(block, sizeof(*block)) != 0xff)
+	if (xor8_buf(block, 0, sizeof(*block)) != 0xff)
 		return -EINVAL;
 
 	return 0;
 }
 
-static void calc_block_sig(struct mlx5_cmd_prot_block *block, u8 token,
-			   int csum)
+static void calc_block_sig(struct mlx5_cmd_prot_block *block)
 {
-	block->token = token;
-	if (csum) {
-		block->ctrl_sig = ~xor8_buf(block->rsvd0, sizeof(*block) -
-					    sizeof(block->data) - 2);
-		block->sig = ~xor8_buf(block, sizeof(*block) - 1);
-	}
+	int ctrl_xor_len = sizeof(*block) - sizeof(block->data) - 2;
+	size_t rsvd0_off = offsetof(struct mlx5_cmd_prot_block, rsvd0);
+
+	block->ctrl_sig = ~xor8_buf(block, rsvd0_off, ctrl_xor_len);
+	block->sig = ~xor8_buf(block, 0, sizeof(*block) - 1);
 }
 
-static void calc_chain_sig(struct mlx5_cmd_msg *msg, u8 token, int csum)
+static void calc_chain_sig(struct mlx5_cmd_msg *msg)
 {
 	struct mlx5_cmd_mailbox *next = msg->next;
-
-	while (next) {
-		calc_block_sig(next->buf, token, csum);
+	int size = msg->len;
+	int blen = size - min_t(int, sizeof(msg->first.data), size);
+	int n = (blen + MLX5_CMD_DATA_BLOCK_SIZE - 1)
+		/ MLX5_CMD_DATA_BLOCK_SIZE;
+	int i = 0;
+
+	for (i = 0; i < n && next; i++)  {
+		calc_block_sig(next->buf);
 		next = next->next;
 	}
 }
 
 static void set_signature(struct mlx5_cmd_work_ent *ent, int csum)
 {
-	ent->lay->sig = ~xor8_buf(ent->lay, sizeof(*ent->lay));
-	calc_chain_sig(ent->in, ent->token, csum);
-	calc_chain_sig(ent->out, ent->token, csum);
+	ent->lay->sig = ~xor8_buf(ent->lay, 0,  sizeof(*ent->lay));
+	if (csum) {
+		calc_chain_sig(ent->in);
+		calc_chain_sig(ent->out);
+	}
 }
 
 static void poll_timeout(struct mlx5_cmd_work_ent *ent)
@@ -222,12 +231,17 @@ static int verify_signature(struct mlx5_cmd_work_ent *ent)
 	struct mlx5_cmd_mailbox *next = ent->out->next;
 	int err;
 	u8 sig;
+	int size = ent->out->len;
+	int blen = size - min_t(int, sizeof(ent->out->first.data), size);
+	int n = (blen + MLX5_CMD_DATA_BLOCK_SIZE - 1)
+		/ MLX5_CMD_DATA_BLOCK_SIZE;
+	int i = 0;
 
-	sig = xor8_buf(ent->lay, sizeof(*ent->lay));
+	sig = xor8_buf(ent->lay, 0, sizeof(*ent->lay));
 	if (sig != 0xff)
 		return -EINVAL;
 
-	while (next) {
+	for (i = 0; i < n && next; i++) {
 		err = verify_block_sig(next->buf);
 		if (err)
 			return err;
@@ -656,7 +670,6 @@ static void cmd_work_handler(struct work_struct *work)
 		spin_unlock_irqrestore(&cmd->alloc_lock, flags);
 	}
 
-	ent->token = alloc_token(cmd);
 	cmd->ent_arr[ent->idx] = ent;
 	lay = get_inst(cmd, ent->idx);
 	ent->lay = lay;
@@ -766,7 +779,8 @@ static u8 *get_status_ptr(struct mlx5_outbox_hdr *out)
 static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 			   struct mlx5_cmd_msg *out, void *uout, int uout_size,
 			   mlx5_cmd_cbk_t callback,
-			   void *context, int page_queue, u8 *status)
+			   void *context, int page_queue, u8 *status,
+			   u8 token)
 {
 	struct mlx5_cmd *cmd = &dev->cmd;
 	struct mlx5_cmd_work_ent *ent;
@@ -783,6 +797,8 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 	if (IS_ERR(ent))
 		return PTR_ERR(ent);
 
+	ent->token = token;
+
 	if (!callback)
 		init_completion(&ent->done);
 
@@ -854,7 +870,8 @@ static const struct file_operations fops = {
 	.write	= dbg_write,
 };
 
-static int mlx5_copy_to_msg(struct mlx5_cmd_msg *to, void *from, int size)
+static int mlx5_copy_to_msg(struct mlx5_cmd_msg *to, void *from, int size,
+			    u8 token)
 {
 	struct mlx5_cmd_prot_block *block;
 	struct mlx5_cmd_mailbox *next;
@@ -880,6 +897,7 @@ static int mlx5_copy_to_msg(struct mlx5_cmd_msg *to, void *from, int size)
 		memcpy(block->data, from, copy);
 		from += copy;
 		size -= copy;
+		block->token = token;
 		next = next->next;
 	}
 
@@ -949,7 +967,8 @@ static void free_cmd_box(struct mlx5_core_dev *dev,
 }
 
 static struct mlx5_cmd_msg *mlx5_alloc_cmd_msg(struct mlx5_core_dev *dev,
-					       gfp_t flags, int size)
+					       gfp_t flags, int size,
+					       u8 token)
 {
 	struct mlx5_cmd_mailbox *tmp, *head = NULL;
 	struct mlx5_cmd_prot_block *block;
@@ -978,6 +997,7 @@ static struct mlx5_cmd_msg *mlx5_alloc_cmd_msg(struct mlx5_core_dev *dev,
 		tmp->next = head;
 		block->next = cpu_to_be64(tmp->next ? tmp->next->dma : 0);
 		block->block_num = cpu_to_be32(n - i - 1);
+		block->token = token;
 		head = tmp;
 	}
 	msg->next = head;
@@ -1352,7 +1372,7 @@ static struct mlx5_cmd_msg *alloc_msg(struct mlx5_core_dev *dev, int in_size,
 	}
 
 	if (IS_ERR(msg))
-		msg = mlx5_alloc_cmd_msg(dev, gfp, in_size);
+		msg = mlx5_alloc_cmd_msg(dev, gfp, in_size, 0);
 
 	return msg;
 }
@@ -1377,6 +1397,7 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 	int err;
 	u8 status = 0;
 	u32 drv_synd;
+	u8 token;
 
 	if (pci_channel_offline(dev->pdev) ||
 	    dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
@@ -1395,20 +1416,22 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 		return err;
 	}
 
-	err = mlx5_copy_to_msg(inb, in, in_size);
+	token = alloc_token(&dev->cmd);
+
+	err = mlx5_copy_to_msg(inb, in, in_size, token);
 	if (err) {
 		mlx5_core_warn(dev, "err %d\n", err);
 		goto out_in;
 	}
 
-	outb = mlx5_alloc_cmd_msg(dev, gfp, out_size);
+	outb = mlx5_alloc_cmd_msg(dev, gfp, out_size, token);
 	if (IS_ERR(outb)) {
 		err = PTR_ERR(outb);
 		goto out_in;
 	}
 
 	err = mlx5_cmd_invoke(dev, inb, outb, out, out_size, callback, context,
-			      pages_queue, &status);
+			      pages_queue, &status, token);
 	if (err)
 		goto out_out;
 
@@ -1476,7 +1499,7 @@ static int create_msg_cache(struct mlx5_core_dev *dev)
 	INIT_LIST_HEAD(&cmd->cache.med.head);
 
 	for (i = 0; i < NUM_LONG_LISTS; i++) {
-		msg = mlx5_alloc_cmd_msg(dev, GFP_KERNEL, LONG_LIST_SIZE);
+		msg = mlx5_alloc_cmd_msg(dev, GFP_KERNEL, LONG_LIST_SIZE, 0);
 		if (IS_ERR(msg)) {
 			err = PTR_ERR(msg);
 			goto ex_err;
@@ -1486,7 +1509,7 @@ static int create_msg_cache(struct mlx5_core_dev *dev)
 	}
 
 	for (i = 0; i < NUM_MED_LISTS; i++) {
-		msg = mlx5_alloc_cmd_msg(dev, GFP_KERNEL, MED_LIST_SIZE);
+		msg = mlx5_alloc_cmd_msg(dev, GFP_KERNEL, MED_LIST_SIZE, 0);
 		if (IS_ERR(msg)) {
 			err = PTR_ERR(msg);
 			goto ex_err;
-- 
2.1.0


From ccfe53b5533ff2a9edd34a56a24eef28bfcf5e7a Mon Sep 17 00:00:00 2001
From: Hadar Hen Zion <hadarh@mellanox.com>
Date: Thu, 18 Aug 2016 21:09:07 +0300
Subject: [PATCH 12/31] net/mlx5e: Use correct flow dissector key on flower
 offloading

[ Upstream commit 1dbd0d373ac338903d27fab5204b13122cc5accd ]

The wrong key is used when extracting the address type field set by
the flower offload code. We have to use the control key and not the
basic key, fix that.

Fixes: e3a2b7ed018e ('net/mlx5e: Support offload cls_flower with drop action')
Signed-off-by: Hadar Hen Zion <hadarh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 704c3d3..0db51cc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -150,7 +150,7 @@ static int parse_cls_flower(struct mlx5e_priv *priv,
 	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) {
 		struct flow_dissector_key_control *key =
 			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
+						  FLOW_DISSECTOR_KEY_CONTROL,
 						  f->key);
 		addr_type = key->addr_type;
 	}
-- 
2.1.0


From 192f936598c93f60a1465e67233f8260794f0481 Mon Sep 17 00:00:00 2001
From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Mon, 22 Aug 2016 07:10:20 -0400
Subject: [PATCH 13/31] net sched: fix encoding to use real length

[ Upstream commit 28a10c426e81afc88514bca8e73affccf850fdf6 ]

Encoding of the metadata was using the padded length as opposed to
the real length of the data which is a bug per specification.
This has not been an issue todate because all metadatum specified
so far has been 32 bit where aligned and data length are the same width.
This also includes a bug fix for validating the length of a u16 field.
But since there is no metadata of size u16 yes we are fine to include it
here.

While at it get rid of magic numbers.

Fixes: ef6980b6becb ("net sched: introduce IFE action")
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ife.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index ea4a2fe..5c4cdea 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -52,7 +52,7 @@ int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen, const void *dval)
 	u32 *tlv = (u32 *)(skbdata);
 	u16 totlen = nla_total_size(dlen);	/*alignment + hdr */
 	char *dptr = (char *)tlv + NLA_HDRLEN;
-	u32 htlv = attrtype << 16 | totlen;
+	u32 htlv = attrtype << 16 | dlen;
 
 	*tlv = htonl(htlv);
 	memset(dptr, 0, totlen - NLA_HDRLEN);
@@ -134,7 +134,7 @@ EXPORT_SYMBOL_GPL(ife_release_meta_gen);
 
 int ife_validate_meta_u32(void *val, int len)
 {
-	if (len == 4)
+	if (len == sizeof(u32))
 		return 0;
 
 	return -EINVAL;
@@ -143,8 +143,8 @@ EXPORT_SYMBOL_GPL(ife_validate_meta_u32);
 
 int ife_validate_meta_u16(void *val, int len)
 {
-	/* length will include padding */
-	if (len == NLA_ALIGN(2))
+	/* length will not include padding */
+	if (len == sizeof(u16))
 		return 0;
 
 	return -EINVAL;
@@ -652,12 +652,14 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a,
 		u8 *tlvdata = (u8 *)tlv;
 		u16 mtype = tlv->type;
 		u16 mlen = tlv->len;
+		u16 alen;
 
 		mtype = ntohs(mtype);
 		mlen = ntohs(mlen);
+		alen = NLA_ALIGN(mlen);
 
-		if (find_decode_metaid(skb, ife, mtype, (mlen - 4),
-				       (void *)(tlvdata + 4))) {
+		if (find_decode_metaid(skb, ife, mtype, (mlen - NLA_HDRLEN),
+				       (void *)(tlvdata + NLA_HDRLEN))) {
 			/* abuse overlimits to count when we receive metadata
 			 * but dont have an ops for it
 			 */
@@ -666,8 +668,8 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a,
 			ife->tcf_qstats.overlimits++;
 		}
 
-		tlvdata += mlen;
-		ifehdrln -= mlen;
+		tlvdata += alen;
+		ifehdrln -= alen;
 		tlv = (struct meta_tlvhdr *)tlvdata;
 	}
 
-- 
2.1.0


From 30d4aecea7fcc5448fb4170590e71d7e3f6cf61d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 23 Aug 2016 13:59:33 -0700
Subject: [PATCH 14/31] udp: fix poll() issue with zero sized packets

[ Upstream commit e83c6744e81abc93a20d0eb3b7f504a176a6126a ]

Laura tracked poll() [and friends] regression caused by commit
e6afc8ace6dd ("udp: remove headers from UDP packets before queueing")

udp_poll() needs to know if there is a valid packet in receive queue,
even if its payload length is 0.

Change first_packet_length() to return an signed int, and use -1
as the indication of an empty queue.

Fixes: e6afc8ace6dd ("udp: remove headers from UDP packets before queueing")
Reported-by: Laura Abbott <labbott@redhat.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Tested-by: Laura Abbott <labbott@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index e61f7cd..00d18c5 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1182,13 +1182,13 @@ out:
  *	@sk: socket
  *
  *	Drops all bad checksum frames, until a valid one is found.
- *	Returns the length of found skb, or 0 if none is found.
+ *	Returns the length of found skb, or -1 if none is found.
  */
-static unsigned int first_packet_length(struct sock *sk)
+static int first_packet_length(struct sock *sk)
 {
 	struct sk_buff_head list_kill, *rcvq = &sk->sk_receive_queue;
 	struct sk_buff *skb;
-	unsigned int res;
+	int res;
 
 	__skb_queue_head_init(&list_kill);
 
@@ -1203,7 +1203,7 @@ static unsigned int first_packet_length(struct sock *sk)
 		__skb_unlink(skb, rcvq);
 		__skb_queue_tail(&list_kill, skb);
 	}
-	res = skb ? skb->len : 0;
+	res = skb ? skb->len : -1;
 	spin_unlock_bh(&rcvq->lock);
 
 	if (!skb_queue_empty(&list_kill)) {
@@ -1232,7 +1232,7 @@ int udp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 
 	case SIOCINQ:
 	{
-		unsigned int amount = first_packet_length(sk);
+		int amount = max_t(int, 0, first_packet_length(sk));
 
 		return put_user(amount, (int __user *)arg);
 	}
@@ -2184,7 +2184,7 @@ unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait)
 
 	/* Check for false positives due to checksum errors */
 	if ((mask & POLLRDNORM) && !(file->f_flags & O_NONBLOCK) &&
-	    !(sk->sk_shutdown & RCV_SHUTDOWN) && !first_packet_length(sk))
+	    !(sk->sk_shutdown & RCV_SHUTDOWN) && first_packet_length(sk) == -1)
 		mask &= ~(POLLIN | POLLRDNORM);
 
 	return mask;
-- 
2.1.0


From 379bc549817f312645c8e7884a67acb7ca50a32e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 22 Aug 2016 11:31:10 -0700
Subject: [PATCH 15/31] tcp: properly scale window in
 tcp_v[46]_reqsk_send_ack()

[ Upstream commit 20a2b49fc538540819a0c552877086548cff8d8d ]

When sending an ack in SYN_RECV state, we must scale the offered
window if wscale option was negotiated and accepted.

Tested:
 Following packetdrill test demonstrates the issue :

0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0

+0 bind(3, ..., ...) = 0
+0 listen(3, 1) = 0

// Establish a connection.
+0 < S 0:0(0) win 20000 <mss 1000,sackOK,wscale 7, nop, TS val 100 ecr 0>
+0 > S. 0:0(0) ack 1 win 28960 <mss 1460,sackOK, TS val 100 ecr 100, nop, wscale 7>

+0 < . 1:11(10) ack 1 win 156 <nop,nop,TS val 99 ecr 100>
// check that window is properly scaled !
+0 > . 1:1(0) ack 1 win 226 <nop,nop,TS val 200 ecr 100>

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c | 8 +++++++-
 net/ipv6/tcp_ipv6.c | 8 +++++++-
 2 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 3708de2..ba7ce3f 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -814,8 +814,14 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
 	u32 seq = (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 :
 					     tcp_sk(sk)->snd_nxt;
 
+	/* RFC 7323 2.3
+	 * The window field (SEG.WND) of every outgoing segment, with the
+	 * exception of <SYN> segments, MUST be right-shifted by
+	 * Rcv.Wind.Shift bits:
+	 */
 	tcp_v4_send_ack(sock_net(sk), skb, seq,
-			tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd,
+			tcp_rsk(req)->rcv_nxt,
+			req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale,
 			tcp_time_stamp,
 			req->ts_recent,
 			0,
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 2255d2b..889acc4 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -937,9 +937,15 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
 	/* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV
 	 * sk->sk_state == TCP_SYN_RECV -> for Fast Open.
 	 */
+	/* RFC 7323 2.3
+	 * The window field (SEG.WND) of every outgoing segment, with the
+	 * exception of <SYN> segments, MUST be right-shifted by
+	 * Rcv.Wind.Shift bits:
+	 */
 	tcp_v6_send_ack(sk, skb, (sk->sk_state == TCP_LISTEN) ?
 			tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt,
-			tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd,
+			tcp_rsk(req)->rcv_nxt,
+			req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale,
 			tcp_time_stamp, req->ts_recent, sk->sk_bound_dev_if,
 			tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr),
 			0, 0);
-- 
2.1.0


From e9787127f87471cbed3abce44c69a90e625ee4de Mon Sep 17 00:00:00 2001
From: Lance Richardson <lrichard@redhat.com>
Date: Tue, 23 Aug 2016 11:40:52 -0400
Subject: [PATCH 16/31] sctp: fix overrun in sctp_diag_dump_one()

[ Upstream commit 232cb53a45965f8789fbf0a9a1962f8c67ab1a3c ]

The function sctp_diag_dump_one() currently performs a memcpy()
of 64 bytes from a 16 byte field into another 16 byte field. Fix
by using correct size, use sizeof to obtain correct size instead
of using a hard-coded constant.

Fixes: 8f840e47f190 ("sctp: add the sctp_diag.c file")
Signed-off-by: Lance Richardson <lrichard@redhat.com>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sctp_diag.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/sctp/sctp_diag.c b/net/sctp/sctp_diag.c
index f69edcf..10bae22 100644
--- a/net/sctp/sctp_diag.c
+++ b/net/sctp/sctp_diag.c
@@ -418,11 +418,13 @@ static int sctp_diag_dump_one(struct sk_buff *in_skb,
 		paddr.v4.sin_family = AF_INET;
 	} else {
 		laddr.v6.sin6_port = req->id.idiag_sport;
-		memcpy(&laddr.v6.sin6_addr, req->id.idiag_src, 64);
+		memcpy(&laddr.v6.sin6_addr, req->id.idiag_src,
+		       sizeof(laddr.v6.sin6_addr));
 		laddr.v6.sin6_family = AF_INET6;
 
 		paddr.v6.sin6_port = req->id.idiag_dport;
-		memcpy(&paddr.v6.sin6_addr, req->id.idiag_dst, 64);
+		memcpy(&paddr.v6.sin6_addr, req->id.idiag_dst,
+		       sizeof(paddr.v6.sin6_addr));
 		paddr.v6.sin6_family = AF_INET6;
 	}
 
-- 
2.1.0


From e529ad1119e14ed467ae7587602f6645899b2622 Mon Sep 17 00:00:00 2001
From: Soheil Hassas Yeganeh <soheil@google.com>
Date: Tue, 23 Aug 2016 18:22:33 -0400
Subject: [PATCH 17/31] tun: fix transmit timestamp support

[ Upstream commit 7b996243fab46092fb3a29c773c54be8152366e4 ]

Instead of using sock_tx_timestamp, use skb_tx_timestamp to record
software transmit timestamp of a packet.

sock_tx_timestamp resets and overrides the tx_flags of the skb.
The function is intended to be called from within the protocol
layer when creating the skb, not from a device driver. This is
inconsistent with other drivers and will cause issues for TCP.

In TCP, we intend to sample the timestamps for the last byte
for each sendmsg/sendpage. For that reason, tcp_sendmsg calls
tcp_tx_timestamp only with the last skb that it generates.
For example, if a 128KB message is split into two 64KB packets
we want to sample the SND timestamp of the last packet. The current
code in the tun driver, however, will result in sampling the SND
timestamp for both packets.

Also, when the last packet is split into smaller packets for
retranmission (see tcp_fragment), the tun driver will record
timestamps for all of the retransmitted packets and not only the
last packet.

Fixes: eda297729171 (tun: Support software transmit time stamping.)
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: Francis Yan <francisyyan@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index e16487c..34259bd 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -878,11 +878,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC)))
 		goto drop;
 
-	if (skb->sk && sk_fullsock(skb->sk)) {
-		sock_tx_timestamp(skb->sk, skb->sk->sk_tsflags,
-				  &skb_shinfo(skb)->tx_flags);
-		sw_tx_timestamp(skb);
-	}
+	skb_tx_timestamp(skb);
 
 	/* Orphan the skb - required as we might hang on to it
 	 * for indefinite time.
-- 
2.1.0


From a99335b01779ec415aaee126e4edcbe1d5f74373 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 24 Aug 2016 11:01:20 -0700
Subject: [PATCH 18/31] net: dsa: bcm_sf2: Fix race condition while unmasking
 interrupts

[ Upstream commit 4f101c47791cdcb831b3ef1f831b1cc51e4fe03c ]

We kept shadow copies of which interrupt sources we have enabled and
disabled, but due to an order bug in how intrl2_mask_clear was defined,
we could run into the following scenario:

CPU0					CPU1
intrl2_1_mask_clear(..)
sets INTRL2_CPU_MASK_CLEAR
					bcm_sf2_switch_1_isr
					read INTRL2_CPU_STATUS and masks with stale
					irq1_mask value
updates irq1_mask value

Which would make us loop again and again trying to process and interrupt
we are not clearing since our copy of whether it was enabled before
still indicates it was not. Fix this by updating the shadow copy first,
and then unasking at the HW level.

Fixes: 246d7f773c13 ("net: dsa: add Broadcom SF2 switch driver")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/bcm_sf2.h b/drivers/net/dsa/bcm_sf2.h
index 200b1f5..71b1e52 100644
--- a/drivers/net/dsa/bcm_sf2.h
+++ b/drivers/net/dsa/bcm_sf2.h
@@ -189,8 +189,8 @@ static inline void name##_writeq(struct bcm_sf2_priv *priv, u64 val,	\
 static inline void intrl2_##which##_mask_clear(struct bcm_sf2_priv *priv, \
 						u32 mask)		\
 {									\
-	intrl2_##which##_writel(priv, mask, INTRL2_CPU_MASK_CLEAR);	\
 	priv->irq##which##_mask &= ~(mask);				\
+	intrl2_##which##_writel(priv, mask, INTRL2_CPU_MASK_CLEAR);	\
 }									\
 static inline void intrl2_##which##_mask_set(struct bcm_sf2_priv *priv, \
 						u32 mask)		\
-- 
2.1.0


From 9468133455b45fcc91f330dd2cb38ff96a4cb8cd Mon Sep 17 00:00:00 2001
From: Xander Huff <xander.huff@ni.com>
Date: Wed, 24 Aug 2016 16:47:53 -0500
Subject: [PATCH 19/31] Revert "phy: IRQ cannot be shared"

[ Upstream commit c3e70edd7c2eed6acd234627a6007627f5c76e8e ]

This reverts:
  commit 33c133cc7598 ("phy: IRQ cannot be shared")

On hardware with multiple PHY devices hooked up to the same IRQ line, allow
them to share it.

Sergei Shtylyov says:
  "I'm not sure now what was the reason I concluded that the IRQ sharing
  was impossible... most probably I thought that the kernel IRQ handling
  code exited the loop over the IRQ actions once IRQ_HANDLED was returned
  -- which is obviously not so in reality..."

Signed-off-by: Xander Huff <xander.huff@ni.com>
Signed-off-by: Nathan Sullivan <nathan.sullivan@ni.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index c5dc2c36..c6f6683 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -722,8 +722,10 @@ phy_err:
 int phy_start_interrupts(struct phy_device *phydev)
 {
 	atomic_set(&phydev->irq_disable, 0);
-	if (request_irq(phydev->irq, phy_interrupt, 0, "phy_interrupt",
-			phydev) < 0) {
+	if (request_irq(phydev->irq, phy_interrupt,
+				IRQF_SHARED,
+				"phy_interrupt",
+				phydev) < 0) {
 		pr_warn("%s: Can't get IRQ %d (PHY)\n",
 			phydev->mdio.bus->name, phydev->irq);
 		phydev->irq = PHY_POLL;
-- 
2.1.0


From cf4d945d79563ef8ca88a6e8cdbf5c60cd7c7b1a Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Sat, 27 Aug 2016 17:33:03 +0100
Subject: [PATCH 20/31] net: smc91x: fix SMC accesses

[ Upstream commit 2fb04fdf30192ff1e2b5834e9b7745889ea8bbcb ]

Commit b70661c70830 ("net: smc91x: use run-time configuration on all ARM
machines") broke some ARM platforms through several mistakes.  Firstly,
the access size must correspond to the following rule:

(a) at least one of 16-bit or 8-bit access size must be supported
(b) 32-bit accesses are optional, and may be enabled in addition to
    the above.

Secondly, it provides no emulation of 16-bit accesses, instead blindly
making 16-bit accesses even when the platform specifies that only 8-bit
is supported.

Reorganise smc91x.h so we can make use of the existing 16-bit access
emulation already provided - if 16-bit accesses are supported, use
16-bit accesses directly, otherwise if 8-bit accesses are supported,
use the provided 16-bit access emulation.  If neither, BUG().  This
exactly reflects the driver behaviour prior to the commit being fixed.

Since the conversion incorrectly cut down the available access sizes on
several platforms, we also need to go through every platform and fix up
the overly-restrictive access size: Arnd assumed that if a platform can
perform 32-bit, 16-bit and 8-bit accesses, then only a 32-bit access
size needed to be specified - not so, all available access sizes must
be specified.

This likely fixes some performance regressions in doing this: if a
platform does not support 8-bit accesses, 8-bit accesses have been
emulated by performing a 16-bit read-modify-write access.

Tested on the Intel Assabet/Neponset platform, which supports only 8-bit
accesses, which was broken by the original commit.

Fixes: b70661c70830 ("net: smc91x: use run-time configuration on all ARM machines")
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Tested-by: Robert Jarzmik <robert.jarzmik@free.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/arm/mach-pxa/idp.c                    |  3 +-
 arch/arm/mach-pxa/xcep.c                   |  3 +-
 arch/arm/mach-realview/core.c              |  3 +-
 arch/arm/mach-sa1100/pleb.c                |  2 +-
 arch/blackfin/mach-bf561/boards/cm_bf561.c |  3 +-
 arch/blackfin/mach-bf561/boards/ezkit.c    |  3 +-
 drivers/net/ethernet/smsc/smc91x.c         |  7 ++++
 drivers/net/ethernet/smsc/smc91x.h         | 65 +++++++++++++++++++++---------
 include/linux/smc91x.h                     | 10 +++++
 9 files changed, 73 insertions(+), 26 deletions(-)

diff --git a/arch/arm/mach-pxa/idp.c b/arch/arm/mach-pxa/idp.c
index c410d84..66070ac 100644
--- a/arch/arm/mach-pxa/idp.c
+++ b/arch/arm/mach-pxa/idp.c
@@ -83,7 +83,8 @@ static struct resource smc91x_resources[] = {
 };
 
 static struct smc91x_platdata smc91x_platdata = {
-	.flags = SMC91X_USE_32BIT | SMC91X_USE_DMA | SMC91X_NOWAIT,
+	.flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+		 SMC91X_USE_DMA | SMC91X_NOWAIT,
 };
 
 static struct platform_device smc91x_device = {
diff --git a/arch/arm/mach-pxa/xcep.c b/arch/arm/mach-pxa/xcep.c
index 3f06cd9..056369e 100644
--- a/arch/arm/mach-pxa/xcep.c
+++ b/arch/arm/mach-pxa/xcep.c
@@ -120,7 +120,8 @@ static struct resource smc91x_resources[] = {
 };
 
 static struct smc91x_platdata xcep_smc91x_info = {
-	.flags	= SMC91X_USE_32BIT | SMC91X_NOWAIT | SMC91X_USE_DMA,
+	.flags	= SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+		  SMC91X_NOWAIT | SMC91X_USE_DMA,
 };
 
 static struct platform_device smc91x_device = {
diff --git a/arch/arm/mach-realview/core.c b/arch/arm/mach-realview/core.c
index baf1745..a0ead0a 100644
--- a/arch/arm/mach-realview/core.c
+++ b/arch/arm/mach-realview/core.c
@@ -93,7 +93,8 @@ static struct smsc911x_platform_config smsc911x_config = {
 };
 
 static struct smc91x_platdata smc91x_platdata = {
-	.flags = SMC91X_USE_32BIT | SMC91X_NOWAIT,
+	.flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+		 SMC91X_NOWAIT,
 };
 
 static struct platform_device realview_eth_device = {
diff --git a/arch/arm/mach-sa1100/pleb.c b/arch/arm/mach-sa1100/pleb.c
index 1525d7b..88149f8 100644
--- a/arch/arm/mach-sa1100/pleb.c
+++ b/arch/arm/mach-sa1100/pleb.c
@@ -45,7 +45,7 @@ static struct resource smc91x_resources[] = {
 };
 
 static struct smc91x_platdata smc91x_platdata = {
-	.flags = SMC91X_USE_16BIT | SMC91X_NOWAIT,
+	.flags = SMC91X_USE_16BIT | SMC91X_USE_8BIT | SMC91X_NOWAIT,
 };
 
 static struct platform_device smc91x_device = {
diff --git a/arch/blackfin/mach-bf561/boards/cm_bf561.c b/arch/blackfin/mach-bf561/boards/cm_bf561.c
index c6db52b..10c5777 100644
--- a/arch/blackfin/mach-bf561/boards/cm_bf561.c
+++ b/arch/blackfin/mach-bf561/boards/cm_bf561.c
@@ -146,7 +146,8 @@ static struct platform_device hitachi_fb_device = {
 #include <linux/smc91x.h>
 
 static struct smc91x_platdata smc91x_info = {
-	.flags = SMC91X_USE_32BIT | SMC91X_NOWAIT,
+	.flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+		 SMC91X_NOWAIT,
 	.leda = RPC_LED_100_10,
 	.ledb = RPC_LED_TX_RX,
 };
diff --git a/arch/blackfin/mach-bf561/boards/ezkit.c b/arch/blackfin/mach-bf561/boards/ezkit.c
index f35525b..57d1c43 100644
--- a/arch/blackfin/mach-bf561/boards/ezkit.c
+++ b/arch/blackfin/mach-bf561/boards/ezkit.c
@@ -134,7 +134,8 @@ static struct platform_device net2272_bfin_device = {
 #include <linux/smc91x.h>
 
 static struct smc91x_platdata smc91x_info = {
-	.flags = SMC91X_USE_32BIT | SMC91X_NOWAIT,
+	.flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+		 SMC91X_NOWAIT,
 	.leda = RPC_LED_100_10,
 	.ledb = RPC_LED_TX_RX,
 };
diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c
index 18ac52d..b69d0e1 100644
--- a/drivers/net/ethernet/smsc/smc91x.c
+++ b/drivers/net/ethernet/smsc/smc91x.c
@@ -2269,6 +2269,13 @@ static int smc_drv_probe(struct platform_device *pdev)
 	if (pd) {
 		memcpy(&lp->cfg, pd, sizeof(lp->cfg));
 		lp->io_shift = SMC91X_IO_SHIFT(lp->cfg.flags);
+
+		if (!SMC_8BIT(lp) && !SMC_16BIT(lp)) {
+			dev_err(&pdev->dev,
+				"at least one of 8-bit or 16-bit access support is required.\n");
+			ret = -ENXIO;
+			goto out_free_netdev;
+		}
 	}
 
 #if IS_BUILTIN(CONFIG_OF)
diff --git a/drivers/net/ethernet/smsc/smc91x.h b/drivers/net/ethernet/smsc/smc91x.h
index 1a55c79..e17671c 100644
--- a/drivers/net/ethernet/smsc/smc91x.h
+++ b/drivers/net/ethernet/smsc/smc91x.h
@@ -37,6 +37,27 @@
 #include <linux/smc91x.h>
 
 /*
+ * Any 16-bit access is performed with two 8-bit accesses if the hardware
+ * can't do it directly. Most registers are 16-bit so those are mandatory.
+ */
+#define SMC_outw_b(x, a, r)						\
+	do {								\
+		unsigned int __val16 = (x);				\
+		unsigned int __reg = (r);				\
+		SMC_outb(__val16, a, __reg);				\
+		SMC_outb(__val16 >> 8, a, __reg + (1 << SMC_IO_SHIFT));	\
+	} while (0)
+
+#define SMC_inw_b(a, r)							\
+	({								\
+		unsigned int __val16;					\
+		unsigned int __reg = r;					\
+		__val16  = SMC_inb(a, __reg);				\
+		__val16 |= SMC_inb(a, __reg + (1 << SMC_IO_SHIFT)) << 8; \
+		__val16;						\
+	})
+
+/*
  * Define your architecture specific bus configuration parameters here.
  */
 
@@ -55,10 +76,30 @@
 #define SMC_IO_SHIFT		(lp->io_shift)
 
 #define SMC_inb(a, r)		readb((a) + (r))
-#define SMC_inw(a, r)		readw((a) + (r))
+#define SMC_inw(a, r)							\
+	({								\
+		unsigned int __smc_r = r;				\
+		SMC_16BIT(lp) ? readw((a) + __smc_r) :			\
+		SMC_8BIT(lp) ? SMC_inw_b(a, __smc_r) :			\
+		({ BUG(); 0; });					\
+	})
+
 #define SMC_inl(a, r)		readl((a) + (r))
 #define SMC_outb(v, a, r)	writeb(v, (a) + (r))
+#define SMC_outw(v, a, r)						\
+	do {								\
+		unsigned int __v = v, __smc_r = r;			\
+		if (SMC_16BIT(lp))					\
+			__SMC_outw(__v, a, __smc_r);			\
+		else if (SMC_8BIT(lp))					\
+			SMC_outw_b(__v, a, __smc_r);			\
+		else							\
+			BUG();						\
+	} while (0)
+
 #define SMC_outl(v, a, r)	writel(v, (a) + (r))
+#define SMC_insb(a, r, p, l)	readsb((a) + (r), p, l)
+#define SMC_outsb(a, r, p, l)	writesb((a) + (r), p, l)
 #define SMC_insw(a, r, p, l)	readsw((a) + (r), p, l)
 #define SMC_outsw(a, r, p, l)	writesw((a) + (r), p, l)
 #define SMC_insl(a, r, p, l)	readsl((a) + (r), p, l)
@@ -66,7 +107,7 @@
 #define SMC_IRQ_FLAGS		(-1)	/* from resource */
 
 /* We actually can't write halfwords properly if not word aligned */
-static inline void SMC_outw(u16 val, void __iomem *ioaddr, int reg)
+static inline void __SMC_outw(u16 val, void __iomem *ioaddr, int reg)
 {
 	if ((machine_is_mainstone() || machine_is_stargate2() ||
 	     machine_is_pxa_idp()) && reg & 2) {
@@ -416,24 +457,8 @@ smc_pxa_dma_insw(void __iomem *ioaddr, struct smc_local *lp, int reg, int dma,
 
 #if ! SMC_CAN_USE_16BIT
 
-/*
- * Any 16-bit access is performed with two 8-bit accesses if the hardware
- * can't do it directly. Most registers are 16-bit so those are mandatory.
- */
-#define SMC_outw(x, ioaddr, reg)					\
-	do {								\
-		unsigned int __val16 = (x);				\
-		SMC_outb( __val16, ioaddr, reg );			\
-		SMC_outb( __val16 >> 8, ioaddr, reg + (1 << SMC_IO_SHIFT));\
-	} while (0)
-#define SMC_inw(ioaddr, reg)						\
-	({								\
-		unsigned int __val16;					\
-		__val16 =  SMC_inb( ioaddr, reg );			\
-		__val16 |= SMC_inb( ioaddr, reg + (1 << SMC_IO_SHIFT)) << 8; \
-		__val16;						\
-	})
-
+#define SMC_outw(x, ioaddr, reg)	SMC_outw_b(x, ioaddr, reg)
+#define SMC_inw(ioaddr, reg)		SMC_inw_b(ioaddr, reg)
 #define SMC_insw(a, r, p, l)		BUG()
 #define SMC_outsw(a, r, p, l)		BUG()
 
diff --git a/include/linux/smc91x.h b/include/linux/smc91x.h
index 76199b7..e302c44 100644
--- a/include/linux/smc91x.h
+++ b/include/linux/smc91x.h
@@ -1,6 +1,16 @@
 #ifndef __SMC91X_H__
 #define __SMC91X_H__
 
+/*
+ * These bits define which access sizes a platform can support, rather
+ * than the maximal access size.  So, if your platform can do 16-bit
+ * and 32-bit accesses to the SMC91x device, but not 8-bit, set both
+ * SMC91X_USE_16BIT and SMC91X_USE_32BIT.
+ *
+ * The SMC91x driver requires at least one of SMC91X_USE_8BIT or
+ * SMC91X_USE_16BIT to be supported - just setting SMC91X_USE_32BIT is
+ * an invalid configuration.
+ */
 #define SMC91X_USE_8BIT (1 << 0)
 #define SMC91X_USE_16BIT (1 << 1)
 #define SMC91X_USE_32BIT (1 << 2)
-- 
2.1.0


From 33b8e38d6b3e8557167f7672b89e7e48c99872b4 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Wed, 31 Aug 2016 14:16:44 +0200
Subject: [PATCH 21/31] bridge: re-introduce 'fix parsing of MLDv2 reports'

[ Upstream commit 9264251ee2a55bce8fb93826b3f581fb9eb7e2c2 ]

commit bc8c20acaea1 ("bridge: multicast: treat igmpv3 report with
INCLUDE and no sources as a leave") seems to have accidentally reverted
commit 47cc84ce0c2f ("bridge: fix parsing of MLDv2 reports"). This
commit brings back a change to br_ip6_multicast_mld2_report() where
parsing of MLDv2 reports stops when the first group is successfully
added to the MDB cache.

Fixes: bc8c20acaea1 ("bridge: multicast: treat igmpv3 report with INCLUDE and no sources as a leave")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Acked-by: Thadeu Lima de Souza Cascardo <cascardo@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 4384414..d3abdae 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1121,7 +1121,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br,
 		} else {
 			err = br_ip6_multicast_add_group(br, port,
 							 &grec->grec_mca, vid);
-			if (!err)
+			if (err)
 				break;
 		}
 	}
-- 
2.1.0


From 4d9f8ac74dccd62f4735fec67d6c49702b5a82c6 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Sun, 28 Aug 2016 21:28:26 -0700
Subject: [PATCH 22/31] kcm: fix a socket double free

[ Upstream commit c0338aff2260ea6c092806312dbb154cec07a242 ]

Dmitry reported a double free on kcm socket, which could
be easily reproduced by:

	#include <unistd.h>
	#include <sys/syscall.h>

	int main()
	{
	  int fd = syscall(SYS_socket, 0x29ul, 0x5ul, 0x0ul, 0, 0, 0);
	  syscall(SYS_ioctl, fd, 0x89e2ul, 0x20a98000ul, 0, 0, 0);
	  return 0;
	}

This is because on the error path, after we install
the new socket file, we call sock_release() to clean
up the socket, which leaves the fd pointing to a freed
socket. Fix this by calling sys_close() on that fd
directly.

Fixes: ab7ac4eb9832 ("kcm: Kernel Connection Multiplexor module")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Tom Herbert <tom@herbertland.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/kcm/kcmsock.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 0b68ba7..48613f5 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -13,6 +13,7 @@
 #include <linux/socket.h>
 #include <linux/uaccess.h>
 #include <linux/workqueue.h>
+#include <linux/syscalls.h>
 #include <net/kcm.h>
 #include <net/netns/generic.h>
 #include <net/sock.h>
@@ -2035,7 +2036,7 @@ static int kcm_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 			if (copy_to_user((void __user *)arg, &info,
 					 sizeof(info))) {
 				err = -EFAULT;
-				sock_release(newsock);
+				sys_close(info.fd);
 			}
 		}
 
-- 
2.1.0


From afbfcc709655ed21b3c8197ed3988b683c0bebf5 Mon Sep 17 00:00:00 2001
From: Mahesh Bandewar <maheshb@google.com>
Date: Thu, 1 Sep 2016 22:18:34 -0700
Subject: [PATCH 23/31] bonding: Fix bonding crash

[ Upstream commit 24b27fc4cdf9e10c5e79e5923b6b7c2c5c95096c ]

Following few steps will crash kernel -

  (a) Create bonding master
      > modprobe bonding miimon=50
  (b) Create macvlan bridge on eth2
      > ip link add link eth2 dev mvl0 address aa:0:0:0:0:01 \
	   type macvlan
  (c) Now try adding eth2 into the bond
      > echo +eth2 > /sys/class/net/bond0/bonding/slaves
      <crash>

Bonding does lots of things before checking if the device enslaved is
busy or not.

In this case when the notifier call-chain sends notifications, the
bond_netdev_event() assumes that the rx_handler /rx_handler_data is
registered while the bond_enslave() hasn't progressed far enough to
register rx_handler for the new slave.

This patch adds a rx_handler check that can be performed right at the
beginning of the enslave code to avoid getting into this situation.

Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c |  7 ++++---
 include/linux/netdevice.h       |  1 +
 net/core/dev.c                  | 16 ++++++++++++++++
 3 files changed, 21 insertions(+), 3 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 4d79819..70dac73 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1341,9 +1341,10 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 			    slave_dev->name);
 	}
 
-	/* already enslaved */
-	if (slave_dev->flags & IFF_SLAVE) {
-		netdev_dbg(bond_dev, "Error: Device was already enslaved\n");
+	/* already in-use? */
+	if (netdev_is_rx_handler_busy(slave_dev)) {
+		netdev_err(bond_dev,
+			   "Error: Device is in use and cannot be enslaved\n");
 		return -EBUSY;
 	}
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index da4b33b..4f0e6fb 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3225,6 +3225,7 @@ static inline void napi_free_frags(struct napi_struct *napi)
 	napi->skb = NULL;
 }
 
+bool netdev_is_rx_handler_busy(struct net_device *dev);
 int netdev_rx_handler_register(struct net_device *dev,
 			       rx_handler_func_t *rx_handler,
 			       void *rx_handler_data);
diff --git a/net/core/dev.c b/net/core/dev.c
index 904ff43..97fb3da 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3979,6 +3979,22 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
 }
 
 /**
+ *	netdev_is_rx_handler_busy - check if receive handler is registered
+ *	@dev: device to check
+ *
+ *	Check if a receive handler is already registered for a given device.
+ *	Return true if there one.
+ *
+ *	The caller must hold the rtnl_mutex.
+ */
+bool netdev_is_rx_handler_busy(struct net_device *dev)
+{
+	ASSERT_RTNL();
+	return dev && rtnl_dereference(dev->rx_handler);
+}
+EXPORT_SYMBOL_GPL(netdev_is_rx_handler_busy);
+
+/**
  *	netdev_rx_handler_register - register receive handler
  *	@dev: device to register a handler for
  *	@rx_handler: receive handler to register
-- 
2.1.0


From a7c161f2c3028d90b8481968f718420dcad7c96c Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Thu, 1 Sep 2016 14:56:49 -0700
Subject: [PATCH 24/31] Revert "af_unix: Fix splice-bind deadlock"

[ Upstream commit 38f7bd94a97b542de86a2be9229289717e33a7a4 ]

This reverts commit c845acb324aa85a39650a14e7696982ceea75dc1.

It turns out that it just replaces one deadlock with another one: we can
still get the wrong lock ordering with the readlock due to overlayfs
calling back into the filesystem layer and still taking the vfs locks
after the readlock.

The proper solution ends up being to just split the readlock into two
pieces: the bind lock (taken *outside* the vfs locks) and the IO lock
(taken *inside* the filesystem locks).  The two locks are independent
anyway.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Reviewed-by: Shmulik Ladkani <shmulik.ladkani@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c | 66 +++++++++++++++++++++---------------------------------
 1 file changed, 26 insertions(+), 40 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 735362c..b791b69 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -953,20 +953,32 @@ fail:
 	return NULL;
 }
 
-static int unix_mknod(struct dentry *dentry, const struct path *path, umode_t mode,
-		      struct path *res)
+static int unix_mknod(const char *sun_path, umode_t mode, struct path *res)
 {
-	int err;
+	struct dentry *dentry;
+	struct path path;
+	int err = 0;
+	/*
+	 * Get the parent directory, calculate the hash for last
+	 * component.
+	 */
+	dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0);
+	err = PTR_ERR(dentry);
+	if (IS_ERR(dentry))
+		return err;
 
-	err = security_path_mknod(path, dentry, mode, 0);
+	/*
+	 * All right, let's create it.
+	 */
+	err = security_path_mknod(&path, dentry, mode, 0);
 	if (!err) {
-		err = vfs_mknod(d_inode(path->dentry), dentry, mode, 0);
+		err = vfs_mknod(d_inode(path.dentry), dentry, mode, 0);
 		if (!err) {
-			res->mnt = mntget(path->mnt);
+			res->mnt = mntget(path.mnt);
 			res->dentry = dget(dentry);
 		}
 	}
-
+	done_path_create(&path, dentry);
 	return err;
 }
 
@@ -977,12 +989,10 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	struct unix_sock *u = unix_sk(sk);
 	struct sockaddr_un *sunaddr = (struct sockaddr_un *)uaddr;
 	char *sun_path = sunaddr->sun_path;
-	int err, name_err;
+	int err;
 	unsigned int hash;
 	struct unix_address *addr;
 	struct hlist_head *list;
-	struct path path;
-	struct dentry *dentry;
 
 	err = -EINVAL;
 	if (sunaddr->sun_family != AF_UNIX)
@@ -998,34 +1008,14 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		goto out;
 	addr_len = err;
 
-	name_err = 0;
-	dentry = NULL;
-	if (sun_path[0]) {
-		/* Get the parent directory, calculate the hash for last
-		 * component.
-		 */
-		dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0);
-
-		if (IS_ERR(dentry)) {
-			/* delay report until after 'already bound' check */
-			name_err = PTR_ERR(dentry);
-			dentry = NULL;
-		}
-	}
-
 	err = mutex_lock_interruptible(&u->readlock);
 	if (err)
-		goto out_path;
+		goto out;
 
 	err = -EINVAL;
 	if (u->addr)
 		goto out_up;
 
-	if (name_err) {
-		err = name_err == -EEXIST ? -EADDRINUSE : name_err;
-		goto out_up;
-	}
-
 	err = -ENOMEM;
 	addr = kmalloc(sizeof(*addr)+addr_len, GFP_KERNEL);
 	if (!addr)
@@ -1036,11 +1026,11 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	addr->hash = hash ^ sk->sk_type;
 	atomic_set(&addr->refcnt, 1);
 
-	if (dentry) {
-		struct path u_path;
+	if (sun_path[0]) {
+		struct path path;
 		umode_t mode = S_IFSOCK |
 		       (SOCK_INODE(sock)->i_mode & ~current_umask());
-		err = unix_mknod(dentry, &path, mode, &u_path);
+		err = unix_mknod(sun_path, mode, &path);
 		if (err) {
 			if (err == -EEXIST)
 				err = -EADDRINUSE;
@@ -1048,9 +1038,9 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 			goto out_up;
 		}
 		addr->hash = UNIX_HASH_SIZE;
-		hash = d_real_inode(dentry)->i_ino & (UNIX_HASH_SIZE - 1);
+		hash = d_real_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE - 1);
 		spin_lock(&unix_table_lock);
-		u->path = u_path;
+		u->path = path;
 		list = &unix_socket_table[hash];
 	} else {
 		spin_lock(&unix_table_lock);
@@ -1073,10 +1063,6 @@ out_unlock:
 	spin_unlock(&unix_table_lock);
 out_up:
 	mutex_unlock(&u->readlock);
-out_path:
-	if (dentry)
-		done_path_create(&path, dentry);
-
 out:
 	return err;
 }
-- 
2.1.0


From f5fe2922d4d6117bce857b8ecc2317200004041f Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Thu, 1 Sep 2016 14:43:53 -0700
Subject: [PATCH 25/31] af_unix: split 'u->readlock' into two: 'iolock' and
 'bindlock'

[ Upstream commit 6e1ce3c3451291142a57c4f3f6f999a29fb5b3bc ]

Right now we use the 'readlock' both for protecting some of the af_unix
IO path and for making the bind be single-threaded.

The two are independent, but using the same lock makes for a nasty
deadlock due to ordering with regards to filesystem locking.  The bind
locking would want to nest outside the VSF pathname locking, but the IO
locking wants to nest inside some of those same locks.

We tried to fix this earlier with commit c845acb324aa ("af_unix: Fix
splice-bind deadlock") which moved the readlock inside the vfs locks,
but that caused problems with overlayfs that will then call back into
filesystem routines that take the lock in the wrong order anyway.

Splitting the locks means that we can go back to having the bind lock be
the outermost lock, and we don't have any deadlocks with lock ordering.

Acked-by: Rainer Weikusat <rweikusat@cyberadapt.com>
Acked-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/af_unix.h |  2 +-
 net/unix/af_unix.c    | 45 +++++++++++++++++++++++----------------------
 2 files changed, 24 insertions(+), 23 deletions(-)

diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index 9b4c418..fd60ecc 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -52,7 +52,7 @@ struct unix_sock {
 	struct sock		sk;
 	struct unix_address     *addr;
 	struct path		path;
-	struct mutex		readlock;
+	struct mutex		iolock, bindlock;
 	struct sock		*peer;
 	struct list_head	link;
 	atomic_long_t		inflight;
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index b791b69..e444fa4 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -661,11 +661,11 @@ static int unix_set_peek_off(struct sock *sk, int val)
 {
 	struct unix_sock *u = unix_sk(sk);
 
-	if (mutex_lock_interruptible(&u->readlock))
+	if (mutex_lock_interruptible(&u->iolock))
 		return -EINTR;
 
 	sk->sk_peek_off = val;
-	mutex_unlock(&u->readlock);
+	mutex_unlock(&u->iolock);
 
 	return 0;
 }
@@ -778,7 +778,8 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern)
 	spin_lock_init(&u->lock);
 	atomic_long_set(&u->inflight, 0);
 	INIT_LIST_HEAD(&u->link);
-	mutex_init(&u->readlock); /* single task reading lock */
+	mutex_init(&u->iolock); /* single task reading lock */
+	mutex_init(&u->bindlock); /* single task binding lock */
 	init_waitqueue_head(&u->peer_wait);
 	init_waitqueue_func_entry(&u->peer_wake, unix_dgram_peer_wake_relay);
 	unix_insert_socket(unix_sockets_unbound(sk), sk);
@@ -847,7 +848,7 @@ static int unix_autobind(struct socket *sock)
 	int err;
 	unsigned int retries = 0;
 
-	err = mutex_lock_interruptible(&u->readlock);
+	err = mutex_lock_interruptible(&u->bindlock);
 	if (err)
 		return err;
 
@@ -894,7 +895,7 @@ retry:
 	spin_unlock(&unix_table_lock);
 	err = 0;
 
-out:	mutex_unlock(&u->readlock);
+out:	mutex_unlock(&u->bindlock);
 	return err;
 }
 
@@ -1008,7 +1009,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		goto out;
 	addr_len = err;
 
-	err = mutex_lock_interruptible(&u->readlock);
+	err = mutex_lock_interruptible(&u->bindlock);
 	if (err)
 		goto out;
 
@@ -1062,7 +1063,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 out_unlock:
 	spin_unlock(&unix_table_lock);
 out_up:
-	mutex_unlock(&u->readlock);
+	mutex_unlock(&u->bindlock);
 out:
 	return err;
 }
@@ -1954,17 +1955,17 @@ static ssize_t unix_stream_sendpage(struct socket *socket, struct page *page,
 	if (false) {
 alloc_skb:
 		unix_state_unlock(other);
-		mutex_unlock(&unix_sk(other)->readlock);
+		mutex_unlock(&unix_sk(other)->iolock);
 		newskb = sock_alloc_send_pskb(sk, 0, 0, flags & MSG_DONTWAIT,
 					      &err, 0);
 		if (!newskb)
 			goto err;
 	}
 
-	/* we must acquire readlock as we modify already present
+	/* we must acquire iolock as we modify already present
 	 * skbs in the sk_receive_queue and mess with skb->len
 	 */
-	err = mutex_lock_interruptible(&unix_sk(other)->readlock);
+	err = mutex_lock_interruptible(&unix_sk(other)->iolock);
 	if (err) {
 		err = flags & MSG_DONTWAIT ? -EAGAIN : -ERESTARTSYS;
 		goto err;
@@ -2031,7 +2032,7 @@ alloc_skb:
 	}
 
 	unix_state_unlock(other);
-	mutex_unlock(&unix_sk(other)->readlock);
+	mutex_unlock(&unix_sk(other)->iolock);
 
 	other->sk_data_ready(other);
 	scm_destroy(&scm);
@@ -2040,7 +2041,7 @@ alloc_skb:
 err_state_unlock:
 	unix_state_unlock(other);
 err_unlock:
-	mutex_unlock(&unix_sk(other)->readlock);
+	mutex_unlock(&unix_sk(other)->iolock);
 err:
 	kfree_skb(newskb);
 	if (send_sigpipe && !(flags & MSG_NOSIGNAL))
@@ -2108,7 +2109,7 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
 	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
 
 	do {
-		mutex_lock(&u->readlock);
+		mutex_lock(&u->iolock);
 
 		skip = sk_peek_offset(sk, flags);
 		skb = __skb_try_recv_datagram(sk, flags, &peeked, &skip, &err,
@@ -2116,14 +2117,14 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
 		if (skb)
 			break;
 
-		mutex_unlock(&u->readlock);
+		mutex_unlock(&u->iolock);
 
 		if (err != -EAGAIN)
 			break;
 	} while (timeo &&
 		 !__skb_wait_for_more_packets(sk, &err, &timeo, last));
 
-	if (!skb) { /* implies readlock unlocked */
+	if (!skb) { /* implies iolock unlocked */
 		unix_state_lock(sk);
 		/* Signal EOF on disconnected non-blocking SEQPACKET socket. */
 		if (sk->sk_type == SOCK_SEQPACKET && err == -EAGAIN &&
@@ -2188,7 +2189,7 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
 
 out_free:
 	skb_free_datagram(sk, skb);
-	mutex_unlock(&u->readlock);
+	mutex_unlock(&u->iolock);
 out:
 	return err;
 }
@@ -2283,7 +2284,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state)
 	/* Lock the socket to prevent queue disordering
 	 * while sleeps in memcpy_tomsg
 	 */
-	mutex_lock(&u->readlock);
+	mutex_lock(&u->iolock);
 
 	if (flags & MSG_PEEK)
 		skip = sk_peek_offset(sk, flags);
@@ -2325,7 +2326,7 @@ again:
 				break;
 			}
 
-			mutex_unlock(&u->readlock);
+			mutex_unlock(&u->iolock);
 
 			timeo = unix_stream_data_wait(sk, timeo, last,
 						      last_len);
@@ -2336,7 +2337,7 @@ again:
 				goto out;
 			}
 
-			mutex_lock(&u->readlock);
+			mutex_lock(&u->iolock);
 			goto redo;
 unlock:
 			unix_state_unlock(sk);
@@ -2439,7 +2440,7 @@ unlock:
 		}
 	} while (size);
 
-	mutex_unlock(&u->readlock);
+	mutex_unlock(&u->iolock);
 	if (state->msg)
 		scm_recv(sock, state->msg, &scm, flags);
 	else
@@ -2480,9 +2481,9 @@ static ssize_t skb_unix_socket_splice(struct sock *sk,
 	int ret;
 	struct unix_sock *u = unix_sk(sk);
 
-	mutex_unlock(&u->readlock);
+	mutex_unlock(&u->iolock);
 	ret = splice_to_pipe(pipe, spd);
-	mutex_lock(&u->readlock);
+	mutex_lock(&u->iolock);
 
 	return ret;
 }
-- 
2.1.0


From b3b354081e90a0a9a882cfd73a4a9eec161b207a Mon Sep 17 00:00:00 2001
From: Dave Jones <davej@codemonkey.org.uk>
Date: Fri, 2 Sep 2016 14:39:50 -0400
Subject: [PATCH 26/31] ipv6: release dst in ping_v6_sendmsg

[ Upstream commit 03c2778a938aaba0893f6d6cdc29511d91a79848 ]

Neither the failure or success paths of ping_v6_sendmsg release
the dst it acquires.  This leads to a flood of warnings from
"net/core/dst.c:288 dst_release" on older kernels that
don't have 8bf4ada2e21378816b28205427ee6b0e1ca4c5f1 backported.

That patch optimistically hoped this had been fixed post 3.10, but
it seems at least one case wasn't, where I've seen this triggered
a lot from machines doing unprivileged icmp sockets.

Cc: Martin Lau <kafai@fb.com>
Signed-off-by: Dave Jones <davej@codemonkey.org.uk>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ping.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 3ee3e44..4086604 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -122,8 +122,10 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	rt = (struct rt6_info *) dst;
 
 	np = inet6_sk(sk);
-	if (!np)
-		return -EBADF;
+	if (!np) {
+		err = -EBADF;
+		goto dst_err_out;
+	}
 
 	if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
 		fl6.flowi6_oif = np->mcast_oif;
@@ -160,6 +162,9 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	}
 	release_sock(sk);
 
+dst_err_out:
+	dst_release(dst);
+
 	if (err)
 		return err;
 
-- 
2.1.0


From 34037b34784d2a8cf918e826b0165f85face272f Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Mon, 5 Sep 2016 01:57:35 -0400
Subject: [PATCH 27/31] bnxt_en: Fix TX push operation on ARM64.

[ Upstream commit 9d13744bb75078175ab49408f2abb980e4dbccc9 ]

There is a code path where we are calling __iowrite64_copy() on
an address that is not 64-bit aligned.  This causes an exception on
some architectures such as arm64.  Fix that code path by using
__iowrite32_copy().

Reported-by: JD Zheng <jiandong.zheng@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index c777cde..e655b76 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -293,8 +293,8 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		push_len = (length + sizeof(*tx_push) + 7) / 8;
 		if (push_len > 16) {
 			__iowrite64_copy(txr->tx_doorbell, tx_push_buf, 16);
-			__iowrite64_copy(txr->tx_doorbell + 4, tx_push_buf + 1,
-					 push_len - 16);
+			__iowrite32_copy(txr->tx_doorbell + 4, tx_push_buf + 1,
+					 (push_len - 16) << 1);
 		} else {
 			__iowrite64_copy(txr->tx_doorbell, tx_push_buf,
 					 push_len);
-- 
2.1.0


From 9e243d4cac8a0cb7c7b64f1819f00729bc8d544e Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Mon, 5 Sep 2016 16:06:31 +0800
Subject: [PATCH 28/31] ipv6: addrconf: fix dev refcont leak when DAD failed

[ Upstream commit 751eb6b6042a596b0080967c1a529a9fe98dac1d ]

In general, when DAD detected IPv6 duplicate address, ifp->state
will be set to INET6_IFADDR_STATE_ERRDAD and DAD is stopped by a
delayed work, the call tree should be like this:

ndisc_recv_ns
  -> addrconf_dad_failure        <- missing ifp put
     -> addrconf_mod_dad_work
       -> schedule addrconf_dad_work()
         -> addrconf_dad_stop()  <- missing ifp hold before call it

addrconf_dad_failure() called with ifp refcont holding but not put.
addrconf_dad_work() call addrconf_dad_stop() without extra holding
refcount. This will not cause any issue normally.

But the race between addrconf_dad_failure() and addrconf_dad_work()
may cause ifp refcount leak and netdevice can not be unregister,
dmesg show the following messages:

IPv6: eth0: IPv6 duplicate address fe80::XX:XXXX:XXXX:XX detected!
...
unregister_netdevice: waiting for eth0 to become free. Usage count = 1

Cc: stable@vger.kernel.org
Fixes: c15b1ccadb32 ("ipv6: move DAD and addrconf_verify processing
to workqueue")
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 355b6da..82e367b 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1906,6 +1906,7 @@ errdad:
 	spin_unlock_bh(&ifp->lock);
 
 	addrconf_mod_dad_work(ifp, 0);
+	in6_ifa_put(ifp);
 }
 
 /* Join to solicited addr multicast group.
@@ -3771,6 +3772,7 @@ static void addrconf_dad_work(struct work_struct *w)
 		addrconf_dad_begin(ifp);
 		goto out;
 	} else if (action == DAD_ABORT) {
+		in6_ifa_hold(ifp);
 		addrconf_dad_stop(ifp, 1);
 		goto out;
 	}
-- 
2.1.0


From 6cf0ee7696851b9bee1f0074af866a26db7ad0dd Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 7 Sep 2016 08:34:11 -0700
Subject: [PATCH 29/31] tcp: fastopen: avoid negative sk_forward_alloc

[ Upstream commit 76061f631c2ea4ab9c4d66f3a96ecc5737f5aaf7 ]

When DATA and/or FIN are carried in a SYN/ACK message or SYN message,
we append an skb in socket receive queue, but we forget to call
sk_forced_mem_schedule().

Effect is that the socket has a negative sk->sk_forward_alloc as long as
the message is not read by the application.

Josh Hunt fixed a similar issue in commit d22e15371811 ("tcp: fix tcp
fin memory accounting")

Fixes: 168a8f58059a ("tcp: TCP Fast Open Server - main code path")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Josh Hunt <johunt@akamai.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_fastopen.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 54d9f9b..478114b 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -150,6 +150,7 @@ void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb)
 	tp->segs_in = 0;
 	tcp_segs_in(tp, skb);
 	__skb_pull(skb, tcp_hdrlen(skb));
+	sk_forced_mem_schedule(sk, skb->truesize);
 	skb_set_owner_r(skb, sk);
 
 	TCP_SKB_CB(skb)->seq++;
-- 
2.1.0


From 202d1426b5c4db7c271521958697ad19e55ec64d Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Wed, 7 Sep 2016 19:08:01 +0300
Subject: [PATCH 30/31] net/mlx5e: Fix parsing of vlan packets when updating
 lro header

[ Upstream commit cd17d230dd060a12f7451c0caeedb3fd5158eaf9 ]

Currently vlan tagged packets were not parsed correctly
and assumed to be regular IPv4/IPv6 packets.
We should check for 802.1Q/802.1ad tags and update the lro header
accordingly.
This fixes the use case where LRO is on and rxvlan is off
(vlan stripping is off).

Fixes: e586b3b0baee ('net/mlx5: Ethernet Datapath files')
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 22 +++++++++++++++-------
 1 file changed, 15 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 9f2a16a..e41a066 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -648,24 +648,32 @@ bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq)
 static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe,
 				 u32 cqe_bcnt)
 {
-	struct ethhdr	*eth	= (struct ethhdr *)(skb->data);
-	struct iphdr	*ipv4	= (struct iphdr *)(skb->data + ETH_HLEN);
-	struct ipv6hdr	*ipv6	= (struct ipv6hdr *)(skb->data + ETH_HLEN);
+	struct ethhdr	*eth = (struct ethhdr *)(skb->data);
+	struct iphdr	*ipv4;
+	struct ipv6hdr	*ipv6;
 	struct tcphdr	*tcp;
+	int network_depth = 0;
+	__be16 proto;
+	u16 tot_len;
 
 	u8 l4_hdr_type = get_cqe_l4_hdr_type(cqe);
 	int tcp_ack = ((CQE_L4_HDR_TYPE_TCP_ACK_NO_DATA  == l4_hdr_type) ||
 		       (CQE_L4_HDR_TYPE_TCP_ACK_AND_DATA == l4_hdr_type));
 
-	u16 tot_len = cqe_bcnt - ETH_HLEN;
+	skb->mac_len = ETH_HLEN;
+	proto = __vlan_get_protocol(skb, eth->h_proto, &network_depth);
 
-	if (eth->h_proto == htons(ETH_P_IP)) {
-		tcp = (struct tcphdr *)(skb->data + ETH_HLEN +
+	ipv4 = (struct iphdr *)(skb->data + network_depth);
+	ipv6 = (struct ipv6hdr *)(skb->data + network_depth);
+	tot_len = cqe_bcnt - network_depth;
+
+	if (proto == htons(ETH_P_IP)) {
+		tcp = (struct tcphdr *)(skb->data + network_depth +
 					sizeof(struct iphdr));
 		ipv6 = NULL;
 		skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
 	} else {
-		tcp = (struct tcphdr *)(skb->data + ETH_HLEN +
+		tcp = (struct tcphdr *)(skb->data + network_depth +
 					sizeof(struct ipv6hdr));
 		ipv4 = NULL;
 		skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
-- 
2.1.0


From a21cbecb60330ffa00d84cccac654b03176fed7b Mon Sep 17 00:00:00 2001
From: Artem Germanov <agermanov@anchorfree.com>
Date: Wed, 7 Sep 2016 10:49:36 -0700
Subject: [PATCH 31/31] tcp: cwnd does not increase in TCP YeAH

[ Upstream commit db7196a0d0984b933ccf2cd6a60e26abf466e8a3 ]

Commit 76174004a0f19785a328f40388e87e982bbf69b9
(tcp: do not slow start when cwnd equals ssthresh )
introduced regression in TCP YeAH. Using 100ms delay 1% loss virtual
ethernet link kernel 4.2 shows bandwidth ~500KB/s for single TCP
connection and kernel 4.3 and above (including 4.8-rc4) shows bandwidth
~100KB/s.
   That is caused by stalled cwnd when cwnd equals ssthresh. This patch
fixes it by proper increasing cwnd in this case.

Signed-off-by: Artem Germanov <agermanov@anchorfree.com>
Acked-by: Dmitry Adamushko <d.adamushko@anchorfree.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_yeah.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c
index 028eb04..9c5fc97 100644
--- a/net/ipv4/tcp_yeah.c
+++ b/net/ipv4/tcp_yeah.c
@@ -76,7 +76,7 @@ static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 	if (!tcp_is_cwnd_limited(sk))
 		return;
 
-	if (tp->snd_cwnd <= tp->snd_ssthresh)
+	if (tcp_in_slow_start(tp))
 		tcp_slow_start(tp, acked);
 
 	else if (!yeah->doing_reno_now) {
-- 
2.1.0

Re: [PATCHES] Networking

[Greg KH]

On Wed, Sep 21, 2016 at 01:07:13AM -0400, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.7 -stable.

Now applied thanks.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 110 bytes --]


Please queue up the following networking bug fixes for 4.4.x and 4.8.x
-stable, respectively.

Thanks a lot!

[-- Attachment #2: net_44.mbox --]
[-- Type: Application/Octet-Stream, Size: 87205 bytes --]

From 0009c14c161dae2ebe637d04c8d1d31bbcc2f524 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 15 Sep 2016 08:12:33 -0700
Subject: [PATCH 01/27] tcp: fix overflow in __tcp_retransmit_skb()

[ Upstream commit ffb4d6c8508657824bcef68a36b2a0f9d8c09d10 ]

If a TCP socket gets a large write queue, an overflow can happen
in a test in __tcp_retransmit_skb() preventing all retransmits.

The flow then stalls and resets after timeouts.

Tested:

sysctl -w net.core.wmem_max=1000000000
netperf -H dest -- -s 1000000000

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 660c967..2902adf 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2569,7 +2569,8 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 	 * copying overhead: fragmentation, tunneling, mangling etc.
 	 */
 	if (atomic_read(&sk->sk_wmem_alloc) >
-	    min(sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2), sk->sk_sndbuf))
+	    min_t(u32, sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2),
+		  sk->sk_sndbuf))
 		return -EAGAIN;
 
 	if (skb_still_in_host_queue(sk, skb))
-- 
2.4.11


From 79d1a86b036667d80549edcd8dcffd7c56fb683c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 15 Sep 2016 08:48:46 -0700
Subject: [PATCH 02/27] net: avoid sk_forward_alloc overflows

[ Upstream commit 20c64d5cd5a2bdcdc8982a06cb05e5e1bd851a3d ]

A malicious TCP receiver, sending SACK, can force the sender to split
skbs in write queue and increase its memory usage.

Then, when socket is closed and its write queue purged, we might
overflow sk_forward_alloc (It becomes negative)

sk_mem_reclaim() does nothing in this case, and more than 2GB
are leaked from TCP perspective (tcp_memory_allocated is not changed)

Then warnings trigger from inet_sock_destruct() and
sk_stream_kill_queues() seeing a not zero sk_forward_alloc

All TCP stack can be stuck because TCP is under memory pressure.

A simple fix is to preemptively reclaim from sk_mem_uncharge().

This makes sure a socket wont have more than 2 MB forward allocated,
after burst and idle period.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/include/net/sock.h b/include/net/sock.h
index 14d3c07..3d5ff74 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1425,6 +1425,16 @@ static inline void sk_mem_uncharge(struct sock *sk, int size)
 	if (!sk_has_account(sk))
 		return;
 	sk->sk_forward_alloc += size;
+
+	/* Avoid a possible overflow.
+	 * TCP send queues can make this happen, if sk_mem_reclaim()
+	 * is not called and more than 2 GBytes are released at once.
+	 *
+	 * If we reach 2 MBytes, reclaim 1 MBytes right now, there is
+	 * no need to hold that much forward allocation anyway.
+	 */
+	if (unlikely(sk->sk_forward_alloc >= 1 << 21))
+		__sk_mem_reclaim(sk, 1 << 20);
 }
 
 static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb)
-- 
2.4.11


From 6e7df95f3f5200dcaefbfdea7827924b3543e4ac Mon Sep 17 00:00:00 2001
From: Douglas Caetano dos Santos <douglascs@taghos.com.br>
Date: Thu, 22 Sep 2016 15:52:04 -0300
Subject: [PATCH 03/27] tcp: fix wrong checksum calculation on MTU probing

[ Upstream commit 2fe664f1fcf7c4da6891f95708a7a56d3c024354 ]

With TCP MTU probing enabled and offload TX checksumming disabled,
tcp_mtu_probe() calculated the wrong checksum when a fragment being copied
into the probe's SKB had an odd length. This was caused by the direct use
of skb_copy_and_csum_bits() to calculate the checksum, as it pads the
fragment being copied, if needed. When this fragment was not the last, a
subsequent call used the previous checksum without considering this
padding.

The effect was a stale connection in one way, as even retransmissions
wouldn't solve the problem, because the checksum was never recalculated for
the full SKB length.

Signed-off-by: Douglas Caetano dos Santos <douglascs@taghos.com.br>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 2902adf..0795647 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1950,12 +1950,14 @@ static int tcp_mtu_probe(struct sock *sk)
 	len = 0;
 	tcp_for_write_queue_from_safe(skb, next, sk) {
 		copy = min_t(int, skb->len, probe_size - len);
-		if (nskb->ip_summed)
+		if (nskb->ip_summed) {
 			skb_copy_bits(skb, 0, skb_put(nskb, copy), copy);
-		else
-			nskb->csum = skb_copy_and_csum_bits(skb, 0,
-							    skb_put(nskb, copy),
-							    copy, nskb->csum);
+		} else {
+			__wsum csum = skb_copy_and_csum_bits(skb, 0,
+							     skb_put(nskb, copy),
+							     copy, 0);
+			nskb->csum = csum_block_add(nskb->csum, csum, len);
+		}
 
 		if (skb->len <= copy) {
 			/* We've eaten all the data from this skb.
-- 
2.4.11


From 97d09bfe58d12418211f79e5f1a6625e77d196a2 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 22 Sep 2016 17:54:00 -0700
Subject: [PATCH 04/27] tcp: fix a compile error in DBGUNDO()

[ Upstream commit 019b1c9fe32a2a32c1153e31375f87ec3e591273 ]

If DBGUNDO() is enabled (FASTRETRANS_DEBUG > 1), a compile
error will happen, since inet6_sk(sk)->daddr became sk->sk_v6_daddr

Fixes: efe4208f47f9 ("ipv6: make lookups simpler and faster")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 12b98e2..7cc0f8a 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2324,10 +2324,9 @@ static void DBGUNDO(struct sock *sk, const char *msg)
 	}
 #if IS_ENABLED(CONFIG_IPV6)
 	else if (sk->sk_family == AF_INET6) {
-		struct ipv6_pinfo *np = inet6_sk(sk);
 		pr_debug("Undo %s %pI6/%u c%u l%u ss%u/%u p%u\n",
 			 msg,
-			 &np->daddr, ntohs(inet->inet_dport),
+			 &sk->sk_v6_daddr, ntohs(inet->inet_dport),
 			 tp->snd_cwnd, tcp_left_out(tp),
 			 tp->snd_ssthresh, tp->prior_ssthresh,
 			 tp->packets_out);
-- 
2.4.11


From 8fcc6a072104f68532462996160d6ea8a92c7177 Mon Sep 17 00:00:00 2001
From: Lance Richardson <lrichard@redhat.com>
Date: Fri, 23 Sep 2016 15:50:29 -0400
Subject: [PATCH 05/27] ip6_gre: fix flowi6_proto value in ip6gre_xmit_other()

[ Upstream commit db32e4e49ce2b0e5fcc17803d011a401c0a637f6 ]

Similar to commit 3be07244b733 ("ip6_gre: fix flowi6_proto value in
xmit path"), set flowi6_proto to IPPROTO_GRE for output route lookup.

Up until now, ip6gre_xmit_other() has set flowi6_proto to a bogus value.
This affected output route lookup for packets sent on an ip6gretap device
in cases where routing was dependent on the value of flowi6_proto.

Since the correct proto is already set in the tunnel flowi6 template via
commit 252f3f5a1189 ("ip6_gre: Set flowi6_proto as IPPROTO_GRE in xmit
path."), simply delete the line setting the incorrect flowi6_proto value.

Suggested-by: Jiri Benc <jbenc@redhat.com>
Fixes: c12b395a4664 ("gre: Support GRE over IPv6")
Reviewed-by: Shmulik Ladkani <shmulik.ladkani@gmail.com>
Signed-off-by: Lance Richardson <lrichard@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 4650c68..17430f3 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -886,7 +886,6 @@ static int ip6gre_xmit_other(struct sk_buff *skb, struct net_device *dev)
 		encap_limit = t->parms.encap_limit;
 
 	memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
-	fl6.flowi6_proto = skb->protocol;
 
 	err = ip6gre_xmit2(skb, dev, 0, &fl6, encap_limit, &mtu);
 
-- 
2.4.11


From 7c4d3527e47dfb5f68d8bd53840b0ffc9c961c6c Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Sun, 25 Sep 2016 23:08:31 +0200
Subject: [PATCH 06/27] ipmr, ip6mr: fix scheduling while atomic and a deadlock
 with ipmr_get_route

[ Upstream commit 2cf750704bb6d7ed8c7d732e071dd1bc890ea5e8 ]

Since the commit below the ipmr/ip6mr rtnl_unicast() code uses the portid
instead of the previous dst_pid which was copied from in_skb's portid.
Since the skb is new the portid is 0 at that point so the packets are sent
to the kernel and we get scheduling while atomic or a deadlock (depending
on where it happens) by trying to acquire rtnl two times.
Also since this is RTM_GETROUTE, it can be triggered by a normal user.

Here's the sleeping while atomic trace:
[ 7858.212557] BUG: sleeping function called from invalid context at kernel/locking/mutex.c:620
[ 7858.212748] in_atomic(): 1, irqs_disabled(): 0, pid: 0, name: swapper/0
[ 7858.212881] 2 locks held by swapper/0/0:
[ 7858.213013]  #0:  (((&mrt->ipmr_expire_timer))){+.-...}, at: [<ffffffff810fbbf5>] call_timer_fn+0x5/0x350
[ 7858.213422]  #1:  (mfc_unres_lock){+.....}, at: [<ffffffff8161e005>] ipmr_expire_process+0x25/0x130
[ 7858.213807] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.8.0-rc7+ #179
[ 7858.213934] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.7.5-20140531_083030-gandalf 04/01/2014
[ 7858.214108]  0000000000000000 ffff88005b403c50 ffffffff813a7804 0000000000000000
[ 7858.214412]  ffffffff81a1338e ffff88005b403c78 ffffffff810a4a72 ffffffff81a1338e
[ 7858.214716]  000000000000026c 0000000000000000 ffff88005b403ca8 ffffffff810a4b9f
[ 7858.215251] Call Trace:
[ 7858.215412]  <IRQ>  [<ffffffff813a7804>] dump_stack+0x85/0xc1
[ 7858.215662]  [<ffffffff810a4a72>] ___might_sleep+0x192/0x250
[ 7858.215868]  [<ffffffff810a4b9f>] __might_sleep+0x6f/0x100
[ 7858.216072]  [<ffffffff8165bea3>] mutex_lock_nested+0x33/0x4d0
[ 7858.216279]  [<ffffffff815a7a5f>] ? netlink_lookup+0x25f/0x460
[ 7858.216487]  [<ffffffff8157474b>] rtnetlink_rcv+0x1b/0x40
[ 7858.216687]  [<ffffffff815a9a0c>] netlink_unicast+0x19c/0x260
[ 7858.216900]  [<ffffffff81573c70>] rtnl_unicast+0x20/0x30
[ 7858.217128]  [<ffffffff8161cd39>] ipmr_destroy_unres+0xa9/0xf0
[ 7858.217351]  [<ffffffff8161e06f>] ipmr_expire_process+0x8f/0x130
[ 7858.217581]  [<ffffffff8161dfe0>] ? ipmr_net_init+0x180/0x180
[ 7858.217785]  [<ffffffff8161dfe0>] ? ipmr_net_init+0x180/0x180
[ 7858.217990]  [<ffffffff810fbc95>] call_timer_fn+0xa5/0x350
[ 7858.218192]  [<ffffffff810fbbf5>] ? call_timer_fn+0x5/0x350
[ 7858.218415]  [<ffffffff8161dfe0>] ? ipmr_net_init+0x180/0x180
[ 7858.218656]  [<ffffffff810fde10>] run_timer_softirq+0x260/0x640
[ 7858.218865]  [<ffffffff8166379b>] ? __do_softirq+0xbb/0x54f
[ 7858.219068]  [<ffffffff816637c8>] __do_softirq+0xe8/0x54f
[ 7858.219269]  [<ffffffff8107a948>] irq_exit+0xb8/0xc0
[ 7858.219463]  [<ffffffff81663452>] smp_apic_timer_interrupt+0x42/0x50
[ 7858.219678]  [<ffffffff816625bc>] apic_timer_interrupt+0x8c/0xa0
[ 7858.219897]  <EOI>  [<ffffffff81055f16>] ? native_safe_halt+0x6/0x10
[ 7858.220165]  [<ffffffff810d64dd>] ? trace_hardirqs_on+0xd/0x10
[ 7858.220373]  [<ffffffff810298e3>] default_idle+0x23/0x190
[ 7858.220574]  [<ffffffff8102a20f>] arch_cpu_idle+0xf/0x20
[ 7858.220790]  [<ffffffff810c9f8c>] default_idle_call+0x4c/0x60
[ 7858.221016]  [<ffffffff810ca33b>] cpu_startup_entry+0x39b/0x4d0
[ 7858.221257]  [<ffffffff8164f995>] rest_init+0x135/0x140
[ 7858.221469]  [<ffffffff81f83014>] start_kernel+0x50e/0x51b
[ 7858.221670]  [<ffffffff81f82120>] ? early_idt_handler_array+0x120/0x120
[ 7858.221894]  [<ffffffff81f8243f>] x86_64_start_reservations+0x2a/0x2c
[ 7858.222113]  [<ffffffff81f8257c>] x86_64_start_kernel+0x13b/0x14a

Fixes: 2942e9005056 ("[RTNETLINK]: Use rtnl_unicast() for rtnetlink unicasts")
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/mroute.h  | 2 +-
 include/linux/mroute6.h | 2 +-
 net/ipv4/ipmr.c         | 3 ++-
 net/ipv4/route.c        | 3 ++-
 net/ipv6/ip6mr.c        | 5 +++--
 net/ipv6/route.c        | 4 +++-
 6 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/include/linux/mroute.h b/include/linux/mroute.h
index 79aaa9f..d5277fc 100644
--- a/include/linux/mroute.h
+++ b/include/linux/mroute.h
@@ -103,5 +103,5 @@ struct mfc_cache {
 struct rtmsg;
 extern int ipmr_get_route(struct net *net, struct sk_buff *skb,
 			  __be32 saddr, __be32 daddr,
-			  struct rtmsg *rtm, int nowait);
+			  struct rtmsg *rtm, int nowait, u32 portid);
 #endif
diff --git a/include/linux/mroute6.h b/include/linux/mroute6.h
index 66982e7..f831155 100644
--- a/include/linux/mroute6.h
+++ b/include/linux/mroute6.h
@@ -115,7 +115,7 @@ struct mfc6_cache {
 
 struct rtmsg;
 extern int ip6mr_get_route(struct net *net, struct sk_buff *skb,
-			   struct rtmsg *rtm, int nowait);
+			   struct rtmsg *rtm, int nowait, u32 portid);
 
 #ifdef CONFIG_IPV6_MROUTE
 extern struct sock *mroute6_socket(struct net *net, struct sk_buff *skb);
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 9d1e555..8e77786 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2192,7 +2192,7 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
 
 int ipmr_get_route(struct net *net, struct sk_buff *skb,
 		   __be32 saddr, __be32 daddr,
-		   struct rtmsg *rtm, int nowait)
+		   struct rtmsg *rtm, int nowait, u32 portid)
 {
 	struct mfc_cache *cache;
 	struct mr_table *mrt;
@@ -2237,6 +2237,7 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb,
 			return -ENOMEM;
 		}
 
+		NETLINK_CB(skb2).portid = portid;
 		skb_push(skb2, sizeof(struct iphdr));
 		skb_reset_network_header(skb2);
 		iph = ip_hdr(skb2);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index b050cf9..8533a75 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2492,7 +2492,8 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src, u32 table_id,
 		    IPV4_DEVCONF_ALL(net, MC_FORWARDING)) {
 			int err = ipmr_get_route(net, skb,
 						 fl4->saddr, fl4->daddr,
-						 r, nowait);
+						 r, nowait, portid);
+
 			if (err <= 0) {
 				if (!nowait) {
 					if (err == 0)
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index e207cb2..d9843e5 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -2276,8 +2276,8 @@ static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
 	return 1;
 }
 
-int ip6mr_get_route(struct net *net,
-		    struct sk_buff *skb, struct rtmsg *rtm, int nowait)
+int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm,
+		    int nowait, u32 portid)
 {
 	int err;
 	struct mr6_table *mrt;
@@ -2322,6 +2322,7 @@ int ip6mr_get_route(struct net *net,
 			return -ENOMEM;
 		}
 
+		NETLINK_CB(skb2).portid = portid;
 		skb_reset_transport_header(skb2);
 
 		skb_put(skb2, sizeof(struct ipv6hdr));
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 5af2cca..dbffc9d 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3140,7 +3140,9 @@ static int rt6_fill_node(struct net *net,
 	if (iif) {
 #ifdef CONFIG_IPV6_MROUTE
 		if (ipv6_addr_is_multicast(&rt->rt6i_dst.addr)) {
-			int err = ip6mr_get_route(net, skb, rtm, nowait);
+			int err = ip6mr_get_route(net, skb, rtm, nowait,
+						  portid);
+
 			if (err <= 0) {
 				if (!nowait) {
 					if (err == 0)
-- 
2.4.11


From ef1a6053d3749e225e3484450dea7f80d00ad589 Mon Sep 17 00:00:00 2001
From: Milton Miller <miltonm@us.ibm.com>
Date: Thu, 29 Sep 2016 13:24:08 -0300
Subject: [PATCH 07/27] tg3: Avoid NULL pointer dereference in
 tg3_io_error_detected()

[ Upstream commit 1b0ff89852d79354e8a091c81a88df21f5aa9f0a ]

While the driver is probing the adapter, an error may occur before the
netdev structure is allocated and attached to pci_dev. In this case,
not only netdev isn't available, but the tg3 private structure is also
not available as it is just math from the NULL pointer, so dereferences
must be skipped.

The following trace is seen when the error is triggered:

  [1.402247] Unable to handle kernel paging request for data at address 0x00001a99
  [1.402410] Faulting instruction address: 0xc0000000007e33f8
  [1.402450] Oops: Kernel access of bad area, sig: 11 [#1]
  [1.402481] SMP NR_CPUS=2048 NUMA PowerNV
  [1.402513] Modules linked in:
  [1.402545] CPU: 0 PID: 651 Comm: eehd Not tainted 4.4.0-36-generic #55-Ubuntu
  [1.402591] task: c000001fe4e42a20 ti: c000001fe4e88000 task.ti: c000001fe4e88000
  [1.402742] NIP: c0000000007e33f8 LR: c0000000007e3164 CTR: c000000000595ea0
  [1.402787] REGS: c000001fe4e8b790 TRAP: 0300   Not tainted  (4.4.0-36-generic)
  [1.402832] MSR: 9000000100009033 <SF,HV,EE,ME,IR,DR,RI,LE>  CR: 28000422  XER: 20000000
  [1.403058] CFAR: c000000000008468 DAR: 0000000000001a99 DSISR: 42000000 SOFTE: 1
  GPR00: c0000000007e3164 c000001fe4e8ba10 c0000000015c5e00 0000000000000000
  GPR04: 0000000000000001 0000000000000000 0000000000000039 0000000000000299
  GPR08: 0000000000000000 0000000000000001 c000001fe4e88000 0000000000000006
  GPR12: 0000000000000000 c00000000fb40000 c0000000000e6558 c000003ca1bffd00
  GPR16: 0000000000000000 0000000000000000 0000000000000000 0000000000000000
  GPR20: 0000000000000000 0000000000000000 0000000000000000 c000000000d52768
  GPR24: c000000000d52740 0000000000000100 c000003ca1b52000 0000000000000002
  GPR28: 0000000000000900 0000000000000000 c00000000152a0c0 c000003ca1b52000
  [1.404226] NIP [c0000000007e33f8] tg3_io_error_detected+0x308/0x340
  [1.404265] LR [c0000000007e3164] tg3_io_error_detected+0x74/0x340

This patch avoids the NULL pointer dereference by moving the access after
the netdev NULL pointer check on tg3_io_error_detected(). Also, we add a
check for netdev being NULL on tg3_io_resume() [suggested by Michael Chan].

Fixes: 0486a063b1ff ("tg3: prevent ifup/ifdown during PCI error recovery")
Fixes: dfc8f370316b ("net/tg3: Release IRQs on permanent error")
Tested-by: Guilherme G. Piccoli <gpiccoli@linux.vnet.ibm.com>
Signed-off-by: Milton Miller <miltonm@us.ibm.com>
Signed-off-by: Guilherme G. Piccoli <gpiccoli@linux.vnet.ibm.com>
Acked-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/tg3.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index ca5ac5d..49056c3 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -18142,14 +18142,14 @@ static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev,
 
 	rtnl_lock();
 
-	/* We needn't recover from permanent error */
-	if (state == pci_channel_io_frozen)
-		tp->pcierr_recovery = true;
-
 	/* We probably don't have netdev yet */
 	if (!netdev || !netif_running(netdev))
 		goto done;
 
+	/* We needn't recover from permanent error */
+	if (state == pci_channel_io_frozen)
+		tp->pcierr_recovery = true;
+
 	tg3_phy_stop(tp);
 
 	tg3_netif_stop(tp);
@@ -18246,7 +18246,7 @@ static void tg3_io_resume(struct pci_dev *pdev)
 
 	rtnl_lock();
 
-	if (!netif_running(netdev))
+	if (!netdev || !netif_running(netdev))
 		goto done;
 
 	tg3_full_lock(tp, 0);
-- 
2.4.11


From 9bb9439dbd7cdcb081c89294bad8f53523cd4361 Mon Sep 17 00:00:00 2001
From: Gavin Schenk <g.schenk@eckelmann.de>
Date: Fri, 30 Sep 2016 11:46:10 +0200
Subject: [PATCH 08/27] net: fec: set mac address unconditionally
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit b82d44d78480faff7456e9e0999acb9d38666057 ]

If the mac address origin is not dt, you can only safely assign a mac
address after "link up" of the device. If the link is off the clocks are
disabled and because of issues assigning registers when clocks are off the
new mac address cannot be written in .ndo_set_mac_address() on some soc's.
This fix sets the mac address unconditionally in fec_restart(...) and
ensures consistency between fec registers and the network layer.

Signed-off-by: Gavin Schenk <g.schenk@eckelmann.de>
Acked-by: Fugang Duan <fugang.duan@nxp.com>
Acked-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Fixes: 9638d19e4816 ("net: fec: add netif status check before set mac address")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_main.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index f6147ff..ab71604 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -944,11 +944,11 @@ fec_restart(struct net_device *ndev)
 	 * enet-mac reset will reset mac address registers too,
 	 * so need to reconfigure it.
 	 */
-	if (fep->quirks & FEC_QUIRK_ENET_MAC) {
-		memcpy(&temp_mac, ndev->dev_addr, ETH_ALEN);
-		writel(cpu_to_be32(temp_mac[0]), fep->hwp + FEC_ADDR_LOW);
-		writel(cpu_to_be32(temp_mac[1]), fep->hwp + FEC_ADDR_HIGH);
-	}
+	memcpy(&temp_mac, ndev->dev_addr, ETH_ALEN);
+	writel((__force u32)cpu_to_be32(temp_mac[0]),
+	       fep->hwp + FEC_ADDR_LOW);
+	writel((__force u32)cpu_to_be32(temp_mac[1]),
+	       fep->hwp + FEC_ADDR_HIGH);
 
 	/* Clear any outstanding interrupt. */
 	writel(0xffffffff, fep->hwp + FEC_IEVENT);
-- 
2.4.11


From 7104c277a297adcb9779a0f90895923df4765135 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 30 Sep 2016 16:56:45 +0200
Subject: [PATCH 09/27] net: pktgen: fix pkt_size

[ Upstream commit 63d75463c91a5b5be7c0aca11ceb45ea5a0ae81d ]

The commit 879c7220e828 ("net: pktgen: Observe needed_headroom
of the device") increased the 'pkt_overhead' field value by
LL_RESERVED_SPACE.
As a side effect the generated packet size, computed as:

	/* Eth + IPh + UDPh + mpls */
	datalen = pkt_dev->cur_pkt_size - 14 - 20 - 8 -
		  pkt_dev->pkt_overhead;

is decreased by the same value.
The above changed slightly the behavior of existing pktgen users,
and made the procfs interface somewhat inconsistent.
Fix it by restoring the previous pkt_overhead value and using
LL_RESERVED_SPACE as extralen in skb allocation.
Also, change pktgen_alloc_skb() to only partially reserve
the headroom to allow the caller to prefetch from ll header
start.

v1 -> v2:
 - fixed some typos in the comments

Fixes: 879c7220e828 ("net: pktgen: Observe needed_headroom of the device")
Suggested-by: Ben Greear <greearb@candelatech.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/pktgen.c | 21 ++++++++++-----------
 1 file changed, 10 insertions(+), 11 deletions(-)

diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 4da4d51..cd79415 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -2278,7 +2278,7 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until)
 
 static inline void set_pkt_overhead(struct pktgen_dev *pkt_dev)
 {
-	pkt_dev->pkt_overhead = LL_RESERVED_SPACE(pkt_dev->odev);
+	pkt_dev->pkt_overhead = 0;
 	pkt_dev->pkt_overhead += pkt_dev->nr_labels*sizeof(u32);
 	pkt_dev->pkt_overhead += VLAN_TAG_SIZE(pkt_dev);
 	pkt_dev->pkt_overhead += SVLAN_TAG_SIZE(pkt_dev);
@@ -2769,13 +2769,13 @@ static void pktgen_finalize_skb(struct pktgen_dev *pkt_dev, struct sk_buff *skb,
 }
 
 static struct sk_buff *pktgen_alloc_skb(struct net_device *dev,
-					struct pktgen_dev *pkt_dev,
-					unsigned int extralen)
+					struct pktgen_dev *pkt_dev)
 {
+	unsigned int extralen = LL_RESERVED_SPACE(dev);
 	struct sk_buff *skb = NULL;
-	unsigned int size = pkt_dev->cur_pkt_size + 64 + extralen +
-			    pkt_dev->pkt_overhead;
+	unsigned int size;
 
+	size = pkt_dev->cur_pkt_size + 64 + extralen + pkt_dev->pkt_overhead;
 	if (pkt_dev->flags & F_NODE) {
 		int node = pkt_dev->node >= 0 ? pkt_dev->node : numa_node_id();
 
@@ -2788,8 +2788,9 @@ static struct sk_buff *pktgen_alloc_skb(struct net_device *dev,
 		 skb = __netdev_alloc_skb(dev, size, GFP_NOWAIT);
 	}
 
+	/* the caller pre-fetches from skb->data and reserves for the mac hdr */
 	if (likely(skb))
-		skb_reserve(skb, LL_RESERVED_SPACE(dev));
+		skb_reserve(skb, extralen - 16);
 
 	return skb;
 }
@@ -2822,16 +2823,14 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev,
 	mod_cur_headers(pkt_dev);
 	queue_map = pkt_dev->cur_queue_map;
 
-	datalen = (odev->hard_header_len + 16) & ~0xf;
-
-	skb = pktgen_alloc_skb(odev, pkt_dev, datalen);
+	skb = pktgen_alloc_skb(odev, pkt_dev);
 	if (!skb) {
 		sprintf(pkt_dev->result, "No memory");
 		return NULL;
 	}
 
 	prefetchw(skb->data);
-	skb_reserve(skb, datalen);
+	skb_reserve(skb, 16);
 
 	/*  Reserve for ethernet and IP header  */
 	eth = (__u8 *) skb_push(skb, 14);
@@ -2951,7 +2950,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev,
 	mod_cur_headers(pkt_dev);
 	queue_map = pkt_dev->cur_queue_map;
 
-	skb = pktgen_alloc_skb(odev, pkt_dev, 16);
+	skb = pktgen_alloc_skb(odev, pkt_dev);
 	if (!skb) {
 		sprintf(pkt_dev->result, "No memory");
 		return NULL;
-- 
2.4.11


From 2d5af4be57792aa3f304aefe5bee0138c8790b22 Mon Sep 17 00:00:00 2001
From: Shmulik Ladkani <shmulik.ladkani@gmail.com>
Date: Thu, 29 Sep 2016 12:10:40 +0300
Subject: [PATCH 10/27] net/sched: act_vlan: Push skb->data to mac_header prior
 calling skb_vlan_*() functions

[ Upstream commit f39acc84aad10710e89835c60d3b6694c43a8dd9 ]

Generic skb_vlan_push/skb_vlan_pop functions don't properly handle the
case where the input skb data pointer does not point at the mac header:

- They're doing push/pop, but fail to properly unwind data back to its
  original location.
  For example, in the skb_vlan_push case, any subsequent
  'skb_push(skb, skb->mac_len)' calls make the skb->data point 4 bytes
  BEFORE start of frame, leading to bogus frames that may be transmitted.

- They update rcsum per the added/removed 4 bytes tag.
  Alas if data is originally after the vlan/eth headers, then these
  bytes were already pulled out of the csum.

OTOH calling skb_vlan_push/skb_vlan_pop with skb->data at mac_header
present no issues.

act_vlan is the only caller to skb_vlan_*() that has skb->data pointing
at network header (upon ingress).
Other calles (ovs, bpf) already adjust skb->data at mac_header.

This patch fixes act_vlan to point to the mac_header prior calling
skb_vlan_*() functions, as other callers do.

Signed-off-by: Shmulik Ladkani <shmulik.ladkani@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Pravin Shelar <pshelar@ovn.org>
Cc: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h | 9 +++++++++
 net/sched/act_vlan.c      | 9 +++++++++
 2 files changed, 18 insertions(+)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 86df083..e5bba89 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -408,6 +408,15 @@ bool tcf_destroy(struct tcf_proto *tp, bool force);
 void tcf_destroy_chain(struct tcf_proto __rcu **fl);
 int skb_do_redirect(struct sk_buff *);
 
+static inline bool skb_at_tc_ingress(const struct sk_buff *skb)
+{
+#ifdef CONFIG_NET_CLS_ACT
+	return G_TC_AT(skb->tc_verd) & AT_INGRESS;
+#else
+	return false;
+#endif
+}
+
 /* Reset all TX qdiscs greater then index of a device.  */
 static inline void qdisc_reset_all_tx_gt(struct net_device *dev, unsigned int i)
 {
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 796785e..d7edba4 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -33,6 +33,12 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a,
 	bstats_update(&v->tcf_bstats, skb);
 	action = v->tcf_action;
 
+	/* Ensure 'data' points at mac_header prior calling vlan manipulating
+	 * functions.
+	 */
+	if (skb_at_tc_ingress(skb))
+		skb_push_rcsum(skb, skb->mac_len);
+
 	switch (v->tcfv_action) {
 	case TCA_VLAN_ACT_POP:
 		err = skb_vlan_pop(skb);
@@ -54,6 +60,9 @@ drop:
 	action = TC_ACT_SHOT;
 	v->tcf_qstats.drops++;
 unlock:
+	if (skb_at_tc_ingress(skb))
+		skb_pull_rcsum(skb, skb->mac_len);
+
 	spin_unlock(&v->tcf_lock);
 	return action;
 }
-- 
2.4.11


From f782ae098223878d7910059422789a84ebf944ac Mon Sep 17 00:00:00 2001
From: Andrew Collins <acollins@cradlepoint.com>
Date: Mon, 3 Oct 2016 13:43:02 -0600
Subject: [PATCH 11/27] net: Add netdev all_adj_list refcnt propagation to fix
 panic

[ Upstream commit 93409033ae653f1c9a949202fb537ab095b2092f ]

This is a respin of a patch to fix a relatively easily reproducible kernel
panic related to the all_adj_list handling for netdevs in recent kernels.

The following sequence of commands will reproduce the issue:

ip link add link eth0 name eth0.100 type vlan id 100
ip link add link eth0 name eth0.200 type vlan id 200
ip link add name testbr type bridge
ip link set eth0.100 master testbr
ip link set eth0.200 master testbr
ip link add link testbr mac0 type macvlan
ip link delete dev testbr

This creates an upper/lower tree of (excuse the poor ASCII art):

            /---eth0.100-eth0
mac0-testbr-
            \---eth0.200-eth0

When testbr is deleted, the all_adj_lists are walked, and eth0 is deleted twice from
the mac0 list. Unfortunately, during setup in __netdev_upper_dev_link, only one
reference to eth0 is added, so this results in a panic.

This change adds reference count propagation so things are handled properly.

Matthias Schiffer reported a similar crash in batman-adv:

https://github.com/freifunk-gluon/gluon/issues/680
https://www.open-mesh.org/issues/247

which this patch also seems to resolve.

Signed-off-by: Andrew Collins <acollins@cradlepoint.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 68 ++++++++++++++++++++++++++++++++--------------------------
 1 file changed, 37 insertions(+), 31 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 0989fea..5d9ec04 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5204,6 +5204,7 @@ static inline bool netdev_adjacent_is_neigh_list(struct net_device *dev,
 
 static int __netdev_adjacent_dev_insert(struct net_device *dev,
 					struct net_device *adj_dev,
+					u16 ref_nr,
 					struct list_head *dev_list,
 					void *private, bool master)
 {
@@ -5213,7 +5214,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev,
 	adj = __netdev_find_adj(adj_dev, dev_list);
 
 	if (adj) {
-		adj->ref_nr++;
+		adj->ref_nr += ref_nr;
 		return 0;
 	}
 
@@ -5223,7 +5224,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev,
 
 	adj->dev = adj_dev;
 	adj->master = master;
-	adj->ref_nr = 1;
+	adj->ref_nr = ref_nr;
 	adj->private = private;
 	dev_hold(adj_dev);
 
@@ -5262,6 +5263,7 @@ free_adj:
 
 static void __netdev_adjacent_dev_remove(struct net_device *dev,
 					 struct net_device *adj_dev,
+					 u16 ref_nr,
 					 struct list_head *dev_list)
 {
 	struct netdev_adjacent *adj;
@@ -5274,10 +5276,10 @@ static void __netdev_adjacent_dev_remove(struct net_device *dev,
 		BUG();
 	}
 
-	if (adj->ref_nr > 1) {
-		pr_debug("%s to %s ref_nr-- = %d\n", dev->name, adj_dev->name,
-			 adj->ref_nr-1);
-		adj->ref_nr--;
+	if (adj->ref_nr > ref_nr) {
+		pr_debug("%s to %s ref_nr-%d = %d\n", dev->name, adj_dev->name,
+			 ref_nr, adj->ref_nr-ref_nr);
+		adj->ref_nr -= ref_nr;
 		return;
 	}
 
@@ -5296,21 +5298,22 @@ static void __netdev_adjacent_dev_remove(struct net_device *dev,
 
 static int __netdev_adjacent_dev_link_lists(struct net_device *dev,
 					    struct net_device *upper_dev,
+					    u16 ref_nr,
 					    struct list_head *up_list,
 					    struct list_head *down_list,
 					    void *private, bool master)
 {
 	int ret;
 
-	ret = __netdev_adjacent_dev_insert(dev, upper_dev, up_list, private,
-					   master);
+	ret = __netdev_adjacent_dev_insert(dev, upper_dev, ref_nr, up_list,
+					   private, master);
 	if (ret)
 		return ret;
 
-	ret = __netdev_adjacent_dev_insert(upper_dev, dev, down_list, private,
-					   false);
+	ret = __netdev_adjacent_dev_insert(upper_dev, dev, ref_nr, down_list,
+					   private, false);
 	if (ret) {
-		__netdev_adjacent_dev_remove(dev, upper_dev, up_list);
+		__netdev_adjacent_dev_remove(dev, upper_dev, ref_nr, up_list);
 		return ret;
 	}
 
@@ -5318,9 +5321,10 @@ static int __netdev_adjacent_dev_link_lists(struct net_device *dev,
 }
 
 static int __netdev_adjacent_dev_link(struct net_device *dev,
-				      struct net_device *upper_dev)
+				      struct net_device *upper_dev,
+				      u16 ref_nr)
 {
-	return __netdev_adjacent_dev_link_lists(dev, upper_dev,
+	return __netdev_adjacent_dev_link_lists(dev, upper_dev, ref_nr,
 						&dev->all_adj_list.upper,
 						&upper_dev->all_adj_list.lower,
 						NULL, false);
@@ -5328,17 +5332,19 @@ static int __netdev_adjacent_dev_link(struct net_device *dev,
 
 static void __netdev_adjacent_dev_unlink_lists(struct net_device *dev,
 					       struct net_device *upper_dev,
+					       u16 ref_nr,
 					       struct list_head *up_list,
 					       struct list_head *down_list)
 {
-	__netdev_adjacent_dev_remove(dev, upper_dev, up_list);
-	__netdev_adjacent_dev_remove(upper_dev, dev, down_list);
+	__netdev_adjacent_dev_remove(dev, upper_dev, ref_nr, up_list);
+	__netdev_adjacent_dev_remove(upper_dev, dev, ref_nr, down_list);
 }
 
 static void __netdev_adjacent_dev_unlink(struct net_device *dev,
-					 struct net_device *upper_dev)
+					 struct net_device *upper_dev,
+					 u16 ref_nr)
 {
-	__netdev_adjacent_dev_unlink_lists(dev, upper_dev,
+	__netdev_adjacent_dev_unlink_lists(dev, upper_dev, ref_nr,
 					   &dev->all_adj_list.upper,
 					   &upper_dev->all_adj_list.lower);
 }
@@ -5347,17 +5353,17 @@ static int __netdev_adjacent_dev_link_neighbour(struct net_device *dev,
 						struct net_device *upper_dev,
 						void *private, bool master)
 {
-	int ret = __netdev_adjacent_dev_link(dev, upper_dev);
+	int ret = __netdev_adjacent_dev_link(dev, upper_dev, 1);
 
 	if (ret)
 		return ret;
 
-	ret = __netdev_adjacent_dev_link_lists(dev, upper_dev,
+	ret = __netdev_adjacent_dev_link_lists(dev, upper_dev, 1,
 					       &dev->adj_list.upper,
 					       &upper_dev->adj_list.lower,
 					       private, master);
 	if (ret) {
-		__netdev_adjacent_dev_unlink(dev, upper_dev);
+		__netdev_adjacent_dev_unlink(dev, upper_dev, 1);
 		return ret;
 	}
 
@@ -5367,8 +5373,8 @@ static int __netdev_adjacent_dev_link_neighbour(struct net_device *dev,
 static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev,
 						   struct net_device *upper_dev)
 {
-	__netdev_adjacent_dev_unlink(dev, upper_dev);
-	__netdev_adjacent_dev_unlink_lists(dev, upper_dev,
+	__netdev_adjacent_dev_unlink(dev, upper_dev, 1);
+	__netdev_adjacent_dev_unlink_lists(dev, upper_dev, 1,
 					   &dev->adj_list.upper,
 					   &upper_dev->adj_list.lower);
 }
@@ -5420,7 +5426,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 		list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) {
 			pr_debug("Interlinking %s with %s, non-neighbour\n",
 				 i->dev->name, j->dev->name);
-			ret = __netdev_adjacent_dev_link(i->dev, j->dev);
+			ret = __netdev_adjacent_dev_link(i->dev, j->dev, i->ref_nr);
 			if (ret)
 				goto rollback_mesh;
 		}
@@ -5430,7 +5436,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 	list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) {
 		pr_debug("linking %s's upper device %s with %s\n",
 			 upper_dev->name, i->dev->name, dev->name);
-		ret = __netdev_adjacent_dev_link(dev, i->dev);
+		ret = __netdev_adjacent_dev_link(dev, i->dev, i->ref_nr);
 		if (ret)
 			goto rollback_upper_mesh;
 	}
@@ -5439,7 +5445,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 	list_for_each_entry(i, &dev->all_adj_list.lower, list) {
 		pr_debug("linking %s's lower device %s with %s\n", dev->name,
 			 i->dev->name, upper_dev->name);
-		ret = __netdev_adjacent_dev_link(i->dev, upper_dev);
+		ret = __netdev_adjacent_dev_link(i->dev, upper_dev, i->ref_nr);
 		if (ret)
 			goto rollback_lower_mesh;
 	}
@@ -5453,7 +5459,7 @@ rollback_lower_mesh:
 	list_for_each_entry(i, &dev->all_adj_list.lower, list) {
 		if (i == to_i)
 			break;
-		__netdev_adjacent_dev_unlink(i->dev, upper_dev);
+		__netdev_adjacent_dev_unlink(i->dev, upper_dev, i->ref_nr);
 	}
 
 	i = NULL;
@@ -5463,7 +5469,7 @@ rollback_upper_mesh:
 	list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) {
 		if (i == to_i)
 			break;
-		__netdev_adjacent_dev_unlink(dev, i->dev);
+		__netdev_adjacent_dev_unlink(dev, i->dev, i->ref_nr);
 	}
 
 	i = j = NULL;
@@ -5475,7 +5481,7 @@ rollback_mesh:
 		list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) {
 			if (i == to_i && j == to_j)
 				break;
-			__netdev_adjacent_dev_unlink(i->dev, j->dev);
+			__netdev_adjacent_dev_unlink(i->dev, j->dev, i->ref_nr);
 		}
 		if (i == to_i)
 			break;
@@ -5559,16 +5565,16 @@ void netdev_upper_dev_unlink(struct net_device *dev,
 	 */
 	list_for_each_entry(i, &dev->all_adj_list.lower, list)
 		list_for_each_entry(j, &upper_dev->all_adj_list.upper, list)
-			__netdev_adjacent_dev_unlink(i->dev, j->dev);
+			__netdev_adjacent_dev_unlink(i->dev, j->dev, i->ref_nr);
 
 	/* remove also the devices itself from lower/upper device
 	 * list
 	 */
 	list_for_each_entry(i, &dev->all_adj_list.lower, list)
-		__netdev_adjacent_dev_unlink(i->dev, upper_dev);
+		__netdev_adjacent_dev_unlink(i->dev, upper_dev, i->ref_nr);
 
 	list_for_each_entry(i, &upper_dev->all_adj_list.upper, list)
-		__netdev_adjacent_dev_unlink(dev, i->dev);
+		__netdev_adjacent_dev_unlink(dev, i->dev, i->ref_nr);
 
 	call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev,
 				      &changeupper_info.info);
-- 
2.4.11


From 72316dc7407c34bbe325f51d98716c47fe9b0d3a Mon Sep 17 00:00:00 2001
From: Anoob Soman <anoob.soman@citrix.com>
Date: Wed, 5 Oct 2016 15:12:54 +0100
Subject: [PATCH 12/27] packet: call fanout_release, while UNREGISTERING a
 netdev

[ Upstream commit 6664498280cf17a59c3e7cf1a931444c02633ed1 ]

If a socket has FANOUT sockopt set, a new proto_hook is registered
as part of fanout_add(). When processing a NETDEV_UNREGISTER event in
af_packet, __fanout_unlink is called for all sockets, but prot_hook which was
registered as part of fanout_add is not removed. Call fanout_release, on a
NETDEV_UNREGISTER, which removes prot_hook and removes fanout from the
fanout_list.

This fixes BUG_ON(!list_empty(&dev->ptype_specific)) in netdev_run_todo()

Signed-off-by: Anoob Soman <anoob.soman@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index a86f26d..ea11156 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3855,6 +3855,7 @@ static int packet_notifier(struct notifier_block *this,
 				}
 				if (msg == NETDEV_UNREGISTER) {
 					packet_cached_dev_reset(po);
+					fanout_release(sk);
 					po->ifindex = -1;
 					if (po->prot_hook.dev)
 						dev_put(po->prot_hook.dev);
-- 
2.4.11


From 266dc378ffec0d3151c05efc3f14dbb3efd5d529 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 6 Oct 2016 04:13:18 +0900
Subject: [PATCH 13/27] netlink: do not enter direct reclaim from
 netlink_dump()

[ Upstream commit d35c99ff77ecb2eb239731b799386f3b3637a31e ]

Since linux-3.15, netlink_dump() can use up to 16384 bytes skb
allocations.

Due to struct skb_shared_info ~320 bytes overhead, we end up using
order-3 (on x86) page allocations, that might trigger direct reclaim and
add stress.

The intent was really to attempt a large allocation but immediately
fallback to a smaller one (order-1 on x86) in case of memory stress.

On recent kernels (linux-4.4), we can remove __GFP_DIRECT_RECLAIM to
meet the goal. Old kernels would need to remove __GFP_WAIT

While we are at it, since we do an order-3 allocation, allow to use
all the allocated bytes instead of 16384 to reduce syscalls during
large dumps.

iproute2 already uses 32KB recvmsg() buffer sizes.

Alexei provided an initial patch downsizing to SKB_WITH_OVERHEAD(16384)

Fixes: 9063e21fb026 ("netlink: autosize skb lengthes")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Alexei Starovoitov <ast@kernel.org>
Cc: Greg Thelen <gthelen@google.com>
Reviewed-by: Greg Rose <grose@lightfleet.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 7a5fa0c..28fc283 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2557,7 +2557,7 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	/* Record the max length of recvmsg() calls for future allocations */
 	nlk->max_recvmsg_len = max(nlk->max_recvmsg_len, len);
 	nlk->max_recvmsg_len = min_t(size_t, nlk->max_recvmsg_len,
-				     16384);
+				     SKB_WITH_OVERHEAD(32768));
 
 	copied = data_skb->len;
 	if (len < copied) {
@@ -2810,14 +2810,13 @@ static int netlink_dump(struct sock *sk)
 	if (alloc_min_size < nlk->max_recvmsg_len) {
 		alloc_size = nlk->max_recvmsg_len;
 		skb = netlink_alloc_skb(sk, alloc_size, nlk->portid,
-					GFP_KERNEL |
-					__GFP_NOWARN |
-					__GFP_NORETRY);
+					(GFP_KERNEL & ~__GFP_DIRECT_RECLAIM) |
+					__GFP_NOWARN | __GFP_NORETRY);
 	}
 	if (!skb) {
 		alloc_size = alloc_min_size;
 		skb = netlink_alloc_skb(sk, alloc_size, nlk->portid,
-					GFP_KERNEL);
+					(GFP_KERNEL & ~__GFP_DIRECT_RECLAIM));
 	}
 	if (!skb)
 		goto errout_skb;
-- 
2.4.11


From f83f689c2271c4ffbd569eb75b2b427f712a73fd Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 12 Oct 2016 19:01:45 +0200
Subject: [PATCH 14/27] ipv6: tcp: restore IP6CB for pktoptions skbs

[ Upstream commit 8ce48623f0cf3d632e32448411feddccb693d351 ]

Baozeng Ding reported following KASAN splat :

BUG: KASAN: use-after-free in ip6_datagram_recv_specific_ctl+0x13f1/0x15c0 at addr ffff880029c84ec8
Read of size 1 by task poc/25548
Call Trace:
 [<ffffffff82cf43c9>] dump_stack+0x12e/0x185 /lib/dump_stack.c:15
 [<     inline     >] print_address_description /mm/kasan/report.c:204
 [<ffffffff817ced3b>] kasan_report_error+0x48b/0x4b0 /mm/kasan/report.c:283
 [<     inline     >] kasan_report /mm/kasan/report.c:303
 [<ffffffff817ced9e>] __asan_report_load1_noabort+0x3e/0x40 /mm/kasan/report.c:321
 [<ffffffff85c71da1>] ip6_datagram_recv_specific_ctl+0x13f1/0x15c0 /net/ipv6/datagram.c:687
 [<ffffffff85c734c3>] ip6_datagram_recv_ctl+0x33/0x40
 [<ffffffff85c0b07c>] do_ipv6_getsockopt.isra.4+0xaec/0x2150
 [<ffffffff85c0c7f6>] ipv6_getsockopt+0x116/0x230
 [<ffffffff859b5a12>] tcp_getsockopt+0x82/0xd0 /net/ipv4/tcp.c:3035
 [<ffffffff855fb385>] sock_common_getsockopt+0x95/0xd0 /net/core/sock.c:2647
 [<     inline     >] SYSC_getsockopt /net/socket.c:1776
 [<ffffffff855f8ba2>] SyS_getsockopt+0x142/0x230 /net/socket.c:1758
 [<ffffffff8685cdc5>] entry_SYSCALL_64_fastpath+0x23/0xc6
Memory state around the buggy address:
 ffff880029c84d80: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
 ffff880029c84e00: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
> ffff880029c84e80: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
                                              ^
 ffff880029c84f00: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
 ffff880029c84f80: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff

He also provided a syzkaller reproducer.

Issue is that ip6_datagram_recv_specific_ctl() expects to find IP6CB
data that was moved at a different place in tcp_v6_rcv()

This patch moves tcp_v6_restore_cb() up and calls it from
tcp_v6_do_rcv() when np->pktoptions is set.

Fixes: 971f10eca186 ("tcp: better TCP_SKB_CB layout to reduce cache line misses")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Baozeng Ding <sploving1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/tcp_ipv6.c | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 2d81e2f..fbd521f 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1179,6 +1179,16 @@ out:
 	return NULL;
 }
 
+static void tcp_v6_restore_cb(struct sk_buff *skb)
+{
+	/* We need to move header back to the beginning if xfrm6_policy_check()
+	 * and tcp_v6_fill_cb() are going to be called again.
+	 * ip6_datagram_recv_specific_ctl() also expects IP6CB to be there.
+	 */
+	memmove(IP6CB(skb), &TCP_SKB_CB(skb)->header.h6,
+		sizeof(struct inet6_skb_parm));
+}
+
 /* The socket must have it's spinlock held when we get
  * here, unless it is a TCP_LISTEN socket.
  *
@@ -1308,6 +1318,7 @@ ipv6_pktoptions:
 			np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb));
 		if (ipv6_opt_accepted(sk, opt_skb, &TCP_SKB_CB(opt_skb)->header.h6)) {
 			skb_set_owner_r(opt_skb, sk);
+			tcp_v6_restore_cb(opt_skb);
 			opt_skb = xchg(&np->pktoptions, opt_skb);
 		} else {
 			__kfree_skb(opt_skb);
@@ -1341,15 +1352,6 @@ static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr,
 	TCP_SKB_CB(skb)->sacked = 0;
 }
 
-static void tcp_v6_restore_cb(struct sk_buff *skb)
-{
-	/* We need to move header back to the beginning if xfrm6_policy_check()
-	 * and tcp_v6_fill_cb() are going to be called again.
-	 */
-	memmove(IP6CB(skb), &TCP_SKB_CB(skb)->header.h6,
-		sizeof(struct inet6_skb_parm));
-}
-
 static int tcp_v6_rcv(struct sk_buff *skb)
 {
 	const struct tcphdr *th;
-- 
2.4.11


From 73035391366ad15958c923fb65c7e145fd999bde Mon Sep 17 00:00:00 2001
From: Vadim Fedorenko <junk@yandex-team.ru>
Date: Tue, 11 Oct 2016 22:47:20 +0300
Subject: [PATCH 15/27] ip6_tunnel: fix ip6_tnl_lookup

[ Upstream commit 68d00f332e0ba7f60f212be74ede290c9f873bc5 ]

The commit ea3dc9601bda ("ip6_tunnel: Add support for wildcard tunnel
endpoints.") introduces support for wildcards in tunnels endpoints,
but in some rare circumstances ip6_tnl_lookup selects wrong tunnel
interface relying only on source or destination address of the packet
and not checking presence of wildcard in tunnels endpoints. Later in
ip6_tnl_rcv this packets can be dicarded because of difference in
ipproto even if fallback device have proper ipproto configuration.

This patch adds checks of wildcard endpoint in tunnel avoiding such
behavior

Fixes: ea3dc9601bda ("ip6_tunnel: Add support for wildcard tunnel endpoints.")
Signed-off-by: Vadim Fedorenko <junk@yandex-team.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 3991b21..e887888 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -246,6 +246,7 @@ ip6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_
 	hash = HASH(&any, local);
 	for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
 		if (ipv6_addr_equal(local, &t->parms.laddr) &&
+		    ipv6_addr_any(&t->parms.raddr) &&
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
@@ -253,6 +254,7 @@ ip6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_
 	hash = HASH(remote, &any);
 	for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
 		if (ipv6_addr_equal(remote, &t->parms.raddr) &&
+		    ipv6_addr_any(&t->parms.laddr) &&
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
-- 
2.4.11


From 5d490cb2af50335b98d8253e3b6d74817a461901 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Wed, 12 Oct 2016 10:10:40 +0200
Subject: [PATCH 16/27] ipv6: correctly add local routes when lo goes up

[ Upstream commit a220445f9f4382c36a53d8ef3e08165fa27f7e2c ]

The goal of the patch is to fix this scenario:
 ip link add dummy1 type dummy
 ip link set dummy1 up
 ip link set lo down ; ip link set lo up

After that sequence, the local route to the link layer address of dummy1 is
not there anymore.

When the loopback is set down, all local routes are deleted by
addrconf_ifdown()/rt6_ifdown(). At this time, the rt6_info entry still
exists, because the corresponding idev has a reference on it. After the rcu
grace period, dst_rcu_free() is called, and thus ___dst_free(), which will
set obsolete to DST_OBSOLETE_DEAD.

In this case, init_loopback() is called before dst_rcu_free(), thus
obsolete is still sets to something <= 0. So, the function doesn't add the
route again. To avoid that race, let's check the rt6 refcnt instead.

Fixes: 25fb6ca4ed9c ("net IPv6 : Fix broken IPv6 routing table after loopback down-up")
Fixes: a881ae1f625c ("ipv6: don't call addrconf_dst_alloc again when enable lo")
Fixes: 33d99113b110 ("ipv6: reallocate addrconf router for ipv6 address when lo device up")
Reported-by: Francesco Santoro <francesco.santoro@6wind.com>
Reported-by: Samuel Gauthier <samuel.gauthier@6wind.com>
CC: Balakumaran Kannan <Balakumaran.Kannan@ap.sony.com>
CC: Maruthi Thotad <Maruthi.Thotad@ap.sony.com>
CC: Sabrina Dubroca <sd@queasysnail.net>
CC: Hannes Frederic Sowa <hannes@stressinduktion.org>
CC: Weilong Chen <chenweilong@huawei.com>
CC: Gao feng <gaofeng@cn.fujitsu.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 036b39e..cb8bb59 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -2916,7 +2916,7 @@ static void init_loopback(struct net_device *dev)
 				 * lo device down, release this obsolete dst and
 				 * reallocate a new router for ifa.
 				 */
-				if (sp_ifa->rt->dst.obsolete > 0) {
+				if (!atomic_read(&sp_ifa->rt->rt6i_ref)) {
 					ip6_rt_put(sp_ifa->rt);
 					sp_ifa->rt = NULL;
 				} else {
-- 
2.4.11


From a8bdd0b8abcbdd4cdf33cb500c1cb5f573466f31 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 15 Oct 2016 17:50:49 +0200
Subject: [PATCH 17/27] net: pktgen: remove rcu locking in pktgen_change_name()

[ Upstream commit 9a0b1e8ba4061778897b544afc898de2163382f7 ]

After Jesper commit back in linux-3.18, we trigger a lockdep
splat in proc_create_data() while allocating memory from
pktgen_change_name().

This patch converts t->if_lock to a mutex, since it is now only
used from control path, and adds proper locking to pktgen_change_name()

1) pktgen_thread_lock to protect the outer loop (iterating threads)
2) t->if_lock to protect the inner loop (iterating devices)

Note that before Jesper patch, pktgen_change_name() was lacking proper
protection, but lockdep was not able to detect the problem.

Fixes: 8788370a1d4b ("pktgen: RCU-ify "if_list" to remove lock in next_to_run()")
Reported-by: John Sperbeck <jsperbeck@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/pktgen.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index cd79415..b632760 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -215,8 +215,8 @@
 #define M_NETIF_RECEIVE 	1	/* Inject packets into stack */
 
 /* If lock -- protects updating of if_list */
-#define   if_lock(t)           spin_lock(&(t->if_lock));
-#define   if_unlock(t)           spin_unlock(&(t->if_lock));
+#define   if_lock(t)           mutex_lock(&(t->if_lock));
+#define   if_unlock(t)           mutex_unlock(&(t->if_lock));
 
 /* Used to help with determining the pkts on receive */
 #define PKTGEN_MAGIC 0xbe9be955
@@ -422,7 +422,7 @@ struct pktgen_net {
 };
 
 struct pktgen_thread {
-	spinlock_t if_lock;		/* for list of devices */
+	struct mutex if_lock;		/* for list of devices */
 	struct list_head if_list;	/* All device here */
 	struct list_head th_list;
 	struct task_struct *tsk;
@@ -2002,11 +2002,13 @@ static void pktgen_change_name(const struct pktgen_net *pn, struct net_device *d
 {
 	struct pktgen_thread *t;
 
+	mutex_lock(&pktgen_thread_lock);
+
 	list_for_each_entry(t, &pn->pktgen_threads, th_list) {
 		struct pktgen_dev *pkt_dev;
 
-		rcu_read_lock();
-		list_for_each_entry_rcu(pkt_dev, &t->if_list, list) {
+		if_lock(t);
+		list_for_each_entry(pkt_dev, &t->if_list, list) {
 			if (pkt_dev->odev != dev)
 				continue;
 
@@ -2021,8 +2023,9 @@ static void pktgen_change_name(const struct pktgen_net *pn, struct net_device *d
 				       dev->name);
 			break;
 		}
-		rcu_read_unlock();
+		if_unlock(t);
 	}
+	mutex_unlock(&pktgen_thread_lock);
 }
 
 static int pktgen_device_event(struct notifier_block *unused,
@@ -3726,7 +3729,7 @@ static int __net_init pktgen_create_thread(int cpu, struct pktgen_net *pn)
 		return -ENOMEM;
 	}
 
-	spin_lock_init(&t->if_lock);
+	mutex_init(&t->if_lock);
 	t->cpu = cpu;
 
 	INIT_LIST_HEAD(&t->if_list);
-- 
2.4.11


From 69ab4e91063ae673c649645c30aea6a38d3f91f2 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Tue, 18 Oct 2016 18:09:48 +0200
Subject: [PATCH 18/27] bridge: multicast: restore perm router ports on
 multicast enable

[ Upstream commit 7cb3f9214dfa443c1ccc2be637dcc6344cc203f0 ]

Satish reported a problem with the perm multicast router ports not getting
reenabled after some series of events, in particular if it happens that the
multicast snooping has been disabled and the port goes to disabled state
then it will be deleted from the router port list, but if it moves into
non-disabled state it will not be re-added because the mcast snooping is
still disabled, and enabling snooping later does nothing.

Here are the steps to reproduce, setup br0 with snooping enabled and eth1
added as a perm router (multicast_router = 2):
1. $ echo 0 > /sys/class/net/br0/bridge/multicast_snooping
2. $ ip l set eth1 down
^ This step deletes the interface from the router list
3. $ ip l set eth1 up
^ This step does not add it again because mcast snooping is disabled
4. $ echo 1 > /sys/class/net/br0/bridge/multicast_snooping
5. $ bridge -d -s mdb show
<empty>

At this point we have mcast enabled and eth1 as a perm router (value = 2)
but it is not in the router list which is incorrect.

After this change:
1. $ echo 0 > /sys/class/net/br0/bridge/multicast_snooping
2. $ ip l set eth1 down
^ This step deletes the interface from the router list
3. $ ip l set eth1 up
^ This step does not add it again because mcast snooping is disabled
4. $ echo 1 > /sys/class/net/br0/bridge/multicast_snooping
5. $ bridge -d -s mdb show
router ports on br0: eth1

Note: we can directly do br_multicast_enable_port for all because the
querier timer already has checks for the port state and will simply
expire if it's in blocking/disabled. See the comment added by
commit 9aa66382163e7 ("bridge: multicast: add a comment to
br_port_state_selection about blocking state")

Fixes: 561f1103a2b7 ("bridge: Add multicast_snooping sysfs toggle")
Reported-by: Satish Ashok <sashok@cumulusnetworks.com>
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c | 23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 9542e84..d80c15d 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -951,13 +951,12 @@ static void br_multicast_enable(struct bridge_mcast_own_query *query)
 		mod_timer(&query->timer, jiffies);
 }
 
-void br_multicast_enable_port(struct net_bridge_port *port)
+static void __br_multicast_enable_port(struct net_bridge_port *port)
 {
 	struct net_bridge *br = port->br;
 
-	spin_lock(&br->multicast_lock);
 	if (br->multicast_disabled || !netif_running(br->dev))
-		goto out;
+		return;
 
 	br_multicast_enable(&port->ip4_own_query);
 #if IS_ENABLED(CONFIG_IPV6)
@@ -965,8 +964,14 @@ void br_multicast_enable_port(struct net_bridge_port *port)
 #endif
 	if (port->multicast_router == 2 && hlist_unhashed(&port->rlist))
 		br_multicast_add_router(br, port);
+}
 
-out:
+void br_multicast_enable_port(struct net_bridge_port *port)
+{
+	struct net_bridge *br = port->br;
+
+	spin_lock(&br->multicast_lock);
+	__br_multicast_enable_port(port);
 	spin_unlock(&br->multicast_lock);
 }
 
@@ -1905,8 +1910,9 @@ static void br_multicast_start_querier(struct net_bridge *br,
 
 int br_multicast_toggle(struct net_bridge *br, unsigned long val)
 {
-	int err = 0;
 	struct net_bridge_mdb_htable *mdb;
+	struct net_bridge_port *port;
+	int err = 0;
 
 	spin_lock_bh(&br->multicast_lock);
 	if (br->multicast_disabled == !val)
@@ -1934,10 +1940,9 @@ rollback:
 			goto rollback;
 	}
 
-	br_multicast_start_querier(br, &br->ip4_own_query);
-#if IS_ENABLED(CONFIG_IPV6)
-	br_multicast_start_querier(br, &br->ip6_own_query);
-#endif
+	br_multicast_open(br);
+	list_for_each_entry(port, &br->port_list, list)
+		__br_multicast_enable_port(port);
 
 unlock:
 	spin_unlock_bh(&br->multicast_lock);
-- 
2.4.11


From 1c91025f75be61f59c0e00d276c0216bb9d07294 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Tue, 18 Oct 2016 18:59:34 +0200
Subject: [PATCH 19/27] rtnetlink: Add rtnexthop offload flag to compare mask

[ Upstream commit 85dda4e5b0ee1f5b4e8cc93d39e475006bc61ccd ]

The offload flag is a status flag and should not be used by
FIB semantics for comparison.

Fixes: 37ed9493699c ("rtnetlink: add RTNH_F_EXTERNAL flag for fib offload")
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/rtnetlink.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 123a5af..fa3b343 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -343,7 +343,7 @@ struct rtnexthop {
 #define RTNH_F_OFFLOAD		8	/* offloaded route */
 #define RTNH_F_LINKDOWN		16	/* carrier-down on nexthop */
 
-#define RTNH_COMPARE_MASK	(RTNH_F_DEAD | RTNH_F_LINKDOWN)
+#define RTNH_COMPARE_MASK	(RTNH_F_DEAD | RTNH_F_LINKDOWN | RTNH_F_OFFLOAD)
 
 /* Macros to handle hexthops */
 
-- 
2.4.11


From 1fd7fc21338733616e3e5d2bb17eee27d41c0871 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Thu, 20 Oct 2016 15:58:02 +0200
Subject: [PATCH 20/27] net: add recursion limit to GRO
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit fcd91dd449867c6bfe56a81cabba76b829fd05cd ]

Currently, GRO can do unlimited recursion through the gro_receive
handlers.  This was fixed for tunneling protocols by limiting tunnel GRO
to one level with encap_mark, but both VLAN and TEB still have this
problem.  Thus, the kernel is vulnerable to a stack overflow, if we
receive a packet composed entirely of VLAN headers.

This patch adds a recursion counter to the GRO layer to prevent stack
overflow.  When a gro_receive function hits the recursion limit, GRO is
aborted for this skb and it is processed normally.  This recursion
counter is put in the GRO CB, but could be turned into a percpu counter
if we run out of space in the CB.

Thanks to Vladimír Beneš <vbenes@redhat.com> for the initial bug report.

Fixes: CVE-2016-7039
Fixes: 9b174d88c257 ("net: Add Transparent Ethernet Bridging GRO support.")
Fixes: 66e5133f19e9 ("vlan: Add GRO support for non hardware accelerated vlan")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Jiri Benc <jbenc@redhat.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c      |  2 +-
 drivers/net/vxlan.c       |  2 +-
 include/linux/netdevice.h | 40 +++++++++++++++++++++++++++++++++++++++-
 net/8021q/vlan.c          |  2 +-
 net/core/dev.c            |  1 +
 net/ethernet/eth.c        |  2 +-
 net/ipv4/af_inet.c        |  2 +-
 net/ipv4/fou.c            |  4 ++--
 net/ipv4/gre_offload.c    |  2 +-
 net/ipv4/udp_offload.c    |  4 ++--
 net/ipv6/ip6_offload.c    |  2 +-
 11 files changed, 51 insertions(+), 12 deletions(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 69e31e2..4827c69 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -440,7 +440,7 @@ static struct sk_buff **geneve_gro_receive(struct sk_buff **head,
 
 	skb_gro_pull(skb, gh_len);
 	skb_gro_postpull_rcsum(skb, gh, gh_len);
-	pp = ptype->callbacks.gro_receive(head, skb);
+	pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb);
 
 out_unlock:
 	rcu_read_unlock();
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 0037809..6fa8e16 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -593,7 +593,7 @@ static struct sk_buff **vxlan_gro_receive(struct sk_buff **head,
 		}
 	}
 
-	pp = eth_gro_receive(head, skb);
+	pp = call_gro_receive(eth_gro_receive, head, skb);
 
 out:
 	skb_gro_remcsum_cleanup(skb, &grc);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 12b4d54..9d60257 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2003,7 +2003,10 @@ struct napi_gro_cb {
 	/* Used in foo-over-udp, set in udp[46]_gro_receive */
 	u8	is_ipv6:1;
 
-	/* 7 bit hole */
+	/* Number of gro_receive callbacks this packet already went through */
+	u8 recursion_counter:4;
+
+	/* 3 bit hole */
 
 	/* used to support CHECKSUM_COMPLETE for tunneling protocols */
 	__wsum	csum;
@@ -2014,6 +2017,25 @@ struct napi_gro_cb {
 
 #define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb)
 
+#define GRO_RECURSION_LIMIT 15
+static inline int gro_recursion_inc_test(struct sk_buff *skb)
+{
+	return ++NAPI_GRO_CB(skb)->recursion_counter == GRO_RECURSION_LIMIT;
+}
+
+typedef struct sk_buff **(*gro_receive_t)(struct sk_buff **, struct sk_buff *);
+static inline struct sk_buff **call_gro_receive(gro_receive_t cb,
+						struct sk_buff **head,
+						struct sk_buff *skb)
+{
+	if (unlikely(gro_recursion_inc_test(skb))) {
+		NAPI_GRO_CB(skb)->flush |= 1;
+		return NULL;
+	}
+
+	return cb(head, skb);
+}
+
 struct packet_type {
 	__be16			type;	/* This is really htons(ether_type). */
 	struct net_device	*dev;	/* NULL is wildcarded here	     */
@@ -2059,6 +2081,22 @@ struct udp_offload {
 	struct udp_offload_callbacks callbacks;
 };
 
+typedef struct sk_buff **(*gro_receive_udp_t)(struct sk_buff **,
+					      struct sk_buff *,
+					      struct udp_offload *);
+static inline struct sk_buff **call_gro_receive_udp(gro_receive_udp_t cb,
+						    struct sk_buff **head,
+						    struct sk_buff *skb,
+						    struct udp_offload *uoff)
+{
+	if (unlikely(gro_recursion_inc_test(skb))) {
+		NAPI_GRO_CB(skb)->flush |= 1;
+		return NULL;
+	}
+
+	return cb(head, skb, uoff);
+}
+
 /* often modified stats are per cpu, other are shared (netdev->stats) */
 struct pcpu_sw_netstats {
 	u64     rx_packets;
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index d2cd9de..ad8d6e6 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -659,7 +659,7 @@ static struct sk_buff **vlan_gro_receive(struct sk_buff **head,
 
 	skb_gro_pull(skb, sizeof(*vhdr));
 	skb_gro_postpull_rcsum(skb, vhdr, sizeof(*vhdr));
-	pp = ptype->callbacks.gro_receive(head, skb);
+	pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb);
 
 out_unlock:
 	rcu_read_unlock();
diff --git a/net/core/dev.c b/net/core/dev.c
index 5d9ec04..d200a7c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4240,6 +4240,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 		NAPI_GRO_CB(skb)->flush = 0;
 		NAPI_GRO_CB(skb)->free = 0;
 		NAPI_GRO_CB(skb)->encap_mark = 0;
+		NAPI_GRO_CB(skb)->recursion_counter = 0;
 		NAPI_GRO_CB(skb)->gro_remcsum_start = 0;
 
 		/* Setup for GRO checksum validation */
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index 9e63f25..de85d4e 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -436,7 +436,7 @@ struct sk_buff **eth_gro_receive(struct sk_buff **head,
 
 	skb_gro_pull(skb, sizeof(*eh));
 	skb_gro_postpull_rcsum(skb, eh, sizeof(*eh));
-	pp = ptype->callbacks.gro_receive(head, skb);
+	pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb);
 
 out_unlock:
 	rcu_read_unlock();
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 1a5c1ca..afc18e9 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1372,7 +1372,7 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
 	skb_gro_pull(skb, sizeof(*iph));
 	skb_set_transport_header(skb, skb_gro_offset(skb));
 
-	pp = ops->callbacks.gro_receive(head, skb);
+	pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
 
 out_unlock:
 	rcu_read_unlock();
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 08d7de5..08d8ee1 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -201,7 +201,7 @@ static struct sk_buff **fou_gro_receive(struct sk_buff **head,
 	if (!ops || !ops->callbacks.gro_receive)
 		goto out_unlock;
 
-	pp = ops->callbacks.gro_receive(head, skb);
+	pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
 
 out_unlock:
 	rcu_read_unlock();
@@ -360,7 +360,7 @@ static struct sk_buff **gue_gro_receive(struct sk_buff **head,
 	if (WARN_ON_ONCE(!ops || !ops->callbacks.gro_receive))
 		goto out_unlock;
 
-	pp = ops->callbacks.gro_receive(head, skb);
+	pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
 
 out_unlock:
 	rcu_read_unlock();
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index e603004..79ae0d7 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -219,7 +219,7 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head,
 	/* Adjusted NAPI_GRO_CB(skb)->csum after skb_gro_pull()*/
 	skb_gro_postpull_rcsum(skb, greh, grehlen);
 
-	pp = ptype->callbacks.gro_receive(head, skb);
+	pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb);
 
 out_unlock:
 	rcu_read_unlock();
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 0e36e56..6396f1c 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -339,8 +339,8 @@ unflush:
 	skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */
 	skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr));
 	NAPI_GRO_CB(skb)->proto = uo_priv->offload->ipproto;
-	pp = uo_priv->offload->callbacks.gro_receive(head, skb,
-						     uo_priv->offload);
+	pp = call_gro_receive_udp(uo_priv->offload->callbacks.gro_receive,
+				  head, skb, uo_priv->offload);
 
 out_unlock:
 	rcu_read_unlock();
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 82e9f30..efe6268 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -247,7 +247,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 
 	skb_gro_postpull_rcsum(skb, iph, nlen);
 
-	pp = ops->callbacks.gro_receive(head, skb);
+	pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
 
 out_unlock:
 	rcu_read_unlock();
-- 
2.4.11


From c577387b66260bde3b36ad9ebbfc4c467898e79a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 20 Oct 2016 10:26:48 -0700
Subject: [PATCH 21/27] ipv4: disable BH in set_ping_group_range()

[ Upstream commit a681574c99be23e4d20b769bf0e543239c364af5 ]

In commit 4ee3bd4a8c746 ("ipv4: disable BH when changing ip local port
range") Cong added BH protection in set_local_port_range() but missed
that same fix was needed in set_ping_group_range()

Fixes: b8f1a55639e6 ("udp: Add function to make source port for UDP tunnels")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Eric Salo <salo@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/sysctl_net_ipv4.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index a0bd7a5..9d82611 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -110,10 +110,10 @@ static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t hig
 	kgid_t *data = table->data;
 	struct net *net =
 		container_of(table->data, struct net, ipv4.ping_group_range.range);
-	write_seqlock(&net->ipv4.ip_local_ports.lock);
+	write_seqlock_bh(&net->ipv4.ip_local_ports.lock);
 	data[0] = low;
 	data[1] = high;
-	write_sequnlock(&net->ipv4.ip_local_ports.lock);
+	write_sequnlock_bh(&net->ipv4.ip_local_ports.lock);
 }
 
 /* Validate changes from /proc interface. */
-- 
2.4.11


From 2af37f91bf44d54b371222a175137ba7bb70ce3f Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Thu, 20 Oct 2016 14:19:46 -0700
Subject: [PATCH 22/27] ipv4: use the right lock for ping_group_range

[ Upstream commit 396a30cce15d084b2b1a395aa6d515c3d559c674 ]

This reverts commit a681574c99be23e4d20b769bf0e543239c364af5
("ipv4: disable BH in set_ping_group_range()") because we never
read ping_group_range in BH context (unlike local_port_range).

Then, since we already have a lock for ping_group_range, those
using ip_local_ports.lock for ping_group_range are clearly typos.

We might consider to share a same lock for both ping_group_range
and local_port_range w.r.t. space saving, but that should be for
net-next.

Fixes: a681574c99be ("ipv4: disable BH in set_ping_group_range()")
Fixes: ba6b918ab234 ("ping: move ping_group_range out of CONFIG_SYSCTL")
Cc: Eric Dumazet <edumazet@google.com>
Cc: Eric Salo <salo@google.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/sysctl_net_ipv4.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 9d82611..70fb352 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -97,11 +97,11 @@ static void inet_get_ping_group_range_table(struct ctl_table *table, kgid_t *low
 		container_of(table->data, struct net, ipv4.ping_group_range.range);
 	unsigned int seq;
 	do {
-		seq = read_seqbegin(&net->ipv4.ip_local_ports.lock);
+		seq = read_seqbegin(&net->ipv4.ping_group_range.lock);
 
 		*low = data[0];
 		*high = data[1];
-	} while (read_seqretry(&net->ipv4.ip_local_ports.lock, seq));
+	} while (read_seqretry(&net->ipv4.ping_group_range.lock, seq));
 }
 
 /* Update system visible IP port range */
@@ -110,10 +110,10 @@ static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t hig
 	kgid_t *data = table->data;
 	struct net *net =
 		container_of(table->data, struct net, ipv4.ping_group_range.range);
-	write_seqlock_bh(&net->ipv4.ip_local_ports.lock);
+	write_seqlock(&net->ipv4.ping_group_range.lock);
 	data[0] = low;
 	data[1] = high;
-	write_sequnlock_bh(&net->ipv4.ip_local_ports.lock);
+	write_sequnlock(&net->ipv4.ping_group_range.lock);
 }
 
 /* Validate changes from /proc interface. */
-- 
2.4.11


From 8e122500aa6bb712c91cd006001265af7682f728 Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jslaby@suse.cz>
Date: Fri, 21 Oct 2016 14:13:24 +0200
Subject: [PATCH 23/27] net: sctp, forbid negative length

[ Upstream commit a4b8e71b05c27bae6bad3bdecddbc6b68a3ad8cf ]

Most of getsockopt handlers in net/sctp/socket.c check len against
sizeof some structure like:
        if (len < sizeof(int))
                return -EINVAL;

On the first look, the check seems to be correct. But since len is int
and sizeof returns size_t, int gets promoted to unsigned size_t too. So
the test returns false for negative lengths. Yes, (-1 < sizeof(long)) is
false.

Fix this in sctp by explicitly checking len < 0 before any getsockopt
handler is called.

Note that sctp_getsockopt_events already handled the negative case.
Since we added the < 0 check elsewhere, this one can be removed.

If not checked, this is the result:
UBSAN: Undefined behaviour in ../mm/page_alloc.c:2722:19
shift exponent 52 is too large for 32-bit type 'int'
CPU: 1 PID: 24535 Comm: syz-executor Not tainted 4.8.1-0-syzkaller #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.1-0-gb3ef39f-prebuilt.qemu-project.org 04/01/2014
 0000000000000000 ffff88006d99f2a8 ffffffffb2f7bdea 0000000041b58ab3
 ffffffffb4363c14 ffffffffb2f7bcde ffff88006d99f2d0 ffff88006d99f270
 0000000000000000 0000000000000000 0000000000000034 ffffffffb5096422
Call Trace:
 [<ffffffffb3051498>] ? __ubsan_handle_shift_out_of_bounds+0x29c/0x300
...
 [<ffffffffb273f0e4>] ? kmalloc_order+0x24/0x90
 [<ffffffffb27416a4>] ? kmalloc_order_trace+0x24/0x220
 [<ffffffffb2819a30>] ? __kmalloc+0x330/0x540
 [<ffffffffc18c25f4>] ? sctp_getsockopt_local_addrs+0x174/0xca0 [sctp]
 [<ffffffffc18d2bcd>] ? sctp_getsockopt+0x10d/0x1b0 [sctp]
 [<ffffffffb37c1219>] ? sock_common_getsockopt+0xb9/0x150
 [<ffffffffb37be2f5>] ? SyS_getsockopt+0x1a5/0x270

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Cc: Vlad Yasevich <vyasevich@gmail.com>
Cc: Neil Horman <nhorman@tuxdriver.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: linux-sctp@vger.kernel.org
Cc: netdev@vger.kernel.org
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index be1489f..402817b 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4371,7 +4371,7 @@ static int sctp_getsockopt_disable_fragments(struct sock *sk, int len,
 static int sctp_getsockopt_events(struct sock *sk, int len, char __user *optval,
 				  int __user *optlen)
 {
-	if (len <= 0)
+	if (len == 0)
 		return -EINVAL;
 	if (len > sizeof(struct sctp_event_subscribe))
 		len = sizeof(struct sctp_event_subscribe);
@@ -5972,6 +5972,9 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname,
 	if (get_user(len, optlen))
 		return -EFAULT;
 
+	if (len < 0)
+		return -EINVAL;
+
 	lock_sock(sk);
 
 	switch (optname) {
-- 
2.4.11


From 976deab686339cfc54f3dcc1d86a98a121dd5846 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 23 Oct 2016 18:03:06 -0700
Subject: [PATCH 24/27] udp: fix IP_CHECKSUM handling

[ Upstream commit 10df8e6152c6c400a563a673e9956320bfce1871 ]

First bug was added in commit ad6f939ab193 ("ip: Add offset parameter to
ip_cmsg_recv") : Tom missed that ipv4 udp messages could be received on
AF_INET6 socket. ip_cmsg_recv(msg, skb) should have been replaced by
ip_cmsg_recv_offset(msg, skb, sizeof(struct udphdr));

Then commit e6afc8ace6dd ("udp: remove headers from UDP packets before
queueing") forgot to adjust the offsets now UDP headers are pulled
before skb are put in receive queue.

Fixes: ad6f939ab193 ("ip: Add offset parameter to ip_cmsg_recv")
Fixes: e6afc8ace6dd ("udp: remove headers from UDP packets before queueing")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Sam Kumar <samanthakumar@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Tested-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h       |  4 ++--
 net/ipv4/ip_sockglue.c | 10 ++++++----
 net/ipv4/udp.c         |  2 +-
 net/ipv6/udp.c         |  3 ++-
 4 files changed, 11 insertions(+), 8 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index 1a98f1c..b450d86 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -553,7 +553,7 @@ int ip_options_rcv_srr(struct sk_buff *skb);
  */
 
 void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb);
-void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb, int offset);
+void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb, int tlen, int offset);
 int ip_cmsg_send(struct net *net, struct msghdr *msg,
 		 struct ipcm_cookie *ipc, bool allow_ipv6);
 int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval,
@@ -575,7 +575,7 @@ void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 dport,
 
 static inline void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb)
 {
-	ip_cmsg_recv_offset(msg, skb, 0);
+	ip_cmsg_recv_offset(msg, skb, 0, 0);
 }
 
 bool icmp_global_allow(void);
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index a501242..9ce2025 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -98,7 +98,7 @@ static void ip_cmsg_recv_retopts(struct msghdr *msg, struct sk_buff *skb)
 }
 
 static void ip_cmsg_recv_checksum(struct msghdr *msg, struct sk_buff *skb,
-				  int offset)
+				  int tlen, int offset)
 {
 	__wsum csum = skb->csum;
 
@@ -106,7 +106,9 @@ static void ip_cmsg_recv_checksum(struct msghdr *msg, struct sk_buff *skb,
 		return;
 
 	if (offset != 0)
-		csum = csum_sub(csum, csum_partial(skb->data, offset, 0));
+		csum = csum_sub(csum,
+				csum_partial(skb->data + tlen,
+					     offset, 0));
 
 	put_cmsg(msg, SOL_IP, IP_CHECKSUM, sizeof(__wsum), &csum);
 }
@@ -152,7 +154,7 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
 }
 
 void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb,
-			 int offset)
+			 int tlen, int offset)
 {
 	struct inet_sock *inet = inet_sk(skb->sk);
 	unsigned int flags = inet->cmsg_flags;
@@ -215,7 +217,7 @@ void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb,
 	}
 
 	if (flags & IP_CMSG_CHECKSUM)
-		ip_cmsg_recv_checksum(msg, skb, offset);
+		ip_cmsg_recv_checksum(msg, skb, tlen, offset);
 }
 EXPORT_SYMBOL(ip_cmsg_recv_offset);
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 0b1ea5a..e9513e3 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1342,7 +1342,7 @@ try_again:
 		*addr_len = sizeof(*sin);
 	}
 	if (inet->cmsg_flags)
-		ip_cmsg_recv_offset(msg, skb, sizeof(struct udphdr));
+		ip_cmsg_recv_offset(msg, skb, sizeof(struct udphdr), off);
 
 	err = copied;
 	if (flags & MSG_TRUNC)
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index e6092bd..dfa85e7 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -498,7 +498,8 @@ try_again:
 
 	if (is_udp4) {
 		if (inet->cmsg_flags)
-			ip_cmsg_recv(msg, skb);
+			ip_cmsg_recv_offset(msg, skb,
+					    sizeof(struct udphdr), off);
 	} else {
 		if (np->rxopt.all)
 			ip6_datagram_recv_specific_ctl(sk, msg, skb);
-- 
2.4.11


From cb0e120501eef92a3f4a4affa9cdb63936be7da9 Mon Sep 17 00:00:00 2001
From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Mon, 24 Oct 2016 20:18:27 -0400
Subject: [PATCH 25/27] net sched filters: fix notification of filter delete
 with proper handle

[ Upstream commit 9ee7837449b3d6f0fcf9132c6b5e5aaa58cc67d4 ]

Daniel says:

While trying out [1][2], I noticed that tc monitor doesn't show the
correct handle on delete:

$ tc monitor
qdisc clsact ffff: dev eno1 parent ffff:fff1
filter dev eno1 ingress protocol all pref 49152 bpf handle 0x2a [...]
deleted filter dev eno1 ingress protocol all pref 49152 bpf handle 0xf3be0c80

some context to explain the above:
The user identity of any tc filter is represented by a 32-bit
identifier encoded in tcm->tcm_handle. Example 0x2a in the bpf filter
above. A user wishing to delete, get or even modify a specific filter
uses this handle to reference it.
Every classifier is free to provide its own semantics for the 32 bit handle.
Example: classifiers like u32 use schemes like 800:1:801 to describe
the semantics of their filters represented as hash table, bucket and
node ids etc.
Classifiers also have internal per-filter representation which is different
from this externally visible identity. Most classifiers set this
internal representation to be a pointer address (which allows fast retrieval
of said filters in their implementations). This internal representation
is referenced with the "fh" variable in the kernel control code.

When a user successfuly deletes a specific filter, by specifying the correct
tcm->tcm_handle, an event is generated to user space which indicates
which specific filter was deleted.

Before this patch, the "fh" value was sent to user space as the identity.
As an example what is shown in the sample bpf filter delete event above
is 0xf3be0c80. This is infact a 32-bit truncation of 0xffff8807f3be0c80
which happens to be a 64-bit memory address of the internal filter
representation (address of the corresponding filter's struct cls_bpf_prog);

After this patch the appropriate user identifiable handle as encoded
in the originating request tcm->tcm_handle is generated in the event.
One of the cardinal rules of netlink rules is to be able to take an
event (such as a delete in this case) and reflect it back to the
kernel and successfully delete the filter. This patch achieves that.

Note, this issue has existed since the original TC action
infrastructure code patch back in 2004 as found in:
https://git.kernel.org/cgit/linux/kernel/git/history/history.git/commit/

[1] http://patchwork.ozlabs.org/patch/682828/
[2] http://patchwork.ozlabs.org/patch/682829/

Fixes: 4e54c4816bfe ("[NET]: Add tc extensions infrastructure.")
Reported-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index a75864d..ecc1904 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -315,7 +315,8 @@ replay:
 			if (err == 0) {
 				struct tcf_proto *next = rtnl_dereference(tp->next);
 
-				tfilter_notify(net, skb, n, tp, fh, RTM_DELTFILTER);
+				tfilter_notify(net, skb, n, tp,
+					       t->tcm_handle, RTM_DELTFILTER);
 				if (tcf_destroy(tp, false))
 					RCU_INIT_POINTER(*back, next);
 			}
-- 
2.4.11


From a244d9f68176659b953ad0af889583cac47b7fe3 Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Tue, 25 Oct 2016 14:27:39 -0200
Subject: [PATCH 26/27] sctp: validate chunk len before actually using it

[ Upstream commit bf911e985d6bbaa328c20c3e05f4eb03de11fdd6 ]

Andrey Konovalov reported that KASAN detected that SCTP was using a slab
beyond the boundaries. It was caused because when handling out of the
blue packets in function sctp_sf_ootb() it was checking the chunk len
only after already processing the first chunk, validating only for the
2nd and subsequent ones.

The fix is to just move the check upwards so it's also validated for the
1st chunk.

Reported-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sm_statefuns.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 22c2bf3..29c7c43 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -3426,6 +3426,12 @@ sctp_disposition_t sctp_sf_ootb(struct net *net,
 			return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
 						  commands);
 
+		/* Report violation if chunk len overflows */
+		ch_end = ((__u8 *)ch) + WORD_ROUND(ntohs(ch->length));
+		if (ch_end > skb_tail_pointer(skb))
+			return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
+						  commands);
+
 		/* Now that we know we at least have a chunk header,
 		 * do things that are type appropriate.
 		 */
@@ -3457,12 +3463,6 @@ sctp_disposition_t sctp_sf_ootb(struct net *net,
 			}
 		}
 
-		/* Report violation if chunk len overflows */
-		ch_end = ((__u8 *)ch) + WORD_ROUND(ntohs(ch->length));
-		if (ch_end > skb_tail_pointer(skb))
-			return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
-						  commands);
-
 		ch = (sctp_chunkhdr_t *) ch_end;
 	} while (ch_end < skb_tail_pointer(skb));
 
-- 
2.4.11


From 94e04f76885e5c29808fed8d05b5e7dd4f8eaf05 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 26 Oct 2016 11:23:07 -0400
Subject: [PATCH 27/27] packet: on direct_xmit, limit tso and csum to supported
 devices

[ Upstream commit 104ba78c98808ae837d1f63aae58c183db5505df ]

When transmitting on a packet socket with PACKET_VNET_HDR and
PACKET_QDISC_BYPASS, validate device support for features requested
in vnet_hdr.

Drop TSO packets sent to devices that do not support TSO or have the
feature disabled. Note that the latter currently do process those
packets correctly, regardless of not advertising the feature.

Because of SKB_GSO_DODGY, it is not sufficient to test device features
with netif_needs_gso. Full validate_xmit_skb is needed.

Switch to software checksum for non-TSO packets that request checksum
offload if that device feature is unsupported or disabled. Note that
similar to the TSO case, device drivers may perform checksum offload
correctly even when not advertising it.

When switching to software checksum, packets hit skb_checksum_help,
which has two BUG_ON checksum not in linear segment. Packet sockets
always allocate at least up to csum_start + csum_off + 2 as linear.

Tested by running github.com/wdebruij/kerneltools/psock_txring_vnet.c

  ethtool -K eth0 tso off tx on
  psock_txring_vnet -d $dst -s $src -i eth0 -l 2000 -n 1 -q -v
  psock_txring_vnet -d $dst -s $src -i eth0 -l 2000 -n 1 -q -v -N

  ethtool -K eth0 tx off
  psock_txring_vnet -d $dst -s $src -i eth0 -l 1000 -n 1 -q -v -G
  psock_txring_vnet -d $dst -s $src -i eth0 -l 1000 -n 1 -q -v -G -N

v2:
  - add EXPORT_SYMBOL_GPL(validate_xmit_skb_list)

Fixes: d346a3fae3ff ("packet: introduce PACKET_QDISC_BYPASS socket option")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c         | 1 +
 net/packet/af_packet.c | 9 ++++-----
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index d200a7c..b3fa4b8 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2836,6 +2836,7 @@ struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *d
 	}
 	return head;
 }
+EXPORT_SYMBOL_GPL(validate_xmit_skb_list);
 
 static void qdisc_pkt_len_init(struct sk_buff *skb)
 {
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index ea11156..34e4fcf 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -249,7 +249,7 @@ static void __fanout_link(struct sock *sk, struct packet_sock *po);
 static int packet_direct_xmit(struct sk_buff *skb)
 {
 	struct net_device *dev = skb->dev;
-	netdev_features_t features;
+	struct sk_buff *orig_skb = skb;
 	struct netdev_queue *txq;
 	int ret = NETDEV_TX_BUSY;
 
@@ -257,9 +257,8 @@ static int packet_direct_xmit(struct sk_buff *skb)
 		     !netif_carrier_ok(dev)))
 		goto drop;
 
-	features = netif_skb_features(skb);
-	if (skb_needs_linearize(skb, features) &&
-	    __skb_linearize(skb))
+	skb = validate_xmit_skb_list(skb, dev);
+	if (skb != orig_skb)
 		goto drop;
 
 	txq = skb_get_tx_queue(dev, skb);
@@ -279,7 +278,7 @@ static int packet_direct_xmit(struct sk_buff *skb)
 	return ret;
 drop:
 	atomic_long_inc(&dev->tx_dropped);
-	kfree_skb(skb);
+	kfree_skb_list(skb);
 	return NET_XMIT_DROP;
 }
 
-- 
2.4.11


[-- Attachment #3: net_48.mbox --]
[-- Type: Application/Octet-Stream, Size: 114209 bytes --]

From efd16cf9a5c038fac030923ab67de619ef3e727a Mon Sep 17 00:00:00 2001
From: Gavin Schenk <g.schenk@eckelmann.de>
Date: Fri, 30 Sep 2016 11:46:10 +0200
Subject: [PATCH 01/34] net: fec: set mac address unconditionally
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit b82d44d78480faff7456e9e0999acb9d38666057 ]

If the mac address origin is not dt, you can only safely assign a mac
address after "link up" of the device. If the link is off the clocks are
disabled and because of issues assigning registers when clocks are off the
new mac address cannot be written in .ndo_set_mac_address() on some soc's.
This fix sets the mac address unconditionally in fec_restart(...) and
ensures consistency between fec registers and the network layer.

Signed-off-by: Gavin Schenk <g.schenk@eckelmann.de>
Acked-by: Fugang Duan <fugang.duan@nxp.com>
Acked-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Fixes: 9638d19e4816 ("net: fec: add netif status check before set mac address")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_main.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 692ee24..f475318 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -913,13 +913,11 @@ fec_restart(struct net_device *ndev)
 	 * enet-mac reset will reset mac address registers too,
 	 * so need to reconfigure it.
 	 */
-	if (fep->quirks & FEC_QUIRK_ENET_MAC) {
-		memcpy(&temp_mac, ndev->dev_addr, ETH_ALEN);
-		writel((__force u32)cpu_to_be32(temp_mac[0]),
-		       fep->hwp + FEC_ADDR_LOW);
-		writel((__force u32)cpu_to_be32(temp_mac[1]),
-		       fep->hwp + FEC_ADDR_HIGH);
-	}
+	memcpy(&temp_mac, ndev->dev_addr, ETH_ALEN);
+	writel((__force u32)cpu_to_be32(temp_mac[0]),
+	       fep->hwp + FEC_ADDR_LOW);
+	writel((__force u32)cpu_to_be32(temp_mac[1]),
+	       fep->hwp + FEC_ADDR_HIGH);
 
 	/* Clear any outstanding interrupt. */
 	writel(0xffffffff, fep->hwp + FEC_IEVENT);
-- 
2.4.11


From ae29ef776f4efde60e62975875acaf7fc8547767 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 30 Sep 2016 16:56:45 +0200
Subject: [PATCH 02/34] net: pktgen: fix pkt_size

[ Upstream commit 63d75463c91a5b5be7c0aca11ceb45ea5a0ae81d ]

The commit 879c7220e828 ("net: pktgen: Observe needed_headroom
of the device") increased the 'pkt_overhead' field value by
LL_RESERVED_SPACE.
As a side effect the generated packet size, computed as:

	/* Eth + IPh + UDPh + mpls */
	datalen = pkt_dev->cur_pkt_size - 14 - 20 - 8 -
		  pkt_dev->pkt_overhead;

is decreased by the same value.
The above changed slightly the behavior of existing pktgen users,
and made the procfs interface somewhat inconsistent.
Fix it by restoring the previous pkt_overhead value and using
LL_RESERVED_SPACE as extralen in skb allocation.
Also, change pktgen_alloc_skb() to only partially reserve
the headroom to allow the caller to prefetch from ll header
start.

v1 -> v2:
 - fixed some typos in the comments

Fixes: 879c7220e828 ("net: pktgen: Observe needed_headroom of the device")
Suggested-by: Ben Greear <greearb@candelatech.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/pktgen.c | 21 ++++++++++-----------
 1 file changed, 10 insertions(+), 11 deletions(-)

diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index bbd118b..5219a9e 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -2286,7 +2286,7 @@ out:
 
 static inline void set_pkt_overhead(struct pktgen_dev *pkt_dev)
 {
-	pkt_dev->pkt_overhead = LL_RESERVED_SPACE(pkt_dev->odev);
+	pkt_dev->pkt_overhead = 0;
 	pkt_dev->pkt_overhead += pkt_dev->nr_labels*sizeof(u32);
 	pkt_dev->pkt_overhead += VLAN_TAG_SIZE(pkt_dev);
 	pkt_dev->pkt_overhead += SVLAN_TAG_SIZE(pkt_dev);
@@ -2777,13 +2777,13 @@ static void pktgen_finalize_skb(struct pktgen_dev *pkt_dev, struct sk_buff *skb,
 }
 
 static struct sk_buff *pktgen_alloc_skb(struct net_device *dev,
-					struct pktgen_dev *pkt_dev,
-					unsigned int extralen)
+					struct pktgen_dev *pkt_dev)
 {
+	unsigned int extralen = LL_RESERVED_SPACE(dev);
 	struct sk_buff *skb = NULL;
-	unsigned int size = pkt_dev->cur_pkt_size + 64 + extralen +
-			    pkt_dev->pkt_overhead;
+	unsigned int size;
 
+	size = pkt_dev->cur_pkt_size + 64 + extralen + pkt_dev->pkt_overhead;
 	if (pkt_dev->flags & F_NODE) {
 		int node = pkt_dev->node >= 0 ? pkt_dev->node : numa_node_id();
 
@@ -2796,8 +2796,9 @@ static struct sk_buff *pktgen_alloc_skb(struct net_device *dev,
 		 skb = __netdev_alloc_skb(dev, size, GFP_NOWAIT);
 	}
 
+	/* the caller pre-fetches from skb->data and reserves for the mac hdr */
 	if (likely(skb))
-		skb_reserve(skb, LL_RESERVED_SPACE(dev));
+		skb_reserve(skb, extralen - 16);
 
 	return skb;
 }
@@ -2830,16 +2831,14 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev,
 	mod_cur_headers(pkt_dev);
 	queue_map = pkt_dev->cur_queue_map;
 
-	datalen = (odev->hard_header_len + 16) & ~0xf;
-
-	skb = pktgen_alloc_skb(odev, pkt_dev, datalen);
+	skb = pktgen_alloc_skb(odev, pkt_dev);
 	if (!skb) {
 		sprintf(pkt_dev->result, "No memory");
 		return NULL;
 	}
 
 	prefetchw(skb->data);
-	skb_reserve(skb, datalen);
+	skb_reserve(skb, 16);
 
 	/*  Reserve for ethernet and IP header  */
 	eth = (__u8 *) skb_push(skb, 14);
@@ -2959,7 +2958,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev,
 	mod_cur_headers(pkt_dev);
 	queue_map = pkt_dev->cur_queue_map;
 
-	skb = pktgen_alloc_skb(odev, pkt_dev, 16);
+	skb = pktgen_alloc_skb(odev, pkt_dev);
 	if (!skb) {
 		sprintf(pkt_dev->result, "No memory");
 		return NULL;
-- 
2.4.11


From 4dff3c224db71654afeb1ffa3d9228ae9884425f Mon Sep 17 00:00:00 2001
From: Shmulik Ladkani <shmulik.ladkani@gmail.com>
Date: Thu, 29 Sep 2016 12:10:40 +0300
Subject: [PATCH 03/34] net/sched: act_vlan: Push skb->data to mac_header prior
 calling skb_vlan_*() functions

[ Upstream commit f39acc84aad10710e89835c60d3b6694c43a8dd9 ]

Generic skb_vlan_push/skb_vlan_pop functions don't properly handle the
case where the input skb data pointer does not point at the mac header:

- They're doing push/pop, but fail to properly unwind data back to its
  original location.
  For example, in the skb_vlan_push case, any subsequent
  'skb_push(skb, skb->mac_len)' calls make the skb->data point 4 bytes
  BEFORE start of frame, leading to bogus frames that may be transmitted.

- They update rcsum per the added/removed 4 bytes tag.
  Alas if data is originally after the vlan/eth headers, then these
  bytes were already pulled out of the csum.

OTOH calling skb_vlan_push/skb_vlan_pop with skb->data at mac_header
present no issues.

act_vlan is the only caller to skb_vlan_*() that has skb->data pointing
at network header (upon ingress).
Other calles (ovs, bpf) already adjust skb->data at mac_header.

This patch fixes act_vlan to point to the mac_header prior calling
skb_vlan_*() functions, as other callers do.

Signed-off-by: Shmulik Ladkani <shmulik.ladkani@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Pravin Shelar <pshelar@ovn.org>
Cc: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_vlan.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 691409d..4ffc6c1 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -36,6 +36,12 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a,
 	bstats_update(&v->tcf_bstats, skb);
 	action = v->tcf_action;
 
+	/* Ensure 'data' points at mac_header prior calling vlan manipulating
+	 * functions.
+	 */
+	if (skb_at_tc_ingress(skb))
+		skb_push_rcsum(skb, skb->mac_len);
+
 	switch (v->tcfv_action) {
 	case TCA_VLAN_ACT_POP:
 		err = skb_vlan_pop(skb);
@@ -57,6 +63,9 @@ drop:
 	action = TC_ACT_SHOT;
 	v->tcf_qstats.drops++;
 unlock:
+	if (skb_at_tc_ingress(skb))
+		skb_pull_rcsum(skb, skb->mac_len);
+
 	spin_unlock(&v->tcf_lock);
 	return action;
 }
-- 
2.4.11


From dccb285acbd26a7f032108a0aa4ae96b2ea63d1a Mon Sep 17 00:00:00 2001
From: Andrew Collins <acollins@cradlepoint.com>
Date: Mon, 3 Oct 2016 13:43:02 -0600
Subject: [PATCH 04/34] net: Add netdev all_adj_list refcnt propagation to fix
 panic

[ Upstream commit 93409033ae653f1c9a949202fb537ab095b2092f ]

This is a respin of a patch to fix a relatively easily reproducible kernel
panic related to the all_adj_list handling for netdevs in recent kernels.

The following sequence of commands will reproduce the issue:

ip link add link eth0 name eth0.100 type vlan id 100
ip link add link eth0 name eth0.200 type vlan id 200
ip link add name testbr type bridge
ip link set eth0.100 master testbr
ip link set eth0.200 master testbr
ip link add link testbr mac0 type macvlan
ip link delete dev testbr

This creates an upper/lower tree of (excuse the poor ASCII art):

            /---eth0.100-eth0
mac0-testbr-
            \---eth0.200-eth0

When testbr is deleted, the all_adj_lists are walked, and eth0 is deleted twice from
the mac0 list. Unfortunately, during setup in __netdev_upper_dev_link, only one
reference to eth0 is added, so this results in a panic.

This change adds reference count propagation so things are handled properly.

Matthias Schiffer reported a similar crash in batman-adv:

https://github.com/freifunk-gluon/gluon/issues/680
https://www.open-mesh.org/issues/247

which this patch also seems to resolve.

Signed-off-by: Andrew Collins <acollins@cradlepoint.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 68 ++++++++++++++++++++++++++++++++--------------------------
 1 file changed, 37 insertions(+), 31 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index ea63120..1da79ef 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5578,6 +5578,7 @@ static inline bool netdev_adjacent_is_neigh_list(struct net_device *dev,
 
 static int __netdev_adjacent_dev_insert(struct net_device *dev,
 					struct net_device *adj_dev,
+					u16 ref_nr,
 					struct list_head *dev_list,
 					void *private, bool master)
 {
@@ -5587,7 +5588,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev,
 	adj = __netdev_find_adj(adj_dev, dev_list);
 
 	if (adj) {
-		adj->ref_nr++;
+		adj->ref_nr += ref_nr;
 		return 0;
 	}
 
@@ -5597,7 +5598,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev,
 
 	adj->dev = adj_dev;
 	adj->master = master;
-	adj->ref_nr = 1;
+	adj->ref_nr = ref_nr;
 	adj->private = private;
 	dev_hold(adj_dev);
 
@@ -5636,6 +5637,7 @@ free_adj:
 
 static void __netdev_adjacent_dev_remove(struct net_device *dev,
 					 struct net_device *adj_dev,
+					 u16 ref_nr,
 					 struct list_head *dev_list)
 {
 	struct netdev_adjacent *adj;
@@ -5648,10 +5650,10 @@ static void __netdev_adjacent_dev_remove(struct net_device *dev,
 		BUG();
 	}
 
-	if (adj->ref_nr > 1) {
-		pr_debug("%s to %s ref_nr-- = %d\n", dev->name, adj_dev->name,
-			 adj->ref_nr-1);
-		adj->ref_nr--;
+	if (adj->ref_nr > ref_nr) {
+		pr_debug("%s to %s ref_nr-%d = %d\n", dev->name, adj_dev->name,
+			 ref_nr, adj->ref_nr-ref_nr);
+		adj->ref_nr -= ref_nr;
 		return;
 	}
 
@@ -5670,21 +5672,22 @@ static void __netdev_adjacent_dev_remove(struct net_device *dev,
 
 static int __netdev_adjacent_dev_link_lists(struct net_device *dev,
 					    struct net_device *upper_dev,
+					    u16 ref_nr,
 					    struct list_head *up_list,
 					    struct list_head *down_list,
 					    void *private, bool master)
 {
 	int ret;
 
-	ret = __netdev_adjacent_dev_insert(dev, upper_dev, up_list, private,
-					   master);
+	ret = __netdev_adjacent_dev_insert(dev, upper_dev, ref_nr, up_list,
+					   private, master);
 	if (ret)
 		return ret;
 
-	ret = __netdev_adjacent_dev_insert(upper_dev, dev, down_list, private,
-					   false);
+	ret = __netdev_adjacent_dev_insert(upper_dev, dev, ref_nr, down_list,
+					   private, false);
 	if (ret) {
-		__netdev_adjacent_dev_remove(dev, upper_dev, up_list);
+		__netdev_adjacent_dev_remove(dev, upper_dev, ref_nr, up_list);
 		return ret;
 	}
 
@@ -5692,9 +5695,10 @@ static int __netdev_adjacent_dev_link_lists(struct net_device *dev,
 }
 
 static int __netdev_adjacent_dev_link(struct net_device *dev,
-				      struct net_device *upper_dev)
+				      struct net_device *upper_dev,
+				      u16 ref_nr)
 {
-	return __netdev_adjacent_dev_link_lists(dev, upper_dev,
+	return __netdev_adjacent_dev_link_lists(dev, upper_dev, ref_nr,
 						&dev->all_adj_list.upper,
 						&upper_dev->all_adj_list.lower,
 						NULL, false);
@@ -5702,17 +5706,19 @@ static int __netdev_adjacent_dev_link(struct net_device *dev,
 
 static void __netdev_adjacent_dev_unlink_lists(struct net_device *dev,
 					       struct net_device *upper_dev,
+					       u16 ref_nr,
 					       struct list_head *up_list,
 					       struct list_head *down_list)
 {
-	__netdev_adjacent_dev_remove(dev, upper_dev, up_list);
-	__netdev_adjacent_dev_remove(upper_dev, dev, down_list);
+	__netdev_adjacent_dev_remove(dev, upper_dev, ref_nr, up_list);
+	__netdev_adjacent_dev_remove(upper_dev, dev, ref_nr, down_list);
 }
 
 static void __netdev_adjacent_dev_unlink(struct net_device *dev,
-					 struct net_device *upper_dev)
+					 struct net_device *upper_dev,
+					 u16 ref_nr)
 {
-	__netdev_adjacent_dev_unlink_lists(dev, upper_dev,
+	__netdev_adjacent_dev_unlink_lists(dev, upper_dev, ref_nr,
 					   &dev->all_adj_list.upper,
 					   &upper_dev->all_adj_list.lower);
 }
@@ -5721,17 +5727,17 @@ static int __netdev_adjacent_dev_link_neighbour(struct net_device *dev,
 						struct net_device *upper_dev,
 						void *private, bool master)
 {
-	int ret = __netdev_adjacent_dev_link(dev, upper_dev);
+	int ret = __netdev_adjacent_dev_link(dev, upper_dev, 1);
 
 	if (ret)
 		return ret;
 
-	ret = __netdev_adjacent_dev_link_lists(dev, upper_dev,
+	ret = __netdev_adjacent_dev_link_lists(dev, upper_dev, 1,
 					       &dev->adj_list.upper,
 					       &upper_dev->adj_list.lower,
 					       private, master);
 	if (ret) {
-		__netdev_adjacent_dev_unlink(dev, upper_dev);
+		__netdev_adjacent_dev_unlink(dev, upper_dev, 1);
 		return ret;
 	}
 
@@ -5741,8 +5747,8 @@ static int __netdev_adjacent_dev_link_neighbour(struct net_device *dev,
 static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev,
 						   struct net_device *upper_dev)
 {
-	__netdev_adjacent_dev_unlink(dev, upper_dev);
-	__netdev_adjacent_dev_unlink_lists(dev, upper_dev,
+	__netdev_adjacent_dev_unlink(dev, upper_dev, 1);
+	__netdev_adjacent_dev_unlink_lists(dev, upper_dev, 1,
 					   &dev->adj_list.upper,
 					   &upper_dev->adj_list.lower);
 }
@@ -5795,7 +5801,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 		list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) {
 			pr_debug("Interlinking %s with %s, non-neighbour\n",
 				 i->dev->name, j->dev->name);
-			ret = __netdev_adjacent_dev_link(i->dev, j->dev);
+			ret = __netdev_adjacent_dev_link(i->dev, j->dev, i->ref_nr);
 			if (ret)
 				goto rollback_mesh;
 		}
@@ -5805,7 +5811,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 	list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) {
 		pr_debug("linking %s's upper device %s with %s\n",
 			 upper_dev->name, i->dev->name, dev->name);
-		ret = __netdev_adjacent_dev_link(dev, i->dev);
+		ret = __netdev_adjacent_dev_link(dev, i->dev, i->ref_nr);
 		if (ret)
 			goto rollback_upper_mesh;
 	}
@@ -5814,7 +5820,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 	list_for_each_entry(i, &dev->all_adj_list.lower, list) {
 		pr_debug("linking %s's lower device %s with %s\n", dev->name,
 			 i->dev->name, upper_dev->name);
-		ret = __netdev_adjacent_dev_link(i->dev, upper_dev);
+		ret = __netdev_adjacent_dev_link(i->dev, upper_dev, i->ref_nr);
 		if (ret)
 			goto rollback_lower_mesh;
 	}
@@ -5832,7 +5838,7 @@ rollback_lower_mesh:
 	list_for_each_entry(i, &dev->all_adj_list.lower, list) {
 		if (i == to_i)
 			break;
-		__netdev_adjacent_dev_unlink(i->dev, upper_dev);
+		__netdev_adjacent_dev_unlink(i->dev, upper_dev, i->ref_nr);
 	}
 
 	i = NULL;
@@ -5842,7 +5848,7 @@ rollback_upper_mesh:
 	list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) {
 		if (i == to_i)
 			break;
-		__netdev_adjacent_dev_unlink(dev, i->dev);
+		__netdev_adjacent_dev_unlink(dev, i->dev, i->ref_nr);
 	}
 
 	i = j = NULL;
@@ -5854,7 +5860,7 @@ rollback_mesh:
 		list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) {
 			if (i == to_i && j == to_j)
 				break;
-			__netdev_adjacent_dev_unlink(i->dev, j->dev);
+			__netdev_adjacent_dev_unlink(i->dev, j->dev, i->ref_nr);
 		}
 		if (i == to_i)
 			break;
@@ -5934,16 +5940,16 @@ void netdev_upper_dev_unlink(struct net_device *dev,
 	 */
 	list_for_each_entry(i, &dev->all_adj_list.lower, list)
 		list_for_each_entry(j, &upper_dev->all_adj_list.upper, list)
-			__netdev_adjacent_dev_unlink(i->dev, j->dev);
+			__netdev_adjacent_dev_unlink(i->dev, j->dev, i->ref_nr);
 
 	/* remove also the devices itself from lower/upper device
 	 * list
 	 */
 	list_for_each_entry(i, &dev->all_adj_list.lower, list)
-		__netdev_adjacent_dev_unlink(i->dev, upper_dev);
+		__netdev_adjacent_dev_unlink(i->dev, upper_dev, i->ref_nr);
 
 	list_for_each_entry(i, &upper_dev->all_adj_list.upper, list)
-		__netdev_adjacent_dev_unlink(dev, i->dev);
+		__netdev_adjacent_dev_unlink(dev, i->dev, i->ref_nr);
 
 	call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev,
 				      &changeupper_info.info);
-- 
2.4.11


From 413e9e99716d00ba7144eefb16a52d11dcadb522 Mon Sep 17 00:00:00 2001
From: Anoob Soman <anoob.soman@citrix.com>
Date: Wed, 5 Oct 2016 15:12:54 +0100
Subject: [PATCH 05/34] packet: call fanout_release, while UNREGISTERING a
 netdev

[ Upstream commit 6664498280cf17a59c3e7cf1a931444c02633ed1 ]

If a socket has FANOUT sockopt set, a new proto_hook is registered
as part of fanout_add(). When processing a NETDEV_UNREGISTER event in
af_packet, __fanout_unlink is called for all sockets, but prot_hook which was
registered as part of fanout_add is not removed. Call fanout_release, on a
NETDEV_UNREGISTER, which removes prot_hook and removes fanout from the
fanout_list.

This fixes BUG_ON(!list_empty(&dev->ptype_specific)) in netdev_run_todo()

Signed-off-by: Anoob Soman <anoob.soman@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 33a4697..11db0d6 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3952,6 +3952,7 @@ static int packet_notifier(struct notifier_block *this,
 				}
 				if (msg == NETDEV_UNREGISTER) {
 					packet_cached_dev_reset(po);
+					fanout_release(sk);
 					po->ifindex = -1;
 					if (po->prot_hook.dev)
 						dev_put(po->prot_hook.dev);
-- 
2.4.11


From 4b43701203c9e1257bc23ea781def57155db19cc Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 6 Oct 2016 04:13:18 +0900
Subject: [PATCH 06/34] netlink: do not enter direct reclaim from
 netlink_dump()

[ Upstream commit d35c99ff77ecb2eb239731b799386f3b3637a31e ]

Since linux-3.15, netlink_dump() can use up to 16384 bytes skb
allocations.

Due to struct skb_shared_info ~320 bytes overhead, we end up using
order-3 (on x86) page allocations, that might trigger direct reclaim and
add stress.

The intent was really to attempt a large allocation but immediately
fallback to a smaller one (order-1 on x86) in case of memory stress.

On recent kernels (linux-4.4), we can remove __GFP_DIRECT_RECLAIM to
meet the goal. Old kernels would need to remove __GFP_WAIT

While we are at it, since we do an order-3 allocation, allow to use
all the allocated bytes instead of 16384 to reduce syscalls during
large dumps.

iproute2 already uses 32KB recvmsg() buffer sizes.

Alexei provided an initial patch downsizing to SKB_WITH_OVERHEAD(16384)

Fixes: 9063e21fb026 ("netlink: autosize skb lengthes")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Alexei Starovoitov <ast@kernel.org>
Cc: Greg Thelen <gthelen@google.com>
Reviewed-by: Greg Rose <grose@lightfleet.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 627f898..62bea45 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1832,7 +1832,7 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	/* Record the max length of recvmsg() calls for future allocations */
 	nlk->max_recvmsg_len = max(nlk->max_recvmsg_len, len);
 	nlk->max_recvmsg_len = min_t(size_t, nlk->max_recvmsg_len,
-				     16384);
+				     SKB_WITH_OVERHEAD(32768));
 
 	copied = data_skb->len;
 	if (len < copied) {
@@ -2083,8 +2083,9 @@ static int netlink_dump(struct sock *sk)
 
 	if (alloc_min_size < nlk->max_recvmsg_len) {
 		alloc_size = nlk->max_recvmsg_len;
-		skb = alloc_skb(alloc_size, GFP_KERNEL |
-					    __GFP_NOWARN | __GFP_NORETRY);
+		skb = alloc_skb(alloc_size,
+				(GFP_KERNEL & ~__GFP_DIRECT_RECLAIM) |
+				__GFP_NOWARN | __GFP_NORETRY);
 	}
 	if (!skb) {
 		alloc_size = alloc_min_size;
-- 
2.4.11


From 0d5887753bc1cbf9500fda6b010d5c8b6467c529 Mon Sep 17 00:00:00 2001
From: Vlad Tsyrklevich <vlad@tsyrklevich.net>
Date: Tue, 11 Oct 2016 15:02:47 +0200
Subject: [PATCH 07/34] drivers/ptp: Fix kernel memory disclosure

[ Upstream commit 02a9079c66341836c4914c33c06a73245060df2e ]

The reserved field precise_offset->rsv is not cleared before being
copied to user space, leaking kernel stack memory. Clear the struct
before it's copied.

Signed-off-by: Vlad Tsyrklevich <vlad@tsyrklevich.net>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/ptp/ptp_chardev.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c
index d637c93..58a97d4 100644
--- a/drivers/ptp/ptp_chardev.c
+++ b/drivers/ptp/ptp_chardev.c
@@ -193,6 +193,7 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg)
 		if (err)
 			break;
 
+		memset(&precise_offset, 0, sizeof(precise_offset));
 		ts = ktime_to_timespec64(xtstamp.device);
 		precise_offset.device.sec = ts.tv_sec;
 		precise_offset.device.nsec = ts.tv_nsec;
-- 
2.4.11


From 5e68b3e373fe241eb644b6d189fc6de548947f74 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Tue, 11 Oct 2016 10:56:45 -0700
Subject: [PATCH 08/34] net_sched: reorder pernet ops and act ops registrations

[ Upstream commit ab102b80cef28c20b3ef7794806c3a982c6444fc ]

Krister reported a kernel NULL pointer dereference after
tcf_action_init_1() invokes a_o->init(), it is a race condition
where one thread calling tcf_register_action() to initialize
the netns data after putting act ops in the global list and
the other thread searching the list and then calling
a_o->init(net, ...).

Fix this by moving the pernet ops registration before making
the action ops visible. This is fine because: a) we don't
rely on act_base in pernet ops->init(), b) in the worst case we
have a fully initialized netns but ops is still not ready so
new actions still can't be created.

Reported-by: Krister Johansen <kjlx@templeofstupid.com>
Tested-by: Krister Johansen <kjlx@templeofstupid.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_api.c | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index d09d068..027ddf4 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -341,22 +341,25 @@ int tcf_register_action(struct tc_action_ops *act,
 	if (!act->act || !act->dump || !act->init || !act->walk || !act->lookup)
 		return -EINVAL;
 
+	/* We have to register pernet ops before making the action ops visible,
+	 * otherwise tcf_action_init_1() could get a partially initialized
+	 * netns.
+	 */
+	ret = register_pernet_subsys(ops);
+	if (ret)
+		return ret;
+
 	write_lock(&act_mod_lock);
 	list_for_each_entry(a, &act_base, head) {
 		if (act->type == a->type || (strcmp(act->kind, a->kind) == 0)) {
 			write_unlock(&act_mod_lock);
+			unregister_pernet_subsys(ops);
 			return -EEXIST;
 		}
 	}
 	list_add_tail(&act->head, &act_base);
 	write_unlock(&act_mod_lock);
 
-	ret = register_pernet_subsys(ops);
-	if (ret) {
-		tcf_unregister_action(act, ops);
-		return ret;
-	}
-
 	return 0;
 }
 EXPORT_SYMBOL(tcf_register_action);
@@ -367,8 +370,6 @@ int tcf_unregister_action(struct tc_action_ops *act,
 	struct tc_action_ops *a;
 	int err = -ENOENT;
 
-	unregister_pernet_subsys(ops);
-
 	write_lock(&act_mod_lock);
 	list_for_each_entry(a, &act_base, head) {
 		if (a == act) {
@@ -378,6 +379,8 @@ int tcf_unregister_action(struct tc_action_ops *act,
 		}
 	}
 	write_unlock(&act_mod_lock);
+	if (!err)
+		unregister_pernet_subsys(ops);
 	return err;
 }
 EXPORT_SYMBOL(tcf_unregister_action);
-- 
2.4.11


From b4040200ac2b612cfb1cd6f122995b159c6952f5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 12 Oct 2016 19:01:45 +0200
Subject: [PATCH 09/34] ipv6: tcp: restore IP6CB for pktoptions skbs

[ Upstream commit 8ce48623f0cf3d632e32448411feddccb693d351 ]

Baozeng Ding reported following KASAN splat :

BUG: KASAN: use-after-free in ip6_datagram_recv_specific_ctl+0x13f1/0x15c0 at addr ffff880029c84ec8
Read of size 1 by task poc/25548
Call Trace:
 [<ffffffff82cf43c9>] dump_stack+0x12e/0x185 /lib/dump_stack.c:15
 [<     inline     >] print_address_description /mm/kasan/report.c:204
 [<ffffffff817ced3b>] kasan_report_error+0x48b/0x4b0 /mm/kasan/report.c:283
 [<     inline     >] kasan_report /mm/kasan/report.c:303
 [<ffffffff817ced9e>] __asan_report_load1_noabort+0x3e/0x40 /mm/kasan/report.c:321
 [<ffffffff85c71da1>] ip6_datagram_recv_specific_ctl+0x13f1/0x15c0 /net/ipv6/datagram.c:687
 [<ffffffff85c734c3>] ip6_datagram_recv_ctl+0x33/0x40
 [<ffffffff85c0b07c>] do_ipv6_getsockopt.isra.4+0xaec/0x2150
 [<ffffffff85c0c7f6>] ipv6_getsockopt+0x116/0x230
 [<ffffffff859b5a12>] tcp_getsockopt+0x82/0xd0 /net/ipv4/tcp.c:3035
 [<ffffffff855fb385>] sock_common_getsockopt+0x95/0xd0 /net/core/sock.c:2647
 [<     inline     >] SYSC_getsockopt /net/socket.c:1776
 [<ffffffff855f8ba2>] SyS_getsockopt+0x142/0x230 /net/socket.c:1758
 [<ffffffff8685cdc5>] entry_SYSCALL_64_fastpath+0x23/0xc6
Memory state around the buggy address:
 ffff880029c84d80: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
 ffff880029c84e00: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
> ffff880029c84e80: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
                                              ^
 ffff880029c84f00: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
 ffff880029c84f80: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff

He also provided a syzkaller reproducer.

Issue is that ip6_datagram_recv_specific_ctl() expects to find IP6CB
data that was moved at a different place in tcp_v6_rcv()

This patch moves tcp_v6_restore_cb() up and calls it from
tcp_v6_do_rcv() when np->pktoptions is set.

Fixes: 971f10eca186 ("tcp: better TCP_SKB_CB layout to reduce cache line misses")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Baozeng Ding <sploving1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/tcp_ipv6.c | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 94f4f89..fc67822 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1193,6 +1193,16 @@ out:
 	return NULL;
 }
 
+static void tcp_v6_restore_cb(struct sk_buff *skb)
+{
+	/* We need to move header back to the beginning if xfrm6_policy_check()
+	 * and tcp_v6_fill_cb() are going to be called again.
+	 * ip6_datagram_recv_specific_ctl() also expects IP6CB to be there.
+	 */
+	memmove(IP6CB(skb), &TCP_SKB_CB(skb)->header.h6,
+		sizeof(struct inet6_skb_parm));
+}
+
 /* The socket must have it's spinlock held when we get
  * here, unless it is a TCP_LISTEN socket.
  *
@@ -1322,6 +1332,7 @@ ipv6_pktoptions:
 			np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb));
 		if (ipv6_opt_accepted(sk, opt_skb, &TCP_SKB_CB(opt_skb)->header.h6)) {
 			skb_set_owner_r(opt_skb, sk);
+			tcp_v6_restore_cb(opt_skb);
 			opt_skb = xchg(&np->pktoptions, opt_skb);
 		} else {
 			__kfree_skb(opt_skb);
@@ -1355,15 +1366,6 @@ static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr,
 	TCP_SKB_CB(skb)->sacked = 0;
 }
 
-static void tcp_v6_restore_cb(struct sk_buff *skb)
-{
-	/* We need to move header back to the beginning if xfrm6_policy_check()
-	 * and tcp_v6_fill_cb() are going to be called again.
-	 */
-	memmove(IP6CB(skb), &TCP_SKB_CB(skb)->header.h6,
-		sizeof(struct inet6_skb_parm));
-}
-
 static int tcp_v6_rcv(struct sk_buff *skb)
 {
 	const struct tcphdr *th;
-- 
2.4.11


From 9827c862fef6592ae9cab2da2df7bd04a49bac44 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Wed, 12 Oct 2016 22:14:53 +0200
Subject: [PATCH 10/34] net: phy: Trigger state machine on state change and not
 polling.

[ Upstream commit 3c293f4e08b58ad5b78f78d89ca1fd41f87f8729 ]

The phy_start() is used to indicate the PHY is now ready to do its
work. The state is changed, normally to PHY_UP which means that both
the MAC and the PHY are ready.

If the phy driver is using polling, when the next poll happens, the
state machine notices the PHY is now in PHY_UP, and kicks off
auto-negotiation, if needed.

If however, the PHY is using interrupts, there is no polling. The phy
is stuck in PHY_UP until the next interrupt comes along. And there is
no reason for the PHY to interrupt.

Have phy_start() schedule the state machine to run, which both speeds
up the polling use case, and makes the interrupt use case actually
work.

This problems exists whenever there is a state change which will not
cause an interrupt. Trigger the state machine in these cases,
e.g. phy_error().

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Cc: Kyle Roeschley <kyle.roeschley@ni.com>
Tested-by: Kyle Roeschley <kyle.roeschley@ni.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 22 ++++++++++++++++++++--
 1 file changed, 20 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index c6f6683..f424b86 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -608,6 +608,21 @@ void phy_start_machine(struct phy_device *phydev)
 }
 
 /**
+ * phy_trigger_machine - trigger the state machine to run
+ *
+ * @phydev: the phy_device struct
+ *
+ * Description: There has been a change in state which requires that the
+ *   state machine runs.
+ */
+
+static void phy_trigger_machine(struct phy_device *phydev)
+{
+	cancel_delayed_work_sync(&phydev->state_queue);
+	queue_delayed_work(system_power_efficient_wq, &phydev->state_queue, 0);
+}
+
+/**
  * phy_stop_machine - stop the PHY state machine tracking
  * @phydev: target phy_device struct
  *
@@ -639,6 +654,8 @@ static void phy_error(struct phy_device *phydev)
 	mutex_lock(&phydev->lock);
 	phydev->state = PHY_HALTED;
 	mutex_unlock(&phydev->lock);
+
+	phy_trigger_machine(phydev);
 }
 
 /**
@@ -800,8 +817,7 @@ void phy_change(struct work_struct *work)
 	}
 
 	/* reschedule state queue work to run as soon as possible */
-	cancel_delayed_work_sync(&phydev->state_queue);
-	queue_delayed_work(system_power_efficient_wq, &phydev->state_queue, 0);
+	phy_trigger_machine(phydev);
 	return;
 
 ignore:
@@ -890,6 +906,8 @@ void phy_start(struct phy_device *phydev)
 	/* if phy was suspended, bring the physical link up again */
 	if (do_resume)
 		phy_resume(phydev);
+
+	phy_trigger_machine(phydev);
 }
 EXPORT_SYMBOL(phy_start);
 
-- 
2.4.11


From 34b6499670539beb9d5bcff35ccefa835ae9d98c Mon Sep 17 00:00:00 2001
From: Vadim Fedorenko <junk@yandex-team.ru>
Date: Tue, 11 Oct 2016 22:47:20 +0300
Subject: [PATCH 11/34] ip6_tunnel: fix ip6_tnl_lookup

[ Upstream commit 68d00f332e0ba7f60f212be74ede290c9f873bc5 ]

The commit ea3dc9601bda ("ip6_tunnel: Add support for wildcard tunnel
endpoints.") introduces support for wildcards in tunnels endpoints,
but in some rare circumstances ip6_tnl_lookup selects wrong tunnel
interface relying only on source or destination address of the packet
and not checking presence of wildcard in tunnels endpoints. Later in
ip6_tnl_rcv this packets can be dicarded because of difference in
ipproto even if fallback device have proper ipproto configuration.

This patch adds checks of wildcard endpoint in tunnel avoiding such
behavior

Fixes: ea3dc9601bda ("ip6_tunnel: Add support for wildcard tunnel endpoints.")
Signed-off-by: Vadim Fedorenko <junk@yandex-team.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 888543d..41a6479 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -155,6 +155,7 @@ ip6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_
 	hash = HASH(&any, local);
 	for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
 		if (ipv6_addr_equal(local, &t->parms.laddr) &&
+		    ipv6_addr_any(&t->parms.raddr) &&
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
@@ -162,6 +163,7 @@ ip6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_
 	hash = HASH(remote, &any);
 	for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
 		if (ipv6_addr_equal(remote, &t->parms.raddr) &&
+		    ipv6_addr_any(&t->parms.laddr) &&
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
-- 
2.4.11


From 1e0daade2ee512af9b009fc3641e334959dd7a5d Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Wed, 12 Oct 2016 10:10:40 +0200
Subject: [PATCH 12/34] ipv6: correctly add local routes when lo goes up

[ Upstream commit a220445f9f4382c36a53d8ef3e08165fa27f7e2c ]

The goal of the patch is to fix this scenario:
 ip link add dummy1 type dummy
 ip link set dummy1 up
 ip link set lo down ; ip link set lo up

After that sequence, the local route to the link layer address of dummy1 is
not there anymore.

When the loopback is set down, all local routes are deleted by
addrconf_ifdown()/rt6_ifdown(). At this time, the rt6_info entry still
exists, because the corresponding idev has a reference on it. After the rcu
grace period, dst_rcu_free() is called, and thus ___dst_free(), which will
set obsolete to DST_OBSOLETE_DEAD.

In this case, init_loopback() is called before dst_rcu_free(), thus
obsolete is still sets to something <= 0. So, the function doesn't add the
route again. To avoid that race, let's check the rt6 refcnt instead.

Fixes: 25fb6ca4ed9c ("net IPv6 : Fix broken IPv6 routing table after loopback down-up")
Fixes: a881ae1f625c ("ipv6: don't call addrconf_dst_alloc again when enable lo")
Fixes: 33d99113b110 ("ipv6: reallocate addrconf router for ipv6 address when lo device up")
Reported-by: Francesco Santoro <francesco.santoro@6wind.com>
Reported-by: Samuel Gauthier <samuel.gauthier@6wind.com>
CC: Balakumaran Kannan <Balakumaran.Kannan@ap.sony.com>
CC: Maruthi Thotad <Maruthi.Thotad@ap.sony.com>
CC: Sabrina Dubroca <sd@queasysnail.net>
CC: Hannes Frederic Sowa <hannes@stressinduktion.org>
CC: Weilong Chen <chenweilong@huawei.com>
CC: Gao feng <gaofeng@cn.fujitsu.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 2f1f5d4..f5432d6 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -2995,7 +2995,7 @@ static void init_loopback(struct net_device *dev)
 				 * lo device down, release this obsolete dst and
 				 * reallocate a new router for ifa.
 				 */
-				if (sp_ifa->rt->dst.obsolete > 0) {
+				if (!atomic_read(&sp_ifa->rt->rt6i_ref)) {
 					ip6_rt_put(sp_ifa->rt);
 					sp_ifa->rt = NULL;
 				} else {
-- 
2.4.11


From 9dd06e920fbbad25d160ed05089929ddcaf0cf01 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 13 Oct 2016 18:26:56 +0200
Subject: [PATCH 13/34] IB/ipoib: move back IB LL address into the hard header

[ Upstream commit fc791b6335152c5278dc4a4991bcb2d329f806f9 ]

After the commit 9207f9d45b0a ("net: preserve IP control block
during GSO segmentation"), the GSO CB and the IPoIB CB conflict.
That destroy the IPoIB address information cached there,
causing a severe performance regression, as better described here:

http://marc.info/?l=linux-kernel&m=146787279825501&w=2

This change moves the data cached by the IPoIB driver from the
skb control lock into the IPoIB hard header, as done before
the commit 936d7de3d736 ("IPoIB: Stop lying about hard_header_len
and use skb->cb to stash LL addresses").
In order to avoid GRO issue, on packet reception, the IPoIB driver
stash into the skb a dummy pseudo header, so that the received
packets have actually a hard header matching the declared length.
To avoid changing the connected mode maximum mtu, the allocated
head buffer size is increased by the pseudo header length.

After this commit, IPoIB performances are back to pre-regression
value.

v2 -> v3: rebased
v1 -> v2: avoid changing the max mtu, increasing the head buf size

Fixes: 9207f9d45b0a ("net: preserve IP control block during GSO segmentation")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/ulp/ipoib/ipoib.h           | 20 +++++++---
 drivers/infiniband/ulp/ipoib/ipoib_cm.c        | 15 +++----
 drivers/infiniband/ulp/ipoib/ipoib_ib.c        | 12 +++---
 drivers/infiniband/ulp/ipoib/ipoib_main.c      | 54 ++++++++++++++++----------
 drivers/infiniband/ulp/ipoib/ipoib_multicast.c |  6 ++-
 5 files changed, 64 insertions(+), 43 deletions(-)

diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index 9dbfcc0..5ff64af 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -63,6 +63,8 @@ enum ipoib_flush_level {
 
 enum {
 	IPOIB_ENCAP_LEN		  = 4,
+	IPOIB_PSEUDO_LEN	  = 20,
+	IPOIB_HARD_LEN		  = IPOIB_ENCAP_LEN + IPOIB_PSEUDO_LEN,
 
 	IPOIB_UD_HEAD_SIZE	  = IB_GRH_BYTES + IPOIB_ENCAP_LEN,
 	IPOIB_UD_RX_SG		  = 2, /* max buffer needed for 4K mtu */
@@ -134,15 +136,21 @@ struct ipoib_header {
 	u16	reserved;
 };
 
-struct ipoib_cb {
-	struct qdisc_skb_cb	qdisc_cb;
-	u8			hwaddr[INFINIBAND_ALEN];
+struct ipoib_pseudo_header {
+	u8	hwaddr[INFINIBAND_ALEN];
 };
 
-static inline struct ipoib_cb *ipoib_skb_cb(const struct sk_buff *skb)
+static inline void skb_add_pseudo_hdr(struct sk_buff *skb)
 {
-	BUILD_BUG_ON(sizeof(skb->cb) < sizeof(struct ipoib_cb));
-	return (struct ipoib_cb *)skb->cb;
+	char *data = skb_push(skb, IPOIB_PSEUDO_LEN);
+
+	/*
+	 * only the ipoib header is present now, make room for a dummy
+	 * pseudo header and set skb field accordingly
+	 */
+	memset(data, 0, IPOIB_PSEUDO_LEN);
+	skb_reset_mac_header(skb);
+	skb_pull(skb, IPOIB_HARD_LEN);
 }
 
 /* Used for all multicast joins (broadcast, IPv4 mcast and IPv6 mcast) */
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 4ad297d..339a1ee 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -63,6 +63,8 @@ MODULE_PARM_DESC(cm_data_debug_level,
 #define IPOIB_CM_RX_DELAY       (3 * 256 * HZ)
 #define IPOIB_CM_RX_UPDATE_MASK (0x3)
 
+#define IPOIB_CM_RX_RESERVE     (ALIGN(IPOIB_HARD_LEN, 16) - IPOIB_ENCAP_LEN)
+
 static struct ib_qp_attr ipoib_cm_err_attr = {
 	.qp_state = IB_QPS_ERR
 };
@@ -146,15 +148,15 @@ static struct sk_buff *ipoib_cm_alloc_rx_skb(struct net_device *dev,
 	struct sk_buff *skb;
 	int i;
 
-	skb = dev_alloc_skb(IPOIB_CM_HEAD_SIZE + 12);
+	skb = dev_alloc_skb(ALIGN(IPOIB_CM_HEAD_SIZE + IPOIB_PSEUDO_LEN, 16));
 	if (unlikely(!skb))
 		return NULL;
 
 	/*
-	 * IPoIB adds a 4 byte header. So we need 12 more bytes to align the
+	 * IPoIB adds a IPOIB_ENCAP_LEN byte header, this will align the
 	 * IP header to a multiple of 16.
 	 */
-	skb_reserve(skb, 12);
+	skb_reserve(skb, IPOIB_CM_RX_RESERVE);
 
 	mapping[0] = ib_dma_map_single(priv->ca, skb->data, IPOIB_CM_HEAD_SIZE,
 				       DMA_FROM_DEVICE);
@@ -624,9 +626,9 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 	if (wc->byte_len < IPOIB_CM_COPYBREAK) {
 		int dlen = wc->byte_len;
 
-		small_skb = dev_alloc_skb(dlen + 12);
+		small_skb = dev_alloc_skb(dlen + IPOIB_CM_RX_RESERVE);
 		if (small_skb) {
-			skb_reserve(small_skb, 12);
+			skb_reserve(small_skb, IPOIB_CM_RX_RESERVE);
 			ib_dma_sync_single_for_cpu(priv->ca, rx_ring[wr_id].mapping[0],
 						   dlen, DMA_FROM_DEVICE);
 			skb_copy_from_linear_data(skb, small_skb->data, dlen);
@@ -663,8 +665,7 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 
 copied:
 	skb->protocol = ((struct ipoib_header *) skb->data)->proto;
-	skb_reset_mac_header(skb);
-	skb_pull(skb, IPOIB_ENCAP_LEN);
+	skb_add_pseudo_hdr(skb);
 
 	++dev->stats.rx_packets;
 	dev->stats.rx_bytes += skb->len;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index be11d5d..830fecb 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -128,16 +128,15 @@ static struct sk_buff *ipoib_alloc_rx_skb(struct net_device *dev, int id)
 
 	buf_size = IPOIB_UD_BUF_SIZE(priv->max_ib_mtu);
 
-	skb = dev_alloc_skb(buf_size + IPOIB_ENCAP_LEN);
+	skb = dev_alloc_skb(buf_size + IPOIB_HARD_LEN);
 	if (unlikely(!skb))
 		return NULL;
 
 	/*
-	 * IB will leave a 40 byte gap for a GRH and IPoIB adds a 4 byte
-	 * header.  So we need 4 more bytes to get to 48 and align the
-	 * IP header to a multiple of 16.
+	 * the IP header will be at IPOIP_HARD_LEN + IB_GRH_BYTES, that is
+	 * 64 bytes aligned
 	 */
-	skb_reserve(skb, 4);
+	skb_reserve(skb, sizeof(struct ipoib_pseudo_header));
 
 	mapping = priv->rx_ring[id].mapping;
 	mapping[0] = ib_dma_map_single(priv->ca, skb->data, buf_size,
@@ -253,8 +252,7 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 	skb_pull(skb, IB_GRH_BYTES);
 
 	skb->protocol = ((struct ipoib_header *) skb->data)->proto;
-	skb_reset_mac_header(skb);
-	skb_pull(skb, IPOIB_ENCAP_LEN);
+	skb_add_pseudo_hdr(skb);
 
 	++dev->stats.rx_packets;
 	dev->stats.rx_bytes += skb->len;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index cc1c1b0..823a528 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -925,9 +925,12 @@ static void neigh_add_path(struct sk_buff *skb, u8 *daddr,
 				ipoib_neigh_free(neigh);
 				goto err_drop;
 			}
-			if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE)
+			if (skb_queue_len(&neigh->queue) <
+			    IPOIB_MAX_PATH_REC_QUEUE) {
+				/* put pseudoheader back on for next time */
+				skb_push(skb, IPOIB_PSEUDO_LEN);
 				__skb_queue_tail(&neigh->queue, skb);
-			else {
+			} else {
 				ipoib_warn(priv, "queue length limit %d. Packet drop.\n",
 					   skb_queue_len(&neigh->queue));
 				goto err_drop;
@@ -964,7 +967,7 @@ err_drop:
 }
 
 static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
-			     struct ipoib_cb *cb)
+			     struct ipoib_pseudo_header *phdr)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct ipoib_path *path;
@@ -972,16 +975,18 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
 
 	spin_lock_irqsave(&priv->lock, flags);
 
-	path = __path_find(dev, cb->hwaddr + 4);
+	path = __path_find(dev, phdr->hwaddr + 4);
 	if (!path || !path->valid) {
 		int new_path = 0;
 
 		if (!path) {
-			path = path_rec_create(dev, cb->hwaddr + 4);
+			path = path_rec_create(dev, phdr->hwaddr + 4);
 			new_path = 1;
 		}
 		if (path) {
 			if (skb_queue_len(&path->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
+				/* put pseudoheader back on for next time */
+				skb_push(skb, IPOIB_PSEUDO_LEN);
 				__skb_queue_tail(&path->queue, skb);
 			} else {
 				++dev->stats.tx_dropped;
@@ -1009,10 +1014,12 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
 			  be16_to_cpu(path->pathrec.dlid));
 
 		spin_unlock_irqrestore(&priv->lock, flags);
-		ipoib_send(dev, skb, path->ah, IPOIB_QPN(cb->hwaddr));
+		ipoib_send(dev, skb, path->ah, IPOIB_QPN(phdr->hwaddr));
 		return;
 	} else if ((path->query || !path_rec_start(dev, path)) &&
 		   skb_queue_len(&path->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
+		/* put pseudoheader back on for next time */
+		skb_push(skb, IPOIB_PSEUDO_LEN);
 		__skb_queue_tail(&path->queue, skb);
 	} else {
 		++dev->stats.tx_dropped;
@@ -1026,13 +1033,15 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct ipoib_neigh *neigh;
-	struct ipoib_cb *cb = ipoib_skb_cb(skb);
+	struct ipoib_pseudo_header *phdr;
 	struct ipoib_header *header;
 	unsigned long flags;
 
+	phdr = (struct ipoib_pseudo_header *) skb->data;
+	skb_pull(skb, sizeof(*phdr));
 	header = (struct ipoib_header *) skb->data;
 
-	if (unlikely(cb->hwaddr[4] == 0xff)) {
+	if (unlikely(phdr->hwaddr[4] == 0xff)) {
 		/* multicast, arrange "if" according to probability */
 		if ((header->proto != htons(ETH_P_IP)) &&
 		    (header->proto != htons(ETH_P_IPV6)) &&
@@ -1045,13 +1054,13 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			return NETDEV_TX_OK;
 		}
 		/* Add in the P_Key for multicast*/
-		cb->hwaddr[8] = (priv->pkey >> 8) & 0xff;
-		cb->hwaddr[9] = priv->pkey & 0xff;
+		phdr->hwaddr[8] = (priv->pkey >> 8) & 0xff;
+		phdr->hwaddr[9] = priv->pkey & 0xff;
 
-		neigh = ipoib_neigh_get(dev, cb->hwaddr);
+		neigh = ipoib_neigh_get(dev, phdr->hwaddr);
 		if (likely(neigh))
 			goto send_using_neigh;
-		ipoib_mcast_send(dev, cb->hwaddr, skb);
+		ipoib_mcast_send(dev, phdr->hwaddr, skb);
 		return NETDEV_TX_OK;
 	}
 
@@ -1060,16 +1069,16 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	case htons(ETH_P_IP):
 	case htons(ETH_P_IPV6):
 	case htons(ETH_P_TIPC):
-		neigh = ipoib_neigh_get(dev, cb->hwaddr);
+		neigh = ipoib_neigh_get(dev, phdr->hwaddr);
 		if (unlikely(!neigh)) {
-			neigh_add_path(skb, cb->hwaddr, dev);
+			neigh_add_path(skb, phdr->hwaddr, dev);
 			return NETDEV_TX_OK;
 		}
 		break;
 	case htons(ETH_P_ARP):
 	case htons(ETH_P_RARP):
 		/* for unicast ARP and RARP should always perform path find */
-		unicast_arp_send(skb, dev, cb);
+		unicast_arp_send(skb, dev, phdr);
 		return NETDEV_TX_OK;
 	default:
 		/* ethertype not supported by IPoIB */
@@ -1086,11 +1095,13 @@ send_using_neigh:
 			goto unref;
 		}
 	} else if (neigh->ah) {
-		ipoib_send(dev, skb, neigh->ah, IPOIB_QPN(cb->hwaddr));
+		ipoib_send(dev, skb, neigh->ah, IPOIB_QPN(phdr->hwaddr));
 		goto unref;
 	}
 
 	if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
+		/* put pseudoheader back on for next time */
+		skb_push(skb, sizeof(*phdr));
 		spin_lock_irqsave(&priv->lock, flags);
 		__skb_queue_tail(&neigh->queue, skb);
 		spin_unlock_irqrestore(&priv->lock, flags);
@@ -1122,8 +1133,8 @@ static int ipoib_hard_header(struct sk_buff *skb,
 			     unsigned short type,
 			     const void *daddr, const void *saddr, unsigned len)
 {
+	struct ipoib_pseudo_header *phdr;
 	struct ipoib_header *header;
-	struct ipoib_cb *cb = ipoib_skb_cb(skb);
 
 	header = (struct ipoib_header *) skb_push(skb, sizeof *header);
 
@@ -1132,12 +1143,13 @@ static int ipoib_hard_header(struct sk_buff *skb,
 
 	/*
 	 * we don't rely on dst_entry structure,  always stuff the
-	 * destination address into skb->cb so we can figure out where
+	 * destination address into skb hard header so we can figure out where
 	 * to send the packet later.
 	 */
-	memcpy(cb->hwaddr, daddr, INFINIBAND_ALEN);
+	phdr = (struct ipoib_pseudo_header *) skb_push(skb, sizeof(*phdr));
+	memcpy(phdr->hwaddr, daddr, INFINIBAND_ALEN);
 
-	return sizeof *header;
+	return IPOIB_HARD_LEN;
 }
 
 static void ipoib_set_mcast_list(struct net_device *dev)
@@ -1759,7 +1771,7 @@ void ipoib_setup(struct net_device *dev)
 
 	dev->flags		|= IFF_BROADCAST | IFF_MULTICAST;
 
-	dev->hard_header_len	 = IPOIB_ENCAP_LEN;
+	dev->hard_header_len	 = IPOIB_HARD_LEN;
 	dev->addr_len		 = INFINIBAND_ALEN;
 	dev->type		 = ARPHRD_INFINIBAND;
 	dev->tx_queue_len	 = ipoib_sendq_size * 2;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index d3394b6..1909dd2 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -796,9 +796,11 @@ void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb)
 			__ipoib_mcast_add(dev, mcast);
 			list_add_tail(&mcast->list, &priv->multicast_list);
 		}
-		if (skb_queue_len(&mcast->pkt_queue) < IPOIB_MAX_MCAST_QUEUE)
+		if (skb_queue_len(&mcast->pkt_queue) < IPOIB_MAX_MCAST_QUEUE) {
+			/* put pseudoheader back on for next time */
+			skb_push(skb, sizeof(struct ipoib_pseudo_header));
 			skb_queue_tail(&mcast->pkt_queue, skb);
-		else {
+		} else {
 			++dev->stats.tx_dropped;
 			dev_kfree_skb_any(skb);
 		}
-- 
2.4.11


From 8b365fcee8dc58d60b2aaaa73d15506e52f9dcaf Mon Sep 17 00:00:00 2001
From: Brenden Blanco <bblanco@plumgrid.com>
Date: Thu, 13 Oct 2016 13:13:11 -0700
Subject: [PATCH 14/34] net/mlx4_en: fixup xdp tx irq to match rx

[ Upstream commit 958b3d396d7f80755e2c2e6a8f873a669f38de10 ]

In cases where the number of tx rings is not a multiple of the number of
rx rings, the tx completion event will be handled on a different core
from the transmit and population of the ring. Races on the ring will
lead to a double-free of the page, and possibly other corruption.

The rings are initialized by default with a valid multiple of rings,
based on the number of cpus, therefore an invalid configuration requires
ethtool to change the ring layout. For instance 'ethtool -L eth0 rx 9 tx
8' will cause packets received on rx0, and XDP_TX'd to tx48, to be
completed on cpu3 (48 % 9 == 3).

Resolve this discrepancy by shifting the irq for the xdp tx queues to
start again from 0, modulo rx_ring_num.

Fixes: 9ecc2d86171a ("net/mlx4_en: add xdp forwarding and data write support")
Reported-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Brenden Blanco <bblanco@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_cq.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
index 132cea6..e3be7e4 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
@@ -127,7 +127,15 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 		/* For TX we use the same irq per
 		ring we assigned for the RX    */
 		struct mlx4_en_cq *rx_cq;
-
+		int xdp_index;
+
+		/* The xdp tx irq must align with the rx ring that forwards to
+		 * it, so reindex these from 0. This should only happen when
+		 * tx_ring_num is not a multiple of rx_ring_num.
+		 */
+		xdp_index = (priv->xdp_ring_num - priv->tx_ring_num) + cq_idx;
+		if (xdp_index >= 0)
+			cq_idx = xdp_index;
 		cq_idx = cq_idx % priv->rx_ring_num;
 		rx_cq = priv->rx_cq[cq_idx];
 		cq->vector = rx_cq->vector;
-- 
2.4.11


From a1b8cb88cb5e746ac8cbe2f7ffc5082549d6e58c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 15 Oct 2016 17:50:49 +0200
Subject: [PATCH 15/34] net: pktgen: remove rcu locking in pktgen_change_name()

[ Upstream commit 9a0b1e8ba4061778897b544afc898de2163382f7 ]

After Jesper commit back in linux-3.18, we trigger a lockdep
splat in proc_create_data() while allocating memory from
pktgen_change_name().

This patch converts t->if_lock to a mutex, since it is now only
used from control path, and adds proper locking to pktgen_change_name()

1) pktgen_thread_lock to protect the outer loop (iterating threads)
2) t->if_lock to protect the inner loop (iterating devices)

Note that before Jesper patch, pktgen_change_name() was lacking proper
protection, but lockdep was not able to detect the problem.

Fixes: 8788370a1d4b ("pktgen: RCU-ify "if_list" to remove lock in next_to_run()")
Reported-by: John Sperbeck <jsperbeck@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/pktgen.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 5219a9e..306b8f0 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -216,8 +216,8 @@
 #define M_QUEUE_XMIT		2	/* Inject packet into qdisc */
 
 /* If lock -- protects updating of if_list */
-#define   if_lock(t)           spin_lock(&(t->if_lock));
-#define   if_unlock(t)           spin_unlock(&(t->if_lock));
+#define   if_lock(t)           mutex_lock(&(t->if_lock));
+#define   if_unlock(t)           mutex_unlock(&(t->if_lock));
 
 /* Used to help with determining the pkts on receive */
 #define PKTGEN_MAGIC 0xbe9be955
@@ -423,7 +423,7 @@ struct pktgen_net {
 };
 
 struct pktgen_thread {
-	spinlock_t if_lock;		/* for list of devices */
+	struct mutex if_lock;		/* for list of devices */
 	struct list_head if_list;	/* All device here */
 	struct list_head th_list;
 	struct task_struct *tsk;
@@ -2010,11 +2010,13 @@ static void pktgen_change_name(const struct pktgen_net *pn, struct net_device *d
 {
 	struct pktgen_thread *t;
 
+	mutex_lock(&pktgen_thread_lock);
+
 	list_for_each_entry(t, &pn->pktgen_threads, th_list) {
 		struct pktgen_dev *pkt_dev;
 
-		rcu_read_lock();
-		list_for_each_entry_rcu(pkt_dev, &t->if_list, list) {
+		if_lock(t);
+		list_for_each_entry(pkt_dev, &t->if_list, list) {
 			if (pkt_dev->odev != dev)
 				continue;
 
@@ -2029,8 +2031,9 @@ static void pktgen_change_name(const struct pktgen_net *pn, struct net_device *d
 				       dev->name);
 			break;
 		}
-		rcu_read_unlock();
+		if_unlock(t);
 	}
+	mutex_unlock(&pktgen_thread_lock);
 }
 
 static int pktgen_device_event(struct notifier_block *unused,
@@ -3762,7 +3765,7 @@ static int __net_init pktgen_create_thread(int cpu, struct pktgen_net *pn)
 		return -ENOMEM;
 	}
 
-	spin_lock_init(&t->if_lock);
+	mutex_init(&t->if_lock);
 	t->cpu = cpu;
 
 	INIT_LIST_HEAD(&t->if_list);
-- 
2.4.11


From 49e192f5a3c3fcae14977bf9dc584dbf938c4b2f Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Tue, 18 Oct 2016 18:09:48 +0200
Subject: [PATCH 16/34] bridge: multicast: restore perm router ports on
 multicast enable

[ Upstream commit 7cb3f9214dfa443c1ccc2be637dcc6344cc203f0 ]

Satish reported a problem with the perm multicast router ports not getting
reenabled after some series of events, in particular if it happens that the
multicast snooping has been disabled and the port goes to disabled state
then it will be deleted from the router port list, but if it moves into
non-disabled state it will not be re-added because the mcast snooping is
still disabled, and enabling snooping later does nothing.

Here are the steps to reproduce, setup br0 with snooping enabled and eth1
added as a perm router (multicast_router = 2):
1. $ echo 0 > /sys/class/net/br0/bridge/multicast_snooping
2. $ ip l set eth1 down
^ This step deletes the interface from the router list
3. $ ip l set eth1 up
^ This step does not add it again because mcast snooping is disabled
4. $ echo 1 > /sys/class/net/br0/bridge/multicast_snooping
5. $ bridge -d -s mdb show
<empty>

At this point we have mcast enabled and eth1 as a perm router (value = 2)
but it is not in the router list which is incorrect.

After this change:
1. $ echo 0 > /sys/class/net/br0/bridge/multicast_snooping
2. $ ip l set eth1 down
^ This step deletes the interface from the router list
3. $ ip l set eth1 up
^ This step does not add it again because mcast snooping is disabled
4. $ echo 1 > /sys/class/net/br0/bridge/multicast_snooping
5. $ bridge -d -s mdb show
router ports on br0: eth1

Note: we can directly do br_multicast_enable_port for all because the
querier timer already has checks for the port state and will simply
expire if it's in blocking/disabled. See the comment added by
commit 9aa66382163e7 ("bridge: multicast: add a comment to
br_port_state_selection about blocking state")

Fixes: 561f1103a2b7 ("bridge: Add multicast_snooping sysfs toggle")
Reported-by: Satish Ashok <sashok@cumulusnetworks.com>
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c | 23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index c5fea93..2136e45 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -972,13 +972,12 @@ static void br_multicast_enable(struct bridge_mcast_own_query *query)
 		mod_timer(&query->timer, jiffies);
 }
 
-void br_multicast_enable_port(struct net_bridge_port *port)
+static void __br_multicast_enable_port(struct net_bridge_port *port)
 {
 	struct net_bridge *br = port->br;
 
-	spin_lock(&br->multicast_lock);
 	if (br->multicast_disabled || !netif_running(br->dev))
-		goto out;
+		return;
 
 	br_multicast_enable(&port->ip4_own_query);
 #if IS_ENABLED(CONFIG_IPV6)
@@ -987,8 +986,14 @@ void br_multicast_enable_port(struct net_bridge_port *port)
 	if (port->multicast_router == MDB_RTR_TYPE_PERM &&
 	    hlist_unhashed(&port->rlist))
 		br_multicast_add_router(br, port);
+}
 
-out:
+void br_multicast_enable_port(struct net_bridge_port *port)
+{
+	struct net_bridge *br = port->br;
+
+	spin_lock(&br->multicast_lock);
+	__br_multicast_enable_port(port);
 	spin_unlock(&br->multicast_lock);
 }
 
@@ -1994,8 +1999,9 @@ static void br_multicast_start_querier(struct net_bridge *br,
 
 int br_multicast_toggle(struct net_bridge *br, unsigned long val)
 {
-	int err = 0;
 	struct net_bridge_mdb_htable *mdb;
+	struct net_bridge_port *port;
+	int err = 0;
 
 	spin_lock_bh(&br->multicast_lock);
 	if (br->multicast_disabled == !val)
@@ -2023,10 +2029,9 @@ rollback:
 			goto rollback;
 	}
 
-	br_multicast_start_querier(br, &br->ip4_own_query);
-#if IS_ENABLED(CONFIG_IPV6)
-	br_multicast_start_querier(br, &br->ip6_own_query);
-#endif
+	br_multicast_open(br);
+	list_for_each_entry(port, &br->port_list, list)
+		__br_multicast_enable_port(port);
 
 unlock:
 	spin_unlock_bh(&br->multicast_lock);
-- 
2.4.11


From f3c7b0ba082452a5b5189422e365218472910a7e Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Tue, 18 Oct 2016 18:50:23 +0200
Subject: [PATCH 17/34] switchdev: Execute bridge ndos only for bridge ports

[ Upstream commit 97c242902c209e7d46e365335db5202634484dcb ]

We recently got the following warning after setting up a vlan device on
top of an offloaded bridge and executing 'bridge link':

WARNING: CPU: 0 PID: 18566 at drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c:81 mlxsw_sp_port_orig_get.part.9+0x55/0x70 [mlxsw_spectrum]
[...]
 CPU: 0 PID: 18566 Comm: bridge Not tainted 4.8.0-rc7 #1
 Hardware name: Mellanox Technologies Ltd. Mellanox switch/Mellanox switch, BIOS 4.6.5 05/21/2015
  0000000000000286 00000000e64ab94f ffff880406e6f8f0 ffffffff8135eaa3
  0000000000000000 0000000000000000 ffff880406e6f930 ffffffff8108c43b
  0000005106e6f988 ffff8803df398840 ffff880403c60108 ffff880406e6f990
 Call Trace:
  [<ffffffff8135eaa3>] dump_stack+0x63/0x90
  [<ffffffff8108c43b>] __warn+0xcb/0xf0
  [<ffffffff8108c56d>] warn_slowpath_null+0x1d/0x20
  [<ffffffffa01420d5>] mlxsw_sp_port_orig_get.part.9+0x55/0x70 [mlxsw_spectrum]
  [<ffffffffa0142195>] mlxsw_sp_port_attr_get+0xa5/0xb0 [mlxsw_spectrum]
  [<ffffffff816f151f>] switchdev_port_attr_get+0x4f/0x140
  [<ffffffff816f15d0>] switchdev_port_attr_get+0x100/0x140
  [<ffffffff816f15d0>] switchdev_port_attr_get+0x100/0x140
  [<ffffffff816f1d6b>] switchdev_port_bridge_getlink+0x5b/0xc0
  [<ffffffff816f2680>] ? switchdev_port_fdb_dump+0x90/0x90
  [<ffffffff815f5427>] rtnl_bridge_getlink+0xe7/0x190
  [<ffffffff8161a1b2>] netlink_dump+0x122/0x290
  [<ffffffff8161b0df>] __netlink_dump_start+0x15f/0x190
  [<ffffffff815f5340>] ? rtnl_bridge_dellink+0x230/0x230
  [<ffffffff815fab46>] rtnetlink_rcv_msg+0x1a6/0x220
  [<ffffffff81208118>] ? __kmalloc_node_track_caller+0x208/0x2c0
  [<ffffffff815f5340>] ? rtnl_bridge_dellink+0x230/0x230
  [<ffffffff815fa9a0>] ? rtnl_newlink+0x890/0x890
  [<ffffffff8161cf54>] netlink_rcv_skb+0xa4/0xc0
  [<ffffffff815f56f8>] rtnetlink_rcv+0x28/0x30
  [<ffffffff8161c92c>] netlink_unicast+0x18c/0x240
  [<ffffffff8161ccdb>] netlink_sendmsg+0x2fb/0x3a0
  [<ffffffff815c5a48>] sock_sendmsg+0x38/0x50
  [<ffffffff815c6031>] SYSC_sendto+0x101/0x190
  [<ffffffff815c7111>] ? __sys_recvmsg+0x51/0x90
  [<ffffffff815c6b6e>] SyS_sendto+0xe/0x10
  [<ffffffff817017f2>] entry_SYSCALL_64_fastpath+0x1a/0xa4

The problem is that the 8021q module propagates the call to
ndo_bridge_getlink() via switchdev ops, but the switch driver doesn't
recognize the netdev, as it's not offloaded.

While we can ignore calls being made to non-bridge ports inside the
driver, a better fix would be to push this check up to the switchdev
layer.

Note that these ndos can be called for non-bridged netdev, but this only
happens in certain PF drivers which don't call the corresponding
switchdev functions anyway.

Fixes: 99f44bb3527b ("mlxsw: spectrum: Enable L3 interfaces on top of bridge devices")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Tamir Winetroub <tamirw@mellanox.com>
Tested-by: Tamir Winetroub <tamirw@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/switchdev/switchdev.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index a5fc9dd..a56c5e6 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -774,6 +774,9 @@ int switchdev_port_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 	u32 mask = BR_LEARNING | BR_LEARNING_SYNC | BR_FLOOD;
 	int err;
 
+	if (!netif_is_bridge_port(dev))
+		return -EOPNOTSUPP;
+
 	err = switchdev_port_attr_get(dev, &attr);
 	if (err && err != -EOPNOTSUPP)
 		return err;
@@ -929,6 +932,9 @@ int switchdev_port_bridge_setlink(struct net_device *dev,
 	struct nlattr *afspec;
 	int err = 0;
 
+	if (!netif_is_bridge_port(dev))
+		return -EOPNOTSUPP;
+
 	protinfo = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg),
 				   IFLA_PROTINFO);
 	if (protinfo) {
@@ -962,6 +968,9 @@ int switchdev_port_bridge_dellink(struct net_device *dev,
 {
 	struct nlattr *afspec;
 
+	if (!netif_is_bridge_port(dev))
+		return -EOPNOTSUPP;
+
 	afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg),
 				 IFLA_AF_SPEC);
 	if (afspec)
-- 
2.4.11


From 2a59c6060e15bf8df7b17470b5dfe63194c09fe6 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Tue, 18 Oct 2016 18:59:34 +0200
Subject: [PATCH 18/34] rtnetlink: Add rtnexthop offload flag to compare mask

[ Upstream commit 85dda4e5b0ee1f5b4e8cc93d39e475006bc61ccd ]

The offload flag is a status flag and should not be used by
FIB semantics for comparison.

Fixes: 37ed9493699c ("rtnetlink: add RTNH_F_EXTERNAL flag for fib offload")
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/rtnetlink.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 262f037..5a78be5 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -350,7 +350,7 @@ struct rtnexthop {
 #define RTNH_F_OFFLOAD		8	/* offloaded route */
 #define RTNH_F_LINKDOWN		16	/* carrier-down on nexthop */
 
-#define RTNH_COMPARE_MASK	(RTNH_F_DEAD | RTNH_F_LINKDOWN)
+#define RTNH_COMPARE_MASK	(RTNH_F_DEAD | RTNH_F_LINKDOWN | RTNH_F_OFFLOAD)
 
 /* Macros to handle hexthops */
 
-- 
2.4.11


From 3801a25cc53d3ace9d25540896c490d8d92bc8c9 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 19 Oct 2016 16:57:08 +0300
Subject: [PATCH 19/34] net: core: Correctly iterate over lower adjacency list

[ Upstream commit e4961b0768852d9eb7383e1a5df178eacb714656 ]

Tamir reported the following trace when processing ARP requests received
via a vlan device on top of a VLAN-aware bridge:

 NMI watchdog: BUG: soft lockup - CPU#1 stuck for 22s! [swapper/1:0]
[...]
 CPU: 1 PID: 0 Comm: swapper/1 Tainted: G        W       4.8.0-rc7 #1
 Hardware name: Mellanox Technologies Ltd. "MSN2100-CB2F"/"SA001017", BIOS 5.6.5 06/07/2016
 task: ffff88017edfea40 task.stack: ffff88017ee10000
 RIP: 0010:[<ffffffff815dcc73>]  [<ffffffff815dcc73>] netdev_all_lower_get_next_rcu+0x33/0x60
[...]
 Call Trace:
  <IRQ>
  [<ffffffffa015de0a>] mlxsw_sp_port_lower_dev_hold+0x5a/0xa0 [mlxsw_spectrum]
  [<ffffffffa016f1b0>] mlxsw_sp_router_netevent_event+0x80/0x150 [mlxsw_spectrum]
  [<ffffffff810ad07a>] notifier_call_chain+0x4a/0x70
  [<ffffffff810ad13a>] atomic_notifier_call_chain+0x1a/0x20
  [<ffffffff815ee77b>] call_netevent_notifiers+0x1b/0x20
  [<ffffffff815f2eb6>] neigh_update+0x306/0x740
  [<ffffffff815f38ce>] neigh_event_ns+0x4e/0xb0
  [<ffffffff8165ea3f>] arp_process+0x66f/0x700
  [<ffffffff8170214c>] ? common_interrupt+0x8c/0x8c
  [<ffffffff8165ec29>] arp_rcv+0x139/0x1d0
  [<ffffffff816e505a>] ? vlan_do_receive+0xda/0x320
  [<ffffffff815e3794>] __netif_receive_skb_core+0x524/0xab0
  [<ffffffff815e6830>] ? dev_queue_xmit+0x10/0x20
  [<ffffffffa06d612d>] ? br_forward_finish+0x3d/0xc0 [bridge]
  [<ffffffffa06e5796>] ? br_handle_vlan+0xf6/0x1b0 [bridge]
  [<ffffffff815e3d38>] __netif_receive_skb+0x18/0x60
  [<ffffffff815e3dc0>] netif_receive_skb_internal+0x40/0xb0
  [<ffffffff815e3e4c>] netif_receive_skb+0x1c/0x70
  [<ffffffffa06d7856>] br_pass_frame_up+0xc6/0x160 [bridge]
  [<ffffffffa06d63d7>] ? deliver_clone+0x37/0x50 [bridge]
  [<ffffffffa06d656c>] ? br_flood+0xcc/0x160 [bridge]
  [<ffffffffa06d7b14>] br_handle_frame_finish+0x224/0x4f0 [bridge]
  [<ffffffffa06d7f94>] br_handle_frame+0x174/0x300 [bridge]
  [<ffffffff815e3599>] __netif_receive_skb_core+0x329/0xab0
  [<ffffffff81374815>] ? find_next_bit+0x15/0x20
  [<ffffffff8135e802>] ? cpumask_next_and+0x32/0x50
  [<ffffffff810c9968>] ? load_balance+0x178/0x9b0
  [<ffffffff815e3d38>] __netif_receive_skb+0x18/0x60
  [<ffffffff815e3dc0>] netif_receive_skb_internal+0x40/0xb0
  [<ffffffff815e3e4c>] netif_receive_skb+0x1c/0x70
  [<ffffffffa01544a1>] mlxsw_sp_rx_listener_func+0x61/0xb0 [mlxsw_spectrum]
  [<ffffffffa005c9f7>] mlxsw_core_skb_receive+0x187/0x200 [mlxsw_core]
  [<ffffffffa007332a>] mlxsw_pci_cq_tasklet+0x63a/0x9b0 [mlxsw_pci]
  [<ffffffff81091986>] tasklet_action+0xf6/0x110
  [<ffffffff81704556>] __do_softirq+0xf6/0x280
  [<ffffffff8109213f>] irq_exit+0xdf/0xf0
  [<ffffffff817042b4>] do_IRQ+0x54/0xd0
  [<ffffffff8170214c>] common_interrupt+0x8c/0x8c

The problem is that netdev_all_lower_get_next_rcu() never advances the
iterator, thereby causing the loop over the lower adjacency list to run
forever.

Fix this by advancing the iterator and avoid the infinite loop.

Fixes: 7ce856aaaf13 ("mlxsw: spectrum: Add couple of lower device helper functions")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Tamir Winetroub <tamirw@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  2 +-
 net/core/dev.c            | 10 +++++++---
 2 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index e8d79d4..ae4b275 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3862,7 +3862,7 @@ struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev,
 	     ldev = netdev_all_lower_get_next(dev, &(iter)))
 
 #define netdev_for_each_all_lower_dev_rcu(dev, ldev, iter) \
-	for (iter = (dev)->all_adj_list.lower.next, \
+	for (iter = &(dev)->all_adj_list.lower, \
 	     ldev = netdev_all_lower_get_next_rcu(dev, &(iter)); \
 	     ldev; \
 	     ldev = netdev_all_lower_get_next_rcu(dev, &(iter)))
diff --git a/net/core/dev.c b/net/core/dev.c
index 1da79ef..746bf316 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5500,10 +5500,14 @@ struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev,
 {
 	struct netdev_adjacent *lower;
 
-	lower = list_first_or_null_rcu(&dev->all_adj_list.lower,
-				       struct netdev_adjacent, list);
+	lower = list_entry_rcu((*iter)->next, struct netdev_adjacent, list);
+
+	if (&lower->list == &dev->all_adj_list.lower)
+		return NULL;
+
+	*iter = &lower->list;
 
-	return lower ? lower->dev : NULL;
+	return lower->dev;
 }
 EXPORT_SYMBOL(netdev_all_lower_get_next_rcu);
 
-- 
2.4.11


From cae63c153152213f24d09c0e7ec55b1e5dc850dc Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Thu, 20 Oct 2016 15:58:02 +0200
Subject: [PATCH 20/34] net: add recursion limit to GRO
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit fcd91dd449867c6bfe56a81cabba76b829fd05cd ]

Currently, GRO can do unlimited recursion through the gro_receive
handlers.  This was fixed for tunneling protocols by limiting tunnel GRO
to one level with encap_mark, but both VLAN and TEB still have this
problem.  Thus, the kernel is vulnerable to a stack overflow, if we
receive a packet composed entirely of VLAN headers.

This patch adds a recursion counter to the GRO layer to prevent stack
overflow.  When a gro_receive function hits the recursion limit, GRO is
aborted for this skb and it is processed normally.  This recursion
counter is put in the GRO CB, but could be turned into a percpu counter
if we run out of space in the CB.

Thanks to Vladimír Beneš <vbenes@redhat.com> for the initial bug report.

Fixes: CVE-2016-7039
Fixes: 9b174d88c257 ("net: Add Transparent Ethernet Bridging GRO support.")
Fixes: 66e5133f19e9 ("vlan: Add GRO support for non hardware accelerated vlan")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Jiri Benc <jbenc@redhat.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c      |  2 +-
 drivers/net/vxlan.c       |  2 +-
 include/linux/netdevice.h | 39 ++++++++++++++++++++++++++++++++++++++-
 net/8021q/vlan.c          |  2 +-
 net/core/dev.c            |  1 +
 net/ethernet/eth.c        |  2 +-
 net/ipv4/af_inet.c        |  2 +-
 net/ipv4/fou.c            |  4 ++--
 net/ipv4/gre_offload.c    |  2 +-
 net/ipv4/udp_offload.c    |  2 +-
 net/ipv6/ip6_offload.c    |  2 +-
 11 files changed, 49 insertions(+), 11 deletions(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 3c20e87..16af1ce 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -453,7 +453,7 @@ static struct sk_buff **geneve_gro_receive(struct sock *sk,
 
 	skb_gro_pull(skb, gh_len);
 	skb_gro_postpull_rcsum(skb, gh, gh_len);
-	pp = ptype->callbacks.gro_receive(head, skb);
+	pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb);
 	flush = 0;
 
 out_unlock:
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 6e65832..5ae664c 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -584,7 +584,7 @@ static struct sk_buff **vxlan_gro_receive(struct sock *sk,
 		}
 	}
 
-	pp = eth_gro_receive(head, skb);
+	pp = call_gro_receive(eth_gro_receive, head, skb);
 	flush = 0;
 
 out:
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index ae4b275..e942c67 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2154,7 +2154,10 @@ struct napi_gro_cb {
 	/* Used to determine if flush_id can be ignored */
 	u8	is_atomic:1;
 
-	/* 5 bit hole */
+	/* Number of gro_receive callbacks this packet already went through */
+	u8 recursion_counter:4;
+
+	/* 1 bit hole */
 
 	/* used to support CHECKSUM_COMPLETE for tunneling protocols */
 	__wsum	csum;
@@ -2165,6 +2168,40 @@ struct napi_gro_cb {
 
 #define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb)
 
+#define GRO_RECURSION_LIMIT 15
+static inline int gro_recursion_inc_test(struct sk_buff *skb)
+{
+	return ++NAPI_GRO_CB(skb)->recursion_counter == GRO_RECURSION_LIMIT;
+}
+
+typedef struct sk_buff **(*gro_receive_t)(struct sk_buff **, struct sk_buff *);
+static inline struct sk_buff **call_gro_receive(gro_receive_t cb,
+						struct sk_buff **head,
+						struct sk_buff *skb)
+{
+	if (unlikely(gro_recursion_inc_test(skb))) {
+		NAPI_GRO_CB(skb)->flush |= 1;
+		return NULL;
+	}
+
+	return cb(head, skb);
+}
+
+typedef struct sk_buff **(*gro_receive_sk_t)(struct sock *, struct sk_buff **,
+					     struct sk_buff *);
+static inline struct sk_buff **call_gro_receive_sk(gro_receive_sk_t cb,
+						   struct sock *sk,
+						   struct sk_buff **head,
+						   struct sk_buff *skb)
+{
+	if (unlikely(gro_recursion_inc_test(skb))) {
+		NAPI_GRO_CB(skb)->flush |= 1;
+		return NULL;
+	}
+
+	return cb(sk, head, skb);
+}
+
 struct packet_type {
 	__be16			type;	/* This is really htons(ether_type). */
 	struct net_device	*dev;	/* NULL is wildcarded here	     */
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 8de138d..f2531ad 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -664,7 +664,7 @@ static struct sk_buff **vlan_gro_receive(struct sk_buff **head,
 
 	skb_gro_pull(skb, sizeof(*vhdr));
 	skb_gro_postpull_rcsum(skb, vhdr, sizeof(*vhdr));
-	pp = ptype->callbacks.gro_receive(head, skb);
+	pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb);
 
 out_unlock:
 	rcu_read_unlock();
diff --git a/net/core/dev.c b/net/core/dev.c
index 746bf316..fc63c6d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4496,6 +4496,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 		NAPI_GRO_CB(skb)->flush = 0;
 		NAPI_GRO_CB(skb)->free = 0;
 		NAPI_GRO_CB(skb)->encap_mark = 0;
+		NAPI_GRO_CB(skb)->recursion_counter = 0;
 		NAPI_GRO_CB(skb)->is_fou = 0;
 		NAPI_GRO_CB(skb)->is_atomic = 1;
 		NAPI_GRO_CB(skb)->gro_remcsum_start = 0;
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index 66dff5e..02acfff 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -439,7 +439,7 @@ struct sk_buff **eth_gro_receive(struct sk_buff **head,
 
 	skb_gro_pull(skb, sizeof(*eh));
 	skb_gro_postpull_rcsum(skb, eh, sizeof(*eh));
-	pp = ptype->callbacks.gro_receive(head, skb);
+	pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb);
 
 out_unlock:
 	rcu_read_unlock();
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 55513e6..eebbc0f 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1388,7 +1388,7 @@ struct sk_buff **inet_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 	skb_gro_pull(skb, sizeof(*iph));
 	skb_set_transport_header(skb, skb_gro_offset(skb));
 
-	pp = ops->callbacks.gro_receive(head, skb);
+	pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
 
 out_unlock:
 	rcu_read_unlock();
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 321d57f..5351b61 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -249,7 +249,7 @@ static struct sk_buff **fou_gro_receive(struct sock *sk,
 	if (!ops || !ops->callbacks.gro_receive)
 		goto out_unlock;
 
-	pp = ops->callbacks.gro_receive(head, skb);
+	pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
 
 out_unlock:
 	rcu_read_unlock();
@@ -441,7 +441,7 @@ next_proto:
 	if (WARN_ON_ONCE(!ops || !ops->callbacks.gro_receive))
 		goto out_unlock;
 
-	pp = ops->callbacks.gro_receive(head, skb);
+	pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
 	flush = 0;
 
 out_unlock:
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index ecd1e09..6871f59 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -227,7 +227,7 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head,
 	/* Adjusted NAPI_GRO_CB(skb)->csum after skb_gro_pull()*/
 	skb_gro_postpull_rcsum(skb, greh, grehlen);
 
-	pp = ptype->callbacks.gro_receive(head, skb);
+	pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb);
 	flush = 0;
 
 out_unlock:
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 81f253b..6de9f97 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -293,7 +293,7 @@ unflush:
 
 	skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */
 	skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr));
-	pp = udp_sk(sk)->gro_receive(sk, head, skb);
+	pp = call_gro_receive_sk(udp_sk(sk)->gro_receive, sk, head, skb);
 
 out_unlock:
 	rcu_read_unlock();
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 22e90e5..a09418b 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -243,7 +243,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 
 	skb_gro_postpull_rcsum(skb, iph, nlen);
 
-	pp = ops->callbacks.gro_receive(head, skb);
+	pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
 
 out_unlock:
 	rcu_read_unlock();
-- 
2.4.11


From a810ff8b733afaeb8b07832bf357982ddc4595cd Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 20 Oct 2016 10:26:48 -0700
Subject: [PATCH 21/34] ipv4: disable BH in set_ping_group_range()

[ Upstream commit a681574c99be23e4d20b769bf0e543239c364af5 ]

In commit 4ee3bd4a8c746 ("ipv4: disable BH when changing ip local port
range") Cong added BH protection in set_local_port_range() but missed
that same fix was needed in set_ping_group_range()

Fixes: b8f1a55639e6 ("udp: Add function to make source port for UDP tunnels")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Eric Salo <salo@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/sysctl_net_ipv4.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 1cb67de..500ae40 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -109,10 +109,10 @@ static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t hig
 	kgid_t *data = table->data;
 	struct net *net =
 		container_of(table->data, struct net, ipv4.ping_group_range.range);
-	write_seqlock(&net->ipv4.ip_local_ports.lock);
+	write_seqlock_bh(&net->ipv4.ip_local_ports.lock);
 	data[0] = low;
 	data[1] = high;
-	write_sequnlock(&net->ipv4.ip_local_ports.lock);
+	write_sequnlock_bh(&net->ipv4.ip_local_ports.lock);
 }
 
 /* Validate changes from /proc interface. */
-- 
2.4.11


From c6855b21e28d11a07fb1da0510a3dbc16e839eb8 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Thu, 20 Oct 2016 14:19:46 -0700
Subject: [PATCH 22/34] ipv4: use the right lock for ping_group_range

[ Upstream commit 396a30cce15d084b2b1a395aa6d515c3d559c674 ]

This reverts commit a681574c99be23e4d20b769bf0e543239c364af5
("ipv4: disable BH in set_ping_group_range()") because we never
read ping_group_range in BH context (unlike local_port_range).

Then, since we already have a lock for ping_group_range, those
using ip_local_ports.lock for ping_group_range are clearly typos.

We might consider to share a same lock for both ping_group_range
and local_port_range w.r.t. space saving, but that should be for
net-next.

Fixes: a681574c99be ("ipv4: disable BH in set_ping_group_range()")
Fixes: ba6b918ab234 ("ping: move ping_group_range out of CONFIG_SYSCTL")
Cc: Eric Dumazet <edumazet@google.com>
Cc: Eric Salo <salo@google.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/sysctl_net_ipv4.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 500ae40..80bc36b 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -96,11 +96,11 @@ static void inet_get_ping_group_range_table(struct ctl_table *table, kgid_t *low
 		container_of(table->data, struct net, ipv4.ping_group_range.range);
 	unsigned int seq;
 	do {
-		seq = read_seqbegin(&net->ipv4.ip_local_ports.lock);
+		seq = read_seqbegin(&net->ipv4.ping_group_range.lock);
 
 		*low = data[0];
 		*high = data[1];
-	} while (read_seqretry(&net->ipv4.ip_local_ports.lock, seq));
+	} while (read_seqretry(&net->ipv4.ping_group_range.lock, seq));
 }
 
 /* Update system visible IP port range */
@@ -109,10 +109,10 @@ static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t hig
 	kgid_t *data = table->data;
 	struct net *net =
 		container_of(table->data, struct net, ipv4.ping_group_range.range);
-	write_seqlock_bh(&net->ipv4.ip_local_ports.lock);
+	write_seqlock(&net->ipv4.ping_group_range.lock);
 	data[0] = low;
 	data[1] = high;
-	write_sequnlock_bh(&net->ipv4.ip_local_ports.lock);
+	write_sequnlock(&net->ipv4.ping_group_range.lock);
 }
 
 /* Validate changes from /proc interface. */
-- 
2.4.11


From 345b222aa31e8207323b553f2c834bf9183d02e1 Mon Sep 17 00:00:00 2001
From: Fabio Estevam <fabio.estevam@nxp.com>
Date: Fri, 21 Oct 2016 09:34:29 -0200
Subject: [PATCH 23/34] net: fec: Call swap_buffer() prior to IP header
 alignment

[ Upstream commit 235bde1ed3f0fff0f68f367ec8807b89ea151258 ]

Commit 3ac72b7b63d5 ("net: fec: align IP header in hardware") breaks
networking on mx28.

There is an erratum on mx28 (ENGR121613 - ENET big endian mode
not compatible with ARM little endian) that requires an additional
byte-swap operation to workaround this problem.

So call swap_buffer() prior to performing the IP header alignment
to restore network functionality on mx28.

Fixes: 3ac72b7b63d5 ("net: fec: align IP header in hardware")
Reported-and-tested-by: Henri Roosen <henri.roosen@ginzinger.com>
Signed-off-by: Fabio Estevam <fabio.estevam@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_main.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index f475318..3474de5 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -1430,14 +1430,14 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
 		skb_put(skb, pkt_len - 4);
 		data = skb->data;
 
+		if (!is_copybreak && need_swap)
+			swap_buffer(data, pkt_len);
+
 #if !defined(CONFIG_M5272)
 		if (fep->quirks & FEC_QUIRK_HAS_RACC)
 			data = skb_pull_inline(skb, 2);
 #endif
 
-		if (!is_copybreak && need_swap)
-			swap_buffer(data, pkt_len);
-
 		/* Extract the enhanced buffer descriptor */
 		ebdp = NULL;
 		if (fep->bufdesc_ex)
-- 
2.4.11


From 1fa70617c09a890816d063146e572046f5869e9b Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jslaby@suse.cz>
Date: Fri, 21 Oct 2016 14:13:24 +0200
Subject: [PATCH 24/34] net: sctp, forbid negative length

[ Upstream commit a4b8e71b05c27bae6bad3bdecddbc6b68a3ad8cf ]

Most of getsockopt handlers in net/sctp/socket.c check len against
sizeof some structure like:
        if (len < sizeof(int))
                return -EINVAL;

On the first look, the check seems to be correct. But since len is int
and sizeof returns size_t, int gets promoted to unsigned size_t too. So
the test returns false for negative lengths. Yes, (-1 < sizeof(long)) is
false.

Fix this in sctp by explicitly checking len < 0 before any getsockopt
handler is called.

Note that sctp_getsockopt_events already handled the negative case.
Since we added the < 0 check elsewhere, this one can be removed.

If not checked, this is the result:
UBSAN: Undefined behaviour in ../mm/page_alloc.c:2722:19
shift exponent 52 is too large for 32-bit type 'int'
CPU: 1 PID: 24535 Comm: syz-executor Not tainted 4.8.1-0-syzkaller #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.1-0-gb3ef39f-prebuilt.qemu-project.org 04/01/2014
 0000000000000000 ffff88006d99f2a8 ffffffffb2f7bdea 0000000041b58ab3
 ffffffffb4363c14 ffffffffb2f7bcde ffff88006d99f2d0 ffff88006d99f270
 0000000000000000 0000000000000000 0000000000000034 ffffffffb5096422
Call Trace:
 [<ffffffffb3051498>] ? __ubsan_handle_shift_out_of_bounds+0x29c/0x300
...
 [<ffffffffb273f0e4>] ? kmalloc_order+0x24/0x90
 [<ffffffffb27416a4>] ? kmalloc_order_trace+0x24/0x220
 [<ffffffffb2819a30>] ? __kmalloc+0x330/0x540
 [<ffffffffc18c25f4>] ? sctp_getsockopt_local_addrs+0x174/0xca0 [sctp]
 [<ffffffffc18d2bcd>] ? sctp_getsockopt+0x10d/0x1b0 [sctp]
 [<ffffffffb37c1219>] ? sock_common_getsockopt+0xb9/0x150
 [<ffffffffb37be2f5>] ? SyS_getsockopt+0x1a5/0x270

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Cc: Vlad Yasevich <vyasevich@gmail.com>
Cc: Neil Horman <nhorman@tuxdriver.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: linux-sctp@vger.kernel.org
Cc: netdev@vger.kernel.org
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 8ed2d99..baccbf3 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4683,7 +4683,7 @@ static int sctp_getsockopt_disable_fragments(struct sock *sk, int len,
 static int sctp_getsockopt_events(struct sock *sk, int len, char __user *optval,
 				  int __user *optlen)
 {
-	if (len <= 0)
+	if (len == 0)
 		return -EINVAL;
 	if (len > sizeof(struct sctp_event_subscribe))
 		len = sizeof(struct sctp_event_subscribe);
@@ -6426,6 +6426,9 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname,
 	if (get_user(len, optlen))
 		return -EFAULT;
 
+	if (len < 0)
+		return -EINVAL;
+
 	lock_sock(sk);
 
 	switch (optname) {
-- 
2.4.11


From 14d242903c0bb449e6525ce5f57c43256b968333 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 24 Oct 2016 01:01:09 +0800
Subject: [PATCH 25/34] sctp: fix the panic caused by route update

[ Upstream commit ecc515d7238f2cffac839069d56dc271141defa0 ]

Commit 7303a1475008 ("sctp: identify chunks that need to be fragmented
at IP level") made the chunk be fragmented at IP level in the next round
if it's size exceed PMTU.

But there still is another case, PMTU can be updated if transport's dst
expires and transport's pmtu_pending is set in sctp_packet_transmit. If
the new PMTU is less than the chunk, the same issue with that commit can
be triggered.

So we should drop this packet and let it retransmit in another round
where it would be fragmented at IP level.

This patch is to fix it by checking the chunk size after PMTU may be
updated and dropping this packet if it's size exceed PMTU.

Fixes: 90017accff61 ("sctp: Add GSO support")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@txudriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/output.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/net/sctp/output.c b/net/sctp/output.c
index 31b7bc3..8192990 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -417,6 +417,7 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp)
 	__u8 has_data = 0;
 	int gso = 0;
 	int pktcount = 0;
+	int auth_len = 0;
 	struct dst_entry *dst;
 	unsigned char *auth = NULL;	/* pointer to auth in skb data */
 
@@ -505,7 +506,12 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp)
 			list_for_each_entry(chunk, &packet->chunk_list, list) {
 				int padded = WORD_ROUND(chunk->skb->len);
 
-				if (pkt_size + padded > tp->pathmtu)
+				if (chunk == packet->auth)
+					auth_len = padded;
+				else if (auth_len + padded + packet->overhead >
+					 tp->pathmtu)
+					goto nomem;
+				else if (pkt_size + padded > tp->pathmtu)
 					break;
 				pkt_size += padded;
 			}
-- 
2.4.11


From d485893e80d24bfe0e20f0779d193d425b849565 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 23 Oct 2016 18:03:06 -0700
Subject: [PATCH 26/34] udp: fix IP_CHECKSUM handling

[ Upstream commit 10df8e6152c6c400a563a673e9956320bfce1871 ]

First bug was added in commit ad6f939ab193 ("ip: Add offset parameter to
ip_cmsg_recv") : Tom missed that ipv4 udp messages could be received on
AF_INET6 socket. ip_cmsg_recv(msg, skb) should have been replaced by
ip_cmsg_recv_offset(msg, skb, sizeof(struct udphdr));

Then commit e6afc8ace6dd ("udp: remove headers from UDP packets before
queueing") forgot to adjust the offsets now UDP headers are pulled
before skb are put in receive queue.

Fixes: ad6f939ab193 ("ip: Add offset parameter to ip_cmsg_recv")
Fixes: e6afc8ace6dd ("udp: remove headers from UDP packets before queueing")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Sam Kumar <samanthakumar@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Tested-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h       |  4 ++--
 net/ipv4/ip_sockglue.c | 11 ++++++-----
 net/ipv4/udp.c         |  2 +-
 net/ipv6/udp.c         |  3 ++-
 4 files changed, 11 insertions(+), 9 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index 9742b92..156b0c1 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -549,7 +549,7 @@ int ip_options_rcv_srr(struct sk_buff *skb);
  */
 
 void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb);
-void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb, int offset);
+void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb, int tlen, int offset);
 int ip_cmsg_send(struct sock *sk, struct msghdr *msg,
 		 struct ipcm_cookie *ipc, bool allow_ipv6);
 int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval,
@@ -571,7 +571,7 @@ void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 dport,
 
 static inline void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb)
 {
-	ip_cmsg_recv_offset(msg, skb, 0);
+	ip_cmsg_recv_offset(msg, skb, 0, 0);
 }
 
 bool icmp_global_allow(void);
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 71a52f4d..11ef96e 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -98,7 +98,7 @@ static void ip_cmsg_recv_retopts(struct msghdr *msg, struct sk_buff *skb)
 }
 
 static void ip_cmsg_recv_checksum(struct msghdr *msg, struct sk_buff *skb,
-				  int offset)
+				  int tlen, int offset)
 {
 	__wsum csum = skb->csum;
 
@@ -106,8 +106,9 @@ static void ip_cmsg_recv_checksum(struct msghdr *msg, struct sk_buff *skb,
 		return;
 
 	if (offset != 0)
-		csum = csum_sub(csum, csum_partial(skb_transport_header(skb),
-						   offset, 0));
+		csum = csum_sub(csum,
+				csum_partial(skb_transport_header(skb) + tlen,
+					     offset, 0));
 
 	put_cmsg(msg, SOL_IP, IP_CHECKSUM, sizeof(__wsum), &csum);
 }
@@ -153,7 +154,7 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
 }
 
 void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb,
-			 int offset)
+			 int tlen, int offset)
 {
 	struct inet_sock *inet = inet_sk(skb->sk);
 	unsigned int flags = inet->cmsg_flags;
@@ -216,7 +217,7 @@ void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb,
 	}
 
 	if (flags & IP_CMSG_CHECKSUM)
-		ip_cmsg_recv_checksum(msg, skb, offset);
+		ip_cmsg_recv_checksum(msg, skb, tlen, offset);
 }
 EXPORT_SYMBOL(ip_cmsg_recv_offset);
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 5fdcb8d..c0d71e7 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1327,7 +1327,7 @@ try_again:
 		*addr_len = sizeof(*sin);
 	}
 	if (inet->cmsg_flags)
-		ip_cmsg_recv_offset(msg, skb, sizeof(struct udphdr) + off);
+		ip_cmsg_recv_offset(msg, skb, sizeof(struct udphdr), off);
 
 	err = copied;
 	if (flags & MSG_TRUNC)
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 19ac3a1..c2a8656 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -427,7 +427,8 @@ try_again:
 
 	if (is_udp4) {
 		if (inet->cmsg_flags)
-			ip_cmsg_recv(msg, skb);
+			ip_cmsg_recv_offset(msg, skb,
+					    sizeof(struct udphdr), off);
 	} else {
 		if (np->rxopt.all)
 			ip6_datagram_recv_specific_ctl(sk, msg, skb);
-- 
2.4.11


From 33a330620fbc4ee225b2ddd951be44aedd44d984 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <sthemmin@microsoft.com>
Date: Sun, 23 Oct 2016 21:32:47 -0700
Subject: [PATCH 27/34] netvsc: fix incorrect receive checksum offloading

[ Upstream commit e52fed7177f74382f742c27de2cc5314790aebb6 ]

The Hyper-V netvsc driver was looking at the incorrect status bits
in the checksum info. It was setting the receive checksum unnecessary
flag based on the IP header checksum being correct. The checksum
flag is skb is about TCP and UDP checksum status. Because of this
bug, any packet received with bad TCP checksum would be passed
up the stack and to the application causing data corruption.
The problem is reproducible via netcat and netem.

This had a side effect of not doing receive checksum offload
on IPv6. The driver was also also always doing checksum offload
independent of the checksum setting done via ethtool.

Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/netvsc_drv.c | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 3ba29fc..c4d9653 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -624,15 +624,18 @@ static struct sk_buff *netvsc_alloc_recv_skb(struct net_device *net,
 	       packet->total_data_buflen);
 
 	skb->protocol = eth_type_trans(skb, net);
-	if (csum_info) {
-		/* We only look at the IP checksum here.
-		 * Should we be dropping the packet if checksum
-		 * failed? How do we deal with other checksums - TCP/UDP?
-		 */
-		if (csum_info->receive.ip_checksum_succeeded)
+
+	/* skb is already created with CHECKSUM_NONE */
+	skb_checksum_none_assert(skb);
+
+	/*
+	 * In Linux, the IP checksum is always checked.
+	 * Do L4 checksum offload if enabled and present.
+	 */
+	if (csum_info && (net->features & NETIF_F_RXCSUM)) {
+		if (csum_info->receive.tcp_checksum_succeeded ||
+		    csum_info->receive.udp_checksum_succeeded)
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
-		else
-			skb->ip_summed = CHECKSUM_NONE;
 	}
 
 	if (vlan_tci & VLAN_TAG_PRESENT)
-- 
2.4.11


From 1d8ef2d8a214237191a6156e647a8998e34afb53 Mon Sep 17 00:00:00 2001
From: Tobias Brunner <tobias@strongswan.org>
Date: Mon, 24 Oct 2016 15:44:26 +0200
Subject: [PATCH 28/34] macsec: Fix header length if SCI is added if explicitly
 disabled

[ Upstream commit e0f841f5cbf2a195c63f3441f3d8ef1cd2bdeeed ]

Even if sending SCIs is explicitly disabled, the code that creates the
Security Tag might still decide to add it (e.g. if multiple RX SCs are
defined on the MACsec interface).
But because the header length so far only depended on the configuration
option the SCI overwrote the original frame's contents (EtherType and
e.g. the beginning of the IP header) and if encrypted did not visibly
end up in the packet, while the SC flag in the TCI field of the Security
Tag was still set, resulting in invalid MACsec frames.

Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver")
Signed-off-by: Tobias Brunner <tobias@strongswan.org>
Acked-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macsec.c | 26 ++++++++++++++++++--------
 1 file changed, 18 insertions(+), 8 deletions(-)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 351e701..b72ddc6 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -397,6 +397,14 @@ static struct macsec_cb *macsec_skb_cb(struct sk_buff *skb)
 #define DEFAULT_ENCRYPT false
 #define DEFAULT_ENCODING_SA 0
 
+static bool send_sci(const struct macsec_secy *secy)
+{
+	const struct macsec_tx_sc *tx_sc = &secy->tx_sc;
+
+	return tx_sc->send_sci ||
+		(secy->n_rx_sc > 1 && !tx_sc->end_station && !tx_sc->scb);
+}
+
 static sci_t make_sci(u8 *addr, __be16 port)
 {
 	sci_t sci;
@@ -437,15 +445,15 @@ static unsigned int macsec_extra_len(bool sci_present)
 
 /* Fill SecTAG according to IEEE 802.1AE-2006 10.5.3 */
 static void macsec_fill_sectag(struct macsec_eth_header *h,
-			       const struct macsec_secy *secy, u32 pn)
+			       const struct macsec_secy *secy, u32 pn,
+			       bool sci_present)
 {
 	const struct macsec_tx_sc *tx_sc = &secy->tx_sc;
 
-	memset(&h->tci_an, 0, macsec_sectag_len(tx_sc->send_sci));
+	memset(&h->tci_an, 0, macsec_sectag_len(sci_present));
 	h->eth.h_proto = htons(ETH_P_MACSEC);
 
-	if (tx_sc->send_sci ||
-	    (secy->n_rx_sc > 1 && !tx_sc->end_station && !tx_sc->scb)) {
+	if (sci_present) {
 		h->tci_an |= MACSEC_TCI_SC;
 		memcpy(&h->secure_channel_id, &secy->sci,
 		       sizeof(h->secure_channel_id));
@@ -650,6 +658,7 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb,
 	struct macsec_tx_sc *tx_sc;
 	struct macsec_tx_sa *tx_sa;
 	struct macsec_dev *macsec = macsec_priv(dev);
+	bool sci_present;
 	u32 pn;
 
 	secy = &macsec->secy;
@@ -687,7 +696,8 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb,
 
 	unprotected_len = skb->len;
 	eth = eth_hdr(skb);
-	hh = (struct macsec_eth_header *)skb_push(skb, macsec_extra_len(tx_sc->send_sci));
+	sci_present = send_sci(secy);
+	hh = (struct macsec_eth_header *)skb_push(skb, macsec_extra_len(sci_present));
 	memmove(hh, eth, 2 * ETH_ALEN);
 
 	pn = tx_sa_update_pn(tx_sa, secy);
@@ -696,7 +706,7 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb,
 		kfree_skb(skb);
 		return ERR_PTR(-ENOLINK);
 	}
-	macsec_fill_sectag(hh, secy, pn);
+	macsec_fill_sectag(hh, secy, pn, sci_present);
 	macsec_set_shortlen(hh, unprotected_len - 2 * ETH_ALEN);
 
 	skb_put(skb, secy->icv_len);
@@ -726,10 +736,10 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb,
 	skb_to_sgvec(skb, sg, 0, skb->len);
 
 	if (tx_sc->encrypt) {
-		int len = skb->len - macsec_hdr_len(tx_sc->send_sci) -
+		int len = skb->len - macsec_hdr_len(sci_present) -
 			  secy->icv_len;
 		aead_request_set_crypt(req, sg, sg, len, iv);
-		aead_request_set_ad(req, macsec_hdr_len(tx_sc->send_sci));
+		aead_request_set_ad(req, macsec_hdr_len(sci_present));
 	} else {
 		aead_request_set_crypt(req, sg, sg, 0, iv);
 		aead_request_set_ad(req, skb->len - secy->icv_len);
-- 
2.4.11


From 4e3d615c3e054661432ab506cec5776ba845be67 Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Mon, 24 Oct 2016 12:27:23 -0700
Subject: [PATCH 29/34] net: ipv6: Do not consider link state for nexthop
 validation

[ Upstream commit d5d32e4b76687f4df9ad3ba8d3702b7347f51fa6 ]

Similar to IPv4, do not consider link state when validating next hops.

Currently, if the link is down default routes can fail to insert:
 $ ip -6 ro add vrf blue default via 2100:2::64 dev eth2
 RTNETLINK answers: No route to host

With this patch the command succeeds.

Fixes: 8c14586fc320 ("net: ipv6: Use passed in table for nexthop lookups")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_route.h | 1 +
 net/ipv6/route.c        | 6 ++++--
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index d97305d..0a2d270 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -32,6 +32,7 @@ struct route_info {
 #define RT6_LOOKUP_F_SRCPREF_TMP	0x00000008
 #define RT6_LOOKUP_F_SRCPREF_PUBLIC	0x00000010
 #define RT6_LOOKUP_F_SRCPREF_COA	0x00000020
+#define RT6_LOOKUP_F_IGNORE_LINKSTATE	0x00000040
 
 /* We do not (yet ?) support IPv6 jumbograms (RFC 2675)
  * Unlike IPv4, hdr->seg_len doesn't include the IPv6 header
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 269218a..23153ac 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -656,7 +656,8 @@ static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict,
 	struct net_device *dev = rt->dst.dev;
 
 	if (dev && !netif_carrier_ok(dev) &&
-	    idev->cnf.ignore_routes_with_linkdown)
+	    idev->cnf.ignore_routes_with_linkdown &&
+	    !(strict & RT6_LOOKUP_F_IGNORE_LINKSTATE))
 		goto out;
 
 	if (rt6_check_expired(rt))
@@ -1050,6 +1051,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 	int strict = 0;
 
 	strict |= flags & RT6_LOOKUP_F_IFACE;
+	strict |= flags & RT6_LOOKUP_F_IGNORE_LINKSTATE;
 	if (net->ipv6.devconf_all->forwarding == 0)
 		strict |= RT6_LOOKUP_F_REACHABLE;
 
@@ -1783,7 +1785,7 @@ static struct rt6_info *ip6_nh_lookup_table(struct net *net,
 	};
 	struct fib6_table *table;
 	struct rt6_info *rt;
-	int flags = RT6_LOOKUP_F_IFACE;
+	int flags = RT6_LOOKUP_F_IFACE | RT6_LOOKUP_F_IGNORE_LINKSTATE;
 
 	table = fib6_get_table(net, cfg->fc_table);
 	if (!table)
-- 
2.4.11


From 7613442378b6e041fd48fe31a7f4a689a7715e0a Mon Sep 17 00:00:00 2001
From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Mon, 24 Oct 2016 20:18:27 -0400
Subject: [PATCH 30/34] net sched filters: fix notification of filter delete
 with proper handle

[ Upstream commit 9ee7837449b3d6f0fcf9132c6b5e5aaa58cc67d4 ]

Daniel says:

While trying out [1][2], I noticed that tc monitor doesn't show the
correct handle on delete:

$ tc monitor
qdisc clsact ffff: dev eno1 parent ffff:fff1
filter dev eno1 ingress protocol all pref 49152 bpf handle 0x2a [...]
deleted filter dev eno1 ingress protocol all pref 49152 bpf handle 0xf3be0c80

some context to explain the above:
The user identity of any tc filter is represented by a 32-bit
identifier encoded in tcm->tcm_handle. Example 0x2a in the bpf filter
above. A user wishing to delete, get or even modify a specific filter
uses this handle to reference it.
Every classifier is free to provide its own semantics for the 32 bit handle.
Example: classifiers like u32 use schemes like 800:1:801 to describe
the semantics of their filters represented as hash table, bucket and
node ids etc.
Classifiers also have internal per-filter representation which is different
from this externally visible identity. Most classifiers set this
internal representation to be a pointer address (which allows fast retrieval
of said filters in their implementations). This internal representation
is referenced with the "fh" variable in the kernel control code.

When a user successfuly deletes a specific filter, by specifying the correct
tcm->tcm_handle, an event is generated to user space which indicates
which specific filter was deleted.

Before this patch, the "fh" value was sent to user space as the identity.
As an example what is shown in the sample bpf filter delete event above
is 0xf3be0c80. This is infact a 32-bit truncation of 0xffff8807f3be0c80
which happens to be a 64-bit memory address of the internal filter
representation (address of the corresponding filter's struct cls_bpf_prog);

After this patch the appropriate user identifiable handle as encoded
in the originating request tcm->tcm_handle is generated in the event.
One of the cardinal rules of netlink rules is to be able to take an
event (such as a delete in this case) and reflect it back to the
kernel and successfully delete the filter. This patch achieves that.

Note, this issue has existed since the original TC action
infrastructure code patch back in 2004 as found in:
https://git.kernel.org/cgit/linux/kernel/git/history/history.git/commit/

[1] http://patchwork.ozlabs.org/patch/682828/
[2] http://patchwork.ozlabs.org/patch/682829/

Fixes: 4e54c4816bfe ("[NET]: Add tc extensions infrastructure.")
Reported-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index a7c5645..74bed5e 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -344,7 +344,8 @@ replay:
 			if (err == 0) {
 				struct tcf_proto *next = rtnl_dereference(tp->next);
 
-				tfilter_notify(net, skb, n, tp, fh, RTM_DELTFILTER);
+				tfilter_notify(net, skb, n, tp,
+					       t->tcm_handle, RTM_DELTFILTER);
 				if (tcf_destroy(tp, false))
 					RCU_INIT_POINTER(*back, next);
 			}
-- 
2.4.11


From 617726d78c6febeb60a7a222cdda13512671d9f6 Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Tue, 25 Oct 2016 14:27:39 -0200
Subject: [PATCH 31/34] sctp: validate chunk len before actually using it

[ Upstream commit bf911e985d6bbaa328c20c3e05f4eb03de11fdd6 ]

Andrey Konovalov reported that KASAN detected that SCTP was using a slab
beyond the boundaries. It was caused because when handling out of the
blue packets in function sctp_sf_ootb() it was checking the chunk len
only after already processing the first chunk, validating only for the
2nd and subsequent ones.

The fix is to just move the check upwards so it's also validated for the
1st chunk.

Reported-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sm_statefuns.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index d88bb2b..920469e 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -3422,6 +3422,12 @@ sctp_disposition_t sctp_sf_ootb(struct net *net,
 			return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
 						  commands);
 
+		/* Report violation if chunk len overflows */
+		ch_end = ((__u8 *)ch) + WORD_ROUND(ntohs(ch->length));
+		if (ch_end > skb_tail_pointer(skb))
+			return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
+						  commands);
+
 		/* Now that we know we at least have a chunk header,
 		 * do things that are type appropriate.
 		 */
@@ -3453,12 +3459,6 @@ sctp_disposition_t sctp_sf_ootb(struct net *net,
 			}
 		}
 
-		/* Report violation if chunk len overflows */
-		ch_end = ((__u8 *)ch) + WORD_ROUND(ntohs(ch->length));
-		if (ch_end > skb_tail_pointer(skb))
-			return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
-						  commands);
-
 		ch = (sctp_chunkhdr_t *) ch_end;
 	} while (ch_end < skb_tail_pointer(skb));
 
-- 
2.4.11


From 9fcafe4c38b6ca6fc0e8814bb0e38d3ac162be45 Mon Sep 17 00:00:00 2001
From: Eli Cooper <elicooper@gmx.com>
Date: Wed, 26 Oct 2016 10:11:09 +0800
Subject: [PATCH 32/34] ip6_tunnel: Update skb->protocol to ETH_P_IPV6 in
 ip6_tnl_xmit()

[ Upstream commit ae148b085876fa771d9ef2c05f85d4b4bf09ce0d ]

This patch updates skb->protocol to ETH_P_IPV6 in ip6_tnl_xmit() when an
IPv6 header is installed to a socket buffer.

This is not a cosmetic change.  Without updating this value, GSO packets
transmitted through an ipip6 tunnel have the protocol of ETH_P_IP and
skb_mac_gso_segment() will attempt to call gso_segment() for IPv4,
which results in the packets being dropped.

Fixes: b8921ca83eed ("ip4ip6: Support for GSO/GRO")
Signed-off-by: Eli Cooper <elicooper@gmx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 41a6479..41489f3 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1134,6 +1134,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 	if (err)
 		return err;
 
+	skb->protocol = htons(ETH_P_IPV6);
 	skb_push(skb, sizeof(struct ipv6hdr));
 	skb_reset_network_header(skb);
 	ipv6h = ipv6_hdr(skb);
-- 
2.4.11


From 00d8e5f966e912e11a85a3b6d750edd622caa29e Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 26 Oct 2016 11:23:07 -0400
Subject: [PATCH 33/34] packet: on direct_xmit, limit tso and csum to supported
 devices

[ Upstream commit 104ba78c98808ae837d1f63aae58c183db5505df ]

When transmitting on a packet socket with PACKET_VNET_HDR and
PACKET_QDISC_BYPASS, validate device support for features requested
in vnet_hdr.

Drop TSO packets sent to devices that do not support TSO or have the
feature disabled. Note that the latter currently do process those
packets correctly, regardless of not advertising the feature.

Because of SKB_GSO_DODGY, it is not sufficient to test device features
with netif_needs_gso. Full validate_xmit_skb is needed.

Switch to software checksum for non-TSO packets that request checksum
offload if that device feature is unsupported or disabled. Note that
similar to the TSO case, device drivers may perform checksum offload
correctly even when not advertising it.

When switching to software checksum, packets hit skb_checksum_help,
which has two BUG_ON checksum not in linear segment. Packet sockets
always allocate at least up to csum_start + csum_off + 2 as linear.

Tested by running github.com/wdebruij/kerneltools/psock_txring_vnet.c

  ethtool -K eth0 tso off tx on
  psock_txring_vnet -d $dst -s $src -i eth0 -l 2000 -n 1 -q -v
  psock_txring_vnet -d $dst -s $src -i eth0 -l 2000 -n 1 -q -v -N

  ethtool -K eth0 tx off
  psock_txring_vnet -d $dst -s $src -i eth0 -l 1000 -n 1 -q -v -G
  psock_txring_vnet -d $dst -s $src -i eth0 -l 1000 -n 1 -q -v -G -N

v2:
  - add EXPORT_SYMBOL_GPL(validate_xmit_skb_list)

Fixes: d346a3fae3ff ("packet: introduce PACKET_QDISC_BYPASS socket option")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c         | 1 +
 net/packet/af_packet.c | 9 ++++-----
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index fc63c6d..44b3ba4 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3035,6 +3035,7 @@ struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *d
 	}
 	return head;
 }
+EXPORT_SYMBOL_GPL(validate_xmit_skb_list);
 
 static void qdisc_pkt_len_init(struct sk_buff *skb)
 {
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 11db0d6..d2238b2 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -250,7 +250,7 @@ static void __fanout_link(struct sock *sk, struct packet_sock *po);
 static int packet_direct_xmit(struct sk_buff *skb)
 {
 	struct net_device *dev = skb->dev;
-	netdev_features_t features;
+	struct sk_buff *orig_skb = skb;
 	struct netdev_queue *txq;
 	int ret = NETDEV_TX_BUSY;
 
@@ -258,9 +258,8 @@ static int packet_direct_xmit(struct sk_buff *skb)
 		     !netif_carrier_ok(dev)))
 		goto drop;
 
-	features = netif_skb_features(skb);
-	if (skb_needs_linearize(skb, features) &&
-	    __skb_linearize(skb))
+	skb = validate_xmit_skb_list(skb, dev);
+	if (skb != orig_skb)
 		goto drop;
 
 	txq = skb_get_tx_queue(dev, skb);
@@ -280,7 +279,7 @@ static int packet_direct_xmit(struct sk_buff *skb)
 	return ret;
 drop:
 	atomic_long_inc(&dev->tx_dropped);
-	kfree_skb(skb);
+	kfree_skb_list(skb);
 	return NET_XMIT_DROP;
 }
 
-- 
2.4.11


From eba1680c5778558499d523bd10cac9f440f5d58e Mon Sep 17 00:00:00 2001
From: Ivan Vecera <ivecera@redhat.com>
Date: Thu, 27 Oct 2016 16:30:06 +0200
Subject: [PATCH 34/34] arch/powerpc: Update parameters for csum_tcpudp_magic &
 csum_tcpudp_nofold

[ Upstream commit f9d4286b9516b02e795214412d36885f572b57ad ]

Commit 01cfbad "ipv4: Update parameters for csum_tcpudp_magic to their
original types" changed parameters for csum_tcpudp_magic and
csum_tcpudp_nofold for many platforms but not for PowerPC.

Fixes: 01cfbad "ipv4: Update parameters for csum_tcpudp_magic to their original types"
Cc: Alexander Duyck <aduyck@mirantis.com>
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Acked-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/powerpc/include/asm/checksum.h | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h
index ee655ed..1e8fceb 100644
--- a/arch/powerpc/include/asm/checksum.h
+++ b/arch/powerpc/include/asm/checksum.h
@@ -53,10 +53,8 @@ static inline __sum16 csum_fold(__wsum sum)
 	return (__force __sum16)(~((__force u32)sum + tmp) >> 16);
 }
 
-static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
-                                     unsigned short len,
-                                     unsigned short proto,
-                                     __wsum sum)
+static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len,
+					__u8 proto, __wsum sum)
 {
 #ifdef __powerpc64__
 	unsigned long s = (__force u32)sum;
@@ -83,10 +81,8 @@ static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
  * computes the checksum of the TCP/UDP pseudo-header
  * returns a 16-bit checksum, already complemented
  */
-static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
-					unsigned short len,
-					unsigned short proto,
-					__wsum sum)
+static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len,
+					__u8 proto, __wsum sum)
 {
 	return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
 }
-- 
2.4.11

Re: [PATCHES] Networking

[Greg KH]

On Wed, Nov 09, 2016 at 12:19:39PM -0500, David Miller wrote:
> 
> Please queue up the following networking bug fixes for 4.4.x and 4.8.x
> -stable, respectively.

Thanks for these, all now applied.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 104 bytes --]


Please queue up the following networking bug fixes for 4.4.x and 4.8.x
-stable, respectively.

Thanks!

[-- Attachment #2: net_44.mbox --]
[-- Type: Application/Octet-Stream, Size: 35259 bytes --]

From 11c5825a2b2837c14412712d7e9cffd6bda2f215 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 28 Oct 2016 18:43:11 +0200
Subject: [PATCH 01/16] dctcp: avoid bogus doubling of cwnd after loss

[ Upstream commit ce6dd23329b1ee6a794acf5f7e40f8e89b8317ee ]

If a congestion control module doesn't provide .undo_cwnd function,
tcp_undo_cwnd_reduction() will set cwnd to

   tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh << 1);

... which makes sense for reno (it sets ssthresh to half the current cwnd),
but it makes no sense for dctcp, which sets ssthresh based on the current
congestion estimate.

This can cause severe growth of cwnd (eventually overflowing u32).

Fix this by saving last cwnd on loss and restore cwnd based on that,
similar to cubic and other algorithms.

Fixes: e3118e8359bb7c ("net: tcp: add DCTCP congestion control algorithm")
Cc: Lawrence Brakmo <brakmo@fb.com>
Cc: Andrew Shewmaker <agshew@gmail.com>
Cc: Glenn Judd <glenn.judd@morganstanley.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_dctcp.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 7e538f7..55d7da1 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -56,6 +56,7 @@ struct dctcp {
 	u32 next_seq;
 	u32 ce_state;
 	u32 delayed_ack_reserved;
+	u32 loss_cwnd;
 };
 
 static unsigned int dctcp_shift_g __read_mostly = 4; /* g = 1/2^4 */
@@ -96,6 +97,7 @@ static void dctcp_init(struct sock *sk)
 		ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA);
 
 		ca->delayed_ack_reserved = 0;
+		ca->loss_cwnd = 0;
 		ca->ce_state = 0;
 
 		dctcp_reset(tp, ca);
@@ -111,9 +113,10 @@ static void dctcp_init(struct sock *sk)
 
 static u32 dctcp_ssthresh(struct sock *sk)
 {
-	const struct dctcp *ca = inet_csk_ca(sk);
+	struct dctcp *ca = inet_csk_ca(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 
+	ca->loss_cwnd = tp->snd_cwnd;
 	return max(tp->snd_cwnd - ((tp->snd_cwnd * ca->dctcp_alpha) >> 11U), 2U);
 }
 
@@ -308,12 +311,20 @@ static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr,
 	return 0;
 }
 
+static u32 dctcp_cwnd_undo(struct sock *sk)
+{
+	const struct dctcp *ca = inet_csk_ca(sk);
+
+	return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd);
+}
+
 static struct tcp_congestion_ops dctcp __read_mostly = {
 	.init		= dctcp_init,
 	.in_ack_event   = dctcp_update_alpha,
 	.cwnd_event	= dctcp_cwnd_event,
 	.ssthresh	= dctcp_ssthresh,
 	.cong_avoid	= tcp_reno_cong_avoid,
+	.undo_cwnd	= dctcp_cwnd_undo,
 	.set_state	= dctcp_state,
 	.get_info	= dctcp_get_info,
 	.flags		= TCP_CONG_NEEDS_ECN,
-- 
2.7.4


From 7c19c99d681ecd2735c92c3720a773de94c3e720 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 28 Oct 2016 13:40:24 -0700
Subject: [PATCH 02/16] net: clear sk_err_soft in sk_clone_lock()

[ Upstream commit e551c32d57c88923f99f8f010e89ca7ed0735e83 ]

At accept() time, it is possible the parent has a non zero
sk_err_soft, leftover from a prior error.

Make sure we do not leave this value in the child, as it
makes future getsockopt(SO_ERROR) calls quite unreliable.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/core/sock.c b/net/core/sock.c
index 0d91f7d..88f01785 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1562,6 +1562,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		}
 
 		newsk->sk_err	   = 0;
+		newsk->sk_err_soft = 0;
 		newsk->sk_priority = 0;
 		newsk->sk_incoming_cpu = raw_smp_processor_id();
 		atomic64_set(&newsk->sk_cookie, 0);
-- 
2.7.4


From ce2454556c4bdd23af78cd9b633fe51cff0b5d9a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 29 Oct 2016 11:02:36 -0700
Subject: [PATCH 03/16] net: mangle zero checksum in skb_checksum_help()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 4f2e4ad56a65f3b7d64c258e373cb71e8d2499f4 ]

Sending zero checksum is ok for TCP, but not for UDP.

UDPv6 receiver should by default drop a frame with a 0 checksum,
and UDPv4 would not verify the checksum and might accept a corrupted
packet.

Simply replace such checksum by 0xffff, regardless of transport.

This error was caught on SIT tunnels, but seems generic.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Maciej Żenczykowski <maze@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Acked-by: Maciej Żenczykowski <maze@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index b3fa4b8..9ca749c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2462,7 +2462,7 @@ int skb_checksum_help(struct sk_buff *skb)
 			goto out;
 	}
 
-	*(__sum16 *)(skb->data + offset) = csum_fold(csum);
+	*(__sum16 *)(skb->data + offset) = csum_fold(csum) ?: CSUM_MANGLED_0;
 out_set_summed:
 	skb->ip_summed = CHECKSUM_NONE;
 out:
-- 
2.7.4


From 915230c4a2650d31b08f375c6324b444e17820cd Mon Sep 17 00:00:00 2001
From: Andy Gospodarek <gospo@broadcom.com>
Date: Mon, 31 Oct 2016 13:32:03 -0400
Subject: [PATCH 04/16] bgmac: stop clearing DMA receive control register right
 after it is set

[ Upstream commit fcdefccac976ee51dd6071832b842d8fb41c479c ]

Current bgmac code initializes some DMA settings in the receive control
register for some hardware and then immediately clears those settings.
Not clearing those settings results in ~420Mbps *improvement* in
throughput; this system can now receive frames at line-rate on Broadcom
5871x hardware compared to ~520Mbps today.  I also tested a few other
values but found there to be no discernible difference in CPU
utilization even if burst size and prefetching values are different.

On the hardware tested there was no need to keep the code that cleared
all but bits 16-17, but since there is a wide variety of hardware that
used this driver (I did not look at all hardware docs for hardware using
this IP block), I find it wise to move this call up and clear bits just
after reading the default value from the hardware rather than completely
removing it.

This is a good candidate for -stable >=3.14 since that is when the code
that was supposed to improve performance (but did not) was introduced.

Signed-off-by: Andy Gospodarek <gospo@broadcom.com>
Fixes: 56ceecde1f29 ("bgmac: initialize the DMA controller of core...")
Cc: Hauke Mehrtens <hauke@hauke-m.de>
Acked-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bgmac.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index c32f5d3..b56c9c5 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -314,6 +314,10 @@ static void bgmac_dma_rx_enable(struct bgmac *bgmac,
 	u32 ctl;
 
 	ctl = bgmac_read(bgmac, ring->mmio_base + BGMAC_DMA_RX_CTL);
+
+	/* preserve ONLY bits 16-17 from current hardware value */
+	ctl &= BGMAC_DMA_RX_ADDREXT_MASK;
+
 	if (bgmac->core->id.rev >= 4) {
 		ctl &= ~BGMAC_DMA_RX_BL_MASK;
 		ctl |= BGMAC_DMA_RX_BL_128 << BGMAC_DMA_RX_BL_SHIFT;
@@ -324,7 +328,6 @@ static void bgmac_dma_rx_enable(struct bgmac *bgmac,
 		ctl &= ~BGMAC_DMA_RX_PT_MASK;
 		ctl |= BGMAC_DMA_RX_PT_1 << BGMAC_DMA_RX_PT_SHIFT;
 	}
-	ctl &= BGMAC_DMA_RX_ADDREXT_MASK;
 	ctl |= BGMAC_DMA_RX_ENABLE;
 	ctl |= BGMAC_DMA_RX_PARITY_DISABLE;
 	ctl |= BGMAC_DMA_RX_OVERFLOW_CONT;
-- 
2.7.4


From f96cc2877fe13a9576092ab8e758e6c49ed7c513 Mon Sep 17 00:00:00 2001
From: Eli Cooper <elicooper@gmx.com>
Date: Tue, 1 Nov 2016 23:45:12 +0800
Subject: [PATCH 05/16] ip6_tunnel: Clear IP6CB in ip6tunnel_xmit()

[ Upstream commit 23f4ffedb7d751c7e298732ba91ca75d224bc1a6 ]

skb->cb may contain data from previous layers. In the observed scenario,
the garbage data were misinterpreted as IP6CB(skb)->frag_max_size, so
that small packets sent through the tunnel are mistakenly fragmented.

This patch unconditionally clears the control buffer in ip6tunnel_xmit(),
which affects ip6_tunnel, ip6_udp_tunnel and ip6_gre. Currently none of
these tunnels set IP6CB(skb)->flags, otherwise it needs to be done earlier.

Cc: stable@vger.kernel.org
Signed-off-by: Eli Cooper <elicooper@gmx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_tunnel.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index ff788b6..9c2c044 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -86,6 +86,7 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb,
 	struct net_device_stats *stats = &dev->stats;
 	int pkt_len, err;
 
+	memset(skb->cb, 0, sizeof(struct inet6_skb_parm));
 	pkt_len = skb->len - skb_inner_network_offset(skb);
 	err = ip6_local_out(dev_net(skb_dst(skb)->dev), sk, skb);
 
-- 
2.7.4


From dea0cf81c76795ce9cf6673c423f701129e3c8cc Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 2 Nov 2016 07:53:17 -0700
Subject: [PATCH 06/16] tcp: fix potential memory corruption
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit ac9e70b17ecd7c6e933ff2eaf7ab37429e71bf4d ]

Imagine initial value of max_skb_frags is 17, and last
skb in write queue has 15 frags.

Then max_skb_frags is lowered to 14 or smaller value.

tcp_sendmsg() will then be allowed to add additional page frags
and eventually go past MAX_SKB_FRAGS, overflowing struct
skb_shared_info.

Fixes: 5f74f82ea34c ("net:Add sysctl_max_skb_frags")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Hans Westgaard Ry <hans.westgaard.ry@oracle.com>
Cc: Håkon Bugge <haakon.bugge@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 036a76b..69daa81 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1212,7 +1212,7 @@ new_segment:
 
 			if (!skb_can_coalesce(skb, i, pfrag->page,
 					      pfrag->offset)) {
-				if (i == sysctl_max_skb_frags || !sg) {
+				if (i >= sysctl_max_skb_frags || !sg) {
 					tcp_mark_push(tp, skb);
 					goto new_segment;
 				}
-- 
2.7.4


From 860aaae2606c334931b9ad35a01edaecb46c1c5e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 2 Nov 2016 18:04:24 -0700
Subject: [PATCH 07/16] dccp: do not send reset to already closed sockets

[ Upstream commit 346da62cc186c4b4b1ac59f87f4482b47a047388 ]

Andrey reported following warning while fuzzing with syzkaller

WARNING: CPU: 1 PID: 21072 at net/dccp/proto.c:83 dccp_set_state+0x229/0x290
Kernel panic - not syncing: panic_on_warn set ...

CPU: 1 PID: 21072 Comm: syz-executor Not tainted 4.9.0-rc1+ #293
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
 ffff88003d4c7738 ffffffff81b474f4 0000000000000003 dffffc0000000000
 ffffffff844f8b00 ffff88003d4c7804 ffff88003d4c7800 ffffffff8140c06a
 0000000041b58ab3 ffffffff8479ab7d ffffffff8140beae ffffffff8140cd00
Call Trace:
 [<     inline     >] __dump_stack lib/dump_stack.c:15
 [<ffffffff81b474f4>] dump_stack+0xb3/0x10f lib/dump_stack.c:51
 [<ffffffff8140c06a>] panic+0x1bc/0x39d kernel/panic.c:179
 [<ffffffff8111125c>] __warn+0x1cc/0x1f0 kernel/panic.c:542
 [<ffffffff8111144c>] warn_slowpath_null+0x2c/0x40 kernel/panic.c:585
 [<ffffffff8389e5d9>] dccp_set_state+0x229/0x290 net/dccp/proto.c:83
 [<ffffffff838a0aa2>] dccp_close+0x612/0xc10 net/dccp/proto.c:1016
 [<ffffffff8316bf1f>] inet_release+0xef/0x1c0 net/ipv4/af_inet.c:415
 [<ffffffff82b6e89e>] sock_release+0x8e/0x1d0 net/socket.c:570
 [<ffffffff82b6e9f6>] sock_close+0x16/0x20 net/socket.c:1017
 [<ffffffff815256ad>] __fput+0x29d/0x720 fs/file_table.c:208
 [<ffffffff81525bb5>] ____fput+0x15/0x20 fs/file_table.c:244
 [<ffffffff811727d8>] task_work_run+0xf8/0x170 kernel/task_work.c:116
 [<     inline     >] exit_task_work include/linux/task_work.h:21
 [<ffffffff8111bc53>] do_exit+0x883/0x2ac0 kernel/exit.c:828
 [<ffffffff811221fe>] do_group_exit+0x10e/0x340 kernel/exit.c:931
 [<ffffffff81143c94>] get_signal+0x634/0x15a0 kernel/signal.c:2307
 [<ffffffff81054aad>] do_signal+0x8d/0x1a30 arch/x86/kernel/signal.c:807
 [<ffffffff81003a05>] exit_to_usermode_loop+0xe5/0x130
arch/x86/entry/common.c:156
 [<     inline     >] prepare_exit_to_usermode arch/x86/entry/common.c:190
 [<ffffffff81006298>] syscall_return_slowpath+0x1a8/0x1e0
arch/x86/entry/common.c:259
 [<ffffffff83fc1a62>] entry_SYSCALL_64_fastpath+0xc0/0xc2
Dumping ftrace buffer:
   (ftrace buffer empty)
Kernel Offset: disabled

Fix this the same way we did for TCP in commit 565b7b2d2e63
("tcp: do not send reset to already closed sockets")

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/proto.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 41e6580..9fe25bf 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -1009,6 +1009,10 @@ void dccp_close(struct sock *sk, long timeout)
 		__kfree_skb(skb);
 	}
 
+	/* If socket has been already reset kill it. */
+	if (sk->sk_state == DCCP_CLOSED)
+		goto adjudge_to_death;
+
 	if (data_was_unread) {
 		/* Unread data was tossed, send an appropriate Reset Code */
 		DCCP_WARN("ABORT with %u bytes unread\n", data_was_unread);
-- 
2.7.4


From fcc00b1ac8a7897b8ad220f665105afb5e42520a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 2 Nov 2016 19:00:40 -0700
Subject: [PATCH 08/16] dccp: fix out of bound access in dccp_v4_err()

[ Upstream commit 6706a97fec963d6cb3f7fc2978ec1427b4651214 ]

dccp_v4_err() does not use pskb_may_pull() and might access garbage.

We only need 4 bytes at the beginning of the DCCP header, like TCP,
so the 8 bytes pulled in icmp_socket_deliver() are more than enough.

This patch might allow to process more ICMP messages, as some routers
are still limiting the size of reflected bytes to 28 (RFC 792), instead
of extended lengths (RFC 1812 4.3.2.3)

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ipv4.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 8be8f27..861e1fa 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -235,7 +235,7 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
 {
 	const struct iphdr *iph = (struct iphdr *)skb->data;
 	const u8 offset = iph->ihl << 2;
-	const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset);
+	const struct dccp_hdr *dh;
 	struct dccp_sock *dp;
 	struct inet_sock *inet;
 	const int type = icmp_hdr(skb)->type;
@@ -245,11 +245,13 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
 	int err;
 	struct net *net = dev_net(skb->dev);
 
-	if (skb->len < offset + sizeof(*dh) ||
-	    skb->len < offset + __dccp_basic_hdr_len(dh)) {
-		ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS);
-		return;
-	}
+	/* Only need dccph_dport & dccph_sport which are the first
+	 * 4 bytes in dccp header.
+	 * Our caller (icmp_socket_deliver()) already pulled 8 bytes for us.
+	 */
+	BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_sport) > 8);
+	BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_dport) > 8);
+	dh = (struct dccp_hdr *)(skb->data + offset);
 
 	sk = __inet_lookup_established(net, &dccp_hashinfo,
 				       iph->daddr, dh->dccph_dport,
-- 
2.7.4


From 5c8428bc80d0e171084279e2dff64fffb984a490 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 2 Nov 2016 20:30:48 -0700
Subject: [PATCH 09/16] ipv6: dccp: fix out of bound access in dccp_v6_err()

[ Upstream commit 1aa9d1a0e7eefcc61696e147d123453fc0016005 ]

dccp_v6_err() does not use pskb_may_pull() and might access garbage.

We only need 4 bytes at the beginning of the DCCP header, like TCP,
so the 8 bytes pulled in icmpv6_notify() are more than enough.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ipv6.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index b8608b7..0773b64 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -70,7 +70,7 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 			u8 type, u8 code, int offset, __be32 info)
 {
 	const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
-	const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset);
+	const struct dccp_hdr *dh;
 	struct dccp_sock *dp;
 	struct ipv6_pinfo *np;
 	struct sock *sk;
@@ -78,12 +78,13 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	__u64 seq;
 	struct net *net = dev_net(skb->dev);
 
-	if (skb->len < offset + sizeof(*dh) ||
-	    skb->len < offset + __dccp_basic_hdr_len(dh)) {
-		ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev),
-				   ICMP6_MIB_INERRORS);
-		return;
-	}
+	/* Only need dccph_dport & dccph_sport which are the first
+	 * 4 bytes in dccp header.
+	 * Our caller (icmpv6_notify()) already pulled 8 bytes for us.
+	 */
+	BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_sport) > 8);
+	BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_dport) > 8);
+	dh = (struct dccp_hdr *)(skb->data + offset);
 
 	sk = __inet6_lookup_established(net, &dccp_hashinfo,
 					&hdr->daddr, dh->dccph_dport,
-- 
2.7.4


From 67130aef4e227367d9f4a32d629355f273b650d4 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 3 Nov 2016 08:59:46 -0700
Subject: [PATCH 10/16] ipv6: dccp: add missing bind_conflict to
 dccp_ipv6_mapped

[ Upstream commit 990ff4d84408fc55942ca6644f67e361737b3d8e ]

While fuzzing kernel with syzkaller, Andrey reported a nasty crash
in inet6_bind() caused by DCCP lacking a required method.

Fixes: ab1e0a13d7029 ("[SOCK] proto: Add hashinfo member to struct proto")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ipv6.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 0773b64..27c4e81 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -948,6 +948,7 @@ static const struct inet_connection_sock_af_ops dccp_ipv6_mapped = {
 	.getsockopt	   = ipv6_getsockopt,
 	.addr2sockaddr	   = inet6_csk_addr2sockaddr,
 	.sockaddr_len	   = sizeof(struct sockaddr_in6),
+	.bind_conflict	   = inet6_csk_bind_conflict,
 #ifdef CONFIG_COMPAT
 	.compat_setsockopt = compat_ipv6_setsockopt,
 	.compat_getsockopt = compat_ipv6_getsockopt,
-- 
2.7.4


From caa025300de2e16a58f5afe6b92adb97700c4651 Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Thu, 3 Nov 2016 17:03:41 -0200
Subject: [PATCH 11/16] sctp: assign assoc_id earlier in __sctp_connect

[ Upstream commit 7233bc84a3aeda835d334499dc00448373caf5c0 ]

sctp_wait_for_connect() currently already holds the asoc to keep it
alive during the sleep, in case another thread release it. But Andrey
Konovalov and Dmitry Vyukov reported an use-after-free in such
situation.

Problem is that __sctp_connect() doesn't get a ref on the asoc and will
do a read on the asoc after calling sctp_wait_for_connect(), but by then
another thread may have closed it and the _put on sctp_wait_for_connect
will actually release it, causing the use-after-free.

Fix is, instead of doing the read after waiting for the connect, do it
before so, and avoid this issue as the socket is still locked by then.
There should be no issue on returning the asoc id in case of failure as
the application shouldn't trust on that number in such situations
anyway.

This issue doesn't exist in sctp_sendmsg() path.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 402817b..b5fd4ab 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1212,9 +1212,12 @@ static int __sctp_connect(struct sock *sk,
 
 	timeo = sock_sndtimeo(sk, f_flags & O_NONBLOCK);
 
-	err = sctp_wait_for_connect(asoc, &timeo);
-	if ((err == 0 || err == -EINPROGRESS) && assoc_id)
+	if (assoc_id)
 		*assoc_id = asoc->assoc_id;
+	err = sctp_wait_for_connect(asoc, &timeo);
+	/* Note: the asoc may be freed after the return of
+	 * sctp_wait_for_connect.
+	 */
 
 	/* Don't free association on exit. */
 	asoc = NULL;
-- 
2.7.4


From 219a5eeecdea535f563be9766afe03b47ed2bd15 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Fri, 4 Nov 2016 15:11:57 -0400
Subject: [PATCH 12/16] fib_trie: Correct /proc/net/route off by one error

[ Upstream commit fd0285a39b1cb496f60210a9a00ad33a815603e7 ]

The display of /proc/net/route has had a couple issues due to the fact that
when I originally rewrote most of fib_trie I made it so that the iterator
was tracking the next value to use instead of the current.

In addition it had an off by 1 error where I was tracking the first piece
of data as position 0, even though in reality that belonged to the
SEQ_START_TOKEN.

This patch updates the code so the iterator tracks the last reported
position and key instead of the next expected position and key.  In
addition it shifts things so that all of the leaves start at 1 instead of
trying to report leaves starting with offset 0 as being valid.  With these
two issues addressed this should resolve any off by one errors that were
present in the display of /proc/net/route.

Fixes: 25b97c016b26 ("ipv4: off-by-one in continuation handling in /proc/net/route")
Cc: Andy Whitcroft <apw@canonical.com>
Reported-by: Jason Baron <jbaron@akamai.com>
Tested-by: Jason Baron <jbaron@akamai.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_trie.c | 21 +++++++++------------
 1 file changed, 9 insertions(+), 12 deletions(-)

diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index e5a3ff2..7c52afb 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -2456,22 +2456,19 @@ static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter,
 	struct key_vector *l, **tp = &iter->tnode;
 	t_key key;
 
-	/* use cache location of next-to-find key */
+	/* use cached location of previously found key */
 	if (iter->pos > 0 && pos >= iter->pos) {
-		pos -= iter->pos;
 		key = iter->key;
 	} else {
-		iter->pos = 0;
+		iter->pos = 1;
 		key = 0;
 	}
 
-	while ((l = leaf_walk_rcu(tp, key)) != NULL) {
+	pos -= iter->pos;
+
+	while ((l = leaf_walk_rcu(tp, key)) && (pos-- > 0)) {
 		key = l->key + 1;
 		iter->pos++;
-
-		if (--pos <= 0)
-			break;
-
 		l = NULL;
 
 		/* handle unlikely case of a key wrap */
@@ -2480,7 +2477,7 @@ static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter,
 	}
 
 	if (l)
-		iter->key = key;	/* remember it */
+		iter->key = l->key;	/* remember it */
 	else
 		iter->pos = 0;		/* forget it */
 
@@ -2508,7 +2505,7 @@ static void *fib_route_seq_start(struct seq_file *seq, loff_t *pos)
 		return fib_route_get_idx(iter, *pos);
 
 	iter->pos = 0;
-	iter->key = 0;
+	iter->key = KEY_MAX;
 
 	return SEQ_START_TOKEN;
 }
@@ -2517,7 +2514,7 @@ static void *fib_route_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	struct fib_route_iter *iter = seq->private;
 	struct key_vector *l = NULL;
-	t_key key = iter->key;
+	t_key key = iter->key + 1;
 
 	++*pos;
 
@@ -2526,7 +2523,7 @@ static void *fib_route_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 		l = leaf_walk_rcu(&iter->tnode, key);
 
 	if (l) {
-		iter->key = l->key + 1;
+		iter->key = l->key;
 		iter->pos++;
 	} else {
 		iter->pos = 0;
-- 
2.7.4


From 6dbd15f7f5ed50865f4c61ab81fee6c84d8ae771 Mon Sep 17 00:00:00 2001
From: Soheil Hassas Yeganeh <soheil@google.com>
Date: Fri, 4 Nov 2016 15:36:49 -0400
Subject: [PATCH 13/16] sock: fix sendmmsg for partial sendmsg
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 3023898b7d4aac65987bd2f485cc22390aae6f78 ]

Do not send the next message in sendmmsg for partial sendmsg
invocations.

sendmmsg assumes that it can continue sending the next message
when the return value of the individual sendmsg invocations
is positive. It results in corrupting the data for TCP,
SCTP, and UNIX streams.

For example, sendmmsg([["abcd"], ["efgh"]]) can result in a stream
of "aefgh" if the first sendmsg invocation sends only the first
byte while the second sendmsg goes through.

Datagram sockets either send the entire datagram or fail, so
this patch affects only sockets of type SOCK_STREAM and
SOCK_SEQPACKET.

Fixes: 228e548e6020 ("net: Add sendmmsg socket system call")
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Maciej Żenczykowski <maze@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/socket.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/socket.c b/net/socket.c
index 263b334..0090225 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2041,6 +2041,8 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
 		if (err)
 			break;
 		++datagrams;
+		if (msg_data_left(&msg_sys))
+			break;
 	}
 
 	fput_light(sock->file, fput_needed);
-- 
2.7.4


From 89c16a32266f7c3af244886f1747510a04604b54 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 9 Nov 2016 16:04:46 -0800
Subject: [PATCH 14/16] net: __skb_flow_dissect() must cap its return value

[ Upstream commit 34fad54c2537f7c99d07375e50cb30aa3c23bd83 ]

After Tom patch, thoff field could point past the end of the buffer,
this could fool some callers.

If an skb was provided, skb->len should be the upper limit.
If not, hlen is supposed to be the upper limit.

Fixes: a6e544b0a88b ("flow_dissector: Jump to exit code in __skb_flow_dissect")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Yibin Yang <yibyang@cisco.com
Acked-by: Alexander Duyck <alexander.h.duyck@intel.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/flow_dissector.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 4ab6ead..9aba9e9 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -131,7 +131,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
 	struct flow_dissector_key_tags *key_tags;
 	struct flow_dissector_key_keyid *key_keyid;
 	u8 ip_proto = 0;
-	bool ret = false;
+	bool ret;
 
 	if (!data) {
 		data = skb->data;
@@ -492,12 +492,17 @@ ip_proto_again:
 out_good:
 	ret = true;
 
-out_bad:
+	key_control->thoff = (u16)nhoff;
+out:
 	key_basic->n_proto = proto;
 	key_basic->ip_proto = ip_proto;
-	key_control->thoff = (u16)nhoff;
 
 	return ret;
+
+out_bad:
+	ret = false;
+	key_control->thoff = min_t(u16, nhoff, skb ? skb->len : hlen);
+	goto out;
 }
 EXPORT_SYMBOL(__skb_flow_dissect);
 
-- 
2.7.4


From 0fe86afdd831de277b7790742f28537f30ae15c7 Mon Sep 17 00:00:00 2001
From: Stephen Suryaputra Lin <stephen.suryaputra.lin@gmail.com>
Date: Thu, 10 Nov 2016 11:16:15 -0500
Subject: [PATCH 15/16] ipv4: use new_gw for redirect neigh lookup

[ Upstream commit 969447f226b451c453ddc83cac6144eaeac6f2e3 ]

In v2.6, ip_rt_redirect() calls arp_bind_neighbour() which returns 0
and then the state of the neigh for the new_gw is checked. If the state
isn't valid then the redirected route is deleted. This behavior is
maintained up to v3.5.7 by check_peer_redirect() because rt->rt_gateway
is assigned to peer->redirect_learned.a4 before calling
ipv4_neigh_lookup().

After commit 5943634fc559 ("ipv4: Maintain redirect and PMTU info in
struct rtable again."), ipv4_neigh_lookup() is performed without the
rt_gateway assigned to the new_gw. In the case when rt_gateway (old_gw)
isn't zero, the function uses it as the key. The neigh is most likely
valid since the old_gw is the one that sends the ICMP redirect message.
Then the new_gw is assigned to fib_nh_exception. The problem is: the
new_gw ARP may never gets resolved and the traffic is blackholed.

So, use the new_gw for neigh lookup.

Changes from v1:
 - use __ipv4_neigh_lookup instead (per Eric Dumazet).

Fixes: 5943634fc559 ("ipv4: Maintain redirect and PMTU info in struct rtable again.")
Signed-off-by: Stephen Suryaputra Lin <ssurya@ieee.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 8533a75..7ceb8a5 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -747,7 +747,9 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
 			goto reject_redirect;
 	}
 
-	n = ipv4_neigh_lookup(&rt->dst, NULL, &new_gw);
+	n = __ipv4_neigh_lookup(rt->dst.dev, new_gw);
+	if (!n)
+		n = neigh_create(&arp_tbl, &new_gw, rt->dst.dev);
 	if (!IS_ERR(n)) {
 		if (!(n->nud_state & NUD_VALID)) {
 			neigh_event_send(n, NULL);
-- 
2.7.4


From fa91c9e75c0e115ad3367b8690c19f8c466c8ce0 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 10 Nov 2016 13:12:35 -0800
Subject: [PATCH 16/16] tcp: take care of truncations done by sk_filter()

[ Upstream commit ac6e780070e30e4c35bd395acfe9191e6268bdd3 ]

With syzkaller help, Marco Grassi found a bug in TCP stack,
crashing in tcp_collapse()

Root cause is that sk_filter() can truncate the incoming skb,
but TCP stack was not really expecting this to happen.
It probably was expecting a simple DROP or ACCEPT behavior.

We first need to make sure no part of TCP header could be removed.
Then we need to adjust TCP_SKB_CB(skb)->end_seq

Many thanks to syzkaller team and Marco for giving us a reproducer.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Marco Grassi <marco.gra@gmail.com>
Reported-by: Vladis Dronov <vdronov@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/filter.h |  6 +++++-
 include/net/tcp.h      |  1 +
 net/core/filter.c      | 10 +++++-----
 net/ipv4/tcp_ipv4.c    | 19 ++++++++++++++++++-
 net/ipv6/tcp_ipv6.c    |  6 ++++--
 5 files changed, 33 insertions(+), 9 deletions(-)

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 5110d42..ccb98b4 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -421,7 +421,11 @@ static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
 }
 #endif /* CONFIG_DEBUG_SET_MODULE_RONX */
 
-int sk_filter(struct sock *sk, struct sk_buff *skb);
+int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap);
+static inline int sk_filter(struct sock *sk, struct sk_buff *skb)
+{
+	return sk_filter_trim_cap(sk, skb, 1);
+}
 
 int bpf_prog_select_runtime(struct bpf_prog *fp);
 void bpf_prog_free(struct bpf_prog *fp);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 9c3ab54..e9d7a8e 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1156,6 +1156,7 @@ static inline void tcp_prequeue_init(struct tcp_sock *tp)
 }
 
 bool tcp_prequeue(struct sock *sk, struct sk_buff *skb);
+int tcp_filter(struct sock *sk, struct sk_buff *skb);
 
 #undef STATE_TRACE
 
diff --git a/net/core/filter.c b/net/core/filter.c
index 75e9b2b..e943554 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -52,9 +52,10 @@
 #include <net/dst.h>
 
 /**
- *	sk_filter - run a packet through a socket filter
+ *	sk_filter_trim_cap - run a packet through a socket filter
  *	@sk: sock associated with &sk_buff
  *	@skb: buffer to filter
+ *	@cap: limit on how short the eBPF program may trim the packet
  *
  * Run the eBPF program and then cut skb->data to correct size returned by
  * the program. If pkt_len is 0 we toss packet. If skb->len is smaller
@@ -63,7 +64,7 @@
  * be accepted or -EPERM if the packet should be tossed.
  *
  */
-int sk_filter(struct sock *sk, struct sk_buff *skb)
+int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap)
 {
 	int err;
 	struct sk_filter *filter;
@@ -84,14 +85,13 @@ int sk_filter(struct sock *sk, struct sk_buff *skb)
 	filter = rcu_dereference(sk->sk_filter);
 	if (filter) {
 		unsigned int pkt_len = bpf_prog_run_save_cb(filter->prog, skb);
-
-		err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM;
+		err = pkt_len ? pskb_trim(skb, max(cap, pkt_len)) : -EPERM;
 	}
 	rcu_read_unlock();
 
 	return err;
 }
-EXPORT_SYMBOL(sk_filter);
+EXPORT_SYMBOL(sk_filter_trim_cap);
 
 static u64 __skb_get_pay_offset(u64 ctx, u64 a, u64 x, u64 r4, u64 r5)
 {
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index b5853ca..b58a38e 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1533,6 +1533,21 @@ bool tcp_prequeue(struct sock *sk, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(tcp_prequeue);
 
+int tcp_filter(struct sock *sk, struct sk_buff *skb)
+{
+	struct tcphdr *th = (struct tcphdr *)skb->data;
+	unsigned int eaten = skb->len;
+	int err;
+
+	err = sk_filter_trim_cap(sk, skb, th->doff * 4);
+	if (!err) {
+		eaten -= skb->len;
+		TCP_SKB_CB(skb)->end_seq -= eaten;
+	}
+	return err;
+}
+EXPORT_SYMBOL(tcp_filter);
+
 /*
  *	From tcp_input.c
  */
@@ -1638,8 +1653,10 @@ process:
 
 	nf_reset(skb);
 
-	if (sk_filter(sk, skb))
+	if (tcp_filter(sk, skb))
 		goto discard_and_relse;
+	th = (const struct tcphdr *)skb->data;
+	iph = ip_hdr(skb);
 
 	skb->dev = NULL;
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index fbd521f..5f58161 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1214,7 +1214,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
 	if (skb->protocol == htons(ETH_P_IP))
 		return tcp_v4_do_rcv(sk, skb);
 
-	if (sk_filter(sk, skb))
+	if (tcp_filter(sk, skb))
 		goto discard;
 
 	/*
@@ -1438,8 +1438,10 @@ process:
 	if (tcp_v6_inbound_md5_hash(sk, skb))
 		goto discard_and_relse;
 
-	if (sk_filter(sk, skb))
+	if (tcp_filter(sk, skb))
 		goto discard_and_relse;
+	th = (const struct tcphdr *)skb->data;
+	hdr = ipv6_hdr(skb);
 
 	skb->dev = NULL;
 
-- 
2.7.4


[-- Attachment #3: net_48.mbox --]
[-- Type: Application/Octet-Stream, Size: 66492 bytes --]

From fc4e2146682b647c30fffaff08e58f05f4ef5c9e Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 28 Oct 2016 18:43:11 +0200
Subject: [PATCH 01/29] dctcp: avoid bogus doubling of cwnd after loss

[ Upstream commit ce6dd23329b1ee6a794acf5f7e40f8e89b8317ee ]

If a congestion control module doesn't provide .undo_cwnd function,
tcp_undo_cwnd_reduction() will set cwnd to

   tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh << 1);

... which makes sense for reno (it sets ssthresh to half the current cwnd),
but it makes no sense for dctcp, which sets ssthresh based on the current
congestion estimate.

This can cause severe growth of cwnd (eventually overflowing u32).

Fix this by saving last cwnd on loss and restore cwnd based on that,
similar to cubic and other algorithms.

Fixes: e3118e8359bb7c ("net: tcp: add DCTCP congestion control algorithm")
Cc: Lawrence Brakmo <brakmo@fb.com>
Cc: Andrew Shewmaker <agshew@gmail.com>
Cc: Glenn Judd <glenn.judd@morganstanley.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_dctcp.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 10d728b..ab37c67 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -56,6 +56,7 @@ struct dctcp {
 	u32 next_seq;
 	u32 ce_state;
 	u32 delayed_ack_reserved;
+	u32 loss_cwnd;
 };
 
 static unsigned int dctcp_shift_g __read_mostly = 4; /* g = 1/2^4 */
@@ -96,6 +97,7 @@ static void dctcp_init(struct sock *sk)
 		ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA);
 
 		ca->delayed_ack_reserved = 0;
+		ca->loss_cwnd = 0;
 		ca->ce_state = 0;
 
 		dctcp_reset(tp, ca);
@@ -111,9 +113,10 @@ static void dctcp_init(struct sock *sk)
 
 static u32 dctcp_ssthresh(struct sock *sk)
 {
-	const struct dctcp *ca = inet_csk_ca(sk);
+	struct dctcp *ca = inet_csk_ca(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 
+	ca->loss_cwnd = tp->snd_cwnd;
 	return max(tp->snd_cwnd - ((tp->snd_cwnd * ca->dctcp_alpha) >> 11U), 2U);
 }
 
@@ -308,12 +311,20 @@ static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr,
 	return 0;
 }
 
+static u32 dctcp_cwnd_undo(struct sock *sk)
+{
+	const struct dctcp *ca = inet_csk_ca(sk);
+
+	return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd);
+}
+
 static struct tcp_congestion_ops dctcp __read_mostly = {
 	.init		= dctcp_init,
 	.in_ack_event   = dctcp_update_alpha,
 	.cwnd_event	= dctcp_cwnd_event,
 	.ssthresh	= dctcp_ssthresh,
 	.cong_avoid	= tcp_reno_cong_avoid,
+	.undo_cwnd	= dctcp_cwnd_undo,
 	.set_state	= dctcp_state,
 	.get_info	= dctcp_get_info,
 	.flags		= TCP_CONG_NEEDS_ECN,
-- 
2.4.11


From 6eb13bf223afaefad7da1fdbe1f3aff26eefad4e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 28 Oct 2016 13:40:24 -0700
Subject: [PATCH 02/29] net: clear sk_err_soft in sk_clone_lock()

[ Upstream commit e551c32d57c88923f99f8f010e89ca7ed0735e83 ]

At accept() time, it is possible the parent has a non zero
sk_err_soft, leftover from a prior error.

Make sure we do not leave this value in the child, as it
makes future getsockopt(SO_ERROR) calls quite unreliable.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/core/sock.c b/net/core/sock.c
index fd7b41e..6b8d224 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1563,6 +1563,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		RCU_INIT_POINTER(newsk->sk_reuseport_cb, NULL);
 
 		newsk->sk_err	   = 0;
+		newsk->sk_err_soft = 0;
 		newsk->sk_priority = 0;
 		newsk->sk_incoming_cpu = raw_smp_processor_id();
 		atomic64_set(&newsk->sk_cookie, 0);
-- 
2.4.11


From 0a674e5cdc1ca308996df7872d20e578b5f564c7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 29 Oct 2016 11:02:36 -0700
Subject: [PATCH 03/29] net: mangle zero checksum in skb_checksum_help()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 4f2e4ad56a65f3b7d64c258e373cb71e8d2499f4 ]

Sending zero checksum is ok for TCP, but not for UDP.

UDPv6 receiver should by default drop a frame with a 0 checksum,
and UDPv4 would not verify the checksum and might accept a corrupted
packet.

Simply replace such checksum by 0xffff, regardless of transport.

This error was caught on SIT tunnels, but seems generic.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Maciej Żenczykowski <maze@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Acked-by: Maciej Żenczykowski <maze@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 44b3ba4..9ce9d72 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2484,7 +2484,7 @@ int skb_checksum_help(struct sk_buff *skb)
 			goto out;
 	}
 
-	*(__sum16 *)(skb->data + offset) = csum_fold(csum);
+	*(__sum16 *)(skb->data + offset) = csum_fold(csum) ?: CSUM_MANGLED_0;
 out_set_summed:
 	skb->ip_summed = CHECKSUM_NONE;
 out:
-- 
2.4.11


From b54a1895ee8f2960107d4f065b5794da6f51880f Mon Sep 17 00:00:00 2001
From: Andy Gospodarek <gospo@broadcom.com>
Date: Mon, 31 Oct 2016 13:32:03 -0400
Subject: [PATCH 04/29] bgmac: stop clearing DMA receive control register right
 after it is set

[ Upstream commit fcdefccac976ee51dd6071832b842d8fb41c479c ]

Current bgmac code initializes some DMA settings in the receive control
register for some hardware and then immediately clears those settings.
Not clearing those settings results in ~420Mbps *improvement* in
throughput; this system can now receive frames at line-rate on Broadcom
5871x hardware compared to ~520Mbps today.  I also tested a few other
values but found there to be no discernible difference in CPU
utilization even if burst size and prefetching values are different.

On the hardware tested there was no need to keep the code that cleared
all but bits 16-17, but since there is a wide variety of hardware that
used this driver (I did not look at all hardware docs for hardware using
this IP block), I find it wise to move this call up and clear bits just
after reading the default value from the hardware rather than completely
removing it.

This is a good candidate for -stable >=3.14 since that is when the code
that was supposed to improve performance (but did not) was introduced.

Signed-off-by: Andy Gospodarek <gospo@broadcom.com>
Fixes: 56ceecde1f29 ("bgmac: initialize the DMA controller of core...")
Cc: Hauke Mehrtens <hauke@hauke-m.de>
Acked-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bgmac.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index c4751ec..45e87c9 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -307,6 +307,10 @@ static void bgmac_dma_rx_enable(struct bgmac *bgmac,
 	u32 ctl;
 
 	ctl = bgmac_read(bgmac, ring->mmio_base + BGMAC_DMA_RX_CTL);
+
+	/* preserve ONLY bits 16-17 from current hardware value */
+	ctl &= BGMAC_DMA_RX_ADDREXT_MASK;
+
 	if (bgmac->feature_flags & BGMAC_FEAT_RX_MASK_SETUP) {
 		ctl &= ~BGMAC_DMA_RX_BL_MASK;
 		ctl |= BGMAC_DMA_RX_BL_128 << BGMAC_DMA_RX_BL_SHIFT;
@@ -317,7 +321,6 @@ static void bgmac_dma_rx_enable(struct bgmac *bgmac,
 		ctl &= ~BGMAC_DMA_RX_PT_MASK;
 		ctl |= BGMAC_DMA_RX_PT_1 << BGMAC_DMA_RX_PT_SHIFT;
 	}
-	ctl &= BGMAC_DMA_RX_ADDREXT_MASK;
 	ctl |= BGMAC_DMA_RX_ENABLE;
 	ctl |= BGMAC_DMA_RX_PARITY_DISABLE;
 	ctl |= BGMAC_DMA_RX_OVERFLOW_CONT;
-- 
2.4.11


From 3b756aefa9e231bcdc56efcf8e7ea5a207fcf24e Mon Sep 17 00:00:00 2001
From: Eli Cooper <elicooper@gmx.com>
Date: Tue, 1 Nov 2016 23:45:12 +0800
Subject: [PATCH 05/29] ip6_tunnel: Clear IP6CB in ip6tunnel_xmit()

[ Upstream commit 23f4ffedb7d751c7e298732ba91ca75d224bc1a6 ]

skb->cb may contain data from previous layers. In the observed scenario,
the garbage data were misinterpreted as IP6CB(skb)->frag_max_size, so
that small packets sent through the tunnel are mistakenly fragmented.

This patch unconditionally clears the control buffer in ip6tunnel_xmit(),
which affects ip6_tunnel, ip6_udp_tunnel and ip6_gre. Currently none of
these tunnels set IP6CB(skb)->flags, otherwise it needs to be done earlier.

Cc: stable@vger.kernel.org
Signed-off-by: Eli Cooper <elicooper@gmx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_tunnel.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index 43a5a0e..b01d5d1 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -145,6 +145,7 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb,
 {
 	int pkt_len, err;
 
+	memset(skb->cb, 0, sizeof(struct inet6_skb_parm));
 	pkt_len = skb->len - skb_inner_network_offset(skb);
 	err = ip6_local_out(dev_net(skb_dst(skb)->dev), sk, skb);
 	if (unlikely(net_xmit_eval(err)))
-- 
2.4.11


From f90690465b491a20fe8ca9833a44d076fb03a95e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 2 Nov 2016 07:53:17 -0700
Subject: [PATCH 06/29] tcp: fix potential memory corruption
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit ac9e70b17ecd7c6e933ff2eaf7ab37429e71bf4d ]

Imagine initial value of max_skb_frags is 17, and last
skb in write queue has 15 frags.

Then max_skb_frags is lowered to 14 or smaller value.

tcp_sendmsg() will then be allowed to add additional page frags
and eventually go past MAX_SKB_FRAGS, overflowing struct
skb_shared_info.

Fixes: 5f74f82ea34c ("net:Add sysctl_max_skb_frags")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Hans Westgaard Ry <hans.westgaard.ry@oracle.com>
Cc: Håkon Bugge <haakon.bugge@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index ffbb218..e5d11df 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1219,7 +1219,7 @@ new_segment:
 
 			if (!skb_can_coalesce(skb, i, pfrag->page,
 					      pfrag->offset)) {
-				if (i == sysctl_max_skb_frags || !sg) {
+				if (i >= sysctl_max_skb_frags || !sg) {
 					tcp_mark_push(tp, skb);
 					goto new_segment;
 				}
-- 
2.4.11


From 96f271d9d54f81ed0be80849b5bdfd9b5d14d779 Mon Sep 17 00:00:00 2001
From: Lance Richardson <lrichard@redhat.com>
Date: Wed, 2 Nov 2016 16:36:17 -0400
Subject: [PATCH 07/29] ipv4: allow local fragmentation in
 ip_finish_output_gso()

[ Upstream commit 9ee6c5dc816aa8256257f2cd4008a9291ec7e985 ]

Some configurations (e.g. geneve interface with default
MTU of 1500 over an ethernet interface with 1500 MTU) result
in the transmission of packets that exceed the configured MTU.
While this should be considered to be a "bad" configuration,
it is still allowed and should not result in the sending
of packets that exceed the configured MTU.

Fix by dropping the assumption in ip_finish_output_gso() that
locally originated gso packets will never need fragmentation.
Basic testing using iperf (observing CPU usage and bandwidth)
have shown no measurable performance impact for traffic not
requiring fragmentation.

Fixes: c7ba65d7b649 ("net: ip: push gso skb forwarding handling down the stack")
Reported-by: Jan Tluka <jtluka@redhat.com>
Signed-off-by: Lance Richardson <lrichard@redhat.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h          |  1 -
 net/ipv4/ip_forward.c     |  2 +-
 net/ipv4/ip_output.c      |  6 ++----
 net/ipv4/ip_tunnel_core.c | 11 -----------
 net/ipv4/ipmr.c           |  2 +-
 5 files changed, 4 insertions(+), 18 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index 156b0c1..0ccf6da 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -47,7 +47,6 @@ struct inet_skb_parm {
 #define IPSKB_REROUTED		BIT(4)
 #define IPSKB_DOREDIRECT	BIT(5)
 #define IPSKB_FRAG_PMTU		BIT(6)
-#define IPSKB_FRAG_SEGS		BIT(7)
 
 	u16			frag_max_size;
 };
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 8b4ffd2..9f0a7b9 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -117,7 +117,7 @@ int ip_forward(struct sk_buff *skb)
 	if (opt->is_strictroute && rt->rt_uses_gateway)
 		goto sr_failed;
 
-	IPCB(skb)->flags |= IPSKB_FORWARDED | IPSKB_FRAG_SEGS;
+	IPCB(skb)->flags |= IPSKB_FORWARDED;
 	mtu = ip_dst_mtu_maybe_forward(&rt->dst, true);
 	if (ip_exceeds_mtu(skb, mtu)) {
 		IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index dde37fb..307daed 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -223,11 +223,9 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk,
 	struct sk_buff *segs;
 	int ret = 0;
 
-	/* common case: fragmentation of segments is not allowed,
-	 * or seglen is <= mtu
+	/* common case: seglen is <= mtu
 	 */
-	if (((IPCB(skb)->flags & IPSKB_FRAG_SEGS) == 0) ||
-	      skb_gso_validate_mtu(skb, mtu))
+	if (skb_gso_validate_mtu(skb, mtu))
 		return ip_finish_output2(net, sk, skb);
 
 	/* Slowpath -  GSO segment length is exceeding the dst MTU.
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 0f227db..afd6b59 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -63,7 +63,6 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
 	int pkt_len = skb->len - skb_inner_network_offset(skb);
 	struct net *net = dev_net(rt->dst.dev);
 	struct net_device *dev = skb->dev;
-	int skb_iif = skb->skb_iif;
 	struct iphdr *iph;
 	int err;
 
@@ -73,16 +72,6 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
 	skb_dst_set(skb, &rt->dst);
 	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
 
-	if (skb_iif && !(df & htons(IP_DF))) {
-		/* Arrived from an ingress interface, got encapsulated, with
-		 * fragmentation of encapulating frames allowed.
-		 * If skb is gso, the resulting encapsulated network segments
-		 * may exceed dst mtu.
-		 * Allow IP Fragmentation of segments.
-		 */
-		IPCB(skb)->flags |= IPSKB_FRAG_SEGS;
-	}
-
 	/* Push down and install the IP header. */
 	skb_push(skb, sizeof(struct iphdr));
 	skb_reset_network_header(skb);
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 5f006e1..27089f5 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1749,7 +1749,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
 		vif->dev->stats.tx_bytes += skb->len;
 	}
 
-	IPCB(skb)->flags |= IPSKB_FORWARDED | IPSKB_FRAG_SEGS;
+	IPCB(skb)->flags |= IPSKB_FORWARDED;
 
 	/* RFC1584 teaches, that DVMRP/PIM router must deliver packets locally
 	 * not only before forwarding, but after forwarding on all output
-- 
2.4.11


From 41563d4f523ab10250e8094279e28c1c9c53946b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 2 Nov 2016 14:41:50 -0700
Subject: [PATCH 08/29] tcp: fix return value for partial writes

[ Upstream commit 79d8665b9545e128637c51cf7febde9c493b6481 ]

After my commit, tcp_sendmsg() might restart its loop after
processing socket backlog.

If sk_err is set, we blindly return an error, even though we
copied data to user space before.

We should instead return number of bytes that could be copied,
otherwise user space might resend data and corrupt the stream.

This might happen if another thread is using recvmsg(MSG_ERRQUEUE)
to process timestamps.

Issue was diagnosed by Soheil and Willem, big kudos to them !

Fixes: d41a69f1d390f ("tcp: make tcp_sendmsg() aware of socket backlog")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Tested-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e5d11df..c876f5d 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1145,7 +1145,7 @@ restart:
 
 	err = -EPIPE;
 	if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
-		goto out_err;
+		goto do_error;
 
 	sg = !!(sk->sk_route_caps & NETIF_F_SG);
 
-- 
2.4.11


From c7143376d7b6211da0e566c9869be00c99aa1431 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 2 Nov 2016 17:14:41 -0700
Subject: [PATCH 09/29] dccp: do not release listeners too soon

[ Upstream commit c3f24cfb3e508c70c26ee8569d537c8ca67a36c6 ]

Andrey Konovalov reported following error while fuzzing with syzkaller :

IPv4: Attempt to release alive inet socket ffff880068e98940
kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] SMP KASAN
Modules linked in:
CPU: 1 PID: 3905 Comm: a.out Not tainted 4.9.0-rc3+ #333
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
task: ffff88006b9e0000 task.stack: ffff880068770000
RIP: 0010:[<ffffffff819ead5f>]  [<ffffffff819ead5f>]
selinux_socket_sock_rcv_skb+0xff/0x6a0 security/selinux/hooks.c:4639
RSP: 0018:ffff8800687771c8  EFLAGS: 00010202
RAX: ffff88006b9e0000 RBX: 1ffff1000d0eee3f RCX: 1ffff1000d1d312a
RDX: 1ffff1000d1d31a6 RSI: dffffc0000000000 RDI: 0000000000000010
RBP: ffff880068777360 R08: 0000000000000000 R09: 0000000000000002
R10: dffffc0000000000 R11: 0000000000000006 R12: ffff880068e98940
R13: 0000000000000002 R14: ffff880068777338 R15: 0000000000000000
FS:  00007f00ff760700(0000) GS:ffff88006cd00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000020008000 CR3: 000000006a308000 CR4: 00000000000006e0
Stack:
 ffff8800687771e0 ffffffff812508a5 ffff8800686f3168 0000000000000007
 ffff88006ac8cdfc ffff8800665ea500 0000000041b58ab3 ffffffff847b5480
 ffffffff819eac60 ffff88006b9e0860 ffff88006b9e0868 ffff88006b9e07f0
Call Trace:
 [<ffffffff819c8dd5>] security_sock_rcv_skb+0x75/0xb0 security/security.c:1317
 [<ffffffff82c2a9e7>] sk_filter_trim_cap+0x67/0x10e0 net/core/filter.c:81
 [<ffffffff82b81e60>] __sk_receive_skb+0x30/0xa00 net/core/sock.c:460
 [<ffffffff838bbf12>] dccp_v4_rcv+0xdb2/0x1910 net/dccp/ipv4.c:873
 [<ffffffff83069d22>] ip_local_deliver_finish+0x332/0xad0
net/ipv4/ip_input.c:216
 [<     inline     >] NF_HOOK_THRESH ./include/linux/netfilter.h:232
 [<     inline     >] NF_HOOK ./include/linux/netfilter.h:255
 [<ffffffff8306abd2>] ip_local_deliver+0x1c2/0x4b0 net/ipv4/ip_input.c:257
 [<     inline     >] dst_input ./include/net/dst.h:507
 [<ffffffff83068500>] ip_rcv_finish+0x750/0x1c40 net/ipv4/ip_input.c:396
 [<     inline     >] NF_HOOK_THRESH ./include/linux/netfilter.h:232
 [<     inline     >] NF_HOOK ./include/linux/netfilter.h:255
 [<ffffffff8306b82f>] ip_rcv+0x96f/0x12f0 net/ipv4/ip_input.c:487
 [<ffffffff82bd9fb7>] __netif_receive_skb_core+0x1897/0x2a50 net/core/dev.c:4213
 [<ffffffff82bdb19a>] __netif_receive_skb+0x2a/0x170 net/core/dev.c:4251
 [<ffffffff82bdb493>] netif_receive_skb_internal+0x1b3/0x390 net/core/dev.c:4279
 [<ffffffff82bdb6b8>] netif_receive_skb+0x48/0x250 net/core/dev.c:4303
 [<ffffffff8241fc75>] tun_get_user+0xbd5/0x28a0 drivers/net/tun.c:1308
 [<ffffffff82421b5a>] tun_chr_write_iter+0xda/0x190 drivers/net/tun.c:1332
 [<     inline     >] new_sync_write fs/read_write.c:499
 [<ffffffff8151bd44>] __vfs_write+0x334/0x570 fs/read_write.c:512
 [<ffffffff8151f85b>] vfs_write+0x17b/0x500 fs/read_write.c:560
 [<     inline     >] SYSC_write fs/read_write.c:607
 [<ffffffff81523184>] SyS_write+0xd4/0x1a0 fs/read_write.c:599
 [<ffffffff83fc02c1>] entry_SYSCALL_64_fastpath+0x1f/0xc2

It turns out DCCP calls __sk_receive_skb(), and this broke when
lookups no longer took a reference on listeners.

Fix this issue by adding a @refcounted parameter to __sk_receive_skb(),
so that sock_put() is used only when needed.

Fixes: 3b24d854cb35 ("tcp/dccp: do not touch listener sk_refcnt under synflood")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h | 4 ++--
 net/core/sock.c    | 5 +++--
 net/dccp/ipv4.c    | 2 +-
 net/dccp/ipv6.c    | 3 ++-
 4 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index 8741988..c26eab9 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1587,11 +1587,11 @@ static inline void sock_put(struct sock *sk)
 void sock_gen_put(struct sock *sk);
 
 int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested,
-		     unsigned int trim_cap);
+		     unsigned int trim_cap, bool refcounted);
 static inline int sk_receive_skb(struct sock *sk, struct sk_buff *skb,
 				 const int nested)
 {
-	return __sk_receive_skb(sk, skb, nested, 1);
+	return __sk_receive_skb(sk, skb, nested, 1, true);
 }
 
 static inline void sk_tx_queue_set(struct sock *sk, int tx_queue)
diff --git a/net/core/sock.c b/net/core/sock.c
index 6b8d224..10acacc 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -453,7 +453,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 EXPORT_SYMBOL(sock_queue_rcv_skb);
 
 int __sk_receive_skb(struct sock *sk, struct sk_buff *skb,
-		     const int nested, unsigned int trim_cap)
+		     const int nested, unsigned int trim_cap, bool refcounted)
 {
 	int rc = NET_RX_SUCCESS;
 
@@ -487,7 +487,8 @@ int __sk_receive_skb(struct sock *sk, struct sk_buff *skb,
 
 	bh_unlock_sock(sk);
 out:
-	sock_put(sk);
+	if (refcounted)
+		sock_put(sk);
 	return rc;
 discard_and_relse:
 	kfree_skb(skb);
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 345a3ae..dff7cfa 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -868,7 +868,7 @@ lookup:
 		goto discard_and_relse;
 	nf_reset(skb);
 
-	return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4);
+	return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4, refcounted);
 
 no_dccp_socket:
 	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 3828f94..09c4e19 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -738,7 +738,8 @@ lookup:
 	if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
 		goto discard_and_relse;
 
-	return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4) ? -1 : 0;
+	return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4,
+				refcounted) ? -1 : 0;
 
 no_dccp_socket:
 	if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
-- 
2.4.11


From c7dd940a33c386748c3fd3314a8d369dfa57c3ac Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 2 Nov 2016 18:04:24 -0700
Subject: [PATCH 10/29] dccp: do not send reset to already closed sockets

[ Upstream commit 346da62cc186c4b4b1ac59f87f4482b47a047388 ]

Andrey reported following warning while fuzzing with syzkaller

WARNING: CPU: 1 PID: 21072 at net/dccp/proto.c:83 dccp_set_state+0x229/0x290
Kernel panic - not syncing: panic_on_warn set ...

CPU: 1 PID: 21072 Comm: syz-executor Not tainted 4.9.0-rc1+ #293
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
 ffff88003d4c7738 ffffffff81b474f4 0000000000000003 dffffc0000000000
 ffffffff844f8b00 ffff88003d4c7804 ffff88003d4c7800 ffffffff8140c06a
 0000000041b58ab3 ffffffff8479ab7d ffffffff8140beae ffffffff8140cd00
Call Trace:
 [<     inline     >] __dump_stack lib/dump_stack.c:15
 [<ffffffff81b474f4>] dump_stack+0xb3/0x10f lib/dump_stack.c:51
 [<ffffffff8140c06a>] panic+0x1bc/0x39d kernel/panic.c:179
 [<ffffffff8111125c>] __warn+0x1cc/0x1f0 kernel/panic.c:542
 [<ffffffff8111144c>] warn_slowpath_null+0x2c/0x40 kernel/panic.c:585
 [<ffffffff8389e5d9>] dccp_set_state+0x229/0x290 net/dccp/proto.c:83
 [<ffffffff838a0aa2>] dccp_close+0x612/0xc10 net/dccp/proto.c:1016
 [<ffffffff8316bf1f>] inet_release+0xef/0x1c0 net/ipv4/af_inet.c:415
 [<ffffffff82b6e89e>] sock_release+0x8e/0x1d0 net/socket.c:570
 [<ffffffff82b6e9f6>] sock_close+0x16/0x20 net/socket.c:1017
 [<ffffffff815256ad>] __fput+0x29d/0x720 fs/file_table.c:208
 [<ffffffff81525bb5>] ____fput+0x15/0x20 fs/file_table.c:244
 [<ffffffff811727d8>] task_work_run+0xf8/0x170 kernel/task_work.c:116
 [<     inline     >] exit_task_work include/linux/task_work.h:21
 [<ffffffff8111bc53>] do_exit+0x883/0x2ac0 kernel/exit.c:828
 [<ffffffff811221fe>] do_group_exit+0x10e/0x340 kernel/exit.c:931
 [<ffffffff81143c94>] get_signal+0x634/0x15a0 kernel/signal.c:2307
 [<ffffffff81054aad>] do_signal+0x8d/0x1a30 arch/x86/kernel/signal.c:807
 [<ffffffff81003a05>] exit_to_usermode_loop+0xe5/0x130
arch/x86/entry/common.c:156
 [<     inline     >] prepare_exit_to_usermode arch/x86/entry/common.c:190
 [<ffffffff81006298>] syscall_return_slowpath+0x1a8/0x1e0
arch/x86/entry/common.c:259
 [<ffffffff83fc1a62>] entry_SYSCALL_64_fastpath+0xc0/0xc2
Dumping ftrace buffer:
   (ftrace buffer empty)
Kernel Offset: disabled

Fix this the same way we did for TCP in commit 565b7b2d2e63
("tcp: do not send reset to already closed sockets")

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/proto.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 41e6580..9fe25bf 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -1009,6 +1009,10 @@ void dccp_close(struct sock *sk, long timeout)
 		__kfree_skb(skb);
 	}
 
+	/* If socket has been already reset kill it. */
+	if (sk->sk_state == DCCP_CLOSED)
+		goto adjudge_to_death;
+
 	if (data_was_unread) {
 		/* Unread data was tossed, send an appropriate Reset Code */
 		DCCP_WARN("ABORT with %u bytes unread\n", data_was_unread);
-- 
2.4.11


From fd5d96eba7d9c534580734fffc9bab2463699c34 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 2 Nov 2016 19:00:40 -0700
Subject: [PATCH 11/29] dccp: fix out of bound access in dccp_v4_err()

[ Upstream commit 6706a97fec963d6cb3f7fc2978ec1427b4651214 ]

dccp_v4_err() does not use pskb_may_pull() and might access garbage.

We only need 4 bytes at the beginning of the DCCP header, like TCP,
so the 8 bytes pulled in icmp_socket_deliver() are more than enough.

This patch might allow to process more ICMP messages, as some routers
are still limiting the size of reflected bytes to 28 (RFC 792), instead
of extended lengths (RFC 1812 4.3.2.3)

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ipv4.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index dff7cfa..b567c87 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -235,7 +235,7 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
 {
 	const struct iphdr *iph = (struct iphdr *)skb->data;
 	const u8 offset = iph->ihl << 2;
-	const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset);
+	const struct dccp_hdr *dh;
 	struct dccp_sock *dp;
 	struct inet_sock *inet;
 	const int type = icmp_hdr(skb)->type;
@@ -245,11 +245,13 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
 	int err;
 	struct net *net = dev_net(skb->dev);
 
-	if (skb->len < offset + sizeof(*dh) ||
-	    skb->len < offset + __dccp_basic_hdr_len(dh)) {
-		__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
-		return;
-	}
+	/* Only need dccph_dport & dccph_sport which are the first
+	 * 4 bytes in dccp header.
+	 * Our caller (icmp_socket_deliver()) already pulled 8 bytes for us.
+	 */
+	BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_sport) > 8);
+	BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_dport) > 8);
+	dh = (struct dccp_hdr *)(skb->data + offset);
 
 	sk = __inet_lookup_established(net, &dccp_hashinfo,
 				       iph->daddr, dh->dccph_dport,
-- 
2.4.11


From f5568a7d0b80c9d19c1876dcb0580ebb4f0853a8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 2 Nov 2016 20:30:48 -0700
Subject: [PATCH 12/29] ipv6: dccp: fix out of bound access in dccp_v6_err()

[ Upstream commit 1aa9d1a0e7eefcc61696e147d123453fc0016005 ]

dccp_v6_err() does not use pskb_may_pull() and might access garbage.

We only need 4 bytes at the beginning of the DCCP header, like TCP,
so the 8 bytes pulled in icmpv6_notify() are more than enough.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ipv6.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 09c4e19..b2a43af 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -70,7 +70,7 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 			u8 type, u8 code, int offset, __be32 info)
 {
 	const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
-	const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset);
+	const struct dccp_hdr *dh;
 	struct dccp_sock *dp;
 	struct ipv6_pinfo *np;
 	struct sock *sk;
@@ -78,12 +78,13 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	__u64 seq;
 	struct net *net = dev_net(skb->dev);
 
-	if (skb->len < offset + sizeof(*dh) ||
-	    skb->len < offset + __dccp_basic_hdr_len(dh)) {
-		__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
-				  ICMP6_MIB_INERRORS);
-		return;
-	}
+	/* Only need dccph_dport & dccph_sport which are the first
+	 * 4 bytes in dccp header.
+	 * Our caller (icmpv6_notify()) already pulled 8 bytes for us.
+	 */
+	BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_sport) > 8);
+	BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_dport) > 8);
+	dh = (struct dccp_hdr *)(skb->data + offset);
 
 	sk = __inet6_lookup_established(net, &dccp_hashinfo,
 					&hdr->daddr, dh->dccph_dport,
-- 
2.4.11


From d769fa8ba2d6d97c744c6992f35c95b5bf2471c2 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 3 Nov 2016 08:59:46 -0700
Subject: [PATCH 13/29] ipv6: dccp: add missing bind_conflict to
 dccp_ipv6_mapped

[ Upstream commit 990ff4d84408fc55942ca6644f67e361737b3d8e ]

While fuzzing kernel with syzkaller, Andrey reported a nasty crash
in inet6_bind() caused by DCCP lacking a required method.

Fixes: ab1e0a13d7029 ("[SOCK] proto: Add hashinfo member to struct proto")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ipv6.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index b2a43af..715e5d1 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -958,6 +958,7 @@ static const struct inet_connection_sock_af_ops dccp_ipv6_mapped = {
 	.getsockopt	   = ipv6_getsockopt,
 	.addr2sockaddr	   = inet6_csk_addr2sockaddr,
 	.sockaddr_len	   = sizeof(struct sockaddr_in6),
+	.bind_conflict	   = inet6_csk_bind_conflict,
 #ifdef CONFIG_COMPAT
 	.compat_setsockopt = compat_ipv6_setsockopt,
 	.compat_getsockopt = compat_ipv6_getsockopt,
-- 
2.4.11


From 014ef553bd16bda11088f3230c519692bb6fc3d7 Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Thu, 3 Nov 2016 17:03:41 -0200
Subject: [PATCH 14/29] sctp: assign assoc_id earlier in __sctp_connect

[ Upstream commit 7233bc84a3aeda835d334499dc00448373caf5c0 ]

sctp_wait_for_connect() currently already holds the asoc to keep it
alive during the sleep, in case another thread release it. But Andrey
Konovalov and Dmitry Vyukov reported an use-after-free in such
situation.

Problem is that __sctp_connect() doesn't get a ref on the asoc and will
do a read on the asoc after calling sctp_wait_for_connect(), but by then
another thread may have closed it and the _put on sctp_wait_for_connect
will actually release it, causing the use-after-free.

Fix is, instead of doing the read after waiting for the connect, do it
before so, and avoid this issue as the socket is still locked by then.
There should be no issue on returning the asoc id in case of failure as
the application shouldn't trust on that number in such situations
anyway.

This issue doesn't exist in sctp_sendmsg() path.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index baccbf3..89bde54 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1214,9 +1214,12 @@ static int __sctp_connect(struct sock *sk,
 
 	timeo = sock_sndtimeo(sk, f_flags & O_NONBLOCK);
 
-	err = sctp_wait_for_connect(asoc, &timeo);
-	if ((err == 0 || err == -EINPROGRESS) && assoc_id)
+	if (assoc_id)
 		*assoc_id = asoc->assoc_id;
+	err = sctp_wait_for_connect(asoc, &timeo);
+	/* Note: the asoc may be freed after the return of
+	 * sctp_wait_for_connect.
+	 */
 
 	/* Don't free association on exit. */
 	asoc = NULL;
-- 
2.4.11


From 3951b5c342a5f792d8aa9310fc79b1cbd4ae2684 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 4 Nov 2016 00:01:19 +0100
Subject: [PATCH 15/29] bpf: fix htab map destruction when extra reserve is in
 use

[ Upstream commit 483bed2b0ddd12ec33fc9407e0c6e1088e77a97c ]

Commit a6ed3ea65d98 ("bpf: restore behavior of bpf_map_update_elem")
added an extra per-cpu reserve to the hash table map to restore old
behaviour from pre prealloc times. When non-prealloc is in use for a
map, then problem is that once a hash table extra element has been
linked into the hash-table, and the hash table is destroyed due to
refcount dropping to zero, then htab_map_free() -> delete_all_elements()
will walk the whole hash table and drop all elements via htab_elem_free().
The problem is that the element from the extra reserve is first fed
to the wrong backend allocator and eventually freed twice.

Fixes: a6ed3ea65d98 ("bpf: restore behavior of bpf_map_update_elem")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/hashtab.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 570eeca..ad1bc67 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -687,7 +687,8 @@ static void delete_all_elements(struct bpf_htab *htab)
 
 		hlist_for_each_entry_safe(l, n, head, hash_node) {
 			hlist_del_rcu(&l->hash_node);
-			htab_elem_free(htab, l);
+			if (l->state != HTAB_EXTRA_ELEM_USED)
+				htab_elem_free(htab, l);
 		}
 	}
 }
-- 
2.4.11


From c5d83456f0c027da5f4774d20080b7d13887a8a6 Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Thu, 3 Nov 2016 16:17:26 -0700
Subject: [PATCH 16/29] net: icmp6_send should use dst dev to determine L3
 domain

[ Upstream commit 5d41ce29e3b91ef305f88d23f72b3359de329cec ]

icmp6_send is called in response to some event. The skb may not have
the device set (skb->dev is NULL), but it is expected to have a dst set.
Update icmp6_send to use the dst on the skb to determine L3 domain.

Fixes: ca254490c8dfd ("net: Add VRF support to IPv6 stack")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/icmp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index bd59c34..7370ad2 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -448,7 +448,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 	if (__ipv6_addr_needs_scope_id(addr_type))
 		iif = skb->dev->ifindex;
 	else
-		iif = l3mdev_master_ifindex(skb->dev);
+		iif = l3mdev_master_ifindex(skb_dst(skb)->dev);
 
 	/*
 	 *	Must not send error if the source does not uniquely
-- 
2.4.11


From 282cd2c0c2d8a0db0514b23eb4a25894ad50edcd Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Fri, 4 Nov 2016 15:11:57 -0400
Subject: [PATCH 17/29] fib_trie: Correct /proc/net/route off by one error

[ Upstream commit fd0285a39b1cb496f60210a9a00ad33a815603e7 ]

The display of /proc/net/route has had a couple issues due to the fact that
when I originally rewrote most of fib_trie I made it so that the iterator
was tracking the next value to use instead of the current.

In addition it had an off by 1 error where I was tracking the first piece
of data as position 0, even though in reality that belonged to the
SEQ_START_TOKEN.

This patch updates the code so the iterator tracks the last reported
position and key instead of the next expected position and key.  In
addition it shifts things so that all of the leaves start at 1 instead of
trying to report leaves starting with offset 0 as being valid.  With these
two issues addressed this should resolve any off by one errors that were
present in the display of /proc/net/route.

Fixes: 25b97c016b26 ("ipv4: off-by-one in continuation handling in /proc/net/route")
Cc: Andy Whitcroft <apw@canonical.com>
Reported-by: Jason Baron <jbaron@akamai.com>
Tested-by: Jason Baron <jbaron@akamai.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_trie.c | 21 +++++++++------------
 1 file changed, 9 insertions(+), 12 deletions(-)

diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index e2ffc2a..7ef7031 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -2455,22 +2455,19 @@ static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter,
 	struct key_vector *l, **tp = &iter->tnode;
 	t_key key;
 
-	/* use cache location of next-to-find key */
+	/* use cached location of previously found key */
 	if (iter->pos > 0 && pos >= iter->pos) {
-		pos -= iter->pos;
 		key = iter->key;
 	} else {
-		iter->pos = 0;
+		iter->pos = 1;
 		key = 0;
 	}
 
-	while ((l = leaf_walk_rcu(tp, key)) != NULL) {
+	pos -= iter->pos;
+
+	while ((l = leaf_walk_rcu(tp, key)) && (pos-- > 0)) {
 		key = l->key + 1;
 		iter->pos++;
-
-		if (--pos <= 0)
-			break;
-
 		l = NULL;
 
 		/* handle unlikely case of a key wrap */
@@ -2479,7 +2476,7 @@ static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter,
 	}
 
 	if (l)
-		iter->key = key;	/* remember it */
+		iter->key = l->key;	/* remember it */
 	else
 		iter->pos = 0;		/* forget it */
 
@@ -2507,7 +2504,7 @@ static void *fib_route_seq_start(struct seq_file *seq, loff_t *pos)
 		return fib_route_get_idx(iter, *pos);
 
 	iter->pos = 0;
-	iter->key = 0;
+	iter->key = KEY_MAX;
 
 	return SEQ_START_TOKEN;
 }
@@ -2516,7 +2513,7 @@ static void *fib_route_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	struct fib_route_iter *iter = seq->private;
 	struct key_vector *l = NULL;
-	t_key key = iter->key;
+	t_key key = iter->key + 1;
 
 	++*pos;
 
@@ -2525,7 +2522,7 @@ static void *fib_route_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 		l = leaf_walk_rcu(&iter->tnode, key);
 
 	if (l) {
-		iter->key = l->key + 1;
+		iter->key = l->key;
 		iter->pos++;
 	} else {
 		iter->pos = 0;
-- 
2.4.11


From 591fb8a07838e4db2c8e5ae86065e999b00eb9c4 Mon Sep 17 00:00:00 2001
From: Soheil Hassas Yeganeh <soheil@google.com>
Date: Fri, 4 Nov 2016 15:36:49 -0400
Subject: [PATCH 18/29] sock: fix sendmmsg for partial sendmsg
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 3023898b7d4aac65987bd2f485cc22390aae6f78 ]

Do not send the next message in sendmmsg for partial sendmsg
invocations.

sendmmsg assumes that it can continue sending the next message
when the return value of the individual sendmsg invocations
is positive. It results in corrupting the data for TCP,
SCTP, and UNIX streams.

For example, sendmmsg([["abcd"], ["efgh"]]) can result in a stream
of "aefgh" if the first sendmsg invocation sends only the first
byte while the second sendmsg goes through.

Datagram sockets either send the entire datagram or fail, so
this patch affects only sockets of type SOCK_STREAM and
SOCK_SEQPACKET.

Fixes: 228e548e6020 ("net: Add sendmmsg socket system call")
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Maciej Żenczykowski <maze@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/socket.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/socket.c b/net/socket.c
index a1bd161..03bc2c2 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2041,6 +2041,8 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
 		if (err)
 			break;
 		++datagrams;
+		if (msg_data_left(&msg_sys))
+			break;
 		cond_resched();
 	}
 
-- 
2.4.11


From 6aaa95e0bf70bb88ff4b984e48736cc772ebf01d Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Mon, 7 Nov 2016 12:03:09 -0800
Subject: [PATCH 19/29] net: icmp_route_lookup should use rt dev to determine
 L3 domain

[ Upstream commit 9d1a6c4ea43e48c7880c85971c17939b56832d8a ]

icmp_send is called in response to some event. The skb may not have
the device set (skb->dev is NULL), but it is expected to have an rt.
Update icmp_route_lookup to use the rt on the skb to determine L3
domain.

Fixes: 613d09b30f8b ("net: Use VRF device index for lookups on TX")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/icmp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 38abe70..48734ee 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -477,7 +477,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
 	fl4->flowi4_proto = IPPROTO_ICMP;
 	fl4->fl4_icmp_type = type;
 	fl4->fl4_icmp_code = code;
-	fl4->flowi4_oif = l3mdev_master_ifindex(skb_in->dev);
+	fl4->flowi4_oif = l3mdev_master_ifindex(skb_dst(skb_in)->dev);
 
 	security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4));
 	rt = __ip_route_output_key_hash(net, fl4,
@@ -502,7 +502,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
 	if (err)
 		goto relookup_failed;
 
-	if (inet_addr_type_dev_table(net, skb_in->dev,
+	if (inet_addr_type_dev_table(net, skb_dst(skb_in)->dev,
 				     fl4_dec.saddr) == RTN_LOCAL) {
 		rt2 = __ip_route_output_key(net, &fl4_dec);
 		if (IS_ERR(rt2))
-- 
2.4.11


From 12aedafa06bf92c3afdb02f5e8055e018b4bf3b6 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 9 Nov 2016 16:04:46 -0800
Subject: [PATCH 20/29] net: __skb_flow_dissect() must cap its return value

[ Upstream commit 34fad54c2537f7c99d07375e50cb30aa3c23bd83 ]

After Tom patch, thoff field could point past the end of the buffer,
this could fool some callers.

If an skb was provided, skb->len should be the upper limit.
If not, hlen is supposed to be the upper limit.

Fixes: a6e544b0a88b ("flow_dissector: Jump to exit code in __skb_flow_dissect")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Yibin Yang <yibyang@cisco.com
Acked-by: Alexander Duyck <alexander.h.duyck@intel.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/flow_dissector.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 52742a0..5550a86 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -118,7 +118,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
 	struct flow_dissector_key_tags *key_tags;
 	struct flow_dissector_key_keyid *key_keyid;
 	u8 ip_proto = 0;
-	bool ret = false;
+	bool ret;
 
 	if (!data) {
 		data = skb->data;
@@ -481,12 +481,17 @@ ip_proto_again:
 out_good:
 	ret = true;
 
-out_bad:
+	key_control->thoff = (u16)nhoff;
+out:
 	key_basic->n_proto = proto;
 	key_basic->ip_proto = ip_proto;
-	key_control->thoff = (u16)nhoff;
 
 	return ret;
+
+out_bad:
+	ret = false;
+	key_control->thoff = min_t(u16, nhoff, skb ? skb->len : hlen);
+	goto out;
 }
 EXPORT_SYMBOL(__skb_flow_dissect);
 
-- 
2.4.11


From 1ae316fd3a5d1819fe0a1e7a481528a9ecfd9e24 Mon Sep 17 00:00:00 2001
From: Stephen Suryaputra Lin <stephen.suryaputra.lin@gmail.com>
Date: Thu, 10 Nov 2016 11:16:15 -0500
Subject: [PATCH 21/29] ipv4: use new_gw for redirect neigh lookup

[ Upstream commit 969447f226b451c453ddc83cac6144eaeac6f2e3 ]

In v2.6, ip_rt_redirect() calls arp_bind_neighbour() which returns 0
and then the state of the neigh for the new_gw is checked. If the state
isn't valid then the redirected route is deleted. This behavior is
maintained up to v3.5.7 by check_peer_redirect() because rt->rt_gateway
is assigned to peer->redirect_learned.a4 before calling
ipv4_neigh_lookup().

After commit 5943634fc559 ("ipv4: Maintain redirect and PMTU info in
struct rtable again."), ipv4_neigh_lookup() is performed without the
rt_gateway assigned to the new_gw. In the case when rt_gateway (old_gw)
isn't zero, the function uses it as the key. The neigh is most likely
valid since the old_gw is the one that sends the ICMP redirect message.
Then the new_gw is assigned to fib_nh_exception. The problem is: the
new_gw ARP may never gets resolved and the traffic is blackholed.

So, use the new_gw for neigh lookup.

Changes from v1:
 - use __ipv4_neigh_lookup instead (per Eric Dumazet).

Fixes: 5943634fc559 ("ipv4: Maintain redirect and PMTU info in struct rtable again.")
Signed-off-by: Stephen Suryaputra Lin <ssurya@ieee.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 62c3ed0..2f23ef1 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -753,7 +753,9 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
 			goto reject_redirect;
 	}
 
-	n = ipv4_neigh_lookup(&rt->dst, NULL, &new_gw);
+	n = __ipv4_neigh_lookup(rt->dst.dev, new_gw);
+	if (!n)
+		n = neigh_create(&arp_tbl, &new_gw, rt->dst.dev);
 	if (!IS_ERR(n)) {
 		if (!(n->nud_state & NUD_VALID)) {
 			neigh_event_send(n, NULL);
-- 
2.4.11


From 19bd61a2547a1cead99de41191ce6c88f6e2038f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 10 Nov 2016 13:12:35 -0800
Subject: [PATCH 22/29] tcp: take care of truncations done by sk_filter()

[ Upstream commit ac6e780070e30e4c35bd395acfe9191e6268bdd3 ]

With syzkaller help, Marco Grassi found a bug in TCP stack,
crashing in tcp_collapse()

Root cause is that sk_filter() can truncate the incoming skb,
but TCP stack was not really expecting this to happen.
It probably was expecting a simple DROP or ACCEPT behavior.

We first need to make sure no part of TCP header could be removed.
Then we need to adjust TCP_SKB_CB(skb)->end_seq

Many thanks to syzkaller team and Marco for giving us a reproducer.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Marco Grassi <marco.gra@gmail.com>
Reported-by: Vladis Dronov <vdronov@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h   |  1 +
 net/ipv4/tcp_ipv4.c | 19 ++++++++++++++++++-
 net/ipv6/tcp_ipv6.c |  6 ++++--
 3 files changed, 23 insertions(+), 3 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 7717302..0de6989 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1164,6 +1164,7 @@ static inline void tcp_prequeue_init(struct tcp_sock *tp)
 }
 
 bool tcp_prequeue(struct sock *sk, struct sk_buff *skb);
+int tcp_filter(struct sock *sk, struct sk_buff *skb);
 
 #undef STATE_TRACE
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 7158d4f..7b235fa 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1537,6 +1537,21 @@ bool tcp_prequeue(struct sock *sk, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(tcp_prequeue);
 
+int tcp_filter(struct sock *sk, struct sk_buff *skb)
+{
+	struct tcphdr *th = (struct tcphdr *)skb->data;
+	unsigned int eaten = skb->len;
+	int err;
+
+	err = sk_filter_trim_cap(sk, skb, th->doff * 4);
+	if (!err) {
+		eaten -= skb->len;
+		TCP_SKB_CB(skb)->end_seq -= eaten;
+	}
+	return err;
+}
+EXPORT_SYMBOL(tcp_filter);
+
 /*
  *	From tcp_input.c
  */
@@ -1648,8 +1663,10 @@ process:
 
 	nf_reset(skb);
 
-	if (sk_filter(sk, skb))
+	if (tcp_filter(sk, skb))
 		goto discard_and_relse;
+	th = (const struct tcphdr *)skb->data;
+	iph = ip_hdr(skb);
 
 	skb->dev = NULL;
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index fc67822..af6a09e 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1228,7 +1228,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
 	if (skb->protocol == htons(ETH_P_IP))
 		return tcp_v4_do_rcv(sk, skb);
 
-	if (sk_filter(sk, skb))
+	if (tcp_filter(sk, skb))
 		goto discard;
 
 	/*
@@ -1455,8 +1455,10 @@ process:
 	if (tcp_v6_inbound_md5_hash(sk, skb))
 		goto discard_and_relse;
 
-	if (sk_filter(sk, skb))
+	if (tcp_filter(sk, skb))
 		goto discard_and_relse;
+	th = (const struct tcphdr *)skb->data;
+	hdr = ipv6_hdr(skb);
 
 	skb->dev = NULL;
 
-- 
2.4.11


From ed2a161454af398296a5abe3a12f79c30a73e31a Mon Sep 17 00:00:00 2001
From: Mike Frysinger <vapier@gentoo.org>
Date: Thu, 10 Nov 2016 19:08:39 -0500
Subject: [PATCH 23/29] Revert "include/uapi/linux/atm_zatm.h: include
 linux/time.h"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 7b5b74efcca00f15c2aec1dc7175bfe34b6ec643 ]

This reverts commit cf00713a655d ("include/uapi/linux/atm_zatm.h: include
linux/time.h").

This attempted to fix userspace breakage that no longer existed when
the patch was merged.  Almost one year earlier, commit 70ba07b675b5
("atm: remove 'struct zatm_t_hist'") deleted the struct in question.

After this patch was merged, we now have to deal with people being
unable to include this header in conjunction with standard C library
headers like stdlib.h (which linux-atm does).  Example breakage:
x86_64-pc-linux-gnu-gcc -DHAVE_CONFIG_H -I. -I../.. -I./../q2931 -I./../saal \
	-I.  -DCPPFLAGS_TEST  -I../../src/include -O2 -march=native -pipe -g \
	-frecord-gcc-switches -freport-bug -Wimplicit-function-declaration \
	-Wnonnull -Wstrict-aliasing -Wparentheses -Warray-bounds \
	-Wfree-nonheap-object -Wreturn-local-addr -fno-strict-aliasing -Wall \
	-Wshadow -Wpointer-arith -Wwrite-strings -Wstrict-prototypes -c zntune.c
In file included from /usr/include/linux/atm_zatm.h:17:0,
                 from zntune.c:17:
/usr/include/linux/time.h:9:8: error: redefinition of ‘struct timespec’
 struct timespec {
        ^
In file included from /usr/include/sys/select.h:43:0,
                 from /usr/include/sys/types.h:219,
                 from /usr/include/stdlib.h:314,
                 from zntune.c:9:
/usr/include/time.h:120:8: note: originally defined here
 struct timespec
        ^

Signed-off-by: Mike Frysinger <vapier@gentoo.org>
Acked-by: Mikko Rapeli <mikko.rapeli@iki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/atm_zatm.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/include/uapi/linux/atm_zatm.h b/include/uapi/linux/atm_zatm.h
index 5cd4d4d..9c9c6ad 100644
--- a/include/uapi/linux/atm_zatm.h
+++ b/include/uapi/linux/atm_zatm.h
@@ -14,7 +14,6 @@
 
 #include <linux/atmapi.h>
 #include <linux/atmioc.h>
-#include <linux/time.h>
 
 #define ZATM_GETPOOL	_IOW('a',ATMIOC_SARPRV+1,struct atmif_sioc)
 						/* get pool statistics */
-- 
2.4.11


From 7b13c882a3d4f27978bd6382f7ba8d618679cea2 Mon Sep 17 00:00:00 2001
From: Yotam Gigi <yotamg@mellanox.com>
Date: Fri, 11 Nov 2016 16:34:25 +0100
Subject: [PATCH 24/29] mlxsw: spectrum: Fix refcount bug on span entries

[ Upstream commit 2d644d4c7506646f9c4a2afceb7fd5f030bc0c9f ]

When binding port to a newly created span entry, its refcount is
initialized to zero even though it has a bound port. That leads
to unexpected behaviour when the user tries to delete that port
from the span entry.

Fix this by initializing the reference count to 1.

Also add a warning to put function.

Fixes: 763b4b70afcd ("mlxsw: spectrum: Add support in matchall mirror TC offloading")
Signed-off-by: Yotam Gigi <yotamg@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index d48873b..5cdc96b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -231,7 +231,7 @@ mlxsw_sp_span_entry_create(struct mlxsw_sp_port *port)
 
 	span_entry->used = true;
 	span_entry->id = index;
-	span_entry->ref_count = 0;
+	span_entry->ref_count = 1;
 	span_entry->local_port = local_port;
 	return span_entry;
 }
@@ -268,6 +268,7 @@ struct mlxsw_sp_span_entry *mlxsw_sp_span_entry_get(struct mlxsw_sp_port *port)
 
 	span_entry = mlxsw_sp_span_entry_find(port);
 	if (span_entry) {
+		/* Already exists, just take a reference */
 		span_entry->ref_count++;
 		return span_entry;
 	}
@@ -278,6 +279,7 @@ struct mlxsw_sp_span_entry *mlxsw_sp_span_entry_get(struct mlxsw_sp_port *port)
 static int mlxsw_sp_span_entry_put(struct mlxsw_sp *mlxsw_sp,
 				   struct mlxsw_sp_span_entry *span_entry)
 {
+	WARN_ON(!span_entry->ref_count);
 	if (--span_entry->ref_count == 0)
 		mlxsw_sp_span_entry_destroy(mlxsw_sp, span_entry);
 	return 0;
-- 
2.4.11


From cb3ed7f79ac0e7162fa01d561b1a044ab5c7681b Mon Sep 17 00:00:00 2001
From: Arkadi Sharshevsky <arkadis@mellanox.com>
Date: Fri, 11 Nov 2016 16:34:26 +0100
Subject: [PATCH 25/29] mlxsw: spectrum_router: Correctly dump neighbour
 activity

[ Upstream commit 42cdb338f40a98e6558bae35456fe86b6e90e1ef ]

The device's neighbour table is periodically dumped in order to update
the kernel about active neighbours. A single dump session may span
multiple queries, until the response carries less records than requested
or when a record (can contain up to four neighbour entries) is not full.
Current code stops the session when the number of returned records is
zero, which can result in infinite loop in case of high packet rate.

Fix this by stopping the session according to the above logic.

Fixes: c723c735fa6b ("mlxsw: spectrum_router: Periodically update the kernel's neigh table")
Signed-off-by: Arkadi Sharshevsky <arkadis@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_router.c  | 22 +++++++++++++++++++++-
 1 file changed, 21 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 3f5c51d..62514b9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -777,6 +777,26 @@ static void mlxsw_sp_router_neigh_rec_process(struct mlxsw_sp *mlxsw_sp,
 	}
 }
 
+static bool mlxsw_sp_router_rauhtd_is_full(char *rauhtd_pl)
+{
+	u8 num_rec, last_rec_index, num_entries;
+
+	num_rec = mlxsw_reg_rauhtd_num_rec_get(rauhtd_pl);
+	last_rec_index = num_rec - 1;
+
+	if (num_rec < MLXSW_REG_RAUHTD_REC_MAX_NUM)
+		return false;
+	if (mlxsw_reg_rauhtd_rec_type_get(rauhtd_pl, last_rec_index) ==
+	    MLXSW_REG_RAUHTD_TYPE_IPV6)
+		return true;
+
+	num_entries = mlxsw_reg_rauhtd_ipv4_rec_num_entries_get(rauhtd_pl,
+								last_rec_index);
+	if (++num_entries == MLXSW_REG_RAUHTD_IPV4_ENT_PER_REC)
+		return true;
+	return false;
+}
+
 static int mlxsw_sp_router_neighs_update_rauhtd(struct mlxsw_sp *mlxsw_sp)
 {
 	char *rauhtd_pl;
@@ -803,7 +823,7 @@ static int mlxsw_sp_router_neighs_update_rauhtd(struct mlxsw_sp *mlxsw_sp)
 		for (i = 0; i < num_rec; i++)
 			mlxsw_sp_router_neigh_rec_process(mlxsw_sp, rauhtd_pl,
 							  i);
-	} while (num_rec);
+	} while (mlxsw_sp_router_rauhtd_is_full(rauhtd_pl));
 	rtnl_unlock();
 
 	kfree(rauhtd_pl);
-- 
2.4.11


From 808f3c6dab3ba19175a4c83ff5f4fba47a019e9f Mon Sep 17 00:00:00 2001
From: Baoquan He <bhe@redhat.com>
Date: Sun, 13 Nov 2016 13:01:32 +0800
Subject: [PATCH 26/29] Revert "bnx2: Reset device during driver
 initialization"

[ Upstream commit 5d0d4b91bf627f14f95167b738d524156c9d440b ]

This reverts commit 3e1be7ad2d38c6bd6aeef96df9bd0a7822f4e51c.

When people build bnx2 driver into kernel, it will fail to detect
and load firmware because firmware is contained in initramfs and
initramfs has not been uncompressed yet during do_initcalls. So
revert commit 3e1be7a and work out a new way in the later patch.

Signed-off-by: Baoquan He <bhe@redhat.com>
Acked-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnx2.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c
index 505ceaf..8fc3f3c 100644
--- a/drivers/net/ethernet/broadcom/bnx2.c
+++ b/drivers/net/ethernet/broadcom/bnx2.c
@@ -6356,6 +6356,10 @@ bnx2_open(struct net_device *dev)
 	struct bnx2 *bp = netdev_priv(dev);
 	int rc;
 
+	rc = bnx2_request_firmware(bp);
+	if (rc < 0)
+		goto out;
+
 	netif_carrier_off(dev);
 
 	bnx2_disable_int(bp);
@@ -6424,6 +6428,7 @@ open_err:
 	bnx2_free_irq(bp);
 	bnx2_free_mem(bp);
 	bnx2_del_napi(bp);
+	bnx2_release_firmware(bp);
 	goto out;
 }
 
@@ -8570,12 +8575,6 @@ bnx2_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	pci_set_drvdata(pdev, dev);
 
-	rc = bnx2_request_firmware(bp);
-	if (rc < 0)
-		goto error;
-
-
-	bnx2_reset_chip(bp, BNX2_DRV_MSG_CODE_RESET);
 	memcpy(dev->dev_addr, bp->mac_addr, ETH_ALEN);
 
 	dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_SG |
@@ -8608,7 +8607,6 @@ bnx2_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	return 0;
 
 error:
-	bnx2_release_firmware(bp);
 	pci_iounmap(pdev, bp->regview);
 	pci_release_regions(pdev);
 	pci_disable_device(pdev);
-- 
2.4.11


From 0eb044db9f4a071ebcf68fd64c0fb27c64d05d96 Mon Sep 17 00:00:00 2001
From: Baoquan He <bhe@redhat.com>
Date: Sun, 13 Nov 2016 13:01:33 +0800
Subject: [PATCH 27/29] bnx2: Wait for in-flight DMA to complete at probe stage

[ Upstream commit 6df77862f63f389df3b1ad879738e04440d7385d ]

In-flight DMA from 1st kernel could continue going in kdump kernel.
New io-page table has been created before bnx2 does reset at open stage.
We have to wait for the in-flight DMA to complete to avoid it look up
into the newly created io-page table at probe stage.

Suggested-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Baoquan He <bhe@redhat.com>
Acked-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnx2.c | 38 ++++++++++++++++++++++++++++++------
 1 file changed, 32 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c
index 8fc3f3c..2c850a9 100644
--- a/drivers/net/ethernet/broadcom/bnx2.c
+++ b/drivers/net/ethernet/broadcom/bnx2.c
@@ -49,6 +49,7 @@
 #include <linux/firmware.h>
 #include <linux/log2.h>
 #include <linux/aer.h>
+#include <linux/crash_dump.h>
 
 #if defined(CONFIG_CNIC) || defined(CONFIG_CNIC_MODULE)
 #define BCM_CNIC 1
@@ -4759,15 +4760,16 @@ bnx2_setup_msix_tbl(struct bnx2 *bp)
 	BNX2_WR(bp, BNX2_PCI_GRC_WINDOW3_ADDR, BNX2_MSIX_PBA_ADDR);
 }
 
-static int
-bnx2_reset_chip(struct bnx2 *bp, u32 reset_code)
+static void
+bnx2_wait_dma_complete(struct bnx2 *bp)
 {
 	u32 val;
-	int i, rc = 0;
-	u8 old_port;
+	int i;
 
-	/* Wait for the current PCI transaction to complete before
-	 * issuing a reset. */
+	/*
+	 * Wait for the current PCI transaction to complete before
+	 * issuing a reset.
+	 */
 	if ((BNX2_CHIP(bp) == BNX2_CHIP_5706) ||
 	    (BNX2_CHIP(bp) == BNX2_CHIP_5708)) {
 		BNX2_WR(bp, BNX2_MISC_ENABLE_CLR_BITS,
@@ -4791,6 +4793,21 @@ bnx2_reset_chip(struct bnx2 *bp, u32 reset_code)
 		}
 	}
 
+	return;
+}
+
+
+static int
+bnx2_reset_chip(struct bnx2 *bp, u32 reset_code)
+{
+	u32 val;
+	int i, rc = 0;
+	u8 old_port;
+
+	/* Wait for the current PCI transaction to complete before
+	 * issuing a reset. */
+	bnx2_wait_dma_complete(bp);
+
 	/* Wait for the firmware to tell us it is ok to issue a reset. */
 	bnx2_fw_sync(bp, BNX2_DRV_MSG_DATA_WAIT0 | reset_code, 1, 1);
 
@@ -8575,6 +8592,15 @@ bnx2_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	pci_set_drvdata(pdev, dev);
 
+	/*
+	 * In-flight DMA from 1st kernel could continue going in kdump kernel.
+	 * New io-page table has been created before bnx2 does reset at open stage.
+	 * We have to wait for the in-flight DMA to complete to avoid it look up
+	 * into the newly created io-page table.
+	 */
+	if (is_kdump_kernel())
+		bnx2_wait_dma_complete(bp);
+
 	memcpy(dev->dev_addr, bp->mac_addr, ETH_ALEN);
 
 	dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_SG |
-- 
2.4.11


From 7e101cfc8fe0715b228f3aeb90f2c7172c67cf2b Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 13 Nov 2016 21:44:37 +0800
Subject: [PATCH 28/29] sctp: change sk state only when it has assocs in
 sctp_shutdown

[ Upstream commit 5bf35ddfee052d44f39ebaa395d87101c8918405 ]

Now when users shutdown a sock with SEND_SHUTDOWN in sctp, even if
this sock has no connection (assoc), sk state would be changed to
SCTP_SS_CLOSING, which is not as we expect.

Besides, after that if users try to listen on this sock, kernel
could even panic when it dereference sctp_sk(sk)->bind_hash in
sctp_inet_listen, as bind_hash is null when sock has no assoc.

This patch is to move sk state change after checking sk assocs
is not empty, and also merge these two if() conditions and reduce
indent level.

Fixes: d46e416c11c8 ("sctp: sctp should change socket state when shutdown is received")
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 89bde54..7b0e059 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4281,19 +4281,18 @@ static void sctp_shutdown(struct sock *sk, int how)
 {
 	struct net *net = sock_net(sk);
 	struct sctp_endpoint *ep;
-	struct sctp_association *asoc;
 
 	if (!sctp_style(sk, TCP))
 		return;
 
-	if (how & SEND_SHUTDOWN) {
+	ep = sctp_sk(sk)->ep;
+	if (how & SEND_SHUTDOWN && !list_empty(&ep->asocs)) {
+		struct sctp_association *asoc;
+
 		sk->sk_state = SCTP_SS_CLOSING;
-		ep = sctp_sk(sk)->ep;
-		if (!list_empty(&ep->asocs)) {
-			asoc = list_entry(ep->asocs.next,
-					  struct sctp_association, asocs);
-			sctp_primitive_SHUTDOWN(net, asoc, NULL);
-		}
+		asoc = list_entry(ep->asocs.next,
+				  struct sctp_association, asocs);
+		sctp_primitive_SHUTDOWN(net, asoc, NULL);
 	}
 }
 
-- 
2.4.11


From 2792654c19c193910742a99ea72fa9d0f15289f0 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Sun, 13 Nov 2016 17:50:35 -0800
Subject: [PATCH 29/29] net: stmmac: Fix lack of link transition for fixed PHYs

[ Upstream commit c51e424dc79e1428afc4d697cdb6a07f7af70cbf ]

Commit 52f95bbfcf72 ("stmmac: fix adjust link call in case of a switch
is attached") added some logic to avoid polling the fixed PHY and
therefore invoking the adjust_link callback more than once, since this
is a fixed PHY and link events won't be generated.

This works fine the first time, because we start with phydev->irq =
PHY_POLL, so we call adjust_link, then we set phydev->irq =
PHY_IGNORE_INTERRUPT and we stop polling the PHY.

Now, if we called ndo_close(), which calls both phy_stop() and does an
explicit netif_carrier_off(), we end up with a link down. Upon calling
ndo_open() again, despite starting the PHY state machine, we have
PHY_IGNORE_INTERRUPT set, and we generate no link event at all, so the
link is permanently down.

Fixes: 52f95bbfcf72 ("stmmac: fix adjust link call in case of a switch is attached")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Acked-by: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 4c8c60a..fe9e7b1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -871,6 +871,13 @@ static int stmmac_init_phy(struct net_device *dev)
 		return -ENODEV;
 	}
 
+	/* stmmac_adjust_link will change this to PHY_IGNORE_INTERRUPT to avoid
+	 * subsequent PHY polling, make sure we force a link transition if
+	 * we have a UP/DOWN/UP transition
+	 */
+	if (phydev->is_pseudo_fixed_link)
+		phydev->irq = PHY_POLL;
+
 	pr_debug("stmmac_init_phy:  %s: attached to PHY (UID 0x%x)"
 		 " Link = %d\n", dev->name, phydev->phy_id, phydev->link);
 
-- 
2.4.11

Re: [PATCHES] Networking

[Greg KH]

On Thu, Nov 17, 2016 at 09:59:01PM -0500, David Miller wrote:
> 
> Please queue up the following networking bug fixes for 4.4.x and 4.8.x
> -stable, respectively.

All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 92 bytes --]


Please queue up the following bug fixes for 4.4.x and 4.8.x
-stable, repectively.

Thanks!

[-- Attachment #2: net_44.mbox --]
[-- Type: Application/Octet-Stream, Size: 56962 bytes --]

From 5d5c658846125a379a2102398ce38fb77b1c6ecc Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 15 Nov 2016 22:24:12 -0800
Subject: [PATCH 01/19] virtio-net: add a missing synchronize_net()

[ Upstream commit 963abe5c8a0273a1cf5913556da1b1189de0e57a ]

It seems many drivers do not respect napi_hash_del() contract.

When napi_hash_del() is used before netif_napi_del(), an RCU grace
period is needed before freeing NAPI object.

Fixes: 91815639d880 ("virtio-net: rx busy polling support")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index f94ab78..0e2a19e 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1465,6 +1465,11 @@ static void virtnet_free_queues(struct virtnet_info *vi)
 		netif_napi_del(&vi->rq[i].napi);
 	}
 
+	/* We called napi_hash_del() before netif_napi_del(),
+	 * we need to respect an RCU grace period before freeing vi->rq
+	 */
+	synchronize_net();
+
 	kfree(vi->rq);
 	kfree(vi->sq);
 }
-- 
2.7.4


From 7d324f7356dc2dc3a3a3aff9f75be0bc79e4ddf0 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Wed, 16 Nov 2016 10:27:02 -0800
Subject: [PATCH 02/19] net: check dead netns for peernet2id_alloc()

[ Upstream commit cfc44a4d147ea605d66ccb917cc24467d15ff867 ]

Andrei reports we still allocate netns ID from idr after we destroy
it in cleanup_net().

cleanup_net():
  ...
  idr_destroy(&net->netns_ids);
  ...
  list_for_each_entry_reverse(ops, &pernet_list, list)
    ops_exit_list(ops, &net_exit_list);
      -> rollback_registered_many()
        -> rtmsg_ifinfo_build_skb()
         -> rtnl_fill_ifinfo()
           -> peernet2id_alloc()

After that point we should not even access net->netns_ids, we
should check the death of the current netns as early as we can in
peernet2id_alloc().

For net-next we can consider to avoid sending rtmsg totally,
it is a good optimization for netns teardown path.

Fixes: 0c7aecd4bde4 ("netns: add rtnl cmd to add and get peer netns ids")
Reported-by: Andrei Vagin <avagin@gmail.com>
Cc: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Andrei Vagin <avagin@openvz.org>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/net_namespace.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 2c2eb1b..2e9a1c2 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -217,6 +217,8 @@ int peernet2id_alloc(struct net *net, struct net *peer)
 	bool alloc;
 	int id;
 
+	if (atomic_read(&net->count) == 0)
+		return NETNSA_NSID_NOT_ASSIGNED;
 	spin_lock_irqsave(&net->nsid_lock, flags);
 	alloc = atomic_read(&peer->count) == 0 ? false : true;
 	id = __peernet2id_alloc(net, peer, &alloc);
-- 
2.7.4


From cdd553181af06697935b756b03ef3dc0b5694031 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 16 Nov 2016 16:26:46 +0100
Subject: [PATCH 03/19] ip6_tunnel: disable caching when the traffic class is
 inherited

[ Upstream commit b5c2d49544e5930c96e2632a7eece3f4325a1888 ]

If an ip6 tunnel is configured to inherit the traffic class from
the inner header, the dst_cache must be disabled or it will foul
the policy routing.

The issue is apprently there since at leat Linux-2.6.12-rc2.

Reported-by: Liam McBirnie <liam.mcbirnie@boeing.com>
Cc: Liam McBirnie <liam.mcbirnie@boeing.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index e887888..2994d1f 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1043,6 +1043,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
 	struct ipv6_tel_txoption opt;
 	struct dst_entry *dst = NULL, *ndst = NULL;
 	struct net_device *tdev;
+	bool use_cache = false;
 	int mtu;
 	unsigned int max_headroom = sizeof(struct ipv6hdr);
 	u8 proto;
@@ -1070,7 +1071,15 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
 
 		memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr));
 		neigh_release(neigh);
-	} else if (!fl6->flowi6_mark)
+	} else if (!(t->parms.flags &
+		     (IP6_TNL_F_USE_ORIG_TCLASS | IP6_TNL_F_USE_ORIG_FWMARK))) {
+		/* enable the cache only only if the routing decision does
+		 * not depend on the current inner header value
+		 */
+		use_cache = true;
+	}
+
+	if (use_cache)
 		dst = ip6_tnl_dst_get(t);
 
 	if (!ip6_tnl_xmit_ctl(t, &fl6->saddr, &fl6->daddr))
@@ -1134,7 +1143,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
 		skb = new_skb;
 	}
 
-	if (!fl6->flowi6_mark && ndst)
+	if (use_cache && ndst)
 		ip6_tnl_dst_set(t, ndst);
 	skb_dst_set(skb, dst);
 
-- 
2.7.4


From 2169db92f47de0433c32bdf87d3e2bda9ea567f0 Mon Sep 17 00:00:00 2001
From: Jeremy Linton <jeremy.linton@arm.com>
Date: Thu, 17 Nov 2016 09:14:25 -0600
Subject: [PATCH 04/19] net: sky2: Fix shutdown crash

[ Upstream commit 06ba3b2133dc203e1e9bc36cee7f0839b79a9e8b ]

The sky2 frequently crashes during machine shutdown with:

sky2_get_stats+0x60/0x3d8 [sky2]
dev_get_stats+0x68/0xd8
rtnl_fill_stats+0x54/0x140
rtnl_fill_ifinfo+0x46c/0xc68
rtmsg_ifinfo_build_skb+0x7c/0xf0
rtmsg_ifinfo.part.22+0x3c/0x70
rtmsg_ifinfo+0x50/0x5c
netdev_state_change+0x4c/0x58
linkwatch_do_dev+0x50/0x88
__linkwatch_run_queue+0x104/0x1a4
linkwatch_event+0x30/0x3c
process_one_work+0x140/0x3e0
worker_thread+0x60/0x44c
kthread+0xdc/0xf0
ret_from_fork+0x10/0x50

This is caused by the sky2 being called after it has been shutdown.
A previous thread about this can be found here:

https://lkml.org/lkml/2016/4/12/410

An alternative fix is to assure that IFF_UP gets cleared by
calling dev_close() during shutdown. This is similar to what the
bnx2/tg3/xgene and maybe others are doing to assure that the driver
isn't being called following _shutdown().

Signed-off-by: Jeremy Linton <jeremy.linton@arm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/sky2.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index 5606a04..4b62aa1 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -5220,6 +5220,19 @@ static SIMPLE_DEV_PM_OPS(sky2_pm_ops, sky2_suspend, sky2_resume);
 
 static void sky2_shutdown(struct pci_dev *pdev)
 {
+	struct sky2_hw *hw = pci_get_drvdata(pdev);
+	int port;
+
+	for (port = 0; port < hw->ports; port++) {
+		struct net_device *ndev = hw->dev[port];
+
+		rtnl_lock();
+		if (netif_running(ndev)) {
+			dev_close(ndev);
+			netif_device_detach(ndev);
+		}
+		rtnl_unlock();
+	}
 	sky2_suspend(&pdev->dev);
 	pci_wake_from_d3(pdev, device_may_wakeup(&pdev->dev));
 	pci_set_power_state(pdev, PCI_D3hot);
-- 
2.7.4


From 124d711d08c85ff1325451b5b818223ccb1fed64 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Thu, 17 Nov 2016 15:55:26 -0800
Subject: [PATCH 05/19] af_unix: conditionally use freezable blocking calls in
 read

[ Upstream commit 06a77b07e3b44aea2b3c0e64de420ea2cfdcbaa9 ]

Commit 2b15af6f95 ("af_unix: use freezable blocking calls in read")
converts schedule_timeout() to its freezable version, it was probably
correct at that time, but later, commit 2b514574f7e8
("net: af_unix: implement splice for stream af_unix sockets") breaks
the strong requirement for a freezable sleep, according to
commit 0f9548ca1091:

    We shouldn't try_to_freeze if locks are held.  Holding a lock can cause a
    deadlock if the lock is later acquired in the suspend or hibernate path
    (e.g.  by dpm).  Holding a lock can also cause a deadlock in the case of
    cgroup_freezer if a lock is held inside a frozen cgroup that is later
    acquired by a process outside that group.

The pipe_lock is still held at that point.

So use freezable version only for the recvmsg call path, avoid impact for
Android.

Fixes: 2b514574f7e8 ("net: af_unix: implement splice for stream af_unix sockets")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Colin Cross <ccross@android.com>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 824cc1e..73f7525 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2194,7 +2194,8 @@ out:
  *	Sleep until more data has arrived. But check for races..
  */
 static long unix_stream_data_wait(struct sock *sk, long timeo,
-				  struct sk_buff *last, unsigned int last_len)
+				  struct sk_buff *last, unsigned int last_len,
+				  bool freezable)
 {
 	struct sk_buff *tail;
 	DEFINE_WAIT(wait);
@@ -2215,7 +2216,10 @@ static long unix_stream_data_wait(struct sock *sk, long timeo,
 
 		sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 		unix_state_unlock(sk);
-		timeo = freezable_schedule_timeout(timeo);
+		if (freezable)
+			timeo = freezable_schedule_timeout(timeo);
+		else
+			timeo = schedule_timeout(timeo);
 		unix_state_lock(sk);
 
 		if (sock_flag(sk, SOCK_DEAD))
@@ -2245,7 +2249,8 @@ struct unix_stream_read_state {
 	unsigned int splice_flags;
 };
 
-static int unix_stream_read_generic(struct unix_stream_read_state *state)
+static int unix_stream_read_generic(struct unix_stream_read_state *state,
+				    bool freezable)
 {
 	struct scm_cookie scm;
 	struct socket *sock = state->socket;
@@ -2324,7 +2329,7 @@ again:
 			mutex_unlock(&u->iolock);
 
 			timeo = unix_stream_data_wait(sk, timeo, last,
-						      last_len);
+						      last_len, freezable);
 
 			if (signal_pending(current)) {
 				err = sock_intr_errno(timeo);
@@ -2466,7 +2471,7 @@ static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg,
 		.flags = flags
 	};
 
-	return unix_stream_read_generic(&state);
+	return unix_stream_read_generic(&state, true);
 }
 
 static ssize_t skb_unix_socket_splice(struct sock *sk,
@@ -2512,7 +2517,7 @@ static ssize_t unix_stream_splice_read(struct socket *sock,  loff_t *ppos,
 	    flags & SPLICE_F_NONBLOCK)
 		state.flags = MSG_DONTWAIT;
 
-	return unix_stream_read_generic(&state);
+	return unix_stream_read_generic(&state, false);
 }
 
 static int unix_shutdown(struct socket *sock, int mode)
-- 
2.7.4


From 9ff92f58a44b0a9823512cfba39b41f93e06b9e4 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 18 Nov 2016 15:50:39 +0100
Subject: [PATCH 06/19] rtnetlink: fix FDB size computation

[ Upstream commit f82ef3e10a870acc19fa04f80ef5877eaa26f41e ]

Add missing NDA_VLAN attribute's size.

Fixes: 1e53d5bb8878 ("net: Pass VLAN ID to rtnl_fdb_notify.")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 87b91ff..b94e165 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2600,7 +2600,10 @@ nla_put_failure:
 
 static inline size_t rtnl_fdb_nlmsg_size(void)
 {
-	return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(ETH_ALEN);
+	return NLMSG_ALIGN(sizeof(struct ndmsg)) +
+	       nla_total_size(ETH_ALEN) +	/* NDA_LLADDR */
+	       nla_total_size(sizeof(u16)) +	/* NDA_VLAN */
+	       0;
 }
 
 static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, u16 vid, int type)
-- 
2.7.4


From f26a8b9b7ab7a554db0cd45ac78cb08bea882e9d Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Fri, 18 Nov 2016 22:13:00 +0100
Subject: [PATCH 07/19] l2tp: fix racy SOCK_ZAPPED flag check in
 l2tp_ip{,6}_bind()

[ Upstream commit 32c231164b762dddefa13af5a0101032c70b50ef ]

Lock socket before checking the SOCK_ZAPPED flag in l2tp_ip6_bind().
Without lock, a concurrent call could modify the socket flags between
the sock_flag(sk, SOCK_ZAPPED) test and the lock_sock() call. This way,
a socket could be inserted twice in l2tp_ip6_bind_table. Releasing it
would then leave a stale pointer there, generating use-after-free
errors when walking through the list or modifying adjacent entries.

BUG: KASAN: use-after-free in l2tp_ip6_close+0x22e/0x290 at addr ffff8800081b0ed8
Write of size 8 by task syz-executor/10987
CPU: 0 PID: 10987 Comm: syz-executor Not tainted 4.8.0+ #39
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.2-0-g33fbe13 by qemu-project.org 04/01/2014
 ffff880031d97838 ffffffff829f835b ffff88001b5a1640 ffff8800081b0ec0
 ffff8800081b15a0 ffff8800081b6d20 ffff880031d97860 ffffffff8174d3cc
 ffff880031d978f0 ffff8800081b0e80 ffff88001b5a1640 ffff880031d978e0
Call Trace:
 [<ffffffff829f835b>] dump_stack+0xb3/0x118 lib/dump_stack.c:15
 [<ffffffff8174d3cc>] kasan_object_err+0x1c/0x70 mm/kasan/report.c:156
 [<     inline     >] print_address_description mm/kasan/report.c:194
 [<ffffffff8174d666>] kasan_report_error+0x1f6/0x4d0 mm/kasan/report.c:283
 [<     inline     >] kasan_report mm/kasan/report.c:303
 [<ffffffff8174db7e>] __asan_report_store8_noabort+0x3e/0x40 mm/kasan/report.c:329
 [<     inline     >] __write_once_size ./include/linux/compiler.h:249
 [<     inline     >] __hlist_del ./include/linux/list.h:622
 [<     inline     >] hlist_del_init ./include/linux/list.h:637
 [<ffffffff8579047e>] l2tp_ip6_close+0x22e/0x290 net/l2tp/l2tp_ip6.c:239
 [<ffffffff850b2dfd>] inet_release+0xed/0x1c0 net/ipv4/af_inet.c:415
 [<ffffffff851dc5a0>] inet6_release+0x50/0x70 net/ipv6/af_inet6.c:422
 [<ffffffff84c4581d>] sock_release+0x8d/0x1d0 net/socket.c:570
 [<ffffffff84c45976>] sock_close+0x16/0x20 net/socket.c:1017
 [<ffffffff817a108c>] __fput+0x28c/0x780 fs/file_table.c:208
 [<ffffffff817a1605>] ____fput+0x15/0x20 fs/file_table.c:244
 [<ffffffff813774f9>] task_work_run+0xf9/0x170
 [<ffffffff81324aae>] do_exit+0x85e/0x2a00
 [<ffffffff81326dc8>] do_group_exit+0x108/0x330
 [<ffffffff81348cf7>] get_signal+0x617/0x17a0 kernel/signal.c:2307
 [<ffffffff811b49af>] do_signal+0x7f/0x18f0
 [<ffffffff810039bf>] exit_to_usermode_loop+0xbf/0x150 arch/x86/entry/common.c:156
 [<     inline     >] prepare_exit_to_usermode arch/x86/entry/common.c:190
 [<ffffffff81006060>] syscall_return_slowpath+0x1a0/0x1e0 arch/x86/entry/common.c:259
 [<ffffffff85e4d726>] entry_SYSCALL_64_fastpath+0xc4/0xc6
Object at ffff8800081b0ec0, in cache L2TP/IPv6 size: 1448
Allocated:
PID = 10987
 [ 1116.897025] [<ffffffff811ddcb6>] save_stack_trace+0x16/0x20
 [ 1116.897025] [<ffffffff8174c736>] save_stack+0x46/0xd0
 [ 1116.897025] [<ffffffff8174c9ad>] kasan_kmalloc+0xad/0xe0
 [ 1116.897025] [<ffffffff8174cee2>] kasan_slab_alloc+0x12/0x20
 [ 1116.897025] [<     inline     >] slab_post_alloc_hook mm/slab.h:417
 [ 1116.897025] [<     inline     >] slab_alloc_node mm/slub.c:2708
 [ 1116.897025] [<     inline     >] slab_alloc mm/slub.c:2716
 [ 1116.897025] [<ffffffff817476a8>] kmem_cache_alloc+0xc8/0x2b0 mm/slub.c:2721
 [ 1116.897025] [<ffffffff84c4f6a9>] sk_prot_alloc+0x69/0x2b0 net/core/sock.c:1326
 [ 1116.897025] [<ffffffff84c58ac8>] sk_alloc+0x38/0xae0 net/core/sock.c:1388
 [ 1116.897025] [<ffffffff851ddf67>] inet6_create+0x2d7/0x1000 net/ipv6/af_inet6.c:182
 [ 1116.897025] [<ffffffff84c4af7b>] __sock_create+0x37b/0x640 net/socket.c:1153
 [ 1116.897025] [<     inline     >] sock_create net/socket.c:1193
 [ 1116.897025] [<     inline     >] SYSC_socket net/socket.c:1223
 [ 1116.897025] [<ffffffff84c4b46f>] SyS_socket+0xef/0x1b0 net/socket.c:1203
 [ 1116.897025] [<ffffffff85e4d685>] entry_SYSCALL_64_fastpath+0x23/0xc6
Freed:
PID = 10987
 [ 1116.897025] [<ffffffff811ddcb6>] save_stack_trace+0x16/0x20
 [ 1116.897025] [<ffffffff8174c736>] save_stack+0x46/0xd0
 [ 1116.897025] [<ffffffff8174cf61>] kasan_slab_free+0x71/0xb0
 [ 1116.897025] [<     inline     >] slab_free_hook mm/slub.c:1352
 [ 1116.897025] [<     inline     >] slab_free_freelist_hook mm/slub.c:1374
 [ 1116.897025] [<     inline     >] slab_free mm/slub.c:2951
 [ 1116.897025] [<ffffffff81748b28>] kmem_cache_free+0xc8/0x330 mm/slub.c:2973
 [ 1116.897025] [<     inline     >] sk_prot_free net/core/sock.c:1369
 [ 1116.897025] [<ffffffff84c541eb>] __sk_destruct+0x32b/0x4f0 net/core/sock.c:1444
 [ 1116.897025] [<ffffffff84c5aca4>] sk_destruct+0x44/0x80 net/core/sock.c:1452
 [ 1116.897025] [<ffffffff84c5ad33>] __sk_free+0x53/0x220 net/core/sock.c:1460
 [ 1116.897025] [<ffffffff84c5af23>] sk_free+0x23/0x30 net/core/sock.c:1471
 [ 1116.897025] [<ffffffff84c5cb6c>] sk_common_release+0x28c/0x3e0 ./include/net/sock.h:1589
 [ 1116.897025] [<ffffffff8579044e>] l2tp_ip6_close+0x1fe/0x290 net/l2tp/l2tp_ip6.c:243
 [ 1116.897025] [<ffffffff850b2dfd>] inet_release+0xed/0x1c0 net/ipv4/af_inet.c:415
 [ 1116.897025] [<ffffffff851dc5a0>] inet6_release+0x50/0x70 net/ipv6/af_inet6.c:422
 [ 1116.897025] [<ffffffff84c4581d>] sock_release+0x8d/0x1d0 net/socket.c:570
 [ 1116.897025] [<ffffffff84c45976>] sock_close+0x16/0x20 net/socket.c:1017
 [ 1116.897025] [<ffffffff817a108c>] __fput+0x28c/0x780 fs/file_table.c:208
 [ 1116.897025] [<ffffffff817a1605>] ____fput+0x15/0x20 fs/file_table.c:244
 [ 1116.897025] [<ffffffff813774f9>] task_work_run+0xf9/0x170
 [ 1116.897025] [<ffffffff81324aae>] do_exit+0x85e/0x2a00
 [ 1116.897025] [<ffffffff81326dc8>] do_group_exit+0x108/0x330
 [ 1116.897025] [<ffffffff81348cf7>] get_signal+0x617/0x17a0 kernel/signal.c:2307
 [ 1116.897025] [<ffffffff811b49af>] do_signal+0x7f/0x18f0
 [ 1116.897025] [<ffffffff810039bf>] exit_to_usermode_loop+0xbf/0x150 arch/x86/entry/common.c:156
 [ 1116.897025] [<     inline     >] prepare_exit_to_usermode arch/x86/entry/common.c:190
 [ 1116.897025] [<ffffffff81006060>] syscall_return_slowpath+0x1a0/0x1e0 arch/x86/entry/common.c:259
 [ 1116.897025] [<ffffffff85e4d726>] entry_SYSCALL_64_fastpath+0xc4/0xc6
Memory state around the buggy address:
 ffff8800081b0d80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 ffff8800081b0e00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
>ffff8800081b0e80: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb
                                                    ^
 ffff8800081b0f00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff8800081b0f80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb

==================================================================

The same issue exists with l2tp_ip_bind() and l2tp_ip_bind_table.

Fixes: c51ce49735c1 ("l2tp: fix oops in L2TP IP sockets for connect() AF_UNSPEC case")
Reported-by: Baozeng Ding <sploving1@gmail.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Baozeng Ding <sploving1@gmail.com>
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ip.c  | 5 +++--
 net/l2tp/l2tp_ip6.c | 5 +++--
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 42de4cc..d0e906d 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -251,8 +251,6 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	int ret;
 	int chk_addr_ret;
 
-	if (!sock_flag(sk, SOCK_ZAPPED))
-		return -EINVAL;
 	if (addr_len < sizeof(struct sockaddr_l2tpip))
 		return -EINVAL;
 	if (addr->l2tp_family != AF_INET)
@@ -267,6 +265,9 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	read_unlock_bh(&l2tp_ip_lock);
 
 	lock_sock(sk);
+	if (!sock_flag(sk, SOCK_ZAPPED))
+		goto out;
+
 	if (sk->sk_state != TCP_CLOSE || addr_len < sizeof(struct sockaddr_l2tpip))
 		goto out;
 
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 9ee4ddb..3c4f867 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -266,8 +266,6 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	int addr_type;
 	int err;
 
-	if (!sock_flag(sk, SOCK_ZAPPED))
-		return -EINVAL;
 	if (addr->l2tp_family != AF_INET6)
 		return -EINVAL;
 	if (addr_len < sizeof(*addr))
@@ -293,6 +291,9 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	lock_sock(sk);
 
 	err = -EINVAL;
+	if (!sock_flag(sk, SOCK_ZAPPED))
+		goto out_unlock;
+
 	if (sk->sk_state != TCP_CLOSE)
 		goto out_unlock;
 
-- 
2.7.4


From f0a24d457c07d3673ef9fe633240ca994a1c200b Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 22 Nov 2016 11:40:58 -0800
Subject: [PATCH 08/19] net: dsa: bcm_sf2: Ensure we re-negotiate EEE during
 after link change

[ Upstream commit 76da8706d90d8641eeb9b8e579942ed80b6c0880 ]

In case the link change and EEE is enabled or disabled, always try to
re-negotiate this with the link partner.

Fixes: 450b05c15f9c ("net: dsa: bcm_sf2: add support for controlling EEE")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 6f946fe..0864f05 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -1137,6 +1137,7 @@ static void bcm_sf2_sw_adjust_link(struct dsa_switch *ds, int port,
 				   struct phy_device *phydev)
 {
 	struct bcm_sf2_priv *priv = ds_to_priv(ds);
+	struct ethtool_eee *p = &priv->port_sts[port].eee;
 	u32 id_mode_dis = 0, port_mode;
 	const char *str = NULL;
 	u32 reg;
@@ -1211,6 +1212,9 @@ force_link:
 		reg |= DUPLX_MODE;
 
 	core_writel(priv, reg, CORE_STS_OVERRIDE_GMIIP_PORT(port));
+
+	if (!phydev->is_pseudo_fixed_link)
+		p->eee_enabled = bcm_sf2_eee_init(ds, port, phydev);
 }
 
 static void bcm_sf2_sw_fixed_link_update(struct dsa_switch *ds, int port,
-- 
2.7.4


From 32345cf3a69f4f85267098df38828329dffb256a Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Sun, 27 Nov 2016 01:18:01 +0100
Subject: [PATCH 09/19] net, sched: respect rcu grace period on cls destruction

[ Upstream commit d936377414fadbafb4d17148d222fe45ca5442d4 ]

Roi reported a crash in flower where tp->root was NULL in ->classify()
callbacks. Reason is that in ->destroy() tp->root is set to NULL via
RCU_INIT_POINTER(). It's problematic for some of the classifiers, because
this doesn't respect RCU grace period for them, and as a result, still
outstanding readers from tc_classify() will try to blindly dereference
a NULL tp->root.

The tp->root object is strictly private to the classifier implementation
and holds internal data the core such as tc_ctl_tfilter() doesn't know
about. Within some classifiers, such as cls_bpf, cls_basic, etc, tp->root
is only checked for NULL in ->get() callback, but nowhere else. This is
misleading and seemed to be copied from old classifier code that was not
cleaned up properly. For example, d3fa76ee6b4a ("[NET_SCHED]: cls_basic:
fix NULL pointer dereference") moved tp->root initialization into ->init()
routine, where before it was part of ->change(), so ->get() had to deal
with tp->root being NULL back then, so that was indeed a valid case, after
d3fa76ee6b4a, not really anymore. We used to set tp->root to NULL long
ago in ->destroy(), see 47a1a1d4be29 ("pkt_sched: remove unnecessary xchg()
in packet classifiers"); but the NULLifying was reintroduced with the
RCUification, but it's not correct for every classifier implementation.

In the cases that are fixed here with one exception of cls_cgroup, tp->root
object is allocated and initialized inside ->init() callback, which is always
performed at a point in time after we allocate a new tp, which means tp and
thus tp->root was not globally visible in the tp chain yet (see tc_ctl_tfilter()).
Also, on destruction tp->root is strictly kfree_rcu()'ed in ->destroy()
handler, same for the tp which is kfree_rcu()'ed right when we return
from ->destroy() in tcf_destroy(). This means, the head object's lifetime
for such classifiers is always tied to the tp lifetime. The RCU callback
invocation for the two kfree_rcu() could be out of order, but that's fine
since both are independent.

Dropping the RCU_INIT_POINTER(tp->root, NULL) for these classifiers here
means that 1) we don't need a useless NULL check in fast-path and, 2) that
outstanding readers of that tp in tc_classify() can still execute under
respect with RCU grace period as it is actually expected.

Things that haven't been touched here: cls_fw and cls_route. They each
handle tp->root being NULL in ->classify() path for historic reasons, so
their ->destroy() implementation can stay as is. If someone actually
cares, they could get cleaned up at some point to avoid the test in fast
path. cls_u32 doesn't set tp->root to NULL. For cls_rsvp, I just added a
!head should anyone actually be using/testing it, so it at least aligns with
cls_fw and cls_route. For cls_flower we additionally need to defer rhashtable
destruction (to a sleepable context) after RCU grace period as concurrent
readers might still access it. (Note that in this case we need to hold module
reference to keep work callback address intact, since we only wait on module
unload for all call_rcu()s to finish.)

This fixes one race to bring RCU grace period guarantees back. Next step
as worked on by Cong however is to fix 1e052be69d04 ("net_sched: destroy
proto tp when all filters are gone") to get the order of unlinking the tp
in tc_ctl_tfilter() for the RTM_DELTFILTER case right by moving
RCU_INIT_POINTER() before tcf_destroy() and let the notification for
removal be done through the prior ->delete() callback. Both are independant
issues. Once we have that right, we can then clean tp->root up for a number
of classifiers by not making them RCU pointers, which requires a new callback
(->uninit) that is triggered from tp's RCU callback, where we just kfree()
tp->root from there.

Fixes: 1f947bf151e9 ("net: sched: rcu'ify cls_bpf")
Fixes: 9888faefe132 ("net: sched: cls_basic use RCU")
Fixes: 70da9f0bf999 ("net: sched: cls_flow use RCU")
Fixes: 77b9900ef53a ("tc: introduce Flower classifier")
Fixes: bf3994d2ed31 ("net/sched: introduce Match-all classifier")
Fixes: 952313bd6258 ("net: sched: cls_cgroup use RCU")
Reported-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: Roi Dayan <roid@mellanox.com>
Cc: Jiri Pirko <jiri@mellanox.com>
Acked-by: John Fastabend <john.r.fastabend@intel.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_basic.c   |  4 ----
 net/sched/cls_bpf.c     |  4 ----
 net/sched/cls_cgroup.c  |  7 +++----
 net/sched/cls_flow.c    |  1 -
 net/sched/cls_flower.c  | 31 ++++++++++++++++++++++++++-----
 net/sched/cls_rsvp.h    |  3 ++-
 net/sched/cls_tcindex.c |  1 -
 7 files changed, 31 insertions(+), 20 deletions(-)

diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c
index 0b8c3ac..1bf1f451 100644
--- a/net/sched/cls_basic.c
+++ b/net/sched/cls_basic.c
@@ -62,9 +62,6 @@ static unsigned long basic_get(struct tcf_proto *tp, u32 handle)
 	struct basic_head *head = rtnl_dereference(tp->root);
 	struct basic_filter *f;
 
-	if (head == NULL)
-		return 0UL;
-
 	list_for_each_entry(f, &head->flist, link) {
 		if (f->handle == handle) {
 			l = (unsigned long) f;
@@ -109,7 +106,6 @@ static bool basic_destroy(struct tcf_proto *tp, bool force)
 		tcf_unbind_filter(tp, &f->res);
 		call_rcu(&f->rcu, basic_delete_filter);
 	}
-	RCU_INIT_POINTER(tp->root, NULL);
 	kfree_rcu(head, rcu);
 	return true;
 }
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 5faaa54..3eef021 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -199,7 +199,6 @@ static bool cls_bpf_destroy(struct tcf_proto *tp, bool force)
 		call_rcu(&prog->rcu, __cls_bpf_delete_prog);
 	}
 
-	RCU_INIT_POINTER(tp->root, NULL);
 	kfree_rcu(head, rcu);
 	return true;
 }
@@ -210,9 +209,6 @@ static unsigned long cls_bpf_get(struct tcf_proto *tp, u32 handle)
 	struct cls_bpf_prog *prog;
 	unsigned long ret = 0UL;
 
-	if (head == NULL)
-		return 0UL;
-
 	list_for_each_entry(prog, &head->plist, link) {
 		if (prog->handle == handle) {
 			ret = (unsigned long) prog;
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index 4c85bd3..c104c20 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -130,11 +130,10 @@ static bool cls_cgroup_destroy(struct tcf_proto *tp, bool force)
 
 	if (!force)
 		return false;
-
-	if (head) {
-		RCU_INIT_POINTER(tp->root, NULL);
+	/* Head can still be NULL due to cls_cgroup_init(). */
+	if (head)
 		call_rcu(&head->rcu, cls_cgroup_destroy_rcu);
-	}
+
 	return true;
 }
 
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index fbfec6a..d7ba2b4 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -583,7 +583,6 @@ static bool flow_destroy(struct tcf_proto *tp, bool force)
 		list_del_rcu(&f->list);
 		call_rcu(&f->rcu, flow_destroy_filter);
 	}
-	RCU_INIT_POINTER(tp->root, NULL);
 	kfree_rcu(head, rcu);
 	return true;
 }
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 95b0212..e5a58c8 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -13,6 +13,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/rhashtable.h>
+#include <linux/workqueue.h>
 
 #include <linux/if_ether.h>
 #include <linux/in6.h>
@@ -55,7 +56,10 @@ struct cls_fl_head {
 	bool mask_assigned;
 	struct list_head filters;
 	struct rhashtable_params ht_params;
-	struct rcu_head rcu;
+	union {
+		struct work_struct work;
+		struct rcu_head	rcu;
+	};
 };
 
 struct cls_fl_filter {
@@ -165,6 +169,24 @@ static void fl_destroy_filter(struct rcu_head *head)
 	kfree(f);
 }
 
+static void fl_destroy_sleepable(struct work_struct *work)
+{
+	struct cls_fl_head *head = container_of(work, struct cls_fl_head,
+						work);
+	if (head->mask_assigned)
+		rhashtable_destroy(&head->ht);
+	kfree(head);
+	module_put(THIS_MODULE);
+}
+
+static void fl_destroy_rcu(struct rcu_head *rcu)
+{
+	struct cls_fl_head *head = container_of(rcu, struct cls_fl_head, rcu);
+
+	INIT_WORK(&head->work, fl_destroy_sleepable);
+	schedule_work(&head->work);
+}
+
 static bool fl_destroy(struct tcf_proto *tp, bool force)
 {
 	struct cls_fl_head *head = rtnl_dereference(tp->root);
@@ -177,10 +199,9 @@ static bool fl_destroy(struct tcf_proto *tp, bool force)
 		list_del_rcu(&f->list);
 		call_rcu(&f->rcu, fl_destroy_filter);
 	}
-	RCU_INIT_POINTER(tp->root, NULL);
-	if (head->mask_assigned)
-		rhashtable_destroy(&head->ht);
-	kfree_rcu(head, rcu);
+
+	__module_get(THIS_MODULE);
+	call_rcu(&head->rcu, fl_destroy_rcu);
 	return true;
 }
 
diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h
index f9c9fc0..9992dfa 100644
--- a/net/sched/cls_rsvp.h
+++ b/net/sched/cls_rsvp.h
@@ -152,7 +152,8 @@ static int rsvp_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 		return -1;
 	nhptr = ip_hdr(skb);
 #endif
-
+	if (unlikely(!head))
+		return -1;
 restart:
 
 #if RSVP_DST_LEN == 4
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 944c8ff..403746b 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -503,7 +503,6 @@ static bool tcindex_destroy(struct tcf_proto *tp, bool force)
 	walker.fn = tcindex_destroy_element;
 	tcindex_walk(tp, &walker);
 
-	RCU_INIT_POINTER(tp->root, NULL);
 	call_rcu(&p->rcu, __tcindex_destroy);
 	return true;
 }
-- 
2.7.4


From 050571b47be4ce76102d46c99d334131274f637e Mon Sep 17 00:00:00 2001
From: Amir Vadai <amir@vadai.me>
Date: Mon, 28 Nov 2016 12:56:40 +0200
Subject: [PATCH 10/19] net/sched: pedit: make sure that offset is valid

[ Upstream commit 95c2027bfeda21a28eb245121e6a249f38d0788e ]

Add a validation function to make sure offset is valid:
1. Not below skb head (could happen when offset is negative).
2. Validate both 'offset' and 'at'.

Signed-off-by: Amir Vadai <amir@vadai.me>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_pedit.c | 24 ++++++++++++++++++++----
 1 file changed, 20 insertions(+), 4 deletions(-)

diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index e38a770..c3434e9 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -104,6 +104,17 @@ static void tcf_pedit_cleanup(struct tc_action *a, int bind)
 	kfree(keys);
 }
 
+static bool offset_valid(struct sk_buff *skb, int offset)
+{
+	if (offset > 0 && offset > skb->len)
+		return false;
+
+	if  (offset < 0 && -offset > skb_headroom(skb))
+		return false;
+
+	return true;
+}
+
 static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a,
 		     struct tcf_result *res)
 {
@@ -130,6 +141,11 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a,
 			if (tkey->offmask) {
 				char *d, _d;
 
+				if (!offset_valid(skb, off + tkey->at)) {
+					pr_info("tc filter pedit 'at' offset %d out of bounds\n",
+						off + tkey->at);
+					goto bad;
+				}
 				d = skb_header_pointer(skb, off + tkey->at, 1,
 						       &_d);
 				if (!d)
@@ -142,10 +158,10 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a,
 					" offset must be on 32 bit boundaries\n");
 				goto bad;
 			}
-			if (offset > 0 && offset > skb->len) {
-				pr_info("tc filter pedit"
-					" offset %d can't exceed pkt length %d\n",
-				       offset, skb->len);
+
+			if (!offset_valid(skb, off + offset)) {
+				pr_info("tc filter pedit offset %d out of bounds\n",
+					offset);
 				goto bad;
 			}
 
-- 
2.7.4


From c7118b7a32707251d687f36d4bfdac8dae77ec84 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Mon, 28 Nov 2016 19:22:12 +0800
Subject: [PATCH 11/19] netlink: Call cb->done from a worker thread

[ Upstream commit 707693c8a498697aa8db240b93eb76ec62e30892 ]

The cb->done interface expects to be called in process context.
This was broken by the netlink RCU conversion.  This patch fixes
it by adding a worker struct to make the cb->done call where
necessary.

Fixes: 21e4902aea80 ("netlink: Lockless lookup with RCU grace...")
Reported-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 27 +++++++++++++++++++++++----
 net/netlink/af_netlink.h |  2 ++
 2 files changed, 25 insertions(+), 4 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 28fc283..bbf7d2e 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -924,14 +924,11 @@ static void netlink_skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
 	sk_mem_charge(sk, skb->truesize);
 }
 
-static void netlink_sock_destruct(struct sock *sk)
+static void __netlink_sock_destruct(struct sock *sk)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
 
 	if (nlk->cb_running) {
-		if (nlk->cb.done)
-			nlk->cb.done(&nlk->cb);
-
 		module_put(nlk->cb.module);
 		kfree_skb(nlk->cb.skb);
 	}
@@ -960,6 +957,28 @@ static void netlink_sock_destruct(struct sock *sk)
 	WARN_ON(nlk_sk(sk)->groups);
 }
 
+static void netlink_sock_destruct_work(struct work_struct *work)
+{
+	struct netlink_sock *nlk = container_of(work, struct netlink_sock,
+						work);
+
+	nlk->cb.done(&nlk->cb);
+	__netlink_sock_destruct(&nlk->sk);
+}
+
+static void netlink_sock_destruct(struct sock *sk)
+{
+	struct netlink_sock *nlk = nlk_sk(sk);
+
+	if (nlk->cb_running && nlk->cb.done) {
+		INIT_WORK(&nlk->work, netlink_sock_destruct_work);
+		schedule_work(&nlk->work);
+		return;
+	}
+
+	__netlink_sock_destruct(sk);
+}
+
 /* This lock without WQ_FLAG_EXCLUSIVE is good on UP and it is _very_ bad on
  * SMP. Look, when several writers sleep and reader wakes them up, all but one
  * immediately hit write lock and grab all the cpus. Exclusive sleep solves
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index 14437d9..df32cb9 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -3,6 +3,7 @@
 
 #include <linux/rhashtable.h>
 #include <linux/atomic.h>
+#include <linux/workqueue.h>
 #include <net/sock.h>
 
 #define NLGRPSZ(x)	(ALIGN(x, sizeof(unsigned long) * 8) / 8)
@@ -53,6 +54,7 @@ struct netlink_sock {
 
 	struct rhash_head	node;
 	struct rcu_head		rcu;
+	struct work_struct	work;
 };
 
 static inline struct netlink_sock *nlk_sk(struct sock *sk)
-- 
2.7.4


From a11bc71f66cfd9068c0de4e5f347430c0a5ea93a Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Mon, 5 Dec 2016 15:28:21 +0800
Subject: [PATCH 12/19] netlink: Do not schedule work from sk_destruct

[ Upstream commit ed5d7788a934a4b6d6d025e948ed4da496b4f12e ]

It is wrong to schedule a work from sk_destruct using the socket
as the memory reserve because the socket will be freed immediately
after the return from sk_destruct.

Instead we should do the deferral prior to sk_free.

This patch does just that.

Fixes: 707693c8a498 ("netlink: Call cb->done from a worker thread")
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 32 +++++++++++++++-----------------
 1 file changed, 15 insertions(+), 17 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index bbf7d2e..360700a 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -924,11 +924,13 @@ static void netlink_skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
 	sk_mem_charge(sk, skb->truesize);
 }
 
-static void __netlink_sock_destruct(struct sock *sk)
+static void netlink_sock_destruct(struct sock *sk)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
 
 	if (nlk->cb_running) {
+		if (nlk->cb.done)
+			nlk->cb.done(&nlk->cb);
 		module_put(nlk->cb.module);
 		kfree_skb(nlk->cb.skb);
 	}
@@ -962,21 +964,7 @@ static void netlink_sock_destruct_work(struct work_struct *work)
 	struct netlink_sock *nlk = container_of(work, struct netlink_sock,
 						work);
 
-	nlk->cb.done(&nlk->cb);
-	__netlink_sock_destruct(&nlk->sk);
-}
-
-static void netlink_sock_destruct(struct sock *sk)
-{
-	struct netlink_sock *nlk = nlk_sk(sk);
-
-	if (nlk->cb_running && nlk->cb.done) {
-		INIT_WORK(&nlk->work, netlink_sock_destruct_work);
-		schedule_work(&nlk->work);
-		return;
-	}
-
-	__netlink_sock_destruct(sk);
+	sk_free(&nlk->sk);
 }
 
 /* This lock without WQ_FLAG_EXCLUSIVE is good on UP and it is _very_ bad on
@@ -1284,8 +1272,18 @@ out_module:
 static void deferred_put_nlk_sk(struct rcu_head *head)
 {
 	struct netlink_sock *nlk = container_of(head, struct netlink_sock, rcu);
+	struct sock *sk = &nlk->sk;
+
+	if (!atomic_dec_and_test(&sk->sk_refcnt))
+		return;
+
+	if (nlk->cb_running && nlk->cb.done) {
+		INIT_WORK(&nlk->work, netlink_sock_destruct_work);
+		schedule_work(&nlk->work);
+		return;
+	}
 
-	sock_put(&nlk->sk);
+	sk_free(sk);
 }
 
 static int netlink_release(struct socket *sock)
-- 
2.7.4


From 202a173ea34d6bf477ecf558b6b785b3020dbd0b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 28 Nov 2016 06:26:49 -0800
Subject: [PATCH 13/19] net/dccp: fix use-after-free in dccp_invalid_packet

[ Upstream commit 648f0c28df282636c0c8a7a19ca3ce5fc80a39c3 ]

pskb_may_pull() can reallocate skb->head, we need to reload dh pointer
in dccp_invalid_packet() or risk use after free.

Bug found by Andrey Konovalov using syzkaller.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ipv4.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 861e1fa..0759f5b 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -698,6 +698,7 @@ int dccp_invalid_packet(struct sk_buff *skb)
 {
 	const struct dccp_hdr *dh;
 	unsigned int cscov;
+	u8 dccph_doff;
 
 	if (skb->pkt_type != PACKET_HOST)
 		return 1;
@@ -719,18 +720,19 @@ int dccp_invalid_packet(struct sk_buff *skb)
 	/*
 	 * If P.Data Offset is too small for packet type, drop packet and return
 	 */
-	if (dh->dccph_doff < dccp_hdr_len(skb) / sizeof(u32)) {
-		DCCP_WARN("P.Data Offset(%u) too small\n", dh->dccph_doff);
+	dccph_doff = dh->dccph_doff;
+	if (dccph_doff < dccp_hdr_len(skb) / sizeof(u32)) {
+		DCCP_WARN("P.Data Offset(%u) too small\n", dccph_doff);
 		return 1;
 	}
 	/*
 	 * If P.Data Offset is too too large for packet, drop packet and return
 	 */
-	if (!pskb_may_pull(skb, dh->dccph_doff * sizeof(u32))) {
-		DCCP_WARN("P.Data Offset(%u) too large\n", dh->dccph_doff);
+	if (!pskb_may_pull(skb, dccph_doff * sizeof(u32))) {
+		DCCP_WARN("P.Data Offset(%u) too large\n", dccph_doff);
 		return 1;
 	}
-
+	dh = dccp_hdr(skb);
 	/*
 	 * If P.type is not Data, Ack, or DataAck and P.X == 0 (the packet
 	 * has short sequence numbers), drop packet and return
-- 
2.7.4


From d7763d9f1df67b032a801abd26ec20a802a96566 Mon Sep 17 00:00:00 2001
From: Philip Pettersson <philip.pettersson@gmail.com>
Date: Wed, 30 Nov 2016 14:55:36 -0800
Subject: [PATCH 14/19] packet: fix race condition in packet_set_ring

[ Upstream commit 84ac7260236a49c79eede91617700174c2c19b0c ]

When packet_set_ring creates a ring buffer it will initialize a
struct timer_list if the packet version is TPACKET_V3. This value
can then be raced by a different thread calling setsockopt to
set the version to TPACKET_V1 before packet_set_ring has finished.

This leads to a use-after-free on a function pointer in the
struct timer_list when the socket is closed as the previously
initialized timer will not be deleted.

The bug is fixed by taking lock_sock(sk) in packet_setsockopt when
changing the packet version while also taking the lock at the start
of packet_set_ring.

Fixes: f6fb8f100b80 ("af-packet: TPACKET_V3 flexible buffer implementation.")
Signed-off-by: Philip Pettersson <philip.pettersson@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 34e4fcf..f223d1c 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3572,19 +3572,25 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 
 		if (optlen != sizeof(val))
 			return -EINVAL;
-		if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
-			return -EBUSY;
 		if (copy_from_user(&val, optval, sizeof(val)))
 			return -EFAULT;
 		switch (val) {
 		case TPACKET_V1:
 		case TPACKET_V2:
 		case TPACKET_V3:
-			po->tp_version = val;
-			return 0;
+			break;
 		default:
 			return -EINVAL;
 		}
+		lock_sock(sk);
+		if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+			ret = -EBUSY;
+		} else {
+			po->tp_version = val;
+			ret = 0;
+		}
+		release_sock(sk);
+		return ret;
 	}
 	case PACKET_RESERVE:
 	{
@@ -4067,6 +4073,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 	/* Added to avoid minimal code churn */
 	struct tpacket_req *req = &req_u->req;
 
+	lock_sock(sk);
 	/* Opening a Tx-ring is NOT supported in TPACKET_V3 */
 	if (!closing && tx_ring && (po->tp_version > TPACKET_V2)) {
 		WARN(1, "Tx-ring is not supported.\n");
@@ -4148,7 +4155,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 			goto out;
 	}
 
-	lock_sock(sk);
 
 	/* Detach socket from network */
 	spin_lock(&po->bind_lock);
@@ -4197,11 +4203,11 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 		if (!tx_ring)
 			prb_shutdown_retire_blk_timer(po, rb_queue);
 	}
-	release_sock(sk);
 
 	if (pg_vec)
 		free_pg_vec(pg_vec, order, req->tp_block_nr);
 out:
+	release_sock(sk);
 	return err;
 }
 
-- 
2.7.4


From 4e46d72f640bd4589d69f1da3d44259157559fe1 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 1 Dec 2016 09:45:45 -0800
Subject: [PATCH 15/19] net: bcmgenet: Utilize correct struct device for all
 DMA operations

[ Upstream commit 8c4799ac799665065f9bf1364fd71bf4f7dc6a4a ]

__bcmgenet_tx_reclaim() and bcmgenet_free_rx_buffers() are not using the
same struct device during unmap that was used for the map operation,
which makes DMA-API debugging warn about it. Fix this by always using
&priv->pdev->dev throughout the driver, using an identical device
reference for all map/unmap calls.

Fixes: 1c1008c793fa ("net: bcmgenet: add main driver file")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 0fb3f8d..9162756 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -1168,6 +1168,7 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
 					  struct bcmgenet_tx_ring *ring)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
+	struct device *kdev = &priv->pdev->dev;
 	struct enet_cb *tx_cb_ptr;
 	struct netdev_queue *txq;
 	unsigned int pkts_compl = 0;
@@ -1195,7 +1196,7 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
 			pkts_compl++;
 			dev->stats.tx_packets++;
 			dev->stats.tx_bytes += tx_cb_ptr->skb->len;
-			dma_unmap_single(&dev->dev,
+			dma_unmap_single(kdev,
 					 dma_unmap_addr(tx_cb_ptr, dma_addr),
 					 dma_unmap_len(tx_cb_ptr, dma_len),
 					 DMA_TO_DEVICE);
@@ -1203,7 +1204,7 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
 		} else if (dma_unmap_addr(tx_cb_ptr, dma_addr)) {
 			dev->stats.tx_bytes +=
 				dma_unmap_len(tx_cb_ptr, dma_len);
-			dma_unmap_page(&dev->dev,
+			dma_unmap_page(kdev,
 				       dma_unmap_addr(tx_cb_ptr, dma_addr),
 				       dma_unmap_len(tx_cb_ptr, dma_len),
 				       DMA_TO_DEVICE);
@@ -1754,6 +1755,7 @@ static int bcmgenet_alloc_rx_buffers(struct bcmgenet_priv *priv,
 
 static void bcmgenet_free_rx_buffers(struct bcmgenet_priv *priv)
 {
+	struct device *kdev = &priv->pdev->dev;
 	struct enet_cb *cb;
 	int i;
 
@@ -1761,7 +1763,7 @@ static void bcmgenet_free_rx_buffers(struct bcmgenet_priv *priv)
 		cb = &priv->rx_cbs[i];
 
 		if (dma_unmap_addr(cb, dma_addr)) {
-			dma_unmap_single(&priv->dev->dev,
+			dma_unmap_single(kdev,
 					 dma_unmap_addr(cb, dma_addr),
 					 priv->rx_buf_len, DMA_FROM_DEVICE);
 			dma_unmap_addr_set(cb, dma_addr, 0);
-- 
2.7.4


From 4d21d6e9b11ae1ac9b17633c1ce562cd9428258d Mon Sep 17 00:00:00 2001
From: Chris Brandt <chris.brandt@renesas.com>
Date: Thu, 1 Dec 2016 13:32:14 -0500
Subject: [PATCH 16/19] sh_eth: remove unchecked interrupts for RZ/A1

[ Upstream commit 33d446dbba4d4d6a77e1e900d434fa99e0f02c86 ]

When streaming a lot of data and the RZ/A1 can't keep up, some status bits
will get set that are not being checked or cleared which cause the
following messages and the Ethernet driver to stop working. This
patch fixes that issue.

irq 21: nobody cared (try booting with the "irqpoll" option)
handlers:
[<c036b71c>] sh_eth_interrupt
Disabling IRQ #21

Fixes: db893473d313a4ad ("sh_eth: Add support for r7s72100")
Signed-off-by: Chris Brandt <chris.brandt@renesas.com>
Acked-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/sh_eth.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 36fc942..480f3da 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -832,7 +832,7 @@ static struct sh_eth_cpu_data r7s72100_data = {
 
 	.ecsr_value	= ECSR_ICD,
 	.ecsipr_value	= ECSIPR_ICDIP,
-	.eesipr_value	= 0xff7f009f,
+	.eesipr_value	= 0xe77f009f,
 
 	.tx_check	= EESR_TC1 | EESR_FTC,
 	.eesr_err_check	= EESR_TWB1 | EESR_TWB | EESR_TABT | EESR_RABT |
-- 
2.7.4


From 6c7f335025d4016a7018989537e571ca30deed88 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 2 Dec 2016 16:49:29 +0100
Subject: [PATCH 17/19] geneve: avoid use-after-free of skb->data

[ Upstream commit 5b01014759991887b1e450c9def01e58c02ab81b ]

geneve{,6}_build_skb can end up doing a pskb_expand_head(), which
makes the ip_hdr(skb) reference we stashed earlier stale. Since it's
only needed as an argument to ip_tunnel_ecn_encap(), move this
directly in the function call.

Fixes: 08399efc6319 ("geneve: ensure ECN info is handled properly in all tx/rx paths")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: John W. Linville <linville@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c | 14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 4827c69..f0961cb 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -815,7 +815,6 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	struct geneve_dev *geneve = netdev_priv(dev);
 	struct geneve_sock *gs4 = geneve->sock4;
 	struct rtable *rt = NULL;
-	const struct iphdr *iip; /* interior IP header */
 	int err = -EINVAL;
 	struct flowi4 fl4;
 	__u8 tos, ttl;
@@ -842,8 +841,6 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
 	skb_reset_mac_header(skb);
 
-	iip = ip_hdr(skb);
-
 	if (info) {
 		const struct ip_tunnel_key *key = &info->key;
 		u8 *opts = NULL;
@@ -859,7 +856,7 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 		if (unlikely(err))
 			goto err;
 
-		tos = ip_tunnel_ecn_encap(key->tos, iip, skb);
+		tos = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb);
 		ttl = key->ttl;
 		df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0;
 	} else {
@@ -869,7 +866,7 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 		if (unlikely(err))
 			goto err;
 
-		tos = ip_tunnel_ecn_encap(fl4.flowi4_tos, iip, skb);
+		tos = ip_tunnel_ecn_encap(fl4.flowi4_tos, ip_hdr(skb), skb);
 		ttl = geneve->ttl;
 		if (!ttl && IN_MULTICAST(ntohl(fl4.daddr)))
 			ttl = 1;
@@ -903,7 +900,6 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	struct geneve_dev *geneve = netdev_priv(dev);
 	struct geneve_sock *gs6 = geneve->sock6;
 	struct dst_entry *dst = NULL;
-	const struct iphdr *iip; /* interior IP header */
 	int err = -EINVAL;
 	struct flowi6 fl6;
 	__u8 prio, ttl;
@@ -927,8 +923,6 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
 	skb_reset_mac_header(skb);
 
-	iip = ip_hdr(skb);
-
 	if (info) {
 		const struct ip_tunnel_key *key = &info->key;
 		u8 *opts = NULL;
@@ -945,7 +939,7 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 		if (unlikely(err))
 			goto err;
 
-		prio = ip_tunnel_ecn_encap(key->tos, iip, skb);
+		prio = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb);
 		ttl = key->ttl;
 	} else {
 		udp_csum = false;
@@ -954,7 +948,7 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 		if (unlikely(err))
 			goto err;
 
-		prio = ip_tunnel_ecn_encap(fl6.flowi6_tos, iip, skb);
+		prio = ip_tunnel_ecn_encap(fl6.flowi6_tos, ip_hdr(skb), skb);
 		ttl = geneve->ttl;
 		if (!ttl && ipv6_addr_is_multicast(&fl6.daddr))
 			ttl = 1;
-- 
2.7.4


From d36fbda441e02905c95df19af8b82303181623c5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 2 Dec 2016 09:44:53 -0800
Subject: [PATCH 18/19] net: avoid signed overflows for SO_{SND|RCV}BUFFORCE

[ Upstream commit b98b0bc8c431e3ceb4b26b0dfc8db509518fb290 ]

CAP_NET_ADMIN users should not be allowed to set negative
sk_sndbuf or sk_rcvbuf values, as it can lead to various memory
corruptions, crashes, OOM...

Note that before commit 82981930125a ("net: cleanups in
sock_setsockopt()"), the bug was even more serious, since SO_SNDBUF
and SO_RCVBUF were vulnerable.

This needs to be backported to all known linux kernels.

Again, many thanks to syzkaller team for discovering this gem.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index 88f01785..f4c0917 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -745,7 +745,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
 		val = min_t(u32, val, sysctl_wmem_max);
 set_sndbuf:
 		sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
-		sk->sk_sndbuf = max_t(u32, val * 2, SOCK_MIN_SNDBUF);
+		sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF);
 		/* Wake up sending tasks if we upped the value. */
 		sk->sk_write_space(sk);
 		break;
@@ -781,7 +781,7 @@ set_rcvbuf:
 		 * returning the value we actually used in getsockopt
 		 * is the most desirable behavior.
 		 */
-		sk->sk_rcvbuf = max_t(u32, val * 2, SOCK_MIN_RCVBUF);
+		sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF);
 		break;
 
 	case SO_RCVBUFFORCE:
-- 
2.7.4


From 93c9e0d11871b686a2447391a7ff957ce7c11cc2 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Mon, 5 Dec 2016 10:34:38 -0800
Subject: [PATCH 19/19] net: ping: check minimum size on ICMP header length

[ Upstream commit 0eab121ef8750a5c8637d51534d5e9143fb0633f ]

Prior to commit c0371da6047a ("put iov_iter into msghdr") in v3.19, there
was no check that the iovec contained enough bytes for an ICMP header,
and the read loop would walk across neighboring stack contents. Since the
iov_iter conversion, bad arguments are noticed, but the returned error is
EFAULT. Returning EINVAL is a clearer error and also solves the problem
prior to v3.19.

This was found using trinity with KASAN on v3.18:

BUG: KASAN: stack-out-of-bounds in memcpy_fromiovec+0x60/0x114 at addr ffffffc071077da0
Read of size 8 by task trinity-c2/9623
page:ffffffbe034b9a08 count:0 mapcount:0 mapping:          (null) index:0x0
flags: 0x0()
page dumped because: kasan: bad access detected
CPU: 0 PID: 9623 Comm: trinity-c2 Tainted: G    BU         3.18.0-dirty #15
Hardware name: Google Tegra210 Smaug Rev 1,3+ (DT)
Call trace:
[<ffffffc000209c98>] dump_backtrace+0x0/0x1ac arch/arm64/kernel/traps.c:90
[<ffffffc000209e54>] show_stack+0x10/0x1c arch/arm64/kernel/traps.c:171
[<     inline     >] __dump_stack lib/dump_stack.c:15
[<ffffffc000f18dc4>] dump_stack+0x7c/0xd0 lib/dump_stack.c:50
[<     inline     >] print_address_description mm/kasan/report.c:147
[<     inline     >] kasan_report_error mm/kasan/report.c:236
[<ffffffc000373dcc>] kasan_report+0x380/0x4b8 mm/kasan/report.c:259
[<     inline     >] check_memory_region mm/kasan/kasan.c:264
[<ffffffc00037352c>] __asan_load8+0x20/0x70 mm/kasan/kasan.c:507
[<ffffffc0005b9624>] memcpy_fromiovec+0x5c/0x114 lib/iovec.c:15
[<     inline     >] memcpy_from_msg include/linux/skbuff.h:2667
[<ffffffc000ddeba0>] ping_common_sendmsg+0x50/0x108 net/ipv4/ping.c:674
[<ffffffc000dded30>] ping_v4_sendmsg+0xd8/0x698 net/ipv4/ping.c:714
[<ffffffc000dc91dc>] inet_sendmsg+0xe0/0x12c net/ipv4/af_inet.c:749
[<     inline     >] __sock_sendmsg_nosec net/socket.c:624
[<     inline     >] __sock_sendmsg net/socket.c:632
[<ffffffc000cab61c>] sock_sendmsg+0x124/0x164 net/socket.c:643
[<     inline     >] SYSC_sendto net/socket.c:1797
[<ffffffc000cad270>] SyS_sendto+0x178/0x1d8 net/socket.c:1761

CVE-2016-8399

Reported-by: Qidan He <i@flanker017.me>
Fixes: c319b4d76b9e ("net: ipv4: add IPPROTO_ICMP socket kind")
Cc: stable@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ping.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index aa67e0e..23160d2 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -660,6 +660,10 @@ int ping_common_sendmsg(int family, struct msghdr *msg, size_t len,
 	if (len > 0xFFFF)
 		return -EMSGSIZE;
 
+	/* Must have at least a full ICMP header. */
+	if (len < icmph_len)
+		return -EINVAL;
+
 	/*
 	 *	Check the flags.
 	 */
-- 
2.7.4


[-- Attachment #3: net_48.mbox --]
[-- Type: Application/Octet-Stream, Size: 104368 bytes --]

From 034a3fad7fb4420f8ced432f0e20438bd738381b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 14 Nov 2016 16:28:42 -0800
Subject: [PATCH 01/34] gro_cells: mark napi struct as not busy poll candidates

[ Upstream commit e88a2766143a27bfe6704b4493b214de4094cf29 ]

Rolf Neugebauer reported very long delays at netns dismantle.

Eric W. Biederman was kind enough to look at this problem
and noticed synchronize_net() occurring from netif_napi_del() that was
added in linux-4.5

Busy polling makes no sense for tunnels NAPI.
If busy poll is used for sessions over tunnels, the poller will need to
poll the physical device queue anyway.

netif_tx_napi_add() could be used here, but function name is misleading,
and renaming it is not stable material, so set NAPI_STATE_NO_BUSY_POLL
bit directly.

This will avoid inserting gro_cells napi structures in napi_hash[]
and avoid the problematic synchronize_net() (per possible cpu) that
Rolf reported.

Fixes: 93d05d4a320c ("net: provide generic busy polling to all NAPI drivers")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Rolf Neugebauer <rolf.neugebauer@docker.com>
Reported-by: Eric W. Biederman <ebiederm@xmission.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Tested-by: Rolf Neugebauer <rolf.neugebauer@docker.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/gro_cells.h | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/include/net/gro_cells.h b/include/net/gro_cells.h
index d15214d..2a1abbf 100644
--- a/include/net/gro_cells.h
+++ b/include/net/gro_cells.h
@@ -68,6 +68,9 @@ static inline int gro_cells_init(struct gro_cells *gcells, struct net_device *de
 		struct gro_cell *cell = per_cpu_ptr(gcells->cells, i);
 
 		__skb_queue_head_init(&cell->napi_skbs);
+
+		set_bit(NAPI_STATE_NO_BUSY_POLL, &cell->napi.state);
+
 		netif_napi_add(dev, &cell->napi, gro_cell_poll, 64);
 		napi_enable(&cell->napi);
 	}
-- 
2.7.4


From 0d7a2f4451231a18ac85b9550df595e4e45f9bc8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 15 Nov 2016 22:24:12 -0800
Subject: [PATCH 02/34] virtio-net: add a missing synchronize_net()

[ Upstream commit 963abe5c8a0273a1cf5913556da1b1189de0e57a ]

It seems many drivers do not respect napi_hash_del() contract.

When napi_hash_del() is used before netif_napi_del(), an RCU grace
period is needed before freeing NAPI object.

Fixes: 91815639d880 ("virtio-net: rx busy polling support")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index bf3fd34..d807209 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1468,6 +1468,11 @@ static void virtnet_free_queues(struct virtnet_info *vi)
 		netif_napi_del(&vi->rq[i].napi);
 	}
 
+	/* We called napi_hash_del() before netif_napi_del(),
+	 * we need to respect an RCU grace period before freeing vi->rq
+	 */
+	synchronize_net();
+
 	kfree(vi->rq);
 	kfree(vi->sq);
 }
-- 
2.7.4


From 755b47dbb83cd279ec907cb96a5cd980cf330f09 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 15 Nov 2016 15:58:15 -0800
Subject: [PATCH 03/34] net: dsa: b53: Fix VLAN usage and how we treat CPU port

[ Upstream commit e47112d9d6009bf6b7438cedc0270316d6b0370d ]

We currently have a fundamental problem in how we treat the CPU port and
its VLAN membership. As soon as a second VLAN is configured to be
untagged, the CPU automatically becomes untagged for that VLAN as well,
and yet, we don't gracefully make sure that the CPU becomes tagged in
the other VLANs it could be a member of. This results in only one VLAN
being effectively usable from the CPU's perspective.

Instead of having some pretty complex logic which tries to maintain the
CPU port's default VLAN and its untagged properties, just do something
very simple which consists in neither altering the CPU port's PVID
settings, nor its untagged settings:

- whenever a VLAN is added, the CPU is automatically a member of this
  VLAN group, as a tagged member
- PVID settings for downstream ports do not alter the CPU port's PVID
  since it now is part of all VLANs in the system

This means that a typical example where e.g: LAN ports are in VLAN1, and
WAN port is in VLAN2, now require having two VLAN interfaces for the
host to properly terminate and send traffic from/to.

Fixes: Fixes: a2482d2ce349 ("net: dsa: b53: Plug in VLAN support")
Reported-by: Hartmut Knaack <knaack.h@gmx.de>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/b53/b53_common.c | 16 ++++------------
 1 file changed, 4 insertions(+), 12 deletions(-)

diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index bda37d3..b081929 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -904,9 +904,10 @@ static void b53_vlan_add(struct dsa_switch *ds, int port,
 
 		vl->members |= BIT(port) | BIT(cpu_port);
 		if (untagged)
-			vl->untag |= BIT(port) | BIT(cpu_port);
+			vl->untag |= BIT(port);
 		else
-			vl->untag &= ~(BIT(port) | BIT(cpu_port));
+			vl->untag &= ~BIT(port);
+		vl->untag &= ~BIT(cpu_port);
 
 		b53_set_vlan_entry(dev, vid, vl);
 		b53_fast_age_vlan(dev, vid);
@@ -915,8 +916,6 @@ static void b53_vlan_add(struct dsa_switch *ds, int port,
 	if (pvid) {
 		b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port),
 			    vlan->vid_end);
-		b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(cpu_port),
-			    vlan->vid_end);
 		b53_fast_age_vlan(dev, vid);
 	}
 }
@@ -926,7 +925,6 @@ static int b53_vlan_del(struct dsa_switch *ds, int port,
 {
 	struct b53_device *dev = ds_to_priv(ds);
 	bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
-	unsigned int cpu_port = dev->cpu_port;
 	struct b53_vlan *vl;
 	u16 vid;
 	u16 pvid;
@@ -939,8 +937,6 @@ static int b53_vlan_del(struct dsa_switch *ds, int port,
 		b53_get_vlan_entry(dev, vid, vl);
 
 		vl->members &= ~BIT(port);
-		if ((vl->members & BIT(cpu_port)) == BIT(cpu_port))
-			vl->members = 0;
 
 		if (pvid == vid) {
 			if (is5325(dev) || is5365(dev))
@@ -949,18 +945,14 @@ static int b53_vlan_del(struct dsa_switch *ds, int port,
 				pvid = 0;
 		}
 
-		if (untagged) {
+		if (untagged)
 			vl->untag &= ~(BIT(port));
-			if ((vl->untag & BIT(cpu_port)) == BIT(cpu_port))
-				vl->untag = 0;
-		}
 
 		b53_set_vlan_entry(dev, vid, vl);
 		b53_fast_age_vlan(dev, vid);
 	}
 
 	b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port), pvid);
-	b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(cpu_port), pvid);
 	b53_fast_age_vlan(dev, pvid);
 
 	return 0;
-- 
2.7.4


From 7fde9632567b123f535bd00ff40ac30af277cdb2 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Wed, 16 Nov 2016 10:27:02 -0800
Subject: [PATCH 04/34] net: check dead netns for peernet2id_alloc()

[ Upstream commit cfc44a4d147ea605d66ccb917cc24467d15ff867 ]

Andrei reports we still allocate netns ID from idr after we destroy
it in cleanup_net().

cleanup_net():
  ...
  idr_destroy(&net->netns_ids);
  ...
  list_for_each_entry_reverse(ops, &pernet_list, list)
    ops_exit_list(ops, &net_exit_list);
      -> rollback_registered_many()
        -> rtmsg_ifinfo_build_skb()
         -> rtnl_fill_ifinfo()
           -> peernet2id_alloc()

After that point we should not even access net->netns_ids, we
should check the death of the current netns as early as we can in
peernet2id_alloc().

For net-next we can consider to avoid sending rtmsg totally,
it is a good optimization for netns teardown path.

Fixes: 0c7aecd4bde4 ("netns: add rtnl cmd to add and get peer netns ids")
Reported-by: Andrei Vagin <avagin@gmail.com>
Cc: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Andrei Vagin <avagin@openvz.org>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/net_namespace.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 2c2eb1b..2e9a1c2 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -217,6 +217,8 @@ int peernet2id_alloc(struct net *net, struct net *peer)
 	bool alloc;
 	int id;
 
+	if (atomic_read(&net->count) == 0)
+		return NETNSA_NSID_NOT_ASSIGNED;
 	spin_lock_irqsave(&net->nsid_lock, flags);
 	alloc = atomic_read(&peer->count) == 0 ? false : true;
 	id = __peernet2id_alloc(net, peer, &alloc);
-- 
2.7.4


From c251ecf4ec7e0576d40a42f8d8ca61ecf8c8ed2e Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 16 Nov 2016 16:26:46 +0100
Subject: [PATCH 05/34] ip6_tunnel: disable caching when the traffic class is
 inherited

[ Upstream commit b5c2d49544e5930c96e2632a7eece3f4325a1888 ]

If an ip6 tunnel is configured to inherit the traffic class from
the inner header, the dst_cache must be disabled or it will foul
the policy routing.

The issue is apprently there since at leat Linux-2.6.12-rc2.

Reported-by: Liam McBirnie <liam.mcbirnie@boeing.com>
Cc: Liam McBirnie <liam.mcbirnie@boeing.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 41489f3..9888976 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1014,6 +1014,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 	int mtu;
 	unsigned int psh_hlen = sizeof(struct ipv6hdr) + t->encap_hlen;
 	unsigned int max_headroom = psh_hlen;
+	bool use_cache = false;
 	int err = -1;
 
 	/* NBMA tunnel */
@@ -1038,7 +1039,15 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 
 		memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr));
 		neigh_release(neigh);
-	} else if (!fl6->flowi6_mark)
+	} else if (!(t->parms.flags &
+		     (IP6_TNL_F_USE_ORIG_TCLASS | IP6_TNL_F_USE_ORIG_FWMARK))) {
+		/* enable the cache only only if the routing decision does
+		 * not depend on the current inner header value
+		 */
+		use_cache = true;
+	}
+
+	if (use_cache)
 		dst = dst_cache_get(&t->dst_cache);
 
 	if (!ip6_tnl_xmit_ctl(t, &fl6->saddr, &fl6->daddr))
@@ -1113,7 +1122,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 		skb = new_skb;
 	}
 
-	if (!fl6->flowi6_mark && ndst)
+	if (use_cache && ndst)
 		dst_cache_set_ip6(&t->dst_cache, ndst, &fl6->saddr);
 	skb_dst_set(skb, dst);
 
-- 
2.7.4


From fe4b1578bc28fc94be5ec9d3c535a77a29559059 Mon Sep 17 00:00:00 2001
From: Jeremy Linton <jeremy.linton@arm.com>
Date: Thu, 17 Nov 2016 09:14:25 -0600
Subject: [PATCH 06/34] net: sky2: Fix shutdown crash

[ Upstream commit 06ba3b2133dc203e1e9bc36cee7f0839b79a9e8b ]

The sky2 frequently crashes during machine shutdown with:

sky2_get_stats+0x60/0x3d8 [sky2]
dev_get_stats+0x68/0xd8
rtnl_fill_stats+0x54/0x140
rtnl_fill_ifinfo+0x46c/0xc68
rtmsg_ifinfo_build_skb+0x7c/0xf0
rtmsg_ifinfo.part.22+0x3c/0x70
rtmsg_ifinfo+0x50/0x5c
netdev_state_change+0x4c/0x58
linkwatch_do_dev+0x50/0x88
__linkwatch_run_queue+0x104/0x1a4
linkwatch_event+0x30/0x3c
process_one_work+0x140/0x3e0
worker_thread+0x60/0x44c
kthread+0xdc/0xf0
ret_from_fork+0x10/0x50

This is caused by the sky2 being called after it has been shutdown.
A previous thread about this can be found here:

https://lkml.org/lkml/2016/4/12/410

An alternative fix is to assure that IFF_UP gets cleared by
calling dev_close() during shutdown. This is similar to what the
bnx2/tg3/xgene and maybe others are doing to assure that the driver
isn't being called following _shutdown().

Signed-off-by: Jeremy Linton <jeremy.linton@arm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/sky2.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index 467138b..d747e17 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -5220,6 +5220,19 @@ static SIMPLE_DEV_PM_OPS(sky2_pm_ops, sky2_suspend, sky2_resume);
 
 static void sky2_shutdown(struct pci_dev *pdev)
 {
+	struct sky2_hw *hw = pci_get_drvdata(pdev);
+	int port;
+
+	for (port = 0; port < hw->ports; port++) {
+		struct net_device *ndev = hw->dev[port];
+
+		rtnl_lock();
+		if (netif_running(ndev)) {
+			dev_close(ndev);
+			netif_device_detach(ndev);
+		}
+		rtnl_unlock();
+	}
 	sky2_suspend(&pdev->dev);
 	pci_wake_from_d3(pdev, device_may_wakeup(&pdev->dev));
 	pci_set_power_state(pdev, PCI_D3hot);
-- 
2.7.4


From 8452b75e0a827cc96973dba4992422cc2a230806 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Thu, 17 Nov 2016 15:55:26 -0800
Subject: [PATCH 07/34] af_unix: conditionally use freezable blocking calls in
 read

[ Upstream commit 06a77b07e3b44aea2b3c0e64de420ea2cfdcbaa9 ]

Commit 2b15af6f95 ("af_unix: use freezable blocking calls in read")
converts schedule_timeout() to its freezable version, it was probably
correct at that time, but later, commit 2b514574f7e8
("net: af_unix: implement splice for stream af_unix sockets") breaks
the strong requirement for a freezable sleep, according to
commit 0f9548ca1091:

    We shouldn't try_to_freeze if locks are held.  Holding a lock can cause a
    deadlock if the lock is later acquired in the suspend or hibernate path
    (e.g.  by dpm).  Holding a lock can also cause a deadlock in the case of
    cgroup_freezer if a lock is held inside a frozen cgroup that is later
    acquired by a process outside that group.

The pipe_lock is still held at that point.

So use freezable version only for the recvmsg call path, avoid impact for
Android.

Fixes: 2b514574f7e8 ("net: af_unix: implement splice for stream af_unix sockets")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Colin Cross <ccross@android.com>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 8309687..568f307 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2199,7 +2199,8 @@ out:
  *	Sleep until more data has arrived. But check for races..
  */
 static long unix_stream_data_wait(struct sock *sk, long timeo,
-				  struct sk_buff *last, unsigned int last_len)
+				  struct sk_buff *last, unsigned int last_len,
+				  bool freezable)
 {
 	struct sk_buff *tail;
 	DEFINE_WAIT(wait);
@@ -2220,7 +2221,10 @@ static long unix_stream_data_wait(struct sock *sk, long timeo,
 
 		sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 		unix_state_unlock(sk);
-		timeo = freezable_schedule_timeout(timeo);
+		if (freezable)
+			timeo = freezable_schedule_timeout(timeo);
+		else
+			timeo = schedule_timeout(timeo);
 		unix_state_lock(sk);
 
 		if (sock_flag(sk, SOCK_DEAD))
@@ -2250,7 +2254,8 @@ struct unix_stream_read_state {
 	unsigned int splice_flags;
 };
 
-static int unix_stream_read_generic(struct unix_stream_read_state *state)
+static int unix_stream_read_generic(struct unix_stream_read_state *state,
+				    bool freezable)
 {
 	struct scm_cookie scm;
 	struct socket *sock = state->socket;
@@ -2330,7 +2335,7 @@ again:
 			mutex_unlock(&u->iolock);
 
 			timeo = unix_stream_data_wait(sk, timeo, last,
-						      last_len);
+						      last_len, freezable);
 
 			if (signal_pending(current)) {
 				err = sock_intr_errno(timeo);
@@ -2472,7 +2477,7 @@ static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg,
 		.flags = flags
 	};
 
-	return unix_stream_read_generic(&state);
+	return unix_stream_read_generic(&state, true);
 }
 
 static ssize_t skb_unix_socket_splice(struct sock *sk,
@@ -2518,7 +2523,7 @@ static ssize_t unix_stream_splice_read(struct socket *sock,  loff_t *ppos,
 	    flags & SPLICE_F_NONBLOCK)
 		state.flags = MSG_DONTWAIT;
 
-	return unix_stream_read_generic(&state);
+	return unix_stream_read_generic(&state, false);
 }
 
 static int unix_shutdown(struct socket *sock, int mode)
-- 
2.7.4


From 85b0b7fd27fe40375d2f3676dda0884a6079781a Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 18 Nov 2016 15:50:39 +0100
Subject: [PATCH 08/34] rtnetlink: fix FDB size computation

[ Upstream commit f82ef3e10a870acc19fa04f80ef5877eaa26f41e ]

Add missing NDA_VLAN attribute's size.

Fixes: 1e53d5bb8878 ("net: Pass VLAN ID to rtnl_fdb_notify.")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 189cc78..9b39088 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2791,7 +2791,10 @@ nla_put_failure:
 
 static inline size_t rtnl_fdb_nlmsg_size(void)
 {
-	return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(ETH_ALEN);
+	return NLMSG_ALIGN(sizeof(struct ndmsg)) +
+	       nla_total_size(ETH_ALEN) +	/* NDA_LLADDR */
+	       nla_total_size(sizeof(u16)) +	/* NDA_VLAN */
+	       0;
 }
 
 static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, u16 vid, int type,
-- 
2.7.4


From 3e4b2c9a40c3ed5bdfa4ba01b4cb46edae188134 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Fri, 18 Nov 2016 22:13:00 +0100
Subject: [PATCH 09/34] l2tp: fix racy SOCK_ZAPPED flag check in
 l2tp_ip{,6}_bind()

[ Upstream commit 32c231164b762dddefa13af5a0101032c70b50ef ]

Lock socket before checking the SOCK_ZAPPED flag in l2tp_ip6_bind().
Without lock, a concurrent call could modify the socket flags between
the sock_flag(sk, SOCK_ZAPPED) test and the lock_sock() call. This way,
a socket could be inserted twice in l2tp_ip6_bind_table. Releasing it
would then leave a stale pointer there, generating use-after-free
errors when walking through the list or modifying adjacent entries.

BUG: KASAN: use-after-free in l2tp_ip6_close+0x22e/0x290 at addr ffff8800081b0ed8
Write of size 8 by task syz-executor/10987
CPU: 0 PID: 10987 Comm: syz-executor Not tainted 4.8.0+ #39
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.2-0-g33fbe13 by qemu-project.org 04/01/2014
 ffff880031d97838 ffffffff829f835b ffff88001b5a1640 ffff8800081b0ec0
 ffff8800081b15a0 ffff8800081b6d20 ffff880031d97860 ffffffff8174d3cc
 ffff880031d978f0 ffff8800081b0e80 ffff88001b5a1640 ffff880031d978e0
Call Trace:
 [<ffffffff829f835b>] dump_stack+0xb3/0x118 lib/dump_stack.c:15
 [<ffffffff8174d3cc>] kasan_object_err+0x1c/0x70 mm/kasan/report.c:156
 [<     inline     >] print_address_description mm/kasan/report.c:194
 [<ffffffff8174d666>] kasan_report_error+0x1f6/0x4d0 mm/kasan/report.c:283
 [<     inline     >] kasan_report mm/kasan/report.c:303
 [<ffffffff8174db7e>] __asan_report_store8_noabort+0x3e/0x40 mm/kasan/report.c:329
 [<     inline     >] __write_once_size ./include/linux/compiler.h:249
 [<     inline     >] __hlist_del ./include/linux/list.h:622
 [<     inline     >] hlist_del_init ./include/linux/list.h:637
 [<ffffffff8579047e>] l2tp_ip6_close+0x22e/0x290 net/l2tp/l2tp_ip6.c:239
 [<ffffffff850b2dfd>] inet_release+0xed/0x1c0 net/ipv4/af_inet.c:415
 [<ffffffff851dc5a0>] inet6_release+0x50/0x70 net/ipv6/af_inet6.c:422
 [<ffffffff84c4581d>] sock_release+0x8d/0x1d0 net/socket.c:570
 [<ffffffff84c45976>] sock_close+0x16/0x20 net/socket.c:1017
 [<ffffffff817a108c>] __fput+0x28c/0x780 fs/file_table.c:208
 [<ffffffff817a1605>] ____fput+0x15/0x20 fs/file_table.c:244
 [<ffffffff813774f9>] task_work_run+0xf9/0x170
 [<ffffffff81324aae>] do_exit+0x85e/0x2a00
 [<ffffffff81326dc8>] do_group_exit+0x108/0x330
 [<ffffffff81348cf7>] get_signal+0x617/0x17a0 kernel/signal.c:2307
 [<ffffffff811b49af>] do_signal+0x7f/0x18f0
 [<ffffffff810039bf>] exit_to_usermode_loop+0xbf/0x150 arch/x86/entry/common.c:156
 [<     inline     >] prepare_exit_to_usermode arch/x86/entry/common.c:190
 [<ffffffff81006060>] syscall_return_slowpath+0x1a0/0x1e0 arch/x86/entry/common.c:259
 [<ffffffff85e4d726>] entry_SYSCALL_64_fastpath+0xc4/0xc6
Object at ffff8800081b0ec0, in cache L2TP/IPv6 size: 1448
Allocated:
PID = 10987
 [ 1116.897025] [<ffffffff811ddcb6>] save_stack_trace+0x16/0x20
 [ 1116.897025] [<ffffffff8174c736>] save_stack+0x46/0xd0
 [ 1116.897025] [<ffffffff8174c9ad>] kasan_kmalloc+0xad/0xe0
 [ 1116.897025] [<ffffffff8174cee2>] kasan_slab_alloc+0x12/0x20
 [ 1116.897025] [<     inline     >] slab_post_alloc_hook mm/slab.h:417
 [ 1116.897025] [<     inline     >] slab_alloc_node mm/slub.c:2708
 [ 1116.897025] [<     inline     >] slab_alloc mm/slub.c:2716
 [ 1116.897025] [<ffffffff817476a8>] kmem_cache_alloc+0xc8/0x2b0 mm/slub.c:2721
 [ 1116.897025] [<ffffffff84c4f6a9>] sk_prot_alloc+0x69/0x2b0 net/core/sock.c:1326
 [ 1116.897025] [<ffffffff84c58ac8>] sk_alloc+0x38/0xae0 net/core/sock.c:1388
 [ 1116.897025] [<ffffffff851ddf67>] inet6_create+0x2d7/0x1000 net/ipv6/af_inet6.c:182
 [ 1116.897025] [<ffffffff84c4af7b>] __sock_create+0x37b/0x640 net/socket.c:1153
 [ 1116.897025] [<     inline     >] sock_create net/socket.c:1193
 [ 1116.897025] [<     inline     >] SYSC_socket net/socket.c:1223
 [ 1116.897025] [<ffffffff84c4b46f>] SyS_socket+0xef/0x1b0 net/socket.c:1203
 [ 1116.897025] [<ffffffff85e4d685>] entry_SYSCALL_64_fastpath+0x23/0xc6
Freed:
PID = 10987
 [ 1116.897025] [<ffffffff811ddcb6>] save_stack_trace+0x16/0x20
 [ 1116.897025] [<ffffffff8174c736>] save_stack+0x46/0xd0
 [ 1116.897025] [<ffffffff8174cf61>] kasan_slab_free+0x71/0xb0
 [ 1116.897025] [<     inline     >] slab_free_hook mm/slub.c:1352
 [ 1116.897025] [<     inline     >] slab_free_freelist_hook mm/slub.c:1374
 [ 1116.897025] [<     inline     >] slab_free mm/slub.c:2951
 [ 1116.897025] [<ffffffff81748b28>] kmem_cache_free+0xc8/0x330 mm/slub.c:2973
 [ 1116.897025] [<     inline     >] sk_prot_free net/core/sock.c:1369
 [ 1116.897025] [<ffffffff84c541eb>] __sk_destruct+0x32b/0x4f0 net/core/sock.c:1444
 [ 1116.897025] [<ffffffff84c5aca4>] sk_destruct+0x44/0x80 net/core/sock.c:1452
 [ 1116.897025] [<ffffffff84c5ad33>] __sk_free+0x53/0x220 net/core/sock.c:1460
 [ 1116.897025] [<ffffffff84c5af23>] sk_free+0x23/0x30 net/core/sock.c:1471
 [ 1116.897025] [<ffffffff84c5cb6c>] sk_common_release+0x28c/0x3e0 ./include/net/sock.h:1589
 [ 1116.897025] [<ffffffff8579044e>] l2tp_ip6_close+0x1fe/0x290 net/l2tp/l2tp_ip6.c:243
 [ 1116.897025] [<ffffffff850b2dfd>] inet_release+0xed/0x1c0 net/ipv4/af_inet.c:415
 [ 1116.897025] [<ffffffff851dc5a0>] inet6_release+0x50/0x70 net/ipv6/af_inet6.c:422
 [ 1116.897025] [<ffffffff84c4581d>] sock_release+0x8d/0x1d0 net/socket.c:570
 [ 1116.897025] [<ffffffff84c45976>] sock_close+0x16/0x20 net/socket.c:1017
 [ 1116.897025] [<ffffffff817a108c>] __fput+0x28c/0x780 fs/file_table.c:208
 [ 1116.897025] [<ffffffff817a1605>] ____fput+0x15/0x20 fs/file_table.c:244
 [ 1116.897025] [<ffffffff813774f9>] task_work_run+0xf9/0x170
 [ 1116.897025] [<ffffffff81324aae>] do_exit+0x85e/0x2a00
 [ 1116.897025] [<ffffffff81326dc8>] do_group_exit+0x108/0x330
 [ 1116.897025] [<ffffffff81348cf7>] get_signal+0x617/0x17a0 kernel/signal.c:2307
 [ 1116.897025] [<ffffffff811b49af>] do_signal+0x7f/0x18f0
 [ 1116.897025] [<ffffffff810039bf>] exit_to_usermode_loop+0xbf/0x150 arch/x86/entry/common.c:156
 [ 1116.897025] [<     inline     >] prepare_exit_to_usermode arch/x86/entry/common.c:190
 [ 1116.897025] [<ffffffff81006060>] syscall_return_slowpath+0x1a0/0x1e0 arch/x86/entry/common.c:259
 [ 1116.897025] [<ffffffff85e4d726>] entry_SYSCALL_64_fastpath+0xc4/0xc6
Memory state around the buggy address:
 ffff8800081b0d80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 ffff8800081b0e00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
>ffff8800081b0e80: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb
                                                    ^
 ffff8800081b0f00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff8800081b0f80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb

==================================================================

The same issue exists with l2tp_ip_bind() and l2tp_ip_bind_table.

Fixes: c51ce49735c1 ("l2tp: fix oops in L2TP IP sockets for connect() AF_UNSPEC case")
Reported-by: Baozeng Ding <sploving1@gmail.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Baozeng Ding <sploving1@gmail.com>
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ip.c  | 5 +++--
 net/l2tp/l2tp_ip6.c | 5 +++--
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 42de4cc..d0e906d 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -251,8 +251,6 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	int ret;
 	int chk_addr_ret;
 
-	if (!sock_flag(sk, SOCK_ZAPPED))
-		return -EINVAL;
 	if (addr_len < sizeof(struct sockaddr_l2tpip))
 		return -EINVAL;
 	if (addr->l2tp_family != AF_INET)
@@ -267,6 +265,9 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	read_unlock_bh(&l2tp_ip_lock);
 
 	lock_sock(sk);
+	if (!sock_flag(sk, SOCK_ZAPPED))
+		goto out;
+
 	if (sk->sk_state != TCP_CLOSE || addr_len < sizeof(struct sockaddr_l2tpip))
 		goto out;
 
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index ea2ae66..b9c6a41 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -269,8 +269,6 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	int addr_type;
 	int err;
 
-	if (!sock_flag(sk, SOCK_ZAPPED))
-		return -EINVAL;
 	if (addr->l2tp_family != AF_INET6)
 		return -EINVAL;
 	if (addr_len < sizeof(*addr))
@@ -296,6 +294,9 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	lock_sock(sk);
 
 	err = -EINVAL;
+	if (!sock_flag(sk, SOCK_ZAPPED))
+		goto out_unlock;
+
 	if (sk->sk_state != TCP_CLOSE)
 		goto out_unlock;
 
-- 
2.7.4


From cb661e5fbb018eab29a3ec12b0029442b06b8b77 Mon Sep 17 00:00:00 2001
From: Zhang Shengju <zhangshengju@cmss.chinamobile.com>
Date: Sat, 19 Nov 2016 23:28:32 +0800
Subject: [PATCH 10/34] rtnl: fix the loop index update error in
 rtnl_dump_ifinfo()

[ Upstream commit 3f0ae05d6fea0ed5b19efdbc9c9f8e02685a3af3 ]

If the link is filtered out, loop index should also be updated. If not,
loop index will not be correct.

Fixes: dc599f76c22b0 ("net: Add support for filtering link dump by master device and kind")
Signed-off-by: Zhang Shengju <zhangshengju@cmss.chinamobile.com>
Acked-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 9b39088..08c3702 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1578,7 +1578,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 		head = &net->dev_index_head[h];
 		hlist_for_each_entry(dev, head, index_hlist) {
 			if (link_dump_filtered(dev, master_idx, kind_ops))
-				continue;
+				goto cont;
 			if (idx < s_idx)
 				goto cont;
 			err = rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK,
-- 
2.7.4


From 0b2935f5e83fdb172563c00404c31e68c7a627fd Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 22 Nov 2016 16:57:40 +0100
Subject: [PATCH 11/34] ipv6: bump genid when the IFA_F_TENTATIVE flag is clear

[ Upstream commit 764d3be6e415b40056834bfd29b994dc3f837606 ]

When an ipv6 address has the tentative flag set, it can't be
used as source for egress traffic, while the associated route,
if any, can be looked up and even stored into some dst_cache.

In the latter scenario, the source ipv6 address selected and
stored in the cache is most probably wrong (e.g. with
link-local scope) and the entity using the dst_cache will
experience lack of ipv6 connectivity until said cache is
cleared or invalidated.

Overall this may cause lack of connectivity over most IPv6 tunnels
(comprising geneve and vxlan), if the first egress packet reaches
the tunnel before the DaD is completed for the used ipv6
address.

This patch bumps a new genid after that the IFA_F_TENTATIVE flag
is cleared, so that dst_cache will be invalidated on
next lookup and ipv6 connectivity restored.

Fixes: 0c1d70af924b ("net: use dst_cache for vxlan device")
Fixes: 468dfffcd762 ("geneve: add dst caching support")
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index f5432d6..8f2e36f 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -163,7 +163,7 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
 
 static void addrconf_dad_start(struct inet6_ifaddr *ifp);
 static void addrconf_dad_work(struct work_struct *w);
-static void addrconf_dad_completed(struct inet6_ifaddr *ifp);
+static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id);
 static void addrconf_dad_run(struct inet6_dev *idev);
 static void addrconf_rs_timer(unsigned long data);
 static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa);
@@ -2893,6 +2893,7 @@ static void add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
 		spin_lock_bh(&ifp->lock);
 		ifp->flags &= ~IFA_F_TENTATIVE;
 		spin_unlock_bh(&ifp->lock);
+		rt_genid_bump_ipv6(dev_net(idev->dev));
 		ipv6_ifa_notify(RTM_NEWADDR, ifp);
 		in6_ifa_put(ifp);
 	}
@@ -3736,7 +3737,7 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
 {
 	struct inet6_dev *idev = ifp->idev;
 	struct net_device *dev = idev->dev;
-	bool notify = false;
+	bool bump_id, notify = false;
 
 	addrconf_join_solict(dev, &ifp->addr);
 
@@ -3751,11 +3752,12 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
 	    idev->cnf.accept_dad < 1 ||
 	    !(ifp->flags&IFA_F_TENTATIVE) ||
 	    ifp->flags & IFA_F_NODAD) {
+		bump_id = ifp->flags & IFA_F_TENTATIVE;
 		ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED);
 		spin_unlock(&ifp->lock);
 		read_unlock_bh(&idev->lock);
 
-		addrconf_dad_completed(ifp);
+		addrconf_dad_completed(ifp, bump_id);
 		return;
 	}
 
@@ -3815,8 +3817,8 @@ static void addrconf_dad_work(struct work_struct *w)
 						struct inet6_ifaddr,
 						dad_work);
 	struct inet6_dev *idev = ifp->idev;
+	bool bump_id, disable_ipv6 = false;
 	struct in6_addr mcaddr;
-	bool disable_ipv6 = false;
 
 	enum {
 		DAD_PROCESS,
@@ -3886,11 +3888,12 @@ static void addrconf_dad_work(struct work_struct *w)
 		 * DAD was successful
 		 */
 
+		bump_id = ifp->flags & IFA_F_TENTATIVE;
 		ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED);
 		spin_unlock(&ifp->lock);
 		write_unlock_bh(&idev->lock);
 
-		addrconf_dad_completed(ifp);
+		addrconf_dad_completed(ifp, bump_id);
 
 		goto out;
 	}
@@ -3927,7 +3930,7 @@ static bool ipv6_lonely_lladdr(struct inet6_ifaddr *ifp)
 	return true;
 }
 
-static void addrconf_dad_completed(struct inet6_ifaddr *ifp)
+static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id)
 {
 	struct net_device *dev = ifp->idev->dev;
 	struct in6_addr lladdr;
@@ -3978,6 +3981,9 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp)
 		spin_unlock(&ifp->lock);
 		write_unlock_bh(&ifp->idev->lock);
 	}
+
+	if (bump_id)
+		rt_genid_bump_ipv6(dev_net(dev));
 }
 
 static void addrconf_dad_run(struct inet6_dev *idev)
-- 
2.7.4


From 64197b5a0ffad26bd5c8f54ad521cc70f21af53d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 22 Nov 2016 09:06:45 -0800
Subject: [PATCH 12/34] udplite: call proper backlog handlers

[ Upstream commit 30c7be26fd3587abcb69587f781098e3ca2d565b ]

In commits 93821778def10 ("udp: Fix rcv socket locking") and
f7ad74fef3af ("net/ipv6/udp: UDP encapsulation: break backlog_rcv into
__udpv6_queue_rcv_skb") UDP backlog handlers were renamed, but UDPlite
was forgotten.

This leads to crashes if UDPlite header is pulled twice, which happens
starting from commit e6afc8ace6dd ("udp: remove headers from UDP packets
before queueing")

Bug found by syzkaller team, thanks a lot guys !

Note that backlog use in UDP/UDPlite is scheduled to be removed starting
from linux-4.10, so this patch is only needed up to linux-4.9

Fixes: 93821778def1 ("udp: Fix rcv socket locking")
Fixes: f7ad74fef3af ("net/ipv6/udp: UDP encapsulation: break backlog_rcv into __udpv6_queue_rcv_skb")
Fixes: e6afc8ace6dd ("udp: remove headers from UDP packets before queueing")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Cc: Benjamin LaHaise <bcrl@kvack.org>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c      | 2 +-
 net/ipv4/udp_impl.h | 2 +-
 net/ipv4/udplite.c  | 2 +-
 net/ipv6/udp.c      | 2 +-
 net/ipv6/udp_impl.h | 2 +-
 net/ipv6/udplite.c  | 2 +-
 6 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index c0d71e7..a2d54f5 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1451,7 +1451,7 @@ static void udp_v4_rehash(struct sock *sk)
 	udp_lib_rehash(sk, new_hash);
 }
 
-static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 {
 	int rc;
 
diff --git a/net/ipv4/udp_impl.h b/net/ipv4/udp_impl.h
index 7e0fe4b..feb50a1 100644
--- a/net/ipv4/udp_impl.h
+++ b/net/ipv4/udp_impl.h
@@ -25,7 +25,7 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
 		int flags, int *addr_len);
 int udp_sendpage(struct sock *sk, struct page *page, int offset, size_t size,
 		 int flags);
-int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
+int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
 void udp_destroy_sock(struct sock *sk);
 
 #ifdef CONFIG_PROC_FS
diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c
index 2eea073..705d9fb 100644
--- a/net/ipv4/udplite.c
+++ b/net/ipv4/udplite.c
@@ -50,7 +50,7 @@ struct proto 	udplite_prot = {
 	.sendmsg	   = udp_sendmsg,
 	.recvmsg	   = udp_recvmsg,
 	.sendpage	   = udp_sendpage,
-	.backlog_rcv	   = udp_queue_rcv_skb,
+	.backlog_rcv	   = __udp_queue_rcv_skb,
 	.hash		   = udp_lib_hash,
 	.unhash		   = udp_lib_unhash,
 	.get_port	   = udp_v4_get_port,
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index c2a8656..fa39ab8 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -514,7 +514,7 @@ out:
 	return;
 }
 
-static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 {
 	int rc;
 
diff --git a/net/ipv6/udp_impl.h b/net/ipv6/udp_impl.h
index 0682c03..3c1dbc9 100644
--- a/net/ipv6/udp_impl.h
+++ b/net/ipv6/udp_impl.h
@@ -26,7 +26,7 @@ int compat_udpv6_getsockopt(struct sock *sk, int level, int optname,
 int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len);
 int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
 		  int flags, int *addr_len);
-int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
+int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
 void udpv6_destroy_sock(struct sock *sk);
 
 void udp_v6_clear_sk(struct sock *sk, int size);
diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c
index fd6ef41..af2895c 100644
--- a/net/ipv6/udplite.c
+++ b/net/ipv6/udplite.c
@@ -45,7 +45,7 @@ struct proto udplitev6_prot = {
 	.getsockopt	   = udpv6_getsockopt,
 	.sendmsg	   = udpv6_sendmsg,
 	.recvmsg	   = udpv6_recvmsg,
-	.backlog_rcv	   = udpv6_queue_rcv_skb,
+	.backlog_rcv	   = __udpv6_queue_rcv_skb,
 	.hash		   = udp_lib_hash,
 	.unhash		   = udp_lib_unhash,
 	.get_port	   = udp_v6_get_port,
-- 
2.7.4


From 33cf0d6fe131c76a70002599f79ffed893a0a5f0 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 22 Nov 2016 11:40:58 -0800
Subject: [PATCH 13/34] net: dsa: bcm_sf2: Ensure we re-negotiate EEE during
 after link change

[ Upstream commit 76da8706d90d8641eeb9b8e579942ed80b6c0880 ]

In case the link change and EEE is enabled or disabled, always try to
re-negotiate this with the link partner.

Fixes: 450b05c15f9c ("net: dsa: bcm_sf2: add support for controlling EEE")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index b2b8387..4036865 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -1167,6 +1167,7 @@ static void bcm_sf2_sw_adjust_link(struct dsa_switch *ds, int port,
 				   struct phy_device *phydev)
 {
 	struct bcm_sf2_priv *priv = ds_to_priv(ds);
+	struct ethtool_eee *p = &priv->port_sts[port].eee;
 	u32 id_mode_dis = 0, port_mode;
 	const char *str = NULL;
 	u32 reg;
@@ -1241,6 +1242,9 @@ force_link:
 		reg |= DUPLX_MODE;
 
 	core_writel(priv, reg, CORE_STS_OVERRIDE_GMIIP_PORT(port));
+
+	if (!phydev->is_pseudo_fixed_link)
+		p->eee_enabled = bcm_sf2_eee_init(ds, port, phydev);
 }
 
 static void bcm_sf2_sw_fixed_link_update(struct dsa_switch *ds, int port,
-- 
2.7.4


From 2875544421e82db81a439e6fafa220688658189d Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Sun, 27 Nov 2016 01:18:01 +0100
Subject: [PATCH 14/34] net, sched: respect rcu grace period on cls destruction

[ Upstream commit d936377414fadbafb4d17148d222fe45ca5442d4 ]

Roi reported a crash in flower where tp->root was NULL in ->classify()
callbacks. Reason is that in ->destroy() tp->root is set to NULL via
RCU_INIT_POINTER(). It's problematic for some of the classifiers, because
this doesn't respect RCU grace period for them, and as a result, still
outstanding readers from tc_classify() will try to blindly dereference
a NULL tp->root.

The tp->root object is strictly private to the classifier implementation
and holds internal data the core such as tc_ctl_tfilter() doesn't know
about. Within some classifiers, such as cls_bpf, cls_basic, etc, tp->root
is only checked for NULL in ->get() callback, but nowhere else. This is
misleading and seemed to be copied from old classifier code that was not
cleaned up properly. For example, d3fa76ee6b4a ("[NET_SCHED]: cls_basic:
fix NULL pointer dereference") moved tp->root initialization into ->init()
routine, where before it was part of ->change(), so ->get() had to deal
with tp->root being NULL back then, so that was indeed a valid case, after
d3fa76ee6b4a, not really anymore. We used to set tp->root to NULL long
ago in ->destroy(), see 47a1a1d4be29 ("pkt_sched: remove unnecessary xchg()
in packet classifiers"); but the NULLifying was reintroduced with the
RCUification, but it's not correct for every classifier implementation.

In the cases that are fixed here with one exception of cls_cgroup, tp->root
object is allocated and initialized inside ->init() callback, which is always
performed at a point in time after we allocate a new tp, which means tp and
thus tp->root was not globally visible in the tp chain yet (see tc_ctl_tfilter()).
Also, on destruction tp->root is strictly kfree_rcu()'ed in ->destroy()
handler, same for the tp which is kfree_rcu()'ed right when we return
from ->destroy() in tcf_destroy(). This means, the head object's lifetime
for such classifiers is always tied to the tp lifetime. The RCU callback
invocation for the two kfree_rcu() could be out of order, but that's fine
since both are independent.

Dropping the RCU_INIT_POINTER(tp->root, NULL) for these classifiers here
means that 1) we don't need a useless NULL check in fast-path and, 2) that
outstanding readers of that tp in tc_classify() can still execute under
respect with RCU grace period as it is actually expected.

Things that haven't been touched here: cls_fw and cls_route. They each
handle tp->root being NULL in ->classify() path for historic reasons, so
their ->destroy() implementation can stay as is. If someone actually
cares, they could get cleaned up at some point to avoid the test in fast
path. cls_u32 doesn't set tp->root to NULL. For cls_rsvp, I just added a
!head should anyone actually be using/testing it, so it at least aligns with
cls_fw and cls_route. For cls_flower we additionally need to defer rhashtable
destruction (to a sleepable context) after RCU grace period as concurrent
readers might still access it. (Note that in this case we need to hold module
reference to keep work callback address intact, since we only wait on module
unload for all call_rcu()s to finish.)

This fixes one race to bring RCU grace period guarantees back. Next step
as worked on by Cong however is to fix 1e052be69d04 ("net_sched: destroy
proto tp when all filters are gone") to get the order of unlinking the tp
in tc_ctl_tfilter() for the RTM_DELTFILTER case right by moving
RCU_INIT_POINTER() before tcf_destroy() and let the notification for
removal be done through the prior ->delete() callback. Both are independant
issues. Once we have that right, we can then clean tp->root up for a number
of classifiers by not making them RCU pointers, which requires a new callback
(->uninit) that is triggered from tp's RCU callback, where we just kfree()
tp->root from there.

Fixes: 1f947bf151e9 ("net: sched: rcu'ify cls_bpf")
Fixes: 9888faefe132 ("net: sched: cls_basic use RCU")
Fixes: 70da9f0bf999 ("net: sched: cls_flow use RCU")
Fixes: 77b9900ef53a ("tc: introduce Flower classifier")
Fixes: bf3994d2ed31 ("net/sched: introduce Match-all classifier")
Fixes: 952313bd6258 ("net: sched: cls_cgroup use RCU")
Reported-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: Roi Dayan <roid@mellanox.com>
Cc: Jiri Pirko <jiri@mellanox.com>
Acked-by: John Fastabend <john.r.fastabend@intel.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_basic.c    |  4 ----
 net/sched/cls_bpf.c      |  4 ----
 net/sched/cls_cgroup.c   |  7 +++----
 net/sched/cls_flow.c     |  1 -
 net/sched/cls_flower.c   | 31 ++++++++++++++++++++++++++-----
 net/sched/cls_matchall.c |  1 -
 net/sched/cls_rsvp.h     |  3 ++-
 net/sched/cls_tcindex.c  |  1 -
 8 files changed, 31 insertions(+), 21 deletions(-)

diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c
index 0b8c3ac..1bf1f451 100644
--- a/net/sched/cls_basic.c
+++ b/net/sched/cls_basic.c
@@ -62,9 +62,6 @@ static unsigned long basic_get(struct tcf_proto *tp, u32 handle)
 	struct basic_head *head = rtnl_dereference(tp->root);
 	struct basic_filter *f;
 
-	if (head == NULL)
-		return 0UL;
-
 	list_for_each_entry(f, &head->flist, link) {
 		if (f->handle == handle) {
 			l = (unsigned long) f;
@@ -109,7 +106,6 @@ static bool basic_destroy(struct tcf_proto *tp, bool force)
 		tcf_unbind_filter(tp, &f->res);
 		call_rcu(&f->rcu, basic_delete_filter);
 	}
-	RCU_INIT_POINTER(tp->root, NULL);
 	kfree_rcu(head, rcu);
 	return true;
 }
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index c3002c2..dbec458 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -200,7 +200,6 @@ static bool cls_bpf_destroy(struct tcf_proto *tp, bool force)
 		call_rcu(&prog->rcu, __cls_bpf_delete_prog);
 	}
 
-	RCU_INIT_POINTER(tp->root, NULL);
 	kfree_rcu(head, rcu);
 	return true;
 }
@@ -211,9 +210,6 @@ static unsigned long cls_bpf_get(struct tcf_proto *tp, u32 handle)
 	struct cls_bpf_prog *prog;
 	unsigned long ret = 0UL;
 
-	if (head == NULL)
-		return 0UL;
-
 	list_for_each_entry(prog, &head->plist, link) {
 		if (prog->handle == handle) {
 			ret = (unsigned long) prog;
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index 4c85bd3..c104c20 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -130,11 +130,10 @@ static bool cls_cgroup_destroy(struct tcf_proto *tp, bool force)
 
 	if (!force)
 		return false;
-
-	if (head) {
-		RCU_INIT_POINTER(tp->root, NULL);
+	/* Head can still be NULL due to cls_cgroup_init(). */
+	if (head)
 		call_rcu(&head->rcu, cls_cgroup_destroy_rcu);
-	}
+
 	return true;
 }
 
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index fbfec6a..d7ba2b4 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -583,7 +583,6 @@ static bool flow_destroy(struct tcf_proto *tp, bool force)
 		list_del_rcu(&f->list);
 		call_rcu(&f->rcu, flow_destroy_filter);
 	}
-	RCU_INIT_POINTER(tp->root, NULL);
 	kfree_rcu(head, rcu);
 	return true;
 }
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 5060801..a411571 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -13,6 +13,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/rhashtable.h>
+#include <linux/workqueue.h>
 
 #include <linux/if_ether.h>
 #include <linux/in6.h>
@@ -55,7 +56,10 @@ struct cls_fl_head {
 	bool mask_assigned;
 	struct list_head filters;
 	struct rhashtable_params ht_params;
-	struct rcu_head rcu;
+	union {
+		struct work_struct work;
+		struct rcu_head	rcu;
+	};
 };
 
 struct cls_fl_filter {
@@ -239,6 +243,24 @@ static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f)
 	dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, &tc);
 }
 
+static void fl_destroy_sleepable(struct work_struct *work)
+{
+	struct cls_fl_head *head = container_of(work, struct cls_fl_head,
+						work);
+	if (head->mask_assigned)
+		rhashtable_destroy(&head->ht);
+	kfree(head);
+	module_put(THIS_MODULE);
+}
+
+static void fl_destroy_rcu(struct rcu_head *rcu)
+{
+	struct cls_fl_head *head = container_of(rcu, struct cls_fl_head, rcu);
+
+	INIT_WORK(&head->work, fl_destroy_sleepable);
+	schedule_work(&head->work);
+}
+
 static bool fl_destroy(struct tcf_proto *tp, bool force)
 {
 	struct cls_fl_head *head = rtnl_dereference(tp->root);
@@ -252,10 +274,9 @@ static bool fl_destroy(struct tcf_proto *tp, bool force)
 		list_del_rcu(&f->list);
 		call_rcu(&f->rcu, fl_destroy_filter);
 	}
-	RCU_INIT_POINTER(tp->root, NULL);
-	if (head->mask_assigned)
-		rhashtable_destroy(&head->ht);
-	kfree_rcu(head, rcu);
+
+	__module_get(THIS_MODULE);
+	call_rcu(&head->rcu, fl_destroy_rcu);
 	return true;
 }
 
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index 25927b6..f935429 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -114,7 +114,6 @@ static bool mall_destroy(struct tcf_proto *tp, bool force)
 
 		call_rcu(&f->rcu, mall_destroy_filter);
 	}
-	RCU_INIT_POINTER(tp->root, NULL);
 	kfree_rcu(head, rcu);
 	return true;
 }
diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h
index f9c9fc0..9992dfa 100644
--- a/net/sched/cls_rsvp.h
+++ b/net/sched/cls_rsvp.h
@@ -152,7 +152,8 @@ static int rsvp_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 		return -1;
 	nhptr = ip_hdr(skb);
 #endif
-
+	if (unlikely(!head))
+		return -1;
 restart:
 
 #if RSVP_DST_LEN == 4
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 944c8ff..403746b 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -503,7 +503,6 @@ static bool tcindex_destroy(struct tcf_proto *tp, bool force)
 	walker.fn = tcindex_destroy_element;
 	tcindex_walk(tp, &walker);
 
-	RCU_INIT_POINTER(tp->root, NULL);
 	call_rcu(&p->rcu, __tcindex_destroy);
 	return true;
 }
-- 
2.7.4


From 021c12ee9fd302aeb5533a53388d6e520101edd7 Mon Sep 17 00:00:00 2001
From: Nikita Yushchenko <nikita.yoush@cogentembedded.com>
Date: Mon, 28 Nov 2016 09:48:48 +0300
Subject: [PATCH 15/34] net: dsa: fix unbalanced dsa_switch_tree reference
 counting

[ Upstream commit 7a99cd6e213685b78118382e6a8fed506c82ccb2 ]

_dsa_register_switch() gets a dsa_switch_tree object either via
dsa_get_dst() or via dsa_add_dst(). Former path does not increase kref
in returned object (resulting into caller not owning a reference),
while later path does create a new object (resulting into caller owning
a reference).

The rest of _dsa_register_switch() assumes that it owns a reference, and
calls dsa_put_dst().

This causes a memory breakage if first switch in the tree initialized
successfully, but second failed to initialize. In particular, freed
dsa_swith_tree object is left referenced by switch that was initialized,
and later access to sysfs attributes of that switch cause OOPS.

To fix, need to add kref_get() call to dsa_get_dst().

Fixes: 83c0afaec7b7 ("net: dsa: Add new binding implementation")
Signed-off-by: Nikita Yushchenko <nikita.yoush@cogentembedded.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/dsa2.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index f30bad9..3bdecd2 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -28,8 +28,10 @@ static struct dsa_switch_tree *dsa_get_dst(u32 tree)
 	struct dsa_switch_tree *dst;
 
 	list_for_each_entry(dst, &dsa_switch_trees, list)
-		if (dst->tree == tree)
+		if (dst->tree == tree) {
+			kref_get(&dst->refcount);
 			return dst;
+		}
 	return NULL;
 }
 
-- 
2.7.4


From e633668d0c335b0cbb98bae04c17728307b19689 Mon Sep 17 00:00:00 2001
From: Amir Vadai <amir@vadai.me>
Date: Mon, 28 Nov 2016 12:56:40 +0200
Subject: [PATCH 16/34] net/sched: pedit: make sure that offset is valid

[ Upstream commit 95c2027bfeda21a28eb245121e6a249f38d0788e ]

Add a validation function to make sure offset is valid:
1. Not below skb head (could happen when offset is negative).
2. Validate both 'offset' and 'at'.

Signed-off-by: Amir Vadai <amir@vadai.me>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_pedit.c | 24 ++++++++++++++++++++----
 1 file changed, 20 insertions(+), 4 deletions(-)

diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index b54d56d..cf9b2fe 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -108,6 +108,17 @@ static void tcf_pedit_cleanup(struct tc_action *a, int bind)
 	kfree(keys);
 }
 
+static bool offset_valid(struct sk_buff *skb, int offset)
+{
+	if (offset > 0 && offset > skb->len)
+		return false;
+
+	if  (offset < 0 && -offset > skb_headroom(skb))
+		return false;
+
+	return true;
+}
+
 static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a,
 		     struct tcf_result *res)
 {
@@ -134,6 +145,11 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a,
 			if (tkey->offmask) {
 				char *d, _d;
 
+				if (!offset_valid(skb, off + tkey->at)) {
+					pr_info("tc filter pedit 'at' offset %d out of bounds\n",
+						off + tkey->at);
+					goto bad;
+				}
 				d = skb_header_pointer(skb, off + tkey->at, 1,
 						       &_d);
 				if (!d)
@@ -146,10 +162,10 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a,
 					" offset must be on 32 bit boundaries\n");
 				goto bad;
 			}
-			if (offset > 0 && offset > skb->len) {
-				pr_info("tc filter pedit"
-					" offset %d can't exceed pkt length %d\n",
-				       offset, skb->len);
+
+			if (!offset_valid(skb, off + offset)) {
+				pr_info("tc filter pedit offset %d out of bounds\n",
+					offset);
 				goto bad;
 			}
 
-- 
2.7.4


From 26370a849affd50461ddd8d5076cbcbbf39fdf9a Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Mon, 28 Nov 2016 19:22:12 +0800
Subject: [PATCH 17/34] netlink: Call cb->done from a worker thread

[ Upstream commit 707693c8a498697aa8db240b93eb76ec62e30892 ]

The cb->done interface expects to be called in process context.
This was broken by the netlink RCU conversion.  This patch fixes
it by adding a worker struct to make the cb->done call where
necessary.

Fixes: 21e4902aea80 ("netlink: Lockless lookup with RCU grace...")
Reported-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 27 +++++++++++++++++++++++----
 net/netlink/af_netlink.h |  2 ++
 2 files changed, 25 insertions(+), 4 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 62bea45..602e5eb 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -322,14 +322,11 @@ static void netlink_skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
 	sk_mem_charge(sk, skb->truesize);
 }
 
-static void netlink_sock_destruct(struct sock *sk)
+static void __netlink_sock_destruct(struct sock *sk)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
 
 	if (nlk->cb_running) {
-		if (nlk->cb.done)
-			nlk->cb.done(&nlk->cb);
-
 		module_put(nlk->cb.module);
 		kfree_skb(nlk->cb.skb);
 	}
@@ -346,6 +343,28 @@ static void netlink_sock_destruct(struct sock *sk)
 	WARN_ON(nlk_sk(sk)->groups);
 }
 
+static void netlink_sock_destruct_work(struct work_struct *work)
+{
+	struct netlink_sock *nlk = container_of(work, struct netlink_sock,
+						work);
+
+	nlk->cb.done(&nlk->cb);
+	__netlink_sock_destruct(&nlk->sk);
+}
+
+static void netlink_sock_destruct(struct sock *sk)
+{
+	struct netlink_sock *nlk = nlk_sk(sk);
+
+	if (nlk->cb_running && nlk->cb.done) {
+		INIT_WORK(&nlk->work, netlink_sock_destruct_work);
+		schedule_work(&nlk->work);
+		return;
+	}
+
+	__netlink_sock_destruct(sk);
+}
+
 /* This lock without WQ_FLAG_EXCLUSIVE is good on UP and it is _very_ bad on
  * SMP. Look, when several writers sleep and reader wakes them up, all but one
  * immediately hit write lock and grab all the cpus. Exclusive sleep solves
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index 3cfd6cc..4fdb383 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -3,6 +3,7 @@
 
 #include <linux/rhashtable.h>
 #include <linux/atomic.h>
+#include <linux/workqueue.h>
 #include <net/sock.h>
 
 #define NLGRPSZ(x)	(ALIGN(x, sizeof(unsigned long) * 8) / 8)
@@ -33,6 +34,7 @@ struct netlink_sock {
 
 	struct rhash_head	node;
 	struct rcu_head		rcu;
+	struct work_struct	work;
 };
 
 static inline struct netlink_sock *nlk_sk(struct sock *sk)
-- 
2.7.4


From 8f2fe0195b1cf7f130a3125bb5d5a83396d1a37b Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Mon, 5 Dec 2016 15:28:21 +0800
Subject: [PATCH 18/34] netlink: Do not schedule work from sk_destruct

[ Upstream commit ed5d7788a934a4b6d6d025e948ed4da496b4f12e ]

It is wrong to schedule a work from sk_destruct using the socket
as the memory reserve because the socket will be freed immediately
after the return from sk_destruct.

Instead we should do the deferral prior to sk_free.

This patch does just that.

Fixes: 707693c8a498 ("netlink: Call cb->done from a worker thread")
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 32 +++++++++++++++-----------------
 1 file changed, 15 insertions(+), 17 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 602e5eb..246f29d 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -322,11 +322,13 @@ static void netlink_skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
 	sk_mem_charge(sk, skb->truesize);
 }
 
-static void __netlink_sock_destruct(struct sock *sk)
+static void netlink_sock_destruct(struct sock *sk)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
 
 	if (nlk->cb_running) {
+		if (nlk->cb.done)
+			nlk->cb.done(&nlk->cb);
 		module_put(nlk->cb.module);
 		kfree_skb(nlk->cb.skb);
 	}
@@ -348,21 +350,7 @@ static void netlink_sock_destruct_work(struct work_struct *work)
 	struct netlink_sock *nlk = container_of(work, struct netlink_sock,
 						work);
 
-	nlk->cb.done(&nlk->cb);
-	__netlink_sock_destruct(&nlk->sk);
-}
-
-static void netlink_sock_destruct(struct sock *sk)
-{
-	struct netlink_sock *nlk = nlk_sk(sk);
-
-	if (nlk->cb_running && nlk->cb.done) {
-		INIT_WORK(&nlk->work, netlink_sock_destruct_work);
-		schedule_work(&nlk->work);
-		return;
-	}
-
-	__netlink_sock_destruct(sk);
+	sk_free(&nlk->sk);
 }
 
 /* This lock without WQ_FLAG_EXCLUSIVE is good on UP and it is _very_ bad on
@@ -667,8 +655,18 @@ out_module:
 static void deferred_put_nlk_sk(struct rcu_head *head)
 {
 	struct netlink_sock *nlk = container_of(head, struct netlink_sock, rcu);
+	struct sock *sk = &nlk->sk;
+
+	if (!atomic_dec_and_test(&sk->sk_refcnt))
+		return;
+
+	if (nlk->cb_running && nlk->cb.done) {
+		INIT_WORK(&nlk->work, netlink_sock_destruct_work);
+		schedule_work(&nlk->work);
+		return;
+	}
 
-	sock_put(&nlk->sk);
+	sk_free(sk);
 }
 
 static int netlink_release(struct socket *sock)
-- 
2.7.4


From 4607b73cf2c5ba9a7c8673e2fc755141f16abbb8 Mon Sep 17 00:00:00 2001
From: Cyrille Pitchen <cyrille.pitchen@atmel.com>
Date: Mon, 28 Nov 2016 14:40:55 +0100
Subject: [PATCH 19/34] net: macb: fix the RX queue reset in macb_rx()

[ Upstream commit a0b44eea372b449ef9744fb1d90491cc063289b8 ]

On macb only (not gem), when a RX queue corruption was detected from
macb_rx(), the RX queue was reset: during this process the RX ring
buffer descriptor was initialized by macb_init_rx_ring() but we forgot
to also set bp->rx_tail to 0.

Indeed, when processing the received frames, bp->rx_tail provides the
macb driver with the index in the RX ring buffer of the next buffer to
process. So when the whole ring buffer is reset we must also reset
bp->rx_tail so the driver is synchronized again with the hardware.

Since macb_init_rx_ring() is called from many locations, currently from
macb_rx() and macb_init_rings(), we'd rather add the "bp->rx_tail = 0;"
line inside macb_init_rx_ring() than add the very same line after each
call of this function.

Without this fix, the rx queue is not reset properly to recover from
queue corruption and connection drop may occur.

Signed-off-by: Cyrille Pitchen <cyrille.pitchen@atmel.com>
Fixes: 9ba723b081a2 ("net: macb: remove BUG_ON() and reset the queue to handle RX errors")
Acked-by: Nicolas Ferre <nicolas.ferre@atmel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index d954a97..ef0dbcf 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -959,6 +959,7 @@ static inline void macb_init_rx_ring(struct macb *bp)
 		addr += bp->rx_buffer_size;
 	}
 	bp->rx_ring[RX_RING_SIZE - 1].addr |= MACB_BIT(RX_WRAP);
+	bp->rx_tail = 0;
 }
 
 static int macb_rx(struct macb *bp, int budget)
@@ -1597,8 +1598,6 @@ static void macb_init_rings(struct macb *bp)
 	bp->queues[0].tx_head = 0;
 	bp->queues[0].tx_tail = 0;
 	bp->queues[0].tx_ring[TX_RING_SIZE - 1].ctrl |= MACB_BIT(TX_WRAP);
-
-	bp->rx_tail = 0;
 }
 
 static void macb_reset_hw(struct macb *bp)
-- 
2.7.4


From cfdc69929ffe62384a46ebb8d369c039ef01a12d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 28 Nov 2016 06:26:49 -0800
Subject: [PATCH 20/34] net/dccp: fix use-after-free in dccp_invalid_packet

[ Upstream commit 648f0c28df282636c0c8a7a19ca3ce5fc80a39c3 ]

pskb_may_pull() can reallocate skb->head, we need to reload dh pointer
in dccp_invalid_packet() or risk use after free.

Bug found by Andrey Konovalov using syzkaller.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ipv4.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index b567c87..edbe59d 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -700,6 +700,7 @@ int dccp_invalid_packet(struct sk_buff *skb)
 {
 	const struct dccp_hdr *dh;
 	unsigned int cscov;
+	u8 dccph_doff;
 
 	if (skb->pkt_type != PACKET_HOST)
 		return 1;
@@ -721,18 +722,19 @@ int dccp_invalid_packet(struct sk_buff *skb)
 	/*
 	 * If P.Data Offset is too small for packet type, drop packet and return
 	 */
-	if (dh->dccph_doff < dccp_hdr_len(skb) / sizeof(u32)) {
-		DCCP_WARN("P.Data Offset(%u) too small\n", dh->dccph_doff);
+	dccph_doff = dh->dccph_doff;
+	if (dccph_doff < dccp_hdr_len(skb) / sizeof(u32)) {
+		DCCP_WARN("P.Data Offset(%u) too small\n", dccph_doff);
 		return 1;
 	}
 	/*
 	 * If P.Data Offset is too too large for packet, drop packet and return
 	 */
-	if (!pskb_may_pull(skb, dh->dccph_doff * sizeof(u32))) {
-		DCCP_WARN("P.Data Offset(%u) too large\n", dh->dccph_doff);
+	if (!pskb_may_pull(skb, dccph_doff * sizeof(u32))) {
+		DCCP_WARN("P.Data Offset(%u) too large\n", dccph_doff);
 		return 1;
 	}
-
+	dh = dccp_hdr(skb);
 	/*
 	 * If P.type is not Data, Ack, or DataAck and P.X == 0 (the packet
 	 * has short sequence numbers), drop packet and return
-- 
2.7.4


From 0f7cbf5c951a73440ccc96d23ee6711729ff2570 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@kernel.org>
Date: Mon, 28 Nov 2016 12:36:58 -0300
Subject: [PATCH 21/34] GSO: Reload iph after pskb_may_pull

[ Upstream commit a510887824171ad260cc4a2603396c6247fdd091 ]

As it may get stale and lead to use after free.

Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Alexander Duyck <aduyck@mirantis.com>
Cc: Andrey Konovalov <andreyknvl@google.com>
Fixes: cbc53e08a793 ("GSO: Add GSO type for fixed IPv4 ID")
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/af_inet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index eebbc0f..ed22af6 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1237,7 +1237,7 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 		fixedid = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TCP_FIXEDID);
 
 		/* fixed ID is invalid if DF bit is not set */
-		if (fixedid && !(iph->frag_off & htons(IP_DF)))
+		if (fixedid && !(ip_hdr(skb)->frag_off & htons(IP_DF)))
 			goto out;
 	}
 
-- 
2.7.4


From 3db24d3eb1bee8ec748256cbf6eb50b4f6b2e3f4 Mon Sep 17 00:00:00 2001
From: Philip Pettersson <philip.pettersson@gmail.com>
Date: Wed, 30 Nov 2016 14:55:36 -0800
Subject: [PATCH 22/34] packet: fix race condition in packet_set_ring

[ Upstream commit 84ac7260236a49c79eede91617700174c2c19b0c ]

When packet_set_ring creates a ring buffer it will initialize a
struct timer_list if the packet version is TPACKET_V3. This value
can then be raced by a different thread calling setsockopt to
set the version to TPACKET_V1 before packet_set_ring has finished.

This leads to a use-after-free on a function pointer in the
struct timer_list when the socket is closed as the previously
initialized timer will not be deleted.

The bug is fixed by taking lock_sock(sk) in packet_setsockopt when
changing the packet version while also taking the lock at the start
of packet_set_ring.

Fixes: f6fb8f100b80 ("af-packet: TPACKET_V3 flexible buffer implementation.")
Signed-off-by: Philip Pettersson <philip.pettersson@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index d2238b2..dd23323 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3648,19 +3648,25 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 
 		if (optlen != sizeof(val))
 			return -EINVAL;
-		if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
-			return -EBUSY;
 		if (copy_from_user(&val, optval, sizeof(val)))
 			return -EFAULT;
 		switch (val) {
 		case TPACKET_V1:
 		case TPACKET_V2:
 		case TPACKET_V3:
-			po->tp_version = val;
-			return 0;
+			break;
 		default:
 			return -EINVAL;
 		}
+		lock_sock(sk);
+		if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+			ret = -EBUSY;
+		} else {
+			po->tp_version = val;
+			ret = 0;
+		}
+		release_sock(sk);
+		return ret;
 	}
 	case PACKET_RESERVE:
 	{
@@ -4164,6 +4170,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 	/* Added to avoid minimal code churn */
 	struct tpacket_req *req = &req_u->req;
 
+	lock_sock(sk);
 	/* Opening a Tx-ring is NOT supported in TPACKET_V3 */
 	if (!closing && tx_ring && (po->tp_version > TPACKET_V2)) {
 		net_warn_ratelimited("Tx-ring is not supported.\n");
@@ -4245,7 +4252,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 			goto out;
 	}
 
-	lock_sock(sk);
 
 	/* Detach socket from network */
 	spin_lock(&po->bind_lock);
@@ -4294,11 +4300,11 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 		if (!tx_ring)
 			prb_shutdown_retire_blk_timer(po, rb_queue);
 	}
-	release_sock(sk);
 
 	if (pg_vec)
 		free_pg_vec(pg_vec, order, req->tp_block_nr);
 out:
+	release_sock(sk);
 	return err;
 }
 
-- 
2.7.4


From eb6be923635a30c450d2f0bcdf8d21cf91a453b4 Mon Sep 17 00:00:00 2001
From: Artem Savkov <asavkov@redhat.com>
Date: Thu, 1 Dec 2016 14:06:04 +0100
Subject: [PATCH 23/34] ip6_offload: check segs for NULL in ipv6_gso_segment.

[ Upstream commit 6b6ebb6b01c873d0cfe3449e8a1219ee6e5fc022 ]

segs needs to be checked for being NULL in ipv6_gso_segment() before calling
skb_shinfo(segs), otherwise kernel can run into a NULL-pointer dereference:

[   97.811262] BUG: unable to handle kernel NULL pointer dereference at 00000000000000cc
[   97.819112] IP: [<ffffffff816e52f9>] ipv6_gso_segment+0x119/0x2f0
[   97.825214] PGD 0 [   97.827047]
[   97.828540] Oops: 0000 [#1] SMP
[   97.831678] Modules linked in: vhost_net vhost macvtap macvlan nfsv3 rpcsec_gss_krb5
nfsv4 dns_resolver nfs fscache xt_CHECKSUM iptable_mangle ipt_MASQUERADE nf_nat_masquerade_ipv4
iptable_nat nf_nat_ipv4 nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_conntrack nf_conntrack
ipt_REJECT nf_reject_ipv4 tun ebtable_filter ebtables ip6table_filter ip6_tables iptable_filter
bridge stp llc snd_hda_codec_realtek snd_hda_codec_hdmi snd_hda_codec_generic snd_hda_intel
snd_hda_codec edac_mce_amd snd_hda_core edac_core snd_hwdep kvm_amd snd_seq kvm snd_seq_device
snd_pcm irqbypass snd_timer ppdev parport_serial snd parport_pc k10temp pcspkr soundcore parport
sp5100_tco shpchp sg wmi i2c_piix4 acpi_cpufreq nfsd auth_rpcgss nfs_acl lockd grace sunrpc
ip_tables xfs libcrc32c sr_mod cdrom sd_mod ata_generic pata_acpi amdkfd amd_iommu_v2 radeon
broadcom bcm_phy_lib i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops
ttm ahci serio_raw tg3 firewire_ohci libahci pata_atiixp drm ptp libata firewire_core pps_core
i2c_core crc_itu_t fjes dm_mirror dm_region_hash dm_log dm_mod
[   97.927721] CPU: 1 PID: 3504 Comm: vhost-3495 Not tainted 4.9.0-7.el7.test.x86_64 #1
[   97.935457] Hardware name: AMD Snook/Snook, BIOS ESK0726A 07/26/2010
[   97.941806] task: ffff880129a1c080 task.stack: ffffc90001bcc000
[   97.947720] RIP: 0010:[<ffffffff816e52f9>]  [<ffffffff816e52f9>] ipv6_gso_segment+0x119/0x2f0
[   97.956251] RSP: 0018:ffff88012fc43a10  EFLAGS: 00010207
[   97.961557] RAX: 0000000000000000 RBX: ffff8801292c8700 RCX: 0000000000000594
[   97.968687] RDX: 0000000000000593 RSI: ffff880129a846c0 RDI: 0000000000240000
[   97.975814] RBP: ffff88012fc43a68 R08: ffff880129a8404e R09: 0000000000000000
[   97.982942] R10: 0000000000000000 R11: ffff880129a84076 R12: 00000020002949b3
[   97.990070] R13: ffff88012a580000 R14: 0000000000000000 R15: ffff88012a580000
[   97.997198] FS:  0000000000000000(0000) GS:ffff88012fc40000(0000) knlGS:0000000000000000
[   98.005280] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   98.011021] CR2: 00000000000000cc CR3: 0000000126c5d000 CR4: 00000000000006e0
[   98.018149] Stack:
[   98.020157]  00000000ffffffff ffff88012fc43ac8 ffffffffa017ad0a 000000000000000e
[   98.027584]  0000001300000000 0000000077d59998 ffff8801292c8700 00000020002949b3
[   98.035010]  ffff88012a580000 0000000000000000 ffff88012a580000 ffff88012fc43a98
[   98.042437] Call Trace:
[   98.044879]  <IRQ> [   98.046803]  [<ffffffffa017ad0a>] ? tg3_start_xmit+0x84a/0xd60 [tg3]
[   98.053156]  [<ffffffff815eeee0>] skb_mac_gso_segment+0xb0/0x130
[   98.059158]  [<ffffffff815eefd3>] __skb_gso_segment+0x73/0x110
[   98.064985]  [<ffffffff815ef40d>] validate_xmit_skb+0x12d/0x2b0
[   98.070899]  [<ffffffff815ef5d2>] validate_xmit_skb_list+0x42/0x70
[   98.077073]  [<ffffffff81618560>] sch_direct_xmit+0xd0/0x1b0
[   98.082726]  [<ffffffff815efd86>] __dev_queue_xmit+0x486/0x690
[   98.088554]  [<ffffffff8135c135>] ? cpumask_next_and+0x35/0x50
[   98.094380]  [<ffffffff815effa0>] dev_queue_xmit+0x10/0x20
[   98.099863]  [<ffffffffa09ce057>] br_dev_queue_push_xmit+0xa7/0x170 [bridge]
[   98.106907]  [<ffffffffa09ce161>] br_forward_finish+0x41/0xc0 [bridge]
[   98.113430]  [<ffffffff81627cf2>] ? nf_iterate+0x52/0x60
[   98.118735]  [<ffffffff81627d6b>] ? nf_hook_slow+0x6b/0xc0
[   98.124216]  [<ffffffffa09ce32c>] __br_forward+0x14c/0x1e0 [bridge]
[   98.130480]  [<ffffffffa09ce120>] ? br_dev_queue_push_xmit+0x170/0x170 [bridge]
[   98.137785]  [<ffffffffa09ce4bd>] br_forward+0x9d/0xb0 [bridge]
[   98.143701]  [<ffffffffa09cfbb7>] br_handle_frame_finish+0x267/0x560 [bridge]
[   98.150834]  [<ffffffffa09d0064>] br_handle_frame+0x174/0x2f0 [bridge]
[   98.157355]  [<ffffffff8102fb89>] ? sched_clock+0x9/0x10
[   98.162662]  [<ffffffff810b63b2>] ? sched_clock_cpu+0x72/0xa0
[   98.168403]  [<ffffffff815eccf5>] __netif_receive_skb_core+0x1e5/0xa20
[   98.174926]  [<ffffffff813659f9>] ? timerqueue_add+0x59/0xb0
[   98.180580]  [<ffffffff815ed548>] __netif_receive_skb+0x18/0x60
[   98.186494]  [<ffffffff815ee625>] process_backlog+0x95/0x140
[   98.192145]  [<ffffffff815edccd>] net_rx_action+0x16d/0x380
[   98.197713]  [<ffffffff8170cff1>] __do_softirq+0xd1/0x283
[   98.203106]  [<ffffffff8170b2bc>] do_softirq_own_stack+0x1c/0x30
[   98.209107]  <EOI> [   98.211029]  [<ffffffff8108a5c0>] do_softirq+0x50/0x60
[   98.216166]  [<ffffffff815ec853>] netif_rx_ni+0x33/0x80
[   98.221386]  [<ffffffffa09eeff7>] tun_get_user+0x487/0x7f0 [tun]
[   98.227388]  [<ffffffffa09ef3ab>] tun_sendmsg+0x4b/0x60 [tun]
[   98.233129]  [<ffffffffa0b68932>] handle_tx+0x282/0x540 [vhost_net]
[   98.239392]  [<ffffffffa0b68c25>] handle_tx_kick+0x15/0x20 [vhost_net]
[   98.245916]  [<ffffffffa0abacfe>] vhost_worker+0x9e/0xf0 [vhost]
[   98.251919]  [<ffffffffa0abac60>] ? vhost_umem_alloc+0x40/0x40 [vhost]
[   98.258440]  [<ffffffff81003a47>] ? do_syscall_64+0x67/0x180
[   98.264094]  [<ffffffff810a44d9>] kthread+0xd9/0xf0
[   98.268965]  [<ffffffff810a4400>] ? kthread_park+0x60/0x60
[   98.274444]  [<ffffffff8170a4d5>] ret_from_fork+0x25/0x30
[   98.279836] Code: 8b 93 d8 00 00 00 48 2b 93 d0 00 00 00 4c 89 e6 48 89 df 66 89 93 c2 00 00 00 ff 10 48 3d 00 f0 ff ff 49 89 c2 0f 87 52 01 00 00 <41> 8b 92 cc 00 00 00 48 8b 80 d0 00 00 00 44 0f b7 74 10 06 66
[   98.299425] RIP  [<ffffffff816e52f9>] ipv6_gso_segment+0x119/0x2f0
[   98.305612]  RSP <ffff88012fc43a10>
[   98.309094] CR2: 00000000000000cc
[   98.312406] ---[ end trace 726a2c7a2d2d78d0 ]---

Signed-off-by: Artem Savkov <asavkov@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_offload.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index a09418b..93294cf 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -98,7 +98,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 		segs = ops->callbacks.gso_segment(skb, features);
 	}
 
-	if (IS_ERR(segs))
+	if (IS_ERR_OR_NULL(segs))
 		goto out;
 
 	for (skb = segs; skb; skb = skb->next) {
-- 
2.7.4


From 17878cc58d08b7e8598551feb447af68bc25dc8c Mon Sep 17 00:00:00 2001
From: Kristian Evensen <kristian.evensen@gmail.com>
Date: Thu, 1 Dec 2016 14:23:17 +0100
Subject: [PATCH 24/34] cdc_ether: Fix handling connection notification
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit d5c83d0d1d83b3798c71e0c8b7c3624d39c91d88 ]

Commit bfe9b9d2df66 ("cdc_ether: Improve ZTE MF823/831/910 handling")
introduced a work-around in usbnet_cdc_status() for devices that exported
cdc carrier on twice on connect. Before the commit, this behavior caused
the link state to be incorrect. It was assumed that all CDC Ethernet
devices would either export this behavior, or send one off and then one on
notification (which seems to be the default behavior).

Unfortunately, it turns out multiple devices sends a connection
notification multiple times per second (via an interrupt), even when
connection state does not change. This has been observed with several
different USB LAN dongles (at least), for example 13b1:0041 (Linksys).
After bfe9b9d2df66, the link state has been set as down and then up for
each notification. This has caused a flood of Netlink NEWLINK messages and
syslog to be flooded with messages similar to:

cdc_ether 2-1:2.0 eth1: kevent 12 may have been dropped

This commit fixes the behavior by reverting usbnet_cdc_status() to how it
was before bfe9b9d2df66. The work-around has been moved to a separate
status-function which is only called when a known, affect device is
detected.

v1->v2:

* Do not open-code netif_carrier_ok() (thanks Henning Schild).
* Call netif_carrier_off() instead of usb_link_change(). This prevents
calling schedule_work() twice without giving the work queue a chance to be
processed (thanks Bjørn Mork).

Fixes: bfe9b9d2df66 ("cdc_ether: Improve ZTE MF823/831/910 handling")
Reported-by: Henning Schild <henning.schild@siemens.com>
Signed-off-by: Kristian Evensen <kristian.evensen@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ether.c | 38 +++++++++++++++++++++++++++++++-------
 1 file changed, 31 insertions(+), 7 deletions(-)

diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index c47ec0a..dd623f6 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -388,12 +388,6 @@ void usbnet_cdc_status(struct usbnet *dev, struct urb *urb)
 	case USB_CDC_NOTIFY_NETWORK_CONNECTION:
 		netif_dbg(dev, timer, dev->net, "CDC: carrier %s\n",
 			  event->wValue ? "on" : "off");
-
-		/* Work-around for devices with broken off-notifications */
-		if (event->wValue &&
-		    !test_bit(__LINK_STATE_NOCARRIER, &dev->net->state))
-			usbnet_link_change(dev, 0, 0);
-
 		usbnet_link_change(dev, !!event->wValue, 0);
 		break;
 	case USB_CDC_NOTIFY_SPEED_CHANGE:	/* tx/rx rates */
@@ -466,6 +460,36 @@ static int usbnet_cdc_zte_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 	return 1;
 }
 
+/* Ensure correct link state
+ *
+ * Some devices (ZTE MF823/831/910) export two carrier on notifications when
+ * connected. This causes the link state to be incorrect. Work around this by
+ * always setting the state to off, then on.
+ */
+void usbnet_cdc_zte_status(struct usbnet *dev, struct urb *urb)
+{
+	struct usb_cdc_notification *event;
+
+	if (urb->actual_length < sizeof(*event))
+		return;
+
+	event = urb->transfer_buffer;
+
+	if (event->bNotificationType != USB_CDC_NOTIFY_NETWORK_CONNECTION) {
+		usbnet_cdc_status(dev, urb);
+		return;
+	}
+
+	netif_dbg(dev, timer, dev->net, "CDC: carrier %s\n",
+		  event->wValue ? "on" : "off");
+
+	if (event->wValue &&
+	    netif_carrier_ok(dev->net))
+		netif_carrier_off(dev->net);
+
+	usbnet_link_change(dev, !!event->wValue, 0);
+}
+
 static const struct driver_info	cdc_info = {
 	.description =	"CDC Ethernet Device",
 	.flags =	FLAG_ETHER | FLAG_POINTTOPOINT,
@@ -481,7 +505,7 @@ static const struct driver_info	zte_cdc_info = {
 	.flags =	FLAG_ETHER | FLAG_POINTTOPOINT,
 	.bind =		usbnet_cdc_zte_bind,
 	.unbind =	usbnet_cdc_unbind,
-	.status =	usbnet_cdc_status,
+	.status =	usbnet_cdc_zte_status,
 	.set_rx_mode =	usbnet_cdc_update_filter,
 	.manage_power =	usbnet_manage_power,
 	.rx_fixup = usbnet_cdc_zte_rx_fixup,
-- 
2.7.4


From bd06898445ab6e15c8a5401c70f33952592276a1 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 1 Dec 2016 09:45:45 -0800
Subject: [PATCH 25/34] net: bcmgenet: Utilize correct struct device for all
 DMA operations

[ Upstream commit 8c4799ac799665065f9bf1364fd71bf4f7dc6a4a ]

__bcmgenet_tx_reclaim() and bcmgenet_free_rx_buffers() are not using the
same struct device during unmap that was used for the map operation,
which makes DMA-API debugging warn about it. Fix this by always using
&priv->pdev->dev throughout the driver, using an identical device
reference for all map/unmap calls.

Fixes: 1c1008c793fa ("net: bcmgenet: add main driver file")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 5414563..842d8b9 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -1172,6 +1172,7 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
 					  struct bcmgenet_tx_ring *ring)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
+	struct device *kdev = &priv->pdev->dev;
 	struct enet_cb *tx_cb_ptr;
 	struct netdev_queue *txq;
 	unsigned int pkts_compl = 0;
@@ -1199,13 +1200,13 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
 		if (tx_cb_ptr->skb) {
 			pkts_compl++;
 			bytes_compl += GENET_CB(tx_cb_ptr->skb)->bytes_sent;
-			dma_unmap_single(&dev->dev,
+			dma_unmap_single(kdev,
 					 dma_unmap_addr(tx_cb_ptr, dma_addr),
 					 dma_unmap_len(tx_cb_ptr, dma_len),
 					 DMA_TO_DEVICE);
 			bcmgenet_free_cb(tx_cb_ptr);
 		} else if (dma_unmap_addr(tx_cb_ptr, dma_addr)) {
-			dma_unmap_page(&dev->dev,
+			dma_unmap_page(kdev,
 				       dma_unmap_addr(tx_cb_ptr, dma_addr),
 				       dma_unmap_len(tx_cb_ptr, dma_len),
 				       DMA_TO_DEVICE);
@@ -1775,6 +1776,7 @@ static int bcmgenet_alloc_rx_buffers(struct bcmgenet_priv *priv,
 
 static void bcmgenet_free_rx_buffers(struct bcmgenet_priv *priv)
 {
+	struct device *kdev = &priv->pdev->dev;
 	struct enet_cb *cb;
 	int i;
 
@@ -1782,7 +1784,7 @@ static void bcmgenet_free_rx_buffers(struct bcmgenet_priv *priv)
 		cb = &priv->rx_cbs[i];
 
 		if (dma_unmap_addr(cb, dma_addr)) {
-			dma_unmap_single(&priv->dev->dev,
+			dma_unmap_single(kdev,
 					 dma_unmap_addr(cb, dma_addr),
 					 priv->rx_buf_len, DMA_FROM_DEVICE);
 			dma_unmap_addr_set(cb, dma_addr, 0);
-- 
2.7.4


From 76250e2ef2777afadc6d5ac9df302ce3bf2a4fc4 Mon Sep 17 00:00:00 2001
From: Chris Brandt <chris.brandt@renesas.com>
Date: Thu, 1 Dec 2016 13:32:14 -0500
Subject: [PATCH 26/34] sh_eth: remove unchecked interrupts for RZ/A1

[ Upstream commit 33d446dbba4d4d6a77e1e900d434fa99e0f02c86 ]

When streaming a lot of data and the RZ/A1 can't keep up, some status bits
will get set that are not being checked or cleared which cause the
following messages and the Ethernet driver to stop working. This
patch fixes that issue.

irq 21: nobody cared (try booting with the "irqpoll" option)
handlers:
[<c036b71c>] sh_eth_interrupt
Disabling IRQ #21

Fixes: db893473d313a4ad ("sh_eth: Add support for r7s72100")
Signed-off-by: Chris Brandt <chris.brandt@renesas.com>
Acked-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/sh_eth.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 054e795..92c9a95 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -518,7 +518,7 @@ static struct sh_eth_cpu_data r7s72100_data = {
 
 	.ecsr_value	= ECSR_ICD,
 	.ecsipr_value	= ECSIPR_ICDIP,
-	.eesipr_value	= 0xff7f009f,
+	.eesipr_value	= 0xe77f009f,
 
 	.tx_check	= EESR_TC1 | EESR_FTC,
 	.eesr_err_check	= EESR_TWB1 | EESR_TWB | EESR_TABT | EESR_RABT |
-- 
2.7.4


From 998c28dc363b2f2e99293e63d69a03a6fccd50cd Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Michal=20Kube=C4=8Dek?= <mkubecek@suse.cz>
Date: Fri, 2 Dec 2016 09:33:41 +0100
Subject: [PATCH 27/34] tipc: check minimum bearer MTU
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 3de81b758853f0b29c61e246679d20b513c4cfec ]

Qian Zhang (张谦) reported a potential socket buffer overflow in
tipc_msg_build() which is also known as CVE-2016-8632: due to
insufficient checks, a buffer overflow can occur if MTU is too short for
even tipc headers. As anyone can set device MTU in a user/net namespace,
this issue can be abused by a regular user.

As agreed in the discussion on Ben Hutchings' original patch, we should
check the MTU at the moment a bearer is attached rather than for each
processed packet. We also need to repeat the check when bearer MTU is
adjusted to new device MTU. UDP case also needs a check to avoid
overflow when calculating bearer MTU.

Fixes: b97bf3fd8f6a ("[TIPC] Initial merge")
Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Reported-by: Qian Zhang (张谦) <zhangqian-c@360.cn>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/bearer.c    | 11 +++++++++--
 net/tipc/bearer.h    | 13 +++++++++++++
 net/tipc/udp_media.c |  5 +++++
 3 files changed, 27 insertions(+), 2 deletions(-)

diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index 65b1bbf..6167699 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -402,6 +402,10 @@ int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b,
 	dev = dev_get_by_name(net, driver_name);
 	if (!dev)
 		return -ENODEV;
+	if (tipc_mtu_bad(dev, 0)) {
+		dev_put(dev);
+		return -EINVAL;
+	}
 
 	/* Associate TIPC bearer with L2 bearer */
 	rcu_assign_pointer(b->media_ptr, dev);
@@ -606,8 +610,6 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt,
 	if (!b)
 		return NOTIFY_DONE;
 
-	b->mtu = dev->mtu;
-
 	switch (evt) {
 	case NETDEV_CHANGE:
 		if (netif_carrier_ok(dev))
@@ -621,6 +623,11 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt,
 		tipc_reset_bearer(net, b);
 		break;
 	case NETDEV_CHANGEMTU:
+		if (tipc_mtu_bad(dev, 0)) {
+			bearer_disable(net, b);
+			break;
+		}
+		b->mtu = dev->mtu;
 		tipc_reset_bearer(net, b);
 		break;
 	case NETDEV_CHANGEADDR:
diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h
index 43757f1..d93f1f1 100644
--- a/net/tipc/bearer.h
+++ b/net/tipc/bearer.h
@@ -39,6 +39,7 @@
 
 #include "netlink.h"
 #include "core.h"
+#include "msg.h"
 #include <net/genetlink.h>
 
 #define MAX_MEDIA	3
@@ -59,6 +60,9 @@
 #define TIPC_MEDIA_TYPE_IB	2
 #define TIPC_MEDIA_TYPE_UDP	3
 
+/* minimum bearer MTU */
+#define TIPC_MIN_BEARER_MTU	(MAX_H_SIZE + INT_H_SIZE)
+
 /**
  * struct tipc_media_addr - destination address used by TIPC bearers
  * @value: address info (format defined by media)
@@ -213,4 +217,13 @@ void tipc_bearer_xmit(struct net *net, u32 bearer_id,
 void tipc_bearer_bc_xmit(struct net *net, u32 bearer_id,
 			 struct sk_buff_head *xmitq);
 
+/* check if device MTU is too low for tipc headers */
+static inline bool tipc_mtu_bad(struct net_device *dev, unsigned int reserve)
+{
+	if (dev->mtu >= TIPC_MIN_BEARER_MTU + reserve)
+		return false;
+	netdev_warn(dev, "MTU too low for tipc bearer\n");
+	return true;
+}
+
 #endif	/* _TIPC_BEARER_H */
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index ae7e14c..f60f346 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -372,6 +372,11 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b,
 		udp_conf.local_ip.s_addr = htonl(INADDR_ANY);
 		udp_conf.use_udp_checksums = false;
 		ub->ifindex = dev->ifindex;
+		if (tipc_mtu_bad(dev, sizeof(struct iphdr) +
+				      sizeof(struct udphdr))) {
+			err = -EINVAL;
+			goto err;
+		}
 		b->mtu = dev->mtu - sizeof(struct iphdr)
 			- sizeof(struct udphdr);
 #if IS_ENABLED(CONFIG_IPV6)
-- 
2.7.4


From 4a52078557945028bd40e5a0c119893cd49a122e Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 2 Dec 2016 16:49:29 +0100
Subject: [PATCH 28/34] geneve: avoid use-after-free of skb->data

[ Upstream commit 5b01014759991887b1e450c9def01e58c02ab81b ]

geneve{,6}_build_skb can end up doing a pskb_expand_head(), which
makes the ip_hdr(skb) reference we stashed earlier stale. Since it's
only needed as an argument to ip_tunnel_ecn_encap(), move this
directly in the function call.

Fixes: 08399efc6319 ("geneve: ensure ECN info is handled properly in all tx/rx paths")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: John W. Linville <linville@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c | 14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 16af1ce..5ad706b 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -844,7 +844,6 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	struct geneve_dev *geneve = netdev_priv(dev);
 	struct geneve_sock *gs4 = geneve->sock4;
 	struct rtable *rt = NULL;
-	const struct iphdr *iip; /* interior IP header */
 	int err = -EINVAL;
 	struct flowi4 fl4;
 	__u8 tos, ttl;
@@ -871,8 +870,6 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
 	skb_reset_mac_header(skb);
 
-	iip = ip_hdr(skb);
-
 	if (info) {
 		const struct ip_tunnel_key *key = &info->key;
 		u8 *opts = NULL;
@@ -892,7 +889,7 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 		if (unlikely(err))
 			goto tx_error;
 
-		tos = ip_tunnel_ecn_encap(key->tos, iip, skb);
+		tos = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb);
 		ttl = key->ttl;
 		df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0;
 	} else {
@@ -901,7 +898,7 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 		if (unlikely(err))
 			goto tx_error;
 
-		tos = ip_tunnel_ecn_encap(fl4.flowi4_tos, iip, skb);
+		tos = ip_tunnel_ecn_encap(fl4.flowi4_tos, ip_hdr(skb), skb);
 		ttl = geneve->ttl;
 		if (!ttl && IN_MULTICAST(ntohl(fl4.daddr)))
 			ttl = 1;
@@ -934,7 +931,6 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	struct geneve_dev *geneve = netdev_priv(dev);
 	struct geneve_sock *gs6 = geneve->sock6;
 	struct dst_entry *dst = NULL;
-	const struct iphdr *iip; /* interior IP header */
 	int err = -EINVAL;
 	struct flowi6 fl6;
 	__u8 prio, ttl;
@@ -959,8 +955,6 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
 	skb_reset_mac_header(skb);
 
-	iip = ip_hdr(skb);
-
 	if (info) {
 		const struct ip_tunnel_key *key = &info->key;
 		u8 *opts = NULL;
@@ -981,7 +975,7 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 		if (unlikely(err))
 			goto tx_error;
 
-		prio = ip_tunnel_ecn_encap(key->tos, iip, skb);
+		prio = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb);
 		ttl = key->ttl;
 		label = info->key.label;
 	} else {
@@ -991,7 +985,7 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 			goto tx_error;
 
 		prio = ip_tunnel_ecn_encap(ip6_tclass(fl6.flowlabel),
-					   iip, skb);
+					   ip_hdr(skb), skb);
 		ttl = geneve->ttl;
 		if (!ttl && ipv6_addr_is_multicast(&fl6.daddr))
 			ttl = 1;
-- 
2.7.4


From 7d6f4906208c1db6f94efc2ddde428b9e8fe10b5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 2 Dec 2016 09:44:53 -0800
Subject: [PATCH 29/34] net: avoid signed overflows for SO_{SND|RCV}BUFFORCE

[ Upstream commit b98b0bc8c431e3ceb4b26b0dfc8db509518fb290 ]

CAP_NET_ADMIN users should not be allowed to set negative
sk_sndbuf or sk_rcvbuf values, as it can lead to various memory
corruptions, crashes, OOM...

Note that before commit 82981930125a ("net: cleanups in
sock_setsockopt()"), the bug was even more serious, since SO_SNDBUF
and SO_RCVBUF were vulnerable.

This needs to be backported to all known linux kernels.

Again, many thanks to syzkaller team for discovering this gem.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index 10acacc..ba27920 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -715,7 +715,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
 		val = min_t(u32, val, sysctl_wmem_max);
 set_sndbuf:
 		sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
-		sk->sk_sndbuf = max_t(u32, val * 2, SOCK_MIN_SNDBUF);
+		sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF);
 		/* Wake up sending tasks if we upped the value. */
 		sk->sk_write_space(sk);
 		break;
@@ -751,7 +751,7 @@ set_rcvbuf:
 		 * returning the value we actually used in getsockopt
 		 * is the most desirable behavior.
 		 */
-		sk->sk_rcvbuf = max_t(u32, val * 2, SOCK_MIN_RCVBUF);
+		sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF);
 		break;
 
 	case SO_RCVBUFFORCE:
-- 
2.7.4


From 24039400fd0bed27598e40ca21728fa6807b417a Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Mon, 5 Dec 2016 10:34:38 -0800
Subject: [PATCH 30/34] net: ping: check minimum size on ICMP header length

[ Upstream commit 0eab121ef8750a5c8637d51534d5e9143fb0633f ]

Prior to commit c0371da6047a ("put iov_iter into msghdr") in v3.19, there
was no check that the iovec contained enough bytes for an ICMP header,
and the read loop would walk across neighboring stack contents. Since the
iov_iter conversion, bad arguments are noticed, but the returned error is
EFAULT. Returning EINVAL is a clearer error and also solves the problem
prior to v3.19.

This was found using trinity with KASAN on v3.18:

BUG: KASAN: stack-out-of-bounds in memcpy_fromiovec+0x60/0x114 at addr ffffffc071077da0
Read of size 8 by task trinity-c2/9623
page:ffffffbe034b9a08 count:0 mapcount:0 mapping:          (null) index:0x0
flags: 0x0()
page dumped because: kasan: bad access detected
CPU: 0 PID: 9623 Comm: trinity-c2 Tainted: G    BU         3.18.0-dirty #15
Hardware name: Google Tegra210 Smaug Rev 1,3+ (DT)
Call trace:
[<ffffffc000209c98>] dump_backtrace+0x0/0x1ac arch/arm64/kernel/traps.c:90
[<ffffffc000209e54>] show_stack+0x10/0x1c arch/arm64/kernel/traps.c:171
[<     inline     >] __dump_stack lib/dump_stack.c:15
[<ffffffc000f18dc4>] dump_stack+0x7c/0xd0 lib/dump_stack.c:50
[<     inline     >] print_address_description mm/kasan/report.c:147
[<     inline     >] kasan_report_error mm/kasan/report.c:236
[<ffffffc000373dcc>] kasan_report+0x380/0x4b8 mm/kasan/report.c:259
[<     inline     >] check_memory_region mm/kasan/kasan.c:264
[<ffffffc00037352c>] __asan_load8+0x20/0x70 mm/kasan/kasan.c:507
[<ffffffc0005b9624>] memcpy_fromiovec+0x5c/0x114 lib/iovec.c:15
[<     inline     >] memcpy_from_msg include/linux/skbuff.h:2667
[<ffffffc000ddeba0>] ping_common_sendmsg+0x50/0x108 net/ipv4/ping.c:674
[<ffffffc000dded30>] ping_v4_sendmsg+0xd8/0x698 net/ipv4/ping.c:714
[<ffffffc000dc91dc>] inet_sendmsg+0xe0/0x12c net/ipv4/af_inet.c:749
[<     inline     >] __sock_sendmsg_nosec net/socket.c:624
[<     inline     >] __sock_sendmsg net/socket.c:632
[<ffffffc000cab61c>] sock_sendmsg+0x124/0x164 net/socket.c:643
[<     inline     >] SYSC_sendto net/socket.c:1797
[<ffffffc000cad270>] SyS_sendto+0x178/0x1d8 net/socket.c:1761

CVE-2016-8399

Reported-by: Qidan He <i@flanker017.me>
Fixes: c319b4d76b9e ("net: ipv4: add IPPROTO_ICMP socket kind")
Cc: stable@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ping.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 66ddcb6..dcdd5ae 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -662,6 +662,10 @@ int ping_common_sendmsg(int family, struct msghdr *msg, size_t len,
 	if (len > 0xFFFF)
 		return -EMSGSIZE;
 
+	/* Must have at least a full ICMP header. */
+	if (len < icmph_len)
+		return -EINVAL;
+
 	/*
 	 *	Check the flags.
 	 */
-- 
2.7.4


From dd9f8bff5ebc50d8c756fb1be5827f4b6aecbef7 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Tue, 15 Nov 2016 05:46:06 -0500
Subject: [PATCH 31/34] ipv4: Restore fib_trie_flush_external function and fix
 call ordering

[ Upstream commit 3b7093346b326e5d3590c7d49f6aefe6fa5b2c9a, the FIB offload
  removal didn't occur in 4.8 so that part of this patch isn't here.  However
  we still need to fib_unmerge() bits. ]

The patch that removed the FIB offload infrastructure was a bit too
aggressive and also removed code needed to clean up us splitting the table
if additional rules were added.  Specifically the function
fib_trie_flush_external was called at the end of a new rule being added to
flush the foreign trie entries from the main trie.

I updated the code so that we only call fib_trie_flush_external on the main
table so that we flush the entries for local from main.  This way we don't
call it for every rule change which is what was happening previously.

Fixes: 347e3b28c1ba2 ("switchdev: remove FIB offload infrastructure")
Reported-by: Eric Dumazet <edumazet@google.com>
Cc: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_frontend.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 1b25daf..9301308 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -157,7 +157,7 @@ static void fib_replace_table(struct net *net, struct fib_table *old,
 
 int fib_unmerge(struct net *net)
 {
-	struct fib_table *old, *new;
+	struct fib_table *old, *new, *main_table;
 
 	/* attempt to fetch local table if it has been allocated */
 	old = fib_get_table(net, RT_TABLE_LOCAL);
@@ -168,11 +168,21 @@ int fib_unmerge(struct net *net)
 	if (!new)
 		return -ENOMEM;
 
+	/* table is already unmerged */
+	if (new == old)
+		return 0;
+
 	/* replace merged table with clean table */
-	if (new != old) {
-		fib_replace_table(net, old, new);
-		fib_free_table(old);
-	}
+	fib_replace_table(net, old, new);
+	fib_free_table(old);
+
+	/* attempt to fetch main table if it has been allocated */
+	main_table = fib_get_table(net, RT_TABLE_MAIN);
+	if (!main_table)
+		return 0;
+
+	/* flush local entries from main table */
+	fib_table_flush_external(main_table);
 
 	return 0;
 }
-- 
2.7.4


From b00e25ef8da22eeeb19882bd3b71a41894302e22 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Tue, 15 Nov 2016 05:46:12 -0500
Subject: [PATCH 32/34] ipv4: Fix memory leak in exception case for splitting
 tries

[ Upstream commit 3114cdfe66c156345b0ae34e2990472f277e0c1b ]

Fix a small memory leak that can occur where we leak a fib_alias in the
event of us not being able to insert it into the local table.

Fixes: 0ddcf43d5d4a0 ("ipv4: FIB Local/MAIN table collapse")
Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_trie.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 7ef7031..79ff363 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1713,8 +1713,10 @@ struct fib_table *fib_trie_unmerge(struct fib_table *oldtb)
 				local_l = fib_find_node(lt, &local_tp, l->key);
 
 			if (fib_insert_alias(lt, local_tp, local_l, new_fa,
-					     NULL, l->key))
+					     NULL, l->key)) {
+				kmem_cache_free(fn_alias_kmem, new_fa);
 				goto out;
+			}
 		}
 
 		/* stop loop if key wrapped back to 0 */
-- 
2.7.4


From cfd8fdccd9702ae7f18009b5b7e63eba43fa2761 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Thu, 1 Dec 2016 07:27:52 -0500
Subject: [PATCH 33/34] ipv4: Drop leaf from suffix pull/push functions

[ Upstream commit 1a239173cccff726b60ac6a9c79ae4a1e26cfa49 ]

It wasn't necessary to pass a leaf in when doing the suffix updates so just
drop it.  Instead just pass the suffix and work with that.

Since we dropped the leaf there is no need to include that in the name so
the names are updated to node_push_suffix and node_pull_suffix.

Finally I noticed that the logic for pulling the suffix length back
actually had some issues.  Specifically it would stop prematurely if there
was a longer suffix, but it was not as long as the original suffix.  I
updated the code to address that in node_pull_suffix.

Fixes: 5405afd1a306 ("fib_trie: Add tracking value for suffix length")
Suggested-by: Robert Shearman <rshearma@brocade.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Reviewed-by: Robert Shearman <rshearma@brocade.com>
Tested-by: Robert Shearman <rshearma@brocade.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_trie.c | 26 ++++++++++++++------------
 1 file changed, 14 insertions(+), 12 deletions(-)

diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 79ff363..b72d295 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -892,22 +892,24 @@ static struct key_vector *resize(struct trie *t, struct key_vector *tn)
 	return tp;
 }
 
-static void leaf_pull_suffix(struct key_vector *tp, struct key_vector *l)
+static void node_pull_suffix(struct key_vector *tn, unsigned char slen)
 {
-	while ((tp->slen > tp->pos) && (tp->slen > l->slen)) {
-		if (update_suffix(tp) > l->slen)
+	unsigned char node_slen = tn->slen;
+
+	while ((node_slen > tn->pos) && (node_slen > slen)) {
+		slen = update_suffix(tn);
+		if (node_slen == slen)
 			break;
-		tp = node_parent(tp);
+
+		tn = node_parent(tn);
+		node_slen = tn->slen;
 	}
 }
 
-static void leaf_push_suffix(struct key_vector *tn, struct key_vector *l)
+static void node_push_suffix(struct key_vector *tn, unsigned char slen)
 {
-	/* if this is a new leaf then tn will be NULL and we can sort
-	 * out parent suffix lengths as a part of trie_rebalance
-	 */
-	while (tn->slen < l->slen) {
-		tn->slen = l->slen;
+	while (tn->slen < slen) {
+		tn->slen = slen;
 		tn = node_parent(tn);
 	}
 }
@@ -1069,7 +1071,7 @@ static int fib_insert_alias(struct trie *t, struct key_vector *tp,
 	/* if we added to the tail node then we need to update slen */
 	if (l->slen < new->fa_slen) {
 		l->slen = new->fa_slen;
-		leaf_push_suffix(tp, l);
+		node_push_suffix(tp, new->fa_slen);
 	}
 
 	return 0;
@@ -1482,7 +1484,7 @@ static void fib_remove_alias(struct trie *t, struct key_vector *tp,
 
 	/* update the trie with the latest suffix length */
 	l->slen = fa->fa_slen;
-	leaf_pull_suffix(tp, l);
+	node_pull_suffix(tp, fa->fa_slen);
 }
 
 /* Caller must hold RTNL. */
-- 
2.7.4


From c0bdc49390d2307b43bfbc7c2ab61fcb99abec07 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Thu, 1 Dec 2016 07:27:57 -0500
Subject: [PATCH 34/34] ipv4: Drop suffix update from resize code

[ Upstream commit a52ca62c4a6771028da9c1de934cdbcd93d54bb4 ]

It has been reported that update_suffix can be expensive when it is called
on a large node in which most of the suffix lengths are the same.  The time
required to add 200K entries had increased from around 3 seconds to almost
49 seconds.

In order to address this we need to move the code for updating the suffix
out of resize and instead just have it handled in the cases where we are
pushing a node that increases the suffix length, or will decrease the
suffix length.

Fixes: 5405afd1a306 ("fib_trie: Add tracking value for suffix length")
Reported-by: Robert Shearman <rshearma@brocade.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Reviewed-by: Robert Shearman <rshearma@brocade.com>
Tested-by: Robert Shearman <rshearma@brocade.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_trie.c | 42 +++++++++++++++++++++---------------------
 1 file changed, 21 insertions(+), 21 deletions(-)

diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index b72d295..84fd7272 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -681,6 +681,13 @@ static unsigned char update_suffix(struct key_vector *tn)
 {
 	unsigned char slen = tn->pos;
 	unsigned long stride, i;
+	unsigned char slen_max;
+
+	/* only vector 0 can have a suffix length greater than or equal to
+	 * tn->pos + tn->bits, the second highest node will have a suffix
+	 * length at most of tn->pos + tn->bits - 1
+	 */
+	slen_max = min_t(unsigned char, tn->pos + tn->bits - 1, tn->slen);
 
 	/* search though the list of children looking for nodes that might
 	 * have a suffix greater than the one we currently have.  This is
@@ -698,12 +705,8 @@ static unsigned char update_suffix(struct key_vector *tn)
 		slen = n->slen;
 		i &= ~(stride - 1);
 
-		/* if slen covers all but the last bit we can stop here
-		 * there will be nothing longer than that since only node
-		 * 0 and 1 << (bits - 1) could have that as their suffix
-		 * length.
-		 */
-		if ((slen + 1) >= (tn->pos + tn->bits))
+		/* stop searching if we have hit the maximum possible value */
+		if (slen >= slen_max)
 			break;
 	}
 
@@ -875,21 +878,7 @@ static struct key_vector *resize(struct trie *t, struct key_vector *tn)
 		return collapse(t, tn);
 
 	/* update parent in case halve failed */
-	tp = node_parent(tn);
-
-	/* Return if at least one deflate was run */
-	if (max_work != MAX_WORK)
-		return tp;
-
-	/* push the suffix length to the parent node */
-	if (tn->slen > tn->pos) {
-		unsigned char slen = update_suffix(tn);
-
-		if (slen > tp->slen)
-			tp->slen = slen;
-	}
-
-	return tp;
+	return node_parent(tn);
 }
 
 static void node_pull_suffix(struct key_vector *tn, unsigned char slen)
@@ -1030,6 +1019,7 @@ static int fib_insert_node(struct trie *t, struct key_vector *tp,
 	}
 
 	/* Case 3: n is NULL, and will just insert a new leaf */
+	node_push_suffix(tp, new->fa_slen);
 	NODE_INIT_PARENT(l, tp);
 	put_child_root(tp, key, l);
 	trie_rebalance(t, tp);
@@ -1472,6 +1462,8 @@ static void fib_remove_alias(struct trie *t, struct key_vector *tp,
 	 * out parent suffix lengths as a part of trie_rebalance
 	 */
 	if (hlist_empty(&l->leaf)) {
+		if (tp->slen == l->slen)
+			node_pull_suffix(tp, tp->pos);
 		put_child_root(tp, l->key, NULL);
 		node_free(l);
 		trie_rebalance(t, tp);
@@ -1755,6 +1747,10 @@ void fib_table_flush_external(struct fib_table *tb)
 			if (IS_TRIE(pn))
 				break;
 
+			/* update the suffix to address pulled leaves */
+			if (pn->slen > pn->pos)
+				update_suffix(pn);
+
 			/* resize completed node */
 			pn = resize(t, pn);
 			cindex = get_index(pkey, pn);
@@ -1830,6 +1826,10 @@ int fib_table_flush(struct fib_table *tb)
 			if (IS_TRIE(pn))
 				break;
 
+			/* update the suffix to address pulled leaves */
+			if (pn->slen > pn->pos)
+				update_suffix(pn);
+
 			/* resize completed node */
 			pn = resize(t, pn);
 			cindex = get_index(pkey, pn);
-- 
2.7.4

Re: [PATCHES] Networking

[Greg KH]

On Wed, Dec 07, 2016 at 06:43:29PM -0500, David Miller wrote:
> 
> Please queue up the following bug fixes for 4.4.x and 4.8.x
> -stable, repectively.

Thanks for these, all queued up!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 104 bytes --]


Please queue up the following networking bug fixes for 4.4.x and
4.9.x -stable, respectively.

Thanks!

[-- Attachment #2: net_44.mbox --]
[-- Type: Application/Octet-Stream, Size: 39840 bytes --]

From 3bff38e735cdc08063b7c04bb564985741dfe8cf Mon Sep 17 00:00:00 2001
From: stephen hemminger <stephen@networkplumber.org>
Date: Tue, 6 Dec 2016 13:43:54 -0800
Subject: [PATCH 01/19] netvsc: reduce maximum GSO size

[ Upstream commit a50af86dd49ee1851d1ccf06dd0019c05b95e297 ]

Hyper-V (and Azure) support using NVGRE which requires some extra space
for encapsulation headers. Because of this the largest allowed TSO
packet is reduced.

For older releases, hard code a fixed reduced value.  For next release,
there is a better solution which uses result of host offload
negotiation.

Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/netvsc_drv.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 409b48e..7a601d8 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -40,6 +40,8 @@
 
 #include "hyperv_net.h"
 
+/* Restrict GSO size to account for NVGRE */
+#define NETVSC_GSO_MAX_SIZE	62768
 
 #define RING_SIZE_MIN 64
 static int ring_size = 128;
@@ -852,6 +854,7 @@ static int netvsc_set_channels(struct net_device *net,
 		}
 		goto recover;
 	}
+	netif_set_gso_max_size(net, NETVSC_GSO_MAX_SIZE);
 
  out:
 	netvsc_open(net);
-- 
2.7.4


From 74cf1b15c0819cfd37adb1dc43c14647de4f3844 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 7 Dec 2016 14:22:03 +0300
Subject: [PATCH 02/19] ser_gigaset: return -ENOMEM on error instead of success

[ Upstream commit 93a97c50cbf1c007caf12db5cc23e0d5b9c8473c ]

If we can't allocate the resources in gigaset_initdriver() then we
should return -ENOMEM instead of zero.

Fixes: 2869b23e4b95 ("[PATCH] drivers/isdn/gigaset: new M101 driver (v2)")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/gigaset/ser-gigaset.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/isdn/gigaset/ser-gigaset.c b/drivers/isdn/gigaset/ser-gigaset.c
index 2a506fe..74bf1a1 100644
--- a/drivers/isdn/gigaset/ser-gigaset.c
+++ b/drivers/isdn/gigaset/ser-gigaset.c
@@ -762,8 +762,10 @@ static int __init ser_gigaset_init(void)
 	driver = gigaset_initdriver(GIGASET_MINOR, GIGASET_MINORS,
 				    GIGASET_MODULENAME, GIGASET_DEVNAME,
 				    &ops, THIS_MODULE);
-	if (!driver)
+	if (!driver) {
+		rc = -ENOMEM;
 		goto error;
+	}
 
 	rc = tty_register_ldisc(N_GIGASET_M101, &gigaset_ldisc);
 	if (rc != 0) {
-- 
2.7.4


From 86a363429e15142e862c5b09679c9bbdb70bcccf Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Wed, 14 Dec 2016 14:31:11 -0800
Subject: [PATCH 03/19] net: vrf: Drop conntrack data after pass through VRF
 device on Tx

[ Upstream commit eb63ecc1706b3e094d0f57438b6c2067cfc299f2 ]

Locally originated traffic in a VRF fails in the presence of a POSTROUTING
rule. For example,

    $ iptables -t nat -A POSTROUTING -s 11.1.1.0/24  -j MASQUERADE
    $ ping -I red -c1 11.1.1.3
    ping: Warning: source address might be selected on device other than red.
    PING 11.1.1.3 (11.1.1.3) from 11.1.1.2 red: 56(84) bytes of data.
    ping: sendmsg: Operation not permitted

Worse, the above causes random corruption resulting in a panic in random
places (I have not seen a consistent backtrace).

Call nf_reset to drop the conntrack info following the pass through the
VRF device.  The nf_reset is needed on Tx but not Rx because of the order
in which NF_HOOK's are hit: on Rx the VRF device is after the real ingress
device and on Tx it is is before the real egress device. Connection
tracking should be tied to the real egress device and not the VRF device.

Fixes: 8f58336d3f78a ("net: Add ethernet header for pass through VRF device")
Fixes: 35402e3136634 ("net: Add IPv6 support to VRF device")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 903bda4..86f59ca 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -410,6 +410,8 @@ static int vrf_finish_output6(struct net *net, struct sock *sk,
 	struct in6_addr *nexthop;
 	int ret;
 
+	nf_reset(skb);
+
 	skb->protocol = htons(ETH_P_IPV6);
 	skb->dev = dev;
 
@@ -521,6 +523,8 @@ static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *s
 	u32 nexthop;
 	int ret = -EINVAL;
 
+	nf_reset(skb);
+
 	/* Be paranoid, rather than too clever. */
 	if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) {
 		struct sk_buff *skb2;
-- 
2.7.4


From c5b7c78a482f5b0c55b8ca77c1a9b000ee688d6b Mon Sep 17 00:00:00 2001
From: Dave Jones <davej@codemonkey.org.uk>
Date: Thu, 22 Dec 2016 11:16:22 -0500
Subject: [PATCH 04/19] ipv6: handle -EFAULT from skb_copy_bits

[ Upstream commit a98f91758995cb59611e61318dddd8a6956b52c3 ]

By setting certain socket options on ipv6 raw sockets, we can confuse the
length calculation in rawv6_push_pending_frames triggering a BUG_ON.

RIP: 0010:[<ffffffff817c6390>] [<ffffffff817c6390>] rawv6_sendmsg+0xc30/0xc40
RSP: 0018:ffff881f6c4a7c18  EFLAGS: 00010282
RAX: 00000000fffffff2 RBX: ffff881f6c681680 RCX: 0000000000000002
RDX: ffff881f6c4a7cf8 RSI: 0000000000000030 RDI: ffff881fed0f6a00
RBP: ffff881f6c4a7da8 R08: 0000000000000000 R09: 0000000000000009
R10: ffff881fed0f6a00 R11: 0000000000000009 R12: 0000000000000030
R13: ffff881fed0f6a00 R14: ffff881fee39ba00 R15: ffff881fefa93a80

Call Trace:
 [<ffffffff8118ba23>] ? unmap_page_range+0x693/0x830
 [<ffffffff81772697>] inet_sendmsg+0x67/0xa0
 [<ffffffff816d93f8>] sock_sendmsg+0x38/0x50
 [<ffffffff816d982f>] SYSC_sendto+0xef/0x170
 [<ffffffff816da27e>] SyS_sendto+0xe/0x10
 [<ffffffff81002910>] do_syscall_64+0x50/0xa0
 [<ffffffff817f7cbc>] entry_SYSCALL64_slow_path+0x25/0x25

Handle by jumping to the failure path if skb_copy_bits gets an EFAULT.

Reproducer:

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <sys/types.h>
#include <sys/socket.h>
#include <netinet/in.h>

#define LEN 504

int main(int argc, char* argv[])
{
	int fd;
	int zero = 0;
	char buf[LEN];

	memset(buf, 0, LEN);

	fd = socket(AF_INET6, SOCK_RAW, 7);

	setsockopt(fd, SOL_IPV6, IPV6_CHECKSUM, &zero, 4);
	setsockopt(fd, SOL_IPV6, IPV6_DSTOPTS, &buf, LEN);

	sendto(fd, buf, 1, 0, (struct sockaddr *) buf, 110);
}

Signed-off-by: Dave Jones <davej@codemonkey.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/raw.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 9914098..8bca90d 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -589,7 +589,11 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
 	}
 
 	offset += skb_transport_offset(skb);
-	BUG_ON(skb_copy_bits(skb, offset, &csum, 2));
+	err = skb_copy_bits(skb, offset, &csum, 2);
+	if (err < 0) {
+		ip6_flush_pending_frames(sk);
+		goto out;
+	}
 
 	/* in case cksum was not initialized */
 	if (unlikely(csum))
-- 
2.7.4


From b5f1f19bb110c286579a0c422f905e7b72468892 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 21 Dec 2016 18:04:11 +0100
Subject: [PATCH 05/19] net, sched: fix soft lockup in tc_classify

[ Upstream commit 628185cfddf1dfb701c4efe2cfd72cf5b09f5702 ]

Shahar reported a soft lockup in tc_classify(), where we run into an
endless loop when walking the classifier chain due to tp->next == tp
which is a state we should never run into. The issue only seems to
trigger under load in the tc control path.

What happens is that in tc_ctl_tfilter(), thread A allocates a new
tp, initializes it, sets tp_created to 1, and calls into tp->ops->change()
with it. In that classifier callback we had to unlock/lock the rtnl
mutex and returned with -EAGAIN. One reason why we need to drop there
is, for example, that we need to request an action module to be loaded.

This happens via tcf_exts_validate() -> tcf_action_init/_1() meaning
after we loaded and found the requested action, we need to redo the
whole request so we don't race against others. While we had to unlock
rtnl in that time, thread B's request was processed next on that CPU.
Thread B added a new tp instance successfully to the classifier chain.
When thread A returned grabbing the rtnl mutex again, propagating -EAGAIN
and destroying its tp instance which never got linked, we goto replay
and redo A's request.

This time when walking the classifier chain in tc_ctl_tfilter() for
checking for existing tp instances we had a priority match and found
the tp instance that was created and linked by thread B. Now calling
again into tp->ops->change() with that tp was successful and returned
without error.

tp_created was never cleared in the second round, thus kernel thinks
that we need to link it into the classifier chain (once again). tp and
*back point to the same object due to the match we had earlier on. Thus
for thread B's already public tp, we reset tp->next to tp itself and
link it into the chain, which eventually causes the mentioned endless
loop in tc_classify() once a packet hits the data path.

Fix is to clear tp_created at the beginning of each request, also when
we replay it. On the paths that can cause -EAGAIN we already destroy
the original tp instance we had and on replay we really need to start
from scratch. It seems that this issue was first introduced in commit
12186be7d2e1 ("net_cls: fix unconfigured struct tcf_proto keeps chaining
and avoid kernel panic when we use cls_cgroup").

Fixes: 12186be7d2e1 ("net_cls: fix unconfigured struct tcf_proto keeps chaining and avoid kernel panic when we use cls_cgroup")
Reported-by: Shahar Klein <shahark@mellanox.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Tested-by: Shahar Klein <shahark@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index ecc1904..20b2f86 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -137,13 +137,15 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n)
 	unsigned long cl;
 	unsigned long fh;
 	int err;
-	int tp_created = 0;
+	int tp_created;
 
 	if ((n->nlmsg_type != RTM_GETTFILTER) &&
 	    !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 replay:
+	tp_created = 0;
+
 	err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL);
 	if (err < 0)
 		return err;
-- 
2.7.4


From 499195a88940fadf146a55f5c35f6c29ad1e9459 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 27 Dec 2016 18:23:06 -0800
Subject: [PATCH 06/19] net: stmmac: Fix race between stmmac_drv_probe and
 stmmac_open

[ Upstream commit 5701659004d68085182d2fd4199c79172165fa65 ]

There is currently a small window during which the network device registered by
stmmac can be made visible, yet all resources, including and clock and MDIO bus
have not had a chance to be set up, this can lead to the following error to
occur:

[  473.919358] stmmaceth 0000:01:00.0 (unnamed net_device) (uninitialized):
                stmmac_dvr_probe: warning: cannot get CSR clock
[  473.919382] stmmaceth 0000:01:00.0: no reset control found
[  473.919412] stmmac - user ID: 0x10, Synopsys ID: 0x42
[  473.919429] stmmaceth 0000:01:00.0: DMA HW capability register supported
[  473.919436] stmmaceth 0000:01:00.0: RX Checksum Offload Engine supported
[  473.919443] stmmaceth 0000:01:00.0: TX Checksum insertion supported
[  473.919451] stmmaceth 0000:01:00.0 (unnamed net_device) (uninitialized):
                Enable RX Mitigation via HW Watchdog Timer
[  473.921395] libphy: PHY stmmac-1:00 not found
[  473.921417] stmmaceth 0000:01:00.0 eth0: Could not attach to PHY
[  473.921427] stmmaceth 0000:01:00.0 eth0: stmmac_open: Cannot attach to
                PHY (error: -19)
[  473.959710] libphy: stmmac: probed
[  473.959724] stmmaceth 0000:01:00.0 eth0: PHY ID 01410cc2 at 0 IRQ POLL
                (stmmac-1:00) active
[  473.959728] stmmaceth 0000:01:00.0 eth0: PHY ID 01410cc2 at 1 IRQ POLL
                (stmmac-1:01)
[  473.959731] stmmaceth 0000:01:00.0 eth0: PHY ID 01410cc2 at 2 IRQ POLL
                (stmmac-1:02)
[  473.959734] stmmaceth 0000:01:00.0 eth0: PHY ID 01410cc2 at 3 IRQ POLL
                (stmmac-1:03)

Fix this by making sure that register_netdev() is the last thing being done,
which guarantees that the clock and the MDIO bus are available.

Fixes: 4bfcbd7abce2 ("stmmac: Move the mdio_register/_unregister in probe/remove")
Reported-by: Kweh, Hock Leong <hock.leong.kweh@intel.com>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 22 +++++++++++++---------
 1 file changed, 13 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index a5b869e..4b100ef 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2939,12 +2939,6 @@ int stmmac_dvr_probe(struct device *device,
 	spin_lock_init(&priv->lock);
 	spin_lock_init(&priv->tx_lock);
 
-	ret = register_netdev(ndev);
-	if (ret) {
-		pr_err("%s: ERROR %i registering the device\n", __func__, ret);
-		goto error_netdev_register;
-	}
-
 	/* If a specific clk_csr value is passed from the platform
 	 * this means that the CSR Clock Range selection cannot be
 	 * changed at run-time and it is fixed. Viceversa the driver'll try to
@@ -2969,11 +2963,21 @@ int stmmac_dvr_probe(struct device *device,
 		}
 	}
 
-	return 0;
+	ret = register_netdev(ndev);
+	if (ret) {
+		netdev_err(priv->dev, "%s: ERROR %i registering the device\n",
+			   __func__, ret);
+		goto error_netdev_register;
+	}
+
+	return ret;
 
-error_mdio_register:
-	unregister_netdev(ndev);
 error_netdev_register:
+	if (priv->pcs != STMMAC_PCS_RGMII &&
+	    priv->pcs != STMMAC_PCS_TBI &&
+	    priv->pcs != STMMAC_PCS_RTBI)
+		stmmac_mdio_unregister(ndev);
+error_mdio_register:
 	netif_napi_del(&priv->napi);
 error_hw_init:
 	clk_disable_unprepare(priv->pclk);
-- 
2.7.4


From c650700d6798d49b0ec59bc3bdbba696afb3104b Mon Sep 17 00:00:00 2001
From: Noa Osherovich <noaos@mellanox.com>
Date: Wed, 28 Dec 2016 14:58:32 +0200
Subject: [PATCH 07/19] net/mlx5: Check FW limitations on log_max_qp before
 setting it

[ Upstream commit 883371c453b937f9eb581fb4915210865982736f ]

When setting HCA capabilities, set log_max_qp to be the minimum
between the selected profile's value and the HCA limitation.

Fixes: 938fe83c8dcb ('net/mlx5_core: New device capabilities...')
Signed-off-by: Noa Osherovich <noaos@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 6cf6d93..552cd60 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -432,6 +432,13 @@ static int handle_hca_cap(struct mlx5_core_dev *dev)
 	MLX5_SET(cmd_hca_cap, set_hca_cap, pkey_table_size,
 		 to_fw_pkey_sz(128));
 
+	/* Check log_max_qp from HCA caps to set in current profile */
+	if (MLX5_CAP_GEN_MAX(dev, log_max_qp) < profile[prof_sel].log_max_qp) {
+		mlx5_core_warn(dev, "log_max_qp value in current profile is %d, changing it to HCA capability limit (%d)\n",
+			       profile[prof_sel].log_max_qp,
+			       MLX5_CAP_GEN_MAX(dev, log_max_qp));
+		profile[prof_sel].log_max_qp = MLX5_CAP_GEN_MAX(dev, log_max_qp);
+	}
 	if (prof->mask & MLX5_PROF_MASK_QP_SIZE)
 		MLX5_SET(cmd_hca_cap, set_hca_cap, log_max_qp,
 			 prof->log_max_qp);
-- 
2.7.4


From 761c8ea62d4de7ca5414cc071f741a42569556f9 Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.com>
Date: Wed, 28 Dec 2016 14:58:34 +0200
Subject: [PATCH 08/19] net/mlx5: Avoid shadowing numa_node

[ Upstream commit d151d73dcc99de87c63bdefebcc4cb69de1cdc40 ]

Avoid using a local variable named numa_node to avoid shadowing a public
one.

Fixes: db058a186f98 ('net/mlx5_core: Set irq affinity hints')
Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 552cd60..ba115ec 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -512,7 +512,6 @@ static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i)
 	struct mlx5_priv *priv  = &mdev->priv;
 	struct msix_entry *msix = priv->msix_arr;
 	int irq                 = msix[i + MLX5_EQ_VEC_COMP_BASE].vector;
-	int numa_node           = priv->numa_node;
 	int err;
 
 	if (!zalloc_cpumask_var(&priv->irq_info[i].mask, GFP_KERNEL)) {
@@ -520,7 +519,7 @@ static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i)
 		return -ENOMEM;
 	}
 
-	cpumask_set_cpu(cpumask_local_spread(i, numa_node),
+	cpumask_set_cpu(cpumask_local_spread(i, priv->numa_node),
 			priv->irq_info[i].mask);
 
 	err = irq_set_affinity_hint(irq, priv->irq_info[i].mask);
-- 
2.7.4


From 45a8e5a57c1c538ec0548d459667c2ffda23b216 Mon Sep 17 00:00:00 2001
From: Reiter Wolfgang <wr0112358@gmail.com>
Date: Sat, 31 Dec 2016 21:11:57 +0100
Subject: [PATCH 09/19] drop_monitor: add missing call to genlmsg_end

[ Upstream commit 4200462d88f47f3759bdf4705f87e207b0f5b2e4 ]

Update nlmsg_len field with genlmsg_end to enable userspace processing
using nlmsg_next helper. Also adds error handling.

Signed-off-by: Reiter Wolfgang <wr0112358@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/drop_monitor.c | 33 ++++++++++++++++++++++++---------
 1 file changed, 24 insertions(+), 9 deletions(-)

diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 252e155..38d39b0 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -80,6 +80,7 @@ static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data)
 	struct nlattr *nla;
 	struct sk_buff *skb;
 	unsigned long flags;
+	void *msg_header;
 
 	al = sizeof(struct net_dm_alert_msg);
 	al += dm_hit_limit * sizeof(struct net_dm_drop_point);
@@ -87,17 +88,31 @@ static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data)
 
 	skb = genlmsg_new(al, GFP_KERNEL);
 
-	if (skb) {
-		genlmsg_put(skb, 0, 0, &net_drop_monitor_family,
-				0, NET_DM_CMD_ALERT);
-		nla = nla_reserve(skb, NLA_UNSPEC,
-				  sizeof(struct net_dm_alert_msg));
-		msg = nla_data(nla);
-		memset(msg, 0, al);
-	} else {
-		mod_timer(&data->send_timer, jiffies + HZ / 10);
+	if (!skb)
+		goto err;
+
+	msg_header = genlmsg_put(skb, 0, 0, &net_drop_monitor_family,
+				 0, NET_DM_CMD_ALERT);
+	if (!msg_header) {
+		nlmsg_free(skb);
+		skb = NULL;
+		goto err;
+	}
+	nla = nla_reserve(skb, NLA_UNSPEC,
+			  sizeof(struct net_dm_alert_msg));
+	if (!nla) {
+		nlmsg_free(skb);
+		skb = NULL;
+		goto err;
 	}
+	msg = nla_data(nla);
+	memset(msg, 0, al);
+	genlmsg_end(skb, msg_header);
+	goto out;
 
+err:
+	mod_timer(&data->send_timer, jiffies + HZ / 10);
+out:
 	spin_lock_irqsave(&data->lock, flags);
 	swap(data->skb, skb);
 	spin_unlock_irqrestore(&data->lock, flags);
-- 
2.7.4


From 62f23b5810c7cbff9a0b74fb1c6a4d73054be240 Mon Sep 17 00:00:00 2001
From: Reiter Wolfgang <wr0112358@gmail.com>
Date: Tue, 3 Jan 2017 01:39:10 +0100
Subject: [PATCH 10/19] drop_monitor: consider inserted data in genlmsg_end

[ Upstream commit 3b48ab2248e61408910e792fe84d6ec466084c1a ]

Final nlmsg_len field update must reflect inserted net_dm_drop_point
data.

This patch depends on previous patch:
"drop_monitor: add missing call to genlmsg_end"

Signed-off-by: Reiter Wolfgang <wr0112358@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/drop_monitor.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 38d39b0..a2270188 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -107,7 +107,6 @@ static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data)
 	}
 	msg = nla_data(nla);
 	memset(msg, 0, al);
-	genlmsg_end(skb, msg_header);
 	goto out;
 
 err:
@@ -117,6 +116,13 @@ out:
 	swap(data->skb, skb);
 	spin_unlock_irqrestore(&data->lock, flags);
 
+	if (skb) {
+		struct nlmsghdr *nlh = (struct nlmsghdr *)skb->data;
+		struct genlmsghdr *gnlh = (struct genlmsghdr *)nlmsg_data(nlh);
+
+		genlmsg_end(skb, genlmsg_data(gnlh));
+	}
+
 	return skb;
 }
 
-- 
2.7.4


From dfd9fc8c16cfd2d95cab0239c2ef1134e32403f4 Mon Sep 17 00:00:00 2001
From: Michal Tesar <mtesar@redhat.com>
Date: Mon, 2 Jan 2017 14:38:36 +0100
Subject: [PATCH 11/19] igmp: Make igmp group member RFC 3376 compliant

[ Upstream commit 7ababb782690e03b78657e27bd051e20163af2d6 ]

5.2. Action on Reception of a Query

 When a system receives a Query, it does not respond immediately.
 Instead, it delays its response by a random amount of time, bounded
 by the Max Resp Time value derived from the Max Resp Code in the
 received Query message.  A system may receive a variety of Queries on
 different interfaces and of different kinds (e.g., General Queries,
 Group-Specific Queries, and Group-and-Source-Specific Queries), each
 of which may require its own delayed response.

 Before scheduling a response to a Query, the system must first
 consider previously scheduled pending responses and in many cases
 schedule a combined response.  Therefore, the system must be able to
 maintain the following state:

 o A timer per interface for scheduling responses to General Queries.

 o A per-group and interface timer for scheduling responses to Group-
   Specific and Group-and-Source-Specific Queries.

 o A per-group and interface list of sources to be reported in the
   response to a Group-and-Source-Specific Query.

 When a new Query with the Router-Alert option arrives on an
 interface, provided the system has state to report, a delay for a
 response is randomly selected in the range (0, [Max Resp Time]) where
 Max Resp Time is derived from Max Resp Code in the received Query
 message.  The following rules are then used to determine if a Report
 needs to be scheduled and the type of Report to schedule.  The rules
 are considered in order and only the first matching rule is applied.

 1. If there is a pending response to a previous General Query
    scheduled sooner than the selected delay, no additional response
    needs to be scheduled.

 2. If the received Query is a General Query, the interface timer is
    used to schedule a response to the General Query after the
    selected delay.  Any previously pending response to a General
    Query is canceled.
--8<--

Currently the timer is rearmed with new random expiration time for
every incoming query regardless of possibly already pending report.
Which is not aligned with the above RFE.
It also might happen that higher rate of incoming queries can
postpone the report after the expiration time of the first query
causing group membership loss.

Now the per interface general query timer is rearmed only
when there is no pending report already scheduled on that interface or
the newly selected expiration time is before the already pending
scheduled report.

Signed-off-by: Michal Tesar <mtesar@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/igmp.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index b3086cf..17adfda 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -225,9 +225,14 @@ static void igmp_start_timer(struct ip_mc_list *im, int max_delay)
 static void igmp_gq_start_timer(struct in_device *in_dev)
 {
 	int tv = prandom_u32() % in_dev->mr_maxdelay;
+	unsigned long exp = jiffies + tv + 2;
+
+	if (in_dev->mr_gq_running &&
+	    time_after_eq(exp, (in_dev->mr_gq_timer).expires))
+		return;
 
 	in_dev->mr_gq_running = 1;
-	if (!mod_timer(&in_dev->mr_gq_timer, jiffies+tv+2))
+	if (!mod_timer(&in_dev->mr_gq_timer, exp))
 		in_dev_hold(in_dev);
 }
 
-- 
2.7.4


From 8a6c70144df2685be9648e36e8b77e91d3e4f2ad Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Mon, 2 Jan 2017 13:32:54 -0800
Subject: [PATCH 12/19] ipv4: Do not allow MAIN to be alias for new LOCAL w/
 custom rules

[ Upstream commit 5350d54f6cd12eaff623e890744c79b700bd3f17 ]

In the case of custom rules being present we need to handle the case of the
LOCAL table being intialized after the new rule has been added.  To address
that I am adding a new check so that we can make certain we don't use an
alias of MAIN for LOCAL when allocating a new table.

Fixes: 0ddcf43d5d4a ("ipv4: FIB Local/MAIN table collapse")
Reported-by: Oliver Brunel <jjk@jjacky.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_frontend.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 63566ec..4e60dae 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -85,7 +85,7 @@ struct fib_table *fib_new_table(struct net *net, u32 id)
 	if (tb)
 		return tb;
 
-	if (id == RT_TABLE_LOCAL)
+	if (id == RT_TABLE_LOCAL && !net->ipv4.fib_has_custom_rules)
 		alias = fib_new_table(net, RT_TABLE_MAIN);
 
 	tb = fib_trie_table(id, alias);
-- 
2.7.4


From 0b5aa495690931bf4719a29130f6ea1cba0796e2 Mon Sep 17 00:00:00 2001
From: hayeswang <hayeswang@realtek.com>
Date: Tue, 10 Jan 2017 17:04:06 +0800
Subject: [PATCH 13/19] r8152: split rtl8152_suspend function

[ Upstream commit 8fb280616878b81c0790a0c33acbeec59c5711f4 ]

Split rtl8152_suspend() into rtl8152_system_suspend() and
rtl8152_rumtime_suspend().

Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 57 ++++++++++++++++++++++++++++++++++---------------
 1 file changed, 40 insertions(+), 17 deletions(-)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 2fb637a..7a6d405 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -3446,39 +3446,62 @@ static bool delay_autosuspend(struct r8152 *tp)
 		return false;
 }
 
-static int rtl8152_suspend(struct usb_interface *intf, pm_message_t message)
+static int rtl8152_rumtime_suspend(struct r8152 *tp)
 {
-	struct r8152 *tp = usb_get_intfdata(intf);
 	struct net_device *netdev = tp->netdev;
 	int ret = 0;
 
-	mutex_lock(&tp->control);
-
-	if (PMSG_IS_AUTO(message)) {
-		if (netif_running(netdev) && delay_autosuspend(tp)) {
+	if (netif_running(netdev) && test_bit(WORK_ENABLE, &tp->flags)) {
+		if (delay_autosuspend(tp)) {
 			ret = -EBUSY;
 			goto out1;
 		}
 
-		set_bit(SELECTIVE_SUSPEND, &tp->flags);
-	} else {
-		netif_device_detach(netdev);
+		clear_bit(WORK_ENABLE, &tp->flags);
+		usb_kill_urb(tp->intr_urb);
+		napi_disable(&tp->napi);
+		rtl_stop_rx(tp);
+		rtl_runtime_suspend_enable(tp, true);
+		napi_enable(&tp->napi);
 	}
 
+	set_bit(SELECTIVE_SUSPEND, &tp->flags);
+
+out1:
+	return ret;
+}
+
+static int rtl8152_system_suspend(struct r8152 *tp)
+{
+	struct net_device *netdev = tp->netdev;
+	int ret = 0;
+
+	netif_device_detach(netdev);
+
 	if (netif_running(netdev) && test_bit(WORK_ENABLE, &tp->flags)) {
 		clear_bit(WORK_ENABLE, &tp->flags);
 		usb_kill_urb(tp->intr_urb);
 		napi_disable(&tp->napi);
-		if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
-			rtl_stop_rx(tp);
-			rtl_runtime_suspend_enable(tp, true);
-		} else {
-			cancel_delayed_work_sync(&tp->schedule);
-			tp->rtl_ops.down(tp);
-		}
+		cancel_delayed_work_sync(&tp->schedule);
+		tp->rtl_ops.down(tp);
 		napi_enable(&tp->napi);
 	}
-out1:
+
+	return ret;
+}
+
+static int rtl8152_suspend(struct usb_interface *intf, pm_message_t message)
+{
+	struct r8152 *tp = usb_get_intfdata(intf);
+	int ret;
+
+	mutex_lock(&tp->control);
+
+	if (PMSG_IS_AUTO(message))
+		ret = rtl8152_rumtime_suspend(tp);
+	else
+		ret = rtl8152_system_suspend(tp);
+
 	mutex_unlock(&tp->control);
 
 	return ret;
-- 
2.7.4


From 786397218800ad90d1c05de0c0b939454fbfd416 Mon Sep 17 00:00:00 2001
From: hayeswang <hayeswang@realtek.com>
Date: Tue, 10 Jan 2017 17:04:07 +0800
Subject: [PATCH 14/19] r8152: fix rx issue for runtime suspend

[ Upstream commit 75dc692eda114cb234a46cb11893a9c3ea520934 ]

Pause the rx and make sure the rx fifo is empty when the autosuspend
occurs.

If the rx data comes when the driver is canceling the rx urb, the host
controller would stop getting the data from the device and continue
it after next rx urb is submitted. That is, one continuing data is
split into two different urb buffers. That let the driver take the
data as a rx descriptor, and unexpected behavior happens.

Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 31 ++++++++++++++++++++++++++++---
 1 file changed, 28 insertions(+), 3 deletions(-)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 7a6d405..32b7ec9 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -3452,17 +3452,42 @@ static int rtl8152_rumtime_suspend(struct r8152 *tp)
 	int ret = 0;
 
 	if (netif_running(netdev) && test_bit(WORK_ENABLE, &tp->flags)) {
+		u32 rcr = 0;
+
 		if (delay_autosuspend(tp)) {
 			ret = -EBUSY;
 			goto out1;
 		}
 
+		if (netif_carrier_ok(netdev)) {
+			u32 ocp_data;
+
+			rcr = ocp_read_dword(tp, MCU_TYPE_PLA, PLA_RCR);
+			ocp_data = rcr & ~RCR_ACPT_ALL;
+			ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RCR, ocp_data);
+			rxdy_gated_en(tp, true);
+			ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA,
+						 PLA_OOB_CTRL);
+			if (!(ocp_data & RXFIFO_EMPTY)) {
+				rxdy_gated_en(tp, false);
+				ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RCR, rcr);
+				ret = -EBUSY;
+				goto out1;
+			}
+		}
+
 		clear_bit(WORK_ENABLE, &tp->flags);
 		usb_kill_urb(tp->intr_urb);
-		napi_disable(&tp->napi);
-		rtl_stop_rx(tp);
+
 		rtl_runtime_suspend_enable(tp, true);
-		napi_enable(&tp->napi);
+
+		if (netif_carrier_ok(netdev)) {
+			napi_disable(&tp->napi);
+			rtl_stop_rx(tp);
+			rxdy_gated_en(tp, false);
+			ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RCR, rcr);
+			napi_enable(&tp->napi);
+		}
 	}
 
 	set_bit(SELECTIVE_SUSPEND, &tp->flags);
-- 
2.7.4


From cad6f6a1088819c6583ad5f04002d9eb8a50e44c Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Tue, 10 Jan 2017 12:24:01 -0800
Subject: [PATCH 15/19] gro: Enter slow-path if there is no tailroom

[ Upstream commit 1272ce87fa017ca4cf32920764d879656b7a005a ]

The GRO path has a fast-path where we avoid calling pskb_may_pull
and pskb_expand by directly accessing frag0.  However, this should
only be done if we have enough tailroom in the skb as otherwise
we'll have to expand it later anyway.

This patch adds the check by capping frag0_len with the skb tailroom.

Fixes: cb18978cbf45 ("gro: Open-code final pskb_may_pull")
Reported-by: Slava Shwartsman <slavash@mellanox.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 9ca749c..ee6c7b0 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4187,7 +4187,8 @@ static void skb_gro_reset_offset(struct sk_buff *skb)
 	    pinfo->nr_frags &&
 	    !PageHighMem(skb_frag_page(frag0))) {
 		NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0);
-		NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(frag0);
+		NAPI_GRO_CB(skb)->frag0_len = min(skb_frag_size(frag0),
+						  skb->end - skb->tail);
 	}
 }
 
-- 
2.7.4


From ac9c814281fe7d61d2ec4c06af7b5b11392c9047 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 10 Jan 2017 19:52:43 -0800
Subject: [PATCH 16/19] gro: use min_t() in skb_gro_reset_offset()

[ Upstream commit 7cfd5fd5a9813f1430290d20c0fead9b4582a307 ]

On 32bit arches, (skb->end - skb->data) is not 'unsigned int',
so we shall use min_t() instead of min() to avoid a compiler error.

Fixes: 1272ce87fa01 ("gro: Enter slow-path if there is no tailroom")
Reported-by: kernel test robot <fengguang.wu@intel.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index ee6c7b0..6f203c7 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4187,8 +4187,9 @@ static void skb_gro_reset_offset(struct sk_buff *skb)
 	    pinfo->nr_frags &&
 	    !PageHighMem(skb_frag_page(frag0))) {
 		NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0);
-		NAPI_GRO_CB(skb)->frag0_len = min(skb_frag_size(frag0),
-						  skb->end - skb->tail);
+		NAPI_GRO_CB(skb)->frag0_len = min_t(unsigned int,
+						    skb_frag_size(frag0),
+						    skb->end - skb->tail);
 	}
 }
 
-- 
2.7.4


From afddf599e4ddd902c0208f0194e82ced77cb3a6a Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Tue, 10 Jan 2017 12:24:15 -0800
Subject: [PATCH 17/19] gro: Disable frag0 optimization on IPv6 ext headers

[ Upstream commit 57ea52a865144aedbcd619ee0081155e658b6f7d ]

The GRO fast path caches the frag0 address.  This address becomes
invalid if frag0 is modified by pskb_may_pull or its variants.
So whenever that happens we must disable the frag0 optimization.

This is usually done through the combination of gro_header_hard
and gro_header_slow, however, the IPv6 extension header path did
the pulling directly and would continue to use the GRO fast path
incorrectly.

This patch fixes it by disabling the fast path when we enter the
IPv6 extension header path.

Fixes: 78a478d0efd9 ("gro: Inline skb_gro_header and cache frag0 virtual address")
Reported-by: Slava Shwartsman <slavash@mellanox.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 9 +++++++--
 net/ipv6/ip6_offload.c    | 1 +
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 9d60257..93a6a2c 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2325,14 +2325,19 @@ static inline int skb_gro_header_hard(struct sk_buff *skb, unsigned int hlen)
 	return NAPI_GRO_CB(skb)->frag0_len < hlen;
 }
 
+static inline void skb_gro_frag0_invalidate(struct sk_buff *skb)
+{
+	NAPI_GRO_CB(skb)->frag0 = NULL;
+	NAPI_GRO_CB(skb)->frag0_len = 0;
+}
+
 static inline void *skb_gro_header_slow(struct sk_buff *skb, unsigned int hlen,
 					unsigned int offset)
 {
 	if (!pskb_may_pull(skb, hlen))
 		return NULL;
 
-	NAPI_GRO_CB(skb)->frag0 = NULL;
-	NAPI_GRO_CB(skb)->frag0_len = 0;
+	skb_gro_frag0_invalidate(skb);
 	return skb->data + offset;
 }
 
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index efe6268..225f5f7 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -196,6 +196,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 	ops = rcu_dereference(inet6_offloads[proto]);
 	if (!ops || !ops->callbacks.gro_receive) {
 		__pskb_pull(skb, skb_gro_offset(skb));
+		skb_gro_frag0_invalidate(skb);
 		proto = ipv6_gso_pull_exthdrs(skb, proto);
 		skb_gro_pull(skb, -skb_transport_offset(skb));
 		skb_reset_transport_header(skb);
-- 
2.7.4


From b0dfc657af12ee366098a0ea7130565e25d8dba7 Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Tue, 10 Jan 2017 14:37:35 -0800
Subject: [PATCH 18/19] net: ipv4: Fix multipath selection with vrf

[ Upstream commit 7a18c5b9fb31a999afc62b0e60978aa896fc89e9 ]

fib_select_path does not call fib_select_multipath if oif is set in the
flow struct. For VRF use cases oif is always set, so multipath route
selection is bypassed. Use the FLOWI_FLAG_SKIP_NH_OIF to skip the oif
check similar to what is done in fib_table_lookup.

Add saddr and proto to the flow struct for the fib lookup done by the
VRF driver to better match hash computation for a flow.

Fixes: 613d09b30f8b ("net: Use VRF device index for lookups on TX")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c        | 2 ++
 net/ipv4/fib_semantics.c | 9 +++++++--
 2 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 86f59ca..bc795b8 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -301,7 +301,9 @@ static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb,
 		.flowi4_tos = RT_TOS(ip4h->tos),
 		.flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_L3MDEV_SRC |
 				FLOWI_FLAG_SKIP_NH_OIF,
+		.flowi4_proto = ip4h->protocol,
 		.daddr = ip4h->daddr,
+		.saddr = ip4h->saddr,
 	};
 
 	if (vrf_send_v4_prep(skb, &fl4, vrf_dev))
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index ffe95d9..840b450 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1588,8 +1588,13 @@ void fib_select_multipath(struct fib_result *res, int hash)
 void fib_select_path(struct net *net, struct fib_result *res,
 		     struct flowi4 *fl4, int mp_hash)
 {
+	bool oif_check;
+
+	oif_check = (fl4->flowi4_oif == 0 ||
+		     fl4->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF);
+
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-	if (res->fi->fib_nhs > 1 && fl4->flowi4_oif == 0) {
+	if (res->fi->fib_nhs > 1 && oif_check) {
 		if (mp_hash < 0)
 			mp_hash = get_hash_from_flowi4(fl4) >> 1;
 
@@ -1599,7 +1604,7 @@ void fib_select_path(struct net *net, struct fib_result *res,
 #endif
 	if (!res->prefixlen &&
 	    res->table->tb_num_default > 1 &&
-	    res->type == RTN_UNICAST && !fl4->flowi4_oif)
+	    res->type == RTN_UNICAST && oif_check)
 		fib_select_default(fl4, res);
 
 	if (!fl4->saddr)
-- 
2.7.4


From 7b076902e6c7dd86f8ab9ccc6e1ca57646c91eba Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Tue, 10 Jan 2017 15:22:25 -0800
Subject: [PATCH 19/19] net: vrf: do not allow table id 0

[ Upstream commit 24c63bbc18e25d5d8439422aa5fd2d66390b88eb ]

Frank reported that vrf devices can be created with a table id of 0.
This breaks many of the run time table id checks and should not be
allowed. Detect this condition at create time and fail with EINVAL.

Fixes: 193125dbd8eb ("net: Introduce VRF device driver")
Reported-by: Frank Kellermann <frank.kellermann@atos.net>
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index bc795b8..d6b6196 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -925,6 +925,8 @@ static int vrf_newlink(struct net *src_net, struct net_device *dev,
 		return -EINVAL;
 
 	vrf->tb_id = nla_get_u32(data[IFLA_VRF_TABLE]);
+	if (vrf->tb_id == RT_TABLE_UNSPEC)
+		return -EINVAL;
 
 	dev->priv_flags |= IFF_L3MDEV_MASTER;
 
-- 
2.7.4


[-- Attachment #3: net_49.mbox --]
[-- Type: Text/Plain, Size: 74373 bytes --]

>From 501cfa4d001500e50ce519512616a2442093e13d Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Wed, 14 Dec 2016 11:06:18 -0800
Subject: [PATCH 01/37] net: vrf: Fix NAT within a VRF

[ Upstream commit a0f37efa82253994b99623dbf41eea8dd0ba169b ]

Connection tracking with VRF is broken because the pass through the VRF
device drops the connection tracking info. Removing the call to nf_reset
allows DNAT and MASQUERADE to work across interfaces within a VRF.

Fixes: 73e20b761acf ("net: vrf: Add support for PREROUTING rules on vrf device")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 820de6a..5b995c4 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -850,8 +850,6 @@ static struct sk_buff *vrf_rcv_nfhook(u8 pf, unsigned int hook,
 {
 	struct net *net = dev_net(dev);
 
-	nf_reset(skb);
-
 	if (NF_HOOK(pf, hook, net, NULL, skb, dev, NULL, vrf_rcv_finish) < 0)
 		skb = NULL;    /* kfree_skb(skb) handled by nf code */
 
-- 
2.7.4


>From 9e335a84c686a198a10d7170f8c694a4bf1cbc2d Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Wed, 14 Dec 2016 14:31:11 -0800
Subject: [PATCH 02/37] net: vrf: Drop conntrack data after pass through VRF
 device on Tx

[ Upstream commit eb63ecc1706b3e094d0f57438b6c2067cfc299f2 ]

Locally originated traffic in a VRF fails in the presence of a POSTROUTING
rule. For example,

    $ iptables -t nat -A POSTROUTING -s 11.1.1.0/24  -j MASQUERADE
    $ ping -I red -c1 11.1.1.3
    ping: Warning: source address might be selected on device other than red.
    PING 11.1.1.3 (11.1.1.3) from 11.1.1.2 red: 56(84) bytes of data.
    ping: sendmsg: Operation not permitted

Worse, the above causes random corruption resulting in a panic in random
places (I have not seen a consistent backtrace).

Call nf_reset to drop the conntrack info following the pass through the
VRF device.  The nf_reset is needed on Tx but not Rx because of the order
in which NF_HOOK's are hit: on Rx the VRF device is after the real ingress
device and on Tx it is is before the real egress device. Connection
tracking should be tied to the real egress device and not the VRF device.

Fixes: 8f58336d3f78a ("net: Add ethernet header for pass through VRF device")
Fixes: 35402e3136634 ("net: Add IPv6 support to VRF device")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 5b995c4..3cb3588 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -371,6 +371,8 @@ static int vrf_finish_output6(struct net *net, struct sock *sk,
 	struct in6_addr *nexthop;
 	int ret;
 
+	nf_reset(skb);
+
 	skb->protocol = htons(ETH_P_IPV6);
 	skb->dev = dev;
 
@@ -552,6 +554,8 @@ static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *s
 	u32 nexthop;
 	int ret = -EINVAL;
 
+	nf_reset(skb);
+
 	/* Be paranoid, rather than too clever. */
 	if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) {
 		struct sk_buff *skb2;
-- 
2.7.4


>From 4960643b24acd5f1ac693b0eb6a9252538a76483 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 15 Dec 2016 23:05:52 +0800
Subject: [PATCH 03/37] sctp: sctp_transport_lookup_process should
 rcu_read_unlock when transport is null

[ Upstream commit 08abb79542c9e8c367d1d8e44fe1026868d3f0a7 ]

Prior to this patch, sctp_transport_lookup_process didn't rcu_read_unlock
when it failed to find a transport by sctp_addrs_lookup_transport.

This patch is to fix it by moving up rcu_read_unlock right before checking
transport and also to remove the out path.

Fixes: 1cceda784980 ("sctp: fix the issue sctp_diag uses lock_sock in rcu_read_lock")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index f23ad91..ca12aa3 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4479,9 +4479,10 @@ int sctp_transport_lookup_process(int (*cb)(struct sctp_transport *, void *),
 
 	rcu_read_lock();
 	transport = sctp_addrs_lookup_transport(net, laddr, paddr);
-	if (!transport || !sctp_transport_hold(transport))
+	if (!transport || !sctp_transport_hold(transport)) {
+		rcu_read_unlock();
 		goto out;
-
+	}
 	rcu_read_unlock();
 	err = cb(transport, p);
 	sctp_transport_put(transport);
-- 
2.7.4


>From 44dec74396881da932e5d50ffac7e7b9bdcda86c Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Thu, 22 Dec 2016 18:19:16 -0500
Subject: [PATCH 04/37] inet: fix IP(V6)_RECVORIGDSTADDR for udp sockets

[ Upstream commit 39b2dd765e0711e1efd1d1df089473a8dd93ad48 ]

Socket cmsg IP(V6)_RECVORIGDSTADDR checks that port range lies within
the packet. For sockets that have transport headers pulled, transport
offset can be negative. Use signed comparison to avoid overflow.

Fixes: e6afc8ace6dd ("udp: remove headers from UDP packets before queueing")
Reported-by: Nisar Jagabar <njagabar@cloudmark.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_sockglue.c | 2 +-
 net/ipv6/datagram.c    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index b8a2d63..e869773 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -137,7 +137,7 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
 	const struct iphdr *iph = ip_hdr(skb);
 	__be16 *ports = (__be16 *)skb_transport_header(skb);
 
-	if (skb_transport_offset(skb) + 4 > skb->len)
+	if (skb_transport_offset(skb) + 4 > (int)skb->len)
 		return;
 
 	/* All current transport protocols have the port numbers in the
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index ccf4055..8616d17 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -700,7 +700,7 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg,
 		struct sockaddr_in6 sin6;
 		__be16 *ports = (__be16 *) skb_transport_header(skb);
 
-		if (skb_transport_offset(skb) + 4 <= skb->len) {
+		if (skb_transport_offset(skb) + 4 <= (int)skb->len) {
 			/* All current transport protocols have the port numbers in the
 			 * first four bytes of the transport header and this function is
 			 * written with this assumption in mind.
-- 
2.7.4


>From 234fdeb0974828952d834f4f9e0737ec9fa61fe1 Mon Sep 17 00:00:00 2001
From: Dave Jones <davej@codemonkey.org.uk>
Date: Thu, 22 Dec 2016 11:16:22 -0500
Subject: [PATCH 05/37] ipv6: handle -EFAULT from skb_copy_bits

[ Upstream commit a98f91758995cb59611e61318dddd8a6956b52c3 ]

By setting certain socket options on ipv6 raw sockets, we can confuse the
length calculation in rawv6_push_pending_frames triggering a BUG_ON.

RIP: 0010:[<ffffffff817c6390>] [<ffffffff817c6390>] rawv6_sendmsg+0xc30/0xc40
RSP: 0018:ffff881f6c4a7c18  EFLAGS: 00010282
RAX: 00000000fffffff2 RBX: ffff881f6c681680 RCX: 0000000000000002
RDX: ffff881f6c4a7cf8 RSI: 0000000000000030 RDI: ffff881fed0f6a00
RBP: ffff881f6c4a7da8 R08: 0000000000000000 R09: 0000000000000009
R10: ffff881fed0f6a00 R11: 0000000000000009 R12: 0000000000000030
R13: ffff881fed0f6a00 R14: ffff881fee39ba00 R15: ffff881fefa93a80

Call Trace:
 [<ffffffff8118ba23>] ? unmap_page_range+0x693/0x830
 [<ffffffff81772697>] inet_sendmsg+0x67/0xa0
 [<ffffffff816d93f8>] sock_sendmsg+0x38/0x50
 [<ffffffff816d982f>] SYSC_sendto+0xef/0x170
 [<ffffffff816da27e>] SyS_sendto+0xe/0x10
 [<ffffffff81002910>] do_syscall_64+0x50/0xa0
 [<ffffffff817f7cbc>] entry_SYSCALL64_slow_path+0x25/0x25

Handle by jumping to the failure path if skb_copy_bits gets an EFAULT.

Reproducer:

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <sys/types.h>
#include <sys/socket.h>
#include <netinet/in.h>

#define LEN 504

int main(int argc, char* argv[])
{
	int fd;
	int zero = 0;
	char buf[LEN];

	memset(buf, 0, LEN);

	fd = socket(AF_INET6, SOCK_RAW, 7);

	setsockopt(fd, SOL_IPV6, IPV6_CHECKSUM, &zero, 4);
	setsockopt(fd, SOL_IPV6, IPV6_DSTOPTS, &buf, LEN);

	sendto(fd, buf, 1, 0, (struct sockaddr *) buf, 110);
}

Signed-off-by: Dave Jones <davej@codemonkey.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/raw.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 054a1d8..869ffc7 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -589,7 +589,11 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
 	}
 
 	offset += skb_transport_offset(skb);
-	BUG_ON(skb_copy_bits(skb, offset, &csum, 2));
+	err = skb_copy_bits(skb, offset, &csum, 2);
+	if (err < 0) {
+		ip6_flush_pending_frames(sk);
+		goto out;
+	}
 
 	/* in case cksum was not initialized */
 	if (unlikely(csum))
-- 
2.7.4


>From e55e6ccbfa137bcdb750561ba6c281752a24fc1b Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 21 Dec 2016 18:04:11 +0100
Subject: [PATCH 06/37] net, sched: fix soft lockup in tc_classify

[ Upstream commit 628185cfddf1dfb701c4efe2cfd72cf5b09f5702 ]

Shahar reported a soft lockup in tc_classify(), where we run into an
endless loop when walking the classifier chain due to tp->next == tp
which is a state we should never run into. The issue only seems to
trigger under load in the tc control path.

What happens is that in tc_ctl_tfilter(), thread A allocates a new
tp, initializes it, sets tp_created to 1, and calls into tp->ops->change()
with it. In that classifier callback we had to unlock/lock the rtnl
mutex and returned with -EAGAIN. One reason why we need to drop there
is, for example, that we need to request an action module to be loaded.

This happens via tcf_exts_validate() -> tcf_action_init/_1() meaning
after we loaded and found the requested action, we need to redo the
whole request so we don't race against others. While we had to unlock
rtnl in that time, thread B's request was processed next on that CPU.
Thread B added a new tp instance successfully to the classifier chain.
When thread A returned grabbing the rtnl mutex again, propagating -EAGAIN
and destroying its tp instance which never got linked, we goto replay
and redo A's request.

This time when walking the classifier chain in tc_ctl_tfilter() for
checking for existing tp instances we had a priority match and found
the tp instance that was created and linked by thread B. Now calling
again into tp->ops->change() with that tp was successful and returned
without error.

tp_created was never cleared in the second round, thus kernel thinks
that we need to link it into the classifier chain (once again). tp and
*back point to the same object due to the match we had earlier on. Thus
for thread B's already public tp, we reset tp->next to tp itself and
link it into the chain, which eventually causes the mentioned endless
loop in tc_classify() once a packet hits the data path.

Fix is to clear tp_created at the beginning of each request, also when
we replay it. On the paths that can cause -EAGAIN we already destroy
the original tp instance we had and on replay we really need to start
from scratch. It seems that this issue was first introduced in commit
12186be7d2e1 ("net_cls: fix unconfigured struct tcf_proto keeps chaining
and avoid kernel panic when we use cls_cgroup").

Fixes: 12186be7d2e1 ("net_cls: fix unconfigured struct tcf_proto keeps chaining and avoid kernel panic when we use cls_cgroup")
Reported-by: Shahar Klein <shahark@mellanox.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Tested-by: Shahar Klein <shahark@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index b05d4a2..c1a4b5d 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -148,13 +148,15 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n)
 	unsigned long cl;
 	unsigned long fh;
 	int err;
-	int tp_created = 0;
+	int tp_created;
 
 	if ((n->nlmsg_type != RTM_GETTFILTER) &&
 	    !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 replay:
+	tp_created = 0;
+
 	err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL);
 	if (err < 0)
 		return err;
-- 
2.7.4


>From 46e7b8c9f109e91e6a0447e0ab6ad7937ae9a6e9 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 27 Dec 2016 18:23:06 -0800
Subject: [PATCH 07/37] net: stmmac: Fix race between stmmac_drv_probe and
 stmmac_open

[ Upstream commit 5701659004d68085182d2fd4199c79172165fa65 ]

There is currently a small window during which the network device registered by
stmmac can be made visible, yet all resources, including and clock and MDIO bus
have not had a chance to be set up, this can lead to the following error to
occur:

[  473.919358] stmmaceth 0000:01:00.0 (unnamed net_device) (uninitialized):
                stmmac_dvr_probe: warning: cannot get CSR clock
[  473.919382] stmmaceth 0000:01:00.0: no reset control found
[  473.919412] stmmac - user ID: 0x10, Synopsys ID: 0x42
[  473.919429] stmmaceth 0000:01:00.0: DMA HW capability register supported
[  473.919436] stmmaceth 0000:01:00.0: RX Checksum Offload Engine supported
[  473.919443] stmmaceth 0000:01:00.0: TX Checksum insertion supported
[  473.919451] stmmaceth 0000:01:00.0 (unnamed net_device) (uninitialized):
                Enable RX Mitigation via HW Watchdog Timer
[  473.921395] libphy: PHY stmmac-1:00 not found
[  473.921417] stmmaceth 0000:01:00.0 eth0: Could not attach to PHY
[  473.921427] stmmaceth 0000:01:00.0 eth0: stmmac_open: Cannot attach to
                PHY (error: -19)
[  473.959710] libphy: stmmac: probed
[  473.959724] stmmaceth 0000:01:00.0 eth0: PHY ID 01410cc2 at 0 IRQ POLL
                (stmmac-1:00) active
[  473.959728] stmmaceth 0000:01:00.0 eth0: PHY ID 01410cc2 at 1 IRQ POLL
                (stmmac-1:01)
[  473.959731] stmmaceth 0000:01:00.0 eth0: PHY ID 01410cc2 at 2 IRQ POLL
                (stmmac-1:02)
[  473.959734] stmmaceth 0000:01:00.0 eth0: PHY ID 01410cc2 at 3 IRQ POLL
                (stmmac-1:03)

Fix this by making sure that register_netdev() is the last thing being done,
which guarantees that the clock and the MDIO bus are available.

Fixes: 4bfcbd7abce2 ("stmmac: Move the mdio_register/_unregister in probe/remove")
Reported-by: Kweh, Hock Leong <hock.leong.kweh@intel.com>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 23 +++++++++++++----------
 1 file changed, 13 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index caf069a..b2893fb 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3349,12 +3349,6 @@ int stmmac_dvr_probe(struct device *device,
 	spin_lock_init(&priv->lock);
 	spin_lock_init(&priv->tx_lock);
 
-	ret = register_netdev(ndev);
-	if (ret) {
-		pr_err("%s: ERROR %i registering the device\n", __func__, ret);
-		goto error_netdev_register;
-	}
-
 	/* If a specific clk_csr value is passed from the platform
 	 * this means that the CSR Clock Range selection cannot be
 	 * changed at run-time and it is fixed. Viceversa the driver'll try to
@@ -3376,15 +3370,24 @@ int stmmac_dvr_probe(struct device *device,
 		if (ret < 0) {
 			pr_debug("%s: MDIO bus (id: %d) registration failed",
 				 __func__, priv->plat->bus_id);
-			goto error_mdio_register;
+			goto error_napi_register;
 		}
 	}
 
-	return 0;
+	ret = register_netdev(ndev);
+	if (ret) {
+		pr_err("%s: ERROR %i registering the device\n", __func__, ret);
+		goto error_netdev_register;
+	}
+
+	return ret;
 
-error_mdio_register:
-	unregister_netdev(ndev);
 error_netdev_register:
+	if (priv->hw->pcs != STMMAC_PCS_RGMII &&
+	    priv->hw->pcs != STMMAC_PCS_TBI &&
+	    priv->hw->pcs != STMMAC_PCS_RTBI)
+		stmmac_mdio_unregister(ndev);
+error_napi_register:
 	netif_napi_del(&priv->napi);
 error_hw_init:
 	clk_disable_unprepare(priv->pclk);
-- 
2.7.4


>From 8941acf18f6391e66edfd0fbb349545d593b70da Mon Sep 17 00:00:00 2001
From: Paul Blakey <paulb@mellanox.com>
Date: Wed, 28 Dec 2016 14:54:47 +0200
Subject: [PATCH 08/37] net/sched: cls_flower: Fix missing addr_type in
 classify

[ Upstream commit 0df0f207aab4f42e5c96a807adf9a6845b69e984 ]

Since we now use a non zero mask on addr_type, we are matching on its
value (IPV4/IPV6). So before this fix, matching on enc_src_ip/enc_dst_ip
failed in SW/classify path since its value was zero.
This patch sets the proper value of addr_type for encapsulated packets.

Fixes: 970bfcd09791 ('net/sched: cls_flower: Use mask for addr_type')
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Reviewed-by: Hadar Hen Zion <hadarh@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_flower.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 9044424..eee299b 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -149,10 +149,14 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 
 		switch (ip_tunnel_info_af(info)) {
 		case AF_INET:
+			skb_key.enc_control.addr_type =
+				FLOW_DISSECTOR_KEY_IPV4_ADDRS;
 			skb_key.enc_ipv4.src = key->u.ipv4.src;
 			skb_key.enc_ipv4.dst = key->u.ipv4.dst;
 			break;
 		case AF_INET6:
+			skb_key.enc_control.addr_type =
+				FLOW_DISSECTOR_KEY_IPV6_ADDRS;
 			skb_key.enc_ipv6.src = key->u.ipv6.src;
 			skb_key.enc_ipv6.dst = key->u.ipv6.dst;
 			break;
-- 
2.7.4


>From 0e3eacd0148368b59477d83881e9165ff7ec594f Mon Sep 17 00:00:00 2001
From: Noa Osherovich <noaos@mellanox.com>
Date: Wed, 28 Dec 2016 14:58:32 +0200
Subject: [PATCH 09/37] net/mlx5: Check FW limitations on log_max_qp before
 setting it

[ Upstream commit 883371c453b937f9eb581fb4915210865982736f ]

When setting HCA capabilities, set log_max_qp to be the minimum
between the selected profile's value and the HCA limitation.

Fixes: 938fe83c8dcb ('net/mlx5_core: New device capabilities...')
Signed-off-by: Noa Osherovich <noaos@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index ada24e1..332769c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -468,6 +468,13 @@ static int handle_hca_cap(struct mlx5_core_dev *dev)
 	MLX5_SET(cmd_hca_cap, set_hca_cap, pkey_table_size,
 		 to_fw_pkey_sz(dev, 128));
 
+	/* Check log_max_qp from HCA caps to set in current profile */
+	if (MLX5_CAP_GEN_MAX(dev, log_max_qp) < profile[prof_sel].log_max_qp) {
+		mlx5_core_warn(dev, "log_max_qp value in current profile is %d, changing it to HCA capability limit (%d)\n",
+			       profile[prof_sel].log_max_qp,
+			       MLX5_CAP_GEN_MAX(dev, log_max_qp));
+		profile[prof_sel].log_max_qp = MLX5_CAP_GEN_MAX(dev, log_max_qp);
+	}
 	if (prof->mask & MLX5_PROF_MASK_QP_SIZE)
 		MLX5_SET(cmd_hca_cap, set_hca_cap, log_max_qp,
 			 prof->log_max_qp);
-- 
2.7.4


>From efeec3a3f5504fc1947488337a62c7c0d16dd1a7 Mon Sep 17 00:00:00 2001
From: Daniel Jurgens <danielj@mellanox.com>
Date: Wed, 28 Dec 2016 14:58:33 +0200
Subject: [PATCH 10/37] net/mlx5: Cancel recovery work in remove flow

[ Upstream commit 689a248df83b6032edc57e86267b4e5cc8d7174e ]

If there is pending delayed work for health recovery it must be canceled
if the device is being unloaded.

Fixes: 05ac2c0b7438 ("net/mlx5: Fix race between PCI error handlers and health work")
Signed-off-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 332769c..15b7e60 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1159,6 +1159,8 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 {
 	int err = 0;
 
+	mlx5_drain_health_wq(dev);
+
 	mutex_lock(&dev->intf_state_mutex);
 	if (test_bit(MLX5_INTERFACE_STATE_DOWN, &dev->intf_state)) {
 		dev_warn(&dev->pdev->dev, "%s: interface is down, NOP\n",
@@ -1319,10 +1321,9 @@ static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev,
 
 	mlx5_enter_error_state(dev);
 	mlx5_unload_one(dev, priv, false);
-	/* In case of kernel call save the pci state and drain health wq */
+	/* In case of kernel call save the pci state */
 	if (state) {
 		pci_save_state(pdev);
-		mlx5_drain_health_wq(dev);
 		mlx5_pci_disable_device(dev);
 	}
 
-- 
2.7.4


>From dda931a2cffceb97eae26545c2f8b72d75c724a0 Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.com>
Date: Wed, 28 Dec 2016 14:58:34 +0200
Subject: [PATCH 11/37] net/mlx5: Avoid shadowing numa_node

[ Upstream commit d151d73dcc99de87c63bdefebcc4cb69de1cdc40 ]

Avoid using a local variable named numa_node to avoid shadowing a public
one.

Fixes: db058a186f98 ('net/mlx5_core: Set irq affinity hints')
Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 15b7e60..92bd13d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -547,7 +547,6 @@ static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i)
 	struct mlx5_priv *priv  = &mdev->priv;
 	struct msix_entry *msix = priv->msix_arr;
 	int irq                 = msix[i + MLX5_EQ_VEC_COMP_BASE].vector;
-	int numa_node           = priv->numa_node;
 	int err;
 
 	if (!zalloc_cpumask_var(&priv->irq_info[i].mask, GFP_KERNEL)) {
@@ -555,7 +554,7 @@ static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i)
 		return -ENOMEM;
 	}
 
-	cpumask_set_cpu(cpumask_local_spread(i, numa_node),
+	cpumask_set_cpu(cpumask_local_spread(i, priv->numa_node),
 			priv->irq_info[i].mask);
 
 	err = irq_set_affinity_hint(irq, priv->irq_info[i].mask);
-- 
2.7.4


>From 6bd939c40912e6eec51d52ef251b785333df6b18 Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@mellanox.com>
Date: Wed, 28 Dec 2016 14:58:35 +0200
Subject: [PATCH 12/37] net/mlx5: Mask destination mac value in ethtool
 steering rules

[ Upstream commit 077b1e8069b9b74477b01d28f6b83774dc19a142 ]

We need to mask the destination mac value with the destination mac
mask when adding steering rule via ethtool.

Fixes: 1174fce8d1410 ('net/mlx5e: Support l3/l4 flow type specs in ethtool flow steering')
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index d17c242..90e81ae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -247,6 +247,7 @@ static int set_flow_attrs(u32 *match_c, u32 *match_v,
 	}
 	if (fs->flow_type & FLOW_MAC_EXT &&
 	    !is_zero_ether_addr(fs->m_ext.h_dest)) {
+		mask_spec(fs->m_ext.h_dest, fs->h_ext.h_dest, ETH_ALEN);
 		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4,
 					     outer_headers_c, dmac_47_16),
 				fs->m_ext.h_dest);
-- 
2.7.4


>From c83b1b583a985fe44ece2ca24abea71611393114 Mon Sep 17 00:00:00 2001
From: Mohamad Haj Yahia <mohamad@mellanox.com>
Date: Wed, 28 Dec 2016 14:58:37 +0200
Subject: [PATCH 13/37] net/mlx5: Prevent setting multicast macs for VFs

[ Upstream commit ccce1700263d8b5b219359d04180492a726cea16 ]

Need to check that VF mac address entered by the admin user is either
zero or unicast mac.
Multicast mac addresses are prohibited.

Fixes: 77256579c6b4 ('net/mlx5: E-Switch, Introduce Vport administration functions')
Signed-off-by: Mohamad Haj Yahia <mohamad@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index be1f733..c7011ef 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1703,7 +1703,7 @@ int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
 
 	if (!ESW_ALLOWED(esw))
 		return -EPERM;
-	if (!LEGAL_VPORT(esw, vport))
+	if (!LEGAL_VPORT(esw, vport) || is_multicast_ether_addr(mac))
 		return -EINVAL;
 
 	mutex_lock(&esw->state_lock);
-- 
2.7.4


>From 4ea5db6017b45457d2c50a42e067b20968a6720c Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Wed, 28 Dec 2016 14:58:41 +0200
Subject: [PATCH 14/37] net/mlx5e: Don't sync netdev state when not registered

[ Upstream commit 610e89e05c3f28a7394935aa6b91f99548c4fd3c ]

Skip setting netdev vxlan ports and netdev rx_mode on driver load
when netdev is not yet registered.

Synchronizing with netdev state is needed only on reset flow where the
netdev remains registered for the whole reset period.

This also fixes an access before initialization of net_device.addr_list_lock
- which for some reason initialized on register_netdev - where we queued
set_rx_mode work on driver load before netdev registration.

Fixes: 26e59d8077a3 ("net/mlx5e: Implement mlx5e interface attach/detach callbacks")
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reported-by: Sebastian Ott <sebott@linux.vnet.ibm.com>
Reviewed-by: Mohamad Haj Yahia <mohamad@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 246d98e..307b270 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3773,14 +3773,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 
 	mlx5_lag_add(mdev, netdev);
 
-	if (mlx5e_vxlan_allowed(mdev)) {
-		rtnl_lock();
-		udp_tunnel_get_rx_info(netdev);
-		rtnl_unlock();
-	}
-
 	mlx5e_enable_async_events(priv);
-	queue_work(priv->wq, &priv->set_rx_mode_work);
 
 	if (MLX5_CAP_GEN(mdev, vport_group_manager)) {
 		mlx5_query_nic_vport_mac_address(mdev, 0, rep.hw_id);
@@ -3790,6 +3783,18 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 		rep.priv_data = priv;
 		mlx5_eswitch_register_vport_rep(esw, 0, &rep);
 	}
+
+	if (netdev->reg_state != NETREG_REGISTERED)
+		return;
+
+	/* Device already registered: sync netdev system state */
+	if (mlx5e_vxlan_allowed(mdev)) {
+		rtnl_lock();
+		udp_tunnel_get_rx_info(netdev);
+		rtnl_unlock();
+	}
+
+	queue_work(priv->wq, &priv->set_rx_mode_work);
 }
 
 static void mlx5e_nic_disable(struct mlx5e_priv *priv)
-- 
2.7.4


>From c078e5909b40fdf6ac4294ce493600498825f709 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Wed, 28 Dec 2016 14:58:42 +0200
Subject: [PATCH 15/37] net/mlx5e: Disable netdev after close

[ Upstream commit 37f304d10030bb425c19099e7b955d9c3ec4cba3 ]

Disable netdev should come after it was closed, although no harm of doing it
before -hence the MLX5E_STATE_DESTROYING bit- but it is more natural this way.

Fixes: 26e59d8077a3 ("net/mlx5e: Implement mlx5e interface attach/detach callbacks")
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Mohamad Haj Yahia <mohamad@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 307b270..5dc3e24 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3942,10 +3942,6 @@ void mlx5e_detach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev)
 	const struct mlx5e_profile *profile = priv->profile;
 
 	set_bit(MLX5E_STATE_DESTROYING, &priv->state);
-	if (profile->disable)
-		profile->disable(priv);
-
-	flush_workqueue(priv->wq);
 
 	rtnl_lock();
 	if (netif_running(netdev))
@@ -3953,6 +3949,10 @@ void mlx5e_detach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev)
 	netif_device_detach(netdev);
 	rtnl_unlock();
 
+	if (profile->disable)
+		profile->disable(priv);
+	flush_workqueue(priv->wq);
+
 	mlx5e_destroy_q_counter(priv);
 	profile->cleanup_rx(priv);
 	mlx5e_close_drop_rq(priv);
-- 
2.7.4


>From b6484b1c5e7ad5191307b45f41a3bba917123ada Mon Sep 17 00:00:00 2001
From: Mathias Krause <minipli@googlemail.com>
Date: Wed, 28 Dec 2016 17:52:15 +0100
Subject: [PATCH 16/37] rtnl: stats - add missing netlink message size checks

[ Upstream commit 4775cc1f2d5abca894ac32774eefc22c45347d1c ]

We miss to check if the netlink message is actually big enough to contain
a struct if_stats_msg.

Add a check to prevent userland from sending us short messages that would
make us access memory beyond the end of the message.

Fixes: 10c9ead9f3c6 ("rtnetlink: add new RTM_GETSTATS message to dump...")
Signed-off-by: Mathias Krause <minipli@googlemail.com>
Cc: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index a6196cf..b7f9ae7 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3886,6 +3886,9 @@ static int rtnl_stats_get(struct sk_buff *skb, struct nlmsghdr *nlh)
 	u32 filter_mask;
 	int err;
 
+	if (nlmsg_len(nlh) < sizeof(*ifsm))
+		return -EINVAL;
+
 	ifsm = nlmsg_data(nlh);
 	if (ifsm->ifindex > 0)
 		dev = __dev_get_by_index(net, ifsm->ifindex);
@@ -3935,6 +3938,9 @@ static int rtnl_stats_dump(struct sk_buff *skb, struct netlink_callback *cb)
 
 	cb->seq = net->dev_base_seq;
 
+	if (nlmsg_len(cb->nlh) < sizeof(*ifsm))
+		return -EINVAL;
+
 	ifsm = nlmsg_data(cb->nlh);
 	filter_mask = ifsm->filter_mask;
 	if (!filter_mask)
-- 
2.7.4


>From 1c0bd98c345cb615972a9f8ce5bbad53ea880132 Mon Sep 17 00:00:00 2001
From: Wei Zhang <asuka.com@163.com>
Date: Thu, 29 Dec 2016 16:45:04 +0800
Subject: [PATCH 17/37] net: fix incorrect original ingress device index in
 PKTINFO

[ Upstream commit f0c16ba8933ed217c2688b277410b2a37ba81591 ]

When we send a packet for our own local address on a non-loopback
interface (e.g. eth0), due to the change had been introduced from
commit 0b922b7a829c ("net: original ingress device index in PKTINFO"), the
original ingress device index would be set as the loopback interface.
However, the packet should be considered as if it is being arrived via the
sending interface (eth0), otherwise it would break the expectation of the
userspace application (e.g. the DHCPRELEASE message from dhcp_release
binary would be ignored by the dnsmasq daemon, since it come from lo which
is not the interface dnsmasq bind to)

Fixes: 0b922b7a829c ("net: original ingress device index in PKTINFO")
Acked-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: Wei Zhang <asuka.com@163.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_sockglue.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index e869773..f226f408 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1202,8 +1202,14 @@ void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb)
 		 * which has interface index (iif) as the first member of the
 		 * underlying inet{6}_skb_parm struct. This code then overlays
 		 * PKTINFO_SKB_CB and in_pktinfo also has iif as the first
-		 * element so the iif is picked up from the prior IPCB
+		 * element so the iif is picked up from the prior IPCB. If iif
+		 * is the loopback interface, then return the sending interface
+		 * (e.g., process binds socket to eth0 for Tx which is
+		 * redirected to loopback in the rtable/dst).
 		 */
+		if (pktinfo->ipi_ifindex == LOOPBACK_IFINDEX)
+			pktinfo->ipi_ifindex = inet_iif(skb);
+
 		pktinfo->ipi_spec_dst.s_addr = fib_compute_spec_dst(skb);
 	} else {
 		pktinfo->ipi_ifindex = 0;
-- 
2.7.4


>From c2736efebfed992e05763f1ec50ecd9cd4b804ac Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Thu, 29 Dec 2016 15:29:03 -0800
Subject: [PATCH 18/37] net: ipv4: dst for local input routes should use l3mdev
 if relevant

[ Upstream commit f5a0aab84b74de68523599817569c057c7ac1622 ]

IPv4 output routes already use l3mdev device instead of loopback for dst's
if it is applicable. Change local input routes to do the same.

This fixes icmp responses for unreachable UDP ports which are directed
to the wrong table after commit 9d1a6c4ea43e4 because local_input
routes use the loopback device. Moving from ingress device to loopback
loses the L3 domain causing responses based on the dst to get to lost.

Fixes: 9d1a6c4ea43e4 ("net: icmp_route_lookup should use rt dev to
		       determine L3 domain")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 2a57566..8197b06 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1902,7 +1902,8 @@ out:	return err;
 		}
 	}
 
-	rth = rt_dst_alloc(net->loopback_dev, flags | RTCF_LOCAL, res.type,
+	rth = rt_dst_alloc(l3mdev_master_dev_rcu(dev) ? : net->loopback_dev,
+			   flags | RTCF_LOCAL, res.type,
 			   IN_DEV_CONF_GET(in_dev, NOPOLICY), false, do_cache);
 	if (!rth)
 		goto e_nobufs;
-- 
2.7.4


>From 5a132f59f6fe185a85b168ee11136f7862111eeb Mon Sep 17 00:00:00 2001
From: Reiter Wolfgang <wr0112358@gmail.com>
Date: Sat, 31 Dec 2016 21:11:57 +0100
Subject: [PATCH 19/37] drop_monitor: add missing call to genlmsg_end

[ Upstream commit 4200462d88f47f3759bdf4705f87e207b0f5b2e4 ]

Update nlmsg_len field with genlmsg_end to enable userspace processing
using nlmsg_next helper. Also adds error handling.

Signed-off-by: Reiter Wolfgang <wr0112358@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/drop_monitor.c | 33 ++++++++++++++++++++++++---------
 1 file changed, 24 insertions(+), 9 deletions(-)

diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 72cfb0c..5de61aa 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -80,6 +80,7 @@ static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data)
 	struct nlattr *nla;
 	struct sk_buff *skb;
 	unsigned long flags;
+	void *msg_header;
 
 	al = sizeof(struct net_dm_alert_msg);
 	al += dm_hit_limit * sizeof(struct net_dm_drop_point);
@@ -87,17 +88,31 @@ static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data)
 
 	skb = genlmsg_new(al, GFP_KERNEL);
 
-	if (skb) {
-		genlmsg_put(skb, 0, 0, &net_drop_monitor_family,
-				0, NET_DM_CMD_ALERT);
-		nla = nla_reserve(skb, NLA_UNSPEC,
-				  sizeof(struct net_dm_alert_msg));
-		msg = nla_data(nla);
-		memset(msg, 0, al);
-	} else {
-		mod_timer(&data->send_timer, jiffies + HZ / 10);
+	if (!skb)
+		goto err;
+
+	msg_header = genlmsg_put(skb, 0, 0, &net_drop_monitor_family,
+				 0, NET_DM_CMD_ALERT);
+	if (!msg_header) {
+		nlmsg_free(skb);
+		skb = NULL;
+		goto err;
+	}
+	nla = nla_reserve(skb, NLA_UNSPEC,
+			  sizeof(struct net_dm_alert_msg));
+	if (!nla) {
+		nlmsg_free(skb);
+		skb = NULL;
+		goto err;
 	}
+	msg = nla_data(nla);
+	memset(msg, 0, al);
+	genlmsg_end(skb, msg_header);
+	goto out;
 
+err:
+	mod_timer(&data->send_timer, jiffies + HZ / 10);
+out:
 	spin_lock_irqsave(&data->lock, flags);
 	swap(data->skb, skb);
 	spin_unlock_irqrestore(&data->lock, flags);
-- 
2.7.4


>From e606a46798f5b6829d535877671e988e9e0e02c8 Mon Sep 17 00:00:00 2001
From: Reiter Wolfgang <wr0112358@gmail.com>
Date: Tue, 3 Jan 2017 01:39:10 +0100
Subject: [PATCH 20/37] drop_monitor: consider inserted data in genlmsg_end

[ Upstream commit 3b48ab2248e61408910e792fe84d6ec466084c1a ]

Final nlmsg_len field update must reflect inserted net_dm_drop_point
data.

This patch depends on previous patch:
"drop_monitor: add missing call to genlmsg_end"

Signed-off-by: Reiter Wolfgang <wr0112358@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/drop_monitor.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 5de61aa..ca2c9c8 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -107,7 +107,6 @@ static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data)
 	}
 	msg = nla_data(nla);
 	memset(msg, 0, al);
-	genlmsg_end(skb, msg_header);
 	goto out;
 
 err:
@@ -117,6 +116,13 @@ static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data)
 	swap(data->skb, skb);
 	spin_unlock_irqrestore(&data->lock, flags);
 
+	if (skb) {
+		struct nlmsghdr *nlh = (struct nlmsghdr *)skb->data;
+		struct genlmsghdr *gnlh = (struct genlmsghdr *)nlmsg_data(nlh);
+
+		genlmsg_end(skb, genlmsg_data(gnlh));
+	}
+
 	return skb;
 }
 
-- 
2.7.4


>From 64e0f8601bf0e45f088f8879df8f79944451394f Mon Sep 17 00:00:00 2001
From: Ian Kumlien <ian.kumlien@gmail.com>
Date: Mon, 2 Jan 2017 09:18:35 +0100
Subject: [PATCH 21/37] flow_dissector: Update pptp handling to avoid null
 pointer deref.

[ Upstream commit d0af683407a26a4437d8fa6e283ea201f2ae8146 ]

__skb_flow_dissect can be called with a skb or a data packet, either
can be NULL. All calls seems to have been moved to __skb_header_pointer
except the pptp handling which is still calling skb_header_pointer.

skb_header_pointer will use skb->data and thus:
[  109.556866] BUG: unable to handle kernel NULL pointer dereference at 0000000000000080
[  109.557102] IP: [<ffffffff88dc02f8>] __skb_flow_dissect+0xa88/0xce0
[  109.557263] PGD 0
[  109.557338]
[  109.557484] Oops: 0000 [#1] SMP
[  109.557562] Modules linked in: chaoskey
[  109.557783] CPU: 2 PID: 0 Comm: swapper/2 Not tainted 4.9.0 #79
[  109.557867] Hardware name: Supermicro A1SRM-LN7F/LN5F/A1SRM-LN7F-2758, BIOS 1.0c 11/04/2015
[  109.557957] task: ffff94085c27bc00 task.stack: ffffb745c0068000
[  109.558041] RIP: 0010:[<ffffffff88dc02f8>]  [<ffffffff88dc02f8>] __skb_flow_dissect+0xa88/0xce0
[  109.558203] RSP: 0018:ffff94087fc83d40  EFLAGS: 00010206
[  109.558286] RAX: 0000000000000130 RBX: ffffffff8975bf80 RCX: ffff94084fab6800
[  109.558373] RDX: 0000000000000010 RSI: 000000000000000c RDI: 0000000000000000
[  109.558460] RBP: 0000000000000b88 R08: 0000000000000000 R09: 0000000000000022
[  109.558547] R10: 0000000000000008 R11: ffff94087fc83e04 R12: 0000000000000000
[  109.558763] R13: ffff94084fab6800 R14: ffff94087fc83e04 R15: 000000000000002f
[  109.558979] FS:  0000000000000000(0000) GS:ffff94087fc80000(0000) knlGS:0000000000000000
[  109.559326] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  109.559539] CR2: 0000000000000080 CR3: 0000000281809000 CR4: 00000000001026e0
[  109.559753] Stack:
[  109.559957]  000000000000000c ffff94084fab6822 0000000000000001 ffff94085c2b5fc0
[  109.560578]  0000000000000001 0000000000002000 0000000000000000 0000000000000000
[  109.561200]  0000000000000000 0000000000000000 0000000000000000 0000000000000000
[  109.561820] Call Trace:
[  109.562027]  <IRQ>
[  109.562108]  [<ffffffff88dfb4fa>] ? eth_get_headlen+0x7a/0xf0
[  109.562522]  [<ffffffff88c5a35a>] ? igb_poll+0x96a/0xe80
[  109.562737]  [<ffffffff88dc912b>] ? net_rx_action+0x20b/0x350
[  109.562953]  [<ffffffff88546d68>] ? __do_softirq+0xe8/0x280
[  109.563169]  [<ffffffff8854704a>] ? irq_exit+0xaa/0xb0
[  109.563382]  [<ffffffff8847229b>] ? do_IRQ+0x4b/0xc0
[  109.563597]  [<ffffffff8902d4ff>] ? common_interrupt+0x7f/0x7f
[  109.563810]  <EOI>
[  109.563890]  [<ffffffff88d57530>] ? cpuidle_enter_state+0x130/0x2c0
[  109.564304]  [<ffffffff88d57520>] ? cpuidle_enter_state+0x120/0x2c0
[  109.564520]  [<ffffffff8857eacf>] ? cpu_startup_entry+0x19f/0x1f0
[  109.564737]  [<ffffffff8848d55a>] ? start_secondary+0x12a/0x140
[  109.564950] Code: 83 e2 20 a8 80 0f 84 60 01 00 00 c7 04 24 08 00
00 00 66 85 d2 0f 84 be fe ff ff e9 69 fe ff ff 8b 34 24 89 f2 83 c2
04 66 85 c0 <41> 8b 84 24 80 00 00 00 0f 49 d6 41 8d 31 01 d6 41 2b 84
24 84
[  109.569959] RIP  [<ffffffff88dc02f8>] __skb_flow_dissect+0xa88/0xce0
[  109.570245]  RSP <ffff94087fc83d40>
[  109.570453] CR2: 0000000000000080

Fixes: ab10dccb1160 ("rps: Inspect PPTP encapsulated by GRE to get flow hash")
Signed-off-by: Ian Kumlien <ian.kumlien@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/flow_dissector.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index c6d8207..32e4e01 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -445,8 +445,9 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
 			if (hdr->flags & GRE_ACK)
 				offset += sizeof(((struct pptp_gre_header *)0)->ack);
 
-			ppp_hdr = skb_header_pointer(skb, nhoff + offset,
-						     sizeof(_ppp_hdr), _ppp_hdr);
+			ppp_hdr = __skb_header_pointer(skb, nhoff + offset,
+						     sizeof(_ppp_hdr),
+						     data, hlen, _ppp_hdr);
 			if (!ppp_hdr)
 				goto out_bad;
 
-- 
2.7.4


>From 0d094f9e59706a3046b2eaf551732038866dd928 Mon Sep 17 00:00:00 2001
From: Michal Tesar <mtesar@redhat.com>
Date: Mon, 2 Jan 2017 14:38:36 +0100
Subject: [PATCH 22/37] igmp: Make igmp group member RFC 3376 compliant

[ Upstream commit 7ababb782690e03b78657e27bd051e20163af2d6 ]

5.2. Action on Reception of a Query

 When a system receives a Query, it does not respond immediately.
 Instead, it delays its response by a random amount of time, bounded
 by the Max Resp Time value derived from the Max Resp Code in the
 received Query message.  A system may receive a variety of Queries on
 different interfaces and of different kinds (e.g., General Queries,
 Group-Specific Queries, and Group-and-Source-Specific Queries), each
 of which may require its own delayed response.

 Before scheduling a response to a Query, the system must first
 consider previously scheduled pending responses and in many cases
 schedule a combined response.  Therefore, the system must be able to
 maintain the following state:

 o A timer per interface for scheduling responses to General Queries.

 o A per-group and interface timer for scheduling responses to Group-
   Specific and Group-and-Source-Specific Queries.

 o A per-group and interface list of sources to be reported in the
   response to a Group-and-Source-Specific Query.

 When a new Query with the Router-Alert option arrives on an
 interface, provided the system has state to report, a delay for a
 response is randomly selected in the range (0, [Max Resp Time]) where
 Max Resp Time is derived from Max Resp Code in the received Query
 message.  The following rules are then used to determine if a Report
 needs to be scheduled and the type of Report to schedule.  The rules
 are considered in order and only the first matching rule is applied.

 1. If there is a pending response to a previous General Query
    scheduled sooner than the selected delay, no additional response
    needs to be scheduled.

 2. If the received Query is a General Query, the interface timer is
    used to schedule a response to the General Query after the
    selected delay.  Any previously pending response to a General
    Query is canceled.
--8<--

Currently the timer is rearmed with new random expiration time for
every incoming query regardless of possibly already pending report.
Which is not aligned with the above RFE.
It also might happen that higher rate of incoming queries can
postpone the report after the expiration time of the first query
causing group membership loss.

Now the per interface general query timer is rearmed only
when there is no pending report already scheduled on that interface or
the newly selected expiration time is before the already pending
scheduled report.

Signed-off-by: Michal Tesar <mtesar@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/igmp.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 15db786..32a08bc 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -219,9 +219,14 @@ static void igmp_start_timer(struct ip_mc_list *im, int max_delay)
 static void igmp_gq_start_timer(struct in_device *in_dev)
 {
 	int tv = prandom_u32() % in_dev->mr_maxdelay;
+	unsigned long exp = jiffies + tv + 2;
+
+	if (in_dev->mr_gq_running &&
+	    time_after_eq(exp, (in_dev->mr_gq_timer).expires))
+		return;
 
 	in_dev->mr_gq_running = 1;
-	if (!mod_timer(&in_dev->mr_gq_timer, jiffies+tv+2))
+	if (!mod_timer(&in_dev->mr_gq_timer, exp))
 		in_dev_hold(in_dev);
 }
 
-- 
2.7.4


>From 936a42dd615006e49e9f0b6014330b86f692ae6c Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Mon, 2 Jan 2017 13:32:54 -0800
Subject: [PATCH 23/37] ipv4: Do not allow MAIN to be alias for new LOCAL w/
 custom rules

[ Upstream commit 5350d54f6cd12eaff623e890744c79b700bd3f17 ]

In the case of custom rules being present we need to handle the case of the
LOCAL table being intialized after the new rule has been added.  To address
that I am adding a new check so that we can make certain we don't use an
alias of MAIN for LOCAL when allocating a new table.

Fixes: 0ddcf43d5d4a ("ipv4: FIB Local/MAIN table collapse")
Reported-by: Oliver Brunel <jjk@jjacky.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_frontend.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 161fc0f..3e4f183 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -85,7 +85,7 @@ struct fib_table *fib_new_table(struct net *net, u32 id)
 	if (tb)
 		return tb;
 
-	if (id == RT_TABLE_LOCAL)
+	if (id == RT_TABLE_LOCAL && !net->ipv4.fib_has_custom_rules)
 		alias = fib_new_table(net, RT_TABLE_MAIN);
 
 	tb = fib_trie_table(id, alias);
-- 
2.7.4


>From e888a3b2b419b4d7729b35f5ed83dda17939f7ee Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Tue, 3 Jan 2017 09:37:55 -0800
Subject: [PATCH 24/37] net: vrf: Add missing Rx counters

[ Upstream commit 926d93a33e59b2729afdbad357233c17184de9d2 ]

The move from rx-handler to L3 receive handler inadvertantly dropped the
rx counters. Restore them.

Fixes: 74b20582ac38 ("net: l3mdev: Add hook in ip and ipv6")
Reported-by: Dinesh Dutt <ddutt@cumulusnetworks.com>
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 3cb3588..809a796 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -968,6 +968,7 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev,
 	 */
 	need_strict = rt6_need_strict(&ipv6_hdr(skb)->daddr);
 	if (!ipv6_ndisc_frame(skb) && !need_strict) {
+		vrf_rx_stats(vrf_dev, skb->len);
 		skb->dev = vrf_dev;
 		skb->skb_iif = vrf_dev->ifindex;
 
@@ -1009,6 +1010,8 @@ static struct sk_buff *vrf_ip_rcv(struct net_device *vrf_dev,
 		goto out;
 	}
 
+	vrf_rx_stats(vrf_dev, skb->len);
+
 	skb_push(skb, skb->mac_len);
 	dev_queue_xmit_nit(skb, vrf_dev);
 	skb_pull(skb, skb->mac_len);
-- 
2.7.4


>From 6753205ca80ed9a0aa3cb983f92cd9ac33c1e1b0 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Sat, 7 Jan 2017 00:26:33 +0100
Subject: [PATCH 25/37] bpf: change back to orig prog on too many passes

[ Upstream commit 9d5ecb09d525469abd1a10c096cb5a17206523f2 ]

If after too many passes still no image could be emitted, then
swap back to the original program as we do in all other cases
and don't use the one with blinding.

Fixes: 959a75791603 ("bpf, x86: add support for constant blinding")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/x86/net/bpf_jit_comp.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index fe04a04..15f7436 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1172,6 +1172,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		set_memory_ro((unsigned long)header, header->pages);
 		prog->bpf_func = (void *)image;
 		prog->jited = 1;
+	} else {
+		prog = orig_prog;
 	}
 
 out_addrs:
-- 
2.7.4


>From d8bb61086e84956d2b6bc146471c0c12fe73729a Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Sat, 7 Jan 2017 21:01:56 -0800
Subject: [PATCH 26/37] net: dsa: bcm_sf2: Do not clobber b53_switch_ops

[ Upstream commit a4c61b92b3a4cbda35bb0251a5063a68f0861b2c ]

We make the bcm_sf2 driver override ds->ops which points to
b53_switch_ops since b53_switch_alloc() did the assignent. This is all
well and good until a second b53 switch comes in, and ends up using the
bcm_sf2 operations. Make a proper local copy, substitute the ds->ops
pointer and then override the operations.

Fixes: f458995b9ad8 ("net: dsa: bcm_sf2: Utilize core B53 driver when possible")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 9ec33b5..2f9f910 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -982,6 +982,7 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev)
 	const char *reg_names[BCM_SF2_REGS_NUM] = BCM_SF2_REGS_NAME;
 	struct device_node *dn = pdev->dev.of_node;
 	struct b53_platform_data *pdata;
+	struct dsa_switch_ops *ops;
 	struct bcm_sf2_priv *priv;
 	struct b53_device *dev;
 	struct dsa_switch *ds;
@@ -995,6 +996,10 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev)
 	if (!priv)
 		return -ENOMEM;
 
+	ops = devm_kzalloc(&pdev->dev, sizeof(*ops), GFP_KERNEL);
+	if (!ops)
+		return -ENOMEM;
+
 	dev = b53_switch_alloc(&pdev->dev, &bcm_sf2_io_ops, priv);
 	if (!dev)
 		return -ENOMEM;
@@ -1014,6 +1019,8 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev)
 	ds = dev->ds;
 
 	/* Override the parts that are non-standard wrt. normal b53 devices */
+	memcpy(ops, ds->ops, sizeof(*ops));
+	ds->ops = ops;
 	ds->ops->get_tag_protocol = bcm_sf2_sw_get_tag_protocol;
 	ds->ops->setup = bcm_sf2_sw_setup;
 	ds->ops->get_phy_flags = bcm_sf2_sw_get_phy_flags;
-- 
2.7.4


>From 9af108aef47c3ba6869a2fdb87bfe910f52c79cd Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Sat, 7 Jan 2017 21:01:57 -0800
Subject: [PATCH 27/37] net: dsa: bcm_sf2: Utilize nested MDIO read/write

[ Upstream commit 2cfe8f8290bd28cf1ee67db914a6e76cf8e6437b ]

We are implementing a MDIO bus which is behind another one, so use the
nested version of the accessors to get lockdep annotations correct.

Fixes: 461cd1b03e32 ("net: dsa: bcm_sf2: Register our slave MDIO bus")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 2f9f910..2ce7ae9 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -393,7 +393,7 @@ static int bcm_sf2_sw_mdio_read(struct mii_bus *bus, int addr, int regnum)
 	if (addr == BRCM_PSEUDO_PHY_ADDR && priv->indir_phy_mask & BIT(addr))
 		return bcm_sf2_sw_indir_rw(priv, 1, addr, regnum, 0);
 	else
-		return mdiobus_read(priv->master_mii_bus, addr, regnum);
+		return mdiobus_read_nested(priv->master_mii_bus, addr, regnum);
 }
 
 static int bcm_sf2_sw_mdio_write(struct mii_bus *bus, int addr, int regnum,
@@ -407,7 +407,7 @@ static int bcm_sf2_sw_mdio_write(struct mii_bus *bus, int addr, int regnum,
 	if (addr == BRCM_PSEUDO_PHY_ADDR && priv->indir_phy_mask & BIT(addr))
 		bcm_sf2_sw_indir_rw(priv, 0, addr, regnum, val);
 	else
-		mdiobus_write(priv->master_mii_bus, addr, regnum, val);
+		mdiobus_write_nested(priv->master_mii_bus, addr, regnum, val);
 
 	return 0;
 }
-- 
2.7.4


>From c006857a93c7c5022d3c881c879d93ecd674b9a1 Mon Sep 17 00:00:00 2001
From: hayeswang <hayeswang@realtek.com>
Date: Tue, 10 Jan 2017 17:04:06 +0800
Subject: [PATCH 28/37] r8152: split rtl8152_suspend function

[ Upstream commit 8fb280616878b81c0790a0c33acbeec59c5711f4 ]

Split rtl8152_suspend() into rtl8152_system_suspend() and
rtl8152_rumtime_suspend().

Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 57 ++++++++++++++++++++++++++++++++++---------------
 1 file changed, 40 insertions(+), 17 deletions(-)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index efb84f0..1d1fc37 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -3576,39 +3576,62 @@ static bool delay_autosuspend(struct r8152 *tp)
 		return false;
 }
 
-static int rtl8152_suspend(struct usb_interface *intf, pm_message_t message)
+static int rtl8152_rumtime_suspend(struct r8152 *tp)
 {
-	struct r8152 *tp = usb_get_intfdata(intf);
 	struct net_device *netdev = tp->netdev;
 	int ret = 0;
 
-	mutex_lock(&tp->control);
-
-	if (PMSG_IS_AUTO(message)) {
-		if (netif_running(netdev) && delay_autosuspend(tp)) {
+	if (netif_running(netdev) && test_bit(WORK_ENABLE, &tp->flags)) {
+		if (delay_autosuspend(tp)) {
 			ret = -EBUSY;
 			goto out1;
 		}
 
-		set_bit(SELECTIVE_SUSPEND, &tp->flags);
-	} else {
-		netif_device_detach(netdev);
+		clear_bit(WORK_ENABLE, &tp->flags);
+		usb_kill_urb(tp->intr_urb);
+		napi_disable(&tp->napi);
+		rtl_stop_rx(tp);
+		tp->rtl_ops.autosuspend_en(tp, true);
+		napi_enable(&tp->napi);
 	}
 
+	set_bit(SELECTIVE_SUSPEND, &tp->flags);
+
+out1:
+	return ret;
+}
+
+static int rtl8152_system_suspend(struct r8152 *tp)
+{
+	struct net_device *netdev = tp->netdev;
+	int ret = 0;
+
+	netif_device_detach(netdev);
+
 	if (netif_running(netdev) && test_bit(WORK_ENABLE, &tp->flags)) {
 		clear_bit(WORK_ENABLE, &tp->flags);
 		usb_kill_urb(tp->intr_urb);
 		napi_disable(&tp->napi);
-		if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
-			rtl_stop_rx(tp);
-			tp->rtl_ops.autosuspend_en(tp, true);
-		} else {
-			cancel_delayed_work_sync(&tp->schedule);
-			tp->rtl_ops.down(tp);
-		}
+		cancel_delayed_work_sync(&tp->schedule);
+		tp->rtl_ops.down(tp);
 		napi_enable(&tp->napi);
 	}
-out1:
+
+	return ret;
+}
+
+static int rtl8152_suspend(struct usb_interface *intf, pm_message_t message)
+{
+	struct r8152 *tp = usb_get_intfdata(intf);
+	int ret;
+
+	mutex_lock(&tp->control);
+
+	if (PMSG_IS_AUTO(message))
+		ret = rtl8152_rumtime_suspend(tp);
+	else
+		ret = rtl8152_system_suspend(tp);
+
 	mutex_unlock(&tp->control);
 
 	return ret;
-- 
2.7.4


>From 52746c2fe0aee121081e4ce28766cbccb1aaf25a Mon Sep 17 00:00:00 2001
From: hayeswang <hayeswang@realtek.com>
Date: Tue, 10 Jan 2017 17:04:07 +0800
Subject: [PATCH 29/37] r8152: fix rx issue for runtime suspend

[ Upstream commit 75dc692eda114cb234a46cb11893a9c3ea520934 ]

Pause the rx and make sure the rx fifo is empty when the autosuspend
occurs.

If the rx data comes when the driver is canceling the rx urb, the host
controller would stop getting the data from the device and continue
it after next rx urb is submitted. That is, one continuing data is
split into two different urb buffers. That let the driver take the
data as a rx descriptor, and unexpected behavior happens.

Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 31 ++++++++++++++++++++++++++++---
 1 file changed, 28 insertions(+), 3 deletions(-)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 1d1fc37..4b5cb16 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -3582,17 +3582,42 @@ static int rtl8152_rumtime_suspend(struct r8152 *tp)
 	int ret = 0;
 
 	if (netif_running(netdev) && test_bit(WORK_ENABLE, &tp->flags)) {
+		u32 rcr = 0;
+
 		if (delay_autosuspend(tp)) {
 			ret = -EBUSY;
 			goto out1;
 		}
 
+		if (netif_carrier_ok(netdev)) {
+			u32 ocp_data;
+
+			rcr = ocp_read_dword(tp, MCU_TYPE_PLA, PLA_RCR);
+			ocp_data = rcr & ~RCR_ACPT_ALL;
+			ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RCR, ocp_data);
+			rxdy_gated_en(tp, true);
+			ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA,
+						 PLA_OOB_CTRL);
+			if (!(ocp_data & RXFIFO_EMPTY)) {
+				rxdy_gated_en(tp, false);
+				ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RCR, rcr);
+				ret = -EBUSY;
+				goto out1;
+			}
+		}
+
 		clear_bit(WORK_ENABLE, &tp->flags);
 		usb_kill_urb(tp->intr_urb);
-		napi_disable(&tp->napi);
-		rtl_stop_rx(tp);
+
 		tp->rtl_ops.autosuspend_en(tp, true);
-		napi_enable(&tp->napi);
+
+		if (netif_carrier_ok(netdev)) {
+			napi_disable(&tp->napi);
+			rtl_stop_rx(tp);
+			rxdy_gated_en(tp, false);
+			ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RCR, rcr);
+			napi_enable(&tp->napi);
+		}
 	}
 
 	set_bit(SELECTIVE_SUSPEND, &tp->flags);
-- 
2.7.4


>From 597031f66434870163bcf5fac8c29f6d0db5c06a Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Mon, 9 Jan 2017 11:58:34 -0800
Subject: [PATCH 30/37] net: dsa: Ensure validity of dst->ds[0]

[ Upstream commit faf3a932fbeb77860226a8323eacb835edc98648 ]

It is perfectly possible to have non zero indexed switches being present
in a DSA switch tree, in such a case, we will be deferencing a NULL
pointer while dsa_cpu_port_ethtool_{setup,restore}. Be more defensive
and ensure that dst->ds[0] is valid before doing anything with it.

Fixes: 0c73c523cf73 ("net: dsa: Initialize CPU port ethtool ops per tree")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/dsa2.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index 5fff951..da38621 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -394,9 +394,11 @@ static int dsa_dst_apply(struct dsa_switch_tree *dst)
 			return err;
 	}
 
-	err = dsa_cpu_port_ethtool_setup(dst->ds[0]);
-	if (err)
-		return err;
+	if (dst->ds[0]) {
+		err = dsa_cpu_port_ethtool_setup(dst->ds[0]);
+		if (err)
+			return err;
+	}
 
 	/* If we use a tagging format that doesn't have an ethertype
 	 * field, make sure that all packets from this point on get
@@ -433,7 +435,8 @@ static void dsa_dst_unapply(struct dsa_switch_tree *dst)
 		dsa_ds_unapply(dst, ds);
 	}
 
-	dsa_cpu_port_ethtool_restore(dst->ds[0]);
+	if (dst->ds[0])
+		dsa_cpu_port_ethtool_restore(dst->ds[0]);
 
 	pr_info("DSA: tree %d unapplied\n", dst->tree);
 	dst->applied = false;
-- 
2.7.4


>From ebcb2f33f7258ad041003398b854744371fd61a9 Mon Sep 17 00:00:00 2001
From: "Anna, Suman" <s-anna@ti.com>
Date: Mon, 9 Jan 2017 21:48:56 -0600
Subject: [PATCH 31/37] net: add the AF_QIPCRTR entries to family name tables

[ Upstream commit 5d722b3024f6762addb8642ffddc9f275b5107ae ]

Commit bdabad3e363d ("net: Add Qualcomm IPC router") introduced a
new address family. Update the family name tables accordingly so
that the lockdep initialization can use the proper names for this
family.

Cc: Courtney Cavin <courtney.cavin@sonymobile.com>
Cc: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: Suman Anna <s-anna@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index 00a074d..bc6543f 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -222,7 +222,7 @@ static const char *const af_family_key_strings[AF_MAX+1] = {
   "sk_lock-AF_RXRPC" , "sk_lock-AF_ISDN"     , "sk_lock-AF_PHONET"   ,
   "sk_lock-AF_IEEE802154", "sk_lock-AF_CAIF" , "sk_lock-AF_ALG"      ,
   "sk_lock-AF_NFC"   , "sk_lock-AF_VSOCK"    , "sk_lock-AF_KCM"      ,
-  "sk_lock-AF_MAX"
+  "sk_lock-AF_QIPCRTR", "sk_lock-AF_MAX"
 };
 static const char *const af_family_slock_key_strings[AF_MAX+1] = {
   "slock-AF_UNSPEC", "slock-AF_UNIX"     , "slock-AF_INET"     ,
@@ -239,7 +239,7 @@ static const char *const af_family_slock_key_strings[AF_MAX+1] = {
   "slock-AF_RXRPC" , "slock-AF_ISDN"     , "slock-AF_PHONET"   ,
   "slock-AF_IEEE802154", "slock-AF_CAIF" , "slock-AF_ALG"      ,
   "slock-AF_NFC"   , "slock-AF_VSOCK"    ,"slock-AF_KCM"       ,
-  "slock-AF_MAX"
+  "slock-AF_QIPCRTR", "slock-AF_MAX"
 };
 static const char *const af_family_clock_key_strings[AF_MAX+1] = {
   "clock-AF_UNSPEC", "clock-AF_UNIX"     , "clock-AF_INET"     ,
@@ -256,7 +256,7 @@ static const char *const af_family_clock_key_strings[AF_MAX+1] = {
   "clock-AF_RXRPC" , "clock-AF_ISDN"     , "clock-AF_PHONET"   ,
   "clock-AF_IEEE802154", "clock-AF_CAIF" , "clock-AF_ALG"      ,
   "clock-AF_NFC"   , "clock-AF_VSOCK"    , "clock-AF_KCM"      ,
-  "clock-AF_MAX"
+  "clock-AF_QIPCRTR", "clock-AF_MAX"
 };
 
 /*
-- 
2.7.4


>From 232ef16cd693ffd121cb5dba2aef7d66c350779d Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Tue, 10 Jan 2017 12:24:01 -0800
Subject: [PATCH 32/37] gro: Enter slow-path if there is no tailroom

[ Upstream commit 1272ce87fa017ca4cf32920764d879656b7a005a ]

The GRO path has a fast-path where we avoid calling pskb_may_pull
and pskb_expand by directly accessing frag0.  However, this should
only be done if we have enough tailroom in the skb as otherwise
we'll have to expand it later anyway.

This patch adds the check by capping frag0_len with the skb tailroom.

Fixes: cb18978cbf45 ("gro: Open-code final pskb_may_pull")
Reported-by: Slava Shwartsman <slavash@mellanox.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 6666b28..7b4fa1e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4453,7 +4453,8 @@ static void skb_gro_reset_offset(struct sk_buff *skb)
 	    pinfo->nr_frags &&
 	    !PageHighMem(skb_frag_page(frag0))) {
 		NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0);
-		NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(frag0);
+		NAPI_GRO_CB(skb)->frag0_len = min(skb_frag_size(frag0),
+						  skb->end - skb->tail);
 	}
 }
 
-- 
2.7.4


>From d6a3b358455606aa77f865c8ed66a1b4bfeacada Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 10 Jan 2017 19:52:43 -0800
Subject: [PATCH 33/37] gro: use min_t() in skb_gro_reset_offset()

[ Upstream commit 7cfd5fd5a9813f1430290d20c0fead9b4582a307 ]

On 32bit arches, (skb->end - skb->data) is not 'unsigned int',
so we shall use min_t() instead of min() to avoid a compiler error.

Fixes: 1272ce87fa01 ("gro: Enter slow-path if there is no tailroom")
Reported-by: kernel test robot <fengguang.wu@intel.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 7b4fa1e..e1d731f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4453,8 +4453,9 @@ static void skb_gro_reset_offset(struct sk_buff *skb)
 	    pinfo->nr_frags &&
 	    !PageHighMem(skb_frag_page(frag0))) {
 		NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0);
-		NAPI_GRO_CB(skb)->frag0_len = min(skb_frag_size(frag0),
-						  skb->end - skb->tail);
+		NAPI_GRO_CB(skb)->frag0_len = min_t(unsigned int,
+						    skb_frag_size(frag0),
+						    skb->end - skb->tail);
 	}
 }
 
-- 
2.7.4


>From bfb32bc40b9716b5e7029f72ddab52de04aae347 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Tue, 10 Jan 2017 12:24:15 -0800
Subject: [PATCH 34/37] gro: Disable frag0 optimization on IPv6 ext headers

[ Upstream commit 57ea52a865144aedbcd619ee0081155e658b6f7d ]

The GRO fast path caches the frag0 address.  This address becomes
invalid if frag0 is modified by pskb_may_pull or its variants.
So whenever that happens we must disable the frag0 optimization.

This is usually done through the combination of gro_header_hard
and gro_header_slow, however, the IPv6 extension header path did
the pulling directly and would continue to use the GRO fast path
incorrectly.

This patch fixes it by disabling the fast path when we enter the
IPv6 extension header path.

Fixes: 78a478d0efd9 ("gro: Inline skb_gro_header and cache frag0 virtual address")
Reported-by: Slava Shwartsman <slavash@mellanox.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 9 +++++++--
 net/ipv6/ip6_offload.c    | 1 +
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index e16a2a9..d83590e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2502,14 +2502,19 @@ static inline int skb_gro_header_hard(struct sk_buff *skb, unsigned int hlen)
 	return NAPI_GRO_CB(skb)->frag0_len < hlen;
 }
 
+static inline void skb_gro_frag0_invalidate(struct sk_buff *skb)
+{
+	NAPI_GRO_CB(skb)->frag0 = NULL;
+	NAPI_GRO_CB(skb)->frag0_len = 0;
+}
+
 static inline void *skb_gro_header_slow(struct sk_buff *skb, unsigned int hlen,
 					unsigned int offset)
 {
 	if (!pskb_may_pull(skb, hlen))
 		return NULL;
 
-	NAPI_GRO_CB(skb)->frag0 = NULL;
-	NAPI_GRO_CB(skb)->frag0_len = 0;
+	skb_gro_frag0_invalidate(skb);
 	return skb->data + offset;
 }
 
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 89c59e6..fc7b401 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -191,6 +191,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 	ops = rcu_dereference(inet6_offloads[proto]);
 	if (!ops || !ops->callbacks.gro_receive) {
 		__pskb_pull(skb, skb_gro_offset(skb));
+		skb_gro_frag0_invalidate(skb);
 		proto = ipv6_gso_pull_exthdrs(skb, proto);
 		skb_gro_pull(skb, -skb_transport_offset(skb));
 		skb_reset_transport_header(skb);
-- 
2.7.4


>From 4dc62f9bfa1aab5b763c90a70aa69bb81f226cf0 Mon Sep 17 00:00:00 2001
From: Gil Rockah <gilr@mellanox.com>
Date: Tue, 10 Jan 2017 22:33:38 +0200
Subject: [PATCH 35/37] net/mlx5e: Remove WARN_ONCE from adaptive moderation
 code

[ Upstream commit 0bbcc0a8fc394d01988fe0263ccf7fddb77a12c3 ]

When trying to do interface down or changing interface configuration
under heavy traffic, some of the adaptive moderation corner cases can
occur and leave a WARN_ONCE call trace in the kernel log.

Those WARN_ONCE are meant for debug only, and should have been inserted
only under debug. We avoid such call traces by removing those WARN_ONCE.

Fixes: cb3c7fd4f839 ("net/mlx5e: Support adaptive RX coalescing")
Signed-off-by: Gil Rockah <gilr@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c
index 1fffe48..cbfac06 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c
@@ -109,7 +109,6 @@ static bool mlx5e_am_on_top(struct mlx5e_rx_am *am)
 	switch (am->tune_state) {
 	case MLX5E_AM_PARKING_ON_TOP:
 	case MLX5E_AM_PARKING_TIRED:
-		WARN_ONCE(true, "mlx5e_am_on_top: PARKING\n");
 		return true;
 	case MLX5E_AM_GOING_RIGHT:
 		return (am->steps_left > 1) && (am->steps_right == 1);
@@ -123,7 +122,6 @@ static void mlx5e_am_turn(struct mlx5e_rx_am *am)
 	switch (am->tune_state) {
 	case MLX5E_AM_PARKING_ON_TOP:
 	case MLX5E_AM_PARKING_TIRED:
-		WARN_ONCE(true, "mlx5e_am_turn: PARKING\n");
 		break;
 	case MLX5E_AM_GOING_RIGHT:
 		am->tune_state = MLX5E_AM_GOING_LEFT;
@@ -144,7 +142,6 @@ static int mlx5e_am_step(struct mlx5e_rx_am *am)
 	switch (am->tune_state) {
 	case MLX5E_AM_PARKING_ON_TOP:
 	case MLX5E_AM_PARKING_TIRED:
-		WARN_ONCE(true, "mlx5e_am_step: PARKING\n");
 		break;
 	case MLX5E_AM_GOING_RIGHT:
 		if (am->profile_ix == (MLX5E_PARAMS_AM_NUM_PROFILES - 1))
@@ -282,10 +279,8 @@ static void mlx5e_am_calc_stats(struct mlx5e_rx_am_sample *start,
 	u32 delta_us = ktime_us_delta(end->time, start->time);
 	unsigned int npkts = end->pkt_ctr - start->pkt_ctr;
 
-	if (!delta_us) {
-		WARN_ONCE(true, "mlx5e_am_calc_stats: delta_us=0\n");
+	if (!delta_us)
 		return;
-	}
 
 	curr_stats->ppms =            (npkts * USEC_PER_MSEC) / delta_us;
 	curr_stats->epms = (MLX5E_AM_NEVENTS * USEC_PER_MSEC) / delta_us;
-- 
2.7.4


>From d1b76429e5c66febb75939f050619f82d25b5361 Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Tue, 10 Jan 2017 14:37:35 -0800
Subject: [PATCH 36/37] net: ipv4: Fix multipath selection with vrf

[ Upstream commit 7a18c5b9fb31a999afc62b0e60978aa896fc89e9 ]

fib_select_path does not call fib_select_multipath if oif is set in the
flow struct. For VRF use cases oif is always set, so multipath route
selection is bypassed. Use the FLOWI_FLAG_SKIP_NH_OIF to skip the oif
check similar to what is done in fib_table_lookup.

Add saddr and proto to the flow struct for the fib lookup done by the
VRF driver to better match hash computation for a flow.

Fixes: 613d09b30f8b ("net: Use VRF device index for lookups on TX")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c        | 2 ++
 net/ipv4/fib_semantics.c | 9 +++++++--
 2 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 809a796..12b8085 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -263,7 +263,9 @@ static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb,
 		.flowi4_iif = LOOPBACK_IFINDEX,
 		.flowi4_tos = RT_TOS(ip4h->tos),
 		.flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_SKIP_NH_OIF,
+		.flowi4_proto = ip4h->protocol,
 		.daddr = ip4h->daddr,
+		.saddr = ip4h->saddr,
 	};
 	struct net *net = dev_net(vrf_dev);
 	struct rtable *rt;
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 388d3e2..a8508b7 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1617,8 +1617,13 @@ void fib_select_multipath(struct fib_result *res, int hash)
 void fib_select_path(struct net *net, struct fib_result *res,
 		     struct flowi4 *fl4, int mp_hash)
 {
+	bool oif_check;
+
+	oif_check = (fl4->flowi4_oif == 0 ||
+		     fl4->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF);
+
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-	if (res->fi->fib_nhs > 1 && fl4->flowi4_oif == 0) {
+	if (res->fi->fib_nhs > 1 && oif_check) {
 		if (mp_hash < 0)
 			mp_hash = get_hash_from_flowi4(fl4) >> 1;
 
@@ -1628,7 +1633,7 @@ void fib_select_path(struct net *net, struct fib_result *res,
 #endif
 	if (!res->prefixlen &&
 	    res->table->tb_num_default > 1 &&
-	    res->type == RTN_UNICAST && !fl4->flowi4_oif)
+	    res->type == RTN_UNICAST && oif_check)
 		fib_select_default(fl4, res);
 
 	if (!fl4->saddr)
-- 
2.7.4


>From be6eb70b61aa2cbaf772ef53cfe0706ecf904aea Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Tue, 10 Jan 2017 15:22:25 -0800
Subject: [PATCH 37/37] net: vrf: do not allow table id 0

[ Upstream commit 24c63bbc18e25d5d8439422aa5fd2d66390b88eb ]

Frank reported that vrf devices can be created with a table id of 0.
This breaks many of the run time table id checks and should not be
allowed. Detect this condition at create time and fail with EINVAL.

Fixes: 193125dbd8eb ("net: Introduce VRF device driver")
Reported-by: Frank Kellermann <frank.kellermann@atos.net>
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 12b8085..95cf1d8 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -1239,6 +1239,8 @@ static int vrf_newlink(struct net *src_net, struct net_device *dev,
 		return -EINVAL;
 
 	vrf->tb_id = nla_get_u32(data[IFLA_VRF_TABLE]);
+	if (vrf->tb_id == RT_TABLE_UNSPEC)
+		return -EINVAL;
 
 	dev->priv_flags |= IFF_L3MDEV_MASTER;
 
-- 
2.7.4

Re: [PATCHES] Networking

[Greg KH]

On Thu, Jan 12, 2017 at 01:55:10PM -0500, David Miller wrote:
> 
> Please queue up the following networking bug fixes for 4.4.x and
> 4.9.x -stable, respectively.

All now queued up, many thanks for these.

greg k-h

[PATCHES] networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 104 bytes --]


Please queue up the following networking bug fixes for 4.4.x and
4.9.x -stable, respectively.

Thanks!

[-- Attachment #2: net_44.mbox --]
[-- Type: Application/Octet-Stream, Size: 48703 bytes --]

From c347005d9a34a8436d11df07c5004c78e105a467 Mon Sep 17 00:00:00 2001
From: hayeswang <hayeswang@realtek.com>
Date: Wed, 11 Jan 2017 16:25:34 +0800
Subject: [PATCH 01/20] r8152: fix the sw rx checksum is unavailable

[ Upstream commit 19c0f40d4fca3a47b8f784a627f0467f0138ccc8 ]

Fix the hw rx checksum is always enabled, and the user couldn't switch
it to sw rx checksum.

Note that the RTL_VER_01 only support sw rx checksum only. Besides,
the hw rx checksum for RTL_VER_02 is disabled after
commit b9a321b48af4 ("r8152: Fix broken RX checksums."). Re-enable it.

Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 32b7ec9..ed512a4 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -1645,7 +1645,7 @@ static u8 r8152_rx_csum(struct r8152 *tp, struct rx_desc *rx_desc)
 	u8 checksum = CHECKSUM_NONE;
 	u32 opts2, opts3;
 
-	if (tp->version == RTL_VER_01)
+	if (!(tp->netdev->features & NETIF_F_RXCSUM))
 		goto return_result;
 
 	opts2 = le32_to_cpu(rx_desc->opts2);
@@ -4221,6 +4221,11 @@ static int rtl8152_probe(struct usb_interface *intf,
 				NETIF_F_HIGHDMA | NETIF_F_FRAGLIST |
 				NETIF_F_IPV6_CSUM | NETIF_F_TSO6;
 
+	if (tp->version == RTL_VER_01) {
+		netdev->features &= ~NETIF_F_RXCSUM;
+		netdev->hw_features &= ~NETIF_F_RXCSUM;
+	}
+
 	netdev->ethtool_ops = &ops;
 	netif_set_gso_max_size(netdev, RTL_LIMITED_TSO_SIZE);
 
-- 
2.4.11


From 17c7ea4a317bc329ada2a6740ea86f4eb138b13b Mon Sep 17 00:00:00 2001
From: Arkadi Sharshevsky <arkadis@mellanox.com>
Date: Thu, 12 Jan 2017 09:10:37 +0100
Subject: [PATCH 02/20] mlxsw: spectrum: Fix memory leak at skb reallocation

[ Upstream commit 36bf38d158d3482119b3e159c0619b3c1539b508 ]

During transmission the skb is checked for headroom in order to
add vendor specific header. In case the skb needs to be re-allocated,
skb_realloc_headroom() is called to make a private copy of the original,
but doesn't release it. Current code assumes that the original skb is
released during reallocation and only releases it at the error path
which causes a memory leak.

Fix this by adding the original skb release to the main path.

Fixes: 56ade8fe3fe1 ("mlxsw: spectrum: Add initial support for Spectrum ASIC")
Signed-off-by: Arkadi Sharshevsky <arkadis@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 3be4a23..cb165c2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -390,6 +390,7 @@ static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb,
 			dev_kfree_skb_any(skb_orig);
 			return NETDEV_TX_OK;
 		}
+		dev_consume_skb_any(skb_orig);
 	}
 
 	if (eth_skb_pad(skb)) {
-- 
2.4.11


From 0d9504106042f0984b6b9ed0cc526a8987f5ff58 Mon Sep 17 00:00:00 2001
From: Arkadi Sharshevsky <arkadis@mellanox.com>
Date: Thu, 12 Jan 2017 09:10:38 +0100
Subject: [PATCH 03/20] mlxsw: switchx2: Fix memory leak at skb reallocation

[ Upstream commit 400fc0106dd8c27ed84781c929c1a184785b9c79 ]

During transmission the skb is checked for headroom in order to
add vendor specific header. In case the skb needs to be re-allocated,
skb_realloc_headroom() is called to make a private copy of the original,
but doesn't release it. Current code assumes that the original skb is
released during reallocation and only releases it at the error path
which causes a memory leak.

Fix this by adding the original skb release to the main path.

Fixes: d003462a50de ("mlxsw: Simplify mlxsw_sx_port_xmit function")
Signed-off-by: Arkadi Sharshevsky <arkadis@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/switchx2.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
index d85960c..fb2d9a8 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
@@ -313,6 +313,7 @@ static netdev_tx_t mlxsw_sx_port_xmit(struct sk_buff *skb,
 			dev_kfree_skb_any(skb_orig);
 			return NETDEV_TX_OK;
 		}
+		dev_consume_skb_any(skb_orig);
 	}
 	mlxsw_sx_txhdr_construct(skb, &tx_info);
 	len = skb->len;
-- 
2.4.11


From 4b0dc039585087f382d449a88ed48451eb182b53 Mon Sep 17 00:00:00 2001
From: Elad Raz <eladr@mellanox.com>
Date: Thu, 12 Jan 2017 09:10:39 +0100
Subject: [PATCH 04/20] mlxsw: pci: Fix EQE structure definition

[ Upstream commit 28e46a0f2e03ab4ed0e23cace1ea89a68c8c115b ]

The event_data starts from address 0x00-0x0C and not from 0x08-0x014. This
leads to duplication with other fields in the Event Queue Element such as
sub-type, cqn and owner.

Fixes: eda6500a987a0 ("mlxsw: Add PCI bus implementation")
Signed-off-by: Elad Raz <eladr@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/pci.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.h b/drivers/net/ethernet/mellanox/mlxsw/pci.h
index 142f33d..a0fbe00 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.h
@@ -206,21 +206,21 @@ MLXSW_ITEM32(pci, eqe, owner, 0x0C, 0, 1);
 /* pci_eqe_cmd_token
  * Command completion event - token
  */
-MLXSW_ITEM32(pci, eqe, cmd_token, 0x08, 16, 16);
+MLXSW_ITEM32(pci, eqe, cmd_token, 0x00, 16, 16);
 
 /* pci_eqe_cmd_status
  * Command completion event - status
  */
-MLXSW_ITEM32(pci, eqe, cmd_status, 0x08, 0, 8);
+MLXSW_ITEM32(pci, eqe, cmd_status, 0x00, 0, 8);
 
 /* pci_eqe_cmd_out_param_h
  * Command completion event - output parameter - higher part
  */
-MLXSW_ITEM32(pci, eqe, cmd_out_param_h, 0x0C, 0, 32);
+MLXSW_ITEM32(pci, eqe, cmd_out_param_h, 0x04, 0, 32);
 
 /* pci_eqe_cmd_out_param_l
  * Command completion event - output parameter - lower part
  */
-MLXSW_ITEM32(pci, eqe, cmd_out_param_l, 0x10, 0, 32);
+MLXSW_ITEM32(pci, eqe, cmd_out_param_l, 0x08, 0, 32);
 
 #endif
-- 
2.4.11


From 4ee4d7fd9cb307e5b08ed3b93f1d2b2cf88d233b Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Wed, 11 Jan 2017 14:29:54 -0800
Subject: [PATCH 05/20] net: lwtunnel: Handle lwtunnel_fill_encap failure

[ Upstream commit ea7a80858f57d8878b1499ea0f1b8a635cc48de7 ]

Handle failure in lwtunnel_fill_encap adding attributes to skb.

Fixes: 571e722676fe ("ipv4: support for fib route lwtunnel encap attributes")
Fixes: 19e42e451506 ("ipv6: support for fib route lwtunnel encap attributes")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_semantics.c | 11 +++++++----
 net/ipv6/route.c         |  3 ++-
 2 files changed, 9 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 840b450..67d44aa 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1277,8 +1277,9 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 		    nla_put_u32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid))
 			goto nla_put_failure;
 #endif
-		if (fi->fib_nh->nh_lwtstate)
-			lwtunnel_fill_encap(skb, fi->fib_nh->nh_lwtstate);
+		if (fi->fib_nh->nh_lwtstate &&
+		    lwtunnel_fill_encap(skb, fi->fib_nh->nh_lwtstate) < 0)
+			goto nla_put_failure;
 	}
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	if (fi->fib_nhs > 1) {
@@ -1314,8 +1315,10 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 			    nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid))
 				goto nla_put_failure;
 #endif
-			if (nh->nh_lwtstate)
-				lwtunnel_fill_encap(skb, nh->nh_lwtstate);
+			if (nh->nh_lwtstate &&
+			    lwtunnel_fill_encap(skb, nh->nh_lwtstate) < 0)
+				goto nla_put_failure;
+
 			/* length of rtnetlink header + attributes */
 			rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *) rtnh;
 		} endfor_nexthops(fi);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index dbffc9d..36bf4c3 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3196,7 +3196,8 @@ static int rt6_fill_node(struct net *net,
 	if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt->rt6i_flags)))
 		goto nla_put_failure;
 
-	lwtunnel_fill_encap(skb, rt->dst.lwtstate);
+	if (lwtunnel_fill_encap(skb, rt->dst.lwtstate) < 0)
+		goto nla_put_failure;
 
 	nlmsg_end(skb, nlh);
 	return 0;
-- 
2.4.11


From 580d4ad45a63a1ec67c8238196b99ff8ad270155 Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Wed, 11 Jan 2017 15:42:17 -0800
Subject: [PATCH 06/20] net: ipv4: fix table id in getroute response

[ Upstream commit 8a430ed50bb1b19ca14a46661f3b1b35f2fb5c39 ]

rtm_table is an 8-bit field while table ids are allowed up to u32. Commit
709772e6e065 ("net: Fix routing tables with id > 255 for legacy software")
added the preference to set rtm_table in dumps to RT_TABLE_COMPAT if the
table id is > 255. The table id returned on get route requests should do
the same.

Fixes: c36ba6603a11 ("net: Allow user to get table id from route lookup")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 7ceb8a5..ef2f527 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2430,7 +2430,7 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src, u32 table_id,
 	r->rtm_dst_len	= 32;
 	r->rtm_src_len	= 0;
 	r->rtm_tos	= fl4->flowi4_tos;
-	r->rtm_table	= table_id;
+	r->rtm_table	= table_id < 256 ? table_id : RT_TABLE_COMPAT;
 	if (nla_put_u32(skb, RTA_TABLE, table_id))
 		goto nla_put_failure;
 	r->rtm_type	= rt->rt_type;
-- 
2.4.11


From b5f09d4fc3d9d8f5e80af0a0e700376e01c41e73 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 12 Jan 2017 12:09:09 -0800
Subject: [PATCH 07/20] net: systemport: Decouple flow control from
 __bcm_sysport_tx_reclaim

[ Upstream commit 148d3d021cf9724fcf189ce4e525a094bbf5ce89 ]

The __bcm_sysport_tx_reclaim() function is used to reclaim transmit
resources in different places within the driver. Most of them should
not affect the state of the transit flow control.

Introduce bcm_sysport_tx_clean() which cleans the ring, but does not
re-enable flow control towards the networking stack, and make
bcm_sysport_tx_reclaim() do the actual transmit queue flow control.

Fixes: 80105befdb4b ("net: systemport: add Broadcom SYSTEMPORT Ethernet MAC driver")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bcmsysport.c | 25 ++++++++++++++++++-------
 1 file changed, 18 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 8581063..8860e74 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -732,11 +732,8 @@ static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv,
 	unsigned int c_index, last_c_index, last_tx_cn, num_tx_cbs;
 	unsigned int pkts_compl = 0, bytes_compl = 0;
 	struct bcm_sysport_cb *cb;
-	struct netdev_queue *txq;
 	u32 hw_ind;
 
-	txq = netdev_get_tx_queue(ndev, ring->index);
-
 	/* Compute how many descriptors have been processed since last call */
 	hw_ind = tdma_readl(priv, TDMA_DESC_RING_PROD_CONS_INDEX(ring->index));
 	c_index = (hw_ind >> RING_CONS_INDEX_SHIFT) & RING_CONS_INDEX_MASK;
@@ -767,9 +764,6 @@ static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv,
 
 	ring->c_index = c_index;
 
-	if (netif_tx_queue_stopped(txq) && pkts_compl)
-		netif_tx_wake_queue(txq);
-
 	netif_dbg(priv, tx_done, ndev,
 		  "ring=%d c_index=%d pkts_compl=%d, bytes_compl=%d\n",
 		  ring->index, ring->c_index, pkts_compl, bytes_compl);
@@ -781,16 +775,33 @@ static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv,
 static unsigned int bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv,
 					   struct bcm_sysport_tx_ring *ring)
 {
+	struct netdev_queue *txq;
 	unsigned int released;
 	unsigned long flags;
 
+	txq = netdev_get_tx_queue(priv->netdev, ring->index);
+
 	spin_lock_irqsave(&ring->lock, flags);
 	released = __bcm_sysport_tx_reclaim(priv, ring);
+	if (released)
+		netif_tx_wake_queue(txq);
+
 	spin_unlock_irqrestore(&ring->lock, flags);
 
 	return released;
 }
 
+/* Locked version of the per-ring TX reclaim, but does not wake the queue */
+static void bcm_sysport_tx_clean(struct bcm_sysport_priv *priv,
+				 struct bcm_sysport_tx_ring *ring)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&ring->lock, flags);
+	__bcm_sysport_tx_reclaim(priv, ring);
+	spin_unlock_irqrestore(&ring->lock, flags);
+}
+
 static int bcm_sysport_tx_poll(struct napi_struct *napi, int budget)
 {
 	struct bcm_sysport_tx_ring *ring =
@@ -1275,7 +1286,7 @@ static void bcm_sysport_fini_tx_ring(struct bcm_sysport_priv *priv,
 	napi_disable(&ring->napi);
 	netif_napi_del(&ring->napi);
 
-	bcm_sysport_tx_reclaim(priv, ring);
+	bcm_sysport_tx_clean(priv, ring);
 
 	kfree(ring->cbs);
 	ring->cbs = NULL;
-- 
2.4.11


From d39cfd48b6cb4fdcf9749794e92769c93e6cc5b2 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@oracle.com>
Date: Thu, 12 Jan 2017 14:24:58 -0800
Subject: [PATCH 08/20] tcp: fix tcp_fastopen unaligned access complaints on
 sparc

[ Upstream commit 003c941057eaa868ca6fedd29a274c863167230d ]

Fix up a data alignment issue on sparc by swapping the order
of the cookie byte array field with the length field in
struct tcp_fastopen_cookie, and making it a proper union
to clean up the typecasting.

This addresses log complaints like these:
    log_unaligned: 113 callbacks suppressed
    Kernel unaligned access at TPC[976490] tcp_try_fastopen+0x2d0/0x360
    Kernel unaligned access at TPC[9764ac] tcp_try_fastopen+0x2ec/0x360
    Kernel unaligned access at TPC[9764c8] tcp_try_fastopen+0x308/0x360
    Kernel unaligned access at TPC[9764e4] tcp_try_fastopen+0x324/0x360
    Kernel unaligned access at TPC[976490] tcp_try_fastopen+0x2d0/0x360

Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Shannon Nelson <shannon.nelson@oracle.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h     | 7 ++++++-
 net/ipv4/tcp_fastopen.c | 2 +-
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index b386361..318c246 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -56,8 +56,13 @@ static inline unsigned int tcp_optlen(const struct sk_buff *skb)
 
 /* TCP Fast Open Cookie as stored in memory */
 struct tcp_fastopen_cookie {
+	union {
+		u8	val[TCP_FASTOPEN_COOKIE_MAX];
+#if IS_ENABLED(CONFIG_IPV6)
+		struct in6_addr addr;
+#endif
+	};
 	s8	len;
-	u8	val[TCP_FASTOPEN_COOKIE_MAX];
 	bool	exp;	/* In RFC6994 experimental option format */
 };
 
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 55be6ac..32489e4 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -112,7 +112,7 @@ static bool tcp_fastopen_cookie_gen(struct request_sock *req,
 		struct tcp_fastopen_cookie tmp;
 
 		if (__tcp_fastopen_cookie_gen(&ip6h->saddr, &tmp)) {
-			struct in6_addr *buf = (struct in6_addr *) tmp.val;
+			struct in6_addr *buf = &tmp.addr;
 			int i;
 
 			for (i = 0; i < 4; i++)
-- 
2.4.11


From 4b5d038c16c959ee63bc597f749c92fbc86abb55 Mon Sep 17 00:00:00 2001
From: Lance Richardson <lrichard@redhat.com>
Date: Thu, 12 Jan 2017 19:33:18 -0500
Subject: [PATCH 09/20] openvswitch: maintain correct checksum state in
 conntrack actions

[ Upstream commit 75f01a4c9cc291ff5cb28ca1216adb163b7a20ee ]

When executing conntrack actions on skbuffs with checksum mode
CHECKSUM_COMPLETE, the checksum must be updated to account for
header pushes and pulls. Otherwise we get "hw csum failure"
logs similar to this (ICMP packet received on geneve tunnel
via ixgbe NIC):

[  405.740065] genev_sys_6081: hw csum failure
[  405.740106] CPU: 3 PID: 0 Comm: swapper/3 Tainted: G          I     4.10.0-rc3+ #1
[  405.740108] Call Trace:
[  405.740110]  <IRQ>
[  405.740113]  dump_stack+0x63/0x87
[  405.740116]  netdev_rx_csum_fault+0x3a/0x40
[  405.740118]  __skb_checksum_complete+0xcf/0xe0
[  405.740120]  nf_ip_checksum+0xc8/0xf0
[  405.740124]  icmp_error+0x1de/0x351 [nf_conntrack_ipv4]
[  405.740132]  nf_conntrack_in+0xe1/0x550 [nf_conntrack]
[  405.740137]  ? find_bucket.isra.2+0x62/0x70 [openvswitch]
[  405.740143]  __ovs_ct_lookup+0x95/0x980 [openvswitch]
[  405.740145]  ? netif_rx_internal+0x44/0x110
[  405.740149]  ovs_ct_execute+0x147/0x4b0 [openvswitch]
[  405.740153]  do_execute_actions+0x22e/0xa70 [openvswitch]
[  405.740157]  ovs_execute_actions+0x40/0x120 [openvswitch]
[  405.740161]  ovs_dp_process_packet+0x84/0x120 [openvswitch]
[  405.740166]  ovs_vport_receive+0x73/0xd0 [openvswitch]
[  405.740168]  ? udp_rcv+0x1a/0x20
[  405.740170]  ? ip_local_deliver_finish+0x93/0x1e0
[  405.740172]  ? ip_local_deliver+0x6f/0xe0
[  405.740174]  ? ip_rcv_finish+0x3a0/0x3a0
[  405.740176]  ? ip_rcv_finish+0xdb/0x3a0
[  405.740177]  ? ip_rcv+0x2a7/0x400
[  405.740180]  ? __netif_receive_skb_core+0x970/0xa00
[  405.740185]  netdev_frame_hook+0xd3/0x160 [openvswitch]
[  405.740187]  __netif_receive_skb_core+0x1dc/0xa00
[  405.740194]  ? ixgbe_clean_rx_irq+0x46d/0xa20 [ixgbe]
[  405.740197]  __netif_receive_skb+0x18/0x60
[  405.740199]  netif_receive_skb_internal+0x40/0xb0
[  405.740201]  napi_gro_receive+0xcd/0x120
[  405.740204]  gro_cell_poll+0x57/0x80 [geneve]
[  405.740206]  net_rx_action+0x260/0x3c0
[  405.740209]  __do_softirq+0xc9/0x28c
[  405.740211]  irq_exit+0xd9/0xf0
[  405.740213]  do_IRQ+0x51/0xd0
[  405.740215]  common_interrupt+0x93/0x93

Fixes: 7f8a436eaa2c ("openvswitch: Add conntrack action")
Signed-off-by: Lance Richardson <lrichard@redhat.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/conntrack.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index e004067..ad58d2a 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -501,7 +501,7 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb,
 
 	/* The conntrack module expects to be working at L3. */
 	nh_ofs = skb_network_offset(skb);
-	skb_pull(skb, nh_ofs);
+	skb_pull_rcsum(skb, nh_ofs);
 
 	if (key->ip.frag != OVS_FRAG_TYPE_NONE) {
 		err = handle_fragments(net, key, info->zone.id, skb);
@@ -527,6 +527,7 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb,
 					&info->labels.mask);
 err:
 	skb_push(skb, nh_ofs);
+	skb_postpush_rcsum(skb, skb->data, nh_ofs);
 	if (err)
 		kfree_skb(skb);
 	return err;
-- 
2.4.11


From bfc5ae4358ab084d87e4892b4c06954cc0f26e7b Mon Sep 17 00:00:00 2001
From: Masaru Nagai <masaru.nagai.vx@renesas.com>
Date: Mon, 16 Jan 2017 11:45:21 +0100
Subject: [PATCH 10/20] ravb: do not use zero-length alignment DMA descriptor

[ Upstream commit 8ec3e8a192ba6f13be4522ee81227c792c86fb1a ]

Due to alignment requirements of the hardware transmissions are split into
two DMA descriptors, a small padding descriptor of 0 - 3 bytes in length
followed by a descriptor for rest of the packet.

In the case of IP packets the first descriptor will never be zero due to
the way that the stack aligns buffers for IP packets. However, for non-IP
packets it may be zero.

In that case it has been reported that timeouts occur, presumably because
transmission stops at the first zero-length DMA descriptor and thus the
packet is not transmitted. However, in my environment a BUG is triggered as
follows:

[   20.381417] ------------[ cut here ]------------
[   20.386054] kernel BUG at lib/swiotlb.c:495!
[   20.390324] Internal error: Oops - BUG: 0 [#1] PREEMPT SMP
[   20.395805] Modules linked in:
[   20.398862] CPU: 0 PID: 2089 Comm: mz Not tainted 4.10.0-rc3-00001-gf13ad2db193f #162
[   20.406689] Hardware name: Renesas Salvator-X board based on r8a7796 (DT)
[   20.413474] task: ffff80063b1f1900 task.stack: ffff80063a71c000
[   20.419404] PC is at swiotlb_tbl_map_single+0x178/0x2ec
[   20.424625] LR is at map_single+0x4c/0x98
[   20.428629] pc : [<ffff00000839c4c0>] lr : [<ffff00000839c680>] pstate: 800001c5
[   20.436019] sp : ffff80063a71f9b0
[   20.439327] x29: ffff80063a71f9b0 x28: ffff80063a20d500
[   20.444636] x27: ffff000008ed5000 x26: 0000000000000000
[   20.449944] x25: 000000067abe2adc x24: 0000000000000000
[   20.455252] x23: 0000000000200000 x22: 0000000000000001
[   20.460559] x21: 0000000000175ffe x20: ffff80063b2a0010
[   20.465866] x19: 0000000000000000 x18: 0000ffffcae6fb20
[   20.471173] x17: 0000ffffa09ba018 x16: ffff0000087c8b70
[   20.476480] x15: 0000ffffa084f588 x14: 0000ffffa09cfa14
[   20.481787] x13: 0000ffffcae87ff0 x12: 000000000063abe2
[   20.487098] x11: ffff000008096360 x10: ffff80063abe2adc
[   20.492407] x9 : 0000000000000000 x8 : 0000000000000000
[   20.497718] x7 : 0000000000000000 x6 : ffff000008ed50d0
[   20.503028] x5 : 0000000000000000 x4 : 0000000000000001
[   20.508338] x3 : 0000000000000000 x2 : 000000067abe2adc
[   20.513648] x1 : 00000000bafff000 x0 : 0000000000000000
[   20.518958]
[   20.520446] Process mz (pid: 2089, stack limit = 0xffff80063a71c000)
[   20.526798] Stack: (0xffff80063a71f9b0 to 0xffff80063a720000)
[   20.532543] f9a0:                                   ffff80063a71fa30 ffff00000839c680
[   20.540374] f9c0: ffff80063b2a0010 ffff80063b2a0010 0000000000000001 0000000000000000
[   20.548204] f9e0: 000000000000006e ffff80063b23c000 ffff80063b23c000 0000000000000000
[   20.556034] fa00: ffff80063b23c000 ffff80063a20d500 000000013b1f1900 0000000000000000
[   20.563864] fa20: ffff80063ffd18e0 ffff80063b2a0010 ffff80063a71fa60 ffff00000839cd10
[   20.571694] fa40: ffff80063b2a0010 0000000000000000 ffff80063ffd18e0 000000067abe2adc
[   20.579524] fa60: ffff80063a71fa90 ffff000008096380 ffff80063b2a0010 0000000000000000
[   20.587353] fa80: 0000000000000000 0000000000000001 ffff80063a71fac0 ffff00000864f770
[   20.595184] faa0: ffff80063b23caf0 0000000000000000 0000000000000000 0000000000000140
[   20.603014] fac0: ffff80063a71fb60 ffff0000087e6498 ffff80063a20d500 ffff80063b23c000
[   20.610843] fae0: 0000000000000000 ffff000008daeaf0 0000000000000000 ffff000008daeb00
[   20.618673] fb00: ffff80063a71fc0c ffff000008da7000 ffff80063b23c090 ffff80063a44f000
[   20.626503] fb20: 0000000000000000 ffff000008daeb00 ffff80063a71fc0c ffff000008da7000
[   20.634333] fb40: ffff80063b23c090 0000000000000000 ffff800600000037 ffff0000087e63d8
[   20.642163] fb60: ffff80063a71fbc0 ffff000008807510 ffff80063a692400 ffff80063a20d500
[   20.649993] fb80: ffff80063a44f000 ffff80063b23c000 ffff80063a69249c 0000000000000000
[   20.657823] fba0: 0000000000000000 ffff80063a087800 ffff80063b23c000 ffff80063a20d500
[   20.665653] fbc0: ffff80063a71fc10 ffff0000087e67dc ffff80063a20d500 ffff80063a692400
[   20.673483] fbe0: ffff80063b23c000 0000000000000000 ffff80063a44f000 ffff80063a69249c
[   20.681312] fc00: ffff80063a5f1a10 000000103a087800 ffff80063a71fc70 ffff0000087e6b24
[   20.689142] fc20: ffff80063a5f1a80 ffff80063a71fde8 000000000000000f 00000000000005ea
[   20.696972] fc40: ffff80063a5f1a10 0000000000000000 000000000000000f ffff00000887fbd0
[   20.704802] fc60: fffffff43a5f1a80 0000000000000000 ffff80063a71fc80 ffff000008880240
[   20.712632] fc80: ffff80063a71fd90 ffff0000087c7a34 ffff80063afc7180 0000000000000000
[   20.720462] fca0: 0000ffffcae6fe18 0000000000000014 0000000060000000 0000000000000015
[   20.728292] fcc0: 0000000000000123 00000000000000ce ffff0000088d2000 ffff80063b1f1900
[   20.736122] fce0: 0000000000008933 ffff000008e7cb80 ffff80063a71fd80 ffff0000087c50a4
[   20.743951] fd00: 0000000000008933 ffff000008e7cb80 ffff000008e7cb80 000000100000000e
[   20.751781] fd20: ffff80063a71fe4c 0000ffff00000300 0000000000000123 0000000000000000
[   20.759611] fd40: 0000000000000000 ffff80063b1f0000 000000000000000e 0000000000000300
[   20.767441] fd60: 0000000000000000 0000000000000000 0000000000000000 0000000000000000
[   20.775271] fd80: 0000000000000000 0000000000000000 ffff80063a71fda0 ffff0000087c8c20
[   20.783100] fda0: 0000000000000000 ffff000008082f30 0000000000000000 0000800637260000
[   20.790930] fdc0: ffffffffffffffff 0000ffffa0903078 0000000000000000 000000001ea87232
[   20.798760] fde0: 000000000000000f ffff80063a71fe40 ffff800600000014 ffff000000000001
[   20.806590] fe00: 0000000000000000 0000000000000000 ffff80063a71fde8 0000000000000000
[   20.814420] fe20: 0000000000000000 0000000000000000 0000000000000000 0000000000000001
[   20.822249] fe40: 0000000203000011 0000000000000000 0000000000000000 ffff80063a68aa00
[   20.830079] fe60: ffff80063a68aa00 0000000000000003 0000000000008933 ffff0000081f1b9c
[   20.837909] fe80: 0000000000000000 ffff000008082f30 0000000000000000 0000800637260000
[   20.845739] fea0: ffffffffffffffff 0000ffffa07ca81c 0000000060000000 0000000000000015
[   20.853569] fec0: 0000000000000003 000000001ea87232 000000000000000f 0000000000000000
[   20.861399] fee0: 0000ffffcae6fe18 0000000000000014 0000000000000300 0000000000000000
[   20.869228] ff00: 00000000000000ce 0000000000000000 00000000ffffffff 0000000000000000
[   20.877059] ff20: 0000000000000002 0000ffffcae87ff0 0000ffffa09cfa14 0000ffffa084f588
[   20.884888] ff40: 0000000000000000 0000ffffa09ba018 0000ffffcae6fb20 000000001ea87010
[   20.892718] ff60: 0000ffffa09b9000 0000ffffcae6fe30 0000ffffcae6fe18 000000000000000f
[   20.900548] ff80: 0000000000000003 000000001ea87232 0000000000000000 0000000000000000
[   20.908378] ffa0: 0000000000000000 0000ffffcae6fdc0 0000ffffa09a7824 0000ffffcae6fdc0
[   20.916208] ffc0: 0000ffffa0903078 0000000060000000 0000000000000003 00000000000000ce
[   20.924038] ffe0: 0000000000000000 0000000000000000 ffffffffffffffff ffffffffffffffff
[   20.931867] Call trace:
[   20.934312] Exception stack(0xffff80063a71f7e0 to 0xffff80063a71f910)
[   20.940750] f7e0: 0000000000000000 0001000000000000 ffff80063a71f9b0 ffff00000839c4c0
[   20.948580] f800: ffff80063a71f840 ffff00000888a6e4 ffff80063a24c418 ffff80063a24c448
[   20.956410] f820: 0000000000000000 ffff00000811cd54 ffff80063a71f860 ffff80063a24c458
[   20.964240] f840: ffff80063a71f870 ffff00000888b258 ffff80063a24c418 0000000000000001
[   20.972070] f860: ffff80063a71f910 ffff80063a7b7028 ffff80063a71f890 ffff0000088825e4
[   20.979899] f880: 0000000000000000 00000000bafff000 000000067abe2adc 0000000000000000
[   20.987729] f8a0: 0000000000000001 0000000000000000 ffff000008ed50d0 0000000000000000
[   20.995560] f8c0: 0000000000000000 0000000000000000 ffff80063abe2adc ffff000008096360
[   21.003390] f8e0: 000000000063abe2 0000ffffcae87ff0 0000ffffa09cfa14 0000ffffa084f588
[   21.011219] f900: ffff0000087c8b70 0000ffffa09ba018
[   21.016097] [<ffff00000839c4c0>] swiotlb_tbl_map_single+0x178/0x2ec
[   21.022362] [<ffff00000839c680>] map_single+0x4c/0x98
[   21.027411] [<ffff00000839cd10>] swiotlb_map_page+0xa4/0x138
[   21.033072] [<ffff000008096380>] __swiotlb_map_page+0x20/0x7c
[   21.038821] [<ffff00000864f770>] ravb_start_xmit+0x174/0x668
[   21.044484] [<ffff0000087e6498>] dev_hard_start_xmit+0x8c/0x120
[   21.050407] [<ffff000008807510>] sch_direct_xmit+0x108/0x1a0
[   21.056064] [<ffff0000087e67dc>] __dev_queue_xmit+0x194/0x4cc
[   21.061807] [<ffff0000087e6b24>] dev_queue_xmit+0x10/0x18
[   21.067214] [<ffff000008880240>] packet_sendmsg+0xf40/0x1220
[   21.072873] [<ffff0000087c7a34>] sock_sendmsg+0x18/0x2c
[   21.078097] [<ffff0000087c8c20>] SyS_sendto+0xb0/0xf0
[   21.083150] [<ffff000008082f30>] el0_svc_naked+0x24/0x28
[   21.088462] Code: d34bfef7 2a1803f3 1a9f86d6 35fff878 (d4210000)
[   21.094611] ---[ end trace 5bc544ad491f3814 ]---
[   21.099234] Kernel panic - not syncing: Fatal exception in interrupt
[   21.105587] Kernel Offset: disabled
[   21.109073] Memory Limit: none
[   21.112126] ---[ end Kernel panic - not syncing: Fatal exception in interrupt

Fixes: 2f45d1902acf ("ravb: minimize TX data copying")
Signed-off-by: Masaru Nagai <masaru.nagai.vx@renesas.com
Signed-off-by: Simon Horman <horms+renesas@verge.net.au>
Acked-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/ravb_main.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 467d416..549ad20 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -1330,6 +1330,19 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	buffer = PTR_ALIGN(priv->tx_align[q], DPTR_ALIGN) +
 		 entry / NUM_TX_DESC * DPTR_ALIGN;
 	len = PTR_ALIGN(skb->data, DPTR_ALIGN) - skb->data;
+	/* Zero length DMA descriptors are problematic as they seem to
+	 * terminate DMA transfers. Avoid them by simply using a length of
+	 * DPTR_ALIGN (4) when skb data is aligned to DPTR_ALIGN.
+	 *
+	 * As skb is guaranteed to have at least ETH_ZLEN (60) bytes of
+	 * data by the call to skb_put_padto() above this is safe with
+	 * respect to both the length of the first DMA descriptor (len)
+	 * overflowing the available data and the length of the second DMA
+	 * descriptor (skb->len - len) being negative.
+	 */
+	if (len == 0)
+		len = DPTR_ALIGN;
+
 	memcpy(buffer, skb->data, len);
 	dma_addr = dma_map_single(ndev->dev.parent, buffer, len, DMA_TO_DEVICE);
 	if (dma_mapping_error(ndev->dev.parent, dma_addr))
-- 
2.4.11


From 98ecb7184d3d71d70bafce27522b635cc99d6521 Mon Sep 17 00:00:00 2001
From: Basil Gunn <basil@pacabunga.com>
Date: Sat, 14 Jan 2017 12:18:55 -0800
Subject: [PATCH 11/20] ax25: Fix segfault after sock connection timeout

[ Upstream commit 8a367e74c0120ef68c8c70d5a025648c96626dff ]

The ax.25 socket connection timed out & the sock struct has been
previously taken down ie. sock struct is now a NULL pointer. Checking
the sock_flag causes the segfault.  Check if the socket struct pointer
is NULL before checking sock_flag. This segfault is seen in
timed out netrom connections.

Please submit to -stable.

Signed-off-by: Basil Gunn <basil@pacabunga.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ax25/ax25_subr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ax25/ax25_subr.c b/net/ax25/ax25_subr.c
index 655a7d4..983f0b5 100644
--- a/net/ax25/ax25_subr.c
+++ b/net/ax25/ax25_subr.c
@@ -264,7 +264,7 @@ void ax25_disconnect(ax25_cb *ax25, int reason)
 {
 	ax25_clear_queues(ax25);
 
-	if (!sock_flag(ax25->sk, SOCK_DESTROY))
+	if (!ax25->sk || !sock_flag(ax25->sk, SOCK_DESTROY))
 		ax25_stop_heartbeat(ax25);
 	ax25_stop_t1timer(ax25);
 	ax25_stop_t2timer(ax25);
-- 
2.4.11


From 0220589c95ba5cbde55cd51c2566882df39a62a5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 18 Jan 2017 12:12:17 -0800
Subject: [PATCH 12/20] net: fix harmonize_features() vs NETIF_F_HIGHDMA

[ Upstream commit 7be2c82cfd5d28d7adb66821a992604eb6dd112e ]

Ashizuka reported a highmem oddity and sent a patch for freescale
fec driver.

But the problem root cause is that core networking stack
must ensure no skb with highmem fragment is ever sent through
a device that does not assert NETIF_F_HIGHDMA in its features.

We need to call illegal_highdma() from harmonize_features()
regardless of CSUM checks.

Fixes: ec5f06156423 ("net: Kill link between CSUM and SG features.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Pravin Shelar <pshelar@ovn.org>
Reported-by: "Ashizuka, Yuusuke" <ashiduka@jp.fujitsu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 6f203c7..0798a0f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2650,9 +2650,9 @@ static netdev_features_t harmonize_features(struct sk_buff *skb,
 	if (skb->ip_summed != CHECKSUM_NONE &&
 	    !can_checksum_protocol(features, type)) {
 		features &= ~NETIF_F_ALL_CSUM;
-	} else if (illegal_highdma(skb->dev, skb)) {
-		features &= ~NETIF_F_SG;
 	}
+	if (illegal_highdma(skb->dev, skb))
+		features &= ~NETIF_F_SG;
 
 	return features;
 }
-- 
2.4.11


From 3427a8c1d631c87a5c003ee91223d78eb82020ce Mon Sep 17 00:00:00 2001
From: Daniel Gonzalez Cabanelas <dgcbueu@gmail.com>
Date: Tue, 17 Jan 2017 16:26:55 -0800
Subject: [PATCH 13/20] net: phy: bcm63xx: Utilize correct config_intr function

[ Upstream commit cd33b3e0da43522ff8e8f2b2b71d3d08298512b0 ]

Commit a1cba5613edf ("net: phy: Add Broadcom phy library for common
interfaces") make the BCM63xx PHY driver utilize bcm_phy_config_intr()
which would appear to do the right thing, except that it does not write
to the MII_BCM63XX_IR register but to MII_BCM54XX_ECR which is
different.

This would be causing invalid link parameters and events from being
generated by the PHY interrupt.

Fixes: a1cba5613edf ("net: phy: Add Broadcom phy library for common interfaces")
Signed-off-by: Daniel Gonzalez Cabanelas <dgcbueu@gmail.com>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/bcm63xx.c | 21 +++++++++++++++++++--
 1 file changed, 19 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/bcm63xx.c b/drivers/net/phy/bcm63xx.c
index 86b2805..9b709f7 100644
--- a/drivers/net/phy/bcm63xx.c
+++ b/drivers/net/phy/bcm63xx.c
@@ -21,6 +21,23 @@ MODULE_DESCRIPTION("Broadcom 63xx internal PHY driver");
 MODULE_AUTHOR("Maxime Bizon <mbizon@freebox.fr>");
 MODULE_LICENSE("GPL");
 
+static int bcm63xx_config_intr(struct phy_device *phydev)
+{
+	int reg, err;
+
+	reg = phy_read(phydev, MII_BCM63XX_IR);
+	if (reg < 0)
+		return reg;
+
+	if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
+		reg &= ~MII_BCM63XX_IR_GMASK;
+	else
+		reg |= MII_BCM63XX_IR_GMASK;
+
+	err = phy_write(phydev, MII_BCM63XX_IR, reg);
+	return err;
+}
+
 static int bcm63xx_config_init(struct phy_device *phydev)
 {
 	int reg, err;
@@ -55,7 +72,7 @@ static struct phy_driver bcm63xx_driver[] = {
 	.config_aneg	= genphy_config_aneg,
 	.read_status	= genphy_read_status,
 	.ack_interrupt	= bcm_phy_ack_intr,
-	.config_intr	= bcm_phy_config_intr,
+	.config_intr	= bcm63xx_config_intr,
 	.driver		= { .owner = THIS_MODULE },
 }, {
 	/* same phy as above, with just a different OUI */
@@ -68,7 +85,7 @@ static struct phy_driver bcm63xx_driver[] = {
 	.config_aneg	= genphy_config_aneg,
 	.read_status	= genphy_read_status,
 	.ack_interrupt	= bcm_phy_ack_intr,
-	.config_intr	= bcm_phy_config_intr,
+	.config_intr	= bcm63xx_config_intr,
 	.driver		= { .owner = THIS_MODULE },
 } };
 
-- 
2.4.11


From 9a18b7a83a457f13987d3d5e9c58118acbbbc6da Mon Sep 17 00:00:00 2001
From: Kefeng Wang <wangkefeng.wang@huawei.com>
Date: Thu, 19 Jan 2017 16:26:21 +0800
Subject: [PATCH 14/20] ipv6: addrconf: Avoid addrconf_disable_change() using
 RCU read-side lock

[ Upstream commit 03e4deff4987f79c34112c5ba4eb195d4f9382b0 ]

Just like commit 4acd4945cd1e ("ipv6: addrconf: Avoid calling
netdevice notifiers with RCU read-side lock"), it is unnecessary
to make addrconf_disable_change() use RCU iteration over the
netdev list, since it already holds the RTNL lock, or we may meet
Illegal context switch in RCU read-side critical section.

Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index cb8bb59..253186a 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5244,8 +5244,7 @@ static void addrconf_disable_change(struct net *net, __s32 newf)
 	struct net_device *dev;
 	struct inet6_dev *idev;
 
-	rcu_read_lock();
-	for_each_netdev_rcu(net, dev) {
+	for_each_netdev(net, dev) {
 		idev = __in6_dev_get(dev);
 		if (idev) {
 			int changed = (!idev->cnf.disable_ipv6) ^ (!newf);
@@ -5254,7 +5253,6 @@ static void addrconf_disable_change(struct net *net, __s32 newf)
 				dev_disable_change(idev);
 		}
 	}
-	rcu_read_unlock();
 }
 
 static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int newf)
-- 
2.4.11


From 7e21fd9964c48597a11ab2f413244db91b16df10 Mon Sep 17 00:00:00 2001
From: Alexey Kodanev <alexey.kodanev@oracle.com>
Date: Thu, 19 Jan 2017 16:36:39 +0300
Subject: [PATCH 15/20] tcp: initialize max window for a new fastopen socket

[ Upstream commit 0dbd7ff3ac5017a46033a9d0a87a8267d69119d9 ]

Found that if we run LTP netstress test with large MSS (65K),
the first attempt from server to send data comparable to this
MSS on fastopen connection will be delayed by the probe timer.

Here is an example:

     < S  seq 0:0 win 43690 options [mss 65495 wscale 7 tfo cookie] length 32
     > S. seq 0:0 ack 1 win 43690 options [mss 65495 wscale 7] length 0
     < .  ack 1 win 342 length 0

Inside tcp_sendmsg(), tcp_send_mss() returns max MSS in 'mss_now',
as well as in 'size_goal'. This results the segment not queued for
transmition until all the data copied from user buffer. Then, inside
__tcp_push_pending_frames(), it breaks on send window test and
continues with the check probe timer.

Fragmentation occurs in tcp_write_wakeup()...

+0.2 > P. seq 1:43777 ack 1 win 342 length 43776
     < .  ack 43777, win 1365 length 0
     > P. seq 43777:65001 ack 1 win 342 options [...] length 21224
     ...

This also contradicts with the fact that we should bound to the half
of the window if it is large.

Fix this flaw by correctly initializing max_window. Before that, it
could have large values that affect further calculations of 'size_goal'.

Fixes: 168a8f58059a ("tcp: TCP Fast Open Server - main code path")
Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_fastopen.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 32489e4..fca6182 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -161,6 +161,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
 	 * scaled. So correct it appropriately.
 	 */
 	tp->snd_wnd = ntohs(tcp_hdr(skb)->window);
+	tp->max_window = tp->snd_wnd;
 
 	/* Activate the retrans timer so that SYNACK can be retransmitted.
 	 * The request socket is not added to the ehash
-- 
2.4.11


From 93e9ba07d1a11e0d300e475d1a437a1651c9e180 Mon Sep 17 00:00:00 2001
From: Ivan Vecera <cera@cera.cz>
Date: Fri, 20 Jan 2017 18:12:17 +0100
Subject: [PATCH 16/20] bridge: netlink: call br_changelink() during
 br_dev_newlink()

[ Upstream commit b6677449dff674cf5b81429b11d5c7f358852ef9 ]

Any bridge options specified during link creation (e.g. ip link add)
are ignored as br_dev_newlink() does not process them.
Use br_changelink() to do it.

Fixes: 133235161721 ("bridge: implement rtnl_link_ops->changelink")
Signed-off-by: Ivan Vecera <cera@cera.cz>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_netlink.c | 33 +++++++++++++++++++--------------
 1 file changed, 19 insertions(+), 14 deletions(-)

diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 40197ff..413d18e 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -773,20 +773,6 @@ static int br_validate(struct nlattr *tb[], struct nlattr *data[])
 	return 0;
 }
 
-static int br_dev_newlink(struct net *src_net, struct net_device *dev,
-			  struct nlattr *tb[], struct nlattr *data[])
-{
-	struct net_bridge *br = netdev_priv(dev);
-
-	if (tb[IFLA_ADDRESS]) {
-		spin_lock_bh(&br->lock);
-		br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS]));
-		spin_unlock_bh(&br->lock);
-	}
-
-	return register_netdevice(dev);
-}
-
 static int br_port_slave_changelink(struct net_device *brdev,
 				    struct net_device *dev,
 				    struct nlattr *tb[],
@@ -1068,6 +1054,25 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
 	return 0;
 }
 
+static int br_dev_newlink(struct net *src_net, struct net_device *dev,
+			  struct nlattr *tb[], struct nlattr *data[])
+{
+	struct net_bridge *br = netdev_priv(dev);
+	int err;
+
+	if (tb[IFLA_ADDRESS]) {
+		spin_lock_bh(&br->lock);
+		br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS]));
+		spin_unlock_bh(&br->lock);
+	}
+
+	err = br_changelink(dev, tb, data);
+	if (err)
+		return err;
+
+	return register_netdevice(dev);
+}
+
 static size_t br_get_size(const struct net_device *brdev)
 {
 	return nla_total_size(sizeof(u32)) +	/* IFLA_BR_FORWARD_DELAY  */
-- 
2.4.11


From 6aa981d69bbd58e30019be2cee406c79ddd3a3e7 Mon Sep 17 00:00:00 2001
From: hayeswang <hayeswang@realtek.com>
Date: Mon, 23 Jan 2017 14:18:43 +0800
Subject: [PATCH 17/20] r8152: don't execute runtime suspend if the tx is not
 empty

[ Upstream commit 6a0b76c04ec157c88ca943debf78a8ee58469f2d ]

Runtime suspend shouldn't be executed if the tx queue is not empty,
because the device is not idle.

Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index ed512a4..fbb1867 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -3442,6 +3442,8 @@ static bool delay_autosuspend(struct r8152 *tp)
 	 */
 	if (!sw_linking && tp->rtl_ops.in_nway(tp))
 		return true;
+	else if (!skb_queue_empty(&tp->tx_queue))
+		return true;
 	else
 		return false;
 }
-- 
2.4.11


From a7e7c6adcfedb3f0b5789549117eceeca6b0056d Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Mon, 23 Jan 2017 11:17:35 -0800
Subject: [PATCH 18/20] af_unix: move unix_mknod() out of bindlock

[ Upstream commit 0fb44559ffd67de8517098b81f675fa0210f13f0 ]

Dmitry reported a deadlock scenario:

unix_bind() path:
u->bindlock ==> sb_writer

do_splice() path:
sb_writer ==> pipe->mutex ==> u->bindlock

In the unix_bind() code path, unix_mknod() does not have to
be done with u->bindlock held, since it is a pure fs operation,
so we can just move unix_mknod() out.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Tested-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Rainer Weikusat <rweikusat@mobileactivedefense.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c | 27 ++++++++++++++++-----------
 1 file changed, 16 insertions(+), 11 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 73f7525..b2e934f 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -994,6 +994,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	unsigned int hash;
 	struct unix_address *addr;
 	struct hlist_head *list;
+	struct path path = { NULL, NULL };
 
 	err = -EINVAL;
 	if (sunaddr->sun_family != AF_UNIX)
@@ -1009,9 +1010,20 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		goto out;
 	addr_len = err;
 
+	if (sun_path[0]) {
+		umode_t mode = S_IFSOCK |
+		       (SOCK_INODE(sock)->i_mode & ~current_umask());
+		err = unix_mknod(sun_path, mode, &path);
+		if (err) {
+			if (err == -EEXIST)
+				err = -EADDRINUSE;
+			goto out;
+		}
+	}
+
 	err = mutex_lock_interruptible(&u->bindlock);
 	if (err)
-		goto out;
+		goto out_put;
 
 	err = -EINVAL;
 	if (u->addr)
@@ -1028,16 +1040,6 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	atomic_set(&addr->refcnt, 1);
 
 	if (sun_path[0]) {
-		struct path path;
-		umode_t mode = S_IFSOCK |
-		       (SOCK_INODE(sock)->i_mode & ~current_umask());
-		err = unix_mknod(sun_path, mode, &path);
-		if (err) {
-			if (err == -EEXIST)
-				err = -EADDRINUSE;
-			unix_release_addr(addr);
-			goto out_up;
-		}
 		addr->hash = UNIX_HASH_SIZE;
 		hash = d_real_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE - 1);
 		spin_lock(&unix_table_lock);
@@ -1064,6 +1066,9 @@ out_unlock:
 	spin_unlock(&unix_table_lock);
 out_up:
 	mutex_unlock(&u->bindlock);
+out_put:
+	if (err)
+		path_put(&path);
 out:
 	return err;
 }
-- 
2.4.11


From f689d680061ec3bda075886e6820c6faf3283c9f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Tue, 24 Jan 2017 10:45:38 +0100
Subject: [PATCH 19/20] qmi_wwan/cdc_ether: add device ID for HP lt2523
 (Novatel E371) WWAN card
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 5b9f57516337b523f7466a53939aaaea7b78141b ]

Another rebranded Novatel E371.  qmi_wwan should drive this device, while
cdc_ether should ignore it.  Even though the USB descriptors are plain
CDC-ETHER that USB interface is a QMI interface.  Ref commit 7fdb7846c9ca
("qmi_wwan/cdc_ether: add device IDs for Dell 5804 (Novatel E371) WWAN
card")

Cc: Dan Williams <dcbw@redhat.com>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ether.c | 8 ++++++++
 drivers/net/usb/qmi_wwan.c  | 7 +++++++
 2 files changed, 15 insertions(+)

diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index 7cba2c3..8c408aa 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -462,6 +462,7 @@ static const struct driver_info wwan_info = {
 #define SAMSUNG_VENDOR_ID	0x04e8
 #define LENOVO_VENDOR_ID	0x17ef
 #define NVIDIA_VENDOR_ID	0x0955
+#define HP_VENDOR_ID		0x03f0
 
 static const struct usb_device_id	products[] = {
 /* BLACKLIST !!
@@ -608,6 +609,13 @@ static const struct usb_device_id	products[] = {
 	.driver_info = 0,
 },
 
+/* HP lt2523 (Novatel E371) - handled by qmi_wwan */
+{
+	USB_DEVICE_AND_INTERFACE_INFO(HP_VENDOR_ID, 0x421d, USB_CLASS_COMM,
+				      USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+	.driver_info = 0,
+},
+
 /* AnyDATA ADU960S - handled by qmi_wwan */
 {
 	USB_DEVICE_AND_INTERFACE_INFO(0x16d5, 0x650a, USB_CLASS_COMM,
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index a34f491..09052f9 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -485,6 +485,13 @@ static const struct usb_device_id products[] = {
 					      USB_CDC_PROTO_NONE),
 		.driver_info        = (unsigned long)&qmi_wwan_info,
 	},
+	{	/* HP lt2523 (Novatel E371) */
+		USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x421d,
+					      USB_CLASS_COMM,
+					      USB_CDC_SUBCLASS_ETHERNET,
+					      USB_CDC_PROTO_NONE),
+		.driver_info        = (unsigned long)&qmi_wwan_info,
+	},
 	{	/* HP lt4112 LTE/HSPA+ Gobi 4G Module (Huawei me906e) */
 		USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x581d, USB_CLASS_VENDOR_SPEC, 1, 7),
 		.driver_info = (unsigned long)&qmi_wwan_info,
-- 
2.4.11


From a24657a5c568964e9fd8aa83ff3d915fed3a4730 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 25 Jan 2017 09:10:41 -0800
Subject: [PATCH 20/20] net: dsa: Bring back device detaching in
 dsa_slave_suspend()

[ Upstream commit f154be241d22298d2b63c9b613f619fa1086ea75 ]

Commit 448b4482c671 ("net: dsa: Add lockdep class to tx queues to avoid
lockdep splat") removed the netif_device_detach() call done in
dsa_slave_suspend() which is necessary, and paired with a corresponding
netif_device_attach(), bring it back.

Fixes: 448b4482c671 ("net: dsa: Add lockdep class to tx queues to avoid lockdep splat")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/slave.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 7bc787b..8dfe9fb 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -1101,6 +1101,8 @@ int dsa_slave_suspend(struct net_device *slave_dev)
 {
 	struct dsa_slave_priv *p = netdev_priv(slave_dev);
 
+	netif_device_detach(slave_dev);
+
 	if (p->phy) {
 		phy_stop(p->phy);
 		p->old_pause = -1;
-- 
2.4.11


[-- Attachment #3: net_49.mbox --]
[-- Type: Application/Octet-Stream, Size: 86650 bytes --]

From fd2bee6234d6360eff4f0819ee7260c3f089ee0b Mon Sep 17 00:00:00 2001
From: hayeswang <hayeswang@realtek.com>
Date: Wed, 11 Jan 2017 16:25:34 +0800
Subject: [PATCH 01/32] r8152: fix the sw rx checksum is unavailable

[ Upstream commit 19c0f40d4fca3a47b8f784a627f0467f0138ccc8 ]

Fix the hw rx checksum is always enabled, and the user couldn't switch
it to sw rx checksum.

Note that the RTL_VER_01 only support sw rx checksum only. Besides,
the hw rx checksum for RTL_VER_02 is disabled after
commit b9a321b48af4 ("r8152: Fix broken RX checksums."). Re-enable it.

Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 4b5cb16..be4c86f 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -1730,7 +1730,7 @@ static u8 r8152_rx_csum(struct r8152 *tp, struct rx_desc *rx_desc)
 	u8 checksum = CHECKSUM_NONE;
 	u32 opts2, opts3;
 
-	if (tp->version == RTL_VER_01 || tp->version == RTL_VER_02)
+	if (!(tp->netdev->features & NETIF_F_RXCSUM))
 		goto return_result;
 
 	opts2 = le32_to_cpu(rx_desc->opts2);
@@ -4358,6 +4358,11 @@ static int rtl8152_probe(struct usb_interface *intf,
 				NETIF_F_HIGHDMA | NETIF_F_FRAGLIST |
 				NETIF_F_IPV6_CSUM | NETIF_F_TSO6;
 
+	if (tp->version == RTL_VER_01) {
+		netdev->features &= ~NETIF_F_RXCSUM;
+		netdev->hw_features &= ~NETIF_F_RXCSUM;
+	}
+
 	netdev->ethtool_ops = &ops;
 	netif_set_gso_max_size(netdev, RTL_LIMITED_TSO_SIZE);
 
-- 
2.4.11


From a1b4466d26ab9f44da0b1f1299bb5b330bc03498 Mon Sep 17 00:00:00 2001
From: stephen hemminger <stephen@networkplumber.org>
Date: Wed, 11 Jan 2017 09:16:32 -0800
Subject: [PATCH 02/32] netvsc: add rcu_read locking to netvsc callback

[ Upstream commit 0719e72ccb801829a3d735d187ca8417f0930459 ]

The receive callback (in tasklet context) is using RCU to get reference
to associated VF network device but this is not safe. RCU read lock
needs to be held. Found by running with full lockdep debugging
enabled.

Fixes: f207c10d9823 ("hv_netvsc: use RCU to protect vf_netdev")
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/netvsc_drv.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index c9140c3..ff038e5 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -659,6 +659,7 @@ int netvsc_recv_callback(struct hv_device *device_obj,
 	 * policy filters on the host). Deliver these via the VF
 	 * interface in the guest.
 	 */
+	rcu_read_lock();
 	vf_netdev = rcu_dereference(net_device_ctx->vf_netdev);
 	if (vf_netdev && (vf_netdev->flags & IFF_UP))
 		net = vf_netdev;
@@ -667,6 +668,7 @@ int netvsc_recv_callback(struct hv_device *device_obj,
 	skb = netvsc_alloc_recv_skb(net, packet, csum_info, *data, vlan_tci);
 	if (unlikely(!skb)) {
 		++net->stats.rx_dropped;
+		rcu_read_unlock();
 		return NVSP_STAT_FAIL;
 	}
 
@@ -696,6 +698,7 @@ int netvsc_recv_callback(struct hv_device *device_obj,
 	 * TODO - use NAPI?
 	 */
 	netif_rx(skb);
+	rcu_read_unlock();
 
 	return 0;
 }
-- 
2.4.11


From 9924db6993a6c4d8de105114213a30e462f89b48 Mon Sep 17 00:00:00 2001
From: Arkadi Sharshevsky <arkadis@mellanox.com>
Date: Thu, 12 Jan 2017 09:10:37 +0100
Subject: [PATCH 03/32] mlxsw: spectrum: Fix memory leak at skb reallocation

[ Upstream commit 36bf38d158d3482119b3e159c0619b3c1539b508 ]

During transmission the skb is checked for headroom in order to
add vendor specific header. In case the skb needs to be re-allocated,
skb_realloc_headroom() is called to make a private copy of the original,
but doesn't release it. Current code assumes that the original skb is
released during reallocation and only releases it at the error path
which causes a memory leak.

Fix this by adding the original skb release to the main path.

Fixes: 56ade8fe3fe1 ("mlxsw: spectrum: Add initial support for Spectrum ASIC")
Signed-off-by: Arkadi Sharshevsky <arkadis@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index dda5761..f902c4d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -684,6 +684,7 @@ static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb,
 			dev_kfree_skb_any(skb_orig);
 			return NETDEV_TX_OK;
 		}
+		dev_consume_skb_any(skb_orig);
 	}
 
 	if (eth_skb_pad(skb)) {
-- 
2.4.11


From c4aed48837f53c42abaae30ec722fdfb4d0c5190 Mon Sep 17 00:00:00 2001
From: Arkadi Sharshevsky <arkadis@mellanox.com>
Date: Thu, 12 Jan 2017 09:10:38 +0100
Subject: [PATCH 04/32] mlxsw: switchx2: Fix memory leak at skb reallocation

[ Upstream commit 400fc0106dd8c27ed84781c929c1a184785b9c79 ]

During transmission the skb is checked for headroom in order to
add vendor specific header. In case the skb needs to be re-allocated,
skb_realloc_headroom() is called to make a private copy of the original,
but doesn't release it. Current code assumes that the original skb is
released during reallocation and only releases it at the error path
which causes a memory leak.

Fix this by adding the original skb release to the main path.

Fixes: d003462a50de ("mlxsw: Simplify mlxsw_sx_port_xmit function")
Signed-off-by: Arkadi Sharshevsky <arkadis@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/switchx2.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
index 92bda87..d548f0a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
@@ -314,6 +314,7 @@ static netdev_tx_t mlxsw_sx_port_xmit(struct sk_buff *skb,
 			dev_kfree_skb_any(skb_orig);
 			return NETDEV_TX_OK;
 		}
+		dev_consume_skb_any(skb_orig);
 	}
 	mlxsw_sx_txhdr_construct(skb, &tx_info);
 	/* TX header is consumed by HW on the way so we shouldn't count its
-- 
2.4.11


From 27bbce8603aa4c05366c58d270253a28369c198a Mon Sep 17 00:00:00 2001
From: Elad Raz <eladr@mellanox.com>
Date: Thu, 12 Jan 2017 09:10:39 +0100
Subject: [PATCH 05/32] mlxsw: pci: Fix EQE structure definition

[ Upstream commit 28e46a0f2e03ab4ed0e23cace1ea89a68c8c115b ]

The event_data starts from address 0x00-0x0C and not from 0x08-0x014. This
leads to duplication with other fields in the Event Queue Element such as
sub-type, cqn and owner.

Fixes: eda6500a987a0 ("mlxsw: Add PCI bus implementation")
Signed-off-by: Elad Raz <eladr@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/pci.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.h b/drivers/net/ethernet/mellanox/mlxsw/pci.h
index d942a3e..846fd4d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.h
@@ -211,21 +211,21 @@ MLXSW_ITEM32(pci, eqe, owner, 0x0C, 0, 1);
 /* pci_eqe_cmd_token
  * Command completion event - token
  */
-MLXSW_ITEM32(pci, eqe, cmd_token, 0x08, 16, 16);
+MLXSW_ITEM32(pci, eqe, cmd_token, 0x00, 16, 16);
 
 /* pci_eqe_cmd_status
  * Command completion event - status
  */
-MLXSW_ITEM32(pci, eqe, cmd_status, 0x08, 0, 8);
+MLXSW_ITEM32(pci, eqe, cmd_status, 0x00, 0, 8);
 
 /* pci_eqe_cmd_out_param_h
  * Command completion event - output parameter - higher part
  */
-MLXSW_ITEM32(pci, eqe, cmd_out_param_h, 0x0C, 0, 32);
+MLXSW_ITEM32(pci, eqe, cmd_out_param_h, 0x04, 0, 32);
 
 /* pci_eqe_cmd_out_param_l
  * Command completion event - output parameter - lower part
  */
-MLXSW_ITEM32(pci, eqe, cmd_out_param_l, 0x10, 0, 32);
+MLXSW_ITEM32(pci, eqe, cmd_out_param_l, 0x08, 0, 32);
 
 #endif
-- 
2.4.11


From 43e0ce26f7b743c8fa56a5e567f14827244fd9bd Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Wed, 11 Jan 2017 14:29:54 -0800
Subject: [PATCH 06/32] net: lwtunnel: Handle lwtunnel_fill_encap failure

[ Upstream commit ea7a80858f57d8878b1499ea0f1b8a635cc48de7 ]

Handle failure in lwtunnel_fill_encap adding attributes to skb.

Fixes: 571e722676fe ("ipv4: support for fib route lwtunnel encap attributes")
Fixes: 19e42e451506 ("ipv6: support for fib route lwtunnel encap attributes")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_semantics.c | 11 +++++++----
 net/ipv6/route.c         |  3 ++-
 2 files changed, 9 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index a8508b7..6a40680 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1278,8 +1278,9 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 		    nla_put_u32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid))
 			goto nla_put_failure;
 #endif
-		if (fi->fib_nh->nh_lwtstate)
-			lwtunnel_fill_encap(skb, fi->fib_nh->nh_lwtstate);
+		if (fi->fib_nh->nh_lwtstate &&
+		    lwtunnel_fill_encap(skb, fi->fib_nh->nh_lwtstate) < 0)
+			goto nla_put_failure;
 	}
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	if (fi->fib_nhs > 1) {
@@ -1315,8 +1316,10 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 			    nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid))
 				goto nla_put_failure;
 #endif
-			if (nh->nh_lwtstate)
-				lwtunnel_fill_encap(skb, nh->nh_lwtstate);
+			if (nh->nh_lwtstate &&
+			    lwtunnel_fill_encap(skb, nh->nh_lwtstate) < 0)
+				goto nla_put_failure;
+
 			/* length of rtnetlink header + attributes */
 			rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *) rtnh;
 		} endfor_nexthops(fi);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 1b57e11..acd80237 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3306,7 +3306,8 @@ static int rt6_fill_node(struct net *net,
 	if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt->rt6i_flags)))
 		goto nla_put_failure;
 
-	lwtunnel_fill_encap(skb, rt->dst.lwtstate);
+	if (lwtunnel_fill_encap(skb, rt->dst.lwtstate) < 0)
+		goto nla_put_failure;
 
 	nlmsg_end(skb, nlh);
 	return 0;
-- 
2.4.11


From c99401a314afc16568073bac3a3286f773bfe5a2 Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Wed, 11 Jan 2017 15:42:17 -0800
Subject: [PATCH 07/32] net: ipv4: fix table id in getroute response

[ Upstream commit 8a430ed50bb1b19ca14a46661f3b1b35f2fb5c39 ]

rtm_table is an 8-bit field while table ids are allowed up to u32. Commit
709772e6e065 ("net: Fix routing tables with id > 255 for legacy software")
added the preference to set rtm_table in dumps to RT_TABLE_COMPAT if the
table id is > 255. The table id returned on get route requests should do
the same.

Fixes: c36ba6603a11 ("net: Allow user to get table id from route lookup")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 8197b06..d851cae 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2440,7 +2440,7 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src, u32 table_id,
 	r->rtm_dst_len	= 32;
 	r->rtm_src_len	= 0;
 	r->rtm_tos	= fl4->flowi4_tos;
-	r->rtm_table	= table_id;
+	r->rtm_table	= table_id < 256 ? table_id : RT_TABLE_COMPAT;
 	if (nla_put_u32(skb, RTA_TABLE, table_id))
 		goto nla_put_failure;
 	r->rtm_type	= rt->rt_type;
-- 
2.4.11


From e679a26c44ce2dce5c9750a6804280ef5f71e37b Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 12 Jan 2017 12:09:09 -0800
Subject: [PATCH 08/32] net: systemport: Decouple flow control from
 __bcm_sysport_tx_reclaim

[ Upstream commit 148d3d021cf9724fcf189ce4e525a094bbf5ce89 ]

The __bcm_sysport_tx_reclaim() function is used to reclaim transmit
resources in different places within the driver. Most of them should
not affect the state of the transit flow control.

Introduce bcm_sysport_tx_clean() which cleans the ring, but does not
re-enable flow control towards the networking stack, and make
bcm_sysport_tx_reclaim() do the actual transmit queue flow control.

Fixes: 80105befdb4b ("net: systemport: add Broadcom SYSTEMPORT Ethernet MAC driver")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bcmsysport.c | 25 ++++++++++++++++++-------
 1 file changed, 18 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 25d1eb4..be7ec5a 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -710,11 +710,8 @@ static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv,
 	unsigned int c_index, last_c_index, last_tx_cn, num_tx_cbs;
 	unsigned int pkts_compl = 0, bytes_compl = 0;
 	struct bcm_sysport_cb *cb;
-	struct netdev_queue *txq;
 	u32 hw_ind;
 
-	txq = netdev_get_tx_queue(ndev, ring->index);
-
 	/* Compute how many descriptors have been processed since last call */
 	hw_ind = tdma_readl(priv, TDMA_DESC_RING_PROD_CONS_INDEX(ring->index));
 	c_index = (hw_ind >> RING_CONS_INDEX_SHIFT) & RING_CONS_INDEX_MASK;
@@ -745,9 +742,6 @@ static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv,
 
 	ring->c_index = c_index;
 
-	if (netif_tx_queue_stopped(txq) && pkts_compl)
-		netif_tx_wake_queue(txq);
-
 	netif_dbg(priv, tx_done, ndev,
 		  "ring=%d c_index=%d pkts_compl=%d, bytes_compl=%d\n",
 		  ring->index, ring->c_index, pkts_compl, bytes_compl);
@@ -759,16 +753,33 @@ static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv,
 static unsigned int bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv,
 					   struct bcm_sysport_tx_ring *ring)
 {
+	struct netdev_queue *txq;
 	unsigned int released;
 	unsigned long flags;
 
+	txq = netdev_get_tx_queue(priv->netdev, ring->index);
+
 	spin_lock_irqsave(&ring->lock, flags);
 	released = __bcm_sysport_tx_reclaim(priv, ring);
+	if (released)
+		netif_tx_wake_queue(txq);
+
 	spin_unlock_irqrestore(&ring->lock, flags);
 
 	return released;
 }
 
+/* Locked version of the per-ring TX reclaim, but does not wake the queue */
+static void bcm_sysport_tx_clean(struct bcm_sysport_priv *priv,
+				 struct bcm_sysport_tx_ring *ring)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&ring->lock, flags);
+	__bcm_sysport_tx_reclaim(priv, ring);
+	spin_unlock_irqrestore(&ring->lock, flags);
+}
+
 static int bcm_sysport_tx_poll(struct napi_struct *napi, int budget)
 {
 	struct bcm_sysport_tx_ring *ring =
@@ -1253,7 +1264,7 @@ static void bcm_sysport_fini_tx_ring(struct bcm_sysport_priv *priv,
 	napi_disable(&ring->napi);
 	netif_napi_del(&ring->napi);
 
-	bcm_sysport_tx_reclaim(priv, ring);
+	bcm_sysport_tx_clean(priv, ring);
 
 	kfree(ring->cbs);
 	ring->cbs = NULL;
-- 
2.4.11


From c2f19c6fba1d7723380ad7ed510e2dcdd00bbd7a Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@oracle.com>
Date: Thu, 12 Jan 2017 14:24:58 -0800
Subject: [PATCH 09/32] tcp: fix tcp_fastopen unaligned access complaints on
 sparc

[ Upstream commit 003c941057eaa868ca6fedd29a274c863167230d ]

Fix up a data alignment issue on sparc by swapping the order
of the cookie byte array field with the length field in
struct tcp_fastopen_cookie, and making it a proper union
to clean up the typecasting.

This addresses log complaints like these:
    log_unaligned: 113 callbacks suppressed
    Kernel unaligned access at TPC[976490] tcp_try_fastopen+0x2d0/0x360
    Kernel unaligned access at TPC[9764ac] tcp_try_fastopen+0x2ec/0x360
    Kernel unaligned access at TPC[9764c8] tcp_try_fastopen+0x308/0x360
    Kernel unaligned access at TPC[9764e4] tcp_try_fastopen+0x324/0x360
    Kernel unaligned access at TPC[976490] tcp_try_fastopen+0x2d0/0x360

Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Shannon Nelson <shannon.nelson@oracle.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h     | 7 ++++++-
 net/ipv4/tcp_fastopen.c | 2 +-
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index a17ae7b..647532b 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -62,8 +62,13 @@ static inline unsigned int tcp_optlen(const struct sk_buff *skb)
 
 /* TCP Fast Open Cookie as stored in memory */
 struct tcp_fastopen_cookie {
+	union {
+		u8	val[TCP_FASTOPEN_COOKIE_MAX];
+#if IS_ENABLED(CONFIG_IPV6)
+		struct in6_addr addr;
+#endif
+	};
 	s8	len;
-	u8	val[TCP_FASTOPEN_COOKIE_MAX];
 	bool	exp;	/* In RFC6994 experimental option format */
 };
 
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 4e777a3..f519195 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -113,7 +113,7 @@ static bool tcp_fastopen_cookie_gen(struct request_sock *req,
 		struct tcp_fastopen_cookie tmp;
 
 		if (__tcp_fastopen_cookie_gen(&ip6h->saddr, &tmp)) {
-			struct in6_addr *buf = (struct in6_addr *) tmp.val;
+			struct in6_addr *buf = &tmp.addr;
 			int i;
 
 			for (i = 0; i < 4; i++)
-- 
2.4.11


From 87b9e01bcef9d938e72632c6e41367b2467231db Mon Sep 17 00:00:00 2001
From: Lance Richardson <lrichard@redhat.com>
Date: Thu, 12 Jan 2017 19:33:18 -0500
Subject: [PATCH 10/32] openvswitch: maintain correct checksum state in
 conntrack actions

[ Upstream commit 75f01a4c9cc291ff5cb28ca1216adb163b7a20ee ]

When executing conntrack actions on skbuffs with checksum mode
CHECKSUM_COMPLETE, the checksum must be updated to account for
header pushes and pulls. Otherwise we get "hw csum failure"
logs similar to this (ICMP packet received on geneve tunnel
via ixgbe NIC):

[  405.740065] genev_sys_6081: hw csum failure
[  405.740106] CPU: 3 PID: 0 Comm: swapper/3 Tainted: G          I     4.10.0-rc3+ #1
[  405.740108] Call Trace:
[  405.740110]  <IRQ>
[  405.740113]  dump_stack+0x63/0x87
[  405.740116]  netdev_rx_csum_fault+0x3a/0x40
[  405.740118]  __skb_checksum_complete+0xcf/0xe0
[  405.740120]  nf_ip_checksum+0xc8/0xf0
[  405.740124]  icmp_error+0x1de/0x351 [nf_conntrack_ipv4]
[  405.740132]  nf_conntrack_in+0xe1/0x550 [nf_conntrack]
[  405.740137]  ? find_bucket.isra.2+0x62/0x70 [openvswitch]
[  405.740143]  __ovs_ct_lookup+0x95/0x980 [openvswitch]
[  405.740145]  ? netif_rx_internal+0x44/0x110
[  405.740149]  ovs_ct_execute+0x147/0x4b0 [openvswitch]
[  405.740153]  do_execute_actions+0x22e/0xa70 [openvswitch]
[  405.740157]  ovs_execute_actions+0x40/0x120 [openvswitch]
[  405.740161]  ovs_dp_process_packet+0x84/0x120 [openvswitch]
[  405.740166]  ovs_vport_receive+0x73/0xd0 [openvswitch]
[  405.740168]  ? udp_rcv+0x1a/0x20
[  405.740170]  ? ip_local_deliver_finish+0x93/0x1e0
[  405.740172]  ? ip_local_deliver+0x6f/0xe0
[  405.740174]  ? ip_rcv_finish+0x3a0/0x3a0
[  405.740176]  ? ip_rcv_finish+0xdb/0x3a0
[  405.740177]  ? ip_rcv+0x2a7/0x400
[  405.740180]  ? __netif_receive_skb_core+0x970/0xa00
[  405.740185]  netdev_frame_hook+0xd3/0x160 [openvswitch]
[  405.740187]  __netif_receive_skb_core+0x1dc/0xa00
[  405.740194]  ? ixgbe_clean_rx_irq+0x46d/0xa20 [ixgbe]
[  405.740197]  __netif_receive_skb+0x18/0x60
[  405.740199]  netif_receive_skb_internal+0x40/0xb0
[  405.740201]  napi_gro_receive+0xcd/0x120
[  405.740204]  gro_cell_poll+0x57/0x80 [geneve]
[  405.740206]  net_rx_action+0x260/0x3c0
[  405.740209]  __do_softirq+0xc9/0x28c
[  405.740211]  irq_exit+0xd9/0xf0
[  405.740213]  do_IRQ+0x51/0xd0
[  405.740215]  common_interrupt+0x93/0x93

Fixes: 7f8a436eaa2c ("openvswitch: Add conntrack action")
Signed-off-by: Lance Richardson <lrichard@redhat.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/conntrack.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index fecefa2..eab210b 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -514,7 +514,7 @@ static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
 	int hooknum, nh_off, err = NF_ACCEPT;
 
 	nh_off = skb_network_offset(skb);
-	skb_pull(skb, nh_off);
+	skb_pull_rcsum(skb, nh_off);
 
 	/* See HOOK2MANIP(). */
 	if (maniptype == NF_NAT_MANIP_SRC)
@@ -579,6 +579,7 @@ static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
 	err = nf_nat_packet(ct, ctinfo, hooknum, skb);
 push:
 	skb_push(skb, nh_off);
+	skb_postpush_rcsum(skb, skb->data, nh_off);
 
 	return err;
 }
@@ -890,7 +891,7 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb,
 
 	/* The conntrack module expects to be working at L3. */
 	nh_ofs = skb_network_offset(skb);
-	skb_pull(skb, nh_ofs);
+	skb_pull_rcsum(skb, nh_ofs);
 
 	if (key->ip.frag != OVS_FRAG_TYPE_NONE) {
 		err = handle_fragments(net, key, info->zone.id, skb);
@@ -904,6 +905,7 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb,
 		err = ovs_ct_lookup(net, key, info, skb);
 
 	skb_push(skb, nh_ofs);
+	skb_postpush_rcsum(skb, skb->data, nh_ofs);
 	if (err)
 		kfree_skb(skb);
 	return err;
-- 
2.4.11


From def6bcf6107c7bebaa40404b62c4d1f4a2870bde Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 13 Jan 2017 08:39:24 -0800
Subject: [PATCH 11/32] mlx4: do not call napi_schedule() without care

[ Upstream commit 8cf699ec849f4ca1413cea01289bd7d37dbcc626 ]

Disable BH around the call to napi_schedule() to avoid following warning

[   52.095499] NOHZ: local_softirq_pending 08
[   52.421291] NOHZ: local_softirq_pending 08
[   52.608313] NOHZ: local_softirq_pending 08

Fixes: 8d59de8f7bb3 ("net/mlx4_en: Process all completions in RX rings after port goes up")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Erez Shitrit <erezsh@mellanox.com>
Cc: Eugenia Emantayev <eugenia@mellanox.com>
Cc: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index fb8bb02..d223e7c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1740,8 +1740,11 @@ int mlx4_en_start_port(struct net_device *dev)
 	/* Process all completions if exist to prevent
 	 * the queues freezing if they are full
 	 */
-	for (i = 0; i < priv->rx_ring_num; i++)
+	for (i = 0; i < priv->rx_ring_num; i++) {
+		local_bh_disable();
 		napi_schedule(&priv->rx_cq[i]->napi);
+		local_bh_enable();
+	}
 
 	netif_tx_start_all_queues(dev);
 	netif_device_attach(dev);
-- 
2.4.11


From 86ede36c29983903e85f1c6271e8806922d58da1 Mon Sep 17 00:00:00 2001
From: Masaru Nagai <masaru.nagai.vx@renesas.com>
Date: Mon, 16 Jan 2017 11:45:21 +0100
Subject: [PATCH 12/32] ravb: do not use zero-length alignment DMA descriptor

[ Upstream commit 8ec3e8a192ba6f13be4522ee81227c792c86fb1a ]

Due to alignment requirements of the hardware transmissions are split into
two DMA descriptors, a small padding descriptor of 0 - 3 bytes in length
followed by a descriptor for rest of the packet.

In the case of IP packets the first descriptor will never be zero due to
the way that the stack aligns buffers for IP packets. However, for non-IP
packets it may be zero.

In that case it has been reported that timeouts occur, presumably because
transmission stops at the first zero-length DMA descriptor and thus the
packet is not transmitted. However, in my environment a BUG is triggered as
follows:

[   20.381417] ------------[ cut here ]------------
[   20.386054] kernel BUG at lib/swiotlb.c:495!
[   20.390324] Internal error: Oops - BUG: 0 [#1] PREEMPT SMP
[   20.395805] Modules linked in:
[   20.398862] CPU: 0 PID: 2089 Comm: mz Not tainted 4.10.0-rc3-00001-gf13ad2db193f #162
[   20.406689] Hardware name: Renesas Salvator-X board based on r8a7796 (DT)
[   20.413474] task: ffff80063b1f1900 task.stack: ffff80063a71c000
[   20.419404] PC is at swiotlb_tbl_map_single+0x178/0x2ec
[   20.424625] LR is at map_single+0x4c/0x98
[   20.428629] pc : [<ffff00000839c4c0>] lr : [<ffff00000839c680>] pstate: 800001c5
[   20.436019] sp : ffff80063a71f9b0
[   20.439327] x29: ffff80063a71f9b0 x28: ffff80063a20d500
[   20.444636] x27: ffff000008ed5000 x26: 0000000000000000
[   20.449944] x25: 000000067abe2adc x24: 0000000000000000
[   20.455252] x23: 0000000000200000 x22: 0000000000000001
[   20.460559] x21: 0000000000175ffe x20: ffff80063b2a0010
[   20.465866] x19: 0000000000000000 x18: 0000ffffcae6fb20
[   20.471173] x17: 0000ffffa09ba018 x16: ffff0000087c8b70
[   20.476480] x15: 0000ffffa084f588 x14: 0000ffffa09cfa14
[   20.481787] x13: 0000ffffcae87ff0 x12: 000000000063abe2
[   20.487098] x11: ffff000008096360 x10: ffff80063abe2adc
[   20.492407] x9 : 0000000000000000 x8 : 0000000000000000
[   20.497718] x7 : 0000000000000000 x6 : ffff000008ed50d0
[   20.503028] x5 : 0000000000000000 x4 : 0000000000000001
[   20.508338] x3 : 0000000000000000 x2 : 000000067abe2adc
[   20.513648] x1 : 00000000bafff000 x0 : 0000000000000000
[   20.518958]
[   20.520446] Process mz (pid: 2089, stack limit = 0xffff80063a71c000)
[   20.526798] Stack: (0xffff80063a71f9b0 to 0xffff80063a720000)
[   20.532543] f9a0:                                   ffff80063a71fa30 ffff00000839c680
[   20.540374] f9c0: ffff80063b2a0010 ffff80063b2a0010 0000000000000001 0000000000000000
[   20.548204] f9e0: 000000000000006e ffff80063b23c000 ffff80063b23c000 0000000000000000
[   20.556034] fa00: ffff80063b23c000 ffff80063a20d500 000000013b1f1900 0000000000000000
[   20.563864] fa20: ffff80063ffd18e0 ffff80063b2a0010 ffff80063a71fa60 ffff00000839cd10
[   20.571694] fa40: ffff80063b2a0010 0000000000000000 ffff80063ffd18e0 000000067abe2adc
[   20.579524] fa60: ffff80063a71fa90 ffff000008096380 ffff80063b2a0010 0000000000000000
[   20.587353] fa80: 0000000000000000 0000000000000001 ffff80063a71fac0 ffff00000864f770
[   20.595184] faa0: ffff80063b23caf0 0000000000000000 0000000000000000 0000000000000140
[   20.603014] fac0: ffff80063a71fb60 ffff0000087e6498 ffff80063a20d500 ffff80063b23c000
[   20.610843] fae0: 0000000000000000 ffff000008daeaf0 0000000000000000 ffff000008daeb00
[   20.618673] fb00: ffff80063a71fc0c ffff000008da7000 ffff80063b23c090 ffff80063a44f000
[   20.626503] fb20: 0000000000000000 ffff000008daeb00 ffff80063a71fc0c ffff000008da7000
[   20.634333] fb40: ffff80063b23c090 0000000000000000 ffff800600000037 ffff0000087e63d8
[   20.642163] fb60: ffff80063a71fbc0 ffff000008807510 ffff80063a692400 ffff80063a20d500
[   20.649993] fb80: ffff80063a44f000 ffff80063b23c000 ffff80063a69249c 0000000000000000
[   20.657823] fba0: 0000000000000000 ffff80063a087800 ffff80063b23c000 ffff80063a20d500
[   20.665653] fbc0: ffff80063a71fc10 ffff0000087e67dc ffff80063a20d500 ffff80063a692400
[   20.673483] fbe0: ffff80063b23c000 0000000000000000 ffff80063a44f000 ffff80063a69249c
[   20.681312] fc00: ffff80063a5f1a10 000000103a087800 ffff80063a71fc70 ffff0000087e6b24
[   20.689142] fc20: ffff80063a5f1a80 ffff80063a71fde8 000000000000000f 00000000000005ea
[   20.696972] fc40: ffff80063a5f1a10 0000000000000000 000000000000000f ffff00000887fbd0
[   20.704802] fc60: fffffff43a5f1a80 0000000000000000 ffff80063a71fc80 ffff000008880240
[   20.712632] fc80: ffff80063a71fd90 ffff0000087c7a34 ffff80063afc7180 0000000000000000
[   20.720462] fca0: 0000ffffcae6fe18 0000000000000014 0000000060000000 0000000000000015
[   20.728292] fcc0: 0000000000000123 00000000000000ce ffff0000088d2000 ffff80063b1f1900
[   20.736122] fce0: 0000000000008933 ffff000008e7cb80 ffff80063a71fd80 ffff0000087c50a4
[   20.743951] fd00: 0000000000008933 ffff000008e7cb80 ffff000008e7cb80 000000100000000e
[   20.751781] fd20: ffff80063a71fe4c 0000ffff00000300 0000000000000123 0000000000000000
[   20.759611] fd40: 0000000000000000 ffff80063b1f0000 000000000000000e 0000000000000300
[   20.767441] fd60: 0000000000000000 0000000000000000 0000000000000000 0000000000000000
[   20.775271] fd80: 0000000000000000 0000000000000000 ffff80063a71fda0 ffff0000087c8c20
[   20.783100] fda0: 0000000000000000 ffff000008082f30 0000000000000000 0000800637260000
[   20.790930] fdc0: ffffffffffffffff 0000ffffa0903078 0000000000000000 000000001ea87232
[   20.798760] fde0: 000000000000000f ffff80063a71fe40 ffff800600000014 ffff000000000001
[   20.806590] fe00: 0000000000000000 0000000000000000 ffff80063a71fde8 0000000000000000
[   20.814420] fe20: 0000000000000000 0000000000000000 0000000000000000 0000000000000001
[   20.822249] fe40: 0000000203000011 0000000000000000 0000000000000000 ffff80063a68aa00
[   20.830079] fe60: ffff80063a68aa00 0000000000000003 0000000000008933 ffff0000081f1b9c
[   20.837909] fe80: 0000000000000000 ffff000008082f30 0000000000000000 0000800637260000
[   20.845739] fea0: ffffffffffffffff 0000ffffa07ca81c 0000000060000000 0000000000000015
[   20.853569] fec0: 0000000000000003 000000001ea87232 000000000000000f 0000000000000000
[   20.861399] fee0: 0000ffffcae6fe18 0000000000000014 0000000000000300 0000000000000000
[   20.869228] ff00: 00000000000000ce 0000000000000000 00000000ffffffff 0000000000000000
[   20.877059] ff20: 0000000000000002 0000ffffcae87ff0 0000ffffa09cfa14 0000ffffa084f588
[   20.884888] ff40: 0000000000000000 0000ffffa09ba018 0000ffffcae6fb20 000000001ea87010
[   20.892718] ff60: 0000ffffa09b9000 0000ffffcae6fe30 0000ffffcae6fe18 000000000000000f
[   20.900548] ff80: 0000000000000003 000000001ea87232 0000000000000000 0000000000000000
[   20.908378] ffa0: 0000000000000000 0000ffffcae6fdc0 0000ffffa09a7824 0000ffffcae6fdc0
[   20.916208] ffc0: 0000ffffa0903078 0000000060000000 0000000000000003 00000000000000ce
[   20.924038] ffe0: 0000000000000000 0000000000000000 ffffffffffffffff ffffffffffffffff
[   20.931867] Call trace:
[   20.934312] Exception stack(0xffff80063a71f7e0 to 0xffff80063a71f910)
[   20.940750] f7e0: 0000000000000000 0001000000000000 ffff80063a71f9b0 ffff00000839c4c0
[   20.948580] f800: ffff80063a71f840 ffff00000888a6e4 ffff80063a24c418 ffff80063a24c448
[   20.956410] f820: 0000000000000000 ffff00000811cd54 ffff80063a71f860 ffff80063a24c458
[   20.964240] f840: ffff80063a71f870 ffff00000888b258 ffff80063a24c418 0000000000000001
[   20.972070] f860: ffff80063a71f910 ffff80063a7b7028 ffff80063a71f890 ffff0000088825e4
[   20.979899] f880: 0000000000000000 00000000bafff000 000000067abe2adc 0000000000000000
[   20.987729] f8a0: 0000000000000001 0000000000000000 ffff000008ed50d0 0000000000000000
[   20.995560] f8c0: 0000000000000000 0000000000000000 ffff80063abe2adc ffff000008096360
[   21.003390] f8e0: 000000000063abe2 0000ffffcae87ff0 0000ffffa09cfa14 0000ffffa084f588
[   21.011219] f900: ffff0000087c8b70 0000ffffa09ba018
[   21.016097] [<ffff00000839c4c0>] swiotlb_tbl_map_single+0x178/0x2ec
[   21.022362] [<ffff00000839c680>] map_single+0x4c/0x98
[   21.027411] [<ffff00000839cd10>] swiotlb_map_page+0xa4/0x138
[   21.033072] [<ffff000008096380>] __swiotlb_map_page+0x20/0x7c
[   21.038821] [<ffff00000864f770>] ravb_start_xmit+0x174/0x668
[   21.044484] [<ffff0000087e6498>] dev_hard_start_xmit+0x8c/0x120
[   21.050407] [<ffff000008807510>] sch_direct_xmit+0x108/0x1a0
[   21.056064] [<ffff0000087e67dc>] __dev_queue_xmit+0x194/0x4cc
[   21.061807] [<ffff0000087e6b24>] dev_queue_xmit+0x10/0x18
[   21.067214] [<ffff000008880240>] packet_sendmsg+0xf40/0x1220
[   21.072873] [<ffff0000087c7a34>] sock_sendmsg+0x18/0x2c
[   21.078097] [<ffff0000087c8c20>] SyS_sendto+0xb0/0xf0
[   21.083150] [<ffff000008082f30>] el0_svc_naked+0x24/0x28
[   21.088462] Code: d34bfef7 2a1803f3 1a9f86d6 35fff878 (d4210000)
[   21.094611] ---[ end trace 5bc544ad491f3814 ]---
[   21.099234] Kernel panic - not syncing: Fatal exception in interrupt
[   21.105587] Kernel Offset: disabled
[   21.109073] Memory Limit: none
[   21.112126] ---[ end Kernel panic - not syncing: Fatal exception in interrupt

Fixes: 2f45d1902acf ("ravb: minimize TX data copying")
Signed-off-by: Masaru Nagai <masaru.nagai.vx@renesas.com
Signed-off-by: Simon Horman <horms+renesas@verge.net.au>
Acked-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/ravb_main.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index d6a2178..862f18e 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -1508,6 +1508,19 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	buffer = PTR_ALIGN(priv->tx_align[q], DPTR_ALIGN) +
 		 entry / NUM_TX_DESC * DPTR_ALIGN;
 	len = PTR_ALIGN(skb->data, DPTR_ALIGN) - skb->data;
+	/* Zero length DMA descriptors are problematic as they seem to
+	 * terminate DMA transfers. Avoid them by simply using a length of
+	 * DPTR_ALIGN (4) when skb data is aligned to DPTR_ALIGN.
+	 *
+	 * As skb is guaranteed to have at least ETH_ZLEN (60) bytes of
+	 * data by the call to skb_put_padto() above this is safe with
+	 * respect to both the length of the first DMA descriptor (len)
+	 * overflowing the available data and the length of the second DMA
+	 * descriptor (skb->len - len) being negative.
+	 */
+	if (len == 0)
+		len = DPTR_ALIGN;
+
 	memcpy(buffer, skb->data, len);
 	dma_addr = dma_map_single(ndev->dev.parent, buffer, len, DMA_TO_DEVICE);
 	if (dma_mapping_error(ndev->dev.parent, dma_addr))
-- 
2.4.11


From 2f010eb0f332f3004eff5a9b480aa4107becf54f Mon Sep 17 00:00:00 2001
From: Jakub Sitnicki <jkbs@redhat.com>
Date: Fri, 13 Jan 2017 10:12:20 +0100
Subject: [PATCH 13/32] ip6_tunnel: Account for tunnel header in tunnel MTU

[ Upstream commit 02ca0423fd65a0a9c4d70da0dbb8f4b8503f08c7 ]

With ip6gre we have a tunnel header which also makes the tunnel MTU
smaller. We need to reserve room for it. Previously we were using up
space reserved for the Tunnel Encapsulation Limit option
header (RFC 2473).

Also, after commit b05229f44228 ("gre6: Cleanup GREv6 transmit path,
call common GRE functions") our contract with the caller has
changed. Now we check if the packet length exceeds the tunnel MTU after
the tunnel header has been pushed, unlike before.

This is reflected in the check where we look at the packet length minus
the size of the tunnel header, which is already accounted for in tunnel
MTU.

Fixes: b05229f44228 ("gre6: Cleanup GREv6 transmit path, call common GRE functions")
Signed-off-by: Jakub Sitnicki <jkbs@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index d76674e..f95437f 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1108,7 +1108,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 				     t->parms.name);
 		goto tx_err_dst_release;
 	}
-	mtu = dst_mtu(dst) - psh_hlen;
+	mtu = dst_mtu(dst) - psh_hlen - t->tun_hlen;
 	if (encap_limit >= 0) {
 		max_headroom += 8;
 		mtu -= 8;
@@ -1117,7 +1117,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 		mtu = IPV6_MIN_MTU;
 	if (skb_dst(skb) && !t->parms.collect_md)
 		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
-	if (skb->len > mtu && !skb_is_gso(skb)) {
+	if (skb->len - t->tun_hlen > mtu && !skb_is_gso(skb)) {
 		*pmtu = mtu;
 		err = -EMSGSIZE;
 		goto tx_err_dst_release;
-- 
2.4.11


From 1752f7781037d0cd384643f5b4d23f0ed4ee5bc7 Mon Sep 17 00:00:00 2001
From: Basil Gunn <basil@pacabunga.com>
Date: Sat, 14 Jan 2017 12:18:55 -0800
Subject: [PATCH 14/32] ax25: Fix segfault after sock connection timeout

[ Upstream commit 8a367e74c0120ef68c8c70d5a025648c96626dff ]

The ax.25 socket connection timed out & the sock struct has been
previously taken down ie. sock struct is now a NULL pointer. Checking
the sock_flag causes the segfault.  Check if the socket struct pointer
is NULL before checking sock_flag. This segfault is seen in
timed out netrom connections.

Please submit to -stable.

Signed-off-by: Basil Gunn <basil@pacabunga.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ax25/ax25_subr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ax25/ax25_subr.c b/net/ax25/ax25_subr.c
index 655a7d4..983f0b5 100644
--- a/net/ax25/ax25_subr.c
+++ b/net/ax25/ax25_subr.c
@@ -264,7 +264,7 @@ void ax25_disconnect(ax25_cb *ax25, int reason)
 {
 	ax25_clear_queues(ax25);
 
-	if (!sock_flag(ax25->sk, SOCK_DESTROY))
+	if (!ax25->sk || !sock_flag(ax25->sk, SOCK_DESTROY))
 		ax25_stop_heartbeat(ax25);
 	ax25_stop_t1timer(ax25);
 	ax25_stop_t2timer(ax25);
-- 
2.4.11


From db606008bbd2ce3ddf0c250292e32e7391a1e43a Mon Sep 17 00:00:00 2001
From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Sun, 15 Jan 2017 10:14:06 -0500
Subject: [PATCH 15/32] net sched actions: fix refcnt when GETing of action
 after bind

[ Upstream commit 0faa9cb5b3836a979864a6357e01d2046884ad52 ]

Demonstrating the issue:

.. add a drop action
$sudo $TC actions add action drop index 10

.. retrieve it
$ sudo $TC -s actions get action gact index 10

	action order 1: gact action drop
	 random type none pass val 0
	 index 10 ref 2 bind 0 installed 29 sec used 29 sec
 	Action statistics:
	Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
	backlog 0b 0p requeues 0

... bug 1 above: reference is two.
    Reference is actually 1 but we forget to subtract 1.

... do a GET again and we see the same issue
    try a few times and nothing changes
~$ sudo $TC -s actions get action gact index 10

	action order 1: gact action drop
	 random type none pass val 0
	 index 10 ref 2 bind 0 installed 31 sec used 31 sec
 	Action statistics:
	Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
	backlog 0b 0p requeues 0

... lets try to bind the action to a filter..
$ sudo $TC qdisc add dev lo ingress
$ sudo $TC filter add dev lo parent ffff: protocol ip prio 1 \
  u32 match ip dst 127.0.0.1/32 flowid 1:1 action gact index 10

... and now a few GETs:
$ sudo $TC -s actions get action gact index 10

	action order 1: gact action drop
	 random type none pass val 0
	 index 10 ref 3 bind 1 installed 204 sec used 204 sec
 	Action statistics:
	Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
	backlog 0b 0p requeues 0

$ sudo $TC -s actions get action gact index 10

	action order 1: gact action drop
	 random type none pass val 0
	 index 10 ref 4 bind 1 installed 206 sec used 206 sec
 	Action statistics:
	Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
	backlog 0b 0p requeues 0

$ sudo $TC -s actions get action gact index 10

	action order 1: gact action drop
	 random type none pass val 0
	 index 10 ref 5 bind 1 installed 235 sec used 235 sec
 	Action statistics:
	Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
	backlog 0b 0p requeues 0

.... as can be observed the reference count keeps going up.

After the fix

$ sudo $TC actions add action drop index 10
$ sudo $TC -s actions get action gact index 10

	action order 1: gact action drop
	 random type none pass val 0
	 index 10 ref 1 bind 0 installed 4 sec used 4 sec
 	Action statistics:
	Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
	backlog 0b 0p requeues 0

$ sudo $TC -s actions get action gact index 10

	action order 1: gact action drop
	 random type none pass val 0
	 index 10 ref 1 bind 0 installed 6 sec used 6 sec
 	Action statistics:
	Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
	backlog 0b 0p requeues 0

$ sudo $TC qdisc add dev lo ingress
$ sudo $TC filter add dev lo parent ffff: protocol ip prio 1 \
  u32 match ip dst 127.0.0.1/32 flowid 1:1 action gact index 10

$ sudo $TC -s actions get action gact index 10

	action order 1: gact action drop
	 random type none pass val 0
	 index 10 ref 2 bind 1 installed 32 sec used 32 sec
 	Action statistics:
	Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
	backlog 0b 0p requeues 0

$ sudo $TC -s actions get action gact index 10

	action order 1: gact action drop
	 random type none pass val 0
	 index 10 ref 2 bind 1 installed 33 sec used 33 sec
 	Action statistics:
	Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
	backlog 0b 0p requeues 0

Fixes: aecc5cefc389 ("net sched actions: fix GETing actions")
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_api.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index f893d18..c6c2a93 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -903,8 +903,6 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
 			goto err;
 		}
 		act->order = i;
-		if (event == RTM_GETACTION)
-			act->tcfa_refcnt++;
 		list_add_tail(&act->list, &actions);
 	}
 
@@ -917,7 +915,8 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
 		return ret;
 	}
 err:
-	tcf_action_destroy(&actions, 0);
+	if (event != RTM_GETACTION)
+		tcf_action_destroy(&actions, 0);
 	return ret;
 }
 
-- 
2.4.11


From c15cd0eb4072c99224f77c7306d11ce7811712c6 Mon Sep 17 00:00:00 2001
From: Rolf Neugebauer <rolf.neugebauer@docker.com>
Date: Tue, 17 Jan 2017 18:13:51 +0000
Subject: [PATCH 16/32] virtio: don't set VIRTIO_NET_HDR_F_DATA_VALID on xmit

[ Upstream commit 501db511397fd6efff3aa5b4e8de415b55559550 ]

This patch part reverts fd2a0437dc33 and e858fae2b0b8 which introduced a
subtle change in how the virtio_net flags are derived from the SKBs
ip_summed field.

With the above commits, the flags are set to VIRTIO_NET_HDR_F_DATA_VALID
when ip_summed == CHECKSUM_UNNECESSARY, thus treating it differently to
ip_summed == CHECKSUM_NONE, which should be the same.

Further, the virtio spec 1.0 / CS04 explicitly says that
VIRTIO_NET_HDR_F_DATA_VALID must not be set by the driver.

Fixes: fd2a0437dc33 ("virtio_net: introduce virtio_net_hdr_{from,to}_skb")
Fixes: e858fae2b0b8 (" virtio_net: use common code for virtio_net_hdr and skb GSO conversion")
Signed-off-by: Rolf Neugebauer <rolf.neugebauer@docker.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/virtio_net.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 1c912f8..40914bb 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -91,8 +91,6 @@ static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb,
 				skb_checksum_start_offset(skb));
 		hdr->csum_offset = __cpu_to_virtio16(little_endian,
 				skb->csum_offset);
-	} else if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
-		hdr->flags = VIRTIO_NET_HDR_F_DATA_VALID;
 	} /* else everything is zero */
 
 	return 0;
-- 
2.4.11


From 1e37e88a3a3848b25d5ecc86137972542707fa22 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Fri, 20 Jan 2017 14:32:42 +0800
Subject: [PATCH 17/32] virtio-net: restore VIRTIO_HDR_F_DATA_VALID on
 receiving

[ Upstream commit 6391a4481ba0796805d6581e42f9f0418c099e34 ]

Commit 501db511397f ("virtio: don't set VIRTIO_NET_HDR_F_DATA_VALID on
xmit") in fact disables VIRTIO_HDR_F_DATA_VALID on receiving path too,
fixing this by adding a hint (has_data_valid) and set it only on the
receiving path.

Cc: Rolf Neugebauer <rolf.neugebauer@docker.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Rolf Neugebauer <rolf.neugebauer@docker.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macvtap.c      | 2 +-
 drivers/net/tun.c          | 2 +-
 drivers/net/virtio_net.c   | 2 +-
 include/linux/virtio_net.h | 6 +++++-
 net/packet/af_packet.c     | 2 +-
 5 files changed, 9 insertions(+), 5 deletions(-)

diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 7869b06..6f38daf 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -827,7 +827,7 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q,
 			return -EINVAL;
 
 		ret = virtio_net_hdr_from_skb(skb, &vnet_hdr,
-					      macvtap_is_little_endian(q));
+					      macvtap_is_little_endian(q), true);
 		if (ret)
 			BUG();
 
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index db6acec..18402d7 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1374,7 +1374,7 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 			return -EINVAL;
 
 		ret = virtio_net_hdr_from_skb(skb, &gso,
-					      tun_is_little_endian(tun));
+					      tun_is_little_endian(tun), true);
 		if (ret) {
 			struct skb_shared_info *sinfo = skb_shinfo(skb);
 			pr_err("unexpected GSO type: "
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index cbf1c61..51fc0c3 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -840,7 +840,7 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
 		hdr = skb_vnet_hdr(skb);
 
 	if (virtio_net_hdr_from_skb(skb, &hdr->hdr,
-				    virtio_is_little_endian(vi->vdev)))
+				    virtio_is_little_endian(vi->vdev), false))
 		BUG();
 
 	if (vi->mergeable_rx_bufs)
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 40914bb..f211c34 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -56,7 +56,8 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 
 static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb,
 					  struct virtio_net_hdr *hdr,
-					  bool little_endian)
+					  bool little_endian,
+					  bool has_data_valid)
 {
 	memset(hdr, 0, sizeof(*hdr));
 
@@ -91,6 +92,9 @@ static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb,
 				skb_checksum_start_offset(skb));
 		hdr->csum_offset = __cpu_to_virtio16(little_endian,
 				skb->csum_offset);
+	} else if (has_data_valid &&
+		   skb->ip_summed == CHECKSUM_UNNECESSARY) {
+		hdr->flags = VIRTIO_NET_HDR_F_DATA_VALID;
 	} /* else everything is zero */
 
 	return 0;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index dd23323..94e4a59 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1972,7 +1972,7 @@ static int __packet_rcv_vnet(const struct sk_buff *skb,
 {
 	*vnet_hdr = (const struct virtio_net_hdr) { 0 };
 
-	if (virtio_net_hdr_from_skb(skb, vnet_hdr, vio_le()))
+	if (virtio_net_hdr_from_skb(skb, vnet_hdr, vio_le(), true))
 		BUG();
 
 	return 0;
-- 
2.4.11


From 380038dc7fcc92ba66571f2994ca671513fbdaf7 Mon Sep 17 00:00:00 2001
From: Lance Richardson <lrichard@redhat.com>
Date: Mon, 16 Jan 2017 18:37:58 -0500
Subject: [PATCH 18/32] vxlan: fix byte order of vxlan-gpe port number

[ Upstream commit d5ff72d9af73bc3cbaa3edb541333a851f8c7295 ]

vxlan->cfg.dst_port is in network byte order, so an htons()
is needed here. Also reduced comment length to stay closer
to 80 column width (still slightly over, however).

Fixes: e1e5314de08b ("vxlan: implement GPE")
Signed-off-by: Lance Richardson <lrichard@redhat.com>
Acked-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 2ba01ca..0fafaa9 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2887,7 +2887,7 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 	memcpy(&vxlan->cfg, conf, sizeof(*conf));
 	if (!vxlan->cfg.dst_port) {
 		if (conf->flags & VXLAN_F_GPE)
-			vxlan->cfg.dst_port = 4790; /* IANA assigned VXLAN-GPE port */
+			vxlan->cfg.dst_port = htons(4790); /* IANA VXLAN-GPE port */
 		else
 			vxlan->cfg.dst_port = default_port;
 	}
-- 
2.4.11


From f2afb38578a3775b9f21acd7305f7bd2613a1409 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 18 Jan 2017 12:12:17 -0800
Subject: [PATCH 19/32] net: fix harmonize_features() vs NETIF_F_HIGHDMA

[ Upstream commit 7be2c82cfd5d28d7adb66821a992604eb6dd112e ]

Ashizuka reported a highmem oddity and sent a patch for freescale
fec driver.

But the problem root cause is that core networking stack
must ensure no skb with highmem fragment is ever sent through
a device that does not assert NETIF_F_HIGHDMA in its features.

We need to call illegal_highdma() from harmonize_features()
regardless of CSUM checks.

Fixes: ec5f06156423 ("net: Kill link between CSUM and SG features.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Pravin Shelar <pshelar@ovn.org>
Reported-by: "Ashizuka, Yuusuke" <ashiduka@jp.fujitsu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index e1d731f..df51c50 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2815,9 +2815,9 @@ static netdev_features_t harmonize_features(struct sk_buff *skb,
 	if (skb->ip_summed != CHECKSUM_NONE &&
 	    !can_checksum_protocol(features, type)) {
 		features &= ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
-	} else if (illegal_highdma(skb->dev, skb)) {
-		features &= ~NETIF_F_SG;
 	}
+	if (illegal_highdma(skb->dev, skb))
+		features &= ~NETIF_F_SG;
 
 	return features;
 }
-- 
2.4.11


From 1676428ac3a9f3907bfd6e6377a6039dc7aa3024 Mon Sep 17 00:00:00 2001
From: Daniel Gonzalez Cabanelas <dgcbueu@gmail.com>
Date: Tue, 17 Jan 2017 16:26:55 -0800
Subject: [PATCH 20/32] net: phy: bcm63xx: Utilize correct config_intr function

[ Upstream commit cd33b3e0da43522ff8e8f2b2b71d3d08298512b0 ]

Commit a1cba5613edf ("net: phy: Add Broadcom phy library for common
interfaces") make the BCM63xx PHY driver utilize bcm_phy_config_intr()
which would appear to do the right thing, except that it does not write
to the MII_BCM63XX_IR register but to MII_BCM54XX_ECR which is
different.

This would be causing invalid link parameters and events from being
generated by the PHY interrupt.

Fixes: a1cba5613edf ("net: phy: Add Broadcom phy library for common interfaces")
Signed-off-by: Daniel Gonzalez Cabanelas <dgcbueu@gmail.com>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/bcm63xx.c | 21 +++++++++++++++++++--
 1 file changed, 19 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/bcm63xx.c b/drivers/net/phy/bcm63xx.c
index e741bf6..b0492ef 100644
--- a/drivers/net/phy/bcm63xx.c
+++ b/drivers/net/phy/bcm63xx.c
@@ -21,6 +21,23 @@ MODULE_DESCRIPTION("Broadcom 63xx internal PHY driver");
 MODULE_AUTHOR("Maxime Bizon <mbizon@freebox.fr>");
 MODULE_LICENSE("GPL");
 
+static int bcm63xx_config_intr(struct phy_device *phydev)
+{
+	int reg, err;
+
+	reg = phy_read(phydev, MII_BCM63XX_IR);
+	if (reg < 0)
+		return reg;
+
+	if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
+		reg &= ~MII_BCM63XX_IR_GMASK;
+	else
+		reg |= MII_BCM63XX_IR_GMASK;
+
+	err = phy_write(phydev, MII_BCM63XX_IR, reg);
+	return err;
+}
+
 static int bcm63xx_config_init(struct phy_device *phydev)
 {
 	int reg, err;
@@ -55,7 +72,7 @@ static struct phy_driver bcm63xx_driver[] = {
 	.config_aneg	= genphy_config_aneg,
 	.read_status	= genphy_read_status,
 	.ack_interrupt	= bcm_phy_ack_intr,
-	.config_intr	= bcm_phy_config_intr,
+	.config_intr	= bcm63xx_config_intr,
 }, {
 	/* same phy as above, with just a different OUI */
 	.phy_id		= 0x002bdc00,
@@ -67,7 +84,7 @@ static struct phy_driver bcm63xx_driver[] = {
 	.config_aneg	= genphy_config_aneg,
 	.read_status	= genphy_read_status,
 	.ack_interrupt	= bcm_phy_ack_intr,
-	.config_intr	= bcm_phy_config_intr,
+	.config_intr	= bcm63xx_config_intr,
 } };
 
 module_phy_driver(bcm63xx_driver);
-- 
2.4.11


From 726ac6aaf2746cb8fbed1819a653e1e45292efbd Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Tue, 17 Jan 2017 14:57:36 -0800
Subject: [PATCH 21/32] lwtunnel: fix autoload of lwt modules

[ Upstream commit 9ed59592e3e379b2e9557dc1d9e9ec8fcbb33f16]

Trying to add an mpls encap route when the MPLS modules are not loaded
hangs. For example:

    CONFIG_MPLS=y
    CONFIG_NET_MPLS_GSO=m
    CONFIG_MPLS_ROUTING=m
    CONFIG_MPLS_IPTUNNEL=m

    $ ip route add 10.10.10.10/32 encap mpls 100 via inet 10.100.1.2

The ip command hangs:
root       880   826  0 21:25 pts/0    00:00:00 ip route add 10.10.10.10/32 encap mpls 100 via inet 10.100.1.2

    $ cat /proc/880/stack
    [<ffffffff81065a9b>] call_usermodehelper_exec+0xd6/0x134
    [<ffffffff81065efc>] __request_module+0x27b/0x30a
    [<ffffffff814542f6>] lwtunnel_build_state+0xe4/0x178
    [<ffffffff814aa1e4>] fib_create_info+0x47f/0xdd4
    [<ffffffff814ae451>] fib_table_insert+0x90/0x41f
    [<ffffffff814a8010>] inet_rtm_newroute+0x4b/0x52
    ...

modprobe is trying to load rtnl-lwt-MPLS:

root       881     5  0 21:25 ?        00:00:00 /sbin/modprobe -q -- rtnl-lwt-MPLS

and it hangs after loading mpls_router:

    $ cat /proc/881/stack
    [<ffffffff81441537>] rtnl_lock+0x12/0x14
    [<ffffffff8142ca2a>] register_netdevice_notifier+0x16/0x179
    [<ffffffffa0033025>] mpls_init+0x25/0x1000 [mpls_router]
    [<ffffffff81000471>] do_one_initcall+0x8e/0x13f
    [<ffffffff81119961>] do_init_module+0x5a/0x1e5
    [<ffffffff810bd070>] load_module+0x13bd/0x17d6
    ...

The problem is that lwtunnel_build_state is called with rtnl lock
held preventing mpls_init from registering.

Given the potential references held by the time lwtunnel_build_state it
can not drop the rtnl lock to the load module. So, extract the module
loading code from lwtunnel_build_state into a new function to validate
the encap type. The new function is called while converting the user
request into a fib_config which is well before any table, device or
fib entries are examined.

Fixes: 745041e2aaf1 ("lwtunnel: autoload of lwt modules")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/lwtunnel.h  | 11 +++++++++
 net/core/lwtunnel.c     | 62 ++++++++++++++++++++++++++++++++++++++++++++-----
 net/ipv4/fib_frontend.c |  8 +++++++
 net/ipv6/route.c        | 12 +++++++++-
 4 files changed, 86 insertions(+), 7 deletions(-)

diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h
index ea3f80f..95581ca 100644
--- a/include/net/lwtunnel.h
+++ b/include/net/lwtunnel.h
@@ -106,6 +106,8 @@ int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op,
 			   unsigned int num);
 int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op,
 			   unsigned int num);
+int lwtunnel_valid_encap_type(u16 encap_type);
+int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len);
 int lwtunnel_build_state(struct net_device *dev, u16 encap_type,
 			 struct nlattr *encap,
 			 unsigned int family, const void *cfg,
@@ -169,6 +171,15 @@ static inline int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op,
 	return -EOPNOTSUPP;
 }
 
+static inline int lwtunnel_valid_encap_type(u16 encap_type)
+{
+	return -EOPNOTSUPP;
+}
+static inline int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline int lwtunnel_build_state(struct net_device *dev, u16 encap_type,
 				       struct nlattr *encap,
 				       unsigned int family, const void *cfg,
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index e5f84c2..2f6db38 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -26,6 +26,7 @@
 #include <net/lwtunnel.h>
 #include <net/rtnetlink.h>
 #include <net/ip6_fib.h>
+#include <net/nexthop.h>
 
 #ifdef CONFIG_MODULES
 
@@ -110,25 +111,74 @@ int lwtunnel_build_state(struct net_device *dev, u16 encap_type,
 	ret = -EOPNOTSUPP;
 	rcu_read_lock();
 	ops = rcu_dereference(lwtun_encaps[encap_type]);
+	if (likely(ops && ops->build_state))
+		ret = ops->build_state(dev, encap, family, cfg, lws);
+	rcu_read_unlock();
+
+	return ret;
+}
+EXPORT_SYMBOL(lwtunnel_build_state);
+
+int lwtunnel_valid_encap_type(u16 encap_type)
+{
+	const struct lwtunnel_encap_ops *ops;
+	int ret = -EINVAL;
+
+	if (encap_type == LWTUNNEL_ENCAP_NONE ||
+	    encap_type > LWTUNNEL_ENCAP_MAX)
+		return ret;
+
+	rcu_read_lock();
+	ops = rcu_dereference(lwtun_encaps[encap_type]);
+	rcu_read_unlock();
 #ifdef CONFIG_MODULES
 	if (!ops) {
 		const char *encap_type_str = lwtunnel_encap_str(encap_type);
 
 		if (encap_type_str) {
-			rcu_read_unlock();
+			__rtnl_unlock();
 			request_module("rtnl-lwt-%s", encap_type_str);
+			rtnl_lock();
+
 			rcu_read_lock();
 			ops = rcu_dereference(lwtun_encaps[encap_type]);
+			rcu_read_unlock();
 		}
 	}
 #endif
-	if (likely(ops && ops->build_state))
-		ret = ops->build_state(dev, encap, family, cfg, lws);
-	rcu_read_unlock();
+	return ops ? 0 : -EOPNOTSUPP;
+}
+EXPORT_SYMBOL(lwtunnel_valid_encap_type);
 
-	return ret;
+int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining)
+{
+	struct rtnexthop *rtnh = (struct rtnexthop *)attr;
+	struct nlattr *nla_entype;
+	struct nlattr *attrs;
+	struct nlattr *nla;
+	u16 encap_type;
+	int attrlen;
+
+	while (rtnh_ok(rtnh, remaining)) {
+		attrlen = rtnh_attrlen(rtnh);
+		if (attrlen > 0) {
+			attrs = rtnh_attrs(rtnh);
+			nla = nla_find(attrs, attrlen, RTA_ENCAP);
+			nla_entype = nla_find(attrs, attrlen, RTA_ENCAP_TYPE);
+
+			if (nla_entype) {
+				encap_type = nla_get_u16(nla_entype);
+
+				if (lwtunnel_valid_encap_type(encap_type) != 0)
+					return -EOPNOTSUPP;
+			}
+		}
+		rtnh = rtnh_next(rtnh, &remaining);
+	}
+
+	return 0;
 }
-EXPORT_SYMBOL(lwtunnel_build_state);
+EXPORT_SYMBOL(lwtunnel_valid_encap_type_attr);
 
 int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate)
 {
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 3e4f183..5b03d7f 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -46,6 +46,7 @@
 #include <net/rtnetlink.h>
 #include <net/xfrm.h>
 #include <net/l3mdev.h>
+#include <net/lwtunnel.h>
 #include <trace/events/fib.h>
 
 #ifndef CONFIG_IP_MULTIPLE_TABLES
@@ -676,6 +677,10 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
 			cfg->fc_mx_len = nla_len(attr);
 			break;
 		case RTA_MULTIPATH:
+			err = lwtunnel_valid_encap_type_attr(nla_data(attr),
+							     nla_len(attr));
+			if (err < 0)
+				goto errout;
 			cfg->fc_mp = nla_data(attr);
 			cfg->fc_mp_len = nla_len(attr);
 			break;
@@ -690,6 +695,9 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
 			break;
 		case RTA_ENCAP_TYPE:
 			cfg->fc_encap_type = nla_get_u16(attr);
+			err = lwtunnel_valid_encap_type(cfg->fc_encap_type);
+			if (err < 0)
+				goto errout;
 			break;
 		}
 	}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index acd80237..bff4460 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2885,6 +2885,11 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (tb[RTA_MULTIPATH]) {
 		cfg->fc_mp = nla_data(tb[RTA_MULTIPATH]);
 		cfg->fc_mp_len = nla_len(tb[RTA_MULTIPATH]);
+
+		err = lwtunnel_valid_encap_type_attr(cfg->fc_mp,
+						     cfg->fc_mp_len);
+		if (err < 0)
+			goto errout;
 	}
 
 	if (tb[RTA_PREF]) {
@@ -2898,9 +2903,14 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (tb[RTA_ENCAP])
 		cfg->fc_encap = tb[RTA_ENCAP];
 
-	if (tb[RTA_ENCAP_TYPE])
+	if (tb[RTA_ENCAP_TYPE]) {
 		cfg->fc_encap_type = nla_get_u16(tb[RTA_ENCAP_TYPE]);
 
+		err = lwtunnel_valid_encap_type(cfg->fc_encap_type);
+		if (err < 0)
+			goto errout;
+	}
+
 	if (tb[RTA_EXPIRES]) {
 		unsigned long timeout = addrconf_timeout_fixup(nla_get_u32(tb[RTA_EXPIRES]), HZ);
 
-- 
2.4.11


From abd3483711ffe5a28ae0411e312ee4a571426155 Mon Sep 17 00:00:00 2001
From: Kefeng Wang <wangkefeng.wang@huawei.com>
Date: Thu, 19 Jan 2017 16:26:21 +0800
Subject: [PATCH 22/32] ipv6: addrconf: Avoid addrconf_disable_change() using
 RCU read-side lock

[ Upstream commit 03e4deff4987f79c34112c5ba4eb195d4f9382b0 ]

Just like commit 4acd4945cd1e ("ipv6: addrconf: Avoid calling
netdevice notifiers with RCU read-side lock"), it is unnecessary
to make addrconf_disable_change() use RCU iteration over the
netdev list, since it already holds the RTNL lock, or we may meet
Illegal context switch in RCU read-side critical section.

Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 4bc5ba3..95dfcba 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5515,8 +5515,7 @@ static void addrconf_disable_change(struct net *net, __s32 newf)
 	struct net_device *dev;
 	struct inet6_dev *idev;
 
-	rcu_read_lock();
-	for_each_netdev_rcu(net, dev) {
+	for_each_netdev(net, dev) {
 		idev = __in6_dev_get(dev);
 		if (idev) {
 			int changed = (!idev->cnf.disable_ipv6) ^ (!newf);
@@ -5525,7 +5524,6 @@ static void addrconf_disable_change(struct net *net, __s32 newf)
 				dev_disable_change(idev);
 		}
 	}
-	rcu_read_unlock();
 }
 
 static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int newf)
-- 
2.4.11


From bce2dd692bf0939bd3051f438643c65133339312 Mon Sep 17 00:00:00 2001
From: Alexey Kodanev <alexey.kodanev@oracle.com>
Date: Thu, 19 Jan 2017 16:36:39 +0300
Subject: [PATCH 23/32] tcp: initialize max window for a new fastopen socket

[ Upstream commit 0dbd7ff3ac5017a46033a9d0a87a8267d69119d9 ]

Found that if we run LTP netstress test with large MSS (65K),
the first attempt from server to send data comparable to this
MSS on fastopen connection will be delayed by the probe timer.

Here is an example:

     < S  seq 0:0 win 43690 options [mss 65495 wscale 7 tfo cookie] length 32
     > S. seq 0:0 ack 1 win 43690 options [mss 65495 wscale 7] length 0
     < .  ack 1 win 342 length 0

Inside tcp_sendmsg(), tcp_send_mss() returns max MSS in 'mss_now',
as well as in 'size_goal'. This results the segment not queued for
transmition until all the data copied from user buffer. Then, inside
__tcp_push_pending_frames(), it breaks on send window test and
continues with the check probe timer.

Fragmentation occurs in tcp_write_wakeup()...

+0.2 > P. seq 1:43777 ack 1 win 342 length 43776
     < .  ack 43777, win 1365 length 0
     > P. seq 43777:65001 ack 1 win 342 options [...] length 21224
     ...

This also contradicts with the fact that we should bound to the half
of the window if it is large.

Fix this flaw by correctly initializing max_window. Before that, it
could have large values that affect further calculations of 'size_goal'.

Fixes: 168a8f58059a ("tcp: TCP Fast Open Server - main code path")
Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_fastopen.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index f519195..dd2560c 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -205,6 +205,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
 	 * scaled. So correct it appropriately.
 	 */
 	tp->snd_wnd = ntohs(tcp_hdr(skb)->window);
+	tp->max_window = tp->snd_wnd;
 
 	/* Activate the retrans timer so that SYNACK can be retransmitted.
 	 * The request socket is not added to the ehash
-- 
2.4.11


From bbb627af4ae638292f41258ff9ec2837cd89915c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 18 Jan 2017 23:03:08 -0800
Subject: [PATCH 24/32] net/mlx5e: Do not recycle pages from emergency reserve

[ Upstream commit e048fc50d7bde23136e098e04a324d7e3404408d ]

A driver using dev_alloc_page() must not reuse a page allocated from
emergency memory reserve.

Otherwise all packets using this page will be immediately dropped,
unless for very specific sockets having SOCK_MEMALLOC bit set.

This issue might be hard to debug, because only a fraction of received
packets would be dropped.

Fixes: 4415a0319f92 ("net/mlx5e: Implement RX mapped page cache for page recycle")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Tariq Toukan <tariqt@mellanox.com>
Cc: Saeed Mahameed <saeedm@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 33495d8..e7b2158 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -193,6 +193,9 @@ static inline bool mlx5e_rx_cache_put(struct mlx5e_rq *rq,
 		return false;
 	}
 
+	if (unlikely(page_is_pfmemalloc(dma_info->page)))
+		return false;
+
 	cache->page_cache[cache->tail] = *dma_info;
 	cache->tail = tail_next;
 	return true;
-- 
2.4.11


From 6c959140a91f694f7348e4f722c9652ac3f3d3db Mon Sep 17 00:00:00 2001
From: Ivan Vecera <cera@cera.cz>
Date: Fri, 20 Jan 2017 18:12:17 +0100
Subject: [PATCH 25/32] bridge: netlink: call br_changelink() during
 br_dev_newlink()

[ Upstream commit b6677449dff674cf5b81429b11d5c7f358852ef9 ]

Any bridge options specified during link creation (e.g. ip link add)
are ignored as br_dev_newlink() does not process them.
Use br_changelink() to do it.

Fixes: 133235161721 ("bridge: implement rtnl_link_ops->changelink")
Signed-off-by: Ivan Vecera <cera@cera.cz>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_netlink.c | 33 +++++++++++++++++++--------------
 1 file changed, 19 insertions(+), 14 deletions(-)

diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index e99037c..0474106 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -781,20 +781,6 @@ static int br_validate(struct nlattr *tb[], struct nlattr *data[])
 	return 0;
 }
 
-static int br_dev_newlink(struct net *src_net, struct net_device *dev,
-			  struct nlattr *tb[], struct nlattr *data[])
-{
-	struct net_bridge *br = netdev_priv(dev);
-
-	if (tb[IFLA_ADDRESS]) {
-		spin_lock_bh(&br->lock);
-		br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS]));
-		spin_unlock_bh(&br->lock);
-	}
-
-	return register_netdevice(dev);
-}
-
 static int br_port_slave_changelink(struct net_device *brdev,
 				    struct net_device *dev,
 				    struct nlattr *tb[],
@@ -1093,6 +1079,25 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
 	return 0;
 }
 
+static int br_dev_newlink(struct net *src_net, struct net_device *dev,
+			  struct nlattr *tb[], struct nlattr *data[])
+{
+	struct net_bridge *br = netdev_priv(dev);
+	int err;
+
+	if (tb[IFLA_ADDRESS]) {
+		spin_lock_bh(&br->lock);
+		br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS]));
+		spin_unlock_bh(&br->lock);
+	}
+
+	err = br_changelink(dev, tb, data);
+	if (err)
+		return err;
+
+	return register_netdevice(dev);
+}
+
 static size_t br_get_size(const struct net_device *brdev)
 {
 	return nla_total_size(sizeof(u32)) +	/* IFLA_BR_FORWARD_DELAY  */
-- 
2.4.11


From 02d8b44c79d000b2e46e36b228441f0cfe8cf891 Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Fri, 20 Jan 2017 12:58:34 -0800
Subject: [PATCH 26/32] net: mpls: Fix multipath selection for LSR use case

[ Upstream commit 9f427a0e474a67b454420c131709600d44850486 ]

MPLS multipath for LSR is broken -- always selecting the first nexthop
in the one label case. For example:

    $ ip -f mpls ro ls
    100
            nexthop as to 200 via inet 172.16.2.2  dev virt12
            nexthop as to 300 via inet 172.16.3.2  dev virt13
    101
            nexthop as to 201 via inet6 2000:2::2  dev virt12
            nexthop as to 301 via inet6 2000:3::2  dev virt13

In this example incoming packets have a single MPLS labels which means
BOS bit is set. The BOS bit is passed from mpls_forward down to
mpls_multipath_hash which never processes the hash loop because BOS is 1.

Update mpls_multipath_hash to process the entire label stack. mpls_hdr_len
tracks the total mpls header length on each pass (on pass N mpls_hdr_len
is N * sizeof(mpls_shim_hdr)). When the label is found with the BOS set
it verifies the skb has sufficient header for ipv4 or ipv6, and find the
IPv4 and IPv6 header by using the last mpls_hdr pointer and adding 1 to
advance past it.

With these changes I have verified the code correctly sees the label,
BOS, IPv4 and IPv6 addresses in the network header and icmp/tcp/udp
traffic for ipv4 and ipv6 are distributed across the nexthops.

Fixes: 1c78efa8319ca ("mpls: flow-based multipath selection")
Acked-by: Robert Shearman <rshearma@brocade.com>
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mpls/af_mpls.c | 48 +++++++++++++++++++++++++-----------------------
 1 file changed, 25 insertions(+), 23 deletions(-)

diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 15fe976..5b77377 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -98,18 +98,19 @@ bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
 }
 EXPORT_SYMBOL_GPL(mpls_pkt_too_big);
 
-static u32 mpls_multipath_hash(struct mpls_route *rt,
-			       struct sk_buff *skb, bool bos)
+static u32 mpls_multipath_hash(struct mpls_route *rt, struct sk_buff *skb)
 {
 	struct mpls_entry_decoded dec;
+	unsigned int mpls_hdr_len = 0;
 	struct mpls_shim_hdr *hdr;
 	bool eli_seen = false;
 	int label_index;
 	u32 hash = 0;
 
-	for (label_index = 0; label_index < MAX_MP_SELECT_LABELS && !bos;
+	for (label_index = 0; label_index < MAX_MP_SELECT_LABELS;
 	     label_index++) {
-		if (!pskb_may_pull(skb, sizeof(*hdr) * label_index))
+		mpls_hdr_len += sizeof(*hdr);
+		if (!pskb_may_pull(skb, mpls_hdr_len))
 			break;
 
 		/* Read and decode the current label */
@@ -134,37 +135,38 @@ static u32 mpls_multipath_hash(struct mpls_route *rt,
 			eli_seen = true;
 		}
 
-		bos = dec.bos;
-		if (bos && pskb_may_pull(skb, sizeof(*hdr) * label_index +
-					 sizeof(struct iphdr))) {
+		if (!dec.bos)
+			continue;
+
+		/* found bottom label; does skb have room for a header? */
+		if (pskb_may_pull(skb, mpls_hdr_len + sizeof(struct iphdr))) {
 			const struct iphdr *v4hdr;
 
-			v4hdr = (const struct iphdr *)(mpls_hdr(skb) +
-						       label_index);
+			v4hdr = (const struct iphdr *)(hdr + 1);
 			if (v4hdr->version == 4) {
 				hash = jhash_3words(ntohl(v4hdr->saddr),
 						    ntohl(v4hdr->daddr),
 						    v4hdr->protocol, hash);
 			} else if (v4hdr->version == 6 &&
-				pskb_may_pull(skb, sizeof(*hdr) * label_index +
-					      sizeof(struct ipv6hdr))) {
+				   pskb_may_pull(skb, mpls_hdr_len +
+						 sizeof(struct ipv6hdr))) {
 				const struct ipv6hdr *v6hdr;
 
-				v6hdr = (const struct ipv6hdr *)(mpls_hdr(skb) +
-								label_index);
-
+				v6hdr = (const struct ipv6hdr *)(hdr + 1);
 				hash = __ipv6_addr_jhash(&v6hdr->saddr, hash);
 				hash = __ipv6_addr_jhash(&v6hdr->daddr, hash);
 				hash = jhash_1word(v6hdr->nexthdr, hash);
 			}
 		}
+
+		break;
 	}
 
 	return hash;
 }
 
 static struct mpls_nh *mpls_select_multipath(struct mpls_route *rt,
-					     struct sk_buff *skb, bool bos)
+					     struct sk_buff *skb)
 {
 	int alive = ACCESS_ONCE(rt->rt_nhn_alive);
 	u32 hash = 0;
@@ -180,7 +182,7 @@ static struct mpls_nh *mpls_select_multipath(struct mpls_route *rt,
 	if (alive <= 0)
 		return NULL;
 
-	hash = mpls_multipath_hash(rt, skb, bos);
+	hash = mpls_multipath_hash(rt, skb);
 	nh_index = hash % alive;
 	if (alive == rt->rt_nhn)
 		goto out;
@@ -278,17 +280,11 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
 	hdr = mpls_hdr(skb);
 	dec = mpls_entry_decode(hdr);
 
-	/* Pop the label */
-	skb_pull(skb, sizeof(*hdr));
-	skb_reset_network_header(skb);
-
-	skb_orphan(skb);
-
 	rt = mpls_route_input_rcu(net, dec.label);
 	if (!rt)
 		goto drop;
 
-	nh = mpls_select_multipath(rt, skb, dec.bos);
+	nh = mpls_select_multipath(rt, skb);
 	if (!nh)
 		goto drop;
 
@@ -297,6 +293,12 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
 	if (!mpls_output_possible(out_dev))
 		goto drop;
 
+	/* Pop the label */
+	skb_pull(skb, sizeof(*hdr));
+	skb_reset_network_header(skb);
+
+	skb_orphan(skb);
+
 	if (skb_warn_if_lro(skb))
 		goto drop;
 
-- 
2.4.11


From 02817b3ffbd1d34e390e31a05d34356e97c5be6f Mon Sep 17 00:00:00 2001
From: hayeswang <hayeswang@realtek.com>
Date: Mon, 23 Jan 2017 14:18:43 +0800
Subject: [PATCH 27/32] r8152: don't execute runtime suspend if the tx is not
 empty

[ Upstream commit 6a0b76c04ec157c88ca943debf78a8ee58469f2d ]

Runtime suspend shouldn't be executed if the tx queue is not empty,
because the device is not idle.

Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index be4c86f..90b426c 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -32,7 +32,7 @@
 #define NETNEXT_VERSION		"08"
 
 /* Information for net */
-#define NET_VERSION		"6"
+#define NET_VERSION		"7"
 
 #define DRIVER_VERSION		"v1." NETNEXT_VERSION "." NET_VERSION
 #define DRIVER_AUTHOR "Realtek linux nic maintainers <nic_swsd@realtek.com>"
@@ -3572,6 +3572,8 @@ static bool delay_autosuspend(struct r8152 *tp)
 	 */
 	if (!sw_linking && tp->rtl_ops.in_nway(tp))
 		return true;
+	else if (!skb_queue_empty(&tp->tx_queue))
+		return true;
 	else
 		return false;
 }
-- 
2.4.11


From edecdbf760b61f74c2b9409166abf0fca8dafe7e Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Mon, 23 Jan 2017 11:17:35 -0800
Subject: [PATCH 28/32] af_unix: move unix_mknod() out of bindlock

[ Upstream commit 0fb44559ffd67de8517098b81f675fa0210f13f0 ]

Dmitry reported a deadlock scenario:

unix_bind() path:
u->bindlock ==> sb_writer

do_splice() path:
sb_writer ==> pipe->mutex ==> u->bindlock

In the unix_bind() code path, unix_mknod() does not have to
be done with u->bindlock held, since it is a pure fs operation,
so we can just move unix_mknod() out.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Tested-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Rainer Weikusat <rweikusat@mobileactivedefense.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c | 27 ++++++++++++++++-----------
 1 file changed, 16 insertions(+), 11 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 2358f26..2d03d5b 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -995,6 +995,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	unsigned int hash;
 	struct unix_address *addr;
 	struct hlist_head *list;
+	struct path path = { NULL, NULL };
 
 	err = -EINVAL;
 	if (sunaddr->sun_family != AF_UNIX)
@@ -1010,9 +1011,20 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		goto out;
 	addr_len = err;
 
+	if (sun_path[0]) {
+		umode_t mode = S_IFSOCK |
+		       (SOCK_INODE(sock)->i_mode & ~current_umask());
+		err = unix_mknod(sun_path, mode, &path);
+		if (err) {
+			if (err == -EEXIST)
+				err = -EADDRINUSE;
+			goto out;
+		}
+	}
+
 	err = mutex_lock_interruptible(&u->bindlock);
 	if (err)
-		goto out;
+		goto out_put;
 
 	err = -EINVAL;
 	if (u->addr)
@@ -1029,16 +1041,6 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	atomic_set(&addr->refcnt, 1);
 
 	if (sun_path[0]) {
-		struct path path;
-		umode_t mode = S_IFSOCK |
-		       (SOCK_INODE(sock)->i_mode & ~current_umask());
-		err = unix_mknod(sun_path, mode, &path);
-		if (err) {
-			if (err == -EEXIST)
-				err = -EADDRINUSE;
-			unix_release_addr(addr);
-			goto out_up;
-		}
 		addr->hash = UNIX_HASH_SIZE;
 		hash = d_real_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE - 1);
 		spin_lock(&unix_table_lock);
@@ -1065,6 +1067,9 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	spin_unlock(&unix_table_lock);
 out_up:
 	mutex_unlock(&u->bindlock);
+out_put:
+	if (err)
+		path_put(&path);
 out:
 	return err;
 }
-- 
2.4.11


From 529d5bd7e4fea7cb1f9d024b8a470b7c6ef5c175 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Tue, 24 Jan 2017 10:45:38 +0100
Subject: [PATCH 29/32] qmi_wwan/cdc_ether: add device ID for HP lt2523
 (Novatel E371) WWAN card
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 5b9f57516337b523f7466a53939aaaea7b78141b ]

Another rebranded Novatel E371.  qmi_wwan should drive this device, while
cdc_ether should ignore it.  Even though the USB descriptors are plain
CDC-ETHER that USB interface is a QMI interface.  Ref commit 7fdb7846c9ca
("qmi_wwan/cdc_ether: add device IDs for Dell 5804 (Novatel E371) WWAN
card")

Cc: Dan Williams <dcbw@redhat.com>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ether.c | 8 ++++++++
 drivers/net/usb/qmi_wwan.c  | 7 +++++++
 2 files changed, 15 insertions(+)

diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index dd623f6..b82be81 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -531,6 +531,7 @@ static const struct driver_info wwan_info = {
 #define SAMSUNG_VENDOR_ID	0x04e8
 #define LENOVO_VENDOR_ID	0x17ef
 #define NVIDIA_VENDOR_ID	0x0955
+#define HP_VENDOR_ID		0x03f0
 
 static const struct usb_device_id	products[] = {
 /* BLACKLIST !!
@@ -677,6 +678,13 @@ static const struct usb_device_id	products[] = {
 	.driver_info = 0,
 },
 
+/* HP lt2523 (Novatel E371) - handled by qmi_wwan */
+{
+	USB_DEVICE_AND_INTERFACE_INFO(HP_VENDOR_ID, 0x421d, USB_CLASS_COMM,
+				      USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+	.driver_info = 0,
+},
+
 /* AnyDATA ADU960S - handled by qmi_wwan */
 {
 	USB_DEVICE_AND_INTERFACE_INFO(0x16d5, 0x650a, USB_CLASS_COMM,
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 6fe1cdb..24d5272 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -654,6 +654,13 @@ static const struct usb_device_id products[] = {
 					      USB_CDC_PROTO_NONE),
 		.driver_info        = (unsigned long)&qmi_wwan_info,
 	},
+	{	/* HP lt2523 (Novatel E371) */
+		USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x421d,
+					      USB_CLASS_COMM,
+					      USB_CDC_SUBCLASS_ETHERNET,
+					      USB_CDC_PROTO_NONE),
+		.driver_info        = (unsigned long)&qmi_wwan_info,
+	},
 	{	/* HP lt4112 LTE/HSPA+ Gobi 4G Module (Huawei me906e) */
 		USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x581d, USB_CLASS_VENDOR_SPEC, 1, 7),
 		.driver_info = (unsigned long)&qmi_wwan_info,
-- 
2.4.11


From 37eaa239d9fcdc437e1aa3427b792865b04b8abe Mon Sep 17 00:00:00 2001
From: Robert Shearman <rshearma@brocade.com>
Date: Tue, 24 Jan 2017 16:26:47 +0000
Subject: [PATCH 30/32] net: Specify the owning module for lwtunnel ops

[ Upstream commit 88ff7334f25909802140e690c0e16433e485b0a0 ]

Modules implementing lwtunnel ops should not be allowed to unload
while there is state alive using those ops, so specify the owning
module for all lwtunnel ops.

Signed-off-by: Robert Shearman <rshearma@brocade.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/lwtunnel.h    | 2 ++
 net/ipv4/ip_tunnel_core.c | 2 ++
 net/ipv6/ila/ila_lwt.c    | 1 +
 net/mpls/mpls_iptunnel.c  | 1 +
 4 files changed, 6 insertions(+)

diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h
index 95581ca..3e0a7a9 100644
--- a/include/net/lwtunnel.h
+++ b/include/net/lwtunnel.h
@@ -43,6 +43,8 @@ struct lwtunnel_encap_ops {
 	int (*get_encap_size)(struct lwtunnel_state *lwtstate);
 	int (*cmp_encap)(struct lwtunnel_state *a, struct lwtunnel_state *b);
 	int (*xmit)(struct sk_buff *skb);
+
+	struct module *owner;
 };
 
 #ifdef CONFIG_LWTUNNEL
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index fed3d29..0fd1976 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -313,6 +313,7 @@ static const struct lwtunnel_encap_ops ip_tun_lwt_ops = {
 	.fill_encap = ip_tun_fill_encap_info,
 	.get_encap_size = ip_tun_encap_nlsize,
 	.cmp_encap = ip_tun_cmp_encap,
+	.owner = THIS_MODULE,
 };
 
 static const struct nla_policy ip6_tun_policy[LWTUNNEL_IP6_MAX + 1] = {
@@ -403,6 +404,7 @@ static const struct lwtunnel_encap_ops ip6_tun_lwt_ops = {
 	.fill_encap = ip6_tun_fill_encap_info,
 	.get_encap_size = ip6_tun_encap_nlsize,
 	.cmp_encap = ip_tun_cmp_encap,
+	.owner = THIS_MODULE,
 };
 
 void __init ip_tunnel_core_init(void)
diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c
index e50c27a..f3db364 100644
--- a/net/ipv6/ila/ila_lwt.c
+++ b/net/ipv6/ila/ila_lwt.c
@@ -164,6 +164,7 @@ static const struct lwtunnel_encap_ops ila_encap_ops = {
 	.fill_encap = ila_fill_encap_info,
 	.get_encap_size = ila_encap_nlsize,
 	.cmp_encap = ila_encap_cmp,
+	.owner = THIS_MODULE,
 };
 
 int ila_lwt_init(void)
diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c
index cf52cf3..bc9aaf5 100644
--- a/net/mpls/mpls_iptunnel.c
+++ b/net/mpls/mpls_iptunnel.c
@@ -218,6 +218,7 @@ static const struct lwtunnel_encap_ops mpls_iptun_ops = {
 	.fill_encap = mpls_fill_encap_info,
 	.get_encap_size = mpls_encap_nlsize,
 	.cmp_encap = mpls_encap_cmp,
+	.owner = THIS_MODULE,
 };
 
 static int __init mpls_iptunnel_init(void)
-- 
2.4.11


From 6bbd00ff473acc8af756e84e9a62c3a0258b1458 Mon Sep 17 00:00:00 2001
From: Robert Shearman <rshearma@brocade.com>
Date: Tue, 24 Jan 2017 16:26:48 +0000
Subject: [PATCH 31/32] lwtunnel: Fix oops on state free after encap module
 unload

[ Upstream commit 85c814016ce3b371016c2c054a905fa2492f5a65 ]

When attempting to free lwtunnel state after the module for the encap
has been unloaded an oops occurs:

BUG: unable to handle kernel NULL pointer dereference at 0000000000000008
IP: lwtstate_free+0x18/0x40
[..]
task: ffff88003e372380 task.stack: ffffc900001fc000
RIP: 0010:lwtstate_free+0x18/0x40
RSP: 0018:ffff88003fd83e88 EFLAGS: 00010246
RAX: 0000000000000000 RBX: ffff88002bbb3380 RCX: ffff88000c91a300
[..]
Call Trace:
 <IRQ>
 free_fib_info_rcu+0x195/0x1a0
 ? rt_fibinfo_free+0x50/0x50
 rcu_process_callbacks+0x2d3/0x850
 ? rcu_process_callbacks+0x296/0x850
 __do_softirq+0xe4/0x4cb
 irq_exit+0xb0/0xc0
 smp_apic_timer_interrupt+0x3d/0x50
 apic_timer_interrupt+0x93/0xa0
[..]
Code: e8 6e c6 fc ff 89 d8 5b 5d c3 bb de ff ff ff eb f4 66 90 66 66 66 66 90 55 48 89 e5 53 0f b7 07 48 89 fb 48 8b 04 c5 00 81 d5 81 <48> 8b 40 08 48 85 c0 74 13 ff d0 48 8d 7b 20 be 20 00 00 00 e8

The problem is after the module for the encap can be unloaded the
corresponding ops is removed and is thus NULL here.

Modules implementing lwtunnel ops should not be allowed to unload
while there is state alive using those ops, so grab the module
reference for the ops on creating lwtunnel state and of course release
the reference when freeing the state.

Fixes: 1104d9ba443a ("lwtunnel: Add destroy state operation")
Signed-off-by: Robert Shearman <rshearma@brocade.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/lwtunnel.h |  5 +----
 net/core/lwtunnel.c    | 14 +++++++++++++-
 2 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h
index 3e0a7a9..fc7c0db 100644
--- a/include/net/lwtunnel.h
+++ b/include/net/lwtunnel.h
@@ -48,10 +48,7 @@ struct lwtunnel_encap_ops {
 };
 
 #ifdef CONFIG_LWTUNNEL
-static inline void lwtstate_free(struct lwtunnel_state *lws)
-{
-	kfree(lws);
-}
+void lwtstate_free(struct lwtunnel_state *lws);
 
 static inline struct lwtunnel_state *
 lwtstate_get(struct lwtunnel_state *lws)
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index 2f6db38..afa64f0 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -66,6 +66,15 @@ EXPORT_SYMBOL(lwtunnel_state_alloc);
 static const struct lwtunnel_encap_ops __rcu *
 		lwtun_encaps[LWTUNNEL_ENCAP_MAX + 1] __read_mostly;
 
+void lwtstate_free(struct lwtunnel_state *lws)
+{
+	const struct lwtunnel_encap_ops *ops = lwtun_encaps[lws->type];
+
+	kfree(lws);
+	module_put(ops->owner);
+}
+EXPORT_SYMBOL(lwtstate_free);
+
 int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *ops,
 			   unsigned int num)
 {
@@ -111,8 +120,11 @@ int lwtunnel_build_state(struct net_device *dev, u16 encap_type,
 	ret = -EOPNOTSUPP;
 	rcu_read_lock();
 	ops = rcu_dereference(lwtun_encaps[encap_type]);
-	if (likely(ops && ops->build_state))
+	if (likely(ops && ops->build_state && try_module_get(ops->owner))) {
 		ret = ops->build_state(dev, encap, family, cfg, lws);
+		if (ret)
+			module_put(ops->owner);
+	}
 	rcu_read_unlock();
 
 	return ret;
-- 
2.4.11


From e341d8db9e449f6268a6dfd99eabc55bbf4c1908 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 25 Jan 2017 09:10:41 -0800
Subject: [PATCH 32/32] net: dsa: Bring back device detaching in
 dsa_slave_suspend()

[ Upstream commit f154be241d22298d2b63c9b613f619fa1086ea75 ]

Commit 448b4482c671 ("net: dsa: Add lockdep class to tx queues to avoid
lockdep splat") removed the netif_device_detach() call done in
dsa_slave_suspend() which is necessary, and paired with a corresponding
netif_device_attach(), bring it back.

Fixes: 448b4482c671 ("net: dsa: Add lockdep class to tx queues to avoid lockdep splat")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/slave.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 30e2e21..3ff9d97 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -1201,6 +1201,8 @@ int dsa_slave_suspend(struct net_device *slave_dev)
 {
 	struct dsa_slave_priv *p = netdev_priv(slave_dev);
 
+	netif_device_detach(slave_dev);
+
 	if (p->phy) {
 		phy_stop(p->phy);
 		p->old_pause = -1;
-- 
2.4.11

Re: [PATCHES] networking

[Greg KH]

On Tue, Jan 31, 2017 at 04:50:51PM -0500, David Miller wrote:
> 
> Please queue up the following networking bug fixes for 4.4.x and
> 4.9.x -stable, respectively.

Many thanks for these, all now queued up.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 102 bytes --]


Please queue up the following networking bug fixes for v4.4 and v4.9
-stable, respectively.

Thanks!

[-- Attachment #2: net_44.mbox --]
[-- Type: Application/Octet-Stream, Size: 57820 bytes --]

From c18c389eacbfad277c089fc69fe02e6be902ef74 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 27 Jan 2017 08:11:44 -0800
Subject: [PATCH 01/20] can: Fix kernel panic at security_sock_rcv_skb

[ Upstream commit f1712c73714088a7252d276a57126d56c7d37e64 ]

Zhang Yanmin reported crashes [1] and provided a patch adding a
synchronize_rcu() call in can_rx_unregister()

The main problem seems that the sockets themselves are not RCU
protected.

If CAN uses RCU for delivery, then sockets should be freed only after
one RCU grace period.

Recent kernels could use sock_set_flag(sk, SOCK_RCU_FREE), but let's
ease stable backports with the following fix instead.

[1]
BUG: unable to handle kernel NULL pointer dereference at (null)
IP: [<ffffffff81495e25>] selinux_socket_sock_rcv_skb+0x65/0x2a0

Call Trace:
 <IRQ>
 [<ffffffff81485d8c>] security_sock_rcv_skb+0x4c/0x60
 [<ffffffff81d55771>] sk_filter+0x41/0x210
 [<ffffffff81d12913>] sock_queue_rcv_skb+0x53/0x3a0
 [<ffffffff81f0a2b3>] raw_rcv+0x2a3/0x3c0
 [<ffffffff81f06eab>] can_rcv_filter+0x12b/0x370
 [<ffffffff81f07af9>] can_receive+0xd9/0x120
 [<ffffffff81f07beb>] can_rcv+0xab/0x100
 [<ffffffff81d362ac>] __netif_receive_skb_core+0xd8c/0x11f0
 [<ffffffff81d36734>] __netif_receive_skb+0x24/0xb0
 [<ffffffff81d37f67>] process_backlog+0x127/0x280
 [<ffffffff81d36f7b>] net_rx_action+0x33b/0x4f0
 [<ffffffff810c88d4>] __do_softirq+0x184/0x440
 [<ffffffff81f9e86c>] do_softirq_own_stack+0x1c/0x30
 <EOI>
 [<ffffffff810c76fb>] do_softirq.part.18+0x3b/0x40
 [<ffffffff810c8bed>] do_softirq+0x1d/0x20
 [<ffffffff81d30085>] netif_rx_ni+0xe5/0x110
 [<ffffffff8199cc87>] slcan_receive_buf+0x507/0x520
 [<ffffffff8167ef7c>] flush_to_ldisc+0x21c/0x230
 [<ffffffff810e3baf>] process_one_work+0x24f/0x670
 [<ffffffff810e44ed>] worker_thread+0x9d/0x6f0
 [<ffffffff810e4450>] ? rescuer_thread+0x480/0x480
 [<ffffffff810ebafc>] kthread+0x12c/0x150
 [<ffffffff81f9ccef>] ret_from_fork+0x3f/0x70

Reported-by: Zhang Yanmin <yanmin.zhang@intel.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/can/core.h |  7 +++----
 net/can/af_can.c         | 12 ++++++++++--
 net/can/af_can.h         |  3 ++-
 net/can/bcm.c            |  4 ++--
 net/can/gw.c             |  2 +-
 net/can/raw.c            |  4 ++--
 6 files changed, 20 insertions(+), 12 deletions(-)

diff --git a/include/linux/can/core.h b/include/linux/can/core.h
index a087500..df08a41 100644
--- a/include/linux/can/core.h
+++ b/include/linux/can/core.h
@@ -45,10 +45,9 @@ struct can_proto {
 extern int  can_proto_register(const struct can_proto *cp);
 extern void can_proto_unregister(const struct can_proto *cp);
 
-extern int  can_rx_register(struct net_device *dev, canid_t can_id,
-			    canid_t mask,
-			    void (*func)(struct sk_buff *, void *),
-			    void *data, char *ident);
+int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask,
+		    void (*func)(struct sk_buff *, void *),
+		    void *data, char *ident, struct sock *sk);
 
 extern void can_rx_unregister(struct net_device *dev, canid_t can_id,
 			      canid_t mask,
diff --git a/net/can/af_can.c b/net/can/af_can.c
index 166d436..928f580 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -445,6 +445,7 @@ static struct hlist_head *find_rcv_list(canid_t *can_id, canid_t *mask,
  * @func: callback function on filter match
  * @data: returned parameter for callback function
  * @ident: string for calling module identification
+ * @sk: socket pointer (might be NULL)
  *
  * Description:
  *  Invokes the callback function with the received sk_buff and the given
@@ -468,7 +469,7 @@ static struct hlist_head *find_rcv_list(canid_t *can_id, canid_t *mask,
  */
 int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask,
 		    void (*func)(struct sk_buff *, void *), void *data,
-		    char *ident)
+		    char *ident, struct sock *sk)
 {
 	struct receiver *r;
 	struct hlist_head *rl;
@@ -496,6 +497,7 @@ int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask,
 		r->func    = func;
 		r->data    = data;
 		r->ident   = ident;
+		r->sk      = sk;
 
 		hlist_add_head_rcu(&r->list, rl);
 		d->entries++;
@@ -520,8 +522,11 @@ EXPORT_SYMBOL(can_rx_register);
 static void can_rx_delete_receiver(struct rcu_head *rp)
 {
 	struct receiver *r = container_of(rp, struct receiver, rcu);
+	struct sock *sk = r->sk;
 
 	kmem_cache_free(rcv_cache, r);
+	if (sk)
+		sock_put(sk);
 }
 
 /**
@@ -596,8 +601,11 @@ void can_rx_unregister(struct net_device *dev, canid_t can_id, canid_t mask,
 	spin_unlock(&can_rcvlists_lock);
 
 	/* schedule the receiver item for deletion */
-	if (r)
+	if (r) {
+		if (r->sk)
+			sock_hold(r->sk);
 		call_rcu(&r->rcu, can_rx_delete_receiver);
+	}
 }
 EXPORT_SYMBOL(can_rx_unregister);
 
diff --git a/net/can/af_can.h b/net/can/af_can.h
index fca0fe9..b86f512 100644
--- a/net/can/af_can.h
+++ b/net/can/af_can.h
@@ -50,13 +50,14 @@
 
 struct receiver {
 	struct hlist_node list;
-	struct rcu_head rcu;
 	canid_t can_id;
 	canid_t mask;
 	unsigned long matches;
 	void (*func)(struct sk_buff *, void *);
 	void *data;
 	char *ident;
+	struct sock *sk;
+	struct rcu_head rcu;
 };
 
 #define CAN_SFF_RCV_ARRAY_SZ (1 << CAN_SFF_ID_BITS)
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 24d66c1..4ccfd35 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -1179,7 +1179,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 				err = can_rx_register(dev, op->can_id,
 						      REGMASK(op->can_id),
 						      bcm_rx_handler, op,
-						      "bcm");
+						      "bcm", sk);
 
 				op->rx_reg_dev = dev;
 				dev_put(dev);
@@ -1188,7 +1188,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		} else
 			err = can_rx_register(NULL, op->can_id,
 					      REGMASK(op->can_id),
-					      bcm_rx_handler, op, "bcm");
+					      bcm_rx_handler, op, "bcm", sk);
 		if (err) {
 			/* this bcm rx op is broken -> remove it */
 			list_del(&op->list);
diff --git a/net/can/gw.c b/net/can/gw.c
index 4551687..77c8af4 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -442,7 +442,7 @@ static inline int cgw_register_filter(struct cgw_job *gwj)
 {
 	return can_rx_register(gwj->src.dev, gwj->ccgw.filter.can_id,
 			       gwj->ccgw.filter.can_mask, can_can_gw_rcv,
-			       gwj, "gw");
+			       gwj, "gw", NULL);
 }
 
 static inline void cgw_unregister_filter(struct cgw_job *gwj)
diff --git a/net/can/raw.c b/net/can/raw.c
index 56af689..e9403a2 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -190,7 +190,7 @@ static int raw_enable_filters(struct net_device *dev, struct sock *sk,
 	for (i = 0; i < count; i++) {
 		err = can_rx_register(dev, filter[i].can_id,
 				      filter[i].can_mask,
-				      raw_rcv, sk, "raw");
+				      raw_rcv, sk, "raw", sk);
 		if (err) {
 			/* clean up successfully registered filters */
 			while (--i >= 0)
@@ -211,7 +211,7 @@ static int raw_enable_errfilter(struct net_device *dev, struct sock *sk,
 
 	if (err_mask)
 		err = can_rx_register(dev, 0, err_mask | CAN_ERR_FLAG,
-				      raw_rcv, sk, "raw");
+				      raw_rcv, sk, "raw", sk);
 
 	return err;
 }
-- 
2.4.11


From 0deca4f4eb86f212a609d592f91ec6673acb8b1e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 23 Jan 2017 16:43:06 -0800
Subject: [PATCH 02/20] ipv6: fix ip6_tnl_parse_tlv_enc_lim()

[ Upstream commit fbfa743a9d2a0ffa24251764f10afc13eb21e739 ]

This function suffers from multiple issues.

First one is that pskb_may_pull() may reallocate skb->head,
so the 'raw' pointer needs either to be reloaded or not used at all.

Second issue is that NEXTHDR_DEST handling does not validate
that the options are present in skb->data, so we might read
garbage or access non existent memory.

With help from Willem de Bruijn.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov  <dvyukov@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 34 ++++++++++++++++++++++------------
 1 file changed, 22 insertions(+), 12 deletions(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 2994d1f..3fed666 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -479,18 +479,19 @@ ip6_tnl_dev_uninit(struct net_device *dev)
 
 __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw)
 {
-	const struct ipv6hdr *ipv6h = (const struct ipv6hdr *) raw;
-	__u8 nexthdr = ipv6h->nexthdr;
-	__u16 off = sizeof(*ipv6h);
+	const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)raw;
+	unsigned int nhoff = raw - skb->data;
+	unsigned int off = nhoff + sizeof(*ipv6h);
+	u8 next, nexthdr = ipv6h->nexthdr;
 
 	while (ipv6_ext_hdr(nexthdr) && nexthdr != NEXTHDR_NONE) {
-		__u16 optlen = 0;
 		struct ipv6_opt_hdr *hdr;
-		if (raw + off + sizeof(*hdr) > skb->data &&
-		    !pskb_may_pull(skb, raw - skb->data + off + sizeof (*hdr)))
+		u16 optlen;
+
+		if (!pskb_may_pull(skb, off + sizeof(*hdr)))
 			break;
 
-		hdr = (struct ipv6_opt_hdr *) (raw + off);
+		hdr = (struct ipv6_opt_hdr *)(skb->data + off);
 		if (nexthdr == NEXTHDR_FRAGMENT) {
 			struct frag_hdr *frag_hdr = (struct frag_hdr *) hdr;
 			if (frag_hdr->frag_off)
@@ -501,20 +502,29 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw)
 		} else {
 			optlen = ipv6_optlen(hdr);
 		}
+		/* cache hdr->nexthdr, since pskb_may_pull() might
+		 * invalidate hdr
+		 */
+		next = hdr->nexthdr;
 		if (nexthdr == NEXTHDR_DEST) {
-			__u16 i = off + 2;
+			u16 i = 2;
+
+			/* Remember : hdr is no longer valid at this point. */
+			if (!pskb_may_pull(skb, off + optlen))
+				break;
+
 			while (1) {
 				struct ipv6_tlv_tnl_enc_lim *tel;
 
 				/* No more room for encapsulation limit */
-				if (i + sizeof (*tel) > off + optlen)
+				if (i + sizeof(*tel) > optlen)
 					break;
 
-				tel = (struct ipv6_tlv_tnl_enc_lim *) &raw[i];
+				tel = (struct ipv6_tlv_tnl_enc_lim *) skb->data + off + i;
 				/* return index of option if found and valid */
 				if (tel->type == IPV6_TLV_TNL_ENCAP_LIMIT &&
 				    tel->length == 1)
-					return i;
+					return i + off - nhoff;
 				/* else jump to next option */
 				if (tel->type)
 					i += tel->length + 2;
@@ -522,7 +532,7 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw)
 					i++;
 			}
 		}
-		nexthdr = hdr->nexthdr;
+		nexthdr = next;
 		off += optlen;
 	}
 	return 0;
-- 
2.4.11


From 621d8bf478c7d4e88929bbdcd98f98c5bb0ad061 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 1 Feb 2017 11:46:32 +0300
Subject: [PATCH 03/20] ipv6: pointer math error in ip6_tnl_parse_tlv_enc_lim()

[ Upstream commit 63117f09c768be05a0bf465911297dc76394f686 ]

Casting is a high precedence operation but "off" and "i" are in terms of
bytes so we need to have some parenthesis here.

Fixes: fbfa743a9d2a ("ipv6: fix ip6_tnl_parse_tlv_enc_lim()")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 3fed666..6c61617 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -520,7 +520,7 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw)
 				if (i + sizeof(*tel) > optlen)
 					break;
 
-				tel = (struct ipv6_tlv_tnl_enc_lim *) skb->data + off + i;
+				tel = (struct ipv6_tlv_tnl_enc_lim *)(skb->data + off + i);
 				/* return index of option if found and valid */
 				if (tel->type == IPV6_TLV_TNL_ENCAP_LIMIT &&
 				    tel->length == 1)
-- 
2.4.11


From 83334f05d016d4aad705775a8891d8dfad0052a3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 1 Feb 2017 08:33:53 -0800
Subject: [PATCH 04/20] tcp: fix 0 divide in __tcp_select_window()

[ Upstream commit 06425c308b92eaf60767bc71d359f4cbc7a561f8 ]

syszkaller fuzzer was able to trigger a divide by zero, when
TCP window scaling is not enabled.

SO_RCVBUF can be used not only to increase sk_rcvbuf, also
to decrease it below current receive buffers utilization.

If mss is negative or 0, just return a zero TCP window.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov  <dvyukov@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 0795647..de95714 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2383,9 +2383,11 @@ u32 __tcp_select_window(struct sock *sk)
 	int full_space = min_t(int, tp->window_clamp, allowed_space);
 	int window;
 
-	if (mss > full_space)
+	if (unlikely(mss > full_space)) {
 		mss = full_space;
-
+		if (mss <= 0)
+			return 0;
+	}
 	if (free_space < (full_space >> 1)) {
 		icsk->icsk_ack.quick = 0;
 
-- 
2.4.11


From 4c0304800ccfde329266fcc6112bf363e15a55ac Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 2 Feb 2017 10:31:35 -0800
Subject: [PATCH 05/20] net: use a work queue to defer net_disable_timestamp()
 work

[ Upstream commit 5fa8bbda38c668e56b0c6cdecced2eac2fe36dec ]

Dmitry reported a warning [1] showing that we were calling
net_disable_timestamp() -> static_key_slow_dec() from a non
process context.

Grabbing a mutex while holding a spinlock or rcu_read_lock()
is not allowed.

As Cong suggested, we now use a work queue.

It is possible netstamp_clear() exits while netstamp_needed_deferred
is not zero, but it is probably not worth trying to do better than that.

netstamp_needed_deferred atomic tracks the exact number of deferred
decrements.

[1]
[ INFO: suspicious RCU usage. ]
4.10.0-rc5+ #192 Not tainted
-------------------------------
./include/linux/rcupdate.h:561 Illegal context switch in RCU read-side
critical section!

other info that might help us debug this:

rcu_scheduler_active = 2, debug_locks = 0
2 locks held by syz-executor14/23111:
 #0:  (sk_lock-AF_INET6){+.+.+.}, at: [<ffffffff83a35c35>] lock_sock
include/net/sock.h:1454 [inline]
 #0:  (sk_lock-AF_INET6){+.+.+.}, at: [<ffffffff83a35c35>]
rawv6_sendmsg+0x1e65/0x3ec0 net/ipv6/raw.c:919
 #1:  (rcu_read_lock){......}, at: [<ffffffff83ae2678>] nf_hook
include/linux/netfilter.h:201 [inline]
 #1:  (rcu_read_lock){......}, at: [<ffffffff83ae2678>]
__ip6_local_out+0x258/0x840 net/ipv6/output_core.c:160

stack backtrace:
CPU: 2 PID: 23111 Comm: syz-executor14 Not tainted 4.10.0-rc5+ #192
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs
01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:15 [inline]
 dump_stack+0x2ee/0x3ef lib/dump_stack.c:51
 lockdep_rcu_suspicious+0x139/0x180 kernel/locking/lockdep.c:4452
 rcu_preempt_sleep_check include/linux/rcupdate.h:560 [inline]
 ___might_sleep+0x560/0x650 kernel/sched/core.c:7748
 __might_sleep+0x95/0x1a0 kernel/sched/core.c:7739
 mutex_lock_nested+0x24f/0x1730 kernel/locking/mutex.c:752
 atomic_dec_and_mutex_lock+0x119/0x160 kernel/locking/mutex.c:1060
 __static_key_slow_dec+0x7a/0x1e0 kernel/jump_label.c:149
 static_key_slow_dec+0x51/0x90 kernel/jump_label.c:174
 net_disable_timestamp+0x3b/0x50 net/core/dev.c:1728
 sock_disable_timestamp+0x98/0xc0 net/core/sock.c:403
 __sk_destruct+0x27d/0x6b0 net/core/sock.c:1441
 sk_destruct+0x47/0x80 net/core/sock.c:1460
 __sk_free+0x57/0x230 net/core/sock.c:1468
 sock_wfree+0xae/0x120 net/core/sock.c:1645
 skb_release_head_state+0xfc/0x200 net/core/skbuff.c:655
 skb_release_all+0x15/0x60 net/core/skbuff.c:668
 __kfree_skb+0x15/0x20 net/core/skbuff.c:684
 kfree_skb+0x16e/0x4c0 net/core/skbuff.c:705
 inet_frag_destroy+0x121/0x290 net/ipv4/inet_fragment.c:304
 inet_frag_put include/net/inet_frag.h:133 [inline]
 nf_ct_frag6_gather+0x1106/0x3840
net/ipv6/netfilter/nf_conntrack_reasm.c:617
 ipv6_defrag+0x1be/0x2b0 net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:68
 nf_hook_entry_hookfn include/linux/netfilter.h:102 [inline]
 nf_hook_slow+0xc3/0x290 net/netfilter/core.c:310
 nf_hook include/linux/netfilter.h:212 [inline]
 __ip6_local_out+0x489/0x840 net/ipv6/output_core.c:160
 ip6_local_out+0x2d/0x170 net/ipv6/output_core.c:170
 ip6_send_skb+0xa1/0x340 net/ipv6/ip6_output.c:1722
 ip6_push_pending_frames+0xb3/0xe0 net/ipv6/ip6_output.c:1742
 rawv6_push_pending_frames net/ipv6/raw.c:613 [inline]
 rawv6_sendmsg+0x2d1a/0x3ec0 net/ipv6/raw.c:927
 inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:744
 sock_sendmsg_nosec net/socket.c:635 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:645
 sock_write_iter+0x326/0x600 net/socket.c:848
 do_iter_readv_writev+0x2e3/0x5b0 fs/read_write.c:695
 do_readv_writev+0x42c/0x9b0 fs/read_write.c:872
 vfs_writev+0x87/0xc0 fs/read_write.c:911
 do_writev+0x110/0x2c0 fs/read_write.c:944
 SYSC_writev fs/read_write.c:1017 [inline]
 SyS_writev+0x27/0x30 fs/read_write.c:1014
 entry_SYSCALL_64_fastpath+0x1f/0xc2
RIP: 0033:0x445559
RSP: 002b:00007f6f46fceb58 EFLAGS: 00000292 ORIG_RAX: 0000000000000014
RAX: ffffffffffffffda RBX: 0000000000000005 RCX: 0000000000445559
RDX: 0000000000000001 RSI: 0000000020f1eff0 RDI: 0000000000000005
RBP: 00000000006e19c0 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000292 R12: 0000000000700000
R13: 0000000020f59000 R14: 0000000000000015 R15: 0000000000020400
BUG: sleeping function called from invalid context at
kernel/locking/mutex.c:752
in_atomic(): 1, irqs_disabled(): 0, pid: 23111, name: syz-executor14
INFO: lockdep is turned off.
CPU: 2 PID: 23111 Comm: syz-executor14 Not tainted 4.10.0-rc5+ #192
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs
01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:15 [inline]
 dump_stack+0x2ee/0x3ef lib/dump_stack.c:51
 ___might_sleep+0x47e/0x650 kernel/sched/core.c:7780
 __might_sleep+0x95/0x1a0 kernel/sched/core.c:7739
 mutex_lock_nested+0x24f/0x1730 kernel/locking/mutex.c:752
 atomic_dec_and_mutex_lock+0x119/0x160 kernel/locking/mutex.c:1060
 __static_key_slow_dec+0x7a/0x1e0 kernel/jump_label.c:149
 static_key_slow_dec+0x51/0x90 kernel/jump_label.c:174
 net_disable_timestamp+0x3b/0x50 net/core/dev.c:1728
 sock_disable_timestamp+0x98/0xc0 net/core/sock.c:403
 __sk_destruct+0x27d/0x6b0 net/core/sock.c:1441
 sk_destruct+0x47/0x80 net/core/sock.c:1460
 __sk_free+0x57/0x230 net/core/sock.c:1468
 sock_wfree+0xae/0x120 net/core/sock.c:1645
 skb_release_head_state+0xfc/0x200 net/core/skbuff.c:655
 skb_release_all+0x15/0x60 net/core/skbuff.c:668
 __kfree_skb+0x15/0x20 net/core/skbuff.c:684
 kfree_skb+0x16e/0x4c0 net/core/skbuff.c:705
 inet_frag_destroy+0x121/0x290 net/ipv4/inet_fragment.c:304
 inet_frag_put include/net/inet_frag.h:133 [inline]
 nf_ct_frag6_gather+0x1106/0x3840
net/ipv6/netfilter/nf_conntrack_reasm.c:617
 ipv6_defrag+0x1be/0x2b0 net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:68
 nf_hook_entry_hookfn include/linux/netfilter.h:102 [inline]
 nf_hook_slow+0xc3/0x290 net/netfilter/core.c:310
 nf_hook include/linux/netfilter.h:212 [inline]
 __ip6_local_out+0x489/0x840 net/ipv6/output_core.c:160
 ip6_local_out+0x2d/0x170 net/ipv6/output_core.c:170
 ip6_send_skb+0xa1/0x340 net/ipv6/ip6_output.c:1722
 ip6_push_pending_frames+0xb3/0xe0 net/ipv6/ip6_output.c:1742
 rawv6_push_pending_frames net/ipv6/raw.c:613 [inline]
 rawv6_sendmsg+0x2d1a/0x3ec0 net/ipv6/raw.c:927
 inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:744
 sock_sendmsg_nosec net/socket.c:635 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:645
 sock_write_iter+0x326/0x600 net/socket.c:848
 do_iter_readv_writev+0x2e3/0x5b0 fs/read_write.c:695
 do_readv_writev+0x42c/0x9b0 fs/read_write.c:872
 vfs_writev+0x87/0xc0 fs/read_write.c:911
 do_writev+0x110/0x2c0 fs/read_write.c:944
 SYSC_writev fs/read_write.c:1017 [inline]
 SyS_writev+0x27/0x30 fs/read_write.c:1014
 entry_SYSCALL_64_fastpath+0x1f/0xc2
RIP: 0033:0x445559

Fixes: b90e5794c5bd ("net: dont call jump_label_dec from irq context")
Suggested-by: Cong Wang <xiyou.wangcong@gmail.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 31 +++++++++++++------------------
 1 file changed, 13 insertions(+), 18 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 0798a0f..08215a8 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1676,24 +1676,19 @@ EXPORT_SYMBOL_GPL(net_dec_ingress_queue);
 
 static struct static_key netstamp_needed __read_mostly;
 #ifdef HAVE_JUMP_LABEL
-/* We are not allowed to call static_key_slow_dec() from irq context
- * If net_disable_timestamp() is called from irq context, defer the
- * static_key_slow_dec() calls.
- */
 static atomic_t netstamp_needed_deferred;
-#endif
-
-void net_enable_timestamp(void)
+static void netstamp_clear(struct work_struct *work)
 {
-#ifdef HAVE_JUMP_LABEL
 	int deferred = atomic_xchg(&netstamp_needed_deferred, 0);
 
-	if (deferred) {
-		while (--deferred)
-			static_key_slow_dec(&netstamp_needed);
-		return;
-	}
+	while (deferred--)
+		static_key_slow_dec(&netstamp_needed);
+}
+static DECLARE_WORK(netstamp_work, netstamp_clear);
 #endif
+
+void net_enable_timestamp(void)
+{
 	static_key_slow_inc(&netstamp_needed);
 }
 EXPORT_SYMBOL(net_enable_timestamp);
@@ -1701,12 +1696,12 @@ EXPORT_SYMBOL(net_enable_timestamp);
 void net_disable_timestamp(void)
 {
 #ifdef HAVE_JUMP_LABEL
-	if (in_interrupt()) {
-		atomic_inc(&netstamp_needed_deferred);
-		return;
-	}
-#endif
+	/* net_disable_timestamp() can be called from non process context */
+	atomic_inc(&netstamp_needed_deferred);
+	schedule_work(&netstamp_work);
+#else
 	static_key_slow_dec(&netstamp_needed);
+#endif
 }
 EXPORT_SYMBOL(net_disable_timestamp);
 
-- 
2.4.11


From 359f9c6bb5ecb5bb85bee08d67c05176826f07a0 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 4 Feb 2017 11:16:52 -0800
Subject: [PATCH 06/20] ipv4: keep skb->dst around in presence of IP options

[ Upstream commit 34b2cef20f19c87999fff3da4071e66937db9644 ]

Andrey Konovalov got crashes in __ip_options_echo() when a NULL skb->dst
is accessed.

ipv4_pktinfo_prepare() should not drop the dst if (evil) IP options
are present.

We could refine the test to the presence of ts_needtime or srr,
but IP options are not often used, so let's be conservative.

Thanks to syzkaller team for finding this bug.

Fixes: d826eb14ecef ("ipv4: PKTINFO doesnt need dst reference")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_sockglue.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 9ce2025..bc14c5b 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1192,7 +1192,14 @@ void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb)
 		pktinfo->ipi_ifindex = 0;
 		pktinfo->ipi_spec_dst.s_addr = 0;
 	}
-	skb_dst_drop(skb);
+	/* We need to keep the dst for __ip_options_echo()
+	 * We could restrict the test to opt.ts_needtime || opt.srr,
+	 * but the following is good enough as IP options are not often used.
+	 */
+	if (unlikely(IPCB(skb)->opt.optlen))
+		skb_dst_force(skb);
+	else
+		skb_dst_drop(skb);
 }
 
 int ip_setsockopt(struct sock *sk, int level,
-- 
2.4.11


From 30454f1ddd89251cd693802d278c90138e9e9766 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 3 Feb 2017 00:03:26 -0800
Subject: [PATCH 07/20] netlabel: out of bound access in cipso_v4_validate()

[ Upstream commit d71b7896886345c53ef1d84bda2bc758554f5d61 ]

syzkaller found another out of bound access in ip_options_compile(),
or more exactly in cipso_v4_validate()

Fixes: 20e2a8648596 ("cipso: handle CIPSO options correctly when NetLabel is disabled")
Fixes: 446fda4f2682 ("[NetLabel]: CIPSOv4 engine")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov  <dvyukov@google.com>
Cc: Paul Moore <paul@paul-moore.com>
Acked-by: Paul Moore <paul@paul-moore.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/cipso_ipv4.h | 4 ++++
 net/ipv4/cipso_ipv4.c    | 4 ++++
 2 files changed, 8 insertions(+)

diff --git a/include/net/cipso_ipv4.h b/include/net/cipso_ipv4.h
index 3ebb168..a34b141 100644
--- a/include/net/cipso_ipv4.h
+++ b/include/net/cipso_ipv4.h
@@ -309,6 +309,10 @@ static inline int cipso_v4_validate(const struct sk_buff *skb,
 	}
 
 	for (opt_iter = 6; opt_iter < opt_len;) {
+		if (opt_iter + 1 == opt_len) {
+			err_offset = opt_iter;
+			goto out;
+		}
 		tag_len = opt[opt_iter + 1];
 		if ((tag_len == 0) || (tag_len > (opt_len - opt_iter))) {
 			err_offset = opt_iter + 1;
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index bdb2a07..6cc3e1d 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -1657,6 +1657,10 @@ int cipso_v4_validate(const struct sk_buff *skb, unsigned char **option)
 				goto validate_return_locked;
 			}
 
+		if (opt_iter + 1 == opt_len) {
+			err_offset = opt_iter;
+			goto validate_return_locked;
+		}
 		tag_len = tag[1];
 		if (tag_len > (opt_len - opt_iter)) {
 			err_offset = opt_iter + 1;
-- 
2.4.11


From 3c3cd9658e05c5c02d653987f44ba63f49a17be7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 4 Feb 2017 23:18:55 -0800
Subject: [PATCH 08/20] ip6_gre: fix ip6gre_err() invalid reads

[ Upstream commit 7892032cfe67f4bde6fc2ee967e45a8fbaf33756 ]

Andrey Konovalov reported out of bound accesses in ip6gre_err()

If GRE flags contains GRE_KEY, the following expression
*(((__be32 *)p) + (grehlen / 4) - 1)

accesses data ~40 bytes after the expected point, since
grehlen includes the size of IPv6 headers.

Let's use a "struct gre_base_hdr *greh" pointer to make this
code more readable.

p[1] becomes greh->protocol.
grhlen is the GRE header length.

Fixes: c12b395a4664 ("gre: Support GRE over IPv6")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 41 ++++++++++++++++++++++-------------------
 1 file changed, 22 insertions(+), 19 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 17430f3..e891358 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -55,6 +55,7 @@
 #include <net/ip6_fib.h>
 #include <net/ip6_route.h>
 #include <net/ip6_tunnel.h>
+#include <net/gre.h>
 
 
 static bool log_ecn_error = true;
@@ -367,35 +368,37 @@ static void ip6gre_tunnel_uninit(struct net_device *dev)
 
 
 static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
-		u8 type, u8 code, int offset, __be32 info)
+		       u8 type, u8 code, int offset, __be32 info)
 {
-	const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)skb->data;
-	__be16 *p = (__be16 *)(skb->data + offset);
-	int grehlen = offset + 4;
+	const struct gre_base_hdr *greh;
+	const struct ipv6hdr *ipv6h;
+	int grehlen = sizeof(*greh);
 	struct ip6_tnl *t;
+	int key_off = 0;
 	__be16 flags;
+	__be32 key;
 
-	flags = p[0];
-	if (flags&(GRE_CSUM|GRE_KEY|GRE_SEQ|GRE_ROUTING|GRE_VERSION)) {
-		if (flags&(GRE_VERSION|GRE_ROUTING))
-			return;
-		if (flags&GRE_KEY) {
-			grehlen += 4;
-			if (flags&GRE_CSUM)
-				grehlen += 4;
-		}
+	if (!pskb_may_pull(skb, offset + grehlen))
+		return;
+	greh = (const struct gre_base_hdr *)(skb->data + offset);
+	flags = greh->flags;
+	if (flags & (GRE_VERSION | GRE_ROUTING))
+		return;
+	if (flags & GRE_CSUM)
+		grehlen += 4;
+	if (flags & GRE_KEY) {
+		key_off = grehlen + offset;
+		grehlen += 4;
 	}
 
-	/* If only 8 bytes returned, keyed message will be dropped here */
-	if (!pskb_may_pull(skb, grehlen))
+	if (!pskb_may_pull(skb, offset + grehlen))
 		return;
 	ipv6h = (const struct ipv6hdr *)skb->data;
-	p = (__be16 *)(skb->data + offset);
+	greh = (const struct gre_base_hdr *)(skb->data + offset);
+	key = key_off ? *(__be32 *)(skb->data + key_off) : 0;
 
 	t = ip6gre_tunnel_lookup(skb->dev, &ipv6h->daddr, &ipv6h->saddr,
-				flags & GRE_KEY ?
-				*(((__be32 *)p) + (grehlen / 4) - 1) : 0,
-				p[1]);
+				 key, greh->protocol);
 	if (!t)
 		return;
 
-- 
2.4.11


From 732776fb63009f6a0c2e46a39750578002b1b21a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 5 Feb 2017 20:23:22 -0800
Subject: [PATCH 09/20] ipv6: tcp: add a missing tcp_v6_restore_cb()

[ Upstream commit ebf6c9cb23d7e56eec8575a88071dec97ad5c6e2 ]

Dmitry reported use-after-free in ip6_datagram_recv_specific_ctl()

A similar bug was fixed in commit 8ce48623f0cf ("ipv6: tcp: restore
IP6CB for pktoptions skbs"), but I missed another spot.

tcp_v6_syn_recv_sock() can indeed set np->pktoptions from ireq->pktopts

Fixes: 971f10eca186 ("tcp: better TCP_SKB_CB layout to reduce cache line misses")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/tcp_ipv6.c | 24 +++++++++++++-----------
 1 file changed, 13 insertions(+), 11 deletions(-)

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 5f58161..76a8c80 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -974,6 +974,16 @@ drop:
 	return 0; /* don't send reset */
 }
 
+static void tcp_v6_restore_cb(struct sk_buff *skb)
+{
+	/* We need to move header back to the beginning if xfrm6_policy_check()
+	 * and tcp_v6_fill_cb() are going to be called again.
+	 * ip6_datagram_recv_specific_ctl() also expects IP6CB to be there.
+	 */
+	memmove(IP6CB(skb), &TCP_SKB_CB(skb)->header.h6,
+		sizeof(struct inet6_skb_parm));
+}
+
 static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 					 struct request_sock *req,
 					 struct dst_entry *dst,
@@ -1163,8 +1173,10 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 						      sk_gfp_atomic(sk, GFP_ATOMIC));
 			consume_skb(ireq->pktopts);
 			ireq->pktopts = NULL;
-			if (newnp->pktoptions)
+			if (newnp->pktoptions) {
+				tcp_v6_restore_cb(newnp->pktoptions);
 				skb_set_owner_r(newnp->pktoptions, newsk);
+			}
 		}
 	}
 
@@ -1179,16 +1191,6 @@ out:
 	return NULL;
 }
 
-static void tcp_v6_restore_cb(struct sk_buff *skb)
-{
-	/* We need to move header back to the beginning if xfrm6_policy_check()
-	 * and tcp_v6_fill_cb() are going to be called again.
-	 * ip6_datagram_recv_specific_ctl() also expects IP6CB to be there.
-	 */
-	memmove(IP6CB(skb), &TCP_SKB_CB(skb)->header.h6,
-		sizeof(struct inet6_skb_parm));
-}
-
 /* The socket must have it's spinlock held when we get
  * here, unless it is a TCP_LISTEN socket.
  *
-- 
2.4.11


From 95b65ece7ba0fcbdb187e9c06cbe539c6c20717d Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 3 Feb 2017 17:35:46 +0100
Subject: [PATCH 10/20] hns: avoid stack overflow with CONFIG_KASAN

[ Upstream commit b3f2d07f4649adcf6905953a10d217b5683e4077 ]

The use of ACCESS_ONCE() looks like a micro-optimization to force gcc to use
an indexed load for the register address, but it has an absolutely detrimental
effect on builds with gcc-5 and CONFIG_KASAN=y, leading to a very likely
kernel stack overflow aside from very complex object code:

hisilicon/hns/hns_dsaf_gmac.c: In function 'hns_gmac_update_stats':
hisilicon/hns/hns_dsaf_gmac.c:419:1: error: the frame size of 2912 bytes is larger than 1024 bytes [-Werror=frame-larger-than=]
hisilicon/hns/hns_dsaf_ppe.c: In function 'hns_ppe_reset_common':
hisilicon/hns/hns_dsaf_ppe.c:390:1: error: the frame size of 1184 bytes is larger than 1024 bytes [-Werror=frame-larger-than=]
hisilicon/hns/hns_dsaf_ppe.c: In function 'hns_ppe_get_regs':
hisilicon/hns/hns_dsaf_ppe.c:621:1: error: the frame size of 3632 bytes is larger than 1024 bytes [-Werror=frame-larger-than=]
hisilicon/hns/hns_dsaf_rcb.c: In function 'hns_rcb_get_common_regs':
hisilicon/hns/hns_dsaf_rcb.c:970:1: error: the frame size of 2784 bytes is larger than 1024 bytes [-Werror=frame-larger-than=]
hisilicon/hns/hns_dsaf_gmac.c: In function 'hns_gmac_get_regs':
hisilicon/hns/hns_dsaf_gmac.c:641:1: error: the frame size of 5728 bytes is larger than 1024 bytes [-Werror=frame-larger-than=]
hisilicon/hns/hns_dsaf_rcb.c: In function 'hns_rcb_get_ring_regs':
hisilicon/hns/hns_dsaf_rcb.c:1021:1: error: the frame size of 2208 bytes is larger than 1024 bytes [-Werror=frame-larger-than=]
hisilicon/hns/hns_dsaf_main.c: In function 'hns_dsaf_comm_init':
hisilicon/hns/hns_dsaf_main.c:1209:1: error: the frame size of 1904 bytes is larger than 1024 bytes [-Werror=frame-larger-than=]
hisilicon/hns/hns_dsaf_xgmac.c: In function 'hns_xgmac_get_regs':
hisilicon/hns/hns_dsaf_xgmac.c:748:1: error: the frame size of 4704 bytes is larger than 1024 bytes [-Werror=frame-larger-than=]
hisilicon/hns/hns_dsaf_main.c: In function 'hns_dsaf_update_stats':
hisilicon/hns/hns_dsaf_main.c:2420:1: error: the frame size of 1088 bytes is larger than 1024 bytes [-Werror=frame-larger-than=]
hisilicon/hns/hns_dsaf_main.c: In function 'hns_dsaf_get_regs':
hisilicon/hns/hns_dsaf_main.c:2753:1: error: the frame size of 10768 bytes is larger than 1024 bytes [-Werror=frame-larger-than=]

This does not seem to happen any more with gcc-7, but removing the ACCESS_ONCE
seems safe anyway and it avoids a serious issue for some people. I have verified
that with gcc-5.3.1, the object code we get is better in the new version
both with and without CONFIG_KASAN, as we no longer allocate a 1344 byte
stack frame for hns_dsaf_get_regs() but otherwise have practically identical
object code.

With gcc-7.0.0, removing ACCESS_ONCE has no effect, the object code is already
good either way.

This patch is probably not urgent to get into 4.11 as only KASAN=y builds
with certain compilers are affected, but I still think it makes sense to
backport into older kernels.

Cc: stable@vger.kernel.org
Fixes: 511e6bc ("net: add Hisilicon Network Subsystem DSAF support")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
index bdbd8042..9ff2881 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
@@ -900,9 +900,7 @@
 
 static inline void dsaf_write_reg(void __iomem *base, u32 reg, u32 value)
 {
-	u8 __iomem *reg_addr = ACCESS_ONCE(base);
-
-	writel(value, reg_addr + reg);
+	writel(value, base + reg);
 }
 
 #define dsaf_write_dev(a, reg, value) \
@@ -910,9 +908,7 @@ static inline void dsaf_write_reg(void __iomem *base, u32 reg, u32 value)
 
 static inline u32 dsaf_read_reg(u8 __iomem *base, u32 reg)
 {
-	u8 __iomem *reg_addr = ACCESS_ONCE(base);
-
-	return readl(reg_addr + reg);
+	return readl(base + reg);
 }
 
 #define dsaf_read_dev(a, reg) \
-- 
2.4.11


From 3b8fb586dfe86af046eb54ecd8de4ec92038a5ef Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 3 Feb 2017 14:59:38 -0800
Subject: [PATCH 11/20] tcp: avoid infinite loop in tcp_splice_read()

[ Upstream commit ccf7abb93af09ad0868ae9033d1ca8108bdaec82 ]

Splicing from TCP socket is vulnerable when a packet with URG flag is
received and stored into receive queue.

__tcp_splice_read() returns 0, and sk_wait_data() immediately
returns since there is the problematic skb in queue.

This is a nice way to burn cpu (aka infinite loop) and trigger
soft lockups.

Again, this gem was found by syzkaller tool.

Fixes: 9c55e01c0cc8 ("[TCP]: Splice receive support.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov  <dvyukov@google.com>
Cc: Willy Tarreau <w@1wt.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 69daa81..600dcda 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -783,6 +783,12 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
 				ret = -EAGAIN;
 				break;
 			}
+			/* if __tcp_splice_read() got nothing while we have
+			 * an skb in receive queue, we do not want to loop.
+			 * This might happen with URG data.
+			 */
+			if (!skb_queue_empty(&sk->sk_receive_queue))
+				break;
 			sk_wait_data(sk, &timeo, NULL);
 			if (signal_pending(current)) {
 				ret = sock_intr_errno(timeo);
-- 
2.4.11


From 9b6f99525b74a9ddc710660945bcff635f8f1d32 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 3 Feb 2017 18:20:48 -0500
Subject: [PATCH 12/20] tun: read vnet_hdr_sz once

[ Upstream commit e1edab87faf6ca30cd137e0795bc73aa9a9a22ec ]

When IFF_VNET_HDR is enabled, a virtio_net header must precede data.
Data length is verified to be greater than or equal to expected header
length tun->vnet_hdr_sz before copying.

Read this value once and cache locally, as it can be updated between
the test and use (TOCTOU).

Signed-off-by: Willem de Bruijn <willemb@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
CC: Eric Dumazet <edumazet@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 111b972..c31d8e7 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1108,9 +1108,11 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	}
 
 	if (tun->flags & IFF_VNET_HDR) {
-		if (len < tun->vnet_hdr_sz)
+		int vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz);
+
+		if (len < vnet_hdr_sz)
 			return -EINVAL;
-		len -= tun->vnet_hdr_sz;
+		len -= vnet_hdr_sz;
 
 		n = copy_from_iter(&gso, sizeof(gso), from);
 		if (n != sizeof(gso))
@@ -1122,7 +1124,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 
 		if (tun16_to_cpu(tun, gso.hdr_len) > len)
 			return -EINVAL;
-		iov_iter_advance(from, tun->vnet_hdr_sz - sizeof(gso));
+		iov_iter_advance(from, vnet_hdr_sz - sizeof(gso));
 	}
 
 	if ((tun->flags & TUN_TYPE_MASK) == IFF_TAP) {
@@ -1301,7 +1303,7 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 		vlan_hlen = VLAN_HLEN;
 
 	if (tun->flags & IFF_VNET_HDR)
-		vnet_hdr_sz = tun->vnet_hdr_sz;
+		vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz);
 
 	total = skb->len + vlan_hlen + vnet_hdr_sz;
 
-- 
2.4.11


From afc4da6683539a38aba6271b8311eccca76b0635 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 3 Feb 2017 18:20:49 -0500
Subject: [PATCH 13/20] macvtap: read vnet_hdr_size once

[ Upstream commit 837585a5375c38d40361cfe64e6fd11e1addb936 ]

When IFF_VNET_HDR is enabled, a virtio_net header must precede data.
Data length is verified to be greater than or equal to expected header
length tun->vnet_hdr_sz before copying.

Macvtap functions read the value once, but unless READ_ONCE is used,
the compiler may ignore this and read multiple times. Enforce a single
read and locally cached value to avoid updates between test and use.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Suggested-by: Eric Dumazet <edumazet@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macvtap.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 159a687..79de960 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -725,7 +725,7 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 	ssize_t n;
 
 	if (q->flags & IFF_VNET_HDR) {
-		vnet_hdr_len = q->vnet_hdr_sz;
+		vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz);
 
 		err = -EINVAL;
 		if (len < vnet_hdr_len)
@@ -865,7 +865,7 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q,
 
 	if (q->flags & IFF_VNET_HDR) {
 		struct virtio_net_hdr vnet_hdr;
-		vnet_hdr_len = q->vnet_hdr_sz;
+		vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz);
 		if (iov_iter_count(iter) < vnet_hdr_len)
 			return -EINVAL;
 
-- 
2.4.11


From e3a701015069e1d40dad7a99a8c8eaf16df7c4af Mon Sep 17 00:00:00 2001
From: Benjamin Poirier <bpoirier@suse.com>
Date: Mon, 6 Feb 2017 10:14:31 -0800
Subject: [PATCH 14/20] mlx4: Invoke softirqs after napi_reschedule

[ Upstream commit bd4ce941c8d5b862b2f83364be5dbe8fc8ab48f8 ]

mlx4 may schedule napi from a workqueue. Afterwards, softirqs are not run
in a deterministic time frame and the following message may be logged:
NOHZ: local_softirq_pending 08

The problem is the same as what was described in commit ec13ee80145c
("virtio_net: invoke softirqs after __napi_schedule") and this patch
applies the same fix to mlx4.

Fixes: 07841f9d94c1 ("net/mlx4_en: Schedule napi when RX buffers allocation fails")
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Benjamin Poirier <bpoirier@suse.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_rx.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index bbff8ec..28a4b34 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -502,8 +502,11 @@ void mlx4_en_recover_from_oom(struct mlx4_en_priv *priv)
 		return;
 
 	for (ring = 0; ring < priv->rx_ring_num; ring++) {
-		if (mlx4_en_is_ring_empty(priv->rx_ring[ring]))
+		if (mlx4_en_is_ring_empty(priv->rx_ring[ring])) {
+			local_bh_disable();
 			napi_reschedule(&priv->rx_cq[ring]->napi);
+			local_bh_enable();
+		}
 	}
 }
 
-- 
2.4.11


From d68b4ad4e5f09904ce977cd9104867f241ef8de4 Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Mon, 6 Feb 2017 18:10:31 -0200
Subject: [PATCH 15/20] sctp: avoid BUG_ON on sctp_wait_for_sndbuf

[ Upstream commit 2dcab598484185dea7ec22219c76dcdd59e3cb90 ]

Alexander Popov reported that an application may trigger a BUG_ON in
sctp_wait_for_sndbuf if the socket tx buffer is full, a thread is
waiting on it to queue more data and meanwhile another thread peels off
the association being used by the first thread.

This patch replaces the BUG_ON call with a proper error handling. It
will return -EPIPE to the original sendmsg call, similarly to what would
have been done if the association wasn't found in the first place.

Acked-by: Alexander Popov <alex.popov@linux.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index b5fd4ab..138f2d6 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -6960,7 +6960,8 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p,
 		 */
 		release_sock(sk);
 		current_timeo = schedule_timeout(current_timeo);
-		BUG_ON(sk != asoc->base.sk);
+		if (sk != asoc->base.sk)
+			goto do_error;
 		lock_sock(sk);
 
 		*timeo_p = current_timeo;
-- 
2.4.11


From 6f0388f172146e11cfc2effa5cf69dced18d0f60 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Wed, 8 Feb 2017 10:02:13 -0800
Subject: [PATCH 16/20] sit: fix a double free on error path

[ Upstream commit d7426c69a1942b2b9b709bf66b944ff09f561484 ]

Dmitry reported a double free in sit_init_net():

  kernel BUG at mm/percpu.c:689!
  invalid opcode: 0000 [#1] SMP KASAN
  Dumping ftrace buffer:
     (ftrace buffer empty)
  Modules linked in:
  CPU: 0 PID: 15692 Comm: syz-executor1 Not tainted 4.10.0-rc6-next-20170206 #1
  Hardware name: Google Google Compute Engine/Google Compute Engine,
  BIOS Google 01/01/2011
  task: ffff8801c9cc27c0 task.stack: ffff88017d1d8000
  RIP: 0010:pcpu_free_area+0x68b/0x810 mm/percpu.c:689
  RSP: 0018:ffff88017d1df488 EFLAGS: 00010046
  RAX: 0000000000010000 RBX: 00000000000007c0 RCX: ffffc90002829000
  RDX: 0000000000010000 RSI: ffffffff81940efb RDI: ffff8801db841d94
  RBP: ffff88017d1df590 R08: dffffc0000000000 R09: 1ffffffff0bb3bdd
  R10: dffffc0000000000 R11: 00000000000135dd R12: ffff8801db841d80
  R13: 0000000000038e40 R14: 00000000000007c0 R15: 00000000000007c0
  FS:  00007f6ea608f700(0000) GS:ffff8801dbe00000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 000000002000aff8 CR3: 00000001c8d44000 CR4: 00000000001426f0
  DR0: 0000000020000000 DR1: 0000000020000000 DR2: 0000000000000000
  DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000600
  Call Trace:
   free_percpu+0x212/0x520 mm/percpu.c:1264
   ipip6_dev_free+0x43/0x60 net/ipv6/sit.c:1335
   sit_init_net+0x3cb/0xa10 net/ipv6/sit.c:1831
   ops_init+0x10a/0x530 net/core/net_namespace.c:115
   setup_net+0x2ed/0x690 net/core/net_namespace.c:291
   copy_net_ns+0x26c/0x530 net/core/net_namespace.c:396
   create_new_namespaces+0x409/0x860 kernel/nsproxy.c:106
   unshare_nsproxy_namespaces+0xae/0x1e0 kernel/nsproxy.c:205
   SYSC_unshare kernel/fork.c:2281 [inline]
   SyS_unshare+0x64e/0xfc0 kernel/fork.c:2231
   entry_SYSCALL_64_fastpath+0x1f/0xc2

This is because when tunnel->dst_cache init fails, we free dev->tstats
once in ipip6_tunnel_init() and twice in sit_init_net(). This looks
redundant but its ndo_uinit() does not seem enough to clean up everything
here. So avoid this by setting dev->tstats to NULL after the first free,
at least for -net.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 3da2b16..184f0fe 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1389,6 +1389,7 @@ static int ipip6_tunnel_init(struct net_device *dev)
 	tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst);
 	if (!tunnel->dst_cache) {
 		free_percpu(dev->tstats);
+		dev->tstats = NULL;
 		return -ENOMEM;
 	}
 
-- 
2.4.11


From b6c0f8b52ea9613814be8527f58d0e215e64f169 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Tue, 7 Feb 2017 15:57:20 -0500
Subject: [PATCH 17/20] net: introduce device min_header_len

[ Upstream commit 217e6fa24ce28ec87fca8da93c9016cb78028612 ]

The stack must not pass packets to device drivers that are shorter
than the minimum link layer header length.

Previously, packet sockets would drop packets smaller than or equal
to dev->hard_header_len, but this has false positives. Zero length
payload is used over Ethernet. Other link layer protocols support
variable length headers. Support for validation of these protocols
removed the min length check for all protocols.

Introduce an explicit dev->min_header_len parameter and drop all
packets below this value. Initially, set it to non-zero only for
Ethernet and loopback. Other protocols can follow in a patch to
net-next.

Fixes: 9ed988cd5915 ("packet: validate variable length ll headers")
Reported-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/loopback.c    | 1 +
 include/linux/netdevice.h | 4 ++++
 net/ethernet/eth.c        | 1 +
 3 files changed, 6 insertions(+)

diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index dc7d970..effcdbf 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -164,6 +164,7 @@ static void loopback_setup(struct net_device *dev)
 {
 	dev->mtu		= 64 * 1024;
 	dev->hard_header_len	= ETH_HLEN;	/* 14	*/
+	dev->min_header_len	= ETH_HLEN;	/* 14	*/
 	dev->addr_len		= ETH_ALEN;	/* 6	*/
 	dev->type		= ARPHRD_LOOPBACK;	/* 0x0001*/
 	dev->flags		= IFF_LOOPBACK;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 93a6a2c..4035bbe 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1399,6 +1399,7 @@ enum netdev_priv_flags {
  *	@mtu:		Interface MTU value
  *	@type:		Interface hardware type
  *	@hard_header_len: Maximum hardware header length.
+ *	@min_header_len:  Minimum hardware header length
  *
  *	@needed_headroom: Extra headroom the hardware may need, but not in all
  *			  cases can this be guaranteed
@@ -1619,6 +1620,7 @@ struct net_device {
 	unsigned int		mtu;
 	unsigned short		type;
 	unsigned short		hard_header_len;
+	unsigned short		min_header_len;
 
 	unsigned short		needed_headroom;
 	unsigned short		needed_tailroom;
@@ -2541,6 +2543,8 @@ static inline bool dev_validate_header(const struct net_device *dev,
 {
 	if (likely(len >= dev->hard_header_len))
 		return true;
+	if (len < dev->min_header_len)
+		return false;
 
 	if (capable(CAP_SYS_RAWIO)) {
 		memset(ll_header + len, 0, dev->hard_header_len - len);
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index de85d4e..52dcd41 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -353,6 +353,7 @@ void ether_setup(struct net_device *dev)
 	dev->header_ops		= &eth_header_ops;
 	dev->type		= ARPHRD_ETHER;
 	dev->hard_header_len 	= ETH_HLEN;
+	dev->min_header_len	= ETH_HLEN;
 	dev->mtu		= ETH_DATA_LEN;
 	dev->addr_len		= ETH_ALEN;
 	dev->tx_queue_len	= 1000;	/* Ethernet wants good queues */
-- 
2.4.11


From 2840f9e1cecad9cdc87695be1b7a4572a397579e Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Tue, 7 Feb 2017 15:57:21 -0500
Subject: [PATCH 18/20] packet: round up linear to header len

[ Upstream commit 57031eb794906eea4e1c7b31dc1e2429c0af0c66 ]

Link layer protocols may unconditionally pull headers, as Ethernet
does in eth_type_trans. Ensure that the entire link layer header
always lies in the skb linear segment. tpacket_snd has such a check.
Extend this to packet_snd.

Variable length link layer headers complicate the computation
somewhat. Here skb->len may be smaller than dev->hard_header_len.

Round up the linear length to be at least as long as the smallest of
the two.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index f223d1c..f2d28ed 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2637,7 +2637,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	int vnet_hdr_len;
 	struct packet_sock *po = pkt_sk(sk);
 	unsigned short gso_type = 0;
-	int hlen, tlen;
+	int hlen, tlen, linear;
 	int extra_len = 0;
 	ssize_t n;
 
@@ -2741,8 +2741,9 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	err = -ENOBUFS;
 	hlen = LL_RESERVED_SPACE(dev);
 	tlen = dev->needed_tailroom;
-	skb = packet_alloc_skb(sk, hlen + tlen, hlen, len,
-			       __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len),
+	linear = __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len);
+	linear = max(linear, min_t(int, len, dev->hard_header_len));
+	skb = packet_alloc_skb(sk, hlen + tlen, hlen, len, linear,
 			       msg->msg_flags & MSG_DONTWAIT, &err);
 	if (skb == NULL)
 		goto out_unlock;
-- 
2.4.11


From bd5f4399d438d0c9780dfe516198ffc13a2cdf94 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Tue, 7 Feb 2017 12:59:46 -0800
Subject: [PATCH 19/20] ping: fix a null pointer dereference

[ Upstream commit 73d2c6678e6c3af7e7a42b1e78cd0211782ade32 ]

Andrey reported a kernel crash:

  general protection fault: 0000 [#1] SMP KASAN
  Dumping ftrace buffer:
     (ftrace buffer empty)
  Modules linked in:
  CPU: 2 PID: 3880 Comm: syz-executor1 Not tainted 4.10.0-rc6+ #124
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
  task: ffff880060048040 task.stack: ffff880069be8000
  RIP: 0010:ping_v4_push_pending_frames net/ipv4/ping.c:647 [inline]
  RIP: 0010:ping_v4_sendmsg+0x1acd/0x23f0 net/ipv4/ping.c:837
  RSP: 0018:ffff880069bef8b8 EFLAGS: 00010206
  RAX: dffffc0000000000 RBX: ffff880069befb90 RCX: 0000000000000000
  RDX: 0000000000000018 RSI: ffff880069befa30 RDI: 00000000000000c2
  RBP: ffff880069befbb8 R08: 0000000000000008 R09: 0000000000000000
  R10: 0000000000000002 R11: 0000000000000000 R12: ffff880069befab0
  R13: ffff88006c624a80 R14: ffff880069befa70 R15: 0000000000000000
  FS:  00007f6f7c716700(0000) GS:ffff88006de00000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 00000000004a6f28 CR3: 000000003a134000 CR4: 00000000000006e0
  Call Trace:
   inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:744
   sock_sendmsg_nosec net/socket.c:635 [inline]
   sock_sendmsg+0xca/0x110 net/socket.c:645
   SYSC_sendto+0x660/0x810 net/socket.c:1687
   SyS_sendto+0x40/0x50 net/socket.c:1655
   entry_SYSCALL_64_fastpath+0x1f/0xc2

This is because we miss a check for NULL pointer for skb_peek() when
the queue is empty. Other places already have the same check.

Fixes: c319b4d76b9e ("net: ipv4: add IPPROTO_ICMP socket kind")
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ping.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 23160d2..3a00512 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -645,6 +645,8 @@ static int ping_v4_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh,
 {
 	struct sk_buff *skb = skb_peek(&sk->sk_write_queue);
 
+	if (!skb)
+		return 0;
 	pfh->wcheck = csum_partial((char *)&pfh->icmph,
 		sizeof(struct icmphdr), pfh->wcheck);
 	pfh->icmph.checksum = csum_fold(pfh->wcheck);
-- 
2.4.11


From aa0866df593814395a63f0c613d5e7b67400b839 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 9 Feb 2017 16:15:52 -0800
Subject: [PATCH 20/20] l2tp: do not use udp_ioctl()

[ Upstream commit 72fb96e7bdbbdd4421b0726992496531060f3636 ]

udp_ioctl(), as its name suggests, is used by UDP protocols,
but is also used by L2TP :(

L2TP should use its own handler, because it really does not
look the same.

SIOCINQ for instance should not assume UDP checksum or headers.

Thanks to Andrey and syzkaller team for providing the report
and a nice reproducer.

While crashes only happen on recent kernels (after commit
7c13f97ffde6 ("udp: do fwd memory scheduling on dequeue")), this
probably needs to be backported to older kernels.

Fixes: 7c13f97ffde6 ("udp: do fwd memory scheduling on dequeue")
Fixes: 85584672012e ("udp: Fix udp_poll() and ioctl()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.h |  1 +
 net/l2tp/l2tp_ip.c   | 27 ++++++++++++++++++++++++++-
 net/l2tp/l2tp_ip6.c  |  2 +-
 3 files changed, 28 insertions(+), 2 deletions(-)

diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 5871537..763e8e2 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -273,6 +273,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb,
 int l2tp_nl_register_ops(enum l2tp_pwtype pw_type,
 			 const struct l2tp_nl_cmd_ops *ops);
 void l2tp_nl_unregister_ops(enum l2tp_pwtype pw_type);
+int l2tp_ioctl(struct sock *sk, int cmd, unsigned long arg);
 
 /* Session reference counts. Incremented when code obtains a reference
  * to a session.
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index d0e906d..445b7cd 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -11,6 +11,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <asm/ioctls.h>
 #include <linux/icmp.h>
 #include <linux/module.h>
 #include <linux/skbuff.h>
@@ -555,6 +556,30 @@ out:
 	return err ? err : copied;
 }
 
+int l2tp_ioctl(struct sock *sk, int cmd, unsigned long arg)
+{
+	struct sk_buff *skb;
+	int amount;
+
+	switch (cmd) {
+	case SIOCOUTQ:
+		amount = sk_wmem_alloc_get(sk);
+		break;
+	case SIOCINQ:
+		spin_lock_bh(&sk->sk_receive_queue.lock);
+		skb = skb_peek(&sk->sk_receive_queue);
+		amount = skb ? skb->len : 0;
+		spin_unlock_bh(&sk->sk_receive_queue.lock);
+		break;
+
+	default:
+		return -ENOIOCTLCMD;
+	}
+
+	return put_user(amount, (int __user *)arg);
+}
+EXPORT_SYMBOL(l2tp_ioctl);
+
 static struct proto l2tp_ip_prot = {
 	.name		   = "L2TP/IP",
 	.owner		   = THIS_MODULE,
@@ -563,7 +588,7 @@ static struct proto l2tp_ip_prot = {
 	.bind		   = l2tp_ip_bind,
 	.connect	   = l2tp_ip_connect,
 	.disconnect	   = l2tp_ip_disconnect,
-	.ioctl		   = udp_ioctl,
+	.ioctl		   = l2tp_ioctl,
 	.destroy	   = l2tp_ip_destroy_sock,
 	.setsockopt	   = ip_setsockopt,
 	.getsockopt	   = ip_getsockopt,
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 3c4f867..bcdab1c 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -714,7 +714,7 @@ static struct proto l2tp_ip6_prot = {
 	.bind		   = l2tp_ip6_bind,
 	.connect	   = l2tp_ip6_connect,
 	.disconnect	   = l2tp_ip6_disconnect,
-	.ioctl		   = udp_ioctl,
+	.ioctl		   = l2tp_ioctl,
 	.destroy	   = l2tp_ip6_destroy_sock,
 	.setsockopt	   = ipv6_setsockopt,
 	.getsockopt	   = ipv6_getsockopt,
-- 
2.4.11


[-- Attachment #3: net_49.mbox --]
[-- Type: Application/Octet-Stream, Size: 102372 bytes --]

From a399faed7d3bad298d658af7b1df1afd7ac9c8c1 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 27 Jan 2017 08:11:44 -0800
Subject: [PATCH 01/33] can: Fix kernel panic at security_sock_rcv_skb

[ Upstream commit f1712c73714088a7252d276a57126d56c7d37e64 ]

Zhang Yanmin reported crashes [1] and provided a patch adding a
synchronize_rcu() call in can_rx_unregister()

The main problem seems that the sockets themselves are not RCU
protected.

If CAN uses RCU for delivery, then sockets should be freed only after
one RCU grace period.

Recent kernels could use sock_set_flag(sk, SOCK_RCU_FREE), but let's
ease stable backports with the following fix instead.

[1]
BUG: unable to handle kernel NULL pointer dereference at (null)
IP: [<ffffffff81495e25>] selinux_socket_sock_rcv_skb+0x65/0x2a0

Call Trace:
 <IRQ>
 [<ffffffff81485d8c>] security_sock_rcv_skb+0x4c/0x60
 [<ffffffff81d55771>] sk_filter+0x41/0x210
 [<ffffffff81d12913>] sock_queue_rcv_skb+0x53/0x3a0
 [<ffffffff81f0a2b3>] raw_rcv+0x2a3/0x3c0
 [<ffffffff81f06eab>] can_rcv_filter+0x12b/0x370
 [<ffffffff81f07af9>] can_receive+0xd9/0x120
 [<ffffffff81f07beb>] can_rcv+0xab/0x100
 [<ffffffff81d362ac>] __netif_receive_skb_core+0xd8c/0x11f0
 [<ffffffff81d36734>] __netif_receive_skb+0x24/0xb0
 [<ffffffff81d37f67>] process_backlog+0x127/0x280
 [<ffffffff81d36f7b>] net_rx_action+0x33b/0x4f0
 [<ffffffff810c88d4>] __do_softirq+0x184/0x440
 [<ffffffff81f9e86c>] do_softirq_own_stack+0x1c/0x30
 <EOI>
 [<ffffffff810c76fb>] do_softirq.part.18+0x3b/0x40
 [<ffffffff810c8bed>] do_softirq+0x1d/0x20
 [<ffffffff81d30085>] netif_rx_ni+0xe5/0x110
 [<ffffffff8199cc87>] slcan_receive_buf+0x507/0x520
 [<ffffffff8167ef7c>] flush_to_ldisc+0x21c/0x230
 [<ffffffff810e3baf>] process_one_work+0x24f/0x670
 [<ffffffff810e44ed>] worker_thread+0x9d/0x6f0
 [<ffffffff810e4450>] ? rescuer_thread+0x480/0x480
 [<ffffffff810ebafc>] kthread+0x12c/0x150
 [<ffffffff81f9ccef>] ret_from_fork+0x3f/0x70

Reported-by: Zhang Yanmin <yanmin.zhang@intel.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/can/core.h |  7 +++----
 net/can/af_can.c         | 12 ++++++++++--
 net/can/af_can.h         |  3 ++-
 net/can/bcm.c            |  4 ++--
 net/can/gw.c             |  2 +-
 net/can/raw.c            |  4 ++--
 6 files changed, 20 insertions(+), 12 deletions(-)

diff --git a/include/linux/can/core.h b/include/linux/can/core.h
index a087500..df08a41 100644
--- a/include/linux/can/core.h
+++ b/include/linux/can/core.h
@@ -45,10 +45,9 @@ struct can_proto {
 extern int  can_proto_register(const struct can_proto *cp);
 extern void can_proto_unregister(const struct can_proto *cp);
 
-extern int  can_rx_register(struct net_device *dev, canid_t can_id,
-			    canid_t mask,
-			    void (*func)(struct sk_buff *, void *),
-			    void *data, char *ident);
+int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask,
+		    void (*func)(struct sk_buff *, void *),
+		    void *data, char *ident, struct sock *sk);
 
 extern void can_rx_unregister(struct net_device *dev, canid_t can_id,
 			      canid_t mask,
diff --git a/net/can/af_can.c b/net/can/af_can.c
index 1108079..5488e4a 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -445,6 +445,7 @@ static struct hlist_head *find_rcv_list(canid_t *can_id, canid_t *mask,
  * @func: callback function on filter match
  * @data: returned parameter for callback function
  * @ident: string for calling module identification
+ * @sk: socket pointer (might be NULL)
  *
  * Description:
  *  Invokes the callback function with the received sk_buff and the given
@@ -468,7 +469,7 @@ static struct hlist_head *find_rcv_list(canid_t *can_id, canid_t *mask,
  */
 int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask,
 		    void (*func)(struct sk_buff *, void *), void *data,
-		    char *ident)
+		    char *ident, struct sock *sk)
 {
 	struct receiver *r;
 	struct hlist_head *rl;
@@ -496,6 +497,7 @@ int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask,
 		r->func    = func;
 		r->data    = data;
 		r->ident   = ident;
+		r->sk      = sk;
 
 		hlist_add_head_rcu(&r->list, rl);
 		d->entries++;
@@ -520,8 +522,11 @@ EXPORT_SYMBOL(can_rx_register);
 static void can_rx_delete_receiver(struct rcu_head *rp)
 {
 	struct receiver *r = container_of(rp, struct receiver, rcu);
+	struct sock *sk = r->sk;
 
 	kmem_cache_free(rcv_cache, r);
+	if (sk)
+		sock_put(sk);
 }
 
 /**
@@ -596,8 +601,11 @@ void can_rx_unregister(struct net_device *dev, canid_t can_id, canid_t mask,
 	spin_unlock(&can_rcvlists_lock);
 
 	/* schedule the receiver item for deletion */
-	if (r)
+	if (r) {
+		if (r->sk)
+			sock_hold(r->sk);
 		call_rcu(&r->rcu, can_rx_delete_receiver);
+	}
 }
 EXPORT_SYMBOL(can_rx_unregister);
 
diff --git a/net/can/af_can.h b/net/can/af_can.h
index fca0fe9..b86f512 100644
--- a/net/can/af_can.h
+++ b/net/can/af_can.h
@@ -50,13 +50,14 @@
 
 struct receiver {
 	struct hlist_node list;
-	struct rcu_head rcu;
 	canid_t can_id;
 	canid_t mask;
 	unsigned long matches;
 	void (*func)(struct sk_buff *, void *);
 	void *data;
 	char *ident;
+	struct sock *sk;
+	struct rcu_head rcu;
 };
 
 #define CAN_SFF_RCV_ARRAY_SZ (1 << CAN_SFF_ID_BITS)
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 5e9ed5e..e4f694d 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -1225,7 +1225,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 				err = can_rx_register(dev, op->can_id,
 						      REGMASK(op->can_id),
 						      bcm_rx_handler, op,
-						      "bcm");
+						      "bcm", sk);
 
 				op->rx_reg_dev = dev;
 				dev_put(dev);
@@ -1234,7 +1234,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		} else
 			err = can_rx_register(NULL, op->can_id,
 					      REGMASK(op->can_id),
-					      bcm_rx_handler, op, "bcm");
+					      bcm_rx_handler, op, "bcm", sk);
 		if (err) {
 			/* this bcm rx op is broken -> remove it */
 			list_del(&op->list);
diff --git a/net/can/gw.c b/net/can/gw.c
index 4551687..77c8af4 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -442,7 +442,7 @@ static inline int cgw_register_filter(struct cgw_job *gwj)
 {
 	return can_rx_register(gwj->src.dev, gwj->ccgw.filter.can_id,
 			       gwj->ccgw.filter.can_mask, can_can_gw_rcv,
-			       gwj, "gw");
+			       gwj, "gw", NULL);
 }
 
 static inline void cgw_unregister_filter(struct cgw_job *gwj)
diff --git a/net/can/raw.c b/net/can/raw.c
index b075f02..6dc546a 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -190,7 +190,7 @@ static int raw_enable_filters(struct net_device *dev, struct sock *sk,
 	for (i = 0; i < count; i++) {
 		err = can_rx_register(dev, filter[i].can_id,
 				      filter[i].can_mask,
-				      raw_rcv, sk, "raw");
+				      raw_rcv, sk, "raw", sk);
 		if (err) {
 			/* clean up successfully registered filters */
 			while (--i >= 0)
@@ -211,7 +211,7 @@ static int raw_enable_errfilter(struct net_device *dev, struct sock *sk,
 
 	if (err_mask)
 		err = can_rx_register(dev, 0, err_mask | CAN_ERR_FLAG,
-				      raw_rcv, sk, "raw");
+				      raw_rcv, sk, "raw", sk);
 
 	return err;
 }
-- 
2.4.11


From 8362a89d9b3d8766069628ee0e54cbfe5ddc07a5 Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Wed, 11 Jan 2017 14:32:26 +0200
Subject: [PATCH 02/33] net/mlx5e: Modify TIRs hash only when it's needed

[ Upstream commit 1d3398facd08a7fd4202f269317a95668eb880b9 ]

We don't need to modify our TIRs unless the user requested a change in
the hash function/key, for example when changing indirection only.

Tested:
 # Modify TIRs hash is needed
ethtool -X ethX hkey  <new key>
ethtool -X ethX hfunc <new func>

 # Modify TIRs hash is not needed
ethtool -X ethX equal <new indirection table>

All cases are verified with TCP Multi-Stream traffic over IPv4 & IPv6.

Fixes: bdfc028de1b3 ("net/mlx5e: Fix ethtool RX hash func configuration change")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 18 +++++++++++++-----
 1 file changed, 13 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 27ff401..51c6a57 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -991,6 +991,7 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	int inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
+	bool hash_changed = false;
 	void *in;
 
 	if ((hfunc != ETH_RSS_HASH_NO_CHANGE) &&
@@ -1012,14 +1013,21 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
 		mlx5e_redirect_rqt(priv, rqtn, MLX5E_INDIR_RQT_SIZE, 0);
 	}
 
-	if (key)
+	if (hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    hfunc != priv->params.rss_hfunc) {
+		priv->params.rss_hfunc = hfunc;
+		hash_changed = true;
+	}
+
+	if (key) {
 		memcpy(priv->params.toeplitz_hash_key, key,
 		       sizeof(priv->params.toeplitz_hash_key));
+		hash_changed = hash_changed ||
+			       priv->params.rss_hfunc == ETH_RSS_HASH_TOP;
+	}
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE)
-		priv->params.rss_hfunc = hfunc;
-
-	mlx5e_modify_tirs_hash(priv, in, inlen);
+	if (hash_changed)
+		mlx5e_modify_tirs_hash(priv, in, inlen);
 
 	mutex_unlock(&priv->state_lock);
 
-- 
2.4.11


From b1ba4df33c94e2f1f98aa14fd13c78de6be7b19a Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Thu, 12 Jan 2017 16:25:46 +0200
Subject: [PATCH 03/33] net/mlx5e: Fix update of hash function/key via ethtool

[ Upstream commit a100ff3eef193d2d79daf98dcd97a54776ffeb78 ]

Modifying TIR hash should change selected fields bitmask in addition to
the function and key.

Formerly, Only on ethool mlx5e_set_rxfh "ethtoo -X" we would not set this
field resulting in zeroing of its value, which means no packet fields are
used for RX RSS hash calculation thus causing all traffic to arrive in
RQ[0].

On driver load out of the box we don't have this issue, since the TIR
hash is fully created from scratch.

Tested:
ethtool -X ethX hkey  <new key>
ethtool -X ethX hfunc <new func>
ethtool -X ethX equal <new indirection table>

All cases are verified with TCP Multi-Stream traffic over IPv4 & IPv6.

Fixes: bdfc028de1b3 ("net/mlx5e: Fix ethtool RX hash func configuration change")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |   3 +-
 .../net/ethernet/mellanox/mlx5/core/en_ethtool.c   |  13 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  | 198 ++++++++++-----------
 3 files changed, 109 insertions(+), 105 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 71382df..81d8e3b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -765,7 +765,8 @@ void mlx5e_disable_vlan_filter(struct mlx5e_priv *priv);
 int mlx5e_modify_rqs_vsd(struct mlx5e_priv *priv, bool vsd);
 
 int mlx5e_redirect_rqt(struct mlx5e_priv *priv, u32 rqtn, int sz, int ix);
-void mlx5e_build_tir_ctx_hash(void *tirc, struct mlx5e_priv *priv);
+void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_priv *priv, void *tirc,
+				    enum mlx5e_traffic_types tt);
 
 int mlx5e_open_locked(struct net_device *netdev);
 int mlx5e_close_locked(struct net_device *netdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 51c6a57..126cfeb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -975,15 +975,18 @@ static int mlx5e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 
 static void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen)
 {
-	struct mlx5_core_dev *mdev = priv->mdev;
 	void *tirc = MLX5_ADDR_OF(modify_tir_in, in, ctx);
-	int i;
+	struct mlx5_core_dev *mdev = priv->mdev;
+	int ctxlen = MLX5_ST_SZ_BYTES(tirc);
+	int tt;
 
 	MLX5_SET(modify_tir_in, in, bitmask.hash, 1);
-	mlx5e_build_tir_ctx_hash(tirc, priv);
 
-	for (i = 0; i < MLX5E_NUM_INDIR_TIRS; i++)
-		mlx5_core_modify_tir(mdev, priv->indir_tir[i].tirn, in, inlen);
+	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
+		memset(tirc, 0, ctxlen);
+		mlx5e_build_indir_tir_ctx_hash(priv, tirc, tt);
+		mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in, inlen);
+	}
 }
 
 static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 5dc3e24..b3067137 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1978,8 +1978,23 @@ static void mlx5e_build_tir_ctx_lro(void *tirc, struct mlx5e_priv *priv)
 	MLX5_SET(tirc, tirc, lro_timeout_period_usecs, priv->params.lro_timeout);
 }
 
-void mlx5e_build_tir_ctx_hash(void *tirc, struct mlx5e_priv *priv)
+void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_priv *priv, void *tirc,
+				    enum mlx5e_traffic_types tt)
 {
+	void *hfso = MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_outer);
+
+#define MLX5_HASH_IP            (MLX5_HASH_FIELD_SEL_SRC_IP   |\
+				 MLX5_HASH_FIELD_SEL_DST_IP)
+
+#define MLX5_HASH_IP_L4PORTS    (MLX5_HASH_FIELD_SEL_SRC_IP   |\
+				 MLX5_HASH_FIELD_SEL_DST_IP   |\
+				 MLX5_HASH_FIELD_SEL_L4_SPORT |\
+				 MLX5_HASH_FIELD_SEL_L4_DPORT)
+
+#define MLX5_HASH_IP_IPSEC_SPI  (MLX5_HASH_FIELD_SEL_SRC_IP   |\
+				 MLX5_HASH_FIELD_SEL_DST_IP   |\
+				 MLX5_HASH_FIELD_SEL_IPSEC_SPI)
+
 	MLX5_SET(tirc, tirc, rx_hash_fn,
 		 mlx5e_rx_hash_fn(priv->params.rss_hfunc));
 	if (priv->params.rss_hfunc == ETH_RSS_HASH_TOP) {
@@ -1991,6 +2006,88 @@ void mlx5e_build_tir_ctx_hash(void *tirc, struct mlx5e_priv *priv)
 		MLX5_SET(tirc, tirc, rx_hash_symmetric, 1);
 		memcpy(rss_key, priv->params.toeplitz_hash_key, len);
 	}
+
+	switch (tt) {
+	case MLX5E_TT_IPV4_TCP:
+		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+			 MLX5_L3_PROT_TYPE_IPV4);
+		MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
+			 MLX5_L4_PROT_TYPE_TCP);
+		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+			 MLX5_HASH_IP_L4PORTS);
+		break;
+
+	case MLX5E_TT_IPV6_TCP:
+		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+			 MLX5_L3_PROT_TYPE_IPV6);
+		MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
+			 MLX5_L4_PROT_TYPE_TCP);
+		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+			 MLX5_HASH_IP_L4PORTS);
+		break;
+
+	case MLX5E_TT_IPV4_UDP:
+		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+			 MLX5_L3_PROT_TYPE_IPV4);
+		MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
+			 MLX5_L4_PROT_TYPE_UDP);
+		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+			 MLX5_HASH_IP_L4PORTS);
+		break;
+
+	case MLX5E_TT_IPV6_UDP:
+		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+			 MLX5_L3_PROT_TYPE_IPV6);
+		MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
+			 MLX5_L4_PROT_TYPE_UDP);
+		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+			 MLX5_HASH_IP_L4PORTS);
+		break;
+
+	case MLX5E_TT_IPV4_IPSEC_AH:
+		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+			 MLX5_L3_PROT_TYPE_IPV4);
+		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+			 MLX5_HASH_IP_IPSEC_SPI);
+		break;
+
+	case MLX5E_TT_IPV6_IPSEC_AH:
+		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+			 MLX5_L3_PROT_TYPE_IPV6);
+		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+			 MLX5_HASH_IP_IPSEC_SPI);
+		break;
+
+	case MLX5E_TT_IPV4_IPSEC_ESP:
+		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+			 MLX5_L3_PROT_TYPE_IPV4);
+		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+			 MLX5_HASH_IP_IPSEC_SPI);
+		break;
+
+	case MLX5E_TT_IPV6_IPSEC_ESP:
+		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+			 MLX5_L3_PROT_TYPE_IPV6);
+		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+			 MLX5_HASH_IP_IPSEC_SPI);
+		break;
+
+	case MLX5E_TT_IPV4:
+		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+			 MLX5_L3_PROT_TYPE_IPV4);
+		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+			 MLX5_HASH_IP);
+		break;
+
+	case MLX5E_TT_IPV6:
+		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+			 MLX5_L3_PROT_TYPE_IPV6);
+		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+			 MLX5_HASH_IP);
+		break;
+	default:
+		WARN_ONCE(true, "%s: bad traffic type!\n", __func__);
+	}
 }
 
 static int mlx5e_modify_tirs_lro(struct mlx5e_priv *priv)
@@ -2360,110 +2457,13 @@ void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv)
 static void mlx5e_build_indir_tir_ctx(struct mlx5e_priv *priv, u32 *tirc,
 				      enum mlx5e_traffic_types tt)
 {
-	void *hfso = MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_outer);
-
 	MLX5_SET(tirc, tirc, transport_domain, priv->mdev->mlx5e_res.td.tdn);
 
-#define MLX5_HASH_IP            (MLX5_HASH_FIELD_SEL_SRC_IP   |\
-				 MLX5_HASH_FIELD_SEL_DST_IP)
-
-#define MLX5_HASH_IP_L4PORTS    (MLX5_HASH_FIELD_SEL_SRC_IP   |\
-				 MLX5_HASH_FIELD_SEL_DST_IP   |\
-				 MLX5_HASH_FIELD_SEL_L4_SPORT |\
-				 MLX5_HASH_FIELD_SEL_L4_DPORT)
-
-#define MLX5_HASH_IP_IPSEC_SPI  (MLX5_HASH_FIELD_SEL_SRC_IP   |\
-				 MLX5_HASH_FIELD_SEL_DST_IP   |\
-				 MLX5_HASH_FIELD_SEL_IPSEC_SPI)
-
 	mlx5e_build_tir_ctx_lro(tirc, priv);
 
 	MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT);
 	MLX5_SET(tirc, tirc, indirect_table, priv->indir_rqt.rqtn);
-	mlx5e_build_tir_ctx_hash(tirc, priv);
-
-	switch (tt) {
-	case MLX5E_TT_IPV4_TCP:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV4);
-		MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
-			 MLX5_L4_PROT_TYPE_TCP);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_L4PORTS);
-		break;
-
-	case MLX5E_TT_IPV6_TCP:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV6);
-		MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
-			 MLX5_L4_PROT_TYPE_TCP);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_L4PORTS);
-		break;
-
-	case MLX5E_TT_IPV4_UDP:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV4);
-		MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
-			 MLX5_L4_PROT_TYPE_UDP);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_L4PORTS);
-		break;
-
-	case MLX5E_TT_IPV6_UDP:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV6);
-		MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
-			 MLX5_L4_PROT_TYPE_UDP);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_L4PORTS);
-		break;
-
-	case MLX5E_TT_IPV4_IPSEC_AH:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV4);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_IPSEC_SPI);
-		break;
-
-	case MLX5E_TT_IPV6_IPSEC_AH:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV6);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_IPSEC_SPI);
-		break;
-
-	case MLX5E_TT_IPV4_IPSEC_ESP:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV4);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_IPSEC_SPI);
-		break;
-
-	case MLX5E_TT_IPV6_IPSEC_ESP:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV6);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_IPSEC_SPI);
-		break;
-
-	case MLX5E_TT_IPV4:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV4);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP);
-		break;
-
-	case MLX5E_TT_IPV6:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV6);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP);
-		break;
-	default:
-		WARN_ONCE(true,
-			  "mlx5e_build_indir_tir_ctx: bad traffic type!\n");
-	}
+	mlx5e_build_indir_tir_ctx_hash(priv, tirc, tt);
 }
 
 static void mlx5e_build_direct_tir_ctx(struct mlx5e_priv *priv, u32 *tirc,
-- 
2.4.11


From ee4f5abaac177183808949a6224581a409b635d3 Mon Sep 17 00:00:00 2001
From: Yotam Gigi <yotamg@mellanox.com>
Date: Tue, 31 Jan 2017 15:14:29 +0200
Subject: [PATCH 04/33] net/sched: matchall: Fix configuration race

[ Upstream commit fd62d9f5c575f0792f150109f1fd24a0d4b3f854 ]

In the current version, the matchall internal state is split into two
structs: cls_matchall_head and cls_matchall_filter. This makes little
sense, as matchall instance supports only one filter, and there is no
situation where one exists and the other does not. In addition, that led
to some races when filter was deleted while packet was processed.

Unify that two structs into one, thus simplifying the process of matchall
creation and deletion. As a result, the new, delete and get callbacks have
a dummy implementation where all the work is done in destroy and change
callbacks, as was done in cls_cgroup.

Fixes: bf3994d2ed31 ("net/sched: introduce Match-all classifier")
Reported-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Yotam Gigi <yotamg@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_matchall.c | 127 +++++++++++++++++------------------------------
 1 file changed, 45 insertions(+), 82 deletions(-)

diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index f935429..b12bc2a 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -16,16 +16,11 @@
 #include <net/sch_generic.h>
 #include <net/pkt_cls.h>
 
-struct cls_mall_filter {
+struct cls_mall_head {
 	struct tcf_exts exts;
 	struct tcf_result res;
 	u32 handle;
-	struct rcu_head	rcu;
 	u32 flags;
-};
-
-struct cls_mall_head {
-	struct cls_mall_filter *filter;
 	struct rcu_head	rcu;
 };
 
@@ -33,38 +28,29 @@ static int mall_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 			 struct tcf_result *res)
 {
 	struct cls_mall_head *head = rcu_dereference_bh(tp->root);
-	struct cls_mall_filter *f = head->filter;
 
-	if (tc_skip_sw(f->flags))
+	if (tc_skip_sw(head->flags))
 		return -1;
 
-	return tcf_exts_exec(skb, &f->exts, res);
+	return tcf_exts_exec(skb, &head->exts, res);
 }
 
 static int mall_init(struct tcf_proto *tp)
 {
-	struct cls_mall_head *head;
-
-	head = kzalloc(sizeof(*head), GFP_KERNEL);
-	if (!head)
-		return -ENOBUFS;
-
-	rcu_assign_pointer(tp->root, head);
-
 	return 0;
 }
 
-static void mall_destroy_filter(struct rcu_head *head)
+static void mall_destroy_rcu(struct rcu_head *rcu)
 {
-	struct cls_mall_filter *f = container_of(head, struct cls_mall_filter, rcu);
+	struct cls_mall_head *head = container_of(rcu, struct cls_mall_head,
+						  rcu);
 
-	tcf_exts_destroy(&f->exts);
-
-	kfree(f);
+	tcf_exts_destroy(&head->exts);
+	kfree(head);
 }
 
 static int mall_replace_hw_filter(struct tcf_proto *tp,
-				  struct cls_mall_filter *f,
+				  struct cls_mall_head *head,
 				  unsigned long cookie)
 {
 	struct net_device *dev = tp->q->dev_queue->dev;
@@ -74,7 +60,7 @@ static int mall_replace_hw_filter(struct tcf_proto *tp,
 	offload.type = TC_SETUP_MATCHALL;
 	offload.cls_mall = &mall_offload;
 	offload.cls_mall->command = TC_CLSMATCHALL_REPLACE;
-	offload.cls_mall->exts = &f->exts;
+	offload.cls_mall->exts = &head->exts;
 	offload.cls_mall->cookie = cookie;
 
 	return dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol,
@@ -82,7 +68,7 @@ static int mall_replace_hw_filter(struct tcf_proto *tp,
 }
 
 static void mall_destroy_hw_filter(struct tcf_proto *tp,
-				   struct cls_mall_filter *f,
+				   struct cls_mall_head *head,
 				   unsigned long cookie)
 {
 	struct net_device *dev = tp->q->dev_queue->dev;
@@ -103,29 +89,20 @@ static bool mall_destroy(struct tcf_proto *tp, bool force)
 {
 	struct cls_mall_head *head = rtnl_dereference(tp->root);
 	struct net_device *dev = tp->q->dev_queue->dev;
-	struct cls_mall_filter *f = head->filter;
 
-	if (!force && f)
-		return false;
+	if (!head)
+		return true;
 
-	if (f) {
-		if (tc_should_offload(dev, tp, f->flags))
-			mall_destroy_hw_filter(tp, f, (unsigned long) f);
+	if (tc_should_offload(dev, tp, head->flags))
+		mall_destroy_hw_filter(tp, head, (unsigned long) head);
 
-		call_rcu(&f->rcu, mall_destroy_filter);
-	}
-	kfree_rcu(head, rcu);
+	call_rcu(&head->rcu, mall_destroy_rcu);
 	return true;
 }
 
 static unsigned long mall_get(struct tcf_proto *tp, u32 handle)
 {
-	struct cls_mall_head *head = rtnl_dereference(tp->root);
-	struct cls_mall_filter *f = head->filter;
-
-	if (f && f->handle == handle)
-		return (unsigned long) f;
-	return 0;
+	return 0UL;
 }
 
 static const struct nla_policy mall_policy[TCA_MATCHALL_MAX + 1] = {
@@ -134,7 +111,7 @@ static const struct nla_policy mall_policy[TCA_MATCHALL_MAX + 1] = {
 };
 
 static int mall_set_parms(struct net *net, struct tcf_proto *tp,
-			  struct cls_mall_filter *f,
+			  struct cls_mall_head *head,
 			  unsigned long base, struct nlattr **tb,
 			  struct nlattr *est, bool ovr)
 {
@@ -147,11 +124,11 @@ static int mall_set_parms(struct net *net, struct tcf_proto *tp,
 		return err;
 
 	if (tb[TCA_MATCHALL_CLASSID]) {
-		f->res.classid = nla_get_u32(tb[TCA_MATCHALL_CLASSID]);
-		tcf_bind_filter(tp, &f->res, base);
+		head->res.classid = nla_get_u32(tb[TCA_MATCHALL_CLASSID]);
+		tcf_bind_filter(tp, &head->res, base);
 	}
 
-	tcf_exts_change(tp, &f->exts, &e);
+	tcf_exts_change(tp, &head->exts, &e);
 
 	return 0;
 }
@@ -162,21 +139,17 @@ static int mall_change(struct net *net, struct sk_buff *in_skb,
 		       unsigned long *arg, bool ovr)
 {
 	struct cls_mall_head *head = rtnl_dereference(tp->root);
-	struct cls_mall_filter *fold = (struct cls_mall_filter *) *arg;
 	struct net_device *dev = tp->q->dev_queue->dev;
-	struct cls_mall_filter *f;
 	struct nlattr *tb[TCA_MATCHALL_MAX + 1];
+	struct cls_mall_head *new;
 	u32 flags = 0;
 	int err;
 
 	if (!tca[TCA_OPTIONS])
 		return -EINVAL;
 
-	if (head->filter)
-		return -EBUSY;
-
-	if (fold)
-		return -EINVAL;
+	if (head)
+		return -EEXIST;
 
 	err = nla_parse_nested(tb, TCA_MATCHALL_MAX,
 			       tca[TCA_OPTIONS], mall_policy);
@@ -189,23 +162,23 @@ static int mall_change(struct net *net, struct sk_buff *in_skb,
 			return -EINVAL;
 	}
 
-	f = kzalloc(sizeof(*f), GFP_KERNEL);
-	if (!f)
+	new = kzalloc(sizeof(*new), GFP_KERNEL);
+	if (!new)
 		return -ENOBUFS;
 
-	tcf_exts_init(&f->exts, TCA_MATCHALL_ACT, 0);
+	tcf_exts_init(&new->exts, TCA_MATCHALL_ACT, 0);
 
 	if (!handle)
 		handle = 1;
-	f->handle = handle;
-	f->flags = flags;
+	new->handle = handle;
+	new->flags = flags;
 
-	err = mall_set_parms(net, tp, f, base, tb, tca[TCA_RATE], ovr);
+	err = mall_set_parms(net, tp, new, base, tb, tca[TCA_RATE], ovr);
 	if (err)
 		goto errout;
 
 	if (tc_should_offload(dev, tp, flags)) {
-		err = mall_replace_hw_filter(tp, f, (unsigned long) f);
+		err = mall_replace_hw_filter(tp, new, (unsigned long) new);
 		if (err) {
 			if (tc_skip_sw(flags))
 				goto errout;
@@ -214,39 +187,29 @@ static int mall_change(struct net *net, struct sk_buff *in_skb,
 		}
 	}
 
-	*arg = (unsigned long) f;
-	rcu_assign_pointer(head->filter, f);
-
+	*arg = (unsigned long) head;
+	rcu_assign_pointer(tp->root, new);
+	if (head)
+		call_rcu(&head->rcu, mall_destroy_rcu);
 	return 0;
 
 errout:
-	kfree(f);
+	kfree(new);
 	return err;
 }
 
 static int mall_delete(struct tcf_proto *tp, unsigned long arg)
 {
-	struct cls_mall_head *head = rtnl_dereference(tp->root);
-	struct cls_mall_filter *f = (struct cls_mall_filter *) arg;
-	struct net_device *dev = tp->q->dev_queue->dev;
-
-	if (tc_should_offload(dev, tp, f->flags))
-		mall_destroy_hw_filter(tp, f, (unsigned long) f);
-
-	RCU_INIT_POINTER(head->filter, NULL);
-	tcf_unbind_filter(tp, &f->res);
-	call_rcu(&f->rcu, mall_destroy_filter);
-	return 0;
+	return -EOPNOTSUPP;
 }
 
 static void mall_walk(struct tcf_proto *tp, struct tcf_walker *arg)
 {
 	struct cls_mall_head *head = rtnl_dereference(tp->root);
-	struct cls_mall_filter *f = head->filter;
 
 	if (arg->count < arg->skip)
 		goto skip;
-	if (arg->fn(tp, (unsigned long) f, arg) < 0)
+	if (arg->fn(tp, (unsigned long) head, arg) < 0)
 		arg->stop = 1;
 skip:
 	arg->count++;
@@ -255,28 +218,28 @@ static void mall_walk(struct tcf_proto *tp, struct tcf_walker *arg)
 static int mall_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
 		     struct sk_buff *skb, struct tcmsg *t)
 {
-	struct cls_mall_filter *f = (struct cls_mall_filter *) fh;
+	struct cls_mall_head *head = (struct cls_mall_head *) fh;
 	struct nlattr *nest;
 
-	if (!f)
+	if (!head)
 		return skb->len;
 
-	t->tcm_handle = f->handle;
+	t->tcm_handle = head->handle;
 
 	nest = nla_nest_start(skb, TCA_OPTIONS);
 	if (!nest)
 		goto nla_put_failure;
 
-	if (f->res.classid &&
-	    nla_put_u32(skb, TCA_MATCHALL_CLASSID, f->res.classid))
+	if (head->res.classid &&
+	    nla_put_u32(skb, TCA_MATCHALL_CLASSID, head->res.classid))
 		goto nla_put_failure;
 
-	if (tcf_exts_dump(skb, &f->exts))
+	if (tcf_exts_dump(skb, &head->exts))
 		goto nla_put_failure;
 
 	nla_nest_end(skb, nest);
 
-	if (tcf_exts_dump_stats(skb, &f->exts) < 0)
+	if (tcf_exts_dump_stats(skb, &head->exts) < 0)
 		goto nla_put_failure;
 
 	return skb->len;
-- 
2.4.11


From fc0c6ef3800ecd2962788831128ebeabe650018a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 23 Jan 2017 16:43:06 -0800
Subject: [PATCH 05/33] ipv6: fix ip6_tnl_parse_tlv_enc_lim()

[ Upstream commit fbfa743a9d2a0ffa24251764f10afc13eb21e739 ]

This function suffers from multiple issues.

First one is that pskb_may_pull() may reallocate skb->head,
so the 'raw' pointer needs either to be reloaded or not used at all.

Second issue is that NEXTHDR_DEST handling does not validate
that the options are present in skb->data, so we might read
garbage or access non existent memory.

With help from Willem de Bruijn.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov  <dvyukov@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 34 ++++++++++++++++++++++------------
 1 file changed, 22 insertions(+), 12 deletions(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index f95437f..12d745b 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -400,18 +400,19 @@ ip6_tnl_dev_uninit(struct net_device *dev)
 
 __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw)
 {
-	const struct ipv6hdr *ipv6h = (const struct ipv6hdr *) raw;
-	__u8 nexthdr = ipv6h->nexthdr;
-	__u16 off = sizeof(*ipv6h);
+	const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)raw;
+	unsigned int nhoff = raw - skb->data;
+	unsigned int off = nhoff + sizeof(*ipv6h);
+	u8 next, nexthdr = ipv6h->nexthdr;
 
 	while (ipv6_ext_hdr(nexthdr) && nexthdr != NEXTHDR_NONE) {
-		__u16 optlen = 0;
 		struct ipv6_opt_hdr *hdr;
-		if (raw + off + sizeof(*hdr) > skb->data &&
-		    !pskb_may_pull(skb, raw - skb->data + off + sizeof (*hdr)))
+		u16 optlen;
+
+		if (!pskb_may_pull(skb, off + sizeof(*hdr)))
 			break;
 
-		hdr = (struct ipv6_opt_hdr *) (raw + off);
+		hdr = (struct ipv6_opt_hdr *)(skb->data + off);
 		if (nexthdr == NEXTHDR_FRAGMENT) {
 			struct frag_hdr *frag_hdr = (struct frag_hdr *) hdr;
 			if (frag_hdr->frag_off)
@@ -422,20 +423,29 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw)
 		} else {
 			optlen = ipv6_optlen(hdr);
 		}
+		/* cache hdr->nexthdr, since pskb_may_pull() might
+		 * invalidate hdr
+		 */
+		next = hdr->nexthdr;
 		if (nexthdr == NEXTHDR_DEST) {
-			__u16 i = off + 2;
+			u16 i = 2;
+
+			/* Remember : hdr is no longer valid at this point. */
+			if (!pskb_may_pull(skb, off + optlen))
+				break;
+
 			while (1) {
 				struct ipv6_tlv_tnl_enc_lim *tel;
 
 				/* No more room for encapsulation limit */
-				if (i + sizeof (*tel) > off + optlen)
+				if (i + sizeof(*tel) > optlen)
 					break;
 
-				tel = (struct ipv6_tlv_tnl_enc_lim *) &raw[i];
+				tel = (struct ipv6_tlv_tnl_enc_lim *) skb->data + off + i;
 				/* return index of option if found and valid */
 				if (tel->type == IPV6_TLV_TNL_ENCAP_LIMIT &&
 				    tel->length == 1)
-					return i;
+					return i + off - nhoff;
 				/* else jump to next option */
 				if (tel->type)
 					i += tel->length + 2;
@@ -443,7 +453,7 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw)
 					i++;
 			}
 		}
-		nexthdr = hdr->nexthdr;
+		nexthdr = next;
 		off += optlen;
 	}
 	return 0;
-- 
2.4.11


From 8bba48469b27c5a20e2578f052a1a1387c974e60 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 1 Feb 2017 11:46:32 +0300
Subject: [PATCH 06/33] ipv6: pointer math error in ip6_tnl_parse_tlv_enc_lim()

[ Upstream commit 63117f09c768be05a0bf465911297dc76394f686 ]

Casting is a high precedence operation but "off" and "i" are in terms of
bytes so we need to have some parenthesis here.

Fixes: fbfa743a9d2a ("ipv6: fix ip6_tnl_parse_tlv_enc_lim()")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 12d745b..f6ba452 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -441,7 +441,7 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw)
 				if (i + sizeof(*tel) > optlen)
 					break;
 
-				tel = (struct ipv6_tlv_tnl_enc_lim *) skb->data + off + i;
+				tel = (struct ipv6_tlv_tnl_enc_lim *)(skb->data + off + i);
 				/* return index of option if found and valid */
 				if (tel->type == IPV6_TLV_TNL_ENCAP_LIMIT &&
 				    tel->length == 1)
-- 
2.4.11


From 91f01cc1148ebca5681c685d6b3ce825572c275c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 1 Feb 2017 08:33:53 -0800
Subject: [PATCH 07/33] tcp: fix 0 divide in __tcp_select_window()

[ Upstream commit 06425c308b92eaf60767bc71d359f4cbc7a561f8 ]

syszkaller fuzzer was able to trigger a divide by zero, when
TCP window scaling is not enabled.

SO_RCVBUF can be used not only to increase sk_rcvbuf, also
to decrease it below current receive buffers utilization.

If mss is negative or 0, just return a zero TCP window.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov  <dvyukov@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 896e9df..65d6189 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2436,9 +2436,11 @@ u32 __tcp_select_window(struct sock *sk)
 	int full_space = min_t(int, tp->window_clamp, allowed_space);
 	int window;
 
-	if (mss > full_space)
+	if (unlikely(mss > full_space)) {
 		mss = full_space;
-
+		if (mss <= 0)
+			return 0;
+	}
 	if (free_space < (full_space >> 1)) {
 		icsk->icsk_ack.quick = 0;
 
-- 
2.4.11


From 52177b11148dd7f5828fb9a1f7665bee7a5695e6 Mon Sep 17 00:00:00 2001
From: Alexey Brodkin <Alexey.Brodkin@synopsys.com>
Date: Fri, 27 Jan 2017 15:24:43 +0300
Subject: [PATCH 08/33] stmmac: Discard masked flags in interrupt status
 register

[ Upstream commit 0a764db103376cf69d04449b10688f3516cc0b88 ]

DW GMAC databook says the following about bits in "Register 15 (Interrupt
Mask Register)":
--------------------------->8-------------------------
When set, this bit __disables_the_assertion_of_the_interrupt_signal__
because of the setting of XXX bit in Register 14 (Interrupt
Status Register).
--------------------------->8-------------------------

In fact even if we mask one bit in the mask register it doesn't prevent
corresponding bit to appear in the status register, it only disables
interrupt generation for corresponding event.

But currently we expect a bit different behavior: status bits to be in
sync with their masks, i.e. if mask for bit A is set in the mask
register then bit A won't appear in the interrupt status register.

This was proven to be incorrect assumption, see discussion here [1].
That misunderstanding causes unexpected behaviour of the GMAC, for
example we were happy enough to just see bogus messages about link
state changes.

So from now on we'll be only checking bits that really may trigger an
interrupt.

[1] https://lkml.org/lkml/2016/11/3/413

Signed-off-by: Alexey Brodkin <abrodkin@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Fabrice Gasnier <fabrice.gasnier@st.com>
Cc: Joachim Eastwood <manabian@gmail.com>
Cc: Phil Reid <preid@electromag.com.au>
Cc: David Miller <davem@davemloft.net>
Cc: Alexandre Torgue <alexandre.torgue@gmail.com>
Cc: Vineet Gupta <vgupta@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
index 7df4ff1..7d19029 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
@@ -305,8 +305,12 @@ static int dwmac1000_irq_status(struct mac_device_info *hw,
 {
 	void __iomem *ioaddr = hw->pcsr;
 	u32 intr_status = readl(ioaddr + GMAC_INT_STATUS);
+	u32 intr_mask = readl(ioaddr + GMAC_INT_MASK);
 	int ret = 0;
 
+	/* Discard masked bits */
+	intr_status &= ~intr_mask;
+
 	/* Not used events (e.g. MMC interrupts) are not handled. */
 	if ((intr_status & GMAC_INT_STATUS_MMCTIS))
 		x->mmc_tx_irq_n++;
-- 
2.4.11


From 8c763c3d44ebd4ccc85a3e62b81a30309c38ba6f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 2 Feb 2017 10:31:35 -0800
Subject: [PATCH 09/33] net: use a work queue to defer net_disable_timestamp()
 work

[ Upstream commit 5fa8bbda38c668e56b0c6cdecced2eac2fe36dec ]

Dmitry reported a warning [1] showing that we were calling
net_disable_timestamp() -> static_key_slow_dec() from a non
process context.

Grabbing a mutex while holding a spinlock or rcu_read_lock()
is not allowed.

As Cong suggested, we now use a work queue.

It is possible netstamp_clear() exits while netstamp_needed_deferred
is not zero, but it is probably not worth trying to do better than that.

netstamp_needed_deferred atomic tracks the exact number of deferred
decrements.

[1]
[ INFO: suspicious RCU usage. ]
4.10.0-rc5+ #192 Not tainted
-------------------------------
./include/linux/rcupdate.h:561 Illegal context switch in RCU read-side
critical section!

other info that might help us debug this:

rcu_scheduler_active = 2, debug_locks = 0
2 locks held by syz-executor14/23111:
 #0:  (sk_lock-AF_INET6){+.+.+.}, at: [<ffffffff83a35c35>] lock_sock
include/net/sock.h:1454 [inline]
 #0:  (sk_lock-AF_INET6){+.+.+.}, at: [<ffffffff83a35c35>]
rawv6_sendmsg+0x1e65/0x3ec0 net/ipv6/raw.c:919
 #1:  (rcu_read_lock){......}, at: [<ffffffff83ae2678>] nf_hook
include/linux/netfilter.h:201 [inline]
 #1:  (rcu_read_lock){......}, at: [<ffffffff83ae2678>]
__ip6_local_out+0x258/0x840 net/ipv6/output_core.c:160

stack backtrace:
CPU: 2 PID: 23111 Comm: syz-executor14 Not tainted 4.10.0-rc5+ #192
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs
01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:15 [inline]
 dump_stack+0x2ee/0x3ef lib/dump_stack.c:51
 lockdep_rcu_suspicious+0x139/0x180 kernel/locking/lockdep.c:4452
 rcu_preempt_sleep_check include/linux/rcupdate.h:560 [inline]
 ___might_sleep+0x560/0x650 kernel/sched/core.c:7748
 __might_sleep+0x95/0x1a0 kernel/sched/core.c:7739
 mutex_lock_nested+0x24f/0x1730 kernel/locking/mutex.c:752
 atomic_dec_and_mutex_lock+0x119/0x160 kernel/locking/mutex.c:1060
 __static_key_slow_dec+0x7a/0x1e0 kernel/jump_label.c:149
 static_key_slow_dec+0x51/0x90 kernel/jump_label.c:174
 net_disable_timestamp+0x3b/0x50 net/core/dev.c:1728
 sock_disable_timestamp+0x98/0xc0 net/core/sock.c:403
 __sk_destruct+0x27d/0x6b0 net/core/sock.c:1441
 sk_destruct+0x47/0x80 net/core/sock.c:1460
 __sk_free+0x57/0x230 net/core/sock.c:1468
 sock_wfree+0xae/0x120 net/core/sock.c:1645
 skb_release_head_state+0xfc/0x200 net/core/skbuff.c:655
 skb_release_all+0x15/0x60 net/core/skbuff.c:668
 __kfree_skb+0x15/0x20 net/core/skbuff.c:684
 kfree_skb+0x16e/0x4c0 net/core/skbuff.c:705
 inet_frag_destroy+0x121/0x290 net/ipv4/inet_fragment.c:304
 inet_frag_put include/net/inet_frag.h:133 [inline]
 nf_ct_frag6_gather+0x1106/0x3840
net/ipv6/netfilter/nf_conntrack_reasm.c:617
 ipv6_defrag+0x1be/0x2b0 net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:68
 nf_hook_entry_hookfn include/linux/netfilter.h:102 [inline]
 nf_hook_slow+0xc3/0x290 net/netfilter/core.c:310
 nf_hook include/linux/netfilter.h:212 [inline]
 __ip6_local_out+0x489/0x840 net/ipv6/output_core.c:160
 ip6_local_out+0x2d/0x170 net/ipv6/output_core.c:170
 ip6_send_skb+0xa1/0x340 net/ipv6/ip6_output.c:1722
 ip6_push_pending_frames+0xb3/0xe0 net/ipv6/ip6_output.c:1742
 rawv6_push_pending_frames net/ipv6/raw.c:613 [inline]
 rawv6_sendmsg+0x2d1a/0x3ec0 net/ipv6/raw.c:927
 inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:744
 sock_sendmsg_nosec net/socket.c:635 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:645
 sock_write_iter+0x326/0x600 net/socket.c:848
 do_iter_readv_writev+0x2e3/0x5b0 fs/read_write.c:695
 do_readv_writev+0x42c/0x9b0 fs/read_write.c:872
 vfs_writev+0x87/0xc0 fs/read_write.c:911
 do_writev+0x110/0x2c0 fs/read_write.c:944
 SYSC_writev fs/read_write.c:1017 [inline]
 SyS_writev+0x27/0x30 fs/read_write.c:1014
 entry_SYSCALL_64_fastpath+0x1f/0xc2
RIP: 0033:0x445559
RSP: 002b:00007f6f46fceb58 EFLAGS: 00000292 ORIG_RAX: 0000000000000014
RAX: ffffffffffffffda RBX: 0000000000000005 RCX: 0000000000445559
RDX: 0000000000000001 RSI: 0000000020f1eff0 RDI: 0000000000000005
RBP: 00000000006e19c0 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000292 R12: 0000000000700000
R13: 0000000020f59000 R14: 0000000000000015 R15: 0000000000020400
BUG: sleeping function called from invalid context at
kernel/locking/mutex.c:752
in_atomic(): 1, irqs_disabled(): 0, pid: 23111, name: syz-executor14
INFO: lockdep is turned off.
CPU: 2 PID: 23111 Comm: syz-executor14 Not tainted 4.10.0-rc5+ #192
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs
01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:15 [inline]
 dump_stack+0x2ee/0x3ef lib/dump_stack.c:51
 ___might_sleep+0x47e/0x650 kernel/sched/core.c:7780
 __might_sleep+0x95/0x1a0 kernel/sched/core.c:7739
 mutex_lock_nested+0x24f/0x1730 kernel/locking/mutex.c:752
 atomic_dec_and_mutex_lock+0x119/0x160 kernel/locking/mutex.c:1060
 __static_key_slow_dec+0x7a/0x1e0 kernel/jump_label.c:149
 static_key_slow_dec+0x51/0x90 kernel/jump_label.c:174
 net_disable_timestamp+0x3b/0x50 net/core/dev.c:1728
 sock_disable_timestamp+0x98/0xc0 net/core/sock.c:403
 __sk_destruct+0x27d/0x6b0 net/core/sock.c:1441
 sk_destruct+0x47/0x80 net/core/sock.c:1460
 __sk_free+0x57/0x230 net/core/sock.c:1468
 sock_wfree+0xae/0x120 net/core/sock.c:1645
 skb_release_head_state+0xfc/0x200 net/core/skbuff.c:655
 skb_release_all+0x15/0x60 net/core/skbuff.c:668
 __kfree_skb+0x15/0x20 net/core/skbuff.c:684
 kfree_skb+0x16e/0x4c0 net/core/skbuff.c:705
 inet_frag_destroy+0x121/0x290 net/ipv4/inet_fragment.c:304
 inet_frag_put include/net/inet_frag.h:133 [inline]
 nf_ct_frag6_gather+0x1106/0x3840
net/ipv6/netfilter/nf_conntrack_reasm.c:617
 ipv6_defrag+0x1be/0x2b0 net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:68
 nf_hook_entry_hookfn include/linux/netfilter.h:102 [inline]
 nf_hook_slow+0xc3/0x290 net/netfilter/core.c:310
 nf_hook include/linux/netfilter.h:212 [inline]
 __ip6_local_out+0x489/0x840 net/ipv6/output_core.c:160
 ip6_local_out+0x2d/0x170 net/ipv6/output_core.c:170
 ip6_send_skb+0xa1/0x340 net/ipv6/ip6_output.c:1722
 ip6_push_pending_frames+0xb3/0xe0 net/ipv6/ip6_output.c:1742
 rawv6_push_pending_frames net/ipv6/raw.c:613 [inline]
 rawv6_sendmsg+0x2d1a/0x3ec0 net/ipv6/raw.c:927
 inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:744
 sock_sendmsg_nosec net/socket.c:635 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:645
 sock_write_iter+0x326/0x600 net/socket.c:848
 do_iter_readv_writev+0x2e3/0x5b0 fs/read_write.c:695
 do_readv_writev+0x42c/0x9b0 fs/read_write.c:872
 vfs_writev+0x87/0xc0 fs/read_write.c:911
 do_writev+0x110/0x2c0 fs/read_write.c:944
 SYSC_writev fs/read_write.c:1017 [inline]
 SyS_writev+0x27/0x30 fs/read_write.c:1014
 entry_SYSCALL_64_fastpath+0x1f/0xc2
RIP: 0033:0x445559

Fixes: b90e5794c5bd ("net: dont call jump_label_dec from irq context")
Suggested-by: Cong Wang <xiyou.wangcong@gmail.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 31 +++++++++++++------------------
 1 file changed, 13 insertions(+), 18 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index df51c50..60b0a604 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1696,24 +1696,19 @@ EXPORT_SYMBOL_GPL(net_dec_egress_queue);
 
 static struct static_key netstamp_needed __read_mostly;
 #ifdef HAVE_JUMP_LABEL
-/* We are not allowed to call static_key_slow_dec() from irq context
- * If net_disable_timestamp() is called from irq context, defer the
- * static_key_slow_dec() calls.
- */
 static atomic_t netstamp_needed_deferred;
-#endif
-
-void net_enable_timestamp(void)
+static void netstamp_clear(struct work_struct *work)
 {
-#ifdef HAVE_JUMP_LABEL
 	int deferred = atomic_xchg(&netstamp_needed_deferred, 0);
 
-	if (deferred) {
-		while (--deferred)
-			static_key_slow_dec(&netstamp_needed);
-		return;
-	}
+	while (deferred--)
+		static_key_slow_dec(&netstamp_needed);
+}
+static DECLARE_WORK(netstamp_work, netstamp_clear);
 #endif
+
+void net_enable_timestamp(void)
+{
 	static_key_slow_inc(&netstamp_needed);
 }
 EXPORT_SYMBOL(net_enable_timestamp);
@@ -1721,12 +1716,12 @@ EXPORT_SYMBOL(net_enable_timestamp);
 void net_disable_timestamp(void)
 {
 #ifdef HAVE_JUMP_LABEL
-	if (in_interrupt()) {
-		atomic_inc(&netstamp_needed_deferred);
-		return;
-	}
-#endif
+	/* net_disable_timestamp() can be called from non process context */
+	atomic_inc(&netstamp_needed_deferred);
+	schedule_work(&netstamp_work);
+#else
 	static_key_slow_dec(&netstamp_needed);
+#endif
 }
 EXPORT_SYMBOL(net_disable_timestamp);
 
-- 
2.4.11


From f314dc59c5f6e849ed7655052f09e3dd023f2bbd Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 4 Feb 2017 11:16:52 -0800
Subject: [PATCH 10/33] ipv4: keep skb->dst around in presence of IP options

[ Upstream commit 34b2cef20f19c87999fff3da4071e66937db9644 ]

Andrey Konovalov got crashes in __ip_options_echo() when a NULL skb->dst
is accessed.

ipv4_pktinfo_prepare() should not drop the dst if (evil) IP options
are present.

We could refine the test to the presence of ts_needtime or srr,
but IP options are not often used, so let's be conservative.

Thanks to syzkaller team for finding this bug.

Fixes: d826eb14ecef ("ipv4: PKTINFO doesnt need dst reference")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_sockglue.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index f226f408..65336f3 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1215,7 +1215,14 @@ void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb)
 		pktinfo->ipi_ifindex = 0;
 		pktinfo->ipi_spec_dst.s_addr = 0;
 	}
-	skb_dst_drop(skb);
+	/* We need to keep the dst for __ip_options_echo()
+	 * We could restrict the test to opt.ts_needtime || opt.srr,
+	 * but the following is good enough as IP options are not often used.
+	 */
+	if (unlikely(IPCB(skb)->opt.optlen))
+		skb_dst_force(skb);
+	else
+		skb_dst_drop(skb);
 }
 
 int ip_setsockopt(struct sock *sk, int level,
-- 
2.4.11


From be28263024389f27e935aa51d3b6062c4707cb78 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 3 Feb 2017 00:03:26 -0800
Subject: [PATCH 11/33] netlabel: out of bound access in cipso_v4_validate()

[ Upstream commit d71b7896886345c53ef1d84bda2bc758554f5d61 ]

syzkaller found another out of bound access in ip_options_compile(),
or more exactly in cipso_v4_validate()

Fixes: 20e2a8648596 ("cipso: handle CIPSO options correctly when NetLabel is disabled")
Fixes: 446fda4f2682 ("[NetLabel]: CIPSOv4 engine")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov  <dvyukov@google.com>
Cc: Paul Moore <paul@paul-moore.com>
Acked-by: Paul Moore <paul@paul-moore.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/cipso_ipv4.h | 4 ++++
 net/ipv4/cipso_ipv4.c    | 4 ++++
 2 files changed, 8 insertions(+)

diff --git a/include/net/cipso_ipv4.h b/include/net/cipso_ipv4.h
index 3ebb168..a34b141 100644
--- a/include/net/cipso_ipv4.h
+++ b/include/net/cipso_ipv4.h
@@ -309,6 +309,10 @@ static inline int cipso_v4_validate(const struct sk_buff *skb,
 	}
 
 	for (opt_iter = 6; opt_iter < opt_len;) {
+		if (opt_iter + 1 == opt_len) {
+			err_offset = opt_iter;
+			goto out;
+		}
 		tag_len = opt[opt_iter + 1];
 		if ((tag_len == 0) || (tag_len > (opt_len - opt_iter))) {
 			err_offset = opt_iter + 1;
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 72d6f05..ae20616 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -1587,6 +1587,10 @@ int cipso_v4_validate(const struct sk_buff *skb, unsigned char **option)
 				goto validate_return_locked;
 			}
 
+		if (opt_iter + 1 == opt_len) {
+			err_offset = opt_iter;
+			goto validate_return_locked;
+		}
 		tag_len = tag[1];
 		if (tag_len > (opt_len - opt_iter)) {
 			err_offset = opt_iter + 1;
-- 
2.4.11


From 56724975787ec4ea5d5c196223672ae491a9118b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 4 Feb 2017 23:18:55 -0800
Subject: [PATCH 12/33] ip6_gre: fix ip6gre_err() invalid reads

[ Upstream commit 7892032cfe67f4bde6fc2ee967e45a8fbaf33756 ]

Andrey Konovalov reported out of bound accesses in ip6gre_err()

If GRE flags contains GRE_KEY, the following expression
*(((__be32 *)p) + (grehlen / 4) - 1)

accesses data ~40 bytes after the expected point, since
grehlen includes the size of IPv6 headers.

Let's use a "struct gre_base_hdr *greh" pointer to make this
code more readable.

p[1] becomes greh->protocol.
grhlen is the GRE header length.

Fixes: c12b395a4664 ("gre: Support GRE over IPv6")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 40 +++++++++++++++++++++-------------------
 1 file changed, 21 insertions(+), 19 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index d7d6d3a..0a59220 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -367,35 +367,37 @@ static void ip6gre_tunnel_uninit(struct net_device *dev)
 
 
 static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
-		u8 type, u8 code, int offset, __be32 info)
+		       u8 type, u8 code, int offset, __be32 info)
 {
-	const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)skb->data;
-	__be16 *p = (__be16 *)(skb->data + offset);
-	int grehlen = offset + 4;
+	const struct gre_base_hdr *greh;
+	const struct ipv6hdr *ipv6h;
+	int grehlen = sizeof(*greh);
 	struct ip6_tnl *t;
+	int key_off = 0;
 	__be16 flags;
+	__be32 key;
 
-	flags = p[0];
-	if (flags&(GRE_CSUM|GRE_KEY|GRE_SEQ|GRE_ROUTING|GRE_VERSION)) {
-		if (flags&(GRE_VERSION|GRE_ROUTING))
-			return;
-		if (flags&GRE_KEY) {
-			grehlen += 4;
-			if (flags&GRE_CSUM)
-				grehlen += 4;
-		}
+	if (!pskb_may_pull(skb, offset + grehlen))
+		return;
+	greh = (const struct gre_base_hdr *)(skb->data + offset);
+	flags = greh->flags;
+	if (flags & (GRE_VERSION | GRE_ROUTING))
+		return;
+	if (flags & GRE_CSUM)
+		grehlen += 4;
+	if (flags & GRE_KEY) {
+		key_off = grehlen + offset;
+		grehlen += 4;
 	}
 
-	/* If only 8 bytes returned, keyed message will be dropped here */
-	if (!pskb_may_pull(skb, grehlen))
+	if (!pskb_may_pull(skb, offset + grehlen))
 		return;
 	ipv6h = (const struct ipv6hdr *)skb->data;
-	p = (__be16 *)(skb->data + offset);
+	greh = (const struct gre_base_hdr *)(skb->data + offset);
+	key = key_off ? *(__be32 *)(skb->data + key_off) : 0;
 
 	t = ip6gre_tunnel_lookup(skb->dev, &ipv6h->daddr, &ipv6h->saddr,
-				flags & GRE_KEY ?
-				*(((__be32 *)p) + (grehlen / 4) - 1) : 0,
-				p[1]);
+				 key, greh->protocol);
 	if (!t)
 		return;
 
-- 
2.4.11


From 4dd7e112665643ad01aa1bf0617eb1f5b3bba42f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 5 Feb 2017 20:23:22 -0800
Subject: [PATCH 13/33] ipv6: tcp: add a missing tcp_v6_restore_cb()

[ Upstream commit ebf6c9cb23d7e56eec8575a88071dec97ad5c6e2 ]

Dmitry reported use-after-free in ip6_datagram_recv_specific_ctl()

A similar bug was fixed in commit 8ce48623f0cf ("ipv6: tcp: restore
IP6CB for pktoptions skbs"), but I missed another spot.

tcp_v6_syn_recv_sock() can indeed set np->pktoptions from ireq->pktopts

Fixes: 971f10eca186 ("tcp: better TCP_SKB_CB layout to reduce cache line misses")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/tcp_ipv6.c | 24 +++++++++++++-----------
 1 file changed, 13 insertions(+), 11 deletions(-)

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index b9f1fee..e5ee107 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -987,6 +987,16 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 	return 0; /* don't send reset */
 }
 
+static void tcp_v6_restore_cb(struct sk_buff *skb)
+{
+	/* We need to move header back to the beginning if xfrm6_policy_check()
+	 * and tcp_v6_fill_cb() are going to be called again.
+	 * ip6_datagram_recv_specific_ctl() also expects IP6CB to be there.
+	 */
+	memmove(IP6CB(skb), &TCP_SKB_CB(skb)->header.h6,
+		sizeof(struct inet6_skb_parm));
+}
+
 static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 					 struct request_sock *req,
 					 struct dst_entry *dst,
@@ -1178,8 +1188,10 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 						      sk_gfp_mask(sk, GFP_ATOMIC));
 			consume_skb(ireq->pktopts);
 			ireq->pktopts = NULL;
-			if (newnp->pktoptions)
+			if (newnp->pktoptions) {
+				tcp_v6_restore_cb(newnp->pktoptions);
 				skb_set_owner_r(newnp->pktoptions, newsk);
+			}
 		}
 	}
 
@@ -1194,16 +1206,6 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 	return NULL;
 }
 
-static void tcp_v6_restore_cb(struct sk_buff *skb)
-{
-	/* We need to move header back to the beginning if xfrm6_policy_check()
-	 * and tcp_v6_fill_cb() are going to be called again.
-	 * ip6_datagram_recv_specific_ctl() also expects IP6CB to be there.
-	 */
-	memmove(IP6CB(skb), &TCP_SKB_CB(skb)->header.h6,
-		sizeof(struct inet6_skb_parm));
-}
-
 /* The socket must have it's spinlock held when we get
  * here, unless it is a TCP_LISTEN socket.
  *
-- 
2.4.11


From 2a01ed7eca9e4ead319695f501de994a761b88e3 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 3 Feb 2017 17:35:46 +0100
Subject: [PATCH 14/33] hns: avoid stack overflow with CONFIG_KASAN

[ Upstream commit b3f2d07f4649adcf6905953a10d217b5683e4077 ]

The use of ACCESS_ONCE() looks like a micro-optimization to force gcc to use
an indexed load for the register address, but it has an absolutely detrimental
effect on builds with gcc-5 and CONFIG_KASAN=y, leading to a very likely
kernel stack overflow aside from very complex object code:

hisilicon/hns/hns_dsaf_gmac.c: In function 'hns_gmac_update_stats':
hisilicon/hns/hns_dsaf_gmac.c:419:1: error: the frame size of 2912 bytes is larger than 1024 bytes [-Werror=frame-larger-than=]
hisilicon/hns/hns_dsaf_ppe.c: In function 'hns_ppe_reset_common':
hisilicon/hns/hns_dsaf_ppe.c:390:1: error: the frame size of 1184 bytes is larger than 1024 bytes [-Werror=frame-larger-than=]
hisilicon/hns/hns_dsaf_ppe.c: In function 'hns_ppe_get_regs':
hisilicon/hns/hns_dsaf_ppe.c:621:1: error: the frame size of 3632 bytes is larger than 1024 bytes [-Werror=frame-larger-than=]
hisilicon/hns/hns_dsaf_rcb.c: In function 'hns_rcb_get_common_regs':
hisilicon/hns/hns_dsaf_rcb.c:970:1: error: the frame size of 2784 bytes is larger than 1024 bytes [-Werror=frame-larger-than=]
hisilicon/hns/hns_dsaf_gmac.c: In function 'hns_gmac_get_regs':
hisilicon/hns/hns_dsaf_gmac.c:641:1: error: the frame size of 5728 bytes is larger than 1024 bytes [-Werror=frame-larger-than=]
hisilicon/hns/hns_dsaf_rcb.c: In function 'hns_rcb_get_ring_regs':
hisilicon/hns/hns_dsaf_rcb.c:1021:1: error: the frame size of 2208 bytes is larger than 1024 bytes [-Werror=frame-larger-than=]
hisilicon/hns/hns_dsaf_main.c: In function 'hns_dsaf_comm_init':
hisilicon/hns/hns_dsaf_main.c:1209:1: error: the frame size of 1904 bytes is larger than 1024 bytes [-Werror=frame-larger-than=]
hisilicon/hns/hns_dsaf_xgmac.c: In function 'hns_xgmac_get_regs':
hisilicon/hns/hns_dsaf_xgmac.c:748:1: error: the frame size of 4704 bytes is larger than 1024 bytes [-Werror=frame-larger-than=]
hisilicon/hns/hns_dsaf_main.c: In function 'hns_dsaf_update_stats':
hisilicon/hns/hns_dsaf_main.c:2420:1: error: the frame size of 1088 bytes is larger than 1024 bytes [-Werror=frame-larger-than=]
hisilicon/hns/hns_dsaf_main.c: In function 'hns_dsaf_get_regs':
hisilicon/hns/hns_dsaf_main.c:2753:1: error: the frame size of 10768 bytes is larger than 1024 bytes [-Werror=frame-larger-than=]

This does not seem to happen any more with gcc-7, but removing the ACCESS_ONCE
seems safe anyway and it avoids a serious issue for some people. I have verified
that with gcc-5.3.1, the object code we get is better in the new version
both with and without CONFIG_KASAN, as we no longer allocate a 1344 byte
stack frame for hns_dsaf_get_regs() but otherwise have practically identical
object code.

With gcc-7.0.0, removing ACCESS_ONCE has no effect, the object code is already
good either way.

This patch is probably not urgent to get into 4.11 as only KASAN=y builds
with certain compilers are affected, but I still think it makes sense to
backport into older kernels.

Cc: stable@vger.kernel.org
Fixes: 511e6bc ("net: add Hisilicon Network Subsystem DSAF support")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
index 878950a..2cf8b1d 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
@@ -1007,9 +1007,7 @@
 
 static inline void dsaf_write_reg(void __iomem *base, u32 reg, u32 value)
 {
-	u8 __iomem *reg_addr = ACCESS_ONCE(base);
-
-	writel(value, reg_addr + reg);
+	writel(value, base + reg);
 }
 
 #define dsaf_write_dev(a, reg, value) \
@@ -1017,9 +1015,7 @@ static inline void dsaf_write_reg(void __iomem *base, u32 reg, u32 value)
 
 static inline u32 dsaf_read_reg(u8 __iomem *base, u32 reg)
 {
-	u8 __iomem *reg_addr = ACCESS_ONCE(base);
-
-	return readl(reg_addr + reg);
+	return readl(base + reg);
 }
 
 static inline void dsaf_write_syscon(struct regmap *base, u32 reg, u32 value)
-- 
2.4.11


From e773367ec23c975f54d84ef8accac72a1930359f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 3 Feb 2017 14:59:38 -0800
Subject: [PATCH 15/33] tcp: avoid infinite loop in tcp_splice_read()

[ Upstream commit ccf7abb93af09ad0868ae9033d1ca8108bdaec82 ]

Splicing from TCP socket is vulnerable when a packet with URG flag is
received and stored into receive queue.

__tcp_splice_read() returns 0, and sk_wait_data() immediately
returns since there is the problematic skb in queue.

This is a nice way to burn cpu (aka infinite loop) and trigger
soft lockups.

Again, this gem was found by syzkaller tool.

Fixes: 9c55e01c0cc8 ("[TCP]: Splice receive support.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov  <dvyukov@google.com>
Cc: Willy Tarreau <w@1wt.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 814af89..6a90a0e 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -772,6 +772,12 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
 				ret = -EAGAIN;
 				break;
 			}
+			/* if __tcp_splice_read() got nothing while we have
+			 * an skb in receive queue, we do not want to loop.
+			 * This might happen with URG data.
+			 */
+			if (!skb_queue_empty(&sk->sk_receive_queue))
+				break;
 			sk_wait_data(sk, &timeo, NULL);
 			if (signal_pending(current)) {
 				ret = sock_intr_errno(timeo);
-- 
2.4.11


From c94644f25ccf2a5a550baaa48aafa1603fe244fe Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 3 Feb 2017 18:20:48 -0500
Subject: [PATCH 16/33] tun: read vnet_hdr_sz once

[ Upstream commit e1edab87faf6ca30cd137e0795bc73aa9a9a22ec ]

When IFF_VNET_HDR is enabled, a virtio_net header must precede data.
Data length is verified to be greater than or equal to expected header
length tun->vnet_hdr_sz before copying.

Read this value once and cache locally, as it can be updated between
the test and use (TOCTOU).

Signed-off-by: Willem de Bruijn <willemb@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
CC: Eric Dumazet <edumazet@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 18402d7..b31aca8 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1187,9 +1187,11 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	}
 
 	if (tun->flags & IFF_VNET_HDR) {
-		if (len < tun->vnet_hdr_sz)
+		int vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz);
+
+		if (len < vnet_hdr_sz)
 			return -EINVAL;
-		len -= tun->vnet_hdr_sz;
+		len -= vnet_hdr_sz;
 
 		n = copy_from_iter(&gso, sizeof(gso), from);
 		if (n != sizeof(gso))
@@ -1201,7 +1203,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 
 		if (tun16_to_cpu(tun, gso.hdr_len) > len)
 			return -EINVAL;
-		iov_iter_advance(from, tun->vnet_hdr_sz - sizeof(gso));
+		iov_iter_advance(from, vnet_hdr_sz - sizeof(gso));
 	}
 
 	if ((tun->flags & TUN_TYPE_MASK) == IFF_TAP) {
@@ -1348,7 +1350,7 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 		vlan_hlen = VLAN_HLEN;
 
 	if (tun->flags & IFF_VNET_HDR)
-		vnet_hdr_sz = tun->vnet_hdr_sz;
+		vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz);
 
 	total = skb->len + vlan_hlen + vnet_hdr_sz;
 
-- 
2.4.11


From 9aa6614af6f48685354bfa8a4536290071e2ef57 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 3 Feb 2017 18:20:49 -0500
Subject: [PATCH 17/33] macvtap: read vnet_hdr_size once

[ Upstream commit 837585a5375c38d40361cfe64e6fd11e1addb936 ]

When IFF_VNET_HDR is enabled, a virtio_net header must precede data.
Data length is verified to be greater than or equal to expected header
length tun->vnet_hdr_sz before copying.

Macvtap functions read the value once, but unless READ_ONCE is used,
the compiler may ignore this and read multiple times. Enforce a single
read and locally cached value to avoid updates between test and use.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Suggested-by: Eric Dumazet <edumazet@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macvtap.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 6f38daf..adea6f5 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -682,7 +682,7 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 	ssize_t n;
 
 	if (q->flags & IFF_VNET_HDR) {
-		vnet_hdr_len = q->vnet_hdr_sz;
+		vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz);
 
 		err = -EINVAL;
 		if (len < vnet_hdr_len)
@@ -822,7 +822,7 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q,
 
 	if (q->flags & IFF_VNET_HDR) {
 		struct virtio_net_hdr vnet_hdr;
-		vnet_hdr_len = q->vnet_hdr_sz;
+		vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz);
 		if (iov_iter_count(iter) < vnet_hdr_len)
 			return -EINVAL;
 
-- 
2.4.11


From 34d8303e508cafaf604760c5769467f10881668d Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben@decadent.org.uk>
Date: Sat, 4 Feb 2017 16:56:03 +0000
Subject: [PATCH 18/33] pegasus: Use heap buffers for all register access
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 5593523f968bc86d42a035c6df47d5e0979b5ace ]

Allocating USB buffers on the stack is not portable, and no longer
works on x86_64 (with VMAP_STACK enabled as per default).

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
References: https://bugs.debian.org/852556
Reported-by: Lisandro Damián Nicanor Pérez Meyer <lisandro@debian.org>
Tested-by: Lisandro Damián Nicanor Pérez Meyer <lisandro@debian.org>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/pegasus.c | 29 +++++++++++++++++++++++++----
 1 file changed, 25 insertions(+), 4 deletions(-)

diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c
index 1434e5d..ee40ac2 100644
--- a/drivers/net/usb/pegasus.c
+++ b/drivers/net/usb/pegasus.c
@@ -126,40 +126,61 @@ static void async_ctrl_callback(struct urb *urb)
 
 static int get_registers(pegasus_t *pegasus, __u16 indx, __u16 size, void *data)
 {
+	u8 *buf;
 	int ret;
 
+	buf = kmalloc(size, GFP_NOIO);
+	if (!buf)
+		return -ENOMEM;
+
 	ret = usb_control_msg(pegasus->usb, usb_rcvctrlpipe(pegasus->usb, 0),
 			      PEGASUS_REQ_GET_REGS, PEGASUS_REQT_READ, 0,
-			      indx, data, size, 1000);
+			      indx, buf, size, 1000);
 	if (ret < 0)
 		netif_dbg(pegasus, drv, pegasus->net,
 			  "%s returned %d\n", __func__, ret);
+	else if (ret <= size)
+		memcpy(data, buf, ret);
+	kfree(buf);
 	return ret;
 }
 
-static int set_registers(pegasus_t *pegasus, __u16 indx, __u16 size, void *data)
+static int set_registers(pegasus_t *pegasus, __u16 indx, __u16 size,
+			 const void *data)
 {
+	u8 *buf;
 	int ret;
 
+	buf = kmemdup(data, size, GFP_NOIO);
+	if (!buf)
+		return -ENOMEM;
+
 	ret = usb_control_msg(pegasus->usb, usb_sndctrlpipe(pegasus->usb, 0),
 			      PEGASUS_REQ_SET_REGS, PEGASUS_REQT_WRITE, 0,
-			      indx, data, size, 100);
+			      indx, buf, size, 100);
 	if (ret < 0)
 		netif_dbg(pegasus, drv, pegasus->net,
 			  "%s returned %d\n", __func__, ret);
+	kfree(buf);
 	return ret;
 }
 
 static int set_register(pegasus_t *pegasus, __u16 indx, __u8 data)
 {
+	u8 *buf;
 	int ret;
 
+	buf = kmemdup(&data, 1, GFP_NOIO);
+	if (!buf)
+		return -ENOMEM;
+
 	ret = usb_control_msg(pegasus->usb, usb_sndctrlpipe(pegasus->usb, 0),
 			      PEGASUS_REQ_SET_REG, PEGASUS_REQT_WRITE, data,
-			      indx, &data, 1, 1000);
+			      indx, buf, 1, 1000);
 	if (ret < 0)
 		netif_dbg(pegasus, drv, pegasus->net,
 			  "%s returned %d\n", __func__, ret);
+	kfree(buf);
 	return ret;
 }
 
-- 
2.4.11


From 549a0052a0a398f576bc597437f8fcfeae795845 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben@decadent.org.uk>
Date: Sat, 4 Feb 2017 16:56:32 +0000
Subject: [PATCH 19/33] rtl8150: Use heap buffers for all register access

[ Upstream commit 7926aff5c57b577ab0f43364ff0c59d968f6a414 ]

Allocating USB buffers on the stack is not portable, and no longer
works on x86_64 (with VMAP_STACK enabled as per default).

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/rtl8150.c | 34 +++++++++++++++++++++++++++-------
 1 file changed, 27 insertions(+), 7 deletions(-)

diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c
index 7c72bfa..dc4f7ea 100644
--- a/drivers/net/usb/rtl8150.c
+++ b/drivers/net/usb/rtl8150.c
@@ -155,16 +155,36 @@ static const char driver_name [] = "rtl8150";
 */
 static int get_registers(rtl8150_t * dev, u16 indx, u16 size, void *data)
 {
-	return usb_control_msg(dev->udev, usb_rcvctrlpipe(dev->udev, 0),
-			       RTL8150_REQ_GET_REGS, RTL8150_REQT_READ,
-			       indx, 0, data, size, 500);
+	void *buf;
+	int ret;
+
+	buf = kmalloc(size, GFP_NOIO);
+	if (!buf)
+		return -ENOMEM;
+
+	ret = usb_control_msg(dev->udev, usb_rcvctrlpipe(dev->udev, 0),
+			      RTL8150_REQ_GET_REGS, RTL8150_REQT_READ,
+			      indx, 0, buf, size, 500);
+	if (ret > 0 && ret <= size)
+		memcpy(data, buf, ret);
+	kfree(buf);
+	return ret;
 }
 
-static int set_registers(rtl8150_t * dev, u16 indx, u16 size, void *data)
+static int set_registers(rtl8150_t * dev, u16 indx, u16 size, const void *data)
 {
-	return usb_control_msg(dev->udev, usb_sndctrlpipe(dev->udev, 0),
-			       RTL8150_REQ_SET_REGS, RTL8150_REQT_WRITE,
-			       indx, 0, data, size, 500);
+	void *buf;
+	int ret;
+
+	buf = kmemdup(data, size, GFP_NOIO);
+	if (!buf)
+		return -ENOMEM;
+
+	ret = usb_control_msg(dev->udev, usb_sndctrlpipe(dev->udev, 0),
+			      RTL8150_REQ_SET_REGS, RTL8150_REQT_WRITE,
+			      indx, 0, buf, size, 500);
+	kfree(buf);
+	return ret;
 }
 
 static void async_set_reg_cb(struct urb *urb)
-- 
2.4.11


From 712b05ed601ebbd127cb1972871c0c475ae15fbc Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben@decadent.org.uk>
Date: Sat, 4 Feb 2017 16:56:56 +0000
Subject: [PATCH 20/33] catc: Combine failure cleanup code in catc_probe()

[ Upstream commit d41149145f98fe26dcd0bfd1d6cc095e6e041418 ]

Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/catc.c | 33 +++++++++++++++++----------------
 1 file changed, 17 insertions(+), 16 deletions(-)

diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c
index d9ca05d..5ce84c9 100644
--- a/drivers/net/usb/catc.c
+++ b/drivers/net/usb/catc.c
@@ -777,7 +777,7 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id
 	struct net_device *netdev;
 	struct catc *catc;
 	u8 broadcast[ETH_ALEN];
-	int i, pktsz;
+	int i, pktsz, ret;
 
 	if (usb_set_interface(usbdev,
 			intf->altsetting->desc.bInterfaceNumber, 1)) {
@@ -812,12 +812,8 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id
 	if ((!catc->ctrl_urb) || (!catc->tx_urb) || 
 	    (!catc->rx_urb) || (!catc->irq_urb)) {
 		dev_err(&intf->dev, "No free urbs available.\n");
-		usb_free_urb(catc->ctrl_urb);
-		usb_free_urb(catc->tx_urb);
-		usb_free_urb(catc->rx_urb);
-		usb_free_urb(catc->irq_urb);
-		free_netdev(netdev);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto fail_free;
 	}
 
 	/* The F5U011 has the same vendor/product as the netmate but a device version of 0x130 */
@@ -914,16 +910,21 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id
 	usb_set_intfdata(intf, catc);
 
 	SET_NETDEV_DEV(netdev, &intf->dev);
-	if (register_netdev(netdev) != 0) {
-		usb_set_intfdata(intf, NULL);
-		usb_free_urb(catc->ctrl_urb);
-		usb_free_urb(catc->tx_urb);
-		usb_free_urb(catc->rx_urb);
-		usb_free_urb(catc->irq_urb);
-		free_netdev(netdev);
-		return -EIO;
-	}
+	ret = register_netdev(netdev);
+	if (ret)
+		goto fail_clear_intfdata;
+
 	return 0;
+
+fail_clear_intfdata:
+	usb_set_intfdata(intf, NULL);
+fail_free:
+	usb_free_urb(catc->ctrl_urb);
+	usb_free_urb(catc->tx_urb);
+	usb_free_urb(catc->rx_urb);
+	usb_free_urb(catc->irq_urb);
+	free_netdev(netdev);
+	return ret;
 }
 
 static void catc_disconnect(struct usb_interface *intf)
-- 
2.4.11


From 07faa409dd4ab29ac09cdda8c8864015da2f5d38 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben@decadent.org.uk>
Date: Sat, 4 Feb 2017 16:57:04 +0000
Subject: [PATCH 21/33] catc: Use heap buffer for memory size test

[ Upstream commit 2d6a0e9de03ee658a9adc3bfb2f0ca55dff1e478 ]

Allocating USB buffers on the stack is not portable, and no longer
works on x86_64 (with VMAP_STACK enabled as per default).

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/catc.c | 25 ++++++++++++++++++-------
 1 file changed, 18 insertions(+), 7 deletions(-)

diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c
index 5ce84c9..4086415 100644
--- a/drivers/net/usb/catc.c
+++ b/drivers/net/usb/catc.c
@@ -777,7 +777,7 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id
 	struct net_device *netdev;
 	struct catc *catc;
 	u8 broadcast[ETH_ALEN];
-	int i, pktsz, ret;
+	int pktsz, ret;
 
 	if (usb_set_interface(usbdev,
 			intf->altsetting->desc.bInterfaceNumber, 1)) {
@@ -841,15 +841,24 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id
                 catc->irq_buf, 2, catc_irq_done, catc, 1);
 
 	if (!catc->is_f5u011) {
+		u32 *buf;
+		int i;
+
 		dev_dbg(dev, "Checking memory size\n");
 
-		i = 0x12345678;
-		catc_write_mem(catc, 0x7a80, &i, 4);
-		i = 0x87654321;	
-		catc_write_mem(catc, 0xfa80, &i, 4);
-		catc_read_mem(catc, 0x7a80, &i, 4);
+		buf = kmalloc(4, GFP_KERNEL);
+		if (!buf) {
+			ret = -ENOMEM;
+			goto fail_free;
+		}
+
+		*buf = 0x12345678;
+		catc_write_mem(catc, 0x7a80, buf, 4);
+		*buf = 0x87654321;
+		catc_write_mem(catc, 0xfa80, buf, 4);
+		catc_read_mem(catc, 0x7a80, buf, 4);
 	  
-		switch (i) {
+		switch (*buf) {
 		case 0x12345678:
 			catc_set_reg(catc, TxBufCount, 8);
 			catc_set_reg(catc, RxBufCount, 32);
@@ -864,6 +873,8 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id
 			dev_dbg(dev, "32k Memory\n");
 			break;
 		}
+
+		kfree(buf);
 	  
 		dev_dbg(dev, "Getting MAC from SEEROM.\n");
 	  
-- 
2.4.11


From 129b94f66609799e8ca2c13a1a74e3d50607a794 Mon Sep 17 00:00:00 2001
From: Benjamin Poirier <bpoirier@suse.com>
Date: Mon, 6 Feb 2017 10:14:31 -0800
Subject: [PATCH 22/33] mlx4: Invoke softirqs after napi_reschedule

[ Upstream commit bd4ce941c8d5b862b2f83364be5dbe8fc8ab48f8 ]

mlx4 may schedule napi from a workqueue. Afterwards, softirqs are not run
in a deterministic time frame and the following message may be logged:
NOHZ: local_softirq_pending 08

The problem is the same as what was described in commit ec13ee80145c
("virtio_net: invoke softirqs after __napi_schedule") and this patch
applies the same fix to mlx4.

Fixes: 07841f9d94c1 ("net/mlx4_en: Schedule napi when RX buffers allocation fails")
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Benjamin Poirier <bpoirier@suse.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_rx.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index f2e8bed..4d3ddc2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -507,8 +507,11 @@ void mlx4_en_recover_from_oom(struct mlx4_en_priv *priv)
 		return;
 
 	for (ring = 0; ring < priv->rx_ring_num; ring++) {
-		if (mlx4_en_is_ring_empty(priv->rx_ring[ring]))
+		if (mlx4_en_is_ring_empty(priv->rx_ring[ring])) {
+			local_bh_disable();
 			napi_reschedule(&priv->rx_cq[ring]->napi);
+			local_bh_enable();
+		}
 	}
 }
 
-- 
2.4.11


From 68fe5fd5e739457962892253ae28c29346761032 Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Mon, 6 Feb 2017 18:10:31 -0200
Subject: [PATCH 23/33] sctp: avoid BUG_ON on sctp_wait_for_sndbuf

[ Upstream commit 2dcab598484185dea7ec22219c76dcdd59e3cb90 ]

Alexander Popov reported that an application may trigger a BUG_ON in
sctp_wait_for_sndbuf if the socket tx buffer is full, a thread is
waiting on it to queue more data and meanwhile another thread peels off
the association being used by the first thread.

This patch replaces the BUG_ON call with a proper error handling. It
will return -EPIPE to the original sendmsg call, similarly to what would
have been done if the association wasn't found in the first place.

Acked-by: Alexander Popov <alex.popov@linux.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index ca12aa3..6cbe5bd 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -7427,7 +7427,8 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p,
 		 */
 		release_sock(sk);
 		current_timeo = schedule_timeout(current_timeo);
-		BUG_ON(sk != asoc->base.sk);
+		if (sk != asoc->base.sk)
+			goto do_error;
 		lock_sock(sk);
 
 		*timeo_p = current_timeo;
-- 
2.4.11


From 30a4f5c321b7a68a605c6f827b775a1d3c4713bc Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Wed, 8 Feb 2017 09:29:00 -0800
Subject: [PATCH 24/33] lwtunnel: valid encap attr check should return 0 when
 lwtunnel is disabled

[ Upstream commit 2bd137de531367fb573d90150d1872cb2a2095f7 ]

An error was reported upgrading to 4.9.8:
    root@Typhoon:~# ip route add default table 210 nexthop dev eth0 via 10.68.64.1
    weight 1 nexthop dev eth0 via 10.68.64.2 weight 1
    RTNETLINK answers: Operation not supported

The problem occurs when CONFIG_LWTUNNEL is not enabled and a multipath
route is submitted.

The point of lwtunnel_valid_encap_type_attr is catch modules that
need to be loaded before any references are taken with rntl held. With
CONFIG_LWTUNNEL disabled, there will be no modules to load so the
lwtunnel_valid_encap_type_attr stub should just return 0.

Fixes: 9ed59592e3e3 ("lwtunnel: fix autoload of lwt modules")
Reported-by: pupilla@libero.it
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/lwtunnel.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h
index fc7c0db..3f40132 100644
--- a/include/net/lwtunnel.h
+++ b/include/net/lwtunnel.h
@@ -176,7 +176,10 @@ static inline int lwtunnel_valid_encap_type(u16 encap_type)
 }
 static inline int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len)
 {
-	return -EOPNOTSUPP;
+	/* return 0 since we are not walking attr looking for
+	 * RTA_ENCAP_TYPE attribute on nexthops.
+	 */
+	return 0;
 }
 
 static inline int lwtunnel_build_state(struct net_device *dev, u16 encap_type,
-- 
2.4.11


From e76d833051e5269f6528872c5a12e6aa7def94d7 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Wed, 8 Feb 2017 10:02:13 -0800
Subject: [PATCH 25/33] sit: fix a double free on error path

[ Upstream commit d7426c69a1942b2b9b709bf66b944ff09f561484 ]

Dmitry reported a double free in sit_init_net():

  kernel BUG at mm/percpu.c:689!
  invalid opcode: 0000 [#1] SMP KASAN
  Dumping ftrace buffer:
     (ftrace buffer empty)
  Modules linked in:
  CPU: 0 PID: 15692 Comm: syz-executor1 Not tainted 4.10.0-rc6-next-20170206 #1
  Hardware name: Google Google Compute Engine/Google Compute Engine,
  BIOS Google 01/01/2011
  task: ffff8801c9cc27c0 task.stack: ffff88017d1d8000
  RIP: 0010:pcpu_free_area+0x68b/0x810 mm/percpu.c:689
  RSP: 0018:ffff88017d1df488 EFLAGS: 00010046
  RAX: 0000000000010000 RBX: 00000000000007c0 RCX: ffffc90002829000
  RDX: 0000000000010000 RSI: ffffffff81940efb RDI: ffff8801db841d94
  RBP: ffff88017d1df590 R08: dffffc0000000000 R09: 1ffffffff0bb3bdd
  R10: dffffc0000000000 R11: 00000000000135dd R12: ffff8801db841d80
  R13: 0000000000038e40 R14: 00000000000007c0 R15: 00000000000007c0
  FS:  00007f6ea608f700(0000) GS:ffff8801dbe00000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 000000002000aff8 CR3: 00000001c8d44000 CR4: 00000000001426f0
  DR0: 0000000020000000 DR1: 0000000020000000 DR2: 0000000000000000
  DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000600
  Call Trace:
   free_percpu+0x212/0x520 mm/percpu.c:1264
   ipip6_dev_free+0x43/0x60 net/ipv6/sit.c:1335
   sit_init_net+0x3cb/0xa10 net/ipv6/sit.c:1831
   ops_init+0x10a/0x530 net/core/net_namespace.c:115
   setup_net+0x2ed/0x690 net/core/net_namespace.c:291
   copy_net_ns+0x26c/0x530 net/core/net_namespace.c:396
   create_new_namespaces+0x409/0x860 kernel/nsproxy.c:106
   unshare_nsproxy_namespaces+0xae/0x1e0 kernel/nsproxy.c:205
   SYSC_unshare kernel/fork.c:2281 [inline]
   SyS_unshare+0x64e/0xfc0 kernel/fork.c:2231
   entry_SYSCALL_64_fastpath+0x1f/0xc2

This is because when tunnel->dst_cache init fails, we free dev->tstats
once in ipip6_tunnel_init() and twice in sit_init_net(). This looks
redundant but its ndo_uinit() does not seem enough to clean up everything
here. So avoid this by setting dev->tstats to NULL after the first free,
at least for -net.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index b1cdf80..40d7405 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1390,6 +1390,7 @@ static int ipip6_tunnel_init(struct net_device *dev)
 	err = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL);
 	if (err) {
 		free_percpu(dev->tstats);
+		dev->tstats = NULL;
 		return err;
 	}
 
-- 
2.4.11


From 525db07c37ec7679e44731d78e0a5b1e95d1087d Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Tue, 7 Feb 2017 15:57:20 -0500
Subject: [PATCH 26/33] net: introduce device min_header_len

[ Upstream commit 217e6fa24ce28ec87fca8da93c9016cb78028612 ]

The stack must not pass packets to device drivers that are shorter
than the minimum link layer header length.

Previously, packet sockets would drop packets smaller than or equal
to dev->hard_header_len, but this has false positives. Zero length
payload is used over Ethernet. Other link layer protocols support
variable length headers. Support for validation of these protocols
removed the min length check for all protocols.

Introduce an explicit dev->min_header_len parameter and drop all
packets below this value. Initially, set it to non-zero only for
Ethernet and loopback. Other protocols can follow in a patch to
net-next.

Fixes: 9ed988cd5915 ("packet: validate variable length ll headers")
Reported-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/loopback.c    | 1 +
 include/linux/netdevice.h | 4 ++++
 net/ethernet/eth.c        | 1 +
 3 files changed, 6 insertions(+)

diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index 6255973..1b65f0f 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -164,6 +164,7 @@ static void loopback_setup(struct net_device *dev)
 {
 	dev->mtu		= 64 * 1024;
 	dev->hard_header_len	= ETH_HLEN;	/* 14	*/
+	dev->min_header_len	= ETH_HLEN;	/* 14	*/
 	dev->addr_len		= ETH_ALEN;	/* 6	*/
 	dev->type		= ARPHRD_LOOPBACK;	/* 0x0001*/
 	dev->flags		= IFF_LOOPBACK;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d83590e..bb9b102 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1508,6 +1508,7 @@ enum netdev_priv_flags {
  *	@mtu:		Interface MTU value
  *	@type:		Interface hardware type
  *	@hard_header_len: Maximum hardware header length.
+ *	@min_header_len:  Minimum hardware header length
  *
  *	@needed_headroom: Extra headroom the hardware may need, but not in all
  *			  cases can this be guaranteed
@@ -1728,6 +1729,7 @@ struct net_device {
 	unsigned int		mtu;
 	unsigned short		type;
 	unsigned short		hard_header_len;
+	unsigned short		min_header_len;
 
 	unsigned short		needed_headroom;
 	unsigned short		needed_tailroom;
@@ -2783,6 +2785,8 @@ static inline bool dev_validate_header(const struct net_device *dev,
 {
 	if (likely(len >= dev->hard_header_len))
 		return true;
+	if (len < dev->min_header_len)
+		return false;
 
 	if (capable(CAP_SYS_RAWIO)) {
 		memset(ll_header + len, 0, dev->hard_header_len - len);
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index 02acfff..24d7aff 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -356,6 +356,7 @@ void ether_setup(struct net_device *dev)
 	dev->header_ops		= &eth_header_ops;
 	dev->type		= ARPHRD_ETHER;
 	dev->hard_header_len 	= ETH_HLEN;
+	dev->min_header_len	= ETH_HLEN;
 	dev->mtu		= ETH_DATA_LEN;
 	dev->addr_len		= ETH_ALEN;
 	dev->tx_queue_len	= 1000;	/* Ethernet wants good queues */
-- 
2.4.11


From 69d45e412ae9fe976d23dd3537dab0e159e8aca7 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Tue, 7 Feb 2017 15:57:21 -0500
Subject: [PATCH 27/33] packet: round up linear to header len

[ Upstream commit 57031eb794906eea4e1c7b31dc1e2429c0af0c66 ]

Link layer protocols may unconditionally pull headers, as Ethernet
does in eth_type_trans. Ensure that the entire link layer header
always lies in the skb linear segment. tpacket_snd has such a check.
Extend this to packet_snd.

Variable length link layer headers complicate the computation
somewhat. Here skb->len may be smaller than dev->hard_header_len.

Round up the linear length to be at least as long as the smallest of
the two.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 94e4a59..458722b 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2813,7 +2813,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	struct virtio_net_hdr vnet_hdr = { 0 };
 	int offset = 0;
 	struct packet_sock *po = pkt_sk(sk);
-	int hlen, tlen;
+	int hlen, tlen, linear;
 	int extra_len = 0;
 
 	/*
@@ -2874,8 +2874,9 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	err = -ENOBUFS;
 	hlen = LL_RESERVED_SPACE(dev);
 	tlen = dev->needed_tailroom;
-	skb = packet_alloc_skb(sk, hlen + tlen, hlen, len,
-			       __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len),
+	linear = __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len);
+	linear = max(linear, min_t(int, len, dev->hard_header_len));
+	skb = packet_alloc_skb(sk, hlen + tlen, hlen, len, linear,
 			       msg->msg_flags & MSG_DONTWAIT, &err);
 	if (skb == NULL)
 		goto out_unlock;
-- 
2.4.11


From 197814b3b9f0a31ed2d471184c53a918971767b4 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Tue, 7 Feb 2017 12:59:46 -0800
Subject: [PATCH 28/33] ping: fix a null pointer dereference

[ Upstream commit 73d2c6678e6c3af7e7a42b1e78cd0211782ade32 ]

Andrey reported a kernel crash:

  general protection fault: 0000 [#1] SMP KASAN
  Dumping ftrace buffer:
     (ftrace buffer empty)
  Modules linked in:
  CPU: 2 PID: 3880 Comm: syz-executor1 Not tainted 4.10.0-rc6+ #124
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
  task: ffff880060048040 task.stack: ffff880069be8000
  RIP: 0010:ping_v4_push_pending_frames net/ipv4/ping.c:647 [inline]
  RIP: 0010:ping_v4_sendmsg+0x1acd/0x23f0 net/ipv4/ping.c:837
  RSP: 0018:ffff880069bef8b8 EFLAGS: 00010206
  RAX: dffffc0000000000 RBX: ffff880069befb90 RCX: 0000000000000000
  RDX: 0000000000000018 RSI: ffff880069befa30 RDI: 00000000000000c2
  RBP: ffff880069befbb8 R08: 0000000000000008 R09: 0000000000000000
  R10: 0000000000000002 R11: 0000000000000000 R12: ffff880069befab0
  R13: ffff88006c624a80 R14: ffff880069befa70 R15: 0000000000000000
  FS:  00007f6f7c716700(0000) GS:ffff88006de00000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 00000000004a6f28 CR3: 000000003a134000 CR4: 00000000000006e0
  Call Trace:
   inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:744
   sock_sendmsg_nosec net/socket.c:635 [inline]
   sock_sendmsg+0xca/0x110 net/socket.c:645
   SYSC_sendto+0x660/0x810 net/socket.c:1687
   SyS_sendto+0x40/0x50 net/socket.c:1655
   entry_SYSCALL_64_fastpath+0x1f/0xc2

This is because we miss a check for NULL pointer for skb_peek() when
the queue is empty. Other places already have the same check.

Fixes: c319b4d76b9e ("net: ipv4: add IPPROTO_ICMP socket kind")
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ping.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 96b8e2b..105c074 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -642,6 +642,8 @@ static int ping_v4_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh,
 {
 	struct sk_buff *skb = skb_peek(&sk->sk_write_queue);
 
+	if (!skb)
+		return 0;
 	pfh->wcheck = csum_partial((char *)&pfh->icmph,
 		sizeof(struct icmphdr), pfh->wcheck);
 	pfh->icmph.checksum = csum_fold(pfh->wcheck);
-- 
2.4.11


From e5b7f923a650f803365983e5b248596f21f5bb7f Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 7 Feb 2017 23:10:13 -0800
Subject: [PATCH 29/33] net: dsa: Do not destroy invalid network devices

[ Upstream commit 382e1eea2d983cd2343482c6a638f497bb44a636 ]

dsa_slave_create() can fail, and dsa_user_port_unapply() will properly check
for the network device not being NULL before attempting to destroy it. We were
not setting the slave network device as NULL if dsa_slave_create() failed, so
we would later on be calling dsa_slave_destroy() on a now free'd and
unitialized network device, causing crashes in dsa_slave_destroy().

Fixes: 83c0afaec7b7 ("net: dsa: Add new binding implementation")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/dsa2.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index da38621..0f99297 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -273,6 +273,7 @@ static int dsa_user_port_apply(struct device_node *port, u32 index,
 	if (err) {
 		dev_warn(ds->dev, "Failed to create slave %d: %d\n",
 			 index, err);
+		ds->ports[index].netdev = NULL;
 		return err;
 	}
 
-- 
2.4.11


From f46522d236f77733ba583cfb7993d54505650834 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 9 Feb 2017 16:15:52 -0800
Subject: [PATCH 31/33] l2tp: do not use udp_ioctl()

[ Upstream commit 72fb96e7bdbbdd4421b0726992496531060f3636 ]

udp_ioctl(), as its name suggests, is used by UDP protocols,
but is also used by L2TP :(

L2TP should use its own handler, because it really does not
look the same.

SIOCINQ for instance should not assume UDP checksum or headers.

Thanks to Andrey and syzkaller team for providing the report
and a nice reproducer.

While crashes only happen on recent kernels (after commit
7c13f97ffde6 ("udp: do fwd memory scheduling on dequeue")), this
probably needs to be backported to older kernels.

Fixes: 7c13f97ffde6 ("udp: do fwd memory scheduling on dequeue")
Fixes: 85584672012e ("udp: Fix udp_poll() and ioctl()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.h |  1 +
 net/l2tp/l2tp_ip.c   | 27 ++++++++++++++++++++++++++-
 net/l2tp/l2tp_ip6.c  |  2 +-
 3 files changed, 28 insertions(+), 2 deletions(-)

diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 2599af6..181e755c 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -273,6 +273,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb,
 int l2tp_nl_register_ops(enum l2tp_pwtype pw_type,
 			 const struct l2tp_nl_cmd_ops *ops);
 void l2tp_nl_unregister_ops(enum l2tp_pwtype pw_type);
+int l2tp_ioctl(struct sock *sk, int cmd, unsigned long arg);
 
 /* Session reference counts. Incremented when code obtains a reference
  * to a session.
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 8938b6b..c0f0750 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -11,6 +11,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <asm/ioctls.h>
 #include <linux/icmp.h>
 #include <linux/module.h>
 #include <linux/skbuff.h>
@@ -560,6 +561,30 @@ static int l2tp_ip_recvmsg(struct sock *sk, struct msghdr *msg,
 	return err ? err : copied;
 }
 
+int l2tp_ioctl(struct sock *sk, int cmd, unsigned long arg)
+{
+	struct sk_buff *skb;
+	int amount;
+
+	switch (cmd) {
+	case SIOCOUTQ:
+		amount = sk_wmem_alloc_get(sk);
+		break;
+	case SIOCINQ:
+		spin_lock_bh(&sk->sk_receive_queue.lock);
+		skb = skb_peek(&sk->sk_receive_queue);
+		amount = skb ? skb->len : 0;
+		spin_unlock_bh(&sk->sk_receive_queue.lock);
+		break;
+
+	default:
+		return -ENOIOCTLCMD;
+	}
+
+	return put_user(amount, (int __user *)arg);
+}
+EXPORT_SYMBOL(l2tp_ioctl);
+
 static struct proto l2tp_ip_prot = {
 	.name		   = "L2TP/IP",
 	.owner		   = THIS_MODULE,
@@ -568,7 +593,7 @@ static struct proto l2tp_ip_prot = {
 	.bind		   = l2tp_ip_bind,
 	.connect	   = l2tp_ip_connect,
 	.disconnect	   = l2tp_ip_disconnect,
-	.ioctl		   = udp_ioctl,
+	.ioctl		   = l2tp_ioctl,
 	.destroy	   = l2tp_ip_destroy_sock,
 	.setsockopt	   = ip_setsockopt,
 	.getsockopt	   = ip_getsockopt,
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index aa821cb..1a65c9a 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -729,7 +729,7 @@ static struct proto l2tp_ip6_prot = {
 	.bind		   = l2tp_ip6_bind,
 	.connect	   = l2tp_ip6_connect,
 	.disconnect	   = l2tp_ip6_disconnect,
-	.ioctl		   = udp_ioctl,
+	.ioctl		   = l2tp_ioctl,
 	.destroy	   = l2tp_ip6_destroy_sock,
 	.setsockopt	   = ipv6_setsockopt,
 	.getsockopt	   = ipv6_getsockopt,
-- 
2.4.11


From acb1f88e387f0b52c99c6249183f7ae7f7b44370 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Thu, 12 Jan 2017 21:19:37 +0800
Subject: [PATCH 32/33] mld: do not remove mld souce list info when set link
 down

[ Upstream commit 1666d49e1d416fcc2cce708242a52fe3317ea8ba ]

This is an IPv6 version of commit 24803f38a5c0 ("igmp: do not remove igmp
souce list..."). In mld_del_delrec(), we will restore back all source filter
info instead of flush them.

Move mld_clear_delrec() from ipv6_mc_down() to ipv6_mc_destroy_dev() since
we should not remove source list info when set link down. Remove
igmp6_group_dropped() in ipv6_mc_destroy_dev() since we have called it in
ipv6_mc_down().

Also clear all source info after igmp6_group_dropped() instead of in it
because ipv6_mc_down() will call igmp6_group_dropped().

Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/mcast.c | 51 ++++++++++++++++++++++++++++++---------------------
 1 file changed, 30 insertions(+), 21 deletions(-)

diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 14a3903..7139fff 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -81,7 +81,7 @@ static void mld_gq_timer_expire(unsigned long data);
 static void mld_ifc_timer_expire(unsigned long data);
 static void mld_ifc_event(struct inet6_dev *idev);
 static void mld_add_delrec(struct inet6_dev *idev, struct ifmcaddr6 *pmc);
-static void mld_del_delrec(struct inet6_dev *idev, const struct in6_addr *addr);
+static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *pmc);
 static void mld_clear_delrec(struct inet6_dev *idev);
 static bool mld_in_v1_mode(const struct inet6_dev *idev);
 static int sf_setstate(struct ifmcaddr6 *pmc);
@@ -692,9 +692,9 @@ static void igmp6_group_dropped(struct ifmcaddr6 *mc)
 			dev_mc_del(dev, buf);
 	}
 
-	if (mc->mca_flags & MAF_NOREPORT)
-		goto done;
 	spin_unlock_bh(&mc->mca_lock);
+	if (mc->mca_flags & MAF_NOREPORT)
+		return;
 
 	if (!mc->idev->dead)
 		igmp6_leave_group(mc);
@@ -702,8 +702,6 @@ static void igmp6_group_dropped(struct ifmcaddr6 *mc)
 	spin_lock_bh(&mc->mca_lock);
 	if (del_timer(&mc->mca_timer))
 		atomic_dec(&mc->mca_refcnt);
-done:
-	ip6_mc_clear_src(mc);
 	spin_unlock_bh(&mc->mca_lock);
 }
 
@@ -748,10 +746,11 @@ static void mld_add_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im)
 	spin_unlock_bh(&idev->mc_lock);
 }
 
-static void mld_del_delrec(struct inet6_dev *idev, const struct in6_addr *pmca)
+static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im)
 {
 	struct ifmcaddr6 *pmc, *pmc_prev;
-	struct ip6_sf_list *psf, *psf_next;
+	struct ip6_sf_list *psf;
+	struct in6_addr *pmca = &im->mca_addr;
 
 	spin_lock_bh(&idev->mc_lock);
 	pmc_prev = NULL;
@@ -768,14 +767,20 @@ static void mld_del_delrec(struct inet6_dev *idev, const struct in6_addr *pmca)
 	}
 	spin_unlock_bh(&idev->mc_lock);
 
+	spin_lock_bh(&im->mca_lock);
 	if (pmc) {
-		for (psf = pmc->mca_tomb; psf; psf = psf_next) {
-			psf_next = psf->sf_next;
-			kfree(psf);
+		im->idev = pmc->idev;
+		im->mca_crcount = idev->mc_qrv;
+		im->mca_sfmode = pmc->mca_sfmode;
+		if (pmc->mca_sfmode == MCAST_INCLUDE) {
+			im->mca_tomb = pmc->mca_tomb;
+			im->mca_sources = pmc->mca_sources;
+			for (psf = im->mca_sources; psf; psf = psf->sf_next)
+				psf->sf_crcount = im->mca_crcount;
 		}
 		in6_dev_put(pmc->idev);
-		kfree(pmc);
 	}
+	spin_unlock_bh(&im->mca_lock);
 }
 
 static void mld_clear_delrec(struct inet6_dev *idev)
@@ -904,7 +909,7 @@ int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr)
 	mca_get(mc);
 	write_unlock_bh(&idev->lock);
 
-	mld_del_delrec(idev, &mc->mca_addr);
+	mld_del_delrec(idev, mc);
 	igmp6_group_added(mc);
 	ma_put(mc);
 	return 0;
@@ -927,6 +932,7 @@ int __ipv6_dev_mc_dec(struct inet6_dev *idev, const struct in6_addr *addr)
 				write_unlock_bh(&idev->lock);
 
 				igmp6_group_dropped(ma);
+				ip6_mc_clear_src(ma);
 
 				ma_put(ma);
 				return 0;
@@ -2501,15 +2507,17 @@ void ipv6_mc_down(struct inet6_dev *idev)
 	/* Withdraw multicast list */
 
 	read_lock_bh(&idev->lock);
-	mld_ifc_stop_timer(idev);
-	mld_gq_stop_timer(idev);
-	mld_dad_stop_timer(idev);
 
 	for (i = idev->mc_list; i; i = i->next)
 		igmp6_group_dropped(i);
-	read_unlock_bh(&idev->lock);
 
-	mld_clear_delrec(idev);
+	/* Should stop timer after group drop. or we will
+	 * start timer again in mld_ifc_event()
+	 */
+	mld_ifc_stop_timer(idev);
+	mld_gq_stop_timer(idev);
+	mld_dad_stop_timer(idev);
+	read_unlock_bh(&idev->lock);
 }
 
 static void ipv6_mc_reset(struct inet6_dev *idev)
@@ -2531,8 +2539,10 @@ void ipv6_mc_up(struct inet6_dev *idev)
 
 	read_lock_bh(&idev->lock);
 	ipv6_mc_reset(idev);
-	for (i = idev->mc_list; i; i = i->next)
+	for (i = idev->mc_list; i; i = i->next) {
+		mld_del_delrec(idev, i);
 		igmp6_group_added(i);
+	}
 	read_unlock_bh(&idev->lock);
 }
 
@@ -2565,6 +2575,7 @@ void ipv6_mc_destroy_dev(struct inet6_dev *idev)
 
 	/* Deactivate timers */
 	ipv6_mc_down(idev);
+	mld_clear_delrec(idev);
 
 	/* Delete all-nodes address. */
 	/* We cannot call ipv6_dev_mc_dec() directly, our caller in
@@ -2579,11 +2590,9 @@ void ipv6_mc_destroy_dev(struct inet6_dev *idev)
 	write_lock_bh(&idev->lock);
 	while ((i = idev->mc_list) != NULL) {
 		idev->mc_list = i->next;
-		write_unlock_bh(&idev->lock);
 
-		igmp6_group_dropped(i);
+		write_unlock_bh(&idev->lock);
 		ma_put(i);
-
 		write_lock_bh(&idev->lock);
 	}
 	write_unlock_bh(&idev->lock);
-- 
2.4.11


From 675057b95170ed1534a2bcd1fd31f46b20a9dc33 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Wed, 8 Feb 2017 21:16:45 +0800
Subject: [PATCH 33/33] igmp, mld: Fix memory leak in igmpv3/mld_del_delrec()

[ Upstream commit 9c8bb163ae784be4f79ae504e78c862806087c54 ]

In function igmpv3/mld_add_delrec() we allocate pmc and put it in
idev->mc_tomb, so we should free it when we don't need it in del_delrec().
But I removed kfree(pmc) incorrectly in latest two patches. Now fix it.

Fixes: 24803f38a5c0 ("igmp: do not remove igmp souce list info when ...")
Fixes: 1666d49e1d41 ("mld: do not remove mld souce list info when ...")
Reported-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/igmp.c  | 1 +
 net/ipv6/mcast.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 32a08bc..1bc623d 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -1172,6 +1172,7 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im)
 				psf->sf_crcount = im->crcount;
 		}
 		in_dev_put(pmc->interface);
+		kfree(pmc);
 	}
 	spin_unlock_bh(&im->lock);
 }
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 7139fff..1bdc703 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -779,6 +779,7 @@ static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im)
 				psf->sf_crcount = im->mca_crcount;
 		}
 		in6_dev_put(pmc->idev);
+		kfree(pmc);
 	}
 	spin_unlock_bh(&im->mca_lock);
 }
-- 
2.4.11

Re: [PATCHES] Networking

[Greg KH]

On Mon, Feb 13, 2017 at 12:15:46PM -0500, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.4 and v4.9
> -stable, respectively.

All now applied, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 113 bytes --]


Please queue up the following networking bug fixes for 4.4.x, 4.9.x,
and 4.10.x -stable, respectively.

Thanks!

[-- Attachment #2: net_44.mbox --]
[-- Type: Application/Octet-Stream, Size: 19842 bytes --]

From f867d0c65c57f5e68edba5ecce22f0523b5a778e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 12 Feb 2017 14:03:52 -0800
Subject: [PATCH 1/7] net/llc: avoid BUG_ON() in skb_orphan()

[ Upstream commit 8b74d439e1697110c5e5c600643e823eb1dd0762 ]

It seems nobody used LLC since linux-3.12.

Fortunately fuzzers like syzkaller still know how to run this code,
otherwise it would be no fun.

Setting skb->sk without skb->destructor leads to all kinds of
bugs, we now prefer to be very strict about it.

Ideally here we would use skb_set_owner() but this helper does not exist yet,
only CAN seems to have a private helper for that.

Fixes: 376c7311bdb6 ("net: add a temporary sanity check in skb_orphan()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/llc/llc_conn.c | 3 +++
 net/llc/llc_sap.c  | 3 +++
 2 files changed, 6 insertions(+)

diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c
index 3e821da..8bc5a1b 100644
--- a/net/llc/llc_conn.c
+++ b/net/llc/llc_conn.c
@@ -821,7 +821,10 @@ void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb)
 		 * another trick required to cope with how the PROCOM state
 		 * machine works. -acme
 		 */
+		skb_orphan(skb);
+		sock_hold(sk);
 		skb->sk = sk;
+		skb->destructor = sock_efree;
 	}
 	if (!sock_owned_by_user(sk))
 		llc_conn_rcv(sk, skb);
diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c
index d0e1e80..5404d0d 100644
--- a/net/llc/llc_sap.c
+++ b/net/llc/llc_sap.c
@@ -290,7 +290,10 @@ static void llc_sap_rcv(struct llc_sap *sap, struct sk_buff *skb,
 
 	ev->type   = LLC_SAP_EV_TYPE_PDU;
 	ev->reason = 0;
+	skb_orphan(skb);
+	sock_hold(sk);
 	skb->sk = sk;
+	skb->destructor = sock_efree;
 	llc_sap_state_process(sap, skb);
 }
 
-- 
2.4.11


From a021b6c39029d98eeaedd9a354e6a35516ad6809 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 14 Feb 2017 09:03:51 -0800
Subject: [PATCH 2/7] packet: fix races in fanout_add()

[ Upstream commit d199fab63c11998a602205f7ee7ff7c05c97164b ]

Multiple threads can call fanout_add() at the same time.

We need to grab fanout_mutex earlier to avoid races that could
lead to one thread freeing po->rollover that was set by another thread.

Do the same in fanout_release(), for peace of mind, and to help us
finding lockdep issues earlier.

Fixes: dc99f600698d ("packet: Add fanout support.")
Fixes: 0648ab70afe6 ("packet: rollover prepare: per-socket state")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 55 +++++++++++++++++++++++++++-----------------------
 1 file changed, 30 insertions(+), 25 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index f2d28ed..b1dc595 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1623,6 +1623,7 @@ static void fanout_release_data(struct packet_fanout *f)
 
 static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 {
+	struct packet_rollover *rollover = NULL;
 	struct packet_sock *po = pkt_sk(sk);
 	struct packet_fanout *f, *match;
 	u8 type = type_flags & 0xff;
@@ -1645,23 +1646,28 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		return -EINVAL;
 	}
 
+	mutex_lock(&fanout_mutex);
+
+	err = -EINVAL;
 	if (!po->running)
-		return -EINVAL;
+		goto out;
 
+	err = -EALREADY;
 	if (po->fanout)
-		return -EALREADY;
+		goto out;
 
 	if (type == PACKET_FANOUT_ROLLOVER ||
 	    (type_flags & PACKET_FANOUT_FLAG_ROLLOVER)) {
-		po->rollover = kzalloc(sizeof(*po->rollover), GFP_KERNEL);
-		if (!po->rollover)
-			return -ENOMEM;
-		atomic_long_set(&po->rollover->num, 0);
-		atomic_long_set(&po->rollover->num_huge, 0);
-		atomic_long_set(&po->rollover->num_failed, 0);
+		err = -ENOMEM;
+		rollover = kzalloc(sizeof(*rollover), GFP_KERNEL);
+		if (!rollover)
+			goto out;
+		atomic_long_set(&rollover->num, 0);
+		atomic_long_set(&rollover->num_huge, 0);
+		atomic_long_set(&rollover->num_failed, 0);
+		po->rollover = rollover;
 	}
 
-	mutex_lock(&fanout_mutex);
 	match = NULL;
 	list_for_each_entry(f, &fanout_list, list) {
 		if (f->id == id &&
@@ -1708,11 +1714,11 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		}
 	}
 out:
-	mutex_unlock(&fanout_mutex);
-	if (err) {
-		kfree(po->rollover);
+	if (err && rollover) {
+		kfree(rollover);
 		po->rollover = NULL;
 	}
+	mutex_unlock(&fanout_mutex);
 	return err;
 }
 
@@ -1721,23 +1727,22 @@ static void fanout_release(struct sock *sk)
 	struct packet_sock *po = pkt_sk(sk);
 	struct packet_fanout *f;
 
-	f = po->fanout;
-	if (!f)
-		return;
-
 	mutex_lock(&fanout_mutex);
-	po->fanout = NULL;
+	f = po->fanout;
+	if (f) {
+		po->fanout = NULL;
+
+		if (atomic_dec_and_test(&f->sk_ref)) {
+			list_del(&f->list);
+			dev_remove_pack(&f->prot_hook);
+			fanout_release_data(f);
+			kfree(f);
+		}
 
-	if (atomic_dec_and_test(&f->sk_ref)) {
-		list_del(&f->list);
-		dev_remove_pack(&f->prot_hook);
-		fanout_release_data(f);
-		kfree(f);
+		if (po->rollover)
+			kfree_rcu(po->rollover, rcu);
 	}
 	mutex_unlock(&fanout_mutex);
-
-	if (po->rollover)
-		kfree_rcu(po->rollover, rcu);
 }
 
 static bool packet_extra_vlan_len_allowed(const struct net_device *dev,
-- 
2.4.11


From 9ae20e9833eb771d22c4c5549de82daf18e9fdb7 Mon Sep 17 00:00:00 2001
From: Anoob Soman <anoob.soman@citrix.com>
Date: Wed, 15 Feb 2017 20:25:39 +0000
Subject: [PATCH 3/7] packet: Do not call fanout_release from atomic contexts

[ Upstream commit 2bd624b4611ffee36422782d16e1c944d1351e98 ]

Commit 6664498280cf ("packet: call fanout_release, while UNREGISTERING a
netdev"), unfortunately, introduced the following issues.

1. calling mutex_lock(&fanout_mutex) (fanout_release()) from inside
rcu_read-side critical section. rcu_read_lock disables preemption, most often,
which prohibits calling sleeping functions.

[  ] include/linux/rcupdate.h:560 Illegal context switch in RCU read-side critical section!
[  ]
[  ] rcu_scheduler_active = 1, debug_locks = 0
[  ] 4 locks held by ovs-vswitchd/1969:
[  ]  #0:  (cb_lock){++++++}, at: [<ffffffff8158a6c9>] genl_rcv+0x19/0x40
[  ]  #1:  (ovs_mutex){+.+.+.}, at: [<ffffffffa04878ca>] ovs_vport_cmd_del+0x4a/0x100 [openvswitch]
[  ]  #2:  (rtnl_mutex){+.+.+.}, at: [<ffffffff81564157>] rtnl_lock+0x17/0x20
[  ]  #3:  (rcu_read_lock){......}, at: [<ffffffff81614165>] packet_notifier+0x5/0x3f0
[  ]
[  ] Call Trace:
[  ]  [<ffffffff813770c1>] dump_stack+0x85/0xc4
[  ]  [<ffffffff810c9077>] lockdep_rcu_suspicious+0x107/0x110
[  ]  [<ffffffff810a2da7>] ___might_sleep+0x57/0x210
[  ]  [<ffffffff810a2fd0>] __might_sleep+0x70/0x90
[  ]  [<ffffffff8162e80c>] mutex_lock_nested+0x3c/0x3a0
[  ]  [<ffffffff810de93f>] ? vprintk_default+0x1f/0x30
[  ]  [<ffffffff81186e88>] ? printk+0x4d/0x4f
[  ]  [<ffffffff816106dd>] fanout_release+0x1d/0xe0
[  ]  [<ffffffff81614459>] packet_notifier+0x2f9/0x3f0

2. calling mutex_lock(&fanout_mutex) inside spin_lock(&po->bind_lock).
"sleeping function called from invalid context"

[  ] BUG: sleeping function called from invalid context at kernel/locking/mutex.c:620
[  ] in_atomic(): 1, irqs_disabled(): 0, pid: 1969, name: ovs-vswitchd
[  ] INFO: lockdep is turned off.
[  ] Call Trace:
[  ]  [<ffffffff813770c1>] dump_stack+0x85/0xc4
[  ]  [<ffffffff810a2f52>] ___might_sleep+0x202/0x210
[  ]  [<ffffffff810a2fd0>] __might_sleep+0x70/0x90
[  ]  [<ffffffff8162e80c>] mutex_lock_nested+0x3c/0x3a0
[  ]  [<ffffffff816106dd>] fanout_release+0x1d/0xe0
[  ]  [<ffffffff81614459>] packet_notifier+0x2f9/0x3f0

3. calling dev_remove_pack(&fanout->prot_hook), from inside
spin_lock(&po->bind_lock) or rcu_read-side critical-section. dev_remove_pack()
-> synchronize_net(), which might sleep.

[  ] BUG: scheduling while atomic: ovs-vswitchd/1969/0x00000002
[  ] INFO: lockdep is turned off.
[  ] Call Trace:
[  ]  [<ffffffff813770c1>] dump_stack+0x85/0xc4
[  ]  [<ffffffff81186274>] __schedule_bug+0x64/0x73
[  ]  [<ffffffff8162b8cb>] __schedule+0x6b/0xd10
[  ]  [<ffffffff8162c5db>] schedule+0x6b/0x80
[  ]  [<ffffffff81630b1d>] schedule_timeout+0x38d/0x410
[  ]  [<ffffffff810ea3fd>] synchronize_sched_expedited+0x53d/0x810
[  ]  [<ffffffff810ea6de>] synchronize_rcu_expedited+0xe/0x10
[  ]  [<ffffffff8154eab5>] synchronize_net+0x35/0x50
[  ]  [<ffffffff8154eae3>] dev_remove_pack+0x13/0x20
[  ]  [<ffffffff8161077e>] fanout_release+0xbe/0xe0
[  ]  [<ffffffff81614459>] packet_notifier+0x2f9/0x3f0

4. fanout_release() races with calls from different CPU.

To fix the above problems, remove the call to fanout_release() under
rcu_read_lock(). Instead, call __dev_remove_pack(&fanout->prot_hook) and
netdev_run_todo will be happy that &dev->ptype_specific list is empty. In order
to achieve this, I moved dev_{add,remove}_pack() out of fanout_{add,release} to
__fanout_{link,unlink}. So, call to {,__}unregister_prot_hook() will make sure
fanout->prot_hook is removed as well.

Fixes: 6664498280cf ("packet: call fanout_release, while UNREGISTERING a netdev")
Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Anoob Soman <anoob.soman@citrix.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 31 ++++++++++++++++++++++---------
 1 file changed, 22 insertions(+), 9 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index b1dc595..d805cd5 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1497,6 +1497,8 @@ static void __fanout_link(struct sock *sk, struct packet_sock *po)
 	f->arr[f->num_members] = sk;
 	smp_wmb();
 	f->num_members++;
+	if (f->num_members == 1)
+		dev_add_pack(&f->prot_hook);
 	spin_unlock(&f->lock);
 }
 
@@ -1513,6 +1515,8 @@ static void __fanout_unlink(struct sock *sk, struct packet_sock *po)
 	BUG_ON(i >= f->num_members);
 	f->arr[i] = f->arr[f->num_members - 1];
 	f->num_members--;
+	if (f->num_members == 0)
+		__dev_remove_pack(&f->prot_hook);
 	spin_unlock(&f->lock);
 }
 
@@ -1697,7 +1701,6 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		match->prot_hook.func = packet_rcv_fanout;
 		match->prot_hook.af_packet_priv = match;
 		match->prot_hook.id_match = match_fanout_group;
-		dev_add_pack(&match->prot_hook);
 		list_add(&match->list, &fanout_list);
 	}
 	err = -EINVAL;
@@ -1722,7 +1725,12 @@ out:
 	return err;
 }
 
-static void fanout_release(struct sock *sk)
+/* If pkt_sk(sk)->fanout->sk_ref is zero, this function removes
+ * pkt_sk(sk)->fanout from fanout_list and returns pkt_sk(sk)->fanout.
+ * It is the responsibility of the caller to call fanout_release_data() and
+ * free the returned packet_fanout (after synchronize_net())
+ */
+static struct packet_fanout *fanout_release(struct sock *sk)
 {
 	struct packet_sock *po = pkt_sk(sk);
 	struct packet_fanout *f;
@@ -1732,17 +1740,17 @@ static void fanout_release(struct sock *sk)
 	if (f) {
 		po->fanout = NULL;
 
-		if (atomic_dec_and_test(&f->sk_ref)) {
+		if (atomic_dec_and_test(&f->sk_ref))
 			list_del(&f->list);
-			dev_remove_pack(&f->prot_hook);
-			fanout_release_data(f);
-			kfree(f);
-		}
+		else
+			f = NULL;
 
 		if (po->rollover)
 			kfree_rcu(po->rollover, rcu);
 	}
 	mutex_unlock(&fanout_mutex);
+
+	return f;
 }
 
 static bool packet_extra_vlan_len_allowed(const struct net_device *dev,
@@ -2851,6 +2859,7 @@ static int packet_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
 	struct packet_sock *po;
+	struct packet_fanout *f;
 	struct net *net;
 	union tpacket_req_u req_u;
 
@@ -2890,9 +2899,14 @@ static int packet_release(struct socket *sock)
 		packet_set_ring(sk, &req_u, 1, 1);
 	}
 
-	fanout_release(sk);
+	f = fanout_release(sk);
 
 	synchronize_net();
+
+	if (f) {
+		fanout_release_data(f);
+		kfree(f);
+	}
 	/*
 	 *	Now the socket is dead. No more input will appear.
 	 */
@@ -3866,7 +3880,6 @@ static int packet_notifier(struct notifier_block *this,
 				}
 				if (msg == NETDEV_UNREGISTER) {
 					packet_cached_dev_reset(po);
-					fanout_release(sk);
 					po->ifindex = -1;
 					if (po->prot_hook.dev)
 						dev_put(po->prot_hook.dev);
-- 
2.4.11


From f6a243e66e79fca8d997aac9932bcc1677363cc8 Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Thu, 16 Feb 2017 17:22:46 +0100
Subject: [PATCH 4/7] dccp: fix freeing skb too early for IPV6_RECVPKTINFO

[ Upstream commit 5edabca9d4cff7f1f2b68f0bac55ef99d9798ba4 ]

In the current DCCP implementation an skb for a DCCP_PKT_REQUEST packet
is forcibly freed via __kfree_skb in dccp_rcv_state_process if
dccp_v6_conn_request successfully returns.

However, if IPV6_RECVPKTINFO is set on a socket, the address of the skb
is saved to ireq->pktopts and the ref count for skb is incremented in
dccp_v6_conn_request, so skb is still in use. Nevertheless, it gets freed
in dccp_rcv_state_process.

Fix by calling consume_skb instead of doing goto discard and therefore
calling __kfree_skb.

Similar fixes for TCP:

fb7e2399ec17f1004c0e0ccfd17439f8759ede01 [TCP]: skb is unexpectedly freed.
0aea76d35c9651d55bbaf746e7914e5f9ae5a25d tcp: SYN packets are now
simply consumed

Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/input.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/dccp/input.c b/net/dccp/input.c
index 3bd14e8..dbe2573 100644
--- a/net/dccp/input.c
+++ b/net/dccp/input.c
@@ -606,7 +606,8 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 			if (inet_csk(sk)->icsk_af_ops->conn_request(sk,
 								    skb) < 0)
 				return 1;
-			goto discard;
+			consume_skb(skb);
+			return 0;
 		}
 		if (dh->dccph_type == DCCP_PKT_RESET)
 			goto discard;
-- 
2.4.11


From 195e5803c0351aca75e6f85fe5647389e28c8db7 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 17 Feb 2017 16:19:39 -0500
Subject: [PATCH 5/7] irda: Fix lockdep annotations in hashbin_delete().

[ Upstream commit 4c03b862b12f980456f9de92db6d508a4999b788 ]

A nested lock depth was added to the hasbin_delete() code but it
doesn't actually work some well and results in tons of lockdep splats.

Fix the code instead to properly drop the lock around the operation
and just keep peeking the head of the hashbin queue.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Tested-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/irda/irqueue.c | 34 ++++++++++++++++------------------
 1 file changed, 16 insertions(+), 18 deletions(-)

diff --git a/net/irda/irqueue.c b/net/irda/irqueue.c
index acbe61c..160dc89 100644
--- a/net/irda/irqueue.c
+++ b/net/irda/irqueue.c
@@ -383,9 +383,6 @@ EXPORT_SYMBOL(hashbin_new);
  *    for deallocating this structure if it's complex. If not the user can
  *    just supply kfree, which should take care of the job.
  */
-#ifdef CONFIG_LOCKDEP
-static int hashbin_lock_depth = 0;
-#endif
 int hashbin_delete( hashbin_t* hashbin, FREE_FUNC free_func)
 {
 	irda_queue_t* queue;
@@ -396,22 +393,27 @@ int hashbin_delete( hashbin_t* hashbin, FREE_FUNC free_func)
 	IRDA_ASSERT(hashbin->magic == HB_MAGIC, return -1;);
 
 	/* Synchronize */
-	if ( hashbin->hb_type & HB_LOCK ) {
-		spin_lock_irqsave_nested(&hashbin->hb_spinlock, flags,
-					 hashbin_lock_depth++);
-	}
+	if (hashbin->hb_type & HB_LOCK)
+		spin_lock_irqsave(&hashbin->hb_spinlock, flags);
 
 	/*
 	 *  Free the entries in the hashbin, TODO: use hashbin_clear when
 	 *  it has been shown to work
 	 */
 	for (i = 0; i < HASHBIN_SIZE; i ++ ) {
-		queue = dequeue_first((irda_queue_t**) &hashbin->hb_queue[i]);
-		while (queue ) {
-			if (free_func)
-				(*free_func)(queue);
-			queue = dequeue_first(
-				(irda_queue_t**) &hashbin->hb_queue[i]);
+		while (1) {
+			queue = dequeue_first((irda_queue_t**) &hashbin->hb_queue[i]);
+
+			if (!queue)
+				break;
+
+			if (free_func) {
+				if (hashbin->hb_type & HB_LOCK)
+					spin_unlock_irqrestore(&hashbin->hb_spinlock, flags);
+				free_func(queue);
+				if (hashbin->hb_type & HB_LOCK)
+					spin_lock_irqsave(&hashbin->hb_spinlock, flags);
+			}
 		}
 	}
 
@@ -420,12 +422,8 @@ int hashbin_delete( hashbin_t* hashbin, FREE_FUNC free_func)
 	hashbin->magic = ~HB_MAGIC;
 
 	/* Release lock */
-	if ( hashbin->hb_type & HB_LOCK) {
+	if (hashbin->hb_type & HB_LOCK)
 		spin_unlock_irqrestore(&hashbin->hb_spinlock, flags);
-#ifdef CONFIG_LOCKDEP
-		hashbin_lock_depth--;
-#endif
-	}
 
 	/*
 	 *  Free the hashbin structure
-- 
2.4.11


From 2b8c1bb409c96f650f189e7afc38b642134ee270 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 21 Feb 2017 09:33:18 +0100
Subject: [PATCH 6/7] ip: fix IP_CHECKSUM handling

[ Upstream commit ca4ef4574f1ee5252e2cd365f8f5d5bafd048f32 ]

The skbs processed by ip_cmsg_recv() are not guaranteed to
be linear e.g. when sending UDP packets over loopback with
MSGMORE.
Using csum_partial() on [potentially] the whole skb len
is dangerous; instead be on the safe side and use skb_checksum().

Thanks to syzkaller team to detect the issue and provide the
reproducer.

v1 -> v2:
 - move the variable declaration in a tighter scope

Fixes: ad6f939ab193 ("ip: Add offset parameter to ip_cmsg_recv")
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_sockglue.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index bc14c5b..f300d1c 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -105,10 +105,10 @@ static void ip_cmsg_recv_checksum(struct msghdr *msg, struct sk_buff *skb,
 	if (skb->ip_summed != CHECKSUM_COMPLETE)
 		return;
 
-	if (offset != 0)
-		csum = csum_sub(csum,
-				csum_partial(skb->data + tlen,
-					     offset, 0));
+	if (offset != 0) {
+		int tend_off = skb_transport_offset(skb) + tlen;
+		csum = csum_sub(csum, skb_checksum(skb, tend_off, offset, 0));
+	}
 
 	put_cmsg(msg, SOL_IP, IP_CHECKSUM, sizeof(__wsum), &csum);
 }
-- 
2.4.11


From 4a33a91828049d60637e250aaf35ecc85809c322 Mon Sep 17 00:00:00 2001
From: Maxime Jayat <maxime.jayat@mobile-devices.fr>
Date: Tue, 21 Feb 2017 18:35:51 +0100
Subject: [PATCH 7/7] net: socket: fix recvmmsg not returning error from
 sock_error

[ Upstream commit e623a9e9dec29ae811d11f83d0074ba254aba374 ]

Commit 34b88a68f26a ("net: Fix use after free in the recvmmsg exit path"),
changed the exit path of recvmmsg to always return the datagrams
variable and modified the error paths to set the variable to the error
code returned by recvmsg if necessary.

However in the case sock_error returned an error, the error code was
then ignored, and recvmmsg returned 0.

Change the error path of recvmmsg to correctly return the error code
of sock_error.

The bug was triggered by using recvmmsg on a CAN interface which was
not up. Linux 4.6 and later return 0 in this case while earlier
releases returned -ENETDOWN.

Fixes: 34b88a68f26a ("net: Fix use after free in the recvmmsg exit path")
Signed-off-by: Maxime Jayat <maxime.jayat@mobile-devices.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/socket.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/socket.c b/net/socket.c
index 0090225..fbfa9d2 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2185,8 +2185,10 @@ int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
 		return err;
 
 	err = sock_error(sock->sk);
-	if (err)
+	if (err) {
+		datagrams = err;
 		goto out_put;
+	}
 
 	entry = mmsg;
 	compat_entry = (struct compat_mmsghdr __user *)mmsg;
-- 
2.4.11


[-- Attachment #3: net_49.mbox --]
[-- Type: Application/Octet-Stream, Size: 37296 bytes --]

From bc9e2c2782221c9e0c1854187e1490e30c27cc4e Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Tue, 7 Feb 2017 12:59:47 -0800
Subject: [PATCH 01/14] kcm: fix 0-length case for kcm_sendmsg()

[ Upstream commit 98e3862ca2b1ae595a13805dcab4c3a6d7718f4d ]

Dmitry reported a kernel warning:

 WARNING: CPU: 3 PID: 2936 at net/kcm/kcmsock.c:627
 kcm_write_msgs+0x12e3/0x1b90 net/kcm/kcmsock.c:627
 CPU: 3 PID: 2936 Comm: a.out Not tainted 4.10.0-rc6+ #209
 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
 Call Trace:
  __dump_stack lib/dump_stack.c:15 [inline]
  dump_stack+0x2ee/0x3ef lib/dump_stack.c:51
  panic+0x1fb/0x412 kernel/panic.c:179
  __warn+0x1c4/0x1e0 kernel/panic.c:539
  warn_slowpath_null+0x2c/0x40 kernel/panic.c:582
  kcm_write_msgs+0x12e3/0x1b90 net/kcm/kcmsock.c:627
  kcm_sendmsg+0x163a/0x2200 net/kcm/kcmsock.c:1029
  sock_sendmsg_nosec net/socket.c:635 [inline]
  sock_sendmsg+0xca/0x110 net/socket.c:645
  sock_write_iter+0x326/0x600 net/socket.c:848
  new_sync_write fs/read_write.c:499 [inline]
  __vfs_write+0x483/0x740 fs/read_write.c:512
  vfs_write+0x187/0x530 fs/read_write.c:560
  SYSC_write fs/read_write.c:607 [inline]
  SyS_write+0xfb/0x230 fs/read_write.c:599
  entry_SYSCALL_64_fastpath+0x1f/0xc2

when calling syscall(__NR_write, sock2, 0x208aaf27ul, 0x0ul) on a KCM
seqpacket socket. It appears that kcm_sendmsg() does not handle len==0
case correctly, which causes an empty skb is allocated and queued.
Fix this by skipping the skb allocation for len==0 case.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Tom Herbert <tom@herbertland.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/kcm/kcmsock.c | 40 ++++++++++++++++++++++------------------
 1 file changed, 22 insertions(+), 18 deletions(-)

diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 7e08a4d..64f0e85 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -929,23 +929,25 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 			goto out_error;
 	}
 
-	/* New message, alloc head skb */
-	head = alloc_skb(0, sk->sk_allocation);
-	while (!head) {
-		kcm_push(kcm);
-		err = sk_stream_wait_memory(sk, &timeo);
-		if (err)
-			goto out_error;
-
+	if (msg_data_left(msg)) {
+		/* New message, alloc head skb */
 		head = alloc_skb(0, sk->sk_allocation);
-	}
+		while (!head) {
+			kcm_push(kcm);
+			err = sk_stream_wait_memory(sk, &timeo);
+			if (err)
+				goto out_error;
 
-	skb = head;
+			head = alloc_skb(0, sk->sk_allocation);
+		}
 
-	/* Set ip_summed to CHECKSUM_UNNECESSARY to avoid calling
-	 * csum_and_copy_from_iter from skb_do_copy_data_nocache.
-	 */
-	skb->ip_summed = CHECKSUM_UNNECESSARY;
+		skb = head;
+
+		/* Set ip_summed to CHECKSUM_UNNECESSARY to avoid calling
+		 * csum_and_copy_from_iter from skb_do_copy_data_nocache.
+		 */
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+	}
 
 start:
 	while (msg_data_left(msg)) {
@@ -1018,10 +1020,12 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	if (eor) {
 		bool not_busy = skb_queue_empty(&sk->sk_write_queue);
 
-		/* Message complete, queue it on send buffer */
-		__skb_queue_tail(&sk->sk_write_queue, head);
-		kcm->seq_skb = NULL;
-		KCM_STATS_INCR(kcm->stats.tx_msgs);
+		if (head) {
+			/* Message complete, queue it on send buffer */
+			__skb_queue_tail(&sk->sk_write_queue, head);
+			kcm->seq_skb = NULL;
+			KCM_STATS_INCR(kcm->stats.tx_msgs);
+		}
 
 		if (msg->msg_flags & MSG_BATCH) {
 			kcm->tx_wait_more = true;
-- 
2.4.11


From e34c784de69a0089d86acef6f2b3fca95401e21b Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Mon, 13 Feb 2017 11:13:16 -0800
Subject: [PATCH 02/14] kcm: fix a null pointer dereference in kcm_sendmsg()

[ Upstream commit cd27b96bc13841ee7af25837a6ae86fee87273d6 ]

In commit 98e3862ca2b1 ("kcm: fix 0-length case for kcm_sendmsg()")
I tried to avoid skb allocation for 0-length case, but missed
a check for NULL pointer in the non EOR case.

Fixes: 98e3862ca2b1 ("kcm: fix 0-length case for kcm_sendmsg()")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Tom Herbert <tom@herbertland.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/kcm/kcmsock.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 64f0e85..a646f34 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -1044,8 +1044,10 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	} else {
 		/* Message not complete, save state */
 partial_message:
-		kcm->seq_skb = head;
-		kcm_tx_msg(head)->last_skb = skb;
+		if (head) {
+			kcm->seq_skb = head;
+			kcm_tx_msg(head)->last_skb = skb;
+		}
 	}
 
 	KCM_STATS_ADD(kcm->stats.tx_bytes, copied);
-- 
2.4.11


From b06b0fec1f0dad63dfe6023e77487625f82f8fa7 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Sun, 12 Feb 2017 11:21:31 +0200
Subject: [PATCH 03/14] net/mlx5e: Disable preemption when doing TC statistics
 upcall

[ Upstream commit fed06ee89b78d3af32e235e0e89ad0d946fcb95d ]

When called by HW offloading drivers, the TC action (e.g
net/sched/act_mirred.c) code uses this_cpu logic, e.g

 _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets)

per the kernel documention, preemption should be disabled, add that.

Before the fix, when running with CONFIG_PREEMPT set, we get a

BUG: using smp_processor_id() in preemptible [00000000] code: tc/3793

asserion from the TC action (mirred) stats_update callback.

Fixes: aad7e08d39bd ('net/mlx5e: Hardware offloaded flower filter statistics support')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 6bb21b3..a543ea6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -567,10 +567,14 @@ int mlx5e_stats_flower(struct mlx5e_priv *priv,
 
 	mlx5_fc_query_cached(counter, &bytes, &packets, &lastuse);
 
+	preempt_disable();
+
 	tcf_exts_to_list(f->exts, &actions);
 	list_for_each_entry(a, &actions, list)
 		tcf_action_stats_update(a, bytes, packets, lastuse);
 
+	preempt_enable();
+
 	return 0;
 }
 
-- 
2.4.11


From d1fb6d33d82398257c9d793a08f860a44ef88b36 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 12 Feb 2017 14:03:52 -0800
Subject: [PATCH 04/14] net/llc: avoid BUG_ON() in skb_orphan()

[ Upstream commit 8b74d439e1697110c5e5c600643e823eb1dd0762 ]

It seems nobody used LLC since linux-3.12.

Fortunately fuzzers like syzkaller still know how to run this code,
otherwise it would be no fun.

Setting skb->sk without skb->destructor leads to all kinds of
bugs, we now prefer to be very strict about it.

Ideally here we would use skb_set_owner() but this helper does not exist yet,
only CAN seems to have a private helper for that.

Fixes: 376c7311bdb6 ("net: add a temporary sanity check in skb_orphan()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/llc/llc_conn.c | 3 +++
 net/llc/llc_sap.c  | 3 +++
 2 files changed, 6 insertions(+)

diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c
index 3e821da..8bc5a1b 100644
--- a/net/llc/llc_conn.c
+++ b/net/llc/llc_conn.c
@@ -821,7 +821,10 @@ void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb)
 		 * another trick required to cope with how the PROCOM state
 		 * machine works. -acme
 		 */
+		skb_orphan(skb);
+		sock_hold(sk);
 		skb->sk = sk;
+		skb->destructor = sock_efree;
 	}
 	if (!sock_owned_by_user(sk))
 		llc_conn_rcv(sk, skb);
diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c
index d0e1e80..5404d0d 100644
--- a/net/llc/llc_sap.c
+++ b/net/llc/llc_sap.c
@@ -290,7 +290,10 @@ static void llc_sap_rcv(struct llc_sap *sap, struct sk_buff *skb,
 
 	ev->type   = LLC_SAP_EV_TYPE_PDU;
 	ev->reason = 0;
+	skb_orphan(skb);
+	sock_hold(sk);
 	skb->sk = sk;
+	skb->destructor = sock_efree;
 	llc_sap_state_process(sap, skb);
 }
 
-- 
2.4.11


From 6a3ce9ed831bd6201b8f1e306d557198675f78a1 Mon Sep 17 00:00:00 2001
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Tue, 14 Feb 2017 14:42:15 +0200
Subject: [PATCH 05/14] net: ethernet: ti: cpsw: fix cpsw assignment in resume

[ Upstream commit a60ced990e309666915d21445e95347d12406694 ]

There is a copy-paste error, which hides breaking of resume
for CPSW driver: there was replaced netdev_priv() to ndev_to_cpsw(ndev)
in suspend, but left it unchanged in resume.

Fixes: 606f39939595a4d4540406bfc11f265b2036af6d
(ti: cpsw: move platform data and slaves info to cpsw_common)

Reported-by: Alexey Starikovskiy <AStarikovskiy@topcon.com>
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index b9087b8..3f1971d 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -2925,7 +2925,7 @@ static int cpsw_resume(struct device *dev)
 {
 	struct platform_device	*pdev = to_platform_device(dev);
 	struct net_device	*ndev = platform_get_drvdata(pdev);
-	struct cpsw_common	*cpsw = netdev_priv(ndev);
+	struct cpsw_common	*cpsw = ndev_to_cpsw(ndev);
 
 	/* Select default pin state */
 	pinctrl_pm_select_default_state(dev);
-- 
2.4.11


From 8f995b3ce7fd849fe169d18c7e34b53091ba5b93 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 14 Feb 2017 09:03:51 -0800
Subject: [PATCH 06/14] packet: fix races in fanout_add()

[ Upstream commit d199fab63c11998a602205f7ee7ff7c05c97164b ]

Multiple threads can call fanout_add() at the same time.

We need to grab fanout_mutex earlier to avoid races that could
lead to one thread freeing po->rollover that was set by another thread.

Do the same in fanout_release(), for peace of mind, and to help us
finding lockdep issues earlier.

Fixes: dc99f600698d ("packet: Add fanout support.")
Fixes: 0648ab70afe6 ("packet: rollover prepare: per-socket state")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 55 +++++++++++++++++++++++++++-----------------------
 1 file changed, 30 insertions(+), 25 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 458722b..87113e86 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1619,6 +1619,7 @@ static void fanout_release_data(struct packet_fanout *f)
 
 static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 {
+	struct packet_rollover *rollover = NULL;
 	struct packet_sock *po = pkt_sk(sk);
 	struct packet_fanout *f, *match;
 	u8 type = type_flags & 0xff;
@@ -1641,23 +1642,28 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		return -EINVAL;
 	}
 
+	mutex_lock(&fanout_mutex);
+
+	err = -EINVAL;
 	if (!po->running)
-		return -EINVAL;
+		goto out;
 
+	err = -EALREADY;
 	if (po->fanout)
-		return -EALREADY;
+		goto out;
 
 	if (type == PACKET_FANOUT_ROLLOVER ||
 	    (type_flags & PACKET_FANOUT_FLAG_ROLLOVER)) {
-		po->rollover = kzalloc(sizeof(*po->rollover), GFP_KERNEL);
-		if (!po->rollover)
-			return -ENOMEM;
-		atomic_long_set(&po->rollover->num, 0);
-		atomic_long_set(&po->rollover->num_huge, 0);
-		atomic_long_set(&po->rollover->num_failed, 0);
+		err = -ENOMEM;
+		rollover = kzalloc(sizeof(*rollover), GFP_KERNEL);
+		if (!rollover)
+			goto out;
+		atomic_long_set(&rollover->num, 0);
+		atomic_long_set(&rollover->num_huge, 0);
+		atomic_long_set(&rollover->num_failed, 0);
+		po->rollover = rollover;
 	}
 
-	mutex_lock(&fanout_mutex);
 	match = NULL;
 	list_for_each_entry(f, &fanout_list, list) {
 		if (f->id == id &&
@@ -1704,11 +1710,11 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		}
 	}
 out:
-	mutex_unlock(&fanout_mutex);
-	if (err) {
-		kfree(po->rollover);
+	if (err && rollover) {
+		kfree(rollover);
 		po->rollover = NULL;
 	}
+	mutex_unlock(&fanout_mutex);
 	return err;
 }
 
@@ -1717,23 +1723,22 @@ static void fanout_release(struct sock *sk)
 	struct packet_sock *po = pkt_sk(sk);
 	struct packet_fanout *f;
 
-	f = po->fanout;
-	if (!f)
-		return;
-
 	mutex_lock(&fanout_mutex);
-	po->fanout = NULL;
+	f = po->fanout;
+	if (f) {
+		po->fanout = NULL;
+
+		if (atomic_dec_and_test(&f->sk_ref)) {
+			list_del(&f->list);
+			dev_remove_pack(&f->prot_hook);
+			fanout_release_data(f);
+			kfree(f);
+		}
 
-	if (atomic_dec_and_test(&f->sk_ref)) {
-		list_del(&f->list);
-		dev_remove_pack(&f->prot_hook);
-		fanout_release_data(f);
-		kfree(f);
+		if (po->rollover)
+			kfree_rcu(po->rollover, rcu);
 	}
 	mutex_unlock(&fanout_mutex);
-
-	if (po->rollover)
-		kfree_rcu(po->rollover, rcu);
 }
 
 static bool packet_extra_vlan_len_allowed(const struct net_device *dev,
-- 
2.4.11


From a1ec2c0e0a0de80a506ca3335136a1f5600a9ee9 Mon Sep 17 00:00:00 2001
From: Anoob Soman <anoob.soman@citrix.com>
Date: Wed, 15 Feb 2017 20:25:39 +0000
Subject: [PATCH 07/14] packet: Do not call fanout_release from atomic contexts

[ Upstream commit 2bd624b4611ffee36422782d16e1c944d1351e98 ]

Commit 6664498280cf ("packet: call fanout_release, while UNREGISTERING a
netdev"), unfortunately, introduced the following issues.

1. calling mutex_lock(&fanout_mutex) (fanout_release()) from inside
rcu_read-side critical section. rcu_read_lock disables preemption, most often,
which prohibits calling sleeping functions.

[  ] include/linux/rcupdate.h:560 Illegal context switch in RCU read-side critical section!
[  ]
[  ] rcu_scheduler_active = 1, debug_locks = 0
[  ] 4 locks held by ovs-vswitchd/1969:
[  ]  #0:  (cb_lock){++++++}, at: [<ffffffff8158a6c9>] genl_rcv+0x19/0x40
[  ]  #1:  (ovs_mutex){+.+.+.}, at: [<ffffffffa04878ca>] ovs_vport_cmd_del+0x4a/0x100 [openvswitch]
[  ]  #2:  (rtnl_mutex){+.+.+.}, at: [<ffffffff81564157>] rtnl_lock+0x17/0x20
[  ]  #3:  (rcu_read_lock){......}, at: [<ffffffff81614165>] packet_notifier+0x5/0x3f0
[  ]
[  ] Call Trace:
[  ]  [<ffffffff813770c1>] dump_stack+0x85/0xc4
[  ]  [<ffffffff810c9077>] lockdep_rcu_suspicious+0x107/0x110
[  ]  [<ffffffff810a2da7>] ___might_sleep+0x57/0x210
[  ]  [<ffffffff810a2fd0>] __might_sleep+0x70/0x90
[  ]  [<ffffffff8162e80c>] mutex_lock_nested+0x3c/0x3a0
[  ]  [<ffffffff810de93f>] ? vprintk_default+0x1f/0x30
[  ]  [<ffffffff81186e88>] ? printk+0x4d/0x4f
[  ]  [<ffffffff816106dd>] fanout_release+0x1d/0xe0
[  ]  [<ffffffff81614459>] packet_notifier+0x2f9/0x3f0

2. calling mutex_lock(&fanout_mutex) inside spin_lock(&po->bind_lock).
"sleeping function called from invalid context"

[  ] BUG: sleeping function called from invalid context at kernel/locking/mutex.c:620
[  ] in_atomic(): 1, irqs_disabled(): 0, pid: 1969, name: ovs-vswitchd
[  ] INFO: lockdep is turned off.
[  ] Call Trace:
[  ]  [<ffffffff813770c1>] dump_stack+0x85/0xc4
[  ]  [<ffffffff810a2f52>] ___might_sleep+0x202/0x210
[  ]  [<ffffffff810a2fd0>] __might_sleep+0x70/0x90
[  ]  [<ffffffff8162e80c>] mutex_lock_nested+0x3c/0x3a0
[  ]  [<ffffffff816106dd>] fanout_release+0x1d/0xe0
[  ]  [<ffffffff81614459>] packet_notifier+0x2f9/0x3f0

3. calling dev_remove_pack(&fanout->prot_hook), from inside
spin_lock(&po->bind_lock) or rcu_read-side critical-section. dev_remove_pack()
-> synchronize_net(), which might sleep.

[  ] BUG: scheduling while atomic: ovs-vswitchd/1969/0x00000002
[  ] INFO: lockdep is turned off.
[  ] Call Trace:
[  ]  [<ffffffff813770c1>] dump_stack+0x85/0xc4
[  ]  [<ffffffff81186274>] __schedule_bug+0x64/0x73
[  ]  [<ffffffff8162b8cb>] __schedule+0x6b/0xd10
[  ]  [<ffffffff8162c5db>] schedule+0x6b/0x80
[  ]  [<ffffffff81630b1d>] schedule_timeout+0x38d/0x410
[  ]  [<ffffffff810ea3fd>] synchronize_sched_expedited+0x53d/0x810
[  ]  [<ffffffff810ea6de>] synchronize_rcu_expedited+0xe/0x10
[  ]  [<ffffffff8154eab5>] synchronize_net+0x35/0x50
[  ]  [<ffffffff8154eae3>] dev_remove_pack+0x13/0x20
[  ]  [<ffffffff8161077e>] fanout_release+0xbe/0xe0
[  ]  [<ffffffff81614459>] packet_notifier+0x2f9/0x3f0

4. fanout_release() races with calls from different CPU.

To fix the above problems, remove the call to fanout_release() under
rcu_read_lock(). Instead, call __dev_remove_pack(&fanout->prot_hook) and
netdev_run_todo will be happy that &dev->ptype_specific list is empty. In order
to achieve this, I moved dev_{add,remove}_pack() out of fanout_{add,release} to
__fanout_{link,unlink}. So, call to {,__}unregister_prot_hook() will make sure
fanout->prot_hook is removed as well.

Fixes: 6664498280cf ("packet: call fanout_release, while UNREGISTERING a netdev")
Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Anoob Soman <anoob.soman@citrix.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 31 ++++++++++++++++++++++---------
 1 file changed, 22 insertions(+), 9 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 87113e86..34de326 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1497,6 +1497,8 @@ static void __fanout_link(struct sock *sk, struct packet_sock *po)
 	f->arr[f->num_members] = sk;
 	smp_wmb();
 	f->num_members++;
+	if (f->num_members == 1)
+		dev_add_pack(&f->prot_hook);
 	spin_unlock(&f->lock);
 }
 
@@ -1513,6 +1515,8 @@ static void __fanout_unlink(struct sock *sk, struct packet_sock *po)
 	BUG_ON(i >= f->num_members);
 	f->arr[i] = f->arr[f->num_members - 1];
 	f->num_members--;
+	if (f->num_members == 0)
+		__dev_remove_pack(&f->prot_hook);
 	spin_unlock(&f->lock);
 }
 
@@ -1693,7 +1697,6 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		match->prot_hook.func = packet_rcv_fanout;
 		match->prot_hook.af_packet_priv = match;
 		match->prot_hook.id_match = match_fanout_group;
-		dev_add_pack(&match->prot_hook);
 		list_add(&match->list, &fanout_list);
 	}
 	err = -EINVAL;
@@ -1718,7 +1721,12 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 	return err;
 }
 
-static void fanout_release(struct sock *sk)
+/* If pkt_sk(sk)->fanout->sk_ref is zero, this function removes
+ * pkt_sk(sk)->fanout from fanout_list and returns pkt_sk(sk)->fanout.
+ * It is the responsibility of the caller to call fanout_release_data() and
+ * free the returned packet_fanout (after synchronize_net())
+ */
+static struct packet_fanout *fanout_release(struct sock *sk)
 {
 	struct packet_sock *po = pkt_sk(sk);
 	struct packet_fanout *f;
@@ -1728,17 +1736,17 @@ static void fanout_release(struct sock *sk)
 	if (f) {
 		po->fanout = NULL;
 
-		if (atomic_dec_and_test(&f->sk_ref)) {
+		if (atomic_dec_and_test(&f->sk_ref))
 			list_del(&f->list);
-			dev_remove_pack(&f->prot_hook);
-			fanout_release_data(f);
-			kfree(f);
-		}
+		else
+			f = NULL;
 
 		if (po->rollover)
 			kfree_rcu(po->rollover, rcu);
 	}
 	mutex_unlock(&fanout_mutex);
+
+	return f;
 }
 
 static bool packet_extra_vlan_len_allowed(const struct net_device *dev,
@@ -2970,6 +2978,7 @@ static int packet_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
 	struct packet_sock *po;
+	struct packet_fanout *f;
 	struct net *net;
 	union tpacket_req_u req_u;
 
@@ -3009,9 +3018,14 @@ static int packet_release(struct socket *sock)
 		packet_set_ring(sk, &req_u, 1, 1);
 	}
 
-	fanout_release(sk);
+	f = fanout_release(sk);
 
 	synchronize_net();
+
+	if (f) {
+		fanout_release_data(f);
+		kfree(f);
+	}
 	/*
 	 *	Now the socket is dead. No more input will appear.
 	 */
@@ -3963,7 +3977,6 @@ static int packet_notifier(struct notifier_block *this,
 				}
 				if (msg == NETDEV_UNREGISTER) {
 					packet_cached_dev_reset(po);
-					fanout_release(sk);
 					po->ifindex = -1;
 					if (po->prot_hook.dev)
 						dev_put(po->prot_hook.dev);
-- 
2.4.11


From 9712a7e62a28742dc95793b6acb65703c9ede52b Mon Sep 17 00:00:00 2001
From: Marcus Huewe <suse-tux@gmx.de>
Date: Wed, 15 Feb 2017 01:00:36 +0100
Subject: [PATCH 08/14] net: neigh: Fix netevent
 NETEVENT_DELAY_PROBE_TIME_UPDATE notification

[ Upstream commit 7627ae6030f56a9a91a5b3867b21f35d79c16e64 ]

When setting a neigh related sysctl parameter, we always send a
NETEVENT_DELAY_PROBE_TIME_UPDATE netevent. For instance, when
executing

	sysctl net.ipv6.neigh.wlp3s0.retrans_time_ms=2000

a NETEVENT_DELAY_PROBE_TIME_UPDATE netevent is generated.

This is caused by commit 2a4501ae18b5 ("neigh: Send a
notification when DELAY_PROBE_TIME changes"). According to the
commit's description, it was intended to generate such an event
when setting the "delay_first_probe_time" sysctl parameter.

In order to fix this, only generate this event when actually
setting the "delay_first_probe_time" sysctl parameter. This fix
should not have any unintended side-effects, because all but one
registered netevent callbacks check for other netevent event
types (the registered callbacks were obtained by grepping for
"register_netevent_notifier"). The only callback that uses the
NETEVENT_DELAY_PROBE_TIME_UPDATE event is
mlxsw_sp_router_netevent_event() (in
drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c): in case
of this event, it only accesses the DELAY_PROBE_TIME of the
passed neigh_parms.

Fixes: 2a4501ae18b5 ("neigh: Send a notification when DELAY_PROBE_TIME changes")
Signed-off-by: Marcus Huewe <suse-tux@gmx.de>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 2ae929f..9901e5b 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2927,7 +2927,8 @@ static void neigh_proc_update(struct ctl_table *ctl, int write)
 		return;
 
 	set_bit(index, p->data_state);
-	call_netevent_notifiers(NETEVENT_DELAY_PROBE_TIME_UPDATE, p);
+	if (index == NEIGH_VAR_DELAY_PROBE_TIME)
+		call_netevent_notifiers(NETEVENT_DELAY_PROBE_TIME_UPDATE, p);
 	if (!dev) /* NULL dev means this is default value */
 		neigh_copy_dflt_parms(net, p, index);
 }
-- 
2.4.11


From 6915736f4655fc5111bbef9f15fff5df4d288173 Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Thu, 16 Feb 2017 17:22:46 +0100
Subject: [PATCH 09/14] dccp: fix freeing skb too early for IPV6_RECVPKTINFO

[ Upstream commit 5edabca9d4cff7f1f2b68f0bac55ef99d9798ba4 ]

In the current DCCP implementation an skb for a DCCP_PKT_REQUEST packet
is forcibly freed via __kfree_skb in dccp_rcv_state_process if
dccp_v6_conn_request successfully returns.

However, if IPV6_RECVPKTINFO is set on a socket, the address of the skb
is saved to ireq->pktopts and the ref count for skb is incremented in
dccp_v6_conn_request, so skb is still in use. Nevertheless, it gets freed
in dccp_rcv_state_process.

Fix by calling consume_skb instead of doing goto discard and therefore
calling __kfree_skb.

Similar fixes for TCP:

fb7e2399ec17f1004c0e0ccfd17439f8759ede01 [TCP]: skb is unexpectedly freed.
0aea76d35c9651d55bbaf746e7914e5f9ae5a25d tcp: SYN packets are now
simply consumed

Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/input.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/dccp/input.c b/net/dccp/input.c
index ba34718..8fedc2d 100644
--- a/net/dccp/input.c
+++ b/net/dccp/input.c
@@ -606,7 +606,8 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 			if (inet_csk(sk)->icsk_af_ops->conn_request(sk,
 								    skb) < 0)
 				return 1;
-			goto discard;
+			consume_skb(skb);
+			return 0;
 		}
 		if (dh->dccph_type == DCCP_PKT_RESET)
 			goto discard;
-- 
2.4.11


From 08493f2a2f32d57c7fd03e7ce7dfa2e5ed595b8f Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 17 Feb 2017 19:14:27 +0100
Subject: [PATCH 10/14] vxlan: fix oops in dev_fill_metadata_dst

[ Upstream commit 22f0708a718daea5e79de2d29b4829de016a4ff4 ]

Since the commit 0c1d70af924b ("net: use dst_cache for vxlan device")
vxlan_fill_metadata_dst() calls vxlan_get_route() passing a NULL
dst_cache pointer, so the latter should explicitly check for
valid dst_cache ptr. Unfortunately the commit d71785ffc7e7 ("net: add
dst_cache to ovs vxlan lwtunnel") removed said check.

As a result is possible to trigger a null pointer access calling
vxlan_fill_metadata_dst(), e.g. with:

ovs-vsctl add-br ovs-br0
ovs-vsctl add-port ovs-br0 vxlan0 -- set interface vxlan0 \
	type=vxlan options:remote_ip=192.168.1.1 \
	options:key=1234 options:dst_port=4789 ofport_request=10
ip address add dev ovs-br0 172.16.1.2/24
ovs-vsctl set Bridge ovs-br0 ipfix=@i -- --id=@i create IPFIX \
	targets=\"172.16.1.1:1234\" sampling=1
iperf -c 172.16.1.1 -u -l 1000 -b 10M -t 1 -p 1234

This commit addresses the issue passing to vxlan_get_route() the
dst_cache already available into the lwt info processed by
vxlan_fill_metadata_dst().

Fixes: d71785ffc7e7 ("net: add dst_cache to ovs vxlan lwtunnel")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 0fafaa9..d4f495b 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2449,7 +2449,8 @@ static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 			return -EINVAL;
 		rt = vxlan_get_route(vxlan, skb, 0, info->key.tos,
 				     info->key.u.ipv4.dst,
-				     &info->key.u.ipv4.src, NULL, info);
+				     &info->key.u.ipv4.src,
+				     &info->dst_cache, info);
 		if (IS_ERR(rt))
 			return PTR_ERR(rt);
 		ip_rt_put(rt);
@@ -2459,7 +2460,8 @@ static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 
 		ndst = vxlan6_get_route(vxlan, skb, 0, info->key.tos,
 					info->key.label, &info->key.u.ipv6.dst,
-					&info->key.u.ipv6.src, NULL, info);
+					&info->key.u.ipv6.src,
+					&info->dst_cache, info);
 		if (IS_ERR(ndst))
 			return PTR_ERR(ndst);
 		dst_release(ndst);
-- 
2.4.11


From 2adc40c8c42203f12b97efeba7a7a587ccba24e4 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 17 Feb 2017 16:19:39 -0500
Subject: [PATCH 11/14] irda: Fix lockdep annotations in hashbin_delete().

[ Upstream commit 4c03b862b12f980456f9de92db6d508a4999b788 ]

A nested lock depth was added to the hasbin_delete() code but it
doesn't actually work some well and results in tons of lockdep splats.

Fix the code instead to properly drop the lock around the operation
and just keep peeking the head of the hashbin queue.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Tested-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/irda/irqueue.c | 34 ++++++++++++++++------------------
 1 file changed, 16 insertions(+), 18 deletions(-)

diff --git a/net/irda/irqueue.c b/net/irda/irqueue.c
index acbe61c..160dc89 100644
--- a/net/irda/irqueue.c
+++ b/net/irda/irqueue.c
@@ -383,9 +383,6 @@ EXPORT_SYMBOL(hashbin_new);
  *    for deallocating this structure if it's complex. If not the user can
  *    just supply kfree, which should take care of the job.
  */
-#ifdef CONFIG_LOCKDEP
-static int hashbin_lock_depth = 0;
-#endif
 int hashbin_delete( hashbin_t* hashbin, FREE_FUNC free_func)
 {
 	irda_queue_t* queue;
@@ -396,22 +393,27 @@ int hashbin_delete( hashbin_t* hashbin, FREE_FUNC free_func)
 	IRDA_ASSERT(hashbin->magic == HB_MAGIC, return -1;);
 
 	/* Synchronize */
-	if ( hashbin->hb_type & HB_LOCK ) {
-		spin_lock_irqsave_nested(&hashbin->hb_spinlock, flags,
-					 hashbin_lock_depth++);
-	}
+	if (hashbin->hb_type & HB_LOCK)
+		spin_lock_irqsave(&hashbin->hb_spinlock, flags);
 
 	/*
 	 *  Free the entries in the hashbin, TODO: use hashbin_clear when
 	 *  it has been shown to work
 	 */
 	for (i = 0; i < HASHBIN_SIZE; i ++ ) {
-		queue = dequeue_first((irda_queue_t**) &hashbin->hb_queue[i]);
-		while (queue ) {
-			if (free_func)
-				(*free_func)(queue);
-			queue = dequeue_first(
-				(irda_queue_t**) &hashbin->hb_queue[i]);
+		while (1) {
+			queue = dequeue_first((irda_queue_t**) &hashbin->hb_queue[i]);
+
+			if (!queue)
+				break;
+
+			if (free_func) {
+				if (hashbin->hb_type & HB_LOCK)
+					spin_unlock_irqrestore(&hashbin->hb_spinlock, flags);
+				free_func(queue);
+				if (hashbin->hb_type & HB_LOCK)
+					spin_lock_irqsave(&hashbin->hb_spinlock, flags);
+			}
 		}
 	}
 
@@ -420,12 +422,8 @@ int hashbin_delete( hashbin_t* hashbin, FREE_FUNC free_func)
 	hashbin->magic = ~HB_MAGIC;
 
 	/* Release lock */
-	if ( hashbin->hb_type & HB_LOCK) {
+	if (hashbin->hb_type & HB_LOCK)
 		spin_unlock_irqrestore(&hashbin->hb_spinlock, flags);
-#ifdef CONFIG_LOCKDEP
-		hashbin_lock_depth--;
-#endif
-	}
 
 	/*
 	 *  Free the hashbin structure
-- 
2.4.11


From 4882ac3375c0e80f17426c01434e52aee82f53be Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Sun, 19 Feb 2017 07:17:17 +0200
Subject: [PATCH 12/14] ptr_ring: fix race conditions when resizing

[ Upstream commit e71695307114335be1ed912f4a347396c2ed0e69 ]

Resizing currently drops consumer lock.  This can cause entries to be
reordered, which isn't good in itself.  More importantly, consumer can
detect a false ring empty condition and block forever.

Further, nesting of consumer within producer lock is problematic for
tun, since it produces entries in a BH, which causes a lock order
reversal:

       CPU0                    CPU1
       ----                    ----
  consume:
  lock(&(&r->consumer_lock)->rlock);
                               resize:
                               local_irq_disable();
                               lock(&(&r->producer_lock)->rlock);
                               lock(&(&r->consumer_lock)->rlock);
  <Interrupt>
  produce:
  lock(&(&r->producer_lock)->rlock);

To fix, nest producer lock within consumer lock during resize,
and keep consumer lock during the whole swap operation.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: stable@vger.kernel.org
Cc: "David S. Miller" <davem@davemloft.net>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ptr_ring.h | 36 +++++++++++++++++++++++++++++++-----
 1 file changed, 31 insertions(+), 5 deletions(-)

diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h
index 2052011..6c70444 100644
--- a/include/linux/ptr_ring.h
+++ b/include/linux/ptr_ring.h
@@ -111,6 +111,11 @@ static inline int __ptr_ring_produce(struct ptr_ring *r, void *ptr)
 	return 0;
 }
 
+/*
+ * Note: resize (below) nests producer lock within consumer lock, so if you
+ * consume in interrupt or BH context, you must disable interrupts/BH when
+ * calling this.
+ */
 static inline int ptr_ring_produce(struct ptr_ring *r, void *ptr)
 {
 	int ret;
@@ -242,6 +247,11 @@ static inline void *__ptr_ring_consume(struct ptr_ring *r)
 	return ptr;
 }
 
+/*
+ * Note: resize (below) nests producer lock within consumer lock, so if you
+ * call this in interrupt or BH context, you must disable interrupts/BH when
+ * producing.
+ */
 static inline void *ptr_ring_consume(struct ptr_ring *r)
 {
 	void *ptr;
@@ -357,7 +367,7 @@ static inline void **__ptr_ring_swap_queue(struct ptr_ring *r, void **queue,
 	void **old;
 	void *ptr;
 
-	while ((ptr = ptr_ring_consume(r)))
+	while ((ptr = __ptr_ring_consume(r)))
 		if (producer < size)
 			queue[producer++] = ptr;
 		else if (destroy)
@@ -372,6 +382,12 @@ static inline void **__ptr_ring_swap_queue(struct ptr_ring *r, void **queue,
 	return old;
 }
 
+/*
+ * Note: producer lock is nested within consumer lock, so if you
+ * resize you must make sure all uses nest correctly.
+ * In particular if you consume ring in interrupt or BH context, you must
+ * disable interrupts/BH when doing so.
+ */
 static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp,
 				  void (*destroy)(void *))
 {
@@ -382,17 +398,25 @@ static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp,
 	if (!queue)
 		return -ENOMEM;
 
-	spin_lock_irqsave(&(r)->producer_lock, flags);
+	spin_lock_irqsave(&(r)->consumer_lock, flags);
+	spin_lock(&(r)->producer_lock);
 
 	old = __ptr_ring_swap_queue(r, queue, size, gfp, destroy);
 
-	spin_unlock_irqrestore(&(r)->producer_lock, flags);
+	spin_unlock(&(r)->producer_lock);
+	spin_unlock_irqrestore(&(r)->consumer_lock, flags);
 
 	kfree(old);
 
 	return 0;
 }
 
+/*
+ * Note: producer lock is nested within consumer lock, so if you
+ * resize you must make sure all uses nest correctly.
+ * In particular if you consume ring in interrupt or BH context, you must
+ * disable interrupts/BH when doing so.
+ */
 static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, int nrings,
 					   int size,
 					   gfp_t gfp, void (*destroy)(void *))
@@ -412,10 +436,12 @@ static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, int nrings,
 	}
 
 	for (i = 0; i < nrings; ++i) {
-		spin_lock_irqsave(&(rings[i])->producer_lock, flags);
+		spin_lock_irqsave(&(rings[i])->consumer_lock, flags);
+		spin_lock(&(rings[i])->producer_lock);
 		queues[i] = __ptr_ring_swap_queue(rings[i], queues[i],
 						  size, gfp, destroy);
-		spin_unlock_irqrestore(&(rings[i])->producer_lock, flags);
+		spin_unlock(&(rings[i])->producer_lock);
+		spin_unlock_irqrestore(&(rings[i])->consumer_lock, flags);
 	}
 
 	for (i = 0; i < nrings; ++i)
-- 
2.4.11


From 64f0de9c27c1a3937be0fbd9c61d14e12dc063da Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 21 Feb 2017 09:33:18 +0100
Subject: [PATCH 13/14] ip: fix IP_CHECKSUM handling

[ Upstream commit ca4ef4574f1ee5252e2cd365f8f5d5bafd048f32 ]

The skbs processed by ip_cmsg_recv() are not guaranteed to
be linear e.g. when sending UDP packets over loopback with
MSGMORE.
Using csum_partial() on [potentially] the whole skb len
is dangerous; instead be on the safe side and use skb_checksum().

Thanks to syzkaller team to detect the issue and provide the
reproducer.

v1 -> v2:
 - move the variable declaration in a tighter scope

Fixes: ad6f939ab193 ("ip: Add offset parameter to ip_cmsg_recv")
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_sockglue.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 65336f3..9826695 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -105,10 +105,10 @@ static void ip_cmsg_recv_checksum(struct msghdr *msg, struct sk_buff *skb,
 	if (skb->ip_summed != CHECKSUM_COMPLETE)
 		return;
 
-	if (offset != 0)
-		csum = csum_sub(csum,
-				csum_partial(skb_transport_header(skb) + tlen,
-					     offset, 0));
+	if (offset != 0) {
+		int tend_off = skb_transport_offset(skb) + tlen;
+		csum = csum_sub(csum, skb_checksum(skb, tend_off, offset, 0));
+	}
 
 	put_cmsg(msg, SOL_IP, IP_CHECKSUM, sizeof(__wsum), &csum);
 }
-- 
2.4.11


From ffc3e173c11dd5e1279e3ac5e0d26554993fffdf Mon Sep 17 00:00:00 2001
From: Maxime Jayat <maxime.jayat@mobile-devices.fr>
Date: Tue, 21 Feb 2017 18:35:51 +0100
Subject: [PATCH 14/14] net: socket: fix recvmmsg not returning error from
 sock_error

[ Upstream commit e623a9e9dec29ae811d11f83d0074ba254aba374 ]

Commit 34b88a68f26a ("net: Fix use after free in the recvmmsg exit path"),
changed the exit path of recvmmsg to always return the datagrams
variable and modified the error paths to set the variable to the error
code returned by recvmsg if necessary.

However in the case sock_error returned an error, the error code was
then ignored, and recvmmsg returned 0.

Change the error path of recvmmsg to correctly return the error code
of sock_error.

The bug was triggered by using recvmmsg on a CAN interface which was
not up. Linux 4.6 and later return 0 in this case while earlier
releases returned -ENETDOWN.

Fixes: 34b88a68f26a ("net: Fix use after free in the recvmmsg exit path")
Signed-off-by: Maxime Jayat <maxime.jayat@mobile-devices.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/socket.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/socket.c b/net/socket.c
index 73dc69f..6bbccf0 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2197,8 +2197,10 @@ int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
 		return err;
 
 	err = sock_error(sock->sk);
-	if (err)
+	if (err) {
+		datagrams = err;
 		goto out_put;
+	}
 
 	entry = mmsg;
 	compat_entry = (struct compat_mmsghdr __user *)mmsg;
-- 
2.4.11


[-- Attachment #4: net_410.mbox --]
[-- Type: Application/Octet-Stream, Size: 7899 bytes --]

From c39daf1ec310c6f330863e581fa29741906d0a48 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Sun, 19 Feb 2017 07:17:17 +0200
Subject: [PATCH 1/3] ptr_ring: fix race conditions when resizing

[ Upstream commit e71695307114335be1ed912f4a347396c2ed0e69 ]

Resizing currently drops consumer lock.  This can cause entries to be
reordered, which isn't good in itself.  More importantly, consumer can
detect a false ring empty condition and block forever.

Further, nesting of consumer within producer lock is problematic for
tun, since it produces entries in a BH, which causes a lock order
reversal:

       CPU0                    CPU1
       ----                    ----
  consume:
  lock(&(&r->consumer_lock)->rlock);
                               resize:
                               local_irq_disable();
                               lock(&(&r->producer_lock)->rlock);
                               lock(&(&r->consumer_lock)->rlock);
  <Interrupt>
  produce:
  lock(&(&r->producer_lock)->rlock);

To fix, nest producer lock within consumer lock during resize,
and keep consumer lock during the whole swap operation.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: stable@vger.kernel.org
Cc: "David S. Miller" <davem@davemloft.net>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ptr_ring.h | 36 +++++++++++++++++++++++++++++++-----
 1 file changed, 31 insertions(+), 5 deletions(-)

diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h
index 2052011..6c70444 100644
--- a/include/linux/ptr_ring.h
+++ b/include/linux/ptr_ring.h
@@ -111,6 +111,11 @@ static inline int __ptr_ring_produce(struct ptr_ring *r, void *ptr)
 	return 0;
 }
 
+/*
+ * Note: resize (below) nests producer lock within consumer lock, so if you
+ * consume in interrupt or BH context, you must disable interrupts/BH when
+ * calling this.
+ */
 static inline int ptr_ring_produce(struct ptr_ring *r, void *ptr)
 {
 	int ret;
@@ -242,6 +247,11 @@ static inline void *__ptr_ring_consume(struct ptr_ring *r)
 	return ptr;
 }
 
+/*
+ * Note: resize (below) nests producer lock within consumer lock, so if you
+ * call this in interrupt or BH context, you must disable interrupts/BH when
+ * producing.
+ */
 static inline void *ptr_ring_consume(struct ptr_ring *r)
 {
 	void *ptr;
@@ -357,7 +367,7 @@ static inline void **__ptr_ring_swap_queue(struct ptr_ring *r, void **queue,
 	void **old;
 	void *ptr;
 
-	while ((ptr = ptr_ring_consume(r)))
+	while ((ptr = __ptr_ring_consume(r)))
 		if (producer < size)
 			queue[producer++] = ptr;
 		else if (destroy)
@@ -372,6 +382,12 @@ static inline void **__ptr_ring_swap_queue(struct ptr_ring *r, void **queue,
 	return old;
 }
 
+/*
+ * Note: producer lock is nested within consumer lock, so if you
+ * resize you must make sure all uses nest correctly.
+ * In particular if you consume ring in interrupt or BH context, you must
+ * disable interrupts/BH when doing so.
+ */
 static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp,
 				  void (*destroy)(void *))
 {
@@ -382,17 +398,25 @@ static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp,
 	if (!queue)
 		return -ENOMEM;
 
-	spin_lock_irqsave(&(r)->producer_lock, flags);
+	spin_lock_irqsave(&(r)->consumer_lock, flags);
+	spin_lock(&(r)->producer_lock);
 
 	old = __ptr_ring_swap_queue(r, queue, size, gfp, destroy);
 
-	spin_unlock_irqrestore(&(r)->producer_lock, flags);
+	spin_unlock(&(r)->producer_lock);
+	spin_unlock_irqrestore(&(r)->consumer_lock, flags);
 
 	kfree(old);
 
 	return 0;
 }
 
+/*
+ * Note: producer lock is nested within consumer lock, so if you
+ * resize you must make sure all uses nest correctly.
+ * In particular if you consume ring in interrupt or BH context, you must
+ * disable interrupts/BH when doing so.
+ */
 static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, int nrings,
 					   int size,
 					   gfp_t gfp, void (*destroy)(void *))
@@ -412,10 +436,12 @@ static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, int nrings,
 	}
 
 	for (i = 0; i < nrings; ++i) {
-		spin_lock_irqsave(&(rings[i])->producer_lock, flags);
+		spin_lock_irqsave(&(rings[i])->consumer_lock, flags);
+		spin_lock(&(rings[i])->producer_lock);
 		queues[i] = __ptr_ring_swap_queue(rings[i], queues[i],
 						  size, gfp, destroy);
-		spin_unlock_irqrestore(&(rings[i])->producer_lock, flags);
+		spin_unlock(&(rings[i])->producer_lock);
+		spin_unlock_irqrestore(&(rings[i])->consumer_lock, flags);
 	}
 
 	for (i = 0; i < nrings; ++i)
-- 
2.4.11


From ec2f2b52efe7347acc4faed886dc882558f6ca99 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 21 Feb 2017 09:33:18 +0100
Subject: [PATCH 2/3] ip: fix IP_CHECKSUM handling

[ Upstream commit ca4ef4574f1ee5252e2cd365f8f5d5bafd048f32 ]

The skbs processed by ip_cmsg_recv() are not guaranteed to
be linear e.g. when sending UDP packets over loopback with
MSGMORE.
Using csum_partial() on [potentially] the whole skb len
is dangerous; instead be on the safe side and use skb_checksum().

Thanks to syzkaller team to detect the issue and provide the
reproducer.

v1 -> v2:
 - move the variable declaration in a tighter scope

Fixes: ad6f939ab193 ("ip: Add offset parameter to ip_cmsg_recv")
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_sockglue.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 9000117..fc4bf4d 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -116,10 +116,10 @@ static void ip_cmsg_recv_checksum(struct msghdr *msg, struct sk_buff *skb,
 	if (skb->ip_summed != CHECKSUM_COMPLETE)
 		return;
 
-	if (offset != 0)
-		csum = csum_sub(csum,
-				csum_partial(skb_transport_header(skb) + tlen,
-					     offset, 0));
+	if (offset != 0) {
+		int tend_off = skb_transport_offset(skb) + tlen;
+		csum = csum_sub(csum, skb_checksum(skb, tend_off, offset, 0));
+	}
 
 	put_cmsg(msg, SOL_IP, IP_CHECKSUM, sizeof(__wsum), &csum);
 }
-- 
2.4.11


From f09b5543584583f25e7caf789dd00d3fe4117cef Mon Sep 17 00:00:00 2001
From: Maxime Jayat <maxime.jayat@mobile-devices.fr>
Date: Tue, 21 Feb 2017 18:35:51 +0100
Subject: [PATCH 3/3] net: socket: fix recvmmsg not returning error from
 sock_error

[ Upstream commit e623a9e9dec29ae811d11f83d0074ba254aba374 ]

Commit 34b88a68f26a ("net: Fix use after free in the recvmmsg exit path"),
changed the exit path of recvmmsg to always return the datagrams
variable and modified the error paths to set the variable to the error
code returned by recvmsg if necessary.

However in the case sock_error returned an error, the error code was
then ignored, and recvmmsg returned 0.

Change the error path of recvmmsg to correctly return the error code
of sock_error.

The bug was triggered by using recvmmsg on a CAN interface which was
not up. Linux 4.6 and later return 0 in this case while earlier
releases returned -ENETDOWN.

Fixes: 34b88a68f26a ("net: Fix use after free in the recvmmsg exit path")
Signed-off-by: Maxime Jayat <maxime.jayat@mobile-devices.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/socket.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/socket.c b/net/socket.c
index 0758e13..02bd924 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2228,8 +2228,10 @@ int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
 		return err;
 
 	err = sock_error(sock->sk);
-	if (err)
+	if (err) {
+		datagrams = err;
 		goto out_put;
+	}
 
 	entry = mmsg;
 	compat_entry = (struct compat_mmsghdr __user *)mmsg;
-- 
2.4.11

Re: [PATCHES] Networking

[Greg KH]

On Thu, Feb 23, 2017 at 02:54:47PM -0500, David Miller wrote:
> 
> Please queue up the following networking bug fixes for 4.4.x, 4.9.x,
> and 4.10.x -stable, respectively.

Wonderful, thanks so much for these, all now queued up.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 95 bytes --]


Please queue up the following bug fixes for v4.9 and v4.10 -stable,
respectively.

Thank you!

[-- Attachment #2: net_49.mbox --]
[-- Type: Application/Octet-Stream, Size: 123038 bytes --]

From 54bb092929689ea854124b11ee85963775f8d484 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Wed, 22 Feb 2017 17:20:12 +0200
Subject: [PATCH 01/41] net/mlx5e: Register/unregister vport representors on
 interface attach/detach

[ Upstream commit 6f08a22c5fb2b9aefb8ecd8496758e7a677c1fde ]

Currently vport representors are added only on driver load and removed on
driver unload.  Apparently we forgot to handle them when we added the
seamless reset flow feature.  This caused to leave the representors
netdevs alive and active with open HW resources on pci shutdown and on
error reset flows.

To overcome this we move their handling to interface attach/detach, so
they would be cleaned up on shutdown and recreated on reset flows.

Fixes: 26e59d8077a3 ("net/mlx5e: Implement mlx5e interface attach/detach callbacks")
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Hadar Hen Zion <hadarh@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 23 +++++++++++++++--------
 1 file changed, 15 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index b3067137..8657b3b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3936,6 +3936,19 @@ static void mlx5e_register_vport_rep(struct mlx5_core_dev *mdev)
 	}
 }
 
+static void mlx5e_unregister_vport_rep(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_eswitch *esw = mdev->priv.eswitch;
+	int total_vfs = MLX5_TOTAL_VPORTS(mdev);
+	int vport;
+
+	if (!MLX5_CAP_GEN(mdev, vport_group_manager))
+		return;
+
+	for (vport = 1; vport < total_vfs; vport++)
+		mlx5_eswitch_unregister_vport_rep(esw, vport);
+}
+
 void mlx5e_detach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -3983,6 +3996,7 @@ static int mlx5e_attach(struct mlx5_core_dev *mdev, void *vpriv)
 		return err;
 	}
 
+	mlx5e_register_vport_rep(mdev);
 	return 0;
 }
 
@@ -3994,6 +4008,7 @@ static void mlx5e_detach(struct mlx5_core_dev *mdev, void *vpriv)
 	if (!netif_device_present(netdev))
 		return;
 
+	mlx5e_unregister_vport_rep(mdev);
 	mlx5e_detach_netdev(mdev, netdev);
 	mlx5e_destroy_mdev_resources(mdev);
 }
@@ -4012,8 +4027,6 @@ static void *mlx5e_add(struct mlx5_core_dev *mdev)
 	if (err)
 		return NULL;
 
-	mlx5e_register_vport_rep(mdev);
-
 	if (MLX5_CAP_GEN(mdev, vport_group_manager))
 		ppriv = &esw->offloads.vport_reps[0];
 
@@ -4065,13 +4078,7 @@ void mlx5e_destroy_netdev(struct mlx5_core_dev *mdev, struct mlx5e_priv *priv)
 
 static void mlx5e_remove(struct mlx5_core_dev *mdev, void *vpriv)
 {
-	struct mlx5_eswitch *esw = mdev->priv.eswitch;
-	int total_vfs = MLX5_TOTAL_VPORTS(mdev);
 	struct mlx5e_priv *priv = vpriv;
-	int vport;
-
-	for (vport = 1; vport < total_vfs; vport++)
-		mlx5_eswitch_unregister_vport_rep(esw, vport);
 
 	unregister_netdev(priv->netdev);
 	mlx5e_detach(mdev, vpriv);
-- 
2.1.0


From 771085dc9a099199efb93951b273e745ce47837d Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Wed, 22 Feb 2017 17:20:13 +0200
Subject: [PATCH 02/41] net/mlx5e: Do not reduce LRO WQE size when not using
 build_skb

[ Upstream commit 4078e637c12f1e0a74293f1ec9563f42bff14a03 ]

When rq_type is Striding RQ, no room of SKB_RESERVE is needed
as SKB allocation is not done via build_skb.

Fixes: e4b85508072b ("net/mlx5e: Slightly reduce hardware LRO size")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 8657b3b..d4fa851 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -81,6 +81,7 @@ static bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
 static void mlx5e_set_rq_type_params(struct mlx5e_priv *priv, u8 rq_type)
 {
 	priv->params.rq_wq_type = rq_type;
+	priv->params.lro_wqe_sz = MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ;
 	switch (priv->params.rq_wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
 		priv->params.log_rq_size = MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE_MPW;
@@ -92,6 +93,10 @@ static void mlx5e_set_rq_type_params(struct mlx5e_priv *priv, u8 rq_type)
 		break;
 	default: /* MLX5_WQ_TYPE_LINKED_LIST */
 		priv->params.log_rq_size = MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE;
+
+		/* Extra room needed for build_skb */
+		priv->params.lro_wqe_sz -= MLX5_RX_HEADROOM +
+			SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 	}
 	priv->params.min_rx_wqes = mlx5_min_rx_wqes(priv->params.rq_wq_type,
 					       BIT(priv->params.log_rq_size));
@@ -3473,12 +3478,6 @@ static void mlx5e_build_nic_netdev_priv(struct mlx5_core_dev *mdev,
 	mlx5e_build_default_indir_rqt(mdev, priv->params.indirection_rqt,
 				      MLX5E_INDIR_RQT_SIZE, profile->max_nch(mdev));
 
-	priv->params.lro_wqe_sz =
-		MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ -
-		/* Extra room needed for build_skb */
-		MLX5_RX_HEADROOM -
-		SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-
 	/* Initialize pflags */
 	MLX5E_SET_PRIV_FLAG(priv, MLX5E_PFLAG_RX_CQE_BASED_MODER,
 			    priv->params.rx_cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE);
-- 
2.1.0


From df20a16dbb8a2ac2ae8ae9680e6e7847bff45f5e Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Wed, 22 Feb 2017 17:20:16 +0200
Subject: [PATCH 03/41] net/mlx5e: Fix wrong CQE decompression

[ Upstream commit 36154be40a28e4afaa0416da2681d80b7e2ca319 ]

In cqe compression with striding RQ, the decompression of the CQE field
wqe_counter was done with a wrong wraparound value.
This caused handling cqes with a wrong pointer to wqe (rx descriptor)
and creating SKBs with wrong data, pointing to wrong (and already consumed)
strides/pages.

The meaning of the CQE field wqe_counter in striding RQ holds the
stride index instead of the WQE index. Hence, when decompressing
a CQE, wqe_counter should have wrapped-around the number of strides
in a single multi-packet WQE.

We dropped this wrap-around mask at all in CQE decompression of striding
RQ. It is not needed as in such cases the CQE compression session would
break because of different value of wqe_id field, starting a new
compression session.

Tested:
 ethtool -K ethxx lro off/on
 ethtool --set-priv-flags ethxx rx_cqe_compress on
 super_netperf 16 {ipv4,ipv6} -t TCP_STREAM -m 50 -D
 verified no csum errors and no page refcount issues.

Fixes: 7219ab34f184 ("net/mlx5e: CQE compression")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reported-by: Tom Herbert <tom@herbertland.com>
Cc: kernel-team@fb.com
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index e7b2158..796bdf0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -92,19 +92,18 @@ static inline void mlx5e_cqes_update_owner(struct mlx5e_cq *cq, u32 cqcc, int n)
 static inline void mlx5e_decompress_cqe(struct mlx5e_rq *rq,
 					struct mlx5e_cq *cq, u32 cqcc)
 {
-	u16 wqe_cnt_step;
-
 	cq->title.byte_cnt     = cq->mini_arr[cq->mini_arr_idx].byte_cnt;
 	cq->title.check_sum    = cq->mini_arr[cq->mini_arr_idx].checksum;
 	cq->title.op_own      &= 0xf0;
 	cq->title.op_own      |= 0x01 & (cqcc >> cq->wq.log_sz);
 	cq->title.wqe_counter  = cpu_to_be16(cq->decmprs_wqe_counter);
 
-	wqe_cnt_step =
-		rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ ?
-		mpwrq_get_cqe_consumed_strides(&cq->title) : 1;
-	cq->decmprs_wqe_counter =
-		(cq->decmprs_wqe_counter + wqe_cnt_step) & rq->wq.sz_m1;
+	if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
+		cq->decmprs_wqe_counter +=
+			mpwrq_get_cqe_consumed_strides(&cq->title);
+	else
+		cq->decmprs_wqe_counter =
+			(cq->decmprs_wqe_counter + 1) & rq->wq.sz_m1;
 }
 
 static inline void mlx5e_decompress_cqe_no_hash(struct mlx5e_rq *rq,
-- 
2.1.0


From a96a5676108daeae9f105cc45998e9cd0e1a8b0c Mon Sep 17 00:00:00 2001
From: Matthias Schiffer <mschiffer@universe-factory.net>
Date: Thu, 23 Feb 2017 17:19:41 +0100
Subject: [PATCH 04/41] vxlan: correctly validate VXLAN ID against VXLAN_N_VID

[ Upstream commit 4e37d6911f36545b286d15073f6f2222f840e81c ]

The incorrect check caused an off-by-one error: the maximum VID 0xffffff
was unusable.

Fixes: d342894c5d2f ("vxlan: virtual extensible lan")
Signed-off-by: Matthias Schiffer <mschiffer@universe-factory.net>
Acked-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index d4f495b..7e3b2e2 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2637,7 +2637,7 @@ static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[])
 
 	if (data[IFLA_VXLAN_ID]) {
 		__u32 id = nla_get_u32(data[IFLA_VXLAN_ID]);
-		if (id >= VXLAN_VID_MASK)
+		if (id >= VXLAN_N_VID)
 			return -ERANGE;
 	}
 
-- 
2.1.0


From e4ced4db0033765f80162bbd83c330052dfdad01 Mon Sep 17 00:00:00 2001
From: David Forster <dforster@brocade.com>
Date: Fri, 24 Feb 2017 14:20:32 +0000
Subject: [PATCH 05/41] vti6: return GRE_KEY for vti6

[ Upstream commit 7dcdf941cdc96692ab99fd790c8cc68945514851 ]

Align vti6 with vti by returning GRE_KEY flag. This enables iproute2
to display tunnel keys on "ip -6 tunnel show"

Signed-off-by: David Forster <dforster@brocade.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_vti.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index c299c1e..66c2b4b 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -691,6 +691,10 @@ vti6_parm_to_user(struct ip6_tnl_parm2 *u, const struct __ip6_tnl_parm *p)
 	u->link = p->link;
 	u->i_key = p->i_key;
 	u->o_key = p->o_key;
+	if (u->i_key)
+		u->i_flags |= GRE_KEY;
+	if (u->o_key)
+		u->o_flags |= GRE_KEY;
 	u->proto = p->proto;
 
 	memcpy(u->name, p->name, sizeof(u->name));
-- 
2.1.0


From 65401308b1b3a4af994657fd330d9962d64b84d1 Mon Sep 17 00:00:00 2001
From: Brian Russell <brussell@brocade.com>
Date: Fri, 24 Feb 2017 17:47:11 +0000
Subject: [PATCH 06/41] vxlan: don't allow overwrite of config src addr

[ Upstream commit 1158632b5a2dcce0786c1b1b99654e81cc867981 ]

When using IPv6 transport and a default dst, a pointer to the configured
source address is passed into the route lookup. If no source address is
configured, then the value is overwritten.

IPv6 route lookup ignores egress ifindex match if the source address is set,
so if egress ifindex match is desired, the source address must be passed
as any. The overwrite breaks this for subsequent lookups.

Avoid this by copying the configured address to an existing stack variable
and pass a pointer to that instead.

Fixes: 272d96a5ab10 ("net: vxlan: lwt: Use source ip address during route lookup.")

Signed-off-by: Brian Russell <brussell@brocade.com>
Acked-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 7e3b2e2..ac3f8d5 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1942,7 +1942,6 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 	const struct iphdr *old_iph;
 	union vxlan_addr *dst;
 	union vxlan_addr remote_ip, local_ip;
-	union vxlan_addr *src;
 	struct vxlan_metadata _md;
 	struct vxlan_metadata *md = &_md;
 	__be16 src_port = 0, dst_port;
@@ -1960,7 +1959,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		dst_port = rdst->remote_port ? rdst->remote_port : vxlan->cfg.dst_port;
 		vni = rdst->remote_vni;
 		dst = &rdst->remote_ip;
-		src = &vxlan->cfg.saddr;
+		local_ip = vxlan->cfg.saddr;
 		dst_cache = &rdst->dst_cache;
 	} else {
 		if (!info) {
@@ -1979,7 +1978,6 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 			local_ip.sin6.sin6_addr = info->key.u.ipv6.src;
 		}
 		dst = &remote_ip;
-		src = &local_ip;
 		dst_cache = &info->dst_cache;
 	}
 
@@ -2028,7 +2026,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		rt = vxlan_get_route(vxlan, skb,
 				     rdst ? rdst->remote_ifindex : 0, tos,
 				     dst->sin.sin_addr.s_addr,
-				     &src->sin.sin_addr.s_addr,
+				     &local_ip.sin.sin_addr.s_addr,
 				     dst_cache, info);
 		if (IS_ERR(rt)) {
 			netdev_dbg(dev, "no route to %pI4\n",
@@ -2071,7 +2069,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		if (err < 0)
 			goto xmit_tx_error;
 
-		udp_tunnel_xmit_skb(rt, sk, skb, src->sin.sin_addr.s_addr,
+		udp_tunnel_xmit_skb(rt, sk, skb, local_ip.sin.sin_addr.s_addr,
 				    dst->sin.sin_addr.s_addr, tos, ttl, df,
 				    src_port, dst_port, xnet, !udp_sum);
 #if IS_ENABLED(CONFIG_IPV6)
@@ -2087,7 +2085,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		ndst = vxlan6_get_route(vxlan, skb,
 					rdst ? rdst->remote_ifindex : 0, tos,
 					label, &dst->sin6.sin6_addr,
-					&src->sin6.sin6_addr,
+					&local_ip.sin6.sin6_addr,
 					dst_cache, info);
 		if (IS_ERR(ndst)) {
 			netdev_dbg(dev, "no route to %pI6\n",
@@ -2134,7 +2132,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 			return;
 		}
 		udp_tunnel6_xmit_skb(ndst, sk, skb, dev,
-				     &src->sin6.sin6_addr,
+				     &local_ip.sin6.sin6_addr,
 				     &dst->sin6.sin6_addr, tos, ttl,
 				     label, src_port, dst_port, !udp_sum);
 #endif
-- 
2.1.0


From a1d5aa3f05b4ae3543c335a3d34fe5da075a2035 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Sun, 26 Feb 2017 17:14:35 +0200
Subject: [PATCH 07/41] ipv4: mask tos for input route

[ Upstream commit 6e28099d38c0e50d62c1afc054e37e573adf3d21 ]

Restore the lost masking of TOS in input route code to
allow ip rules to match it properly.

Problem [1] noticed by Shmulik Ladkani <shmulik.ladkani@gmail.com>

[1] http://marc.info/?t=137331755300040&r=1&w=2

Fixes: 89aef8921bfb ("ipv4: Delete routing cache.")
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d851cae..17e6fbf 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1968,6 +1968,7 @@ int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 {
 	int res;
 
+	tos &= IPTOS_RT_MASK;
 	rcu_read_lock();
 
 	/* Multicast recognition logic is moved from route cache to here.
-- 
2.1.0


From 10213ff09a07c5e815421e112cc5848b1a1e0192 Mon Sep 17 00:00:00 2001
From: Roman Mashak <mrv@mojatatu.com>
Date: Fri, 24 Feb 2017 11:00:32 -0500
Subject: [PATCH 08/41] net sched actions: decrement module reference count
 after table flush.

[ Upstream commit edb9d1bff4bbe19b8ae0e71b1f38732591a9eeb2 ]

When tc actions are loaded as a module and no actions have been installed,
flushing them would result in actions removed from the memory, but modules
reference count not being decremented, so that the modules would not be
unloaded.

Following is example with GACT action:

% sudo modprobe act_gact
% lsmod
Module                  Size  Used by
act_gact               16384  0
%
% sudo tc actions ls action gact
%
% sudo tc actions flush action gact
% lsmod
Module                  Size  Used by
act_gact               16384  1
% sudo tc actions flush action gact
% lsmod
Module                  Size  Used by
act_gact               16384  2
% sudo rmmod act_gact
rmmod: ERROR: Module act_gact is in use
....

After the fix:
% lsmod
Module                  Size  Used by
act_gact               16384  0
%
% sudo tc actions add action pass index 1
% sudo tc actions add action pass index 2
% sudo tc actions add action pass index 3
% lsmod
Module                  Size  Used by
act_gact               16384  3
%
% sudo tc actions flush action gact
% lsmod
Module                  Size  Used by
act_gact               16384  0
%
% sudo tc actions flush action gact
% lsmod
Module                  Size  Used by
act_gact               16384  0
% sudo rmmod act_gact
% lsmod
Module                  Size  Used by
%

Fixes: f97017cdefef ("net-sched: Fix actions flushing")
Signed-off-by: Roman Mashak <mrv@mojatatu.com>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_api.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index c6c2a93..c651cfc 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -820,10 +820,8 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
 		goto out_module_put;
 
 	err = ops->walk(net, skb, &dcb, RTM_DELACTION, ops);
-	if (err < 0)
+	if (err <= 0)
 		goto out_module_put;
-	if (err == 0)
-		goto noflush_out;
 
 	nla_nest_end(skb, nest);
 
@@ -840,7 +838,6 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
 out_module_put:
 	module_put(ops->owner);
 err_out:
-noflush_out:
 	kfree_skb(skb);
 	return err;
 }
-- 
2.1.0


From 419202741448a112cabb7678eaf55a080308725f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Paul=20H=C3=BCber?= <phueber@kernsp.in>
Date: Sun, 26 Feb 2017 17:58:19 +0100
Subject: [PATCH 09/41] l2tp: avoid use-after-free caused by
 l2tp_ip_backlog_recv
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 51fb60eb162ab84c5edf2ae9c63cf0b878e5547e ]

l2tp_ip_backlog_recv may not return -1 if the packet gets dropped.
The return value is passed up to ip_local_deliver_finish, which treats
negative values as an IP protocol number for resubmission.

Signed-off-by: Paul Hüber <phueber@kernsp.in>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ip.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index c0f0750..ff750bb 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -388,7 +388,7 @@ static int l2tp_ip_backlog_recv(struct sock *sk, struct sk_buff *skb)
 drop:
 	IP_INC_STATS(sock_net(sk), IPSTATS_MIB_INDISCARDS);
 	kfree_skb(skb);
-	return -1;
+	return 0;
 }
 
 /* Userspace will call sendmsg() on the tunnel socket to send L2TP
-- 
2.1.0


From 5da188b5466a5e76b1d326c8de1624a86c27b627 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 20 Jan 2017 15:31:52 -0800
Subject: [PATCH 10/41] net: phy: Avoid deadlock during phy_error()

[ Upstream commit eab127717a6af54401ba534790c793ec143cd1fc ]

phy_error() is called in the PHY state machine workqueue context, and
calls phy_trigger_machine() which does a cancel_delayed_work_sync() of
the workqueue we execute from, causing a deadlock situation.

Augment phy_trigger_machine() machine with a sync boolean indicating
whether we should use cancel_*_sync() or just cancel_*_work().

Fixes: 3c293f4e08b5 ("net: phy: Trigger state machine on state change and not polling.")
Reported-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index f424b86..201ffa5 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -611,14 +611,18 @@ void phy_start_machine(struct phy_device *phydev)
  * phy_trigger_machine - trigger the state machine to run
  *
  * @phydev: the phy_device struct
+ * @sync: indicate whether we should wait for the workqueue cancelation
  *
  * Description: There has been a change in state which requires that the
  *   state machine runs.
  */
 
-static void phy_trigger_machine(struct phy_device *phydev)
+static void phy_trigger_machine(struct phy_device *phydev, bool sync)
 {
-	cancel_delayed_work_sync(&phydev->state_queue);
+	if (sync)
+		cancel_delayed_work_sync(&phydev->state_queue);
+	else
+		cancel_delayed_work(&phydev->state_queue);
 	queue_delayed_work(system_power_efficient_wq, &phydev->state_queue, 0);
 }
 
@@ -655,7 +659,7 @@ static void phy_error(struct phy_device *phydev)
 	phydev->state = PHY_HALTED;
 	mutex_unlock(&phydev->lock);
 
-	phy_trigger_machine(phydev);
+	phy_trigger_machine(phydev, false);
 }
 
 /**
@@ -817,7 +821,7 @@ void phy_change(struct work_struct *work)
 	}
 
 	/* reschedule state queue work to run as soon as possible */
-	phy_trigger_machine(phydev);
+	phy_trigger_machine(phydev, true);
 	return;
 
 ignore:
@@ -907,7 +911,7 @@ void phy_start(struct phy_device *phydev)
 	if (do_resume)
 		phy_resume(phydev);
 
-	phy_trigger_machine(phydev);
+	phy_trigger_machine(phydev, true);
 }
 EXPORT_SYMBOL(phy_start);
 
-- 
2.1.0


From 0f447d3430ac432dffd6d37c2b68c900648de8c4 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 24 Feb 2017 11:43:36 -0800
Subject: [PATCH 11/41] vxlan: lock RCU on TX path

[ Upstream commit 56de859e9967c070464a9a9f4f18d73f9447298e ]

There is no guarantees that callers of the TX path will hold
the RCU lock.  Grab it explicitly.

Fixes: c6fcc4fc5f8b ("vxlan: avoid using stale vxlan socket.")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index ac3f8d5..3c4c2cf 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1955,6 +1955,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 
 	info = skb_tunnel_info(skb);
 
+	rcu_read_lock();
 	if (rdst) {
 		dst_port = rdst->remote_port ? rdst->remote_port : vxlan->cfg.dst_port;
 		vni = rdst->remote_vni;
@@ -1985,7 +1986,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		if (did_rsc) {
 			/* short-circuited back to local bridge */
 			vxlan_encap_bypass(skb, vxlan, vxlan);
-			return;
+			goto out_unlock;
 		}
 		goto drop;
 	}
@@ -2054,7 +2055,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 			if (!dst_vxlan)
 				goto tx_error;
 			vxlan_encap_bypass(skb, vxlan, dst_vxlan);
-			return;
+			goto out_unlock;
 		}
 
 		if (!info)
@@ -2115,7 +2116,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 			if (!dst_vxlan)
 				goto tx_error;
 			vxlan_encap_bypass(skb, vxlan, dst_vxlan);
-			return;
+			goto out_unlock;
 		}
 
 		if (!info)
@@ -2129,7 +2130,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		if (err < 0) {
 			dst_release(ndst);
 			dev->stats.tx_errors++;
-			return;
+			goto out_unlock;
 		}
 		udp_tunnel6_xmit_skb(ndst, sk, skb, dev,
 				     &local_ip.sin6.sin6_addr,
@@ -2137,7 +2138,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 				     label, src_port, dst_port, !udp_sum);
 #endif
 	}
-
+out_unlock:
+	rcu_read_unlock();
 	return;
 
 drop:
@@ -2153,6 +2155,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 	dev->stats.tx_errors++;
 tx_free:
 	dev_kfree_skb(skb);
+	rcu_read_unlock();
 }
 
 /* Transmit local packets over Vxlan
-- 
2.1.0


From b066312155fb7fa63726624bbb36652ee7958220 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 24 Feb 2017 11:43:37 -0800
Subject: [PATCH 12/41] geneve: lock RCU on TX path

[ Upstream commit a717e3f740803cc88bd5c9a70c93504f6a368663 ]

There is no guarantees that callers of the TX path will hold
the RCU lock.  Grab it explicitly.

Fixes: fceb9c3e3825 ("geneve: avoid using stale geneve socket.")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 8b4822a..3c1f89a 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1039,16 +1039,22 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct geneve_dev *geneve = netdev_priv(dev);
 	struct ip_tunnel_info *info = NULL;
+	int err;
 
 	if (geneve->collect_md)
 		info = skb_tunnel_info(skb);
 
+	rcu_read_lock();
 #if IS_ENABLED(CONFIG_IPV6)
 	if ((info && ip_tunnel_info_af(info) == AF_INET6) ||
 	    (!info && geneve->remote.sa.sa_family == AF_INET6))
-		return geneve6_xmit_skb(skb, dev, info);
+		err = geneve6_xmit_skb(skb, dev, info);
+	else
 #endif
-	return geneve_xmit_skb(skb, dev, info);
+		err = geneve_xmit_skb(skb, dev, info);
+	rcu_read_unlock();
+
+	return err;
 }
 
 static int __geneve_change_mtu(struct net_device *dev, int new_mtu, bool strict)
-- 
2.1.0


From a32ebeaacac792bff7c7f2604e30fd107c36aa50 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Tue, 28 Feb 2017 08:55:40 +0100
Subject: [PATCH 13/41] mlxsw: spectrum_router: Avoid potential packets loss

[ Upstream commit f7df4923fa986247e93ec2cdff5ca168fff14dcf ]

When the structure of the LPM tree changes (f.e., due to the addition of
a new prefix), we unbind the old tree and then bind the new one. This
may result in temporary packet loss.

Instead, overwrite the old binding with the new one.

Fixes: 6b75c4807db3 ("mlxsw: spectrum_router: Add virtual router management")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_router.c  | 30 ++++++++++++++--------
 1 file changed, 20 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index e83072d..6905630 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -500,30 +500,40 @@ static int
 mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr,
 			   struct mlxsw_sp_prefix_usage *req_prefix_usage)
 {
-	struct mlxsw_sp_lpm_tree *lpm_tree;
+	struct mlxsw_sp_lpm_tree *lpm_tree = vr->lpm_tree;
+	struct mlxsw_sp_lpm_tree *new_tree;
+	int err;
 
-	if (mlxsw_sp_prefix_usage_eq(req_prefix_usage,
-				     &vr->lpm_tree->prefix_usage))
+	if (mlxsw_sp_prefix_usage_eq(req_prefix_usage, &lpm_tree->prefix_usage))
 		return 0;
 
-	lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, req_prefix_usage,
+	new_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, req_prefix_usage,
 					 vr->proto, false);
-	if (IS_ERR(lpm_tree)) {
+	if (IS_ERR(new_tree)) {
 		/* We failed to get a tree according to the required
 		 * prefix usage. However, the current tree might be still good
 		 * for us if our requirement is subset of the prefixes used
 		 * in the tree.
 		 */
 		if (mlxsw_sp_prefix_usage_subset(req_prefix_usage,
-						 &vr->lpm_tree->prefix_usage))
+						 &lpm_tree->prefix_usage))
 			return 0;
-		return PTR_ERR(lpm_tree);
+		return PTR_ERR(new_tree);
 	}
 
-	mlxsw_sp_vr_lpm_tree_unbind(mlxsw_sp, vr);
-	mlxsw_sp_lpm_tree_put(mlxsw_sp, vr->lpm_tree);
+	/* Prevent packet loss by overwriting existing binding */
+	vr->lpm_tree = new_tree;
+	err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, vr);
+	if (err)
+		goto err_tree_bind;
+	mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree);
+
+	return 0;
+
+err_tree_bind:
 	vr->lpm_tree = lpm_tree;
-	return mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, vr);
+	mlxsw_sp_lpm_tree_put(mlxsw_sp, new_tree);
+	return err;
 }
 
 static struct mlxsw_sp_vr *mlxsw_sp_vr_get(struct mlxsw_sp *mlxsw_sp,
-- 
2.1.0


From ae5a873defeeae44760268074372295926021b37 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 1 Mar 2017 08:39:49 -0800
Subject: [PATCH 14/41] tcp/dccp: block BH for SYN processing

[ Upstream commit 449809a66c1d0b1563dee84493e14bf3104d2d7e ]

SYN processing really was meant to be handled from BH.

When I got rid of BH blocking while processing socket backlog
in commit 5413d1babe8f ("net: do not block BH while processing socket
backlog"), I forgot that a malicious user could transition to TCP_LISTEN
from a state that allowed (SYN) packets to be parked in the socket
backlog while socket is owned by the thread doing the listen() call.

Sure enough syzkaller found this and reported the bug ;)

=================================
[ INFO: inconsistent lock state ]
4.10.0+ #60 Not tainted
---------------------------------
inconsistent {IN-SOFTIRQ-W} -> {SOFTIRQ-ON-W} usage.
syz-executor0/5090 [HC0[0]:SC0[0]:HE1:SE1] takes:
 (&(&hashinfo->ehash_locks[i])->rlock){+.?...}, at:
[<ffffffff83a6a370>] spin_lock include/linux/spinlock.h:299 [inline]
 (&(&hashinfo->ehash_locks[i])->rlock){+.?...}, at:
[<ffffffff83a6a370>] inet_ehash_insert+0x240/0xad0
net/ipv4/inet_hashtables.c:407
{IN-SOFTIRQ-W} state was registered at:
  mark_irqflags kernel/locking/lockdep.c:2923 [inline]
  __lock_acquire+0xbcf/0x3270 kernel/locking/lockdep.c:3295
  lock_acquire+0x241/0x580 kernel/locking/lockdep.c:3753
  __raw_spin_lock include/linux/spinlock_api_smp.h:142 [inline]
  _raw_spin_lock+0x33/0x50 kernel/locking/spinlock.c:151
  spin_lock include/linux/spinlock.h:299 [inline]
  inet_ehash_insert+0x240/0xad0 net/ipv4/inet_hashtables.c:407
  reqsk_queue_hash_req net/ipv4/inet_connection_sock.c:753 [inline]
  inet_csk_reqsk_queue_hash_add+0x1b7/0x2a0 net/ipv4/inet_connection_sock.c:764
  tcp_conn_request+0x25cc/0x3310 net/ipv4/tcp_input.c:6399
  tcp_v4_conn_request+0x157/0x220 net/ipv4/tcp_ipv4.c:1262
  tcp_rcv_state_process+0x802/0x4130 net/ipv4/tcp_input.c:5889
  tcp_v4_do_rcv+0x56b/0x940 net/ipv4/tcp_ipv4.c:1433
  tcp_v4_rcv+0x2e12/0x3210 net/ipv4/tcp_ipv4.c:1711
  ip_local_deliver_finish+0x4ce/0xc40 net/ipv4/ip_input.c:216
  NF_HOOK include/linux/netfilter.h:257 [inline]
  ip_local_deliver+0x1ce/0x710 net/ipv4/ip_input.c:257
  dst_input include/net/dst.h:492 [inline]
  ip_rcv_finish+0xb1d/0x2110 net/ipv4/ip_input.c:396
  NF_HOOK include/linux/netfilter.h:257 [inline]
  ip_rcv+0xd90/0x19c0 net/ipv4/ip_input.c:487
  __netif_receive_skb_core+0x1ad1/0x3400 net/core/dev.c:4179
  __netif_receive_skb+0x2a/0x170 net/core/dev.c:4217
  netif_receive_skb_internal+0x1d6/0x430 net/core/dev.c:4245
  napi_skb_finish net/core/dev.c:4602 [inline]
  napi_gro_receive+0x4e6/0x680 net/core/dev.c:4636
  e1000_receive_skb drivers/net/ethernet/intel/e1000/e1000_main.c:4033 [inline]
  e1000_clean_rx_irq+0x5e0/0x1490
drivers/net/ethernet/intel/e1000/e1000_main.c:4489
  e1000_clean+0xb9a/0x2910 drivers/net/ethernet/intel/e1000/e1000_main.c:3834
  napi_poll net/core/dev.c:5171 [inline]
  net_rx_action+0xe70/0x1900 net/core/dev.c:5236
  __do_softirq+0x2fb/0xb7d kernel/softirq.c:284
  invoke_softirq kernel/softirq.c:364 [inline]
  irq_exit+0x19e/0x1d0 kernel/softirq.c:405
  exiting_irq arch/x86/include/asm/apic.h:658 [inline]
  do_IRQ+0x81/0x1a0 arch/x86/kernel/irq.c:250
  ret_from_intr+0x0/0x20
  native_safe_halt+0x6/0x10 arch/x86/include/asm/irqflags.h:53
  arch_safe_halt arch/x86/include/asm/paravirt.h:98 [inline]
  default_idle+0x8f/0x410 arch/x86/kernel/process.c:271
  arch_cpu_idle+0xa/0x10 arch/x86/kernel/process.c:262
  default_idle_call+0x36/0x60 kernel/sched/idle.c:96
  cpuidle_idle_call kernel/sched/idle.c:154 [inline]
  do_idle+0x348/0x440 kernel/sched/idle.c:243
  cpu_startup_entry+0x18/0x20 kernel/sched/idle.c:345
  start_secondary+0x344/0x440 arch/x86/kernel/smpboot.c:272
  verify_cpu+0x0/0xfc
irq event stamp: 1741
hardirqs last  enabled at (1741): [<ffffffff84d49d77>]
__raw_spin_unlock_irqrestore include/linux/spinlock_api_smp.h:160
[inline]
hardirqs last  enabled at (1741): [<ffffffff84d49d77>]
_raw_spin_unlock_irqrestore+0xf7/0x1a0 kernel/locking/spinlock.c:191
hardirqs last disabled at (1740): [<ffffffff84d4a732>]
__raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:108 [inline]
hardirqs last disabled at (1740): [<ffffffff84d4a732>]
_raw_spin_lock_irqsave+0xa2/0x110 kernel/locking/spinlock.c:159
softirqs last  enabled at (1738): [<ffffffff84d4deff>]
__do_softirq+0x7cf/0xb7d kernel/softirq.c:310
softirqs last disabled at (1571): [<ffffffff84d4b92c>]
do_softirq_own_stack+0x1c/0x30 arch/x86/entry/entry_64.S:902

other info that might help us debug this:
 Possible unsafe locking scenario:

       CPU0
       ----
  lock(&(&hashinfo->ehash_locks[i])->rlock);
  <Interrupt>
    lock(&(&hashinfo->ehash_locks[i])->rlock);

 *** DEADLOCK ***

1 lock held by syz-executor0/5090:
 #0:  (sk_lock-AF_INET6){+.+.+.}, at: [<ffffffff83406b43>] lock_sock
include/net/sock.h:1460 [inline]
 #0:  (sk_lock-AF_INET6){+.+.+.}, at: [<ffffffff83406b43>]
sock_setsockopt+0x233/0x1e40 net/core/sock.c:683

stack backtrace:
CPU: 1 PID: 5090 Comm: syz-executor0 Not tainted 4.10.0+ #60
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:15 [inline]
 dump_stack+0x292/0x398 lib/dump_stack.c:51
 print_usage_bug+0x3ef/0x450 kernel/locking/lockdep.c:2387
 valid_state kernel/locking/lockdep.c:2400 [inline]
 mark_lock_irq kernel/locking/lockdep.c:2602 [inline]
 mark_lock+0xf30/0x1410 kernel/locking/lockdep.c:3065
 mark_irqflags kernel/locking/lockdep.c:2941 [inline]
 __lock_acquire+0x6dc/0x3270 kernel/locking/lockdep.c:3295
 lock_acquire+0x241/0x580 kernel/locking/lockdep.c:3753
 __raw_spin_lock include/linux/spinlock_api_smp.h:142 [inline]
 _raw_spin_lock+0x33/0x50 kernel/locking/spinlock.c:151
 spin_lock include/linux/spinlock.h:299 [inline]
 inet_ehash_insert+0x240/0xad0 net/ipv4/inet_hashtables.c:407
 reqsk_queue_hash_req net/ipv4/inet_connection_sock.c:753 [inline]
 inet_csk_reqsk_queue_hash_add+0x1b7/0x2a0 net/ipv4/inet_connection_sock.c:764
 dccp_v6_conn_request+0xada/0x11b0 net/dccp/ipv6.c:380
 dccp_rcv_state_process+0x51e/0x1660 net/dccp/input.c:606
 dccp_v6_do_rcv+0x213/0x350 net/dccp/ipv6.c:632
 sk_backlog_rcv include/net/sock.h:896 [inline]
 __release_sock+0x127/0x3a0 net/core/sock.c:2052
 release_sock+0xa5/0x2b0 net/core/sock.c:2539
 sock_setsockopt+0x60f/0x1e40 net/core/sock.c:1016
 SYSC_setsockopt net/socket.c:1782 [inline]
 SyS_setsockopt+0x2fb/0x3a0 net/socket.c:1765
 entry_SYSCALL_64_fastpath+0x1f/0xc2
RIP: 0033:0x4458b9
RSP: 002b:00007fe8b26c2b58 EFLAGS: 00000292 ORIG_RAX: 0000000000000036
RAX: ffffffffffffffda RBX: 0000000000000006 RCX: 00000000004458b9
RDX: 000000000000001a RSI: 0000000000000001 RDI: 0000000000000006
RBP: 00000000006e2110 R08: 0000000000000010 R09: 0000000000000000
R10: 00000000208c3000 R11: 0000000000000292 R12: 0000000000708000
R13: 0000000020000000 R14: 0000000000001000 R15: 0000000000000000

Fixes: 5413d1babe8f ("net: do not block BH while processing socket backlog")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/input.c     | 10 ++++++++--
 net/ipv4/tcp_input.c | 10 ++++++++--
 2 files changed, 16 insertions(+), 4 deletions(-)

diff --git a/net/dccp/input.c b/net/dccp/input.c
index 8fedc2d..4a05d78 100644
--- a/net/dccp/input.c
+++ b/net/dccp/input.c
@@ -577,6 +577,7 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 	struct dccp_sock *dp = dccp_sk(sk);
 	struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
 	const int old_state = sk->sk_state;
+	bool acceptable;
 	int queued = 0;
 
 	/*
@@ -603,8 +604,13 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 	 */
 	if (sk->sk_state == DCCP_LISTEN) {
 		if (dh->dccph_type == DCCP_PKT_REQUEST) {
-			if (inet_csk(sk)->icsk_af_ops->conn_request(sk,
-								    skb) < 0)
+			/* It is possible that we process SYN packets from backlog,
+			 * so we need to make sure to disable BH right there.
+			 */
+			local_bh_disable();
+			acceptable = inet_csk(sk)->icsk_af_ops->conn_request(sk, skb) >= 0;
+			local_bh_enable();
+			if (!acceptable)
 				return 1;
 			consume_skb(skb);
 			return 0;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index c71d49c..ce42ded 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5916,9 +5916,15 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 		if (th->syn) {
 			if (th->fin)
 				goto discard;
-			if (icsk->icsk_af_ops->conn_request(sk, skb) < 0)
-				return 1;
+			/* It is possible that we process SYN packets from backlog,
+			 * so we need to make sure to disable BH right there.
+			 */
+			local_bh_disable();
+			acceptable = icsk->icsk_af_ops->conn_request(sk, skb) >= 0;
+			local_bh_enable();
 
+			if (!acceptable)
+				return 1;
 			consume_skb(skb);
 			return 0;
 		}
-- 
2.1.0


From ceb1273fd1ec2e0dceccd435629c1addad148b65 Mon Sep 17 00:00:00 2001
From: Mike Manning <mmanning@brocade.com>
Date: Wed, 1 Mar 2017 09:55:28 +0000
Subject: [PATCH 15/41] net: bridge: allow IPv6 when multicast flood is
 disabled

[ Upstream commit 8953de2f02ad7b15e4964c82f9afd60f128e4e98 ]

Even with multicast flooding turned off, IPv6 ND should still work so
that IPv6 connectivity is provided. Allow this by continuing to flood
multicast traffic originated by us.

Fixes: b6cb5ac8331b ("net: bridge: add per-port multicast flood flag")
Cc: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: Mike Manning <mmanning@brocade.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_forward.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 7cb41ae..8498e35 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -186,8 +186,9 @@ void br_flood(struct net_bridge *br, struct sk_buff *skb,
 		/* Do not flood unicast traffic to ports that turn it off */
 		if (pkt_type == BR_PKT_UNICAST && !(p->flags & BR_FLOOD))
 			continue;
+		/* Do not flood if mc off, except for traffic we originate */
 		if (pkt_type == BR_PKT_MULTICAST &&
-		    !(p->flags & BR_MCAST_FLOOD))
+		    !(p->flags & BR_MCAST_FLOOD) && skb->dev != br->dev)
 			continue;
 
 		/* Do not flood to ports that enable proxy ARP */
-- 
2.1.0


From e22db34379412faf71424a8481af2a87ab859be5 Mon Sep 17 00:00:00 2001
From: Alexander Potapenko <glider@google.com>
Date: Wed, 1 Mar 2017 12:57:20 +0100
Subject: [PATCH 16/41] net: don't call strlen() on the user buffer in
 packet_bind_spkt()

[ Upstream commit 540e2894f7905538740aaf122bd8e0548e1c34a4 ]

KMSAN (KernelMemorySanitizer, a new error detection tool) reports use of
uninitialized memory in packet_bind_spkt():
Acked-by: Eric Dumazet <edumazet@google.com>

==================================================================
BUG: KMSAN: use of unitialized memory
CPU: 0 PID: 1074 Comm: packet Not tainted 4.8.0-rc6+ #1891
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs
01/01/2011
 0000000000000000 ffff88006b6dfc08 ffffffff82559ae8 ffff88006b6dfb48
 ffffffff818a7c91 ffffffff85b9c870 0000000000000092 ffffffff85b9c550
 0000000000000000 0000000000000092 00000000ec400911 0000000000000002
Call Trace:
 [<     inline     >] __dump_stack lib/dump_stack.c:15
 [<ffffffff82559ae8>] dump_stack+0x238/0x290 lib/dump_stack.c:51
 [<ffffffff818a6626>] kmsan_report+0x276/0x2e0 mm/kmsan/kmsan.c:1003
 [<ffffffff818a783b>] __msan_warning+0x5b/0xb0
mm/kmsan/kmsan_instr.c:424
 [<     inline     >] strlen lib/string.c:484
 [<ffffffff8259b58d>] strlcpy+0x9d/0x200 lib/string.c:144
 [<ffffffff84b2eca4>] packet_bind_spkt+0x144/0x230
net/packet/af_packet.c:3132
 [<ffffffff84242e4d>] SYSC_bind+0x40d/0x5f0 net/socket.c:1370
 [<ffffffff84242a22>] SyS_bind+0x82/0xa0 net/socket.c:1356
 [<ffffffff8515991b>] entry_SYSCALL_64_fastpath+0x13/0x8f
arch/x86/entry/entry_64.o:?
chained origin: 00000000eba00911
 [<ffffffff810bb787>] save_stack_trace+0x27/0x50
arch/x86/kernel/stacktrace.c:67
 [<     inline     >] kmsan_save_stack_with_flags mm/kmsan/kmsan.c:322
 [<     inline     >] kmsan_save_stack mm/kmsan/kmsan.c:334
 [<ffffffff818a59f8>] kmsan_internal_chain_origin+0x118/0x1e0
mm/kmsan/kmsan.c:527
 [<ffffffff818a7773>] __msan_set_alloca_origin4+0xc3/0x130
mm/kmsan/kmsan_instr.c:380
 [<ffffffff84242b69>] SYSC_bind+0x129/0x5f0 net/socket.c:1356
 [<ffffffff84242a22>] SyS_bind+0x82/0xa0 net/socket.c:1356
 [<ffffffff8515991b>] entry_SYSCALL_64_fastpath+0x13/0x8f
arch/x86/entry/entry_64.o:?
origin description: ----address@SYSC_bind (origin=00000000eb400911)
==================================================================
(the line numbers are relative to 4.8-rc6, but the bug persists
upstream)

, when I run the following program as root:

=====================================
 #include <string.h>
 #include <sys/socket.h>
 #include <netpacket/packet.h>
 #include <net/ethernet.h>

 int main() {
   struct sockaddr addr;
   memset(&addr, 0xff, sizeof(addr));
   addr.sa_family = AF_PACKET;
   int fd = socket(PF_PACKET, SOCK_PACKET, htons(ETH_P_ALL));
   bind(fd, &addr, sizeof(addr));
   return 0;
 }
=====================================

This happens because addr.sa_data copied from the userspace is not
zero-terminated, and copying it with strlcpy() in packet_bind_spkt()
results in calling strlen() on the kernel copy of that non-terminated
buffer.

Signed-off-by: Alexander Potapenko <glider@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 34de326..f2b04a7 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3140,7 +3140,7 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr,
 			    int addr_len)
 {
 	struct sock *sk = sock->sk;
-	char name[15];
+	char name[sizeof(uaddr->sa_data) + 1];
 
 	/*
 	 *	Check legality
@@ -3148,7 +3148,11 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr,
 
 	if (addr_len != sizeof(struct sockaddr))
 		return -EINVAL;
-	strlcpy(name, uaddr->sa_data, sizeof(name));
+	/* uaddr->sa_data comes from the userspace, it's not guaranteed to be
+	 * zero-terminated.
+	 */
+	memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data));
+	name[sizeof(uaddr->sa_data)] = 0;
 
 	return packet_do_bind(sk, name, 0, pkt_sk(sk)->num);
 }
-- 
2.1.0


From 42f924bd4b640dbd3b1e03e812626a41f7645af2 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 1 Mar 2017 14:28:39 -0800
Subject: [PATCH 17/41] net: net_enable_timestamp() can be called from irq
 contexts

[ Upstream commit 13baa00ad01bb3a9f893e3a08cbc2d072fc0c15d ]

It is now very clear that silly TCP listeners might play with
enabling/disabling timestamping while new children are added
to their accept queue.

Meaning net_enable_timestamp() can be called from BH context
while current state of the static key is not enabled.

Lets play safe and allow all contexts.

The work queue is scheduled only under the problematic cases,
which are the static key enable/disable transition, to not slow down
critical paths.

This extends and improves what we did in commit 5fa8bbda38c6 ("net: use
a work queue to defer net_disable_timestamp() work")

Fixes: b90e5794c5bd ("net: dont call jump_label_dec from irq context")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 35 +++++++++++++++++++++++++++++++----
 1 file changed, 31 insertions(+), 4 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 60b0a604..2e04fd1 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1697,27 +1697,54 @@ EXPORT_SYMBOL_GPL(net_dec_egress_queue);
 static struct static_key netstamp_needed __read_mostly;
 #ifdef HAVE_JUMP_LABEL
 static atomic_t netstamp_needed_deferred;
+static atomic_t netstamp_wanted;
 static void netstamp_clear(struct work_struct *work)
 {
 	int deferred = atomic_xchg(&netstamp_needed_deferred, 0);
+	int wanted;
 
-	while (deferred--)
-		static_key_slow_dec(&netstamp_needed);
+	wanted = atomic_add_return(deferred, &netstamp_wanted);
+	if (wanted > 0)
+		static_key_enable(&netstamp_needed);
+	else
+		static_key_disable(&netstamp_needed);
 }
 static DECLARE_WORK(netstamp_work, netstamp_clear);
 #endif
 
 void net_enable_timestamp(void)
 {
+#ifdef HAVE_JUMP_LABEL
+	int wanted;
+
+	while (1) {
+		wanted = atomic_read(&netstamp_wanted);
+		if (wanted <= 0)
+			break;
+		if (atomic_cmpxchg(&netstamp_wanted, wanted, wanted + 1) == wanted)
+			return;
+	}
+	atomic_inc(&netstamp_needed_deferred);
+	schedule_work(&netstamp_work);
+#else
 	static_key_slow_inc(&netstamp_needed);
+#endif
 }
 EXPORT_SYMBOL(net_enable_timestamp);
 
 void net_disable_timestamp(void)
 {
 #ifdef HAVE_JUMP_LABEL
-	/* net_disable_timestamp() can be called from non process context */
-	atomic_inc(&netstamp_needed_deferred);
+	int wanted;
+
+	while (1) {
+		wanted = atomic_read(&netstamp_wanted);
+		if (wanted <= 1)
+			break;
+		if (atomic_cmpxchg(&netstamp_wanted, wanted, wanted - 1) == wanted)
+			return;
+	}
+	atomic_dec(&netstamp_needed_deferred);
 	schedule_work(&netstamp_work);
 #else
 	static_key_slow_dec(&netstamp_needed);
-- 
2.1.0


From 4a9dec660fbd0400698a56952168ec8cce245c41 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 1 Mar 2017 14:45:06 -0800
Subject: [PATCH 18/41] ipv6: orphan skbs in reassembly unit

[ Upstream commit 48cac18ecf1de82f76259a54402c3adb7839ad01 ]

Andrey reported a use-after-free in IPv6 stack.

Issue here is that we free the socket while it still has skb
in TX path and in some queues.

It happens here because IPv6 reassembly unit messes skb->truesize,
breaking skb_set_owner_w() badly.

We fixed a similar issue for IPV4 in commit 8282f27449bf ("inet: frag:
Always orphan skbs inside ip_defrag()")
Acked-by: Joe Stringer <joe@ovn.org>

==================================================================
BUG: KASAN: use-after-free in sock_wfree+0x118/0x120
Read of size 8 at addr ffff880062da0060 by task a.out/4140

page:ffffea00018b6800 count:1 mapcount:0 mapping:          (null)
index:0x0 compound_mapcount: 0
flags: 0x100000000008100(slab|head)
raw: 0100000000008100 0000000000000000 0000000000000000 0000000180130013
raw: dead000000000100 dead000000000200 ffff88006741f140 0000000000000000
page dumped because: kasan: bad access detected

CPU: 0 PID: 4140 Comm: a.out Not tainted 4.10.0-rc3+ #59
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:15
 dump_stack+0x292/0x398 lib/dump_stack.c:51
 describe_address mm/kasan/report.c:262
 kasan_report_error+0x121/0x560 mm/kasan/report.c:370
 kasan_report mm/kasan/report.c:392
 __asan_report_load8_noabort+0x3e/0x40 mm/kasan/report.c:413
 sock_flag ./arch/x86/include/asm/bitops.h:324
 sock_wfree+0x118/0x120 net/core/sock.c:1631
 skb_release_head_state+0xfc/0x250 net/core/skbuff.c:655
 skb_release_all+0x15/0x60 net/core/skbuff.c:668
 __kfree_skb+0x15/0x20 net/core/skbuff.c:684
 kfree_skb+0x16e/0x4e0 net/core/skbuff.c:705
 inet_frag_destroy+0x121/0x290 net/ipv4/inet_fragment.c:304
 inet_frag_put ./include/net/inet_frag.h:133
 nf_ct_frag6_gather+0x1125/0x38b0 net/ipv6/netfilter/nf_conntrack_reasm.c:617
 ipv6_defrag+0x21b/0x350 net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:68
 nf_hook_entry_hookfn ./include/linux/netfilter.h:102
 nf_hook_slow+0xc3/0x290 net/netfilter/core.c:310
 nf_hook ./include/linux/netfilter.h:212
 __ip6_local_out+0x52c/0xaf0 net/ipv6/output_core.c:160
 ip6_local_out+0x2d/0x170 net/ipv6/output_core.c:170
 ip6_send_skb+0xa1/0x340 net/ipv6/ip6_output.c:1722
 ip6_push_pending_frames+0xb3/0xe0 net/ipv6/ip6_output.c:1742
 rawv6_push_pending_frames net/ipv6/raw.c:613
 rawv6_sendmsg+0x2cff/0x4130 net/ipv6/raw.c:927
 inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:744
 sock_sendmsg_nosec net/socket.c:635
 sock_sendmsg+0xca/0x110 net/socket.c:645
 sock_write_iter+0x326/0x620 net/socket.c:848
 new_sync_write fs/read_write.c:499
 __vfs_write+0x483/0x760 fs/read_write.c:512
 vfs_write+0x187/0x530 fs/read_write.c:560
 SYSC_write fs/read_write.c:607
 SyS_write+0xfb/0x230 fs/read_write.c:599
 entry_SYSCALL_64_fastpath+0x1f/0xc2 arch/x86/entry/entry_64.S:203
RIP: 0033:0x7ff26e6f5b79
RSP: 002b:00007ff268e0ed98 EFLAGS: 00000206 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 00007ff268e0f9c0 RCX: 00007ff26e6f5b79
RDX: 0000000000000010 RSI: 0000000020f50fe1 RDI: 0000000000000003
RBP: 00007ff26ebc1220 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000206 R12: 0000000000000000
R13: 00007ff268e0f9c0 R14: 00007ff26efec040 R15: 0000000000000003

The buggy address belongs to the object at ffff880062da0000
 which belongs to the cache RAWv6 of size 1504
The buggy address ffff880062da0060 is located 96 bytes inside
 of 1504-byte region [ffff880062da0000, ffff880062da05e0)

Freed by task 4113:
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57
 save_stack+0x43/0xd0 mm/kasan/kasan.c:502
 set_track mm/kasan/kasan.c:514
 kasan_slab_free+0x73/0xc0 mm/kasan/kasan.c:578
 slab_free_hook mm/slub.c:1352
 slab_free_freelist_hook mm/slub.c:1374
 slab_free mm/slub.c:2951
 kmem_cache_free+0xb2/0x2c0 mm/slub.c:2973
 sk_prot_free net/core/sock.c:1377
 __sk_destruct+0x49c/0x6e0 net/core/sock.c:1452
 sk_destruct+0x47/0x80 net/core/sock.c:1460
 __sk_free+0x57/0x230 net/core/sock.c:1468
 sk_free+0x23/0x30 net/core/sock.c:1479
 sock_put ./include/net/sock.h:1638
 sk_common_release+0x31e/0x4e0 net/core/sock.c:2782
 rawv6_close+0x54/0x80 net/ipv6/raw.c:1214
 inet_release+0xed/0x1c0 net/ipv4/af_inet.c:425
 inet6_release+0x50/0x70 net/ipv6/af_inet6.c:431
 sock_release+0x8d/0x1e0 net/socket.c:599
 sock_close+0x16/0x20 net/socket.c:1063
 __fput+0x332/0x7f0 fs/file_table.c:208
 ____fput+0x15/0x20 fs/file_table.c:244
 task_work_run+0x19b/0x270 kernel/task_work.c:116
 exit_task_work ./include/linux/task_work.h:21
 do_exit+0x186b/0x2800 kernel/exit.c:839
 do_group_exit+0x149/0x420 kernel/exit.c:943
 SYSC_exit_group kernel/exit.c:954
 SyS_exit_group+0x1d/0x20 kernel/exit.c:952
 entry_SYSCALL_64_fastpath+0x1f/0xc2 arch/x86/entry/entry_64.S:203

Allocated by task 4115:
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57
 save_stack+0x43/0xd0 mm/kasan/kasan.c:502
 set_track mm/kasan/kasan.c:514
 kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:605
 kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:544
 slab_post_alloc_hook mm/slab.h:432
 slab_alloc_node mm/slub.c:2708
 slab_alloc mm/slub.c:2716
 kmem_cache_alloc+0x1af/0x250 mm/slub.c:2721
 sk_prot_alloc+0x65/0x2a0 net/core/sock.c:1334
 sk_alloc+0x105/0x1010 net/core/sock.c:1396
 inet6_create+0x44d/0x1150 net/ipv6/af_inet6.c:183
 __sock_create+0x4f6/0x880 net/socket.c:1199
 sock_create net/socket.c:1239
 SYSC_socket net/socket.c:1269
 SyS_socket+0xf9/0x230 net/socket.c:1249
 entry_SYSCALL_64_fastpath+0x1f/0xc2 arch/x86/entry/entry_64.S:203

Memory state around the buggy address:
 ffff880062d9ff00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 ffff880062d9ff80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
>ffff880062da0000: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                                                       ^
 ffff880062da0080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff880062da0100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
==================================================================

Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/netfilter/nf_conntrack_reasm.c | 1 +
 net/openvswitch/conntrack.c             | 1 -
 2 files changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 9948b5c..986d4ca 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -589,6 +589,7 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
 	hdr = ipv6_hdr(skb);
 	fhdr = (struct frag_hdr *)skb_transport_header(skb);
 
+	skb_orphan(skb);
 	fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr,
 		     skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
 	if (fq == NULL) {
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index eab210b..48386bf 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -367,7 +367,6 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key,
 	} else if (key->eth.type == htons(ETH_P_IPV6)) {
 		enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone;
 
-		skb_orphan(skb);
 		memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));
 		err = nf_ct_frag6_gather(net, skb, user);
 		if (err) {
-- 
2.1.0


From 5105f57101764c77ceedee8ad47567e7423ac168 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 1 Mar 2017 16:35:07 -0300
Subject: [PATCH 19/41] dccp: Unlock sock before calling sk_free()

[ Upstream commit d5afb6f9b6bb2c57bd0c05e76e12489dc0d037d9 ]

The code where sk_clone() came from created a new socket and locked it,
but then, on the error path didn't unlock it.

This problem stayed there for a long while, till b0691c8ee7c2 ("net:
Unlock sock before calling sk_free()") fixed it, but unfortunately the
callers of sk_clone() (now sk_clone_locked()) were not audited and the
one in dccp_create_openreq_child() remained.

Now in the age of the syskaller fuzzer, this was finally uncovered, as
reported by Dmitry:

 ---- 8< ----

I've got the following report while running syzkaller fuzzer on
86292b33d4b7 ("Merge branch 'akpm' (patches from Andrew)")

  [ BUG: held lock freed! ]
  4.10.0+ #234 Not tainted
  -------------------------
  syz-executor6/6898 is freeing memory
  ffff88006286cac0-ffff88006286d3b7, with a lock still held there!
   (slock-AF_INET6){+.-...}, at: [<ffffffff8362c2c9>] spin_lock
  include/linux/spinlock.h:299 [inline]
   (slock-AF_INET6){+.-...}, at: [<ffffffff8362c2c9>]
  sk_clone_lock+0x3d9/0x12c0 net/core/sock.c:1504
  5 locks held by syz-executor6/6898:
   #0:  (sk_lock-AF_INET6){+.+.+.}, at: [<ffffffff839a34b4>] lock_sock
  include/net/sock.h:1460 [inline]
   #0:  (sk_lock-AF_INET6){+.+.+.}, at: [<ffffffff839a34b4>]
  inet_stream_connect+0x44/0xa0 net/ipv4/af_inet.c:681
   #1:  (rcu_read_lock){......}, at: [<ffffffff83bc1c2a>]
  inet6_csk_xmit+0x12a/0x5d0 net/ipv6/inet6_connection_sock.c:126
   #2:  (rcu_read_lock){......}, at: [<ffffffff8369b424>] __skb_unlink
  include/linux/skbuff.h:1767 [inline]
   #2:  (rcu_read_lock){......}, at: [<ffffffff8369b424>] __skb_dequeue
  include/linux/skbuff.h:1783 [inline]
   #2:  (rcu_read_lock){......}, at: [<ffffffff8369b424>]
  process_backlog+0x264/0x730 net/core/dev.c:4835
   #3:  (rcu_read_lock){......}, at: [<ffffffff83aeb5c0>]
  ip6_input_finish+0x0/0x1700 net/ipv6/ip6_input.c:59
   #4:  (slock-AF_INET6){+.-...}, at: [<ffffffff8362c2c9>] spin_lock
  include/linux/spinlock.h:299 [inline]
   #4:  (slock-AF_INET6){+.-...}, at: [<ffffffff8362c2c9>]
  sk_clone_lock+0x3d9/0x12c0 net/core/sock.c:1504

Fix it just like was done by b0691c8ee7c2 ("net: Unlock sock before calling
sk_free()").

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20170301153510.GE15145@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/minisocks.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index 53eddf9..d20d948 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -122,6 +122,7 @@ struct sock *dccp_create_openreq_child(const struct sock *sk,
 			/* It is still raw copy of parent, so invalidate
 			 * destructor and make plain sk_free() */
 			newsk->sk_destruct = NULL;
+			bh_unlock_sock(newsk);
 			sk_free(newsk);
 			return NULL;
 		}
-- 
2.1.0


From e75e0c43f17a8e522cc6a47730faad5a54017e94 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Fri, 3 Mar 2017 12:21:14 -0800
Subject: [PATCH 20/41] strparser: destroy workqueue on module exit

[ Upstream commit f78ef7cd9a0686b979679d0de061c6dbfd8d649e ]

Fixes: 43a0c6751a32 ("strparser: Stream parser for messages")
Cc: Tom Herbert <tom@herbertland.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/strparser/strparser.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index 41adf36..b5c279b 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -504,6 +504,7 @@ static int __init strp_mod_init(void)
 
 static void __exit strp_mod_exit(void)
 {
+	destroy_workqueue(strp_wq);
 }
 module_init(strp_mod_init);
 module_exit(strp_mod_exit);
-- 
2.1.0


From b8a6f23355e3c155bfeb20295b226f5c1c8dff4e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 3 Mar 2017 14:08:21 -0800
Subject: [PATCH 21/41] tcp: fix various issues for sockets morphing to listen
 state

[ Upstream commit 02b2faaf0af1d85585f6d6980e286d53612acfc2 ]

Dmitry Vyukov reported a divide by 0 triggered by syzkaller, exploiting
tcp_disconnect() path that was never really considered and/or used
before syzkaller ;)

I was not able to reproduce the bug, but it seems issues here are the
three possible actions that assumed they would never trigger on a
listener.

1) tcp_write_timer_handler
2) tcp_delack_timer_handler
3) MTU reduction

Only IPv6 MTU reduction was properly testing TCP_CLOSE and TCP_LISTEN
 states from tcp_v6_mtu_reduced()

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c  | 7 +++++--
 net/ipv4/tcp_timer.c | 6 ++++--
 2 files changed, 9 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 2259114..5bb809f 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -269,10 +269,13 @@ EXPORT_SYMBOL(tcp_v4_connect);
  */
 void tcp_v4_mtu_reduced(struct sock *sk)
 {
-	struct dst_entry *dst;
 	struct inet_sock *inet = inet_sk(sk);
-	u32 mtu = tcp_sk(sk)->mtu_info;
+	struct dst_entry *dst;
+	u32 mtu;
 
+	if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
+		return;
+	mtu = tcp_sk(sk)->mtu_info;
 	dst = inet_csk_update_pmtu(sk, mtu);
 	if (!dst)
 		return;
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 3ea1cf8..b1e65b3 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -249,7 +249,8 @@ void tcp_delack_timer_handler(struct sock *sk)
 
 	sk_mem_reclaim_partial(sk);
 
-	if (sk->sk_state == TCP_CLOSE || !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
+	if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
+	    !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
 		goto out;
 
 	if (time_after(icsk->icsk_ack.timeout, jiffies)) {
@@ -552,7 +553,8 @@ void tcp_write_timer_handler(struct sock *sk)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	int event;
 
-	if (sk->sk_state == TCP_CLOSE || !icsk->icsk_pending)
+	if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
+	    !icsk->icsk_pending)
 		goto out;
 
 	if (time_after(icsk->icsk_timeout, jiffies)) {
-- 
2.1.0


From a737b41282f42865c31632f6fa47ec6d458a5441 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 3 Mar 2017 21:01:02 -0800
Subject: [PATCH 22/41] net: fix socket refcounting in skb_complete_wifi_ack()

[ Upstream commit dd4f10722aeb10f4f582948839f066bebe44e5fb ]

TX skbs do not necessarily hold a reference on skb->sk->sk_refcnt
By the time TX completion happens, sk_refcnt might be already 0.

sock_hold()/sock_put() would then corrupt critical state, like
sk_wmem_alloc.

Fixes: bf7fa551e0ce ("mac80211: Resolve sk_refcnt/sk_wmem_alloc issue in wifi ack path")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 1e3e008..b806677 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3871,7 +3871,7 @@ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked)
 {
 	struct sock *sk = skb->sk;
 	struct sock_exterr_skb *serr;
-	int err;
+	int err = 1;
 
 	skb->wifi_acked_valid = 1;
 	skb->wifi_acked = acked;
@@ -3881,14 +3881,15 @@ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked)
 	serr->ee.ee_errno = ENOMSG;
 	serr->ee.ee_origin = SO_EE_ORIGIN_TXSTATUS;
 
-	/* take a reference to prevent skb_orphan() from freeing the socket */
-	sock_hold(sk);
-
-	err = sock_queue_err_skb(sk, skb);
+	/* Take a reference to prevent skb_orphan() from freeing the socket,
+	 * but only if the socket refcount is not zero.
+	 */
+	if (likely(atomic_inc_not_zero(&sk->sk_refcnt))) {
+		err = sock_queue_err_skb(sk, skb);
+		sock_put(sk);
+	}
 	if (err)
 		kfree_skb(skb);
-
-	sock_put(sk);
 }
 EXPORT_SYMBOL_GPL(skb_complete_wifi_ack);
 
-- 
2.1.0


From 6bbf227fec57cd4f92a839ced8d01198af99015e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 3 Mar 2017 21:01:03 -0800
Subject: [PATCH 23/41] net: fix socket refcounting in
 skb_complete_tx_timestamp()

[ Upstream commit 9ac25fc063751379cb77434fef9f3b088cd3e2f7 ]

TX skbs do not necessarily hold a reference on skb->sk->sk_refcnt
By the time TX completion happens, sk_refcnt might be already 0.

sock_hold()/sock_put() would then corrupt critical state, like
sk_wmem_alloc and lead to leaks or use after free.

Fixes: 62bccb8cdb69 ("net-timestamp: Make the clone operation stand-alone from phy timestamping")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index b806677..f0f462c 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3814,13 +3814,14 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
 	if (!skb_may_tx_timestamp(sk, false))
 		return;
 
-	/* take a reference to prevent skb_orphan() from freeing the socket */
-	sock_hold(sk);
-
-	*skb_hwtstamps(skb) = *hwtstamps;
-	__skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND);
-
-	sock_put(sk);
+	/* Take a reference to prevent skb_orphan() from freeing the socket,
+	 * but only if the socket refcount is not zero.
+	 */
+	if (likely(atomic_inc_not_zero(&sk->sk_refcnt))) {
+		*skb_hwtstamps(skb) = *hwtstamps;
+		__skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND);
+		sock_put(sk);
+	}
 }
 EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp);
 
-- 
2.1.0


From a38943f78da8a40ac14fe79c010feaf8399ed79c Mon Sep 17 00:00:00 2001
From: Alexey Khoroshilov <khoroshilov@ispras.ru>
Date: Sun, 5 Mar 2017 03:01:55 +0300
Subject: [PATCH 24/41] net/sched: act_skbmod: remove unneeded rcu_read_unlock
 in tcf_skbmod_dump

[ Upstream commit 6c4dc75c251721f517e9daeb5370ea606b5b35ce ]

Found by Linux Driver Verification project (linuxtesting.org).

Signed-off-by: Alexey Khoroshilov <khoroshilov@ispras.ru>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_skbmod.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index e7d9638..f85313d 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -228,7 +228,6 @@ static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a,
 
 	return skb->len;
 nla_put_failure:
-	rcu_read_unlock();
 	nlmsg_trim(skb, b);
 	return -1;
 }
-- 
2.1.0


From 01ad7cb644aca66df2e9d9f0e5bfc084d613c899 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 5 Mar 2017 10:52:16 -0800
Subject: [PATCH 25/41] dccp: fix use-after-free in dccp_feat_activate_values

[ Upstream commit 62f8f4d9066c1c6f2474845d1ca7e2891f2ae3fd ]

Dmitry reported crashes in DCCP stack [1]

Problem here is that when I got rid of listener spinlock, I missed the
fact that DCCP stores a complex state in struct dccp_request_sock,
while TCP does not.

Since multiple cpus could access it at the same time, we need to add
protection.

[1]
BUG: KASAN: use-after-free in dccp_feat_activate_values+0x967/0xab0
net/dccp/feat.c:1541 at addr ffff88003713be68
Read of size 8 by task syz-executor2/8457
CPU: 2 PID: 8457 Comm: syz-executor2 Not tainted 4.10.0-rc7+ #127
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:15 [inline]
 dump_stack+0x292/0x398 lib/dump_stack.c:51
 kasan_object_err+0x1c/0x70 mm/kasan/report.c:162
 print_address_description mm/kasan/report.c:200 [inline]
 kasan_report_error mm/kasan/report.c:289 [inline]
 kasan_report.part.1+0x20e/0x4e0 mm/kasan/report.c:311
 kasan_report mm/kasan/report.c:332 [inline]
 __asan_report_load8_noabort+0x29/0x30 mm/kasan/report.c:332
 dccp_feat_activate_values+0x967/0xab0 net/dccp/feat.c:1541
 dccp_create_openreq_child+0x464/0x610 net/dccp/minisocks.c:121
 dccp_v6_request_recv_sock+0x1f6/0x1960 net/dccp/ipv6.c:457
 dccp_check_req+0x335/0x5a0 net/dccp/minisocks.c:186
 dccp_v6_rcv+0x69e/0x1d00 net/dccp/ipv6.c:711
 ip6_input_finish+0x46d/0x17a0 net/ipv6/ip6_input.c:279
 NF_HOOK include/linux/netfilter.h:257 [inline]
 ip6_input+0xdb/0x590 net/ipv6/ip6_input.c:322
 dst_input include/net/dst.h:507 [inline]
 ip6_rcv_finish+0x289/0x890 net/ipv6/ip6_input.c:69
 NF_HOOK include/linux/netfilter.h:257 [inline]
 ipv6_rcv+0x12ec/0x23d0 net/ipv6/ip6_input.c:203
 __netif_receive_skb_core+0x1ae5/0x3400 net/core/dev.c:4190
 __netif_receive_skb+0x2a/0x170 net/core/dev.c:4228
 process_backlog+0xe5/0x6c0 net/core/dev.c:4839
 napi_poll net/core/dev.c:5202 [inline]
 net_rx_action+0xe70/0x1900 net/core/dev.c:5267
 __do_softirq+0x2fb/0xb7d kernel/softirq.c:284
 do_softirq_own_stack+0x1c/0x30 arch/x86/entry/entry_64.S:902
 </IRQ>
 do_softirq.part.17+0x1e8/0x230 kernel/softirq.c:328
 do_softirq kernel/softirq.c:176 [inline]
 __local_bh_enable_ip+0x1f2/0x200 kernel/softirq.c:181
 local_bh_enable include/linux/bottom_half.h:31 [inline]
 rcu_read_unlock_bh include/linux/rcupdate.h:971 [inline]
 ip6_finish_output2+0xbb0/0x23d0 net/ipv6/ip6_output.c:123
 ip6_finish_output+0x302/0x960 net/ipv6/ip6_output.c:148
 NF_HOOK_COND include/linux/netfilter.h:246 [inline]
 ip6_output+0x1cb/0x8d0 net/ipv6/ip6_output.c:162
 ip6_xmit+0xcdf/0x20d0 include/net/dst.h:501
 inet6_csk_xmit+0x320/0x5f0 net/ipv6/inet6_connection_sock.c:179
 dccp_transmit_skb+0xb09/0x1120 net/dccp/output.c:141
 dccp_xmit_packet+0x215/0x760 net/dccp/output.c:280
 dccp_write_xmit+0x168/0x1d0 net/dccp/output.c:362
 dccp_sendmsg+0x79c/0xb10 net/dccp/proto.c:796
 inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:744
 sock_sendmsg_nosec net/socket.c:635 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:645
 SYSC_sendto+0x660/0x810 net/socket.c:1687
 SyS_sendto+0x40/0x50 net/socket.c:1655
 entry_SYSCALL_64_fastpath+0x1f/0xc2
RIP: 0033:0x4458b9
RSP: 002b:00007f8ceb77bb58 EFLAGS: 00000282 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 0000000000000017 RCX: 00000000004458b9
RDX: 0000000000000023 RSI: 0000000020e60000 RDI: 0000000000000017
RBP: 00000000006e1b90 R08: 00000000200f9fe1 R09: 0000000000000020
R10: 0000000000008010 R11: 0000000000000282 R12: 00000000007080a8
R13: 0000000000000000 R14: 00007f8ceb77c9c0 R15: 00007f8ceb77c700
Object at ffff88003713be50, in cache kmalloc-64 size: 64
Allocated:
PID = 8446
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57
 save_stack+0x43/0xd0 mm/kasan/kasan.c:502
 set_track mm/kasan/kasan.c:514 [inline]
 kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:605
 kmem_cache_alloc_trace+0x82/0x270 mm/slub.c:2738
 kmalloc include/linux/slab.h:490 [inline]
 dccp_feat_entry_new+0x214/0x410 net/dccp/feat.c:467
 dccp_feat_push_change+0x38/0x220 net/dccp/feat.c:487
 __feat_register_sp+0x223/0x2f0 net/dccp/feat.c:741
 dccp_feat_propagate_ccid+0x22b/0x2b0 net/dccp/feat.c:949
 dccp_feat_server_ccid_dependencies+0x1b3/0x250 net/dccp/feat.c:1012
 dccp_make_response+0x1f1/0xc90 net/dccp/output.c:423
 dccp_v6_send_response+0x4ec/0xc20 net/dccp/ipv6.c:217
 dccp_v6_conn_request+0xaba/0x11b0 net/dccp/ipv6.c:377
 dccp_rcv_state_process+0x51e/0x1650 net/dccp/input.c:606
 dccp_v6_do_rcv+0x213/0x350 net/dccp/ipv6.c:632
 sk_backlog_rcv include/net/sock.h:893 [inline]
 __sk_receive_skb+0x36f/0xcc0 net/core/sock.c:479
 dccp_v6_rcv+0xba5/0x1d00 net/dccp/ipv6.c:742
 ip6_input_finish+0x46d/0x17a0 net/ipv6/ip6_input.c:279
 NF_HOOK include/linux/netfilter.h:257 [inline]
 ip6_input+0xdb/0x590 net/ipv6/ip6_input.c:322
 dst_input include/net/dst.h:507 [inline]
 ip6_rcv_finish+0x289/0x890 net/ipv6/ip6_input.c:69
 NF_HOOK include/linux/netfilter.h:257 [inline]
 ipv6_rcv+0x12ec/0x23d0 net/ipv6/ip6_input.c:203
 __netif_receive_skb_core+0x1ae5/0x3400 net/core/dev.c:4190
 __netif_receive_skb+0x2a/0x170 net/core/dev.c:4228
 process_backlog+0xe5/0x6c0 net/core/dev.c:4839
 napi_poll net/core/dev.c:5202 [inline]
 net_rx_action+0xe70/0x1900 net/core/dev.c:5267
 __do_softirq+0x2fb/0xb7d kernel/softirq.c:284
Freed:
PID = 15
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57
 save_stack+0x43/0xd0 mm/kasan/kasan.c:502
 set_track mm/kasan/kasan.c:514 [inline]
 kasan_slab_free+0x73/0xc0 mm/kasan/kasan.c:578
 slab_free_hook mm/slub.c:1355 [inline]
 slab_free_freelist_hook mm/slub.c:1377 [inline]
 slab_free mm/slub.c:2954 [inline]
 kfree+0xe8/0x2b0 mm/slub.c:3874
 dccp_feat_entry_destructor.part.4+0x48/0x60 net/dccp/feat.c:418
 dccp_feat_entry_destructor net/dccp/feat.c:416 [inline]
 dccp_feat_list_pop net/dccp/feat.c:541 [inline]
 dccp_feat_activate_values+0x57f/0xab0 net/dccp/feat.c:1543
 dccp_create_openreq_child+0x464/0x610 net/dccp/minisocks.c:121
 dccp_v6_request_recv_sock+0x1f6/0x1960 net/dccp/ipv6.c:457
 dccp_check_req+0x335/0x5a0 net/dccp/minisocks.c:186
 dccp_v6_rcv+0x69e/0x1d00 net/dccp/ipv6.c:711
 ip6_input_finish+0x46d/0x17a0 net/ipv6/ip6_input.c:279
 NF_HOOK include/linux/netfilter.h:257 [inline]
 ip6_input+0xdb/0x590 net/ipv6/ip6_input.c:322
 dst_input include/net/dst.h:507 [inline]
 ip6_rcv_finish+0x289/0x890 net/ipv6/ip6_input.c:69
 NF_HOOK include/linux/netfilter.h:257 [inline]
 ipv6_rcv+0x12ec/0x23d0 net/ipv6/ip6_input.c:203
 __netif_receive_skb_core+0x1ae5/0x3400 net/core/dev.c:4190
 __netif_receive_skb+0x2a/0x170 net/core/dev.c:4228
 process_backlog+0xe5/0x6c0 net/core/dev.c:4839
 napi_poll net/core/dev.c:5202 [inline]
 net_rx_action+0xe70/0x1900 net/core/dev.c:5267
 __do_softirq+0x2fb/0xb7d kernel/softirq.c:284
Memory state around the buggy address:
 ffff88003713bd00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 ffff88003713bd80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
>ffff88003713be00: fc fc fc fc fc fc fc fc fc fc fb fb fb fb fb fb
                                                          ^

Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Tested-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/dccp.h |  1 +
 net/dccp/minisocks.c | 24 ++++++++++++++++--------
 2 files changed, 17 insertions(+), 8 deletions(-)

diff --git a/include/linux/dccp.h b/include/linux/dccp.h
index 61d042b..6844929 100644
--- a/include/linux/dccp.h
+++ b/include/linux/dccp.h
@@ -163,6 +163,7 @@ struct dccp_request_sock {
 	__u64			 dreq_isr;
 	__u64			 dreq_gsr;
 	__be32			 dreq_service;
+	spinlock_t		 dreq_lock;
 	struct list_head	 dreq_featneg;
 	__u32			 dreq_timestamp_echo;
 	__u32			 dreq_timestamp_time;
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index d20d948..39e7e2b 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -146,6 +146,13 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
 	struct dccp_request_sock *dreq = dccp_rsk(req);
 	bool own_req;
 
+	/* TCP/DCCP listeners became lockless.
+	 * DCCP stores complex state in its request_sock, so we need
+	 * a protection for them, now this code runs without being protected
+	 * by the parent (listener) lock.
+	 */
+	spin_lock_bh(&dreq->dreq_lock);
+
 	/* Check for retransmitted REQUEST */
 	if (dccp_hdr(skb)->dccph_type == DCCP_PKT_REQUEST) {
 
@@ -160,7 +167,7 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
 			inet_rtx_syn_ack(sk, req);
 		}
 		/* Network Duplicate, discard packet */
-		return NULL;
+		goto out;
 	}
 
 	DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_PACKET_ERROR;
@@ -186,20 +193,20 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
 
 	child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL,
 							 req, &own_req);
-	if (!child)
-		goto listen_overflow;
-
-	return inet_csk_complete_hashdance(sk, child, req, own_req);
+	if (child) {
+		child = inet_csk_complete_hashdance(sk, child, req, own_req);
+		goto out;
+	}
 
-listen_overflow:
-	dccp_pr_debug("listen_overflow!\n");
 	DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_TOO_BUSY;
 drop:
 	if (dccp_hdr(skb)->dccph_type != DCCP_PKT_RESET)
 		req->rsk_ops->send_reset(sk, skb);
 
 	inet_csk_reqsk_queue_drop(sk, req);
-	return NULL;
+out:
+	spin_unlock_bh(&dreq->dreq_lock);
+	return child;
 }
 
 EXPORT_SYMBOL_GPL(dccp_check_req);
@@ -250,6 +257,7 @@ int dccp_reqsk_init(struct request_sock *req,
 {
 	struct dccp_request_sock *dreq = dccp_rsk(req);
 
+	spin_lock_init(&dreq->dreq_lock);
 	inet_rsk(req)->ir_rmt_port = dccp_hdr(skb)->dccph_sport;
 	inet_rsk(req)->ir_num	   = ntohs(dccp_hdr(skb)->dccph_dport);
 	inet_rsk(req)->acked	   = 0;
-- 
2.1.0


From eee6a4091bf68979699b93828618211c1c3eacf5 Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Mon, 6 Mar 2017 08:53:04 -0800
Subject: [PATCH 26/41] vrf: Fix use-after-free in vrf_xmit

[ Upstream commit f7887d40e541f74402df0684a1463c0a0bb68c68 ]

KASAN detected a use-after-free:

[  269.467067] BUG: KASAN: use-after-free in vrf_xmit+0x7f1/0x827 [vrf] at addr ffff8800350a21c0
[  269.467067] Read of size 4 by task ssh/1879
[  269.467067] CPU: 1 PID: 1879 Comm: ssh Not tainted 4.10.0+ #249
[  269.467067] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.7.5-20140531_083030-gandalf 04/01/2014
[  269.467067] Call Trace:
[  269.467067]  dump_stack+0x81/0xb6
[  269.467067]  kasan_object_err+0x21/0x78
[  269.467067]  kasan_report+0x2f7/0x450
[  269.467067]  ? vrf_xmit+0x7f1/0x827 [vrf]
[  269.467067]  ? ip_output+0xa4/0xdb
[  269.467067]  __asan_load4+0x6b/0x6d
[  269.467067]  vrf_xmit+0x7f1/0x827 [vrf]
...

Which corresponds to the skb access after xmit handling. Fix by saving
skb->len and using the saved value to update stats.

Fixes: 193125dbd8eb2 ("net: Introduce VRF device driver")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 95cf1d8..bc744ac 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -346,6 +346,7 @@ static netdev_tx_t is_ip_tx_frame(struct sk_buff *skb, struct net_device *dev)
 
 static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev)
 {
+	int len = skb->len;
 	netdev_tx_t ret = is_ip_tx_frame(skb, dev);
 
 	if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) {
@@ -353,7 +354,7 @@ static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev)
 
 		u64_stats_update_begin(&dstats->syncp);
 		dstats->tx_pkts++;
-		dstats->tx_bytes += skb->len;
+		dstats->tx_bytes += len;
 		u64_stats_update_end(&dstats->syncp);
 	} else {
 		this_cpu_inc(dev->dstats->tx_drps);
-- 
2.1.0


From d6fec813fdcdd88b86bafab00096f1a7bd851d03 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 7 Mar 2017 18:33:31 +0100
Subject: [PATCH 27/41] net/tunnel: set inner protocol in network gro hooks

[ Upstream commit 294acf1c01bace5cea5d30b510504238bf5f7c25 ]

The gso code of several tunnels type (gre and udp tunnels)
takes for granted that the skb->inner_protocol is properly
initialized and drops the packet elsewhere.

On the forwarding path no one is initializing such field,
so gro encapsulated packets are dropped on forward.

Since commit 38720352412a ("gre: Use inner_proto to obtain
inner header protocol"), this can be reproduced when the
encapsulated packets use gre as the tunneling protocol.

The issue happens also with vxlan and geneve tunnels since
commit 8bce6d7d0d1e ("udp: Generalize skb_udp_segment"), if the
forwarding host's ingress nic has h/w offload for such tunnel
and a vxlan/geneve device is configured on top of it, regardless
of the configured peer address and vni.

To address the issue, this change initialize the inner_protocol
field for encapsulated packets in both ipv4 and ipv6 gro complete
callbacks.

Fixes: 38720352412a ("gre: Use inner_proto to obtain inner header protocol")
Fixes: 8bce6d7d0d1e ("udp: Generalize skb_udp_segment")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/af_inet.c     | 4 +++-
 net/ipv6/ip6_offload.c | 4 +++-
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 21514324..971b947 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1460,8 +1460,10 @@ int inet_gro_complete(struct sk_buff *skb, int nhoff)
 	int proto = iph->protocol;
 	int err = -ENOSYS;
 
-	if (skb->encapsulation)
+	if (skb->encapsulation) {
+		skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IP));
 		skb_set_inner_network_header(skb, nhoff);
+	}
 
 	csum_replace2(&iph->check, iph->tot_len, newlen);
 	iph->tot_len = newlen;
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index fc7b401..33b04ec 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -294,8 +294,10 @@ static int ipv6_gro_complete(struct sk_buff *skb, int nhoff)
 	struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + nhoff);
 	int err = -ENOSYS;
 
-	if (skb->encapsulation)
+	if (skb->encapsulation) {
+		skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IPV6));
 		skb_set_inner_network_header(skb, nhoff);
+	}
 
 	iph->payload_len = htons(skb->len - nhoff - sizeof(*iph));
 
-- 
2.1.0


From 7c7142cb3074c4372a1f96394e32a71524982313 Mon Sep 17 00:00:00 2001
From: "Dmitry V. Levin" <ldv@altlinux.org>
Date: Tue, 7 Mar 2017 23:50:50 +0300
Subject: [PATCH 28/41] uapi: fix linux/packet_diag.h userspace compilation
 error

[ Upstream commit 745cb7f8a5de0805cade3de3991b7a95317c7c73 ]

Replace MAX_ADDR_LEN with its numeric value to fix the following
linux/packet_diag.h userspace compilation error:

/usr/include/linux/packet_diag.h:67:17: error: 'MAX_ADDR_LEN' undeclared here (not in a function)
  __u8 pdmc_addr[MAX_ADDR_LEN];

This is not the first case in the UAPI where the numeric value
of MAX_ADDR_LEN is used instead of symbolic one, uapi/linux/if_link.h
already does the same:

$ grep MAX_ADDR_LEN include/uapi/linux/if_link.h
	__u8 mac[32]; /* MAX_ADDR_LEN */

There are no UAPI headers besides these two that use MAX_ADDR_LEN.

Signed-off-by: Dmitry V. Levin <ldv@altlinux.org>
Acked-by: Pavel Emelyanov <xemul@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/packet_diag.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/uapi/linux/packet_diag.h b/include/uapi/linux/packet_diag.h
index d08c63f..0c5d5dd 100644
--- a/include/uapi/linux/packet_diag.h
+++ b/include/uapi/linux/packet_diag.h
@@ -64,7 +64,7 @@ struct packet_diag_mclist {
 	__u32	pdmc_count;
 	__u16	pdmc_type;
 	__u16	pdmc_alen;
-	__u8	pdmc_addr[MAX_ADDR_LEN];
+	__u8	pdmc_addr[32]; /* MAX_ADDR_LEN */
 };
 
 struct packet_diag_ring {
-- 
2.1.0


From 45c0883fa49b02a6ba575222530cd922b249ca9b Mon Sep 17 00:00:00 2001
From: Etienne Noss <etienne.noss@wifirst.fr>
Date: Fri, 10 Mar 2017 16:55:32 +0100
Subject: [PATCH 29/41] act_connmark: avoid crashing on malformed nlattrs with
 null parms
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 52491c7607c5527138095edf44c53169dc1ddb82 ]

tcf_connmark_init does not check in its configuration if TCA_CONNMARK_PARMS
is set, resulting in a null pointer dereference when trying to access it.

[501099.043007] BUG: unable to handle kernel NULL pointer dereference at 0000000000000004
[501099.043039] IP: [<ffffffffc10c60fb>] tcf_connmark_init+0x8b/0x180 [act_connmark]
...
[501099.044334] Call Trace:
[501099.044345]  [<ffffffffa47270e8>] ? tcf_action_init_1+0x198/0x1b0
[501099.044363]  [<ffffffffa47271b0>] ? tcf_action_init+0xb0/0x120
[501099.044380]  [<ffffffffa47250a4>] ? tcf_exts_validate+0xc4/0x110
[501099.044398]  [<ffffffffc0f5fa97>] ? u32_set_parms+0xa7/0x270 [cls_u32]
[501099.044417]  [<ffffffffc0f60bf0>] ? u32_change+0x680/0x87b [cls_u32]
[501099.044436]  [<ffffffffa4725d1d>] ? tc_ctl_tfilter+0x4dd/0x8a0
[501099.044454]  [<ffffffffa44a23a1>] ? security_capable+0x41/0x60
[501099.044471]  [<ffffffffa470ca01>] ? rtnetlink_rcv_msg+0xe1/0x220
[501099.044490]  [<ffffffffa470c920>] ? rtnl_newlink+0x870/0x870
[501099.044507]  [<ffffffffa472cc61>] ? netlink_rcv_skb+0xa1/0xc0
[501099.044524]  [<ffffffffa47073f4>] ? rtnetlink_rcv+0x24/0x30
[501099.044541]  [<ffffffffa472c634>] ? netlink_unicast+0x184/0x230
[501099.044558]  [<ffffffffa472c9d8>] ? netlink_sendmsg+0x2f8/0x3b0
[501099.044576]  [<ffffffffa46d8880>] ? sock_sendmsg+0x30/0x40
[501099.044592]  [<ffffffffa46d8e03>] ? SYSC_sendto+0xd3/0x150
[501099.044608]  [<ffffffffa425fda1>] ? __do_page_fault+0x2d1/0x510
[501099.044626]  [<ffffffffa47fbd7b>] ? system_call_fast_compare_end+0xc/0x9b

Fixes: 22a5dc0e5e3e ("net: sched: Introduce connmark action")
Signed-off-by: Étienne Noss <etienne.noss@wifirst.fr>
Signed-off-by: Victorien Molle <victorien.molle@wifirst.fr>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_connmark.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index eae07a2..1191179 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -113,6 +113,9 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla,
 	if (ret < 0)
 		return ret;
 
+	if (!tb[TCA_CONNMARK_PARMS])
+		return -EINVAL;
+
 	parm = nla_data(tb[TCA_CONNMARK_PARMS]);
 
 	if (!tcf_hash_check(tn, parm->index, a, bind)) {
-- 
2.1.0


From df098aa5a160cf7cdf20b5d59dff20219b4fbea4 Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Fri, 10 Mar 2017 09:46:15 -0800
Subject: [PATCH 30/41] mpls: Send route delete notifications when router
 module is unloaded

[ Upstream commit e37791ec1ad785b59022ae211f63a16189bacebf ]

When the mpls_router module is unloaded, mpls routes are deleted but
notifications are not sent to userspace leaving userspace caches
out of sync. Add the call to mpls_notify_route in mpls_net_exit as
routes are freed.

Fixes: 0189197f44160 ("mpls: Basic routing support")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mpls/af_mpls.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 5b77377..2a21ff1 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -1696,6 +1696,7 @@ static void mpls_net_exit(struct net *net)
 	for (index = 0; index < platform_labels; index++) {
 		struct mpls_route *rt = rtnl_dereference(platform_label[index]);
 		RCU_INIT_POINTER(platform_label[index], NULL);
+		mpls_notify_route(net, index, rt, NULL, NULL);
 		mpls_rt_free(rt);
 	}
 	rtnl_unlock();
-- 
2.1.0


From bdcfc4df2239e46bbf96602e2e0888f7a22f607e Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Fri, 10 Mar 2017 14:11:39 -0800
Subject: [PATCH 31/41] mpls: Do not decrement alive counter for unregister
 events

[ Upstream commit 79099aab38c8f5c746748b066ae74ba984fe2cc8 ]

Multipath routes can be rendered usesless when a device in one of the
paths is deleted. For example:

$ ip -f mpls ro ls
100
	nexthop as to 200 via inet 172.16.2.2  dev virt12
	nexthop as to 300 via inet 172.16.3.2  dev br0
101
	nexthop as to 201 via inet6 2000:2::2  dev virt12
	nexthop as to 301 via inet6 2000:3::2  dev br0

$ ip li del br0

When br0 is deleted the other hop is not considered in
mpls_select_multipath because of the alive check -- rt_nhn_alive
is 0.

rt_nhn_alive is decremented once in mpls_ifdown when the device is taken
down (NETDEV_DOWN) and again when it is deleted (NETDEV_UNREGISTER). For
a 2 hop route, deleting one device drops the alive count to 0. Since
devices are taken down before unregistering, the decrement on
NETDEV_UNREGISTER is redundant.

Fixes: c89359a42e2a4 ("mpls: support for dead routes")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mpls/af_mpls.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 2a21ff1..1309e2c 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -956,7 +956,8 @@ static void mpls_ifdown(struct net_device *dev, int event)
 				/* fall through */
 			case NETDEV_CHANGE:
 				nh->nh_flags |= RTNH_F_LINKDOWN;
-				ACCESS_ONCE(rt->rt_nhn_alive) = rt->rt_nhn_alive - 1;
+				if (event != NETDEV_UNREGISTER)
+					ACCESS_ONCE(rt->rt_nhn_alive) = rt->rt_nhn_alive - 1;
 				break;
 			}
 			if (event == NETDEV_UNREGISTER)
-- 
2.1.0


From 69d7db15c7abf3ae5fa865b5a3dc61bf59556279 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Mon, 13 Mar 2017 13:28:09 +0100
Subject: [PATCH 32/41] ipv6: make ECMP route replacement less greedy

[ Upstream commit 67e194007be08d071294456274dd53e0a04fdf90 ]

Commit 27596472473a ("ipv6: fix ECMP route replacement") introduced a
loop that removes all siblings of an ECMP route that is being
replaced. However, this loop doesn't stop when it has replaced
siblings, and keeps removing other routes with a higher metric.
We also end up triggering the WARN_ON after the loop, because after
this nsiblings < 0.

Instead, stop the loop when we have taken care of all routes with the
same metric as the route being replaced.

  Reproducer:
  ===========
    #!/bin/sh

    ip netns add ns1
    ip netns add ns2
    ip -net ns1 link set lo up

    for x in 0 1 2 ; do
        ip link add veth$x netns ns2 type veth peer name eth$x netns ns1
        ip -net ns1 link set eth$x up
        ip -net ns2 link set veth$x up
    done

    ip -net ns1 -6 r a 2000::/64 nexthop via fe80::0 dev eth0 \
            nexthop via fe80::1 dev eth1 nexthop via fe80::2 dev eth2
    ip -net ns1 -6 r a 2000::/64 via fe80::42 dev eth0 metric 256
    ip -net ns1 -6 r a 2000::/64 via fe80::43 dev eth0 metric 2048

    echo "before replace, 3 routes"
    ip -net ns1 -6 r | grep -v '^fe80\|^ff00'
    echo

    ip -net ns1 -6 r c 2000::/64 nexthop via fe80::4 dev eth0 \
            nexthop via fe80::5 dev eth1 nexthop via fe80::6 dev eth2

    echo "after replace, only 2 routes, metric 2048 is gone"
    ip -net ns1 -6 r | grep -v '^fe80\|^ff00'

Fixes: 27596472473a ("ipv6: fix ECMP route replacement")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Reviewed-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_fib.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index ef54852..8c88a37 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -908,6 +908,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 			ins = &rt->dst.rt6_next;
 			iter = *ins;
 			while (iter) {
+				if (iter->rt6i_metric > rt->rt6i_metric)
+					break;
 				if (rt6_qualify_for_ecmp(iter)) {
 					*ins = iter->dst.rt6_next;
 					fib6_purge_rt(iter, fn, info->nl_net);
-- 
2.1.0


From 11a57b16f878486fd80a6f3fe40c152e2ca5c732 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 13 Mar 2017 16:24:28 +0100
Subject: [PATCH 33/41] ipv6: avoid write to a possibly cloned skb

[ Upstream commit 79e49503efe53a8c51d8b695bedc8a346c5e4a87 ]

ip6_fragment, in case skb has a fraglist, checks if the
skb is cloned.  If it is, it will move to the 'slow path' and allocates
new skbs for each fragment.

However, right before entering the slowpath loop, it updates the
nexthdr value of the last ipv6 extension header to NEXTHDR_FRAGMENT,
to account for the fragment header that will be inserted in the new
ipv6-fragment skbs.

In case original skb is cloned this munges nexthdr value of another
skb.  Avoid this by doing the nexthdr update for each of the new fragment
skbs separately.

This was observed with tcpdump on a bridge device where netfilter ipv6
reassembly is active:  tcpdump shows malformed fragment headers as
the l4 header (icmpv6, tcp, etc). is decoded as a fragment header.

Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Reported-by: Andreas Karis <akaris@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_output.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 9a87bfb..e27b8fd 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -757,13 +757,14 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 	 *	Fragment the datagram.
 	 */
 
-	*prevhdr = NEXTHDR_FRAGMENT;
 	troom = rt->dst.dev->needed_tailroom;
 
 	/*
 	 *	Keep copying data until we run out.
 	 */
 	while (left > 0)	{
+		u8 *fragnexthdr_offset;
+
 		len = left;
 		/* IF: it doesn't fit, use 'mtu' - the data space left */
 		if (len > mtu)
@@ -808,6 +809,10 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		 */
 		skb_copy_from_linear_data(skb, skb_network_header(frag), hlen);
 
+		fragnexthdr_offset = skb_network_header(frag);
+		fragnexthdr_offset += prevhdr - skb_network_header(skb);
+		*fragnexthdr_offset = NEXTHDR_FRAGMENT;
+
 		/*
 		 *	Build fragment header.
 		 */
-- 
2.1.0


From fc972464cb99de5348423a5756766e7757a80601 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 13 Mar 2017 17:38:17 +0100
Subject: [PATCH 34/41] bridge: drop netfilter fake rtable unconditionally

[ Upstream commit a13b2082ece95247779b9995c4e91b4246bed023 ]

Andreas reports kernel oops during rmmod of the br_netfilter module.
Hannes debugged the oops down to a NULL rt6info->rt6i_indev.

Problem is that br_netfilter has the nasty concept of adding a fake
rtable to skb->dst; this happens in a br_netfilter prerouting hook.

A second hook (in bridge LOCAL_IN) is supposed to remove these again
before the skb is handed up the stack.

However, on module unload hooks get unregistered which means an
skb could traverse the prerouting hook that attaches the fake_rtable,
while the 'fake rtable remove' hook gets removed from the hooklist
immediately after.

Fixes: 34666d467cbf1e2e3c7 ("netfilter: bridge: move br_netfilter out of the core")
Reported-by: Andreas Karis <akaris@redhat.com>
Debugged-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_input.c           |  1 +
 net/bridge/br_netfilter_hooks.c | 21 ---------------------
 2 files changed, 1 insertion(+), 21 deletions(-)

diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 855b72f..267b46a 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -29,6 +29,7 @@ EXPORT_SYMBOL(br_should_route_hook);
 static int
 br_netif_receive_skb(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
+	br_drop_fake_rtable(skb);
 	return netif_receive_skb(skb);
 }
 
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 7fbdbae..aa1df1a 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -521,21 +521,6 @@ static unsigned int br_nf_pre_routing(void *priv,
 }
 
 
-/* PF_BRIDGE/LOCAL_IN ************************************************/
-/* The packet is locally destined, which requires a real
- * dst_entry, so detach the fake one.  On the way up, the
- * packet would pass through PRE_ROUTING again (which already
- * took place when the packet entered the bridge), but we
- * register an IPv4 PRE_ROUTING 'sabotage' hook that will
- * prevent this from happening. */
-static unsigned int br_nf_local_in(void *priv,
-				   struct sk_buff *skb,
-				   const struct nf_hook_state *state)
-{
-	br_drop_fake_rtable(skb);
-	return NF_ACCEPT;
-}
-
 /* PF_BRIDGE/FORWARD *************************************************/
 static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
@@ -906,12 +891,6 @@ static struct nf_hook_ops br_nf_ops[] __read_mostly = {
 		.priority = NF_BR_PRI_BRNF,
 	},
 	{
-		.hook = br_nf_local_in,
-		.pf = NFPROTO_BRIDGE,
-		.hooknum = NF_BR_LOCAL_IN,
-		.priority = NF_BR_PRI_BRNF,
-	},
-	{
 		.hook = br_nf_forward_ip,
 		.pf = NFPROTO_BRIDGE,
 		.hooknum = NF_BR_FORWARD,
-- 
2.1.0


From e99fea9bc5cbcab067d4eff941b154afc96a2639 Mon Sep 17 00:00:00 2001
From: Jon Maxwell <jmaxwell37@gmail.com>
Date: Fri, 10 Mar 2017 16:40:33 +1100
Subject: [PATCH 35/41] dccp/tcp: fix routing redirect race
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 45caeaa5ac0b4b11784ac6f932c0ad4c6b67cda0 ]

As Eric Dumazet pointed out this also needs to be fixed in IPv6.
v2: Contains the IPv6 tcp/Ipv6 dccp patches as well.

We have seen a few incidents lately where a dst_enty has been freed
with a dangling TCP socket reference (sk->sk_dst_cache) pointing to that
dst_entry. If the conditions/timings are right a crash then ensues when the
freed dst_entry is referenced later on. A Common crashing back trace is:

 #8 [] page_fault at ffffffff8163e648
    [exception RIP: __tcp_ack_snd_check+74]
.
.
 #9 [] tcp_rcv_established at ffffffff81580b64
#10 [] tcp_v4_do_rcv at ffffffff8158b54a
#11 [] tcp_v4_rcv at ffffffff8158cd02
#12 [] ip_local_deliver_finish at ffffffff815668f4
#13 [] ip_local_deliver at ffffffff81566bd9
#14 [] ip_rcv_finish at ffffffff8156656d
#15 [] ip_rcv at ffffffff81566f06
#16 [] __netif_receive_skb_core at ffffffff8152b3a2
#17 [] __netif_receive_skb at ffffffff8152b608
#18 [] netif_receive_skb at ffffffff8152b690
#19 [] vmxnet3_rq_rx_complete at ffffffffa015eeaf [vmxnet3]
#20 [] vmxnet3_poll_rx_only at ffffffffa015f32a [vmxnet3]
#21 [] net_rx_action at ffffffff8152bac2
#22 [] __do_softirq at ffffffff81084b4f
#23 [] call_softirq at ffffffff8164845c
#24 [] do_softirq at ffffffff81016fc5
#25 [] irq_exit at ffffffff81084ee5
#26 [] do_IRQ at ffffffff81648ff8

Of course it may happen with other NIC drivers as well.

It's found the freed dst_entry here:

 224 static bool tcp_in_quickack_mode(struct sock *sk)↩
 225 {↩
 226 ▹       const struct inet_connection_sock *icsk = inet_csk(sk);↩
 227 ▹       const struct dst_entry *dst = __sk_dst_get(sk);↩
 228 ↩
 229 ▹       return (dst && dst_metric(dst, RTAX_QUICKACK)) ||↩
 230 ▹       ▹       (icsk->icsk_ack.quick && !icsk->icsk_ack.pingpong);↩
 231 }↩

But there are other backtraces attributed to the same freed dst_entry in
netfilter code as well.

All the vmcores showed 2 significant clues:

- Remote hosts behind the default gateway had always been redirected to a
different gateway. A rtable/dst_entry will be added for that host. Making
more dst_entrys with lower reference counts. Making this more probable.

- All vmcores showed a postitive LockDroppedIcmps value, e.g:

LockDroppedIcmps                  267

A closer look at the tcp_v4_err() handler revealed that do_redirect() will run
regardless of whether user space has the socket locked. This can result in a
race condition where the same dst_entry cached in sk->sk_dst_entry can be
decremented twice for the same socket via:

do_redirect()->__sk_dst_check()-> dst_release().

Which leads to the dst_entry being prematurely freed with another socket
pointing to it via sk->sk_dst_cache and a subsequent crash.

To fix this skip do_redirect() if usespace has the socket locked. Instead let
the redirect take place later when user space does not have the socket
locked.

The dccp/IPv6 code is very similar in this respect, so fixing it there too.

As Eric Garver pointed out the following commit now invalidates routes. Which
can set the dst->obsolete flag so that ipv4_dst_check() returns null and
triggers the dst_release().

Fixes: ceb3320610d6 ("ipv4: Kill routes during PMTU/redirect updates.")
Cc: Eric Garver <egarver@redhat.com>
Cc: Hannes Sowa <hsowa@redhat.com>
Signed-off-by: Jon Maxwell <jmaxwell37@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ipv4.c     | 3 ++-
 net/dccp/ipv6.c     | 8 +++++---
 net/ipv4/tcp_ipv4.c | 3 ++-
 net/ipv6/tcp_ipv6.c | 8 +++++---
 4 files changed, 14 insertions(+), 8 deletions(-)

diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index edbe59d..86b0933 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -289,7 +289,8 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
 
 	switch (type) {
 	case ICMP_REDIRECT:
-		dccp_do_redirect(skb, sk);
+		if (!sock_owned_by_user(sk))
+			dccp_do_redirect(skb, sk);
 		goto out;
 	case ICMP_SOURCE_QUENCH:
 		/* Just silently ignore these. */
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 7506c03..237d62c 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -122,10 +122,12 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	np = inet6_sk(sk);
 
 	if (type == NDISC_REDIRECT) {
-		struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
+		if (!sock_owned_by_user(sk)) {
+			struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
 
-		if (dst)
-			dst->ops->redirect(dst, sk, skb);
+			if (dst)
+				dst->ops->redirect(dst, sk, skb);
+		}
 		goto out;
 	}
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 5bb809f..6988566 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -421,7 +421,8 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 
 	switch (type) {
 	case ICMP_REDIRECT:
-		do_redirect(icmp_skb, sk);
+		if (!sock_owned_by_user(sk))
+			do_redirect(icmp_skb, sk);
 		goto out;
 	case ICMP_SOURCE_QUENCH:
 		/* Just silently ignore these. */
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 6673965..b2e61a0 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -375,10 +375,12 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	np = inet6_sk(sk);
 
 	if (type == NDISC_REDIRECT) {
-		struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
+		if (!sock_owned_by_user(sk)) {
+			struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
 
-		if (dst)
-			dst->ops->redirect(dst, sk, skb);
+			if (dst)
+				dst->ops->redirect(dst, sk, skb);
+		}
 		goto out;
 	}
 
-- 
2.1.0


From 3aca1a3e65c089f36ba27fc477096212cdb3aca4 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Mon, 13 Mar 2017 00:00:26 +0100
Subject: [PATCH 36/41] tun: fix premature POLLOUT notification on tun devices
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit b20e2d54789c6acbf6bd0efdbec2cf5fa4d90ef1 ]

aszlig observed failing ssh tunnels (-w) during initialization since
commit cc9da6cc4f56e0 ("ipv6: addrconf: use stable address generator for
ARPHRD_NONE"). We already had reports that the mentioned commit breaks
Juniper VPN connections. I can't clearly say that the Juniper VPN client
has the same problem, but it is worth a try to hint to this patch.

Because of the early generation of link local addresses, the kernel now
can start asking for routers on the local subnet much earlier than usual.
Those router solicitation packets arrive inside the ssh channels and
should be transmitted to the tun fd before the configuration scripts
might have upped the interface and made it ready for transmission.

ssh polls on the interface and receives back a POLL_OUT. It tries to send
the earily router solicitation packet to the tun interface.  Unfortunately
it hasn't been up'ed yet by config scripts, thus failing with -EIO. ssh
doesn't retry again and considers the tun interface broken forever.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=121131
Fixes: cc9da6cc4f56 ("ipv6: addrconf: use stable address generator for ARPHRD_NONE")
Cc: Bjørn Mork <bjorn@mork.no>
Reported-by: Valdis Kletnieks <Valdis.Kletnieks@vt.edu>
Cc: Valdis Kletnieks <Valdis.Kletnieks@vt.edu>
Reported-by: Jonas Lippuner <jonas@lippuner.ca>
Cc: Jonas Lippuner <jonas@lippuner.ca>
Reported-by: aszlig <aszlig@redmoonstudios.org>
Cc: aszlig <aszlig@redmoonstudios.org>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index b31aca8..a931b73 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -819,7 +819,18 @@ static void tun_net_uninit(struct net_device *dev)
 /* Net device open. */
 static int tun_net_open(struct net_device *dev)
 {
+	struct tun_struct *tun = netdev_priv(dev);
+	int i;
+
 	netif_tx_start_all_queues(dev);
+
+	for (i = 0; i < tun->numqueues; i++) {
+		struct tun_file *tfile;
+
+		tfile = rtnl_dereference(tun->tfiles[i]);
+		tfile->socket.sk->sk_write_space(tfile->socket.sk);
+	}
+
 	return 0;
 }
 
@@ -1116,9 +1127,10 @@ static unsigned int tun_chr_poll(struct file *file, poll_table *wait)
 	if (!skb_array_empty(&tfile->tx_array))
 		mask |= POLLIN | POLLRDNORM;
 
-	if (sock_writeable(sk) ||
-	    (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) &&
-	     sock_writeable(sk)))
+	if (tun->dev->flags & IFF_UP &&
+	    (sock_writeable(sk) ||
+	     (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) &&
+	      sock_writeable(sk))))
 		mask |= POLLOUT | POLLWRNORM;
 
 	if (tun->dev->reg_state != NETREG_REGISTERED)
-- 
2.1.0


From 024396bf63b5ec98872cc9617b21800724a5ed2f Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Mon, 13 Mar 2017 00:01:30 +0100
Subject: [PATCH 37/41] dccp: fix memory leak during tear-down of unsuccessful
 connection request

[ Upstream commit 72ef9c4125c7b257e3a714d62d778ab46583d6a3 ]

This patch fixes a memory leak, which happens if the connection request
is not fulfilled between parsing the DCCP options and handling the SYN
(because e.g. the backlog is full), because we forgot to free the
list of ack vectors.

Reported-by: Jianwen Ji <jiji@redhat.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ccids/ccid2.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c
index f053198..5e3a730 100644
--- a/net/dccp/ccids/ccid2.c
+++ b/net/dccp/ccids/ccid2.c
@@ -749,6 +749,7 @@ static void ccid2_hc_tx_exit(struct sock *sk)
 	for (i = 0; i < hc->tx_seqbufc; i++)
 		kfree(hc->tx_seqbuf[i]);
 	hc->tx_seqbufc = 0;
+	dccp_ackvec_parsed_cleanup(&hc->tx_av_chunks);
 }
 
 static void ccid2_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb)
-- 
2.1.0


From 92a6169e4d8e08c09a0c4a85204c099093f5869e Mon Sep 17 00:00:00 2001
From: Thomas Graf <tgraf@suug.ch>
Date: Tue, 18 Oct 2016 19:51:19 +0200
Subject: [PATCH 38/41] bpf: Detect identical PTR_TO_MAP_VALUE_OR_NULL
 registers

[ Upstream commit 57a09bf0a416700676e77102c28f9cfcb48267e0 ]

A BPF program is required to check the return register of a
map_elem_lookup() call before accessing memory. The verifier keeps
track of this by converting the type of the result register from
PTR_TO_MAP_VALUE_OR_NULL to PTR_TO_MAP_VALUE after a conditional
jump ensures safety. This check is currently exclusively performed
for the result register 0.

In the event the compiler reorders instructions, BPF_MOV64_REG
instructions may be moved before the conditional jump which causes
them to keep their type PTR_TO_MAP_VALUE_OR_NULL to which the
verifier objects when the register is accessed:

0: (b7) r1 = 10
1: (7b) *(u64 *)(r10 -8) = r1
2: (bf) r2 = r10
3: (07) r2 += -8
4: (18) r1 = 0x59c00000
6: (85) call 1
7: (bf) r4 = r0
8: (15) if r0 == 0x0 goto pc+1
 R0=map_value(ks=8,vs=8) R4=map_value_or_null(ks=8,vs=8) R10=fp
9: (7a) *(u64 *)(r4 +0) = 0
R4 invalid mem access 'map_value_or_null'

This commit extends the verifier to keep track of all identical
PTR_TO_MAP_VALUE_OR_NULL registers after a map_elem_lookup() by
assigning them an ID and then marking them all when the conditional
jump is observed.

Signed-off-by: Thomas Graf <tgraf@suug.ch>
Reviewed-by: Josef Bacik <jbacik@fb.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/bpf_verifier.h |  2 +-
 kernel/bpf/verifier.c        | 61 ++++++++++++++++++++++++++++++++------------
 2 files changed, 46 insertions(+), 17 deletions(-)

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 6aaf425..7453c12 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -24,13 +24,13 @@ struct bpf_reg_state {
 	 */
 	s64 min_value;
 	u64 max_value;
+	u32 id;
 	union {
 		/* valid when type == CONST_IMM | PTR_TO_STACK | UNKNOWN_VALUE */
 		s64 imm;
 
 		/* valid when type == PTR_TO_PACKET* */
 		struct {
-			u32 id;
 			u16 off;
 			u16 range;
 		};
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 8199821..c428c9f 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -212,9 +212,10 @@ static void print_verifier_state(struct bpf_verifier_state *state)
 		else if (t == CONST_PTR_TO_MAP || t == PTR_TO_MAP_VALUE ||
 			 t == PTR_TO_MAP_VALUE_OR_NULL ||
 			 t == PTR_TO_MAP_VALUE_ADJ)
-			verbose("(ks=%d,vs=%d)",
+			verbose("(ks=%d,vs=%d,id=%u)",
 				reg->map_ptr->key_size,
-				reg->map_ptr->value_size);
+				reg->map_ptr->value_size,
+				reg->id);
 		if (reg->min_value != BPF_REGISTER_MIN_RANGE)
 			verbose(",min_value=%lld",
 				(long long)reg->min_value);
@@ -447,6 +448,7 @@ static void mark_reg_unknown_value(struct bpf_reg_state *regs, u32 regno)
 {
 	BUG_ON(regno >= MAX_BPF_REG);
 	regs[regno].type = UNKNOWN_VALUE;
+	regs[regno].id = 0;
 	regs[regno].imm = 0;
 }
 
@@ -1252,6 +1254,7 @@ static int check_call(struct bpf_verifier_env *env, int func_id)
 			return -EINVAL;
 		}
 		regs[BPF_REG_0].map_ptr = meta.map_ptr;
+		regs[BPF_REG_0].id = ++env->id_gen;
 	} else {
 		verbose("unknown return type %d of func %d\n",
 			fn->ret_type, func_id);
@@ -1668,8 +1671,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 						insn->src_reg);
 					return -EACCES;
 				}
-				regs[insn->dst_reg].type = UNKNOWN_VALUE;
-				regs[insn->dst_reg].map_ptr = NULL;
+				mark_reg_unknown_value(regs, insn->dst_reg);
 			}
 		} else {
 			/* case: R = imm
@@ -1931,6 +1933,38 @@ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg,
 	check_reg_overflow(true_reg);
 }
 
+static void mark_map_reg(struct bpf_reg_state *regs, u32 regno, u32 id,
+			 enum bpf_reg_type type)
+{
+	struct bpf_reg_state *reg = &regs[regno];
+
+	if (reg->type == PTR_TO_MAP_VALUE_OR_NULL && reg->id == id) {
+		reg->type = type;
+		if (type == UNKNOWN_VALUE)
+			mark_reg_unknown_value(regs, regno);
+	}
+}
+
+/* The logic is similar to find_good_pkt_pointers(), both could eventually
+ * be folded together at some point.
+ */
+static void mark_map_regs(struct bpf_verifier_state *state, u32 regno,
+			  enum bpf_reg_type type)
+{
+	struct bpf_reg_state *regs = state->regs;
+	int i;
+
+	for (i = 0; i < MAX_BPF_REG; i++)
+		mark_map_reg(regs, i, regs[regno].id, type);
+
+	for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
+		if (state->stack_slot_type[i] != STACK_SPILL)
+			continue;
+		mark_map_reg(state->spilled_regs, i / BPF_REG_SIZE,
+			     regs[regno].id, type);
+	}
+}
+
 static int check_cond_jmp_op(struct bpf_verifier_env *env,
 			     struct bpf_insn *insn, int *insn_idx)
 {
@@ -2018,18 +2052,13 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 	if (BPF_SRC(insn->code) == BPF_K &&
 	    insn->imm == 0 && (opcode == BPF_JEQ || opcode == BPF_JNE) &&
 	    dst_reg->type == PTR_TO_MAP_VALUE_OR_NULL) {
-		if (opcode == BPF_JEQ) {
-			/* next fallthrough insn can access memory via
-			 * this register
-			 */
-			regs[insn->dst_reg].type = PTR_TO_MAP_VALUE;
-			/* branch targer cannot access it, since reg == 0 */
-			mark_reg_unknown_value(other_branch->regs,
-					       insn->dst_reg);
-		} else {
-			other_branch->regs[insn->dst_reg].type = PTR_TO_MAP_VALUE;
-			mark_reg_unknown_value(regs, insn->dst_reg);
-		}
+		/* Mark all identical map registers in each branch as either
+		 * safe or unknown depending R == 0 or R != 0 conditional.
+		 */
+		mark_map_regs(this_branch, insn->dst_reg,
+			      opcode == BPF_JEQ ? PTR_TO_MAP_VALUE : UNKNOWN_VALUE);
+		mark_map_regs(other_branch, insn->dst_reg,
+			      opcode == BPF_JEQ ? UNKNOWN_VALUE : PTR_TO_MAP_VALUE);
 	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT &&
 		   dst_reg->type == PTR_TO_PACKET &&
 		   regs[insn->src_reg].type == PTR_TO_PACKET_END) {
-- 
2.1.0


From 005ec60914e7013727354aa049994da0e26f3b74 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@fb.com>
Date: Wed, 7 Dec 2016 10:57:59 -0800
Subject: [PATCH 39/41] bpf: fix state equivalence

[ Upstream commit d2a4dd37f6b41fbcad76efbf63124eb3126c66fe ]

Commmits 57a09bf0a416 ("bpf: Detect identical PTR_TO_MAP_VALUE_OR_NULL registers")
and 484611357c19 ("bpf: allow access into map value arrays") by themselves
are correct, but in combination they make state equivalence ignore 'id' field
of the register state which can lead to accepting invalid program.

Fixes: 57a09bf0a416 ("bpf: Detect identical PTR_TO_MAP_VALUE_OR_NULL registers")
Fixes: 484611357c19 ("bpf: allow access into map value arrays")
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/bpf_verifier.h | 14 +++++++-------
 kernel/bpf/verifier.c        |  2 +-
 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 7453c12..a13b031 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -18,13 +18,6 @@
 
 struct bpf_reg_state {
 	enum bpf_reg_type type;
-	/*
-	 * Used to determine if any memory access using this register will
-	 * result in a bad access.
-	 */
-	s64 min_value;
-	u64 max_value;
-	u32 id;
 	union {
 		/* valid when type == CONST_IMM | PTR_TO_STACK | UNKNOWN_VALUE */
 		s64 imm;
@@ -40,6 +33,13 @@ struct bpf_reg_state {
 		 */
 		struct bpf_map *map_ptr;
 	};
+	u32 id;
+	/* Used to determine if any memory access using this register will
+	 * result in a bad access. These two fields must be last.
+	 * See states_equal()
+	 */
+	s64 min_value;
+	u64 max_value;
 };
 
 enum bpf_stack_slot_type {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c428c9f..6036d1e 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2498,7 +2498,7 @@ static bool states_equal(struct bpf_verifier_env *env,
 		 * we didn't do a variable access into a map then we are a-ok.
 		 */
 		if (!varlen_map_access &&
-		    rold->type == rcur->type && rold->imm == rcur->imm)
+		    memcmp(rold, rcur, offsetofend(struct bpf_reg_state, id)) == 0)
 			continue;
 
 		/* If we didn't map access then again we don't care about the
-- 
2.1.0


From cdc075b4cb4367e0da0e45030304b73ac0b89b0e Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 15 Dec 2016 01:30:06 +0100
Subject: [PATCH 40/41] bpf: fix regression on verifier pruning wrt map lookups

[ Upstream commit a08dd0da5307ba01295c8383923e51e7997c3576 ]

Commit 57a09bf0a416 ("bpf: Detect identical PTR_TO_MAP_VALUE_OR_NULL
registers") introduced a regression where existing programs stopped
loading due to reaching the verifier's maximum complexity limit,
whereas prior to this commit they were loading just fine; the affected
program has roughly 2k instructions.

What was found is that state pruning couldn't be performed effectively
anymore due to mismatches of the verifier's register state, in particular
in the id tracking. It doesn't mean that 57a09bf0a416 is incorrect per
se, but rather that verifier needs to perform a lot more work for the
same program with regards to involved map lookups.

Since commit 57a09bf0a416 is only about tracking registers with type
PTR_TO_MAP_VALUE_OR_NULL, the id is only needed to follow registers
until they are promoted through pattern matching with a NULL check to
either PTR_TO_MAP_VALUE or UNKNOWN_VALUE type. After that point, the
id becomes irrelevant for the transitioned types.

For UNKNOWN_VALUE, id is already reset to 0 via mark_reg_unknown_value(),
but not so for PTR_TO_MAP_VALUE where id is becoming stale. It's even
transferred further into other types that don't make use of it. Among
others, one example is where UNKNOWN_VALUE is set on function call
return with RET_INTEGER return type.

states_equal() will then fall through the memcmp() on register state;
note that the second memcmp() uses offsetofend(), so the id is part of
that since d2a4dd37f6b4 ("bpf: fix state equivalence"). But the bisect
pointed already to 57a09bf0a416, where we really reach beyond complexity
limit. What I found was that states_equal() often failed in this
case due to id mismatches in spilled regs with registers in type
PTR_TO_MAP_VALUE. Unlike non-spilled regs, spilled regs just perform
a memcmp() on their reg state and don't have any other optimizations
in place, therefore also id was relevant in this case for making a
pruning decision.

We can safely reset id to 0 as well when converting to PTR_TO_MAP_VALUE.
For the affected program, it resulted in a ~17 fold reduction of
complexity and let the program load fine again. Selftest suite also
runs fine. The only other place where env->id_gen is used currently is
through direct packet access, but for these cases id is long living, thus
a different scenario.

Also, the current logic in mark_map_regs() is not fully correct when
marking NULL branch with UNKNOWN_VALUE. We need to cache the destination
reg's id in any case. Otherwise, once we marked that reg as UNKNOWN_VALUE,
it's id is reset and any subsequent registers that hold the original id
and are of type PTR_TO_MAP_VALUE_OR_NULL won't be marked UNKNOWN_VALUE
anymore, since mark_map_reg() reuses the uncached regs[regno].id that
was just overridden. Note, we don't need to cache it outside of
mark_map_regs(), since it's called once on this_branch and the other
time on other_branch, which are both two independent verifier states.
A test case for this is added here, too.

Fixes: 57a09bf0a416 ("bpf: Detect identical PTR_TO_MAP_VALUE_OR_NULL registers")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Thomas Graf <tgraf@suug.ch>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 6036d1e..a967ae8 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1940,6 +1940,11 @@ static void mark_map_reg(struct bpf_reg_state *regs, u32 regno, u32 id,
 
 	if (reg->type == PTR_TO_MAP_VALUE_OR_NULL && reg->id == id) {
 		reg->type = type;
+		/* We don't need id from this point onwards anymore, thus we
+		 * should better reset it, so that state pruning has chances
+		 * to take effect.
+		 */
+		reg->id = 0;
 		if (type == UNKNOWN_VALUE)
 			mark_reg_unknown_value(regs, regno);
 	}
@@ -1952,16 +1957,16 @@ static void mark_map_regs(struct bpf_verifier_state *state, u32 regno,
 			  enum bpf_reg_type type)
 {
 	struct bpf_reg_state *regs = state->regs;
+	u32 id = regs[regno].id;
 	int i;
 
 	for (i = 0; i < MAX_BPF_REG; i++)
-		mark_map_reg(regs, i, regs[regno].id, type);
+		mark_map_reg(regs, i, id, type);
 
 	for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
 		if (state->stack_slot_type[i] != STACK_SPILL)
 			continue;
-		mark_map_reg(state->spilled_regs, i / BPF_REG_SIZE,
-			     regs[regno].id, type);
+		mark_map_reg(state->spilled_regs, i / BPF_REG_SIZE, id, type);
 	}
 }
 
-- 
2.1.0


From cfd8a76889e4ebed3cb6afbf26da4c66d923d538 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Sun, 18 Dec 2016 01:52:59 +0100
Subject: [PATCH 41/41] bpf: fix mark_reg_unknown_value for spilled regs on map
 value marking

[ Upstream commit 6760bf2ddde8ad64f8205a651223a93de3a35494 ]

Martin reported a verifier issue that hit the BUG_ON() for his
test case in the mark_reg_unknown_value() function:

  [  202.861380] kernel BUG at kernel/bpf/verifier.c:467!
  [...]
  [  203.291109] Call Trace:
  [  203.296501]  [<ffffffff811364d5>] mark_map_reg+0x45/0x50
  [  203.308225]  [<ffffffff81136558>] mark_map_regs+0x78/0x90
  [  203.320140]  [<ffffffff8113938d>] do_check+0x226d/0x2c90
  [  203.331865]  [<ffffffff8113a6ab>] bpf_check+0x48b/0x780
  [  203.343403]  [<ffffffff81134c8e>] bpf_prog_load+0x27e/0x440
  [  203.355705]  [<ffffffff8118a38f>] ? handle_mm_fault+0x11af/0x1230
  [  203.369158]  [<ffffffff812d8188>] ? security_capable+0x48/0x60
  [  203.382035]  [<ffffffff811351a4>] SyS_bpf+0x124/0x960
  [  203.393185]  [<ffffffff810515f6>] ? __do_page_fault+0x276/0x490
  [  203.406258]  [<ffffffff816db320>] entry_SYSCALL_64_fastpath+0x13/0x94

This issue got uncovered after the fix in a08dd0da5307 ("bpf: fix
regression on verifier pruning wrt map lookups"). The reason why it
wasn't noticed before was, because as mentioned in a08dd0da5307,
mark_map_regs() was doing the id matching incorrectly based on the
uncached regs[regno].id. So, in the first loop, we walked all regs
and as soon as we found regno == i, then this reg's id was cleared
when calling mark_reg_unknown_value() thus that every subsequent
register was probed against id of 0 (which, in combination with the
PTR_TO_MAP_VALUE_OR_NULL type is an invalid condition that no other
register state can hold), and therefore wasn't type transitioned such
as in the spilled register case for the second loop.

Now since that got fixed, it turned out that 57a09bf0a416 ("bpf:
Detect identical PTR_TO_MAP_VALUE_OR_NULL registers") used
mark_reg_unknown_value() incorrectly for the spilled regs, and thus
hitting the BUG_ON() in some cases due to regno >= MAX_BPF_REG.

Although spilled regs have the same type as the non-spilled regs
for the verifier state, that is, struct bpf_reg_state, they are
semantically different from the non-spilled regs. In other words,
there can be up to 64 (MAX_BPF_STACK / BPF_REG_SIZE) spilled regs
in the stack, for example, register R<x> could have been spilled by
the program to stack location X, Y, Z, and in mark_map_regs() we
need to scan these stack slots of type STACK_SPILL for potential
registers that we have to transition from PTR_TO_MAP_VALUE_OR_NULL.
Therefore, depending on the location, the spilled_regs regno can
be a lot higher than just MAX_BPF_REG's value since we operate on
stack instead. The reset in mark_reg_unknown_value() itself is
just fine, only that the BUG_ON() was inappropriate for this. Fix
it by making a __mark_reg_unknown_value() version that can be
called from mark_map_reg() generically; we know for the non-spilled
case that the regno is always < MAX_BPF_REG anyway.

Fixes: 57a09bf0a416 ("bpf: Detect identical PTR_TO_MAP_VALUE_OR_NULL registers")
Reported-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index a967ae8..85d1c94 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -444,14 +444,19 @@ static void init_reg_state(struct bpf_reg_state *regs)
 	regs[BPF_REG_1].type = PTR_TO_CTX;
 }
 
-static void mark_reg_unknown_value(struct bpf_reg_state *regs, u32 regno)
+static void __mark_reg_unknown_value(struct bpf_reg_state *regs, u32 regno)
 {
-	BUG_ON(regno >= MAX_BPF_REG);
 	regs[regno].type = UNKNOWN_VALUE;
 	regs[regno].id = 0;
 	regs[regno].imm = 0;
 }
 
+static void mark_reg_unknown_value(struct bpf_reg_state *regs, u32 regno)
+{
+	BUG_ON(regno >= MAX_BPF_REG);
+	__mark_reg_unknown_value(regs, regno);
+}
+
 static void reset_reg_range_values(struct bpf_reg_state *regs, u32 regno)
 {
 	regs[regno].min_value = BPF_REGISTER_MIN_RANGE;
@@ -1946,7 +1951,7 @@ static void mark_map_reg(struct bpf_reg_state *regs, u32 regno, u32 id,
 		 */
 		reg->id = 0;
 		if (type == UNKNOWN_VALUE)
-			mark_reg_unknown_value(regs, regno);
+			__mark_reg_unknown_value(regs, regno);
 	}
 }
 
-- 
2.1.0


[-- Attachment #3: net_410.mbox --]
[-- Type: Application/Octet-Stream, Size: 127979 bytes --]

From 4b2afdacad630d9f70754581f4a91480a7889557 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Wed, 22 Feb 2017 17:20:12 +0200
Subject: [PATCH 01/48] net/mlx5e: Register/unregister vport representors on
 interface attach/detach

[ Upstream commit 6f08a22c5fb2b9aefb8ecd8496758e7a677c1fde ]

Currently vport representors are added only on driver load and removed on
driver unload.  Apparently we forgot to handle them when we added the
seamless reset flow feature.  This caused to leave the representors
netdevs alive and active with open HW resources on pci shutdown and on
error reset flows.

To overcome this we move their handling to interface attach/detach, so
they would be cleaned up on shutdown and recreated on reset flows.

Fixes: 26e59d8077a3 ("net/mlx5e: Implement mlx5e interface attach/detach callbacks")
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Hadar Hen Zion <hadarh@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 23 +++++++++++++++--------
 1 file changed, 15 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index f14ca33..2b35730 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3940,6 +3940,19 @@ static void mlx5e_register_vport_rep(struct mlx5_core_dev *mdev)
 	}
 }
 
+static void mlx5e_unregister_vport_rep(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_eswitch *esw = mdev->priv.eswitch;
+	int total_vfs = MLX5_TOTAL_VPORTS(mdev);
+	int vport;
+
+	if (!MLX5_CAP_GEN(mdev, vport_group_manager))
+		return;
+
+	for (vport = 1; vport < total_vfs; vport++)
+		mlx5_eswitch_unregister_vport_rep(esw, vport);
+}
+
 void mlx5e_detach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -3986,6 +3999,7 @@ static int mlx5e_attach(struct mlx5_core_dev *mdev, void *vpriv)
 		return err;
 	}
 
+	mlx5e_register_vport_rep(mdev);
 	return 0;
 }
 
@@ -3997,6 +4011,7 @@ static void mlx5e_detach(struct mlx5_core_dev *mdev, void *vpriv)
 	if (!netif_device_present(netdev))
 		return;
 
+	mlx5e_unregister_vport_rep(mdev);
 	mlx5e_detach_netdev(mdev, netdev);
 	mlx5e_destroy_mdev_resources(mdev);
 }
@@ -4015,8 +4030,6 @@ static void *mlx5e_add(struct mlx5_core_dev *mdev)
 	if (err)
 		return NULL;
 
-	mlx5e_register_vport_rep(mdev);
-
 	if (MLX5_CAP_GEN(mdev, vport_group_manager))
 		ppriv = &esw->offloads.vport_reps[0];
 
@@ -4068,13 +4081,7 @@ void mlx5e_destroy_netdev(struct mlx5_core_dev *mdev, struct mlx5e_priv *priv)
 
 static void mlx5e_remove(struct mlx5_core_dev *mdev, void *vpriv)
 {
-	struct mlx5_eswitch *esw = mdev->priv.eswitch;
-	int total_vfs = MLX5_TOTAL_VPORTS(mdev);
 	struct mlx5e_priv *priv = vpriv;
-	int vport;
-
-	for (vport = 1; vport < total_vfs; vport++)
-		mlx5_eswitch_unregister_vport_rep(esw, vport);
 
 	unregister_netdev(priv->netdev);
 	mlx5e_detach(mdev, vpriv);
-- 
2.1.0


From c01393bb1c6e606cc3ed8bc84100c1cb5989bf2d Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Wed, 22 Feb 2017 17:20:13 +0200
Subject: [PATCH 02/48] net/mlx5e: Do not reduce LRO WQE size when not using
 build_skb

[ Upstream commit 4078e637c12f1e0a74293f1ec9563f42bff14a03 ]

When rq_type is Striding RQ, no room of SKB_RESERVE is needed
as SKB allocation is not done via build_skb.

Fixes: e4b85508072b ("net/mlx5e: Slightly reduce hardware LRO size")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 2b35730..7a2b87c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -81,6 +81,7 @@ static bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
 static void mlx5e_set_rq_type_params(struct mlx5e_priv *priv, u8 rq_type)
 {
 	priv->params.rq_wq_type = rq_type;
+	priv->params.lro_wqe_sz = MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ;
 	switch (priv->params.rq_wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
 		priv->params.log_rq_size = MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE_MPW;
@@ -93,6 +94,10 @@ static void mlx5e_set_rq_type_params(struct mlx5e_priv *priv, u8 rq_type)
 		break;
 	default: /* MLX5_WQ_TYPE_LINKED_LIST */
 		priv->params.log_rq_size = MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE;
+
+		/* Extra room needed for build_skb */
+		priv->params.lro_wqe_sz -= MLX5_RX_HEADROOM +
+			SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 	}
 	priv->params.min_rx_wqes = mlx5_min_rx_wqes(priv->params.rq_wq_type,
 					       BIT(priv->params.log_rq_size));
@@ -3517,12 +3522,6 @@ static void mlx5e_build_nic_netdev_priv(struct mlx5_core_dev *mdev,
 	mlx5e_build_default_indir_rqt(mdev, priv->params.indirection_rqt,
 				      MLX5E_INDIR_RQT_SIZE, profile->max_nch(mdev));
 
-	priv->params.lro_wqe_sz =
-		MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ -
-		/* Extra room needed for build_skb */
-		MLX5_RX_HEADROOM -
-		SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-
 	/* Initialize pflags */
 	MLX5E_SET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_BASED_MODER,
 			priv->params.rx_cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE);
-- 
2.1.0


From 65dfc4b01ec29bf44a03a12ee8a7532b65a567eb Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Wed, 22 Feb 2017 17:20:14 +0200
Subject: [PATCH 03/48] net/mlx5e: Fix broken CQE compression initialization

[ Upstream commit b0d4660b4cc52e6477ca3a43435351d565dfcedc ]

Some of RQ type parameters are derived from CQE compression state flag,
CQE compression flag was initialized only after RQ type parameters
setup. This leads to load RQ with stride size smaller than what we
want for when CQE compression is on.

This bug introduces no functional damage, it only makes CQE compression
occur less often, since in ConnectX4-LX CQE compression is performed
only on packets smaller than stride size.

Fix this by marking default status of CQE compression in PFLAG prior to
calling mlx5e_set_rq_priv_params(), as it inits some fields based on it.

Tested:
 load driver on systems where rx CQE compress will be on (MH)
 pktgen with  64 < pkt size < 256 and netperf TCP_STREAM (IPv4/IPv6)
 verify `ethtool -S ethxx | grep compress` are advancing more often
 (rapidly)

Fixes: 2fc4bfb7250d ("net/mlx5e: Dynamic RQ type infrastructure")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Cc: kernel-team@fb.com
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 7a2b87c..a2401ed 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3500,6 +3500,9 @@ static void mlx5e_build_nic_netdev_priv(struct mlx5_core_dev *mdev,
 			cqe_compress_heuristic(link_speed, pci_bw);
 	}
 
+	MLX5E_SET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS,
+			priv->params.rx_cqe_compress_def);
+
 	mlx5e_set_rq_priv_params(priv);
 	if (priv->params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
 		priv->params.lro_en = true;
@@ -3525,7 +3528,6 @@ static void mlx5e_build_nic_netdev_priv(struct mlx5_core_dev *mdev,
 	/* Initialize pflags */
 	MLX5E_SET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_BASED_MODER,
 			priv->params.rx_cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE);
-	MLX5E_SET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS, priv->params.rx_cqe_compress_def);
 
 	mutex_init(&priv->state_lock);
 
-- 
2.1.0


From cf6330e58d47bf1ed41c8e00142532bc3c684d8d Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Wed, 22 Feb 2017 17:20:15 +0200
Subject: [PATCH 04/48] net/mlx5e: Update MPWQE stride size when modifying CQE
 compress state

[ Upstream commit 6dc4b54e77282caf17f0ff72aa32dd296037fbc0 ]

When the admin enables/disables cqe compression, updating
mpwqe stride size is required:
    CQE compress ON  ==> stride size = 256B
    CQE compress OFF ==> stride size = 64B

This is already done on driver load via mlx5e_set_rq_type_params, all we
need is just to call it on arbitrary admin changes of cqe compression
state via priv flags or when changing timestamping state
(as it is mutually exclusive with cqe compression).

This bug introduces no functional damage, it only makes cqe compression
occur less often, since in ConnectX4-LX CQE compression is performed
only on packets smaller than stride size.

Tested:
 ethtool --set-priv-flags ethxx rx_cqe_compress on
 pktgen with  64 < pkt size < 256 and netperf TCP_STREAM (IPv4/IPv6)
 verify `ethtool -S ethxx | grep compress` are advancing more often
 (rapidly)

Fixes: 7219ab34f184 ("net/mlx5e: CQE compression")
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Cc: kernel-team@fb.com
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h         | 1 +
 drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 1 +
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c    | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c      | 1 +
 4 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index d5ecb8f..c69a1f8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -803,6 +803,7 @@ int mlx5e_get_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
 
 void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params,
 				 u8 cq_period_mode);
+void mlx5e_set_rq_type_params(struct mlx5e_priv *priv, u8 rq_type);
 
 static inline void mlx5e_tx_notify_hw(struct mlx5e_sq *sq,
 				      struct mlx5_wqe_ctrl_seg *ctrl, int bf_sz)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index bb67863..6906dea 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1477,6 +1477,7 @@ static int set_pflag_rx_cqe_compress(struct net_device *netdev,
 
 	MLX5E_SET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS, enable);
 	priv->params.rx_cqe_compress_def = enable;
+	mlx5e_set_rq_type_params(priv, priv->params.rq_wq_type);
 
 	if (reset)
 		err = mlx5e_open_locked(netdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index a2401ed..9d9c649 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -78,7 +78,7 @@ static bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
 		MLX5_CAP_ETH(mdev, reg_umr_sq);
 }
 
-static void mlx5e_set_rq_type_params(struct mlx5e_priv *priv, u8 rq_type)
+void mlx5e_set_rq_type_params(struct mlx5e_priv *priv, u8 rq_type)
 {
 	priv->params.rq_wq_type = rq_type;
 	priv->params.lro_wqe_sz = MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 06d5e6f..817fa7c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -172,6 +172,7 @@ void mlx5e_modify_rx_cqe_compression(struct mlx5e_priv *priv, bool val)
 		mlx5e_close_locked(priv->netdev);
 
 	MLX5E_SET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS, val);
+	mlx5e_set_rq_type_params(priv, priv->params.rq_wq_type);
 
 	if (was_opened)
 		mlx5e_open_locked(priv->netdev);
-- 
2.1.0


From e3ac69282eee6b4f8b5a1b7f8b6407270a6f5c14 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Wed, 22 Feb 2017 17:20:16 +0200
Subject: [PATCH 05/48] net/mlx5e: Fix wrong CQE decompression

[ Upstream commit 36154be40a28e4afaa0416da2681d80b7e2ca319 ]

In cqe compression with striding RQ, the decompression of the CQE field
wqe_counter was done with a wrong wraparound value.
This caused handling cqes with a wrong pointer to wqe (rx descriptor)
and creating SKBs with wrong data, pointing to wrong (and already consumed)
strides/pages.

The meaning of the CQE field wqe_counter in striding RQ holds the
stride index instead of the WQE index. Hence, when decompressing
a CQE, wqe_counter should have wrapped-around the number of strides
in a single multi-packet WQE.

We dropped this wrap-around mask at all in CQE decompression of striding
RQ. It is not needed as in such cases the CQE compression session would
break because of different value of wqe_id field, starting a new
compression session.

Tested:
 ethtool -K ethxx lro off/on
 ethtool --set-priv-flags ethxx rx_cqe_compress on
 super_netperf 16 {ipv4,ipv6} -t TCP_STREAM -m 50 -D
 verified no csum errors and no page refcount issues.

Fixes: 7219ab34f184 ("net/mlx5e: CQE compression")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reported-by: Tom Herbert <tom@herbertland.com>
Cc: kernel-team@fb.com
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 817fa7c..e3b88bb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -92,19 +92,18 @@ static inline void mlx5e_cqes_update_owner(struct mlx5e_cq *cq, u32 cqcc, int n)
 static inline void mlx5e_decompress_cqe(struct mlx5e_rq *rq,
 					struct mlx5e_cq *cq, u32 cqcc)
 {
-	u16 wqe_cnt_step;
-
 	cq->title.byte_cnt     = cq->mini_arr[cq->mini_arr_idx].byte_cnt;
 	cq->title.check_sum    = cq->mini_arr[cq->mini_arr_idx].checksum;
 	cq->title.op_own      &= 0xf0;
 	cq->title.op_own      |= 0x01 & (cqcc >> cq->wq.log_sz);
 	cq->title.wqe_counter  = cpu_to_be16(cq->decmprs_wqe_counter);
 
-	wqe_cnt_step =
-		rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ ?
-		mpwrq_get_cqe_consumed_strides(&cq->title) : 1;
-	cq->decmprs_wqe_counter =
-		(cq->decmprs_wqe_counter + wqe_cnt_step) & rq->wq.sz_m1;
+	if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
+		cq->decmprs_wqe_counter +=
+			mpwrq_get_cqe_consumed_strides(&cq->title);
+	else
+		cq->decmprs_wqe_counter =
+			(cq->decmprs_wqe_counter + 1) & rq->wq.sz_m1;
 }
 
 static inline void mlx5e_decompress_cqe_no_hash(struct mlx5e_rq *rq,
-- 
2.1.0


From 03b4c481143696b1a500dcec409cd4e27fce3420 Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Thu, 23 Feb 2017 09:31:18 -0300
Subject: [PATCH 06/48] sctp: deny peeloff operation on asocs with threads
 sleeping on it

[ Upstream commit dfcb9f4f99f1e9a49e43398a7bfbf56927544af1 ]

commit 2dcab5984841 ("sctp: avoid BUG_ON on sctp_wait_for_sndbuf")
attempted to avoid a BUG_ON call when the association being used for a
sendmsg() is blocked waiting for more sndbuf and another thread did a
peeloff operation on such asoc, moving it to another socket.

As Ben Hutchings noticed, then in such case it would return without
locking back the socket and would cause two unlocks in a row.

Further analysis also revealed that it could allow a double free if the
application managed to peeloff the asoc that is created during the
sendmsg call, because then sctp_sendmsg() would try to free the asoc
that was created only for that call.

This patch takes another approach. It will deny the peeloff operation
if there is a thread sleeping on the asoc, so this situation doesn't
exist anymore. This avoids the issues described above and also honors
the syscalls that are already being handled (it can be multiple sendmsg
calls).

Joint work with Xin Long.

Fixes: 2dcab5984841 ("sctp: avoid BUG_ON on sctp_wait_for_sndbuf")
Cc: Alexander Popov <alex.popov@linux.com>
Cc: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 1b5d669..d04a8b6 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4734,6 +4734,12 @@ int sctp_do_peeloff(struct sock *sk, sctp_assoc_t id, struct socket **sockp)
 	if (!asoc)
 		return -EINVAL;
 
+	/* If there is a thread waiting on more sndbuf space for
+	 * sending on this asoc, it cannot be peeled.
+	 */
+	if (waitqueue_active(&asoc->wait))
+		return -EBUSY;
+
 	/* An association cannot be branched off from an already peeled-off
 	 * socket, nor is this supported for tcp style sockets.
 	 */
@@ -7426,8 +7432,6 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p,
 		 */
 		release_sock(sk);
 		current_timeo = schedule_timeout(current_timeo);
-		if (sk != asoc->base.sk)
-			goto do_error;
 		lock_sock(sk);
 
 		*timeo_p = current_timeo;
-- 
2.1.0


From 9001258daf51e474eba7613c90b291b20705cc52 Mon Sep 17 00:00:00 2001
From: Matthias Schiffer <mschiffer@universe-factory.net>
Date: Thu, 23 Feb 2017 17:19:41 +0100
Subject: [PATCH 07/48] vxlan: correctly validate VXLAN ID against VXLAN_N_VID

[ Upstream commit 4e37d6911f36545b286d15073f6f2222f840e81c ]

The incorrect check caused an off-by-one error: the maximum VID 0xffffff
was unusable.

Fixes: d342894c5d2f ("vxlan: virtual extensible lan")
Signed-off-by: Matthias Schiffer <mschiffer@universe-factory.net>
Acked-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 30b04cf..d646775 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2626,7 +2626,7 @@ static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[])
 
 	if (data[IFLA_VXLAN_ID]) {
 		__u32 id = nla_get_u32(data[IFLA_VXLAN_ID]);
-		if (id >= VXLAN_VID_MASK)
+		if (id >= VXLAN_N_VID)
 			return -ERANGE;
 	}
 
-- 
2.1.0


From ee0a0a022ea1898262aee722e9b916c7f8b2adc7 Mon Sep 17 00:00:00 2001
From: David Forster <dforster@brocade.com>
Date: Fri, 24 Feb 2017 14:20:32 +0000
Subject: [PATCH 08/48] vti6: return GRE_KEY for vti6

[ Upstream commit 7dcdf941cdc96692ab99fd790c8cc68945514851 ]

Align vti6 with vti by returning GRE_KEY flag. This enables iproute2
to display tunnel keys on "ip -6 tunnel show"

Signed-off-by: David Forster <dforster@brocade.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_vti.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index d82042c..733c63e 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -692,6 +692,10 @@ vti6_parm_to_user(struct ip6_tnl_parm2 *u, const struct __ip6_tnl_parm *p)
 	u->link = p->link;
 	u->i_key = p->i_key;
 	u->o_key = p->o_key;
+	if (u->i_key)
+		u->i_flags |= GRE_KEY;
+	if (u->o_key)
+		u->o_flags |= GRE_KEY;
 	u->proto = p->proto;
 
 	memcpy(u->name, p->name, sizeof(u->name));
-- 
2.1.0


From a4b60c8944a8ffb188fe14d123e002389e0c8b9f Mon Sep 17 00:00:00 2001
From: Brian Russell <brussell@brocade.com>
Date: Fri, 24 Feb 2017 17:47:11 +0000
Subject: [PATCH 09/48] vxlan: don't allow overwrite of config src addr

[ Upstream commit 1158632b5a2dcce0786c1b1b99654e81cc867981 ]

When using IPv6 transport and a default dst, a pointer to the configured
source address is passed into the route lookup. If no source address is
configured, then the value is overwritten.

IPv6 route lookup ignores egress ifindex match if the source address is set,
so if egress ifindex match is desired, the source address must be passed
as any. The overwrite breaks this for subsequent lookups.

Avoid this by copying the configured address to an existing stack variable
and pass a pointer to that instead.

Fixes: 272d96a5ab10 ("net: vxlan: lwt: Use source ip address during route lookup.")

Signed-off-by: Brian Russell <brussell@brocade.com>
Acked-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index d646775..c03cab5a 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1992,7 +1992,6 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 	const struct iphdr *old_iph = ip_hdr(skb);
 	union vxlan_addr *dst;
 	union vxlan_addr remote_ip, local_ip;
-	union vxlan_addr *src;
 	struct vxlan_metadata _md;
 	struct vxlan_metadata *md = &_md;
 	__be16 src_port = 0, dst_port;
@@ -2019,7 +2018,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 
 		dst_port = rdst->remote_port ? rdst->remote_port : vxlan->cfg.dst_port;
 		vni = rdst->remote_vni;
-		src = &vxlan->cfg.saddr;
+		local_ip = vxlan->cfg.saddr;
 		dst_cache = &rdst->dst_cache;
 		md->gbp = skb->mark;
 		ttl = vxlan->cfg.ttl;
@@ -2052,7 +2051,6 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		dst = &remote_ip;
 		dst_port = info->key.tp_dst ? : vxlan->cfg.dst_port;
 		vni = tunnel_id_to_key32(info->key.tun_id);
-		src = &local_ip;
 		dst_cache = &info->dst_cache;
 		if (info->options_len)
 			md = ip_tunnel_info_opts(info);
@@ -2072,7 +2070,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		rt = vxlan_get_route(vxlan, dev, sock4, skb,
 				     rdst ? rdst->remote_ifindex : 0, tos,
 				     dst->sin.sin_addr.s_addr,
-				     &src->sin.sin_addr.s_addr,
+				     &local_ip.sin.sin_addr.s_addr,
 				     dst_port, src_port,
 				     dst_cache, info);
 		if (IS_ERR(rt)) {
@@ -2099,7 +2097,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		if (err < 0)
 			goto tx_error;
 
-		udp_tunnel_xmit_skb(rt, sock4->sock->sk, skb, src->sin.sin_addr.s_addr,
+		udp_tunnel_xmit_skb(rt, sock4->sock->sk, skb, local_ip.sin.sin_addr.s_addr,
 				    dst->sin.sin_addr.s_addr, tos, ttl, df,
 				    src_port, dst_port, xnet, !udp_sum);
 #if IS_ENABLED(CONFIG_IPV6)
@@ -2109,7 +2107,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		ndst = vxlan6_get_route(vxlan, dev, sock6, skb,
 					rdst ? rdst->remote_ifindex : 0, tos,
 					label, &dst->sin6.sin6_addr,
-					&src->sin6.sin6_addr,
+					&local_ip.sin6.sin6_addr,
 					dst_port, src_port,
 					dst_cache, info);
 		if (IS_ERR(ndst)) {
@@ -2137,7 +2135,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 			goto tx_error;
 
 		udp_tunnel6_xmit_skb(ndst, sock6->sock->sk, skb, dev,
-				     &src->sin6.sin6_addr,
+				     &local_ip.sin6.sin6_addr,
 				     &dst->sin6.sin6_addr, tos, ttl,
 				     label, src_port, dst_port, !udp_sum);
 #endif
-- 
2.1.0


From b622fea4079579b6f69cd1848947083da9cd4ca7 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Sun, 26 Feb 2017 15:50:52 +0200
Subject: [PATCH 10/48] ipv4: add missing initialization for flowi4_uid

[ Upstream commit 8bcfd0925ef15f072ba1e7bee2c25e9e1b5fd6ca ]

Avoid matching of random stack value for uid when rules
are looked up on input route or when RP filter is used.
Problem should affect only setups that use ip rules with
uid range.

Fixes: 622ec2c9d524 ("net: core: add UID to flows, rules, and routes")
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_frontend.c | 6 +++---
 net/ipv4/route.c        | 1 +
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 7db2ad2..b39a791 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -319,7 +319,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 	int ret, no_addr;
 	struct fib_result res;
 	struct flowi4 fl4;
-	struct net *net;
+	struct net *net = dev_net(dev);
 	bool dev_match;
 
 	fl4.flowi4_oif = 0;
@@ -332,6 +332,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 	fl4.flowi4_scope = RT_SCOPE_UNIVERSE;
 	fl4.flowi4_tun_key.tun_id = 0;
 	fl4.flowi4_flags = 0;
+	fl4.flowi4_uid = sock_net_uid(net, NULL);
 
 	no_addr = idev->ifa_list == NULL;
 
@@ -339,13 +340,12 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 
 	trace_fib_validate_source(dev, &fl4);
 
-	net = dev_net(dev);
 	if (fib_lookup(net, &fl4, &res, 0))
 		goto last_resort;
 	if (res.type != RTN_UNICAST &&
 	    (res.type != RTN_LOCAL || !IN_DEV_ACCEPT_LOCAL(idev)))
 		goto e_inval;
-	if (!rpf && !fib_num_tclassid_users(dev_net(dev)) &&
+	if (!rpf && !fib_num_tclassid_users(net) &&
 	    (dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev)))
 		goto last_resort;
 	fib_combine_itag(itag, &res);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 709ffe6..25fc88c 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1858,6 +1858,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	fl4.flowi4_flags = 0;
 	fl4.daddr = daddr;
 	fl4.saddr = saddr;
+	fl4.flowi4_uid = sock_net_uid(net, NULL);
 	err = fib_lookup(net, &fl4, &res, 0);
 	if (err != 0) {
 		if (!IN_DEV_FORWARD(in_dev))
-- 
2.1.0


From afda9243cafb6ee404de9e5072bcbae1f930692d Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Sun, 26 Feb 2017 17:14:35 +0200
Subject: [PATCH 11/48] ipv4: mask tos for input route

[ Upstream commit 6e28099d38c0e50d62c1afc054e37e573adf3d21 ]

Restore the lost masking of TOS in input route code to
allow ip rules to match it properly.

Problem [1] noticed by Shmulik Ladkani <shmulik.ladkani@gmail.com>

[1] http://marc.info/?t=137331755300040&r=1&w=2

Fixes: 89aef8921bfb ("ipv4: Delete routing cache.")
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 25fc88c..8976887 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1991,6 +1991,7 @@ int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 {
 	int res;
 
+	tos &= IPTOS_RT_MASK;
 	rcu_read_lock();
 
 	/* Multicast recognition logic is moved from route cache to here.
-- 
2.1.0


From 5caf9571e5e2af98570854705925bae5e7da4db2 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Fri, 24 Feb 2017 15:18:46 +0800
Subject: [PATCH 12/48] sctp: set sin_port for addr param when checking
 duplicate address

[ Upstream commit 2e3ce5bc2aa938653c3866aa7f4901a1f199b1c8 ]

Commit b8607805dd15 ("sctp: not copying duplicate addrs to the assoc's
bind address list") tried to check for duplicate address before copying
to asoc's bind_addr list from global addr list.

But all the addrs' sin_ports in global addr list are 0 while the addrs'
sin_ports are bp->port in asoc's bind_addr list. It means even if it's
a duplicate address, af->cmp_addr will still return 0 as the their
sin_ports are different.

This patch is to fix it by setting the sin_port for addr param with
bp->port before comparing the addrs.

Fixes: b8607805dd15 ("sctp: not copying duplicate addrs to the assoc's bind address list")
Reported-by: Wei Chen <weichen@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/protocol.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 616a942..4ee4a33 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -199,6 +199,7 @@ int sctp_copy_local_addr_list(struct net *net, struct sctp_bind_addr *bp,
 			      sctp_scope_t scope, gfp_t gfp, int copy_flags)
 {
 	struct sctp_sockaddr_entry *addr;
+	union sctp_addr laddr;
 	int error = 0;
 
 	rcu_read_lock();
@@ -220,7 +221,10 @@ int sctp_copy_local_addr_list(struct net *net, struct sctp_bind_addr *bp,
 		     !(copy_flags & SCTP_ADDR6_PEERSUPP)))
 			continue;
 
-		if (sctp_bind_addr_state(bp, &addr->a) != -1)
+		laddr = addr->a;
+		/* also works for setting ipv6 address port */
+		laddr.v4.sin_port = htons(bp->port);
+		if (sctp_bind_addr_state(bp, &laddr) != -1)
 			continue;
 
 		error = sctp_add_bind_addr(bp, &addr->a, sizeof(addr->a),
-- 
2.1.0


From 365893d674a918f88c55309ea686859a2927baca Mon Sep 17 00:00:00 2001
From: Roman Mashak <mrv@mojatatu.com>
Date: Fri, 24 Feb 2017 11:00:32 -0500
Subject: [PATCH 13/48] net sched actions: decrement module reference count
 after table flush.

[ Upstream commit edb9d1bff4bbe19b8ae0e71b1f38732591a9eeb2 ]

When tc actions are loaded as a module and no actions have been installed,
flushing them would result in actions removed from the memory, but modules
reference count not being decremented, so that the modules would not be
unloaded.

Following is example with GACT action:

% sudo modprobe act_gact
% lsmod
Module                  Size  Used by
act_gact               16384  0
%
% sudo tc actions ls action gact
%
% sudo tc actions flush action gact
% lsmod
Module                  Size  Used by
act_gact               16384  1
% sudo tc actions flush action gact
% lsmod
Module                  Size  Used by
act_gact               16384  2
% sudo rmmod act_gact
rmmod: ERROR: Module act_gact is in use
....

After the fix:
% lsmod
Module                  Size  Used by
act_gact               16384  0
%
% sudo tc actions add action pass index 1
% sudo tc actions add action pass index 2
% sudo tc actions add action pass index 3
% lsmod
Module                  Size  Used by
act_gact               16384  3
%
% sudo tc actions flush action gact
% lsmod
Module                  Size  Used by
act_gact               16384  0
%
% sudo tc actions flush action gact
% lsmod
Module                  Size  Used by
act_gact               16384  0
% sudo rmmod act_gact
% lsmod
Module                  Size  Used by
%

Fixes: f97017cdefef ("net-sched: Fix actions flushing")
Signed-off-by: Roman Mashak <mrv@mojatatu.com>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_api.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index e10456ef6f..9b29b61 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -817,10 +817,8 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
 		goto out_module_put;
 
 	err = ops->walk(net, skb, &dcb, RTM_DELACTION, ops);
-	if (err < 0)
+	if (err <= 0)
 		goto out_module_put;
-	if (err == 0)
-		goto noflush_out;
 
 	nla_nest_end(skb, nest);
 
@@ -837,7 +835,6 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
 out_module_put:
 	module_put(ops->owner);
 err_out:
-noflush_out:
 	kfree_skb(skb);
 	return err;
 }
-- 
2.1.0


From 6b9f345bb68934db81f6e7a2e91955bb7ea885c8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Paul=20H=C3=BCber?= <phueber@kernsp.in>
Date: Sun, 26 Feb 2017 17:58:19 +0100
Subject: [PATCH 14/48] l2tp: avoid use-after-free caused by
 l2tp_ip_backlog_recv
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 51fb60eb162ab84c5edf2ae9c63cf0b878e5547e ]

l2tp_ip_backlog_recv may not return -1 if the packet gets dropped.
The return value is passed up to ip_local_deliver_finish, which treats
negative values as an IP protocol number for resubmission.

Signed-off-by: Paul Hüber <phueber@kernsp.in>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ip.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 28c2154..3ed3015 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -381,7 +381,7 @@ static int l2tp_ip_backlog_recv(struct sock *sk, struct sk_buff *skb)
 drop:
 	IP_INC_STATS(sock_net(sk), IPSTATS_MIB_INDISCARDS);
 	kfree_skb(skb);
-	return -1;
+	return 0;
 }
 
 /* Userspace will call sendmsg() on the tunnel socket to send L2TP
-- 
2.1.0


From 9c8e0a0c283181ff12ae3546918fc35447e29da2 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 24 Feb 2017 11:43:36 -0800
Subject: [PATCH 15/48] vxlan: lock RCU on TX path

[ Upstream commit 56de859e9967c070464a9a9f4f18d73f9447298e ]

There is no guarantees that callers of the TX path will hold
the RCU lock.  Grab it explicitly.

Fixes: c6fcc4fc5f8b ("vxlan: avoid using stale vxlan socket.")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index c03cab5a..0e204f1 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2062,6 +2062,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 	src_port = udp_flow_src_port(dev_net(dev), skb, vxlan->cfg.port_min,
 				     vxlan->cfg.port_max, true);
 
+	rcu_read_lock();
 	if (dst->sa.sa_family == AF_INET) {
 		struct vxlan_sock *sock4 = rcu_dereference(vxlan->vn4_sock);
 		struct rtable *rt;
@@ -2084,7 +2085,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 						    dst_port, vni, &rt->dst,
 						    rt->rt_flags);
 			if (err)
-				return;
+				goto out_unlock;
 		} else if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT) {
 			df = htons(IP_DF);
 		}
@@ -2123,7 +2124,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 						    dst_port, vni, ndst,
 						    rt6i_flags);
 			if (err)
-				return;
+				goto out_unlock;
 		}
 
 		tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
@@ -2140,6 +2141,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 				     label, src_port, dst_port, !udp_sum);
 #endif
 	}
+out_unlock:
+	rcu_read_unlock();
 	return;
 
 drop:
@@ -2148,6 +2151,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 	return;
 
 tx_error:
+	rcu_read_unlock();
 	if (err == -ELOOP)
 		dev->stats.collisions++;
 	else if (err == -ENETUNREACH)
-- 
2.1.0


From 8dcba596c1f24b2b2427dd95203aa9a10b8e6917 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 24 Feb 2017 11:43:37 -0800
Subject: [PATCH 16/48] geneve: lock RCU on TX path

[ Upstream commit a717e3f740803cc88bd5c9a70c93504f6a368663 ]

There is no guarantees that callers of the TX path will hold
the RCU lock.  Grab it explicitly.

Fixes: fceb9c3e3825 ("geneve: avoid using stale geneve socket.")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 45301cb..7074b40 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -881,12 +881,14 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
 		info = &geneve->info;
 	}
 
+	rcu_read_lock();
 #if IS_ENABLED(CONFIG_IPV6)
 	if (info->mode & IP_TUNNEL_INFO_IPV6)
 		err = geneve6_xmit_skb(skb, dev, geneve, info);
 	else
 #endif
 		err = geneve_xmit_skb(skb, dev, geneve, info);
+	rcu_read_unlock();
 
 	if (likely(!err))
 		return NETDEV_TX_OK;
-- 
2.1.0


From 496a8c4603840813d53b0d79f59ad42ffcfe28dd Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Tue, 28 Feb 2017 08:55:40 +0100
Subject: [PATCH 17/48] mlxsw: spectrum_router: Avoid potential packets loss

[ Upstream commit f7df4923fa986247e93ec2cdff5ca168fff14dcf ]

When the structure of the LPM tree changes (f.e., due to the addition of
a new prefix), we unbind the old tree and then bind the new one. This
may result in temporary packet loss.

Instead, overwrite the old binding with the new one.

Fixes: 6b75c4807db3 ("mlxsw: spectrum_router: Add virtual router management")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_router.c  | 30 ++++++++++++++--------
 1 file changed, 20 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 9e494a4..f17f906 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -496,30 +496,40 @@ static int
 mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr,
 			   struct mlxsw_sp_prefix_usage *req_prefix_usage)
 {
-	struct mlxsw_sp_lpm_tree *lpm_tree;
+	struct mlxsw_sp_lpm_tree *lpm_tree = vr->lpm_tree;
+	struct mlxsw_sp_lpm_tree *new_tree;
+	int err;
 
-	if (mlxsw_sp_prefix_usage_eq(req_prefix_usage,
-				     &vr->lpm_tree->prefix_usage))
+	if (mlxsw_sp_prefix_usage_eq(req_prefix_usage, &lpm_tree->prefix_usage))
 		return 0;
 
-	lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, req_prefix_usage,
+	new_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, req_prefix_usage,
 					 vr->proto, false);
-	if (IS_ERR(lpm_tree)) {
+	if (IS_ERR(new_tree)) {
 		/* We failed to get a tree according to the required
 		 * prefix usage. However, the current tree might be still good
 		 * for us if our requirement is subset of the prefixes used
 		 * in the tree.
 		 */
 		if (mlxsw_sp_prefix_usage_subset(req_prefix_usage,
-						 &vr->lpm_tree->prefix_usage))
+						 &lpm_tree->prefix_usage))
 			return 0;
-		return PTR_ERR(lpm_tree);
+		return PTR_ERR(new_tree);
 	}
 
-	mlxsw_sp_vr_lpm_tree_unbind(mlxsw_sp, vr);
-	mlxsw_sp_lpm_tree_put(mlxsw_sp, vr->lpm_tree);
+	/* Prevent packet loss by overwriting existing binding */
+	vr->lpm_tree = new_tree;
+	err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, vr);
+	if (err)
+		goto err_tree_bind;
+	mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree);
+
+	return 0;
+
+err_tree_bind:
 	vr->lpm_tree = lpm_tree;
-	return mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, vr);
+	mlxsw_sp_lpm_tree_put(mlxsw_sp, new_tree);
+	return err;
 }
 
 static struct mlxsw_sp_vr *mlxsw_sp_vr_get(struct mlxsw_sp *mlxsw_sp,
-- 
2.1.0


From d1f1188b6bb13b371948db8de74b1860c0c63aea Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 1 Mar 2017 08:39:49 -0800
Subject: [PATCH 18/48] tcp/dccp: block BH for SYN processing

[ Upstream commit 449809a66c1d0b1563dee84493e14bf3104d2d7e ]

SYN processing really was meant to be handled from BH.

When I got rid of BH blocking while processing socket backlog
in commit 5413d1babe8f ("net: do not block BH while processing socket
backlog"), I forgot that a malicious user could transition to TCP_LISTEN
from a state that allowed (SYN) packets to be parked in the socket
backlog while socket is owned by the thread doing the listen() call.

Sure enough syzkaller found this and reported the bug ;)

=================================
[ INFO: inconsistent lock state ]
4.10.0+ #60 Not tainted
---------------------------------
inconsistent {IN-SOFTIRQ-W} -> {SOFTIRQ-ON-W} usage.
syz-executor0/5090 [HC0[0]:SC0[0]:HE1:SE1] takes:
 (&(&hashinfo->ehash_locks[i])->rlock){+.?...}, at:
[<ffffffff83a6a370>] spin_lock include/linux/spinlock.h:299 [inline]
 (&(&hashinfo->ehash_locks[i])->rlock){+.?...}, at:
[<ffffffff83a6a370>] inet_ehash_insert+0x240/0xad0
net/ipv4/inet_hashtables.c:407
{IN-SOFTIRQ-W} state was registered at:
  mark_irqflags kernel/locking/lockdep.c:2923 [inline]
  __lock_acquire+0xbcf/0x3270 kernel/locking/lockdep.c:3295
  lock_acquire+0x241/0x580 kernel/locking/lockdep.c:3753
  __raw_spin_lock include/linux/spinlock_api_smp.h:142 [inline]
  _raw_spin_lock+0x33/0x50 kernel/locking/spinlock.c:151
  spin_lock include/linux/spinlock.h:299 [inline]
  inet_ehash_insert+0x240/0xad0 net/ipv4/inet_hashtables.c:407
  reqsk_queue_hash_req net/ipv4/inet_connection_sock.c:753 [inline]
  inet_csk_reqsk_queue_hash_add+0x1b7/0x2a0 net/ipv4/inet_connection_sock.c:764
  tcp_conn_request+0x25cc/0x3310 net/ipv4/tcp_input.c:6399
  tcp_v4_conn_request+0x157/0x220 net/ipv4/tcp_ipv4.c:1262
  tcp_rcv_state_process+0x802/0x4130 net/ipv4/tcp_input.c:5889
  tcp_v4_do_rcv+0x56b/0x940 net/ipv4/tcp_ipv4.c:1433
  tcp_v4_rcv+0x2e12/0x3210 net/ipv4/tcp_ipv4.c:1711
  ip_local_deliver_finish+0x4ce/0xc40 net/ipv4/ip_input.c:216
  NF_HOOK include/linux/netfilter.h:257 [inline]
  ip_local_deliver+0x1ce/0x710 net/ipv4/ip_input.c:257
  dst_input include/net/dst.h:492 [inline]
  ip_rcv_finish+0xb1d/0x2110 net/ipv4/ip_input.c:396
  NF_HOOK include/linux/netfilter.h:257 [inline]
  ip_rcv+0xd90/0x19c0 net/ipv4/ip_input.c:487
  __netif_receive_skb_core+0x1ad1/0x3400 net/core/dev.c:4179
  __netif_receive_skb+0x2a/0x170 net/core/dev.c:4217
  netif_receive_skb_internal+0x1d6/0x430 net/core/dev.c:4245
  napi_skb_finish net/core/dev.c:4602 [inline]
  napi_gro_receive+0x4e6/0x680 net/core/dev.c:4636
  e1000_receive_skb drivers/net/ethernet/intel/e1000/e1000_main.c:4033 [inline]
  e1000_clean_rx_irq+0x5e0/0x1490
drivers/net/ethernet/intel/e1000/e1000_main.c:4489
  e1000_clean+0xb9a/0x2910 drivers/net/ethernet/intel/e1000/e1000_main.c:3834
  napi_poll net/core/dev.c:5171 [inline]
  net_rx_action+0xe70/0x1900 net/core/dev.c:5236
  __do_softirq+0x2fb/0xb7d kernel/softirq.c:284
  invoke_softirq kernel/softirq.c:364 [inline]
  irq_exit+0x19e/0x1d0 kernel/softirq.c:405
  exiting_irq arch/x86/include/asm/apic.h:658 [inline]
  do_IRQ+0x81/0x1a0 arch/x86/kernel/irq.c:250
  ret_from_intr+0x0/0x20
  native_safe_halt+0x6/0x10 arch/x86/include/asm/irqflags.h:53
  arch_safe_halt arch/x86/include/asm/paravirt.h:98 [inline]
  default_idle+0x8f/0x410 arch/x86/kernel/process.c:271
  arch_cpu_idle+0xa/0x10 arch/x86/kernel/process.c:262
  default_idle_call+0x36/0x60 kernel/sched/idle.c:96
  cpuidle_idle_call kernel/sched/idle.c:154 [inline]
  do_idle+0x348/0x440 kernel/sched/idle.c:243
  cpu_startup_entry+0x18/0x20 kernel/sched/idle.c:345
  start_secondary+0x344/0x440 arch/x86/kernel/smpboot.c:272
  verify_cpu+0x0/0xfc
irq event stamp: 1741
hardirqs last  enabled at (1741): [<ffffffff84d49d77>]
__raw_spin_unlock_irqrestore include/linux/spinlock_api_smp.h:160
[inline]
hardirqs last  enabled at (1741): [<ffffffff84d49d77>]
_raw_spin_unlock_irqrestore+0xf7/0x1a0 kernel/locking/spinlock.c:191
hardirqs last disabled at (1740): [<ffffffff84d4a732>]
__raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:108 [inline]
hardirqs last disabled at (1740): [<ffffffff84d4a732>]
_raw_spin_lock_irqsave+0xa2/0x110 kernel/locking/spinlock.c:159
softirqs last  enabled at (1738): [<ffffffff84d4deff>]
__do_softirq+0x7cf/0xb7d kernel/softirq.c:310
softirqs last disabled at (1571): [<ffffffff84d4b92c>]
do_softirq_own_stack+0x1c/0x30 arch/x86/entry/entry_64.S:902

other info that might help us debug this:
 Possible unsafe locking scenario:

       CPU0
       ----
  lock(&(&hashinfo->ehash_locks[i])->rlock);
  <Interrupt>
    lock(&(&hashinfo->ehash_locks[i])->rlock);

 *** DEADLOCK ***

1 lock held by syz-executor0/5090:
 #0:  (sk_lock-AF_INET6){+.+.+.}, at: [<ffffffff83406b43>] lock_sock
include/net/sock.h:1460 [inline]
 #0:  (sk_lock-AF_INET6){+.+.+.}, at: [<ffffffff83406b43>]
sock_setsockopt+0x233/0x1e40 net/core/sock.c:683

stack backtrace:
CPU: 1 PID: 5090 Comm: syz-executor0 Not tainted 4.10.0+ #60
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:15 [inline]
 dump_stack+0x292/0x398 lib/dump_stack.c:51
 print_usage_bug+0x3ef/0x450 kernel/locking/lockdep.c:2387
 valid_state kernel/locking/lockdep.c:2400 [inline]
 mark_lock_irq kernel/locking/lockdep.c:2602 [inline]
 mark_lock+0xf30/0x1410 kernel/locking/lockdep.c:3065
 mark_irqflags kernel/locking/lockdep.c:2941 [inline]
 __lock_acquire+0x6dc/0x3270 kernel/locking/lockdep.c:3295
 lock_acquire+0x241/0x580 kernel/locking/lockdep.c:3753
 __raw_spin_lock include/linux/spinlock_api_smp.h:142 [inline]
 _raw_spin_lock+0x33/0x50 kernel/locking/spinlock.c:151
 spin_lock include/linux/spinlock.h:299 [inline]
 inet_ehash_insert+0x240/0xad0 net/ipv4/inet_hashtables.c:407
 reqsk_queue_hash_req net/ipv4/inet_connection_sock.c:753 [inline]
 inet_csk_reqsk_queue_hash_add+0x1b7/0x2a0 net/ipv4/inet_connection_sock.c:764
 dccp_v6_conn_request+0xada/0x11b0 net/dccp/ipv6.c:380
 dccp_rcv_state_process+0x51e/0x1660 net/dccp/input.c:606
 dccp_v6_do_rcv+0x213/0x350 net/dccp/ipv6.c:632
 sk_backlog_rcv include/net/sock.h:896 [inline]
 __release_sock+0x127/0x3a0 net/core/sock.c:2052
 release_sock+0xa5/0x2b0 net/core/sock.c:2539
 sock_setsockopt+0x60f/0x1e40 net/core/sock.c:1016
 SYSC_setsockopt net/socket.c:1782 [inline]
 SyS_setsockopt+0x2fb/0x3a0 net/socket.c:1765
 entry_SYSCALL_64_fastpath+0x1f/0xc2
RIP: 0033:0x4458b9
RSP: 002b:00007fe8b26c2b58 EFLAGS: 00000292 ORIG_RAX: 0000000000000036
RAX: ffffffffffffffda RBX: 0000000000000006 RCX: 00000000004458b9
RDX: 000000000000001a RSI: 0000000000000001 RDI: 0000000000000006
RBP: 00000000006e2110 R08: 0000000000000010 R09: 0000000000000000
R10: 00000000208c3000 R11: 0000000000000292 R12: 0000000000708000
R13: 0000000020000000 R14: 0000000000001000 R15: 0000000000000000

Fixes: 5413d1babe8f ("net: do not block BH while processing socket backlog")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/input.c     | 10 ++++++++--
 net/ipv4/tcp_input.c | 10 ++++++++--
 2 files changed, 16 insertions(+), 4 deletions(-)

diff --git a/net/dccp/input.c b/net/dccp/input.c
index 8fedc2d..4a05d78 100644
--- a/net/dccp/input.c
+++ b/net/dccp/input.c
@@ -577,6 +577,7 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 	struct dccp_sock *dp = dccp_sk(sk);
 	struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
 	const int old_state = sk->sk_state;
+	bool acceptable;
 	int queued = 0;
 
 	/*
@@ -603,8 +604,13 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 	 */
 	if (sk->sk_state == DCCP_LISTEN) {
 		if (dh->dccph_type == DCCP_PKT_REQUEST) {
-			if (inet_csk(sk)->icsk_af_ops->conn_request(sk,
-								    skb) < 0)
+			/* It is possible that we process SYN packets from backlog,
+			 * so we need to make sure to disable BH right there.
+			 */
+			local_bh_disable();
+			acceptable = inet_csk(sk)->icsk_af_ops->conn_request(sk, skb) >= 0;
+			local_bh_enable();
+			if (!acceptable)
 				return 1;
 			consume_skb(skb);
 			return 0;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 41dcbd5..28777a0 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5916,9 +5916,15 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 		if (th->syn) {
 			if (th->fin)
 				goto discard;
-			if (icsk->icsk_af_ops->conn_request(sk, skb) < 0)
-				return 1;
+			/* It is possible that we process SYN packets from backlog,
+			 * so we need to make sure to disable BH right there.
+			 */
+			local_bh_disable();
+			acceptable = icsk->icsk_af_ops->conn_request(sk, skb) >= 0;
+			local_bh_enable();
 
+			if (!acceptable)
+				return 1;
 			consume_skb(skb);
 			return 0;
 		}
-- 
2.1.0


From 63bcbb5da9e6a2e49dc914d453b18e602ca61f2c Mon Sep 17 00:00:00 2001
From: Mike Manning <mmanning@brocade.com>
Date: Wed, 1 Mar 2017 09:55:28 +0000
Subject: [PATCH 19/48] net: bridge: allow IPv6 when multicast flood is
 disabled

[ Upstream commit 8953de2f02ad7b15e4964c82f9afd60f128e4e98 ]

Even with multicast flooding turned off, IPv6 ND should still work so
that IPv6 connectivity is provided. Allow this by continuing to flood
multicast traffic originated by us.

Fixes: b6cb5ac8331b ("net: bridge: add per-port multicast flood flag")
Cc: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: Mike Manning <mmanning@brocade.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_forward.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 7cb41ae..8498e35 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -186,8 +186,9 @@ void br_flood(struct net_bridge *br, struct sk_buff *skb,
 		/* Do not flood unicast traffic to ports that turn it off */
 		if (pkt_type == BR_PKT_UNICAST && !(p->flags & BR_FLOOD))
 			continue;
+		/* Do not flood if mc off, except for traffic we originate */
 		if (pkt_type == BR_PKT_MULTICAST &&
-		    !(p->flags & BR_MCAST_FLOOD))
+		    !(p->flags & BR_MCAST_FLOOD) && skb->dev != br->dev)
 			continue;
 
 		/* Do not flood to ports that enable proxy ARP */
-- 
2.1.0


From ca730be584733fd75a2f8051c2779a09d475a126 Mon Sep 17 00:00:00 2001
From: Alexander Potapenko <glider@google.com>
Date: Wed, 1 Mar 2017 12:57:20 +0100
Subject: [PATCH 20/48] net: don't call strlen() on the user buffer in
 packet_bind_spkt()

[ Upstream commit 540e2894f7905538740aaf122bd8e0548e1c34a4 ]

KMSAN (KernelMemorySanitizer, a new error detection tool) reports use of
uninitialized memory in packet_bind_spkt():
Acked-by: Eric Dumazet <edumazet@google.com>

==================================================================
BUG: KMSAN: use of unitialized memory
CPU: 0 PID: 1074 Comm: packet Not tainted 4.8.0-rc6+ #1891
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs
01/01/2011
 0000000000000000 ffff88006b6dfc08 ffffffff82559ae8 ffff88006b6dfb48
 ffffffff818a7c91 ffffffff85b9c870 0000000000000092 ffffffff85b9c550
 0000000000000000 0000000000000092 00000000ec400911 0000000000000002
Call Trace:
 [<     inline     >] __dump_stack lib/dump_stack.c:15
 [<ffffffff82559ae8>] dump_stack+0x238/0x290 lib/dump_stack.c:51
 [<ffffffff818a6626>] kmsan_report+0x276/0x2e0 mm/kmsan/kmsan.c:1003
 [<ffffffff818a783b>] __msan_warning+0x5b/0xb0
mm/kmsan/kmsan_instr.c:424
 [<     inline     >] strlen lib/string.c:484
 [<ffffffff8259b58d>] strlcpy+0x9d/0x200 lib/string.c:144
 [<ffffffff84b2eca4>] packet_bind_spkt+0x144/0x230
net/packet/af_packet.c:3132
 [<ffffffff84242e4d>] SYSC_bind+0x40d/0x5f0 net/socket.c:1370
 [<ffffffff84242a22>] SyS_bind+0x82/0xa0 net/socket.c:1356
 [<ffffffff8515991b>] entry_SYSCALL_64_fastpath+0x13/0x8f
arch/x86/entry/entry_64.o:?
chained origin: 00000000eba00911
 [<ffffffff810bb787>] save_stack_trace+0x27/0x50
arch/x86/kernel/stacktrace.c:67
 [<     inline     >] kmsan_save_stack_with_flags mm/kmsan/kmsan.c:322
 [<     inline     >] kmsan_save_stack mm/kmsan/kmsan.c:334
 [<ffffffff818a59f8>] kmsan_internal_chain_origin+0x118/0x1e0
mm/kmsan/kmsan.c:527
 [<ffffffff818a7773>] __msan_set_alloca_origin4+0xc3/0x130
mm/kmsan/kmsan_instr.c:380
 [<ffffffff84242b69>] SYSC_bind+0x129/0x5f0 net/socket.c:1356
 [<ffffffff84242a22>] SyS_bind+0x82/0xa0 net/socket.c:1356
 [<ffffffff8515991b>] entry_SYSCALL_64_fastpath+0x13/0x8f
arch/x86/entry/entry_64.o:?
origin description: ----address@SYSC_bind (origin=00000000eb400911)
==================================================================
(the line numbers are relative to 4.8-rc6, but the bug persists
upstream)

, when I run the following program as root:

=====================================
 #include <string.h>
 #include <sys/socket.h>
 #include <netpacket/packet.h>
 #include <net/ethernet.h>

 int main() {
   struct sockaddr addr;
   memset(&addr, 0xff, sizeof(addr));
   addr.sa_family = AF_PACKET;
   int fd = socket(PF_PACKET, SOCK_PACKET, htons(ETH_P_ALL));
   bind(fd, &addr, sizeof(addr));
   return 0;
 }
=====================================

This happens because addr.sa_data copied from the userspace is not
zero-terminated, and copying it with strlcpy() in packet_bind_spkt()
results in calling strlen() on the kernel copy of that non-terminated
buffer.

Signed-off-by: Alexander Potapenko <glider@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 70f5b6a..c59fcc7 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3082,7 +3082,7 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr,
 			    int addr_len)
 {
 	struct sock *sk = sock->sk;
-	char name[15];
+	char name[sizeof(uaddr->sa_data) + 1];
 
 	/*
 	 *	Check legality
@@ -3090,7 +3090,11 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr,
 
 	if (addr_len != sizeof(struct sockaddr))
 		return -EINVAL;
-	strlcpy(name, uaddr->sa_data, sizeof(name));
+	/* uaddr->sa_data comes from the userspace, it's not guaranteed to be
+	 * zero-terminated.
+	 */
+	memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data));
+	name[sizeof(uaddr->sa_data)] = 0;
 
 	return packet_do_bind(sk, name, 0, pkt_sk(sk)->num);
 }
-- 
2.1.0


From d36aaf61db4563735e2a5b73d81eeebf7de1a7bb Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 1 Mar 2017 14:28:39 -0800
Subject: [PATCH 21/48] net: net_enable_timestamp() can be called from irq
 contexts

[ Upstream commit 13baa00ad01bb3a9f893e3a08cbc2d072fc0c15d ]

It is now very clear that silly TCP listeners might play with
enabling/disabling timestamping while new children are added
to their accept queue.

Meaning net_enable_timestamp() can be called from BH context
while current state of the static key is not enabled.

Lets play safe and allow all contexts.

The work queue is scheduled only under the problematic cases,
which are the static key enable/disable transition, to not slow down
critical paths.

This extends and improves what we did in commit 5fa8bbda38c6 ("net: use
a work queue to defer net_disable_timestamp() work")

Fixes: b90e5794c5bd ("net: dont call jump_label_dec from irq context")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 35 +++++++++++++++++++++++++++++++----
 1 file changed, 31 insertions(+), 4 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 29101c9..fd6e2df 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1696,27 +1696,54 @@ EXPORT_SYMBOL_GPL(net_dec_egress_queue);
 static struct static_key netstamp_needed __read_mostly;
 #ifdef HAVE_JUMP_LABEL
 static atomic_t netstamp_needed_deferred;
+static atomic_t netstamp_wanted;
 static void netstamp_clear(struct work_struct *work)
 {
 	int deferred = atomic_xchg(&netstamp_needed_deferred, 0);
+	int wanted;
 
-	while (deferred--)
-		static_key_slow_dec(&netstamp_needed);
+	wanted = atomic_add_return(deferred, &netstamp_wanted);
+	if (wanted > 0)
+		static_key_enable(&netstamp_needed);
+	else
+		static_key_disable(&netstamp_needed);
 }
 static DECLARE_WORK(netstamp_work, netstamp_clear);
 #endif
 
 void net_enable_timestamp(void)
 {
+#ifdef HAVE_JUMP_LABEL
+	int wanted;
+
+	while (1) {
+		wanted = atomic_read(&netstamp_wanted);
+		if (wanted <= 0)
+			break;
+		if (atomic_cmpxchg(&netstamp_wanted, wanted, wanted + 1) == wanted)
+			return;
+	}
+	atomic_inc(&netstamp_needed_deferred);
+	schedule_work(&netstamp_work);
+#else
 	static_key_slow_inc(&netstamp_needed);
+#endif
 }
 EXPORT_SYMBOL(net_enable_timestamp);
 
 void net_disable_timestamp(void)
 {
 #ifdef HAVE_JUMP_LABEL
-	/* net_disable_timestamp() can be called from non process context */
-	atomic_inc(&netstamp_needed_deferred);
+	int wanted;
+
+	while (1) {
+		wanted = atomic_read(&netstamp_wanted);
+		if (wanted <= 1)
+			break;
+		if (atomic_cmpxchg(&netstamp_wanted, wanted, wanted - 1) == wanted)
+			return;
+	}
+	atomic_dec(&netstamp_needed_deferred);
 	schedule_work(&netstamp_work);
 #else
 	static_key_slow_dec(&netstamp_needed);
-- 
2.1.0


From 285f275a6153bb1ce6862146b6c30ba3d0866f3f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 1 Mar 2017 14:45:06 -0800
Subject: [PATCH 22/48] ipv6: orphan skbs in reassembly unit

[ Upstream commit 48cac18ecf1de82f76259a54402c3adb7839ad01 ]

Andrey reported a use-after-free in IPv6 stack.

Issue here is that we free the socket while it still has skb
in TX path and in some queues.

It happens here because IPv6 reassembly unit messes skb->truesize,
breaking skb_set_owner_w() badly.

We fixed a similar issue for IPV4 in commit 8282f27449bf ("inet: frag:
Always orphan skbs inside ip_defrag()")
Acked-by: Joe Stringer <joe@ovn.org>

==================================================================
BUG: KASAN: use-after-free in sock_wfree+0x118/0x120
Read of size 8 at addr ffff880062da0060 by task a.out/4140

page:ffffea00018b6800 count:1 mapcount:0 mapping:          (null)
index:0x0 compound_mapcount: 0
flags: 0x100000000008100(slab|head)
raw: 0100000000008100 0000000000000000 0000000000000000 0000000180130013
raw: dead000000000100 dead000000000200 ffff88006741f140 0000000000000000
page dumped because: kasan: bad access detected

CPU: 0 PID: 4140 Comm: a.out Not tainted 4.10.0-rc3+ #59
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:15
 dump_stack+0x292/0x398 lib/dump_stack.c:51
 describe_address mm/kasan/report.c:262
 kasan_report_error+0x121/0x560 mm/kasan/report.c:370
 kasan_report mm/kasan/report.c:392
 __asan_report_load8_noabort+0x3e/0x40 mm/kasan/report.c:413
 sock_flag ./arch/x86/include/asm/bitops.h:324
 sock_wfree+0x118/0x120 net/core/sock.c:1631
 skb_release_head_state+0xfc/0x250 net/core/skbuff.c:655
 skb_release_all+0x15/0x60 net/core/skbuff.c:668
 __kfree_skb+0x15/0x20 net/core/skbuff.c:684
 kfree_skb+0x16e/0x4e0 net/core/skbuff.c:705
 inet_frag_destroy+0x121/0x290 net/ipv4/inet_fragment.c:304
 inet_frag_put ./include/net/inet_frag.h:133
 nf_ct_frag6_gather+0x1125/0x38b0 net/ipv6/netfilter/nf_conntrack_reasm.c:617
 ipv6_defrag+0x21b/0x350 net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:68
 nf_hook_entry_hookfn ./include/linux/netfilter.h:102
 nf_hook_slow+0xc3/0x290 net/netfilter/core.c:310
 nf_hook ./include/linux/netfilter.h:212
 __ip6_local_out+0x52c/0xaf0 net/ipv6/output_core.c:160
 ip6_local_out+0x2d/0x170 net/ipv6/output_core.c:170
 ip6_send_skb+0xa1/0x340 net/ipv6/ip6_output.c:1722
 ip6_push_pending_frames+0xb3/0xe0 net/ipv6/ip6_output.c:1742
 rawv6_push_pending_frames net/ipv6/raw.c:613
 rawv6_sendmsg+0x2cff/0x4130 net/ipv6/raw.c:927
 inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:744
 sock_sendmsg_nosec net/socket.c:635
 sock_sendmsg+0xca/0x110 net/socket.c:645
 sock_write_iter+0x326/0x620 net/socket.c:848
 new_sync_write fs/read_write.c:499
 __vfs_write+0x483/0x760 fs/read_write.c:512
 vfs_write+0x187/0x530 fs/read_write.c:560
 SYSC_write fs/read_write.c:607
 SyS_write+0xfb/0x230 fs/read_write.c:599
 entry_SYSCALL_64_fastpath+0x1f/0xc2 arch/x86/entry/entry_64.S:203
RIP: 0033:0x7ff26e6f5b79
RSP: 002b:00007ff268e0ed98 EFLAGS: 00000206 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 00007ff268e0f9c0 RCX: 00007ff26e6f5b79
RDX: 0000000000000010 RSI: 0000000020f50fe1 RDI: 0000000000000003
RBP: 00007ff26ebc1220 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000206 R12: 0000000000000000
R13: 00007ff268e0f9c0 R14: 00007ff26efec040 R15: 0000000000000003

The buggy address belongs to the object at ffff880062da0000
 which belongs to the cache RAWv6 of size 1504
The buggy address ffff880062da0060 is located 96 bytes inside
 of 1504-byte region [ffff880062da0000, ffff880062da05e0)

Freed by task 4113:
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57
 save_stack+0x43/0xd0 mm/kasan/kasan.c:502
 set_track mm/kasan/kasan.c:514
 kasan_slab_free+0x73/0xc0 mm/kasan/kasan.c:578
 slab_free_hook mm/slub.c:1352
 slab_free_freelist_hook mm/slub.c:1374
 slab_free mm/slub.c:2951
 kmem_cache_free+0xb2/0x2c0 mm/slub.c:2973
 sk_prot_free net/core/sock.c:1377
 __sk_destruct+0x49c/0x6e0 net/core/sock.c:1452
 sk_destruct+0x47/0x80 net/core/sock.c:1460
 __sk_free+0x57/0x230 net/core/sock.c:1468
 sk_free+0x23/0x30 net/core/sock.c:1479
 sock_put ./include/net/sock.h:1638
 sk_common_release+0x31e/0x4e0 net/core/sock.c:2782
 rawv6_close+0x54/0x80 net/ipv6/raw.c:1214
 inet_release+0xed/0x1c0 net/ipv4/af_inet.c:425
 inet6_release+0x50/0x70 net/ipv6/af_inet6.c:431
 sock_release+0x8d/0x1e0 net/socket.c:599
 sock_close+0x16/0x20 net/socket.c:1063
 __fput+0x332/0x7f0 fs/file_table.c:208
 ____fput+0x15/0x20 fs/file_table.c:244
 task_work_run+0x19b/0x270 kernel/task_work.c:116
 exit_task_work ./include/linux/task_work.h:21
 do_exit+0x186b/0x2800 kernel/exit.c:839
 do_group_exit+0x149/0x420 kernel/exit.c:943
 SYSC_exit_group kernel/exit.c:954
 SyS_exit_group+0x1d/0x20 kernel/exit.c:952
 entry_SYSCALL_64_fastpath+0x1f/0xc2 arch/x86/entry/entry_64.S:203

Allocated by task 4115:
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57
 save_stack+0x43/0xd0 mm/kasan/kasan.c:502
 set_track mm/kasan/kasan.c:514
 kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:605
 kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:544
 slab_post_alloc_hook mm/slab.h:432
 slab_alloc_node mm/slub.c:2708
 slab_alloc mm/slub.c:2716
 kmem_cache_alloc+0x1af/0x250 mm/slub.c:2721
 sk_prot_alloc+0x65/0x2a0 net/core/sock.c:1334
 sk_alloc+0x105/0x1010 net/core/sock.c:1396
 inet6_create+0x44d/0x1150 net/ipv6/af_inet6.c:183
 __sock_create+0x4f6/0x880 net/socket.c:1199
 sock_create net/socket.c:1239
 SYSC_socket net/socket.c:1269
 SyS_socket+0xf9/0x230 net/socket.c:1249
 entry_SYSCALL_64_fastpath+0x1f/0xc2 arch/x86/entry/entry_64.S:203

Memory state around the buggy address:
 ffff880062d9ff00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 ffff880062d9ff80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
>ffff880062da0000: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                                                       ^
 ffff880062da0080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff880062da0100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
==================================================================

Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/netfilter/nf_conntrack_reasm.c | 1 +
 net/openvswitch/conntrack.c             | 1 -
 2 files changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 9948b5c..986d4ca 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -589,6 +589,7 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
 	hdr = ipv6_hdr(skb);
 	fhdr = (struct frag_hdr *)skb_transport_header(skb);
 
+	skb_orphan(skb);
 	fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr,
 		     skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
 	if (fq == NULL) {
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 54253ea..919d66e 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -367,7 +367,6 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key,
 	} else if (key->eth.type == htons(ETH_P_IPV6)) {
 		enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone;
 
-		skb_orphan(skb);
 		memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));
 		err = nf_ct_frag6_gather(net, skb, user);
 		if (err) {
-- 
2.1.0


From c9b284a0edd2acaea21859d57efdcfa4a0c5404b Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 1 Mar 2017 16:35:07 -0300
Subject: [PATCH 23/48] dccp: Unlock sock before calling sk_free()

[ Upstream commit d5afb6f9b6bb2c57bd0c05e76e12489dc0d037d9 ]

The code where sk_clone() came from created a new socket and locked it,
but then, on the error path didn't unlock it.

This problem stayed there for a long while, till b0691c8ee7c2 ("net:
Unlock sock before calling sk_free()") fixed it, but unfortunately the
callers of sk_clone() (now sk_clone_locked()) were not audited and the
one in dccp_create_openreq_child() remained.

Now in the age of the syskaller fuzzer, this was finally uncovered, as
reported by Dmitry:

 ---- 8< ----

I've got the following report while running syzkaller fuzzer on
86292b33d4b7 ("Merge branch 'akpm' (patches from Andrew)")

  [ BUG: held lock freed! ]
  4.10.0+ #234 Not tainted
  -------------------------
  syz-executor6/6898 is freeing memory
  ffff88006286cac0-ffff88006286d3b7, with a lock still held there!
   (slock-AF_INET6){+.-...}, at: [<ffffffff8362c2c9>] spin_lock
  include/linux/spinlock.h:299 [inline]
   (slock-AF_INET6){+.-...}, at: [<ffffffff8362c2c9>]
  sk_clone_lock+0x3d9/0x12c0 net/core/sock.c:1504
  5 locks held by syz-executor6/6898:
   #0:  (sk_lock-AF_INET6){+.+.+.}, at: [<ffffffff839a34b4>] lock_sock
  include/net/sock.h:1460 [inline]
   #0:  (sk_lock-AF_INET6){+.+.+.}, at: [<ffffffff839a34b4>]
  inet_stream_connect+0x44/0xa0 net/ipv4/af_inet.c:681
   #1:  (rcu_read_lock){......}, at: [<ffffffff83bc1c2a>]
  inet6_csk_xmit+0x12a/0x5d0 net/ipv6/inet6_connection_sock.c:126
   #2:  (rcu_read_lock){......}, at: [<ffffffff8369b424>] __skb_unlink
  include/linux/skbuff.h:1767 [inline]
   #2:  (rcu_read_lock){......}, at: [<ffffffff8369b424>] __skb_dequeue
  include/linux/skbuff.h:1783 [inline]
   #2:  (rcu_read_lock){......}, at: [<ffffffff8369b424>]
  process_backlog+0x264/0x730 net/core/dev.c:4835
   #3:  (rcu_read_lock){......}, at: [<ffffffff83aeb5c0>]
  ip6_input_finish+0x0/0x1700 net/ipv6/ip6_input.c:59
   #4:  (slock-AF_INET6){+.-...}, at: [<ffffffff8362c2c9>] spin_lock
  include/linux/spinlock.h:299 [inline]
   #4:  (slock-AF_INET6){+.-...}, at: [<ffffffff8362c2c9>]
  sk_clone_lock+0x3d9/0x12c0 net/core/sock.c:1504

Fix it just like was done by b0691c8ee7c2 ("net: Unlock sock before calling
sk_free()").

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20170301153510.GE15145@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/minisocks.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index 53eddf9..d20d948 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -122,6 +122,7 @@ struct sock *dccp_create_openreq_child(const struct sock *sk,
 			/* It is still raw copy of parent, so invalidate
 			 * destructor and make plain sk_free() */
 			newsk->sk_destruct = NULL;
+			bh_unlock_sock(newsk);
 			sk_free(newsk);
 			return NULL;
 		}
-- 
2.1.0


From 603a5219b062359da1491b3e056b9bde973a7739 Mon Sep 17 00:00:00 2001
From: "Lendacky, Thomas" <Thomas.Lendacky@amd.com>
Date: Tue, 28 Feb 2017 15:02:51 -0600
Subject: [PATCH 24/48] amd-xgbe: Stop the PHY before releasing interrupts

[ Upstream commit 402168b4c2dc0734b8fbd282eff77da0275c5129 ]

Some configurations require the use of the hardware's MDIO support to
communicate with external PHYs. The MDIO commands indicate completion
through the device interrupt. When bringing down the device the interrupts
were released before stopping the external PHY, resulting in MDIO command
timeouts. Move the stopping of the PHY to before the releasing of the
interrupts.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe-drv.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 1c87cc2..0f4bbe1f 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -1131,12 +1131,12 @@ static void xgbe_stop(struct xgbe_prv_data *pdata)
 	hw_if->disable_tx(pdata);
 	hw_if->disable_rx(pdata);
 
+	phy_if->phy_stop(pdata);
+
 	xgbe_free_irqs(pdata);
 
 	xgbe_napi_disable(pdata, 1);
 
-	phy_if->phy_stop(pdata);
-
 	hw_if->exit(pdata);
 
 	channel = pdata->channel;
-- 
2.1.0


From de2289a47236bf7d4cf6891b751a65aaaa9722ad Mon Sep 17 00:00:00 2001
From: "Lendacky, Thomas" <Thomas.Lendacky@amd.com>
Date: Tue, 28 Feb 2017 15:03:01 -0600
Subject: [PATCH 25/48] amd-xgbe: Be sure to set MDIO modes on device (re)start

[ Upstream commit b42c6761fd1651f564491b53016046c9ebf0b2a9 ]

The MDIO register mode is set when the device is probed. But when the
device is brought down and then back up, the MDIO register mode has been
reset.  Be sure to reset the mode during device startup and only change
the mode of the address specified.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe-dev.c    |  2 +-
 drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c | 22 ++++++++++++++++++++++
 2 files changed, 23 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
index a7d16db..937f37a 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
@@ -1323,7 +1323,7 @@ static int xgbe_read_ext_mii_regs(struct xgbe_prv_data *pdata, int addr,
 static int xgbe_set_ext_mii_mode(struct xgbe_prv_data *pdata, unsigned int port,
 				 enum xgbe_mdio_mode mode)
 {
-	unsigned int reg_val = 0;
+	unsigned int reg_val = XGMAC_IOREAD(pdata, MAC_MDIOCL22R);
 
 	switch (mode) {
 	case XGBE_MDIO_MODE_CL22:
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
index 9d8c9530..04804cb 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
@@ -875,6 +875,16 @@ static int xgbe_phy_find_phy_device(struct xgbe_prv_data *pdata)
 	    !phy_data->sfp_phy_avail)
 		return 0;
 
+	/* Set the proper MDIO mode for the PHY */
+	ret = pdata->hw_if.set_ext_mii_mode(pdata, phy_data->mdio_addr,
+					    phy_data->phydev_mode);
+	if (ret) {
+		netdev_err(pdata->netdev,
+			   "mdio port/clause not compatible (%u/%u)\n",
+			   phy_data->mdio_addr, phy_data->phydev_mode);
+		return ret;
+	}
+
 	/* Create and connect to the PHY device */
 	phydev = get_phy_device(phy_data->mii, phy_data->mdio_addr,
 				(phy_data->phydev_mode == XGBE_MDIO_MODE_CL45));
@@ -2722,6 +2732,18 @@ static int xgbe_phy_start(struct xgbe_prv_data *pdata)
 	if (ret)
 		return ret;
 
+	/* Set the proper MDIO mode for the re-driver */
+	if (phy_data->redrv && !phy_data->redrv_if) {
+		ret = pdata->hw_if.set_ext_mii_mode(pdata, phy_data->redrv_addr,
+						    XGBE_MDIO_MODE_CL22);
+		if (ret) {
+			netdev_err(pdata->netdev,
+				   "redriver mdio port not compatible (%u)\n",
+				   phy_data->redrv_addr);
+			return ret;
+		}
+	}
+
 	/* Start in highest supported mode */
 	xgbe_phy_set_mode(pdata, phy_data->start_mode);
 
-- 
2.1.0


From 72eb25188a904487e9b7f5a45f0f1b382525b011 Mon Sep 17 00:00:00 2001
From: "Lendacky, Thomas" <Thomas.Lendacky@amd.com>
Date: Tue, 28 Feb 2017 15:03:10 -0600
Subject: [PATCH 26/48] amd-xgbe: Don't overwrite SFP PHY mod_absent settings

[ Upstream commit 2697ea5a859b83ca49511dcfd98daf42584eb3cf ]

If an SFP module is not present, xgbe_phy_sfp_phy_settings() should
return after applying the default settings. Currently there is no return
statement and the default settings are overwritten.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
index 04804cb..e707c49 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
@@ -716,6 +716,8 @@ static void xgbe_phy_sfp_phy_settings(struct xgbe_prv_data *pdata)
 		pdata->phy.duplex = DUPLEX_UNKNOWN;
 		pdata->phy.autoneg = AUTONEG_ENABLE;
 		pdata->phy.advertising = pdata->phy.supported;
+
+		return;
 	}
 
 	pdata->phy.advertising &= ~ADVERTISED_Autoneg;
-- 
2.1.0


From 3392b635ae8288437a951c1a4aaeb1aa3f53e0f3 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Thu, 2 Mar 2017 12:24:36 -0800
Subject: [PATCH 27/48] bonding: use ETH_MAX_MTU as max mtu

[ Upstream commit 31c05415f5b471fd333fe42629788364faea8e0d ]

This restores the ability of setting bond device's mtu to 9000.

Fixes: 91572088e3fd ("net: use core MTU range checking in core net infra")
Reported-by: daznis@gmail.com
Reported-by: Brad Campbell <lists2009@fnarfbargle.com>
Cc: Jarod Wilson <jarod@redhat.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 8029dd4..644d2bf 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -4185,6 +4185,7 @@ void bond_setup(struct net_device *bond_dev)
 
 	/* Initialize the device entry points */
 	ether_setup(bond_dev);
+	bond_dev->max_mtu = ETH_MAX_MTU;
 	bond_dev->netdev_ops = &bond_netdev_ops;
 	bond_dev->ethtool_ops = &bond_ethtool_ops;
 
-- 
2.1.0


From cb070fb462aff1534cb4aa860b7248f92c2c45a2 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Fri, 3 Mar 2017 12:21:14 -0800
Subject: [PATCH 28/48] strparser: destroy workqueue on module exit

[ Upstream commit f78ef7cd9a0686b979679d0de061c6dbfd8d649e ]

Fixes: 43a0c6751a32 ("strparser: Stream parser for messages")
Cc: Tom Herbert <tom@herbertland.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/strparser/strparser.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index 41adf36..b5c279b 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -504,6 +504,7 @@ static int __init strp_mod_init(void)
 
 static void __exit strp_mod_exit(void)
 {
+	destroy_workqueue(strp_wq);
 }
 module_init(strp_mod_init);
 module_exit(strp_mod_exit);
-- 
2.1.0


From d8ac70885a014e6712372e95877d632c7016bd38 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 3 Mar 2017 14:08:21 -0800
Subject: [PATCH 29/48] tcp: fix various issues for sockets morphing to listen
 state

[ Upstream commit 02b2faaf0af1d85585f6d6980e286d53612acfc2 ]

Dmitry Vyukov reported a divide by 0 triggered by syzkaller, exploiting
tcp_disconnect() path that was never really considered and/or used
before syzkaller ;)

I was not able to reproduce the bug, but it seems issues here are the
three possible actions that assumed they would never trigger on a
listener.

1) tcp_write_timer_handler
2) tcp_delack_timer_handler
3) MTU reduction

Only IPv6 MTU reduction was properly testing TCP_CLOSE and TCP_LISTEN
 states from tcp_v6_mtu_reduced()

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c  | 7 +++++--
 net/ipv4/tcp_timer.c | 6 ++++--
 2 files changed, 9 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index fe9da4f..90c1d78 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -269,10 +269,13 @@ EXPORT_SYMBOL(tcp_v4_connect);
  */
 void tcp_v4_mtu_reduced(struct sock *sk)
 {
-	struct dst_entry *dst;
 	struct inet_sock *inet = inet_sk(sk);
-	u32 mtu = tcp_sk(sk)->mtu_info;
+	struct dst_entry *dst;
+	u32 mtu;
 
+	if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
+		return;
+	mtu = tcp_sk(sk)->mtu_info;
 	dst = inet_csk_update_pmtu(sk, mtu);
 	if (!dst)
 		return;
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 3705075..45d7075 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -249,7 +249,8 @@ void tcp_delack_timer_handler(struct sock *sk)
 
 	sk_mem_reclaim_partial(sk);
 
-	if (sk->sk_state == TCP_CLOSE || !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
+	if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
+	    !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
 		goto out;
 
 	if (time_after(icsk->icsk_ack.timeout, jiffies)) {
@@ -552,7 +553,8 @@ void tcp_write_timer_handler(struct sock *sk)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	int event;
 
-	if (sk->sk_state == TCP_CLOSE || !icsk->icsk_pending)
+	if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
+	    !icsk->icsk_pending)
 		goto out;
 
 	if (time_after(icsk->icsk_timeout, jiffies)) {
-- 
2.1.0


From 803364a08c7a65404f26db6802e62deed12e9707 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 3 Mar 2017 21:01:02 -0800
Subject: [PATCH 30/48] net: fix socket refcounting in skb_complete_wifi_ack()

[ Upstream commit dd4f10722aeb10f4f582948839f066bebe44e5fb ]

TX skbs do not necessarily hold a reference on skb->sk->sk_refcnt
By the time TX completion happens, sk_refcnt might be already 0.

sock_hold()/sock_put() would then corrupt critical state, like
sk_wmem_alloc.

Fixes: bf7fa551e0ce ("mac80211: Resolve sk_refcnt/sk_wmem_alloc issue in wifi ack path")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 734c714..cebb961 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3889,7 +3889,7 @@ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked)
 {
 	struct sock *sk = skb->sk;
 	struct sock_exterr_skb *serr;
-	int err;
+	int err = 1;
 
 	skb->wifi_acked_valid = 1;
 	skb->wifi_acked = acked;
@@ -3899,14 +3899,15 @@ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked)
 	serr->ee.ee_errno = ENOMSG;
 	serr->ee.ee_origin = SO_EE_ORIGIN_TXSTATUS;
 
-	/* take a reference to prevent skb_orphan() from freeing the socket */
-	sock_hold(sk);
-
-	err = sock_queue_err_skb(sk, skb);
+	/* Take a reference to prevent skb_orphan() from freeing the socket,
+	 * but only if the socket refcount is not zero.
+	 */
+	if (likely(atomic_inc_not_zero(&sk->sk_refcnt))) {
+		err = sock_queue_err_skb(sk, skb);
+		sock_put(sk);
+	}
 	if (err)
 		kfree_skb(skb);
-
-	sock_put(sk);
 }
 EXPORT_SYMBOL_GPL(skb_complete_wifi_ack);
 
-- 
2.1.0


From 4bbecabe54635fa5d26de4037d1206b226d5e83d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 3 Mar 2017 21:01:03 -0800
Subject: [PATCH 31/48] net: fix socket refcounting in
 skb_complete_tx_timestamp()

[ Upstream commit 9ac25fc063751379cb77434fef9f3b088cd3e2f7 ]

TX skbs do not necessarily hold a reference on skb->sk->sk_refcnt
By the time TX completion happens, sk_refcnt might be already 0.

sock_hold()/sock_put() would then corrupt critical state, like
sk_wmem_alloc and lead to leaks or use after free.

Fixes: 62bccb8cdb69 ("net-timestamp: Make the clone operation stand-alone from phy timestamping")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index cebb961..aa3a133 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3824,13 +3824,14 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
 	if (!skb_may_tx_timestamp(sk, false))
 		return;
 
-	/* take a reference to prevent skb_orphan() from freeing the socket */
-	sock_hold(sk);
-
-	*skb_hwtstamps(skb) = *hwtstamps;
-	__skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND);
-
-	sock_put(sk);
+	/* Take a reference to prevent skb_orphan() from freeing the socket,
+	 * but only if the socket refcount is not zero.
+	 */
+	if (likely(atomic_inc_not_zero(&sk->sk_refcnt))) {
+		*skb_hwtstamps(skb) = *hwtstamps;
+		__skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND);
+		sock_put(sk);
+	}
 }
 EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp);
 
-- 
2.1.0


From a8484b26192f114ee55c34394bf696b1bd6b0ae9 Mon Sep 17 00:00:00 2001
From: Alexey Khoroshilov <khoroshilov@ispras.ru>
Date: Sun, 5 Mar 2017 03:01:55 +0300
Subject: [PATCH 32/48] net/sched: act_skbmod: remove unneeded rcu_read_unlock
 in tcf_skbmod_dump

[ Upstream commit 6c4dc75c251721f517e9daeb5370ea606b5b35ce ]

Found by Linux Driver Verification project (linuxtesting.org).

Signed-off-by: Alexey Khoroshilov <khoroshilov@ispras.ru>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_skbmod.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index 3b7074e..c736627 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -228,7 +228,6 @@ static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a,
 
 	return skb->len;
 nla_put_failure:
-	rcu_read_unlock();
 	nlmsg_trim(skb, b);
 	return -1;
 }
-- 
2.1.0


From fe0b537fe01fa8690c4f182d86a5fa64d0868379 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 5 Mar 2017 10:52:16 -0800
Subject: [PATCH 33/48] dccp: fix use-after-free in dccp_feat_activate_values

[ Upstream commit 62f8f4d9066c1c6f2474845d1ca7e2891f2ae3fd ]

Dmitry reported crashes in DCCP stack [1]

Problem here is that when I got rid of listener spinlock, I missed the
fact that DCCP stores a complex state in struct dccp_request_sock,
while TCP does not.

Since multiple cpus could access it at the same time, we need to add
protection.

[1]
BUG: KASAN: use-after-free in dccp_feat_activate_values+0x967/0xab0
net/dccp/feat.c:1541 at addr ffff88003713be68
Read of size 8 by task syz-executor2/8457
CPU: 2 PID: 8457 Comm: syz-executor2 Not tainted 4.10.0-rc7+ #127
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:15 [inline]
 dump_stack+0x292/0x398 lib/dump_stack.c:51
 kasan_object_err+0x1c/0x70 mm/kasan/report.c:162
 print_address_description mm/kasan/report.c:200 [inline]
 kasan_report_error mm/kasan/report.c:289 [inline]
 kasan_report.part.1+0x20e/0x4e0 mm/kasan/report.c:311
 kasan_report mm/kasan/report.c:332 [inline]
 __asan_report_load8_noabort+0x29/0x30 mm/kasan/report.c:332
 dccp_feat_activate_values+0x967/0xab0 net/dccp/feat.c:1541
 dccp_create_openreq_child+0x464/0x610 net/dccp/minisocks.c:121
 dccp_v6_request_recv_sock+0x1f6/0x1960 net/dccp/ipv6.c:457
 dccp_check_req+0x335/0x5a0 net/dccp/minisocks.c:186
 dccp_v6_rcv+0x69e/0x1d00 net/dccp/ipv6.c:711
 ip6_input_finish+0x46d/0x17a0 net/ipv6/ip6_input.c:279
 NF_HOOK include/linux/netfilter.h:257 [inline]
 ip6_input+0xdb/0x590 net/ipv6/ip6_input.c:322
 dst_input include/net/dst.h:507 [inline]
 ip6_rcv_finish+0x289/0x890 net/ipv6/ip6_input.c:69
 NF_HOOK include/linux/netfilter.h:257 [inline]
 ipv6_rcv+0x12ec/0x23d0 net/ipv6/ip6_input.c:203
 __netif_receive_skb_core+0x1ae5/0x3400 net/core/dev.c:4190
 __netif_receive_skb+0x2a/0x170 net/core/dev.c:4228
 process_backlog+0xe5/0x6c0 net/core/dev.c:4839
 napi_poll net/core/dev.c:5202 [inline]
 net_rx_action+0xe70/0x1900 net/core/dev.c:5267
 __do_softirq+0x2fb/0xb7d kernel/softirq.c:284
 do_softirq_own_stack+0x1c/0x30 arch/x86/entry/entry_64.S:902
 </IRQ>
 do_softirq.part.17+0x1e8/0x230 kernel/softirq.c:328
 do_softirq kernel/softirq.c:176 [inline]
 __local_bh_enable_ip+0x1f2/0x200 kernel/softirq.c:181
 local_bh_enable include/linux/bottom_half.h:31 [inline]
 rcu_read_unlock_bh include/linux/rcupdate.h:971 [inline]
 ip6_finish_output2+0xbb0/0x23d0 net/ipv6/ip6_output.c:123
 ip6_finish_output+0x302/0x960 net/ipv6/ip6_output.c:148
 NF_HOOK_COND include/linux/netfilter.h:246 [inline]
 ip6_output+0x1cb/0x8d0 net/ipv6/ip6_output.c:162
 ip6_xmit+0xcdf/0x20d0 include/net/dst.h:501
 inet6_csk_xmit+0x320/0x5f0 net/ipv6/inet6_connection_sock.c:179
 dccp_transmit_skb+0xb09/0x1120 net/dccp/output.c:141
 dccp_xmit_packet+0x215/0x760 net/dccp/output.c:280
 dccp_write_xmit+0x168/0x1d0 net/dccp/output.c:362
 dccp_sendmsg+0x79c/0xb10 net/dccp/proto.c:796
 inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:744
 sock_sendmsg_nosec net/socket.c:635 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:645
 SYSC_sendto+0x660/0x810 net/socket.c:1687
 SyS_sendto+0x40/0x50 net/socket.c:1655
 entry_SYSCALL_64_fastpath+0x1f/0xc2
RIP: 0033:0x4458b9
RSP: 002b:00007f8ceb77bb58 EFLAGS: 00000282 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 0000000000000017 RCX: 00000000004458b9
RDX: 0000000000000023 RSI: 0000000020e60000 RDI: 0000000000000017
RBP: 00000000006e1b90 R08: 00000000200f9fe1 R09: 0000000000000020
R10: 0000000000008010 R11: 0000000000000282 R12: 00000000007080a8
R13: 0000000000000000 R14: 00007f8ceb77c9c0 R15: 00007f8ceb77c700
Object at ffff88003713be50, in cache kmalloc-64 size: 64
Allocated:
PID = 8446
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57
 save_stack+0x43/0xd0 mm/kasan/kasan.c:502
 set_track mm/kasan/kasan.c:514 [inline]
 kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:605
 kmem_cache_alloc_trace+0x82/0x270 mm/slub.c:2738
 kmalloc include/linux/slab.h:490 [inline]
 dccp_feat_entry_new+0x214/0x410 net/dccp/feat.c:467
 dccp_feat_push_change+0x38/0x220 net/dccp/feat.c:487
 __feat_register_sp+0x223/0x2f0 net/dccp/feat.c:741
 dccp_feat_propagate_ccid+0x22b/0x2b0 net/dccp/feat.c:949
 dccp_feat_server_ccid_dependencies+0x1b3/0x250 net/dccp/feat.c:1012
 dccp_make_response+0x1f1/0xc90 net/dccp/output.c:423
 dccp_v6_send_response+0x4ec/0xc20 net/dccp/ipv6.c:217
 dccp_v6_conn_request+0xaba/0x11b0 net/dccp/ipv6.c:377
 dccp_rcv_state_process+0x51e/0x1650 net/dccp/input.c:606
 dccp_v6_do_rcv+0x213/0x350 net/dccp/ipv6.c:632
 sk_backlog_rcv include/net/sock.h:893 [inline]
 __sk_receive_skb+0x36f/0xcc0 net/core/sock.c:479
 dccp_v6_rcv+0xba5/0x1d00 net/dccp/ipv6.c:742
 ip6_input_finish+0x46d/0x17a0 net/ipv6/ip6_input.c:279
 NF_HOOK include/linux/netfilter.h:257 [inline]
 ip6_input+0xdb/0x590 net/ipv6/ip6_input.c:322
 dst_input include/net/dst.h:507 [inline]
 ip6_rcv_finish+0x289/0x890 net/ipv6/ip6_input.c:69
 NF_HOOK include/linux/netfilter.h:257 [inline]
 ipv6_rcv+0x12ec/0x23d0 net/ipv6/ip6_input.c:203
 __netif_receive_skb_core+0x1ae5/0x3400 net/core/dev.c:4190
 __netif_receive_skb+0x2a/0x170 net/core/dev.c:4228
 process_backlog+0xe5/0x6c0 net/core/dev.c:4839
 napi_poll net/core/dev.c:5202 [inline]
 net_rx_action+0xe70/0x1900 net/core/dev.c:5267
 __do_softirq+0x2fb/0xb7d kernel/softirq.c:284
Freed:
PID = 15
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57
 save_stack+0x43/0xd0 mm/kasan/kasan.c:502
 set_track mm/kasan/kasan.c:514 [inline]
 kasan_slab_free+0x73/0xc0 mm/kasan/kasan.c:578
 slab_free_hook mm/slub.c:1355 [inline]
 slab_free_freelist_hook mm/slub.c:1377 [inline]
 slab_free mm/slub.c:2954 [inline]
 kfree+0xe8/0x2b0 mm/slub.c:3874
 dccp_feat_entry_destructor.part.4+0x48/0x60 net/dccp/feat.c:418
 dccp_feat_entry_destructor net/dccp/feat.c:416 [inline]
 dccp_feat_list_pop net/dccp/feat.c:541 [inline]
 dccp_feat_activate_values+0x57f/0xab0 net/dccp/feat.c:1543
 dccp_create_openreq_child+0x464/0x610 net/dccp/minisocks.c:121
 dccp_v6_request_recv_sock+0x1f6/0x1960 net/dccp/ipv6.c:457
 dccp_check_req+0x335/0x5a0 net/dccp/minisocks.c:186
 dccp_v6_rcv+0x69e/0x1d00 net/dccp/ipv6.c:711
 ip6_input_finish+0x46d/0x17a0 net/ipv6/ip6_input.c:279
 NF_HOOK include/linux/netfilter.h:257 [inline]
 ip6_input+0xdb/0x590 net/ipv6/ip6_input.c:322
 dst_input include/net/dst.h:507 [inline]
 ip6_rcv_finish+0x289/0x890 net/ipv6/ip6_input.c:69
 NF_HOOK include/linux/netfilter.h:257 [inline]
 ipv6_rcv+0x12ec/0x23d0 net/ipv6/ip6_input.c:203
 __netif_receive_skb_core+0x1ae5/0x3400 net/core/dev.c:4190
 __netif_receive_skb+0x2a/0x170 net/core/dev.c:4228
 process_backlog+0xe5/0x6c0 net/core/dev.c:4839
 napi_poll net/core/dev.c:5202 [inline]
 net_rx_action+0xe70/0x1900 net/core/dev.c:5267
 __do_softirq+0x2fb/0xb7d kernel/softirq.c:284
Memory state around the buggy address:
 ffff88003713bd00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 ffff88003713bd80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
>ffff88003713be00: fc fc fc fc fc fc fc fc fc fc fb fb fb fb fb fb
                                                          ^

Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Tested-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/dccp.h |  1 +
 net/dccp/minisocks.c | 24 ++++++++++++++++--------
 2 files changed, 17 insertions(+), 8 deletions(-)

diff --git a/include/linux/dccp.h b/include/linux/dccp.h
index 61d042b..6844929 100644
--- a/include/linux/dccp.h
+++ b/include/linux/dccp.h
@@ -163,6 +163,7 @@ struct dccp_request_sock {
 	__u64			 dreq_isr;
 	__u64			 dreq_gsr;
 	__be32			 dreq_service;
+	spinlock_t		 dreq_lock;
 	struct list_head	 dreq_featneg;
 	__u32			 dreq_timestamp_echo;
 	__u32			 dreq_timestamp_time;
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index d20d948..39e7e2b 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -146,6 +146,13 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
 	struct dccp_request_sock *dreq = dccp_rsk(req);
 	bool own_req;
 
+	/* TCP/DCCP listeners became lockless.
+	 * DCCP stores complex state in its request_sock, so we need
+	 * a protection for them, now this code runs without being protected
+	 * by the parent (listener) lock.
+	 */
+	spin_lock_bh(&dreq->dreq_lock);
+
 	/* Check for retransmitted REQUEST */
 	if (dccp_hdr(skb)->dccph_type == DCCP_PKT_REQUEST) {
 
@@ -160,7 +167,7 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
 			inet_rtx_syn_ack(sk, req);
 		}
 		/* Network Duplicate, discard packet */
-		return NULL;
+		goto out;
 	}
 
 	DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_PACKET_ERROR;
@@ -186,20 +193,20 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
 
 	child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL,
 							 req, &own_req);
-	if (!child)
-		goto listen_overflow;
-
-	return inet_csk_complete_hashdance(sk, child, req, own_req);
+	if (child) {
+		child = inet_csk_complete_hashdance(sk, child, req, own_req);
+		goto out;
+	}
 
-listen_overflow:
-	dccp_pr_debug("listen_overflow!\n");
 	DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_TOO_BUSY;
 drop:
 	if (dccp_hdr(skb)->dccph_type != DCCP_PKT_RESET)
 		req->rsk_ops->send_reset(sk, skb);
 
 	inet_csk_reqsk_queue_drop(sk, req);
-	return NULL;
+out:
+	spin_unlock_bh(&dreq->dreq_lock);
+	return child;
 }
 
 EXPORT_SYMBOL_GPL(dccp_check_req);
@@ -250,6 +257,7 @@ int dccp_reqsk_init(struct request_sock *req,
 {
 	struct dccp_request_sock *dreq = dccp_rsk(req);
 
+	spin_lock_init(&dreq->dreq_lock);
 	inet_rsk(req)->ir_rmt_port = dccp_hdr(skb)->dccph_sport;
 	inet_rsk(req)->ir_num	   = ntohs(dccp_hdr(skb)->dccph_dport);
 	inet_rsk(req)->acked	   = 0;
-- 
2.1.0


From 2d39335a78023e3d865b5af5befd13896d7e127c Mon Sep 17 00:00:00 2001
From: Jarod Wilson <jarod@redhat.com>
Date: Mon, 6 Mar 2017 08:48:58 -0500
Subject: [PATCH 34/48] team: use ETH_MAX_MTU as max mtu

[ Upstream commit 3331aa378e9bcbd0d16de9034b0c20f4050e26b4 ]

This restores the ability to set a team device's mtu to anything higher
than 1500. Similar to the reported issue with bonding, the team driver
calls ether_setup(), which sets an initial max_mtu of 1500, while the
underlying hardware can handle something much larger. Just set it to
ETH_MAX_MTU to support all possible values, and the limitations of the
underlying devices will prevent setting anything too large.

Fixes: 91572088e3fd ("net: use core MTU range checking in core net infra")
CC: Cong Wang <xiyou.wangcong@gmail.com>
CC: Jiri Pirko <jiri@resnulli.us>
CC: netdev@vger.kernel.org
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index bdc5856..7073215 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -2075,6 +2075,7 @@ static int team_dev_type_check_change(struct net_device *dev,
 static void team_setup(struct net_device *dev)
 {
 	ether_setup(dev);
+	dev->max_mtu = ETH_MAX_MTU;
 
 	dev->netdev_ops = &team_netdev_ops;
 	dev->ethtool_ops = &team_ethtool_ops;
-- 
2.1.0


From 56b1a4735671838eee43bdfc3fe7f8af273413be Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Mon, 6 Mar 2017 08:53:04 -0800
Subject: [PATCH 35/48] vrf: Fix use-after-free in vrf_xmit

[ Upstream commit f7887d40e541f74402df0684a1463c0a0bb68c68 ]

KASAN detected a use-after-free:

[  269.467067] BUG: KASAN: use-after-free in vrf_xmit+0x7f1/0x827 [vrf] at addr ffff8800350a21c0
[  269.467067] Read of size 4 by task ssh/1879
[  269.467067] CPU: 1 PID: 1879 Comm: ssh Not tainted 4.10.0+ #249
[  269.467067] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.7.5-20140531_083030-gandalf 04/01/2014
[  269.467067] Call Trace:
[  269.467067]  dump_stack+0x81/0xb6
[  269.467067]  kasan_object_err+0x21/0x78
[  269.467067]  kasan_report+0x2f7/0x450
[  269.467067]  ? vrf_xmit+0x7f1/0x827 [vrf]
[  269.467067]  ? ip_output+0xa4/0xdb
[  269.467067]  __asan_load4+0x6b/0x6d
[  269.467067]  vrf_xmit+0x7f1/0x827 [vrf]
...

Which corresponds to the skb access after xmit handling. Fix by saving
skb->len and using the saved value to update stats.

Fixes: 193125dbd8eb2 ("net: Introduce VRF device driver")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 454f907..682aac0 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -341,6 +341,7 @@ static netdev_tx_t is_ip_tx_frame(struct sk_buff *skb, struct net_device *dev)
 
 static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev)
 {
+	int len = skb->len;
 	netdev_tx_t ret = is_ip_tx_frame(skb, dev);
 
 	if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) {
@@ -348,7 +349,7 @@ static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev)
 
 		u64_stats_update_begin(&dstats->syncp);
 		dstats->tx_pkts++;
-		dstats->tx_bytes += skb->len;
+		dstats->tx_bytes += len;
 		u64_stats_update_end(&dstats->syncp);
 	} else {
 		this_cpu_inc(dev->dstats->tx_drps);
-- 
2.1.0


From 8a1825613887c82a46b9bb6801ea421bcfe2776c Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 7 Mar 2017 18:33:31 +0100
Subject: [PATCH 36/48] net/tunnel: set inner protocol in network gro hooks

[ Upstream commit 294acf1c01bace5cea5d30b510504238bf5f7c25 ]

The gso code of several tunnels type (gre and udp tunnels)
takes for granted that the skb->inner_protocol is properly
initialized and drops the packet elsewhere.

On the forwarding path no one is initializing such field,
so gro encapsulated packets are dropped on forward.

Since commit 38720352412a ("gre: Use inner_proto to obtain
inner header protocol"), this can be reproduced when the
encapsulated packets use gre as the tunneling protocol.

The issue happens also with vxlan and geneve tunnels since
commit 8bce6d7d0d1e ("udp: Generalize skb_udp_segment"), if the
forwarding host's ingress nic has h/w offload for such tunnel
and a vxlan/geneve device is configured on top of it, regardless
of the configured peer address and vni.

To address the issue, this change initialize the inner_protocol
field for encapsulated packets in both ipv4 and ipv6 gro complete
callbacks.

Fixes: 38720352412a ("gre: Use inner_proto to obtain inner header protocol")
Fixes: 8bce6d7d0d1e ("udp: Generalize skb_udp_segment")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/af_inet.c     | 4 +++-
 net/ipv6/ip6_offload.c | 4 +++-
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index f750698..4391da9 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1470,8 +1470,10 @@ int inet_gro_complete(struct sk_buff *skb, int nhoff)
 	int proto = iph->protocol;
 	int err = -ENOSYS;
 
-	if (skb->encapsulation)
+	if (skb->encapsulation) {
+		skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IP));
 		skb_set_inner_network_header(skb, nhoff);
+	}
 
 	csum_replace2(&iph->check, iph->tot_len, newlen);
 	iph->tot_len = newlen;
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index fc7b401..33b04ec 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -294,8 +294,10 @@ static int ipv6_gro_complete(struct sk_buff *skb, int nhoff)
 	struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + nhoff);
 	int err = -ENOSYS;
 
-	if (skb->encapsulation)
+	if (skb->encapsulation) {
+		skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IPV6));
 		skb_set_inner_network_header(skb, nhoff);
+	}
 
 	iph->payload_len = htons(skb->len - nhoff - sizeof(*iph));
 
-- 
2.1.0


From c74d94ac145f12c14c4fbfee57669240c6427245 Mon Sep 17 00:00:00 2001
From: "Dmitry V. Levin" <ldv@altlinux.org>
Date: Tue, 7 Mar 2017 23:50:50 +0300
Subject: [PATCH 37/48] uapi: fix linux/packet_diag.h userspace compilation
 error

[ Upstream commit 745cb7f8a5de0805cade3de3991b7a95317c7c73 ]

Replace MAX_ADDR_LEN with its numeric value to fix the following
linux/packet_diag.h userspace compilation error:

/usr/include/linux/packet_diag.h:67:17: error: 'MAX_ADDR_LEN' undeclared here (not in a function)
  __u8 pdmc_addr[MAX_ADDR_LEN];

This is not the first case in the UAPI where the numeric value
of MAX_ADDR_LEN is used instead of symbolic one, uapi/linux/if_link.h
already does the same:

$ grep MAX_ADDR_LEN include/uapi/linux/if_link.h
	__u8 mac[32]; /* MAX_ADDR_LEN */

There are no UAPI headers besides these two that use MAX_ADDR_LEN.

Signed-off-by: Dmitry V. Levin <ldv@altlinux.org>
Acked-by: Pavel Emelyanov <xemul@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/packet_diag.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/uapi/linux/packet_diag.h b/include/uapi/linux/packet_diag.h
index d08c63f..0c5d5dd 100644
--- a/include/uapi/linux/packet_diag.h
+++ b/include/uapi/linux/packet_diag.h
@@ -64,7 +64,7 @@ struct packet_diag_mclist {
 	__u32	pdmc_count;
 	__u16	pdmc_type;
 	__u16	pdmc_alen;
-	__u8	pdmc_addr[MAX_ADDR_LEN];
+	__u8	pdmc_addr[32]; /* MAX_ADDR_LEN */
 };
 
 struct packet_diag_ring {
-- 
2.1.0


From 89f37bd894966e5542fa16a868050703742102c2 Mon Sep 17 00:00:00 2001
From: "Lendacky, Thomas" <Thomas.Lendacky@amd.com>
Date: Thu, 9 Mar 2017 17:48:23 -0600
Subject: [PATCH 38/48] amd-xgbe: Enable IRQs only if napi_complete_done() is
 true

[ Upstream commit d7aba644ffdebf756e51e26a2229055211838e89 ]

Depending on the hardware, the amd-xgbe driver may use disable_irq_nosync()
and enable_irq() when an interrupt is received to process Rx packets. If
the napi_complete_done() return value isn't checked an unbalanced enable
for the IRQ could result, generating a warning stack trace.

Update the driver to only enable interrupts if napi_complete_done() returns
true.

Reported-by: Jeremy Linton <jeremy.linton@arm.com>
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe-drv.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 0f4bbe1f..742e5d1b 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -2274,10 +2274,7 @@ static int xgbe_one_poll(struct napi_struct *napi, int budget)
 	processed = xgbe_rx_poll(channel, budget);
 
 	/* If we processed everything, we are done */
-	if (processed < budget) {
-		/* Turn off polling */
-		napi_complete_done(napi, processed);
-
+	if ((processed < budget) && napi_complete_done(napi, processed)) {
 		/* Enable Tx and Rx interrupts */
 		if (pdata->channel_irq_mode)
 			xgbe_enable_rx_tx_int(pdata, channel);
@@ -2319,10 +2316,7 @@ static int xgbe_all_poll(struct napi_struct *napi, int budget)
 	} while ((processed < budget) && (processed != last_processed));
 
 	/* If we processed everything, we are done */
-	if (processed < budget) {
-		/* Turn off polling */
-		napi_complete_done(napi, processed);
-
+	if ((processed < budget) && napi_complete_done(napi, processed)) {
 		/* Enable Tx and Rx interrupts */
 		xgbe_enable_rx_tx_ints(pdata);
 	}
-- 
2.1.0


From ea7b310766b31ab013f84f5ddd782a2f352466a7 Mon Sep 17 00:00:00 2001
From: Etienne Noss <etienne.noss@wifirst.fr>
Date: Fri, 10 Mar 2017 16:55:32 +0100
Subject: [PATCH 39/48] act_connmark: avoid crashing on malformed nlattrs with
 null parms
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 52491c7607c5527138095edf44c53169dc1ddb82 ]

tcf_connmark_init does not check in its configuration if TCA_CONNMARK_PARMS
is set, resulting in a null pointer dereference when trying to access it.

[501099.043007] BUG: unable to handle kernel NULL pointer dereference at 0000000000000004
[501099.043039] IP: [<ffffffffc10c60fb>] tcf_connmark_init+0x8b/0x180 [act_connmark]
...
[501099.044334] Call Trace:
[501099.044345]  [<ffffffffa47270e8>] ? tcf_action_init_1+0x198/0x1b0
[501099.044363]  [<ffffffffa47271b0>] ? tcf_action_init+0xb0/0x120
[501099.044380]  [<ffffffffa47250a4>] ? tcf_exts_validate+0xc4/0x110
[501099.044398]  [<ffffffffc0f5fa97>] ? u32_set_parms+0xa7/0x270 [cls_u32]
[501099.044417]  [<ffffffffc0f60bf0>] ? u32_change+0x680/0x87b [cls_u32]
[501099.044436]  [<ffffffffa4725d1d>] ? tc_ctl_tfilter+0x4dd/0x8a0
[501099.044454]  [<ffffffffa44a23a1>] ? security_capable+0x41/0x60
[501099.044471]  [<ffffffffa470ca01>] ? rtnetlink_rcv_msg+0xe1/0x220
[501099.044490]  [<ffffffffa470c920>] ? rtnl_newlink+0x870/0x870
[501099.044507]  [<ffffffffa472cc61>] ? netlink_rcv_skb+0xa1/0xc0
[501099.044524]  [<ffffffffa47073f4>] ? rtnetlink_rcv+0x24/0x30
[501099.044541]  [<ffffffffa472c634>] ? netlink_unicast+0x184/0x230
[501099.044558]  [<ffffffffa472c9d8>] ? netlink_sendmsg+0x2f8/0x3b0
[501099.044576]  [<ffffffffa46d8880>] ? sock_sendmsg+0x30/0x40
[501099.044592]  [<ffffffffa46d8e03>] ? SYSC_sendto+0xd3/0x150
[501099.044608]  [<ffffffffa425fda1>] ? __do_page_fault+0x2d1/0x510
[501099.044626]  [<ffffffffa47fbd7b>] ? system_call_fast_compare_end+0xc/0x9b

Fixes: 22a5dc0e5e3e ("net: sched: Introduce connmark action")
Signed-off-by: Étienne Noss <etienne.noss@wifirst.fr>
Signed-off-by: Victorien Molle <victorien.molle@wifirst.fr>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_connmark.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index ab80629..f9bb43c 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -113,6 +113,9 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla,
 	if (ret < 0)
 		return ret;
 
+	if (!tb[TCA_CONNMARK_PARMS])
+		return -EINVAL;
+
 	parm = nla_data(tb[TCA_CONNMARK_PARMS]);
 
 	if (!tcf_hash_check(tn, parm->index, a, bind)) {
-- 
2.1.0


From b9d5f900f6c4e236d6dc074dcbd47531df05c43f Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Fri, 10 Mar 2017 09:46:15 -0800
Subject: [PATCH 40/48] mpls: Send route delete notifications when router
 module is unloaded

[ Upstream commit e37791ec1ad785b59022ae211f63a16189bacebf ]

When the mpls_router module is unloaded, mpls routes are deleted but
notifications are not sent to userspace leaving userspace caches
out of sync. Add the call to mpls_notify_route in mpls_net_exit as
routes are freed.

Fixes: 0189197f44160 ("mpls: Basic routing support")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mpls/af_mpls.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 5b77377..2a21ff1 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -1696,6 +1696,7 @@ static void mpls_net_exit(struct net *net)
 	for (index = 0; index < platform_labels; index++) {
 		struct mpls_route *rt = rtnl_dereference(platform_label[index]);
 		RCU_INIT_POINTER(platform_label[index], NULL);
+		mpls_notify_route(net, index, rt, NULL, NULL);
 		mpls_rt_free(rt);
 	}
 	rtnl_unlock();
-- 
2.1.0


From c9492781e6efd77660fa9df78cebbd09892a1071 Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Fri, 10 Mar 2017 14:11:39 -0800
Subject: [PATCH 41/48] mpls: Do not decrement alive counter for unregister
 events

[ Upstream commit 79099aab38c8f5c746748b066ae74ba984fe2cc8 ]

Multipath routes can be rendered usesless when a device in one of the
paths is deleted. For example:

$ ip -f mpls ro ls
100
	nexthop as to 200 via inet 172.16.2.2  dev virt12
	nexthop as to 300 via inet 172.16.3.2  dev br0
101
	nexthop as to 201 via inet6 2000:2::2  dev virt12
	nexthop as to 301 via inet6 2000:3::2  dev br0

$ ip li del br0

When br0 is deleted the other hop is not considered in
mpls_select_multipath because of the alive check -- rt_nhn_alive
is 0.

rt_nhn_alive is decremented once in mpls_ifdown when the device is taken
down (NETDEV_DOWN) and again when it is deleted (NETDEV_UNREGISTER). For
a 2 hop route, deleting one device drops the alive count to 0. Since
devices are taken down before unregistering, the decrement on
NETDEV_UNREGISTER is redundant.

Fixes: c89359a42e2a4 ("mpls: support for dead routes")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mpls/af_mpls.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 2a21ff1..1309e2c 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -956,7 +956,8 @@ static void mpls_ifdown(struct net_device *dev, int event)
 				/* fall through */
 			case NETDEV_CHANGE:
 				nh->nh_flags |= RTNH_F_LINKDOWN;
-				ACCESS_ONCE(rt->rt_nhn_alive) = rt->rt_nhn_alive - 1;
+				if (event != NETDEV_UNREGISTER)
+					ACCESS_ONCE(rt->rt_nhn_alive) = rt->rt_nhn_alive - 1;
 				break;
 			}
 			if (event == NETDEV_UNREGISTER)
-- 
2.1.0


From 47d24acd0c1aea0b834ed58501e87bd7e9e33ae3 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Mon, 13 Mar 2017 13:28:09 +0100
Subject: [PATCH 42/48] ipv6: make ECMP route replacement less greedy

[ Upstream commit 67e194007be08d071294456274dd53e0a04fdf90 ]

Commit 27596472473a ("ipv6: fix ECMP route replacement") introduced a
loop that removes all siblings of an ECMP route that is being
replaced. However, this loop doesn't stop when it has replaced
siblings, and keeps removing other routes with a higher metric.
We also end up triggering the WARN_ON after the loop, because after
this nsiblings < 0.

Instead, stop the loop when we have taken care of all routes with the
same metric as the route being replaced.

  Reproducer:
  ===========
    #!/bin/sh

    ip netns add ns1
    ip netns add ns2
    ip -net ns1 link set lo up

    for x in 0 1 2 ; do
        ip link add veth$x netns ns2 type veth peer name eth$x netns ns1
        ip -net ns1 link set eth$x up
        ip -net ns2 link set veth$x up
    done

    ip -net ns1 -6 r a 2000::/64 nexthop via fe80::0 dev eth0 \
            nexthop via fe80::1 dev eth1 nexthop via fe80::2 dev eth2
    ip -net ns1 -6 r a 2000::/64 via fe80::42 dev eth0 metric 256
    ip -net ns1 -6 r a 2000::/64 via fe80::43 dev eth0 metric 2048

    echo "before replace, 3 routes"
    ip -net ns1 -6 r | grep -v '^fe80\|^ff00'
    echo

    ip -net ns1 -6 r c 2000::/64 nexthop via fe80::4 dev eth0 \
            nexthop via fe80::5 dev eth1 nexthop via fe80::6 dev eth2

    echo "after replace, only 2 routes, metric 2048 is gone"
    ip -net ns1 -6 r | grep -v '^fe80\|^ff00'

Fixes: 27596472473a ("ipv6: fix ECMP route replacement")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Reviewed-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_fib.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index ef54852..8c88a37 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -908,6 +908,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 			ins = &rt->dst.rt6_next;
 			iter = *ins;
 			while (iter) {
+				if (iter->rt6i_metric > rt->rt6i_metric)
+					break;
 				if (rt6_qualify_for_ecmp(iter)) {
 					*ins = iter->dst.rt6_next;
 					fib6_purge_rt(iter, fn, info->nl_net);
-- 
2.1.0


From e026035b8dc975f617f2790a9ee4a0c88c75d04a Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 13 Mar 2017 16:24:28 +0100
Subject: [PATCH 43/48] ipv6: avoid write to a possibly cloned skb

[ Upstream commit 79e49503efe53a8c51d8b695bedc8a346c5e4a87 ]

ip6_fragment, in case skb has a fraglist, checks if the
skb is cloned.  If it is, it will move to the 'slow path' and allocates
new skbs for each fragment.

However, right before entering the slowpath loop, it updates the
nexthdr value of the last ipv6 extension header to NEXTHDR_FRAGMENT,
to account for the fragment header that will be inserted in the new
ipv6-fragment skbs.

In case original skb is cloned this munges nexthdr value of another
skb.  Avoid this by doing the nexthdr update for each of the new fragment
skbs separately.

This was observed with tcpdump on a bridge device where netfilter ipv6
reassembly is active:  tcpdump shows malformed fragment headers as
the l4 header (icmpv6, tcp, etc). is decoded as a fragment header.

Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Reported-by: Andreas Karis <akaris@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_output.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 7cebee5..d57f4ee 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -767,13 +767,14 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 	 *	Fragment the datagram.
 	 */
 
-	*prevhdr = NEXTHDR_FRAGMENT;
 	troom = rt->dst.dev->needed_tailroom;
 
 	/*
 	 *	Keep copying data until we run out.
 	 */
 	while (left > 0)	{
+		u8 *fragnexthdr_offset;
+
 		len = left;
 		/* IF: it doesn't fit, use 'mtu' - the data space left */
 		if (len > mtu)
@@ -818,6 +819,10 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		 */
 		skb_copy_from_linear_data(skb, skb_network_header(frag), hlen);
 
+		fragnexthdr_offset = skb_network_header(frag);
+		fragnexthdr_offset += prevhdr - skb_network_header(skb);
+		*fragnexthdr_offset = NEXTHDR_FRAGMENT;
+
 		/*
 		 *	Build fragment header.
 		 */
-- 
2.1.0


From affda36e856d8d633d8e5ff5e82fbbd6af4dbd7e Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 13 Mar 2017 17:38:17 +0100
Subject: [PATCH 44/48] bridge: drop netfilter fake rtable unconditionally

[ Upstream commit a13b2082ece95247779b9995c4e91b4246bed023 ]

Andreas reports kernel oops during rmmod of the br_netfilter module.
Hannes debugged the oops down to a NULL rt6info->rt6i_indev.

Problem is that br_netfilter has the nasty concept of adding a fake
rtable to skb->dst; this happens in a br_netfilter prerouting hook.

A second hook (in bridge LOCAL_IN) is supposed to remove these again
before the skb is handed up the stack.

However, on module unload hooks get unregistered which means an
skb could traverse the prerouting hook that attaches the fake_rtable,
while the 'fake rtable remove' hook gets removed from the hooklist
immediately after.

Fixes: 34666d467cbf1e2e3c7 ("netfilter: bridge: move br_netfilter out of the core")
Reported-by: Andreas Karis <akaris@redhat.com>
Debugged-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_input.c           |  1 +
 net/bridge/br_netfilter_hooks.c | 21 ---------------------
 2 files changed, 1 insertion(+), 21 deletions(-)

diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 855b72f..267b46a 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -29,6 +29,7 @@ EXPORT_SYMBOL(br_should_route_hook);
 static int
 br_netif_receive_skb(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
+	br_drop_fake_rtable(skb);
 	return netif_receive_skb(skb);
 }
 
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 95087e6..fa87fbd 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -521,21 +521,6 @@ static unsigned int br_nf_pre_routing(void *priv,
 }
 
 
-/* PF_BRIDGE/LOCAL_IN ************************************************/
-/* The packet is locally destined, which requires a real
- * dst_entry, so detach the fake one.  On the way up, the
- * packet would pass through PRE_ROUTING again (which already
- * took place when the packet entered the bridge), but we
- * register an IPv4 PRE_ROUTING 'sabotage' hook that will
- * prevent this from happening. */
-static unsigned int br_nf_local_in(void *priv,
-				   struct sk_buff *skb,
-				   const struct nf_hook_state *state)
-{
-	br_drop_fake_rtable(skb);
-	return NF_ACCEPT;
-}
-
 /* PF_BRIDGE/FORWARD *************************************************/
 static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
@@ -908,12 +893,6 @@ static struct nf_hook_ops br_nf_ops[] __read_mostly = {
 		.priority = NF_BR_PRI_BRNF,
 	},
 	{
-		.hook = br_nf_local_in,
-		.pf = NFPROTO_BRIDGE,
-		.hooknum = NF_BR_LOCAL_IN,
-		.priority = NF_BR_PRI_BRNF,
-	},
-	{
 		.hook = br_nf_forward_ip,
 		.pf = NFPROTO_BRIDGE,
 		.hooknum = NF_BR_FORWARD,
-- 
2.1.0


From eb69dec736379600f489d0a6f99f20814c69e833 Mon Sep 17 00:00:00 2001
From: Andrey Vagin <avagin@openvz.org>
Date: Sun, 12 Mar 2017 21:36:18 -0700
Subject: [PATCH 45/48] net: use net->count to check whether a netns is alive
 or not
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 91864f5852f9996210fad400cf70fb85af091243 ]

The previous idea was to check whether a net namespace is in
net_exit_list or not. It doesn't work, because net->exit_list is used in
__register_pernet_operations and __unregister_pernet_operations where
all namespaces are added to a temporary list to make cleanup in a error
case, so list_empty(&net->exit_list) always returns false.

Reported-by: Mantas Mikulėnas <grawity@gmail.com>
Fixes: 002d8a1a6c11 ("net: skip genenerating uevents for network namespaces that are exiting")
Signed-off-by: Andrei Vagin <avagin@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/net-sysfs.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index b0c04cf..1004418 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -952,7 +952,7 @@ net_rx_queue_update_kobjects(struct net_device *dev, int old_num, int new_num)
 	while (--i >= new_num) {
 		struct kobject *kobj = &dev->_rx[i].kobj;
 
-		if (!list_empty(&dev_net(dev)->exit_list))
+		if (!atomic_read(&dev_net(dev)->count))
 			kobj->uevent_suppress = 1;
 		if (dev->sysfs_rx_queue_group)
 			sysfs_remove_group(kobj, dev->sysfs_rx_queue_group);
@@ -1370,7 +1370,7 @@ netdev_queue_update_kobjects(struct net_device *dev, int old_num, int new_num)
 	while (--i >= new_num) {
 		struct netdev_queue *queue = dev->_tx + i;
 
-		if (!list_empty(&dev_net(dev)->exit_list))
+		if (!atomic_read(&dev_net(dev)->count))
 			queue->kobj.uevent_suppress = 1;
 #ifdef CONFIG_BQL
 		sysfs_remove_group(&queue->kobj, &dql_group);
@@ -1557,7 +1557,7 @@ void netdev_unregister_kobject(struct net_device *ndev)
 {
 	struct device *dev = &(ndev->dev);
 
-	if (!list_empty(&dev_net(ndev)->exit_list))
+	if (!atomic_read(&dev_net(ndev)->count))
 		dev_set_uevent_suppress(dev, 1);
 
 	kobject_get(&dev->kobj);
-- 
2.1.0


From 05276193f690054ef3fe9d3dbc8ad09fde187fdb Mon Sep 17 00:00:00 2001
From: Jon Maxwell <jmaxwell37@gmail.com>
Date: Fri, 10 Mar 2017 16:40:33 +1100
Subject: [PATCH 46/48] dccp/tcp: fix routing redirect race
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 45caeaa5ac0b4b11784ac6f932c0ad4c6b67cda0 ]

As Eric Dumazet pointed out this also needs to be fixed in IPv6.
v2: Contains the IPv6 tcp/Ipv6 dccp patches as well.

We have seen a few incidents lately where a dst_enty has been freed
with a dangling TCP socket reference (sk->sk_dst_cache) pointing to that
dst_entry. If the conditions/timings are right a crash then ensues when the
freed dst_entry is referenced later on. A Common crashing back trace is:

 #8 [] page_fault at ffffffff8163e648
    [exception RIP: __tcp_ack_snd_check+74]
.
.
 #9 [] tcp_rcv_established at ffffffff81580b64
#10 [] tcp_v4_do_rcv at ffffffff8158b54a
#11 [] tcp_v4_rcv at ffffffff8158cd02
#12 [] ip_local_deliver_finish at ffffffff815668f4
#13 [] ip_local_deliver at ffffffff81566bd9
#14 [] ip_rcv_finish at ffffffff8156656d
#15 [] ip_rcv at ffffffff81566f06
#16 [] __netif_receive_skb_core at ffffffff8152b3a2
#17 [] __netif_receive_skb at ffffffff8152b608
#18 [] netif_receive_skb at ffffffff8152b690
#19 [] vmxnet3_rq_rx_complete at ffffffffa015eeaf [vmxnet3]
#20 [] vmxnet3_poll_rx_only at ffffffffa015f32a [vmxnet3]
#21 [] net_rx_action at ffffffff8152bac2
#22 [] __do_softirq at ffffffff81084b4f
#23 [] call_softirq at ffffffff8164845c
#24 [] do_softirq at ffffffff81016fc5
#25 [] irq_exit at ffffffff81084ee5
#26 [] do_IRQ at ffffffff81648ff8

Of course it may happen with other NIC drivers as well.

It's found the freed dst_entry here:

 224 static bool tcp_in_quickack_mode(struct sock *sk)↩
 225 {↩
 226 ▹       const struct inet_connection_sock *icsk = inet_csk(sk);↩
 227 ▹       const struct dst_entry *dst = __sk_dst_get(sk);↩
 228 ↩
 229 ▹       return (dst && dst_metric(dst, RTAX_QUICKACK)) ||↩
 230 ▹       ▹       (icsk->icsk_ack.quick && !icsk->icsk_ack.pingpong);↩
 231 }↩

But there are other backtraces attributed to the same freed dst_entry in
netfilter code as well.

All the vmcores showed 2 significant clues:

- Remote hosts behind the default gateway had always been redirected to a
different gateway. A rtable/dst_entry will be added for that host. Making
more dst_entrys with lower reference counts. Making this more probable.

- All vmcores showed a postitive LockDroppedIcmps value, e.g:

LockDroppedIcmps                  267

A closer look at the tcp_v4_err() handler revealed that do_redirect() will run
regardless of whether user space has the socket locked. This can result in a
race condition where the same dst_entry cached in sk->sk_dst_entry can be
decremented twice for the same socket via:

do_redirect()->__sk_dst_check()-> dst_release().

Which leads to the dst_entry being prematurely freed with another socket
pointing to it via sk->sk_dst_cache and a subsequent crash.

To fix this skip do_redirect() if usespace has the socket locked. Instead let
the redirect take place later when user space does not have the socket
locked.

The dccp/IPv6 code is very similar in this respect, so fixing it there too.

As Eric Garver pointed out the following commit now invalidates routes. Which
can set the dst->obsolete flag so that ipv4_dst_check() returns null and
triggers the dst_release().

Fixes: ceb3320610d6 ("ipv4: Kill routes during PMTU/redirect updates.")
Cc: Eric Garver <egarver@redhat.com>
Cc: Hannes Sowa <hsowa@redhat.com>
Signed-off-by: Jon Maxwell <jmaxwell37@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ipv4.c     | 3 ++-
 net/dccp/ipv6.c     | 8 +++++---
 net/ipv4/tcp_ipv4.c | 3 ++-
 net/ipv6/tcp_ipv6.c | 8 +++++---
 4 files changed, 14 insertions(+), 8 deletions(-)

diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index d859a5c..b0a1ba9 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -289,7 +289,8 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
 
 	switch (type) {
 	case ICMP_REDIRECT:
-		dccp_do_redirect(skb, sk);
+		if (!sock_owned_by_user(sk))
+			dccp_do_redirect(skb, sk);
 		goto out;
 	case ICMP_SOURCE_QUENCH:
 		/* Just silently ignore these. */
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index c4e879c..2f3e8bb 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -122,10 +122,12 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	np = inet6_sk(sk);
 
 	if (type == NDISC_REDIRECT) {
-		struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
+		if (!sock_owned_by_user(sk)) {
+			struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
 
-		if (dst)
-			dst->ops->redirect(dst, sk, skb);
+			if (dst)
+				dst->ops->redirect(dst, sk, skb);
+		}
 		goto out;
 	}
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 90c1d78..bb629dc 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -421,7 +421,8 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 
 	switch (type) {
 	case ICMP_REDIRECT:
-		do_redirect(icmp_skb, sk);
+		if (!sock_owned_by_user(sk))
+			do_redirect(icmp_skb, sk);
 		goto out;
 	case ICMP_SOURCE_QUENCH:
 		/* Just silently ignore these. */
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 4c60c6f..cfc2327 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -382,10 +382,12 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	np = inet6_sk(sk);
 
 	if (type == NDISC_REDIRECT) {
-		struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
+		if (!sock_owned_by_user(sk)) {
+			struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
 
-		if (dst)
-			dst->ops->redirect(dst, sk, skb);
+			if (dst)
+				dst->ops->redirect(dst, sk, skb);
+		}
 		goto out;
 	}
 
-- 
2.1.0


From 40e75e08ed5a5a1a49fbbdf86ea481d13db00591 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Mon, 13 Mar 2017 00:00:26 +0100
Subject: [PATCH 47/48] tun: fix premature POLLOUT notification on tun devices
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit b20e2d54789c6acbf6bd0efdbec2cf5fa4d90ef1 ]

aszlig observed failing ssh tunnels (-w) during initialization since
commit cc9da6cc4f56e0 ("ipv6: addrconf: use stable address generator for
ARPHRD_NONE"). We already had reports that the mentioned commit breaks
Juniper VPN connections. I can't clearly say that the Juniper VPN client
has the same problem, but it is worth a try to hint to this patch.

Because of the early generation of link local addresses, the kernel now
can start asking for routers on the local subnet much earlier than usual.
Those router solicitation packets arrive inside the ssh channels and
should be transmitted to the tun fd before the configuration scripts
might have upped the interface and made it ready for transmission.

ssh polls on the interface and receives back a POLL_OUT. It tries to send
the earily router solicitation packet to the tun interface.  Unfortunately
it hasn't been up'ed yet by config scripts, thus failing with -EIO. ssh
doesn't retry again and considers the tun interface broken forever.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=121131
Fixes: cc9da6cc4f56 ("ipv6: addrconf: use stable address generator for ARPHRD_NONE")
Cc: Bjørn Mork <bjorn@mork.no>
Reported-by: Valdis Kletnieks <Valdis.Kletnieks@vt.edu>
Cc: Valdis Kletnieks <Valdis.Kletnieks@vt.edu>
Reported-by: Jonas Lippuner <jonas@lippuner.ca>
Cc: Jonas Lippuner <jonas@lippuner.ca>
Reported-by: aszlig <aszlig@redmoonstudios.org>
Cc: aszlig <aszlig@redmoonstudios.org>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index bfabe18..cdf6339 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -819,7 +819,18 @@ static void tun_net_uninit(struct net_device *dev)
 /* Net device open. */
 static int tun_net_open(struct net_device *dev)
 {
+	struct tun_struct *tun = netdev_priv(dev);
+	int i;
+
 	netif_tx_start_all_queues(dev);
+
+	for (i = 0; i < tun->numqueues; i++) {
+		struct tun_file *tfile;
+
+		tfile = rtnl_dereference(tun->tfiles[i]);
+		tfile->socket.sk->sk_write_space(tfile->socket.sk);
+	}
+
 	return 0;
 }
 
@@ -1101,9 +1112,10 @@ static unsigned int tun_chr_poll(struct file *file, poll_table *wait)
 	if (!skb_array_empty(&tfile->tx_array))
 		mask |= POLLIN | POLLRDNORM;
 
-	if (sock_writeable(sk) ||
-	    (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) &&
-	     sock_writeable(sk)))
+	if (tun->dev->flags & IFF_UP &&
+	    (sock_writeable(sk) ||
+	     (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) &&
+	      sock_writeable(sk))))
 		mask |= POLLOUT | POLLWRNORM;
 
 	if (tun->dev->reg_state != NETREG_REGISTERED)
-- 
2.1.0


From 66d6c1fb438863272d8ff9df865e615dab57c6b0 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Mon, 13 Mar 2017 00:01:30 +0100
Subject: [PATCH 48/48] dccp: fix memory leak during tear-down of unsuccessful
 connection request

[ Upstream commit 72ef9c4125c7b257e3a714d62d778ab46583d6a3 ]

This patch fixes a memory leak, which happens if the connection request
is not fulfilled between parsing the DCCP options and handling the SYN
(because e.g. the backlog is full), because we forgot to free the
list of ack vectors.

Reported-by: Jianwen Ji <jiji@redhat.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ccids/ccid2.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c
index f053198..5e3a730 100644
--- a/net/dccp/ccids/ccid2.c
+++ b/net/dccp/ccids/ccid2.c
@@ -749,6 +749,7 @@ static void ccid2_hc_tx_exit(struct sock *sk)
 	for (i = 0; i < hc->tx_seqbufc; i++)
 		kfree(hc->tx_seqbuf[i]);
 	hc->tx_seqbufc = 0;
+	dccp_ackvec_parsed_cleanup(&hc->tx_av_chunks);
 }
 
 static void ccid2_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb)
-- 
2.1.0

Re: [PATCHES] Networking

[Greg KH]

On Thu, Mar 16, 2017 at 06:48:04PM -0700, David Miller wrote:
> 
> Please queue up the following bug fixes for v4.9 and v4.10 -stable,
> respectively.

Many thanks for these, all now queued up!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 92 bytes --]


Please queue up the following bug fixes for v4.9 and v4.10 -stable,
respectively.

Thanks!

[-- Attachment #2: net_49.mbox --]
[-- Type: Application/Octet-Stream, Size: 409918 bytes --]

From 9e354abf9ce35fbce434b99f0f4ab292152049af Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Wed, 22 Feb 2017 17:20:12 +0200
Subject: [PATCH 001/112] net/mlx5e: Register/unregister vport representors on
 interface attach/detach

[ Upstream commit 6f08a22c5fb2b9aefb8ecd8496758e7a677c1fde ]

Currently vport representors are added only on driver load and removed on
driver unload.  Apparently we forgot to handle them when we added the
seamless reset flow feature.  This caused to leave the representors
netdevs alive and active with open HW resources on pci shutdown and on
error reset flows.

To overcome this we move their handling to interface attach/detach, so
they would be cleaned up on shutdown and recreated on reset flows.

Fixes: 26e59d8077a3 ("net/mlx5e: Implement mlx5e interface attach/detach callbacks")
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Hadar Hen Zion <hadarh@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 23 +++++++++++++++--------
 1 file changed, 15 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index b3067137..8657b3b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3936,6 +3936,19 @@ static void mlx5e_register_vport_rep(struct mlx5_core_dev *mdev)
 	}
 }
 
+static void mlx5e_unregister_vport_rep(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_eswitch *esw = mdev->priv.eswitch;
+	int total_vfs = MLX5_TOTAL_VPORTS(mdev);
+	int vport;
+
+	if (!MLX5_CAP_GEN(mdev, vport_group_manager))
+		return;
+
+	for (vport = 1; vport < total_vfs; vport++)
+		mlx5_eswitch_unregister_vport_rep(esw, vport);
+}
+
 void mlx5e_detach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -3983,6 +3996,7 @@ static int mlx5e_attach(struct mlx5_core_dev *mdev, void *vpriv)
 		return err;
 	}
 
+	mlx5e_register_vport_rep(mdev);
 	return 0;
 }
 
@@ -3994,6 +4008,7 @@ static void mlx5e_detach(struct mlx5_core_dev *mdev, void *vpriv)
 	if (!netif_device_present(netdev))
 		return;
 
+	mlx5e_unregister_vport_rep(mdev);
 	mlx5e_detach_netdev(mdev, netdev);
 	mlx5e_destroy_mdev_resources(mdev);
 }
@@ -4012,8 +4027,6 @@ static void *mlx5e_add(struct mlx5_core_dev *mdev)
 	if (err)
 		return NULL;
 
-	mlx5e_register_vport_rep(mdev);
-
 	if (MLX5_CAP_GEN(mdev, vport_group_manager))
 		ppriv = &esw->offloads.vport_reps[0];
 
@@ -4065,13 +4078,7 @@ void mlx5e_destroy_netdev(struct mlx5_core_dev *mdev, struct mlx5e_priv *priv)
 
 static void mlx5e_remove(struct mlx5_core_dev *mdev, void *vpriv)
 {
-	struct mlx5_eswitch *esw = mdev->priv.eswitch;
-	int total_vfs = MLX5_TOTAL_VPORTS(mdev);
 	struct mlx5e_priv *priv = vpriv;
-	int vport;
-
-	for (vport = 1; vport < total_vfs; vport++)
-		mlx5_eswitch_unregister_vport_rep(esw, vport);
 
 	unregister_netdev(priv->netdev);
 	mlx5e_detach(mdev, vpriv);
-- 
2.1.0


From a63326646995ffeacea6517c89cd178abb2c2af8 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Wed, 22 Feb 2017 17:20:13 +0200
Subject: [PATCH 002/112] net/mlx5e: Do not reduce LRO WQE size when not using
 build_skb

[ Upstream commit 4078e637c12f1e0a74293f1ec9563f42bff14a03 ]

When rq_type is Striding RQ, no room of SKB_RESERVE is needed
as SKB allocation is not done via build_skb.

Fixes: e4b85508072b ("net/mlx5e: Slightly reduce hardware LRO size")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 8657b3b..d4fa851 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -81,6 +81,7 @@ static bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
 static void mlx5e_set_rq_type_params(struct mlx5e_priv *priv, u8 rq_type)
 {
 	priv->params.rq_wq_type = rq_type;
+	priv->params.lro_wqe_sz = MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ;
 	switch (priv->params.rq_wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
 		priv->params.log_rq_size = MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE_MPW;
@@ -92,6 +93,10 @@ static void mlx5e_set_rq_type_params(struct mlx5e_priv *priv, u8 rq_type)
 		break;
 	default: /* MLX5_WQ_TYPE_LINKED_LIST */
 		priv->params.log_rq_size = MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE;
+
+		/* Extra room needed for build_skb */
+		priv->params.lro_wqe_sz -= MLX5_RX_HEADROOM +
+			SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 	}
 	priv->params.min_rx_wqes = mlx5_min_rx_wqes(priv->params.rq_wq_type,
 					       BIT(priv->params.log_rq_size));
@@ -3473,12 +3478,6 @@ static void mlx5e_build_nic_netdev_priv(struct mlx5_core_dev *mdev,
 	mlx5e_build_default_indir_rqt(mdev, priv->params.indirection_rqt,
 				      MLX5E_INDIR_RQT_SIZE, profile->max_nch(mdev));
 
-	priv->params.lro_wqe_sz =
-		MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ -
-		/* Extra room needed for build_skb */
-		MLX5_RX_HEADROOM -
-		SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-
 	/* Initialize pflags */
 	MLX5E_SET_PRIV_FLAG(priv, MLX5E_PFLAG_RX_CQE_BASED_MODER,
 			    priv->params.rx_cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE);
-- 
2.1.0


From 0c6e38e791e94ae0b2a773ea7262688719072316 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Wed, 22 Feb 2017 17:20:16 +0200
Subject: [PATCH 003/112] net/mlx5e: Fix wrong CQE decompression

[ Upstream commit 36154be40a28e4afaa0416da2681d80b7e2ca319 ]

In cqe compression with striding RQ, the decompression of the CQE field
wqe_counter was done with a wrong wraparound value.
This caused handling cqes with a wrong pointer to wqe (rx descriptor)
and creating SKBs with wrong data, pointing to wrong (and already consumed)
strides/pages.

The meaning of the CQE field wqe_counter in striding RQ holds the
stride index instead of the WQE index. Hence, when decompressing
a CQE, wqe_counter should have wrapped-around the number of strides
in a single multi-packet WQE.

We dropped this wrap-around mask at all in CQE decompression of striding
RQ. It is not needed as in such cases the CQE compression session would
break because of different value of wqe_id field, starting a new
compression session.

Tested:
 ethtool -K ethxx lro off/on
 ethtool --set-priv-flags ethxx rx_cqe_compress on
 super_netperf 16 {ipv4,ipv6} -t TCP_STREAM -m 50 -D
 verified no csum errors and no page refcount issues.

Fixes: 7219ab34f184 ("net/mlx5e: CQE compression")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reported-by: Tom Herbert <tom@herbertland.com>
Cc: kernel-team@fb.com
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index e7b2158..796bdf0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -92,19 +92,18 @@ static inline void mlx5e_cqes_update_owner(struct mlx5e_cq *cq, u32 cqcc, int n)
 static inline void mlx5e_decompress_cqe(struct mlx5e_rq *rq,
 					struct mlx5e_cq *cq, u32 cqcc)
 {
-	u16 wqe_cnt_step;
-
 	cq->title.byte_cnt     = cq->mini_arr[cq->mini_arr_idx].byte_cnt;
 	cq->title.check_sum    = cq->mini_arr[cq->mini_arr_idx].checksum;
 	cq->title.op_own      &= 0xf0;
 	cq->title.op_own      |= 0x01 & (cqcc >> cq->wq.log_sz);
 	cq->title.wqe_counter  = cpu_to_be16(cq->decmprs_wqe_counter);
 
-	wqe_cnt_step =
-		rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ ?
-		mpwrq_get_cqe_consumed_strides(&cq->title) : 1;
-	cq->decmprs_wqe_counter =
-		(cq->decmprs_wqe_counter + wqe_cnt_step) & rq->wq.sz_m1;
+	if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
+		cq->decmprs_wqe_counter +=
+			mpwrq_get_cqe_consumed_strides(&cq->title);
+	else
+		cq->decmprs_wqe_counter =
+			(cq->decmprs_wqe_counter + 1) & rq->wq.sz_m1;
 }
 
 static inline void mlx5e_decompress_cqe_no_hash(struct mlx5e_rq *rq,
-- 
2.1.0


From ee2da79de289d062c9c3a5714b3f4d37fa6c868f Mon Sep 17 00:00:00 2001
From: Matthias Schiffer <mschiffer@universe-factory.net>
Date: Thu, 23 Feb 2017 17:19:41 +0100
Subject: [PATCH 004/112] vxlan: correctly validate VXLAN ID against
 VXLAN_N_VID

[ Upstream commit 4e37d6911f36545b286d15073f6f2222f840e81c ]

The incorrect check caused an off-by-one error: the maximum VID 0xffffff
was unusable.

Fixes: d342894c5d2f ("vxlan: virtual extensible lan")
Signed-off-by: Matthias Schiffer <mschiffer@universe-factory.net>
Acked-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/net/vxlan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index d4f495b..7e3b2e2 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2637,7 +2637,7 @@ static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[])
 
 	if (data[IFLA_VXLAN_ID]) {
 		__u32 id = nla_get_u32(data[IFLA_VXLAN_ID]);
-		if (id >= VXLAN_VID_MASK)
+		if (id >= VXLAN_N_VID)
 			return -ERANGE;
 	}
 
-- 
2.1.0


From f7081057d12c0cb50a84869bae03fb9d406037f0 Mon Sep 17 00:00:00 2001
From: David Forster <dforster@brocade.com>
Date: Fri, 24 Feb 2017 14:20:32 +0000
Subject: [PATCH 005/112] vti6: return GRE_KEY for vti6

[ Upstream commit 7dcdf941cdc96692ab99fd790c8cc68945514851 ]

Align vti6 with vti by returning GRE_KEY flag. This enables iproute2
to display tunnel keys on "ip -6 tunnel show"

Signed-off-by: David Forster <dforster@brocade.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/ipv6/ip6_vti.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index c299c1e..66c2b4b 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -691,6 +691,10 @@ vti6_parm_to_user(struct ip6_tnl_parm2 *u, const struct __ip6_tnl_parm *p)
 	u->link = p->link;
 	u->i_key = p->i_key;
 	u->o_key = p->o_key;
+	if (u->i_key)
+		u->i_flags |= GRE_KEY;
+	if (u->o_key)
+		u->o_flags |= GRE_KEY;
 	u->proto = p->proto;
 
 	memcpy(u->name, p->name, sizeof(u->name));
-- 
2.1.0


From a64407fafe09ca33b09aabd49c5d526b1b6b7528 Mon Sep 17 00:00:00 2001
From: Brian Russell <brussell@brocade.com>
Date: Fri, 24 Feb 2017 17:47:11 +0000
Subject: [PATCH 006/112] vxlan: don't allow overwrite of config src addr

[ Upstream commit 1158632b5a2dcce0786c1b1b99654e81cc867981 ]

When using IPv6 transport and a default dst, a pointer to the configured
source address is passed into the route lookup. If no source address is
configured, then the value is overwritten.

IPv6 route lookup ignores egress ifindex match if the source address is set,
so if egress ifindex match is desired, the source address must be passed
as any. The overwrite breaks this for subsequent lookups.

Avoid this by copying the configured address to an existing stack variable
and pass a pointer to that instead.

Fixes: 272d96a5ab10 ("net: vxlan: lwt: Use source ip address during route lookup.")

Signed-off-by: Brian Russell <brussell@brocade.com>
Acked-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/net/vxlan.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 7e3b2e2..ac3f8d5 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1942,7 +1942,6 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 	const struct iphdr *old_iph;
 	union vxlan_addr *dst;
 	union vxlan_addr remote_ip, local_ip;
-	union vxlan_addr *src;
 	struct vxlan_metadata _md;
 	struct vxlan_metadata *md = &_md;
 	__be16 src_port = 0, dst_port;
@@ -1960,7 +1959,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		dst_port = rdst->remote_port ? rdst->remote_port : vxlan->cfg.dst_port;
 		vni = rdst->remote_vni;
 		dst = &rdst->remote_ip;
-		src = &vxlan->cfg.saddr;
+		local_ip = vxlan->cfg.saddr;
 		dst_cache = &rdst->dst_cache;
 	} else {
 		if (!info) {
@@ -1979,7 +1978,6 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 			local_ip.sin6.sin6_addr = info->key.u.ipv6.src;
 		}
 		dst = &remote_ip;
-		src = &local_ip;
 		dst_cache = &info->dst_cache;
 	}
 
@@ -2028,7 +2026,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		rt = vxlan_get_route(vxlan, skb,
 				     rdst ? rdst->remote_ifindex : 0, tos,
 				     dst->sin.sin_addr.s_addr,
-				     &src->sin.sin_addr.s_addr,
+				     &local_ip.sin.sin_addr.s_addr,
 				     dst_cache, info);
 		if (IS_ERR(rt)) {
 			netdev_dbg(dev, "no route to %pI4\n",
@@ -2071,7 +2069,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		if (err < 0)
 			goto xmit_tx_error;
 
-		udp_tunnel_xmit_skb(rt, sk, skb, src->sin.sin_addr.s_addr,
+		udp_tunnel_xmit_skb(rt, sk, skb, local_ip.sin.sin_addr.s_addr,
 				    dst->sin.sin_addr.s_addr, tos, ttl, df,
 				    src_port, dst_port, xnet, !udp_sum);
 #if IS_ENABLED(CONFIG_IPV6)
@@ -2087,7 +2085,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		ndst = vxlan6_get_route(vxlan, skb,
 					rdst ? rdst->remote_ifindex : 0, tos,
 					label, &dst->sin6.sin6_addr,
-					&src->sin6.sin6_addr,
+					&local_ip.sin6.sin6_addr,
 					dst_cache, info);
 		if (IS_ERR(ndst)) {
 			netdev_dbg(dev, "no route to %pI6\n",
@@ -2134,7 +2132,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 			return;
 		}
 		udp_tunnel6_xmit_skb(ndst, sk, skb, dev,
-				     &src->sin6.sin6_addr,
+				     &local_ip.sin6.sin6_addr,
 				     &dst->sin6.sin6_addr, tos, ttl,
 				     label, src_port, dst_port, !udp_sum);
 #endif
-- 
2.1.0


From 36931eb015ee44fe2c8f220b46500b25f7282442 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Sun, 26 Feb 2017 17:14:35 +0200
Subject: [PATCH 007/112] ipv4: mask tos for input route

[ Upstream commit 6e28099d38c0e50d62c1afc054e37e573adf3d21 ]

Restore the lost masking of TOS in input route code to
allow ip rules to match it properly.

Problem [1] noticed by Shmulik Ladkani <shmulik.ladkani@gmail.com>

[1] http://marc.info/?t=137331755300040&r=1&w=2

Fixes: 89aef8921bfb ("ipv4: Delete routing cache.")
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/ipv4/route.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d851cae..17e6fbf 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1968,6 +1968,7 @@ int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 {
 	int res;
 
+	tos &= IPTOS_RT_MASK;
 	rcu_read_lock();
 
 	/* Multicast recognition logic is moved from route cache to here.
-- 
2.1.0


From 063893e4ec88c253ff52a8e8486169fcf5e2d840 Mon Sep 17 00:00:00 2001
From: Roman Mashak <mrv@mojatatu.com>
Date: Fri, 24 Feb 2017 11:00:32 -0500
Subject: [PATCH 008/112] net sched actions: decrement module reference count
 after table flush.

[ Upstream commit edb9d1bff4bbe19b8ae0e71b1f38732591a9eeb2 ]

When tc actions are loaded as a module and no actions have been installed,
flushing them would result in actions removed from the memory, but modules
reference count not being decremented, so that the modules would not be
unloaded.

Following is example with GACT action:

% sudo modprobe act_gact
% lsmod
Module                  Size  Used by
act_gact               16384  0
%
% sudo tc actions ls action gact
%
% sudo tc actions flush action gact
% lsmod
Module                  Size  Used by
act_gact               16384  1
% sudo tc actions flush action gact
% lsmod
Module                  Size  Used by
act_gact               16384  2
% sudo rmmod act_gact
rmmod: ERROR: Module act_gact is in use
....

After the fix:
% lsmod
Module                  Size  Used by
act_gact               16384  0
%
% sudo tc actions add action pass index 1
% sudo tc actions add action pass index 2
% sudo tc actions add action pass index 3
% lsmod
Module                  Size  Used by
act_gact               16384  3
%
% sudo tc actions flush action gact
% lsmod
Module                  Size  Used by
act_gact               16384  0
%
% sudo tc actions flush action gact
% lsmod
Module                  Size  Used by
act_gact               16384  0
% sudo rmmod act_gact
% lsmod
Module                  Size  Used by
%

Fixes: f97017cdefef ("net-sched: Fix actions flushing")
Signed-off-by: Roman Mashak <mrv@mojatatu.com>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/sched/act_api.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index c6c2a93..c651cfc 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -820,10 +820,8 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
 		goto out_module_put;
 
 	err = ops->walk(net, skb, &dcb, RTM_DELACTION, ops);
-	if (err < 0)
+	if (err <= 0)
 		goto out_module_put;
-	if (err == 0)
-		goto noflush_out;
 
 	nla_nest_end(skb, nest);
 
@@ -840,7 +838,6 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
 out_module_put:
 	module_put(ops->owner);
 err_out:
-noflush_out:
 	kfree_skb(skb);
 	return err;
 }
-- 
2.1.0


From 837786cbbb60f00770b02efd15546b36008b536e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Paul=20H=C3=BCber?= <phueber@kernsp.in>
Date: Sun, 26 Feb 2017 17:58:19 +0100
Subject: [PATCH 009/112] l2tp: avoid use-after-free caused by
 l2tp_ip_backlog_recv
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 51fb60eb162ab84c5edf2ae9c63cf0b878e5547e ]

l2tp_ip_backlog_recv may not return -1 if the packet gets dropped.
The return value is passed up to ip_local_deliver_finish, which treats
negative values as an IP protocol number for resubmission.

Signed-off-by: Paul Hüber <phueber@kernsp.in>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/l2tp/l2tp_ip.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index c0f0750..ff750bb 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -388,7 +388,7 @@ static int l2tp_ip_backlog_recv(struct sock *sk, struct sk_buff *skb)
 drop:
 	IP_INC_STATS(sock_net(sk), IPSTATS_MIB_INDISCARDS);
 	kfree_skb(skb);
-	return -1;
+	return 0;
 }
 
 /* Userspace will call sendmsg() on the tunnel socket to send L2TP
-- 
2.1.0


From feaa5bab43350b95428dc01cf1f064305e72dd87 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 20 Jan 2017 15:31:52 -0800
Subject: [PATCH 010/112] net: phy: Avoid deadlock during phy_error()

[ Upstream commit eab127717a6af54401ba534790c793ec143cd1fc ]

phy_error() is called in the PHY state machine workqueue context, and
calls phy_trigger_machine() which does a cancel_delayed_work_sync() of
the workqueue we execute from, causing a deadlock situation.

Augment phy_trigger_machine() machine with a sync boolean indicating
whether we should use cancel_*_sync() or just cancel_*_work().

Fixes: 3c293f4e08b5 ("net: phy: Trigger state machine on state change and not polling.")
Reported-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/net/phy/phy.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index f424b86..201ffa5 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -611,14 +611,18 @@ void phy_start_machine(struct phy_device *phydev)
  * phy_trigger_machine - trigger the state machine to run
  *
  * @phydev: the phy_device struct
+ * @sync: indicate whether we should wait for the workqueue cancelation
  *
  * Description: There has been a change in state which requires that the
  *   state machine runs.
  */
 
-static void phy_trigger_machine(struct phy_device *phydev)
+static void phy_trigger_machine(struct phy_device *phydev, bool sync)
 {
-	cancel_delayed_work_sync(&phydev->state_queue);
+	if (sync)
+		cancel_delayed_work_sync(&phydev->state_queue);
+	else
+		cancel_delayed_work(&phydev->state_queue);
 	queue_delayed_work(system_power_efficient_wq, &phydev->state_queue, 0);
 }
 
@@ -655,7 +659,7 @@ static void phy_error(struct phy_device *phydev)
 	phydev->state = PHY_HALTED;
 	mutex_unlock(&phydev->lock);
 
-	phy_trigger_machine(phydev);
+	phy_trigger_machine(phydev, false);
 }
 
 /**
@@ -817,7 +821,7 @@ void phy_change(struct work_struct *work)
 	}
 
 	/* reschedule state queue work to run as soon as possible */
-	phy_trigger_machine(phydev);
+	phy_trigger_machine(phydev, true);
 	return;
 
 ignore:
@@ -907,7 +911,7 @@ void phy_start(struct phy_device *phydev)
 	if (do_resume)
 		phy_resume(phydev);
 
-	phy_trigger_machine(phydev);
+	phy_trigger_machine(phydev, true);
 }
 EXPORT_SYMBOL(phy_start);
 
-- 
2.1.0


From 0a40da4a74f1767c8ff7faffe86bcb06cae280ed Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 24 Feb 2017 11:43:36 -0800
Subject: [PATCH 011/112] vxlan: lock RCU on TX path

[ Upstream commit 56de859e9967c070464a9a9f4f18d73f9447298e ]

There is no guarantees that callers of the TX path will hold
the RCU lock.  Grab it explicitly.

Fixes: c6fcc4fc5f8b ("vxlan: avoid using stale vxlan socket.")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/net/vxlan.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index ac3f8d5..3c4c2cf 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1955,6 +1955,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 
 	info = skb_tunnel_info(skb);
 
+	rcu_read_lock();
 	if (rdst) {
 		dst_port = rdst->remote_port ? rdst->remote_port : vxlan->cfg.dst_port;
 		vni = rdst->remote_vni;
@@ -1985,7 +1986,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		if (did_rsc) {
 			/* short-circuited back to local bridge */
 			vxlan_encap_bypass(skb, vxlan, vxlan);
-			return;
+			goto out_unlock;
 		}
 		goto drop;
 	}
@@ -2054,7 +2055,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 			if (!dst_vxlan)
 				goto tx_error;
 			vxlan_encap_bypass(skb, vxlan, dst_vxlan);
-			return;
+			goto out_unlock;
 		}
 
 		if (!info)
@@ -2115,7 +2116,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 			if (!dst_vxlan)
 				goto tx_error;
 			vxlan_encap_bypass(skb, vxlan, dst_vxlan);
-			return;
+			goto out_unlock;
 		}
 
 		if (!info)
@@ -2129,7 +2130,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		if (err < 0) {
 			dst_release(ndst);
 			dev->stats.tx_errors++;
-			return;
+			goto out_unlock;
 		}
 		udp_tunnel6_xmit_skb(ndst, sk, skb, dev,
 				     &local_ip.sin6.sin6_addr,
@@ -2137,7 +2138,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 				     label, src_port, dst_port, !udp_sum);
 #endif
 	}
-
+out_unlock:
+	rcu_read_unlock();
 	return;
 
 drop:
@@ -2153,6 +2155,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 	dev->stats.tx_errors++;
 tx_free:
 	dev_kfree_skb(skb);
+	rcu_read_unlock();
 }
 
 /* Transmit local packets over Vxlan
-- 
2.1.0


From 02595f472548738cd1ab3abf424277d6f489048f Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 24 Feb 2017 11:43:37 -0800
Subject: [PATCH 012/112] geneve: lock RCU on TX path

[ Upstream commit a717e3f740803cc88bd5c9a70c93504f6a368663 ]

There is no guarantees that callers of the TX path will hold
the RCU lock.  Grab it explicitly.

Fixes: fceb9c3e3825 ("geneve: avoid using stale geneve socket.")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/net/geneve.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 8b4822a..3c1f89a 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1039,16 +1039,22 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct geneve_dev *geneve = netdev_priv(dev);
 	struct ip_tunnel_info *info = NULL;
+	int err;
 
 	if (geneve->collect_md)
 		info = skb_tunnel_info(skb);
 
+	rcu_read_lock();
 #if IS_ENABLED(CONFIG_IPV6)
 	if ((info && ip_tunnel_info_af(info) == AF_INET6) ||
 	    (!info && geneve->remote.sa.sa_family == AF_INET6))
-		return geneve6_xmit_skb(skb, dev, info);
+		err = geneve6_xmit_skb(skb, dev, info);
+	else
 #endif
-	return geneve_xmit_skb(skb, dev, info);
+		err = geneve_xmit_skb(skb, dev, info);
+	rcu_read_unlock();
+
+	return err;
 }
 
 static int __geneve_change_mtu(struct net_device *dev, int new_mtu, bool strict)
-- 
2.1.0


From 8f4db60c7fb5120050309717123efcfd25a02034 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Tue, 28 Feb 2017 08:55:40 +0100
Subject: [PATCH 013/112] mlxsw: spectrum_router: Avoid potential packets loss

[ Upstream commit f7df4923fa986247e93ec2cdff5ca168fff14dcf ]

When the structure of the LPM tree changes (f.e., due to the addition of
a new prefix), we unbind the old tree and then bind the new one. This
may result in temporary packet loss.

Instead, overwrite the old binding with the new one.

Fixes: 6b75c4807db3 ("mlxsw: spectrum_router: Add virtual router management")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_router.c  | 30 ++++++++++++++--------
 1 file changed, 20 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index e83072d..6905630 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -500,30 +500,40 @@ static int
 mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr,
 			   struct mlxsw_sp_prefix_usage *req_prefix_usage)
 {
-	struct mlxsw_sp_lpm_tree *lpm_tree;
+	struct mlxsw_sp_lpm_tree *lpm_tree = vr->lpm_tree;
+	struct mlxsw_sp_lpm_tree *new_tree;
+	int err;
 
-	if (mlxsw_sp_prefix_usage_eq(req_prefix_usage,
-				     &vr->lpm_tree->prefix_usage))
+	if (mlxsw_sp_prefix_usage_eq(req_prefix_usage, &lpm_tree->prefix_usage))
 		return 0;
 
-	lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, req_prefix_usage,
+	new_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, req_prefix_usage,
 					 vr->proto, false);
-	if (IS_ERR(lpm_tree)) {
+	if (IS_ERR(new_tree)) {
 		/* We failed to get a tree according to the required
 		 * prefix usage. However, the current tree might be still good
 		 * for us if our requirement is subset of the prefixes used
 		 * in the tree.
 		 */
 		if (mlxsw_sp_prefix_usage_subset(req_prefix_usage,
-						 &vr->lpm_tree->prefix_usage))
+						 &lpm_tree->prefix_usage))
 			return 0;
-		return PTR_ERR(lpm_tree);
+		return PTR_ERR(new_tree);
 	}
 
-	mlxsw_sp_vr_lpm_tree_unbind(mlxsw_sp, vr);
-	mlxsw_sp_lpm_tree_put(mlxsw_sp, vr->lpm_tree);
+	/* Prevent packet loss by overwriting existing binding */
+	vr->lpm_tree = new_tree;
+	err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, vr);
+	if (err)
+		goto err_tree_bind;
+	mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree);
+
+	return 0;
+
+err_tree_bind:
 	vr->lpm_tree = lpm_tree;
-	return mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, vr);
+	mlxsw_sp_lpm_tree_put(mlxsw_sp, new_tree);
+	return err;
 }
 
 static struct mlxsw_sp_vr *mlxsw_sp_vr_get(struct mlxsw_sp *mlxsw_sp,
-- 
2.1.0


From bbaeb9b73fa890dd7a6fa379a7e4822687643a4e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 1 Mar 2017 08:39:49 -0800
Subject: [PATCH 014/112] tcp/dccp: block BH for SYN processing

[ Upstream commit 449809a66c1d0b1563dee84493e14bf3104d2d7e ]

SYN processing really was meant to be handled from BH.

When I got rid of BH blocking while processing socket backlog
in commit 5413d1babe8f ("net: do not block BH while processing socket
backlog"), I forgot that a malicious user could transition to TCP_LISTEN
from a state that allowed (SYN) packets to be parked in the socket
backlog while socket is owned by the thread doing the listen() call.

Sure enough syzkaller found this and reported the bug ;)

=================================
[ INFO: inconsistent lock state ]
4.10.0+ #60 Not tainted
---------------------------------
inconsistent {IN-SOFTIRQ-W} -> {SOFTIRQ-ON-W} usage.
syz-executor0/5090 [HC0[0]:SC0[0]:HE1:SE1] takes:
 (&(&hashinfo->ehash_locks[i])->rlock){+.?...}, at:
[<ffffffff83a6a370>] spin_lock include/linux/spinlock.h:299 [inline]
 (&(&hashinfo->ehash_locks[i])->rlock){+.?...}, at:
[<ffffffff83a6a370>] inet_ehash_insert+0x240/0xad0
net/ipv4/inet_hashtables.c:407
{IN-SOFTIRQ-W} state was registered at:
  mark_irqflags kernel/locking/lockdep.c:2923 [inline]
  __lock_acquire+0xbcf/0x3270 kernel/locking/lockdep.c:3295
  lock_acquire+0x241/0x580 kernel/locking/lockdep.c:3753
  __raw_spin_lock include/linux/spinlock_api_smp.h:142 [inline]
  _raw_spin_lock+0x33/0x50 kernel/locking/spinlock.c:151
  spin_lock include/linux/spinlock.h:299 [inline]
  inet_ehash_insert+0x240/0xad0 net/ipv4/inet_hashtables.c:407
  reqsk_queue_hash_req net/ipv4/inet_connection_sock.c:753 [inline]
  inet_csk_reqsk_queue_hash_add+0x1b7/0x2a0 net/ipv4/inet_connection_sock.c:764
  tcp_conn_request+0x25cc/0x3310 net/ipv4/tcp_input.c:6399
  tcp_v4_conn_request+0x157/0x220 net/ipv4/tcp_ipv4.c:1262
  tcp_rcv_state_process+0x802/0x4130 net/ipv4/tcp_input.c:5889
  tcp_v4_do_rcv+0x56b/0x940 net/ipv4/tcp_ipv4.c:1433
  tcp_v4_rcv+0x2e12/0x3210 net/ipv4/tcp_ipv4.c:1711
  ip_local_deliver_finish+0x4ce/0xc40 net/ipv4/ip_input.c:216
  NF_HOOK include/linux/netfilter.h:257 [inline]
  ip_local_deliver+0x1ce/0x710 net/ipv4/ip_input.c:257
  dst_input include/net/dst.h:492 [inline]
  ip_rcv_finish+0xb1d/0x2110 net/ipv4/ip_input.c:396
  NF_HOOK include/linux/netfilter.h:257 [inline]
  ip_rcv+0xd90/0x19c0 net/ipv4/ip_input.c:487
  __netif_receive_skb_core+0x1ad1/0x3400 net/core/dev.c:4179
  __netif_receive_skb+0x2a/0x170 net/core/dev.c:4217
  netif_receive_skb_internal+0x1d6/0x430 net/core/dev.c:4245
  napi_skb_finish net/core/dev.c:4602 [inline]
  napi_gro_receive+0x4e6/0x680 net/core/dev.c:4636
  e1000_receive_skb drivers/net/ethernet/intel/e1000/e1000_main.c:4033 [inline]
  e1000_clean_rx_irq+0x5e0/0x1490
drivers/net/ethernet/intel/e1000/e1000_main.c:4489
  e1000_clean+0xb9a/0x2910 drivers/net/ethernet/intel/e1000/e1000_main.c:3834
  napi_poll net/core/dev.c:5171 [inline]
  net_rx_action+0xe70/0x1900 net/core/dev.c:5236
  __do_softirq+0x2fb/0xb7d kernel/softirq.c:284
  invoke_softirq kernel/softirq.c:364 [inline]
  irq_exit+0x19e/0x1d0 kernel/softirq.c:405
  exiting_irq arch/x86/include/asm/apic.h:658 [inline]
  do_IRQ+0x81/0x1a0 arch/x86/kernel/irq.c:250
  ret_from_intr+0x0/0x20
  native_safe_halt+0x6/0x10 arch/x86/include/asm/irqflags.h:53
  arch_safe_halt arch/x86/include/asm/paravirt.h:98 [inline]
  default_idle+0x8f/0x410 arch/x86/kernel/process.c:271
  arch_cpu_idle+0xa/0x10 arch/x86/kernel/process.c:262
  default_idle_call+0x36/0x60 kernel/sched/idle.c:96
  cpuidle_idle_call kernel/sched/idle.c:154 [inline]
  do_idle+0x348/0x440 kernel/sched/idle.c:243
  cpu_startup_entry+0x18/0x20 kernel/sched/idle.c:345
  start_secondary+0x344/0x440 arch/x86/kernel/smpboot.c:272
  verify_cpu+0x0/0xfc
irq event stamp: 1741
hardirqs last  enabled at (1741): [<ffffffff84d49d77>]
__raw_spin_unlock_irqrestore include/linux/spinlock_api_smp.h:160
[inline]
hardirqs last  enabled at (1741): [<ffffffff84d49d77>]
_raw_spin_unlock_irqrestore+0xf7/0x1a0 kernel/locking/spinlock.c:191
hardirqs last disabled at (1740): [<ffffffff84d4a732>]
__raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:108 [inline]
hardirqs last disabled at (1740): [<ffffffff84d4a732>]
_raw_spin_lock_irqsave+0xa2/0x110 kernel/locking/spinlock.c:159
softirqs last  enabled at (1738): [<ffffffff84d4deff>]
__do_softirq+0x7cf/0xb7d kernel/softirq.c:310
softirqs last disabled at (1571): [<ffffffff84d4b92c>]
do_softirq_own_stack+0x1c/0x30 arch/x86/entry/entry_64.S:902

other info that might help us debug this:
 Possible unsafe locking scenario:

       CPU0
       ----
  lock(&(&hashinfo->ehash_locks[i])->rlock);
  <Interrupt>
    lock(&(&hashinfo->ehash_locks[i])->rlock);

 *** DEADLOCK ***

1 lock held by syz-executor0/5090:
 #0:  (sk_lock-AF_INET6){+.+.+.}, at: [<ffffffff83406b43>] lock_sock
include/net/sock.h:1460 [inline]
 #0:  (sk_lock-AF_INET6){+.+.+.}, at: [<ffffffff83406b43>]
sock_setsockopt+0x233/0x1e40 net/core/sock.c:683

stack backtrace:
CPU: 1 PID: 5090 Comm: syz-executor0 Not tainted 4.10.0+ #60
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:15 [inline]
 dump_stack+0x292/0x398 lib/dump_stack.c:51
 print_usage_bug+0x3ef/0x450 kernel/locking/lockdep.c:2387
 valid_state kernel/locking/lockdep.c:2400 [inline]
 mark_lock_irq kernel/locking/lockdep.c:2602 [inline]
 mark_lock+0xf30/0x1410 kernel/locking/lockdep.c:3065
 mark_irqflags kernel/locking/lockdep.c:2941 [inline]
 __lock_acquire+0x6dc/0x3270 kernel/locking/lockdep.c:3295
 lock_acquire+0x241/0x580 kernel/locking/lockdep.c:3753
 __raw_spin_lock include/linux/spinlock_api_smp.h:142 [inline]
 _raw_spin_lock+0x33/0x50 kernel/locking/spinlock.c:151
 spin_lock include/linux/spinlock.h:299 [inline]
 inet_ehash_insert+0x240/0xad0 net/ipv4/inet_hashtables.c:407
 reqsk_queue_hash_req net/ipv4/inet_connection_sock.c:753 [inline]
 inet_csk_reqsk_queue_hash_add+0x1b7/0x2a0 net/ipv4/inet_connection_sock.c:764
 dccp_v6_conn_request+0xada/0x11b0 net/dccp/ipv6.c:380
 dccp_rcv_state_process+0x51e/0x1660 net/dccp/input.c:606
 dccp_v6_do_rcv+0x213/0x350 net/dccp/ipv6.c:632
 sk_backlog_rcv include/net/sock.h:896 [inline]
 __release_sock+0x127/0x3a0 net/core/sock.c:2052
 release_sock+0xa5/0x2b0 net/core/sock.c:2539
 sock_setsockopt+0x60f/0x1e40 net/core/sock.c:1016
 SYSC_setsockopt net/socket.c:1782 [inline]
 SyS_setsockopt+0x2fb/0x3a0 net/socket.c:1765
 entry_SYSCALL_64_fastpath+0x1f/0xc2
RIP: 0033:0x4458b9
RSP: 002b:00007fe8b26c2b58 EFLAGS: 00000292 ORIG_RAX: 0000000000000036
RAX: ffffffffffffffda RBX: 0000000000000006 RCX: 00000000004458b9
RDX: 000000000000001a RSI: 0000000000000001 RDI: 0000000000000006
RBP: 00000000006e2110 R08: 0000000000000010 R09: 0000000000000000
R10: 00000000208c3000 R11: 0000000000000292 R12: 0000000000708000
R13: 0000000020000000 R14: 0000000000001000 R15: 0000000000000000

Fixes: 5413d1babe8f ("net: do not block BH while processing socket backlog")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/dccp/input.c     | 10 ++++++++--
 net/ipv4/tcp_input.c | 10 ++++++++--
 2 files changed, 16 insertions(+), 4 deletions(-)

diff --git a/net/dccp/input.c b/net/dccp/input.c
index 8fedc2d..4a05d78 100644
--- a/net/dccp/input.c
+++ b/net/dccp/input.c
@@ -577,6 +577,7 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 	struct dccp_sock *dp = dccp_sk(sk);
 	struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
 	const int old_state = sk->sk_state;
+	bool acceptable;
 	int queued = 0;
 
 	/*
@@ -603,8 +604,13 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 	 */
 	if (sk->sk_state == DCCP_LISTEN) {
 		if (dh->dccph_type == DCCP_PKT_REQUEST) {
-			if (inet_csk(sk)->icsk_af_ops->conn_request(sk,
-								    skb) < 0)
+			/* It is possible that we process SYN packets from backlog,
+			 * so we need to make sure to disable BH right there.
+			 */
+			local_bh_disable();
+			acceptable = inet_csk(sk)->icsk_af_ops->conn_request(sk, skb) >= 0;
+			local_bh_enable();
+			if (!acceptable)
 				return 1;
 			consume_skb(skb);
 			return 0;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index c71d49c..ce42ded 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5916,9 +5916,15 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 		if (th->syn) {
 			if (th->fin)
 				goto discard;
-			if (icsk->icsk_af_ops->conn_request(sk, skb) < 0)
-				return 1;
+			/* It is possible that we process SYN packets from backlog,
+			 * so we need to make sure to disable BH right there.
+			 */
+			local_bh_disable();
+			acceptable = icsk->icsk_af_ops->conn_request(sk, skb) >= 0;
+			local_bh_enable();
 
+			if (!acceptable)
+				return 1;
 			consume_skb(skb);
 			return 0;
 		}
-- 
2.1.0


From fa7c48fb3ad1744dab7a9a2783ae589bd87b732b Mon Sep 17 00:00:00 2001
From: Mike Manning <mmanning@brocade.com>
Date: Wed, 1 Mar 2017 09:55:28 +0000
Subject: [PATCH 015/112] net: bridge: allow IPv6 when multicast flood is
 disabled

[ Upstream commit 8953de2f02ad7b15e4964c82f9afd60f128e4e98 ]

Even with multicast flooding turned off, IPv6 ND should still work so
that IPv6 connectivity is provided. Allow this by continuing to flood
multicast traffic originated by us.

Fixes: b6cb5ac8331b ("net: bridge: add per-port multicast flood flag")
Cc: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: Mike Manning <mmanning@brocade.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/bridge/br_forward.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 7cb41ae..8498e35 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -186,8 +186,9 @@ void br_flood(struct net_bridge *br, struct sk_buff *skb,
 		/* Do not flood unicast traffic to ports that turn it off */
 		if (pkt_type == BR_PKT_UNICAST && !(p->flags & BR_FLOOD))
 			continue;
+		/* Do not flood if mc off, except for traffic we originate */
 		if (pkt_type == BR_PKT_MULTICAST &&
-		    !(p->flags & BR_MCAST_FLOOD))
+		    !(p->flags & BR_MCAST_FLOOD) && skb->dev != br->dev)
 			continue;
 
 		/* Do not flood to ports that enable proxy ARP */
-- 
2.1.0


From 62fe0521fb6cc3b887fdc00ddca9c38d2614b8b0 Mon Sep 17 00:00:00 2001
From: Alexander Potapenko <glider@google.com>
Date: Wed, 1 Mar 2017 12:57:20 +0100
Subject: [PATCH 016/112] net: don't call strlen() on the user buffer in
 packet_bind_spkt()

[ Upstream commit 540e2894f7905538740aaf122bd8e0548e1c34a4 ]

KMSAN (KernelMemorySanitizer, a new error detection tool) reports use of
uninitialized memory in packet_bind_spkt():
Acked-by: Eric Dumazet <edumazet@google.com>

==================================================================
BUG: KMSAN: use of unitialized memory
CPU: 0 PID: 1074 Comm: packet Not tainted 4.8.0-rc6+ #1891
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs
01/01/2011
 0000000000000000 ffff88006b6dfc08 ffffffff82559ae8 ffff88006b6dfb48
 ffffffff818a7c91 ffffffff85b9c870 0000000000000092 ffffffff85b9c550
 0000000000000000 0000000000000092 00000000ec400911 0000000000000002
Call Trace:
 [<     inline     >] __dump_stack lib/dump_stack.c:15
 [<ffffffff82559ae8>] dump_stack+0x238/0x290 lib/dump_stack.c:51
 [<ffffffff818a6626>] kmsan_report+0x276/0x2e0 mm/kmsan/kmsan.c:1003
 [<ffffffff818a783b>] __msan_warning+0x5b/0xb0
mm/kmsan/kmsan_instr.c:424
 [<     inline     >] strlen lib/string.c:484
 [<ffffffff8259b58d>] strlcpy+0x9d/0x200 lib/string.c:144
 [<ffffffff84b2eca4>] packet_bind_spkt+0x144/0x230
net/packet/af_packet.c:3132
 [<ffffffff84242e4d>] SYSC_bind+0x40d/0x5f0 net/socket.c:1370
 [<ffffffff84242a22>] SyS_bind+0x82/0xa0 net/socket.c:1356
 [<ffffffff8515991b>] entry_SYSCALL_64_fastpath+0x13/0x8f
arch/x86/entry/entry_64.o:?
chained origin: 00000000eba00911
 [<ffffffff810bb787>] save_stack_trace+0x27/0x50
arch/x86/kernel/stacktrace.c:67
 [<     inline     >] kmsan_save_stack_with_flags mm/kmsan/kmsan.c:322
 [<     inline     >] kmsan_save_stack mm/kmsan/kmsan.c:334
 [<ffffffff818a59f8>] kmsan_internal_chain_origin+0x118/0x1e0
mm/kmsan/kmsan.c:527
 [<ffffffff818a7773>] __msan_set_alloca_origin4+0xc3/0x130
mm/kmsan/kmsan_instr.c:380
 [<ffffffff84242b69>] SYSC_bind+0x129/0x5f0 net/socket.c:1356
 [<ffffffff84242a22>] SyS_bind+0x82/0xa0 net/socket.c:1356
 [<ffffffff8515991b>] entry_SYSCALL_64_fastpath+0x13/0x8f
arch/x86/entry/entry_64.o:?
origin description: ----address@SYSC_bind (origin=00000000eb400911)
==================================================================
(the line numbers are relative to 4.8-rc6, but the bug persists
upstream)

, when I run the following program as root:

=====================================
 #include <string.h>
 #include <sys/socket.h>
 #include <netpacket/packet.h>
 #include <net/ethernet.h>

 int main() {
   struct sockaddr addr;
   memset(&addr, 0xff, sizeof(addr));
   addr.sa_family = AF_PACKET;
   int fd = socket(PF_PACKET, SOCK_PACKET, htons(ETH_P_ALL));
   bind(fd, &addr, sizeof(addr));
   return 0;
 }
=====================================

This happens because addr.sa_data copied from the userspace is not
zero-terminated, and copying it with strlcpy() in packet_bind_spkt()
results in calling strlen() on the kernel copy of that non-terminated
buffer.

Signed-off-by: Alexander Potapenko <glider@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/packet/af_packet.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 34de326..f2b04a7 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3140,7 +3140,7 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr,
 			    int addr_len)
 {
 	struct sock *sk = sock->sk;
-	char name[15];
+	char name[sizeof(uaddr->sa_data) + 1];
 
 	/*
 	 *	Check legality
@@ -3148,7 +3148,11 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr,
 
 	if (addr_len != sizeof(struct sockaddr))
 		return -EINVAL;
-	strlcpy(name, uaddr->sa_data, sizeof(name));
+	/* uaddr->sa_data comes from the userspace, it's not guaranteed to be
+	 * zero-terminated.
+	 */
+	memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data));
+	name[sizeof(uaddr->sa_data)] = 0;
 
 	return packet_do_bind(sk, name, 0, pkt_sk(sk)->num);
 }
-- 
2.1.0


From 3d87dce3dfd665a892d107b797e68697204c3e43 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 1 Mar 2017 14:28:39 -0800
Subject: [PATCH 017/112] net: net_enable_timestamp() can be called from irq
 contexts

[ Upstream commit 13baa00ad01bb3a9f893e3a08cbc2d072fc0c15d ]

It is now very clear that silly TCP listeners might play with
enabling/disabling timestamping while new children are added
to their accept queue.

Meaning net_enable_timestamp() can be called from BH context
while current state of the static key is not enabled.

Lets play safe and allow all contexts.

The work queue is scheduled only under the problematic cases,
which are the static key enable/disable transition, to not slow down
critical paths.

This extends and improves what we did in commit 5fa8bbda38c6 ("net: use
a work queue to defer net_disable_timestamp() work")

Fixes: b90e5794c5bd ("net: dont call jump_label_dec from irq context")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/core/dev.c | 35 +++++++++++++++++++++++++++++++----
 1 file changed, 31 insertions(+), 4 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 60b0a604..2e04fd1 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1697,27 +1697,54 @@ EXPORT_SYMBOL_GPL(net_dec_egress_queue);
 static struct static_key netstamp_needed __read_mostly;
 #ifdef HAVE_JUMP_LABEL
 static atomic_t netstamp_needed_deferred;
+static atomic_t netstamp_wanted;
 static void netstamp_clear(struct work_struct *work)
 {
 	int deferred = atomic_xchg(&netstamp_needed_deferred, 0);
+	int wanted;
 
-	while (deferred--)
-		static_key_slow_dec(&netstamp_needed);
+	wanted = atomic_add_return(deferred, &netstamp_wanted);
+	if (wanted > 0)
+		static_key_enable(&netstamp_needed);
+	else
+		static_key_disable(&netstamp_needed);
 }
 static DECLARE_WORK(netstamp_work, netstamp_clear);
 #endif
 
 void net_enable_timestamp(void)
 {
+#ifdef HAVE_JUMP_LABEL
+	int wanted;
+
+	while (1) {
+		wanted = atomic_read(&netstamp_wanted);
+		if (wanted <= 0)
+			break;
+		if (atomic_cmpxchg(&netstamp_wanted, wanted, wanted + 1) == wanted)
+			return;
+	}
+	atomic_inc(&netstamp_needed_deferred);
+	schedule_work(&netstamp_work);
+#else
 	static_key_slow_inc(&netstamp_needed);
+#endif
 }
 EXPORT_SYMBOL(net_enable_timestamp);
 
 void net_disable_timestamp(void)
 {
 #ifdef HAVE_JUMP_LABEL
-	/* net_disable_timestamp() can be called from non process context */
-	atomic_inc(&netstamp_needed_deferred);
+	int wanted;
+
+	while (1) {
+		wanted = atomic_read(&netstamp_wanted);
+		if (wanted <= 1)
+			break;
+		if (atomic_cmpxchg(&netstamp_wanted, wanted, wanted - 1) == wanted)
+			return;
+	}
+	atomic_dec(&netstamp_needed_deferred);
 	schedule_work(&netstamp_work);
 #else
 	static_key_slow_dec(&netstamp_needed);
-- 
2.1.0


From 0bcc319d554cbc2414b721d773b775b3cade9bd8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 1 Mar 2017 14:45:06 -0800
Subject: [PATCH 018/112] ipv6: orphan skbs in reassembly unit

[ Upstream commit 48cac18ecf1de82f76259a54402c3adb7839ad01 ]

Andrey reported a use-after-free in IPv6 stack.

Issue here is that we free the socket while it still has skb
in TX path and in some queues.

It happens here because IPv6 reassembly unit messes skb->truesize,
breaking skb_set_owner_w() badly.

We fixed a similar issue for IPV4 in commit 8282f27449bf ("inet: frag:
Always orphan skbs inside ip_defrag()")
Acked-by: Joe Stringer <joe@ovn.org>

==================================================================
BUG: KASAN: use-after-free in sock_wfree+0x118/0x120
Read of size 8 at addr ffff880062da0060 by task a.out/4140

page:ffffea00018b6800 count:1 mapcount:0 mapping:          (null)
index:0x0 compound_mapcount: 0
flags: 0x100000000008100(slab|head)
raw: 0100000000008100 0000000000000000 0000000000000000 0000000180130013
raw: dead000000000100 dead000000000200 ffff88006741f140 0000000000000000
page dumped because: kasan: bad access detected

CPU: 0 PID: 4140 Comm: a.out Not tainted 4.10.0-rc3+ #59
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:15
 dump_stack+0x292/0x398 lib/dump_stack.c:51
 describe_address mm/kasan/report.c:262
 kasan_report_error+0x121/0x560 mm/kasan/report.c:370
 kasan_report mm/kasan/report.c:392
 __asan_report_load8_noabort+0x3e/0x40 mm/kasan/report.c:413
 sock_flag ./arch/x86/include/asm/bitops.h:324
 sock_wfree+0x118/0x120 net/core/sock.c:1631
 skb_release_head_state+0xfc/0x250 net/core/skbuff.c:655
 skb_release_all+0x15/0x60 net/core/skbuff.c:668
 __kfree_skb+0x15/0x20 net/core/skbuff.c:684
 kfree_skb+0x16e/0x4e0 net/core/skbuff.c:705
 inet_frag_destroy+0x121/0x290 net/ipv4/inet_fragment.c:304
 inet_frag_put ./include/net/inet_frag.h:133
 nf_ct_frag6_gather+0x1125/0x38b0 net/ipv6/netfilter/nf_conntrack_reasm.c:617
 ipv6_defrag+0x21b/0x350 net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:68
 nf_hook_entry_hookfn ./include/linux/netfilter.h:102
 nf_hook_slow+0xc3/0x290 net/netfilter/core.c:310
 nf_hook ./include/linux/netfilter.h:212
 __ip6_local_out+0x52c/0xaf0 net/ipv6/output_core.c:160
 ip6_local_out+0x2d/0x170 net/ipv6/output_core.c:170
 ip6_send_skb+0xa1/0x340 net/ipv6/ip6_output.c:1722
 ip6_push_pending_frames+0xb3/0xe0 net/ipv6/ip6_output.c:1742
 rawv6_push_pending_frames net/ipv6/raw.c:613
 rawv6_sendmsg+0x2cff/0x4130 net/ipv6/raw.c:927
 inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:744
 sock_sendmsg_nosec net/socket.c:635
 sock_sendmsg+0xca/0x110 net/socket.c:645
 sock_write_iter+0x326/0x620 net/socket.c:848
 new_sync_write fs/read_write.c:499
 __vfs_write+0x483/0x760 fs/read_write.c:512
 vfs_write+0x187/0x530 fs/read_write.c:560
 SYSC_write fs/read_write.c:607
 SyS_write+0xfb/0x230 fs/read_write.c:599
 entry_SYSCALL_64_fastpath+0x1f/0xc2 arch/x86/entry/entry_64.S:203
RIP: 0033:0x7ff26e6f5b79
RSP: 002b:00007ff268e0ed98 EFLAGS: 00000206 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 00007ff268e0f9c0 RCX: 00007ff26e6f5b79
RDX: 0000000000000010 RSI: 0000000020f50fe1 RDI: 0000000000000003
RBP: 00007ff26ebc1220 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000206 R12: 0000000000000000
R13: 00007ff268e0f9c0 R14: 00007ff26efec040 R15: 0000000000000003

The buggy address belongs to the object at ffff880062da0000
 which belongs to the cache RAWv6 of size 1504
The buggy address ffff880062da0060 is located 96 bytes inside
 of 1504-byte region [ffff880062da0000, ffff880062da05e0)

Freed by task 4113:
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57
 save_stack+0x43/0xd0 mm/kasan/kasan.c:502
 set_track mm/kasan/kasan.c:514
 kasan_slab_free+0x73/0xc0 mm/kasan/kasan.c:578
 slab_free_hook mm/slub.c:1352
 slab_free_freelist_hook mm/slub.c:1374
 slab_free mm/slub.c:2951
 kmem_cache_free+0xb2/0x2c0 mm/slub.c:2973
 sk_prot_free net/core/sock.c:1377
 __sk_destruct+0x49c/0x6e0 net/core/sock.c:1452
 sk_destruct+0x47/0x80 net/core/sock.c:1460
 __sk_free+0x57/0x230 net/core/sock.c:1468
 sk_free+0x23/0x30 net/core/sock.c:1479
 sock_put ./include/net/sock.h:1638
 sk_common_release+0x31e/0x4e0 net/core/sock.c:2782
 rawv6_close+0x54/0x80 net/ipv6/raw.c:1214
 inet_release+0xed/0x1c0 net/ipv4/af_inet.c:425
 inet6_release+0x50/0x70 net/ipv6/af_inet6.c:431
 sock_release+0x8d/0x1e0 net/socket.c:599
 sock_close+0x16/0x20 net/socket.c:1063
 __fput+0x332/0x7f0 fs/file_table.c:208
 ____fput+0x15/0x20 fs/file_table.c:244
 task_work_run+0x19b/0x270 kernel/task_work.c:116
 exit_task_work ./include/linux/task_work.h:21
 do_exit+0x186b/0x2800 kernel/exit.c:839
 do_group_exit+0x149/0x420 kernel/exit.c:943
 SYSC_exit_group kernel/exit.c:954
 SyS_exit_group+0x1d/0x20 kernel/exit.c:952
 entry_SYSCALL_64_fastpath+0x1f/0xc2 arch/x86/entry/entry_64.S:203

Allocated by task 4115:
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57
 save_stack+0x43/0xd0 mm/kasan/kasan.c:502
 set_track mm/kasan/kasan.c:514
 kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:605
 kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:544
 slab_post_alloc_hook mm/slab.h:432
 slab_alloc_node mm/slub.c:2708
 slab_alloc mm/slub.c:2716
 kmem_cache_alloc+0x1af/0x250 mm/slub.c:2721
 sk_prot_alloc+0x65/0x2a0 net/core/sock.c:1334
 sk_alloc+0x105/0x1010 net/core/sock.c:1396
 inet6_create+0x44d/0x1150 net/ipv6/af_inet6.c:183
 __sock_create+0x4f6/0x880 net/socket.c:1199
 sock_create net/socket.c:1239
 SYSC_socket net/socket.c:1269
 SyS_socket+0xf9/0x230 net/socket.c:1249
 entry_SYSCALL_64_fastpath+0x1f/0xc2 arch/x86/entry/entry_64.S:203

Memory state around the buggy address:
 ffff880062d9ff00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 ffff880062d9ff80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
>ffff880062da0000: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                                                       ^
 ffff880062da0080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff880062da0100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
==================================================================

Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/ipv6/netfilter/nf_conntrack_reasm.c | 1 +
 net/openvswitch/conntrack.c             | 1 -
 2 files changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 9948b5c..986d4ca 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -589,6 +589,7 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
 	hdr = ipv6_hdr(skb);
 	fhdr = (struct frag_hdr *)skb_transport_header(skb);
 
+	skb_orphan(skb);
 	fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr,
 		     skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
 	if (fq == NULL) {
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index eab210b..48386bf 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -367,7 +367,6 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key,
 	} else if (key->eth.type == htons(ETH_P_IPV6)) {
 		enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone;
 
-		skb_orphan(skb);
 		memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));
 		err = nf_ct_frag6_gather(net, skb, user);
 		if (err) {
-- 
2.1.0


From 51ae1fbcf17325d47c20f65fb968be2d2d12fed0 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 1 Mar 2017 16:35:07 -0300
Subject: [PATCH 019/112] dccp: Unlock sock before calling sk_free()

[ Upstream commit d5afb6f9b6bb2c57bd0c05e76e12489dc0d037d9 ]

The code where sk_clone() came from created a new socket and locked it,
but then, on the error path didn't unlock it.

This problem stayed there for a long while, till b0691c8ee7c2 ("net:
Unlock sock before calling sk_free()") fixed it, but unfortunately the
callers of sk_clone() (now sk_clone_locked()) were not audited and the
one in dccp_create_openreq_child() remained.

Now in the age of the syskaller fuzzer, this was finally uncovered, as
reported by Dmitry:

 ---- 8< ----

I've got the following report while running syzkaller fuzzer on
86292b33d4b7 ("Merge branch 'akpm' (patches from Andrew)")

  [ BUG: held lock freed! ]
  4.10.0+ #234 Not tainted
  -------------------------
  syz-executor6/6898 is freeing memory
  ffff88006286cac0-ffff88006286d3b7, with a lock still held there!
   (slock-AF_INET6){+.-...}, at: [<ffffffff8362c2c9>] spin_lock
  include/linux/spinlock.h:299 [inline]
   (slock-AF_INET6){+.-...}, at: [<ffffffff8362c2c9>]
  sk_clone_lock+0x3d9/0x12c0 net/core/sock.c:1504
  5 locks held by syz-executor6/6898:
   #0:  (sk_lock-AF_INET6){+.+.+.}, at: [<ffffffff839a34b4>] lock_sock
  include/net/sock.h:1460 [inline]
   #0:  (sk_lock-AF_INET6){+.+.+.}, at: [<ffffffff839a34b4>]
  inet_stream_connect+0x44/0xa0 net/ipv4/af_inet.c:681
   #1:  (rcu_read_lock){......}, at: [<ffffffff83bc1c2a>]
  inet6_csk_xmit+0x12a/0x5d0 net/ipv6/inet6_connection_sock.c:126
   #2:  (rcu_read_lock){......}, at: [<ffffffff8369b424>] __skb_unlink
  include/linux/skbuff.h:1767 [inline]
   #2:  (rcu_read_lock){......}, at: [<ffffffff8369b424>] __skb_dequeue
  include/linux/skbuff.h:1783 [inline]
   #2:  (rcu_read_lock){......}, at: [<ffffffff8369b424>]
  process_backlog+0x264/0x730 net/core/dev.c:4835
   #3:  (rcu_read_lock){......}, at: [<ffffffff83aeb5c0>]
  ip6_input_finish+0x0/0x1700 net/ipv6/ip6_input.c:59
   #4:  (slock-AF_INET6){+.-...}, at: [<ffffffff8362c2c9>] spin_lock
  include/linux/spinlock.h:299 [inline]
   #4:  (slock-AF_INET6){+.-...}, at: [<ffffffff8362c2c9>]
  sk_clone_lock+0x3d9/0x12c0 net/core/sock.c:1504

Fix it just like was done by b0691c8ee7c2 ("net: Unlock sock before calling
sk_free()").

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20170301153510.GE15145@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/dccp/minisocks.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index 53eddf9..d20d948 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -122,6 +122,7 @@ struct sock *dccp_create_openreq_child(const struct sock *sk,
 			/* It is still raw copy of parent, so invalidate
 			 * destructor and make plain sk_free() */
 			newsk->sk_destruct = NULL;
+			bh_unlock_sock(newsk);
 			sk_free(newsk);
 			return NULL;
 		}
-- 
2.1.0


From 4547f03d1a624d7e92c65077b7cb5b2a33839cb3 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Fri, 3 Mar 2017 12:21:14 -0800
Subject: [PATCH 020/112] strparser: destroy workqueue on module exit

[ Upstream commit f78ef7cd9a0686b979679d0de061c6dbfd8d649e ]

Fixes: 43a0c6751a32 ("strparser: Stream parser for messages")
Cc: Tom Herbert <tom@herbertland.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/strparser/strparser.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index 41adf36..b5c279b 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -504,6 +504,7 @@ static int __init strp_mod_init(void)
 
 static void __exit strp_mod_exit(void)
 {
+	destroy_workqueue(strp_wq);
 }
 module_init(strp_mod_init);
 module_exit(strp_mod_exit);
-- 
2.1.0


From 07753bc6a2816c1c3b9f7bff133251f623c7bc91 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 3 Mar 2017 14:08:21 -0800
Subject: [PATCH 021/112] tcp: fix various issues for sockets morphing to
 listen state

[ Upstream commit 02b2faaf0af1d85585f6d6980e286d53612acfc2 ]

Dmitry Vyukov reported a divide by 0 triggered by syzkaller, exploiting
tcp_disconnect() path that was never really considered and/or used
before syzkaller ;)

I was not able to reproduce the bug, but it seems issues here are the
three possible actions that assumed they would never trigger on a
listener.

1) tcp_write_timer_handler
2) tcp_delack_timer_handler
3) MTU reduction

Only IPv6 MTU reduction was properly testing TCP_CLOSE and TCP_LISTEN
 states from tcp_v6_mtu_reduced()

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/ipv4/tcp_ipv4.c  | 7 +++++--
 net/ipv4/tcp_timer.c | 6 ++++--
 2 files changed, 9 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 2259114..5bb809f 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -269,10 +269,13 @@ EXPORT_SYMBOL(tcp_v4_connect);
  */
 void tcp_v4_mtu_reduced(struct sock *sk)
 {
-	struct dst_entry *dst;
 	struct inet_sock *inet = inet_sk(sk);
-	u32 mtu = tcp_sk(sk)->mtu_info;
+	struct dst_entry *dst;
+	u32 mtu;
 
+	if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
+		return;
+	mtu = tcp_sk(sk)->mtu_info;
 	dst = inet_csk_update_pmtu(sk, mtu);
 	if (!dst)
 		return;
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 3ea1cf8..b1e65b3 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -249,7 +249,8 @@ void tcp_delack_timer_handler(struct sock *sk)
 
 	sk_mem_reclaim_partial(sk);
 
-	if (sk->sk_state == TCP_CLOSE || !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
+	if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
+	    !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
 		goto out;
 
 	if (time_after(icsk->icsk_ack.timeout, jiffies)) {
@@ -552,7 +553,8 @@ void tcp_write_timer_handler(struct sock *sk)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	int event;
 
-	if (sk->sk_state == TCP_CLOSE || !icsk->icsk_pending)
+	if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
+	    !icsk->icsk_pending)
 		goto out;
 
 	if (time_after(icsk->icsk_timeout, jiffies)) {
-- 
2.1.0


From 98fa3d2a8e399c40f681bca83f8ab522657c16db Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 3 Mar 2017 21:01:02 -0800
Subject: [PATCH 022/112] net: fix socket refcounting in
 skb_complete_wifi_ack()

[ Upstream commit dd4f10722aeb10f4f582948839f066bebe44e5fb ]

TX skbs do not necessarily hold a reference on skb->sk->sk_refcnt
By the time TX completion happens, sk_refcnt might be already 0.

sock_hold()/sock_put() would then corrupt critical state, like
sk_wmem_alloc.

Fixes: bf7fa551e0ce ("mac80211: Resolve sk_refcnt/sk_wmem_alloc issue in wifi ack path")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/core/skbuff.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 1e3e008..b806677 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3871,7 +3871,7 @@ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked)
 {
 	struct sock *sk = skb->sk;
 	struct sock_exterr_skb *serr;
-	int err;
+	int err = 1;
 
 	skb->wifi_acked_valid = 1;
 	skb->wifi_acked = acked;
@@ -3881,14 +3881,15 @@ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked)
 	serr->ee.ee_errno = ENOMSG;
 	serr->ee.ee_origin = SO_EE_ORIGIN_TXSTATUS;
 
-	/* take a reference to prevent skb_orphan() from freeing the socket */
-	sock_hold(sk);
-
-	err = sock_queue_err_skb(sk, skb);
+	/* Take a reference to prevent skb_orphan() from freeing the socket,
+	 * but only if the socket refcount is not zero.
+	 */
+	if (likely(atomic_inc_not_zero(&sk->sk_refcnt))) {
+		err = sock_queue_err_skb(sk, skb);
+		sock_put(sk);
+	}
 	if (err)
 		kfree_skb(skb);
-
-	sock_put(sk);
 }
 EXPORT_SYMBOL_GPL(skb_complete_wifi_ack);
 
-- 
2.1.0


From f157cc1d7251403c950d960e3bcf988c14d9deda Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 3 Mar 2017 21:01:03 -0800
Subject: [PATCH 023/112] net: fix socket refcounting in
 skb_complete_tx_timestamp()

[ Upstream commit 9ac25fc063751379cb77434fef9f3b088cd3e2f7 ]

TX skbs do not necessarily hold a reference on skb->sk->sk_refcnt
By the time TX completion happens, sk_refcnt might be already 0.

sock_hold()/sock_put() would then corrupt critical state, like
sk_wmem_alloc and lead to leaks or use after free.

Fixes: 62bccb8cdb69 ("net-timestamp: Make the clone operation stand-alone from phy timestamping")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/core/skbuff.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index b806677..f0f462c 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3814,13 +3814,14 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
 	if (!skb_may_tx_timestamp(sk, false))
 		return;
 
-	/* take a reference to prevent skb_orphan() from freeing the socket */
-	sock_hold(sk);
-
-	*skb_hwtstamps(skb) = *hwtstamps;
-	__skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND);
-
-	sock_put(sk);
+	/* Take a reference to prevent skb_orphan() from freeing the socket,
+	 * but only if the socket refcount is not zero.
+	 */
+	if (likely(atomic_inc_not_zero(&sk->sk_refcnt))) {
+		*skb_hwtstamps(skb) = *hwtstamps;
+		__skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND);
+		sock_put(sk);
+	}
 }
 EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp);
 
-- 
2.1.0


From 5f79aab41dedaa869ef3c706e4c0872318665884 Mon Sep 17 00:00:00 2001
From: Alexey Khoroshilov <khoroshilov@ispras.ru>
Date: Sun, 5 Mar 2017 03:01:55 +0300
Subject: [PATCH 024/112] net/sched: act_skbmod: remove unneeded
 rcu_read_unlock in tcf_skbmod_dump

[ Upstream commit 6c4dc75c251721f517e9daeb5370ea606b5b35ce ]

Found by Linux Driver Verification project (linuxtesting.org).

Signed-off-by: Alexey Khoroshilov <khoroshilov@ispras.ru>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/sched/act_skbmod.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index e7d9638..f85313d 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -228,7 +228,6 @@ static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a,
 
 	return skb->len;
 nla_put_failure:
-	rcu_read_unlock();
 	nlmsg_trim(skb, b);
 	return -1;
 }
-- 
2.1.0


From 7c0eaeec84d14d4b85773ccac8bffe8b2eafea7c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 5 Mar 2017 10:52:16 -0800
Subject: [PATCH 025/112] dccp: fix use-after-free in dccp_feat_activate_values

[ Upstream commit 62f8f4d9066c1c6f2474845d1ca7e2891f2ae3fd ]

Dmitry reported crashes in DCCP stack [1]

Problem here is that when I got rid of listener spinlock, I missed the
fact that DCCP stores a complex state in struct dccp_request_sock,
while TCP does not.

Since multiple cpus could access it at the same time, we need to add
protection.

[1]
BUG: KASAN: use-after-free in dccp_feat_activate_values+0x967/0xab0
net/dccp/feat.c:1541 at addr ffff88003713be68
Read of size 8 by task syz-executor2/8457
CPU: 2 PID: 8457 Comm: syz-executor2 Not tainted 4.10.0-rc7+ #127
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:15 [inline]
 dump_stack+0x292/0x398 lib/dump_stack.c:51
 kasan_object_err+0x1c/0x70 mm/kasan/report.c:162
 print_address_description mm/kasan/report.c:200 [inline]
 kasan_report_error mm/kasan/report.c:289 [inline]
 kasan_report.part.1+0x20e/0x4e0 mm/kasan/report.c:311
 kasan_report mm/kasan/report.c:332 [inline]
 __asan_report_load8_noabort+0x29/0x30 mm/kasan/report.c:332
 dccp_feat_activate_values+0x967/0xab0 net/dccp/feat.c:1541
 dccp_create_openreq_child+0x464/0x610 net/dccp/minisocks.c:121
 dccp_v6_request_recv_sock+0x1f6/0x1960 net/dccp/ipv6.c:457
 dccp_check_req+0x335/0x5a0 net/dccp/minisocks.c:186
 dccp_v6_rcv+0x69e/0x1d00 net/dccp/ipv6.c:711
 ip6_input_finish+0x46d/0x17a0 net/ipv6/ip6_input.c:279
 NF_HOOK include/linux/netfilter.h:257 [inline]
 ip6_input+0xdb/0x590 net/ipv6/ip6_input.c:322
 dst_input include/net/dst.h:507 [inline]
 ip6_rcv_finish+0x289/0x890 net/ipv6/ip6_input.c:69
 NF_HOOK include/linux/netfilter.h:257 [inline]
 ipv6_rcv+0x12ec/0x23d0 net/ipv6/ip6_input.c:203
 __netif_receive_skb_core+0x1ae5/0x3400 net/core/dev.c:4190
 __netif_receive_skb+0x2a/0x170 net/core/dev.c:4228
 process_backlog+0xe5/0x6c0 net/core/dev.c:4839
 napi_poll net/core/dev.c:5202 [inline]
 net_rx_action+0xe70/0x1900 net/core/dev.c:5267
 __do_softirq+0x2fb/0xb7d kernel/softirq.c:284
 do_softirq_own_stack+0x1c/0x30 arch/x86/entry/entry_64.S:902
 </IRQ>
 do_softirq.part.17+0x1e8/0x230 kernel/softirq.c:328
 do_softirq kernel/softirq.c:176 [inline]
 __local_bh_enable_ip+0x1f2/0x200 kernel/softirq.c:181
 local_bh_enable include/linux/bottom_half.h:31 [inline]
 rcu_read_unlock_bh include/linux/rcupdate.h:971 [inline]
 ip6_finish_output2+0xbb0/0x23d0 net/ipv6/ip6_output.c:123
 ip6_finish_output+0x302/0x960 net/ipv6/ip6_output.c:148
 NF_HOOK_COND include/linux/netfilter.h:246 [inline]
 ip6_output+0x1cb/0x8d0 net/ipv6/ip6_output.c:162
 ip6_xmit+0xcdf/0x20d0 include/net/dst.h:501
 inet6_csk_xmit+0x320/0x5f0 net/ipv6/inet6_connection_sock.c:179
 dccp_transmit_skb+0xb09/0x1120 net/dccp/output.c:141
 dccp_xmit_packet+0x215/0x760 net/dccp/output.c:280
 dccp_write_xmit+0x168/0x1d0 net/dccp/output.c:362
 dccp_sendmsg+0x79c/0xb10 net/dccp/proto.c:796
 inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:744
 sock_sendmsg_nosec net/socket.c:635 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:645
 SYSC_sendto+0x660/0x810 net/socket.c:1687
 SyS_sendto+0x40/0x50 net/socket.c:1655
 entry_SYSCALL_64_fastpath+0x1f/0xc2
RIP: 0033:0x4458b9
RSP: 002b:00007f8ceb77bb58 EFLAGS: 00000282 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 0000000000000017 RCX: 00000000004458b9
RDX: 0000000000000023 RSI: 0000000020e60000 RDI: 0000000000000017
RBP: 00000000006e1b90 R08: 00000000200f9fe1 R09: 0000000000000020
R10: 0000000000008010 R11: 0000000000000282 R12: 00000000007080a8
R13: 0000000000000000 R14: 00007f8ceb77c9c0 R15: 00007f8ceb77c700
Object at ffff88003713be50, in cache kmalloc-64 size: 64
Allocated:
PID = 8446
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57
 save_stack+0x43/0xd0 mm/kasan/kasan.c:502
 set_track mm/kasan/kasan.c:514 [inline]
 kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:605
 kmem_cache_alloc_trace+0x82/0x270 mm/slub.c:2738
 kmalloc include/linux/slab.h:490 [inline]
 dccp_feat_entry_new+0x214/0x410 net/dccp/feat.c:467
 dccp_feat_push_change+0x38/0x220 net/dccp/feat.c:487
 __feat_register_sp+0x223/0x2f0 net/dccp/feat.c:741
 dccp_feat_propagate_ccid+0x22b/0x2b0 net/dccp/feat.c:949
 dccp_feat_server_ccid_dependencies+0x1b3/0x250 net/dccp/feat.c:1012
 dccp_make_response+0x1f1/0xc90 net/dccp/output.c:423
 dccp_v6_send_response+0x4ec/0xc20 net/dccp/ipv6.c:217
 dccp_v6_conn_request+0xaba/0x11b0 net/dccp/ipv6.c:377
 dccp_rcv_state_process+0x51e/0x1650 net/dccp/input.c:606
 dccp_v6_do_rcv+0x213/0x350 net/dccp/ipv6.c:632
 sk_backlog_rcv include/net/sock.h:893 [inline]
 __sk_receive_skb+0x36f/0xcc0 net/core/sock.c:479
 dccp_v6_rcv+0xba5/0x1d00 net/dccp/ipv6.c:742
 ip6_input_finish+0x46d/0x17a0 net/ipv6/ip6_input.c:279
 NF_HOOK include/linux/netfilter.h:257 [inline]
 ip6_input+0xdb/0x590 net/ipv6/ip6_input.c:322
 dst_input include/net/dst.h:507 [inline]
 ip6_rcv_finish+0x289/0x890 net/ipv6/ip6_input.c:69
 NF_HOOK include/linux/netfilter.h:257 [inline]
 ipv6_rcv+0x12ec/0x23d0 net/ipv6/ip6_input.c:203
 __netif_receive_skb_core+0x1ae5/0x3400 net/core/dev.c:4190
 __netif_receive_skb+0x2a/0x170 net/core/dev.c:4228
 process_backlog+0xe5/0x6c0 net/core/dev.c:4839
 napi_poll net/core/dev.c:5202 [inline]
 net_rx_action+0xe70/0x1900 net/core/dev.c:5267
 __do_softirq+0x2fb/0xb7d kernel/softirq.c:284
Freed:
PID = 15
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57
 save_stack+0x43/0xd0 mm/kasan/kasan.c:502
 set_track mm/kasan/kasan.c:514 [inline]
 kasan_slab_free+0x73/0xc0 mm/kasan/kasan.c:578
 slab_free_hook mm/slub.c:1355 [inline]
 slab_free_freelist_hook mm/slub.c:1377 [inline]
 slab_free mm/slub.c:2954 [inline]
 kfree+0xe8/0x2b0 mm/slub.c:3874
 dccp_feat_entry_destructor.part.4+0x48/0x60 net/dccp/feat.c:418
 dccp_feat_entry_destructor net/dccp/feat.c:416 [inline]
 dccp_feat_list_pop net/dccp/feat.c:541 [inline]
 dccp_feat_activate_values+0x57f/0xab0 net/dccp/feat.c:1543
 dccp_create_openreq_child+0x464/0x610 net/dccp/minisocks.c:121
 dccp_v6_request_recv_sock+0x1f6/0x1960 net/dccp/ipv6.c:457
 dccp_check_req+0x335/0x5a0 net/dccp/minisocks.c:186
 dccp_v6_rcv+0x69e/0x1d00 net/dccp/ipv6.c:711
 ip6_input_finish+0x46d/0x17a0 net/ipv6/ip6_input.c:279
 NF_HOOK include/linux/netfilter.h:257 [inline]
 ip6_input+0xdb/0x590 net/ipv6/ip6_input.c:322
 dst_input include/net/dst.h:507 [inline]
 ip6_rcv_finish+0x289/0x890 net/ipv6/ip6_input.c:69
 NF_HOOK include/linux/netfilter.h:257 [inline]
 ipv6_rcv+0x12ec/0x23d0 net/ipv6/ip6_input.c:203
 __netif_receive_skb_core+0x1ae5/0x3400 net/core/dev.c:4190
 __netif_receive_skb+0x2a/0x170 net/core/dev.c:4228
 process_backlog+0xe5/0x6c0 net/core/dev.c:4839
 napi_poll net/core/dev.c:5202 [inline]
 net_rx_action+0xe70/0x1900 net/core/dev.c:5267
 __do_softirq+0x2fb/0xb7d kernel/softirq.c:284
Memory state around the buggy address:
 ffff88003713bd00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 ffff88003713bd80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
>ffff88003713be00: fc fc fc fc fc fc fc fc fc fc fb fb fb fb fb fb
                                                          ^

Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Tested-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/dccp.h |  1 +
 net/dccp/minisocks.c | 24 ++++++++++++++++--------
 2 files changed, 17 insertions(+), 8 deletions(-)

diff --git a/include/linux/dccp.h b/include/linux/dccp.h
index 61d042b..6844929 100644
--- a/include/linux/dccp.h
+++ b/include/linux/dccp.h
@@ -163,6 +163,7 @@ struct dccp_request_sock {
 	__u64			 dreq_isr;
 	__u64			 dreq_gsr;
 	__be32			 dreq_service;
+	spinlock_t		 dreq_lock;
 	struct list_head	 dreq_featneg;
 	__u32			 dreq_timestamp_echo;
 	__u32			 dreq_timestamp_time;
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index d20d948..39e7e2b 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -146,6 +146,13 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
 	struct dccp_request_sock *dreq = dccp_rsk(req);
 	bool own_req;
 
+	/* TCP/DCCP listeners became lockless.
+	 * DCCP stores complex state in its request_sock, so we need
+	 * a protection for them, now this code runs without being protected
+	 * by the parent (listener) lock.
+	 */
+	spin_lock_bh(&dreq->dreq_lock);
+
 	/* Check for retransmitted REQUEST */
 	if (dccp_hdr(skb)->dccph_type == DCCP_PKT_REQUEST) {
 
@@ -160,7 +167,7 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
 			inet_rtx_syn_ack(sk, req);
 		}
 		/* Network Duplicate, discard packet */
-		return NULL;
+		goto out;
 	}
 
 	DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_PACKET_ERROR;
@@ -186,20 +193,20 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
 
 	child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL,
 							 req, &own_req);
-	if (!child)
-		goto listen_overflow;
-
-	return inet_csk_complete_hashdance(sk, child, req, own_req);
+	if (child) {
+		child = inet_csk_complete_hashdance(sk, child, req, own_req);
+		goto out;
+	}
 
-listen_overflow:
-	dccp_pr_debug("listen_overflow!\n");
 	DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_TOO_BUSY;
 drop:
 	if (dccp_hdr(skb)->dccph_type != DCCP_PKT_RESET)
 		req->rsk_ops->send_reset(sk, skb);
 
 	inet_csk_reqsk_queue_drop(sk, req);
-	return NULL;
+out:
+	spin_unlock_bh(&dreq->dreq_lock);
+	return child;
 }
 
 EXPORT_SYMBOL_GPL(dccp_check_req);
@@ -250,6 +257,7 @@ int dccp_reqsk_init(struct request_sock *req,
 {
 	struct dccp_request_sock *dreq = dccp_rsk(req);
 
+	spin_lock_init(&dreq->dreq_lock);
 	inet_rsk(req)->ir_rmt_port = dccp_hdr(skb)->dccph_sport;
 	inet_rsk(req)->ir_num	   = ntohs(dccp_hdr(skb)->dccph_dport);
 	inet_rsk(req)->acked	   = 0;
-- 
2.1.0


From db6e7796186a8d9a41e9d14b4a824c9cb80aaaf4 Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Mon, 6 Mar 2017 08:53:04 -0800
Subject: [PATCH 026/112] vrf: Fix use-after-free in vrf_xmit

[ Upstream commit f7887d40e541f74402df0684a1463c0a0bb68c68 ]

KASAN detected a use-after-free:

[  269.467067] BUG: KASAN: use-after-free in vrf_xmit+0x7f1/0x827 [vrf] at addr ffff8800350a21c0
[  269.467067] Read of size 4 by task ssh/1879
[  269.467067] CPU: 1 PID: 1879 Comm: ssh Not tainted 4.10.0+ #249
[  269.467067] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.7.5-20140531_083030-gandalf 04/01/2014
[  269.467067] Call Trace:
[  269.467067]  dump_stack+0x81/0xb6
[  269.467067]  kasan_object_err+0x21/0x78
[  269.467067]  kasan_report+0x2f7/0x450
[  269.467067]  ? vrf_xmit+0x7f1/0x827 [vrf]
[  269.467067]  ? ip_output+0xa4/0xdb
[  269.467067]  __asan_load4+0x6b/0x6d
[  269.467067]  vrf_xmit+0x7f1/0x827 [vrf]
...

Which corresponds to the skb access after xmit handling. Fix by saving
skb->len and using the saved value to update stats.

Fixes: 193125dbd8eb2 ("net: Introduce VRF device driver")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/net/vrf.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 95cf1d8..bc744ac 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -346,6 +346,7 @@ static netdev_tx_t is_ip_tx_frame(struct sk_buff *skb, struct net_device *dev)
 
 static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev)
 {
+	int len = skb->len;
 	netdev_tx_t ret = is_ip_tx_frame(skb, dev);
 
 	if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) {
@@ -353,7 +354,7 @@ static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev)
 
 		u64_stats_update_begin(&dstats->syncp);
 		dstats->tx_pkts++;
-		dstats->tx_bytes += skb->len;
+		dstats->tx_bytes += len;
 		u64_stats_update_end(&dstats->syncp);
 	} else {
 		this_cpu_inc(dev->dstats->tx_drps);
-- 
2.1.0


From b07eed8f7119d43cbfe4d2d66241bd04099e6585 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 7 Mar 2017 18:33:31 +0100
Subject: [PATCH 027/112] net/tunnel: set inner protocol in network gro hooks

[ Upstream commit 294acf1c01bace5cea5d30b510504238bf5f7c25 ]

The gso code of several tunnels type (gre and udp tunnels)
takes for granted that the skb->inner_protocol is properly
initialized and drops the packet elsewhere.

On the forwarding path no one is initializing such field,
so gro encapsulated packets are dropped on forward.

Since commit 38720352412a ("gre: Use inner_proto to obtain
inner header protocol"), this can be reproduced when the
encapsulated packets use gre as the tunneling protocol.

The issue happens also with vxlan and geneve tunnels since
commit 8bce6d7d0d1e ("udp: Generalize skb_udp_segment"), if the
forwarding host's ingress nic has h/w offload for such tunnel
and a vxlan/geneve device is configured on top of it, regardless
of the configured peer address and vni.

To address the issue, this change initialize the inner_protocol
field for encapsulated packets in both ipv4 and ipv6 gro complete
callbacks.

Fixes: 38720352412a ("gre: Use inner_proto to obtain inner header protocol")
Fixes: 8bce6d7d0d1e ("udp: Generalize skb_udp_segment")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/ipv4/af_inet.c     | 4 +++-
 net/ipv6/ip6_offload.c | 4 +++-
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 21514324..971b947 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1460,8 +1460,10 @@ int inet_gro_complete(struct sk_buff *skb, int nhoff)
 	int proto = iph->protocol;
 	int err = -ENOSYS;
 
-	if (skb->encapsulation)
+	if (skb->encapsulation) {
+		skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IP));
 		skb_set_inner_network_header(skb, nhoff);
+	}
 
 	csum_replace2(&iph->check, iph->tot_len, newlen);
 	iph->tot_len = newlen;
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index fc7b401..33b04ec 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -294,8 +294,10 @@ static int ipv6_gro_complete(struct sk_buff *skb, int nhoff)
 	struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + nhoff);
 	int err = -ENOSYS;
 
-	if (skb->encapsulation)
+	if (skb->encapsulation) {
+		skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IPV6));
 		skb_set_inner_network_header(skb, nhoff);
+	}
 
 	iph->payload_len = htons(skb->len - nhoff - sizeof(*iph));
 
-- 
2.1.0


From ccb65adc6ca6f1cf80cae474a4b8c8f6e6c36168 Mon Sep 17 00:00:00 2001
From: "Dmitry V. Levin" <ldv@altlinux.org>
Date: Tue, 7 Mar 2017 23:50:50 +0300
Subject: [PATCH 028/112] uapi: fix linux/packet_diag.h userspace compilation
 error

[ Upstream commit 745cb7f8a5de0805cade3de3991b7a95317c7c73 ]

Replace MAX_ADDR_LEN with its numeric value to fix the following
linux/packet_diag.h userspace compilation error:

/usr/include/linux/packet_diag.h:67:17: error: 'MAX_ADDR_LEN' undeclared here (not in a function)
  __u8 pdmc_addr[MAX_ADDR_LEN];

This is not the first case in the UAPI where the numeric value
of MAX_ADDR_LEN is used instead of symbolic one, uapi/linux/if_link.h
already does the same:

$ grep MAX_ADDR_LEN include/uapi/linux/if_link.h
	__u8 mac[32]; /* MAX_ADDR_LEN */

There are no UAPI headers besides these two that use MAX_ADDR_LEN.

Signed-off-by: Dmitry V. Levin <ldv@altlinux.org>
Acked-by: Pavel Emelyanov <xemul@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/uapi/linux/packet_diag.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/uapi/linux/packet_diag.h b/include/uapi/linux/packet_diag.h
index d08c63f..0c5d5dd 100644
--- a/include/uapi/linux/packet_diag.h
+++ b/include/uapi/linux/packet_diag.h
@@ -64,7 +64,7 @@ struct packet_diag_mclist {
 	__u32	pdmc_count;
 	__u16	pdmc_type;
 	__u16	pdmc_alen;
-	__u8	pdmc_addr[MAX_ADDR_LEN];
+	__u8	pdmc_addr[32]; /* MAX_ADDR_LEN */
 };
 
 struct packet_diag_ring {
-- 
2.1.0


From 47c8dc47c0080c86c9aba36f58f6fb4a7bf84c0c Mon Sep 17 00:00:00 2001
From: Etienne Noss <etienne.noss@wifirst.fr>
Date: Fri, 10 Mar 2017 16:55:32 +0100
Subject: [PATCH 029/112] act_connmark: avoid crashing on malformed nlattrs
 with null parms
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 52491c7607c5527138095edf44c53169dc1ddb82 ]

tcf_connmark_init does not check in its configuration if TCA_CONNMARK_PARMS
is set, resulting in a null pointer dereference when trying to access it.

[501099.043007] BUG: unable to handle kernel NULL pointer dereference at 0000000000000004
[501099.043039] IP: [<ffffffffc10c60fb>] tcf_connmark_init+0x8b/0x180 [act_connmark]
...
[501099.044334] Call Trace:
[501099.044345]  [<ffffffffa47270e8>] ? tcf_action_init_1+0x198/0x1b0
[501099.044363]  [<ffffffffa47271b0>] ? tcf_action_init+0xb0/0x120
[501099.044380]  [<ffffffffa47250a4>] ? tcf_exts_validate+0xc4/0x110
[501099.044398]  [<ffffffffc0f5fa97>] ? u32_set_parms+0xa7/0x270 [cls_u32]
[501099.044417]  [<ffffffffc0f60bf0>] ? u32_change+0x680/0x87b [cls_u32]
[501099.044436]  [<ffffffffa4725d1d>] ? tc_ctl_tfilter+0x4dd/0x8a0
[501099.044454]  [<ffffffffa44a23a1>] ? security_capable+0x41/0x60
[501099.044471]  [<ffffffffa470ca01>] ? rtnetlink_rcv_msg+0xe1/0x220
[501099.044490]  [<ffffffffa470c920>] ? rtnl_newlink+0x870/0x870
[501099.044507]  [<ffffffffa472cc61>] ? netlink_rcv_skb+0xa1/0xc0
[501099.044524]  [<ffffffffa47073f4>] ? rtnetlink_rcv+0x24/0x30
[501099.044541]  [<ffffffffa472c634>] ? netlink_unicast+0x184/0x230
[501099.044558]  [<ffffffffa472c9d8>] ? netlink_sendmsg+0x2f8/0x3b0
[501099.044576]  [<ffffffffa46d8880>] ? sock_sendmsg+0x30/0x40
[501099.044592]  [<ffffffffa46d8e03>] ? SYSC_sendto+0xd3/0x150
[501099.044608]  [<ffffffffa425fda1>] ? __do_page_fault+0x2d1/0x510
[501099.044626]  [<ffffffffa47fbd7b>] ? system_call_fast_compare_end+0xc/0x9b

Fixes: 22a5dc0e5e3e ("net: sched: Introduce connmark action")
Signed-off-by: Étienne Noss <etienne.noss@wifirst.fr>
Signed-off-by: Victorien Molle <victorien.molle@wifirst.fr>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/sched/act_connmark.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index eae07a2..1191179 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -113,6 +113,9 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla,
 	if (ret < 0)
 		return ret;
 
+	if (!tb[TCA_CONNMARK_PARMS])
+		return -EINVAL;
+
 	parm = nla_data(tb[TCA_CONNMARK_PARMS]);
 
 	if (!tcf_hash_check(tn, parm->index, a, bind)) {
-- 
2.1.0


From b61206e253020adbfde31f662ec7b5ea8b54935f Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Fri, 10 Mar 2017 09:46:15 -0800
Subject: [PATCH 030/112] mpls: Send route delete notifications when router
 module is unloaded

[ Upstream commit e37791ec1ad785b59022ae211f63a16189bacebf ]

When the mpls_router module is unloaded, mpls routes are deleted but
notifications are not sent to userspace leaving userspace caches
out of sync. Add the call to mpls_notify_route in mpls_net_exit as
routes are freed.

Fixes: 0189197f44160 ("mpls: Basic routing support")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/mpls/af_mpls.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 5b77377..2a21ff1 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -1696,6 +1696,7 @@ static void mpls_net_exit(struct net *net)
 	for (index = 0; index < platform_labels; index++) {
 		struct mpls_route *rt = rtnl_dereference(platform_label[index]);
 		RCU_INIT_POINTER(platform_label[index], NULL);
+		mpls_notify_route(net, index, rt, NULL, NULL);
 		mpls_rt_free(rt);
 	}
 	rtnl_unlock();
-- 
2.1.0


From 87c0286a07f93edc874c861a9159e586fc51ee6b Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Fri, 10 Mar 2017 14:11:39 -0800
Subject: [PATCH 031/112] mpls: Do not decrement alive counter for unregister
 events

[ Upstream commit 79099aab38c8f5c746748b066ae74ba984fe2cc8 ]

Multipath routes can be rendered usesless when a device in one of the
paths is deleted. For example:

$ ip -f mpls ro ls
100
	nexthop as to 200 via inet 172.16.2.2  dev virt12
	nexthop as to 300 via inet 172.16.3.2  dev br0
101
	nexthop as to 201 via inet6 2000:2::2  dev virt12
	nexthop as to 301 via inet6 2000:3::2  dev br0

$ ip li del br0

When br0 is deleted the other hop is not considered in
mpls_select_multipath because of the alive check -- rt_nhn_alive
is 0.

rt_nhn_alive is decremented once in mpls_ifdown when the device is taken
down (NETDEV_DOWN) and again when it is deleted (NETDEV_UNREGISTER). For
a 2 hop route, deleting one device drops the alive count to 0. Since
devices are taken down before unregistering, the decrement on
NETDEV_UNREGISTER is redundant.

Fixes: c89359a42e2a4 ("mpls: support for dead routes")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/mpls/af_mpls.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 2a21ff1..1309e2c 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -956,7 +956,8 @@ static void mpls_ifdown(struct net_device *dev, int event)
 				/* fall through */
 			case NETDEV_CHANGE:
 				nh->nh_flags |= RTNH_F_LINKDOWN;
-				ACCESS_ONCE(rt->rt_nhn_alive) = rt->rt_nhn_alive - 1;
+				if (event != NETDEV_UNREGISTER)
+					ACCESS_ONCE(rt->rt_nhn_alive) = rt->rt_nhn_alive - 1;
 				break;
 			}
 			if (event == NETDEV_UNREGISTER)
-- 
2.1.0


From 4a8d3bb73a821e1923ba7157b3bb364e5aeab0c9 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Mon, 13 Mar 2017 13:28:09 +0100
Subject: [PATCH 032/112] ipv6: make ECMP route replacement less greedy

[ Upstream commit 67e194007be08d071294456274dd53e0a04fdf90 ]

Commit 27596472473a ("ipv6: fix ECMP route replacement") introduced a
loop that removes all siblings of an ECMP route that is being
replaced. However, this loop doesn't stop when it has replaced
siblings, and keeps removing other routes with a higher metric.
We also end up triggering the WARN_ON after the loop, because after
this nsiblings < 0.

Instead, stop the loop when we have taken care of all routes with the
same metric as the route being replaced.

  Reproducer:
  ===========
    #!/bin/sh

    ip netns add ns1
    ip netns add ns2
    ip -net ns1 link set lo up

    for x in 0 1 2 ; do
        ip link add veth$x netns ns2 type veth peer name eth$x netns ns1
        ip -net ns1 link set eth$x up
        ip -net ns2 link set veth$x up
    done

    ip -net ns1 -6 r a 2000::/64 nexthop via fe80::0 dev eth0 \
            nexthop via fe80::1 dev eth1 nexthop via fe80::2 dev eth2
    ip -net ns1 -6 r a 2000::/64 via fe80::42 dev eth0 metric 256
    ip -net ns1 -6 r a 2000::/64 via fe80::43 dev eth0 metric 2048

    echo "before replace, 3 routes"
    ip -net ns1 -6 r | grep -v '^fe80\|^ff00'
    echo

    ip -net ns1 -6 r c 2000::/64 nexthop via fe80::4 dev eth0 \
            nexthop via fe80::5 dev eth1 nexthop via fe80::6 dev eth2

    echo "after replace, only 2 routes, metric 2048 is gone"
    ip -net ns1 -6 r | grep -v '^fe80\|^ff00'

Fixes: 27596472473a ("ipv6: fix ECMP route replacement")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Reviewed-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/ipv6/ip6_fib.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index ef54852..8c88a37 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -908,6 +908,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 			ins = &rt->dst.rt6_next;
 			iter = *ins;
 			while (iter) {
+				if (iter->rt6i_metric > rt->rt6i_metric)
+					break;
 				if (rt6_qualify_for_ecmp(iter)) {
 					*ins = iter->dst.rt6_next;
 					fib6_purge_rt(iter, fn, info->nl_net);
-- 
2.1.0


From 683100ed45761d56a5d2b3d79919ecdd12f8cbba Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 13 Mar 2017 16:24:28 +0100
Subject: [PATCH 033/112] ipv6: avoid write to a possibly cloned skb

[ Upstream commit 79e49503efe53a8c51d8b695bedc8a346c5e4a87 ]

ip6_fragment, in case skb has a fraglist, checks if the
skb is cloned.  If it is, it will move to the 'slow path' and allocates
new skbs for each fragment.

However, right before entering the slowpath loop, it updates the
nexthdr value of the last ipv6 extension header to NEXTHDR_FRAGMENT,
to account for the fragment header that will be inserted in the new
ipv6-fragment skbs.

In case original skb is cloned this munges nexthdr value of another
skb.  Avoid this by doing the nexthdr update for each of the new fragment
skbs separately.

This was observed with tcpdump on a bridge device where netfilter ipv6
reassembly is active:  tcpdump shows malformed fragment headers as
the l4 header (icmpv6, tcp, etc). is decoded as a fragment header.

Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Reported-by: Andreas Karis <akaris@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/ipv6/ip6_output.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 9a87bfb..e27b8fd 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -757,13 +757,14 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 	 *	Fragment the datagram.
 	 */
 
-	*prevhdr = NEXTHDR_FRAGMENT;
 	troom = rt->dst.dev->needed_tailroom;
 
 	/*
 	 *	Keep copying data until we run out.
 	 */
 	while (left > 0)	{
+		u8 *fragnexthdr_offset;
+
 		len = left;
 		/* IF: it doesn't fit, use 'mtu' - the data space left */
 		if (len > mtu)
@@ -808,6 +809,10 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		 */
 		skb_copy_from_linear_data(skb, skb_network_header(frag), hlen);
 
+		fragnexthdr_offset = skb_network_header(frag);
+		fragnexthdr_offset += prevhdr - skb_network_header(skb);
+		*fragnexthdr_offset = NEXTHDR_FRAGMENT;
+
 		/*
 		 *	Build fragment header.
 		 */
-- 
2.1.0


From 9bce26f224d87cd454ba567eb2e01a6b0252c052 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 13 Mar 2017 17:38:17 +0100
Subject: [PATCH 034/112] bridge: drop netfilter fake rtable unconditionally

[ Upstream commit a13b2082ece95247779b9995c4e91b4246bed023 ]

Andreas reports kernel oops during rmmod of the br_netfilter module.
Hannes debugged the oops down to a NULL rt6info->rt6i_indev.

Problem is that br_netfilter has the nasty concept of adding a fake
rtable to skb->dst; this happens in a br_netfilter prerouting hook.

A second hook (in bridge LOCAL_IN) is supposed to remove these again
before the skb is handed up the stack.

However, on module unload hooks get unregistered which means an
skb could traverse the prerouting hook that attaches the fake_rtable,
while the 'fake rtable remove' hook gets removed from the hooklist
immediately after.

Fixes: 34666d467cbf1e2e3c7 ("netfilter: bridge: move br_netfilter out of the core")
Reported-by: Andreas Karis <akaris@redhat.com>
Debugged-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/bridge/br_input.c           |  1 +
 net/bridge/br_netfilter_hooks.c | 21 ---------------------
 2 files changed, 1 insertion(+), 21 deletions(-)

diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 855b72f..267b46a 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -29,6 +29,7 @@ EXPORT_SYMBOL(br_should_route_hook);
 static int
 br_netif_receive_skb(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
+	br_drop_fake_rtable(skb);
 	return netif_receive_skb(skb);
 }
 
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 7fbdbae..aa1df1a 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -521,21 +521,6 @@ static unsigned int br_nf_pre_routing(void *priv,
 }
 
 
-/* PF_BRIDGE/LOCAL_IN ************************************************/
-/* The packet is locally destined, which requires a real
- * dst_entry, so detach the fake one.  On the way up, the
- * packet would pass through PRE_ROUTING again (which already
- * took place when the packet entered the bridge), but we
- * register an IPv4 PRE_ROUTING 'sabotage' hook that will
- * prevent this from happening. */
-static unsigned int br_nf_local_in(void *priv,
-				   struct sk_buff *skb,
-				   const struct nf_hook_state *state)
-{
-	br_drop_fake_rtable(skb);
-	return NF_ACCEPT;
-}
-
 /* PF_BRIDGE/FORWARD *************************************************/
 static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
@@ -906,12 +891,6 @@ static struct nf_hook_ops br_nf_ops[] __read_mostly = {
 		.priority = NF_BR_PRI_BRNF,
 	},
 	{
-		.hook = br_nf_local_in,
-		.pf = NFPROTO_BRIDGE,
-		.hooknum = NF_BR_LOCAL_IN,
-		.priority = NF_BR_PRI_BRNF,
-	},
-	{
 		.hook = br_nf_forward_ip,
 		.pf = NFPROTO_BRIDGE,
 		.hooknum = NF_BR_FORWARD,
-- 
2.1.0


From 98933eb36dd25cb6797768bafb9b67af84e80a70 Mon Sep 17 00:00:00 2001
From: Jon Maxwell <jmaxwell37@gmail.com>
Date: Fri, 10 Mar 2017 16:40:33 +1100
Subject: [PATCH 035/112] dccp/tcp: fix routing redirect race
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 45caeaa5ac0b4b11784ac6f932c0ad4c6b67cda0 ]

As Eric Dumazet pointed out this also needs to be fixed in IPv6.
v2: Contains the IPv6 tcp/Ipv6 dccp patches as well.

We have seen a few incidents lately where a dst_enty has been freed
with a dangling TCP socket reference (sk->sk_dst_cache) pointing to that
dst_entry. If the conditions/timings are right a crash then ensues when the
freed dst_entry is referenced later on. A Common crashing back trace is:

 #8 [] page_fault at ffffffff8163e648
    [exception RIP: __tcp_ack_snd_check+74]
.
.
 #9 [] tcp_rcv_established at ffffffff81580b64
#10 [] tcp_v4_do_rcv at ffffffff8158b54a
#11 [] tcp_v4_rcv at ffffffff8158cd02
#12 [] ip_local_deliver_finish at ffffffff815668f4
#13 [] ip_local_deliver at ffffffff81566bd9
#14 [] ip_rcv_finish at ffffffff8156656d
#15 [] ip_rcv at ffffffff81566f06
#16 [] __netif_receive_skb_core at ffffffff8152b3a2
#17 [] __netif_receive_skb at ffffffff8152b608
#18 [] netif_receive_skb at ffffffff8152b690
#19 [] vmxnet3_rq_rx_complete at ffffffffa015eeaf [vmxnet3]
#20 [] vmxnet3_poll_rx_only at ffffffffa015f32a [vmxnet3]
#21 [] net_rx_action at ffffffff8152bac2
#22 [] __do_softirq at ffffffff81084b4f
#23 [] call_softirq at ffffffff8164845c
#24 [] do_softirq at ffffffff81016fc5
#25 [] irq_exit at ffffffff81084ee5
#26 [] do_IRQ at ffffffff81648ff8

Of course it may happen with other NIC drivers as well.

It's found the freed dst_entry here:

 224 static bool tcp_in_quickack_mode(struct sock *sk)↩
 225 {↩
 226 ▹       const struct inet_connection_sock *icsk = inet_csk(sk);↩
 227 ▹       const struct dst_entry *dst = __sk_dst_get(sk);↩
 228 ↩
 229 ▹       return (dst && dst_metric(dst, RTAX_QUICKACK)) ||↩
 230 ▹       ▹       (icsk->icsk_ack.quick && !icsk->icsk_ack.pingpong);↩
 231 }↩

But there are other backtraces attributed to the same freed dst_entry in
netfilter code as well.

All the vmcores showed 2 significant clues:

- Remote hosts behind the default gateway had always been redirected to a
different gateway. A rtable/dst_entry will be added for that host. Making
more dst_entrys with lower reference counts. Making this more probable.

- All vmcores showed a postitive LockDroppedIcmps value, e.g:

LockDroppedIcmps                  267

A closer look at the tcp_v4_err() handler revealed that do_redirect() will run
regardless of whether user space has the socket locked. This can result in a
race condition where the same dst_entry cached in sk->sk_dst_entry can be
decremented twice for the same socket via:

do_redirect()->__sk_dst_check()-> dst_release().

Which leads to the dst_entry being prematurely freed with another socket
pointing to it via sk->sk_dst_cache and a subsequent crash.

To fix this skip do_redirect() if usespace has the socket locked. Instead let
the redirect take place later when user space does not have the socket
locked.

The dccp/IPv6 code is very similar in this respect, so fixing it there too.

As Eric Garver pointed out the following commit now invalidates routes. Which
can set the dst->obsolete flag so that ipv4_dst_check() returns null and
triggers the dst_release().

Fixes: ceb3320610d6 ("ipv4: Kill routes during PMTU/redirect updates.")
Cc: Eric Garver <egarver@redhat.com>
Cc: Hannes Sowa <hsowa@redhat.com>
Signed-off-by: Jon Maxwell <jmaxwell37@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/dccp/ipv4.c     | 3 ++-
 net/dccp/ipv6.c     | 8 +++++---
 net/ipv4/tcp_ipv4.c | 3 ++-
 net/ipv6/tcp_ipv6.c | 8 +++++---
 4 files changed, 14 insertions(+), 8 deletions(-)

diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index edbe59d..86b0933 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -289,7 +289,8 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
 
 	switch (type) {
 	case ICMP_REDIRECT:
-		dccp_do_redirect(skb, sk);
+		if (!sock_owned_by_user(sk))
+			dccp_do_redirect(skb, sk);
 		goto out;
 	case ICMP_SOURCE_QUENCH:
 		/* Just silently ignore these. */
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 7506c03..237d62c 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -122,10 +122,12 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	np = inet6_sk(sk);
 
 	if (type == NDISC_REDIRECT) {
-		struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
+		if (!sock_owned_by_user(sk)) {
+			struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
 
-		if (dst)
-			dst->ops->redirect(dst, sk, skb);
+			if (dst)
+				dst->ops->redirect(dst, sk, skb);
+		}
 		goto out;
 	}
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 5bb809f..6988566 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -421,7 +421,8 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 
 	switch (type) {
 	case ICMP_REDIRECT:
-		do_redirect(icmp_skb, sk);
+		if (!sock_owned_by_user(sk))
+			do_redirect(icmp_skb, sk);
 		goto out;
 	case ICMP_SOURCE_QUENCH:
 		/* Just silently ignore these. */
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 6673965..b2e61a0 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -375,10 +375,12 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	np = inet6_sk(sk);
 
 	if (type == NDISC_REDIRECT) {
-		struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
+		if (!sock_owned_by_user(sk)) {
+			struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
 
-		if (dst)
-			dst->ops->redirect(dst, sk, skb);
+			if (dst)
+				dst->ops->redirect(dst, sk, skb);
+		}
 		goto out;
 	}
 
-- 
2.1.0


From beaa66cce55689076cacd3b6b290886d503eaa35 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Mon, 13 Mar 2017 00:00:26 +0100
Subject: [PATCH 036/112] tun: fix premature POLLOUT notification on tun
 devices
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit b20e2d54789c6acbf6bd0efdbec2cf5fa4d90ef1 ]

aszlig observed failing ssh tunnels (-w) during initialization since
commit cc9da6cc4f56e0 ("ipv6: addrconf: use stable address generator for
ARPHRD_NONE"). We already had reports that the mentioned commit breaks
Juniper VPN connections. I can't clearly say that the Juniper VPN client
has the same problem, but it is worth a try to hint to this patch.

Because of the early generation of link local addresses, the kernel now
can start asking for routers on the local subnet much earlier than usual.
Those router solicitation packets arrive inside the ssh channels and
should be transmitted to the tun fd before the configuration scripts
might have upped the interface and made it ready for transmission.

ssh polls on the interface and receives back a POLL_OUT. It tries to send
the earily router solicitation packet to the tun interface.  Unfortunately
it hasn't been up'ed yet by config scripts, thus failing with -EIO. ssh
doesn't retry again and considers the tun interface broken forever.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=121131
Fixes: cc9da6cc4f56 ("ipv6: addrconf: use stable address generator for ARPHRD_NONE")
Cc: Bjørn Mork <bjorn@mork.no>
Reported-by: Valdis Kletnieks <Valdis.Kletnieks@vt.edu>
Cc: Valdis Kletnieks <Valdis.Kletnieks@vt.edu>
Reported-by: Jonas Lippuner <jonas@lippuner.ca>
Cc: Jonas Lippuner <jonas@lippuner.ca>
Reported-by: aszlig <aszlig@redmoonstudios.org>
Cc: aszlig <aszlig@redmoonstudios.org>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/net/tun.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index b31aca8..a931b73 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -819,7 +819,18 @@ static void tun_net_uninit(struct net_device *dev)
 /* Net device open. */
 static int tun_net_open(struct net_device *dev)
 {
+	struct tun_struct *tun = netdev_priv(dev);
+	int i;
+
 	netif_tx_start_all_queues(dev);
+
+	for (i = 0; i < tun->numqueues; i++) {
+		struct tun_file *tfile;
+
+		tfile = rtnl_dereference(tun->tfiles[i]);
+		tfile->socket.sk->sk_write_space(tfile->socket.sk);
+	}
+
 	return 0;
 }
 
@@ -1116,9 +1127,10 @@ static unsigned int tun_chr_poll(struct file *file, poll_table *wait)
 	if (!skb_array_empty(&tfile->tx_array))
 		mask |= POLLIN | POLLRDNORM;
 
-	if (sock_writeable(sk) ||
-	    (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) &&
-	     sock_writeable(sk)))
+	if (tun->dev->flags & IFF_UP &&
+	    (sock_writeable(sk) ||
+	     (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) &&
+	      sock_writeable(sk))))
 		mask |= POLLOUT | POLLWRNORM;
 
 	if (tun->dev->reg_state != NETREG_REGISTERED)
-- 
2.1.0


From 9e38375a4b1748946ab46a317def3046bb425f1e Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Mon, 13 Mar 2017 00:01:30 +0100
Subject: [PATCH 037/112] dccp: fix memory leak during tear-down of
 unsuccessful connection request

[ Upstream commit 72ef9c4125c7b257e3a714d62d778ab46583d6a3 ]

This patch fixes a memory leak, which happens if the connection request
is not fulfilled between parsing the DCCP options and handling the SYN
(because e.g. the backlog is full), because we forgot to free the
list of ack vectors.

Reported-by: Jianwen Ji <jiji@redhat.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/dccp/ccids/ccid2.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c
index f053198..5e3a730 100644
--- a/net/dccp/ccids/ccid2.c
+++ b/net/dccp/ccids/ccid2.c
@@ -749,6 +749,7 @@ static void ccid2_hc_tx_exit(struct sock *sk)
 	for (i = 0; i < hc->tx_seqbufc; i++)
 		kfree(hc->tx_seqbuf[i]);
 	hc->tx_seqbufc = 0;
+	dccp_ackvec_parsed_cleanup(&hc->tx_av_chunks);
 }
 
 static void ccid2_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb)
-- 
2.1.0


From 1411707acb85c514c603f692327c98db48127900 Mon Sep 17 00:00:00 2001
From: Thomas Graf <tgraf@suug.ch>
Date: Tue, 18 Oct 2016 19:51:19 +0200
Subject: [PATCH 038/112] bpf: Detect identical PTR_TO_MAP_VALUE_OR_NULL
 registers

[ Upstream commit 57a09bf0a416700676e77102c28f9cfcb48267e0 ]

A BPF program is required to check the return register of a
map_elem_lookup() call before accessing memory. The verifier keeps
track of this by converting the type of the result register from
PTR_TO_MAP_VALUE_OR_NULL to PTR_TO_MAP_VALUE after a conditional
jump ensures safety. This check is currently exclusively performed
for the result register 0.

In the event the compiler reorders instructions, BPF_MOV64_REG
instructions may be moved before the conditional jump which causes
them to keep their type PTR_TO_MAP_VALUE_OR_NULL to which the
verifier objects when the register is accessed:

0: (b7) r1 = 10
1: (7b) *(u64 *)(r10 -8) = r1
2: (bf) r2 = r10
3: (07) r2 += -8
4: (18) r1 = 0x59c00000
6: (85) call 1
7: (bf) r4 = r0
8: (15) if r0 == 0x0 goto pc+1
 R0=map_value(ks=8,vs=8) R4=map_value_or_null(ks=8,vs=8) R10=fp
9: (7a) *(u64 *)(r4 +0) = 0
R4 invalid mem access 'map_value_or_null'

This commit extends the verifier to keep track of all identical
PTR_TO_MAP_VALUE_OR_NULL registers after a map_elem_lookup() by
assigning them an ID and then marking them all when the conditional
jump is observed.

Signed-off-by: Thomas Graf <tgraf@suug.ch>
Reviewed-by: Josef Bacik <jbacik@fb.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/bpf_verifier.h |  2 +-
 kernel/bpf/verifier.c        | 61 ++++++++++++++++++++++++++++++++------------
 2 files changed, 46 insertions(+), 17 deletions(-)

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 6aaf425..7453c12 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -24,13 +24,13 @@ struct bpf_reg_state {
 	 */
 	s64 min_value;
 	u64 max_value;
+	u32 id;
 	union {
 		/* valid when type == CONST_IMM | PTR_TO_STACK | UNKNOWN_VALUE */
 		s64 imm;
 
 		/* valid when type == PTR_TO_PACKET* */
 		struct {
-			u32 id;
 			u16 off;
 			u16 range;
 		};
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 8199821..c428c9f 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -212,9 +212,10 @@ static void print_verifier_state(struct bpf_verifier_state *state)
 		else if (t == CONST_PTR_TO_MAP || t == PTR_TO_MAP_VALUE ||
 			 t == PTR_TO_MAP_VALUE_OR_NULL ||
 			 t == PTR_TO_MAP_VALUE_ADJ)
-			verbose("(ks=%d,vs=%d)",
+			verbose("(ks=%d,vs=%d,id=%u)",
 				reg->map_ptr->key_size,
-				reg->map_ptr->value_size);
+				reg->map_ptr->value_size,
+				reg->id);
 		if (reg->min_value != BPF_REGISTER_MIN_RANGE)
 			verbose(",min_value=%lld",
 				(long long)reg->min_value);
@@ -447,6 +448,7 @@ static void mark_reg_unknown_value(struct bpf_reg_state *regs, u32 regno)
 {
 	BUG_ON(regno >= MAX_BPF_REG);
 	regs[regno].type = UNKNOWN_VALUE;
+	regs[regno].id = 0;
 	regs[regno].imm = 0;
 }
 
@@ -1252,6 +1254,7 @@ static int check_call(struct bpf_verifier_env *env, int func_id)
 			return -EINVAL;
 		}
 		regs[BPF_REG_0].map_ptr = meta.map_ptr;
+		regs[BPF_REG_0].id = ++env->id_gen;
 	} else {
 		verbose("unknown return type %d of func %d\n",
 			fn->ret_type, func_id);
@@ -1668,8 +1671,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 						insn->src_reg);
 					return -EACCES;
 				}
-				regs[insn->dst_reg].type = UNKNOWN_VALUE;
-				regs[insn->dst_reg].map_ptr = NULL;
+				mark_reg_unknown_value(regs, insn->dst_reg);
 			}
 		} else {
 			/* case: R = imm
@@ -1931,6 +1933,38 @@ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg,
 	check_reg_overflow(true_reg);
 }
 
+static void mark_map_reg(struct bpf_reg_state *regs, u32 regno, u32 id,
+			 enum bpf_reg_type type)
+{
+	struct bpf_reg_state *reg = &regs[regno];
+
+	if (reg->type == PTR_TO_MAP_VALUE_OR_NULL && reg->id == id) {
+		reg->type = type;
+		if (type == UNKNOWN_VALUE)
+			mark_reg_unknown_value(regs, regno);
+	}
+}
+
+/* The logic is similar to find_good_pkt_pointers(), both could eventually
+ * be folded together at some point.
+ */
+static void mark_map_regs(struct bpf_verifier_state *state, u32 regno,
+			  enum bpf_reg_type type)
+{
+	struct bpf_reg_state *regs = state->regs;
+	int i;
+
+	for (i = 0; i < MAX_BPF_REG; i++)
+		mark_map_reg(regs, i, regs[regno].id, type);
+
+	for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
+		if (state->stack_slot_type[i] != STACK_SPILL)
+			continue;
+		mark_map_reg(state->spilled_regs, i / BPF_REG_SIZE,
+			     regs[regno].id, type);
+	}
+}
+
 static int check_cond_jmp_op(struct bpf_verifier_env *env,
 			     struct bpf_insn *insn, int *insn_idx)
 {
@@ -2018,18 +2052,13 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 	if (BPF_SRC(insn->code) == BPF_K &&
 	    insn->imm == 0 && (opcode == BPF_JEQ || opcode == BPF_JNE) &&
 	    dst_reg->type == PTR_TO_MAP_VALUE_OR_NULL) {
-		if (opcode == BPF_JEQ) {
-			/* next fallthrough insn can access memory via
-			 * this register
-			 */
-			regs[insn->dst_reg].type = PTR_TO_MAP_VALUE;
-			/* branch targer cannot access it, since reg == 0 */
-			mark_reg_unknown_value(other_branch->regs,
-					       insn->dst_reg);
-		} else {
-			other_branch->regs[insn->dst_reg].type = PTR_TO_MAP_VALUE;
-			mark_reg_unknown_value(regs, insn->dst_reg);
-		}
+		/* Mark all identical map registers in each branch as either
+		 * safe or unknown depending R == 0 or R != 0 conditional.
+		 */
+		mark_map_regs(this_branch, insn->dst_reg,
+			      opcode == BPF_JEQ ? PTR_TO_MAP_VALUE : UNKNOWN_VALUE);
+		mark_map_regs(other_branch, insn->dst_reg,
+			      opcode == BPF_JEQ ? UNKNOWN_VALUE : PTR_TO_MAP_VALUE);
 	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT &&
 		   dst_reg->type == PTR_TO_PACKET &&
 		   regs[insn->src_reg].type == PTR_TO_PACKET_END) {
-- 
2.1.0


From b7f5aa1ca0bedbd109be7563f6a94c9a37714537 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@fb.com>
Date: Wed, 7 Dec 2016 10:57:59 -0800
Subject: [PATCH 039/112] bpf: fix state equivalence

[ Upstream commit d2a4dd37f6b41fbcad76efbf63124eb3126c66fe ]

Commmits 57a09bf0a416 ("bpf: Detect identical PTR_TO_MAP_VALUE_OR_NULL registers")
and 484611357c19 ("bpf: allow access into map value arrays") by themselves
are correct, but in combination they make state equivalence ignore 'id' field
of the register state which can lead to accepting invalid program.

Fixes: 57a09bf0a416 ("bpf: Detect identical PTR_TO_MAP_VALUE_OR_NULL registers")
Fixes: 484611357c19 ("bpf: allow access into map value arrays")
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/bpf_verifier.h | 14 +++++++-------
 kernel/bpf/verifier.c        |  2 +-
 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 7453c12..a13b031 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -18,13 +18,6 @@
 
 struct bpf_reg_state {
 	enum bpf_reg_type type;
-	/*
-	 * Used to determine if any memory access using this register will
-	 * result in a bad access.
-	 */
-	s64 min_value;
-	u64 max_value;
-	u32 id;
 	union {
 		/* valid when type == CONST_IMM | PTR_TO_STACK | UNKNOWN_VALUE */
 		s64 imm;
@@ -40,6 +33,13 @@ struct bpf_reg_state {
 		 */
 		struct bpf_map *map_ptr;
 	};
+	u32 id;
+	/* Used to determine if any memory access using this register will
+	 * result in a bad access. These two fields must be last.
+	 * See states_equal()
+	 */
+	s64 min_value;
+	u64 max_value;
 };
 
 enum bpf_stack_slot_type {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c428c9f..6036d1e 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2498,7 +2498,7 @@ static bool states_equal(struct bpf_verifier_env *env,
 		 * we didn't do a variable access into a map then we are a-ok.
 		 */
 		if (!varlen_map_access &&
-		    rold->type == rcur->type && rold->imm == rcur->imm)
+		    memcmp(rold, rcur, offsetofend(struct bpf_reg_state, id)) == 0)
 			continue;
 
 		/* If we didn't map access then again we don't care about the
-- 
2.1.0


From 1889d6d9b5e767c7070ad31f93371dcb05b0cea4 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 15 Dec 2016 01:30:06 +0100
Subject: [PATCH 040/112] bpf: fix regression on verifier pruning wrt map
 lookups

[ Upstream commit a08dd0da5307ba01295c8383923e51e7997c3576 ]

Commit 57a09bf0a416 ("bpf: Detect identical PTR_TO_MAP_VALUE_OR_NULL
registers") introduced a regression where existing programs stopped
loading due to reaching the verifier's maximum complexity limit,
whereas prior to this commit they were loading just fine; the affected
program has roughly 2k instructions.

What was found is that state pruning couldn't be performed effectively
anymore due to mismatches of the verifier's register state, in particular
in the id tracking. It doesn't mean that 57a09bf0a416 is incorrect per
se, but rather that verifier needs to perform a lot more work for the
same program with regards to involved map lookups.

Since commit 57a09bf0a416 is only about tracking registers with type
PTR_TO_MAP_VALUE_OR_NULL, the id is only needed to follow registers
until they are promoted through pattern matching with a NULL check to
either PTR_TO_MAP_VALUE or UNKNOWN_VALUE type. After that point, the
id becomes irrelevant for the transitioned types.

For UNKNOWN_VALUE, id is already reset to 0 via mark_reg_unknown_value(),
but not so for PTR_TO_MAP_VALUE where id is becoming stale. It's even
transferred further into other types that don't make use of it. Among
others, one example is where UNKNOWN_VALUE is set on function call
return with RET_INTEGER return type.

states_equal() will then fall through the memcmp() on register state;
note that the second memcmp() uses offsetofend(), so the id is part of
that since d2a4dd37f6b4 ("bpf: fix state equivalence"). But the bisect
pointed already to 57a09bf0a416, where we really reach beyond complexity
limit. What I found was that states_equal() often failed in this
case due to id mismatches in spilled regs with registers in type
PTR_TO_MAP_VALUE. Unlike non-spilled regs, spilled regs just perform
a memcmp() on their reg state and don't have any other optimizations
in place, therefore also id was relevant in this case for making a
pruning decision.

We can safely reset id to 0 as well when converting to PTR_TO_MAP_VALUE.
For the affected program, it resulted in a ~17 fold reduction of
complexity and let the program load fine again. Selftest suite also
runs fine. The only other place where env->id_gen is used currently is
through direct packet access, but for these cases id is long living, thus
a different scenario.

Also, the current logic in mark_map_regs() is not fully correct when
marking NULL branch with UNKNOWN_VALUE. We need to cache the destination
reg's id in any case. Otherwise, once we marked that reg as UNKNOWN_VALUE,
it's id is reset and any subsequent registers that hold the original id
and are of type PTR_TO_MAP_VALUE_OR_NULL won't be marked UNKNOWN_VALUE
anymore, since mark_map_reg() reuses the uncached regs[regno].id that
was just overridden. Note, we don't need to cache it outside of
mark_map_regs(), since it's called once on this_branch and the other
time on other_branch, which are both two independent verifier states.
A test case for this is added here, too.

Fixes: 57a09bf0a416 ("bpf: Detect identical PTR_TO_MAP_VALUE_OR_NULL registers")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Thomas Graf <tgraf@suug.ch>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 kernel/bpf/verifier.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 6036d1e..a967ae8 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1940,6 +1940,11 @@ static void mark_map_reg(struct bpf_reg_state *regs, u32 regno, u32 id,
 
 	if (reg->type == PTR_TO_MAP_VALUE_OR_NULL && reg->id == id) {
 		reg->type = type;
+		/* We don't need id from this point onwards anymore, thus we
+		 * should better reset it, so that state pruning has chances
+		 * to take effect.
+		 */
+		reg->id = 0;
 		if (type == UNKNOWN_VALUE)
 			mark_reg_unknown_value(regs, regno);
 	}
@@ -1952,16 +1957,16 @@ static void mark_map_regs(struct bpf_verifier_state *state, u32 regno,
 			  enum bpf_reg_type type)
 {
 	struct bpf_reg_state *regs = state->regs;
+	u32 id = regs[regno].id;
 	int i;
 
 	for (i = 0; i < MAX_BPF_REG; i++)
-		mark_map_reg(regs, i, regs[regno].id, type);
+		mark_map_reg(regs, i, id, type);
 
 	for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
 		if (state->stack_slot_type[i] != STACK_SPILL)
 			continue;
-		mark_map_reg(state->spilled_regs, i / BPF_REG_SIZE,
-			     regs[regno].id, type);
+		mark_map_reg(state->spilled_regs, i / BPF_REG_SIZE, id, type);
 	}
 }
 
-- 
2.1.0


From 0e0f1d6fdb353fc886ee99d646c561e4ad3d4ebc Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Sun, 18 Dec 2016 01:52:59 +0100
Subject: [PATCH 041/112] bpf: fix mark_reg_unknown_value for spilled regs on
 map value marking

[ Upstream commit 6760bf2ddde8ad64f8205a651223a93de3a35494 ]

Martin reported a verifier issue that hit the BUG_ON() for his
test case in the mark_reg_unknown_value() function:

  [  202.861380] kernel BUG at kernel/bpf/verifier.c:467!
  [...]
  [  203.291109] Call Trace:
  [  203.296501]  [<ffffffff811364d5>] mark_map_reg+0x45/0x50
  [  203.308225]  [<ffffffff81136558>] mark_map_regs+0x78/0x90
  [  203.320140]  [<ffffffff8113938d>] do_check+0x226d/0x2c90
  [  203.331865]  [<ffffffff8113a6ab>] bpf_check+0x48b/0x780
  [  203.343403]  [<ffffffff81134c8e>] bpf_prog_load+0x27e/0x440
  [  203.355705]  [<ffffffff8118a38f>] ? handle_mm_fault+0x11af/0x1230
  [  203.369158]  [<ffffffff812d8188>] ? security_capable+0x48/0x60
  [  203.382035]  [<ffffffff811351a4>] SyS_bpf+0x124/0x960
  [  203.393185]  [<ffffffff810515f6>] ? __do_page_fault+0x276/0x490
  [  203.406258]  [<ffffffff816db320>] entry_SYSCALL_64_fastpath+0x13/0x94

This issue got uncovered after the fix in a08dd0da5307 ("bpf: fix
regression on verifier pruning wrt map lookups"). The reason why it
wasn't noticed before was, because as mentioned in a08dd0da5307,
mark_map_regs() was doing the id matching incorrectly based on the
uncached regs[regno].id. So, in the first loop, we walked all regs
and as soon as we found regno == i, then this reg's id was cleared
when calling mark_reg_unknown_value() thus that every subsequent
register was probed against id of 0 (which, in combination with the
PTR_TO_MAP_VALUE_OR_NULL type is an invalid condition that no other
register state can hold), and therefore wasn't type transitioned such
as in the spilled register case for the second loop.

Now since that got fixed, it turned out that 57a09bf0a416 ("bpf:
Detect identical PTR_TO_MAP_VALUE_OR_NULL registers") used
mark_reg_unknown_value() incorrectly for the spilled regs, and thus
hitting the BUG_ON() in some cases due to regno >= MAX_BPF_REG.

Although spilled regs have the same type as the non-spilled regs
for the verifier state, that is, struct bpf_reg_state, they are
semantically different from the non-spilled regs. In other words,
there can be up to 64 (MAX_BPF_STACK / BPF_REG_SIZE) spilled regs
in the stack, for example, register R<x> could have been spilled by
the program to stack location X, Y, Z, and in mark_map_regs() we
need to scan these stack slots of type STACK_SPILL for potential
registers that we have to transition from PTR_TO_MAP_VALUE_OR_NULL.
Therefore, depending on the location, the spilled_regs regno can
be a lot higher than just MAX_BPF_REG's value since we operate on
stack instead. The reset in mark_reg_unknown_value() itself is
just fine, only that the BUG_ON() was inappropriate for this. Fix
it by making a __mark_reg_unknown_value() version that can be
called from mark_map_reg() generically; we know for the non-spilled
case that the regno is always < MAX_BPF_REG anyway.

Fixes: 57a09bf0a416 ("bpf: Detect identical PTR_TO_MAP_VALUE_OR_NULL registers")
Reported-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 kernel/bpf/verifier.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index a967ae8..85d1c94 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -444,14 +444,19 @@ static void init_reg_state(struct bpf_reg_state *regs)
 	regs[BPF_REG_1].type = PTR_TO_CTX;
 }
 
-static void mark_reg_unknown_value(struct bpf_reg_state *regs, u32 regno)
+static void __mark_reg_unknown_value(struct bpf_reg_state *regs, u32 regno)
 {
-	BUG_ON(regno >= MAX_BPF_REG);
 	regs[regno].type = UNKNOWN_VALUE;
 	regs[regno].id = 0;
 	regs[regno].imm = 0;
 }
 
+static void mark_reg_unknown_value(struct bpf_reg_state *regs, u32 regno)
+{
+	BUG_ON(regno >= MAX_BPF_REG);
+	__mark_reg_unknown_value(regs, regno);
+}
+
 static void reset_reg_range_values(struct bpf_reg_state *regs, u32 regno)
 {
 	regs[regno].min_value = BPF_REGISTER_MIN_RANGE;
@@ -1946,7 +1951,7 @@ static void mark_map_reg(struct bpf_reg_state *regs, u32 regno, u32 id,
 		 */
 		reg->id = 0;
 		if (type == UNKNOWN_VALUE)
-			mark_reg_unknown_value(regs, regno);
+			__mark_reg_unknown_value(regs, regno);
 	}
 }
 
-- 
2.1.0


From 2382c1486c62a21d162f0d457c61cd87a2498ffd Mon Sep 17 00:00:00 2001
From: Krister Johansen <kjlx@templeofstupid.com>
Date: Wed, 4 Jan 2017 01:22:52 -0800
Subject: [PATCH 042/112] dmaengine: iota: ioat_alloc_chan_resources should not
 perform sleeping allocations.

commit 21d25f6a4217e755906cb548b55ddab39d0e88b9 upstream.

On a kernel with DEBUG_LOCKS, ioat_free_chan_resources triggers an
in_interrupt() warning.  With PROVE_LOCKING, it reports detecting a
SOFTIRQ-safe to SOFTIRQ-unsafe lock ordering in the same code path.

This is because dma_generic_alloc_coherent() checks if the GFP flags
permit blocking.  It allocates from different subsystems if blocking is
permitted.  The free path knows how to return the memory to the correct
allocator.  If GFP_KERNEL is specified then the alloc and free end up
going through cma_alloc(), which uses mutexes.

Given that ioat_free_chan_resources() can be called in interrupt
context, ioat_alloc_chan_resources() must specify GFP_NOWAIT so that the
allocations do not block and instead use an allocator that uses
spinlocks.

Signed-off-by: Krister Johansen <kjlx@templeofstupid.com>
Acked-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/dma/ioat/init.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/dma/ioat/init.c b/drivers/dma/ioat/init.c
index 015f711..d235fbe 100644
--- a/drivers/dma/ioat/init.c
+++ b/drivers/dma/ioat/init.c
@@ -691,7 +691,7 @@ static int ioat_alloc_chan_resources(struct dma_chan *c)
 	/* doing 2 32bit writes to mmio since 1 64b write doesn't work */
 	ioat_chan->completion =
 		dma_pool_zalloc(ioat_chan->ioat_dma->completion_pool,
-				GFP_KERNEL, &ioat_chan->completion_dma);
+				GFP_NOWAIT, &ioat_chan->completion_dma);
 	if (!ioat_chan->completion)
 		return -ENOMEM;
 
@@ -701,7 +701,7 @@ static int ioat_alloc_chan_resources(struct dma_chan *c)
 	       ioat_chan->reg_base + IOAT_CHANCMP_OFFSET_HIGH);
 
 	order = IOAT_MAX_ORDER;
-	ring = ioat_alloc_ring(c, order, GFP_KERNEL);
+	ring = ioat_alloc_ring(c, order, GFP_NOWAIT);
 	if (!ring)
 		return -ENOMEM;
 
-- 
2.1.0


From 4b40611a9b7e5d06626674af898608167ac3f727 Mon Sep 17 00:00:00 2001
From: Dan Streetman <ddstreet@ieee.org>
Date: Fri, 17 Mar 2017 00:48:18 +0000
Subject: [PATCH 043/112] xen: do not re-use pirq number cached in pci device
 msi msg data

[ Upstream commit c74fd80f2f41d05f350bb478151021f88551afe8 ]

Revert the main part of commit:
af42b8d12f8a ("xen: fix MSI setup and teardown for PV on HVM guests")

That commit introduced reading the pci device's msi message data to see
if a pirq was previously configured for the device's msi/msix, and re-use
that pirq.  At the time, that was the correct behavior.  However, a
later change to Qemu caused it to call into the Xen hypervisor to unmap
all pirqs for a pci device, when the pci device disables its MSI/MSIX
vectors; specifically the Qemu commit:
c976437c7dba9c7444fb41df45468968aaa326ad
("qemu-xen: free all the pirqs for msi/msix when driver unload")

Once Qemu added this pirq unmapping, it was no longer correct for the
kernel to re-use the pirq number cached in the pci device msi message
data.  All Qemu releases since 2.1.0 contain the patch that unmaps the
pirqs when the pci device disables its MSI/MSIX vectors.

This bug is causing failures to initialize multiple NVMe controllers
under Xen, because the NVMe driver sets up a single MSIX vector for
each controller (concurrently), and then after using that to talk to
the controller for some configuration data, it disables the single MSIX
vector and re-configures all the MSIX vectors it needs.  So the MSIX
setup code tries to re-use the cached pirq from the first vector
for each controller, but the hypervisor has already given away that
pirq to another controller, and its initialization fails.

This is discussed in more detail at:
https://lists.xen.org/archives/html/xen-devel/2017-01/msg00447.html

Fixes: af42b8d12f8a ("xen: fix MSI setup and teardown for PV on HVM guests")
Signed-off-by: Dan Streetman <dan.streetman@canonical.com>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
Acked-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/x86/pci/xen.c | 23 +++++++----------------
 1 file changed, 7 insertions(+), 16 deletions(-)

diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index bedfab9..a00a6c0 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -234,23 +234,14 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 		return 1;
 
 	for_each_pci_msi_entry(msidesc, dev) {
-		__pci_read_msi_msg(msidesc, &msg);
-		pirq = MSI_ADDR_EXT_DEST_ID(msg.address_hi) |
-			((msg.address_lo >> MSI_ADDR_DEST_ID_SHIFT) & 0xff);
-		if (msg.data != XEN_PIRQ_MSI_DATA ||
-		    xen_irq_from_pirq(pirq) < 0) {
-			pirq = xen_allocate_pirq_msi(dev, msidesc);
-			if (pirq < 0) {
-				irq = -ENODEV;
-				goto error;
-			}
-			xen_msi_compose_msg(dev, pirq, &msg);
-			__pci_write_msi_msg(msidesc, &msg);
-			dev_dbg(&dev->dev, "xen: msi bound to pirq=%d\n", pirq);
-		} else {
-			dev_dbg(&dev->dev,
-				"xen: msi already bound to pirq=%d\n", pirq);
+		pirq = xen_allocate_pirq_msi(dev, msidesc);
+		if (pirq < 0) {
+			irq = -ENODEV;
+			goto error;
 		}
+		xen_msi_compose_msg(dev, pirq, &msg);
+		__pci_write_msi_msg(msidesc, &msg);
+		dev_dbg(&dev->dev, "xen: msi bound to pirq=%d\n", pirq);
 		irq = xen_bind_pirq_msi_to_irq(dev, msidesc, pirq,
 					       (type == PCI_CAP_ID_MSI) ? nvec : 1,
 					       (type == PCI_CAP_ID_MSIX) ?
-- 
2.1.0


From 15ffc931eeb94d9673c2a163828704a7cf4c1df5 Mon Sep 17 00:00:00 2001
From: Chris J Arges <christopherarges@gmail.com>
Date: Fri, 17 Mar 2017 00:48:19 +0000
Subject: [PATCH 044/112] igb: Workaround for igb i210 firmware issue

[ Upstream commit 4e684f59d760a2c7c716bb60190783546e2d08a1 ]

Sometimes firmware may not properly initialize I347AT4_PAGE_SELECT causing
the probe of an igb i210 NIC to fail. This patch adds an addition zeroing
of this register during igb_get_phy_id to workaround this issue.

Thanks for Jochen Henneberg for the idea and original patch.

Signed-off-by: Chris J Arges <christopherarges@gmail.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/net/ethernet/intel/igb/e1000_phy.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/intel/igb/e1000_phy.c b/drivers/net/ethernet/intel/igb/e1000_phy.c
index 5b54254..569ee25 100644
--- a/drivers/net/ethernet/intel/igb/e1000_phy.c
+++ b/drivers/net/ethernet/intel/igb/e1000_phy.c
@@ -77,6 +77,10 @@ s32 igb_get_phy_id(struct e1000_hw *hw)
 	s32 ret_val = 0;
 	u16 phy_id;
 
+	/* ensure PHY page selection to fix misconfigured i210 */
+	if (hw->mac.type == e1000_i210)
+		phy->ops.write_reg(hw, I347AT4_PAGE_SELECT, 0);
+
 	ret_val = phy->ops.read_reg(hw, PHY_ID1, &phy_id);
 	if (ret_val)
 		goto out;
-- 
2.1.0


From 61229e62c1aa4d397aab9949325cab49acfd7dab Mon Sep 17 00:00:00 2001
From: Todd Fujinaka <todd.fujinaka@intel.com>
Date: Fri, 17 Mar 2017 00:48:19 +0000
Subject: [PATCH 045/112] igb: add i211 to i210 PHY workaround

[ Upstream commit 5bc8c230e2a993b49244f9457499f17283da9ec7 ]

i210 and i211 share the same PHY but have different PCI IDs. Don't
forget i211 for any i210 workarounds.

Signed-off-by: Todd Fujinaka <todd.fujinaka@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/net/ethernet/intel/igb/e1000_phy.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/igb/e1000_phy.c b/drivers/net/ethernet/intel/igb/e1000_phy.c
index 569ee25..2788a54 100644
--- a/drivers/net/ethernet/intel/igb/e1000_phy.c
+++ b/drivers/net/ethernet/intel/igb/e1000_phy.c
@@ -78,7 +78,7 @@ s32 igb_get_phy_id(struct e1000_hw *hw)
 	u16 phy_id;
 
 	/* ensure PHY page selection to fix misconfigured i210 */
-	if (hw->mac.type == e1000_i210)
+	if ((hw->mac.type == e1000_i210) || (hw->mac.type == e1000_i211))
 		phy->ops.write_reg(hw, I347AT4_PAGE_SELECT, 0);
 
 	ret_val = phy->ops.read_reg(hw, PHY_ID1, &phy_id);
-- 
2.1.0


From 0ad1d7660a57152ab6c7ae8ff5d02b6460b281a8 Mon Sep 17 00:00:00 2001
From: Michael Cyr <mikecyr@us.ibm.com>
Date: Fri, 17 Mar 2017 00:48:20 +0000
Subject: [PATCH 046/112] scsi: ibmvscsis: Issues from Dan Carpenter/Smatch

[ Upstream commit 11950d70b52d2bc5e3580da8cd63909ef38d67db ]

Signed-off-by: Michael Cyr <mikecyr@us.ibm.com>
Signed-off-by: Bryant G. Ly <bryantly@linux.vnet.ibm.com>
Tested-by: Steven Royer <seroyer@linux.vnet.ibm.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c | 13 +++----------
 1 file changed, 3 insertions(+), 10 deletions(-)

diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
index 91dfd58..292a3f3 100644
--- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
+++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
@@ -1746,14 +1746,7 @@ static long ibmvscsis_mad(struct scsi_info *vscsi, struct viosrp_crq *crq)
 
 		pr_debug("mad: type %d\n", be32_to_cpu(mad->type));
 
-		if (be16_to_cpu(mad->length) < 0) {
-			dev_err(&vscsi->dev, "mad: length is < 0\n");
-			ibmvscsis_post_disconnect(vscsi,
-						  ERR_DISCONNECT_RECONNECT, 0);
-			rc = SRP_VIOLATION;
-		} else {
-			rc = ibmvscsis_process_mad(vscsi, iue);
-		}
+		rc = ibmvscsis_process_mad(vscsi, iue);
 
 		pr_debug("mad: status %hd, rc %ld\n", be16_to_cpu(mad->status),
 			 rc);
@@ -2523,7 +2516,6 @@ static void ibmvscsis_parse_cmd(struct scsi_info *vscsi,
 		dev_err(&vscsi->dev, "0x%llx: parsing SRP descriptor table failed.\n",
 			srp->tag);
 		goto fail;
-		return;
 	}
 
 	cmd->rsp.sol_not = srp->sol_not;
@@ -3379,7 +3371,8 @@ static int ibmvscsis_probe(struct vio_dev *vdev,
 	INIT_LIST_HEAD(&vscsi->waiting_rsp);
 	INIT_LIST_HEAD(&vscsi->active_q);
 
-	snprintf(vscsi->tport.tport_name, 256, "%s", dev_name(&vdev->dev));
+	snprintf(vscsi->tport.tport_name, IBMVSCSIS_NAMELEN, "%s",
+		 dev_name(&vdev->dev));
 
 	pr_debug("probe tport_name: %s\n", vscsi->tport.tport_name);
 
-- 
2.1.0


From 29022860df8efabdf0a2d356fd614d4dba2791a5 Mon Sep 17 00:00:00 2001
From: Michael Cyr <mikecyr@us.ibm.com>
Date: Fri, 17 Mar 2017 00:48:20 +0000
Subject: [PATCH 047/112] scsi: ibmvscsis: Return correct partition name/# to
 client

[ Upstream commit 9c93cf03d4eb3dc58931ff7cac0af9c344fe5e0b ]

Signed-off-by: Michael Cyr <mikecyr@us.ibm.com>
Signed-off-by: Bryant G. Ly <bryantly@linux.vnet.ibm.com>
Tested-by: Steven Royer <seroyer@linux.vnet.ibm.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
index 292a3f3..8d5eeb1 100644
--- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
+++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
@@ -3387,6 +3387,9 @@ static int ibmvscsis_probe(struct vio_dev *vdev,
 	strncat(vscsi->eye, vdev->name, MAX_EYE);
 
 	vscsi->dds.unit_id = vdev->unit_address;
+	strncpy(vscsi->dds.partition_name, partition_name,
+		sizeof(vscsi->dds.partition_name));
+	vscsi->dds.partition_num = partition_number;
 
 	spin_lock_bh(&ibmvscsis_dev_lock);
 	list_add_tail(&vscsi->list, &ibmvscsis_dev_list);
@@ -3603,7 +3606,7 @@ static int ibmvscsis_get_system_info(void)
 
 	num = of_get_property(rootdn, "ibm,partition-no", NULL);
 	if (num)
-		partition_number = *num;
+		partition_number = of_read_number(num, 1);
 
 	of_node_put(rootdn);
 
-- 
2.1.0


From 4d36f4859fa443e02e7834b9a5ce01b63f7af2c3 Mon Sep 17 00:00:00 2001
From: Michael Cyr <mikecyr@us.ibm.com>
Date: Fri, 17 Mar 2017 00:48:20 +0000
Subject: [PATCH 048/112] scsi: ibmvscsis: Clean up properly if
 target_submit_cmd/tmr fails

[ Upstream commit 7435b32e2d2fb5da6c2ae9b9c8ce56d8a3cb3bc3 ]

Signed-off-by: Michael Cyr <mikecyr@us.ibm.com>
Signed-off-by: Bryant G. Ly <bryantly@linux.vnet.ibm.com>
Tested-by: Steven Royer <seroyer@linux.vnet.ibm.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
index 8d5eeb1..e4cd8ff 100644
--- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
+++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
@@ -2552,6 +2552,10 @@ static void ibmvscsis_parse_cmd(struct scsi_info *vscsi,
 			       data_len, attr, dir, 0);
 	if (rc) {
 		dev_err(&vscsi->dev, "target_submit_cmd failed, rc %d\n", rc);
+		spin_lock_bh(&vscsi->intr_lock);
+		list_del(&cmd->list);
+		ibmvscsis_free_cmd_resources(vscsi, cmd);
+		spin_unlock_bh(&vscsi->intr_lock);
 		goto fail;
 	}
 	return;
@@ -2631,6 +2635,9 @@ static void ibmvscsis_parse_task(struct scsi_info *vscsi,
 		if (rc) {
 			dev_err(&vscsi->dev, "target_submit_tmr failed, rc %d\n",
 				rc);
+			spin_lock_bh(&vscsi->intr_lock);
+			list_del(&cmd->list);
+			spin_unlock_bh(&vscsi->intr_lock);
 			cmd->se_cmd.se_tmr_req->response =
 				TMR_FUNCTION_REJECTED;
 		}
-- 
2.1.0


From 189491f81cf639d2d0292334580b9969c8a424df Mon Sep 17 00:00:00 2001
From: Michael Cyr <mikecyr@us.ibm.com>
Date: Fri, 17 Mar 2017 00:48:21 +0000
Subject: [PATCH 049/112] scsi: ibmvscsis: Rearrange functions for future
 patches

[ Upstream commit 79fac9c9b74f4951c9ce82b22e714bcc34ae4a56 ]

This patch reorders functions in a manner necessary for a follow-on
patch.  It also makes some minor styling changes (mostly removing extra
spaces) and fixes some typos.

There are no code changes in this patch, with one exception: due to the
reordering of the functions, I needed to explicitly declare a function
at the top of the file.  However, this will be removed in the next patch,
since the code requiring the predeclaration will be removed.

Signed-off-by: Michael Cyr <mikecyr@us.ibm.com>
Signed-off-by: Bryant G. Ly <bryantly@linux.vnet.ibm.com>
Tested-by: Steven Royer <seroyer@linux.vnet.ibm.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c | 796 ++++++++++++++++---------------
 1 file changed, 399 insertions(+), 397 deletions(-)

diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
index e4cd8ff..4feae43 100644
--- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
+++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
@@ -22,7 +22,7 @@
  *
  ****************************************************************************/
 
-#define pr_fmt(fmt)     KBUILD_MODNAME ": " fmt
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
 #include <linux/module.h>
 #include <linux/kernel.h>
@@ -62,6 +62,8 @@ static long ibmvscsis_parse_command(struct scsi_info *vscsi,
 
 static void ibmvscsis_adapter_idle(struct scsi_info *vscsi);
 
+static void ibmvscsis_reset_queue(struct scsi_info *vscsi, uint new_state);
+
 static void ibmvscsis_determine_resid(struct se_cmd *se_cmd,
 				      struct srp_rsp *rsp)
 {
@@ -82,7 +84,7 @@ static void ibmvscsis_determine_resid(struct se_cmd *se_cmd,
 		}
 	} else if (se_cmd->se_cmd_flags & SCF_OVERFLOW_BIT) {
 		if (se_cmd->data_direction == DMA_TO_DEVICE) {
-			/*  residual data from an overflow write */
+			/* residual data from an overflow write */
 			rsp->flags = SRP_RSP_FLAG_DOOVER;
 			rsp->data_out_res_cnt = cpu_to_be32(residual_count);
 		} else if (se_cmd->data_direction == DMA_FROM_DEVICE) {
@@ -102,7 +104,7 @@ static void ibmvscsis_determine_resid(struct se_cmd *se_cmd,
  * and the function returns TRUE.
  *
  * EXECUTION ENVIRONMENT:
- *      Interrupt or Process environment
+ *	Interrupt or Process environment
  */
 static bool connection_broken(struct scsi_info *vscsi)
 {
@@ -325,7 +327,7 @@ static struct viosrp_crq *ibmvscsis_cmd_q_dequeue(uint mask,
 }
 
 /**
- * ibmvscsis_send_init_message() -  send initialize message to the client
+ * ibmvscsis_send_init_message() - send initialize message to the client
  * @vscsi:	Pointer to our adapter structure
  * @format:	Which Init Message format to send
  *
@@ -383,13 +385,13 @@ static long ibmvscsis_check_init_msg(struct scsi_info *vscsi, uint *format)
 					      vscsi->cmd_q.base_addr);
 		if (crq) {
 			*format = (uint)(crq->format);
-			rc =  ERROR;
+			rc = ERROR;
 			crq->valid = INVALIDATE_CMD_RESP_EL;
 			dma_rmb();
 		}
 	} else {
 		*format = (uint)(crq->format);
-		rc =  ERROR;
+		rc = ERROR;
 		crq->valid = INVALIDATE_CMD_RESP_EL;
 		dma_rmb();
 	}
@@ -398,166 +400,6 @@ static long ibmvscsis_check_init_msg(struct scsi_info *vscsi, uint *format)
 }
 
 /**
- * ibmvscsis_establish_new_q() - Establish new CRQ queue
- * @vscsi:	Pointer to our adapter structure
- * @new_state:	New state being established after resetting the queue
- *
- * Must be called with interrupt lock held.
- */
-static long ibmvscsis_establish_new_q(struct scsi_info *vscsi,  uint new_state)
-{
-	long rc = ADAPT_SUCCESS;
-	uint format;
-
-	vscsi->flags &= PRESERVE_FLAG_FIELDS;
-	vscsi->rsp_q_timer.timer_pops = 0;
-	vscsi->debit = 0;
-	vscsi->credit = 0;
-
-	rc = vio_enable_interrupts(vscsi->dma_dev);
-	if (rc) {
-		pr_warn("reset_queue: failed to enable interrupts, rc %ld\n",
-			rc);
-		return rc;
-	}
-
-	rc = ibmvscsis_check_init_msg(vscsi, &format);
-	if (rc) {
-		dev_err(&vscsi->dev, "reset_queue: check_init_msg failed, rc %ld\n",
-			rc);
-		return rc;
-	}
-
-	if (format == UNUSED_FORMAT && new_state == WAIT_CONNECTION) {
-		rc = ibmvscsis_send_init_message(vscsi, INIT_MSG);
-		switch (rc) {
-		case H_SUCCESS:
-		case H_DROPPED:
-		case H_CLOSED:
-			rc = ADAPT_SUCCESS;
-			break;
-
-		case H_PARAMETER:
-		case H_HARDWARE:
-			break;
-
-		default:
-			vscsi->state = UNDEFINED;
-			rc = H_HARDWARE;
-			break;
-		}
-	}
-
-	return rc;
-}
-
-/**
- * ibmvscsis_reset_queue() - Reset CRQ Queue
- * @vscsi:	Pointer to our adapter structure
- * @new_state:	New state to establish after resetting the queue
- *
- * This function calls h_free_q and then calls h_reg_q and does all
- * of the bookkeeping to get us back to where we can communicate.
- *
- * Actually, we don't always call h_free_crq.  A problem was discovered
- * where one partition would close and reopen his queue, which would
- * cause his partner to get a transport event, which would cause him to
- * close and reopen his queue, which would cause the original partition
- * to get a transport event, etc., etc.  To prevent this, we don't
- * actually close our queue if the client initiated the reset, (i.e.
- * either we got a transport event or we have detected that the client's
- * queue is gone)
- *
- * EXECUTION ENVIRONMENT:
- *	Process environment, called with interrupt lock held
- */
-static void ibmvscsis_reset_queue(struct scsi_info *vscsi, uint new_state)
-{
-	int bytes;
-	long rc = ADAPT_SUCCESS;
-
-	pr_debug("reset_queue: flags 0x%x\n", vscsi->flags);
-
-	/* don't reset, the client did it for us */
-	if (vscsi->flags & (CLIENT_FAILED | TRANS_EVENT)) {
-		vscsi->flags &=  PRESERVE_FLAG_FIELDS;
-		vscsi->rsp_q_timer.timer_pops = 0;
-		vscsi->debit = 0;
-		vscsi->credit = 0;
-		vscsi->state = new_state;
-		vio_enable_interrupts(vscsi->dma_dev);
-	} else {
-		rc = ibmvscsis_free_command_q(vscsi);
-		if (rc == ADAPT_SUCCESS) {
-			vscsi->state = new_state;
-
-			bytes = vscsi->cmd_q.size * PAGE_SIZE;
-			rc = h_reg_crq(vscsi->dds.unit_id,
-				       vscsi->cmd_q.crq_token, bytes);
-			if (rc == H_CLOSED || rc == H_SUCCESS) {
-				rc = ibmvscsis_establish_new_q(vscsi,
-							       new_state);
-			}
-
-			if (rc != ADAPT_SUCCESS) {
-				pr_debug("reset_queue: reg_crq rc %ld\n", rc);
-
-				vscsi->state = ERR_DISCONNECTED;
-				vscsi->flags |=  RESPONSE_Q_DOWN;
-				ibmvscsis_free_command_q(vscsi);
-			}
-		} else {
-			vscsi->state = ERR_DISCONNECTED;
-			vscsi->flags |= RESPONSE_Q_DOWN;
-		}
-	}
-}
-
-/**
- * ibmvscsis_free_cmd_resources() - Free command resources
- * @vscsi:	Pointer to our adapter structure
- * @cmd:	Command which is not longer in use
- *
- * Must be called with interrupt lock held.
- */
-static void ibmvscsis_free_cmd_resources(struct scsi_info *vscsi,
-					 struct ibmvscsis_cmd *cmd)
-{
-	struct iu_entry *iue = cmd->iue;
-
-	switch (cmd->type) {
-	case TASK_MANAGEMENT:
-	case SCSI_CDB:
-		/*
-		 * When the queue goes down this value is cleared, so it
-		 * cannot be cleared in this general purpose function.
-		 */
-		if (vscsi->debit)
-			vscsi->debit -= 1;
-		break;
-	case ADAPTER_MAD:
-		vscsi->flags &= ~PROCESSING_MAD;
-		break;
-	case UNSET_TYPE:
-		break;
-	default:
-		dev_err(&vscsi->dev, "free_cmd_resources unknown type %d\n",
-			cmd->type);
-		break;
-	}
-
-	cmd->iue = NULL;
-	list_add_tail(&cmd->list, &vscsi->free_cmd);
-	srp_iu_put(iue);
-
-	if (list_empty(&vscsi->active_q) && list_empty(&vscsi->schedule_q) &&
-	    list_empty(&vscsi->waiting_rsp) && (vscsi->flags & WAIT_FOR_IDLE)) {
-		vscsi->flags &= ~WAIT_FOR_IDLE;
-		complete(&vscsi->wait_idle);
-	}
-}
-
-/**
  * ibmvscsis_disconnect() - Helper function to disconnect
  * @work:	Pointer to work_struct, gives access to our adapter structure
  *
@@ -590,7 +432,7 @@ static void ibmvscsis_disconnect(struct work_struct *work)
 	 * should transitition to the new state
 	 */
 	switch (vscsi->state) {
-	/*  Should never be called while in this state. */
+	/* Should never be called while in this state. */
 	case NO_QUEUE:
 	/*
 	 * Can never transition from this state;
@@ -726,84 +568,394 @@ static void ibmvscsis_disconnect(struct work_struct *work)
  * the new state (if the one passed in is more "severe" than the
  * previous one).
  *
- * PRECONDITION:
- *	interrupt lock is held
+ * PRECONDITION:
+ *	interrupt lock is held
+ */
+static void ibmvscsis_post_disconnect(struct scsi_info *vscsi, uint new_state,
+				      uint flag_bits)
+{
+	uint state;
+
+	/* check the validity of the new state */
+	switch (new_state) {
+	case UNCONFIGURING:
+	case ERR_DISCONNECT:
+	case ERR_DISCONNECT_RECONNECT:
+	case WAIT_IDLE:
+		break;
+
+	default:
+		dev_err(&vscsi->dev, "post_disconnect: Invalid new state %d\n",
+			new_state);
+		return;
+	}
+
+	vscsi->flags |= flag_bits;
+
+	pr_debug("post_disconnect: new_state 0x%x, flag_bits 0x%x, vscsi->flags 0x%x, state %hx\n",
+		 new_state, flag_bits, vscsi->flags, vscsi->state);
+
+	if (!(vscsi->flags & (DISCONNECT_SCHEDULED | SCHEDULE_DISCONNECT))) {
+		vscsi->flags |= SCHEDULE_DISCONNECT;
+		vscsi->new_state = new_state;
+
+		INIT_WORK(&vscsi->proc_work, ibmvscsis_disconnect);
+		(void)queue_work(vscsi->work_q, &vscsi->proc_work);
+	} else {
+		if (vscsi->new_state)
+			state = vscsi->new_state;
+		else
+			state = vscsi->state;
+
+		switch (state) {
+		case NO_QUEUE:
+		case UNCONFIGURING:
+			break;
+
+		case ERR_DISCONNECTED:
+		case ERR_DISCONNECT:
+		case UNDEFINED:
+			if (new_state == UNCONFIGURING)
+				vscsi->new_state = new_state;
+			break;
+
+		case ERR_DISCONNECT_RECONNECT:
+			switch (new_state) {
+			case UNCONFIGURING:
+			case ERR_DISCONNECT:
+				vscsi->new_state = new_state;
+				break;
+			default:
+				break;
+			}
+			break;
+
+		case WAIT_ENABLED:
+		case PART_UP_WAIT_ENAB:
+		case WAIT_IDLE:
+		case WAIT_CONNECTION:
+		case CONNECTED:
+		case SRP_PROCESSING:
+			vscsi->new_state = new_state;
+			break;
+
+		default:
+			break;
+		}
+	}
+
+	pr_debug("Leaving post_disconnect: flags 0x%x, new_state 0x%x\n",
+		 vscsi->flags, vscsi->new_state);
+}
+
+/**
+ * ibmvscsis_handle_init_compl_msg() - Respond to an Init Complete Message
+ * @vscsi:	Pointer to our adapter structure
+ *
+ * Must be called with interrupt lock held.
+ */
+static long ibmvscsis_handle_init_compl_msg(struct scsi_info *vscsi)
+{
+	long rc = ADAPT_SUCCESS;
+
+	switch (vscsi->state) {
+	case NO_QUEUE:
+	case ERR_DISCONNECT:
+	case ERR_DISCONNECT_RECONNECT:
+	case ERR_DISCONNECTED:
+	case UNCONFIGURING:
+	case UNDEFINED:
+		rc = ERROR;
+		break;
+
+	case WAIT_CONNECTION:
+		vscsi->state = CONNECTED;
+		break;
+
+	case WAIT_IDLE:
+	case SRP_PROCESSING:
+	case CONNECTED:
+	case WAIT_ENABLED:
+	case PART_UP_WAIT_ENAB:
+	default:
+		rc = ERROR;
+		dev_err(&vscsi->dev, "init_msg: invalid state %d to get init compl msg\n",
+			vscsi->state);
+		ibmvscsis_post_disconnect(vscsi, ERR_DISCONNECT_RECONNECT, 0);
+		break;
+	}
+
+	return rc;
+}
+
+/**
+ * ibmvscsis_handle_init_msg() - Respond to an Init Message
+ * @vscsi:	Pointer to our adapter structure
+ *
+ * Must be called with interrupt lock held.
+ */
+static long ibmvscsis_handle_init_msg(struct scsi_info *vscsi)
+{
+	long rc = ADAPT_SUCCESS;
+
+	switch (vscsi->state) {
+	case WAIT_ENABLED:
+		vscsi->state = PART_UP_WAIT_ENAB;
+		break;
+
+	case WAIT_CONNECTION:
+		rc = ibmvscsis_send_init_message(vscsi, INIT_COMPLETE_MSG);
+		switch (rc) {
+		case H_SUCCESS:
+			vscsi->state = CONNECTED;
+			break;
+
+		case H_PARAMETER:
+			dev_err(&vscsi->dev, "init_msg: failed to send, rc %ld\n",
+				rc);
+			ibmvscsis_post_disconnect(vscsi, ERR_DISCONNECT, 0);
+			break;
+
+		case H_DROPPED:
+			dev_err(&vscsi->dev, "init_msg: failed to send, rc %ld\n",
+				rc);
+			rc = ERROR;
+			ibmvscsis_post_disconnect(vscsi,
+						  ERR_DISCONNECT_RECONNECT, 0);
+			break;
+
+		case H_CLOSED:
+			pr_warn("init_msg: failed to send, rc %ld\n", rc);
+			rc = 0;
+			break;
+		}
+		break;
+
+	case UNDEFINED:
+		rc = ERROR;
+		break;
+
+	case UNCONFIGURING:
+		break;
+
+	case PART_UP_WAIT_ENAB:
+	case CONNECTED:
+	case SRP_PROCESSING:
+	case WAIT_IDLE:
+	case NO_QUEUE:
+	case ERR_DISCONNECT:
+	case ERR_DISCONNECT_RECONNECT:
+	case ERR_DISCONNECTED:
+	default:
+		rc = ERROR;
+		dev_err(&vscsi->dev, "init_msg: invalid state %d to get init msg\n",
+			vscsi->state);
+		ibmvscsis_post_disconnect(vscsi, ERR_DISCONNECT_RECONNECT, 0);
+		break;
+	}
+
+	return rc;
+}
+
+/**
+ * ibmvscsis_init_msg() - Respond to an init message
+ * @vscsi:	Pointer to our adapter structure
+ * @crq:	Pointer to CRQ element containing the Init Message
+ *
+ * EXECUTION ENVIRONMENT:
+ *	Interrupt, interrupt lock held
+ */
+static long ibmvscsis_init_msg(struct scsi_info *vscsi, struct viosrp_crq *crq)
+{
+	long rc = ADAPT_SUCCESS;
+
+	pr_debug("init_msg: state 0x%hx\n", vscsi->state);
+
+	rc = h_vioctl(vscsi->dds.unit_id, H_GET_PARTNER_INFO,
+		      (u64)vscsi->map_ioba | ((u64)PAGE_SIZE << 32), 0, 0, 0,
+		      0);
+	if (rc == H_SUCCESS) {
+		vscsi->client_data.partition_number =
+			be64_to_cpu(*(u64 *)vscsi->map_buf);
+		pr_debug("init_msg, part num %d\n",
+			 vscsi->client_data.partition_number);
+	} else {
+		pr_debug("init_msg h_vioctl rc %ld\n", rc);
+		rc = ADAPT_SUCCESS;
+	}
+
+	if (crq->format == INIT_MSG) {
+		rc = ibmvscsis_handle_init_msg(vscsi);
+	} else if (crq->format == INIT_COMPLETE_MSG) {
+		rc = ibmvscsis_handle_init_compl_msg(vscsi);
+	} else {
+		rc = ERROR;
+		dev_err(&vscsi->dev, "init_msg: invalid format %d\n",
+			(uint)crq->format);
+		ibmvscsis_post_disconnect(vscsi, ERR_DISCONNECT_RECONNECT, 0);
+	}
+
+	return rc;
+}
+
+/**
+ * ibmvscsis_establish_new_q() - Establish new CRQ queue
+ * @vscsi:	Pointer to our adapter structure
+ * @new_state:	New state being established after resetting the queue
+ *
+ * Must be called with interrupt lock held.
+ */
+static long ibmvscsis_establish_new_q(struct scsi_info *vscsi, uint new_state)
+{
+	long rc = ADAPT_SUCCESS;
+	uint format;
+
+	vscsi->flags &= PRESERVE_FLAG_FIELDS;
+	vscsi->rsp_q_timer.timer_pops = 0;
+	vscsi->debit = 0;
+	vscsi->credit = 0;
+
+	rc = vio_enable_interrupts(vscsi->dma_dev);
+	if (rc) {
+		pr_warn("reset_queue: failed to enable interrupts, rc %ld\n",
+			rc);
+		return rc;
+	}
+
+	rc = ibmvscsis_check_init_msg(vscsi, &format);
+	if (rc) {
+		dev_err(&vscsi->dev, "reset_queue: check_init_msg failed, rc %ld\n",
+			rc);
+		return rc;
+	}
+
+	if (format == UNUSED_FORMAT && new_state == WAIT_CONNECTION) {
+		rc = ibmvscsis_send_init_message(vscsi, INIT_MSG);
+		switch (rc) {
+		case H_SUCCESS:
+		case H_DROPPED:
+		case H_CLOSED:
+			rc = ADAPT_SUCCESS;
+			break;
+
+		case H_PARAMETER:
+		case H_HARDWARE:
+			break;
+
+		default:
+			vscsi->state = UNDEFINED;
+			rc = H_HARDWARE;
+			break;
+		}
+	}
+
+	return rc;
+}
+
+/**
+ * ibmvscsis_reset_queue() - Reset CRQ Queue
+ * @vscsi:	Pointer to our adapter structure
+ * @new_state:	New state to establish after resetting the queue
+ *
+ * This function calls h_free_q and then calls h_reg_q and does all
+ * of the bookkeeping to get us back to where we can communicate.
+ *
+ * Actually, we don't always call h_free_crq.  A problem was discovered
+ * where one partition would close and reopen his queue, which would
+ * cause his partner to get a transport event, which would cause him to
+ * close and reopen his queue, which would cause the original partition
+ * to get a transport event, etc., etc.  To prevent this, we don't
+ * actually close our queue if the client initiated the reset, (i.e.
+ * either we got a transport event or we have detected that the client's
+ * queue is gone)
+ *
+ * EXECUTION ENVIRONMENT:
+ *	Process environment, called with interrupt lock held
+ */
+static void ibmvscsis_reset_queue(struct scsi_info *vscsi, uint new_state)
+{
+	int bytes;
+	long rc = ADAPT_SUCCESS;
+
+	pr_debug("reset_queue: flags 0x%x\n", vscsi->flags);
+
+	/* don't reset, the client did it for us */
+	if (vscsi->flags & (CLIENT_FAILED | TRANS_EVENT)) {
+		vscsi->flags &= PRESERVE_FLAG_FIELDS;
+		vscsi->rsp_q_timer.timer_pops = 0;
+		vscsi->debit = 0;
+		vscsi->credit = 0;
+		vscsi->state = new_state;
+		vio_enable_interrupts(vscsi->dma_dev);
+	} else {
+		rc = ibmvscsis_free_command_q(vscsi);
+		if (rc == ADAPT_SUCCESS) {
+			vscsi->state = new_state;
+
+			bytes = vscsi->cmd_q.size * PAGE_SIZE;
+			rc = h_reg_crq(vscsi->dds.unit_id,
+				       vscsi->cmd_q.crq_token, bytes);
+			if (rc == H_CLOSED || rc == H_SUCCESS) {
+				rc = ibmvscsis_establish_new_q(vscsi,
+							       new_state);
+			}
+
+			if (rc != ADAPT_SUCCESS) {
+				pr_debug("reset_queue: reg_crq rc %ld\n", rc);
+
+				vscsi->state = ERR_DISCONNECTED;
+				vscsi->flags |= RESPONSE_Q_DOWN;
+				ibmvscsis_free_command_q(vscsi);
+			}
+		} else {
+			vscsi->state = ERR_DISCONNECTED;
+			vscsi->flags |= RESPONSE_Q_DOWN;
+		}
+	}
+}
+
+/**
+ * ibmvscsis_free_cmd_resources() - Free command resources
+ * @vscsi:	Pointer to our adapter structure
+ * @cmd:	Command which is not longer in use
+ *
+ * Must be called with interrupt lock held.
  */
-static void ibmvscsis_post_disconnect(struct scsi_info *vscsi, uint new_state,
-				      uint flag_bits)
+static void ibmvscsis_free_cmd_resources(struct scsi_info *vscsi,
+					 struct ibmvscsis_cmd *cmd)
 {
-	uint state;
+	struct iu_entry *iue = cmd->iue;
 
-	/* check the validity of the new state */
-	switch (new_state) {
-	case UNCONFIGURING:
-	case ERR_DISCONNECT:
-	case ERR_DISCONNECT_RECONNECT:
-	case WAIT_IDLE:
+	switch (cmd->type) {
+	case TASK_MANAGEMENT:
+	case SCSI_CDB:
+		/*
+		 * When the queue goes down this value is cleared, so it
+		 * cannot be cleared in this general purpose function.
+		 */
+		if (vscsi->debit)
+			vscsi->debit -= 1;
+		break;
+	case ADAPTER_MAD:
+		vscsi->flags &= ~PROCESSING_MAD;
+		break;
+	case UNSET_TYPE:
 		break;
-
 	default:
-		dev_err(&vscsi->dev, "post_disconnect: Invalid new state %d\n",
-			new_state);
-		return;
+		dev_err(&vscsi->dev, "free_cmd_resources unknown type %d\n",
+			cmd->type);
+		break;
 	}
 
-	vscsi->flags |= flag_bits;
-
-	pr_debug("post_disconnect: new_state 0x%x, flag_bits 0x%x, vscsi->flags 0x%x, state %hx\n",
-		 new_state, flag_bits, vscsi->flags, vscsi->state);
-
-	if (!(vscsi->flags & (DISCONNECT_SCHEDULED | SCHEDULE_DISCONNECT))) {
-		vscsi->flags |= SCHEDULE_DISCONNECT;
-		vscsi->new_state = new_state;
-
-		INIT_WORK(&vscsi->proc_work, ibmvscsis_disconnect);
-		(void)queue_work(vscsi->work_q, &vscsi->proc_work);
-	} else {
-		if (vscsi->new_state)
-			state = vscsi->new_state;
-		else
-			state = vscsi->state;
-
-		switch (state) {
-		case NO_QUEUE:
-		case UNCONFIGURING:
-			break;
-
-		case ERR_DISCONNECTED:
-		case ERR_DISCONNECT:
-		case UNDEFINED:
-			if (new_state == UNCONFIGURING)
-				vscsi->new_state = new_state;
-			break;
-
-		case ERR_DISCONNECT_RECONNECT:
-			switch (new_state) {
-			case UNCONFIGURING:
-			case ERR_DISCONNECT:
-				vscsi->new_state = new_state;
-				break;
-			default:
-				break;
-			}
-			break;
-
-		case WAIT_ENABLED:
-		case PART_UP_WAIT_ENAB:
-		case WAIT_IDLE:
-		case WAIT_CONNECTION:
-		case CONNECTED:
-		case SRP_PROCESSING:
-			vscsi->new_state = new_state;
-			break;
+	cmd->iue = NULL;
+	list_add_tail(&cmd->list, &vscsi->free_cmd);
+	srp_iu_put(iue);
 
-		default:
-			break;
-		}
+	if (list_empty(&vscsi->active_q) && list_empty(&vscsi->schedule_q) &&
+	    list_empty(&vscsi->waiting_rsp) && (vscsi->flags & WAIT_FOR_IDLE)) {
+		vscsi->flags &= ~WAIT_FOR_IDLE;
+		complete(&vscsi->wait_idle);
 	}
-
-	pr_debug("Leaving post_disconnect: flags 0x%x, new_state 0x%x\n",
-		 vscsi->flags, vscsi->new_state);
 }
 
 /**
@@ -896,7 +1048,7 @@ static long ibmvscsis_trans_event(struct scsi_info *vscsi,
 		}
 	}
 
-	rc =  vscsi->flags & SCHEDULE_DISCONNECT;
+	rc = vscsi->flags & SCHEDULE_DISCONNECT;
 
 	pr_debug("Leaving trans_event: flags 0x%x, state 0x%hx, rc %ld\n",
 		 vscsi->flags, vscsi->state, rc);
@@ -1221,7 +1373,7 @@ static long ibmvscsis_copy_crq_packet(struct scsi_info *vscsi,
  * @iue:	Information Unit containing the Adapter Info MAD request
  *
  * EXECUTION ENVIRONMENT:
- *	Interrupt adpater lock is held
+ *	Interrupt adapter lock is held
  */
 static long ibmvscsis_adapter_info(struct scsi_info *vscsi,
 				   struct iu_entry *iue)
@@ -1692,7 +1844,7 @@ static void ibmvscsis_send_mad_resp(struct scsi_info *vscsi,
  * @crq:	Pointer to the CRQ entry containing the MAD request
  *
  * EXECUTION ENVIRONMENT:
- *	Interrupt  called with adapter lock held
+ *	Interrupt, called with adapter lock held
  */
 static long ibmvscsis_mad(struct scsi_info *vscsi, struct viosrp_crq *crq)
 {
@@ -1858,7 +2010,7 @@ static long ibmvscsis_srp_login_rej(struct scsi_info *vscsi,
 		break;
 	case H_PERMISSION:
 		if (connection_broken(vscsi))
-			flag_bits =  RESPONSE_Q_DOWN | CLIENT_FAILED;
+			flag_bits = RESPONSE_Q_DOWN | CLIENT_FAILED;
 		dev_err(&vscsi->dev, "login_rej: error copying to client, rc %ld\n",
 			rc);
 		ibmvscsis_post_disconnect(vscsi, ERR_DISCONNECT_RECONNECT,
@@ -2181,156 +2333,6 @@ static long ibmvscsis_ping_response(struct scsi_info *vscsi)
 }
 
 /**
- * ibmvscsis_handle_init_compl_msg() - Respond to an Init Complete Message
- * @vscsi:	Pointer to our adapter structure
- *
- * Must be called with interrupt lock held.
- */
-static long ibmvscsis_handle_init_compl_msg(struct scsi_info *vscsi)
-{
-	long rc = ADAPT_SUCCESS;
-
-	switch (vscsi->state) {
-	case NO_QUEUE:
-	case ERR_DISCONNECT:
-	case ERR_DISCONNECT_RECONNECT:
-	case ERR_DISCONNECTED:
-	case UNCONFIGURING:
-	case UNDEFINED:
-		rc = ERROR;
-		break;
-
-	case WAIT_CONNECTION:
-		vscsi->state = CONNECTED;
-		break;
-
-	case WAIT_IDLE:
-	case SRP_PROCESSING:
-	case CONNECTED:
-	case WAIT_ENABLED:
-	case PART_UP_WAIT_ENAB:
-	default:
-		rc = ERROR;
-		dev_err(&vscsi->dev, "init_msg: invalid state %d to get init compl msg\n",
-			vscsi->state);
-		ibmvscsis_post_disconnect(vscsi, ERR_DISCONNECT_RECONNECT, 0);
-		break;
-	}
-
-	return rc;
-}
-
-/**
- * ibmvscsis_handle_init_msg() - Respond to an Init Message
- * @vscsi:	Pointer to our adapter structure
- *
- * Must be called with interrupt lock held.
- */
-static long ibmvscsis_handle_init_msg(struct scsi_info *vscsi)
-{
-	long rc = ADAPT_SUCCESS;
-
-	switch (vscsi->state) {
-	case WAIT_ENABLED:
-		vscsi->state = PART_UP_WAIT_ENAB;
-		break;
-
-	case WAIT_CONNECTION:
-		rc = ibmvscsis_send_init_message(vscsi, INIT_COMPLETE_MSG);
-		switch (rc) {
-		case H_SUCCESS:
-			vscsi->state = CONNECTED;
-			break;
-
-		case H_PARAMETER:
-			dev_err(&vscsi->dev, "init_msg: failed to send, rc %ld\n",
-				rc);
-			ibmvscsis_post_disconnect(vscsi, ERR_DISCONNECT, 0);
-			break;
-
-		case H_DROPPED:
-			dev_err(&vscsi->dev, "init_msg: failed to send, rc %ld\n",
-				rc);
-			rc = ERROR;
-			ibmvscsis_post_disconnect(vscsi,
-						  ERR_DISCONNECT_RECONNECT, 0);
-			break;
-
-		case H_CLOSED:
-			pr_warn("init_msg: failed to send, rc %ld\n", rc);
-			rc = 0;
-			break;
-		}
-		break;
-
-	case UNDEFINED:
-		rc = ERROR;
-		break;
-
-	case UNCONFIGURING:
-		break;
-
-	case PART_UP_WAIT_ENAB:
-	case CONNECTED:
-	case SRP_PROCESSING:
-	case WAIT_IDLE:
-	case NO_QUEUE:
-	case ERR_DISCONNECT:
-	case ERR_DISCONNECT_RECONNECT:
-	case ERR_DISCONNECTED:
-	default:
-		rc = ERROR;
-		dev_err(&vscsi->dev, "init_msg: invalid state %d to get init msg\n",
-			vscsi->state);
-		ibmvscsis_post_disconnect(vscsi, ERR_DISCONNECT_RECONNECT, 0);
-		break;
-	}
-
-	return rc;
-}
-
-/**
- * ibmvscsis_init_msg() - Respond to an init message
- * @vscsi:	Pointer to our adapter structure
- * @crq:	Pointer to CRQ element containing the Init Message
- *
- * EXECUTION ENVIRONMENT:
- *	Interrupt, interrupt lock held
- */
-static long ibmvscsis_init_msg(struct scsi_info *vscsi, struct viosrp_crq *crq)
-{
-	long rc = ADAPT_SUCCESS;
-
-	pr_debug("init_msg: state 0x%hx\n", vscsi->state);
-
-	rc = h_vioctl(vscsi->dds.unit_id, H_GET_PARTNER_INFO,
-		      (u64)vscsi->map_ioba | ((u64)PAGE_SIZE << 32), 0, 0, 0,
-		      0);
-	if (rc == H_SUCCESS) {
-		vscsi->client_data.partition_number =
-			be64_to_cpu(*(u64 *)vscsi->map_buf);
-		pr_debug("init_msg, part num %d\n",
-			 vscsi->client_data.partition_number);
-	} else {
-		pr_debug("init_msg h_vioctl rc %ld\n", rc);
-		rc = ADAPT_SUCCESS;
-	}
-
-	if (crq->format == INIT_MSG) {
-		rc = ibmvscsis_handle_init_msg(vscsi);
-	} else if (crq->format == INIT_COMPLETE_MSG) {
-		rc = ibmvscsis_handle_init_compl_msg(vscsi);
-	} else {
-		rc = ERROR;
-		dev_err(&vscsi->dev, "init_msg: invalid format %d\n",
-			(uint)crq->format);
-		ibmvscsis_post_disconnect(vscsi, ERR_DISCONNECT_RECONNECT, 0);
-	}
-
-	return rc;
-}
-
-/**
  * ibmvscsis_parse_command() - Parse an element taken from the cmd rsp queue.
  * @vscsi:	Pointer to our adapter structure
  * @crq:	Pointer to CRQ element containing the SRP request
@@ -2385,7 +2387,7 @@ static long ibmvscsis_parse_command(struct scsi_info *vscsi,
 		break;
 
 	case VALID_TRANS_EVENT:
-		rc =  ibmvscsis_trans_event(vscsi, crq);
+		rc = ibmvscsis_trans_event(vscsi, crq);
 		break;
 
 	case VALID_INIT_MSG:
@@ -3270,7 +3272,7 @@ static void ibmvscsis_handle_crq(unsigned long data)
 	/*
 	 * if we are in a path where we are waiting for all pending commands
 	 * to complete because we received a transport event and anything in
-	 * the command queue is for a new connection,  do nothing
+	 * the command queue is for a new connection, do nothing
 	 */
 	if (TARGET_STOP(vscsi)) {
 		vio_enable_interrupts(vscsi->dma_dev);
@@ -3314,7 +3316,7 @@ static void ibmvscsis_handle_crq(unsigned long data)
 				 * everything but transport events on the queue
 				 *
 				 * need to decrement the queue index so we can
-				 * look at the elment again
+				 * look at the element again
 				 */
 				if (vscsi->cmd_q.index)
 					vscsi->cmd_q.index -= 1;
@@ -3988,10 +3990,10 @@ static struct attribute *ibmvscsis_dev_attrs[] = {
 ATTRIBUTE_GROUPS(ibmvscsis_dev);
 
 static struct class ibmvscsis_class = {
-	.name           = "ibmvscsis",
-	.dev_release    = ibmvscsis_dev_release,
-	.class_attrs    = ibmvscsis_class_attrs,
-	.dev_groups     = ibmvscsis_dev_groups,
+	.name		= "ibmvscsis",
+	.dev_release	= ibmvscsis_dev_release,
+	.class_attrs	= ibmvscsis_class_attrs,
+	.dev_groups	= ibmvscsis_dev_groups,
 };
 
 static struct vio_device_id ibmvscsis_device_table[] = {
-- 
2.1.0


From 94700877c25f64cc3660b0f72c0a8f2165f5c696 Mon Sep 17 00:00:00 2001
From: Michael Cyr <mikecyr@us.ibm.com>
Date: Fri, 17 Mar 2017 00:48:21 +0000
Subject: [PATCH 050/112] scsi: ibmvscsis: Synchronize cmds at tpg_enable_store
 time

[ Upstream commit c9b3379f60a83288a5e2f8ea75476460978689b0 ]

This patch changes the way the IBM vSCSI server driver manages its
Command/Response Queue (CRQ).  We used to register the CRQ with phyp at
probe time.  Now we wait until tpg_enable_store.  Similarly, when
tpg_enable_store is called to "disable" (i.e. the stored value is 0),
we unregister the queue with phyp.

One consquence to this is that we have no need for the PART_UP_WAIT_ENAB
state, since we can't get an Init Message from the client in our CRQ if
we're waiting to be enabled, since we haven't registered the queue yet.

Signed-off-by: Michael Cyr <mikecyr@us.ibm.com>
Signed-off-by: Bryant G. Ly <bryantly@linux.vnet.ibm.com>
Tested-by: Steven Royer <seroyer@linux.vnet.ibm.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c | 224 ++++++-------------------------
 drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.h |   2 -
 2 files changed, 38 insertions(+), 188 deletions(-)

diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
index 4feae43..504e593 100644
--- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
+++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
@@ -62,8 +62,6 @@ static long ibmvscsis_parse_command(struct scsi_info *vscsi,
 
 static void ibmvscsis_adapter_idle(struct scsi_info *vscsi);
 
-static void ibmvscsis_reset_queue(struct scsi_info *vscsi, uint new_state);
-
 static void ibmvscsis_determine_resid(struct se_cmd *se_cmd,
 				      struct srp_rsp *rsp)
 {
@@ -418,7 +416,6 @@ static void ibmvscsis_disconnect(struct work_struct *work)
 					       proc_work);
 	u16 new_state;
 	bool wait_idle = false;
-	long rc = ADAPT_SUCCESS;
 
 	spin_lock_bh(&vscsi->intr_lock);
 	new_state = vscsi->new_state;
@@ -471,30 +468,12 @@ static void ibmvscsis_disconnect(struct work_struct *work)
 			vscsi->state = new_state;
 		break;
 
-	/*
-	 * If this is a transition into an error state.
-	 * a client is attempting to establish a connection
-	 * and has violated the RPA protocol.
-	 * There can be nothing pending on the adapter although
-	 * there can be requests in the command queue.
-	 */
 	case WAIT_ENABLED:
-	case PART_UP_WAIT_ENAB:
 		switch (new_state) {
+		/* should never happen */
 		case ERR_DISCONNECT:
-			vscsi->flags |= RESPONSE_Q_DOWN;
-			vscsi->state = new_state;
-			vscsi->flags &= ~(SCHEDULE_DISCONNECT |
-					  DISCONNECT_SCHEDULED);
-			ibmvscsis_free_command_q(vscsi);
-			break;
 		case ERR_DISCONNECT_RECONNECT:
-			ibmvscsis_reset_queue(vscsi, WAIT_ENABLED);
-			break;
-
-		/* should never happen */
 		case WAIT_IDLE:
-			rc = ERROR;
 			dev_err(&vscsi->dev, "disconnect: invalid state %d for WAIT_IDLE\n",
 				vscsi->state);
 			break;
@@ -631,7 +610,6 @@ static void ibmvscsis_post_disconnect(struct scsi_info *vscsi, uint new_state,
 			break;
 
 		case WAIT_ENABLED:
-		case PART_UP_WAIT_ENAB:
 		case WAIT_IDLE:
 		case WAIT_CONNECTION:
 		case CONNECTED:
@@ -676,7 +654,6 @@ static long ibmvscsis_handle_init_compl_msg(struct scsi_info *vscsi)
 	case SRP_PROCESSING:
 	case CONNECTED:
 	case WAIT_ENABLED:
-	case PART_UP_WAIT_ENAB:
 	default:
 		rc = ERROR;
 		dev_err(&vscsi->dev, "init_msg: invalid state %d to get init compl msg\n",
@@ -699,10 +676,6 @@ static long ibmvscsis_handle_init_msg(struct scsi_info *vscsi)
 	long rc = ADAPT_SUCCESS;
 
 	switch (vscsi->state) {
-	case WAIT_ENABLED:
-		vscsi->state = PART_UP_WAIT_ENAB;
-		break;
-
 	case WAIT_CONNECTION:
 		rc = ibmvscsis_send_init_message(vscsi, INIT_COMPLETE_MSG);
 		switch (rc) {
@@ -738,7 +711,7 @@ static long ibmvscsis_handle_init_msg(struct scsi_info *vscsi)
 	case UNCONFIGURING:
 		break;
 
-	case PART_UP_WAIT_ENAB:
+	case WAIT_ENABLED:
 	case CONNECTED:
 	case SRP_PROCESSING:
 	case WAIT_IDLE:
@@ -801,11 +774,10 @@ static long ibmvscsis_init_msg(struct scsi_info *vscsi, struct viosrp_crq *crq)
 /**
  * ibmvscsis_establish_new_q() - Establish new CRQ queue
  * @vscsi:	Pointer to our adapter structure
- * @new_state:	New state being established after resetting the queue
  *
  * Must be called with interrupt lock held.
  */
-static long ibmvscsis_establish_new_q(struct scsi_info *vscsi, uint new_state)
+static long ibmvscsis_establish_new_q(struct scsi_info *vscsi)
 {
 	long rc = ADAPT_SUCCESS;
 	uint format;
@@ -817,19 +789,19 @@ static long ibmvscsis_establish_new_q(struct scsi_info *vscsi, uint new_state)
 
 	rc = vio_enable_interrupts(vscsi->dma_dev);
 	if (rc) {
-		pr_warn("reset_queue: failed to enable interrupts, rc %ld\n",
+		pr_warn("establish_new_q: failed to enable interrupts, rc %ld\n",
 			rc);
 		return rc;
 	}
 
 	rc = ibmvscsis_check_init_msg(vscsi, &format);
 	if (rc) {
-		dev_err(&vscsi->dev, "reset_queue: check_init_msg failed, rc %ld\n",
+		dev_err(&vscsi->dev, "establish_new_q: check_init_msg failed, rc %ld\n",
 			rc);
 		return rc;
 	}
 
-	if (format == UNUSED_FORMAT && new_state == WAIT_CONNECTION) {
+	if (format == UNUSED_FORMAT) {
 		rc = ibmvscsis_send_init_message(vscsi, INIT_MSG);
 		switch (rc) {
 		case H_SUCCESS:
@@ -847,6 +819,8 @@ static long ibmvscsis_establish_new_q(struct scsi_info *vscsi, uint new_state)
 			rc = H_HARDWARE;
 			break;
 		}
+	} else if (format == INIT_MSG) {
+		rc = ibmvscsis_handle_init_msg(vscsi);
 	}
 
 	return rc;
@@ -855,7 +829,6 @@ static long ibmvscsis_establish_new_q(struct scsi_info *vscsi, uint new_state)
 /**
  * ibmvscsis_reset_queue() - Reset CRQ Queue
  * @vscsi:	Pointer to our adapter structure
- * @new_state:	New state to establish after resetting the queue
  *
  * This function calls h_free_q and then calls h_reg_q and does all
  * of the bookkeeping to get us back to where we can communicate.
@@ -872,7 +845,7 @@ static long ibmvscsis_establish_new_q(struct scsi_info *vscsi, uint new_state)
  * EXECUTION ENVIRONMENT:
  *	Process environment, called with interrupt lock held
  */
-static void ibmvscsis_reset_queue(struct scsi_info *vscsi, uint new_state)
+static void ibmvscsis_reset_queue(struct scsi_info *vscsi)
 {
 	int bytes;
 	long rc = ADAPT_SUCCESS;
@@ -885,19 +858,18 @@ static void ibmvscsis_reset_queue(struct scsi_info *vscsi, uint new_state)
 		vscsi->rsp_q_timer.timer_pops = 0;
 		vscsi->debit = 0;
 		vscsi->credit = 0;
-		vscsi->state = new_state;
+		vscsi->state = WAIT_CONNECTION;
 		vio_enable_interrupts(vscsi->dma_dev);
 	} else {
 		rc = ibmvscsis_free_command_q(vscsi);
 		if (rc == ADAPT_SUCCESS) {
-			vscsi->state = new_state;
+			vscsi->state = WAIT_CONNECTION;
 
 			bytes = vscsi->cmd_q.size * PAGE_SIZE;
 			rc = h_reg_crq(vscsi->dds.unit_id,
 				       vscsi->cmd_q.crq_token, bytes);
 			if (rc == H_CLOSED || rc == H_SUCCESS) {
-				rc = ibmvscsis_establish_new_q(vscsi,
-							       new_state);
+				rc = ibmvscsis_establish_new_q(vscsi);
 			}
 
 			if (rc != ADAPT_SUCCESS) {
@@ -1016,10 +988,6 @@ static long ibmvscsis_trans_event(struct scsi_info *vscsi,
 						   TRANS_EVENT));
 			break;
 
-		case PART_UP_WAIT_ENAB:
-			vscsi->state = WAIT_ENABLED;
-			break;
-
 		case SRP_PROCESSING:
 			if ((vscsi->debit > 0) ||
 			    !list_empty(&vscsi->schedule_q) ||
@@ -1220,15 +1188,18 @@ static void ibmvscsis_adapter_idle(struct scsi_info *vscsi)
 
 	switch (vscsi->state) {
 	case ERR_DISCONNECT_RECONNECT:
-		ibmvscsis_reset_queue(vscsi, WAIT_CONNECTION);
+		ibmvscsis_reset_queue(vscsi);
 		pr_debug("adapter_idle, disc_rec: flags 0x%x\n", vscsi->flags);
 		break;
 
 	case ERR_DISCONNECT:
 		ibmvscsis_free_command_q(vscsi);
-		vscsi->flags &= ~DISCONNECT_SCHEDULED;
+		vscsi->flags &= ~(SCHEDULE_DISCONNECT | DISCONNECT_SCHEDULED);
 		vscsi->flags |= RESPONSE_Q_DOWN;
-		vscsi->state = ERR_DISCONNECTED;
+		if (vscsi->tport.enabled)
+			vscsi->state = ERR_DISCONNECTED;
+		else
+			vscsi->state = WAIT_ENABLED;
 		pr_debug("adapter_idle, disc: flags 0x%x, state 0x%hx\n",
 			 vscsi->flags, vscsi->state);
 		break;
@@ -1773,8 +1744,8 @@ static void ibmvscsis_send_messages(struct scsi_info *vscsi)
 					be64_to_cpu(msg_hi),
 					be64_to_cpu(cmd->rsp.tag));
 
-			pr_debug("send_messages: tag 0x%llx, rc %ld\n",
-				 be64_to_cpu(cmd->rsp.tag), rc);
+			pr_debug("send_messages: cmd %p, tag 0x%llx, rc %ld\n",
+				 cmd, be64_to_cpu(cmd->rsp.tag), rc);
 
 			/* if all ok free up the command element resources */
 			if (rc == H_SUCCESS) {
@@ -2788,36 +2759,6 @@ static irqreturn_t ibmvscsis_interrupt(int dummy, void *data)
 }
 
 /**
- * ibmvscsis_check_q() - Helper function to Check Init Message Valid
- * @vscsi:	Pointer to our adapter structure
- *
- * Checks if a initialize message was queued by the initiatior
- * while the timing window was open.  This function is called from
- * probe after the CRQ is created and interrupts are enabled.
- * It would only be used by adapters who wait for some event before
- * completing the init handshake with the client.  For ibmvscsi, this
- * event is waiting for the port to be enabled.
- *
- * EXECUTION ENVIRONMENT:
- *	Process level only, interrupt lock held
- */
-static long ibmvscsis_check_q(struct scsi_info *vscsi)
-{
-	uint format;
-	long rc;
-
-	rc = ibmvscsis_check_init_msg(vscsi, &format);
-	if (rc)
-		ibmvscsis_post_disconnect(vscsi, ERR_DISCONNECT_RECONNECT, 0);
-	else if (format == UNUSED_FORMAT)
-		vscsi->state = WAIT_ENABLED;
-	else
-		vscsi->state = PART_UP_WAIT_ENAB;
-
-	return rc;
-}
-
-/**
  * ibmvscsis_enable_change_state() - Set new state based on enabled status
  * @vscsi:	Pointer to our adapter structure
  *
@@ -2828,77 +2769,19 @@ static long ibmvscsis_check_q(struct scsi_info *vscsi)
  */
 static long ibmvscsis_enable_change_state(struct scsi_info *vscsi)
 {
+	int bytes;
 	long rc = ADAPT_SUCCESS;
 
-handle_state_change:
-	switch (vscsi->state) {
-	case WAIT_ENABLED:
-		rc = ibmvscsis_send_init_message(vscsi, INIT_MSG);
-		switch (rc) {
-		case H_SUCCESS:
-		case H_DROPPED:
-		case H_CLOSED:
-			vscsi->state =  WAIT_CONNECTION;
-			rc = ADAPT_SUCCESS;
-			break;
-
-		case H_PARAMETER:
-			break;
-
-		case H_HARDWARE:
-			break;
-
-		default:
-			vscsi->state = UNDEFINED;
-			rc = H_HARDWARE;
-			break;
-		}
-		break;
-	case PART_UP_WAIT_ENAB:
-		rc = ibmvscsis_send_init_message(vscsi, INIT_COMPLETE_MSG);
-		switch (rc) {
-		case H_SUCCESS:
-			vscsi->state = CONNECTED;
-			rc = ADAPT_SUCCESS;
-			break;
-
-		case H_DROPPED:
-		case H_CLOSED:
-			vscsi->state = WAIT_ENABLED;
-			goto handle_state_change;
-
-		case H_PARAMETER:
-			break;
-
-		case H_HARDWARE:
-			break;
-
-		default:
-			rc = H_HARDWARE;
-			break;
-		}
-		break;
-
-	case WAIT_CONNECTION:
-	case WAIT_IDLE:
-	case SRP_PROCESSING:
-	case CONNECTED:
-		rc = ADAPT_SUCCESS;
-		break;
-		/* should not be able to get here */
-	case UNCONFIGURING:
-		rc = ERROR;
-		vscsi->state = UNDEFINED;
-		break;
+	bytes = vscsi->cmd_q.size * PAGE_SIZE;
+	rc = h_reg_crq(vscsi->dds.unit_id, vscsi->cmd_q.crq_token, bytes);
+	if (rc == H_CLOSED || rc == H_SUCCESS) {
+		vscsi->state = WAIT_CONNECTION;
+		rc = ibmvscsis_establish_new_q(vscsi);
+	}
 
-		/* driver should never allow this to happen */
-	case ERR_DISCONNECT:
-	case ERR_DISCONNECT_RECONNECT:
-	default:
-		dev_err(&vscsi->dev, "in invalid state %d during enable_change_state\n",
-			vscsi->state);
-		rc = ADAPT_SUCCESS;
-		break;
+	if (rc != ADAPT_SUCCESS) {
+		vscsi->state = ERR_DISCONNECTED;
+		vscsi->flags |= RESPONSE_Q_DOWN;
 	}
 
 	return rc;
@@ -2918,7 +2801,6 @@ static long ibmvscsis_enable_change_state(struct scsi_info *vscsi)
  */
 static long ibmvscsis_create_command_q(struct scsi_info *vscsi, int num_cmds)
 {
-	long rc = 0;
 	int pages;
 	struct vio_dev *vdev = vscsi->dma_dev;
 
@@ -2942,22 +2824,7 @@ static long ibmvscsis_create_command_q(struct scsi_info *vscsi, int num_cmds)
 		return -ENOMEM;
 	}
 
-	rc =  h_reg_crq(vscsi->dds.unit_id, vscsi->cmd_q.crq_token, PAGE_SIZE);
-	if (rc) {
-		if (rc == H_CLOSED) {
-			vscsi->state = WAIT_ENABLED;
-			rc = 0;
-		} else {
-			dma_unmap_single(&vdev->dev, vscsi->cmd_q.crq_token,
-					 PAGE_SIZE, DMA_BIDIRECTIONAL);
-			free_page((unsigned long)vscsi->cmd_q.base_addr);
-			rc = -ENODEV;
-		}
-	} else {
-		vscsi->state = WAIT_ENABLED;
-	}
-
-	return rc;
+	return 0;
 }
 
 /**
@@ -3491,31 +3358,12 @@ static int ibmvscsis_probe(struct vio_dev *vdev,
 		goto destroy_WQ;
 	}
 
-	spin_lock_bh(&vscsi->intr_lock);
-	vio_enable_interrupts(vdev);
-	if (rc) {
-		dev_err(&vscsi->dev, "enabling interrupts failed, rc %d\n", rc);
-		rc = -ENODEV;
-		spin_unlock_bh(&vscsi->intr_lock);
-		goto free_irq;
-	}
-
-	if (ibmvscsis_check_q(vscsi)) {
-		rc = ERROR;
-		dev_err(&vscsi->dev, "probe: check_q failed, rc %d\n", rc);
-		spin_unlock_bh(&vscsi->intr_lock);
-		goto disable_interrupt;
-	}
-	spin_unlock_bh(&vscsi->intr_lock);
+	vscsi->state = WAIT_ENABLED;
 
 	dev_set_drvdata(&vdev->dev, vscsi);
 
 	return 0;
 
-disable_interrupt:
-	vio_disable_interrupts(vdev);
-free_irq:
-	free_irq(vdev->irq, vscsi);
 destroy_WQ:
 	destroy_workqueue(vscsi->work_q);
 unmap_buf:
@@ -3909,18 +3757,22 @@ static ssize_t ibmvscsis_tpg_enable_store(struct config_item *item,
 	}
 
 	if (tmp) {
-		tport->enabled = true;
 		spin_lock_bh(&vscsi->intr_lock);
+		tport->enabled = true;
 		lrc = ibmvscsis_enable_change_state(vscsi);
 		if (lrc)
 			pr_err("enable_change_state failed, rc %ld state %d\n",
 			       lrc, vscsi->state);
 		spin_unlock_bh(&vscsi->intr_lock);
 	} else {
+		spin_lock_bh(&vscsi->intr_lock);
 		tport->enabled = false;
+		/* This simulates the server going down */
+		ibmvscsis_post_disconnect(vscsi, ERR_DISCONNECT, 0);
+		spin_unlock_bh(&vscsi->intr_lock);
 	}
 
-	pr_debug("tpg_enable_store, state %d\n", vscsi->state);
+	pr_debug("tpg_enable_store, tmp %ld, state %d\n", tmp, vscsi->state);
 
 	return count;
 }
diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.h b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.h
index 981a0c9..17e0ef4 100644
--- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.h
+++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.h
@@ -204,8 +204,6 @@ struct scsi_info {
 	struct list_head waiting_rsp;
 #define NO_QUEUE                    0x00
 #define WAIT_ENABLED                0X01
-	/* driver has received an initialize command */
-#define PART_UP_WAIT_ENAB           0x02
 #define WAIT_CONNECTION             0x04
 	/* have established a connection */
 #define CONNECTED                   0x08
-- 
2.1.0


From 456be98b4e79a2ed0316bbc0e885c526cbe8afad Mon Sep 17 00:00:00 2001
From: Michael Cyr <mikecyr@us.ibm.com>
Date: Fri, 17 Mar 2017 00:48:22 +0000
Subject: [PATCH 051/112] scsi: ibmvscsis: Synchronize cmds at remove time

[ Upstream commit 8bf11557d44d00562360d370de8aa70ba89aa0d5 ]

This patch adds code to disconnect from the client, which will make sure
any outstanding commands have been completed, before continuing on with
the remove operation.

Signed-off-by: Michael Cyr <mikecyr@us.ibm.com>
Signed-off-by: Bryant G. Ly <bryantly@linux.vnet.ibm.com>
Tested-by: Steven Royer <seroyer@linux.vnet.ibm.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c | 39 ++++++++++++++++++++++++++++----
 drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.h |  3 +++
 2 files changed, 37 insertions(+), 5 deletions(-)

diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
index 504e593..c4fe95a 100644
--- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
+++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
@@ -470,6 +470,18 @@ static void ibmvscsis_disconnect(struct work_struct *work)
 
 	case WAIT_ENABLED:
 		switch (new_state) {
+		case UNCONFIGURING:
+			vscsi->state = new_state;
+			vscsi->flags |= RESPONSE_Q_DOWN;
+			vscsi->flags &= ~(SCHEDULE_DISCONNECT |
+					  DISCONNECT_SCHEDULED);
+			dma_rmb();
+			if (vscsi->flags & CFG_SLEEPING) {
+				vscsi->flags &= ~CFG_SLEEPING;
+				complete(&vscsi->unconfig);
+			}
+			break;
+
 		/* should never happen */
 		case ERR_DISCONNECT:
 		case ERR_DISCONNECT_RECONNECT:
@@ -482,6 +494,13 @@ static void ibmvscsis_disconnect(struct work_struct *work)
 
 	case WAIT_IDLE:
 		switch (new_state) {
+		case UNCONFIGURING:
+			vscsi->flags |= RESPONSE_Q_DOWN;
+			vscsi->state = new_state;
+			vscsi->flags &= ~(SCHEDULE_DISCONNECT |
+					  DISCONNECT_SCHEDULED);
+			ibmvscsis_free_command_q(vscsi);
+			break;
 		case ERR_DISCONNECT:
 		case ERR_DISCONNECT_RECONNECT:
 			vscsi->state = new_state;
@@ -1187,6 +1206,15 @@ static void ibmvscsis_adapter_idle(struct scsi_info *vscsi)
 		free_qs = true;
 
 	switch (vscsi->state) {
+	case UNCONFIGURING:
+		ibmvscsis_free_command_q(vscsi);
+		dma_rmb();
+		isync();
+		if (vscsi->flags & CFG_SLEEPING) {
+			vscsi->flags &= ~CFG_SLEEPING;
+			complete(&vscsi->unconfig);
+		}
+		break;
 	case ERR_DISCONNECT_RECONNECT:
 		ibmvscsis_reset_queue(vscsi);
 		pr_debug("adapter_idle, disc_rec: flags 0x%x\n", vscsi->flags);
@@ -3342,6 +3370,7 @@ static int ibmvscsis_probe(struct vio_dev *vdev,
 		     (unsigned long)vscsi);
 
 	init_completion(&vscsi->wait_idle);
+	init_completion(&vscsi->unconfig);
 
 	snprintf(wq_name, 24, "ibmvscsis%s", dev_name(&vdev->dev));
 	vscsi->work_q = create_workqueue(wq_name);
@@ -3397,10 +3426,11 @@ static int ibmvscsis_remove(struct vio_dev *vdev)
 
 	pr_debug("remove (%s)\n", dev_name(&vscsi->dma_dev->dev));
 
-	/*
-	 * TBD: Need to handle if there are commands on the waiting_rsp q
-	 *      Actually, can there still be cmds outstanding to tcm?
-	 */
+	spin_lock_bh(&vscsi->intr_lock);
+	ibmvscsis_post_disconnect(vscsi, UNCONFIGURING, 0);
+	vscsi->flags |= CFG_SLEEPING;
+	spin_unlock_bh(&vscsi->intr_lock);
+	wait_for_completion(&vscsi->unconfig);
 
 	vio_disable_interrupts(vdev);
 	free_irq(vdev->irq, vscsi);
@@ -3409,7 +3439,6 @@ static int ibmvscsis_remove(struct vio_dev *vdev)
 			 DMA_BIDIRECTIONAL);
 	kfree(vscsi->map_buf);
 	tasklet_kill(&vscsi->work_task);
-	ibmvscsis_unregister_command_q(vscsi);
 	ibmvscsis_destroy_command_q(vscsi);
 	ibmvscsis_freetimer(vscsi);
 	ibmvscsis_free_cmds(vscsi);
diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.h b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.h
index 17e0ef4..98b0ca7 100644
--- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.h
+++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.h
@@ -257,6 +257,8 @@ struct scsi_info {
 #define SCHEDULE_DISCONNECT           0x00400
 	/* disconnect handler is scheduled */
 #define DISCONNECT_SCHEDULED          0x00800
+	/* remove function is sleeping */
+#define CFG_SLEEPING                  0x01000
 	u32 flags;
 	/* adapter lock */
 	spinlock_t intr_lock;
@@ -285,6 +287,7 @@ struct scsi_info {
 
 	struct workqueue_struct *work_q;
 	struct completion wait_idle;
+	struct completion unconfig;
 	struct device dev;
 	struct vio_dev *dma_dev;
 	struct srp_target target;
-- 
2.1.0


From 29d928785f5e76b5abfafe4a91cc1db4155cd677 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Fri, 17 Mar 2017 00:48:22 +0000
Subject: [PATCH 052/112] x86/hyperv: Handle unknown NMIs on one CPU when
 unknown_nmi_panic

[ Upstream commit 59107e2f48831daedc46973ce4988605ab066de3 ]

There is a feature in Hyper-V ('Debug-VM --InjectNonMaskableInterrupt')
which injects NMI to the guest. We may want to crash the guest and do kdump
on this NMI by enabling unknown_nmi_panic. To make kdump succeed we need to
allow the kdump kernel to re-establish VMBus connection so it will see
VMBus devices (storage, network,..).

To properly unload VMBus making it possible to start over during kdump we
need to do the following:

 - Send an 'unload' message to the hypervisor. This can be done on any CPU
   so we do this the crashing CPU.

 - Receive the 'unload finished' reply message. WS2012R2 delivers this
   message to the CPU which was used to establish VMBus connection during
   module load and this CPU may differ from the CPU sending 'unload'.

Receiving a VMBus message means the following:

 - There is a per-CPU slot in memory for one message. This slot can in
   theory be accessed by any CPU.

 - We get an interrupt on the CPU when a message was placed into the slot.

 - When we read the message we need to clear the slot and signal the fact
   to the hypervisor. In case there are more messages to this CPU pending
   the hypervisor will deliver the next message. The signaling is done by
   writing to an MSR so this can only be done on the appropriate CPU.

To avoid doing cross-CPU work on crash we have vmbus_wait_for_unload()
function which checks message slots for all CPUs in a loop waiting for the
'unload finished' messages. However, there is an issue which arises when
these conditions are met:

 - We're crashing on a CPU which is different from the one which was used
   to initially contact the hypervisor.

 - The CPU which was used for the initial contact is blocked with interrupts
   disabled and there is a message pending in the message slot.

In this case we won't be able to read the 'unload finished' message on the
crashing CPU. This is reproducible when we receive unknown NMIs on all CPUs
simultaneously: the first CPU entering panic() will proceed to crash and
all other CPUs will stop themselves with interrupts disabled.

The suggested solution is to handle unknown NMIs for Hyper-V guests on the
first CPU which gets them only. This will allow us to rely on VMBus
interrupt handler being able to receive the 'unload finish' message in
case it is delivered to a different CPU.

The issue is not reproducible on WS2016 as Debug-VM delivers NMI to the
boot CPU only, WS2012R2 and earlier Hyper-V versions are affected.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Acked-by: K. Y. Srinivasan <kys@microsoft.com>
Cc: devel@linuxdriverproject.org
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Link: http://lkml.kernel.org/r/20161202100720.28121-1-vkuznets@redhat.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/x86/kernel/cpu/mshyperv.c | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 8f44c5a..f228f74 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -31,6 +31,7 @@
 #include <asm/apic.h>
 #include <asm/timer.h>
 #include <asm/reboot.h>
+#include <asm/nmi.h>
 
 struct ms_hyperv_info ms_hyperv;
 EXPORT_SYMBOL_GPL(ms_hyperv);
@@ -158,6 +159,26 @@ static unsigned char hv_get_nmi_reason(void)
 	return 0;
 }
 
+#ifdef CONFIG_X86_LOCAL_APIC
+/*
+ * Prior to WS2016 Debug-VM sends NMIs to all CPUs which makes
+ * it dificult to process CHANNELMSG_UNLOAD in case of crash. Handle
+ * unknown NMI on the first CPU which gets it.
+ */
+static int hv_nmi_unknown(unsigned int val, struct pt_regs *regs)
+{
+	static atomic_t nmi_cpu = ATOMIC_INIT(-1);
+
+	if (!unknown_nmi_panic)
+		return NMI_DONE;
+
+	if (atomic_cmpxchg(&nmi_cpu, -1, raw_smp_processor_id()) != -1)
+		return NMI_HANDLED;
+
+	return NMI_DONE;
+}
+#endif
+
 static void __init ms_hyperv_init_platform(void)
 {
 	/*
@@ -183,6 +204,9 @@ static void __init ms_hyperv_init_platform(void)
 		pr_info("HyperV: LAPIC Timer Frequency: %#x\n",
 			lapic_timer_frequency);
 	}
+
+	register_nmi_handler(NMI_UNKNOWN, hv_nmi_unknown, NMI_FLAG_FIRST,
+			     "hv_nmi_unknown");
 #endif
 
 	if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE)
-- 
2.1.0


From 6a5f3e664ac798b54448fc55e7e7c3a9fd1ee9d4 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Fri, 17 Mar 2017 00:48:22 +0000
Subject: [PATCH 053/112] PCI: Separate VF BAR updates from standard BAR
 updates

[ Upstream commit 6ffa2489c51da77564a0881a73765ea2169f955d ]

Previously pci_update_resource() used the same code path for updating
standard BARs and VF BARs in SR-IOV capabilities.

Split the VF BAR update into a new pci_iov_update_resource() internal
interface, which makes it simpler to compute the BAR address (we can get
rid of pci_resource_bar() and pci_iov_resource_bar()).

This patch:

  - Renames pci_update_resource() to pci_std_update_resource(),
  - Adds pci_iov_update_resource(),
  - Makes pci_update_resource() a wrapper that calls the appropriate one,

No functional change intended.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/pci/iov.c       | 50 +++++++++++++++++++++++++++++++++++++++++++++++++
 drivers/pci/pci.h       |  1 +
 drivers/pci/setup-res.c | 13 +++++++++++--
 3 files changed, 62 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index e30f05c..39888cf 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -571,6 +571,56 @@ int pci_iov_resource_bar(struct pci_dev *dev, int resno)
 		4 * (resno - PCI_IOV_RESOURCES);
 }
 
+/**
+ * pci_iov_update_resource - update a VF BAR
+ * @dev: the PCI device
+ * @resno: the resource number
+ *
+ * Update a VF BAR in the SR-IOV capability of a PF.
+ */
+void pci_iov_update_resource(struct pci_dev *dev, int resno)
+{
+	struct pci_sriov *iov = dev->is_physfn ? dev->sriov : NULL;
+	struct resource *res = dev->resource + resno;
+	int vf_bar = resno - PCI_IOV_RESOURCES;
+	struct pci_bus_region region;
+	u32 new;
+	int reg;
+
+	/*
+	 * The generic pci_restore_bars() path calls this for all devices,
+	 * including VFs and non-SR-IOV devices.  If this is not a PF, we
+	 * have nothing to do.
+	 */
+	if (!iov)
+		return;
+
+	/*
+	 * Ignore unimplemented BARs, unused resource slots for 64-bit
+	 * BARs, and non-movable resources, e.g., those described via
+	 * Enhanced Allocation.
+	 */
+	if (!res->flags)
+		return;
+
+	if (res->flags & IORESOURCE_UNSET)
+		return;
+
+	if (res->flags & IORESOURCE_PCI_FIXED)
+		return;
+
+	pcibios_resource_to_bus(dev->bus, &region, res);
+	new = region.start;
+	new |= res->flags & ~PCI_BASE_ADDRESS_MEM_MASK;
+
+	reg = iov->pos + PCI_SRIOV_BAR + 4 * vf_bar;
+	pci_write_config_dword(dev, reg, new);
+	if (res->flags & IORESOURCE_MEM_64) {
+		new = region.start >> 16 >> 16;
+		pci_write_config_dword(dev, reg + 4, new);
+	}
+}
+
 resource_size_t __weak pcibios_iov_resource_alignment(struct pci_dev *dev,
 						      int resno)
 {
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 4518562..5bfcb92 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -290,6 +290,7 @@ static inline void pci_restore_ats_state(struct pci_dev *dev)
 int pci_iov_init(struct pci_dev *dev);
 void pci_iov_release(struct pci_dev *dev);
 int pci_iov_resource_bar(struct pci_dev *dev, int resno);
+void pci_iov_update_resource(struct pci_dev *dev, int resno);
 resource_size_t pci_sriov_resource_alignment(struct pci_dev *dev, int resno);
 void pci_restore_iov_state(struct pci_dev *dev);
 int pci_iov_bus_range(struct pci_bus *bus);
diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c
index 9526e34..695f32d 100644
--- a/drivers/pci/setup-res.c
+++ b/drivers/pci/setup-res.c
@@ -25,8 +25,7 @@
 #include <linux/slab.h>
 #include "pci.h"
 
-
-void pci_update_resource(struct pci_dev *dev, int resno)
+static void pci_std_update_resource(struct pci_dev *dev, int resno)
 {
 	struct pci_bus_region region;
 	bool disable;
@@ -110,6 +109,16 @@ void pci_update_resource(struct pci_dev *dev, int resno)
 		pci_write_config_word(dev, PCI_COMMAND, cmd);
 }
 
+void pci_update_resource(struct pci_dev *dev, int resno)
+{
+	if (resno <= PCI_ROM_RESOURCE)
+		pci_std_update_resource(dev, resno);
+#ifdef CONFIG_PCI_IOV
+	else if (resno >= PCI_IOV_RESOURCES && resno <= PCI_IOV_RESOURCE_END)
+		pci_iov_update_resource(dev, resno);
+#endif
+}
+
 int pci_claim_resource(struct pci_dev *dev, int resource)
 {
 	struct resource *res = &dev->resource[resource];
-- 
2.1.0


From 7b65c3a84311026200b19eb86c9a76ff004402f8 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Fri, 17 Mar 2017 00:48:23 +0000
Subject: [PATCH 054/112] PCI: Remove pci_resource_bar() and
 pci_iov_resource_bar()

[ Upstream commit 286c2378aaccc7343ebf17ec6cd86567659caf70 ]

pci_std_update_resource() only deals with standard BARs, so we don't have
to worry about the complications of VF BARs in an SR-IOV capability.

Compute the BAR address inline and remove pci_resource_bar().  That makes
pci_iov_resource_bar() unused, so remove that as well.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/pci/iov.c       | 18 ------------------
 drivers/pci/pci.c       | 30 ------------------------------
 drivers/pci/pci.h       |  6 ------
 drivers/pci/setup-res.c | 13 +++++++------
 4 files changed, 7 insertions(+), 60 deletions(-)

diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index 39888cf..3fb8d2a 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -554,24 +554,6 @@ void pci_iov_release(struct pci_dev *dev)
 }
 
 /**
- * pci_iov_resource_bar - get position of the SR-IOV BAR
- * @dev: the PCI device
- * @resno: the resource number
- *
- * Returns position of the BAR encapsulated in the SR-IOV capability.
- */
-int pci_iov_resource_bar(struct pci_dev *dev, int resno)
-{
-	if (resno < PCI_IOV_RESOURCES || resno > PCI_IOV_RESOURCE_END)
-		return 0;
-
-	BUG_ON(!dev->is_physfn);
-
-	return dev->sriov->pos + PCI_SRIOV_BAR +
-		4 * (resno - PCI_IOV_RESOURCES);
-}
-
-/**
  * pci_iov_update_resource - update a VF BAR
  * @dev: the PCI device
  * @resno: the resource number
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index eda6a7c..1fc2cf4 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -4835,36 +4835,6 @@ int pci_select_bars(struct pci_dev *dev, unsigned long flags)
 }
 EXPORT_SYMBOL(pci_select_bars);
 
-/**
- * pci_resource_bar - get position of the BAR associated with a resource
- * @dev: the PCI device
- * @resno: the resource number
- * @type: the BAR type to be filled in
- *
- * Returns BAR position in config space, or 0 if the BAR is invalid.
- */
-int pci_resource_bar(struct pci_dev *dev, int resno, enum pci_bar_type *type)
-{
-	int reg;
-
-	if (resno < PCI_ROM_RESOURCE) {
-		*type = pci_bar_unknown;
-		return PCI_BASE_ADDRESS_0 + 4 * resno;
-	} else if (resno == PCI_ROM_RESOURCE) {
-		*type = pci_bar_mem32;
-		return dev->rom_base_reg;
-	} else if (resno < PCI_BRIDGE_RESOURCES) {
-		/* device specific resource */
-		*type = pci_bar_unknown;
-		reg = pci_iov_resource_bar(dev, resno);
-		if (reg)
-			return reg;
-	}
-
-	dev_err(&dev->dev, "BAR %d: invalid resource\n", resno);
-	return 0;
-}
-
 /* Some architectures require additional programming to enable VGA */
 static arch_set_vga_state_t arch_set_vga_state;
 
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 5bfcb92..a5d37f6 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -245,7 +245,6 @@ bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *pl,
 int pci_setup_device(struct pci_dev *dev);
 int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 		    struct resource *res, unsigned int reg);
-int pci_resource_bar(struct pci_dev *dev, int resno, enum pci_bar_type *type);
 void pci_configure_ari(struct pci_dev *dev);
 void __pci_bus_size_bridges(struct pci_bus *bus,
 			struct list_head *realloc_head);
@@ -289,7 +288,6 @@ static inline void pci_restore_ats_state(struct pci_dev *dev)
 #ifdef CONFIG_PCI_IOV
 int pci_iov_init(struct pci_dev *dev);
 void pci_iov_release(struct pci_dev *dev);
-int pci_iov_resource_bar(struct pci_dev *dev, int resno);
 void pci_iov_update_resource(struct pci_dev *dev, int resno);
 resource_size_t pci_sriov_resource_alignment(struct pci_dev *dev, int resno);
 void pci_restore_iov_state(struct pci_dev *dev);
@@ -304,10 +302,6 @@ static inline void pci_iov_release(struct pci_dev *dev)
 
 {
 }
-static inline int pci_iov_resource_bar(struct pci_dev *dev, int resno)
-{
-	return 0;
-}
 static inline void pci_restore_iov_state(struct pci_dev *dev)
 {
 }
diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c
index 695f32d..182d0f0 100644
--- a/drivers/pci/setup-res.c
+++ b/drivers/pci/setup-res.c
@@ -32,7 +32,6 @@ static void pci_std_update_resource(struct pci_dev *dev, int resno)
 	u16 cmd;
 	u32 new, check, mask;
 	int reg;
-	enum pci_bar_type type;
 	struct resource *res = dev->resource + resno;
 
 	if (dev->is_virtfn) {
@@ -66,14 +65,16 @@ static void pci_std_update_resource(struct pci_dev *dev, int resno)
 	else
 		mask = (u32)PCI_BASE_ADDRESS_MEM_MASK;
 
-	reg = pci_resource_bar(dev, resno, &type);
-	if (!reg)
-		return;
-	if (type != pci_bar_unknown) {
+	if (resno < PCI_ROM_RESOURCE) {
+		reg = PCI_BASE_ADDRESS_0 + 4 * resno;
+	} else if (resno == PCI_ROM_RESOURCE) {
 		if (!(res->flags & IORESOURCE_ROM_ENABLE))
 			return;
+
+		reg = dev->rom_base_reg;
 		new |= PCI_ROM_ADDRESS_ENABLE;
-	}
+	} else
+		return;
 
 	/*
 	 * We can't update a 64-bit BAR atomically, so when possible,
-- 
2.1.0


From ed09d211d28e260e81b857e1933e43a3f230cf34 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Fri, 17 Mar 2017 00:48:23 +0000
Subject: [PATCH 055/112] PCI: Add comments about ROM BAR updating

[ Upstream commit 0b457dde3cf8b7c76a60f8e960f21bbd4abdc416 ]

pci_update_resource() updates a hardware BAR so its address matches the
kernel's struct resource UNLESS it's a disabled ROM BAR.  We only update
those when we enable the ROM.

It's not obvious from the code why ROM BARs should be handled specially.
Apparently there are Matrox devices with defective ROM BARs that read as
zero when disabled.  That means that if pci_enable_rom() reads the disabled
BAR, sets PCI_ROM_ADDRESS_ENABLE (without re-inserting the address), and
writes it back, it would enable the ROM at address zero.

Add comments and references to explain why we can't make the code look more
rational.

The code changes are from 755528c860b0 ("Ignore disabled ROM resources at
setup") and 8085ce084c0f ("[PATCH] Fix PCI ROM mapping").

Link: https://lkml.org/lkml/2005/8/30/138
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/pci/rom.c       | 5 +++++
 drivers/pci/setup-res.c | 6 ++++++
 2 files changed, 11 insertions(+)

diff --git a/drivers/pci/rom.c b/drivers/pci/rom.c
index 06663d3..b6edb18 100644
--- a/drivers/pci/rom.c
+++ b/drivers/pci/rom.c
@@ -35,6 +35,11 @@ int pci_enable_rom(struct pci_dev *pdev)
 	if (res->flags & IORESOURCE_ROM_SHADOW)
 		return 0;
 
+	/*
+	 * Ideally pci_update_resource() would update the ROM BAR address,
+	 * and we would only set the enable bit here.  But apparently some
+	 * devices have buggy ROM BARs that read as zero when disabled.
+	 */
 	pcibios_resource_to_bus(pdev->bus, &region, res);
 	pci_read_config_dword(pdev, pdev->rom_base_reg, &rom_addr);
 	rom_addr &= ~PCI_ROM_ADDRESS_MASK;
diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c
index 182d0f0..bd6fca9 100644
--- a/drivers/pci/setup-res.c
+++ b/drivers/pci/setup-res.c
@@ -68,6 +68,12 @@ static void pci_std_update_resource(struct pci_dev *dev, int resno)
 	if (resno < PCI_ROM_RESOURCE) {
 		reg = PCI_BASE_ADDRESS_0 + 4 * resno;
 	} else if (resno == PCI_ROM_RESOURCE) {
+
+		/*
+		 * Apparently some Matrox devices have ROM BARs that read
+		 * as zero when disabled, so don't update ROM BARs unless
+		 * they're enabled.  See https://lkml.org/lkml/2005/8/30/138.
+		 */
 		if (!(res->flags & IORESOURCE_ROM_ENABLE))
 			return;
 
-- 
2.1.0


From bb479246bb3ee7d8f4b1caada0db9a268e958f1e Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Fri, 17 Mar 2017 00:48:23 +0000
Subject: [PATCH 056/112] PCI: Decouple IORESOURCE_ROM_ENABLE and
 PCI_ROM_ADDRESS_ENABLE

[ Upstream commit 7a6d312b50e63f598f5b5914c4fd21878ac2b595 ]

Remove the assumption that IORESOURCE_ROM_ENABLE == PCI_ROM_ADDRESS_ENABLE.
PCI_ROM_ADDRESS_ENABLE is the ROM enable bit defined by the PCI spec, so if
we're reading or writing a BAR register value, that's what we should use.
IORESOURCE_ROM_ENABLE is a corresponding bit in struct resource flags.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/pci/probe.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 300770c..d266d80 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -227,7 +227,8 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 			mask64 = (u32)PCI_BASE_ADDRESS_MEM_MASK;
 		}
 	} else {
-		res->flags |= (l & IORESOURCE_ROM_ENABLE);
+		if (l & PCI_ROM_ADDRESS_ENABLE)
+			res->flags |= IORESOURCE_ROM_ENABLE;
 		l64 = l & PCI_ROM_ADDRESS_MASK;
 		sz64 = sz & PCI_ROM_ADDRESS_MASK;
 		mask64 = (u32)PCI_ROM_ADDRESS_MASK;
-- 
2.1.0


From a38012dc69eb2fb1a660bbc88e98c882b5cf2fcb Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Fri, 17 Mar 2017 00:48:24 +0000
Subject: [PATCH 057/112] PCI: Don't update VF BARs while VF memory space is
 enabled

[ Upstream commit 546ba9f8f22f71b0202b6ba8967be5cc6dae4e21 ]

If we update a VF BAR while it's enabled, there are two potential problems:

  1) Any driver that's using the VF has a cached BAR value that is stale
     after the update, and

  2) We can't update 64-bit BARs atomically, so the intermediate state
     (new lower dword with old upper dword) may conflict with another
     device, and an access by a driver unrelated to the VF may cause a bus
     error.

Warn about attempts to update VF BARs while they are enabled.  This is a
programming error, so use dev_WARN() to get a backtrace.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/pci/iov.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index 3fb8d2a..8255d28 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -566,6 +566,7 @@ void pci_iov_update_resource(struct pci_dev *dev, int resno)
 	struct resource *res = dev->resource + resno;
 	int vf_bar = resno - PCI_IOV_RESOURCES;
 	struct pci_bus_region region;
+	u16 cmd;
 	u32 new;
 	int reg;
 
@@ -577,6 +578,13 @@ void pci_iov_update_resource(struct pci_dev *dev, int resno)
 	if (!iov)
 		return;
 
+	pci_read_config_word(dev, iov->pos + PCI_SRIOV_CTRL, &cmd);
+	if ((cmd & PCI_SRIOV_CTRL_VFE) && (cmd & PCI_SRIOV_CTRL_MSE)) {
+		dev_WARN(&dev->dev, "can't update enabled VF BAR%d %pR\n",
+			 vf_bar, res);
+		return;
+	}
+
 	/*
 	 * Ignore unimplemented BARs, unused resource slots for 64-bit
 	 * BARs, and non-movable resources, e.g., those described via
-- 
2.1.0


From 74cce811a4b60d64c5c30496f326ecd18a72a6b2 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Fri, 17 Mar 2017 00:48:24 +0000
Subject: [PATCH 058/112] PCI: Update BARs using property bits appropriate for
 type

[ Upstream commit 45d004f4afefdd8d79916ee6d97a9ecd94bb1ffe ]

The BAR property bits (0-3 for memory BARs, 0-1 for I/O BARs) are supposed
to be read-only, but we do save them in res->flags and include them when
updating the BAR.

Mask the I/O property bits with ~PCI_BASE_ADDRESS_IO_MASK (0x3) instead of
PCI_REGION_FLAG_MASK (0xf) to make it obvious that we can't corrupt bits
2-3 of I/O addresses.

Use PCI_ROM_ADDRESS_MASK for ROM BARs.  This means we'll only check the top
21 bits (instead of the 28 bits we used to check) of a ROM BAR to see if
the update was successful.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/pci/setup-res.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c
index bd6fca9..8a7322c 100644
--- a/drivers/pci/setup-res.c
+++ b/drivers/pci/setup-res.c
@@ -58,12 +58,17 @@ static void pci_std_update_resource(struct pci_dev *dev, int resno)
 		return;
 
 	pcibios_resource_to_bus(dev->bus, &region, res);
+	new = region.start;
 
-	new = region.start | (res->flags & PCI_REGION_FLAG_MASK);
-	if (res->flags & IORESOURCE_IO)
+	if (res->flags & IORESOURCE_IO) {
 		mask = (u32)PCI_BASE_ADDRESS_IO_MASK;
-	else
+		new |= res->flags & ~PCI_BASE_ADDRESS_IO_MASK;
+	} else if (resno == PCI_ROM_RESOURCE) {
+		mask = (u32)PCI_ROM_ADDRESS_MASK;
+	} else {
 		mask = (u32)PCI_BASE_ADDRESS_MEM_MASK;
+		new |= res->flags & ~PCI_BASE_ADDRESS_MEM_MASK;
+	}
 
 	if (resno < PCI_ROM_RESOURCE) {
 		reg = PCI_BASE_ADDRESS_0 + 4 * resno;
-- 
2.1.0


From 3d58444dea81ba0556ffcb356a19fc2d224d4eac Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Fri, 17 Mar 2017 00:48:24 +0000
Subject: [PATCH 059/112] PCI: Ignore BAR updates on virtual functions

[ Upstream commit 63880b230a4af502c56dde3d4588634c70c66006 ]

VF BARs are read-only zero, so updating VF BARs will not have any effect.
See the SR-IOV spec r1.1, sec 3.4.1.11.

We already ignore these updates because of 70675e0b6a1a ("PCI: Don't try to
restore VF BARs"); this merely restructures it slightly to make it easier
to split updates for standard and SR-IOV BARs.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/pci/pci.c       | 4 ----
 drivers/pci/setup-res.c | 5 ++---
 2 files changed, 2 insertions(+), 7 deletions(-)

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 1fc2cf4..6922964 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -564,10 +564,6 @@ static void pci_restore_bars(struct pci_dev *dev)
 {
 	int i;
 
-	/* Per SR-IOV spec 3.4.1.11, VF BARs are RO zero */
-	if (dev->is_virtfn)
-		return;
-
 	for (i = 0; i < PCI_BRIDGE_RESOURCES; i++)
 		pci_update_resource(dev, i);
 }
diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c
index 8a7322c..4bc589e 100644
--- a/drivers/pci/setup-res.c
+++ b/drivers/pci/setup-res.c
@@ -34,10 +34,9 @@ static void pci_std_update_resource(struct pci_dev *dev, int resno)
 	int reg;
 	struct resource *res = dev->resource + resno;
 
-	if (dev->is_virtfn) {
-		dev_warn(&dev->dev, "can't update VF BAR%d\n", resno);
+	/* Per SR-IOV spec 3.4.1.11, VF BARs are RO zero */
+	if (dev->is_virtfn)
 		return;
-	}
 
 	/*
 	 * Ignore resources for unimplemented BARs and unused resource slots
-- 
2.1.0


From fb7c521a1460ad46a17859274d79f30599bdb5ea Mon Sep 17 00:00:00 2001
From: Gavin Shan <gwshan@linux.vnet.ibm.com>
Date: Fri, 17 Mar 2017 00:48:25 +0000
Subject: [PATCH 060/112] PCI: Do any VF BAR updates before enabling the BARs

[ Upstream commit f40ec3c748c6912f6266c56a7f7992de61b255ed ]

Previously we enabled VFs and enable their memory space before calling
pcibios_sriov_enable().  But pcibios_sriov_enable() may update the VF BARs:
for example, on PPC PowerNV we may change them to manage the association of
VFs to PEs.

Because 64-bit BARs cannot be updated atomically, it's unsafe to update
them while they're enabled.  The half-updated state may conflict with other
devices in the system.

Call pcibios_sriov_enable() before enabling the VFs so any BAR updates
happen while the VF BARs are disabled.

[bhelgaas: changelog]
Tested-by: Carol Soto <clsoto@us.ibm.com>
Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>

Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/pci/iov.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index 8255d28..4722782 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -306,13 +306,6 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn)
 			return rc;
 	}
 
-	pci_iov_set_numvfs(dev, nr_virtfn);
-	iov->ctrl |= PCI_SRIOV_CTRL_VFE | PCI_SRIOV_CTRL_MSE;
-	pci_cfg_access_lock(dev);
-	pci_write_config_word(dev, iov->pos + PCI_SRIOV_CTRL, iov->ctrl);
-	msleep(100);
-	pci_cfg_access_unlock(dev);
-
 	iov->initial_VFs = initial;
 	if (nr_virtfn < initial)
 		initial = nr_virtfn;
@@ -323,6 +316,13 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn)
 		goto err_pcibios;
 	}
 
+	pci_iov_set_numvfs(dev, nr_virtfn);
+	iov->ctrl |= PCI_SRIOV_CTRL_VFE | PCI_SRIOV_CTRL_MSE;
+	pci_cfg_access_lock(dev);
+	pci_write_config_word(dev, iov->pos + PCI_SRIOV_CTRL, iov->ctrl);
+	msleep(100);
+	pci_cfg_access_unlock(dev);
+
 	for (i = 0; i < initial; i++) {
 		rc = pci_iov_add_virtfn(dev, i, 0);
 		if (rc)
-- 
2.1.0


From 3e5a7f5b95f00bf69e93a3b7019355ced807c3d0 Mon Sep 17 00:00:00 2001
From: Thomas Falcon <tlfalcon@linux.vnet.ibm.com>
Date: Fri, 17 Mar 2017 00:48:25 +0000
Subject: [PATCH 061/112] ibmveth: calculate gso_segs for large packets

[ Upstream commit 94acf164dc8f1184e8d0737be7125134c2701dbe ]

Include calculations to compute the number of segments
that comprise an aggregated large packet.

Signed-off-by: Thomas Falcon <tlfalcon@linux.vnet.ibm.com>
Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Reviewed-by: Jonathan Maxwell <jmaxwell37@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/net/ethernet/ibm/ibmveth.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index a36022b..03dca73 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -1181,7 +1181,9 @@ static netdev_tx_t ibmveth_start_xmit(struct sk_buff *skb,
 
 static void ibmveth_rx_mss_helper(struct sk_buff *skb, u16 mss, int lrg_pkt)
 {
+	struct tcphdr *tcph;
 	int offset = 0;
+	int hdr_len;
 
 	/* only TCP packets will be aggregated */
 	if (skb->protocol == htons(ETH_P_IP)) {
@@ -1208,14 +1210,20 @@ static void ibmveth_rx_mss_helper(struct sk_buff *skb, u16 mss, int lrg_pkt)
 	/* if mss is not set through Large Packet bit/mss in rx buffer,
 	 * expect that the mss will be written to the tcp header checksum.
 	 */
+	tcph = (struct tcphdr *)(skb->data + offset);
 	if (lrg_pkt) {
 		skb_shinfo(skb)->gso_size = mss;
 	} else if (offset) {
-		struct tcphdr *tcph = (struct tcphdr *)(skb->data + offset);
-
 		skb_shinfo(skb)->gso_size = ntohs(tcph->check);
 		tcph->check = 0;
 	}
+
+	if (skb_shinfo(skb)->gso_size) {
+		hdr_len = offset + tcph->doff * 4;
+		skb_shinfo(skb)->gso_segs =
+				DIV_ROUND_UP(skb->len - hdr_len,
+					     skb_shinfo(skb)->gso_size);
+	}
 }
 
 static int ibmveth_poll(struct napi_struct *napi, int budget)
-- 
2.1.0


From 3c0cbb47a8d634978225a52764691096a7fc1468 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Fri, 17 Mar 2017 00:48:26 +0000
Subject: [PATCH 062/112] Drivers: hv: ring_buffer: count on wrap around
 mappings in get_next_pkt_raw() (v2)

[ Upstream commit fa32ff6576623616c1751562edaed8c164ca5199 ]

With wrap around mappings in place we can always provide drivers with
direct links to packets on the ring buffer, even when they wrap around.
Do the required updates to get_next_pkt_raw()/put_pkt_raw()

The first version of this commit was reverted (65a532f3d50a) to deal with
cross-tree merge issues which are (hopefully) resolved now.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Tested-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/hyperv.h | 32 +++++++++++---------------------
 1 file changed, 11 insertions(+), 21 deletions(-)

diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 192eef2f..d596a07 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1548,31 +1548,23 @@ static inline struct vmpacket_descriptor *
 get_next_pkt_raw(struct vmbus_channel *channel)
 {
 	struct hv_ring_buffer_info *ring_info = &channel->inbound;
-	u32 read_loc = ring_info->priv_read_index;
+	u32 priv_read_loc = ring_info->priv_read_index;
 	void *ring_buffer = hv_get_ring_buffer(ring_info);
-	struct vmpacket_descriptor *cur_desc;
-	u32 packetlen;
 	u32 dsize = ring_info->ring_datasize;
-	u32 delta = read_loc - ring_info->ring_buffer->read_index;
+	/*
+	 * delta is the difference between what is available to read and
+	 * what was already consumed in place. We commit read index after
+	 * the whole batch is processed.
+	 */
+	u32 delta = priv_read_loc >= ring_info->ring_buffer->read_index ?
+		priv_read_loc - ring_info->ring_buffer->read_index :
+		(dsize - ring_info->ring_buffer->read_index) + priv_read_loc;
 	u32 bytes_avail_toread = (hv_get_bytes_to_read(ring_info) - delta);
 
 	if (bytes_avail_toread < sizeof(struct vmpacket_descriptor))
 		return NULL;
 
-	if ((read_loc + sizeof(*cur_desc)) > dsize)
-		return NULL;
-
-	cur_desc = ring_buffer + read_loc;
-	packetlen = cur_desc->len8 << 3;
-
-	/*
-	 * If the packet under consideration is wrapping around,
-	 * return failure.
-	 */
-	if ((read_loc + packetlen + VMBUS_PKT_TRAILER) > (dsize - 1))
-		return NULL;
-
-	return cur_desc;
+	return ring_buffer + priv_read_loc;
 }
 
 /*
@@ -1584,16 +1576,14 @@ static inline void put_pkt_raw(struct vmbus_channel *channel,
 				struct vmpacket_descriptor *desc)
 {
 	struct hv_ring_buffer_info *ring_info = &channel->inbound;
-	u32 read_loc = ring_info->priv_read_index;
 	u32 packetlen = desc->len8 << 3;
 	u32 dsize = ring_info->ring_datasize;
 
-	if ((read_loc + packetlen + VMBUS_PKT_TRAILER) > dsize)
-		BUG();
 	/*
 	 * Include the packet trailer.
 	 */
 	ring_info->priv_read_index += packetlen + VMBUS_PKT_TRAILER;
+	ring_info->priv_read_index %= dsize;
 }
 
 /*
-- 
2.1.0


From 5d8b3e755974494296e4a2c5874c04aba9532566 Mon Sep 17 00:00:00 2001
From: Alexey Kardashevskiy <aik@ozlabs.ru>
Date: Fri, 17 Mar 2017 00:48:26 +0000
Subject: [PATCH 063/112] vfio/spapr: Postpone allocation of userspace version
 of TCE table

[ Upstream commit 39701e56f5f16ea0cf8fc9e8472e645f8de91d23 ]

The iommu_table struct manages a hardware TCE table and a vmalloc'd
table with corresponding userspace addresses. Both are allocated when
the default DMA window is created and this happens when the very first
group is attached to a container.

As we are going to allow the userspace to configure container in one
memory context and pas container fd to another, we have to postpones
such allocations till a container fd is passed to the destination
user process so we would account locked memory limit against the actual
container user constrainsts.

This postpones the it_userspace array allocation till it is used first
time for mapping. The unmapping patch already checks if the array is
allocated.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Acked-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/vfio/vfio_iommu_spapr_tce.c | 20 +++++++-------------
 1 file changed, 7 insertions(+), 13 deletions(-)

diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index 80378dd..2a6e138 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -509,6 +509,12 @@ static long tce_iommu_build_v2(struct tce_container *container,
 	unsigned long hpa;
 	enum dma_data_direction dirtmp;
 
+	if (!tbl->it_userspace) {
+		ret = tce_iommu_userspace_view_alloc(tbl);
+		if (ret)
+			return ret;
+	}
+
 	for (i = 0; i < pages; ++i) {
 		struct mm_iommu_table_group_mem_t *mem = NULL;
 		unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl,
@@ -582,15 +588,6 @@ static long tce_iommu_create_table(struct tce_container *container,
 	WARN_ON(!ret && !(*ptbl)->it_ops->free);
 	WARN_ON(!ret && ((*ptbl)->it_allocated_size != table_size));
 
-	if (!ret && container->v2) {
-		ret = tce_iommu_userspace_view_alloc(*ptbl);
-		if (ret)
-			(*ptbl)->it_ops->free(*ptbl);
-	}
-
-	if (ret)
-		decrement_locked_vm(table_size >> PAGE_SHIFT);
-
 	return ret;
 }
 
@@ -1062,10 +1059,7 @@ static int tce_iommu_take_ownership(struct tce_container *container,
 		if (!tbl || !tbl->it_map)
 			continue;
 
-		rc = tce_iommu_userspace_view_alloc(tbl);
-		if (!rc)
-			rc = iommu_take_ownership(tbl);
-
+		rc = iommu_take_ownership(tbl);
 		if (rc) {
 			for (j = 0; j < i; ++j)
 				iommu_release_ownership(
-- 
2.1.0


From 2ba7ef21820ec5cb2376078774e24d6f6a7386b2 Mon Sep 17 00:00:00 2001
From: Alexey Kardashevskiy <aik@ozlabs.ru>
Date: Fri, 17 Mar 2017 00:48:26 +0000
Subject: [PATCH 064/112] powerpc/iommu: Pass mm_struct to init/cleanup helpers

[ Upstream commit 88f54a3581eb9deaa3bd1aade40aef266d782385 ]

We are going to get rid of @current references in mmu_context_boos3s64.c
and cache mm_struct in the VFIO container. Since mm_context_t does not
have reference counting, we will be using mm_struct which does have
the reference counter.

This changes mm_iommu_init/mm_iommu_cleanup to receive mm_struct rather
than mm_context_t (which is embedded into mm).

This should not cause any behavioral change.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/powerpc/include/asm/mmu_context.h | 4 ++--
 arch/powerpc/kernel/setup-common.c     | 2 +-
 arch/powerpc/mm/mmu_context_book3s64.c | 4 ++--
 arch/powerpc/mm/mmu_context_iommu.c    | 9 +++++----
 4 files changed, 10 insertions(+), 9 deletions(-)

diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index 5c45114..424844b 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -23,8 +23,8 @@ extern bool mm_iommu_preregistered(void);
 extern long mm_iommu_get(unsigned long ua, unsigned long entries,
 		struct mm_iommu_table_group_mem_t **pmem);
 extern long mm_iommu_put(struct mm_iommu_table_group_mem_t *mem);
-extern void mm_iommu_init(mm_context_t *ctx);
-extern void mm_iommu_cleanup(mm_context_t *ctx);
+extern void mm_iommu_init(struct mm_struct *mm);
+extern void mm_iommu_cleanup(struct mm_struct *mm);
 extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup(unsigned long ua,
 		unsigned long size);
 extern struct mm_iommu_table_group_mem_t *mm_iommu_find(unsigned long ua,
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 270ee30..f516ac5 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -915,7 +915,7 @@ void __init setup_arch(char **cmdline_p)
 	init_mm.context.pte_frag = NULL;
 #endif
 #ifdef CONFIG_SPAPR_TCE_IOMMU
-	mm_iommu_init(&init_mm.context);
+	mm_iommu_init(&init_mm);
 #endif
 	irqstack_early_init();
 	exc_lvl_early_init();
diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c
index b114f8b..ad82735 100644
--- a/arch/powerpc/mm/mmu_context_book3s64.c
+++ b/arch/powerpc/mm/mmu_context_book3s64.c
@@ -115,7 +115,7 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 	mm->context.pte_frag = NULL;
 #endif
 #ifdef CONFIG_SPAPR_TCE_IOMMU
-	mm_iommu_init(&mm->context);
+	mm_iommu_init(mm);
 #endif
 	return 0;
 }
@@ -160,7 +160,7 @@ static inline void destroy_pagetable_page(struct mm_struct *mm)
 void destroy_context(struct mm_struct *mm)
 {
 #ifdef CONFIG_SPAPR_TCE_IOMMU
-	mm_iommu_cleanup(&mm->context);
+	mm_iommu_cleanup(mm);
 #endif
 
 #ifdef CONFIG_PPC_ICSWX
diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index e0f1c33..ad2e575 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -373,16 +373,17 @@ void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem)
 }
 EXPORT_SYMBOL_GPL(mm_iommu_mapped_dec);
 
-void mm_iommu_init(mm_context_t *ctx)
+void mm_iommu_init(struct mm_struct *mm)
 {
-	INIT_LIST_HEAD_RCU(&ctx->iommu_group_mem_list);
+	INIT_LIST_HEAD_RCU(&mm->context.iommu_group_mem_list);
 }
 
-void mm_iommu_cleanup(mm_context_t *ctx)
+void mm_iommu_cleanup(struct mm_struct *mm)
 {
 	struct mm_iommu_table_group_mem_t *mem, *tmp;
 
-	list_for_each_entry_safe(mem, tmp, &ctx->iommu_group_mem_list, next) {
+	list_for_each_entry_safe(mem, tmp, &mm->context.iommu_group_mem_list,
+			next) {
 		list_del_rcu(&mem->next);
 		mm_iommu_do_free(mem);
 	}
-- 
2.1.0


From 5b34666bd2e70046f9880db01119c7d908e0888d Mon Sep 17 00:00:00 2001
From: Alexey Kardashevskiy <aik@ozlabs.ru>
Date: Fri, 17 Mar 2017 00:48:27 +0000
Subject: [PATCH 065/112] powerpc/iommu: Stop using @current in mm_iommu_xxx

[ Upstream commit d7baee6901b34c4895eb78efdbf13a49079d7404 ]

This changes mm_iommu_xxx helpers to take mm_struct as a parameter
instead of getting it from @current which in some situations may
not have a valid reference to mm.

This changes helpers to receive @mm and moves all references to @current
to the caller, including checks for !current and !current->mm;
checks in mm_iommu_preregistered() are removed as there is no caller
yet.

This moves the mm_iommu_adjust_locked_vm() call to the caller as
it receives mm_iommu_table_group_mem_t but it needs mm.

This should cause no behavioral change.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Acked-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/powerpc/include/asm/mmu_context.h | 16 ++++++------
 arch/powerpc/mm/mmu_context_iommu.c    | 46 +++++++++++++---------------------
 drivers/vfio/vfio_iommu_spapr_tce.c    | 14 ++++++++---
 3 files changed, 36 insertions(+), 40 deletions(-)

diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index 424844b..b9e3f0a 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -19,16 +19,18 @@ extern void destroy_context(struct mm_struct *mm);
 struct mm_iommu_table_group_mem_t;
 
 extern int isolate_lru_page(struct page *page);	/* from internal.h */
-extern bool mm_iommu_preregistered(void);
-extern long mm_iommu_get(unsigned long ua, unsigned long entries,
+extern bool mm_iommu_preregistered(struct mm_struct *mm);
+extern long mm_iommu_get(struct mm_struct *mm,
+		unsigned long ua, unsigned long entries,
 		struct mm_iommu_table_group_mem_t **pmem);
-extern long mm_iommu_put(struct mm_iommu_table_group_mem_t *mem);
+extern long mm_iommu_put(struct mm_struct *mm,
+		struct mm_iommu_table_group_mem_t *mem);
 extern void mm_iommu_init(struct mm_struct *mm);
 extern void mm_iommu_cleanup(struct mm_struct *mm);
-extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup(unsigned long ua,
-		unsigned long size);
-extern struct mm_iommu_table_group_mem_t *mm_iommu_find(unsigned long ua,
-		unsigned long entries);
+extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup(struct mm_struct *mm,
+		unsigned long ua, unsigned long size);
+extern struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm,
+		unsigned long ua, unsigned long entries);
 extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
 		unsigned long ua, unsigned long *hpa);
 extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem);
diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index ad2e575..4c6db09 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -56,7 +56,7 @@ static long mm_iommu_adjust_locked_vm(struct mm_struct *mm,
 	}
 
 	pr_debug("[%d] RLIMIT_MEMLOCK HASH64 %c%ld %ld/%ld\n",
-			current->pid,
+			current ? current->pid : 0,
 			incr ? '+' : '-',
 			npages << PAGE_SHIFT,
 			mm->locked_vm << PAGE_SHIFT,
@@ -66,12 +66,9 @@ static long mm_iommu_adjust_locked_vm(struct mm_struct *mm,
 	return ret;
 }
 
-bool mm_iommu_preregistered(void)
+bool mm_iommu_preregistered(struct mm_struct *mm)
 {
-	if (!current || !current->mm)
-		return false;
-
-	return !list_empty(&current->mm->context.iommu_group_mem_list);
+	return !list_empty(&mm->context.iommu_group_mem_list);
 }
 EXPORT_SYMBOL_GPL(mm_iommu_preregistered);
 
@@ -124,19 +121,16 @@ static int mm_iommu_move_page_from_cma(struct page *page)
 	return 0;
 }
 
-long mm_iommu_get(unsigned long ua, unsigned long entries,
+long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
 		struct mm_iommu_table_group_mem_t **pmem)
 {
 	struct mm_iommu_table_group_mem_t *mem;
 	long i, j, ret = 0, locked_entries = 0;
 	struct page *page = NULL;
 
-	if (!current || !current->mm)
-		return -ESRCH; /* process exited */
-
 	mutex_lock(&mem_list_mutex);
 
-	list_for_each_entry_rcu(mem, &current->mm->context.iommu_group_mem_list,
+	list_for_each_entry_rcu(mem, &mm->context.iommu_group_mem_list,
 			next) {
 		if ((mem->ua == ua) && (mem->entries == entries)) {
 			++mem->used;
@@ -154,7 +148,7 @@ long mm_iommu_get(unsigned long ua, unsigned long entries,
 
 	}
 
-	ret = mm_iommu_adjust_locked_vm(current->mm, entries, true);
+	ret = mm_iommu_adjust_locked_vm(mm, entries, true);
 	if (ret)
 		goto unlock_exit;
 
@@ -215,11 +209,11 @@ long mm_iommu_get(unsigned long ua, unsigned long entries,
 	mem->entries = entries;
 	*pmem = mem;
 
-	list_add_rcu(&mem->next, &current->mm->context.iommu_group_mem_list);
+	list_add_rcu(&mem->next, &mm->context.iommu_group_mem_list);
 
 unlock_exit:
 	if (locked_entries && ret)
-		mm_iommu_adjust_locked_vm(current->mm, locked_entries, false);
+		mm_iommu_adjust_locked_vm(mm, locked_entries, false);
 
 	mutex_unlock(&mem_list_mutex);
 
@@ -264,17 +258,13 @@ static void mm_iommu_free(struct rcu_head *head)
 static void mm_iommu_release(struct mm_iommu_table_group_mem_t *mem)
 {
 	list_del_rcu(&mem->next);
-	mm_iommu_adjust_locked_vm(current->mm, mem->entries, false);
 	call_rcu(&mem->rcu, mm_iommu_free);
 }
 
-long mm_iommu_put(struct mm_iommu_table_group_mem_t *mem)
+long mm_iommu_put(struct mm_struct *mm, struct mm_iommu_table_group_mem_t *mem)
 {
 	long ret = 0;
 
-	if (!current || !current->mm)
-		return -ESRCH; /* process exited */
-
 	mutex_lock(&mem_list_mutex);
 
 	if (mem->used == 0) {
@@ -297,6 +287,8 @@ long mm_iommu_put(struct mm_iommu_table_group_mem_t *mem)
 	/* @mapped became 0 so now mappings are disabled, release the region */
 	mm_iommu_release(mem);
 
+	mm_iommu_adjust_locked_vm(mm, mem->entries, false);
+
 unlock_exit:
 	mutex_unlock(&mem_list_mutex);
 
@@ -304,14 +296,12 @@ long mm_iommu_put(struct mm_iommu_table_group_mem_t *mem)
 }
 EXPORT_SYMBOL_GPL(mm_iommu_put);
 
-struct mm_iommu_table_group_mem_t *mm_iommu_lookup(unsigned long ua,
-		unsigned long size)
+struct mm_iommu_table_group_mem_t *mm_iommu_lookup(struct mm_struct *mm,
+		unsigned long ua, unsigned long size)
 {
 	struct mm_iommu_table_group_mem_t *mem, *ret = NULL;
 
-	list_for_each_entry_rcu(mem,
-			&current->mm->context.iommu_group_mem_list,
-			next) {
+	list_for_each_entry_rcu(mem, &mm->context.iommu_group_mem_list, next) {
 		if ((mem->ua <= ua) &&
 				(ua + size <= mem->ua +
 				 (mem->entries << PAGE_SHIFT))) {
@@ -324,14 +314,12 @@ struct mm_iommu_table_group_mem_t *mm_iommu_lookup(unsigned long ua,
 }
 EXPORT_SYMBOL_GPL(mm_iommu_lookup);
 
-struct mm_iommu_table_group_mem_t *mm_iommu_find(unsigned long ua,
-		unsigned long entries)
+struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm,
+		unsigned long ua, unsigned long entries)
 {
 	struct mm_iommu_table_group_mem_t *mem, *ret = NULL;
 
-	list_for_each_entry_rcu(mem,
-			&current->mm->context.iommu_group_mem_list,
-			next) {
+	list_for_each_entry_rcu(mem, &mm->context.iommu_group_mem_list, next) {
 		if ((mem->ua == ua) && (mem->entries == entries)) {
 			ret = mem;
 			break;
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index 2a6e138..4efd2b2 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -107,14 +107,17 @@ static long tce_iommu_unregister_pages(struct tce_container *container,
 {
 	struct mm_iommu_table_group_mem_t *mem;
 
+	if (!current || !current->mm)
+		return -ESRCH; /* process exited */
+
 	if ((vaddr & ~PAGE_MASK) || (size & ~PAGE_MASK))
 		return -EINVAL;
 
-	mem = mm_iommu_find(vaddr, size >> PAGE_SHIFT);
+	mem = mm_iommu_find(current->mm, vaddr, size >> PAGE_SHIFT);
 	if (!mem)
 		return -ENOENT;
 
-	return mm_iommu_put(mem);
+	return mm_iommu_put(current->mm, mem);
 }
 
 static long tce_iommu_register_pages(struct tce_container *container,
@@ -124,11 +127,14 @@ static long tce_iommu_register_pages(struct tce_container *container,
 	struct mm_iommu_table_group_mem_t *mem = NULL;
 	unsigned long entries = size >> PAGE_SHIFT;
 
+	if (!current || !current->mm)
+		return -ESRCH; /* process exited */
+
 	if ((vaddr & ~PAGE_MASK) || (size & ~PAGE_MASK) ||
 			((vaddr + size) < vaddr))
 		return -EINVAL;
 
-	ret = mm_iommu_get(vaddr, entries, &mem);
+	ret = mm_iommu_get(current->mm, vaddr, entries, &mem);
 	if (ret)
 		return ret;
 
@@ -375,7 +381,7 @@ static int tce_iommu_prereg_ua_to_hpa(unsigned long tce, unsigned long size,
 	long ret = 0;
 	struct mm_iommu_table_group_mem_t *mem;
 
-	mem = mm_iommu_lookup(tce, size);
+	mem = mm_iommu_lookup(current->mm, tce, size);
 	if (!mem)
 		return -EINVAL;
 
-- 
2.1.0


From 92e44bcd71ae5ae2f6d259963caf0b134243caad Mon Sep 17 00:00:00 2001
From: Alexey Kardashevskiy <aik@ozlabs.ru>
Date: Fri, 17 Mar 2017 00:48:27 +0000
Subject: [PATCH 066/112] vfio/spapr: Reference mm in tce_container

[ Upstream commit bc82d122ae4a0e9f971f13403995898fcfa0c09e ]

In some situations the userspace memory context may live longer than
the userspace process itself so if we need to do proper memory context
cleanup, we better have tce_container take a reference to mm_struct and
use it later when the process is gone (@current or @current->mm is NULL).

This references mm and stores the pointer in the container; this is done
in a new helper - tce_iommu_mm_set() - when one of the following happens:
- a container is enabled (IOMMU v1);
- a first attempt to pre-register memory is made (IOMMU v2);
- a DMA window is created (IOMMU v2).
The @mm stays referenced till the container is destroyed.

This replaces current->mm with container->mm everywhere except debug
prints.

This adds a check that current->mm is the same as the one stored in
the container to prevent userspace from making changes to a memory
context of other processes.

DMA map/unmap ioctls() do not check for @mm as they already check
for @enabled which is set after tce_iommu_mm_set() is called.

This does not reference a task as multiple threads within the same mm
are allowed to ioctl() to vfio and supposedly they will have same limits
and capabilities and if they do not, we'll just fail with no harm made.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Acked-by: Alex Williamson <alex.williamson@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/vfio/vfio_iommu_spapr_tce.c | 160 ++++++++++++++++++++++--------------
 1 file changed, 100 insertions(+), 60 deletions(-)

diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index 4efd2b2..4bebe81 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -31,49 +31,49 @@
 static void tce_iommu_detach_group(void *iommu_data,
 		struct iommu_group *iommu_group);
 
-static long try_increment_locked_vm(long npages)
+static long try_increment_locked_vm(struct mm_struct *mm, long npages)
 {
 	long ret = 0, locked, lock_limit;
 
-	if (!current || !current->mm)
-		return -ESRCH; /* process exited */
+	if (WARN_ON_ONCE(!mm))
+		return -EPERM;
 
 	if (!npages)
 		return 0;
 
-	down_write(&current->mm->mmap_sem);
-	locked = current->mm->locked_vm + npages;
+	down_write(&mm->mmap_sem);
+	locked = mm->locked_vm + npages;
 	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
 	if (locked > lock_limit && !capable(CAP_IPC_LOCK))
 		ret = -ENOMEM;
 	else
-		current->mm->locked_vm += npages;
+		mm->locked_vm += npages;
 
 	pr_debug("[%d] RLIMIT_MEMLOCK +%ld %ld/%ld%s\n", current->pid,
 			npages << PAGE_SHIFT,
-			current->mm->locked_vm << PAGE_SHIFT,
+			mm->locked_vm << PAGE_SHIFT,
 			rlimit(RLIMIT_MEMLOCK),
 			ret ? " - exceeded" : "");
 
-	up_write(&current->mm->mmap_sem);
+	up_write(&mm->mmap_sem);
 
 	return ret;
 }
 
-static void decrement_locked_vm(long npages)
+static void decrement_locked_vm(struct mm_struct *mm, long npages)
 {
-	if (!current || !current->mm || !npages)
-		return; /* process exited */
+	if (!mm || !npages)
+		return;
 
-	down_write(&current->mm->mmap_sem);
-	if (WARN_ON_ONCE(npages > current->mm->locked_vm))
-		npages = current->mm->locked_vm;
-	current->mm->locked_vm -= npages;
+	down_write(&mm->mmap_sem);
+	if (WARN_ON_ONCE(npages > mm->locked_vm))
+		npages = mm->locked_vm;
+	mm->locked_vm -= npages;
 	pr_debug("[%d] RLIMIT_MEMLOCK -%ld %ld/%ld\n", current->pid,
 			npages << PAGE_SHIFT,
-			current->mm->locked_vm << PAGE_SHIFT,
+			mm->locked_vm << PAGE_SHIFT,
 			rlimit(RLIMIT_MEMLOCK));
-	up_write(&current->mm->mmap_sem);
+	up_write(&mm->mmap_sem);
 }
 
 /*
@@ -98,26 +98,38 @@ struct tce_container {
 	bool enabled;
 	bool v2;
 	unsigned long locked_pages;
+	struct mm_struct *mm;
 	struct iommu_table *tables[IOMMU_TABLE_GROUP_MAX_TABLES];
 	struct list_head group_list;
 };
 
+static long tce_iommu_mm_set(struct tce_container *container)
+{
+	if (container->mm) {
+		if (container->mm == current->mm)
+			return 0;
+		return -EPERM;
+	}
+	BUG_ON(!current->mm);
+	container->mm = current->mm;
+	atomic_inc(&container->mm->mm_count);
+
+	return 0;
+}
+
 static long tce_iommu_unregister_pages(struct tce_container *container,
 		__u64 vaddr, __u64 size)
 {
 	struct mm_iommu_table_group_mem_t *mem;
 
-	if (!current || !current->mm)
-		return -ESRCH; /* process exited */
-
 	if ((vaddr & ~PAGE_MASK) || (size & ~PAGE_MASK))
 		return -EINVAL;
 
-	mem = mm_iommu_find(current->mm, vaddr, size >> PAGE_SHIFT);
+	mem = mm_iommu_find(container->mm, vaddr, size >> PAGE_SHIFT);
 	if (!mem)
 		return -ENOENT;
 
-	return mm_iommu_put(current->mm, mem);
+	return mm_iommu_put(container->mm, mem);
 }
 
 static long tce_iommu_register_pages(struct tce_container *container,
@@ -127,14 +139,11 @@ static long tce_iommu_register_pages(struct tce_container *container,
 	struct mm_iommu_table_group_mem_t *mem = NULL;
 	unsigned long entries = size >> PAGE_SHIFT;
 
-	if (!current || !current->mm)
-		return -ESRCH; /* process exited */
-
 	if ((vaddr & ~PAGE_MASK) || (size & ~PAGE_MASK) ||
 			((vaddr + size) < vaddr))
 		return -EINVAL;
 
-	ret = mm_iommu_get(current->mm, vaddr, entries, &mem);
+	ret = mm_iommu_get(container->mm, vaddr, entries, &mem);
 	if (ret)
 		return ret;
 
@@ -143,7 +152,8 @@ static long tce_iommu_register_pages(struct tce_container *container,
 	return 0;
 }
 
-static long tce_iommu_userspace_view_alloc(struct iommu_table *tbl)
+static long tce_iommu_userspace_view_alloc(struct iommu_table *tbl,
+		struct mm_struct *mm)
 {
 	unsigned long cb = _ALIGN_UP(sizeof(tbl->it_userspace[0]) *
 			tbl->it_size, PAGE_SIZE);
@@ -152,13 +162,13 @@ static long tce_iommu_userspace_view_alloc(struct iommu_table *tbl)
 
 	BUG_ON(tbl->it_userspace);
 
-	ret = try_increment_locked_vm(cb >> PAGE_SHIFT);
+	ret = try_increment_locked_vm(mm, cb >> PAGE_SHIFT);
 	if (ret)
 		return ret;
 
 	uas = vzalloc(cb);
 	if (!uas) {
-		decrement_locked_vm(cb >> PAGE_SHIFT);
+		decrement_locked_vm(mm, cb >> PAGE_SHIFT);
 		return -ENOMEM;
 	}
 	tbl->it_userspace = uas;
@@ -166,7 +176,8 @@ static long tce_iommu_userspace_view_alloc(struct iommu_table *tbl)
 	return 0;
 }
 
-static void tce_iommu_userspace_view_free(struct iommu_table *tbl)
+static void tce_iommu_userspace_view_free(struct iommu_table *tbl,
+		struct mm_struct *mm)
 {
 	unsigned long cb = _ALIGN_UP(sizeof(tbl->it_userspace[0]) *
 			tbl->it_size, PAGE_SIZE);
@@ -176,7 +187,7 @@ static void tce_iommu_userspace_view_free(struct iommu_table *tbl)
 
 	vfree(tbl->it_userspace);
 	tbl->it_userspace = NULL;
-	decrement_locked_vm(cb >> PAGE_SHIFT);
+	decrement_locked_vm(mm, cb >> PAGE_SHIFT);
 }
 
 static bool tce_page_is_contained(struct page *page, unsigned page_shift)
@@ -236,9 +247,6 @@ static int tce_iommu_enable(struct tce_container *container)
 	struct iommu_table_group *table_group;
 	struct tce_iommu_group *tcegrp;
 
-	if (!current->mm)
-		return -ESRCH; /* process exited */
-
 	if (container->enabled)
 		return -EBUSY;
 
@@ -283,8 +291,12 @@ static int tce_iommu_enable(struct tce_container *container)
 	if (!table_group->tce32_size)
 		return -EPERM;
 
+	ret = tce_iommu_mm_set(container);
+	if (ret)
+		return ret;
+
 	locked = table_group->tce32_size >> PAGE_SHIFT;
-	ret = try_increment_locked_vm(locked);
+	ret = try_increment_locked_vm(container->mm, locked);
 	if (ret)
 		return ret;
 
@@ -302,10 +314,8 @@ static void tce_iommu_disable(struct tce_container *container)
 
 	container->enabled = false;
 
-	if (!current->mm)
-		return;
-
-	decrement_locked_vm(container->locked_pages);
+	BUG_ON(!container->mm);
+	decrement_locked_vm(container->mm, container->locked_pages);
 }
 
 static void *tce_iommu_open(unsigned long arg)
@@ -332,7 +342,8 @@ static void *tce_iommu_open(unsigned long arg)
 static int tce_iommu_clear(struct tce_container *container,
 		struct iommu_table *tbl,
 		unsigned long entry, unsigned long pages);
-static void tce_iommu_free_table(struct iommu_table *tbl);
+static void tce_iommu_free_table(struct tce_container *container,
+		struct iommu_table *tbl);
 
 static void tce_iommu_release(void *iommu_data)
 {
@@ -357,10 +368,12 @@ static void tce_iommu_release(void *iommu_data)
 			continue;
 
 		tce_iommu_clear(container, tbl, tbl->it_offset, tbl->it_size);
-		tce_iommu_free_table(tbl);
+		tce_iommu_free_table(container, tbl);
 	}
 
 	tce_iommu_disable(container);
+	if (container->mm)
+		mmdrop(container->mm);
 	mutex_destroy(&container->lock);
 
 	kfree(container);
@@ -375,13 +388,14 @@ static void tce_iommu_unuse_page(struct tce_container *container,
 	put_page(page);
 }
 
-static int tce_iommu_prereg_ua_to_hpa(unsigned long tce, unsigned long size,
+static int tce_iommu_prereg_ua_to_hpa(struct tce_container *container,
+		unsigned long tce, unsigned long size,
 		unsigned long *phpa, struct mm_iommu_table_group_mem_t **pmem)
 {
 	long ret = 0;
 	struct mm_iommu_table_group_mem_t *mem;
 
-	mem = mm_iommu_lookup(current->mm, tce, size);
+	mem = mm_iommu_lookup(container->mm, tce, size);
 	if (!mem)
 		return -EINVAL;
 
@@ -394,18 +408,18 @@ static int tce_iommu_prereg_ua_to_hpa(unsigned long tce, unsigned long size,
 	return 0;
 }
 
-static void tce_iommu_unuse_page_v2(struct iommu_table *tbl,
-		unsigned long entry)
+static void tce_iommu_unuse_page_v2(struct tce_container *container,
+		struct iommu_table *tbl, unsigned long entry)
 {
 	struct mm_iommu_table_group_mem_t *mem = NULL;
 	int ret;
 	unsigned long hpa = 0;
 	unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
 
-	if (!pua || !current || !current->mm)
+	if (!pua)
 		return;
 
-	ret = tce_iommu_prereg_ua_to_hpa(*pua, IOMMU_PAGE_SIZE(tbl),
+	ret = tce_iommu_prereg_ua_to_hpa(container, *pua, IOMMU_PAGE_SIZE(tbl),
 			&hpa, &mem);
 	if (ret)
 		pr_debug("%s: tce %lx at #%lx was not cached, ret=%d\n",
@@ -435,7 +449,7 @@ static int tce_iommu_clear(struct tce_container *container,
 			continue;
 
 		if (container->v2) {
-			tce_iommu_unuse_page_v2(tbl, entry);
+			tce_iommu_unuse_page_v2(container, tbl, entry);
 			continue;
 		}
 
@@ -516,7 +530,7 @@ static long tce_iommu_build_v2(struct tce_container *container,
 	enum dma_data_direction dirtmp;
 
 	if (!tbl->it_userspace) {
-		ret = tce_iommu_userspace_view_alloc(tbl);
+		ret = tce_iommu_userspace_view_alloc(tbl, container->mm);
 		if (ret)
 			return ret;
 	}
@@ -526,8 +540,8 @@ static long tce_iommu_build_v2(struct tce_container *container,
 		unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl,
 				entry + i);
 
-		ret = tce_iommu_prereg_ua_to_hpa(tce, IOMMU_PAGE_SIZE(tbl),
-				&hpa, &mem);
+		ret = tce_iommu_prereg_ua_to_hpa(container,
+				tce, IOMMU_PAGE_SIZE(tbl), &hpa, &mem);
 		if (ret)
 			break;
 
@@ -548,7 +562,7 @@ static long tce_iommu_build_v2(struct tce_container *container,
 		ret = iommu_tce_xchg(tbl, entry + i, &hpa, &dirtmp);
 		if (ret) {
 			/* dirtmp cannot be DMA_NONE here */
-			tce_iommu_unuse_page_v2(tbl, entry + i);
+			tce_iommu_unuse_page_v2(container, tbl, entry + i);
 			pr_err("iommu_tce: %s failed ioba=%lx, tce=%lx, ret=%ld\n",
 					__func__, entry << tbl->it_page_shift,
 					tce, ret);
@@ -556,7 +570,7 @@ static long tce_iommu_build_v2(struct tce_container *container,
 		}
 
 		if (dirtmp != DMA_NONE)
-			tce_iommu_unuse_page_v2(tbl, entry + i);
+			tce_iommu_unuse_page_v2(container, tbl, entry + i);
 
 		*pua = tce;
 
@@ -584,7 +598,7 @@ static long tce_iommu_create_table(struct tce_container *container,
 	if (!table_size)
 		return -EINVAL;
 
-	ret = try_increment_locked_vm(table_size >> PAGE_SHIFT);
+	ret = try_increment_locked_vm(container->mm, table_size >> PAGE_SHIFT);
 	if (ret)
 		return ret;
 
@@ -597,13 +611,14 @@ static long tce_iommu_create_table(struct tce_container *container,
 	return ret;
 }
 
-static void tce_iommu_free_table(struct iommu_table *tbl)
+static void tce_iommu_free_table(struct tce_container *container,
+		struct iommu_table *tbl)
 {
 	unsigned long pages = tbl->it_allocated_size >> PAGE_SHIFT;
 
-	tce_iommu_userspace_view_free(tbl);
+	tce_iommu_userspace_view_free(tbl, container->mm);
 	tbl->it_ops->free(tbl);
-	decrement_locked_vm(pages);
+	decrement_locked_vm(container->mm, pages);
 }
 
 static long tce_iommu_create_window(struct tce_container *container,
@@ -666,7 +681,7 @@ static long tce_iommu_create_window(struct tce_container *container,
 		table_group = iommu_group_get_iommudata(tcegrp->grp);
 		table_group->ops->unset_window(table_group, num);
 	}
-	tce_iommu_free_table(tbl);
+	tce_iommu_free_table(container, tbl);
 
 	return ret;
 }
@@ -704,7 +719,7 @@ static long tce_iommu_remove_window(struct tce_container *container,
 
 	/* Free table */
 	tce_iommu_clear(container, tbl, tbl->it_offset, tbl->it_size);
-	tce_iommu_free_table(tbl);
+	tce_iommu_free_table(container, tbl);
 	container->tables[num] = NULL;
 
 	return 0;
@@ -730,7 +745,17 @@ static long tce_iommu_ioctl(void *iommu_data,
 		}
 
 		return (ret < 0) ? 0 : ret;
+	}
+
+	/*
+	 * Sanity check to prevent one userspace from manipulating
+	 * another userspace mm.
+	 */
+	BUG_ON(!container);
+	if (container->mm && container->mm != current->mm)
+		return -EPERM;
 
+	switch (cmd) {
 	case VFIO_IOMMU_SPAPR_TCE_GET_INFO: {
 		struct vfio_iommu_spapr_tce_info info;
 		struct tce_iommu_group *tcegrp;
@@ -891,6 +916,10 @@ static long tce_iommu_ioctl(void *iommu_data,
 		minsz = offsetofend(struct vfio_iommu_spapr_register_memory,
 				size);
 
+		ret = tce_iommu_mm_set(container);
+		if (ret)
+			return ret;
+
 		if (copy_from_user(&param, (void __user *)arg, minsz))
 			return -EFAULT;
 
@@ -914,6 +943,9 @@ static long tce_iommu_ioctl(void *iommu_data,
 		if (!container->v2)
 			break;
 
+		if (!container->mm)
+			return -EPERM;
+
 		minsz = offsetofend(struct vfio_iommu_spapr_register_memory,
 				size);
 
@@ -972,6 +1004,10 @@ static long tce_iommu_ioctl(void *iommu_data,
 		if (!container->v2)
 			break;
 
+		ret = tce_iommu_mm_set(container);
+		if (ret)
+			return ret;
+
 		if (!tce_groups_attached(container))
 			return -ENXIO;
 
@@ -1006,6 +1042,10 @@ static long tce_iommu_ioctl(void *iommu_data,
 		if (!container->v2)
 			break;
 
+		ret = tce_iommu_mm_set(container);
+		if (ret)
+			return ret;
+
 		if (!tce_groups_attached(container))
 			return -ENXIO;
 
@@ -1046,7 +1086,7 @@ static void tce_iommu_release_ownership(struct tce_container *container,
 			continue;
 
 		tce_iommu_clear(container, tbl, tbl->it_offset, tbl->it_size);
-		tce_iommu_userspace_view_free(tbl);
+		tce_iommu_userspace_view_free(tbl, container->mm);
 		if (tbl->it_map)
 			iommu_release_ownership(tbl);
 
-- 
2.1.0


From 080eb13542a853b0ee6061f17bf124079d08e64e Mon Sep 17 00:00:00 2001
From: Alexey Kardashevskiy <aik@ozlabs.ru>
Date: Fri, 17 Mar 2017 00:48:27 +0000
Subject: [PATCH 067/112] powerpc/mm/iommu, vfio/spapr: Put pages on VFIO
 container shutdown

[ Upstream commit 4b6fad7097f883335b6d9627c883cb7f276d94c9 ]

At the moment the userspace tool is expected to request pinning of
the entire guest RAM when VFIO IOMMU SPAPR v2 driver is present.
When the userspace process finishes, all the pinned pages need to
be put; this is done as a part of the userspace memory context (MM)
destruction which happens on the very last mmdrop().

This approach has a problem that a MM of the userspace process
may live longer than the userspace process itself as kernel threads
use userspace process MMs which was runnning on a CPU where
the kernel thread was scheduled to. If this happened, the MM remains
referenced until this exact kernel thread wakes up again
and releases the very last reference to the MM, on an idle system this
can take even hours.

This moves preregistered regions tracking from MM to VFIO; insteads of
using mm_iommu_table_group_mem_t::used, tce_container::prereg_list is
added so each container releases regions which it has pre-registered.

This changes the userspace interface to return EBUSY if a memory
region is already registered in a container. However it should not
have any practical effect as the only userspace tool available now
does register memory region once per container anyway.

As tce_iommu_register_pages/tce_iommu_unregister_pages are called
under container->lock, this does not need additional locking.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Acked-by: Alex Williamson <alex.williamson@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/powerpc/mm/mmu_context_book3s64.c |  4 +--
 arch/powerpc/mm/mmu_context_iommu.c    | 11 ------
 drivers/vfio/vfio_iommu_spapr_tce.c    | 61 +++++++++++++++++++++++++++++++++-
 3 files changed, 61 insertions(+), 15 deletions(-)

diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c
index ad82735..73bf6e1 100644
--- a/arch/powerpc/mm/mmu_context_book3s64.c
+++ b/arch/powerpc/mm/mmu_context_book3s64.c
@@ -156,13 +156,11 @@ static inline void destroy_pagetable_page(struct mm_struct *mm)
 }
 #endif
 
-
 void destroy_context(struct mm_struct *mm)
 {
 #ifdef CONFIG_SPAPR_TCE_IOMMU
-	mm_iommu_cleanup(mm);
+	WARN_ON_ONCE(!list_empty(&mm->context.iommu_group_mem_list));
 #endif
-
 #ifdef CONFIG_PPC_ICSWX
 	drop_cop(mm->context.acop, mm);
 	kfree(mm->context.cop_lockp);
diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index 4c6db09..104bad0 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -365,14 +365,3 @@ void mm_iommu_init(struct mm_struct *mm)
 {
 	INIT_LIST_HEAD_RCU(&mm->context.iommu_group_mem_list);
 }
-
-void mm_iommu_cleanup(struct mm_struct *mm)
-{
-	struct mm_iommu_table_group_mem_t *mem, *tmp;
-
-	list_for_each_entry_safe(mem, tmp, &mm->context.iommu_group_mem_list,
-			next) {
-		list_del_rcu(&mem->next);
-		mm_iommu_do_free(mem);
-	}
-}
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index 4bebe81..33e5995 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -89,6 +89,15 @@ struct tce_iommu_group {
 };
 
 /*
+ * A container needs to remember which preregistered region  it has
+ * referenced to do proper cleanup at the userspace process exit.
+ */
+struct tce_iommu_prereg {
+	struct list_head next;
+	struct mm_iommu_table_group_mem_t *mem;
+};
+
+/*
  * The container descriptor supports only a single group per container.
  * Required by the API as the container is not supplied with the IOMMU group
  * at the moment of initialization.
@@ -101,6 +110,7 @@ struct tce_container {
 	struct mm_struct *mm;
 	struct iommu_table *tables[IOMMU_TABLE_GROUP_MAX_TABLES];
 	struct list_head group_list;
+	struct list_head prereg_list;
 };
 
 static long tce_iommu_mm_set(struct tce_container *container)
@@ -117,10 +127,27 @@ static long tce_iommu_mm_set(struct tce_container *container)
 	return 0;
 }
 
+static long tce_iommu_prereg_free(struct tce_container *container,
+		struct tce_iommu_prereg *tcemem)
+{
+	long ret;
+
+	ret = mm_iommu_put(container->mm, tcemem->mem);
+	if (ret)
+		return ret;
+
+	list_del(&tcemem->next);
+	kfree(tcemem);
+
+	return 0;
+}
+
 static long tce_iommu_unregister_pages(struct tce_container *container,
 		__u64 vaddr, __u64 size)
 {
 	struct mm_iommu_table_group_mem_t *mem;
+	struct tce_iommu_prereg *tcemem;
+	bool found = false;
 
 	if ((vaddr & ~PAGE_MASK) || (size & ~PAGE_MASK))
 		return -EINVAL;
@@ -129,7 +156,17 @@ static long tce_iommu_unregister_pages(struct tce_container *container,
 	if (!mem)
 		return -ENOENT;
 
-	return mm_iommu_put(container->mm, mem);
+	list_for_each_entry(tcemem, &container->prereg_list, next) {
+		if (tcemem->mem == mem) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found)
+		return -ENOENT;
+
+	return tce_iommu_prereg_free(container, tcemem);
 }
 
 static long tce_iommu_register_pages(struct tce_container *container,
@@ -137,16 +174,29 @@ static long tce_iommu_register_pages(struct tce_container *container,
 {
 	long ret = 0;
 	struct mm_iommu_table_group_mem_t *mem = NULL;
+	struct tce_iommu_prereg *tcemem;
 	unsigned long entries = size >> PAGE_SHIFT;
 
 	if ((vaddr & ~PAGE_MASK) || (size & ~PAGE_MASK) ||
 			((vaddr + size) < vaddr))
 		return -EINVAL;
 
+	mem = mm_iommu_find(container->mm, vaddr, entries);
+	if (mem) {
+		list_for_each_entry(tcemem, &container->prereg_list, next) {
+			if (tcemem->mem == mem)
+				return -EBUSY;
+		}
+	}
+
 	ret = mm_iommu_get(container->mm, vaddr, entries, &mem);
 	if (ret)
 		return ret;
 
+	tcemem = kzalloc(sizeof(*tcemem), GFP_KERNEL);
+	tcemem->mem = mem;
+	list_add(&tcemem->next, &container->prereg_list);
+
 	container->enabled = true;
 
 	return 0;
@@ -333,6 +383,7 @@ static void *tce_iommu_open(unsigned long arg)
 
 	mutex_init(&container->lock);
 	INIT_LIST_HEAD_RCU(&container->group_list);
+	INIT_LIST_HEAD_RCU(&container->prereg_list);
 
 	container->v2 = arg == VFIO_SPAPR_TCE_v2_IOMMU;
 
@@ -371,6 +422,14 @@ static void tce_iommu_release(void *iommu_data)
 		tce_iommu_free_table(container, tbl);
 	}
 
+	while (!list_empty(&container->prereg_list)) {
+		struct tce_iommu_prereg *tcemem;
+
+		tcemem = list_first_entry(&container->prereg_list,
+				struct tce_iommu_prereg, next);
+		WARN_ON_ONCE(tce_iommu_prereg_free(container, tcemem));
+	}
+
 	tce_iommu_disable(container);
 	if (container->mm)
 		mmdrop(container->mm);
-- 
2.1.0


From 2e60baca235b05d4026207e31b6fc385c0c1c122 Mon Sep 17 00:00:00 2001
From: Alexey Kardashevskiy <aik@ozlabs.ru>
Date: Fri, 17 Mar 2017 00:48:28 +0000
Subject: [PATCH 068/112] vfio/spapr: Add a helper to create default DMA window

[ Upstream commit 6f01cc692a16405235d5c34056455b182682123c ]

There is already a helper to create a DMA window which does allocate
a table and programs it to the IOMMU group. However
tce_iommu_take_ownership_ddw() did not use it and did these 2 calls
itself to simplify error path.

Since we are going to delay the default window creation till
the default window is accessed/removed or new window is added,
we need a helper to create a default window from all these cases.

This adds tce_iommu_create_default_window(). Since it relies on
a VFIO container to have at least one IOMMU group (for future use),
this changes tce_iommu_attach_group() to add a group to the container
first and then call the new helper.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Acked-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/vfio/vfio_iommu_spapr_tce.c | 87 ++++++++++++++++++-------------------
 1 file changed, 42 insertions(+), 45 deletions(-)

diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index 33e5995..e95c3eb 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -784,6 +784,29 @@ static long tce_iommu_remove_window(struct tce_container *container,
 	return 0;
 }
 
+static long tce_iommu_create_default_window(struct tce_container *container)
+{
+	long ret;
+	__u64 start_addr = 0;
+	struct tce_iommu_group *tcegrp;
+	struct iommu_table_group *table_group;
+
+	if (!tce_groups_attached(container))
+		return -ENODEV;
+
+	tcegrp = list_first_entry(&container->group_list,
+			struct tce_iommu_group, next);
+	table_group = iommu_group_get_iommudata(tcegrp->grp);
+	if (!table_group)
+		return -ENODEV;
+
+	ret = tce_iommu_create_window(container, IOMMU_PAGE_SHIFT_4K,
+			table_group->tce32_size, 1, &start_addr);
+	WARN_ON_ONCE(!ret && start_addr);
+
+	return ret;
+}
+
 static long tce_iommu_ioctl(void *iommu_data,
 				 unsigned int cmd, unsigned long arg)
 {
@@ -1199,9 +1222,6 @@ static void tce_iommu_release_ownership_ddw(struct tce_container *container,
 static long tce_iommu_take_ownership_ddw(struct tce_container *container,
 		struct iommu_table_group *table_group)
 {
-	long i, ret = 0;
-	struct iommu_table *tbl = NULL;
-
 	if (!table_group->ops->create_table || !table_group->ops->set_window ||
 			!table_group->ops->release_ownership) {
 		WARN_ON_ONCE(1);
@@ -1210,47 +1230,7 @@ static long tce_iommu_take_ownership_ddw(struct tce_container *container,
 
 	table_group->ops->take_ownership(table_group);
 
-	/*
-	 * If it the first group attached, check if there is
-	 * a default DMA window and create one if none as
-	 * the userspace expects it to exist.
-	 */
-	if (!tce_groups_attached(container) && !container->tables[0]) {
-		ret = tce_iommu_create_table(container,
-				table_group,
-				0, /* window number */
-				IOMMU_PAGE_SHIFT_4K,
-				table_group->tce32_size,
-				1, /* default levels */
-				&tbl);
-		if (ret)
-			goto release_exit;
-		else
-			container->tables[0] = tbl;
-	}
-
-	/* Set all windows to the new group */
-	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
-		tbl = container->tables[i];
-
-		if (!tbl)
-			continue;
-
-		/* Set the default window to a new group */
-		ret = table_group->ops->set_window(table_group, i, tbl);
-		if (ret)
-			goto release_exit;
-	}
-
 	return 0;
-
-release_exit:
-	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i)
-		table_group->ops->unset_window(table_group, i);
-
-	table_group->ops->release_ownership(table_group);
-
-	return ret;
 }
 
 static int tce_iommu_attach_group(void *iommu_data,
@@ -1260,6 +1240,7 @@ static int tce_iommu_attach_group(void *iommu_data,
 	struct tce_container *container = iommu_data;
 	struct iommu_table_group *table_group;
 	struct tce_iommu_group *tcegrp = NULL;
+	bool create_default_window = false;
 
 	mutex_lock(&container->lock);
 
@@ -1302,14 +1283,30 @@ static int tce_iommu_attach_group(void *iommu_data,
 	}
 
 	if (!table_group->ops || !table_group->ops->take_ownership ||
-			!table_group->ops->release_ownership)
+			!table_group->ops->release_ownership) {
 		ret = tce_iommu_take_ownership(container, table_group);
-	else
+	} else {
 		ret = tce_iommu_take_ownership_ddw(container, table_group);
+		if (!tce_groups_attached(container) && !container->tables[0])
+			create_default_window = true;
+	}
 
 	if (!ret) {
 		tcegrp->grp = iommu_group;
 		list_add(&tcegrp->next, &container->group_list);
+		/*
+		 * If it the first group attached, check if there is
+		 * a default DMA window and create one if none as
+		 * the userspace expects it to exist.
+		 */
+		if (create_default_window) {
+			ret = tce_iommu_create_default_window(container);
+			if (ret) {
+				list_del(&tcegrp->next);
+				tce_iommu_release_ownership_ddw(container,
+						table_group);
+			}
+		}
 	}
 
 unlock_exit:
-- 
2.1.0


From 53e18968a9c0753e542cc4f6b0cc2da5db64ffd9 Mon Sep 17 00:00:00 2001
From: Alexey Kardashevskiy <aik@ozlabs.ru>
Date: Fri, 17 Mar 2017 00:48:29 +0000
Subject: [PATCH 069/112] vfio/spapr: Postpone default window creation

[ Upstream commit d9c728949ddc9de5734bf3b12ea906ca8a77f2a0 ]

We are going to allow the userspace to configure container in
one memory context and pass container fd to another so
we are postponing memory allocations accounted against
the locked memory limit. One of previous patches took care of
it_userspace.

At the moment we create the default DMA window when the first group is
attached to a container; this is done for the userspace which is not
DDW-aware but familiar with the SPAPR TCE IOMMU v2 in the part of memory
pre-registration - such client expects the default DMA window to exist.

This postpones the default DMA window allocation till one of
the folliwing happens:
1. first map/unmap request arrives;
2. new window is requested;
This adds noop for the case when the userspace requested removal
of the default window which has not been created yet.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Acked-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/vfio/vfio_iommu_spapr_tce.c | 40 +++++++++++++++++++++++--------------
 1 file changed, 25 insertions(+), 15 deletions(-)

diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index e95c3eb..c882357 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -106,6 +106,7 @@ struct tce_container {
 	struct mutex lock;
 	bool enabled;
 	bool v2;
+	bool def_window_pending;
 	unsigned long locked_pages;
 	struct mm_struct *mm;
 	struct iommu_table *tables[IOMMU_TABLE_GROUP_MAX_TABLES];
@@ -791,6 +792,9 @@ static long tce_iommu_create_default_window(struct tce_container *container)
 	struct tce_iommu_group *tcegrp;
 	struct iommu_table_group *table_group;
 
+	if (!container->def_window_pending)
+		return 0;
+
 	if (!tce_groups_attached(container))
 		return -ENODEV;
 
@@ -804,6 +808,9 @@ static long tce_iommu_create_default_window(struct tce_container *container)
 			table_group->tce32_size, 1, &start_addr);
 	WARN_ON_ONCE(!ret && start_addr);
 
+	if (!ret)
+		container->def_window_pending = false;
+
 	return ret;
 }
 
@@ -907,6 +914,10 @@ static long tce_iommu_ioctl(void *iommu_data,
 				VFIO_DMA_MAP_FLAG_WRITE))
 			return -EINVAL;
 
+		ret = tce_iommu_create_default_window(container);
+		if (ret)
+			return ret;
+
 		num = tce_iommu_find_table(container, param.iova, &tbl);
 		if (num < 0)
 			return -ENXIO;
@@ -970,6 +981,10 @@ static long tce_iommu_ioctl(void *iommu_data,
 		if (param.flags)
 			return -EINVAL;
 
+		ret = tce_iommu_create_default_window(container);
+		if (ret)
+			return ret;
+
 		num = tce_iommu_find_table(container, param.iova, &tbl);
 		if (num < 0)
 			return -ENXIO;
@@ -1107,6 +1122,10 @@ static long tce_iommu_ioctl(void *iommu_data,
 
 		mutex_lock(&container->lock);
 
+		ret = tce_iommu_create_default_window(container);
+		if (ret)
+			return ret;
+
 		ret = tce_iommu_create_window(container, create.page_shift,
 				create.window_size, create.levels,
 				&create.start_addr);
@@ -1143,6 +1162,11 @@ static long tce_iommu_ioctl(void *iommu_data,
 		if (remove.flags)
 			return -EINVAL;
 
+		if (container->def_window_pending && !remove.start_addr) {
+			container->def_window_pending = false;
+			return 0;
+		}
+
 		mutex_lock(&container->lock);
 
 		ret = tce_iommu_remove_window(container, remove.start_addr);
@@ -1240,7 +1264,6 @@ static int tce_iommu_attach_group(void *iommu_data,
 	struct tce_container *container = iommu_data;
 	struct iommu_table_group *table_group;
 	struct tce_iommu_group *tcegrp = NULL;
-	bool create_default_window = false;
 
 	mutex_lock(&container->lock);
 
@@ -1288,25 +1311,12 @@ static int tce_iommu_attach_group(void *iommu_data,
 	} else {
 		ret = tce_iommu_take_ownership_ddw(container, table_group);
 		if (!tce_groups_attached(container) && !container->tables[0])
-			create_default_window = true;
+			container->def_window_pending = true;
 	}
 
 	if (!ret) {
 		tcegrp->grp = iommu_group;
 		list_add(&tcegrp->next, &container->group_list);
-		/*
-		 * If it the first group attached, check if there is
-		 * a default DMA window and create one if none as
-		 * the userspace expects it to exist.
-		 */
-		if (create_default_window) {
-			ret = tce_iommu_create_default_window(container);
-			if (ret) {
-				list_del(&tcegrp->next);
-				tce_iommu_release_ownership_ddw(container,
-						table_group);
-			}
-		}
 	}
 
 unlock_exit:
-- 
2.1.0


From ddc23b5212b9cfa2e4f802bd95e365e63a6b2cc7 Mon Sep 17 00:00:00 2001
From: Ben Skeggs <bskeggs@redhat.com>
Date: Fri, 17 Mar 2017 00:48:29 +0000
Subject: [PATCH 070/112] drm/nouveau/disp/gp102: fix cursor/overlay immediate
 channel indices

[ Upstream commit e50fcff15fe120ef2103a9e18af6644235c2b14d ]

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild    |  2 ++
 .../gpu/drm/nouveau/nvkm/engine/disp/channv50.h    |  2 ++
 .../gpu/drm/nouveau/nvkm/engine/disp/cursgp102.c   | 37 ++++++++++++++++++++++
 .../gpu/drm/nouveau/nvkm/engine/disp/oimmgp102.c   | 37 ++++++++++++++++++++++
 .../gpu/drm/nouveau/nvkm/engine/disp/rootgp104.c   |  4 +--
 5 files changed, 80 insertions(+), 2 deletions(-)
 create mode 100644 drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgp102.c
 create mode 100644 drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmgp102.c

diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild
index 77a52b5..70f0344 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild
@@ -95,9 +95,11 @@ nvkm-y += nvkm/engine/disp/cursg84.o
 nvkm-y += nvkm/engine/disp/cursgt215.o
 nvkm-y += nvkm/engine/disp/cursgf119.o
 nvkm-y += nvkm/engine/disp/cursgk104.o
+nvkm-y += nvkm/engine/disp/cursgp102.o
 
 nvkm-y += nvkm/engine/disp/oimmnv50.o
 nvkm-y += nvkm/engine/disp/oimmg84.o
 nvkm-y += nvkm/engine/disp/oimmgt215.o
 nvkm-y += nvkm/engine/disp/oimmgf119.o
 nvkm-y += nvkm/engine/disp/oimmgk104.o
+nvkm-y += nvkm/engine/disp/oimmgp102.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.h
index f5f683d..04a7e58 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.h
@@ -114,6 +114,8 @@ extern const struct nv50_disp_pioc_oclass gf119_disp_curs_oclass;
 extern const struct nv50_disp_pioc_oclass gk104_disp_oimm_oclass;
 extern const struct nv50_disp_pioc_oclass gk104_disp_curs_oclass;
 
+extern const struct nv50_disp_pioc_oclass gp102_disp_oimm_oclass;
+extern const struct nv50_disp_pioc_oclass gp102_disp_curs_oclass;
 
 int nv50_disp_curs_new(const struct nv50_disp_chan_func *,
 		       const struct nv50_disp_chan_mthd *,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgp102.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgp102.c
new file mode 100644
index 0000000..e958210
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgp102.c
@@ -0,0 +1,37 @@
+/*
+ * Copyright 2016 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs <bskeggs@redhat.com>
+ */
+#include "channv50.h"
+#include "rootnv50.h"
+
+#include <nvif/class.h>
+
+const struct nv50_disp_pioc_oclass
+gp102_disp_curs_oclass = {
+	.base.oclass = GK104_DISP_CURSOR,
+	.base.minver = 0,
+	.base.maxver = 0,
+	.ctor = nv50_disp_curs_new,
+	.func = &gf119_disp_pioc_func,
+	.chid = { 13, 17 },
+};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmgp102.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmgp102.c
new file mode 100644
index 0000000..abf8236
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmgp102.c
@@ -0,0 +1,37 @@
+/*
+ * Copyright 2016 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs <bskeggs@redhat.com>
+ */
+#include "channv50.h"
+#include "rootnv50.h"
+
+#include <nvif/class.h>
+
+const struct nv50_disp_pioc_oclass
+gp102_disp_oimm_oclass = {
+	.base.oclass = GK104_DISP_OVERLAY,
+	.base.minver = 0,
+	.base.maxver = 0,
+	.ctor = nv50_disp_oimm_new,
+	.func = &gf119_disp_pioc_func,
+	.chid = { 9, 13 },
+};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgp104.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgp104.c
index 8443e04..b053b29 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgp104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootgp104.c
@@ -36,8 +36,8 @@ gp104_disp_root = {
 		&gp104_disp_ovly_oclass,
 	},
 	.pioc = {
-		&gk104_disp_oimm_oclass,
-		&gk104_disp_curs_oclass,
+		&gp102_disp_oimm_oclass,
+		&gp102_disp_curs_oclass,
 	},
 };
 
-- 
2.1.0


From 5001756c1c70ab555d4d3ca6965547ac02410d4b Mon Sep 17 00:00:00 2001
From: Ben Skeggs <bskeggs@redhat.com>
Date: Fri, 17 Mar 2017 00:48:29 +0000
Subject: [PATCH 071/112] drm/nouveau/disp/nv50-: split chid into chid.ctrl and
 chid.user

[ Upstream commit 4391d7f5c79a9fe6fa11cf6c160ca7f7bdb49d2a ]

GP102/GP104 make life difficult by redefining the channel indices for
some registers, but not others.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../gpu/drm/nouveau/nvkm/engine/disp/channv50.c    | 23 +++++------
 .../gpu/drm/nouveau/nvkm/engine/disp/channv50.h    |  6 ++-
 .../gpu/drm/nouveau/nvkm/engine/disp/dmacgf119.c   | 44 +++++++++++-----------
 .../gpu/drm/nouveau/nvkm/engine/disp/dmacgp104.c   | 23 +++++------
 .../gpu/drm/nouveau/nvkm/engine/disp/dmacnv50.c    | 44 +++++++++++-----------
 .../gpu/drm/nouveau/nvkm/engine/disp/piocgf119.c   | 28 +++++++-------
 .../gpu/drm/nouveau/nvkm/engine/disp/piocnv50.c    | 30 ++++++++-------
 7 files changed, 106 insertions(+), 92 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c
index dd2953b..376f2c6 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c
@@ -82,7 +82,7 @@ nv50_disp_chan_mthd(struct nv50_disp_chan *chan, int debug)
 
 			if (mthd->addr) {
 				snprintf(cname_, sizeof(cname_), "%s %d",
-					 mthd->name, chan->chid);
+					 mthd->name, chan->chid.user);
 				cname = cname_;
 			}
 
@@ -139,7 +139,7 @@ nv50_disp_chan_uevent_ctor(struct nvkm_object *object, void *data, u32 size,
 	if (!(ret = nvif_unvers(ret, &data, &size, args->none))) {
 		notify->size  = sizeof(struct nvif_notify_uevent_rep);
 		notify->types = 1;
-		notify->index = chan->chid;
+		notify->index = chan->chid.user;
 		return 0;
 	}
 
@@ -159,7 +159,7 @@ nv50_disp_chan_rd32(struct nvkm_object *object, u64 addr, u32 *data)
 	struct nv50_disp_chan *chan = nv50_disp_chan(object);
 	struct nv50_disp *disp = chan->root->disp;
 	struct nvkm_device *device = disp->base.engine.subdev.device;
-	*data = nvkm_rd32(device, 0x640000 + (chan->chid * 0x1000) + addr);
+	*data = nvkm_rd32(device, 0x640000 + (chan->chid.user * 0x1000) + addr);
 	return 0;
 }
 
@@ -169,7 +169,7 @@ nv50_disp_chan_wr32(struct nvkm_object *object, u64 addr, u32 data)
 	struct nv50_disp_chan *chan = nv50_disp_chan(object);
 	struct nv50_disp *disp = chan->root->disp;
 	struct nvkm_device *device = disp->base.engine.subdev.device;
-	nvkm_wr32(device, 0x640000 + (chan->chid * 0x1000) + addr, data);
+	nvkm_wr32(device, 0x640000 + (chan->chid.user * 0x1000) + addr, data);
 	return 0;
 }
 
@@ -196,7 +196,7 @@ nv50_disp_chan_map(struct nvkm_object *object, u64 *addr, u32 *size)
 	struct nv50_disp *disp = chan->root->disp;
 	struct nvkm_device *device = disp->base.engine.subdev.device;
 	*addr = device->func->resource_addr(device, 0) +
-		0x640000 + (chan->chid * 0x1000);
+		0x640000 + (chan->chid.user * 0x1000);
 	*size = 0x001000;
 	return 0;
 }
@@ -243,8 +243,8 @@ nv50_disp_chan_dtor(struct nvkm_object *object)
 {
 	struct nv50_disp_chan *chan = nv50_disp_chan(object);
 	struct nv50_disp *disp = chan->root->disp;
-	if (chan->chid >= 0)
-		disp->chan[chan->chid] = NULL;
+	if (chan->chid.user >= 0)
+		disp->chan[chan->chid.user] = NULL;
 	return chan->func->dtor ? chan->func->dtor(chan) : chan;
 }
 
@@ -273,14 +273,15 @@ nv50_disp_chan_ctor(const struct nv50_disp_chan_func *func,
 	chan->func = func;
 	chan->mthd = mthd;
 	chan->root = root;
-	chan->chid = chid;
+	chan->chid.ctrl = chid;
+	chan->chid.user = chid;
 	chan->head = head;
 
-	if (disp->chan[chan->chid]) {
-		chan->chid = -1;
+	if (disp->chan[chan->chid.user]) {
+		chan->chid.user = -1;
 		return -EBUSY;
 	}
-	disp->chan[chan->chid] = chan;
+	disp->chan[chan->chid.user] = chan;
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.h
index 04a7e58..7b5a2ea 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.h
@@ -7,7 +7,11 @@ struct nv50_disp_chan {
 	const struct nv50_disp_chan_func *func;
 	const struct nv50_disp_chan_mthd *mthd;
 	struct nv50_disp_root *root;
-	int chid;
+
+	struct {
+		int ctrl;
+		int user;
+	} chid;
 	int head;
 
 	struct nvkm_object object;
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacgf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacgf119.c
index a57f7ce..ce7cd74 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacgf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacgf119.c
@@ -32,8 +32,8 @@ gf119_disp_dmac_bind(struct nv50_disp_dmac *chan,
 		     struct nvkm_object *object, u32 handle)
 {
 	return nvkm_ramht_insert(chan->base.root->ramht, object,
-				 chan->base.chid, -9, handle,
-				 chan->base.chid << 27 | 0x00000001);
+				 chan->base.chid.user, -9, handle,
+				 chan->base.chid.user << 27 | 0x00000001);
 }
 
 void
@@ -42,22 +42,23 @@ gf119_disp_dmac_fini(struct nv50_disp_dmac *chan)
 	struct nv50_disp *disp = chan->base.root->disp;
 	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
 	struct nvkm_device *device = subdev->device;
-	int chid = chan->base.chid;
+	int ctrl = chan->base.chid.ctrl;
+	int user = chan->base.chid.user;
 
 	/* deactivate channel */
-	nvkm_mask(device, 0x610490 + (chid * 0x0010), 0x00001010, 0x00001000);
-	nvkm_mask(device, 0x610490 + (chid * 0x0010), 0x00000003, 0x00000000);
+	nvkm_mask(device, 0x610490 + (ctrl * 0x0010), 0x00001010, 0x00001000);
+	nvkm_mask(device, 0x610490 + (ctrl * 0x0010), 0x00000003, 0x00000000);
 	if (nvkm_msec(device, 2000,
-		if (!(nvkm_rd32(device, 0x610490 + (chid * 0x10)) & 0x001e0000))
+		if (!(nvkm_rd32(device, 0x610490 + (ctrl * 0x10)) & 0x001e0000))
 			break;
 	) < 0) {
-		nvkm_error(subdev, "ch %d fini: %08x\n", chid,
-			   nvkm_rd32(device, 0x610490 + (chid * 0x10)));
+		nvkm_error(subdev, "ch %d fini: %08x\n", user,
+			   nvkm_rd32(device, 0x610490 + (ctrl * 0x10)));
 	}
 
 	/* disable error reporting and completion notification */
-	nvkm_mask(device, 0x610090, 0x00000001 << chid, 0x00000000);
-	nvkm_mask(device, 0x6100a0, 0x00000001 << chid, 0x00000000);
+	nvkm_mask(device, 0x610090, 0x00000001 << user, 0x00000000);
+	nvkm_mask(device, 0x6100a0, 0x00000001 << user, 0x00000000);
 }
 
 static int
@@ -66,26 +67,27 @@ gf119_disp_dmac_init(struct nv50_disp_dmac *chan)
 	struct nv50_disp *disp = chan->base.root->disp;
 	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
 	struct nvkm_device *device = subdev->device;
-	int chid = chan->base.chid;
+	int ctrl = chan->base.chid.ctrl;
+	int user = chan->base.chid.user;
 
 	/* enable error reporting */
-	nvkm_mask(device, 0x6100a0, 0x00000001 << chid, 0x00000001 << chid);
+	nvkm_mask(device, 0x6100a0, 0x00000001 << user, 0x00000001 << user);
 
 	/* initialise channel for dma command submission */
-	nvkm_wr32(device, 0x610494 + (chid * 0x0010), chan->push);
-	nvkm_wr32(device, 0x610498 + (chid * 0x0010), 0x00010000);
-	nvkm_wr32(device, 0x61049c + (chid * 0x0010), 0x00000001);
-	nvkm_mask(device, 0x610490 + (chid * 0x0010), 0x00000010, 0x00000010);
-	nvkm_wr32(device, 0x640000 + (chid * 0x1000), 0x00000000);
-	nvkm_wr32(device, 0x610490 + (chid * 0x0010), 0x00000013);
+	nvkm_wr32(device, 0x610494 + (ctrl * 0x0010), chan->push);
+	nvkm_wr32(device, 0x610498 + (ctrl * 0x0010), 0x00010000);
+	nvkm_wr32(device, 0x61049c + (ctrl * 0x0010), 0x00000001);
+	nvkm_mask(device, 0x610490 + (ctrl * 0x0010), 0x00000010, 0x00000010);
+	nvkm_wr32(device, 0x640000 + (ctrl * 0x1000), 0x00000000);
+	nvkm_wr32(device, 0x610490 + (ctrl * 0x0010), 0x00000013);
 
 	/* wait for it to go inactive */
 	if (nvkm_msec(device, 2000,
-		if (!(nvkm_rd32(device, 0x610490 + (chid * 0x10)) & 0x80000000))
+		if (!(nvkm_rd32(device, 0x610490 + (ctrl * 0x10)) & 0x80000000))
 			break;
 	) < 0) {
-		nvkm_error(subdev, "ch %d init: %08x\n", chid,
-			   nvkm_rd32(device, 0x610490 + (chid * 0x10)));
+		nvkm_error(subdev, "ch %d init: %08x\n", user,
+			   nvkm_rd32(device, 0x610490 + (ctrl * 0x10)));
 		return -EBUSY;
 	}
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacgp104.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacgp104.c
index ad24c2c..d26d3b4 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacgp104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacgp104.c
@@ -32,26 +32,27 @@ gp104_disp_dmac_init(struct nv50_disp_dmac *chan)
 	struct nv50_disp *disp = chan->base.root->disp;
 	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
 	struct nvkm_device *device = subdev->device;
-	int chid = chan->base.chid;
+	int ctrl = chan->base.chid.ctrl;
+	int user = chan->base.chid.user;
 
 	/* enable error reporting */
-	nvkm_mask(device, 0x6100a0, 0x00000001 << chid, 0x00000001 << chid);
+	nvkm_mask(device, 0x6100a0, 0x00000001 << user, 0x00000001 << user);
 
 	/* initialise channel for dma command submission */
-	nvkm_wr32(device, 0x611494 + (chid * 0x0010), chan->push);
-	nvkm_wr32(device, 0x611498 + (chid * 0x0010), 0x00010000);
-	nvkm_wr32(device, 0x61149c + (chid * 0x0010), 0x00000001);
-	nvkm_mask(device, 0x610490 + (chid * 0x0010), 0x00000010, 0x00000010);
-	nvkm_wr32(device, 0x640000 + (chid * 0x1000), 0x00000000);
-	nvkm_wr32(device, 0x610490 + (chid * 0x0010), 0x00000013);
+	nvkm_wr32(device, 0x611494 + (ctrl * 0x0010), chan->push);
+	nvkm_wr32(device, 0x611498 + (ctrl * 0x0010), 0x00010000);
+	nvkm_wr32(device, 0x61149c + (ctrl * 0x0010), 0x00000001);
+	nvkm_mask(device, 0x610490 + (ctrl * 0x0010), 0x00000010, 0x00000010);
+	nvkm_wr32(device, 0x640000 + (ctrl * 0x1000), 0x00000000);
+	nvkm_wr32(device, 0x610490 + (ctrl * 0x0010), 0x00000013);
 
 	/* wait for it to go inactive */
 	if (nvkm_msec(device, 2000,
-		if (!(nvkm_rd32(device, 0x610490 + (chid * 0x10)) & 0x80000000))
+		if (!(nvkm_rd32(device, 0x610490 + (ctrl * 0x10)) & 0x80000000))
 			break;
 	) < 0) {
-		nvkm_error(subdev, "ch %d init: %08x\n", chid,
-			   nvkm_rd32(device, 0x610490 + (chid * 0x10)));
+		nvkm_error(subdev, "ch %d init: %08x\n", user,
+			   nvkm_rd32(device, 0x610490 + (ctrl * 0x10)));
 		return -EBUSY;
 	}
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacnv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacnv50.c
index 9c6645a..cfba994 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacnv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacnv50.c
@@ -179,9 +179,9 @@ nv50_disp_dmac_bind(struct nv50_disp_dmac *chan,
 		    struct nvkm_object *object, u32 handle)
 {
 	return nvkm_ramht_insert(chan->base.root->ramht, object,
-				 chan->base.chid, -10, handle,
-				 chan->base.chid << 28 |
-				 chan->base.chid);
+				 chan->base.chid.user, -10, handle,
+				 chan->base.chid.user << 28 |
+				 chan->base.chid.user);
 }
 
 static void
@@ -190,21 +190,22 @@ nv50_disp_dmac_fini(struct nv50_disp_dmac *chan)
 	struct nv50_disp *disp = chan->base.root->disp;
 	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
 	struct nvkm_device *device = subdev->device;
-	int chid = chan->base.chid;
+	int ctrl = chan->base.chid.ctrl;
+	int user = chan->base.chid.user;
 
 	/* deactivate channel */
-	nvkm_mask(device, 0x610200 + (chid * 0x0010), 0x00001010, 0x00001000);
-	nvkm_mask(device, 0x610200 + (chid * 0x0010), 0x00000003, 0x00000000);
+	nvkm_mask(device, 0x610200 + (ctrl * 0x0010), 0x00001010, 0x00001000);
+	nvkm_mask(device, 0x610200 + (ctrl * 0x0010), 0x00000003, 0x00000000);
 	if (nvkm_msec(device, 2000,
-		if (!(nvkm_rd32(device, 0x610200 + (chid * 0x10)) & 0x001e0000))
+		if (!(nvkm_rd32(device, 0x610200 + (ctrl * 0x10)) & 0x001e0000))
 			break;
 	) < 0) {
-		nvkm_error(subdev, "ch %d fini timeout, %08x\n", chid,
-			   nvkm_rd32(device, 0x610200 + (chid * 0x10)));
+		nvkm_error(subdev, "ch %d fini timeout, %08x\n", user,
+			   nvkm_rd32(device, 0x610200 + (ctrl * 0x10)));
 	}
 
 	/* disable error reporting and completion notifications */
-	nvkm_mask(device, 0x610028, 0x00010001 << chid, 0x00000000 << chid);
+	nvkm_mask(device, 0x610028, 0x00010001 << user, 0x00000000 << user);
 }
 
 static int
@@ -213,26 +214,27 @@ nv50_disp_dmac_init(struct nv50_disp_dmac *chan)
 	struct nv50_disp *disp = chan->base.root->disp;
 	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
 	struct nvkm_device *device = subdev->device;
-	int chid = chan->base.chid;
+	int ctrl = chan->base.chid.ctrl;
+	int user = chan->base.chid.user;
 
 	/* enable error reporting */
-	nvkm_mask(device, 0x610028, 0x00010000 << chid, 0x00010000 << chid);
+	nvkm_mask(device, 0x610028, 0x00010000 << user, 0x00010000 << user);
 
 	/* initialise channel for dma command submission */
-	nvkm_wr32(device, 0x610204 + (chid * 0x0010), chan->push);
-	nvkm_wr32(device, 0x610208 + (chid * 0x0010), 0x00010000);
-	nvkm_wr32(device, 0x61020c + (chid * 0x0010), chid);
-	nvkm_mask(device, 0x610200 + (chid * 0x0010), 0x00000010, 0x00000010);
-	nvkm_wr32(device, 0x640000 + (chid * 0x1000), 0x00000000);
-	nvkm_wr32(device, 0x610200 + (chid * 0x0010), 0x00000013);
+	nvkm_wr32(device, 0x610204 + (ctrl * 0x0010), chan->push);
+	nvkm_wr32(device, 0x610208 + (ctrl * 0x0010), 0x00010000);
+	nvkm_wr32(device, 0x61020c + (ctrl * 0x0010), ctrl);
+	nvkm_mask(device, 0x610200 + (ctrl * 0x0010), 0x00000010, 0x00000010);
+	nvkm_wr32(device, 0x640000 + (ctrl * 0x1000), 0x00000000);
+	nvkm_wr32(device, 0x610200 + (ctrl * 0x0010), 0x00000013);
 
 	/* wait for it to go inactive */
 	if (nvkm_msec(device, 2000,
-		if (!(nvkm_rd32(device, 0x610200 + (chid * 0x10)) & 0x80000000))
+		if (!(nvkm_rd32(device, 0x610200 + (ctrl * 0x10)) & 0x80000000))
 			break;
 	) < 0) {
-		nvkm_error(subdev, "ch %d init timeout, %08x\n", chid,
-			   nvkm_rd32(device, 0x610200 + (chid * 0x10)));
+		nvkm_error(subdev, "ch %d init timeout, %08x\n", user,
+			   nvkm_rd32(device, 0x610200 + (ctrl * 0x10)));
 		return -EBUSY;
 	}
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/piocgf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/piocgf119.c
index a625a98..0abaa64 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/piocgf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/piocgf119.c
@@ -32,20 +32,21 @@ gf119_disp_pioc_fini(struct nv50_disp_chan *chan)
 	struct nv50_disp *disp = chan->root->disp;
 	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
 	struct nvkm_device *device = subdev->device;
-	int chid = chan->chid;
+	int ctrl = chan->chid.ctrl;
+	int user = chan->chid.user;
 
-	nvkm_mask(device, 0x610490 + (chid * 0x10), 0x00000001, 0x00000000);
+	nvkm_mask(device, 0x610490 + (ctrl * 0x10), 0x00000001, 0x00000000);
 	if (nvkm_msec(device, 2000,
-		if (!(nvkm_rd32(device, 0x610490 + (chid * 0x10)) & 0x00030000))
+		if (!(nvkm_rd32(device, 0x610490 + (ctrl * 0x10)) & 0x00030000))
 			break;
 	) < 0) {
-		nvkm_error(subdev, "ch %d fini: %08x\n", chid,
-			   nvkm_rd32(device, 0x610490 + (chid * 0x10)));
+		nvkm_error(subdev, "ch %d fini: %08x\n", user,
+			   nvkm_rd32(device, 0x610490 + (ctrl * 0x10)));
 	}
 
 	/* disable error reporting and completion notification */
-	nvkm_mask(device, 0x610090, 0x00000001 << chid, 0x00000000);
-	nvkm_mask(device, 0x6100a0, 0x00000001 << chid, 0x00000000);
+	nvkm_mask(device, 0x610090, 0x00000001 << user, 0x00000000);
+	nvkm_mask(device, 0x6100a0, 0x00000001 << user, 0x00000000);
 }
 
 static int
@@ -54,20 +55,21 @@ gf119_disp_pioc_init(struct nv50_disp_chan *chan)
 	struct nv50_disp *disp = chan->root->disp;
 	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
 	struct nvkm_device *device = subdev->device;
-	int chid = chan->chid;
+	int ctrl = chan->chid.ctrl;
+	int user = chan->chid.user;
 
 	/* enable error reporting */
-	nvkm_mask(device, 0x6100a0, 0x00000001 << chid, 0x00000001 << chid);
+	nvkm_mask(device, 0x6100a0, 0x00000001 << user, 0x00000001 << user);
 
 	/* activate channel */
-	nvkm_wr32(device, 0x610490 + (chid * 0x10), 0x00000001);
+	nvkm_wr32(device, 0x610490 + (ctrl * 0x10), 0x00000001);
 	if (nvkm_msec(device, 2000,
-		u32 tmp = nvkm_rd32(device, 0x610490 + (chid * 0x10));
+		u32 tmp = nvkm_rd32(device, 0x610490 + (ctrl * 0x10));
 		if ((tmp & 0x00030000) == 0x00010000)
 			break;
 	) < 0) {
-		nvkm_error(subdev, "ch %d init: %08x\n", chid,
-			   nvkm_rd32(device, 0x610490 + (chid * 0x10)));
+		nvkm_error(subdev, "ch %d init: %08x\n", user,
+			   nvkm_rd32(device, 0x610490 + (ctrl * 0x10)));
 		return -EBUSY;
 	}
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/piocnv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/piocnv50.c
index 9d2618d..0211e0e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/piocnv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/piocnv50.c
@@ -32,15 +32,16 @@ nv50_disp_pioc_fini(struct nv50_disp_chan *chan)
 	struct nv50_disp *disp = chan->root->disp;
 	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
 	struct nvkm_device *device = subdev->device;
-	int chid = chan->chid;
+	int ctrl = chan->chid.ctrl;
+	int user = chan->chid.user;
 
-	nvkm_mask(device, 0x610200 + (chid * 0x10), 0x00000001, 0x00000000);
+	nvkm_mask(device, 0x610200 + (ctrl * 0x10), 0x00000001, 0x00000000);
 	if (nvkm_msec(device, 2000,
-		if (!(nvkm_rd32(device, 0x610200 + (chid * 0x10)) & 0x00030000))
+		if (!(nvkm_rd32(device, 0x610200 + (ctrl * 0x10)) & 0x00030000))
 			break;
 	) < 0) {
-		nvkm_error(subdev, "ch %d timeout: %08x\n", chid,
-			   nvkm_rd32(device, 0x610200 + (chid * 0x10)));
+		nvkm_error(subdev, "ch %d timeout: %08x\n", user,
+			   nvkm_rd32(device, 0x610200 + (ctrl * 0x10)));
 	}
 }
 
@@ -50,26 +51,27 @@ nv50_disp_pioc_init(struct nv50_disp_chan *chan)
 	struct nv50_disp *disp = chan->root->disp;
 	struct nvkm_subdev *subdev = &disp->base.engine.subdev;
 	struct nvkm_device *device = subdev->device;
-	int chid = chan->chid;
+	int ctrl = chan->chid.ctrl;
+	int user = chan->chid.user;
 
-	nvkm_wr32(device, 0x610200 + (chid * 0x10), 0x00002000);
+	nvkm_wr32(device, 0x610200 + (ctrl * 0x10), 0x00002000);
 	if (nvkm_msec(device, 2000,
-		if (!(nvkm_rd32(device, 0x610200 + (chid * 0x10)) & 0x00030000))
+		if (!(nvkm_rd32(device, 0x610200 + (ctrl * 0x10)) & 0x00030000))
 			break;
 	) < 0) {
-		nvkm_error(subdev, "ch %d timeout0: %08x\n", chid,
-			   nvkm_rd32(device, 0x610200 + (chid * 0x10)));
+		nvkm_error(subdev, "ch %d timeout0: %08x\n", user,
+			   nvkm_rd32(device, 0x610200 + (ctrl * 0x10)));
 		return -EBUSY;
 	}
 
-	nvkm_wr32(device, 0x610200 + (chid * 0x10), 0x00000001);
+	nvkm_wr32(device, 0x610200 + (ctrl * 0x10), 0x00000001);
 	if (nvkm_msec(device, 2000,
-		u32 tmp = nvkm_rd32(device, 0x610200 + (chid * 0x10));
+		u32 tmp = nvkm_rd32(device, 0x610200 + (ctrl * 0x10));
 		if ((tmp & 0x00030000) == 0x00010000)
 			break;
 	) < 0) {
-		nvkm_error(subdev, "ch %d timeout1: %08x\n", chid,
-			   nvkm_rd32(device, 0x610200 + (chid * 0x10)));
+		nvkm_error(subdev, "ch %d timeout1: %08x\n", user,
+			   nvkm_rd32(device, 0x610200 + (ctrl * 0x10)));
 		return -EBUSY;
 	}
 
-- 
2.1.0


From 0042afe117c69e41511e22c15994e853a856e10f Mon Sep 17 00:00:00 2001
From: Ben Skeggs <bskeggs@redhat.com>
Date: Fri, 17 Mar 2017 00:48:30 +0000
Subject: [PATCH 072/112] drm/nouveau/disp/nv50-: specify ctrl/user separately
 when constructing classes

[ Upstream commit 2a32b9b1866a2ee9f01fbf2a48d99012f0120739 ]

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c  | 11 ++++++-----
 drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.h  | 15 +++++++++------
 drivers/gpu/drm/nouveau/nvkm/engine/disp/cursg84.c   |  2 +-
 drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgf119.c |  2 +-
 drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgk104.c |  2 +-
 drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgt215.c |  2 +-
 drivers/gpu/drm/nouveau/nvkm/engine/disp/cursnv50.c  |  6 +++---
 drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacnv50.c  |  2 +-
 drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmg84.c   |  2 +-
 drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmgf119.c |  2 +-
 drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmgk104.c |  2 +-
 drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmgt215.c |  2 +-
 drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmnv50.c  |  6 +++---
 drivers/gpu/drm/nouveau/nvkm/engine/disp/rootnv50.c  |  4 ++--
 14 files changed, 32 insertions(+), 28 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c
index 376f2c6..9d90d8b 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c
@@ -263,7 +263,7 @@ nv50_disp_chan = {
 int
 nv50_disp_chan_ctor(const struct nv50_disp_chan_func *func,
 		    const struct nv50_disp_chan_mthd *mthd,
-		    struct nv50_disp_root *root, int chid, int head,
+		    struct nv50_disp_root *root, int ctrl, int user, int head,
 		    const struct nvkm_oclass *oclass,
 		    struct nv50_disp_chan *chan)
 {
@@ -273,8 +273,8 @@ nv50_disp_chan_ctor(const struct nv50_disp_chan_func *func,
 	chan->func = func;
 	chan->mthd = mthd;
 	chan->root = root;
-	chan->chid.ctrl = chid;
-	chan->chid.user = chid;
+	chan->chid.ctrl = ctrl;
+	chan->chid.user = user;
 	chan->head = head;
 
 	if (disp->chan[chan->chid.user]) {
@@ -288,7 +288,7 @@ nv50_disp_chan_ctor(const struct nv50_disp_chan_func *func,
 int
 nv50_disp_chan_new_(const struct nv50_disp_chan_func *func,
 		    const struct nv50_disp_chan_mthd *mthd,
-		    struct nv50_disp_root *root, int chid, int head,
+		    struct nv50_disp_root *root, int ctrl, int user, int head,
 		    const struct nvkm_oclass *oclass,
 		    struct nvkm_object **pobject)
 {
@@ -298,5 +298,6 @@ nv50_disp_chan_new_(const struct nv50_disp_chan_func *func,
 		return -ENOMEM;
 	*pobject = &chan->object;
 
-	return nv50_disp_chan_ctor(func, mthd, root, chid, head, oclass, chan);
+	return nv50_disp_chan_ctor(func, mthd, root, ctrl, user,
+				   head, oclass, chan);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.h
index 7b5a2ea..737b38f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.h
@@ -29,11 +29,11 @@ struct nv50_disp_chan_func {
 
 int nv50_disp_chan_ctor(const struct nv50_disp_chan_func *,
 			const struct nv50_disp_chan_mthd *,
-			struct nv50_disp_root *, int chid, int head,
+			struct nv50_disp_root *, int ctrl, int user, int head,
 			const struct nvkm_oclass *, struct nv50_disp_chan *);
 int nv50_disp_chan_new_(const struct nv50_disp_chan_func *,
 			const struct nv50_disp_chan_mthd *,
-			struct nv50_disp_root *, int chid, int head,
+			struct nv50_disp_root *, int ctrl, int user, int head,
 			const struct nvkm_oclass *, struct nvkm_object **);
 
 extern const struct nv50_disp_chan_func nv50_disp_pioc_func;
@@ -94,13 +94,16 @@ extern const struct nv50_disp_chan_mthd gk104_disp_ovly_chan_mthd;
 struct nv50_disp_pioc_oclass {
 	int (*ctor)(const struct nv50_disp_chan_func *,
 		    const struct nv50_disp_chan_mthd *,
-		    struct nv50_disp_root *, int chid,
+		    struct nv50_disp_root *, int ctrl, int user,
 		    const struct nvkm_oclass *, void *data, u32 size,
 		    struct nvkm_object **);
 	struct nvkm_sclass base;
 	const struct nv50_disp_chan_func *func;
 	const struct nv50_disp_chan_mthd *mthd;
-	int chid;
+	struct {
+		int ctrl;
+		int user;
+	} chid;
 };
 
 extern const struct nv50_disp_pioc_oclass nv50_disp_oimm_oclass;
@@ -123,12 +126,12 @@ extern const struct nv50_disp_pioc_oclass gp102_disp_curs_oclass;
 
 int nv50_disp_curs_new(const struct nv50_disp_chan_func *,
 		       const struct nv50_disp_chan_mthd *,
-		       struct nv50_disp_root *, int chid,
+		       struct nv50_disp_root *, int ctrl, int user,
 		       const struct nvkm_oclass *, void *data, u32 size,
 		       struct nvkm_object **);
 int nv50_disp_oimm_new(const struct nv50_disp_chan_func *,
 		       const struct nv50_disp_chan_mthd *,
-		       struct nv50_disp_root *, int chid,
+		       struct nv50_disp_root *, int ctrl, int user,
 		       const struct nvkm_oclass *, void *data, u32 size,
 		       struct nvkm_object **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursg84.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursg84.c
index dd99fc7..fa781b5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursg84.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursg84.c
@@ -33,5 +33,5 @@ g84_disp_curs_oclass = {
 	.base.maxver = 0,
 	.ctor = nv50_disp_curs_new,
 	.func = &nv50_disp_pioc_func,
-	.chid = 7,
+	.chid = { 7, 7 },
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgf119.c
index 2a1574e..2be6fb0 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgf119.c
@@ -33,5 +33,5 @@ gf119_disp_curs_oclass = {
 	.base.maxver = 0,
 	.ctor = nv50_disp_curs_new,
 	.func = &gf119_disp_pioc_func,
-	.chid = 13,
+	.chid = { 13, 13 },
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgk104.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgk104.c
index 28e8f06..2a99db4 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgk104.c
@@ -33,5 +33,5 @@ gk104_disp_curs_oclass = {
 	.base.maxver = 0,
 	.ctor = nv50_disp_curs_new,
 	.func = &gf119_disp_pioc_func,
-	.chid = 13,
+	.chid = { 13, 13 },
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgt215.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgt215.c
index d8a4b9c..00a7f35 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgt215.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursgt215.c
@@ -33,5 +33,5 @@ gt215_disp_curs_oclass = {
 	.base.maxver = 0,
 	.ctor = nv50_disp_curs_new,
 	.func = &nv50_disp_pioc_func,
-	.chid = 7,
+	.chid = { 7, 7 },
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursnv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursnv50.c
index 8b13204..82ff82d 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursnv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/cursnv50.c
@@ -33,7 +33,7 @@
 int
 nv50_disp_curs_new(const struct nv50_disp_chan_func *func,
 		   const struct nv50_disp_chan_mthd *mthd,
-		   struct nv50_disp_root *root, int chid,
+		   struct nv50_disp_root *root, int ctrl, int user,
 		   const struct nvkm_oclass *oclass, void *data, u32 size,
 		   struct nvkm_object **pobject)
 {
@@ -54,7 +54,7 @@ nv50_disp_curs_new(const struct nv50_disp_chan_func *func,
 	} else
 		return ret;
 
-	return nv50_disp_chan_new_(func, mthd, root, chid + head,
+	return nv50_disp_chan_new_(func, mthd, root, ctrl + head, user + head,
 				   head, oclass, pobject);
 }
 
@@ -65,5 +65,5 @@ nv50_disp_curs_oclass = {
 	.base.maxver = 0,
 	.ctor = nv50_disp_curs_new,
 	.func = &nv50_disp_pioc_func,
-	.chid = 7,
+	.chid = { 7, 7 },
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacnv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacnv50.c
index cfba994..0a1381a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacnv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dmacnv50.c
@@ -149,7 +149,7 @@ nv50_disp_dmac_new_(const struct nv50_disp_dmac_func *func,
 	chan->func = func;
 
 	ret = nv50_disp_chan_ctor(&nv50_disp_dmac_func_, mthd, root,
-				  chid, head, oclass, &chan->base);
+				  chid, chid, head, oclass, &chan->base);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmg84.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmg84.c
index 54a4ae8..5ad5d0f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmg84.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmg84.c
@@ -33,5 +33,5 @@ g84_disp_oimm_oclass = {
 	.base.maxver = 0,
 	.ctor = nv50_disp_oimm_new,
 	.func = &nv50_disp_pioc_func,
-	.chid = 5,
+	.chid = { 5, 5 },
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmgf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmgf119.c
index c658db5..1f9fd34 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmgf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmgf119.c
@@ -33,5 +33,5 @@ gf119_disp_oimm_oclass = {
 	.base.maxver = 0,
 	.ctor = nv50_disp_oimm_new,
 	.func = &gf119_disp_pioc_func,
-	.chid = 9,
+	.chid = { 9, 9 },
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmgk104.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmgk104.c
index b1fde8c..0c09fe8 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmgk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmgk104.c
@@ -33,5 +33,5 @@ gk104_disp_oimm_oclass = {
 	.base.maxver = 0,
 	.ctor = nv50_disp_oimm_new,
 	.func = &gf119_disp_pioc_func,
-	.chid = 9,
+	.chid = { 9, 9 },
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmgt215.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmgt215.c
index f4e7eb3..1281db2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmgt215.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmgt215.c
@@ -33,5 +33,5 @@ gt215_disp_oimm_oclass = {
 	.base.maxver = 0,
 	.ctor = nv50_disp_oimm_new,
 	.func = &nv50_disp_pioc_func,
-	.chid = 5,
+	.chid = { 5, 5 },
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmnv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmnv50.c
index 3940b9c..07540f3 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmnv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/oimmnv50.c
@@ -33,7 +33,7 @@
 int
 nv50_disp_oimm_new(const struct nv50_disp_chan_func *func,
 		   const struct nv50_disp_chan_mthd *mthd,
-		   struct nv50_disp_root *root, int chid,
+		   struct nv50_disp_root *root, int ctrl, int user,
 		   const struct nvkm_oclass *oclass, void *data, u32 size,
 		   struct nvkm_object **pobject)
 {
@@ -54,7 +54,7 @@ nv50_disp_oimm_new(const struct nv50_disp_chan_func *func,
 	} else
 		return ret;
 
-	return nv50_disp_chan_new_(func, mthd, root, chid + head,
+	return nv50_disp_chan_new_(func, mthd, root, ctrl + head, user + head,
 				   head, oclass, pobject);
 }
 
@@ -65,5 +65,5 @@ nv50_disp_oimm_oclass = {
 	.base.maxver = 0,
 	.ctor = nv50_disp_oimm_new,
 	.func = &nv50_disp_pioc_func,
-	.chid = 5,
+	.chid = { 5, 5 },
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootnv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootnv50.c
index 2f9cecd..05c829a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootnv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootnv50.c
@@ -207,8 +207,8 @@ nv50_disp_root_pioc_new_(const struct nvkm_oclass *oclass,
 {
 	const struct nv50_disp_pioc_oclass *sclass = oclass->priv;
 	struct nv50_disp_root *root = nv50_disp_root(oclass->parent);
-	return sclass->ctor(sclass->func, sclass->mthd, root, sclass->chid,
-			    oclass, data, size, pobject);
+	return sclass->ctor(sclass->func, sclass->mthd, root, sclass->chid.ctrl,
+			    sclass->chid.user, oclass, data, size, pobject);
 }
 
 static int
-- 
2.1.0


From 61a153d06ef4ce17bf2a200dc6e7247dc3b56a57 Mon Sep 17 00:00:00 2001
From: Mauricio Faria de Oliveira <mauricfo@linux.vnet.ibm.com>
Date: Fri, 17 Mar 2017 00:48:30 +0000
Subject: [PATCH 073/112] block: allow WRITE_SAME commands with the SG_IO ioctl

[ Upstream commit 25cdb64510644f3e854d502d69c73f21c6df88a9 ]

The WRITE_SAME commands are not present in the blk_default_cmd_filter
write_ok list, and thus are failed with -EPERM when the SG_IO ioctl()
is executed without CAP_SYS_RAWIO capability (e.g., unprivileged users).
[ sg_io() -> blk_fill_sghdr_rq() > blk_verify_command() -> -EPERM ]

The problem can be reproduced with the sg_write_same command

  # sg_write_same --num 1 --xferlen 512 /dev/sda
  #

  # capsh --drop=cap_sys_rawio -- -c \
    'sg_write_same --num 1 --xferlen 512 /dev/sda'
    Write same: pass through os error: Operation not permitted
  #

For comparison, the WRITE_VERIFY command does not observe this problem,
since it is in that list:

  # capsh --drop=cap_sys_rawio -- -c \
    'sg_write_verify --num 1 --ilen 512 --lba 0 /dev/sda'
  #

So, this patch adds the WRITE_SAME commands to the list, in order
for the SG_IO ioctl to finish successfully:

  # capsh --drop=cap_sys_rawio -- -c \
    'sg_write_same --num 1 --xferlen 512 /dev/sda'
  #

That case happens to be exercised by QEMU KVM guests with 'scsi-block' devices
(qemu "-device scsi-block" [1], libvirt "<disk type='block' device='lun'>" [2]),
which employs the SG_IO ioctl() and runs as an unprivileged user (libvirt-qemu).

In that scenario, when a filesystem (e.g., ext4) performs its zero-out calls,
which are translated to write-same calls in the guest kernel, and then into
SG_IO ioctls to the host kernel, SCSI I/O errors may be observed in the guest:

  [...] sd 0:0:0:0: [sda] tag#0 FAILED Result: hostbyte=DID_OK driverbyte=DRIVER_SENSE
  [...] sd 0:0:0:0: [sda] tag#0 Sense Key : Aborted Command [current]
  [...] sd 0:0:0:0: [sda] tag#0 Add. Sense: I/O process terminated
  [...] sd 0:0:0:0: [sda] tag#0 CDB: Write Same(10) 41 00 01 04 e0 78 00 00 08 00
  [...] blk_update_request: I/O error, dev sda, sector 17096824

Links:
[1] http://git.qemu.org/?p=qemu.git;a=commit;h=336a6915bc7089fb20fea4ba99972ad9a97c5f52
[2] https://libvirt.org/formatdomain.html#elementsDisks (see 'disk' -> 'device')

Signed-off-by: Mauricio Faria de Oliveira <mauricfo@linux.vnet.ibm.com>
Signed-off-by: Brahadambal Srinivasan <latha@linux.vnet.ibm.com>
Reported-by: Manjunatha H R <manjuhr1@in.ibm.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 block/scsi_ioctl.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 0774799..c6fee74 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -182,6 +182,9 @@ static void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter)
 	__set_bit(WRITE_16, filter->write_ok);
 	__set_bit(WRITE_LONG, filter->write_ok);
 	__set_bit(WRITE_LONG_2, filter->write_ok);
+	__set_bit(WRITE_SAME, filter->write_ok);
+	__set_bit(WRITE_SAME_16, filter->write_ok);
+	__set_bit(WRITE_SAME_32, filter->write_ok);
 	__set_bit(ERASE, filter->write_ok);
 	__set_bit(GPCMD_MODE_SELECT_10, filter->write_ok);
 	__set_bit(MODE_SELECT, filter->write_ok);
-- 
2.1.0


From e627116c0c35d3d42fb031683606a49ce7d63cc5 Mon Sep 17 00:00:00 2001
From: Harald Freudenberger <freude@linux.vnet.ibm.com>
Date: Fri, 17 Mar 2017 00:48:31 +0000
Subject: [PATCH 074/112] s390/zcrypt: Introduce CEX6 toleration

[ Upstream commit b3e8652bcbfa04807e44708d4d0c8cdad39c9215 ]

Signed-off-by: Harald Freudenberger <freude@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/s390/crypto/ap_bus.c | 3 +++
 drivers/s390/crypto/ap_bus.h | 1 +
 2 files changed, 4 insertions(+)

diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index ed92fb0..76b802c 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -1712,6 +1712,9 @@ static void ap_scan_bus(struct work_struct *unused)
 		ap_dev->queue_depth = queue_depth;
 		ap_dev->raw_hwtype = device_type;
 		ap_dev->device_type = device_type;
+		/* CEX6 toleration: map to CEX5 */
+		if (device_type == AP_DEVICE_TYPE_CEX6)
+			ap_dev->device_type = AP_DEVICE_TYPE_CEX5;
 		ap_dev->functions = device_functions;
 		spin_lock_init(&ap_dev->lock);
 		INIT_LIST_HEAD(&ap_dev->pendingq);
diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h
index d7fdf5c..fd66d2c 100644
--- a/drivers/s390/crypto/ap_bus.h
+++ b/drivers/s390/crypto/ap_bus.h
@@ -105,6 +105,7 @@ static inline int ap_test_bit(unsigned int *ptr, unsigned int nr)
 #define AP_DEVICE_TYPE_CEX3C	9
 #define AP_DEVICE_TYPE_CEX4	10
 #define AP_DEVICE_TYPE_CEX5	11
+#define AP_DEVICE_TYPE_CEX6	12
 
 /*
  * Known function facilities
-- 
2.1.0


From bd2de45031b9b05738c91b87c1c360471c075bbd Mon Sep 17 00:00:00 2001
From: Henrik Ingo <henrik.ingo@avoinelama.fi>
Date: Fri, 17 Mar 2017 00:48:31 +0000
Subject: [PATCH 075/112] uvcvideo: uvc_scan_fallback() for webcams with broken
 chain

[ Upstream commit e950267ab802c8558f1100eafd4087fd039ad634 ]

Some devices have invalid baSourceID references, causing uvc_scan_chain()
to fail, but if we just take the entities we can find and put them
together in the most sensible chain we can think of, turns out they do
work anyway. Note: This heuristic assumes there is a single chain.

At the time of writing, devices known to have such a broken chain are
  - Acer Integrated Camera (5986:055a)
  - Realtek rtl157a7 (0bda:57a7)

Signed-off-by: Henrik Ingo <henrik.ingo@avoinelama.fi>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@s-opensource.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/media/usb/uvc/uvc_driver.c | 118 +++++++++++++++++++++++++++++++++++--
 1 file changed, 112 insertions(+), 6 deletions(-)

diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c
index 302e284..cde43b6 100644
--- a/drivers/media/usb/uvc/uvc_driver.c
+++ b/drivers/media/usb/uvc/uvc_driver.c
@@ -1595,6 +1595,114 @@ static const char *uvc_print_chain(struct uvc_video_chain *chain)
 	return buffer;
 }
 
+static struct uvc_video_chain *uvc_alloc_chain(struct uvc_device *dev)
+{
+	struct uvc_video_chain *chain;
+
+	chain = kzalloc(sizeof(*chain), GFP_KERNEL);
+	if (chain == NULL)
+		return NULL;
+
+	INIT_LIST_HEAD(&chain->entities);
+	mutex_init(&chain->ctrl_mutex);
+	chain->dev = dev;
+	v4l2_prio_init(&chain->prio);
+
+	return chain;
+}
+
+/*
+ * Fallback heuristic for devices that don't connect units and terminals in a
+ * valid chain.
+ *
+ * Some devices have invalid baSourceID references, causing uvc_scan_chain()
+ * to fail, but if we just take the entities we can find and put them together
+ * in the most sensible chain we can think of, turns out they do work anyway.
+ * Note: This heuristic assumes there is a single chain.
+ *
+ * At the time of writing, devices known to have such a broken chain are
+ *  - Acer Integrated Camera (5986:055a)
+ *  - Realtek rtl157a7 (0bda:57a7)
+ */
+static int uvc_scan_fallback(struct uvc_device *dev)
+{
+	struct uvc_video_chain *chain;
+	struct uvc_entity *iterm = NULL;
+	struct uvc_entity *oterm = NULL;
+	struct uvc_entity *entity;
+	struct uvc_entity *prev;
+
+	/*
+	 * Start by locating the input and output terminals. We only support
+	 * devices with exactly one of each for now.
+	 */
+	list_for_each_entry(entity, &dev->entities, list) {
+		if (UVC_ENTITY_IS_ITERM(entity)) {
+			if (iterm)
+				return -EINVAL;
+			iterm = entity;
+		}
+
+		if (UVC_ENTITY_IS_OTERM(entity)) {
+			if (oterm)
+				return -EINVAL;
+			oterm = entity;
+		}
+	}
+
+	if (iterm == NULL || oterm == NULL)
+		return -EINVAL;
+
+	/* Allocate the chain and fill it. */
+	chain = uvc_alloc_chain(dev);
+	if (chain == NULL)
+		return -ENOMEM;
+
+	if (uvc_scan_chain_entity(chain, oterm) < 0)
+		goto error;
+
+	prev = oterm;
+
+	/*
+	 * Add all Processing and Extension Units with two pads. The order
+	 * doesn't matter much, use reverse list traversal to connect units in
+	 * UVC descriptor order as we build the chain from output to input. This
+	 * leads to units appearing in the order meant by the manufacturer for
+	 * the cameras known to require this heuristic.
+	 */
+	list_for_each_entry_reverse(entity, &dev->entities, list) {
+		if (entity->type != UVC_VC_PROCESSING_UNIT &&
+		    entity->type != UVC_VC_EXTENSION_UNIT)
+			continue;
+
+		if (entity->num_pads != 2)
+			continue;
+
+		if (uvc_scan_chain_entity(chain, entity) < 0)
+			goto error;
+
+		prev->baSourceID[0] = entity->id;
+		prev = entity;
+	}
+
+	if (uvc_scan_chain_entity(chain, iterm) < 0)
+		goto error;
+
+	prev->baSourceID[0] = iterm->id;
+
+	list_add_tail(&chain->list, &dev->chains);
+
+	uvc_trace(UVC_TRACE_PROBE,
+		  "Found a video chain by fallback heuristic (%s).\n",
+		  uvc_print_chain(chain));
+
+	return 0;
+
+error:
+	kfree(chain);
+	return -EINVAL;
+}
+
 /*
  * Scan the device for video chains and register video devices.
  *
@@ -1617,15 +1725,10 @@ static int uvc_scan_device(struct uvc_device *dev)
 		if (term->chain.next || term->chain.prev)
 			continue;
 
-		chain = kzalloc(sizeof(*chain), GFP_KERNEL);
+		chain = uvc_alloc_chain(dev);
 		if (chain == NULL)
 			return -ENOMEM;
 
-		INIT_LIST_HEAD(&chain->entities);
-		mutex_init(&chain->ctrl_mutex);
-		chain->dev = dev;
-		v4l2_prio_init(&chain->prio);
-
 		term->flags |= UVC_ENTITY_FLAG_DEFAULT;
 
 		if (uvc_scan_chain(chain, term) < 0) {
@@ -1639,6 +1742,9 @@ static int uvc_scan_device(struct uvc_device *dev)
 		list_add_tail(&chain->list, &dev->chains);
 	}
 
+	if (list_empty(&dev->chains))
+		uvc_scan_fallback(dev);
+
 	if (list_empty(&dev->chains)) {
 		uvc_printk(KERN_INFO, "No valid video chain found.\n");
 		return -1;
-- 
2.1.0


From bc01eb939899762eede303ffbbbfcda197316234 Mon Sep 17 00:00:00 2001
From: Vladimir Davydov <vdavydov.dev@gmail.com>
Date: Fri, 17 Mar 2017 00:48:31 +0000
Subject: [PATCH 076/112] slub: move synchronize_sched out of slab_mutex on
 shrink

[ Upstream commit 89e364db71fb5e7fc8d93228152abfa67daf35fa ]

synchronize_sched() is a heavy operation and calling it per each cache
owned by a memory cgroup being destroyed may take quite some time.  What
is worse, it's currently called under the slab_mutex, stalling all works
doing cache creation/destruction.

Actually, there isn't much point in calling synchronize_sched() for each
cache - it's enough to call it just once - after setting cpu_partial for
all caches and before shrinking them.  This way, we can also move it out
of the slab_mutex, which we have to hold for iterating over the slab
cache list.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=172991
Link: http://lkml.kernel.org/r/0a10d71ecae3db00fb4421bcd3f82bcc911f4be4.1475329751.git.vdavydov.dev@gmail.com
Signed-off-by: Vladimir Davydov <vdavydov.dev@gmail.com>
Reported-by: Doug Smythies <dsmythies@telus.net>
Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Pekka Enberg <penberg@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 mm/slab.c        |  4 ++--
 mm/slab.h        |  2 +-
 mm/slab_common.c | 27 +++++++++++++++++++++++++--
 mm/slob.c        |  2 +-
 mm/slub.c        | 19 ++-----------------
 5 files changed, 31 insertions(+), 23 deletions(-)

diff --git a/mm/slab.c b/mm/slab.c
index bd878f0..1f82d16 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -2332,7 +2332,7 @@ static int drain_freelist(struct kmem_cache *cache,
 	return nr_freed;
 }
 
-int __kmem_cache_shrink(struct kmem_cache *cachep, bool deactivate)
+int __kmem_cache_shrink(struct kmem_cache *cachep)
 {
 	int ret = 0;
 	int node;
@@ -2352,7 +2352,7 @@ int __kmem_cache_shrink(struct kmem_cache *cachep, bool deactivate)
 
 int __kmem_cache_shutdown(struct kmem_cache *cachep)
 {
-	return __kmem_cache_shrink(cachep, false);
+	return __kmem_cache_shrink(cachep);
 }
 
 void __kmem_cache_release(struct kmem_cache *cachep)
diff --git a/mm/slab.h b/mm/slab.h
index bc05fdc..ceb7d70 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -146,7 +146,7 @@ static inline unsigned long kmem_cache_flags(unsigned long object_size,
 
 int __kmem_cache_shutdown(struct kmem_cache *);
 void __kmem_cache_release(struct kmem_cache *);
-int __kmem_cache_shrink(struct kmem_cache *, bool);
+int __kmem_cache_shrink(struct kmem_cache *);
 void slab_kmem_cache_release(struct kmem_cache *);
 
 struct seq_file;
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 329b038..5d2f24f 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -573,6 +573,29 @@ void memcg_deactivate_kmem_caches(struct mem_cgroup *memcg)
 	get_online_cpus();
 	get_online_mems();
 
+#ifdef CONFIG_SLUB
+	/*
+	 * In case of SLUB, we need to disable empty slab caching to
+	 * avoid pinning the offline memory cgroup by freeable kmem
+	 * pages charged to it. SLAB doesn't need this, as it
+	 * periodically purges unused slabs.
+	 */
+	mutex_lock(&slab_mutex);
+	list_for_each_entry(s, &slab_caches, list) {
+		c = is_root_cache(s) ? cache_from_memcg_idx(s, idx) : NULL;
+		if (c) {
+			c->cpu_partial = 0;
+			c->min_partial = 0;
+		}
+	}
+	mutex_unlock(&slab_mutex);
+	/*
+	 * kmem_cache->cpu_partial is checked locklessly (see
+	 * put_cpu_partial()). Make sure the change is visible.
+	 */
+	synchronize_sched();
+#endif
+
 	mutex_lock(&slab_mutex);
 	list_for_each_entry(s, &slab_caches, list) {
 		if (!is_root_cache(s))
@@ -584,7 +607,7 @@ void memcg_deactivate_kmem_caches(struct mem_cgroup *memcg)
 		if (!c)
 			continue;
 
-		__kmem_cache_shrink(c, true);
+		__kmem_cache_shrink(c);
 		arr->entries[idx] = NULL;
 	}
 	mutex_unlock(&slab_mutex);
@@ -755,7 +778,7 @@ int kmem_cache_shrink(struct kmem_cache *cachep)
 	get_online_cpus();
 	get_online_mems();
 	kasan_cache_shrink(cachep);
-	ret = __kmem_cache_shrink(cachep, false);
+	ret = __kmem_cache_shrink(cachep);
 	put_online_mems();
 	put_online_cpus();
 	return ret;
diff --git a/mm/slob.c b/mm/slob.c
index 5ec1580..eac04d43 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -634,7 +634,7 @@ void __kmem_cache_release(struct kmem_cache *c)
 {
 }
 
-int __kmem_cache_shrink(struct kmem_cache *d, bool deactivate)
+int __kmem_cache_shrink(struct kmem_cache *d)
 {
 	return 0;
 }
diff --git a/mm/slub.c b/mm/slub.c
index 7aa0e97..58c7526 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3887,7 +3887,7 @@ EXPORT_SYMBOL(kfree);
  * being allocated from last increasing the chance that the last objects
  * are freed in them.
  */
-int __kmem_cache_shrink(struct kmem_cache *s, bool deactivate)
+int __kmem_cache_shrink(struct kmem_cache *s)
 {
 	int node;
 	int i;
@@ -3899,21 +3899,6 @@ int __kmem_cache_shrink(struct kmem_cache *s, bool deactivate)
 	unsigned long flags;
 	int ret = 0;
 
-	if (deactivate) {
-		/*
-		 * Disable empty slabs caching. Used to avoid pinning offline
-		 * memory cgroups by kmem pages that can be freed.
-		 */
-		s->cpu_partial = 0;
-		s->min_partial = 0;
-
-		/*
-		 * s->cpu_partial is checked locklessly (see put_cpu_partial),
-		 * so we have to make sure the change is visible.
-		 */
-		synchronize_sched();
-	}
-
 	flush_all(s);
 	for_each_kmem_cache_node(s, node, n) {
 		INIT_LIST_HEAD(&discard);
@@ -3970,7 +3955,7 @@ static int slab_mem_going_offline_callback(void *arg)
 
 	mutex_lock(&slab_mutex);
 	list_for_each_entry(s, &slab_caches, list)
-		__kmem_cache_shrink(s, false);
+		__kmem_cache_shrink(s);
 	mutex_unlock(&slab_mutex);
 
 	return 0;
-- 
2.1.0


From 5c19e9070df8165db7ba26c13f39848d94e2ce8a Mon Sep 17 00:00:00 2001
From: Alex Hung <alex.hung@canonical.com>
Date: Fri, 17 Mar 2017 00:48:32 +0000
Subject: [PATCH 077/112] ACPI / blacklist: add _REV quirks for Dell Precision
 5520 and 3520

[ Upstream commit 9523b9bf6dceef6b0215e90b2348cd646597f796 ]

Precision 5520 and 3520 either hang at login and during suspend or reboot.

It turns out that that adding them to acpi_rev_dmi_table[] helps to work
around those issues.

Signed-off-by: Alex Hung <alex.hung@canonical.com>
[ rjw: Changelog ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/acpi/blacklist.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/drivers/acpi/blacklist.c b/drivers/acpi/blacklist.c
index bdc67ba..4f87fd7 100644
--- a/drivers/acpi/blacklist.c
+++ b/drivers/acpi/blacklist.c
@@ -160,6 +160,22 @@ static struct dmi_system_id acpi_rev_dmi_table[] __initdata = {
 		      DMI_MATCH(DMI_PRODUCT_NAME, "XPS 13 9343"),
 		},
 	},
+	{
+	 .callback = dmi_enable_rev_override,
+	 .ident = "DELL Precision 5520",
+	 .matches = {
+		      DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		      DMI_MATCH(DMI_PRODUCT_NAME, "Precision 5520"),
+		},
+	},
+	{
+	 .callback = dmi_enable_rev_override,
+	 .ident = "DELL Precision 3520",
+	 .matches = {
+		      DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		      DMI_MATCH(DMI_PRODUCT_NAME, "Precision 3520"),
+		},
+	},
 #endif
 	{}
 };
-- 
2.1.0


From 56c28e7983a8c877e99de0152ce3f7f5eea98963 Mon Sep 17 00:00:00 2001
From: Michael Pobega <mpobega@neverware.com>
Date: Fri, 17 Mar 2017 00:48:32 +0000
Subject: [PATCH 078/112] ACPI / blacklist: Make Dell Latitude 3350 ethernet
 work

[ Upstream commit 708f5dcc21ae9b35f395865fc154b0105baf4de4 ]

The Dell Latitude 3350's ethernet card attempts to use a reserved
IRQ (18), resulting in ACPI being unable to enable the ethernet.

Adding it to acpi_rev_dmi_table[] helps to work around this problem.

Signed-off-by: Michael Pobega <mpobega@neverware.com>
[ rjw: Changelog ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/acpi/blacklist.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/acpi/blacklist.c b/drivers/acpi/blacklist.c
index 4f87fd7..4421f7c 100644
--- a/drivers/acpi/blacklist.c
+++ b/drivers/acpi/blacklist.c
@@ -176,6 +176,18 @@ static struct dmi_system_id acpi_rev_dmi_table[] __initdata = {
 		      DMI_MATCH(DMI_PRODUCT_NAME, "Precision 3520"),
 		},
 	},
+	/*
+	 * Resolves a quirk with the Dell Latitude 3350 that
+	 * causes the ethernet adapter to not function.
+	 */
+	{
+	 .callback = dmi_enable_rev_override,
+	 .ident = "DELL Latitude 3350",
+	 .matches = {
+		      DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		      DMI_MATCH(DMI_PRODUCT_NAME, "Latitude 3350"),
+		},
+	},
 #endif
 	{}
 };
-- 
2.1.0


From 4fa1c65cf040a933ee8d2d0d1c0df83361add7ab Mon Sep 17 00:00:00 2001
From: Gabriel Krisman Bertazi <krisman@linux.vnet.ibm.com>
Date: Fri, 17 Mar 2017 00:48:32 +0000
Subject: [PATCH 079/112] serial: 8250_pci: Detach low-level driver during PCI
 error recovery

[ Upstream commit f209fa03fc9d131b3108c2e4936181eabab87416 ]

During a PCI error recovery, like the ones provoked by EEH in the ppc64
platform, all IO to the device must be blocked while the recovery is
completed.  Current 8250_pci implementation only suspends the port
instead of detaching it, which doesn't prevent incoming accesses like
TIOCMGET and TIOCMSET calls from reaching the device.  Those end up
racing with the EEH recovery, crashing it.  Similar races were also
observed when opening the device and when shutting it down during
recovery.

This patch implements a more robust IO blockage for the 8250_pci
recovery by unregistering the port at the beginning of the procedure and
re-adding it afterwards.  Since the port is detached from the uart
layer, we can be sure that no request will make through to the device
during recovery.  This is similar to the solution used by the JSM serial
driver.

I thank Peter Hurley <peter@hurleysoftware.com> for valuable input on
this one over one year ago.

Signed-off-by: Gabriel Krisman Bertazi <krisman@linux.vnet.ibm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_pci.c | 23 +++++++++++++++++++----
 1 file changed, 19 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c
index 4d09bd4..6e3e636 100644
--- a/drivers/tty/serial/8250/8250_pci.c
+++ b/drivers/tty/serial/8250/8250_pci.c
@@ -52,6 +52,7 @@ struct serial_private {
 	struct pci_dev		*dev;
 	unsigned int		nr;
 	struct pci_serial_quirk	*quirk;
+	const struct pciserial_board *board;
 	int			line[0];
 };
 
@@ -3871,6 +3872,7 @@ pciserial_init_ports(struct pci_dev *dev, const struct pciserial_board *board)
 		}
 	}
 	priv->nr = i;
+	priv->board = board;
 	return priv;
 
 err_deinit:
@@ -3881,7 +3883,7 @@ pciserial_init_ports(struct pci_dev *dev, const struct pciserial_board *board)
 }
 EXPORT_SYMBOL_GPL(pciserial_init_ports);
 
-void pciserial_remove_ports(struct serial_private *priv)
+void pciserial_detach_ports(struct serial_private *priv)
 {
 	struct pci_serial_quirk *quirk;
 	int i;
@@ -3895,7 +3897,11 @@ void pciserial_remove_ports(struct serial_private *priv)
 	quirk = find_quirk(priv->dev);
 	if (quirk->exit)
 		quirk->exit(priv->dev);
+}
 
+void pciserial_remove_ports(struct serial_private *priv)
+{
+	pciserial_detach_ports(priv);
 	kfree(priv);
 }
 EXPORT_SYMBOL_GPL(pciserial_remove_ports);
@@ -5590,7 +5596,7 @@ static pci_ers_result_t serial8250_io_error_detected(struct pci_dev *dev,
 		return PCI_ERS_RESULT_DISCONNECT;
 
 	if (priv)
-		pciserial_suspend_ports(priv);
+		pciserial_detach_ports(priv);
 
 	pci_disable_device(dev);
 
@@ -5615,9 +5621,18 @@ static pci_ers_result_t serial8250_io_slot_reset(struct pci_dev *dev)
 static void serial8250_io_resume(struct pci_dev *dev)
 {
 	struct serial_private *priv = pci_get_drvdata(dev);
+	const struct pciserial_board *board;
 
-	if (priv)
-		pciserial_resume_ports(priv);
+	if (!priv)
+		return;
+
+	board = priv->board;
+	kfree(priv);
+	priv = pciserial_init_ports(dev, board);
+
+	if (!IS_ERR(priv)) {
+		pci_set_drvdata(dev, priv);
+	}
 }
 
 static const struct pci_error_handlers serial8250_err_handler = {
-- 
2.1.0


From ce7aeffe7596343fce49307f374444b199b950a1 Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@free-electrons.com>
Date: Fri, 17 Mar 2017 00:48:33 +0000
Subject: [PATCH 080/112] usb: gadget: udc: atmel: remove memory leak

[ Upstream commit 32856eea7bf75dfb99b955ada6e147f553a11366 ]

Commit bbe097f092b0 ("usb: gadget: udc: atmel: fix endpoint name")
introduced a memory leak when unbinding the driver. The endpoint names
would not be freed. Solve that by including the name as a string in struct
usba_ep so it is freed when the endpoint is.

Signed-off-by: Alexandre Belloni <alexandre.belloni@free-electrons.com>
Signed-off-by: Felipe Balbi <felipe.balbi@linux.intel.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/udc/atmel_usba_udc.c | 3 ++-
 drivers/usb/gadget/udc/atmel_usba_udc.h | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c
index 45bc997..a95b3e7 100644
--- a/drivers/usb/gadget/udc/atmel_usba_udc.c
+++ b/drivers/usb/gadget/udc/atmel_usba_udc.c
@@ -1978,7 +1978,8 @@ static struct usba_ep * atmel_udc_of_init(struct platform_device *pdev,
 			dev_err(&pdev->dev, "of_probe: name error(%d)\n", ret);
 			goto err;
 		}
-		ep->ep.name = kasprintf(GFP_KERNEL, "ep%d", ep->index);
+		sprintf(ep->name, "ep%d", ep->index);
+		ep->ep.name = ep->name;
 
 		ep->ep_regs = udc->regs + USBA_EPT_BASE(i);
 		ep->dma_regs = udc->regs + USBA_DMA_BASE(i);
diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.h b/drivers/usb/gadget/udc/atmel_usba_udc.h
index 3e1c9d5..b03b2eb 100644
--- a/drivers/usb/gadget/udc/atmel_usba_udc.h
+++ b/drivers/usb/gadget/udc/atmel_usba_udc.h
@@ -280,6 +280,7 @@ struct usba_ep {
 	void __iomem				*ep_regs;
 	void __iomem				*dma_regs;
 	void __iomem				*fifo;
+	char					name[8];
 	struct usb_ep				ep;
 	struct usba_udc				*udc;
 
-- 
2.1.0


From 7885195b9177042aea3da65c4789790f8e788aa6 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Fri, 17 Mar 2017 00:48:33 +0000
Subject: [PATCH 081/112] powerpc/mm: Fix build break when CMA=n &&
 SPAPR_TCE_IOMMU=y
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit a05ef161cdd22faccffe06f21fc8f1e249565385 ]

Currently the build breaks if CMA=n and SPAPR_TCE_IOMMU=y:

  arch/powerpc/mm/mmu_context_iommu.c: In function ‘mm_iommu_get’:
  arch/powerpc/mm/mmu_context_iommu.c:193:42: error: ‘MIGRATE_CMA’ undeclared (first use in this function)
  if (get_pageblock_migratetype(page) == MIGRATE_CMA) {
  ^~~~~~~~~~~

Fix it by using the existing is_migrate_cma_page(), which evaulates to
false when CMA=n.

Fixes: 2e5bbb5461f1 ("KVM: PPC: Book3S HV: Migrate pinned pages out of CMA")
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/powerpc/mm/mmu_context_iommu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index 104bad0..7de7124 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -184,7 +184,7 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
 		 * of the CMA zone if possible. NOTE: faulting in + migration
 		 * can be expensive. Batching can be considered later
 		 */
-		if (get_pageblock_migratetype(page) == MIGRATE_CMA) {
+		if (is_migrate_cma_page(page)) {
 			if (mm_iommu_move_page_from_cma(page))
 				goto populate;
 			if (1 != get_user_pages_fast(ua + (i << PAGE_SHIFT),
-- 
2.1.0


From f4d40cfd61ea6e99f965576d19b76b42fd371365 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@free-electrons.com>
Date: Tue, 22 Nov 2016 12:45:28 -0800
Subject: [PATCH 082/112] clk: bcm2835: Fix ->fixed_divider of pllh_aux

commit f2a46926aba1f0c33944901d2420a6a887455ddc upstream.

There is no fixed divider on pllh_aux.

Signed-off-by: Boris Brezillon <boris.brezillon@free-electrons.com>
Signed-off-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Cc: Amit Pundir <amit.pundir@linaro.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/clk/bcm/clk-bcm2835.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/clk/bcm/clk-bcm2835.c b/drivers/clk/bcm/clk-bcm2835.c
index 3bbd2a5..2acaa77 100644
--- a/drivers/clk/bcm/clk-bcm2835.c
+++ b/drivers/clk/bcm/clk-bcm2835.c
@@ -1598,7 +1598,7 @@ static const struct bcm2835_clk_desc clk_desc_array[] = {
 		.a2w_reg = A2W_PLLH_AUX,
 		.load_mask = CM_PLLH_LOADAUX,
 		.hold_mask = 0,
-		.fixed_divider = 10),
+		.fixed_divider = 1),
 	[BCM2835_PLLH_PIX]	= REGISTER_PLL_DIV(
 		.name = "pllh_pix",
 		.source_pll = "pllh",
-- 
2.1.0


From 6b3306706733cc98bf14e30ff54fa9084b76cd55 Mon Sep 17 00:00:00 2001
From: Derek Foreman <derekf@osg.samsung.com>
Date: Thu, 24 Nov 2016 12:11:55 -0600
Subject: [PATCH 083/112] drm/vc4: Fix race between page flip completion event
 and clean-up

commit 26fc78f6fef39b9d7a15def5e7e9826ff68303f4 upstream.

There was a small window where a userspace program could submit
a pageflip after receiving a pageflip completion event yet still
receive EBUSY.

Signed-off-by: Derek Foreman <derekf@osg.samsung.com>
Signed-off-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Daniel Stone <daniels@collabora.com>
Cc: Amit Pundir <amit.pundir@linaro.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/gpu/drm/vc4/vc4_crtc.c |  8 ++++++++
 drivers/gpu/drm/vc4/vc4_drv.h  |  1 +
 drivers/gpu/drm/vc4/vc4_kms.c  | 33 +++++++++++++++++++++++++--------
 3 files changed, 34 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c
index d544ff9..a062228 100644
--- a/drivers/gpu/drm/vc4/vc4_crtc.c
+++ b/drivers/gpu/drm/vc4/vc4_crtc.c
@@ -669,6 +669,14 @@ void vc4_disable_vblank(struct drm_device *dev, unsigned int crtc_id)
 	CRTC_WRITE(PV_INTEN, 0);
 }
 
+/* Must be called with the event lock held */
+bool vc4_event_pending(struct drm_crtc *crtc)
+{
+	struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc);
+
+	return !!vc4_crtc->event;
+}
+
 static void vc4_crtc_handle_page_flip(struct vc4_crtc *vc4_crtc)
 {
 	struct drm_crtc *crtc = &vc4_crtc->base;
diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h
index 7c1e4d9..cc77b8b 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.h
+++ b/drivers/gpu/drm/vc4/vc4_drv.h
@@ -440,6 +440,7 @@ int vc4_bo_stats_debugfs(struct seq_file *m, void *arg);
 extern struct platform_driver vc4_crtc_driver;
 int vc4_enable_vblank(struct drm_device *dev, unsigned int crtc_id);
 void vc4_disable_vblank(struct drm_device *dev, unsigned int crtc_id);
+bool vc4_event_pending(struct drm_crtc *crtc);
 int vc4_crtc_debugfs_regs(struct seq_file *m, void *arg);
 int vc4_crtc_get_scanoutpos(struct drm_device *dev, unsigned int crtc_id,
 			    unsigned int flags, int *vpos, int *hpos,
diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c
index c1f65c6..67af2af 100644
--- a/drivers/gpu/drm/vc4/vc4_kms.c
+++ b/drivers/gpu/drm/vc4/vc4_kms.c
@@ -119,17 +119,34 @@ static int vc4_atomic_commit(struct drm_device *dev,
 
 	/* Make sure that any outstanding modesets have finished. */
 	if (nonblock) {
-		ret = down_trylock(&vc4->async_modeset);
-		if (ret) {
+		struct drm_crtc *crtc;
+		struct drm_crtc_state *crtc_state;
+		unsigned long flags;
+		bool busy = false;
+
+		/*
+		 * If there's an undispatched event to send then we're
+		 * obviously still busy.  If there isn't, then we can
+		 * unconditionally wait for the semaphore because it
+		 * shouldn't be contended (for long).
+		 *
+		 * This is to prevent a race where queuing a new flip
+		 * from userspace immediately on receipt of an event
+		 * beats our clean-up and returns EBUSY.
+		 */
+		spin_lock_irqsave(&dev->event_lock, flags);
+		for_each_crtc_in_state(state, crtc, crtc_state, i)
+			busy |= vc4_event_pending(crtc);
+		spin_unlock_irqrestore(&dev->event_lock, flags);
+		if (busy) {
 			kfree(c);
 			return -EBUSY;
 		}
-	} else {
-		ret = down_interruptible(&vc4->async_modeset);
-		if (ret) {
-			kfree(c);
-			return ret;
-		}
+	}
+	ret = down_interruptible(&vc4->async_modeset);
+	if (ret) {
+		kfree(c);
+		return ret;
 	}
 
 	ret = drm_atomic_helper_prepare_planes(dev, state);
-- 
2.1.0


From 8ca7ef0d9af9644a65e3e22ccc1937f00caa777b Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@free-electrons.com>
Date: Fri, 2 Dec 2016 14:48:07 +0100
Subject: [PATCH 084/112] drm/vc4: Fix ->clock_select setting for the VEC
 encoder

commit ab8df60e3a3b68420d0d4477c5f07c00fbfb078b upstream.

PV_CONTROL_CLK_SELECT_VEC is actually 2 and not 0. Fix the definition and
rework the vc4_set_crtc_possible_masks() to cover the full range of the
PV_CONTROL_CLK_SELECT field.

Signed-off-by: Boris Brezillon <boris.brezillon@free-electrons.com>
Signed-off-by: Eric Anholt <eric@anholt.net>
Cc: Amit Pundir <amit.pundir@linaro.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/gpu/drm/vc4/vc4_crtc.c | 38 +++++++++++++++++++++++---------------
 drivers/gpu/drm/vc4/vc4_drv.h  |  1 +
 drivers/gpu/drm/vc4/vc4_regs.h |  3 ++-
 3 files changed, 26 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c
index a062228..7aadce1 100644
--- a/drivers/gpu/drm/vc4/vc4_crtc.c
+++ b/drivers/gpu/drm/vc4/vc4_crtc.c
@@ -83,8 +83,7 @@ struct vc4_crtc_data {
 	/* Which channel of the HVS this pixelvalve sources from. */
 	int hvs_channel;
 
-	enum vc4_encoder_type encoder0_type;
-	enum vc4_encoder_type encoder1_type;
+	enum vc4_encoder_type encoder_types[4];
 };
 
 #define CRTC_WRITE(offset, val) writel(val, vc4_crtc->regs + (offset))
@@ -867,20 +866,26 @@ static const struct drm_crtc_helper_funcs vc4_crtc_helper_funcs = {
 
 static const struct vc4_crtc_data pv0_data = {
 	.hvs_channel = 0,
-	.encoder0_type = VC4_ENCODER_TYPE_DSI0,
-	.encoder1_type = VC4_ENCODER_TYPE_DPI,
+	.encoder_types = {
+		[PV_CONTROL_CLK_SELECT_DSI] = VC4_ENCODER_TYPE_DSI0,
+		[PV_CONTROL_CLK_SELECT_DPI_SMI_HDMI] = VC4_ENCODER_TYPE_DPI,
+	},
 };
 
 static const struct vc4_crtc_data pv1_data = {
 	.hvs_channel = 2,
-	.encoder0_type = VC4_ENCODER_TYPE_DSI1,
-	.encoder1_type = VC4_ENCODER_TYPE_SMI,
+	.encoder_types = {
+		[PV_CONTROL_CLK_SELECT_DSI] = VC4_ENCODER_TYPE_DSI1,
+		[PV_CONTROL_CLK_SELECT_DPI_SMI_HDMI] = VC4_ENCODER_TYPE_SMI,
+	},
 };
 
 static const struct vc4_crtc_data pv2_data = {
 	.hvs_channel = 1,
-	.encoder0_type = VC4_ENCODER_TYPE_VEC,
-	.encoder1_type = VC4_ENCODER_TYPE_HDMI,
+	.encoder_types = {
+		[PV_CONTROL_CLK_SELECT_DPI_SMI_HDMI] = VC4_ENCODER_TYPE_HDMI,
+		[PV_CONTROL_CLK_SELECT_VEC] = VC4_ENCODER_TYPE_VEC,
+	},
 };
 
 static const struct of_device_id vc4_crtc_dt_match[] = {
@@ -894,17 +899,20 @@ static void vc4_set_crtc_possible_masks(struct drm_device *drm,
 					struct drm_crtc *crtc)
 {
 	struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc);
+	const struct vc4_crtc_data *crtc_data = vc4_crtc->data;
+	const enum vc4_encoder_type *encoder_types = crtc_data->encoder_types;
 	struct drm_encoder *encoder;
 
 	drm_for_each_encoder(encoder, drm) {
 		struct vc4_encoder *vc4_encoder = to_vc4_encoder(encoder);
-
-		if (vc4_encoder->type == vc4_crtc->data->encoder0_type) {
-			vc4_encoder->clock_select = 0;
-			encoder->possible_crtcs |= drm_crtc_mask(crtc);
-		} else if (vc4_encoder->type == vc4_crtc->data->encoder1_type) {
-			vc4_encoder->clock_select = 1;
-			encoder->possible_crtcs |= drm_crtc_mask(crtc);
+		int i;
+
+		for (i = 0; i < ARRAY_SIZE(crtc_data->encoder_types); i++) {
+			if (vc4_encoder->type == encoder_types[i]) {
+				vc4_encoder->clock_select = i;
+				encoder->possible_crtcs |= drm_crtc_mask(crtc);
+				break;
+			}
 		}
 	}
 }
diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h
index cc77b8b..50a55ef 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.h
+++ b/drivers/gpu/drm/vc4/vc4_drv.h
@@ -194,6 +194,7 @@ to_vc4_plane(struct drm_plane *plane)
 }
 
 enum vc4_encoder_type {
+	VC4_ENCODER_TYPE_NONE,
 	VC4_ENCODER_TYPE_HDMI,
 	VC4_ENCODER_TYPE_VEC,
 	VC4_ENCODER_TYPE_DSI0,
diff --git a/drivers/gpu/drm/vc4/vc4_regs.h b/drivers/gpu/drm/vc4/vc4_regs.h
index 1aa44c2..39f6886 100644
--- a/drivers/gpu/drm/vc4/vc4_regs.h
+++ b/drivers/gpu/drm/vc4/vc4_regs.h
@@ -177,8 +177,9 @@
 # define PV_CONTROL_WAIT_HSTART			BIT(12)
 # define PV_CONTROL_PIXEL_REP_MASK		VC4_MASK(5, 4)
 # define PV_CONTROL_PIXEL_REP_SHIFT		4
-# define PV_CONTROL_CLK_SELECT_DSI_VEC		0
+# define PV_CONTROL_CLK_SELECT_DSI		0
 # define PV_CONTROL_CLK_SELECT_DPI_SMI_HDMI	1
+# define PV_CONTROL_CLK_SELECT_VEC		2
 # define PV_CONTROL_CLK_SELECT_MASK		VC4_MASK(3, 2)
 # define PV_CONTROL_CLK_SELECT_SHIFT		2
 # define PV_CONTROL_FIFO_CLR			BIT(1)
-- 
2.1.0


From 61e79860b4bc6259a9685a107a6b34352d6dc7bd Mon Sep 17 00:00:00 2001
From: Marc Zyngier <marc.zyngier@arm.com>
Date: Fri, 17 Feb 2017 14:32:18 +0000
Subject: [PATCH 085/112] arm64: KVM: VHE: Clear HCR_TGE when invalidating
 guest TLBs

commit 68925176296a8b995e503349200e256674bfe5ac upstream.

When invalidating guest TLBs, special care must be taken to
actually shoot the guest TLBs and not the host ones if we're
running on a VHE system.  This is controlled by the HCR_EL2.TGE
bit, which we forget to clear before invalidating TLBs.

Address the issue by introducing two wrappers (__tlb_switch_to_guest
and __tlb_switch_to_host) that take care of both the VTTBR_EL2
and HCR_EL2.TGE switching.

Reported-by: Tomasz Nowicki <tnowicki@caviumnetworks.com>
Tested-by: Tomasz Nowicki <tnowicki@caviumnetworks.com>
Reviewed-by: Christoffer Dall <cdall@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/arm64/kvm/hyp/tlb.c | 64 +++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 55 insertions(+), 9 deletions(-)

diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c
index 88e2f2b..55889d0 100644
--- a/arch/arm64/kvm/hyp/tlb.c
+++ b/arch/arm64/kvm/hyp/tlb.c
@@ -17,14 +17,62 @@
 
 #include <asm/kvm_hyp.h>
 
+static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm)
+{
+	u64 val;
+
+	/*
+	 * With VHE enabled, we have HCR_EL2.{E2H,TGE} = {1,1}, and
+	 * most TLB operations target EL2/EL0. In order to affect the
+	 * guest TLBs (EL1/EL0), we need to change one of these two
+	 * bits. Changing E2H is impossible (goodbye TTBR1_EL2), so
+	 * let's flip TGE before executing the TLB operation.
+	 */
+	write_sysreg(kvm->arch.vttbr, vttbr_el2);
+	val = read_sysreg(hcr_el2);
+	val &= ~HCR_TGE;
+	write_sysreg(val, hcr_el2);
+	isb();
+}
+
+static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm)
+{
+	write_sysreg(kvm->arch.vttbr, vttbr_el2);
+	isb();
+}
+
+static hyp_alternate_select(__tlb_switch_to_guest,
+			    __tlb_switch_to_guest_nvhe,
+			    __tlb_switch_to_guest_vhe,
+			    ARM64_HAS_VIRT_HOST_EXTN);
+
+static void __hyp_text __tlb_switch_to_host_vhe(struct kvm *kvm)
+{
+	/*
+	 * We're done with the TLB operation, let's restore the host's
+	 * view of HCR_EL2.
+	 */
+	write_sysreg(0, vttbr_el2);
+	write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
+}
+
+static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm)
+{
+	write_sysreg(0, vttbr_el2);
+}
+
+static hyp_alternate_select(__tlb_switch_to_host,
+			    __tlb_switch_to_host_nvhe,
+			    __tlb_switch_to_host_vhe,
+			    ARM64_HAS_VIRT_HOST_EXTN);
+
 void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 {
 	dsb(ishst);
 
 	/* Switch to requested VMID */
 	kvm = kern_hyp_va(kvm);
-	write_sysreg(kvm->arch.vttbr, vttbr_el2);
-	isb();
+	__tlb_switch_to_guest()(kvm);
 
 	/*
 	 * We could do so much better if we had the VA as well.
@@ -45,7 +93,7 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 	dsb(ish);
 	isb();
 
-	write_sysreg(0, vttbr_el2);
+	__tlb_switch_to_host()(kvm);
 }
 
 void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm)
@@ -54,14 +102,13 @@ void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm)
 
 	/* Switch to requested VMID */
 	kvm = kern_hyp_va(kvm);
-	write_sysreg(kvm->arch.vttbr, vttbr_el2);
-	isb();
+	__tlb_switch_to_guest()(kvm);
 
 	asm volatile("tlbi vmalls12e1is" : : );
 	dsb(ish);
 	isb();
 
-	write_sysreg(0, vttbr_el2);
+	__tlb_switch_to_host()(kvm);
 }
 
 void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
@@ -69,14 +116,13 @@ void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
 	struct kvm *kvm = kern_hyp_va(kern_hyp_va(vcpu)->kvm);
 
 	/* Switch to requested VMID */
-	write_sysreg(kvm->arch.vttbr, vttbr_el2);
-	isb();
+	__tlb_switch_to_guest()(kvm);
 
 	asm volatile("tlbi vmalle1" : : );
 	dsb(nsh);
 	isb();
 
-	write_sysreg(0, vttbr_el2);
+	__tlb_switch_to_host()(kvm);
 }
 
 void __hyp_text __kvm_flush_vm_context(void)
-- 
2.1.0


From 095635be809ade2429c844d09e8391330fa9bca4 Mon Sep 17 00:00:00 2001
From: Shanker Donthineni <shankerd@codeaurora.org>
Date: Tue, 7 Mar 2017 08:20:38 -0600
Subject: [PATCH 086/112] irqchip/gicv3-its: Add workaround for QDF2400 ITS
 erratum 0065

commit 90922a2d03d84de36bf8a9979d62580102f31a92 upstream.

On Qualcomm Datacenter Technologies QDF2400 SoCs, the ITS hardware
implementation uses 16Bytes for Interrupt Translation Entry (ITE),
but reports an incorrect value of 8Bytes in GITS_TYPER.ITTE_size.

It might cause kernel memory corruption depending on the number
of MSI(x) that are configured and the amount of memory that has
been allocated for ITEs in its_create_device().

This patch fixes the potential memory corruption by setting the
correct ITE size to 16Bytes.

Cc: stable@vger.kernel.org
Signed-off-by: Shanker Donthineni <shankerd@codeaurora.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/arm64/silicon-errata.txt | 44 ++++++++++++++++++----------------
 arch/arm64/Kconfig                     | 10 ++++++++
 drivers/irqchip/irq-gic-v3-its.c       | 16 +++++++++++++
 3 files changed, 49 insertions(+), 21 deletions(-)

diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt
index 405da11..d11af52 100644
--- a/Documentation/arm64/silicon-errata.txt
+++ b/Documentation/arm64/silicon-errata.txt
@@ -42,24 +42,26 @@ file acts as a registry of software workarounds in the Linux Kernel and
 will be updated when new workarounds are committed and backported to
 stable kernels.
 
-| Implementor    | Component       | Erratum ID      | Kconfig                 |
-+----------------+-----------------+-----------------+-------------------------+
-| ARM            | Cortex-A53      | #826319         | ARM64_ERRATUM_826319    |
-| ARM            | Cortex-A53      | #827319         | ARM64_ERRATUM_827319    |
-| ARM            | Cortex-A53      | #824069         | ARM64_ERRATUM_824069    |
-| ARM            | Cortex-A53      | #819472         | ARM64_ERRATUM_819472    |
-| ARM            | Cortex-A53      | #845719         | ARM64_ERRATUM_845719    |
-| ARM            | Cortex-A53      | #843419         | ARM64_ERRATUM_843419    |
-| ARM            | Cortex-A57      | #832075         | ARM64_ERRATUM_832075    |
-| ARM            | Cortex-A57      | #852523         | N/A                     |
-| ARM            | Cortex-A57      | #834220         | ARM64_ERRATUM_834220    |
-| ARM            | Cortex-A72      | #853709         | N/A                     |
-| ARM            | MMU-500         | #841119,#826419 | N/A                     |
-|                |                 |                 |                         |
-| Cavium         | ThunderX ITS    | #22375, #24313  | CAVIUM_ERRATUM_22375    |
-| Cavium         | ThunderX ITS    | #23144          | CAVIUM_ERRATUM_23144    |
-| Cavium         | ThunderX GICv3  | #23154          | CAVIUM_ERRATUM_23154    |
-| Cavium         | ThunderX Core   | #27456          | CAVIUM_ERRATUM_27456    |
-| Cavium         | ThunderX SMMUv2 | #27704          | N/A		       |
-|                |                 |                 |                         |
-| Freescale/NXP  | LS2080A/LS1043A | A-008585        | FSL_ERRATUM_A008585     |
+| Implementor    | Component       | Erratum ID      | Kconfig                     |
++----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Cortex-A53      | #826319         | ARM64_ERRATUM_826319        |
+| ARM            | Cortex-A53      | #827319         | ARM64_ERRATUM_827319        |
+| ARM            | Cortex-A53      | #824069         | ARM64_ERRATUM_824069        |
+| ARM            | Cortex-A53      | #819472         | ARM64_ERRATUM_819472        |
+| ARM            | Cortex-A53      | #845719         | ARM64_ERRATUM_845719        |
+| ARM            | Cortex-A53      | #843419         | ARM64_ERRATUM_843419        |
+| ARM            | Cortex-A57      | #832075         | ARM64_ERRATUM_832075        |
+| ARM            | Cortex-A57      | #852523         | N/A                         |
+| ARM            | Cortex-A57      | #834220         | ARM64_ERRATUM_834220        |
+| ARM            | Cortex-A72      | #853709         | N/A                         |
+| ARM            | MMU-500         | #841119,#826419 | N/A                         |
+|                |                 |                 |                             |
+| Cavium         | ThunderX ITS    | #22375, #24313  | CAVIUM_ERRATUM_22375        |
+| Cavium         | ThunderX ITS    | #23144          | CAVIUM_ERRATUM_23144        |
+| Cavium         | ThunderX GICv3  | #23154          | CAVIUM_ERRATUM_23154        |
+| Cavium         | ThunderX Core   | #27456          | CAVIUM_ERRATUM_27456        |
+| Cavium         | ThunderX SMMUv2 | #27704          | N/A                         |
+|                |                 |                 |                             |
+| Freescale/NXP  | LS2080A/LS1043A | A-008585        | FSL_ERRATUM_A008585         |
+|                |                 |                 |                             |
+| Qualcomm Tech. | QDF2400 ITS     | E0065           | QCOM_QDF2400_ERRATUM_0065   |
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 969ef88..cf57a77 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -474,6 +474,16 @@ config CAVIUM_ERRATUM_27456
 
 	  If unsure, say Y.
 
+config QCOM_QDF2400_ERRATUM_0065
+	bool "QDF2400 E0065: Incorrect GITS_TYPER.ITT_Entry_size"
+	default y
+	help
+	  On Qualcomm Datacenter Technologies QDF2400 SoC, ITS hardware reports
+	  ITE size incorrectly. The GITS_TYPER.ITT_Entry_size field should have
+	  been indicated as 16Bytes (0xf), not 8Bytes (0x7).
+
+	  If unsure, say Y.
+
 endmenu
 
 
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index c5dee30..acb9d25 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -1598,6 +1598,14 @@ static void __maybe_unused its_enable_quirk_cavium_23144(void *data)
 	its->flags |= ITS_FLAGS_WORKAROUND_CAVIUM_23144;
 }
 
+static void __maybe_unused its_enable_quirk_qdf2400_e0065(void *data)
+{
+	struct its_node *its = data;
+
+	/* On QDF2400, the size of the ITE is 16Bytes */
+	its->ite_size = 16;
+}
+
 static const struct gic_quirk its_quirks[] = {
 #ifdef CONFIG_CAVIUM_ERRATUM_22375
 	{
@@ -1615,6 +1623,14 @@ static const struct gic_quirk its_quirks[] = {
 		.init	= its_enable_quirk_cavium_23144,
 	},
 #endif
+#ifdef CONFIG_QCOM_QDF2400_ERRATUM_0065
+	{
+		.desc	= "ITS: QDF2400 erratum 0065",
+		.iidr	= 0x00001070, /* QDF2400 ITS rev 1.x */
+		.mask	= 0xffffffff,
+		.init	= its_enable_quirk_qdf2400_e0065,
+	},
+#endif
 	{
 	}
 };
-- 
2.1.0


From 5ec98e6ffdce5eb5dbe3593df2aa824d04d70842 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 13 Mar 2017 15:57:12 +0100
Subject: [PATCH 087/112] x86/tsc: Fix ART for TSC_KNOWN_FREQ

commit 44fee88cea43d3c2cac962e0439cb10a3cabff6d upstream.

Subhransu reported that convert_art_to_tsc() isn't working for him.

The ART to TSC relation is only set up for systems which use the refined
TSC calibration. Systems with known TSC frequency (available via CPUID 15)
are not using the refined calibration and therefor the ART to TSC relation
is never established.

Add the setup to the known frequency init path which skips ART
calibration. The init code needs to be duplicated as for systems which use
refined calibration the ART setup must be delayed until calibration has
been done.

The problem has been there since the ART support was introdduced, but only
detected now because Subhransu tested the first time on hardware which has
TSC frequency enumerated via CPUID 15.

Note for stable: The conditional has changed from TSC_RELIABLE to
     	 	 TSC_KNOWN_FREQUENCY.

[ tglx: Rewrote changelog and identified the proper 'Fixes' commit ]

Fixes: f9677e0f8308 ("x86/tsc: Always Running Timer (ART) correlated clocksource")
Reported-by: "Prusty, Subhransu S" <subhransu.s.prusty@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org
Cc: christopher.s.hall@intel.com
Cc: kevin.b.stanton@intel.com
Cc: john.stultz@linaro.org
Cc: akataria@vmware.com
Link: http://lkml.kernel.org/r/20170313145712.GI3312@twins.programming.kicks-ass.net
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/x86/kernel/tsc.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 46b2f41..eea88fe 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -1287,6 +1287,8 @@ static int __init init_tsc_clocksource(void)
 	 * exporting a reliable TSC.
 	 */
 	if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) {
+		if (boot_cpu_has(X86_FEATURE_ART))
+			art_related_clocksource = &clocksource_tsc;
 		clocksource_register_khz(&clocksource_tsc, tsc_khz);
 		return 0;
 	}
-- 
2.1.0


From 24ba2842a49da3338581b42a5618088d2a0b0730 Mon Sep 17 00:00:00 2001
From: Andrey Ryabinin <aryabinin@virtuozzo.com>
Date: Mon, 13 Mar 2017 19:33:37 +0300
Subject: [PATCH 088/112] x86/kasan: Fix boot with KASAN=y and
 PROFILE_ANNOTATED_BRANCHES=y

commit be3606ff739d1c1be36389f8737c577ad87e1f57 upstream.

The kernel doesn't boot with both PROFILE_ANNOTATED_BRANCHES=y and KASAN=y
options selected. With branch profiling enabled we end up calling
ftrace_likely_update() before kasan_early_init(). ftrace_likely_update() is
built with KASAN instrumentation, so calling it before kasan has been
initialized leads to crash.

Use DISABLE_BRANCH_PROFILING define to make sure that we don't call
ftrace_likely_update() from early code before kasan_early_init().

Fixes: ef7f0d6a6ca8 ("x86_64: add KASan support")
Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: kasan-dev@googlegroups.com
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: lkp@01.org
Cc: Dmitry Vyukov <dvyukov@google.com>
Link: http://lkml.kernel.org/r/20170313163337.1704-1-aryabinin@virtuozzo.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/x86/kernel/head64.c    | 1 +
 arch/x86/mm/kasan_init_64.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 54a2372..b5785c1 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -4,6 +4,7 @@
  *  Copyright (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE
  */
 
+#define DISABLE_BRANCH_PROFILING
 #include <linux/init.h>
 #include <linux/linkage.h>
 #include <linux/types.h>
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index 0493c17..333362f 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -1,3 +1,4 @@
+#define DISABLE_BRANCH_PROFILING
 #define pr_fmt(fmt) "kasan: " fmt
 #include <linux/bootmem.h>
 #include <linux/kasan.h>
-- 
2.1.0


From 9f9115b67aa5821e1d5490d94c1ad87d0396f7b6 Mon Sep 17 00:00:00 2001
From: Andy Lutomirski <luto@kernel.org>
Date: Thu, 16 Mar 2017 12:59:39 -0700
Subject: [PATCH 089/112] x86/perf: Fix CR4.PCE propagation to use active_mm
 instead of mm

commit 5dc855d44c2ad960a86f593c60461f1ae1566b6d upstream.

If one thread mmaps a perf event while another thread in the same mm
is in some context where active_mm != mm (which can happen in the
scheduler, for example), refresh_pce() would write the wrong value
to CR4.PCE.  This broke some PAPI tests.

Reported-and-tested-by: Vince Weaver <vincent.weaver@maine.edu>
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Borislav Petkov <bpetkov@suse.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 7911d3f7af14 ("perf/x86: Only allow rdpmc if a perf_event is mapped")
Link: http://lkml.kernel.org/r/0c5b38a76ea50e405f9abe07a13dfaef87c173a1.1489694270.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/x86/events/core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 7fe88bb..38623e2 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2096,8 +2096,8 @@ static int x86_pmu_event_init(struct perf_event *event)
 
 static void refresh_pce(void *ignored)
 {
-	if (current->mm)
-		load_mm_cr4(current->mm);
+	if (current->active_mm)
+		load_mm_cr4(current->active_mm);
 }
 
 static void x86_pmu_event_mapped(struct perf_event *event)
-- 
2.1.0


From 6244ffc5a1221e593a937c7ad3c03a9ce691a8df Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Sat, 4 Mar 2017 10:27:18 +0100
Subject: [PATCH 090/112] futex: Fix potential use-after-free in
 FUTEX_REQUEUE_PI

commit c236c8e95a3d395b0494e7108f0d41cf36ec107c upstream.

While working on the futex code, I stumbled over this potential
use-after-free scenario. Dmitry triggered it later with syzkaller.

pi_mutex is a pointer into pi_state, which we drop the reference on in
unqueue_me_pi(). So any access to that pointer after that is bad.

Since other sites already do rt_mutex_unlock() with hb->lock held, see
for example futex_lock_pi(), simply move the unlock before
unqueue_me_pi().

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Darren Hart <dvhart@linux.intel.com>
Cc: juri.lelli@arm.com
Cc: bigeasy@linutronix.de
Cc: xlpang@redhat.com
Cc: rostedt@goodmis.org
Cc: mathieu.desnoyers@efficios.com
Cc: jdesfossez@efficios.com
Cc: dvhart@infradead.org
Cc: bristot@redhat.com
Link: http://lkml.kernel.org/r/20170304093558.801744246@infradead.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 kernel/futex.c | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/kernel/futex.c b/kernel/futex.c
index 38b68c2..aa45c4e 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -2813,7 +2813,6 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 {
 	struct hrtimer_sleeper timeout, *to = NULL;
 	struct rt_mutex_waiter rt_waiter;
-	struct rt_mutex *pi_mutex = NULL;
 	struct futex_hash_bucket *hb;
 	union futex_key key2 = FUTEX_KEY_INIT;
 	struct futex_q q = futex_q_init;
@@ -2905,6 +2904,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 			spin_unlock(q.lock_ptr);
 		}
 	} else {
+		struct rt_mutex *pi_mutex;
+
 		/*
 		 * We have been woken up by futex_unlock_pi(), a timeout, or a
 		 * signal.  futex_unlock_pi() will not destroy the lock_ptr nor
@@ -2928,18 +2929,19 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 		if (res)
 			ret = (res < 0) ? res : 0;
 
+		/*
+		 * If fixup_pi_state_owner() faulted and was unable to handle
+		 * the fault, unlock the rt_mutex and return the fault to
+		 * userspace.
+		 */
+		if (ret && rt_mutex_owner(pi_mutex) == current)
+			rt_mutex_unlock(pi_mutex);
+
 		/* Unqueue and drop the lock. */
 		unqueue_me_pi(&q);
 	}
 
-	/*
-	 * If fixup_pi_state_owner() faulted and was unable to handle the
-	 * fault, unlock the rt_mutex and return the fault to userspace.
-	 */
-	if (ret == -EFAULT) {
-		if (pi_mutex && rt_mutex_owner(pi_mutex) == current)
-			rt_mutex_unlock(pi_mutex);
-	} else if (ret == -EINTR) {
+	if (ret == -EINTR) {
 		/*
 		 * We've already been requeued, but cannot restart by calling
 		 * futex_lock_pi() directly. We could restart this syscall, but
-- 
2.1.0


From 1522181f4bc14a61c72981439fcbe9a87496f3cf Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Sat, 4 Mar 2017 10:27:19 +0100
Subject: [PATCH 091/112] futex: Add missing error handling to FUTEX_REQUEUE_PI

commit 9bbb25afeb182502ca4f2c4f3f88af0681b34cae upstream.

Thomas spotted that fixup_pi_state_owner() can return errors and we
fail to unlock the rt_mutex in that case.

Reported-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Darren Hart <dvhart@linux.intel.com>
Cc: juri.lelli@arm.com
Cc: bigeasy@linutronix.de
Cc: xlpang@redhat.com
Cc: rostedt@goodmis.org
Cc: mathieu.desnoyers@efficios.com
Cc: jdesfossez@efficios.com
Cc: dvhart@infradead.org
Cc: bristot@redhat.com
Link: http://lkml.kernel.org/r/20170304093558.867401760@infradead.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 kernel/futex.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/kernel/futex.c b/kernel/futex.c
index aa45c4e..4c6b6e6 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -2896,6 +2896,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 		if (q.pi_state && (q.pi_state->owner != current)) {
 			spin_lock(q.lock_ptr);
 			ret = fixup_pi_state_owner(uaddr2, &q, current);
+			if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current)
+				rt_mutex_unlock(&q.pi_state->pi_mutex);
 			/*
 			 * Drop the reference to the pi state which
 			 * the requeue_pi() code acquired for us.
-- 
2.1.0


From c40609652267440ae6f800303ea1f3be17d357e2 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <niklas.cassel@axis.com>
Date: Sat, 25 Feb 2017 01:17:53 +0100
Subject: [PATCH 092/112] locking/rwsem: Fix down_write_killable() for
 CONFIG_RWSEM_GENERIC_SPINLOCK=y

commit 17fcbd590d0c3e35bd9646e2215f86586378bc42 upstream.

We hang if SIGKILL has been sent, but the task is stuck in down_read()
(after do_exit()), even though no task is doing down_write() on the
rwsem in question:

  INFO: task libupnp:21868 blocked for more than 120 seconds.
  libupnp         D    0 21868      1 0x08100008
  ...
  Call Trace:
  __schedule()
  schedule()
  __down_read()
  do_exit()
  do_group_exit()
  __wake_up_parent()

This bug has already been fixed for CONFIG_RWSEM_XCHGADD_ALGORITHM=y in
the following commit:

 04cafed7fc19 ("locking/rwsem: Fix down_write_killable()")

... however, this bug also exists for CONFIG_RWSEM_GENERIC_SPINLOCK=y.

Signed-off-by: Niklas Cassel <niklas.cassel@axis.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: <mhocko@suse.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Niklas Cassel <niklass@axis.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: d47996082f52 ("locking/rwsem: Introduce basis for down_write_killable()")
Link: http://lkml.kernel.org/r/1487981873-12649-1-git-send-email-niklass@axis.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 kernel/locking/rwsem-spinlock.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c
index 1591f6b..2bef4ab 100644
--- a/kernel/locking/rwsem-spinlock.c
+++ b/kernel/locking/rwsem-spinlock.c
@@ -216,10 +216,8 @@ int __sched __down_write_common(struct rw_semaphore *sem, int state)
 		 */
 		if (sem->count == 0)
 			break;
-		if (signal_pending_state(state, current)) {
-			ret = -EINTR;
-			goto out;
-		}
+		if (signal_pending_state(state, current))
+			goto out_nolock;
 		set_task_state(tsk, state);
 		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 		schedule();
@@ -227,12 +225,19 @@ int __sched __down_write_common(struct rw_semaphore *sem, int state)
 	}
 	/* got the lock */
 	sem->count = -1;
-out:
 	list_del(&waiter.list);
 
 	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 
 	return ret;
+
+out_nolock:
+	list_del(&waiter.list);
+	if (!list_empty(&sem->wait_list))
+		__rwsem_do_wake(sem, 1);
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+
+	return -EINTR;
 }
 
 void __sched __down_write(struct rw_semaphore *sem)
-- 
2.1.0


From ecdc5b12d7a01707b5b3f334cdf47f01e50d2ce3 Mon Sep 17 00:00:00 2001
From: Daniel Axtens <dja@axtens.net>
Date: Fri, 3 Mar 2017 17:56:55 +1100
Subject: [PATCH 093/112] crypto: powerpc - Fix initialisation of crc32c
 context

commit aa2be9b3d6d2d699e9ca7cbfc00867c80e5da213 upstream.

Turning on crypto self-tests on a POWER8 shows:

    alg: hash: Test 1 failed for crc32c-vpmsum
    00000000: ff ff ff ff

Comparing the code with the Intel CRC32c implementation on which
ours is based shows that we are doing an init with 0, not ~0
as CRC32c requires.

This probably wasn't caught because btrfs does its own weird
open-coded initialisation.

Initialise our internal context to ~0 on init.

This makes the self-tests pass, and btrfs continues to work.

Fixes: 6dd7a82cc54e ("crypto: powerpc - Add POWER8 optimised crc32c")
Cc: Anton Blanchard <anton@samba.org>
Signed-off-by: Daniel Axtens <dja@axtens.net>
Acked-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/powerpc/crypto/crc32c-vpmsum_glue.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/crypto/crc32c-vpmsum_glue.c b/arch/powerpc/crypto/crc32c-vpmsum_glue.c
index 9fa046d..4119945 100644
--- a/arch/powerpc/crypto/crc32c-vpmsum_glue.c
+++ b/arch/powerpc/crypto/crc32c-vpmsum_glue.c
@@ -52,7 +52,7 @@ static int crc32c_vpmsum_cra_init(struct crypto_tfm *tfm)
 {
 	u32 *key = crypto_tfm_ctx(tfm);
 
-	*key = 0;
+	*key = ~0;
 
 	return 0;
 }
-- 
2.1.0


From c3825da143fc419e2639e602f62d793ed0de4657 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Wed, 22 Mar 2017 12:44:07 +0100
Subject: [PATCH 094/112] Linux 4.9.17

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index 4e0f962..004f90a 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 9
-SUBLEVEL = 16
+SUBLEVEL = 17
 EXTRAVERSION =
 NAME = Roaring Lionus
 
-- 
2.1.0


From e5ae0e88159a2b6d27ac43690a6b31d88748f5f7 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Wed, 15 Mar 2017 18:10:47 +0200
Subject: [PATCH 095/112] net/openvswitch: Set the ipv6 source tunnel key
 address attribute correctly

[ Upstream commit 3d20f1f7bd575d147ffa75621fa560eea0aec690 ]

When dealing with ipv6 source tunnel key address attribute
(OVS_TUNNEL_KEY_ATTR_IPV6_SRC) we are wrongly setting the tunnel
dst ip, fix that.

Fixes: 6b26ba3a7d95 ('openvswitch: netlink attributes for IPv6 tunneling')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reported-by: Paul Blakey <paulb@mellanox.com>
Acked-by: Jiri Benc <jbenc@redhat.com>
Acked-by: Joe Stringer <joe@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/flow_netlink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index ae25ded..677d7cc 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -588,7 +588,7 @@ static int ip_tun_from_nlattr(const struct nlattr *attr,
 			ipv4 = true;
 			break;
 		case OVS_TUNNEL_KEY_ATTR_IPV6_SRC:
-			SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.dst,
+			SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.src,
 					nla_get_in6_addr(a), is_mask);
 			ipv6 = true;
 			break;
-- 
2.1.0


From aa56be0e5d1e26b4d8d4c38a26d521f305b1164f Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 15 Mar 2017 12:57:21 -0700
Subject: [PATCH 096/112] net: bcmgenet: Do not suspend PHY if Wake-on-LAN is
 enabled

[ Upstream commit 5371bbf4b295eea334ed453efa286afa2c3ccff3 ]

Suspending the PHY would be putting it in a low power state where it
may no longer allow us to do Wake-on-LAN.

Fixes: cc013fb48898 ("net: bcmgenet: correctly suspend and resume PHY device")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index a4e60e5..0975af2 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -3402,7 +3402,8 @@ static int bcmgenet_suspend(struct device *d)
 
 	bcmgenet_netif_stop(dev);
 
-	phy_suspend(priv->phydev);
+	if (!device_may_wakeup(d))
+		phy_suspend(priv->phydev);
 
 	netif_device_detach(dev);
 
@@ -3499,7 +3500,8 @@ static int bcmgenet_resume(struct device *d)
 
 	netif_device_attach(dev);
 
-	phy_resume(priv->phydev);
+	if (!device_may_wakeup(d))
+		phy_resume(priv->phydev);
 
 	if (priv->eee.eee_enabled)
 		bcmgenet_eee_enable_set(dev, true);
-- 
2.1.0


From b866d039dbcd9ab896c647a8bc2c423587ffd6fe Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 15 Mar 2017 13:21:28 -0700
Subject: [PATCH 097/112] net: properly release sk_frag.page

[ Upstream commit 22a0e18eac7a9e986fec76c60fa4a2926d1291e2 ]

I mistakenly added the code to release sk->sk_frag in
sk_common_release() instead of sk_destruct()

TCP sockets using sk->sk_allocation == GFP_ATOMIC do no call
sk_common_release() at close time, thus leaking one (order-3) page.

iSCSI is using such sockets.

Fixes: 5640f7685831 ("net: use a per task frag allocator")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index bc6543f..47809e9 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1437,6 +1437,11 @@ static void __sk_destruct(struct rcu_head *head)
 		pr_debug("%s: optmem leakage (%d bytes) detected\n",
 			 __func__, atomic_read(&sk->sk_omem_alloc));
 
+	if (sk->sk_frag.page) {
+		put_page(sk->sk_frag.page);
+		sk->sk_frag.page = NULL;
+	}
+
 	if (sk->sk_peer_cred)
 		put_cred(sk->sk_peer_cred);
 	put_pid(sk->sk_peer_pid);
@@ -2738,11 +2743,6 @@ void sk_common_release(struct sock *sk)
 
 	sk_refcnt_debug_release(sk);
 
-	if (sk->sk_frag.page) {
-		put_page(sk->sk_frag.page);
-		sk->sk_frag.page = NULL;
-	}
-
 	sock_put(sk);
 }
 EXPORT_SYMBOL(sk_common_release);
-- 
2.1.0


From 0562031233c4a386b1e6ee058c67612b569db94d Mon Sep 17 00:00:00 2001
From: "Lendacky, Thomas" <Thomas.Lendacky@amd.com>
Date: Wed, 15 Mar 2017 15:11:23 -0500
Subject: [PATCH 098/112] amd-xgbe: Fix jumbo MTU processing on newer hardware

[ Upstream commit 622c36f143fc9566ba49d7cec994c2da1182d9e2 ]

Newer hardware does not provide a cumulative payload length when multiple
descriptors are needed to handle the data. Once the MTU increases beyond
the size that can be handled by a single descriptor, the SKB does not get
built properly by the driver.

The driver will now calculate the size of the data buffers used by the
hardware.  The first buffer of the first descriptor is for packet headers
or packet headers and data when the headers can't be split. Subsequent
descriptors in a multi-descriptor chain will not use the first buffer. The
second buffer is used by all the descriptors in the chain for payload data.
Based on whether the driver is processing the first, intermediate, or last
descriptor it can calculate the buffer usage and build the SKB properly.

Tested and verified on both old and new hardware.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe-common.h |   6 +-
 drivers/net/ethernet/amd/xgbe/xgbe-dev.c    |  20 +++---
 drivers/net/ethernet/amd/xgbe/xgbe-drv.c    | 102 +++++++++++++++++-----------
 3 files changed, 78 insertions(+), 50 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
index bbef959..1592e1c 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
@@ -917,8 +917,8 @@
 #define RX_PACKET_ATTRIBUTES_CSUM_DONE_WIDTH	1
 #define RX_PACKET_ATTRIBUTES_VLAN_CTAG_INDEX	1
 #define RX_PACKET_ATTRIBUTES_VLAN_CTAG_WIDTH	1
-#define RX_PACKET_ATTRIBUTES_INCOMPLETE_INDEX	2
-#define RX_PACKET_ATTRIBUTES_INCOMPLETE_WIDTH	1
+#define RX_PACKET_ATTRIBUTES_LAST_INDEX		2
+#define RX_PACKET_ATTRIBUTES_LAST_WIDTH		1
 #define RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_INDEX	3
 #define RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_WIDTH	1
 #define RX_PACKET_ATTRIBUTES_CONTEXT_INDEX	4
@@ -927,6 +927,8 @@
 #define RX_PACKET_ATTRIBUTES_RX_TSTAMP_WIDTH	1
 #define RX_PACKET_ATTRIBUTES_RSS_HASH_INDEX	6
 #define RX_PACKET_ATTRIBUTES_RSS_HASH_WIDTH	1
+#define RX_PACKET_ATTRIBUTES_FIRST_INDEX	7
+#define RX_PACKET_ATTRIBUTES_FIRST_WIDTH	1
 
 #define RX_NORMAL_DESC0_OVT_INDEX		0
 #define RX_NORMAL_DESC0_OVT_WIDTH		16
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
index 1babcc1..ca106d4 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
@@ -1721,10 +1721,15 @@ static int xgbe_dev_read(struct xgbe_channel *channel)
 
 	/* Get the header length */
 	if (XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, FD)) {
+		XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
+			       FIRST, 1);
 		rdata->rx.hdr_len = XGMAC_GET_BITS_LE(rdesc->desc2,
 						      RX_NORMAL_DESC2, HL);
 		if (rdata->rx.hdr_len)
 			pdata->ext_stats.rx_split_header_packets++;
+	} else {
+		XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
+			       FIRST, 0);
 	}
 
 	/* Get the RSS hash */
@@ -1747,19 +1752,16 @@ static int xgbe_dev_read(struct xgbe_channel *channel)
 		}
 	}
 
-	/* Get the packet length */
-	rdata->rx.len = XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, PL);
-
-	if (!XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, LD)) {
-		/* Not all the data has been transferred for this packet */
-		XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
-			       INCOMPLETE, 1);
+	/* Not all the data has been transferred for this packet */
+	if (!XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, LD))
 		return 0;
-	}
 
 	/* This is the last of the data for this packet */
 	XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
-		       INCOMPLETE, 0);
+		       LAST, 1);
+
+	/* Get the packet length */
+	rdata->rx.len = XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, PL);
 
 	/* Set checksum done indicator as appropriate */
 	if (netdev->features & NETIF_F_RXCSUM)
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 7f9216d..0f0f3014 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -1752,13 +1752,12 @@ static struct sk_buff *xgbe_create_skb(struct xgbe_prv_data *pdata,
 {
 	struct sk_buff *skb;
 	u8 *packet;
-	unsigned int copy_len;
 
 	skb = napi_alloc_skb(napi, rdata->rx.hdr.dma_len);
 	if (!skb)
 		return NULL;
 
-	/* Start with the header buffer which may contain just the header
+	/* Pull in the header buffer which may contain just the header
 	 * or the header plus data
 	 */
 	dma_sync_single_range_for_cpu(pdata->dev, rdata->rx.hdr.dma_base,
@@ -1767,30 +1766,49 @@ static struct sk_buff *xgbe_create_skb(struct xgbe_prv_data *pdata,
 
 	packet = page_address(rdata->rx.hdr.pa.pages) +
 		 rdata->rx.hdr.pa.pages_offset;
-	copy_len = (rdata->rx.hdr_len) ? rdata->rx.hdr_len : len;
-	copy_len = min(rdata->rx.hdr.dma_len, copy_len);
-	skb_copy_to_linear_data(skb, packet, copy_len);
-	skb_put(skb, copy_len);
-
-	len -= copy_len;
-	if (len) {
-		/* Add the remaining data as a frag */
-		dma_sync_single_range_for_cpu(pdata->dev,
-					      rdata->rx.buf.dma_base,
-					      rdata->rx.buf.dma_off,
-					      rdata->rx.buf.dma_len,
-					      DMA_FROM_DEVICE);
-
-		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
-				rdata->rx.buf.pa.pages,
-				rdata->rx.buf.pa.pages_offset,
-				len, rdata->rx.buf.dma_len);
-		rdata->rx.buf.pa.pages = NULL;
-	}
+	skb_copy_to_linear_data(skb, packet, len);
+	skb_put(skb, len);
 
 	return skb;
 }
 
+static unsigned int xgbe_rx_buf1_len(struct xgbe_ring_data *rdata,
+				     struct xgbe_packet_data *packet)
+{
+	/* Always zero if not the first descriptor */
+	if (!XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, FIRST))
+		return 0;
+
+	/* First descriptor with split header, return header length */
+	if (rdata->rx.hdr_len)
+		return rdata->rx.hdr_len;
+
+	/* First descriptor but not the last descriptor and no split header,
+	 * so the full buffer was used
+	 */
+	if (!XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, LAST))
+		return rdata->rx.hdr.dma_len;
+
+	/* First descriptor and last descriptor and no split header, so
+	 * calculate how much of the buffer was used
+	 */
+	return min_t(unsigned int, rdata->rx.hdr.dma_len, rdata->rx.len);
+}
+
+static unsigned int xgbe_rx_buf2_len(struct xgbe_ring_data *rdata,
+				     struct xgbe_packet_data *packet,
+				     unsigned int len)
+{
+	/* Always the full buffer if not the last descriptor */
+	if (!XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, LAST))
+		return rdata->rx.buf.dma_len;
+
+	/* Last descriptor so calculate how much of the buffer was used
+	 * for the last bit of data
+	 */
+	return rdata->rx.len - len;
+}
+
 static int xgbe_tx_poll(struct xgbe_channel *channel)
 {
 	struct xgbe_prv_data *pdata = channel->pdata;
@@ -1873,8 +1891,8 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
 	struct napi_struct *napi;
 	struct sk_buff *skb;
 	struct skb_shared_hwtstamps *hwtstamps;
-	unsigned int incomplete, error, context_next, context;
-	unsigned int len, rdesc_len, max_len;
+	unsigned int last, error, context_next, context;
+	unsigned int len, buf1_len, buf2_len, max_len;
 	unsigned int received = 0;
 	int packet_count = 0;
 
@@ -1884,7 +1902,7 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
 	if (!ring)
 		return 0;
 
-	incomplete = 0;
+	last = 0;
 	context_next = 0;
 
 	napi = (pdata->per_channel_irq) ? &channel->napi : &pdata->napi;
@@ -1918,9 +1936,8 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
 		received++;
 		ring->cur++;
 
-		incomplete = XGMAC_GET_BITS(packet->attributes,
-					    RX_PACKET_ATTRIBUTES,
-					    INCOMPLETE);
+		last = XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
+				      LAST);
 		context_next = XGMAC_GET_BITS(packet->attributes,
 					      RX_PACKET_ATTRIBUTES,
 					      CONTEXT_NEXT);
@@ -1929,7 +1946,7 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
 					 CONTEXT);
 
 		/* Earlier error, just drain the remaining data */
-		if ((incomplete || context_next) && error)
+		if ((!last || context_next) && error)
 			goto read_again;
 
 		if (error || packet->errors) {
@@ -1941,16 +1958,22 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
 		}
 
 		if (!context) {
-			/* Length is cumulative, get this descriptor's length */
-			rdesc_len = rdata->rx.len - len;
-			len += rdesc_len;
+			/* Get the data length in the descriptor buffers */
+			buf1_len = xgbe_rx_buf1_len(rdata, packet);
+			len += buf1_len;
+			buf2_len = xgbe_rx_buf2_len(rdata, packet, len);
+			len += buf2_len;
 
-			if (rdesc_len && !skb) {
+			if (!skb) {
 				skb = xgbe_create_skb(pdata, napi, rdata,
-						      rdesc_len);
-				if (!skb)
+						      buf1_len);
+				if (!skb) {
 					error = 1;
-			} else if (rdesc_len) {
+					goto skip_data;
+				}
+			}
+
+			if (buf2_len) {
 				dma_sync_single_range_for_cpu(pdata->dev,
 							rdata->rx.buf.dma_base,
 							rdata->rx.buf.dma_off,
@@ -1960,13 +1983,14 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
 				skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
 						rdata->rx.buf.pa.pages,
 						rdata->rx.buf.pa.pages_offset,
-						rdesc_len,
+						buf2_len,
 						rdata->rx.buf.dma_len);
 				rdata->rx.buf.pa.pages = NULL;
 			}
 		}
 
-		if (incomplete || context_next)
+skip_data:
+		if (!last || context_next)
 			goto read_again;
 
 		if (!skb)
@@ -2024,7 +2048,7 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
 	}
 
 	/* Check if we need to save state before leaving */
-	if (received && (incomplete || context_next)) {
+	if (received && (!last || context_next)) {
 		rdata = XGBE_GET_DESC_DATA(ring, ring->cur);
 		rdata->state_saved = 1;
 		rdata->state.skb = skb;
-- 
2.1.0


From cfc6abd09f9d4f49d8c85508b8e4627a92707cb8 Mon Sep 17 00:00:00 2001
From: Kris Murphy <kriskend@linux.vnet.ibm.com>
Date: Thu, 16 Mar 2017 10:51:28 -0500
Subject: [PATCH 099/112] openvswitch: Add missing case OVS_TUNNEL_KEY_ATTR_PAD

[ Upstream commit 8f3dbfd79ed9ef9770305a7cc4e13dfd31ad2cd0 ]

Added a case for OVS_TUNNEL_KEY_ATTR_PAD to the switch statement
in ip_tun_from_nlattr in order to prevent the default case
returning an error.

Fixes: b46f6ded906e ("libnl: nla_put_be64(): align on a 64-bit area")
Signed-off-by: Kris Murphy <kriskend@linux.vnet.ibm.com>
Acked-by: Joe Stringer <joe@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/flow_netlink.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 677d7cc..0792541 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -649,6 +649,8 @@ static int ip_tun_from_nlattr(const struct nlattr *attr,
 			tun_flags |= TUNNEL_VXLAN_OPT;
 			opts_type = type;
 			break;
+		case OVS_TUNNEL_KEY_ATTR_PAD:
+			break;
 		default:
 			OVS_NLERR(log, "Unknown IP tunnel attribute %d",
 				  type);
-- 
2.1.0


From 09098344a4ac49c9b25f90d53579adb07caa3970 Mon Sep 17 00:00:00 2001
From: Andrey Ulanov <andreyu@google.com>
Date: Tue, 14 Mar 2017 20:16:42 -0700
Subject: [PATCH 100/112] net: unix: properly re-increment inflight counter of
 GC discarded candidates

[ Upstream commit 7df9c24625b9981779afb8fcdbe2bb4765e61147 ]

Dmitry has reported that a BUG_ON() condition in unix_notinflight()
may be triggered by a simple code that forwards unix socket in an
SCM_RIGHTS message.
That is caused by incorrect unix socket GC implementation in unix_gc().

The GC first collects list of candidates, then (a) decrements their
"children's" inflight counter, (b) checks which inflight counters are
now 0, and then (c) increments all inflight counters back.
(a) and (c) are done by calling scan_children() with inc_inflight or
dec_inflight as the second argument.

Commit 6209344f5a37 ("net: unix: fix inflight counting bug in garbage
collector") changed scan_children() such that it no longer considers
sockets that do not have UNIX_GC_CANDIDATE flag. It also added a block
of code that that unsets this flag _before_ invoking
scan_children(, dec_iflight, ). This may lead to incorrect inflight
counters for some sockets.

This change fixes this bug by changing order of operations:
UNIX_GC_CANDIDATE is now unset only after all inflight counters are
restored to the original state.

  kernel BUG at net/unix/garbage.c:149!
  RIP: 0010:[<ffffffff8717ebf4>]  [<ffffffff8717ebf4>]
  unix_notinflight+0x3b4/0x490 net/unix/garbage.c:149
  Call Trace:
   [<ffffffff8716cfbf>] unix_detach_fds.isra.19+0xff/0x170 net/unix/af_unix.c:1487
   [<ffffffff8716f6a9>] unix_destruct_scm+0xf9/0x210 net/unix/af_unix.c:1496
   [<ffffffff86a90a01>] skb_release_head_state+0x101/0x200 net/core/skbuff.c:655
   [<ffffffff86a9808a>] skb_release_all+0x1a/0x60 net/core/skbuff.c:668
   [<ffffffff86a980ea>] __kfree_skb+0x1a/0x30 net/core/skbuff.c:684
   [<ffffffff86a98284>] kfree_skb+0x184/0x570 net/core/skbuff.c:705
   [<ffffffff871789d5>] unix_release_sock+0x5b5/0xbd0 net/unix/af_unix.c:559
   [<ffffffff87179039>] unix_release+0x49/0x90 net/unix/af_unix.c:836
   [<ffffffff86a694b2>] sock_release+0x92/0x1f0 net/socket.c:570
   [<ffffffff86a6962b>] sock_close+0x1b/0x20 net/socket.c:1017
   [<ffffffff81a76b8e>] __fput+0x34e/0x910 fs/file_table.c:208
   [<ffffffff81a771da>] ____fput+0x1a/0x20 fs/file_table.c:244
   [<ffffffff81483ab0>] task_work_run+0x1a0/0x280 kernel/task_work.c:116
   [<     inline     >] exit_task_work include/linux/task_work.h:21
   [<ffffffff8141287a>] do_exit+0x183a/0x2640 kernel/exit.c:828
   [<ffffffff8141383e>] do_group_exit+0x14e/0x420 kernel/exit.c:931
   [<ffffffff814429d3>] get_signal+0x663/0x1880 kernel/signal.c:2307
   [<ffffffff81239b45>] do_signal+0xc5/0x2190 arch/x86/kernel/signal.c:807
   [<ffffffff8100666a>] exit_to_usermode_loop+0x1ea/0x2d0
  arch/x86/entry/common.c:156
   [<     inline     >] prepare_exit_to_usermode arch/x86/entry/common.c:190
   [<ffffffff81009693>] syscall_return_slowpath+0x4d3/0x570
  arch/x86/entry/common.c:259
   [<ffffffff881478e6>] entry_SYSCALL_64_fastpath+0xc4/0xc6

Link: https://lkml.org/lkml/2017/3/6/252
Signed-off-by: Andrey Ulanov <andreyu@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Fixes: 6209344 ("net: unix: fix inflight counting bug in garbage collector")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/garbage.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 6a0d485..c36757e 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -146,6 +146,7 @@ void unix_notinflight(struct user_struct *user, struct file *fp)
 	if (s) {
 		struct unix_sock *u = unix_sk(s);
 
+		BUG_ON(!atomic_long_read(&u->inflight));
 		BUG_ON(list_empty(&u->link));
 
 		if (atomic_long_dec_and_test(&u->inflight))
@@ -341,6 +342,14 @@ void unix_gc(void)
 	}
 	list_del(&cursor);
 
+	/* Now gc_candidates contains only garbage.  Restore original
+	 * inflight counters for these as well, and remove the skbuffs
+	 * which are creating the cycle(s).
+	 */
+	skb_queue_head_init(&hitlist);
+	list_for_each_entry(u, &gc_candidates, link)
+		scan_children(&u->sk, inc_inflight, &hitlist);
+
 	/* not_cycle_list contains those sockets which do not make up a
 	 * cycle.  Restore these to the inflight list.
 	 */
@@ -350,14 +359,6 @@ void unix_gc(void)
 		list_move_tail(&u->link, &gc_inflight_list);
 	}
 
-	/* Now gc_candidates contains only garbage.  Restore original
-	 * inflight counters for these as well, and remove the skbuffs
-	 * which are creating the cycle(s).
-	 */
-	skb_queue_head_init(&hitlist);
-	list_for_each_entry(u, &gc_candidates, link)
-	scan_children(&u->sk, inc_inflight, &hitlist);
-
 	spin_unlock(&unix_gc_lock);
 
 	/* Here we are. Hitlist is filled. Die. */
-- 
2.1.0


From c571bf29d2f2ace7c56acc4b5a0a0ebb1ba0e17e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Fri, 17 Mar 2017 17:20:48 +0100
Subject: [PATCH 101/112] qmi_wwan: add Dell DW5811e
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 6bd845d1cf98b45c634baacb8381436dad3c2dd0 ]

This is a Dell branded Sierra Wireless EM7455. It is operating in
MBIM mode by default, but can be configured to provide two QMI/RMNET
functions.

Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 24d5272..0d519a9 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -924,6 +924,8 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x413c, 0x81a9, 8)},	/* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */
 	{QMI_FIXED_INTF(0x413c, 0x81b1, 8)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card */
 	{QMI_FIXED_INTF(0x413c, 0x81b3, 8)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */
+	{QMI_FIXED_INTF(0x413c, 0x81b6, 8)},	/* Dell Wireless 5811e */
+	{QMI_FIXED_INTF(0x413c, 0x81b6, 10)},	/* Dell Wireless 5811e */
 	{QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)},	/* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */
 	{QMI_FIXED_INTF(0x22de, 0x9061, 3)},	/* WeTelecom WPD-600N */
 	{QMI_FIXED_INTF(0x1e0e, 0x9001, 5)},	/* SIMCom 7230E */
-- 
2.1.0


From 6ae15b2ce2370bdde6a928dfb19dbe1b924b2ae3 Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Fri, 17 Mar 2017 16:07:11 -0700
Subject: [PATCH 102/112] net: vrf: Reset rt6i_idev in local dst after put

[ Upstream commit 3dc857f0e8fc22610a59cbb346ba62c6e921863f ]

The VRF driver takes a reference to the inet6_dev on the VRF device for
its rt6_local dst when handling local traffic through the VRF device as
a loopback. When the device is deleted the driver does a put on the idev
but does not reset rt6i_idev in the rt6_info struct. When the dst is
destroyed, dst_destroy calls ip6_dst_destroy which does a second put for
what is essentially the same reference causing it to be prematurely freed.
Reset rt6i_idev after the put in the vrf driver.

Fixes: b4869aa2f881e ("net: vrf: ipv6 support for local traffic to
                       local addresses")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index bc744ac..a2afb8e 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -467,8 +467,10 @@ static void vrf_rt6_release(struct net_device *dev, struct net_vrf *vrf)
 	}
 
 	if (rt6_local) {
-		if (rt6_local->rt6i_idev)
+		if (rt6_local->rt6i_idev) {
 			in6_dev_put(rt6_local->rt6i_idev);
+			rt6_local->rt6i_idev = NULL;
+		}
 
 		dst = &rt6_local->dst;
 		dev_put(dst->dev);
-- 
2.1.0


From 87b90df38b028f79231a5ff1a1afe31ae22e41ac Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Tue, 21 Mar 2017 15:59:12 +0200
Subject: [PATCH 103/112] net/mlx5: Add missing entries for set/query rate
 limit commands

[ Upstream commit 1f30a86c58093046dc3e49c23d2618894e098f7a ]

The switch cases for the rate limit set and query commands were
missing, which could get us wrong under fw error or driver reset
flow, fix that.

Fixes: 1466cc5b23d1 ('net/mlx5: Rate limit tables support')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Hadar Hen Zion <hadarh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index bfe410e..3f51a44 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -367,6 +367,8 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_QUERY_VPORT_COUNTER:
 	case MLX5_CMD_OP_ALLOC_Q_COUNTER:
 	case MLX5_CMD_OP_QUERY_Q_COUNTER:
+	case MLX5_CMD_OP_SET_RATE_LIMIT:
+	case MLX5_CMD_OP_QUERY_RATE_LIMIT:
 	case MLX5_CMD_OP_ALLOC_PD:
 	case MLX5_CMD_OP_ALLOC_UAR:
 	case MLX5_CMD_OP_CONFIG_INT_MODERATION:
@@ -500,6 +502,8 @@ const char *mlx5_command_str(int command)
 	MLX5_COMMAND_STR_CASE(ALLOC_Q_COUNTER);
 	MLX5_COMMAND_STR_CASE(DEALLOC_Q_COUNTER);
 	MLX5_COMMAND_STR_CASE(QUERY_Q_COUNTER);
+	MLX5_COMMAND_STR_CASE(SET_RATE_LIMIT);
+	MLX5_COMMAND_STR_CASE(QUERY_RATE_LIMIT);
 	MLX5_COMMAND_STR_CASE(ALLOC_PD);
 	MLX5_COMMAND_STR_CASE(DEALLOC_PD);
 	MLX5_COMMAND_STR_CASE(ALLOC_UAR);
-- 
2.1.0


From c746a315ef1f7a87eef383ed0ba74fd74d3be034 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Tue, 21 Mar 2017 15:59:15 +0200
Subject: [PATCH 104/112] net/mlx5e: Use the proper UAPI values when offloading
 TC vlan actions

[ Upstream commit 09c91ddf2cd33489c2c14edfef43ae38d412888e ]

Currently we use the non UAPI values and we miss erring on
the modify action which is not supported, fix that.

Fixes: 8b32580df1cb ('net/mlx5e: Add TC vlan action for SRIOV offloads')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reported-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index a543ea6..3fd471a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -427,14 +427,16 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 		}
 
 		if (is_tcf_vlan(a)) {
-			if (tcf_vlan_action(a) == VLAN_F_POP) {
+			if (tcf_vlan_action(a) == TCA_VLAN_ACT_POP) {
 				attr->action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP;
-			} else if (tcf_vlan_action(a) == VLAN_F_PUSH) {
+			} else if (tcf_vlan_action(a) == TCA_VLAN_ACT_PUSH) {
 				if (tcf_vlan_push_proto(a) != htons(ETH_P_8021Q))
 					return -EOPNOTSUPP;
 
 				attr->action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH;
 				attr->vlan = tcf_vlan_push_vid(a);
+			} else { /* action is TCA_VLAN_ACT_MODIFY */
+				return -EOPNOTSUPP;
 			}
 			continue;
 		}
-- 
2.1.0


From 23f6003af4698c238e44f1f4201a61c3417f8808 Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@mellanox.com>
Date: Tue, 21 Mar 2017 15:59:17 +0200
Subject: [PATCH 105/112] net/mlx5: Increase number of max QPs in default
 profile

[ Upstream commit 5f40b4ed975c26016cf41953b7510fe90718e21c ]

With ConnectX-4 sharing SRQs from the same space as QPs, we hit a
limit preventing some applications to allocate needed QPs amount.
Double the size to 256K.

Fixes: e126ba97dba9e ('mlx5: Add driver for Mellanox Connect-IB adapters')
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 0c9ef87..7a196a0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -87,7 +87,7 @@ static struct mlx5_profile profile[] = {
 	[2] = {
 		.mask		= MLX5_PROF_MASK_QP_SIZE |
 				  MLX5_PROF_MASK_MR_CACHE,
-		.log_max_qp	= 17,
+		.log_max_qp	= 18,
 		.mr_cache[0]	= {
 			.size	= 500,
 			.limit	= 250
-- 
2.1.0


From 720b30c1738a7b4a4f603dd7895d335a890c4d17 Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Tue, 21 Mar 2017 15:59:18 +0200
Subject: [PATCH 106/112] net/mlx5e: Count GSO packets correctly

[ Upstream commit d3a4e4da54c7adb420d5f48e89be913b14bdeff1 ]

TX packets statistics ('tx_packets' counter) used to count GSO packets
as one, even though it contains multiple segments.
This patch will increment the counter by the number of segments, and
align the driver with the behavior of other drivers in the stack.

Note that no information is lost in this patch due to 'tx_tso_packets'
counter existence.

Before, ethtool showed:
$ ethtool -S ens6 | egrep "tx_packets|tx_tso_packets"
     tx_packets: 61340
     tx_tso_packets: 60954
     tx_packets_phy: 2451115

Now, we will see the more logical statistics:
$ ethtool -S ens6 | egrep "tx_packets|tx_tso_packets"
     tx_packets: 2451115
     tx_tso_packets: 60954
     tx_packets_phy: 2451115

Fixes: e586b3b0baee ("net/mlx5: Ethernet Datapath files")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Cc: kernel-team@fb.com
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index cfb6837..5743110 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -272,15 +272,18 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
 			sq->stats.tso_bytes += skb->len - ihs;
 		}
 
+		sq->stats.packets += skb_shinfo(skb)->gso_segs;
 		num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs;
 	} else {
 		bf = sq->bf_budget &&
 		     !skb->xmit_more &&
 		     !skb_shinfo(skb)->nr_frags;
 		ihs = mlx5e_get_inline_hdr_size(sq, skb, bf);
+		sq->stats.packets++;
 		num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN);
 	}
 
+	sq->stats.bytes += num_bytes;
 	wi->num_bytes = num_bytes;
 
 	if (skb_vlan_tag_present(skb)) {
@@ -377,8 +380,6 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
 	if (bf)
 		sq->bf_budget--;
 
-	sq->stats.packets++;
-	sq->stats.bytes += num_bytes;
 	return NETDEV_TX_OK;
 
 dma_unmap_wqe_err:
-- 
2.1.0


From cacf18ca47457cd517097521cd51876f9199255d Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Tue, 21 Mar 2017 15:59:19 +0200
Subject: [PATCH 107/112] net/mlx5e: Count LRO packets correctly

[ Upstream commit 8ab7e2ae15d84ba758b2c8c6f4075722e9bd2a08 ]

RX packets statistics ('rx_packets' counter) used to count LRO packets
as one, even though it contains multiple segments.
This patch will increment the counter by the number of segments, and
align the driver with the behavior of other drivers in the stack.

Note that no information is lost in this patch due to 'rx_lro_packets'
counter existence.

Before, ethtool showed:
$ ethtool -S ens6 | egrep "rx_packets|rx_lro_packets"
     rx_packets: 435277
     rx_lro_packets: 35847
     rx_packets_phy: 1935066

Now, we will see the more logical statistics:
$ ethtool -S ens6 | egrep "rx_packets|rx_lro_packets"
     rx_packets: 1935066
     rx_lro_packets: 35847
     rx_packets_phy: 1935066

Fixes: e586b3b0baee ("net/mlx5: Ethernet Datapath files")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Cc: kernel-team@fb.com
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 796bdf0..7309ae3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -602,6 +602,10 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
 	if (lro_num_seg > 1) {
 		mlx5e_lro_update_hdr(skb, cqe, cqe_bcnt);
 		skb_shinfo(skb)->gso_size = DIV_ROUND_UP(cqe_bcnt, lro_num_seg);
+		/* Subtract one since we already counted this as one
+		 * "regular" packet in mlx5e_complete_rx_cqe()
+		 */
+		rq->stats.packets += lro_num_seg - 1;
 		rq->stats.lro_packets++;
 		rq->stats.lro_bytes += cqe_bcnt;
 	}
-- 
2.1.0


From 249cbba744191c0d511c6ee9a65d50404dac155f Mon Sep 17 00:00:00 2001
From: Alexander Potapenko <glider@google.com>
Date: Tue, 21 Mar 2017 17:14:27 +0100
Subject: [PATCH 108/112] ipv6: make sure to initialize sockc.tsflags before
 first use

[ Upstream commit d515684d78148884d5fc425ba904c50f03844020 ]

In the case udp_sk(sk)->pending is AF_INET6, udpv6_sendmsg() would
jump to do_append_data, skipping the initialization of sockc.tsflags.
Fix the problem by moving sockc.tsflags initialization earlier.

The bug was detected with KMSAN.

Fixes: c14ac9451c34 ("sock: enable timestamping using control messages")
Signed-off-by: Alexander Potapenko <glider@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/udp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index e4a8000..40a289f 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1037,6 +1037,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	ipc6.hlimit = -1;
 	ipc6.tclass = -1;
 	ipc6.dontfrag = -1;
+	sockc.tsflags = sk->sk_tsflags;
 
 	/* destination address check */
 	if (sin6) {
@@ -1156,7 +1157,6 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
 
 	fl6.flowi6_mark = sk->sk_mark;
-	sockc.tsflags = sk->sk_tsflags;
 
 	if (msg->msg_controllen) {
 		opt = &opt_space;
-- 
2.1.0


From 42dffca1a3effc010545650514ecfa3911a365fb Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Tue, 21 Mar 2017 14:01:06 -0700
Subject: [PATCH 109/112] net: bcmgenet: remove bcmgenet_internal_phy_setup()

[ Upstream commit 31739eae738ccbe8b9d627c3f2251017ca03f4d2 ]

Commit 6ac3ce8295e6 ("net: bcmgenet: Remove excessive PHY reset")
removed the bcmgenet_mii_reset() function from bcmgenet_power_up() and
bcmgenet_internal_phy_setup() functions.  In so doing it broke the reset
of the internal PHY devices used by the GENETv1-GENETv3 which required
this reset before the UniMAC was enabled.  It also broke the internal
GPHY devices used by the GENETv4 because the config_init that installed
the AFE workaround was no longer occurring after the reset of the GPHY
performed by bcmgenet_phy_power_set() in bcmgenet_internal_phy_setup().
In addition the code in bcmgenet_internal_phy_setup() related to the
"enable APD" comment goes with the bcmgenet_mii_reset() so it should
have also been removed.

Commit bd4060a6108b ("net: bcmgenet: Power on integrated GPHY in
bcmgenet_power_up()") moved the bcmgenet_phy_power_set() call to the
bcmgenet_power_up() function, but failed to remove it from the
bcmgenet_internal_phy_setup() function.  Had it done so, the
bcmgenet_internal_phy_setup() function would have been empty and could
have been removed at that time.

Commit 5dbebbb44a6a ("net: bcmgenet: Software reset EPHY after power on")
was submitted to correct the functional problems introduced by
commit 6ac3ce8295e6 ("net: bcmgenet: Remove excessive PHY reset"). It
was included in v4.4 and made available on 4.3-stable. Unfortunately,
it didn't fully revert the commit because this bcmgenet_mii_reset()
doesn't apply the soft reset to the internal GPHY used by GENETv4 like
the previous one did. This prevents the restoration of the AFE work-
arounds for internal GPHY devices after the bcmgenet_phy_power_set() in
bcmgenet_internal_phy_setup().

This commit takes the alternate approach of removing the unnecessary
bcmgenet_internal_phy_setup() function which shouldn't have been in v4.3
so that when bcmgenet_mii_reset() was restored it should have only gone
into bcmgenet_power_up().  This will avoid the problems while also
removing the redundancy (and hopefully some of the confusion).

Fixes: 6ac3ce8295e6 ("net: bcmgenet: Remove excessive PHY reset")
Signed-off-by: Doug Berger <opendmb@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmmii.c | 15 ---------------
 1 file changed, 15 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index e876076..2f92819 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -220,20 +220,6 @@ void bcmgenet_phy_power_set(struct net_device *dev, bool enable)
 	udelay(60);
 }
 
-static void bcmgenet_internal_phy_setup(struct net_device *dev)
-{
-	struct bcmgenet_priv *priv = netdev_priv(dev);
-	u32 reg;
-
-	/* Power up PHY */
-	bcmgenet_phy_power_set(dev, true);
-	/* enable APD */
-	reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);
-	reg |= EXT_PWR_DN_EN_LD;
-	bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
-	bcmgenet_mii_reset(dev);
-}
-
 static void bcmgenet_moca_phy_setup(struct bcmgenet_priv *priv)
 {
 	u32 reg;
@@ -281,7 +267,6 @@ int bcmgenet_mii_config(struct net_device *dev)
 
 		if (priv->internal_phy) {
 			phy_name = "internal PHY";
-			bcmgenet_internal_phy_setup(dev);
 		} else if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) {
 			phy_name = "MoCA";
 			bcmgenet_moca_phy_setup(priv);
-- 
2.1.0


From 72e4f3eb00ac88a9643ed20f0c408ee392c96310 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 21 Mar 2017 19:22:28 -0700
Subject: [PATCH 110/112] ipv4: provide stronger user input validation in
 nl_fib_input()

[ Upstream commit c64c0b3cac4c5b8cb093727d2c19743ea3965c0b ]

Alexander reported a KMSAN splat caused by reads of uninitialized
field (tb_id_in) from user provided struct fib_result_nl

It turns out nl_fib_input() sanity tests on user input is a bit
wrong :

User can pretend nlh->nlmsg_len is big enough, but provide
at sendmsg() time a too small buffer.

Reported-by: Alexander Potapenko <glider@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_frontend.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 5b03d7f..6789e48 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1081,7 +1081,8 @@ static void nl_fib_input(struct sk_buff *skb)
 
 	net = sock_net(skb->sk);
 	nlh = nlmsg_hdr(skb);
-	if (skb->len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len ||
+	if (skb->len < nlmsg_total_size(sizeof(*frn)) ||
+	    skb->len < nlh->nlmsg_len ||
 	    nlmsg_len(nlh) < sizeof(*frn))
 		return;
 
-- 
2.1.0


From b4e900e8510b8232edc917ac3fc7279100d819de Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 22 Mar 2017 13:08:08 +0100
Subject: [PATCH 111/112] socket, bpf: fix sk_filter use after free in
 sk_clone_lock

[ Upstream commit a97e50cc4cb67e1e7bff56f6b41cda62ca832336 ]

In sk_clone_lock(), we create a new socket and inherit most of the
parent's members via sock_copy() which memcpy()'s various sections.
Now, in case the parent socket had a BPF socket filter attached,
then newsk->sk_filter points to the same instance as the original
sk->sk_filter.

sk_filter_charge() is then called on the newsk->sk_filter to take a
reference and should that fail due to hitting max optmem, we bail
out and release the newsk instance.

The issue is that commit 278571baca2a ("net: filter: simplify socket
charging") wrongly combined the dismantle path with the failure path
of xfrm_sk_clone_policy(). This means, even when charging failed, we
call sk_free_unlock_clone() on the newsk, which then still points to
the same sk_filter as the original sk.

Thus, sk_free_unlock_clone() calls into __sk_destruct() eventually
where it tests for present sk_filter and calls sk_filter_uncharge()
on it, which potentially lets sk_omem_alloc wrap around and releases
the eBPF prog and sk_filter structure from the (still intact) parent.

Fix it by making sure that when sk_filter_charge() failed, we reset
newsk->sk_filter back to NULL before passing to sk_free_unlock_clone(),
so that we don't mess with the parents sk_filter.

Only if xfrm_sk_clone_policy() fails, we did reach the point where
either the parent's filter was NULL and as a result newsk's as well
or where we previously had a successful sk_filter_charge(), thus for
that case, we do need sk_filter_uncharge() to release the prior taken
reference on sk_filter.

Fixes: 278571baca2a ("net: filter: simplify socket charging")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/core/sock.c b/net/core/sock.c
index 47809e9..470a204 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1538,6 +1538,12 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 			is_charged = sk_filter_charge(newsk, filter);
 
 		if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) {
+			/* We need to make sure that we don't uncharge the new
+			 * socket if we couldn't charge it in the first place
+			 * as otherwise we uncharge the parent's filter.
+			 */
+			if (!is_charged)
+				RCU_INIT_POINTER(newsk->sk_filter, NULL);
 			/* It is still raw copy of parent, so invalidate
 			 * destructor and make plain sk_free() */
 			newsk->sk_destruct = NULL;
-- 
2.1.0


From c4ebbb059048c45ac599ad72c8b5a4afbd69e94a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 22 Mar 2017 08:10:21 -0700
Subject: [PATCH 112/112] tcp: initialize icsk_ack.lrcvtime at session start
 time

[ Upstream commit 15bb7745e94a665caf42bfaabf0ce062845b533b ]

icsk_ack.lrcvtime has a 0 value at socket creation time.

tcpi_last_data_recv can have bogus value if no payload is ever received.

This patch initializes icsk_ack.lrcvtime for active sessions
in tcp_finish_connect(), and for passive sessions in
tcp_create_openreq_child()

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c     | 2 +-
 net/ipv4/tcp_minisocks.c | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index ce42ded..7727ffe 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5571,6 +5571,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
 	tcp_set_state(sk, TCP_ESTABLISHED);
+	icsk->icsk_ack.lrcvtime = tcp_time_stamp;
 
 	if (skb) {
 		icsk->icsk_af_ops->sk_rx_dst_set(sk, skb);
@@ -5789,7 +5790,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 			 * to stand against the temptation 8)     --ANK
 			 */
 			inet_csk_schedule_ack(sk);
-			icsk->icsk_ack.lrcvtime = tcp_time_stamp;
 			tcp_enter_quickack_mode(sk);
 			inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
 						  TCP_DELACK_MAX, TCP_RTO_MAX);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 6234eba..8615a6b 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -466,6 +466,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 		newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
 		minmax_reset(&newtp->rtt_min, tcp_time_stamp, ~0U);
 		newicsk->icsk_rto = TCP_TIMEOUT_INIT;
+		newicsk->icsk_ack.lrcvtime = tcp_time_stamp;
 
 		newtp->packets_out = 0;
 		newtp->retrans_out = 0;
-- 
2.1.0


[-- Attachment #3: net_410.mbox --]
[-- Type: Application/Octet-Stream, Size: 71179 bytes --]

From 56bd4e2b2f5b3a38816a2768aa39ae0b969b8bb9 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Wed, 15 Mar 2017 18:10:47 +0200
Subject: [PATCH 01/24] net/openvswitch: Set the ipv6 source tunnel key address
 attribute correctly

[ Upstream commit 3d20f1f7bd575d147ffa75621fa560eea0aec690 ]

When dealing with ipv6 source tunnel key address attribute
(OVS_TUNNEL_KEY_ATTR_IPV6_SRC) we are wrongly setting the tunnel
dst ip, fix that.

Fixes: 6b26ba3a7d95 ('openvswitch: netlink attributes for IPv6 tunneling')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reported-by: Paul Blakey <paulb@mellanox.com>
Acked-by: Jiri Benc <jbenc@redhat.com>
Acked-by: Joe Stringer <joe@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/flow_netlink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index c87d359..9425d32 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -588,7 +588,7 @@ static int ip_tun_from_nlattr(const struct nlattr *attr,
 			ipv4 = true;
 			break;
 		case OVS_TUNNEL_KEY_ATTR_IPV6_SRC:
-			SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.dst,
+			SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.src,
 					nla_get_in6_addr(a), is_mask);
 			ipv6 = true;
 			break;
-- 
2.1.0


From f1a1d442336a0ad0eeb3fd888dc862b8514712b3 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 15 Mar 2017 12:57:21 -0700
Subject: [PATCH 02/24] net: bcmgenet: Do not suspend PHY if Wake-on-LAN is
 enabled

[ Upstream commit 5371bbf4b295eea334ed453efa286afa2c3ccff3 ]

Suspending the PHY would be putting it in a low power state where it
may no longer allow us to do Wake-on-LAN.

Fixes: cc013fb48898 ("net: bcmgenet: correctly suspend and resume PHY device")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index f928968..3789bed 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -3395,7 +3395,8 @@ static int bcmgenet_suspend(struct device *d)
 
 	bcmgenet_netif_stop(dev);
 
-	phy_suspend(priv->phydev);
+	if (!device_may_wakeup(d))
+		phy_suspend(priv->phydev);
 
 	netif_device_detach(dev);
 
@@ -3492,7 +3493,8 @@ static int bcmgenet_resume(struct device *d)
 
 	netif_device_attach(dev);
 
-	phy_resume(priv->phydev);
+	if (!device_may_wakeup(d))
+		phy_resume(priv->phydev);
 
 	if (priv->eee.eee_enabled)
 		bcmgenet_eee_enable_set(dev, true);
-- 
2.1.0


From 95625ac228d7b304a6e19a2a29a69be41138e619 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 15 Mar 2017 13:21:28 -0700
Subject: [PATCH 03/24] net: properly release sk_frag.page

[ Upstream commit 22a0e18eac7a9e986fec76c60fa4a2926d1291e2 ]

I mistakenly added the code to release sk->sk_frag in
sk_common_release() instead of sk_destruct()

TCP sockets using sk->sk_allocation == GFP_ATOMIC do no call
sk_common_release() at close time, thus leaking one (order-3) page.

iSCSI is using such sockets.

Fixes: 5640f7685831 ("net: use a per task frag allocator")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index 4eca27d..c8a5cbf 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1444,6 +1444,11 @@ static void __sk_destruct(struct rcu_head *head)
 		pr_debug("%s: optmem leakage (%d bytes) detected\n",
 			 __func__, atomic_read(&sk->sk_omem_alloc));
 
+	if (sk->sk_frag.page) {
+		put_page(sk->sk_frag.page);
+		sk->sk_frag.page = NULL;
+	}
+
 	if (sk->sk_peer_cred)
 		put_cred(sk->sk_peer_cred);
 	put_pid(sk->sk_peer_pid);
@@ -2774,11 +2779,6 @@ void sk_common_release(struct sock *sk)
 
 	sk_refcnt_debug_release(sk);
 
-	if (sk->sk_frag.page) {
-		put_page(sk->sk_frag.page);
-		sk->sk_frag.page = NULL;
-	}
-
 	sock_put(sk);
 }
 EXPORT_SYMBOL(sk_common_release);
-- 
2.1.0


From 55a6da7436cb37f9c020815b1ddb61eabab11a9b Mon Sep 17 00:00:00 2001
From: "Lendacky, Thomas" <Thomas.Lendacky@amd.com>
Date: Wed, 15 Mar 2017 15:11:23 -0500
Subject: [PATCH 04/24] amd-xgbe: Fix jumbo MTU processing on newer hardware

[ Upstream commit 622c36f143fc9566ba49d7cec994c2da1182d9e2 ]

Newer hardware does not provide a cumulative payload length when multiple
descriptors are needed to handle the data. Once the MTU increases beyond
the size that can be handled by a single descriptor, the SKB does not get
built properly by the driver.

The driver will now calculate the size of the data buffers used by the
hardware.  The first buffer of the first descriptor is for packet headers
or packet headers and data when the headers can't be split. Subsequent
descriptors in a multi-descriptor chain will not use the first buffer. The
second buffer is used by all the descriptors in the chain for payload data.
Based on whether the driver is processing the first, intermediate, or last
descriptor it can calculate the buffer usage and build the SKB properly.

Tested and verified on both old and new hardware.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe-common.h |   6 +-
 drivers/net/ethernet/amd/xgbe/xgbe-dev.c    |  20 +++---
 drivers/net/ethernet/amd/xgbe/xgbe-drv.c    | 102 +++++++++++++++++-----------
 3 files changed, 78 insertions(+), 50 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
index 8a280e7..86f1626 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
@@ -1148,8 +1148,8 @@
 #define RX_PACKET_ATTRIBUTES_CSUM_DONE_WIDTH	1
 #define RX_PACKET_ATTRIBUTES_VLAN_CTAG_INDEX	1
 #define RX_PACKET_ATTRIBUTES_VLAN_CTAG_WIDTH	1
-#define RX_PACKET_ATTRIBUTES_INCOMPLETE_INDEX	2
-#define RX_PACKET_ATTRIBUTES_INCOMPLETE_WIDTH	1
+#define RX_PACKET_ATTRIBUTES_LAST_INDEX		2
+#define RX_PACKET_ATTRIBUTES_LAST_WIDTH		1
 #define RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_INDEX	3
 #define RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_WIDTH	1
 #define RX_PACKET_ATTRIBUTES_CONTEXT_INDEX	4
@@ -1158,6 +1158,8 @@
 #define RX_PACKET_ATTRIBUTES_RX_TSTAMP_WIDTH	1
 #define RX_PACKET_ATTRIBUTES_RSS_HASH_INDEX	6
 #define RX_PACKET_ATTRIBUTES_RSS_HASH_WIDTH	1
+#define RX_PACKET_ATTRIBUTES_FIRST_INDEX	7
+#define RX_PACKET_ATTRIBUTES_FIRST_WIDTH	1
 
 #define RX_NORMAL_DESC0_OVT_INDEX		0
 #define RX_NORMAL_DESC0_OVT_WIDTH		16
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
index 937f37a..24a687c 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
@@ -1896,10 +1896,15 @@ static int xgbe_dev_read(struct xgbe_channel *channel)
 
 	/* Get the header length */
 	if (XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, FD)) {
+		XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
+			       FIRST, 1);
 		rdata->rx.hdr_len = XGMAC_GET_BITS_LE(rdesc->desc2,
 						      RX_NORMAL_DESC2, HL);
 		if (rdata->rx.hdr_len)
 			pdata->ext_stats.rx_split_header_packets++;
+	} else {
+		XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
+			       FIRST, 0);
 	}
 
 	/* Get the RSS hash */
@@ -1922,19 +1927,16 @@ static int xgbe_dev_read(struct xgbe_channel *channel)
 		}
 	}
 
-	/* Get the packet length */
-	rdata->rx.len = XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, PL);
-
-	if (!XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, LD)) {
-		/* Not all the data has been transferred for this packet */
-		XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
-			       INCOMPLETE, 1);
+	/* Not all the data has been transferred for this packet */
+	if (!XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, LD))
 		return 0;
-	}
 
 	/* This is the last of the data for this packet */
 	XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
-		       INCOMPLETE, 0);
+		       LAST, 1);
+
+	/* Get the packet length */
+	rdata->rx.len = XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, PL);
 
 	/* Set checksum done indicator as appropriate */
 	if (netdev->features & NETIF_F_RXCSUM)
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 742e5d1b..36fd1a1 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -1973,13 +1973,12 @@ static struct sk_buff *xgbe_create_skb(struct xgbe_prv_data *pdata,
 {
 	struct sk_buff *skb;
 	u8 *packet;
-	unsigned int copy_len;
 
 	skb = napi_alloc_skb(napi, rdata->rx.hdr.dma_len);
 	if (!skb)
 		return NULL;
 
-	/* Start with the header buffer which may contain just the header
+	/* Pull in the header buffer which may contain just the header
 	 * or the header plus data
 	 */
 	dma_sync_single_range_for_cpu(pdata->dev, rdata->rx.hdr.dma_base,
@@ -1988,30 +1987,49 @@ static struct sk_buff *xgbe_create_skb(struct xgbe_prv_data *pdata,
 
 	packet = page_address(rdata->rx.hdr.pa.pages) +
 		 rdata->rx.hdr.pa.pages_offset;
-	copy_len = (rdata->rx.hdr_len) ? rdata->rx.hdr_len : len;
-	copy_len = min(rdata->rx.hdr.dma_len, copy_len);
-	skb_copy_to_linear_data(skb, packet, copy_len);
-	skb_put(skb, copy_len);
-
-	len -= copy_len;
-	if (len) {
-		/* Add the remaining data as a frag */
-		dma_sync_single_range_for_cpu(pdata->dev,
-					      rdata->rx.buf.dma_base,
-					      rdata->rx.buf.dma_off,
-					      rdata->rx.buf.dma_len,
-					      DMA_FROM_DEVICE);
-
-		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
-				rdata->rx.buf.pa.pages,
-				rdata->rx.buf.pa.pages_offset,
-				len, rdata->rx.buf.dma_len);
-		rdata->rx.buf.pa.pages = NULL;
-	}
+	skb_copy_to_linear_data(skb, packet, len);
+	skb_put(skb, len);
 
 	return skb;
 }
 
+static unsigned int xgbe_rx_buf1_len(struct xgbe_ring_data *rdata,
+				     struct xgbe_packet_data *packet)
+{
+	/* Always zero if not the first descriptor */
+	if (!XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, FIRST))
+		return 0;
+
+	/* First descriptor with split header, return header length */
+	if (rdata->rx.hdr_len)
+		return rdata->rx.hdr_len;
+
+	/* First descriptor but not the last descriptor and no split header,
+	 * so the full buffer was used
+	 */
+	if (!XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, LAST))
+		return rdata->rx.hdr.dma_len;
+
+	/* First descriptor and last descriptor and no split header, so
+	 * calculate how much of the buffer was used
+	 */
+	return min_t(unsigned int, rdata->rx.hdr.dma_len, rdata->rx.len);
+}
+
+static unsigned int xgbe_rx_buf2_len(struct xgbe_ring_data *rdata,
+				     struct xgbe_packet_data *packet,
+				     unsigned int len)
+{
+	/* Always the full buffer if not the last descriptor */
+	if (!XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, LAST))
+		return rdata->rx.buf.dma_len;
+
+	/* Last descriptor so calculate how much of the buffer was used
+	 * for the last bit of data
+	 */
+	return rdata->rx.len - len;
+}
+
 static int xgbe_tx_poll(struct xgbe_channel *channel)
 {
 	struct xgbe_prv_data *pdata = channel->pdata;
@@ -2094,8 +2112,8 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
 	struct napi_struct *napi;
 	struct sk_buff *skb;
 	struct skb_shared_hwtstamps *hwtstamps;
-	unsigned int incomplete, error, context_next, context;
-	unsigned int len, rdesc_len, max_len;
+	unsigned int last, error, context_next, context;
+	unsigned int len, buf1_len, buf2_len, max_len;
 	unsigned int received = 0;
 	int packet_count = 0;
 
@@ -2105,7 +2123,7 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
 	if (!ring)
 		return 0;
 
-	incomplete = 0;
+	last = 0;
 	context_next = 0;
 
 	napi = (pdata->per_channel_irq) ? &channel->napi : &pdata->napi;
@@ -2139,9 +2157,8 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
 		received++;
 		ring->cur++;
 
-		incomplete = XGMAC_GET_BITS(packet->attributes,
-					    RX_PACKET_ATTRIBUTES,
-					    INCOMPLETE);
+		last = XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
+				      LAST);
 		context_next = XGMAC_GET_BITS(packet->attributes,
 					      RX_PACKET_ATTRIBUTES,
 					      CONTEXT_NEXT);
@@ -2150,7 +2167,7 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
 					 CONTEXT);
 
 		/* Earlier error, just drain the remaining data */
-		if ((incomplete || context_next) && error)
+		if ((!last || context_next) && error)
 			goto read_again;
 
 		if (error || packet->errors) {
@@ -2162,16 +2179,22 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
 		}
 
 		if (!context) {
-			/* Length is cumulative, get this descriptor's length */
-			rdesc_len = rdata->rx.len - len;
-			len += rdesc_len;
+			/* Get the data length in the descriptor buffers */
+			buf1_len = xgbe_rx_buf1_len(rdata, packet);
+			len += buf1_len;
+			buf2_len = xgbe_rx_buf2_len(rdata, packet, len);
+			len += buf2_len;
 
-			if (rdesc_len && !skb) {
+			if (!skb) {
 				skb = xgbe_create_skb(pdata, napi, rdata,
-						      rdesc_len);
-				if (!skb)
+						      buf1_len);
+				if (!skb) {
 					error = 1;
-			} else if (rdesc_len) {
+					goto skip_data;
+				}
+			}
+
+			if (buf2_len) {
 				dma_sync_single_range_for_cpu(pdata->dev,
 							rdata->rx.buf.dma_base,
 							rdata->rx.buf.dma_off,
@@ -2181,13 +2204,14 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
 				skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
 						rdata->rx.buf.pa.pages,
 						rdata->rx.buf.pa.pages_offset,
-						rdesc_len,
+						buf2_len,
 						rdata->rx.buf.dma_len);
 				rdata->rx.buf.pa.pages = NULL;
 			}
 		}
 
-		if (incomplete || context_next)
+skip_data:
+		if (!last || context_next)
 			goto read_again;
 
 		if (!skb)
@@ -2245,7 +2269,7 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
 	}
 
 	/* Check if we need to save state before leaving */
-	if (received && (incomplete || context_next)) {
+	if (received && (!last || context_next)) {
 		rdata = XGBE_GET_DESC_DATA(ring, ring->cur);
 		rdata->state_saved = 1;
 		rdata->state.skb = skb;
-- 
2.1.0


From 1c729a46da3d5d01d4dbc3332aed154e64ec26c8 Mon Sep 17 00:00:00 2001
From: Kris Murphy <kriskend@linux.vnet.ibm.com>
Date: Thu, 16 Mar 2017 10:51:28 -0500
Subject: [PATCH 05/24] openvswitch: Add missing case OVS_TUNNEL_KEY_ATTR_PAD

[ Upstream commit 8f3dbfd79ed9ef9770305a7cc4e13dfd31ad2cd0 ]

Added a case for OVS_TUNNEL_KEY_ATTR_PAD to the switch statement
in ip_tun_from_nlattr in order to prevent the default case
returning an error.

Fixes: b46f6ded906e ("libnl: nla_put_be64(): align on a 64-bit area")
Signed-off-by: Kris Murphy <kriskend@linux.vnet.ibm.com>
Acked-by: Joe Stringer <joe@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/flow_netlink.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 9425d32..256e8f1 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -649,6 +649,8 @@ static int ip_tun_from_nlattr(const struct nlattr *attr,
 			tun_flags |= TUNNEL_VXLAN_OPT;
 			opts_type = type;
 			break;
+		case OVS_TUNNEL_KEY_ATTR_PAD:
+			break;
 		default:
 			OVS_NLERR(log, "Unknown IP tunnel attribute %d",
 				  type);
-- 
2.1.0


From b8aea892aca7fc56687a7174226ffa13b3677998 Mon Sep 17 00:00:00 2001
From: Andrey Ulanov <andreyu@google.com>
Date: Tue, 14 Mar 2017 20:16:42 -0700
Subject: [PATCH 06/24] net: unix: properly re-increment inflight counter of GC
 discarded candidates

[ Upstream commit 7df9c24625b9981779afb8fcdbe2bb4765e61147 ]

Dmitry has reported that a BUG_ON() condition in unix_notinflight()
may be triggered by a simple code that forwards unix socket in an
SCM_RIGHTS message.
That is caused by incorrect unix socket GC implementation in unix_gc().

The GC first collects list of candidates, then (a) decrements their
"children's" inflight counter, (b) checks which inflight counters are
now 0, and then (c) increments all inflight counters back.
(a) and (c) are done by calling scan_children() with inc_inflight or
dec_inflight as the second argument.

Commit 6209344f5a37 ("net: unix: fix inflight counting bug in garbage
collector") changed scan_children() such that it no longer considers
sockets that do not have UNIX_GC_CANDIDATE flag. It also added a block
of code that that unsets this flag _before_ invoking
scan_children(, dec_iflight, ). This may lead to incorrect inflight
counters for some sockets.

This change fixes this bug by changing order of operations:
UNIX_GC_CANDIDATE is now unset only after all inflight counters are
restored to the original state.

  kernel BUG at net/unix/garbage.c:149!
  RIP: 0010:[<ffffffff8717ebf4>]  [<ffffffff8717ebf4>]
  unix_notinflight+0x3b4/0x490 net/unix/garbage.c:149
  Call Trace:
   [<ffffffff8716cfbf>] unix_detach_fds.isra.19+0xff/0x170 net/unix/af_unix.c:1487
   [<ffffffff8716f6a9>] unix_destruct_scm+0xf9/0x210 net/unix/af_unix.c:1496
   [<ffffffff86a90a01>] skb_release_head_state+0x101/0x200 net/core/skbuff.c:655
   [<ffffffff86a9808a>] skb_release_all+0x1a/0x60 net/core/skbuff.c:668
   [<ffffffff86a980ea>] __kfree_skb+0x1a/0x30 net/core/skbuff.c:684
   [<ffffffff86a98284>] kfree_skb+0x184/0x570 net/core/skbuff.c:705
   [<ffffffff871789d5>] unix_release_sock+0x5b5/0xbd0 net/unix/af_unix.c:559
   [<ffffffff87179039>] unix_release+0x49/0x90 net/unix/af_unix.c:836
   [<ffffffff86a694b2>] sock_release+0x92/0x1f0 net/socket.c:570
   [<ffffffff86a6962b>] sock_close+0x1b/0x20 net/socket.c:1017
   [<ffffffff81a76b8e>] __fput+0x34e/0x910 fs/file_table.c:208
   [<ffffffff81a771da>] ____fput+0x1a/0x20 fs/file_table.c:244
   [<ffffffff81483ab0>] task_work_run+0x1a0/0x280 kernel/task_work.c:116
   [<     inline     >] exit_task_work include/linux/task_work.h:21
   [<ffffffff8141287a>] do_exit+0x183a/0x2640 kernel/exit.c:828
   [<ffffffff8141383e>] do_group_exit+0x14e/0x420 kernel/exit.c:931
   [<ffffffff814429d3>] get_signal+0x663/0x1880 kernel/signal.c:2307
   [<ffffffff81239b45>] do_signal+0xc5/0x2190 arch/x86/kernel/signal.c:807
   [<ffffffff8100666a>] exit_to_usermode_loop+0x1ea/0x2d0
  arch/x86/entry/common.c:156
   [<     inline     >] prepare_exit_to_usermode arch/x86/entry/common.c:190
   [<ffffffff81009693>] syscall_return_slowpath+0x4d3/0x570
  arch/x86/entry/common.c:259
   [<ffffffff881478e6>] entry_SYSCALL_64_fastpath+0xc4/0xc6

Link: https://lkml.org/lkml/2017/3/6/252
Signed-off-by: Andrey Ulanov <andreyu@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Fixes: 6209344 ("net: unix: fix inflight counting bug in garbage collector")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/garbage.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 6a0d485..c36757e 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -146,6 +146,7 @@ void unix_notinflight(struct user_struct *user, struct file *fp)
 	if (s) {
 		struct unix_sock *u = unix_sk(s);
 
+		BUG_ON(!atomic_long_read(&u->inflight));
 		BUG_ON(list_empty(&u->link));
 
 		if (atomic_long_dec_and_test(&u->inflight))
@@ -341,6 +342,14 @@ void unix_gc(void)
 	}
 	list_del(&cursor);
 
+	/* Now gc_candidates contains only garbage.  Restore original
+	 * inflight counters for these as well, and remove the skbuffs
+	 * which are creating the cycle(s).
+	 */
+	skb_queue_head_init(&hitlist);
+	list_for_each_entry(u, &gc_candidates, link)
+		scan_children(&u->sk, inc_inflight, &hitlist);
+
 	/* not_cycle_list contains those sockets which do not make up a
 	 * cycle.  Restore these to the inflight list.
 	 */
@@ -350,14 +359,6 @@ void unix_gc(void)
 		list_move_tail(&u->link, &gc_inflight_list);
 	}
 
-	/* Now gc_candidates contains only garbage.  Restore original
-	 * inflight counters for these as well, and remove the skbuffs
-	 * which are creating the cycle(s).
-	 */
-	skb_queue_head_init(&hitlist);
-	list_for_each_entry(u, &gc_candidates, link)
-	scan_children(&u->sk, inc_inflight, &hitlist);
-
 	spin_unlock(&unix_gc_lock);
 
 	/* Here we are. Hitlist is filled. Die. */
-- 
2.1.0


From c7cebb819d100f646ab615d82e0502df23f33ef9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Fri, 17 Mar 2017 17:20:48 +0100
Subject: [PATCH 07/24] qmi_wwan: add Dell DW5811e
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 6bd845d1cf98b45c634baacb8381436dad3c2dd0 ]

This is a Dell branded Sierra Wireless EM7455. It is operating in
MBIM mode by default, but can be configured to provide two QMI/RMNET
functions.

Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 24d5272..0d519a9 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -924,6 +924,8 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x413c, 0x81a9, 8)},	/* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */
 	{QMI_FIXED_INTF(0x413c, 0x81b1, 8)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card */
 	{QMI_FIXED_INTF(0x413c, 0x81b3, 8)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */
+	{QMI_FIXED_INTF(0x413c, 0x81b6, 8)},	/* Dell Wireless 5811e */
+	{QMI_FIXED_INTF(0x413c, 0x81b6, 10)},	/* Dell Wireless 5811e */
 	{QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)},	/* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */
 	{QMI_FIXED_INTF(0x22de, 0x9061, 3)},	/* WeTelecom WPD-600N */
 	{QMI_FIXED_INTF(0x1e0e, 0x9001, 5)},	/* SIMCom 7230E */
-- 
2.1.0


From 78f86dde03dc5afc109ec286f111e5f8862bee33 Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Fri, 17 Mar 2017 16:07:11 -0700
Subject: [PATCH 08/24] net: vrf: Reset rt6i_idev in local dst after put

[ Upstream commit 3dc857f0e8fc22610a59cbb346ba62c6e921863f ]

The VRF driver takes a reference to the inet6_dev on the VRF device for
its rt6_local dst when handling local traffic through the VRF device as
a loopback. When the device is deleted the driver does a put on the idev
but does not reset rt6i_idev in the rt6_info struct. When the dst is
destroyed, dst_destroy calls ip6_dst_destroy which does a second put for
what is essentially the same reference causing it to be prematurely freed.
Reset rt6i_idev after the put in the vrf driver.

Fixes: b4869aa2f881e ("net: vrf: ipv6 support for local traffic to
                       local addresses")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 682aac0..921fef2 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -462,8 +462,10 @@ static void vrf_rt6_release(struct net_device *dev, struct net_vrf *vrf)
 	}
 
 	if (rt6_local) {
-		if (rt6_local->rt6i_idev)
+		if (rt6_local->rt6i_idev) {
 			in6_dev_put(rt6_local->rt6i_idev);
+			rt6_local->rt6i_idev = NULL;
+		}
 
 		dst = &rt6_local->dst;
 		dev_put(dst->dev);
-- 
2.1.0


From b638e0ae45eed2d501c8cc393ade59e065ed3334 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Tue, 21 Mar 2017 15:59:12 +0200
Subject: [PATCH 09/24] net/mlx5: Add missing entries for set/query rate limit
 commands

[ Upstream commit 1f30a86c58093046dc3e49c23d2618894e098f7a ]

The switch cases for the rate limit set and query commands were
missing, which could get us wrong under fw error or driver reset
flow, fix that.

Fixes: 1466cc5b23d1 ('net/mlx5: Rate limit tables support')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Hadar Hen Zion <hadarh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index caa837e..a380353 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -361,6 +361,8 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_QUERY_VPORT_COUNTER:
 	case MLX5_CMD_OP_ALLOC_Q_COUNTER:
 	case MLX5_CMD_OP_QUERY_Q_COUNTER:
+	case MLX5_CMD_OP_SET_RATE_LIMIT:
+	case MLX5_CMD_OP_QUERY_RATE_LIMIT:
 	case MLX5_CMD_OP_ALLOC_PD:
 	case MLX5_CMD_OP_ALLOC_UAR:
 	case MLX5_CMD_OP_CONFIG_INT_MODERATION:
@@ -497,6 +499,8 @@ const char *mlx5_command_str(int command)
 	MLX5_COMMAND_STR_CASE(ALLOC_Q_COUNTER);
 	MLX5_COMMAND_STR_CASE(DEALLOC_Q_COUNTER);
 	MLX5_COMMAND_STR_CASE(QUERY_Q_COUNTER);
+	MLX5_COMMAND_STR_CASE(SET_RATE_LIMIT);
+	MLX5_COMMAND_STR_CASE(QUERY_RATE_LIMIT);
 	MLX5_COMMAND_STR_CASE(ALLOC_PD);
 	MLX5_COMMAND_STR_CASE(DEALLOC_PD);
 	MLX5_COMMAND_STR_CASE(ALLOC_UAR);
-- 
2.1.0


From 0e92ce6e6fcdbbb51e876bfabe2cd3cd57d13790 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Tue, 21 Mar 2017 15:59:13 +0200
Subject: [PATCH 10/24] net/mlx5e: Change the TC offload rule add/del code path
 to be per NIC or E-Switch

[ Upstream commit d85cdccbb3fe9a632ec9d0f4e4526c8c84fc3523 ]

Refactor the code to deal with add/del TC rules to have handler per NIC/E-switch
offloading use case, and push the latter into the e-switch code. This provides
better separation and is to be used in down-stream patch for applying a fix.

Fixes: bffaa916588e ("net/mlx5: E-Switch, Add control for inline mode")
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c    | 57 +++++++++++++++-------
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h  |  5 ++
 .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 14 ++++++
 3 files changed, 58 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 2ebbe80..b2378a8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -128,6 +128,23 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
 	return rule;
 }
 
+static void mlx5e_tc_del_nic_flow(struct mlx5e_priv *priv,
+				  struct mlx5e_tc_flow *flow)
+{
+	struct mlx5_fc *counter = NULL;
+
+	if (!IS_ERR(flow->rule)) {
+		counter = mlx5_flow_rule_counter(flow->rule);
+		mlx5_del_flow_rules(flow->rule);
+		mlx5_fc_destroy(priv->mdev, counter);
+	}
+
+	if (!mlx5e_tc_num_filters(priv) && (priv->fs.tc.t)) {
+		mlx5_destroy_flow_table(priv->fs.tc.t);
+		priv->fs.tc.t = NULL;
+	}
+}
+
 static struct mlx5_flow_handle *
 mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 		      struct mlx5_flow_spec *spec,
@@ -144,7 +161,24 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 }
 
 static void mlx5e_detach_encap(struct mlx5e_priv *priv,
-			       struct mlx5e_tc_flow *flow) {
+			       struct mlx5e_tc_flow *flow);
+
+static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
+				  struct mlx5e_tc_flow *flow)
+{
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+
+	mlx5_eswitch_del_offloaded_rule(esw, flow->rule, flow->attr);
+
+	mlx5_eswitch_del_vlan_action(esw, flow->attr);
+
+	if (flow->attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP)
+		mlx5e_detach_encap(priv, flow);
+}
+
+static void mlx5e_detach_encap(struct mlx5e_priv *priv,
+			       struct mlx5e_tc_flow *flow)
+{
 	struct list_head *next = flow->encap.next;
 
 	list_del(&flow->encap);
@@ -169,24 +203,11 @@ static void mlx5e_tc_del_flow(struct mlx5e_priv *priv,
 			      struct mlx5e_tc_flow *flow)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-	struct mlx5_fc *counter = NULL;
-
-	if (!IS_ERR(flow->rule)) {
-		counter = mlx5_flow_rule_counter(flow->rule);
-		mlx5_del_flow_rules(flow->rule);
-		mlx5_fc_destroy(priv->mdev, counter);
-	}
 
-	if (esw && esw->mode == SRIOV_OFFLOADS) {
-		mlx5_eswitch_del_vlan_action(esw, flow->attr);
-		if (flow->attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP)
-			mlx5e_detach_encap(priv, flow);
-	}
-
-	if (!mlx5e_tc_num_filters(priv) && (priv->fs.tc.t)) {
-		mlx5_destroy_flow_table(priv->fs.tc.t);
-		priv->fs.tc.t = NULL;
-	}
+	if (esw && esw->mode == SRIOV_OFFLOADS)
+		mlx5e_tc_del_fdb_flow(priv, flow);
+	else
+		mlx5e_tc_del_nic_flow(priv, flow);
 }
 
 static void parse_vxlan_attr(struct mlx5_flow_spec *spec,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 8661dd3..44ccd0c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -263,6 +263,11 @@ struct mlx5_flow_handle *
 mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 				struct mlx5_flow_spec *spec,
 				struct mlx5_esw_flow_attr *attr);
+void
+mlx5_eswitch_del_offloaded_rule(struct mlx5_eswitch *esw,
+				struct mlx5_flow_handle *rule,
+				struct mlx5_esw_flow_attr *attr);
+
 struct mlx5_flow_handle *
 mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, int vport, u32 tirn);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 595f7c7..8a29959 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -97,6 +97,20 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 	return rule;
 }
 
+void
+mlx5_eswitch_del_offloaded_rule(struct mlx5_eswitch *esw,
+				struct mlx5_flow_handle *rule,
+				struct mlx5_esw_flow_attr *attr)
+{
+	struct mlx5_fc *counter = NULL;
+
+	if (!IS_ERR(rule)) {
+		counter = mlx5_flow_rule_counter(rule);
+		mlx5_del_flow_rules(rule);
+		mlx5_fc_destroy(esw->dev, counter);
+	}
+}
+
 static int esw_set_global_vlan_pop(struct mlx5_eswitch *esw, u8 val)
 {
 	struct mlx5_eswitch_rep *rep;
-- 
2.1.0


From b97bb3b573467985f09bf9cce3d43b91e6458246 Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@mellanox.com>
Date: Tue, 21 Mar 2017 15:59:14 +0200
Subject: [PATCH 11/24] net/mlx5: E-Switch, Don't allow changing inline mode
 when flows are configured

[ Upstream commit 375f51e2b5b7b9a42b3139aea519cbb1bfc5d6ef ]

Changing the eswitch inline mode can potentially cause already configured
flows not to match the policy. E.g. set policy L4, add some L4 rules,
set policy to L2 --> bad! Hence we disallow it.

Keep track of how many offloaded rules are now set and refuse
inline mode changes if this isn't zero.

Fixes: bffaa916588e ("net/mlx5: E-Switch, Add control for inline mode")
Signed-off-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h          | 1 +
 drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 8 ++++++++
 2 files changed, 9 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 44ccd0c..b5967df 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -201,6 +201,7 @@ struct mlx5_esw_offload {
 	struct mlx5_eswitch_rep *vport_reps;
 	DECLARE_HASHTABLE(encap_tbl, 8);
 	u8 inline_mode;
+	u64 num_flows;
 };
 
 struct mlx5_eswitch {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 8a29959..7bce2bd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -93,6 +93,8 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 				   spec, &flow_act, dest, i);
 	if (IS_ERR(rule))
 		mlx5_fc_destroy(esw->dev, counter);
+	else
+		esw->offloads.num_flows++;
 
 	return rule;
 }
@@ -108,6 +110,7 @@ mlx5_eswitch_del_offloaded_rule(struct mlx5_eswitch *esw,
 		counter = mlx5_flow_rule_counter(rule);
 		mlx5_del_flow_rules(rule);
 		mlx5_fc_destroy(esw->dev, counter);
+		esw->offloads.num_flows--;
 	}
 }
 
@@ -919,6 +922,11 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode)
 	    MLX5_CAP_INLINE_MODE_VPORT_CONTEXT)
 		return -EOPNOTSUPP;
 
+	if (esw->offloads.num_flows > 0) {
+		esw_warn(dev, "Can't set inline mode when flows are configured\n");
+		return -EOPNOTSUPP;
+	}
+
 	err = esw_inline_mode_from_devlink(mode, &mlx5_mode);
 	if (err)
 		goto out;
-- 
2.1.0


From adf18d65e25b62ff28a823280bced7d0976e0b3f Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Tue, 21 Mar 2017 15:59:15 +0200
Subject: [PATCH 12/24] net/mlx5e: Use the proper UAPI values when offloading
 TC vlan actions

[ Upstream commit 09c91ddf2cd33489c2c14edfef43ae38d412888e ]

Currently we use the non UAPI values and we miss erring on
the modify action which is not supported, fix that.

Fixes: 8b32580df1cb ('net/mlx5e: Add TC vlan action for SRIOV offloads')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reported-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index b2378a8..cbc01a1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -974,14 +974,16 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 		}
 
 		if (is_tcf_vlan(a)) {
-			if (tcf_vlan_action(a) == VLAN_F_POP) {
+			if (tcf_vlan_action(a) == TCA_VLAN_ACT_POP) {
 				attr->action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP;
-			} else if (tcf_vlan_action(a) == VLAN_F_PUSH) {
+			} else if (tcf_vlan_action(a) == TCA_VLAN_ACT_PUSH) {
 				if (tcf_vlan_push_proto(a) != htons(ETH_P_8021Q))
 					return -EOPNOTSUPP;
 
 				attr->action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH;
 				attr->vlan = tcf_vlan_push_vid(a);
+			} else { /* action is TCA_VLAN_ACT_MODIFY */
+				return -EOPNOTSUPP;
 			}
 			continue;
 		}
-- 
2.1.0


From 4cbfcd859f9e28f965496ff6aa206424d1525a57 Mon Sep 17 00:00:00 2001
From: Paul Blakey <paulb@mellanox.com>
Date: Tue, 21 Mar 2017 15:59:16 +0200
Subject: [PATCH 13/24] net/mlx5e: Avoid supporting udp tunnel port ndo for VF
 reps

[ Upstream commit 1ad9a00ae0efc2e9337148d6c382fad3d27bf99a ]

This was added to allow the TC offloading code to identify offloading
encap/decap vxlan rules.

The VF reps are effectively related to the same mlx5 PCI device as the
PF. Since the kernel invokes the (say) delete ndo for each netdev, the
FW erred on multiple vxlan dst port deletes when the port was deleted
from the system.

We fix that by keeping the registration to be carried out only by the
PF. Since the PF serves as the uplink device, the VF reps will look
up a port there and realize if they are ok to offload that.

Tested:
 <SETUP VFS>
 <SETUP switchdev mode to have representors>
 ip link add vxlan1 type vxlan id 44 dev ens5f0 dstport 9999
 ip link set vxlan1 up
 ip link del dev vxlan1

Fixes: 4a25730eb202 ('net/mlx5e: Add ndo_udp_tunnel_add to VF representors')
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      | 4 ----
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 8 ++++----
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c  | 2 --
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c   | 9 +++++++--
 4 files changed, 11 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index c69a1f8..41db470 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -921,10 +921,6 @@ void mlx5e_destroy_netdev(struct mlx5_core_dev *mdev, struct mlx5e_priv *priv);
 int mlx5e_attach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev);
 void mlx5e_detach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev);
 u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout);
-void mlx5e_add_vxlan_port(struct net_device *netdev,
-			  struct udp_tunnel_info *ti);
-void mlx5e_del_vxlan_port(struct net_device *netdev,
-			  struct udp_tunnel_info *ti);
 
 int mlx5e_get_offload_stats(int attr_id, const struct net_device *dev,
 			    void *sp);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 9d9c649..a501d82 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3055,8 +3055,8 @@ static int mlx5e_get_vf_stats(struct net_device *dev,
 					    vf_stats);
 }
 
-void mlx5e_add_vxlan_port(struct net_device *netdev,
-			  struct udp_tunnel_info *ti)
+static void mlx5e_add_vxlan_port(struct net_device *netdev,
+				 struct udp_tunnel_info *ti)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
@@ -3069,8 +3069,8 @@ void mlx5e_add_vxlan_port(struct net_device *netdev,
 	mlx5e_vxlan_queue_work(priv, ti->sa_family, be16_to_cpu(ti->port), 1);
 }
 
-void mlx5e_del_vxlan_port(struct net_device *netdev,
-			  struct udp_tunnel_info *ti)
+static void mlx5e_del_vxlan_port(struct net_device *netdev,
+				 struct udp_tunnel_info *ti)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 8503788..871ff3b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -394,8 +394,6 @@ static const struct net_device_ops mlx5e_netdev_ops_rep = {
 	.ndo_get_phys_port_name  = mlx5e_rep_get_phys_port_name,
 	.ndo_setup_tc            = mlx5e_rep_ndo_setup_tc,
 	.ndo_get_stats64         = mlx5e_rep_get_stats,
-	.ndo_udp_tunnel_add      = mlx5e_add_vxlan_port,
-	.ndo_udp_tunnel_del      = mlx5e_del_vxlan_port,
 	.ndo_has_offload_stats	 = mlx5e_has_offload_stats,
 	.ndo_get_offload_stats	 = mlx5e_get_offload_stats,
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index cbc01a1..cc71881 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -264,12 +264,15 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
 			skb_flow_dissector_target(f->dissector,
 						  FLOW_DISSECTOR_KEY_ENC_PORTS,
 						  f->mask);
+		struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+		struct net_device *up_dev = mlx5_eswitch_get_uplink_netdev(esw);
+		struct mlx5e_priv *up_priv = netdev_priv(up_dev);
 
 		/* Full udp dst port must be given */
 		if (memchr_inv(&mask->dst, 0xff, sizeof(mask->dst)))
 			goto vxlan_match_offload_err;
 
-		if (mlx5e_vxlan_lookup_port(priv, be16_to_cpu(key->dst)) &&
+		if (mlx5e_vxlan_lookup_port(up_priv, be16_to_cpu(key->dst)) &&
 		    MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap))
 			parse_vxlan_attr(spec, f);
 		else {
@@ -827,6 +830,8 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
 			      struct mlx5_esw_flow_attr *attr)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	struct net_device *up_dev = mlx5_eswitch_get_uplink_netdev(esw);
+	struct mlx5e_priv *up_priv = netdev_priv(up_dev);
 	unsigned short family = ip_tunnel_info_af(tun_info);
 	struct ip_tunnel_key *key = &tun_info->key;
 	struct mlx5_encap_info info;
@@ -849,7 +854,7 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
 		return -EOPNOTSUPP;
 	}
 
-	if (mlx5e_vxlan_lookup_port(priv, be16_to_cpu(key->tp_dst)) &&
+	if (mlx5e_vxlan_lookup_port(up_priv, be16_to_cpu(key->tp_dst)) &&
 	    MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap)) {
 		info.tp_dst = key->tp_dst;
 		info.tun_id = tunnel_id_to_key32(key->tun_id);
-- 
2.1.0


From c63a8e304b9551d06ff7566bd7c423be2d28c9c3 Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@mellanox.com>
Date: Tue, 21 Mar 2017 15:59:17 +0200
Subject: [PATCH 14/24] net/mlx5: Increase number of max QPs in default profile

[ Upstream commit 5f40b4ed975c26016cf41953b7510fe90718e21c ]

With ConnectX-4 sharing SRQs from the same space as QPs, we hit a
limit preventing some applications to allocate needed QPs amount.
Double the size to 256K.

Fixes: e126ba97dba9e ('mlx5: Add driver for Mellanox Connect-IB adapters')
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 3c315eb..4aca265 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -87,7 +87,7 @@ static struct mlx5_profile profile[] = {
 	[2] = {
 		.mask		= MLX5_PROF_MASK_QP_SIZE |
 				  MLX5_PROF_MASK_MR_CACHE,
-		.log_max_qp	= 17,
+		.log_max_qp	= 18,
 		.mr_cache[0]	= {
 			.size	= 500,
 			.limit	= 250
-- 
2.1.0


From 15dec2b42bc9c81f5a5d3af64d68995813a15bae Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Tue, 21 Mar 2017 15:59:18 +0200
Subject: [PATCH 15/24] net/mlx5e: Count GSO packets correctly

[ Upstream commit d3a4e4da54c7adb420d5f48e89be913b14bdeff1 ]

TX packets statistics ('tx_packets' counter) used to count GSO packets
as one, even though it contains multiple segments.
This patch will increment the counter by the number of segments, and
align the driver with the behavior of other drivers in the stack.

Note that no information is lost in this patch due to 'tx_tso_packets'
counter existence.

Before, ethtool showed:
$ ethtool -S ens6 | egrep "tx_packets|tx_tso_packets"
     tx_packets: 61340
     tx_tso_packets: 60954
     tx_packets_phy: 2451115

Now, we will see the more logical statistics:
$ ethtool -S ens6 | egrep "tx_packets|tx_tso_packets"
     tx_packets: 2451115
     tx_tso_packets: 60954
     tx_packets_phy: 2451115

Fixes: e586b3b0baee ("net/mlx5: Ethernet Datapath files")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Cc: kernel-team@fb.com
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index cfb6837..5743110 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -272,15 +272,18 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
 			sq->stats.tso_bytes += skb->len - ihs;
 		}
 
+		sq->stats.packets += skb_shinfo(skb)->gso_segs;
 		num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs;
 	} else {
 		bf = sq->bf_budget &&
 		     !skb->xmit_more &&
 		     !skb_shinfo(skb)->nr_frags;
 		ihs = mlx5e_get_inline_hdr_size(sq, skb, bf);
+		sq->stats.packets++;
 		num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN);
 	}
 
+	sq->stats.bytes += num_bytes;
 	wi->num_bytes = num_bytes;
 
 	if (skb_vlan_tag_present(skb)) {
@@ -377,8 +380,6 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
 	if (bf)
 		sq->bf_budget--;
 
-	sq->stats.packets++;
-	sq->stats.bytes += num_bytes;
 	return NETDEV_TX_OK;
 
 dma_unmap_wqe_err:
-- 
2.1.0


From fe090f7d0a26ebfa8e6b48e8bfbbebcce144fbea Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Tue, 21 Mar 2017 15:59:19 +0200
Subject: [PATCH 16/24] net/mlx5e: Count LRO packets correctly

[ Upstream commit 8ab7e2ae15d84ba758b2c8c6f4075722e9bd2a08 ]

RX packets statistics ('rx_packets' counter) used to count LRO packets
as one, even though it contains multiple segments.
This patch will increment the counter by the number of segments, and
align the driver with the behavior of other drivers in the stack.

Note that no information is lost in this patch due to 'rx_lro_packets'
counter existence.

Before, ethtool showed:
$ ethtool -S ens6 | egrep "rx_packets|rx_lro_packets"
     rx_packets: 435277
     rx_lro_packets: 35847
     rx_packets_phy: 1935066

Now, we will see the more logical statistics:
$ ethtool -S ens6 | egrep "rx_packets|rx_lro_packets"
     rx_packets: 1935066
     rx_lro_packets: 35847
     rx_packets_phy: 1935066

Fixes: e586b3b0baee ("net/mlx5: Ethernet Datapath files")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Cc: kernel-team@fb.com
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index e3b88bb..b1939a1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -603,6 +603,10 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
 	if (lro_num_seg > 1) {
 		mlx5e_lro_update_hdr(skb, cqe, cqe_bcnt);
 		skb_shinfo(skb)->gso_size = DIV_ROUND_UP(cqe_bcnt, lro_num_seg);
+		/* Subtract one since we already counted this as one
+		 * "regular" packet in mlx5e_complete_rx_cqe()
+		 */
+		rq->stats.packets += lro_num_seg - 1;
 		rq->stats.lro_packets++;
 		rq->stats.lro_bytes += cqe_bcnt;
 	}
-- 
2.1.0


From 40b2abcd3bc8cdc440b6a57f7f7151e4f3ec0659 Mon Sep 17 00:00:00 2001
From: Alexander Potapenko <glider@google.com>
Date: Tue, 21 Mar 2017 17:14:27 +0100
Subject: [PATCH 17/24] ipv6: make sure to initialize sockc.tsflags before
 first use

[ Upstream commit d515684d78148884d5fc425ba904c50f03844020 ]

In the case udp_sk(sk)->pending is AF_INET6, udpv6_sendmsg() would
jump to do_append_data, skipping the initialization of sockc.tsflags.
Fix the problem by moving sockc.tsflags initialization earlier.

The bug was detected with KMSAN.

Fixes: c14ac9451c34 ("sock: enable timestamping using control messages")
Signed-off-by: Alexander Potapenko <glider@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/udp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 221825a..0770f95 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1022,6 +1022,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	ipc6.hlimit = -1;
 	ipc6.tclass = -1;
 	ipc6.dontfrag = -1;
+	sockc.tsflags = sk->sk_tsflags;
 
 	/* destination address check */
 	if (sin6) {
@@ -1146,7 +1147,6 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	fl6.flowi6_mark = sk->sk_mark;
 	fl6.flowi6_uid = sk->sk_uid;
-	sockc.tsflags = sk->sk_tsflags;
 
 	if (msg->msg_controllen) {
 		opt = &opt_space;
-- 
2.1.0


From 0147494503423fd89594a61f4c3f74b1b7d1751d Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Tue, 21 Mar 2017 14:01:06 -0700
Subject: [PATCH 18/24] net: bcmgenet: remove bcmgenet_internal_phy_setup()

[ Upstream commit 31739eae738ccbe8b9d627c3f2251017ca03f4d2 ]

Commit 6ac3ce8295e6 ("net: bcmgenet: Remove excessive PHY reset")
removed the bcmgenet_mii_reset() function from bcmgenet_power_up() and
bcmgenet_internal_phy_setup() functions.  In so doing it broke the reset
of the internal PHY devices used by the GENETv1-GENETv3 which required
this reset before the UniMAC was enabled.  It also broke the internal
GPHY devices used by the GENETv4 because the config_init that installed
the AFE workaround was no longer occurring after the reset of the GPHY
performed by bcmgenet_phy_power_set() in bcmgenet_internal_phy_setup().
In addition the code in bcmgenet_internal_phy_setup() related to the
"enable APD" comment goes with the bcmgenet_mii_reset() so it should
have also been removed.

Commit bd4060a6108b ("net: bcmgenet: Power on integrated GPHY in
bcmgenet_power_up()") moved the bcmgenet_phy_power_set() call to the
bcmgenet_power_up() function, but failed to remove it from the
bcmgenet_internal_phy_setup() function.  Had it done so, the
bcmgenet_internal_phy_setup() function would have been empty and could
have been removed at that time.

Commit 5dbebbb44a6a ("net: bcmgenet: Software reset EPHY after power on")
was submitted to correct the functional problems introduced by
commit 6ac3ce8295e6 ("net: bcmgenet: Remove excessive PHY reset"). It
was included in v4.4 and made available on 4.3-stable. Unfortunately,
it didn't fully revert the commit because this bcmgenet_mii_reset()
doesn't apply the soft reset to the internal GPHY used by GENETv4 like
the previous one did. This prevents the restoration of the AFE work-
arounds for internal GPHY devices after the bcmgenet_phy_power_set() in
bcmgenet_internal_phy_setup().

This commit takes the alternate approach of removing the unnecessary
bcmgenet_internal_phy_setup() function which shouldn't have been in v4.3
so that when bcmgenet_mii_reset() was restored it should have only gone
into bcmgenet_power_up().  This will avoid the problems while also
removing the redundancy (and hopefully some of the confusion).

Fixes: 6ac3ce8295e6 ("net: bcmgenet: Remove excessive PHY reset")
Signed-off-by: Doug Berger <opendmb@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmmii.c | 15 ---------------
 1 file changed, 15 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index e876076..2f92819 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -220,20 +220,6 @@ void bcmgenet_phy_power_set(struct net_device *dev, bool enable)
 	udelay(60);
 }
 
-static void bcmgenet_internal_phy_setup(struct net_device *dev)
-{
-	struct bcmgenet_priv *priv = netdev_priv(dev);
-	u32 reg;
-
-	/* Power up PHY */
-	bcmgenet_phy_power_set(dev, true);
-	/* enable APD */
-	reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);
-	reg |= EXT_PWR_DN_EN_LD;
-	bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
-	bcmgenet_mii_reset(dev);
-}
-
 static void bcmgenet_moca_phy_setup(struct bcmgenet_priv *priv)
 {
 	u32 reg;
@@ -281,7 +267,6 @@ int bcmgenet_mii_config(struct net_device *dev)
 
 		if (priv->internal_phy) {
 			phy_name = "internal PHY";
-			bcmgenet_internal_phy_setup(dev);
 		} else if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) {
 			phy_name = "MoCA";
 			bcmgenet_moca_phy_setup(priv);
-- 
2.1.0


From d2d34190186da93e9a644a05369a00b8a393785f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 21 Mar 2017 19:22:28 -0700
Subject: [PATCH 19/24] ipv4: provide stronger user input validation in
 nl_fib_input()

[ Upstream commit c64c0b3cac4c5b8cb093727d2c19743ea3965c0b ]

Alexander reported a KMSAN splat caused by reads of uninitialized
field (tb_id_in) from user provided struct fib_result_nl

It turns out nl_fib_input() sanity tests on user input is a bit
wrong :

User can pretend nlh->nlmsg_len is big enough, but provide
at sendmsg() time a too small buffer.

Reported-by: Alexander Potapenko <glider@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_frontend.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index b39a791..091de0b 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1082,7 +1082,8 @@ static void nl_fib_input(struct sk_buff *skb)
 
 	net = sock_net(skb->sk);
 	nlh = nlmsg_hdr(skb);
-	if (skb->len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len ||
+	if (skb->len < nlmsg_total_size(sizeof(*frn)) ||
+	    skb->len < nlh->nlmsg_len ||
 	    nlmsg_len(nlh) < sizeof(*frn))
 		return;
 
-- 
2.1.0


From 49cca2b6aa9964ff98e402ff1752a09fabe7f15d Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 22 Mar 2017 13:08:08 +0100
Subject: [PATCH 20/24] socket, bpf: fix sk_filter use after free in
 sk_clone_lock

[ Upstream commit a97e50cc4cb67e1e7bff56f6b41cda62ca832336 ]

In sk_clone_lock(), we create a new socket and inherit most of the
parent's members via sock_copy() which memcpy()'s various sections.
Now, in case the parent socket had a BPF socket filter attached,
then newsk->sk_filter points to the same instance as the original
sk->sk_filter.

sk_filter_charge() is then called on the newsk->sk_filter to take a
reference and should that fail due to hitting max optmem, we bail
out and release the newsk instance.

The issue is that commit 278571baca2a ("net: filter: simplify socket
charging") wrongly combined the dismantle path with the failure path
of xfrm_sk_clone_policy(). This means, even when charging failed, we
call sk_free_unlock_clone() on the newsk, which then still points to
the same sk_filter as the original sk.

Thus, sk_free_unlock_clone() calls into __sk_destruct() eventually
where it tests for present sk_filter and calls sk_filter_uncharge()
on it, which potentially lets sk_omem_alloc wrap around and releases
the eBPF prog and sk_filter structure from the (still intact) parent.

Fix it by making sure that when sk_filter_charge() failed, we reset
newsk->sk_filter back to NULL before passing to sk_free_unlock_clone(),
so that we don't mess with the parents sk_filter.

Only if xfrm_sk_clone_policy() fails, we did reach the point where
either the parent's filter was NULL and as a result newsk's as well
or where we previously had a successful sk_filter_charge(), thus for
that case, we do need sk_filter_uncharge() to release the prior taken
reference on sk_filter.

Fixes: 278571baca2a ("net: filter: simplify socket charging")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/core/sock.c b/net/core/sock.c
index c8a5cbf..4e7f10c 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1545,6 +1545,12 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 			is_charged = sk_filter_charge(newsk, filter);
 
 		if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) {
+			/* We need to make sure that we don't uncharge the new
+			 * socket if we couldn't charge it in the first place
+			 * as otherwise we uncharge the parent's filter.
+			 */
+			if (!is_charged)
+				RCU_INIT_POINTER(newsk->sk_filter, NULL);
 			/* It is still raw copy of parent, so invalidate
 			 * destructor and make plain sk_free() */
 			newsk->sk_destruct = NULL;
-- 
2.1.0


From 4c47d1010b2efe329cd36aa506ddcb7e435a6930 Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <sgruszka@redhat.com>
Date: Wed, 22 Mar 2017 16:08:33 +0100
Subject: [PATCH 21/24] genetlink: fix counting regression on ctrl_dumpfamily()

[ Upstream commit 1d2a6a5e4bf2921531071fcff8538623dce74efa ]

Commit 2ae0f17df1cd ("genetlink: use idr to track families") replaced

	if (++n < fams_to_skip)
		continue;
into:

	if (n++ < fams_to_skip)
		continue;

This subtle change cause that on retry ctrl_dumpfamily() call we omit
one family that failed to do ctrl_fill_info() on previous call, because
cb->args[0] = n number counts also family that failed to do
ctrl_fill_info().

Patch fixes the problem and avoid confusion in the future just decrease
n counter when ctrl_fill_info() fail.

User visible problem caused by this bug is failure to get access to
some genetlink family i.e. nl80211. However problem is reproducible
only if number of registered genetlink families is big enough to
cause second call of ctrl_dumpfamily().

Cc: Xose Vazquez Perez <xose.vazquez@gmail.com>
Cc: Larry Finger <Larry.Finger@lwfinger.net>
Cc: Johannes Berg <johannes@sipsolutions.net>
Fixes: 2ae0f17df1cd ("genetlink: use idr to track families")
Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Acked-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/genetlink.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index fb6e10f..92e0981 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -783,8 +783,10 @@ static int ctrl_dumpfamily(struct sk_buff *skb, struct netlink_callback *cb)
 
 		if (ctrl_fill_info(rt, NETLINK_CB(cb->skb).portid,
 				   cb->nlh->nlmsg_seq, NLM_F_MULTI,
-				   skb, CTRL_CMD_NEWFAMILY) < 0)
+				   skb, CTRL_CMD_NEWFAMILY) < 0) {
+			n--;
 			break;
+		}
 	}
 
 	cb->args[0] = n;
-- 
2.1.0


From 4eadf934b454d90855f5cc255bafc04e1ee6b9a2 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 22 Mar 2017 08:10:21 -0700
Subject: [PATCH 22/24] tcp: initialize icsk_ack.lrcvtime at session start time

[ Upstream commit 15bb7745e94a665caf42bfaabf0ce062845b533b ]

icsk_ack.lrcvtime has a 0 value at socket creation time.

tcpi_last_data_recv can have bogus value if no payload is ever received.

This patch initializes icsk_ack.lrcvtime for active sessions
in tcp_finish_connect(), and for passive sessions in
tcp_create_openreq_child()

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c     | 2 +-
 net/ipv4/tcp_minisocks.c | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 28777a0..e7516ef 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5571,6 +5571,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
 	tcp_set_state(sk, TCP_ESTABLISHED);
+	icsk->icsk_ack.lrcvtime = tcp_time_stamp;
 
 	if (skb) {
 		icsk->icsk_af_ops->sk_rx_dst_set(sk, skb);
@@ -5789,7 +5790,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 			 * to stand against the temptation 8)     --ANK
 			 */
 			inet_csk_schedule_ack(sk);
-			icsk->icsk_ack.lrcvtime = tcp_time_stamp;
 			tcp_enter_quickack_mode(sk);
 			inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
 						  TCP_DELACK_MAX, TCP_RTO_MAX);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 28ce5ee..80ff517 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -466,6 +466,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 		newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
 		minmax_reset(&newtp->rtt_min, tcp_time_stamp, ~0U);
 		newicsk->icsk_rto = TCP_TIMEOUT_INIT;
+		newicsk->icsk_ack.lrcvtime = tcp_time_stamp;
 
 		newtp->packets_out = 0;
 		newtp->retrans_out = 0;
-- 
2.1.0


From adc7e0aa084b14f7550cb4c88aa89e18d8235a69 Mon Sep 17 00:00:00 2001
From: "Lendacky, Thomas" <Thomas.Lendacky@amd.com>
Date: Wed, 22 Mar 2017 17:25:27 -0500
Subject: [PATCH 23/24] amd-xgbe: Fix the ECC-related bit position definitions

[ Upstream commit f43feef4e6acde10857fcbfdede790d6b3f2c71d ]

The ECC bit positions that describe whether the ECC interrupt is for
Tx, Rx or descriptor memory and whether the it is a single correctable
or double detected error were defined in incorrectly (reversed order).
Fix the bit position definitions for these settings so that the proper
ECC handling is performed.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe-common.h | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
index 86f1626..127adbe 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
@@ -984,29 +984,29 @@
 #define XP_ECC_CNT1_DESC_DED_WIDTH		8
 #define XP_ECC_CNT1_DESC_SEC_INDEX		0
 #define XP_ECC_CNT1_DESC_SEC_WIDTH		8
-#define XP_ECC_IER_DESC_DED_INDEX		0
+#define XP_ECC_IER_DESC_DED_INDEX		5
 #define XP_ECC_IER_DESC_DED_WIDTH		1
-#define XP_ECC_IER_DESC_SEC_INDEX		1
+#define XP_ECC_IER_DESC_SEC_INDEX		4
 #define XP_ECC_IER_DESC_SEC_WIDTH		1
-#define XP_ECC_IER_RX_DED_INDEX			2
+#define XP_ECC_IER_RX_DED_INDEX			3
 #define XP_ECC_IER_RX_DED_WIDTH			1
-#define XP_ECC_IER_RX_SEC_INDEX			3
+#define XP_ECC_IER_RX_SEC_INDEX			2
 #define XP_ECC_IER_RX_SEC_WIDTH			1
-#define XP_ECC_IER_TX_DED_INDEX			4
+#define XP_ECC_IER_TX_DED_INDEX			1
 #define XP_ECC_IER_TX_DED_WIDTH			1
-#define XP_ECC_IER_TX_SEC_INDEX			5
+#define XP_ECC_IER_TX_SEC_INDEX			0
 #define XP_ECC_IER_TX_SEC_WIDTH			1
-#define XP_ECC_ISR_DESC_DED_INDEX		0
+#define XP_ECC_ISR_DESC_DED_INDEX		5
 #define XP_ECC_ISR_DESC_DED_WIDTH		1
-#define XP_ECC_ISR_DESC_SEC_INDEX		1
+#define XP_ECC_ISR_DESC_SEC_INDEX		4
 #define XP_ECC_ISR_DESC_SEC_WIDTH		1
-#define XP_ECC_ISR_RX_DED_INDEX			2
+#define XP_ECC_ISR_RX_DED_INDEX			3
 #define XP_ECC_ISR_RX_DED_WIDTH			1
-#define XP_ECC_ISR_RX_SEC_INDEX			3
+#define XP_ECC_ISR_RX_SEC_INDEX			2
 #define XP_ECC_ISR_RX_SEC_WIDTH			1
-#define XP_ECC_ISR_TX_DED_INDEX			4
+#define XP_ECC_ISR_TX_DED_INDEX			1
 #define XP_ECC_ISR_TX_DED_WIDTH			1
-#define XP_ECC_ISR_TX_SEC_INDEX			5
+#define XP_ECC_ISR_TX_SEC_INDEX			0
 #define XP_ECC_ISR_TX_SEC_WIDTH			1
 #define XP_I2C_MUTEX_BUSY_INDEX			31
 #define XP_I2C_MUTEX_BUSY_WIDTH			1
-- 
2.1.0


From f92682e9f6900432eddac4fd4e3197332a6ff7a8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 16 Mar 2017 19:02:33 -0700
Subject: [PATCH 24/24] net: solve a NAPI race

commit 39e6c8208d7b6fb9d2047850fb3327db567b564b upstream.

While playing with mlx4 hardware timestamping of RX packets, I found
that some packets were received by TCP stack with a ~200 ms delay...

Since the timestamp was provided by the NIC, and my probe was added
in tcp_v4_rcv() while in BH handler, I was confident it was not
a sender issue, or a drop in the network.

This would happen with a very low probability, but hurting RPC
workloads.

A NAPI driver normally arms the IRQ after the napi_complete_done(),
after NAPI_STATE_SCHED is cleared, so that the hard irq handler can grab
it.

Problem is that if another point in the stack grabs NAPI_STATE_SCHED bit
while IRQ are not disabled, we might have later an IRQ firing and
finding this bit set, right before napi_complete_done() clears it.

This can happen with busy polling users, or if gro_flush_timeout is
used. But some other uses of napi_schedule() in drivers can cause this
as well.

thread 1                                 thread 2 (could be on same cpu, or not)

// busy polling or napi_watchdog()
napi_schedule();
...
napi->poll()

device polling:
read 2 packets from ring buffer
                                          Additional 3rd packet is
available.
                                          device hard irq

                                          // does nothing because
NAPI_STATE_SCHED bit is owned by thread 1
                                          napi_schedule();

napi_complete_done(napi, 2);
rearm_irq();

Note that rearm_irq() will not force the device to send an additional
IRQ for the packet it already signaled (3rd packet in my example)

This patch adds a new NAPI_STATE_MISSED bit, that napi_schedule_prep()
can set if it could not grab NAPI_STATE_SCHED

Then napi_complete_done() properly reschedules the napi to make sure
we do not miss something.

Since we manipulate multiple bits at once, use cmpxchg() like in
sk_busy_loop() to provide proper transactions.

In v2, I changed napi_watchdog() to use a relaxed variant of
napi_schedule_prep() : No need to set NAPI_STATE_MISSED from this point.

In v3, I added more details in the changelog and clears
NAPI_STATE_MISSED in busy_poll_stop()

In v4, I added the ideas given by Alexander Duyck in v3 review

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Alexander Duyck <alexander.duyck@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 29 ++++++-----------
 net/core/dev.c            | 81 +++++++++++++++++++++++++++++++++++++++++++----
 2 files changed, 83 insertions(+), 27 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 2791467..bdef8b7 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -330,6 +330,7 @@ struct napi_struct {
 
 enum {
 	NAPI_STATE_SCHED,	/* Poll is scheduled */
+	NAPI_STATE_MISSED,	/* reschedule a napi */
 	NAPI_STATE_DISABLE,	/* Disable pending */
 	NAPI_STATE_NPSVC,	/* Netpoll - don't dequeue from poll_list */
 	NAPI_STATE_HASHED,	/* In NAPI hash (busy polling possible) */
@@ -338,12 +339,13 @@ enum {
 };
 
 enum {
-	NAPIF_STATE_SCHED	 = (1UL << NAPI_STATE_SCHED),
-	NAPIF_STATE_DISABLE	 = (1UL << NAPI_STATE_DISABLE),
-	NAPIF_STATE_NPSVC	 = (1UL << NAPI_STATE_NPSVC),
-	NAPIF_STATE_HASHED	 = (1UL << NAPI_STATE_HASHED),
-	NAPIF_STATE_NO_BUSY_POLL = (1UL << NAPI_STATE_NO_BUSY_POLL),
-	NAPIF_STATE_IN_BUSY_POLL = (1UL << NAPI_STATE_IN_BUSY_POLL),
+	NAPIF_STATE_SCHED	 = BIT(NAPI_STATE_SCHED),
+	NAPIF_STATE_MISSED	 = BIT(NAPI_STATE_MISSED),
+	NAPIF_STATE_DISABLE	 = BIT(NAPI_STATE_DISABLE),
+	NAPIF_STATE_NPSVC	 = BIT(NAPI_STATE_NPSVC),
+	NAPIF_STATE_HASHED	 = BIT(NAPI_STATE_HASHED),
+	NAPIF_STATE_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL),
+	NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL),
 };
 
 enum gro_result {
@@ -413,20 +415,7 @@ static inline bool napi_disable_pending(struct napi_struct *n)
 	return test_bit(NAPI_STATE_DISABLE, &n->state);
 }
 
-/**
- *	napi_schedule_prep - check if NAPI can be scheduled
- *	@n: NAPI context
- *
- * Test if NAPI routine is already running, and if not mark
- * it as running.  This is used as a condition variable to
- * insure only one NAPI poll instance runs.  We also make
- * sure there is no pending NAPI disable.
- */
-static inline bool napi_schedule_prep(struct napi_struct *n)
-{
-	return !napi_disable_pending(n) &&
-		!test_and_set_bit(NAPI_STATE_SCHED, &n->state);
-}
+bool napi_schedule_prep(struct napi_struct *n);
 
 /**
  *	napi_schedule - schedule NAPI poll
diff --git a/net/core/dev.c b/net/core/dev.c
index fd6e2df..54f8c16 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4913,6 +4913,39 @@ void __napi_schedule(struct napi_struct *n)
 EXPORT_SYMBOL(__napi_schedule);
 
 /**
+ *	napi_schedule_prep - check if napi can be scheduled
+ *	@n: napi context
+ *
+ * Test if NAPI routine is already running, and if not mark
+ * it as running.  This is used as a condition variable
+ * insure only one NAPI poll instance runs.  We also make
+ * sure there is no pending NAPI disable.
+ */
+bool napi_schedule_prep(struct napi_struct *n)
+{
+	unsigned long val, new;
+
+	do {
+		val = READ_ONCE(n->state);
+		if (unlikely(val & NAPIF_STATE_DISABLE))
+			return false;
+		new = val | NAPIF_STATE_SCHED;
+
+		/* Sets STATE_MISSED bit if STATE_SCHED was already set
+		 * This was suggested by Alexander Duyck, as compiler
+		 * emits better code than :
+		 * if (val & NAPIF_STATE_SCHED)
+		 *     new |= NAPIF_STATE_MISSED;
+		 */
+		new |= (val & NAPIF_STATE_SCHED) / NAPIF_STATE_SCHED *
+						   NAPIF_STATE_MISSED;
+	} while (cmpxchg(&n->state, val, new) != val);
+
+	return !(val & NAPIF_STATE_SCHED);
+}
+EXPORT_SYMBOL(napi_schedule_prep);
+
+/**
  * __napi_schedule_irqoff - schedule for receive
  * @n: entry to schedule
  *
@@ -4943,7 +4976,7 @@ EXPORT_SYMBOL(__napi_complete);
 
 bool napi_complete_done(struct napi_struct *n, int work_done)
 {
-	unsigned long flags;
+	unsigned long flags, val, new;
 
 	/*
 	 * 1) Don't let napi dequeue from the cpu poll list
@@ -4967,14 +5000,33 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 		else
 			napi_gro_flush(n, false);
 	}
-	if (likely(list_empty(&n->poll_list))) {
-		WARN_ON_ONCE(!test_and_clear_bit(NAPI_STATE_SCHED, &n->state));
-	} else {
+	if (unlikely(!list_empty(&n->poll_list))) {
 		/* If n->poll_list is not empty, we need to mask irqs */
 		local_irq_save(flags);
-		__napi_complete(n);
+		list_del_init(&n->poll_list);
 		local_irq_restore(flags);
 	}
+
+	do {
+		val = READ_ONCE(n->state);
+
+		WARN_ON_ONCE(!(val & NAPIF_STATE_SCHED));
+
+		new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED);
+
+		/* If STATE_MISSED was set, leave STATE_SCHED set,
+		 * because we will call napi->poll() one more time.
+		 * This C code was suggested by Alexander Duyck to help gcc.
+		 */
+		new |= (val & NAPIF_STATE_MISSED) / NAPIF_STATE_MISSED *
+						    NAPIF_STATE_SCHED;
+	} while (cmpxchg(&n->state, val, new) != val);
+
+	if (unlikely(val & NAPIF_STATE_MISSED)) {
+		__napi_schedule(n);
+		return false;
+	}
+
 	return true;
 }
 EXPORT_SYMBOL(napi_complete_done);
@@ -5000,6 +5052,16 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock)
 {
 	int rc;
 
+	/* Busy polling means there is a high chance device driver hard irq
+	 * could not grab NAPI_STATE_SCHED, and that NAPI_STATE_MISSED was
+	 * set in napi_schedule_prep().
+	 * Since we are about to call napi->poll() once more, we can safely
+	 * clear NAPI_STATE_MISSED.
+	 *
+	 * Note: x86 could use a single "lock and ..." instruction
+	 * to perform these two clear_bit()
+	 */
+	clear_bit(NAPI_STATE_MISSED, &napi->state);
 	clear_bit(NAPI_STATE_IN_BUSY_POLL, &napi->state);
 
 	local_bh_disable();
@@ -5146,8 +5208,13 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer)
 	struct napi_struct *napi;
 
 	napi = container_of(timer, struct napi_struct, timer);
-	if (napi->gro_list)
-		napi_schedule(napi);
+
+	/* Note : we use a relaxed variant of napi_schedule_prep() not setting
+	 * NAPI_STATE_MISSED, since we do not react to a device IRQ.
+	 */
+	if (napi->gro_list && !napi_disable_pending(napi) &&
+	    !test_and_set_bit(NAPI_STATE_SCHED, &napi->state))
+		__napi_schedule_irqoff(napi);
 
 	return HRTIMER_NORESTART;
 }
-- 
2.1.0

Re: [PATCHES] Networking

[Thomas Backlund]

Den 25.03.2017 kl. 09:53, skrev David Miller:
>
> Please queue up the following bug fixes for v4.9 and v4.10 -stable,
> respectively.
>
> Thanks!
>

The net_49.mbox is messed up...

besided the network related patches, it seems to contain every stable 
patch from the 4.9.16 -> 4.9.17 update...

--
Thomas

Re: [PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 426 bytes --]

From: Thomas Backlund <tmb@mageia.org>
Date: Sat, 25 Mar 2017 11:26:13 +0200

> Den 25.03.2017 kl. 09:53, skrev David Miller:
>>
>> Please queue up the following bug fixes for v4.9 and v4.10 -stable,
>> respectively.
>>
>> Thanks!
>>
> 
> The net_49.mbox is messed up...
> 
> besided the network related patches, it seems to contain every stable
> patch from the 4.9.16 -> 4.9.17 update...

My bad, this one should be better:

[-- Attachment #2: net_49.mbox --]
[-- Type: Application/Octet-Stream, Size: 44435 bytes --]

From e5ae0e88159a2b6d27ac43690a6b31d88748f5f7 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Wed, 15 Mar 2017 18:10:47 +0200
Subject: [PATCH 01/18] net/openvswitch: Set the ipv6 source tunnel key address
 attribute correctly

[ Upstream commit 3d20f1f7bd575d147ffa75621fa560eea0aec690 ]

When dealing with ipv6 source tunnel key address attribute
(OVS_TUNNEL_KEY_ATTR_IPV6_SRC) we are wrongly setting the tunnel
dst ip, fix that.

Fixes: 6b26ba3a7d95 ('openvswitch: netlink attributes for IPv6 tunneling')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reported-by: Paul Blakey <paulb@mellanox.com>
Acked-by: Jiri Benc <jbenc@redhat.com>
Acked-by: Joe Stringer <joe@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/flow_netlink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index ae25ded..677d7cc 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -588,7 +588,7 @@ static int ip_tun_from_nlattr(const struct nlattr *attr,
 			ipv4 = true;
 			break;
 		case OVS_TUNNEL_KEY_ATTR_IPV6_SRC:
-			SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.dst,
+			SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.src,
 					nla_get_in6_addr(a), is_mask);
 			ipv6 = true;
 			break;
-- 
2.1.0


From aa56be0e5d1e26b4d8d4c38a26d521f305b1164f Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 15 Mar 2017 12:57:21 -0700
Subject: [PATCH 02/18] net: bcmgenet: Do not suspend PHY if Wake-on-LAN is
 enabled

[ Upstream commit 5371bbf4b295eea334ed453efa286afa2c3ccff3 ]

Suspending the PHY would be putting it in a low power state where it
may no longer allow us to do Wake-on-LAN.

Fixes: cc013fb48898 ("net: bcmgenet: correctly suspend and resume PHY device")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index a4e60e5..0975af2 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -3402,7 +3402,8 @@ static int bcmgenet_suspend(struct device *d)
 
 	bcmgenet_netif_stop(dev);
 
-	phy_suspend(priv->phydev);
+	if (!device_may_wakeup(d))
+		phy_suspend(priv->phydev);
 
 	netif_device_detach(dev);
 
@@ -3499,7 +3500,8 @@ static int bcmgenet_resume(struct device *d)
 
 	netif_device_attach(dev);
 
-	phy_resume(priv->phydev);
+	if (!device_may_wakeup(d))
+		phy_resume(priv->phydev);
 
 	if (priv->eee.eee_enabled)
 		bcmgenet_eee_enable_set(dev, true);
-- 
2.1.0


From b866d039dbcd9ab896c647a8bc2c423587ffd6fe Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 15 Mar 2017 13:21:28 -0700
Subject: [PATCH 03/18] net: properly release sk_frag.page

[ Upstream commit 22a0e18eac7a9e986fec76c60fa4a2926d1291e2 ]

I mistakenly added the code to release sk->sk_frag in
sk_common_release() instead of sk_destruct()

TCP sockets using sk->sk_allocation == GFP_ATOMIC do no call
sk_common_release() at close time, thus leaking one (order-3) page.

iSCSI is using such sockets.

Fixes: 5640f7685831 ("net: use a per task frag allocator")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index bc6543f..47809e9 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1437,6 +1437,11 @@ static void __sk_destruct(struct rcu_head *head)
 		pr_debug("%s: optmem leakage (%d bytes) detected\n",
 			 __func__, atomic_read(&sk->sk_omem_alloc));
 
+	if (sk->sk_frag.page) {
+		put_page(sk->sk_frag.page);
+		sk->sk_frag.page = NULL;
+	}
+
 	if (sk->sk_peer_cred)
 		put_cred(sk->sk_peer_cred);
 	put_pid(sk->sk_peer_pid);
@@ -2738,11 +2743,6 @@ void sk_common_release(struct sock *sk)
 
 	sk_refcnt_debug_release(sk);
 
-	if (sk->sk_frag.page) {
-		put_page(sk->sk_frag.page);
-		sk->sk_frag.page = NULL;
-	}
-
 	sock_put(sk);
 }
 EXPORT_SYMBOL(sk_common_release);
-- 
2.1.0


From 0562031233c4a386b1e6ee058c67612b569db94d Mon Sep 17 00:00:00 2001
From: "Lendacky, Thomas" <Thomas.Lendacky@amd.com>
Date: Wed, 15 Mar 2017 15:11:23 -0500
Subject: [PATCH 04/18] amd-xgbe: Fix jumbo MTU processing on newer hardware

[ Upstream commit 622c36f143fc9566ba49d7cec994c2da1182d9e2 ]

Newer hardware does not provide a cumulative payload length when multiple
descriptors are needed to handle the data. Once the MTU increases beyond
the size that can be handled by a single descriptor, the SKB does not get
built properly by the driver.

The driver will now calculate the size of the data buffers used by the
hardware.  The first buffer of the first descriptor is for packet headers
or packet headers and data when the headers can't be split. Subsequent
descriptors in a multi-descriptor chain will not use the first buffer. The
second buffer is used by all the descriptors in the chain for payload data.
Based on whether the driver is processing the first, intermediate, or last
descriptor it can calculate the buffer usage and build the SKB properly.

Tested and verified on both old and new hardware.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe-common.h |   6 +-
 drivers/net/ethernet/amd/xgbe/xgbe-dev.c    |  20 +++---
 drivers/net/ethernet/amd/xgbe/xgbe-drv.c    | 102 +++++++++++++++++-----------
 3 files changed, 78 insertions(+), 50 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
index bbef959..1592e1c 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
@@ -917,8 +917,8 @@
 #define RX_PACKET_ATTRIBUTES_CSUM_DONE_WIDTH	1
 #define RX_PACKET_ATTRIBUTES_VLAN_CTAG_INDEX	1
 #define RX_PACKET_ATTRIBUTES_VLAN_CTAG_WIDTH	1
-#define RX_PACKET_ATTRIBUTES_INCOMPLETE_INDEX	2
-#define RX_PACKET_ATTRIBUTES_INCOMPLETE_WIDTH	1
+#define RX_PACKET_ATTRIBUTES_LAST_INDEX		2
+#define RX_PACKET_ATTRIBUTES_LAST_WIDTH		1
 #define RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_INDEX	3
 #define RX_PACKET_ATTRIBUTES_CONTEXT_NEXT_WIDTH	1
 #define RX_PACKET_ATTRIBUTES_CONTEXT_INDEX	4
@@ -927,6 +927,8 @@
 #define RX_PACKET_ATTRIBUTES_RX_TSTAMP_WIDTH	1
 #define RX_PACKET_ATTRIBUTES_RSS_HASH_INDEX	6
 #define RX_PACKET_ATTRIBUTES_RSS_HASH_WIDTH	1
+#define RX_PACKET_ATTRIBUTES_FIRST_INDEX	7
+#define RX_PACKET_ATTRIBUTES_FIRST_WIDTH	1
 
 #define RX_NORMAL_DESC0_OVT_INDEX		0
 #define RX_NORMAL_DESC0_OVT_WIDTH		16
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
index 1babcc1..ca106d4 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
@@ -1721,10 +1721,15 @@ static int xgbe_dev_read(struct xgbe_channel *channel)
 
 	/* Get the header length */
 	if (XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, FD)) {
+		XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
+			       FIRST, 1);
 		rdata->rx.hdr_len = XGMAC_GET_BITS_LE(rdesc->desc2,
 						      RX_NORMAL_DESC2, HL);
 		if (rdata->rx.hdr_len)
 			pdata->ext_stats.rx_split_header_packets++;
+	} else {
+		XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
+			       FIRST, 0);
 	}
 
 	/* Get the RSS hash */
@@ -1747,19 +1752,16 @@ static int xgbe_dev_read(struct xgbe_channel *channel)
 		}
 	}
 
-	/* Get the packet length */
-	rdata->rx.len = XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, PL);
-
-	if (!XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, LD)) {
-		/* Not all the data has been transferred for this packet */
-		XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
-			       INCOMPLETE, 1);
+	/* Not all the data has been transferred for this packet */
+	if (!XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, LD))
 		return 0;
-	}
 
 	/* This is the last of the data for this packet */
 	XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
-		       INCOMPLETE, 0);
+		       LAST, 1);
+
+	/* Get the packet length */
+	rdata->rx.len = XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, PL);
 
 	/* Set checksum done indicator as appropriate */
 	if (netdev->features & NETIF_F_RXCSUM)
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 7f9216d..0f0f3014 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -1752,13 +1752,12 @@ static struct sk_buff *xgbe_create_skb(struct xgbe_prv_data *pdata,
 {
 	struct sk_buff *skb;
 	u8 *packet;
-	unsigned int copy_len;
 
 	skb = napi_alloc_skb(napi, rdata->rx.hdr.dma_len);
 	if (!skb)
 		return NULL;
 
-	/* Start with the header buffer which may contain just the header
+	/* Pull in the header buffer which may contain just the header
 	 * or the header plus data
 	 */
 	dma_sync_single_range_for_cpu(pdata->dev, rdata->rx.hdr.dma_base,
@@ -1767,30 +1766,49 @@ static struct sk_buff *xgbe_create_skb(struct xgbe_prv_data *pdata,
 
 	packet = page_address(rdata->rx.hdr.pa.pages) +
 		 rdata->rx.hdr.pa.pages_offset;
-	copy_len = (rdata->rx.hdr_len) ? rdata->rx.hdr_len : len;
-	copy_len = min(rdata->rx.hdr.dma_len, copy_len);
-	skb_copy_to_linear_data(skb, packet, copy_len);
-	skb_put(skb, copy_len);
-
-	len -= copy_len;
-	if (len) {
-		/* Add the remaining data as a frag */
-		dma_sync_single_range_for_cpu(pdata->dev,
-					      rdata->rx.buf.dma_base,
-					      rdata->rx.buf.dma_off,
-					      rdata->rx.buf.dma_len,
-					      DMA_FROM_DEVICE);
-
-		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
-				rdata->rx.buf.pa.pages,
-				rdata->rx.buf.pa.pages_offset,
-				len, rdata->rx.buf.dma_len);
-		rdata->rx.buf.pa.pages = NULL;
-	}
+	skb_copy_to_linear_data(skb, packet, len);
+	skb_put(skb, len);
 
 	return skb;
 }
 
+static unsigned int xgbe_rx_buf1_len(struct xgbe_ring_data *rdata,
+				     struct xgbe_packet_data *packet)
+{
+	/* Always zero if not the first descriptor */
+	if (!XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, FIRST))
+		return 0;
+
+	/* First descriptor with split header, return header length */
+	if (rdata->rx.hdr_len)
+		return rdata->rx.hdr_len;
+
+	/* First descriptor but not the last descriptor and no split header,
+	 * so the full buffer was used
+	 */
+	if (!XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, LAST))
+		return rdata->rx.hdr.dma_len;
+
+	/* First descriptor and last descriptor and no split header, so
+	 * calculate how much of the buffer was used
+	 */
+	return min_t(unsigned int, rdata->rx.hdr.dma_len, rdata->rx.len);
+}
+
+static unsigned int xgbe_rx_buf2_len(struct xgbe_ring_data *rdata,
+				     struct xgbe_packet_data *packet,
+				     unsigned int len)
+{
+	/* Always the full buffer if not the last descriptor */
+	if (!XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, LAST))
+		return rdata->rx.buf.dma_len;
+
+	/* Last descriptor so calculate how much of the buffer was used
+	 * for the last bit of data
+	 */
+	return rdata->rx.len - len;
+}
+
 static int xgbe_tx_poll(struct xgbe_channel *channel)
 {
 	struct xgbe_prv_data *pdata = channel->pdata;
@@ -1873,8 +1891,8 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
 	struct napi_struct *napi;
 	struct sk_buff *skb;
 	struct skb_shared_hwtstamps *hwtstamps;
-	unsigned int incomplete, error, context_next, context;
-	unsigned int len, rdesc_len, max_len;
+	unsigned int last, error, context_next, context;
+	unsigned int len, buf1_len, buf2_len, max_len;
 	unsigned int received = 0;
 	int packet_count = 0;
 
@@ -1884,7 +1902,7 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
 	if (!ring)
 		return 0;
 
-	incomplete = 0;
+	last = 0;
 	context_next = 0;
 
 	napi = (pdata->per_channel_irq) ? &channel->napi : &pdata->napi;
@@ -1918,9 +1936,8 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
 		received++;
 		ring->cur++;
 
-		incomplete = XGMAC_GET_BITS(packet->attributes,
-					    RX_PACKET_ATTRIBUTES,
-					    INCOMPLETE);
+		last = XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
+				      LAST);
 		context_next = XGMAC_GET_BITS(packet->attributes,
 					      RX_PACKET_ATTRIBUTES,
 					      CONTEXT_NEXT);
@@ -1929,7 +1946,7 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
 					 CONTEXT);
 
 		/* Earlier error, just drain the remaining data */
-		if ((incomplete || context_next) && error)
+		if ((!last || context_next) && error)
 			goto read_again;
 
 		if (error || packet->errors) {
@@ -1941,16 +1958,22 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
 		}
 
 		if (!context) {
-			/* Length is cumulative, get this descriptor's length */
-			rdesc_len = rdata->rx.len - len;
-			len += rdesc_len;
+			/* Get the data length in the descriptor buffers */
+			buf1_len = xgbe_rx_buf1_len(rdata, packet);
+			len += buf1_len;
+			buf2_len = xgbe_rx_buf2_len(rdata, packet, len);
+			len += buf2_len;
 
-			if (rdesc_len && !skb) {
+			if (!skb) {
 				skb = xgbe_create_skb(pdata, napi, rdata,
-						      rdesc_len);
-				if (!skb)
+						      buf1_len);
+				if (!skb) {
 					error = 1;
-			} else if (rdesc_len) {
+					goto skip_data;
+				}
+			}
+
+			if (buf2_len) {
 				dma_sync_single_range_for_cpu(pdata->dev,
 							rdata->rx.buf.dma_base,
 							rdata->rx.buf.dma_off,
@@ -1960,13 +1983,14 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
 				skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
 						rdata->rx.buf.pa.pages,
 						rdata->rx.buf.pa.pages_offset,
-						rdesc_len,
+						buf2_len,
 						rdata->rx.buf.dma_len);
 				rdata->rx.buf.pa.pages = NULL;
 			}
 		}
 
-		if (incomplete || context_next)
+skip_data:
+		if (!last || context_next)
 			goto read_again;
 
 		if (!skb)
@@ -2024,7 +2048,7 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
 	}
 
 	/* Check if we need to save state before leaving */
-	if (received && (incomplete || context_next)) {
+	if (received && (!last || context_next)) {
 		rdata = XGBE_GET_DESC_DATA(ring, ring->cur);
 		rdata->state_saved = 1;
 		rdata->state.skb = skb;
-- 
2.1.0


From cfc6abd09f9d4f49d8c85508b8e4627a92707cb8 Mon Sep 17 00:00:00 2001
From: Kris Murphy <kriskend@linux.vnet.ibm.com>
Date: Thu, 16 Mar 2017 10:51:28 -0500
Subject: [PATCH 05/18] openvswitch: Add missing case OVS_TUNNEL_KEY_ATTR_PAD

[ Upstream commit 8f3dbfd79ed9ef9770305a7cc4e13dfd31ad2cd0 ]

Added a case for OVS_TUNNEL_KEY_ATTR_PAD to the switch statement
in ip_tun_from_nlattr in order to prevent the default case
returning an error.

Fixes: b46f6ded906e ("libnl: nla_put_be64(): align on a 64-bit area")
Signed-off-by: Kris Murphy <kriskend@linux.vnet.ibm.com>
Acked-by: Joe Stringer <joe@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/flow_netlink.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 677d7cc..0792541 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -649,6 +649,8 @@ static int ip_tun_from_nlattr(const struct nlattr *attr,
 			tun_flags |= TUNNEL_VXLAN_OPT;
 			opts_type = type;
 			break;
+		case OVS_TUNNEL_KEY_ATTR_PAD:
+			break;
 		default:
 			OVS_NLERR(log, "Unknown IP tunnel attribute %d",
 				  type);
-- 
2.1.0


From 09098344a4ac49c9b25f90d53579adb07caa3970 Mon Sep 17 00:00:00 2001
From: Andrey Ulanov <andreyu@google.com>
Date: Tue, 14 Mar 2017 20:16:42 -0700
Subject: [PATCH 06/18] net: unix: properly re-increment inflight counter of GC
 discarded candidates

[ Upstream commit 7df9c24625b9981779afb8fcdbe2bb4765e61147 ]

Dmitry has reported that a BUG_ON() condition in unix_notinflight()
may be triggered by a simple code that forwards unix socket in an
SCM_RIGHTS message.
That is caused by incorrect unix socket GC implementation in unix_gc().

The GC first collects list of candidates, then (a) decrements their
"children's" inflight counter, (b) checks which inflight counters are
now 0, and then (c) increments all inflight counters back.
(a) and (c) are done by calling scan_children() with inc_inflight or
dec_inflight as the second argument.

Commit 6209344f5a37 ("net: unix: fix inflight counting bug in garbage
collector") changed scan_children() such that it no longer considers
sockets that do not have UNIX_GC_CANDIDATE flag. It also added a block
of code that that unsets this flag _before_ invoking
scan_children(, dec_iflight, ). This may lead to incorrect inflight
counters for some sockets.

This change fixes this bug by changing order of operations:
UNIX_GC_CANDIDATE is now unset only after all inflight counters are
restored to the original state.

  kernel BUG at net/unix/garbage.c:149!
  RIP: 0010:[<ffffffff8717ebf4>]  [<ffffffff8717ebf4>]
  unix_notinflight+0x3b4/0x490 net/unix/garbage.c:149
  Call Trace:
   [<ffffffff8716cfbf>] unix_detach_fds.isra.19+0xff/0x170 net/unix/af_unix.c:1487
   [<ffffffff8716f6a9>] unix_destruct_scm+0xf9/0x210 net/unix/af_unix.c:1496
   [<ffffffff86a90a01>] skb_release_head_state+0x101/0x200 net/core/skbuff.c:655
   [<ffffffff86a9808a>] skb_release_all+0x1a/0x60 net/core/skbuff.c:668
   [<ffffffff86a980ea>] __kfree_skb+0x1a/0x30 net/core/skbuff.c:684
   [<ffffffff86a98284>] kfree_skb+0x184/0x570 net/core/skbuff.c:705
   [<ffffffff871789d5>] unix_release_sock+0x5b5/0xbd0 net/unix/af_unix.c:559
   [<ffffffff87179039>] unix_release+0x49/0x90 net/unix/af_unix.c:836
   [<ffffffff86a694b2>] sock_release+0x92/0x1f0 net/socket.c:570
   [<ffffffff86a6962b>] sock_close+0x1b/0x20 net/socket.c:1017
   [<ffffffff81a76b8e>] __fput+0x34e/0x910 fs/file_table.c:208
   [<ffffffff81a771da>] ____fput+0x1a/0x20 fs/file_table.c:244
   [<ffffffff81483ab0>] task_work_run+0x1a0/0x280 kernel/task_work.c:116
   [<     inline     >] exit_task_work include/linux/task_work.h:21
   [<ffffffff8141287a>] do_exit+0x183a/0x2640 kernel/exit.c:828
   [<ffffffff8141383e>] do_group_exit+0x14e/0x420 kernel/exit.c:931
   [<ffffffff814429d3>] get_signal+0x663/0x1880 kernel/signal.c:2307
   [<ffffffff81239b45>] do_signal+0xc5/0x2190 arch/x86/kernel/signal.c:807
   [<ffffffff8100666a>] exit_to_usermode_loop+0x1ea/0x2d0
  arch/x86/entry/common.c:156
   [<     inline     >] prepare_exit_to_usermode arch/x86/entry/common.c:190
   [<ffffffff81009693>] syscall_return_slowpath+0x4d3/0x570
  arch/x86/entry/common.c:259
   [<ffffffff881478e6>] entry_SYSCALL_64_fastpath+0xc4/0xc6

Link: https://lkml.org/lkml/2017/3/6/252
Signed-off-by: Andrey Ulanov <andreyu@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Fixes: 6209344 ("net: unix: fix inflight counting bug in garbage collector")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/garbage.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 6a0d485..c36757e 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -146,6 +146,7 @@ void unix_notinflight(struct user_struct *user, struct file *fp)
 	if (s) {
 		struct unix_sock *u = unix_sk(s);
 
+		BUG_ON(!atomic_long_read(&u->inflight));
 		BUG_ON(list_empty(&u->link));
 
 		if (atomic_long_dec_and_test(&u->inflight))
@@ -341,6 +342,14 @@ void unix_gc(void)
 	}
 	list_del(&cursor);
 
+	/* Now gc_candidates contains only garbage.  Restore original
+	 * inflight counters for these as well, and remove the skbuffs
+	 * which are creating the cycle(s).
+	 */
+	skb_queue_head_init(&hitlist);
+	list_for_each_entry(u, &gc_candidates, link)
+		scan_children(&u->sk, inc_inflight, &hitlist);
+
 	/* not_cycle_list contains those sockets which do not make up a
 	 * cycle.  Restore these to the inflight list.
 	 */
@@ -350,14 +359,6 @@ void unix_gc(void)
 		list_move_tail(&u->link, &gc_inflight_list);
 	}
 
-	/* Now gc_candidates contains only garbage.  Restore original
-	 * inflight counters for these as well, and remove the skbuffs
-	 * which are creating the cycle(s).
-	 */
-	skb_queue_head_init(&hitlist);
-	list_for_each_entry(u, &gc_candidates, link)
-	scan_children(&u->sk, inc_inflight, &hitlist);
-
 	spin_unlock(&unix_gc_lock);
 
 	/* Here we are. Hitlist is filled. Die. */
-- 
2.1.0


From c571bf29d2f2ace7c56acc4b5a0a0ebb1ba0e17e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Fri, 17 Mar 2017 17:20:48 +0100
Subject: [PATCH 07/18] qmi_wwan: add Dell DW5811e
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 6bd845d1cf98b45c634baacb8381436dad3c2dd0 ]

This is a Dell branded Sierra Wireless EM7455. It is operating in
MBIM mode by default, but can be configured to provide two QMI/RMNET
functions.

Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 24d5272..0d519a9 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -924,6 +924,8 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x413c, 0x81a9, 8)},	/* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */
 	{QMI_FIXED_INTF(0x413c, 0x81b1, 8)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card */
 	{QMI_FIXED_INTF(0x413c, 0x81b3, 8)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */
+	{QMI_FIXED_INTF(0x413c, 0x81b6, 8)},	/* Dell Wireless 5811e */
+	{QMI_FIXED_INTF(0x413c, 0x81b6, 10)},	/* Dell Wireless 5811e */
 	{QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)},	/* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */
 	{QMI_FIXED_INTF(0x22de, 0x9061, 3)},	/* WeTelecom WPD-600N */
 	{QMI_FIXED_INTF(0x1e0e, 0x9001, 5)},	/* SIMCom 7230E */
-- 
2.1.0


From 6ae15b2ce2370bdde6a928dfb19dbe1b924b2ae3 Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Fri, 17 Mar 2017 16:07:11 -0700
Subject: [PATCH 08/18] net: vrf: Reset rt6i_idev in local dst after put

[ Upstream commit 3dc857f0e8fc22610a59cbb346ba62c6e921863f ]

The VRF driver takes a reference to the inet6_dev on the VRF device for
its rt6_local dst when handling local traffic through the VRF device as
a loopback. When the device is deleted the driver does a put on the idev
but does not reset rt6i_idev in the rt6_info struct. When the dst is
destroyed, dst_destroy calls ip6_dst_destroy which does a second put for
what is essentially the same reference causing it to be prematurely freed.
Reset rt6i_idev after the put in the vrf driver.

Fixes: b4869aa2f881e ("net: vrf: ipv6 support for local traffic to
                       local addresses")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index bc744ac..a2afb8e 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -467,8 +467,10 @@ static void vrf_rt6_release(struct net_device *dev, struct net_vrf *vrf)
 	}
 
 	if (rt6_local) {
-		if (rt6_local->rt6i_idev)
+		if (rt6_local->rt6i_idev) {
 			in6_dev_put(rt6_local->rt6i_idev);
+			rt6_local->rt6i_idev = NULL;
+		}
 
 		dst = &rt6_local->dst;
 		dev_put(dst->dev);
-- 
2.1.0


From 87b90df38b028f79231a5ff1a1afe31ae22e41ac Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Tue, 21 Mar 2017 15:59:12 +0200
Subject: [PATCH 09/18] net/mlx5: Add missing entries for set/query rate limit
 commands

[ Upstream commit 1f30a86c58093046dc3e49c23d2618894e098f7a ]

The switch cases for the rate limit set and query commands were
missing, which could get us wrong under fw error or driver reset
flow, fix that.

Fixes: 1466cc5b23d1 ('net/mlx5: Rate limit tables support')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Hadar Hen Zion <hadarh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index bfe410e..3f51a44 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -367,6 +367,8 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_QUERY_VPORT_COUNTER:
 	case MLX5_CMD_OP_ALLOC_Q_COUNTER:
 	case MLX5_CMD_OP_QUERY_Q_COUNTER:
+	case MLX5_CMD_OP_SET_RATE_LIMIT:
+	case MLX5_CMD_OP_QUERY_RATE_LIMIT:
 	case MLX5_CMD_OP_ALLOC_PD:
 	case MLX5_CMD_OP_ALLOC_UAR:
 	case MLX5_CMD_OP_CONFIG_INT_MODERATION:
@@ -500,6 +502,8 @@ const char *mlx5_command_str(int command)
 	MLX5_COMMAND_STR_CASE(ALLOC_Q_COUNTER);
 	MLX5_COMMAND_STR_CASE(DEALLOC_Q_COUNTER);
 	MLX5_COMMAND_STR_CASE(QUERY_Q_COUNTER);
+	MLX5_COMMAND_STR_CASE(SET_RATE_LIMIT);
+	MLX5_COMMAND_STR_CASE(QUERY_RATE_LIMIT);
 	MLX5_COMMAND_STR_CASE(ALLOC_PD);
 	MLX5_COMMAND_STR_CASE(DEALLOC_PD);
 	MLX5_COMMAND_STR_CASE(ALLOC_UAR);
-- 
2.1.0


From c746a315ef1f7a87eef383ed0ba74fd74d3be034 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Tue, 21 Mar 2017 15:59:15 +0200
Subject: [PATCH 10/18] net/mlx5e: Use the proper UAPI values when offloading
 TC vlan actions

[ Upstream commit 09c91ddf2cd33489c2c14edfef43ae38d412888e ]

Currently we use the non UAPI values and we miss erring on
the modify action which is not supported, fix that.

Fixes: 8b32580df1cb ('net/mlx5e: Add TC vlan action for SRIOV offloads')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reported-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index a543ea6..3fd471a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -427,14 +427,16 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 		}
 
 		if (is_tcf_vlan(a)) {
-			if (tcf_vlan_action(a) == VLAN_F_POP) {
+			if (tcf_vlan_action(a) == TCA_VLAN_ACT_POP) {
 				attr->action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP;
-			} else if (tcf_vlan_action(a) == VLAN_F_PUSH) {
+			} else if (tcf_vlan_action(a) == TCA_VLAN_ACT_PUSH) {
 				if (tcf_vlan_push_proto(a) != htons(ETH_P_8021Q))
 					return -EOPNOTSUPP;
 
 				attr->action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH;
 				attr->vlan = tcf_vlan_push_vid(a);
+			} else { /* action is TCA_VLAN_ACT_MODIFY */
+				return -EOPNOTSUPP;
 			}
 			continue;
 		}
-- 
2.1.0


From 23f6003af4698c238e44f1f4201a61c3417f8808 Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@mellanox.com>
Date: Tue, 21 Mar 2017 15:59:17 +0200
Subject: [PATCH 11/18] net/mlx5: Increase number of max QPs in default profile

[ Upstream commit 5f40b4ed975c26016cf41953b7510fe90718e21c ]

With ConnectX-4 sharing SRQs from the same space as QPs, we hit a
limit preventing some applications to allocate needed QPs amount.
Double the size to 256K.

Fixes: e126ba97dba9e ('mlx5: Add driver for Mellanox Connect-IB adapters')
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 0c9ef87..7a196a0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -87,7 +87,7 @@ static struct mlx5_profile profile[] = {
 	[2] = {
 		.mask		= MLX5_PROF_MASK_QP_SIZE |
 				  MLX5_PROF_MASK_MR_CACHE,
-		.log_max_qp	= 17,
+		.log_max_qp	= 18,
 		.mr_cache[0]	= {
 			.size	= 500,
 			.limit	= 250
-- 
2.1.0


From 720b30c1738a7b4a4f603dd7895d335a890c4d17 Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Tue, 21 Mar 2017 15:59:18 +0200
Subject: [PATCH 12/18] net/mlx5e: Count GSO packets correctly

[ Upstream commit d3a4e4da54c7adb420d5f48e89be913b14bdeff1 ]

TX packets statistics ('tx_packets' counter) used to count GSO packets
as one, even though it contains multiple segments.
This patch will increment the counter by the number of segments, and
align the driver with the behavior of other drivers in the stack.

Note that no information is lost in this patch due to 'tx_tso_packets'
counter existence.

Before, ethtool showed:
$ ethtool -S ens6 | egrep "tx_packets|tx_tso_packets"
     tx_packets: 61340
     tx_tso_packets: 60954
     tx_packets_phy: 2451115

Now, we will see the more logical statistics:
$ ethtool -S ens6 | egrep "tx_packets|tx_tso_packets"
     tx_packets: 2451115
     tx_tso_packets: 60954
     tx_packets_phy: 2451115

Fixes: e586b3b0baee ("net/mlx5: Ethernet Datapath files")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Cc: kernel-team@fb.com
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index cfb6837..5743110 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -272,15 +272,18 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
 			sq->stats.tso_bytes += skb->len - ihs;
 		}
 
+		sq->stats.packets += skb_shinfo(skb)->gso_segs;
 		num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs;
 	} else {
 		bf = sq->bf_budget &&
 		     !skb->xmit_more &&
 		     !skb_shinfo(skb)->nr_frags;
 		ihs = mlx5e_get_inline_hdr_size(sq, skb, bf);
+		sq->stats.packets++;
 		num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN);
 	}
 
+	sq->stats.bytes += num_bytes;
 	wi->num_bytes = num_bytes;
 
 	if (skb_vlan_tag_present(skb)) {
@@ -377,8 +380,6 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
 	if (bf)
 		sq->bf_budget--;
 
-	sq->stats.packets++;
-	sq->stats.bytes += num_bytes;
 	return NETDEV_TX_OK;
 
 dma_unmap_wqe_err:
-- 
2.1.0


From cacf18ca47457cd517097521cd51876f9199255d Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Tue, 21 Mar 2017 15:59:19 +0200
Subject: [PATCH 13/18] net/mlx5e: Count LRO packets correctly

[ Upstream commit 8ab7e2ae15d84ba758b2c8c6f4075722e9bd2a08 ]

RX packets statistics ('rx_packets' counter) used to count LRO packets
as one, even though it contains multiple segments.
This patch will increment the counter by the number of segments, and
align the driver with the behavior of other drivers in the stack.

Note that no information is lost in this patch due to 'rx_lro_packets'
counter existence.

Before, ethtool showed:
$ ethtool -S ens6 | egrep "rx_packets|rx_lro_packets"
     rx_packets: 435277
     rx_lro_packets: 35847
     rx_packets_phy: 1935066

Now, we will see the more logical statistics:
$ ethtool -S ens6 | egrep "rx_packets|rx_lro_packets"
     rx_packets: 1935066
     rx_lro_packets: 35847
     rx_packets_phy: 1935066

Fixes: e586b3b0baee ("net/mlx5: Ethernet Datapath files")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Cc: kernel-team@fb.com
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 796bdf0..7309ae3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -602,6 +602,10 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
 	if (lro_num_seg > 1) {
 		mlx5e_lro_update_hdr(skb, cqe, cqe_bcnt);
 		skb_shinfo(skb)->gso_size = DIV_ROUND_UP(cqe_bcnt, lro_num_seg);
+		/* Subtract one since we already counted this as one
+		 * "regular" packet in mlx5e_complete_rx_cqe()
+		 */
+		rq->stats.packets += lro_num_seg - 1;
 		rq->stats.lro_packets++;
 		rq->stats.lro_bytes += cqe_bcnt;
 	}
-- 
2.1.0


From 249cbba744191c0d511c6ee9a65d50404dac155f Mon Sep 17 00:00:00 2001
From: Alexander Potapenko <glider@google.com>
Date: Tue, 21 Mar 2017 17:14:27 +0100
Subject: [PATCH 14/18] ipv6: make sure to initialize sockc.tsflags before
 first use

[ Upstream commit d515684d78148884d5fc425ba904c50f03844020 ]

In the case udp_sk(sk)->pending is AF_INET6, udpv6_sendmsg() would
jump to do_append_data, skipping the initialization of sockc.tsflags.
Fix the problem by moving sockc.tsflags initialization earlier.

The bug was detected with KMSAN.

Fixes: c14ac9451c34 ("sock: enable timestamping using control messages")
Signed-off-by: Alexander Potapenko <glider@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/udp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index e4a8000..40a289f 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1037,6 +1037,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	ipc6.hlimit = -1;
 	ipc6.tclass = -1;
 	ipc6.dontfrag = -1;
+	sockc.tsflags = sk->sk_tsflags;
 
 	/* destination address check */
 	if (sin6) {
@@ -1156,7 +1157,6 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
 
 	fl6.flowi6_mark = sk->sk_mark;
-	sockc.tsflags = sk->sk_tsflags;
 
 	if (msg->msg_controllen) {
 		opt = &opt_space;
-- 
2.1.0


From 42dffca1a3effc010545650514ecfa3911a365fb Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Tue, 21 Mar 2017 14:01:06 -0700
Subject: [PATCH 15/18] net: bcmgenet: remove bcmgenet_internal_phy_setup()

[ Upstream commit 31739eae738ccbe8b9d627c3f2251017ca03f4d2 ]

Commit 6ac3ce8295e6 ("net: bcmgenet: Remove excessive PHY reset")
removed the bcmgenet_mii_reset() function from bcmgenet_power_up() and
bcmgenet_internal_phy_setup() functions.  In so doing it broke the reset
of the internal PHY devices used by the GENETv1-GENETv3 which required
this reset before the UniMAC was enabled.  It also broke the internal
GPHY devices used by the GENETv4 because the config_init that installed
the AFE workaround was no longer occurring after the reset of the GPHY
performed by bcmgenet_phy_power_set() in bcmgenet_internal_phy_setup().
In addition the code in bcmgenet_internal_phy_setup() related to the
"enable APD" comment goes with the bcmgenet_mii_reset() so it should
have also been removed.

Commit bd4060a6108b ("net: bcmgenet: Power on integrated GPHY in
bcmgenet_power_up()") moved the bcmgenet_phy_power_set() call to the
bcmgenet_power_up() function, but failed to remove it from the
bcmgenet_internal_phy_setup() function.  Had it done so, the
bcmgenet_internal_phy_setup() function would have been empty and could
have been removed at that time.

Commit 5dbebbb44a6a ("net: bcmgenet: Software reset EPHY after power on")
was submitted to correct the functional problems introduced by
commit 6ac3ce8295e6 ("net: bcmgenet: Remove excessive PHY reset"). It
was included in v4.4 and made available on 4.3-stable. Unfortunately,
it didn't fully revert the commit because this bcmgenet_mii_reset()
doesn't apply the soft reset to the internal GPHY used by GENETv4 like
the previous one did. This prevents the restoration of the AFE work-
arounds for internal GPHY devices after the bcmgenet_phy_power_set() in
bcmgenet_internal_phy_setup().

This commit takes the alternate approach of removing the unnecessary
bcmgenet_internal_phy_setup() function which shouldn't have been in v4.3
so that when bcmgenet_mii_reset() was restored it should have only gone
into bcmgenet_power_up().  This will avoid the problems while also
removing the redundancy (and hopefully some of the confusion).

Fixes: 6ac3ce8295e6 ("net: bcmgenet: Remove excessive PHY reset")
Signed-off-by: Doug Berger <opendmb@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmmii.c | 15 ---------------
 1 file changed, 15 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index e876076..2f92819 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -220,20 +220,6 @@ void bcmgenet_phy_power_set(struct net_device *dev, bool enable)
 	udelay(60);
 }
 
-static void bcmgenet_internal_phy_setup(struct net_device *dev)
-{
-	struct bcmgenet_priv *priv = netdev_priv(dev);
-	u32 reg;
-
-	/* Power up PHY */
-	bcmgenet_phy_power_set(dev, true);
-	/* enable APD */
-	reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);
-	reg |= EXT_PWR_DN_EN_LD;
-	bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
-	bcmgenet_mii_reset(dev);
-}
-
 static void bcmgenet_moca_phy_setup(struct bcmgenet_priv *priv)
 {
 	u32 reg;
@@ -281,7 +267,6 @@ int bcmgenet_mii_config(struct net_device *dev)
 
 		if (priv->internal_phy) {
 			phy_name = "internal PHY";
-			bcmgenet_internal_phy_setup(dev);
 		} else if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) {
 			phy_name = "MoCA";
 			bcmgenet_moca_phy_setup(priv);
-- 
2.1.0


From 72e4f3eb00ac88a9643ed20f0c408ee392c96310 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 21 Mar 2017 19:22:28 -0700
Subject: [PATCH 16/18] ipv4: provide stronger user input validation in
 nl_fib_input()

[ Upstream commit c64c0b3cac4c5b8cb093727d2c19743ea3965c0b ]

Alexander reported a KMSAN splat caused by reads of uninitialized
field (tb_id_in) from user provided struct fib_result_nl

It turns out nl_fib_input() sanity tests on user input is a bit
wrong :

User can pretend nlh->nlmsg_len is big enough, but provide
at sendmsg() time a too small buffer.

Reported-by: Alexander Potapenko <glider@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_frontend.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 5b03d7f..6789e48 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1081,7 +1081,8 @@ static void nl_fib_input(struct sk_buff *skb)
 
 	net = sock_net(skb->sk);
 	nlh = nlmsg_hdr(skb);
-	if (skb->len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len ||
+	if (skb->len < nlmsg_total_size(sizeof(*frn)) ||
+	    skb->len < nlh->nlmsg_len ||
 	    nlmsg_len(nlh) < sizeof(*frn))
 		return;
 
-- 
2.1.0


From b4e900e8510b8232edc917ac3fc7279100d819de Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 22 Mar 2017 13:08:08 +0100
Subject: [PATCH 17/18] socket, bpf: fix sk_filter use after free in
 sk_clone_lock

[ Upstream commit a97e50cc4cb67e1e7bff56f6b41cda62ca832336 ]

In sk_clone_lock(), we create a new socket and inherit most of the
parent's members via sock_copy() which memcpy()'s various sections.
Now, in case the parent socket had a BPF socket filter attached,
then newsk->sk_filter points to the same instance as the original
sk->sk_filter.

sk_filter_charge() is then called on the newsk->sk_filter to take a
reference and should that fail due to hitting max optmem, we bail
out and release the newsk instance.

The issue is that commit 278571baca2a ("net: filter: simplify socket
charging") wrongly combined the dismantle path with the failure path
of xfrm_sk_clone_policy(). This means, even when charging failed, we
call sk_free_unlock_clone() on the newsk, which then still points to
the same sk_filter as the original sk.

Thus, sk_free_unlock_clone() calls into __sk_destruct() eventually
where it tests for present sk_filter and calls sk_filter_uncharge()
on it, which potentially lets sk_omem_alloc wrap around and releases
the eBPF prog and sk_filter structure from the (still intact) parent.

Fix it by making sure that when sk_filter_charge() failed, we reset
newsk->sk_filter back to NULL before passing to sk_free_unlock_clone(),
so that we don't mess with the parents sk_filter.

Only if xfrm_sk_clone_policy() fails, we did reach the point where
either the parent's filter was NULL and as a result newsk's as well
or where we previously had a successful sk_filter_charge(), thus for
that case, we do need sk_filter_uncharge() to release the prior taken
reference on sk_filter.

Fixes: 278571baca2a ("net: filter: simplify socket charging")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/core/sock.c b/net/core/sock.c
index 47809e9..470a204 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1538,6 +1538,12 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 			is_charged = sk_filter_charge(newsk, filter);
 
 		if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) {
+			/* We need to make sure that we don't uncharge the new
+			 * socket if we couldn't charge it in the first place
+			 * as otherwise we uncharge the parent's filter.
+			 */
+			if (!is_charged)
+				RCU_INIT_POINTER(newsk->sk_filter, NULL);
 			/* It is still raw copy of parent, so invalidate
 			 * destructor and make plain sk_free() */
 			newsk->sk_destruct = NULL;
-- 
2.1.0


From c4ebbb059048c45ac599ad72c8b5a4afbd69e94a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 22 Mar 2017 08:10:21 -0700
Subject: [PATCH 18/18] tcp: initialize icsk_ack.lrcvtime at session start time

[ Upstream commit 15bb7745e94a665caf42bfaabf0ce062845b533b ]

icsk_ack.lrcvtime has a 0 value at socket creation time.

tcpi_last_data_recv can have bogus value if no payload is ever received.

This patch initializes icsk_ack.lrcvtime for active sessions
in tcp_finish_connect(), and for passive sessions in
tcp_create_openreq_child()

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c     | 2 +-
 net/ipv4/tcp_minisocks.c | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index ce42ded..7727ffe 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5571,6 +5571,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
 	tcp_set_state(sk, TCP_ESTABLISHED);
+	icsk->icsk_ack.lrcvtime = tcp_time_stamp;
 
 	if (skb) {
 		icsk->icsk_af_ops->sk_rx_dst_set(sk, skb);
@@ -5789,7 +5790,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 			 * to stand against the temptation 8)     --ANK
 			 */
 			inet_csk_schedule_ack(sk);
-			icsk->icsk_ack.lrcvtime = tcp_time_stamp;
 			tcp_enter_quickack_mode(sk);
 			inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
 						  TCP_DELACK_MAX, TCP_RTO_MAX);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 6234eba..8615a6b 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -466,6 +466,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 		newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
 		minmax_reset(&newtp->rtt_min, tcp_time_stamp, ~0U);
 		newicsk->icsk_rto = TCP_TIMEOUT_INIT;
+		newicsk->icsk_ack.lrcvtime = tcp_time_stamp;
 
 		newtp->packets_out = 0;
 		newtp->retrans_out = 0;
-- 
2.1.0

Re: [PATCHES] Networking

[Thomas Backlund]

Den 25.03.2017 kl. 19:38, skrev David Miller:
> From: Thomas Backlund <tmb@mageia.org>
> Date: Sat, 25 Mar 2017 11:26:13 +0200
>
>> Den 25.03.2017 kl. 09:53, skrev David Miller:
>>> Please queue up the following bug fixes for v4.9 and v4.10 -stable,
>>> respectively.
>>>
>>> Thanks!
>>>
>> The net_49.mbox is messed up...
>>
>> besided the network related patches, it seems to contain every stable
>> patch from the 4.9.16 -> 4.9.17 update...
> My bad, this one should be better:

That works, thanks!

--
Thomas

Re: [PATCHES] Networking

[Greg KH]

On Sat, Mar 25, 2017 at 10:38:59AM -0700, David Miller wrote:
> From: Thomas Backlund <tmb@mageia.org>
> Date: Sat, 25 Mar 2017 11:26:13 +0200
> 
> > Den 25.03.2017 kl. 09:53, skrev David Miller:
> >>
> >> Please queue up the following bug fixes for v4.9 and v4.10 -stable,
> >> respectively.
> >>
> >> Thanks!
> >>
> > 
> > The net_49.mbox is messed up...
> > 
> > besided the network related patches, it seems to contain every stable
> > patch from the 4.9.16 -> 4.9.17 update...
> 
> My bad, this one should be better:


Thanks for this, and the 4.10 mbox, all now applied.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 103 bytes --]


Please queue up the following networking bug fixes for v4.9
and v4.10 -stable, respectively.

Thanks!

[-- Attachment #2: net_49.mbox --]
[-- Type: Application/Octet-Stream, Size: 80505 bytes --]

From f1452c1d6f47940ab30dd6d628d877da51a5f660 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 23 Mar 2017 12:39:21 -0700
Subject: [PATCH 01/33] net: neigh: guard against NULL solicit() method

[ Upstream commit 48481c8fa16410ffa45939b13b6c53c2ca609e5f ]

Dmitry posted a nice reproducer of a bug triggering in neigh_probe()
when dereferencing a NULL neigh->ops->solicit method.

This can happen for arp_direct_ops/ndisc_direct_ops and similar,
which can be used for NUD_NOARP neighbours (created when dev->header_ops
is NULL). Admin can then force changing nud_state to some other state
that would fire neigh timer.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 9901e5b..f45f619 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -859,7 +859,8 @@ static void neigh_probe(struct neighbour *neigh)
 	if (skb)
 		skb = skb_clone(skb, GFP_ATOMIC);
 	write_unlock(&neigh->lock);
-	neigh->ops->solicit(neigh, skb);
+	if (neigh->ops->solicit)
+		neigh->ops->solicit(neigh, skb);
 	atomic_inc(&neigh->probes);
 	kfree_skb(skb);
 }
-- 
2.4.11


From 7f973d6b03b13f28fa42894574bbb9b4dbbedd1b Mon Sep 17 00:00:00 2001
From: Nathan Sullivan <nathan.sullivan@ni.com>
Date: Wed, 22 Mar 2017 15:27:01 -0500
Subject: [PATCH 02/33] net: phy: handle state correctly in phy_stop_machine

[ Upstream commit 49d52e8108a21749dc2114b924c907db43358984 ]

If the PHY is halted on stop, then do not set the state to PHY_UP.  This
ensures the phy will be restarted later in phy_start when the machine is
started again.

Fixes: 00db8189d984 ("This patch adds a PHY Abstraction Layer to the Linux Kernel, enabling ethernet drivers to remain as ignorant as is reasonable of the connected PHY's design and operation details.")
Signed-off-by: Nathan Sullivan <nathan.sullivan@ni.com>
Signed-off-by: Brad Mouring <brad.mouring@ni.com>
Acked-by: Xander Huff <xander.huff@ni.com>
Acked-by: Kyle Roeschley <kyle.roeschley@ni.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 201ffa5..56fe169 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -639,7 +639,7 @@ void phy_stop_machine(struct phy_device *phydev)
 	cancel_delayed_work_sync(&phydev->state_queue);
 
 	mutex_lock(&phydev->lock);
-	if (phydev->state > PHY_UP)
+	if (phydev->state > PHY_UP && phydev->state != PHY_HALTED)
 		phydev->state = PHY_UP;
 	mutex_unlock(&phydev->lock);
 }
-- 
2.4.11


From 0c07deb028a336d09f50723016cb55d6449f6675 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Thu, 23 Mar 2017 11:03:31 -0700
Subject: [PATCH 03/33] kcm: return immediately after copy_from_user() failure

[ Upstream commit a80db69e47d764bbcaf2fec54b1f308925e7c490 ]

There is no reason to continue after a copy_from_user()
failure.

Fixes: ab7ac4eb9832 ("kcm: Kernel Connection Multiplexor module")
Cc: Tom Herbert <tom@herbertland.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/kcm/kcmsock.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index a646f34..fecad10 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -1685,7 +1685,7 @@ static int kcm_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 		struct kcm_attach info;
 
 		if (copy_from_user(&info, (void __user *)arg, sizeof(info)))
-			err = -EFAULT;
+			return -EFAULT;
 
 		err = kcm_attach_ioctl(sock, &info);
 
@@ -1695,7 +1695,7 @@ static int kcm_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 		struct kcm_unattach info;
 
 		if (copy_from_user(&info, (void __user *)arg, sizeof(info)))
-			err = -EFAULT;
+			return -EFAULT;
 
 		err = kcm_unattach_ioctl(sock, &info);
 
@@ -1706,7 +1706,7 @@ static int kcm_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 		struct socket *newsock = NULL;
 
 		if (copy_from_user(&info, (void __user *)arg, sizeof(info)))
-			err = -EFAULT;
+			return -EFAULT;
 
 		err = kcm_clone(sock, &info, &newsock);
 
-- 
2.4.11


From 31e43fb392e309019fc6ceaadc22aaab4188b195 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 24 Mar 2017 19:36:13 -0700
Subject: [PATCH 04/33] ping: implement proper locking

[ Upstream commit 43a6684519ab0a6c52024b5e25322476cabad893 ]

We got a report of yet another bug in ping

http://www.openwall.com/lists/oss-security/2017/03/24/6

->disconnect() is not called with socket lock held.

Fix this by acquiring ping rwlock earlier.

Thanks to Daniel, Alexander and Andrey for letting us know this problem.

Fixes: c319b4d76b9e ("net: ipv4: add IPPROTO_ICMP socket kind")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Daniel Jiang <danieljiang0415@gmail.com>
Reported-by: Solar Designer <solar@openwall.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ping.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 105c074..e612991 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -156,17 +156,18 @@ int ping_hash(struct sock *sk)
 void ping_unhash(struct sock *sk)
 {
 	struct inet_sock *isk = inet_sk(sk);
+
 	pr_debug("ping_unhash(isk=%p,isk->num=%u)\n", isk, isk->inet_num);
+	write_lock_bh(&ping_table.lock);
 	if (sk_hashed(sk)) {
-		write_lock_bh(&ping_table.lock);
 		hlist_nulls_del(&sk->sk_nulls_node);
 		sk_nulls_node_init(&sk->sk_nulls_node);
 		sock_put(sk);
 		isk->inet_num = 0;
 		isk->inet_sport = 0;
 		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
-		write_unlock_bh(&ping_table.lock);
 	}
+	write_unlock_bh(&ping_table.lock);
 }
 EXPORT_SYMBOL_GPL(ping_unhash);
 
-- 
2.4.11


From e2af885804c0d302c7a68ca8759ae211ee478b67 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@fb.com>
Date: Fri, 24 Mar 2017 15:57:33 -0700
Subject: [PATCH 05/33] bpf: improve verifier packet range checks

[ Upstream commit b1977682a3858b5584ffea7cfb7bd863f68db18d ]

llvm can optimize the 'if (ptr > data_end)' checks to be in the order
slightly different than the original C code which will confuse verifier.
Like:
if (ptr + 16 > data_end)
  return TC_ACT_SHOT;
// may be followed by
if (ptr + 14 > data_end)
  return TC_ACT_SHOT;
while llvm can see that 'ptr' is valid for all 16 bytes,
the verifier could not.
Fix verifier logic to account for such case and add a test.

Reported-by: Huapeng Zhou <hzhou@fb.com>
Fixes: 969bf05eb3ce ("bpf: direct packet access")
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 85d1c94..7c9f94c 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1829,14 +1829,15 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state,
 
 	for (i = 0; i < MAX_BPF_REG; i++)
 		if (regs[i].type == PTR_TO_PACKET && regs[i].id == dst_reg->id)
-			regs[i].range = dst_reg->off;
+			/* keep the maximum range already checked */
+			regs[i].range = max(regs[i].range, dst_reg->off);
 
 	for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
 		if (state->stack_slot_type[i] != STACK_SPILL)
 			continue;
 		reg = &state->spilled_regs[i / BPF_REG_SIZE];
 		if (reg->type == PTR_TO_PACKET && reg->id == dst_reg->id)
-			reg->range = dst_reg->off;
+			reg->range = max(reg->range, dst_reg->off);
 	}
 }
 
-- 
2.4.11


From 54d29f4a1d0c4d3cb59e81885439542a50232ee5 Mon Sep 17 00:00:00 2001
From: Talat Batheesh <talatb@mellanox.com>
Date: Tue, 28 Mar 2017 16:13:41 +0300
Subject: [PATCH 06/33] net/mlx5: Avoid dereferencing uninitialized pointer

[ Upstream commit e497ec680c4cd51e76bfcdd49363d9ab8d32a757 ]

In NETDEV_CHANGEUPPER event the upper_info field is valid
only when linking is true. Otherwise it should be ignored.

Fixes: 7907f23adc18 (net/mlx5: Implement RoCE LAG feature)
Signed-off-by: Talat Batheesh <talatb@mellanox.com>
Reviewed-by: Aviv Heller <avivh@mellanox.com>
Reviewed-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/lag.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index 5595724..b5d5519 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -294,7 +294,7 @@ static int mlx5_handle_changeupper_event(struct mlx5_lag *ldev,
 					 struct netdev_notifier_changeupper_info *info)
 {
 	struct net_device *upper = info->upper_dev, *ndev_tmp;
-	struct netdev_lag_upper_info *lag_upper_info;
+	struct netdev_lag_upper_info *lag_upper_info = NULL;
 	bool is_bonded;
 	int bond_status = 0;
 	int num_slaves = 0;
@@ -303,7 +303,8 @@ static int mlx5_handle_changeupper_event(struct mlx5_lag *ldev,
 	if (!netif_is_lag_master(upper))
 		return 0;
 
-	lag_upper_info = info->upper_info;
+	if (info->linking)
+		lag_upper_info = info->upper_info;
 
 	/* The event may still be of interest if the slave does not belong to
 	 * us, but is enslaved to a master which has one or more of our netdevs
-- 
2.4.11


From ebd3fb7e0727c94bdd232a27b8ec0c979bc72160 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Wed, 29 Mar 2017 08:44:59 +0200
Subject: [PATCH 07/33] l2tp: hold tunnel socket when handling control frames
 in l2tp_ip and l2tp_ip6

[ Upstream commit 94d7ee0baa8b764cf64ad91ed69464c1a6a0066b ]

The code following l2tp_tunnel_find() expects that a new reference is
held on sk. Either sk_receive_skb() or the discard_put error path will
drop a reference from the tunnel's socket.

This issue exists in both l2tp_ip and l2tp_ip6.

Fixes: a3c18422a4b4 ("l2tp: hold socket before dropping lock in l2tp_ip{, 6}_recv()")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ip.c  | 5 +++--
 net/l2tp/l2tp_ip6.c | 5 +++--
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index ff750bb..2066953 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -178,9 +178,10 @@ static int l2tp_ip_recv(struct sk_buff *skb)
 
 	tunnel_id = ntohl(*(__be32 *) &skb->data[4]);
 	tunnel = l2tp_tunnel_find(net, tunnel_id);
-	if (tunnel != NULL)
+	if (tunnel) {
 		sk = tunnel->sock;
-	else {
+		sock_hold(sk);
+	} else {
 		struct iphdr *iph = (struct iphdr *) skb_network_header(skb);
 
 		read_lock_bh(&l2tp_ip_lock);
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 1a65c9a..a4b0c92 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -191,9 +191,10 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
 
 	tunnel_id = ntohl(*(__be32 *) &skb->data[4]);
 	tunnel = l2tp_tunnel_find(net, tunnel_id);
-	if (tunnel != NULL)
+	if (tunnel) {
 		sk = tunnel->sock;
-	else {
+		sock_hold(sk);
+	} else {
 		struct ipv6hdr *iph = ipv6_hdr(skb);
 
 		read_lock_bh(&l2tp_ip6_lock);
-- 
2.4.11


From 0f977df87755c9a1a073d79857cfae9ea7a2df7a Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Wed, 29 Mar 2017 08:45:29 +0200
Subject: [PATCH 08/33] l2tp: purge socket queues in the .destruct() callback

[ Upstream commit e91793bb615cf6cdd59c0b6749fe173687bb0947 ]

The Rx path may grab the socket right before pppol2tp_release(), but
nothing guarantees that it will enqueue packets before
skb_queue_purge(). Therefore, the socket can be destroyed without its
queues fully purged.

Fix this by purging queues in pppol2tp_session_destruct() where we're
guaranteed nothing is still referencing the socket.

Fixes: 9e9cb6221aa7 ("l2tp: fix userspace reception on plain L2TP sockets")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ppp.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 41d47bf..51c190d 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -450,6 +450,10 @@ static void pppol2tp_session_close(struct l2tp_session *session)
 static void pppol2tp_session_destruct(struct sock *sk)
 {
 	struct l2tp_session *session = sk->sk_user_data;
+
+	skb_queue_purge(&sk->sk_receive_queue);
+	skb_queue_purge(&sk->sk_write_queue);
+
 	if (session) {
 		sk->sk_user_data = NULL;
 		BUG_ON(session->magic != L2TP_SESSION_MAGIC);
@@ -488,9 +492,6 @@ static int pppol2tp_release(struct socket *sock)
 		l2tp_session_queue_purge(session);
 		sock_put(sk);
 	}
-	skb_queue_purge(&sk->sk_receive_queue);
-	skb_queue_purge(&sk->sk_write_queue);
-
 	release_sock(sk);
 
 	/* This will delete the session context via
-- 
2.4.11


From 2a853c3f61591cc17628198b4316402e3a7b7d60 Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Wed, 29 Mar 2017 16:11:21 +0200
Subject: [PATCH 09/33] net/packet: fix overflow in check for tp_frame_nr

[ Upstream commit 8f8d28e4d6d815a391285e121c3a53a0b6cb9e7b ]

When calculating rb->frames_per_block * req->tp_block_nr the result
can overflow.

Add a check that tp_block_size * tp_block_nr <= UINT_MAX.

Since frames_per_block <= tp_block_size, the expression would
never overflow.

Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 8ab0974..e064e33 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -4247,6 +4247,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 		rb->frames_per_block = req->tp_block_size / req->tp_frame_size;
 		if (unlikely(rb->frames_per_block == 0))
 			goto out;
+		if (unlikely(req->tp_block_size > UINT_MAX / req->tp_block_nr))
+			goto out;
 		if (unlikely((rb->frames_per_block * req->tp_block_nr) !=
 					req->tp_frame_nr))
 			goto out;
-- 
2.4.11


From efaec1ad30b21cbea24946dbe91e8f7df2d1473d Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Wed, 29 Mar 2017 16:11:22 +0200
Subject: [PATCH 10/33] net/packet: fix overflow in check for tp_reserve

[ Upstream commit bcc5364bdcfe131e6379363f089e7b4108d35b70 ]

When calculating po->tp_hdrlen + po->tp_reserve the result can overflow.

Fix by checking that tp_reserve <= INT_MAX on assign.

Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index e064e33..cb76ff3 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3702,6 +3702,8 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 			return -EBUSY;
 		if (copy_from_user(&val, optval, sizeof(val)))
 			return -EFAULT;
+		if (val > INT_MAX)
+			return -EINVAL;
 		po->tp_reserve = val;
 		return 0;
 	}
-- 
2.4.11


From ed8d43ce33ee199c1ebb80d5e92629dba2f9226b Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Mon, 3 Apr 2017 12:03:13 +0200
Subject: [PATCH 11/33] l2tp: take reference on sessions being dumped

[ Upstream commit e08293a4ccbcc993ded0fdc46f1e57926b833d63 ]

Take a reference on the sessions returned by l2tp_session_find_nth()
(and rename it l2tp_session_get_nth() to reflect this change), so that
caller is assured that the session isn't going to disappear while
processing it.

For procfs and debugfs handlers, the session is held in the .start()
callback and dropped in .show(). Given that pppol2tp_seq_session_show()
dereferences the associated PPPoL2TP socket and that
l2tp_dfs_seq_session_show() might call pppol2tp_show(), we also need to
call the session's .ref() callback to prevent the socket from going
away from under us.

Fixes: fd558d186df2 ("l2tp: Split pppol2tp patch into separate l2tp and ppp parts")
Fixes: 0ad6614048cf ("l2tp: Add debugfs files for dumping l2tp debug info")
Fixes: 309795f4bec2 ("l2tp: Add netlink control API for L2TP")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c    |  8 ++++++--
 net/l2tp/l2tp_core.h    |  3 ++-
 net/l2tp/l2tp_debugfs.c | 10 +++++++---
 net/l2tp/l2tp_netlink.c |  7 +++++--
 net/l2tp/l2tp_ppp.c     | 10 +++++++---
 5 files changed, 27 insertions(+), 11 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index a2ed3bd..e702cb9 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -278,7 +278,8 @@ struct l2tp_session *l2tp_session_find(struct net *net, struct l2tp_tunnel *tunn
 }
 EXPORT_SYMBOL_GPL(l2tp_session_find);
 
-struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth)
+struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth,
+					  bool do_ref)
 {
 	int hash;
 	struct l2tp_session *session;
@@ -288,6 +289,9 @@ struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth)
 	for (hash = 0; hash < L2TP_HASH_SIZE; hash++) {
 		hlist_for_each_entry(session, &tunnel->session_hlist[hash], hlist) {
 			if (++count > nth) {
+				l2tp_session_inc_refcount(session);
+				if (do_ref && session->ref)
+					session->ref(session);
 				read_unlock_bh(&tunnel->hlist_lock);
 				return session;
 			}
@@ -298,7 +302,7 @@ struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth)
 
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(l2tp_session_find_nth);
+EXPORT_SYMBOL_GPL(l2tp_session_get_nth);
 
 /* Lookup a session by interface name.
  * This is very inefficient but is only used by management interfaces.
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 181e755c..e7233ba 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -243,7 +243,8 @@ static inline struct l2tp_tunnel *l2tp_sock_to_tunnel(struct sock *sk)
 struct l2tp_session *l2tp_session_find(struct net *net,
 				       struct l2tp_tunnel *tunnel,
 				       u32 session_id);
-struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth);
+struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth,
+					  bool do_ref);
 struct l2tp_session *l2tp_session_find_by_ifname(struct net *net, char *ifname);
 struct l2tp_tunnel *l2tp_tunnel_find(struct net *net, u32 tunnel_id);
 struct l2tp_tunnel *l2tp_tunnel_find_nth(struct net *net, int nth);
diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c
index 2d6760a..d100aed 100644
--- a/net/l2tp/l2tp_debugfs.c
+++ b/net/l2tp/l2tp_debugfs.c
@@ -53,7 +53,7 @@ static void l2tp_dfs_next_tunnel(struct l2tp_dfs_seq_data *pd)
 
 static void l2tp_dfs_next_session(struct l2tp_dfs_seq_data *pd)
 {
-	pd->session = l2tp_session_find_nth(pd->tunnel, pd->session_idx);
+	pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx, true);
 	pd->session_idx++;
 
 	if (pd->session == NULL) {
@@ -238,10 +238,14 @@ static int l2tp_dfs_seq_show(struct seq_file *m, void *v)
 	}
 
 	/* Show the tunnel or session context */
-	if (pd->session == NULL)
+	if (!pd->session) {
 		l2tp_dfs_seq_tunnel_show(m, pd->tunnel);
-	else
+	} else {
 		l2tp_dfs_seq_session_show(m, pd->session);
+		if (pd->session->deref)
+			pd->session->deref(pd->session);
+		l2tp_session_dec_refcount(pd->session);
+	}
 
 out:
 	return 0;
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index bf31177..9f66272 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -844,7 +844,7 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback
 				goto out;
 		}
 
-		session = l2tp_session_find_nth(tunnel, si);
+		session = l2tp_session_get_nth(tunnel, si, false);
 		if (session == NULL) {
 			ti++;
 			tunnel = NULL;
@@ -854,8 +854,11 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback
 
 		if (l2tp_nl_session_send(skb, NETLINK_CB(cb->skb).portid,
 					 cb->nlh->nlmsg_seq, NLM_F_MULTI,
-					 session, L2TP_CMD_SESSION_GET) < 0)
+					 session, L2TP_CMD_SESSION_GET) < 0) {
+			l2tp_session_dec_refcount(session);
 			break;
+		}
+		l2tp_session_dec_refcount(session);
 
 		si++;
 	}
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 51c190d..4db3317 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1555,7 +1555,7 @@ static void pppol2tp_next_tunnel(struct net *net, struct pppol2tp_seq_data *pd)
 
 static void pppol2tp_next_session(struct net *net, struct pppol2tp_seq_data *pd)
 {
-	pd->session = l2tp_session_find_nth(pd->tunnel, pd->session_idx);
+	pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx, true);
 	pd->session_idx++;
 
 	if (pd->session == NULL) {
@@ -1682,10 +1682,14 @@ static int pppol2tp_seq_show(struct seq_file *m, void *v)
 
 	/* Show the tunnel or session context.
 	 */
-	if (pd->session == NULL)
+	if (!pd->session) {
 		pppol2tp_seq_tunnel_show(m, pd->tunnel);
-	else
+	} else {
 		pppol2tp_seq_session_show(m, pd->session);
+		if (pd->session->deref)
+			pd->session->deref(pd->session);
+		l2tp_session_dec_refcount(pd->session);
+	}
 
 out:
 	return 0;
-- 
2.4.11


From 6bfe95133afeb470078db06a31983a503c4e6ede Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Mon, 3 Apr 2017 13:23:15 +0200
Subject: [PATCH 12/33] l2tp: fix PPP pseudo-wire auto-loading

[ Upstream commit 249ee819e24c180909f43c1173c8ef6724d21faf ]

PPP pseudo-wire type is 7 (11 is L2TP_PWTYPE_IP).

Fixes: f1f39f911027 ("l2tp: auto load type modules")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ppp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 4db3317..1387f54 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1848,4 +1848,4 @@ MODULE_DESCRIPTION("PPP over L2TP over UDP");
 MODULE_LICENSE("GPL");
 MODULE_VERSION(PPPOL2TP_DRV_VERSION);
 MODULE_ALIAS_NET_PF_PROTO(PF_PPPOX, PX_PROTO_OL2TP);
-MODULE_ALIAS_L2TP_PWTYPE(11);
+MODULE_ALIAS_L2TP_PWTYPE(7);
-- 
2.4.11


From 0fa5d805d144b151d0565b784c2ab28303974645 Mon Sep 17 00:00:00 2001
From: Florian Larysch <fl@n621.de>
Date: Mon, 3 Apr 2017 16:46:09 +0200
Subject: [PATCH 13/33] net: ipv4: fix multipath RTM_GETROUTE behavior when iif
 is given

[ Upstream commit a8801799c6975601fd58ae62f48964caec2eb83f ]

inet_rtm_getroute synthesizes a skeletal ICMP skb, which is passed to
ip_route_input when iif is given. If a multipath route is present for
the designated destination, ip_multipath_icmp_hash ends up being called,
which uses the source/destination addresses within the skb to calculate
a hash. However, those are not set in the synthetic skb, causing it to
return an arbitrary and incorrect result.

Instead, use UDP, which gets no such special treatment.

Signed-off-by: Florian Larysch <fl@n621.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 17e6fbf..6dbcb37 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2569,7 +2569,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 	skb_reset_network_header(skb);
 
 	/* Bugfix: need to give ip_route_input enough of an IP header to not gag. */
-	ip_hdr(skb)->protocol = IPPROTO_ICMP;
+	ip_hdr(skb)->protocol = IPPROTO_UDP;
 	skb_reserve(skb, MAX_HEADER + sizeof(struct iphdr));
 
 	src = tb[RTA_SRC] ? nla_get_in_addr(tb[RTA_SRC]) : 0;
-- 
2.4.11


From 5833f7d7fc7bbba4c8a664e1e266ee32d3209502 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 6 Apr 2017 13:10:52 +0800
Subject: [PATCH 14/33] sctp: listen on the sock only when it's state is
 listening or closed

[ Upstream commit 34b2789f1d9bf8dcca9b5cb553d076ca2cd898ee ]

Now sctp doesn't check sock's state before listening on it. It could
even cause changing a sock with any state to become a listening sock
when doing sctp_listen.

This patch is to fix it by checking sock's state in sctp_listen, so
that it will listen on the sock with right state.

Reported-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 6734420..14346dc 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -6861,6 +6861,9 @@ int sctp_inet_listen(struct socket *sock, int backlog)
 	if (sock->state != SS_UNCONNECTED)
 		goto out;
 
+	if (!sctp_sstate(sk, LISTENING) && !sctp_sstate(sk, CLOSED))
+		goto out;
+
 	/* If backlog is zero, disable listening. */
 	if (!backlog) {
 		if (sctp_sstate(sk, CLOSED))
-- 
2.4.11


From c8bfbb17d27793811aafcfeba5825c7ddba76b3f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 8 Apr 2017 08:07:33 -0700
Subject: [PATCH 15/33] tcp: clear saved_syn in tcp_disconnect()

[ Upstream commit 17c3060b1701fc69daedb4c90be6325d3d9fca8e ]

In the (very unlikely) case a passive socket becomes a listener,
we do not want to duplicate its saved SYN headers.

This would lead to double frees, use after free, and please hackers and
various fuzzers

Tested:
    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
   +0 setsockopt(3, IPPROTO_TCP, TCP_SAVE_SYN, [1], 4) = 0
   +0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0

   +0 bind(3, ..., ...) = 0
   +0 listen(3, 5) = 0

   +0 < S 0:0(0) win 32972 <mss 1460,nop,wscale 7>
   +0 > S. 0:0(0) ack 1 <...>
  +.1 < . 1:1(0) ack 1 win 257
   +0 accept(3, ..., ...) = 4

   +0 connect(4, AF_UNSPEC, ...) = 0
   +0 close(3) = 0
   +0 bind(4, ..., ...) = 0
   +0 listen(4, 5) = 0

   +0 < S 0:0(0) win 32972 <mss 1460,nop,wscale 7>
   +0 > S. 0:0(0) ack 1 <...>
  +.1 < . 1:1(0) ack 1 win 257

Fixes: cd8ae85299d5 ("tcp: provide SYN headers for passive connections")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 6a90a0e..eb142ca 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2297,6 +2297,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tcp_init_send_head(sk);
 	memset(&tp->rx_opt, 0, sizeof(tp->rx_opt));
 	__sk_dst_reset(sk);
+	tcp_saved_syn_free(tp);
 
 	WARN_ON(inet->inet_num && !icsk->icsk_bind_hash);
 
-- 
2.4.11


From 3304d2b21cd5d67cd61dde4484c9366057d261b0 Mon Sep 17 00:00:00 2001
From: Rabin Vincent <rabinv@axis.com>
Date: Mon, 10 Apr 2017 08:36:39 +0200
Subject: [PATCH 16/33] ipv6: Fix idev->addr_list corruption

[ Upstream commit a2d6cbb0670d54806f18192cb0db266b4a6d285a ]

addrconf_ifdown() removes elements from the idev->addr_list without
holding the idev->lock.

If this happens while the loop in __ipv6_dev_get_saddr() is handling the
same element, that function ends up in an infinite loop:

  NMI watchdog: BUG: soft lockup - CPU#1 stuck for 23s! [test:1719]
  Call Trace:
   ipv6_get_saddr_eval+0x13c/0x3a0
   __ipv6_dev_get_saddr+0xe4/0x1f0
   ipv6_dev_get_saddr+0x1b4/0x204
   ip6_dst_lookup_tail+0xcc/0x27c
   ip6_dst_lookup_flow+0x38/0x80
   udpv6_sendmsg+0x708/0xba8
   sock_sendmsg+0x18/0x30
   SyS_sendto+0xb8/0xf8
   syscall_common+0x34/0x58

Fixes: 6a923934c33 (Revert "ipv6: Revert optional address flusing on ifdown.")
Signed-off-by: Rabin Vincent <rabinv@axis.com>
Acked-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 95dfcba..cbcc991 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3602,14 +3602,19 @@ static int addrconf_ifdown(struct net_device *dev, int how)
 	INIT_LIST_HEAD(&del_list);
 	list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) {
 		struct rt6_info *rt = NULL;
+		bool keep;
 
 		addrconf_del_dad_work(ifa);
 
+		keep = keep_addr && (ifa->flags & IFA_F_PERMANENT) &&
+			!addr_is_local(&ifa->addr);
+		if (!keep)
+			list_move(&ifa->if_list, &del_list);
+
 		write_unlock_bh(&idev->lock);
 		spin_lock_bh(&ifa->lock);
 
-		if (keep_addr && (ifa->flags & IFA_F_PERMANENT) &&
-		    !addr_is_local(&ifa->addr)) {
+		if (keep) {
 			/* set state to skip the notifier below */
 			state = INET6_IFADDR_STATE_DEAD;
 			ifa->state = 0;
@@ -3621,8 +3626,6 @@ static int addrconf_ifdown(struct net_device *dev, int how)
 		} else {
 			state = ifa->state;
 			ifa->state = INET6_IFADDR_STATE_DEAD;
-
-			list_move(&ifa->if_list, &del_list);
 		}
 
 		spin_unlock_bh(&ifa->lock);
-- 
2.4.11


From f05ca4a374e157f66a8a6252688a2c449a8a19d7 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 12 Apr 2017 19:24:35 -0400
Subject: [PATCH 17/33] net-timestamp: avoid use-after-free in ip_recv_error

[ Upstream commit 1862d6208db0aeca9c8ace44915b08d5ab2cd667 ]

Syzkaller reported a use-after-free in ip_recv_error at line

    info->ipi_ifindex = skb->dev->ifindex;

This function is called on dequeue from the error queue, at which
point the device pointer may no longer be valid.

Save ifindex on enqueue in __skb_complete_tx_timestamp, when the
pointer is valid or NULL. Store it in temporary storage skb->cb.

It is safe to reference skb->dev here, as called from device drivers
or dev_queue_xmit. The exception is when called from tcp_ack_tstamp;
in that case it is NULL and ifindex is set to 0 (invalid).

Do not return a pktinfo cmsg if ifindex is 0. This maintains the
current behavior of not returning a cmsg if skb->dev was NULL.

On dequeue, the ipv4 path will cast from sock_exterr_skb to
in_pktinfo. Both have ifindex as their first element, so no explicit
conversion is needed. This is by design, introduced in commit
0b922b7a829c ("net: original ingress device index in PKTINFO"). For
ipv6 ip6_datagram_support_cmsg converts to in6_pktinfo.

Fixes: 829ae9d61165 ("net-timestamp: allow reading recv cmsg on errqueue with origin tstamp")
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c      |  1 +
 net/ipv4/ip_sockglue.c |  9 ++++-----
 net/ipv6/datagram.c    | 10 +---------
 3 files changed, 6 insertions(+), 14 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index f0f462c..5ec34ea 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3779,6 +3779,7 @@ static void __skb_complete_tx_timestamp(struct sk_buff *skb,
 	serr->ee.ee_errno = ENOMSG;
 	serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING;
 	serr->ee.ee_info = tstype;
+	serr->header.h4.iif = skb->dev ? skb->dev->ifindex : 0;
 	if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) {
 		serr->ee.ee_data = skb_shinfo(skb)->tskey;
 		if (sk->sk_protocol == IPPROTO_TCP &&
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 9826695..4d37bdc 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -474,16 +474,15 @@ static bool ipv4_datagram_support_cmsg(const struct sock *sk,
 		return false;
 
 	/* Support IP_PKTINFO on tstamp packets if requested, to correlate
-	 * timestamp with egress dev. Not possible for packets without dev
+	 * timestamp with egress dev. Not possible for packets without iif
 	 * or without payload (SOF_TIMESTAMPING_OPT_TSONLY).
 	 */
-	if ((!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_CMSG)) ||
-	    (!skb->dev))
+	info = PKTINFO_SKB_CB(skb);
+	if (!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_CMSG) ||
+	    !info->ipi_ifindex)
 		return false;
 
-	info = PKTINFO_SKB_CB(skb);
 	info->ipi_spec_dst.s_addr = ip_hdr(skb)->saddr;
-	info->ipi_ifindex = skb->dev->ifindex;
 	return true;
 }
 
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 8616d17..442ec1f 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -400,9 +400,6 @@ static inline bool ipv6_datagram_support_addr(struct sock_exterr_skb *serr)
  * At one point, excluding local errors was a quick test to identify icmp/icmp6
  * errors. This is no longer true, but the test remained, so the v6 stack,
  * unlike v4, also honors cmsg requests on all wifi and timestamp errors.
- *
- * Timestamp code paths do not initialize the fields expected by cmsg:
- * the PKTINFO fields in skb->cb[]. Fill those in here.
  */
 static bool ip6_datagram_support_cmsg(struct sk_buff *skb,
 				      struct sock_exterr_skb *serr)
@@ -414,14 +411,9 @@ static bool ip6_datagram_support_cmsg(struct sk_buff *skb,
 	if (serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL)
 		return false;
 
-	if (!skb->dev)
+	if (!IP6CB(skb)->iif)
 		return false;
 
-	if (skb->protocol == htons(ETH_P_IPV6))
-		IP6CB(skb)->iif = skb->dev->ifindex;
-	else
-		PKTINFO_SKB_CB(skb)->ipi_ifindex = skb->dev->ifindex;
-
 	return true;
 }
 
-- 
2.4.11


From 189588b388ae21d0380a8223a38299403f51b593 Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Thu, 13 Apr 2017 10:57:15 -0600
Subject: [PATCH 18/33] net: vrf: Fix setting NLM_F_EXCL flag when adding
 l3mdev rule

[ Upstream commit 426c87caa2b4578b43cd3f689f02c65b743b2559 ]

Only need 1 l3mdev FIB rule. Fix setting NLM_F_EXCL in the nlmsghdr.

Fixes: 1aa6c4f6b8cd8 ("net: vrf: Add l3mdev rules on first device create")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index a2afb8e..80ef486 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -1124,7 +1124,7 @@ static int vrf_fib_rule(const struct net_device *dev, __u8 family, bool add_it)
 		goto nla_put_failure;
 
 	/* rule only needs to appear once */
-	nlh->nlmsg_flags &= NLM_F_EXCL;
+	nlh->nlmsg_flags |= NLM_F_EXCL;
 
 	frh = nlmsg_data(nlh);
 	memset(frh, 0, sizeof(*frh));
-- 
2.4.11


From 78ab99a41327ea4c5ad7c6b5ad26cc3640f889cd Mon Sep 17 00:00:00 2001
From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Date: Mon, 17 Apr 2017 15:55:22 +0300
Subject: [PATCH 19/33] sh_eth: unmap DMA buffers when freeing rings

[ Upstream commit 1debdc8f9ebd07daf140e417b3841596911e0066 ]

The DMA API debugging (when enabled) causes:

WARNING: CPU: 0 PID: 1445 at lib/dma-debug.c:519 add_dma_entry+0xe0/0x12c
DMA-API: exceeded 7 overlapping mappings of cacheline 0x01b2974d

to be  printed after repeated initialization of the Ether device, e.g.
suspend/resume or 'ifconfig' up/down. This is because DMA buffers mapped
using dma_map_single() in sh_eth_ring_format() and sh_eth_start_xmit() are
never unmapped. Resolve this problem by unmapping the buffers when freeing
the descriptor  rings;  in order  to do it right, we'd have to add an extra
parameter to sh_eth_txfree() (we rename this function to sh_eth_tx_free(),
while at it).

Based on the commit a47b70ea86bd ("ravb: unmap descriptors when freeing
rings").

Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/sh_eth.c | 122 +++++++++++++++++++---------------
 1 file changed, 67 insertions(+), 55 deletions(-)

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 1a92de7..a2d218b 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -1059,12 +1059,70 @@ static struct mdiobb_ops bb_ops = {
 	.get_mdio_data = sh_get_mdio,
 };
 
+/* free Tx skb function */
+static int sh_eth_tx_free(struct net_device *ndev, bool sent_only)
+{
+	struct sh_eth_private *mdp = netdev_priv(ndev);
+	struct sh_eth_txdesc *txdesc;
+	int free_num = 0;
+	int entry;
+	bool sent;
+
+	for (; mdp->cur_tx - mdp->dirty_tx > 0; mdp->dirty_tx++) {
+		entry = mdp->dirty_tx % mdp->num_tx_ring;
+		txdesc = &mdp->tx_ring[entry];
+		sent = !(txdesc->status & cpu_to_le32(TD_TACT));
+		if (sent_only && !sent)
+			break;
+		/* TACT bit must be checked before all the following reads */
+		dma_rmb();
+		netif_info(mdp, tx_done, ndev,
+			   "tx entry %d status 0x%08x\n",
+			   entry, le32_to_cpu(txdesc->status));
+		/* Free the original skb. */
+		if (mdp->tx_skbuff[entry]) {
+			dma_unmap_single(&ndev->dev, le32_to_cpu(txdesc->addr),
+					 le32_to_cpu(txdesc->len) >> 16,
+					 DMA_TO_DEVICE);
+			dev_kfree_skb_irq(mdp->tx_skbuff[entry]);
+			mdp->tx_skbuff[entry] = NULL;
+			free_num++;
+		}
+		txdesc->status = cpu_to_le32(TD_TFP);
+		if (entry >= mdp->num_tx_ring - 1)
+			txdesc->status |= cpu_to_le32(TD_TDLE);
+
+		if (sent) {
+			ndev->stats.tx_packets++;
+			ndev->stats.tx_bytes += le32_to_cpu(txdesc->len) >> 16;
+		}
+	}
+	return free_num;
+}
+
 /* free skb and descriptor buffer */
 static void sh_eth_ring_free(struct net_device *ndev)
 {
 	struct sh_eth_private *mdp = netdev_priv(ndev);
 	int ringsize, i;
 
+	if (mdp->rx_ring) {
+		for (i = 0; i < mdp->num_rx_ring; i++) {
+			if (mdp->rx_skbuff[i]) {
+				struct sh_eth_rxdesc *rxdesc = &mdp->rx_ring[i];
+
+				dma_unmap_single(&ndev->dev,
+						 le32_to_cpu(rxdesc->addr),
+						 ALIGN(mdp->rx_buf_sz, 32),
+						 DMA_FROM_DEVICE);
+			}
+		}
+		ringsize = sizeof(struct sh_eth_rxdesc) * mdp->num_rx_ring;
+		dma_free_coherent(NULL, ringsize, mdp->rx_ring,
+				  mdp->rx_desc_dma);
+		mdp->rx_ring = NULL;
+	}
+
 	/* Free Rx skb ringbuffer */
 	if (mdp->rx_skbuff) {
 		for (i = 0; i < mdp->num_rx_ring; i++)
@@ -1073,27 +1131,18 @@ static void sh_eth_ring_free(struct net_device *ndev)
 	kfree(mdp->rx_skbuff);
 	mdp->rx_skbuff = NULL;
 
-	/* Free Tx skb ringbuffer */
-	if (mdp->tx_skbuff) {
-		for (i = 0; i < mdp->num_tx_ring; i++)
-			dev_kfree_skb(mdp->tx_skbuff[i]);
-	}
-	kfree(mdp->tx_skbuff);
-	mdp->tx_skbuff = NULL;
-
-	if (mdp->rx_ring) {
-		ringsize = sizeof(struct sh_eth_rxdesc) * mdp->num_rx_ring;
-		dma_free_coherent(NULL, ringsize, mdp->rx_ring,
-				  mdp->rx_desc_dma);
-		mdp->rx_ring = NULL;
-	}
-
 	if (mdp->tx_ring) {
+		sh_eth_tx_free(ndev, false);
+
 		ringsize = sizeof(struct sh_eth_txdesc) * mdp->num_tx_ring;
 		dma_free_coherent(NULL, ringsize, mdp->tx_ring,
 				  mdp->tx_desc_dma);
 		mdp->tx_ring = NULL;
 	}
+
+	/* Free Tx skb ringbuffer */
+	kfree(mdp->tx_skbuff);
+	mdp->tx_skbuff = NULL;
 }
 
 /* format skb and descriptor buffer */
@@ -1341,43 +1390,6 @@ static void sh_eth_dev_exit(struct net_device *ndev)
 	update_mac_address(ndev);
 }
 
-/* free Tx skb function */
-static int sh_eth_txfree(struct net_device *ndev)
-{
-	struct sh_eth_private *mdp = netdev_priv(ndev);
-	struct sh_eth_txdesc *txdesc;
-	int free_num = 0;
-	int entry;
-
-	for (; mdp->cur_tx - mdp->dirty_tx > 0; mdp->dirty_tx++) {
-		entry = mdp->dirty_tx % mdp->num_tx_ring;
-		txdesc = &mdp->tx_ring[entry];
-		if (txdesc->status & cpu_to_le32(TD_TACT))
-			break;
-		/* TACT bit must be checked before all the following reads */
-		dma_rmb();
-		netif_info(mdp, tx_done, ndev,
-			   "tx entry %d status 0x%08x\n",
-			   entry, le32_to_cpu(txdesc->status));
-		/* Free the original skb. */
-		if (mdp->tx_skbuff[entry]) {
-			dma_unmap_single(&ndev->dev, le32_to_cpu(txdesc->addr),
-					 le32_to_cpu(txdesc->len) >> 16,
-					 DMA_TO_DEVICE);
-			dev_kfree_skb_irq(mdp->tx_skbuff[entry]);
-			mdp->tx_skbuff[entry] = NULL;
-			free_num++;
-		}
-		txdesc->status = cpu_to_le32(TD_TFP);
-		if (entry >= mdp->num_tx_ring - 1)
-			txdesc->status |= cpu_to_le32(TD_TDLE);
-
-		ndev->stats.tx_packets++;
-		ndev->stats.tx_bytes += le32_to_cpu(txdesc->len) >> 16;
-	}
-	return free_num;
-}
-
 /* Packet receive function */
 static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota)
 {
@@ -1620,7 +1632,7 @@ static void sh_eth_error(struct net_device *ndev, u32 intr_status)
 			   intr_status, mdp->cur_tx, mdp->dirty_tx,
 			   (u32)ndev->state, edtrr);
 		/* dirty buffer free */
-		sh_eth_txfree(ndev);
+		sh_eth_tx_free(ndev, true);
 
 		/* SH7712 BUG */
 		if (edtrr ^ sh_eth_get_edtrr_trns(mdp)) {
@@ -1679,7 +1691,7 @@ static irqreturn_t sh_eth_interrupt(int irq, void *netdev)
 		/* Clear Tx interrupts */
 		sh_eth_write(ndev, intr_status & cd->tx_check, EESR);
 
-		sh_eth_txfree(ndev);
+		sh_eth_tx_free(ndev, true);
 		netif_wake_queue(ndev);
 	}
 
@@ -2307,7 +2319,7 @@ static int sh_eth_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 
 	spin_lock_irqsave(&mdp->lock, flags);
 	if ((mdp->cur_tx - mdp->dirty_tx) >= (mdp->num_tx_ring - 4)) {
-		if (!sh_eth_txfree(ndev)) {
+		if (!sh_eth_tx_free(ndev, true)) {
 			netif_warn(mdp, tx_queued, ndev, "TxFD exhausted.\n");
 			netif_stop_queue(ndev);
 			spin_unlock_irqrestore(&mdp->lock, flags);
-- 
2.4.11


From eb651b2d8470c41592b44e970ebdfc0e0882319d Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Tue, 18 Apr 2017 22:14:26 +0300
Subject: [PATCH 20/33] dp83640: don't recieve time stamps twice
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 9d386cd9a755c8293e8916264d4d053878a7c9c7 ]

This patch is prompted by a static checker warning about a potential
use after free.  The concern is that netif_rx_ni() can free "skb" and we
call it twice.

When I look at the commit that added this, it looks like some stray
lines were added accidentally.  It doesn't make sense to me that we
would recieve the same data two times.  I asked the author but never
recieved a response.

I can't test this code, but I'm pretty sure my patch is correct.

Fixes: 4b063258ab93 ("dp83640: Delay scheduled work.")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Stefan Sørensen <stefan.sorensen@spectralink.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/dp83640.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index 7a240fc..4865221 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -1438,8 +1438,6 @@ static bool dp83640_rxtstamp(struct phy_device *phydev,
 		skb_info->tmo = jiffies + SKB_TIMESTAMP_TIMEOUT;
 		skb_queue_tail(&dp83640->rx_queue, skb);
 		schedule_delayed_work(&dp83640->ts_work, SKB_TIMESTAMP_TIMEOUT);
-	} else {
-		netif_rx_ni(skb);
 	}
 
 	return true;
-- 
2.4.11


From f655e39666e540f8181547a5d400196a640a7e6e Mon Sep 17 00:00:00 2001
From: Ilan Tayari <ilant@mellanox.com>
Date: Wed, 19 Apr 2017 21:26:07 +0300
Subject: [PATCH 21/33] gso: Validate assumption of frag_list segementation

[ Upstream commit 43170c4e0ba709c79130c3fe5a41e66279950cd0 ]

Commit 07b26c9454a2 ("gso: Support partial splitting at the frag_list
pointer") assumes that all SKBs in a frag_list (except maybe the last
one) contain the same amount of GSO payload.

This assumption is not always correct, resulting in the following
warning message in the log:
    skb_segment: too many frags

For example, mlx5 driver in Striding RQ mode creates some RX SKBs with
one frag, and some with 2 frags.
After GRO, the frag_list SKBs end up having different amounts of payload.
If this frag_list SKB is then forwarded, the aforementioned assumption
is violated.

Validate the assumption, and fall back to software GSO if it not true.

Change-Id: Ia03983f4a47b6534dd987d7a2aad96d54d46d212
Fixes: 07b26c9454a2 ("gso: Support partial splitting at the frag_list pointer")
Signed-off-by: Ilan Tayari <ilant@mellanox.com>
Signed-off-by: Ilya Lesokhin <ilyal@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 5ec34ea..fe008f1 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3076,22 +3076,32 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 	if (sg && csum && (mss != GSO_BY_FRAGS))  {
 		if (!(features & NETIF_F_GSO_PARTIAL)) {
 			struct sk_buff *iter;
+			unsigned int frag_len;
 
 			if (!list_skb ||
 			    !net_gso_ok(features, skb_shinfo(head_skb)->gso_type))
 				goto normal;
 
-			/* Split the buffer at the frag_list pointer.
-			 * This is based on the assumption that all
-			 * buffers in the chain excluding the last
-			 * containing the same amount of data.
+			/* If we get here then all the required
+			 * GSO features except frag_list are supported.
+			 * Try to split the SKB to multiple GSO SKBs
+			 * with no frag_list.
+			 * Currently we can do that only when the buffers don't
+			 * have a linear part and all the buffers except
+			 * the last are of the same length.
 			 */
+			frag_len = list_skb->len;
 			skb_walk_frags(head_skb, iter) {
+				if (frag_len != iter->len && iter->next)
+					goto normal;
 				if (skb_headlen(iter))
 					goto normal;
 
 				len -= iter->len;
 			}
+
+			if (len != frag_len)
+				goto normal;
 		}
 
 		/* GSO partial only requires that we trim off any excess that
-- 
2.4.11


From 1735145b6d3039b42507c0cb3dd2ffe54699f552 Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Wed, 19 Apr 2017 14:19:43 -0700
Subject: [PATCH 22/33] net: ipv6: RTF_PCPU should not be settable from
 userspace

[ Upstream commit 557c44be917c322860665be3d28376afa84aa936 ]

Andrey reported a fault in the IPv6 route code:

kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] SMP KASAN
Modules linked in:
CPU: 1 PID: 4035 Comm: a.out Not tainted 4.11.0-rc7+ #250
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
task: ffff880069809600 task.stack: ffff880062dc8000
RIP: 0010:ip6_rt_cache_alloc+0xa6/0x560 net/ipv6/route.c:975
RSP: 0018:ffff880062dced30 EFLAGS: 00010206
RAX: dffffc0000000000 RBX: ffff8800670561c0 RCX: 0000000000000006
RDX: 0000000000000003 RSI: ffff880062dcfb28 RDI: 0000000000000018
RBP: ffff880062dced68 R08: 0000000000000001 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
R13: ffff880062dcfb28 R14: dffffc0000000000 R15: 0000000000000000
FS:  00007feebe37e7c0(0000) GS:ffff88006cb00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000205a0fe4 CR3: 000000006b5c9000 CR4: 00000000000006e0
Call Trace:
 ip6_pol_route+0x1512/0x1f20 net/ipv6/route.c:1128
 ip6_pol_route_output+0x4c/0x60 net/ipv6/route.c:1212
...

Andrey's syzkaller program passes rtmsg.rtmsg_flags with the RTF_PCPU bit
set. Flags passed to the kernel are blindly copied to the allocated
rt6_info by ip6_route_info_create making a newly inserted route appear
as though it is a per-cpu route. ip6_rt_cache_alloc sees the flag set
and expects rt->dst.from to be set - which it is not since it is not
really a per-cpu copy. The subsequent call to __ip6_dst_alloc then
generates the fault.

Fix by checking for the flag and failing with EINVAL.

Fixes: d52d3997f843f ("ipv6: Create percpu rt6_info")
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/ipv6_route.h | 2 +-
 net/ipv6/route.c                | 4 ++++
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/ipv6_route.h b/include/uapi/linux/ipv6_route.h
index f6598d1..316e838 100644
--- a/include/uapi/linux/ipv6_route.h
+++ b/include/uapi/linux/ipv6_route.h
@@ -34,7 +34,7 @@
 #define RTF_PREF(pref)	((pref) << 27)
 #define RTF_PREF_MASK	0x18000000
 
-#define RTF_PCPU	0x40000000
+#define RTF_PCPU	0x40000000	/* read-only: can not be set by user */
 #define RTF_LOCAL	0x80000000
 
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 8d6c09f..9f1bc75 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1826,6 +1826,10 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg)
 	int addr_type;
 	int err = -EINVAL;
 
+	/* RTF_PCPU is an internal flag; can not be set by userspace */
+	if (cfg->fc_flags & RTF_PCPU)
+		goto out;
+
 	if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128)
 		goto out;
 #ifndef CONFIG_IPV6_SUBTREES
-- 
2.4.11


From d1fc407cdbfbba20d6f750583bc9cd6c761d3a71 Mon Sep 17 00:00:00 2001
From: Tushar Dave <tushar.n.dave@oracle.com>
Date: Thu, 20 Apr 2017 15:57:31 -0700
Subject: [PATCH 23/33] netpoll: Check for skb->queue_mapping

[ Upstream commit c70b17b775edb21280e9de7531acf6db3b365274 ]

Reducing real_num_tx_queues needs to be in sync with skb queue_mapping
otherwise skbs with queue_mapping greater than real_num_tx_queues
can be sent to the underlying driver and can result in kernel panic.

One such event is running netconsole and enabling VF on the same
device. Or running netconsole and changing number of tx queues via
ethtool on same device.

e.g.
Unable to handle kernel NULL pointer dereference
tsk->{mm,active_mm}->context = 0000000000001525
tsk->{mm,active_mm}->pgd = fff800130ff9a000
              \|/ ____ \|/
              "@'/ .. \`@"
              /_| \__/ |_\
                 \__U_/
kworker/48:1(475): Oops [#1]
CPU: 48 PID: 475 Comm: kworker/48:1 Tainted: G           OE
4.11.0-rc3-davem-net+ #7
Workqueue: events queue_process
task: fff80013113299c0 task.stack: fff800131132c000
TSTATE: 0000004480e01600 TPC: 00000000103f9e3c TNPC: 00000000103f9e40 Y:
00000000    Tainted: G           OE
TPC: <ixgbe_xmit_frame_ring+0x7c/0x6c0 [ixgbe]>
g0: 0000000000000000 g1: 0000000000003fff g2: 0000000000000000 g3:
0000000000000001
g4: fff80013113299c0 g5: fff8001fa6808000 g6: fff800131132c000 g7:
00000000000000c0
o0: fff8001fa760c460 o1: fff8001311329a50 o2: fff8001fa7607504 o3:
0000000000000003
o4: fff8001f96e63a40 o5: fff8001311d77ec0 sp: fff800131132f0e1 ret_pc:
000000000049ed94
RPC: <set_next_entity+0x34/0xb80>
l0: 0000000000000000 l1: 0000000000000800 l2: 0000000000000000 l3:
0000000000000000
l4: 000b2aa30e34b10d l5: 0000000000000000 l6: 0000000000000000 l7:
fff8001fa7605028
i0: fff80013111a8a00 i1: fff80013155a0780 i2: 0000000000000000 i3:
0000000000000000
i4: 0000000000000000 i5: 0000000000100000 i6: fff800131132f1a1 i7:
00000000103fa4b0
I7: <ixgbe_xmit_frame+0x30/0xa0 [ixgbe]>
Call Trace:
 [00000000103fa4b0] ixgbe_xmit_frame+0x30/0xa0 [ixgbe]
 [0000000000998c74] netpoll_start_xmit+0xf4/0x200
 [0000000000998e10] queue_process+0x90/0x160
 [0000000000485fa8] process_one_work+0x188/0x480
 [0000000000486410] worker_thread+0x170/0x4c0
 [000000000048c6b8] kthread+0xd8/0x120
 [0000000000406064] ret_from_fork+0x1c/0x2c
 [0000000000000000]           (null)
Disabling lock debugging due to kernel taint
Caller[00000000103fa4b0]: ixgbe_xmit_frame+0x30/0xa0 [ixgbe]
Caller[0000000000998c74]: netpoll_start_xmit+0xf4/0x200
Caller[0000000000998e10]: queue_process+0x90/0x160
Caller[0000000000485fa8]: process_one_work+0x188/0x480
Caller[0000000000486410]: worker_thread+0x170/0x4c0
Caller[000000000048c6b8]: kthread+0xd8/0x120
Caller[0000000000406064]: ret_from_fork+0x1c/0x2c
Caller[0000000000000000]:           (null)

Signed-off-by: Tushar Dave <tushar.n.dave@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/netpoll.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 53599bd..457f882 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -105,15 +105,21 @@ static void queue_process(struct work_struct *work)
 	while ((skb = skb_dequeue(&npinfo->txq))) {
 		struct net_device *dev = skb->dev;
 		struct netdev_queue *txq;
+		unsigned int q_index;
 
 		if (!netif_device_present(dev) || !netif_running(dev)) {
 			kfree_skb(skb);
 			continue;
 		}
 
-		txq = skb_get_tx_queue(dev, skb);
-
 		local_irq_save(flags);
+		/* check if skb->queue_mapping is still valid */
+		q_index = skb_get_queue_mapping(skb);
+		if (unlikely(q_index >= dev->real_num_tx_queues)) {
+			q_index = q_index % dev->real_num_tx_queues;
+			skb_set_queue_mapping(skb, q_index);
+		}
+		txq = netdev_get_tx_queue(dev, q_index);
 		HARD_TX_LOCK(dev, txq, smp_processor_id());
 		if (netif_xmit_frozen_or_stopped(txq) ||
 		    netpoll_start_xmit(skb, dev, txq) != NETDEV_TX_OK) {
-- 
2.4.11


From 48dbf9a84a4fdd22b5379652a8eab9040a7cdfcb Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Fri, 21 Apr 2017 20:42:16 +0300
Subject: [PATCH 24/33] ip6mr: fix notification device destruction

[ Upstream commit 723b929ca0f79c0796f160c2eeda4597ee98d2b8 ]

Andrey Konovalov reported a BUG caused by the ip6mr code which is caused
because we call unregister_netdevice_many for a device that is already
being destroyed. In IPv4's ipmr that has been resolved by two commits
long time ago by introducing the "notify" parameter to the delete
function and avoiding the unregister when called from a notifier, so
let's do the same for ip6mr.

The trace from Andrey:
------------[ cut here ]------------
kernel BUG at net/core/dev.c:6813!
invalid opcode: 0000 [#1] SMP KASAN
Modules linked in:
CPU: 1 PID: 1165 Comm: kworker/u4:3 Not tainted 4.11.0-rc7+ #251
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs
01/01/2011
Workqueue: netns cleanup_net
task: ffff880069208000 task.stack: ffff8800692d8000
RIP: 0010:rollback_registered_many+0x348/0xeb0 net/core/dev.c:6813
RSP: 0018:ffff8800692de7f0 EFLAGS: 00010297
RAX: ffff880069208000 RBX: 0000000000000002 RCX: 0000000000000001
RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff88006af90569
RBP: ffff8800692de9f0 R08: ffff8800692dec60 R09: 0000000000000000
R10: 0000000000000006 R11: 0000000000000000 R12: ffff88006af90070
R13: ffff8800692debf0 R14: dffffc0000000000 R15: ffff88006af90000
FS:  0000000000000000(0000) GS:ffff88006cb00000(0000)
knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007fe7e897d870 CR3: 00000000657e7000 CR4: 00000000000006e0
Call Trace:
 unregister_netdevice_many.part.105+0x87/0x440 net/core/dev.c:7881
 unregister_netdevice_many+0xc8/0x120 net/core/dev.c:7880
 ip6mr_device_event+0x362/0x3f0 net/ipv6/ip6mr.c:1346
 notifier_call_chain+0x145/0x2f0 kernel/notifier.c:93
 __raw_notifier_call_chain kernel/notifier.c:394
 raw_notifier_call_chain+0x2d/0x40 kernel/notifier.c:401
 call_netdevice_notifiers_info+0x51/0x90 net/core/dev.c:1647
 call_netdevice_notifiers net/core/dev.c:1663
 rollback_registered_many+0x919/0xeb0 net/core/dev.c:6841
 unregister_netdevice_many.part.105+0x87/0x440 net/core/dev.c:7881
 unregister_netdevice_many net/core/dev.c:7880
 default_device_exit_batch+0x4fa/0x640 net/core/dev.c:8333
 ops_exit_list.isra.4+0x100/0x150 net/core/net_namespace.c:144
 cleanup_net+0x5a8/0xb40 net/core/net_namespace.c:463
 process_one_work+0xc04/0x1c10 kernel/workqueue.c:2097
 worker_thread+0x223/0x19c0 kernel/workqueue.c:2231
 kthread+0x35e/0x430 kernel/kthread.c:231
 ret_from_fork+0x31/0x40 arch/x86/entry/entry_64.S:430
Code: 3c 32 00 0f 85 70 0b 00 00 48 b8 00 02 00 00 00 00 ad de 49 89
47 78 e9 93 fe ff ff 49 8d 57 70 49 8d 5f 78 eb 9e e8 88 7a 14 fe <0f>
0b 48 8b 9d 28 fe ff ff e8 7a 7a 14 fe 48 b8 00 00 00 00 00
RIP: rollback_registered_many+0x348/0xeb0 RSP: ffff8800692de7f0
---[ end trace e0b29c57e9b3292c ]---

Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6mr.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 7f4265b..117405d 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -774,7 +774,8 @@ static struct net_device *ip6mr_reg_vif(struct net *net, struct mr6_table *mrt)
  *	Delete a VIF entry
  */
 
-static int mif6_delete(struct mr6_table *mrt, int vifi, struct list_head *head)
+static int mif6_delete(struct mr6_table *mrt, int vifi, int notify,
+		       struct list_head *head)
 {
 	struct mif_device *v;
 	struct net_device *dev;
@@ -820,7 +821,7 @@ static int mif6_delete(struct mr6_table *mrt, int vifi, struct list_head *head)
 					     dev->ifindex, &in6_dev->cnf);
 	}
 
-	if (v->flags & MIFF_REGISTER)
+	if ((v->flags & MIFF_REGISTER) && !notify)
 		unregister_netdevice_queue(dev, head);
 
 	dev_put(dev);
@@ -1331,7 +1332,6 @@ static int ip6mr_device_event(struct notifier_block *this,
 	struct mr6_table *mrt;
 	struct mif_device *v;
 	int ct;
-	LIST_HEAD(list);
 
 	if (event != NETDEV_UNREGISTER)
 		return NOTIFY_DONE;
@@ -1340,10 +1340,9 @@ static int ip6mr_device_event(struct notifier_block *this,
 		v = &mrt->vif6_table[0];
 		for (ct = 0; ct < mrt->maxvif; ct++, v++) {
 			if (v->dev == dev)
-				mif6_delete(mrt, ct, &list);
+				mif6_delete(mrt, ct, 1, NULL);
 		}
 	}
-	unregister_netdevice_many(&list);
 
 	return NOTIFY_DONE;
 }
@@ -1552,7 +1551,7 @@ static void mroute_clean_tables(struct mr6_table *mrt, bool all)
 	for (i = 0; i < mrt->maxvif; i++) {
 		if (!all && (mrt->vif6_table[i].flags & VIFF_STATIC))
 			continue;
-		mif6_delete(mrt, i, &list);
+		mif6_delete(mrt, i, 0, &list);
 	}
 	unregister_netdevice_many(&list);
 
@@ -1706,7 +1705,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
 		if (copy_from_user(&mifi, optval, sizeof(mifi_t)))
 			return -EFAULT;
 		rtnl_lock();
-		ret = mif6_delete(mrt, mifi, NULL);
+		ret = mif6_delete(mrt, mifi, 0, NULL);
 		rtnl_unlock();
 		return ret;
 
-- 
2.4.11


From b395af7a60a04afc8a14980806adeb90f90d3d17 Mon Sep 17 00:00:00 2001
From: Mohamad Haj Yahia <mohamad@mellanox.com>
Date: Thu, 30 Mar 2017 17:00:25 +0300
Subject: [PATCH 25/33] net/mlx5: Fix driver load bad flow when having fw
 initializing timeout

[ Upstream commit 55378a238e04b39cc82957d91d16499704ea719b ]

If FW is stuck in initializing state we will skip the driver load, but
current error handling flow doesn't clean previously allocated command
interface resources.

Fixes: e3297246c2c8 ('net/mlx5_core: Wait for FW readiness on startup')
Signed-off-by: Mohamad Haj Yahia <mohamad@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 7a196a0..d776db7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -966,7 +966,7 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 	if (err) {
 		dev_err(&dev->pdev->dev, "Firmware over %d MS in initializing state, aborting\n",
 			FW_INIT_TIMEOUT_MILI);
-		goto out_err;
+		goto err_cmd_cleanup;
 	}
 
 	err = mlx5_core_enable_hca(dev, 0);
-- 
2.4.11


From 6fb24f56ab3bcb7c04f466fe4f6b41c58de51f8d Mon Sep 17 00:00:00 2001
From: Eugenia Emantayev <eugenia@mellanox.com>
Date: Wed, 22 Mar 2017 11:44:14 +0200
Subject: [PATCH 26/33] net/mlx5e: Fix small packet threshold

[ Upstream commit cbad8cddb6ed7ef3a5f0a9a70f1711d4d7fb9a8f ]

RX packet headers are meant to be contained in SKB linear part,
and chose a threshold of 128.
It turns out this is not enough, i.e. for IPv6 packet over VxLAN.
In this case, UDP/IPv4 needs 42 bytes, GENEVE header is 8 bytes,
and 86 bytes for TCP/IPv6. In total 136 bytes that is more than
current 128 bytes. In this case expand header flow is reached.
The warning in skb_try_coalesce() caused by a wrong truesize
was already fixed here:
commit 158f323b9868 ("net: adjust skb->truesize in pskb_expand_head()").
Still, we prefer to totally avoid the expand header flow for performance reasons.
Tested regular TCP_STREAM with iperf for 1 and 8 streams, no degradation was found.

Fixes: 461017cb006a ("net/mlx5e: Support RX multi-packet WQE (Striding RQ)")
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 81d8e3b..21ce0b7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -82,7 +82,7 @@
 #define MLX5E_VALID_NUM_MTTS(num_mtts) (MLX5_MTT_OCTW(num_mtts) <= U16_MAX)
 
 #define MLX5_UMR_ALIGN				(2048)
-#define MLX5_MPWRQ_SMALL_PACKET_THRESHOLD	(128)
+#define MLX5_MPWRQ_SMALL_PACKET_THRESHOLD	(256)
 
 #define MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ                 (64 * 1024)
 #define MLX5E_DEFAULT_LRO_TIMEOUT                       32
-- 
2.4.11


From ec5cfa43fb5f73d3dcfcfd87f0b1d32ddc33e1d3 Mon Sep 17 00:00:00 2001
From: Ilan Tayari <ilant@mellanox.com>
Date: Thu, 2 Mar 2017 15:49:45 +0200
Subject: [PATCH 27/33] net/mlx5e: Fix ETHTOOL_GRXCLSRLALL handling

[ Upstream commit 5e82c9e4ed60beba83f46a1a5a8307b99a23e982 ]

Handler for ETHTOOL_GRXCLSRLALL must set info->data to the size
of the table, regardless of the amount of entries in it.
Existing code does not do that, and this breaks all usage of ethtool -N
or -n without explicit location, with this error:
rmgr: Invalid RX class rules table size: Success

Set info->data to the table size.

Tested:
ethtool -n ens8
ethtool -N ens8 flow-type ip4 src-ip 1.1.1.1 dst-ip 2.2.2.2 action 1
ethtool -N ens8 flow-type ip4 src-ip 1.1.1.1 dst-ip 2.2.2.2 action 1 loc 55
ethtool -n ens8
ethtool -N ens8 delete 1023
ethtool -N ens8 delete 55

Fixes: f913a72aa008 ("net/mlx5e: Add support to get ethtool flow rules")
Signed-off-by: Ilan Tayari <ilant@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index 90e81ae..e034dbc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -563,6 +563,7 @@ int mlx5e_ethtool_get_all_flows(struct mlx5e_priv *priv, struct ethtool_rxnfc *i
 	int idx = 0;
 	int err = 0;
 
+	info->data = MAX_NUM_OF_ETHTOOL_RULES;
 	while ((!err || err == -ENOENT) && idx < info->rule_cnt) {
 		err = mlx5e_ethtool_get_flow(priv, info, location);
 		if (!err)
-- 
2.4.11


From f8db69cf18e39ce4fd20147e909e2ae3f8981db9 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Thu, 20 Apr 2017 20:55:12 +0800
Subject: [PATCH 28/33] macvlan: Fix device ref leak when purging bc_queue

[ Upstream commit f6478218e6edc2a587b8f132f66373baa7b2497c ]

When a parent macvlan device is destroyed we end up purging its
broadcast queue without dropping the device reference count on
the packet source device.  This causes the source device to linger.

This patch drops that reference count.

Fixes: 260916dfb48c ("macvlan: Fix potential use-after free for...")
Reported-by: Joe Ghalam <Joe.Ghalam@dell.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macvlan.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 26d6f0b..dc8ccac 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -1140,6 +1140,7 @@ static int macvlan_port_create(struct net_device *dev)
 static void macvlan_port_destroy(struct net_device *dev)
 {
 	struct macvlan_port *port = macvlan_port_get_rtnl(dev);
+	struct sk_buff *skb;
 
 	dev->priv_flags &= ~IFF_MACVLAN_PORT;
 	netdev_rx_handler_unregister(dev);
@@ -1148,7 +1149,15 @@ static void macvlan_port_destroy(struct net_device *dev)
 	 * but we need to cancel it and purge left skbs if any.
 	 */
 	cancel_work_sync(&port->bc_work);
-	__skb_queue_purge(&port->bc_queue);
+
+	while ((skb = __skb_dequeue(&port->bc_queue))) {
+		const struct macvlan_dev *src = MACVLAN_SKB_CB(skb)->src;
+
+		if (src)
+			dev_put(src->dev);
+
+		kfree_skb(skb);
+	}
 
 	kfree_rcu(port, rcu);
 }
-- 
2.4.11


From 573d7d011d3ca09a81d8d718d40b504cebc8345f Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Tue, 25 Apr 2017 09:17:29 -0700
Subject: [PATCH 29/33] net: ipv6: regenerate host route if moved to gc list

[ Upstream commit 8048ced9beb21a52e3305f3332ae82020619f24e ]

Taking down the loopback device wreaks havoc on IPv6 routing. By
extension, taking down a VRF device wreaks havoc on its table.

Dmitry and Andrey both reported heap out-of-bounds reports in the IPv6
FIB code while running syzkaller fuzzer. The root cause is a dead dst
that is on the garbage list gets reinserted into the IPv6 FIB. While on
the gc (or perhaps when it gets added to the gc list) the dst->next is
set to an IPv4 dst. A subsequent walk of the ipv6 tables causes the
out-of-bounds access.

Andrey's reproducer was the key to getting to the bottom of this.

With IPv6, host routes for an address have the dst->dev set to the
loopback device. When the 'lo' device is taken down, rt6_ifdown initiates
a walk of the fib evicting routes with the 'lo' device which means all
host routes are removed. That process moves the dst which is attached to
an inet6_ifaddr to the gc list and marks it as dead.

The recent change to keep global IPv6 addresses added a new function,
fixup_permanent_addr, that is called on admin up. That function restarts
dad for an inet6_ifaddr and when it completes the host route attached
to it is inserted into the fib. Since the route was marked dead and
moved to the gc list, re-inserting the route causes the reported
out-of-bounds accesses. If the device with the address is taken down
or the address is removed, the WARN_ON in fib6_del is triggered.

All of those faults are fixed by regenerating the host route if the
existing one has been moved to the gc list, something that can be
determined by checking if the rt6i_ref counter is 0.

Fixes: f1705ec197e7 ("net: ipv6: Make address flushing on ifdown optional")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index cbcc991..cffdbdb 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3253,14 +3253,24 @@ static void addrconf_gre_config(struct net_device *dev)
 static int fixup_permanent_addr(struct inet6_dev *idev,
 				struct inet6_ifaddr *ifp)
 {
-	if (!ifp->rt) {
-		struct rt6_info *rt;
+	/* rt6i_ref == 0 means the host route was removed from the
+	 * FIB, for example, if 'lo' device is taken down. In that
+	 * case regenerate the host route.
+	 */
+	if (!ifp->rt || !atomic_read(&ifp->rt->rt6i_ref)) {
+		struct rt6_info *rt, *prev;
 
 		rt = addrconf_dst_alloc(idev, &ifp->addr, false);
 		if (unlikely(IS_ERR(rt)))
 			return PTR_ERR(rt);
 
+		/* ifp->rt can be accessed outside of rtnl */
+		spin_lock(&ifp->lock);
+		prev = ifp->rt;
 		ifp->rt = rt;
+		spin_unlock(&ifp->lock);
+
+		ip6_rt_put(prev);
 	}
 
 	if (!(ifp->flags & IFA_F_NOPREFIXROUTE)) {
-- 
2.4.11


From 8f836bdab9db8dabc03f416d26a1cfaec7cbbe09 Mon Sep 17 00:00:00 2001
From: Alexander Kochetkov <al.kochet@gmail.com>
Date: Thu, 20 Apr 2017 14:00:04 +0300
Subject: [PATCH 30/33] net: phy: fix auto-negotiation stall due to unavailable
 interrupt

[ Upstream commit f555f34fdc586a56204cd16d9a7c104ec6cb6650 ]

The Ethernet link on an interrupt driven PHY was not coming up if the Ethernet
cable was plugged before the Ethernet interface was brought up.

The patch trigger PHY state machine to update link state if PHY was requested to
do auto-negotiation and auto-negotiation complete flag already set.

During power-up cycle the PHY do auto-negotiation, generate interrupt and set
auto-negotiation complete flag. Interrupt is handled by PHY state machine but
doesn't update link state because PHY is in PHY_READY state. After some time
MAC bring up, start and request PHY to do auto-negotiation. If there are no new
settings to advertise genphy_config_aneg() doesn't start PHY auto-negotiation.
PHY continue to stay in auto-negotiation complete state and doesn't fire
interrupt. At the same time PHY state machine expect that PHY started
auto-negotiation and is waiting for interrupt from PHY and it won't get it.

Fixes: 321beec5047a ("net: phy: Use interrupts when available in NOLINK state")
Signed-off-by: Alexander Kochetkov <al.kochet@gmail.com>
Cc: stable <stable@vger.kernel.org> # v4.9+
Tested-by: Roger Quadros <rogerq@ti.com>
Tested-by: Alexandre Belloni <alexandre.belloni@free-electrons.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 40 ++++++++++++++++++++++++++++++++++++----
 include/linux/phy.h   |  1 +
 2 files changed, 37 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 56fe169..a9be26f 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -552,16 +552,18 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd)
 EXPORT_SYMBOL(phy_mii_ioctl);
 
 /**
- * phy_start_aneg - start auto-negotiation for this PHY device
+ * phy_start_aneg_priv - start auto-negotiation for this PHY device
  * @phydev: the phy_device struct
+ * @sync: indicate whether we should wait for the workqueue cancelation
  *
  * Description: Sanitizes the settings (if we're not autonegotiating
  *   them), and then calls the driver's config_aneg function.
  *   If the PHYCONTROL Layer is operating, we change the state to
  *   reflect the beginning of Auto-negotiation or forcing.
  */
-int phy_start_aneg(struct phy_device *phydev)
+static int phy_start_aneg_priv(struct phy_device *phydev, bool sync)
 {
+	bool trigger = 0;
 	int err;
 
 	mutex_lock(&phydev->lock);
@@ -586,10 +588,40 @@ int phy_start_aneg(struct phy_device *phydev)
 		}
 	}
 
+	/* Re-schedule a PHY state machine to check PHY status because
+	 * negotiation may already be done and aneg interrupt may not be
+	 * generated.
+	 */
+	if (phy_interrupt_is_valid(phydev) && (phydev->state == PHY_AN)) {
+		err = phy_aneg_done(phydev);
+		if (err > 0) {
+			trigger = true;
+			err = 0;
+		}
+	}
+
 out_unlock:
 	mutex_unlock(&phydev->lock);
+
+	if (trigger)
+		phy_trigger_machine(phydev, sync);
+
 	return err;
 }
+
+/**
+ * phy_start_aneg - start auto-negotiation for this PHY device
+ * @phydev: the phy_device struct
+ *
+ * Description: Sanitizes the settings (if we're not autonegotiating
+ *   them), and then calls the driver's config_aneg function.
+ *   If the PHYCONTROL Layer is operating, we change the state to
+ *   reflect the beginning of Auto-negotiation or forcing.
+ */
+int phy_start_aneg(struct phy_device *phydev)
+{
+	return phy_start_aneg_priv(phydev, true);
+}
 EXPORT_SYMBOL(phy_start_aneg);
 
 /**
@@ -617,7 +649,7 @@ void phy_start_machine(struct phy_device *phydev)
  *   state machine runs.
  */
 
-static void phy_trigger_machine(struct phy_device *phydev, bool sync)
+void phy_trigger_machine(struct phy_device *phydev, bool sync)
 {
 	if (sync)
 		cancel_delayed_work_sync(&phydev->state_queue);
@@ -1100,7 +1132,7 @@ void phy_state_machine(struct work_struct *work)
 	mutex_unlock(&phydev->lock);
 
 	if (needs_aneg)
-		err = phy_start_aneg(phydev);
+		err = phy_start_aneg_priv(phydev, false);
 	else if (do_suspend)
 		phy_suspend(phydev);
 
diff --git a/include/linux/phy.h b/include/linux/phy.h
index e25f183..bd22670 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -806,6 +806,7 @@ void phy_change(struct work_struct *work);
 void phy_mac_interrupt(struct phy_device *phydev, int new_link);
 void phy_start_machine(struct phy_device *phydev);
 void phy_stop_machine(struct phy_device *phydev);
+void phy_trigger_machine(struct phy_device *phydev, bool sync);
 int phy_ethtool_sset(struct phy_device *phydev, struct ethtool_cmd *cmd);
 int phy_ethtool_gset(struct phy_device *phydev, struct ethtool_cmd *cmd);
 int phy_ethtool_ksettings_get(struct phy_device *phydev,
-- 
2.4.11


From 911d4e1133d4a15194aafb616940f6c988e690b1 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Tue, 25 Apr 2017 14:37:15 -0700
Subject: [PATCH 31/33] ipv6: check skb->protocol before lookup for nexthop

[ Upstream commit 199ab00f3cdb6f154ea93fa76fd80192861a821d ]

Andrey reported a out-of-bound access in ip6_tnl_xmit(), this
is because we use an ipv4 dst in ip6_tnl_xmit() and cast an IPv4
neigh key as an IPv6 address:

        neigh = dst_neigh_lookup(skb_dst(skb),
                                 &ipv6_hdr(skb)->daddr);
        if (!neigh)
                goto tx_err_link_failure;

        addr6 = (struct in6_addr *)&neigh->primary_key; // <=== HERE
        addr_type = ipv6_addr_type(addr6);

        if (addr_type == IPV6_ADDR_ANY)
                addr6 = &ipv6_hdr(skb)->daddr;

        memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr));

Also the network header of the skb at this point should be still IPv4
for 4in6 tunnels, we shold not just use it as IPv6 header.

This patch fixes it by checking if skb->protocol is ETH_P_IPV6: if it
is, we are safe to do the nexthop lookup using skb_dst() and
ipv6_hdr(skb)->daddr; if not (aka IPv4), we have no clue about which
dest address we can pick here, we have to rely on callers to fill it
from tunnel config, so just fall to ip6_route_output() to make the
decision.

Fixes: ea3dc9601bda ("ip6_tunnel: Add support for wildcard tunnel endpoints.")
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 34 ++++++++++++++++++----------------
 1 file changed, 18 insertions(+), 16 deletions(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index f6ba452..116b4da 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1037,7 +1037,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 	struct ip6_tnl *t = netdev_priv(dev);
 	struct net *net = t->net;
 	struct net_device_stats *stats = &t->dev->stats;
-	struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+	struct ipv6hdr *ipv6h;
 	struct ipv6_tel_txoption opt;
 	struct dst_entry *dst = NULL, *ndst = NULL;
 	struct net_device *tdev;
@@ -1057,26 +1057,28 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 
 	/* NBMA tunnel */
 	if (ipv6_addr_any(&t->parms.raddr)) {
-		struct in6_addr *addr6;
-		struct neighbour *neigh;
-		int addr_type;
+		if (skb->protocol == htons(ETH_P_IPV6)) {
+			struct in6_addr *addr6;
+			struct neighbour *neigh;
+			int addr_type;
 
-		if (!skb_dst(skb))
-			goto tx_err_link_failure;
+			if (!skb_dst(skb))
+				goto tx_err_link_failure;
 
-		neigh = dst_neigh_lookup(skb_dst(skb),
-					 &ipv6_hdr(skb)->daddr);
-		if (!neigh)
-			goto tx_err_link_failure;
+			neigh = dst_neigh_lookup(skb_dst(skb),
+						 &ipv6_hdr(skb)->daddr);
+			if (!neigh)
+				goto tx_err_link_failure;
 
-		addr6 = (struct in6_addr *)&neigh->primary_key;
-		addr_type = ipv6_addr_type(addr6);
+			addr6 = (struct in6_addr *)&neigh->primary_key;
+			addr_type = ipv6_addr_type(addr6);
 
-		if (addr_type == IPV6_ADDR_ANY)
-			addr6 = &ipv6_hdr(skb)->daddr;
+			if (addr_type == IPV6_ADDR_ANY)
+				addr6 = &ipv6_hdr(skb)->daddr;
 
-		memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr));
-		neigh_release(neigh);
+			memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr));
+			neigh_release(neigh);
+		}
 	} else if (!(t->parms.flags &
 		     (IP6_TNL_F_USE_ORIG_TCLASS | IP6_TNL_F_USE_ORIG_FWMARK))) {
 		/* enable the cache only only if the routing decision does
-- 
2.4.11


From c53d10495cd395666f60680d83a85e8292ac0297 Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Tue, 25 Apr 2017 17:38:02 -0700
Subject: [PATCH 32/33] tcp: memset ca_priv data to 0 properly

[ Upstream commit c1201444075009507a6818de6518e2822b9a87c8 ]

Always zero out ca_priv data in tcp_assign_congestion_control() so that
ca_priv data is cleared out during socket creation.
Also always zero out ca_priv data in tcp_reinit_congestion_control() so
that when cc algorithm is changed, ca_priv data is cleared out as well.
We should still zero out ca_priv data even in TCP_CLOSE state because
user could call connect() on AF_UNSPEC to disconnect the socket and
leave it in TCP_CLOSE state and later call setsockopt() to switch cc
algorithm on this socket.

Fixes: 2b0a8c9ee ("tcp: add CDG congestion control")
Reported-by: Andrey Konovalov  <andreyknvl@google.com>
Signed-off-by: Wei Wang <weiwan@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_cong.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index f9038d6b..baea5df 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -167,12 +167,8 @@ void tcp_assign_congestion_control(struct sock *sk)
 	}
 out:
 	rcu_read_unlock();
+	memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
 
-	/* Clear out private data before diag gets it and
-	 * the ca has not been initialized.
-	 */
-	if (ca->get_info)
-		memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
 	if (ca->flags & TCP_CONG_NEEDS_ECN)
 		INET_ECN_xmit(sk);
 	else
@@ -199,11 +195,10 @@ static void tcp_reinit_congestion_control(struct sock *sk,
 	tcp_cleanup_congestion_control(sk);
 	icsk->icsk_ca_ops = ca;
 	icsk->icsk_ca_setsockopt = 1;
+	memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
 
-	if (sk->sk_state != TCP_CLOSE) {
-		memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
+	if (sk->sk_state != TCP_CLOSE)
 		tcp_init_congestion_control(sk);
-	}
 }
 
 /* Manage refcounts on socket close. */
-- 
2.4.11


From f2c20178f2342305f83f295e607f35c1e9cdcf05 Mon Sep 17 00:00:00 2001
From: Jamie Bainbridge <jbainbri@redhat.com>
Date: Wed, 26 Apr 2017 10:43:27 +1000
Subject: [PATCH 33/33] ipv6: check raw payload size correctly in ioctl

[ Upstream commit 105f5528b9bbaa08b526d3405a5bcd2ff0c953c8 ]

In situations where an skb is paged, the transport header pointer and
tail pointer can be the same because the skb contents are in frags.

This results in ioctl(SIOCINQ/FIONREAD) incorrectly returning a
length of 0 when the length to receive is actually greater than zero.

skb->len is already correctly set in ip6_input_finish() with
pskb_pull(), so use skb->len as it always returns the correct result
for both linear and paged data.

Signed-off-by: Jamie Bainbridge <jbainbri@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/raw.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 869ffc7..ced3817 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -1171,8 +1171,7 @@ static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg)
 		spin_lock_bh(&sk->sk_receive_queue.lock);
 		skb = skb_peek(&sk->sk_receive_queue);
 		if (skb)
-			amount = skb_tail_pointer(skb) -
-				skb_transport_header(skb);
+			amount = skb->len;
 		spin_unlock_bh(&sk->sk_receive_queue.lock);
 		return put_user(amount, (int __user *)arg);
 	}
-- 
2.4.11


[-- Attachment #3: net_410.mbox --]
[-- Type: Application/Octet-Stream, Size: 102818 bytes --]

From 5e372b95406ee0afdbb92f3e66d508ba16d84b3c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 23 Mar 2017 12:39:21 -0700
Subject: [PATCH 01/41] net: neigh: guard against NULL solicit() method

[ Upstream commit 48481c8fa16410ffa45939b13b6c53c2ca609e5f ]

Dmitry posted a nice reproducer of a bug triggering in neigh_probe()
when dereferencing a NULL neigh->ops->solicit method.

This can happen for arp_direct_ops/ndisc_direct_ops and similar,
which can be used for NUD_NOARP neighbours (created when dev->header_ops
is NULL). Admin can then force changing nud_state to some other state
that would fire neigh timer.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index e7c12ca..4526cbd 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -860,7 +860,8 @@ static void neigh_probe(struct neighbour *neigh)
 	if (skb)
 		skb = skb_clone(skb, GFP_ATOMIC);
 	write_unlock(&neigh->lock);
-	neigh->ops->solicit(neigh, skb);
+	if (neigh->ops->solicit)
+		neigh->ops->solicit(neigh, skb);
 	atomic_inc(&neigh->probes);
 	kfree_skb(skb);
 }
-- 
2.4.11


From 1fafc23c6add76b9b300317e1de188da63362d43 Mon Sep 17 00:00:00 2001
From: Nathan Sullivan <nathan.sullivan@ni.com>
Date: Wed, 22 Mar 2017 15:27:01 -0500
Subject: [PATCH 02/41] net: phy: handle state correctly in phy_stop_machine

[ Upstream commit 49d52e8108a21749dc2114b924c907db43358984 ]

If the PHY is halted on stop, then do not set the state to PHY_UP.  This
ensures the phy will be restarted later in phy_start when the machine is
started again.

Fixes: 00db8189d984 ("This patch adds a PHY Abstraction Layer to the Linux Kernel, enabling ethernet drivers to remain as ignorant as is reasonable of the connected PHY's design and operation details.")
Signed-off-by: Nathan Sullivan <nathan.sullivan@ni.com>
Signed-off-by: Brad Mouring <brad.mouring@ni.com>
Acked-by: Xander Huff <xander.huff@ni.com>
Acked-by: Kyle Roeschley <kyle.roeschley@ni.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 7cc1b7d..fe2d4c4 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -678,7 +678,7 @@ void phy_stop_machine(struct phy_device *phydev)
 	cancel_delayed_work_sync(&phydev->state_queue);
 
 	mutex_lock(&phydev->lock);
-	if (phydev->state > PHY_UP)
+	if (phydev->state > PHY_UP && phydev->state != PHY_HALTED)
 		phydev->state = PHY_UP;
 	mutex_unlock(&phydev->lock);
 }
-- 
2.4.11


From bef856a937762df6f59936271866da6f3e545dbd Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Thu, 23 Mar 2017 11:03:31 -0700
Subject: [PATCH 03/41] kcm: return immediately after copy_from_user() failure

[ Upstream commit a80db69e47d764bbcaf2fec54b1f308925e7c490 ]

There is no reason to continue after a copy_from_user()
failure.

Fixes: ab7ac4eb9832 ("kcm: Kernel Connection Multiplexor module")
Cc: Tom Herbert <tom@herbertland.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/kcm/kcmsock.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index a646f34..fecad10 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -1685,7 +1685,7 @@ static int kcm_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 		struct kcm_attach info;
 
 		if (copy_from_user(&info, (void __user *)arg, sizeof(info)))
-			err = -EFAULT;
+			return -EFAULT;
 
 		err = kcm_attach_ioctl(sock, &info);
 
@@ -1695,7 +1695,7 @@ static int kcm_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 		struct kcm_unattach info;
 
 		if (copy_from_user(&info, (void __user *)arg, sizeof(info)))
-			err = -EFAULT;
+			return -EFAULT;
 
 		err = kcm_unattach_ioctl(sock, &info);
 
@@ -1706,7 +1706,7 @@ static int kcm_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 		struct socket *newsock = NULL;
 
 		if (copy_from_user(&info, (void __user *)arg, sizeof(info)))
-			err = -EFAULT;
+			return -EFAULT;
 
 		err = kcm_clone(sock, &info, &newsock);
 
-- 
2.4.11


From 6f46b05f8b24fede634608d574f33abfa1e34ebb Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Sat, 25 Mar 2017 10:58:24 +0100
Subject: [PATCH 04/41] secure_seq: downgrade to per-host timestamp offsets

[ Upstream commit 28ee1b746f493b7c62347d714f58fbf4f70df4f0 ]

Unfortunately too many devices (not under our control) use tcp_tw_recycle=1,
which depends on timestamps being identical of the same saddr.

Although tcp_tw_recycle got removed in net-next we can't make
such end hosts disappear so downgrade to per-host timestamp offsets.

4.10 note: original patch uses siphash (added in 4.11), since
ts_off is only used to obscure uptime (and doesn't use same secret
as isn generator) this uses jhash instead.

Cc: Soheil Hassas Yeganeh <soheil@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Reported-by: Yvan Vanrossomme <yvan@vanrossomme.net>
Fixes: 95a22caee396c ("tcp: randomize tcp timestamp offsets for each connection")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/secure_seq.c | 29 +++++++++++++++++++++++++++--
 1 file changed, 27 insertions(+), 2 deletions(-)

diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
index 88a8e42..0fd4217 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -16,9 +16,11 @@
 #define NET_SECRET_SIZE (MD5_MESSAGE_BYTES / 4)
 
 static u32 net_secret[NET_SECRET_SIZE] ____cacheline_aligned;
+static u32 ts_secret[2];
 
 static __always_inline void net_secret_init(void)
 {
+	net_get_random_once(ts_secret, sizeof(ts_secret));
 	net_get_random_once(net_secret, sizeof(net_secret));
 }
 #endif
@@ -41,6 +43,21 @@ static u32 seq_scale(u32 seq)
 #endif
 
 #if IS_ENABLED(CONFIG_IPV6)
+static u32 secure_tcpv6_ts_off(const __be32 *saddr, const __be32 *daddr)
+{
+	u32 hash[4 + 4 + 1];
+
+	if (sysctl_tcp_timestamps != 1)
+		return 0;
+
+	memcpy(hash, saddr, 16);
+	memcpy(hash + 4, daddr, 16);
+
+	hash[8] = ts_secret[0];
+
+	return jhash2(hash, ARRAY_SIZE(hash), ts_secret[1]);
+}
+
 u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr,
 				 __be16 sport, __be16 dport, u32 *tsoff)
 {
@@ -59,7 +76,7 @@ u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr,
 
 	md5_transform(hash, secret);
 
-	*tsoff = sysctl_tcp_timestamps == 1 ? hash[1] : 0;
+	*tsoff = secure_tcpv6_ts_off(saddr, daddr);
 	return seq_scale(hash[0]);
 }
 EXPORT_SYMBOL(secure_tcpv6_sequence_number);
@@ -87,6 +104,14 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral);
 #endif
 
 #ifdef CONFIG_INET
+static u32 secure_tcp_ts_off(__be32 saddr, __be32 daddr)
+{
+	if (sysctl_tcp_timestamps != 1)
+		return 0;
+
+	return jhash_3words((__force u32)saddr, (__force u32)daddr,
+			    ts_secret[0], ts_secret[1]);
+}
 
 u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
 			       __be16 sport, __be16 dport, u32 *tsoff)
@@ -101,7 +126,7 @@ u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
 
 	md5_transform(hash, net_secret);
 
-	*tsoff = sysctl_tcp_timestamps == 1 ? hash[1] : 0;
+	*tsoff = secure_tcp_ts_off(saddr, daddr);
 	return seq_scale(hash[0]);
 }
 
-- 
2.4.11


From 3e5896fadb2b0ab4e25e589f638409b4b10cfd6a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 24 Mar 2017 19:36:13 -0700
Subject: [PATCH 05/41] ping: implement proper locking

[ Upstream commit 43a6684519ab0a6c52024b5e25322476cabad893 ]

We got a report of yet another bug in ping

http://www.openwall.com/lists/oss-security/2017/03/24/6

->disconnect() is not called with socket lock held.

Fix this by acquiring ping rwlock earlier.

Thanks to Daniel, Alexander and Andrey for letting us know this problem.

Fixes: c319b4d76b9e ("net: ipv4: add IPPROTO_ICMP socket kind")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Daniel Jiang <danieljiang0415@gmail.com>
Reported-by: Solar Designer <solar@openwall.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ping.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 68d77b1..51e2f3c 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -156,17 +156,18 @@ int ping_hash(struct sock *sk)
 void ping_unhash(struct sock *sk)
 {
 	struct inet_sock *isk = inet_sk(sk);
+
 	pr_debug("ping_unhash(isk=%p,isk->num=%u)\n", isk, isk->inet_num);
+	write_lock_bh(&ping_table.lock);
 	if (sk_hashed(sk)) {
-		write_lock_bh(&ping_table.lock);
 		hlist_nulls_del(&sk->sk_nulls_node);
 		sk_nulls_node_init(&sk->sk_nulls_node);
 		sock_put(sk);
 		isk->inet_num = 0;
 		isk->inet_sport = 0;
 		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
-		write_unlock_bh(&ping_table.lock);
 	}
+	write_unlock_bh(&ping_table.lock);
 }
 EXPORT_SYMBOL_GPL(ping_unhash);
 
-- 
2.4.11


From 874cc4dd7b11300f43e845ce2a5a1da9645dbbf6 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@fb.com>
Date: Fri, 24 Mar 2017 15:57:33 -0700
Subject: [PATCH 06/41] bpf: improve verifier packet range checks

[ Upstream commit b1977682a3858b5584ffea7cfb7bd863f68db18d ]

llvm can optimize the 'if (ptr > data_end)' checks to be in the order
slightly different than the original C code which will confuse verifier.
Like:
if (ptr + 16 > data_end)
  return TC_ACT_SHOT;
// may be followed by
if (ptr + 14 > data_end)
  return TC_ACT_SHOT;
while llvm can see that 'ptr' is valid for all 16 bytes,
the verifier could not.
Fix verifier logic to account for such case and add a test.

Reported-by: Huapeng Zhou <hzhou@fb.com>
Fixes: 969bf05eb3ce ("bpf: direct packet access")
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c                       |  5 +++--
 tools/testing/selftests/bpf/test_verifier.c | 20 ++++++++++++++++++++
 2 files changed, 23 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index cdc43b8..f3c938b 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1859,14 +1859,15 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state,
 
 	for (i = 0; i < MAX_BPF_REG; i++)
 		if (regs[i].type == PTR_TO_PACKET && regs[i].id == dst_reg->id)
-			regs[i].range = dst_reg->off;
+			/* keep the maximum range already checked */
+			regs[i].range = max(regs[i].range, dst_reg->off);
 
 	for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
 		if (state->stack_slot_type[i] != STACK_SPILL)
 			continue;
 		reg = &state->spilled_regs[i / BPF_REG_SIZE];
 		if (reg->type == PTR_TO_PACKET && reg->id == dst_reg->id)
-			reg->range = dst_reg->off;
+			reg->range = max(reg->range, dst_reg->off);
 	}
 }
 
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 853d7e4..e1aea9e 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -2876,6 +2876,26 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_LWT_XMIT,
 	},
 	{
+		"overlapping checks for direct packet access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 4),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_2, 6),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_LWT_XMIT,
+	},
+	{
 		"invalid access of tc_classid for LWT_IN",
 		.insns = {
 			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-- 
2.4.11


From b070d9f65248147e1f66fb418cabb031b741ef96 Mon Sep 17 00:00:00 2001
From: Talat Batheesh <talatb@mellanox.com>
Date: Tue, 28 Mar 2017 16:13:41 +0300
Subject: [PATCH 07/41] net/mlx5: Avoid dereferencing uninitialized pointer

[ Upstream commit e497ec680c4cd51e76bfcdd49363d9ab8d32a757 ]

In NETDEV_CHANGEUPPER event the upper_info field is valid
only when linking is true. Otherwise it should be ignored.

Fixes: 7907f23adc18 (net/mlx5: Implement RoCE LAG feature)
Signed-off-by: Talat Batheesh <talatb@mellanox.com>
Reviewed-by: Aviv Heller <avivh@mellanox.com>
Reviewed-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/lag.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index 5595724..b5d5519 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -294,7 +294,7 @@ static int mlx5_handle_changeupper_event(struct mlx5_lag *ldev,
 					 struct netdev_notifier_changeupper_info *info)
 {
 	struct net_device *upper = info->upper_dev, *ndev_tmp;
-	struct netdev_lag_upper_info *lag_upper_info;
+	struct netdev_lag_upper_info *lag_upper_info = NULL;
 	bool is_bonded;
 	int bond_status = 0;
 	int num_slaves = 0;
@@ -303,7 +303,8 @@ static int mlx5_handle_changeupper_event(struct mlx5_lag *ldev,
 	if (!netif_is_lag_master(upper))
 		return 0;
 
-	lag_upper_info = info->upper_info;
+	if (info->linking)
+		lag_upper_info = info->upper_info;
 
 	/* The event may still be of interest if the slave does not belong to
 	 * us, but is enslaved to a master which has one or more of our netdevs
-- 
2.4.11


From 3870536d265856982201a49c4374024bc62cf666 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Wed, 29 Mar 2017 08:44:59 +0200
Subject: [PATCH 08/41] l2tp: hold tunnel socket when handling control frames
 in l2tp_ip and l2tp_ip6

[ Upstream commit 94d7ee0baa8b764cf64ad91ed69464c1a6a0066b ]

The code following l2tp_tunnel_find() expects that a new reference is
held on sk. Either sk_receive_skb() or the discard_put error path will
drop a reference from the tunnel's socket.

This issue exists in both l2tp_ip and l2tp_ip6.

Fixes: a3c18422a4b4 ("l2tp: hold socket before dropping lock in l2tp_ip{, 6}_recv()")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ip.c  | 5 +++--
 net/l2tp/l2tp_ip6.c | 5 +++--
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 3ed3015..fa2bcfc 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -171,9 +171,10 @@ static int l2tp_ip_recv(struct sk_buff *skb)
 
 	tunnel_id = ntohl(*(__be32 *) &skb->data[4]);
 	tunnel = l2tp_tunnel_find(net, tunnel_id);
-	if (tunnel != NULL)
+	if (tunnel) {
 		sk = tunnel->sock;
-	else {
+		sock_hold(sk);
+	} else {
 		struct iphdr *iph = (struct iphdr *) skb_network_header(skb);
 
 		read_lock_bh(&l2tp_ip_lock);
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index f47c452..4e4fa15 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -183,9 +183,10 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
 
 	tunnel_id = ntohl(*(__be32 *) &skb->data[4]);
 	tunnel = l2tp_tunnel_find(net, tunnel_id);
-	if (tunnel != NULL)
+	if (tunnel) {
 		sk = tunnel->sock;
-	else {
+		sock_hold(sk);
+	} else {
 		struct ipv6hdr *iph = ipv6_hdr(skb);
 
 		read_lock_bh(&l2tp_ip6_lock);
-- 
2.4.11


From b5df48b60a63eea9944ef85252e9af943d94851c Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Wed, 29 Mar 2017 08:45:29 +0200
Subject: [PATCH 09/41] l2tp: purge socket queues in the .destruct() callback

[ Upstream commit e91793bb615cf6cdd59c0b6749fe173687bb0947 ]

The Rx path may grab the socket right before pppol2tp_release(), but
nothing guarantees that it will enqueue packets before
skb_queue_purge(). Therefore, the socket can be destroyed without its
queues fully purged.

Fix this by purging queues in pppol2tp_session_destruct() where we're
guaranteed nothing is still referencing the socket.

Fixes: 9e9cb6221aa7 ("l2tp: fix userspace reception on plain L2TP sockets")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ppp.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 36cc56f..123b6a2 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -450,6 +450,10 @@ static void pppol2tp_session_close(struct l2tp_session *session)
 static void pppol2tp_session_destruct(struct sock *sk)
 {
 	struct l2tp_session *session = sk->sk_user_data;
+
+	skb_queue_purge(&sk->sk_receive_queue);
+	skb_queue_purge(&sk->sk_write_queue);
+
 	if (session) {
 		sk->sk_user_data = NULL;
 		BUG_ON(session->magic != L2TP_SESSION_MAGIC);
@@ -488,9 +492,6 @@ static int pppol2tp_release(struct socket *sock)
 		l2tp_session_queue_purge(session);
 		sock_put(sk);
 	}
-	skb_queue_purge(&sk->sk_receive_queue);
-	skb_queue_purge(&sk->sk_write_queue);
-
 	release_sock(sk);
 
 	/* This will delete the session context via
-- 
2.4.11


From 77e3bf168bb5a9fb36e5abc0d7392e2c1077b93f Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Wed, 29 Mar 2017 16:11:21 +0200
Subject: [PATCH 10/41] net/packet: fix overflow in check for tp_frame_nr

[ Upstream commit 8f8d28e4d6d815a391285e121c3a53a0b6cb9e7b ]

When calculating rb->frames_per_block * req->tp_block_nr the result
can overflow.

Add a check that tp_block_size * tp_block_nr <= UINT_MAX.

Since frames_per_block <= tp_block_size, the expression would
never overflow.

Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 5c91993..624d188 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -4189,6 +4189,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 		rb->frames_per_block = req->tp_block_size / req->tp_frame_size;
 		if (unlikely(rb->frames_per_block == 0))
 			goto out;
+		if (unlikely(req->tp_block_size > UINT_MAX / req->tp_block_nr))
+			goto out;
 		if (unlikely((rb->frames_per_block * req->tp_block_nr) !=
 					req->tp_frame_nr))
 			goto out;
-- 
2.4.11


From c2da497e23a4e7db1cdf570fbbc3651c8790224b Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Wed, 29 Mar 2017 16:11:22 +0200
Subject: [PATCH 11/41] net/packet: fix overflow in check for tp_reserve

[ Upstream commit bcc5364bdcfe131e6379363f089e7b4108d35b70 ]

When calculating po->tp_hdrlen + po->tp_reserve the result can overflow.

Fix by checking that tp_reserve <= INT_MAX on assign.

Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 624d188..0f074c9 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3644,6 +3644,8 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 			return -EBUSY;
 		if (copy_from_user(&val, optval, sizeof(val)))
 			return -EFAULT;
+		if (val > INT_MAX)
+			return -EINVAL;
 		po->tp_reserve = val;
 		return 0;
 	}
-- 
2.4.11


From 7bcd282625fb5321db84b2c57aabcbf87c45c991 Mon Sep 17 00:00:00 2001
From: Yi-Hung Wei <yihung.wei@gmail.com>
Date: Thu, 30 Mar 2017 12:36:03 -0700
Subject: [PATCH 12/41] openvswitch: Fix ovs_flow_key_update()

[ Upstream commit 6f56f6186c18e3fd54122b73da68e870687b8c59 ]

ovs_flow_key_update() is called when the flow key is invalid, and it is
used to update and revalidate the flow key. Commit 329f45bc4f19
("openvswitch: add mac_proto field to the flow key") introduces mac_proto
field to flow key and use it to determine whether the flow key is valid.
However, the commit does not update the code path in ovs_flow_key_update()
to revalidate the flow key which may cause BUG_ON() on execute_recirc().
This patch addresses the aforementioned issue.

Fixes: 329f45bc4f19 ("openvswitch: add mac_proto field to the flow key")
Signed-off-by: Yi-Hung Wei <yihung.wei@gmail.com>
Acked-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/flow.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 2c0a00f..bb78935 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -527,7 +527,7 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 
 	/* Link layer. */
 	clear_vlan(key);
-	if (key->mac_proto == MAC_PROTO_NONE) {
+	if (ovs_key_mac_proto(key) == MAC_PROTO_NONE) {
 		if (unlikely(eth_type_vlan(skb->protocol)))
 			return -EINVAL;
 
@@ -745,7 +745,13 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 
 int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key)
 {
-	return key_extract(skb, key);
+	int res;
+
+	res = key_extract(skb, key);
+	if (!res)
+		key->mac_proto &= ~SW_FLOW_KEY_INVALID;
+
+	return res;
 }
 
 static int key_extract_mac_proto(struct sk_buff *skb)
-- 
2.4.11


From 692703d5207bfb2d355e0c718e871fe307783c19 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Mon, 3 Apr 2017 12:03:13 +0200
Subject: [PATCH 13/41] l2tp: take reference on sessions being dumped

[ Upstream commit e08293a4ccbcc993ded0fdc46f1e57926b833d63 ]

Take a reference on the sessions returned by l2tp_session_find_nth()
(and rename it l2tp_session_get_nth() to reflect this change), so that
caller is assured that the session isn't going to disappear while
processing it.

For procfs and debugfs handlers, the session is held in the .start()
callback and dropped in .show(). Given that pppol2tp_seq_session_show()
dereferences the associated PPPoL2TP socket and that
l2tp_dfs_seq_session_show() might call pppol2tp_show(), we also need to
call the session's .ref() callback to prevent the socket from going
away from under us.

Fixes: fd558d186df2 ("l2tp: Split pppol2tp patch into separate l2tp and ppp parts")
Fixes: 0ad6614048cf ("l2tp: Add debugfs files for dumping l2tp debug info")
Fixes: 309795f4bec2 ("l2tp: Add netlink control API for L2TP")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c    |  8 ++++++--
 net/l2tp/l2tp_core.h    |  3 ++-
 net/l2tp/l2tp_debugfs.c | 10 +++++++---
 net/l2tp/l2tp_netlink.c |  7 +++++--
 net/l2tp/l2tp_ppp.c     | 10 +++++++---
 5 files changed, 27 insertions(+), 11 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 85948c6..56036ab 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -278,7 +278,8 @@ struct l2tp_session *l2tp_session_find(struct net *net, struct l2tp_tunnel *tunn
 }
 EXPORT_SYMBOL_GPL(l2tp_session_find);
 
-struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth)
+struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth,
+					  bool do_ref)
 {
 	int hash;
 	struct l2tp_session *session;
@@ -288,6 +289,9 @@ struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth)
 	for (hash = 0; hash < L2TP_HASH_SIZE; hash++) {
 		hlist_for_each_entry(session, &tunnel->session_hlist[hash], hlist) {
 			if (++count > nth) {
+				l2tp_session_inc_refcount(session);
+				if (do_ref && session->ref)
+					session->ref(session);
 				read_unlock_bh(&tunnel->hlist_lock);
 				return session;
 			}
@@ -298,7 +302,7 @@ struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth)
 
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(l2tp_session_find_nth);
+EXPORT_SYMBOL_GPL(l2tp_session_get_nth);
 
 /* Lookup a session by interface name.
  * This is very inefficient but is only used by management interfaces.
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index aebf281..221648b 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -233,7 +233,8 @@ static inline struct l2tp_tunnel *l2tp_sock_to_tunnel(struct sock *sk)
 struct l2tp_session *l2tp_session_find(struct net *net,
 				       struct l2tp_tunnel *tunnel,
 				       u32 session_id);
-struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth);
+struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth,
+					  bool do_ref);
 struct l2tp_session *l2tp_session_find_by_ifname(struct net *net, char *ifname);
 struct l2tp_tunnel *l2tp_tunnel_find(struct net *net, u32 tunnel_id);
 struct l2tp_tunnel *l2tp_tunnel_find_nth(struct net *net, int nth);
diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c
index 2d6760a..d100aed 100644
--- a/net/l2tp/l2tp_debugfs.c
+++ b/net/l2tp/l2tp_debugfs.c
@@ -53,7 +53,7 @@ static void l2tp_dfs_next_tunnel(struct l2tp_dfs_seq_data *pd)
 
 static void l2tp_dfs_next_session(struct l2tp_dfs_seq_data *pd)
 {
-	pd->session = l2tp_session_find_nth(pd->tunnel, pd->session_idx);
+	pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx, true);
 	pd->session_idx++;
 
 	if (pd->session == NULL) {
@@ -238,10 +238,14 @@ static int l2tp_dfs_seq_show(struct seq_file *m, void *v)
 	}
 
 	/* Show the tunnel or session context */
-	if (pd->session == NULL)
+	if (!pd->session) {
 		l2tp_dfs_seq_tunnel_show(m, pd->tunnel);
-	else
+	} else {
 		l2tp_dfs_seq_session_show(m, pd->session);
+		if (pd->session->deref)
+			pd->session->deref(pd->session);
+		l2tp_session_dec_refcount(pd->session);
+	}
 
 out:
 	return 0;
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index 3620fba..ad191a7 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -852,7 +852,7 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback
 				goto out;
 		}
 
-		session = l2tp_session_find_nth(tunnel, si);
+		session = l2tp_session_get_nth(tunnel, si, false);
 		if (session == NULL) {
 			ti++;
 			tunnel = NULL;
@@ -862,8 +862,11 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback
 
 		if (l2tp_nl_session_send(skb, NETLINK_CB(cb->skb).portid,
 					 cb->nlh->nlmsg_seq, NLM_F_MULTI,
-					 session, L2TP_CMD_SESSION_GET) < 0)
+					 session, L2TP_CMD_SESSION_GET) < 0) {
+			l2tp_session_dec_refcount(session);
 			break;
+		}
+		l2tp_session_dec_refcount(session);
 
 		si++;
 	}
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 123b6a2..2f1944c 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1555,7 +1555,7 @@ static void pppol2tp_next_tunnel(struct net *net, struct pppol2tp_seq_data *pd)
 
 static void pppol2tp_next_session(struct net *net, struct pppol2tp_seq_data *pd)
 {
-	pd->session = l2tp_session_find_nth(pd->tunnel, pd->session_idx);
+	pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx, true);
 	pd->session_idx++;
 
 	if (pd->session == NULL) {
@@ -1682,10 +1682,14 @@ static int pppol2tp_seq_show(struct seq_file *m, void *v)
 
 	/* Show the tunnel or session context.
 	 */
-	if (pd->session == NULL)
+	if (!pd->session) {
 		pppol2tp_seq_tunnel_show(m, pd->tunnel);
-	else
+	} else {
 		pppol2tp_seq_session_show(m, pd->session);
+		if (pd->session->deref)
+			pd->session->deref(pd->session);
+		l2tp_session_dec_refcount(pd->session);
+	}
 
 out:
 	return 0;
-- 
2.4.11


From 935f574afcce75bd7bcd422afbcda33f71ae66d3 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Mon, 3 Apr 2017 13:23:15 +0200
Subject: [PATCH 14/41] l2tp: fix PPP pseudo-wire auto-loading

[ Upstream commit 249ee819e24c180909f43c1173c8ef6724d21faf ]

PPP pseudo-wire type is 7 (11 is L2TP_PWTYPE_IP).

Fixes: f1f39f911027 ("l2tp: auto load type modules")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ppp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 2f1944c..781d222 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1848,4 +1848,4 @@ MODULE_DESCRIPTION("PPP over L2TP over UDP");
 MODULE_LICENSE("GPL");
 MODULE_VERSION(PPPOL2TP_DRV_VERSION);
 MODULE_ALIAS_NET_PF_PROTO(PF_PPPOX, PX_PROTO_OL2TP);
-MODULE_ALIAS_L2TP_PWTYPE(11);
+MODULE_ALIAS_L2TP_PWTYPE(7);
-- 
2.4.11


From 6e30f17be1bcf826b9558577b968cd2fc62c7dae Mon Sep 17 00:00:00 2001
From: Florian Larysch <fl@n621.de>
Date: Mon, 3 Apr 2017 16:46:09 +0200
Subject: [PATCH 15/41] net: ipv4: fix multipath RTM_GETROUTE behavior when iif
 is given

[ Upstream commit a8801799c6975601fd58ae62f48964caec2eb83f ]

inet_rtm_getroute synthesizes a skeletal ICMP skb, which is passed to
ip_route_input when iif is given. If a multipath route is present for
the designated destination, ip_multipath_icmp_hash ends up being called,
which uses the source/destination addresses within the skb to calculate
a hash. However, those are not set in the synthetic skb, causing it to
return an arbitrary and incorrect result.

Instead, use UDP, which gets no such special treatment.

Signed-off-by: Florian Larysch <fl@n621.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 8976887..6263af2 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2608,7 +2608,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 	skb_reset_network_header(skb);
 
 	/* Bugfix: need to give ip_route_input enough of an IP header to not gag. */
-	ip_hdr(skb)->protocol = IPPROTO_ICMP;
+	ip_hdr(skb)->protocol = IPPROTO_UDP;
 	skb_reserve(skb, MAX_HEADER + sizeof(struct iphdr));
 
 	src = tb[RTA_SRC] ? nla_get_in_addr(tb[RTA_SRC]) : 0;
-- 
2.4.11


From 2b427bec255743c3e3e44905a1fe290fa39b073c Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 6 Apr 2017 13:10:52 +0800
Subject: [PATCH 16/41] sctp: listen on the sock only when it's state is
 listening or closed

[ Upstream commit 34b2789f1d9bf8dcca9b5cb553d076ca2cd898ee ]

Now sctp doesn't check sock's state before listening on it. It could
even cause changing a sock with any state to become a listening sock
when doing sctp_listen.

This patch is to fix it by checking sock's state in sctp_listen, so
that it will listen on the sock with right state.

Reported-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index d04a8b6..6932cf3 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -6860,6 +6860,9 @@ int sctp_inet_listen(struct socket *sock, int backlog)
 	if (sock->state != SS_UNCONNECTED)
 		goto out;
 
+	if (!sctp_sstate(sk, LISTENING) && !sctp_sstate(sk, CLOSED))
+		goto out;
+
 	/* If backlog is zero, disable listening. */
 	if (!backlog) {
 		if (sctp_sstate(sk, CLOSED))
-- 
2.4.11


From 7432c0476304df9f4423328082e62b84af82d8e8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 8 Apr 2017 08:07:33 -0700
Subject: [PATCH 17/41] tcp: clear saved_syn in tcp_disconnect()

[ Upstream commit 17c3060b1701fc69daedb4c90be6325d3d9fca8e ]

In the (very unlikely) case a passive socket becomes a listener,
we do not want to duplicate its saved SYN headers.

This would lead to double frees, use after free, and please hackers and
various fuzzers

Tested:
    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
   +0 setsockopt(3, IPPROTO_TCP, TCP_SAVE_SYN, [1], 4) = 0
   +0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0

   +0 bind(3, ..., ...) = 0
   +0 listen(3, 5) = 0

   +0 < S 0:0(0) win 32972 <mss 1460,nop,wscale 7>
   +0 > S. 0:0(0) ack 1 <...>
  +.1 < . 1:1(0) ack 1 win 257
   +0 accept(3, ..., ...) = 4

   +0 connect(4, AF_UNSPEC, ...) = 0
   +0 close(3) = 0
   +0 bind(4, ..., ...) = 0
   +0 listen(4, 5) = 0

   +0 < S 0:0(0) win 32972 <mss 1460,nop,wscale 7>
   +0 > S. 0:0(0) ack 1 <...>
  +.1 < . 1:1(0) ack 1 win 257

Fixes: cd8ae85299d5 ("tcp: provide SYN headers for passive connections")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 0efb4c7..53fa3a4 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2301,6 +2301,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tcp_init_send_head(sk);
 	memset(&tp->rx_opt, 0, sizeof(tp->rx_opt));
 	__sk_dst_reset(sk);
+	tcp_saved_syn_free(tp);
 
 	WARN_ON(inet->inet_num && !icsk->icsk_bind_hash);
 
-- 
2.4.11


From 64afc426f91a6f2d0bcfb0ba32cb5cf0c1026a66 Mon Sep 17 00:00:00 2001
From: Rabin Vincent <rabinv@axis.com>
Date: Mon, 10 Apr 2017 08:36:39 +0200
Subject: [PATCH 18/41] ipv6: Fix idev->addr_list corruption

[ Upstream commit a2d6cbb0670d54806f18192cb0db266b4a6d285a ]

addrconf_ifdown() removes elements from the idev->addr_list without
holding the idev->lock.

If this happens while the loop in __ipv6_dev_get_saddr() is handling the
same element, that function ends up in an infinite loop:

  NMI watchdog: BUG: soft lockup - CPU#1 stuck for 23s! [test:1719]
  Call Trace:
   ipv6_get_saddr_eval+0x13c/0x3a0
   __ipv6_dev_get_saddr+0xe4/0x1f0
   ipv6_dev_get_saddr+0x1b4/0x204
   ip6_dst_lookup_tail+0xcc/0x27c
   ip6_dst_lookup_flow+0x38/0x80
   udpv6_sendmsg+0x708/0xba8
   sock_sendmsg+0x18/0x30
   SyS_sendto+0xb8/0xf8
   syscall_common+0x34/0x58

Fixes: 6a923934c33 (Revert "ipv6: Revert optional address flusing on ifdown.")
Signed-off-by: Rabin Vincent <rabinv@axis.com>
Acked-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index a7bcc0a..8c4ee4e 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3618,14 +3618,19 @@ static int addrconf_ifdown(struct net_device *dev, int how)
 	INIT_LIST_HEAD(&del_list);
 	list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) {
 		struct rt6_info *rt = NULL;
+		bool keep;
 
 		addrconf_del_dad_work(ifa);
 
+		keep = keep_addr && (ifa->flags & IFA_F_PERMANENT) &&
+			!addr_is_local(&ifa->addr);
+		if (!keep)
+			list_move(&ifa->if_list, &del_list);
+
 		write_unlock_bh(&idev->lock);
 		spin_lock_bh(&ifa->lock);
 
-		if (keep_addr && (ifa->flags & IFA_F_PERMANENT) &&
-		    !addr_is_local(&ifa->addr)) {
+		if (keep) {
 			/* set state to skip the notifier below */
 			state = INET6_IFADDR_STATE_DEAD;
 			ifa->state = 0;
@@ -3637,8 +3642,6 @@ static int addrconf_ifdown(struct net_device *dev, int how)
 		} else {
 			state = ifa->state;
 			ifa->state = INET6_IFADDR_STATE_DEAD;
-
-			list_move(&ifa->if_list, &del_list);
 		}
 
 		spin_unlock_bh(&ifa->lock);
-- 
2.4.11


From be87efe20b39a534ee5ddda5a73a7308b784cb2a Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 12 Apr 2017 19:24:35 -0400
Subject: [PATCH 19/41] net-timestamp: avoid use-after-free in ip_recv_error

[ Upstream commit 1862d6208db0aeca9c8ace44915b08d5ab2cd667 ]

Syzkaller reported a use-after-free in ip_recv_error at line

    info->ipi_ifindex = skb->dev->ifindex;

This function is called on dequeue from the error queue, at which
point the device pointer may no longer be valid.

Save ifindex on enqueue in __skb_complete_tx_timestamp, when the
pointer is valid or NULL. Store it in temporary storage skb->cb.

It is safe to reference skb->dev here, as called from device drivers
or dev_queue_xmit. The exception is when called from tcp_ack_tstamp;
in that case it is NULL and ifindex is set to 0 (invalid).

Do not return a pktinfo cmsg if ifindex is 0. This maintains the
current behavior of not returning a cmsg if skb->dev was NULL.

On dequeue, the ipv4 path will cast from sock_exterr_skb to
in_pktinfo. Both have ifindex as their first element, so no explicit
conversion is needed. This is by design, introduced in commit
0b922b7a829c ("net: original ingress device index in PKTINFO"). For
ipv6 ip6_datagram_support_cmsg converts to in6_pktinfo.

Fixes: 829ae9d61165 ("net-timestamp: allow reading recv cmsg on errqueue with origin tstamp")
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c      |  1 +
 net/ipv4/ip_sockglue.c |  9 ++++-----
 net/ipv6/datagram.c    | 10 +---------
 3 files changed, 6 insertions(+), 14 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index aa3a133..39ca3e6 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3789,6 +3789,7 @@ static void __skb_complete_tx_timestamp(struct sk_buff *skb,
 	serr->ee.ee_errno = ENOMSG;
 	serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING;
 	serr->ee.ee_info = tstype;
+	serr->header.h4.iif = skb->dev ? skb->dev->ifindex : 0;
 	if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) {
 		serr->ee.ee_data = skb_shinfo(skb)->tskey;
 		if (sk->sk_protocol == IPPROTO_TCP &&
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index fc4bf4d..fcf53a3 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -488,16 +488,15 @@ static bool ipv4_datagram_support_cmsg(const struct sock *sk,
 		return false;
 
 	/* Support IP_PKTINFO on tstamp packets if requested, to correlate
-	 * timestamp with egress dev. Not possible for packets without dev
+	 * timestamp with egress dev. Not possible for packets without iif
 	 * or without payload (SOF_TIMESTAMPING_OPT_TSONLY).
 	 */
-	if ((!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_CMSG)) ||
-	    (!skb->dev))
+	info = PKTINFO_SKB_CB(skb);
+	if (!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_CMSG) ||
+	    !info->ipi_ifindex)
 		return false;
 
-	info = PKTINFO_SKB_CB(skb);
 	info->ipi_spec_dst.s_addr = ip_hdr(skb)->saddr;
-	info->ipi_ifindex = skb->dev->ifindex;
 	return true;
 }
 
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index eec27f8..e011122 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -405,9 +405,6 @@ static inline bool ipv6_datagram_support_addr(struct sock_exterr_skb *serr)
  * At one point, excluding local errors was a quick test to identify icmp/icmp6
  * errors. This is no longer true, but the test remained, so the v6 stack,
  * unlike v4, also honors cmsg requests on all wifi and timestamp errors.
- *
- * Timestamp code paths do not initialize the fields expected by cmsg:
- * the PKTINFO fields in skb->cb[]. Fill those in here.
  */
 static bool ip6_datagram_support_cmsg(struct sk_buff *skb,
 				      struct sock_exterr_skb *serr)
@@ -419,14 +416,9 @@ static bool ip6_datagram_support_cmsg(struct sk_buff *skb,
 	if (serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL)
 		return false;
 
-	if (!skb->dev)
+	if (!IP6CB(skb)->iif)
 		return false;
 
-	if (skb->protocol == htons(ETH_P_IPV6))
-		IP6CB(skb)->iif = skb->dev->ifindex;
-	else
-		PKTINFO_SKB_CB(skb)->ipi_ifindex = skb->dev->ifindex;
-
 	return true;
 }
 
-- 
2.4.11


From 1c277dbf5acb49de92a8fb6b7cb1a96ca91e6c97 Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Thu, 13 Apr 2017 10:57:15 -0600
Subject: [PATCH 20/41] net: vrf: Fix setting NLM_F_EXCL flag when adding
 l3mdev rule

[ Upstream commit 426c87caa2b4578b43cd3f689f02c65b743b2559 ]

Only need 1 l3mdev FIB rule. Fix setting NLM_F_EXCL in the nlmsghdr.

Fixes: 1aa6c4f6b8cd8 ("net: vrf: Add l3mdev rules on first device create")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 921fef2..f2fd52e 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -1126,7 +1126,7 @@ static int vrf_fib_rule(const struct net_device *dev, __u8 family, bool add_it)
 		goto nla_put_failure;
 
 	/* rule only needs to appear once */
-	nlh->nlmsg_flags &= NLM_F_EXCL;
+	nlh->nlmsg_flags |= NLM_F_EXCL;
 
 	frh = nlmsg_data(nlh);
 	memset(frh, 0, sizeof(*frh));
-- 
2.4.11


From 8b4c585b3eeab6deaaa7e9e4f36e8bc45a8c07eb Mon Sep 17 00:00:00 2001
From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Date: Mon, 17 Apr 2017 15:55:22 +0300
Subject: [PATCH 21/41] sh_eth: unmap DMA buffers when freeing rings

[ Upstream commit 1debdc8f9ebd07daf140e417b3841596911e0066 ]

The DMA API debugging (when enabled) causes:

WARNING: CPU: 0 PID: 1445 at lib/dma-debug.c:519 add_dma_entry+0xe0/0x12c
DMA-API: exceeded 7 overlapping mappings of cacheline 0x01b2974d

to be  printed after repeated initialization of the Ether device, e.g.
suspend/resume or 'ifconfig' up/down. This is because DMA buffers mapped
using dma_map_single() in sh_eth_ring_format() and sh_eth_start_xmit() are
never unmapped. Resolve this problem by unmapping the buffers when freeing
the descriptor  rings;  in order  to do it right, we'd have to add an extra
parameter to sh_eth_txfree() (we rename this function to sh_eth_tx_free(),
while at it).

Based on the commit a47b70ea86bd ("ravb: unmap descriptors when freeing
rings").

Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/sh_eth.c | 122 +++++++++++++++++++---------------
 1 file changed, 67 insertions(+), 55 deletions(-)

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index f729a6b..1a012b3 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -1061,12 +1061,70 @@ static struct mdiobb_ops bb_ops = {
 	.get_mdio_data = sh_get_mdio,
 };
 
+/* free Tx skb function */
+static int sh_eth_tx_free(struct net_device *ndev, bool sent_only)
+{
+	struct sh_eth_private *mdp = netdev_priv(ndev);
+	struct sh_eth_txdesc *txdesc;
+	int free_num = 0;
+	int entry;
+	bool sent;
+
+	for (; mdp->cur_tx - mdp->dirty_tx > 0; mdp->dirty_tx++) {
+		entry = mdp->dirty_tx % mdp->num_tx_ring;
+		txdesc = &mdp->tx_ring[entry];
+		sent = !(txdesc->status & cpu_to_le32(TD_TACT));
+		if (sent_only && !sent)
+			break;
+		/* TACT bit must be checked before all the following reads */
+		dma_rmb();
+		netif_info(mdp, tx_done, ndev,
+			   "tx entry %d status 0x%08x\n",
+			   entry, le32_to_cpu(txdesc->status));
+		/* Free the original skb. */
+		if (mdp->tx_skbuff[entry]) {
+			dma_unmap_single(&ndev->dev, le32_to_cpu(txdesc->addr),
+					 le32_to_cpu(txdesc->len) >> 16,
+					 DMA_TO_DEVICE);
+			dev_kfree_skb_irq(mdp->tx_skbuff[entry]);
+			mdp->tx_skbuff[entry] = NULL;
+			free_num++;
+		}
+		txdesc->status = cpu_to_le32(TD_TFP);
+		if (entry >= mdp->num_tx_ring - 1)
+			txdesc->status |= cpu_to_le32(TD_TDLE);
+
+		if (sent) {
+			ndev->stats.tx_packets++;
+			ndev->stats.tx_bytes += le32_to_cpu(txdesc->len) >> 16;
+		}
+	}
+	return free_num;
+}
+
 /* free skb and descriptor buffer */
 static void sh_eth_ring_free(struct net_device *ndev)
 {
 	struct sh_eth_private *mdp = netdev_priv(ndev);
 	int ringsize, i;
 
+	if (mdp->rx_ring) {
+		for (i = 0; i < mdp->num_rx_ring; i++) {
+			if (mdp->rx_skbuff[i]) {
+				struct sh_eth_rxdesc *rxdesc = &mdp->rx_ring[i];
+
+				dma_unmap_single(&ndev->dev,
+						 le32_to_cpu(rxdesc->addr),
+						 ALIGN(mdp->rx_buf_sz, 32),
+						 DMA_FROM_DEVICE);
+			}
+		}
+		ringsize = sizeof(struct sh_eth_rxdesc) * mdp->num_rx_ring;
+		dma_free_coherent(NULL, ringsize, mdp->rx_ring,
+				  mdp->rx_desc_dma);
+		mdp->rx_ring = NULL;
+	}
+
 	/* Free Rx skb ringbuffer */
 	if (mdp->rx_skbuff) {
 		for (i = 0; i < mdp->num_rx_ring; i++)
@@ -1075,27 +1133,18 @@ static void sh_eth_ring_free(struct net_device *ndev)
 	kfree(mdp->rx_skbuff);
 	mdp->rx_skbuff = NULL;
 
-	/* Free Tx skb ringbuffer */
-	if (mdp->tx_skbuff) {
-		for (i = 0; i < mdp->num_tx_ring; i++)
-			dev_kfree_skb(mdp->tx_skbuff[i]);
-	}
-	kfree(mdp->tx_skbuff);
-	mdp->tx_skbuff = NULL;
-
-	if (mdp->rx_ring) {
-		ringsize = sizeof(struct sh_eth_rxdesc) * mdp->num_rx_ring;
-		dma_free_coherent(NULL, ringsize, mdp->rx_ring,
-				  mdp->rx_desc_dma);
-		mdp->rx_ring = NULL;
-	}
-
 	if (mdp->tx_ring) {
+		sh_eth_tx_free(ndev, false);
+
 		ringsize = sizeof(struct sh_eth_txdesc) * mdp->num_tx_ring;
 		dma_free_coherent(NULL, ringsize, mdp->tx_ring,
 				  mdp->tx_desc_dma);
 		mdp->tx_ring = NULL;
 	}
+
+	/* Free Tx skb ringbuffer */
+	kfree(mdp->tx_skbuff);
+	mdp->tx_skbuff = NULL;
 }
 
 /* format skb and descriptor buffer */
@@ -1343,43 +1392,6 @@ static void sh_eth_dev_exit(struct net_device *ndev)
 	update_mac_address(ndev);
 }
 
-/* free Tx skb function */
-static int sh_eth_txfree(struct net_device *ndev)
-{
-	struct sh_eth_private *mdp = netdev_priv(ndev);
-	struct sh_eth_txdesc *txdesc;
-	int free_num = 0;
-	int entry;
-
-	for (; mdp->cur_tx - mdp->dirty_tx > 0; mdp->dirty_tx++) {
-		entry = mdp->dirty_tx % mdp->num_tx_ring;
-		txdesc = &mdp->tx_ring[entry];
-		if (txdesc->status & cpu_to_le32(TD_TACT))
-			break;
-		/* TACT bit must be checked before all the following reads */
-		dma_rmb();
-		netif_info(mdp, tx_done, ndev,
-			   "tx entry %d status 0x%08x\n",
-			   entry, le32_to_cpu(txdesc->status));
-		/* Free the original skb. */
-		if (mdp->tx_skbuff[entry]) {
-			dma_unmap_single(&ndev->dev, le32_to_cpu(txdesc->addr),
-					 le32_to_cpu(txdesc->len) >> 16,
-					 DMA_TO_DEVICE);
-			dev_kfree_skb_irq(mdp->tx_skbuff[entry]);
-			mdp->tx_skbuff[entry] = NULL;
-			free_num++;
-		}
-		txdesc->status = cpu_to_le32(TD_TFP);
-		if (entry >= mdp->num_tx_ring - 1)
-			txdesc->status |= cpu_to_le32(TD_TDLE);
-
-		ndev->stats.tx_packets++;
-		ndev->stats.tx_bytes += le32_to_cpu(txdesc->len) >> 16;
-	}
-	return free_num;
-}
-
 /* Packet receive function */
 static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota)
 {
@@ -1622,7 +1634,7 @@ static void sh_eth_error(struct net_device *ndev, u32 intr_status)
 			   intr_status, mdp->cur_tx, mdp->dirty_tx,
 			   (u32)ndev->state, edtrr);
 		/* dirty buffer free */
-		sh_eth_txfree(ndev);
+		sh_eth_tx_free(ndev, true);
 
 		/* SH7712 BUG */
 		if (edtrr ^ sh_eth_get_edtrr_trns(mdp)) {
@@ -1681,7 +1693,7 @@ static irqreturn_t sh_eth_interrupt(int irq, void *netdev)
 		/* Clear Tx interrupts */
 		sh_eth_write(ndev, intr_status & cd->tx_check, EESR);
 
-		sh_eth_txfree(ndev);
+		sh_eth_tx_free(ndev, true);
 		netif_wake_queue(ndev);
 	}
 
@@ -2309,7 +2321,7 @@ static int sh_eth_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 
 	spin_lock_irqsave(&mdp->lock, flags);
 	if ((mdp->cur_tx - mdp->dirty_tx) >= (mdp->num_tx_ring - 4)) {
-		if (!sh_eth_txfree(ndev)) {
+		if (!sh_eth_tx_free(ndev, true)) {
 			netif_warn(mdp, tx_queued, ndev, "TxFD exhausted.\n");
 			netif_stop_queue(ndev);
 			spin_unlock_irqrestore(&mdp->lock, flags);
-- 
2.4.11


From 4e6f9857788283a138402eaba765663d78a2868b Mon Sep 17 00:00:00 2001
From: David Lebrun <david.lebrun@uclouvain.be>
Date: Tue, 18 Apr 2017 17:59:49 +0200
Subject: [PATCH 22/41] ipv6: sr: fix out-of-bounds access in SRH validation

[ Upstream commit 2f3bb64247b5b083d05ccecad9c2e139bbfdc294 ]

This patch fixes an out-of-bounds access in seg6_validate_srh() when the
trailing data is less than sizeof(struct sr6_tlv).

Reported-by: Andrey Konovalov <andreyknvl@google.com>
Cc: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David Lebrun <david.lebrun@uclouvain.be>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/seg6.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c
index a855eb3..5f44ffe 100644
--- a/net/ipv6/seg6.c
+++ b/net/ipv6/seg6.c
@@ -53,6 +53,9 @@ bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len)
 		struct sr6_tlv *tlv;
 		unsigned int tlv_len;
 
+		if (trailing < sizeof(*tlv))
+			return false;
+
 		tlv = (struct sr6_tlv *)((unsigned char *)srh + tlv_offset);
 		tlv_len = sizeof(*tlv) + tlv->len;
 
-- 
2.4.11


From 95afa6407c1c5253a692260a3ce38d8a38a52563 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Tue, 18 Apr 2017 22:14:26 +0300
Subject: [PATCH 23/41] dp83640: don't recieve time stamps twice
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 9d386cd9a755c8293e8916264d4d053878a7c9c7 ]

This patch is prompted by a static checker warning about a potential
use after free.  The concern is that netif_rx_ni() can free "skb" and we
call it twice.

When I look at the commit that added this, it looks like some stray
lines were added accidentally.  It doesn't make sense to me that we
would recieve the same data two times.  I asked the author but never
recieved a response.

I can't test this code, but I'm pretty sure my patch is correct.

Fixes: 4b063258ab93 ("dp83640: Delay scheduled work.")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Stefan Sørensen <stefan.sorensen@spectralink.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/dp83640.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index e2460a5..ed0d10f 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -1438,8 +1438,6 @@ static bool dp83640_rxtstamp(struct phy_device *phydev,
 		skb_info->tmo = jiffies + SKB_TIMESTAMP_TIMEOUT;
 		skb_queue_tail(&dp83640->rx_queue, skb);
 		schedule_delayed_work(&dp83640->ts_work, SKB_TIMESTAMP_TIMEOUT);
-	} else {
-		netif_rx_ni(skb);
 	}
 
 	return true;
-- 
2.4.11


From 2e9af2d485d272540672f8baa8cece5e9e4199cf Mon Sep 17 00:00:00 2001
From: David Lebrun <david.lebrun@uclouvain.be>
Date: Wed, 19 Apr 2017 16:10:19 +0200
Subject: [PATCH 24/41] ipv6: sr: fix double free of skb after handling invalid
 SRH

[ Upstream commit 95b9b88d2da5e43e025400afcb492643933bf858 ]

The icmpv6_param_prob() function already does a kfree_skb(),
this patch removes the duplicate one.

Fixes: 1ababeba4a21f3dba3da3523c670b207fb2feb62 ("ipv6: implement dataplane support for rthdr type 4 (Segment Routing Header)")
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Cc: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David Lebrun <david.lebrun@uclouvain.be>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/exthdrs.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 275cac6..25192a3 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -388,7 +388,6 @@ static int ipv6_srh_rcv(struct sk_buff *skb)
 		icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
 				  ((&hdr->segments_left) -
 				   skb_network_header(skb)));
-		kfree_skb(skb);
 		return -1;
 	}
 
-- 
2.4.11


From 6fd7d6fdcaca35a5af22c0b4400a14d4f167ab46 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 25 Apr 2017 15:56:50 +0200
Subject: [PATCH 25/41] ipv6: fix source routing

[ Upstream commit ec9c4215fef37da6668c4105f5ad3891aaa6527a ]

Commit a149e7c7ce81 ("ipv6: sr: add support for SRH injection through
setsockopt") introduced handling of IPV6_SRCRT_TYPE_4, but at the same
time restricted it to only IPV6_SRCRT_TYPE_0 and
IPV6_SRCRT_TYPE_4. Previously, ipv6_push_exthdr() and fl6_update_dst()
would also handle other values (ie STRICT and TYPE_2).

Restore previous source routing behavior, by handling IPV6_SRCRT_STRICT
and IPV6_SRCRT_TYPE_2 the same way as IPV6_SRCRT_TYPE_0 in
ipv6_push_exthdr() and fl6_update_dst().

Fixes: a149e7c7ce81 ("ipv6: sr: add support for SRH injection through setsockopt")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/exthdrs.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 25192a3..d32e211 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -909,6 +909,8 @@ static void ipv6_push_rthdr(struct sk_buff *skb, u8 *proto,
 {
 	switch (opt->type) {
 	case IPV6_SRCRT_TYPE_0:
+	case IPV6_SRCRT_STRICT:
+	case IPV6_SRCRT_TYPE_2:
 		ipv6_push_rthdr0(skb, proto, opt, addr_p, saddr);
 		break;
 	case IPV6_SRCRT_TYPE_4:
@@ -1163,6 +1165,8 @@ struct in6_addr *fl6_update_dst(struct flowi6 *fl6,
 
 	switch (opt->srcrt->type) {
 	case IPV6_SRCRT_TYPE_0:
+	case IPV6_SRCRT_STRICT:
+	case IPV6_SRCRT_TYPE_2:
 		fl6->daddr = *((struct rt0_hdr *)opt->srcrt)->addr;
 		break;
 	case IPV6_SRCRT_TYPE_4:
-- 
2.4.11


From 3e0226b1af25c4de8186b82bb317f3b907ce2230 Mon Sep 17 00:00:00 2001
From: Ilan Tayari <ilant@mellanox.com>
Date: Wed, 19 Apr 2017 21:26:07 +0300
Subject: [PATCH 26/41] gso: Validate assumption of frag_list segementation

[ Upstream commit 43170c4e0ba709c79130c3fe5a41e66279950cd0 ]

Commit 07b26c9454a2 ("gso: Support partial splitting at the frag_list
pointer") assumes that all SKBs in a frag_list (except maybe the last
one) contain the same amount of GSO payload.

This assumption is not always correct, resulting in the following
warning message in the log:
    skb_segment: too many frags

For example, mlx5 driver in Striding RQ mode creates some RX SKBs with
one frag, and some with 2 frags.
After GRO, the frag_list SKBs end up having different amounts of payload.
If this frag_list SKB is then forwarded, the aforementioned assumption
is violated.

Validate the assumption, and fall back to software GSO if it not true.

Change-Id: Ia03983f4a47b6534dd987d7a2aad96d54d46d212
Fixes: 07b26c9454a2 ("gso: Support partial splitting at the frag_list pointer")
Signed-off-by: Ilan Tayari <ilant@mellanox.com>
Signed-off-by: Ilya Lesokhin <ilyal@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 39ca3e6..c3cb99c 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3078,22 +3078,32 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 	if (sg && csum && (mss != GSO_BY_FRAGS))  {
 		if (!(features & NETIF_F_GSO_PARTIAL)) {
 			struct sk_buff *iter;
+			unsigned int frag_len;
 
 			if (!list_skb ||
 			    !net_gso_ok(features, skb_shinfo(head_skb)->gso_type))
 				goto normal;
 
-			/* Split the buffer at the frag_list pointer.
-			 * This is based on the assumption that all
-			 * buffers in the chain excluding the last
-			 * containing the same amount of data.
+			/* If we get here then all the required
+			 * GSO features except frag_list are supported.
+			 * Try to split the SKB to multiple GSO SKBs
+			 * with no frag_list.
+			 * Currently we can do that only when the buffers don't
+			 * have a linear part and all the buffers except
+			 * the last are of the same length.
 			 */
+			frag_len = list_skb->len;
 			skb_walk_frags(head_skb, iter) {
+				if (frag_len != iter->len && iter->next)
+					goto normal;
 				if (skb_headlen(iter))
 					goto normal;
 
 				len -= iter->len;
 			}
+
+			if (len != frag_len)
+				goto normal;
 		}
 
 		/* GSO partial only requires that we trim off any excess that
-- 
2.4.11


From bfa2169bd1aad5d2e4be5b0a5c52d678252091a3 Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Wed, 19 Apr 2017 14:19:43 -0700
Subject: [PATCH 27/41] net: ipv6: RTF_PCPU should not be settable from
 userspace

[ Upstream commit 557c44be917c322860665be3d28376afa84aa936 ]

Andrey reported a fault in the IPv6 route code:

kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] SMP KASAN
Modules linked in:
CPU: 1 PID: 4035 Comm: a.out Not tainted 4.11.0-rc7+ #250
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
task: ffff880069809600 task.stack: ffff880062dc8000
RIP: 0010:ip6_rt_cache_alloc+0xa6/0x560 net/ipv6/route.c:975
RSP: 0018:ffff880062dced30 EFLAGS: 00010206
RAX: dffffc0000000000 RBX: ffff8800670561c0 RCX: 0000000000000006
RDX: 0000000000000003 RSI: ffff880062dcfb28 RDI: 0000000000000018
RBP: ffff880062dced68 R08: 0000000000000001 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
R13: ffff880062dcfb28 R14: dffffc0000000000 R15: 0000000000000000
FS:  00007feebe37e7c0(0000) GS:ffff88006cb00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000205a0fe4 CR3: 000000006b5c9000 CR4: 00000000000006e0
Call Trace:
 ip6_pol_route+0x1512/0x1f20 net/ipv6/route.c:1128
 ip6_pol_route_output+0x4c/0x60 net/ipv6/route.c:1212
...

Andrey's syzkaller program passes rtmsg.rtmsg_flags with the RTF_PCPU bit
set. Flags passed to the kernel are blindly copied to the allocated
rt6_info by ip6_route_info_create making a newly inserted route appear
as though it is a per-cpu route. ip6_rt_cache_alloc sees the flag set
and expects rt->dst.from to be set - which it is not since it is not
really a per-cpu copy. The subsequent call to __ip6_dst_alloc then
generates the fault.

Fix by checking for the flag and failing with EINVAL.

Fixes: d52d3997f843f ("ipv6: Create percpu rt6_info")
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/ipv6_route.h | 2 +-
 net/ipv6/route.c                | 4 ++++
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/ipv6_route.h b/include/uapi/linux/ipv6_route.h
index f6598d1..316e838 100644
--- a/include/uapi/linux/ipv6_route.h
+++ b/include/uapi/linux/ipv6_route.h
@@ -34,7 +34,7 @@
 #define RTF_PREF(pref)	((pref) << 27)
 #define RTF_PREF_MASK	0x18000000
 
-#define RTF_PCPU	0x40000000
+#define RTF_PCPU	0x40000000	/* read-only: can not be set by user */
 #define RTF_LOCAL	0x80000000
 
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 7ea8537..523681a 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1831,6 +1831,10 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg)
 	int addr_type;
 	int err = -EINVAL;
 
+	/* RTF_PCPU is an internal flag; can not be set by userspace */
+	if (cfg->fc_flags & RTF_PCPU)
+		goto out;
+
 	if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128)
 		goto out;
 #ifndef CONFIG_IPV6_SUBTREES
-- 
2.4.11


From 404c802ede2bbd06054e7384b4dc2b4ada5a16c5 Mon Sep 17 00:00:00 2001
From: Tushar Dave <tushar.n.dave@oracle.com>
Date: Thu, 20 Apr 2017 15:57:31 -0700
Subject: [PATCH 28/41] netpoll: Check for skb->queue_mapping

[ Upstream commit c70b17b775edb21280e9de7531acf6db3b365274 ]

Reducing real_num_tx_queues needs to be in sync with skb queue_mapping
otherwise skbs with queue_mapping greater than real_num_tx_queues
can be sent to the underlying driver and can result in kernel panic.

One such event is running netconsole and enabling VF on the same
device. Or running netconsole and changing number of tx queues via
ethtool on same device.

e.g.
Unable to handle kernel NULL pointer dereference
tsk->{mm,active_mm}->context = 0000000000001525
tsk->{mm,active_mm}->pgd = fff800130ff9a000
              \|/ ____ \|/
              "@'/ .. \`@"
              /_| \__/ |_\
                 \__U_/
kworker/48:1(475): Oops [#1]
CPU: 48 PID: 475 Comm: kworker/48:1 Tainted: G           OE
4.11.0-rc3-davem-net+ #7
Workqueue: events queue_process
task: fff80013113299c0 task.stack: fff800131132c000
TSTATE: 0000004480e01600 TPC: 00000000103f9e3c TNPC: 00000000103f9e40 Y:
00000000    Tainted: G           OE
TPC: <ixgbe_xmit_frame_ring+0x7c/0x6c0 [ixgbe]>
g0: 0000000000000000 g1: 0000000000003fff g2: 0000000000000000 g3:
0000000000000001
g4: fff80013113299c0 g5: fff8001fa6808000 g6: fff800131132c000 g7:
00000000000000c0
o0: fff8001fa760c460 o1: fff8001311329a50 o2: fff8001fa7607504 o3:
0000000000000003
o4: fff8001f96e63a40 o5: fff8001311d77ec0 sp: fff800131132f0e1 ret_pc:
000000000049ed94
RPC: <set_next_entity+0x34/0xb80>
l0: 0000000000000000 l1: 0000000000000800 l2: 0000000000000000 l3:
0000000000000000
l4: 000b2aa30e34b10d l5: 0000000000000000 l6: 0000000000000000 l7:
fff8001fa7605028
i0: fff80013111a8a00 i1: fff80013155a0780 i2: 0000000000000000 i3:
0000000000000000
i4: 0000000000000000 i5: 0000000000100000 i6: fff800131132f1a1 i7:
00000000103fa4b0
I7: <ixgbe_xmit_frame+0x30/0xa0 [ixgbe]>
Call Trace:
 [00000000103fa4b0] ixgbe_xmit_frame+0x30/0xa0 [ixgbe]
 [0000000000998c74] netpoll_start_xmit+0xf4/0x200
 [0000000000998e10] queue_process+0x90/0x160
 [0000000000485fa8] process_one_work+0x188/0x480
 [0000000000486410] worker_thread+0x170/0x4c0
 [000000000048c6b8] kthread+0xd8/0x120
 [0000000000406064] ret_from_fork+0x1c/0x2c
 [0000000000000000]           (null)
Disabling lock debugging due to kernel taint
Caller[00000000103fa4b0]: ixgbe_xmit_frame+0x30/0xa0 [ixgbe]
Caller[0000000000998c74]: netpoll_start_xmit+0xf4/0x200
Caller[0000000000998e10]: queue_process+0x90/0x160
Caller[0000000000485fa8]: process_one_work+0x188/0x480
Caller[0000000000486410]: worker_thread+0x170/0x4c0
Caller[000000000048c6b8]: kthread+0xd8/0x120
Caller[0000000000406064]: ret_from_fork+0x1c/0x2c
Caller[0000000000000000]:           (null)

Signed-off-by: Tushar Dave <tushar.n.dave@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/netpoll.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 9424673..29be246 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -105,15 +105,21 @@ static void queue_process(struct work_struct *work)
 	while ((skb = skb_dequeue(&npinfo->txq))) {
 		struct net_device *dev = skb->dev;
 		struct netdev_queue *txq;
+		unsigned int q_index;
 
 		if (!netif_device_present(dev) || !netif_running(dev)) {
 			kfree_skb(skb);
 			continue;
 		}
 
-		txq = skb_get_tx_queue(dev, skb);
-
 		local_irq_save(flags);
+		/* check if skb->queue_mapping is still valid */
+		q_index = skb_get_queue_mapping(skb);
+		if (unlikely(q_index >= dev->real_num_tx_queues)) {
+			q_index = q_index % dev->real_num_tx_queues;
+			skb_set_queue_mapping(skb, q_index);
+		}
+		txq = netdev_get_tx_queue(dev, q_index);
 		HARD_TX_LOCK(dev, txq, smp_processor_id());
 		if (netif_xmit_frozen_or_stopped(txq) ||
 		    netpoll_start_xmit(skb, dev, txq) != NETDEV_TX_OK) {
-- 
2.4.11


From bd89f6b4589e2eb93f950308018b39f648deead2 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Fri, 21 Apr 2017 20:42:16 +0300
Subject: [PATCH 29/41] ip6mr: fix notification device destruction

[ Upstream commit 723b929ca0f79c0796f160c2eeda4597ee98d2b8 ]

Andrey Konovalov reported a BUG caused by the ip6mr code which is caused
because we call unregister_netdevice_many for a device that is already
being destroyed. In IPv4's ipmr that has been resolved by two commits
long time ago by introducing the "notify" parameter to the delete
function and avoiding the unregister when called from a notifier, so
let's do the same for ip6mr.

The trace from Andrey:
------------[ cut here ]------------
kernel BUG at net/core/dev.c:6813!
invalid opcode: 0000 [#1] SMP KASAN
Modules linked in:
CPU: 1 PID: 1165 Comm: kworker/u4:3 Not tainted 4.11.0-rc7+ #251
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs
01/01/2011
Workqueue: netns cleanup_net
task: ffff880069208000 task.stack: ffff8800692d8000
RIP: 0010:rollback_registered_many+0x348/0xeb0 net/core/dev.c:6813
RSP: 0018:ffff8800692de7f0 EFLAGS: 00010297
RAX: ffff880069208000 RBX: 0000000000000002 RCX: 0000000000000001
RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff88006af90569
RBP: ffff8800692de9f0 R08: ffff8800692dec60 R09: 0000000000000000
R10: 0000000000000006 R11: 0000000000000000 R12: ffff88006af90070
R13: ffff8800692debf0 R14: dffffc0000000000 R15: ffff88006af90000
FS:  0000000000000000(0000) GS:ffff88006cb00000(0000)
knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007fe7e897d870 CR3: 00000000657e7000 CR4: 00000000000006e0
Call Trace:
 unregister_netdevice_many.part.105+0x87/0x440 net/core/dev.c:7881
 unregister_netdevice_many+0xc8/0x120 net/core/dev.c:7880
 ip6mr_device_event+0x362/0x3f0 net/ipv6/ip6mr.c:1346
 notifier_call_chain+0x145/0x2f0 kernel/notifier.c:93
 __raw_notifier_call_chain kernel/notifier.c:394
 raw_notifier_call_chain+0x2d/0x40 kernel/notifier.c:401
 call_netdevice_notifiers_info+0x51/0x90 net/core/dev.c:1647
 call_netdevice_notifiers net/core/dev.c:1663
 rollback_registered_many+0x919/0xeb0 net/core/dev.c:6841
 unregister_netdevice_many.part.105+0x87/0x440 net/core/dev.c:7881
 unregister_netdevice_many net/core/dev.c:7880
 default_device_exit_batch+0x4fa/0x640 net/core/dev.c:8333
 ops_exit_list.isra.4+0x100/0x150 net/core/net_namespace.c:144
 cleanup_net+0x5a8/0xb40 net/core/net_namespace.c:463
 process_one_work+0xc04/0x1c10 kernel/workqueue.c:2097
 worker_thread+0x223/0x19c0 kernel/workqueue.c:2231
 kthread+0x35e/0x430 kernel/kthread.c:231
 ret_from_fork+0x31/0x40 arch/x86/entry/entry_64.S:430
Code: 3c 32 00 0f 85 70 0b 00 00 48 b8 00 02 00 00 00 00 ad de 49 89
47 78 e9 93 fe ff ff 49 8d 57 70 49 8d 5f 78 eb 9e e8 88 7a 14 fe <0f>
0b 48 8b 9d 28 fe ff ff e8 7a 7a 14 fe 48 b8 00 00 00 00 00
RIP: rollback_registered_many+0x348/0xeb0 RSP: ffff8800692de7f0
---[ end trace e0b29c57e9b3292c ]---

Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6mr.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 604d895..72a00e4 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -774,7 +774,8 @@ static struct net_device *ip6mr_reg_vif(struct net *net, struct mr6_table *mrt)
  *	Delete a VIF entry
  */
 
-static int mif6_delete(struct mr6_table *mrt, int vifi, struct list_head *head)
+static int mif6_delete(struct mr6_table *mrt, int vifi, int notify,
+		       struct list_head *head)
 {
 	struct mif_device *v;
 	struct net_device *dev;
@@ -820,7 +821,7 @@ static int mif6_delete(struct mr6_table *mrt, int vifi, struct list_head *head)
 					     dev->ifindex, &in6_dev->cnf);
 	}
 
-	if (v->flags & MIFF_REGISTER)
+	if ((v->flags & MIFF_REGISTER) && !notify)
 		unregister_netdevice_queue(dev, head);
 
 	dev_put(dev);
@@ -1331,7 +1332,6 @@ static int ip6mr_device_event(struct notifier_block *this,
 	struct mr6_table *mrt;
 	struct mif_device *v;
 	int ct;
-	LIST_HEAD(list);
 
 	if (event != NETDEV_UNREGISTER)
 		return NOTIFY_DONE;
@@ -1340,10 +1340,9 @@ static int ip6mr_device_event(struct notifier_block *this,
 		v = &mrt->vif6_table[0];
 		for (ct = 0; ct < mrt->maxvif; ct++, v++) {
 			if (v->dev == dev)
-				mif6_delete(mrt, ct, &list);
+				mif6_delete(mrt, ct, 1, NULL);
 		}
 	}
-	unregister_netdevice_many(&list);
 
 	return NOTIFY_DONE;
 }
@@ -1552,7 +1551,7 @@ static void mroute_clean_tables(struct mr6_table *mrt, bool all)
 	for (i = 0; i < mrt->maxvif; i++) {
 		if (!all && (mrt->vif6_table[i].flags & VIFF_STATIC))
 			continue;
-		mif6_delete(mrt, i, &list);
+		mif6_delete(mrt, i, 0, &list);
 	}
 	unregister_netdevice_many(&list);
 
@@ -1706,7 +1705,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
 		if (copy_from_user(&mifi, optval, sizeof(mifi_t)))
 			return -EFAULT;
 		rtnl_lock();
-		ret = mif6_delete(mrt, mifi, NULL);
+		ret = mif6_delete(mrt, mifi, 0, NULL);
 		rtnl_unlock();
 		return ret;
 
-- 
2.4.11


From 776b40dbf07088c5637995cb31c69c59170a5bde Mon Sep 17 00:00:00 2001
From: Mohamad Haj Yahia <mohamad@mellanox.com>
Date: Thu, 30 Mar 2017 17:00:25 +0300
Subject: [PATCH 30/41] net/mlx5: Fix driver load bad flow when having fw
 initializing timeout

[ Upstream commit 55378a238e04b39cc82957d91d16499704ea719b ]

If FW is stuck in initializing state we will skip the driver load, but
current error handling flow doesn't clean previously allocated command
interface resources.

Fixes: e3297246c2c8 ('net/mlx5_core: Wait for FW readiness on startup')
Signed-off-by: Mohamad Haj Yahia <mohamad@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 4aca265..4ee7ea7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1001,7 +1001,7 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 	if (err) {
 		dev_err(&dev->pdev->dev, "Firmware over %d MS in initializing state, aborting\n",
 			FW_INIT_TIMEOUT_MILI);
-		goto out_err;
+		goto err_cmd_cleanup;
 	}
 
 	err = mlx5_core_enable_hca(dev, 0);
-- 
2.4.11


From 9bf02930398aee045e71883e2969d3ed7e507e58 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Thu, 30 Mar 2017 15:56:10 +0200
Subject: [PATCH 31/41] net/mlx5: E-Switch, Correctly deal with inline mode on
 ConnectX-5

[ Upstream commit c415f704c8276bc686abcb0497bf2606038ca73c ]

On ConnectX5 the wqe inline mode is "none" and hence the FW
reports MLX5_CAP_INLINE_MODE_NOT_REQUIRED.

Fix our devlink callbacks to deal with that on get and set.

Also fix the tc flow parsing code not to fail anything when
inline isn't required.

Fixes: bffaa916588e ('net/mlx5: E-Switch, Add control for inline mode')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c    |  3 +-
 .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 36 ++++++++++++++--------
 2 files changed, 26 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index cc71881..dc5c594f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -611,7 +611,8 @@ static int parse_cls_flower(struct mlx5e_priv *priv,
 
 	if (!err && esw->mode == SRIOV_OFFLOADS &&
 	    rep->vport != FDB_UPLINK_VPORT) {
-		if (min_inline > esw->offloads.inline_mode) {
+		if (esw->offloads.inline_mode != MLX5_INLINE_MODE_NONE &&
+		    esw->offloads.inline_mode < min_inline) {
 			netdev_warn(priv->netdev,
 				    "Flow is not offloaded due to min inline setting, required %d actual %d\n",
 				    min_inline, esw->offloads.inline_mode);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 7bce2bd..4d111c1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -908,8 +908,7 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode)
 	struct mlx5_core_dev *dev = devlink_priv(devlink);
 	struct mlx5_eswitch *esw = dev->priv.eswitch;
 	int num_vports = esw->enabled_vports;
-	int err;
-	int vport;
+	int err, vport;
 	u8 mlx5_mode;
 
 	if (!MLX5_CAP_GEN(dev, vport_group_manager))
@@ -918,9 +917,17 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode)
 	if (esw->mode == SRIOV_NONE)
 		return -EOPNOTSUPP;
 
-	if (MLX5_CAP_ETH(dev, wqe_inline_mode) !=
-	    MLX5_CAP_INLINE_MODE_VPORT_CONTEXT)
+	switch (MLX5_CAP_ETH(dev, wqe_inline_mode)) {
+	case MLX5_CAP_INLINE_MODE_NOT_REQUIRED:
+		if (mode == DEVLINK_ESWITCH_INLINE_MODE_NONE)
+			return 0;
+		/* fall through */
+	case MLX5_CAP_INLINE_MODE_L2:
+		esw_warn(dev, "Inline mode can't be set\n");
 		return -EOPNOTSUPP;
+	case MLX5_CAP_INLINE_MODE_VPORT_CONTEXT:
+		break;
+	}
 
 	if (esw->offloads.num_flows > 0) {
 		esw_warn(dev, "Can't set inline mode when flows are configured\n");
@@ -963,18 +970,14 @@ int mlx5_devlink_eswitch_inline_mode_get(struct devlink *devlink, u8 *mode)
 	if (esw->mode == SRIOV_NONE)
 		return -EOPNOTSUPP;
 
-	if (MLX5_CAP_ETH(dev, wqe_inline_mode) !=
-	    MLX5_CAP_INLINE_MODE_VPORT_CONTEXT)
-		return -EOPNOTSUPP;
-
 	return esw_inline_mode_to_devlink(esw->offloads.inline_mode, mode);
 }
 
 int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, int nvfs, u8 *mode)
 {
+	u8 prev_mlx5_mode, mlx5_mode = MLX5_INLINE_MODE_L2;
 	struct mlx5_core_dev *dev = esw->dev;
 	int vport;
-	u8 prev_mlx5_mode, mlx5_mode = MLX5_INLINE_MODE_L2;
 
 	if (!MLX5_CAP_GEN(dev, vport_group_manager))
 		return -EOPNOTSUPP;
@@ -982,10 +985,18 @@ int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, int nvfs, u8 *mode)
 	if (esw->mode == SRIOV_NONE)
 		return -EOPNOTSUPP;
 
-	if (MLX5_CAP_ETH(dev, wqe_inline_mode) !=
-	    MLX5_CAP_INLINE_MODE_VPORT_CONTEXT)
-		return -EOPNOTSUPP;
+	switch (MLX5_CAP_ETH(dev, wqe_inline_mode)) {
+	case MLX5_CAP_INLINE_MODE_NOT_REQUIRED:
+		mlx5_mode = MLX5_INLINE_MODE_NONE;
+		goto out;
+	case MLX5_CAP_INLINE_MODE_L2:
+		mlx5_mode = MLX5_INLINE_MODE_L2;
+		goto out;
+	case MLX5_CAP_INLINE_MODE_VPORT_CONTEXT:
+		goto query_vports;
+	}
 
+query_vports:
 	for (vport = 1; vport <= nvfs; vport++) {
 		mlx5_query_nic_vport_min_inline(dev, vport, &mlx5_mode);
 		if (vport > 1 && prev_mlx5_mode != mlx5_mode)
@@ -993,6 +1004,7 @@ int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, int nvfs, u8 *mode)
 		prev_mlx5_mode = mlx5_mode;
 	}
 
+out:
 	*mode = mlx5_mode;
 	return 0;
 }
-- 
2.4.11


From f5fd87b706e5d91c4cd16d31ffa3edaf8dc1c130 Mon Sep 17 00:00:00 2001
From: Eugenia Emantayev <eugenia@mellanox.com>
Date: Wed, 22 Mar 2017 11:44:14 +0200
Subject: [PATCH 32/41] net/mlx5e: Fix small packet threshold

[ Upstream commit cbad8cddb6ed7ef3a5f0a9a70f1711d4d7fb9a8f ]

RX packet headers are meant to be contained in SKB linear part,
and chose a threshold of 128.
It turns out this is not enough, i.e. for IPv6 packet over VxLAN.
In this case, UDP/IPv4 needs 42 bytes, GENEVE header is 8 bytes,
and 86 bytes for TCP/IPv6. In total 136 bytes that is more than
current 128 bytes. In this case expand header flow is reached.
The warning in skb_try_coalesce() caused by a wrong truesize
was already fixed here:
commit 158f323b9868 ("net: adjust skb->truesize in pskb_expand_head()").
Still, we prefer to totally avoid the expand header flow for performance reasons.
Tested regular TCP_STREAM with iperf for 1 and 8 streams, no degradation was found.

Fixes: 461017cb006a ("net/mlx5e: Support RX multi-packet WQE (Striding RQ)")
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 41db470..0145765 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -82,7 +82,7 @@
 #define MLX5E_VALID_NUM_MTTS(num_mtts) (MLX5_MTT_OCTW(num_mtts) - 1 <= U16_MAX)
 
 #define MLX5_UMR_ALIGN				(2048)
-#define MLX5_MPWRQ_SMALL_PACKET_THRESHOLD	(128)
+#define MLX5_MPWRQ_SMALL_PACKET_THRESHOLD	(256)
 
 #define MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ                 (64 * 1024)
 #define MLX5E_DEFAULT_LRO_TIMEOUT                       32
-- 
2.4.11


From 20777f5f9490c799d24e0546b3eff48a54b96aa6 Mon Sep 17 00:00:00 2001
From: Ilan Tayari <ilant@mellanox.com>
Date: Thu, 2 Mar 2017 15:49:45 +0200
Subject: [PATCH 33/41] net/mlx5e: Fix ETHTOOL_GRXCLSRLALL handling

[ Upstream commit 5e82c9e4ed60beba83f46a1a5a8307b99a23e982 ]

Handler for ETHTOOL_GRXCLSRLALL must set info->data to the size
of the table, regardless of the amount of entries in it.
Existing code does not do that, and this breaks all usage of ethtool -N
or -n without explicit location, with this error:
rmgr: Invalid RX class rules table size: Success

Set info->data to the table size.

Tested:
ethtool -n ens8
ethtool -N ens8 flow-type ip4 src-ip 1.1.1.1 dst-ip 2.2.2.2 action 1
ethtool -N ens8 flow-type ip4 src-ip 1.1.1.1 dst-ip 2.2.2.2 action 1 loc 55
ethtool -n ens8
ethtool -N ens8 delete 1023
ethtool -N ens8 delete 55

Fixes: f913a72aa008 ("net/mlx5e: Add support to get ethtool flow rules")
Signed-off-by: Ilan Tayari <ilant@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index f33f72d..32d56cd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -564,6 +564,7 @@ int mlx5e_ethtool_get_all_flows(struct mlx5e_priv *priv, struct ethtool_rxnfc *i
 	int idx = 0;
 	int err = 0;
 
+	info->data = MAX_NUM_OF_ETHTOOL_RULES;
 	while ((!err || err == -ENOENT) && idx < info->rule_cnt) {
 		err = mlx5e_ethtool_get_flow(priv, info, location);
 		if (!err)
-- 
2.4.11


From 52d67f80527e6b27dabeab0f8c397f785367a636 Mon Sep 17 00:00:00 2001
From: Soheil Hassas Yeganeh <soheil@google.com>
Date: Sat, 18 Mar 2017 17:02:59 -0400
Subject: [PATCH 34/41] tcp: fix SCM_TIMESTAMPING_OPT_STATS for normal skbs

[ Upstream commit 8605330aac5a5785630aec8f64378a54891937cc ]

__sock_recv_timestamp can be called for both normal skbs (for
receive timestamps) and for skbs on the error queue (for transmit
timestamps).

Commit 1c885808e456
(tcp: SOF_TIMESTAMPING_OPT_STATS option for SO_TIMESTAMPING)
assumes any skb passed to __sock_recv_timestamp are from
the error queue, containing OPT_STATS in the content of the skb.
This results in accessing invalid memory or generating junk
data.

To fix this, set skb->pkt_type to PACKET_OUTGOING for packets
on the error queue. This is safe because on the receive path
on local sockets skb->pkt_type is never set to PACKET_OUTGOING.
With that, copy OPT_STATS from a packet, only if its pkt_type
is PACKET_OUTGOING.

Fixes: 1c885808e456 ("tcp: SOF_TIMESTAMPING_OPT_STATS option for SO_TIMESTAMPING")
Reported-by: JongHwan Kim <zzoru007@gmail.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 10 ++++++++++
 net/socket.c      | 13 ++++++++++++-
 2 files changed, 22 insertions(+), 1 deletion(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index c3cb99c..e4b6d54 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3700,6 +3700,15 @@ static void sock_rmem_free(struct sk_buff *skb)
 	atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
 }
 
+static void skb_set_err_queue(struct sk_buff *skb)
+{
+	/* pkt_type of skbs received on local sockets is never PACKET_OUTGOING.
+	 * So, it is safe to (mis)use it to mark skbs on the error queue.
+	 */
+	skb->pkt_type = PACKET_OUTGOING;
+	BUILD_BUG_ON(PACKET_OUTGOING == 0);
+}
+
 /*
  * Note: We dont mem charge error packets (no sk_forward_alloc changes)
  */
@@ -3713,6 +3722,7 @@ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
 	skb->sk = sk;
 	skb->destructor = sock_rmem_free;
 	atomic_add(skb->truesize, &sk->sk_rmem_alloc);
+	skb_set_err_queue(skb);
 
 	/* before exiting rcu section, make sure dst is refcounted */
 	skb_dst_force(skb);
diff --git a/net/socket.c b/net/socket.c
index 02bd924..bfdb358 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -654,6 +654,16 @@ int kernel_sendmsg(struct socket *sock, struct msghdr *msg,
 }
 EXPORT_SYMBOL(kernel_sendmsg);
 
+static bool skb_is_err_queue(const struct sk_buff *skb)
+{
+	/* pkt_type of skbs enqueued on the error queue are set to
+	 * PACKET_OUTGOING in skb_set_err_queue(). This is only safe to do
+	 * in recvmsg, since skbs received on a local socket will never
+	 * have a pkt_type of PACKET_OUTGOING.
+	 */
+	return skb->pkt_type == PACKET_OUTGOING;
+}
+
 /*
  * called from sock_recv_timestamp() if sock_flag(sk, SOCK_RCVTSTAMP)
  */
@@ -697,7 +707,8 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
 		put_cmsg(msg, SOL_SOCKET,
 			 SCM_TIMESTAMPING, sizeof(tss), &tss);
 
-		if (skb->len && (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_STATS))
+		if (skb_is_err_queue(skb) && skb->len &&
+		    (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_STATS))
 			put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING_OPT_STATS,
 				 skb->len, skb->data);
 	}
-- 
2.4.11


From bd3ac5292ade9c7662c8e120c4093937ac281407 Mon Sep 17 00:00:00 2001
From: Soheil Hassas Yeganeh <soheil@google.com>
Date: Sat, 18 Mar 2017 17:03:00 -0400
Subject: [PATCH 35/41] tcp: mark skbs with SCM_TIMESTAMPING_OPT_STATS

[ Upstream commit 4ef1b2869447411ad3ef91ad7d4891a83c1a509a ]

SOF_TIMESTAMPING_OPT_STATS can be enabled and disabled
while packets are collected on the error queue.
So, checking SOF_TIMESTAMPING_OPT_STATS in sk->sk_tsflags
is not enough to safely assume that the skb contains
OPT_STATS data.

Add a bit in sock_exterr_skb to indicate whether the
skb contains opt_stats data.

Fixes: 1c885808e456 ("tcp: SOF_TIMESTAMPING_OPT_STATS option for SO_TIMESTAMPING")
Reported-by: JongHwan Kim <zzoru007@gmail.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/errqueue.h |  2 ++
 net/core/skbuff.c        | 17 +++++++++++------
 net/socket.c             |  2 +-
 3 files changed, 14 insertions(+), 7 deletions(-)

diff --git a/include/linux/errqueue.h b/include/linux/errqueue.h
index 9ca23fc..6fdfc88 100644
--- a/include/linux/errqueue.h
+++ b/include/linux/errqueue.h
@@ -20,6 +20,8 @@ struct sock_exterr_skb {
 	struct sock_extended_err	ee;
 	u16				addr_offset;
 	__be16				port;
+	u8				opt_stats:1,
+					unused:7;
 };
 
 #endif
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index e4b6d54..887995e 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3799,16 +3799,20 @@ EXPORT_SYMBOL(skb_clone_sk);
 
 static void __skb_complete_tx_timestamp(struct sk_buff *skb,
 					struct sock *sk,
-					int tstype)
+					int tstype,
+					bool opt_stats)
 {
 	struct sock_exterr_skb *serr;
 	int err;
 
+	BUILD_BUG_ON(sizeof(struct sock_exterr_skb) > sizeof(skb->cb));
+
 	serr = SKB_EXT_ERR(skb);
 	memset(serr, 0, sizeof(*serr));
 	serr->ee.ee_errno = ENOMSG;
 	serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING;
 	serr->ee.ee_info = tstype;
+	serr->opt_stats = opt_stats;
 	serr->header.h4.iif = skb->dev ? skb->dev->ifindex : 0;
 	if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) {
 		serr->ee.ee_data = skb_shinfo(skb)->tskey;
@@ -3850,7 +3854,7 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
 	 */
 	if (likely(atomic_inc_not_zero(&sk->sk_refcnt))) {
 		*skb_hwtstamps(skb) = *hwtstamps;
-		__skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND);
+		__skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND, false);
 		sock_put(sk);
 	}
 }
@@ -3861,7 +3865,7 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
 		     struct sock *sk, int tstype)
 {
 	struct sk_buff *skb;
-	bool tsonly;
+	bool tsonly, opt_stats = false;
 
 	if (!sk)
 		return;
@@ -3874,9 +3878,10 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
 #ifdef CONFIG_INET
 		if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_STATS) &&
 		    sk->sk_protocol == IPPROTO_TCP &&
-		    sk->sk_type == SOCK_STREAM)
+		    sk->sk_type == SOCK_STREAM) {
 			skb = tcp_get_timestamping_opt_stats(sk);
-		else
+			opt_stats = true;
+		} else
 #endif
 			skb = alloc_skb(0, GFP_ATOMIC);
 	} else {
@@ -3895,7 +3900,7 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
 	else
 		skb->tstamp = ktime_get_real();
 
-	__skb_complete_tx_timestamp(skb, sk, tstype);
+	__skb_complete_tx_timestamp(skb, sk, tstype, opt_stats);
 }
 EXPORT_SYMBOL_GPL(__skb_tstamp_tx);
 
diff --git a/net/socket.c b/net/socket.c
index bfdb358..6361d31 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -708,7 +708,7 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
 			 SCM_TIMESTAMPING, sizeof(tss), &tss);
 
 		if (skb_is_err_queue(skb) && skb->len &&
-		    (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_STATS))
+		    SKB_EXT_ERR(skb)->opt_stats)
 			put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING_OPT_STATS,
 				 skb->len, skb->data);
 	}
-- 
2.4.11


From be89249c9fcb01e968710387c64bf61218798507 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Thu, 20 Apr 2017 20:55:12 +0800
Subject: [PATCH 36/41] macvlan: Fix device ref leak when purging bc_queue

[ Upstream commit f6478218e6edc2a587b8f132f66373baa7b2497c ]

When a parent macvlan device is destroyed we end up purging its
broadcast queue without dropping the device reference count on
the packet source device.  This causes the source device to linger.

This patch drops that reference count.

Fixes: 260916dfb48c ("macvlan: Fix potential use-after free for...")
Reported-by: Joe Ghalam <Joe.Ghalam@dell.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macvlan.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 20b3fdf2..7d49a36 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -1140,6 +1140,7 @@ static int macvlan_port_create(struct net_device *dev)
 static void macvlan_port_destroy(struct net_device *dev)
 {
 	struct macvlan_port *port = macvlan_port_get_rtnl(dev);
+	struct sk_buff *skb;
 
 	dev->priv_flags &= ~IFF_MACVLAN_PORT;
 	netdev_rx_handler_unregister(dev);
@@ -1148,7 +1149,15 @@ static void macvlan_port_destroy(struct net_device *dev)
 	 * but we need to cancel it and purge left skbs if any.
 	 */
 	cancel_work_sync(&port->bc_work);
-	__skb_queue_purge(&port->bc_queue);
+
+	while ((skb = __skb_dequeue(&port->bc_queue))) {
+		const struct macvlan_dev *src = MACVLAN_SKB_CB(skb)->src;
+
+		if (src)
+			dev_put(src->dev);
+
+		kfree_skb(skb);
+	}
 
 	kfree(port);
 }
-- 
2.4.11


From 91a27593502be9500e768ae8756e6b7ad495610b Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Tue, 25 Apr 2017 09:17:29 -0700
Subject: [PATCH 37/41] net: ipv6: regenerate host route if moved to gc list

[ Upstream commit 8048ced9beb21a52e3305f3332ae82020619f24e ]

Taking down the loopback device wreaks havoc on IPv6 routing. By
extension, taking down a VRF device wreaks havoc on its table.

Dmitry and Andrey both reported heap out-of-bounds reports in the IPv6
FIB code while running syzkaller fuzzer. The root cause is a dead dst
that is on the garbage list gets reinserted into the IPv6 FIB. While on
the gc (or perhaps when it gets added to the gc list) the dst->next is
set to an IPv4 dst. A subsequent walk of the ipv6 tables causes the
out-of-bounds access.

Andrey's reproducer was the key to getting to the bottom of this.

With IPv6, host routes for an address have the dst->dev set to the
loopback device. When the 'lo' device is taken down, rt6_ifdown initiates
a walk of the fib evicting routes with the 'lo' device which means all
host routes are removed. That process moves the dst which is attached to
an inet6_ifaddr to the gc list and marks it as dead.

The recent change to keep global IPv6 addresses added a new function,
fixup_permanent_addr, that is called on admin up. That function restarts
dad for an inet6_ifaddr and when it completes the host route attached
to it is inserted into the fib. Since the route was marked dead and
moved to the gc list, re-inserting the route causes the reported
out-of-bounds accesses. If the device with the address is taken down
or the address is removed, the WARN_ON in fib6_del is triggered.

All of those faults are fixed by regenerating the host route if the
existing one has been moved to the gc list, something that can be
determined by checking if the rt6i_ref counter is 0.

Fixes: f1705ec197e7 ("net: ipv6: Make address flushing on ifdown optional")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 8c4ee4e..ec76bbe 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3263,14 +3263,24 @@ static void addrconf_gre_config(struct net_device *dev)
 static int fixup_permanent_addr(struct inet6_dev *idev,
 				struct inet6_ifaddr *ifp)
 {
-	if (!ifp->rt) {
-		struct rt6_info *rt;
+	/* rt6i_ref == 0 means the host route was removed from the
+	 * FIB, for example, if 'lo' device is taken down. In that
+	 * case regenerate the host route.
+	 */
+	if (!ifp->rt || !atomic_read(&ifp->rt->rt6i_ref)) {
+		struct rt6_info *rt, *prev;
 
 		rt = addrconf_dst_alloc(idev, &ifp->addr, false);
 		if (unlikely(IS_ERR(rt)))
 			return PTR_ERR(rt);
 
+		/* ifp->rt can be accessed outside of rtnl */
+		spin_lock(&ifp->lock);
+		prev = ifp->rt;
 		ifp->rt = rt;
+		spin_unlock(&ifp->lock);
+
+		ip6_rt_put(prev);
 	}
 
 	if (!(ifp->flags & IFA_F_NOPREFIXROUTE)) {
-- 
2.4.11


From d2dee9ad54cad234a3f8bf0698041f11d9d87d54 Mon Sep 17 00:00:00 2001
From: Alexander Kochetkov <al.kochet@gmail.com>
Date: Thu, 20 Apr 2017 14:00:04 +0300
Subject: [PATCH 38/41] net: phy: fix auto-negotiation stall due to unavailable
 interrupt

[ Upstream commit f555f34fdc586a56204cd16d9a7c104ec6cb6650 ]

The Ethernet link on an interrupt driven PHY was not coming up if the Ethernet
cable was plugged before the Ethernet interface was brought up.

The patch trigger PHY state machine to update link state if PHY was requested to
do auto-negotiation and auto-negotiation complete flag already set.

During power-up cycle the PHY do auto-negotiation, generate interrupt and set
auto-negotiation complete flag. Interrupt is handled by PHY state machine but
doesn't update link state because PHY is in PHY_READY state. After some time
MAC bring up, start and request PHY to do auto-negotiation. If there are no new
settings to advertise genphy_config_aneg() doesn't start PHY auto-negotiation.
PHY continue to stay in auto-negotiation complete state and doesn't fire
interrupt. At the same time PHY state machine expect that PHY started
auto-negotiation and is waiting for interrupt from PHY and it won't get it.

Fixes: 321beec5047a ("net: phy: Use interrupts when available in NOLINK state")
Signed-off-by: Alexander Kochetkov <al.kochet@gmail.com>
Cc: stable <stable@vger.kernel.org> # v4.9+
Tested-by: Roger Quadros <rogerq@ti.com>
Tested-by: Alexandre Belloni <alexandre.belloni@free-electrons.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 40 ++++++++++++++++++++++++++++++++++++----
 include/linux/phy.h   |  1 +
 2 files changed, 37 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index fe2d4c4..b41a32b 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -591,16 +591,18 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd)
 EXPORT_SYMBOL(phy_mii_ioctl);
 
 /**
- * phy_start_aneg - start auto-negotiation for this PHY device
+ * phy_start_aneg_priv - start auto-negotiation for this PHY device
  * @phydev: the phy_device struct
+ * @sync: indicate whether we should wait for the workqueue cancelation
  *
  * Description: Sanitizes the settings (if we're not autonegotiating
  *   them), and then calls the driver's config_aneg function.
  *   If the PHYCONTROL Layer is operating, we change the state to
  *   reflect the beginning of Auto-negotiation or forcing.
  */
-int phy_start_aneg(struct phy_device *phydev)
+static int phy_start_aneg_priv(struct phy_device *phydev, bool sync)
 {
+	bool trigger = 0;
 	int err;
 
 	mutex_lock(&phydev->lock);
@@ -625,10 +627,40 @@ int phy_start_aneg(struct phy_device *phydev)
 		}
 	}
 
+	/* Re-schedule a PHY state machine to check PHY status because
+	 * negotiation may already be done and aneg interrupt may not be
+	 * generated.
+	 */
+	if (phy_interrupt_is_valid(phydev) && (phydev->state == PHY_AN)) {
+		err = phy_aneg_done(phydev);
+		if (err > 0) {
+			trigger = true;
+			err = 0;
+		}
+	}
+
 out_unlock:
 	mutex_unlock(&phydev->lock);
+
+	if (trigger)
+		phy_trigger_machine(phydev, sync);
+
 	return err;
 }
+
+/**
+ * phy_start_aneg - start auto-negotiation for this PHY device
+ * @phydev: the phy_device struct
+ *
+ * Description: Sanitizes the settings (if we're not autonegotiating
+ *   them), and then calls the driver's config_aneg function.
+ *   If the PHYCONTROL Layer is operating, we change the state to
+ *   reflect the beginning of Auto-negotiation or forcing.
+ */
+int phy_start_aneg(struct phy_device *phydev)
+{
+	return phy_start_aneg_priv(phydev, true);
+}
 EXPORT_SYMBOL(phy_start_aneg);
 
 /**
@@ -656,7 +688,7 @@ void phy_start_machine(struct phy_device *phydev)
  *   state machine runs.
  */
 
-static void phy_trigger_machine(struct phy_device *phydev, bool sync)
+void phy_trigger_machine(struct phy_device *phydev, bool sync)
 {
 	if (sync)
 		cancel_delayed_work_sync(&phydev->state_queue);
@@ -1151,7 +1183,7 @@ void phy_state_machine(struct work_struct *work)
 	mutex_unlock(&phydev->lock);
 
 	if (needs_aneg)
-		err = phy_start_aneg(phydev);
+		err = phy_start_aneg_priv(phydev, false);
 	else if (do_suspend)
 		phy_suspend(phydev);
 
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 7fc1105..b19ae66 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -840,6 +840,7 @@ void phy_change_work(struct work_struct *work);
 void phy_mac_interrupt(struct phy_device *phydev, int new_link);
 void phy_start_machine(struct phy_device *phydev);
 void phy_stop_machine(struct phy_device *phydev);
+void phy_trigger_machine(struct phy_device *phydev, bool sync);
 int phy_ethtool_sset(struct phy_device *phydev, struct ethtool_cmd *cmd);
 int phy_ethtool_gset(struct phy_device *phydev, struct ethtool_cmd *cmd);
 int phy_ethtool_ksettings_get(struct phy_device *phydev,
-- 
2.4.11


From b4a1695ec6d7c71cc5087dc12f44322e37531d54 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Tue, 25 Apr 2017 14:37:15 -0700
Subject: [PATCH 39/41] ipv6: check skb->protocol before lookup for nexthop

[ Upstream commit 199ab00f3cdb6f154ea93fa76fd80192861a821d ]

Andrey reported a out-of-bound access in ip6_tnl_xmit(), this
is because we use an ipv4 dst in ip6_tnl_xmit() and cast an IPv4
neigh key as an IPv6 address:

        neigh = dst_neigh_lookup(skb_dst(skb),
                                 &ipv6_hdr(skb)->daddr);
        if (!neigh)
                goto tx_err_link_failure;

        addr6 = (struct in6_addr *)&neigh->primary_key; // <=== HERE
        addr_type = ipv6_addr_type(addr6);

        if (addr_type == IPV6_ADDR_ANY)
                addr6 = &ipv6_hdr(skb)->daddr;

        memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr));

Also the network header of the skb at this point should be still IPv4
for 4in6 tunnels, we shold not just use it as IPv6 header.

This patch fixes it by checking if skb->protocol is ETH_P_IPV6: if it
is, we are safe to do the nexthop lookup using skb_dst() and
ipv6_hdr(skb)->daddr; if not (aka IPv4), we have no clue about which
dest address we can pick here, we have to rely on callers to fill it
from tunnel config, so just fall to ip6_route_output() to make the
decision.

Fixes: ea3dc9601bda ("ip6_tunnel: Add support for wildcard tunnel endpoints.")
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 34 ++++++++++++++++++----------------
 1 file changed, 18 insertions(+), 16 deletions(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 75fac93..a9692ec 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1037,7 +1037,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 	struct ip6_tnl *t = netdev_priv(dev);
 	struct net *net = t->net;
 	struct net_device_stats *stats = &t->dev->stats;
-	struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+	struct ipv6hdr *ipv6h;
 	struct ipv6_tel_txoption opt;
 	struct dst_entry *dst = NULL, *ndst = NULL;
 	struct net_device *tdev;
@@ -1057,26 +1057,28 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 
 	/* NBMA tunnel */
 	if (ipv6_addr_any(&t->parms.raddr)) {
-		struct in6_addr *addr6;
-		struct neighbour *neigh;
-		int addr_type;
+		if (skb->protocol == htons(ETH_P_IPV6)) {
+			struct in6_addr *addr6;
+			struct neighbour *neigh;
+			int addr_type;
 
-		if (!skb_dst(skb))
-			goto tx_err_link_failure;
+			if (!skb_dst(skb))
+				goto tx_err_link_failure;
 
-		neigh = dst_neigh_lookup(skb_dst(skb),
-					 &ipv6_hdr(skb)->daddr);
-		if (!neigh)
-			goto tx_err_link_failure;
+			neigh = dst_neigh_lookup(skb_dst(skb),
+						 &ipv6_hdr(skb)->daddr);
+			if (!neigh)
+				goto tx_err_link_failure;
 
-		addr6 = (struct in6_addr *)&neigh->primary_key;
-		addr_type = ipv6_addr_type(addr6);
+			addr6 = (struct in6_addr *)&neigh->primary_key;
+			addr_type = ipv6_addr_type(addr6);
 
-		if (addr_type == IPV6_ADDR_ANY)
-			addr6 = &ipv6_hdr(skb)->daddr;
+			if (addr_type == IPV6_ADDR_ANY)
+				addr6 = &ipv6_hdr(skb)->daddr;
 
-		memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr));
-		neigh_release(neigh);
+			memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr));
+			neigh_release(neigh);
+		}
 	} else if (!(t->parms.flags &
 		     (IP6_TNL_F_USE_ORIG_TCLASS | IP6_TNL_F_USE_ORIG_FWMARK))) {
 		/* enable the cache only only if the routing decision does
-- 
2.4.11


From 99626d6edebc47c8a9e72035f514968b21f09d5d Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Tue, 25 Apr 2017 17:38:02 -0700
Subject: [PATCH 40/41] tcp: memset ca_priv data to 0 properly

[ Upstream commit c1201444075009507a6818de6518e2822b9a87c8 ]

Always zero out ca_priv data in tcp_assign_congestion_control() so that
ca_priv data is cleared out during socket creation.
Also always zero out ca_priv data in tcp_reinit_congestion_control() so
that when cc algorithm is changed, ca_priv data is cleared out as well.
We should still zero out ca_priv data even in TCP_CLOSE state because
user could call connect() on AF_UNSPEC to disconnect the socket and
leave it in TCP_CLOSE state and later call setsockopt() to switch cc
algorithm on this socket.

Fixes: 2b0a8c9ee ("tcp: add CDG congestion control")
Reported-by: Andrey Konovalov  <andreyknvl@google.com>
Signed-off-by: Wei Wang <weiwan@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_cong.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 79c4817..6e3c512 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -168,12 +168,8 @@ void tcp_assign_congestion_control(struct sock *sk)
 	}
 out:
 	rcu_read_unlock();
+	memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
 
-	/* Clear out private data before diag gets it and
-	 * the ca has not been initialized.
-	 */
-	if (ca->get_info)
-		memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
 	if (ca->flags & TCP_CONG_NEEDS_ECN)
 		INET_ECN_xmit(sk);
 	else
@@ -200,11 +196,10 @@ static void tcp_reinit_congestion_control(struct sock *sk,
 	tcp_cleanup_congestion_control(sk);
 	icsk->icsk_ca_ops = ca;
 	icsk->icsk_ca_setsockopt = 1;
+	memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
 
-	if (sk->sk_state != TCP_CLOSE) {
-		memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
+	if (sk->sk_state != TCP_CLOSE)
 		tcp_init_congestion_control(sk);
-	}
 }
 
 /* Manage refcounts on socket close. */
-- 
2.4.11


From c1cde7dc4d275ffcbdcd50d17078ee744acfd2cb Mon Sep 17 00:00:00 2001
From: Jamie Bainbridge <jbainbri@redhat.com>
Date: Wed, 26 Apr 2017 10:43:27 +1000
Subject: [PATCH 41/41] ipv6: check raw payload size correctly in ioctl

[ Upstream commit 105f5528b9bbaa08b526d3405a5bcd2ff0c953c8 ]

In situations where an skb is paged, the transport header pointer and
tail pointer can be the same because the skb contents are in frags.

This results in ioctl(SIOCINQ/FIONREAD) incorrectly returning a
length of 0 when the length to receive is actually greater than zero.

skb->len is already correctly set in ip6_input_finish() with
pskb_pull(), so use skb->len as it always returns the correct result
for both linear and paged data.

Signed-off-by: Jamie Bainbridge <jbainbri@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/raw.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index ea89073..294fb6f 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -1174,8 +1174,7 @@ static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg)
 		spin_lock_bh(&sk->sk_receive_queue.lock);
 		skb = skb_peek(&sk->sk_receive_queue);
 		if (skb)
-			amount = skb_tail_pointer(skb) -
-				skb_transport_header(skb);
+			amount = skb->len;
 		spin_unlock_bh(&sk->sk_receive_queue.lock);
 		return put_user(amount, (int __user *)arg);
 	}
-- 
2.4.11

Re: [PATCHES] Networking

[Greg KH]

On Fri, Apr 28, 2017 at 03:41:15PM -0400, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.9
> and v4.10 -stable, respectively.

Many thanks for these, all now applied.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 105 bytes --]


Please queue up the following networking bug fixes for 4.10
and 4.11 -stable, respectively.

Thank you.

[-- Attachment #2: net_410.mbox --]
[-- Type: Application/Octet-Stream, Size: 53863 bytes --]

From 2b9b3da35f7b83f149aca94c58f554e45f78d9eb Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Tue, 25 Apr 2017 19:08:18 +0200
Subject: [PATCH 01/19] macsec: dynamically allocate space for sglist

[ Upstream commit 5294b83086cc1c35b4efeca03644cf9d12282e5b ]

We call skb_cow_data, which is good anyway to ensure we can actually
modify the skb as such (another error from prior). Now that we have the
number of fragments required, we can safely allocate exactly that amount
of memory.

Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver")
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Acked-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macsec.c | 29 ++++++++++++++++++++++-------
 1 file changed, 22 insertions(+), 7 deletions(-)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 8420069..4b14d2f 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -617,7 +617,8 @@ static void macsec_encrypt_done(struct crypto_async_request *base, int err)
 
 static struct aead_request *macsec_alloc_req(struct crypto_aead *tfm,
 					     unsigned char **iv,
-					     struct scatterlist **sg)
+					     struct scatterlist **sg,
+					     int num_frags)
 {
 	size_t size, iv_offset, sg_offset;
 	struct aead_request *req;
@@ -629,7 +630,7 @@ static struct aead_request *macsec_alloc_req(struct crypto_aead *tfm,
 
 	size = ALIGN(size, __alignof__(struct scatterlist));
 	sg_offset = size;
-	size += sizeof(struct scatterlist) * (MAX_SKB_FRAGS + 1);
+	size += sizeof(struct scatterlist) * num_frags;
 
 	tmp = kmalloc(size, GFP_ATOMIC);
 	if (!tmp)
@@ -649,6 +650,7 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb,
 {
 	int ret;
 	struct scatterlist *sg;
+	struct sk_buff *trailer;
 	unsigned char *iv;
 	struct ethhdr *eth;
 	struct macsec_eth_header *hh;
@@ -723,7 +725,14 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb,
 		return ERR_PTR(-EINVAL);
 	}
 
-	req = macsec_alloc_req(tx_sa->key.tfm, &iv, &sg);
+	ret = skb_cow_data(skb, 0, &trailer);
+	if (unlikely(ret < 0)) {
+		macsec_txsa_put(tx_sa);
+		kfree_skb(skb);
+		return ERR_PTR(ret);
+	}
+
+	req = macsec_alloc_req(tx_sa->key.tfm, &iv, &sg, ret);
 	if (!req) {
 		macsec_txsa_put(tx_sa);
 		kfree_skb(skb);
@@ -732,7 +741,7 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb,
 
 	macsec_fill_iv(iv, secy->sci, pn);
 
-	sg_init_table(sg, MAX_SKB_FRAGS + 1);
+	sg_init_table(sg, ret);
 	skb_to_sgvec(skb, sg, 0, skb->len);
 
 	if (tx_sc->encrypt) {
@@ -914,6 +923,7 @@ static struct sk_buff *macsec_decrypt(struct sk_buff *skb,
 {
 	int ret;
 	struct scatterlist *sg;
+	struct sk_buff *trailer;
 	unsigned char *iv;
 	struct aead_request *req;
 	struct macsec_eth_header *hdr;
@@ -924,7 +934,12 @@ static struct sk_buff *macsec_decrypt(struct sk_buff *skb,
 	if (!skb)
 		return ERR_PTR(-ENOMEM);
 
-	req = macsec_alloc_req(rx_sa->key.tfm, &iv, &sg);
+	ret = skb_cow_data(skb, 0, &trailer);
+	if (unlikely(ret < 0)) {
+		kfree_skb(skb);
+		return ERR_PTR(ret);
+	}
+	req = macsec_alloc_req(rx_sa->key.tfm, &iv, &sg, ret);
 	if (!req) {
 		kfree_skb(skb);
 		return ERR_PTR(-ENOMEM);
@@ -933,7 +948,7 @@ static struct sk_buff *macsec_decrypt(struct sk_buff *skb,
 	hdr = (struct macsec_eth_header *)skb->data;
 	macsec_fill_iv(iv, sci, ntohl(hdr->packet_number));
 
-	sg_init_table(sg, MAX_SKB_FRAGS + 1);
+	sg_init_table(sg, ret);
 	skb_to_sgvec(skb, sg, 0, skb->len);
 
 	if (hdr->tci_an & MACSEC_TCI_E) {
@@ -2713,7 +2728,7 @@ static netdev_tx_t macsec_start_xmit(struct sk_buff *skb,
 }
 
 #define MACSEC_FEATURES \
-	(NETIF_F_SG | NETIF_F_HIGHDMA)
+	(NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST)
 static struct lock_class_key macsec_netdev_addr_lock_key;
 
 static int macsec_dev_init(struct net_device *dev)
-- 
2.7.4


From 73292f38a5b4f64603c00530795e42de67ea1983 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 26 Apr 2017 17:15:40 -0700
Subject: [PATCH 02/19] tcp: do not underestimate skb->truesize in
 tcp_trim_head()

[ Upstream commit 7162fb242cb8322beb558828fd26b33c3e9fc805 ]

Andrey found a way to trigger the WARN_ON_ONCE(delta < len) in
skb_try_coalesce() using syzkaller and a filter attached to a TCP
socket over loopback interface.

I believe one issue with looped skbs is that tcp_trim_head() can end up
producing skb with under estimated truesize.

It hardly matters for normal conditions, since packets sent over
loopback are never truncated.

Bytes trimmed from skb->head should not change skb truesize, since
skb->head is not reallocated.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 8ce50dc3..b7236ad 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1257,7 +1257,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
  * eventually). The difference is that pulled data not copied, but
  * immediately discarded.
  */
-static void __pskb_trim_head(struct sk_buff *skb, int len)
+static int __pskb_trim_head(struct sk_buff *skb, int len)
 {
 	struct skb_shared_info *shinfo;
 	int i, k, eat;
@@ -1267,7 +1267,7 @@ static void __pskb_trim_head(struct sk_buff *skb, int len)
 		__skb_pull(skb, eat);
 		len -= eat;
 		if (!len)
-			return;
+			return 0;
 	}
 	eat = len;
 	k = 0;
@@ -1293,23 +1293,28 @@ static void __pskb_trim_head(struct sk_buff *skb, int len)
 	skb_reset_tail_pointer(skb);
 	skb->data_len -= len;
 	skb->len = skb->data_len;
+	return len;
 }
 
 /* Remove acked data from a packet in the transmit queue. */
 int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
 {
+	u32 delta_truesize;
+
 	if (skb_unclone(skb, GFP_ATOMIC))
 		return -ENOMEM;
 
-	__pskb_trim_head(skb, len);
+	delta_truesize = __pskb_trim_head(skb, len);
 
 	TCP_SKB_CB(skb)->seq += len;
 	skb->ip_summed = CHECKSUM_PARTIAL;
 
-	skb->truesize	     -= len;
-	sk->sk_wmem_queued   -= len;
-	sk_mem_uncharge(sk, len);
-	sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
+	if (delta_truesize) {
+		skb->truesize	   -= delta_truesize;
+		sk->sk_wmem_queued -= delta_truesize;
+		sk_mem_uncharge(sk, delta_truesize);
+		sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
+	}
 
 	/* Any change of skb->len requires recalculation of tso factor. */
 	if (tcp_skb_pcount(skb) > 1)
-- 
2.7.4


From bbe6dedfdce03e46af8406b92ea8d1c8357fc7c8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 26 Apr 2017 09:07:46 -0700
Subject: [PATCH 03/19] net: adjust skb->truesize in ___pskb_trim()

[ Upstream commit c21b48cc1bbf2f5af3ef54ada559f7fadf8b508b ]

Andrey found a way to trigger the WARN_ON_ONCE(delta < len) in
skb_try_coalesce() using syzkaller and a filter attached to a TCP
socket.

As we did recently in commit 158f323b9868 ("net: adjust skb->truesize in
pskb_expand_head()") we can adjust skb->truesize from ___pskb_trim(),
via a call to skb_condense().

If all frags were freed, then skb->truesize can be recomputed.

This call can be done if skb is not yet owned, or destructor is
sock_edemux().

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 887995e..7d6369b 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1572,6 +1572,8 @@ int ___pskb_trim(struct sk_buff *skb, unsigned int len)
 		skb_set_tail_pointer(skb, len);
 	}
 
+	if (!skb->sk || skb->destructor == sock_edemux)
+		skb_condense(skb);
 	return 0;
 }
 EXPORT_SYMBOL(___pskb_trim);
-- 
2.7.4


From cfcd0e7d35a0461869ec03b434ab96e88314d189 Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@free-electrons.com>
Date: Wed, 26 Apr 2017 12:06:28 +0200
Subject: [PATCH 04/19] net: macb: fix phy interrupt parsing

[ Upstream commit ae3696c167cc04d32634c4af82f43b446c5176b0 ]

Since 83a77e9ec415, the phydev irq is explicitly set to PHY_POLL when
there is no pdata. It doesn't work on DT enabled platforms because the
phydev irq is already set by libphy before.

Fixes: 83a77e9ec415 ("net: macb: Added PCI wrapper for Platform Driver.")
Signed-off-by: Alexandre Belloni <alexandre.belloni@free-electrons.com>
Acked-by: Nicolas Ferre <nicolas.ferre@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index baba2db..0b92b88 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -432,15 +432,17 @@ static int macb_mii_probe(struct net_device *dev)
 	}
 
 	pdata = dev_get_platdata(&bp->pdev->dev);
-	if (pdata && gpio_is_valid(pdata->phy_irq_pin)) {
-		ret = devm_gpio_request(&bp->pdev->dev, pdata->phy_irq_pin,
-					"phy int");
-		if (!ret) {
-			phy_irq = gpio_to_irq(pdata->phy_irq_pin);
-			phydev->irq = (phy_irq < 0) ? PHY_POLL : phy_irq;
+	if (pdata) {
+		if (gpio_is_valid(pdata->phy_irq_pin)) {
+			ret = devm_gpio_request(&bp->pdev->dev,
+						pdata->phy_irq_pin, "phy int");
+			if (!ret) {
+				phy_irq = gpio_to_irq(pdata->phy_irq_pin);
+				phydev->irq = (phy_irq < 0) ? PHY_POLL : phy_irq;
+			}
+		} else {
+			phydev->irq = PHY_POLL;
 		}
-	} else {
-		phydev->irq = PHY_POLL;
 	}
 
 	/* attach the mac to the phy */
-- 
2.7.4


From 69547292a2af7927b0db0eb65a72131adb5ac2fc Mon Sep 17 00:00:00 2001
From: Girish Moodalbail <girish.moodalbail@oracle.com>
Date: Thu, 27 Apr 2017 14:11:53 -0700
Subject: [PATCH 05/19] geneve: fix incorrect setting of UDP checksum flag

[ Upstream commit 5e0740c445e6ae4026f5e52456ff8d0be9725183 ]

Creating a geneve link with 'udpcsum' set results in a creation of link
for which UDP checksum will NOT be computed on outbound packets, as can
be seen below.

11: gen0: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN
    link/ether c2:85:27:b6:b4:15 brd ff:ff:ff:ff:ff:ff promiscuity 0
    geneve id 200 remote 192.168.13.1 dstport 6081 noudpcsum

Similarly, creating a link with 'noudpcsum' set results in a creation
of link for which UDP checksum will be computed on outbound packets.

Fixes: 9b4437a5b870 ("geneve: Unify LWT and netdev handling.")
Signed-off-by: Girish Moodalbail <girish.moodalbail@oracle.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Acked-by: Lance Richardson <lrichard@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 7074b40..dec5d56 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1244,7 +1244,7 @@ static int geneve_newlink(struct net *net, struct net_device *dev,
 		metadata = true;
 
 	if (data[IFLA_GENEVE_UDP_CSUM] &&
-	    !nla_get_u8(data[IFLA_GENEVE_UDP_CSUM]))
+	    nla_get_u8(data[IFLA_GENEVE_UDP_CSUM]))
 		info.key.tun_flags |= TUNNEL_CSUM;
 
 	if (data[IFLA_GENEVE_UDP_ZERO_CSUM6_TX] &&
-- 
2.7.4


From f12bc954c085ee2fc7c60380b9e5b9b88585b014 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Sat, 29 Apr 2017 22:52:42 -0700
Subject: [PATCH 06/19] bpf: enhance verifier to understand stack pointer
 arithmetic

[ Upstream commit 332270fdc8b6fba07d059a9ad44df9e1a2ad4529 ]

llvm 4.0 and above generates the code like below:
....
440: (b7) r1 = 15
441: (05) goto pc+73
515: (79) r6 = *(u64 *)(r10 -152)
516: (bf) r7 = r10
517: (07) r7 += -112
518: (bf) r2 = r7
519: (0f) r2 += r1
520: (71) r1 = *(u8 *)(r8 +0)
521: (73) *(u8 *)(r2 +45) = r1
....
and the verifier complains "R2 invalid mem access 'inv'" for insn #521.
This is because verifier marks register r2 as unknown value after #519
where r2 is a stack pointer and r1 holds a constant value.

Teach verifier to recognize "stack_ptr + imm" and
"stack_ptr + reg with const val" as valid stack_ptr with new offset.

Signed-off-by: Yonghong Song <yhs@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c                       | 11 +++++++++++
 tools/testing/selftests/bpf/test_verifier.c | 18 ++++++++++++------
 2 files changed, 23 insertions(+), 6 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index f3c938b..ce16f80 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1779,6 +1779,17 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 			return 0;
 		} else if (opcode == BPF_ADD &&
 			   BPF_CLASS(insn->code) == BPF_ALU64 &&
+			   dst_reg->type == PTR_TO_STACK &&
+			   ((BPF_SRC(insn->code) == BPF_X &&
+			     regs[insn->src_reg].type == CONST_IMM) ||
+			    BPF_SRC(insn->code) == BPF_K)) {
+			if (BPF_SRC(insn->code) == BPF_X)
+				dst_reg->imm += regs[insn->src_reg].imm;
+			else
+				dst_reg->imm += insn->imm;
+			return 0;
+		} else if (opcode == BPF_ADD &&
+			   BPF_CLASS(insn->code) == BPF_ALU64 &&
 			   (dst_reg->type == PTR_TO_PACKET ||
 			    (BPF_SRC(insn->code) == BPF_X &&
 			     regs[insn->src_reg].type == PTR_TO_PACKET))) {
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index e1aea9e..35e9f50 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -1357,16 +1357,22 @@ static struct bpf_test tests[] = {
 		.result = ACCEPT,
 	},
 	{
-		"unpriv: obfuscate stack pointer",
+		"stack pointer arithmetic",
 		.insns = {
-			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_MOV64_IMM(BPF_REG_1, 4),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 0),
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -10),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_1),
+			BPF_ST_MEM(0, BPF_REG_2, 4, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 8),
+			BPF_ST_MEM(0, BPF_REG_2, 4, 0),
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.errstr_unpriv = "R2 pointer arithmetic",
-		.result_unpriv = REJECT,
 		.result = ACCEPT,
 	},
 	{
-- 
2.7.4


From e58f3358a7bbf405a2ff785b64f8bac096697bc1 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Tue, 2 May 2017 20:34:54 +0200
Subject: [PATCH 07/19] bpf, arm64: fix jit branch offset related to ldimm64

[ Upstream commit ddc665a4bb4b728b4e6ecec8db1b64efa9184b9c ]

When the instruction right before the branch destination is
a 64 bit load immediate, we currently calculate the wrong
jump offset in the ctx->offset[] array as we only account
one instruction slot for the 64 bit load immediate although
it uses two BPF instructions. Fix it up by setting the offset
into the right slot after we incremented the index.

Before (ldimm64 test 1):

  [...]
  00000020:  52800007  mov w7, #0x0 // #0
  00000024:  d2800060  mov x0, #0x3 // #3
  00000028:  d2800041  mov x1, #0x2 // #2
  0000002c:  eb01001f  cmp x0, x1
  00000030:  54ffff82  b.cs 0x00000020
  00000034:  d29fffe7  mov x7, #0xffff // #65535
  00000038:  f2bfffe7  movk x7, #0xffff, lsl #16
  0000003c:  f2dfffe7  movk x7, #0xffff, lsl #32
  00000040:  f2ffffe7  movk x7, #0xffff, lsl #48
  00000044:  d29dddc7  mov x7, #0xeeee // #61166
  00000048:  f2bdddc7  movk x7, #0xeeee, lsl #16
  0000004c:  f2ddddc7  movk x7, #0xeeee, lsl #32
  00000050:  f2fdddc7  movk x7, #0xeeee, lsl #48
  [...]

After (ldimm64 test 1):

  [...]
  00000020:  52800007  mov w7, #0x0 // #0
  00000024:  d2800060  mov x0, #0x3 // #3
  00000028:  d2800041  mov x1, #0x2 // #2
  0000002c:  eb01001f  cmp x0, x1
  00000030:  540000a2  b.cs 0x00000044
  00000034:  d29fffe7  mov x7, #0xffff // #65535
  00000038:  f2bfffe7  movk x7, #0xffff, lsl #16
  0000003c:  f2dfffe7  movk x7, #0xffff, lsl #32
  00000040:  f2ffffe7  movk x7, #0xffff, lsl #48
  00000044:  d29dddc7  mov x7, #0xeeee // #61166
  00000048:  f2bdddc7  movk x7, #0xeeee, lsl #16
  0000004c:  f2ddddc7  movk x7, #0xeeee, lsl #32
  00000050:  f2fdddc7  movk x7, #0xeeee, lsl #48
  [...]

Also, add a couple of test cases to make sure JITs pass
this test. Tested on Cavium ThunderX ARMv8. The added
test cases all pass after the fix.

Fixes: 8eee539ddea0 ("arm64: bpf: fix out-of-bounds read in bpf2a64_offset()")
Reported-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Cc: Xi Wang <xi.wang@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/arm64/net/bpf_jit_comp.c |  8 ++++----
 lib/test_bpf.c                | 45 +++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 49 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index b2fc97a..9c4b57a 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -779,14 +779,14 @@ static int build_body(struct jit_ctx *ctx)
 		int ret;
 
 		ret = build_insn(insn, ctx);
-
-		if (ctx->image == NULL)
-			ctx->offset[i] = ctx->idx;
-
 		if (ret > 0) {
 			i++;
+			if (ctx->image == NULL)
+				ctx->offset[i] = ctx->idx;
 			continue;
 		}
+		if (ctx->image == NULL)
+			ctx->offset[i] = ctx->idx;
 		if (ret)
 			return ret;
 	}
diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index 0362da0..2e38502 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -4656,6 +4656,51 @@ static struct bpf_test tests[] = {
 		{ },
 		{ { 0, 1 } },
 	},
+	{
+		/* Mainly testing JIT + imm64 here. */
+		"JMP_JGE_X: ldimm64 test 1",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_LD_IMM64(R1, 3),
+			BPF_LD_IMM64(R2, 2),
+			BPF_JMP_REG(BPF_JGE, R1, R2, 2),
+			BPF_LD_IMM64(R0, 0xffffffffffffffffUL),
+			BPF_LD_IMM64(R0, 0xeeeeeeeeeeeeeeeeUL),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xeeeeeeeeU } },
+	},
+	{
+		"JMP_JGE_X: ldimm64 test 2",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_LD_IMM64(R1, 3),
+			BPF_LD_IMM64(R2, 2),
+			BPF_JMP_REG(BPF_JGE, R1, R2, 0),
+			BPF_LD_IMM64(R0, 0xffffffffffffffffUL),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xffffffffU } },
+	},
+	{
+		"JMP_JGE_X: ldimm64 test 3",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_LD_IMM64(R1, 3),
+			BPF_LD_IMM64(R2, 2),
+			BPF_JMP_REG(BPF_JGE, R1, R2, 4),
+			BPF_LD_IMM64(R0, 0xffffffffffffffffUL),
+			BPF_LD_IMM64(R0, 0xeeeeeeeeeeeeeeeeUL),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
 	/* BPF_JMP | BPF_JNE | BPF_X */
 	{
 		"JMP_JNE_X: if (3 != 2) return 1",
-- 
2.7.4


From 31060ffbaf29abcf878f95a8378277f0cac28dff Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 1 May 2017 15:29:48 -0700
Subject: [PATCH 08/19] tcp: fix wraparound issue in tcp_lp

[ Upstream commit a9f11f963a546fea9144f6a6d1a307e814a387e7 ]

Be careful when comparing tcp_time_stamp to some u32 quantity,
otherwise result can be surprising.

Fixes: 7c106d7e782b ("[TCP]: TCP Low Priority congestion control")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_lp.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c
index 046fd39..d6fb6c0 100644
--- a/net/ipv4/tcp_lp.c
+++ b/net/ipv4/tcp_lp.c
@@ -264,13 +264,15 @@ static void tcp_lp_pkts_acked(struct sock *sk, const struct ack_sample *sample)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct lp *lp = inet_csk_ca(sk);
+	u32 delta;
 
 	if (sample->rtt_us > 0)
 		tcp_lp_rtt_sample(sk, sample->rtt_us);
 
 	/* calc inference */
-	if (tcp_time_stamp > tp->rx_opt.rcv_tsecr)
-		lp->inference = 3 * (tcp_time_stamp - tp->rx_opt.rcv_tsecr);
+	delta = tcp_time_stamp - tp->rx_opt.rcv_tsecr;
+	if ((s32)delta > 0)
+		lp->inference = 3 * delta;
 
 	/* test if within inference */
 	if (lp->last_drop && (tcp_time_stamp - lp->last_drop < lp->inference))
-- 
2.7.4


From 24bb2b390142353c9fc3662a579a14d5ff3c80e9 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 2 May 2017 14:43:44 -0700
Subject: [PATCH 09/19] net: ipv6: Do not duplicate DAD on link up

[ Upstream commit 6d717134a1a6e1b34a7d0d70e953037bc2642046 ]

Andrey reported a warning triggered by the rcu code:

------------[ cut here ]------------
WARNING: CPU: 1 PID: 5911 at lib/debugobjects.c:289
debug_print_object+0x175/0x210
ODEBUG: activate active (active state 1) object type: rcu_head hint:
        (null)
Modules linked in:
CPU: 1 PID: 5911 Comm: a.out Not tainted 4.11.0-rc8+ #271
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:16
 dump_stack+0x192/0x22d lib/dump_stack.c:52
 __warn+0x19f/0x1e0 kernel/panic.c:549
 warn_slowpath_fmt+0xe0/0x120 kernel/panic.c:564
 debug_print_object+0x175/0x210 lib/debugobjects.c:286
 debug_object_activate+0x574/0x7e0 lib/debugobjects.c:442
 debug_rcu_head_queue kernel/rcu/rcu.h:75
 __call_rcu.constprop.76+0xff/0x9c0 kernel/rcu/tree.c:3229
 call_rcu_sched+0x12/0x20 kernel/rcu/tree.c:3288
 rt6_rcu_free net/ipv6/ip6_fib.c:158
 rt6_release+0x1ea/0x290 net/ipv6/ip6_fib.c:188
 fib6_del_route net/ipv6/ip6_fib.c:1461
 fib6_del+0xa42/0xdc0 net/ipv6/ip6_fib.c:1500
 __ip6_del_rt+0x100/0x160 net/ipv6/route.c:2174
 ip6_del_rt+0x140/0x1b0 net/ipv6/route.c:2187
 __ipv6_ifa_notify+0x269/0x780 net/ipv6/addrconf.c:5520
 addrconf_ifdown+0xe60/0x1a20 net/ipv6/addrconf.c:3672
...

Andrey's reproducer program runs in a very tight loop, calling
'unshare -n' and then spawning 2 sets of 14 threads running random ioctl
calls. The relevant networking sequence:

1. New network namespace created via unshare -n
- ip6tnl0 device is created in down state

2. address added to ip6tnl0
- equivalent to ip -6 addr add dev ip6tnl0 fd00::bb/1
- DAD is started on the address and when it completes the host
  route is inserted into the FIB

3. ip6tnl0 is brought up
- the new fixup_permanent_addr function restarts DAD on the address

4. exit namespace
- teardown / cleanup sequence starts
- once in a blue moon, lo teardown appears to happen BEFORE teardown
  of ip6tunl0
  + down on 'lo' removes the host route from the FIB since the dst->dev
    for the route is loobback
  + host route added to rcu callback list
    * rcu callback has not run yet, so rt is NOT on the gc list so it has
      NOT been marked obsolete

5. in parallel to 4. worker_thread runs addrconf_dad_completed
- DAD on the address on ip6tnl0 completes
- calls ipv6_ifa_notify which inserts the host route

All of that happens very quickly. The result is that a host route that
has been deleted from the IPv6 FIB and added to the RCU list is re-inserted
into the FIB.

The exit namespace eventually gets to cleaning up ip6tnl0 which removes the
host route from the FIB again, calls the rcu function for cleanup -- and
triggers the double rcu trace.

The root cause is duplicate DAD on the address -- steps 2 and 3. Arguably,
DAD should not be started in step 2. The interface is in the down state,
so it can not really send out requests for the address which makes starting
DAD pointless.

Since the second DAD was introduced by a recent change, seems appropriate
to use it for the Fixes tag and have the fixup function only start DAD for
addresses in the PREDAD state which occurs in addrconf_ifdown if the
address is retained.

Big thanks to Andrey for isolating a reliable reproducer for this problem.
Fixes: f1705ec197e7 ("net: ipv6: Make address flushing on ifdown optional")
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index ec76bbe..f10ecd9 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3288,7 +3288,8 @@ static int fixup_permanent_addr(struct inet6_dev *idev,
 				      idev->dev, 0, 0);
 	}
 
-	addrconf_dad_start(ifp);
+	if (ifp->state == INET6_IFADDR_STATE_PREDAD)
+		addrconf_dad_start(ifp);
 
 	return 0;
 }
@@ -3643,7 +3644,7 @@ static int addrconf_ifdown(struct net_device *dev, int how)
 		if (keep) {
 			/* set state to skip the notifier below */
 			state = INET6_IFADDR_STATE_DEAD;
-			ifa->state = 0;
+			ifa->state = INET6_IFADDR_STATE_PREDAD;
 			if (!(ifa->flags & IFA_F_NODAD))
 				ifa->flags |= IFA_F_TENTATIVE;
 
-- 
2.7.4


From 263e90b6c8a40881976fb20c21149a811b8a80fc Mon Sep 17 00:00:00 2001
From: Daniele Palmas <dnlplm@gmail.com>
Date: Wed, 3 May 2017 10:30:11 +0200
Subject: [PATCH 10/19] net: usb: qmi_wwan: add Telit ME910 support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 4c54dc0277d0d55a9248c43aebd31858f926a056 ]

This patch adds support for Telit ME910 PID 0x1100.

Signed-off-by: Daniele Palmas <dnlplm@gmail.com>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 0d519a9..34d997c 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -902,6 +902,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x2357, 0x0201, 4)},	/* TP-LINK HSUPA Modem MA180 */
 	{QMI_FIXED_INTF(0x2357, 0x9000, 4)},	/* TP-LINK MA260 */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1040, 2)},	/* Telit LE922A */
+	{QMI_FIXED_INTF(0x1bc7, 0x1100, 3)},	/* Telit ME910 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)},	/* Telit LE920 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1201, 2)},	/* Telit LE920 */
 	{QMI_FIXED_INTF(0x1c9e, 0x9b01, 3)},	/* XS Stick W100-2 from 4G Systems */
-- 
2.7.4


From 7236e625e072c367bd9e291ce34ffdc141787ce0 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 3 May 2017 06:39:31 -0700
Subject: [PATCH 11/19] tcp: do not inherit fastopen_req from parent

[ Upstream commit 8b485ce69876c65db12ed390e7f9c0d2a64eff2c ]

Under fuzzer stress, it is possible that a child gets a non NULL
fastopen_req pointer from its parent at accept() time, when/if parent
morphs from listener to active session.

We need to make sure this can not happen, by clearing the field after
socket cloning.

BUG: Double free or freeing an invalid pointer
Unexpected shadow byte: 0xFB
CPU: 3 PID: 20933 Comm: syz-executor3 Not tainted 4.11.0+ #306
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs
01/01/2011
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:16 [inline]
 dump_stack+0x292/0x395 lib/dump_stack.c:52
 kasan_object_err+0x1c/0x70 mm/kasan/report.c:164
 kasan_report_double_free+0x5c/0x70 mm/kasan/report.c:185
 kasan_slab_free+0x9d/0xc0 mm/kasan/kasan.c:580
 slab_free_hook mm/slub.c:1357 [inline]
 slab_free_freelist_hook mm/slub.c:1379 [inline]
 slab_free mm/slub.c:2961 [inline]
 kfree+0xe8/0x2b0 mm/slub.c:3882
 tcp_free_fastopen_req net/ipv4/tcp.c:1077 [inline]
 tcp_disconnect+0xc15/0x13e0 net/ipv4/tcp.c:2328
 inet_child_forget+0xb8/0x600 net/ipv4/inet_connection_sock.c:898
 inet_csk_reqsk_queue_add+0x1e7/0x250
net/ipv4/inet_connection_sock.c:928
 tcp_get_cookie_sock+0x21a/0x510 net/ipv4/syncookies.c:217
 cookie_v4_check+0x1a19/0x28b0 net/ipv4/syncookies.c:384
 tcp_v4_cookie_check net/ipv4/tcp_ipv4.c:1384 [inline]
 tcp_v4_do_rcv+0x731/0x940 net/ipv4/tcp_ipv4.c:1421
 tcp_v4_rcv+0x2dc0/0x31c0 net/ipv4/tcp_ipv4.c:1715
 ip_local_deliver_finish+0x4cc/0xc20 net/ipv4/ip_input.c:216
 NF_HOOK include/linux/netfilter.h:257 [inline]
 ip_local_deliver+0x1ce/0x700 net/ipv4/ip_input.c:257
 dst_input include/net/dst.h:492 [inline]
 ip_rcv_finish+0xb1d/0x20b0 net/ipv4/ip_input.c:396
 NF_HOOK include/linux/netfilter.h:257 [inline]
 ip_rcv+0xd8c/0x19c0 net/ipv4/ip_input.c:487
 __netif_receive_skb_core+0x1ad1/0x3400 net/core/dev.c:4210
 __netif_receive_skb+0x2a/0x1a0 net/core/dev.c:4248
 process_backlog+0xe5/0x6c0 net/core/dev.c:4868
 napi_poll net/core/dev.c:5270 [inline]
 net_rx_action+0xe70/0x18e0 net/core/dev.c:5335
 __do_softirq+0x2fb/0xb99 kernel/softirq.c:284
 do_softirq_own_stack+0x1c/0x30 arch/x86/entry/entry_64.S:899
 </IRQ>
 do_softirq.part.17+0x1e8/0x230 kernel/softirq.c:328
 do_softirq kernel/softirq.c:176 [inline]
 __local_bh_enable_ip+0x1cf/0x1e0 kernel/softirq.c:181
 local_bh_enable include/linux/bottom_half.h:31 [inline]
 rcu_read_unlock_bh include/linux/rcupdate.h:931 [inline]
 ip_finish_output2+0x9ab/0x15e0 net/ipv4/ip_output.c:230
 ip_finish_output+0xa35/0xdf0 net/ipv4/ip_output.c:316
 NF_HOOK_COND include/linux/netfilter.h:246 [inline]
 ip_output+0x1f6/0x7b0 net/ipv4/ip_output.c:404
 dst_output include/net/dst.h:486 [inline]
 ip_local_out+0x95/0x160 net/ipv4/ip_output.c:124
 ip_queue_xmit+0x9a8/0x1a10 net/ipv4/ip_output.c:503
 tcp_transmit_skb+0x1ade/0x3470 net/ipv4/tcp_output.c:1057
 tcp_write_xmit+0x79e/0x55b0 net/ipv4/tcp_output.c:2265
 __tcp_push_pending_frames+0xfa/0x3a0 net/ipv4/tcp_output.c:2450
 tcp_push+0x4ee/0x780 net/ipv4/tcp.c:683
 tcp_sendmsg+0x128d/0x39b0 net/ipv4/tcp.c:1342
 inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:762
 sock_sendmsg_nosec net/socket.c:633 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:643
 SYSC_sendto+0x660/0x810 net/socket.c:1696
 SyS_sendto+0x40/0x50 net/socket.c:1664
 entry_SYSCALL_64_fastpath+0x1f/0xbe
RIP: 0033:0x446059
RSP: 002b:00007faa6761fb58 EFLAGS: 00000282 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 0000000000000017 RCX: 0000000000446059
RDX: 0000000000000001 RSI: 0000000020ba3fcd RDI: 0000000000000017
RBP: 00000000006e40a0 R08: 0000000020ba4ff0 R09: 0000000000000010
R10: 0000000020000000 R11: 0000000000000282 R12: 0000000000708150
R13: 0000000000000000 R14: 00007faa676209c0 R15: 00007faa67620700
Object at ffff88003b5bbcb8, in cache kmalloc-64 size: 64
Allocated:
PID = 20909
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
 save_stack+0x43/0xd0 mm/kasan/kasan.c:513
 set_track mm/kasan/kasan.c:525 [inline]
 kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:616
 kmem_cache_alloc_trace+0x82/0x270 mm/slub.c:2745
 kmalloc include/linux/slab.h:490 [inline]
 kzalloc include/linux/slab.h:663 [inline]
 tcp_sendmsg_fastopen net/ipv4/tcp.c:1094 [inline]
 tcp_sendmsg+0x221a/0x39b0 net/ipv4/tcp.c:1139
 inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:762
 sock_sendmsg_nosec net/socket.c:633 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:643
 SYSC_sendto+0x660/0x810 net/socket.c:1696
 SyS_sendto+0x40/0x50 net/socket.c:1664
 entry_SYSCALL_64_fastpath+0x1f/0xbe
Freed:
PID = 20909
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
 save_stack+0x43/0xd0 mm/kasan/kasan.c:513
 set_track mm/kasan/kasan.c:525 [inline]
 kasan_slab_free+0x73/0xc0 mm/kasan/kasan.c:589
 slab_free_hook mm/slub.c:1357 [inline]
 slab_free_freelist_hook mm/slub.c:1379 [inline]
 slab_free mm/slub.c:2961 [inline]
 kfree+0xe8/0x2b0 mm/slub.c:3882
 tcp_free_fastopen_req net/ipv4/tcp.c:1077 [inline]
 tcp_disconnect+0xc15/0x13e0 net/ipv4/tcp.c:2328
 __inet_stream_connect+0x20c/0xf90 net/ipv4/af_inet.c:593
 tcp_sendmsg_fastopen net/ipv4/tcp.c:1111 [inline]
 tcp_sendmsg+0x23a8/0x39b0 net/ipv4/tcp.c:1139
 inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:762
 sock_sendmsg_nosec net/socket.c:633 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:643
 SYSC_sendto+0x660/0x810 net/socket.c:1696
 SyS_sendto+0x40/0x50 net/socket.c:1664
 entry_SYSCALL_64_fastpath+0x1f/0xbe

Fixes: e994b2f0fb92 ("tcp: do not lock listener to process SYN packets")
Fixes: 7db92362d2fe ("tcp: fix potential double free issue for fastopen_req")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Acked-by: Wei Wang <weiwan@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_minisocks.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 80ff517..64bea51 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -543,6 +543,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 			newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len;
 		newtp->rx_opt.mss_clamp = req->mss;
 		tcp_ecn_openreq_child(newtp, req);
+		newtp->fastopen_req = NULL;
 		newtp->fastopen_rsk = NULL;
 		newtp->syn_data_acked = 0;
 		newtp->rack.mstamp.v64 = 0;
-- 
2.7.4


From 10ffb856d4d45969283f1fd45ad8cb584e8f205b Mon Sep 17 00:00:00 2001
From: Alexander Potapenko <glider@google.com>
Date: Wed, 3 May 2017 17:06:58 +0200
Subject: [PATCH 12/19] ipv4, ipv6: ensure raw socket message is big enough to
 hold an IP header

[ Upstream commit 86f4c90a1c5c1493f07f2d12c1079f5bf01936f2 ]

raw_send_hdrinc() and rawv6_send_hdrinc() expect that the buffer copied
from the userspace contains the IPv4/IPv6 header, so if too few bytes are
copied, parts of the header may remain uninitialized.

This bug has been detected with KMSAN.

For the record, the KMSAN report:

==================================================================
BUG: KMSAN: use of unitialized memory in nf_ct_frag6_gather+0xf5a/0x44a0
inter: 0
CPU: 0 PID: 1036 Comm: probe Not tainted 4.11.0-rc5+ #2455
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:16
 dump_stack+0x143/0x1b0 lib/dump_stack.c:52
 kmsan_report+0x16b/0x1e0 mm/kmsan/kmsan.c:1078
 __kmsan_warning_32+0x5c/0xa0 mm/kmsan/kmsan_instr.c:510
 nf_ct_frag6_gather+0xf5a/0x44a0 net/ipv6/netfilter/nf_conntrack_reasm.c:577
 ipv6_defrag+0x1d9/0x280 net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:68
 nf_hook_entry_hookfn ./include/linux/netfilter.h:102
 nf_hook_slow+0x13f/0x3c0 net/netfilter/core.c:310
 nf_hook ./include/linux/netfilter.h:212
 NF_HOOK ./include/linux/netfilter.h:255
 rawv6_send_hdrinc net/ipv6/raw.c:673
 rawv6_sendmsg+0x2fcb/0x41a0 net/ipv6/raw.c:919
 inet_sendmsg+0x3f8/0x6d0 net/ipv4/af_inet.c:762
 sock_sendmsg_nosec net/socket.c:633
 sock_sendmsg net/socket.c:643
 SYSC_sendto+0x6a5/0x7c0 net/socket.c:1696
 SyS_sendto+0xbc/0xe0 net/socket.c:1664
 do_syscall_64+0x72/0xa0 arch/x86/entry/common.c:285
 entry_SYSCALL64_slow_path+0x25/0x25 arch/x86/entry/entry_64.S:246
RIP: 0033:0x436e03
RSP: 002b:00007ffce48baf38 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 00000000004002b0 RCX: 0000000000436e03
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000003
RBP: 00007ffce48baf90 R08: 00007ffce48baf50 R09: 000000000000001c
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 0000000000401790 R14: 0000000000401820 R15: 0000000000000000
origin: 00000000d9400053
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:362
 kmsan_internal_poison_shadow+0xb1/0x1a0 mm/kmsan/kmsan.c:257
 kmsan_poison_shadow+0x6d/0xc0 mm/kmsan/kmsan.c:270
 slab_alloc_node mm/slub.c:2735
 __kmalloc_node_track_caller+0x1f4/0x390 mm/slub.c:4341
 __kmalloc_reserve net/core/skbuff.c:138
 __alloc_skb+0x2cd/0x740 net/core/skbuff.c:231
 alloc_skb ./include/linux/skbuff.h:933
 alloc_skb_with_frags+0x209/0xbc0 net/core/skbuff.c:4678
 sock_alloc_send_pskb+0x9ff/0xe00 net/core/sock.c:1903
 sock_alloc_send_skb+0xe4/0x100 net/core/sock.c:1920
 rawv6_send_hdrinc net/ipv6/raw.c:638
 rawv6_sendmsg+0x2918/0x41a0 net/ipv6/raw.c:919
 inet_sendmsg+0x3f8/0x6d0 net/ipv4/af_inet.c:762
 sock_sendmsg_nosec net/socket.c:633
 sock_sendmsg net/socket.c:643
 SYSC_sendto+0x6a5/0x7c0 net/socket.c:1696
 SyS_sendto+0xbc/0xe0 net/socket.c:1664
 do_syscall_64+0x72/0xa0 arch/x86/entry/common.c:285
 return_from_SYSCALL_64+0x0/0x6a arch/x86/entry/entry_64.S:246
==================================================================

, triggered by the following syscalls:
  socket(PF_INET6, SOCK_RAW, IPPROTO_RAW) = 3
  sendto(3, NULL, 0, 0, {sa_family=AF_INET6, sin6_port=htons(0), inet_pton(AF_INET6, "ff00::", &sin6_addr), sin6_flowinfo=0, sin6_scope_id=0}, 28) = -1 EPERM

A similar report is triggered in net/ipv4/raw.c if we use a PF_INET socket
instead of a PF_INET6 one.

Signed-off-by: Alexander Potapenko <glider@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/raw.c | 3 +++
 net/ipv6/raw.c | 2 ++
 2 files changed, 5 insertions(+)

diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 4e49e5c..259fbcd 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -358,6 +358,9 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
 			       rt->dst.dev->mtu);
 		return -EMSGSIZE;
 	}
+	if (length < sizeof(struct iphdr))
+		return -EINVAL;
+
 	if (flags&MSG_PROBE)
 		goto out;
 
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 294fb6f..6006b32 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -632,6 +632,8 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length,
 		ipv6_local_error(sk, EMSGSIZE, fl6, rt->dst.dev->mtu);
 		return -EMSGSIZE;
 	}
+	if (length < sizeof(struct ipv6hdr))
+		return -EINVAL;
 	if (flags&MSG_PROBE)
 		goto out;
 
-- 
2.7.4


From ad8da32f8286849019ce1bacfd9f91bbb16efaa5 Mon Sep 17 00:00:00 2001
From: Michal Schmidt <mschmidt@redhat.com>
Date: Thu, 4 May 2017 16:48:58 +0200
Subject: [PATCH 13/19] rtnetlink: NUL-terminate IFLA_PHYS_PORT_NAME string

[ Upstream commit 77ef033b687c3e030017c94a29bf6ea3aaaef678 ]

IFLA_PHYS_PORT_NAME is a string attribute, so terminate it with \0.
Otherwise libnl3 fails to validate netlink messages with this attribute.
"ip -detail a" assumes too that the attribute is NUL-terminated when
printing it. It often was, due to padding.

I noticed this as libvirtd failing to start on a system with sfc driver
after upgrading it to Linux 4.11, i.e. when sfc added support for
phys_port_name.

Signed-off-by: Michal Schmidt <mschmidt@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 75e3ea7..d64d8d1 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1059,7 +1059,7 @@ static int rtnl_phys_port_name_fill(struct sk_buff *skb, struct net_device *dev)
 		return err;
 	}
 
-	if (nla_put(skb, IFLA_PHYS_PORT_NAME, strlen(name), name))
+	if (nla_put_string(skb, IFLA_PHYS_PORT_NAME, name))
 		return -EMSGSIZE;
 
 	return 0;
-- 
2.7.4


From 2828fadb537d3d3bd94e11ae3043bf1548eb66df Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Wed, 3 May 2017 22:07:31 -0700
Subject: [PATCH 14/19] ipv6: initialize route null entry in addrconf_init()

[ Upstream commit 2f460933f58eee3393aba64f0f6d14acb08d1724 ]

Andrey reported a crash on init_net.ipv6.ip6_null_entry->rt6i_idev
since it is always NULL.

This is clearly wrong, we have code to initialize it to loopback_dev,
unfortunately the order is still not correct.

loopback_dev is registered very early during boot, we lose a chance
to re-initialize it in notifier. addrconf_init() is called after
ip6_route_init(), which means we have no chance to correct it.

Fix it by moving this initialization explicitly after
ipv6_add_dev(init_net.loopback_dev) in addrconf_init().

Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_route.h |  1 +
 net/ipv6/addrconf.c     |  2 ++
 net/ipv6/route.c        | 26 +++++++++++++++-----------
 3 files changed, 18 insertions(+), 11 deletions(-)

diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 9dc2c18..f5e625f 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -84,6 +84,7 @@ struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6,
 struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 			       int ifindex, struct flowi6 *fl6, int flags);
 
+void ip6_route_init_special_entries(void);
 int ip6_route_init(void);
 void ip6_route_cleanup(void);
 
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index f10ecd9..9eab7e9 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -6324,6 +6324,8 @@ int __init addrconf_init(void)
 		goto errlo;
 	}
 
+	ip6_route_init_special_entries();
+
 	for (i = 0; i < IN6_ADDR_HSIZE; i++)
 		INIT_HLIST_HEAD(&inet6_addr_lst[i]);
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 523681a..6027b80 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3813,6 +3813,21 @@ static struct notifier_block ip6_route_dev_notifier = {
 	.priority = 0,
 };
 
+void __init ip6_route_init_special_entries(void)
+{
+	/* Registering of the loopback is done before this portion of code,
+	 * the loopback reference in rt6_info will not be taken, do it
+	 * manually for init_net */
+	init_net.ipv6.ip6_null_entry->dst.dev = init_net.loopback_dev;
+	init_net.ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
+  #ifdef CONFIG_IPV6_MULTIPLE_TABLES
+	init_net.ipv6.ip6_prohibit_entry->dst.dev = init_net.loopback_dev;
+	init_net.ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
+	init_net.ipv6.ip6_blk_hole_entry->dst.dev = init_net.loopback_dev;
+	init_net.ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
+  #endif
+}
+
 int __init ip6_route_init(void)
 {
 	int ret;
@@ -3839,17 +3854,6 @@ int __init ip6_route_init(void)
 
 	ip6_dst_blackhole_ops.kmem_cachep = ip6_dst_ops_template.kmem_cachep;
 
-	/* Registering of the loopback is done before this portion of code,
-	 * the loopback reference in rt6_info will not be taken, do it
-	 * manually for init_net */
-	init_net.ipv6.ip6_null_entry->dst.dev = init_net.loopback_dev;
-	init_net.ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
-  #ifdef CONFIG_IPV6_MULTIPLE_TABLES
-	init_net.ipv6.ip6_prohibit_entry->dst.dev = init_net.loopback_dev;
-	init_net.ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
-	init_net.ipv6.ip6_blk_hole_entry->dst.dev = init_net.loopback_dev;
-	init_net.ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
-  #endif
 	ret = fib6_init();
 	if (ret)
 		goto out_register_subsys;
-- 
2.7.4


From 273daf282b6db39ad356d5d7bf1874eaf0f22f74 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Mon, 8 May 2017 10:12:13 -0700
Subject: [PATCH 15/19] ipv6: reorder ip6_route_dev_notifier after
 ipv6_dev_notf

[ Upstream commit 242d3a49a2a1a71d8eb9f953db1bcaa9d698ce00 ]

For each netns (except init_net), we initialize its null entry
in 3 places:

1) The template itself, as we use kmemdup()
2) Code around dst_init_metrics() in ip6_route_net_init()
3) ip6_route_dev_notify(), which is supposed to initialize it after
   loopback registers

Unfortunately the last one still happens in a wrong order because
we expect to initialize net->ipv6.ip6_null_entry->rt6i_idev to
net->loopback_dev's idev, thus we have to do that after we add
idev to loopback. However, this notifier has priority == 0 same as
ipv6_dev_notf, and ipv6_dev_notf is registered after
ip6_route_dev_notifier so it is called actually after
ip6_route_dev_notifier. This is similar to commit 2f460933f58e
("ipv6: initialize route null entry in addrconf_init()") which
fixes init_net.

Fix it by picking a smaller priority for ip6_route_dev_notifier.
Also, we have to release the refcnt accordingly when unregistering
loopback_dev because device exit functions are called before subsys
exit functions.

Acked-by: David Ahern <dsahern@gmail.com>
Tested-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/addrconf.h |  2 ++
 net/ipv6/addrconf.c    |  1 +
 net/ipv6/route.c       | 13 +++++++++++--
 3 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 8f998af..b8ee8a1 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -20,6 +20,8 @@
 #define ADDRCONF_TIMER_FUZZ		(HZ / 4)
 #define ADDRCONF_TIMER_FUZZ_MAX		(HZ)
 
+#define ADDRCONF_NOTIFY_PRIORITY	0
+
 #include <linux/in.h>
 #include <linux/in6.h>
 
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 9eab7e9..82a5598 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3508,6 +3508,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
  */
 static struct notifier_block ipv6_dev_notf = {
 	.notifier_call = addrconf_notify,
+	.priority = ADDRCONF_NOTIFY_PRIORITY,
 };
 
 static void addrconf_type_change(struct net_device *dev, unsigned long event)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 6027b80..d5c2e35 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3495,7 +3495,10 @@ static int ip6_route_dev_notify(struct notifier_block *this,
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct net *net = dev_net(dev);
 
-	if (event == NETDEV_REGISTER && (dev->flags & IFF_LOOPBACK)) {
+	if (!(dev->flags & IFF_LOOPBACK))
+		return NOTIFY_OK;
+
+	if (event == NETDEV_REGISTER) {
 		net->ipv6.ip6_null_entry->dst.dev = dev;
 		net->ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(dev);
 #ifdef CONFIG_IPV6_MULTIPLE_TABLES
@@ -3504,6 +3507,12 @@ static int ip6_route_dev_notify(struct notifier_block *this,
 		net->ipv6.ip6_blk_hole_entry->dst.dev = dev;
 		net->ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(dev);
 #endif
+	 } else if (event == NETDEV_UNREGISTER) {
+		in6_dev_put(net->ipv6.ip6_null_entry->rt6i_idev);
+#ifdef CONFIG_IPV6_MULTIPLE_TABLES
+		in6_dev_put(net->ipv6.ip6_prohibit_entry->rt6i_idev);
+		in6_dev_put(net->ipv6.ip6_blk_hole_entry->rt6i_idev);
+#endif
 	}
 
 	return NOTIFY_OK;
@@ -3810,7 +3819,7 @@ static struct pernet_operations ip6_route_net_late_ops = {
 
 static struct notifier_block ip6_route_dev_notifier = {
 	.notifier_call = ip6_route_dev_notify,
-	.priority = 0,
+	.priority = ADDRCONF_NOTIFY_PRIORITY - 10,
 };
 
 void __init ip6_route_init_special_entries(void)
-- 
2.7.4


From e4fbcc8e588916a99e10318a7f959d7c36d15e86 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Sat, 6 May 2017 03:49:01 +0300
Subject: [PATCH 16/19] bnxt_en: allocate enough space for ->ntp_fltr_bmap

[ Upstream commit ac45bd93a5035c2f39c9862b8b6ed692db0fdc87 ]

We have the number of longs, but we need to calculate the number of
bytes required.

Fixes: c0c050c58d84 ("bnxt_en: New Broadcom ethernet driver.")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 4fcc6a8..8bc5785 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -2869,7 +2869,8 @@ static int bnxt_alloc_ntp_fltrs(struct bnxt *bp)
 		INIT_HLIST_HEAD(&bp->ntp_fltr_hash_tbl[i]);
 
 	bp->ntp_fltr_count = 0;
-	bp->ntp_fltr_bmap = kzalloc(BITS_TO_LONGS(BNXT_NTP_FLTR_MAX_FLTR),
+	bp->ntp_fltr_bmap = kcalloc(BITS_TO_LONGS(BNXT_NTP_FLTR_MAX_FLTR),
+				    sizeof(long),
 				    GFP_KERNEL);
 
 	if (!bp->ntp_fltr_bmap)
-- 
2.7.4


From 8fea941b3b4f7e8887bd77417b23509a24da18c2 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Mon, 8 May 2017 00:04:09 +0200
Subject: [PATCH 17/19] bpf: don't let ldimm64 leak map addresses on
 unprivileged

[ Upstream commit 0d0e57697f162da4aa218b5feafe614fb666db07 ]

The patch fixes two things at once:

1) It checks the env->allow_ptr_leaks and only prints the map address to
   the log if we have the privileges to do so, otherwise it just dumps 0
   as we would when kptr_restrict is enabled on %pK. Given the latter is
   off by default and not every distro sets it, I don't want to rely on
   this, hence the 0 by default for unprivileged.

2) Printing of ldimm64 in the verifier log is currently broken in that
   we don't print the full immediate, but only the 32 bit part of the
   first insn part for ldimm64. Thus, fix this up as well; it's okay to
   access, since we verified all ldimm64 earlier already (including just
   constants) through replace_map_fd_with_map_ptr().

Fixes: 1be7f75d1668 ("bpf: enable non-root eBPF programs")
Fixes: cbd357008604 ("bpf: verifier (add ability to receive verification log)")
Reported-by: Jann Horn <jannh@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c | 21 ++++++++++++++++-----
 1 file changed, 16 insertions(+), 5 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index ce16f80..b54585d 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -296,7 +296,8 @@ static const char *const bpf_jmp_string[16] = {
 	[BPF_EXIT >> 4] = "exit",
 };
 
-static void print_bpf_insn(struct bpf_insn *insn)
+static void print_bpf_insn(const struct bpf_verifier_env *env,
+			   const struct bpf_insn *insn)
 {
 	u8 class = BPF_CLASS(insn->code);
 
@@ -360,9 +361,19 @@ static void print_bpf_insn(struct bpf_insn *insn)
 				insn->code,
 				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
 				insn->src_reg, insn->imm);
-		} else if (BPF_MODE(insn->code) == BPF_IMM) {
-			verbose("(%02x) r%d = 0x%x\n",
-				insn->code, insn->dst_reg, insn->imm);
+		} else if (BPF_MODE(insn->code) == BPF_IMM &&
+			   BPF_SIZE(insn->code) == BPF_DW) {
+			/* At this point, we already made sure that the second
+			 * part of the ldimm64 insn is accessible.
+			 */
+			u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm;
+			bool map_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD;
+
+			if (map_ptr && !env->allow_ptr_leaks)
+				imm = 0;
+
+			verbose("(%02x) r%d = 0x%llx\n", insn->code,
+				insn->dst_reg, (unsigned long long)imm);
 		} else {
 			verbose("BUG_ld_%02x\n", insn->code);
 			return;
@@ -2704,7 +2715,7 @@ static int do_check(struct bpf_verifier_env *env)
 
 		if (log_level) {
 			verbose("%d: ", insn_idx);
-			print_bpf_insn(insn);
+			print_bpf_insn(env, insn);
 		}
 
 		err = ext_analyzer_insn_hook(env, insn_idx, prev_insn_idx);
-- 
2.7.4


From 274d0515ce19637df3e580d1583c57ab3a493e3f Mon Sep 17 00:00:00 2001
From: Jon Mason <jon.mason@broadcom.com>
Date: Mon, 8 May 2017 17:48:35 -0400
Subject: [PATCH 18/19] net: mdio-mux: bcm-iproc: call mdiobus_free() in error
 path

[ Upstream commit 922c60e89d52730050c6ccca218bff40cc8bcd8e ]

If an error is encountered in mdio_mux_init(), the error path will call
mdiobus_free().  Since mdiobus_register() has been called prior to
mdio_mux_init(), the bus->state will not be MDIOBUS_UNREGISTERED.  This
causes a BUG_ON() in mdiobus_free().  To correct this issue, add an
error path for mdio_mux_init() which calls mdiobus_unregister() prior to
mdiobus_free().

Signed-off-by: Jon Mason <jon.mason@broadcom.com>
Fixes: 98bc865a1ec8 ("net: mdio-mux: Add MDIO mux driver for iProc SoCs")
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mdio-mux-bcm-iproc.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/mdio-mux-bcm-iproc.c b/drivers/net/phy/mdio-mux-bcm-iproc.c
index 0a04125..0a5f62e 100644
--- a/drivers/net/phy/mdio-mux-bcm-iproc.c
+++ b/drivers/net/phy/mdio-mux-bcm-iproc.c
@@ -203,11 +203,14 @@ static int mdio_mux_iproc_probe(struct platform_device *pdev)
 			   &md->mux_handle, md, md->mii_bus);
 	if (rc) {
 		dev_info(md->dev, "mdiomux initialization failed\n");
-		goto out;
+		goto out_register;
 	}
 
 	dev_info(md->dev, "iProc mdiomux registered\n");
 	return 0;
+
+out_register:
+	mdiobus_unregister(bus);
 out:
 	mdiobus_free(bus);
 	return rc;
-- 
2.7.4


From cce9d9ef1cb25f57987c8f6e84d96e8094859420 Mon Sep 17 00:00:00 2001
From: Jarno Rajahalme <jarno@ovn.org>
Date: Tue, 14 Feb 2017 21:16:28 -0800
Subject: [PATCH 19/19] openvswitch: Set internal device max mtu to
 ETH_MAX_MTU.

[ Upstream commit 425df17ce3a26d98f76e2b6b0af2acf4aeb0b026 ]

Commit 91572088e3fd ("net: use core MTU range checking in core net
infra") changed the openvswitch internal device to use the core net
infra for controlling the MTU range, but failed to actually set the
max_mtu as described in the commit message, which now defaults to
ETH_DATA_LEN.

This patch fixes this by setting max_mtu to ETH_MAX_MTU after
ether_setup() call.

Fixes: 91572088e3fd ("net: use core MTU range checking in core net infra")
Signed-off-by: Jarno Rajahalme <jarno@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/vport-internal_dev.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c
index d5d6cae..695acd2 100644
--- a/net/openvswitch/vport-internal_dev.c
+++ b/net/openvswitch/vport-internal_dev.c
@@ -151,6 +151,8 @@ static void do_setup(struct net_device *netdev)
 {
 	ether_setup(netdev);
 
+	netdev->max_mtu = ETH_MAX_MTU;
+
 	netdev->netdev_ops = &internal_dev_netdev_ops;
 
 	netdev->priv_flags &= ~IFF_TX_SKB_SHARING;
-- 
2.7.4


[-- Attachment #3: net_411.mbox --]
[-- Type: Application/Octet-Stream, Size: 61975 bytes --]

From ad535f9f1336a4384f81d98c47f6011e937a0eef Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@free-electrons.com>
Date: Wed, 26 Apr 2017 12:06:28 +0200
Subject: [PATCH 01/17] net: macb: fix phy interrupt parsing

[ Upstream commit ae3696c167cc04d32634c4af82f43b446c5176b0 ]

Since 83a77e9ec415, the phydev irq is explicitly set to PHY_POLL when
there is no pdata. It doesn't work on DT enabled platforms because the
phydev irq is already set by libphy before.

Fixes: 83a77e9ec415 ("net: macb: Added PCI wrapper for Platform Driver.")
Signed-off-by: Alexandre Belloni <alexandre.belloni@free-electrons.com>
Acked-by: Nicolas Ferre <nicolas.ferre@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index 30606b1..377fb0f 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -432,15 +432,17 @@ static int macb_mii_probe(struct net_device *dev)
 	}
 
 	pdata = dev_get_platdata(&bp->pdev->dev);
-	if (pdata && gpio_is_valid(pdata->phy_irq_pin)) {
-		ret = devm_gpio_request(&bp->pdev->dev, pdata->phy_irq_pin,
-					"phy int");
-		if (!ret) {
-			phy_irq = gpio_to_irq(pdata->phy_irq_pin);
-			phydev->irq = (phy_irq < 0) ? PHY_POLL : phy_irq;
+	if (pdata) {
+		if (gpio_is_valid(pdata->phy_irq_pin)) {
+			ret = devm_gpio_request(&bp->pdev->dev,
+						pdata->phy_irq_pin, "phy int");
+			if (!ret) {
+				phy_irq = gpio_to_irq(pdata->phy_irq_pin);
+				phydev->irq = (phy_irq < 0) ? PHY_POLL : phy_irq;
+			}
+		} else {
+			phydev->irq = PHY_POLL;
 		}
-	} else {
-		phydev->irq = PHY_POLL;
 	}
 
 	/* attach the mac to the phy */
-- 
2.7.4


From d99291adb9afa4336afbcc832756df45af1d1d6c Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Wed, 26 Apr 2017 19:07:35 +0200
Subject: [PATCH 02/17] tcp: fix access to sk->sk_state in tcp_poll()

[ Upstream commit d68be71ea14d609a5f31534003319be5db422595 ]

avoid direct access to sk->sk_state when tcp_poll() is called on a socket
using active TCP fastopen with deferred connect. Use local variable
'state', which stores the result of sk_state_load(), like it was done in
commit 00fd38d938db ("tcp: ensure proper barriers in lockless contexts").

Fixes: 19f6d3f3c842 ("net/tcp-fastopen: Add new API support")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Wei Wang <weiwan@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 40ba424..2dc7fcf 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -533,7 +533,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 
 		if (tp->urg_data & TCP_URG_VALID)
 			mask |= POLLPRI;
-	} else if (sk->sk_state == TCP_SYN_SENT && inet_sk(sk)->defer_connect) {
+	} else if (state == TCP_SYN_SENT && inet_sk(sk)->defer_connect) {
 		/* Active TCP fastopen socket with defer_connect
 		 * Return POLLOUT so application can call write()
 		 * in order for kernel to generate SYN+data
-- 
2.7.4


From c32234f9736e60b81031b69160a8236dd8d81093 Mon Sep 17 00:00:00 2001
From: Girish Moodalbail <girish.moodalbail@oracle.com>
Date: Thu, 27 Apr 2017 14:11:53 -0700
Subject: [PATCH 03/17] geneve: fix incorrect setting of UDP checksum flag

[ Upstream commit 5e0740c445e6ae4026f5e52456ff8d0be9725183 ]

Creating a geneve link with 'udpcsum' set results in a creation of link
for which UDP checksum will NOT be computed on outbound packets, as can
be seen below.

11: gen0: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN
    link/ether c2:85:27:b6:b4:15 brd ff:ff:ff:ff:ff:ff promiscuity 0
    geneve id 200 remote 192.168.13.1 dstport 6081 noudpcsum

Similarly, creating a link with 'noudpcsum' set results in a creation
of link for which UDP checksum will be computed on outbound packets.

Fixes: 9b4437a5b870 ("geneve: Unify LWT and netdev handling.")
Signed-off-by: Girish Moodalbail <girish.moodalbail@oracle.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Acked-by: Lance Richardson <lrichard@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 7074b40..dec5d56 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1244,7 +1244,7 @@ static int geneve_newlink(struct net *net, struct net_device *dev,
 		metadata = true;
 
 	if (data[IFLA_GENEVE_UDP_CSUM] &&
-	    !nla_get_u8(data[IFLA_GENEVE_UDP_CSUM]))
+	    nla_get_u8(data[IFLA_GENEVE_UDP_CSUM]))
 		info.key.tun_flags |= TUNNEL_CSUM;
 
 	if (data[IFLA_GENEVE_UDP_ZERO_CSUM6_TX] &&
-- 
2.7.4


From 6c21f349f3c89e93924cf54908a6c4300d2e10c8 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Sat, 29 Apr 2017 22:52:42 -0700
Subject: [PATCH 04/17] bpf: enhance verifier to understand stack pointer
 arithmetic

[ Upstream commit 332270fdc8b6fba07d059a9ad44df9e1a2ad4529 ]

llvm 4.0 and above generates the code like below:
....
440: (b7) r1 = 15
441: (05) goto pc+73
515: (79) r6 = *(u64 *)(r10 -152)
516: (bf) r7 = r10
517: (07) r7 += -112
518: (bf) r2 = r7
519: (0f) r2 += r1
520: (71) r1 = *(u8 *)(r8 +0)
521: (73) *(u8 *)(r2 +45) = r1
....
and the verifier complains "R2 invalid mem access 'inv'" for insn #521.
This is because verifier marks register r2 as unknown value after #519
where r2 is a stack pointer and r1 holds a constant value.

Teach verifier to recognize "stack_ptr + imm" and
"stack_ptr + reg with const val" as valid stack_ptr with new offset.

Signed-off-by: Yonghong Song <yhs@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c                       | 11 +++++++++++
 tools/testing/selftests/bpf/test_verifier.c | 18 ++++++++++++------
 2 files changed, 23 insertions(+), 6 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index a834068..f27849e 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1911,6 +1911,17 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 			return 0;
 		} else if (opcode == BPF_ADD &&
 			   BPF_CLASS(insn->code) == BPF_ALU64 &&
+			   dst_reg->type == PTR_TO_STACK &&
+			   ((BPF_SRC(insn->code) == BPF_X &&
+			     regs[insn->src_reg].type == CONST_IMM) ||
+			    BPF_SRC(insn->code) == BPF_K)) {
+			if (BPF_SRC(insn->code) == BPF_X)
+				dst_reg->imm += regs[insn->src_reg].imm;
+			else
+				dst_reg->imm += insn->imm;
+			return 0;
+		} else if (opcode == BPF_ADD &&
+			   BPF_CLASS(insn->code) == BPF_ALU64 &&
 			   (dst_reg->type == PTR_TO_PACKET ||
 			    (BPF_SRC(insn->code) == BPF_X &&
 			     regs[insn->src_reg].type == PTR_TO_PACKET))) {
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index c848e90..8b433bf 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -1809,16 +1809,22 @@ static struct bpf_test tests[] = {
 		.result = ACCEPT,
 	},
 	{
-		"unpriv: obfuscate stack pointer",
+		"stack pointer arithmetic",
 		.insns = {
-			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_MOV64_IMM(BPF_REG_1, 4),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 0),
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -10),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_1),
+			BPF_ST_MEM(0, BPF_REG_2, 4, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 8),
+			BPF_ST_MEM(0, BPF_REG_2, 4, 0),
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
-		.errstr_unpriv = "R2 pointer arithmetic",
-		.result_unpriv = REJECT,
 		.result = ACCEPT,
 	},
 	{
-- 
2.7.4


From 17554da6d01f454b04ff0dea188674a4bb85e951 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Tue, 2 May 2017 20:34:54 +0200
Subject: [PATCH 05/17] bpf, arm64: fix jit branch offset related to ldimm64

[ Upstream commit ddc665a4bb4b728b4e6ecec8db1b64efa9184b9c ]

When the instruction right before the branch destination is
a 64 bit load immediate, we currently calculate the wrong
jump offset in the ctx->offset[] array as we only account
one instruction slot for the 64 bit load immediate although
it uses two BPF instructions. Fix it up by setting the offset
into the right slot after we incremented the index.

Before (ldimm64 test 1):

  [...]
  00000020:  52800007  mov w7, #0x0 // #0
  00000024:  d2800060  mov x0, #0x3 // #3
  00000028:  d2800041  mov x1, #0x2 // #2
  0000002c:  eb01001f  cmp x0, x1
  00000030:  54ffff82  b.cs 0x00000020
  00000034:  d29fffe7  mov x7, #0xffff // #65535
  00000038:  f2bfffe7  movk x7, #0xffff, lsl #16
  0000003c:  f2dfffe7  movk x7, #0xffff, lsl #32
  00000040:  f2ffffe7  movk x7, #0xffff, lsl #48
  00000044:  d29dddc7  mov x7, #0xeeee // #61166
  00000048:  f2bdddc7  movk x7, #0xeeee, lsl #16
  0000004c:  f2ddddc7  movk x7, #0xeeee, lsl #32
  00000050:  f2fdddc7  movk x7, #0xeeee, lsl #48
  [...]

After (ldimm64 test 1):

  [...]
  00000020:  52800007  mov w7, #0x0 // #0
  00000024:  d2800060  mov x0, #0x3 // #3
  00000028:  d2800041  mov x1, #0x2 // #2
  0000002c:  eb01001f  cmp x0, x1
  00000030:  540000a2  b.cs 0x00000044
  00000034:  d29fffe7  mov x7, #0xffff // #65535
  00000038:  f2bfffe7  movk x7, #0xffff, lsl #16
  0000003c:  f2dfffe7  movk x7, #0xffff, lsl #32
  00000040:  f2ffffe7  movk x7, #0xffff, lsl #48
  00000044:  d29dddc7  mov x7, #0xeeee // #61166
  00000048:  f2bdddc7  movk x7, #0xeeee, lsl #16
  0000004c:  f2ddddc7  movk x7, #0xeeee, lsl #32
  00000050:  f2fdddc7  movk x7, #0xeeee, lsl #48
  [...]

Also, add a couple of test cases to make sure JITs pass
this test. Tested on Cavium ThunderX ARMv8. The added
test cases all pass after the fix.

Fixes: 8eee539ddea0 ("arm64: bpf: fix out-of-bounds read in bpf2a64_offset()")
Reported-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Cc: Xi Wang <xi.wang@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/arm64/net/bpf_jit_comp.c |  8 ++++----
 lib/test_bpf.c                | 45 +++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 49 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index a785554..ce8ab04 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -779,14 +779,14 @@ static int build_body(struct jit_ctx *ctx)
 		int ret;
 
 		ret = build_insn(insn, ctx);
-
-		if (ctx->image == NULL)
-			ctx->offset[i] = ctx->idx;
-
 		if (ret > 0) {
 			i++;
+			if (ctx->image == NULL)
+				ctx->offset[i] = ctx->idx;
 			continue;
 		}
+		if (ctx->image == NULL)
+			ctx->offset[i] = ctx->idx;
 		if (ret)
 			return ret;
 	}
diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index 0362da0..2e38502 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -4656,6 +4656,51 @@ static struct bpf_test tests[] = {
 		{ },
 		{ { 0, 1 } },
 	},
+	{
+		/* Mainly testing JIT + imm64 here. */
+		"JMP_JGE_X: ldimm64 test 1",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_LD_IMM64(R1, 3),
+			BPF_LD_IMM64(R2, 2),
+			BPF_JMP_REG(BPF_JGE, R1, R2, 2),
+			BPF_LD_IMM64(R0, 0xffffffffffffffffUL),
+			BPF_LD_IMM64(R0, 0xeeeeeeeeeeeeeeeeUL),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xeeeeeeeeU } },
+	},
+	{
+		"JMP_JGE_X: ldimm64 test 2",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_LD_IMM64(R1, 3),
+			BPF_LD_IMM64(R2, 2),
+			BPF_JMP_REG(BPF_JGE, R1, R2, 0),
+			BPF_LD_IMM64(R0, 0xffffffffffffffffUL),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xffffffffU } },
+	},
+	{
+		"JMP_JGE_X: ldimm64 test 3",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_LD_IMM64(R1, 3),
+			BPF_LD_IMM64(R2, 2),
+			BPF_JMP_REG(BPF_JGE, R1, R2, 4),
+			BPF_LD_IMM64(R0, 0xffffffffffffffffUL),
+			BPF_LD_IMM64(R0, 0xeeeeeeeeeeeeeeeeUL),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+	},
 	/* BPF_JMP | BPF_JNE | BPF_X */
 	{
 		"JMP_JNE_X: if (3 != 2) return 1",
-- 
2.7.4


From 170d1c113c8f2d065d32471a42fcd4a29189b8c1 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 1 May 2017 15:29:48 -0700
Subject: [PATCH 06/17] tcp: fix wraparound issue in tcp_lp

[ Upstream commit a9f11f963a546fea9144f6a6d1a307e814a387e7 ]

Be careful when comparing tcp_time_stamp to some u32 quantity,
otherwise result can be surprising.

Fixes: 7c106d7e782b ("[TCP]: TCP Low Priority congestion control")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_lp.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c
index 046fd39..d6fb6c0 100644
--- a/net/ipv4/tcp_lp.c
+++ b/net/ipv4/tcp_lp.c
@@ -264,13 +264,15 @@ static void tcp_lp_pkts_acked(struct sock *sk, const struct ack_sample *sample)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct lp *lp = inet_csk_ca(sk);
+	u32 delta;
 
 	if (sample->rtt_us > 0)
 		tcp_lp_rtt_sample(sk, sample->rtt_us);
 
 	/* calc inference */
-	if (tcp_time_stamp > tp->rx_opt.rcv_tsecr)
-		lp->inference = 3 * (tcp_time_stamp - tp->rx_opt.rcv_tsecr);
+	delta = tcp_time_stamp - tp->rx_opt.rcv_tsecr;
+	if ((s32)delta > 0)
+		lp->inference = 3 * delta;
 
 	/* test if within inference */
 	if (lp->last_drop && (tcp_time_stamp - lp->last_drop < lp->inference))
-- 
2.7.4


From 0ca34d2479a04eb1ae7fad21fd6d405e6fa35f08 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 2 May 2017 14:43:44 -0700
Subject: [PATCH 07/17] net: ipv6: Do not duplicate DAD on link up

[ Upstream commit 6d717134a1a6e1b34a7d0d70e953037bc2642046 ]

Andrey reported a warning triggered by the rcu code:

------------[ cut here ]------------
WARNING: CPU: 1 PID: 5911 at lib/debugobjects.c:289
debug_print_object+0x175/0x210
ODEBUG: activate active (active state 1) object type: rcu_head hint:
        (null)
Modules linked in:
CPU: 1 PID: 5911 Comm: a.out Not tainted 4.11.0-rc8+ #271
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:16
 dump_stack+0x192/0x22d lib/dump_stack.c:52
 __warn+0x19f/0x1e0 kernel/panic.c:549
 warn_slowpath_fmt+0xe0/0x120 kernel/panic.c:564
 debug_print_object+0x175/0x210 lib/debugobjects.c:286
 debug_object_activate+0x574/0x7e0 lib/debugobjects.c:442
 debug_rcu_head_queue kernel/rcu/rcu.h:75
 __call_rcu.constprop.76+0xff/0x9c0 kernel/rcu/tree.c:3229
 call_rcu_sched+0x12/0x20 kernel/rcu/tree.c:3288
 rt6_rcu_free net/ipv6/ip6_fib.c:158
 rt6_release+0x1ea/0x290 net/ipv6/ip6_fib.c:188
 fib6_del_route net/ipv6/ip6_fib.c:1461
 fib6_del+0xa42/0xdc0 net/ipv6/ip6_fib.c:1500
 __ip6_del_rt+0x100/0x160 net/ipv6/route.c:2174
 ip6_del_rt+0x140/0x1b0 net/ipv6/route.c:2187
 __ipv6_ifa_notify+0x269/0x780 net/ipv6/addrconf.c:5520
 addrconf_ifdown+0xe60/0x1a20 net/ipv6/addrconf.c:3672
...

Andrey's reproducer program runs in a very tight loop, calling
'unshare -n' and then spawning 2 sets of 14 threads running random ioctl
calls. The relevant networking sequence:

1. New network namespace created via unshare -n
- ip6tnl0 device is created in down state

2. address added to ip6tnl0
- equivalent to ip -6 addr add dev ip6tnl0 fd00::bb/1
- DAD is started on the address and when it completes the host
  route is inserted into the FIB

3. ip6tnl0 is brought up
- the new fixup_permanent_addr function restarts DAD on the address

4. exit namespace
- teardown / cleanup sequence starts
- once in a blue moon, lo teardown appears to happen BEFORE teardown
  of ip6tunl0
  + down on 'lo' removes the host route from the FIB since the dst->dev
    for the route is loobback
  + host route added to rcu callback list
    * rcu callback has not run yet, so rt is NOT on the gc list so it has
      NOT been marked obsolete

5. in parallel to 4. worker_thread runs addrconf_dad_completed
- DAD on the address on ip6tnl0 completes
- calls ipv6_ifa_notify which inserts the host route

All of that happens very quickly. The result is that a host route that
has been deleted from the IPv6 FIB and added to the RCU list is re-inserted
into the FIB.

The exit namespace eventually gets to cleaning up ip6tnl0 which removes the
host route from the FIB again, calls the rcu function for cleanup -- and
triggers the double rcu trace.

The root cause is duplicate DAD on the address -- steps 2 and 3. Arguably,
DAD should not be started in step 2. The interface is in the down state,
so it can not really send out requests for the address which makes starting
DAD pointless.

Since the second DAD was introduced by a recent change, seems appropriate
to use it for the Fixes tag and have the fixup function only start DAD for
addresses in the PREDAD state which occurs in addrconf_ifdown if the
address is retained.

Big thanks to Andrey for isolating a reliable reproducer for this problem.
Fixes: f1705ec197e7 ("net: ipv6: Make address flushing on ifdown optional")
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 0ea96c4..78b1b6a 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3296,7 +3296,8 @@ static int fixup_permanent_addr(struct inet6_dev *idev,
 				      idev->dev, 0, 0);
 	}
 
-	addrconf_dad_start(ifp);
+	if (ifp->state == INET6_IFADDR_STATE_PREDAD)
+		addrconf_dad_start(ifp);
 
 	return 0;
 }
@@ -3651,7 +3652,7 @@ static int addrconf_ifdown(struct net_device *dev, int how)
 		if (keep) {
 			/* set state to skip the notifier below */
 			state = INET6_IFADDR_STATE_DEAD;
-			ifa->state = 0;
+			ifa->state = INET6_IFADDR_STATE_PREDAD;
 			if (!(ifa->flags & IFA_F_NODAD))
 				ifa->flags |= IFA_F_TENTATIVE;
 
-- 
2.7.4


From 49bd5bea058423cf42bf747ab5b67f53f5bcb5be Mon Sep 17 00:00:00 2001
From: Daniele Palmas <dnlplm@gmail.com>
Date: Wed, 3 May 2017 10:30:11 +0200
Subject: [PATCH 08/17] net: usb: qmi_wwan: add Telit ME910 support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 4c54dc0277d0d55a9248c43aebd31858f926a056 ]

This patch adds support for Telit ME910 PID 0x1100.

Signed-off-by: Daniele Palmas <dnlplm@gmail.com>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 2474618..4e34568 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -907,6 +907,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x2357, 0x0201, 4)},	/* TP-LINK HSUPA Modem MA180 */
 	{QMI_FIXED_INTF(0x2357, 0x9000, 4)},	/* TP-LINK MA260 */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1040, 2)},	/* Telit LE922A */
+	{QMI_FIXED_INTF(0x1bc7, 0x1100, 3)},	/* Telit ME910 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)},	/* Telit LE920 */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1201, 2)},	/* Telit LE920, LE920A4 */
 	{QMI_FIXED_INTF(0x1c9e, 0x9b01, 3)},	/* XS Stick W100-2 from 4G Systems */
-- 
2.7.4


From d496fbb25156d23d86130b4749b766bdd1c7fe3b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 3 May 2017 06:39:31 -0700
Subject: [PATCH 09/17] tcp: do not inherit fastopen_req from parent

[ Upstream commit 8b485ce69876c65db12ed390e7f9c0d2a64eff2c ]

Under fuzzer stress, it is possible that a child gets a non NULL
fastopen_req pointer from its parent at accept() time, when/if parent
morphs from listener to active session.

We need to make sure this can not happen, by clearing the field after
socket cloning.

BUG: Double free or freeing an invalid pointer
Unexpected shadow byte: 0xFB
CPU: 3 PID: 20933 Comm: syz-executor3 Not tainted 4.11.0+ #306
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs
01/01/2011
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:16 [inline]
 dump_stack+0x292/0x395 lib/dump_stack.c:52
 kasan_object_err+0x1c/0x70 mm/kasan/report.c:164
 kasan_report_double_free+0x5c/0x70 mm/kasan/report.c:185
 kasan_slab_free+0x9d/0xc0 mm/kasan/kasan.c:580
 slab_free_hook mm/slub.c:1357 [inline]
 slab_free_freelist_hook mm/slub.c:1379 [inline]
 slab_free mm/slub.c:2961 [inline]
 kfree+0xe8/0x2b0 mm/slub.c:3882
 tcp_free_fastopen_req net/ipv4/tcp.c:1077 [inline]
 tcp_disconnect+0xc15/0x13e0 net/ipv4/tcp.c:2328
 inet_child_forget+0xb8/0x600 net/ipv4/inet_connection_sock.c:898
 inet_csk_reqsk_queue_add+0x1e7/0x250
net/ipv4/inet_connection_sock.c:928
 tcp_get_cookie_sock+0x21a/0x510 net/ipv4/syncookies.c:217
 cookie_v4_check+0x1a19/0x28b0 net/ipv4/syncookies.c:384
 tcp_v4_cookie_check net/ipv4/tcp_ipv4.c:1384 [inline]
 tcp_v4_do_rcv+0x731/0x940 net/ipv4/tcp_ipv4.c:1421
 tcp_v4_rcv+0x2dc0/0x31c0 net/ipv4/tcp_ipv4.c:1715
 ip_local_deliver_finish+0x4cc/0xc20 net/ipv4/ip_input.c:216
 NF_HOOK include/linux/netfilter.h:257 [inline]
 ip_local_deliver+0x1ce/0x700 net/ipv4/ip_input.c:257
 dst_input include/net/dst.h:492 [inline]
 ip_rcv_finish+0xb1d/0x20b0 net/ipv4/ip_input.c:396
 NF_HOOK include/linux/netfilter.h:257 [inline]
 ip_rcv+0xd8c/0x19c0 net/ipv4/ip_input.c:487
 __netif_receive_skb_core+0x1ad1/0x3400 net/core/dev.c:4210
 __netif_receive_skb+0x2a/0x1a0 net/core/dev.c:4248
 process_backlog+0xe5/0x6c0 net/core/dev.c:4868
 napi_poll net/core/dev.c:5270 [inline]
 net_rx_action+0xe70/0x18e0 net/core/dev.c:5335
 __do_softirq+0x2fb/0xb99 kernel/softirq.c:284
 do_softirq_own_stack+0x1c/0x30 arch/x86/entry/entry_64.S:899
 </IRQ>
 do_softirq.part.17+0x1e8/0x230 kernel/softirq.c:328
 do_softirq kernel/softirq.c:176 [inline]
 __local_bh_enable_ip+0x1cf/0x1e0 kernel/softirq.c:181
 local_bh_enable include/linux/bottom_half.h:31 [inline]
 rcu_read_unlock_bh include/linux/rcupdate.h:931 [inline]
 ip_finish_output2+0x9ab/0x15e0 net/ipv4/ip_output.c:230
 ip_finish_output+0xa35/0xdf0 net/ipv4/ip_output.c:316
 NF_HOOK_COND include/linux/netfilter.h:246 [inline]
 ip_output+0x1f6/0x7b0 net/ipv4/ip_output.c:404
 dst_output include/net/dst.h:486 [inline]
 ip_local_out+0x95/0x160 net/ipv4/ip_output.c:124
 ip_queue_xmit+0x9a8/0x1a10 net/ipv4/ip_output.c:503
 tcp_transmit_skb+0x1ade/0x3470 net/ipv4/tcp_output.c:1057
 tcp_write_xmit+0x79e/0x55b0 net/ipv4/tcp_output.c:2265
 __tcp_push_pending_frames+0xfa/0x3a0 net/ipv4/tcp_output.c:2450
 tcp_push+0x4ee/0x780 net/ipv4/tcp.c:683
 tcp_sendmsg+0x128d/0x39b0 net/ipv4/tcp.c:1342
 inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:762
 sock_sendmsg_nosec net/socket.c:633 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:643
 SYSC_sendto+0x660/0x810 net/socket.c:1696
 SyS_sendto+0x40/0x50 net/socket.c:1664
 entry_SYSCALL_64_fastpath+0x1f/0xbe
RIP: 0033:0x446059
RSP: 002b:00007faa6761fb58 EFLAGS: 00000282 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 0000000000000017 RCX: 0000000000446059
RDX: 0000000000000001 RSI: 0000000020ba3fcd RDI: 0000000000000017
RBP: 00000000006e40a0 R08: 0000000020ba4ff0 R09: 0000000000000010
R10: 0000000020000000 R11: 0000000000000282 R12: 0000000000708150
R13: 0000000000000000 R14: 00007faa676209c0 R15: 00007faa67620700
Object at ffff88003b5bbcb8, in cache kmalloc-64 size: 64
Allocated:
PID = 20909
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
 save_stack+0x43/0xd0 mm/kasan/kasan.c:513
 set_track mm/kasan/kasan.c:525 [inline]
 kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:616
 kmem_cache_alloc_trace+0x82/0x270 mm/slub.c:2745
 kmalloc include/linux/slab.h:490 [inline]
 kzalloc include/linux/slab.h:663 [inline]
 tcp_sendmsg_fastopen net/ipv4/tcp.c:1094 [inline]
 tcp_sendmsg+0x221a/0x39b0 net/ipv4/tcp.c:1139
 inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:762
 sock_sendmsg_nosec net/socket.c:633 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:643
 SYSC_sendto+0x660/0x810 net/socket.c:1696
 SyS_sendto+0x40/0x50 net/socket.c:1664
 entry_SYSCALL_64_fastpath+0x1f/0xbe
Freed:
PID = 20909
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
 save_stack+0x43/0xd0 mm/kasan/kasan.c:513
 set_track mm/kasan/kasan.c:525 [inline]
 kasan_slab_free+0x73/0xc0 mm/kasan/kasan.c:589
 slab_free_hook mm/slub.c:1357 [inline]
 slab_free_freelist_hook mm/slub.c:1379 [inline]
 slab_free mm/slub.c:2961 [inline]
 kfree+0xe8/0x2b0 mm/slub.c:3882
 tcp_free_fastopen_req net/ipv4/tcp.c:1077 [inline]
 tcp_disconnect+0xc15/0x13e0 net/ipv4/tcp.c:2328
 __inet_stream_connect+0x20c/0xf90 net/ipv4/af_inet.c:593
 tcp_sendmsg_fastopen net/ipv4/tcp.c:1111 [inline]
 tcp_sendmsg+0x23a8/0x39b0 net/ipv4/tcp.c:1139
 inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:762
 sock_sendmsg_nosec net/socket.c:633 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:643
 SYSC_sendto+0x660/0x810 net/socket.c:1696
 SyS_sendto+0x40/0x50 net/socket.c:1664
 entry_SYSCALL_64_fastpath+0x1f/0xbe

Fixes: e994b2f0fb92 ("tcp: do not lock listener to process SYN packets")
Fixes: 7db92362d2fe ("tcp: fix potential double free issue for fastopen_req")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Acked-by: Wei Wang <weiwan@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_minisocks.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 65c0f3d..c1259cc 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -536,6 +536,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 			newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len;
 		newtp->rx_opt.mss_clamp = req->mss;
 		tcp_ecn_openreq_child(newtp, req);
+		newtp->fastopen_req = NULL;
 		newtp->fastopen_rsk = NULL;
 		newtp->syn_data_acked = 0;
 		newtp->rack.mstamp.v64 = 0;
-- 
2.7.4


From c399c3888e1c1032916b1af999c116a2a5ac4fcd Mon Sep 17 00:00:00 2001
From: Alexander Potapenko <glider@google.com>
Date: Wed, 3 May 2017 17:06:58 +0200
Subject: [PATCH 10/17] ipv4, ipv6: ensure raw socket message is big enough to
 hold an IP header

[ Upstream commit 86f4c90a1c5c1493f07f2d12c1079f5bf01936f2 ]

raw_send_hdrinc() and rawv6_send_hdrinc() expect that the buffer copied
from the userspace contains the IPv4/IPv6 header, so if too few bytes are
copied, parts of the header may remain uninitialized.

This bug has been detected with KMSAN.

For the record, the KMSAN report:

==================================================================
BUG: KMSAN: use of unitialized memory in nf_ct_frag6_gather+0xf5a/0x44a0
inter: 0
CPU: 0 PID: 1036 Comm: probe Not tainted 4.11.0-rc5+ #2455
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:16
 dump_stack+0x143/0x1b0 lib/dump_stack.c:52
 kmsan_report+0x16b/0x1e0 mm/kmsan/kmsan.c:1078
 __kmsan_warning_32+0x5c/0xa0 mm/kmsan/kmsan_instr.c:510
 nf_ct_frag6_gather+0xf5a/0x44a0 net/ipv6/netfilter/nf_conntrack_reasm.c:577
 ipv6_defrag+0x1d9/0x280 net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:68
 nf_hook_entry_hookfn ./include/linux/netfilter.h:102
 nf_hook_slow+0x13f/0x3c0 net/netfilter/core.c:310
 nf_hook ./include/linux/netfilter.h:212
 NF_HOOK ./include/linux/netfilter.h:255
 rawv6_send_hdrinc net/ipv6/raw.c:673
 rawv6_sendmsg+0x2fcb/0x41a0 net/ipv6/raw.c:919
 inet_sendmsg+0x3f8/0x6d0 net/ipv4/af_inet.c:762
 sock_sendmsg_nosec net/socket.c:633
 sock_sendmsg net/socket.c:643
 SYSC_sendto+0x6a5/0x7c0 net/socket.c:1696
 SyS_sendto+0xbc/0xe0 net/socket.c:1664
 do_syscall_64+0x72/0xa0 arch/x86/entry/common.c:285
 entry_SYSCALL64_slow_path+0x25/0x25 arch/x86/entry/entry_64.S:246
RIP: 0033:0x436e03
RSP: 002b:00007ffce48baf38 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 00000000004002b0 RCX: 0000000000436e03
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000003
RBP: 00007ffce48baf90 R08: 00007ffce48baf50 R09: 000000000000001c
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 0000000000401790 R14: 0000000000401820 R15: 0000000000000000
origin: 00000000d9400053
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:362
 kmsan_internal_poison_shadow+0xb1/0x1a0 mm/kmsan/kmsan.c:257
 kmsan_poison_shadow+0x6d/0xc0 mm/kmsan/kmsan.c:270
 slab_alloc_node mm/slub.c:2735
 __kmalloc_node_track_caller+0x1f4/0x390 mm/slub.c:4341
 __kmalloc_reserve net/core/skbuff.c:138
 __alloc_skb+0x2cd/0x740 net/core/skbuff.c:231
 alloc_skb ./include/linux/skbuff.h:933
 alloc_skb_with_frags+0x209/0xbc0 net/core/skbuff.c:4678
 sock_alloc_send_pskb+0x9ff/0xe00 net/core/sock.c:1903
 sock_alloc_send_skb+0xe4/0x100 net/core/sock.c:1920
 rawv6_send_hdrinc net/ipv6/raw.c:638
 rawv6_sendmsg+0x2918/0x41a0 net/ipv6/raw.c:919
 inet_sendmsg+0x3f8/0x6d0 net/ipv4/af_inet.c:762
 sock_sendmsg_nosec net/socket.c:633
 sock_sendmsg net/socket.c:643
 SYSC_sendto+0x6a5/0x7c0 net/socket.c:1696
 SyS_sendto+0xbc/0xe0 net/socket.c:1664
 do_syscall_64+0x72/0xa0 arch/x86/entry/common.c:285
 return_from_SYSCALL_64+0x0/0x6a arch/x86/entry/entry_64.S:246
==================================================================

, triggered by the following syscalls:
  socket(PF_INET6, SOCK_RAW, IPPROTO_RAW) = 3
  sendto(3, NULL, 0, 0, {sa_family=AF_INET6, sin6_port=htons(0), inet_pton(AF_INET6, "ff00::", &sin6_addr), sin6_flowinfo=0, sin6_scope_id=0}, 28) = -1 EPERM

A similar report is triggered in net/ipv4/raw.c if we use a PF_INET socket
instead of a PF_INET6 one.

Signed-off-by: Alexander Potapenko <glider@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/raw.c | 3 +++
 net/ipv6/raw.c | 2 ++
 2 files changed, 5 insertions(+)

diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 9d94397..bdffad8 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -358,6 +358,9 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
 			       rt->dst.dev->mtu);
 		return -EMSGSIZE;
 	}
+	if (length < sizeof(struct iphdr))
+		return -EINVAL;
+
 	if (flags&MSG_PROBE)
 		goto out;
 
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 0da6a12..1f992d9 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -632,6 +632,8 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length,
 		ipv6_local_error(sk, EMSGSIZE, fl6, rt->dst.dev->mtu);
 		return -EMSGSIZE;
 	}
+	if (length < sizeof(struct ipv6hdr))
+		return -EINVAL;
 	if (flags&MSG_PROBE)
 		goto out;
 
-- 
2.7.4


From ae74bf1693f1c8d3be579952a6ffe5e85b2489b6 Mon Sep 17 00:00:00 2001
From: Michal Schmidt <mschmidt@redhat.com>
Date: Thu, 4 May 2017 16:48:58 +0200
Subject: [PATCH 11/17] rtnetlink: NUL-terminate IFLA_PHYS_PORT_NAME string

[ Upstream commit 77ef033b687c3e030017c94a29bf6ea3aaaef678 ]

IFLA_PHYS_PORT_NAME is a string attribute, so terminate it with \0.
Otherwise libnl3 fails to validate netlink messages with this attribute.
"ip -detail a" assumes too that the attribute is NUL-terminated when
printing it. It often was, due to padding.

I noticed this as libvirtd failing to start on a system with sfc driver
after upgrading it to Linux 4.11, i.e. when sfc added support for
phys_port_name.

Signed-off-by: Michal Schmidt <mschmidt@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index c4e84c5..69daf39 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1056,7 +1056,7 @@ static int rtnl_phys_port_name_fill(struct sk_buff *skb, struct net_device *dev)
 		return err;
 	}
 
-	if (nla_put(skb, IFLA_PHYS_PORT_NAME, strlen(name), name))
+	if (nla_put_string(skb, IFLA_PHYS_PORT_NAME, name))
 		return -EMSGSIZE;
 
 	return 0;
-- 
2.7.4


From ff7abb27ee362d7d1b00375cdafa28f5a776b6d5 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Wed, 3 May 2017 22:07:31 -0700
Subject: [PATCH 12/17] ipv6: initialize route null entry in addrconf_init()

[ Upstream commit 2f460933f58eee3393aba64f0f6d14acb08d1724 ]

Andrey reported a crash on init_net.ipv6.ip6_null_entry->rt6i_idev
since it is always NULL.

This is clearly wrong, we have code to initialize it to loopback_dev,
unfortunately the order is still not correct.

loopback_dev is registered very early during boot, we lose a chance
to re-initialize it in notifier. addrconf_init() is called after
ip6_route_init(), which means we have no chance to correct it.

Fix it by moving this initialization explicitly after
ipv6_add_dev(init_net.loopback_dev) in addrconf_init().

Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_route.h |  1 +
 net/ipv6/addrconf.c     |  2 ++
 net/ipv6/route.c        | 26 +++++++++++++++-----------
 3 files changed, 18 insertions(+), 11 deletions(-)

diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 9dc2c18..f5e625f 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -84,6 +84,7 @@ struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6,
 struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 			       int ifindex, struct flowi6 *fl6, int flags);
 
+void ip6_route_init_special_entries(void);
 int ip6_route_init(void);
 void ip6_route_cleanup(void);
 
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 78b1b6a..5793b64f 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -6409,6 +6409,8 @@ int __init addrconf_init(void)
 		goto errlo;
 	}
 
+	ip6_route_init_special_entries();
+
 	for (i = 0; i < IN6_ADDR_HSIZE; i++)
 		INIT_HLIST_HEAD(&inet6_addr_lst[i]);
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index fb174b5..4933184 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -4022,6 +4022,21 @@ static struct notifier_block ip6_route_dev_notifier = {
 	.priority = 0,
 };
 
+void __init ip6_route_init_special_entries(void)
+{
+	/* Registering of the loopback is done before this portion of code,
+	 * the loopback reference in rt6_info will not be taken, do it
+	 * manually for init_net */
+	init_net.ipv6.ip6_null_entry->dst.dev = init_net.loopback_dev;
+	init_net.ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
+  #ifdef CONFIG_IPV6_MULTIPLE_TABLES
+	init_net.ipv6.ip6_prohibit_entry->dst.dev = init_net.loopback_dev;
+	init_net.ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
+	init_net.ipv6.ip6_blk_hole_entry->dst.dev = init_net.loopback_dev;
+	init_net.ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
+  #endif
+}
+
 int __init ip6_route_init(void)
 {
 	int ret;
@@ -4048,17 +4063,6 @@ int __init ip6_route_init(void)
 
 	ip6_dst_blackhole_ops.kmem_cachep = ip6_dst_ops_template.kmem_cachep;
 
-	/* Registering of the loopback is done before this portion of code,
-	 * the loopback reference in rt6_info will not be taken, do it
-	 * manually for init_net */
-	init_net.ipv6.ip6_null_entry->dst.dev = init_net.loopback_dev;
-	init_net.ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
-  #ifdef CONFIG_IPV6_MULTIPLE_TABLES
-	init_net.ipv6.ip6_prohibit_entry->dst.dev = init_net.loopback_dev;
-	init_net.ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
-	init_net.ipv6.ip6_blk_hole_entry->dst.dev = init_net.loopback_dev;
-	init_net.ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
-  #endif
 	ret = fib6_init();
 	if (ret)
 		goto out_register_subsys;
-- 
2.7.4


From 4f9e823307b709bdb4b5b31e28ad24a873800f25 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Mon, 8 May 2017 10:12:13 -0700
Subject: [PATCH 13/17] ipv6: reorder ip6_route_dev_notifier after
 ipv6_dev_notf

[ Upstream commit 242d3a49a2a1a71d8eb9f953db1bcaa9d698ce00 ]

For each netns (except init_net), we initialize its null entry
in 3 places:

1) The template itself, as we use kmemdup()
2) Code around dst_init_metrics() in ip6_route_net_init()
3) ip6_route_dev_notify(), which is supposed to initialize it after
   loopback registers

Unfortunately the last one still happens in a wrong order because
we expect to initialize net->ipv6.ip6_null_entry->rt6i_idev to
net->loopback_dev's idev, thus we have to do that after we add
idev to loopback. However, this notifier has priority == 0 same as
ipv6_dev_notf, and ipv6_dev_notf is registered after
ip6_route_dev_notifier so it is called actually after
ip6_route_dev_notifier. This is similar to commit 2f460933f58e
("ipv6: initialize route null entry in addrconf_init()") which
fixes init_net.

Fix it by picking a smaller priority for ip6_route_dev_notifier.
Also, we have to release the refcnt accordingly when unregistering
loopback_dev because device exit functions are called before subsys
exit functions.

Acked-by: David Ahern <dsahern@gmail.com>
Tested-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/addrconf.h |  2 ++
 net/ipv6/addrconf.c    |  1 +
 net/ipv6/route.c       | 13 +++++++++++--
 3 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 17c6fd8..4d93c5e 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -20,6 +20,8 @@
 #define ADDRCONF_TIMER_FUZZ		(HZ / 4)
 #define ADDRCONF_TIMER_FUZZ_MAX		(HZ)
 
+#define ADDRCONF_NOTIFY_PRIORITY	0
+
 #include <linux/in.h>
 #include <linux/in6.h>
 
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 5793b64f..311f456 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3516,6 +3516,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
  */
 static struct notifier_block ipv6_dev_notf = {
 	.notifier_call = addrconf_notify,
+	.priority = ADDRCONF_NOTIFY_PRIORITY,
 };
 
 static void addrconf_type_change(struct net_device *dev, unsigned long event)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 4933184..d316d00 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3704,7 +3704,10 @@ static int ip6_route_dev_notify(struct notifier_block *this,
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct net *net = dev_net(dev);
 
-	if (event == NETDEV_REGISTER && (dev->flags & IFF_LOOPBACK)) {
+	if (!(dev->flags & IFF_LOOPBACK))
+		return NOTIFY_OK;
+
+	if (event == NETDEV_REGISTER) {
 		net->ipv6.ip6_null_entry->dst.dev = dev;
 		net->ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(dev);
 #ifdef CONFIG_IPV6_MULTIPLE_TABLES
@@ -3713,6 +3716,12 @@ static int ip6_route_dev_notify(struct notifier_block *this,
 		net->ipv6.ip6_blk_hole_entry->dst.dev = dev;
 		net->ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(dev);
 #endif
+	 } else if (event == NETDEV_UNREGISTER) {
+		in6_dev_put(net->ipv6.ip6_null_entry->rt6i_idev);
+#ifdef CONFIG_IPV6_MULTIPLE_TABLES
+		in6_dev_put(net->ipv6.ip6_prohibit_entry->rt6i_idev);
+		in6_dev_put(net->ipv6.ip6_blk_hole_entry->rt6i_idev);
+#endif
 	}
 
 	return NOTIFY_OK;
@@ -4019,7 +4028,7 @@ static struct pernet_operations ip6_route_net_late_ops = {
 
 static struct notifier_block ip6_route_dev_notifier = {
 	.notifier_call = ip6_route_dev_notify,
-	.priority = 0,
+	.priority = ADDRCONF_NOTIFY_PRIORITY - 10,
 };
 
 void __init ip6_route_init_special_entries(void)
-- 
2.7.4


From bac5bd143ea03bbd749e9ae94aafd419846adb13 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 5 May 2017 06:56:54 -0700
Subject: [PATCH 14/17] tcp: randomize timestamps on syncookies

[ Upstream commit 84b114b98452c431299d99c135f751659e517acb ]

Whole point of randomization was to hide server uptime, but an attacker
can simply start a syn flood and TCP generates 'old style' timestamps,
directly revealing server jiffies value.

Also, TSval sent by the server to a particular remote address vary
depending on syncookies being sent or not, potentially triggering PAWS
drops for innocent clients.

Lets implement proper randomization, including for SYNcookies.

Also we do not need to export sysctl_tcp_timestamps, since it is not
used from a module.

In v2, I added Florian feedback and contribution, adding tsoff to
tcp_get_cookie_sock().

v3 removed one unused variable in tcp_v4_connect() as Florian spotted.

Fixes: 95a22caee396c ("tcp: randomize tcp timestamp offsets for each connection")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Florian Westphal <fw@strlen.de>
Tested-by: Florian Westphal <fw@strlen.de>
Cc: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/secure_seq.h | 10 ++++++----
 include/net/tcp.h        |  5 +++--
 net/core/secure_seq.c    | 34 ++++++++++++++++++++--------------
 net/ipv4/syncookies.c    | 12 ++++++++++--
 net/ipv4/tcp_input.c     |  8 +++-----
 net/ipv4/tcp_ipv4.c      | 32 +++++++++++++++++++-------------
 net/ipv6/syncookies.c    | 10 +++++++++-
 net/ipv6/tcp_ipv6.c      | 32 +++++++++++++++++++-------------
 8 files changed, 89 insertions(+), 54 deletions(-)

diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h
index 0caee63..b94006f 100644
--- a/include/net/secure_seq.h
+++ b/include/net/secure_seq.h
@@ -6,10 +6,12 @@
 u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport);
 u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
 			       __be16 dport);
-u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
-			       __be16 sport, __be16 dport, u32 *tsoff);
-u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr,
-				 __be16 sport, __be16 dport, u32 *tsoff);
+u32 secure_tcp_seq(__be32 saddr, __be32 daddr,
+		   __be16 sport, __be16 dport);
+u32 secure_tcp_ts_off(__be32 saddr, __be32 daddr);
+u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr,
+		     __be16 sport, __be16 dport);
+u32 secure_tcpv6_ts_off(const __be32 *saddr, const __be32 *daddr);
 u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr,
 				__be16 sport, __be16 dport);
 u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr,
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 6ec4ea6..6423b46 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -471,7 +471,7 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb);
 /* From syncookies.c */
 struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb,
 				 struct request_sock *req,
-				 struct dst_entry *dst);
+				 struct dst_entry *dst, u32 tsoff);
 int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th,
 		      u32 cookie);
 struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb);
@@ -1816,7 +1816,8 @@ struct tcp_request_sock_ops {
 	struct dst_entry *(*route_req)(const struct sock *sk, struct flowi *fl,
 				       const struct request_sock *req,
 				       bool *strict);
-	__u32 (*init_seq)(const struct sk_buff *skb, u32 *tsoff);
+	u32 (*init_seq)(const struct sk_buff *skb);
+	u32 (*init_ts_off)(const struct sk_buff *skb);
 	int (*send_synack)(const struct sock *sk, struct dst_entry *dst,
 			   struct flowi *fl, struct request_sock *req,
 			   struct tcp_fastopen_cookie *foc,
diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
index d28da7d..ae35cce 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -24,9 +24,13 @@ static siphash_key_t ts_secret __read_mostly;
 
 static __always_inline void net_secret_init(void)
 {
-	net_get_random_once(&ts_secret, sizeof(ts_secret));
 	net_get_random_once(&net_secret, sizeof(net_secret));
 }
+
+static __always_inline void ts_secret_init(void)
+{
+	net_get_random_once(&ts_secret, sizeof(ts_secret));
+}
 #endif
 
 #ifdef CONFIG_INET
@@ -47,7 +51,7 @@ static u32 seq_scale(u32 seq)
 #endif
 
 #if IS_ENABLED(CONFIG_IPV6)
-static u32 secure_tcpv6_ts_off(const __be32 *saddr, const __be32 *daddr)
+u32 secure_tcpv6_ts_off(const __be32 *saddr, const __be32 *daddr)
 {
 	const struct {
 		struct in6_addr saddr;
@@ -60,12 +64,14 @@ static u32 secure_tcpv6_ts_off(const __be32 *saddr, const __be32 *daddr)
 	if (sysctl_tcp_timestamps != 1)
 		return 0;
 
+	ts_secret_init();
 	return siphash(&combined, offsetofend(typeof(combined), daddr),
 		       &ts_secret);
 }
+EXPORT_SYMBOL(secure_tcpv6_ts_off);
 
-u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr,
-				 __be16 sport, __be16 dport, u32 *tsoff)
+u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr,
+		     __be16 sport, __be16 dport)
 {
 	const struct {
 		struct in6_addr saddr;
@@ -78,14 +84,14 @@ u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr,
 		.sport = sport,
 		.dport = dport
 	};
-	u64 hash;
+	u32 hash;
+
 	net_secret_init();
 	hash = siphash(&combined, offsetofend(typeof(combined), dport),
 		       &net_secret);
-	*tsoff = secure_tcpv6_ts_off(saddr, daddr);
 	return seq_scale(hash);
 }
-EXPORT_SYMBOL(secure_tcpv6_sequence_number);
+EXPORT_SYMBOL(secure_tcpv6_seq);
 
 u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
 			       __be16 dport)
@@ -107,30 +113,30 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral);
 #endif
 
 #ifdef CONFIG_INET
-static u32 secure_tcp_ts_off(__be32 saddr, __be32 daddr)
+u32 secure_tcp_ts_off(__be32 saddr, __be32 daddr)
 {
 	if (sysctl_tcp_timestamps != 1)
 		return 0;
 
+	ts_secret_init();
 	return siphash_2u32((__force u32)saddr, (__force u32)daddr,
 			    &ts_secret);
 }
 
-/* secure_tcp_sequence_number(a, b, 0, d) == secure_ipv4_port_ephemeral(a, b, d),
+/* secure_tcp_seq_and_tsoff(a, b, 0, d) == secure_ipv4_port_ephemeral(a, b, d),
  * but fortunately, `sport' cannot be 0 in any circumstances. If this changes,
  * it would be easy enough to have the former function use siphash_4u32, passing
  * the arguments as separate u32.
  */
-
-u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
-			       __be16 sport, __be16 dport, u32 *tsoff)
+u32 secure_tcp_seq(__be32 saddr, __be32 daddr,
+		   __be16 sport, __be16 dport)
 {
-	u64 hash;
+	u32 hash;
+
 	net_secret_init();
 	hash = siphash_3u32((__force u32)saddr, (__force u32)daddr,
 			    (__force u32)sport << 16 | (__force u32)dport,
 			    &net_secret);
-	*tsoff = secure_tcp_ts_off(saddr, daddr);
 	return seq_scale(hash);
 }
 
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 496b97e..0257d96 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -16,6 +16,7 @@
 #include <linux/siphash.h>
 #include <linux/kernel.h>
 #include <linux/export.h>
+#include <net/secure_seq.h>
 #include <net/tcp.h>
 #include <net/route.h>
 
@@ -203,7 +204,7 @@ EXPORT_SYMBOL_GPL(__cookie_v4_check);
 
 struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb,
 				 struct request_sock *req,
-				 struct dst_entry *dst)
+				 struct dst_entry *dst, u32 tsoff)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct sock *child;
@@ -213,6 +214,7 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb,
 						 NULL, &own_req);
 	if (child) {
 		atomic_set(&req->rsk_refcnt, 1);
+		tcp_sk(child)->tsoffset = tsoff;
 		sock_rps_save_rxhash(child, skb);
 		inet_csk_reqsk_queue_add(sk, req, child);
 	} else {
@@ -292,6 +294,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	struct rtable *rt;
 	__u8 rcv_wscale;
 	struct flowi4 fl4;
+	u32 tsoff = 0;
 
 	if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies || !th->ack || th->rst)
 		goto out;
@@ -311,6 +314,11 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	memset(&tcp_opt, 0, sizeof(tcp_opt));
 	tcp_parse_options(skb, &tcp_opt, 0, NULL);
 
+	if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) {
+		tsoff = secure_tcp_ts_off(ip_hdr(skb)->daddr, ip_hdr(skb)->saddr);
+		tcp_opt.rcv_tsecr -= tsoff;
+	}
+
 	if (!cookie_timestamp_decode(&tcp_opt))
 		goto out;
 
@@ -381,7 +389,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	ireq->rcv_wscale  = rcv_wscale;
 	ireq->ecn_ok = cookie_ecn_ok(&tcp_opt, sock_net(sk), &rt->dst);
 
-	ret = tcp_get_cookie_sock(sk, skb, req, &rt->dst);
+	ret = tcp_get_cookie_sock(sk, skb, req, &rt->dst, tsoff);
 	/* ip_queue_xmit() depends on our flow being setup
 	 * Normal sockets get it right from inet_csk_route_child_sock()
 	 */
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 659d1ba..3c6c878 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -85,7 +85,6 @@ int sysctl_tcp_dsack __read_mostly = 1;
 int sysctl_tcp_app_win __read_mostly = 31;
 int sysctl_tcp_adv_win_scale __read_mostly = 1;
 EXPORT_SYMBOL(sysctl_tcp_adv_win_scale);
-EXPORT_SYMBOL(sysctl_tcp_timestamps);
 
 /* rfc5961 challenge ack rate limiting */
 int sysctl_tcp_challenge_ack_limit = 1000;
@@ -6332,8 +6331,8 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	if (security_inet_conn_request(sk, skb, req))
 		goto drop_and_free;
 
-	if (isn && tmp_opt.tstamp_ok)
-		af_ops->init_seq(skb, &tcp_rsk(req)->ts_off);
+	if (tmp_opt.tstamp_ok)
+		tcp_rsk(req)->ts_off = af_ops->init_ts_off(skb);
 
 	if (!want_cookie && !isn) {
 		/* VJ's idea. We save last timestamp seen
@@ -6375,7 +6374,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 			goto drop_and_release;
 		}
 
-		isn = af_ops->init_seq(skb, &tcp_rsk(req)->ts_off);
+		isn = af_ops->init_seq(skb);
 	}
 	if (!dst) {
 		dst = af_ops->route_req(sk, &fl, req, NULL);
@@ -6387,7 +6386,6 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 
 	if (want_cookie) {
 		isn = cookie_init_sequence(af_ops, sk, skb, &req->mss);
-		tcp_rsk(req)->ts_off = 0;
 		req->cookie_ts = tmp_opt.tstamp_ok;
 		if (!tmp_opt.tstamp_ok)
 			inet_rsk(req)->ecn_ok = 0;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 575e19d..1a5fa95 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -94,12 +94,18 @@ static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
 struct inet_hashinfo tcp_hashinfo;
 EXPORT_SYMBOL(tcp_hashinfo);
 
-static u32 tcp_v4_init_sequence(const struct sk_buff *skb, u32 *tsoff)
+static u32 tcp_v4_init_seq(const struct sk_buff *skb)
 {
-	return secure_tcp_sequence_number(ip_hdr(skb)->daddr,
-					  ip_hdr(skb)->saddr,
-					  tcp_hdr(skb)->dest,
-					  tcp_hdr(skb)->source, tsoff);
+	return secure_tcp_seq(ip_hdr(skb)->daddr,
+			      ip_hdr(skb)->saddr,
+			      tcp_hdr(skb)->dest,
+			      tcp_hdr(skb)->source);
+}
+
+static u32 tcp_v4_init_ts_off(const struct sk_buff *skb)
+{
+	return secure_tcp_ts_off(ip_hdr(skb)->daddr,
+				 ip_hdr(skb)->saddr);
 }
 
 int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
@@ -145,7 +151,6 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	struct flowi4 *fl4;
 	struct rtable *rt;
 	int err;
-	u32 seq;
 	struct ip_options_rcu *inet_opt;
 	struct inet_timewait_death_row *tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row;
 
@@ -236,13 +241,13 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	rt = NULL;
 
 	if (likely(!tp->repair)) {
-		seq = secure_tcp_sequence_number(inet->inet_saddr,
-						 inet->inet_daddr,
-						 inet->inet_sport,
-						 usin->sin_port,
-						 &tp->tsoffset);
 		if (!tp->write_seq)
-			tp->write_seq = seq;
+			tp->write_seq = secure_tcp_seq(inet->inet_saddr,
+						       inet->inet_daddr,
+						       inet->inet_sport,
+						       usin->sin_port);
+		tp->tsoffset = secure_tcp_ts_off(inet->inet_saddr,
+						 inet->inet_daddr);
 	}
 
 	inet->inet_id = tp->write_seq ^ jiffies;
@@ -1253,7 +1258,8 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = {
 	.cookie_init_seq =	cookie_v4_init_sequence,
 #endif
 	.route_req	=	tcp_v4_route_req,
-	.init_seq	=	tcp_v4_init_sequence,
+	.init_seq	=	tcp_v4_init_seq,
+	.init_ts_off	=	tcp_v4_init_ts_off,
 	.send_synack	=	tcp_v4_send_synack,
 };
 
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 895ff65..5abc369 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -18,6 +18,7 @@
 #include <linux/random.h>
 #include <linux/siphash.h>
 #include <linux/kernel.h>
+#include <net/secure_seq.h>
 #include <net/ipv6.h>
 #include <net/tcp.h>
 
@@ -143,6 +144,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	int mss;
 	struct dst_entry *dst;
 	__u8 rcv_wscale;
+	u32 tsoff = 0;
 
 	if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies || !th->ack || th->rst)
 		goto out;
@@ -162,6 +164,12 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	memset(&tcp_opt, 0, sizeof(tcp_opt));
 	tcp_parse_options(skb, &tcp_opt, 0, NULL);
 
+	if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) {
+		tsoff = secure_tcpv6_ts_off(ipv6_hdr(skb)->daddr.s6_addr32,
+					    ipv6_hdr(skb)->saddr.s6_addr32);
+		tcp_opt.rcv_tsecr -= tsoff;
+	}
+
 	if (!cookie_timestamp_decode(&tcp_opt))
 		goto out;
 
@@ -242,7 +250,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	ireq->rcv_wscale = rcv_wscale;
 	ireq->ecn_ok = cookie_ecn_ok(&tcp_opt, sock_net(sk), dst);
 
-	ret = tcp_get_cookie_sock(sk, skb, req, dst);
+	ret = tcp_get_cookie_sock(sk, skb, req, dst, tsoff);
 out:
 	return ret;
 out_free:
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 49fa2e8..4c4afdc 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -101,12 +101,18 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
 	}
 }
 
-static u32 tcp_v6_init_sequence(const struct sk_buff *skb, u32 *tsoff)
+static u32 tcp_v6_init_seq(const struct sk_buff *skb)
 {
-	return secure_tcpv6_sequence_number(ipv6_hdr(skb)->daddr.s6_addr32,
-					    ipv6_hdr(skb)->saddr.s6_addr32,
-					    tcp_hdr(skb)->dest,
-					    tcp_hdr(skb)->source, tsoff);
+	return secure_tcpv6_seq(ipv6_hdr(skb)->daddr.s6_addr32,
+				ipv6_hdr(skb)->saddr.s6_addr32,
+				tcp_hdr(skb)->dest,
+				tcp_hdr(skb)->source);
+}
+
+static u32 tcp_v6_init_ts_off(const struct sk_buff *skb)
+{
+	return secure_tcpv6_ts_off(ipv6_hdr(skb)->daddr.s6_addr32,
+				   ipv6_hdr(skb)->saddr.s6_addr32);
 }
 
 static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
@@ -122,7 +128,6 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	struct flowi6 fl6;
 	struct dst_entry *dst;
 	int addr_type;
-	u32 seq;
 	int err;
 	struct inet_timewait_death_row *tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row;
 
@@ -287,13 +292,13 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	sk_set_txhash(sk);
 
 	if (likely(!tp->repair)) {
-		seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32,
-						   sk->sk_v6_daddr.s6_addr32,
-						   inet->inet_sport,
-						   inet->inet_dport,
-						   &tp->tsoffset);
 		if (!tp->write_seq)
-			tp->write_seq = seq;
+			tp->write_seq = secure_tcpv6_seq(np->saddr.s6_addr32,
+							 sk->sk_v6_daddr.s6_addr32,
+							 inet->inet_sport,
+							 inet->inet_dport);
+		tp->tsoffset = secure_tcpv6_ts_off(np->saddr.s6_addr32,
+						   sk->sk_v6_daddr.s6_addr32);
 	}
 
 	if (tcp_fastopen_defer_connect(sk, &err))
@@ -757,7 +762,8 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {
 	.cookie_init_seq =	cookie_v6_init_sequence,
 #endif
 	.route_req	=	tcp_v6_route_req,
-	.init_seq	=	tcp_v6_init_sequence,
+	.init_seq	=	tcp_v6_init_seq,
+	.init_ts_off	=	tcp_v6_init_ts_off,
 	.send_synack	=	tcp_v6_send_synack,
 };
 
-- 
2.7.4


From e1808612a18da824b2d5929ae5673e45b2b9e1a9 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Sat, 6 May 2017 03:49:01 +0300
Subject: [PATCH 15/17] bnxt_en: allocate enough space for ->ntp_fltr_bmap

[ Upstream commit ac45bd93a5035c2f39c9862b8b6ed692db0fdc87 ]

We have the number of longs, but we need to calculate the number of
bytes required.

Fixes: c0c050c58d84 ("bnxt_en: New Broadcom ethernet driver.")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 1f1e54b..2c02a4c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -3000,7 +3000,8 @@ static int bnxt_alloc_ntp_fltrs(struct bnxt *bp)
 		INIT_HLIST_HEAD(&bp->ntp_fltr_hash_tbl[i]);
 
 	bp->ntp_fltr_count = 0;
-	bp->ntp_fltr_bmap = kzalloc(BITS_TO_LONGS(BNXT_NTP_FLTR_MAX_FLTR),
+	bp->ntp_fltr_bmap = kcalloc(BITS_TO_LONGS(BNXT_NTP_FLTR_MAX_FLTR),
+				    sizeof(long),
 				    GFP_KERNEL);
 
 	if (!bp->ntp_fltr_bmap)
-- 
2.7.4


From 4079a2d7cb30b7b509ecdf469ddb1b1a4d8dc96f Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Mon, 8 May 2017 00:04:09 +0200
Subject: [PATCH 16/17] bpf: don't let ldimm64 leak map addresses on
 unprivileged

[ Upstream commit 0d0e57697f162da4aa218b5feafe614fb666db07 ]

The patch fixes two things at once:

1) It checks the env->allow_ptr_leaks and only prints the map address to
   the log if we have the privileges to do so, otherwise it just dumps 0
   as we would when kptr_restrict is enabled on %pK. Given the latter is
   off by default and not every distro sets it, I don't want to rely on
   this, hence the 0 by default for unprivileged.

2) Printing of ldimm64 in the verifier log is currently broken in that
   we don't print the full immediate, but only the 32 bit part of the
   first insn part for ldimm64. Thus, fix this up as well; it's okay to
   access, since we verified all ldimm64 earlier already (including just
   constants) through replace_map_fd_with_map_ptr().

Fixes: 1be7f75d1668 ("bpf: enable non-root eBPF programs")
Fixes: cbd357008604 ("bpf: verifier (add ability to receive verification log)")
Reported-by: Jann Horn <jannh@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c | 21 ++++++++++++++++-----
 1 file changed, 16 insertions(+), 5 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index f27849e..6fd78d4 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -296,7 +296,8 @@ static const char *const bpf_jmp_string[16] = {
 	[BPF_EXIT >> 4] = "exit",
 };
 
-static void print_bpf_insn(struct bpf_insn *insn)
+static void print_bpf_insn(const struct bpf_verifier_env *env,
+			   const struct bpf_insn *insn)
 {
 	u8 class = BPF_CLASS(insn->code);
 
@@ -360,9 +361,19 @@ static void print_bpf_insn(struct bpf_insn *insn)
 				insn->code,
 				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
 				insn->src_reg, insn->imm);
-		} else if (BPF_MODE(insn->code) == BPF_IMM) {
-			verbose("(%02x) r%d = 0x%x\n",
-				insn->code, insn->dst_reg, insn->imm);
+		} else if (BPF_MODE(insn->code) == BPF_IMM &&
+			   BPF_SIZE(insn->code) == BPF_DW) {
+			/* At this point, we already made sure that the second
+			 * part of the ldimm64 insn is accessible.
+			 */
+			u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm;
+			bool map_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD;
+
+			if (map_ptr && !env->allow_ptr_leaks)
+				imm = 0;
+
+			verbose("(%02x) r%d = 0x%llx\n", insn->code,
+				insn->dst_reg, (unsigned long long)imm);
 		} else {
 			verbose("BUG_ld_%02x\n", insn->code);
 			return;
@@ -2835,7 +2846,7 @@ static int do_check(struct bpf_verifier_env *env)
 
 		if (log_level) {
 			verbose("%d: ", insn_idx);
-			print_bpf_insn(insn);
+			print_bpf_insn(env, insn);
 		}
 
 		err = ext_analyzer_insn_hook(env, insn_idx, prev_insn_idx);
-- 
2.7.4


From eb5d5ed1ec5f480f2936249b971bd89f284344ad Mon Sep 17 00:00:00 2001
From: Jon Mason <jon.mason@broadcom.com>
Date: Mon, 8 May 2017 17:48:35 -0400
Subject: [PATCH 17/17] net: mdio-mux: bcm-iproc: call mdiobus_free() in error
 path

[ Upstream commit 922c60e89d52730050c6ccca218bff40cc8bcd8e ]

If an error is encountered in mdio_mux_init(), the error path will call
mdiobus_free().  Since mdiobus_register() has been called prior to
mdio_mux_init(), the bus->state will not be MDIOBUS_UNREGISTERED.  This
causes a BUG_ON() in mdiobus_free().  To correct this issue, add an
error path for mdio_mux_init() which calls mdiobus_unregister() prior to
mdiobus_free().

Signed-off-by: Jon Mason <jon.mason@broadcom.com>
Fixes: 98bc865a1ec8 ("net: mdio-mux: Add MDIO mux driver for iProc SoCs")
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mdio-mux-bcm-iproc.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/mdio-mux-bcm-iproc.c b/drivers/net/phy/mdio-mux-bcm-iproc.c
index 0a04125..0a5f62e 100644
--- a/drivers/net/phy/mdio-mux-bcm-iproc.c
+++ b/drivers/net/phy/mdio-mux-bcm-iproc.c
@@ -203,11 +203,14 @@ static int mdio_mux_iproc_probe(struct platform_device *pdev)
 			   &md->mux_handle, md, md->mii_bus);
 	if (rc) {
 		dev_info(md->dev, "mdiomux initialization failed\n");
-		goto out;
+		goto out_register;
 	}
 
 	dev_info(md->dev, "iProc mdiomux registered\n");
 	return 0;
+
+out_register:
+	mdiobus_unregister(bus);
 out:
 	mdiobus_free(bus);
 	return rc;
-- 
2.7.4

Re: [PATCHES] Networking

[Greg KH]

On Wed, May 10, 2017 at 10:41:30PM -0400, David Miller wrote:
> 
> Please queue up the following networking bug fixes for 4.10
> and 4.11 -stable, respectively.

All queued up, thanks.

greg k-h

Re: [PATCHES] Networking

[Greg KH]

On Wed, May 10, 2017 at 10:41:30PM -0400, David Miller wrote:
> 
> Please queue up the following networking bug fixes for 4.10
> and 4.11 -stable, respectively.

FWY, 4.10 is now dead, so no need to send me any more patches for that
tree.

thanks,

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 103 bytes --]


Please queue up the following networking bug fixes for v4.9 and
v4.11 -stable, respectively.

Thanks!

[-- Attachment #2: net_490.mbox --]
[-- Type: Application/Octet-Stream, Size: 104800 bytes --]

From 2ca052263c72aae73ee2c60bdacee63ac7117ff3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 9 May 2017 06:29:19 -0700
Subject: [PATCH 01/34] dccp/tcp: do not inherit mc_list from parent

[ Upstream commit 657831ffc38e30092a2d5f03d385d710eb88b09a ]

syzkaller found a way to trigger double frees from ip_mc_drop_socket()

It turns out that leave a copy of parent mc_list at accept() time,
which is very bad.

Very similar to commit 8b485ce69876 ("tcp: do not inherit
fastopen_req from parent")

Initial report from Pray3r, completed by Andrey one.
Thanks a lot to them !

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Pray3r <pray3r.z@gmail.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/inet_connection_sock.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 61a9dee..cf3d567 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -665,6 +665,8 @@ struct sock *inet_csk_clone_lock(const struct sock *sk,
 		/* listeners have SOCK_RCU_FREE, not the children */
 		sock_reset_flag(newsk, SOCK_RCU_FREE);
 
+		inet_sk(newsk)->mc_list = NULL;
+
 		newsk->sk_mark = inet_rsk(req)->ir_mark;
 		atomic64_set(&newsk->sk_cookie,
 			     atomic64_read(&inet_rsk(req)->ir_cookie));
-- 
2.9.4


From 286698f0e44c2b7536db4baa1d16ea01ed823e59 Mon Sep 17 00:00:00 2001
From: Gao Feng <gfree.wind@vip.163.com>
Date: Tue, 9 May 2017 18:27:33 +0800
Subject: [PATCH 02/34] driver: vrf: Fix one possible use-after-free issue

[ Upstream commit 1a4a5bf52a4adb477adb075e5afce925824ad132 ]

The current codes only deal with the case that the skb is dropped, it
may meet one use-after-free issue when NF_HOOK returns 0 that means
the skb is stolen by one netfilter rule or hook.

When one netfilter rule or hook stoles the skb and return NF_STOLEN,
it means the skb is taken by the rule, and other modules should not
touch this skb ever. Maybe the skb is queued or freed directly by the
rule.

Now uses the nf_hook instead of NF_HOOK to get the result of netfilter,
and check the return value of nf_hook. Only when its value equals 1, it
means the skb could go ahead. Or reset the skb as NULL.

BTW, because vrf_rcv_finish is empty function, so needn't invoke it
even though nf_hook returns 1. But we need to modify vrf_rcv_finish
to deal with the NF_STOLEN case.

There are two cases when skb is stolen.
1. The skb is stolen and freed directly.
   There is nothing we need to do, and vrf_rcv_finish isn't invoked.
2. The skb is queued and reinjected again.
   The vrf_rcv_finish would be invoked as okfn, so need to free the
   skb in it.

Signed-off-by: Gao Feng <gfree.wind@vip.163.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 80ef486..ee02605 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -850,6 +850,7 @@ static u32 vrf_fib_table(const struct net_device *dev)
 
 static int vrf_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
+	kfree_skb(skb);
 	return 0;
 }
 
@@ -859,7 +860,7 @@ static struct sk_buff *vrf_rcv_nfhook(u8 pf, unsigned int hook,
 {
 	struct net *net = dev_net(dev);
 
-	if (NF_HOOK(pf, hook, net, NULL, skb, dev, NULL, vrf_rcv_finish) < 0)
+	if (nf_hook(pf, hook, net, NULL, skb, dev, NULL, vrf_rcv_finish) != 1)
 		skb = NULL;    /* kfree_skb(skb) handled by nf code */
 
 	return skb;
-- 
2.9.4


From 34638db960863ca49e4cfadf3d0b11f55e9014a9 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Tue, 9 May 2017 16:59:54 -0700
Subject: [PATCH 03/34] ipv6/dccp: do not inherit ipv6_mc_list from parent

[ Upstream commit 83eaddab4378db256d00d295bda6ca997cd13a52 ]

Like commit 657831ffc38e ("dccp/tcp: do not inherit mc_list from parent")
we should clear ipv6_mc_list etc. for IPv6 sockets too.

Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ipv6.c     | 6 ++++++
 net/ipv6/tcp_ipv6.c | 2 ++
 2 files changed, 8 insertions(+)

diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 237d62c..2ac9d2a 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -426,6 +426,9 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk,
 		newsk->sk_backlog_rcv = dccp_v4_do_rcv;
 		newnp->pktoptions  = NULL;
 		newnp->opt	   = NULL;
+		newnp->ipv6_mc_list = NULL;
+		newnp->ipv6_ac_list = NULL;
+		newnp->ipv6_fl_list = NULL;
 		newnp->mcast_oif   = inet6_iif(skb);
 		newnp->mcast_hops  = ipv6_hdr(skb)->hop_limit;
 
@@ -490,6 +493,9 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk,
 	/* Clone RX bits */
 	newnp->rxopt.all = np->rxopt.all;
 
+	newnp->ipv6_mc_list = NULL;
+	newnp->ipv6_ac_list = NULL;
+	newnp->ipv6_fl_list = NULL;
 	newnp->pktoptions = NULL;
 	newnp->opt	  = NULL;
 	newnp->mcast_oif  = inet6_iif(skb);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index b2e61a0..aef9b28 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1046,6 +1046,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 		newtp->af_specific = &tcp_sock_ipv6_mapped_specific;
 #endif
 
+		newnp->ipv6_mc_list = NULL;
 		newnp->ipv6_ac_list = NULL;
 		newnp->ipv6_fl_list = NULL;
 		newnp->pktoptions  = NULL;
@@ -1115,6 +1116,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 	   First: no IPv4 options.
 	 */
 	newinet->inet_opt = NULL;
+	newnp->ipv6_mc_list = NULL;
 	newnp->ipv6_ac_list = NULL;
 	newnp->ipv6_fl_list = NULL;
 
-- 
2.9.4


From a188fd4a9a359146fdb4c57b13acc56800d0ec05 Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.vnet.ibm.com>
Date: Wed, 10 May 2017 19:07:51 +0200
Subject: [PATCH 04/34] s390/qeth: handle sysfs error during initialization

[ Upstream commit 9111e7880ccf419548c7b0887df020b08eadb075 ]

When setting up the device from within the layer discipline's
probe routine, creating the layer-specific sysfs attributes can fail.
Report this error back to the caller, and handle it by
releasing the layer discipline.

Signed-off-by: Ursula Braun <ubraun@linux.vnet.ibm.com>
[jwi: updated commit msg, moved an OSN change to a subsequent patch]
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 4 +++-
 drivers/s390/net/qeth_core_sys.c  | 2 ++
 drivers/s390/net/qeth_l2_main.c   | 5 ++++-
 drivers/s390/net/qeth_l3_main.c   | 5 ++++-
 4 files changed, 13 insertions(+), 3 deletions(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 20cf296..4bf1f60 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -5663,8 +5663,10 @@ static int qeth_core_set_online(struct ccwgroup_device *gdev)
 		if (rc)
 			goto err;
 		rc = card->discipline->setup(card->gdev);
-		if (rc)
+		if (rc) {
+			qeth_core_free_discipline(card);
 			goto err;
+		}
 	}
 	rc = card->discipline->set_online(gdev);
 err:
diff --git a/drivers/s390/net/qeth_core_sys.c b/drivers/s390/net/qeth_core_sys.c
index 75b29fd2..412ff61 100644
--- a/drivers/s390/net/qeth_core_sys.c
+++ b/drivers/s390/net/qeth_core_sys.c
@@ -426,6 +426,8 @@ static ssize_t qeth_dev_layer2_store(struct device *dev,
 		goto out;
 
 	rc = card->discipline->setup(card->gdev);
+	if (rc)
+		qeth_core_free_discipline(card);
 out:
 	mutex_unlock(&card->discipline_mutex);
 	return rc ? rc : count;
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index bb27058..73260a4 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -1024,8 +1024,11 @@ static int qeth_l2_stop(struct net_device *dev)
 static int qeth_l2_probe_device(struct ccwgroup_device *gdev)
 {
 	struct qeth_card *card = dev_get_drvdata(&gdev->dev);
+	int rc;
 
-	qeth_l2_create_device_attributes(&gdev->dev);
+	rc = qeth_l2_create_device_attributes(&gdev->dev);
+	if (rc)
+		return rc;
 	INIT_LIST_HEAD(&card->vid_list);
 	hash_init(card->mac_htable);
 	card->options.layer2 = 1;
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 272d9e7..93fa331 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -3157,8 +3157,11 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
 static int qeth_l3_probe_device(struct ccwgroup_device *gdev)
 {
 	struct qeth_card *card = dev_get_drvdata(&gdev->dev);
+	int rc;
 
-	qeth_l3_create_device_attributes(&gdev->dev);
+	rc = qeth_l3_create_device_attributes(&gdev->dev);
+	if (rc)
+		return rc;
 	card->options.layer2 = 0;
 	card->info.hwtrap = 0;
 	return 0;
-- 
2.9.4


From 17482b309f7dc1e9b3d9b643fbb5397f9a4bec89 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Wed, 10 May 2017 19:07:52 +0200
Subject: [PATCH 05/34] s390/qeth: unbreak OSM and OSN support

[ Upstream commit 2d2ebb3ed0c6acfb014f98e427298673a5d07b82 ]

commit b4d72c08b358 ("qeth: bridgeport support - basic control")
broke the support for OSM and OSN devices as follows:

As OSM and OSN are L2 only, qeth_core_probe_device() does an early
setup by loading the l2 discipline and calling qeth_l2_probe_device().
In this context, adding the l2-specific bridgeport sysfs attributes
via qeth_l2_create_device_attributes() hits a BUG_ON in fs/sysfs/group.c,
since the basic sysfs infrastructure for the device hasn't been
established yet.

Note that OSN actually has its own unique sysfs attributes
(qeth_osn_devtype), so the additional attributes shouldn't be created
at all.
For OSM, add a new qeth_l2_devtype that contains all the common
and l2-specific sysfs attributes.
When qeth_core_probe_device() does early setup for OSM or OSN, assign
the corresponding devtype so that the ccwgroup probe code creates the
full set of sysfs attributes.
This allows us to skip qeth_l2_create_device_attributes() in case
of an early setup.

Any device that can't do early setup will initially have only the
generic sysfs attributes, and when it's probed later
qeth_l2_probe_device() adds the l2-specific attributes.

If an early-setup device is removed (by calling ccwgroup_ungroup()),
device_unregister() will - using the devtype - delete the
l2-specific attributes before qeth_l2_remove_device() is called.
So make sure to not remove them twice.

What complicates the issue is that qeth_l2_probe_device() and
qeth_l2_remove_device() is also called on a device when its
layer2 attribute changes (ie. its layer mode is switched).
For early-setup devices this wouldn't work properly - we wouldn't
remove the l2-specific attributes when switching to L3.
But switching the layer mode doesn't actually make any sense;
we already decided that the device can only operate in L2!
So just refuse to switch the layer mode on such devices. Note that
OSN doesn't have a layer2 attribute, so we only need to special-case
OSM.

Based on an initial patch by Ursula Braun.

Fixes: b4d72c08b358 ("qeth: bridgeport support - basic control")
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core.h      |  4 ++++
 drivers/s390/net/qeth_core_main.c | 17 +++++++++--------
 drivers/s390/net/qeth_core_sys.c  | 22 ++++++++++++++--------
 drivers/s390/net/qeth_l2.h        |  2 ++
 drivers/s390/net/qeth_l2_main.c   | 17 +++++++++++++----
 drivers/s390/net/qeth_l2_sys.c    |  8 ++++++++
 drivers/s390/net/qeth_l3_main.c   |  1 +
 7 files changed, 51 insertions(+), 20 deletions(-)

diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 6d4b68c4..f3756ca 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -718,6 +718,7 @@ enum qeth_discipline_id {
 };
 
 struct qeth_discipline {
+	const struct device_type *devtype;
 	void (*start_poll)(struct ccw_device *, int, unsigned long);
 	qdio_handler_t *input_handler;
 	qdio_handler_t *output_handler;
@@ -893,6 +894,9 @@ extern struct qeth_discipline qeth_l2_discipline;
 extern struct qeth_discipline qeth_l3_discipline;
 extern const struct attribute_group *qeth_generic_attr_groups[];
 extern const struct attribute_group *qeth_osn_attr_groups[];
+extern const struct attribute_group qeth_device_attr_group;
+extern const struct attribute_group qeth_device_blkt_group;
+extern const struct device_type qeth_generic_devtype;
 extern struct workqueue_struct *qeth_wq;
 
 int qeth_card_hw_is_reachable(struct qeth_card *);
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 4bf1f60..e8c4830 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -5462,10 +5462,12 @@ void qeth_core_free_discipline(struct qeth_card *card)
 	card->discipline = NULL;
 }
 
-static const struct device_type qeth_generic_devtype = {
+const struct device_type qeth_generic_devtype = {
 	.name = "qeth_generic",
 	.groups = qeth_generic_attr_groups,
 };
+EXPORT_SYMBOL_GPL(qeth_generic_devtype);
+
 static const struct device_type qeth_osn_devtype = {
 	.name = "qeth_osn",
 	.groups = qeth_osn_attr_groups,
@@ -5591,23 +5593,22 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev)
 		goto err_card;
 	}
 
-	if (card->info.type == QETH_CARD_TYPE_OSN)
-		gdev->dev.type = &qeth_osn_devtype;
-	else
-		gdev->dev.type = &qeth_generic_devtype;
-
 	switch (card->info.type) {
 	case QETH_CARD_TYPE_OSN:
 	case QETH_CARD_TYPE_OSM:
 		rc = qeth_core_load_discipline(card, QETH_DISCIPLINE_LAYER2);
 		if (rc)
 			goto err_card;
+
+		gdev->dev.type = (card->info.type != QETH_CARD_TYPE_OSN)
+					? card->discipline->devtype
+					: &qeth_osn_devtype;
 		rc = card->discipline->setup(card->gdev);
 		if (rc)
 			goto err_disc;
-	case QETH_CARD_TYPE_OSD:
-	case QETH_CARD_TYPE_OSX:
+		break;
 	default:
+		gdev->dev.type = &qeth_generic_devtype;
 		break;
 	}
 
diff --git a/drivers/s390/net/qeth_core_sys.c b/drivers/s390/net/qeth_core_sys.c
index 412ff61..db6a285 100644
--- a/drivers/s390/net/qeth_core_sys.c
+++ b/drivers/s390/net/qeth_core_sys.c
@@ -413,12 +413,16 @@ static ssize_t qeth_dev_layer2_store(struct device *dev,
 
 	if (card->options.layer2 == newdis)
 		goto out;
-	else {
-		card->info.mac_bits  = 0;
-		if (card->discipline) {
-			card->discipline->remove(card->gdev);
-			qeth_core_free_discipline(card);
-		}
+	if (card->info.type == QETH_CARD_TYPE_OSM) {
+		/* fixed layer, can't switch */
+		rc = -EOPNOTSUPP;
+		goto out;
+	}
+
+	card->info.mac_bits = 0;
+	if (card->discipline) {
+		card->discipline->remove(card->gdev);
+		qeth_core_free_discipline(card);
 	}
 
 	rc = qeth_core_load_discipline(card, newdis);
@@ -705,10 +709,11 @@ static struct attribute *qeth_blkt_device_attrs[] = {
 	&dev_attr_inter_jumbo.attr,
 	NULL,
 };
-static struct attribute_group qeth_device_blkt_group = {
+const struct attribute_group qeth_device_blkt_group = {
 	.name = "blkt",
 	.attrs = qeth_blkt_device_attrs,
 };
+EXPORT_SYMBOL_GPL(qeth_device_blkt_group);
 
 static struct attribute *qeth_device_attrs[] = {
 	&dev_attr_state.attr,
@@ -728,9 +733,10 @@ static struct attribute *qeth_device_attrs[] = {
 	&dev_attr_switch_attrs.attr,
 	NULL,
 };
-static struct attribute_group qeth_device_attr_group = {
+const struct attribute_group qeth_device_attr_group = {
 	.attrs = qeth_device_attrs,
 };
+EXPORT_SYMBOL_GPL(qeth_device_attr_group);
 
 const struct attribute_group *qeth_generic_attr_groups[] = {
 	&qeth_device_attr_group,
diff --git a/drivers/s390/net/qeth_l2.h b/drivers/s390/net/qeth_l2.h
index 29d9fb3..0d59f9a 100644
--- a/drivers/s390/net/qeth_l2.h
+++ b/drivers/s390/net/qeth_l2.h
@@ -8,6 +8,8 @@
 
 #include "qeth_core.h"
 
+extern const struct attribute_group *qeth_l2_attr_groups[];
+
 int qeth_l2_create_device_attributes(struct device *);
 void qeth_l2_remove_device_attributes(struct device *);
 void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card);
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 73260a4..cdb0340 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -1021,14 +1021,21 @@ static int qeth_l2_stop(struct net_device *dev)
 	return 0;
 }
 
+static const struct device_type qeth_l2_devtype = {
+	.name = "qeth_layer2",
+	.groups = qeth_l2_attr_groups,
+};
+
 static int qeth_l2_probe_device(struct ccwgroup_device *gdev)
 {
 	struct qeth_card *card = dev_get_drvdata(&gdev->dev);
 	int rc;
 
-	rc = qeth_l2_create_device_attributes(&gdev->dev);
-	if (rc)
-		return rc;
+	if (gdev->dev.type == &qeth_generic_devtype) {
+		rc = qeth_l2_create_device_attributes(&gdev->dev);
+		if (rc)
+			return rc;
+	}
 	INIT_LIST_HEAD(&card->vid_list);
 	hash_init(card->mac_htable);
 	card->options.layer2 = 1;
@@ -1040,7 +1047,8 @@ static void qeth_l2_remove_device(struct ccwgroup_device *cgdev)
 {
 	struct qeth_card *card = dev_get_drvdata(&cgdev->dev);
 
-	qeth_l2_remove_device_attributes(&cgdev->dev);
+	if (cgdev->dev.type == &qeth_generic_devtype)
+		qeth_l2_remove_device_attributes(&cgdev->dev);
 	qeth_set_allowed_threads(card, 0, 1);
 	wait_event(card->wait_q, qeth_threads_running(card, 0xffffffff) == 0);
 
@@ -1437,6 +1445,7 @@ static int qeth_l2_control_event(struct qeth_card *card,
 }
 
 struct qeth_discipline qeth_l2_discipline = {
+	.devtype = &qeth_l2_devtype,
 	.start_poll = qeth_qdio_start_poll,
 	.input_handler = (qdio_handler_t *) qeth_qdio_input_handler,
 	.output_handler = (qdio_handler_t *) qeth_qdio_output_handler,
diff --git a/drivers/s390/net/qeth_l2_sys.c b/drivers/s390/net/qeth_l2_sys.c
index 692db49..a48ed9e 100644
--- a/drivers/s390/net/qeth_l2_sys.c
+++ b/drivers/s390/net/qeth_l2_sys.c
@@ -272,3 +272,11 @@ void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card)
 	} else
 		qeth_bridgeport_an_set(card, 0);
 }
+
+const struct attribute_group *qeth_l2_attr_groups[] = {
+	&qeth_device_attr_group,
+	&qeth_device_blkt_group,
+	/* l2 specific, see l2_{create,remove}_device_attributes(): */
+	&qeth_l2_bridgeport_attr_group,
+	NULL,
+};
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 93fa331..ad4ea58 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -3453,6 +3453,7 @@ static int qeth_l3_control_event(struct qeth_card *card,
 }
 
 struct qeth_discipline qeth_l3_discipline = {
+	.devtype = &qeth_generic_devtype,
 	.start_poll = qeth_qdio_start_poll,
 	.input_handler = (qdio_handler_t *) qeth_qdio_input_handler,
 	.output_handler = (qdio_handler_t *) qeth_qdio_output_handler,
-- 
2.9.4


From 3a3525f16df29db90ead2f09d38abc2c660cb2e1 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Wed, 10 May 2017 19:07:53 +0200
Subject: [PATCH 06/34] s390/qeth: avoid null pointer dereference on OSN

[ Upstream commit 25e2c341e7818a394da9abc403716278ee646014 ]

Access card->dev only after checking whether's its valid.

Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Reviewed-by: Ursula Braun <ubraun@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_l2_main.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index cdb0340..5d010aa 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -1106,7 +1106,6 @@ static int qeth_l2_setup_netdev(struct qeth_card *card)
 	case QETH_CARD_TYPE_OSN:
 		card->dev = alloc_netdev(0, "osn%d", NET_NAME_UNKNOWN,
 					 ether_setup);
-		card->dev->flags |= IFF_NOARP;
 		break;
 	default:
 		card->dev = alloc_etherdev(0);
@@ -1119,9 +1118,12 @@ static int qeth_l2_setup_netdev(struct qeth_card *card)
 	card->dev->watchdog_timeo = QETH_TX_TIMEOUT;
 	card->dev->mtu = card->info.initial_mtu;
 	card->dev->netdev_ops = &qeth_l2_netdev_ops;
-	card->dev->ethtool_ops =
-		(card->info.type != QETH_CARD_TYPE_OSN) ?
-		&qeth_l2_ethtool_ops : &qeth_l2_osn_ops;
+	if (card->info.type == QETH_CARD_TYPE_OSN) {
+		card->dev->ethtool_ops = &qeth_l2_osn_ops;
+		card->dev->flags |= IFF_NOARP;
+	} else {
+		card->dev->ethtool_ops = &qeth_l2_ethtool_ops;
+	}
 	card->dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
 	if (card->info.type == QETH_CARD_TYPE_OSD && !card->info.guestlan) {
 		card->dev->hw_features = NETIF_F_SG;
-- 
2.9.4


From 2f3e1ecafaa43ed22c22643c79e9e7a637a27b19 Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.vnet.ibm.com>
Date: Wed, 10 May 2017 19:07:54 +0200
Subject: [PATCH 07/34] s390/qeth: add missing hash table initializations

[ Upstream commit ebccc7397e4a49ff64c8f44a54895de9d32fe742 ]

commit 5f78e29ceebf ("qeth: optimize IP handling in rx_mode callback")
added new hash tables, but missed to initialize them.

Fixes: 5f78e29ceebf ("qeth: optimize IP handling in rx_mode callback")
Signed-off-by: Ursula Braun <ubraun@linux.vnet.ibm.com>
Reviewed-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_l3_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index ad4ea58..171be5e 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -3162,6 +3162,8 @@ static int qeth_l3_probe_device(struct ccwgroup_device *gdev)
 	rc = qeth_l3_create_device_attributes(&gdev->dev);
 	if (rc)
 		return rc;
+	hash_init(card->ip_htable);
+	hash_init(card->ip_mc_htable);
 	card->options.layer2 = 0;
 	card->info.hwtrap = 0;
 	return 0;
-- 
2.9.4


From fb8d6c6a67b9b4780175567b652edcc82c971bac Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 11 May 2017 01:53:15 +0200
Subject: [PATCH 08/34] bpf, arm64: fix faulty emission of map access in tail
 calls

[ Upstream commit d8b54110ee944de522ccd3531191f39986ec20f9 ]

Shubham was recently asking on netdev why in arm64 JIT we don't multiply
the index for accessing the tail call map by 8. That led me into testing
out arm64 JIT wrt tail calls and it turned out I got a NULL pointer
dereference on the tail call.

The buggy access is at:

  prog = array->ptrs[index];
  if (prog == NULL)
      goto out;

  [...]
  00000060:  d2800e0a  mov x10, #0x70 // #112
  00000064:  f86a682a  ldr x10, [x1,x10]
  00000068:  f862694b  ldr x11, [x10,x2]
  0000006c:  b40000ab  cbz x11, 0x00000080
  [...]

The code triggering the crash is f862694b. x1 at the time contains the
address of the bpf array, x10 offsetof(struct bpf_array, ptrs). Meaning,
above we load the pointer to the program at map slot 0 into x10. x10
can then be NULL if the slot is not occupied, which we later on try to
access with a user given offset in x2 that is the map index.

Fix this by emitting the following instead:

  [...]
  00000060:  d2800e0a  mov x10, #0x70 // #112
  00000064:  8b0a002a  add x10, x1, x10
  00000068:  d37df04b  lsl x11, x2, #3
  0000006c:  f86b694b  ldr x11, [x10,x11]
  00000070:  b40000ab  cbz x11, 0x00000084
  [...]

This basically adds the offset to ptrs to the base address of the bpf
array we got and we later on access the map with an index * 8 offset
relative to that. The tail call map itself is basically one large area
with meta data at the head followed by the array of prog pointers.
This makes tail calls working again, tested on Cavium ThunderX ARMv8.

Fixes: ddb55992b04d ("arm64: bpf: implement bpf_tail_call() helper")
Reported-by: Shubham Bansal <illusionist.neo@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/arm64/net/bpf_jit_comp.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 9c4b57a..d8199e1 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -252,8 +252,9 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	 */
 	off = offsetof(struct bpf_array, ptrs);
 	emit_a64_mov_i64(tmp, off, ctx);
-	emit(A64_LDR64(tmp, r2, tmp), ctx);
-	emit(A64_LDR64(prg, tmp, r3), ctx);
+	emit(A64_ADD(1, tmp, r2, tmp), ctx);
+	emit(A64_LSL(1, prg, r3, 3), ctx);
+	emit(A64_LDR64(prg, tmp, prg), ctx);
 	emit(A64_CBZ(1, prg, jmp_offset), ctx);
 
 	/* goto *(prog->bpf_func + prologue_size); */
-- 
2.9.4


From db1d5eb4a8ea73a74bee551e5f38dfda89534962 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 11 May 2017 15:24:41 -0700
Subject: [PATCH 09/34] netem: fix skb_orphan_partial()

[ Upstream commit f6ba8d33cfbb46df569972e64dbb5bb7e929bfd9 ]

I should have known that lowering skb->truesize was dangerous :/

In case packets are not leaving the host via a standard Ethernet device,
but looped back to local sockets, bad things can happen, as reported
by Michael Madsen ( https://bugzilla.kernel.org/show_bug.cgi?id=195713 )

So instead of tweaking skb->truesize, lets change skb->destructor
and keep a reference on the owner socket via its sk_refcnt.

Fixes: f2f872f9272a ("netem: Introduce skb_orphan_partial() helper")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Michael Madsen <mkm@nabto.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 20 ++++++++------------
 1 file changed, 8 insertions(+), 12 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index 470a204..03dcfc5 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1687,28 +1687,24 @@ EXPORT_SYMBOL(skb_set_owner_w);
  * delay queue. We want to allow the owner socket to send more
  * packets, as if they were already TX completed by a typical driver.
  * But we also want to keep skb->sk set because some packet schedulers
- * rely on it (sch_fq for example). So we set skb->truesize to a small
- * amount (1) and decrease sk_wmem_alloc accordingly.
+ * rely on it (sch_fq for example).
  */
 void skb_orphan_partial(struct sk_buff *skb)
 {
-	/* If this skb is a TCP pure ACK or already went here,
-	 * we have nothing to do. 2 is already a very small truesize.
-	 */
-	if (skb->truesize <= 2)
+	if (skb_is_tcp_pure_ack(skb))
 		return;
 
-	/* TCP stack sets skb->ooo_okay based on sk_wmem_alloc,
-	 * so we do not completely orphan skb, but transfert all
-	 * accounted bytes but one, to avoid unexpected reorders.
-	 */
 	if (skb->destructor == sock_wfree
 #ifdef CONFIG_INET
 	    || skb->destructor == tcp_wfree
 #endif
 		) {
-		atomic_sub(skb->truesize - 1, &skb->sk->sk_wmem_alloc);
-		skb->truesize = 1;
+		struct sock *sk = skb->sk;
+
+		if (atomic_inc_not_zero(&sk->sk_refcnt)) {
+			atomic_sub(skb->truesize, &sk->sk_wmem_alloc);
+			skb->destructor = sock_efree;
+		}
 	} else {
 		skb_orphan(skb);
 	}
-- 
2.9.4


From 933df461acc8558fa074ceca9133053009bc414f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 16 May 2017 13:27:53 -0700
Subject: [PATCH 10/34] net: fix compile error in skb_orphan_partial()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 9142e9007f2d7ab58a587a1e1d921b0064a339aa ]

If CONFIG_INET is not set, net/core/sock.c can not compile :

net/core/sock.c: In function ‘skb_orphan_partial’:
net/core/sock.c:1810:2: error: implicit declaration of function
‘skb_is_tcp_pure_ack’ [-Werror=implicit-function-declaration]
  if (skb_is_tcp_pure_ack(skb))
  ^

Fix this by always including <net/tcp.h>

Fixes: f6ba8d33cfbb ("netem: fix skb_orphan_partial()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index 03dcfc5..1989b3d 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -138,10 +138,7 @@
 
 #include <trace/events/sock.h>
 
-#ifdef CONFIG_INET
 #include <net/tcp.h>
-#endif
-
 #include <net/busy_poll.h>
 
 static DEFINE_MUTEX(proto_list_mutex);
-- 
2.9.4


From 7f856f9b3586ce741f36724991b102b5f7082049 Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Wed, 10 May 2017 17:01:27 -0700
Subject: [PATCH 11/34] tcp: avoid fragmenting peculiar skbs in SACK

[ Upstream commit b451e5d24ba6687c6f0e7319c727a709a1846c06 ]

This patch fixes a bug in splitting an SKB during SACK
processing. Specifically if an skb contains multiple
packets and is only partially sacked in the higher sequences,
tcp_match_sack_to_skb() splits the skb and marks the second fragment
as SACKed.

The current code further attempts rounding up the first fragment
to MSS boundaries. But it misses a boundary condition when the
rounded-up fragment size (pkt_len) is exactly skb size.  Spliting
such an skb is pointless and causses a kernel warning and aborts
the SACK processing. This patch universally checks such over-split
before calling tcp_fragment to prevent these unnecessary warnings.

Fixes: adb92db857ee ("tcp: Make SACK code to split only at mss boundaries")
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 7727ffe..22335d8 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1177,13 +1177,14 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb,
 		 */
 		if (pkt_len > mss) {
 			unsigned int new_len = (pkt_len / mss) * mss;
-			if (!in_sack && new_len < pkt_len) {
+			if (!in_sack && new_len < pkt_len)
 				new_len += mss;
-				if (new_len >= skb->len)
-					return 0;
-			}
 			pkt_len = new_len;
 		}
+
+		if (pkt_len >= skb->len && !in_sack)
+			return 0;
+
 		err = tcp_fragment(sk, skb, pkt_len, mss, GFP_ATOMIC);
 		if (err < 0)
 			return err;
-- 
2.9.4


From d50e84cc2200953839d9af1b13137d0e2efb51dc Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Fri, 12 May 2017 14:39:52 +0800
Subject: [PATCH 12/34] sctp: fix src address selection if using secondary
 addresses for ipv6

[ Upstream commit dbc2b5e9a09e9a6664679a667ff81cff6e5f2641 ]

Commit 0ca50d12fe46 ("sctp: fix src address selection if using secondary
addresses") has fixed a src address selection issue when using secondary
addresses for ipv4.

Now sctp ipv6 also has the similar issue. When using a secondary address,
sctp_v6_get_dst tries to choose the saddr which has the most same bits
with the daddr by sctp_v6_addr_match_len. It may make some cases not work
as expected.

hostA:
  [1] fd21:356b:459a:cf10::11 (eth1)
  [2] fd21:356b:459a:cf20::11 (eth2)

hostB:
  [a] fd21:356b:459a:cf30::2  (eth1)
  [b] fd21:356b:459a:cf40::2  (eth2)

route from hostA to hostB:
  fd21:356b:459a:cf30::/64 dev eth1  metric 1024  mtu 1500

The expected path should be:
  fd21:356b:459a:cf10::11 <-> fd21:356b:459a:cf30::2
But addr[2] matches addr[a] more bits than addr[1] does, according to
sctp_v6_addr_match_len. It causes the path to be:
  fd21:356b:459a:cf20::11 <-> fd21:356b:459a:cf30::2

This patch is to fix it with the same way as Marcelo's fix for sctp ipv4.
As no ip_dev_find for ipv6, this patch is to use ipv6_chk_addr to check
if the saddr is in a dev instead.

Note that for backwards compatibility, it will still do the addr_match_len
check here when no optimal is found.

Reported-by: Patrick Talbert <ptalbert@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ipv6.c | 46 +++++++++++++++++++++++++++++-----------------
 1 file changed, 29 insertions(+), 17 deletions(-)

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 6a2532d..b9cbdf5 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -240,12 +240,10 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 	struct sctp_bind_addr *bp;
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct sctp_sockaddr_entry *laddr;
-	union sctp_addr *baddr = NULL;
 	union sctp_addr *daddr = &t->ipaddr;
 	union sctp_addr dst_saddr;
 	struct in6_addr *final_p, final;
 	__u8 matchlen = 0;
-	__u8 bmatchlen;
 	sctp_scope_t scope;
 
 	memset(fl6, 0, sizeof(struct flowi6));
@@ -312,23 +310,37 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 	 */
 	rcu_read_lock();
 	list_for_each_entry_rcu(laddr, &bp->address_list, list) {
-		if (!laddr->valid)
+		struct dst_entry *bdst;
+		__u8 bmatchlen;
+
+		if (!laddr->valid ||
+		    laddr->state != SCTP_ADDR_SRC ||
+		    laddr->a.sa.sa_family != AF_INET6 ||
+		    scope > sctp_scope(&laddr->a))
 			continue;
-		if ((laddr->state == SCTP_ADDR_SRC) &&
-		    (laddr->a.sa.sa_family == AF_INET6) &&
-		    (scope <= sctp_scope(&laddr->a))) {
-			bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a);
-			if (!baddr || (matchlen < bmatchlen)) {
-				baddr = &laddr->a;
-				matchlen = bmatchlen;
-			}
-		}
-	}
-	if (baddr) {
-		fl6->saddr = baddr->v6.sin6_addr;
-		fl6->fl6_sport = baddr->v6.sin6_port;
+
+		fl6->saddr = laddr->a.v6.sin6_addr;
+		fl6->fl6_sport = laddr->a.v6.sin6_port;
 		final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
-		dst = ip6_dst_lookup_flow(sk, fl6, final_p);
+		bdst = ip6_dst_lookup_flow(sk, fl6, final_p);
+
+		if (!IS_ERR(bdst) &&
+		    ipv6_chk_addr(dev_net(bdst->dev),
+				  &laddr->a.v6.sin6_addr, bdst->dev, 1)) {
+			if (!IS_ERR_OR_NULL(dst))
+				dst_release(dst);
+			dst = bdst;
+			break;
+		}
+
+		bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a);
+		if (matchlen > bmatchlen)
+			continue;
+
+		if (!IS_ERR_OR_NULL(dst))
+			dst_release(dst);
+		dst = bdst;
+		matchlen = bmatchlen;
 	}
 	rcu_read_unlock();
 
-- 
2.9.4


From 8677ec92dd5d28173ebc5509c9b3588d7bc25d50 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 17 May 2017 07:16:40 -0700
Subject: [PATCH 13/34] sctp: do not inherit ipv6_{mc|ac|fl}_list from parent

[ Upstream commit fdcee2cbb8438702ea1b328fb6e0ac5e9a40c7f8 ]

SCTP needs fixes similar to 83eaddab4378 ("ipv6/dccp: do not inherit
ipv6_mc_list from parent"), otherwise bad things can happen.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ipv6.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index b9cbdf5..0c09060 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -678,6 +678,9 @@ static struct sock *sctp_v6_create_accept_sk(struct sock *sk,
 	newnp = inet6_sk(newsk);
 
 	memcpy(newnp, np, sizeof(struct ipv6_pinfo));
+	newnp->ipv6_mc_list = NULL;
+	newnp->ipv6_ac_list = NULL;
+	newnp->ipv6_fl_list = NULL;
 
 	rcu_read_lock();
 	opt = rcu_dereference(np->opt);
-- 
2.9.4


From 2663eeeabadd30142b70f1dd85071d58aa961684 Mon Sep 17 00:00:00 2001
From: Douglas Caetano dos Santos <douglascs@taghos.com.br>
Date: Fri, 12 May 2017 15:19:15 -0300
Subject: [PATCH 14/34] net/packet: fix missing net_device reference release

[ Upstream commit d19b183cdc1fa3d70d6abe2a4c369e748cd7ebb8 ]

When using a TX ring buffer, if an error occurs processing a control
message (e.g. invalid message), the net_device reference is not
released.

Fixes c14ac9451c348 ("sock: enable timestamping using control messages")
Signed-off-by: Douglas Caetano dos Santos <douglascs@taghos.com.br>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index cb76ff3..6a563e6 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2652,13 +2652,6 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 		dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex);
 	}
 
-	sockc.tsflags = po->sk.sk_tsflags;
-	if (msg->msg_controllen) {
-		err = sock_cmsg_send(&po->sk, msg, &sockc);
-		if (unlikely(err))
-			goto out;
-	}
-
 	err = -ENXIO;
 	if (unlikely(dev == NULL))
 		goto out;
@@ -2666,6 +2659,13 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 	if (unlikely(!(dev->flags & IFF_UP)))
 		goto out_put;
 
+	sockc.tsflags = po->sk.sk_tsflags;
+	if (msg->msg_controllen) {
+		err = sock_cmsg_send(&po->sk, msg, &sockc);
+		if (unlikely(err))
+			goto out_put;
+	}
+
 	if (po->sk.sk_socket->type == SOCK_RAW)
 		reserve = dev->hard_header_len;
 	size_max = po->tx_ring.frame_size
-- 
2.9.4


From 12d6f6826d311d9bc7d8de4b6004118a0f443638 Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Mon, 3 Apr 2017 15:11:22 +0300
Subject: [PATCH 15/34] net/mlx5e: Use the correct pause values for ethtool
 advertising

[ Upstream commit b383b544f2666d67446b951a9a97af239dafed5d ]

Query the operational pause from firmware (PFCC register) instead of
always passing zeros.

Fixes: 665bc53969d7 ("net/mlx5e: Use new ethtool get/set link ksettings API")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Cc: kernel-team@fb.com
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 126cfeb..6a9155f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -806,6 +806,8 @@ static int mlx5e_get_link_ksettings(struct net_device *netdev,
 	struct mlx5e_priv *priv    = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
 	u32 out[MLX5_ST_SZ_DW(ptys_reg)] = {0};
+	u32 rx_pause = 0;
+	u32 tx_pause = 0;
 	u32 eth_proto_cap;
 	u32 eth_proto_admin;
 	u32 eth_proto_lp;
@@ -828,11 +830,13 @@ static int mlx5e_get_link_ksettings(struct net_device *netdev,
 	an_disable_admin = MLX5_GET(ptys_reg, out, an_disable_admin);
 	an_status        = MLX5_GET(ptys_reg, out, an_status);
 
+	mlx5_query_port_pause(mdev, &rx_pause, &tx_pause);
+
 	ethtool_link_ksettings_zero_link_mode(link_ksettings, supported);
 	ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising);
 
 	get_supported(eth_proto_cap, link_ksettings);
-	get_advertising(eth_proto_admin, 0, 0, link_ksettings);
+	get_advertising(eth_proto_admin, tx_pause, rx_pause, link_ksettings);
 	get_speed_duplex(netdev, eth_proto_oper, link_ksettings);
 
 	eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap;
-- 
2.9.4


From 7554d13a33a4570a19e39677a796224425c0c20a Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Wed, 19 Apr 2017 14:35:15 +0300
Subject: [PATCH 16/34] net/mlx5e: Fix ethtool pause support and advertise
 reporting

[ Upstream commit e3c19503712d6360239b19c14cded56dd63c40d7 ]

Pause bit should set when RX pause is on, not TX pause.
Also, setting Asym_Pause is incorrect, and should be turned off.

Fixes: 665bc53969d7 ("net/mlx5e: Use new ethtool get/set link ksettings API")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Cc: kernel-team@fb.com
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 6a9155f..3744e2f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -751,7 +751,6 @@ static void get_supported(u32 eth_proto_cap,
 	ptys2ethtool_supported_port(link_ksettings, eth_proto_cap);
 	ptys2ethtool_supported_link(supported, eth_proto_cap);
 	ethtool_link_ksettings_add_link_mode(link_ksettings, supported, Pause);
-	ethtool_link_ksettings_add_link_mode(link_ksettings, supported, Asym_Pause);
 }
 
 static void get_advertising(u32 eth_proto_cap, u8 tx_pause,
@@ -761,7 +760,7 @@ static void get_advertising(u32 eth_proto_cap, u8 tx_pause,
 	unsigned long *advertising = link_ksettings->link_modes.advertising;
 
 	ptys2ethtool_adver_link(advertising, eth_proto_cap);
-	if (tx_pause)
+	if (rx_pause)
 		ethtool_link_ksettings_add_link_mode(link_ksettings, advertising, Pause);
 	if (tx_pause ^ rx_pause)
 		ethtool_link_ksettings_add_link_mode(link_ksettings, advertising, Asym_Pause);
-- 
2.9.4


From c63749a85e47fd08b8f96bb184415fe49a25acaa Mon Sep 17 00:00:00 2001
From: Soheil Hassas Yeganeh <soheil@google.com>
Date: Mon, 15 May 2017 17:05:47 -0400
Subject: [PATCH 17/34] tcp: eliminate negative reordering in
 tcp_clean_rtx_queue

[ Upstream commit bafbb9c73241760023d8981191ddd30bb1c6dbac ]

tcp_ack() can call tcp_fragment() which may dededuct the
value tp->fackets_out when MSS changes. When prior_fackets
is larger than tp->fackets_out, tcp_clean_rtx_queue() can
invoke tcp_update_reordering() with negative values. This
results in absurd tp->reodering values higher than
sysctl_tcp_max_reordering.

Note that tcp_update_reordering indeeds sets tp->reordering
to min(sysctl_tcp_max_reordering, metric), but because
the comparison is signed, a negative metric always wins.

Fixes: c7caf8d3ed7a ("[TCP]: Fix reord detection due to snd_una covered holes")
Reported-by: Rebecca Isaacs <risaacs@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 22335d8..01336aa 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3233,7 +3233,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 			int delta;
 
 			/* Non-retransmitted hole got filled? That's reordering */
-			if (reord < prior_fackets)
+			if (reord < prior_fackets && reord <= tp->fackets_out)
 				tcp_update_reordering(sk, tp->fackets_out - reord, 0);
 
 			delta = tcp_is_fack(tp) ? pkts_acked :
-- 
2.9.4


From 55768df67560e44714599a2fe2d2a7ad2d6e9c48 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Mon, 15 May 2017 23:19:17 -0700
Subject: [PATCH 18/34] net: Improve handling of failures on link and route
 dumps

[ Upstream commit f6c5775ff0bfa62b072face6bf1d40f659f194b2 ]

In general, rtnetlink dumps do not anticipate failure to dump a single
object (e.g., link or route) on a single pass. As both route and link
objects have grown via more attributes, that is no longer a given.

netlink dumps can handle a failure if the dump function returns an
error; specifically, netlink_dump adds the return code to the response
if it is <= 0 so userspace is notified of the failure. The missing
piece is the rtnetlink dump functions returning the error.

Fix route and link dump functions to return the errors if no object is
added to an skb (detected by skb->len != 0). IPv6 route dumps
(rt6_dump_route) already return the error; this patch updates IPv4 and
link dumps. Other dump functions may need to be ajusted as well.

Reported-by: Jan Moskyto Matejka <mq@ucw.cz>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c    | 36 ++++++++++++++++++++++++------------
 net/ipv4/fib_frontend.c | 15 +++++++++++----
 net/ipv4/fib_trie.c     | 26 ++++++++++++++------------
 3 files changed, 49 insertions(+), 28 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index b490af6..1d91607 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1617,13 +1617,13 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 					       cb->nlh->nlmsg_seq, 0,
 					       flags,
 					       ext_filter_mask);
-			/* If we ran out of room on the first message,
-			 * we're in trouble
-			 */
-			WARN_ON((err == -EMSGSIZE) && (skb->len == 0));
 
-			if (err < 0)
-				goto out;
+			if (err < 0) {
+				if (likely(skb->len))
+					goto out;
+
+				goto out_err;
+			}
 
 			nl_dump_check_consistent(cb, nlmsg_hdr(skb));
 cont:
@@ -1631,10 +1631,12 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 		}
 	}
 out:
+	err = skb->len;
+out_err:
 	cb->args[1] = idx;
 	cb->args[0] = h;
 
-	return skb->len;
+	return err;
 }
 
 int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len)
@@ -3413,8 +3415,12 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb)
 				err = br_dev->netdev_ops->ndo_bridge_getlink(
 						skb, portid, seq, dev,
 						filter_mask, NLM_F_MULTI);
-				if (err < 0 && err != -EOPNOTSUPP)
-					break;
+				if (err < 0 && err != -EOPNOTSUPP) {
+					if (likely(skb->len))
+						break;
+
+					goto out_err;
+				}
 			}
 			idx++;
 		}
@@ -3425,16 +3431,22 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb)
 							      seq, dev,
 							      filter_mask,
 							      NLM_F_MULTI);
-				if (err < 0 && err != -EOPNOTSUPP)
-					break;
+				if (err < 0 && err != -EOPNOTSUPP) {
+					if (likely(skb->len))
+						break;
+
+					goto out_err;
+				}
 			}
 			idx++;
 		}
 	}
+	err = skb->len;
+out_err:
 	rcu_read_unlock();
 	cb->args[0] = idx;
 
-	return skb->len;
+	return err;
 }
 
 static inline size_t bridge_nlmsg_size(void)
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 6789e48..3d92534 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -758,7 +758,7 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 	unsigned int e = 0, s_e;
 	struct fib_table *tb;
 	struct hlist_head *head;
-	int dumped = 0;
+	int dumped = 0, err;
 
 	if (nlmsg_len(cb->nlh) >= sizeof(struct rtmsg) &&
 	    ((struct rtmsg *) nlmsg_data(cb->nlh))->rtm_flags & RTM_F_CLONED)
@@ -778,20 +778,27 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 			if (dumped)
 				memset(&cb->args[2], 0, sizeof(cb->args) -
 						 2 * sizeof(cb->args[0]));
-			if (fib_table_dump(tb, skb, cb) < 0)
-				goto out;
+			err = fib_table_dump(tb, skb, cb);
+			if (err < 0) {
+				if (likely(skb->len))
+					goto out;
+
+				goto out_err;
+			}
 			dumped = 1;
 next:
 			e++;
 		}
 	}
 out:
+	err = skb->len;
+out_err:
 	rcu_read_unlock();
 
 	cb->args[1] = e;
 	cb->args[0] = h;
 
-	return skb->len;
+	return err;
 }
 
 /* Prepare and feed intra-kernel routing request.
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index e3665bf..ef40bb6 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1932,6 +1932,8 @@ static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb,
 
 	/* rcu_read_lock is hold by caller */
 	hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) {
+		int err;
+
 		if (i < s_i) {
 			i++;
 			continue;
@@ -1942,17 +1944,14 @@ static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb,
 			continue;
 		}
 
-		if (fib_dump_info(skb, NETLINK_CB(cb->skb).portid,
-				  cb->nlh->nlmsg_seq,
-				  RTM_NEWROUTE,
-				  tb->tb_id,
-				  fa->fa_type,
-				  xkey,
-				  KEYLENGTH - fa->fa_slen,
-				  fa->fa_tos,
-				  fa->fa_info, NLM_F_MULTI) < 0) {
+		err = fib_dump_info(skb, NETLINK_CB(cb->skb).portid,
+				    cb->nlh->nlmsg_seq, RTM_NEWROUTE,
+				    tb->tb_id, fa->fa_type,
+				    xkey, KEYLENGTH - fa->fa_slen,
+				    fa->fa_tos, fa->fa_info, NLM_F_MULTI);
+		if (err < 0) {
 			cb->args[4] = i;
-			return -1;
+			return err;
 		}
 		i++;
 	}
@@ -1974,10 +1973,13 @@ int fib_table_dump(struct fib_table *tb, struct sk_buff *skb,
 	t_key key = cb->args[3];
 
 	while ((l = leaf_walk_rcu(&tp, key)) != NULL) {
-		if (fn_trie_dump_leaf(l, tb, skb, cb) < 0) {
+		int err;
+
+		err = fn_trie_dump_leaf(l, tb, skb, cb);
+		if (err < 0) {
 			cb->args[3] = key;
 			cb->args[2] = count;
-			return -1;
+			return err;
 		}
 
 		++count;
-- 
2.9.4


From 1dbeca5d1881c63bbf931f61020b1f5865935a5b Mon Sep 17 00:00:00 2001
From: Craig Gallek <kraig@google.com>
Date: Tue, 16 May 2017 14:36:23 -0400
Subject: [PATCH 19/34] ipv6: Prevent overrun when parsing v6 header options

[ Upstream commit 2423496af35d94a87156b063ea5cedffc10a70a1 ]

The KASAN warning repoted below was discovered with a syzkaller
program.  The reproducer is basically:
  int s = socket(AF_INET6, SOCK_RAW, NEXTHDR_HOP);
  send(s, &one_byte_of_data, 1, MSG_MORE);
  send(s, &more_than_mtu_bytes_data, 2000, 0);

The socket() call sets the nexthdr field of the v6 header to
NEXTHDR_HOP, the first send call primes the payload with a non zero
byte of data, and the second send call triggers the fragmentation path.

The fragmentation code tries to parse the header options in order
to figure out where to insert the fragment option.  Since nexthdr points
to an invalid option, the calculation of the size of the network header
can made to be much larger than the linear section of the skb and data
is read outside of it.

This fix makes ip6_find_1stfrag return an error if it detects
running out-of-bounds.

[   42.361487] ==================================================================
[   42.364412] BUG: KASAN: slab-out-of-bounds in ip6_fragment+0x11c8/0x3730
[   42.365471] Read of size 840 at addr ffff88000969e798 by task ip6_fragment-oo/3789
[   42.366469]
[   42.366696] CPU: 1 PID: 3789 Comm: ip6_fragment-oo Not tainted 4.11.0+ #41
[   42.367628] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.1-1ubuntu1 04/01/2014
[   42.368824] Call Trace:
[   42.369183]  dump_stack+0xb3/0x10b
[   42.369664]  print_address_description+0x73/0x290
[   42.370325]  kasan_report+0x252/0x370
[   42.370839]  ? ip6_fragment+0x11c8/0x3730
[   42.371396]  check_memory_region+0x13c/0x1a0
[   42.371978]  memcpy+0x23/0x50
[   42.372395]  ip6_fragment+0x11c8/0x3730
[   42.372920]  ? nf_ct_expect_unregister_notifier+0x110/0x110
[   42.373681]  ? ip6_copy_metadata+0x7f0/0x7f0
[   42.374263]  ? ip6_forward+0x2e30/0x2e30
[   42.374803]  ip6_finish_output+0x584/0x990
[   42.375350]  ip6_output+0x1b7/0x690
[   42.375836]  ? ip6_finish_output+0x990/0x990
[   42.376411]  ? ip6_fragment+0x3730/0x3730
[   42.376968]  ip6_local_out+0x95/0x160
[   42.377471]  ip6_send_skb+0xa1/0x330
[   42.377969]  ip6_push_pending_frames+0xb3/0xe0
[   42.378589]  rawv6_sendmsg+0x2051/0x2db0
[   42.379129]  ? rawv6_bind+0x8b0/0x8b0
[   42.379633]  ? _copy_from_user+0x84/0xe0
[   42.380193]  ? debug_check_no_locks_freed+0x290/0x290
[   42.380878]  ? ___sys_sendmsg+0x162/0x930
[   42.381427]  ? rcu_read_lock_sched_held+0xa3/0x120
[   42.382074]  ? sock_has_perm+0x1f6/0x290
[   42.382614]  ? ___sys_sendmsg+0x167/0x930
[   42.383173]  ? lock_downgrade+0x660/0x660
[   42.383727]  inet_sendmsg+0x123/0x500
[   42.384226]  ? inet_sendmsg+0x123/0x500
[   42.384748]  ? inet_recvmsg+0x540/0x540
[   42.385263]  sock_sendmsg+0xca/0x110
[   42.385758]  SYSC_sendto+0x217/0x380
[   42.386249]  ? SYSC_connect+0x310/0x310
[   42.386783]  ? __might_fault+0x110/0x1d0
[   42.387324]  ? lock_downgrade+0x660/0x660
[   42.387880]  ? __fget_light+0xa1/0x1f0
[   42.388403]  ? __fdget+0x18/0x20
[   42.388851]  ? sock_common_setsockopt+0x95/0xd0
[   42.389472]  ? SyS_setsockopt+0x17f/0x260
[   42.390021]  ? entry_SYSCALL_64_fastpath+0x5/0xbe
[   42.390650]  SyS_sendto+0x40/0x50
[   42.391103]  entry_SYSCALL_64_fastpath+0x1f/0xbe
[   42.391731] RIP: 0033:0x7fbbb711e383
[   42.392217] RSP: 002b:00007ffff4d34f28 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
[   42.393235] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007fbbb711e383
[   42.394195] RDX: 0000000000001000 RSI: 00007ffff4d34f60 RDI: 0000000000000003
[   42.395145] RBP: 0000000000000046 R08: 00007ffff4d34f40 R09: 0000000000000018
[   42.396056] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000400aad
[   42.396598] R13: 0000000000000066 R14: 00007ffff4d34ee0 R15: 00007fbbb717af00
[   42.397257]
[   42.397411] Allocated by task 3789:
[   42.397702]  save_stack_trace+0x16/0x20
[   42.398005]  save_stack+0x46/0xd0
[   42.398267]  kasan_kmalloc+0xad/0xe0
[   42.398548]  kasan_slab_alloc+0x12/0x20
[   42.398848]  __kmalloc_node_track_caller+0xcb/0x380
[   42.399224]  __kmalloc_reserve.isra.32+0x41/0xe0
[   42.399654]  __alloc_skb+0xf8/0x580
[   42.400003]  sock_wmalloc+0xab/0xf0
[   42.400346]  __ip6_append_data.isra.41+0x2472/0x33d0
[   42.400813]  ip6_append_data+0x1a8/0x2f0
[   42.401122]  rawv6_sendmsg+0x11ee/0x2db0
[   42.401505]  inet_sendmsg+0x123/0x500
[   42.401860]  sock_sendmsg+0xca/0x110
[   42.402209]  ___sys_sendmsg+0x7cb/0x930
[   42.402582]  __sys_sendmsg+0xd9/0x190
[   42.402941]  SyS_sendmsg+0x2d/0x50
[   42.403273]  entry_SYSCALL_64_fastpath+0x1f/0xbe
[   42.403718]
[   42.403871] Freed by task 1794:
[   42.404146]  save_stack_trace+0x16/0x20
[   42.404515]  save_stack+0x46/0xd0
[   42.404827]  kasan_slab_free+0x72/0xc0
[   42.405167]  kfree+0xe8/0x2b0
[   42.405462]  skb_free_head+0x74/0xb0
[   42.405806]  skb_release_data+0x30e/0x3a0
[   42.406198]  skb_release_all+0x4a/0x60
[   42.406563]  consume_skb+0x113/0x2e0
[   42.406910]  skb_free_datagram+0x1a/0xe0
[   42.407288]  netlink_recvmsg+0x60d/0xe40
[   42.407667]  sock_recvmsg+0xd7/0x110
[   42.408022]  ___sys_recvmsg+0x25c/0x580
[   42.408395]  __sys_recvmsg+0xd6/0x190
[   42.408753]  SyS_recvmsg+0x2d/0x50
[   42.409086]  entry_SYSCALL_64_fastpath+0x1f/0xbe
[   42.409513]
[   42.409665] The buggy address belongs to the object at ffff88000969e780
[   42.409665]  which belongs to the cache kmalloc-512 of size 512
[   42.410846] The buggy address is located 24 bytes inside of
[   42.410846]  512-byte region [ffff88000969e780, ffff88000969e980)
[   42.411941] The buggy address belongs to the page:
[   42.412405] page:ffffea000025a780 count:1 mapcount:0 mapping:          (null) index:0x0 compound_mapcount: 0
[   42.413298] flags: 0x100000000008100(slab|head)
[   42.413729] raw: 0100000000008100 0000000000000000 0000000000000000 00000001800c000c
[   42.414387] raw: ffffea00002a9500 0000000900000007 ffff88000c401280 0000000000000000
[   42.415074] page dumped because: kasan: bad access detected
[   42.415604]
[   42.415757] Memory state around the buggy address:
[   42.416222]  ffff88000969e880: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[   42.416904]  ffff88000969e900: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[   42.417591] >ffff88000969e980: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[   42.418273]                    ^
[   42.418588]  ffff88000969ea00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[   42.419273]  ffff88000969ea80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[   42.419882] ==================================================================

Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Craig Gallek <kraig@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_offload.c |  2 ++
 net/ipv6/ip6_output.c  |  4 ++++
 net/ipv6/output_core.c | 14 ++++++++------
 net/ipv6/udp_offload.c |  2 ++
 4 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 33b04ec..9881a87 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -117,6 +117,8 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 
 		if (udpfrag) {
 			unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr);
+			if (unfrag_ip6hlen < 0)
+				return ERR_PTR(unfrag_ip6hlen);
 			fptr = (struct frag_hdr *)((u8 *)ipv6h + unfrag_ip6hlen);
 			fptr->frag_off = htons(offset);
 			if (skb->next)
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index e27b8fd..6e0bb77 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -587,6 +587,10 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 	u8 *prevhdr, nexthdr = 0;
 
 	hlen = ip6_find_1stfragopt(skb, &prevhdr);
+	if (hlen < 0) {
+		err = hlen;
+		goto fail;
+	}
 	nexthdr = *prevhdr;
 
 	mtu = ip6_skb_dst_mtu(skb);
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index cd42523..e9065b8 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -79,14 +79,13 @@ EXPORT_SYMBOL(ipv6_select_ident);
 int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 {
 	u16 offset = sizeof(struct ipv6hdr);
-	struct ipv6_opt_hdr *exthdr =
-				(struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1);
 	unsigned int packet_len = skb_tail_pointer(skb) -
 		skb_network_header(skb);
 	int found_rhdr = 0;
 	*nexthdr = &ipv6_hdr(skb)->nexthdr;
 
-	while (offset + 1 <= packet_len) {
+	while (offset <= packet_len) {
+		struct ipv6_opt_hdr *exthdr;
 
 		switch (**nexthdr) {
 
@@ -107,13 +106,16 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 			return offset;
 		}
 
-		offset += ipv6_optlen(exthdr);
-		*nexthdr = &exthdr->nexthdr;
+		if (offset + sizeof(struct ipv6_opt_hdr) > packet_len)
+			return -EINVAL;
+
 		exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) +
 						 offset);
+		offset += ipv6_optlen(exthdr);
+		*nexthdr = &exthdr->nexthdr;
 	}
 
-	return offset;
+	return -EINVAL;
 }
 EXPORT_SYMBOL(ip6_find_1stfragopt);
 
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index ac858c4..b348cff 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -91,6 +91,8 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 		 * bytes to insert fragment header.
 		 */
 		unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr);
+		if (unfrag_ip6hlen < 0)
+			return ERR_PTR(unfrag_ip6hlen);
 		nexthdr = *prevhdr;
 		*prevhdr = NEXTHDR_FRAGMENT;
 		unfrag_len = (skb_network_header(skb) - skb_mac_header(skb)) +
-- 
2.9.4


From a1c28966475e0b154d8951797191b7cb3bce5993 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Wed, 17 May 2017 22:54:11 -0400
Subject: [PATCH 20/34] ipv6: Check ip6_find_1stfragopt() return value
 properly.

[ Upstream commit 7dd7eb9513bd02184d45f000ab69d78cb1fa1531 ]

Do not use unsigned variables to see if it returns a negative
error or not.

Fixes: 2423496af35d ("ipv6: Prevent overrun when parsing v6 header options")
Reported-by: Julia Lawall <julia.lawall@lip6.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_offload.c | 9 ++++-----
 net/ipv6/ip6_output.c  | 7 +++----
 net/ipv6/udp_offload.c | 8 +++++---
 3 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 9881a87..013086b 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -63,7 +63,6 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 	const struct net_offload *ops;
 	int proto;
 	struct frag_hdr *fptr;
-	unsigned int unfrag_ip6hlen;
 	unsigned int payload_len;
 	u8 *prevhdr;
 	int offset = 0;
@@ -116,10 +115,10 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 		skb->network_header = (u8 *)ipv6h - skb->head;
 
 		if (udpfrag) {
-			unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr);
-			if (unfrag_ip6hlen < 0)
-				return ERR_PTR(unfrag_ip6hlen);
-			fptr = (struct frag_hdr *)((u8 *)ipv6h + unfrag_ip6hlen);
+			int err = ip6_find_1stfragopt(skb, &prevhdr);
+			if (err < 0)
+				return ERR_PTR(err);
+			fptr = (struct frag_hdr *)((u8 *)ipv6h + err);
 			fptr->frag_off = htons(offset);
 			if (skb->next)
 				fptr->frag_off |= htons(IP6_MF);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 6e0bb77..b1e8ee5 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -586,11 +586,10 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 	int ptr, offset = 0, err = 0;
 	u8 *prevhdr, nexthdr = 0;
 
-	hlen = ip6_find_1stfragopt(skb, &prevhdr);
-	if (hlen < 0) {
-		err = hlen;
+	err = ip6_find_1stfragopt(skb, &prevhdr);
+	if (err < 0)
 		goto fail;
-	}
+	hlen = err;
 	nexthdr = *prevhdr;
 
 	mtu = ip6_skb_dst_mtu(skb);
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index b348cff..a2267f8 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -29,6 +29,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 	u8 frag_hdr_sz = sizeof(struct frag_hdr);
 	__wsum csum;
 	int tnl_hlen;
+	int err;
 
 	mss = skb_shinfo(skb)->gso_size;
 	if (unlikely(skb->len <= mss))
@@ -90,9 +91,10 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 		/* Find the unfragmentable header and shift it left by frag_hdr_sz
 		 * bytes to insert fragment header.
 		 */
-		unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr);
-		if (unfrag_ip6hlen < 0)
-			return ERR_PTR(unfrag_ip6hlen);
+		err = ip6_find_1stfragopt(skb, &prevhdr);
+		if (err < 0)
+			return ERR_PTR(err);
+		unfrag_ip6hlen = err;
 		nexthdr = *prevhdr;
 		*prevhdr = NEXTHDR_FRAGMENT;
 		unfrag_len = (skb_network_header(skb) - skb_mac_header(skb)) +
-- 
2.9.4


From ae4ec172d2f70cc3b951b97e2433864983205ac7 Mon Sep 17 00:00:00 2001
From: Tobias Jungel <tobias.jungel@bisdn.de>
Date: Wed, 17 May 2017 09:29:12 +0200
Subject: [PATCH 21/34] bridge: netlink: check vlan_default_pvid range

[ Upstream commit a285860211bf257b0e6d522dac6006794be348af ]

Currently it is allowed to set the default pvid of a bridge to a value
above VLAN_VID_MASK (0xfff). This patch adds a check to br_validate and
returns -EINVAL in case the pvid is out of bounds.

Reproduce by calling:

[root@test ~]# ip l a type bridge
[root@test ~]# ip l a type dummy
[root@test ~]# ip l s bridge0 type bridge vlan_filtering 1
[root@test ~]# ip l s bridge0 type bridge vlan_default_pvid 9999
[root@test ~]# ip l s dummy0 master bridge0
[root@test ~]# bridge vlan
port	vlan ids
bridge0	 9999 PVID Egress Untagged

dummy0	 9999 PVID Egress Untagged

Fixes: 0f963b7592ef ("bridge: netlink: add support for default_pvid")
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: Tobias Jungel <tobias.jungel@bisdn.de>
Acked-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_netlink.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 0474106..7625ec8 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -776,6 +776,13 @@ static int br_validate(struct nlattr *tb[], struct nlattr *data[])
 			return -EPROTONOSUPPORT;
 		}
 	}
+
+	if (data[IFLA_BR_VLAN_DEFAULT_PVID]) {
+		__u16 defpvid = nla_get_u16(data[IFLA_BR_VLAN_DEFAULT_PVID]);
+
+		if (defpvid >= VLAN_VID_MASK)
+			return -EINVAL;
+	}
 #endif
 
 	return 0;
-- 
2.9.4


From 46cc5f6f3dd1b060cc9954984316f6bde3f7bf34 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Wed, 17 May 2017 16:31:41 +0200
Subject: [PATCH 22/34] qmi_wwan: add another Lenovo EM74xx device ID
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 486181bcb3248e2f1977f4e69387a898234a4e1e ]

In their infinite wisdom, and never ending quest for end user frustration,
Lenovo has decided to use a new USB device ID for the wwan modules in
their 2017 laptops.  The actual hardware is still the Sierra Wireless
EM7455 or EM7430, depending on region.

Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 34d997c..2f260c6 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -897,6 +897,8 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1199, 0x9071, 10)},	/* Sierra Wireless MC74xx */
 	{QMI_FIXED_INTF(0x1199, 0x9079, 8)},	/* Sierra Wireless EM74xx */
 	{QMI_FIXED_INTF(0x1199, 0x9079, 10)},	/* Sierra Wireless EM74xx */
+	{QMI_FIXED_INTF(0x1199, 0x907b, 8)},	/* Sierra Wireless EM74xx */
+	{QMI_FIXED_INTF(0x1199, 0x907b, 10)},	/* Sierra Wireless EM74xx */
 	{QMI_FIXED_INTF(0x1bbb, 0x011e, 4)},	/* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */
 	{QMI_FIXED_INTF(0x1bbb, 0x0203, 2)},	/* Alcatel L800MA */
 	{QMI_FIXED_INTF(0x2357, 0x0201, 4)},	/* TP-LINK HSUPA Modem MA180 */
-- 
2.9.4


From 47f726a0649eecaa051b9c2e8603f55a9b99610f Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Fri, 19 May 2017 22:20:29 +0800
Subject: [PATCH 23/34] bridge: start hello_timer when enabling KERNEL_STP in
 br_stp_start

[ Upstream commit 6d18c732b95c0a9d35e9f978b4438bba15412284 ]

Since commit 76b91c32dd86 ("bridge: stp: when using userspace stp stop
kernel hello and hold timers"), bridge would not start hello_timer if
stp_enabled is not KERNEL_STP when br_dev_open.

The problem is even if users set stp_enabled with KERNEL_STP later,
the timer will still not be started. It causes that KERNEL_STP can
not really work. Users have to re-ifup the bridge to avoid this.

This patch is to fix it by starting br->hello_timer when enabling
KERNEL_STP in br_stp_start.

As an improvement, it's also to start hello_timer again only when
br->stp_enabled is KERNEL_STP in br_hello_timer_expired, there is
no reason to start the timer again when it's NO_STP.

Fixes: 76b91c32dd86 ("bridge: stp: when using userspace stp stop kernel hello and hold timers")
Reported-by: Haidong Li <haili@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Reviewed-by: Ivan Vecera <cera@cera.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_stp_if.c    | 1 +
 net/bridge/br_stp_timer.c | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
index d8ad73b..5a782f5 100644
--- a/net/bridge/br_stp_if.c
+++ b/net/bridge/br_stp_if.c
@@ -185,6 +185,7 @@ static void br_stp_start(struct net_bridge *br)
 		br_debug(br, "using kernel STP\n");
 
 		/* To start timers on any ports left in blocking */
+		mod_timer(&br->hello_timer, jiffies + br->hello_time);
 		br_port_state_selection(br);
 	}
 
diff --git a/net/bridge/br_stp_timer.c b/net/bridge/br_stp_timer.c
index da058b8..15826fd 100644
--- a/net/bridge/br_stp_timer.c
+++ b/net/bridge/br_stp_timer.c
@@ -40,7 +40,7 @@ static void br_hello_timer_expired(unsigned long arg)
 	if (br->dev->flags & IFF_UP) {
 		br_config_bpdu_generation(br);
 
-		if (br->stp_enabled != BR_USER_STP)
+		if (br->stp_enabled == BR_KERNEL_STP)
 			mod_timer(&br->hello_timer,
 				  round_jiffies(jiffies + br->hello_time));
 	}
-- 
2.9.4


From 0a3f1c07042cd2431122ab47abbedea56461b314 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 19 May 2017 14:17:48 -0700
Subject: [PATCH 24/34] ipv6: fix out of bound writes in __ip6_append_data()

[ Upstream commit 232cd35d0804cc241eb887bb8d4d9b3b9881c64a ]

Andrey Konovalov and idaifish@gmail.com reported crashes caused by
one skb shared_info being overwritten from __ip6_append_data()

Andrey program lead to following state :

copy -4200 datalen 2000 fraglen 2040
maxfraglen 2040 alloclen 2048 transhdrlen 0 offset 0 fraggap 6200

The skb_copy_and_csum_bits(skb_prev, maxfraglen, data + transhdrlen,
fraggap, 0); is overwriting skb->head and skb_shared_info

Since we apparently detect this rare condition too late, move the
code earlier to even avoid allocating skb and risking crashes.

Once again, many thanks to Andrey and syzkaller team.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Reported-by: <idaifish@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_output.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index b1e8ee5..1ac3cea 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1447,6 +1447,11 @@ static int __ip6_append_data(struct sock *sk,
 			 */
 			alloclen += sizeof(struct frag_hdr);
 
+			copy = datalen - transhdrlen - fraggap;
+			if (copy < 0) {
+				err = -EINVAL;
+				goto error;
+			}
 			if (transhdrlen) {
 				skb = sock_alloc_send_skb(sk,
 						alloclen + hh_len,
@@ -1496,13 +1501,9 @@ static int __ip6_append_data(struct sock *sk,
 				data += fraggap;
 				pskb_trim_unique(skb_prev, maxfraglen);
 			}
-			copy = datalen - transhdrlen - fraggap;
-
-			if (copy < 0) {
-				err = -EINVAL;
-				kfree_skb(skb);
-				goto error;
-			} else if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) {
+			if (copy > 0 &&
+			    getfrag(from, data + transhdrlen, offset,
+				    copy, fraggap, skb) < 0) {
 				err = -EFAULT;
 				kfree_skb(skb);
 				goto error;
-- 
2.9.4


From 83cf88e4364128ff2cf7c05c5ab848b1122090a1 Mon Sep 17 00:00:00 2001
From: Jarod Wilson <jarod@redhat.com>
Date: Fri, 19 May 2017 19:43:45 -0400
Subject: [PATCH 25/34] bonding: fix accounting of active ports in 3ad

[ Upstream commit 751da2a69b7cc82d83dc310ed7606225f2d6e014 ]

As of 7bb11dc9f59d and 0622cab0341c, bond slaves in a 3ad bond are not
removed from the aggregator when they are down, and the active slave count
is NOT equal to number of ports in the aggregator, but rather the number
of ports in the aggregator that are still enabled. The sysfs spew for
bonding_show_ad_num_ports() has a comment that says "Show number of active
802.3ad ports.", but it's currently showing total number of ports, both
active and inactive. Remedy it by using the same logic introduced in
0622cab0341c in __bond_3ad_get_active_agg_info(), so sysfs, procfs and
netlink all report the number of active ports. Note that this means that
IFLA_BOND_AD_INFO_NUM_PORTS really means NUM_ACTIVE_PORTS instead of
NUM_PORTS, and thus perhaps should be renamed for clarity.

Lightly tested on a dual i40e lacp bond, simulating link downs with an ip
link set dev <slave2> down, was able to produce the state where I could
see both in the same aggregator, but a number of ports count of 1.

MII Status: up
Active Aggregator Info:
        Aggregator ID: 1
        Number of ports: 2 <---
Slave Interface: ens10
MII Status: up <---
Aggregator ID: 1
Slave Interface: ens11
MII Status: up
Aggregator ID: 1

MII Status: up
Active Aggregator Info:
        Aggregator ID: 1
        Number of ports: 1 <---
Slave Interface: ens10
MII Status: down <---
Aggregator ID: 1
Slave Interface: ens11
MII Status: up
Aggregator ID: 1

CC: Jay Vosburgh <j.vosburgh@gmail.com>
CC: Veaceslav Falico <vfalico@gmail.com>
CC: Andy Gospodarek <andy@greyhouse.net>
CC: netdev@vger.kernel.org
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_3ad.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index edc70ff..6dcc42d 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -2573,7 +2573,7 @@ int __bond_3ad_get_active_agg_info(struct bonding *bond,
 		return -1;
 
 	ad_info->aggregator_id = aggregator->aggregator_identifier;
-	ad_info->ports = aggregator->num_of_ports;
+	ad_info->ports = __agg_active_ports(aggregator);
 	ad_info->actor_key = aggregator->actor_oper_aggregator_key;
 	ad_info->partner_key = aggregator->partner_oper_aggregator_key;
 	ether_addr_copy(ad_info->partner_system,
-- 
2.9.4


From ff4bff51d7851d0edb51eb54ee187c0b99af8639 Mon Sep 17 00:00:00 2001
From: Mohamad Haj Yahia <mohamad@mellanox.com>
Date: Thu, 23 Feb 2017 11:19:36 +0200
Subject: [PATCH 26/34] net/mlx5: Avoid using pending command interface slots

[ Upstream commit 73dd3a4839c1d27c36d4dcc92e1ff44225ecbeb7 ]

Currently when firmware command gets stuck or it takes long time to
complete, the driver command will get timeout and the command slot is
freed and can be used for new commands, and if the firmware receive new
command on the old busy slot its behavior is unexpected and this could
be harmful.
To fix this when the driver command gets timeout we return failure,
but we don't free the command slot and we wait for the firmware to
explicitly respond to that command.
Once all the entries are busy we will stop processing new firmware
commands.

Fixes: 9cba4ebcf374 ('net/mlx5: Fix potential deadlock in command mode change')
Signed-off-by: Mohamad Haj Yahia <mohamad@mellanox.com>
Cc: kernel-team@fb.com
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c    | 41 +++++++++++++++++++++---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c     |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/health.c |  2 +-
 include/linux/mlx5/driver.h                      |  7 +++-
 4 files changed, 44 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 3f51a44..cb45390 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -767,7 +767,7 @@ static void cb_timeout_handler(struct work_struct *work)
 	mlx5_core_warn(dev, "%s(0x%x) timeout. Will cause a leak of a command resource\n",
 		       mlx5_command_str(msg_to_opcode(ent->in)),
 		       msg_to_opcode(ent->in));
-	mlx5_cmd_comp_handler(dev, 1UL << ent->idx);
+	mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
 }
 
 static void cmd_work_handler(struct work_struct *work)
@@ -797,6 +797,7 @@ static void cmd_work_handler(struct work_struct *work)
 	}
 
 	cmd->ent_arr[ent->idx] = ent;
+	set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state);
 	lay = get_inst(cmd, ent->idx);
 	ent->lay = lay;
 	memset(lay, 0, sizeof(*lay));
@@ -818,6 +819,20 @@ static void cmd_work_handler(struct work_struct *work)
 	if (ent->callback)
 		schedule_delayed_work(&ent->cb_timeout_work, cb_timeout);
 
+	/* Skip sending command to fw if internal error */
+	if (pci_channel_offline(dev->pdev) ||
+	    dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
+		u8 status = 0;
+		u32 drv_synd;
+
+		ent->ret = mlx5_internal_err_ret_value(dev, msg_to_opcode(ent->in), &drv_synd, &status);
+		MLX5_SET(mbox_out, ent->out, status, status);
+		MLX5_SET(mbox_out, ent->out, syndrome, drv_synd);
+
+		mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
+		return;
+	}
+
 	/* ring doorbell after the descriptor is valid */
 	mlx5_core_dbg(dev, "writing 0x%x to command doorbell\n", 1 << ent->idx);
 	wmb();
@@ -828,7 +843,7 @@ static void cmd_work_handler(struct work_struct *work)
 		poll_timeout(ent);
 		/* make sure we read the descriptor after ownership is SW */
 		rmb();
-		mlx5_cmd_comp_handler(dev, 1UL << ent->idx);
+		mlx5_cmd_comp_handler(dev, 1UL << ent->idx, (ent->ret == -ETIMEDOUT));
 	}
 }
 
@@ -872,7 +887,7 @@ static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
 		wait_for_completion(&ent->done);
 	} else if (!wait_for_completion_timeout(&ent->done, timeout)) {
 		ent->ret = -ETIMEDOUT;
-		mlx5_cmd_comp_handler(dev, 1UL << ent->idx);
+		mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
 	}
 
 	err = ent->ret;
@@ -1369,7 +1384,7 @@ static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg)
 	}
 }
 
-void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec)
+void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced)
 {
 	struct mlx5_cmd *cmd = &dev->cmd;
 	struct mlx5_cmd_work_ent *ent;
@@ -1389,6 +1404,19 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec)
 			struct semaphore *sem;
 
 			ent = cmd->ent_arr[i];
+
+			/* if we already completed the command, ignore it */
+			if (!test_and_clear_bit(MLX5_CMD_ENT_STATE_PENDING_COMP,
+						&ent->state)) {
+				/* only real completion can free the cmd slot */
+				if (!forced) {
+					mlx5_core_err(dev, "Command completion arrived after timeout (entry idx = %d).\n",
+						      ent->idx);
+					free_ent(cmd, ent->idx);
+				}
+				continue;
+			}
+
 			if (ent->callback)
 				cancel_delayed_work(&ent->cb_timeout_work);
 			if (ent->page_queue)
@@ -1411,7 +1439,10 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec)
 				mlx5_core_dbg(dev, "command completed. ret 0x%x, delivery status %s(0x%x)\n",
 					      ent->ret, deliv_status_to_str(ent->status), ent->status);
 			}
-			free_ent(cmd, ent->idx);
+
+			/* only real completion will free the entry slot */
+			if (!forced)
+				free_ent(cmd, ent->idx);
 
 			if (ent->callback) {
 				ds = ent->ts2 - ent->ts1;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index aaca090..f86e9ff 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -234,7 +234,7 @@ static int mlx5_eq_int(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
 			break;
 
 		case MLX5_EVENT_TYPE_CMD:
-			mlx5_cmd_comp_handler(dev, be32_to_cpu(eqe->data.cmd.vector));
+			mlx5_cmd_comp_handler(dev, be32_to_cpu(eqe->data.cmd.vector), false);
 			break;
 
 		case MLX5_EVENT_TYPE_PORT_CHANGE:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 5bcf934..2115c8a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -90,7 +90,7 @@ static void trigger_cmd_completions(struct mlx5_core_dev *dev)
 	spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags);
 
 	mlx5_core_dbg(dev, "vector 0x%llx\n", vector);
-	mlx5_cmd_comp_handler(dev, vector);
+	mlx5_cmd_comp_handler(dev, vector, true);
 	return;
 
 no_trig:
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index ecc451d..e1a903a 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -640,7 +640,12 @@ enum {
 
 typedef void (*mlx5_cmd_cbk_t)(int status, void *context);
 
+enum {
+	MLX5_CMD_ENT_STATE_PENDING_COMP,
+};
+
 struct mlx5_cmd_work_ent {
+	unsigned long		state;
 	struct mlx5_cmd_msg    *in;
 	struct mlx5_cmd_msg    *out;
 	void		       *uout;
@@ -838,7 +843,7 @@ void mlx5_eq_pagefault(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe);
 #endif
 void mlx5_srq_event(struct mlx5_core_dev *dev, u32 srqn, int event_type);
 struct mlx5_core_srq *mlx5_core_get_srq(struct mlx5_core_dev *dev, u32 srqn);
-void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec);
+void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced);
 void mlx5_cq_event(struct mlx5_core_dev *dev, u32 cqn, int event_type);
 int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
 		       int nent, u64 mask, const char *name, struct mlx5_uar *uar);
-- 
2.9.4


From 43dd2f53539801d66003c807b108467e9816383c Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Tue, 23 May 2017 17:49:13 +0200
Subject: [PATCH 27/34] net: phy: marvell: Limit errata to 88m1101

[ Upstream commit f2899788353c13891412b273fdff5f02d49aa40f ]

The 88m1101 has an errata when configuring autoneg. However, it was
being applied to many other Marvell PHYs as well. Limit its scope to
just the 88m1101.

Fixes: 76884679c644 ("phylib: Add support for Marvell 88e1111S and 88e1145")
Reported-by: Daniel Walker <danielwa@cisco.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Acked-by: Harini Katakam <harinik@xilinx.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/marvell.c | 66 ++++++++++++++++++++++++++---------------------
 1 file changed, 37 insertions(+), 29 deletions(-)

diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index c2dcf02..d6a541b 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -240,34 +240,6 @@ static int marvell_config_aneg(struct phy_device *phydev)
 {
 	int err;
 
-	/* The Marvell PHY has an errata which requires
-	 * that certain registers get written in order
-	 * to restart autonegotiation */
-	err = phy_write(phydev, MII_BMCR, BMCR_RESET);
-
-	if (err < 0)
-		return err;
-
-	err = phy_write(phydev, 0x1d, 0x1f);
-	if (err < 0)
-		return err;
-
-	err = phy_write(phydev, 0x1e, 0x200c);
-	if (err < 0)
-		return err;
-
-	err = phy_write(phydev, 0x1d, 0x5);
-	if (err < 0)
-		return err;
-
-	err = phy_write(phydev, 0x1e, 0);
-	if (err < 0)
-		return err;
-
-	err = phy_write(phydev, 0x1e, 0x100);
-	if (err < 0)
-		return err;
-
 	err = marvell_set_polarity(phydev, phydev->mdix);
 	if (err < 0)
 		return err;
@@ -301,6 +273,42 @@ static int marvell_config_aneg(struct phy_device *phydev)
 	return 0;
 }
 
+static int m88e1101_config_aneg(struct phy_device *phydev)
+{
+	int err;
+
+	/* This Marvell PHY has an errata which requires
+	 * that certain registers get written in order
+	 * to restart autonegotiation
+	 */
+	err = phy_write(phydev, MII_BMCR, BMCR_RESET);
+
+	if (err < 0)
+		return err;
+
+	err = phy_write(phydev, 0x1d, 0x1f);
+	if (err < 0)
+		return err;
+
+	err = phy_write(phydev, 0x1e, 0x200c);
+	if (err < 0)
+		return err;
+
+	err = phy_write(phydev, 0x1d, 0x5);
+	if (err < 0)
+		return err;
+
+	err = phy_write(phydev, 0x1e, 0);
+	if (err < 0)
+		return err;
+
+	err = phy_write(phydev, 0x1e, 0x100);
+	if (err < 0)
+		return err;
+
+	return marvell_config_aneg(phydev);
+}
+
 static int m88e1111_config_aneg(struct phy_device *phydev)
 {
 	int err;
@@ -1491,7 +1499,7 @@ static struct phy_driver marvell_drivers[] = {
 		.probe = marvell_probe,
 		.flags = PHY_HAS_INTERRUPT,
 		.config_init = &marvell_config_init,
-		.config_aneg = &marvell_config_aneg,
+		.config_aneg = &m88e1101_config_aneg,
 		.read_status = &genphy_read_status,
 		.ack_interrupt = &marvell_ack_interrupt,
 		.config_intr = &marvell_config_intr,
-- 
2.9.4


From f1069e0807a41219fed0f5add520148907c3fd05 Mon Sep 17 00:00:00 2001
From: Vlad Yasevich <vyasevich@gmail.com>
Date: Tue, 23 May 2017 13:38:41 -0400
Subject: [PATCH 28/34] vlan: Fix tcp checksum offloads in Q-in-Q vlans

[ Upstream commit 35d2f80b07bbe03fb358afb0bdeff7437a7d67ff ]

It appears that TCP checksum offloading has been broken for
Q-in-Q vlans.  The behavior was execerbated by the
series
    commit afb0bc972b52 ("Merge branch 'stacked_vlan_tso'")
that that enabled accleleration features on stacked vlans.

However, event without that series, it is possible to trigger
this issue.  It just requires a lot more specialized configuration.

The root cause is the interaction between how
netdev_intersect_features() works, the features actually set on
the vlan devices and HW having the ability to run checksum with
longer headers.

The issue starts when netdev_interesect_features() replaces
NETIF_F_HW_CSUM with a combination of NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM,
if the HW advertises IP|IPV6 specific checksums.  This happens
for tagged and multi-tagged packets.   However, HW that enables
IP|IPV6 checksum offloading doesn't gurantee that packets with
arbitrarily long headers can be checksummed.

This patch disables IP|IPV6 checksums on the packet for multi-tagged
packets.

CC: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
CC: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: Vladislav Yasevich <vyasevic@redhat.com>
Acked-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_vlan.h | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 3319d97..8feecd5 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -630,14 +630,16 @@ static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb)
 static inline netdev_features_t vlan_features_check(const struct sk_buff *skb,
 						    netdev_features_t features)
 {
-	if (skb_vlan_tagged_multi(skb))
-		features = netdev_intersect_features(features,
-						     NETIF_F_SG |
-						     NETIF_F_HIGHDMA |
-						     NETIF_F_FRAGLIST |
-						     NETIF_F_HW_CSUM |
-						     NETIF_F_HW_VLAN_CTAG_TX |
-						     NETIF_F_HW_VLAN_STAG_TX);
+	if (skb_vlan_tagged_multi(skb)) {
+		/* In the case of multi-tagged packets, use a direct mask
+		 * instead of using netdev_interesect_features(), to make
+		 * sure that only devices supporting NETIF_F_HW_CSUM will
+		 * have checksum offloading support.
+		 */
+		features &= NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_HW_CSUM |
+			    NETIF_F_FRAGLIST | NETIF_F_HW_VLAN_CTAG_TX |
+			    NETIF_F_HW_VLAN_STAG_TX;
+	}
 
 	return features;
 }
-- 
2.9.4


From 97910146368e47d41be95577bf6e07e418310f21 Mon Sep 17 00:00:00 2001
From: Vlad Yasevich <vyasevich@gmail.com>
Date: Tue, 23 May 2017 13:38:42 -0400
Subject: [PATCH 29/34] be2net: Fix offload features for Q-in-Q packets

[ Upstream commit cc6e9de62a7f84c9293a2ea41bc412b55bb46e85 ]

At least some of the be2net cards do not seem to be capabled
of performing checksum offload computions on Q-in-Q packets.
In these case, the recevied checksum on the remote is invalid
and TCP syn packets are dropped.

This patch adds a call to check disbled acceleration features
on Q-in-Q tagged traffic.

CC: Sathya Perla <sathya.perla@broadcom.com>
CC: Ajit Khaparde <ajit.khaparde@broadcom.com>
CC: Sriharsha Basavapatna <sriharsha.basavapatna@broadcom.com>
CC: Somnath Kotur <somnath.kotur@broadcom.com>
Signed-off-by: Vladislav Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/emulex/benet/be_main.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 93aa293..9711ca4 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -5144,9 +5144,11 @@ static netdev_features_t be_features_check(struct sk_buff *skb,
 	struct be_adapter *adapter = netdev_priv(dev);
 	u8 l4_hdr = 0;
 
-	/* The code below restricts offload features for some tunneled packets.
+	/* The code below restricts offload features for some tunneled and
+	 * Q-in-Q packets.
 	 * Offload features for normal (non tunnel) packets are unchanged.
 	 */
+	features = vlan_features_check(skb, features);
 	if (!skb->encapsulation ||
 	    !(adapter->flags & BE_FLAGS_VXLAN_OFFLOADS))
 		return features;
-- 
2.9.4


From 1f49288815d99773f985f9bfd4872c7abc9bb6d0 Mon Sep 17 00:00:00 2001
From: Vlad Yasevich <vyasevich@gmail.com>
Date: Tue, 23 May 2017 13:38:43 -0400
Subject: [PATCH 30/34] virtio-net: enable TSO/checksum offloads for Q-in-Q
 vlans

[ Upstream commit 2836b4f224d4fd7d1a2b23c3eecaf0f0ae199a74 ]

Since virtio does not provide it's own ndo_features_check handler,
TSO, and now checksum offload, are disabled for stacked vlans.
Re-enable the support and let the host take care of it.  This
restores/improves Guest-to-Guest performance over Q-in-Q vlans.

Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Vladislav Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 51fc0c3..7ca9989 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1456,6 +1456,7 @@ static const struct net_device_ops virtnet_netdev = {
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	.ndo_busy_poll		= virtnet_busy_poll,
 #endif
+	.ndo_features_check	= passthru_features_check,
 };
 
 static void virtnet_config_changed_work(struct work_struct *work)
-- 
2.9.4


From 70837d2610f5617d589a8585a81cf1bd7e43a3c3 Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Wed, 24 May 2017 09:59:31 -0700
Subject: [PATCH 31/34] tcp: avoid fastopen API to be used on AF_UNSPEC

[ Upstream commit ba615f675281d76fd19aa03558777f81fb6b6084 ]

Fastopen API should be used to perform fastopen operations on the TCP
socket. It does not make sense to use fastopen API to perform disconnect
by calling it with AF_UNSPEC. The fastopen data path is also prone to
race conditions and bugs when using with AF_UNSPEC.

One issue reported and analyzed by Vegard Nossum is as follows:
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Thread A:                            Thread B:
------------------------------------------------------------------------
sendto()
 - tcp_sendmsg()
     - sk_stream_memory_free() = 0
         - goto wait_for_sndbuf
	     - sk_stream_wait_memory()
	        - sk_wait_event() // sleep
          |                          sendto(flags=MSG_FASTOPEN, dest_addr=AF_UNSPEC)
	  |                           - tcp_sendmsg()
	  |                              - tcp_sendmsg_fastopen()
	  |                                 - __inet_stream_connect()
	  |                                    - tcp_disconnect() //because of AF_UNSPEC
	  |                                       - tcp_transmit_skb()// send RST
	  |                                    - return 0; // no reconnect!
	  |                           - sk_stream_wait_connect()
	  |                                 - sock_error()
	  |                                    - xchg(&sk->sk_err, 0)
	  |                                    - return -ECONNRESET
	- ... // wake up, see sk->sk_err == 0
    - skb_entail() on TCP_CLOSE socket

If the connection is reopened then we will send a brand new SYN packet
after thread A has already queued a buffer. At this point I think the
socket internal state (sequence numbers etc.) becomes messed up.

When the new connection is closed, the FIN-ACK is rejected because the
sequence number is outside the window. The other side tries to
retransmit,
but __tcp_retransmit_skb() calls tcp_trim_head() on an empty skb which
corrupts the skb data length and hits a BUG() in copy_and_csum_bits().
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++

Hence, this patch adds a check for AF_UNSPEC in the fastopen data path
and return EOPNOTSUPP to user if such case happens.

Fixes: cf60af03ca4e7 ("tcp: Fast Open client - sendmsg(MSG_FASTOPEN)")
Reported-by: Vegard Nossum <vegard.nossum@oracle.com>
Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index eb142ca..86fbf0f 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1078,9 +1078,12 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
 				int *copied, size_t size)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	struct sockaddr *uaddr = msg->msg_name;
 	int err, flags;
 
-	if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE))
+	if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) ||
+	    (uaddr && msg->msg_namelen >= sizeof(uaddr->sa_family) &&
+	     uaddr->sa_family == AF_UNSPEC))
 		return -EOPNOTSUPP;
 	if (tp->fastopen_req)
 		return -EALREADY; /* Another Fast Open is in progress */
@@ -1093,7 +1096,7 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
 	tp->fastopen_req->size = size;
 
 	flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0;
-	err = __inet_stream_connect(sk->sk_socket, msg->msg_name,
+	err = __inet_stream_connect(sk->sk_socket, uaddr,
 				    msg->msg_namelen, flags);
 	*copied = tp->fastopen_req->copied;
 	tcp_free_fastopen_req(tp);
-- 
2.9.4


From 75a3583047ec15a874cf8483cb7b20ffcd28b74f Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Thu, 25 May 2017 19:14:56 +0200
Subject: [PATCH 32/34] sctp: fix ICMP processing if skb is non-linear

[ Upstream commit 804ec7ebe8ea003999ca8d1bfc499edc6a9e07df ]

sometimes ICMP replies to INIT chunks are ignored by the client, even if
the encapsulated SCTP headers match an open socket. This happens when the
ICMP packet is carried by a paged skb: use skb_header_pointer() to read
packet contents beyond the SCTP header, so that chunk header and initiate
tag are validated correctly.

v2:
- don't use skb_header_pointer() to read the transport header, since
  icmp_socket_deliver() already puts these 8 bytes in the linear area.
- change commit message to make specific reference to INIT chunks.

Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/input.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/net/sctp/input.c b/net/sctp/input.c
index a01a56e..6c79915 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -473,15 +473,14 @@ struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *skb,
 			     struct sctp_association **app,
 			     struct sctp_transport **tpp)
 {
+	struct sctp_init_chunk *chunkhdr, _chunkhdr;
 	union sctp_addr saddr;
 	union sctp_addr daddr;
 	struct sctp_af *af;
 	struct sock *sk = NULL;
 	struct sctp_association *asoc;
 	struct sctp_transport *transport = NULL;
-	struct sctp_init_chunk *chunkhdr;
 	__u32 vtag = ntohl(sctphdr->vtag);
-	int len = skb->len - ((void *)sctphdr - (void *)skb->data);
 
 	*app = NULL; *tpp = NULL;
 
@@ -516,13 +515,16 @@ struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *skb,
 	 * discard the packet.
 	 */
 	if (vtag == 0) {
-		chunkhdr = (void *)sctphdr + sizeof(struct sctphdr);
-		if (len < sizeof(struct sctphdr) + sizeof(sctp_chunkhdr_t)
-			  + sizeof(__be32) ||
+		/* chunk header + first 4 octects of init header */
+		chunkhdr = skb_header_pointer(skb, skb_transport_offset(skb) +
+					      sizeof(struct sctphdr),
+					      sizeof(struct sctp_chunkhdr) +
+					      sizeof(__be32), &_chunkhdr);
+		if (!chunkhdr ||
 		    chunkhdr->chunk_hdr.type != SCTP_CID_INIT ||
-		    ntohl(chunkhdr->init_hdr.init_tag) != asoc->c.my_vtag) {
+		    ntohl(chunkhdr->init_hdr.init_tag) != asoc->c.my_vtag)
 			goto out;
-		}
+
 	} else if (vtag != asoc->c.peer_vtag) {
 		goto out;
 	}
-- 
2.9.4


From 52770ce4d2ab8da6edef95ce16005b16dad82b9c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 25 May 2017 14:27:35 -0700
Subject: [PATCH 33/34] ipv4: add reference counting to metrics

[ Upstream commit 3fb07daff8e99243366a081e5129560734de4ada ]

Andrey Konovalov reported crashes in ipv4_mtu()

I could reproduce the issue with KASAN kernels, between
10.246.7.151 and 10.246.7.152 :

1) 20 concurrent netperf -t TCP_RR -H 10.246.7.152 -l 1000 &

2) At the same time run following loop :
while :
do
 ip ro add 10.246.7.152 dev eth0 src 10.246.7.151 mtu 1500
 ip ro del 10.246.7.152 dev eth0 src 10.246.7.151 mtu 1500
done

Cong Wang attempted to add back rt->fi in commit
82486aa6f1b9 ("ipv4: restore rt->fi for reference counting")
but this proved to add some issues that were complex to solve.

Instead, I suggested to add a refcount to the metrics themselves,
being a standalone object (in particular, no reference to other objects)

I tried to make this patch as small as possible to ease its backport,
instead of being super clean. Note that we believe that only ipv4 dst
need to take care of the metric refcount. But if this is wrong,
this patch adds the basic infrastructure to extend this to other
families.

Many thanks to Julian Anastasov for reviewing this patch, and Cong Wang
for his efforts on this problem.

Fixes: 2860583fe840 ("ipv4: Kill rt->fi")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Reviewed-by: Julian Anastasov <ja@ssi.bg>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst.h        |  8 +++++++-
 include/net/ip_fib.h     | 10 +++++-----
 net/core/dst.c           | 23 ++++++++++++++---------
 net/ipv4/fib_semantics.c | 17 ++++++++++-------
 net/ipv4/route.c         | 10 +++++++++-
 5 files changed, 45 insertions(+), 23 deletions(-)

diff --git a/include/net/dst.h b/include/net/dst.h
index 6835d22..ddcff17 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -107,10 +107,16 @@ struct dst_entry {
 	};
 };
 
+struct dst_metrics {
+	u32		metrics[RTAX_MAX];
+	atomic_t	refcnt;
+};
+extern const struct dst_metrics dst_default_metrics;
+
 u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old);
-extern const u32 dst_default_metrics[];
 
 #define DST_METRICS_READ_ONLY		0x1UL
+#define DST_METRICS_REFCOUNTED		0x2UL
 #define DST_METRICS_FLAGS		0x3UL
 #define __DST_METRICS_PTR(Y)	\
 	((u32 *)((Y) & ~DST_METRICS_FLAGS))
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index f390c3b..aa75828 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -114,11 +114,11 @@ struct fib_info {
 	__be32			fib_prefsrc;
 	u32			fib_tb_id;
 	u32			fib_priority;
-	u32			*fib_metrics;
-#define fib_mtu fib_metrics[RTAX_MTU-1]
-#define fib_window fib_metrics[RTAX_WINDOW-1]
-#define fib_rtt fib_metrics[RTAX_RTT-1]
-#define fib_advmss fib_metrics[RTAX_ADVMSS-1]
+	struct dst_metrics	*fib_metrics;
+#define fib_mtu fib_metrics->metrics[RTAX_MTU-1]
+#define fib_window fib_metrics->metrics[RTAX_WINDOW-1]
+#define fib_rtt fib_metrics->metrics[RTAX_RTT-1]
+#define fib_advmss fib_metrics->metrics[RTAX_ADVMSS-1]
 	int			fib_nhs;
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	int			fib_weight;
diff --git a/net/core/dst.c b/net/core/dst.c
index b5cbbe0..656b70d 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -151,13 +151,13 @@ int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(dst_discard_out);
 
-const u32 dst_default_metrics[RTAX_MAX + 1] = {
+const struct dst_metrics dst_default_metrics = {
 	/* This initializer is needed to force linker to place this variable
 	 * into const section. Otherwise it might end into bss section.
 	 * We really want to avoid false sharing on this variable, and catch
 	 * any writes on it.
 	 */
-	[RTAX_MAX] = 0xdeadbeef,
+	.refcnt = ATOMIC_INIT(1),
 };
 
 void dst_init(struct dst_entry *dst, struct dst_ops *ops,
@@ -169,7 +169,7 @@ void dst_init(struct dst_entry *dst, struct dst_ops *ops,
 	if (dev)
 		dev_hold(dev);
 	dst->ops = ops;
-	dst_init_metrics(dst, dst_default_metrics, true);
+	dst_init_metrics(dst, dst_default_metrics.metrics, true);
 	dst->expires = 0UL;
 	dst->path = dst;
 	dst->from = NULL;
@@ -315,25 +315,30 @@ EXPORT_SYMBOL(dst_release);
 
 u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old)
 {
-	u32 *p = kmalloc(sizeof(u32) * RTAX_MAX, GFP_ATOMIC);
+	struct dst_metrics *p = kmalloc(sizeof(*p), GFP_ATOMIC);
 
 	if (p) {
-		u32 *old_p = __DST_METRICS_PTR(old);
+		struct dst_metrics *old_p = (struct dst_metrics *)__DST_METRICS_PTR(old);
 		unsigned long prev, new;
 
-		memcpy(p, old_p, sizeof(u32) * RTAX_MAX);
+		atomic_set(&p->refcnt, 1);
+		memcpy(p->metrics, old_p->metrics, sizeof(p->metrics));
 
 		new = (unsigned long) p;
 		prev = cmpxchg(&dst->_metrics, old, new);
 
 		if (prev != old) {
 			kfree(p);
-			p = __DST_METRICS_PTR(prev);
+			p = (struct dst_metrics *)__DST_METRICS_PTR(prev);
 			if (prev & DST_METRICS_READ_ONLY)
 				p = NULL;
+		} else if (prev & DST_METRICS_REFCOUNTED) {
+			if (atomic_dec_and_test(&old_p->refcnt))
+				kfree(old_p);
 		}
 	}
-	return p;
+	BUILD_BUG_ON(offsetof(struct dst_metrics, metrics) != 0);
+	return (u32 *)p;
 }
 EXPORT_SYMBOL(dst_cow_metrics_generic);
 
@@ -342,7 +347,7 @@ void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old)
 {
 	unsigned long prev, new;
 
-	new = ((unsigned long) dst_default_metrics) | DST_METRICS_READ_ONLY;
+	new = ((unsigned long) &dst_default_metrics) | DST_METRICS_READ_ONLY;
 	prev = cmpxchg(&dst->_metrics, old, new);
 	if (prev == old)
 		kfree(__DST_METRICS_PTR(old));
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 6a40680..7563831 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -204,6 +204,7 @@ static void rt_fibinfo_free_cpus(struct rtable __rcu * __percpu *rtp)
 static void free_fib_info_rcu(struct rcu_head *head)
 {
 	struct fib_info *fi = container_of(head, struct fib_info, rcu);
+	struct dst_metrics *m;
 
 	change_nexthops(fi) {
 		if (nexthop_nh->nh_dev)
@@ -214,8 +215,9 @@ static void free_fib_info_rcu(struct rcu_head *head)
 		rt_fibinfo_free(&nexthop_nh->nh_rth_input);
 	} endfor_nexthops(fi);
 
-	if (fi->fib_metrics != (u32 *) dst_default_metrics)
-		kfree(fi->fib_metrics);
+	m = fi->fib_metrics;
+	if (m != &dst_default_metrics && atomic_dec_and_test(&m->refcnt))
+		kfree(m);
 	kfree(fi);
 }
 
@@ -982,11 +984,11 @@ fib_convert_metrics(struct fib_info *fi, const struct fib_config *cfg)
 			val = 255;
 		if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK))
 			return -EINVAL;
-		fi->fib_metrics[type - 1] = val;
+		fi->fib_metrics->metrics[type - 1] = val;
 	}
 
 	if (ecn_ca)
-		fi->fib_metrics[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA;
+		fi->fib_metrics->metrics[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA;
 
 	return 0;
 }
@@ -1044,11 +1046,12 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 		goto failure;
 	fib_info_cnt++;
 	if (cfg->fc_mx) {
-		fi->fib_metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL);
+		fi->fib_metrics = kzalloc(sizeof(*fi->fib_metrics), GFP_KERNEL);
 		if (!fi->fib_metrics)
 			goto failure;
+		atomic_set(&fi->fib_metrics->refcnt, 1);
 	} else
-		fi->fib_metrics = (u32 *) dst_default_metrics;
+		fi->fib_metrics = (struct dst_metrics *)&dst_default_metrics;
 
 	fi->fib_net = net;
 	fi->fib_protocol = cfg->fc_protocol;
@@ -1252,7 +1255,7 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 	if (fi->fib_priority &&
 	    nla_put_u32(skb, RTA_PRIORITY, fi->fib_priority))
 		goto nla_put_failure;
-	if (rtnetlink_put_metrics(skb, fi->fib_metrics) < 0)
+	if (rtnetlink_put_metrics(skb, fi->fib_metrics->metrics) < 0)
 		goto nla_put_failure;
 
 	if (fi->fib_prefsrc &&
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 6dbcb37..6cd49fd 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1364,8 +1364,12 @@ static void rt_add_uncached_list(struct rtable *rt)
 
 static void ipv4_dst_destroy(struct dst_entry *dst)
 {
+	struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst);
 	struct rtable *rt = (struct rtable *) dst;
 
+	if (p != &dst_default_metrics && atomic_dec_and_test(&p->refcnt))
+		kfree(p);
+
 	if (!list_empty(&rt->rt_uncached)) {
 		struct uncached_list *ul = rt->rt_uncached_list;
 
@@ -1417,7 +1421,11 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
 			rt->rt_gateway = nh->nh_gw;
 			rt->rt_uses_gateway = 1;
 		}
-		dst_init_metrics(&rt->dst, fi->fib_metrics, true);
+		dst_init_metrics(&rt->dst, fi->fib_metrics->metrics, true);
+		if (fi->fib_metrics != &dst_default_metrics) {
+			rt->dst._metrics |= DST_METRICS_REFCOUNTED;
+			atomic_inc(&fi->fib_metrics->refcnt);
+		}
 #ifdef CONFIG_IP_ROUTE_CLASSID
 		rt->dst.tclassid = nh->nh_tclassid;
 #endif
-- 
2.9.4


From bc56b1f69e805b0a4c53d37e61122906f8505bc6 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 25 May 2017 01:05:07 +0200
Subject: [PATCH 34/34] bpf: add bpf_clone_redirect to
 bpf_helper_changes_pkt_data

[ Upstream commit 41703a731066fde79c3e5ccf3391cf77a98aeda5 ]

The bpf_clone_redirect() still needs to be listed in
bpf_helper_changes_pkt_data() since we call into
bpf_try_make_head_writable() from there, thus we need
to invalidate prior pkt regs as well.

Fixes: 36bbef52c7eb ("bpf: direct packet write and access for helpers for clsact progs")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/filter.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/core/filter.c b/net/core/filter.c
index b391209..4eb4ce0 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2198,6 +2198,7 @@ bool bpf_helper_changes_skb_data(void *func)
 	    func == bpf_skb_change_proto ||
 	    func == bpf_skb_change_tail ||
 	    func == bpf_skb_pull_data ||
+	    func == bpf_clone_redirect ||
 	    func == bpf_l3_csum_replace ||
 	    func == bpf_l4_csum_replace)
 		return true;
-- 
2.9.4


[-- Attachment #3: net_411.mbox --]
[-- Type: Application/Octet-Stream, Size: 130161 bytes --]

From 27bd7c3026481facc9241b3a353b29ef03bd3a06 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 9 May 2017 06:29:19 -0700
Subject: [PATCH 01/41] dccp/tcp: do not inherit mc_list from parent

[ Upstream commit 657831ffc38e30092a2d5f03d385d710eb88b09a ]

syzkaller found a way to trigger double frees from ip_mc_drop_socket()

It turns out that leave a copy of parent mc_list at accept() time,
which is very bad.

Very similar to commit 8b485ce69876 ("tcp: do not inherit
fastopen_req from parent")

Initial report from Pray3r, completed by Andrey one.
Thanks a lot to them !

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Pray3r <pray3r.z@gmail.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/inet_connection_sock.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 5e313c1..1054d33 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -794,6 +794,8 @@ struct sock *inet_csk_clone_lock(const struct sock *sk,
 		/* listeners have SOCK_RCU_FREE, not the children */
 		sock_reset_flag(newsk, SOCK_RCU_FREE);
 
+		inet_sk(newsk)->mc_list = NULL;
+
 		newsk->sk_mark = inet_rsk(req)->ir_mark;
 		atomic64_set(&newsk->sk_cookie,
 			     atomic64_read(&inet_rsk(req)->ir_cookie));
-- 
2.4.11


From a852a4fccae7b2c7e516746510b239bb01123f31 Mon Sep 17 00:00:00 2001
From: Gao Feng <gfree.wind@vip.163.com>
Date: Tue, 9 May 2017 18:27:33 +0800
Subject: [PATCH 02/41] driver: vrf: Fix one possible use-after-free issue

[ Upstream commit 1a4a5bf52a4adb477adb075e5afce925824ad132 ]

The current codes only deal with the case that the skb is dropped, it
may meet one use-after-free issue when NF_HOOK returns 0 that means
the skb is stolen by one netfilter rule or hook.

When one netfilter rule or hook stoles the skb and return NF_STOLEN,
it means the skb is taken by the rule, and other modules should not
touch this skb ever. Maybe the skb is queued or freed directly by the
rule.

Now uses the nf_hook instead of NF_HOOK to get the result of netfilter,
and check the return value of nf_hook. Only when its value equals 1, it
means the skb could go ahead. Or reset the skb as NULL.

BTW, because vrf_rcv_finish is empty function, so needn't invoke it
even though nf_hook returns 1. But we need to modify vrf_rcv_finish
to deal with the NF_STOLEN case.

There are two cases when skb is stolen.
1. The skb is stolen and freed directly.
   There is nothing we need to do, and vrf_rcv_finish isn't invoked.
2. The skb is queued and reinjected again.
   The vrf_rcv_finish would be invoked as okfn, so need to free the
   skb in it.

Signed-off-by: Gao Feng <gfree.wind@vip.163.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 7d909c8..df74efc 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -851,6 +851,7 @@ static u32 vrf_fib_table(const struct net_device *dev)
 
 static int vrf_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
+	kfree_skb(skb);
 	return 0;
 }
 
@@ -860,7 +861,7 @@ static struct sk_buff *vrf_rcv_nfhook(u8 pf, unsigned int hook,
 {
 	struct net *net = dev_net(dev);
 
-	if (NF_HOOK(pf, hook, net, NULL, skb, dev, NULL, vrf_rcv_finish) < 0)
+	if (nf_hook(pf, hook, net, NULL, skb, dev, NULL, vrf_rcv_finish) != 1)
 		skb = NULL;    /* kfree_skb(skb) handled by nf code */
 
 	return skb;
-- 
2.4.11


From c6c8fb631aebd7206714e96a2ce0577790117e2c Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Tue, 9 May 2017 16:59:54 -0700
Subject: [PATCH 03/41] ipv6/dccp: do not inherit ipv6_mc_list from parent

[ Upstream commit 83eaddab4378db256d00d295bda6ca997cd13a52 ]

Like commit 657831ffc38e ("dccp/tcp: do not inherit mc_list from parent")
we should clear ipv6_mc_list etc. for IPv6 sockets too.

Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ipv6.c     | 6 ++++++
 net/ipv6/tcp_ipv6.c | 2 ++
 2 files changed, 8 insertions(+)

diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index d9b6a4e..b6bbb71 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -426,6 +426,9 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk,
 		newsk->sk_backlog_rcv = dccp_v4_do_rcv;
 		newnp->pktoptions  = NULL;
 		newnp->opt	   = NULL;
+		newnp->ipv6_mc_list = NULL;
+		newnp->ipv6_ac_list = NULL;
+		newnp->ipv6_fl_list = NULL;
 		newnp->mcast_oif   = inet6_iif(skb);
 		newnp->mcast_hops  = ipv6_hdr(skb)->hop_limit;
 
@@ -490,6 +493,9 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk,
 	/* Clone RX bits */
 	newnp->rxopt.all = np->rxopt.all;
 
+	newnp->ipv6_mc_list = NULL;
+	newnp->ipv6_ac_list = NULL;
+	newnp->ipv6_fl_list = NULL;
 	newnp->pktoptions = NULL;
 	newnp->opt	  = NULL;
 	newnp->mcast_oif  = inet6_iif(skb);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 4c4afdc..ff5f876 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1070,6 +1070,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 		newtp->af_specific = &tcp_sock_ipv6_mapped_specific;
 #endif
 
+		newnp->ipv6_mc_list = NULL;
 		newnp->ipv6_ac_list = NULL;
 		newnp->ipv6_fl_list = NULL;
 		newnp->pktoptions  = NULL;
@@ -1139,6 +1140,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 	   First: no IPv4 options.
 	 */
 	newinet->inet_opt = NULL;
+	newnp->ipv6_mc_list = NULL;
 	newnp->ipv6_ac_list = NULL;
 	newnp->ipv6_fl_list = NULL;
 
-- 
2.4.11


From 7fbd417b308d2ab8230a7814dce046caf464296b Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.vnet.ibm.com>
Date: Wed, 10 May 2017 19:07:51 +0200
Subject: [PATCH 04/41] s390/qeth: handle sysfs error during initialization

[ Upstream commit 9111e7880ccf419548c7b0887df020b08eadb075 ]

When setting up the device from within the layer discipline's
probe routine, creating the layer-specific sysfs attributes can fail.
Report this error back to the caller, and handle it by
releasing the layer discipline.

Signed-off-by: Ursula Braun <ubraun@linux.vnet.ibm.com>
[jwi: updated commit msg, moved an OSN change to a subsequent patch]
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 4 +++-
 drivers/s390/net/qeth_core_sys.c  | 2 ++
 drivers/s390/net/qeth_l2_main.c   | 5 ++++-
 drivers/s390/net/qeth_l3_main.c   | 5 ++++-
 4 files changed, 13 insertions(+), 3 deletions(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 9a5f99c..5c072b7 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -5661,8 +5661,10 @@ static int qeth_core_set_online(struct ccwgroup_device *gdev)
 		if (rc)
 			goto err;
 		rc = card->discipline->setup(card->gdev);
-		if (rc)
+		if (rc) {
+			qeth_core_free_discipline(card);
 			goto err;
+		}
 	}
 	rc = card->discipline->set_online(gdev);
 err:
diff --git a/drivers/s390/net/qeth_core_sys.c b/drivers/s390/net/qeth_core_sys.c
index 75b29fd2..412ff61 100644
--- a/drivers/s390/net/qeth_core_sys.c
+++ b/drivers/s390/net/qeth_core_sys.c
@@ -426,6 +426,8 @@ static ssize_t qeth_dev_layer2_store(struct device *dev,
 		goto out;
 
 	rc = card->discipline->setup(card->gdev);
+	if (rc)
+		qeth_core_free_discipline(card);
 out:
 	mutex_unlock(&card->discipline_mutex);
 	return rc ? rc : count;
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index af4e6a6..95d3ec8 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -1009,8 +1009,11 @@ static int qeth_l2_stop(struct net_device *dev)
 static int qeth_l2_probe_device(struct ccwgroup_device *gdev)
 {
 	struct qeth_card *card = dev_get_drvdata(&gdev->dev);
+	int rc;
 
-	qeth_l2_create_device_attributes(&gdev->dev);
+	rc = qeth_l2_create_device_attributes(&gdev->dev);
+	if (rc)
+		return rc;
 	INIT_LIST_HEAD(&card->vid_list);
 	hash_init(card->mac_htable);
 	card->options.layer2 = 1;
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 653f0fb..5fe37fa 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -3153,8 +3153,11 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
 static int qeth_l3_probe_device(struct ccwgroup_device *gdev)
 {
 	struct qeth_card *card = dev_get_drvdata(&gdev->dev);
+	int rc;
 
-	qeth_l3_create_device_attributes(&gdev->dev);
+	rc = qeth_l3_create_device_attributes(&gdev->dev);
+	if (rc)
+		return rc;
 	card->options.layer2 = 0;
 	card->info.hwtrap = 0;
 	return 0;
-- 
2.4.11


From a4726cfaf3a24975b0235ed2d837ac1e54ee963d Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Wed, 10 May 2017 19:07:52 +0200
Subject: [PATCH 05/41] s390/qeth: unbreak OSM and OSN support

[ Upstream commit 2d2ebb3ed0c6acfb014f98e427298673a5d07b82 ]

commit b4d72c08b358 ("qeth: bridgeport support - basic control")
broke the support for OSM and OSN devices as follows:

As OSM and OSN are L2 only, qeth_core_probe_device() does an early
setup by loading the l2 discipline and calling qeth_l2_probe_device().
In this context, adding the l2-specific bridgeport sysfs attributes
via qeth_l2_create_device_attributes() hits a BUG_ON in fs/sysfs/group.c,
since the basic sysfs infrastructure for the device hasn't been
established yet.

Note that OSN actually has its own unique sysfs attributes
(qeth_osn_devtype), so the additional attributes shouldn't be created
at all.
For OSM, add a new qeth_l2_devtype that contains all the common
and l2-specific sysfs attributes.
When qeth_core_probe_device() does early setup for OSM or OSN, assign
the corresponding devtype so that the ccwgroup probe code creates the
full set of sysfs attributes.
This allows us to skip qeth_l2_create_device_attributes() in case
of an early setup.

Any device that can't do early setup will initially have only the
generic sysfs attributes, and when it's probed later
qeth_l2_probe_device() adds the l2-specific attributes.

If an early-setup device is removed (by calling ccwgroup_ungroup()),
device_unregister() will - using the devtype - delete the
l2-specific attributes before qeth_l2_remove_device() is called.
So make sure to not remove them twice.

What complicates the issue is that qeth_l2_probe_device() and
qeth_l2_remove_device() is also called on a device when its
layer2 attribute changes (ie. its layer mode is switched).
For early-setup devices this wouldn't work properly - we wouldn't
remove the l2-specific attributes when switching to L3.
But switching the layer mode doesn't actually make any sense;
we already decided that the device can only operate in L2!
So just refuse to switch the layer mode on such devices. Note that
OSN doesn't have a layer2 attribute, so we only need to special-case
OSM.

Based on an initial patch by Ursula Braun.

Fixes: b4d72c08b358 ("qeth: bridgeport support - basic control")
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core.h      |  4 ++++
 drivers/s390/net/qeth_core_main.c | 17 +++++++++--------
 drivers/s390/net/qeth_core_sys.c  | 22 ++++++++++++++--------
 drivers/s390/net/qeth_l2.h        |  2 ++
 drivers/s390/net/qeth_l2_main.c   | 17 +++++++++++++----
 drivers/s390/net/qeth_l2_sys.c    |  8 ++++++++
 drivers/s390/net/qeth_l3_main.c   |  1 +
 7 files changed, 51 insertions(+), 20 deletions(-)

diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index d9561e3..a26b7e8 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -714,6 +714,7 @@ enum qeth_discipline_id {
 };
 
 struct qeth_discipline {
+	const struct device_type *devtype;
 	void (*start_poll)(struct ccw_device *, int, unsigned long);
 	qdio_handler_t *input_handler;
 	qdio_handler_t *output_handler;
@@ -889,6 +890,9 @@ extern struct qeth_discipline qeth_l2_discipline;
 extern struct qeth_discipline qeth_l3_discipline;
 extern const struct attribute_group *qeth_generic_attr_groups[];
 extern const struct attribute_group *qeth_osn_attr_groups[];
+extern const struct attribute_group qeth_device_attr_group;
+extern const struct attribute_group qeth_device_blkt_group;
+extern const struct device_type qeth_generic_devtype;
 extern struct workqueue_struct *qeth_wq;
 
 int qeth_card_hw_is_reachable(struct qeth_card *);
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 5c072b7..3a8ff75 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -5460,10 +5460,12 @@ void qeth_core_free_discipline(struct qeth_card *card)
 	card->discipline = NULL;
 }
 
-static const struct device_type qeth_generic_devtype = {
+const struct device_type qeth_generic_devtype = {
 	.name = "qeth_generic",
 	.groups = qeth_generic_attr_groups,
 };
+EXPORT_SYMBOL_GPL(qeth_generic_devtype);
+
 static const struct device_type qeth_osn_devtype = {
 	.name = "qeth_osn",
 	.groups = qeth_osn_attr_groups,
@@ -5589,23 +5591,22 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev)
 		goto err_card;
 	}
 
-	if (card->info.type == QETH_CARD_TYPE_OSN)
-		gdev->dev.type = &qeth_osn_devtype;
-	else
-		gdev->dev.type = &qeth_generic_devtype;
-
 	switch (card->info.type) {
 	case QETH_CARD_TYPE_OSN:
 	case QETH_CARD_TYPE_OSM:
 		rc = qeth_core_load_discipline(card, QETH_DISCIPLINE_LAYER2);
 		if (rc)
 			goto err_card;
+
+		gdev->dev.type = (card->info.type != QETH_CARD_TYPE_OSN)
+					? card->discipline->devtype
+					: &qeth_osn_devtype;
 		rc = card->discipline->setup(card->gdev);
 		if (rc)
 			goto err_disc;
-	case QETH_CARD_TYPE_OSD:
-	case QETH_CARD_TYPE_OSX:
+		break;
 	default:
+		gdev->dev.type = &qeth_generic_devtype;
 		break;
 	}
 
diff --git a/drivers/s390/net/qeth_core_sys.c b/drivers/s390/net/qeth_core_sys.c
index 412ff61..db6a285 100644
--- a/drivers/s390/net/qeth_core_sys.c
+++ b/drivers/s390/net/qeth_core_sys.c
@@ -413,12 +413,16 @@ static ssize_t qeth_dev_layer2_store(struct device *dev,
 
 	if (card->options.layer2 == newdis)
 		goto out;
-	else {
-		card->info.mac_bits  = 0;
-		if (card->discipline) {
-			card->discipline->remove(card->gdev);
-			qeth_core_free_discipline(card);
-		}
+	if (card->info.type == QETH_CARD_TYPE_OSM) {
+		/* fixed layer, can't switch */
+		rc = -EOPNOTSUPP;
+		goto out;
+	}
+
+	card->info.mac_bits = 0;
+	if (card->discipline) {
+		card->discipline->remove(card->gdev);
+		qeth_core_free_discipline(card);
 	}
 
 	rc = qeth_core_load_discipline(card, newdis);
@@ -705,10 +709,11 @@ static struct attribute *qeth_blkt_device_attrs[] = {
 	&dev_attr_inter_jumbo.attr,
 	NULL,
 };
-static struct attribute_group qeth_device_blkt_group = {
+const struct attribute_group qeth_device_blkt_group = {
 	.name = "blkt",
 	.attrs = qeth_blkt_device_attrs,
 };
+EXPORT_SYMBOL_GPL(qeth_device_blkt_group);
 
 static struct attribute *qeth_device_attrs[] = {
 	&dev_attr_state.attr,
@@ -728,9 +733,10 @@ static struct attribute *qeth_device_attrs[] = {
 	&dev_attr_switch_attrs.attr,
 	NULL,
 };
-static struct attribute_group qeth_device_attr_group = {
+const struct attribute_group qeth_device_attr_group = {
 	.attrs = qeth_device_attrs,
 };
+EXPORT_SYMBOL_GPL(qeth_device_attr_group);
 
 const struct attribute_group *qeth_generic_attr_groups[] = {
 	&qeth_device_attr_group,
diff --git a/drivers/s390/net/qeth_l2.h b/drivers/s390/net/qeth_l2.h
index 29d9fb3..0d59f9a 100644
--- a/drivers/s390/net/qeth_l2.h
+++ b/drivers/s390/net/qeth_l2.h
@@ -8,6 +8,8 @@
 
 #include "qeth_core.h"
 
+extern const struct attribute_group *qeth_l2_attr_groups[];
+
 int qeth_l2_create_device_attributes(struct device *);
 void qeth_l2_remove_device_attributes(struct device *);
 void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card);
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 95d3ec8..918e74f 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -1006,14 +1006,21 @@ static int qeth_l2_stop(struct net_device *dev)
 	return 0;
 }
 
+static const struct device_type qeth_l2_devtype = {
+	.name = "qeth_layer2",
+	.groups = qeth_l2_attr_groups,
+};
+
 static int qeth_l2_probe_device(struct ccwgroup_device *gdev)
 {
 	struct qeth_card *card = dev_get_drvdata(&gdev->dev);
 	int rc;
 
-	rc = qeth_l2_create_device_attributes(&gdev->dev);
-	if (rc)
-		return rc;
+	if (gdev->dev.type == &qeth_generic_devtype) {
+		rc = qeth_l2_create_device_attributes(&gdev->dev);
+		if (rc)
+			return rc;
+	}
 	INIT_LIST_HEAD(&card->vid_list);
 	hash_init(card->mac_htable);
 	card->options.layer2 = 1;
@@ -1025,7 +1032,8 @@ static void qeth_l2_remove_device(struct ccwgroup_device *cgdev)
 {
 	struct qeth_card *card = dev_get_drvdata(&cgdev->dev);
 
-	qeth_l2_remove_device_attributes(&cgdev->dev);
+	if (cgdev->dev.type == &qeth_generic_devtype)
+		qeth_l2_remove_device_attributes(&cgdev->dev);
 	qeth_set_allowed_threads(card, 0, 1);
 	wait_event(card->wait_q, qeth_threads_running(card, 0xffffffff) == 0);
 
@@ -1409,6 +1417,7 @@ static int qeth_l2_control_event(struct qeth_card *card,
 }
 
 struct qeth_discipline qeth_l2_discipline = {
+	.devtype = &qeth_l2_devtype,
 	.start_poll = qeth_qdio_start_poll,
 	.input_handler = (qdio_handler_t *) qeth_qdio_input_handler,
 	.output_handler = (qdio_handler_t *) qeth_qdio_output_handler,
diff --git a/drivers/s390/net/qeth_l2_sys.c b/drivers/s390/net/qeth_l2_sys.c
index 692db49..a48ed9e 100644
--- a/drivers/s390/net/qeth_l2_sys.c
+++ b/drivers/s390/net/qeth_l2_sys.c
@@ -272,3 +272,11 @@ void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card)
 	} else
 		qeth_bridgeport_an_set(card, 0);
 }
+
+const struct attribute_group *qeth_l2_attr_groups[] = {
+	&qeth_device_attr_group,
+	&qeth_device_blkt_group,
+	/* l2 specific, see l2_{create,remove}_device_attributes(): */
+	&qeth_l2_bridgeport_attr_group,
+	NULL,
+};
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 5fe37fa..aeeb672 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -3434,6 +3434,7 @@ static int qeth_l3_control_event(struct qeth_card *card,
 }
 
 struct qeth_discipline qeth_l3_discipline = {
+	.devtype = &qeth_generic_devtype,
 	.start_poll = qeth_qdio_start_poll,
 	.input_handler = (qdio_handler_t *) qeth_qdio_input_handler,
 	.output_handler = (qdio_handler_t *) qeth_qdio_output_handler,
-- 
2.4.11


From 5832799be4078521a9f14a661912396e9d1bef43 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Wed, 10 May 2017 19:07:53 +0200
Subject: [PATCH 06/41] s390/qeth: avoid null pointer dereference on OSN

[ Upstream commit 25e2c341e7818a394da9abc403716278ee646014 ]

Access card->dev only after checking whether's its valid.

Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Reviewed-by: Ursula Braun <ubraun@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_l2_main.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 918e74f..a2bb77d 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -1091,7 +1091,6 @@ static int qeth_l2_setup_netdev(struct qeth_card *card)
 	case QETH_CARD_TYPE_OSN:
 		card->dev = alloc_netdev(0, "osn%d", NET_NAME_UNKNOWN,
 					 ether_setup);
-		card->dev->flags |= IFF_NOARP;
 		break;
 	default:
 		card->dev = alloc_etherdev(0);
@@ -1106,9 +1105,12 @@ static int qeth_l2_setup_netdev(struct qeth_card *card)
 	card->dev->min_mtu = 64;
 	card->dev->max_mtu = ETH_MAX_MTU;
 	card->dev->netdev_ops = &qeth_l2_netdev_ops;
-	card->dev->ethtool_ops =
-		(card->info.type != QETH_CARD_TYPE_OSN) ?
-		&qeth_l2_ethtool_ops : &qeth_l2_osn_ops;
+	if (card->info.type == QETH_CARD_TYPE_OSN) {
+		card->dev->ethtool_ops = &qeth_l2_osn_ops;
+		card->dev->flags |= IFF_NOARP;
+	} else {
+		card->dev->ethtool_ops = &qeth_l2_ethtool_ops;
+	}
 	card->dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
 	if (card->info.type == QETH_CARD_TYPE_OSD && !card->info.guestlan) {
 		card->dev->hw_features = NETIF_F_SG;
-- 
2.4.11


From b4cadfbf658b6db25ac06e706926a9a257403a64 Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.vnet.ibm.com>
Date: Wed, 10 May 2017 19:07:54 +0200
Subject: [PATCH 07/41] s390/qeth: add missing hash table initializations

[ Upstream commit ebccc7397e4a49ff64c8f44a54895de9d32fe742 ]

commit 5f78e29ceebf ("qeth: optimize IP handling in rx_mode callback")
added new hash tables, but missed to initialize them.

Fixes: 5f78e29ceebf ("qeth: optimize IP handling in rx_mode callback")
Signed-off-by: Ursula Braun <ubraun@linux.vnet.ibm.com>
Reviewed-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_l3_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index aeeb672..d2fb50f 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -3158,6 +3158,8 @@ static int qeth_l3_probe_device(struct ccwgroup_device *gdev)
 	rc = qeth_l3_create_device_attributes(&gdev->dev);
 	if (rc)
 		return rc;
+	hash_init(card->ip_htable);
+	hash_init(card->ip_mc_htable);
 	card->options.layer2 = 0;
 	card->info.hwtrap = 0;
 	return 0;
-- 
2.4.11


From f03b22a0be6ca30e4c456cf3642fd1ee28690d5b Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 11 May 2017 01:53:15 +0200
Subject: [PATCH 08/41] bpf, arm64: fix faulty emission of map access in tail
 calls

[ Upstream commit d8b54110ee944de522ccd3531191f39986ec20f9 ]

Shubham was recently asking on netdev why in arm64 JIT we don't multiply
the index for accessing the tail call map by 8. That led me into testing
out arm64 JIT wrt tail calls and it turned out I got a NULL pointer
dereference on the tail call.

The buggy access is at:

  prog = array->ptrs[index];
  if (prog == NULL)
      goto out;

  [...]
  00000060:  d2800e0a  mov x10, #0x70 // #112
  00000064:  f86a682a  ldr x10, [x1,x10]
  00000068:  f862694b  ldr x11, [x10,x2]
  0000006c:  b40000ab  cbz x11, 0x00000080
  [...]

The code triggering the crash is f862694b. x1 at the time contains the
address of the bpf array, x10 offsetof(struct bpf_array, ptrs). Meaning,
above we load the pointer to the program at map slot 0 into x10. x10
can then be NULL if the slot is not occupied, which we later on try to
access with a user given offset in x2 that is the map index.

Fix this by emitting the following instead:

  [...]
  00000060:  d2800e0a  mov x10, #0x70 // #112
  00000064:  8b0a002a  add x10, x1, x10
  00000068:  d37df04b  lsl x11, x2, #3
  0000006c:  f86b694b  ldr x11, [x10,x11]
  00000070:  b40000ab  cbz x11, 0x00000084
  [...]

This basically adds the offset to ptrs to the base address of the bpf
array we got and we later on access the map with an index * 8 offset
relative to that. The tail call map itself is basically one large area
with meta data at the head followed by the array of prog pointers.
This makes tail calls working again, tested on Cavium ThunderX ARMv8.

Fixes: ddb55992b04d ("arm64: bpf: implement bpf_tail_call() helper")
Reported-by: Shubham Bansal <illusionist.neo@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/arm64/net/bpf_jit_comp.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index ce8ab04..4b0e0ed 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -252,8 +252,9 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	 */
 	off = offsetof(struct bpf_array, ptrs);
 	emit_a64_mov_i64(tmp, off, ctx);
-	emit(A64_LDR64(tmp, r2, tmp), ctx);
-	emit(A64_LDR64(prg, tmp, r3), ctx);
+	emit(A64_ADD(1, tmp, r2, tmp), ctx);
+	emit(A64_LSL(1, prg, r3, 3), ctx);
+	emit(A64_LDR64(prg, tmp, prg), ctx);
 	emit(A64_CBZ(1, prg, jmp_offset), ctx);
 
 	/* goto *(prog->bpf_func + prologue_size); */
-- 
2.4.11


From 6ad2310fc90c953aeffc2a75431df4a26249f587 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 11 May 2017 15:24:41 -0700
Subject: [PATCH 09/41] netem: fix skb_orphan_partial()

[ Upstream commit f6ba8d33cfbb46df569972e64dbb5bb7e929bfd9 ]

I should have known that lowering skb->truesize was dangerous :/

In case packets are not leaving the host via a standard Ethernet device,
but looped back to local sockets, bad things can happen, as reported
by Michael Madsen ( https://bugzilla.kernel.org/show_bug.cgi?id=195713 )

So instead of tweaking skb->truesize, lets change skb->destructor
and keep a reference on the owner socket via its sk_refcnt.

Fixes: f2f872f9272a ("netem: Introduce skb_orphan_partial() helper")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Michael Madsen <mkm@nabto.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 20 ++++++++------------
 1 file changed, 8 insertions(+), 12 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index 2c4f574..3a7260f 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1699,28 +1699,24 @@ EXPORT_SYMBOL(skb_set_owner_w);
  * delay queue. We want to allow the owner socket to send more
  * packets, as if they were already TX completed by a typical driver.
  * But we also want to keep skb->sk set because some packet schedulers
- * rely on it (sch_fq for example). So we set skb->truesize to a small
- * amount (1) and decrease sk_wmem_alloc accordingly.
+ * rely on it (sch_fq for example).
  */
 void skb_orphan_partial(struct sk_buff *skb)
 {
-	/* If this skb is a TCP pure ACK or already went here,
-	 * we have nothing to do. 2 is already a very small truesize.
-	 */
-	if (skb->truesize <= 2)
+	if (skb_is_tcp_pure_ack(skb))
 		return;
 
-	/* TCP stack sets skb->ooo_okay based on sk_wmem_alloc,
-	 * so we do not completely orphan skb, but transfert all
-	 * accounted bytes but one, to avoid unexpected reorders.
-	 */
 	if (skb->destructor == sock_wfree
 #ifdef CONFIG_INET
 	    || skb->destructor == tcp_wfree
 #endif
 		) {
-		atomic_sub(skb->truesize - 1, &skb->sk->sk_wmem_alloc);
-		skb->truesize = 1;
+		struct sock *sk = skb->sk;
+
+		if (atomic_inc_not_zero(&sk->sk_refcnt)) {
+			atomic_sub(skb->truesize, &sk->sk_wmem_alloc);
+			skb->destructor = sock_efree;
+		}
 	} else {
 		skb_orphan(skb);
 	}
-- 
2.4.11


From d0e75f4a1d3f6b5848177e219d7ce4d6b002db30 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 16 May 2017 13:27:53 -0700
Subject: [PATCH 10/41] net: fix compile error in skb_orphan_partial()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 9142e9007f2d7ab58a587a1e1d921b0064a339aa ]

If CONFIG_INET is not set, net/core/sock.c can not compile :

net/core/sock.c: In function ‘skb_orphan_partial’:
net/core/sock.c:1810:2: error: implicit declaration of function
‘skb_is_tcp_pure_ack’ [-Werror=implicit-function-declaration]
  if (skb_is_tcp_pure_ack(skb))
  ^

Fix this by always including <net/tcp.h>

Fixes: f6ba8d33cfbb ("netem: fix skb_orphan_partial()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index 3a7260f..59edc0e 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -138,10 +138,7 @@
 
 #include <trace/events/sock.h>
 
-#ifdef CONFIG_INET
 #include <net/tcp.h>
-#endif
-
 #include <net/busy_poll.h>
 
 static DEFINE_MUTEX(proto_list_mutex);
-- 
2.4.11


From 691759e44050364a77425e74d4eb4b2349088e6d Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Wed, 10 May 2017 17:01:27 -0700
Subject: [PATCH 11/41] tcp: avoid fragmenting peculiar skbs in SACK

[ Upstream commit b451e5d24ba6687c6f0e7319c727a709a1846c06 ]

This patch fixes a bug in splitting an SKB during SACK
processing. Specifically if an skb contains multiple
packets and is only partially sacked in the higher sequences,
tcp_match_sack_to_skb() splits the skb and marks the second fragment
as SACKed.

The current code further attempts rounding up the first fragment
to MSS boundaries. But it misses a boundary condition when the
rounded-up fragment size (pkt_len) is exactly skb size.  Spliting
such an skb is pointless and causses a kernel warning and aborts
the SACK processing. This patch universally checks such over-split
before calling tcp_fragment to prevent these unnecessary warnings.

Fixes: adb92db857ee ("tcp: Make SACK code to split only at mss boundaries")
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 3c6c878..b72b061 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1174,13 +1174,14 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb,
 		 */
 		if (pkt_len > mss) {
 			unsigned int new_len = (pkt_len / mss) * mss;
-			if (!in_sack && new_len < pkt_len) {
+			if (!in_sack && new_len < pkt_len)
 				new_len += mss;
-				if (new_len >= skb->len)
-					return 0;
-			}
 			pkt_len = new_len;
 		}
+
+		if (pkt_len >= skb->len && !in_sack)
+			return 0;
+
 		err = tcp_fragment(sk, skb, pkt_len, mss, GFP_ATOMIC);
 		if (err < 0)
 			return err;
-- 
2.4.11


From c6d0e1bc7e76bbe37e17ad468d154618c8572ebc Mon Sep 17 00:00:00 2001
From: Jon Paul Maloy <jon.maloy@ericsson.com>
Date: Thu, 11 May 2017 20:28:15 +0200
Subject: [PATCH 12/41] tipc: make macro tipc_wait_for_cond() smp safe

[ Upstream commit 844cf763fba654436d3a4279b6a672c196cf1901 ]

The macro tipc_wait_for_cond() is embedding the macro sk_wait_event()
to fulfil its task. The latter, in turn, is evaluating the stated
condition outside the socket lock context. This is problematic if
the condition is accessing non-trivial data structures which may be
altered by incoming interrupts, as is the case with the cong_links()
linked list, used by socket to keep track of the current set of
congested links. We sometimes see crashes when this list is accessed
by a condition function at the same time as a SOCK_WAKEUP interrupt
is removing an element from the list.

We fix this by expanding selected parts of sk_wait_event() into the
outer macro, while ensuring that all evaluations of a given condition
are performed under socket lock protection.

Fixes: commit 365ad353c256 ("tipc: reduce risk of user starvation during link congestion")
Reviewed-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/socket.c | 38 +++++++++++++++++++-------------------
 1 file changed, 19 insertions(+), 19 deletions(-)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index bdce99f..599c69b 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -361,25 +361,25 @@ static int tipc_sk_sock_err(struct socket *sock, long *timeout)
 	return 0;
 }
 
-#define tipc_wait_for_cond(sock_, timeout_, condition_)			\
-({								        \
-	int rc_ = 0;							\
-	int done_ = 0;							\
-									\
-	while (!(condition_) && !done_) {				\
-		struct sock *sk_ = sock->sk;				\
-		DEFINE_WAIT_FUNC(wait_, woken_wake_function);		\
-									\
-		rc_ = tipc_sk_sock_err(sock_, timeout_);		\
-		if (rc_)						\
-			break;						\
-		prepare_to_wait(sk_sleep(sk_), &wait_,			\
-				TASK_INTERRUPTIBLE);			\
-		done_ = sk_wait_event(sk_, timeout_,			\
-				      (condition_), &wait_);		\
-		remove_wait_queue(sk_sleep(sk_), &wait_);		\
-	}								\
-	rc_;								\
+#define tipc_wait_for_cond(sock_, timeo_, condition_)			       \
+({                                                                             \
+	struct sock *sk_;						       \
+	int rc_;							       \
+									       \
+	while ((rc_ = !(condition_))) {					       \
+		DEFINE_WAIT_FUNC(wait_, woken_wake_function);	               \
+		sk_ = (sock_)->sk;					       \
+		rc_ = tipc_sk_sock_err((sock_), timeo_);		       \
+		if (rc_)						       \
+			break;						       \
+		prepare_to_wait(sk_sleep(sk_), &wait_, TASK_INTERRUPTIBLE);    \
+		release_sock(sk_);					       \
+		*(timeo_) = wait_woken(&wait_, TASK_INTERRUPTIBLE, *(timeo_)); \
+		sched_annotate_sleep();				               \
+		lock_sock(sk_);						       \
+		remove_wait_queue(sk_sleep(sk_), &wait_);		       \
+	}								       \
+	rc_;								       \
 })
 
 /**
-- 
2.4.11


From 24af51b65df9ba719402315e1039554ea5e136d6 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Fri, 12 May 2017 14:39:52 +0800
Subject: [PATCH 13/41] sctp: fix src address selection if using secondary
 addresses for ipv6

[ Upstream commit dbc2b5e9a09e9a6664679a667ff81cff6e5f2641 ]

Commit 0ca50d12fe46 ("sctp: fix src address selection if using secondary
addresses") has fixed a src address selection issue when using secondary
addresses for ipv4.

Now sctp ipv6 also has the similar issue. When using a secondary address,
sctp_v6_get_dst tries to choose the saddr which has the most same bits
with the daddr by sctp_v6_addr_match_len. It may make some cases not work
as expected.

hostA:
  [1] fd21:356b:459a:cf10::11 (eth1)
  [2] fd21:356b:459a:cf20::11 (eth2)

hostB:
  [a] fd21:356b:459a:cf30::2  (eth1)
  [b] fd21:356b:459a:cf40::2  (eth2)

route from hostA to hostB:
  fd21:356b:459a:cf30::/64 dev eth1  metric 1024  mtu 1500

The expected path should be:
  fd21:356b:459a:cf10::11 <-> fd21:356b:459a:cf30::2
But addr[2] matches addr[a] more bits than addr[1] does, according to
sctp_v6_addr_match_len. It causes the path to be:
  fd21:356b:459a:cf20::11 <-> fd21:356b:459a:cf30::2

This patch is to fix it with the same way as Marcelo's fix for sctp ipv4.
As no ip_dev_find for ipv6, this patch is to use ipv6_chk_addr to check
if the saddr is in a dev instead.

Note that for backwards compatibility, it will still do the addr_match_len
check here when no optimal is found.

Reported-by: Patrick Talbert <ptalbert@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ipv6.c | 46 +++++++++++++++++++++++++++++-----------------
 1 file changed, 29 insertions(+), 17 deletions(-)

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 961ee59..142b70e 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -240,12 +240,10 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 	struct sctp_bind_addr *bp;
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct sctp_sockaddr_entry *laddr;
-	union sctp_addr *baddr = NULL;
 	union sctp_addr *daddr = &t->ipaddr;
 	union sctp_addr dst_saddr;
 	struct in6_addr *final_p, final;
 	__u8 matchlen = 0;
-	__u8 bmatchlen;
 	sctp_scope_t scope;
 
 	memset(fl6, 0, sizeof(struct flowi6));
@@ -312,23 +310,37 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 	 */
 	rcu_read_lock();
 	list_for_each_entry_rcu(laddr, &bp->address_list, list) {
-		if (!laddr->valid)
+		struct dst_entry *bdst;
+		__u8 bmatchlen;
+
+		if (!laddr->valid ||
+		    laddr->state != SCTP_ADDR_SRC ||
+		    laddr->a.sa.sa_family != AF_INET6 ||
+		    scope > sctp_scope(&laddr->a))
 			continue;
-		if ((laddr->state == SCTP_ADDR_SRC) &&
-		    (laddr->a.sa.sa_family == AF_INET6) &&
-		    (scope <= sctp_scope(&laddr->a))) {
-			bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a);
-			if (!baddr || (matchlen < bmatchlen)) {
-				baddr = &laddr->a;
-				matchlen = bmatchlen;
-			}
-		}
-	}
-	if (baddr) {
-		fl6->saddr = baddr->v6.sin6_addr;
-		fl6->fl6_sport = baddr->v6.sin6_port;
+
+		fl6->saddr = laddr->a.v6.sin6_addr;
+		fl6->fl6_sport = laddr->a.v6.sin6_port;
 		final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
-		dst = ip6_dst_lookup_flow(sk, fl6, final_p);
+		bdst = ip6_dst_lookup_flow(sk, fl6, final_p);
+
+		if (!IS_ERR(bdst) &&
+		    ipv6_chk_addr(dev_net(bdst->dev),
+				  &laddr->a.v6.sin6_addr, bdst->dev, 1)) {
+			if (!IS_ERR_OR_NULL(dst))
+				dst_release(dst);
+			dst = bdst;
+			break;
+		}
+
+		bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a);
+		if (matchlen > bmatchlen)
+			continue;
+
+		if (!IS_ERR_OR_NULL(dst))
+			dst_release(dst);
+		dst = bdst;
+		matchlen = bmatchlen;
 	}
 	rcu_read_unlock();
 
-- 
2.4.11


From 5097969ca1e25a02a702cee78e11443776862537 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 17 May 2017 07:16:40 -0700
Subject: [PATCH 14/41] sctp: do not inherit ipv6_{mc|ac|fl}_list from parent

[ Upstream commit fdcee2cbb8438702ea1b328fb6e0ac5e9a40c7f8 ]

SCTP needs fixes similar to 83eaddab4378 ("ipv6/dccp: do not inherit
ipv6_mc_list from parent"), otherwise bad things can happen.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ipv6.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 142b70e..f5b45b8 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -677,6 +677,9 @@ static struct sock *sctp_v6_create_accept_sk(struct sock *sk,
 	newnp = inet6_sk(newsk);
 
 	memcpy(newnp, np, sizeof(struct ipv6_pinfo));
+	newnp->ipv6_mc_list = NULL;
+	newnp->ipv6_ac_list = NULL;
+	newnp->ipv6_fl_list = NULL;
 
 	rcu_read_lock();
 	opt = rcu_dereference(np->opt);
-- 
2.4.11


From 9226dbffffc7485c7c64a4799d7028c7eeb7c889 Mon Sep 17 00:00:00 2001
From: Douglas Caetano dos Santos <douglascs@taghos.com.br>
Date: Fri, 12 May 2017 15:19:15 -0300
Subject: [PATCH 15/41] net/packet: fix missing net_device reference release

[ Upstream commit d19b183cdc1fa3d70d6abe2a4c369e748cd7ebb8 ]

When using a TX ring buffer, if an error occurs processing a control
message (e.g. invalid message), the net_device reference is not
released.

Fixes c14ac9451c348 ("sock: enable timestamping using control messages")
Signed-off-by: Douglas Caetano dos Santos <douglascs@taghos.com.br>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index ea81ccf..b2d8e8c 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2614,13 +2614,6 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 		dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex);
 	}
 
-	sockc.tsflags = po->sk.sk_tsflags;
-	if (msg->msg_controllen) {
-		err = sock_cmsg_send(&po->sk, msg, &sockc);
-		if (unlikely(err))
-			goto out;
-	}
-
 	err = -ENXIO;
 	if (unlikely(dev == NULL))
 		goto out;
@@ -2628,6 +2621,13 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 	if (unlikely(!(dev->flags & IFF_UP)))
 		goto out_put;
 
+	sockc.tsflags = po->sk.sk_tsflags;
+	if (msg->msg_controllen) {
+		err = sock_cmsg_send(&po->sk, msg, &sockc);
+		if (unlikely(err))
+			goto out_put;
+	}
+
 	if (po->sk.sk_socket->type == SOCK_RAW)
 		reserve = dev->hard_header_len;
 	size_max = po->tx_ring.frame_size
-- 
2.4.11


From 826ab5332a3f8f64ee6ce4c608581afa69cead54 Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Mon, 3 Apr 2017 15:11:22 +0300
Subject: [PATCH 16/41] net/mlx5e: Use the correct pause values for ethtool
 advertising

[ Upstream commit b383b544f2666d67446b951a9a97af239dafed5d ]

Query the operational pause from firmware (PFCC register) instead of
always passing zeros.

Fixes: 665bc53969d7 ("net/mlx5e: Use new ethtool get/set link ksettings API")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Cc: kernel-team@fb.com
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index a004a5a..69bfd8f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -828,6 +828,8 @@ static int mlx5e_get_link_ksettings(struct net_device *netdev,
 	struct mlx5e_priv *priv    = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
 	u32 out[MLX5_ST_SZ_DW(ptys_reg)] = {0};
+	u32 rx_pause = 0;
+	u32 tx_pause = 0;
 	u32 eth_proto_cap;
 	u32 eth_proto_admin;
 	u32 eth_proto_lp;
@@ -850,11 +852,13 @@ static int mlx5e_get_link_ksettings(struct net_device *netdev,
 	an_disable_admin = MLX5_GET(ptys_reg, out, an_disable_admin);
 	an_status        = MLX5_GET(ptys_reg, out, an_status);
 
+	mlx5_query_port_pause(mdev, &rx_pause, &tx_pause);
+
 	ethtool_link_ksettings_zero_link_mode(link_ksettings, supported);
 	ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising);
 
 	get_supported(eth_proto_cap, link_ksettings);
-	get_advertising(eth_proto_admin, 0, 0, link_ksettings);
+	get_advertising(eth_proto_admin, tx_pause, rx_pause, link_ksettings);
 	get_speed_duplex(netdev, eth_proto_oper, link_ksettings);
 
 	eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap;
-- 
2.4.11


From e8dc9a40127686be2833d03289afbaaf0827ae5f Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Wed, 19 Apr 2017 14:35:15 +0300
Subject: [PATCH 17/41] net/mlx5e: Fix ethtool pause support and advertise
 reporting

[ Upstream commit e3c19503712d6360239b19c14cded56dd63c40d7 ]

Pause bit should set when RX pause is on, not TX pause.
Also, setting Asym_Pause is incorrect, and should be turned off.

Fixes: 665bc53969d7 ("net/mlx5e: Use new ethtool get/set link ksettings API")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Cc: kernel-team@fb.com
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 69bfd8f..949fbad 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -773,7 +773,6 @@ static void get_supported(u32 eth_proto_cap,
 	ptys2ethtool_supported_port(link_ksettings, eth_proto_cap);
 	ptys2ethtool_supported_link(supported, eth_proto_cap);
 	ethtool_link_ksettings_add_link_mode(link_ksettings, supported, Pause);
-	ethtool_link_ksettings_add_link_mode(link_ksettings, supported, Asym_Pause);
 }
 
 static void get_advertising(u32 eth_proto_cap, u8 tx_pause,
@@ -783,7 +782,7 @@ static void get_advertising(u32 eth_proto_cap, u8 tx_pause,
 	unsigned long *advertising = link_ksettings->link_modes.advertising;
 
 	ptys2ethtool_adver_link(advertising, eth_proto_cap);
-	if (tx_pause)
+	if (rx_pause)
 		ethtool_link_ksettings_add_link_mode(link_ksettings, advertising, Pause);
 	if (tx_pause ^ rx_pause)
 		ethtool_link_ksettings_add_link_mode(link_ksettings, advertising, Asym_Pause);
-- 
2.4.11


From f15cb0d4d673b67d1b3dae0af1a1192f987ac869 Mon Sep 17 00:00:00 2001
From: Soheil Hassas Yeganeh <soheil@google.com>
Date: Mon, 15 May 2017 17:05:47 -0400
Subject: [PATCH 18/41] tcp: eliminate negative reordering in
 tcp_clean_rtx_queue

[ Upstream commit bafbb9c73241760023d8981191ddd30bb1c6dbac ]

tcp_ack() can call tcp_fragment() which may dededuct the
value tp->fackets_out when MSS changes. When prior_fackets
is larger than tp->fackets_out, tcp_clean_rtx_queue() can
invoke tcp_update_reordering() with negative values. This
results in absurd tp->reodering values higher than
sysctl_tcp_max_reordering.

Note that tcp_update_reordering indeeds sets tp->reordering
to min(sysctl_tcp_max_reordering, metric), but because
the comparison is signed, a negative metric always wins.

Fixes: c7caf8d3ed7a ("[TCP]: Fix reord detection due to snd_una covered holes")
Reported-by: Rebecca Isaacs <risaacs@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index b72b061..896a045 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3189,7 +3189,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 			int delta;
 
 			/* Non-retransmitted hole got filled? That's reordering */
-			if (reord < prior_fackets)
+			if (reord < prior_fackets && reord <= tp->fackets_out)
 				tcp_update_reordering(sk, tp->fackets_out - reord, 0);
 
 			delta = tcp_is_fack(tp) ? pkts_acked :
-- 
2.4.11


From 65f70173348ae15e17f519007d235520fddd3cc3 Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.vnet.ibm.com>
Date: Mon, 15 May 2017 17:33:37 +0200
Subject: [PATCH 19/41] smc: switch to usage of IB_PD_UNSAFE_GLOBAL_RKEY

[ Upstream commit 263eec9b2a82e8697d064709414914b5b10ac538 ]

Currently, SMC enables remote access to physical memory when a user
has successfully configured and established an SMC-connection until ten
minutes after the last SMC connection is closed. Because this is considered
a security risk, drivers are supposed to use IB_PD_UNSAFE_GLOBAL_RKEY in
such a case.

This patch changes the current SMC code to use IB_PD_UNSAFE_GLOBAL_RKEY.
This improves user awareness, but does not remove the security risk itself.

Signed-off-by: Ursula Braun <ubraun@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/smc_clc.c  |  4 ++--
 net/smc/smc_core.c | 16 +++-------------
 net/smc/smc_core.h |  2 +-
 net/smc/smc_ib.c   | 21 ++-------------------
 net/smc/smc_ib.h   |  2 --
 5 files changed, 8 insertions(+), 37 deletions(-)

diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index e41f594..03ec058 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -204,7 +204,7 @@ int smc_clc_send_confirm(struct smc_sock *smc)
 	memcpy(&cclc.lcl.mac, &link->smcibdev->mac[link->ibport - 1], ETH_ALEN);
 	hton24(cclc.qpn, link->roce_qp->qp_num);
 	cclc.rmb_rkey =
-		htonl(conn->rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey);
+		htonl(conn->rmb_desc->rkey[SMC_SINGLE_LINK]);
 	cclc.conn_idx = 1; /* for now: 1 RMB = 1 RMBE */
 	cclc.rmbe_alert_token = htonl(conn->alert_token_local);
 	cclc.qp_mtu = min(link->path_mtu, link->peer_mtu);
@@ -256,7 +256,7 @@ int smc_clc_send_accept(struct smc_sock *new_smc, int srv_first_contact)
 	memcpy(&aclc.lcl.mac, link->smcibdev->mac[link->ibport - 1], ETH_ALEN);
 	hton24(aclc.qpn, link->roce_qp->qp_num);
 	aclc.rmb_rkey =
-		htonl(conn->rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey);
+		htonl(conn->rmb_desc->rkey[SMC_SINGLE_LINK]);
 	aclc.conn_idx = 1;			/* as long as 1 RMB = 1 RMBE */
 	aclc.rmbe_alert_token = htonl(conn->alert_token_local);
 	aclc.qp_mtu = link->path_mtu;
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 0eac633..88cbb8a 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -613,19 +613,8 @@ int smc_rmb_create(struct smc_sock *smc)
 			rmb_desc = NULL;
 			continue; /* if mapping failed, try smaller one */
 		}
-		rc = smc_ib_get_memory_region(lgr->lnk[SMC_SINGLE_LINK].roce_pd,
-					      IB_ACCESS_REMOTE_WRITE |
-					      IB_ACCESS_LOCAL_WRITE,
-					     &rmb_desc->mr_rx[SMC_SINGLE_LINK]);
-		if (rc) {
-			smc_ib_buf_unmap(lgr->lnk[SMC_SINGLE_LINK].smcibdev,
-					 tmp_bufsize, rmb_desc,
-					 DMA_FROM_DEVICE);
-			kfree(rmb_desc->cpu_addr);
-			kfree(rmb_desc);
-			rmb_desc = NULL;
-			continue;
-		}
+		rmb_desc->rkey[SMC_SINGLE_LINK] =
+			lgr->lnk[SMC_SINGLE_LINK].roce_pd->unsafe_global_rkey;
 		rmb_desc->used = 1;
 		write_lock_bh(&lgr->rmbs_lock);
 		list_add(&rmb_desc->list,
@@ -668,6 +657,7 @@ int smc_rmb_rtoken_handling(struct smc_connection *conn,
 
 	for (i = 0; i < SMC_RMBS_PER_LGR_MAX; i++) {
 		if ((lgr->rtokens[i][SMC_SINGLE_LINK].rkey == rkey) &&
+		    (lgr->rtokens[i][SMC_SINGLE_LINK].dma_addr == dma_addr) &&
 		    test_bit(i, lgr->rtokens_used_mask)) {
 			conn->rtoken_idx = i;
 			return 0;
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index 27eb3805..b013cb4 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -93,7 +93,7 @@ struct smc_buf_desc {
 	u64			dma_addr[SMC_LINKS_PER_LGR_MAX];
 						/* mapped address of buffer */
 	void			*cpu_addr;	/* virtual address of buffer */
-	struct ib_mr		*mr_rx[SMC_LINKS_PER_LGR_MAX];
+	u32			rkey[SMC_LINKS_PER_LGR_MAX];
 						/* for rmb only:
 						 * rkey provided to peer
 						 */
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index e6743c0..51e5f01 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -37,24 +37,6 @@ u8 local_systemid[SMC_SYSTEMID_LEN] = SMC_LOCAL_SYSTEMID_RESET;	/* unique system
 								 * identifier
 								 */
 
-int smc_ib_get_memory_region(struct ib_pd *pd, int access_flags,
-			     struct ib_mr **mr)
-{
-	int rc;
-
-	if (*mr)
-		return 0; /* already done */
-
-	/* obtain unique key -
-	 * next invocation of get_dma_mr returns a different key!
-	 */
-	*mr = pd->device->get_dma_mr(pd, access_flags);
-	rc = PTR_ERR_OR_ZERO(*mr);
-	if (IS_ERR(*mr))
-		*mr = NULL;
-	return rc;
-}
-
 static int smc_ib_modify_qp_init(struct smc_link *lnk)
 {
 	struct ib_qp_attr qp_attr;
@@ -213,7 +195,8 @@ int smc_ib_create_protection_domain(struct smc_link *lnk)
 {
 	int rc;
 
-	lnk->roce_pd = ib_alloc_pd(lnk->smcibdev->ibdev, 0);
+	lnk->roce_pd = ib_alloc_pd(lnk->smcibdev->ibdev,
+				   IB_PD_UNSAFE_GLOBAL_RKEY);
 	rc = PTR_ERR_OR_ZERO(lnk->roce_pd);
 	if (IS_ERR(lnk->roce_pd))
 		lnk->roce_pd = NULL;
diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h
index a95f74b..cde2126 100644
--- a/net/smc/smc_ib.h
+++ b/net/smc/smc_ib.h
@@ -60,8 +60,6 @@ void smc_ib_dealloc_protection_domain(struct smc_link *lnk);
 int smc_ib_create_protection_domain(struct smc_link *lnk);
 void smc_ib_destroy_queue_pair(struct smc_link *lnk);
 int smc_ib_create_queue_pair(struct smc_link *lnk);
-int smc_ib_get_memory_region(struct ib_pd *pd, int access_flags,
-			     struct ib_mr **mr);
 int smc_ib_ready_link(struct smc_link *lnk);
 int smc_ib_modify_qp_rts(struct smc_link *lnk);
 int smc_ib_modify_qp_reset(struct smc_link *lnk);
-- 
2.4.11


From f95282287fe16310c9a256d8b94c53b7de87eb4b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 16 May 2017 09:51:38 +0300
Subject: [PATCH 20/41] net/smc: Add warning about remote memory exposure

[ Upstream commit 19a0f7e37c0761a0a1cbf550705a6063c9675223 ]

The driver explicitly bypasses APIs to register all memory once a
connection is made, and thus allows remote access to memory.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Acked-by: Ursula Braun <ubraun@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/Kconfig | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/smc/Kconfig b/net/smc/Kconfig
index c717ef0..3395485 100644
--- a/net/smc/Kconfig
+++ b/net/smc/Kconfig
@@ -8,6 +8,10 @@ config SMC
 	  The Linux implementation of the SMC-R solution is designed as
 	  a separate socket family SMC.
 
+	  Warning: SMC will expose all memory for remote reads and writes
+	  once a connection is established.  Don't enable this option except
+	  for tightly controlled lab environment.
+
 	  Select this option if you want to run SMC socket applications
 
 config SMC_DIAG
-- 
2.4.11


From 42a1e6a77f46bc78e9f857361630b6ed0291baa2 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Mon, 15 May 2017 23:19:17 -0700
Subject: [PATCH 21/41] net: Improve handling of failures on link and route
 dumps

[ Upstream commit f6c5775ff0bfa62b072face6bf1d40f659f194b2 ]

In general, rtnetlink dumps do not anticipate failure to dump a single
object (e.g., link or route) on a single pass. As both route and link
objects have grown via more attributes, that is no longer a given.

netlink dumps can handle a failure if the dump function returns an
error; specifically, netlink_dump adds the return code to the response
if it is <= 0 so userspace is notified of the failure. The missing
piece is the rtnetlink dump functions returning the error.

Fix route and link dump functions to return the errors if no object is
added to an skb (detected by skb->len != 0). IPv6 route dumps
(rt6_dump_route) already return the error; this patch updates IPv4 and
link dumps. Other dump functions may need to be ajusted as well.

Reported-by: Jan Moskyto Matejka <mq@ucw.cz>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c    | 36 ++++++++++++++++++++++++------------
 net/ipv4/fib_frontend.c | 15 +++++++++++----
 net/ipv4/fib_trie.c     | 26 ++++++++++++++------------
 3 files changed, 49 insertions(+), 28 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 69daf39..8d4a185 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1620,13 +1620,13 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 					       cb->nlh->nlmsg_seq, 0,
 					       flags,
 					       ext_filter_mask);
-			/* If we ran out of room on the first message,
-			 * we're in trouble
-			 */
-			WARN_ON((err == -EMSGSIZE) && (skb->len == 0));
 
-			if (err < 0)
-				goto out;
+			if (err < 0) {
+				if (likely(skb->len))
+					goto out;
+
+				goto out_err;
+			}
 
 			nl_dump_check_consistent(cb, nlmsg_hdr(skb));
 cont:
@@ -1634,10 +1634,12 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 		}
 	}
 out:
+	err = skb->len;
+out_err:
 	cb->args[1] = idx;
 	cb->args[0] = h;
 
-	return skb->len;
+	return err;
 }
 
 int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len)
@@ -3427,8 +3429,12 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb)
 				err = br_dev->netdev_ops->ndo_bridge_getlink(
 						skb, portid, seq, dev,
 						filter_mask, NLM_F_MULTI);
-				if (err < 0 && err != -EOPNOTSUPP)
-					break;
+				if (err < 0 && err != -EOPNOTSUPP) {
+					if (likely(skb->len))
+						break;
+
+					goto out_err;
+				}
 			}
 			idx++;
 		}
@@ -3439,16 +3445,22 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb)
 							      seq, dev,
 							      filter_mask,
 							      NLM_F_MULTI);
-				if (err < 0 && err != -EOPNOTSUPP)
-					break;
+				if (err < 0 && err != -EOPNOTSUPP) {
+					if (likely(skb->len))
+						break;
+
+					goto out_err;
+				}
 			}
 			idx++;
 		}
 	}
+	err = skb->len;
+out_err:
 	rcu_read_unlock();
 	cb->args[0] = idx;
 
-	return skb->len;
+	return err;
 }
 
 static inline size_t bridge_nlmsg_size(void)
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 8f2133f..a2f7de2 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -760,7 +760,7 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 	unsigned int e = 0, s_e;
 	struct fib_table *tb;
 	struct hlist_head *head;
-	int dumped = 0;
+	int dumped = 0, err;
 
 	if (nlmsg_len(cb->nlh) >= sizeof(struct rtmsg) &&
 	    ((struct rtmsg *) nlmsg_data(cb->nlh))->rtm_flags & RTM_F_CLONED)
@@ -780,20 +780,27 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 			if (dumped)
 				memset(&cb->args[2], 0, sizeof(cb->args) -
 						 2 * sizeof(cb->args[0]));
-			if (fib_table_dump(tb, skb, cb) < 0)
-				goto out;
+			err = fib_table_dump(tb, skb, cb);
+			if (err < 0) {
+				if (likely(skb->len))
+					goto out;
+
+				goto out_err;
+			}
 			dumped = 1;
 next:
 			e++;
 		}
 	}
 out:
+	err = skb->len;
+out_err:
 	rcu_read_unlock();
 
 	cb->args[1] = e;
 	cb->args[0] = h;
 
-	return skb->len;
+	return err;
 }
 
 /* Prepare and feed intra-kernel routing request.
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 2f0d823..08709fb 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -2079,6 +2079,8 @@ static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb,
 
 	/* rcu_read_lock is hold by caller */
 	hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) {
+		int err;
+
 		if (i < s_i) {
 			i++;
 			continue;
@@ -2089,17 +2091,14 @@ static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb,
 			continue;
 		}
 
-		if (fib_dump_info(skb, NETLINK_CB(cb->skb).portid,
-				  cb->nlh->nlmsg_seq,
-				  RTM_NEWROUTE,
-				  tb->tb_id,
-				  fa->fa_type,
-				  xkey,
-				  KEYLENGTH - fa->fa_slen,
-				  fa->fa_tos,
-				  fa->fa_info, NLM_F_MULTI) < 0) {
+		err = fib_dump_info(skb, NETLINK_CB(cb->skb).portid,
+				    cb->nlh->nlmsg_seq, RTM_NEWROUTE,
+				    tb->tb_id, fa->fa_type,
+				    xkey, KEYLENGTH - fa->fa_slen,
+				    fa->fa_tos, fa->fa_info, NLM_F_MULTI);
+		if (err < 0) {
 			cb->args[4] = i;
-			return -1;
+			return err;
 		}
 		i++;
 	}
@@ -2121,10 +2120,13 @@ int fib_table_dump(struct fib_table *tb, struct sk_buff *skb,
 	t_key key = cb->args[3];
 
 	while ((l = leaf_walk_rcu(&tp, key)) != NULL) {
-		if (fn_trie_dump_leaf(l, tb, skb, cb) < 0) {
+		int err;
+
+		err = fn_trie_dump_leaf(l, tb, skb, cb);
+		if (err < 0) {
 			cb->args[3] = key;
 			cb->args[2] = count;
-			return -1;
+			return err;
 		}
 
 		++count;
-- 
2.4.11


From 82e74f3ee6fad16bc02a9ba1ab21824e68b67bc4 Mon Sep 17 00:00:00 2001
From: Craig Gallek <kraig@google.com>
Date: Tue, 16 May 2017 14:36:23 -0400
Subject: [PATCH 22/41] ipv6: Prevent overrun when parsing v6 header options

[ Upstream commit 2423496af35d94a87156b063ea5cedffc10a70a1 ]

The KASAN warning repoted below was discovered with a syzkaller
program.  The reproducer is basically:
  int s = socket(AF_INET6, SOCK_RAW, NEXTHDR_HOP);
  send(s, &one_byte_of_data, 1, MSG_MORE);
  send(s, &more_than_mtu_bytes_data, 2000, 0);

The socket() call sets the nexthdr field of the v6 header to
NEXTHDR_HOP, the first send call primes the payload with a non zero
byte of data, and the second send call triggers the fragmentation path.

The fragmentation code tries to parse the header options in order
to figure out where to insert the fragment option.  Since nexthdr points
to an invalid option, the calculation of the size of the network header
can made to be much larger than the linear section of the skb and data
is read outside of it.

This fix makes ip6_find_1stfrag return an error if it detects
running out-of-bounds.

[   42.361487] ==================================================================
[   42.364412] BUG: KASAN: slab-out-of-bounds in ip6_fragment+0x11c8/0x3730
[   42.365471] Read of size 840 at addr ffff88000969e798 by task ip6_fragment-oo/3789
[   42.366469]
[   42.366696] CPU: 1 PID: 3789 Comm: ip6_fragment-oo Not tainted 4.11.0+ #41
[   42.367628] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.1-1ubuntu1 04/01/2014
[   42.368824] Call Trace:
[   42.369183]  dump_stack+0xb3/0x10b
[   42.369664]  print_address_description+0x73/0x290
[   42.370325]  kasan_report+0x252/0x370
[   42.370839]  ? ip6_fragment+0x11c8/0x3730
[   42.371396]  check_memory_region+0x13c/0x1a0
[   42.371978]  memcpy+0x23/0x50
[   42.372395]  ip6_fragment+0x11c8/0x3730
[   42.372920]  ? nf_ct_expect_unregister_notifier+0x110/0x110
[   42.373681]  ? ip6_copy_metadata+0x7f0/0x7f0
[   42.374263]  ? ip6_forward+0x2e30/0x2e30
[   42.374803]  ip6_finish_output+0x584/0x990
[   42.375350]  ip6_output+0x1b7/0x690
[   42.375836]  ? ip6_finish_output+0x990/0x990
[   42.376411]  ? ip6_fragment+0x3730/0x3730
[   42.376968]  ip6_local_out+0x95/0x160
[   42.377471]  ip6_send_skb+0xa1/0x330
[   42.377969]  ip6_push_pending_frames+0xb3/0xe0
[   42.378589]  rawv6_sendmsg+0x2051/0x2db0
[   42.379129]  ? rawv6_bind+0x8b0/0x8b0
[   42.379633]  ? _copy_from_user+0x84/0xe0
[   42.380193]  ? debug_check_no_locks_freed+0x290/0x290
[   42.380878]  ? ___sys_sendmsg+0x162/0x930
[   42.381427]  ? rcu_read_lock_sched_held+0xa3/0x120
[   42.382074]  ? sock_has_perm+0x1f6/0x290
[   42.382614]  ? ___sys_sendmsg+0x167/0x930
[   42.383173]  ? lock_downgrade+0x660/0x660
[   42.383727]  inet_sendmsg+0x123/0x500
[   42.384226]  ? inet_sendmsg+0x123/0x500
[   42.384748]  ? inet_recvmsg+0x540/0x540
[   42.385263]  sock_sendmsg+0xca/0x110
[   42.385758]  SYSC_sendto+0x217/0x380
[   42.386249]  ? SYSC_connect+0x310/0x310
[   42.386783]  ? __might_fault+0x110/0x1d0
[   42.387324]  ? lock_downgrade+0x660/0x660
[   42.387880]  ? __fget_light+0xa1/0x1f0
[   42.388403]  ? __fdget+0x18/0x20
[   42.388851]  ? sock_common_setsockopt+0x95/0xd0
[   42.389472]  ? SyS_setsockopt+0x17f/0x260
[   42.390021]  ? entry_SYSCALL_64_fastpath+0x5/0xbe
[   42.390650]  SyS_sendto+0x40/0x50
[   42.391103]  entry_SYSCALL_64_fastpath+0x1f/0xbe
[   42.391731] RIP: 0033:0x7fbbb711e383
[   42.392217] RSP: 002b:00007ffff4d34f28 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
[   42.393235] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007fbbb711e383
[   42.394195] RDX: 0000000000001000 RSI: 00007ffff4d34f60 RDI: 0000000000000003
[   42.395145] RBP: 0000000000000046 R08: 00007ffff4d34f40 R09: 0000000000000018
[   42.396056] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000400aad
[   42.396598] R13: 0000000000000066 R14: 00007ffff4d34ee0 R15: 00007fbbb717af00
[   42.397257]
[   42.397411] Allocated by task 3789:
[   42.397702]  save_stack_trace+0x16/0x20
[   42.398005]  save_stack+0x46/0xd0
[   42.398267]  kasan_kmalloc+0xad/0xe0
[   42.398548]  kasan_slab_alloc+0x12/0x20
[   42.398848]  __kmalloc_node_track_caller+0xcb/0x380
[   42.399224]  __kmalloc_reserve.isra.32+0x41/0xe0
[   42.399654]  __alloc_skb+0xf8/0x580
[   42.400003]  sock_wmalloc+0xab/0xf0
[   42.400346]  __ip6_append_data.isra.41+0x2472/0x33d0
[   42.400813]  ip6_append_data+0x1a8/0x2f0
[   42.401122]  rawv6_sendmsg+0x11ee/0x2db0
[   42.401505]  inet_sendmsg+0x123/0x500
[   42.401860]  sock_sendmsg+0xca/0x110
[   42.402209]  ___sys_sendmsg+0x7cb/0x930
[   42.402582]  __sys_sendmsg+0xd9/0x190
[   42.402941]  SyS_sendmsg+0x2d/0x50
[   42.403273]  entry_SYSCALL_64_fastpath+0x1f/0xbe
[   42.403718]
[   42.403871] Freed by task 1794:
[   42.404146]  save_stack_trace+0x16/0x20
[   42.404515]  save_stack+0x46/0xd0
[   42.404827]  kasan_slab_free+0x72/0xc0
[   42.405167]  kfree+0xe8/0x2b0
[   42.405462]  skb_free_head+0x74/0xb0
[   42.405806]  skb_release_data+0x30e/0x3a0
[   42.406198]  skb_release_all+0x4a/0x60
[   42.406563]  consume_skb+0x113/0x2e0
[   42.406910]  skb_free_datagram+0x1a/0xe0
[   42.407288]  netlink_recvmsg+0x60d/0xe40
[   42.407667]  sock_recvmsg+0xd7/0x110
[   42.408022]  ___sys_recvmsg+0x25c/0x580
[   42.408395]  __sys_recvmsg+0xd6/0x190
[   42.408753]  SyS_recvmsg+0x2d/0x50
[   42.409086]  entry_SYSCALL_64_fastpath+0x1f/0xbe
[   42.409513]
[   42.409665] The buggy address belongs to the object at ffff88000969e780
[   42.409665]  which belongs to the cache kmalloc-512 of size 512
[   42.410846] The buggy address is located 24 bytes inside of
[   42.410846]  512-byte region [ffff88000969e780, ffff88000969e980)
[   42.411941] The buggy address belongs to the page:
[   42.412405] page:ffffea000025a780 count:1 mapcount:0 mapping:          (null) index:0x0 compound_mapcount: 0
[   42.413298] flags: 0x100000000008100(slab|head)
[   42.413729] raw: 0100000000008100 0000000000000000 0000000000000000 00000001800c000c
[   42.414387] raw: ffffea00002a9500 0000000900000007 ffff88000c401280 0000000000000000
[   42.415074] page dumped because: kasan: bad access detected
[   42.415604]
[   42.415757] Memory state around the buggy address:
[   42.416222]  ffff88000969e880: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[   42.416904]  ffff88000969e900: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[   42.417591] >ffff88000969e980: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[   42.418273]                    ^
[   42.418588]  ffff88000969ea00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[   42.419273]  ffff88000969ea80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[   42.419882] ==================================================================

Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Craig Gallek <kraig@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_offload.c |  2 ++
 net/ipv6/ip6_output.c  |  4 ++++
 net/ipv6/output_core.c | 14 ++++++++------
 net/ipv6/udp_offload.c |  2 ++
 4 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 93e58a5..eab36ab 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -117,6 +117,8 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 
 		if (udpfrag) {
 			unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr);
+			if (unfrag_ip6hlen < 0)
+				return ERR_PTR(unfrag_ip6hlen);
 			fptr = (struct frag_hdr *)((u8 *)ipv6h + unfrag_ip6hlen);
 			fptr->frag_off = htons(offset);
 			if (skb->next)
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 58f6288..01deecd 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -598,6 +598,10 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 	u8 *prevhdr, nexthdr = 0;
 
 	hlen = ip6_find_1stfragopt(skb, &prevhdr);
+	if (hlen < 0) {
+		err = hlen;
+		goto fail;
+	}
 	nexthdr = *prevhdr;
 
 	mtu = ip6_skb_dst_mtu(skb);
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index cd42523..e9065b8 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -79,14 +79,13 @@ EXPORT_SYMBOL(ipv6_select_ident);
 int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 {
 	u16 offset = sizeof(struct ipv6hdr);
-	struct ipv6_opt_hdr *exthdr =
-				(struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1);
 	unsigned int packet_len = skb_tail_pointer(skb) -
 		skb_network_header(skb);
 	int found_rhdr = 0;
 	*nexthdr = &ipv6_hdr(skb)->nexthdr;
 
-	while (offset + 1 <= packet_len) {
+	while (offset <= packet_len) {
+		struct ipv6_opt_hdr *exthdr;
 
 		switch (**nexthdr) {
 
@@ -107,13 +106,16 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 			return offset;
 		}
 
-		offset += ipv6_optlen(exthdr);
-		*nexthdr = &exthdr->nexthdr;
+		if (offset + sizeof(struct ipv6_opt_hdr) > packet_len)
+			return -EINVAL;
+
 		exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) +
 						 offset);
+		offset += ipv6_optlen(exthdr);
+		*nexthdr = &exthdr->nexthdr;
 	}
 
-	return offset;
+	return -EINVAL;
 }
 EXPORT_SYMBOL(ip6_find_1stfragopt);
 
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index ac858c4..b348cff 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -91,6 +91,8 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 		 * bytes to insert fragment header.
 		 */
 		unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr);
+		if (unfrag_ip6hlen < 0)
+			return ERR_PTR(unfrag_ip6hlen);
 		nexthdr = *prevhdr;
 		*prevhdr = NEXTHDR_FRAGMENT;
 		unfrag_len = (skb_network_header(skb) - skb_mac_header(skb)) +
-- 
2.4.11


From 259761d80bba1d6e3f79f22f0ce6d0b4aa244fe1 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Wed, 17 May 2017 22:54:11 -0400
Subject: [PATCH 23/41] ipv6: Check ip6_find_1stfragopt() return value
 properly.

[ Upstream commit 7dd7eb9513bd02184d45f000ab69d78cb1fa1531 ]

Do not use unsigned variables to see if it returns a negative
error or not.

Fixes: 2423496af35d ("ipv6: Prevent overrun when parsing v6 header options")
Reported-by: Julia Lawall <julia.lawall@lip6.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_offload.c | 9 ++++-----
 net/ipv6/ip6_output.c  | 7 +++----
 net/ipv6/udp_offload.c | 8 +++++---
 3 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index eab36ab..280268f 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -63,7 +63,6 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 	const struct net_offload *ops;
 	int proto;
 	struct frag_hdr *fptr;
-	unsigned int unfrag_ip6hlen;
 	unsigned int payload_len;
 	u8 *prevhdr;
 	int offset = 0;
@@ -116,10 +115,10 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 		skb->network_header = (u8 *)ipv6h - skb->head;
 
 		if (udpfrag) {
-			unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr);
-			if (unfrag_ip6hlen < 0)
-				return ERR_PTR(unfrag_ip6hlen);
-			fptr = (struct frag_hdr *)((u8 *)ipv6h + unfrag_ip6hlen);
+			int err = ip6_find_1stfragopt(skb, &prevhdr);
+			if (err < 0)
+				return ERR_PTR(err);
+			fptr = (struct frag_hdr *)((u8 *)ipv6h + err);
 			fptr->frag_off = htons(offset);
 			if (skb->next)
 				fptr->frag_off |= htons(IP6_MF);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 01deecd..d4a31be 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -597,11 +597,10 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 	int ptr, offset = 0, err = 0;
 	u8 *prevhdr, nexthdr = 0;
 
-	hlen = ip6_find_1stfragopt(skb, &prevhdr);
-	if (hlen < 0) {
-		err = hlen;
+	err = ip6_find_1stfragopt(skb, &prevhdr);
+	if (err < 0)
 		goto fail;
-	}
+	hlen = err;
 	nexthdr = *prevhdr;
 
 	mtu = ip6_skb_dst_mtu(skb);
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index b348cff..a2267f8 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -29,6 +29,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 	u8 frag_hdr_sz = sizeof(struct frag_hdr);
 	__wsum csum;
 	int tnl_hlen;
+	int err;
 
 	mss = skb_shinfo(skb)->gso_size;
 	if (unlikely(skb->len <= mss))
@@ -90,9 +91,10 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 		/* Find the unfragmentable header and shift it left by frag_hdr_sz
 		 * bytes to insert fragment header.
 		 */
-		unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr);
-		if (unfrag_ip6hlen < 0)
-			return ERR_PTR(unfrag_ip6hlen);
+		err = ip6_find_1stfragopt(skb, &prevhdr);
+		if (err < 0)
+			return ERR_PTR(err);
+		unfrag_ip6hlen = err;
 		nexthdr = *prevhdr;
 		*prevhdr = NEXTHDR_FRAGMENT;
 		unfrag_len = (skb_network_header(skb) - skb_mac_header(skb)) +
-- 
2.4.11


From 1d312fa07755450e2290cf2fd897efdbac29a43b Mon Sep 17 00:00:00 2001
From: Tobias Jungel <tobias.jungel@bisdn.de>
Date: Wed, 17 May 2017 09:29:12 +0200
Subject: [PATCH 24/41] bridge: netlink: check vlan_default_pvid range

[ Upstream commit a285860211bf257b0e6d522dac6006794be348af ]

Currently it is allowed to set the default pvid of a bridge to a value
above VLAN_VID_MASK (0xfff). This patch adds a check to br_validate and
returns -EINVAL in case the pvid is out of bounds.

Reproduce by calling:

[root@test ~]# ip l a type bridge
[root@test ~]# ip l a type dummy
[root@test ~]# ip l s bridge0 type bridge vlan_filtering 1
[root@test ~]# ip l s bridge0 type bridge vlan_default_pvid 9999
[root@test ~]# ip l s dummy0 master bridge0
[root@test ~]# bridge vlan
port	vlan ids
bridge0	 9999 PVID Egress Untagged

dummy0	 9999 PVID Egress Untagged

Fixes: 0f963b7592ef ("bridge: netlink: add support for default_pvid")
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: Tobias Jungel <tobias.jungel@bisdn.de>
Acked-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_netlink.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 225ef7d..0488c67 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -828,6 +828,13 @@ static int br_validate(struct nlattr *tb[], struct nlattr *data[])
 			return -EPROTONOSUPPORT;
 		}
 	}
+
+	if (data[IFLA_BR_VLAN_DEFAULT_PVID]) {
+		__u16 defpvid = nla_get_u16(data[IFLA_BR_VLAN_DEFAULT_PVID]);
+
+		if (defpvid >= VLAN_VID_MASK)
+			return -EINVAL;
+	}
 #endif
 
 	return 0;
-- 
2.4.11


From 7da2e6aea36359bb1d4751465d76b663647530f6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Wed, 17 May 2017 16:31:41 +0200
Subject: [PATCH 25/41] qmi_wwan: add another Lenovo EM74xx device ID
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 486181bcb3248e2f1977f4e69387a898234a4e1e ]

In their infinite wisdom, and never ending quest for end user frustration,
Lenovo has decided to use a new USB device ID for the wwan modules in
their 2017 laptops.  The actual hardware is still the Sierra Wireless
EM7455 or EM7430, depending on region.

Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 4e34568..87746c2 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -902,6 +902,8 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1199, 0x9071, 10)},	/* Sierra Wireless MC74xx */
 	{QMI_FIXED_INTF(0x1199, 0x9079, 8)},	/* Sierra Wireless EM74xx */
 	{QMI_FIXED_INTF(0x1199, 0x9079, 10)},	/* Sierra Wireless EM74xx */
+	{QMI_FIXED_INTF(0x1199, 0x907b, 8)},	/* Sierra Wireless EM74xx */
+	{QMI_FIXED_INTF(0x1199, 0x907b, 10)},	/* Sierra Wireless EM74xx */
 	{QMI_FIXED_INTF(0x1bbb, 0x011e, 4)},	/* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */
 	{QMI_FIXED_INTF(0x1bbb, 0x0203, 2)},	/* Alcatel L800MA */
 	{QMI_FIXED_INTF(0x2357, 0x0201, 4)},	/* TP-LINK HSUPA Modem MA180 */
-- 
2.4.11


From 8eabcd23295b61ade5cb7bb98a63d1c6a8550ee1 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Fri, 19 May 2017 22:20:29 +0800
Subject: [PATCH 26/41] bridge: start hello_timer when enabling KERNEL_STP in
 br_stp_start

[ Upstream commit 6d18c732b95c0a9d35e9f978b4438bba15412284 ]

Since commit 76b91c32dd86 ("bridge: stp: when using userspace stp stop
kernel hello and hold timers"), bridge would not start hello_timer if
stp_enabled is not KERNEL_STP when br_dev_open.

The problem is even if users set stp_enabled with KERNEL_STP later,
the timer will still not be started. It causes that KERNEL_STP can
not really work. Users have to re-ifup the bridge to avoid this.

This patch is to fix it by starting br->hello_timer when enabling
KERNEL_STP in br_stp_start.

As an improvement, it's also to start hello_timer again only when
br->stp_enabled is KERNEL_STP in br_hello_timer_expired, there is
no reason to start the timer again when it's NO_STP.

Fixes: 76b91c32dd86 ("bridge: stp: when using userspace stp stop kernel hello and hold timers")
Reported-by: Haidong Li <haili@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Reviewed-by: Ivan Vecera <cera@cera.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_stp_if.c    | 1 +
 net/bridge/br_stp_timer.c | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
index 08341d2..0db8102 100644
--- a/net/bridge/br_stp_if.c
+++ b/net/bridge/br_stp_if.c
@@ -179,6 +179,7 @@ static void br_stp_start(struct net_bridge *br)
 		br_debug(br, "using kernel STP\n");
 
 		/* To start timers on any ports left in blocking */
+		mod_timer(&br->hello_timer, jiffies + br->hello_time);
 		br_port_state_selection(br);
 	}
 
diff --git a/net/bridge/br_stp_timer.c b/net/bridge/br_stp_timer.c
index c98b3e5..60b6fe2 100644
--- a/net/bridge/br_stp_timer.c
+++ b/net/bridge/br_stp_timer.c
@@ -40,7 +40,7 @@ static void br_hello_timer_expired(unsigned long arg)
 	if (br->dev->flags & IFF_UP) {
 		br_config_bpdu_generation(br);
 
-		if (br->stp_enabled != BR_USER_STP)
+		if (br->stp_enabled == BR_KERNEL_STP)
 			mod_timer(&br->hello_timer,
 				  round_jiffies(jiffies + br->hello_time));
 	}
-- 
2.4.11


From e12bb5180f3a80adcddbf9da736884a68e5e0ca2 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 19 May 2017 14:17:48 -0700
Subject: [PATCH 27/41] ipv6: fix out of bound writes in __ip6_append_data()

[ Upstream commit 232cd35d0804cc241eb887bb8d4d9b3b9881c64a ]

Andrey Konovalov and idaifish@gmail.com reported crashes caused by
one skb shared_info being overwritten from __ip6_append_data()

Andrey program lead to following state :

copy -4200 datalen 2000 fraglen 2040
maxfraglen 2040 alloclen 2048 transhdrlen 0 offset 0 fraggap 6200

The skb_copy_and_csum_bits(skb_prev, maxfraglen, data + transhdrlen,
fraggap, 0); is overwriting skb->head and skb_shared_info

Since we apparently detect this rare condition too late, move the
code earlier to even avoid allocating skb and risking crashes.

Once again, many thanks to Andrey and syzkaller team.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Reported-by: <idaifish@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_output.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index d4a31be..bf8a58a 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1466,6 +1466,11 @@ static int __ip6_append_data(struct sock *sk,
 			 */
 			alloclen += sizeof(struct frag_hdr);
 
+			copy = datalen - transhdrlen - fraggap;
+			if (copy < 0) {
+				err = -EINVAL;
+				goto error;
+			}
 			if (transhdrlen) {
 				skb = sock_alloc_send_skb(sk,
 						alloclen + hh_len,
@@ -1515,13 +1520,9 @@ static int __ip6_append_data(struct sock *sk,
 				data += fraggap;
 				pskb_trim_unique(skb_prev, maxfraglen);
 			}
-			copy = datalen - transhdrlen - fraggap;
-
-			if (copy < 0) {
-				err = -EINVAL;
-				kfree_skb(skb);
-				goto error;
-			} else if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) {
+			if (copy > 0 &&
+			    getfrag(from, data + transhdrlen, offset,
+				    copy, fraggap, skb) < 0) {
 				err = -EFAULT;
 				kfree_skb(skb);
 				goto error;
-- 
2.4.11


From bce671e2b5f597fc0629d7ae4c0c00349330eb46 Mon Sep 17 00:00:00 2001
From: Jarod Wilson <jarod@redhat.com>
Date: Fri, 19 May 2017 19:43:45 -0400
Subject: [PATCH 28/41] bonding: fix accounting of active ports in 3ad

[ Upstream commit 751da2a69b7cc82d83dc310ed7606225f2d6e014 ]

As of 7bb11dc9f59d and 0622cab0341c, bond slaves in a 3ad bond are not
removed from the aggregator when they are down, and the active slave count
is NOT equal to number of ports in the aggregator, but rather the number
of ports in the aggregator that are still enabled. The sysfs spew for
bonding_show_ad_num_ports() has a comment that says "Show number of active
802.3ad ports.", but it's currently showing total number of ports, both
active and inactive. Remedy it by using the same logic introduced in
0622cab0341c in __bond_3ad_get_active_agg_info(), so sysfs, procfs and
netlink all report the number of active ports. Note that this means that
IFLA_BOND_AD_INFO_NUM_PORTS really means NUM_ACTIVE_PORTS instead of
NUM_PORTS, and thus perhaps should be renamed for clarity.

Lightly tested on a dual i40e lacp bond, simulating link downs with an ip
link set dev <slave2> down, was able to produce the state where I could
see both in the same aggregator, but a number of ports count of 1.

MII Status: up
Active Aggregator Info:
        Aggregator ID: 1
        Number of ports: 2 <---
Slave Interface: ens10
MII Status: up <---
Aggregator ID: 1
Slave Interface: ens11
MII Status: up
Aggregator ID: 1

MII Status: up
Active Aggregator Info:
        Aggregator ID: 1
        Number of ports: 1 <---
Slave Interface: ens10
MII Status: down <---
Aggregator ID: 1
Slave Interface: ens11
MII Status: up
Aggregator ID: 1

CC: Jay Vosburgh <j.vosburgh@gmail.com>
CC: Veaceslav Falico <vfalico@gmail.com>
CC: Andy Gospodarek <andy@greyhouse.net>
CC: netdev@vger.kernel.org
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_3ad.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index edc70ff..6dcc42d 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -2573,7 +2573,7 @@ int __bond_3ad_get_active_agg_info(struct bonding *bond,
 		return -1;
 
 	ad_info->aggregator_id = aggregator->aggregator_identifier;
-	ad_info->ports = aggregator->num_of_ports;
+	ad_info->ports = __agg_active_ports(aggregator);
 	ad_info->actor_key = aggregator->actor_oper_aggregator_key;
 	ad_info->partner_key = aggregator->partner_oper_aggregator_key;
 	ether_addr_copy(ad_info->partner_system,
-- 
2.4.11


From aa2427ec01d5ab3c35b816533426ae49e1f441a2 Mon Sep 17 00:00:00 2001
From: Mohamad Haj Yahia <mohamad@mellanox.com>
Date: Thu, 23 Feb 2017 11:19:36 +0200
Subject: [PATCH 29/41] net/mlx5: Avoid using pending command interface slots

[ Upstream commit 73dd3a4839c1d27c36d4dcc92e1ff44225ecbeb7 ]

Currently when firmware command gets stuck or it takes long time to
complete, the driver command will get timeout and the command slot is
freed and can be used for new commands, and if the firmware receive new
command on the old busy slot its behavior is unexpected and this could
be harmful.
To fix this when the driver command gets timeout we return failure,
but we don't free the command slot and we wait for the firmware to
explicitly respond to that command.
Once all the entries are busy we will stop processing new firmware
commands.

Fixes: 9cba4ebcf374 ('net/mlx5: Fix potential deadlock in command mode change')
Signed-off-by: Mohamad Haj Yahia <mohamad@mellanox.com>
Cc: kernel-team@fb.com
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c    | 41 +++++++++++++++++++++---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c     |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/health.c |  2 +-
 include/linux/mlx5/driver.h                      |  7 +++-
 4 files changed, 44 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index a380353..f95c869 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -770,7 +770,7 @@ static void cb_timeout_handler(struct work_struct *work)
 	mlx5_core_warn(dev, "%s(0x%x) timeout. Will cause a leak of a command resource\n",
 		       mlx5_command_str(msg_to_opcode(ent->in)),
 		       msg_to_opcode(ent->in));
-	mlx5_cmd_comp_handler(dev, 1UL << ent->idx);
+	mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
 }
 
 static void cmd_work_handler(struct work_struct *work)
@@ -800,6 +800,7 @@ static void cmd_work_handler(struct work_struct *work)
 	}
 
 	cmd->ent_arr[ent->idx] = ent;
+	set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state);
 	lay = get_inst(cmd, ent->idx);
 	ent->lay = lay;
 	memset(lay, 0, sizeof(*lay));
@@ -821,6 +822,20 @@ static void cmd_work_handler(struct work_struct *work)
 	if (ent->callback)
 		schedule_delayed_work(&ent->cb_timeout_work, cb_timeout);
 
+	/* Skip sending command to fw if internal error */
+	if (pci_channel_offline(dev->pdev) ||
+	    dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
+		u8 status = 0;
+		u32 drv_synd;
+
+		ent->ret = mlx5_internal_err_ret_value(dev, msg_to_opcode(ent->in), &drv_synd, &status);
+		MLX5_SET(mbox_out, ent->out, status, status);
+		MLX5_SET(mbox_out, ent->out, syndrome, drv_synd);
+
+		mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
+		return;
+	}
+
 	/* ring doorbell after the descriptor is valid */
 	mlx5_core_dbg(dev, "writing 0x%x to command doorbell\n", 1 << ent->idx);
 	wmb();
@@ -831,7 +846,7 @@ static void cmd_work_handler(struct work_struct *work)
 		poll_timeout(ent);
 		/* make sure we read the descriptor after ownership is SW */
 		rmb();
-		mlx5_cmd_comp_handler(dev, 1UL << ent->idx);
+		mlx5_cmd_comp_handler(dev, 1UL << ent->idx, (ent->ret == -ETIMEDOUT));
 	}
 }
 
@@ -875,7 +890,7 @@ static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
 		wait_for_completion(&ent->done);
 	} else if (!wait_for_completion_timeout(&ent->done, timeout)) {
 		ent->ret = -ETIMEDOUT;
-		mlx5_cmd_comp_handler(dev, 1UL << ent->idx);
+		mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
 	}
 
 	err = ent->ret;
@@ -1371,7 +1386,7 @@ static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg)
 	}
 }
 
-void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec)
+void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced)
 {
 	struct mlx5_cmd *cmd = &dev->cmd;
 	struct mlx5_cmd_work_ent *ent;
@@ -1391,6 +1406,19 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec)
 			struct semaphore *sem;
 
 			ent = cmd->ent_arr[i];
+
+			/* if we already completed the command, ignore it */
+			if (!test_and_clear_bit(MLX5_CMD_ENT_STATE_PENDING_COMP,
+						&ent->state)) {
+				/* only real completion can free the cmd slot */
+				if (!forced) {
+					mlx5_core_err(dev, "Command completion arrived after timeout (entry idx = %d).\n",
+						      ent->idx);
+					free_ent(cmd, ent->idx);
+				}
+				continue;
+			}
+
 			if (ent->callback)
 				cancel_delayed_work(&ent->cb_timeout_work);
 			if (ent->page_queue)
@@ -1413,7 +1441,10 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec)
 				mlx5_core_dbg(dev, "command completed. ret 0x%x, delivery status %s(0x%x)\n",
 					      ent->ret, deliv_status_to_str(ent->status), ent->status);
 			}
-			free_ent(cmd, ent->idx);
+
+			/* only real completion will free the entry slot */
+			if (!forced)
+				free_ent(cmd, ent->idx);
 
 			if (ent->callback) {
 				ds = ent->ts2 - ent->ts1;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index ea5d8d3..33eae5a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -422,7 +422,7 @@ static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr)
 			break;
 
 		case MLX5_EVENT_TYPE_CMD:
-			mlx5_cmd_comp_handler(dev, be32_to_cpu(eqe->data.cmd.vector));
+			mlx5_cmd_comp_handler(dev, be32_to_cpu(eqe->data.cmd.vector), false);
 			break;
 
 		case MLX5_EVENT_TYPE_PORT_CHANGE:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index d051539..44f59b1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -90,7 +90,7 @@ static void trigger_cmd_completions(struct mlx5_core_dev *dev)
 	spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags);
 
 	mlx5_core_dbg(dev, "vector 0x%llx\n", vector);
-	mlx5_cmd_comp_handler(dev, vector);
+	mlx5_cmd_comp_handler(dev, vector, true);
 	return;
 
 no_trig:
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 2fcff6b..c965d11 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -785,7 +785,12 @@ enum {
 
 typedef void (*mlx5_cmd_cbk_t)(int status, void *context);
 
+enum {
+	MLX5_CMD_ENT_STATE_PENDING_COMP,
+};
+
 struct mlx5_cmd_work_ent {
+	unsigned long		state;
 	struct mlx5_cmd_msg    *in;
 	struct mlx5_cmd_msg    *out;
 	void		       *uout;
@@ -979,7 +984,7 @@ void mlx5_cq_completion(struct mlx5_core_dev *dev, u32 cqn);
 void mlx5_rsc_event(struct mlx5_core_dev *dev, u32 rsn, int event_type);
 void mlx5_srq_event(struct mlx5_core_dev *dev, u32 srqn, int event_type);
 struct mlx5_core_srq *mlx5_core_get_srq(struct mlx5_core_dev *dev, u32 srqn);
-void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec);
+void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced);
 void mlx5_cq_event(struct mlx5_core_dev *dev, u32 cqn, int event_type);
 int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
 		       int nent, u64 mask, const char *name,
-- 
2.4.11


From 89ccac8f383ad19f7f3cb7b68c31b280272af1ee Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Tue, 23 May 2017 17:49:13 +0200
Subject: [PATCH 30/41] net: phy: marvell: Limit errata to 88m1101

[ Upstream commit f2899788353c13891412b273fdff5f02d49aa40f ]

The 88m1101 has an errata when configuring autoneg. However, it was
being applied to many other Marvell PHYs as well. Limit its scope to
just the 88m1101.

Fixes: 76884679c644 ("phylib: Add support for Marvell 88e1111S and 88e1145")
Reported-by: Daniel Walker <danielwa@cisco.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Acked-by: Harini Katakam <harinik@xilinx.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/marvell.c | 66 ++++++++++++++++++++++++++---------------------
 1 file changed, 37 insertions(+), 29 deletions(-)

diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index 272b051..9097e42 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -255,34 +255,6 @@ static int marvell_config_aneg(struct phy_device *phydev)
 {
 	int err;
 
-	/* The Marvell PHY has an errata which requires
-	 * that certain registers get written in order
-	 * to restart autonegotiation */
-	err = phy_write(phydev, MII_BMCR, BMCR_RESET);
-
-	if (err < 0)
-		return err;
-
-	err = phy_write(phydev, 0x1d, 0x1f);
-	if (err < 0)
-		return err;
-
-	err = phy_write(phydev, 0x1e, 0x200c);
-	if (err < 0)
-		return err;
-
-	err = phy_write(phydev, 0x1d, 0x5);
-	if (err < 0)
-		return err;
-
-	err = phy_write(phydev, 0x1e, 0);
-	if (err < 0)
-		return err;
-
-	err = phy_write(phydev, 0x1e, 0x100);
-	if (err < 0)
-		return err;
-
 	err = marvell_set_polarity(phydev, phydev->mdix_ctrl);
 	if (err < 0)
 		return err;
@@ -316,6 +288,42 @@ static int marvell_config_aneg(struct phy_device *phydev)
 	return 0;
 }
 
+static int m88e1101_config_aneg(struct phy_device *phydev)
+{
+	int err;
+
+	/* This Marvell PHY has an errata which requires
+	 * that certain registers get written in order
+	 * to restart autonegotiation
+	 */
+	err = phy_write(phydev, MII_BMCR, BMCR_RESET);
+
+	if (err < 0)
+		return err;
+
+	err = phy_write(phydev, 0x1d, 0x1f);
+	if (err < 0)
+		return err;
+
+	err = phy_write(phydev, 0x1e, 0x200c);
+	if (err < 0)
+		return err;
+
+	err = phy_write(phydev, 0x1d, 0x5);
+	if (err < 0)
+		return err;
+
+	err = phy_write(phydev, 0x1e, 0);
+	if (err < 0)
+		return err;
+
+	err = phy_write(phydev, 0x1e, 0x100);
+	if (err < 0)
+		return err;
+
+	return marvell_config_aneg(phydev);
+}
+
 static int m88e1111_config_aneg(struct phy_device *phydev)
 {
 	int err;
@@ -1892,7 +1900,7 @@ static struct phy_driver marvell_drivers[] = {
 		.flags = PHY_HAS_INTERRUPT,
 		.probe = marvell_probe,
 		.config_init = &marvell_config_init,
-		.config_aneg = &marvell_config_aneg,
+		.config_aneg = &m88e1101_config_aneg,
 		.read_status = &genphy_read_status,
 		.ack_interrupt = &marvell_ack_interrupt,
 		.config_intr = &marvell_config_intr,
-- 
2.4.11


From a273446ca9357e71f7f6397d4977ba86403545d1 Mon Sep 17 00:00:00 2001
From: Vlad Yasevich <vyasevich@gmail.com>
Date: Tue, 23 May 2017 13:38:41 -0400
Subject: [PATCH 31/41] vlan: Fix tcp checksum offloads in Q-in-Q vlans

[ Upstream commit 35d2f80b07bbe03fb358afb0bdeff7437a7d67ff ]

It appears that TCP checksum offloading has been broken for
Q-in-Q vlans.  The behavior was execerbated by the
series
    commit afb0bc972b52 ("Merge branch 'stacked_vlan_tso'")
that that enabled accleleration features on stacked vlans.

However, event without that series, it is possible to trigger
this issue.  It just requires a lot more specialized configuration.

The root cause is the interaction between how
netdev_intersect_features() works, the features actually set on
the vlan devices and HW having the ability to run checksum with
longer headers.

The issue starts when netdev_interesect_features() replaces
NETIF_F_HW_CSUM with a combination of NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM,
if the HW advertises IP|IPV6 specific checksums.  This happens
for tagged and multi-tagged packets.   However, HW that enables
IP|IPV6 checksum offloading doesn't gurantee that packets with
arbitrarily long headers can be checksummed.

This patch disables IP|IPV6 checksums on the packet for multi-tagged
packets.

CC: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
CC: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: Vladislav Yasevich <vyasevic@redhat.com>
Acked-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_vlan.h | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 8d5fcd6..283dc2f 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -614,14 +614,16 @@ static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb)
 static inline netdev_features_t vlan_features_check(const struct sk_buff *skb,
 						    netdev_features_t features)
 {
-	if (skb_vlan_tagged_multi(skb))
-		features = netdev_intersect_features(features,
-						     NETIF_F_SG |
-						     NETIF_F_HIGHDMA |
-						     NETIF_F_FRAGLIST |
-						     NETIF_F_HW_CSUM |
-						     NETIF_F_HW_VLAN_CTAG_TX |
-						     NETIF_F_HW_VLAN_STAG_TX);
+	if (skb_vlan_tagged_multi(skb)) {
+		/* In the case of multi-tagged packets, use a direct mask
+		 * instead of using netdev_interesect_features(), to make
+		 * sure that only devices supporting NETIF_F_HW_CSUM will
+		 * have checksum offloading support.
+		 */
+		features &= NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_HW_CSUM |
+			    NETIF_F_FRAGLIST | NETIF_F_HW_VLAN_CTAG_TX |
+			    NETIF_F_HW_VLAN_STAG_TX;
+	}
 
 	return features;
 }
-- 
2.4.11


From 5c80b088af97098bb30ed11ec3772ae934834007 Mon Sep 17 00:00:00 2001
From: Vlad Yasevich <vyasevich@gmail.com>
Date: Tue, 23 May 2017 13:38:42 -0400
Subject: [PATCH 32/41] be2net: Fix offload features for Q-in-Q packets

[ Upstream commit cc6e9de62a7f84c9293a2ea41bc412b55bb46e85 ]

At least some of the be2net cards do not seem to be capabled
of performing checksum offload computions on Q-in-Q packets.
In these case, the recevied checksum on the remote is invalid
and TCP syn packets are dropped.

This patch adds a call to check disbled acceleration features
on Q-in-Q tagged traffic.

CC: Sathya Perla <sathya.perla@broadcom.com>
CC: Ajit Khaparde <ajit.khaparde@broadcom.com>
CC: Sriharsha Basavapatna <sriharsha.basavapatna@broadcom.com>
CC: Somnath Kotur <somnath.kotur@broadcom.com>
Signed-off-by: Vladislav Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/emulex/benet/be_main.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 6be3b9a..ff617be 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -5027,9 +5027,11 @@ static netdev_features_t be_features_check(struct sk_buff *skb,
 	struct be_adapter *adapter = netdev_priv(dev);
 	u8 l4_hdr = 0;
 
-	/* The code below restricts offload features for some tunneled packets.
+	/* The code below restricts offload features for some tunneled and
+	 * Q-in-Q packets.
 	 * Offload features for normal (non tunnel) packets are unchanged.
 	 */
+	features = vlan_features_check(skb, features);
 	if (!skb->encapsulation ||
 	    !(adapter->flags & BE_FLAGS_VXLAN_OFFLOADS))
 		return features;
-- 
2.4.11


From ae78858dc6fa33234591dc673694cafb54bae9df Mon Sep 17 00:00:00 2001
From: Vlad Yasevich <vyasevich@gmail.com>
Date: Tue, 23 May 2017 13:38:43 -0400
Subject: [PATCH 33/41] virtio-net: enable TSO/checksum offloads for Q-in-Q
 vlans

[ Upstream commit 2836b4f224d4fd7d1a2b23c3eecaf0f0ae199a74 ]

Since virtio does not provide it's own ndo_features_check handler,
TSO, and now checksum offload, are disabled for stacked vlans.
Re-enable the support and let the host take care of it.  This
restores/improves Guest-to-Guest performance over Q-in-Q vlans.

Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Vladislav Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index f365846..d9d8f4f 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1894,6 +1894,7 @@ static const struct net_device_ops virtnet_netdev = {
 	.ndo_poll_controller = virtnet_netpoll,
 #endif
 	.ndo_xdp		= virtnet_xdp,
+	.ndo_features_check	= passthru_features_check,
 };
 
 static void virtnet_config_changed_work(struct work_struct *work)
-- 
2.4.11


From 650719ce861b3fa19da1dec8ab3c3f35a0d3696a Mon Sep 17 00:00:00 2001
From: Eric Garver <e@erig.me>
Date: Tue, 23 May 2017 18:37:27 -0400
Subject: [PATCH 34/41] geneve: fix fill_info when using collect_metadata

[ Upstream commit 11387fe4a98f75d1f4cdb3efe3b42b19205c9df5 ]

Since 9b4437a5b870 ("geneve: Unify LWT and netdev handling.") fill_info
does not return UDP_ZERO_CSUM6_RX when using COLLECT_METADATA. This is
because it uses ip_tunnel_info_af() with the device level info, which is
not valid for COLLECT_METADATA.

Fix by checking for the presence of the actual sockets.

Fixes: 9b4437a5b870 ("geneve: Unify LWT and netdev handling.")
Signed-off-by: Eric Garver <e@erig.me>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index dec5d56..959fd12 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1293,7 +1293,7 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	if (nla_put_u32(skb, IFLA_GENEVE_ID, vni))
 		goto nla_put_failure;
 
-	if (ip_tunnel_info_af(info) == AF_INET) {
+	if (rtnl_dereference(geneve->sock4)) {
 		if (nla_put_in_addr(skb, IFLA_GENEVE_REMOTE,
 				    info->key.u.ipv4.dst))
 			goto nla_put_failure;
@@ -1302,8 +1302,10 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev)
 			       !!(info->key.tun_flags & TUNNEL_CSUM)))
 			goto nla_put_failure;
 
+	}
+
 #if IS_ENABLED(CONFIG_IPV6)
-	} else {
+	if (rtnl_dereference(geneve->sock6)) {
 		if (nla_put_in6_addr(skb, IFLA_GENEVE_REMOTE6,
 				     &info->key.u.ipv6.dst))
 			goto nla_put_failure;
@@ -1315,8 +1317,8 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev)
 		if (nla_put_u8(skb, IFLA_GENEVE_UDP_ZERO_CSUM6_RX,
 			       !geneve->use_udp6_rx_checksums))
 			goto nla_put_failure;
-#endif
 	}
+#endif
 
 	if (nla_put_u8(skb, IFLA_GENEVE_TTL, info->key.ttl) ||
 	    nla_put_u8(skb, IFLA_GENEVE_TOS, info->key.tos) ||
-- 
2.4.11


From a54f5645199011f7eadb27a69155f3a553e58660 Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Wed, 24 May 2017 09:59:31 -0700
Subject: [PATCH 35/41] tcp: avoid fastopen API to be used on AF_UNSPEC

[ Upstream commit ba615f675281d76fd19aa03558777f81fb6b6084 ]

Fastopen API should be used to perform fastopen operations on the TCP
socket. It does not make sense to use fastopen API to perform disconnect
by calling it with AF_UNSPEC. The fastopen data path is also prone to
race conditions and bugs when using with AF_UNSPEC.

One issue reported and analyzed by Vegard Nossum is as follows:
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Thread A:                            Thread B:
------------------------------------------------------------------------
sendto()
 - tcp_sendmsg()
     - sk_stream_memory_free() = 0
         - goto wait_for_sndbuf
	     - sk_stream_wait_memory()
	        - sk_wait_event() // sleep
          |                          sendto(flags=MSG_FASTOPEN, dest_addr=AF_UNSPEC)
	  |                           - tcp_sendmsg()
	  |                              - tcp_sendmsg_fastopen()
	  |                                 - __inet_stream_connect()
	  |                                    - tcp_disconnect() //because of AF_UNSPEC
	  |                                       - tcp_transmit_skb()// send RST
	  |                                    - return 0; // no reconnect!
	  |                           - sk_stream_wait_connect()
	  |                                 - sock_error()
	  |                                    - xchg(&sk->sk_err, 0)
	  |                                    - return -ECONNRESET
	- ... // wake up, see sk->sk_err == 0
    - skb_entail() on TCP_CLOSE socket

If the connection is reopened then we will send a brand new SYN packet
after thread A has already queued a buffer. At this point I think the
socket internal state (sequence numbers etc.) becomes messed up.

When the new connection is closed, the FIN-ACK is rejected because the
sequence number is outside the window. The other side tries to
retransmit,
but __tcp_retransmit_skb() calls tcp_trim_head() on an empty skb which
corrupts the skb data length and hits a BUG() in copy_and_csum_bits().
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++

Hence, this patch adds a check for AF_UNSPEC in the fastopen data path
and return EOPNOTSUPP to user if such case happens.

Fixes: cf60af03ca4e7 ("tcp: Fast Open client - sendmsg(MSG_FASTOPEN)")
Reported-by: Vegard Nossum <vegard.nossum@oracle.com>
Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 2dc7fcf..651f1f0 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1084,9 +1084,12 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_sock *inet = inet_sk(sk);
+	struct sockaddr *uaddr = msg->msg_name;
 	int err, flags;
 
-	if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE))
+	if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) ||
+	    (uaddr && msg->msg_namelen >= sizeof(uaddr->sa_family) &&
+	     uaddr->sa_family == AF_UNSPEC))
 		return -EOPNOTSUPP;
 	if (tp->fastopen_req)
 		return -EALREADY; /* Another Fast Open is in progress */
@@ -1108,7 +1111,7 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
 		}
 	}
 	flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0;
-	err = __inet_stream_connect(sk->sk_socket, msg->msg_name,
+	err = __inet_stream_connect(sk->sk_socket, uaddr,
 				    msg->msg_namelen, flags, 1);
 	/* fastopen_req could already be freed in __inet_stream_connect
 	 * if the connection times out or gets rst
-- 
2.4.11


From ef9e2aa6989cbf7f4bcc321628b0f027d3b80413 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Thu, 25 May 2017 19:14:56 +0200
Subject: [PATCH 36/41] sctp: fix ICMP processing if skb is non-linear

[ Upstream commit 804ec7ebe8ea003999ca8d1bfc499edc6a9e07df ]

sometimes ICMP replies to INIT chunks are ignored by the client, even if
the encapsulated SCTP headers match an open socket. This happens when the
ICMP packet is carried by a paged skb: use skb_header_pointer() to read
packet contents beyond the SCTP header, so that chunk header and initiate
tag are validated correctly.

v2:
- don't use skb_header_pointer() to read the transport header, since
  icmp_socket_deliver() already puts these 8 bytes in the linear area.
- change commit message to make specific reference to INIT chunks.

Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/input.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/net/sctp/input.c b/net/sctp/input.c
index 0e06a27..ba9ad32 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -473,15 +473,14 @@ struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *skb,
 			     struct sctp_association **app,
 			     struct sctp_transport **tpp)
 {
+	struct sctp_init_chunk *chunkhdr, _chunkhdr;
 	union sctp_addr saddr;
 	union sctp_addr daddr;
 	struct sctp_af *af;
 	struct sock *sk = NULL;
 	struct sctp_association *asoc;
 	struct sctp_transport *transport = NULL;
-	struct sctp_init_chunk *chunkhdr;
 	__u32 vtag = ntohl(sctphdr->vtag);
-	int len = skb->len - ((void *)sctphdr - (void *)skb->data);
 
 	*app = NULL; *tpp = NULL;
 
@@ -516,13 +515,16 @@ struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *skb,
 	 * discard the packet.
 	 */
 	if (vtag == 0) {
-		chunkhdr = (void *)sctphdr + sizeof(struct sctphdr);
-		if (len < sizeof(struct sctphdr) + sizeof(sctp_chunkhdr_t)
-			  + sizeof(__be32) ||
+		/* chunk header + first 4 octects of init header */
+		chunkhdr = skb_header_pointer(skb, skb_transport_offset(skb) +
+					      sizeof(struct sctphdr),
+					      sizeof(struct sctp_chunkhdr) +
+					      sizeof(__be32), &_chunkhdr);
+		if (!chunkhdr ||
 		    chunkhdr->chunk_hdr.type != SCTP_CID_INIT ||
-		    ntohl(chunkhdr->init_hdr.init_tag) != asoc->c.my_vtag) {
+		    ntohl(chunkhdr->init_hdr.init_tag) != asoc->c.my_vtag)
 			goto out;
-		}
+
 	} else if (vtag != asoc->c.peer_vtag) {
 		goto out;
 	}
-- 
2.4.11


From beca5473329b9d2095a1ec7bc123301d5a75dabd Mon Sep 17 00:00:00 2001
From: Peter Dawson <petedaws@gmail.com>
Date: Fri, 26 May 2017 06:35:18 +1000
Subject: [PATCH 37/41] ip6_tunnel, ip6_gre: fix setting of DSCP on
 encapsulated packets

[ Upstream commit 0e9a709560dbcfbace8bf4019dc5298619235891 ]

This fix addresses two problems in the way the DSCP field is formulated
 on the encapsulating header of IPv6 tunnels.
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=195661

1) The IPv6 tunneling code was manipulating the DSCP field of the
 encapsulating packet using the 32b flowlabel. Since the flowlabel is
 only the lower 20b it was incorrect to assume that the upper 12b
 containing the DSCP and ECN fields would remain intact when formulating
 the encapsulating header. This fix handles the 'inherit' and
 'fixed-value' DSCP cases explicitly using the extant dsfield u8 variable.

2) The use of INET_ECN_encapsulate(0, dsfield) in ip6_tnl_xmit was
 incorrect and resulted in the DSCP value always being set to 0.

Commit 90427ef5d2a4 ("ipv6: fix flow labels when the traffic class
 is non-0") caused the regression by masking out the flowlabel
 which exposed the incorrect handling of the DSCP portion of the
 flowlabel in ip6_tunnel and ip6_gre.

Fixes: 90427ef5d2a4 ("ipv6: fix flow labels when the traffic class is non-0")
Signed-off-by: Peter Dawson <peter.a.dawson@boeing.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c    | 13 +++++++------
 net/ipv6/ip6_tunnel.c | 21 +++++++++++++--------
 2 files changed, 20 insertions(+), 14 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 6fcb7cb..4d60164 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -537,11 +537,10 @@ static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev)
 
 	memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
 
-	dsfield = ipv4_get_dsfield(iph);
-
 	if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)
-		fl6.flowlabel |= htonl((__u32)iph->tos << IPV6_TCLASS_SHIFT)
-					  & IPV6_TCLASS_MASK;
+		dsfield = ipv4_get_dsfield(iph);
+	else
+		dsfield = ip6_tclass(t->parms.flowinfo);
 	if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
 		fl6.flowi6_mark = skb->mark;
 
@@ -596,9 +595,11 @@ static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev)
 
 	memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
 
-	dsfield = ipv6_get_dsfield(ipv6h);
 	if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)
-		fl6.flowlabel |= (*(__be32 *) ipv6h & IPV6_TCLASS_MASK);
+		dsfield = ipv6_get_dsfield(ipv6h);
+	else
+		dsfield = ip6_tclass(t->parms.flowinfo);
+
 	if (t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL)
 		fl6.flowlabel |= ip6_flowlabel(ipv6h);
 	if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index a9692ec..15ff339 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1196,7 +1196,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 	skb_push(skb, sizeof(struct ipv6hdr));
 	skb_reset_network_header(skb);
 	ipv6h = ipv6_hdr(skb);
-	ip6_flow_hdr(ipv6h, INET_ECN_encapsulate(0, dsfield),
+	ip6_flow_hdr(ipv6h, dsfield,
 		     ip6_make_flowlabel(net, skb, fl6->flowlabel, true, fl6));
 	ipv6h->hop_limit = hop_limit;
 	ipv6h->nexthdr = proto;
@@ -1231,8 +1231,6 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (tproto != IPPROTO_IPIP && tproto != 0)
 		return -1;
 
-	dsfield = ipv4_get_dsfield(iph);
-
 	if (t->parms.collect_md) {
 		struct ip_tunnel_info *tun_info;
 		const struct ip_tunnel_key *key;
@@ -1246,6 +1244,7 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 		fl6.flowi6_proto = IPPROTO_IPIP;
 		fl6.daddr = key->u.ipv6.dst;
 		fl6.flowlabel = key->label;
+		dsfield = ip6_tclass(key->label);
 	} else {
 		if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
 			encap_limit = t->parms.encap_limit;
@@ -1254,8 +1253,9 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 		fl6.flowi6_proto = IPPROTO_IPIP;
 
 		if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)
-			fl6.flowlabel |= htonl((__u32)iph->tos << IPV6_TCLASS_SHIFT)
-					 & IPV6_TCLASS_MASK;
+			dsfield = ipv4_get_dsfield(iph);
+		else
+			dsfield = ip6_tclass(t->parms.flowinfo);
 		if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
 			fl6.flowi6_mark = skb->mark;
 	}
@@ -1265,6 +1265,8 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6))
 		return -1;
 
+	dsfield = INET_ECN_encapsulate(dsfield, ipv4_get_dsfield(iph));
+
 	skb_set_inner_ipproto(skb, IPPROTO_IPIP);
 
 	err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu,
@@ -1298,8 +1300,6 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	    ip6_tnl_addr_conflict(t, ipv6h))
 		return -1;
 
-	dsfield = ipv6_get_dsfield(ipv6h);
-
 	if (t->parms.collect_md) {
 		struct ip_tunnel_info *tun_info;
 		const struct ip_tunnel_key *key;
@@ -1313,6 +1313,7 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 		fl6.flowi6_proto = IPPROTO_IPV6;
 		fl6.daddr = key->u.ipv6.dst;
 		fl6.flowlabel = key->label;
+		dsfield = ip6_tclass(key->label);
 	} else {
 		offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb));
 		/* ip6_tnl_parse_tlv_enc_lim() might have reallocated skb->head */
@@ -1335,7 +1336,9 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 		fl6.flowi6_proto = IPPROTO_IPV6;
 
 		if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)
-			fl6.flowlabel |= (*(__be32 *)ipv6h & IPV6_TCLASS_MASK);
+			dsfield = ipv6_get_dsfield(ipv6h);
+		else
+			dsfield = ip6_tclass(t->parms.flowinfo);
 		if (t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL)
 			fl6.flowlabel |= ip6_flowlabel(ipv6h);
 		if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
@@ -1347,6 +1350,8 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6))
 		return -1;
 
+	dsfield = INET_ECN_encapsulate(dsfield, ipv6_get_dsfield(ipv6h));
+
 	skb_set_inner_ipproto(skb, IPPROTO_IPV6);
 
 	err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu,
-- 
2.4.11


From ef6bda3029a8049fb0c3c77ec2d9909be4c91119 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 25 May 2017 14:27:35 -0700
Subject: [PATCH 38/41] ipv4: add reference counting to metrics

[ Upstream commit 3fb07daff8e99243366a081e5129560734de4ada ]

Andrey Konovalov reported crashes in ipv4_mtu()

I could reproduce the issue with KASAN kernels, between
10.246.7.151 and 10.246.7.152 :

1) 20 concurrent netperf -t TCP_RR -H 10.246.7.152 -l 1000 &

2) At the same time run following loop :
while :
do
 ip ro add 10.246.7.152 dev eth0 src 10.246.7.151 mtu 1500
 ip ro del 10.246.7.152 dev eth0 src 10.246.7.151 mtu 1500
done

Cong Wang attempted to add back rt->fi in commit
82486aa6f1b9 ("ipv4: restore rt->fi for reference counting")
but this proved to add some issues that were complex to solve.

Instead, I suggested to add a refcount to the metrics themselves,
being a standalone object (in particular, no reference to other objects)

I tried to make this patch as small as possible to ease its backport,
instead of being super clean. Note that we believe that only ipv4 dst
need to take care of the metric refcount. But if this is wrong,
this patch adds the basic infrastructure to extend this to other
families.

Many thanks to Julian Anastasov for reviewing this patch, and Cong Wang
for his efforts on this problem.

Fixes: 2860583fe840 ("ipv4: Kill rt->fi")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Reviewed-by: Julian Anastasov <ja@ssi.bg>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst.h        |  8 +++++++-
 include/net/ip_fib.h     | 10 +++++-----
 net/core/dst.c           | 23 ++++++++++++++---------
 net/ipv4/fib_semantics.c | 17 ++++++++++-------
 net/ipv4/route.c         | 10 +++++++++-
 5 files changed, 45 insertions(+), 23 deletions(-)

diff --git a/include/net/dst.h b/include/net/dst.h
index 049af33..cfc0437 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -107,10 +107,16 @@ struct dst_entry {
 	};
 };
 
+struct dst_metrics {
+	u32		metrics[RTAX_MAX];
+	atomic_t	refcnt;
+};
+extern const struct dst_metrics dst_default_metrics;
+
 u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old);
-extern const u32 dst_default_metrics[];
 
 #define DST_METRICS_READ_ONLY		0x1UL
+#define DST_METRICS_REFCOUNTED		0x2UL
 #define DST_METRICS_FLAGS		0x3UL
 #define __DST_METRICS_PTR(Y)	\
 	((u32 *)((Y) & ~DST_METRICS_FLAGS))
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 368bb40..892f8dc 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -114,11 +114,11 @@ struct fib_info {
 	__be32			fib_prefsrc;
 	u32			fib_tb_id;
 	u32			fib_priority;
-	u32			*fib_metrics;
-#define fib_mtu fib_metrics[RTAX_MTU-1]
-#define fib_window fib_metrics[RTAX_WINDOW-1]
-#define fib_rtt fib_metrics[RTAX_RTT-1]
-#define fib_advmss fib_metrics[RTAX_ADVMSS-1]
+	struct dst_metrics	*fib_metrics;
+#define fib_mtu fib_metrics->metrics[RTAX_MTU-1]
+#define fib_window fib_metrics->metrics[RTAX_WINDOW-1]
+#define fib_rtt fib_metrics->metrics[RTAX_RTT-1]
+#define fib_advmss fib_metrics->metrics[RTAX_ADVMSS-1]
 	int			fib_nhs;
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	int			fib_weight;
diff --git a/net/core/dst.c b/net/core/dst.c
index 960e503..6192f11 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -151,13 +151,13 @@ int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(dst_discard_out);
 
-const u32 dst_default_metrics[RTAX_MAX + 1] = {
+const struct dst_metrics dst_default_metrics = {
 	/* This initializer is needed to force linker to place this variable
 	 * into const section. Otherwise it might end into bss section.
 	 * We really want to avoid false sharing on this variable, and catch
 	 * any writes on it.
 	 */
-	[RTAX_MAX] = 0xdeadbeef,
+	.refcnt = ATOMIC_INIT(1),
 };
 
 void dst_init(struct dst_entry *dst, struct dst_ops *ops,
@@ -169,7 +169,7 @@ void dst_init(struct dst_entry *dst, struct dst_ops *ops,
 	if (dev)
 		dev_hold(dev);
 	dst->ops = ops;
-	dst_init_metrics(dst, dst_default_metrics, true);
+	dst_init_metrics(dst, dst_default_metrics.metrics, true);
 	dst->expires = 0UL;
 	dst->path = dst;
 	dst->from = NULL;
@@ -314,25 +314,30 @@ EXPORT_SYMBOL(dst_release);
 
 u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old)
 {
-	u32 *p = kmalloc(sizeof(u32) * RTAX_MAX, GFP_ATOMIC);
+	struct dst_metrics *p = kmalloc(sizeof(*p), GFP_ATOMIC);
 
 	if (p) {
-		u32 *old_p = __DST_METRICS_PTR(old);
+		struct dst_metrics *old_p = (struct dst_metrics *)__DST_METRICS_PTR(old);
 		unsigned long prev, new;
 
-		memcpy(p, old_p, sizeof(u32) * RTAX_MAX);
+		atomic_set(&p->refcnt, 1);
+		memcpy(p->metrics, old_p->metrics, sizeof(p->metrics));
 
 		new = (unsigned long) p;
 		prev = cmpxchg(&dst->_metrics, old, new);
 
 		if (prev != old) {
 			kfree(p);
-			p = __DST_METRICS_PTR(prev);
+			p = (struct dst_metrics *)__DST_METRICS_PTR(prev);
 			if (prev & DST_METRICS_READ_ONLY)
 				p = NULL;
+		} else if (prev & DST_METRICS_REFCOUNTED) {
+			if (atomic_dec_and_test(&old_p->refcnt))
+				kfree(old_p);
 		}
 	}
-	return p;
+	BUILD_BUG_ON(offsetof(struct dst_metrics, metrics) != 0);
+	return (u32 *)p;
 }
 EXPORT_SYMBOL(dst_cow_metrics_generic);
 
@@ -341,7 +346,7 @@ void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old)
 {
 	unsigned long prev, new;
 
-	new = ((unsigned long) dst_default_metrics) | DST_METRICS_READ_ONLY;
+	new = ((unsigned long) &dst_default_metrics) | DST_METRICS_READ_ONLY;
 	prev = cmpxchg(&dst->_metrics, old, new);
 	if (prev == old)
 		kfree(__DST_METRICS_PTR(old));
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 317026a..6cf74de 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -204,6 +204,7 @@ static void rt_fibinfo_free_cpus(struct rtable __rcu * __percpu *rtp)
 static void free_fib_info_rcu(struct rcu_head *head)
 {
 	struct fib_info *fi = container_of(head, struct fib_info, rcu);
+	struct dst_metrics *m;
 
 	change_nexthops(fi) {
 		if (nexthop_nh->nh_dev)
@@ -214,8 +215,9 @@ static void free_fib_info_rcu(struct rcu_head *head)
 		rt_fibinfo_free(&nexthop_nh->nh_rth_input);
 	} endfor_nexthops(fi);
 
-	if (fi->fib_metrics != (u32 *) dst_default_metrics)
-		kfree(fi->fib_metrics);
+	m = fi->fib_metrics;
+	if (m != &dst_default_metrics && atomic_dec_and_test(&m->refcnt))
+		kfree(m);
 	kfree(fi);
 }
 
@@ -975,11 +977,11 @@ fib_convert_metrics(struct fib_info *fi, const struct fib_config *cfg)
 			val = 255;
 		if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK))
 			return -EINVAL;
-		fi->fib_metrics[type - 1] = val;
+		fi->fib_metrics->metrics[type - 1] = val;
 	}
 
 	if (ecn_ca)
-		fi->fib_metrics[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA;
+		fi->fib_metrics->metrics[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA;
 
 	return 0;
 }
@@ -1037,11 +1039,12 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 		goto failure;
 	fib_info_cnt++;
 	if (cfg->fc_mx) {
-		fi->fib_metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL);
+		fi->fib_metrics = kzalloc(sizeof(*fi->fib_metrics), GFP_KERNEL);
 		if (!fi->fib_metrics)
 			goto failure;
+		atomic_set(&fi->fib_metrics->refcnt, 1);
 	} else
-		fi->fib_metrics = (u32 *) dst_default_metrics;
+		fi->fib_metrics = (struct dst_metrics *)&dst_default_metrics;
 
 	fi->fib_net = net;
 	fi->fib_protocol = cfg->fc_protocol;
@@ -1242,7 +1245,7 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 	if (fi->fib_priority &&
 	    nla_put_u32(skb, RTA_PRIORITY, fi->fib_priority))
 		goto nla_put_failure;
-	if (rtnetlink_put_metrics(skb, fi->fib_metrics) < 0)
+	if (rtnetlink_put_metrics(skb, fi->fib_metrics->metrics) < 0)
 		goto nla_put_failure;
 
 	if (fi->fib_prefsrc &&
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d972488..e0cc6c1 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1389,8 +1389,12 @@ static void rt_add_uncached_list(struct rtable *rt)
 
 static void ipv4_dst_destroy(struct dst_entry *dst)
 {
+	struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst);
 	struct rtable *rt = (struct rtable *) dst;
 
+	if (p != &dst_default_metrics && atomic_dec_and_test(&p->refcnt))
+		kfree(p);
+
 	if (!list_empty(&rt->rt_uncached)) {
 		struct uncached_list *ul = rt->rt_uncached_list;
 
@@ -1442,7 +1446,11 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
 			rt->rt_gateway = nh->nh_gw;
 			rt->rt_uses_gateway = 1;
 		}
-		dst_init_metrics(&rt->dst, fi->fib_metrics, true);
+		dst_init_metrics(&rt->dst, fi->fib_metrics->metrics, true);
+		if (fi->fib_metrics != &dst_default_metrics) {
+			rt->dst._metrics |= DST_METRICS_REFCOUNTED;
+			atomic_inc(&fi->fib_metrics->refcnt);
+		}
 #ifdef CONFIG_IP_ROUTE_CLASSID
 		rt->dst.tclassid = nh->nh_tclassid;
 #endif
-- 
2.4.11


From 230d32d7462ce0b6014add43614b847abc35d645 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 25 May 2017 01:05:07 +0200
Subject: [PATCH 39/41] bpf: add bpf_clone_redirect to
 bpf_helper_changes_pkt_data

[ Upstream commit 41703a731066fde79c3e5ccf3391cf77a98aeda5 ]

The bpf_clone_redirect() still needs to be listed in
bpf_helper_changes_pkt_data() since we call into
bpf_try_make_head_writable() from there, thus we need
to invalidate prior pkt regs as well.

Fixes: 36bbef52c7eb ("bpf: direct packet write and access for helpers for clsact progs")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/filter.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/core/filter.c b/net/core/filter.c
index ebaeaf2..6ca3b05 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2266,6 +2266,7 @@ bool bpf_helper_changes_pkt_data(void *func)
 	    func == bpf_skb_change_head ||
 	    func == bpf_skb_change_tail ||
 	    func == bpf_skb_pull_data ||
+	    func == bpf_clone_redirect ||
 	    func == bpf_l3_csum_replace ||
 	    func == bpf_l4_csum_replace ||
 	    func == bpf_xdp_adjust_head)
-- 
2.4.11


From 5b98b47d9fb21685e27fa05f045618a9d0d3a270 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 25 May 2017 01:05:08 +0200
Subject: [PATCH 40/41] bpf: fix wrong exposure of map_flags into fdinfo for
 lpm

[ Upstream commit a316338cb71a3260201490e615f2f6d5c0d8fb2c ]

trie_alloc() always needs to have BPF_F_NO_PREALLOC passed in via
attr->map_flags, since it does not support preallocation yet. We
check the flag, but we never copy the flag into trie->map.map_flags,
which is later on exposed into fdinfo and used by loaders such as
iproute2. Latter uses this in bpf_map_selfcheck_pinned() to test
whether a pinned map has the same spec as the one from the BPF obj
file and if not, bails out, which is currently the case for lpm
since it exposes always 0 as flags.

Also copy over flags in array_map_alloc() and stack_map_alloc().
They always have to be 0 right now, but we should make sure to not
miss to copy them over at a later point in time when we add actual
flags for them to use.

Fixes: b95a5c4db09b ("bpf: add a longest prefix match trie map implementation")
Reported-by: Jarno Rajahalme <jarno@covalent.io>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/arraymap.c | 1 +
 kernel/bpf/lpm_trie.c | 1 +
 kernel/bpf/stackmap.c | 1 +
 3 files changed, 3 insertions(+)

diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 6b6f41f..892f47c 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -83,6 +83,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 	array->map.key_size = attr->key_size;
 	array->map.value_size = attr->value_size;
 	array->map.max_entries = attr->max_entries;
+	array->map.map_flags = attr->map_flags;
 	array->elem_size = elem_size;
 
 	if (!percpu)
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index b37bd9a..7ab9e42 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -432,6 +432,7 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr)
 	trie->map.key_size = attr->key_size;
 	trie->map.value_size = attr->value_size;
 	trie->map.max_entries = attr->max_entries;
+	trie->map.map_flags = attr->map_flags;
 	trie->data_size = attr->key_size -
 			  offsetof(struct bpf_lpm_trie_key, data);
 	trie->max_prefixlen = trie->data_size * 8;
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 22aa45c..96f6043 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -88,6 +88,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
 	smap->map.key_size = attr->key_size;
 	smap->map.value_size = value_size;
 	smap->map.max_entries = attr->max_entries;
+	smap->map.map_flags = attr->map_flags;
 	smap->n_buckets = n_buckets;
 	smap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
 
-- 
2.4.11


From 49989248ce85537ddbcb2460cc00d0fa33cdd156 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 18 May 2017 03:00:06 +0200
Subject: [PATCH 41/41] bpf: adjust verifier heuristics

[ Upstream commit 3c2ce60bdd3d57051bf85615deec04a694473840 ]

Current limits with regards to processing program paths do not
really reflect today's needs anymore due to programs becoming
more complex and verifier smarter, keeping track of more data
such as const ALU operations, alignment tracking, spilling of
PTR_TO_MAP_VALUE_ADJ registers, and other features allowing for
smarter matching of what LLVM generates.

This also comes with the side-effect that we result in fewer
opportunities to prune search states and thus often need to do
more work to prove safety than in the past due to different
register states and stack layout where we mismatch. Generally,
it's quite hard to determine what caused a sudden increase in
complexity, it could be caused by something as trivial as a
single branch somewhere at the beginning of the program where
LLVM assigned a stack slot that is marked differently throughout
other branches and thus causing a mismatch, where verifier
then needs to prove safety for the whole rest of the program.
Subsequently, programs with even less than half the insn size
limit can get rejected. We noticed that while some programs
load fine under pre 4.11, they get rejected due to hitting
limits on more recent kernels. We saw that in the vast majority
of cases (90+%) pruning failed due to register mismatches. In
case of stack mismatches, majority of cases failed due to
different stack slot types (invalid, spill, misc) rather than
differences in spilled registers.

This patch makes pruning more aggressive by also adding markers
that sit at conditional jumps as well. Currently, we only mark
jump targets for pruning. For example in direct packet access,
these are usually error paths where we bail out. We found that
adding these markers, it can reduce number of processed insns
by up to 30%. Another option is to ignore reg->id in probing
PTR_TO_MAP_VALUE_OR_NULL registers, which can help pruning
slightly as well by up to 7% observed complexity reduction as
stand-alone. Meaning, if a previous path with register type
PTR_TO_MAP_VALUE_OR_NULL for map X was found to be safe, then
in the current state a PTR_TO_MAP_VALUE_OR_NULL register for
the same map X must be safe as well. Last but not least the
patch also adds a scheduling point and bumps the current limit
for instructions to be processed to a more adequate value.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 6fd78d4..904decd 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -140,7 +140,7 @@ struct bpf_verifier_stack_elem {
 	struct bpf_verifier_stack_elem *next;
 };
 
-#define BPF_COMPLEXITY_LIMIT_INSNS	65536
+#define BPF_COMPLEXITY_LIMIT_INSNS	98304
 #define BPF_COMPLEXITY_LIMIT_STACK	1024
 
 struct bpf_call_arg_meta {
@@ -2546,6 +2546,7 @@ static int check_cfg(struct bpf_verifier_env *env)
 				env->explored_states[t + 1] = STATE_LIST_MARK;
 		} else {
 			/* conditional jump with two edges */
+			env->explored_states[t] = STATE_LIST_MARK;
 			ret = push_insn(t, t + 1, FALLTHROUGH, env);
 			if (ret == 1)
 				goto peek_stack;
@@ -2704,6 +2705,12 @@ static bool states_equal(struct bpf_verifier_env *env,
 		     rcur->type != NOT_INIT))
 			continue;
 
+		/* Don't care about the reg->id in this case. */
+		if (rold->type == PTR_TO_MAP_VALUE_OR_NULL &&
+		    rcur->type == PTR_TO_MAP_VALUE_OR_NULL &&
+		    rold->map_ptr == rcur->map_ptr)
+			continue;
+
 		if (rold->type == PTR_TO_PACKET && rcur->type == PTR_TO_PACKET &&
 		    compare_ptrs_to_packet(rold, rcur))
 			continue;
@@ -2838,6 +2845,9 @@ static int do_check(struct bpf_verifier_env *env)
 			goto process_bpf_exit;
 		}
 
+		if (need_resched())
+			cond_resched();
+
 		if (log_level && do_print_state) {
 			verbose("\nfrom %d to %d:", prev_insn_idx, insn_idx);
 			print_verifier_state(&env->cur_state);
-- 
2.4.11

Re: [PATCHES] Networking

[Greg KH]

On Tue, May 30, 2017 at 07:14:13PM -0400, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.9 and
> v4.11 -stable, respectively.

Thanks for these, all now queued up.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 106 bytes --]


Please queue up the following networking bug fixes for v4.9 and v4.11
-stable, respectively.

Thank you!

[-- Attachment #2: net_49.mbox --]
[-- Type: Application/Octet-Stream, Size: 54035 bytes --]

From fad101b1d1fdbb23e17080439bc3add30e3496f1 Mon Sep 17 00:00:00 2001
From: Alexander Potapenko <glider@google.com>
Date: Tue, 6 Jun 2017 15:56:54 +0200
Subject: [PATCH 01/24] net: don't call strlen on non-terminated string in
 dev_set_alias()

[ Upstream commit c28294b941232931fbd714099798eb7aa7e865d7 ]

KMSAN reported a use of uninitialized memory in dev_set_alias(),
which was caused by calling strlcpy() (which in turn called strlen())
on the user-supplied non-terminated string.

Signed-off-by: Alexander Potapenko <glider@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 2e04fd1..97f8061 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1250,8 +1250,9 @@ int dev_set_alias(struct net_device *dev, const char *alias, size_t len)
 	if (!new_ifalias)
 		return -ENOMEM;
 	dev->ifalias = new_ifalias;
+	memcpy(dev->ifalias, alias, len);
+	dev->ifalias[len] = 0;
 
-	strlcpy(dev->ifalias, alias, len+1);
 	return len;
 }
 
-- 
2.4.11


From cd94e6910d4cd1013baaf50e11252a2b15ab1339 Mon Sep 17 00:00:00 2001
From: Mateusz Jurczyk <mjurczyk@google.com>
Date: Wed, 7 Jun 2017 16:14:29 +0200
Subject: [PATCH 02/24] decnet: dn_rtmsg: Improve input length sanitization in
 dnrmg_receive_user_skb

[ Upstream commit dd0da17b209ed91f39872766634ca967c170ada1 ]

Verify that the length of the socket buffer is sufficient to cover the
nlmsghdr structure before accessing the nlh->nlmsg_len field for further
input sanitization. If the client only supplies 1-3 bytes of data in
sk_buff, then nlh->nlmsg_len remains partially uninitialized and
contains leftover memory from the corresponding kernel allocation.
Operating on such data may result in indeterminate evaluation of the
nlmsg_len < sizeof(*nlh) expression.

The bug was discovered by a runtime instrumentation designed to detect
use of uninitialized memory in the kernel. The patch prevents this and
other similar tools (e.g. KMSAN) from flagging this behavior in the future.

Signed-off-by: Mateusz Jurczyk <mjurczyk@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/decnet/netfilter/dn_rtmsg.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c
index 85f2fdc..29246bc 100644
--- a/net/decnet/netfilter/dn_rtmsg.c
+++ b/net/decnet/netfilter/dn_rtmsg.c
@@ -102,7 +102,9 @@ static inline void dnrmg_receive_user_skb(struct sk_buff *skb)
 {
 	struct nlmsghdr *nlh = nlmsg_hdr(skb);
 
-	if (nlh->nlmsg_len < sizeof(*nlh) || skb->len < nlh->nlmsg_len)
+	if (skb->len < sizeof(*nlh) ||
+	    nlh->nlmsg_len < sizeof(*nlh) ||
+	    skb->len < nlh->nlmsg_len)
 		return;
 
 	if (!netlink_capable(skb, CAP_NET_ADMIN))
-- 
2.4.11


From 0bc2cbc81549e957b2ae90e5c48051b6a52ec3f8 Mon Sep 17 00:00:00 2001
From: "Mintz, Yuval" <Yuval.Mintz@cavium.com>
Date: Wed, 7 Jun 2017 21:00:33 +0300
Subject: [PATCH 03/24] net: Zero ifla_vf_info in rtnl_fill_vfinfo()

[ Upstream commit 0eed9cf58446b28b233388b7f224cbca268b6986 ]

Some of the structure's fields are not initialized by the
rtnetlink. If driver doesn't set those in ndo_get_vf_config(),
they'd leak memory to user.

Signed-off-by: Yuval Mintz <Yuval.Mintz@cavium.com>
CC: Michal Schmidt <mschmidt@redhat.com>
Reviewed-by: Greg Rose <gvrose8192@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 1d91607..d574409 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1130,6 +1130,8 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb,
 	struct ifla_vf_mac vf_mac;
 	struct ifla_vf_info ivi;
 
+	memset(&ivi, 0, sizeof(ivi));
+
 	/* Not all SR-IOV capable drivers support the
 	 * spoofcheck and "RSS query enable" query.  Preset to
 	 * -1 so the user space tool can detect that the driver
@@ -1138,7 +1140,6 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb,
 	ivi.spoofchk = -1;
 	ivi.rss_query_en = -1;
 	ivi.trusted = -1;
-	memset(ivi.mac, 0, sizeof(ivi.mac));
 	/* The default value for VF link state is "auto"
 	 * IFLA_VF_LINK_STATE_AUTO which equals zero
 	 */
-- 
2.4.11


From 61ba4b974b28e16cf0854353878cdcced258118d Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Thu, 8 Jun 2017 11:31:11 -0600
Subject: [PATCH 04/24] net: vrf: Make add_fib_rules per network namespace flag

[ Upstream commit 097d3c9508dc58286344e4a22b300098cf0c1566 ]

Commit 1aa6c4f6b8cd8 ("net: vrf: Add l3mdev rules on first device create")
adds the l3mdev FIB rule the first time a VRF device is created. However,
it only creates the rule once and only in the namespace the first device
is created - which may not be init_net. Fix by using the net_generic
capability to make the add_fib_rules flag per network namespace.

Fixes: 1aa6c4f6b8cd8 ("net: vrf: Add l3mdev rules on first device create")
Reported-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 36 ++++++++++++++++++++++++++++++++----
 1 file changed, 32 insertions(+), 4 deletions(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index ee02605..642df93 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -36,12 +36,14 @@
 #include <net/addrconf.h>
 #include <net/l3mdev.h>
 #include <net/fib_rules.h>
+#include <net/netns/generic.h>
 
 #define DRV_NAME	"vrf"
 #define DRV_VERSION	"1.0"
 
 #define FIB_RULE_PREF  1000       /* default preference for FIB rules */
-static bool add_fib_rules = true;
+
+static unsigned int vrf_net_id;
 
 struct net_vrf {
 	struct rtable __rcu	*rth;
@@ -1237,6 +1239,8 @@ static int vrf_newlink(struct net *src_net, struct net_device *dev,
 		       struct nlattr *tb[], struct nlattr *data[])
 {
 	struct net_vrf *vrf = netdev_priv(dev);
+	bool *add_fib_rules;
+	struct net *net;
 	int err;
 
 	if (!data || !data[IFLA_VRF_TABLE])
@@ -1252,13 +1256,15 @@ static int vrf_newlink(struct net *src_net, struct net_device *dev,
 	if (err)
 		goto out;
 
-	if (add_fib_rules) {
+	net = dev_net(dev);
+	add_fib_rules = net_generic(net, vrf_net_id);
+	if (*add_fib_rules) {
 		err = vrf_add_fib_rules(dev);
 		if (err) {
 			unregister_netdevice(dev);
 			goto out;
 		}
-		add_fib_rules = false;
+		*add_fib_rules = false;
 	}
 
 out:
@@ -1341,16 +1347,38 @@ static struct notifier_block vrf_notifier_block __read_mostly = {
 	.notifier_call = vrf_device_event,
 };
 
+/* Initialize per network namespace state */
+static int __net_init vrf_netns_init(struct net *net)
+{
+	bool *add_fib_rules = net_generic(net, vrf_net_id);
+
+	*add_fib_rules = true;
+
+	return 0;
+}
+
+static struct pernet_operations vrf_net_ops __net_initdata = {
+	.init = vrf_netns_init,
+	.id   = &vrf_net_id,
+	.size = sizeof(bool),
+};
+
 static int __init vrf_init_module(void)
 {
 	int rc;
 
 	register_netdevice_notifier(&vrf_notifier_block);
 
-	rc = rtnl_link_register(&vrf_link_ops);
+	rc = register_pernet_subsys(&vrf_net_ops);
 	if (rc < 0)
 		goto error;
 
+	rc = rtnl_link_register(&vrf_link_ops);
+	if (rc < 0) {
+		unregister_pernet_subsys(&vrf_net_ops);
+		goto error;
+	}
+
 	return 0;
 
 error:
-- 
2.4.11


From 1f5c331fcda1acf2e95869316ec68c791fb65500 Mon Sep 17 00:00:00 2001
From: Mateusz Jurczyk <mjurczyk@google.com>
Date: Thu, 8 Jun 2017 11:13:36 +0200
Subject: [PATCH 05/24] af_unix: Add sockaddr length checks before accessing
 sa_family in bind and connect handlers

[ Upstream commit defbcf2decc903a28d8398aa477b6881e711e3ea ]

Verify that the caller-provided sockaddr structure is large enough to
contain the sa_family field, before accessing it in bind() and connect()
handlers of the AF_UNIX socket. Since neither syscall enforces a minimum
size of the corresponding memory region, very short sockaddrs (zero or
one byte long) result in operating on uninitialized memory while
referencing .sa_family.

Signed-off-by: Mateusz Jurczyk <mjurczyk@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 2d03d5b..915abe9 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -998,7 +998,8 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	struct path path = { NULL, NULL };
 
 	err = -EINVAL;
-	if (sunaddr->sun_family != AF_UNIX)
+	if (addr_len < offsetofend(struct sockaddr_un, sun_family) ||
+	    sunaddr->sun_family != AF_UNIX)
 		goto out;
 
 	if (addr_len == sizeof(short)) {
@@ -1109,6 +1110,10 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr,
 	unsigned int hash;
 	int err;
 
+	err = -EINVAL;
+	if (alen < offsetofend(struct sockaddr, sa_family))
+		goto out;
+
 	if (addr->sa_family != AF_UNSPEC) {
 		err = unix_mkname(sunaddr, alen, &hash);
 		if (err < 0)
-- 
2.4.11


From 0e4b717c023be07122ccd6ca5ffb12846c0d9888 Mon Sep 17 00:00:00 2001
From: Krister Johansen <kjlx@templeofstupid.com>
Date: Thu, 8 Jun 2017 13:12:38 -0700
Subject: [PATCH 06/24] Fix an intermittent pr_emerg warning about lo becoming
 free.

[ Upstream commit f186ce61bb8235d80068c390dc2aad7ca427a4c2 ]

It looks like this:

Message from syslogd@flamingo at Apr 26 00:45:00 ...
 kernel:unregister_netdevice: waiting for lo to become free. Usage count = 4

They seem to coincide with net namespace teardown.

The message is emitted by netdev_wait_allrefs().

Forced a kdump in netdev_run_todo, but found that the refcount on the lo
device was already 0 at the time we got to the panic.

Used bcc to check the blocking in netdev_run_todo.  The only places
where we're off cpu there are in the rcu_barrier() and msleep() calls.
That behavior is expected.  The msleep time coincides with the amount of
time we spend waiting for the refcount to reach zero; the rcu_barrier()
wait times are not excessive.

After looking through the list of callbacks that the netdevice notifiers
invoke in this path, it appears that the dst_dev_event is the most
interesting.  The dst_ifdown path places a hold on the loopback_dev as
part of releasing the dev associated with the original dst cache entry.
Most of our notifier callbacks are straight-forward, but this one a)
looks complex, and b) places a hold on the network interface in
question.

I constructed a new bcc script that watches various events in the
liftime of a dst cache entry.  Note that dst_ifdown will take a hold on
the loopback device until the invalidated dst entry gets freed.

[      __dst_free] on DST: ffff883ccabb7900 IF tap1008300eth0 invoked at 1282115677036183
    __dst_free
    rcu_nocb_kthread
    kthread
    ret_from_fork
Acked-by: Eric Dumazet <edumazet@google.com>

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dst.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/net/core/dst.c b/net/core/dst.c
index 656b70d..39cc119 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -470,6 +470,20 @@ static int dst_dev_event(struct notifier_block *this, unsigned long event,
 		spin_lock_bh(&dst_garbage.lock);
 		dst = dst_garbage.list;
 		dst_garbage.list = NULL;
+		/* The code in dst_ifdown places a hold on the loopback device.
+		 * If the gc entry processing is set to expire after a lengthy
+		 * interval, this hold can cause netdev_wait_allrefs() to hang
+		 * out and wait for a long time -- until the the loopback
+		 * interface is released.  If we're really unlucky, it'll emit
+		 * pr_emerg messages to console too.  Reset the interval here,
+		 * so dst cleanups occur in a more timely fashion.
+		 */
+		if (dst_garbage.timer_inc > DST_GC_INC) {
+			dst_garbage.timer_inc = DST_GC_INC;
+			dst_garbage.timer_expires = DST_GC_MIN;
+			mod_delayed_work(system_wq, &dst_gc_work,
+					 dst_garbage.timer_expires);
+		}
 		spin_unlock_bh(&dst_garbage.lock);
 
 		if (last)
-- 
2.4.11


From 5bf79f5f3f21c0bae7cfb4ad49de29301ad97307 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sat, 10 Jun 2017 14:48:14 +0800
Subject: [PATCH 07/24] sctp: disable BH in sctp_for_each_endpoint

[ Upstream commit 581409dacc9176b0de1f6c4ca8d66e13aa8e1b29 ]

Now sctp holds read_lock when foreach sctp_ep_hashtable without disabling
BH. If CPU schedules to another thread A at this moment, the thread A may
be trying to hold the write_lock with disabling BH.

As BH is disabled and CPU cannot schedule back to the thread holding the
read_lock, while the thread A keeps waiting for the read_lock. A dead
lock would be triggered by this.

This patch is to fix this dead lock by calling read_lock_bh instead to
disable BH when holding the read_lock in sctp_for_each_endpoint.

Fixes: 626d16f50f39 ("sctp: export some apis or variables for sctp_diag and reuse some for proc")
Reported-by: Xiumei Mu <xmu@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index e1719c6..0c5257e 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4460,13 +4460,13 @@ int sctp_for_each_endpoint(int (*cb)(struct sctp_endpoint *, void *),
 
 	for (head = sctp_ep_hashtable; hash < sctp_ep_hashsize;
 	     hash++, head++) {
-		read_lock(&head->lock);
+		read_lock_bh(&head->lock);
 		sctp_for_each_hentry(epb, &head->chain) {
 			err = cb(sctp_ep(epb), p);
 			if (err)
 				break;
 		}
-		read_unlock(&head->lock);
+		read_unlock_bh(&head->lock);
 	}
 
 	return err;
-- 
2.4.11


From 54be623eda46de239fec353df0f3d501a70332d4 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@163.com>
Date: Sat, 10 Jun 2017 16:49:39 +0800
Subject: [PATCH 08/24] net: caif: Fix a sleep-in-atomic bug in
 cfpkt_create_pfx

[ Upstream commit f146e872eb12ebbe92d8e583b2637e0741440db3 ]

The kernel may sleep under a rcu read lock in cfpkt_create_pfx, and the
function call path is:
cfcnfg_linkup_rsp (acquire the lock by rcu_read_lock)
  cfctrl_linkdown_req
    cfpkt_create
      cfpkt_create_pfx
        alloc_skb(GFP_KERNEL) --> may sleep
cfserl_receive (acquire the lock by rcu_read_lock)
  cfpkt_split
    cfpkt_create_pfx
      alloc_skb(GFP_KERNEL) --> may sleep

There is "in_interrupt" in cfpkt_create_pfx to decide use "GFP_KERNEL" or
"GFP_ATOMIC". In this situation, "GFP_KERNEL" is used because the function
is called under a rcu read lock, instead in interrupt.

To fix it, only "GFP_ATOMIC" is used in cfpkt_create_pfx.

Signed-off-by: Jia-Ju Bai <baijiaju1990@163.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/caif/cfpkt_skbuff.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/net/caif/cfpkt_skbuff.c b/net/caif/cfpkt_skbuff.c
index 59ce1fc..71b6ab2 100644
--- a/net/caif/cfpkt_skbuff.c
+++ b/net/caif/cfpkt_skbuff.c
@@ -81,11 +81,7 @@ static struct cfpkt *cfpkt_create_pfx(u16 len, u16 pfx)
 {
 	struct sk_buff *skb;
 
-	if (likely(in_interrupt()))
-		skb = alloc_skb(len + pfx, GFP_ATOMIC);
-	else
-		skb = alloc_skb(len + pfx, GFP_KERNEL);
-
+	skb = alloc_skb(len + pfx, GFP_ATOMIC);
 	if (unlikely(skb == NULL))
 		return NULL;
 
-- 
2.4.11


From 4dbfa687082810aca8f218e2ac7c8ef86dbf6ea8 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@163.com>
Date: Sat, 10 Jun 2017 17:03:35 +0800
Subject: [PATCH 09/24] net: tipc: Fix a sleep-in-atomic bug in
 tipc_msg_reverse

[ Upstream commit 343eba69c6968190d8654b857aea952fed9a6749 ]

The kernel may sleep under a rcu read lock in tipc_msg_reverse, and the
function call path is:
tipc_l2_rcv_msg (acquire the lock by rcu_read_lock)
  tipc_rcv
    tipc_sk_rcv
      tipc_msg_reverse
        pskb_expand_head(GFP_KERNEL) --> may sleep
tipc_node_broadcast
  tipc_node_xmit_skb
    tipc_node_xmit
      tipc_sk_rcv
        tipc_msg_reverse
          pskb_expand_head(GFP_KERNEL) --> may sleep

To fix it, "GFP_KERNEL" is replaced with "GFP_ATOMIC".

Signed-off-by: Jia-Ju Bai <baijiaju1990@163.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/msg.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index 17201aa..1bd9817 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -508,7 +508,7 @@ bool tipc_msg_reverse(u32 own_node,  struct sk_buff **skb, int err)
 	}
 
 	if (skb_cloned(_skb) &&
-	    pskb_expand_head(_skb, BUF_HEADROOM, BUF_TAILROOM, GFP_KERNEL))
+	    pskb_expand_head(_skb, BUF_HEADROOM, BUF_TAILROOM, GFP_ATOMIC))
 		goto exit;
 
 	/* Now reverse the concerned fields */
-- 
2.4.11


From 704f24ce8dfc4283c7017cc4dc9a08fa741c3d1c Mon Sep 17 00:00:00 2001
From: Tal Gilboa <talgi@mellanox.com>
Date: Mon, 15 May 2017 14:13:16 +0300
Subject: [PATCH 10/24] net/mlx5e: Added BW check for DIM decision mechanism

[ Upstream commit c3164d2fc48fd4fa0477ab658b644559c3fe9073 ]

DIM (Dynamically-tuned Interrupt Moderation) is a mechanism designed for
changing the channel interrupt moderation values in order to reduce CPU
overhead for all traffic types.
Until now only interrupt and packet rate were sampled.
We found a scenario on which we get a false indication since a change in
DIM caused more aggregation and reduced packet rate while increasing BW.

We now regard a change as succesfull iff:
current_BW > (prev_BW + threshold) or
current_BW ~= prev_BW and current_PR > (prev_PR + threshold) or
current_BW ~= prev_BW and current_PR ~= prev_PR and
    current_IR < (prev_IR - threshold)
Where BW = Bandwidth, PR = Packet rate and IR = Interrupt rate

Improvements (ConnectX-4Lx 25GbE, single RX queue, LRO off)
    --------------------------------------------------
    packet size | before[Mb/s] | after[Mb/s] | gain  |
    2B          | 343.4        | 359.4       |  4.5% |
    16B         | 2739.7       | 2814.8      |  2.7% |
    64B         | 9739         | 10185.3     |  4.5% |

Fixes: cb3c7fd4f839 ("net/mlx5e: Support adaptive RX coalescing")
Signed-off-by: Tal Gilboa <talgi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |  2 ++
 drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c | 37 ++++++++++++----------
 2 files changed, 22 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 21ce0b7..6edc8b2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -283,12 +283,14 @@ struct mlx5e_dma_info {
 
 struct mlx5e_rx_am_stats {
 	int ppms; /* packets per msec */
+	int bpms; /* bytes per msec */
 	int epms; /* events per msec */
 };
 
 struct mlx5e_rx_am_sample {
 	ktime_t		time;
 	unsigned int	pkt_ctr;
+	unsigned int    byte_ctr;
 	u16		event_ctr;
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c
index cbfac06..1750388 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c
@@ -183,28 +183,27 @@ static void mlx5e_am_exit_parking(struct mlx5e_rx_am *am)
 	mlx5e_am_step(am);
 }
 
+#define IS_SIGNIFICANT_DIFF(val, ref) \
+	(((100 * abs((val) - (ref))) / (ref)) > 10) /* more than 10% difference */
+
 static int mlx5e_am_stats_compare(struct mlx5e_rx_am_stats *curr,
 				  struct mlx5e_rx_am_stats *prev)
 {
-	int diff;
-
-	if (!prev->ppms)
-		return curr->ppms ? MLX5E_AM_STATS_BETTER :
+	if (!prev->bpms)
+		return curr->bpms ? MLX5E_AM_STATS_BETTER :
 				    MLX5E_AM_STATS_SAME;
 
-	diff = curr->ppms - prev->ppms;
-	if (((100 * abs(diff)) / prev->ppms) > 10) /* more than 10% diff */
-		return (diff > 0) ? MLX5E_AM_STATS_BETTER :
-				    MLX5E_AM_STATS_WORSE;
+	if (IS_SIGNIFICANT_DIFF(curr->bpms, prev->bpms))
+		return (curr->bpms > prev->bpms) ? MLX5E_AM_STATS_BETTER :
+						   MLX5E_AM_STATS_WORSE;
 
-	if (!prev->epms)
-		return curr->epms ? MLX5E_AM_STATS_WORSE :
-				    MLX5E_AM_STATS_SAME;
+	if (IS_SIGNIFICANT_DIFF(curr->ppms, prev->ppms))
+		return (curr->ppms > prev->ppms) ? MLX5E_AM_STATS_BETTER :
+						   MLX5E_AM_STATS_WORSE;
 
-	diff = curr->epms - prev->epms;
-	if (((100 * abs(diff)) / prev->epms) > 10) /* more than 10% diff */
-		return (diff < 0) ? MLX5E_AM_STATS_BETTER :
-				    MLX5E_AM_STATS_WORSE;
+	if (IS_SIGNIFICANT_DIFF(curr->epms, prev->epms))
+		return (curr->epms < prev->epms) ? MLX5E_AM_STATS_BETTER :
+						   MLX5E_AM_STATS_WORSE;
 
 	return MLX5E_AM_STATS_SAME;
 }
@@ -266,6 +265,7 @@ static void mlx5e_am_sample(struct mlx5e_rq *rq,
 {
 	s->time	     = ktime_get();
 	s->pkt_ctr   = rq->stats.packets;
+	s->byte_ctr  = rq->stats.bytes;
 	s->event_ctr = rq->cq.event_ctr;
 }
 
@@ -278,12 +278,15 @@ static void mlx5e_am_calc_stats(struct mlx5e_rx_am_sample *start,
 	/* u32 holds up to 71 minutes, should be enough */
 	u32 delta_us = ktime_us_delta(end->time, start->time);
 	unsigned int npkts = end->pkt_ctr - start->pkt_ctr;
+	unsigned int nbytes = end->byte_ctr - start->byte_ctr;
 
 	if (!delta_us)
 		return;
 
-	curr_stats->ppms =            (npkts * USEC_PER_MSEC) / delta_us;
-	curr_stats->epms = (MLX5E_AM_NEVENTS * USEC_PER_MSEC) / delta_us;
+	curr_stats->ppms = DIV_ROUND_UP(npkts * USEC_PER_MSEC, delta_us);
+	curr_stats->bpms = DIV_ROUND_UP(nbytes * USEC_PER_MSEC, delta_us);
+	curr_stats->epms = DIV_ROUND_UP(MLX5E_AM_NEVENTS * USEC_PER_MSEC,
+					delta_us);
 }
 
 void mlx5e_rx_am_work(struct work_struct *work)
-- 
2.4.11


From dd9c306816f121e8e562073870df15e38a82cfa7 Mon Sep 17 00:00:00 2001
From: Tal Gilboa <talgi@mellanox.com>
Date: Mon, 29 May 2017 17:02:55 +0300
Subject: [PATCH 11/24] net/mlx5e: Fix wrong indications in DIM due to counter
 wraparound

[ Upstream commit 53acd76ce571e3b71f9205f2d49ab285a9f1aad8 ]

DIM (Dynamically-tuned Interrupt Moderation) is a mechanism designed for
changing the channel interrupt moderation values in order to reduce CPU
overhead for all traffic types.
Each iteration of the algorithm, DIM calculates the difference in
throughput, packet rate and interrupt rate from last iteration in order
to make a decision. DIM relies on counters for each metric. When these
counters get to their type's max value they wraparound. In this case
the delta between 'end' and 'start' samples is negative and when
translated to unsigned integers - very high. This results in a false
indication to the algorithm and might result in a wrong decision.

The fix calculates the 'distance' between 'end' and 'start' samples in a
cyclic way around the relevant type's max value. It can also be viewed as
an absolute value around the type's max value instead of around 0.

Testing show higher stability in DIM profile selection and no wraparound
issues.

Fixes: cb3c7fd4f839 ("net/mlx5e: Support adaptive RX coalescing")
Signed-off-by: Tal Gilboa <talgi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |  8 ++++----
 drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c | 10 +++++++---
 2 files changed, 11 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 6edc8b2..6180ad4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -288,10 +288,10 @@ struct mlx5e_rx_am_stats {
 };
 
 struct mlx5e_rx_am_sample {
-	ktime_t		time;
-	unsigned int	pkt_ctr;
-	unsigned int    byte_ctr;
-	u16		event_ctr;
+	ktime_t	time;
+	u32	pkt_ctr;
+	u32	byte_ctr;
+	u16	event_ctr;
 };
 
 struct mlx5e_rx_am { /* Adaptive Moderation */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c
index 1750388..23ccec4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c
@@ -270,6 +270,8 @@ static void mlx5e_am_sample(struct mlx5e_rq *rq,
 }
 
 #define MLX5E_AM_NEVENTS 64
+#define BITS_PER_TYPE(type) (sizeof(type) * BITS_PER_BYTE)
+#define BIT_GAP(bits, end, start) ((((end) - (start)) + BIT_ULL(bits)) & (BIT_ULL(bits) - 1))
 
 static void mlx5e_am_calc_stats(struct mlx5e_rx_am_sample *start,
 				struct mlx5e_rx_am_sample *end,
@@ -277,8 +279,9 @@ static void mlx5e_am_calc_stats(struct mlx5e_rx_am_sample *start,
 {
 	/* u32 holds up to 71 minutes, should be enough */
 	u32 delta_us = ktime_us_delta(end->time, start->time);
-	unsigned int npkts = end->pkt_ctr - start->pkt_ctr;
-	unsigned int nbytes = end->byte_ctr - start->byte_ctr;
+	u32 npkts = BIT_GAP(BITS_PER_TYPE(u32), end->pkt_ctr, start->pkt_ctr);
+	u32 nbytes = BIT_GAP(BITS_PER_TYPE(u32), end->byte_ctr,
+			     start->byte_ctr);
 
 	if (!delta_us)
 		return;
@@ -311,7 +314,8 @@ void mlx5e_rx_am(struct mlx5e_rq *rq)
 
 	switch (am->state) {
 	case MLX5E_AM_MEASURE_IN_PROGRESS:
-		nevents = rq->cq.event_ctr - am->start_sample.event_ctr;
+		nevents = BIT_GAP(BITS_PER_TYPE(u16), rq->cq.event_ctr,
+				  am->start_sample.event_ctr);
 		if (nevents < MLX5E_AM_NEVENTS)
 			break;
 		mlx5e_am_sample(rq, &end_sample);
-- 
2.4.11


From 3e7a17f94ab84d1607448c5f7cfbce7347999f7a Mon Sep 17 00:00:00 2001
From: Christian Perle <christian.perle@secunet.com>
Date: Mon, 12 Jun 2017 10:06:57 +0200
Subject: [PATCH 12/24] proc: snmp6: Use correct type in memset

[ Upstream commit 3500cd73dff48f28f4ba80c171c4c80034d40f76 ]

Reading /proc/net/snmp6 yields bogus values on 32 bit kernels.
Use "u64" instead of "unsigned long" in sizeof().

Fixes: 4a4857b1c81e ("proc: Reduce cache miss in snmp6_seq_show")
Signed-off-by: Christian Perle <christian.perle@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/proc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index cc8e3ae..e88bcb8 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -219,7 +219,7 @@ static void snmp6_seq_show_item64(struct seq_file *seq, void __percpu *mib,
 	u64 buff64[SNMP_MIB_MAX];
 	int i;
 
-	memset(buff64, 0, sizeof(unsigned long) * SNMP_MIB_MAX);
+	memset(buff64, 0, sizeof(u64) * SNMP_MIB_MAX);
 
 	snmp_get_cpu_field64_batch(buff64, itemlist, mib, syncpoff);
 	for (i = 0; itemlist[i].name; i++)
-- 
2.4.11


From f0d2481771529d7234406bcbf1e4f812a4d9ec02 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Mon, 12 Jun 2017 09:52:26 -0700
Subject: [PATCH 13/24] igmp: acquire pmc lock for ip_mc_clear_src()

[ Upstream commit c38b7d327aafd1e3ad7ff53eefac990673b65667 ]

Andrey reported a use-after-free in add_grec():

        for (psf = *psf_list; psf; psf = psf_next) {
		...
                psf_next = psf->sf_next;

where the struct ip_sf_list's were already freed by:

 kfree+0xe8/0x2b0 mm/slub.c:3882
 ip_mc_clear_src+0x69/0x1c0 net/ipv4/igmp.c:2078
 ip_mc_dec_group+0x19a/0x470 net/ipv4/igmp.c:1618
 ip_mc_drop_socket+0x145/0x230 net/ipv4/igmp.c:2609
 inet_release+0x4e/0x1c0 net/ipv4/af_inet.c:411
 sock_release+0x8d/0x1e0 net/socket.c:597
 sock_close+0x16/0x20 net/socket.c:1072

This happens because we don't hold pmc->lock in ip_mc_clear_src()
and a parallel mr_ifc_timer timer could jump in and access them.

The RCU lock is there but it is merely for pmc itself, this
spinlock could actually ensure we don't access them in parallel.

Thanks to Eric and Long for discussion on this bug.

Reported-by: Andrey Konovalov <andreyknvl@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Xin Long <lucien.xin@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/igmp.c | 21 +++++++++++++--------
 1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 1bc623d..8520eff 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -2071,21 +2071,26 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode,
 
 static void ip_mc_clear_src(struct ip_mc_list *pmc)
 {
-	struct ip_sf_list *psf, *nextpsf;
+	struct ip_sf_list *psf, *nextpsf, *tomb, *sources;
 
-	for (psf = pmc->tomb; psf; psf = nextpsf) {
+	spin_lock_bh(&pmc->lock);
+	tomb = pmc->tomb;
+	pmc->tomb = NULL;
+	sources = pmc->sources;
+	pmc->sources = NULL;
+	pmc->sfmode = MCAST_EXCLUDE;
+	pmc->sfcount[MCAST_INCLUDE] = 0;
+	pmc->sfcount[MCAST_EXCLUDE] = 1;
+	spin_unlock_bh(&pmc->lock);
+
+	for (psf = tomb; psf; psf = nextpsf) {
 		nextpsf = psf->sf_next;
 		kfree(psf);
 	}
-	pmc->tomb = NULL;
-	for (psf = pmc->sources; psf; psf = nextpsf) {
+	for (psf = sources; psf; psf = nextpsf) {
 		nextpsf = psf->sf_next;
 		kfree(psf);
 	}
-	pmc->sources = NULL;
-	pmc->sfmode = MCAST_EXCLUDE;
-	pmc->sfcount[MCAST_INCLUDE] = 0;
-	pmc->sfcount[MCAST_EXCLUDE] = 1;
 }
 
 /* Join a multicast group
-- 
2.4.11


From 66b06f0c7f52fd439d8891ff1105129fe463c978 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Tue, 20 Jun 2017 10:46:27 -0700
Subject: [PATCH 14/24] igmp: add a missing spin_lock_init()

[ Upstream commit b4846fc3c8559649277e3e4e6b5cec5348a8d208 ]

Andrey reported a lockdep warning on non-initialized
spinlock:

 INFO: trying to register non-static key.
 the code is fine but needs lockdep annotation.
 turning off the locking correctness validator.
 CPU: 1 PID: 4099 Comm: a.out Not tainted 4.12.0-rc6+ #9
 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
 Call Trace:
  __dump_stack lib/dump_stack.c:16
  dump_stack+0x292/0x395 lib/dump_stack.c:52
  register_lock_class+0x717/0x1aa0 kernel/locking/lockdep.c:755
  ? 0xffffffffa0000000
  __lock_acquire+0x269/0x3690 kernel/locking/lockdep.c:3255
  lock_acquire+0x22d/0x560 kernel/locking/lockdep.c:3855
  __raw_spin_lock_bh ./include/linux/spinlock_api_smp.h:135
  _raw_spin_lock_bh+0x36/0x50 kernel/locking/spinlock.c:175
  spin_lock_bh ./include/linux/spinlock.h:304
  ip_mc_clear_src+0x27/0x1e0 net/ipv4/igmp.c:2076
  igmpv3_clear_delrec+0xee/0x4f0 net/ipv4/igmp.c:1194
  ip_mc_destroy_dev+0x4e/0x190 net/ipv4/igmp.c:1736

We miss a spin_lock_init() in igmpv3_add_delrec(), probably
because previously we never use it on this code path. Since
we already unlink it from the global mc_tomb list, it is
probably safe not to acquire this spinlock here. It does not
harm to have it although, to avoid conditional locking.

Fixes: c38b7d327aaf ("igmp: acquire pmc lock for ip_mc_clear_src()")
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/igmp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 8520eff..19930da 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -1112,6 +1112,7 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im)
 	pmc = kzalloc(sizeof(*pmc), GFP_KERNEL);
 	if (!pmc)
 		return;
+	spin_lock_init(&pmc->lock);
 	spin_lock_bh(&im->lock);
 	pmc->interface = im->interface;
 	in_dev_hold(in_dev);
-- 
2.4.11


From f1e4193d1156daf0b794b3c588e2de736f4e4d0a Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 15 Jun 2017 16:33:58 +0800
Subject: [PATCH 15/24] ipv6: fix calling in6_ifa_hold incorrectly for dad work

[ Upstream commit f8a894b218138888542a5058d0e902378fd0d4ec ]

Now when starting the dad work in addrconf_mod_dad_work, if the dad work
is idle and queued, it needs to hold ifa.

The problem is there's one gap in [1], during which if the pending dad work
is removed elsewhere. It will miss to hold ifa, but the dad word is still
idea and queue.

        if (!delayed_work_pending(&ifp->dad_work))
                in6_ifa_hold(ifp);
                    <--------------[1]
        mod_delayed_work(addrconf_wq, &ifp->dad_work, delay);

An use-after-free issue can be caused by this.

Chen Wei found this issue when WARN_ON(!hlist_unhashed(&ifp->addr_lst)) in
net6_ifa_finish_destroy was hit because of it.

As Hannes' suggestion, this patch is to fix it by holding ifa first in
addrconf_mod_dad_work, then calling mod_delayed_work and putting ifa if
the dad_work is already in queue.

Note that this patch did not choose to fix it with:

  if (!mod_delayed_work(delay))
          in6_ifa_hold(ifp);

As with it, when delay == 0, dad_work would be scheduled immediately, all
addrconf_mod_dad_work(0) callings had to be moved under ifp->lock.

Reported-by: Wei Chen <weichen@redhat.com>
Suggested-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 0457383..b6f4c42 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -315,9 +315,9 @@ static void addrconf_mod_rs_timer(struct inet6_dev *idev,
 static void addrconf_mod_dad_work(struct inet6_ifaddr *ifp,
 				   unsigned long delay)
 {
-	if (!delayed_work_pending(&ifp->dad_work))
-		in6_ifa_hold(ifp);
-	mod_delayed_work(addrconf_wq, &ifp->dad_work, delay);
+	in6_ifa_hold(ifp);
+	if (mod_delayed_work(addrconf_wq, &ifp->dad_work, delay))
+		in6_ifa_put(ifp);
 }
 
 static int snmp6_alloc_dev(struct inet6_dev *idev)
-- 
2.4.11


From 10b066748f3ae2106dc8058cbbae03ceeb2d982f Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 15 Jun 2017 17:49:08 +0800
Subject: [PATCH 16/24] sctp: return next obj by passing pos + 1 into
 sctp_transport_get_idx

[ Upstream commit 988c7322116970696211e902b468aefec95b6ec4 ]

In sctp_for_each_transport, pos is used to save how many objs it has
dumped. Now it gets the last obj by sctp_transport_get_idx, then gets
the next obj by sctp_transport_get_next.

The issue is that in the meanwhile if some objs in transport hashtable
are removed and the objs nums are less than pos, sctp_transport_get_idx
would return NULL and hti.walker.tbl is NULL as well. At this moment
it should stop hti, instead of continue getting the next obj. Or it
would cause a NULL pointer dereference in sctp_transport_get_next.

This patch is to pass pos + 1 into sctp_transport_get_idx to get the
next obj directly, even if pos > objs nums, it would return NULL and
stop hti.

Fixes: 626d16f50f39 ("sctp: export some apis or variables for sctp_diag and reuse some for proc")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 0c5257e..487c127 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4506,9 +4506,8 @@ int sctp_for_each_transport(int (*cb)(struct sctp_transport *, void *),
 	if (err)
 		return err;
 
-	sctp_transport_get_idx(net, &hti, pos);
-	obj = sctp_transport_get_next(net, &hti);
-	for (; obj && !IS_ERR(obj); obj = sctp_transport_get_next(net, &hti)) {
+	obj = sctp_transport_get_idx(net, &hti, pos + 1);
+	for (; !IS_ERR_OR_NULL(obj); obj = sctp_transport_get_next(net, &hti)) {
 		struct sctp_transport *transport = obj;
 
 		if (!sctp_transport_hold(transport))
-- 
2.4.11


From 83575ced1a9de908bd72c052d2b49eac61cf5039 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Thu, 15 Jun 2017 20:08:32 +0300
Subject: [PATCH 17/24] net/mlx5e: Avoid doing a cleanup call if the profile
 doesn't have it

[ Upstream commit 31ac93386d135a6c96de9c8bab406f5ccabf5a4d ]

The error flow of mlx5e_create_netdev calls the cleanup call
of the given profile without checking if it exists, fix that.

Currently the VF reps don't register that callback and we crash
if getting into error -- can be reproduced by the user doing ctrl^C
while attempting to change the sriov mode from legacy to switchdev.

Fixes: 26e59d8077a3 '(net/mlx5e: Implement mlx5e interface attach/detach callbacks')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reported-by: Sabrina Dubroca <sdubroca@redhat.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index d4fa851..ea58234 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3846,7 +3846,8 @@ struct net_device *mlx5e_create_netdev(struct mlx5_core_dev *mdev,
 	return netdev;
 
 err_cleanup_nic:
-	profile->cleanup(priv);
+	if (profile->cleanup)
+		profile->cleanup(priv);
 	free_netdev(netdev);
 
 	return NULL;
-- 
2.4.11


From 0ba299c50d9f30a6edbc976f1030cd6429353bd2 Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.com>
Date: Thu, 8 Jun 2017 11:33:16 -0500
Subject: [PATCH 18/24] net/mlx5: Wait for FW readiness before initializing
 command interface

[ Upstream commit 6c780a0267b8a1075f40b39851132eeaefefcff5 ]

Before attempting to initialize the command interface we must wait till
the fw_initializing bit is clear.

If we fail to meet this condition the hardware will drop our
configuration, specifically the descriptors page address.  This scenario
can happen when the firmware is still executing an FLR flow and did not
finish yet so the driver needs to wait for that to finish.

Fixes: e3297246c2c8 ('net/mlx5_core: Wait for FW readiness on startup')
Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index d776db7..5bea0bf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -155,8 +155,9 @@ static struct mlx5_profile profile[] = {
 	},
 };
 
-#define FW_INIT_TIMEOUT_MILI	2000
-#define FW_INIT_WAIT_MS		2
+#define FW_INIT_TIMEOUT_MILI		2000
+#define FW_INIT_WAIT_MS			2
+#define FW_PRE_INIT_TIMEOUT_MILI	10000
 
 static int wait_fw_init(struct mlx5_core_dev *dev, u32 max_wait_mili)
 {
@@ -956,6 +957,15 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 	 */
 	dev->state = MLX5_DEVICE_STATE_UP;
 
+	/* wait for firmware to accept initialization segments configurations
+	 */
+	err = wait_fw_init(dev, FW_PRE_INIT_TIMEOUT_MILI);
+	if (err) {
+		dev_err(&dev->pdev->dev, "Firmware over %d MS in pre-initializing state, aborting\n",
+			FW_PRE_INIT_TIMEOUT_MILI);
+		goto out;
+	}
+
 	err = mlx5_cmd_init(dev);
 	if (err) {
 		dev_err(&pdev->dev, "Failed initializing command interface, aborting\n");
-- 
2.4.11


From e9ebfac7bb57e0f0b7df338c5d8366707acfa798 Mon Sep 17 00:00:00 2001
From: Maor Dickman <maord@mellanox.com>
Date: Thu, 18 May 2017 15:15:08 +0300
Subject: [PATCH 19/24] net/mlx5e: Fix timestamping capabilities reporting

[ Upstream commit f0b381178b01b831f9907d72f467d6443afdea67 ]

Misuse of (BIT) macro caused to report wrong flags for
"Hardware Transmit Timestamp Modes" and "Hardware Receive
Filter Modes"

Fixes: ef9814deafd0 ('net/mlx5e: Add HW timestamping (TS) support')
Signed-off-by: Maor Dickman <maord@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 3744e2f..da1d73f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1183,11 +1183,11 @@ static int mlx5e_get_ts_info(struct net_device *dev,
 				 SOF_TIMESTAMPING_RX_HARDWARE |
 				 SOF_TIMESTAMPING_RAW_HARDWARE;
 
-	info->tx_types = (BIT(1) << HWTSTAMP_TX_OFF) |
-			 (BIT(1) << HWTSTAMP_TX_ON);
+	info->tx_types = BIT(HWTSTAMP_TX_OFF) |
+			 BIT(HWTSTAMP_TX_ON);
 
-	info->rx_filters = (BIT(1) << HWTSTAMP_FILTER_NONE) |
-			   (BIT(1) << HWTSTAMP_FILTER_ALL);
+	info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) |
+			   BIT(HWTSTAMP_FILTER_ALL);
 
 	return 0;
 }
-- 
2.4.11


From bb9f5a2bb205ef32f9b1dc377bdae057d06ff92c Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Fri, 16 Jun 2017 10:46:37 -0700
Subject: [PATCH 20/24] decnet: always not take dst->__refcnt when inserting
 dst into hash table

[ Upstream commit 76371d2e3ad1f84426a30ebcd8c3b9b98f4c724f ]

In the existing dn_route.c code, dn_route_output_slow() takes
dst->__refcnt before calling dn_insert_route() while dn_route_input_slow()
does not take dst->__refcnt before calling dn_insert_route().
This makes the whole routing code very buggy.
In dn_dst_check_expire(), dnrt_free() is called when rt expires. This
makes the routes inserted by dn_route_output_slow() not able to be
freed as the refcnt is not released.
In dn_dst_gc(), dnrt_drop() is called to release rt which could
potentially cause the dst->__refcnt to be dropped to -1.
In dn_run_flush(), dst_free() is called to release all the dst. Again,
it makes the dst inserted by dn_route_output_slow() not able to be
released and also, it does not wait on the rcu and could potentially
cause crash in the path where other users still refer to this dst.

This patch makes sure both input and output path do not take
dst->__refcnt before calling dn_insert_route() and also makes sure
dnrt_free()/dst_free() is called when removing dst from the hash table.
The only difference between those 2 calls is that dnrt_free() waits on
the rcu while dst_free() does not.

Signed-off-by: Wei Wang <weiwan@google.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/decnet/dn_route.c | 14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index b1dc096..403593b 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -188,12 +188,6 @@ static inline void dnrt_free(struct dn_route *rt)
 	call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free);
 }
 
-static inline void dnrt_drop(struct dn_route *rt)
-{
-	dst_release(&rt->dst);
-	call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free);
-}
-
 static void dn_dst_check_expire(unsigned long dummy)
 {
 	int i;
@@ -248,7 +242,7 @@ static int dn_dst_gc(struct dst_ops *ops)
 			}
 			*rtp = rt->dst.dn_next;
 			rt->dst.dn_next = NULL;
-			dnrt_drop(rt);
+			dnrt_free(rt);
 			break;
 		}
 		spin_unlock_bh(&dn_rt_hash_table[i].lock);
@@ -350,7 +344,7 @@ static int dn_insert_route(struct dn_route *rt, unsigned int hash, struct dn_rou
 			dst_use(&rth->dst, now);
 			spin_unlock_bh(&dn_rt_hash_table[hash].lock);
 
-			dnrt_drop(rt);
+			dst_free(&rt->dst);
 			*rp = rth;
 			return 0;
 		}
@@ -380,7 +374,7 @@ static void dn_run_flush(unsigned long dummy)
 		for(; rt; rt = next) {
 			next = rcu_dereference_raw(rt->dst.dn_next);
 			RCU_INIT_POINTER(rt->dst.dn_next, NULL);
-			dst_free((struct dst_entry *)rt);
+			dnrt_free(rt);
 		}
 
 nothing_to_declare:
@@ -1187,7 +1181,7 @@ static int dn_route_output_slow(struct dst_entry **pprt, const struct flowidn *o
 	if (dev_out->flags & IFF_LOOPBACK)
 		flags |= RTCF_LOCAL;
 
-	rt = dst_alloc(&dn_dst_ops, dev_out, 1, DST_OBSOLETE_NONE, DST_HOST);
+	rt = dst_alloc(&dn_dst_ops, dev_out, 0, DST_OBSOLETE_NONE, DST_HOST);
 	if (rt == NULL)
 		goto e_nobufs;
 
-- 
2.4.11


From b93aff4d0f32dc25d515079dfb08e386048717ae Mon Sep 17 00:00:00 2001
From: Gao Feng <gfree.wind@vip.163.com>
Date: Fri, 16 Jun 2017 15:00:02 +0800
Subject: [PATCH 21/24] net: 8021q: Fix one possible panic caused by BUG_ON in
 free_netdev

[ Upstream commit 9745e362add89432d2c951272a99b0a5fe4348a9 ]

The register_vlan_device would invoke free_netdev directly, when
register_vlan_dev failed. It would trigger the BUG_ON in free_netdev
if the dev was already registered. In this case, the netdev would be
freed in netdev_run_todo later.

So add one condition check now. Only when dev is not registered, then
free it directly.

The following is the part coredump when netdev_upper_dev_link failed
in register_vlan_dev. I removed the lines which are too long.

[  411.237457] ------------[ cut here ]------------
[  411.237458] kernel BUG at net/core/dev.c:7998!
[  411.237484] invalid opcode: 0000 [#1] SMP
[  411.237705]  [last unloaded: 8021q]
[  411.237718] CPU: 1 PID: 12845 Comm: vconfig Tainted: G            E   4.12.0-rc5+ #6
[  411.237737] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 07/02/2015
[  411.237764] task: ffff9cbeb6685580 task.stack: ffffa7d2807d8000
[  411.237782] RIP: 0010:free_netdev+0x116/0x120
[  411.237794] RSP: 0018:ffffa7d2807dbdb0 EFLAGS: 00010297
[  411.237808] RAX: 0000000000000002 RBX: ffff9cbeb6ba8fd8 RCX: 0000000000001878
[  411.237826] RDX: 0000000000000001 RSI: 0000000000000282 RDI: 0000000000000000
[  411.237844] RBP: ffffa7d2807dbdc8 R08: 0002986100029841 R09: 0002982100029801
[  411.237861] R10: 0004000100029980 R11: 0004000100029980 R12: ffff9cbeb6ba9000
[  411.238761] R13: ffff9cbeb6ba9060 R14: ffff9cbe60f1a000 R15: ffff9cbeb6ba9000
[  411.239518] FS:  00007fb690d81700(0000) GS:ffff9cbebb640000(0000) knlGS:0000000000000000
[  411.239949] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  411.240454] CR2: 00007f7115624000 CR3: 0000000077cdf000 CR4: 00000000003406e0
[  411.240936] Call Trace:
[  411.241462]  vlan_ioctl_handler+0x3f1/0x400 [8021q]
[  411.241910]  sock_ioctl+0x18b/0x2c0
[  411.242394]  do_vfs_ioctl+0xa1/0x5d0
[  411.242853]  ? sock_alloc_file+0xa6/0x130
[  411.243465]  SyS_ioctl+0x79/0x90
[  411.243900]  entry_SYSCALL_64_fastpath+0x1e/0xa9
[  411.244425] RIP: 0033:0x7fb69089a357
[  411.244863] RSP: 002b:00007ffcd04e0fc8 EFLAGS: 00000202 ORIG_RAX: 0000000000000010
[  411.245445] RAX: ffffffffffffffda RBX: 00007ffcd04e2884 RCX: 00007fb69089a357
[  411.245903] RDX: 00007ffcd04e0fd0 RSI: 0000000000008983 RDI: 0000000000000003
[  411.246527] RBP: 00007ffcd04e0fd0 R08: 0000000000000000 R09: 1999999999999999
[  411.246976] R10: 000000000000053f R11: 0000000000000202 R12: 0000000000000004
[  411.247414] R13: 00007ffcd04e1128 R14: 00007ffcd04e2888 R15: 0000000000000001
[  411.249129] RIP: free_netdev+0x116/0x120 RSP: ffffa7d2807dbdb0

Signed-off-by: Gao Feng <gfree.wind@vip.163.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/8021q/vlan.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index f2531ad..8d213f9 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -277,7 +277,8 @@ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id)
 	return 0;
 
 out_free_newdev:
-	free_netdev(new_dev);
+	if (new_dev->reg_state == NETREG_UNINITIALIZED)
+		free_netdev(new_dev);
 	return err;
 }
 
-- 
2.4.11


From 4a0310d2942bb07a75c065dbc029477d061cae4d Mon Sep 17 00:00:00 2001
From: Bert Kenward <bkenward@solarflare.com>
Date: Fri, 16 Jun 2017 09:45:08 +0100
Subject: [PATCH 22/24] sfc: provide dummy definitions of vswitch functions

efx_probe_all() calls efx->type->vswitching_probe during probe. For
SFC4000 (Falcon) NICs this function is not defined, leading to a BUG
with the top of the call stack similar to:
  ? efx_pci_probe_main+0x29a/0x830
  efx_pci_probe+0x7d3/0xe70

vswitching_restore and vswitching_remove also need to be defined.

Fixed in mainline by:
commit 5a6681e22c14 ("sfc: separate out SFC4000 ("Falcon") support into new sfc-falcon driver")

Fixes: 6d8aaaf6f798 ("sfc: create VEB vswitch and vport above default firmware setup")
Signed-off-by: Bert Kenward <bkenward@solarflare.com>
---
 drivers/net/ethernet/sfc/falcon.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/net/ethernet/sfc/falcon.c b/drivers/net/ethernet/sfc/falcon.c
index 1a70926..1bfb214 100644
--- a/drivers/net/ethernet/sfc/falcon.c
+++ b/drivers/net/ethernet/sfc/falcon.c
@@ -2801,6 +2801,11 @@ const struct efx_nic_type falcon_a1_nic_type = {
 	.timer_period_max =  1 << FRF_AB_TC_TIMER_VAL_WIDTH,
 	.offload_features = NETIF_F_IP_CSUM,
 	.mcdi_max_ver = -1,
+#ifdef CONFIG_SFC_SRIOV
+	.vswitching_probe = efx_port_dummy_op_int,
+	.vswitching_restore = efx_port_dummy_op_int,
+	.vswitching_remove = efx_port_dummy_op_void,
+#endif
 };
 
 const struct efx_nic_type falcon_b0_nic_type = {
@@ -2902,4 +2907,9 @@ const struct efx_nic_type falcon_b0_nic_type = {
 	.offload_features = NETIF_F_IP_CSUM | NETIF_F_RXHASH | NETIF_F_NTUPLE,
 	.mcdi_max_ver = -1,
 	.max_rx_ip_filters = FR_BZ_RX_FILTER_TBL0_ROWS,
+#ifdef CONFIG_SFC_SRIOV
+	.vswitching_probe = efx_port_dummy_op_int,
+	.vswitching_restore = efx_port_dummy_op_int,
+	.vswitching_remove = efx_port_dummy_op_void,
+#endif
 };
-- 
2.4.11


From 7a4e475eaf7f1e7542665b75b979a80b35e9940e Mon Sep 17 00:00:00 2001
From: Serhey Popovych <serhe.popovych@gmail.com>
Date: Tue, 20 Jun 2017 13:29:25 +0300
Subject: [PATCH 23/24] ipv6: Do not leak throw route references

[ Upstream commit 07f615574f8ac499875b21c1142f26308234a92c ]

While commit 73ba57bfae4a ("ipv6: fix backtracking for throw routes")
does good job on error propagation to the fib_rules_lookup()
in fib rules core framework that also corrects throw routes
handling, it does not solve route reference leakage problem
happened when we return -EAGAIN to the fib_rules_lookup()
and leave routing table entry referenced in arg->result.

If rule with matched throw route isn't last matched in the
list we overwrite arg->result losing reference on throw
route stored previously forever.

We also partially revert commit ab997ad40839 ("ipv6: fix the
incorrect return value of throw route") since we never return
routing table entry with dst.error == -EAGAIN when
CONFIG_IPV6_MULTIPLE_TABLES is on. Also there is no point
to check for RTF_REJECT flag since it is always set throw
route.

Fixes: 73ba57bfae4a ("ipv6: fix backtracking for throw routes")
Signed-off-by: Serhey Popovych <serhe.popovych@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/fib6_rules.c | 22 ++++++----------------
 net/ipv6/ip6_fib.c    |  3 +--
 2 files changed, 7 insertions(+), 18 deletions(-)

diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index eea23b5..ec849d8 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -32,7 +32,6 @@ struct fib6_rule {
 struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
 				   int flags, pol_lookup_t lookup)
 {
-	struct rt6_info *rt;
 	struct fib_lookup_arg arg = {
 		.lookup_ptr = lookup,
 		.flags = FIB_LOOKUP_NOREF,
@@ -44,21 +43,11 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
 	fib_rules_lookup(net->ipv6.fib6_rules_ops,
 			 flowi6_to_flowi(fl6), flags, &arg);
 
-	rt = arg.result;
+	if (arg.result)
+		return arg.result;
 
-	if (!rt) {
-		dst_hold(&net->ipv6.ip6_null_entry->dst);
-		return &net->ipv6.ip6_null_entry->dst;
-	}
-
-	if (rt->rt6i_flags & RTF_REJECT &&
-	    rt->dst.error == -EAGAIN) {
-		ip6_rt_put(rt);
-		rt = net->ipv6.ip6_null_entry;
-		dst_hold(&rt->dst);
-	}
-
-	return &rt->dst;
+	dst_hold(&net->ipv6.ip6_null_entry->dst);
+	return &net->ipv6.ip6_null_entry->dst;
 }
 
 static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
@@ -121,7 +110,8 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
 			flp6->saddr = saddr;
 		}
 		err = rt->dst.error;
-		goto out;
+		if (err != -EAGAIN)
+			goto out;
 	}
 again:
 	ip6_rt_put(rt);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 8c88a37..636d4d8 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -289,8 +289,7 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
 	struct rt6_info *rt;
 
 	rt = lookup(net, net->ipv6.fib6_main_tbl, fl6, flags);
-	if (rt->rt6i_flags & RTF_REJECT &&
-	    rt->dst.error == -EAGAIN) {
+	if (rt->dst.error == -EAGAIN) {
 		ip6_rt_put(rt);
 		rt = net->ipv6.ip6_null_entry;
 		dst_hold(&rt->dst);
-- 
2.4.11


From 961dff2bc75da699c1b92ec959587cb6ed8c1b02 Mon Sep 17 00:00:00 2001
From: Serhey Popovych <serhe.popovych@gmail.com>
Date: Tue, 20 Jun 2017 14:35:23 +0300
Subject: [PATCH 24/24] rtnetlink: add IFLA_GROUP to ifla_policy

[ Upstream commit db833d40ad3263b2ee3b59a1ba168bb3cfed8137 ]

Network interface groups support added while ago, however
there is no IFLA_GROUP attribute description in policy
and netlink message size calculations until now.

Add IFLA_GROUP attribute to the policy.

Fixes: cbda10fa97d7 ("net_device: add support for network device groups")
Signed-off-by: Serhey Popovych <serhe.popovych@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index d574409..9c6fd7f 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -937,6 +937,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + nla_total_size(1) /* IFLA_LINKMODE */
 	       + nla_total_size(4) /* IFLA_CARRIER_CHANGES */
 	       + nla_total_size(4) /* IFLA_LINK_NETNSID */
+	       + nla_total_size(4) /* IFLA_GROUP */
 	       + nla_total_size(ext_filter_mask
 			        & RTEXT_FILTER_VF ? 4 : 0) /* IFLA_NUM_VF */
 	       + rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */
@@ -1465,6 +1466,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
 	[IFLA_LINK_NETNSID]	= { .type = NLA_S32 },
 	[IFLA_PROTO_DOWN]	= { .type = NLA_U8 },
 	[IFLA_XDP]		= { .type = NLA_NESTED },
+	[IFLA_GROUP]		= { .type = NLA_U32 },
 };
 
 static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
-- 
2.4.11


[-- Attachment #3: net_411.mbox --]
[-- Type: Application/Octet-Stream, Size: 111327 bytes --]

From 4a34589ae91ebd4c37466a432b4702d3c535383e Mon Sep 17 00:00:00 2001
From: Alexander Potapenko <glider@google.com>
Date: Tue, 6 Jun 2017 15:56:54 +0200
Subject: [PATCH 01/32] net: don't call strlen on non-terminated string in
 dev_set_alias()

[ Upstream commit c28294b941232931fbd714099798eb7aa7e865d7 ]

KMSAN reported a use of uninitialized memory in dev_set_alias(),
which was caused by calling strlcpy() (which in turn called strlen())
on the user-supplied non-terminated string.

Signed-off-by: Alexander Potapenko <glider@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 9b58753..85c626b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1251,8 +1251,9 @@ int dev_set_alias(struct net_device *dev, const char *alias, size_t len)
 	if (!new_ifalias)
 		return -ENOMEM;
 	dev->ifalias = new_ifalias;
+	memcpy(dev->ifalias, alias, len);
+	dev->ifalias[len] = 0;
 
-	strlcpy(dev->ifalias, alias, len+1);
 	return len;
 }
 
-- 
2.4.11


From 54c729ec72a2ee3d447fb924e3354139e4f200dd Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Mon, 8 May 2017 12:52:56 -0400
Subject: [PATCH 02/32] net: Fix inconsistent teardown and release of private
 netdev state.

[ Upstream commit cf124db566e6b036b8bcbe8decbed740bdfac8c6 ]

Network devices can allocate reasources and private memory using
netdev_ops->ndo_init().  However, the release of these resources
can occur in one of two different places.

Either netdev_ops->ndo_uninit() or netdev->destructor().

The decision of which operation frees the resources depends upon
whether it is necessary for all netdev refs to be released before it
is safe to perform the freeing.

netdev_ops->ndo_uninit() presumably can occur right after the
NETDEV_UNREGISTER notifier completes and the unicast and multicast
address lists are flushed.

netdev->destructor(), on the other hand, does not run until the
netdev references all go away.

Further complicating the situation is that netdev->destructor()
almost universally does also a free_netdev().

This creates a problem for the logic in register_netdevice().
Because all callers of register_netdevice() manage the freeing
of the netdev, and invoke free_netdev(dev) if register_netdevice()
fails.

If netdev_ops->ndo_init() succeeds, but something else fails inside
of register_netdevice(), it does call ndo_ops->ndo_uninit().  But
it is not able to invoke netdev->destructor().

This is because netdev->destructor() will do a free_netdev() and
then the caller of register_netdevice() will do the same.

However, this means that the resources that would normally be released
by netdev->destructor() will not be.

Over the years drivers have added local hacks to deal with this, by
invoking their destructor parts by hand when register_netdevice()
fails.

Many drivers do not try to deal with this, and instead we have leaks.

Let's close this hole by formalizing the distinction between what
private things need to be freed up by netdev->destructor() and whether
the driver needs unregister_netdevice() to perform the free_netdev().

netdev->priv_destructor() performs all actions to free up the private
resources that used to be freed by netdev->destructor(), except for
free_netdev().

netdev->needs_free_netdev is a boolean that indicates whether
free_netdev() should be done at the end of unregister_netdevice().

Now, register_netdevice() can sanely release all resources after
ndo_ops->ndo_init() succeeds, by invoking both ndo_ops->ndo_uninit()
and netdev->priv_destructor().

And at the end of unregister_netdevice(), we invoke
netdev->priv_destructor() and optionally call free_netdev().

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c                             | 6 +++---
 drivers/net/caif/caif_hsi.c                                 | 2 +-
 drivers/net/caif/caif_serial.c                              | 2 +-
 drivers/net/caif/caif_spi.c                                 | 2 +-
 drivers/net/caif/caif_virtio.c                              | 2 +-
 drivers/net/can/slcan.c                                     | 7 +++----
 drivers/net/can/vcan.c                                      | 2 +-
 drivers/net/dummy.c                                         | 4 ++--
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c             | 2 +-
 drivers/net/geneve.c                                        | 2 +-
 drivers/net/gtp.c                                           | 2 +-
 drivers/net/hamradio/6pack.c                                | 2 +-
 drivers/net/hamradio/bpqether.c                             | 2 +-
 drivers/net/ifb.c                                           | 4 ++--
 drivers/net/ipvlan/ipvlan_main.c                            | 2 +-
 drivers/net/loopback.c                                      | 4 ++--
 drivers/net/macsec.c                                        | 4 ++--
 drivers/net/macvlan.c                                       | 2 +-
 drivers/net/nlmon.c                                         | 2 +-
 drivers/net/slip/slip.c                                     | 7 +++----
 drivers/net/team/team.c                                     | 4 ++--
 drivers/net/tun.c                                           | 4 ++--
 drivers/net/usb/cdc-phonet.c                                | 2 +-
 drivers/net/veth.c                                          | 4 ++--
 drivers/net/vrf.c                                           | 2 +-
 drivers/net/vxlan.c                                         | 2 +-
 drivers/net/wan/dlci.c                                      | 2 +-
 drivers/net/wan/hdlc_fr.c                                   | 2 +-
 drivers/net/wan/lapbether.c                                 | 2 +-
 drivers/net/wireless/ath/ath6kl/main.c                      | 2 +-
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c | 1 -
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c     | 3 ++-
 drivers/net/wireless/intersil/hostap/hostap_main.c          | 2 +-
 drivers/net/wireless/mac80211_hwsim.c                       | 2 +-
 drivers/net/wireless/marvell/mwifiex/main.c                 | 2 +-
 drivers/staging/rtl8188eu/os_dep/mon.c                      | 2 +-
 drivers/usb/gadget/function/f_phonet.c                      | 2 +-
 include/linux/netdevice.h                                   | 7 ++++---
 net/8021q/vlan_dev.c                                        | 4 ++--
 net/batman-adv/soft-interface.c                             | 5 ++---
 net/bluetooth/6lowpan.c                                     | 2 +-
 net/bridge/br_device.c                                      | 2 +-
 net/caif/chnl_net.c                                         | 4 ++--
 net/core/dev.c                                              | 8 ++++++--
 net/hsr/hsr_device.c                                        | 4 ++--
 net/ieee802154/6lowpan/core.c                               | 2 +-
 net/ipv4/ip_tunnel.c                                        | 4 ++--
 net/ipv4/ipmr.c                                             | 2 +-
 net/ipv6/ip6_gre.c                                          | 9 +++++----
 net/ipv6/ip6_tunnel.c                                       | 8 ++++----
 net/ipv6/ip6_vti.c                                          | 8 ++++----
 net/ipv6/ip6mr.c                                            | 2 +-
 net/ipv6/sit.c                                              | 6 +++---
 net/irda/irlan/irlan_eth.c                                  | 2 +-
 net/l2tp/l2tp_eth.c                                         | 2 +-
 net/mac80211/iface.c                                        | 6 +++---
 net/mac802154/iface.c                                       | 7 +++----
 net/openvswitch/vport-internal_dev.c                        | 4 ++--
 net/phonet/pep-gprs.c                                       | 2 +-
 59 files changed, 102 insertions(+), 100 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 34481c9..6d80067 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -4163,7 +4163,6 @@ static void bond_destructor(struct net_device *bond_dev)
 	struct bonding *bond = netdev_priv(bond_dev);
 	if (bond->wq)
 		destroy_workqueue(bond->wq);
-	free_netdev(bond_dev);
 }
 
 void bond_setup(struct net_device *bond_dev)
@@ -4183,7 +4182,8 @@ void bond_setup(struct net_device *bond_dev)
 	bond_dev->netdev_ops = &bond_netdev_ops;
 	bond_dev->ethtool_ops = &bond_ethtool_ops;
 
-	bond_dev->destructor = bond_destructor;
+	bond_dev->needs_free_netdev = true;
+	bond_dev->priv_destructor = bond_destructor;
 
 	SET_NETDEV_DEVTYPE(bond_dev, &bond_type);
 
@@ -4689,7 +4689,7 @@ int bond_create(struct net *net, const char *name)
 
 	rtnl_unlock();
 	if (res < 0)
-		bond_destructor(bond_dev);
+		free_netdev(bond_dev);
 	return res;
 }
 
diff --git a/drivers/net/caif/caif_hsi.c b/drivers/net/caif/caif_hsi.c
index ddabce7..71a7c3b 100644
--- a/drivers/net/caif/caif_hsi.c
+++ b/drivers/net/caif/caif_hsi.c
@@ -1121,7 +1121,7 @@ static void cfhsi_setup(struct net_device *dev)
 	dev->flags = IFF_POINTOPOINT | IFF_NOARP;
 	dev->mtu = CFHSI_MAX_CAIF_FRAME_SZ;
 	dev->priv_flags |= IFF_NO_QUEUE;
-	dev->destructor = free_netdev;
+	dev->needs_free_netdev = true;
 	dev->netdev_ops = &cfhsi_netdevops;
 	for (i = 0; i < CFHSI_PRIO_LAST; ++i)
 		skb_queue_head_init(&cfhsi->qhead[i]);
diff --git a/drivers/net/caif/caif_serial.c b/drivers/net/caif/caif_serial.c
index c2dea49..76e1d35 100644
--- a/drivers/net/caif/caif_serial.c
+++ b/drivers/net/caif/caif_serial.c
@@ -428,7 +428,7 @@ static void caifdev_setup(struct net_device *dev)
 	dev->flags = IFF_POINTOPOINT | IFF_NOARP;
 	dev->mtu = CAIF_MAX_MTU;
 	dev->priv_flags |= IFF_NO_QUEUE;
-	dev->destructor = free_netdev;
+	dev->needs_free_netdev = true;
 	skb_queue_head_init(&serdev->head);
 	serdev->common.link_select = CAIF_LINK_LOW_LATENCY;
 	serdev->common.use_frag = true;
diff --git a/drivers/net/caif/caif_spi.c b/drivers/net/caif/caif_spi.c
index 3a529fb..fc21afe 100644
--- a/drivers/net/caif/caif_spi.c
+++ b/drivers/net/caif/caif_spi.c
@@ -712,7 +712,7 @@ static void cfspi_setup(struct net_device *dev)
 	dev->flags = IFF_NOARP | IFF_POINTOPOINT;
 	dev->priv_flags |= IFF_NO_QUEUE;
 	dev->mtu = SPI_MAX_PAYLOAD_SIZE;
-	dev->destructor = free_netdev;
+	dev->needs_free_netdev = true;
 	skb_queue_head_init(&cfspi->qhead);
 	skb_queue_head_init(&cfspi->chead);
 	cfspi->cfdev.link_select = CAIF_LINK_HIGH_BANDW;
diff --git a/drivers/net/caif/caif_virtio.c b/drivers/net/caif/caif_virtio.c
index bc0eb47..8bffd25 100644
--- a/drivers/net/caif/caif_virtio.c
+++ b/drivers/net/caif/caif_virtio.c
@@ -617,7 +617,7 @@ static void cfv_netdev_setup(struct net_device *netdev)
 	netdev->tx_queue_len = 100;
 	netdev->flags = IFF_POINTOPOINT | IFF_NOARP;
 	netdev->mtu = CFV_DEF_MTU_SIZE;
-	netdev->destructor = free_netdev;
+	netdev->needs_free_netdev = true;
 }
 
 /* Create debugfs counters for the device */
diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c
index eb71737..6a6e896 100644
--- a/drivers/net/can/slcan.c
+++ b/drivers/net/can/slcan.c
@@ -417,7 +417,7 @@ static int slc_open(struct net_device *dev)
 static void slc_free_netdev(struct net_device *dev)
 {
 	int i = dev->base_addr;
-	free_netdev(dev);
+
 	slcan_devs[i] = NULL;
 }
 
@@ -436,7 +436,8 @@ static const struct net_device_ops slc_netdev_ops = {
 static void slc_setup(struct net_device *dev)
 {
 	dev->netdev_ops		= &slc_netdev_ops;
-	dev->destructor		= slc_free_netdev;
+	dev->needs_free_netdev	= true;
+	dev->priv_destructor	= slc_free_netdev;
 
 	dev->hard_header_len	= 0;
 	dev->addr_len		= 0;
@@ -761,8 +762,6 @@ static void __exit slcan_exit(void)
 		if (sl->tty) {
 			printk(KERN_ERR "%s: tty discipline still running\n",
 			       dev->name);
-			/* Intentionally leak the control block. */
-			dev->destructor = NULL;
 		}
 
 		unregister_netdev(dev);
diff --git a/drivers/net/can/vcan.c b/drivers/net/can/vcan.c
index 674f367..25d1209 100644
--- a/drivers/net/can/vcan.c
+++ b/drivers/net/can/vcan.c
@@ -160,7 +160,7 @@ static void vcan_setup(struct net_device *dev)
 		dev->flags |= IFF_ECHO;
 
 	dev->netdev_ops		= &vcan_netdev_ops;
-	dev->destructor		= free_netdev;
+	dev->needs_free_netdev	= true;
 }
 
 static struct rtnl_link_ops vcan_link_ops __read_mostly = {
diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c
index 2c80611..b66fbe5 100644
--- a/drivers/net/dummy.c
+++ b/drivers/net/dummy.c
@@ -313,7 +313,6 @@ static void dummy_free_netdev(struct net_device *dev)
 	struct dummy_priv *priv = netdev_priv(dev);
 
 	kfree(priv->vfinfo);
-	free_netdev(dev);
 }
 
 static void dummy_setup(struct net_device *dev)
@@ -323,7 +322,8 @@ static void dummy_setup(struct net_device *dev)
 	/* Initialize the device structure. */
 	dev->netdev_ops = &dummy_netdev_ops;
 	dev->ethtool_ops = &dummy_ethtool_ops;
-	dev->destructor = dummy_free_netdev;
+	dev->needs_free_netdev = true;
+	dev->priv_destructor = dummy_free_netdev;
 
 	/* Fill in device structure with ethernet-generic values. */
 	dev->flags |= IFF_NOARP;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 012194b..6e9f82e 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -4528,7 +4528,7 @@ static void dummy_setup(struct net_device *dev)
 	/* Initialize the device structure. */
 	dev->netdev_ops = &cxgb4_mgmt_netdev_ops;
 	dev->ethtool_ops = &cxgb4_mgmt_ethtool_ops;
-	dev->destructor = free_netdev;
+	dev->needs_free_netdev = true;
 }
 
 static int config_mgmt_dev(struct pci_dev *pdev)
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 6ebb0f5..199459b 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1007,7 +1007,7 @@ static void geneve_setup(struct net_device *dev)
 
 	dev->netdev_ops = &geneve_netdev_ops;
 	dev->ethtool_ops = &geneve_ethtool_ops;
-	dev->destructor = free_netdev;
+	dev->needs_free_netdev = true;
 
 	SET_NETDEV_DEVTYPE(dev, &geneve_type);
 
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 8969874..4293870 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -618,7 +618,7 @@ static const struct net_device_ops gtp_netdev_ops = {
 static void gtp_link_setup(struct net_device *dev)
 {
 	dev->netdev_ops		= &gtp_netdev_ops;
-	dev->destructor		= free_netdev;
+	dev->needs_free_netdev	= true;
 
 	dev->hard_header_len = 0;
 	dev->addr_len = 0;
diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c
index 922bf44..021a8ec 100644
--- a/drivers/net/hamradio/6pack.c
+++ b/drivers/net/hamradio/6pack.c
@@ -311,7 +311,7 @@ static void sp_setup(struct net_device *dev)
 {
 	/* Finish setting up the DEVICE info. */
 	dev->netdev_ops		= &sp_netdev_ops;
-	dev->destructor		= free_netdev;
+	dev->needs_free_netdev	= true;
 	dev->mtu		= SIXP_MTU;
 	dev->hard_header_len	= AX25_MAX_HEADER_LEN;
 	dev->header_ops 	= &ax25_header_ops;
diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c
index f62e7f3..78a6414 100644
--- a/drivers/net/hamradio/bpqether.c
+++ b/drivers/net/hamradio/bpqether.c
@@ -476,7 +476,7 @@ static const struct net_device_ops bpq_netdev_ops = {
 static void bpq_setup(struct net_device *dev)
 {
 	dev->netdev_ops	     = &bpq_netdev_ops;
-	dev->destructor	     = free_netdev;
+	dev->needs_free_netdev = true;
 
 	memcpy(dev->broadcast, &ax25_bcast, AX25_ADDR_LEN);
 	memcpy(dev->dev_addr,  &ax25_defaddr, AX25_ADDR_LEN);
diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c
index 312fce7..144ea5a 100644
--- a/drivers/net/ifb.c
+++ b/drivers/net/ifb.c
@@ -207,7 +207,6 @@ static void ifb_dev_free(struct net_device *dev)
 		__skb_queue_purge(&txp->tq);
 	}
 	kfree(dp->tx_private);
-	free_netdev(dev);
 }
 
 static void ifb_setup(struct net_device *dev)
@@ -230,7 +229,8 @@ static void ifb_setup(struct net_device *dev)
 	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	netif_keep_dst(dev);
 	eth_hw_addr_random(dev);
-	dev->destructor = ifb_dev_free;
+	dev->needs_free_netdev = true;
+	dev->priv_destructor = ifb_dev_free;
 }
 
 static netdev_tx_t ifb_xmit(struct sk_buff *skb, struct net_device *dev)
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index aa8575c..48e6c4e 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -621,7 +621,7 @@ void ipvlan_link_setup(struct net_device *dev)
 	dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING);
 	dev->priv_flags |= IFF_UNICAST_FLT | IFF_NO_QUEUE;
 	dev->netdev_ops = &ipvlan_netdev_ops;
-	dev->destructor = free_netdev;
+	dev->needs_free_netdev = true;
 	dev->header_ops = &ipvlan_header_ops;
 	dev->ethtool_ops = &ipvlan_ethtool_ops;
 }
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index b23b719..80e3ace 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -145,7 +145,6 @@ static void loopback_dev_free(struct net_device *dev)
 {
 	dev_net(dev)->loopback_dev = NULL;
 	free_percpu(dev->lstats);
-	free_netdev(dev);
 }
 
 static const struct net_device_ops loopback_ops = {
@@ -183,7 +182,8 @@ static void loopback_setup(struct net_device *dev)
 	dev->ethtool_ops	= &loopback_ethtool_ops;
 	dev->header_ops		= &eth_header_ops;
 	dev->netdev_ops		= &loopback_ops;
-	dev->destructor		= loopback_dev_free;
+	dev->needs_free_netdev	= true;
+	dev->priv_destructor	= loopback_dev_free;
 }
 
 /* Setup and register the loopback device. */
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 49ce4e9..43f3e1b 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -2994,7 +2994,6 @@ static void macsec_free_netdev(struct net_device *dev)
 	free_percpu(macsec->secy.tx_sc.stats);
 
 	dev_put(real_dev);
-	free_netdev(dev);
 }
 
 static void macsec_setup(struct net_device *dev)
@@ -3004,7 +3003,8 @@ static void macsec_setup(struct net_device *dev)
 	dev->max_mtu = ETH_MAX_MTU;
 	dev->priv_flags |= IFF_NO_QUEUE;
 	dev->netdev_ops = &macsec_netdev_ops;
-	dev->destructor = macsec_free_netdev;
+	dev->needs_free_netdev = true;
+	dev->priv_destructor = macsec_free_netdev;
 	SET_NETDEV_DEVTYPE(dev, &macsec_type);
 
 	eth_zero_addr(dev->broadcast);
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index b34eaaa..b8cec52 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -1089,7 +1089,7 @@ void macvlan_common_setup(struct net_device *dev)
 	netif_keep_dst(dev);
 	dev->priv_flags	       |= IFF_UNICAST_FLT;
 	dev->netdev_ops		= &macvlan_netdev_ops;
-	dev->destructor		= free_netdev;
+	dev->needs_free_netdev	= true;
 	dev->header_ops		= &macvlan_hard_header_ops;
 	dev->ethtool_ops	= &macvlan_ethtool_ops;
 }
diff --git a/drivers/net/nlmon.c b/drivers/net/nlmon.c
index b916038..c4b3362 100644
--- a/drivers/net/nlmon.c
+++ b/drivers/net/nlmon.c
@@ -113,7 +113,7 @@ static void nlmon_setup(struct net_device *dev)
 
 	dev->netdev_ops	= &nlmon_ops;
 	dev->ethtool_ops = &nlmon_ethtool_ops;
-	dev->destructor	= free_netdev;
+	dev->needs_free_netdev = true;
 
 	dev->features = NETIF_F_SG | NETIF_F_FRAGLIST |
 			NETIF_F_HIGHDMA | NETIF_F_LLTX;
diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c
index 1da31dc..74b9072 100644
--- a/drivers/net/slip/slip.c
+++ b/drivers/net/slip/slip.c
@@ -629,7 +629,7 @@ static void sl_uninit(struct net_device *dev)
 static void sl_free_netdev(struct net_device *dev)
 {
 	int i = dev->base_addr;
-	free_netdev(dev);
+
 	slip_devs[i] = NULL;
 }
 
@@ -651,7 +651,8 @@ static const struct net_device_ops sl_netdev_ops = {
 static void sl_setup(struct net_device *dev)
 {
 	dev->netdev_ops		= &sl_netdev_ops;
-	dev->destructor		= sl_free_netdev;
+	dev->needs_free_netdev	= true;
+	dev->priv_destructor	= sl_free_netdev;
 
 	dev->hard_header_len	= 0;
 	dev->addr_len		= 0;
@@ -1369,8 +1370,6 @@ static void __exit slip_exit(void)
 		if (sl->tty) {
 			printk(KERN_ERR "%s: tty discipline still running\n",
 			       dev->name);
-			/* Intentionally leak the control block. */
-			dev->destructor = NULL;
 		}
 
 		unregister_netdev(dev);
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 85c0124..eaa6ee7 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1643,7 +1643,6 @@ static void team_destructor(struct net_device *dev)
 	struct team *team = netdev_priv(dev);
 
 	free_percpu(team->pcpu_stats);
-	free_netdev(dev);
 }
 
 static int team_open(struct net_device *dev)
@@ -2079,7 +2078,8 @@ static void team_setup(struct net_device *dev)
 
 	dev->netdev_ops = &team_netdev_ops;
 	dev->ethtool_ops = &team_ethtool_ops;
-	dev->destructor	= team_destructor;
+	dev->needs_free_netdev = true;
+	dev->priv_destructor = team_destructor;
 	dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING);
 	dev->priv_flags |= IFF_NO_QUEUE;
 	dev->priv_flags |= IFF_TEAM;
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index cc88cd7..7f3db49 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1560,7 +1560,6 @@ static void tun_free_netdev(struct net_device *dev)
 	free_percpu(tun->pcpu_stats);
 	tun_flow_uninit(tun);
 	security_tun_dev_free_security(tun->security);
-	free_netdev(dev);
 }
 
 static void tun_setup(struct net_device *dev)
@@ -1571,7 +1570,8 @@ static void tun_setup(struct net_device *dev)
 	tun->group = INVALID_GID;
 
 	dev->ethtool_ops = &tun_ethtool_ops;
-	dev->destructor = tun_free_netdev;
+	dev->needs_free_netdev = true;
+	dev->priv_destructor = tun_free_netdev;
 	/* We prefer our own queue length */
 	dev->tx_queue_len = TUN_READQ_SIZE;
 }
diff --git a/drivers/net/usb/cdc-phonet.c b/drivers/net/usb/cdc-phonet.c
index eb52de8..c7a350b 100644
--- a/drivers/net/usb/cdc-phonet.c
+++ b/drivers/net/usb/cdc-phonet.c
@@ -298,7 +298,7 @@ static void usbpn_setup(struct net_device *dev)
 	dev->addr_len		= 1;
 	dev->tx_queue_len	= 3;
 
-	dev->destructor		= free_netdev;
+	dev->needs_free_netdev	= true;
 }
 
 /*
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 8c39d6d..2efbe98 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -227,7 +227,6 @@ static int veth_dev_init(struct net_device *dev)
 static void veth_dev_free(struct net_device *dev)
 {
 	free_percpu(dev->vstats);
-	free_netdev(dev);
 }
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
@@ -322,7 +321,8 @@ static void veth_setup(struct net_device *dev)
 			       NETIF_F_HW_VLAN_STAG_TX |
 			       NETIF_F_HW_VLAN_CTAG_RX |
 			       NETIF_F_HW_VLAN_STAG_RX);
-	dev->destructor = veth_dev_free;
+	dev->needs_free_netdev = true;
+	dev->priv_destructor = veth_dev_free;
 	dev->max_mtu = ETH_MAX_MTU;
 
 	dev->hw_features = VETH_FEATURES;
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index df74efc..e669372 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -1206,7 +1206,7 @@ static void vrf_setup(struct net_device *dev)
 	dev->netdev_ops = &vrf_netdev_ops;
 	dev->l3mdev_ops = &vrf_l3mdev_ops;
 	dev->ethtool_ops = &vrf_ethtool_ops;
-	dev->destructor = free_netdev;
+	dev->needs_free_netdev = true;
 
 	/* Fill in device structure with ethernet-generic values. */
 	eth_hw_addr_random(dev);
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 70dbd5a..4574b95 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2607,7 +2607,7 @@ static void vxlan_setup(struct net_device *dev)
 	eth_hw_addr_random(dev);
 	ether_setup(dev);
 
-	dev->destructor = free_netdev;
+	dev->needs_free_netdev = true;
 	SET_NETDEV_DEVTYPE(dev, &vxlan_type);
 
 	dev->features	|= NETIF_F_LLTX;
diff --git a/drivers/net/wan/dlci.c b/drivers/net/wan/dlci.c
index 65ee2a6..a0d76f7 100644
--- a/drivers/net/wan/dlci.c
+++ b/drivers/net/wan/dlci.c
@@ -475,7 +475,7 @@ static void dlci_setup(struct net_device *dev)
 	dev->flags		= 0;
 	dev->header_ops		= &dlci_header_ops;
 	dev->netdev_ops		= &dlci_netdev_ops;
-	dev->destructor		= free_netdev;
+	dev->needs_free_netdev	= true;
 
 	dlp->receive		= dlci_receive;
 
diff --git a/drivers/net/wan/hdlc_fr.c b/drivers/net/wan/hdlc_fr.c
index eb91528..78596e4 100644
--- a/drivers/net/wan/hdlc_fr.c
+++ b/drivers/net/wan/hdlc_fr.c
@@ -1106,7 +1106,7 @@ static int fr_add_pvc(struct net_device *frad, unsigned int dlci, int type)
 		return -EIO;
 	}
 
-	dev->destructor = free_netdev;
+	dev->needs_free_netdev = true;
 	*get_dev_p(pvc, type) = dev;
 	if (!used) {
 		state(hdlc)->dce_changed = 1;
diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c
index 9df9ed6..63f7490 100644
--- a/drivers/net/wan/lapbether.c
+++ b/drivers/net/wan/lapbether.c
@@ -306,7 +306,7 @@ static const struct net_device_ops lapbeth_netdev_ops = {
 static void lapbeth_setup(struct net_device *dev)
 {
 	dev->netdev_ops	     = &lapbeth_netdev_ops;
-	dev->destructor	     = free_netdev;
+	dev->needs_free_netdev = true;
 	dev->type            = ARPHRD_X25;
 	dev->hard_header_len = 3;
 	dev->mtu             = 1000;
diff --git a/drivers/net/wireless/ath/ath6kl/main.c b/drivers/net/wireless/ath/ath6kl/main.c
index 91ee542..b90c77e 100644
--- a/drivers/net/wireless/ath/ath6kl/main.c
+++ b/drivers/net/wireless/ath/ath6kl/main.c
@@ -1287,7 +1287,7 @@ void init_netdev(struct net_device *dev)
 	struct ath6kl *ar = ath6kl_priv(dev);
 
 	dev->netdev_ops = &ath6kl_netdev_ops;
-	dev->destructor = free_netdev;
+	dev->needs_free_netdev = true;
 	dev->watchdog_timeo = ATH6KL_TX_TIMEOUT;
 
 	dev->needed_headroom = ETH_HLEN;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index 944b83c..017e20b 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -5209,7 +5209,6 @@ void brcmf_cfg80211_free_netdev(struct net_device *ndev)
 
 	if (vif)
 		brcmf_free_vif(vif);
-	free_netdev(ndev);
 }
 
 static bool brcmf_is_linkup(const struct brcmf_event_msg *e)
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
index f6b17fb..d02e7f6 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
@@ -652,7 +652,8 @@ struct brcmf_if *brcmf_add_if(struct brcmf_pub *drvr, s32 bsscfgidx, s32 ifidx,
 		if (!ndev)
 			return ERR_PTR(-ENOMEM);
 
-		ndev->destructor = brcmf_cfg80211_free_netdev;
+		ndev->needs_free_netdev = true;
+		ndev->priv_destructor = brcmf_cfg80211_free_netdev;
 		ifp = netdev_priv(ndev);
 		ifp->ndev = ndev;
 		/* store mapping ifidx to bsscfgidx */
diff --git a/drivers/net/wireless/intersil/hostap/hostap_main.c b/drivers/net/wireless/intersil/hostap/hostap_main.c
index 544fc09..1372b20 100644
--- a/drivers/net/wireless/intersil/hostap/hostap_main.c
+++ b/drivers/net/wireless/intersil/hostap/hostap_main.c
@@ -73,7 +73,7 @@ struct net_device * hostap_add_interface(struct local_info *local,
 	dev->mem_end = mdev->mem_end;
 
 	hostap_setup_dev(dev, local, type);
-	dev->destructor = free_netdev;
+	dev->needs_free_netdev = true;
 
 	sprintf(dev->name, "%s%s", prefix, name);
 	if (!rtnl_locked)
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 50c219f..2aa5cc6 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -2807,7 +2807,7 @@ static const struct net_device_ops hwsim_netdev_ops = {
 static void hwsim_mon_setup(struct net_device *dev)
 {
 	dev->netdev_ops = &hwsim_netdev_ops;
-	dev->destructor = free_netdev;
+	dev->needs_free_netdev = true;
 	ether_setup(dev);
 	dev->priv_flags |= IFF_NO_QUEUE;
 	dev->type = ARPHRD_IEEE80211_RADIOTAP;
diff --git a/drivers/net/wireless/marvell/mwifiex/main.c b/drivers/net/wireless/marvell/mwifiex/main.c
index b62e03d..46073bb 100644
--- a/drivers/net/wireless/marvell/mwifiex/main.c
+++ b/drivers/net/wireless/marvell/mwifiex/main.c
@@ -1277,7 +1277,7 @@ void mwifiex_init_priv_params(struct mwifiex_private *priv,
 			      struct net_device *dev)
 {
 	dev->netdev_ops = &mwifiex_netdev_ops;
-	dev->destructor = free_netdev;
+	dev->needs_free_netdev = true;
 	/* Initialize private structure */
 	priv->current_key_index = 0;
 	priv->media_connected = false;
diff --git a/drivers/staging/rtl8188eu/os_dep/mon.c b/drivers/staging/rtl8188eu/os_dep/mon.c
index cfe37eb..859d0d6 100644
--- a/drivers/staging/rtl8188eu/os_dep/mon.c
+++ b/drivers/staging/rtl8188eu/os_dep/mon.c
@@ -152,7 +152,7 @@ static const struct net_device_ops mon_netdev_ops = {
 static void mon_setup(struct net_device *dev)
 {
 	dev->netdev_ops = &mon_netdev_ops;
-	dev->destructor = free_netdev;
+	dev->needs_free_netdev = true;
 	ether_setup(dev);
 	dev->priv_flags |= IFF_NO_QUEUE;
 	dev->type = ARPHRD_IEEE80211;
diff --git a/drivers/usb/gadget/function/f_phonet.c b/drivers/usb/gadget/function/f_phonet.c
index b4058f0..6a1ce6a 100644
--- a/drivers/usb/gadget/function/f_phonet.c
+++ b/drivers/usb/gadget/function/f_phonet.c
@@ -281,7 +281,7 @@ static void pn_net_setup(struct net_device *dev)
 	dev->tx_queue_len	= 1;
 
 	dev->netdev_ops		= &pn_netdev_ops;
-	dev->destructor		= free_netdev;
+	dev->needs_free_netdev	= true;
 	dev->header_ops		= &phonet_header_ops;
 }
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 97456b25..3ccabb4 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1581,8 +1581,8 @@ enum netdev_priv_flags {
  *	@rtnl_link_state:	This enum represents the phases of creating
  *				a new link
  *
- *	@destructor:		Called from unregister,
- *				can be used to call free_netdev
+ *	@needs_free_netdev:	Should unregister perform free_netdev?
+ *	@priv_destructor:	Called from unregister
  *	@npinfo:		XXX: need comments on this one
  * 	@nd_net:		Network namespace this network device is inside
  *
@@ -1838,7 +1838,8 @@ struct net_device {
 		RTNL_LINK_INITIALIZING,
 	} rtnl_link_state:16;
 
-	void (*destructor)(struct net_device *dev);
+	bool needs_free_netdev;
+	void (*priv_destructor)(struct net_device *dev);
 
 #ifdef CONFIG_NETPOLL
 	struct netpoll_info __rcu	*npinfo;
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index e97ab82..0064dfd 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -807,7 +807,6 @@ static void vlan_dev_free(struct net_device *dev)
 
 	free_percpu(vlan->vlan_pcpu_stats);
 	vlan->vlan_pcpu_stats = NULL;
-	free_netdev(dev);
 }
 
 void vlan_setup(struct net_device *dev)
@@ -820,7 +819,8 @@ void vlan_setup(struct net_device *dev)
 	netif_keep_dst(dev);
 
 	dev->netdev_ops		= &vlan_netdev_ops;
-	dev->destructor		= vlan_dev_free;
+	dev->needs_free_netdev	= true;
+	dev->priv_destructor	= vlan_dev_free;
 	dev->ethtool_ops	= &vlan_ethtool_ops;
 
 	dev->min_mtu		= 0;
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index d042c99..07ca0e8 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -961,8 +961,6 @@ static void batadv_softif_free(struct net_device *dev)
 	 * netdev and its private data (bat_priv)
 	 */
 	rcu_barrier();
-
-	free_netdev(dev);
 }
 
 /**
@@ -976,7 +974,8 @@ static void batadv_softif_init_early(struct net_device *dev)
 	ether_setup(dev);
 
 	dev->netdev_ops = &batadv_netdev_ops;
-	dev->destructor = batadv_softif_free;
+	dev->needs_free_netdev = true;
+	dev->priv_destructor = batadv_softif_free;
 	dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_NETNS_LOCAL;
 	dev->priv_flags |= IFF_NO_QUEUE;
 
diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
index d491529..7ffeca7 100644
--- a/net/bluetooth/6lowpan.c
+++ b/net/bluetooth/6lowpan.c
@@ -653,7 +653,7 @@ static void netdev_setup(struct net_device *dev)
 
 	dev->netdev_ops		= &netdev_ops;
 	dev->header_ops		= &header_ops;
-	dev->destructor		= free_netdev;
+	dev->needs_free_netdev	= true;
 }
 
 static struct device_type bt_type = {
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 430b53e..f0f3447 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -379,7 +379,7 @@ void br_dev_setup(struct net_device *dev)
 	ether_setup(dev);
 
 	dev->netdev_ops = &br_netdev_ops;
-	dev->destructor = free_netdev;
+	dev->needs_free_netdev = true;
 	dev->ethtool_ops = &br_ethtool_ops;
 	SET_NETDEV_DEVTYPE(dev, &br_type);
 	dev->priv_flags = IFF_EBRIDGE | IFF_NO_QUEUE;
diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c
index 1816fc9..fe3c53e 100644
--- a/net/caif/chnl_net.c
+++ b/net/caif/chnl_net.c
@@ -392,14 +392,14 @@ static void chnl_net_destructor(struct net_device *dev)
 {
 	struct chnl_net *priv = netdev_priv(dev);
 	caif_free_client(&priv->chnl);
-	free_netdev(dev);
 }
 
 static void ipcaif_net_setup(struct net_device *dev)
 {
 	struct chnl_net *priv;
 	dev->netdev_ops = &netdev_ops;
-	dev->destructor = chnl_net_destructor;
+	dev->needs_free_netdev = true;
+	dev->priv_destructor = chnl_net_destructor;
 	dev->flags |= IFF_NOARP;
 	dev->flags |= IFF_POINTOPOINT;
 	dev->mtu = GPRS_PDP_MTU;
diff --git a/net/core/dev.c b/net/core/dev.c
index 85c626b..9debc1b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7346,6 +7346,8 @@ int register_netdevice(struct net_device *dev)
 err_uninit:
 	if (dev->netdev_ops->ndo_uninit)
 		dev->netdev_ops->ndo_uninit(dev);
+	if (dev->priv_destructor)
+		dev->priv_destructor(dev);
 	goto out;
 }
 EXPORT_SYMBOL(register_netdevice);
@@ -7553,8 +7555,10 @@ void netdev_run_todo(void)
 		WARN_ON(rcu_access_pointer(dev->ip6_ptr));
 		WARN_ON(dev->dn_ptr);
 
-		if (dev->destructor)
-			dev->destructor(dev);
+		if (dev->priv_destructor)
+			dev->priv_destructor(dev);
+		if (dev->needs_free_netdev)
+			free_netdev(dev);
 
 		/* Report a network device has been unregistered */
 		rtnl_lock();
diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index c73160f..0a0a392 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -378,7 +378,6 @@ static void hsr_dev_destroy(struct net_device *hsr_dev)
 	del_timer_sync(&hsr->announce_timer);
 
 	synchronize_rcu();
-	free_netdev(hsr_dev);
 }
 
 static const struct net_device_ops hsr_device_ops = {
@@ -404,7 +403,8 @@ void hsr_dev_setup(struct net_device *dev)
 	SET_NETDEV_DEVTYPE(dev, &hsr_type);
 	dev->priv_flags |= IFF_NO_QUEUE;
 
-	dev->destructor = hsr_dev_destroy;
+	dev->needs_free_netdev = true;
+	dev->priv_destructor = hsr_dev_destroy;
 
 	dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA |
 			   NETIF_F_GSO_MASK | NETIF_F_HW_CSUM |
diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c
index d7efbf0..0a866f33 100644
--- a/net/ieee802154/6lowpan/core.c
+++ b/net/ieee802154/6lowpan/core.c
@@ -107,7 +107,7 @@ static void lowpan_setup(struct net_device *ldev)
 
 	ldev->netdev_ops	= &lowpan_netdev_ops;
 	ldev->header_ops	= &lowpan_header_ops;
-	ldev->destructor	= free_netdev;
+	ldev->needs_free_netdev	= true;
 	ldev->features		|= NETIF_F_NETNS_LOCAL;
 }
 
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 823abae..b2d1be5 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -961,7 +961,6 @@ static void ip_tunnel_dev_free(struct net_device *dev)
 	gro_cells_destroy(&tunnel->gro_cells);
 	dst_cache_destroy(&tunnel->dst_cache);
 	free_percpu(dev->tstats);
-	free_netdev(dev);
 }
 
 void ip_tunnel_dellink(struct net_device *dev, struct list_head *head)
@@ -1148,7 +1147,8 @@ int ip_tunnel_init(struct net_device *dev)
 	struct iphdr *iph = &tunnel->parms.iph;
 	int err;
 
-	dev->destructor	= ip_tunnel_dev_free;
+	dev->needs_free_netdev = true;
+	dev->priv_destructor = ip_tunnel_dev_free;
 	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
 	if (!dev->tstats)
 		return -ENOMEM;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index b036e85..96c5681 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -501,7 +501,7 @@ static void reg_vif_setup(struct net_device *dev)
 	dev->mtu		= ETH_DATA_LEN - sizeof(struct iphdr) - 8;
 	dev->flags		= IFF_NOARP;
 	dev->netdev_ops		= &reg_vif_netdev_ops;
-	dev->destructor		= free_netdev;
+	dev->needs_free_netdev	= true;
 	dev->features		|= NETIF_F_NETNS_LOCAL;
 }
 
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 4d60164..0f1c249 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -986,13 +986,13 @@ static void ip6gre_dev_free(struct net_device *dev)
 
 	dst_cache_destroy(&t->dst_cache);
 	free_percpu(dev->tstats);
-	free_netdev(dev);
 }
 
 static void ip6gre_tunnel_setup(struct net_device *dev)
 {
 	dev->netdev_ops = &ip6gre_netdev_ops;
-	dev->destructor = ip6gre_dev_free;
+	dev->needs_free_netdev = true;
+	dev->priv_destructor = ip6gre_dev_free;
 
 	dev->type = ARPHRD_IP6GRE;
 
@@ -1143,7 +1143,7 @@ static int __net_init ip6gre_init_net(struct net *net)
 	return 0;
 
 err_reg_dev:
-	ip6gre_dev_free(ign->fb_tunnel_dev);
+	free_netdev(ign->fb_tunnel_dev);
 err_alloc_dev:
 	return err;
 }
@@ -1292,7 +1292,8 @@ static void ip6gre_tap_setup(struct net_device *dev)
 	ether_setup(dev);
 
 	dev->netdev_ops = &ip6gre_tap_netdev_ops;
-	dev->destructor = ip6gre_dev_free;
+	dev->needs_free_netdev = true;
+	dev->priv_destructor = ip6gre_dev_free;
 
 	dev->features |= NETIF_F_NETNS_LOCAL;
 	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index e2d7867..292f24c 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -254,7 +254,6 @@ static void ip6_dev_free(struct net_device *dev)
 	gro_cells_destroy(&t->gro_cells);
 	dst_cache_destroy(&t->dst_cache);
 	free_percpu(dev->tstats);
-	free_netdev(dev);
 }
 
 static int ip6_tnl_create2(struct net_device *dev)
@@ -322,7 +321,7 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p)
 	return t;
 
 failed_free:
-	ip6_dev_free(dev);
+	free_netdev(dev);
 failed:
 	return ERR_PTR(err);
 }
@@ -1772,7 +1771,8 @@ static const struct net_device_ops ip6_tnl_netdev_ops = {
 static void ip6_tnl_dev_setup(struct net_device *dev)
 {
 	dev->netdev_ops = &ip6_tnl_netdev_ops;
-	dev->destructor = ip6_dev_free;
+	dev->needs_free_netdev = true;
+	dev->priv_destructor = ip6_dev_free;
 
 	dev->type = ARPHRD_TUNNEL6;
 	dev->flags |= IFF_NOARP;
@@ -2211,7 +2211,7 @@ static int __net_init ip6_tnl_init_net(struct net *net)
 	return 0;
 
 err_register:
-	ip6_dev_free(ip6n->fb_tnl_dev);
+	free_netdev(ip6n->fb_tnl_dev);
 err_alloc_dev:
 	return err;
 }
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 3d8a3b6..5659f4a 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -180,7 +180,6 @@ vti6_tnl_unlink(struct vti6_net *ip6n, struct ip6_tnl *t)
 static void vti6_dev_free(struct net_device *dev)
 {
 	free_percpu(dev->tstats);
-	free_netdev(dev);
 }
 
 static int vti6_tnl_create2(struct net_device *dev)
@@ -235,7 +234,7 @@ static struct ip6_tnl *vti6_tnl_create(struct net *net, struct __ip6_tnl_parm *p
 	return t;
 
 failed_free:
-	vti6_dev_free(dev);
+	free_netdev(dev);
 failed:
 	return NULL;
 }
@@ -841,7 +840,8 @@ static const struct net_device_ops vti6_netdev_ops = {
 static void vti6_dev_setup(struct net_device *dev)
 {
 	dev->netdev_ops = &vti6_netdev_ops;
-	dev->destructor = vti6_dev_free;
+	dev->needs_free_netdev = true;
+	dev->priv_destructor = vti6_dev_free;
 
 	dev->type = ARPHRD_TUNNEL6;
 	dev->hard_header_len = LL_MAX_HEADER + sizeof(struct ipv6hdr);
@@ -1092,7 +1092,7 @@ static int __net_init vti6_init_net(struct net *net)
 	return 0;
 
 err_register:
-	vti6_dev_free(ip6n->fb_tnl_dev);
+	free_netdev(ip6n->fb_tnl_dev);
 err_alloc_dev:
 	return err;
 }
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index bf34d09..576fd93 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -733,7 +733,7 @@ static void reg_vif_setup(struct net_device *dev)
 	dev->mtu		= 1500 - sizeof(struct ipv6hdr) - 8;
 	dev->flags		= IFF_NOARP;
 	dev->netdev_ops		= &reg_vif_netdev_ops;
-	dev->destructor		= free_netdev;
+	dev->needs_free_netdev	= true;
 	dev->features		|= NETIF_F_NETNS_LOCAL;
 }
 
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 99853c6..4f07a21 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -265,7 +265,7 @@ static struct ip_tunnel *ipip6_tunnel_locate(struct net *net,
 	return nt;
 
 failed_free:
-	ipip6_dev_free(dev);
+	free_netdev(dev);
 failed:
 	return NULL;
 }
@@ -1333,7 +1333,6 @@ static void ipip6_dev_free(struct net_device *dev)
 
 	dst_cache_destroy(&tunnel->dst_cache);
 	free_percpu(dev->tstats);
-	free_netdev(dev);
 }
 
 #define SIT_FEATURES (NETIF_F_SG	   | \
@@ -1348,7 +1347,8 @@ static void ipip6_tunnel_setup(struct net_device *dev)
 	int t_hlen = tunnel->hlen + sizeof(struct iphdr);
 
 	dev->netdev_ops		= &ipip6_netdev_ops;
-	dev->destructor		= ipip6_dev_free;
+	dev->needs_free_netdev	= true;
+	dev->priv_destructor	= ipip6_dev_free;
 
 	dev->type		= ARPHRD_SIT;
 	dev->hard_header_len	= LL_MAX_HEADER + t_hlen;
diff --git a/net/irda/irlan/irlan_eth.c b/net/irda/irlan/irlan_eth.c
index 74d09f9..3be8528 100644
--- a/net/irda/irlan/irlan_eth.c
+++ b/net/irda/irlan/irlan_eth.c
@@ -65,7 +65,7 @@ static void irlan_eth_setup(struct net_device *dev)
 	ether_setup(dev);
 
 	dev->netdev_ops		= &irlan_eth_netdev_ops;
-	dev->destructor		= free_netdev;
+	dev->needs_free_netdev	= true;
 	dev->min_mtu		= 0;
 	dev->max_mtu		= ETH_MAX_MTU;
 
diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index 6fd41d7..cafb667 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -133,7 +133,7 @@ static void l2tp_eth_dev_setup(struct net_device *dev)
 	dev->priv_flags		&= ~IFF_TX_SKB_SHARING;
 	dev->features		|= NETIF_F_LLTX;
 	dev->netdev_ops		= &l2tp_eth_netdev_ops;
-	dev->destructor		= free_netdev;
+	dev->needs_free_netdev	= true;
 }
 
 static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb, int data_len)
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 5bb0c50..6d23427 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1198,7 +1198,6 @@ static const struct net_device_ops ieee80211_monitorif_ops = {
 static void ieee80211_if_free(struct net_device *dev)
 {
 	free_percpu(dev->tstats);
-	free_netdev(dev);
 }
 
 static void ieee80211_if_setup(struct net_device *dev)
@@ -1206,7 +1205,8 @@ static void ieee80211_if_setup(struct net_device *dev)
 	ether_setup(dev);
 	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	dev->netdev_ops = &ieee80211_dataif_ops;
-	dev->destructor = ieee80211_if_free;
+	dev->needs_free_netdev = true;
+	dev->priv_destructor = ieee80211_if_free;
 }
 
 static void ieee80211_if_setup_no_queue(struct net_device *dev)
@@ -1899,7 +1899,7 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name,
 
 		ret = register_netdevice(ndev);
 		if (ret) {
-			ieee80211_if_free(ndev);
+			free_netdev(ndev);
 			return ret;
 		}
 	}
diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c
index 06019db..bd88a9b 100644
--- a/net/mac802154/iface.c
+++ b/net/mac802154/iface.c
@@ -526,8 +526,6 @@ static void mac802154_wpan_free(struct net_device *dev)
 	struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev);
 
 	mac802154_llsec_destroy(&sdata->sec);
-
-	free_netdev(dev);
 }
 
 static void ieee802154_if_setup(struct net_device *dev)
@@ -593,7 +591,8 @@ ieee802154_setup_sdata(struct ieee802154_sub_if_data *sdata,
 					sdata->dev->dev_addr);
 
 		sdata->dev->header_ops = &mac802154_header_ops;
-		sdata->dev->destructor = mac802154_wpan_free;
+		sdata->dev->needs_free_netdev = true;
+		sdata->dev->priv_destructor = mac802154_wpan_free;
 		sdata->dev->netdev_ops = &mac802154_wpan_ops;
 		sdata->dev->ml_priv = &mac802154_mlme_wpan;
 		wpan_dev->promiscuous_mode = false;
@@ -608,7 +607,7 @@ ieee802154_setup_sdata(struct ieee802154_sub_if_data *sdata,
 
 		break;
 	case NL802154_IFTYPE_MONITOR:
-		sdata->dev->destructor = free_netdev;
+		sdata->dev->needs_free_netdev = true;
 		sdata->dev->netdev_ops = &mac802154_monitor_ops;
 		wpan_dev->promiscuous_mode = true;
 		break;
diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c
index 89193a6..04a3128 100644
--- a/net/openvswitch/vport-internal_dev.c
+++ b/net/openvswitch/vport-internal_dev.c
@@ -94,7 +94,6 @@ static void internal_dev_destructor(struct net_device *dev)
 	struct vport *vport = ovs_internal_dev_get_vport(dev);
 
 	ovs_vport_free(vport);
-	free_netdev(dev);
 }
 
 static void
@@ -156,7 +155,8 @@ static void do_setup(struct net_device *netdev)
 	netdev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_OPENVSWITCH |
 			      IFF_PHONY_HEADROOM | IFF_NO_QUEUE;
-	netdev->destructor = internal_dev_destructor;
+	netdev->needs_free_netdev = true;
+	netdev->priv_destructor = internal_dev_destructor;
 	netdev->ethtool_ops = &internal_dev_ethtool_ops;
 	netdev->rtnl_link_ops = &internal_dev_link_ops;
 
diff --git a/net/phonet/pep-gprs.c b/net/phonet/pep-gprs.c
index 21c28b5..2c93379 100644
--- a/net/phonet/pep-gprs.c
+++ b/net/phonet/pep-gprs.c
@@ -236,7 +236,7 @@ static void gprs_setup(struct net_device *dev)
 	dev->tx_queue_len	= 10;
 
 	dev->netdev_ops		= &gprs_netdev_ops;
-	dev->destructor		= free_netdev;
+	dev->needs_free_netdev	= true;
 }
 
 /*
-- 
2.4.11


From a46503609dc39c7c5ae57662fd3f86ffd655e063 Mon Sep 17 00:00:00 2001
From: Stephen Rothwell <sfr@canb.auug.org.au>
Date: Thu, 8 Jun 2017 19:06:29 +1000
Subject: [PATCH 03/32] net: s390: fix up for "Fix inconsistent teardown and
 release of private netdev state"

[ Upstream commit cd1997f6c11483da819a7719aa013093b8003743 ]

Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/netiucv.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/s390/net/netiucv.c b/drivers/s390/net/netiucv.c
index 3f85b97..6d3494b 100644
--- a/drivers/s390/net/netiucv.c
+++ b/drivers/s390/net/netiucv.c
@@ -1954,7 +1954,6 @@ static void netiucv_free_netdevice(struct net_device *dev)
 		privptr->conn = NULL; privptr->fsm = NULL;
 		/* privptr gets freed by free_netdev() */
 	}
-	free_netdev(dev);
 }
 
 /**
@@ -1972,7 +1971,8 @@ static void netiucv_setup_netdevice(struct net_device *dev)
 	dev->mtu	         = NETIUCV_MTU_DEFAULT;
 	dev->min_mtu		 = 576;
 	dev->max_mtu		 = NETIUCV_MTU_MAX;
-	dev->destructor          = netiucv_free_netdevice;
+	dev->needs_free_netdev   = true;
+	dev->priv_destructor     = netiucv_free_netdevice;
 	dev->hard_header_len     = NETIUCV_HDRLEN;
 	dev->addr_len            = 0;
 	dev->type                = ARPHRD_SLIP;
-- 
2.4.11


From 307b970fa5d2c90ae048296b1006b04de38b8ca1 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 9 Jun 2017 21:33:09 +0200
Subject: [PATCH 04/32] mac80211: free netdev on dev_alloc_name() error

[ Upstream commit c7a61cba71fd151cc7d9ebe53a090e0e61eeebf3 ]

The change to remove free_netdev() from ieee80211_if_free()
erroneously didn't add the necessary free_netdev() for when
ieee80211_if_free() is called directly in one place, rather
than as the priv_destructor. Add the missing call.

Fixes: cf124db566e6 ("net: Fix inconsistent teardown and release of private netdev state.")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mac80211/iface.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 6d23427..8f783d5 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1810,6 +1810,7 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name,
 		ret = dev_alloc_name(ndev, ndev->name);
 		if (ret < 0) {
 			ieee80211_if_free(ndev);
+			free_netdev(ndev);
 			return ret;
 		}
 
-- 
2.4.11


From 9169c673446a67ab9c41180837d70b650f476361 Mon Sep 17 00:00:00 2001
From: Mateusz Jurczyk <mjurczyk@google.com>
Date: Wed, 7 Jun 2017 16:14:29 +0200
Subject: [PATCH 05/32] decnet: dn_rtmsg: Improve input length sanitization in
 dnrmg_receive_user_skb

[ Upstream commit dd0da17b209ed91f39872766634ca967c170ada1 ]

Verify that the length of the socket buffer is sufficient to cover the
nlmsghdr structure before accessing the nlh->nlmsg_len field for further
input sanitization. If the client only supplies 1-3 bytes of data in
sk_buff, then nlh->nlmsg_len remains partially uninitialized and
contains leftover memory from the corresponding kernel allocation.
Operating on such data may result in indeterminate evaluation of the
nlmsg_len < sizeof(*nlh) expression.

The bug was discovered by a runtime instrumentation designed to detect
use of uninitialized memory in the kernel. The patch prevents this and
other similar tools (e.g. KMSAN) from flagging this behavior in the future.

Signed-off-by: Mateusz Jurczyk <mjurczyk@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/decnet/netfilter/dn_rtmsg.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c
index 85f2fdc..29246bc 100644
--- a/net/decnet/netfilter/dn_rtmsg.c
+++ b/net/decnet/netfilter/dn_rtmsg.c
@@ -102,7 +102,9 @@ static inline void dnrmg_receive_user_skb(struct sk_buff *skb)
 {
 	struct nlmsghdr *nlh = nlmsg_hdr(skb);
 
-	if (nlh->nlmsg_len < sizeof(*nlh) || skb->len < nlh->nlmsg_len)
+	if (skb->len < sizeof(*nlh) ||
+	    nlh->nlmsg_len < sizeof(*nlh) ||
+	    skb->len < nlh->nlmsg_len)
 		return;
 
 	if (!netlink_capable(skb, CAP_NET_ADMIN))
-- 
2.4.11


From 891929f5708ffd25c2a06c5f0b0a5063b9b9a2e6 Mon Sep 17 00:00:00 2001
From: "Mintz, Yuval" <Yuval.Mintz@cavium.com>
Date: Wed, 7 Jun 2017 21:00:33 +0300
Subject: [PATCH 06/32] net: Zero ifla_vf_info in rtnl_fill_vfinfo()

[ Upstream commit 0eed9cf58446b28b233388b7f224cbca268b6986 ]

Some of the structure's fields are not initialized by the
rtnetlink. If driver doesn't set those in ndo_get_vf_config(),
they'd leak memory to user.

Signed-off-by: Yuval Mintz <Yuval.Mintz@cavium.com>
CC: Michal Schmidt <mschmidt@redhat.com>
Reviewed-by: Greg Rose <gvrose8192@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 8d4a185..a2610e1 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1127,6 +1127,8 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb,
 	struct ifla_vf_mac vf_mac;
 	struct ifla_vf_info ivi;
 
+	memset(&ivi, 0, sizeof(ivi));
+
 	/* Not all SR-IOV capable drivers support the
 	 * spoofcheck and "RSS query enable" query.  Preset to
 	 * -1 so the user space tool can detect that the driver
@@ -1135,7 +1137,6 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb,
 	ivi.spoofchk = -1;
 	ivi.rss_query_en = -1;
 	ivi.trusted = -1;
-	memset(ivi.mac, 0, sizeof(ivi.mac));
 	/* The default value for VF link state is "auto"
 	 * IFLA_VF_LINK_STATE_AUTO which equals zero
 	 */
-- 
2.4.11


From cda0bf095047581454dcff1f0e7e0a9d910b1332 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 7 Jun 2017 12:26:23 -0600
Subject: [PATCH 07/32] net: ipv6: Release route when device is unregistering

[ Upstream commit 8397ed36b7c585f8d3e06c431f4137309124f78f ]

Roopa reported attempts to delete a bond device that is referenced in a
multipath route is hanging:

$ ifdown bond2    # ifupdown2 command that deletes virtual devices
unregister_netdevice: waiting for bond2 to become free. Usage count = 2

Steps to reproduce:
    echo 1 > /proc/sys/net/ipv6/conf/all/ignore_routes_with_linkdown
    ip link add dev bond12 type bond
    ip link add dev bond13 type bond
    ip addr add 2001:db8:2::0/64 dev bond12
    ip addr add 2001:db8:3::0/64 dev bond13
    ip route add 2001:db8:33::0/64 nexthop via 2001:db8:2::2 nexthop via 2001:db8:3::2
    ip link del dev bond12
    ip link del dev bond13

The root cause is the recent change to keep routes on a linkdown. Update
the check to detect when the device is unregistering and release the
route for that case.

Fixes: a1a22c12060e4 ("net: ipv6: Keep nexthop of multipath route on admin down")
Reported-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Acked-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 5 +++++
 net/ipv6/route.c          | 1 +
 2 files changed, 6 insertions(+)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 3ccabb4..aa38bb1 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4232,6 +4232,11 @@ static inline const char *netdev_name(const struct net_device *dev)
 	return dev->name;
 }
 
+static inline bool netdev_unregistering(const struct net_device *dev)
+{
+	return dev->reg_state == NETREG_UNREGISTERING;
+}
+
 static inline const char *netdev_reg_state(const struct net_device *dev)
 {
 	switch (dev->reg_state) {
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index d316d00..1072fc1 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2804,6 +2804,7 @@ static int fib6_ifdown(struct rt6_info *rt, void *arg)
 	if ((rt->dst.dev == dev || !dev) &&
 	    rt != adn->net->ipv6.ip6_null_entry &&
 	    (rt->rt6i_nsiblings == 0 ||
+	     (dev && netdev_unregistering(dev)) ||
 	     !rt->rt6i_idev->cnf.ignore_routes_with_linkdown))
 		return -1;
 
-- 
2.4.11


From cbea8c18110ee5db744360bb91b6fca915f4936a Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Thu, 8 Jun 2017 11:31:11 -0600
Subject: [PATCH 08/32] net: vrf: Make add_fib_rules per network namespace flag

[ Upstream commit 097d3c9508dc58286344e4a22b300098cf0c1566 ]

Commit 1aa6c4f6b8cd8 ("net: vrf: Add l3mdev rules on first device create")
adds the l3mdev FIB rule the first time a VRF device is created. However,
it only creates the rule once and only in the namespace the first device
is created - which may not be init_net. Fix by using the net_generic
capability to make the add_fib_rules flag per network namespace.

Fixes: 1aa6c4f6b8cd8 ("net: vrf: Add l3mdev rules on first device create")
Reported-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 36 ++++++++++++++++++++++++++++++++----
 1 file changed, 32 insertions(+), 4 deletions(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index e669372..2e62c4d 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -36,12 +36,14 @@
 #include <net/addrconf.h>
 #include <net/l3mdev.h>
 #include <net/fib_rules.h>
+#include <net/netns/generic.h>
 
 #define DRV_NAME	"vrf"
 #define DRV_VERSION	"1.0"
 
 #define FIB_RULE_PREF  1000       /* default preference for FIB rules */
-static bool add_fib_rules = true;
+
+static unsigned int vrf_net_id;
 
 struct net_vrf {
 	struct rtable __rcu	*rth;
@@ -1252,6 +1254,8 @@ static int vrf_newlink(struct net *src_net, struct net_device *dev,
 		       struct nlattr *tb[], struct nlattr *data[])
 {
 	struct net_vrf *vrf = netdev_priv(dev);
+	bool *add_fib_rules;
+	struct net *net;
 	int err;
 
 	if (!data || !data[IFLA_VRF_TABLE])
@@ -1267,13 +1271,15 @@ static int vrf_newlink(struct net *src_net, struct net_device *dev,
 	if (err)
 		goto out;
 
-	if (add_fib_rules) {
+	net = dev_net(dev);
+	add_fib_rules = net_generic(net, vrf_net_id);
+	if (*add_fib_rules) {
 		err = vrf_add_fib_rules(dev);
 		if (err) {
 			unregister_netdevice(dev);
 			goto out;
 		}
-		add_fib_rules = false;
+		*add_fib_rules = false;
 	}
 
 out:
@@ -1356,16 +1362,38 @@ static struct notifier_block vrf_notifier_block __read_mostly = {
 	.notifier_call = vrf_device_event,
 };
 
+/* Initialize per network namespace state */
+static int __net_init vrf_netns_init(struct net *net)
+{
+	bool *add_fib_rules = net_generic(net, vrf_net_id);
+
+	*add_fib_rules = true;
+
+	return 0;
+}
+
+static struct pernet_operations vrf_net_ops __net_initdata = {
+	.init = vrf_netns_init,
+	.id   = &vrf_net_id,
+	.size = sizeof(bool),
+};
+
 static int __init vrf_init_module(void)
 {
 	int rc;
 
 	register_netdevice_notifier(&vrf_notifier_block);
 
-	rc = rtnl_link_register(&vrf_link_ops);
+	rc = register_pernet_subsys(&vrf_net_ops);
 	if (rc < 0)
 		goto error;
 
+	rc = rtnl_link_register(&vrf_link_ops);
+	if (rc < 0) {
+		unregister_pernet_subsys(&vrf_net_ops);
+		goto error;
+	}
+
 	return 0;
 
 error:
-- 
2.4.11


From 034b41c44ca7904d75c9cdab91a7ba447132041d Mon Sep 17 00:00:00 2001
From: Mateusz Jurczyk <mjurczyk@google.com>
Date: Thu, 8 Jun 2017 11:13:36 +0200
Subject: [PATCH 09/32] af_unix: Add sockaddr length checks before accessing
 sa_family in bind and connect handlers

[ Upstream commit defbcf2decc903a28d8398aa477b6881e711e3ea ]

Verify that the caller-provided sockaddr structure is large enough to
contain the sa_family field, before accessing it in bind() and connect()
handlers of the AF_UNIX socket. Since neither syscall enforces a minimum
size of the corresponding memory region, very short sockaddrs (zero or
one byte long) result in operating on uninitialized memory while
referencing .sa_family.

Signed-off-by: Mateusz Jurczyk <mjurczyk@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 928691c..475e1170 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -999,7 +999,8 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	struct path path = { NULL, NULL };
 
 	err = -EINVAL;
-	if (sunaddr->sun_family != AF_UNIX)
+	if (addr_len < offsetofend(struct sockaddr_un, sun_family) ||
+	    sunaddr->sun_family != AF_UNIX)
 		goto out;
 
 	if (addr_len == sizeof(short)) {
@@ -1110,6 +1111,10 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr,
 	unsigned int hash;
 	int err;
 
+	err = -EINVAL;
+	if (alen < offsetofend(struct sockaddr, sa_family))
+		goto out;
+
 	if (addr->sa_family != AF_UNSPEC) {
 		err = unix_mkname(sunaddr, alen, &hash);
 		if (err < 0)
-- 
2.4.11


From f86422800467a91fd7ff7a7a199a13234e8db1d6 Mon Sep 17 00:00:00 2001
From: Krister Johansen <kjlx@templeofstupid.com>
Date: Thu, 8 Jun 2017 13:12:38 -0700
Subject: [PATCH 10/32] Fix an intermittent pr_emerg warning about lo becoming
 free.

[ Upstream commit f186ce61bb8235d80068c390dc2aad7ca427a4c2 ]

It looks like this:

Message from syslogd@flamingo at Apr 26 00:45:00 ...
 kernel:unregister_netdevice: waiting for lo to become free. Usage count = 4

They seem to coincide with net namespace teardown.

The message is emitted by netdev_wait_allrefs().

Forced a kdump in netdev_run_todo, but found that the refcount on the lo
device was already 0 at the time we got to the panic.

Used bcc to check the blocking in netdev_run_todo.  The only places
where we're off cpu there are in the rcu_barrier() and msleep() calls.
That behavior is expected.  The msleep time coincides with the amount of
time we spend waiting for the refcount to reach zero; the rcu_barrier()
wait times are not excessive.

After looking through the list of callbacks that the netdevice notifiers
invoke in this path, it appears that the dst_dev_event is the most
interesting.  The dst_ifdown path places a hold on the loopback_dev as
part of releasing the dev associated with the original dst cache entry.
Most of our notifier callbacks are straight-forward, but this one a)
looks complex, and b) places a hold on the network interface in
question.

I constructed a new bcc script that watches various events in the
liftime of a dst cache entry.  Note that dst_ifdown will take a hold on
the loopback device until the invalidated dst entry gets freed.

[      __dst_free] on DST: ffff883ccabb7900 IF tap1008300eth0 invoked at 1282115677036183
    __dst_free
    rcu_nocb_kthread
    kthread
    ret_from_fork
Acked-by: Eric Dumazet <edumazet@google.com>

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dst.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/net/core/dst.c b/net/core/dst.c
index 6192f11..13ba4a0 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -469,6 +469,20 @@ static int dst_dev_event(struct notifier_block *this, unsigned long event,
 		spin_lock_bh(&dst_garbage.lock);
 		dst = dst_garbage.list;
 		dst_garbage.list = NULL;
+		/* The code in dst_ifdown places a hold on the loopback device.
+		 * If the gc entry processing is set to expire after a lengthy
+		 * interval, this hold can cause netdev_wait_allrefs() to hang
+		 * out and wait for a long time -- until the the loopback
+		 * interface is released.  If we're really unlucky, it'll emit
+		 * pr_emerg messages to console too.  Reset the interval here,
+		 * so dst cleanups occur in a more timely fashion.
+		 */
+		if (dst_garbage.timer_inc > DST_GC_INC) {
+			dst_garbage.timer_inc = DST_GC_INC;
+			dst_garbage.timer_expires = DST_GC_MIN;
+			mod_delayed_work(system_wq, &dst_gc_work,
+					 dst_garbage.timer_expires);
+		}
 		spin_unlock_bh(&dst_garbage.lock);
 
 		if (last)
-- 
2.4.11


From 1e38023882be191a5339acd17de4b06927d01968 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sat, 10 Jun 2017 14:48:14 +0800
Subject: [PATCH 11/32] sctp: disable BH in sctp_for_each_endpoint

[ Upstream commit 581409dacc9176b0de1f6c4ca8d66e13aa8e1b29 ]

Now sctp holds read_lock when foreach sctp_ep_hashtable without disabling
BH. If CPU schedules to another thread A at this moment, the thread A may
be trying to hold the write_lock with disabling BH.

As BH is disabled and CPU cannot schedule back to the thread holding the
read_lock, while the thread A keeps waiting for the read_lock. A dead
lock would be triggered by this.

This patch is to fix this dead lock by calling read_lock_bh instead to
disable BH when holding the read_lock in sctp_for_each_endpoint.

Fixes: 626d16f50f39 ("sctp: export some apis or variables for sctp_diag and reuse some for proc")
Reported-by: Xiumei Mu <xmu@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index d9d4c92..956a17d 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4586,13 +4586,13 @@ int sctp_for_each_endpoint(int (*cb)(struct sctp_endpoint *, void *),
 
 	for (head = sctp_ep_hashtable; hash < sctp_ep_hashsize;
 	     hash++, head++) {
-		read_lock(&head->lock);
+		read_lock_bh(&head->lock);
 		sctp_for_each_hentry(epb, &head->chain) {
 			err = cb(sctp_ep(epb), p);
 			if (err)
 				break;
 		}
-		read_unlock(&head->lock);
+		read_unlock_bh(&head->lock);
 	}
 
 	return err;
-- 
2.4.11


From a082cf766454af4b90b45fccdc4320516c6c329d Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@163.com>
Date: Sat, 10 Jun 2017 16:49:39 +0800
Subject: [PATCH 12/32] net: caif: Fix a sleep-in-atomic bug in
 cfpkt_create_pfx

[ Upstream commit f146e872eb12ebbe92d8e583b2637e0741440db3 ]

The kernel may sleep under a rcu read lock in cfpkt_create_pfx, and the
function call path is:
cfcnfg_linkup_rsp (acquire the lock by rcu_read_lock)
  cfctrl_linkdown_req
    cfpkt_create
      cfpkt_create_pfx
        alloc_skb(GFP_KERNEL) --> may sleep
cfserl_receive (acquire the lock by rcu_read_lock)
  cfpkt_split
    cfpkt_create_pfx
      alloc_skb(GFP_KERNEL) --> may sleep

There is "in_interrupt" in cfpkt_create_pfx to decide use "GFP_KERNEL" or
"GFP_ATOMIC". In this situation, "GFP_KERNEL" is used because the function
is called under a rcu read lock, instead in interrupt.

To fix it, only "GFP_ATOMIC" is used in cfpkt_create_pfx.

Signed-off-by: Jia-Ju Bai <baijiaju1990@163.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/caif/cfpkt_skbuff.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/net/caif/cfpkt_skbuff.c b/net/caif/cfpkt_skbuff.c
index 59ce1fc..71b6ab2 100644
--- a/net/caif/cfpkt_skbuff.c
+++ b/net/caif/cfpkt_skbuff.c
@@ -81,11 +81,7 @@ static struct cfpkt *cfpkt_create_pfx(u16 len, u16 pfx)
 {
 	struct sk_buff *skb;
 
-	if (likely(in_interrupt()))
-		skb = alloc_skb(len + pfx, GFP_ATOMIC);
-	else
-		skb = alloc_skb(len + pfx, GFP_KERNEL);
-
+	skb = alloc_skb(len + pfx, GFP_ATOMIC);
 	if (unlikely(skb == NULL))
 		return NULL;
 
-- 
2.4.11


From 37d7ff14627f981e63d4c1124e3f6c313149b5b1 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@163.com>
Date: Sat, 10 Jun 2017 17:03:35 +0800
Subject: [PATCH 13/32] net: tipc: Fix a sleep-in-atomic bug in
 tipc_msg_reverse

[ Upstream commit 343eba69c6968190d8654b857aea952fed9a6749 ]

The kernel may sleep under a rcu read lock in tipc_msg_reverse, and the
function call path is:
tipc_l2_rcv_msg (acquire the lock by rcu_read_lock)
  tipc_rcv
    tipc_sk_rcv
      tipc_msg_reverse
        pskb_expand_head(GFP_KERNEL) --> may sleep
tipc_node_broadcast
  tipc_node_xmit_skb
    tipc_node_xmit
      tipc_sk_rcv
        tipc_msg_reverse
          pskb_expand_head(GFP_KERNEL) --> may sleep

To fix it, "GFP_KERNEL" is replaced with "GFP_ATOMIC".

Signed-off-by: Jia-Ju Bai <baijiaju1990@163.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/msg.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index 312ef7d..ab30876 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -508,7 +508,7 @@ bool tipc_msg_reverse(u32 own_node,  struct sk_buff **skb, int err)
 	}
 
 	if (skb_cloned(_skb) &&
-	    pskb_expand_head(_skb, BUF_HEADROOM, BUF_TAILROOM, GFP_KERNEL))
+	    pskb_expand_head(_skb, BUF_HEADROOM, BUF_TAILROOM, GFP_ATOMIC))
 		goto exit;
 
 	/* Now reverse the concerned fields */
-- 
2.4.11


From 0bd04268b07a027e889686f13fff24b145536d56 Mon Sep 17 00:00:00 2001
From: Huy Nguyen <huyn@mellanox.com>
Date: Mon, 8 May 2017 11:46:50 -0500
Subject: [PATCH 14/32] net/mlx5: Remove several module events out of ethtool
 stats

[ Upstream commit f729860a177d097ac44321fb2f7d927a0c54c5a3 ]

Remove the following module event counters out of ethtool stats. The
reason for removing these event counters is that these events do not
occur without techinician's intervention.
  module_pwr_budget_exd
  module_long_range
  module_no_eeprom
  module_enforce_part
  module_unknown_id
  module_unknown_status
  module_plug

Fixes: bedb7c909c19 ("net/mlx5e: Add port module event counters to ethtool stats")
Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Reviewed by: Gal Pressman <galp@mellanox.com>

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.h | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 53e4992..f81c3aa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -417,20 +417,13 @@ struct mlx5e_stats {
 };
 
 static const struct counter_desc mlx5e_pme_status_desc[] = {
-	{ "module_plug", 0 },
 	{ "module_unplug", 8 },
 };
 
 static const struct counter_desc mlx5e_pme_error_desc[] = {
-	{ "module_pwr_budget_exd", 0 },  /* power budget exceed */
-	{ "module_long_range", 8 },      /* long range for non MLNX cable */
-	{ "module_bus_stuck", 16 },      /* bus stuck (I2C or data shorted) */
-	{ "module_no_eeprom", 24 },      /* no eeprom/retry time out */
-	{ "module_enforce_part", 32 },   /* enforce part number list */
-	{ "module_unknown_id", 40 },     /* unknown identifier */
-	{ "module_high_temp", 48 },      /* high temperature */
+	{ "module_bus_stuck", 16 },       /* bus stuck (I2C or data shorted) */
+	{ "module_high_temp", 48 },       /* high temperature */
 	{ "module_bad_shorted", 56 },    /* bad or shorted cable/module */
-	{ "module_unknown_status", 64 },
 };
 
 #endif /* __MLX5_EN_STATS_H__ */
-- 
2.4.11


From 2b2dd30bcef712cdbe96a78681ef6fe896cd7f5c Mon Sep 17 00:00:00 2001
From: Tal Gilboa <talgi@mellanox.com>
Date: Mon, 15 May 2017 14:13:16 +0300
Subject: [PATCH 15/32] net/mlx5e: Added BW check for DIM decision mechanism

[ Upstream commit c3164d2fc48fd4fa0477ab658b644559c3fe9073 ]

DIM (Dynamically-tuned Interrupt Moderation) is a mechanism designed for
changing the channel interrupt moderation values in order to reduce CPU
overhead for all traffic types.
Until now only interrupt and packet rate were sampled.
We found a scenario on which we get a false indication since a change in
DIM caused more aggregation and reduced packet rate while increasing BW.

We now regard a change as succesfull iff:
current_BW > (prev_BW + threshold) or
current_BW ~= prev_BW and current_PR > (prev_PR + threshold) or
current_BW ~= prev_BW and current_PR ~= prev_PR and
    current_IR < (prev_IR - threshold)
Where BW = Bandwidth, PR = Packet rate and IR = Interrupt rate

Improvements (ConnectX-4Lx 25GbE, single RX queue, LRO off)
    --------------------------------------------------
    packet size | before[Mb/s] | after[Mb/s] | gain  |
    2B          | 343.4        | 359.4       |  4.5% |
    16B         | 2739.7       | 2814.8      |  2.7% |
    64B         | 9739         | 10185.3     |  4.5% |

Fixes: cb3c7fd4f839 ("net/mlx5e: Support adaptive RX coalescing")
Signed-off-by: Tal Gilboa <talgi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |  2 ++
 drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c | 37 ++++++++++++----------
 2 files changed, 22 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 3d9490c..fad0594 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -313,12 +313,14 @@ struct mlx5e_dma_info {
 
 struct mlx5e_rx_am_stats {
 	int ppms; /* packets per msec */
+	int bpms; /* bytes per msec */
 	int epms; /* events per msec */
 };
 
 struct mlx5e_rx_am_sample {
 	ktime_t		time;
 	unsigned int	pkt_ctr;
+	unsigned int    byte_ctr;
 	u16		event_ctr;
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c
index cbfac06..1750388 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c
@@ -183,28 +183,27 @@ static void mlx5e_am_exit_parking(struct mlx5e_rx_am *am)
 	mlx5e_am_step(am);
 }
 
+#define IS_SIGNIFICANT_DIFF(val, ref) \
+	(((100 * abs((val) - (ref))) / (ref)) > 10) /* more than 10% difference */
+
 static int mlx5e_am_stats_compare(struct mlx5e_rx_am_stats *curr,
 				  struct mlx5e_rx_am_stats *prev)
 {
-	int diff;
-
-	if (!prev->ppms)
-		return curr->ppms ? MLX5E_AM_STATS_BETTER :
+	if (!prev->bpms)
+		return curr->bpms ? MLX5E_AM_STATS_BETTER :
 				    MLX5E_AM_STATS_SAME;
 
-	diff = curr->ppms - prev->ppms;
-	if (((100 * abs(diff)) / prev->ppms) > 10) /* more than 10% diff */
-		return (diff > 0) ? MLX5E_AM_STATS_BETTER :
-				    MLX5E_AM_STATS_WORSE;
+	if (IS_SIGNIFICANT_DIFF(curr->bpms, prev->bpms))
+		return (curr->bpms > prev->bpms) ? MLX5E_AM_STATS_BETTER :
+						   MLX5E_AM_STATS_WORSE;
 
-	if (!prev->epms)
-		return curr->epms ? MLX5E_AM_STATS_WORSE :
-				    MLX5E_AM_STATS_SAME;
+	if (IS_SIGNIFICANT_DIFF(curr->ppms, prev->ppms))
+		return (curr->ppms > prev->ppms) ? MLX5E_AM_STATS_BETTER :
+						   MLX5E_AM_STATS_WORSE;
 
-	diff = curr->epms - prev->epms;
-	if (((100 * abs(diff)) / prev->epms) > 10) /* more than 10% diff */
-		return (diff < 0) ? MLX5E_AM_STATS_BETTER :
-				    MLX5E_AM_STATS_WORSE;
+	if (IS_SIGNIFICANT_DIFF(curr->epms, prev->epms))
+		return (curr->epms < prev->epms) ? MLX5E_AM_STATS_BETTER :
+						   MLX5E_AM_STATS_WORSE;
 
 	return MLX5E_AM_STATS_SAME;
 }
@@ -266,6 +265,7 @@ static void mlx5e_am_sample(struct mlx5e_rq *rq,
 {
 	s->time	     = ktime_get();
 	s->pkt_ctr   = rq->stats.packets;
+	s->byte_ctr  = rq->stats.bytes;
 	s->event_ctr = rq->cq.event_ctr;
 }
 
@@ -278,12 +278,15 @@ static void mlx5e_am_calc_stats(struct mlx5e_rx_am_sample *start,
 	/* u32 holds up to 71 minutes, should be enough */
 	u32 delta_us = ktime_us_delta(end->time, start->time);
 	unsigned int npkts = end->pkt_ctr - start->pkt_ctr;
+	unsigned int nbytes = end->byte_ctr - start->byte_ctr;
 
 	if (!delta_us)
 		return;
 
-	curr_stats->ppms =            (npkts * USEC_PER_MSEC) / delta_us;
-	curr_stats->epms = (MLX5E_AM_NEVENTS * USEC_PER_MSEC) / delta_us;
+	curr_stats->ppms = DIV_ROUND_UP(npkts * USEC_PER_MSEC, delta_us);
+	curr_stats->bpms = DIV_ROUND_UP(nbytes * USEC_PER_MSEC, delta_us);
+	curr_stats->epms = DIV_ROUND_UP(MLX5E_AM_NEVENTS * USEC_PER_MSEC,
+					delta_us);
 }
 
 void mlx5e_rx_am_work(struct work_struct *work)
-- 
2.4.11


From 9f091ebae821ace30da46600b1eed1dc9d91659a Mon Sep 17 00:00:00 2001
From: Tal Gilboa <talgi@mellanox.com>
Date: Mon, 29 May 2017 17:02:55 +0300
Subject: [PATCH 16/32] net/mlx5e: Fix wrong indications in DIM due to counter
 wraparound

[ Upstream commit 53acd76ce571e3b71f9205f2d49ab285a9f1aad8 ]

DIM (Dynamically-tuned Interrupt Moderation) is a mechanism designed for
changing the channel interrupt moderation values in order to reduce CPU
overhead for all traffic types.
Each iteration of the algorithm, DIM calculates the difference in
throughput, packet rate and interrupt rate from last iteration in order
to make a decision. DIM relies on counters for each metric. When these
counters get to their type's max value they wraparound. In this case
the delta between 'end' and 'start' samples is negative and when
translated to unsigned integers - very high. This results in a false
indication to the algorithm and might result in a wrong decision.

The fix calculates the 'distance' between 'end' and 'start' samples in a
cyclic way around the relevant type's max value. It can also be viewed as
an absolute value around the type's max value instead of around 0.

Testing show higher stability in DIM profile selection and no wraparound
issues.

Fixes: cb3c7fd4f839 ("net/mlx5e: Support adaptive RX coalescing")
Signed-off-by: Tal Gilboa <talgi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |  8 ++++----
 drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c | 10 +++++++---
 2 files changed, 11 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index fad0594..8f7108c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -318,10 +318,10 @@ struct mlx5e_rx_am_stats {
 };
 
 struct mlx5e_rx_am_sample {
-	ktime_t		time;
-	unsigned int	pkt_ctr;
-	unsigned int    byte_ctr;
-	u16		event_ctr;
+	ktime_t	time;
+	u32	pkt_ctr;
+	u32	byte_ctr;
+	u16	event_ctr;
 };
 
 struct mlx5e_rx_am { /* Adaptive Moderation */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c
index 1750388..23ccec4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c
@@ -270,6 +270,8 @@ static void mlx5e_am_sample(struct mlx5e_rq *rq,
 }
 
 #define MLX5E_AM_NEVENTS 64
+#define BITS_PER_TYPE(type) (sizeof(type) * BITS_PER_BYTE)
+#define BIT_GAP(bits, end, start) ((((end) - (start)) + BIT_ULL(bits)) & (BIT_ULL(bits) - 1))
 
 static void mlx5e_am_calc_stats(struct mlx5e_rx_am_sample *start,
 				struct mlx5e_rx_am_sample *end,
@@ -277,8 +279,9 @@ static void mlx5e_am_calc_stats(struct mlx5e_rx_am_sample *start,
 {
 	/* u32 holds up to 71 minutes, should be enough */
 	u32 delta_us = ktime_us_delta(end->time, start->time);
-	unsigned int npkts = end->pkt_ctr - start->pkt_ctr;
-	unsigned int nbytes = end->byte_ctr - start->byte_ctr;
+	u32 npkts = BIT_GAP(BITS_PER_TYPE(u32), end->pkt_ctr, start->pkt_ctr);
+	u32 nbytes = BIT_GAP(BITS_PER_TYPE(u32), end->byte_ctr,
+			     start->byte_ctr);
 
 	if (!delta_us)
 		return;
@@ -311,7 +314,8 @@ void mlx5e_rx_am(struct mlx5e_rq *rq)
 
 	switch (am->state) {
 	case MLX5E_AM_MEASURE_IN_PROGRESS:
-		nevents = rq->cq.event_ctr - am->start_sample.event_ctr;
+		nevents = BIT_GAP(BITS_PER_TYPE(u16), rq->cq.event_ctr,
+				  am->start_sample.event_ctr);
 		if (nevents < MLX5E_AM_NEVENTS)
 			break;
 		mlx5e_am_sample(rq, &end_sample);
-- 
2.4.11


From 9b7558d4059f6dbb22ea316e0dad89a4b0bc2062 Mon Sep 17 00:00:00 2001
From: Majd Dibbiny <majd@mellanox.com>
Date: Sun, 28 May 2017 14:47:56 +0300
Subject: [PATCH 17/32] net/mlx5: Enable 4K UAR only when page size is bigger
 than 4K

[ Upstream commit 91828bd89940e8145f91751a015bc11bc486aad0 ]

When the page size isn't bigger than 4K, there is no added value of enabling 4K
UAR feature in the Firmware.

Modified the condition of enabling the 4K UAR accordingly.

Fixes: f502d834950a ("net/mlx5: Activate support for 4K UARs")
Signed-off-by: Majd Dibbiny <majd@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 0ad6632..4d7e4e6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -537,8 +537,10 @@ static int handle_hca_cap(struct mlx5_core_dev *dev)
 	/* disable cmdif checksum */
 	MLX5_SET(cmd_hca_cap, set_hca_cap, cmdif_checksum, 0);
 
-	/* If the HCA supports 4K UARs use it */
-	if (MLX5_CAP_GEN_MAX(dev, uar_4k))
+	/* Enable 4K UAR only when HCA supports it and page size is bigger
+	 * than 4K.
+	 */
+	if (MLX5_CAP_GEN_MAX(dev, uar_4k) && PAGE_SIZE > 4096)
 		MLX5_SET(cmd_hca_cap, set_hca_cap, uar_4k, 1);
 
 	MLX5_SET(cmd_hca_cap, set_hca_cap, log_uar_page_sz, PAGE_SHIFT - 12);
-- 
2.4.11


From 598a972c17e2b11e0a66123833778e1e661e2a1e Mon Sep 17 00:00:00 2001
From: Christian Perle <christian.perle@secunet.com>
Date: Mon, 12 Jun 2017 10:06:57 +0200
Subject: [PATCH 18/32] proc: snmp6: Use correct type in memset

[ Upstream commit 3500cd73dff48f28f4ba80c171c4c80034d40f76 ]

Reading /proc/net/snmp6 yields bogus values on 32 bit kernels.
Use "u64" instead of "unsigned long" in sizeof().

Fixes: 4a4857b1c81e ("proc: Reduce cache miss in snmp6_seq_show")
Signed-off-by: Christian Perle <christian.perle@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/proc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index cc8e3ae..e88bcb8 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -219,7 +219,7 @@ static void snmp6_seq_show_item64(struct seq_file *seq, void __percpu *mib,
 	u64 buff64[SNMP_MIB_MAX];
 	int i;
 
-	memset(buff64, 0, sizeof(unsigned long) * SNMP_MIB_MAX);
+	memset(buff64, 0, sizeof(u64) * SNMP_MIB_MAX);
 
 	snmp_get_cpu_field64_batch(buff64, itemlist, mib, syncpoff);
 	for (i = 0; itemlist[i].name; i++)
-- 
2.4.11


From 9c77a5e374424c5407751c0165315c6a02ea0794 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Mon, 12 Jun 2017 09:52:26 -0700
Subject: [PATCH 19/32] igmp: acquire pmc lock for ip_mc_clear_src()

[ Upstream commit c38b7d327aafd1e3ad7ff53eefac990673b65667 ]

Andrey reported a use-after-free in add_grec():

        for (psf = *psf_list; psf; psf = psf_next) {
		...
                psf_next = psf->sf_next;

where the struct ip_sf_list's were already freed by:

 kfree+0xe8/0x2b0 mm/slub.c:3882
 ip_mc_clear_src+0x69/0x1c0 net/ipv4/igmp.c:2078
 ip_mc_dec_group+0x19a/0x470 net/ipv4/igmp.c:1618
 ip_mc_drop_socket+0x145/0x230 net/ipv4/igmp.c:2609
 inet_release+0x4e/0x1c0 net/ipv4/af_inet.c:411
 sock_release+0x8d/0x1e0 net/socket.c:597
 sock_close+0x16/0x20 net/socket.c:1072

This happens because we don't hold pmc->lock in ip_mc_clear_src()
and a parallel mr_ifc_timer timer could jump in and access them.

The RCU lock is there but it is merely for pmc itself, this
spinlock could actually ensure we don't access them in parallel.

Thanks to Eric and Long for discussion on this bug.

Reported-by: Andrey Konovalov <andreyknvl@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Xin Long <lucien.xin@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/igmp.c | 21 +++++++++++++--------
 1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 44fd86d..8f6b5bb 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -2071,21 +2071,26 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode,
 
 static void ip_mc_clear_src(struct ip_mc_list *pmc)
 {
-	struct ip_sf_list *psf, *nextpsf;
+	struct ip_sf_list *psf, *nextpsf, *tomb, *sources;
 
-	for (psf = pmc->tomb; psf; psf = nextpsf) {
+	spin_lock_bh(&pmc->lock);
+	tomb = pmc->tomb;
+	pmc->tomb = NULL;
+	sources = pmc->sources;
+	pmc->sources = NULL;
+	pmc->sfmode = MCAST_EXCLUDE;
+	pmc->sfcount[MCAST_INCLUDE] = 0;
+	pmc->sfcount[MCAST_EXCLUDE] = 1;
+	spin_unlock_bh(&pmc->lock);
+
+	for (psf = tomb; psf; psf = nextpsf) {
 		nextpsf = psf->sf_next;
 		kfree(psf);
 	}
-	pmc->tomb = NULL;
-	for (psf = pmc->sources; psf; psf = nextpsf) {
+	for (psf = sources; psf; psf = nextpsf) {
 		nextpsf = psf->sf_next;
 		kfree(psf);
 	}
-	pmc->sources = NULL;
-	pmc->sfmode = MCAST_EXCLUDE;
-	pmc->sfcount[MCAST_INCLUDE] = 0;
-	pmc->sfcount[MCAST_EXCLUDE] = 1;
 }
 
 /* Join a multicast group
-- 
2.4.11


From 119bd07eedcde276ab97a4941bec99a4e3f37cc8 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Tue, 20 Jun 2017 10:46:27 -0700
Subject: [PATCH 20/32] igmp: add a missing spin_lock_init()

[ Upstream commit b4846fc3c8559649277e3e4e6b5cec5348a8d208 ]

Andrey reported a lockdep warning on non-initialized
spinlock:

 INFO: trying to register non-static key.
 the code is fine but needs lockdep annotation.
 turning off the locking correctness validator.
 CPU: 1 PID: 4099 Comm: a.out Not tainted 4.12.0-rc6+ #9
 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
 Call Trace:
  __dump_stack lib/dump_stack.c:16
  dump_stack+0x292/0x395 lib/dump_stack.c:52
  register_lock_class+0x717/0x1aa0 kernel/locking/lockdep.c:755
  ? 0xffffffffa0000000
  __lock_acquire+0x269/0x3690 kernel/locking/lockdep.c:3255
  lock_acquire+0x22d/0x560 kernel/locking/lockdep.c:3855
  __raw_spin_lock_bh ./include/linux/spinlock_api_smp.h:135
  _raw_spin_lock_bh+0x36/0x50 kernel/locking/spinlock.c:175
  spin_lock_bh ./include/linux/spinlock.h:304
  ip_mc_clear_src+0x27/0x1e0 net/ipv4/igmp.c:2076
  igmpv3_clear_delrec+0xee/0x4f0 net/ipv4/igmp.c:1194
  ip_mc_destroy_dev+0x4e/0x190 net/ipv4/igmp.c:1736

We miss a spin_lock_init() in igmpv3_add_delrec(), probably
because previously we never use it on this code path. Since
we already unlink it from the global mc_tomb list, it is
probably safe not to acquire this spinlock here. It does not
harm to have it although, to avoid conditional locking.

Fixes: c38b7d327aaf ("igmp: acquire pmc lock for ip_mc_clear_src()")
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/igmp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 8f6b5bb..ec9a396 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -1112,6 +1112,7 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im)
 	pmc = kzalloc(sizeof(*pmc), GFP_KERNEL);
 	if (!pmc)
 		return;
+	spin_lock_init(&pmc->lock);
 	spin_lock_bh(&im->lock);
 	pmc->interface = im->interface;
 	in_dev_hold(in_dev);
-- 
2.4.11


From 195efa787760f72446ae833f458a81455371f3e8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Tue, 13 Jun 2017 19:10:18 +0200
Subject: [PATCH 21/32] qmi_wwan: new Telewell and Sierra device IDs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 60cfe1eaccb8af598ebe1bdc44e157ea30fcdd81 ]

A new Sierra Wireless EM7305 device ID used in a Toshiba laptop,
and two Longcheer device IDs entries used by Telewell TW-3G HSPA+
branded modems.

Reported-by: Petr Kloc <petr_kloc@yahoo.com>
Reported-by: Teemu Likonen <tlikonen@iki.fi>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 87746c2..d4c8c96 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -898,6 +898,8 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1199, 0x9056, 8)},	/* Sierra Wireless Modem */
 	{QMI_FIXED_INTF(0x1199, 0x9057, 8)},
 	{QMI_FIXED_INTF(0x1199, 0x9061, 8)},	/* Sierra Wireless Modem */
+	{QMI_FIXED_INTF(0x1199, 0x9063, 8)},	/* Sierra Wireless EM7305 */
+	{QMI_FIXED_INTF(0x1199, 0x9063, 10)},	/* Sierra Wireless EM7305 */
 	{QMI_FIXED_INTF(0x1199, 0x9071, 8)},	/* Sierra Wireless MC74xx */
 	{QMI_FIXED_INTF(0x1199, 0x9071, 10)},	/* Sierra Wireless MC74xx */
 	{QMI_FIXED_INTF(0x1199, 0x9079, 8)},	/* Sierra Wireless EM74xx */
@@ -912,6 +914,8 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1bc7, 0x1100, 3)},	/* Telit ME910 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)},	/* Telit LE920 */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1201, 2)},	/* Telit LE920, LE920A4 */
+	{QMI_FIXED_INTF(0x1c9e, 0x9801, 3)},	/* Telewell TW-3G HSPA+ */
+	{QMI_FIXED_INTF(0x1c9e, 0x9803, 4)},	/* Telewell TW-3G HSPA+ */
 	{QMI_FIXED_INTF(0x1c9e, 0x9b01, 3)},	/* XS Stick W100-2 from 4G Systems */
 	{QMI_FIXED_INTF(0x0b3c, 0xc000, 4)},	/* Olivetti Olicard 100 */
 	{QMI_FIXED_INTF(0x0b3c, 0xc001, 4)},	/* Olivetti Olicard 120 */
-- 
2.4.11


From 99951db5e844446cc745b25c66f8ac6a57873c87 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Wed, 14 Jun 2017 13:27:37 +0200
Subject: [PATCH 22/32] net: don't global ICMP rate limit packets originating
 from loopback

[ Upstream commit 849a44de91636c24cea799cb8ad8c36433feb913 ]

Florian Weimer seems to have a glibc test-case which requires that
loopback interfaces does not get ICMP ratelimited.  This was broken by
commit c0303efeab73 ("net: reduce cycles spend on ICMP replies that
gets rate limited").

An ICMP response will usually be routed back-out the same incoming
interface.  Thus, take advantage of this and skip global ICMP
ratelimit when the incoming device is loopback.  In the unlikely event
that the outgoing it not loopback, due to strange routing policy
rules, ICMP rate limiting still works via peer ratelimiting via
icmpv4_xrlim_allow().  Thus, we should still comply with RFC1812
(section 4.3.2.8 "Rate Limiting").

This seems to fix the reproducer given by Florian.  While still
avoiding to perform expensive and unneeded outgoing route lookup for
rate limited packets (in the non-loopback case).

Fixes: c0303efeab73 ("net: reduce cycles spend on ICMP replies that gets rate limited")
Reported-by: Florian Weimer <fweimer@redhat.com>
Reported-by: "H.J. Lu" <hjl.tools@gmail.com>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/icmp.c | 8 ++++++--
 net/ipv6/icmp.c | 2 +-
 2 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index fc310db..760311f 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -674,8 +674,12 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 	/* Needed by both icmp_global_allow and icmp_xmit_lock */
 	local_bh_disable();
 
-	/* Check global sysctl_icmp_msgs_per_sec ratelimit */
-	if (!icmpv4_global_allow(net, type, code))
+	/* Check global sysctl_icmp_msgs_per_sec ratelimit, unless
+	 * incoming dev is loopback.  If outgoing dev change to not be
+	 * loopback, then peer ratelimit still work (in icmpv4_xrlim_allow)
+	 */
+	if (!(skb_in->dev && (skb_in->dev->flags&IFF_LOOPBACK)) &&
+	      !icmpv4_global_allow(net, type, code))
 		goto out_bh_enable;
 
 	sk = icmp_xmit_lock(net);
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 230b5aa..8d7b113 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -491,7 +491,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 	local_bh_disable();
 
 	/* Check global sysctl_icmp_msgs_per_sec ratelimit */
-	if (!icmpv6_global_allow(type))
+	if (!(skb->dev->flags&IFF_LOOPBACK) && !icmpv6_global_allow(type))
 		goto out_bh_enable;
 
 	mip6_addr_swap(skb);
-- 
2.4.11


From 7bc6b117cc55aed389eb1a892a23a5a59d42f482 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 15 Jun 2017 16:33:58 +0800
Subject: [PATCH 23/32] ipv6: fix calling in6_ifa_hold incorrectly for dad work

[ Upstream commit f8a894b218138888542a5058d0e902378fd0d4ec ]

Now when starting the dad work in addrconf_mod_dad_work, if the dad work
is idle and queued, it needs to hold ifa.

The problem is there's one gap in [1], during which if the pending dad work
is removed elsewhere. It will miss to hold ifa, but the dad word is still
idea and queue.

        if (!delayed_work_pending(&ifp->dad_work))
                in6_ifa_hold(ifp);
                    <--------------[1]
        mod_delayed_work(addrconf_wq, &ifp->dad_work, delay);

An use-after-free issue can be caused by this.

Chen Wei found this issue when WARN_ON(!hlist_unhashed(&ifp->addr_lst)) in
net6_ifa_finish_destroy was hit because of it.

As Hannes' suggestion, this patch is to fix it by holding ifa first in
addrconf_mod_dad_work, then calling mod_delayed_work and putting ifa if
the dad_work is already in queue.

Note that this patch did not choose to fix it with:

  if (!mod_delayed_work(delay))
          in6_ifa_hold(ifp);

As with it, when delay == 0, dad_work would be scheduled immediately, all
addrconf_mod_dad_work(0) callings had to be moved under ifp->lock.

Reported-by: Wei Chen <weichen@redhat.com>
Suggested-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 311f456..9725e8f 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -328,9 +328,9 @@ static void addrconf_mod_rs_timer(struct inet6_dev *idev,
 static void addrconf_mod_dad_work(struct inet6_ifaddr *ifp,
 				   unsigned long delay)
 {
-	if (!delayed_work_pending(&ifp->dad_work))
-		in6_ifa_hold(ifp);
-	mod_delayed_work(addrconf_wq, &ifp->dad_work, delay);
+	in6_ifa_hold(ifp);
+	if (mod_delayed_work(addrconf_wq, &ifp->dad_work, delay))
+		in6_ifa_put(ifp);
 }
 
 static int snmp6_alloc_dev(struct inet6_dev *idev)
-- 
2.4.11


From 434852b59ae1a2e689803f2afd7729e010853e98 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 15 Jun 2017 17:49:08 +0800
Subject: [PATCH 24/32] sctp: return next obj by passing pos + 1 into
 sctp_transport_get_idx

[ Upstream commit 988c7322116970696211e902b468aefec95b6ec4 ]

In sctp_for_each_transport, pos is used to save how many objs it has
dumped. Now it gets the last obj by sctp_transport_get_idx, then gets
the next obj by sctp_transport_get_next.

The issue is that in the meanwhile if some objs in transport hashtable
are removed and the objs nums are less than pos, sctp_transport_get_idx
would return NULL and hti.walker.tbl is NULL as well. At this moment
it should stop hti, instead of continue getting the next obj. Or it
would cause a NULL pointer dereference in sctp_transport_get_next.

This patch is to pass pos + 1 into sctp_transport_get_idx to get the
next obj directly, even if pos > objs nums, it would return NULL and
stop hti.

Fixes: 626d16f50f39 ("sctp: export some apis or variables for sctp_diag and reuse some for proc")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 956a17d..74f7610 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4630,9 +4630,8 @@ int sctp_for_each_transport(int (*cb)(struct sctp_transport *, void *),
 	if (err)
 		return err;
 
-	sctp_transport_get_idx(net, &hti, pos);
-	obj = sctp_transport_get_next(net, &hti);
-	for (; obj && !IS_ERR(obj); obj = sctp_transport_get_next(net, &hti)) {
+	obj = sctp_transport_get_idx(net, &hti, pos + 1);
+	for (; !IS_ERR_OR_NULL(obj); obj = sctp_transport_get_next(net, &hti)) {
 		struct sctp_transport *transport = obj;
 
 		if (!sctp_transport_hold(transport))
-- 
2.4.11


From 07c9854a66da3989ec8a79df12536063827b9d39 Mon Sep 17 00:00:00 2001
From: Chris Mi <chrism@mellanox.com>
Date: Tue, 16 May 2017 07:07:11 -0400
Subject: [PATCH 25/32] net/mlx5e: Fix min inline value for VF rep SQs

[ Upstream commit 5f195c2c5cba60241004146cd12d71451d6b0fc4 ]

The offending commit only changed the code path for PF/VF, but it
didn't take care of VF representors. As a result, since
params->tx_min_inline_mode for VF representors is kzalloced to 0
(MLX5_INLINE_MODE_NONE), all VF reps SQs were set to that mode.

This actually works on CX5 by default but broke CX4. Fix that by
adding a call to query the min inline mode from the VF rep build up code.

Fixes: a6f402e49901 ("net/mlx5e: Tx, no inline copy on ConnectX-5")
Signed-off-by: Chris Mi <chrism@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index f621373..4be6b34 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -424,6 +424,8 @@ static void mlx5e_build_rep_netdev_priv(struct mlx5_core_dev *mdev,
 	priv->params.lro_wqe_sz            =
 		MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ;
 
+	mlx5_query_min_inline(mdev, &priv->params.tx_min_inline_mode);
+
 	priv->mdev                         = mdev;
 	priv->netdev                       = netdev;
 	priv->params.num_channels          = profile->max_nch(mdev);
-- 
2.4.11


From b8519655acc8ce42c3988da18fd17a9728523aa9 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Thu, 15 Jun 2017 20:08:32 +0300
Subject: [PATCH 26/32] net/mlx5e: Avoid doing a cleanup call if the profile
 doesn't have it

[ Upstream commit 31ac93386d135a6c96de9c8bab406f5ccabf5a4d ]

The error flow of mlx5e_create_netdev calls the cleanup call
of the given profile without checking if it exists, fix that.

Currently the VF reps don't register that callback and we crash
if getting into error -- can be reproduced by the user doing ctrl^C
while attempting to change the sriov mode from legacy to switchdev.

Fixes: 26e59d8077a3 '(net/mlx5e: Implement mlx5e interface attach/detach callbacks')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reported-by: Sabrina Dubroca <sdubroca@redhat.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 15cc7b4..f778436 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3885,7 +3885,8 @@ struct net_device *mlx5e_create_netdev(struct mlx5_core_dev *mdev,
 	return netdev;
 
 err_cleanup_nic:
-	profile->cleanup(priv);
+	if (profile->cleanup)
+		profile->cleanup(priv);
 	free_netdev(netdev);
 
 	return NULL;
-- 
2.4.11


From b9fff21c022f71716f6cd6343c09b1e6ea3575e6 Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.com>
Date: Thu, 8 Jun 2017 11:33:16 -0500
Subject: [PATCH 27/32] net/mlx5: Wait for FW readiness before initializing
 command interface

[ Upstream commit 6c780a0267b8a1075f40b39851132eeaefefcff5 ]

Before attempting to initialize the command interface we must wait till
the fw_initializing bit is clear.

If we fail to meet this condition the hardware will drop our
configuration, specifically the descriptors page address.  This scenario
can happen when the firmware is still executing an FLR flow and did not
finish yet so the driver needs to wait for that to finish.

Fixes: e3297246c2c8 ('net/mlx5_core: Wait for FW readiness on startup')
Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 4d7e4e6..9862a74 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -175,8 +175,9 @@ static struct mlx5_profile profile[] = {
 	},
 };
 
-#define FW_INIT_TIMEOUT_MILI	2000
-#define FW_INIT_WAIT_MS		2
+#define FW_INIT_TIMEOUT_MILI		2000
+#define FW_INIT_WAIT_MS			2
+#define FW_PRE_INIT_TIMEOUT_MILI	10000
 
 static int wait_fw_init(struct mlx5_core_dev *dev, u32 max_wait_mili)
 {
@@ -1021,6 +1022,15 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 	 */
 	dev->state = MLX5_DEVICE_STATE_UP;
 
+	/* wait for firmware to accept initialization segments configurations
+	 */
+	err = wait_fw_init(dev, FW_PRE_INIT_TIMEOUT_MILI);
+	if (err) {
+		dev_err(&dev->pdev->dev, "Firmware over %d MS in pre-initializing state, aborting\n",
+			FW_PRE_INIT_TIMEOUT_MILI);
+		goto out;
+	}
+
 	err = mlx5_cmd_init(dev);
 	if (err) {
 		dev_err(&pdev->dev, "Failed initializing command interface, aborting\n");
-- 
2.4.11


From e6e5fe96f5305a0bd699a0009137590139b7dba3 Mon Sep 17 00:00:00 2001
From: Maor Dickman <maord@mellanox.com>
Date: Thu, 18 May 2017 15:15:08 +0300
Subject: [PATCH 28/32] net/mlx5e: Fix timestamping capabilities reporting

[ Upstream commit f0b381178b01b831f9907d72f467d6443afdea67 ]

Misuse of (BIT) macro caused to report wrong flags for
"Hardware Transmit Timestamp Modes" and "Hardware Receive
Filter Modes"

Fixes: ef9814deafd0 ('net/mlx5e: Add HW timestamping (TS) support')
Signed-off-by: Maor Dickman <maord@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 949fbad..aae8b6c0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1205,11 +1205,11 @@ static int mlx5e_get_ts_info(struct net_device *dev,
 				 SOF_TIMESTAMPING_RX_HARDWARE |
 				 SOF_TIMESTAMPING_RAW_HARDWARE;
 
-	info->tx_types = (BIT(1) << HWTSTAMP_TX_OFF) |
-			 (BIT(1) << HWTSTAMP_TX_ON);
+	info->tx_types = BIT(HWTSTAMP_TX_OFF) |
+			 BIT(HWTSTAMP_TX_ON);
 
-	info->rx_filters = (BIT(1) << HWTSTAMP_FILTER_NONE) |
-			   (BIT(1) << HWTSTAMP_FILTER_ALL);
+	info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) |
+			   BIT(HWTSTAMP_FILTER_ALL);
 
 	return 0;
 }
-- 
2.4.11


From b2b5754525d0f9e533a9e90179ba5485ef957052 Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Fri, 16 Jun 2017 10:46:37 -0700
Subject: [PATCH 29/32] decnet: always not take dst->__refcnt when inserting
 dst into hash table

[ Upstream commit 76371d2e3ad1f84426a30ebcd8c3b9b98f4c724f ]

In the existing dn_route.c code, dn_route_output_slow() takes
dst->__refcnt before calling dn_insert_route() while dn_route_input_slow()
does not take dst->__refcnt before calling dn_insert_route().
This makes the whole routing code very buggy.
In dn_dst_check_expire(), dnrt_free() is called when rt expires. This
makes the routes inserted by dn_route_output_slow() not able to be
freed as the refcnt is not released.
In dn_dst_gc(), dnrt_drop() is called to release rt which could
potentially cause the dst->__refcnt to be dropped to -1.
In dn_run_flush(), dst_free() is called to release all the dst. Again,
it makes the dst inserted by dn_route_output_slow() not able to be
released and also, it does not wait on the rcu and could potentially
cause crash in the path where other users still refer to this dst.

This patch makes sure both input and output path do not take
dst->__refcnt before calling dn_insert_route() and also makes sure
dnrt_free()/dst_free() is called when removing dst from the hash table.
The only difference between those 2 calls is that dnrt_free() waits on
the rcu while dst_free() does not.

Signed-off-by: Wei Wang <weiwan@google.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/decnet/dn_route.c | 14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index b1dc096..403593b 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -188,12 +188,6 @@ static inline void dnrt_free(struct dn_route *rt)
 	call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free);
 }
 
-static inline void dnrt_drop(struct dn_route *rt)
-{
-	dst_release(&rt->dst);
-	call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free);
-}
-
 static void dn_dst_check_expire(unsigned long dummy)
 {
 	int i;
@@ -248,7 +242,7 @@ static int dn_dst_gc(struct dst_ops *ops)
 			}
 			*rtp = rt->dst.dn_next;
 			rt->dst.dn_next = NULL;
-			dnrt_drop(rt);
+			dnrt_free(rt);
 			break;
 		}
 		spin_unlock_bh(&dn_rt_hash_table[i].lock);
@@ -350,7 +344,7 @@ static int dn_insert_route(struct dn_route *rt, unsigned int hash, struct dn_rou
 			dst_use(&rth->dst, now);
 			spin_unlock_bh(&dn_rt_hash_table[hash].lock);
 
-			dnrt_drop(rt);
+			dst_free(&rt->dst);
 			*rp = rth;
 			return 0;
 		}
@@ -380,7 +374,7 @@ static void dn_run_flush(unsigned long dummy)
 		for(; rt; rt = next) {
 			next = rcu_dereference_raw(rt->dst.dn_next);
 			RCU_INIT_POINTER(rt->dst.dn_next, NULL);
-			dst_free((struct dst_entry *)rt);
+			dnrt_free(rt);
 		}
 
 nothing_to_declare:
@@ -1187,7 +1181,7 @@ static int dn_route_output_slow(struct dst_entry **pprt, const struct flowidn *o
 	if (dev_out->flags & IFF_LOOPBACK)
 		flags |= RTCF_LOCAL;
 
-	rt = dst_alloc(&dn_dst_ops, dev_out, 1, DST_OBSOLETE_NONE, DST_HOST);
+	rt = dst_alloc(&dn_dst_ops, dev_out, 0, DST_OBSOLETE_NONE, DST_HOST);
 	if (rt == NULL)
 		goto e_nobufs;
 
-- 
2.4.11


From 0fdb2b4ca074198ec0b146bcf2b923cfb7f9e494 Mon Sep 17 00:00:00 2001
From: Gao Feng <gfree.wind@vip.163.com>
Date: Fri, 16 Jun 2017 15:00:02 +0800
Subject: [PATCH 30/32] net: 8021q: Fix one possible panic caused by BUG_ON in
 free_netdev

[ Upstream commit 9745e362add89432d2c951272a99b0a5fe4348a9 ]

The register_vlan_device would invoke free_netdev directly, when
register_vlan_dev failed. It would trigger the BUG_ON in free_netdev
if the dev was already registered. In this case, the netdev would be
freed in netdev_run_todo later.

So add one condition check now. Only when dev is not registered, then
free it directly.

The following is the part coredump when netdev_upper_dev_link failed
in register_vlan_dev. I removed the lines which are too long.

[  411.237457] ------------[ cut here ]------------
[  411.237458] kernel BUG at net/core/dev.c:7998!
[  411.237484] invalid opcode: 0000 [#1] SMP
[  411.237705]  [last unloaded: 8021q]
[  411.237718] CPU: 1 PID: 12845 Comm: vconfig Tainted: G            E   4.12.0-rc5+ #6
[  411.237737] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 07/02/2015
[  411.237764] task: ffff9cbeb6685580 task.stack: ffffa7d2807d8000
[  411.237782] RIP: 0010:free_netdev+0x116/0x120
[  411.237794] RSP: 0018:ffffa7d2807dbdb0 EFLAGS: 00010297
[  411.237808] RAX: 0000000000000002 RBX: ffff9cbeb6ba8fd8 RCX: 0000000000001878
[  411.237826] RDX: 0000000000000001 RSI: 0000000000000282 RDI: 0000000000000000
[  411.237844] RBP: ffffa7d2807dbdc8 R08: 0002986100029841 R09: 0002982100029801
[  411.237861] R10: 0004000100029980 R11: 0004000100029980 R12: ffff9cbeb6ba9000
[  411.238761] R13: ffff9cbeb6ba9060 R14: ffff9cbe60f1a000 R15: ffff9cbeb6ba9000
[  411.239518] FS:  00007fb690d81700(0000) GS:ffff9cbebb640000(0000) knlGS:0000000000000000
[  411.239949] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  411.240454] CR2: 00007f7115624000 CR3: 0000000077cdf000 CR4: 00000000003406e0
[  411.240936] Call Trace:
[  411.241462]  vlan_ioctl_handler+0x3f1/0x400 [8021q]
[  411.241910]  sock_ioctl+0x18b/0x2c0
[  411.242394]  do_vfs_ioctl+0xa1/0x5d0
[  411.242853]  ? sock_alloc_file+0xa6/0x130
[  411.243465]  SyS_ioctl+0x79/0x90
[  411.243900]  entry_SYSCALL_64_fastpath+0x1e/0xa9
[  411.244425] RIP: 0033:0x7fb69089a357
[  411.244863] RSP: 002b:00007ffcd04e0fc8 EFLAGS: 00000202 ORIG_RAX: 0000000000000010
[  411.245445] RAX: ffffffffffffffda RBX: 00007ffcd04e2884 RCX: 00007fb69089a357
[  411.245903] RDX: 00007ffcd04e0fd0 RSI: 0000000000008983 RDI: 0000000000000003
[  411.246527] RBP: 00007ffcd04e0fd0 R08: 0000000000000000 R09: 1999999999999999
[  411.246976] R10: 000000000000053f R11: 0000000000000202 R12: 0000000000000004
[  411.247414] R13: 00007ffcd04e1128 R14: 00007ffcd04e2888 R15: 0000000000000001
[  411.249129] RIP: free_netdev+0x116/0x120 RSP: ffffa7d2807dbdb0

Signed-off-by: Gao Feng <gfree.wind@vip.163.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/8021q/vlan.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 467069b..9649579 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -277,7 +277,8 @@ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id)
 	return 0;
 
 out_free_newdev:
-	free_netdev(new_dev);
+	if (new_dev->reg_state == NETREG_UNINITIALIZED)
+		free_netdev(new_dev);
 	return err;
 }
 
-- 
2.4.11


From 66782dcc8a93a9137f3bb8aa65385de25ff4e938 Mon Sep 17 00:00:00 2001
From: Serhey Popovych <serhe.popovych@gmail.com>
Date: Tue, 20 Jun 2017 13:29:25 +0300
Subject: [PATCH 31/32] ipv6: Do not leak throw route references

[ Upstream commit 07f615574f8ac499875b21c1142f26308234a92c ]

While commit 73ba57bfae4a ("ipv6: fix backtracking for throw routes")
does good job on error propagation to the fib_rules_lookup()
in fib rules core framework that also corrects throw routes
handling, it does not solve route reference leakage problem
happened when we return -EAGAIN to the fib_rules_lookup()
and leave routing table entry referenced in arg->result.

If rule with matched throw route isn't last matched in the
list we overwrite arg->result losing reference on throw
route stored previously forever.

We also partially revert commit ab997ad40839 ("ipv6: fix the
incorrect return value of throw route") since we never return
routing table entry with dst.error == -EAGAIN when
CONFIG_IPV6_MULTIPLE_TABLES is on. Also there is no point
to check for RTF_REJECT flag since it is always set throw
route.

Fixes: 73ba57bfae4a ("ipv6: fix backtracking for throw routes")
Signed-off-by: Serhey Popovych <serhe.popovych@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/fib6_rules.c | 22 ++++++----------------
 net/ipv6/ip6_fib.c    |  3 +--
 2 files changed, 7 insertions(+), 18 deletions(-)

diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index eea23b5..ec849d8 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -32,7 +32,6 @@ struct fib6_rule {
 struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
 				   int flags, pol_lookup_t lookup)
 {
-	struct rt6_info *rt;
 	struct fib_lookup_arg arg = {
 		.lookup_ptr = lookup,
 		.flags = FIB_LOOKUP_NOREF,
@@ -44,21 +43,11 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
 	fib_rules_lookup(net->ipv6.fib6_rules_ops,
 			 flowi6_to_flowi(fl6), flags, &arg);
 
-	rt = arg.result;
+	if (arg.result)
+		return arg.result;
 
-	if (!rt) {
-		dst_hold(&net->ipv6.ip6_null_entry->dst);
-		return &net->ipv6.ip6_null_entry->dst;
-	}
-
-	if (rt->rt6i_flags & RTF_REJECT &&
-	    rt->dst.error == -EAGAIN) {
-		ip6_rt_put(rt);
-		rt = net->ipv6.ip6_null_entry;
-		dst_hold(&rt->dst);
-	}
-
-	return &rt->dst;
+	dst_hold(&net->ipv6.ip6_null_entry->dst);
+	return &net->ipv6.ip6_null_entry->dst;
 }
 
 static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
@@ -121,7 +110,8 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
 			flp6->saddr = saddr;
 		}
 		err = rt->dst.error;
-		goto out;
+		if (err != -EAGAIN)
+			goto out;
 	}
 again:
 	ip6_rt_put(rt);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index d4bf2c6..e6b78ba 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -289,8 +289,7 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
 	struct rt6_info *rt;
 
 	rt = lookup(net, net->ipv6.fib6_main_tbl, fl6, flags);
-	if (rt->rt6i_flags & RTF_REJECT &&
-	    rt->dst.error == -EAGAIN) {
+	if (rt->dst.error == -EAGAIN) {
 		ip6_rt_put(rt);
 		rt = net->ipv6.ip6_null_entry;
 		dst_hold(&rt->dst);
-- 
2.4.11


From 1ceaf9fc51b725f3845a9baf17f352b0a4708e5d Mon Sep 17 00:00:00 2001
From: Serhey Popovych <serhe.popovych@gmail.com>
Date: Tue, 20 Jun 2017 14:35:23 +0300
Subject: [PATCH 32/32] rtnetlink: add IFLA_GROUP to ifla_policy

[ Upstream commit db833d40ad3263b2ee3b59a1ba168bb3cfed8137 ]

Network interface groups support added while ago, however
there is no IFLA_GROUP attribute description in policy
and netlink message size calculations until now.

Add IFLA_GROUP attribute to the policy.

Fixes: cbda10fa97d7 ("net_device: add support for network device groups")
Signed-off-by: Serhey Popovych <serhe.popovych@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index a2610e1..05436c0 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -934,6 +934,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + nla_total_size(1) /* IFLA_LINKMODE */
 	       + nla_total_size(4) /* IFLA_CARRIER_CHANGES */
 	       + nla_total_size(4) /* IFLA_LINK_NETNSID */
+	       + nla_total_size(4) /* IFLA_GROUP */
 	       + nla_total_size(ext_filter_mask
 			        & RTEXT_FILTER_VF ? 4 : 0) /* IFLA_NUM_VF */
 	       + rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */
@@ -1462,6 +1463,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
 	[IFLA_LINK_NETNSID]	= { .type = NLA_S32 },
 	[IFLA_PROTO_DOWN]	= { .type = NLA_U8 },
 	[IFLA_XDP]		= { .type = NLA_NESTED },
+	[IFLA_GROUP]		= { .type = NLA_U32 },
 };
 
 static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
-- 
2.4.11

Re: [PATCHES] Networking

[Greg KH]

On Thu, Jun 29, 2017 at 12:19:07PM -0400, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.9 and v4.11
> -stable, respectively.
> 
> Thank you!


Thanks for these, all now queued up!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 107 bytes --]


Please queue up the following networking bug fixes for v4.11 and
v4.12 -stable, respectively.

Thank you.

[-- Attachment #2: net_411.mbox --]
[-- Type: Application/Octet-Stream, Size: 84305 bytes --]

From aa99f9486fd434ff010a4df524dc2fb6dde31168 Mon Sep 17 00:00:00 2001
From: Zach Brown <zach.brown@ni.com>
Date: Tue, 20 Jun 2017 12:48:11 -0500
Subject: [PATCH 01/30] net/phy: micrel: configure intterupts after autoneg
 workaround

[ Upstream commit b866203d872d5deeafcecd25ea429d6748b5bd56 ]

The commit ("net/phy: micrel: Add workaround for bad autoneg") fixes an
autoneg failure case by resetting the hardware. This turns off
intterupts. Things will work themselves out if the phy polls, as it will
figure out it's state during a poll. However if the phy uses only
intterupts, the phy will stall, since interrupts are off. This patch
fixes the issue by calling config_intr after resetting the phy.

Fixes: d2fd719bcb0e ("net/phy: micrel: Add workaround for bad autoneg ")
Signed-off-by: Zach Brown <zach.brown@ni.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/micrel.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index da5b39268370..4b7a6e0d4c39 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -611,6 +611,8 @@ static int ksz9031_read_status(struct phy_device *phydev)
 	if ((regval & 0xFF) == 0xFF) {
 		phy_init_hw(phydev);
 		phydev->link = 0;
+		if (phydev->drv->config_intr && phy_interrupt_is_valid(phydev))
+			phydev->drv->config_intr(phydev);
 	}
 
 	return 0;
-- 
2.13.0


From 1e4155f9f66cff53da852a0b85ec40a9456fe7ac Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Wed, 21 Jun 2017 14:34:58 -0700
Subject: [PATCH 02/30] ipv6: avoid unregistering inet6_dev for loopback

[ Upstream commit 60abc0be96e00ca71bac083215ac91ad2e575096 ]

The per netns loopback_dev->ip6_ptr is unregistered and set to
NULL when its mtu is set to smaller than IPV6_MIN_MTU, this
leads to that we could set rt->rt6i_idev NULL after a
rt6_uncached_list_flush_dev() and then crash after another
call.

In this case we should just bring its inet6_dev down, rather
than unregistering it, at least prior to commit 176c39af29bc
("netns: fix addrconf_ifdown kernel panic") we always
override the case for loopback.

Thanks a lot to Andrey for finding a reliable reproducer.

Fixes: 176c39af29bc ("netns: fix addrconf_ifdown kernel panic")
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Cc: Andrey Konovalov <andreyknvl@google.com>
Cc: Daniel Lezcano <dlezcano@fr.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: David Ahern <dsahern@gmail.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 9725e8faf56d..177eee060027 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3334,6 +3334,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct netdev_notifier_changeupper_info *info;
 	struct inet6_dev *idev = __in6_dev_get(dev);
+	struct net *net = dev_net(dev);
 	int run_pending = 0;
 	int err;
 
@@ -3349,7 +3350,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
 	case NETDEV_CHANGEMTU:
 		/* if MTU under IPV6_MIN_MTU stop IPv6 on this interface. */
 		if (dev->mtu < IPV6_MIN_MTU) {
-			addrconf_ifdown(dev, 1);
+			addrconf_ifdown(dev, dev != net->loopback_dev);
 			break;
 		}
 
@@ -3465,7 +3466,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
 			 * IPV6_MIN_MTU stop IPv6 on this interface.
 			 */
 			if (dev->mtu < IPV6_MIN_MTU)
-				addrconf_ifdown(dev, 1);
+				addrconf_ifdown(dev, dev != net->loopback_dev);
 		}
 		break;
 
-- 
2.13.0


From 40cf1968bfe78a3eac529e69bc0d3e958ca3d062 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 22 Jun 2017 00:16:37 +0200
Subject: [PATCH 03/30] netvsc: don't access netdev->num_rx_queues directly

[ Upstream commit b92b7d3312033a08cae2c879b9243c42ad7de94b ]

This structure member is hidden behind CONFIG_SYSFS, and we
get a build error when that is disabled:

drivers/net/hyperv/netvsc_drv.c: In function 'netvsc_set_channels':
drivers/net/hyperv/netvsc_drv.c:754:49: error: 'struct net_device' has no member named 'num_rx_queues'; did you mean 'num_tx_queues'?
drivers/net/hyperv/netvsc_drv.c: In function 'netvsc_set_rxfh':
drivers/net/hyperv/netvsc_drv.c:1181:25: error: 'struct net_device' has no member named 'num_rx_queues'; did you mean 'num_tx_queues'?

As the value is only set once to the argument of alloc_netdev_mq(),
we can compare against that constant directly.

Fixes: ff4a44199012 ("netvsc: allow get/set of RSS indirection table")
Fixes: 2b01888d1b45 ("netvsc: allow more flexible setting of number of channels")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/netvsc_drv.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 5ede87f30463..09b0becb3843 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -753,7 +753,7 @@ static int netvsc_set_channels(struct net_device *net,
 	    channels->rx_count || channels->tx_count || channels->other_count)
 		return -EINVAL;
 
-	if (count > net->num_tx_queues || count > net->num_rx_queues)
+	if (count > net->num_tx_queues || count > VRSS_CHANNEL_MAX)
 		return -EINVAL;
 
 	if (net_device_ctx->start_remove || !nvdev || nvdev->destroy)
@@ -1142,7 +1142,7 @@ static int netvsc_set_rxfh(struct net_device *dev, const u32 *indir,
 
 	if (indir) {
 		for (i = 0; i < ITAB_NUM; i++)
-			if (indir[i] >= dev->num_rx_queues)
+			if (indir[i] >= VRSS_CHANNEL_MAX)
 				return -EINVAL;
 
 		for (i = 0; i < ITAB_NUM; i++)
-- 
2.13.0


From a203d20606bf9a159acb36ee7de5fa6b08889848 Mon Sep 17 00:00:00 2001
From: Martin Habets <mhabets@solarflare.com>
Date: Thu, 22 Jun 2017 10:50:41 +0100
Subject: [PATCH 04/30] sfc: Fix MCDI command size for filter operations

[ Upstream commit bb53f4d4f5116d3dae76bb12fb16bc73771f958a ]

The 8000 series adapters uses catch-all filters for encapsulated traffic
to support filtering VXLAN, NVGRE and GENEVE traffic.
This new filter functionality requires a longer MCDI command.
This patch increases the size of buffers on stack that were missed, which
fixes a kernel panic from the stack protector.

Fixes: 9b41080125176 ("sfc: insert catch-all filters for encapsulated traffic")
Signed-off-by: Martin Habets <mhabets@solarflare.com>
Acked-by: Edward Cree <ecree@solarflare.com>
Acked-by: Bert Kenward bkenward@solarflare.com
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/ef10.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index c60c2d4c646a..f4aed889b6ce 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -4171,7 +4171,7 @@ static s32 efx_ef10_filter_insert(struct efx_nic *efx,
 	 * recipients
 	 */
 	if (is_mc_recip) {
-		MCDI_DECLARE_BUF(inbuf, MC_CMD_FILTER_OP_IN_LEN);
+		MCDI_DECLARE_BUF(inbuf, MC_CMD_FILTER_OP_EXT_IN_LEN);
 		unsigned int depth, i;
 
 		memset(inbuf, 0, sizeof(inbuf));
@@ -4319,7 +4319,7 @@ static int efx_ef10_filter_remove_internal(struct efx_nic *efx,
 			efx_ef10_filter_set_entry(table, filter_idx, NULL, 0);
 		} else {
 			efx_mcdi_display_error(efx, MC_CMD_FILTER_OP,
-					       MC_CMD_FILTER_OP_IN_LEN,
+					       MC_CMD_FILTER_OP_EXT_IN_LEN,
 					       NULL, 0, rc);
 		}
 	}
@@ -4452,7 +4452,7 @@ static s32 efx_ef10_filter_rfs_insert(struct efx_nic *efx,
 				      struct efx_filter_spec *spec)
 {
 	struct efx_ef10_filter_table *table = efx->filter_state;
-	MCDI_DECLARE_BUF(inbuf, MC_CMD_FILTER_OP_IN_LEN);
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_FILTER_OP_EXT_IN_LEN);
 	struct efx_filter_spec *saved_spec;
 	unsigned int hash, i, depth = 1;
 	bool replacing = false;
@@ -4939,7 +4939,7 @@ static void efx_ef10_filter_table_restore(struct efx_nic *efx)
 static void efx_ef10_filter_table_remove(struct efx_nic *efx)
 {
 	struct efx_ef10_filter_table *table = efx->filter_state;
-	MCDI_DECLARE_BUF(inbuf, MC_CMD_FILTER_OP_IN_LEN);
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_FILTER_OP_EXT_IN_LEN);
 	struct efx_filter_spec *spec;
 	unsigned int filter_idx;
 	int rc;
-- 
2.13.0


From 72d2dad53e498564954926489fecbdc68bdeb164 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Michal=20Kube=C4=8Dek?= <mkubecek@suse.cz>
Date: Mon, 19 Jun 2017 13:03:43 +0200
Subject: [PATCH 05/30] net: account for current skb length when deciding about
 UFO

[ Upstream commit a5cb659bbc1c8644efa0c3138a757a1e432a4880 ]

Our customer encountered stuck NFS writes for blocks starting at specific
offsets w.r.t. page boundary caused by networking stack sending packets via
UFO enabled device with wrong checksum. The problem can be reproduced by
composing a long UDP datagram from multiple parts using MSG_MORE flag:

  sendto(sd, buff, 1000, MSG_MORE, ...);
  sendto(sd, buff, 1000, MSG_MORE, ...);
  sendto(sd, buff, 3000, 0, ...);

Assume this packet is to be routed via a device with MTU 1500 and
NETIF_F_UFO enabled. When second sendto() gets into __ip_append_data(),
this condition is tested (among others) to decide whether to call
ip_ufo_append_data():

  ((length + fragheaderlen) > mtu) || (skb && skb_is_gso(skb))

At the moment, we already have skb with 1028 bytes of data which is not
marked for GSO so that the test is false (fragheaderlen is usually 20).
Thus we append second 1000 bytes to this skb without invoking UFO. Third
sendto(), however, has sufficient length to trigger the UFO path so that we
end up with non-UFO skb followed by a UFO one. Later on, udp_send_skb()
uses udp_csum() to calculate the checksum but that assumes all fragments
have correct checksum in skb->csum which is not true for UFO fragments.

When checking against MTU, we need to add skb->len to length of new segment
if we already have a partially filled skb and fragheaderlen only if there
isn't one.

In the IPv6 case, skb can only be null if this is the first segment so that
we have to use headersize (length of the first IPv6 header) rather than
fragheaderlen (length of IPv6 header of further fragments) for skb == NULL.

Fixes: e89e9cf539a2 ("[IPv4/IPv6]: UFO Scatter-gather approach")
Fixes: e4c5e13aa45c ("ipv6: Should use consistent conditional judgement for
	ip6 fragment between __ip6_append_data and ip6_finish_output")
Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Acked-by: Vlad Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_output.c  | 3 ++-
 net/ipv6/ip6_output.c | 2 +-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 7a3fd25e8913..532b36e9ce2a 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -964,7 +964,8 @@ static int __ip_append_data(struct sock *sk,
 		csummode = CHECKSUM_PARTIAL;
 
 	cork->length += length;
-	if ((((length + fragheaderlen) > mtu) || (skb && skb_is_gso(skb))) &&
+	if ((((length + (skb ? skb->len : fragheaderlen)) > mtu) ||
+	     (skb && skb_is_gso(skb))) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
 	    (rt->dst.dev->features & NETIF_F_UFO) && !dst_xfrm(&rt->dst) &&
 	    (sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx) {
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index bf8a58a1c32d..1699acb2fa2c 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1390,7 +1390,7 @@ static int __ip6_append_data(struct sock *sk,
 	 */
 
 	cork->length += length;
-	if ((((length + fragheaderlen) > mtu) ||
+	if ((((length + (skb ? skb->len : headersize)) > mtu) ||
 	     (skb && skb_is_gso(skb))) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
 	    (rt->dst.dev->features & NETIF_F_UFO) && !dst_xfrm(&rt->dst) &&
-- 
2.13.0


From 26dcfa52b4dddac9db874f60f45f0f3a3bbcdeda Mon Sep 17 00:00:00 2001
From: Richard Cochran <richardcochran@gmail.com>
Date: Fri, 23 Jun 2017 17:51:31 +0200
Subject: [PATCH 06/30] net: dp83640: Avoid NULL pointer dereference.

[ Upstream commit db9d8b29d19d2801793e4419f4c6272bf8951c62 ]

The function, skb_complete_tx_timestamp(), used to allow passing in a
NULL pointer for the time stamps, but that was changed in commit
62bccb8cdb69051b95a55ab0c489e3cab261c8ef ("net-timestamp: Make the
clone operation stand-alone from phy timestamping"), and the existing
call sites, all of which are in the dp83640 driver, were fixed up.

Even though the kernel-doc was subsequently updated in commit
7a76a021cd5a292be875fbc616daf03eab1e6996 ("net-timestamp: Update
skb_complete_tx_timestamp comment"), still a bug fix from Manfred
Rudigier came into the driver using the old semantics.  Probably
Manfred derived that patch from an older kernel version.

This fix should be applied to the stable trees as well.

Fixes: 81e8f2e930fe ("net: dp83640: Fix tx timestamp overflow handling.")
Signed-off-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/dp83640.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index ed0d10f54f26..c3065236ffcc 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -908,7 +908,7 @@ static void decode_txts(struct dp83640_private *dp83640,
 	if (overflow) {
 		pr_debug("tx timestamp queue overflow, count %d\n", overflow);
 		while (skb) {
-			skb_complete_tx_timestamp(skb, NULL);
+			kfree_skb(skb);
 			skb = skb_dequeue(&dp83640->tx_queue);
 		}
 		return;
-- 
2.13.0


From 60b61f11cafb911405aa20eacf36bed79ae3fc22 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Sat, 24 Jun 2017 23:50:30 -0700
Subject: [PATCH 07/30] tcp: reset sk_rx_dst in tcp_disconnect()

[ Upstream commit d747a7a51b00984127a88113cdbbc26f91e9d815 ]

We have to reset the sk->sk_rx_dst when we disconnect a TCP
connection, because otherwise when we re-connect it this
dst reference is simply overridden in tcp_finish_connect().

This fixes a dst leak which leads to a loopback dev refcnt
leak. It is a long-standing bug, Kevin reported a very similar
(if not same) bug before. Thanks to Andrei for providing such
a reliable reproducer which greatly narrows down the problem.

Fixes: 41063e9dd119 ("ipv4: Early TCP socket demux.")
Reported-by: Andrei Vagin <avagin@gmail.com>
Reported-by: Kevin Xu <kaiwen.xu@hulu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 651f1f058a64..2391a07e4566 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2325,6 +2325,8 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tcp_init_send_head(sk);
 	memset(&tp->rx_opt, 0, sizeof(tp->rx_opt));
 	__sk_dst_reset(sk);
+	dst_release(sk->sk_rx_dst);
+	sk->sk_rx_dst = NULL;
 	tcp_saved_syn_free(tp);
 
 	/* Clean up fastopen related fields */
-- 
2.13.0


From 246cc544a7697aa87602f2cfa6305dd6eb4aed53 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 27 Jun 2017 07:02:20 -0700
Subject: [PATCH 08/30] net: prevent sign extension in dev_get_stats()

[ Upstream commit 6f64ec74515925cced6df4571638b5a099a49aae ]

Similar to the fix provided by Dominik Heidler in commit
9b3dc0a17d73 ("l2tp: cast l2tp traffic counter to unsigned")
we need to take care of 32bit kernels in dev_get_stats().

When using atomic_long_read(), we add a 'long' to u64 and
might misinterpret high order bit, unless we cast to unsigned.

Fixes: caf586e5f23ce ("net: add a core netdev->rx_dropped counter")
Fixes: 015f0688f57ca ("net: net: add a core netdev->tx_dropped counter")
Fixes: 6e7333d315a76 ("net: add rx_nohandler stat counter")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jarod Wilson <jarod@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 9debc1b26ce9..e384d98e66c2 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7623,9 +7623,9 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev,
 	} else {
 		netdev_stats_to_stats64(storage, &dev->stats);
 	}
-	storage->rx_dropped += atomic_long_read(&dev->rx_dropped);
-	storage->tx_dropped += atomic_long_read(&dev->tx_dropped);
-	storage->rx_nohandler += atomic_long_read(&dev->rx_nohandler);
+	storage->rx_dropped += (unsigned long)atomic_long_read(&dev->rx_dropped);
+	storage->tx_dropped += (unsigned long)atomic_long_read(&dev->tx_dropped);
+	storage->rx_nohandler += (unsigned long)atomic_long_read(&dev->rx_nohandler);
 	return storage;
 }
 EXPORT_SYMBOL(dev_get_stats);
-- 
2.13.0


From f7ccc35c9c3040f09269713330c15acf6a18b5ae Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Wed, 28 Jun 2017 09:51:03 +0800
Subject: [PATCH 09/30] virtio-net: serialize tx routine during reset

[ Upstream commit 713a98d90c5ea072c1bb00ef40617aee2cef2232 ]

We don't hold any tx lock when trying to disable TX during reset, this
would lead a use after free since ndo_start_xmit() tries to access
the virtqueue which has already been freed. Fix this by using
netif_tx_disable() before freeing the vqs, this could make sure no tx
after vq freeing.

Reported-by: Jean-Philippe Menil <jpmenil@gmail.com>
Tested-by: Jean-Philippe Menil <jpmenil@gmail.com>
Fixes commit f600b6905015 ("virtio_net: Add XDP support")
Cc: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Robert McCabe <robert.mccabe@rockwellcollins.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index d9d8f4f43f90..7e171d7aed66 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1709,6 +1709,7 @@ static void virtnet_freeze_down(struct virtio_device *vdev)
 	flush_work(&vi->config_work);
 
 	netif_device_detach(vi->dev);
+	netif_tx_disable(vi->dev);
 	cancel_delayed_work_sync(&vi->refill);
 
 	if (netif_running(vi->dev)) {
-- 
2.13.0


From adc4e34f47a1009b64be3364b5f01486e9196b5a Mon Sep 17 00:00:00 2001
From: Gao Feng <gfree.wind@vip.163.com>
Date: Wed, 28 Jun 2017 12:53:54 +0800
Subject: [PATCH 10/30] net: sched: Fix one possible panic when no destroy
 callback

[ Upstream commit c1a4872ebfb83b1af7144f7b29ac8c4b344a12a8 ]

When qdisc fail to init, qdisc_create would invoke the destroy callback
to cleanup. But there is no check if the callback exists really. So it
would cause the panic if there is no real destroy callback like the qdisc
codel, fq, and so on.

Take codel as an example following:
When a malicious user constructs one invalid netlink msg, it would cause
codel_init->codel_change->nla_parse_nested failed.
Then kernel would invoke the destroy callback directly but qdisc codel
doesn't define one. It causes one panic as a result.

Now add one the check for destroy to avoid the possible panic.

Fixes: 87b60cfacf9f ("net_sched: fix error recovery at qdisc creation")
Signed-off-by: Gao Feng <gfree.wind@vip.163.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_api.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index bcf49cd22786..6ca1db73d1d1 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1008,7 +1008,8 @@ static struct Qdisc *qdisc_create(struct net_device *dev,
 		return sch;
 	}
 	/* ops->init() failed, we call ->destroy() like qdisc_create_dflt() */
-	ops->destroy(sch);
+	if (ops->destroy)
+		ops->destroy(sch);
 err_out3:
 	dev_put(dev);
 	kfree((char *) sch - sch->padded);
-- 
2.13.0


From 3f31689a6716b6126d10bfce960dc652e86e5d09 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 28 Jun 2017 09:03:12 +0300
Subject: [PATCH 11/30] mlxsw: spectrum_router: Fix NULL pointer dereference

[ Upstream commit 6b27c8adf27edf1dabe2cdcfaa101ef7e2712415 ]

In case a VLAN device is enslaved to a bridge we shouldn't create a
router interface (RIF) for it when it's configured with an IP address.
This is already handled by the driver for other types of netdevs, such
as physical ports and LAG devices.

If this IP address is then removed and the interface is subsequently
unlinked from the bridge, a NULL pointer dereference can happen, as the
original 802.1d FID was replaced with an rFID which was then deleted.

To reproduce:
$ ip link set dev enp3s0np9 up
$ ip link add name enp3s0np9.111 link enp3s0np9 type vlan id 111
$ ip link set dev enp3s0np9.111 up
$ ip link add name br0 type bridge
$ ip link set dev br0 up
$ ip link set enp3s0np9.111 master br0
$ ip address add dev enp3s0np9.111 192.168.0.1/24
$ ip address del dev enp3s0np9.111 192.168.0.1/24
$ ip link set dev enp3s0np9.111 nomaster

Fixes: 99724c18fc66 ("mlxsw: spectrum: Introduce support for router interfaces")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Petr Machata <petrm@mellanox.com>
Tested-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 16484f24b7db..5995ca1a43f9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -3829,6 +3829,9 @@ static int mlxsw_sp_inetaddr_vlan_event(struct net_device *vlan_dev,
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(vlan_dev);
 	u16 vid = vlan_dev_vlan_id(vlan_dev);
 
+	if (netif_is_bridge_port(vlan_dev))
+		return 0;
+
 	if (mlxsw_sp_port_dev_check(real_dev))
 		return mlxsw_sp_inetaddr_vport_event(vlan_dev, real_dev, event,
 						     vid);
-- 
2.13.0


From ae744d808f4d47e5aa9a77f2845e84eedd17e357 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 28 Jun 2017 14:44:21 +0300
Subject: [PATCH 12/30] rocker: move dereference before free

[ Upstream commit acb4b7df48b539cb391287921de57e4e5fae3460 ]

My static checker complains that ofdpa_neigh_del() can sometimes free
"found".   It just makes sense to use it first before deleting it.

Fixes: ecf244f753e0 ("rocker: fix maybe-uninitialized warning")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/rocker/rocker_ofdpa.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/rocker/rocker_ofdpa.c b/drivers/net/ethernet/rocker/rocker_ofdpa.c
index 2ae852454780..a9ce82d3e9cf 100644
--- a/drivers/net/ethernet/rocker/rocker_ofdpa.c
+++ b/drivers/net/ethernet/rocker/rocker_ofdpa.c
@@ -1505,8 +1505,8 @@ static int ofdpa_port_ipv4_nh(struct ofdpa_port *ofdpa_port,
 		*index = entry->index;
 		resolved = false;
 	} else if (removing) {
-		ofdpa_neigh_del(trans, found);
 		*index = found->index;
+		ofdpa_neigh_del(trans, found);
 	} else if (updating) {
 		ofdpa_neigh_update(found, trans, NULL, false);
 		resolved = !is_zero_ether_addr(found->eth_dst);
-- 
2.13.0


From d3c8743a21ba8f464bd1eb3ff476f2b98ddc7dbf Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 29 Jun 2017 03:04:59 +0200
Subject: [PATCH 13/30] bpf: prevent leaking pointer via xadd on unpriviledged

[ Upstream commit 6bdf6abc56b53103324dfd270a86580306e1a232 ]

Leaking kernel addresses on unpriviledged is generally disallowed,
for example, verifier rejects the following:

  0: (b7) r0 = 0
  1: (18) r2 = 0xffff897e82304400
  3: (7b) *(u64 *)(r1 +48) = r2
  R2 leaks addr into ctx

Doing pointer arithmetic on them is also forbidden, so that they
don't turn into unknown value and then get leaked out. However,
there's xadd as a special case, where we don't check the src reg
for being a pointer register, e.g. the following will pass:

  0: (b7) r0 = 0
  1: (7b) *(u64 *)(r1 +48) = r0
  2: (18) r2 = 0xffff897e82304400 ; map
  4: (db) lock *(u64 *)(r1 +48) += r2
  5: (95) exit

We could store the pointer into skb->cb, loose the type context,
and then read it out from there again to leak it eventually out
of a map value. Or more easily in a different variant, too:

   0: (bf) r6 = r1
   1: (7a) *(u64 *)(r10 -8) = 0
   2: (bf) r2 = r10
   3: (07) r2 += -8
   4: (18) r1 = 0x0
   6: (85) call bpf_map_lookup_elem#1
   7: (15) if r0 == 0x0 goto pc+3
   R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R6=ctx R10=fp
   8: (b7) r3 = 0
   9: (7b) *(u64 *)(r0 +0) = r3
  10: (db) lock *(u64 *)(r0 +0) += r6
  11: (b7) r0 = 0
  12: (95) exit

  from 7 to 11: R0=inv,min_value=0,max_value=0 R6=ctx R10=fp
  11: (b7) r0 = 0
  12: (95) exit

Prevent this by checking xadd src reg for pointer types. Also
add a couple of test cases related to this.

Fixes: 1be7f75d1668 ("bpf: enable non-root eBPF programs")
Fixes: 17a5267067f3 ("bpf: verifier (add verifier core)")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c                       |  5 +++
 tools/testing/selftests/bpf/test_verifier.c | 66 +++++++++++++++++++++++++++++
 2 files changed, 71 insertions(+)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 904decd32783..7a6462b7f72a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -951,6 +951,11 @@ static int check_xadd(struct bpf_verifier_env *env, struct bpf_insn *insn)
 	if (err)
 		return err;
 
+	if (is_pointer_value(env, insn->src_reg)) {
+		verbose("R%d leaks addr into mem\n", insn->src_reg);
+		return -EACCES;
+	}
+
 	/* check whether atomic_add can read the memory */
 	err = check_mem_access(env, insn->dst_reg, insn->off,
 			       BPF_SIZE(insn->code), BPF_READ, -1);
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 8b433bf3fdd7..5238d0a1398c 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -3518,6 +3518,72 @@ static struct bpf_test tests[] = {
 		.errstr = "invalid bpf_context access",
 	},
 	{
+		"leak pointer into ctx 1",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0,
+				    offsetof(struct __sk_buff, cb[0])),
+			BPF_LD_MAP_FD(BPF_REG_2, 0),
+			BPF_STX_XADD(BPF_DW, BPF_REG_1, BPF_REG_2,
+				      offsetof(struct __sk_buff, cb[0])),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map1 = { 2 },
+		.errstr_unpriv = "R2 leaks addr into mem",
+		.result_unpriv = REJECT,
+		.result = ACCEPT,
+	},
+	{
+		"leak pointer into ctx 2",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0,
+				    offsetof(struct __sk_buff, cb[0])),
+			BPF_STX_XADD(BPF_DW, BPF_REG_1, BPF_REG_10,
+				      offsetof(struct __sk_buff, cb[0])),
+			BPF_EXIT_INSN(),
+		},
+		.errstr_unpriv = "R10 leaks addr into mem",
+		.result_unpriv = REJECT,
+		.result = ACCEPT,
+	},
+	{
+		"leak pointer into ctx 3",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_LD_MAP_FD(BPF_REG_2, 0),
+			BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2,
+				      offsetof(struct __sk_buff, cb[0])),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map1 = { 1 },
+		.errstr_unpriv = "R2 leaks addr into ctx",
+		.result_unpriv = REJECT,
+		.result = ACCEPT,
+	},
+	{
+		"leak pointer into map val",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_map_lookup_elem),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
+			BPF_MOV64_IMM(BPF_REG_3, 0),
+			BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_3, 0),
+			BPF_STX_XADD(BPF_DW, BPF_REG_0, BPF_REG_6, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map1 = { 4 },
+		.errstr_unpriv = "R6 leaks addr into mem",
+		.result_unpriv = REJECT,
+		.result = ACCEPT,
+	},
+	{
 		"helper access to map: full range",
 		.insns = {
 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-- 
2.13.0


From 2cc084597b1edb3f4b1f5957a18a9d07de242a32 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Michal=20Kube=C4=8Dek?= <mkubecek@suse.cz>
Date: Thu, 29 Jun 2017 11:13:36 +0200
Subject: [PATCH 14/30] net: handle NAPI_GRO_FREE_STOLEN_HEAD case also in
 napi_frags_finish()

[ Upstream commit e44699d2c28067f69698ccb68dd3ddeacfebc434 ]

Recently I started seeing warnings about pages with refcount -1. The
problem was traced to packets being reused after their head was merged into
a GRO packet by skb_gro_receive(). While bisecting the issue pointed to
commit c21b48cc1bbf ("net: adjust skb->truesize in ___pskb_trim()") and
I have never seen it on a kernel with it reverted, I believe the real
problem appeared earlier when the option to merge head frag in GRO was
implemented.

Handling NAPI_GRO_FREE_STOLEN_HEAD state was only added to GRO_MERGED_FREE
branch of napi_skb_finish() so that if the driver uses napi_gro_frags()
and head is merged (which in my case happens after the skb_condense()
call added by the commit mentioned above), the skb is reused including the
head that has been merged. As a result, we release the page reference
twice and eventually end up with negative page refcount.

To fix the problem, handle NAPI_GRO_FREE_STOLEN_HEAD in napi_frags_finish()
the same way it's done in napi_skb_finish().

Fixes: d7e8883cfcf4 ("net: make GRO aware of skb->head_frag")
Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 24 +++++++++++++++++-------
 1 file changed, 17 insertions(+), 7 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index e384d98e66c2..1f664e54096c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4627,6 +4627,13 @@ struct packet_offload *gro_find_complete_by_type(__be16 type)
 }
 EXPORT_SYMBOL(gro_find_complete_by_type);
 
+static void napi_skb_free_stolen_head(struct sk_buff *skb)
+{
+	skb_dst_drop(skb);
+	secpath_reset(skb);
+	kmem_cache_free(skbuff_head_cache, skb);
+}
+
 static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
 {
 	switch (ret) {
@@ -4640,13 +4647,10 @@ static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
 		break;
 
 	case GRO_MERGED_FREE:
-		if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) {
-			skb_dst_drop(skb);
-			secpath_reset(skb);
-			kmem_cache_free(skbuff_head_cache, skb);
-		} else {
+		if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD)
+			napi_skb_free_stolen_head(skb);
+		else
 			__kfree_skb(skb);
-		}
 		break;
 
 	case GRO_HELD:
@@ -4718,10 +4722,16 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi,
 		break;
 
 	case GRO_DROP:
-	case GRO_MERGED_FREE:
 		napi_reuse_skb(napi, skb);
 		break;
 
+	case GRO_MERGED_FREE:
+		if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD)
+			napi_skb_free_stolen_head(skb);
+		else
+			napi_reuse_skb(napi, skb);
+		break;
+
 	case GRO_MERGED:
 	case GRO_CONSUMED:
 		break;
-- 
2.13.0


From c1daf53b4d752b5b04cad223585dce3183b46843 Mon Sep 17 00:00:00 2001
From: Mohamad Haj Yahia <mohamad@mellanox.com>
Date: Thu, 30 Mar 2017 17:09:00 +0300
Subject: [PATCH 15/30] net/mlx5: Cancel delayed recovery work when unloading
 the driver

[ Upstream commit 2a0165a034ac024b60cca49c61e46f4afa2e4d98 ]

Draining the health workqueue will ignore future health works including
the one that report hardware failure and thus we can't enter error state
Instead cancel the recovery flow and make sure only recovery flow won't
be scheduled.

Fixes: 5e44fca50470 ('net/mlx5: Only cancel recovery work when cleaning up device')
Signed-off-by: Mohamad Haj Yahia <mohamad@mellanox.com>
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/health.c | 15 ++++++++++++++-
 drivers/net/ethernet/mellanox/mlx5/core/main.c   |  2 +-
 include/linux/mlx5/driver.h                      |  1 +
 3 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 44f59b1d6f0f..9c4b74d44234 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -67,6 +67,7 @@ enum {
 
 enum {
 	MLX5_DROP_NEW_HEALTH_WORK,
+	MLX5_DROP_NEW_RECOVERY_WORK,
 };
 
 static u8 get_nic_state(struct mlx5_core_dev *dev)
@@ -193,7 +194,7 @@ static void health_care(struct work_struct *work)
 	mlx5_handle_bad_state(dev);
 
 	spin_lock(&health->wq_lock);
-	if (!test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags))
+	if (!test_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags))
 		schedule_delayed_work(&health->recover_work, recover_delay);
 	else
 		dev_err(&dev->pdev->dev,
@@ -314,6 +315,7 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev)
 	init_timer(&health->timer);
 	health->sick = 0;
 	clear_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags);
+	clear_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags);
 	health->health = &dev->iseg->health;
 	health->health_counter = &dev->iseg->health_counter;
 
@@ -336,11 +338,22 @@ void mlx5_drain_health_wq(struct mlx5_core_dev *dev)
 
 	spin_lock(&health->wq_lock);
 	set_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags);
+	set_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags);
 	spin_unlock(&health->wq_lock);
 	cancel_delayed_work_sync(&health->recover_work);
 	cancel_work_sync(&health->work);
 }
 
+void mlx5_drain_health_recovery(struct mlx5_core_dev *dev)
+{
+	struct mlx5_core_health *health = &dev->priv.health;
+
+	spin_lock(&health->wq_lock);
+	set_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags);
+	spin_unlock(&health->wq_lock);
+	cancel_delayed_work_sync(&dev->priv.health.recover_work);
+}
+
 void mlx5_health_cleanup(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_health *health = &dev->priv.health;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 9862a741b32a..23173be1cbc0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1236,7 +1236,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 	int err = 0;
 
 	if (cleanup)
-		mlx5_drain_health_wq(dev);
+		mlx5_drain_health_recovery(dev);
 
 	mutex_lock(&dev->intf_state_mutex);
 	if (test_bit(MLX5_INTERFACE_STATE_DOWN, &dev->intf_state)) {
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index c965d1165df6..77bdfcdd5a04 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -928,6 +928,7 @@ int mlx5_health_init(struct mlx5_core_dev *dev);
 void mlx5_start_health_poll(struct mlx5_core_dev *dev);
 void mlx5_stop_health_poll(struct mlx5_core_dev *dev);
 void mlx5_drain_health_wq(struct mlx5_core_dev *dev);
+void mlx5_drain_health_recovery(struct mlx5_core_dev *dev);
 int mlx5_buf_alloc_node(struct mlx5_core_dev *dev, int size,
 			struct mlx5_buf *buf, int node);
 int mlx5_buf_alloc(struct mlx5_core_dev *dev, int size, struct mlx5_buf *buf);
-- 
2.13.0


From 043bbca030cb2371197515faf8e801f14213e7d8 Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Sun, 25 Jun 2017 16:46:25 +0300
Subject: [PATCH 16/30] net/mlx5e: Fix TX carrier errors report in get stats
 ndo

[ Upstream commit 8ff93de7668bd81bc8efa819d1184ebd48fae72d ]

Symbol error during carrier counter from PPCNT was mistakenly reported as
TX carrier errors in get_stats ndo, although it's an RX counter.

Fixes: 269e6b3af3bf ("net/mlx5e: Report additional error statistics in get stats ndo")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index f778436a2d28..00104de79d0e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2771,8 +2771,6 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 		PPORT_802_3_GET(pstats, a_frame_check_sequence_errors);
 	stats->rx_frame_errors = PPORT_802_3_GET(pstats, a_alignment_errors);
 	stats->tx_aborted_errors = PPORT_2863_GET(pstats, if_out_discards);
-	stats->tx_carrier_errors =
-		PPORT_802_3_GET(pstats, a_symbol_error_during_carrier);
 	stats->rx_errors = stats->rx_length_errors + stats->rx_crc_errors +
 			   stats->rx_frame_errors;
 	stats->tx_errors = stats->tx_aborted_errors + stats->tx_carrier_errors;
-- 
2.13.0


From c267e4a1f4e88287fcc8d386aa84feb8abc2cc1a Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Thu, 29 Jun 2017 16:56:54 +0200
Subject: [PATCH 17/30] ipv6: dad: don't remove dynamic addresses if link is
 down

[ Upstream commit ec8add2a4c9df723c94a863b8fcd6d93c472deed ]

Currently, when the link for $DEV is down, this command succeeds but the
address is removed immediately by DAD (1):

    ip addr add 1111::12/64 dev $DEV valid_lft 3600 preferred_lft 1800

In the same situation, this will succeed and not remove the address (2):

    ip addr add 1111::12/64 dev $DEV
    ip addr change 1111::12/64 dev $DEV valid_lft 3600 preferred_lft 1800

The comment in addrconf_dad_begin() when !IF_READY makes it look like
this is the intended behavior, but doesn't explain why:

     * If the device is not ready:
     * - keep it tentative if it is a permanent address.
     * - otherwise, kill it.

We clearly cannot prevent userspace from doing (2), but we can make (1)
work consistently with (2).

addrconf_dad_stop() is only called in two cases: if DAD failed, or to
skip DAD when the link is down. In that second case, the fix is to avoid
deleting the address, like we already do for permanent addresses.

Fixes: 3c21edbd1137 ("[IPV6]: Defer IPv6 device initialization until the link becomes ready.")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 177eee060027..682ea6417db3 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1888,15 +1888,7 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed)
 	if (dad_failed)
 		ifp->flags |= IFA_F_DADFAILED;
 
-	if (ifp->flags&IFA_F_PERMANENT) {
-		spin_lock_bh(&ifp->lock);
-		addrconf_del_dad_work(ifp);
-		ifp->flags |= IFA_F_TENTATIVE;
-		spin_unlock_bh(&ifp->lock);
-		if (dad_failed)
-			ipv6_ifa_notify(0, ifp);
-		in6_ifa_put(ifp);
-	} else if (ifp->flags&IFA_F_TEMPORARY) {
+	if (ifp->flags&IFA_F_TEMPORARY) {
 		struct inet6_ifaddr *ifpub;
 		spin_lock_bh(&ifp->lock);
 		ifpub = ifp->ifpub;
@@ -1909,6 +1901,14 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed)
 			spin_unlock_bh(&ifp->lock);
 		}
 		ipv6_del_addr(ifp);
+	} else if (ifp->flags&IFA_F_PERMANENT || !dad_failed) {
+		spin_lock_bh(&ifp->lock);
+		addrconf_del_dad_work(ifp);
+		ifp->flags |= IFA_F_TENTATIVE;
+		spin_unlock_bh(&ifp->lock);
+		if (dad_failed)
+			ipv6_ifa_notify(0, ifp);
+		in6_ifa_put(ifp);
 	} else {
 		ipv6_del_addr(ifp);
 	}
-- 
2.13.0


From 3b1ccfadc9c531e346779487ffe46ca25caae5a0 Mon Sep 17 00:00:00 2001
From: Jiri Benc <jbenc@redhat.com>
Date: Sun, 2 Jul 2017 19:00:57 +0200
Subject: [PATCH 18/30] vxlan: fix hlist corruption

[ Upstream commit 69e766612c4bcb79e19cebed9eed61d4222c1d47 ]

It's not a good idea to add the same hlist_node to two different hash lists.
This leads to various hard to debug memory corruptions.

Fixes: b1be00a6c39f ("vxlan: support both IPv4 and IPv6 sockets in a single vxlan device")
Signed-off-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 30 ++++++++++++++++++++----------
 include/net/vxlan.h | 10 +++++++++-
 2 files changed, 29 insertions(+), 11 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 4574b95c7938..3911fd19635d 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -228,15 +228,15 @@ static struct vxlan_sock *vxlan_find_sock(struct net *net, sa_family_t family,
 
 static struct vxlan_dev *vxlan_vs_find_vni(struct vxlan_sock *vs, __be32 vni)
 {
-	struct vxlan_dev *vxlan;
+	struct vxlan_dev_node *node;
 
 	/* For flow based devices, map all packets to VNI 0 */
 	if (vs->flags & VXLAN_F_COLLECT_METADATA)
 		vni = 0;
 
-	hlist_for_each_entry_rcu(vxlan, vni_head(vs, vni), hlist) {
-		if (vxlan->default_dst.remote_vni == vni)
-			return vxlan;
+	hlist_for_each_entry_rcu(node, vni_head(vs, vni), hlist) {
+		if (node->vxlan->default_dst.remote_vni == vni)
+			return node->vxlan;
 	}
 
 	return NULL;
@@ -2361,17 +2361,22 @@ static void vxlan_vs_del_dev(struct vxlan_dev *vxlan)
 	struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
 
 	spin_lock(&vn->sock_lock);
-	hlist_del_init_rcu(&vxlan->hlist);
+	hlist_del_init_rcu(&vxlan->hlist4.hlist);
+#if IS_ENABLED(CONFIG_IPV6)
+	hlist_del_init_rcu(&vxlan->hlist6.hlist);
+#endif
 	spin_unlock(&vn->sock_lock);
 }
 
-static void vxlan_vs_add_dev(struct vxlan_sock *vs, struct vxlan_dev *vxlan)
+static void vxlan_vs_add_dev(struct vxlan_sock *vs, struct vxlan_dev *vxlan,
+			     struct vxlan_dev_node *node)
 {
 	struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
 	__be32 vni = vxlan->default_dst.remote_vni;
 
+	node->vxlan = vxlan;
 	spin_lock(&vn->sock_lock);
-	hlist_add_head_rcu(&vxlan->hlist, vni_head(vs, vni));
+	hlist_add_head_rcu(&node->hlist, vni_head(vs, vni));
 	spin_unlock(&vn->sock_lock);
 }
 
@@ -2817,6 +2822,7 @@ static int __vxlan_sock_add(struct vxlan_dev *vxlan, bool ipv6)
 {
 	struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
 	struct vxlan_sock *vs = NULL;
+	struct vxlan_dev_node *node;
 
 	if (!vxlan->cfg.no_share) {
 		spin_lock(&vn->sock_lock);
@@ -2834,12 +2840,16 @@ static int __vxlan_sock_add(struct vxlan_dev *vxlan, bool ipv6)
 	if (IS_ERR(vs))
 		return PTR_ERR(vs);
 #if IS_ENABLED(CONFIG_IPV6)
-	if (ipv6)
+	if (ipv6) {
 		rcu_assign_pointer(vxlan->vn6_sock, vs);
-	else
+		node = &vxlan->hlist6;
+	} else
 #endif
+	{
 		rcu_assign_pointer(vxlan->vn4_sock, vs);
-	vxlan_vs_add_dev(vs, vxlan);
+		node = &vxlan->hlist4;
+	}
+	vxlan_vs_add_dev(vs, vxlan, node);
 	return 0;
 }
 
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 49a59202f85e..da7d6b89df77 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -221,9 +221,17 @@ struct vxlan_config {
 	bool			no_share;
 };
 
+struct vxlan_dev_node {
+	struct hlist_node hlist;
+	struct vxlan_dev *vxlan;
+};
+
 /* Pseudo network device */
 struct vxlan_dev {
-	struct hlist_node hlist;	/* vni hash table */
+	struct vxlan_dev_node hlist4;	/* vni hash table for IPv4 socket */
+#if IS_ENABLED(CONFIG_IPV6)
+	struct vxlan_dev_node hlist6;	/* vni hash table for IPv6 socket */
+#endif
 	struct list_head  next;		/* vxlan's per namespace list */
 	struct vxlan_sock __rcu *vn4_sock;	/* listening socket for IPv4 */
 #if IS_ENABLED(CONFIG_IPV6)
-- 
2.13.0


From e5e0660fd14c428e5c3c60782e371f2b1413f49e Mon Sep 17 00:00:00 2001
From: Jiri Benc <jbenc@redhat.com>
Date: Sun, 2 Jul 2017 19:00:58 +0200
Subject: [PATCH 19/30] geneve: fix hlist corruption

[ Upstream commit 4b4c21fad6ae6bd58ff1566f23b0f4f70fdc9a30 ]

It's not a good idea to add the same hlist_node to two different hash lists.
This leads to various hard to debug memory corruptions.

Fixes: 8ed66f0e8235 ("geneve: implement support for IPv6-based tunnels")
Cc: John W. Linville <linville@tuxdriver.com>
Signed-off-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c | 48 ++++++++++++++++++++++++++++++++----------------
 1 file changed, 32 insertions(+), 16 deletions(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 199459bd6961..6ec8fc9aad8f 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -45,9 +45,17 @@ struct geneve_net {
 
 static unsigned int geneve_net_id;
 
+struct geneve_dev_node {
+	struct hlist_node hlist;
+	struct geneve_dev *geneve;
+};
+
 /* Pseudo network device */
 struct geneve_dev {
-	struct hlist_node  hlist;	/* vni hash table */
+	struct geneve_dev_node hlist4;	/* vni hash table for IPv4 socket */
+#if IS_ENABLED(CONFIG_IPV6)
+	struct geneve_dev_node hlist6;	/* vni hash table for IPv6 socket */
+#endif
 	struct net	   *net;	/* netns for packet i/o */
 	struct net_device  *dev;	/* netdev for geneve tunnel */
 	struct ip_tunnel_info info;
@@ -123,16 +131,16 @@ static struct geneve_dev *geneve_lookup(struct geneve_sock *gs,
 					__be32 addr, u8 vni[])
 {
 	struct hlist_head *vni_list_head;
-	struct geneve_dev *geneve;
+	struct geneve_dev_node *node;
 	__u32 hash;
 
 	/* Find the device for this VNI */
 	hash = geneve_net_vni_hash(vni);
 	vni_list_head = &gs->vni_list[hash];
-	hlist_for_each_entry_rcu(geneve, vni_list_head, hlist) {
-		if (eq_tun_id_and_vni((u8 *)&geneve->info.key.tun_id, vni) &&
-		    addr == geneve->info.key.u.ipv4.dst)
-			return geneve;
+	hlist_for_each_entry_rcu(node, vni_list_head, hlist) {
+		if (eq_tun_id_and_vni((u8 *)&node->geneve->info.key.tun_id, vni) &&
+		    addr == node->geneve->info.key.u.ipv4.dst)
+			return node->geneve;
 	}
 	return NULL;
 }
@@ -142,16 +150,16 @@ static struct geneve_dev *geneve6_lookup(struct geneve_sock *gs,
 					 struct in6_addr addr6, u8 vni[])
 {
 	struct hlist_head *vni_list_head;
-	struct geneve_dev *geneve;
+	struct geneve_dev_node *node;
 	__u32 hash;
 
 	/* Find the device for this VNI */
 	hash = geneve_net_vni_hash(vni);
 	vni_list_head = &gs->vni_list[hash];
-	hlist_for_each_entry_rcu(geneve, vni_list_head, hlist) {
-		if (eq_tun_id_and_vni((u8 *)&geneve->info.key.tun_id, vni) &&
-		    ipv6_addr_equal(&addr6, &geneve->info.key.u.ipv6.dst))
-			return geneve;
+	hlist_for_each_entry_rcu(node, vni_list_head, hlist) {
+		if (eq_tun_id_and_vni((u8 *)&node->geneve->info.key.tun_id, vni) &&
+		    ipv6_addr_equal(&addr6, &node->geneve->info.key.u.ipv6.dst))
+			return node->geneve;
 	}
 	return NULL;
 }
@@ -579,6 +587,7 @@ static int geneve_sock_add(struct geneve_dev *geneve, bool ipv6)
 {
 	struct net *net = geneve->net;
 	struct geneve_net *gn = net_generic(net, geneve_net_id);
+	struct geneve_dev_node *node;
 	struct geneve_sock *gs;
 	__u8 vni[3];
 	__u32 hash;
@@ -597,15 +606,20 @@ static int geneve_sock_add(struct geneve_dev *geneve, bool ipv6)
 out:
 	gs->collect_md = geneve->collect_md;
 #if IS_ENABLED(CONFIG_IPV6)
-	if (ipv6)
+	if (ipv6) {
 		rcu_assign_pointer(geneve->sock6, gs);
-	else
+		node = &geneve->hlist6;
+	} else
 #endif
+	{
 		rcu_assign_pointer(geneve->sock4, gs);
+		node = &geneve->hlist4;
+	}
+	node->geneve = geneve;
 
 	tunnel_id_to_vni(geneve->info.key.tun_id, vni);
 	hash = geneve_net_vni_hash(vni);
-	hlist_add_head_rcu(&geneve->hlist, &gs->vni_list[hash]);
+	hlist_add_head_rcu(&node->hlist, &gs->vni_list[hash]);
 	return 0;
 }
 
@@ -632,8 +646,10 @@ static int geneve_stop(struct net_device *dev)
 {
 	struct geneve_dev *geneve = netdev_priv(dev);
 
-	if (!hlist_unhashed(&geneve->hlist))
-		hlist_del_rcu(&geneve->hlist);
+	hlist_del_init_rcu(&geneve->hlist4.hlist);
+#if IS_ENABLED(CONFIG_IPV6)
+	hlist_del_init_rcu(&geneve->hlist6.hlist);
+#endif
 	geneve_sock_release(geneve);
 	return 0;
 }
-- 
2.13.0


From a23cf5f9b18e71f1eca4fa040a8ae4596580db48 Mon Sep 17 00:00:00 2001
From: Alban Browaeys <alban.browaeys@gmail.com>
Date: Mon, 3 Jul 2017 03:20:13 +0200
Subject: [PATCH 20/30] net: core: Fix slab-out-of-bounds in
 netdev_stats_to_stats64

[ Upstream commit 9af9959e142c274f4a30fefb71d97d2b028b337f ]

commit 9256645af098 ("net/core: relax BUILD_BUG_ON in
netdev_stats_to_stats64") made an attempt to read beyond
the size of the source a possibility.

Fix to only copy src size to dest. As dest might be bigger than src.

 ==================================================================
 BUG: KASAN: slab-out-of-bounds in netdev_stats_to_stats64+0xe/0x30 at addr ffff8801be248b20
 Read of size 192 by task VBoxNetAdpCtl/6734
 CPU: 1 PID: 6734 Comm: VBoxNetAdpCtl Tainted: G           O    4.11.4prahal+intel+ #118
 Hardware name: LENOVO 20CDCTO1WW/20CDCTO1WW, BIOS GQET52WW (1.32 ) 05/04/2017
 Call Trace:
  dump_stack+0x63/0x86
  kasan_object_err+0x1c/0x70
  kasan_report+0x270/0x520
  ? netdev_stats_to_stats64+0xe/0x30
  ? sched_clock_cpu+0x1b/0x190
  ? __module_address+0x3e/0x3b0
  ? unwind_next_frame+0x1ea/0xb00
  check_memory_region+0x13c/0x1a0
  memcpy+0x23/0x50
  netdev_stats_to_stats64+0xe/0x30
  dev_get_stats+0x1b9/0x230
  rtnl_fill_stats+0x44/0xc00
  ? nla_put+0xc6/0x130
  rtnl_fill_ifinfo+0xe9e/0x3700
  ? rtnl_fill_vfinfo+0xde0/0xde0
  ? sched_clock+0x9/0x10
  ? sched_clock+0x9/0x10
  ? sched_clock_local+0x120/0x130
  ? __module_address+0x3e/0x3b0
  ? unwind_next_frame+0x1ea/0xb00
  ? sched_clock+0x9/0x10
  ? sched_clock+0x9/0x10
  ? sched_clock_cpu+0x1b/0x190
  ? VBoxNetAdpLinuxIOCtlUnlocked+0x14b/0x280 [vboxnetadp]
  ? depot_save_stack+0x1d8/0x4a0
  ? depot_save_stack+0x34f/0x4a0
  ? depot_save_stack+0x34f/0x4a0
  ? save_stack+0xb1/0xd0
  ? save_stack_trace+0x16/0x20
  ? save_stack+0x46/0xd0
  ? kasan_slab_alloc+0x12/0x20
  ? __kmalloc_node_track_caller+0x10d/0x350
  ? __kmalloc_reserve.isra.36+0x2c/0xc0
  ? __alloc_skb+0xd0/0x560
  ? rtmsg_ifinfo_build_skb+0x61/0x120
  ? rtmsg_ifinfo.part.25+0x16/0xb0
  ? rtmsg_ifinfo+0x47/0x70
  ? register_netdev+0x15/0x30
  ? vboxNetAdpOsCreate+0xc0/0x1c0 [vboxnetadp]
  ? vboxNetAdpCreate+0x210/0x400 [vboxnetadp]
  ? VBoxNetAdpLinuxIOCtlUnlocked+0x14b/0x280 [vboxnetadp]
  ? do_vfs_ioctl+0x17f/0xff0
  ? SyS_ioctl+0x74/0x80
  ? do_syscall_64+0x182/0x390
  ? __alloc_skb+0xd0/0x560
  ? __alloc_skb+0xd0/0x560
  ? save_stack_trace+0x16/0x20
  ? init_object+0x64/0xa0
  ? ___slab_alloc+0x1ae/0x5c0
  ? ___slab_alloc+0x1ae/0x5c0
  ? __alloc_skb+0xd0/0x560
  ? sched_clock+0x9/0x10
  ? kasan_unpoison_shadow+0x35/0x50
  ? kasan_kmalloc+0xad/0xe0
  ? __kmalloc_node_track_caller+0x246/0x350
  ? __alloc_skb+0xd0/0x560
  ? kasan_unpoison_shadow+0x35/0x50
  ? memset+0x31/0x40
  ? __alloc_skb+0x31f/0x560
  ? napi_consume_skb+0x320/0x320
  ? br_get_link_af_size_filtered+0xb7/0x120 [bridge]
  ? if_nlmsg_size+0x440/0x630
  rtmsg_ifinfo_build_skb+0x83/0x120
  rtmsg_ifinfo.part.25+0x16/0xb0
  rtmsg_ifinfo+0x47/0x70
  register_netdevice+0xa2b/0xe50
  ? __kmalloc+0x171/0x2d0
  ? netdev_change_features+0x80/0x80
  register_netdev+0x15/0x30
  vboxNetAdpOsCreate+0xc0/0x1c0 [vboxnetadp]
  vboxNetAdpCreate+0x210/0x400 [vboxnetadp]
  ? vboxNetAdpComposeMACAddress+0x1d0/0x1d0 [vboxnetadp]
  ? kasan_check_write+0x14/0x20
  VBoxNetAdpLinuxIOCtlUnlocked+0x14b/0x280 [vboxnetadp]
  ? VBoxNetAdpLinuxOpen+0x20/0x20 [vboxnetadp]
  ? lock_acquire+0x11c/0x270
  ? __audit_syscall_entry+0x2fb/0x660
  do_vfs_ioctl+0x17f/0xff0
  ? __audit_syscall_entry+0x2fb/0x660
  ? ioctl_preallocate+0x1d0/0x1d0
  ? __audit_syscall_entry+0x2fb/0x660
  ? kmem_cache_free+0xb2/0x250
  ? syscall_trace_enter+0x537/0xd00
  ? exit_to_usermode_loop+0x100/0x100
  SyS_ioctl+0x74/0x80
  ? do_sys_open+0x350/0x350
  ? do_vfs_ioctl+0xff0/0xff0
  do_syscall_64+0x182/0x390
  entry_SYSCALL64_slow_path+0x25/0x25
 RIP: 0033:0x7f7e39a1ae07
 RSP: 002b:00007ffc6f04c6d8 EFLAGS: 00000206 ORIG_RAX: 0000000000000010
 RAX: ffffffffffffffda RBX: 00007ffc6f04c730 RCX: 00007f7e39a1ae07
 RDX: 00007ffc6f04c730 RSI: 00000000c0207601 RDI: 0000000000000007
 RBP: 00007ffc6f04c700 R08: 00007ffc6f04c780 R09: 0000000000000008
 R10: 0000000000000541 R11: 0000000000000206 R12: 0000000000000007
 R13: 00000000c0207601 R14: 00007ffc6f04c730 R15: 0000000000000012
 Object at ffff8801be248008, in cache kmalloc-4096 size: 4096
 Allocated:
 PID = 6734
  save_stack_trace+0x16/0x20
  save_stack+0x46/0xd0
  kasan_kmalloc+0xad/0xe0
  __kmalloc+0x171/0x2d0
  alloc_netdev_mqs+0x8a7/0xbe0
  vboxNetAdpOsCreate+0x65/0x1c0 [vboxnetadp]
  vboxNetAdpCreate+0x210/0x400 [vboxnetadp]
  VBoxNetAdpLinuxIOCtlUnlocked+0x14b/0x280 [vboxnetadp]
  do_vfs_ioctl+0x17f/0xff0
  SyS_ioctl+0x74/0x80
  do_syscall_64+0x182/0x390
  return_from_SYSCALL_64+0x0/0x6a
 Freed:
 PID = 5600
  save_stack_trace+0x16/0x20
  save_stack+0x46/0xd0
  kasan_slab_free+0x73/0xc0
  kfree+0xe4/0x220
  kvfree+0x25/0x30
  single_release+0x74/0xb0
  __fput+0x265/0x6b0
  ____fput+0x9/0x10
  task_work_run+0xd5/0x150
  exit_to_usermode_loop+0xe2/0x100
  do_syscall_64+0x26c/0x390
  return_from_SYSCALL_64+0x0/0x6a
 Memory state around the buggy address:
  ffff8801be248a80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
  ffff8801be248b00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
 >ffff8801be248b80: 00 00 00 00 00 00 00 00 00 00 00 07 fc fc fc fc
                                                     ^
  ffff8801be248c00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
  ffff8801be248c80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 ==================================================================

Signed-off-by: Alban Browaeys <alban.browaeys@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 1f664e54096c..84d27d3145f9 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7591,7 +7591,7 @@ void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64,
 {
 #if BITS_PER_LONG == 64
 	BUILD_BUG_ON(sizeof(*stats64) < sizeof(*netdev_stats));
-	memcpy(stats64, netdev_stats, sizeof(*stats64));
+	memcpy(stats64, netdev_stats, sizeof(*netdev_stats));
 	/* zero out counters that only exist in rtnl_link_stats64 */
 	memset((char *)stats64 + sizeof(*netdev_stats), 0,
 	       sizeof(*stats64) - sizeof(*netdev_stats));
-- 
2.13.0


From c5c73b7828d01011835e5bc933171f6d82e28eb7 Mon Sep 17 00:00:00 2001
From: Derek Chickles <derek.chickles@cavium.com>
Date: Wed, 5 Jul 2017 11:59:27 -0700
Subject: [PATCH 21/30] liquidio: fix bug in soft reset failure detection

[ Upstream commit 05a6b4cae8c0cc1680c9dd33a97a49a13c0f01bc ]

The code that detects a failed soft reset of Octeon is comparing the wrong
value against the reset value of the Octeon SLI_SCRATCH_1 register,
resulting in an inability to detect a soft reset failure.  Fix it by using
the correct value in the comparison, which is any non-zero value.

Fixes: f21fb3ed364b ("Add support of Cavium Liquidio ethernet adapters")
Fixes: c0eab5b3580a ("liquidio: CN23XX firmware download")
Signed-off-by: Derek Chickles <derek.chickles@cavium.com>
Signed-off-by: Satanand Burla <satananda.burla@cavium.com>
Signed-off-by: Raghu Vatsavayi <raghu.vatsavayi@cavium.com>
Signed-off-by: Felix Manlunas <felix.manlunas@cavium.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c | 2 +-
 drivers/net/ethernet/cavium/liquidio/cn66xx_device.c    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
index 962dcbcef8b5..0dcda0b9b0cc 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
@@ -221,7 +221,7 @@ static int cn23xx_pf_soft_reset(struct octeon_device *oct)
 	/* Wait for 100ms as Octeon resets. */
 	mdelay(100);
 
-	if (octeon_read_csr64(oct, CN23XX_SLI_SCRATCH1) == 0x1234ULL) {
+	if (octeon_read_csr64(oct, CN23XX_SLI_SCRATCH1)) {
 		dev_err(&oct->pci_dev->dev, "OCTEON[%d]: Soft reset failed\n",
 			oct->octeon_id);
 		return 1;
diff --git a/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c b/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c
index bdec051107a6..d62a5096768e 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c
@@ -44,7 +44,7 @@ int lio_cn6xxx_soft_reset(struct octeon_device *oct)
 	/* Wait for 10ms as Octeon resets. */
 	mdelay(100);
 
-	if (octeon_read_csr64(oct, CN6XXX_SLI_SCRATCH1) == 0x1234ULL) {
+	if (octeon_read_csr64(oct, CN6XXX_SLI_SCRATCH1)) {
 		dev_err(&oct->pci_dev->dev, "Soft reset failed\n");
 		return 1;
 	}
-- 
2.13.0


From adb3c99003290594e96d0add7f60ecea34019523 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 5 Jul 2017 14:41:46 -0600
Subject: [PATCH 22/30] net: ipv6: Compare lwstate in detecting duplicate
 nexthops
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit f06b7549b79e29a672336d4e134524373fb7a232 ]

Lennert reported a failure to add different mpls encaps in a multipath
route:

  $ ip -6 route add 1234::/16 \
        nexthop encap mpls 10 via fe80::1 dev ens3 \
        nexthop encap mpls 20 via fe80::1 dev ens3
  RTNETLINK answers: File exists

The problem is that the duplicate nexthop detection does not compare
lwtunnel configuration. Add it.

Fixes: 19e42e451506 ("ipv6: support for fib route lwtunnel encap attributes")
Signed-off-by: David Ahern <dsahern@gmail.com>
Reported-by: João Taveira Araújo <joao.taveira@gmail.com>
Reported-by: Lennert Buytenhek <buytenh@wantstofly.org>
Acked-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Tested-by: Lennert Buytenhek <buytenh@wantstofly.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_route.h | 8 ++++++++
 net/ipv6/ip6_fib.c      | 5 +----
 net/ipv6/route.c        | 8 +-------
 3 files changed, 10 insertions(+), 11 deletions(-)

diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index f5e625f53367..4341731f39a5 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -22,6 +22,7 @@ struct route_info {
 #include <net/flow.h>
 #include <net/ip6_fib.h>
 #include <net/sock.h>
+#include <net/lwtunnel.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/route.h>
@@ -233,4 +234,11 @@ static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt,
 		return daddr;
 }
 
+static inline bool rt6_duplicate_nexthop(struct rt6_info *a, struct rt6_info *b)
+{
+	return a->dst.dev == b->dst.dev &&
+	       a->rt6i_idev == b->rt6i_idev &&
+	       ipv6_addr_equal(&a->rt6i_gateway, &b->rt6i_gateway) &&
+	       !lwtunnel_cmp_encap(a->dst.lwtstate, b->dst.lwtstate);
+}
 #endif
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index e6b78ba0e636..e4e9f752ebbf 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -784,10 +784,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 				goto next_iter;
 			}
 
-			if (iter->dst.dev == rt->dst.dev &&
-			    iter->rt6i_idev == rt->rt6i_idev &&
-			    ipv6_addr_equal(&iter->rt6i_gateway,
-					    &rt->rt6i_gateway)) {
+			if (rt6_duplicate_nexthop(iter, rt)) {
 				if (rt->rt6i_nsiblings)
 					rt->rt6i_nsiblings = 0;
 				if (!(iter->rt6i_flags & RTF_EXPIRES))
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 1072fc189708..78a54eedf739 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3047,17 +3047,11 @@ static int ip6_route_info_append(struct list_head *rt6_nh_list,
 				 struct rt6_info *rt, struct fib6_config *r_cfg)
 {
 	struct rt6_nh *nh;
-	struct rt6_info *rtnh;
 	int err = -EEXIST;
 
 	list_for_each_entry(nh, rt6_nh_list, next) {
 		/* check if rt6_info already exists */
-		rtnh = nh->rt6_info;
-
-		if (rtnh->dst.dev == rt->dst.dev &&
-		    rtnh->rt6i_idev == rt->rt6i_idev &&
-		    ipv6_addr_equal(&rtnh->rt6i_gateway,
-				    &rt->rt6i_gateway))
+		if (rt6_duplicate_nexthop(nh->rt6_info, rt))
 			return err;
 	}
 
-- 
2.13.0


From ccad1e34c758cccecbc500f1ae80acdec07b408d Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Thu, 6 Jul 2017 15:24:40 +0300
Subject: [PATCH 23/30] vrf: fix bug_on triggered by rx when destroying a vrf

[ Upstream commit f630c38ef0d785101363a8992bbd4f302180f86f ]

When destroying a VRF device we cleanup the slaves in its ndo_uninit()
function, but that causes packets to be switched (skb->dev == vrf being
destroyed) even though we're pass the point where the VRF should be
receiving any packets while it is being dismantled. This causes a BUG_ON
to trigger if we have raw sockets (trace below).
The reason is that the inetdev of the VRF has been destroyed but we're
still sending packets up the stack with it, so let's free the slaves in
the dellink callback as David Ahern suggested.

Note that this fix doesn't prevent packets from going up when the VRF
device is admin down.

[   35.631371] ------------[ cut here ]------------
[   35.631603] kernel BUG at net/ipv4/fib_frontend.c:285!
[   35.631854] invalid opcode: 0000 [#1] SMP
[   35.631977] Modules linked in:
[   35.632081] CPU: 2 PID: 22 Comm: ksoftirqd/2 Not tainted 4.12.0-rc7+ #45
[   35.632247] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.7.5-20140531_083030-gandalf 04/01/2014
[   35.632477] task: ffff88005ad68000 task.stack: ffff88005ad64000
[   35.632632] RIP: 0010:fib_compute_spec_dst+0xfc/0x1ee
[   35.632769] RSP: 0018:ffff88005ad67978 EFLAGS: 00010202
[   35.632910] RAX: 0000000000000001 RBX: ffff880059a7f200 RCX: 0000000000000000
[   35.633084] RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffffffff82274af0
[   35.633256] RBP: ffff88005ad679f8 R08: 000000000001ef70 R09: 0000000000000046
[   35.633430] R10: ffff88005ad679f8 R11: ffff880037731cb0 R12: 0000000000000001
[   35.633603] R13: ffff8800599e3000 R14: 0000000000000000 R15: ffff8800599cb852
[   35.634114] FS:  0000000000000000(0000) GS:ffff88005d900000(0000) knlGS:0000000000000000
[   35.634306] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   35.634456] CR2: 00007f3563227095 CR3: 000000000201d000 CR4: 00000000000406e0
[   35.634632] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[   35.634865] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[   35.635055] Call Trace:
[   35.635271]  ? __lock_acquire+0xf0d/0x1117
[   35.635522]  ipv4_pktinfo_prepare+0x82/0x151
[   35.635831]  raw_rcv_skb+0x17/0x3c
[   35.636062]  raw_rcv+0xe5/0xf7
[   35.636287]  raw_local_deliver+0x169/0x1d9
[   35.636534]  ip_local_deliver_finish+0x87/0x1c4
[   35.636820]  ip_local_deliver+0x63/0x7f
[   35.637058]  ip_rcv_finish+0x340/0x3a1
[   35.637295]  ip_rcv+0x314/0x34a
[   35.637525]  __netif_receive_skb_core+0x49f/0x7c5
[   35.637780]  ? lock_acquire+0x13f/0x1d7
[   35.638018]  ? lock_acquire+0x15e/0x1d7
[   35.638259]  __netif_receive_skb+0x1e/0x94
[   35.638502]  ? __netif_receive_skb+0x1e/0x94
[   35.638748]  netif_receive_skb_internal+0x74/0x300
[   35.639002]  ? dev_gro_receive+0x2ed/0x411
[   35.639246]  ? lock_is_held_type+0xc4/0xd2
[   35.639491]  napi_gro_receive+0x105/0x1a0
[   35.639736]  receive_buf+0xc32/0xc74
[   35.639965]  ? detach_buf+0x67/0x153
[   35.640201]  ? virtqueue_get_buf_ctx+0x120/0x176
[   35.640453]  virtnet_poll+0x128/0x1c5
[   35.640690]  net_rx_action+0x103/0x343
[   35.640932]  __do_softirq+0x1c7/0x4b7
[   35.641171]  run_ksoftirqd+0x23/0x5c
[   35.641403]  smpboot_thread_fn+0x24f/0x26d
[   35.641646]  ? sort_range+0x22/0x22
[   35.641878]  kthread+0x129/0x131
[   35.642104]  ? __list_add+0x31/0x31
[   35.642335]  ? __list_add+0x31/0x31
[   35.642568]  ret_from_fork+0x2a/0x40
[   35.642804] Code: 05 bd 87 a3 00 01 e8 1f ef 98 ff 4d 85 f6 48 c7 c7 f0 4a 27 82 41 0f 94 c4 31 c9 31 d2 41 0f b6 f4 e8 04 71 a1 ff 45 84 e4 74 02 <0f> 0b 0f b7 93 c4 00 00 00 4d 8b a5 80 05 00 00 48 03 93 d0 00
[   35.644342] RIP: fib_compute_spec_dst+0xfc/0x1ee RSP: ffff88005ad67978

Fixes: 193125dbd8eb ("net: Introduce VRF device driver")
Reported-by: Chris Cormier <chriscormier@cumulusnetworks.com>
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 2e62c4d1b220..608ecaf16fe4 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -788,15 +788,10 @@ static int vrf_del_slave(struct net_device *dev, struct net_device *port_dev)
 static void vrf_dev_uninit(struct net_device *dev)
 {
 	struct net_vrf *vrf = netdev_priv(dev);
-	struct net_device *port_dev;
-	struct list_head *iter;
 
 	vrf_rtable_release(dev, vrf);
 	vrf_rt6_release(dev, vrf);
 
-	netdev_for_each_lower_dev(dev, port_dev, iter)
-		vrf_del_slave(dev, port_dev);
-
 	free_percpu(dev->dstats);
 	dev->dstats = NULL;
 }
@@ -1247,6 +1242,12 @@ static int vrf_validate(struct nlattr *tb[], struct nlattr *data[])
 
 static void vrf_dellink(struct net_device *dev, struct list_head *head)
 {
+	struct net_device *port_dev;
+	struct list_head *iter;
+
+	netdev_for_each_lower_dev(dev, port_dev, iter)
+		vrf_del_slave(dev, port_dev);
+
 	unregister_netdevice_queue(dev, head);
 }
 
-- 
2.13.0


From 905cfaabb02e92e6372ed8072ff5e8baf59f150a Mon Sep 17 00:00:00 2001
From: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Date: Thu, 6 Jul 2017 08:15:06 -0700
Subject: [PATCH 24/30] rds: tcp: use sock_create_lite() to create the accept
 socket

[ Upstream commit 0933a578cd55b02dc80f219dc8f2efb17ec61c9a ]

There are two problems with calling sock_create_kern() from
rds_tcp_accept_one()
1. it sets up a new_sock->sk that is wasteful, because this ->sk
   is going to get replaced by inet_accept() in the subsequent ->accept()
2. The new_sock->sk is a leaked reference in sock_graft() which
   expects to find a null parent->sk

Avoid these problems by calling sock_create_lite().

Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/tcp_listen.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index 507678853e6c..9a1798d6ae94 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -125,7 +125,7 @@ int rds_tcp_accept_one(struct socket *sock)
 	if (!sock) /* module unload or netns delete in progress */
 		return -ENETUNREACH;
 
-	ret = sock_create_kern(sock_net(sock->sk), sock->sk->sk_family,
+	ret = sock_create_lite(sock->sk->sk_family,
 			       sock->sk->sk_type, sock->sk->sk_protocol,
 			       &new_sock);
 	if (ret)
-- 
2.13.0


From 2a792f82a14c65872e9742471d1f41e58272ef2a Mon Sep 17 00:00:00 2001
From: Huy Nguyen <huyn@mellanox.com>
Date: Thu, 29 Jun 2017 16:50:01 -0500
Subject: [PATCH 25/30] net/mlx5e: Initialize CEE's getpermhwaddr address
 buffer to 0xff

[ Upstream commit d968f0f2e4404152f37ed2384b4a2269dd2dae5a ]

Latest change in open-lldp code uses bytes 6-11 of perm_addr buffer
as the Ethernet source address for the host TLV packet.
Since our driver does not fill these bytes, they stay at zero and
the open-lldp code ends up sending the TLV packet with zero source
address and the switch drops this packet.

The fix is to initialize these bytes to 0xff. The open-lldp code
considers 0xff:ff:ff:ff:ff:ff as the invalid address and falls back to
use the host's mac address as the Ethernet source address.

Fixes: 3a6a931dfb8e ("net/mlx5e: Support DCBX CEE API")
Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index 8fa23f6a1f67..2eb54d36e16e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -464,6 +464,8 @@ static void mlx5e_dcbnl_getpermhwaddr(struct net_device *netdev,
 	if (!perm_addr)
 		return;
 
+	memset(perm_addr, 0xff, MAX_ADDR_LEN);
+
 	mlx5_query_nic_vport_mac_address(priv->mdev, 0, perm_addr);
 }
 
-- 
2.13.0


From 22abe270317dee2cd736d5d91d53d2736103efa9 Mon Sep 17 00:00:00 2001
From: "Guilherme G. Piccoli" <gpiccoli@linux.vnet.ibm.com>
Date: Mon, 10 Jul 2017 10:55:46 -0300
Subject: [PATCH 26/30] cxgb4: fix BUG() on interrupt deallocating path of ULD

[ Upstream commit 6a146f3a5894b751cef16feb3d7903e45e3c445c ]

Since the introduction of ULD (Upper-Layer Drivers), the MSI-X
deallocating path changed in cxgb4: the driver frees the interrupts
of ULD when unregistering it or on shutdown PCI handler.

Problem is that if a MSI-X is not freed before deallocated in the PCI
layer, it will trigger a BUG() due to still "alive" interrupt being
tentatively quiesced.

The below trace was observed when doing a simple unbind of Chelsio's
adapter PCI function, like:
  "echo 001e:80:00.4 > /sys/bus/pci/drivers/cxgb4/unbind"

Trace:

  kernel BUG at drivers/pci/msi.c:352!
  Oops: Exception in kernel mode, sig: 5 [#1]
  ...
  NIP [c0000000005a5e60] free_msi_irqs+0xa0/0x250
  LR [c0000000005a5e50] free_msi_irqs+0x90/0x250
  Call Trace:
  [c0000000005a5e50] free_msi_irqs+0x90/0x250 (unreliable)
  [c0000000005a72c4] pci_disable_msix+0x124/0x180
  [d000000011e06708] disable_msi+0x88/0xb0 [cxgb4]
  [d000000011e06948] free_some_resources+0xa8/0x160 [cxgb4]
  [d000000011e06d60] remove_one+0x170/0x3c0 [cxgb4]
  [c00000000058a910] pci_device_remove+0x70/0x110
  [c00000000064ef04] device_release_driver_internal+0x1f4/0x2c0
  ...

This patch fixes the issue by refactoring the shutdown path of ULD on
cxgb4 driver, by properly freeing and disabling interrupts on PCI
remove handler too.

Fixes: 0fbc81b3ad51 ("Allocate resources dynamically for all cxgb4 ULD's")
Reported-by: Harsha Thyagaraja <hathyaga@in.ibm.com>
Signed-off-by: Guilherme G. Piccoli <gpiccoli@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 16 +++++++---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c  | 42 +++++++++++++++----------
 2 files changed, 36 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index fb0951929be9..10c85d3525a4 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -2076,12 +2076,12 @@ static void detach_ulds(struct adapter *adap)
 
 	mutex_lock(&uld_mutex);
 	list_del(&adap->list_node);
+
 	for (i = 0; i < CXGB4_ULD_MAX; i++)
-		if (adap->uld && adap->uld[i].handle) {
+		if (adap->uld && adap->uld[i].handle)
 			adap->uld[i].state_change(adap->uld[i].handle,
 					     CXGB4_STATE_DETACH);
-			adap->uld[i].handle = NULL;
-		}
+
 	if (netevent_registered && list_empty(&adapter_list)) {
 		unregister_netevent_notifier(&cxgb4_netevent_nb);
 		netevent_registered = false;
@@ -5089,8 +5089,10 @@ static void remove_one(struct pci_dev *pdev)
 		 */
 		destroy_workqueue(adapter->workq);
 
-		if (is_uld(adapter))
+		if (is_uld(adapter)) {
 			detach_ulds(adapter);
+			t4_uld_clean_up(adapter);
+		}
 
 		disable_interrupts(adapter);
 
@@ -5167,7 +5169,11 @@ static void shutdown_one(struct pci_dev *pdev)
 			if (adapter->port[i]->reg_state == NETREG_REGISTERED)
 				cxgb_close(adapter->port[i]);
 
-		t4_uld_clean_up(adapter);
+		if (is_uld(adapter)) {
+			detach_ulds(adapter);
+			t4_uld_clean_up(adapter);
+		}
+
 		disable_interrupts(adapter);
 		disable_msi(adapter);
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
index d0868c2320da..dbbc2b7f0d46 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
@@ -589,22 +589,37 @@ void t4_uld_mem_free(struct adapter *adap)
 	kfree(adap->uld);
 }
 
+/* This function should be called with uld_mutex taken. */
+static void cxgb4_shutdown_uld_adapter(struct adapter *adap, enum cxgb4_uld type)
+{
+	if (adap->uld[type].handle) {
+		adap->uld[type].handle = NULL;
+		adap->uld[type].add = NULL;
+		release_sge_txq_uld(adap, type);
+
+		if (adap->flags & FULL_INIT_DONE)
+			quiesce_rx_uld(adap, type);
+
+		if (adap->flags & USING_MSIX)
+			free_msix_queue_irqs_uld(adap, type);
+
+		free_sge_queues_uld(adap, type);
+		free_queues_uld(adap, type);
+	}
+}
+
 void t4_uld_clean_up(struct adapter *adap)
 {
 	unsigned int i;
 
-	if (!adap->uld)
-		return;
+	mutex_lock(&uld_mutex);
 	for (i = 0; i < CXGB4_ULD_MAX; i++) {
 		if (!adap->uld[i].handle)
 			continue;
-		if (adap->flags & FULL_INIT_DONE)
-			quiesce_rx_uld(adap, i);
-		if (adap->flags & USING_MSIX)
-			free_msix_queue_irqs_uld(adap, i);
-		free_sge_queues_uld(adap, i);
-		free_queues_uld(adap, i);
+
+		cxgb4_shutdown_uld_adapter(adap, i);
 	}
+	mutex_unlock(&uld_mutex);
 }
 
 static void uld_init(struct adapter *adap, struct cxgb4_lld_info *lld)
@@ -782,15 +797,8 @@ int cxgb4_unregister_uld(enum cxgb4_uld type)
 			continue;
 		if (type == CXGB4_ULD_ISCSIT && is_t4(adap->params.chip))
 			continue;
-		adap->uld[type].handle = NULL;
-		adap->uld[type].add = NULL;
-		release_sge_txq_uld(adap, type);
-		if (adap->flags & FULL_INIT_DONE)
-			quiesce_rx_uld(adap, type);
-		if (adap->flags & USING_MSIX)
-			free_msix_queue_irqs_uld(adap, type);
-		free_sge_queues_uld(adap, type);
-		free_queues_uld(adap, type);
+
+		cxgb4_shutdown_uld_adapter(adap, type);
 	}
 	mutex_unlock(&uld_mutex);
 
-- 
2.13.0


From 716ae312aef18286a4b1da2d25665022be354967 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Mon, 10 Jul 2017 10:05:50 -0700
Subject: [PATCH 27/30] tap: convert a mutex to a spinlock

[ Upstream commit ffa423fb3251f8737303ffc3b0659e86e501808e ]

We are not allowed to block on the RCU reader side, so can't
just hold the mutex as before. As a quick fix, convert it to
a spinlock.

Fixes: d9f1f61c0801 ("tap: Extending tap device create/destroy APIs")
Reported-by: Christian Borntraeger <borntraeger@de.ibm.com>
Tested-by: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Sainath Grandhi <sainath.grandhi@intel.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tap.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index 4d4173d25dd0..d88ae3c2edbf 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -106,7 +106,7 @@ struct major_info {
 	struct rcu_head rcu;
 	dev_t major;
 	struct idr minor_idr;
-	struct mutex minor_lock;
+	spinlock_t minor_lock;
 	const char *device_name;
 	struct list_head next;
 };
@@ -416,15 +416,15 @@ int tap_get_minor(dev_t major, struct tap_dev *tap)
 		goto unlock;
 	}
 
-	mutex_lock(&tap_major->minor_lock);
-	retval = idr_alloc(&tap_major->minor_idr, tap, 1, TAP_NUM_DEVS, GFP_KERNEL);
+	spin_lock(&tap_major->minor_lock);
+	retval = idr_alloc(&tap_major->minor_idr, tap, 1, TAP_NUM_DEVS, GFP_ATOMIC);
 	if (retval >= 0) {
 		tap->minor = retval;
 	} else if (retval == -ENOSPC) {
 		netdev_err(tap->dev, "Too many tap devices\n");
 		retval = -EINVAL;
 	}
-	mutex_unlock(&tap_major->minor_lock);
+	spin_unlock(&tap_major->minor_lock);
 
 unlock:
 	rcu_read_unlock();
@@ -442,12 +442,12 @@ void tap_free_minor(dev_t major, struct tap_dev *tap)
 		goto unlock;
 	}
 
-	mutex_lock(&tap_major->minor_lock);
+	spin_lock(&tap_major->minor_lock);
 	if (tap->minor) {
 		idr_remove(&tap_major->minor_idr, tap->minor);
 		tap->minor = 0;
 	}
-	mutex_unlock(&tap_major->minor_lock);
+	spin_unlock(&tap_major->minor_lock);
 
 unlock:
 	rcu_read_unlock();
@@ -467,13 +467,13 @@ static struct tap_dev *dev_get_by_tap_file(int major, int minor)
 		goto unlock;
 	}
 
-	mutex_lock(&tap_major->minor_lock);
+	spin_lock(&tap_major->minor_lock);
 	tap = idr_find(&tap_major->minor_idr, minor);
 	if (tap) {
 		dev = tap->dev;
 		dev_hold(dev);
 	}
-	mutex_unlock(&tap_major->minor_lock);
+	spin_unlock(&tap_major->minor_lock);
 
 unlock:
 	rcu_read_unlock();
@@ -1227,7 +1227,7 @@ static int tap_list_add(dev_t major, const char *device_name)
 	tap_major->major = MAJOR(major);
 
 	idr_init(&tap_major->minor_idr);
-	mutex_init(&tap_major->minor_lock);
+	spin_lock_init(&tap_major->minor_lock);
 
 	tap_major->device_name = device_name;
 
-- 
2.13.0


From a5ea101e9539efa1f68aeca98fd56236f2b23b40 Mon Sep 17 00:00:00 2001
From: Eduardo Valentin <eduval@amazon.com>
Date: Tue, 11 Jul 2017 14:55:12 -0700
Subject: [PATCH 28/30] bridge: mdb: fix leak on complete_info ptr on fail path

[ Upstream commit 1bfb159673957644951ab0a8d2aec44b93ddb1ae ]

We currently get the following kmemleak report:
unreferenced object 0xffff8800039d9820 (size 32):
  comm "softirq", pid 0, jiffies 4295212383 (age 792.416s)
  hex dump (first 32 bytes):
    00 0c e0 03 00 88 ff ff ff 02 00 00 00 00 00 00  ................
    00 00 00 01 ff 11 00 02 86 dd 00 00 ff ff ff ff  ................
  backtrace:
    [<ffffffff8152b4aa>] kmemleak_alloc+0x4a/0xa0
    [<ffffffff811d8ec8>] kmem_cache_alloc_trace+0xb8/0x1c0
    [<ffffffffa0389683>] __br_mdb_notify+0x2a3/0x300 [bridge]
    [<ffffffffa038a0ce>] br_mdb_notify+0x6e/0x70 [bridge]
    [<ffffffffa0386479>] br_multicast_add_group+0x109/0x150 [bridge]
    [<ffffffffa0386518>] br_ip6_multicast_add_group+0x58/0x60 [bridge]
    [<ffffffffa0387fb5>] br_multicast_rcv+0x1d5/0xdb0 [bridge]
    [<ffffffffa037d7cf>] br_handle_frame_finish+0xcf/0x510 [bridge]
    [<ffffffffa03a236b>] br_nf_hook_thresh.part.27+0xb/0x10 [br_netfilter]
    [<ffffffffa03a3738>] br_nf_hook_thresh+0x48/0xb0 [br_netfilter]
    [<ffffffffa03a3fb9>] br_nf_pre_routing_finish_ipv6+0x109/0x1d0 [br_netfilter]
    [<ffffffffa03a4400>] br_nf_pre_routing_ipv6+0xd0/0x14c [br_netfilter]
    [<ffffffffa03a3c27>] br_nf_pre_routing+0x197/0x3d0 [br_netfilter]
    [<ffffffff814a2952>] nf_iterate+0x52/0x60
    [<ffffffff814a29bc>] nf_hook_slow+0x5c/0xb0
    [<ffffffffa037ddf4>] br_handle_frame+0x1a4/0x2c0 [bridge]

This happens when switchdev_port_obj_add() fails. This patch
frees complete_info object in the fail path.

Reviewed-by: Vallish Vaidyeshwara <vallish@amazon.com>
Signed-off-by: Eduardo Valentin <eduval@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_mdb.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index 056e6ac49d8f..57e94a1b57e1 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -323,7 +323,8 @@ static void __br_mdb_notify(struct net_device *dev, struct net_bridge_port *p,
 			__mdb_entry_to_br_ip(entry, &complete_info->ip);
 			mdb.obj.complete_priv = complete_info;
 			mdb.obj.complete = br_mdb_complete;
-			switchdev_port_obj_add(port_dev, &mdb.obj);
+			if (switchdev_port_obj_add(port_dev, &mdb.obj))
+				kfree(complete_info);
 		}
 	} else if (port_dev && type == RTM_DELMDB) {
 		switchdev_port_obj_del(port_dev, &mdb.obj);
-- 
2.13.0


From 79da4a75b84649428c35fb37a69dc371ac52104e Mon Sep 17 00:00:00 2001
From: Arend van Spriel <arend.vanspriel@broadcom.com>
Date: Fri, 7 Jul 2017 21:09:06 +0100
Subject: [PATCH 29/30] brcmfmac: fix possible buffer overflow in
 brcmf_cfg80211_mgmt_tx()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 8f44c9a41386729fea410e688959ddaa9d51be7c ]

The lower level nl80211 code in cfg80211 ensures that "len" is between
25 and NL80211_ATTR_FRAME (2304).  We subtract DOT11_MGMT_HDR_LEN (24) from
"len" so thats's max of 2280.  However, the action_frame->data[] buffer is
only BRCMF_FIL_ACTION_FRAME_SIZE (1800) bytes long so this memcpy() can
overflow.

	memcpy(action_frame->data, &buf[DOT11_MGMT_HDR_LEN],
	       le16_to_cpu(action_frame->len));

Cc: stable@vger.kernel.org # 3.9.x
Fixes: 18e2f61db3b70 ("brcmfmac: P2P action frame tx.")
Reported-by: "freenerguo(郭大兴)" <freenerguo@tencent.com>
Signed-off-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index 017e20b34304..2097ddc6c2f9 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -4835,6 +4835,11 @@ brcmf_cfg80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
 		cfg80211_mgmt_tx_status(wdev, *cookie, buf, len, true,
 					GFP_KERNEL);
 	} else if (ieee80211_is_action(mgmt->frame_control)) {
+		if (len > BRCMF_FIL_ACTION_FRAME_SIZE + DOT11_MGMT_HDR_LEN) {
+			brcmf_err("invalid action frame length\n");
+			err = -EINVAL;
+			goto exit;
+		}
 		af_params = kzalloc(sizeof(*af_params), GFP_KERNEL);
 		if (af_params == NULL) {
 			brcmf_err("unable to allocate frame\n");
-- 
2.13.0


From 7fb4bf27bf904b32e608f96c86d3d30c01e0355b Mon Sep 17 00:00:00 2001
From: Bert Kenward <bkenward@solarflare.com>
Date: Wed, 12 Jul 2017 17:19:41 +0100
Subject: [PATCH 30/30] sfc: don't read beyond unicast address list

[ Upstream commit c70d68150f71b84cea6997a53493e17bf18a54db ]

If we have more than 32 unicast MAC addresses assigned to an interface
we will read beyond the end of the address table in the driver when
adding filters. The next 256 entries store multicast addresses, so we
will end up attempting to insert duplicate filters, which is mostly
harmless. If we add more than 288 unicast addresses we will then read
past the multicast address table, which is likely to be more exciting.

Fixes: 12fb0da45c9a ("sfc: clean fallbacks between promisc/normal in efx_ef10_filter_sync_rx_mode")
Signed-off-by: Bert Kenward <bkenward@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/ef10.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index f4aed889b6ce..5a1b9b219a42 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -5033,12 +5033,9 @@ static void efx_ef10_filter_uc_addr_list(struct efx_nic *efx)
 	struct efx_ef10_filter_table *table = efx->filter_state;
 	struct net_device *net_dev = efx->net_dev;
 	struct netdev_hw_addr *uc;
-	int addr_count;
 	unsigned int i;
 
-	addr_count = netdev_uc_count(net_dev);
 	table->uc_promisc = !!(net_dev->flags & IFF_PROMISC);
-	table->dev_uc_count = 1 + addr_count;
 	ether_addr_copy(table->dev_uc_list[0].addr, net_dev->dev_addr);
 	i = 1;
 	netdev_for_each_uc_addr(uc, net_dev) {
@@ -5049,6 +5046,8 @@ static void efx_ef10_filter_uc_addr_list(struct efx_nic *efx)
 		ether_addr_copy(table->dev_uc_list[i].addr, uc->addr);
 		i++;
 	}
+
+	table->dev_uc_count = i;
 }
 
 static void efx_ef10_filter_mc_addr_list(struct efx_nic *efx)
@@ -5056,11 +5055,10 @@ static void efx_ef10_filter_mc_addr_list(struct efx_nic *efx)
 	struct efx_ef10_filter_table *table = efx->filter_state;
 	struct net_device *net_dev = efx->net_dev;
 	struct netdev_hw_addr *mc;
-	unsigned int i, addr_count;
+	unsigned int i;
 
 	table->mc_promisc = !!(net_dev->flags & (IFF_PROMISC | IFF_ALLMULTI));
 
-	addr_count = netdev_mc_count(net_dev);
 	i = 0;
 	netdev_for_each_mc_addr(mc, net_dev) {
 		if (i >= EFX_EF10_FILTER_DEV_MC_MAX) {
-- 
2.13.0


[-- Attachment #3: net_412.mbox --]
[-- Type: Application/Octet-Stream, Size: 54565 bytes --]

From 95326f54538e480fb55e2ae60342a3ef8e855a23 Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Mon, 19 Jun 2017 18:25:59 +0300
Subject: [PATCH 01/18] net/mlx5: Fix driver load error flow when firmware is
 stuck

[ Upstream commit 8ce59b16b4b6eacedaec1f7b652b4781cdbfe15f ]

When wait for firmware init fails, previous code would mistakenly
return success and cause inconsistency in the driver state.

Fixes: 6c780a0267b8 ("net/mlx5: Wait for FW readiness before initializing command interface")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 13be264587f1..fd47b5134841 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1020,7 +1020,7 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 	if (err) {
 		dev_err(&dev->pdev->dev, "Firmware over %d MS in pre-initializing state, aborting\n",
 			FW_PRE_INIT_TIMEOUT_MILI);
-		goto out;
+		goto out_err;
 	}
 
 	err = mlx5_cmd_init(dev);
-- 
2.13.0


From 42d0388b1ce663f11cc692303b48b21f42a84924 Mon Sep 17 00:00:00 2001
From: Mohamad Haj Yahia <mohamad@mellanox.com>
Date: Thu, 30 Mar 2017 17:09:00 +0300
Subject: [PATCH 02/18] net/mlx5: Cancel delayed recovery work when unloading
 the driver

[ Upstream commit 2a0165a034ac024b60cca49c61e46f4afa2e4d98 ]

Draining the health workqueue will ignore future health works including
the one that report hardware failure and thus we can't enter error state
Instead cancel the recovery flow and make sure only recovery flow won't
be scheduled.

Fixes: 5e44fca50470 ('net/mlx5: Only cancel recovery work when cleaning up device')
Signed-off-by: Mohamad Haj Yahia <mohamad@mellanox.com>
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/health.c | 15 ++++++++++++++-
 drivers/net/ethernet/mellanox/mlx5/core/main.c   |  2 +-
 include/linux/mlx5/driver.h                      |  1 +
 3 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index f27f84ffbc85..8a8b5f0e497c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -67,6 +67,7 @@ enum {
 
 enum {
 	MLX5_DROP_NEW_HEALTH_WORK,
+	MLX5_DROP_NEW_RECOVERY_WORK,
 };
 
 static u8 get_nic_state(struct mlx5_core_dev *dev)
@@ -193,7 +194,7 @@ static void health_care(struct work_struct *work)
 	mlx5_handle_bad_state(dev);
 
 	spin_lock(&health->wq_lock);
-	if (!test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags))
+	if (!test_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags))
 		schedule_delayed_work(&health->recover_work, recover_delay);
 	else
 		dev_err(&dev->pdev->dev,
@@ -313,6 +314,7 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev)
 	init_timer(&health->timer);
 	health->sick = 0;
 	clear_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags);
+	clear_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags);
 	health->health = &dev->iseg->health;
 	health->health_counter = &dev->iseg->health_counter;
 
@@ -335,11 +337,22 @@ void mlx5_drain_health_wq(struct mlx5_core_dev *dev)
 
 	spin_lock(&health->wq_lock);
 	set_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags);
+	set_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags);
 	spin_unlock(&health->wq_lock);
 	cancel_delayed_work_sync(&health->recover_work);
 	cancel_work_sync(&health->work);
 }
 
+void mlx5_drain_health_recovery(struct mlx5_core_dev *dev)
+{
+	struct mlx5_core_health *health = &dev->priv.health;
+
+	spin_lock(&health->wq_lock);
+	set_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags);
+	spin_unlock(&health->wq_lock);
+	cancel_delayed_work_sync(&dev->priv.health.recover_work);
+}
+
 void mlx5_health_cleanup(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_health *health = &dev->priv.health;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index fd47b5134841..524c16f72e83 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1228,7 +1228,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 	int err = 0;
 
 	if (cleanup)
-		mlx5_drain_health_wq(dev);
+		mlx5_drain_health_recovery(dev);
 
 	mutex_lock(&dev->intf_state_mutex);
 	if (test_bit(MLX5_INTERFACE_STATE_DOWN, &dev->intf_state)) {
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 93273d9ea4d1..ba260330ce5e 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -925,6 +925,7 @@ int mlx5_health_init(struct mlx5_core_dev *dev);
 void mlx5_start_health_poll(struct mlx5_core_dev *dev);
 void mlx5_stop_health_poll(struct mlx5_core_dev *dev);
 void mlx5_drain_health_wq(struct mlx5_core_dev *dev);
+void mlx5_drain_health_recovery(struct mlx5_core_dev *dev);
 int mlx5_buf_alloc_node(struct mlx5_core_dev *dev, int size,
 			struct mlx5_buf *buf, int node);
 int mlx5_buf_alloc(struct mlx5_core_dev *dev, int size, struct mlx5_buf *buf);
-- 
2.13.0


From a75b0f9e6da8c717d8e8f97a9b444b5a1c4480bd Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Sun, 25 Jun 2017 16:46:25 +0300
Subject: [PATCH 03/18] net/mlx5e: Fix TX carrier errors report in get stats
 ndo

[ Upstream commit 8ff93de7668bd81bc8efa819d1184ebd48fae72d ]

Symbol error during carrier counter from PPCNT was mistakenly reported as
TX carrier errors in get_stats ndo, although it's an RX counter.

Fixes: 269e6b3af3bf ("net/mlx5e: Report additional error statistics in get stats ndo")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 277f4de30375..7819fe9ede22 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3053,8 +3053,6 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 		PPORT_802_3_GET(pstats, a_frame_check_sequence_errors);
 	stats->rx_frame_errors = PPORT_802_3_GET(pstats, a_alignment_errors);
 	stats->tx_aborted_errors = PPORT_2863_GET(pstats, if_out_discards);
-	stats->tx_carrier_errors =
-		PPORT_802_3_GET(pstats, a_symbol_error_during_carrier);
 	stats->rx_errors = stats->rx_length_errors + stats->rx_crc_errors +
 			   stats->rx_frame_errors;
 	stats->tx_errors = stats->tx_aborted_errors + stats->tx_carrier_errors;
-- 
2.13.0


From c75663c13548b2eaa54873c7cd81f29ee43833f5 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Thu, 29 Jun 2017 16:56:54 +0200
Subject: [PATCH 04/18] ipv6: dad: don't remove dynamic addresses if link is
 down

[ Upstream commit ec8add2a4c9df723c94a863b8fcd6d93c472deed ]

Currently, when the link for $DEV is down, this command succeeds but the
address is removed immediately by DAD (1):

    ip addr add 1111::12/64 dev $DEV valid_lft 3600 preferred_lft 1800

In the same situation, this will succeed and not remove the address (2):

    ip addr add 1111::12/64 dev $DEV
    ip addr change 1111::12/64 dev $DEV valid_lft 3600 preferred_lft 1800

The comment in addrconf_dad_begin() when !IF_READY makes it look like
this is the intended behavior, but doesn't explain why:

     * If the device is not ready:
     * - keep it tentative if it is a permanent address.
     * - otherwise, kill it.

We clearly cannot prevent userspace from doing (2), but we can make (1)
work consistently with (2).

addrconf_dad_stop() is only called in two cases: if DAD failed, or to
skip DAD when the link is down. In that second case, the fix is to avoid
deleting the address, like we already do for permanent addresses.

Fixes: 3c21edbd1137 ("[IPV6]: Defer IPv6 device initialization until the link becomes ready.")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 1d2dbace42ff..39a44c0598f7 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1912,15 +1912,7 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed)
 	if (dad_failed)
 		ifp->flags |= IFA_F_DADFAILED;
 
-	if (ifp->flags&IFA_F_PERMANENT) {
-		spin_lock_bh(&ifp->lock);
-		addrconf_del_dad_work(ifp);
-		ifp->flags |= IFA_F_TENTATIVE;
-		spin_unlock_bh(&ifp->lock);
-		if (dad_failed)
-			ipv6_ifa_notify(0, ifp);
-		in6_ifa_put(ifp);
-	} else if (ifp->flags&IFA_F_TEMPORARY) {
+	if (ifp->flags&IFA_F_TEMPORARY) {
 		struct inet6_ifaddr *ifpub;
 		spin_lock_bh(&ifp->lock);
 		ifpub = ifp->ifpub;
@@ -1933,6 +1925,14 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed)
 			spin_unlock_bh(&ifp->lock);
 		}
 		ipv6_del_addr(ifp);
+	} else if (ifp->flags&IFA_F_PERMANENT || !dad_failed) {
+		spin_lock_bh(&ifp->lock);
+		addrconf_del_dad_work(ifp);
+		ifp->flags |= IFA_F_TENTATIVE;
+		spin_unlock_bh(&ifp->lock);
+		if (dad_failed)
+			ipv6_ifa_notify(0, ifp);
+		in6_ifa_put(ifp);
 	} else {
 		ipv6_del_addr(ifp);
 	}
-- 
2.13.0


From 1207f1e8f0df56d1a41e0a3ffa1b66db35e7d9d7 Mon Sep 17 00:00:00 2001
From: Jiri Benc <jbenc@redhat.com>
Date: Sun, 2 Jul 2017 19:00:57 +0200
Subject: [PATCH 05/18] vxlan: fix hlist corruption

[ Upstream commit 69e766612c4bcb79e19cebed9eed61d4222c1d47 ]

It's not a good idea to add the same hlist_node to two different hash lists.
This leads to various hard to debug memory corruptions.

Fixes: b1be00a6c39f ("vxlan: support both IPv4 and IPv6 sockets in a single vxlan device")
Signed-off-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 30 ++++++++++++++++++++----------
 include/net/vxlan.h | 10 +++++++++-
 2 files changed, 29 insertions(+), 11 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 5fa798a5c9a6..c4e540126258 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -228,15 +228,15 @@ static struct vxlan_sock *vxlan_find_sock(struct net *net, sa_family_t family,
 
 static struct vxlan_dev *vxlan_vs_find_vni(struct vxlan_sock *vs, __be32 vni)
 {
-	struct vxlan_dev *vxlan;
+	struct vxlan_dev_node *node;
 
 	/* For flow based devices, map all packets to VNI 0 */
 	if (vs->flags & VXLAN_F_COLLECT_METADATA)
 		vni = 0;
 
-	hlist_for_each_entry_rcu(vxlan, vni_head(vs, vni), hlist) {
-		if (vxlan->default_dst.remote_vni == vni)
-			return vxlan;
+	hlist_for_each_entry_rcu(node, vni_head(vs, vni), hlist) {
+		if (node->vxlan->default_dst.remote_vni == vni)
+			return node->vxlan;
 	}
 
 	return NULL;
@@ -2365,17 +2365,22 @@ static void vxlan_vs_del_dev(struct vxlan_dev *vxlan)
 	struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
 
 	spin_lock(&vn->sock_lock);
-	hlist_del_init_rcu(&vxlan->hlist);
+	hlist_del_init_rcu(&vxlan->hlist4.hlist);
+#if IS_ENABLED(CONFIG_IPV6)
+	hlist_del_init_rcu(&vxlan->hlist6.hlist);
+#endif
 	spin_unlock(&vn->sock_lock);
 }
 
-static void vxlan_vs_add_dev(struct vxlan_sock *vs, struct vxlan_dev *vxlan)
+static void vxlan_vs_add_dev(struct vxlan_sock *vs, struct vxlan_dev *vxlan,
+			     struct vxlan_dev_node *node)
 {
 	struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
 	__be32 vni = vxlan->default_dst.remote_vni;
 
+	node->vxlan = vxlan;
 	spin_lock(&vn->sock_lock);
-	hlist_add_head_rcu(&vxlan->hlist, vni_head(vs, vni));
+	hlist_add_head_rcu(&node->hlist, vni_head(vs, vni));
 	spin_unlock(&vn->sock_lock);
 }
 
@@ -2819,6 +2824,7 @@ static int __vxlan_sock_add(struct vxlan_dev *vxlan, bool ipv6)
 {
 	struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
 	struct vxlan_sock *vs = NULL;
+	struct vxlan_dev_node *node;
 
 	if (!vxlan->cfg.no_share) {
 		spin_lock(&vn->sock_lock);
@@ -2836,12 +2842,16 @@ static int __vxlan_sock_add(struct vxlan_dev *vxlan, bool ipv6)
 	if (IS_ERR(vs))
 		return PTR_ERR(vs);
 #if IS_ENABLED(CONFIG_IPV6)
-	if (ipv6)
+	if (ipv6) {
 		rcu_assign_pointer(vxlan->vn6_sock, vs);
-	else
+		node = &vxlan->hlist6;
+	} else
 #endif
+	{
 		rcu_assign_pointer(vxlan->vn4_sock, vs);
-	vxlan_vs_add_dev(vs, vxlan);
+		node = &vxlan->hlist4;
+	}
+	vxlan_vs_add_dev(vs, vxlan, node);
 	return 0;
 }
 
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 49a59202f85e..da7d6b89df77 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -221,9 +221,17 @@ struct vxlan_config {
 	bool			no_share;
 };
 
+struct vxlan_dev_node {
+	struct hlist_node hlist;
+	struct vxlan_dev *vxlan;
+};
+
 /* Pseudo network device */
 struct vxlan_dev {
-	struct hlist_node hlist;	/* vni hash table */
+	struct vxlan_dev_node hlist4;	/* vni hash table for IPv4 socket */
+#if IS_ENABLED(CONFIG_IPV6)
+	struct vxlan_dev_node hlist6;	/* vni hash table for IPv6 socket */
+#endif
 	struct list_head  next;		/* vxlan's per namespace list */
 	struct vxlan_sock __rcu *vn4_sock;	/* listening socket for IPv4 */
 #if IS_ENABLED(CONFIG_IPV6)
-- 
2.13.0


From 8b91c318bf7dfdf6b0932f17a932be6067cfb7d6 Mon Sep 17 00:00:00 2001
From: Jiri Benc <jbenc@redhat.com>
Date: Sun, 2 Jul 2017 19:00:58 +0200
Subject: [PATCH 06/18] geneve: fix hlist corruption

[ Upstream commit 4b4c21fad6ae6bd58ff1566f23b0f4f70fdc9a30 ]

It's not a good idea to add the same hlist_node to two different hash lists.
This leads to various hard to debug memory corruptions.

Fixes: 8ed66f0e8235 ("geneve: implement support for IPv6-based tunnels")
Cc: John W. Linville <linville@tuxdriver.com>
Signed-off-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c | 48 ++++++++++++++++++++++++++++++++----------------
 1 file changed, 32 insertions(+), 16 deletions(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 199459bd6961..6ec8fc9aad8f 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -45,9 +45,17 @@ struct geneve_net {
 
 static unsigned int geneve_net_id;
 
+struct geneve_dev_node {
+	struct hlist_node hlist;
+	struct geneve_dev *geneve;
+};
+
 /* Pseudo network device */
 struct geneve_dev {
-	struct hlist_node  hlist;	/* vni hash table */
+	struct geneve_dev_node hlist4;	/* vni hash table for IPv4 socket */
+#if IS_ENABLED(CONFIG_IPV6)
+	struct geneve_dev_node hlist6;	/* vni hash table for IPv6 socket */
+#endif
 	struct net	   *net;	/* netns for packet i/o */
 	struct net_device  *dev;	/* netdev for geneve tunnel */
 	struct ip_tunnel_info info;
@@ -123,16 +131,16 @@ static struct geneve_dev *geneve_lookup(struct geneve_sock *gs,
 					__be32 addr, u8 vni[])
 {
 	struct hlist_head *vni_list_head;
-	struct geneve_dev *geneve;
+	struct geneve_dev_node *node;
 	__u32 hash;
 
 	/* Find the device for this VNI */
 	hash = geneve_net_vni_hash(vni);
 	vni_list_head = &gs->vni_list[hash];
-	hlist_for_each_entry_rcu(geneve, vni_list_head, hlist) {
-		if (eq_tun_id_and_vni((u8 *)&geneve->info.key.tun_id, vni) &&
-		    addr == geneve->info.key.u.ipv4.dst)
-			return geneve;
+	hlist_for_each_entry_rcu(node, vni_list_head, hlist) {
+		if (eq_tun_id_and_vni((u8 *)&node->geneve->info.key.tun_id, vni) &&
+		    addr == node->geneve->info.key.u.ipv4.dst)
+			return node->geneve;
 	}
 	return NULL;
 }
@@ -142,16 +150,16 @@ static struct geneve_dev *geneve6_lookup(struct geneve_sock *gs,
 					 struct in6_addr addr6, u8 vni[])
 {
 	struct hlist_head *vni_list_head;
-	struct geneve_dev *geneve;
+	struct geneve_dev_node *node;
 	__u32 hash;
 
 	/* Find the device for this VNI */
 	hash = geneve_net_vni_hash(vni);
 	vni_list_head = &gs->vni_list[hash];
-	hlist_for_each_entry_rcu(geneve, vni_list_head, hlist) {
-		if (eq_tun_id_and_vni((u8 *)&geneve->info.key.tun_id, vni) &&
-		    ipv6_addr_equal(&addr6, &geneve->info.key.u.ipv6.dst))
-			return geneve;
+	hlist_for_each_entry_rcu(node, vni_list_head, hlist) {
+		if (eq_tun_id_and_vni((u8 *)&node->geneve->info.key.tun_id, vni) &&
+		    ipv6_addr_equal(&addr6, &node->geneve->info.key.u.ipv6.dst))
+			return node->geneve;
 	}
 	return NULL;
 }
@@ -579,6 +587,7 @@ static int geneve_sock_add(struct geneve_dev *geneve, bool ipv6)
 {
 	struct net *net = geneve->net;
 	struct geneve_net *gn = net_generic(net, geneve_net_id);
+	struct geneve_dev_node *node;
 	struct geneve_sock *gs;
 	__u8 vni[3];
 	__u32 hash;
@@ -597,15 +606,20 @@ static int geneve_sock_add(struct geneve_dev *geneve, bool ipv6)
 out:
 	gs->collect_md = geneve->collect_md;
 #if IS_ENABLED(CONFIG_IPV6)
-	if (ipv6)
+	if (ipv6) {
 		rcu_assign_pointer(geneve->sock6, gs);
-	else
+		node = &geneve->hlist6;
+	} else
 #endif
+	{
 		rcu_assign_pointer(geneve->sock4, gs);
+		node = &geneve->hlist4;
+	}
+	node->geneve = geneve;
 
 	tunnel_id_to_vni(geneve->info.key.tun_id, vni);
 	hash = geneve_net_vni_hash(vni);
-	hlist_add_head_rcu(&geneve->hlist, &gs->vni_list[hash]);
+	hlist_add_head_rcu(&node->hlist, &gs->vni_list[hash]);
 	return 0;
 }
 
@@ -632,8 +646,10 @@ static int geneve_stop(struct net_device *dev)
 {
 	struct geneve_dev *geneve = netdev_priv(dev);
 
-	if (!hlist_unhashed(&geneve->hlist))
-		hlist_del_rcu(&geneve->hlist);
+	hlist_del_init_rcu(&geneve->hlist4.hlist);
+#if IS_ENABLED(CONFIG_IPV6)
+	hlist_del_init_rcu(&geneve->hlist6.hlist);
+#endif
 	geneve_sock_release(geneve);
 	return 0;
 }
-- 
2.13.0


From 331ec91e0db0a72a5bc2b78abcab8bf2e7fcfdfa Mon Sep 17 00:00:00 2001
From: Alban Browaeys <alban.browaeys@gmail.com>
Date: Mon, 3 Jul 2017 03:20:13 +0200
Subject: [PATCH 07/18] net: core: Fix slab-out-of-bounds in
 netdev_stats_to_stats64

[ Upstream commit 9af9959e142c274f4a30fefb71d97d2b028b337f ]

commit 9256645af098 ("net/core: relax BUILD_BUG_ON in
netdev_stats_to_stats64") made an attempt to read beyond
the size of the source a possibility.

Fix to only copy src size to dest. As dest might be bigger than src.

 ==================================================================
 BUG: KASAN: slab-out-of-bounds in netdev_stats_to_stats64+0xe/0x30 at addr ffff8801be248b20
 Read of size 192 by task VBoxNetAdpCtl/6734
 CPU: 1 PID: 6734 Comm: VBoxNetAdpCtl Tainted: G           O    4.11.4prahal+intel+ #118
 Hardware name: LENOVO 20CDCTO1WW/20CDCTO1WW, BIOS GQET52WW (1.32 ) 05/04/2017
 Call Trace:
  dump_stack+0x63/0x86
  kasan_object_err+0x1c/0x70
  kasan_report+0x270/0x520
  ? netdev_stats_to_stats64+0xe/0x30
  ? sched_clock_cpu+0x1b/0x190
  ? __module_address+0x3e/0x3b0
  ? unwind_next_frame+0x1ea/0xb00
  check_memory_region+0x13c/0x1a0
  memcpy+0x23/0x50
  netdev_stats_to_stats64+0xe/0x30
  dev_get_stats+0x1b9/0x230
  rtnl_fill_stats+0x44/0xc00
  ? nla_put+0xc6/0x130
  rtnl_fill_ifinfo+0xe9e/0x3700
  ? rtnl_fill_vfinfo+0xde0/0xde0
  ? sched_clock+0x9/0x10
  ? sched_clock+0x9/0x10
  ? sched_clock_local+0x120/0x130
  ? __module_address+0x3e/0x3b0
  ? unwind_next_frame+0x1ea/0xb00
  ? sched_clock+0x9/0x10
  ? sched_clock+0x9/0x10
  ? sched_clock_cpu+0x1b/0x190
  ? VBoxNetAdpLinuxIOCtlUnlocked+0x14b/0x280 [vboxnetadp]
  ? depot_save_stack+0x1d8/0x4a0
  ? depot_save_stack+0x34f/0x4a0
  ? depot_save_stack+0x34f/0x4a0
  ? save_stack+0xb1/0xd0
  ? save_stack_trace+0x16/0x20
  ? save_stack+0x46/0xd0
  ? kasan_slab_alloc+0x12/0x20
  ? __kmalloc_node_track_caller+0x10d/0x350
  ? __kmalloc_reserve.isra.36+0x2c/0xc0
  ? __alloc_skb+0xd0/0x560
  ? rtmsg_ifinfo_build_skb+0x61/0x120
  ? rtmsg_ifinfo.part.25+0x16/0xb0
  ? rtmsg_ifinfo+0x47/0x70
  ? register_netdev+0x15/0x30
  ? vboxNetAdpOsCreate+0xc0/0x1c0 [vboxnetadp]
  ? vboxNetAdpCreate+0x210/0x400 [vboxnetadp]
  ? VBoxNetAdpLinuxIOCtlUnlocked+0x14b/0x280 [vboxnetadp]
  ? do_vfs_ioctl+0x17f/0xff0
  ? SyS_ioctl+0x74/0x80
  ? do_syscall_64+0x182/0x390
  ? __alloc_skb+0xd0/0x560
  ? __alloc_skb+0xd0/0x560
  ? save_stack_trace+0x16/0x20
  ? init_object+0x64/0xa0
  ? ___slab_alloc+0x1ae/0x5c0
  ? ___slab_alloc+0x1ae/0x5c0
  ? __alloc_skb+0xd0/0x560
  ? sched_clock+0x9/0x10
  ? kasan_unpoison_shadow+0x35/0x50
  ? kasan_kmalloc+0xad/0xe0
  ? __kmalloc_node_track_caller+0x246/0x350
  ? __alloc_skb+0xd0/0x560
  ? kasan_unpoison_shadow+0x35/0x50
  ? memset+0x31/0x40
  ? __alloc_skb+0x31f/0x560
  ? napi_consume_skb+0x320/0x320
  ? br_get_link_af_size_filtered+0xb7/0x120 [bridge]
  ? if_nlmsg_size+0x440/0x630
  rtmsg_ifinfo_build_skb+0x83/0x120
  rtmsg_ifinfo.part.25+0x16/0xb0
  rtmsg_ifinfo+0x47/0x70
  register_netdevice+0xa2b/0xe50
  ? __kmalloc+0x171/0x2d0
  ? netdev_change_features+0x80/0x80
  register_netdev+0x15/0x30
  vboxNetAdpOsCreate+0xc0/0x1c0 [vboxnetadp]
  vboxNetAdpCreate+0x210/0x400 [vboxnetadp]
  ? vboxNetAdpComposeMACAddress+0x1d0/0x1d0 [vboxnetadp]
  ? kasan_check_write+0x14/0x20
  VBoxNetAdpLinuxIOCtlUnlocked+0x14b/0x280 [vboxnetadp]
  ? VBoxNetAdpLinuxOpen+0x20/0x20 [vboxnetadp]
  ? lock_acquire+0x11c/0x270
  ? __audit_syscall_entry+0x2fb/0x660
  do_vfs_ioctl+0x17f/0xff0
  ? __audit_syscall_entry+0x2fb/0x660
  ? ioctl_preallocate+0x1d0/0x1d0
  ? __audit_syscall_entry+0x2fb/0x660
  ? kmem_cache_free+0xb2/0x250
  ? syscall_trace_enter+0x537/0xd00
  ? exit_to_usermode_loop+0x100/0x100
  SyS_ioctl+0x74/0x80
  ? do_sys_open+0x350/0x350
  ? do_vfs_ioctl+0xff0/0xff0
  do_syscall_64+0x182/0x390
  entry_SYSCALL64_slow_path+0x25/0x25
 RIP: 0033:0x7f7e39a1ae07
 RSP: 002b:00007ffc6f04c6d8 EFLAGS: 00000206 ORIG_RAX: 0000000000000010
 RAX: ffffffffffffffda RBX: 00007ffc6f04c730 RCX: 00007f7e39a1ae07
 RDX: 00007ffc6f04c730 RSI: 00000000c0207601 RDI: 0000000000000007
 RBP: 00007ffc6f04c700 R08: 00007ffc6f04c780 R09: 0000000000000008
 R10: 0000000000000541 R11: 0000000000000206 R12: 0000000000000007
 R13: 00000000c0207601 R14: 00007ffc6f04c730 R15: 0000000000000012
 Object at ffff8801be248008, in cache kmalloc-4096 size: 4096
 Allocated:
 PID = 6734
  save_stack_trace+0x16/0x20
  save_stack+0x46/0xd0
  kasan_kmalloc+0xad/0xe0
  __kmalloc+0x171/0x2d0
  alloc_netdev_mqs+0x8a7/0xbe0
  vboxNetAdpOsCreate+0x65/0x1c0 [vboxnetadp]
  vboxNetAdpCreate+0x210/0x400 [vboxnetadp]
  VBoxNetAdpLinuxIOCtlUnlocked+0x14b/0x280 [vboxnetadp]
  do_vfs_ioctl+0x17f/0xff0
  SyS_ioctl+0x74/0x80
  do_syscall_64+0x182/0x390
  return_from_SYSCALL_64+0x0/0x6a
 Freed:
 PID = 5600
  save_stack_trace+0x16/0x20
  save_stack+0x46/0xd0
  kasan_slab_free+0x73/0xc0
  kfree+0xe4/0x220
  kvfree+0x25/0x30
  single_release+0x74/0xb0
  __fput+0x265/0x6b0
  ____fput+0x9/0x10
  task_work_run+0xd5/0x150
  exit_to_usermode_loop+0xe2/0x100
  do_syscall_64+0x26c/0x390
  return_from_SYSCALL_64+0x0/0x6a
 Memory state around the buggy address:
  ffff8801be248a80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
  ffff8801be248b00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
 >ffff8801be248b80: 00 00 00 00 00 00 00 00 00 00 00 07 fc fc fc fc
                                                     ^
  ffff8801be248c00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
  ffff8801be248c80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 ==================================================================

Signed-off-by: Alban Browaeys <alban.browaeys@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 416137c64bf8..25f9461eff3f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7751,7 +7751,7 @@ void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64,
 {
 #if BITS_PER_LONG == 64
 	BUILD_BUG_ON(sizeof(*stats64) < sizeof(*netdev_stats));
-	memcpy(stats64, netdev_stats, sizeof(*stats64));
+	memcpy(stats64, netdev_stats, sizeof(*netdev_stats));
 	/* zero out counters that only exist in rtnl_link_stats64 */
 	memset((char *)stats64 + sizeof(*netdev_stats), 0,
 	       sizeof(*stats64) - sizeof(*netdev_stats));
-- 
2.13.0


From 3884720e1b1c622a14582d270ddf48e988403615 Mon Sep 17 00:00:00 2001
From: Derek Chickles <derek.chickles@cavium.com>
Date: Wed, 5 Jul 2017 11:59:27 -0700
Subject: [PATCH 08/18] liquidio: fix bug in soft reset failure detection

[ Upstream commit 05a6b4cae8c0cc1680c9dd33a97a49a13c0f01bc ]

The code that detects a failed soft reset of Octeon is comparing the wrong
value against the reset value of the Octeon SLI_SCRATCH_1 register,
resulting in an inability to detect a soft reset failure.  Fix it by using
the correct value in the comparison, which is any non-zero value.

Fixes: f21fb3ed364b ("Add support of Cavium Liquidio ethernet adapters")
Fixes: c0eab5b3580a ("liquidio: CN23XX firmware download")
Signed-off-by: Derek Chickles <derek.chickles@cavium.com>
Signed-off-by: Satanand Burla <satananda.burla@cavium.com>
Signed-off-by: Raghu Vatsavayi <raghu.vatsavayi@cavium.com>
Signed-off-by: Felix Manlunas <felix.manlunas@cavium.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c | 2 +-
 drivers/net/ethernet/cavium/liquidio/cn66xx_device.c    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
index 962dcbcef8b5..0dcda0b9b0cc 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
@@ -221,7 +221,7 @@ static int cn23xx_pf_soft_reset(struct octeon_device *oct)
 	/* Wait for 100ms as Octeon resets. */
 	mdelay(100);
 
-	if (octeon_read_csr64(oct, CN23XX_SLI_SCRATCH1) == 0x1234ULL) {
+	if (octeon_read_csr64(oct, CN23XX_SLI_SCRATCH1)) {
 		dev_err(&oct->pci_dev->dev, "OCTEON[%d]: Soft reset failed\n",
 			oct->octeon_id);
 		return 1;
diff --git a/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c b/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c
index bdec051107a6..d62a5096768e 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c
@@ -44,7 +44,7 @@ int lio_cn6xxx_soft_reset(struct octeon_device *oct)
 	/* Wait for 10ms as Octeon resets. */
 	mdelay(100);
 
-	if (octeon_read_csr64(oct, CN6XXX_SLI_SCRATCH1) == 0x1234ULL) {
+	if (octeon_read_csr64(oct, CN6XXX_SLI_SCRATCH1)) {
 		dev_err(&oct->pci_dev->dev, "Soft reset failed\n");
 		return 1;
 	}
-- 
2.13.0


From 22fcaa0336873da62d0f9ffea4a947d37c0050a5 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 5 Jul 2017 14:41:46 -0600
Subject: [PATCH 09/18] net: ipv6: Compare lwstate in detecting duplicate
 nexthops
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit f06b7549b79e29a672336d4e134524373fb7a232 ]

Lennert reported a failure to add different mpls encaps in a multipath
route:

  $ ip -6 route add 1234::/16 \
        nexthop encap mpls 10 via fe80::1 dev ens3 \
        nexthop encap mpls 20 via fe80::1 dev ens3
  RTNETLINK answers: File exists

The problem is that the duplicate nexthop detection does not compare
lwtunnel configuration. Add it.

Fixes: 19e42e451506 ("ipv6: support for fib route lwtunnel encap attributes")
Signed-off-by: David Ahern <dsahern@gmail.com>
Reported-by: João Taveira Araújo <joao.taveira@gmail.com>
Reported-by: Lennert Buytenhek <buytenh@wantstofly.org>
Acked-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Tested-by: Lennert Buytenhek <buytenh@wantstofly.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_route.h | 8 ++++++++
 net/ipv6/ip6_fib.c      | 5 +----
 net/ipv6/route.c        | 8 +-------
 3 files changed, 10 insertions(+), 11 deletions(-)

diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index f5e625f53367..4341731f39a5 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -22,6 +22,7 @@ struct route_info {
 #include <net/flow.h>
 #include <net/ip6_fib.h>
 #include <net/sock.h>
+#include <net/lwtunnel.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/route.h>
@@ -233,4 +234,11 @@ static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt,
 		return daddr;
 }
 
+static inline bool rt6_duplicate_nexthop(struct rt6_info *a, struct rt6_info *b)
+{
+	return a->dst.dev == b->dst.dev &&
+	       a->rt6i_idev == b->rt6i_idev &&
+	       ipv6_addr_equal(&a->rt6i_gateway, &b->rt6i_gateway) &&
+	       !lwtunnel_cmp_encap(a->dst.lwtstate, b->dst.lwtstate);
+}
 #endif
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index e6b78ba0e636..e4e9f752ebbf 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -784,10 +784,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 				goto next_iter;
 			}
 
-			if (iter->dst.dev == rt->dst.dev &&
-			    iter->rt6i_idev == rt->rt6i_idev &&
-			    ipv6_addr_equal(&iter->rt6i_gateway,
-					    &rt->rt6i_gateway)) {
+			if (rt6_duplicate_nexthop(iter, rt)) {
 				if (rt->rt6i_nsiblings)
 					rt->rt6i_nsiblings = 0;
 				if (!(iter->rt6i_flags & RTF_EXPIRES))
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 322bd62e688b..bc49f9a82994 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3048,17 +3048,11 @@ static int ip6_route_info_append(struct list_head *rt6_nh_list,
 				 struct rt6_info *rt, struct fib6_config *r_cfg)
 {
 	struct rt6_nh *nh;
-	struct rt6_info *rtnh;
 	int err = -EEXIST;
 
 	list_for_each_entry(nh, rt6_nh_list, next) {
 		/* check if rt6_info already exists */
-		rtnh = nh->rt6_info;
-
-		if (rtnh->dst.dev == rt->dst.dev &&
-		    rtnh->rt6i_idev == rt->rt6i_idev &&
-		    ipv6_addr_equal(&rtnh->rt6i_gateway,
-				    &rt->rt6i_gateway))
+		if (rt6_duplicate_nexthop(nh->rt6_info, rt))
 			return err;
 	}
 
-- 
2.13.0


From 52fb3f9f758876d06b8f487b884c0bd77be8d125 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Thu, 6 Jul 2017 15:24:40 +0300
Subject: [PATCH 10/18] vrf: fix bug_on triggered by rx when destroying a vrf

[ Upstream commit f630c38ef0d785101363a8992bbd4f302180f86f ]

When destroying a VRF device we cleanup the slaves in its ndo_uninit()
function, but that causes packets to be switched (skb->dev == vrf being
destroyed) even though we're pass the point where the VRF should be
receiving any packets while it is being dismantled. This causes a BUG_ON
to trigger if we have raw sockets (trace below).
The reason is that the inetdev of the VRF has been destroyed but we're
still sending packets up the stack with it, so let's free the slaves in
the dellink callback as David Ahern suggested.

Note that this fix doesn't prevent packets from going up when the VRF
device is admin down.

[   35.631371] ------------[ cut here ]------------
[   35.631603] kernel BUG at net/ipv4/fib_frontend.c:285!
[   35.631854] invalid opcode: 0000 [#1] SMP
[   35.631977] Modules linked in:
[   35.632081] CPU: 2 PID: 22 Comm: ksoftirqd/2 Not tainted 4.12.0-rc7+ #45
[   35.632247] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.7.5-20140531_083030-gandalf 04/01/2014
[   35.632477] task: ffff88005ad68000 task.stack: ffff88005ad64000
[   35.632632] RIP: 0010:fib_compute_spec_dst+0xfc/0x1ee
[   35.632769] RSP: 0018:ffff88005ad67978 EFLAGS: 00010202
[   35.632910] RAX: 0000000000000001 RBX: ffff880059a7f200 RCX: 0000000000000000
[   35.633084] RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffffffff82274af0
[   35.633256] RBP: ffff88005ad679f8 R08: 000000000001ef70 R09: 0000000000000046
[   35.633430] R10: ffff88005ad679f8 R11: ffff880037731cb0 R12: 0000000000000001
[   35.633603] R13: ffff8800599e3000 R14: 0000000000000000 R15: ffff8800599cb852
[   35.634114] FS:  0000000000000000(0000) GS:ffff88005d900000(0000) knlGS:0000000000000000
[   35.634306] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   35.634456] CR2: 00007f3563227095 CR3: 000000000201d000 CR4: 00000000000406e0
[   35.634632] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[   35.634865] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[   35.635055] Call Trace:
[   35.635271]  ? __lock_acquire+0xf0d/0x1117
[   35.635522]  ipv4_pktinfo_prepare+0x82/0x151
[   35.635831]  raw_rcv_skb+0x17/0x3c
[   35.636062]  raw_rcv+0xe5/0xf7
[   35.636287]  raw_local_deliver+0x169/0x1d9
[   35.636534]  ip_local_deliver_finish+0x87/0x1c4
[   35.636820]  ip_local_deliver+0x63/0x7f
[   35.637058]  ip_rcv_finish+0x340/0x3a1
[   35.637295]  ip_rcv+0x314/0x34a
[   35.637525]  __netif_receive_skb_core+0x49f/0x7c5
[   35.637780]  ? lock_acquire+0x13f/0x1d7
[   35.638018]  ? lock_acquire+0x15e/0x1d7
[   35.638259]  __netif_receive_skb+0x1e/0x94
[   35.638502]  ? __netif_receive_skb+0x1e/0x94
[   35.638748]  netif_receive_skb_internal+0x74/0x300
[   35.639002]  ? dev_gro_receive+0x2ed/0x411
[   35.639246]  ? lock_is_held_type+0xc4/0xd2
[   35.639491]  napi_gro_receive+0x105/0x1a0
[   35.639736]  receive_buf+0xc32/0xc74
[   35.639965]  ? detach_buf+0x67/0x153
[   35.640201]  ? virtqueue_get_buf_ctx+0x120/0x176
[   35.640453]  virtnet_poll+0x128/0x1c5
[   35.640690]  net_rx_action+0x103/0x343
[   35.640932]  __do_softirq+0x1c7/0x4b7
[   35.641171]  run_ksoftirqd+0x23/0x5c
[   35.641403]  smpboot_thread_fn+0x24f/0x26d
[   35.641646]  ? sort_range+0x22/0x22
[   35.641878]  kthread+0x129/0x131
[   35.642104]  ? __list_add+0x31/0x31
[   35.642335]  ? __list_add+0x31/0x31
[   35.642568]  ret_from_fork+0x2a/0x40
[   35.642804] Code: 05 bd 87 a3 00 01 e8 1f ef 98 ff 4d 85 f6 48 c7 c7 f0 4a 27 82 41 0f 94 c4 31 c9 31 d2 41 0f b6 f4 e8 04 71 a1 ff 45 84 e4 74 02 <0f> 0b 0f b7 93 c4 00 00 00 4d 8b a5 80 05 00 00 48 03 93 d0 00
[   35.644342] RIP: fib_compute_spec_dst+0xfc/0x1ee RSP: ffff88005ad67978

Fixes: 193125dbd8eb ("net: Introduce VRF device driver")
Reported-by: Chris Cormier <chriscormier@cumulusnetworks.com>
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 022c0b5f9844..c7ee8e3cd38d 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -926,15 +926,10 @@ static int vrf_del_slave(struct net_device *dev, struct net_device *port_dev)
 static void vrf_dev_uninit(struct net_device *dev)
 {
 	struct net_vrf *vrf = netdev_priv(dev);
-	struct net_device *port_dev;
-	struct list_head *iter;
 
 	vrf_rtable_release(dev, vrf);
 	vrf_rt6_release(dev, vrf);
 
-	netdev_for_each_lower_dev(dev, port_dev, iter)
-		vrf_del_slave(dev, port_dev);
-
 	free_percpu(dev->dstats);
 	dev->dstats = NULL;
 }
@@ -1389,6 +1384,12 @@ static int vrf_validate(struct nlattr *tb[], struct nlattr *data[])
 
 static void vrf_dellink(struct net_device *dev, struct list_head *head)
 {
+	struct net_device *port_dev;
+	struct list_head *iter;
+
+	netdev_for_each_lower_dev(dev, port_dev, iter)
+		vrf_del_slave(dev, port_dev);
+
 	unregister_netdevice_queue(dev, head);
 }
 
-- 
2.13.0


From 4d1d1af865ed86054b0a1b3637c2f7575899c029 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Fri, 7 Jul 2017 19:56:09 +0800
Subject: [PATCH 11/18] virtio-net: fix leaking of ctx array

[ Upstream commit 55281621b6047d2ffb934a0b984ab0cdb1ad1d76 ]

Fixes: commit d45b897b11ea ("virtio_net: allow specifying context for rx")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 143d8a95a60d..6633dd4bb649 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2221,6 +2221,7 @@ static int virtnet_find_vqs(struct virtnet_info *vi)
 	kfree(names);
 	kfree(callbacks);
 	kfree(vqs);
+	kfree(ctx);
 
 	return 0;
 
-- 
2.13.0


From 23d4eba16a0d94575cdaf5c64a60ecc295a3a4de Mon Sep 17 00:00:00 2001
From: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Date: Thu, 6 Jul 2017 08:15:06 -0700
Subject: [PATCH 12/18] rds: tcp: use sock_create_lite() to create the accept
 socket

[ Upstream commit 0933a578cd55b02dc80f219dc8f2efb17ec61c9a ]

There are two problems with calling sock_create_kern() from
rds_tcp_accept_one()
1. it sets up a new_sock->sk that is wasteful, because this ->sk
   is going to get replaced by inet_accept() in the subsequent ->accept()
2. The new_sock->sk is a leaked reference in sock_graft() which
   expects to find a null parent->sk

Avoid these problems by calling sock_create_lite().

Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/tcp_listen.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index 507678853e6c..9a1798d6ae94 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -125,7 +125,7 @@ int rds_tcp_accept_one(struct socket *sock)
 	if (!sock) /* module unload or netns delete in progress */
 		return -ENETUNREACH;
 
-	ret = sock_create_kern(sock_net(sock->sk), sock->sk->sk_family,
+	ret = sock_create_lite(sock->sk->sk_family,
 			       sock->sk->sk_type, sock->sk->sk_protocol,
 			       &new_sock);
 	if (ret)
-- 
2.13.0


From ee7cff44d68c145e7cf6de2237da8261327c079f Mon Sep 17 00:00:00 2001
From: Huy Nguyen <huyn@mellanox.com>
Date: Thu, 29 Jun 2017 16:50:01 -0500
Subject: [PATCH 13/18] net/mlx5e: Initialize CEE's getpermhwaddr address
 buffer to 0xff

[ Upstream commit d968f0f2e4404152f37ed2384b4a2269dd2dae5a ]

Latest change in open-lldp code uses bytes 6-11 of perm_addr buffer
as the Ethernet source address for the host TLV packet.
Since our driver does not fill these bytes, they stay at zero and
the open-lldp code ends up sending the TLV packet with zero source
address and the switch drops this packet.

The fix is to initialize these bytes to 0xff. The open-lldp code
considers 0xff:ff:ff:ff:ff:ff as the invalid address and falls back to
use the host's mac address as the Ethernet source address.

Fixes: 3a6a931dfb8e ("net/mlx5e: Support DCBX CEE API")
Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index 8fa23f6a1f67..2eb54d36e16e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -464,6 +464,8 @@ static void mlx5e_dcbnl_getpermhwaddr(struct net_device *netdev,
 	if (!perm_addr)
 		return;
 
+	memset(perm_addr, 0xff, MAX_ADDR_LEN);
+
 	mlx5_query_nic_vport_mac_address(priv->mdev, 0, perm_addr);
 }
 
-- 
2.13.0


From a0924dcfd5033ab0d0333486e50077c9499fe1c8 Mon Sep 17 00:00:00 2001
From: "Guilherme G. Piccoli" <gpiccoli@linux.vnet.ibm.com>
Date: Mon, 10 Jul 2017 10:55:46 -0300
Subject: [PATCH 14/18] cxgb4: fix BUG() on interrupt deallocating path of ULD

[ Upstream commit 6a146f3a5894b751cef16feb3d7903e45e3c445c ]

Since the introduction of ULD (Upper-Layer Drivers), the MSI-X
deallocating path changed in cxgb4: the driver frees the interrupts
of ULD when unregistering it or on shutdown PCI handler.

Problem is that if a MSI-X is not freed before deallocated in the PCI
layer, it will trigger a BUG() due to still "alive" interrupt being
tentatively quiesced.

The below trace was observed when doing a simple unbind of Chelsio's
adapter PCI function, like:
  "echo 001e:80:00.4 > /sys/bus/pci/drivers/cxgb4/unbind"

Trace:

  kernel BUG at drivers/pci/msi.c:352!
  Oops: Exception in kernel mode, sig: 5 [#1]
  ...
  NIP [c0000000005a5e60] free_msi_irqs+0xa0/0x250
  LR [c0000000005a5e50] free_msi_irqs+0x90/0x250
  Call Trace:
  [c0000000005a5e50] free_msi_irqs+0x90/0x250 (unreliable)
  [c0000000005a72c4] pci_disable_msix+0x124/0x180
  [d000000011e06708] disable_msi+0x88/0xb0 [cxgb4]
  [d000000011e06948] free_some_resources+0xa8/0x160 [cxgb4]
  [d000000011e06d60] remove_one+0x170/0x3c0 [cxgb4]
  [c00000000058a910] pci_device_remove+0x70/0x110
  [c00000000064ef04] device_release_driver_internal+0x1f4/0x2c0
  ...

This patch fixes the issue by refactoring the shutdown path of ULD on
cxgb4 driver, by properly freeing and disabling interrupts on PCI
remove handler too.

Fixes: 0fbc81b3ad51 ("Allocate resources dynamically for all cxgb4 ULD's")
Reported-by: Harsha Thyagaraja <hathyaga@in.ibm.com>
Signed-off-by: Guilherme G. Piccoli <gpiccoli@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 16 +++++++---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c  | 42 +++++++++++++++----------
 2 files changed, 36 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 53309f659951..0ac1a5500fc3 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -2055,12 +2055,12 @@ static void detach_ulds(struct adapter *adap)
 
 	mutex_lock(&uld_mutex);
 	list_del(&adap->list_node);
+
 	for (i = 0; i < CXGB4_ULD_MAX; i++)
-		if (adap->uld && adap->uld[i].handle) {
+		if (adap->uld && adap->uld[i].handle)
 			adap->uld[i].state_change(adap->uld[i].handle,
 					     CXGB4_STATE_DETACH);
-			adap->uld[i].handle = NULL;
-		}
+
 	if (netevent_registered && list_empty(&adapter_list)) {
 		unregister_netevent_notifier(&cxgb4_netevent_nb);
 		netevent_registered = false;
@@ -5086,8 +5086,10 @@ static void remove_one(struct pci_dev *pdev)
 		 */
 		destroy_workqueue(adapter->workq);
 
-		if (is_uld(adapter))
+		if (is_uld(adapter)) {
 			detach_ulds(adapter);
+			t4_uld_clean_up(adapter);
+		}
 
 		disable_interrupts(adapter);
 
@@ -5164,7 +5166,11 @@ static void shutdown_one(struct pci_dev *pdev)
 			if (adapter->port[i]->reg_state == NETREG_REGISTERED)
 				cxgb_close(adapter->port[i]);
 
-		t4_uld_clean_up(adapter);
+		if (is_uld(adapter)) {
+			detach_ulds(adapter);
+			t4_uld_clean_up(adapter);
+		}
+
 		disable_interrupts(adapter);
 		disable_msi(adapter);
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
index d0868c2320da..dbbc2b7f0d46 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
@@ -589,22 +589,37 @@ void t4_uld_mem_free(struct adapter *adap)
 	kfree(adap->uld);
 }
 
+/* This function should be called with uld_mutex taken. */
+static void cxgb4_shutdown_uld_adapter(struct adapter *adap, enum cxgb4_uld type)
+{
+	if (adap->uld[type].handle) {
+		adap->uld[type].handle = NULL;
+		adap->uld[type].add = NULL;
+		release_sge_txq_uld(adap, type);
+
+		if (adap->flags & FULL_INIT_DONE)
+			quiesce_rx_uld(adap, type);
+
+		if (adap->flags & USING_MSIX)
+			free_msix_queue_irqs_uld(adap, type);
+
+		free_sge_queues_uld(adap, type);
+		free_queues_uld(adap, type);
+	}
+}
+
 void t4_uld_clean_up(struct adapter *adap)
 {
 	unsigned int i;
 
-	if (!adap->uld)
-		return;
+	mutex_lock(&uld_mutex);
 	for (i = 0; i < CXGB4_ULD_MAX; i++) {
 		if (!adap->uld[i].handle)
 			continue;
-		if (adap->flags & FULL_INIT_DONE)
-			quiesce_rx_uld(adap, i);
-		if (adap->flags & USING_MSIX)
-			free_msix_queue_irqs_uld(adap, i);
-		free_sge_queues_uld(adap, i);
-		free_queues_uld(adap, i);
+
+		cxgb4_shutdown_uld_adapter(adap, i);
 	}
+	mutex_unlock(&uld_mutex);
 }
 
 static void uld_init(struct adapter *adap, struct cxgb4_lld_info *lld)
@@ -782,15 +797,8 @@ int cxgb4_unregister_uld(enum cxgb4_uld type)
 			continue;
 		if (type == CXGB4_ULD_ISCSIT && is_t4(adap->params.chip))
 			continue;
-		adap->uld[type].handle = NULL;
-		adap->uld[type].add = NULL;
-		release_sge_txq_uld(adap, type);
-		if (adap->flags & FULL_INIT_DONE)
-			quiesce_rx_uld(adap, type);
-		if (adap->flags & USING_MSIX)
-			free_msix_queue_irqs_uld(adap, type);
-		free_sge_queues_uld(adap, type);
-		free_queues_uld(adap, type);
+
+		cxgb4_shutdown_uld_adapter(adap, type);
 	}
 	mutex_unlock(&uld_mutex);
 
-- 
2.13.0


From ddc6e09cf396361152970bb54de94ce0123c7113 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Mon, 10 Jul 2017 10:05:50 -0700
Subject: [PATCH 15/18] tap: convert a mutex to a spinlock

[ Upstream commit ffa423fb3251f8737303ffc3b0659e86e501808e ]

We are not allowed to block on the RCU reader side, so can't
just hold the mutex as before. As a quick fix, convert it to
a spinlock.

Fixes: d9f1f61c0801 ("tap: Extending tap device create/destroy APIs")
Reported-by: Christian Borntraeger <borntraeger@de.ibm.com>
Tested-by: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Sainath Grandhi <sainath.grandhi@intel.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tap.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index 4d4173d25dd0..d88ae3c2edbf 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -106,7 +106,7 @@ struct major_info {
 	struct rcu_head rcu;
 	dev_t major;
 	struct idr minor_idr;
-	struct mutex minor_lock;
+	spinlock_t minor_lock;
 	const char *device_name;
 	struct list_head next;
 };
@@ -416,15 +416,15 @@ int tap_get_minor(dev_t major, struct tap_dev *tap)
 		goto unlock;
 	}
 
-	mutex_lock(&tap_major->minor_lock);
-	retval = idr_alloc(&tap_major->minor_idr, tap, 1, TAP_NUM_DEVS, GFP_KERNEL);
+	spin_lock(&tap_major->minor_lock);
+	retval = idr_alloc(&tap_major->minor_idr, tap, 1, TAP_NUM_DEVS, GFP_ATOMIC);
 	if (retval >= 0) {
 		tap->minor = retval;
 	} else if (retval == -ENOSPC) {
 		netdev_err(tap->dev, "Too many tap devices\n");
 		retval = -EINVAL;
 	}
-	mutex_unlock(&tap_major->minor_lock);
+	spin_unlock(&tap_major->minor_lock);
 
 unlock:
 	rcu_read_unlock();
@@ -442,12 +442,12 @@ void tap_free_minor(dev_t major, struct tap_dev *tap)
 		goto unlock;
 	}
 
-	mutex_lock(&tap_major->minor_lock);
+	spin_lock(&tap_major->minor_lock);
 	if (tap->minor) {
 		idr_remove(&tap_major->minor_idr, tap->minor);
 		tap->minor = 0;
 	}
-	mutex_unlock(&tap_major->minor_lock);
+	spin_unlock(&tap_major->minor_lock);
 
 unlock:
 	rcu_read_unlock();
@@ -467,13 +467,13 @@ static struct tap_dev *dev_get_by_tap_file(int major, int minor)
 		goto unlock;
 	}
 
-	mutex_lock(&tap_major->minor_lock);
+	spin_lock(&tap_major->minor_lock);
 	tap = idr_find(&tap_major->minor_idr, minor);
 	if (tap) {
 		dev = tap->dev;
 		dev_hold(dev);
 	}
-	mutex_unlock(&tap_major->minor_lock);
+	spin_unlock(&tap_major->minor_lock);
 
 unlock:
 	rcu_read_unlock();
@@ -1227,7 +1227,7 @@ static int tap_list_add(dev_t major, const char *device_name)
 	tap_major->major = MAJOR(major);
 
 	idr_init(&tap_major->minor_idr);
-	mutex_init(&tap_major->minor_lock);
+	spin_lock_init(&tap_major->minor_lock);
 
 	tap_major->device_name = device_name;
 
-- 
2.13.0


From 4806658ad5a347261247585336b0e80a03f6b6b9 Mon Sep 17 00:00:00 2001
From: Eduardo Valentin <eduval@amazon.com>
Date: Tue, 11 Jul 2017 14:55:12 -0700
Subject: [PATCH 16/18] bridge: mdb: fix leak on complete_info ptr on fail path

[ Upstream commit 1bfb159673957644951ab0a8d2aec44b93ddb1ae ]

We currently get the following kmemleak report:
unreferenced object 0xffff8800039d9820 (size 32):
  comm "softirq", pid 0, jiffies 4295212383 (age 792.416s)
  hex dump (first 32 bytes):
    00 0c e0 03 00 88 ff ff ff 02 00 00 00 00 00 00  ................
    00 00 00 01 ff 11 00 02 86 dd 00 00 ff ff ff ff  ................
  backtrace:
    [<ffffffff8152b4aa>] kmemleak_alloc+0x4a/0xa0
    [<ffffffff811d8ec8>] kmem_cache_alloc_trace+0xb8/0x1c0
    [<ffffffffa0389683>] __br_mdb_notify+0x2a3/0x300 [bridge]
    [<ffffffffa038a0ce>] br_mdb_notify+0x6e/0x70 [bridge]
    [<ffffffffa0386479>] br_multicast_add_group+0x109/0x150 [bridge]
    [<ffffffffa0386518>] br_ip6_multicast_add_group+0x58/0x60 [bridge]
    [<ffffffffa0387fb5>] br_multicast_rcv+0x1d5/0xdb0 [bridge]
    [<ffffffffa037d7cf>] br_handle_frame_finish+0xcf/0x510 [bridge]
    [<ffffffffa03a236b>] br_nf_hook_thresh.part.27+0xb/0x10 [br_netfilter]
    [<ffffffffa03a3738>] br_nf_hook_thresh+0x48/0xb0 [br_netfilter]
    [<ffffffffa03a3fb9>] br_nf_pre_routing_finish_ipv6+0x109/0x1d0 [br_netfilter]
    [<ffffffffa03a4400>] br_nf_pre_routing_ipv6+0xd0/0x14c [br_netfilter]
    [<ffffffffa03a3c27>] br_nf_pre_routing+0x197/0x3d0 [br_netfilter]
    [<ffffffff814a2952>] nf_iterate+0x52/0x60
    [<ffffffff814a29bc>] nf_hook_slow+0x5c/0xb0
    [<ffffffffa037ddf4>] br_handle_frame+0x1a4/0x2c0 [bridge]

This happens when switchdev_port_obj_add() fails. This patch
frees complete_info object in the fail path.

Reviewed-by: Vallish Vaidyeshwara <vallish@amazon.com>
Signed-off-by: Eduardo Valentin <eduval@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_mdb.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index b0845480a3ae..c1030f852b3c 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -323,7 +323,8 @@ static void __br_mdb_notify(struct net_device *dev, struct net_bridge_port *p,
 			__mdb_entry_to_br_ip(entry, &complete_info->ip);
 			mdb.obj.complete_priv = complete_info;
 			mdb.obj.complete = br_mdb_complete;
-			switchdev_port_obj_add(port_dev, &mdb.obj);
+			if (switchdev_port_obj_add(port_dev, &mdb.obj))
+				kfree(complete_info);
 		}
 	} else if (port_dev && type == RTM_DELMDB) {
 		switchdev_port_obj_del(port_dev, &mdb.obj);
-- 
2.13.0


From e91d3748790cb77a65a511f71cb1d92c60bb3d98 Mon Sep 17 00:00:00 2001
From: Arend van Spriel <arend.vanspriel@broadcom.com>
Date: Fri, 7 Jul 2017 21:09:06 +0100
Subject: [PATCH 17/18] brcmfmac: fix possible buffer overflow in
 brcmf_cfg80211_mgmt_tx()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 8f44c9a41386729fea410e688959ddaa9d51be7c ]

The lower level nl80211 code in cfg80211 ensures that "len" is between
25 and NL80211_ATTR_FRAME (2304).  We subtract DOT11_MGMT_HDR_LEN (24) from
"len" so thats's max of 2280.  However, the action_frame->data[] buffer is
only BRCMF_FIL_ACTION_FRAME_SIZE (1800) bytes long so this memcpy() can
overflow.

	memcpy(action_frame->data, &buf[DOT11_MGMT_HDR_LEN],
	       le16_to_cpu(action_frame->len));

Cc: stable@vger.kernel.org # 3.9.x
Fixes: 18e2f61db3b70 ("brcmfmac: P2P action frame tx.")
Reported-by: "freenerguo(郭大兴)" <freenerguo@tencent.com>
Signed-off-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index 617199c0e5a0..110c9cd2822e 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -4851,6 +4851,11 @@ brcmf_cfg80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
 		cfg80211_mgmt_tx_status(wdev, *cookie, buf, len, true,
 					GFP_KERNEL);
 	} else if (ieee80211_is_action(mgmt->frame_control)) {
+		if (len > BRCMF_FIL_ACTION_FRAME_SIZE + DOT11_MGMT_HDR_LEN) {
+			brcmf_err("invalid action frame length\n");
+			err = -EINVAL;
+			goto exit;
+		}
 		af_params = kzalloc(sizeof(*af_params), GFP_KERNEL);
 		if (af_params == NULL) {
 			brcmf_err("unable to allocate frame\n");
-- 
2.13.0


From fb34dc6b127cc43b0d94d48c574604a6a6f2e9e7 Mon Sep 17 00:00:00 2001
From: Bert Kenward <bkenward@solarflare.com>
Date: Wed, 12 Jul 2017 17:19:41 +0100
Subject: [PATCH 18/18] sfc: don't read beyond unicast address list

[ Upstream commit c70d68150f71b84cea6997a53493e17bf18a54db ]

If we have more than 32 unicast MAC addresses assigned to an interface
we will read beyond the end of the address table in the driver when
adding filters. The next 256 entries store multicast addresses, so we
will end up attempting to insert duplicate filters, which is mostly
harmless. If we add more than 288 unicast addresses we will then read
past the multicast address table, which is likely to be more exciting.

Fixes: 12fb0da45c9a ("sfc: clean fallbacks between promisc/normal in efx_ef10_filter_sync_rx_mode")
Signed-off-by: Bert Kenward <bkenward@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/ef10.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 78f9e43420e0..f2da073f4b2b 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -5034,12 +5034,9 @@ static void efx_ef10_filter_uc_addr_list(struct efx_nic *efx)
 	struct efx_ef10_filter_table *table = efx->filter_state;
 	struct net_device *net_dev = efx->net_dev;
 	struct netdev_hw_addr *uc;
-	int addr_count;
 	unsigned int i;
 
-	addr_count = netdev_uc_count(net_dev);
 	table->uc_promisc = !!(net_dev->flags & IFF_PROMISC);
-	table->dev_uc_count = 1 + addr_count;
 	ether_addr_copy(table->dev_uc_list[0].addr, net_dev->dev_addr);
 	i = 1;
 	netdev_for_each_uc_addr(uc, net_dev) {
@@ -5050,6 +5047,8 @@ static void efx_ef10_filter_uc_addr_list(struct efx_nic *efx)
 		ether_addr_copy(table->dev_uc_list[i].addr, uc->addr);
 		i++;
 	}
+
+	table->dev_uc_count = i;
 }
 
 static void efx_ef10_filter_mc_addr_list(struct efx_nic *efx)
@@ -5057,12 +5056,11 @@ static void efx_ef10_filter_mc_addr_list(struct efx_nic *efx)
 	struct efx_ef10_filter_table *table = efx->filter_state;
 	struct net_device *net_dev = efx->net_dev;
 	struct netdev_hw_addr *mc;
-	unsigned int i, addr_count;
+	unsigned int i;
 
 	table->mc_overflow = false;
 	table->mc_promisc = !!(net_dev->flags & (IFF_PROMISC | IFF_ALLMULTI));
 
-	addr_count = netdev_mc_count(net_dev);
 	i = 0;
 	netdev_for_each_mc_addr(mc, net_dev) {
 		if (i >= EFX_EF10_FILTER_DEV_MC_MAX) {
-- 
2.13.0

Re: [PATCHES] Networking

[Greg KH]

On Mon, Jul 17, 2017 at 09:44:28AM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.11 and
> v4.12 -stable, respectively.

Applied to both trees, thanks!

greg k-h

Re: [PATCHES] Networking

[Greg KH]

On Mon, Jul 17, 2017 at 09:23:15PM +0200, Greg KH wrote:
> On Mon, Jul 17, 2017 at 09:44:28AM -0700, David Miller wrote:
> > 
> > Please queue up the following networking bug fixes for v4.11 and
> > v4.12 -stable, respectively.
> 
> Applied to both trees, thanks!

Note, this is going to be the last 4.11.y kernel that I release, so no
need to make patches up for that tree anymore.

thanks,

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 105 bytes --]


Please queue up the following networking bug fixes for 4.9.x
and 4.12.x -stable, respectively.

Thanks!

[-- Attachment #2: net_49.mbox --]
[-- Type: Application/Octet-Stream, Size: 64761 bytes --]

From affc8b3c726b72633b1cc110ac52e2a62d4d3362 Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Fri, 14 Jul 2017 17:49:21 -0400
Subject: [PATCH 01/28] tcp_bbr: cut pacing rate only if filled pipe

[ Upstream commit 4aea287e90dd61a48268ff2994b56f9799441b62 ]

In bbr_set_pacing_rate(), which decides whether to cut the pacing
rate, there was some code that considered exiting STARTUP to be
equivalent to the notion of filling the pipe (i.e.,
bbr_full_bw_reached()). Specifically, as the code was structured,
exiting STARTUP and going into PROBE_RTT could cause us to cut the
pacing rate down to something silly and low, based on whatever
bandwidth samples we've had so far, when it's possible that all of
them have been small app-limited bandwidth samples that are not
representative of the bandwidth available in the path. (The code was
correct at the time it was written, but the state machine changed
without this spot being adjusted correspondingly.)

Fixes: 0f8782ea1497 ("tcp_bbr: add BBR congestion control")
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_bbr.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 0ea66c2c9344..9e3d438faef8 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -191,12 +191,11 @@ static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain)
  */
 static void bbr_set_pacing_rate(struct sock *sk, u32 bw, int gain)
 {
-	struct bbr *bbr = inet_csk_ca(sk);
 	u64 rate = bw;
 
 	rate = bbr_rate_bytes_per_sec(sk, rate, gain);
 	rate = min_t(u64, rate, sk->sk_max_pacing_rate);
-	if (bbr->mode != BBR_STARTUP || rate > sk->sk_pacing_rate)
+	if (bbr_full_bw_reached(sk) || rate > sk->sk_pacing_rate)
 		sk->sk_pacing_rate = rate;
 }
 
-- 
2.13.4


From bd6123a876dffc4ca41a341bb74cc694f8ce3e2e Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Fri, 14 Jul 2017 17:49:22 -0400
Subject: [PATCH 02/28] tcp_bbr: introduce bbr_bw_to_pacing_rate() helper

[ Upstream commit f19fd62dafaf1ed6cf615dba655b82fa9df59074 ]

Introduce a helper to convert a BBR bandwidth and gain factor to a
pacing rate in bytes per second. This is a pure refactor, but is
needed for two following fixes.

Fixes: 0f8782ea1497 ("tcp_bbr: add BBR congestion control")
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_bbr.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 9e3d438faef8..5c5c9f1ef913 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -182,6 +182,16 @@ static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain)
 	return rate >> BW_SCALE;
 }
 
+/* Convert a BBR bw and gain factor to a pacing rate in bytes per second. */
+static u32 bbr_bw_to_pacing_rate(struct sock *sk, u32 bw, int gain)
+{
+	u64 rate = bw;
+
+	rate = bbr_rate_bytes_per_sec(sk, rate, gain);
+	rate = min_t(u64, rate, sk->sk_max_pacing_rate);
+	return rate;
+}
+
 /* Pace using current bw estimate and a gain factor. In order to help drive the
  * network toward lower queues while maintaining high utilization and low
  * latency, the average pacing rate aims to be slightly (~1%) lower than the
@@ -191,10 +201,8 @@ static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain)
  */
 static void bbr_set_pacing_rate(struct sock *sk, u32 bw, int gain)
 {
-	u64 rate = bw;
+	u32 rate = bbr_bw_to_pacing_rate(sk, bw, gain);
 
-	rate = bbr_rate_bytes_per_sec(sk, rate, gain);
-	rate = min_t(u64, rate, sk->sk_max_pacing_rate);
 	if (bbr_full_bw_reached(sk) || rate > sk->sk_pacing_rate)
 		sk->sk_pacing_rate = rate;
 }
-- 
2.13.4


From e25f22d7f0431a1696c2c10f827b4d87cdb4f41b Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Fri, 14 Jul 2017 17:49:23 -0400
Subject: [PATCH 03/28] tcp_bbr: introduce bbr_init_pacing_rate_from_rtt()
 helper

[ Upstream commit 79135b89b8af304456bd67916b80116ddf03d7b6 ]

Introduce a helper to initialize the BBR pacing rate unconditionally,
based on the current cwnd and RTT estimate. This is a pure refactor,
but is needed for two following fixes.

Fixes: 0f8782ea1497 ("tcp_bbr: add BBR congestion control")
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_bbr.c | 23 ++++++++++++++++++-----
 1 file changed, 18 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 5c5c9f1ef913..c7a4c3f95016 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -192,6 +192,23 @@ static u32 bbr_bw_to_pacing_rate(struct sock *sk, u32 bw, int gain)
 	return rate;
 }
 
+/* Initialize pacing rate to: high_gain * init_cwnd / RTT. */
+static void bbr_init_pacing_rate_from_rtt(struct sock *sk)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	u64 bw;
+	u32 rtt_us;
+
+	if (tp->srtt_us) {		/* any RTT sample yet? */
+		rtt_us = max(tp->srtt_us >> 3, 1U);
+	} else {			 /* no RTT sample yet */
+		rtt_us = USEC_PER_MSEC;	 /* use nominal default RTT */
+	}
+	bw = (u64)tp->snd_cwnd * BW_UNIT;
+	do_div(bw, rtt_us);
+	sk->sk_pacing_rate = bbr_bw_to_pacing_rate(sk, bw, bbr_high_gain);
+}
+
 /* Pace using current bw estimate and a gain factor. In order to help drive the
  * network toward lower queues while maintaining high utilization and low
  * latency, the average pacing rate aims to be slightly (~1%) lower than the
@@ -776,7 +793,6 @@ static void bbr_init(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct bbr *bbr = inet_csk_ca(sk);
-	u64 bw;
 
 	bbr->prior_cwnd = 0;
 	bbr->tso_segs_goal = 0;	 /* default segs per skb until first ACK */
@@ -792,11 +808,8 @@ static void bbr_init(struct sock *sk)
 
 	minmax_reset(&bbr->bw, bbr->rtt_cnt, 0);  /* init max bw to 0 */
 
-	/* Initialize pacing rate to: high_gain * init_cwnd / RTT. */
-	bw = (u64)tp->snd_cwnd * BW_UNIT;
-	do_div(bw, (tp->srtt_us >> 3) ? : USEC_PER_MSEC);
 	sk->sk_pacing_rate = 0;		/* force an update of sk_pacing_rate */
-	bbr_set_pacing_rate(sk, bw, bbr_high_gain);
+	bbr_init_pacing_rate_from_rtt(sk);
 
 	bbr->restore_cwnd = 0;
 	bbr->round_start = 0;
-- 
2.13.4


From cc38c2f0c49dad3131e97b14213acdc4abdf7323 Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Fri, 14 Jul 2017 17:49:24 -0400
Subject: [PATCH 04/28] tcp_bbr: remove sk_pacing_rate=0 transient during init

[ Upstream commit 1d3648eb5d1fe9ed3d095ed8fa19ad11ca4c8bc0 ]

Fix a corner case noticed by Eric Dumazet, where BBR's setting
sk->sk_pacing_rate to 0 during initialization could theoretically
cause packets in the sending host to hang if there were packets "in
flight" in the pacing infrastructure at the time the BBR congestion
control state is initialized. This could occur if the pacing
infrastructure happened to race with bbr_init() in a way such that the
pacer read the 0 rather than the immediately following non-zero pacing
rate.

Fixes: 0f8782ea1497 ("tcp_bbr: add BBR congestion control")
Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_bbr.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index c7a4c3f95016..c798788877e2 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -808,7 +808,6 @@ static void bbr_init(struct sock *sk)
 
 	minmax_reset(&bbr->bw, bbr->rtt_cnt, 0);  /* init max bw to 0 */
 
-	sk->sk_pacing_rate = 0;		/* force an update of sk_pacing_rate */
 	bbr_init_pacing_rate_from_rtt(sk);
 
 	bbr->restore_cwnd = 0;
-- 
2.13.4


From 9bd49b154a829d2be7f408a560aa8206078411d2 Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Fri, 14 Jul 2017 17:49:25 -0400
Subject: [PATCH 05/28] tcp_bbr: init pacing rate on first RTT sample

[ Upstream commit 32984565574da7ed3afa10647bb4020d7a9e6c93 ]

Fixes the following behavior: for connections that had no RTT sample
at the time of initializing congestion control, BBR was initializing
the pacing rate to a high nominal rate (based an a guess of RTT=1ms,
in case this is LAN traffic). Then BBR never adjusted the pacing rate
downward upon obtaining an actual RTT sample, if the connection never
filled the pipe (e.g. all sends were small app-limited writes()).

This fix adjusts the pacing rate upon obtaining the first RTT sample.

Fixes: 0f8782ea1497 ("tcp_bbr: add BBR congestion control")
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_bbr.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index c798788877e2..cb8db347c680 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -83,7 +83,8 @@ struct bbr {
 		cwnd_gain:10,	/* current gain for setting cwnd */
 		full_bw_cnt:3,	/* number of rounds without large bw gains */
 		cycle_idx:3,	/* current index in pacing_gain cycle array */
-		unused_b:6;
+		has_seen_rtt:1, /* have we seen an RTT sample yet? */
+		unused_b:5;
 	u32	prior_cwnd;	/* prior cwnd upon entering loss recovery */
 	u32	full_bw;	/* recent bw, to estimate if pipe is full */
 };
@@ -196,11 +197,13 @@ static u32 bbr_bw_to_pacing_rate(struct sock *sk, u32 bw, int gain)
 static void bbr_init_pacing_rate_from_rtt(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	struct bbr *bbr = inet_csk_ca(sk);
 	u64 bw;
 	u32 rtt_us;
 
 	if (tp->srtt_us) {		/* any RTT sample yet? */
 		rtt_us = max(tp->srtt_us >> 3, 1U);
+		bbr->has_seen_rtt = 1;
 	} else {			 /* no RTT sample yet */
 		rtt_us = USEC_PER_MSEC;	 /* use nominal default RTT */
 	}
@@ -218,8 +221,12 @@ static void bbr_init_pacing_rate_from_rtt(struct sock *sk)
  */
 static void bbr_set_pacing_rate(struct sock *sk, u32 bw, int gain)
 {
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct bbr *bbr = inet_csk_ca(sk);
 	u32 rate = bbr_bw_to_pacing_rate(sk, bw, gain);
 
+	if (unlikely(!bbr->has_seen_rtt && tp->srtt_us))
+		bbr_init_pacing_rate_from_rtt(sk);
 	if (bbr_full_bw_reached(sk) || rate > sk->sk_pacing_rate)
 		sk->sk_pacing_rate = rate;
 }
@@ -808,6 +815,7 @@ static void bbr_init(struct sock *sk)
 
 	minmax_reset(&bbr->bw, bbr->rtt_cnt, 0);  /* init max bw to 0 */
 
+	bbr->has_seen_rtt = 0;
 	bbr_init_pacing_rate_from_rtt(sk);
 
 	bbr->restore_cwnd = 0;
-- 
2.13.4


From 538b7e58eee137e7c56f28d0da75a06edf072471 Mon Sep 17 00:00:00 2001
From: Alexander Potapenko <glider@google.com>
Date: Mon, 17 Jul 2017 12:35:58 +0200
Subject: [PATCH 06/28] ipv4: ipv6: initialize treq->txhash in
 cookie_v[46]_check()

[ Upstream commit 18bcf2907df935981266532e1e0d052aff2e6fae ]

KMSAN reported use of uninitialized memory in skb_set_hash_from_sk(),
which originated from the TCP request socket created in
cookie_v6_check():

 ==================================================================
 BUG: KMSAN: use of uninitialized memory in tcp_transmit_skb+0xf77/0x3ec0
 CPU: 1 PID: 2949 Comm: syz-execprog Not tainted 4.11.0-rc5+ #2931
 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
 TCP: request_sock_TCPv6: Possible SYN flooding on port 20028. Sending cookies.  Check SNMP counters.
 Call Trace:
  <IRQ>
  __dump_stack lib/dump_stack.c:16
  dump_stack+0x172/0x1c0 lib/dump_stack.c:52
  kmsan_report+0x12a/0x180 mm/kmsan/kmsan.c:927
  __msan_warning_32+0x61/0xb0 mm/kmsan/kmsan_instr.c:469
  skb_set_hash_from_sk ./include/net/sock.h:2011
  tcp_transmit_skb+0xf77/0x3ec0 net/ipv4/tcp_output.c:983
  tcp_send_ack+0x75b/0x830 net/ipv4/tcp_output.c:3493
  tcp_delack_timer_handler+0x9a6/0xb90 net/ipv4/tcp_timer.c:284
  tcp_delack_timer+0x1b0/0x310 net/ipv4/tcp_timer.c:309
  call_timer_fn+0x240/0x520 kernel/time/timer.c:1268
  expire_timers kernel/time/timer.c:1307
  __run_timers+0xc13/0xf10 kernel/time/timer.c:1601
  run_timer_softirq+0x36/0xa0 kernel/time/timer.c:1614
  __do_softirq+0x485/0x942 kernel/softirq.c:284
  invoke_softirq kernel/softirq.c:364
  irq_exit+0x1fa/0x230 kernel/softirq.c:405
  exiting_irq+0xe/0x10 ./arch/x86/include/asm/apic.h:657
  smp_apic_timer_interrupt+0x5a/0x80 arch/x86/kernel/apic/apic.c:966
  apic_timer_interrupt+0x86/0x90 arch/x86/entry/entry_64.S:489
 RIP: 0010:native_restore_fl ./arch/x86/include/asm/irqflags.h:36
 RIP: 0010:arch_local_irq_restore ./arch/x86/include/asm/irqflags.h:77
 RIP: 0010:__msan_poison_alloca+0xed/0x120 mm/kmsan/kmsan_instr.c:440
 RSP: 0018:ffff880024917cd8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff10
 RAX: 0000000000000246 RBX: ffff8800224c0000 RCX: 0000000000000005
 RDX: 0000000000000004 RSI: ffff880000000000 RDI: ffffea0000b6d770
 RBP: ffff880024917d58 R08: 0000000000000dd8 R09: 0000000000000004
 R10: 0000160000000000 R11: 0000000000000000 R12: ffffffff85abf810
 R13: ffff880024917dd8 R14: 0000000000000010 R15: ffffffff81cabde4
  </IRQ>
  poll_select_copy_remaining+0xac/0x6b0 fs/select.c:293
  SYSC_select+0x4b4/0x4e0 fs/select.c:653
  SyS_select+0x76/0xa0 fs/select.c:634
  entry_SYSCALL_64_fastpath+0x13/0x94 arch/x86/entry/entry_64.S:204
 RIP: 0033:0x4597e7
 RSP: 002b:000000c420037ee0 EFLAGS: 00000246 ORIG_RAX: 0000000000000017
 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00000000004597e7
 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
 RBP: 000000c420037ef0 R08: 000000c420037ee0 R09: 0000000000000059
 R10: 0000000000000000 R11: 0000000000000246 R12: 000000000042dc20
 R13: 00000000000000f3 R14: 0000000000000030 R15: 0000000000000003
 chained origin:
  save_stack_trace+0x37/0x40 arch/x86/kernel/stacktrace.c:59
  kmsan_save_stack_with_flags mm/kmsan/kmsan.c:302
  kmsan_save_stack mm/kmsan/kmsan.c:317
  kmsan_internal_chain_origin+0x12a/0x1f0 mm/kmsan/kmsan.c:547
  __msan_store_shadow_origin_4+0xac/0x110 mm/kmsan/kmsan_instr.c:259
  tcp_create_openreq_child+0x709/0x1ae0 net/ipv4/tcp_minisocks.c:472
  tcp_v6_syn_recv_sock+0x7eb/0x2a30 net/ipv6/tcp_ipv6.c:1103
  tcp_get_cookie_sock+0x136/0x5f0 net/ipv4/syncookies.c:212
  cookie_v6_check+0x17a9/0x1b50 net/ipv6/syncookies.c:245
  tcp_v6_cookie_check net/ipv6/tcp_ipv6.c:989
  tcp_v6_do_rcv+0xdd8/0x1c60 net/ipv6/tcp_ipv6.c:1298
  tcp_v6_rcv+0x41a3/0x4f00 net/ipv6/tcp_ipv6.c:1487
  ip6_input_finish+0x82f/0x1ee0 net/ipv6/ip6_input.c:279
  NF_HOOK ./include/linux/netfilter.h:257
  ip6_input+0x239/0x290 net/ipv6/ip6_input.c:322
  dst_input ./include/net/dst.h:492
  ip6_rcv_finish net/ipv6/ip6_input.c:69
  NF_HOOK ./include/linux/netfilter.h:257
  ipv6_rcv+0x1dbd/0x22e0 net/ipv6/ip6_input.c:203
  __netif_receive_skb_core+0x2f6f/0x3a20 net/core/dev.c:4208
  __netif_receive_skb net/core/dev.c:4246
  process_backlog+0x667/0xba0 net/core/dev.c:4866
  napi_poll net/core/dev.c:5268
  net_rx_action+0xc95/0x1590 net/core/dev.c:5333
  __do_softirq+0x485/0x942 kernel/softirq.c:284
 origin:
  save_stack_trace+0x37/0x40 arch/x86/kernel/stacktrace.c:59
  kmsan_save_stack_with_flags mm/kmsan/kmsan.c:302
  kmsan_internal_poison_shadow+0xb1/0x1a0 mm/kmsan/kmsan.c:198
  kmsan_kmalloc+0x7f/0xe0 mm/kmsan/kmsan.c:337
  kmem_cache_alloc+0x1c2/0x1e0 mm/slub.c:2766
  reqsk_alloc ./include/net/request_sock.h:87
  inet_reqsk_alloc+0xa4/0x5b0 net/ipv4/tcp_input.c:6200
  cookie_v6_check+0x4f4/0x1b50 net/ipv6/syncookies.c:169
  tcp_v6_cookie_check net/ipv6/tcp_ipv6.c:989
  tcp_v6_do_rcv+0xdd8/0x1c60 net/ipv6/tcp_ipv6.c:1298
  tcp_v6_rcv+0x41a3/0x4f00 net/ipv6/tcp_ipv6.c:1487
  ip6_input_finish+0x82f/0x1ee0 net/ipv6/ip6_input.c:279
  NF_HOOK ./include/linux/netfilter.h:257
  ip6_input+0x239/0x290 net/ipv6/ip6_input.c:322
  dst_input ./include/net/dst.h:492
  ip6_rcv_finish net/ipv6/ip6_input.c:69
  NF_HOOK ./include/linux/netfilter.h:257
  ipv6_rcv+0x1dbd/0x22e0 net/ipv6/ip6_input.c:203
  __netif_receive_skb_core+0x2f6f/0x3a20 net/core/dev.c:4208
  __netif_receive_skb net/core/dev.c:4246
  process_backlog+0x667/0xba0 net/core/dev.c:4866
  napi_poll net/core/dev.c:5268
  net_rx_action+0xc95/0x1590 net/core/dev.c:5333
  __do_softirq+0x485/0x942 kernel/softirq.c:284
 ==================================================================

Similar error is reported for cookie_v4_check().

Fixes: 58d607d3e52f ("tcp: provide skb->hash to synack packets")
Signed-off-by: Alexander Potapenko <glider@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/syncookies.c | 1 +
 net/ipv6/syncookies.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index e3c4043c27de..b6f710d515d0 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -334,6 +334,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	treq = tcp_rsk(req);
 	treq->rcv_isn		= ntohl(th->seq) - 1;
 	treq->snt_isn		= cookie;
+	treq->txhash		= net_tx_rndhash();
 	req->mss		= mss;
 	ireq->ir_num		= ntohs(th->dest);
 	ireq->ir_rmt_port	= th->source;
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 59c483937aec..7a86433d8896 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -209,6 +209,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	treq->snt_synack.v64	= 0;
 	treq->rcv_isn = ntohl(th->seq) - 1;
 	treq->snt_isn = cookie;
+	treq->txhash = net_tx_rndhash();
 
 	/*
 	 * We need to lookup the dst_entry to get the correct window size.
-- 
2.13.4


From 76317a2b6210084f897868176234cca508bb37e3 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Wed, 19 Jul 2017 13:33:24 -0700
Subject: [PATCH 07/28] net: Zero terminate ifr_name in dev_ifname().

[ Upstream commit 63679112c536289826fec61c917621de95ba2ade ]

The ifr.ifr_name is passed around and assumed to be NULL terminated.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev_ioctl.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index b94b1d293506..151e047ce072 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -28,6 +28,7 @@ static int dev_ifname(struct net *net, struct ifreq __user *arg)
 
 	if (copy_from_user(&ifr, arg, sizeof(struct ifreq)))
 		return -EFAULT;
+	ifr.ifr_name[IFNAMSIZ-1] = 0;
 
 	error = netdev_get_name(net, ifr.ifr_name, ifr.ifr_ifindex);
 	if (error)
-- 
2.13.4


From c44a4116b2f51ebf8164902891bc9c2ffc6d0759 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Wed, 19 Jul 2017 22:28:55 +0200
Subject: [PATCH 08/28] ipv6: avoid overflow of offset in ip6_find_1stfragopt

[ Upstream commit 6399f1fae4ec29fab5ec76070435555e256ca3a6 ]

In some cases, offset can overflow and can cause an infinite loop in
ip6_find_1stfragopt(). Make it unsigned int to prevent the overflow, and
cap it at IPV6_MAXPLEN, since packets larger than that should be invalid.

This problem has been here since before the beginning of git history.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/output_core.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index e9065b8d3af8..abb2c307fbe8 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -78,7 +78,7 @@ EXPORT_SYMBOL(ipv6_select_ident);
 
 int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 {
-	u16 offset = sizeof(struct ipv6hdr);
+	unsigned int offset = sizeof(struct ipv6hdr);
 	unsigned int packet_len = skb_tail_pointer(skb) -
 		skb_network_header(skb);
 	int found_rhdr = 0;
@@ -86,6 +86,7 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 
 	while (offset <= packet_len) {
 		struct ipv6_opt_hdr *exthdr;
+		unsigned int len;
 
 		switch (**nexthdr) {
 
@@ -111,7 +112,10 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 
 		exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) +
 						 offset);
-		offset += ipv6_optlen(exthdr);
+		len = ipv6_optlen(exthdr);
+		if (len + offset >= IPV6_MAXPLEN)
+			return -EINVAL;
+		offset += len;
 		*nexthdr = &exthdr->nexthdr;
 	}
 
-- 
2.13.4


From 9acca17bcba0c37605115c594db4b1f8b1fa5da4 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 20 Jul 2017 12:25:22 -0700
Subject: [PATCH 09/28] net: dsa: b53: Add missing ARL entries for BCM53125

[ Upstream commit be35e8c516c1915a3035d266a2015b41f73ba3f9 ]

The BCM53125 entry was missing an arl_entries member which would
basically prevent the ARL search from terminating properly. This switch
has 4 ARL entries, so add that.

Fixes: 1da6df85c6fb ("net: dsa: b53: Implement ARL add/del/dump operations")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/b53/b53_common.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 947adda3397d..3ec573c13dac 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -1558,6 +1558,7 @@ static const struct b53_chip_data b53_switch_chips[] = {
 		.dev_name = "BCM53125",
 		.vlans = 4096,
 		.enabled_ports = 0xff,
+		.arl_entries = 4,
 		.cpu_port = B53_CPU_PORT,
 		.vta_regs = B53_VTA_REGS,
 		.duplex_reg = B53_DUPLEX_STAT_GE,
-- 
2.13.4


From baa2622224f76b29726f5aa5ac7368b58249db24 Mon Sep 17 00:00:00 2001
From: Mahesh Bandewar <maheshb@google.com>
Date: Wed, 19 Jul 2017 15:41:33 -0700
Subject: [PATCH 10/28] ipv4: initialize fib_trie prior to
 register_netdev_notifier call.

[ Upstream commit 8799a221f5944a7d74516ecf46d58c28ec1d1f75 ]

Net stack initialization currently initializes fib-trie after the
first call to netdevice_notifier() call. In fact fib_trie initialization
needs to happen before first rtnl_register(). It does not cause any problem
since there are no devices UP at this moment, but trying to bring 'lo'
UP at initialization would make this assumption wrong and exposes the issue.

Fixes following crash

 Call Trace:
  ? alternate_node_alloc+0x76/0xa0
  fib_table_insert+0x1b7/0x4b0
  fib_magic.isra.17+0xea/0x120
  fib_add_ifaddr+0x7b/0x190
  fib_netdev_event+0xc0/0x130
  register_netdevice_notifier+0x1c1/0x1d0
  ip_fib_init+0x72/0x85
  ip_rt_init+0x187/0x1e9
  ip_init+0xe/0x1a
  inet_init+0x171/0x26c
  ? ipv4_offload_init+0x66/0x66
  do_one_initcall+0x43/0x160
  kernel_init_freeable+0x191/0x219
  ? rest_init+0x80/0x80
  kernel_init+0xe/0x150
  ret_from_fork+0x22/0x30
 Code: f6 46 23 04 74 86 4c 89 f7 e8 ae 45 01 00 49 89 c7 4d 85 ff 0f 85 7b ff ff ff 31 db eb 08 4c 89 ff e8 16 47 01 00 48 8b 44 24 38 <45> 8b 6e 14 4d 63 76 74 48 89 04 24 0f 1f 44 00 00 48 83 c4 08
 RIP: kmem_cache_alloc+0xcf/0x1c0 RSP: ffff9b1500017c28
 CR2: 0000000000000014

Fixes: 7b1a74fdbb9e ("[NETNS]: Refactor fib initialization so it can handle multiple namespaces.")
Fixes: 7f9b80529b8a ("[IPV4]: fib hash|trie initialization")

Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_frontend.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 3d92534c4450..968d8e165e3d 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1319,13 +1319,14 @@ static struct pernet_operations fib_net_ops = {
 
 void __init ip_fib_init(void)
 {
-	rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, NULL);
-	rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, NULL);
-	rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, NULL);
+	fib_trie_init();
 
 	register_pernet_subsys(&fib_net_ops);
+
 	register_netdevice_notifier(&fib_netdev_notifier);
 	register_inetaddr_notifier(&fib_inetaddr_notifier);
 
-	fib_trie_init();
+	rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, NULL);
+	rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, NULL);
+	rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, NULL);
 }
-- 
2.13.4


From e4e548963576b45c944c131437b253818077efa0 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Thu, 20 Jul 2017 11:27:57 -0700
Subject: [PATCH 11/28] rtnetlink: allocate more memory for
 dev_set_mac_address()

[ Upstream commit 153711f9421be5dbc973dc57a4109dc9d54c89b1 ]

virtnet_set_mac_address() interprets mac address as struct
sockaddr, but upper layer only allocates dev->addr_len
which is ETH_ALEN + sizeof(sa_family_t) in this case.

We lack a unified definition for mac address, so just fix
the upper layer, this also allows drivers to interpret it
to struct sockaddr freely.

Reported-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 9c6fd7f83a4a..4d2629781e8b 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1965,7 +1965,8 @@ static int do_setlink(const struct sk_buff *skb,
 		struct sockaddr *sa;
 		int len;
 
-		len = sizeof(sa_family_t) + dev->addr_len;
+		len = sizeof(sa_family_t) + max_t(size_t, dev->addr_len,
+						  sizeof(*sa));
 		sa = kmalloc(len, GFP_KERNEL);
 		if (!sa) {
 			err = -ENOMEM;
-- 
2.13.4


From 5f6155d93f071f74eea0ab0086f3a9dc8f12a2d2 Mon Sep 17 00:00:00 2001
From: Thomas Jarosch <thomas.jarosch@intra2net.com>
Date: Sat, 22 Jul 2017 17:14:34 +0200
Subject: [PATCH 12/28] mcs7780: Fix initialization when CONFIG_VMAP_STACK is
 enabled

[ Upstream commit 9476d393667968b4a02afbe9d35a3558482b943e ]

DMA transfers are not allowed to buffers that are on the stack.
Therefore allocate a buffer to store the result of usb_control_message().

Fixes these bugreports:
https://bugzilla.kernel.org/show_bug.cgi?id=195217

https://bugzilla.redhat.com/show_bug.cgi?id=1421387
https://bugzilla.redhat.com/show_bug.cgi?id=1427398

Shortened kernel backtrace from 4.11.9-200.fc25.x86_64:
kernel: ------------[ cut here ]------------
kernel: WARNING: CPU: 3 PID: 2957 at drivers/usb/core/hcd.c:1587
kernel: transfer buffer not dma capable
kernel: Call Trace:
kernel: dump_stack+0x63/0x86
kernel: __warn+0xcb/0xf0
kernel: warn_slowpath_fmt+0x5a/0x80
kernel: usb_hcd_map_urb_for_dma+0x37f/0x570
kernel: ? try_to_del_timer_sync+0x53/0x80
kernel: usb_hcd_submit_urb+0x34e/0xb90
kernel: ? schedule_timeout+0x17e/0x300
kernel: ? del_timer_sync+0x50/0x50
kernel: ? __slab_free+0xa9/0x300
kernel: usb_submit_urb+0x2f4/0x560
kernel: ? urb_destroy+0x24/0x30
kernel: usb_start_wait_urb+0x6e/0x170
kernel: usb_control_msg+0xdc/0x120
kernel: mcs_get_reg+0x36/0x40 [mcs7780]
kernel: mcs_net_open+0xb5/0x5c0 [mcs7780]
...

Regression goes back to 4.9, so it's a good candidate for -stable.
Though it's the decision of the maintainer.

Thanks to Dan Williams for adding the "transfer buffer not dma capable"
warning in the first place. It instantly pointed me in the right direction.

Patch has been tested with transferring data from a Polar watch.

Signed-off-by: Thomas Jarosch <thomas.jarosch@intra2net.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/irda/mcs7780.c | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/drivers/net/irda/mcs7780.c b/drivers/net/irda/mcs7780.c
index bca6a1e72d1d..e1bb802d4a4d 100644
--- a/drivers/net/irda/mcs7780.c
+++ b/drivers/net/irda/mcs7780.c
@@ -141,9 +141,19 @@ static int mcs_set_reg(struct mcs_cb *mcs, __u16 reg, __u16 val)
 static int mcs_get_reg(struct mcs_cb *mcs, __u16 reg, __u16 * val)
 {
 	struct usb_device *dev = mcs->usbdev;
-	int ret = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), MCS_RDREQ,
-				  MCS_RD_RTYPE, 0, reg, val, 2,
-				  msecs_to_jiffies(MCS_CTRL_TIMEOUT));
+	void *dmabuf;
+	int ret;
+
+	dmabuf = kmalloc(sizeof(__u16), GFP_KERNEL);
+	if (!dmabuf)
+		return -ENOMEM;
+
+	ret = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), MCS_RDREQ,
+			      MCS_RD_RTYPE, 0, reg, dmabuf, 2,
+			      msecs_to_jiffies(MCS_CTRL_TIMEOUT));
+
+	memcpy(val, dmabuf, sizeof(__u16));
+	kfree(dmabuf);
 
 	return ret;
 }
-- 
2.13.4


From bed74f87f60b7332d663d241461e4115eb905981 Mon Sep 17 00:00:00 2001
From: Liping Zhang <zlpnobody@gmail.com>
Date: Sun, 23 Jul 2017 17:52:23 +0800
Subject: [PATCH 13/28] openvswitch: fix potential out of bound access in
 parse_ct

[ Upstream commit 69ec932e364b1ba9c3a2085fe96b76c8a3f71e7c ]

Before the 'type' is validated, we shouldn't use it to fetch the
ovs_ct_attr_lens's minlen and maxlen, else, out of bound access
may happen.

Fixes: 7f8a436eaa2c ("openvswitch: Add conntrack action")
Signed-off-by: Liping Zhang <zlpnobody@gmail.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/conntrack.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 48386bff8b4e..b28e45b691de 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -1088,8 +1088,8 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info,
 
 	nla_for_each_nested(a, attr, rem) {
 		int type = nla_type(a);
-		int maxlen = ovs_ct_attr_lens[type].maxlen;
-		int minlen = ovs_ct_attr_lens[type].minlen;
+		int maxlen;
+		int minlen;
 
 		if (type > OVS_CT_ATTR_MAX) {
 			OVS_NLERR(log,
@@ -1097,6 +1097,9 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info,
 				  type, OVS_CT_ATTR_MAX);
 			return -EINVAL;
 		}
+
+		maxlen = ovs_ct_attr_lens[type].maxlen;
+		minlen = ovs_ct_attr_lens[type].minlen;
 		if (nla_len(a) < minlen || nla_len(a) > maxlen) {
 			OVS_NLERR(log,
 				  "Conntrack attr type has unexpected length (type=%d, length=%d, expected=%d)",
-- 
2.13.4


From 8d992e4e2e92b2c66ebcb255c992859f1a49ec72 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Mon, 24 Jul 2017 10:07:32 -0700
Subject: [PATCH 14/28] packet: fix use-after-free in
 prb_retire_rx_blk_timer_expired()

[ Upstream commit c800aaf8d869f2b9b47b10c5c312fe19f0a94042 ]

There are multiple reports showing we have a use-after-free in
the timer prb_retire_rx_blk_timer_expired(), where we use struct
tpacket_kbdq_core::pkbdq, a pg_vec, after it gets freed by
free_pg_vec().

The interesting part is it is not freed via packet_release() but
via packet_setsockopt(), which means we are not closing the socket.
Looking into the big and fat function packet_set_ring(), this could
happen if we satisfy the following conditions:

1. closing == 0, not on packet_release() path
2. req->tp_block_nr == 0, we don't allocate a new pg_vec
3. rx_ring->pg_vec is already set as V3, which means we already called
   packet_set_ring() wtih req->tp_block_nr > 0 previously
4. req->tp_frame_nr == 0, pass sanity check
5. po->mapped == 0, never called mmap()

In this scenario we are clearing the old rx_ring->pg_vec, so we need
to free this pg_vec, but we don't stop the timer on this path because
of closing==0.

The timer has to be stopped as long as we need to free pg_vec, therefore
the check on closing!=0 is wrong, we should check pg_vec!=NULL instead.

Thanks to liujian for testing different fixes.

Reported-by: alexander.levin@verizon.com
Reported-by: Dave Jones <davej@codemonkey.org.uk>
Reported-by: liujian (CE) <liujian56@huawei.com>
Tested-by: liujian (CE) <liujian56@huawei.com>
Cc: Ding Tianhong <dingtianhong@huawei.com>
Cc: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 6a563e6e24de..365c83fcee02 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -4322,7 +4322,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 		register_prot_hook(sk);
 	}
 	spin_unlock(&po->bind_lock);
-	if (closing && (po->tp_version > TPACKET_V2)) {
+	if (pg_vec && (po->tp_version > TPACKET_V2)) {
 		/* Because we don't support block-based V3 on tx-ring */
 		if (!tx_ring)
 			prb_shutdown_retire_blk_timer(po, rb_queue);
-- 
2.13.4


From 9a03fd9e19ec6e65dd36d36855c7dcc5310eb6c9 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Mon, 24 Jul 2017 23:14:28 +0200
Subject: [PATCH 15/28] ipv6: Don't increase IPSTATS_MIB_FRAGFAILS twice in
 ip6_fragment()

[ Upstream commit afce615aaabfbaad02550e75c0bec106dafa1adf ]

RFC 2465 defines ipv6IfStatsOutFragFails as:

	"The number of IPv6 datagrams that have been discarded
	 because they needed to be fragmented at this output
	 interface but could not be."

The existing implementation, instead, would increase the counter
twice in case we fail to allocate room for single fragments:
once for the fragment, once for the datagram.

This didn't look intentional though. In one of the two affected
affected failure paths, the double increase was simply a result
of a new 'goto fail' statement, introduced to avoid a skb leak.
The other path appears to be affected since at least 2.6.12-rc2.

Reported-by: Sabrina Dubroca <sdubroca@redhat.com>
Fixes: 1d325d217c7f ("ipv6: ip6_fragment: fix headroom tests and skb leak")
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_output.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 5a4b8e7bcedd..efe811c6eccf 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -662,8 +662,6 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		*prevhdr = NEXTHDR_FRAGMENT;
 		tmp_hdr = kmemdup(skb_network_header(skb), hlen, GFP_ATOMIC);
 		if (!tmp_hdr) {
-			IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
-				      IPSTATS_MIB_FRAGFAILS);
 			err = -ENOMEM;
 			goto fail;
 		}
@@ -782,8 +780,6 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		frag = alloc_skb(len + hlen + sizeof(struct frag_hdr) +
 				 hroom + troom, GFP_ATOMIC);
 		if (!frag) {
-			IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
-				      IPSTATS_MIB_FRAGFAILS);
 			err = -ENOMEM;
 			goto fail;
 		}
-- 
2.13.4


From 13f0b414ecacd548515c5f3101b463fb1937bfff Mon Sep 17 00:00:00 2001
From: Marc Gonzalez <marc_gonzalez@sigmadesigns.com>
Date: Tue, 25 Jul 2017 14:35:03 +0200
Subject: [PATCH 16/28] net: ethernet: nb8800: Handle all 4 RGMII modes
 identically

[ Upstream commit 4813497b537c6208c90d6cbecac5072d347de900 ]

Before commit bf8f6952a233 ("Add blurb about RGMII") it was unclear
whose responsibility it was to insert the required clock skew, and
in hindsight, some PHY drivers got it wrong. The solution forward
is to introduce a new property, explicitly requiring skew from the
node to which it is attached. In the interim, this driver will handle
all 4 RGMII modes identically (no skew).

Fixes: 52dfc8301248 ("net: ethernet: add driver for Aurora VLSI NB8800 Ethernet controller")
Signed-off-by: Marc Gonzalez <marc_gonzalez@sigmadesigns.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aurora/nb8800.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c
index e078d8da978c..29d29af612d1 100644
--- a/drivers/net/ethernet/aurora/nb8800.c
+++ b/drivers/net/ethernet/aurora/nb8800.c
@@ -609,7 +609,7 @@ static void nb8800_mac_config(struct net_device *dev)
 		mac_mode |= HALF_DUPLEX;
 
 	if (gigabit) {
-		if (priv->phy_mode == PHY_INTERFACE_MODE_RGMII)
+		if (phy_interface_is_rgmii(dev->phydev))
 			mac_mode |= RGMII_MODE;
 
 		mac_mode |= GMAC_MODE;
@@ -1277,11 +1277,10 @@ static int nb8800_tangox_init(struct net_device *dev)
 		break;
 
 	case PHY_INTERFACE_MODE_RGMII:
-		pad_mode = PAD_MODE_RGMII;
-		break;
-
+	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
 	case PHY_INTERFACE_MODE_RGMII_TXID:
-		pad_mode = PAD_MODE_RGMII | PAD_MODE_GTX_CLK_DELAY;
+		pad_mode = PAD_MODE_RGMII;
 		break;
 
 	default:
-- 
2.13.4


From f2e71caea8612ce2e0259f5a75351fed95c463b4 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 26 Jul 2017 14:19:09 +0800
Subject: [PATCH 17/28] dccp: fix a memleak that dccp_ipv6 doesn't put reqsk
 properly

[ Upstream commit 0c2232b0a71db0ac1d22f751aa1ac0cadb950fd2 ]

In dccp_v6_conn_request, after reqsk gets alloced and hashed into
ehash table, reqsk's refcnt is set 3. one is for req->rsk_timer,
one is for hlist, and the other one is for current using.

The problem is when dccp_v6_conn_request returns and finishes using
reqsk, it doesn't put reqsk. This will cause reqsk refcnt leaks and
reqsk obj never gets freed.

Jianlin found this issue when running dccp_memleak.c in a loop, the
system memory would run out.

dccp_memleak.c:
  int s1 = socket(PF_INET6, 6, IPPROTO_IP);
  bind(s1, &sa1, 0x20);
  listen(s1, 0x9);
  int s2 = socket(PF_INET6, 6, IPPROTO_IP);
  connect(s2, &sa1, 0x20);
  close(s1);
  close(s2);

This patch is to put the reqsk before dccp_v6_conn_request returns,
just as what tcp_conn_request does.

Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ipv6.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 2ac9d2a1aaab..28e8252cc5ea 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -380,6 +380,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 		goto drop_and_free;
 
 	inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT);
+	reqsk_put(req);
 	return 0;
 
 drop_and_free:
-- 
2.13.4


From 602b0fdb4f733c9269de14b6c0b838f560853d6f Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 26 Jul 2017 14:19:46 +0800
Subject: [PATCH 18/28] dccp: fix a memleak that dccp_ipv4 doesn't put reqsk
 properly

[ Upstream commit b7953d3c0e30a5fc944f6b7bd0bcceb0794bcd85 ]

The patch "dccp: fix a memleak that dccp_ipv6 doesn't put reqsk
properly" fixed reqsk refcnt leak for dccp_ipv6. The same issue
exists on dccp_ipv4.

This patch is to fix it for dccp_ipv4.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ipv4.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 86b0933ecd45..8fc160098e11 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -637,6 +637,7 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 		goto drop_and_free;
 
 	inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT);
+	reqsk_put(req);
 	return 0;
 
 drop_and_free:
-- 
2.13.4


From d7fc67089887f40af1b5bb5e7652b1b9d2dfd6ef Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 26 Jul 2017 14:20:15 +0800
Subject: [PATCH 19/28] dccp: fix a memleak for dccp_feat_init err process

[ Upstream commit e90ce2fc27cad7e7b1e72b9e66201a7a4c124c2b ]

In dccp_feat_init, when ccid_get_builtin_ccids failsto alloc
memory for rx.val, it should free tx.val before returning an
error.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/feat.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/dccp/feat.c b/net/dccp/feat.c
index 1704948e6a12..f227f002c73d 100644
--- a/net/dccp/feat.c
+++ b/net/dccp/feat.c
@@ -1471,9 +1471,12 @@ int dccp_feat_init(struct sock *sk)
 	 * singleton values (which always leads to failure).
 	 * These settings can still (later) be overridden via sockopts.
 	 */
-	if (ccid_get_builtin_ccids(&tx.val, &tx.len) ||
-	    ccid_get_builtin_ccids(&rx.val, &rx.len))
+	if (ccid_get_builtin_ccids(&tx.val, &tx.len))
 		return -ENOBUFS;
+	if (ccid_get_builtin_ccids(&rx.val, &rx.len)) {
+		kfree(tx.val);
+		return -ENOBUFS;
+	}
 
 	if (!dccp_feat_prefer(sysctl_dccp_tx_ccid, tx.val, tx.len) ||
 	    !dccp_feat_prefer(sysctl_dccp_rx_ccid, rx.val, rx.len))
-- 
2.13.4


From a46cc1f53dad7e4e26b684be0a6cc591affd0c42 Mon Sep 17 00:00:00 2001
From: Alexander Potapenko <glider@google.com>
Date: Fri, 14 Jul 2017 18:32:45 +0200
Subject: [PATCH 20/28] sctp: don't dereference ptr before leaving
 _sctp_walk_{params, errors}()

[ Upstream commit b1f5bfc27a19f214006b9b4db7b9126df2dfdf5a ]

If the length field of the iterator (|pos.p| or |err|) is past the end
of the chunk, we shouldn't access it.

This bug has been detected by KMSAN. For the following pair of system
calls:

  socket(PF_INET6, SOCK_STREAM, 0x84 /* IPPROTO_??? */) = 3
  sendto(3, "A", 1, MSG_OOB, {sa_family=AF_INET6, sin6_port=htons(0),
         inet_pton(AF_INET6, "::1", &sin6_addr), sin6_flowinfo=0,
         sin6_scope_id=0}, 28) = 1

the tool has reported a use of uninitialized memory:

  ==================================================================
  BUG: KMSAN: use of uninitialized memory in sctp_rcv+0x17b8/0x43b0
  CPU: 1 PID: 2940 Comm: probe Not tainted 4.11.0-rc5+ #2926
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs
  01/01/2011
  Call Trace:
   <IRQ>
   __dump_stack lib/dump_stack.c:16
   dump_stack+0x172/0x1c0 lib/dump_stack.c:52
   kmsan_report+0x12a/0x180 mm/kmsan/kmsan.c:927
   __msan_warning_32+0x61/0xb0 mm/kmsan/kmsan_instr.c:469
   __sctp_rcv_init_lookup net/sctp/input.c:1074
   __sctp_rcv_lookup_harder net/sctp/input.c:1233
   __sctp_rcv_lookup net/sctp/input.c:1255
   sctp_rcv+0x17b8/0x43b0 net/sctp/input.c:170
   sctp6_rcv+0x32/0x70 net/sctp/ipv6.c:984
   ip6_input_finish+0x82f/0x1ee0 net/ipv6/ip6_input.c:279
   NF_HOOK ./include/linux/netfilter.h:257
   ip6_input+0x239/0x290 net/ipv6/ip6_input.c:322
   dst_input ./include/net/dst.h:492
   ip6_rcv_finish net/ipv6/ip6_input.c:69
   NF_HOOK ./include/linux/netfilter.h:257
   ipv6_rcv+0x1dbd/0x22e0 net/ipv6/ip6_input.c:203
   __netif_receive_skb_core+0x2f6f/0x3a20 net/core/dev.c:4208
   __netif_receive_skb net/core/dev.c:4246
   process_backlog+0x667/0xba0 net/core/dev.c:4866
   napi_poll net/core/dev.c:5268
   net_rx_action+0xc95/0x1590 net/core/dev.c:5333
   __do_softirq+0x485/0x942 kernel/softirq.c:284
   do_softirq_own_stack+0x1c/0x30 arch/x86/entry/entry_64.S:902
   </IRQ>
   do_softirq kernel/softirq.c:328
   __local_bh_enable_ip+0x25b/0x290 kernel/softirq.c:181
   local_bh_enable+0x37/0x40 ./include/linux/bottom_half.h:31
   rcu_read_unlock_bh ./include/linux/rcupdate.h:931
   ip6_finish_output2+0x19b2/0x1cf0 net/ipv6/ip6_output.c:124
   ip6_finish_output+0x764/0x970 net/ipv6/ip6_output.c:149
   NF_HOOK_COND ./include/linux/netfilter.h:246
   ip6_output+0x456/0x520 net/ipv6/ip6_output.c:163
   dst_output ./include/net/dst.h:486
   NF_HOOK ./include/linux/netfilter.h:257
   ip6_xmit+0x1841/0x1c00 net/ipv6/ip6_output.c:261
   sctp_v6_xmit+0x3b7/0x470 net/sctp/ipv6.c:225
   sctp_packet_transmit+0x38cb/0x3a20 net/sctp/output.c:632
   sctp_outq_flush+0xeb3/0x46e0 net/sctp/outqueue.c:885
   sctp_outq_uncork+0xb2/0xd0 net/sctp/outqueue.c:750
   sctp_side_effects net/sctp/sm_sideeffect.c:1773
   sctp_do_sm+0x6962/0x6ec0 net/sctp/sm_sideeffect.c:1147
   sctp_primitive_ASSOCIATE+0x12c/0x160 net/sctp/primitive.c:88
   sctp_sendmsg+0x43e5/0x4f90 net/sctp/socket.c:1954
   inet_sendmsg+0x498/0x670 net/ipv4/af_inet.c:762
   sock_sendmsg_nosec net/socket.c:633
   sock_sendmsg net/socket.c:643
   SYSC_sendto+0x608/0x710 net/socket.c:1696
   SyS_sendto+0x8a/0xb0 net/socket.c:1664
   do_syscall_64+0xe6/0x130 arch/x86/entry/common.c:285
   entry_SYSCALL64_slow_path+0x25/0x25 arch/x86/entry/entry_64.S:246
  RIP: 0033:0x401133
  RSP: 002b:00007fff6d99cd38 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
  RAX: ffffffffffffffda RBX: 00000000004002b0 RCX: 0000000000401133
  RDX: 0000000000000001 RSI: 0000000000494088 RDI: 0000000000000003
  RBP: 00007fff6d99cd90 R08: 00007fff6d99cd50 R09: 000000000000001c
  R10: 0000000000000001 R11: 0000000000000246 R12: 0000000000000000
  R13: 00000000004063d0 R14: 0000000000406460 R15: 0000000000000000
  origin:
   save_stack_trace+0x37/0x40 arch/x86/kernel/stacktrace.c:59
   kmsan_save_stack_with_flags mm/kmsan/kmsan.c:302
   kmsan_internal_poison_shadow+0xb1/0x1a0 mm/kmsan/kmsan.c:198
   kmsan_poison_shadow+0x6d/0xc0 mm/kmsan/kmsan.c:211
   slab_alloc_node mm/slub.c:2743
   __kmalloc_node_track_caller+0x200/0x360 mm/slub.c:4351
   __kmalloc_reserve net/core/skbuff.c:138
   __alloc_skb+0x26b/0x840 net/core/skbuff.c:231
   alloc_skb ./include/linux/skbuff.h:933
   sctp_packet_transmit+0x31e/0x3a20 net/sctp/output.c:570
   sctp_outq_flush+0xeb3/0x46e0 net/sctp/outqueue.c:885
   sctp_outq_uncork+0xb2/0xd0 net/sctp/outqueue.c:750
   sctp_side_effects net/sctp/sm_sideeffect.c:1773
   sctp_do_sm+0x6962/0x6ec0 net/sctp/sm_sideeffect.c:1147
   sctp_primitive_ASSOCIATE+0x12c/0x160 net/sctp/primitive.c:88
   sctp_sendmsg+0x43e5/0x4f90 net/sctp/socket.c:1954
   inet_sendmsg+0x498/0x670 net/ipv4/af_inet.c:762
   sock_sendmsg_nosec net/socket.c:633
   sock_sendmsg net/socket.c:643
   SYSC_sendto+0x608/0x710 net/socket.c:1696
   SyS_sendto+0x8a/0xb0 net/socket.c:1664
   do_syscall_64+0xe6/0x130 arch/x86/entry/common.c:285
   return_from_SYSCALL_64+0x0/0x6a arch/x86/entry/entry_64.S:246
  ==================================================================

Signed-off-by: Alexander Potapenko <glider@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/sctp.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 31acc3f4f132..02170bbb4490 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -460,6 +460,8 @@ _sctp_walk_params((pos), (chunk), ntohs((chunk)->chunk_hdr.length), member)
 
 #define _sctp_walk_params(pos, chunk, end, member)\
 for (pos.v = chunk->member;\
+     (pos.v + offsetof(struct sctp_paramhdr, length) + sizeof(pos.p->length) <\
+      (void *)chunk + end) &&\
      pos.v <= (void *)chunk + end - ntohs(pos.p->length) &&\
      ntohs(pos.p->length) >= sizeof(sctp_paramhdr_t);\
      pos.v += SCTP_PAD4(ntohs(pos.p->length)))
@@ -470,6 +472,8 @@ _sctp_walk_errors((err), (chunk_hdr), ntohs((chunk_hdr)->length))
 #define _sctp_walk_errors(err, chunk_hdr, end)\
 for (err = (sctp_errhdr_t *)((void *)chunk_hdr + \
 	    sizeof(sctp_chunkhdr_t));\
+     ((void *)err + offsetof(sctp_errhdr_t, length) + sizeof(err->length) <\
+      (void *)chunk_hdr + end) &&\
      (void *)err <= (void *)chunk_hdr + end - ntohs(err->length) &&\
      ntohs(err->length) >= sizeof(sctp_errhdr_t); \
      err = (sctp_errhdr_t *)((void *)err + SCTP_PAD4(ntohs(err->length))))
-- 
2.13.4


From d6c35f36322951cd934b82872ca8696e45288637 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 26 Jul 2017 16:24:59 +0800
Subject: [PATCH 21/28] sctp: fix the check for _sctp_walk_params and
 _sctp_walk_errors

[ Upstream commit 6b84202c946cd3da3a8daa92c682510e9ed80321 ]

Commit b1f5bfc27a19 ("sctp: don't dereference ptr before leaving
_sctp_walk_{params, errors}()") tried to fix the issue that it
may overstep the chunk end for _sctp_walk_{params, errors} with
'chunk_end > offset(length) + sizeof(length)'.

But it introduced a side effect: When processing INIT, it verifies
the chunks with 'param.v == chunk_end' after iterating all params
by sctp_walk_params(). With the check 'chunk_end > offset(length)
+ sizeof(length)', it would return when the last param is not yet
accessed. Because the last param usually is fwdtsn supported param
whose size is 4 and 'chunk_end == offset(length) + sizeof(length)'

This is a badly issue even causing sctp couldn't process 4-shakes.
Client would always get abort when connecting to server, due to
the failure of INIT chunk verification on server.

The patch is to use 'chunk_end <= offset(length) + sizeof(length)'
instead of 'chunk_end < offset(length) + sizeof(length)' for both
_sctp_walk_params and _sctp_walk_errors.

Fixes: b1f5bfc27a19 ("sctp: don't dereference ptr before leaving _sctp_walk_{params, errors}()")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/sctp.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 02170bbb4490..61d9ce89d10d 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -460,7 +460,7 @@ _sctp_walk_params((pos), (chunk), ntohs((chunk)->chunk_hdr.length), member)
 
 #define _sctp_walk_params(pos, chunk, end, member)\
 for (pos.v = chunk->member;\
-     (pos.v + offsetof(struct sctp_paramhdr, length) + sizeof(pos.p->length) <\
+     (pos.v + offsetof(struct sctp_paramhdr, length) + sizeof(pos.p->length) <=\
       (void *)chunk + end) &&\
      pos.v <= (void *)chunk + end - ntohs(pos.p->length) &&\
      ntohs(pos.p->length) >= sizeof(sctp_paramhdr_t);\
@@ -472,7 +472,7 @@ _sctp_walk_errors((err), (chunk_hdr), ntohs((chunk_hdr)->length))
 #define _sctp_walk_errors(err, chunk_hdr, end)\
 for (err = (sctp_errhdr_t *)((void *)chunk_hdr + \
 	    sizeof(sctp_chunkhdr_t));\
-     ((void *)err + offsetof(sctp_errhdr_t, length) + sizeof(err->length) <\
+     ((void *)err + offsetof(sctp_errhdr_t, length) + sizeof(err->length) <=\
       (void *)chunk_hdr + end) &&\
      (void *)err <= (void *)chunk_hdr + end - ntohs(err->length) &&\
      ntohs(err->length) >= sizeof(sctp_errhdr_t); \
-- 
2.13.4


From 3b34102561f988bb02259b506f2edbd5e7e338f7 Mon Sep 17 00:00:00 2001
From: Aviv Heller <avivh@mellanox.com>
Date: Sun, 2 Jul 2017 19:13:43 +0300
Subject: [PATCH 22/28] net/mlx5: Consider tx_enabled in all modes on remap

[ Upstream commit dc798b4cc0f2a06e7ad7d522403de274b86a0a6f ]

The tx_enabled lag event field is used to determine whether a slave is
active.
Current logic uses this value only if the mode is active-backup.

However, LACP mode, although considered a load balancing mode, can mark
a slave as inactive in certain situations (e.g., LACP timeout).

This fix takes the tx_enabled value into account when remapping, with
no respect to the LAG mode (this should not affect the behavior in XOR
mode, since in this mode both slaves are marked as active).

Fixes: 7907f23adc18 (net/mlx5: Implement RoCE LAG feature)
Signed-off-by: Aviv Heller <avivh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/lag.c | 25 ++++++++++---------------
 1 file changed, 10 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index b5d5519542e8..0ca4623bda6b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -157,22 +157,17 @@ static bool mlx5_lag_is_bonded(struct mlx5_lag *ldev)
 static void mlx5_infer_tx_affinity_mapping(struct lag_tracker *tracker,
 					   u8 *port1, u8 *port2)
 {
-	if (tracker->tx_type == NETDEV_LAG_TX_TYPE_ACTIVEBACKUP) {
-		if (tracker->netdev_state[0].tx_enabled) {
-			*port1 = 1;
-			*port2 = 1;
-		} else {
-			*port1 = 2;
-			*port2 = 2;
-		}
-	} else {
-		*port1 = 1;
-		*port2 = 2;
-		if (!tracker->netdev_state[0].link_up)
-			*port1 = 2;
-		else if (!tracker->netdev_state[1].link_up)
-			*port2 = 1;
+	*port1 = 1;
+	*port2 = 2;
+	if (!tracker->netdev_state[0].tx_enabled ||
+	    !tracker->netdev_state[0].link_up) {
+		*port1 = 2;
+		return;
 	}
+
+	if (!tracker->netdev_state[1].tx_enabled ||
+	    !tracker->netdev_state[1].link_up)
+		*port2 = 1;
 }
 
 static void mlx5_activate_lag(struct mlx5_lag *ldev,
-- 
2.13.4


From 2b207cbc1bd41a0f89c80840ed5c4c5759f4efc4 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Sun, 25 Jun 2017 18:45:32 +0300
Subject: [PATCH 23/28] net/mlx5: Fix command bad flow on command entry
 allocation failure

[ Upstream commit 219c81f7d1d5a89656cb3b53d3b4e11e93608d80 ]

When driver fail to allocate an entry to send command to FW, it must
notify the calling function and release the memory allocated for
this command.

Fixes: e126ba97dba9e ('mlx5: Add driver for Mellanox Connect-IB adapters')
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Cc: kernel-team@fb.com
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index cb45390c7623..f7fabecc104f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -770,6 +770,10 @@ static void cb_timeout_handler(struct work_struct *work)
 	mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
 }
 
+static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg);
+static void mlx5_free_cmd_msg(struct mlx5_core_dev *dev,
+			      struct mlx5_cmd_msg *msg);
+
 static void cmd_work_handler(struct work_struct *work)
 {
 	struct mlx5_cmd_work_ent *ent = container_of(work, struct mlx5_cmd_work_ent, work);
@@ -779,16 +783,27 @@ static void cmd_work_handler(struct work_struct *work)
 	struct mlx5_cmd_layout *lay;
 	struct semaphore *sem;
 	unsigned long flags;
+	int alloc_ret;
 
 	sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem;
 	down(sem);
 	if (!ent->page_queue) {
-		ent->idx = alloc_ent(cmd);
-		if (ent->idx < 0) {
+		alloc_ret = alloc_ent(cmd);
+		if (alloc_ret < 0) {
+			if (ent->callback) {
+				ent->callback(-EAGAIN, ent->context);
+				mlx5_free_cmd_msg(dev, ent->out);
+				free_msg(dev, ent->in);
+				free_cmd(ent);
+			} else {
+				ent->ret = -EAGAIN;
+				complete(&ent->done);
+			}
 			mlx5_core_err(dev, "failed to allocate command entry\n");
 			up(sem);
 			return;
 		}
+		ent->idx = alloc_ret;
 	} else {
 		ent->idx = cmd->max_reg_cmds;
 		spin_lock_irqsave(&cmd->alloc_lock, flags);
-- 
2.13.4


From 5c12320309aaae08a200204555dfbd8b204c734e Mon Sep 17 00:00:00 2001
From: Ilan Tayari <ilant@mellanox.com>
Date: Wed, 5 Jul 2017 10:17:04 +0300
Subject: [PATCH 24/28] net/mlx5e: Fix outer_header_zero() check size

[ Upstream commit 0242f4a0bb03906010bbf80495512be00494a0ef ]

outer_header_zero() routine checks if the outer_headers match of a
flow-table entry are all zero.

This function uses the size of whole fte_match_param, instead of just
the outer_headers member, causing failure to detect all-zeros if
any other members of the fte_match_param are non-zero.

Use the correct size for zero check.

Fixes: 6dc6071cfcde ("net/mlx5e: Add ethtool flow steering support")
Signed-off-by: Ilan Tayari <ilant@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index e034dbc4913d..cf070fc0fb6b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -276,7 +276,7 @@ static void add_rule_to_list(struct mlx5e_priv *priv,
 
 static bool outer_header_zero(u32 *match_criteria)
 {
-	int size = MLX5_ST_SZ_BYTES(fte_match_param);
+	int size = MLX5_FLD_SZ_BYTES(fte_match_param, outer_headers);
 	char *outer_headers_c = MLX5_ADDR_OF(fte_match_param, match_criteria,
 					     outer_headers);
 
-- 
2.13.4


From 9934951097a73c45a5af346f8d6e613afd73ee91 Mon Sep 17 00:00:00 2001
From: Eugenia Emantayev <eugenia@mellanox.com>
Date: Wed, 12 Jul 2017 17:27:18 +0300
Subject: [PATCH 25/28] net/mlx5e: Fix wrong delay calculation for overflow
 check scheduling

[ Upstream commit d439c84509a510e864fdc6166c760482cd03fc57 ]

The overflow_period is calculated in seconds. In order to use it
for delayed work scheduling translation to jiffies is needed.

Fixes: ef9814deafd0 ('net/mlx5e: Add HW timestamping (TS) support')
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_clock.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
index 13dc388667b6..fddcff015522 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
@@ -67,7 +67,8 @@ static void mlx5e_timestamp_overflow(struct work_struct *work)
 	write_lock_irqsave(&tstamp->lock, flags);
 	timecounter_read(&tstamp->clock);
 	write_unlock_irqrestore(&tstamp->lock, flags);
-	schedule_delayed_work(&tstamp->overflow_work, tstamp->overflow_period);
+	schedule_delayed_work(&tstamp->overflow_work,
+			      msecs_to_jiffies(tstamp->overflow_period * 1000));
 }
 
 int mlx5e_hwstamp_set(struct net_device *dev, struct ifreq *ifr)
-- 
2.13.4


From 88173a9c07f0a42394ff28e7db037a7260106356 Mon Sep 17 00:00:00 2001
From: Eugenia Emantayev <eugenia@mellanox.com>
Date: Wed, 12 Jul 2017 17:44:07 +0300
Subject: [PATCH 26/28] net/mlx5e: Schedule overflow check work to mlx5e
 workqueue

[ Upstream commit f08c39ed0bfb503c7b3e013cd40d036ce6a0941a ]

This is done in order to ensure that work will not run after the cleanup.

Fixes: ef9814deafd0 ('net/mlx5e: Add HW timestamping (TS) support')
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_clock.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
index fddcff015522..1612ec0d9103 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
@@ -62,13 +62,14 @@ static void mlx5e_timestamp_overflow(struct work_struct *work)
 	struct delayed_work *dwork = to_delayed_work(work);
 	struct mlx5e_tstamp *tstamp = container_of(dwork, struct mlx5e_tstamp,
 						   overflow_work);
+	struct mlx5e_priv *priv = container_of(tstamp, struct mlx5e_priv, tstamp);
 	unsigned long flags;
 
 	write_lock_irqsave(&tstamp->lock, flags);
 	timecounter_read(&tstamp->clock);
 	write_unlock_irqrestore(&tstamp->lock, flags);
-	schedule_delayed_work(&tstamp->overflow_work,
-			      msecs_to_jiffies(tstamp->overflow_period * 1000));
+	queue_delayed_work(priv->wq, &tstamp->overflow_work,
+			   msecs_to_jiffies(tstamp->overflow_period * 1000));
 }
 
 int mlx5e_hwstamp_set(struct net_device *dev, struct ifreq *ifr)
@@ -264,7 +265,7 @@ void mlx5e_timestamp_init(struct mlx5e_priv *priv)
 
 	INIT_DELAYED_WORK(&tstamp->overflow_work, mlx5e_timestamp_overflow);
 	if (tstamp->overflow_period)
-		schedule_delayed_work(&tstamp->overflow_work, 0);
+		queue_delayed_work(priv->wq, &tstamp->overflow_work, 0);
 	else
 		mlx5_core_warn(priv->mdev, "invalid overflow period, overflow_work is not scheduled\n");
 
-- 
2.13.4


From c36db1e5ea6743219f1133b51e131489693783cf Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 28 Jul 2017 11:58:36 -0700
Subject: [PATCH 27/28] net: phy: Correctly process PHY_HALTED in
 phy_stop_machine()

[ Upstream commit 7ad813f208533cebfcc32d3d7474dc1677d1b09a ]

Marc reported that he was not getting the PHY library adjust_link()
callback function to run when calling phy_stop() + phy_disconnect()
which does not indeed happen because we set the state machine to
PHY_HALTED but we don't get to run it to process this state past that
point.

Fix this with a synchronous call to phy_state_machine() in order to have
the state machine actually act on PHY_HALTED, set the PHY device's link
down, turn the network device's carrier off and finally call the
adjust_link() function.

Reported-by: Marc Gonzalez <marc_gonzalez@sigmadesigns.com>
Fixes: a390d1f379cf ("phylib: convert state_queue work to delayed_work")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Marc Gonzalez <marc_gonzalez@sigmadesigns.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index edd30ebbf275..7103dc1d20f2 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -674,6 +674,9 @@ void phy_stop_machine(struct phy_device *phydev)
 	if (phydev->state > PHY_UP && phydev->state != PHY_HALTED)
 		phydev->state = PHY_UP;
 	mutex_unlock(&phydev->lock);
+
+	/* Now we can run the state machine synchronously */
+	phy_state_machine(&phydev->state_queue.work);
 }
 
 /**
-- 
2.13.4


From 14fb03c2bf95411c5ca3e78f20c170719b606e84 Mon Sep 17 00:00:00 2001
From: Wei Liu <wei.liu2@citrix.com>
Date: Wed, 21 Jun 2017 10:21:22 +0100
Subject: [PATCH 28/28] xen-netback: correctly schedule rate-limited queues

[ Upstream commit dfa523ae9f2542bee4cddaea37b3be3e157f6e6b ]

Add a flag to indicate if a queue is rate-limited. Test the flag in
NAPI poll handler and avoid rescheduling the queue if true, otherwise
we risk locking up the host. The rescheduling will be done in the
timer callback function.

Reported-by: Jean-Louis Dupond <jean-louis@dupond.be>
Signed-off-by: Wei Liu <wei.liu2@citrix.com>
Tested-by: Jean-Louis Dupond <jean-louis@dupond.be>
Reviewed-by: Paul Durrant <paul.durrant@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netback/common.h    | 1 +
 drivers/net/xen-netback/interface.c | 6 +++++-
 drivers/net/xen-netback/netback.c   | 6 +++++-
 3 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
index 3ce1f7da8647..cb7365bdf6e0 100644
--- a/drivers/net/xen-netback/common.h
+++ b/drivers/net/xen-netback/common.h
@@ -199,6 +199,7 @@ struct xenvif_queue { /* Per-queue data for xenvif */
 	unsigned long   remaining_credit;
 	struct timer_list credit_timeout;
 	u64 credit_window_start;
+	bool rate_limited;
 
 	/* Statistics */
 	struct xenvif_stats stats;
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index b009d7966b46..5bfaf5578810 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -105,7 +105,11 @@ static int xenvif_poll(struct napi_struct *napi, int budget)
 
 	if (work_done < budget) {
 		napi_complete(napi);
-		xenvif_napi_schedule_or_enable_events(queue);
+		/* If the queue is rate-limited, it shall be
+		 * rescheduled in the timer callback.
+		 */
+		if (likely(!queue->rate_limited))
+			xenvif_napi_schedule_or_enable_events(queue);
 	}
 
 	return work_done;
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 47b481095d77..d9b5b73c35a0 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -179,6 +179,7 @@ static void tx_add_credit(struct xenvif_queue *queue)
 		max_credit = ULONG_MAX; /* wrapped: clamp to ULONG_MAX */
 
 	queue->remaining_credit = min(max_credit, max_burst);
+	queue->rate_limited = false;
 }
 
 void xenvif_tx_credit_callback(unsigned long data)
@@ -685,8 +686,10 @@ static bool tx_credit_exceeded(struct xenvif_queue *queue, unsigned size)
 		msecs_to_jiffies(queue->credit_usec / 1000);
 
 	/* Timer could already be pending in rare cases. */
-	if (timer_pending(&queue->credit_timeout))
+	if (timer_pending(&queue->credit_timeout)) {
+		queue->rate_limited = true;
 		return true;
+	}
 
 	/* Passed the point where we can replenish credit? */
 	if (time_after_eq64(now, next_credit)) {
@@ -701,6 +704,7 @@ static bool tx_credit_exceeded(struct xenvif_queue *queue, unsigned size)
 		mod_timer(&queue->credit_timeout,
 			  next_credit);
 		queue->credit_window_start = next_credit;
+		queue->rate_limited = true;
 
 		return true;
 	}
-- 
2.13.4


[-- Attachment #3: net_412.mbox --]
[-- Type: Application/Octet-Stream, Size: 112411 bytes --]

From 331ed0dd601575d4f93267b7f544a1136b637191 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Fri, 14 Jul 2017 22:07:33 +0800
Subject: [PATCH 01/45] sctp: fix an array overflow when all ext chunks are set

[ Upstream commit 10b3bf54406bb7f4e78da9bb2a485c5c986678ad ]

Marcelo noticed an array overflow caused by commit c28445c3cb07
("sctp: add reconf_enable in asoc ep and netns"), in which sctp
would add SCTP_CID_RECONF into extensions when reconf_enable is
set in sctp_make_init and sctp_make_init_ack.

Then now when all ext chunks are set, 4 ext chunk ids can be put
into extensions array while extensions array size is 3. It would
cause a kernel panic because of this overflow.

This patch is to fix it by defining extensions array size is 4 in
both sctp_make_init and sctp_make_init_ack.

Fixes: c28445c3cb07 ("sctp: add reconf_enable in asoc ep and netns")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sm_make_chunk.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 92e332e17391..961a6f81ae64 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -228,7 +228,7 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc,
 	sctp_adaptation_ind_param_t aiparam;
 	sctp_supported_ext_param_t ext_param;
 	int num_ext = 0;
-	__u8 extensions[3];
+	__u8 extensions[4];
 	sctp_paramhdr_t *auth_chunks = NULL,
 			*auth_hmacs = NULL;
 
@@ -396,7 +396,7 @@ struct sctp_chunk *sctp_make_init_ack(const struct sctp_association *asoc,
 	sctp_adaptation_ind_param_t aiparam;
 	sctp_supported_ext_param_t ext_param;
 	int num_ext = 0;
-	__u8 extensions[3];
+	__u8 extensions[4];
 	sctp_paramhdr_t *auth_chunks = NULL,
 			*auth_hmacs = NULL,
 			*auth_random = NULL;
-- 
2.13.4


From c2ab492166892944cdf0b933bb5a311262acd4f2 Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Fri, 14 Jul 2017 17:49:21 -0400
Subject: [PATCH 02/45] tcp_bbr: cut pacing rate only if filled pipe

[ Upstream commit 4aea287e90dd61a48268ff2994b56f9799441b62 ]

In bbr_set_pacing_rate(), which decides whether to cut the pacing
rate, there was some code that considered exiting STARTUP to be
equivalent to the notion of filling the pipe (i.e.,
bbr_full_bw_reached()). Specifically, as the code was structured,
exiting STARTUP and going into PROBE_RTT could cause us to cut the
pacing rate down to something silly and low, based on whatever
bandwidth samples we've had so far, when it's possible that all of
them have been small app-limited bandwidth samples that are not
representative of the bandwidth available in the path. (The code was
correct at the time it was written, but the state machine changed
without this spot being adjusted correspondingly.)

Fixes: 0f8782ea1497 ("tcp_bbr: add BBR congestion control")
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_bbr.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index b89bce4c721e..b152e1d3b754 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -221,12 +221,11 @@ static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain)
  */
 static void bbr_set_pacing_rate(struct sock *sk, u32 bw, int gain)
 {
-	struct bbr *bbr = inet_csk_ca(sk);
 	u64 rate = bw;
 
 	rate = bbr_rate_bytes_per_sec(sk, rate, gain);
 	rate = min_t(u64, rate, sk->sk_max_pacing_rate);
-	if (bbr->mode != BBR_STARTUP || rate > sk->sk_pacing_rate)
+	if (bbr_full_bw_reached(sk) || rate > sk->sk_pacing_rate)
 		sk->sk_pacing_rate = rate;
 }
 
-- 
2.13.4


From b1fddd984cc34095923a687a603e0a86a82fbd10 Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Fri, 14 Jul 2017 17:49:22 -0400
Subject: [PATCH 03/45] tcp_bbr: introduce bbr_bw_to_pacing_rate() helper

[ Upstream commit f19fd62dafaf1ed6cf615dba655b82fa9df59074 ]

Introduce a helper to convert a BBR bandwidth and gain factor to a
pacing rate in bytes per second. This is a pure refactor, but is
needed for two following fixes.

Fixes: 0f8782ea1497 ("tcp_bbr: add BBR congestion control")
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_bbr.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index b152e1d3b754..14e0eba7aa7a 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -212,6 +212,16 @@ static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain)
 	return rate >> BW_SCALE;
 }
 
+/* Convert a BBR bw and gain factor to a pacing rate in bytes per second. */
+static u32 bbr_bw_to_pacing_rate(struct sock *sk, u32 bw, int gain)
+{
+	u64 rate = bw;
+
+	rate = bbr_rate_bytes_per_sec(sk, rate, gain);
+	rate = min_t(u64, rate, sk->sk_max_pacing_rate);
+	return rate;
+}
+
 /* Pace using current bw estimate and a gain factor. In order to help drive the
  * network toward lower queues while maintaining high utilization and low
  * latency, the average pacing rate aims to be slightly (~1%) lower than the
@@ -221,10 +231,8 @@ static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain)
  */
 static void bbr_set_pacing_rate(struct sock *sk, u32 bw, int gain)
 {
-	u64 rate = bw;
+	u32 rate = bbr_bw_to_pacing_rate(sk, bw, gain);
 
-	rate = bbr_rate_bytes_per_sec(sk, rate, gain);
-	rate = min_t(u64, rate, sk->sk_max_pacing_rate);
 	if (bbr_full_bw_reached(sk) || rate > sk->sk_pacing_rate)
 		sk->sk_pacing_rate = rate;
 }
-- 
2.13.4


From 0e6dff5a57d270b3b6e41408318b32aa97bdb02a Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Fri, 14 Jul 2017 17:49:23 -0400
Subject: [PATCH 04/45] tcp_bbr: introduce bbr_init_pacing_rate_from_rtt()
 helper

[ Upstream commit 79135b89b8af304456bd67916b80116ddf03d7b6 ]

Introduce a helper to initialize the BBR pacing rate unconditionally,
based on the current cwnd and RTT estimate. This is a pure refactor,
but is needed for two following fixes.

Fixes: 0f8782ea1497 ("tcp_bbr: add BBR congestion control")
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_bbr.c | 23 ++++++++++++++++++-----
 1 file changed, 18 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 14e0eba7aa7a..e69c8b44568a 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -222,6 +222,23 @@ static u32 bbr_bw_to_pacing_rate(struct sock *sk, u32 bw, int gain)
 	return rate;
 }
 
+/* Initialize pacing rate to: high_gain * init_cwnd / RTT. */
+static void bbr_init_pacing_rate_from_rtt(struct sock *sk)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	u64 bw;
+	u32 rtt_us;
+
+	if (tp->srtt_us) {		/* any RTT sample yet? */
+		rtt_us = max(tp->srtt_us >> 3, 1U);
+	} else {			 /* no RTT sample yet */
+		rtt_us = USEC_PER_MSEC;	 /* use nominal default RTT */
+	}
+	bw = (u64)tp->snd_cwnd * BW_UNIT;
+	do_div(bw, rtt_us);
+	sk->sk_pacing_rate = bbr_bw_to_pacing_rate(sk, bw, bbr_high_gain);
+}
+
 /* Pace using current bw estimate and a gain factor. In order to help drive the
  * network toward lower queues while maintaining high utilization and low
  * latency, the average pacing rate aims to be slightly (~1%) lower than the
@@ -806,7 +823,6 @@ static void bbr_init(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct bbr *bbr = inet_csk_ca(sk);
-	u64 bw;
 
 	bbr->prior_cwnd = 0;
 	bbr->tso_segs_goal = 0;	 /* default segs per skb until first ACK */
@@ -822,11 +838,8 @@ static void bbr_init(struct sock *sk)
 
 	minmax_reset(&bbr->bw, bbr->rtt_cnt, 0);  /* init max bw to 0 */
 
-	/* Initialize pacing rate to: high_gain * init_cwnd / RTT. */
-	bw = (u64)tp->snd_cwnd * BW_UNIT;
-	do_div(bw, (tp->srtt_us >> 3) ? : USEC_PER_MSEC);
 	sk->sk_pacing_rate = 0;		/* force an update of sk_pacing_rate */
-	bbr_set_pacing_rate(sk, bw, bbr_high_gain);
+	bbr_init_pacing_rate_from_rtt(sk);
 
 	bbr->restore_cwnd = 0;
 	bbr->round_start = 0;
-- 
2.13.4


From 54aa677f2636d475cae0466a75ee3c5d3c133f83 Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Fri, 14 Jul 2017 17:49:24 -0400
Subject: [PATCH 05/45] tcp_bbr: remove sk_pacing_rate=0 transient during init

[ Upstream commit 1d3648eb5d1fe9ed3d095ed8fa19ad11ca4c8bc0 ]

Fix a corner case noticed by Eric Dumazet, where BBR's setting
sk->sk_pacing_rate to 0 during initialization could theoretically
cause packets in the sending host to hang if there were packets "in
flight" in the pacing infrastructure at the time the BBR congestion
control state is initialized. This could occur if the pacing
infrastructure happened to race with bbr_init() in a way such that the
pacer read the 0 rather than the immediately following non-zero pacing
rate.

Fixes: 0f8782ea1497 ("tcp_bbr: add BBR congestion control")
Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_bbr.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index e69c8b44568a..20d834fd557d 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -838,7 +838,6 @@ static void bbr_init(struct sock *sk)
 
 	minmax_reset(&bbr->bw, bbr->rtt_cnt, 0);  /* init max bw to 0 */
 
-	sk->sk_pacing_rate = 0;		/* force an update of sk_pacing_rate */
 	bbr_init_pacing_rate_from_rtt(sk);
 
 	bbr->restore_cwnd = 0;
-- 
2.13.4


From bf995e3ec4e864f6ecf4c1b1638101de470a2f2e Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Fri, 14 Jul 2017 17:49:25 -0400
Subject: [PATCH 06/45] tcp_bbr: init pacing rate on first RTT sample

[ Upstream commit 32984565574da7ed3afa10647bb4020d7a9e6c93 ]

Fixes the following behavior: for connections that had no RTT sample
at the time of initializing congestion control, BBR was initializing
the pacing rate to a high nominal rate (based an a guess of RTT=1ms,
in case this is LAN traffic). Then BBR never adjusted the pacing rate
downward upon obtaining an actual RTT sample, if the connection never
filled the pipe (e.g. all sends were small app-limited writes()).

This fix adjusts the pacing rate upon obtaining the first RTT sample.

Fixes: 0f8782ea1497 ("tcp_bbr: add BBR congestion control")
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_bbr.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 20d834fd557d..96c95c8d981e 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -113,7 +113,8 @@ struct bbr {
 		cwnd_gain:10,	/* current gain for setting cwnd */
 		full_bw_cnt:3,	/* number of rounds without large bw gains */
 		cycle_idx:3,	/* current index in pacing_gain cycle array */
-		unused_b:6;
+		has_seen_rtt:1, /* have we seen an RTT sample yet? */
+		unused_b:5;
 	u32	prior_cwnd;	/* prior cwnd upon entering loss recovery */
 	u32	full_bw;	/* recent bw, to estimate if pipe is full */
 };
@@ -226,11 +227,13 @@ static u32 bbr_bw_to_pacing_rate(struct sock *sk, u32 bw, int gain)
 static void bbr_init_pacing_rate_from_rtt(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	struct bbr *bbr = inet_csk_ca(sk);
 	u64 bw;
 	u32 rtt_us;
 
 	if (tp->srtt_us) {		/* any RTT sample yet? */
 		rtt_us = max(tp->srtt_us >> 3, 1U);
+		bbr->has_seen_rtt = 1;
 	} else {			 /* no RTT sample yet */
 		rtt_us = USEC_PER_MSEC;	 /* use nominal default RTT */
 	}
@@ -248,8 +251,12 @@ static void bbr_init_pacing_rate_from_rtt(struct sock *sk)
  */
 static void bbr_set_pacing_rate(struct sock *sk, u32 bw, int gain)
 {
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct bbr *bbr = inet_csk_ca(sk);
 	u32 rate = bbr_bw_to_pacing_rate(sk, bw, gain);
 
+	if (unlikely(!bbr->has_seen_rtt && tp->srtt_us))
+		bbr_init_pacing_rate_from_rtt(sk);
 	if (bbr_full_bw_reached(sk) || rate > sk->sk_pacing_rate)
 		sk->sk_pacing_rate = rate;
 }
@@ -838,6 +845,7 @@ static void bbr_init(struct sock *sk)
 
 	minmax_reset(&bbr->bw, bbr->rtt_cnt, 0);  /* init max bw to 0 */
 
+	bbr->has_seen_rtt = 0;
 	bbr_init_pacing_rate_from_rtt(sk);
 
 	bbr->restore_cwnd = 0;
-- 
2.13.4


From 976ae5ea4318e3347a534b8b8d6dc3f4090da473 Mon Sep 17 00:00:00 2001
From: Alexander Potapenko <glider@google.com>
Date: Mon, 17 Jul 2017 12:35:58 +0200
Subject: [PATCH 08/45] ipv4: ipv6: initialize treq->txhash in
 cookie_v[46]_check()

[ Upstream commit 18bcf2907df935981266532e1e0d052aff2e6fae ]

KMSAN reported use of uninitialized memory in skb_set_hash_from_sk(),
which originated from the TCP request socket created in
cookie_v6_check():

 ==================================================================
 BUG: KMSAN: use of uninitialized memory in tcp_transmit_skb+0xf77/0x3ec0
 CPU: 1 PID: 2949 Comm: syz-execprog Not tainted 4.11.0-rc5+ #2931
 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
 TCP: request_sock_TCPv6: Possible SYN flooding on port 20028. Sending cookies.  Check SNMP counters.
 Call Trace:
  <IRQ>
  __dump_stack lib/dump_stack.c:16
  dump_stack+0x172/0x1c0 lib/dump_stack.c:52
  kmsan_report+0x12a/0x180 mm/kmsan/kmsan.c:927
  __msan_warning_32+0x61/0xb0 mm/kmsan/kmsan_instr.c:469
  skb_set_hash_from_sk ./include/net/sock.h:2011
  tcp_transmit_skb+0xf77/0x3ec0 net/ipv4/tcp_output.c:983
  tcp_send_ack+0x75b/0x830 net/ipv4/tcp_output.c:3493
  tcp_delack_timer_handler+0x9a6/0xb90 net/ipv4/tcp_timer.c:284
  tcp_delack_timer+0x1b0/0x310 net/ipv4/tcp_timer.c:309
  call_timer_fn+0x240/0x520 kernel/time/timer.c:1268
  expire_timers kernel/time/timer.c:1307
  __run_timers+0xc13/0xf10 kernel/time/timer.c:1601
  run_timer_softirq+0x36/0xa0 kernel/time/timer.c:1614
  __do_softirq+0x485/0x942 kernel/softirq.c:284
  invoke_softirq kernel/softirq.c:364
  irq_exit+0x1fa/0x230 kernel/softirq.c:405
  exiting_irq+0xe/0x10 ./arch/x86/include/asm/apic.h:657
  smp_apic_timer_interrupt+0x5a/0x80 arch/x86/kernel/apic/apic.c:966
  apic_timer_interrupt+0x86/0x90 arch/x86/entry/entry_64.S:489
 RIP: 0010:native_restore_fl ./arch/x86/include/asm/irqflags.h:36
 RIP: 0010:arch_local_irq_restore ./arch/x86/include/asm/irqflags.h:77
 RIP: 0010:__msan_poison_alloca+0xed/0x120 mm/kmsan/kmsan_instr.c:440
 RSP: 0018:ffff880024917cd8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff10
 RAX: 0000000000000246 RBX: ffff8800224c0000 RCX: 0000000000000005
 RDX: 0000000000000004 RSI: ffff880000000000 RDI: ffffea0000b6d770
 RBP: ffff880024917d58 R08: 0000000000000dd8 R09: 0000000000000004
 R10: 0000160000000000 R11: 0000000000000000 R12: ffffffff85abf810
 R13: ffff880024917dd8 R14: 0000000000000010 R15: ffffffff81cabde4
  </IRQ>
  poll_select_copy_remaining+0xac/0x6b0 fs/select.c:293
  SYSC_select+0x4b4/0x4e0 fs/select.c:653
  SyS_select+0x76/0xa0 fs/select.c:634
  entry_SYSCALL_64_fastpath+0x13/0x94 arch/x86/entry/entry_64.S:204
 RIP: 0033:0x4597e7
 RSP: 002b:000000c420037ee0 EFLAGS: 00000246 ORIG_RAX: 0000000000000017
 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00000000004597e7
 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
 RBP: 000000c420037ef0 R08: 000000c420037ee0 R09: 0000000000000059
 R10: 0000000000000000 R11: 0000000000000246 R12: 000000000042dc20
 R13: 00000000000000f3 R14: 0000000000000030 R15: 0000000000000003
 chained origin:
  save_stack_trace+0x37/0x40 arch/x86/kernel/stacktrace.c:59
  kmsan_save_stack_with_flags mm/kmsan/kmsan.c:302
  kmsan_save_stack mm/kmsan/kmsan.c:317
  kmsan_internal_chain_origin+0x12a/0x1f0 mm/kmsan/kmsan.c:547
  __msan_store_shadow_origin_4+0xac/0x110 mm/kmsan/kmsan_instr.c:259
  tcp_create_openreq_child+0x709/0x1ae0 net/ipv4/tcp_minisocks.c:472
  tcp_v6_syn_recv_sock+0x7eb/0x2a30 net/ipv6/tcp_ipv6.c:1103
  tcp_get_cookie_sock+0x136/0x5f0 net/ipv4/syncookies.c:212
  cookie_v6_check+0x17a9/0x1b50 net/ipv6/syncookies.c:245
  tcp_v6_cookie_check net/ipv6/tcp_ipv6.c:989
  tcp_v6_do_rcv+0xdd8/0x1c60 net/ipv6/tcp_ipv6.c:1298
  tcp_v6_rcv+0x41a3/0x4f00 net/ipv6/tcp_ipv6.c:1487
  ip6_input_finish+0x82f/0x1ee0 net/ipv6/ip6_input.c:279
  NF_HOOK ./include/linux/netfilter.h:257
  ip6_input+0x239/0x290 net/ipv6/ip6_input.c:322
  dst_input ./include/net/dst.h:492
  ip6_rcv_finish net/ipv6/ip6_input.c:69
  NF_HOOK ./include/linux/netfilter.h:257
  ipv6_rcv+0x1dbd/0x22e0 net/ipv6/ip6_input.c:203
  __netif_receive_skb_core+0x2f6f/0x3a20 net/core/dev.c:4208
  __netif_receive_skb net/core/dev.c:4246
  process_backlog+0x667/0xba0 net/core/dev.c:4866
  napi_poll net/core/dev.c:5268
  net_rx_action+0xc95/0x1590 net/core/dev.c:5333
  __do_softirq+0x485/0x942 kernel/softirq.c:284
 origin:
  save_stack_trace+0x37/0x40 arch/x86/kernel/stacktrace.c:59
  kmsan_save_stack_with_flags mm/kmsan/kmsan.c:302
  kmsan_internal_poison_shadow+0xb1/0x1a0 mm/kmsan/kmsan.c:198
  kmsan_kmalloc+0x7f/0xe0 mm/kmsan/kmsan.c:337
  kmem_cache_alloc+0x1c2/0x1e0 mm/slub.c:2766
  reqsk_alloc ./include/net/request_sock.h:87
  inet_reqsk_alloc+0xa4/0x5b0 net/ipv4/tcp_input.c:6200
  cookie_v6_check+0x4f4/0x1b50 net/ipv6/syncookies.c:169
  tcp_v6_cookie_check net/ipv6/tcp_ipv6.c:989
  tcp_v6_do_rcv+0xdd8/0x1c60 net/ipv6/tcp_ipv6.c:1298
  tcp_v6_rcv+0x41a3/0x4f00 net/ipv6/tcp_ipv6.c:1487
  ip6_input_finish+0x82f/0x1ee0 net/ipv6/ip6_input.c:279
  NF_HOOK ./include/linux/netfilter.h:257
  ip6_input+0x239/0x290 net/ipv6/ip6_input.c:322
  dst_input ./include/net/dst.h:492
  ip6_rcv_finish net/ipv6/ip6_input.c:69
  NF_HOOK ./include/linux/netfilter.h:257
  ipv6_rcv+0x1dbd/0x22e0 net/ipv6/ip6_input.c:203
  __netif_receive_skb_core+0x2f6f/0x3a20 net/core/dev.c:4208
  __netif_receive_skb net/core/dev.c:4246
  process_backlog+0x667/0xba0 net/core/dev.c:4866
  napi_poll net/core/dev.c:5268
  net_rx_action+0xc95/0x1590 net/core/dev.c:5333
  __do_softirq+0x485/0x942 kernel/softirq.c:284
 ==================================================================

Similar error is reported for cookie_v4_check().

Fixes: 58d607d3e52f ("tcp: provide skb->hash to synack packets")
Signed-off-by: Alexander Potapenko <glider@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/syncookies.c | 1 +
 net/ipv6/syncookies.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 0257d965f111..4a97fe20f59e 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -332,6 +332,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	treq->rcv_isn		= ntohl(th->seq) - 1;
 	treq->snt_isn		= cookie;
 	treq->ts_off		= 0;
+	treq->txhash		= net_tx_rndhash();
 	req->mss		= mss;
 	ireq->ir_num		= ntohs(th->dest);
 	ireq->ir_rmt_port	= th->source;
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 5abc3692b901..ca7895454cec 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -215,6 +215,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	treq->rcv_isn = ntohl(th->seq) - 1;
 	treq->snt_isn = cookie;
 	treq->ts_off = 0;
+	treq->txhash = net_tx_rndhash();
 
 	/*
 	 * We need to lookup the dst_entry to get the correct window size.
-- 
2.13.4


From 4fd2efc4cc52548cae02ae1b2629f25fd480c3d6 Mon Sep 17 00:00:00 2001
From: "Levin, Alexander" <alexander.levin@verizon.com>
Date: Tue, 18 Jul 2017 04:23:16 +0000
Subject: [PATCH 09/45] wireless: wext: terminate ifr name coming from
 userspace

[ Upstream commit 98de4e0ea47d106846fc0e30ce4e644283fa7fc2 ]

ifr name is assumed to be a valid string by the kernel, but nothing
was forcing username to pass a valid string.

In turn, this would cause panics as we tried to access the string
past it's valid memory.

Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev_ioctl.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 27fad31784a8..434413f1074a 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -423,6 +423,8 @@ int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 		if (copy_from_user(&iwr, arg, sizeof(iwr)))
 			return -EFAULT;
 
+		iwr.ifr_name[sizeof(iwr.ifr_name) - 1] = 0;
+
 		return wext_handle_ioctl(net, &iwr, cmd, arg);
 	}
 
-- 
2.13.4


From e7b1fe2e6c63adee70dfedffc7d0213a807f6b41 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Wed, 19 Jul 2017 13:33:24 -0700
Subject: [PATCH 10/45] net: Zero terminate ifr_name in dev_ifname().

[ Upstream commit 63679112c536289826fec61c917621de95ba2ade ]

The ifr.ifr_name is passed around and assumed to be NULL terminated.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev_ioctl.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 434413f1074a..18f9cb9aa87d 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -28,6 +28,7 @@ static int dev_ifname(struct net *net, struct ifreq __user *arg)
 
 	if (copy_from_user(&ifr, arg, sizeof(struct ifreq)))
 		return -EFAULT;
+	ifr.ifr_name[IFNAMSIZ-1] = 0;
 
 	error = netdev_get_name(net, ifr.ifr_name, ifr.ifr_ifindex);
 	if (error)
-- 
2.13.4


From db97c0279e07eb4cfe4f736a0cd02cf4be3072e7 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Martin=20Hundeb=C3=B8ll?= <mnhu@prevas.dk>
Date: Wed, 19 Jul 2017 08:17:02 +0200
Subject: [PATCH 11/45] net: dsa: mv88e6xxx: Enable CMODE config support for
 6390X
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit bb0a2675f72b458e64f47071e8aabdb225a6af4d ]

Commit f39908d3b1c45 ('net: dsa: mv88e6xxx: Set the CMODE for mv88e6390
ports 9 & 10') added support for setting the CMODE for the 6390X family,
but only enabled it for 9290 and 6390 - and left out 6390X.

Fix support for setting the CMODE on 6390X also by assigning
mv88e6390x_port_set_cmode() to the .port_set_cmode function pointer in
mv88e6390x_ops too.

Fixes: f39908d3b1c4 ("net: dsa: mv88e6xxx: Set the CMODE for mv88e6390 ports 9 & 10")
Signed-off-by: Martin Hundebøll <mnhu@prevas.dk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index d034d8cd7d22..32864a47c4c1 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -3377,6 +3377,7 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = {
 	.port_jumbo_config = mv88e6165_port_jumbo_config,
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_config = mv88e6390_port_pause_config,
+	.port_set_cmode = mv88e6390x_port_set_cmode,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
-- 
2.13.4


From b11e970b2c90dc232be84bf70752de1371af22a2 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 19 Jul 2017 10:22:40 -0700
Subject: [PATCH 12/45] Revert "rtnetlink: Do not generate notifications for
 CHANGEADDR event"

[ Upstream commit 3753654e541938717b13f2b25791c3171a3a06aa ]

This reverts commit cd8966e75ed3c6b41a37047a904617bc44fa481f.

The duplicate CHANGEADDR event message is sent regardless of link
status whereas the setlink changes only generate a notification when
the link is up. Not sending a notification when the link is down breaks
dhcpcd which only processes hwaddr changes when the link is down.

Fixes reported regression:
    https://bugzilla.kernel.org/show_bug.cgi?id=196355

Reported-by: Yaroslav Isakov <yaroslav.isakov@gmail.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 467a2f4510a7..099eca1524c0 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -4165,6 +4165,7 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi
 
 	switch (event) {
 	case NETDEV_REBOOT:
+	case NETDEV_CHANGEADDR:
 	case NETDEV_CHANGENAME:
 	case NETDEV_FEAT_CHANGE:
 	case NETDEV_BONDING_FAILOVER:
-- 
2.13.4


From 4bfa9244390b29d04dc739f27d7f92aa82da07b7 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Wed, 19 Jul 2017 22:28:55 +0200
Subject: [PATCH 13/45] ipv6: avoid overflow of offset in ip6_find_1stfragopt

[ Upstream commit 6399f1fae4ec29fab5ec76070435555e256ca3a6 ]

In some cases, offset can overflow and can cause an infinite loop in
ip6_find_1stfragopt(). Make it unsigned int to prevent the overflow, and
cap it at IPV6_MAXPLEN, since packets larger than that should be invalid.

This problem has been here since before the beginning of git history.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/output_core.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index e9065b8d3af8..abb2c307fbe8 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -78,7 +78,7 @@ EXPORT_SYMBOL(ipv6_select_ident);
 
 int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 {
-	u16 offset = sizeof(struct ipv6hdr);
+	unsigned int offset = sizeof(struct ipv6hdr);
 	unsigned int packet_len = skb_tail_pointer(skb) -
 		skb_network_header(skb);
 	int found_rhdr = 0;
@@ -86,6 +86,7 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 
 	while (offset <= packet_len) {
 		struct ipv6_opt_hdr *exthdr;
+		unsigned int len;
 
 		switch (**nexthdr) {
 
@@ -111,7 +112,10 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 
 		exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) +
 						 offset);
-		offset += ipv6_optlen(exthdr);
+		len = ipv6_optlen(exthdr);
+		if (len + offset >= IPV6_MAXPLEN)
+			return -EINVAL;
+		offset += len;
 		*nexthdr = &exthdr->nexthdr;
 	}
 
-- 
2.13.4


From 0a48b040bdd6d47f8b9089e5173084366b122481 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 20 Jul 2017 12:25:22 -0700
Subject: [PATCH 14/45] net: dsa: b53: Add missing ARL entries for BCM53125

[ Upstream commit be35e8c516c1915a3035d266a2015b41f73ba3f9 ]

The BCM53125 entry was missing an arl_entries member which would
basically prevent the ARL search from terminating properly. This switch
has 4 ARL entries, so add that.

Fixes: 1da6df85c6fb ("net: dsa: b53: Implement ARL add/del/dump operations")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/b53/b53_common.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index fa0eece21eef..d9cc94a7d44e 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -1668,6 +1668,7 @@ static const struct b53_chip_data b53_switch_chips[] = {
 		.dev_name = "BCM53125",
 		.vlans = 4096,
 		.enabled_ports = 0xff,
+		.arl_entries = 4,
 		.cpu_port = B53_CPU_PORT,
 		.vta_regs = B53_VTA_REGS,
 		.duplex_reg = B53_DUPLEX_STAT_GE,
-- 
2.13.4


From 58e6ee6b8f4e7d8571ee1d8105db005715032444 Mon Sep 17 00:00:00 2001
From: Mahesh Bandewar <maheshb@google.com>
Date: Wed, 19 Jul 2017 15:41:33 -0700
Subject: [PATCH 15/45] ipv4: initialize fib_trie prior to
 register_netdev_notifier call.

[ Upstream commit 8799a221f5944a7d74516ecf46d58c28ec1d1f75 ]

Net stack initialization currently initializes fib-trie after the
first call to netdevice_notifier() call. In fact fib_trie initialization
needs to happen before first rtnl_register(). It does not cause any problem
since there are no devices UP at this moment, but trying to bring 'lo'
UP at initialization would make this assumption wrong and exposes the issue.

Fixes following crash

 Call Trace:
  ? alternate_node_alloc+0x76/0xa0
  fib_table_insert+0x1b7/0x4b0
  fib_magic.isra.17+0xea/0x120
  fib_add_ifaddr+0x7b/0x190
  fib_netdev_event+0xc0/0x130
  register_netdevice_notifier+0x1c1/0x1d0
  ip_fib_init+0x72/0x85
  ip_rt_init+0x187/0x1e9
  ip_init+0xe/0x1a
  inet_init+0x171/0x26c
  ? ipv4_offload_init+0x66/0x66
  do_one_initcall+0x43/0x160
  kernel_init_freeable+0x191/0x219
  ? rest_init+0x80/0x80
  kernel_init+0xe/0x150
  ret_from_fork+0x22/0x30
 Code: f6 46 23 04 74 86 4c 89 f7 e8 ae 45 01 00 49 89 c7 4d 85 ff 0f 85 7b ff ff ff 31 db eb 08 4c 89 ff e8 16 47 01 00 48 8b 44 24 38 <45> 8b 6e 14 4d 63 76 74 48 89 04 24 0f 1f 44 00 00 48 83 c4 08
 RIP: kmem_cache_alloc+0xcf/0x1c0 RSP: ffff9b1500017c28
 CR2: 0000000000000014

Fixes: 7b1a74fdbb9e ("[NETNS]: Refactor fib initialization so it can handle multiple namespaces.")
Fixes: 7f9b80529b8a ("[IPV4]: fib hash|trie initialization")

Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_frontend.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 83e3ed258467..3acc8261477c 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1327,13 +1327,14 @@ static struct pernet_operations fib_net_ops = {
 
 void __init ip_fib_init(void)
 {
-	rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, NULL);
-	rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, NULL);
-	rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, NULL);
+	fib_trie_init();
 
 	register_pernet_subsys(&fib_net_ops);
+
 	register_netdevice_notifier(&fib_netdev_notifier);
 	register_inetaddr_notifier(&fib_inetaddr_notifier);
 
-	fib_trie_init();
+	rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, NULL);
+	rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, NULL);
+	rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, NULL);
 }
-- 
2.13.4


From ce80b6e61dabf705d6f4be9d24b21b89a2675f22 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Thu, 20 Jul 2017 11:27:57 -0700
Subject: [PATCH 16/45] rtnetlink: allocate more memory for
 dev_set_mac_address()

[ Upstream commit 153711f9421be5dbc973dc57a4109dc9d54c89b1 ]

virtnet_set_mac_address() interprets mac address as struct
sockaddr, but upper layer only allocates dev->addr_len
which is ETH_ALEN + sizeof(sa_family_t) in this case.

We lack a unified definition for mac address, so just fix
the upper layer, this also allows drivers to interpret it
to struct sockaddr freely.

Reported-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 099eca1524c0..52bfeb60c886 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1977,7 +1977,8 @@ static int do_setlink(const struct sk_buff *skb,
 		struct sockaddr *sa;
 		int len;
 
-		len = sizeof(sa_family_t) + dev->addr_len;
+		len = sizeof(sa_family_t) + max_t(size_t, dev->addr_len,
+						  sizeof(*sa));
 		sa = kmalloc(len, GFP_KERNEL);
 		if (!sa) {
 			err = -ENOMEM;
-- 
2.13.4


From 7e5ccac919ea825d2441c8b5d4c421db0e4a6ca8 Mon Sep 17 00:00:00 2001
From: Kosuke Tatsukawa <tatsu@ab.jp.nec.com>
Date: Thu, 20 Jul 2017 05:20:40 +0000
Subject: [PATCH 17/45] net: bonding: Fix transmit load balancing in
 balance-alb mode

[ Upstream commit cbf5ecb305601d063dc94a57680dfbc3f96c188d ]

balance-alb mode used to have transmit dynamic load balancing feature
enabled by default.  However, transmit dynamic load balancing no longer
works in balance-alb after commit 8b426dc54cf4 ("bonding: remove
hardcoded value").

Both balance-tlb and balance-alb use the function bond_do_alb_xmit() to
send packets.  This function uses the parameter tlb_dynamic_lb.
tlb_dynamic_lb used to have the default value of 1 for balance-alb, but
now the value is set to 0 except in balance-tlb.

Re-enable transmit dyanmic load balancing by initializing tlb_dynamic_lb
for balance-alb similar to balance-tlb.

Fixes: 8b426dc54cf4 ("bonding: remove hardcoded value")
Signed-off-by: Kosuke Tatsukawa <tatsu@ab.jp.nec.com>
Acked-by: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 8ab6bdbe1682..619c6f8d8142 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -4598,7 +4598,7 @@ static int bond_check_params(struct bond_params *params)
 	}
 	ad_user_port_key = valptr->value;
 
-	if (bond_mode == BOND_MODE_TLB) {
+	if ((bond_mode == BOND_MODE_TLB) || (bond_mode == BOND_MODE_ALB)) {
 		bond_opt_initstr(&newval, "default");
 		valptr = bond_opt_parse(bond_opt_get(BOND_OPT_TLB_DYNAMIC_LB),
 					&newval);
-- 
2.13.4


From 01a99fce5f118543b968e2708bb56e15ac6d0982 Mon Sep 17 00:00:00 2001
From: Thomas Jarosch <thomas.jarosch@intra2net.com>
Date: Sat, 22 Jul 2017 17:14:34 +0200
Subject: [PATCH 18/45] mcs7780: Fix initialization when CONFIG_VMAP_STACK is
 enabled

[ Upstream commit 9476d393667968b4a02afbe9d35a3558482b943e ]

DMA transfers are not allowed to buffers that are on the stack.
Therefore allocate a buffer to store the result of usb_control_message().

Fixes these bugreports:
https://bugzilla.kernel.org/show_bug.cgi?id=195217

https://bugzilla.redhat.com/show_bug.cgi?id=1421387
https://bugzilla.redhat.com/show_bug.cgi?id=1427398

Shortened kernel backtrace from 4.11.9-200.fc25.x86_64:
kernel: ------------[ cut here ]------------
kernel: WARNING: CPU: 3 PID: 2957 at drivers/usb/core/hcd.c:1587
kernel: transfer buffer not dma capable
kernel: Call Trace:
kernel: dump_stack+0x63/0x86
kernel: __warn+0xcb/0xf0
kernel: warn_slowpath_fmt+0x5a/0x80
kernel: usb_hcd_map_urb_for_dma+0x37f/0x570
kernel: ? try_to_del_timer_sync+0x53/0x80
kernel: usb_hcd_submit_urb+0x34e/0xb90
kernel: ? schedule_timeout+0x17e/0x300
kernel: ? del_timer_sync+0x50/0x50
kernel: ? __slab_free+0xa9/0x300
kernel: usb_submit_urb+0x2f4/0x560
kernel: ? urb_destroy+0x24/0x30
kernel: usb_start_wait_urb+0x6e/0x170
kernel: usb_control_msg+0xdc/0x120
kernel: mcs_get_reg+0x36/0x40 [mcs7780]
kernel: mcs_net_open+0xb5/0x5c0 [mcs7780]
...

Regression goes back to 4.9, so it's a good candidate for -stable.
Though it's the decision of the maintainer.

Thanks to Dan Williams for adding the "transfer buffer not dma capable"
warning in the first place. It instantly pointed me in the right direction.

Patch has been tested with transferring data from a Polar watch.

Signed-off-by: Thomas Jarosch <thomas.jarosch@intra2net.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/irda/mcs7780.c | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/drivers/net/irda/mcs7780.c b/drivers/net/irda/mcs7780.c
index 6f6ed75b63c9..765de3bedb88 100644
--- a/drivers/net/irda/mcs7780.c
+++ b/drivers/net/irda/mcs7780.c
@@ -141,9 +141,19 @@ static int mcs_set_reg(struct mcs_cb *mcs, __u16 reg, __u16 val)
 static int mcs_get_reg(struct mcs_cb *mcs, __u16 reg, __u16 * val)
 {
 	struct usb_device *dev = mcs->usbdev;
-	int ret = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), MCS_RDREQ,
-				  MCS_RD_RTYPE, 0, reg, val, 2,
-				  msecs_to_jiffies(MCS_CTRL_TIMEOUT));
+	void *dmabuf;
+	int ret;
+
+	dmabuf = kmalloc(sizeof(__u16), GFP_KERNEL);
+	if (!dmabuf)
+		return -ENOMEM;
+
+	ret = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), MCS_RDREQ,
+			      MCS_RD_RTYPE, 0, reg, dmabuf, 2,
+			      msecs_to_jiffies(MCS_CTRL_TIMEOUT));
+
+	memcpy(val, dmabuf, sizeof(__u16));
+	kfree(dmabuf);
 
 	return ret;
 }
-- 
2.13.4


From 20f2d2331a95183237e7b51d157ac0a7c78d3340 Mon Sep 17 00:00:00 2001
From: Liping Zhang <zlpnobody@gmail.com>
Date: Sun, 23 Jul 2017 17:52:23 +0800
Subject: [PATCH 19/45] openvswitch: fix potential out of bound access in
 parse_ct

[ Upstream commit 69ec932e364b1ba9c3a2085fe96b76c8a3f71e7c ]

Before the 'type' is validated, we shouldn't use it to fetch the
ovs_ct_attr_lens's minlen and maxlen, else, out of bound access
may happen.

Fixes: 7f8a436eaa2c ("openvswitch: Add conntrack action")
Signed-off-by: Liping Zhang <zlpnobody@gmail.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/conntrack.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 08679ebb3068..b3bf66bbf4dc 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -1289,8 +1289,8 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info,
 
 	nla_for_each_nested(a, attr, rem) {
 		int type = nla_type(a);
-		int maxlen = ovs_ct_attr_lens[type].maxlen;
-		int minlen = ovs_ct_attr_lens[type].minlen;
+		int maxlen;
+		int minlen;
 
 		if (type > OVS_CT_ATTR_MAX) {
 			OVS_NLERR(log,
@@ -1298,6 +1298,9 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info,
 				  type, OVS_CT_ATTR_MAX);
 			return -EINVAL;
 		}
+
+		maxlen = ovs_ct_attr_lens[type].maxlen;
+		minlen = ovs_ct_attr_lens[type].minlen;
 		if (nla_len(a) < minlen || nla_len(a) > maxlen) {
 			OVS_NLERR(log,
 				  "Conntrack attr type has unexpected length (type=%d, length=%d, expected=%d)",
-- 
2.13.4


From 7d6cf335693002fcb13624cc81a20e8ba79cb034 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Mon, 24 Jul 2017 10:07:32 -0700
Subject: [PATCH 20/45] packet: fix use-after-free in
 prb_retire_rx_blk_timer_expired()

[ Upstream commit c800aaf8d869f2b9b47b10c5c312fe19f0a94042 ]

There are multiple reports showing we have a use-after-free in
the timer prb_retire_rx_blk_timer_expired(), where we use struct
tpacket_kbdq_core::pkbdq, a pg_vec, after it gets freed by
free_pg_vec().

The interesting part is it is not freed via packet_release() but
via packet_setsockopt(), which means we are not closing the socket.
Looking into the big and fat function packet_set_ring(), this could
happen if we satisfy the following conditions:

1. closing == 0, not on packet_release() path
2. req->tp_block_nr == 0, we don't allocate a new pg_vec
3. rx_ring->pg_vec is already set as V3, which means we already called
   packet_set_ring() wtih req->tp_block_nr > 0 previously
4. req->tp_frame_nr == 0, pass sanity check
5. po->mapped == 0, never called mmap()

In this scenario we are clearing the old rx_ring->pg_vec, so we need
to free this pg_vec, but we don't stop the timer on this path because
of closing==0.

The timer has to be stopped as long as we need to free pg_vec, therefore
the check on closing!=0 is wrong, we should check pg_vec!=NULL instead.

Thanks to liujian for testing different fixes.

Reported-by: alexander.levin@verizon.com
Reported-by: Dave Jones <davej@codemonkey.org.uk>
Reported-by: liujian (CE) <liujian56@huawei.com>
Tested-by: liujian (CE) <liujian56@huawei.com>
Cc: Ding Tianhong <dingtianhong@huawei.com>
Cc: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index e3eeed19cc7a..0880e0a9d151 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -4334,7 +4334,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 		register_prot_hook(sk);
 	}
 	spin_unlock(&po->bind_lock);
-	if (closing && (po->tp_version > TPACKET_V2)) {
+	if (pg_vec && (po->tp_version > TPACKET_V2)) {
 		/* Because we don't support block-based V3 on tx-ring */
 		if (!tx_ring)
 			prb_shutdown_retire_blk_timer(po, rb_queue);
-- 
2.13.4


From afefadcd39f9d62e5e3aa89381f4cf9803f84586 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Mon, 24 Jul 2017 23:14:28 +0200
Subject: [PATCH 21/45] ipv6: Don't increase IPSTATS_MIB_FRAGFAILS twice in
 ip6_fragment()

[ Upstream commit afce615aaabfbaad02550e75c0bec106dafa1adf ]

RFC 2465 defines ipv6IfStatsOutFragFails as:

	"The number of IPv6 datagrams that have been discarded
	 because they needed to be fragmented at this output
	 interface but could not be."

The existing implementation, instead, would increase the counter
twice in case we fail to allocate room for single fragments:
once for the fragment, once for the datagram.

This didn't look intentional though. In one of the two affected
affected failure paths, the double increase was simply a result
of a new 'goto fail' statement, introduced to avoid a skb leak.
The other path appears to be affected since at least 2.6.12-rc2.

Reported-by: Sabrina Dubroca <sdubroca@redhat.com>
Fixes: 1d325d217c7f ("ipv6: ip6_fragment: fix headroom tests and skb leak")
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_output.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 1699acb2fa2c..be0306778938 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -673,8 +673,6 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		*prevhdr = NEXTHDR_FRAGMENT;
 		tmp_hdr = kmemdup(skb_network_header(skb), hlen, GFP_ATOMIC);
 		if (!tmp_hdr) {
-			IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
-				      IPSTATS_MIB_FRAGFAILS);
 			err = -ENOMEM;
 			goto fail;
 		}
@@ -793,8 +791,6 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		frag = alloc_skb(len + hlen + sizeof(struct frag_hdr) +
 				 hroom + troom, GFP_ATOMIC);
 		if (!frag) {
-			IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
-				      IPSTATS_MIB_FRAGFAILS);
 			err = -ENOMEM;
 			goto fail;
 		}
-- 
2.13.4


From fc273f1f8dfacbc876237036f742a09a3dfc5e6c Mon Sep 17 00:00:00 2001
From: Marc Gonzalez <marc_gonzalez@sigmadesigns.com>
Date: Tue, 25 Jul 2017 14:35:03 +0200
Subject: [PATCH 22/45] net: ethernet: nb8800: Handle all 4 RGMII modes
 identically

[ Upstream commit 4813497b537c6208c90d6cbecac5072d347de900 ]

Before commit bf8f6952a233 ("Add blurb about RGMII") it was unclear
whose responsibility it was to insert the required clock skew, and
in hindsight, some PHY drivers got it wrong. The solution forward
is to introduce a new property, explicitly requiring skew from the
node to which it is attached. In the interim, this driver will handle
all 4 RGMII modes identically (no skew).

Fixes: 52dfc8301248 ("net: ethernet: add driver for Aurora VLSI NB8800 Ethernet controller")
Signed-off-by: Marc Gonzalez <marc_gonzalez@sigmadesigns.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aurora/nb8800.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c
index 5711fbbd6ae3..878cffd37e1f 100644
--- a/drivers/net/ethernet/aurora/nb8800.c
+++ b/drivers/net/ethernet/aurora/nb8800.c
@@ -609,7 +609,7 @@ static void nb8800_mac_config(struct net_device *dev)
 		mac_mode |= HALF_DUPLEX;
 
 	if (gigabit) {
-		if (priv->phy_mode == PHY_INTERFACE_MODE_RGMII)
+		if (phy_interface_is_rgmii(dev->phydev))
 			mac_mode |= RGMII_MODE;
 
 		mac_mode |= GMAC_MODE;
@@ -1268,11 +1268,10 @@ static int nb8800_tangox_init(struct net_device *dev)
 		break;
 
 	case PHY_INTERFACE_MODE_RGMII:
-		pad_mode = PAD_MODE_RGMII;
-		break;
-
+	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
 	case PHY_INTERFACE_MODE_RGMII_TXID:
-		pad_mode = PAD_MODE_RGMII | PAD_MODE_GTX_CLK_DELAY;
+		pad_mode = PAD_MODE_RGMII;
 		break;
 
 	default:
-- 
2.13.4


From f8366678a18e5ec051232b6442787efc55bf4cc3 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Tue, 25 Jul 2017 09:44:25 -0700
Subject: [PATCH 23/45] bonding: commit link status change after propose

[ Upstream commit d94708a553022bf012fa95af10532a134eeb5a52 ]

Commit de77ecd4ef02 ("bonding: improve link-status update in mii-monitoring")
moves link status commitment into bond_mii_monitor(), but it still relies
on the return value of bond_miimon_inspect() as the hint. We need to return
non-zero as long as we propose a link status change.

Fixes: de77ecd4ef02 ("bonding: improve link-status update in mii-monitoring")
Reported-by: Benjamin Gilbert <benjamin.gilbert@coreos.com>
Tested-by: Benjamin Gilbert <benjamin.gilbert@coreos.com>
Cc: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 619c6f8d8142..224e93aa6d23 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2047,6 +2047,7 @@ static int bond_miimon_inspect(struct bonding *bond)
 				continue;
 
 			bond_propose_link_state(slave, BOND_LINK_FAIL);
+			commit++;
 			slave->delay = bond->params.downdelay;
 			if (slave->delay) {
 				netdev_info(bond->dev, "link status down for %sinterface %s, disabling it in %d ms\n",
@@ -2085,6 +2086,7 @@ static int bond_miimon_inspect(struct bonding *bond)
 				continue;
 
 			bond_propose_link_state(slave, BOND_LINK_BACK);
+			commit++;
 			slave->delay = bond->params.updelay;
 
 			if (slave->delay) {
-- 
2.13.4


From 46482058577f2e902c7346d838959cb2255bf527 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 26 Jul 2017 14:19:09 +0800
Subject: [PATCH 24/45] dccp: fix a memleak that dccp_ipv6 doesn't put reqsk
 properly

[ Upstream commit 0c2232b0a71db0ac1d22f751aa1ac0cadb950fd2 ]

In dccp_v6_conn_request, after reqsk gets alloced and hashed into
ehash table, reqsk's refcnt is set 3. one is for req->rsk_timer,
one is for hlist, and the other one is for current using.

The problem is when dccp_v6_conn_request returns and finishes using
reqsk, it doesn't put reqsk. This will cause reqsk refcnt leaks and
reqsk obj never gets freed.

Jianlin found this issue when running dccp_memleak.c in a loop, the
system memory would run out.

dccp_memleak.c:
  int s1 = socket(PF_INET6, 6, IPPROTO_IP);
  bind(s1, &sa1, 0x20);
  listen(s1, 0x9);
  int s2 = socket(PF_INET6, 6, IPPROTO_IP);
  connect(s2, &sa1, 0x20);
  close(s1);
  close(s2);

This patch is to put the reqsk before dccp_v6_conn_request returns,
just as what tcp_conn_request does.

Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ipv6.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 992621172220..cf3e40df4765 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -380,6 +380,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 		goto drop_and_free;
 
 	inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT);
+	reqsk_put(req);
 	return 0;
 
 drop_and_free:
-- 
2.13.4


From fa4ff10876a298a8847042ceffe7304612d1e1ad Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 26 Jul 2017 14:19:46 +0800
Subject: [PATCH 25/45] dccp: fix a memleak that dccp_ipv4 doesn't put reqsk
 properly

[ Upstream commit b7953d3c0e30a5fc944f6b7bd0bcceb0794bcd85 ]

The patch "dccp: fix a memleak that dccp_ipv6 doesn't put reqsk
properly" fixed reqsk refcnt leak for dccp_ipv6. The same issue
exists on dccp_ipv4.

This patch is to fix it for dccp_ipv4.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ipv4.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index f75482bdee9a..97368f229876 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -631,6 +631,7 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 		goto drop_and_free;
 
 	inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT);
+	reqsk_put(req);
 	return 0;
 
 drop_and_free:
-- 
2.13.4


From aa9bbb98c94d5c65fc165b89d522a6e9cd5f83e6 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 26 Jul 2017 14:20:15 +0800
Subject: [PATCH 26/45] dccp: fix a memleak for dccp_feat_init err process

[ Upstream commit e90ce2fc27cad7e7b1e72b9e66201a7a4c124c2b ]

In dccp_feat_init, when ccid_get_builtin_ccids failsto alloc
memory for rx.val, it should free tx.val before returning an
error.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/feat.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/dccp/feat.c b/net/dccp/feat.c
index 1704948e6a12..f227f002c73d 100644
--- a/net/dccp/feat.c
+++ b/net/dccp/feat.c
@@ -1471,9 +1471,12 @@ int dccp_feat_init(struct sock *sk)
 	 * singleton values (which always leads to failure).
 	 * These settings can still (later) be overridden via sockopts.
 	 */
-	if (ccid_get_builtin_ccids(&tx.val, &tx.len) ||
-	    ccid_get_builtin_ccids(&rx.val, &rx.len))
+	if (ccid_get_builtin_ccids(&tx.val, &tx.len))
 		return -ENOBUFS;
+	if (ccid_get_builtin_ccids(&rx.val, &rx.len)) {
+		kfree(tx.val);
+		return -ENOBUFS;
+	}
 
 	if (!dccp_feat_prefer(sysctl_dccp_tx_ccid, tx.val, tx.len) ||
 	    !dccp_feat_prefer(sysctl_dccp_rx_ccid, rx.val, rx.len))
-- 
2.13.4


From 93b7c731357b2f304dcf1fd5c5fcec10ae54e6d1 Mon Sep 17 00:00:00 2001
From: Aviv Heller <avivh@mellanox.com>
Date: Sun, 2 Jul 2017 19:13:43 +0300
Subject: [PATCH 27/45] net/mlx5: Consider tx_enabled in all modes on remap

[ Upstream commit dc798b4cc0f2a06e7ad7d522403de274b86a0a6f ]

The tx_enabled lag event field is used to determine whether a slave is
active.
Current logic uses this value only if the mode is active-backup.

However, LACP mode, although considered a load balancing mode, can mark
a slave as inactive in certain situations (e.g., LACP timeout).

This fix takes the tx_enabled value into account when remapping, with
no respect to the LAG mode (this should not affect the behavior in XOR
mode, since in this mode both slaves are marked as active).

Fixes: 7907f23adc18 (net/mlx5: Implement RoCE LAG feature)
Signed-off-by: Aviv Heller <avivh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/lag.c | 25 ++++++++++---------------
 1 file changed, 10 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index b5d5519542e8..0ca4623bda6b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -157,22 +157,17 @@ static bool mlx5_lag_is_bonded(struct mlx5_lag *ldev)
 static void mlx5_infer_tx_affinity_mapping(struct lag_tracker *tracker,
 					   u8 *port1, u8 *port2)
 {
-	if (tracker->tx_type == NETDEV_LAG_TX_TYPE_ACTIVEBACKUP) {
-		if (tracker->netdev_state[0].tx_enabled) {
-			*port1 = 1;
-			*port2 = 1;
-		} else {
-			*port1 = 2;
-			*port2 = 2;
-		}
-	} else {
-		*port1 = 1;
-		*port2 = 2;
-		if (!tracker->netdev_state[0].link_up)
-			*port1 = 2;
-		else if (!tracker->netdev_state[1].link_up)
-			*port2 = 1;
+	*port1 = 1;
+	*port2 = 2;
+	if (!tracker->netdev_state[0].tx_enabled ||
+	    !tracker->netdev_state[0].link_up) {
+		*port1 = 2;
+		return;
 	}
+
+	if (!tracker->netdev_state[1].tx_enabled ||
+	    !tracker->netdev_state[1].link_up)
+		*port2 = 1;
 }
 
 static void mlx5_activate_lag(struct mlx5_lag *ldev,
-- 
2.13.4


From 1e2463b36d7da0550f3ff3105960310f268f4c30 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Thu, 6 Jul 2017 15:48:40 +0300
Subject: [PATCH 28/45] net/mlx5: Fix command completion after timeout access
 invalid structure

[ Upstream commit 061870800efb4e3d1ad4082a2569363629bdfcfc ]

Completion on timeout should not free the driver command entry structure
as it will need to access it again once real completion event from FW
will occur.

Fixes: 73dd3a4839c1 ('net/mlx5: Avoid using pending command interface slots')
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Cc: kernel-team@fb.com
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 10d282841f5b..516e5d317885 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -955,7 +955,7 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 
 	err = wait_func(dev, ent);
 	if (err == -ETIMEDOUT)
-		goto out_free;
+		goto out;
 
 	ds = ent->ts2 - ent->ts1;
 	op = MLX5_GET(mbox_in, in->first.data, opcode);
@@ -1419,6 +1419,7 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced)
 					mlx5_core_err(dev, "Command completion arrived after timeout (entry idx = %d).\n",
 						      ent->idx);
 					free_ent(cmd, ent->idx);
+					free_cmd(ent);
 				}
 				continue;
 			}
@@ -1477,7 +1478,8 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced)
 				free_msg(dev, ent->in);
 
 				err = err ? err : ent->status;
-				free_cmd(ent);
+				if (!forced)
+					free_cmd(ent);
 				callback(err, context);
 			} else {
 				complete(&ent->done);
-- 
2.13.4


From 146c95bfb57ca1020c1118569c26eeae57ba47cf Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Sun, 25 Jun 2017 18:45:32 +0300
Subject: [PATCH 29/45] net/mlx5: Fix command bad flow on command entry
 allocation failure

[ Upstream commit 219c81f7d1d5a89656cb3b53d3b4e11e93608d80 ]

When driver fail to allocate an entry to send command to FW, it must
notify the calling function and release the memory allocated for
this command.

Fixes: e126ba97dba9e ('mlx5: Add driver for Mellanox Connect-IB adapters')
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Cc: kernel-team@fb.com
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 516e5d317885..ac0a460c006a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -777,6 +777,10 @@ static void cb_timeout_handler(struct work_struct *work)
 	mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
 }
 
+static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg);
+static void mlx5_free_cmd_msg(struct mlx5_core_dev *dev,
+			      struct mlx5_cmd_msg *msg);
+
 static void cmd_work_handler(struct work_struct *work)
 {
 	struct mlx5_cmd_work_ent *ent = container_of(work, struct mlx5_cmd_work_ent, work);
@@ -786,16 +790,27 @@ static void cmd_work_handler(struct work_struct *work)
 	struct mlx5_cmd_layout *lay;
 	struct semaphore *sem;
 	unsigned long flags;
+	int alloc_ret;
 
 	sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem;
 	down(sem);
 	if (!ent->page_queue) {
-		ent->idx = alloc_ent(cmd);
-		if (ent->idx < 0) {
+		alloc_ret = alloc_ent(cmd);
+		if (alloc_ret < 0) {
 			mlx5_core_err(dev, "failed to allocate command entry\n");
+			if (ent->callback) {
+				ent->callback(-EAGAIN, ent->context);
+				mlx5_free_cmd_msg(dev, ent->out);
+				free_msg(dev, ent->in);
+				free_cmd(ent);
+			} else {
+				ent->ret = -EAGAIN;
+				complete(&ent->done);
+			}
 			up(sem);
 			return;
 		}
+		ent->idx = alloc_ret;
 	} else {
 		ent->idx = cmd->max_reg_cmds;
 		spin_lock_irqsave(&cmd->alloc_lock, flags);
-- 
2.13.4


From f9290fd96dba620a01626bb3d1ac4875557dbd9f Mon Sep 17 00:00:00 2001
From: Alexander Potapenko <glider@google.com>
Date: Fri, 14 Jul 2017 18:32:45 +0200
Subject: [PATCH 30/45] sctp: don't dereference ptr before leaving
 _sctp_walk_{params, errors}()

[ Upstream commit b1f5bfc27a19f214006b9b4db7b9126df2dfdf5a ]

If the length field of the iterator (|pos.p| or |err|) is past the end
of the chunk, we shouldn't access it.

This bug has been detected by KMSAN. For the following pair of system
calls:

  socket(PF_INET6, SOCK_STREAM, 0x84 /* IPPROTO_??? */) = 3
  sendto(3, "A", 1, MSG_OOB, {sa_family=AF_INET6, sin6_port=htons(0),
         inet_pton(AF_INET6, "::1", &sin6_addr), sin6_flowinfo=0,
         sin6_scope_id=0}, 28) = 1

the tool has reported a use of uninitialized memory:

  ==================================================================
  BUG: KMSAN: use of uninitialized memory in sctp_rcv+0x17b8/0x43b0
  CPU: 1 PID: 2940 Comm: probe Not tainted 4.11.0-rc5+ #2926
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs
  01/01/2011
  Call Trace:
   <IRQ>
   __dump_stack lib/dump_stack.c:16
   dump_stack+0x172/0x1c0 lib/dump_stack.c:52
   kmsan_report+0x12a/0x180 mm/kmsan/kmsan.c:927
   __msan_warning_32+0x61/0xb0 mm/kmsan/kmsan_instr.c:469
   __sctp_rcv_init_lookup net/sctp/input.c:1074
   __sctp_rcv_lookup_harder net/sctp/input.c:1233
   __sctp_rcv_lookup net/sctp/input.c:1255
   sctp_rcv+0x17b8/0x43b0 net/sctp/input.c:170
   sctp6_rcv+0x32/0x70 net/sctp/ipv6.c:984
   ip6_input_finish+0x82f/0x1ee0 net/ipv6/ip6_input.c:279
   NF_HOOK ./include/linux/netfilter.h:257
   ip6_input+0x239/0x290 net/ipv6/ip6_input.c:322
   dst_input ./include/net/dst.h:492
   ip6_rcv_finish net/ipv6/ip6_input.c:69
   NF_HOOK ./include/linux/netfilter.h:257
   ipv6_rcv+0x1dbd/0x22e0 net/ipv6/ip6_input.c:203
   __netif_receive_skb_core+0x2f6f/0x3a20 net/core/dev.c:4208
   __netif_receive_skb net/core/dev.c:4246
   process_backlog+0x667/0xba0 net/core/dev.c:4866
   napi_poll net/core/dev.c:5268
   net_rx_action+0xc95/0x1590 net/core/dev.c:5333
   __do_softirq+0x485/0x942 kernel/softirq.c:284
   do_softirq_own_stack+0x1c/0x30 arch/x86/entry/entry_64.S:902
   </IRQ>
   do_softirq kernel/softirq.c:328
   __local_bh_enable_ip+0x25b/0x290 kernel/softirq.c:181
   local_bh_enable+0x37/0x40 ./include/linux/bottom_half.h:31
   rcu_read_unlock_bh ./include/linux/rcupdate.h:931
   ip6_finish_output2+0x19b2/0x1cf0 net/ipv6/ip6_output.c:124
   ip6_finish_output+0x764/0x970 net/ipv6/ip6_output.c:149
   NF_HOOK_COND ./include/linux/netfilter.h:246
   ip6_output+0x456/0x520 net/ipv6/ip6_output.c:163
   dst_output ./include/net/dst.h:486
   NF_HOOK ./include/linux/netfilter.h:257
   ip6_xmit+0x1841/0x1c00 net/ipv6/ip6_output.c:261
   sctp_v6_xmit+0x3b7/0x470 net/sctp/ipv6.c:225
   sctp_packet_transmit+0x38cb/0x3a20 net/sctp/output.c:632
   sctp_outq_flush+0xeb3/0x46e0 net/sctp/outqueue.c:885
   sctp_outq_uncork+0xb2/0xd0 net/sctp/outqueue.c:750
   sctp_side_effects net/sctp/sm_sideeffect.c:1773
   sctp_do_sm+0x6962/0x6ec0 net/sctp/sm_sideeffect.c:1147
   sctp_primitive_ASSOCIATE+0x12c/0x160 net/sctp/primitive.c:88
   sctp_sendmsg+0x43e5/0x4f90 net/sctp/socket.c:1954
   inet_sendmsg+0x498/0x670 net/ipv4/af_inet.c:762
   sock_sendmsg_nosec net/socket.c:633
   sock_sendmsg net/socket.c:643
   SYSC_sendto+0x608/0x710 net/socket.c:1696
   SyS_sendto+0x8a/0xb0 net/socket.c:1664
   do_syscall_64+0xe6/0x130 arch/x86/entry/common.c:285
   entry_SYSCALL64_slow_path+0x25/0x25 arch/x86/entry/entry_64.S:246
  RIP: 0033:0x401133
  RSP: 002b:00007fff6d99cd38 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
  RAX: ffffffffffffffda RBX: 00000000004002b0 RCX: 0000000000401133
  RDX: 0000000000000001 RSI: 0000000000494088 RDI: 0000000000000003
  RBP: 00007fff6d99cd90 R08: 00007fff6d99cd50 R09: 000000000000001c
  R10: 0000000000000001 R11: 0000000000000246 R12: 0000000000000000
  R13: 00000000004063d0 R14: 0000000000406460 R15: 0000000000000000
  origin:
   save_stack_trace+0x37/0x40 arch/x86/kernel/stacktrace.c:59
   kmsan_save_stack_with_flags mm/kmsan/kmsan.c:302
   kmsan_internal_poison_shadow+0xb1/0x1a0 mm/kmsan/kmsan.c:198
   kmsan_poison_shadow+0x6d/0xc0 mm/kmsan/kmsan.c:211
   slab_alloc_node mm/slub.c:2743
   __kmalloc_node_track_caller+0x200/0x360 mm/slub.c:4351
   __kmalloc_reserve net/core/skbuff.c:138
   __alloc_skb+0x26b/0x840 net/core/skbuff.c:231
   alloc_skb ./include/linux/skbuff.h:933
   sctp_packet_transmit+0x31e/0x3a20 net/sctp/output.c:570
   sctp_outq_flush+0xeb3/0x46e0 net/sctp/outqueue.c:885
   sctp_outq_uncork+0xb2/0xd0 net/sctp/outqueue.c:750
   sctp_side_effects net/sctp/sm_sideeffect.c:1773
   sctp_do_sm+0x6962/0x6ec0 net/sctp/sm_sideeffect.c:1147
   sctp_primitive_ASSOCIATE+0x12c/0x160 net/sctp/primitive.c:88
   sctp_sendmsg+0x43e5/0x4f90 net/sctp/socket.c:1954
   inet_sendmsg+0x498/0x670 net/ipv4/af_inet.c:762
   sock_sendmsg_nosec net/socket.c:633
   sock_sendmsg net/socket.c:643
   SYSC_sendto+0x608/0x710 net/socket.c:1696
   SyS_sendto+0x8a/0xb0 net/socket.c:1664
   do_syscall_64+0xe6/0x130 arch/x86/entry/common.c:285
   return_from_SYSCALL_64+0x0/0x6a arch/x86/entry/entry_64.S:246
  ==================================================================

Signed-off-by: Alexander Potapenko <glider@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/sctp.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 069582ee5d7f..257af3f88295 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -469,6 +469,8 @@ _sctp_walk_params((pos), (chunk), ntohs((chunk)->chunk_hdr.length), member)
 
 #define _sctp_walk_params(pos, chunk, end, member)\
 for (pos.v = chunk->member;\
+     (pos.v + offsetof(struct sctp_paramhdr, length) + sizeof(pos.p->length) <\
+      (void *)chunk + end) &&\
      pos.v <= (void *)chunk + end - ntohs(pos.p->length) &&\
      ntohs(pos.p->length) >= sizeof(sctp_paramhdr_t);\
      pos.v += SCTP_PAD4(ntohs(pos.p->length)))
@@ -479,6 +481,8 @@ _sctp_walk_errors((err), (chunk_hdr), ntohs((chunk_hdr)->length))
 #define _sctp_walk_errors(err, chunk_hdr, end)\
 for (err = (sctp_errhdr_t *)((void *)chunk_hdr + \
 	    sizeof(sctp_chunkhdr_t));\
+     ((void *)err + offsetof(sctp_errhdr_t, length) + sizeof(err->length) <\
+      (void *)chunk_hdr + end) &&\
      (void *)err <= (void *)chunk_hdr + end - ntohs(err->length) &&\
      ntohs(err->length) >= sizeof(sctp_errhdr_t); \
      err = (sctp_errhdr_t *)((void *)err + SCTP_PAD4(ntohs(err->length))))
-- 
2.13.4


From 0d23638c23e6de2923f831bdc963a4e43a319222 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 26 Jul 2017 16:24:59 +0800
Subject: [PATCH 31/45] sctp: fix the check for _sctp_walk_params and
 _sctp_walk_errors

[ Upstream commit 6b84202c946cd3da3a8daa92c682510e9ed80321 ]

Commit b1f5bfc27a19 ("sctp: don't dereference ptr before leaving
_sctp_walk_{params, errors}()") tried to fix the issue that it
may overstep the chunk end for _sctp_walk_{params, errors} with
'chunk_end > offset(length) + sizeof(length)'.

But it introduced a side effect: When processing INIT, it verifies
the chunks with 'param.v == chunk_end' after iterating all params
by sctp_walk_params(). With the check 'chunk_end > offset(length)
+ sizeof(length)', it would return when the last param is not yet
accessed. Because the last param usually is fwdtsn supported param
whose size is 4 and 'chunk_end == offset(length) + sizeof(length)'

This is a badly issue even causing sctp couldn't process 4-shakes.
Client would always get abort when connecting to server, due to
the failure of INIT chunk verification on server.

The patch is to use 'chunk_end <= offset(length) + sizeof(length)'
instead of 'chunk_end < offset(length) + sizeof(length)' for both
_sctp_walk_params and _sctp_walk_errors.

Fixes: b1f5bfc27a19 ("sctp: don't dereference ptr before leaving _sctp_walk_{params, errors}()")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/sctp.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 257af3f88295..06db0c3ec384 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -469,7 +469,7 @@ _sctp_walk_params((pos), (chunk), ntohs((chunk)->chunk_hdr.length), member)
 
 #define _sctp_walk_params(pos, chunk, end, member)\
 for (pos.v = chunk->member;\
-     (pos.v + offsetof(struct sctp_paramhdr, length) + sizeof(pos.p->length) <\
+     (pos.v + offsetof(struct sctp_paramhdr, length) + sizeof(pos.p->length) <=\
       (void *)chunk + end) &&\
      pos.v <= (void *)chunk + end - ntohs(pos.p->length) &&\
      ntohs(pos.p->length) >= sizeof(sctp_paramhdr_t);\
@@ -481,7 +481,7 @@ _sctp_walk_errors((err), (chunk_hdr), ntohs((chunk_hdr)->length))
 #define _sctp_walk_errors(err, chunk_hdr, end)\
 for (err = (sctp_errhdr_t *)((void *)chunk_hdr + \
 	    sizeof(sctp_chunkhdr_t));\
-     ((void *)err + offsetof(sctp_errhdr_t, length) + sizeof(err->length) <\
+     ((void *)err + offsetof(sctp_errhdr_t, length) + sizeof(err->length) <=\
       (void *)chunk_hdr + end) &&\
      (void *)err <= (void *)chunk_hdr + end - ntohs(err->length) &&\
      ntohs(err->length) >= sizeof(sctp_errhdr_t); \
-- 
2.13.4


From 6c83bb940448bc82bccc1701f9c5e26ab509893d Mon Sep 17 00:00:00 2001
From: Alex Vesker <valex@mellanox.com>
Date: Thu, 6 Jul 2017 15:40:32 +0300
Subject: [PATCH 32/45] net/mlx5e: IPoIB, Modify add/remove underlay QPN flows

[ Upstream commit 58569ef8f619761548e7d198f59e8ebe3af91d04 ]

On interface remove, the clean-up was done incorrectly causing
an error in the log:
"SET_FLOW_TABLE_ROOT(0x92f) op_mod(0x0) failed...syndrome (0x7e9f14)"

This was caused by the following flow:
-ndo_uninit:
 Move QP state to RST (this disconnects the QP from FT),
 the QP cannot be attached to any FT unless it is in RTS.

-mlx5_rdma_netdev_free:
 cleanup_rx: Destroy FT
 cleanup_tx: Destroy QP and remove QPN from FT

This caused a problem when destroying current FT we tried to
re-attach the QP to the next FT which is not needed.

The correct flow is:
-mlx5_rdma_netdev_free:
	cleanup_rx: remove QPN from FT & Destroy FT
	cleanup_tx: Destroy QP

Fixes: 508541146af1 ("net/mlx5: Use underlay QPN from the root name space")
Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/ipoib.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib.c
index cc1858752e70..6d90e9e3bfd1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib.c
@@ -160,8 +160,6 @@ static int mlx5i_create_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core
 
 static void mlx5i_destroy_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp)
 {
-	mlx5_fs_remove_rx_underlay_qpn(mdev, qp->qpn);
-
 	mlx5_core_destroy_qp(mdev, qp);
 }
 
@@ -176,8 +174,6 @@ static int mlx5i_init_tx(struct mlx5e_priv *priv)
 		return err;
 	}
 
-	mlx5_fs_add_rx_underlay_qpn(priv->mdev, ipriv->qp.qpn);
-
 	err = mlx5e_create_tis(priv->mdev, 0 /* tc */, ipriv->qp.qpn, &priv->tisn[0]);
 	if (err) {
 		mlx5_core_warn(priv->mdev, "create tis failed, %d\n", err);
@@ -235,6 +231,7 @@ static void mlx5i_destroy_flow_steering(struct mlx5e_priv *priv)
 
 static int mlx5i_init_rx(struct mlx5e_priv *priv)
 {
+	struct mlx5i_priv *ipriv  = priv->ppriv;
 	int err;
 
 	err = mlx5e_create_indirect_rqt(priv);
@@ -253,12 +250,18 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv)
 	if (err)
 		goto err_destroy_indirect_tirs;
 
-	err = mlx5i_create_flow_steering(priv);
+	err = mlx5_fs_add_rx_underlay_qpn(priv->mdev, ipriv->qp.qpn);
 	if (err)
 		goto err_destroy_direct_tirs;
 
+	err = mlx5i_create_flow_steering(priv);
+	if (err)
+		goto err_remove_rx_underlay_qpn;
+
 	return 0;
 
+err_remove_rx_underlay_qpn:
+	mlx5_fs_remove_rx_underlay_qpn(priv->mdev, ipriv->qp.qpn);
 err_destroy_direct_tirs:
 	mlx5e_destroy_direct_tirs(priv);
 err_destroy_indirect_tirs:
@@ -272,6 +275,9 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv)
 
 static void mlx5i_cleanup_rx(struct mlx5e_priv *priv)
 {
+	struct mlx5i_priv *ipriv  = priv->ppriv;
+
+	mlx5_fs_remove_rx_underlay_qpn(priv->mdev, ipriv->qp.qpn);
 	mlx5i_destroy_flow_steering(priv);
 	mlx5e_destroy_direct_tirs(priv);
 	mlx5e_destroy_indirect_tirs(priv);
-- 
2.13.4


From cd642425b35a1f9d91911ad1a02bfd5d60074302 Mon Sep 17 00:00:00 2001
From: Ilan Tayari <ilant@mellanox.com>
Date: Wed, 5 Jul 2017 10:17:04 +0300
Subject: [PATCH 33/45] net/mlx5e: Fix outer_header_zero() check size

[ Upstream commit 0242f4a0bb03906010bbf80495512be00494a0ef ]

outer_header_zero() routine checks if the outer_headers match of a
flow-table entry are all zero.

This function uses the size of whole fte_match_param, instead of just
the outer_headers member, causing failure to detect all-zeros if
any other members of the fte_match_param are non-zero.

Use the correct size for zero check.

Fixes: 6dc6071cfcde ("net/mlx5e: Add ethtool flow steering support")
Signed-off-by: Ilan Tayari <ilant@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index 85bf4a389295..969ddb3aaf6e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -276,7 +276,7 @@ static void add_rule_to_list(struct mlx5e_priv *priv,
 
 static bool outer_header_zero(u32 *match_criteria)
 {
-	int size = MLX5_ST_SZ_BYTES(fte_match_param);
+	int size = MLX5_FLD_SZ_BYTES(fte_match_param, outer_headers);
 	char *outer_headers_c = MLX5_ADDR_OF(fte_match_param, match_criteria,
 					     outer_headers);
 
-- 
2.13.4


From 14fdd157cca9f4f48a5de583a4c78846b6bd9a2d Mon Sep 17 00:00:00 2001
From: Eugenia Emantayev <eugenia@mellanox.com>
Date: Thu, 25 May 2017 15:11:26 +0300
Subject: [PATCH 34/45] net/mlx5: Fix mlx5_ifc_mtpps_reg_bits structure size

[ Upstream commit 0b794ffae7afa7c4e5accac8791c4b78e8d080ce ]

Fix miscalculation in reserved_at_1a0 field.

Fixes: ee7f12205abc ('net/mlx5e: Implement 1PPS support')
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 include/linux/mlx5/mlx5_ifc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index edafedb7b509..9d1241a25436 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -8131,7 +8131,7 @@ struct mlx5_ifc_mtpps_reg_bits {
 	u8         out_pulse_duration[0x10];
 	u8         out_periodic_adjustment[0x10];
 
-	u8         reserved_at_1a0[0x60];
+	u8         reserved_at_1a0[0x40];
 };
 
 struct mlx5_ifc_mtppse_reg_bits {
-- 
2.13.4


From 76a7e666a143c7ffc2fa8bc94beefe078194f2fa Mon Sep 17 00:00:00 2001
From: Eugenia Emantayev <eugenia@mellanox.com>
Date: Thu, 25 May 2017 16:09:34 +0300
Subject: [PATCH 35/45] net/mlx5e: Add field select to MTPPS register

[ Upstream commit fa3676885e3b5be1edfa1b2cc775e20a45b34a19 ]

In order to mark relevant fields while setting the MTPPS register
add field select. Otherwise it can cause a misconfiguration in
firmware.

Fixes: ee7f12205abc ('net/mlx5e: Implement 1PPS support')
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_clock.c | 29 +++++++++++++++++-----
 drivers/net/ethernet/mellanox/mlx5/core/eq.c       |  2 +-
 .../net/ethernet/mellanox/mlx5/core/mlx5_core.h    |  5 ++++
 include/linux/mlx5/mlx5_ifc.h                      | 10 +++++---
 4 files changed, 36 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
index e706a87fc8b2..353a4898d95b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
@@ -53,6 +53,15 @@ enum {
 	MLX5E_EVENT_MODE_ONCE_TILL_ARM	= 0x2,
 };
 
+enum {
+	MLX5E_MTPPS_FS_ENABLE			= BIT(0x0),
+	MLX5E_MTPPS_FS_PATTERN			= BIT(0x2),
+	MLX5E_MTPPS_FS_PIN_MODE			= BIT(0x3),
+	MLX5E_MTPPS_FS_TIME_STAMP		= BIT(0x4),
+	MLX5E_MTPPS_FS_OUT_PULSE_DURATION	= BIT(0x5),
+	MLX5E_MTPPS_FS_ENH_OUT_PER_ADJ		= BIT(0x7),
+};
+
 void mlx5e_fill_hwstamp(struct mlx5e_tstamp *tstamp, u64 timestamp,
 			struct skb_shared_hwtstamps *hwts)
 {
@@ -222,7 +231,10 @@ static int mlx5e_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta)
 
 		/* For future use need to add a loop for finding all 1PPS out pins */
 		MLX5_SET(mtpps_reg, in, pin_mode, MLX5E_PIN_MODE_OUT);
-		MLX5_SET(mtpps_reg, in, out_periodic_adjustment, delta & 0xFFFF);
+		MLX5_SET(mtpps_reg, in, enhanced_out_periodic_adjustment, delta);
+		MLX5_SET(mtpps_reg, in, field_select,
+			 MLX5E_MTPPS_FS_PIN_MODE |
+			 MLX5E_MTPPS_FS_ENH_OUT_PER_ADJ);
 
 		mlx5_set_mtpps(priv->mdev, in, sizeof(in));
 	}
@@ -258,8 +270,7 @@ static int mlx5e_extts_configure(struct ptp_clock_info *ptp,
 	int pin = -1;
 	int err = 0;
 
-	if (!MLX5_CAP_GEN(priv->mdev, pps) ||
-	    !MLX5_CAP_GEN(priv->mdev, pps_modify))
+	if (!MLX5_PPS_CAP(priv->mdev))
 		return -EOPNOTSUPP;
 
 	if (rq->extts.index >= tstamp->ptp_info.n_pins)
@@ -278,6 +289,9 @@ static int mlx5e_extts_configure(struct ptp_clock_info *ptp,
 	MLX5_SET(mtpps_reg, in, pin_mode, MLX5E_PIN_MODE_IN);
 	MLX5_SET(mtpps_reg, in, pattern, pattern);
 	MLX5_SET(mtpps_reg, in, enable, on);
+	MLX5_SET(mtpps_reg, in, field_select, MLX5E_MTPPS_FS_PIN_MODE |
+					      MLX5E_MTPPS_FS_PATTERN |
+					      MLX5E_MTPPS_FS_ENABLE);
 
 	err = mlx5_set_mtpps(priv->mdev, in, sizeof(in));
 	if (err)
@@ -303,7 +317,7 @@ static int mlx5e_perout_configure(struct ptp_clock_info *ptp,
 	int pin = -1;
 	s64 ns;
 
-	if (!MLX5_CAP_GEN(priv->mdev, pps_modify))
+	if (!MLX5_PPS_CAP(priv->mdev))
 		return -EOPNOTSUPP;
 
 	if (rq->perout.index >= tstamp->ptp_info.n_pins)
@@ -338,7 +352,10 @@ static int mlx5e_perout_configure(struct ptp_clock_info *ptp,
 	MLX5_SET(mtpps_reg, in, pattern, MLX5E_OUT_PATTERN_PERIODIC);
 	MLX5_SET(mtpps_reg, in, enable, on);
 	MLX5_SET64(mtpps_reg, in, time_stamp, time_stamp);
-
+	MLX5_SET(mtpps_reg, in, field_select, MLX5E_MTPPS_FS_PIN_MODE |
+					      MLX5E_MTPPS_FS_PATTERN |
+					      MLX5E_MTPPS_FS_ENABLE |
+					      MLX5E_MTPPS_FS_TIME_STAMP);
 	return mlx5_set_mtpps(priv->mdev, in, sizeof(in));
 }
 
@@ -488,7 +505,7 @@ void mlx5e_timestamp_init(struct mlx5e_priv *priv)
 #define MAX_PIN_NUM	8
 	tstamp->pps_pin_caps = kzalloc(sizeof(u8) * MAX_PIN_NUM, GFP_KERNEL);
 	if (tstamp->pps_pin_caps) {
-		if (MLX5_CAP_GEN(priv->mdev, pps))
+		if (MLX5_PPS_CAP(priv->mdev))
 			mlx5e_get_pps_caps(priv, tstamp);
 		if (tstamp->ptp_info.n_pins)
 			mlx5e_init_pin_config(tstamp);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 33eae5ad2fb0..58a9f5c96d10 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -690,7 +690,7 @@ int mlx5_start_eqs(struct mlx5_core_dev *dev)
 	else
 		mlx5_core_dbg(dev, "port_module_event is not set\n");
 
-	if (MLX5_CAP_GEN(dev, pps))
+	if (MLX5_PPS_CAP(dev))
 		async_event_mask |= (1ull << MLX5_EVENT_TYPE_PPS_EVENT);
 
 	err = mlx5_create_map_eq(dev, &table->cmd_eq, MLX5_EQ_VEC_CMD,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index fbc6e9e9e305..1874aa96c1a1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -153,6 +153,11 @@ int mlx5_set_mtpps(struct mlx5_core_dev *mdev, u32 *mtpps, u32 mtpps_size);
 int mlx5_query_mtppse(struct mlx5_core_dev *mdev, u8 pin, u8 *arm, u8 *mode);
 int mlx5_set_mtppse(struct mlx5_core_dev *mdev, u8 pin, u8 arm, u8 mode);
 
+#define MLX5_PPS_CAP(mdev) (MLX5_CAP_GEN((mdev), pps) &&		\
+			    MLX5_CAP_GEN((mdev), pps_modify) &&		\
+			    MLX5_CAP_MCAM_FEATURE((mdev), mtpps_fs) &&	\
+			    MLX5_CAP_MCAM_FEATURE((mdev), mtpps_enh_out_per_adj))
+
 void mlx5e_init(void);
 void mlx5e_cleanup(void);
 
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 9d1241a25436..e21a0b3d6454 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -7718,8 +7718,10 @@ struct mlx5_ifc_pcam_reg_bits {
 };
 
 struct mlx5_ifc_mcam_enhanced_features_bits {
-	u8         reserved_at_0[0x7f];
+	u8         reserved_at_0[0x7d];
 
+	u8         mtpps_enh_out_per_adj[0x1];
+	u8         mtpps_fs[0x1];
 	u8         pcie_performance_group[0x1];
 };
 
@@ -8115,7 +8117,8 @@ struct mlx5_ifc_mtpps_reg_bits {
 	u8         reserved_at_78[0x4];
 	u8         cap_pin_4_mode[0x4];
 
-	u8         reserved_at_80[0x80];
+	u8         field_select[0x20];
+	u8         reserved_at_a0[0x60];
 
 	u8         enable[0x1];
 	u8         reserved_at_101[0xb];
@@ -8130,8 +8133,9 @@ struct mlx5_ifc_mtpps_reg_bits {
 
 	u8         out_pulse_duration[0x10];
 	u8         out_periodic_adjustment[0x10];
+	u8         enhanced_out_periodic_adjustment[0x20];
 
-	u8         reserved_at_1a0[0x40];
+	u8         reserved_at_1c0[0x20];
 };
 
 struct mlx5_ifc_mtppse_reg_bits {
-- 
2.13.4


From 1111e97a9b2c8e92bb7e1781bebfa364e227367f Mon Sep 17 00:00:00 2001
From: Eugenia Emantayev <eugenia@mellanox.com>
Date: Sun, 28 May 2017 12:01:38 +0300
Subject: [PATCH 36/45] net/mlx5e: Fix broken disable 1PPS flow

[ Upstream commit 49c5031ca6f0628ef973a11b17e463e088bf859e ]

Need to disable the MTPPS and unsubscribe from the pulse events
when user disables the 1PPS functionality.

Fixes: ee7f12205abc ('net/mlx5e: Implement 1PPS support')
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_clock.c | 75 +++++++++++++---------
 1 file changed, 46 insertions(+), 29 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
index 353a4898d95b..41397de86f89 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
@@ -266,6 +266,8 @@ static int mlx5e_extts_configure(struct ptp_clock_info *ptp,
 	struct mlx5e_priv *priv =
 		container_of(tstamp, struct mlx5e_priv, tstamp);
 	u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
+	u32 field_select = 0;
+	u8 pin_mode = 0;
 	u8 pattern = 0;
 	int pin = -1;
 	int err = 0;
@@ -280,18 +282,21 @@ static int mlx5e_extts_configure(struct ptp_clock_info *ptp,
 		pin = ptp_find_pin(tstamp->ptp, PTP_PF_EXTTS, rq->extts.index);
 		if (pin < 0)
 			return -EBUSY;
+		pin_mode = MLX5E_PIN_MODE_IN;
+		pattern = !!(rq->extts.flags & PTP_FALLING_EDGE);
+		field_select = MLX5E_MTPPS_FS_PIN_MODE |
+			       MLX5E_MTPPS_FS_PATTERN |
+			       MLX5E_MTPPS_FS_ENABLE;
+	} else {
+		pin = rq->extts.index;
+		field_select = MLX5E_MTPPS_FS_ENABLE;
 	}
 
-	if (rq->extts.flags & PTP_FALLING_EDGE)
-		pattern = 1;
-
 	MLX5_SET(mtpps_reg, in, pin, pin);
-	MLX5_SET(mtpps_reg, in, pin_mode, MLX5E_PIN_MODE_IN);
+	MLX5_SET(mtpps_reg, in, pin_mode, pin_mode);
 	MLX5_SET(mtpps_reg, in, pattern, pattern);
 	MLX5_SET(mtpps_reg, in, enable, on);
-	MLX5_SET(mtpps_reg, in, field_select, MLX5E_MTPPS_FS_PIN_MODE |
-					      MLX5E_MTPPS_FS_PATTERN |
-					      MLX5E_MTPPS_FS_ENABLE);
+	MLX5_SET(mtpps_reg, in, field_select, field_select);
 
 	err = mlx5_set_mtpps(priv->mdev, in, sizeof(in));
 	if (err)
@@ -314,6 +319,9 @@ static int mlx5e_perout_configure(struct ptp_clock_info *ptp,
 	u64 cycles_now, cycles_delta;
 	struct timespec64 ts;
 	unsigned long flags;
+	u32 field_select = 0;
+	u8 pin_mode = 0;
+	u8 pattern = 0;
 	int pin = -1;
 	s64 ns;
 
@@ -328,34 +336,43 @@ static int mlx5e_perout_configure(struct ptp_clock_info *ptp,
 				   rq->perout.index);
 		if (pin < 0)
 			return -EBUSY;
-	}
 
-	ts.tv_sec = rq->perout.period.sec;
-	ts.tv_nsec = rq->perout.period.nsec;
-	ns = timespec64_to_ns(&ts);
-	if (on)
+		pin_mode = MLX5E_PIN_MODE_OUT;
+		pattern = MLX5E_OUT_PATTERN_PERIODIC;
+		ts.tv_sec = rq->perout.period.sec;
+		ts.tv_nsec = rq->perout.period.nsec;
+		ns = timespec64_to_ns(&ts);
+
 		if ((ns >> 1) != 500000000LL)
 			return -EINVAL;
-	ts.tv_sec = rq->perout.start.sec;
-	ts.tv_nsec = rq->perout.start.nsec;
-	ns = timespec64_to_ns(&ts);
-	cycles_now = mlx5_read_internal_timer(tstamp->mdev);
-	write_lock_irqsave(&tstamp->lock, flags);
-	nsec_now = timecounter_cyc2time(&tstamp->clock, cycles_now);
-	nsec_delta = ns - nsec_now;
-	cycles_delta = div64_u64(nsec_delta << tstamp->cycles.shift,
-				 tstamp->cycles.mult);
-	write_unlock_irqrestore(&tstamp->lock, flags);
-	time_stamp = cycles_now + cycles_delta;
+
+		ts.tv_sec = rq->perout.start.sec;
+		ts.tv_nsec = rq->perout.start.nsec;
+		ns = timespec64_to_ns(&ts);
+		cycles_now = mlx5_read_internal_timer(tstamp->mdev);
+		write_lock_irqsave(&tstamp->lock, flags);
+		nsec_now = timecounter_cyc2time(&tstamp->clock, cycles_now);
+		nsec_delta = ns - nsec_now;
+		cycles_delta = div64_u64(nsec_delta << tstamp->cycles.shift,
+					 tstamp->cycles.mult);
+		write_unlock_irqrestore(&tstamp->lock, flags);
+		time_stamp = cycles_now + cycles_delta;
+		field_select = MLX5E_MTPPS_FS_PIN_MODE |
+			       MLX5E_MTPPS_FS_PATTERN |
+			       MLX5E_MTPPS_FS_ENABLE |
+			       MLX5E_MTPPS_FS_TIME_STAMP;
+	} else {
+		pin = rq->perout.index;
+		field_select = MLX5E_MTPPS_FS_ENABLE;
+	}
+
 	MLX5_SET(mtpps_reg, in, pin, pin);
-	MLX5_SET(mtpps_reg, in, pin_mode, MLX5E_PIN_MODE_OUT);
-	MLX5_SET(mtpps_reg, in, pattern, MLX5E_OUT_PATTERN_PERIODIC);
+	MLX5_SET(mtpps_reg, in, pin_mode, pin_mode);
+	MLX5_SET(mtpps_reg, in, pattern, pattern);
 	MLX5_SET(mtpps_reg, in, enable, on);
 	MLX5_SET64(mtpps_reg, in, time_stamp, time_stamp);
-	MLX5_SET(mtpps_reg, in, field_select, MLX5E_MTPPS_FS_PIN_MODE |
-					      MLX5E_MTPPS_FS_PATTERN |
-					      MLX5E_MTPPS_FS_ENABLE |
-					      MLX5E_MTPPS_FS_TIME_STAMP);
+	MLX5_SET(mtpps_reg, in, field_select, field_select);
+
 	return mlx5_set_mtpps(priv->mdev, in, sizeof(in));
 }
 
-- 
2.13.4


From e64e97f32cf84e1f9edd1068f288fed65a59dd57 Mon Sep 17 00:00:00 2001
From: Eugenia Emantayev <eugenia@mellanox.com>
Date: Sun, 28 May 2017 14:06:01 +0300
Subject: [PATCH 37/45] net/mlx5e: Change 1PPS out scheme

[ Upstream commit 4272f9b88db9223216cdf87314f570f6d81295b4 ]

In order to fix the drift in 1PPS out need to adjust the next pulse.
On each 1PPS out falling edge driver gets the event, then the event
handler adjusts the next pulse starting time.

Fixes: ee7f12205abc ('net/mlx5e: Implement 1PPS support')
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |   9 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_clock.c | 116 ++++++++++++++-------
 2 files changed, 87 insertions(+), 38 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 944fc1742464..08c303c0be10 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -261,6 +261,13 @@ struct mlx5e_dcbx {
 };
 #endif
 
+#define MAX_PIN_NUM	8
+struct mlx5e_pps {
+	u8                         pin_caps[MAX_PIN_NUM];
+	struct work_struct         out_work;
+	u64                        start[MAX_PIN_NUM];
+};
+
 struct mlx5e_tstamp {
 	rwlock_t                   lock;
 	struct cyclecounter        cycles;
@@ -272,7 +279,7 @@ struct mlx5e_tstamp {
 	struct mlx5_core_dev      *mdev;
 	struct ptp_clock          *ptp;
 	struct ptp_clock_info      ptp_info;
-	u8                        *pps_pin_caps;
+	struct mlx5e_pps           pps_info;
 };
 
 enum {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
index 41397de86f89..da9fa20f93d5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
@@ -82,6 +82,33 @@ static u64 mlx5e_read_internal_timer(const struct cyclecounter *cc)
 	return mlx5_read_internal_timer(tstamp->mdev) & cc->mask;
 }
 
+static void mlx5e_pps_out(struct work_struct *work)
+{
+	struct mlx5e_pps *pps_info = container_of(work, struct mlx5e_pps,
+						  out_work);
+	struct mlx5e_tstamp *tstamp = container_of(pps_info, struct mlx5e_tstamp,
+						   pps_info);
+	u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
+	unsigned long flags;
+	int i;
+
+	for (i = 0; i < tstamp->ptp_info.n_pins; i++) {
+		u64 tstart;
+
+		write_lock_irqsave(&tstamp->lock, flags);
+		tstart = tstamp->pps_info.start[i];
+		tstamp->pps_info.start[i] = 0;
+		write_unlock_irqrestore(&tstamp->lock, flags);
+		if (!tstart)
+			continue;
+
+		MLX5_SET(mtpps_reg, in, pin, i);
+		MLX5_SET64(mtpps_reg, in, time_stamp, tstart);
+		MLX5_SET(mtpps_reg, in, field_select, MLX5E_MTPPS_FS_TIME_STAMP);
+		mlx5_set_mtpps(tstamp->mdev, in, sizeof(in));
+	}
+}
+
 static void mlx5e_timestamp_overflow(struct work_struct *work)
 {
 	struct delayed_work *dwork = to_delayed_work(work);
@@ -223,21 +250,6 @@ static int mlx5e_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta)
 	int neg_adj = 0;
 	struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp,
 						  ptp_info);
-	struct mlx5e_priv *priv =
-		container_of(tstamp, struct mlx5e_priv, tstamp);
-
-	if (MLX5_CAP_GEN(priv->mdev, pps_modify)) {
-		u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
-
-		/* For future use need to add a loop for finding all 1PPS out pins */
-		MLX5_SET(mtpps_reg, in, pin_mode, MLX5E_PIN_MODE_OUT);
-		MLX5_SET(mtpps_reg, in, enhanced_out_periodic_adjustment, delta);
-		MLX5_SET(mtpps_reg, in, field_select,
-			 MLX5E_MTPPS_FS_PIN_MODE |
-			 MLX5E_MTPPS_FS_ENH_OUT_PER_ADJ);
-
-		mlx5_set_mtpps(priv->mdev, in, sizeof(in));
-	}
 
 	if (delta < 0) {
 		neg_adj = 1;
@@ -315,7 +327,7 @@ static int mlx5e_perout_configure(struct ptp_clock_info *ptp,
 	struct mlx5e_priv *priv =
 		container_of(tstamp, struct mlx5e_priv, tstamp);
 	u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
-	u64 nsec_now, nsec_delta, time_stamp;
+	u64 nsec_now, nsec_delta, time_stamp = 0;
 	u64 cycles_now, cycles_delta;
 	struct timespec64 ts;
 	unsigned long flags;
@@ -323,6 +335,7 @@ static int mlx5e_perout_configure(struct ptp_clock_info *ptp,
 	u8 pin_mode = 0;
 	u8 pattern = 0;
 	int pin = -1;
+	int err = 0;
 	s64 ns;
 
 	if (!MLX5_PPS_CAP(priv->mdev))
@@ -373,7 +386,12 @@ static int mlx5e_perout_configure(struct ptp_clock_info *ptp,
 	MLX5_SET64(mtpps_reg, in, time_stamp, time_stamp);
 	MLX5_SET(mtpps_reg, in, field_select, field_select);
 
-	return mlx5_set_mtpps(priv->mdev, in, sizeof(in));
+	err = mlx5_set_mtpps(priv->mdev, in, sizeof(in));
+	if (err)
+		return err;
+
+	return mlx5_set_mtppse(priv->mdev, pin, 0,
+			       MLX5E_EVENT_MODE_REPETETIVE & on);
 }
 
 static int mlx5e_ptp_enable(struct ptp_clock_info *ptp,
@@ -457,22 +475,50 @@ static void mlx5e_get_pps_caps(struct mlx5e_priv *priv,
 	tstamp->ptp_info.n_per_out = MLX5_GET(mtpps_reg, out,
 					      cap_max_num_of_pps_out_pins);
 
-	tstamp->pps_pin_caps[0] = MLX5_GET(mtpps_reg, out, cap_pin_0_mode);
-	tstamp->pps_pin_caps[1] = MLX5_GET(mtpps_reg, out, cap_pin_1_mode);
-	tstamp->pps_pin_caps[2] = MLX5_GET(mtpps_reg, out, cap_pin_2_mode);
-	tstamp->pps_pin_caps[3] = MLX5_GET(mtpps_reg, out, cap_pin_3_mode);
-	tstamp->pps_pin_caps[4] = MLX5_GET(mtpps_reg, out, cap_pin_4_mode);
-	tstamp->pps_pin_caps[5] = MLX5_GET(mtpps_reg, out, cap_pin_5_mode);
-	tstamp->pps_pin_caps[6] = MLX5_GET(mtpps_reg, out, cap_pin_6_mode);
-	tstamp->pps_pin_caps[7] = MLX5_GET(mtpps_reg, out, cap_pin_7_mode);
+	tstamp->pps_info.pin_caps[0] = MLX5_GET(mtpps_reg, out, cap_pin_0_mode);
+	tstamp->pps_info.pin_caps[1] = MLX5_GET(mtpps_reg, out, cap_pin_1_mode);
+	tstamp->pps_info.pin_caps[2] = MLX5_GET(mtpps_reg, out, cap_pin_2_mode);
+	tstamp->pps_info.pin_caps[3] = MLX5_GET(mtpps_reg, out, cap_pin_3_mode);
+	tstamp->pps_info.pin_caps[4] = MLX5_GET(mtpps_reg, out, cap_pin_4_mode);
+	tstamp->pps_info.pin_caps[5] = MLX5_GET(mtpps_reg, out, cap_pin_5_mode);
+	tstamp->pps_info.pin_caps[6] = MLX5_GET(mtpps_reg, out, cap_pin_6_mode);
+	tstamp->pps_info.pin_caps[7] = MLX5_GET(mtpps_reg, out, cap_pin_7_mode);
 }
 
 void mlx5e_pps_event_handler(struct mlx5e_priv *priv,
 			     struct ptp_clock_event *event)
 {
+	struct net_device *netdev = priv->netdev;
 	struct mlx5e_tstamp *tstamp = &priv->tstamp;
+	struct timespec64 ts;
+	u64 nsec_now, nsec_delta;
+	u64 cycles_now, cycles_delta;
+	int pin = event->index;
+	s64 ns;
+	unsigned long flags;
 
-	ptp_clock_event(tstamp->ptp, event);
+	switch (tstamp->ptp_info.pin_config[pin].func) {
+	case PTP_PF_EXTTS:
+		ptp_clock_event(tstamp->ptp, event);
+		break;
+	case PTP_PF_PEROUT:
+		mlx5e_ptp_gettime(&tstamp->ptp_info, &ts);
+		cycles_now = mlx5_read_internal_timer(tstamp->mdev);
+		ts.tv_sec += 1;
+		ts.tv_nsec = 0;
+		ns = timespec64_to_ns(&ts);
+		write_lock_irqsave(&tstamp->lock, flags);
+		nsec_now = timecounter_cyc2time(&tstamp->clock, cycles_now);
+		nsec_delta = ns - nsec_now;
+		cycles_delta = div64_u64(nsec_delta << tstamp->cycles.shift,
+					 tstamp->cycles.mult);
+		tstamp->pps_info.start[pin] = cycles_now + cycles_delta;
+		queue_work(priv->wq, &tstamp->pps_info.out_work);
+		write_unlock_irqrestore(&tstamp->lock, flags);
+		break;
+	default:
+		netdev_err(netdev, "%s: Unhandled event\n", __func__);
+	}
 }
 
 void mlx5e_timestamp_init(struct mlx5e_priv *priv)
@@ -508,6 +554,7 @@ void mlx5e_timestamp_init(struct mlx5e_priv *priv)
 	do_div(ns, NSEC_PER_SEC / 2 / HZ);
 	tstamp->overflow_period = ns;
 
+	INIT_WORK(&tstamp->pps_info.out_work, mlx5e_pps_out);
 	INIT_DELAYED_WORK(&tstamp->overflow_work, mlx5e_timestamp_overflow);
 	if (tstamp->overflow_period)
 		schedule_delayed_work(&tstamp->overflow_work, 0);
@@ -519,16 +566,10 @@ void mlx5e_timestamp_init(struct mlx5e_priv *priv)
 	snprintf(tstamp->ptp_info.name, 16, "mlx5 ptp");
 
 	/* Initialize 1PPS data structures */
-#define MAX_PIN_NUM	8
-	tstamp->pps_pin_caps = kzalloc(sizeof(u8) * MAX_PIN_NUM, GFP_KERNEL);
-	if (tstamp->pps_pin_caps) {
-		if (MLX5_PPS_CAP(priv->mdev))
-			mlx5e_get_pps_caps(priv, tstamp);
-		if (tstamp->ptp_info.n_pins)
-			mlx5e_init_pin_config(tstamp);
-	} else {
-		mlx5_core_warn(priv->mdev, "1PPS initialization failed\n");
-	}
+	if (MLX5_PPS_CAP(priv->mdev))
+		mlx5e_get_pps_caps(priv, tstamp);
+	if (tstamp->ptp_info.n_pins)
+		mlx5e_init_pin_config(tstamp);
 
 	tstamp->ptp = ptp_clock_register(&tstamp->ptp_info,
 					 &priv->mdev->pdev->dev);
@@ -551,7 +592,8 @@ void mlx5e_timestamp_cleanup(struct mlx5e_priv *priv)
 		priv->tstamp.ptp = NULL;
 	}
 
-	kfree(tstamp->pps_pin_caps);
+	cancel_work_sync(&tstamp->pps_info.out_work);
+
 	kfree(tstamp->ptp_info.pin_config);
 
 	cancel_delayed_work_sync(&tstamp->overflow_work);
-- 
2.13.4


From 7aef96bc1591184628cec26222f400db2e042088 Mon Sep 17 00:00:00 2001
From: Eugenia Emantayev <eugenia@mellanox.com>
Date: Sun, 28 May 2017 14:27:02 +0300
Subject: [PATCH 38/45] net/mlx5e: Add missing support for PTP_CLK_REQ_PPS
 request

[ Upstream commit cf5033089b078303b102b65e3ccbbfa3ce0f4367 ]

Add the missing option to enable the PTP_CLK_PPS function.
In this case pin should be configured as 1PPS IN first and
then it will be connected to PPS mechanism.
Events will be reported as PTP_CLOCK_PPSUSR events to relevant sysfs.

Fixes: ee7f12205abc ('net/mlx5e: Implement 1PPS support')
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |  1 +
 drivers/net/ethernet/mellanox/mlx5/core/en_clock.c | 20 ++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  |  1 -
 3 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 08c303c0be10..3b39dbd97e57 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -266,6 +266,7 @@ struct mlx5e_pps {
 	u8                         pin_caps[MAX_PIN_NUM];
 	struct work_struct         out_work;
 	u64                        start[MAX_PIN_NUM];
+	u8                         enabled;
 };
 
 struct mlx5e_tstamp {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
index da9fa20f93d5..a972125708c8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
@@ -394,6 +394,17 @@ static int mlx5e_perout_configure(struct ptp_clock_info *ptp,
 			       MLX5E_EVENT_MODE_REPETETIVE & on);
 }
 
+static int mlx5e_pps_configure(struct ptp_clock_info *ptp,
+			       struct ptp_clock_request *rq,
+			       int on)
+{
+	struct mlx5e_tstamp *tstamp =
+		container_of(ptp, struct mlx5e_tstamp, ptp_info);
+
+	tstamp->pps_info.enabled = !!on;
+	return 0;
+}
+
 static int mlx5e_ptp_enable(struct ptp_clock_info *ptp,
 			    struct ptp_clock_request *rq,
 			    int on)
@@ -403,6 +414,8 @@ static int mlx5e_ptp_enable(struct ptp_clock_info *ptp,
 		return mlx5e_extts_configure(ptp, rq, on);
 	case PTP_CLK_REQ_PEROUT:
 		return mlx5e_perout_configure(ptp, rq, on);
+	case PTP_CLK_REQ_PPS:
+		return mlx5e_pps_configure(ptp, rq, on);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -448,6 +461,7 @@ static int mlx5e_init_pin_config(struct mlx5e_tstamp *tstamp)
 		return -ENOMEM;
 	tstamp->ptp_info.enable = mlx5e_ptp_enable;
 	tstamp->ptp_info.verify = mlx5e_ptp_verify;
+	tstamp->ptp_info.pps = 1;
 
 	for (i = 0; i < tstamp->ptp_info.n_pins; i++) {
 		snprintf(tstamp->ptp_info.pin_config[i].name,
@@ -499,6 +513,12 @@ void mlx5e_pps_event_handler(struct mlx5e_priv *priv,
 
 	switch (tstamp->ptp_info.pin_config[pin].func) {
 	case PTP_PF_EXTTS:
+		if (tstamp->pps_info.enabled) {
+			event->type = PTP_CLOCK_PPSUSR;
+			event->pps_times.ts_real = ns_to_timespec64(event->timestamp);
+		} else {
+			event->type = PTP_CLOCK_EXTTS;
+		}
 		ptp_clock_event(tstamp->ptp, event);
 		break;
 	case PTP_PF_PEROUT:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 7819fe9ede22..072aa8a13a0a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -365,7 +365,6 @@ static void mlx5e_async_event(struct mlx5_core_dev *mdev, void *vpriv,
 		break;
 	case MLX5_DEV_EVENT_PPS:
 		eqe = (struct mlx5_eqe *)param;
-		ptp_event.type = PTP_CLOCK_EXTTS;
 		ptp_event.index = eqe->data.pps.pin;
 		ptp_event.timestamp =
 			timecounter_cyc2time(&priv->tstamp.clock,
-- 
2.13.4


From 499c81e13207bf0041c9062b9a83335287ec28e0 Mon Sep 17 00:00:00 2001
From: Eugenia Emantayev <eugenia@mellanox.com>
Date: Wed, 12 Jul 2017 17:27:18 +0300
Subject: [PATCH 39/45] net/mlx5e: Fix wrong delay calculation for overflow
 check scheduling

[ Upstream commit d439c84509a510e864fdc6166c760482cd03fc57 ]

The overflow_period is calculated in seconds. In order to use it
for delayed work scheduling translation to jiffies is needed.

Fixes: ef9814deafd0 ('net/mlx5e: Add HW timestamping (TS) support')
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_clock.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
index a972125708c8..5d9c0f1d5dd1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
@@ -119,7 +119,8 @@ static void mlx5e_timestamp_overflow(struct work_struct *work)
 	write_lock_irqsave(&tstamp->lock, flags);
 	timecounter_read(&tstamp->clock);
 	write_unlock_irqrestore(&tstamp->lock, flags);
-	schedule_delayed_work(&tstamp->overflow_work, tstamp->overflow_period);
+	schedule_delayed_work(&tstamp->overflow_work,
+			      msecs_to_jiffies(tstamp->overflow_period * 1000));
 }
 
 int mlx5e_hwstamp_set(struct net_device *dev, struct ifreq *ifr)
-- 
2.13.4


From c4448667c2ba6e2b5592df1f958e69adfd5c736e Mon Sep 17 00:00:00 2001
From: Eugenia Emantayev <eugenia@mellanox.com>
Date: Wed, 12 Jul 2017 17:44:07 +0300
Subject: [PATCH 40/45] net/mlx5e: Schedule overflow check work to mlx5e
 workqueue

[ Upstream commit f08c39ed0bfb503c7b3e013cd40d036ce6a0941a ]

This is done in order to ensure that work will not run after the cleanup.

Fixes: ef9814deafd0 ('net/mlx5e: Add HW timestamping (TS) support')
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_clock.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
index 5d9c0f1d5dd1..80c500f87ab6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
@@ -114,13 +114,14 @@ static void mlx5e_timestamp_overflow(struct work_struct *work)
 	struct delayed_work *dwork = to_delayed_work(work);
 	struct mlx5e_tstamp *tstamp = container_of(dwork, struct mlx5e_tstamp,
 						   overflow_work);
+	struct mlx5e_priv *priv = container_of(tstamp, struct mlx5e_priv, tstamp);
 	unsigned long flags;
 
 	write_lock_irqsave(&tstamp->lock, flags);
 	timecounter_read(&tstamp->clock);
 	write_unlock_irqrestore(&tstamp->lock, flags);
-	schedule_delayed_work(&tstamp->overflow_work,
-			      msecs_to_jiffies(tstamp->overflow_period * 1000));
+	queue_delayed_work(priv->wq, &tstamp->overflow_work,
+			   msecs_to_jiffies(tstamp->overflow_period * 1000));
 }
 
 int mlx5e_hwstamp_set(struct net_device *dev, struct ifreq *ifr)
@@ -578,7 +579,7 @@ void mlx5e_timestamp_init(struct mlx5e_priv *priv)
 	INIT_WORK(&tstamp->pps_info.out_work, mlx5e_pps_out);
 	INIT_DELAYED_WORK(&tstamp->overflow_work, mlx5e_timestamp_overflow);
 	if (tstamp->overflow_period)
-		schedule_delayed_work(&tstamp->overflow_work, 0);
+		queue_delayed_work(priv->wq, &tstamp->overflow_work, 0);
 	else
 		mlx5_core_warn(priv->mdev, "invalid overflow period, overflow_work is not scheduled\n");
 
@@ -614,8 +615,6 @@ void mlx5e_timestamp_cleanup(struct mlx5e_priv *priv)
 	}
 
 	cancel_work_sync(&tstamp->pps_info.out_work);
-
-	kfree(tstamp->ptp_info.pin_config);
-
 	cancel_delayed_work_sync(&tstamp->overflow_work);
+	kfree(tstamp->ptp_info.pin_config);
 }
-- 
2.13.4


From 706f5a40ceafccf74b621eac9b0196fb688f0ae7 Mon Sep 17 00:00:00 2001
From: Paul Blakey <paulb@mellanox.com>
Date: Thu, 6 Jul 2017 16:40:34 +0300
Subject: [PATCH 41/45] net/mlx5: Fix mlx5_add_flow_rules call with correct num
 of dests

[ Upstream commit bcec601f30fb41e9233674942fa4040a6e63657a ]

When adding ethtool steering rule with action DISCARD we wrongly
pass a NULL dest with dest_num 1 to mlx5_add_flow_rules().
What this error seems to have caused is sending VPORT 0
(MLX5_FLOW_DESTINATION_TYPE_VPORT) as the fte dest instead of no dests.
We have fte action correctly set to DROP so it might been ignored
anyways.

To reproduce use:
 # sudo ethtool --config-nfc <dev> flow-type ether \
   dst aa:bb:cc:dd:ee:ff action -1

Fixes: 74491de93712 ("net/mlx5: Add multi dest support")
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index 969ddb3aaf6e..986387de13ee 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -320,7 +320,7 @@ add_ethtool_flow_rule(struct mlx5e_priv *priv,
 
 	spec->match_criteria_enable = (!outer_header_zero(spec->match_criteria));
 	flow_act.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG;
-	rule = mlx5_add_flow_rules(ft, spec, &flow_act, dst, 1);
+	rule = mlx5_add_flow_rules(ft, spec, &flow_act, dst, dst ? 1 : 0);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
 		netdev_err(priv->netdev, "%s: failed to add ethtool steering rule: %d\n",
-- 
2.13.4


From f373e07dd6224ace26df9e6ef309fb239a4f548d Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 27 Jul 2017 14:45:09 +0200
Subject: [PATCH 42/45] udp6: fix socket leak on early demux

[ Upstream commit c9f2c1ae123a751d4e4f949144500219354d5ee1 ]

When an early demuxed packet reaches __udp6_lib_lookup_skb(), the
sk reference is retrieved and used, but the relevant reference
count is leaked and the socket destructor is never called.
Beyond leaking the sk memory, if there are pending UDP packets
in the receive queue, even the related accounted memory is leaked.

In the long run, this will cause persistent forward allocation errors
and no UDP skbs (both ipv4 and ipv6) will be able to reach the
user-space.

Fix this by explicitly accessing the early demux reference before
the lookup, and properly decreasing the socket reference count
after usage.

Also drop the skb_steal_sock() in __udp6_lib_lookup_skb(), and
the now obsoleted comment about "socket cache".

The newly added code is derived from the current ipv4 code for the
similar path.

v1 -> v2:
  fixed the __udp6_lib_rcv() return code for resubmission,
  as suggested by Eric

Reported-by: Sam Edwards <CFSworks@gmail.com>
Reported-by: Marc Haber <mh+netdev@zugschlus.de>
Fixes: 5425077d73e0 ("net: ipv6: Add early demux handler for UDP unicast")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/udp.h |  1 +
 net/ipv4/udp.c    |  3 ++-
 net/ipv6/udp.c    | 27 ++++++++++++++++++---------
 3 files changed, 21 insertions(+), 10 deletions(-)

diff --git a/include/net/udp.h b/include/net/udp.h
index 3391dbd73959..1933442cf1a6 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -265,6 +265,7 @@ static inline struct sk_buff *skb_recv_udp(struct sock *sk, unsigned int flags,
 }
 
 void udp_v4_early_demux(struct sk_buff *skb);
+void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst);
 int udp_get_port(struct sock *sk, unsigned short snum,
 		 int (*saddr_cmp)(const struct sock *,
 				  const struct sock *));
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 1d6219bf2d6b..b9a84eba60b8 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1762,7 +1762,7 @@ static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 /* For TCP sockets, sk_rx_dst is protected by socket lock
  * For UDP, we use xchg() to guard against concurrent changes.
  */
-static void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
+void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
 {
 	struct dst_entry *old;
 
@@ -2120,6 +2120,7 @@ void udp_destroy_sock(struct sock *sk)
 			encap_destroy(sk);
 	}
 }
+EXPORT_SYMBOL(udp_sk_rx_dst_set);
 
 /*
  *	Socket option code for UDP
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 75703fda23e7..592270c310f4 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -291,11 +291,7 @@ static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb,
 					  struct udp_table *udptable)
 {
 	const struct ipv6hdr *iph = ipv6_hdr(skb);
-	struct sock *sk;
 
-	sk = skb_steal_sock(skb);
-	if (unlikely(sk))
-		return sk;
 	return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport,
 				 &iph->daddr, dport, inet6_iif(skb),
 				 udptable, skb);
@@ -798,6 +794,24 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	if (udp6_csum_init(skb, uh, proto))
 		goto csum_error;
 
+	/* Check if the socket is already available, e.g. due to early demux */
+	sk = skb_steal_sock(skb);
+	if (sk) {
+		struct dst_entry *dst = skb_dst(skb);
+		int ret;
+
+		if (unlikely(sk->sk_rx_dst != dst))
+			udp_sk_rx_dst_set(sk, dst);
+
+		ret = udpv6_queue_rcv_skb(sk, skb);
+		sock_put(sk);
+
+		/* a return value > 0 means to resubmit the input */
+		if (ret > 0)
+			return ret;
+		return 0;
+	}
+
 	/*
 	 *	Multicast receive code
 	 */
@@ -806,11 +820,6 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 				saddr, daddr, udptable, proto);
 
 	/* Unicast */
-
-	/*
-	 * check socket cache ... must talk to Alan about his plans
-	 * for sock caches... i'll skip this for now.
-	 */
 	sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
 	if (sk) {
 		int ret;
-- 
2.13.4


From 090f18a214d97f48a75eb584d113b8a516b1e505 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 28 Jul 2017 11:58:36 -0700
Subject: [PATCH 43/45] net: phy: Correctly process PHY_HALTED in
 phy_stop_machine()

[ Upstream commit 7ad813f208533cebfcc32d3d7474dc1677d1b09a ]

Marc reported that he was not getting the PHY library adjust_link()
callback function to run when calling phy_stop() + phy_disconnect()
which does not indeed happen because we set the state machine to
PHY_HALTED but we don't get to run it to process this state past that
point.

Fix this with a synchronous call to phy_state_machine() in order to have
the state machine actually act on PHY_HALTED, set the PHY device's link
down, turn the network device's carrier off and finally call the
adjust_link() function.

Reported-by: Marc Gonzalez <marc_gonzalez@sigmadesigns.com>
Fixes: a390d1f379cf ("phylib: convert state_queue work to delayed_work")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Marc Gonzalez <marc_gonzalez@sigmadesigns.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index eebb0e1c70ff..b30d9ceee8bc 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -749,6 +749,9 @@ void phy_stop_machine(struct phy_device *phydev)
 	if (phydev->state > PHY_UP && phydev->state != PHY_HALTED)
 		phydev->state = PHY_UP;
 	mutex_unlock(&phydev->lock);
+
+	/* Now we can run the state machine synchronously */
+	phy_state_machine(&phydev->state_queue.work);
 }
 
 /**
-- 
2.13.4


From a6acfd639d68fbe4f4f0f27ab9b3346e8e0f45d6 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Fri, 28 Jul 2017 23:27:44 +0300
Subject: [PATCH 44/45] ipv4: fib: Fix NULL pointer deref during
 fib_sync_down_dev()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 71ed7ee35ad2c5300f4b51634185a0193b4fb0fa ]

Michał reported a NULL pointer deref during fib_sync_down_dev() when
unregistering a netdevice. The problem is that we don't check for
'in_dev' being NULL, which can happen in very specific cases.

Usually routes are flushed upon NETDEV_DOWN sent in either the netdev or
the inetaddr notification chains. However, if an interface isn't
configured with any IP address, then it's possible for host routes to be
flushed following NETDEV_UNREGISTER, after NULLing dev->ip_ptr in
inetdev_destroy().

To reproduce:
$ ip link add type dummy
$ ip route add local 1.1.1.0/24 dev dummy0
$ ip link del dev dummy0

Fix this by checking for the presence of 'in_dev' before referencing it.

Fixes: 982acb97560c ("ipv4: fib: Notify about nexthop status changes")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Tested-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_semantics.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index ad9ad4aab5da..ce7bc2e5175a 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1372,7 +1372,7 @@ static int call_fib_nh_notifiers(struct fib_nh *fib_nh,
 		return call_fib_notifiers(dev_net(fib_nh->nh_dev), event_type,
 					  &info.info);
 	case FIB_EVENT_NH_DEL:
-		if ((IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
+		if ((in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
 		     fib_nh->nh_flags & RTNH_F_LINKDOWN) ||
 		    (fib_nh->nh_flags & RTNH_F_DEAD))
 			return call_fib_notifiers(dev_net(fib_nh->nh_dev),
-- 
2.13.4


From e8e6006f23e481e13298a67071bcaafd59af138f Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Mon, 31 Jul 2017 21:49:49 +0300
Subject: [PATCH 45/45] virtio_net: fix truesize for mergeable buffers

[ Upstream commit 1daa8790d0280d2c719658e39bd59fce65efa909 ]

Seth Forshee noticed a performance degradation with some workloads.
This turns out to be due to packet drops.  Euan Kemp noticed that this
is because we drop all packets where length exceeds the truesize, but
for some packets we add in extra memory without updating the truesize.
This in turn was kept around unchanged from ab7db91705e95 ("virtio-net:
auto-tune mergeable rx buffer size for improved performance").  That
commit had an internal reason not to account for the extra space: not
enough bits to do it.  No longer true so let's account for the allocated
length exactly.

Many thanks to Seth Forshee for the report and bisecting and Euan Kemp
for debugging the issue.

Fixes: 680557cf79f8 ("virtio_net: rework mergeable buffer handling")
Reported-by: Euan Kemp <euan.kemp@coreos.com>
Tested-by: Euan Kemp <euan.kemp@coreos.com>
Reported-by: Seth Forshee <seth.forshee@canonical.com>
Tested-by: Seth Forshee <seth.forshee@canonical.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 6633dd4bb649..acb754eb1ccb 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -889,21 +889,20 @@ static int add_recvbuf_mergeable(struct virtnet_info *vi,
 
 	buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset;
 	buf += headroom; /* advance address leaving hole at front of pkt */
-	ctx = (void *)(unsigned long)len;
 	get_page(alloc_frag->page);
 	alloc_frag->offset += len + headroom;
 	hole = alloc_frag->size - alloc_frag->offset;
 	if (hole < len + headroom) {
 		/* To avoid internal fragmentation, if there is very likely not
 		 * enough space for another buffer, add the remaining space to
-		 * the current buffer. This extra space is not included in
-		 * the truesize stored in ctx.
+		 * the current buffer.
 		 */
 		len += hole;
 		alloc_frag->offset += hole;
 	}
 
 	sg_init_one(rq->sg, buf, len);
+	ctx = (void *)(unsigned long)len;
 	err = virtqueue_add_inbuf_ctx(rq->vq, rq->sg, 1, buf, ctx, gfp);
 	if (err < 0)
 		put_page(virt_to_head_page(buf));
-- 
2.13.4

Re: [PATCHES] Networking

[Greg KH]

On Tue, Aug 08, 2017 at 04:21:26PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for 4.9.x
> and 4.12.x -stable, respectively.

All queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 106 bytes --]


Please queue up the following networking bug fixes for v4.9 and
v4.12 -stable, respectively.

Thank you!

[-- Attachment #2: net_49.mbox --]
[-- Type: Application/Octet-Stream, Size: 33331 bytes --]

From 262792e22f605ea884ad4695ae68b62bfb7707be Mon Sep 17 00:00:00 2001
From: Gao Feng <gfree.wind@vip.163.com>
Date: Mon, 17 Jul 2017 18:34:42 +0800
Subject: [PATCH 01/12] ppp: Fix false xmit recursion detect with two ppp
 devices

[ Upstream commit e5dadc65f9e0177eb649bcd9d333f1ebf871223e ]

The global percpu variable ppp_xmit_recursion is used to detect the ppp
xmit recursion to avoid the deadlock, which is caused by one CPU tries to
lock the xmit lock twice. But it would report false recursion when one CPU
wants to send the skb from two different PPP devices, like one L2TP on the
PPPoE. It is a normal case actually.

Now use one percpu member of struct ppp instead of the gloable variable to
detect the xmit recursion of one ppp device.

Fixes: 55454a565836 ("ppp: avoid dealock on recursive xmit")
Signed-off-by: Gao Feng <gfree.wind@vip.163.com>
Signed-off-by: Liu Jianying <jianying.liu@ikuai8.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/ppp_generic.c | 30 +++++++++++++++++++++---------
 1 file changed, 21 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 5489c0ec1d9a..667f197ab66c 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -119,6 +119,7 @@ struct ppp {
 	int		n_channels;	/* how many channels are attached 54 */
 	spinlock_t	rlock;		/* lock for receive side 58 */
 	spinlock_t	wlock;		/* lock for transmit side 5c */
+	int		*xmit_recursion __percpu; /* xmit recursion detect */
 	int		mru;		/* max receive unit 60 */
 	unsigned int	flags;		/* control bits 64 */
 	unsigned int	xstate;		/* transmit state bits 68 */
@@ -1024,6 +1025,7 @@ static int ppp_dev_configure(struct net *src_net, struct net_device *dev,
 	struct ppp *ppp = netdev_priv(dev);
 	int indx;
 	int err;
+	int cpu;
 
 	ppp->dev = dev;
 	ppp->ppp_net = src_net;
@@ -1038,6 +1040,15 @@ static int ppp_dev_configure(struct net *src_net, struct net_device *dev,
 	INIT_LIST_HEAD(&ppp->channels);
 	spin_lock_init(&ppp->rlock);
 	spin_lock_init(&ppp->wlock);
+
+	ppp->xmit_recursion = alloc_percpu(int);
+	if (!ppp->xmit_recursion) {
+		err = -ENOMEM;
+		goto err1;
+	}
+	for_each_possible_cpu(cpu)
+		(*per_cpu_ptr(ppp->xmit_recursion, cpu)) = 0;
+
 #ifdef CONFIG_PPP_MULTILINK
 	ppp->minseq = -1;
 	skb_queue_head_init(&ppp->mrq);
@@ -1049,11 +1060,15 @@ static int ppp_dev_configure(struct net *src_net, struct net_device *dev,
 
 	err = ppp_unit_register(ppp, conf->unit, conf->ifname_is_set);
 	if (err < 0)
-		return err;
+		goto err2;
 
 	conf->file->private_data = &ppp->file;
 
 	return 0;
+err2:
+	free_percpu(ppp->xmit_recursion);
+err1:
+	return err;
 }
 
 static const struct nla_policy ppp_nl_policy[IFLA_PPP_MAX + 1] = {
@@ -1399,18 +1414,16 @@ static void __ppp_xmit_process(struct ppp *ppp)
 	ppp_xmit_unlock(ppp);
 }
 
-static DEFINE_PER_CPU(int, ppp_xmit_recursion);
-
 static void ppp_xmit_process(struct ppp *ppp)
 {
 	local_bh_disable();
 
-	if (unlikely(__this_cpu_read(ppp_xmit_recursion)))
+	if (unlikely(*this_cpu_ptr(ppp->xmit_recursion)))
 		goto err;
 
-	__this_cpu_inc(ppp_xmit_recursion);
+	(*this_cpu_ptr(ppp->xmit_recursion))++;
 	__ppp_xmit_process(ppp);
-	__this_cpu_dec(ppp_xmit_recursion);
+	(*this_cpu_ptr(ppp->xmit_recursion))--;
 
 	local_bh_enable();
 
@@ -1904,7 +1917,7 @@ static void __ppp_channel_push(struct channel *pch)
 		read_lock_bh(&pch->upl);
 		ppp = pch->ppp;
 		if (ppp)
-			__ppp_xmit_process(ppp);
+			ppp_xmit_process(ppp);
 		read_unlock_bh(&pch->upl);
 	}
 }
@@ -1913,9 +1926,7 @@ static void ppp_channel_push(struct channel *pch)
 {
 	local_bh_disable();
 
-	__this_cpu_inc(ppp_xmit_recursion);
 	__ppp_channel_push(pch);
-	__this_cpu_dec(ppp_xmit_recursion);
 
 	local_bh_enable();
 }
@@ -3056,6 +3067,7 @@ static void ppp_destroy_interface(struct ppp *ppp)
 #endif /* CONFIG_PPP_FILTER */
 
 	kfree_skb(ppp->xmit_pending);
+	free_percpu(ppp->xmit_recursion);
 
 	free_netdev(ppp->dev);
 }
-- 
2.13.4


From 421ea5c71451c04d9cb72e72b70382df50a4ac9e Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Tue, 8 Aug 2017 11:43:24 +0200
Subject: [PATCH 02/12] ppp: fix xmit recursion detection on ppp channels

[ Upstream commit 0a0e1a85c83775a648041be2b15de6d0a2f2b8eb ]

Commit e5dadc65f9e0 ("ppp: Fix false xmit recursion detect with two ppp
devices") dropped the xmit_recursion counter incrementation in
ppp_channel_push() and relied on ppp_xmit_process() for this task.
But __ppp_channel_push() can also send packets directly (using the
.start_xmit() channel callback), in which case the xmit_recursion
counter isn't incremented anymore. If such packets get routed back to
the parent ppp unit, ppp_xmit_process() won't notice the recursion and
will call ppp_channel_push() on the same channel, effectively creating
the deadlock situation that the xmit_recursion mechanism was supposed
to prevent.

This patch re-introduces the xmit_recursion counter incrementation in
ppp_channel_push(). Since the xmit_recursion variable is now part of
the parent ppp unit, incrementation is skipped if the channel doesn't
have any. This is fine because only packets routed through the parent
unit may enter the channel recursively.

Finally, we have to ensure that pch->ppp is not going to be modified
while executing ppp_channel_push(). Instead of taking this lock only
while calling ppp_xmit_process(), we now have to hold it for the full
ppp_channel_push() execution. This respects the ppp locks ordering
which requires locking ->upl before ->downl.

Fixes: e5dadc65f9e0 ("ppp: Fix false xmit recursion detect with two ppp devices")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/ppp_generic.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 667f197ab66c..96fa0e61d3af 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -1914,21 +1914,23 @@ static void __ppp_channel_push(struct channel *pch)
 	spin_unlock_bh(&pch->downl);
 	/* see if there is anything from the attached unit to be sent */
 	if (skb_queue_empty(&pch->file.xq)) {
-		read_lock_bh(&pch->upl);
 		ppp = pch->ppp;
 		if (ppp)
-			ppp_xmit_process(ppp);
-		read_unlock_bh(&pch->upl);
+			__ppp_xmit_process(ppp);
 	}
 }
 
 static void ppp_channel_push(struct channel *pch)
 {
-	local_bh_disable();
-
-	__ppp_channel_push(pch);
-
-	local_bh_enable();
+	read_lock_bh(&pch->upl);
+	if (pch->ppp) {
+		(*this_cpu_ptr(pch->ppp->xmit_recursion))++;
+		__ppp_channel_push(pch);
+		(*this_cpu_ptr(pch->ppp->xmit_recursion))--;
+	} else {
+		__ppp_channel_push(pch);
+	}
+	read_unlock_bh(&pch->upl);
 }
 
 /*
-- 
2.13.4


From af047b1eec861b21fb501a84b5bc71ee33c2d8c2 Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Tue, 1 Aug 2017 13:22:32 -0700
Subject: [PATCH 03/12] tcp: avoid setting cwnd to invalid ssthresh after cwnd
 reduction states

[ Upstream commit ed254971edea92c3ac5c67c6a05247a92aa6075e ]

If the sender switches the congestion control during ECN-triggered
cwnd-reduction state (CA_CWR), upon exiting recovery cwnd is set to
the ssthresh value calculated by the previous congestion control. If
the previous congestion control is BBR that always keep ssthresh
to TCP_INIFINITE_SSTHRESH, cwnd ends up being infinite. The safe
step is to avoid assigning invalid ssthresh value when recovery ends.

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 01336aa5f973..32c540145c17 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2560,8 +2560,8 @@ static inline void tcp_end_cwnd_reduction(struct sock *sk)
 		return;
 
 	/* Reset cwnd to ssthresh in CWR or Recovery (unless it's undone) */
-	if (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR ||
-	    (tp->undo_marker && tp->snd_ssthresh < TCP_INFINITE_SSTHRESH)) {
+	if (tp->snd_ssthresh < TCP_INFINITE_SSTHRESH &&
+	    (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR || tp->undo_marker)) {
 		tp->snd_cwnd = tp->snd_ssthresh;
 		tp->snd_cwnd_stamp = tcp_time_stamp;
 	}
-- 
2.13.4


From a264fcbd330fd852cabbf7569bd4699ffec3aa61 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 2 Aug 2017 23:10:46 -0700
Subject: [PATCH 04/12] net: fix keepalive code vs TCP_FASTOPEN_CONNECT

[ Upstream commit 2dda640040876cd8ae646408b69eea40c24f9ae9 ]

syzkaller was able to trigger a divide by 0 in TCP stack [1]

Issue here is that keepalive timer needs to be updated to not attempt
to send a probe if the connection setup was deferred using
TCP_FASTOPEN_CONNECT socket option added in linux-4.11

[1]
 divide error: 0000 [#1] SMP
 CPU: 18 PID: 0 Comm: swapper/18 Not tainted
 task: ffff986f62f4b040 ti: ffff986f62fa2000 task.ti: ffff986f62fa2000
 RIP: 0010:[<ffffffff8409cc0d>]  [<ffffffff8409cc0d>] __tcp_select_window+0x8d/0x160
 Call Trace:
  <IRQ>
  [<ffffffff8409d951>] tcp_transmit_skb+0x11/0x20
  [<ffffffff8409da21>] tcp_xmit_probe_skb+0xc1/0xe0
  [<ffffffff840a0ee8>] tcp_write_wakeup+0x68/0x160
  [<ffffffff840a151b>] tcp_keepalive_timer+0x17b/0x230
  [<ffffffff83b3f799>] call_timer_fn+0x39/0xf0
  [<ffffffff83b40797>] run_timer_softirq+0x1d7/0x280
  [<ffffffff83a04ddb>] __do_softirq+0xcb/0x257
  [<ffffffff83ae03ac>] irq_exit+0x9c/0xb0
  [<ffffffff83a04c1a>] smp_apic_timer_interrupt+0x6a/0x80
  [<ffffffff83a03eaf>] apic_timer_interrupt+0x7f/0x90
  <EOI>
  [<ffffffff83fed2ea>] ? cpuidle_enter_state+0x13a/0x3b0
  [<ffffffff83fed2cd>] ? cpuidle_enter_state+0x11d/0x3b0

Tested:

Following packetdrill no longer crashes the kernel

`echo 0 >/proc/sys/net/ipv4/tcp_timestamps`

// Cache warmup: send a Fast Open cookie request
    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
   +0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0
   +0 setsockopt(3, SOL_TCP, TCP_FASTOPEN_CONNECT, [1], 4) = 0
   +0 connect(3, ..., ...) = -1 EINPROGRESS (Operation is now in progress)
   +0 > S 0:0(0) <mss 1460,nop,nop,sackOK,nop,wscale 8,FO,nop,nop>
 +.01 < S. 123:123(0) ack 1 win 14600 <mss 1460,nop,nop,sackOK,nop,wscale 6,FO abcd1234,nop,nop>
   +0 > . 1:1(0) ack 1
   +0 close(3) = 0
   +0 > F. 1:1(0) ack 1
   +0 < F. 1:1(0) ack 2 win 92
   +0 > .  2:2(0) ack 2

   +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4
   +0 fcntl(4, F_SETFL, O_RDWR|O_NONBLOCK) = 0
   +0 setsockopt(4, SOL_TCP, TCP_FASTOPEN_CONNECT, [1], 4) = 0
   +0 setsockopt(4, SOL_SOCKET, SO_KEEPALIVE, [1], 4) = 0
 +.01 connect(4, ..., ...) = 0
   +0 setsockopt(4, SOL_TCP, TCP_KEEPIDLE, [5], 4) = 0
   +10 close(4) = 0

`echo 1 >/proc/sys/net/ipv4/tcp_timestamps`

Fixes: 19f6d3f3c842 ("net/tcp-fastopen: Add new API support")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Wei Wang <weiwan@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_timer.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index b1e65b3b4361..74db43b47917 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -654,7 +654,8 @@ static void tcp_keepalive_timer (unsigned long data)
 		goto death;
 	}
 
-	if (!sock_flag(sk, SOCK_KEEPOPEN) || sk->sk_state == TCP_CLOSE)
+	if (!sock_flag(sk, SOCK_KEEPOPEN) ||
+	    ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT)))
 		goto out;
 
 	elapsed = keepalive_time_when(tp);
-- 
2.13.4


From 6fb238a9dc3dca51168874ec38b983524b6d3a09 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 4 Aug 2017 14:20:54 +0200
Subject: [PATCH 05/12] bpf, s390: fix jit branch offset related to ldimm64

[ Upstream commit b0a0c2566f28e71e5e32121992ac8060cec75510 ]

While testing some other work that required JIT modifications, I
run into test_bpf causing a hang when JIT enabled on s390. The
problematic test case was the one from ddc665a4bb4b (bpf, arm64:
fix jit branch offset related to ldimm64), and turns out that we
do have a similar issue on s390 as well. In bpf_jit_prog() we
update next instruction address after returning from bpf_jit_insn()
with an insn_count. bpf_jit_insn() returns either -1 in case of
error (e.g. unsupported insn), 1 or 2. The latter is only the
case for ldimm64 due to spanning 2 insns, however, next address
is only set to i + 1 not taking actual insn_count into account,
thus fix is to use insn_count instead of 1. bpf_jit_enable in
mode 2 provides also disasm on s390:

Before fix:

  000003ff800349b6: a7f40003   brc     15,3ff800349bc                 ; target
  000003ff800349ba: 0000               unknown
  000003ff800349bc: e3b0f0700024       stg     %r11,112(%r15)
  000003ff800349c2: e3e0f0880024       stg     %r14,136(%r15)
  000003ff800349c8: 0db0               basr    %r11,%r0
  000003ff800349ca: c0ef00000000       llilf   %r14,0
  000003ff800349d0: e320b0360004       lg      %r2,54(%r11)
  000003ff800349d6: e330b03e0004       lg      %r3,62(%r11)
  000003ff800349dc: ec23ffeda065       clgrj   %r2,%r3,10,3ff800349b6 ; jmp
  000003ff800349e2: e3e0b0460004       lg      %r14,70(%r11)
  000003ff800349e8: e3e0b04e0004       lg      %r14,78(%r11)
  000003ff800349ee: b904002e   lgr     %r2,%r14
  000003ff800349f2: e3b0f0700004       lg      %r11,112(%r15)
  000003ff800349f8: e3e0f0880004       lg      %r14,136(%r15)
  000003ff800349fe: 07fe               bcr     15,%r14

After fix:

  000003ff80ef3db4: a7f40003   brc     15,3ff80ef3dba
  000003ff80ef3db8: 0000               unknown
  000003ff80ef3dba: e3b0f0700024       stg     %r11,112(%r15)
  000003ff80ef3dc0: e3e0f0880024       stg     %r14,136(%r15)
  000003ff80ef3dc6: 0db0               basr    %r11,%r0
  000003ff80ef3dc8: c0ef00000000       llilf   %r14,0
  000003ff80ef3dce: e320b0360004       lg      %r2,54(%r11)
  000003ff80ef3dd4: e330b03e0004       lg      %r3,62(%r11)
  000003ff80ef3dda: ec230006a065       clgrj   %r2,%r3,10,3ff80ef3de6 ; jmp
  000003ff80ef3de0: e3e0b0460004       lg      %r14,70(%r11)
  000003ff80ef3de6: e3e0b04e0004       lg      %r14,78(%r11)          ; target
  000003ff80ef3dec: b904002e   lgr     %r2,%r14
  000003ff80ef3df0: e3b0f0700004       lg      %r11,112(%r15)
  000003ff80ef3df6: e3e0f0880004       lg      %r14,136(%r15)
  000003ff80ef3dfc: 07fe               bcr     15,%r14

test_bpf.ko suite runs fine after the fix.

Fixes: 054623105728 ("s390/bpf: Add s390x eBPF JIT compiler backend")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/s390/net/bpf_jit_comp.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index bee281f3163d..e8dee623d545 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -1252,7 +1252,8 @@ static int bpf_jit_prog(struct bpf_jit *jit, struct bpf_prog *fp)
 		insn_count = bpf_jit_insn(jit, fp, i);
 		if (insn_count < 0)
 			return -1;
-		jit->addrs[i + 1] = jit->prg; /* Next instruction address */
+		/* Next instruction address */
+		jit->addrs[i + insn_count] = jit->prg;
 	}
 	bpf_jit_epilogue(jit);
 
-- 
2.13.4


From c905fea114784e45d55753e23603e56a76382657 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Thu, 3 Aug 2017 22:54:48 +0200
Subject: [PATCH 06/12] net/mlx4_en: don't set CHECKSUM_COMPLETE on SCTP
 packets

[ Upstream commit e718fe450e616227b74d27a233cdf37b4df0c82b ]

if the NIC fails to validate the checksum on TCP/UDP, and validation of IP
checksum is successful, the driver subtracts the pseudo-header checksum
from the value obtained by the hardware and sets CHECKSUM_COMPLETE. Don't
do that if protocol is IPPROTO_SCTP, otherwise CRC32c validation fails.

V2: don't test MLX4_CQE_STATUS_IPV6 if MLX4_CQE_STATUS_IPV4 is set

Reported-by: Shuang Li <shuali@redhat.com>
Fixes: f8c6455bb04b ("net/mlx4_en: Extend checksum offloading by CHECKSUM COMPLETE")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_rx.c | 29 ++++++++++++++++++-----------
 1 file changed, 18 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 5d484581becd..bcbb80ff86a7 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -724,16 +724,21 @@ static inline __wsum get_fixed_vlan_csum(__wsum hw_checksum,
  * header, the HW adds it. To address that, we are subtracting the pseudo
  * header checksum from the checksum value provided by the HW.
  */
-static void get_fixed_ipv4_csum(__wsum hw_checksum, struct sk_buff *skb,
-				struct iphdr *iph)
+static int get_fixed_ipv4_csum(__wsum hw_checksum, struct sk_buff *skb,
+			       struct iphdr *iph)
 {
 	__u16 length_for_csum = 0;
 	__wsum csum_pseudo_header = 0;
+	__u8 ipproto = iph->protocol;
+
+	if (unlikely(ipproto == IPPROTO_SCTP))
+		return -1;
 
 	length_for_csum = (be16_to_cpu(iph->tot_len) - (iph->ihl << 2));
 	csum_pseudo_header = csum_tcpudp_nofold(iph->saddr, iph->daddr,
-						length_for_csum, iph->protocol, 0);
+						length_for_csum, ipproto, 0);
 	skb->csum = csum_sub(hw_checksum, csum_pseudo_header);
+	return 0;
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
@@ -744,17 +749,20 @@ static void get_fixed_ipv4_csum(__wsum hw_checksum, struct sk_buff *skb,
 static int get_fixed_ipv6_csum(__wsum hw_checksum, struct sk_buff *skb,
 			       struct ipv6hdr *ipv6h)
 {
+	__u8 nexthdr = ipv6h->nexthdr;
 	__wsum csum_pseudo_hdr = 0;
 
-	if (unlikely(ipv6h->nexthdr == IPPROTO_FRAGMENT ||
-		     ipv6h->nexthdr == IPPROTO_HOPOPTS))
+	if (unlikely(nexthdr == IPPROTO_FRAGMENT ||
+		     nexthdr == IPPROTO_HOPOPTS ||
+		     nexthdr == IPPROTO_SCTP))
 		return -1;
-	hw_checksum = csum_add(hw_checksum, (__force __wsum)htons(ipv6h->nexthdr));
+	hw_checksum = csum_add(hw_checksum, (__force __wsum)htons(nexthdr));
 
 	csum_pseudo_hdr = csum_partial(&ipv6h->saddr,
 				       sizeof(ipv6h->saddr) + sizeof(ipv6h->daddr), 0);
 	csum_pseudo_hdr = csum_add(csum_pseudo_hdr, (__force __wsum)ipv6h->payload_len);
-	csum_pseudo_hdr = csum_add(csum_pseudo_hdr, (__force __wsum)ntohs(ipv6h->nexthdr));
+	csum_pseudo_hdr = csum_add(csum_pseudo_hdr,
+				   (__force __wsum)htons(nexthdr));
 
 	skb->csum = csum_sub(hw_checksum, csum_pseudo_hdr);
 	skb->csum = csum_add(skb->csum, csum_partial(ipv6h, sizeof(struct ipv6hdr), 0));
@@ -777,11 +785,10 @@ static int check_csum(struct mlx4_cqe *cqe, struct sk_buff *skb, void *va,
 	}
 
 	if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPV4))
-		get_fixed_ipv4_csum(hw_checksum, skb, hdr);
+		return get_fixed_ipv4_csum(hw_checksum, skb, hdr);
 #if IS_ENABLED(CONFIG_IPV6)
-	else if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPV6))
-		if (unlikely(get_fixed_ipv6_csum(hw_checksum, skb, hdr)))
-			return -1;
+	if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPV6))
+		return get_fixed_ipv6_csum(hw_checksum, skb, hdr);
 #endif
 	return 0;
 }
-- 
2.13.4


From e6027a2237540ff9dad4978f903f9981ca3ab29a Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 9 Aug 2017 18:15:19 +0800
Subject: [PATCH 07/12] net: sched: set xt_tgchk_param par.nft_compat as 0 in
 ipt_init_target

[ Upstream commit 96d9703050a0036a3360ec98bb41e107c90664fe ]

Commit 55917a21d0cc ("netfilter: x_tables: add context to know if
extension runs from nft_compat") introduced a member nft_compat to
xt_tgchk_param structure.

But it didn't set it's value for ipt_init_target. With unexpected
value in par.nft_compat, it may return unexpected result in some
target's checkentry.

This patch is to set all it's fields as 0 and only initialize the
non-zero fields in ipt_init_target.

v1->v2:
  As Wang Cong's suggestion, fix it by setting all it's fields as
  0 and only initializing the non-zero fields.

Fixes: 55917a21d0cc ("netfilter: x_tables: add context to know if extension runs from nft_compat")
Suggested-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ipt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 378c1c976058..a1aec0a6c789 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -49,8 +49,8 @@ static int ipt_init_target(struct xt_entry_target *t, char *table,
 		return PTR_ERR(target);
 
 	t->u.kernel.target = target;
+	memset(&par, 0, sizeof(par));
 	par.table     = table;
-	par.entryinfo = NULL;
 	par.target    = target;
 	par.targinfo  = t->data;
 	par.hook_mask = hook;
-- 
2.13.4


From 3a26d6c471e6381a94b4925f20e4fc2b8bac47c0 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 8 Aug 2017 01:41:58 -0700
Subject: [PATCH 08/12] tcp: fastopen: tcp_connect() must refresh the route

[ Upstream commit 8ba60924710cde564a3905588b6219741d6356d0 ]

With new TCP_FASTOPEN_CONNECT socket option, there is a possibility
to call tcp_connect() while socket sk_dst_cache is either NULL
or invalid.

 +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4
 +0 fcntl(4, F_SETFL, O_RDWR|O_NONBLOCK) = 0
 +0 setsockopt(4, SOL_TCP, TCP_FASTOPEN_CONNECT, [1], 4) = 0
 +0 connect(4, ..., ...) = 0

<< sk->sk_dst_cache becomes obsolete, or even set to NULL >>

 +1 sendto(4, ..., 1000, MSG_FASTOPEN, ..., ...) = 1000

We need to refresh the route otherwise bad things can happen,
especially when syzkaller is running on the host :/

Fixes: 19f6d3f3c8422 ("net/tcp-fastopen: Add new API support")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Wei Wang <weiwan@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Acked-by: Wei Wang <weiwan@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index dc4258fd15dc..5d836b037442 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3344,6 +3344,9 @@ int tcp_connect(struct sock *sk)
 	struct sk_buff *buff;
 	int err;
 
+	if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk))
+		return -EHOSTUNREACH; /* Routing failure or similar. */
+
 	tcp_connect_init(sk);
 
 	if (unlikely(tp->repair)) {
-- 
2.13.4


From 778631270239bc3d05936e17baa4ec493b449a96 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Tue, 8 Aug 2017 14:22:55 -0400
Subject: [PATCH 09/12] net: avoid skb_warn_bad_offload false positives on UFO

[ Upstream commit 8d63bee643f1fb53e472f0e135cae4eb99d62d19 ]

skb_warn_bad_offload triggers a warning when an skb enters the GSO
stack at __skb_gso_segment that does not have CHECKSUM_PARTIAL
checksum offload set.

Commit b2504a5dbef3 ("net: reduce skb_warn_bad_offload() noise")
observed that SKB_GSO_DODGY producers can trigger the check and
that passing those packets through the GSO handlers will fix it
up. But, the software UFO handler will set ip_summed to
CHECKSUM_NONE.

When __skb_gso_segment is called from the receive path, this
triggers the warning again.

Make UFO set CHECKSUM_UNNECESSARY instead of CHECKSUM_NONE. On
Tx these two are equivalent. On Rx, this better matches the
skb state (checksum computed), as CHECKSUM_NONE here means no
checksum computed.

See also this thread for context:
http://patchwork.ozlabs.org/patch/799015/

Fixes: b2504a5dbef3 ("net: reduce skb_warn_bad_offload() noise")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c         | 2 +-
 net/ipv4/udp_offload.c | 2 +-
 net/ipv6/udp_offload.c | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 0af019dfe846..1d0a7369d5a2 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2703,7 +2703,7 @@ static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path)
 {
 	if (tx_path)
 		return skb->ip_summed != CHECKSUM_PARTIAL &&
-		       skb->ip_summed != CHECKSUM_NONE;
+		       skb->ip_summed != CHECKSUM_UNNECESSARY;
 
 	return skb->ip_summed == CHECKSUM_NONE;
 }
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index b2be1d9757ef..6de016f80f17 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -232,7 +232,7 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 	if (uh->check == 0)
 		uh->check = CSUM_MANGLED_0;
 
-	skb->ip_summed = CHECKSUM_NONE;
+	skb->ip_summed = CHECKSUM_UNNECESSARY;
 
 	/* If there is no outer header we can fake a checksum offload
 	 * due to the fact that we have already done the checksum in
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index a2267f80febb..e7d378c032cb 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -72,7 +72,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 		if (uh->check == 0)
 			uh->check = CSUM_MANGLED_0;
 
-		skb->ip_summed = CHECKSUM_NONE;
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
 
 		/* If there is no outer header we can fake a checksum offload
 		 * due to the fact that we have already done the checksum in
-- 
2.13.4


From dff28738559fd065b0d92ad77b5942012b28ca54 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 9 Aug 2017 14:38:04 +0300
Subject: [PATCH 10/12] igmp: Fix regression caused by igmp sysctl namespace
 code.

[ Upstream commit 1714020e42b17135032c8606f7185b3fb2ba5d78 ]

Commit dcd87999d415 ("igmp: net: Move igmp namespace init to correct file")
moved the igmp sysctls initialization from tcp_sk_init to igmp_net_init. This
function is only called as part of per-namespace initialization, only if
CONFIG_IP_MULTICAST is defined, otherwise igmp_mc_init() call in ip_init is
compiled out, casuing the igmp pernet ops to not be registerd and those sysctl
being left initialized with 0. However, there are certain functions, such as
ip_mc_join_group which are always compiled and make use of some of those
sysctls. Let's do a partial revert of the aforementioned commit and move the
sysctl initialization into inet_init_net, that way they will always have
sane values.

Fixes: dcd87999d415 ("igmp: net: Move igmp namespace init to correct file")
Link: https://bugzilla.kernel.org/show_bug.cgi?id=196595
Reported-by: Gerardo Exequiel Pozzi <vmlinuz386@gmail.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/af_inet.c | 7 +++++++
 net/ipv4/igmp.c    | 6 ------
 2 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index f60fe82c2c1e..b5116ec31757 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1693,6 +1693,13 @@ static __net_init int inet_init_net(struct net *net)
 	net->ipv4.sysctl_ip_dynaddr = 0;
 	net->ipv4.sysctl_ip_early_demux = 1;
 
+	/* Some igmp sysctl, whose values are always used */
+	net->ipv4.sysctl_igmp_max_memberships = 20;
+	net->ipv4.sysctl_igmp_max_msf = 10;
+	/* IGMP reports for link-local multicast groups are enabled by default */
+	net->ipv4.sysctl_igmp_llm_reports = 1;
+	net->ipv4.sysctl_igmp_qrv = 2;
+
 	return 0;
 }
 
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 19930da56b0a..08575e3bd135 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -2974,12 +2974,6 @@ static int __net_init igmp_net_init(struct net *net)
 		goto out_sock;
 	}
 
-	/* Sysctl initialization */
-	net->ipv4.sysctl_igmp_max_memberships = 20;
-	net->ipv4.sysctl_igmp_max_msf = 10;
-	/* IGMP reports for link-local multicast groups are enabled by default */
-	net->ipv4.sysctl_igmp_llm_reports = 1;
-	net->ipv4.sysctl_igmp_qrv = 2;
 	return 0;
 
 out_sock:
-- 
2.13.4


From 383bbe4651ee8006232fd22745982ce0d918dde9 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Thu, 10 Aug 2017 12:29:19 -0400
Subject: [PATCH 11/12] udp: consistently apply ufo or fragmentation

[ Upstream commit 85f1bd9a7b5a79d5baa8bf44af19658f7bf77bfa ]

When iteratively building a UDP datagram with MSG_MORE and that
datagram exceeds MTU, consistently choose UFO or fragmentation.

Once skb_is_gso, always apply ufo. Conversely, once a datagram is
split across multiple skbs, do not consider ufo.

Sendpage already maintains the first invariant, only add the second.
IPv6 does not have a sendpage implementation to modify.

A gso skb must have a partial checksum, do not follow sk_no_check_tx
in udp_send_skb.

Found by syzkaller.

Fixes: e89e9cf539a2 ("[IPv4/IPv6]: UFO Scatter-gather approach")
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_output.c  | 7 +++++--
 net/ipv4/udp.c        | 2 +-
 net/ipv6/ip6_output.c | 7 ++++---
 3 files changed, 10 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index e5c1dbef3626..93c6cddfbab1 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -936,10 +936,12 @@ static int __ip_append_data(struct sock *sk,
 		csummode = CHECKSUM_PARTIAL;
 
 	cork->length += length;
-	if (((length > mtu) || (skb && skb_is_gso(skb))) &&
+	if ((skb && skb_is_gso(skb)) ||
+	    ((length > mtu) && 
+	    (skb_queue_len(queue) <= 1) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
 	    (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len &&
-	    (sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx) {
+	    (sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx)) {
 		err = ip_ufo_append_data(sk, queue, getfrag, from, length,
 					 hh_len, fragheaderlen, transhdrlen,
 					 maxfraglen, flags);
@@ -1255,6 +1257,7 @@ ssize_t	ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
 		return -EINVAL;
 
 	if ((size + skb->len > mtu) &&
+	    (skb_queue_len(&sk->sk_write_queue) == 1) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
 	    (rt->dst.dev->features & NETIF_F_UFO)) {
 		if (skb->ip_summed != CHECKSUM_PARTIAL)
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 5bab6c3f7a2f..4363b1e89bdf 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -813,7 +813,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4)
 	if (is_udplite)  				 /*     UDP-Lite      */
 		csum = udplite_csum(skb);
 
-	else if (sk->sk_no_check_tx) {   /* UDP csum disabled */
+	else if (sk->sk_no_check_tx && !skb_is_gso(skb)) {   /* UDP csum off */
 
 		skb->ip_summed = CHECKSUM_NONE;
 		goto send;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 5a4b8e7bcedd..255c0e646137 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1376,11 +1376,12 @@ static int __ip6_append_data(struct sock *sk,
 	 */
 
 	cork->length += length;
-	if ((((length + fragheaderlen) > mtu) ||
-	     (skb && skb_is_gso(skb))) &&
+	if ((skb && skb_is_gso(skb)) ||
+	    (((length + fragheaderlen) > mtu) &&
+	    (skb_queue_len(queue) <= 1) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
 	    (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len &&
-	    (sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk)) {
+	    (sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk))) {
 		err = ip6_ufo_append_data(sk, queue, getfrag, from, length,
 					  hh_len, fragheaderlen, exthdrlen,
 					  transhdrlen, mtu, flags, fl6);
-- 
2.13.4


From 9ce2f7b5c25a185dde1bd1f5391a3269521e03de Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Thu, 10 Aug 2017 12:41:58 -0400
Subject: [PATCH 12/12] packet: fix tp_reserve race in packet_set_ring

[ Upstream commit c27927e372f0785f3303e8fad94b85945e2c97b7 ]

Updates to tp_reserve can race with reads of the field in
packet_set_ring. Avoid this by holding the socket lock during
updates in setsockopt PACKET_RESERVE.

This bug was discovered by syzkaller.

Fixes: 8913336a7e8d ("packet: add PACKET_RESERVE sockopt")
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 6a563e6e24de..5d15b3fef939 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3698,14 +3698,19 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 
 		if (optlen != sizeof(val))
 			return -EINVAL;
-		if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
-			return -EBUSY;
 		if (copy_from_user(&val, optval, sizeof(val)))
 			return -EFAULT;
 		if (val > INT_MAX)
 			return -EINVAL;
-		po->tp_reserve = val;
-		return 0;
+		lock_sock(sk);
+		if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+			ret = -EBUSY;
+		} else {
+			po->tp_reserve = val;
+			ret = 0;
+		}
+		release_sock(sk);
+		return ret;
 	}
 	case PACKET_LOSS:
 	{
-- 
2.13.4


[-- Attachment #3: net_412.mbox --]
[-- Type: Application/Octet-Stream, Size: 43841 bytes --]

From 98eb14aab6eb6bf4320755533a46adc8597ef091 Mon Sep 17 00:00:00 2001
From: Gao Feng <gfree.wind@vip.163.com>
Date: Mon, 17 Jul 2017 18:34:42 +0800
Subject: [PATCH 01/15] ppp: Fix false xmit recursion detect with two ppp
 devices

[ Upstream commit e5dadc65f9e0177eb649bcd9d333f1ebf871223e ]

The global percpu variable ppp_xmit_recursion is used to detect the ppp
xmit recursion to avoid the deadlock, which is caused by one CPU tries to
lock the xmit lock twice. But it would report false recursion when one CPU
wants to send the skb from two different PPP devices, like one L2TP on the
PPPoE. It is a normal case actually.

Now use one percpu member of struct ppp instead of the gloable variable to
detect the xmit recursion of one ppp device.

Fixes: 55454a565836 ("ppp: avoid dealock on recursive xmit")
Signed-off-by: Gao Feng <gfree.wind@vip.163.com>
Signed-off-by: Liu Jianying <jianying.liu@ikuai8.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/ppp_generic.c | 30 +++++++++++++++++++++---------
 1 file changed, 21 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index f9c0e62716ea..0d9f776442cb 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -120,6 +120,7 @@ struct ppp {
 	int		n_channels;	/* how many channels are attached 54 */
 	spinlock_t	rlock;		/* lock for receive side 58 */
 	spinlock_t	wlock;		/* lock for transmit side 5c */
+	int		*xmit_recursion __percpu; /* xmit recursion detect */
 	int		mru;		/* max receive unit 60 */
 	unsigned int	flags;		/* control bits 64 */
 	unsigned int	xstate;		/* transmit state bits 68 */
@@ -1025,6 +1026,7 @@ static int ppp_dev_configure(struct net *src_net, struct net_device *dev,
 	struct ppp *ppp = netdev_priv(dev);
 	int indx;
 	int err;
+	int cpu;
 
 	ppp->dev = dev;
 	ppp->ppp_net = src_net;
@@ -1039,6 +1041,15 @@ static int ppp_dev_configure(struct net *src_net, struct net_device *dev,
 	INIT_LIST_HEAD(&ppp->channels);
 	spin_lock_init(&ppp->rlock);
 	spin_lock_init(&ppp->wlock);
+
+	ppp->xmit_recursion = alloc_percpu(int);
+	if (!ppp->xmit_recursion) {
+		err = -ENOMEM;
+		goto err1;
+	}
+	for_each_possible_cpu(cpu)
+		(*per_cpu_ptr(ppp->xmit_recursion, cpu)) = 0;
+
 #ifdef CONFIG_PPP_MULTILINK
 	ppp->minseq = -1;
 	skb_queue_head_init(&ppp->mrq);
@@ -1050,11 +1061,15 @@ static int ppp_dev_configure(struct net *src_net, struct net_device *dev,
 
 	err = ppp_unit_register(ppp, conf->unit, conf->ifname_is_set);
 	if (err < 0)
-		return err;
+		goto err2;
 
 	conf->file->private_data = &ppp->file;
 
 	return 0;
+err2:
+	free_percpu(ppp->xmit_recursion);
+err1:
+	return err;
 }
 
 static const struct nla_policy ppp_nl_policy[IFLA_PPP_MAX + 1] = {
@@ -1398,18 +1413,16 @@ static void __ppp_xmit_process(struct ppp *ppp)
 	ppp_xmit_unlock(ppp);
 }
 
-static DEFINE_PER_CPU(int, ppp_xmit_recursion);
-
 static void ppp_xmit_process(struct ppp *ppp)
 {
 	local_bh_disable();
 
-	if (unlikely(__this_cpu_read(ppp_xmit_recursion)))
+	if (unlikely(*this_cpu_ptr(ppp->xmit_recursion)))
 		goto err;
 
-	__this_cpu_inc(ppp_xmit_recursion);
+	(*this_cpu_ptr(ppp->xmit_recursion))++;
 	__ppp_xmit_process(ppp);
-	__this_cpu_dec(ppp_xmit_recursion);
+	(*this_cpu_ptr(ppp->xmit_recursion))--;
 
 	local_bh_enable();
 
@@ -1903,7 +1916,7 @@ static void __ppp_channel_push(struct channel *pch)
 		read_lock_bh(&pch->upl);
 		ppp = pch->ppp;
 		if (ppp)
-			__ppp_xmit_process(ppp);
+			ppp_xmit_process(ppp);
 		read_unlock_bh(&pch->upl);
 	}
 }
@@ -1912,9 +1925,7 @@ static void ppp_channel_push(struct channel *pch)
 {
 	local_bh_disable();
 
-	__this_cpu_inc(ppp_xmit_recursion);
 	__ppp_channel_push(pch);
-	__this_cpu_dec(ppp_xmit_recursion);
 
 	local_bh_enable();
 }
@@ -3055,6 +3066,7 @@ static void ppp_destroy_interface(struct ppp *ppp)
 #endif /* CONFIG_PPP_FILTER */
 
 	kfree_skb(ppp->xmit_pending);
+	free_percpu(ppp->xmit_recursion);
 
 	free_netdev(ppp->dev);
 }
-- 
2.13.4


From c58c0b441344dda218fe80d75595f02910484102 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Tue, 8 Aug 2017 11:43:24 +0200
Subject: [PATCH 02/15] ppp: fix xmit recursion detection on ppp channels

[ Upstream commit 0a0e1a85c83775a648041be2b15de6d0a2f2b8eb ]

Commit e5dadc65f9e0 ("ppp: Fix false xmit recursion detect with two ppp
devices") dropped the xmit_recursion counter incrementation in
ppp_channel_push() and relied on ppp_xmit_process() for this task.
But __ppp_channel_push() can also send packets directly (using the
.start_xmit() channel callback), in which case the xmit_recursion
counter isn't incremented anymore. If such packets get routed back to
the parent ppp unit, ppp_xmit_process() won't notice the recursion and
will call ppp_channel_push() on the same channel, effectively creating
the deadlock situation that the xmit_recursion mechanism was supposed
to prevent.

This patch re-introduces the xmit_recursion counter incrementation in
ppp_channel_push(). Since the xmit_recursion variable is now part of
the parent ppp unit, incrementation is skipped if the channel doesn't
have any. This is fine because only packets routed through the parent
unit may enter the channel recursively.

Finally, we have to ensure that pch->ppp is not going to be modified
while executing ppp_channel_push(). Instead of taking this lock only
while calling ppp_xmit_process(), we now have to hold it for the full
ppp_channel_push() execution. This respects the ppp locks ordering
which requires locking ->upl before ->downl.

Fixes: e5dadc65f9e0 ("ppp: Fix false xmit recursion detect with two ppp devices")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/ppp_generic.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 0d9f776442cb..18fb00d55aa1 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -1913,21 +1913,23 @@ static void __ppp_channel_push(struct channel *pch)
 	spin_unlock_bh(&pch->downl);
 	/* see if there is anything from the attached unit to be sent */
 	if (skb_queue_empty(&pch->file.xq)) {
-		read_lock_bh(&pch->upl);
 		ppp = pch->ppp;
 		if (ppp)
-			ppp_xmit_process(ppp);
-		read_unlock_bh(&pch->upl);
+			__ppp_xmit_process(ppp);
 	}
 }
 
 static void ppp_channel_push(struct channel *pch)
 {
-	local_bh_disable();
-
-	__ppp_channel_push(pch);
-
-	local_bh_enable();
+	read_lock_bh(&pch->upl);
+	if (pch->ppp) {
+		(*this_cpu_ptr(pch->ppp->xmit_recursion))++;
+		__ppp_channel_push(pch);
+		(*this_cpu_ptr(pch->ppp->xmit_recursion))--;
+	} else {
+		__ppp_channel_push(pch);
+	}
+	read_unlock_bh(&pch->upl);
 }
 
 /*
-- 
2.13.4


From f3761e759025dc147ff37c89d59566357f408cf6 Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Tue, 1 Aug 2017 13:22:32 -0700
Subject: [PATCH 03/15] tcp: avoid setting cwnd to invalid ssthresh after cwnd
 reduction states

[ Upstream commit ed254971edea92c3ac5c67c6a05247a92aa6075e ]

If the sender switches the congestion control during ECN-triggered
cwnd-reduction state (CA_CWR), upon exiting recovery cwnd is set to
the ssthresh value calculated by the previous congestion control. If
the previous congestion control is BBR that always keep ssthresh
to TCP_INIFINITE_SSTHRESH, cwnd ends up being infinite. The safe
step is to avoid assigning invalid ssthresh value when recovery ends.

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 174d4376baa5..57bcae81fe42 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2517,8 +2517,8 @@ static inline void tcp_end_cwnd_reduction(struct sock *sk)
 		return;
 
 	/* Reset cwnd to ssthresh in CWR or Recovery (unless it's undone) */
-	if (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR ||
-	    (tp->undo_marker && tp->snd_ssthresh < TCP_INFINITE_SSTHRESH)) {
+	if (tp->snd_ssthresh < TCP_INFINITE_SSTHRESH &&
+	    (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR || tp->undo_marker)) {
 		tp->snd_cwnd = tp->snd_ssthresh;
 		tp->snd_cwnd_stamp = tcp_time_stamp;
 	}
-- 
2.13.4


From 9cc15aa63a47ffc5eba07961800f252e497c24b1 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 2 Aug 2017 23:10:46 -0700
Subject: [PATCH 04/15] net: fix keepalive code vs TCP_FASTOPEN_CONNECT

[ Upstream commit 2dda640040876cd8ae646408b69eea40c24f9ae9 ]

syzkaller was able to trigger a divide by 0 in TCP stack [1]

Issue here is that keepalive timer needs to be updated to not attempt
to send a probe if the connection setup was deferred using
TCP_FASTOPEN_CONNECT socket option added in linux-4.11

[1]
 divide error: 0000 [#1] SMP
 CPU: 18 PID: 0 Comm: swapper/18 Not tainted
 task: ffff986f62f4b040 ti: ffff986f62fa2000 task.ti: ffff986f62fa2000
 RIP: 0010:[<ffffffff8409cc0d>]  [<ffffffff8409cc0d>] __tcp_select_window+0x8d/0x160
 Call Trace:
  <IRQ>
  [<ffffffff8409d951>] tcp_transmit_skb+0x11/0x20
  [<ffffffff8409da21>] tcp_xmit_probe_skb+0xc1/0xe0
  [<ffffffff840a0ee8>] tcp_write_wakeup+0x68/0x160
  [<ffffffff840a151b>] tcp_keepalive_timer+0x17b/0x230
  [<ffffffff83b3f799>] call_timer_fn+0x39/0xf0
  [<ffffffff83b40797>] run_timer_softirq+0x1d7/0x280
  [<ffffffff83a04ddb>] __do_softirq+0xcb/0x257
  [<ffffffff83ae03ac>] irq_exit+0x9c/0xb0
  [<ffffffff83a04c1a>] smp_apic_timer_interrupt+0x6a/0x80
  [<ffffffff83a03eaf>] apic_timer_interrupt+0x7f/0x90
  <EOI>
  [<ffffffff83fed2ea>] ? cpuidle_enter_state+0x13a/0x3b0
  [<ffffffff83fed2cd>] ? cpuidle_enter_state+0x11d/0x3b0

Tested:

Following packetdrill no longer crashes the kernel

`echo 0 >/proc/sys/net/ipv4/tcp_timestamps`

// Cache warmup: send a Fast Open cookie request
    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
   +0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0
   +0 setsockopt(3, SOL_TCP, TCP_FASTOPEN_CONNECT, [1], 4) = 0
   +0 connect(3, ..., ...) = -1 EINPROGRESS (Operation is now in progress)
   +0 > S 0:0(0) <mss 1460,nop,nop,sackOK,nop,wscale 8,FO,nop,nop>
 +.01 < S. 123:123(0) ack 1 win 14600 <mss 1460,nop,nop,sackOK,nop,wscale 6,FO abcd1234,nop,nop>
   +0 > . 1:1(0) ack 1
   +0 close(3) = 0
   +0 > F. 1:1(0) ack 1
   +0 < F. 1:1(0) ack 2 win 92
   +0 > .  2:2(0) ack 2

   +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4
   +0 fcntl(4, F_SETFL, O_RDWR|O_NONBLOCK) = 0
   +0 setsockopt(4, SOL_TCP, TCP_FASTOPEN_CONNECT, [1], 4) = 0
   +0 setsockopt(4, SOL_SOCKET, SO_KEEPALIVE, [1], 4) = 0
 +.01 connect(4, ..., ...) = 0
   +0 setsockopt(4, SOL_TCP, TCP_KEEPIDLE, [5], 4) = 0
   +10 close(4) = 0

`echo 1 >/proc/sys/net/ipv4/tcp_timestamps`

Fixes: 19f6d3f3c842 ("net/tcp-fastopen: Add new API support")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Wei Wang <weiwan@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_timer.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 14672543cf0b..0733ea7e17cd 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -654,7 +654,8 @@ static void tcp_keepalive_timer (unsigned long data)
 		goto death;
 	}
 
-	if (!sock_flag(sk, SOCK_KEEPOPEN) || sk->sk_state == TCP_CLOSE)
+	if (!sock_flag(sk, SOCK_KEEPOPEN) ||
+	    ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT)))
 		goto out;
 
 	elapsed = keepalive_time_when(tp);
-- 
2.13.4


From da8c4f1e229aaccbb621ac844cc974225b86b869 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 3 Aug 2017 14:13:46 +0800
Subject: [PATCH 05/15] ipv6: set rt6i_protocol properly in the route when it
 is installed

[ Upstream commit b91d532928dff2141ea9c107c3e73104d9843767 ]

After commit c2ed1880fd61 ("net: ipv6: check route protocol when
deleting routes"), ipv6 route checks rt protocol when trying to
remove a rt entry.

It introduced a side effect causing 'ip -6 route flush cache' not
to work well. When flushing caches with iproute, all route caches
get dumped from kernel then removed one by one by sending DELROUTE
requests to kernel for each cache.

The thing is iproute sends the request with the cache whose proto
is set with RTPROT_REDIRECT by rt6_fill_node() when kernel dumps
it. But in kernel the rt_cache protocol is still 0, which causes
the cache not to be matched and removed.

So the real reason is rt6i_protocol in the route is not set when
it is allocated. As David Ahern's suggestion, this patch is to
set rt6i_protocol properly in the route when it is installed and
remove the codes setting rtm_protocol according to rt6i_flags in
rt6_fill_node.

This is also an improvement to keep rt6i_protocol consistent with
rtm_protocol.

Fixes: c2ed1880fd61 ("net: ipv6: check route protocol when deleting routes")
Reported-by: Jianlin Shi <jishi@redhat.com>
Suggested-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index bc49f9a82994..aeb7097acc0a 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2366,6 +2366,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
 	if (on_link)
 		nrt->rt6i_flags &= ~RTF_GATEWAY;
 
+	nrt->rt6i_protocol = RTPROT_REDIRECT;
 	nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key;
 
 	if (ip6_ins_rt(nrt))
@@ -2470,6 +2471,7 @@ static struct rt6_info *rt6_add_route_info(struct net *net,
 		.fc_dst_len	= prefixlen,
 		.fc_flags	= RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO |
 				  RTF_UP | RTF_PREF(pref),
+		.fc_protocol = RTPROT_RA,
 		.fc_nlinfo.portid = 0,
 		.fc_nlinfo.nlh = NULL,
 		.fc_nlinfo.nl_net = net,
@@ -2522,6 +2524,7 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr,
 		.fc_ifindex	= dev->ifindex,
 		.fc_flags	= RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT |
 				  RTF_UP | RTF_EXPIRES | RTF_PREF(pref),
+		.fc_protocol = RTPROT_RA,
 		.fc_nlinfo.portid = 0,
 		.fc_nlinfo.nlh = NULL,
 		.fc_nlinfo.nl_net = dev_net(dev),
@@ -3434,14 +3437,6 @@ static int rt6_fill_node(struct net *net,
 	rtm->rtm_flags = 0;
 	rtm->rtm_scope = RT_SCOPE_UNIVERSE;
 	rtm->rtm_protocol = rt->rt6i_protocol;
-	if (rt->rt6i_flags & RTF_DYNAMIC)
-		rtm->rtm_protocol = RTPROT_REDIRECT;
-	else if (rt->rt6i_flags & RTF_ADDRCONF) {
-		if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ROUTEINFO))
-			rtm->rtm_protocol = RTPROT_RA;
-		else
-			rtm->rtm_protocol = RTPROT_KERNEL;
-	}
 
 	if (rt->rt6i_flags & RTF_CACHE)
 		rtm->rtm_flags |= RTM_F_CLONED;
-- 
2.13.4


From a467bb3d3b2bf5fcc7cf2a46e96dd23871ba5698 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 4 Aug 2017 14:20:54 +0200
Subject: [PATCH 06/15] bpf, s390: fix jit branch offset related to ldimm64

[ Upstream commit b0a0c2566f28e71e5e32121992ac8060cec75510 ]

While testing some other work that required JIT modifications, I
run into test_bpf causing a hang when JIT enabled on s390. The
problematic test case was the one from ddc665a4bb4b (bpf, arm64:
fix jit branch offset related to ldimm64), and turns out that we
do have a similar issue on s390 as well. In bpf_jit_prog() we
update next instruction address after returning from bpf_jit_insn()
with an insn_count. bpf_jit_insn() returns either -1 in case of
error (e.g. unsupported insn), 1 or 2. The latter is only the
case for ldimm64 due to spanning 2 insns, however, next address
is only set to i + 1 not taking actual insn_count into account,
thus fix is to use insn_count instead of 1. bpf_jit_enable in
mode 2 provides also disasm on s390:

Before fix:

  000003ff800349b6: a7f40003   brc     15,3ff800349bc                 ; target
  000003ff800349ba: 0000               unknown
  000003ff800349bc: e3b0f0700024       stg     %r11,112(%r15)
  000003ff800349c2: e3e0f0880024       stg     %r14,136(%r15)
  000003ff800349c8: 0db0               basr    %r11,%r0
  000003ff800349ca: c0ef00000000       llilf   %r14,0
  000003ff800349d0: e320b0360004       lg      %r2,54(%r11)
  000003ff800349d6: e330b03e0004       lg      %r3,62(%r11)
  000003ff800349dc: ec23ffeda065       clgrj   %r2,%r3,10,3ff800349b6 ; jmp
  000003ff800349e2: e3e0b0460004       lg      %r14,70(%r11)
  000003ff800349e8: e3e0b04e0004       lg      %r14,78(%r11)
  000003ff800349ee: b904002e   lgr     %r2,%r14
  000003ff800349f2: e3b0f0700004       lg      %r11,112(%r15)
  000003ff800349f8: e3e0f0880004       lg      %r14,136(%r15)
  000003ff800349fe: 07fe               bcr     15,%r14

After fix:

  000003ff80ef3db4: a7f40003   brc     15,3ff80ef3dba
  000003ff80ef3db8: 0000               unknown
  000003ff80ef3dba: e3b0f0700024       stg     %r11,112(%r15)
  000003ff80ef3dc0: e3e0f0880024       stg     %r14,136(%r15)
  000003ff80ef3dc6: 0db0               basr    %r11,%r0
  000003ff80ef3dc8: c0ef00000000       llilf   %r14,0
  000003ff80ef3dce: e320b0360004       lg      %r2,54(%r11)
  000003ff80ef3dd4: e330b03e0004       lg      %r3,62(%r11)
  000003ff80ef3dda: ec230006a065       clgrj   %r2,%r3,10,3ff80ef3de6 ; jmp
  000003ff80ef3de0: e3e0b0460004       lg      %r14,70(%r11)
  000003ff80ef3de6: e3e0b04e0004       lg      %r14,78(%r11)          ; target
  000003ff80ef3dec: b904002e   lgr     %r2,%r14
  000003ff80ef3df0: e3b0f0700004       lg      %r11,112(%r15)
  000003ff80ef3df6: e3e0f0880004       lg      %r14,136(%r15)
  000003ff80ef3dfc: 07fe               bcr     15,%r14

test_bpf.ko suite runs fine after the fix.

Fixes: 054623105728 ("s390/bpf: Add s390x eBPF JIT compiler backend")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/s390/net/bpf_jit_comp.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 6e97a2e3fd8d..8cea684f1f53 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -1253,7 +1253,8 @@ static int bpf_jit_prog(struct bpf_jit *jit, struct bpf_prog *fp)
 		insn_count = bpf_jit_insn(jit, fp, i);
 		if (insn_count < 0)
 			return -1;
-		jit->addrs[i + 1] = jit->prg; /* Next instruction address */
+		/* Next instruction address */
+		jit->addrs[i + insn_count] = jit->prg;
 	}
 	bpf_jit_epilogue(jit);
 
-- 
2.13.4


From a18ef0049ae0b2e245fcb0241603646fe71337fe Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Thu, 3 Aug 2017 22:54:48 +0200
Subject: [PATCH 07/15] net/mlx4_en: don't set CHECKSUM_COMPLETE on SCTP
 packets

[ Upstream commit e718fe450e616227b74d27a233cdf37b4df0c82b ]

if the NIC fails to validate the checksum on TCP/UDP, and validation of IP
checksum is successful, the driver subtracts the pseudo-header checksum
from the value obtained by the hardware and sets CHECKSUM_COMPLETE. Don't
do that if protocol is IPPROTO_SCTP, otherwise CRC32c validation fails.

V2: don't test MLX4_CQE_STATUS_IPV6 if MLX4_CQE_STATUS_IPV4 is set

Reported-by: Shuang Li <shuali@redhat.com>
Fixes: f8c6455bb04b ("net/mlx4_en: Extend checksum offloading by CHECKSUM COMPLETE")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_rx.c | 29 ++++++++++++++++++-----------
 1 file changed, 18 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 77abd1813047..802f0e8bff3a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -572,16 +572,21 @@ static inline __wsum get_fixed_vlan_csum(__wsum hw_checksum,
  * header, the HW adds it. To address that, we are subtracting the pseudo
  * header checksum from the checksum value provided by the HW.
  */
-static void get_fixed_ipv4_csum(__wsum hw_checksum, struct sk_buff *skb,
-				struct iphdr *iph)
+static int get_fixed_ipv4_csum(__wsum hw_checksum, struct sk_buff *skb,
+			       struct iphdr *iph)
 {
 	__u16 length_for_csum = 0;
 	__wsum csum_pseudo_header = 0;
+	__u8 ipproto = iph->protocol;
+
+	if (unlikely(ipproto == IPPROTO_SCTP))
+		return -1;
 
 	length_for_csum = (be16_to_cpu(iph->tot_len) - (iph->ihl << 2));
 	csum_pseudo_header = csum_tcpudp_nofold(iph->saddr, iph->daddr,
-						length_for_csum, iph->protocol, 0);
+						length_for_csum, ipproto, 0);
 	skb->csum = csum_sub(hw_checksum, csum_pseudo_header);
+	return 0;
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
@@ -592,17 +597,20 @@ static void get_fixed_ipv4_csum(__wsum hw_checksum, struct sk_buff *skb,
 static int get_fixed_ipv6_csum(__wsum hw_checksum, struct sk_buff *skb,
 			       struct ipv6hdr *ipv6h)
 {
+	__u8 nexthdr = ipv6h->nexthdr;
 	__wsum csum_pseudo_hdr = 0;
 
-	if (unlikely(ipv6h->nexthdr == IPPROTO_FRAGMENT ||
-		     ipv6h->nexthdr == IPPROTO_HOPOPTS))
+	if (unlikely(nexthdr == IPPROTO_FRAGMENT ||
+		     nexthdr == IPPROTO_HOPOPTS ||
+		     nexthdr == IPPROTO_SCTP))
 		return -1;
-	hw_checksum = csum_add(hw_checksum, (__force __wsum)htons(ipv6h->nexthdr));
+	hw_checksum = csum_add(hw_checksum, (__force __wsum)htons(nexthdr));
 
 	csum_pseudo_hdr = csum_partial(&ipv6h->saddr,
 				       sizeof(ipv6h->saddr) + sizeof(ipv6h->daddr), 0);
 	csum_pseudo_hdr = csum_add(csum_pseudo_hdr, (__force __wsum)ipv6h->payload_len);
-	csum_pseudo_hdr = csum_add(csum_pseudo_hdr, (__force __wsum)ntohs(ipv6h->nexthdr));
+	csum_pseudo_hdr = csum_add(csum_pseudo_hdr,
+				   (__force __wsum)htons(nexthdr));
 
 	skb->csum = csum_sub(hw_checksum, csum_pseudo_hdr);
 	skb->csum = csum_add(skb->csum, csum_partial(ipv6h, sizeof(struct ipv6hdr), 0));
@@ -625,11 +633,10 @@ static int check_csum(struct mlx4_cqe *cqe, struct sk_buff *skb, void *va,
 	}
 
 	if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPV4))
-		get_fixed_ipv4_csum(hw_checksum, skb, hdr);
+		return get_fixed_ipv4_csum(hw_checksum, skb, hdr);
 #if IS_ENABLED(CONFIG_IPV6)
-	else if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPV6))
-		if (unlikely(get_fixed_ipv6_csum(hw_checksum, skb, hdr)))
-			return -1;
+	if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPV6))
+		return get_fixed_ipv6_csum(hw_checksum, skb, hdr);
 #endif
 	return 0;
 }
-- 
2.13.4


From 668fc0f76e49d90eb8560591b79c79c1e154d9d5 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 8 Aug 2017 15:25:25 +0800
Subject: [PATCH 08/15] net: sched: set xt_tgchk_param par.net properly in
 ipt_init_target

[ Upstream commit ec0acb09313074ba1a4976945791d9c6815f39fb ]

Now xt_tgchk_param par in ipt_init_target is a local varibale,
par.net is not initialized there. Later when xt_check_target
calls target's checkentry in which it may access par.net, it
would cause kernel panic.

Jaroslav found this panic when running:

  # ip link add TestIface type dummy
  # tc qd add dev TestIface ingress handle ffff:
  # tc filter add dev TestIface parent ffff: u32 match u32 0 0 \
    action xt -j CONNMARK --set-mark 4

This patch is to pass net param into ipt_init_target and set
par.net with it properly in there.

v1->v2:
  As Wang Cong pointed, I missed ipt_net_id != xt_net_id, so fix
  it by also passing net_id to __tcf_ipt_init.
v2->v3:
  Missed the fixes tag, so add it.

Fixes: ecb2421b5ddf ("netfilter: add and use nf_ct_netns_get/put")
Reported-by: Jaroslav Aster <jaster@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ipt.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 36f0ced9e60c..94ba5cfab860 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -36,8 +36,8 @@ static struct tc_action_ops act_ipt_ops;
 static unsigned int xt_net_id;
 static struct tc_action_ops act_xt_ops;
 
-static int ipt_init_target(struct xt_entry_target *t, char *table,
-			   unsigned int hook)
+static int ipt_init_target(struct net *net, struct xt_entry_target *t,
+			   char *table, unsigned int hook)
 {
 	struct xt_tgchk_param par;
 	struct xt_target *target;
@@ -49,6 +49,7 @@ static int ipt_init_target(struct xt_entry_target *t, char *table,
 		return PTR_ERR(target);
 
 	t->u.kernel.target = target;
+	par.net       = net;
 	par.table     = table;
 	par.entryinfo = NULL;
 	par.target    = target;
@@ -91,10 +92,11 @@ static const struct nla_policy ipt_policy[TCA_IPT_MAX + 1] = {
 	[TCA_IPT_TARG]	= { .len = sizeof(struct xt_entry_target) },
 };
 
-static int __tcf_ipt_init(struct tc_action_net *tn, struct nlattr *nla,
+static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla,
 			  struct nlattr *est, struct tc_action **a,
 			  const struct tc_action_ops *ops, int ovr, int bind)
 {
+	struct tc_action_net *tn = net_generic(net, id);
 	struct nlattr *tb[TCA_IPT_MAX + 1];
 	struct tcf_ipt *ipt;
 	struct xt_entry_target *td, *t;
@@ -159,7 +161,7 @@ static int __tcf_ipt_init(struct tc_action_net *tn, struct nlattr *nla,
 	if (unlikely(!t))
 		goto err2;
 
-	err = ipt_init_target(t, tname, hook);
+	err = ipt_init_target(net, t, tname, hook);
 	if (err < 0)
 		goto err3;
 
@@ -193,18 +195,16 @@ static int tcf_ipt_init(struct net *net, struct nlattr *nla,
 			struct nlattr *est, struct tc_action **a, int ovr,
 			int bind)
 {
-	struct tc_action_net *tn = net_generic(net, ipt_net_id);
-
-	return __tcf_ipt_init(tn, nla, est, a, &act_ipt_ops, ovr, bind);
+	return __tcf_ipt_init(net, ipt_net_id, nla, est, a, &act_ipt_ops, ovr,
+			      bind);
 }
 
 static int tcf_xt_init(struct net *net, struct nlattr *nla,
 		       struct nlattr *est, struct tc_action **a, int ovr,
 		       int bind)
 {
-	struct tc_action_net *tn = net_generic(net, xt_net_id);
-
-	return __tcf_ipt_init(tn, nla, est, a, &act_xt_ops, ovr, bind);
+	return __tcf_ipt_init(net, xt_net_id, nla, est, a, &act_xt_ops, ovr,
+			      bind);
 }
 
 static int tcf_ipt(struct sk_buff *skb, const struct tc_action *a,
-- 
2.13.4


From ebf787c0667316f24a566523f66908b251cca352 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 9 Aug 2017 18:15:19 +0800
Subject: [PATCH 09/15] net: sched: set xt_tgchk_param par.nft_compat as 0 in
 ipt_init_target

[ Upstream commit 96d9703050a0036a3360ec98bb41e107c90664fe ]

Commit 55917a21d0cc ("netfilter: x_tables: add context to know if
extension runs from nft_compat") introduced a member nft_compat to
xt_tgchk_param structure.

But it didn't set it's value for ipt_init_target. With unexpected
value in par.nft_compat, it may return unexpected result in some
target's checkentry.

This patch is to set all it's fields as 0 and only initialize the
non-zero fields in ipt_init_target.

v1->v2:
  As Wang Cong's suggestion, fix it by setting all it's fields as
  0 and only initializing the non-zero fields.

Fixes: 55917a21d0cc ("netfilter: x_tables: add context to know if extension runs from nft_compat")
Suggested-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ipt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 94ba5cfab860..d516ba8178b8 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -49,9 +49,9 @@ static int ipt_init_target(struct net *net, struct xt_entry_target *t,
 		return PTR_ERR(target);
 
 	t->u.kernel.target = target;
+	memset(&par, 0, sizeof(par));
 	par.net       = net;
 	par.table     = table;
-	par.entryinfo = NULL;
 	par.target    = target;
 	par.targinfo  = t->data;
 	par.hook_mask = hook;
-- 
2.13.4


From b8803dbe5f16672a9ffc68d06492d8c40926586d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 8 Aug 2017 01:41:58 -0700
Subject: [PATCH 10/15] tcp: fastopen: tcp_connect() must refresh the route

[ Upstream commit 8ba60924710cde564a3905588b6219741d6356d0 ]

With new TCP_FASTOPEN_CONNECT socket option, there is a possibility
to call tcp_connect() while socket sk_dst_cache is either NULL
or invalid.

 +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4
 +0 fcntl(4, F_SETFL, O_RDWR|O_NONBLOCK) = 0
 +0 setsockopt(4, SOL_TCP, TCP_FASTOPEN_CONNECT, [1], 4) = 0
 +0 connect(4, ..., ...) = 0

<< sk->sk_dst_cache becomes obsolete, or even set to NULL >>

 +1 sendto(4, ..., 1000, MSG_FASTOPEN, ..., ...) = 1000

We need to refresh the route otherwise bad things can happen,
especially when syzkaller is running on the host :/

Fixes: 19f6d3f3c8422 ("net/tcp-fastopen: Add new API support")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Wei Wang <weiwan@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Acked-by: Wei Wang <weiwan@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 4858e190f6ac..8963b8c5fb41 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3361,6 +3361,9 @@ int tcp_connect(struct sock *sk)
 	struct sk_buff *buff;
 	int err;
 
+	if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk))
+		return -EHOSTUNREACH; /* Routing failure or similar. */
+
 	tcp_connect_init(sk);
 
 	if (unlikely(tp->repair)) {
-- 
2.13.4


From 99726e8f6e431b50b11df882b6a805986cb0f96a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Tue, 8 Aug 2017 18:02:11 +0200
Subject: [PATCH 11/15] qmi_wwan: fix NULL deref on disconnect
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit bbae08e592706dc32e5c7c97827b13c1c178668b ]

qmi_wwan_disconnect is called twice when disconnecting devices with
separate control and data interfaces.  The first invocation will set
the interface data to NULL for both interfaces to flag that the
disconnect has been handled.  But the matching NULL check was left
out when qmi_wwan_disconnect was added, resulting in this oops:

  usb 2-1.4: USB disconnect, device number 4
  qmi_wwan 2-1.4:1.6 wwp0s29u1u4i6: unregister 'qmi_wwan' usb-0000:00:1d.0-1.4, WWAN/QMI device
  BUG: unable to handle kernel NULL pointer dereference at 00000000000000e0
  IP: qmi_wwan_disconnect+0x25/0xc0 [qmi_wwan]
  PGD 0
  P4D 0
  Oops: 0000 [#1] SMP
  Modules linked in: <stripped irrelevant module list>
  CPU: 2 PID: 33 Comm: kworker/2:1 Tainted: G            E   4.12.3-nr44-normandy-r1500619820+ #1
  Hardware name: LENOVO 4291LR7/4291LR7, BIOS CBET4000 4.6-810-g50522254fb 07/21/2017
  Workqueue: usb_hub_wq hub_event [usbcore]
  task: ffff8c882b716040 task.stack: ffffb8e800d84000
  RIP: 0010:qmi_wwan_disconnect+0x25/0xc0 [qmi_wwan]
  RSP: 0018:ffffb8e800d87b38 EFLAGS: 00010246
  RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000
  RDX: 0000000000000001 RSI: ffff8c8824f3f1d0 RDI: ffff8c8824ef6400
  RBP: ffff8c8824ef6400 R08: 0000000000000000 R09: 0000000000000000
  R10: ffffb8e800d87780 R11: 0000000000000011 R12: ffffffffc07ea0e8
  R13: ffff8c8824e2e000 R14: ffff8c8824e2e098 R15: 0000000000000000
  FS:  0000000000000000(0000) GS:ffff8c8835300000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 00000000000000e0 CR3: 0000000229ca5000 CR4: 00000000000406e0
  Call Trace:
   ? usb_unbind_interface+0x71/0x270 [usbcore]
   ? device_release_driver_internal+0x154/0x210
   ? qmi_wwan_unbind+0x6d/0xc0 [qmi_wwan]
   ? usbnet_disconnect+0x6c/0xf0 [usbnet]
   ? qmi_wwan_disconnect+0x87/0xc0 [qmi_wwan]
   ? usb_unbind_interface+0x71/0x270 [usbcore]
   ? device_release_driver_internal+0x154/0x210

Reported-and-tested-by: Nathaniel Roach <nroach44@gmail.com>
Fixes: c6adf77953bc ("net: usb: qmi_wwan: add qmap mux protocol support")
Cc: Daniele Palmas <dnlplm@gmail.com>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 32a22f4e8356..c42153a985be 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1340,10 +1340,14 @@ static int qmi_wwan_probe(struct usb_interface *intf,
 static void qmi_wwan_disconnect(struct usb_interface *intf)
 {
 	struct usbnet *dev = usb_get_intfdata(intf);
-	struct qmi_wwan_state *info = (void *)&dev->data;
+	struct qmi_wwan_state *info;
 	struct list_head *iter;
 	struct net_device *ldev;
 
+	/* called twice if separate control and data intf */
+	if (!dev)
+		return;
+	info = (void *)&dev->data;
 	if (info->flags & QMI_WWAN_FLAG_MUX) {
 		if (!rtnl_trylock()) {
 			restart_syscall();
-- 
2.13.4


From dbf5090803c54cbd89a334e663e3c06074a9a72e Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Tue, 8 Aug 2017 14:22:55 -0400
Subject: [PATCH 12/15] net: avoid skb_warn_bad_offload false positives on UFO

[ Upstream commit 8d63bee643f1fb53e472f0e135cae4eb99d62d19 ]

skb_warn_bad_offload triggers a warning when an skb enters the GSO
stack at __skb_gso_segment that does not have CHECKSUM_PARTIAL
checksum offload set.

Commit b2504a5dbef3 ("net: reduce skb_warn_bad_offload() noise")
observed that SKB_GSO_DODGY producers can trigger the check and
that passing those packets through the GSO handlers will fix it
up. But, the software UFO handler will set ip_summed to
CHECKSUM_NONE.

When __skb_gso_segment is called from the receive path, this
triggers the warning again.

Make UFO set CHECKSUM_UNNECESSARY instead of CHECKSUM_NONE. On
Tx these two are equivalent. On Rx, this better matches the
skb state (checksum computed), as CHECKSUM_NONE here means no
checksum computed.

See also this thread for context:
http://patchwork.ozlabs.org/patch/799015/

Fixes: b2504a5dbef3 ("net: reduce skb_warn_bad_offload() noise")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c         | 2 +-
 net/ipv4/udp_offload.c | 2 +-
 net/ipv6/udp_offload.c | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 25f9461eff3f..528edc68a64a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2670,7 +2670,7 @@ static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path)
 {
 	if (tx_path)
 		return skb->ip_summed != CHECKSUM_PARTIAL &&
-		       skb->ip_summed != CHECKSUM_NONE;
+		       skb->ip_summed != CHECKSUM_UNNECESSARY;
 
 	return skb->ip_summed == CHECKSUM_NONE;
 }
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 781250151d40..0932c85b42af 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -235,7 +235,7 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 	if (uh->check == 0)
 		uh->check = CSUM_MANGLED_0;
 
-	skb->ip_summed = CHECKSUM_NONE;
+	skb->ip_summed = CHECKSUM_UNNECESSARY;
 
 	/* If there is no outer header we can fake a checksum offload
 	 * due to the fact that we have already done the checksum in
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index a2267f80febb..e7d378c032cb 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -72,7 +72,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 		if (uh->check == 0)
 			uh->check = CSUM_MANGLED_0;
 
-		skb->ip_summed = CHECKSUM_NONE;
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
 
 		/* If there is no outer header we can fake a checksum offload
 		 * due to the fact that we have already done the checksum in
-- 
2.13.4


From 8c6cb0c2336408fceb6bba19e832210a64a125a0 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 9 Aug 2017 14:38:04 +0300
Subject: [PATCH 13/15] igmp: Fix regression caused by igmp sysctl namespace
 code.

[ Upstream commit 1714020e42b17135032c8606f7185b3fb2ba5d78 ]

Commit dcd87999d415 ("igmp: net: Move igmp namespace init to correct file")
moved the igmp sysctls initialization from tcp_sk_init to igmp_net_init. This
function is only called as part of per-namespace initialization, only if
CONFIG_IP_MULTICAST is defined, otherwise igmp_mc_init() call in ip_init is
compiled out, casuing the igmp pernet ops to not be registerd and those sysctl
being left initialized with 0. However, there are certain functions, such as
ip_mc_join_group which are always compiled and make use of some of those
sysctls. Let's do a partial revert of the aforementioned commit and move the
sysctl initialization into inet_init_net, that way they will always have
sane values.

Fixes: dcd87999d415 ("igmp: net: Move igmp namespace init to correct file")
Link: https://bugzilla.kernel.org/show_bug.cgi?id=196595
Reported-by: Gerardo Exequiel Pozzi <vmlinuz386@gmail.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/af_inet.c | 7 +++++++
 net/ipv4/igmp.c    | 6 ------
 2 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 58925b6597de..ab8ebd440423 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1731,6 +1731,13 @@ static __net_init int inet_init_net(struct net *net)
 	net->ipv4.sysctl_ip_prot_sock = PROT_SOCK;
 #endif
 
+	/* Some igmp sysctl, whose values are always used */
+	net->ipv4.sysctl_igmp_max_memberships = 20;
+	net->ipv4.sysctl_igmp_max_msf = 10;
+	/* IGMP reports for link-local multicast groups are enabled by default */
+	net->ipv4.sysctl_igmp_llm_reports = 1;
+	net->ipv4.sysctl_igmp_qrv = 2;
+
 	return 0;
 }
 
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index ec9a396fa466..3db1adb6b7a0 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -2974,12 +2974,6 @@ static int __net_init igmp_net_init(struct net *net)
 		goto out_sock;
 	}
 
-	/* Sysctl initialization */
-	net->ipv4.sysctl_igmp_max_memberships = 20;
-	net->ipv4.sysctl_igmp_max_msf = 10;
-	/* IGMP reports for link-local multicast groups are enabled by default */
-	net->ipv4.sysctl_igmp_llm_reports = 1;
-	net->ipv4.sysctl_igmp_qrv = 2;
 	return 0;
 
 out_sock:
-- 
2.13.4


From c441f8735173f07c74c36420f3f75c9c11d497f4 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Thu, 10 Aug 2017 12:29:19 -0400
Subject: [PATCH 14/15] udp: consistently apply ufo or fragmentation

[ Upstream commit 85f1bd9a7b5a79d5baa8bf44af19658f7bf77bfa ]

When iteratively building a UDP datagram with MSG_MORE and that
datagram exceeds MTU, consistently choose UFO or fragmentation.

Once skb_is_gso, always apply ufo. Conversely, once a datagram is
split across multiple skbs, do not consider ufo.

Sendpage already maintains the first invariant, only add the second.
IPv6 does not have a sendpage implementation to modify.

A gso skb must have a partial checksum, do not follow sk_no_check_tx
in udp_send_skb.

Found by syzkaller.

Fixes: e89e9cf539a2 ("[IPv4/IPv6]: UFO Scatter-gather approach")
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_output.c  | 8 +++++---
 net/ipv4/udp.c        | 2 +-
 net/ipv6/ip6_output.c | 7 ++++---
 3 files changed, 10 insertions(+), 7 deletions(-)

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 532b36e9ce2a..e5948c0c9759 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -964,11 +964,12 @@ static int __ip_append_data(struct sock *sk,
 		csummode = CHECKSUM_PARTIAL;
 
 	cork->length += length;
-	if ((((length + (skb ? skb->len : fragheaderlen)) > mtu) ||
-	     (skb && skb_is_gso(skb))) &&
+	if ((skb && skb_is_gso(skb)) ||
+	    (((length + (skb ? skb->len : fragheaderlen)) > mtu) &&
+	    (skb_queue_len(queue) <= 1) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
 	    (rt->dst.dev->features & NETIF_F_UFO) && !dst_xfrm(&rt->dst) &&
-	    (sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx) {
+	    (sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx)) {
 		err = ip_ufo_append_data(sk, queue, getfrag, from, length,
 					 hh_len, fragheaderlen, transhdrlen,
 					 maxfraglen, flags);
@@ -1287,6 +1288,7 @@ ssize_t	ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
 		return -EINVAL;
 
 	if ((size + skb->len > mtu) &&
+	    (skb_queue_len(&sk->sk_write_queue) == 1) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
 	    (rt->dst.dev->features & NETIF_F_UFO)) {
 		if (skb->ip_summed != CHECKSUM_PARTIAL)
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 1d6219bf2d6b..363e013e3984 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -802,7 +802,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4)
 	if (is_udplite)  				 /*     UDP-Lite      */
 		csum = udplite_csum(skb);
 
-	else if (sk->sk_no_check_tx) {   /* UDP csum disabled */
+	else if (sk->sk_no_check_tx && !skb_is_gso(skb)) {   /* UDP csum off */
 
 		skb->ip_summed = CHECKSUM_NONE;
 		goto send;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 1699acb2fa2c..90e8c3d57423 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1390,11 +1390,12 @@ static int __ip6_append_data(struct sock *sk,
 	 */
 
 	cork->length += length;
-	if ((((length + (skb ? skb->len : headersize)) > mtu) ||
-	     (skb && skb_is_gso(skb))) &&
+	if ((skb && skb_is_gso(skb)) ||
+	    (((length + (skb ? skb->len : headersize)) > mtu) &&
+	    (skb_queue_len(queue) <= 1) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
 	    (rt->dst.dev->features & NETIF_F_UFO) && !dst_xfrm(&rt->dst) &&
-	    (sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk)) {
+	    (sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk))) {
 		err = ip6_ufo_append_data(sk, queue, getfrag, from, length,
 					  hh_len, fragheaderlen, exthdrlen,
 					  transhdrlen, mtu, flags, fl6);
-- 
2.13.4


From b05eda8e44cf7249c2852924512b4a64f29fb96f Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Thu, 10 Aug 2017 12:41:58 -0400
Subject: [PATCH 15/15] packet: fix tp_reserve race in packet_set_ring

[ Upstream commit c27927e372f0785f3303e8fad94b85945e2c97b7 ]

Updates to tp_reserve can race with reads of the field in
packet_set_ring. Avoid this by holding the socket lock during
updates in setsockopt PACKET_RESERVE.

This bug was discovered by syzkaller.

Fixes: 8913336a7e8d ("packet: add PACKET_RESERVE sockopt")
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index e3eeed19cc7a..8cb32ca43416 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3705,14 +3705,19 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 
 		if (optlen != sizeof(val))
 			return -EINVAL;
-		if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
-			return -EBUSY;
 		if (copy_from_user(&val, optval, sizeof(val)))
 			return -EFAULT;
 		if (val > INT_MAX)
 			return -EINVAL;
-		po->tp_reserve = val;
-		return 0;
+		lock_sock(sk);
+		if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+			ret = -EBUSY;
+		} else {
+			po->tp_reserve = val;
+			ret = 0;
+		}
+		release_sock(sk);
+		return ret;
 	}
 	case PACKET_LOSS:
 	{
-- 
2.13.4

Re: [PATCHES] Networking

[Greg KH]

On Thu, Aug 10, 2017 at 10:25:42PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.9 and
> v4.12 -stable, respectively.

All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 102 bytes --]


Please queue up the following networking fixes for v4.9 and v4.12
-stable, respectively.

Thank you!

[-- Attachment #2: net_49.mbox --]
[-- Type: Application/Octet-Stream, Size: 106165 bytes --]

From d14811d21d471919e24c4520bb0254b0a42ea4f0 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 14 Aug 2017 10:16:45 -0700
Subject: [PATCH 01/25] af_key: do not use GFP_KERNEL in atomic contexts

[ Upstream commit 36f41f8fc6d8aa9f8c9072d66ff7cf9055f5e69b ]

pfkey_broadcast() might be called from non process contexts,
we can not use GFP_KERNEL in these cases [1].

This patch partially reverts commit ba51b6be38c1 ("net: Fix RCU splat in
af_key"), only keeping the GFP_ATOMIC forcing under rcu_read_lock()
section.

[1] : syzkaller reported :

in_atomic(): 1, irqs_disabled(): 0, pid: 2932, name: syzkaller183439
3 locks held by syzkaller183439/2932:
 #0:  (&net->xfrm.xfrm_cfg_mutex){+.+.+.}, at: [<ffffffff83b43888>] pfkey_sendmsg+0x4c8/0x9f0 net/key/af_key.c:3649
 #1:  (&pfk->dump_lock){+.+.+.}, at: [<ffffffff83b467f6>] pfkey_do_dump+0x76/0x3f0 net/key/af_key.c:293
 #2:  (&(&net->xfrm.xfrm_policy_lock)->rlock){+...+.}, at: [<ffffffff83957632>] spin_lock_bh include/linux/spinlock.h:304 [inline]
 #2:  (&(&net->xfrm.xfrm_policy_lock)->rlock){+...+.}, at: [<ffffffff83957632>] xfrm_policy_walk+0x192/0xa30 net/xfrm/xfrm_policy.c:1028
CPU: 0 PID: 2932 Comm: syzkaller183439 Not tainted 4.13.0-rc4+ #24
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:16 [inline]
 dump_stack+0x194/0x257 lib/dump_stack.c:52
 ___might_sleep+0x2b2/0x470 kernel/sched/core.c:5994
 __might_sleep+0x95/0x190 kernel/sched/core.c:5947
 slab_pre_alloc_hook mm/slab.h:416 [inline]
 slab_alloc mm/slab.c:3383 [inline]
 kmem_cache_alloc+0x24b/0x6e0 mm/slab.c:3559
 skb_clone+0x1a0/0x400 net/core/skbuff.c:1037
 pfkey_broadcast_one+0x4b2/0x6f0 net/key/af_key.c:207
 pfkey_broadcast+0x4ba/0x770 net/key/af_key.c:281
 dump_sp+0x3d6/0x500 net/key/af_key.c:2685
 xfrm_policy_walk+0x2f1/0xa30 net/xfrm/xfrm_policy.c:1042
 pfkey_dump_sp+0x42/0x50 net/key/af_key.c:2695
 pfkey_do_dump+0xaa/0x3f0 net/key/af_key.c:299
 pfkey_spddump+0x1a0/0x210 net/key/af_key.c:2722
 pfkey_process+0x606/0x710 net/key/af_key.c:2814
 pfkey_sendmsg+0x4d6/0x9f0 net/key/af_key.c:3650
sock_sendmsg_nosec net/socket.c:633 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:643
 ___sys_sendmsg+0x755/0x890 net/socket.c:2035
 __sys_sendmsg+0xe5/0x210 net/socket.c:2069
 SYSC_sendmsg net/socket.c:2080 [inline]
 SyS_sendmsg+0x2d/0x50 net/socket.c:2076
 entry_SYSCALL_64_fastpath+0x1f/0xbe
RIP: 0033:0x445d79
RSP: 002b:00007f32447c1dc8 EFLAGS: 00000202 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 0000000000445d79
RDX: 0000000000000000 RSI: 000000002023dfc8 RDI: 0000000000000008
RBP: 0000000000000086 R08: 00007f32447c2700 R09: 00007f32447c2700
R10: 00007f32447c2700 R11: 0000000000000202 R12: 0000000000000000
R13: 00007ffe33edec4f R14: 00007f32447c29c0 R15: 0000000000000000

Fixes: ba51b6be38c1 ("net: Fix RCU splat in af_key")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: David Ahern <dsa@cumulusnetworks.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/key/af_key.c | 48 ++++++++++++++++++++++++++----------------------
 1 file changed, 26 insertions(+), 22 deletions(-)

diff --git a/net/key/af_key.c b/net/key/af_key.c
index 2e1050ec2cf0..94bf810ad242 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -228,7 +228,7 @@ static int pfkey_broadcast_one(struct sk_buff *skb, struct sk_buff **skb2,
 #define BROADCAST_ONE		1
 #define BROADCAST_REGISTERED	2
 #define BROADCAST_PROMISC_ONLY	4
-static int pfkey_broadcast(struct sk_buff *skb,
+static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation,
 			   int broadcast_flags, struct sock *one_sk,
 			   struct net *net)
 {
@@ -278,7 +278,7 @@ static int pfkey_broadcast(struct sk_buff *skb,
 	rcu_read_unlock();
 
 	if (one_sk != NULL)
-		err = pfkey_broadcast_one(skb, &skb2, GFP_KERNEL, one_sk);
+		err = pfkey_broadcast_one(skb, &skb2, allocation, one_sk);
 
 	kfree_skb(skb2);
 	kfree_skb(skb);
@@ -311,7 +311,7 @@ static int pfkey_do_dump(struct pfkey_sock *pfk)
 		hdr = (struct sadb_msg *) pfk->dump.skb->data;
 		hdr->sadb_msg_seq = 0;
 		hdr->sadb_msg_errno = rc;
-		pfkey_broadcast(pfk->dump.skb, BROADCAST_ONE,
+		pfkey_broadcast(pfk->dump.skb, GFP_ATOMIC, BROADCAST_ONE,
 				&pfk->sk, sock_net(&pfk->sk));
 		pfk->dump.skb = NULL;
 	}
@@ -355,7 +355,7 @@ static int pfkey_error(const struct sadb_msg *orig, int err, struct sock *sk)
 	hdr->sadb_msg_len = (sizeof(struct sadb_msg) /
 			     sizeof(uint64_t));
 
-	pfkey_broadcast(skb, BROADCAST_ONE, sk, sock_net(sk));
+	pfkey_broadcast(skb, GFP_KERNEL, BROADCAST_ONE, sk, sock_net(sk));
 
 	return 0;
 }
@@ -1396,7 +1396,7 @@ static int pfkey_getspi(struct sock *sk, struct sk_buff *skb, const struct sadb_
 
 	xfrm_state_put(x);
 
-	pfkey_broadcast(resp_skb, BROADCAST_ONE, sk, net);
+	pfkey_broadcast(resp_skb, GFP_KERNEL, BROADCAST_ONE, sk, net);
 
 	return 0;
 }
@@ -1483,7 +1483,7 @@ static int key_notify_sa(struct xfrm_state *x, const struct km_event *c)
 	hdr->sadb_msg_seq = c->seq;
 	hdr->sadb_msg_pid = c->portid;
 
-	pfkey_broadcast(skb, BROADCAST_ALL, NULL, xs_net(x));
+	pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, xs_net(x));
 
 	return 0;
 }
@@ -1596,7 +1596,7 @@ static int pfkey_get(struct sock *sk, struct sk_buff *skb, const struct sadb_msg
 	out_hdr->sadb_msg_reserved = 0;
 	out_hdr->sadb_msg_seq = hdr->sadb_msg_seq;
 	out_hdr->sadb_msg_pid = hdr->sadb_msg_pid;
-	pfkey_broadcast(out_skb, BROADCAST_ONE, sk, sock_net(sk));
+	pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ONE, sk, sock_net(sk));
 
 	return 0;
 }
@@ -1701,8 +1701,8 @@ static int pfkey_register(struct sock *sk, struct sk_buff *skb, const struct sad
 		return -ENOBUFS;
 	}
 
-	pfkey_broadcast(supp_skb, BROADCAST_REGISTERED, sk, sock_net(sk));
-
+	pfkey_broadcast(supp_skb, GFP_KERNEL, BROADCAST_REGISTERED, sk,
+			sock_net(sk));
 	return 0;
 }
 
@@ -1720,7 +1720,8 @@ static int unicast_flush_resp(struct sock *sk, const struct sadb_msg *ihdr)
 	hdr->sadb_msg_errno = (uint8_t) 0;
 	hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t));
 
-	return pfkey_broadcast(skb, BROADCAST_ONE, sk, sock_net(sk));
+	return pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ONE, sk,
+			       sock_net(sk));
 }
 
 static int key_notify_sa_flush(const struct km_event *c)
@@ -1741,7 +1742,7 @@ static int key_notify_sa_flush(const struct km_event *c)
 	hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t));
 	hdr->sadb_msg_reserved = 0;
 
-	pfkey_broadcast(skb, BROADCAST_ALL, NULL, c->net);
+	pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, c->net);
 
 	return 0;
 }
@@ -1798,7 +1799,7 @@ static int dump_sa(struct xfrm_state *x, int count, void *ptr)
 	out_hdr->sadb_msg_pid = pfk->dump.msg_portid;
 
 	if (pfk->dump.skb)
-		pfkey_broadcast(pfk->dump.skb, BROADCAST_ONE,
+		pfkey_broadcast(pfk->dump.skb, GFP_ATOMIC, BROADCAST_ONE,
 				&pfk->sk, sock_net(&pfk->sk));
 	pfk->dump.skb = out_skb;
 
@@ -1886,7 +1887,7 @@ static int pfkey_promisc(struct sock *sk, struct sk_buff *skb, const struct sadb
 		new_hdr->sadb_msg_errno = 0;
 	}
 
-	pfkey_broadcast(skb, BROADCAST_ALL, NULL, sock_net(sk));
+	pfkey_broadcast(skb, GFP_KERNEL, BROADCAST_ALL, NULL, sock_net(sk));
 	return 0;
 }
 
@@ -2219,7 +2220,7 @@ static int key_notify_policy(struct xfrm_policy *xp, int dir, const struct km_ev
 	out_hdr->sadb_msg_errno = 0;
 	out_hdr->sadb_msg_seq = c->seq;
 	out_hdr->sadb_msg_pid = c->portid;
-	pfkey_broadcast(out_skb, BROADCAST_ALL, NULL, xp_net(xp));
+	pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ALL, NULL, xp_net(xp));
 	return 0;
 
 }
@@ -2439,7 +2440,7 @@ static int key_pol_get_resp(struct sock *sk, struct xfrm_policy *xp, const struc
 	out_hdr->sadb_msg_errno = 0;
 	out_hdr->sadb_msg_seq = hdr->sadb_msg_seq;
 	out_hdr->sadb_msg_pid = hdr->sadb_msg_pid;
-	pfkey_broadcast(out_skb, BROADCAST_ONE, sk, xp_net(xp));
+	pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ONE, sk, xp_net(xp));
 	err = 0;
 
 out:
@@ -2695,7 +2696,7 @@ static int dump_sp(struct xfrm_policy *xp, int dir, int count, void *ptr)
 	out_hdr->sadb_msg_pid = pfk->dump.msg_portid;
 
 	if (pfk->dump.skb)
-		pfkey_broadcast(pfk->dump.skb, BROADCAST_ONE,
+		pfkey_broadcast(pfk->dump.skb, GFP_ATOMIC, BROADCAST_ONE,
 				&pfk->sk, sock_net(&pfk->sk));
 	pfk->dump.skb = out_skb;
 
@@ -2752,7 +2753,7 @@ static int key_notify_policy_flush(const struct km_event *c)
 	hdr->sadb_msg_satype = SADB_SATYPE_UNSPEC;
 	hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t));
 	hdr->sadb_msg_reserved = 0;
-	pfkey_broadcast(skb_out, BROADCAST_ALL, NULL, c->net);
+	pfkey_broadcast(skb_out, GFP_ATOMIC, BROADCAST_ALL, NULL, c->net);
 	return 0;
 
 }
@@ -2814,7 +2815,7 @@ static int pfkey_process(struct sock *sk, struct sk_buff *skb, const struct sadb
 	void *ext_hdrs[SADB_EXT_MAX];
 	int err;
 
-	pfkey_broadcast(skb_clone(skb, GFP_KERNEL),
+	pfkey_broadcast(skb_clone(skb, GFP_KERNEL), GFP_KERNEL,
 			BROADCAST_PROMISC_ONLY, NULL, sock_net(sk));
 
 	memset(ext_hdrs, 0, sizeof(ext_hdrs));
@@ -3036,7 +3037,8 @@ static int key_notify_sa_expire(struct xfrm_state *x, const struct km_event *c)
 	out_hdr->sadb_msg_seq = 0;
 	out_hdr->sadb_msg_pid = 0;
 
-	pfkey_broadcast(out_skb, BROADCAST_REGISTERED, NULL, xs_net(x));
+	pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_REGISTERED, NULL,
+			xs_net(x));
 	return 0;
 }
 
@@ -3226,7 +3228,8 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct
 		       xfrm_ctx->ctx_len);
 	}
 
-	return pfkey_broadcast(skb, BROADCAST_REGISTERED, NULL, xs_net(x));
+	return pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_REGISTERED, NULL,
+			       xs_net(x));
 }
 
 static struct xfrm_policy *pfkey_compile_policy(struct sock *sk, int opt,
@@ -3424,7 +3427,8 @@ static int pfkey_send_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr,
 	n_port->sadb_x_nat_t_port_port = sport;
 	n_port->sadb_x_nat_t_port_reserved = 0;
 
-	return pfkey_broadcast(skb, BROADCAST_REGISTERED, NULL, xs_net(x));
+	return pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_REGISTERED, NULL,
+			       xs_net(x));
 }
 
 #ifdef CONFIG_NET_KEY_MIGRATE
@@ -3616,7 +3620,7 @@ static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 	}
 
 	/* broadcast migrate message to sockets */
-	pfkey_broadcast(skb, BROADCAST_ALL, NULL, &init_net);
+	pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, &init_net);
 
 	return 0;
 
-- 
2.13.5


From e3370ac8dcdc599191b7af0cf90229488b6b449c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 14 Aug 2017 14:10:25 -0700
Subject: [PATCH 02/25] dccp: purge write queue in dccp_destroy_sock()

[ Upstream commit 7749d4ff88d31b0be17c8683143135adaaadc6a7 ]

syzkaller reported that DCCP could have a non empty
write queue at dismantle time.

WARNING: CPU: 1 PID: 2953 at net/core/stream.c:199 sk_stream_kill_queues+0x3ce/0x520 net/core/stream.c:199
Kernel panic - not syncing: panic_on_warn set ...

CPU: 1 PID: 2953 Comm: syz-executor0 Not tainted 4.13.0-rc4+ #2
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:16 [inline]
 dump_stack+0x194/0x257 lib/dump_stack.c:52
 panic+0x1e4/0x417 kernel/panic.c:180
 __warn+0x1c4/0x1d9 kernel/panic.c:541
 report_bug+0x211/0x2d0 lib/bug.c:183
 fixup_bug+0x40/0x90 arch/x86/kernel/traps.c:190
 do_trap_no_signal arch/x86/kernel/traps.c:224 [inline]
 do_trap+0x260/0x390 arch/x86/kernel/traps.c:273
 do_error_trap+0x120/0x390 arch/x86/kernel/traps.c:310
 do_invalid_op+0x1b/0x20 arch/x86/kernel/traps.c:323
 invalid_op+0x1e/0x30 arch/x86/entry/entry_64.S:846
RIP: 0010:sk_stream_kill_queues+0x3ce/0x520 net/core/stream.c:199
RSP: 0018:ffff8801d182f108 EFLAGS: 00010297
RAX: ffff8801d1144140 RBX: ffff8801d13cb280 RCX: 0000000000000000
RDX: 0000000000000000 RSI: ffffffff85137b00 RDI: ffff8801d13cb280
RBP: ffff8801d182f148 R08: 0000000000000001 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: ffff8801d13cb4d0
R13: ffff8801d13cb3b8 R14: ffff8801d13cb300 R15: ffff8801d13cb3b8
 inet_csk_destroy_sock+0x175/0x3f0 net/ipv4/inet_connection_sock.c:835
 dccp_close+0x84d/0xc10 net/dccp/proto.c:1067
 inet_release+0xed/0x1c0 net/ipv4/af_inet.c:425
 sock_release+0x8d/0x1e0 net/socket.c:597
 sock_close+0x16/0x20 net/socket.c:1126
 __fput+0x327/0x7e0 fs/file_table.c:210
 ____fput+0x15/0x20 fs/file_table.c:246
 task_work_run+0x18a/0x260 kernel/task_work.c:116
 exit_task_work include/linux/task_work.h:21 [inline]
 do_exit+0xa32/0x1b10 kernel/exit.c:865
 do_group_exit+0x149/0x400 kernel/exit.c:969
 get_signal+0x7e8/0x17e0 kernel/signal.c:2330
 do_signal+0x94/0x1ee0 arch/x86/kernel/signal.c:808
 exit_to_usermode_loop+0x21c/0x2d0 arch/x86/entry/common.c:157
 prepare_exit_to_usermode arch/x86/entry/common.c:194 [inline]
 syscall_return_slowpath+0x3a7/0x450 arch/x86/entry/common.c:263

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/proto.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 9fe25bf63296..86bc40ba6ba5 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -201,10 +201,7 @@ void dccp_destroy_sock(struct sock *sk)
 {
 	struct dccp_sock *dp = dccp_sk(sk);
 
-	/*
-	 * DCCP doesn't use sk_write_queue, just sk_send_head
-	 * for retransmissions
-	 */
+	__skb_queue_purge(&sk->sk_write_queue);
 	if (sk->sk_send_head != NULL) {
 		kfree_skb(sk->sk_send_head);
 		sk->sk_send_head = NULL;
-- 
2.13.5


From 5db71c4f638b0853d86c4c44dadf749e62dd91af Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 16 Aug 2017 07:03:15 -0700
Subject: [PATCH 03/25] dccp: defer ccid_hc_tx_delete() at dismantle time

[ Upstream commit 120e9dabaf551c6dc03d3a10a1f026376cb1811c ]

syszkaller team reported another problem in DCCP [1]

Problem here is that the structure holding RTO timer
(ccid2_hc_tx_rto_expire() handler) is freed too soon.

We can not use del_timer_sync() to cancel the timer
since this timer wants to grab socket lock (that would risk a dead lock)

Solution is to defer the freeing of memory when all references to
the socket were released. Socket timers do own a reference, so this
should fix the issue.

[1]

==================================================================
BUG: KASAN: use-after-free in ccid2_hc_tx_rto_expire+0x51c/0x5c0 net/dccp/ccids/ccid2.c:144
Read of size 4 at addr ffff8801d2660540 by task kworker/u4:7/3365

CPU: 1 PID: 3365 Comm: kworker/u4:7 Not tainted 4.13.0-rc4+ #3
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Workqueue: events_unbound call_usermodehelper_exec_work
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:16 [inline]
 dump_stack+0x194/0x257 lib/dump_stack.c:52
 print_address_description+0x73/0x250 mm/kasan/report.c:252
 kasan_report_error mm/kasan/report.c:351 [inline]
 kasan_report+0x24e/0x340 mm/kasan/report.c:409
 __asan_report_load4_noabort+0x14/0x20 mm/kasan/report.c:429
 ccid2_hc_tx_rto_expire+0x51c/0x5c0 net/dccp/ccids/ccid2.c:144
 call_timer_fn+0x233/0x830 kernel/time/timer.c:1268
 expire_timers kernel/time/timer.c:1307 [inline]
 __run_timers+0x7fd/0xb90 kernel/time/timer.c:1601
 run_timer_softirq+0x21/0x80 kernel/time/timer.c:1614
 __do_softirq+0x2f5/0xba3 kernel/softirq.c:284
 invoke_softirq kernel/softirq.c:364 [inline]
 irq_exit+0x1cc/0x200 kernel/softirq.c:405
 exiting_irq arch/x86/include/asm/apic.h:638 [inline]
 smp_apic_timer_interrupt+0x76/0xa0 arch/x86/kernel/apic/apic.c:1044
 apic_timer_interrupt+0x93/0xa0 arch/x86/entry/entry_64.S:702
RIP: 0010:arch_local_irq_enable arch/x86/include/asm/paravirt.h:824 [inline]
RIP: 0010:__raw_write_unlock_irq include/linux/rwlock_api_smp.h:267 [inline]
RIP: 0010:_raw_write_unlock_irq+0x56/0x70 kernel/locking/spinlock.c:343
RSP: 0018:ffff8801cd50eaa8 EFLAGS: 00000286 ORIG_RAX: ffffffffffffff10
RAX: dffffc0000000000 RBX: ffffffff85a090c0 RCX: 0000000000000006
RDX: 1ffffffff0b595f3 RSI: 1ffff1003962f989 RDI: ffffffff85acaf98
RBP: ffff8801cd50eab0 R08: 0000000000000001 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: ffff8801cc96ea60
R13: dffffc0000000000 R14: ffff8801cc96e4c0 R15: ffff8801cc96e4c0
 </IRQ>
 release_task+0xe9e/0x1a40 kernel/exit.c:220
 wait_task_zombie kernel/exit.c:1162 [inline]
 wait_consider_task+0x29b8/0x33c0 kernel/exit.c:1389
 do_wait_thread kernel/exit.c:1452 [inline]
 do_wait+0x441/0xa90 kernel/exit.c:1523
 kernel_wait4+0x1f5/0x370 kernel/exit.c:1665
 SYSC_wait4+0x134/0x140 kernel/exit.c:1677
 SyS_wait4+0x2c/0x40 kernel/exit.c:1673
 call_usermodehelper_exec_sync kernel/kmod.c:286 [inline]
 call_usermodehelper_exec_work+0x1a0/0x2c0 kernel/kmod.c:323
 process_one_work+0xbf3/0x1bc0 kernel/workqueue.c:2097
 worker_thread+0x223/0x1860 kernel/workqueue.c:2231
 kthread+0x35e/0x430 kernel/kthread.c:231
 ret_from_fork+0x2a/0x40 arch/x86/entry/entry_64.S:425

Allocated by task 21267:
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
 save_stack+0x43/0xd0 mm/kasan/kasan.c:447
 set_track mm/kasan/kasan.c:459 [inline]
 kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:551
 kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:489
 kmem_cache_alloc+0x127/0x750 mm/slab.c:3561
 ccid_new+0x20e/0x390 net/dccp/ccid.c:151
 dccp_hdlr_ccid+0x27/0x140 net/dccp/feat.c:44
 __dccp_feat_activate+0x142/0x2a0 net/dccp/feat.c:344
 dccp_feat_activate_values+0x34e/0xa90 net/dccp/feat.c:1538
 dccp_rcv_request_sent_state_process net/dccp/input.c:472 [inline]
 dccp_rcv_state_process+0xed1/0x1620 net/dccp/input.c:677
 dccp_v4_do_rcv+0xeb/0x160 net/dccp/ipv4.c:679
 sk_backlog_rcv include/net/sock.h:911 [inline]
 __release_sock+0x124/0x360 net/core/sock.c:2269
 release_sock+0xa4/0x2a0 net/core/sock.c:2784
 inet_wait_for_connect net/ipv4/af_inet.c:557 [inline]
 __inet_stream_connect+0x671/0xf00 net/ipv4/af_inet.c:643
 inet_stream_connect+0x58/0xa0 net/ipv4/af_inet.c:682
 SYSC_connect+0x204/0x470 net/socket.c:1642
 SyS_connect+0x24/0x30 net/socket.c:1623
 entry_SYSCALL_64_fastpath+0x1f/0xbe

Freed by task 3049:
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
 save_stack+0x43/0xd0 mm/kasan/kasan.c:447
 set_track mm/kasan/kasan.c:459 [inline]
 kasan_slab_free+0x71/0xc0 mm/kasan/kasan.c:524
 __cache_free mm/slab.c:3503 [inline]
 kmem_cache_free+0x77/0x280 mm/slab.c:3763
 ccid_hc_tx_delete+0xc5/0x100 net/dccp/ccid.c:190
 dccp_destroy_sock+0x1d1/0x2b0 net/dccp/proto.c:225
 inet_csk_destroy_sock+0x166/0x3f0 net/ipv4/inet_connection_sock.c:833
 dccp_done+0xb7/0xd0 net/dccp/proto.c:145
 dccp_time_wait+0x13d/0x300 net/dccp/minisocks.c:72
 dccp_rcv_reset+0x1d1/0x5b0 net/dccp/input.c:160
 dccp_rcv_state_process+0x8fc/0x1620 net/dccp/input.c:663
 dccp_v4_do_rcv+0xeb/0x160 net/dccp/ipv4.c:679
 sk_backlog_rcv include/net/sock.h:911 [inline]
 __sk_receive_skb+0x33e/0xc00 net/core/sock.c:521
 dccp_v4_rcv+0xef1/0x1c00 net/dccp/ipv4.c:871
 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216
 NF_HOOK include/linux/netfilter.h:248 [inline]
 ip_local_deliver+0x1ce/0x6d0 net/ipv4/ip_input.c:257
 dst_input include/net/dst.h:477 [inline]
 ip_rcv_finish+0x8db/0x19c0 net/ipv4/ip_input.c:397
 NF_HOOK include/linux/netfilter.h:248 [inline]
 ip_rcv+0xc3f/0x17d0 net/ipv4/ip_input.c:488
 __netif_receive_skb_core+0x19af/0x33d0 net/core/dev.c:4417
 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4455
 process_backlog+0x203/0x740 net/core/dev.c:5130
 napi_poll net/core/dev.c:5527 [inline]
 net_rx_action+0x792/0x1910 net/core/dev.c:5593
 __do_softirq+0x2f5/0xba3 kernel/softirq.c:284

The buggy address belongs to the object at ffff8801d2660100
 which belongs to the cache ccid2_hc_tx_sock of size 1240
The buggy address is located 1088 bytes inside of
 1240-byte region [ffff8801d2660100, ffff8801d26605d8)
The buggy address belongs to the page:
page:ffffea0007499800 count:1 mapcount:0 mapping:ffff8801d2660100 index:0x0 compound_mapcount: 0
flags: 0x200000000008100(slab|head)
raw: 0200000000008100 ffff8801d2660100 0000000000000000 0000000100000005
raw: ffffea00075271a0 ffffea0007538820 ffff8801d3aef9c0 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff8801d2660400: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff8801d2660480: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff8801d2660500: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                                           ^
 ffff8801d2660580: fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc fc
 ffff8801d2660600: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
==================================================================

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/proto.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 86bc40ba6ba5..b68168fcc06a 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -24,6 +24,7 @@
 #include <net/checksum.h>
 
 #include <net/inet_sock.h>
+#include <net/inet_common.h>
 #include <net/sock.h>
 #include <net/xfrm.h>
 
@@ -170,6 +171,15 @@ const char *dccp_packet_name(const int type)
 
 EXPORT_SYMBOL_GPL(dccp_packet_name);
 
+static void dccp_sk_destruct(struct sock *sk)
+{
+	struct dccp_sock *dp = dccp_sk(sk);
+
+	ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk);
+	dp->dccps_hc_tx_ccid = NULL;
+	inet_sock_destruct(sk);
+}
+
 int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized)
 {
 	struct dccp_sock *dp = dccp_sk(sk);
@@ -179,6 +189,7 @@ int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized)
 	icsk->icsk_syn_retries	= sysctl_dccp_request_retries;
 	sk->sk_state		= DCCP_CLOSED;
 	sk->sk_write_space	= dccp_write_space;
+	sk->sk_destruct		= dccp_sk_destruct;
 	icsk->icsk_sync_mss	= dccp_sync_mss;
 	dp->dccps_mss_cache	= 536;
 	dp->dccps_rate_last	= jiffies;
@@ -219,8 +230,7 @@ void dccp_destroy_sock(struct sock *sk)
 		dp->dccps_hc_rx_ackvec = NULL;
 	}
 	ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk);
-	ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk);
-	dp->dccps_hc_rx_ccid = dp->dccps_hc_tx_ccid = NULL;
+	dp->dccps_hc_rx_ccid = NULL;
 
 	/* clean up feature negotiation state */
 	dccp_feat_list_purge(&dp->dccps_featneg);
-- 
2.13.5


From 261a7e0f954a3a2c3d4cde558e1c9b64a0059812 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 15 Aug 2017 05:26:17 -0700
Subject: [PATCH 04/25] ipv4: fix NULL dereference in free_fib_info_rcu()

[ Upstream commit 187e5b3ac84d3421d2de3aca949b2791fbcad554 ]

If fi->fib_metrics could not be allocated in fib_create_info()
we attempt to dereference a NULL pointer in free_fib_info_rcu() :

    m = fi->fib_metrics;
    if (m != &dst_default_metrics && atomic_dec_and_test(&m->refcnt))
            kfree(m);

Before my recent patch, we used to call kfree(NULL) and nothing wrong
happened.

Instead of using RCU to defer freeing while we are under memory stress,
it seems better to take immediate action.

This was reported by syzkaller team.

Fixes: 3fb07daff8e9 ("ipv4: add reference counting to metrics")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_semantics.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 7563831fa432..38c1c979ecb1 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1044,15 +1044,17 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 	fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL);
 	if (!fi)
 		goto failure;
-	fib_info_cnt++;
 	if (cfg->fc_mx) {
 		fi->fib_metrics = kzalloc(sizeof(*fi->fib_metrics), GFP_KERNEL);
-		if (!fi->fib_metrics)
-			goto failure;
+		if (unlikely(!fi->fib_metrics)) {
+			kfree(fi);
+			return ERR_PTR(err);
+		}
 		atomic_set(&fi->fib_metrics->refcnt, 1);
-	} else
+	} else {
 		fi->fib_metrics = (struct dst_metrics *)&dst_default_metrics;
-
+	}
+	fib_info_cnt++;
 	fi->fib_net = net;
 	fi->fib_protocol = cfg->fc_protocol;
 	fi->fib_scope = cfg->fc_scope;
-- 
2.13.5


From 473e538fe6aa691b702f9d454748a6751f4d86e8 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Date: Tue, 15 Aug 2017 16:37:04 +0300
Subject: [PATCH 05/25] net_sched/sfq: update hierarchical backlog when drop
 packet

[ Upstream commit 325d5dc3f7e7c2840b65e4a2988c082c2c0025c5 ]

When sfq_enqueue() drops head packet or packet from another queue it
have to update backlog at upper qdiscs too.

Fixes: 2ccccf5fb43f ("net_sched: update hierarchical backlog too")
Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_sfq.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index bc5e99584e41..ea8a56f76b32 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -434,6 +434,7 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
 		qdisc_drop(head, sch, to_free);
 
 		slot_queue_add(slot, skb);
+		qdisc_tree_reduce_backlog(sch, 0, delta);
 		return NET_XMIT_CN;
 	}
 
@@ -465,8 +466,10 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
 	/* Return Congestion Notification only if we dropped a packet
 	 * from this flow.
 	 */
-	if (qlen != slot->qlen)
+	if (qlen != slot->qlen) {
+		qdisc_tree_reduce_backlog(sch, 0, dropped - qdisc_pkt_len(skb));
 		return NET_XMIT_CN;
+	}
 
 	/* As we dropped a packet, better let upper stack know this */
 	qdisc_tree_reduce_backlog(sch, 1, dropped);
-- 
2.13.5


From 6e38092120c8a1adda0e680becae64b8351bebcd Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Date: Tue, 15 Aug 2017 16:39:05 +0300
Subject: [PATCH 06/25] net_sched: remove warning from qdisc_hash_add

[ Upstream commit c90e95147c27b1780e76c6e8fea1b5c78d7d387f ]

It was added in commit e57a784d8cae ("pkt_sched: set root qdisc
before change() in attach_default_qdiscs()") to hide duplicates
from "tc qdisc show" for incative deivices.

After 59cc1f61f ("net: sched: convert qdisc linked list to hashtable")
it triggered when classful qdisc is added to inactive device because
default qdiscs are added before switching root qdisc.

Anyway after commit ea3274695353 ("net: sched: avoid duplicates in
qdisc dump") duplicates are filtered right in dumper.

Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_api.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index ff27a85a71a9..195a3b2d9afc 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -277,9 +277,6 @@ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle)
 void qdisc_hash_add(struct Qdisc *q)
 {
 	if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) {
-		struct Qdisc *root = qdisc_dev(q)->qdisc;
-
-		WARN_ON_ONCE(root == &noop_qdisc);
 		ASSERT_RTNL();
 		hash_add_rcu(qdisc_dev(q)->qdisc_hash, &q->hash, q->handle);
 	}
-- 
2.13.5


From 2536fc56659c822c8a21793315a1fd430c8a0258 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 16 Aug 2017 01:45:33 +0200
Subject: [PATCH 07/25] bpf: fix bpf_trace_printk on 32 bit archs

[ Upstream commit 88a5c690b66110ad255380d8f629c629cf6ca559 ]

James reported that on MIPS32 bpf_trace_printk() is currently
broken while MIPS64 works fine:

  bpf_trace_printk() uses conditional operators to attempt to
  pass different types to __trace_printk() depending on the
  format operators. This doesn't work as intended on 32-bit
  architectures where u32 and long are passed differently to
  u64, since the result of C conditional operators follows the
  "usual arithmetic conversions" rules, such that the values
  passed to __trace_printk() will always be u64 [causing issues
  later in the va_list handling for vscnprintf()].

  For example the samples/bpf/tracex5 test printed lines like
  below on MIPS32, where the fd and buf have come from the u64
  fd argument, and the size from the buf argument:

    [...] 1180.941542: 0x00000001: write(fd=1, buf=  (null), size=6258688)

  Instead of this:

    [...] 1625.616026: 0x00000001: write(fd=1, buf=009e4000, size=512)

One way to get it working is to expand various combinations
of argument types into 8 different combinations for 32 bit
and 64 bit kernels. Fix tested by James on MIPS32 and MIPS64
as well that it resolves the issue.

Fixes: 9c959c863f82 ("tracing: Allow BPF programs to call bpf_trace_printk()")
Reported-by: James Hogan <james.hogan@imgtec.com>
Tested-by: James Hogan <james.hogan@imgtec.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/trace/bpf_trace.c | 34 ++++++++++++++++++++++++++++++----
 1 file changed, 30 insertions(+), 4 deletions(-)

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 5dcb99281259..41805fb3c661 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -203,10 +203,36 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
 		fmt_cnt++;
 	}
 
-	return __trace_printk(1/* fake ip will not be printed */, fmt,
-			      mod[0] == 2 ? arg1 : mod[0] == 1 ? (long) arg1 : (u32) arg1,
-			      mod[1] == 2 ? arg2 : mod[1] == 1 ? (long) arg2 : (u32) arg2,
-			      mod[2] == 2 ? arg3 : mod[2] == 1 ? (long) arg3 : (u32) arg3);
+/* Horrid workaround for getting va_list handling working with different
+ * argument type combinations generically for 32 and 64 bit archs.
+ */
+#define __BPF_TP_EMIT()	__BPF_ARG3_TP()
+#define __BPF_TP(...)							\
+	__trace_printk(1 /* Fake ip will not be printed. */,		\
+		       fmt, ##__VA_ARGS__)
+
+#define __BPF_ARG1_TP(...)						\
+	((mod[0] == 2 || (mod[0] == 1 && __BITS_PER_LONG == 64))	\
+	  ? __BPF_TP(arg1, ##__VA_ARGS__)				\
+	  : ((mod[0] == 1 || (mod[0] == 0 && __BITS_PER_LONG == 32))	\
+	      ? __BPF_TP((long)arg1, ##__VA_ARGS__)			\
+	      : __BPF_TP((u32)arg1, ##__VA_ARGS__)))
+
+#define __BPF_ARG2_TP(...)						\
+	((mod[1] == 2 || (mod[1] == 1 && __BITS_PER_LONG == 64))	\
+	  ? __BPF_ARG1_TP(arg2, ##__VA_ARGS__)				\
+	  : ((mod[1] == 1 || (mod[1] == 0 && __BITS_PER_LONG == 32))	\
+	      ? __BPF_ARG1_TP((long)arg2, ##__VA_ARGS__)		\
+	      : __BPF_ARG1_TP((u32)arg2, ##__VA_ARGS__)))
+
+#define __BPF_ARG3_TP(...)						\
+	((mod[2] == 2 || (mod[2] == 1 && __BITS_PER_LONG == 64))	\
+	  ? __BPF_ARG2_TP(arg3, ##__VA_ARGS__)				\
+	  : ((mod[2] == 1 || (mod[2] == 0 && __BITS_PER_LONG == 32))	\
+	      ? __BPF_ARG2_TP((long)arg3, ##__VA_ARGS__)		\
+	      : __BPF_ARG2_TP((u32)arg3, ##__VA_ARGS__)))
+
+	return __BPF_TP_EMIT();
 }
 
 static const struct bpf_func_proto bpf_trace_printk_proto = {
-- 
2.13.5


From 283a1ad21a47cd8b557c25258d36ac3cc6206e29 Mon Sep 17 00:00:00 2001
From: Liping Zhang <zlpnobody@gmail.com>
Date: Wed, 16 Aug 2017 13:30:07 +0800
Subject: [PATCH 08/25] openvswitch: fix skb_panic due to the incorrect actions
 attrlen

[ Upstream commit 494bea39f3201776cdfddc232705f54a0bd210c4 ]

For sw_flow_actions, the actions_len only represents the kernel part's
size, and when we dump the actions to the userspace, we will do the
convertions, so it's true size may become bigger than the actions_len.

But unfortunately, for OVS_PACKET_ATTR_ACTIONS, we use the actions_len
to alloc the skbuff, so the user_skb's size may become insufficient and
oops will happen like this:
  skbuff: skb_over_panic: text:ffffffff8148fabf len:1749 put:157 head:
  ffff881300f39000 data:ffff881300f39000 tail:0x6d5 end:0x6c0 dev:<NULL>
  ------------[ cut here ]------------
  kernel BUG at net/core/skbuff.c:129!
  [...]
  Call Trace:
   <IRQ>
   [<ffffffff8148be82>] skb_put+0x43/0x44
   [<ffffffff8148fabf>] skb_zerocopy+0x6c/0x1f4
   [<ffffffffa0290d36>] queue_userspace_packet+0x3a3/0x448 [openvswitch]
   [<ffffffffa0292023>] ovs_dp_upcall+0x30/0x5c [openvswitch]
   [<ffffffffa028d435>] output_userspace+0x132/0x158 [openvswitch]
   [<ffffffffa01e6890>] ? ip6_rcv_finish+0x74/0x77 [ipv6]
   [<ffffffffa028e277>] do_execute_actions+0xcc1/0xdc8 [openvswitch]
   [<ffffffffa028e3f2>] ovs_execute_actions+0x74/0x106 [openvswitch]
   [<ffffffffa0292130>] ovs_dp_process_packet+0xe1/0xfd [openvswitch]
   [<ffffffffa0292b77>] ? key_extract+0x63c/0x8d5 [openvswitch]
   [<ffffffffa029848b>] ovs_vport_receive+0xa1/0xc3 [openvswitch]
  [...]

Also we can find that the actions_len is much little than the orig_len:
  crash> struct sw_flow_actions 0xffff8812f539d000
  struct sw_flow_actions {
    rcu = {
      next = 0xffff8812f5398800,
      func = 0xffffe3b00035db32
    },
    orig_len = 1384,
    actions_len = 592,
    actions = 0xffff8812f539d01c
  }

So as a quick fix, use the orig_len instead of the actions_len to alloc
the user_skb.

Last, this oops happened on our system running a relative old kernel, but
the same risk still exists on the mainline, since we use the wrong
actions_len from the beginning.

Fixes: ccea74457bbd ("openvswitch: include datapath actions with sampled-packet upcall to userspace")
Cc: Neil McKee <neil.mckee@inmon.com>
Signed-off-by: Liping Zhang <zlpnobody@gmail.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/actions.c  | 1 +
 net/openvswitch/datapath.c | 7 ++++---
 net/openvswitch/datapath.h | 2 ++
 3 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 4e03f64709bc..05d9f42fc309 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -1240,6 +1240,7 @@ int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
 		goto out;
 	}
 
+	OVS_CB(skb)->acts_origlen = acts->orig_len;
 	err = do_execute_actions(dp, skb, key,
 				 acts->actions, acts->actions_len);
 
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 4d67ea856067..453f806afe6e 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -383,7 +383,7 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
 }
 
 static size_t upcall_msg_size(const struct dp_upcall_info *upcall_info,
-			      unsigned int hdrlen)
+			      unsigned int hdrlen, int actions_attrlen)
 {
 	size_t size = NLMSG_ALIGN(sizeof(struct ovs_header))
 		+ nla_total_size(hdrlen) /* OVS_PACKET_ATTR_PACKET */
@@ -400,7 +400,7 @@ static size_t upcall_msg_size(const struct dp_upcall_info *upcall_info,
 
 	/* OVS_PACKET_ATTR_ACTIONS */
 	if (upcall_info->actions_len)
-		size += nla_total_size(upcall_info->actions_len);
+		size += nla_total_size(actions_attrlen);
 
 	/* OVS_PACKET_ATTR_MRU */
 	if (upcall_info->mru)
@@ -467,7 +467,8 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 	else
 		hlen = skb->len;
 
-	len = upcall_msg_size(upcall_info, hlen - cutlen);
+	len = upcall_msg_size(upcall_info, hlen - cutlen,
+			      OVS_CB(skb)->acts_origlen);
 	user_skb = genlmsg_new(len, GFP_ATOMIC);
 	if (!user_skb) {
 		err = -ENOMEM;
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index ab85c1cae255..e19ace428e38 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -100,12 +100,14 @@ struct datapath {
  * @input_vport: The original vport packet came in on. This value is cached
  * when a packet is received by OVS.
  * @mru: The maximum received fragement size; 0 if the packet is not
+ * @acts_origlen: The netlink size of the flow actions applied to this skb.
  * @cutlen: The number of bytes from the packet end to be removed.
  * fragmented.
  */
 struct ovs_skb_cb {
 	struct vport		*input_vport;
 	u16			mru;
+	u16			acts_origlen;
 	u32			cutlen;
 };
 #define OVS_CB(skb) ((struct ovs_skb_cb *)(skb)->cb)
-- 
2.13.5


From b86f23def8a3b1a3447caa9d0ad485fff4990356 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 16 Aug 2017 10:36:47 -0700
Subject: [PATCH 09/25] ptr_ring: use kmalloc_array()

[ Upstream commit 81fbfe8adaf38d4f5a98c19bebfd41c5d6acaee8 ]

As found by syzkaller, malicious users can set whatever tx_queue_len
on a tun device and eventually crash the kernel.

Lets remove the ALIGN(XXX, SMP_CACHE_BYTES) thing since a small
ring buffer is not fast anyway.

Fixes: 2e0ab8ca83c1 ("ptr_ring: array based FIFO for pointers")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ptr_ring.h  | 9 +++++----
 include/linux/skb_array.h | 3 ++-
 2 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h
index 6c70444da3b9..b83507c0640c 100644
--- a/include/linux/ptr_ring.h
+++ b/include/linux/ptr_ring.h
@@ -340,9 +340,9 @@ static inline void *ptr_ring_consume_bh(struct ptr_ring *r)
 	__PTR_RING_PEEK_CALL_v; \
 })
 
-static inline void **__ptr_ring_init_queue_alloc(int size, gfp_t gfp)
+static inline void **__ptr_ring_init_queue_alloc(unsigned int size, gfp_t gfp)
 {
-	return kzalloc(ALIGN(size * sizeof(void *), SMP_CACHE_BYTES), gfp);
+	return kcalloc(size, sizeof(void *), gfp);
 }
 
 static inline int ptr_ring_init(struct ptr_ring *r, int size, gfp_t gfp)
@@ -417,7 +417,8 @@ static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp,
  * In particular if you consume ring in interrupt or BH context, you must
  * disable interrupts/BH when doing so.
  */
-static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, int nrings,
+static inline int ptr_ring_resize_multiple(struct ptr_ring **rings,
+					   unsigned int nrings,
 					   int size,
 					   gfp_t gfp, void (*destroy)(void *))
 {
@@ -425,7 +426,7 @@ static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, int nrings,
 	void ***queues;
 	int i;
 
-	queues = kmalloc(nrings * sizeof *queues, gfp);
+	queues = kmalloc_array(nrings, sizeof(*queues), gfp);
 	if (!queues)
 		goto noqueues;
 
diff --git a/include/linux/skb_array.h b/include/linux/skb_array.h
index f4dfade428f0..be8b902b5845 100644
--- a/include/linux/skb_array.h
+++ b/include/linux/skb_array.h
@@ -162,7 +162,8 @@ static inline int skb_array_resize(struct skb_array *a, int size, gfp_t gfp)
 }
 
 static inline int skb_array_resize_multiple(struct skb_array **rings,
-					    int nrings, int size, gfp_t gfp)
+					    int nrings, unsigned int size,
+					    gfp_t gfp)
 {
 	BUILD_BUG_ON(offsetof(struct skb_array, ring));
 	return ptr_ring_resize_multiple((struct ptr_ring **)rings,
-- 
2.13.5


From a99d77acad082de1ca1906d47b6a08938239bd6a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 16 Aug 2017 11:09:12 -0700
Subject: [PATCH 10/25] ipv4: better IP_MAX_MTU enforcement

[ Upstream commit c780a049f9bf442314335372c9abc4548bfe3e44 ]

While working on yet another syzkaller report, I found
that our IP_MAX_MTU enforcements were not properly done.

gcc seems to reload dev->mtu for min(dev->mtu, IP_MAX_MTU), and
final result can be bigger than IP_MAX_MTU :/

This is a problem because device mtu can be changed on other cpus or
threads.

While this patch does not fix the issue I am working on, it is
probably worth addressing it.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h | 4 ++--
 net/ipv4/route.c | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index d3a107850a41..51c6b9786c46 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -339,7 +339,7 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst,
 	    !forwarding)
 		return dst_mtu(dst);
 
-	return min(dst->dev->mtu, IP_MAX_MTU);
+	return min(READ_ONCE(dst->dev->mtu), IP_MAX_MTU);
 }
 
 static inline unsigned int ip_skb_dst_mtu(struct sock *sk,
@@ -351,7 +351,7 @@ static inline unsigned int ip_skb_dst_mtu(struct sock *sk,
 		return ip_dst_mtu_maybe_forward(skb_dst(skb), forwarding);
 	}
 
-	return min(skb_dst(skb)->dev->mtu, IP_MAX_MTU);
+	return min(READ_ONCE(skb_dst(skb)->dev->mtu), IP_MAX_MTU);
 }
 
 u32 ip_idents_reserve(u32 hash, int segs);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 6cd49fd17ac0..6a5b7783932e 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1247,7 +1247,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst)
 	if (mtu)
 		return mtu;
 
-	mtu = dst->dev->mtu;
+	mtu = READ_ONCE(dst->dev->mtu);
 
 	if (unlikely(dst_metric_locked(dst, RTAX_MTU))) {
 		if (rt->rt_uses_gateway && mtu > 576)
-- 
2.13.5


From 7afaa3a7065889c1d1241056902e886f4444a567 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Fri, 18 Aug 2017 12:11:50 +0100
Subject: [PATCH 11/25] nfp: fix infinite loop on umapping cleanup

[ Upstream commit eac2c68d663effb077210218788952b5a0c1f60e ]

The while loop that performs the dma page unmapping never decrements
index counter f and hence loops forever. Fix this with a pre-decrement
on f.

Detected by CoverityScan, CID#1357309 ("Infinite loop")

Fixes: 4c3523623dc0 ("net: add driver for Netronome NFP4000/NFP6000 NIC VFs")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index aee3fd2b6538..4ca82bd8c4f0 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -871,8 +871,7 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
 	return NETDEV_TX_OK;
 
 err_unmap:
-	--f;
-	while (f >= 0) {
+	while (--f >= 0) {
 		frag = &skb_shinfo(skb)->frags[f];
 		dma_unmap_page(&nn->pdev->dev,
 			       tx_ring->txbufs[wr_idx].dma_addr,
-- 
2.13.5


From baf3d6d1470d8e8af92e5841fa28728bf6f43479 Mon Sep 17 00:00:00 2001
From: Alexander Potapenko <glider@google.com>
Date: Wed, 16 Aug 2017 20:16:40 +0200
Subject: [PATCH 12/25] sctp: fully initialize the IPv6 address in
 sctp_v6_to_addr()

[ Upstream commit 15339e441ec46fbc3bf3486bb1ae4845b0f1bb8d ]

KMSAN reported use of uninitialized sctp_addr->v4.sin_addr.s_addr and
sctp_addr->v6.sin6_scope_id in sctp_v6_cmp_addr() (see below).
Make sure all fields of an IPv6 address are initialized, which
guarantees that the IPv4 fields are also initialized.

==================================================================
 BUG: KMSAN: use of uninitialized memory in sctp_v6_cmp_addr+0x8d4/0x9f0
 net/sctp/ipv6.c:517
 CPU: 2 PID: 31056 Comm: syz-executor1 Not tainted 4.11.0-rc5+ #2944
 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs
 01/01/2011
 Call Trace:
  dump_stack+0x172/0x1c0 lib/dump_stack.c:42
  is_logbuf_locked mm/kmsan/kmsan.c:59 [inline]
  kmsan_report+0x12a/0x180 mm/kmsan/kmsan.c:938
  native_save_fl arch/x86/include/asm/irqflags.h:18 [inline]
  arch_local_save_flags arch/x86/include/asm/irqflags.h:72 [inline]
  arch_local_irq_save arch/x86/include/asm/irqflags.h:113 [inline]
  __msan_warning_32+0x61/0xb0 mm/kmsan/kmsan_instr.c:467
  sctp_v6_cmp_addr+0x8d4/0x9f0 net/sctp/ipv6.c:517
  sctp_v6_get_dst+0x8c7/0x1630 net/sctp/ipv6.c:290
  sctp_transport_route+0x101/0x570 net/sctp/transport.c:292
  sctp_assoc_add_peer+0x66d/0x16f0 net/sctp/associola.c:651
  sctp_sendmsg+0x35a5/0x4f90 net/sctp/socket.c:1871
  inet_sendmsg+0x498/0x670 net/ipv4/af_inet.c:762
  sock_sendmsg_nosec net/socket.c:633 [inline]
  sock_sendmsg net/socket.c:643 [inline]
  SYSC_sendto+0x608/0x710 net/socket.c:1696
  SyS_sendto+0x8a/0xb0 net/socket.c:1664
  entry_SYSCALL_64_fastpath+0x13/0x94
 RIP: 0033:0x44b479
 RSP: 002b:00007f6213f21c08 EFLAGS: 00000286 ORIG_RAX: 000000000000002c
 RAX: ffffffffffffffda RBX: 0000000020000000 RCX: 000000000044b479
 RDX: 0000000000000041 RSI: 0000000020edd000 RDI: 0000000000000006
 RBP: 00000000007080a8 R08: 0000000020b85fe4 R09: 000000000000001c
 R10: 0000000000040005 R11: 0000000000000286 R12: 00000000ffffffff
 R13: 0000000000003760 R14: 00000000006e5820 R15: 0000000000ff8000
 origin description: ----dst_saddr@sctp_v6_get_dst
 local variable created at:
  sk_fullsock include/net/sock.h:2321 [inline]
  inet6_sk include/linux/ipv6.h:309 [inline]
  sctp_v6_get_dst+0x91/0x1630 net/sctp/ipv6.c:241
  sctp_transport_route+0x101/0x570 net/sctp/transport.c:292
==================================================================
 BUG: KMSAN: use of uninitialized memory in sctp_v6_cmp_addr+0x8d4/0x9f0
 net/sctp/ipv6.c:517
 CPU: 2 PID: 31056 Comm: syz-executor1 Not tainted 4.11.0-rc5+ #2944
 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs
 01/01/2011
 Call Trace:
  dump_stack+0x172/0x1c0 lib/dump_stack.c:42
  is_logbuf_locked mm/kmsan/kmsan.c:59 [inline]
  kmsan_report+0x12a/0x180 mm/kmsan/kmsan.c:938
  native_save_fl arch/x86/include/asm/irqflags.h:18 [inline]
  arch_local_save_flags arch/x86/include/asm/irqflags.h:72 [inline]
  arch_local_irq_save arch/x86/include/asm/irqflags.h:113 [inline]
  __msan_warning_32+0x61/0xb0 mm/kmsan/kmsan_instr.c:467
  sctp_v6_cmp_addr+0x8d4/0x9f0 net/sctp/ipv6.c:517
  sctp_v6_get_dst+0x8c7/0x1630 net/sctp/ipv6.c:290
  sctp_transport_route+0x101/0x570 net/sctp/transport.c:292
  sctp_assoc_add_peer+0x66d/0x16f0 net/sctp/associola.c:651
  sctp_sendmsg+0x35a5/0x4f90 net/sctp/socket.c:1871
  inet_sendmsg+0x498/0x670 net/ipv4/af_inet.c:762
  sock_sendmsg_nosec net/socket.c:633 [inline]
  sock_sendmsg net/socket.c:643 [inline]
  SYSC_sendto+0x608/0x710 net/socket.c:1696
  SyS_sendto+0x8a/0xb0 net/socket.c:1664
  entry_SYSCALL_64_fastpath+0x13/0x94
 RIP: 0033:0x44b479
 RSP: 002b:00007f6213f21c08 EFLAGS: 00000286 ORIG_RAX: 000000000000002c
 RAX: ffffffffffffffda RBX: 0000000020000000 RCX: 000000000044b479
 RDX: 0000000000000041 RSI: 0000000020edd000 RDI: 0000000000000006
 RBP: 00000000007080a8 R08: 0000000020b85fe4 R09: 000000000000001c
 R10: 0000000000040005 R11: 0000000000000286 R12: 00000000ffffffff
 R13: 0000000000003760 R14: 00000000006e5820 R15: 0000000000ff8000
 origin description: ----dst_saddr@sctp_v6_get_dst
 local variable created at:
  sk_fullsock include/net/sock.h:2321 [inline]
  inet6_sk include/linux/ipv6.h:309 [inline]
  sctp_v6_get_dst+0x91/0x1630 net/sctp/ipv6.c:241
  sctp_transport_route+0x101/0x570 net/sctp/transport.c:292
==================================================================

Signed-off-by: Alexander Potapenko <glider@google.com>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ipv6.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 0c090600f377..ca4a63e3eadd 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -512,7 +512,9 @@ static void sctp_v6_to_addr(union sctp_addr *addr, struct in6_addr *saddr,
 {
 	addr->sa.sa_family = AF_INET6;
 	addr->v6.sin6_port = port;
+	addr->v6.sin6_flowinfo = 0;
 	addr->v6.sin6_addr = *saddr;
+	addr->v6.sin6_scope_id = 0;
 }
 
 /* Compare addresses exactly.
-- 
2.13.5


From b5910da3749d1891338a6677ad2b951b7af9372e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 16 Aug 2017 09:41:54 -0700
Subject: [PATCH 13/25] tipc: fix use-after-free

[ Upstream commit 5bfd37b4de5c98e86b12bd13be5aa46c7484a125 ]

syszkaller reported use-after-free in tipc [1]

When msg->rep skb is freed, set the pointer to NULL,
so that caller does not free it again.

[1]

==================================================================
BUG: KASAN: use-after-free in skb_push+0xd4/0xe0 net/core/skbuff.c:1466
Read of size 8 at addr ffff8801c6e71e90 by task syz-executor5/4115

CPU: 1 PID: 4115 Comm: syz-executor5 Not tainted 4.13.0-rc4+ #32
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:16 [inline]
 dump_stack+0x194/0x257 lib/dump_stack.c:52
 print_address_description+0x73/0x250 mm/kasan/report.c:252
 kasan_report_error mm/kasan/report.c:351 [inline]
 kasan_report+0x24e/0x340 mm/kasan/report.c:409
 __asan_report_load8_noabort+0x14/0x20 mm/kasan/report.c:430
 skb_push+0xd4/0xe0 net/core/skbuff.c:1466
 tipc_nl_compat_recv+0x833/0x18f0 net/tipc/netlink_compat.c:1209
 genl_family_rcv_msg+0x7b7/0xfb0 net/netlink/genetlink.c:598
 genl_rcv_msg+0xb2/0x140 net/netlink/genetlink.c:623
 netlink_rcv_skb+0x216/0x440 net/netlink/af_netlink.c:2397
 genl_rcv+0x28/0x40 net/netlink/genetlink.c:634
 netlink_unicast_kernel net/netlink/af_netlink.c:1265 [inline]
 netlink_unicast+0x4e8/0x6f0 net/netlink/af_netlink.c:1291
 netlink_sendmsg+0xa4a/0xe60 net/netlink/af_netlink.c:1854
 sock_sendmsg_nosec net/socket.c:633 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:643
 sock_write_iter+0x31a/0x5d0 net/socket.c:898
 call_write_iter include/linux/fs.h:1743 [inline]
 new_sync_write fs/read_write.c:457 [inline]
 __vfs_write+0x684/0x970 fs/read_write.c:470
 vfs_write+0x189/0x510 fs/read_write.c:518
 SYSC_write fs/read_write.c:565 [inline]
 SyS_write+0xef/0x220 fs/read_write.c:557
 entry_SYSCALL_64_fastpath+0x1f/0xbe
RIP: 0033:0x4512e9
RSP: 002b:00007f3bc8184c08 EFLAGS: 00000216 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 0000000000718000 RCX: 00000000004512e9
RDX: 0000000000000020 RSI: 0000000020fdb000 RDI: 0000000000000006
RBP: 0000000000000086 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000216 R12: 00000000004b5e76
R13: 00007f3bc8184b48 R14: 00000000004b5e86 R15: 0000000000000000

Allocated by task 4115:
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
 save_stack+0x43/0xd0 mm/kasan/kasan.c:447
 set_track mm/kasan/kasan.c:459 [inline]
 kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:551
 kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:489
 kmem_cache_alloc_node+0x13d/0x750 mm/slab.c:3651
 __alloc_skb+0xf1/0x740 net/core/skbuff.c:219
 alloc_skb include/linux/skbuff.h:903 [inline]
 tipc_tlv_alloc+0x26/0xb0 net/tipc/netlink_compat.c:148
 tipc_nl_compat_dumpit+0xf2/0x3c0 net/tipc/netlink_compat.c:248
 tipc_nl_compat_handle net/tipc/netlink_compat.c:1130 [inline]
 tipc_nl_compat_recv+0x756/0x18f0 net/tipc/netlink_compat.c:1199
 genl_family_rcv_msg+0x7b7/0xfb0 net/netlink/genetlink.c:598
 genl_rcv_msg+0xb2/0x140 net/netlink/genetlink.c:623
 netlink_rcv_skb+0x216/0x440 net/netlink/af_netlink.c:2397
 genl_rcv+0x28/0x40 net/netlink/genetlink.c:634
 netlink_unicast_kernel net/netlink/af_netlink.c:1265 [inline]
 netlink_unicast+0x4e8/0x6f0 net/netlink/af_netlink.c:1291
 netlink_sendmsg+0xa4a/0xe60 net/netlink/af_netlink.c:1854
 sock_sendmsg_nosec net/socket.c:633 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:643
 sock_write_iter+0x31a/0x5d0 net/socket.c:898
 call_write_iter include/linux/fs.h:1743 [inline]
 new_sync_write fs/read_write.c:457 [inline]
 __vfs_write+0x684/0x970 fs/read_write.c:470
 vfs_write+0x189/0x510 fs/read_write.c:518
 SYSC_write fs/read_write.c:565 [inline]
 SyS_write+0xef/0x220 fs/read_write.c:557
 entry_SYSCALL_64_fastpath+0x1f/0xbe

Freed by task 4115:
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
 save_stack+0x43/0xd0 mm/kasan/kasan.c:447
 set_track mm/kasan/kasan.c:459 [inline]
 kasan_slab_free+0x71/0xc0 mm/kasan/kasan.c:524
 __cache_free mm/slab.c:3503 [inline]
 kmem_cache_free+0x77/0x280 mm/slab.c:3763
 kfree_skbmem+0x1a1/0x1d0 net/core/skbuff.c:622
 __kfree_skb net/core/skbuff.c:682 [inline]
 kfree_skb+0x165/0x4c0 net/core/skbuff.c:699
 tipc_nl_compat_dumpit+0x36a/0x3c0 net/tipc/netlink_compat.c:260
 tipc_nl_compat_handle net/tipc/netlink_compat.c:1130 [inline]
 tipc_nl_compat_recv+0x756/0x18f0 net/tipc/netlink_compat.c:1199
 genl_family_rcv_msg+0x7b7/0xfb0 net/netlink/genetlink.c:598
 genl_rcv_msg+0xb2/0x140 net/netlink/genetlink.c:623
 netlink_rcv_skb+0x216/0x440 net/netlink/af_netlink.c:2397
 genl_rcv+0x28/0x40 net/netlink/genetlink.c:634
 netlink_unicast_kernel net/netlink/af_netlink.c:1265 [inline]
 netlink_unicast+0x4e8/0x6f0 net/netlink/af_netlink.c:1291
 netlink_sendmsg+0xa4a/0xe60 net/netlink/af_netlink.c:1854
 sock_sendmsg_nosec net/socket.c:633 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:643
 sock_write_iter+0x31a/0x5d0 net/socket.c:898
 call_write_iter include/linux/fs.h:1743 [inline]
 new_sync_write fs/read_write.c:457 [inline]
 __vfs_write+0x684/0x970 fs/read_write.c:470
 vfs_write+0x189/0x510 fs/read_write.c:518
 SYSC_write fs/read_write.c:565 [inline]
 SyS_write+0xef/0x220 fs/read_write.c:557
 entry_SYSCALL_64_fastpath+0x1f/0xbe

The buggy address belongs to the object at ffff8801c6e71dc0
 which belongs to the cache skbuff_head_cache of size 224
The buggy address is located 208 bytes inside of
 224-byte region [ffff8801c6e71dc0, ffff8801c6e71ea0)
The buggy address belongs to the page:
page:ffffea00071b9c40 count:1 mapcount:0 mapping:ffff8801c6e71000 index:0x0
flags: 0x200000000000100(slab)
raw: 0200000000000100 ffff8801c6e71000 0000000000000000 000000010000000c
raw: ffffea0007224a20 ffff8801d98caf48 ffff8801d9e79040 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff8801c6e71d80: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb
 ffff8801c6e71e00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff8801c6e71e80: fb fb fb fb fc fc fc fc fc fc fc fc fc fc fc fc
                         ^
 ffff8801c6e71f00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 ffff8801c6e71f80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
==================================================================

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov  <dvyukov@google.com>
Cc: Jon Maloy <jon.maloy@ericsson.com>
Cc: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/netlink_compat.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 1fd464764765..aedc476fac02 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -258,13 +258,15 @@ static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd,
 	arg = nlmsg_new(0, GFP_KERNEL);
 	if (!arg) {
 		kfree_skb(msg->rep);
+		msg->rep = NULL;
 		return -ENOMEM;
 	}
 
 	err = __tipc_nl_compat_dumpit(cmd, msg, arg);
-	if (err)
+	if (err) {
 		kfree_skb(msg->rep);
-
+		msg->rep = NULL;
+	}
 	kfree_skb(arg);
 
 	return err;
-- 
2.13.5


From 911d75453c23fee19aac4bf8e9c21ad74b40bd6f Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Wed, 16 Aug 2017 11:18:09 -0700
Subject: [PATCH 14/25] ipv6: reset fn->rr_ptr when replacing route

[ Upstream commit 383143f31d7d3525a1dbff733d52fff917f82f15 ]

syzcaller reported the following use-after-free issue in rt6_select():
BUG: KASAN: use-after-free in rt6_select net/ipv6/route.c:755 [inline] at addr ffff8800bc6994e8
BUG: KASAN: use-after-free in ip6_pol_route.isra.46+0x1429/0x1470 net/ipv6/route.c:1084 at addr ffff8800bc6994e8
Read of size 4 by task syz-executor1/439628
CPU: 0 PID: 439628 Comm: syz-executor1 Not tainted 4.3.5+ #8
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
 0000000000000000 ffff88018fe435b0 ffffffff81ca384d ffff8801d3588c00
 ffff8800bc699380 ffff8800bc699500 dffffc0000000000 ffff8801d40a47c0
 ffff88018fe435d8 ffffffff81735751 ffff88018fe43660 ffff8800bc699380
Call Trace:
 [<ffffffff81ca384d>] __dump_stack lib/dump_stack.c:15 [inline]
 [<ffffffff81ca384d>] dump_stack+0xc1/0x124 lib/dump_stack.c:51
sctp: [Deprecated]: syz-executor0 (pid 439615) Use of struct sctp_assoc_value in delayed_ack socket option.
Use struct sctp_sack_info instead
 [<ffffffff81735751>] kasan_object_err+0x21/0x70 mm/kasan/report.c:158
 [<ffffffff817359c4>] print_address_description mm/kasan/report.c:196 [inline]
 [<ffffffff817359c4>] kasan_report_error+0x1b4/0x4a0 mm/kasan/report.c:285
 [<ffffffff81735d93>] kasan_report mm/kasan/report.c:305 [inline]
 [<ffffffff81735d93>] __asan_report_load4_noabort+0x43/0x50 mm/kasan/report.c:325
 [<ffffffff82a28e39>] rt6_select net/ipv6/route.c:755 [inline]
 [<ffffffff82a28e39>] ip6_pol_route.isra.46+0x1429/0x1470 net/ipv6/route.c:1084
 [<ffffffff82a28fb1>] ip6_pol_route_output+0x81/0xb0 net/ipv6/route.c:1203
 [<ffffffff82ab0a50>] fib6_rule_action+0x1f0/0x680 net/ipv6/fib6_rules.c:95
 [<ffffffff8265cbb6>] fib_rules_lookup+0x2a6/0x7a0 net/core/fib_rules.c:223
 [<ffffffff82ab1430>] fib6_rule_lookup+0xd0/0x250 net/ipv6/fib6_rules.c:41
 [<ffffffff82a22006>] ip6_route_output+0x1d6/0x2c0 net/ipv6/route.c:1224
 [<ffffffff829e83d2>] ip6_dst_lookup_tail+0x4d2/0x890 net/ipv6/ip6_output.c:943
 [<ffffffff829e889a>] ip6_dst_lookup_flow+0x9a/0x250 net/ipv6/ip6_output.c:1079
 [<ffffffff82a9f7d8>] ip6_datagram_dst_update+0x538/0xd40 net/ipv6/datagram.c:91
 [<ffffffff82aa0978>] __ip6_datagram_connect net/ipv6/datagram.c:251 [inline]
 [<ffffffff82aa0978>] ip6_datagram_connect+0x518/0xe50 net/ipv6/datagram.c:272
 [<ffffffff82aa1313>] ip6_datagram_connect_v6_only+0x63/0x90 net/ipv6/datagram.c:284
 [<ffffffff8292f790>] inet_dgram_connect+0x170/0x1f0 net/ipv4/af_inet.c:564
 [<ffffffff82565547>] SYSC_connect+0x1a7/0x2f0 net/socket.c:1582
 [<ffffffff8256a649>] SyS_connect+0x29/0x30 net/socket.c:1563
 [<ffffffff82c72032>] entry_SYSCALL_64_fastpath+0x12/0x17
Object at ffff8800bc699380, in cache ip6_dst_cache size: 384

The root cause of it is that in fib6_add_rt2node(), when it replaces an
existing route with the new one, it does not update fn->rr_ptr.
This commit resets fn->rr_ptr to NULL when it points to a route which is
replaced in fib6_add_rt2node().

Fixes: 27596472473a ("ipv6: fix ECMP route replacement")
Signed-off-by: Wei Wang <weiwan@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_fib.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 4345ee39f180..1421a846ad36 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -897,6 +897,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 		}
 		nsiblings = iter->rt6i_nsiblings;
 		fib6_purge_rt(iter, fn, info->nl_net);
+		if (fn->rr_ptr == iter)
+			fn->rr_ptr = NULL;
 		rt6_release(iter);
 
 		if (nsiblings) {
@@ -909,6 +911,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 				if (rt6_qualify_for_ecmp(iter)) {
 					*ins = iter->dst.rt6_next;
 					fib6_purge_rt(iter, fn, info->nl_net);
+					if (fn->rr_ptr == iter)
+						fn->rr_ptr = NULL;
 					rt6_release(iter);
 					nsiblings--;
 				} else {
-- 
2.13.5


From 24d3a0cd900d8a3057e4bac588c06f230918b6af Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Fri, 18 Aug 2017 17:14:49 -0700
Subject: [PATCH 15/25] ipv6: repair fib6 tree in failure case

[ Upstream commit 348a4002729ccab8b888b38cbc099efa2f2a2036 ]

In fib6_add(), it is possible that fib6_add_1() picks an intermediate
node and sets the node's fn->leaf to NULL in order to add this new
route. However, if fib6_add_rt2node() fails to add the new
route for some reason, fn->leaf will be left as NULL and could
potentially cause crash when fn->leaf is accessed in fib6_locate().
This patch makes sure fib6_repair_tree() is called to properly repair
fn->leaf in the above failure case.

Here is the syzkaller reported general protection fault in fib6_locate:
kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] SMP KASAN
Modules linked in:
CPU: 0 PID: 40937 Comm: syz-executor3 Not tainted
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
task: ffff8801d7d64100 ti: ffff8801d01a0000 task.ti: ffff8801d01a0000
RIP: 0010:[<ffffffff82a3e0e1>]  [<ffffffff82a3e0e1>] __ipv6_prefix_equal64_half include/net/ipv6.h:475 [inline]
RIP: 0010:[<ffffffff82a3e0e1>]  [<ffffffff82a3e0e1>] ipv6_prefix_equal include/net/ipv6.h:492 [inline]
RIP: 0010:[<ffffffff82a3e0e1>]  [<ffffffff82a3e0e1>] fib6_locate_1 net/ipv6/ip6_fib.c:1210 [inline]
RIP: 0010:[<ffffffff82a3e0e1>]  [<ffffffff82a3e0e1>] fib6_locate+0x281/0x3c0 net/ipv6/ip6_fib.c:1233
RSP: 0018:ffff8801d01a36a8  EFLAGS: 00010202
RAX: 0000000000000020 RBX: ffff8801bc790e00 RCX: ffffc90002983000
RDX: 0000000000001219 RSI: ffff8801d01a37a0 RDI: 0000000000000100
RBP: ffff8801d01a36f0 R08: 00000000000000ff R09: 0000000000000000
R10: 0000000000000003 R11: 0000000000000000 R12: 0000000000000001
R13: dffffc0000000000 R14: ffff8801d01a37a0 R15: 0000000000000000
FS:  00007f6afd68c700(0000) GS:ffff8801db400000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000004c6340 CR3: 00000000ba41f000 CR4: 00000000001426f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Stack:
 ffff8801d01a37a8 ffff8801d01a3780 ffffed003a0346f5 0000000c82a23ea0
 ffff8800b7bd7700 ffff8801d01a3780 ffff8800b6a1c940 ffffffff82a23ea0
 ffff8801d01a3920 ffff8801d01a3748 ffffffff82a223d6 ffff8801d7d64988
Call Trace:
 [<ffffffff82a223d6>] ip6_route_del+0x106/0x570 net/ipv6/route.c:2109
 [<ffffffff82a23f9d>] inet6_rtm_delroute+0xfd/0x100 net/ipv6/route.c:3075
 [<ffffffff82621359>] rtnetlink_rcv_msg+0x549/0x7a0 net/core/rtnetlink.c:3450
 [<ffffffff8274c1d1>] netlink_rcv_skb+0x141/0x370 net/netlink/af_netlink.c:2281
 [<ffffffff82613ddf>] rtnetlink_rcv+0x2f/0x40 net/core/rtnetlink.c:3456
 [<ffffffff8274ad38>] netlink_unicast_kernel net/netlink/af_netlink.c:1206 [inline]
 [<ffffffff8274ad38>] netlink_unicast+0x518/0x750 net/netlink/af_netlink.c:1232
 [<ffffffff8274b83e>] netlink_sendmsg+0x8ce/0xc30 net/netlink/af_netlink.c:1778
 [<ffffffff82564aff>] sock_sendmsg_nosec net/socket.c:609 [inline]
 [<ffffffff82564aff>] sock_sendmsg+0xcf/0x110 net/socket.c:619
 [<ffffffff82564d62>] sock_write_iter+0x222/0x3a0 net/socket.c:834
 [<ffffffff8178523d>] new_sync_write+0x1dd/0x2b0 fs/read_write.c:478
 [<ffffffff817853f4>] __vfs_write+0xe4/0x110 fs/read_write.c:491
 [<ffffffff81786c38>] vfs_write+0x178/0x4b0 fs/read_write.c:538
 [<ffffffff817892a9>] SYSC_write fs/read_write.c:585 [inline]
 [<ffffffff817892a9>] SyS_write+0xd9/0x1b0 fs/read_write.c:577
 [<ffffffff82c71e32>] entry_SYSCALL_64_fastpath+0x12/0x17

Note: there is no "Fixes" tag as this seems to be a bug introduced
very early.

Signed-off-by: Wei Wang <weiwan@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_fib.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 1421a846ad36..ff389591a340 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1001,7 +1001,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 			/* Create subtree root node */
 			sfn = node_alloc();
 			if (!sfn)
-				goto st_failure;
+				goto failure;
 
 			sfn->leaf = info->nl_net->ipv6.ip6_null_entry;
 			atomic_inc(&info->nl_net->ipv6.ip6_null_entry->rt6i_ref);
@@ -1017,12 +1017,12 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 
 			if (IS_ERR(sn)) {
 				/* If it is failed, discard just allocated
-				   root, and then (in st_failure) stale node
+				   root, and then (in failure) stale node
 				   in main tree.
 				 */
 				node_free(sfn);
 				err = PTR_ERR(sn);
-				goto st_failure;
+				goto failure;
 			}
 
 			/* Now link new subtree to main tree */
@@ -1036,7 +1036,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 
 			if (IS_ERR(sn)) {
 				err = PTR_ERR(sn);
-				goto st_failure;
+				goto failure;
 			}
 		}
 
@@ -1078,22 +1078,22 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 			atomic_inc(&pn->leaf->rt6i_ref);
 		}
 #endif
-		if (!(rt->dst.flags & DST_NOCACHE))
-			dst_free(&rt->dst);
+		goto failure;
 	}
 	return err;
 
-#ifdef CONFIG_IPV6_SUBTREES
-	/* Subtree creation failed, probably main tree node
-	   is orphan. If it is, shoot it.
+failure:
+	/* fn->leaf could be NULL if fn is an intermediate node and we
+	 * failed to add the new route to it in both subtree creation
+	 * failure and fib6_add_rt2node() failure case.
+	 * In both cases, fib6_repair_tree() should be called to fix
+	 * fn->leaf.
 	 */
-st_failure:
 	if (fn && !(fn->fn_flags & (RTN_RTINFO|RTN_ROOT)))
 		fib6_repair_tree(info->nl_net, fn);
 	if (!(rt->dst.flags & DST_NOCACHE))
 		dst_free(&rt->dst);
 	return err;
-#endif
 }
 
 /*
-- 
2.13.5


From 9d7d7c3d7dcd12b0b6780a01e4cf5f9ae7ca69be Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Wed, 16 Aug 2017 17:53:36 -0400
Subject: [PATCH 16/25] tcp: when rearming RTO, if RTO time is in past then
 fire RTO ASAP

[ Upstream commit cdbeb633ca71a02b7b63bfeb94994bf4e1a0b894 ]

In some situations tcp_send_loss_probe() can realize that it's unable
to send a loss probe (TLP), and falls back to calling tcp_rearm_rto()
to schedule an RTO timer. In such cases, sometimes tcp_rearm_rto()
realizes that the RTO was eligible to fire immediately or at some
point in the past (delta_us <= 0). Previously in such cases
tcp_rearm_rto() was scheduling such "overdue" RTOs to happen at now +
icsk_rto, which caused needless delays of hundreds of milliseconds
(and non-linear behavior that made reproducible testing
difficult). This commit changes the logic to schedule "overdue" RTOs
ASAP, rather than at now + icsk_rto.

Fixes: 6ba8a3b19e76 ("tcp: Tail loss probe (TLP)")
Suggested-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 32c540145c17..9d9f5ba72493 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3036,8 +3036,7 @@ void tcp_rearm_rto(struct sock *sk)
 			/* delta may not be positive if the socket is locked
 			 * when the retrans timer fires and is rescheduled.
 			 */
-			if (delta > 0)
-				rto = delta;
+			delta = max(delta, 1);
 		}
 		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto,
 					  TCP_RTO_MAX);
-- 
2.13.5


From e4d55c566e2b9d39215edf2fa58d31a68237e862 Mon Sep 17 00:00:00 2001
From: Huy Nguyen <huyn@mellanox.com>
Date: Thu, 17 Aug 2017 18:29:52 +0300
Subject: [PATCH 17/25] net/mlx4_core: Enable 4K UAR if SRIOV module parameter
 is not enabled

[ Upstream commit ca3d89a3ebe79367bd41b6b8ba37664478ae2dba ]

enable_4k_uar module parameter was added in patch cited below to
address the backward compatibility issue in SRIOV when the VM has
system's PAGE_SIZE uar implementation and the Hypervisor has 4k uar
implementation.

The above compatibility issue does not exist in the non SRIOV case.
In this patch, we always enable 4k uar implementation if SRIOV
is not enabled on mlx4's supported cards.

Fixes: 76e39ccf9c36 ("net/mlx4_core: Fix backward compatibility on VFs")
Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 551786f58e59..ba652d8a2b93 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -430,7 +430,7 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 		/* Virtual PCI function needs to determine UAR page size from
 		 * firmware. Only master PCI function can set the uar page size
 		 */
-		if (enable_4k_uar)
+		if (enable_4k_uar || !dev->persist->num_vfs)
 			dev->uar_page_shift = DEFAULT_UAR_PAGE_SHIFT;
 		else
 			dev->uar_page_shift = PAGE_SHIFT;
@@ -2269,7 +2269,7 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
 
 		dev->caps.max_fmr_maps = (1 << (32 - ilog2(dev->caps.num_mpts))) - 1;
 
-		if (enable_4k_uar) {
+		if (enable_4k_uar || !dev->persist->num_vfs) {
 			init_hca.log_uar_sz = ilog2(dev->caps.num_uars) +
 						    PAGE_SHIFT - DEFAULT_UAR_PAGE_SHIFT;
 			init_hca.uar_page_sz = DEFAULT_UAR_PAGE_SHIFT - 12;
-- 
2.13.5


From 2c9d33de4e85d8d2fe7f3ed2263908b241a1f04c Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Thu, 17 Aug 2017 23:14:58 +0100
Subject: [PATCH 18/25] irda: do not leak initialized list.dev to userspace

[ Upstream commit b024d949a3c24255a7ef1a470420eb478949aa4c ]

list.dev has not been initialized and so the copy_to_user is copying
data from the stack back to user space which is a potential
information leak. Fix this ensuring all of list is initialized to
zero.

Detected by CoverityScan, CID#1357894 ("Uninitialized scalar variable")

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/irda/af_irda.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index 391c3cbd2eed..101ed6c42808 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -2223,7 +2223,7 @@ static int irda_getsockopt(struct socket *sock, int level, int optname,
 {
 	struct sock *sk = sock->sk;
 	struct irda_sock *self = irda_sk(sk);
-	struct irda_device_list list;
+	struct irda_device_list list = { 0 };
 	struct irda_device_info *discoveries;
 	struct irda_ias_set *	ias_opt;	/* IAS get/query params */
 	struct ias_object *	ias_obj;	/* Object in IAS */
-- 
2.13.5


From 8084e255021919eee67d41b6c7207b138ff373f7 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Fri, 18 Aug 2017 11:01:36 +0800
Subject: [PATCH 19/25] net: sched: fix NULL pointer dereference when action
 calls some targets

[ Upstream commit 4f8a881acc9d1adaf1e552349a0b1df28933a04c ]

As we know in some target's checkentry it may dereference par.entryinfo
to check entry stuff inside. But when sched action calls xt_check_target,
par.entryinfo is set with NULL. It would cause kernel panic when calling
some targets.

It can be reproduce with:
  # tc qd add dev eth1 ingress handle ffff:
  # tc filter add dev eth1 parent ffff: u32 match u32 0 0 action xt \
    -j ECN --ecn-tcp-remove

It could also crash kernel when using target CLUSTERIP or TPROXY.

By now there's no proper value for par.entryinfo in ipt_init_target,
but it can not be set with NULL. This patch is to void all these
panics by setting it with an ipt_entry obj with all members = 0.

Note that this issue has been there since the very beginning.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ipt.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index a1aec0a6c789..50030519a89b 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -41,6 +41,7 @@ static int ipt_init_target(struct xt_entry_target *t, char *table,
 {
 	struct xt_tgchk_param par;
 	struct xt_target *target;
+	struct ipt_entry e = {};
 	int ret = 0;
 
 	target = xt_request_find_target(AF_INET, t->u.user.name,
@@ -51,6 +52,7 @@ static int ipt_init_target(struct xt_entry_target *t, char *table,
 	t->u.kernel.target = target;
 	memset(&par, 0, sizeof(par));
 	par.table     = table;
+	par.entryinfo = &e;
 	par.target    = target;
 	par.targinfo  = t->data;
 	par.hook_mask = hook;
-- 
2.13.5


From 77a2295177e36d37194aac13a80c9d5d663a54db Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Date: Sat, 19 Aug 2017 15:37:07 +0300
Subject: [PATCH 20/25] net_sched: fix order of queue length updates in
 qdisc_replace()

[ Upstream commit 68a66d149a8c78ec6720f268597302883e48e9fa ]

This important to call qdisc_tree_reduce_backlog() after changing queue
length. Parent qdisc should deactivate class in ->qlen_notify() called from
qdisc_tree_reduce_backlog() but this happens only if qdisc->q.qlen in zero.

Missed class deactivations leads to crashes/warnings at picking packets
from empty qdisc and corrupting state at reactivating this class in future.

Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Fixes: 86a7996cc8a0 ("net_sched: introduce qdisc_replace() helper")
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index e6aa0a249672..f18fc1a0321f 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -768,8 +768,11 @@ static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new,
 	old = *pold;
 	*pold = new;
 	if (old != NULL) {
-		qdisc_tree_reduce_backlog(old, old->q.qlen, old->qstats.backlog);
+		unsigned int qlen = old->q.qlen;
+		unsigned int backlog = old->qstats.backlog;
+
 		qdisc_reset(old);
+		qdisc_tree_reduce_backlog(old, qlen, backlog);
 	}
 	sch_tree_unlock(sch);
 
-- 
2.13.5


From 4a32a692cd1acd3991a70110a76218a22155bb05 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Sun, 2 Jul 2017 02:13:30 +0200
Subject: [PATCH 21/25] bpf, verifier: add additional patterns to
 evaluate_reg_imm_alu

[ Upstream commit 43188702b3d98d2792969a3377a30957f05695e6 ]

Currently the verifier does not track imm across alu operations when
the source register is of unknown type. This adds additional pattern
matching to catch this and track imm. We've seen LLVM generating this
pattern while working on cilium.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c | 62 +++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 62 insertions(+)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 8ce679d36c58..404b6ea7dd92 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1467,6 +1467,65 @@ static int evaluate_reg_alu(struct bpf_verifier_env *env, struct bpf_insn *insn)
 	return 0;
 }
 
+static int evaluate_reg_imm_alu_unknown(struct bpf_verifier_env *env,
+					struct bpf_insn *insn)
+{
+	struct bpf_reg_state *regs = env->cur_state.regs;
+	struct bpf_reg_state *dst_reg = &regs[insn->dst_reg];
+	struct bpf_reg_state *src_reg = &regs[insn->src_reg];
+	u8 opcode = BPF_OP(insn->code);
+	s64 imm_log2 = __ilog2_u64((long long)dst_reg->imm);
+
+	/* BPF_X code with src_reg->type UNKNOWN_VALUE here. */
+	if (src_reg->imm > 0 && dst_reg->imm) {
+		switch (opcode) {
+		case BPF_ADD:
+			/* dreg += sreg
+			 * where both have zero upper bits. Adding them
+			 * can only result making one more bit non-zero
+			 * in the larger value.
+			 * Ex. 0xffff (imm=48) + 1 (imm=63) = 0x10000 (imm=47)
+			 *     0xffff (imm=48) + 0xffff = 0x1fffe (imm=47)
+			 */
+			dst_reg->imm = min(src_reg->imm, 63 - imm_log2);
+			dst_reg->imm--;
+			break;
+		case BPF_AND:
+			/* dreg &= sreg
+			 * AND can not extend zero bits only shrink
+			 * Ex.  0x00..00ffffff
+			 *    & 0x0f..ffffffff
+			 *     ----------------
+			 *      0x00..00ffffff
+			 */
+			dst_reg->imm = max(src_reg->imm, 63 - imm_log2);
+			break;
+		case BPF_OR:
+			/* dreg |= sreg
+			 * OR can only extend zero bits
+			 * Ex.  0x00..00ffffff
+			 *    | 0x0f..ffffffff
+			 *     ----------------
+			 *      0x0f..00ffffff
+			 */
+			dst_reg->imm = min(src_reg->imm, 63 - imm_log2);
+			break;
+		case BPF_SUB:
+		case BPF_MUL:
+		case BPF_RSH:
+		case BPF_LSH:
+			/* These may be flushed out later */
+		default:
+			mark_reg_unknown_value(regs, insn->dst_reg);
+		}
+	} else {
+		mark_reg_unknown_value(regs, insn->dst_reg);
+	}
+
+	dst_reg->type = UNKNOWN_VALUE;
+	return 0;
+}
+
 static int evaluate_reg_imm_alu(struct bpf_verifier_env *env,
 				struct bpf_insn *insn)
 {
@@ -1475,6 +1534,9 @@ static int evaluate_reg_imm_alu(struct bpf_verifier_env *env,
 	struct bpf_reg_state *src_reg = &regs[insn->src_reg];
 	u8 opcode = BPF_OP(insn->code);
 
+	if (BPF_SRC(insn->code) == BPF_X && src_reg->type == UNKNOWN_VALUE)
+		return evaluate_reg_imm_alu_unknown(env, insn);
+
 	/* dst_reg->type == CONST_IMM here, simulate execution of 'add' insn.
 	 * Don't care about overflow or negative values, just add them
 	 */
-- 
2.13.5


From 6e9c7a507b78cb8b311088c34c9a52dce7eba6a8 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 18 May 2017 03:00:06 +0200
Subject: [PATCH 22/25] bpf: adjust verifier heuristics

[ Upstream commit 3c2ce60bdd3d57051bf85615deec04a694473840 ]

Current limits with regards to processing program paths do not
really reflect today's needs anymore due to programs becoming
more complex and verifier smarter, keeping track of more data
such as const ALU operations, alignment tracking, spilling of
PTR_TO_MAP_VALUE_ADJ registers, and other features allowing for
smarter matching of what LLVM generates.

This also comes with the side-effect that we result in fewer
opportunities to prune search states and thus often need to do
more work to prove safety than in the past due to different
register states and stack layout where we mismatch. Generally,
it's quite hard to determine what caused a sudden increase in
complexity, it could be caused by something as trivial as a
single branch somewhere at the beginning of the program where
LLVM assigned a stack slot that is marked differently throughout
other branches and thus causing a mismatch, where verifier
then needs to prove safety for the whole rest of the program.
Subsequently, programs with even less than half the insn size
limit can get rejected. We noticed that while some programs
load fine under pre 4.11, they get rejected due to hitting
limits on more recent kernels. We saw that in the vast majority
of cases (90+%) pruning failed due to register mismatches. In
case of stack mismatches, majority of cases failed due to
different stack slot types (invalid, spill, misc) rather than
differences in spilled registers.

This patch makes pruning more aggressive by also adding markers
that sit at conditional jumps as well. Currently, we only mark
jump targets for pruning. For example in direct packet access,
these are usually error paths where we bail out. We found that
adding these markers, it can reduce number of processed insns
by up to 30%. Another option is to ignore reg->id in probing
PTR_TO_MAP_VALUE_OR_NULL registers, which can help pruning
slightly as well by up to 7% observed complexity reduction as
stand-alone. Meaning, if a previous path with register type
PTR_TO_MAP_VALUE_OR_NULL for map X was found to be safe, then
in the current state a PTR_TO_MAP_VALUE_OR_NULL register for
the same map X must be safe as well. Last but not least the
patch also adds a scheduling point and bumps the current limit
for instructions to be processed to a more adequate value.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 404b6ea7dd92..2ee2e7970df6 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -139,7 +139,7 @@ struct bpf_verifier_stack_elem {
 	struct bpf_verifier_stack_elem *next;
 };
 
-#define BPF_COMPLEXITY_LIMIT_INSNS	65536
+#define BPF_COMPLEXITY_LIMIT_INSNS	98304
 #define BPF_COMPLEXITY_LIMIT_STACK	1024
 
 struct bpf_call_arg_meta {
@@ -2452,6 +2452,7 @@ static int check_cfg(struct bpf_verifier_env *env)
 				env->explored_states[t + 1] = STATE_LIST_MARK;
 		} else {
 			/* conditional jump with two edges */
+			env->explored_states[t] = STATE_LIST_MARK;
 			ret = push_insn(t, t + 1, FALLTHROUGH, env);
 			if (ret == 1)
 				goto peek_stack;
@@ -2610,6 +2611,12 @@ static bool states_equal(struct bpf_verifier_env *env,
 		     rcur->type != NOT_INIT))
 			continue;
 
+		/* Don't care about the reg->id in this case. */
+		if (rold->type == PTR_TO_MAP_VALUE_OR_NULL &&
+		    rcur->type == PTR_TO_MAP_VALUE_OR_NULL &&
+		    rold->map_ptr == rcur->map_ptr)
+			continue;
+
 		if (rold->type == PTR_TO_PACKET && rcur->type == PTR_TO_PACKET &&
 		    compare_ptrs_to_packet(rold, rcur))
 			continue;
@@ -2744,6 +2751,9 @@ static int do_check(struct bpf_verifier_env *env)
 			goto process_bpf_exit;
 		}
 
+		if (need_resched())
+			cond_resched();
+
 		if (log_level && do_print_state) {
 			verbose("\nfrom %d to %d:", prev_insn_idx, insn_idx);
 			print_verifier_state(&env->cur_state);
-- 
2.13.5


From 787b8354be98d2d73637c673d2d64f45f85ffce8 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 31 Mar 2017 02:24:02 +0200
Subject: [PATCH 23/25] bpf, verifier: fix alu ops against map_value{, _adj}
 register types

[ Upstream commit fce366a9dd0ddc47e7ce05611c266e8574a45116 ]

While looking into map_value_adj, I noticed that alu operations
directly on the map_value() resp. map_value_adj() register (any
alu operation on a map_value() register will turn it into a
map_value_adj() typed register) are not sufficiently protected
against some of the operations. Two non-exhaustive examples are
provided that the verifier needs to reject:

 i) BPF_AND on r0 (map_value_adj):

  0: (bf) r2 = r10
  1: (07) r2 += -8
  2: (7a) *(u64 *)(r2 +0) = 0
  3: (18) r1 = 0xbf842a00
  5: (85) call bpf_map_lookup_elem#1
  6: (15) if r0 == 0x0 goto pc+2
   R0=map_value(ks=8,vs=48,id=0),min_value=0,max_value=0 R10=fp
  7: (57) r0 &= 8
  8: (7a) *(u64 *)(r0 +0) = 22
   R0=map_value_adj(ks=8,vs=48,id=0),min_value=0,max_value=8 R10=fp
  9: (95) exit

  from 6 to 9: R0=inv,min_value=0,max_value=0 R10=fp
  9: (95) exit
  processed 10 insns

ii) BPF_ADD in 32 bit mode on r0 (map_value_adj):

  0: (bf) r2 = r10
  1: (07) r2 += -8
  2: (7a) *(u64 *)(r2 +0) = 0
  3: (18) r1 = 0xc24eee00
  5: (85) call bpf_map_lookup_elem#1
  6: (15) if r0 == 0x0 goto pc+2
   R0=map_value(ks=8,vs=48,id=0),min_value=0,max_value=0 R10=fp
  7: (04) (u32) r0 += (u32) 0
  8: (7a) *(u64 *)(r0 +0) = 22
   R0=map_value_adj(ks=8,vs=48,id=0),min_value=0,max_value=0 R10=fp
  9: (95) exit

  from 6 to 9: R0=inv,min_value=0,max_value=0 R10=fp
  9: (95) exit
  processed 10 insns

Issue is, while min_value / max_value boundaries for the access
are adjusted appropriately, we change the pointer value in a way
that cannot be sufficiently tracked anymore from its origin.
Operations like BPF_{AND,OR,DIV,MUL,etc} on a destination register
that is PTR_TO_MAP_VALUE{,_ADJ} was probably unintended, in fact,
all the test cases coming with 484611357c19 ("bpf: allow access
into map value arrays") perform BPF_ADD only on the destination
register that is PTR_TO_MAP_VALUE_ADJ.

Only for UNKNOWN_VALUE register types such operations make sense,
f.e. with unknown memory content fetched initially from a constant
offset from the map value memory into a register. That register is
then later tested against lower / upper bounds, so that the verifier
can then do the tracking of min_value / max_value, and properly
check once that UNKNOWN_VALUE register is added to the destination
register with type PTR_TO_MAP_VALUE{,_ADJ}. This is also what the
original use-case is solving. Note, tracking on what is being
added is done through adjust_reg_min_max_vals() and later access
to the map value enforced with these boundaries and the given offset
from the insn through check_map_access_adj().

Tests will fail for non-root environment due to prohibited pointer
arithmetic, in particular in check_alu_op(), we bail out on the
is_pointer_value() check on the dst_reg (which is false in root
case as we allow for pointer arithmetic via env->allow_ptr_leaks).

Similarly to PTR_TO_PACKET, one way to fix it is to restrict the
allowed operations on PTR_TO_MAP_VALUE{,_ADJ} registers to 64 bit
mode BPF_ADD. The test_verifier suite runs fine after the patch
and it also rejects mentioned test cases.

Fixes: 484611357c19 ("bpf: allow access into map value arrays")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Josef Bacik <jbacik@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 2ee2e7970df6..df0485bdaccd 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1870,6 +1870,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 		 * register as unknown.
 		 */
 		if (env->allow_ptr_leaks &&
+		    BPF_CLASS(insn->code) == BPF_ALU64 && opcode == BPF_ADD &&
 		    (dst_reg->type == PTR_TO_MAP_VALUE ||
 		     dst_reg->type == PTR_TO_MAP_VALUE_ADJ))
 			dst_reg->type = PTR_TO_MAP_VALUE_ADJ;
-- 
2.13.5


From b69dfb0fd8acb624b0dcfc3f5c1905f8b6d143a3 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 21 Jul 2017 00:00:21 +0200
Subject: [PATCH 24/25] bpf: fix mixed signed/unsigned derived min/max value
 bounds

[ Upstream commit 4cabc5b186b5427b9ee5a7495172542af105f02b ]

Edward reported that there's an issue in min/max value bounds
tracking when signed and unsigned compares both provide hints
on limits when having unknown variables. E.g. a program such
as the following should have been rejected:

   0: (7a) *(u64 *)(r10 -8) = 0
   1: (bf) r2 = r10
   2: (07) r2 += -8
   3: (18) r1 = 0xffff8a94cda93400
   5: (85) call bpf_map_lookup_elem#1
   6: (15) if r0 == 0x0 goto pc+7
  R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R10=fp
   7: (7a) *(u64 *)(r10 -16) = -8
   8: (79) r1 = *(u64 *)(r10 -16)
   9: (b7) r2 = -1
  10: (2d) if r1 > r2 goto pc+3
  R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R1=inv,min_value=0
  R2=imm-1,max_value=18446744073709551615,min_align=1 R10=fp
  11: (65) if r1 s> 0x1 goto pc+2
  R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R1=inv,min_value=0,max_value=1
  R2=imm-1,max_value=18446744073709551615,min_align=1 R10=fp
  12: (0f) r0 += r1
  13: (72) *(u8 *)(r0 +0) = 0
  R0=map_value_adj(ks=8,vs=8,id=0),min_value=0,max_value=1 R1=inv,min_value=0,max_value=1
  R2=imm-1,max_value=18446744073709551615,min_align=1 R10=fp
  14: (b7) r0 = 0
  15: (95) exit

What happens is that in the first part ...

   8: (79) r1 = *(u64 *)(r10 -16)
   9: (b7) r2 = -1
  10: (2d) if r1 > r2 goto pc+3

... r1 carries an unsigned value, and is compared as unsigned
against a register carrying an immediate. Verifier deduces in
reg_set_min_max() that since the compare is unsigned and operation
is greater than (>), that in the fall-through/false case, r1's
minimum bound must be 0 and maximum bound must be r2. Latter is
larger than the bound and thus max value is reset back to being
'invalid' aka BPF_REGISTER_MAX_RANGE. Thus, r1 state is now
'R1=inv,min_value=0'. The subsequent test ...

  11: (65) if r1 s> 0x1 goto pc+2

... is a signed compare of r1 with immediate value 1. Here,
verifier deduces in reg_set_min_max() that since the compare
is signed this time and operation is greater than (>), that
in the fall-through/false case, we can deduce that r1's maximum
bound must be 1, meaning with prior test, we result in r1 having
the following state: R1=inv,min_value=0,max_value=1. Given that
the actual value this holds is -8, the bounds are wrongly deduced.
When this is being added to r0 which holds the map_value(_adj)
type, then subsequent store access in above case will go through
check_mem_access() which invokes check_map_access_adj(), that
will then probe whether the map memory is in bounds based
on the min_value and max_value as well as access size since
the actual unknown value is min_value <= x <= max_value; commit
fce366a9dd0d ("bpf, verifier: fix alu ops against map_value{,
_adj} register types") provides some more explanation on the
semantics.

It's worth to note in this context that in the current code,
min_value and max_value tracking are used for two things, i)
dynamic map value access via check_map_access_adj() and since
commit 06c1c049721a ("bpf: allow helpers access to variable memory")
ii) also enforced at check_helper_mem_access() when passing a
memory address (pointer to packet, map value, stack) and length
pair to a helper and the length in this case is an unknown value
defining an access range through min_value/max_value in that
case. The min_value/max_value tracking is /not/ used in the
direct packet access case to track ranges. However, the issue
also affects case ii), for example, the following crafted program
based on the same principle must be rejected as well:

   0: (b7) r2 = 0
   1: (bf) r3 = r10
   2: (07) r3 += -512
   3: (7a) *(u64 *)(r10 -16) = -8
   4: (79) r4 = *(u64 *)(r10 -16)
   5: (b7) r6 = -1
   6: (2d) if r4 > r6 goto pc+5
  R1=ctx R2=imm0,min_value=0,max_value=0,min_align=2147483648 R3=fp-512
  R4=inv,min_value=0 R6=imm-1,max_value=18446744073709551615,min_align=1 R10=fp
   7: (65) if r4 s> 0x1 goto pc+4
  R1=ctx R2=imm0,min_value=0,max_value=0,min_align=2147483648 R3=fp-512
  R4=inv,min_value=0,max_value=1 R6=imm-1,max_value=18446744073709551615,min_align=1
  R10=fp
   8: (07) r4 += 1
   9: (b7) r5 = 0
  10: (6a) *(u16 *)(r10 -512) = 0
  11: (85) call bpf_skb_load_bytes#26
  12: (b7) r0 = 0
  13: (95) exit

Meaning, while we initialize the max_value stack slot that the
verifier thinks we access in the [1,2] range, in reality we
pass -7 as length which is interpreted as u32 in the helper.
Thus, this issue is relevant also for the case of helper ranges.
Resetting both bounds in check_reg_overflow() in case only one
of them exceeds limits is also not enough as similar test can be
created that uses values which are within range, thus also here
learned min value in r1 is incorrect when mixed with later signed
test to create a range:

   0: (7a) *(u64 *)(r10 -8) = 0
   1: (bf) r2 = r10
   2: (07) r2 += -8
   3: (18) r1 = 0xffff880ad081fa00
   5: (85) call bpf_map_lookup_elem#1
   6: (15) if r0 == 0x0 goto pc+7
  R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R10=fp
   7: (7a) *(u64 *)(r10 -16) = -8
   8: (79) r1 = *(u64 *)(r10 -16)
   9: (b7) r2 = 2
  10: (3d) if r2 >= r1 goto pc+3
  R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R1=inv,min_value=3
  R2=imm2,min_value=2,max_value=2,min_align=2 R10=fp
  11: (65) if r1 s> 0x4 goto pc+2
  R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0
  R1=inv,min_value=3,max_value=4 R2=imm2,min_value=2,max_value=2,min_align=2 R10=fp
  12: (0f) r0 += r1
  13: (72) *(u8 *)(r0 +0) = 0
  R0=map_value_adj(ks=8,vs=8,id=0),min_value=3,max_value=4
  R1=inv,min_value=3,max_value=4 R2=imm2,min_value=2,max_value=2,min_align=2 R10=fp
  14: (b7) r0 = 0
  15: (95) exit

This leaves us with two options for fixing this: i) to invalidate
all prior learned information once we switch signed context, ii)
to track min/max signed and unsigned boundaries separately as
done in [0]. (Given latter introduces major changes throughout
the whole verifier, it's rather net-next material, thus this
patch follows option i), meaning we can derive bounds either
from only signed tests or only unsigned tests.) There is still the
case of adjust_reg_min_max_vals(), where we adjust bounds on ALU
operations, meaning programs like the following where boundaries
on the reg get mixed in context later on when bounds are merged
on the dst reg must get rejected, too:

   0: (7a) *(u64 *)(r10 -8) = 0
   1: (bf) r2 = r10
   2: (07) r2 += -8
   3: (18) r1 = 0xffff89b2bf87ce00
   5: (85) call bpf_map_lookup_elem#1
   6: (15) if r0 == 0x0 goto pc+6
  R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R10=fp
   7: (7a) *(u64 *)(r10 -16) = -8
   8: (79) r1 = *(u64 *)(r10 -16)
   9: (b7) r2 = 2
  10: (3d) if r2 >= r1 goto pc+2
  R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R1=inv,min_value=3
  R2=imm2,min_value=2,max_value=2,min_align=2 R10=fp
  11: (b7) r7 = 1
  12: (65) if r7 s> 0x0 goto pc+2
  R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R1=inv,min_value=3
  R2=imm2,min_value=2,max_value=2,min_align=2 R7=imm1,max_value=0 R10=fp
  13: (b7) r0 = 0
  14: (95) exit

  from 12 to 15: R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0
  R1=inv,min_value=3 R2=imm2,min_value=2,max_value=2,min_align=2 R7=imm1,min_value=1 R10=fp
  15: (0f) r7 += r1
  16: (65) if r7 s> 0x4 goto pc+2
  R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R1=inv,min_value=3
  R2=imm2,min_value=2,max_value=2,min_align=2 R7=inv,min_value=4,max_value=4 R10=fp
  17: (0f) r0 += r7
  18: (72) *(u8 *)(r0 +0) = 0
  R0=map_value_adj(ks=8,vs=8,id=0),min_value=4,max_value=4 R1=inv,min_value=3
  R2=imm2,min_value=2,max_value=2,min_align=2 R7=inv,min_value=4,max_value=4 R10=fp
  19: (b7) r0 = 0
  20: (95) exit

Meaning, in adjust_reg_min_max_vals() we must also reset range
values on the dst when src/dst registers have mixed signed/
unsigned derived min/max value bounds with one unbounded value
as otherwise they can be added together deducing false boundaries.
Once both boundaries are established from either ALU ops or
compare operations w/o mixing signed/unsigned insns, then they
can safely be added to other regs also having both boundaries
established. Adding regs with one unbounded side to a map value
where the bounded side has been learned w/o mixing ops is
possible, but the resulting map value won't recover from that,
meaning such op is considered invalid on the time of actual
access. Invalid bounds are set on the dst reg in case i) src reg,
or ii) in case dst reg already had them. The only way to recover
would be to perform i) ALU ops but only 'add' is allowed on map
value types or ii) comparisons, but these are disallowed on
pointers in case they span a range. This is fine as only BPF_JEQ
and BPF_JNE may be performed on PTR_TO_MAP_VALUE_OR_NULL registers
which potentially turn them into PTR_TO_MAP_VALUE type depending
on the branch, so only here min/max value cannot be invalidated
for them.

In terms of state pruning, value_from_signed is considered
as well in states_equal() when dealing with adjusted map values.
With regards to breaking existing programs, there is a small
risk, but use-cases are rather quite narrow where this could
occur and mixing compares probably unlikely.

Joint work with Josef and Edward.

  [0] https://lists.iovisor.org/pipermail/iovisor-dev/2017-June/000822.html

Fixes: 484611357c19 ("bpf: allow access into map value arrays")
Reported-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/bpf_verifier.h |   1 +
 kernel/bpf/verifier.c        | 110 +++++++++++++++++++++++++++++++++++++------
 2 files changed, 97 insertions(+), 14 deletions(-)

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index a13b031dc6b8..3101141661a1 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -40,6 +40,7 @@ struct bpf_reg_state {
 	 */
 	s64 min_value;
 	u64 max_value;
+	bool value_from_signed;
 };
 
 enum bpf_stack_slot_type {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index df0485bdaccd..4f9fa4c24c30 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -682,12 +682,13 @@ static int check_ctx_access(struct bpf_verifier_env *env, int off, int size,
 	return -EACCES;
 }
 
-static bool is_pointer_value(struct bpf_verifier_env *env, int regno)
+static bool __is_pointer_value(bool allow_ptr_leaks,
+			       const struct bpf_reg_state *reg)
 {
-	if (env->allow_ptr_leaks)
+	if (allow_ptr_leaks)
 		return false;
 
-	switch (env->cur_state.regs[regno].type) {
+	switch (reg->type) {
 	case UNKNOWN_VALUE:
 	case CONST_IMM:
 		return false;
@@ -696,6 +697,11 @@ static bool is_pointer_value(struct bpf_verifier_env *env, int regno)
 	}
 }
 
+static bool is_pointer_value(struct bpf_verifier_env *env, int regno)
+{
+	return __is_pointer_value(env->allow_ptr_leaks, &env->cur_state.regs[regno]);
+}
+
 static int check_ptr_alignment(struct bpf_verifier_env *env,
 			       struct bpf_reg_state *reg, int off, int size)
 {
@@ -1592,10 +1598,24 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 	}
 
 	/* We don't know anything about what was done to this register, mark it
-	 * as unknown.
+	 * as unknown. Also, if both derived bounds came from signed/unsigned
+	 * mixed compares and one side is unbounded, we cannot really do anything
+	 * with them as boundaries cannot be trusted. Thus, arithmetic of two
+	 * regs of such kind will get invalidated bounds on the dst side.
 	 */
-	if (min_val == BPF_REGISTER_MIN_RANGE &&
-	    max_val == BPF_REGISTER_MAX_RANGE) {
+	if ((min_val == BPF_REGISTER_MIN_RANGE &&
+	     max_val == BPF_REGISTER_MAX_RANGE) ||
+	    (BPF_SRC(insn->code) == BPF_X &&
+	     ((min_val != BPF_REGISTER_MIN_RANGE &&
+	       max_val == BPF_REGISTER_MAX_RANGE) ||
+	      (min_val == BPF_REGISTER_MIN_RANGE &&
+	       max_val != BPF_REGISTER_MAX_RANGE) ||
+	      (dst_reg->min_value != BPF_REGISTER_MIN_RANGE &&
+	       dst_reg->max_value == BPF_REGISTER_MAX_RANGE) ||
+	      (dst_reg->min_value == BPF_REGISTER_MIN_RANGE &&
+	       dst_reg->max_value != BPF_REGISTER_MAX_RANGE)) &&
+	     regs[insn->dst_reg].value_from_signed !=
+	     regs[insn->src_reg].value_from_signed)) {
 		reset_reg_range_values(regs, insn->dst_reg);
 		return;
 	}
@@ -1939,38 +1959,63 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg,
 			    struct bpf_reg_state *false_reg, u64 val,
 			    u8 opcode)
 {
+	bool value_from_signed = true;
+	bool is_range = true;
+
 	switch (opcode) {
 	case BPF_JEQ:
 		/* If this is false then we know nothing Jon Snow, but if it is
 		 * true then we know for sure.
 		 */
 		true_reg->max_value = true_reg->min_value = val;
+		is_range = false;
 		break;
 	case BPF_JNE:
 		/* If this is true we know nothing Jon Snow, but if it is false
 		 * we know the value for sure;
 		 */
 		false_reg->max_value = false_reg->min_value = val;
+		is_range = false;
 		break;
 	case BPF_JGT:
-		/* Unsigned comparison, the minimum value is 0. */
-		false_reg->min_value = 0;
+		value_from_signed = false;
+		/* fallthrough */
 	case BPF_JSGT:
+		if (true_reg->value_from_signed != value_from_signed)
+			reset_reg_range_values(true_reg, 0);
+		if (false_reg->value_from_signed != value_from_signed)
+			reset_reg_range_values(false_reg, 0);
+		if (opcode == BPF_JGT) {
+			/* Unsigned comparison, the minimum value is 0. */
+			false_reg->min_value = 0;
+		}
 		/* If this is false then we know the maximum val is val,
 		 * otherwise we know the min val is val+1.
 		 */
 		false_reg->max_value = val;
+		false_reg->value_from_signed = value_from_signed;
 		true_reg->min_value = val + 1;
+		true_reg->value_from_signed = value_from_signed;
 		break;
 	case BPF_JGE:
-		/* Unsigned comparison, the minimum value is 0. */
-		false_reg->min_value = 0;
+		value_from_signed = false;
+		/* fallthrough */
 	case BPF_JSGE:
+		if (true_reg->value_from_signed != value_from_signed)
+			reset_reg_range_values(true_reg, 0);
+		if (false_reg->value_from_signed != value_from_signed)
+			reset_reg_range_values(false_reg, 0);
+		if (opcode == BPF_JGE) {
+			/* Unsigned comparison, the minimum value is 0. */
+			false_reg->min_value = 0;
+		}
 		/* If this is false then we know the maximum value is val - 1,
 		 * otherwise we know the mimimum value is val.
 		 */
 		false_reg->max_value = val - 1;
+		false_reg->value_from_signed = value_from_signed;
 		true_reg->min_value = val;
+		true_reg->value_from_signed = value_from_signed;
 		break;
 	default:
 		break;
@@ -1978,6 +2023,12 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg,
 
 	check_reg_overflow(false_reg);
 	check_reg_overflow(true_reg);
+	if (is_range) {
+		if (__is_pointer_value(false, false_reg))
+			reset_reg_range_values(false_reg, 0);
+		if (__is_pointer_value(false, true_reg))
+			reset_reg_range_values(true_reg, 0);
+	}
 }
 
 /* Same as above, but for the case that dst_reg is a CONST_IMM reg and src_reg
@@ -1987,39 +2038,64 @@ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg,
 				struct bpf_reg_state *false_reg, u64 val,
 				u8 opcode)
 {
+	bool value_from_signed = true;
+	bool is_range = true;
+
 	switch (opcode) {
 	case BPF_JEQ:
 		/* If this is false then we know nothing Jon Snow, but if it is
 		 * true then we know for sure.
 		 */
 		true_reg->max_value = true_reg->min_value = val;
+		is_range = false;
 		break;
 	case BPF_JNE:
 		/* If this is true we know nothing Jon Snow, but if it is false
 		 * we know the value for sure;
 		 */
 		false_reg->max_value = false_reg->min_value = val;
+		is_range = false;
 		break;
 	case BPF_JGT:
-		/* Unsigned comparison, the minimum value is 0. */
-		true_reg->min_value = 0;
+		value_from_signed = false;
+		/* fallthrough */
 	case BPF_JSGT:
+		if (true_reg->value_from_signed != value_from_signed)
+			reset_reg_range_values(true_reg, 0);
+		if (false_reg->value_from_signed != value_from_signed)
+			reset_reg_range_values(false_reg, 0);
+		if (opcode == BPF_JGT) {
+			/* Unsigned comparison, the minimum value is 0. */
+			true_reg->min_value = 0;
+		}
 		/*
 		 * If this is false, then the val is <= the register, if it is
 		 * true the register <= to the val.
 		 */
 		false_reg->min_value = val;
+		false_reg->value_from_signed = value_from_signed;
 		true_reg->max_value = val - 1;
+		true_reg->value_from_signed = value_from_signed;
 		break;
 	case BPF_JGE:
-		/* Unsigned comparison, the minimum value is 0. */
-		true_reg->min_value = 0;
+		value_from_signed = false;
+		/* fallthrough */
 	case BPF_JSGE:
+		if (true_reg->value_from_signed != value_from_signed)
+			reset_reg_range_values(true_reg, 0);
+		if (false_reg->value_from_signed != value_from_signed)
+			reset_reg_range_values(false_reg, 0);
+		if (opcode == BPF_JGE) {
+			/* Unsigned comparison, the minimum value is 0. */
+			true_reg->min_value = 0;
+		}
 		/* If this is false then constant < register, if it is true then
 		 * the register < constant.
 		 */
 		false_reg->min_value = val + 1;
+		false_reg->value_from_signed = value_from_signed;
 		true_reg->max_value = val;
+		true_reg->value_from_signed = value_from_signed;
 		break;
 	default:
 		break;
@@ -2027,6 +2103,12 @@ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg,
 
 	check_reg_overflow(false_reg);
 	check_reg_overflow(true_reg);
+	if (is_range) {
+		if (__is_pointer_value(false, false_reg))
+			reset_reg_range_values(false_reg, 0);
+		if (__is_pointer_value(false, true_reg))
+			reset_reg_range_values(true_reg, 0);
+	}
 }
 
 static void mark_map_reg(struct bpf_reg_state *regs, u32 regno, u32 id,
-- 
2.13.5


From 39ee5266e0a067354b0a835e663e9c78c154d53a Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Fri, 21 Jul 2017 14:37:34 +0100
Subject: [PATCH 25/25] bpf/verifier: fix min/max handling in BPF_SUB

[ Upstream commit 9305706c2e808ae59f1eb201867f82f1ddf6d7a6 ]

We have to subtract the src max from the dst min, and vice-versa, since
 (e.g.) the smallest result comes from the largest subtrahend.

Fixes: 484611357c19 ("bpf: allow access into map value arrays")
Signed-off-by: Edward Cree <ecree@solarflare.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c | 21 +++++++++++++++------
 1 file changed, 15 insertions(+), 6 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 4f9fa4c24c30..779c871c5dcd 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1624,10 +1624,12 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 	 * do our normal operations to the register, we need to set the values
 	 * to the min/max since they are undefined.
 	 */
-	if (min_val == BPF_REGISTER_MIN_RANGE)
-		dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
-	if (max_val == BPF_REGISTER_MAX_RANGE)
-		dst_reg->max_value = BPF_REGISTER_MAX_RANGE;
+	if (opcode != BPF_SUB) {
+		if (min_val == BPF_REGISTER_MIN_RANGE)
+			dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
+		if (max_val == BPF_REGISTER_MAX_RANGE)
+			dst_reg->max_value = BPF_REGISTER_MAX_RANGE;
+	}
 
 	switch (opcode) {
 	case BPF_ADD:
@@ -1637,10 +1639,17 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 			dst_reg->max_value += max_val;
 		break;
 	case BPF_SUB:
+		/* If one of our values was at the end of our ranges, then the
+		 * _opposite_ value in the dst_reg goes to the end of our range.
+		 */
+		if (min_val == BPF_REGISTER_MIN_RANGE)
+			dst_reg->max_value = BPF_REGISTER_MAX_RANGE;
+		if (max_val == BPF_REGISTER_MAX_RANGE)
+			dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
 		if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
-			dst_reg->min_value -= min_val;
+			dst_reg->min_value -= max_val;
 		if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
-			dst_reg->max_value -= max_val;
+			dst_reg->max_value -= min_val;
 		break;
 	case BPF_MUL:
 		if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
-- 
2.13.5


[-- Attachment #3: net_412.mbox --]
[-- Type: Application/Octet-Stream, Size: 110306 bytes --]

From 6d1d438884ad68706bad96d4caf64828275c82ed Mon Sep 17 00:00:00 2001
From: Andreas Born <futur.andy@googlemail.com>
Date: Thu, 10 Aug 2017 06:41:44 +0200
Subject: [PATCH 01/27] bonding: require speed/duplex only for 802.3ad, alb and
 tlb

[ Upstream commit ad729bc9acfb7c47112964b4877ef5404578ed13 ]

The patch c4adfc822bf5 ("bonding: make speed, duplex setting consistent
with link state") puts the link state to down if
bond_update_speed_duplex() cannot retrieve speed and duplex settings.
Assumably the patch was written with 802.3ad mode in mind which relies
on link speed/duplex settings. For other modes like active-backup these
settings are not required. Thus, only for these other modes, this patch
reintroduces support for slaves that do not support reporting speed or
duplex such as wireless devices. This fixes the regression reported in
bug 196547 (https://bugzilla.kernel.org/show_bug.cgi?id=196547).

Fixes: c4adfc822bf5 ("bonding: make speed, duplex setting consistent
with link state")
Signed-off-by: Andreas Born <futur.andy@googlemail.com>
Acked-by: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 6 ++++--
 include/net/bonding.h           | 5 +++++
 2 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 224e93aa6d23..a063d28304ff 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1569,7 +1569,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	new_slave->delay = 0;
 	new_slave->link_failure_count = 0;
 
-	if (bond_update_speed_duplex(new_slave))
+	if (bond_update_speed_duplex(new_slave) &&
+	    bond_needs_speed_duplex(bond))
 		new_slave->link = BOND_LINK_DOWN;
 
 	new_slave->last_rx = jiffies -
@@ -2137,7 +2138,8 @@ static void bond_miimon_commit(struct bonding *bond)
 			continue;
 
 		case BOND_LINK_UP:
-			if (bond_update_speed_duplex(slave)) {
+			if (bond_update_speed_duplex(slave) &&
+			    bond_needs_speed_duplex(bond)) {
 				slave->link = BOND_LINK_DOWN;
 				netdev_warn(bond->dev,
 					    "failed to get link speed/duplex for %s\n",
diff --git a/include/net/bonding.h b/include/net/bonding.h
index b00508d22e0a..b2e68657a216 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -277,6 +277,11 @@ static inline bool bond_is_lb(const struct bonding *bond)
 	       BOND_MODE(bond) == BOND_MODE_ALB;
 }
 
+static inline bool bond_needs_speed_duplex(const struct bonding *bond)
+{
+	return BOND_MODE(bond) == BOND_MODE_8023AD || bond_is_lb(bond);
+}
+
 static inline bool bond_is_nondyn_tlb(const struct bonding *bond)
 {
 	return (BOND_MODE(bond) == BOND_MODE_TLB)  &&
-- 
2.13.5


From 0ed9f7149ca15ba15fca944b01c1e2cb0b7a6c23 Mon Sep 17 00:00:00 2001
From: Andreas Born <futur.andy@googlemail.com>
Date: Sat, 12 Aug 2017 00:36:55 +0200
Subject: [PATCH 02/27] bonding: ratelimit failed speed/duplex update warning

[ Upstream commit 11e9d7829dd08dbafb24517fe922f11c3a8a9dc2 ]

bond_miimon_commit() handles the UP transition for each slave of a bond
in the case of MII. It is triggered 10 times per second for the default
MII Polling interval of 100ms. For device drivers that do not implement
__ethtool_get_link_ksettings() the call to bond_update_speed_duplex()
fails persistently while the MII status could remain UP. That is, in
this and other cases where the speed/duplex update keeps failing over a
longer period of time while the MII state is UP, a warning is printed
every MII polling interval.

To address these excessive warnings net_ratelimit() should be used.
Printing a warning once would not be sufficient since the call to
bond_update_speed_duplex() could recover to succeed and fail again
later. In that case there would be no new indication what went wrong.

Fixes: b5bf0f5b16b9c (bonding: correctly update link status during mii-commit phase)
Signed-off-by: Andreas Born <futur.andy@googlemail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index a063d28304ff..510a580e0348 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2141,9 +2141,10 @@ static void bond_miimon_commit(struct bonding *bond)
 			if (bond_update_speed_duplex(slave) &&
 			    bond_needs_speed_duplex(bond)) {
 				slave->link = BOND_LINK_DOWN;
-				netdev_warn(bond->dev,
-					    "failed to get link speed/duplex for %s\n",
-					    slave->dev->name);
+				if (net_ratelimit())
+					netdev_warn(bond->dev,
+						    "failed to get link speed/duplex for %s\n",
+						    slave->dev->name);
 				continue;
 			}
 			bond_set_slave_link_state(slave, BOND_LINK_UP,
-- 
2.13.5


From f57c8c34ca10de921254e0e26f7fd9919b74a37e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 14 Aug 2017 10:16:45 -0700
Subject: [PATCH 03/27] af_key: do not use GFP_KERNEL in atomic contexts

[ Upstream commit 36f41f8fc6d8aa9f8c9072d66ff7cf9055f5e69b ]

pfkey_broadcast() might be called from non process contexts,
we can not use GFP_KERNEL in these cases [1].

This patch partially reverts commit ba51b6be38c1 ("net: Fix RCU splat in
af_key"), only keeping the GFP_ATOMIC forcing under rcu_read_lock()
section.

[1] : syzkaller reported :

in_atomic(): 1, irqs_disabled(): 0, pid: 2932, name: syzkaller183439
3 locks held by syzkaller183439/2932:
 #0:  (&net->xfrm.xfrm_cfg_mutex){+.+.+.}, at: [<ffffffff83b43888>] pfkey_sendmsg+0x4c8/0x9f0 net/key/af_key.c:3649
 #1:  (&pfk->dump_lock){+.+.+.}, at: [<ffffffff83b467f6>] pfkey_do_dump+0x76/0x3f0 net/key/af_key.c:293
 #2:  (&(&net->xfrm.xfrm_policy_lock)->rlock){+...+.}, at: [<ffffffff83957632>] spin_lock_bh include/linux/spinlock.h:304 [inline]
 #2:  (&(&net->xfrm.xfrm_policy_lock)->rlock){+...+.}, at: [<ffffffff83957632>] xfrm_policy_walk+0x192/0xa30 net/xfrm/xfrm_policy.c:1028
CPU: 0 PID: 2932 Comm: syzkaller183439 Not tainted 4.13.0-rc4+ #24
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:16 [inline]
 dump_stack+0x194/0x257 lib/dump_stack.c:52
 ___might_sleep+0x2b2/0x470 kernel/sched/core.c:5994
 __might_sleep+0x95/0x190 kernel/sched/core.c:5947
 slab_pre_alloc_hook mm/slab.h:416 [inline]
 slab_alloc mm/slab.c:3383 [inline]
 kmem_cache_alloc+0x24b/0x6e0 mm/slab.c:3559
 skb_clone+0x1a0/0x400 net/core/skbuff.c:1037
 pfkey_broadcast_one+0x4b2/0x6f0 net/key/af_key.c:207
 pfkey_broadcast+0x4ba/0x770 net/key/af_key.c:281
 dump_sp+0x3d6/0x500 net/key/af_key.c:2685
 xfrm_policy_walk+0x2f1/0xa30 net/xfrm/xfrm_policy.c:1042
 pfkey_dump_sp+0x42/0x50 net/key/af_key.c:2695
 pfkey_do_dump+0xaa/0x3f0 net/key/af_key.c:299
 pfkey_spddump+0x1a0/0x210 net/key/af_key.c:2722
 pfkey_process+0x606/0x710 net/key/af_key.c:2814
 pfkey_sendmsg+0x4d6/0x9f0 net/key/af_key.c:3650
sock_sendmsg_nosec net/socket.c:633 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:643
 ___sys_sendmsg+0x755/0x890 net/socket.c:2035
 __sys_sendmsg+0xe5/0x210 net/socket.c:2069
 SYSC_sendmsg net/socket.c:2080 [inline]
 SyS_sendmsg+0x2d/0x50 net/socket.c:2076
 entry_SYSCALL_64_fastpath+0x1f/0xbe
RIP: 0033:0x445d79
RSP: 002b:00007f32447c1dc8 EFLAGS: 00000202 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 0000000000445d79
RDX: 0000000000000000 RSI: 000000002023dfc8 RDI: 0000000000000008
RBP: 0000000000000086 R08: 00007f32447c2700 R09: 00007f32447c2700
R10: 00007f32447c2700 R11: 0000000000000202 R12: 0000000000000000
R13: 00007ffe33edec4f R14: 00007f32447c29c0 R15: 0000000000000000

Fixes: ba51b6be38c1 ("net: Fix RCU splat in af_key")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: David Ahern <dsa@cumulusnetworks.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/key/af_key.c | 48 ++++++++++++++++++++++++++----------------------
 1 file changed, 26 insertions(+), 22 deletions(-)

diff --git a/net/key/af_key.c b/net/key/af_key.c
index b1432b668033..166e32c93038 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -228,7 +228,7 @@ static int pfkey_broadcast_one(struct sk_buff *skb, struct sk_buff **skb2,
 #define BROADCAST_ONE		1
 #define BROADCAST_REGISTERED	2
 #define BROADCAST_PROMISC_ONLY	4
-static int pfkey_broadcast(struct sk_buff *skb,
+static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation,
 			   int broadcast_flags, struct sock *one_sk,
 			   struct net *net)
 {
@@ -278,7 +278,7 @@ static int pfkey_broadcast(struct sk_buff *skb,
 	rcu_read_unlock();
 
 	if (one_sk != NULL)
-		err = pfkey_broadcast_one(skb, &skb2, GFP_KERNEL, one_sk);
+		err = pfkey_broadcast_one(skb, &skb2, allocation, one_sk);
 
 	kfree_skb(skb2);
 	kfree_skb(skb);
@@ -311,7 +311,7 @@ static int pfkey_do_dump(struct pfkey_sock *pfk)
 		hdr = (struct sadb_msg *) pfk->dump.skb->data;
 		hdr->sadb_msg_seq = 0;
 		hdr->sadb_msg_errno = rc;
-		pfkey_broadcast(pfk->dump.skb, BROADCAST_ONE,
+		pfkey_broadcast(pfk->dump.skb, GFP_ATOMIC, BROADCAST_ONE,
 				&pfk->sk, sock_net(&pfk->sk));
 		pfk->dump.skb = NULL;
 	}
@@ -355,7 +355,7 @@ static int pfkey_error(const struct sadb_msg *orig, int err, struct sock *sk)
 	hdr->sadb_msg_len = (sizeof(struct sadb_msg) /
 			     sizeof(uint64_t));
 
-	pfkey_broadcast(skb, BROADCAST_ONE, sk, sock_net(sk));
+	pfkey_broadcast(skb, GFP_KERNEL, BROADCAST_ONE, sk, sock_net(sk));
 
 	return 0;
 }
@@ -1396,7 +1396,7 @@ static int pfkey_getspi(struct sock *sk, struct sk_buff *skb, const struct sadb_
 
 	xfrm_state_put(x);
 
-	pfkey_broadcast(resp_skb, BROADCAST_ONE, sk, net);
+	pfkey_broadcast(resp_skb, GFP_KERNEL, BROADCAST_ONE, sk, net);
 
 	return 0;
 }
@@ -1483,7 +1483,7 @@ static int key_notify_sa(struct xfrm_state *x, const struct km_event *c)
 	hdr->sadb_msg_seq = c->seq;
 	hdr->sadb_msg_pid = c->portid;
 
-	pfkey_broadcast(skb, BROADCAST_ALL, NULL, xs_net(x));
+	pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, xs_net(x));
 
 	return 0;
 }
@@ -1596,7 +1596,7 @@ static int pfkey_get(struct sock *sk, struct sk_buff *skb, const struct sadb_msg
 	out_hdr->sadb_msg_reserved = 0;
 	out_hdr->sadb_msg_seq = hdr->sadb_msg_seq;
 	out_hdr->sadb_msg_pid = hdr->sadb_msg_pid;
-	pfkey_broadcast(out_skb, BROADCAST_ONE, sk, sock_net(sk));
+	pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ONE, sk, sock_net(sk));
 
 	return 0;
 }
@@ -1701,8 +1701,8 @@ static int pfkey_register(struct sock *sk, struct sk_buff *skb, const struct sad
 		return -ENOBUFS;
 	}
 
-	pfkey_broadcast(supp_skb, BROADCAST_REGISTERED, sk, sock_net(sk));
-
+	pfkey_broadcast(supp_skb, GFP_KERNEL, BROADCAST_REGISTERED, sk,
+			sock_net(sk));
 	return 0;
 }
 
@@ -1720,7 +1720,8 @@ static int unicast_flush_resp(struct sock *sk, const struct sadb_msg *ihdr)
 	hdr->sadb_msg_errno = (uint8_t) 0;
 	hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t));
 
-	return pfkey_broadcast(skb, BROADCAST_ONE, sk, sock_net(sk));
+	return pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ONE, sk,
+			       sock_net(sk));
 }
 
 static int key_notify_sa_flush(const struct km_event *c)
@@ -1741,7 +1742,7 @@ static int key_notify_sa_flush(const struct km_event *c)
 	hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t));
 	hdr->sadb_msg_reserved = 0;
 
-	pfkey_broadcast(skb, BROADCAST_ALL, NULL, c->net);
+	pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, c->net);
 
 	return 0;
 }
@@ -1798,7 +1799,7 @@ static int dump_sa(struct xfrm_state *x, int count, void *ptr)
 	out_hdr->sadb_msg_pid = pfk->dump.msg_portid;
 
 	if (pfk->dump.skb)
-		pfkey_broadcast(pfk->dump.skb, BROADCAST_ONE,
+		pfkey_broadcast(pfk->dump.skb, GFP_ATOMIC, BROADCAST_ONE,
 				&pfk->sk, sock_net(&pfk->sk));
 	pfk->dump.skb = out_skb;
 
@@ -1886,7 +1887,7 @@ static int pfkey_promisc(struct sock *sk, struct sk_buff *skb, const struct sadb
 		new_hdr->sadb_msg_errno = 0;
 	}
 
-	pfkey_broadcast(skb, BROADCAST_ALL, NULL, sock_net(sk));
+	pfkey_broadcast(skb, GFP_KERNEL, BROADCAST_ALL, NULL, sock_net(sk));
 	return 0;
 }
 
@@ -2219,7 +2220,7 @@ static int key_notify_policy(struct xfrm_policy *xp, int dir, const struct km_ev
 	out_hdr->sadb_msg_errno = 0;
 	out_hdr->sadb_msg_seq = c->seq;
 	out_hdr->sadb_msg_pid = c->portid;
-	pfkey_broadcast(out_skb, BROADCAST_ALL, NULL, xp_net(xp));
+	pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ALL, NULL, xp_net(xp));
 	return 0;
 
 }
@@ -2439,7 +2440,7 @@ static int key_pol_get_resp(struct sock *sk, struct xfrm_policy *xp, const struc
 	out_hdr->sadb_msg_errno = 0;
 	out_hdr->sadb_msg_seq = hdr->sadb_msg_seq;
 	out_hdr->sadb_msg_pid = hdr->sadb_msg_pid;
-	pfkey_broadcast(out_skb, BROADCAST_ONE, sk, xp_net(xp));
+	pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ONE, sk, xp_net(xp));
 	err = 0;
 
 out:
@@ -2695,7 +2696,7 @@ static int dump_sp(struct xfrm_policy *xp, int dir, int count, void *ptr)
 	out_hdr->sadb_msg_pid = pfk->dump.msg_portid;
 
 	if (pfk->dump.skb)
-		pfkey_broadcast(pfk->dump.skb, BROADCAST_ONE,
+		pfkey_broadcast(pfk->dump.skb, GFP_ATOMIC, BROADCAST_ONE,
 				&pfk->sk, sock_net(&pfk->sk));
 	pfk->dump.skb = out_skb;
 
@@ -2752,7 +2753,7 @@ static int key_notify_policy_flush(const struct km_event *c)
 	hdr->sadb_msg_satype = SADB_SATYPE_UNSPEC;
 	hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t));
 	hdr->sadb_msg_reserved = 0;
-	pfkey_broadcast(skb_out, BROADCAST_ALL, NULL, c->net);
+	pfkey_broadcast(skb_out, GFP_ATOMIC, BROADCAST_ALL, NULL, c->net);
 	return 0;
 
 }
@@ -2816,7 +2817,7 @@ static int pfkey_process(struct sock *sk, struct sk_buff *skb, const struct sadb
 	void *ext_hdrs[SADB_EXT_MAX];
 	int err;
 
-	pfkey_broadcast(skb_clone(skb, GFP_KERNEL),
+	pfkey_broadcast(skb_clone(skb, GFP_KERNEL), GFP_KERNEL,
 			BROADCAST_PROMISC_ONLY, NULL, sock_net(sk));
 
 	memset(ext_hdrs, 0, sizeof(ext_hdrs));
@@ -3038,7 +3039,8 @@ static int key_notify_sa_expire(struct xfrm_state *x, const struct km_event *c)
 	out_hdr->sadb_msg_seq = 0;
 	out_hdr->sadb_msg_pid = 0;
 
-	pfkey_broadcast(out_skb, BROADCAST_REGISTERED, NULL, xs_net(x));
+	pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_REGISTERED, NULL,
+			xs_net(x));
 	return 0;
 }
 
@@ -3228,7 +3230,8 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct
 		       xfrm_ctx->ctx_len);
 	}
 
-	return pfkey_broadcast(skb, BROADCAST_REGISTERED, NULL, xs_net(x));
+	return pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_REGISTERED, NULL,
+			       xs_net(x));
 }
 
 static struct xfrm_policy *pfkey_compile_policy(struct sock *sk, int opt,
@@ -3426,7 +3429,8 @@ static int pfkey_send_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr,
 	n_port->sadb_x_nat_t_port_port = sport;
 	n_port->sadb_x_nat_t_port_reserved = 0;
 
-	return pfkey_broadcast(skb, BROADCAST_REGISTERED, NULL, xs_net(x));
+	return pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_REGISTERED, NULL,
+			       xs_net(x));
 }
 
 #ifdef CONFIG_NET_KEY_MIGRATE
@@ -3618,7 +3622,7 @@ static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 	}
 
 	/* broadcast migrate message to sockets */
-	pfkey_broadcast(skb, BROADCAST_ALL, NULL, &init_net);
+	pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, &init_net);
 
 	return 0;
 
-- 
2.13.5


From 5560159ebbad0c3e054baba2861f9bccd4f6a8ed Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 14 Aug 2017 14:10:25 -0700
Subject: [PATCH 04/27] dccp: purge write queue in dccp_destroy_sock()

[ Upstream commit 7749d4ff88d31b0be17c8683143135adaaadc6a7 ]

syzkaller reported that DCCP could have a non empty
write queue at dismantle time.

WARNING: CPU: 1 PID: 2953 at net/core/stream.c:199 sk_stream_kill_queues+0x3ce/0x520 net/core/stream.c:199
Kernel panic - not syncing: panic_on_warn set ...

CPU: 1 PID: 2953 Comm: syz-executor0 Not tainted 4.13.0-rc4+ #2
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:16 [inline]
 dump_stack+0x194/0x257 lib/dump_stack.c:52
 panic+0x1e4/0x417 kernel/panic.c:180
 __warn+0x1c4/0x1d9 kernel/panic.c:541
 report_bug+0x211/0x2d0 lib/bug.c:183
 fixup_bug+0x40/0x90 arch/x86/kernel/traps.c:190
 do_trap_no_signal arch/x86/kernel/traps.c:224 [inline]
 do_trap+0x260/0x390 arch/x86/kernel/traps.c:273
 do_error_trap+0x120/0x390 arch/x86/kernel/traps.c:310
 do_invalid_op+0x1b/0x20 arch/x86/kernel/traps.c:323
 invalid_op+0x1e/0x30 arch/x86/entry/entry_64.S:846
RIP: 0010:sk_stream_kill_queues+0x3ce/0x520 net/core/stream.c:199
RSP: 0018:ffff8801d182f108 EFLAGS: 00010297
RAX: ffff8801d1144140 RBX: ffff8801d13cb280 RCX: 0000000000000000
RDX: 0000000000000000 RSI: ffffffff85137b00 RDI: ffff8801d13cb280
RBP: ffff8801d182f148 R08: 0000000000000001 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: ffff8801d13cb4d0
R13: ffff8801d13cb3b8 R14: ffff8801d13cb300 R15: ffff8801d13cb3b8
 inet_csk_destroy_sock+0x175/0x3f0 net/ipv4/inet_connection_sock.c:835
 dccp_close+0x84d/0xc10 net/dccp/proto.c:1067
 inet_release+0xed/0x1c0 net/ipv4/af_inet.c:425
 sock_release+0x8d/0x1e0 net/socket.c:597
 sock_close+0x16/0x20 net/socket.c:1126
 __fput+0x327/0x7e0 fs/file_table.c:210
 ____fput+0x15/0x20 fs/file_table.c:246
 task_work_run+0x18a/0x260 kernel/task_work.c:116
 exit_task_work include/linux/task_work.h:21 [inline]
 do_exit+0xa32/0x1b10 kernel/exit.c:865
 do_group_exit+0x149/0x400 kernel/exit.c:969
 get_signal+0x7e8/0x17e0 kernel/signal.c:2330
 do_signal+0x94/0x1ee0 arch/x86/kernel/signal.c:808
 exit_to_usermode_loop+0x21c/0x2d0 arch/x86/entry/common.c:157
 prepare_exit_to_usermode arch/x86/entry/common.c:194 [inline]
 syscall_return_slowpath+0x3a7/0x450 arch/x86/entry/common.c:263

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/proto.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 9fe25bf63296..86bc40ba6ba5 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -201,10 +201,7 @@ void dccp_destroy_sock(struct sock *sk)
 {
 	struct dccp_sock *dp = dccp_sk(sk);
 
-	/*
-	 * DCCP doesn't use sk_write_queue, just sk_send_head
-	 * for retransmissions
-	 */
+	__skb_queue_purge(&sk->sk_write_queue);
 	if (sk->sk_send_head != NULL) {
 		kfree_skb(sk->sk_send_head);
 		sk->sk_send_head = NULL;
-- 
2.13.5


From bef8f171a698c0eb7a02fafac04964c86e60b27b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 16 Aug 2017 07:03:15 -0700
Subject: [PATCH 05/27] dccp: defer ccid_hc_tx_delete() at dismantle time

[ Upstream commit 120e9dabaf551c6dc03d3a10a1f026376cb1811c ]

syszkaller team reported another problem in DCCP [1]

Problem here is that the structure holding RTO timer
(ccid2_hc_tx_rto_expire() handler) is freed too soon.

We can not use del_timer_sync() to cancel the timer
since this timer wants to grab socket lock (that would risk a dead lock)

Solution is to defer the freeing of memory when all references to
the socket were released. Socket timers do own a reference, so this
should fix the issue.

[1]

==================================================================
BUG: KASAN: use-after-free in ccid2_hc_tx_rto_expire+0x51c/0x5c0 net/dccp/ccids/ccid2.c:144
Read of size 4 at addr ffff8801d2660540 by task kworker/u4:7/3365

CPU: 1 PID: 3365 Comm: kworker/u4:7 Not tainted 4.13.0-rc4+ #3
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Workqueue: events_unbound call_usermodehelper_exec_work
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:16 [inline]
 dump_stack+0x194/0x257 lib/dump_stack.c:52
 print_address_description+0x73/0x250 mm/kasan/report.c:252
 kasan_report_error mm/kasan/report.c:351 [inline]
 kasan_report+0x24e/0x340 mm/kasan/report.c:409
 __asan_report_load4_noabort+0x14/0x20 mm/kasan/report.c:429
 ccid2_hc_tx_rto_expire+0x51c/0x5c0 net/dccp/ccids/ccid2.c:144
 call_timer_fn+0x233/0x830 kernel/time/timer.c:1268
 expire_timers kernel/time/timer.c:1307 [inline]
 __run_timers+0x7fd/0xb90 kernel/time/timer.c:1601
 run_timer_softirq+0x21/0x80 kernel/time/timer.c:1614
 __do_softirq+0x2f5/0xba3 kernel/softirq.c:284
 invoke_softirq kernel/softirq.c:364 [inline]
 irq_exit+0x1cc/0x200 kernel/softirq.c:405
 exiting_irq arch/x86/include/asm/apic.h:638 [inline]
 smp_apic_timer_interrupt+0x76/0xa0 arch/x86/kernel/apic/apic.c:1044
 apic_timer_interrupt+0x93/0xa0 arch/x86/entry/entry_64.S:702
RIP: 0010:arch_local_irq_enable arch/x86/include/asm/paravirt.h:824 [inline]
RIP: 0010:__raw_write_unlock_irq include/linux/rwlock_api_smp.h:267 [inline]
RIP: 0010:_raw_write_unlock_irq+0x56/0x70 kernel/locking/spinlock.c:343
RSP: 0018:ffff8801cd50eaa8 EFLAGS: 00000286 ORIG_RAX: ffffffffffffff10
RAX: dffffc0000000000 RBX: ffffffff85a090c0 RCX: 0000000000000006
RDX: 1ffffffff0b595f3 RSI: 1ffff1003962f989 RDI: ffffffff85acaf98
RBP: ffff8801cd50eab0 R08: 0000000000000001 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: ffff8801cc96ea60
R13: dffffc0000000000 R14: ffff8801cc96e4c0 R15: ffff8801cc96e4c0
 </IRQ>
 release_task+0xe9e/0x1a40 kernel/exit.c:220
 wait_task_zombie kernel/exit.c:1162 [inline]
 wait_consider_task+0x29b8/0x33c0 kernel/exit.c:1389
 do_wait_thread kernel/exit.c:1452 [inline]
 do_wait+0x441/0xa90 kernel/exit.c:1523
 kernel_wait4+0x1f5/0x370 kernel/exit.c:1665
 SYSC_wait4+0x134/0x140 kernel/exit.c:1677
 SyS_wait4+0x2c/0x40 kernel/exit.c:1673
 call_usermodehelper_exec_sync kernel/kmod.c:286 [inline]
 call_usermodehelper_exec_work+0x1a0/0x2c0 kernel/kmod.c:323
 process_one_work+0xbf3/0x1bc0 kernel/workqueue.c:2097
 worker_thread+0x223/0x1860 kernel/workqueue.c:2231
 kthread+0x35e/0x430 kernel/kthread.c:231
 ret_from_fork+0x2a/0x40 arch/x86/entry/entry_64.S:425

Allocated by task 21267:
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
 save_stack+0x43/0xd0 mm/kasan/kasan.c:447
 set_track mm/kasan/kasan.c:459 [inline]
 kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:551
 kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:489
 kmem_cache_alloc+0x127/0x750 mm/slab.c:3561
 ccid_new+0x20e/0x390 net/dccp/ccid.c:151
 dccp_hdlr_ccid+0x27/0x140 net/dccp/feat.c:44
 __dccp_feat_activate+0x142/0x2a0 net/dccp/feat.c:344
 dccp_feat_activate_values+0x34e/0xa90 net/dccp/feat.c:1538
 dccp_rcv_request_sent_state_process net/dccp/input.c:472 [inline]
 dccp_rcv_state_process+0xed1/0x1620 net/dccp/input.c:677
 dccp_v4_do_rcv+0xeb/0x160 net/dccp/ipv4.c:679
 sk_backlog_rcv include/net/sock.h:911 [inline]
 __release_sock+0x124/0x360 net/core/sock.c:2269
 release_sock+0xa4/0x2a0 net/core/sock.c:2784
 inet_wait_for_connect net/ipv4/af_inet.c:557 [inline]
 __inet_stream_connect+0x671/0xf00 net/ipv4/af_inet.c:643
 inet_stream_connect+0x58/0xa0 net/ipv4/af_inet.c:682
 SYSC_connect+0x204/0x470 net/socket.c:1642
 SyS_connect+0x24/0x30 net/socket.c:1623
 entry_SYSCALL_64_fastpath+0x1f/0xbe

Freed by task 3049:
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
 save_stack+0x43/0xd0 mm/kasan/kasan.c:447
 set_track mm/kasan/kasan.c:459 [inline]
 kasan_slab_free+0x71/0xc0 mm/kasan/kasan.c:524
 __cache_free mm/slab.c:3503 [inline]
 kmem_cache_free+0x77/0x280 mm/slab.c:3763
 ccid_hc_tx_delete+0xc5/0x100 net/dccp/ccid.c:190
 dccp_destroy_sock+0x1d1/0x2b0 net/dccp/proto.c:225
 inet_csk_destroy_sock+0x166/0x3f0 net/ipv4/inet_connection_sock.c:833
 dccp_done+0xb7/0xd0 net/dccp/proto.c:145
 dccp_time_wait+0x13d/0x300 net/dccp/minisocks.c:72
 dccp_rcv_reset+0x1d1/0x5b0 net/dccp/input.c:160
 dccp_rcv_state_process+0x8fc/0x1620 net/dccp/input.c:663
 dccp_v4_do_rcv+0xeb/0x160 net/dccp/ipv4.c:679
 sk_backlog_rcv include/net/sock.h:911 [inline]
 __sk_receive_skb+0x33e/0xc00 net/core/sock.c:521
 dccp_v4_rcv+0xef1/0x1c00 net/dccp/ipv4.c:871
 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216
 NF_HOOK include/linux/netfilter.h:248 [inline]
 ip_local_deliver+0x1ce/0x6d0 net/ipv4/ip_input.c:257
 dst_input include/net/dst.h:477 [inline]
 ip_rcv_finish+0x8db/0x19c0 net/ipv4/ip_input.c:397
 NF_HOOK include/linux/netfilter.h:248 [inline]
 ip_rcv+0xc3f/0x17d0 net/ipv4/ip_input.c:488
 __netif_receive_skb_core+0x19af/0x33d0 net/core/dev.c:4417
 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4455
 process_backlog+0x203/0x740 net/core/dev.c:5130
 napi_poll net/core/dev.c:5527 [inline]
 net_rx_action+0x792/0x1910 net/core/dev.c:5593
 __do_softirq+0x2f5/0xba3 kernel/softirq.c:284

The buggy address belongs to the object at ffff8801d2660100
 which belongs to the cache ccid2_hc_tx_sock of size 1240
The buggy address is located 1088 bytes inside of
 1240-byte region [ffff8801d2660100, ffff8801d26605d8)
The buggy address belongs to the page:
page:ffffea0007499800 count:1 mapcount:0 mapping:ffff8801d2660100 index:0x0 compound_mapcount: 0
flags: 0x200000000008100(slab|head)
raw: 0200000000008100 ffff8801d2660100 0000000000000000 0000000100000005
raw: ffffea00075271a0 ffffea0007538820 ffff8801d3aef9c0 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff8801d2660400: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff8801d2660480: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff8801d2660500: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                                           ^
 ffff8801d2660580: fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc fc
 ffff8801d2660600: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
==================================================================

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/proto.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 86bc40ba6ba5..b68168fcc06a 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -24,6 +24,7 @@
 #include <net/checksum.h>
 
 #include <net/inet_sock.h>
+#include <net/inet_common.h>
 #include <net/sock.h>
 #include <net/xfrm.h>
 
@@ -170,6 +171,15 @@ const char *dccp_packet_name(const int type)
 
 EXPORT_SYMBOL_GPL(dccp_packet_name);
 
+static void dccp_sk_destruct(struct sock *sk)
+{
+	struct dccp_sock *dp = dccp_sk(sk);
+
+	ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk);
+	dp->dccps_hc_tx_ccid = NULL;
+	inet_sock_destruct(sk);
+}
+
 int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized)
 {
 	struct dccp_sock *dp = dccp_sk(sk);
@@ -179,6 +189,7 @@ int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized)
 	icsk->icsk_syn_retries	= sysctl_dccp_request_retries;
 	sk->sk_state		= DCCP_CLOSED;
 	sk->sk_write_space	= dccp_write_space;
+	sk->sk_destruct		= dccp_sk_destruct;
 	icsk->icsk_sync_mss	= dccp_sync_mss;
 	dp->dccps_mss_cache	= 536;
 	dp->dccps_rate_last	= jiffies;
@@ -219,8 +230,7 @@ void dccp_destroy_sock(struct sock *sk)
 		dp->dccps_hc_rx_ackvec = NULL;
 	}
 	ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk);
-	ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk);
-	dp->dccps_hc_rx_ccid = dp->dccps_hc_tx_ccid = NULL;
+	dp->dccps_hc_rx_ccid = NULL;
 
 	/* clean up feature negotiation state */
 	dccp_feat_list_purge(&dp->dccps_featneg);
-- 
2.13.5


From 168a84f006de09a6c5e67cedacd386a9a3c0ec2b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 15 Aug 2017 05:26:17 -0700
Subject: [PATCH 06/27] ipv4: fix NULL dereference in free_fib_info_rcu()

[ Upstream commit 187e5b3ac84d3421d2de3aca949b2791fbcad554 ]

If fi->fib_metrics could not be allocated in fib_create_info()
we attempt to dereference a NULL pointer in free_fib_info_rcu() :

    m = fi->fib_metrics;
    if (m != &dst_default_metrics && atomic_dec_and_test(&m->refcnt))
            kfree(m);

Before my recent patch, we used to call kfree(NULL) and nothing wrong
happened.

Instead of using RCU to defer freeing while we are under memory stress,
it seems better to take immediate action.

This was reported by syzkaller team.

Fixes: 3fb07daff8e9 ("ipv4: add reference counting to metrics")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_semantics.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index ce7bc2e5175a..ac9a8fbbacfd 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1033,15 +1033,17 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 	fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL);
 	if (!fi)
 		goto failure;
-	fib_info_cnt++;
 	if (cfg->fc_mx) {
 		fi->fib_metrics = kzalloc(sizeof(*fi->fib_metrics), GFP_KERNEL);
-		if (!fi->fib_metrics)
-			goto failure;
+		if (unlikely(!fi->fib_metrics)) {
+			kfree(fi);
+			return ERR_PTR(err);
+		}
 		atomic_set(&fi->fib_metrics->refcnt, 1);
-	} else
+	} else {
 		fi->fib_metrics = (struct dst_metrics *)&dst_default_metrics;
-
+	}
+	fib_info_cnt++;
 	fi->fib_net = net;
 	fi->fib_protocol = cfg->fc_protocol;
 	fi->fib_scope = cfg->fc_scope;
-- 
2.13.5


From d758e8c1af1c62eabe40a3fdd4648d89b8c9e0f3 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Date: Tue, 15 Aug 2017 16:37:04 +0300
Subject: [PATCH 07/27] net_sched/sfq: update hierarchical backlog when drop
 packet

[ Upstream commit 325d5dc3f7e7c2840b65e4a2988c082c2c0025c5 ]

When sfq_enqueue() drops head packet or packet from another queue it
have to update backlog at upper qdiscs too.

Fixes: 2ccccf5fb43f ("net_sched: update hierarchical backlog too")
Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_sfq.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 332d94be6e1c..22451a9eb89d 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -435,6 +435,7 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
 		qdisc_drop(head, sch, to_free);
 
 		slot_queue_add(slot, skb);
+		qdisc_tree_reduce_backlog(sch, 0, delta);
 		return NET_XMIT_CN;
 	}
 
@@ -466,8 +467,10 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
 	/* Return Congestion Notification only if we dropped a packet
 	 * from this flow.
 	 */
-	if (qlen != slot->qlen)
+	if (qlen != slot->qlen) {
+		qdisc_tree_reduce_backlog(sch, 0, dropped - qdisc_pkt_len(skb));
 		return NET_XMIT_CN;
+	}
 
 	/* As we dropped a packet, better let upper stack know this */
 	qdisc_tree_reduce_backlog(sch, 1, dropped);
-- 
2.13.5


From 79543be0b28fae543650dbf86bd54251b5c3d472 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Date: Tue, 15 Aug 2017 16:39:05 +0300
Subject: [PATCH 08/27] net_sched: remove warning from qdisc_hash_add

[ Upstream commit c90e95147c27b1780e76c6e8fea1b5c78d7d387f ]

It was added in commit e57a784d8cae ("pkt_sched: set root qdisc
before change() in attach_default_qdiscs()") to hide duplicates
from "tc qdisc show" for incative deivices.

After 59cc1f61f ("net: sched: convert qdisc linked list to hashtable")
it triggered when classful qdisc is added to inactive device because
default qdiscs are added before switching root qdisc.

Anyway after commit ea3274695353 ("net: sched: avoid duplicates in
qdisc dump") duplicates are filtered right in dumper.

Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_api.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index cfdbfa18a95e..fdbbdfd8e9a8 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -286,9 +286,6 @@ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle)
 void qdisc_hash_add(struct Qdisc *q, bool invisible)
 {
 	if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) {
-		struct Qdisc *root = qdisc_dev(q)->qdisc;
-
-		WARN_ON_ONCE(root == &noop_qdisc);
 		ASSERT_RTNL();
 		hash_add_rcu(qdisc_dev(q)->qdisc_hash, &q->hash, q->handle);
 		if (invisible)
-- 
2.13.5


From 91d3e96ab5907cc4f7c6e0483845179996db8c7b Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 16 Aug 2017 01:45:33 +0200
Subject: [PATCH 09/27] bpf: fix bpf_trace_printk on 32 bit archs

[ Upstream commit 88a5c690b66110ad255380d8f629c629cf6ca559 ]

James reported that on MIPS32 bpf_trace_printk() is currently
broken while MIPS64 works fine:

  bpf_trace_printk() uses conditional operators to attempt to
  pass different types to __trace_printk() depending on the
  format operators. This doesn't work as intended on 32-bit
  architectures where u32 and long are passed differently to
  u64, since the result of C conditional operators follows the
  "usual arithmetic conversions" rules, such that the values
  passed to __trace_printk() will always be u64 [causing issues
  later in the va_list handling for vscnprintf()].

  For example the samples/bpf/tracex5 test printed lines like
  below on MIPS32, where the fd and buf have come from the u64
  fd argument, and the size from the buf argument:

    [...] 1180.941542: 0x00000001: write(fd=1, buf=  (null), size=6258688)

  Instead of this:

    [...] 1625.616026: 0x00000001: write(fd=1, buf=009e4000, size=512)

One way to get it working is to expand various combinations
of argument types into 8 different combinations for 32 bit
and 64 bit kernels. Fix tested by James on MIPS32 and MIPS64
as well that it resolves the issue.

Fixes: 9c959c863f82 ("tracing: Allow BPF programs to call bpf_trace_printk()")
Reported-by: James Hogan <james.hogan@imgtec.com>
Tested-by: James Hogan <james.hogan@imgtec.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/trace/bpf_trace.c | 34 ++++++++++++++++++++++++++++++----
 1 file changed, 30 insertions(+), 4 deletions(-)

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 460a031c77e5..d521b301dee9 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -203,10 +203,36 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
 		fmt_cnt++;
 	}
 
-	return __trace_printk(1/* fake ip will not be printed */, fmt,
-			      mod[0] == 2 ? arg1 : mod[0] == 1 ? (long) arg1 : (u32) arg1,
-			      mod[1] == 2 ? arg2 : mod[1] == 1 ? (long) arg2 : (u32) arg2,
-			      mod[2] == 2 ? arg3 : mod[2] == 1 ? (long) arg3 : (u32) arg3);
+/* Horrid workaround for getting va_list handling working with different
+ * argument type combinations generically for 32 and 64 bit archs.
+ */
+#define __BPF_TP_EMIT()	__BPF_ARG3_TP()
+#define __BPF_TP(...)							\
+	__trace_printk(1 /* Fake ip will not be printed. */,		\
+		       fmt, ##__VA_ARGS__)
+
+#define __BPF_ARG1_TP(...)						\
+	((mod[0] == 2 || (mod[0] == 1 && __BITS_PER_LONG == 64))	\
+	  ? __BPF_TP(arg1, ##__VA_ARGS__)				\
+	  : ((mod[0] == 1 || (mod[0] == 0 && __BITS_PER_LONG == 32))	\
+	      ? __BPF_TP((long)arg1, ##__VA_ARGS__)			\
+	      : __BPF_TP((u32)arg1, ##__VA_ARGS__)))
+
+#define __BPF_ARG2_TP(...)						\
+	((mod[1] == 2 || (mod[1] == 1 && __BITS_PER_LONG == 64))	\
+	  ? __BPF_ARG1_TP(arg2, ##__VA_ARGS__)				\
+	  : ((mod[1] == 1 || (mod[1] == 0 && __BITS_PER_LONG == 32))	\
+	      ? __BPF_ARG1_TP((long)arg2, ##__VA_ARGS__)		\
+	      : __BPF_ARG1_TP((u32)arg2, ##__VA_ARGS__)))
+
+#define __BPF_ARG3_TP(...)						\
+	((mod[2] == 2 || (mod[2] == 1 && __BITS_PER_LONG == 64))	\
+	  ? __BPF_ARG2_TP(arg3, ##__VA_ARGS__)				\
+	  : ((mod[2] == 1 || (mod[2] == 0 && __BITS_PER_LONG == 32))	\
+	      ? __BPF_ARG2_TP((long)arg3, ##__VA_ARGS__)		\
+	      : __BPF_ARG2_TP((u32)arg3, ##__VA_ARGS__)))
+
+	return __BPF_TP_EMIT();
 }
 
 static const struct bpf_func_proto bpf_trace_printk_proto = {
-- 
2.13.5


From a748e13990ec10436015a1039ec8b6df90bde2a8 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 15 Aug 2017 18:38:42 -0700
Subject: [PATCH 10/27] net: igmp: Use ingress interface rather than vrf device

[ Upstream commit c7b725be84985532161bcb4fbecd056326998a77 ]

Anuradha reported that statically added groups for interfaces enslaved
to a VRF device were not persisting. The problem is that igmp queries
and reports need to use the data in the in_dev for the real ingress
device rather than the VRF device. Update igmp_rcv accordingly.

Fixes: e58e41596811 ("net: Enable support for VRF with ipv4 multicast")
Reported-by: Anuradha Karuppiah <anuradhak@cumulusnetworks.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/igmp.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 3db1adb6b7a0..abdbe79ee175 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -1007,10 +1007,18 @@ int igmp_rcv(struct sk_buff *skb)
 {
 	/* This basically follows the spec line by line -- see RFC1112 */
 	struct igmphdr *ih;
-	struct in_device *in_dev = __in_dev_get_rcu(skb->dev);
+	struct net_device *dev = skb->dev;
+	struct in_device *in_dev;
 	int len = skb->len;
 	bool dropped = true;
 
+	if (netif_is_l3_master(dev)) {
+		dev = dev_get_by_index_rcu(dev_net(dev), IPCB(skb)->iif);
+		if (!dev)
+			goto drop;
+	}
+
+	in_dev = __in_dev_get_rcu(dev);
 	if (!in_dev)
 		goto drop;
 
-- 
2.13.5


From 92290c0d678175d8cfc362658c737d705bfb305c Mon Sep 17 00:00:00 2001
From: Liping Zhang <zlpnobody@gmail.com>
Date: Wed, 16 Aug 2017 13:30:07 +0800
Subject: [PATCH 11/27] openvswitch: fix skb_panic due to the incorrect actions
 attrlen

[ Upstream commit 494bea39f3201776cdfddc232705f54a0bd210c4 ]

For sw_flow_actions, the actions_len only represents the kernel part's
size, and when we dump the actions to the userspace, we will do the
convertions, so it's true size may become bigger than the actions_len.

But unfortunately, for OVS_PACKET_ATTR_ACTIONS, we use the actions_len
to alloc the skbuff, so the user_skb's size may become insufficient and
oops will happen like this:
  skbuff: skb_over_panic: text:ffffffff8148fabf len:1749 put:157 head:
  ffff881300f39000 data:ffff881300f39000 tail:0x6d5 end:0x6c0 dev:<NULL>
  ------------[ cut here ]------------
  kernel BUG at net/core/skbuff.c:129!
  [...]
  Call Trace:
   <IRQ>
   [<ffffffff8148be82>] skb_put+0x43/0x44
   [<ffffffff8148fabf>] skb_zerocopy+0x6c/0x1f4
   [<ffffffffa0290d36>] queue_userspace_packet+0x3a3/0x448 [openvswitch]
   [<ffffffffa0292023>] ovs_dp_upcall+0x30/0x5c [openvswitch]
   [<ffffffffa028d435>] output_userspace+0x132/0x158 [openvswitch]
   [<ffffffffa01e6890>] ? ip6_rcv_finish+0x74/0x77 [ipv6]
   [<ffffffffa028e277>] do_execute_actions+0xcc1/0xdc8 [openvswitch]
   [<ffffffffa028e3f2>] ovs_execute_actions+0x74/0x106 [openvswitch]
   [<ffffffffa0292130>] ovs_dp_process_packet+0xe1/0xfd [openvswitch]
   [<ffffffffa0292b77>] ? key_extract+0x63c/0x8d5 [openvswitch]
   [<ffffffffa029848b>] ovs_vport_receive+0xa1/0xc3 [openvswitch]
  [...]

Also we can find that the actions_len is much little than the orig_len:
  crash> struct sw_flow_actions 0xffff8812f539d000
  struct sw_flow_actions {
    rcu = {
      next = 0xffff8812f5398800,
      func = 0xffffe3b00035db32
    },
    orig_len = 1384,
    actions_len = 592,
    actions = 0xffff8812f539d01c
  }

So as a quick fix, use the orig_len instead of the actions_len to alloc
the user_skb.

Last, this oops happened on our system running a relative old kernel, but
the same risk still exists on the mainline, since we use the wrong
actions_len from the beginning.

Fixes: ccea74457bbd ("openvswitch: include datapath actions with sampled-packet upcall to userspace")
Cc: Neil McKee <neil.mckee@inmon.com>
Signed-off-by: Liping Zhang <zlpnobody@gmail.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/actions.c  | 1 +
 net/openvswitch/datapath.c | 7 ++++---
 net/openvswitch/datapath.h | 2 ++
 3 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index e4610676299b..a54a556fcdb5 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -1337,6 +1337,7 @@ int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
 		goto out;
 	}
 
+	OVS_CB(skb)->acts_origlen = acts->orig_len;
 	err = do_execute_actions(dp, skb, key,
 				 acts->actions, acts->actions_len);
 
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 7b17da9a94a0..57ce10b6cf6b 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -381,7 +381,7 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
 }
 
 static size_t upcall_msg_size(const struct dp_upcall_info *upcall_info,
-			      unsigned int hdrlen)
+			      unsigned int hdrlen, int actions_attrlen)
 {
 	size_t size = NLMSG_ALIGN(sizeof(struct ovs_header))
 		+ nla_total_size(hdrlen) /* OVS_PACKET_ATTR_PACKET */
@@ -398,7 +398,7 @@ static size_t upcall_msg_size(const struct dp_upcall_info *upcall_info,
 
 	/* OVS_PACKET_ATTR_ACTIONS */
 	if (upcall_info->actions_len)
-		size += nla_total_size(upcall_info->actions_len);
+		size += nla_total_size(actions_attrlen);
 
 	/* OVS_PACKET_ATTR_MRU */
 	if (upcall_info->mru)
@@ -465,7 +465,8 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 	else
 		hlen = skb->len;
 
-	len = upcall_msg_size(upcall_info, hlen - cutlen);
+	len = upcall_msg_size(upcall_info, hlen - cutlen,
+			      OVS_CB(skb)->acts_origlen);
 	user_skb = genlmsg_new(len, GFP_ATOMIC);
 	if (!user_skb) {
 		err = -ENOMEM;
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index da931bdef8a7..98a28f78aff2 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -98,12 +98,14 @@ struct datapath {
  * @input_vport: The original vport packet came in on. This value is cached
  * when a packet is received by OVS.
  * @mru: The maximum received fragement size; 0 if the packet is not
+ * @acts_origlen: The netlink size of the flow actions applied to this skb.
  * @cutlen: The number of bytes from the packet end to be removed.
  * fragmented.
  */
 struct ovs_skb_cb {
 	struct vport		*input_vport;
 	u16			mru;
+	u16			acts_origlen;
 	u32			cutlen;
 };
 #define OVS_CB(skb) ((struct ovs_skb_cb *)(skb)->cb)
-- 
2.13.5


From 10ce377e2fdbca671f764b691d8f8537f558d136 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 16 Aug 2017 10:36:47 -0700
Subject: [PATCH 12/27] ptr_ring: use kmalloc_array()

[ Upstream commit 81fbfe8adaf38d4f5a98c19bebfd41c5d6acaee8 ]

As found by syzkaller, malicious users can set whatever tx_queue_len
on a tun device and eventually crash the kernel.

Lets remove the ALIGN(XXX, SMP_CACHE_BYTES) thing since a small
ring buffer is not fast anyway.

Fixes: 2e0ab8ca83c1 ("ptr_ring: array based FIFO for pointers")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ptr_ring.h  | 9 +++++----
 include/linux/skb_array.h | 3 ++-
 2 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h
index 6b2e0dd88569..feff771e8ea0 100644
--- a/include/linux/ptr_ring.h
+++ b/include/linux/ptr_ring.h
@@ -371,9 +371,9 @@ static inline void *ptr_ring_consume_bh(struct ptr_ring *r)
 	__PTR_RING_PEEK_CALL_v; \
 })
 
-static inline void **__ptr_ring_init_queue_alloc(int size, gfp_t gfp)
+static inline void **__ptr_ring_init_queue_alloc(unsigned int size, gfp_t gfp)
 {
-	return kzalloc(ALIGN(size * sizeof(void *), SMP_CACHE_BYTES), gfp);
+	return kcalloc(size, sizeof(void *), gfp);
 }
 
 static inline void __ptr_ring_set_size(struct ptr_ring *r, int size)
@@ -462,7 +462,8 @@ static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp,
  * In particular if you consume ring in interrupt or BH context, you must
  * disable interrupts/BH when doing so.
  */
-static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, int nrings,
+static inline int ptr_ring_resize_multiple(struct ptr_ring **rings,
+					   unsigned int nrings,
 					   int size,
 					   gfp_t gfp, void (*destroy)(void *))
 {
@@ -470,7 +471,7 @@ static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, int nrings,
 	void ***queues;
 	int i;
 
-	queues = kmalloc(nrings * sizeof *queues, gfp);
+	queues = kmalloc_array(nrings, sizeof(*queues), gfp);
 	if (!queues)
 		goto noqueues;
 
diff --git a/include/linux/skb_array.h b/include/linux/skb_array.h
index f4dfade428f0..be8b902b5845 100644
--- a/include/linux/skb_array.h
+++ b/include/linux/skb_array.h
@@ -162,7 +162,8 @@ static inline int skb_array_resize(struct skb_array *a, int size, gfp_t gfp)
 }
 
 static inline int skb_array_resize_multiple(struct skb_array **rings,
-					    int nrings, int size, gfp_t gfp)
+					    int nrings, unsigned int size,
+					    gfp_t gfp)
 {
 	BUILD_BUG_ON(offsetof(struct skb_array, ring));
 	return ptr_ring_resize_multiple((struct ptr_ring **)rings,
-- 
2.13.5


From 0ddde403729bd9b98f956e1db5926c2d0d99809a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 16 Aug 2017 11:09:12 -0700
Subject: [PATCH 13/27] ipv4: better IP_MAX_MTU enforcement

[ Upstream commit c780a049f9bf442314335372c9abc4548bfe3e44 ]

While working on yet another syzkaller report, I found
that our IP_MAX_MTU enforcements were not properly done.

gcc seems to reload dev->mtu for min(dev->mtu, IP_MAX_MTU), and
final result can be bigger than IP_MAX_MTU :/

This is a problem because device mtu can be changed on other cpus or
threads.

While this patch does not fix the issue I am working on, it is
probably worth addressing it.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h | 4 ++--
 net/ipv4/route.c | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index 821cedcc8e73..0cf7f5a65fe6 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -352,7 +352,7 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst,
 	    !forwarding)
 		return dst_mtu(dst);
 
-	return min(dst->dev->mtu, IP_MAX_MTU);
+	return min(READ_ONCE(dst->dev->mtu), IP_MAX_MTU);
 }
 
 static inline unsigned int ip_skb_dst_mtu(struct sock *sk,
@@ -364,7 +364,7 @@ static inline unsigned int ip_skb_dst_mtu(struct sock *sk,
 		return ip_dst_mtu_maybe_forward(skb_dst(skb), forwarding);
 	}
 
-	return min(skb_dst(skb)->dev->mtu, IP_MAX_MTU);
+	return min(READ_ONCE(skb_dst(skb)->dev->mtu), IP_MAX_MTU);
 }
 
 u32 ip_idents_reserve(u32 hash, int segs);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 6883b3d4ba8f..22ba873546c3 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1268,7 +1268,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst)
 	if (mtu)
 		return mtu;
 
-	mtu = dst->dev->mtu;
+	mtu = READ_ONCE(dst->dev->mtu);
 
 	if (unlikely(dst_metric_locked(dst, RTAX_MTU))) {
 		if (rt->rt_uses_gateway && mtu > 576)
-- 
2.13.5


From 0622af29e530d327687af157dd0c158fb261cac2 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Fri, 18 Aug 2017 12:11:50 +0100
Subject: [PATCH 14/27] nfp: fix infinite loop on umapping cleanup

[ Upstream commit eac2c68d663effb077210218788952b5a0c1f60e ]

The while loop that performs the dma page unmapping never decrements
index counter f and hence loops forever. Fix this with a pre-decrement
on f.

Detected by CoverityScan, CID#1357309 ("Infinite loop")

Fixes: 4c3523623dc0 ("net: add driver for Netronome NFP4000/NFP6000 NIC VFs")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 82bd6b0935f1..fd4a785431ac 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -881,8 +881,7 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
 	return NETDEV_TX_OK;
 
 err_unmap:
-	--f;
-	while (f >= 0) {
+	while (--f >= 0) {
 		frag = &skb_shinfo(skb)->frags[f];
 		dma_unmap_page(dp->dev, tx_ring->txbufs[wr_idx].dma_addr,
 			       skb_frag_size(frag), DMA_TO_DEVICE);
-- 
2.13.5


From 4c348dde87047d562cebc14e3b68b1cf1d0533b9 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 18 Aug 2017 13:39:56 -0700
Subject: [PATCH 15/27] tun: handle register_netdevice() failures properly

[ Upstream commit ff244c6b29b176f3f448bc75e55df297225e1b3a ]

syzkaller reported a double free [1], caused by the fact
that tun driver was not updated properly when priv_destructor
was added.

When/if register_netdevice() fails, priv_destructor() must have been
called already.

[1]
BUG: KASAN: double-free or invalid-free in selinux_tun_dev_free_security+0x15/0x20 security/selinux/hooks.c:5023

CPU: 0 PID: 2919 Comm: syzkaller227220 Not tainted 4.13.0-rc4+ #23
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:16 [inline]
 dump_stack+0x194/0x257 lib/dump_stack.c:52
 print_address_description+0x7f/0x260 mm/kasan/report.c:252
 kasan_report_double_free+0x55/0x80 mm/kasan/report.c:333
 kasan_slab_free+0xa0/0xc0 mm/kasan/kasan.c:514
 __cache_free mm/slab.c:3503 [inline]
 kfree+0xd3/0x260 mm/slab.c:3820
 selinux_tun_dev_free_security+0x15/0x20 security/selinux/hooks.c:5023
 security_tun_dev_free_security+0x48/0x80 security/security.c:1512
 tun_set_iff drivers/net/tun.c:1884 [inline]
 __tun_chr_ioctl+0x2ce6/0x3d50 drivers/net/tun.c:2064
 tun_chr_ioctl+0x2a/0x40 drivers/net/tun.c:2309
 vfs_ioctl fs/ioctl.c:45 [inline]
 do_vfs_ioctl+0x1b1/0x1520 fs/ioctl.c:685
 SYSC_ioctl fs/ioctl.c:700 [inline]
 SyS_ioctl+0x8f/0xc0 fs/ioctl.c:691
 entry_SYSCALL_64_fastpath+0x1f/0xbe
RIP: 0033:0x443ff9
RSP: 002b:00007ffc34271f68 EFLAGS: 00000217 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 00000000004002e0 RCX: 0000000000443ff9
RDX: 0000000020533000 RSI: 00000000400454ca RDI: 0000000000000003
RBP: 0000000000000086 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000217 R12: 0000000000401ce0
R13: 0000000000401d70 R14: 0000000000000000 R15: 0000000000000000

Allocated by task 2919:
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
 save_stack+0x43/0xd0 mm/kasan/kasan.c:447
 set_track mm/kasan/kasan.c:459 [inline]
 kasan_kmalloc+0xaa/0xd0 mm/kasan/kasan.c:551
 kmem_cache_alloc_trace+0x101/0x6f0 mm/slab.c:3627
 kmalloc include/linux/slab.h:493 [inline]
 kzalloc include/linux/slab.h:666 [inline]
 selinux_tun_dev_alloc_security+0x49/0x170 security/selinux/hooks.c:5012
 security_tun_dev_alloc_security+0x6d/0xa0 security/security.c:1506
 tun_set_iff drivers/net/tun.c:1839 [inline]
 __tun_chr_ioctl+0x1730/0x3d50 drivers/net/tun.c:2064
 tun_chr_ioctl+0x2a/0x40 drivers/net/tun.c:2309
 vfs_ioctl fs/ioctl.c:45 [inline]
 do_vfs_ioctl+0x1b1/0x1520 fs/ioctl.c:685
 SYSC_ioctl fs/ioctl.c:700 [inline]
 SyS_ioctl+0x8f/0xc0 fs/ioctl.c:691
 entry_SYSCALL_64_fastpath+0x1f/0xbe

Freed by task 2919:
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
 save_stack+0x43/0xd0 mm/kasan/kasan.c:447
 set_track mm/kasan/kasan.c:459 [inline]
 kasan_slab_free+0x6e/0xc0 mm/kasan/kasan.c:524
 __cache_free mm/slab.c:3503 [inline]
 kfree+0xd3/0x260 mm/slab.c:3820
 selinux_tun_dev_free_security+0x15/0x20 security/selinux/hooks.c:5023
 security_tun_dev_free_security+0x48/0x80 security/security.c:1512
 tun_free_netdev+0x13b/0x1b0 drivers/net/tun.c:1563
 register_netdevice+0x8d0/0xee0 net/core/dev.c:7605
 tun_set_iff drivers/net/tun.c:1859 [inline]
 __tun_chr_ioctl+0x1caf/0x3d50 drivers/net/tun.c:2064
 tun_chr_ioctl+0x2a/0x40 drivers/net/tun.c:2309
 vfs_ioctl fs/ioctl.c:45 [inline]
 do_vfs_ioctl+0x1b1/0x1520 fs/ioctl.c:685
 SYSC_ioctl fs/ioctl.c:700 [inline]
 SyS_ioctl+0x8f/0xc0 fs/ioctl.c:691
 entry_SYSCALL_64_fastpath+0x1f/0xbe

The buggy address belongs to the object at ffff8801d2843b40
 which belongs to the cache kmalloc-32 of size 32
The buggy address is located 0 bytes inside of
 32-byte region [ffff8801d2843b40, ffff8801d2843b60)
The buggy address belongs to the page:
page:ffffea000660cea8 count:1 mapcount:0 mapping:ffff8801d2843000 index:0xffff8801d2843fc1
flags: 0x200000000000100(slab)
raw: 0200000000000100 ffff8801d2843000 ffff8801d2843fc1 000000010000003f
raw: ffffea0006626a40 ffffea00066141a0 ffff8801dbc00100
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff8801d2843a00: fb fb fb fb fc fc fc fc fb fb fb fb fc fc fc fc
 ffff8801d2843a80: 00 00 00 fc fc fc fc fc fb fb fb fb fc fc fc fc
>ffff8801d2843b00: 00 00 00 00 fc fc fc fc fb fb fb fb fc fc fc fc
                                           ^
 ffff8801d2843b80: fb fb fb fb fc fc fc fc fb fb fb fb fc fc fc fc
 ffff8801d2843c00: fb fb fb fb fc fc fc fc fb fb fb fb fc fc fc fc

==================================================================

Fixes: cf124db566e6 ("net: Fix inconsistent teardown and release of private netdev state.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 9ee7d4275640..5bd954d12541 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1876,6 +1876,9 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 
 err_detach:
 	tun_detach_all(dev);
+	/* register_netdevice() already called tun_free_netdev() */
+	goto err_free_dev;
+
 err_free_flow:
 	tun_flow_uninit(tun);
 	security_tun_dev_free_security(tun->security);
-- 
2.13.5


From 7bfce86e706f57734a21ea85ac82f810932045d0 Mon Sep 17 00:00:00 2001
From: Alexander Potapenko <glider@google.com>
Date: Wed, 16 Aug 2017 20:16:40 +0200
Subject: [PATCH 16/27] sctp: fully initialize the IPv6 address in
 sctp_v6_to_addr()

[ Upstream commit 15339e441ec46fbc3bf3486bb1ae4845b0f1bb8d ]

KMSAN reported use of uninitialized sctp_addr->v4.sin_addr.s_addr and
sctp_addr->v6.sin6_scope_id in sctp_v6_cmp_addr() (see below).
Make sure all fields of an IPv6 address are initialized, which
guarantees that the IPv4 fields are also initialized.

==================================================================
 BUG: KMSAN: use of uninitialized memory in sctp_v6_cmp_addr+0x8d4/0x9f0
 net/sctp/ipv6.c:517
 CPU: 2 PID: 31056 Comm: syz-executor1 Not tainted 4.11.0-rc5+ #2944
 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs
 01/01/2011
 Call Trace:
  dump_stack+0x172/0x1c0 lib/dump_stack.c:42
  is_logbuf_locked mm/kmsan/kmsan.c:59 [inline]
  kmsan_report+0x12a/0x180 mm/kmsan/kmsan.c:938
  native_save_fl arch/x86/include/asm/irqflags.h:18 [inline]
  arch_local_save_flags arch/x86/include/asm/irqflags.h:72 [inline]
  arch_local_irq_save arch/x86/include/asm/irqflags.h:113 [inline]
  __msan_warning_32+0x61/0xb0 mm/kmsan/kmsan_instr.c:467
  sctp_v6_cmp_addr+0x8d4/0x9f0 net/sctp/ipv6.c:517
  sctp_v6_get_dst+0x8c7/0x1630 net/sctp/ipv6.c:290
  sctp_transport_route+0x101/0x570 net/sctp/transport.c:292
  sctp_assoc_add_peer+0x66d/0x16f0 net/sctp/associola.c:651
  sctp_sendmsg+0x35a5/0x4f90 net/sctp/socket.c:1871
  inet_sendmsg+0x498/0x670 net/ipv4/af_inet.c:762
  sock_sendmsg_nosec net/socket.c:633 [inline]
  sock_sendmsg net/socket.c:643 [inline]
  SYSC_sendto+0x608/0x710 net/socket.c:1696
  SyS_sendto+0x8a/0xb0 net/socket.c:1664
  entry_SYSCALL_64_fastpath+0x13/0x94
 RIP: 0033:0x44b479
 RSP: 002b:00007f6213f21c08 EFLAGS: 00000286 ORIG_RAX: 000000000000002c
 RAX: ffffffffffffffda RBX: 0000000020000000 RCX: 000000000044b479
 RDX: 0000000000000041 RSI: 0000000020edd000 RDI: 0000000000000006
 RBP: 00000000007080a8 R08: 0000000020b85fe4 R09: 000000000000001c
 R10: 0000000000040005 R11: 0000000000000286 R12: 00000000ffffffff
 R13: 0000000000003760 R14: 00000000006e5820 R15: 0000000000ff8000
 origin description: ----dst_saddr@sctp_v6_get_dst
 local variable created at:
  sk_fullsock include/net/sock.h:2321 [inline]
  inet6_sk include/linux/ipv6.h:309 [inline]
  sctp_v6_get_dst+0x91/0x1630 net/sctp/ipv6.c:241
  sctp_transport_route+0x101/0x570 net/sctp/transport.c:292
==================================================================
 BUG: KMSAN: use of uninitialized memory in sctp_v6_cmp_addr+0x8d4/0x9f0
 net/sctp/ipv6.c:517
 CPU: 2 PID: 31056 Comm: syz-executor1 Not tainted 4.11.0-rc5+ #2944
 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs
 01/01/2011
 Call Trace:
  dump_stack+0x172/0x1c0 lib/dump_stack.c:42
  is_logbuf_locked mm/kmsan/kmsan.c:59 [inline]
  kmsan_report+0x12a/0x180 mm/kmsan/kmsan.c:938
  native_save_fl arch/x86/include/asm/irqflags.h:18 [inline]
  arch_local_save_flags arch/x86/include/asm/irqflags.h:72 [inline]
  arch_local_irq_save arch/x86/include/asm/irqflags.h:113 [inline]
  __msan_warning_32+0x61/0xb0 mm/kmsan/kmsan_instr.c:467
  sctp_v6_cmp_addr+0x8d4/0x9f0 net/sctp/ipv6.c:517
  sctp_v6_get_dst+0x8c7/0x1630 net/sctp/ipv6.c:290
  sctp_transport_route+0x101/0x570 net/sctp/transport.c:292
  sctp_assoc_add_peer+0x66d/0x16f0 net/sctp/associola.c:651
  sctp_sendmsg+0x35a5/0x4f90 net/sctp/socket.c:1871
  inet_sendmsg+0x498/0x670 net/ipv4/af_inet.c:762
  sock_sendmsg_nosec net/socket.c:633 [inline]
  sock_sendmsg net/socket.c:643 [inline]
  SYSC_sendto+0x608/0x710 net/socket.c:1696
  SyS_sendto+0x8a/0xb0 net/socket.c:1664
  entry_SYSCALL_64_fastpath+0x13/0x94
 RIP: 0033:0x44b479
 RSP: 002b:00007f6213f21c08 EFLAGS: 00000286 ORIG_RAX: 000000000000002c
 RAX: ffffffffffffffda RBX: 0000000020000000 RCX: 000000000044b479
 RDX: 0000000000000041 RSI: 0000000020edd000 RDI: 0000000000000006
 RBP: 00000000007080a8 R08: 0000000020b85fe4 R09: 000000000000001c
 R10: 0000000000040005 R11: 0000000000000286 R12: 00000000ffffffff
 R13: 0000000000003760 R14: 00000000006e5820 R15: 0000000000ff8000
 origin description: ----dst_saddr@sctp_v6_get_dst
 local variable created at:
  sk_fullsock include/net/sock.h:2321 [inline]
  inet6_sk include/linux/ipv6.h:309 [inline]
  sctp_v6_get_dst+0x91/0x1630 net/sctp/ipv6.c:241
  sctp_transport_route+0x101/0x570 net/sctp/transport.c:292
==================================================================

Signed-off-by: Alexander Potapenko <glider@google.com>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ipv6.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index f5b45b8b8b16..0de5f5f8ddbc 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -510,7 +510,9 @@ static void sctp_v6_to_addr(union sctp_addr *addr, struct in6_addr *saddr,
 {
 	addr->sa.sa_family = AF_INET6;
 	addr->v6.sin6_port = port;
+	addr->v6.sin6_flowinfo = 0;
 	addr->v6.sin6_addr = *saddr;
+	addr->v6.sin6_scope_id = 0;
 }
 
 /* Compare addresses exactly.
-- 
2.13.5


From dea35c23c4fbe3b65430465163531c0e31ba5f94 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 16 Aug 2017 09:41:54 -0700
Subject: [PATCH 17/27] tipc: fix use-after-free

[ Upstream commit 5bfd37b4de5c98e86b12bd13be5aa46c7484a125 ]

syszkaller reported use-after-free in tipc [1]

When msg->rep skb is freed, set the pointer to NULL,
so that caller does not free it again.

[1]

==================================================================
BUG: KASAN: use-after-free in skb_push+0xd4/0xe0 net/core/skbuff.c:1466
Read of size 8 at addr ffff8801c6e71e90 by task syz-executor5/4115

CPU: 1 PID: 4115 Comm: syz-executor5 Not tainted 4.13.0-rc4+ #32
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:16 [inline]
 dump_stack+0x194/0x257 lib/dump_stack.c:52
 print_address_description+0x73/0x250 mm/kasan/report.c:252
 kasan_report_error mm/kasan/report.c:351 [inline]
 kasan_report+0x24e/0x340 mm/kasan/report.c:409
 __asan_report_load8_noabort+0x14/0x20 mm/kasan/report.c:430
 skb_push+0xd4/0xe0 net/core/skbuff.c:1466
 tipc_nl_compat_recv+0x833/0x18f0 net/tipc/netlink_compat.c:1209
 genl_family_rcv_msg+0x7b7/0xfb0 net/netlink/genetlink.c:598
 genl_rcv_msg+0xb2/0x140 net/netlink/genetlink.c:623
 netlink_rcv_skb+0x216/0x440 net/netlink/af_netlink.c:2397
 genl_rcv+0x28/0x40 net/netlink/genetlink.c:634
 netlink_unicast_kernel net/netlink/af_netlink.c:1265 [inline]
 netlink_unicast+0x4e8/0x6f0 net/netlink/af_netlink.c:1291
 netlink_sendmsg+0xa4a/0xe60 net/netlink/af_netlink.c:1854
 sock_sendmsg_nosec net/socket.c:633 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:643
 sock_write_iter+0x31a/0x5d0 net/socket.c:898
 call_write_iter include/linux/fs.h:1743 [inline]
 new_sync_write fs/read_write.c:457 [inline]
 __vfs_write+0x684/0x970 fs/read_write.c:470
 vfs_write+0x189/0x510 fs/read_write.c:518
 SYSC_write fs/read_write.c:565 [inline]
 SyS_write+0xef/0x220 fs/read_write.c:557
 entry_SYSCALL_64_fastpath+0x1f/0xbe
RIP: 0033:0x4512e9
RSP: 002b:00007f3bc8184c08 EFLAGS: 00000216 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 0000000000718000 RCX: 00000000004512e9
RDX: 0000000000000020 RSI: 0000000020fdb000 RDI: 0000000000000006
RBP: 0000000000000086 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000216 R12: 00000000004b5e76
R13: 00007f3bc8184b48 R14: 00000000004b5e86 R15: 0000000000000000

Allocated by task 4115:
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
 save_stack+0x43/0xd0 mm/kasan/kasan.c:447
 set_track mm/kasan/kasan.c:459 [inline]
 kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:551
 kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:489
 kmem_cache_alloc_node+0x13d/0x750 mm/slab.c:3651
 __alloc_skb+0xf1/0x740 net/core/skbuff.c:219
 alloc_skb include/linux/skbuff.h:903 [inline]
 tipc_tlv_alloc+0x26/0xb0 net/tipc/netlink_compat.c:148
 tipc_nl_compat_dumpit+0xf2/0x3c0 net/tipc/netlink_compat.c:248
 tipc_nl_compat_handle net/tipc/netlink_compat.c:1130 [inline]
 tipc_nl_compat_recv+0x756/0x18f0 net/tipc/netlink_compat.c:1199
 genl_family_rcv_msg+0x7b7/0xfb0 net/netlink/genetlink.c:598
 genl_rcv_msg+0xb2/0x140 net/netlink/genetlink.c:623
 netlink_rcv_skb+0x216/0x440 net/netlink/af_netlink.c:2397
 genl_rcv+0x28/0x40 net/netlink/genetlink.c:634
 netlink_unicast_kernel net/netlink/af_netlink.c:1265 [inline]
 netlink_unicast+0x4e8/0x6f0 net/netlink/af_netlink.c:1291
 netlink_sendmsg+0xa4a/0xe60 net/netlink/af_netlink.c:1854
 sock_sendmsg_nosec net/socket.c:633 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:643
 sock_write_iter+0x31a/0x5d0 net/socket.c:898
 call_write_iter include/linux/fs.h:1743 [inline]
 new_sync_write fs/read_write.c:457 [inline]
 __vfs_write+0x684/0x970 fs/read_write.c:470
 vfs_write+0x189/0x510 fs/read_write.c:518
 SYSC_write fs/read_write.c:565 [inline]
 SyS_write+0xef/0x220 fs/read_write.c:557
 entry_SYSCALL_64_fastpath+0x1f/0xbe

Freed by task 4115:
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
 save_stack+0x43/0xd0 mm/kasan/kasan.c:447
 set_track mm/kasan/kasan.c:459 [inline]
 kasan_slab_free+0x71/0xc0 mm/kasan/kasan.c:524
 __cache_free mm/slab.c:3503 [inline]
 kmem_cache_free+0x77/0x280 mm/slab.c:3763
 kfree_skbmem+0x1a1/0x1d0 net/core/skbuff.c:622
 __kfree_skb net/core/skbuff.c:682 [inline]
 kfree_skb+0x165/0x4c0 net/core/skbuff.c:699
 tipc_nl_compat_dumpit+0x36a/0x3c0 net/tipc/netlink_compat.c:260
 tipc_nl_compat_handle net/tipc/netlink_compat.c:1130 [inline]
 tipc_nl_compat_recv+0x756/0x18f0 net/tipc/netlink_compat.c:1199
 genl_family_rcv_msg+0x7b7/0xfb0 net/netlink/genetlink.c:598
 genl_rcv_msg+0xb2/0x140 net/netlink/genetlink.c:623
 netlink_rcv_skb+0x216/0x440 net/netlink/af_netlink.c:2397
 genl_rcv+0x28/0x40 net/netlink/genetlink.c:634
 netlink_unicast_kernel net/netlink/af_netlink.c:1265 [inline]
 netlink_unicast+0x4e8/0x6f0 net/netlink/af_netlink.c:1291
 netlink_sendmsg+0xa4a/0xe60 net/netlink/af_netlink.c:1854
 sock_sendmsg_nosec net/socket.c:633 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:643
 sock_write_iter+0x31a/0x5d0 net/socket.c:898
 call_write_iter include/linux/fs.h:1743 [inline]
 new_sync_write fs/read_write.c:457 [inline]
 __vfs_write+0x684/0x970 fs/read_write.c:470
 vfs_write+0x189/0x510 fs/read_write.c:518
 SYSC_write fs/read_write.c:565 [inline]
 SyS_write+0xef/0x220 fs/read_write.c:557
 entry_SYSCALL_64_fastpath+0x1f/0xbe

The buggy address belongs to the object at ffff8801c6e71dc0
 which belongs to the cache skbuff_head_cache of size 224
The buggy address is located 208 bytes inside of
 224-byte region [ffff8801c6e71dc0, ffff8801c6e71ea0)
The buggy address belongs to the page:
page:ffffea00071b9c40 count:1 mapcount:0 mapping:ffff8801c6e71000 index:0x0
flags: 0x200000000000100(slab)
raw: 0200000000000100 ffff8801c6e71000 0000000000000000 000000010000000c
raw: ffffea0007224a20 ffff8801d98caf48 ffff8801d9e79040 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff8801c6e71d80: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb
 ffff8801c6e71e00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff8801c6e71e80: fb fb fb fb fc fc fc fc fc fc fc fc fc fc fc fc
                         ^
 ffff8801c6e71f00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 ffff8801c6e71f80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
==================================================================

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov  <dvyukov@google.com>
Cc: Jon Maloy <jon.maloy@ericsson.com>
Cc: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/netlink_compat.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 9bfe886ab330..750949dfc1d7 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -258,13 +258,15 @@ static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd,
 	arg = nlmsg_new(0, GFP_KERNEL);
 	if (!arg) {
 		kfree_skb(msg->rep);
+		msg->rep = NULL;
 		return -ENOMEM;
 	}
 
 	err = __tipc_nl_compat_dumpit(cmd, msg, arg);
-	if (err)
+	if (err) {
 		kfree_skb(msg->rep);
-
+		msg->rep = NULL;
+	}
 	kfree_skb(arg);
 
 	return err;
-- 
2.13.5


From c90956996a7f3549184b28c437634dc7128ba188 Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Wed, 16 Aug 2017 11:18:09 -0700
Subject: [PATCH 18/27] ipv6: reset fn->rr_ptr when replacing route

[ Upstream commit 383143f31d7d3525a1dbff733d52fff917f82f15 ]

syzcaller reported the following use-after-free issue in rt6_select():
BUG: KASAN: use-after-free in rt6_select net/ipv6/route.c:755 [inline] at addr ffff8800bc6994e8
BUG: KASAN: use-after-free in ip6_pol_route.isra.46+0x1429/0x1470 net/ipv6/route.c:1084 at addr ffff8800bc6994e8
Read of size 4 by task syz-executor1/439628
CPU: 0 PID: 439628 Comm: syz-executor1 Not tainted 4.3.5+ #8
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
 0000000000000000 ffff88018fe435b0 ffffffff81ca384d ffff8801d3588c00
 ffff8800bc699380 ffff8800bc699500 dffffc0000000000 ffff8801d40a47c0
 ffff88018fe435d8 ffffffff81735751 ffff88018fe43660 ffff8800bc699380
Call Trace:
 [<ffffffff81ca384d>] __dump_stack lib/dump_stack.c:15 [inline]
 [<ffffffff81ca384d>] dump_stack+0xc1/0x124 lib/dump_stack.c:51
sctp: [Deprecated]: syz-executor0 (pid 439615) Use of struct sctp_assoc_value in delayed_ack socket option.
Use struct sctp_sack_info instead
 [<ffffffff81735751>] kasan_object_err+0x21/0x70 mm/kasan/report.c:158
 [<ffffffff817359c4>] print_address_description mm/kasan/report.c:196 [inline]
 [<ffffffff817359c4>] kasan_report_error+0x1b4/0x4a0 mm/kasan/report.c:285
 [<ffffffff81735d93>] kasan_report mm/kasan/report.c:305 [inline]
 [<ffffffff81735d93>] __asan_report_load4_noabort+0x43/0x50 mm/kasan/report.c:325
 [<ffffffff82a28e39>] rt6_select net/ipv6/route.c:755 [inline]
 [<ffffffff82a28e39>] ip6_pol_route.isra.46+0x1429/0x1470 net/ipv6/route.c:1084
 [<ffffffff82a28fb1>] ip6_pol_route_output+0x81/0xb0 net/ipv6/route.c:1203
 [<ffffffff82ab0a50>] fib6_rule_action+0x1f0/0x680 net/ipv6/fib6_rules.c:95
 [<ffffffff8265cbb6>] fib_rules_lookup+0x2a6/0x7a0 net/core/fib_rules.c:223
 [<ffffffff82ab1430>] fib6_rule_lookup+0xd0/0x250 net/ipv6/fib6_rules.c:41
 [<ffffffff82a22006>] ip6_route_output+0x1d6/0x2c0 net/ipv6/route.c:1224
 [<ffffffff829e83d2>] ip6_dst_lookup_tail+0x4d2/0x890 net/ipv6/ip6_output.c:943
 [<ffffffff829e889a>] ip6_dst_lookup_flow+0x9a/0x250 net/ipv6/ip6_output.c:1079
 [<ffffffff82a9f7d8>] ip6_datagram_dst_update+0x538/0xd40 net/ipv6/datagram.c:91
 [<ffffffff82aa0978>] __ip6_datagram_connect net/ipv6/datagram.c:251 [inline]
 [<ffffffff82aa0978>] ip6_datagram_connect+0x518/0xe50 net/ipv6/datagram.c:272
 [<ffffffff82aa1313>] ip6_datagram_connect_v6_only+0x63/0x90 net/ipv6/datagram.c:284
 [<ffffffff8292f790>] inet_dgram_connect+0x170/0x1f0 net/ipv4/af_inet.c:564
 [<ffffffff82565547>] SYSC_connect+0x1a7/0x2f0 net/socket.c:1582
 [<ffffffff8256a649>] SyS_connect+0x29/0x30 net/socket.c:1563
 [<ffffffff82c72032>] entry_SYSCALL_64_fastpath+0x12/0x17
Object at ffff8800bc699380, in cache ip6_dst_cache size: 384

The root cause of it is that in fib6_add_rt2node(), when it replaces an
existing route with the new one, it does not update fn->rr_ptr.
This commit resets fn->rr_ptr to NULL when it points to a route which is
replaced in fib6_add_rt2node().

Fixes: 27596472473a ("ipv6: fix ECMP route replacement")
Signed-off-by: Wei Wang <weiwan@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_fib.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index e4e9f752ebbf..e93932d70620 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -912,6 +912,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 		}
 		nsiblings = iter->rt6i_nsiblings;
 		fib6_purge_rt(iter, fn, info->nl_net);
+		if (fn->rr_ptr == iter)
+			fn->rr_ptr = NULL;
 		rt6_release(iter);
 
 		if (nsiblings) {
@@ -924,6 +926,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 				if (rt6_qualify_for_ecmp(iter)) {
 					*ins = iter->dst.rt6_next;
 					fib6_purge_rt(iter, fn, info->nl_net);
+					if (fn->rr_ptr == iter)
+						fn->rr_ptr = NULL;
 					rt6_release(iter);
 					nsiblings--;
 				} else {
-- 
2.13.5


From ca2ec1ce5afff4d0dc09a57b00e8917d52872eb4 Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Fri, 18 Aug 2017 17:14:49 -0700
Subject: [PATCH 19/27] ipv6: repair fib6 tree in failure case

[ Upstream commit 348a4002729ccab8b888b38cbc099efa2f2a2036 ]

In fib6_add(), it is possible that fib6_add_1() picks an intermediate
node and sets the node's fn->leaf to NULL in order to add this new
route. However, if fib6_add_rt2node() fails to add the new
route for some reason, fn->leaf will be left as NULL and could
potentially cause crash when fn->leaf is accessed in fib6_locate().
This patch makes sure fib6_repair_tree() is called to properly repair
fn->leaf in the above failure case.

Here is the syzkaller reported general protection fault in fib6_locate:
kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] SMP KASAN
Modules linked in:
CPU: 0 PID: 40937 Comm: syz-executor3 Not tainted
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
task: ffff8801d7d64100 ti: ffff8801d01a0000 task.ti: ffff8801d01a0000
RIP: 0010:[<ffffffff82a3e0e1>]  [<ffffffff82a3e0e1>] __ipv6_prefix_equal64_half include/net/ipv6.h:475 [inline]
RIP: 0010:[<ffffffff82a3e0e1>]  [<ffffffff82a3e0e1>] ipv6_prefix_equal include/net/ipv6.h:492 [inline]
RIP: 0010:[<ffffffff82a3e0e1>]  [<ffffffff82a3e0e1>] fib6_locate_1 net/ipv6/ip6_fib.c:1210 [inline]
RIP: 0010:[<ffffffff82a3e0e1>]  [<ffffffff82a3e0e1>] fib6_locate+0x281/0x3c0 net/ipv6/ip6_fib.c:1233
RSP: 0018:ffff8801d01a36a8  EFLAGS: 00010202
RAX: 0000000000000020 RBX: ffff8801bc790e00 RCX: ffffc90002983000
RDX: 0000000000001219 RSI: ffff8801d01a37a0 RDI: 0000000000000100
RBP: ffff8801d01a36f0 R08: 00000000000000ff R09: 0000000000000000
R10: 0000000000000003 R11: 0000000000000000 R12: 0000000000000001
R13: dffffc0000000000 R14: ffff8801d01a37a0 R15: 0000000000000000
FS:  00007f6afd68c700(0000) GS:ffff8801db400000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000004c6340 CR3: 00000000ba41f000 CR4: 00000000001426f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Stack:
 ffff8801d01a37a8 ffff8801d01a3780 ffffed003a0346f5 0000000c82a23ea0
 ffff8800b7bd7700 ffff8801d01a3780 ffff8800b6a1c940 ffffffff82a23ea0
 ffff8801d01a3920 ffff8801d01a3748 ffffffff82a223d6 ffff8801d7d64988
Call Trace:
 [<ffffffff82a223d6>] ip6_route_del+0x106/0x570 net/ipv6/route.c:2109
 [<ffffffff82a23f9d>] inet6_rtm_delroute+0xfd/0x100 net/ipv6/route.c:3075
 [<ffffffff82621359>] rtnetlink_rcv_msg+0x549/0x7a0 net/core/rtnetlink.c:3450
 [<ffffffff8274c1d1>] netlink_rcv_skb+0x141/0x370 net/netlink/af_netlink.c:2281
 [<ffffffff82613ddf>] rtnetlink_rcv+0x2f/0x40 net/core/rtnetlink.c:3456
 [<ffffffff8274ad38>] netlink_unicast_kernel net/netlink/af_netlink.c:1206 [inline]
 [<ffffffff8274ad38>] netlink_unicast+0x518/0x750 net/netlink/af_netlink.c:1232
 [<ffffffff8274b83e>] netlink_sendmsg+0x8ce/0xc30 net/netlink/af_netlink.c:1778
 [<ffffffff82564aff>] sock_sendmsg_nosec net/socket.c:609 [inline]
 [<ffffffff82564aff>] sock_sendmsg+0xcf/0x110 net/socket.c:619
 [<ffffffff82564d62>] sock_write_iter+0x222/0x3a0 net/socket.c:834
 [<ffffffff8178523d>] new_sync_write+0x1dd/0x2b0 fs/read_write.c:478
 [<ffffffff817853f4>] __vfs_write+0xe4/0x110 fs/read_write.c:491
 [<ffffffff81786c38>] vfs_write+0x178/0x4b0 fs/read_write.c:538
 [<ffffffff817892a9>] SYSC_write fs/read_write.c:585 [inline]
 [<ffffffff817892a9>] SyS_write+0xd9/0x1b0 fs/read_write.c:577
 [<ffffffff82c71e32>] entry_SYSCALL_64_fastpath+0x12/0x17

Note: there is no "Fixes" tag as this seems to be a bug introduced
very early.

Signed-off-by: Wei Wang <weiwan@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_fib.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index e93932d70620..cd8dd8c4e819 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1016,7 +1016,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 			/* Create subtree root node */
 			sfn = node_alloc();
 			if (!sfn)
-				goto st_failure;
+				goto failure;
 
 			sfn->leaf = info->nl_net->ipv6.ip6_null_entry;
 			atomic_inc(&info->nl_net->ipv6.ip6_null_entry->rt6i_ref);
@@ -1032,12 +1032,12 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 
 			if (IS_ERR(sn)) {
 				/* If it is failed, discard just allocated
-				   root, and then (in st_failure) stale node
+				   root, and then (in failure) stale node
 				   in main tree.
 				 */
 				node_free(sfn);
 				err = PTR_ERR(sn);
-				goto st_failure;
+				goto failure;
 			}
 
 			/* Now link new subtree to main tree */
@@ -1051,7 +1051,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 
 			if (IS_ERR(sn)) {
 				err = PTR_ERR(sn);
-				goto st_failure;
+				goto failure;
 			}
 		}
 
@@ -1093,22 +1093,22 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 			atomic_inc(&pn->leaf->rt6i_ref);
 		}
 #endif
-		if (!(rt->dst.flags & DST_NOCACHE))
-			dst_free(&rt->dst);
+		goto failure;
 	}
 	return err;
 
-#ifdef CONFIG_IPV6_SUBTREES
-	/* Subtree creation failed, probably main tree node
-	   is orphan. If it is, shoot it.
+failure:
+	/* fn->leaf could be NULL if fn is an intermediate node and we
+	 * failed to add the new route to it in both subtree creation
+	 * failure and fib6_add_rt2node() failure case.
+	 * In both cases, fib6_repair_tree() should be called to fix
+	 * fn->leaf.
 	 */
-st_failure:
 	if (fn && !(fn->fn_flags & (RTN_RTINFO|RTN_ROOT)))
 		fib6_repair_tree(info->nl_net, fn);
 	if (!(rt->dst.flags & DST_NOCACHE))
 		dst_free(&rt->dst);
 	return err;
-#endif
 }
 
 /*
-- 
2.13.5


From f5b505ce91819dfa6a85568befd9097d501d6424 Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Wed, 16 Aug 2017 17:53:36 -0400
Subject: [PATCH 20/27] tcp: when rearming RTO, if RTO time is in past then
 fire RTO ASAP

[ Upstream commit cdbeb633ca71a02b7b63bfeb94994bf4e1a0b894 ]

In some situations tcp_send_loss_probe() can realize that it's unable
to send a loss probe (TLP), and falls back to calling tcp_rearm_rto()
to schedule an RTO timer. In such cases, sometimes tcp_rearm_rto()
realizes that the RTO was eligible to fire immediately or at some
point in the past (delta_us <= 0). Previously in such cases
tcp_rearm_rto() was scheduling such "overdue" RTOs to happen at now +
icsk_rto, which caused needless delays of hundreds of milliseconds
(and non-linear behavior that made reproducible testing
difficult). This commit changes the logic to schedule "overdue" RTOs
ASAP, rather than at now + icsk_rto.

Fixes: 6ba8a3b19e76 ("tcp: Tail loss probe (TLP)")
Suggested-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 57bcae81fe42..fbaac4423a99 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3007,8 +3007,7 @@ void tcp_rearm_rto(struct sock *sk)
 			/* delta may not be positive if the socket is locked
 			 * when the retrans timer fires and is rescheduled.
 			 */
-			if (delta > 0)
-				rto = delta;
+			rto = max(delta, 1);
 		}
 		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto,
 					  TCP_RTO_MAX);
-- 
2.13.5


From 826efe95a4e93539a35ffeb392b0cf899972332d Mon Sep 17 00:00:00 2001
From: Huy Nguyen <huyn@mellanox.com>
Date: Thu, 17 Aug 2017 18:29:52 +0300
Subject: [PATCH 21/27] net/mlx4_core: Enable 4K UAR if SRIOV module parameter
 is not enabled

[ Upstream commit ca3d89a3ebe79367bd41b6b8ba37664478ae2dba ]

enable_4k_uar module parameter was added in patch cited below to
address the backward compatibility issue in SRIOV when the VM has
system's PAGE_SIZE uar implementation and the Hypervisor has 4k uar
implementation.

The above compatibility issue does not exist in the non SRIOV case.
In this patch, we always enable 4k uar implementation if SRIOV
is not enabled on mlx4's supported cards.

Fixes: 76e39ccf9c36 ("net/mlx4_core: Fix backward compatibility on VFs")
Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 83aab1e4c8c8..9f214f9fb48c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -430,7 +430,7 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 		/* Virtual PCI function needs to determine UAR page size from
 		 * firmware. Only master PCI function can set the uar page size
 		 */
-		if (enable_4k_uar)
+		if (enable_4k_uar || !dev->persist->num_vfs)
 			dev->uar_page_shift = DEFAULT_UAR_PAGE_SHIFT;
 		else
 			dev->uar_page_shift = PAGE_SHIFT;
@@ -2275,7 +2275,7 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
 
 		dev->caps.max_fmr_maps = (1 << (32 - ilog2(dev->caps.num_mpts))) - 1;
 
-		if (enable_4k_uar) {
+		if (enable_4k_uar || !dev->persist->num_vfs) {
 			init_hca.log_uar_sz = ilog2(dev->caps.num_uars) +
 						    PAGE_SHIFT - DEFAULT_UAR_PAGE_SHIFT;
 			init_hca.uar_page_sz = DEFAULT_UAR_PAGE_SHIFT - 12;
-- 
2.13.5


From 6b093ce76d0ed3de3949fc4edf9139726a4abacd Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Thu, 17 Aug 2017 23:14:58 +0100
Subject: [PATCH 22/27] irda: do not leak initialized list.dev to userspace

[ Upstream commit b024d949a3c24255a7ef1a470420eb478949aa4c ]

list.dev has not been initialized and so the copy_to_user is copying
data from the stack back to user space which is a potential
information leak. Fix this ensuring all of list is initialized to
zero.

Detected by CoverityScan, CID#1357894 ("Uninitialized scalar variable")

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/irda/af_irda.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index 8d77ad5cadaf..4cadc29f547c 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -2225,7 +2225,7 @@ static int irda_getsockopt(struct socket *sock, int level, int optname,
 {
 	struct sock *sk = sock->sk;
 	struct irda_sock *self = irda_sk(sk);
-	struct irda_device_list list;
+	struct irda_device_list list = { 0 };
 	struct irda_device_info *discoveries;
 	struct irda_ias_set *	ias_opt;	/* IAS get/query params */
 	struct ias_object *	ias_obj;	/* Object in IAS */
-- 
2.13.5


From f7c8f55a33f335fea5ee2648710d860061067665 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Fri, 18 Aug 2017 11:01:36 +0800
Subject: [PATCH 23/27] net: sched: fix NULL pointer dereference when action
 calls some targets

[ Upstream commit 4f8a881acc9d1adaf1e552349a0b1df28933a04c ]

As we know in some target's checkentry it may dereference par.entryinfo
to check entry stuff inside. But when sched action calls xt_check_target,
par.entryinfo is set with NULL. It would cause kernel panic when calling
some targets.

It can be reproduce with:
  # tc qd add dev eth1 ingress handle ffff:
  # tc filter add dev eth1 parent ffff: u32 match u32 0 0 action xt \
    -j ECN --ecn-tcp-remove

It could also crash kernel when using target CLUSTERIP or TPROXY.

By now there's no proper value for par.entryinfo in ipt_init_target,
but it can not be set with NULL. This patch is to void all these
panics by setting it with an ipt_entry obj with all members = 0.

Note that this issue has been there since the very beginning.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ipt.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index d516ba8178b8..541707802a23 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -41,6 +41,7 @@ static int ipt_init_target(struct net *net, struct xt_entry_target *t,
 {
 	struct xt_tgchk_param par;
 	struct xt_target *target;
+	struct ipt_entry e = {};
 	int ret = 0;
 
 	target = xt_request_find_target(AF_INET, t->u.user.name,
@@ -52,6 +53,7 @@ static int ipt_init_target(struct net *net, struct xt_entry_target *t,
 	memset(&par, 0, sizeof(par));
 	par.net       = net;
 	par.table     = table;
+	par.entryinfo = &e;
 	par.target    = target;
 	par.targinfo  = t->data;
 	par.hook_mask = hook;
-- 
2.13.5


From 1d8bda32a0968ce03ab8f5189fd52d25c5aeb193 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Date: Sat, 19 Aug 2017 15:37:07 +0300
Subject: [PATCH 24/27] net_sched: fix order of queue length updates in
 qdisc_replace()

[ Upstream commit 68a66d149a8c78ec6720f268597302883e48e9fa ]

This important to call qdisc_tree_reduce_backlog() after changing queue
length. Parent qdisc should deactivate class in ->qlen_notify() called from
qdisc_tree_reduce_backlog() but this happens only if qdisc->q.qlen in zero.

Missed class deactivations leads to crashes/warnings at picking packets
from empty qdisc and corrupting state at reactivating this class in future.

Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Fixes: 86a7996cc8a0 ("net_sched: introduce qdisc_replace() helper")
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 22e52093bfda..db5b6b6346b3 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -785,8 +785,11 @@ static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new,
 	old = *pold;
 	*pold = new;
 	if (old != NULL) {
-		qdisc_tree_reduce_backlog(old, old->q.qlen, old->qstats.backlog);
+		unsigned int qlen = old->q.qlen;
+		unsigned int backlog = old->qstats.backlog;
+
 		qdisc_reset(old);
+		qdisc_tree_reduce_backlog(old, qlen, backlog);
 	}
 	sch_tree_unlock(sch);
 
-- 
2.13.5


From ba75231c8ff0e1dd9cb4beb9414d6650bd3ad32f Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Sun, 2 Jul 2017 02:13:30 +0200
Subject: [PATCH 25/27] bpf, verifier: add additional patterns to
 evaluate_reg_imm_alu

[ Upstream commit 43188702b3d98d2792969a3377a30957f05695e6 ]

Currently the verifier does not track imm across alu operations when
the source register is of unknown type. This adds additional pattern
matching to catch this and track imm. We've seen LLVM generating this
pattern while working on cilium.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c | 62 +++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 62 insertions(+)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index a8a725697bed..03f8d02849be 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1650,6 +1650,65 @@ static int evaluate_reg_alu(struct bpf_verifier_env *env, struct bpf_insn *insn)
 	return 0;
 }
 
+static int evaluate_reg_imm_alu_unknown(struct bpf_verifier_env *env,
+					struct bpf_insn *insn)
+{
+	struct bpf_reg_state *regs = env->cur_state.regs;
+	struct bpf_reg_state *dst_reg = &regs[insn->dst_reg];
+	struct bpf_reg_state *src_reg = &regs[insn->src_reg];
+	u8 opcode = BPF_OP(insn->code);
+	s64 imm_log2 = __ilog2_u64((long long)dst_reg->imm);
+
+	/* BPF_X code with src_reg->type UNKNOWN_VALUE here. */
+	if (src_reg->imm > 0 && dst_reg->imm) {
+		switch (opcode) {
+		case BPF_ADD:
+			/* dreg += sreg
+			 * where both have zero upper bits. Adding them
+			 * can only result making one more bit non-zero
+			 * in the larger value.
+			 * Ex. 0xffff (imm=48) + 1 (imm=63) = 0x10000 (imm=47)
+			 *     0xffff (imm=48) + 0xffff = 0x1fffe (imm=47)
+			 */
+			dst_reg->imm = min(src_reg->imm, 63 - imm_log2);
+			dst_reg->imm--;
+			break;
+		case BPF_AND:
+			/* dreg &= sreg
+			 * AND can not extend zero bits only shrink
+			 * Ex.  0x00..00ffffff
+			 *    & 0x0f..ffffffff
+			 *     ----------------
+			 *      0x00..00ffffff
+			 */
+			dst_reg->imm = max(src_reg->imm, 63 - imm_log2);
+			break;
+		case BPF_OR:
+			/* dreg |= sreg
+			 * OR can only extend zero bits
+			 * Ex.  0x00..00ffffff
+			 *    | 0x0f..ffffffff
+			 *     ----------------
+			 *      0x0f..00ffffff
+			 */
+			dst_reg->imm = min(src_reg->imm, 63 - imm_log2);
+			break;
+		case BPF_SUB:
+		case BPF_MUL:
+		case BPF_RSH:
+		case BPF_LSH:
+			/* These may be flushed out later */
+		default:
+			mark_reg_unknown_value(regs, insn->dst_reg);
+		}
+	} else {
+		mark_reg_unknown_value(regs, insn->dst_reg);
+	}
+
+	dst_reg->type = UNKNOWN_VALUE;
+	return 0;
+}
+
 static int evaluate_reg_imm_alu(struct bpf_verifier_env *env,
 				struct bpf_insn *insn)
 {
@@ -1659,6 +1718,9 @@ static int evaluate_reg_imm_alu(struct bpf_verifier_env *env,
 	u8 opcode = BPF_OP(insn->code);
 	u64 dst_imm = dst_reg->imm;
 
+	if (BPF_SRC(insn->code) == BPF_X && src_reg->type == UNKNOWN_VALUE)
+		return evaluate_reg_imm_alu_unknown(env, insn);
+
 	/* dst_reg->type == CONST_IMM here. Simulate execution of insns
 	 * containing ALU ops. Don't care about overflow or negative
 	 * values, just add/sub/... them; registers are in u64.
-- 
2.13.5


From 6702c5e8722bb43f9c5c1c4f6da633e28313aa92 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 21 Jul 2017 00:00:21 +0200
Subject: [PATCH 26/27] bpf: fix mixed signed/unsigned derived min/max value
 bounds

[ Upstream commit 4cabc5b186b5427b9ee5a7495172542af105f02b ]

Edward reported that there's an issue in min/max value bounds
tracking when signed and unsigned compares both provide hints
on limits when having unknown variables. E.g. a program such
as the following should have been rejected:

   0: (7a) *(u64 *)(r10 -8) = 0
   1: (bf) r2 = r10
   2: (07) r2 += -8
   3: (18) r1 = 0xffff8a94cda93400
   5: (85) call bpf_map_lookup_elem#1
   6: (15) if r0 == 0x0 goto pc+7
  R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R10=fp
   7: (7a) *(u64 *)(r10 -16) = -8
   8: (79) r1 = *(u64 *)(r10 -16)
   9: (b7) r2 = -1
  10: (2d) if r1 > r2 goto pc+3
  R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R1=inv,min_value=0
  R2=imm-1,max_value=18446744073709551615,min_align=1 R10=fp
  11: (65) if r1 s> 0x1 goto pc+2
  R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R1=inv,min_value=0,max_value=1
  R2=imm-1,max_value=18446744073709551615,min_align=1 R10=fp
  12: (0f) r0 += r1
  13: (72) *(u8 *)(r0 +0) = 0
  R0=map_value_adj(ks=8,vs=8,id=0),min_value=0,max_value=1 R1=inv,min_value=0,max_value=1
  R2=imm-1,max_value=18446744073709551615,min_align=1 R10=fp
  14: (b7) r0 = 0
  15: (95) exit

What happens is that in the first part ...

   8: (79) r1 = *(u64 *)(r10 -16)
   9: (b7) r2 = -1
  10: (2d) if r1 > r2 goto pc+3

... r1 carries an unsigned value, and is compared as unsigned
against a register carrying an immediate. Verifier deduces in
reg_set_min_max() that since the compare is unsigned and operation
is greater than (>), that in the fall-through/false case, r1's
minimum bound must be 0 and maximum bound must be r2. Latter is
larger than the bound and thus max value is reset back to being
'invalid' aka BPF_REGISTER_MAX_RANGE. Thus, r1 state is now
'R1=inv,min_value=0'. The subsequent test ...

  11: (65) if r1 s> 0x1 goto pc+2

... is a signed compare of r1 with immediate value 1. Here,
verifier deduces in reg_set_min_max() that since the compare
is signed this time and operation is greater than (>), that
in the fall-through/false case, we can deduce that r1's maximum
bound must be 1, meaning with prior test, we result in r1 having
the following state: R1=inv,min_value=0,max_value=1. Given that
the actual value this holds is -8, the bounds are wrongly deduced.
When this is being added to r0 which holds the map_value(_adj)
type, then subsequent store access in above case will go through
check_mem_access() which invokes check_map_access_adj(), that
will then probe whether the map memory is in bounds based
on the min_value and max_value as well as access size since
the actual unknown value is min_value <= x <= max_value; commit
fce366a9dd0d ("bpf, verifier: fix alu ops against map_value{,
_adj} register types") provides some more explanation on the
semantics.

It's worth to note in this context that in the current code,
min_value and max_value tracking are used for two things, i)
dynamic map value access via check_map_access_adj() and since
commit 06c1c049721a ("bpf: allow helpers access to variable memory")
ii) also enforced at check_helper_mem_access() when passing a
memory address (pointer to packet, map value, stack) and length
pair to a helper and the length in this case is an unknown value
defining an access range through min_value/max_value in that
case. The min_value/max_value tracking is /not/ used in the
direct packet access case to track ranges. However, the issue
also affects case ii), for example, the following crafted program
based on the same principle must be rejected as well:

   0: (b7) r2 = 0
   1: (bf) r3 = r10
   2: (07) r3 += -512
   3: (7a) *(u64 *)(r10 -16) = -8
   4: (79) r4 = *(u64 *)(r10 -16)
   5: (b7) r6 = -1
   6: (2d) if r4 > r6 goto pc+5
  R1=ctx R2=imm0,min_value=0,max_value=0,min_align=2147483648 R3=fp-512
  R4=inv,min_value=0 R6=imm-1,max_value=18446744073709551615,min_align=1 R10=fp
   7: (65) if r4 s> 0x1 goto pc+4
  R1=ctx R2=imm0,min_value=0,max_value=0,min_align=2147483648 R3=fp-512
  R4=inv,min_value=0,max_value=1 R6=imm-1,max_value=18446744073709551615,min_align=1
  R10=fp
   8: (07) r4 += 1
   9: (b7) r5 = 0
  10: (6a) *(u16 *)(r10 -512) = 0
  11: (85) call bpf_skb_load_bytes#26
  12: (b7) r0 = 0
  13: (95) exit

Meaning, while we initialize the max_value stack slot that the
verifier thinks we access in the [1,2] range, in reality we
pass -7 as length which is interpreted as u32 in the helper.
Thus, this issue is relevant also for the case of helper ranges.
Resetting both bounds in check_reg_overflow() in case only one
of them exceeds limits is also not enough as similar test can be
created that uses values which are within range, thus also here
learned min value in r1 is incorrect when mixed with later signed
test to create a range:

   0: (7a) *(u64 *)(r10 -8) = 0
   1: (bf) r2 = r10
   2: (07) r2 += -8
   3: (18) r1 = 0xffff880ad081fa00
   5: (85) call bpf_map_lookup_elem#1
   6: (15) if r0 == 0x0 goto pc+7
  R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R10=fp
   7: (7a) *(u64 *)(r10 -16) = -8
   8: (79) r1 = *(u64 *)(r10 -16)
   9: (b7) r2 = 2
  10: (3d) if r2 >= r1 goto pc+3
  R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R1=inv,min_value=3
  R2=imm2,min_value=2,max_value=2,min_align=2 R10=fp
  11: (65) if r1 s> 0x4 goto pc+2
  R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0
  R1=inv,min_value=3,max_value=4 R2=imm2,min_value=2,max_value=2,min_align=2 R10=fp
  12: (0f) r0 += r1
  13: (72) *(u8 *)(r0 +0) = 0
  R0=map_value_adj(ks=8,vs=8,id=0),min_value=3,max_value=4
  R1=inv,min_value=3,max_value=4 R2=imm2,min_value=2,max_value=2,min_align=2 R10=fp
  14: (b7) r0 = 0
  15: (95) exit

This leaves us with two options for fixing this: i) to invalidate
all prior learned information once we switch signed context, ii)
to track min/max signed and unsigned boundaries separately as
done in [0]. (Given latter introduces major changes throughout
the whole verifier, it's rather net-next material, thus this
patch follows option i), meaning we can derive bounds either
from only signed tests or only unsigned tests.) There is still the
case of adjust_reg_min_max_vals(), where we adjust bounds on ALU
operations, meaning programs like the following where boundaries
on the reg get mixed in context later on when bounds are merged
on the dst reg must get rejected, too:

   0: (7a) *(u64 *)(r10 -8) = 0
   1: (bf) r2 = r10
   2: (07) r2 += -8
   3: (18) r1 = 0xffff89b2bf87ce00
   5: (85) call bpf_map_lookup_elem#1
   6: (15) if r0 == 0x0 goto pc+6
  R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R10=fp
   7: (7a) *(u64 *)(r10 -16) = -8
   8: (79) r1 = *(u64 *)(r10 -16)
   9: (b7) r2 = 2
  10: (3d) if r2 >= r1 goto pc+2
  R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R1=inv,min_value=3
  R2=imm2,min_value=2,max_value=2,min_align=2 R10=fp
  11: (b7) r7 = 1
  12: (65) if r7 s> 0x0 goto pc+2
  R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R1=inv,min_value=3
  R2=imm2,min_value=2,max_value=2,min_align=2 R7=imm1,max_value=0 R10=fp
  13: (b7) r0 = 0
  14: (95) exit

  from 12 to 15: R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0
  R1=inv,min_value=3 R2=imm2,min_value=2,max_value=2,min_align=2 R7=imm1,min_value=1 R10=fp
  15: (0f) r7 += r1
  16: (65) if r7 s> 0x4 goto pc+2
  R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R1=inv,min_value=3
  R2=imm2,min_value=2,max_value=2,min_align=2 R7=inv,min_value=4,max_value=4 R10=fp
  17: (0f) r0 += r7
  18: (72) *(u8 *)(r0 +0) = 0
  R0=map_value_adj(ks=8,vs=8,id=0),min_value=4,max_value=4 R1=inv,min_value=3
  R2=imm2,min_value=2,max_value=2,min_align=2 R7=inv,min_value=4,max_value=4 R10=fp
  19: (b7) r0 = 0
  20: (95) exit

Meaning, in adjust_reg_min_max_vals() we must also reset range
values on the dst when src/dst registers have mixed signed/
unsigned derived min/max value bounds with one unbounded value
as otherwise they can be added together deducing false boundaries.
Once both boundaries are established from either ALU ops or
compare operations w/o mixing signed/unsigned insns, then they
can safely be added to other regs also having both boundaries
established. Adding regs with one unbounded side to a map value
where the bounded side has been learned w/o mixing ops is
possible, but the resulting map value won't recover from that,
meaning such op is considered invalid on the time of actual
access. Invalid bounds are set on the dst reg in case i) src reg,
or ii) in case dst reg already had them. The only way to recover
would be to perform i) ALU ops but only 'add' is allowed on map
value types or ii) comparisons, but these are disallowed on
pointers in case they span a range. This is fine as only BPF_JEQ
and BPF_JNE may be performed on PTR_TO_MAP_VALUE_OR_NULL registers
which potentially turn them into PTR_TO_MAP_VALUE type depending
on the branch, so only here min/max value cannot be invalidated
for them.

In terms of state pruning, value_from_signed is considered
as well in states_equal() when dealing with adjusted map values.
With regards to breaking existing programs, there is a small
risk, but use-cases are rather quite narrow where this could
occur and mixing compares probably unlikely.

Joint work with Josef and Edward.

  [0] https://lists.iovisor.org/pipermail/iovisor-dev/2017-June/000822.html

Fixes: 484611357c19 ("bpf: allow access into map value arrays")
Reported-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/bpf_verifier.h |   1 +
 kernel/bpf/verifier.c        | 108 +++++++++++++++++++++++++++++++++++++------
 2 files changed, 95 insertions(+), 14 deletions(-)

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index d5093b52b485..88f4289e7eee 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -43,6 +43,7 @@ struct bpf_reg_state {
 	u32 min_align;
 	u32 aux_off;
 	u32 aux_off_align;
+	bool value_from_signed;
 };
 
 enum bpf_stack_slot_type {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 03f8d02849be..56c0257e0026 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -504,6 +504,7 @@ static void reset_reg_range_values(struct bpf_reg_state *regs, u32 regno)
 {
 	regs[regno].min_value = BPF_REGISTER_MIN_RANGE;
 	regs[regno].max_value = BPF_REGISTER_MAX_RANGE;
+	regs[regno].value_from_signed = false;
 	regs[regno].min_align = 0;
 }
 
@@ -777,12 +778,13 @@ static int check_ctx_access(struct bpf_verifier_env *env, int off, int size,
 	return -EACCES;
 }
 
-static bool is_pointer_value(struct bpf_verifier_env *env, int regno)
+static bool __is_pointer_value(bool allow_ptr_leaks,
+			       const struct bpf_reg_state *reg)
 {
-	if (env->allow_ptr_leaks)
+	if (allow_ptr_leaks)
 		return false;
 
-	switch (env->cur_state.regs[regno].type) {
+	switch (reg->type) {
 	case UNKNOWN_VALUE:
 	case CONST_IMM:
 		return false;
@@ -791,6 +793,11 @@ static bool is_pointer_value(struct bpf_verifier_env *env, int regno)
 	}
 }
 
+static bool is_pointer_value(struct bpf_verifier_env *env, int regno)
+{
+	return __is_pointer_value(env->allow_ptr_leaks, &env->cur_state.regs[regno]);
+}
+
 static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg,
 				   int off, int size, bool strict)
 {
@@ -1825,10 +1832,24 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 	dst_align = dst_reg->min_align;
 
 	/* We don't know anything about what was done to this register, mark it
-	 * as unknown.
+	 * as unknown. Also, if both derived bounds came from signed/unsigned
+	 * mixed compares and one side is unbounded, we cannot really do anything
+	 * with them as boundaries cannot be trusted. Thus, arithmetic of two
+	 * regs of such kind will get invalidated bounds on the dst side.
 	 */
-	if (min_val == BPF_REGISTER_MIN_RANGE &&
-	    max_val == BPF_REGISTER_MAX_RANGE) {
+	if ((min_val == BPF_REGISTER_MIN_RANGE &&
+	     max_val == BPF_REGISTER_MAX_RANGE) ||
+	    (BPF_SRC(insn->code) == BPF_X &&
+	     ((min_val != BPF_REGISTER_MIN_RANGE &&
+	       max_val == BPF_REGISTER_MAX_RANGE) ||
+	      (min_val == BPF_REGISTER_MIN_RANGE &&
+	       max_val != BPF_REGISTER_MAX_RANGE) ||
+	      (dst_reg->min_value != BPF_REGISTER_MIN_RANGE &&
+	       dst_reg->max_value == BPF_REGISTER_MAX_RANGE) ||
+	      (dst_reg->min_value == BPF_REGISTER_MIN_RANGE &&
+	       dst_reg->max_value != BPF_REGISTER_MAX_RANGE)) &&
+	     regs[insn->dst_reg].value_from_signed !=
+	     regs[insn->src_reg].value_from_signed)) {
 		reset_reg_range_values(regs, insn->dst_reg);
 		return;
 	}
@@ -2015,6 +2036,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 			regs[insn->dst_reg].max_value = insn->imm;
 			regs[insn->dst_reg].min_value = insn->imm;
 			regs[insn->dst_reg].min_align = calc_align(insn->imm);
+			regs[insn->dst_reg].value_from_signed = false;
 		}
 
 	} else if (opcode > BPF_END) {
@@ -2190,40 +2212,63 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg,
 			    struct bpf_reg_state *false_reg, u64 val,
 			    u8 opcode)
 {
+	bool value_from_signed = true;
+	bool is_range = true;
+
 	switch (opcode) {
 	case BPF_JEQ:
 		/* If this is false then we know nothing Jon Snow, but if it is
 		 * true then we know for sure.
 		 */
 		true_reg->max_value = true_reg->min_value = val;
+		is_range = false;
 		break;
 	case BPF_JNE:
 		/* If this is true we know nothing Jon Snow, but if it is false
 		 * we know the value for sure;
 		 */
 		false_reg->max_value = false_reg->min_value = val;
+		is_range = false;
 		break;
 	case BPF_JGT:
-		/* Unsigned comparison, the minimum value is 0. */
-		false_reg->min_value = 0;
+		value_from_signed = false;
 		/* fallthrough */
 	case BPF_JSGT:
+		if (true_reg->value_from_signed != value_from_signed)
+			reset_reg_range_values(true_reg, 0);
+		if (false_reg->value_from_signed != value_from_signed)
+			reset_reg_range_values(false_reg, 0);
+		if (opcode == BPF_JGT) {
+			/* Unsigned comparison, the minimum value is 0. */
+			false_reg->min_value = 0;
+		}
 		/* If this is false then we know the maximum val is val,
 		 * otherwise we know the min val is val+1.
 		 */
 		false_reg->max_value = val;
+		false_reg->value_from_signed = value_from_signed;
 		true_reg->min_value = val + 1;
+		true_reg->value_from_signed = value_from_signed;
 		break;
 	case BPF_JGE:
-		/* Unsigned comparison, the minimum value is 0. */
-		false_reg->min_value = 0;
+		value_from_signed = false;
 		/* fallthrough */
 	case BPF_JSGE:
+		if (true_reg->value_from_signed != value_from_signed)
+			reset_reg_range_values(true_reg, 0);
+		if (false_reg->value_from_signed != value_from_signed)
+			reset_reg_range_values(false_reg, 0);
+		if (opcode == BPF_JGE) {
+			/* Unsigned comparison, the minimum value is 0. */
+			false_reg->min_value = 0;
+		}
 		/* If this is false then we know the maximum value is val - 1,
 		 * otherwise we know the mimimum value is val.
 		 */
 		false_reg->max_value = val - 1;
+		false_reg->value_from_signed = value_from_signed;
 		true_reg->min_value = val;
+		true_reg->value_from_signed = value_from_signed;
 		break;
 	default:
 		break;
@@ -2231,6 +2276,12 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg,
 
 	check_reg_overflow(false_reg);
 	check_reg_overflow(true_reg);
+	if (is_range) {
+		if (__is_pointer_value(false, false_reg))
+			reset_reg_range_values(false_reg, 0);
+		if (__is_pointer_value(false, true_reg))
+			reset_reg_range_values(true_reg, 0);
+	}
 }
 
 /* Same as above, but for the case that dst_reg is a CONST_IMM reg and src_reg
@@ -2240,41 +2291,64 @@ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg,
 				struct bpf_reg_state *false_reg, u64 val,
 				u8 opcode)
 {
+	bool value_from_signed = true;
+	bool is_range = true;
+
 	switch (opcode) {
 	case BPF_JEQ:
 		/* If this is false then we know nothing Jon Snow, but if it is
 		 * true then we know for sure.
 		 */
 		true_reg->max_value = true_reg->min_value = val;
+		is_range = false;
 		break;
 	case BPF_JNE:
 		/* If this is true we know nothing Jon Snow, but if it is false
 		 * we know the value for sure;
 		 */
 		false_reg->max_value = false_reg->min_value = val;
+		is_range = false;
 		break;
 	case BPF_JGT:
-		/* Unsigned comparison, the minimum value is 0. */
-		true_reg->min_value = 0;
+		value_from_signed = false;
 		/* fallthrough */
 	case BPF_JSGT:
+		if (true_reg->value_from_signed != value_from_signed)
+			reset_reg_range_values(true_reg, 0);
+		if (false_reg->value_from_signed != value_from_signed)
+			reset_reg_range_values(false_reg, 0);
+		if (opcode == BPF_JGT) {
+			/* Unsigned comparison, the minimum value is 0. */
+			true_reg->min_value = 0;
+		}
 		/*
 		 * If this is false, then the val is <= the register, if it is
 		 * true the register <= to the val.
 		 */
 		false_reg->min_value = val;
+		false_reg->value_from_signed = value_from_signed;
 		true_reg->max_value = val - 1;
+		true_reg->value_from_signed = value_from_signed;
 		break;
 	case BPF_JGE:
-		/* Unsigned comparison, the minimum value is 0. */
-		true_reg->min_value = 0;
+		value_from_signed = false;
 		/* fallthrough */
 	case BPF_JSGE:
+		if (true_reg->value_from_signed != value_from_signed)
+			reset_reg_range_values(true_reg, 0);
+		if (false_reg->value_from_signed != value_from_signed)
+			reset_reg_range_values(false_reg, 0);
+		if (opcode == BPF_JGE) {
+			/* Unsigned comparison, the minimum value is 0. */
+			true_reg->min_value = 0;
+		}
 		/* If this is false then constant < register, if it is true then
 		 * the register < constant.
 		 */
 		false_reg->min_value = val + 1;
+		false_reg->value_from_signed = value_from_signed;
 		true_reg->max_value = val;
+		true_reg->value_from_signed = value_from_signed;
 		break;
 	default:
 		break;
@@ -2282,6 +2356,12 @@ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg,
 
 	check_reg_overflow(false_reg);
 	check_reg_overflow(true_reg);
+	if (is_range) {
+		if (__is_pointer_value(false, false_reg))
+			reset_reg_range_values(false_reg, 0);
+		if (__is_pointer_value(false, true_reg))
+			reset_reg_range_values(true_reg, 0);
+	}
 }
 
 static void mark_map_reg(struct bpf_reg_state *regs, u32 regno, u32 id,
-- 
2.13.5


From a44f11588c8506059c6843a2a0221979e547f86e Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Fri, 21 Jul 2017 14:37:34 +0100
Subject: [PATCH 27/27] bpf/verifier: fix min/max handling in BPF_SUB

[ Upstream commit 9305706c2e808ae59f1eb201867f82f1ddf6d7a6 ]

We have to subtract the src max from the dst min, and vice-versa, since
 (e.g.) the smallest result comes from the largest subtrahend.

Fixes: 484611357c19 ("bpf: allow access into map value arrays")
Signed-off-by: Edward Cree <ecree@solarflare.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c | 21 +++++++++++++++------
 1 file changed, 15 insertions(+), 6 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 56c0257e0026..1e64ee3dd650 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1858,10 +1858,12 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 	 * do our normal operations to the register, we need to set the values
 	 * to the min/max since they are undefined.
 	 */
-	if (min_val == BPF_REGISTER_MIN_RANGE)
-		dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
-	if (max_val == BPF_REGISTER_MAX_RANGE)
-		dst_reg->max_value = BPF_REGISTER_MAX_RANGE;
+	if (opcode != BPF_SUB) {
+		if (min_val == BPF_REGISTER_MIN_RANGE)
+			dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
+		if (max_val == BPF_REGISTER_MAX_RANGE)
+			dst_reg->max_value = BPF_REGISTER_MAX_RANGE;
+	}
 
 	switch (opcode) {
 	case BPF_ADD:
@@ -1872,10 +1874,17 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 		dst_reg->min_align = min(src_align, dst_align);
 		break;
 	case BPF_SUB:
+		/* If one of our values was at the end of our ranges, then the
+		 * _opposite_ value in the dst_reg goes to the end of our range.
+		 */
+		if (min_val == BPF_REGISTER_MIN_RANGE)
+			dst_reg->max_value = BPF_REGISTER_MAX_RANGE;
+		if (max_val == BPF_REGISTER_MAX_RANGE)
+			dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
 		if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
-			dst_reg->min_value -= min_val;
+			dst_reg->min_value -= max_val;
 		if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
-			dst_reg->max_value -= max_val;
+			dst_reg->max_value -= min_val;
 		dst_reg->min_align = min(src_align, dst_align);
 		break;
 	case BPF_MUL:
-- 
2.13.5

Re: [PATCHES] Networking

[Greg KH]

On Wed, Aug 23, 2017 at 08:24:49PM -0700, David Miller wrote:
> 
> Please queue up the following networking fixes for v4.9 and v4.12
> -stable, respectively.

All queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 114 bytes --]


Please queue up the following networking bug fixes for v4.9, v4.12, and
v4.13 -stable, respectively.

Thank you.

[-- Attachment #2: net_49.mbox --]
[-- Type: Application/Octet-Stream, Size: 68612 bytes --]

From 24743acf203b39a9f54b9067452a5ac5e564f25e Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Fri, 18 Aug 2017 14:40:53 +0200
Subject: [PATCH 01/25] ipv6: accept 64k - 1 packet length in
 ip6_find_1stfragopt()

[ Upstream commit 3de33e1ba0506723ab25734e098cf280ecc34756 ]

A packet length of exactly IPV6_MAXPLEN is allowed, we should
refuse parsing options only if the size is 64KiB or more.

While at it, remove one extra variable and one assignment which
were also introduced by the commit that introduced the size
check. Checking the sum 'offset + len' and only later adding
'len' to 'offset' doesn't provide any advantage over directly
summing to 'offset' and checking it.

Fixes: 6399f1fae4ec ("ipv6: avoid overflow of offset in ip6_find_1stfragopt")
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/output_core.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index abb2c307fbe8..a338bbc33cf3 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -86,7 +86,6 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 
 	while (offset <= packet_len) {
 		struct ipv6_opt_hdr *exthdr;
-		unsigned int len;
 
 		switch (**nexthdr) {
 
@@ -112,10 +111,9 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 
 		exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) +
 						 offset);
-		len = ipv6_optlen(exthdr);
-		if (len + offset >= IPV6_MAXPLEN)
+		offset += ipv6_optlen(exthdr);
+		if (offset > IPV6_MAXPLEN)
 			return -EINVAL;
-		offset += len;
 		*nexthdr = &exthdr->nexthdr;
 	}
 
-- 
2.13.5


From f22f5104e11db0dc8115f3e6e33b9603559d2dfa Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Mon, 21 Aug 2017 09:47:10 -0700
Subject: [PATCH 02/25] ipv6: add rcu grace period before freeing fib6_node

[ Upstream commit c5cff8561d2d0006e972bd114afd51f082fee77c ]

We currently keep rt->rt6i_node pointing to the fib6_node for the route.
And some functions make use of this pointer to dereference the fib6_node
from rt structure, e.g. rt6_check(). However, as there is neither
refcount nor rcu taken when dereferencing rt->rt6i_node, it could
potentially cause crashes as rt->rt6i_node could be set to NULL by other
CPUs when doing a route deletion.
This patch introduces an rcu grace period before freeing fib6_node and
makes sure the functions that dereference it takes rcu_read_lock().

Note: there is no "Fixes" tag because this bug was there in a very
early stage.

Signed-off-by: Wei Wang <weiwan@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h | 30 +++++++++++++++++++++++++++++-
 net/ipv6/ip6_fib.c    | 20 ++++++++++++++++----
 net/ipv6/route.c      | 14 +++++++++++---
 3 files changed, 56 insertions(+), 8 deletions(-)

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index a74e2aa40ef4..c17180118897 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -68,6 +68,7 @@ struct fib6_node {
 	__u16			fn_flags;
 	int			fn_sernum;
 	struct rt6_info		*rr_ptr;
+	struct rcu_head		rcu;
 };
 
 #ifndef CONFIG_IPV6_SUBTREES
@@ -165,13 +166,40 @@ static inline void rt6_update_expires(struct rt6_info *rt0, int timeout)
 	rt0->rt6i_flags |= RTF_EXPIRES;
 }
 
+/* Function to safely get fn->sernum for passed in rt
+ * and store result in passed in cookie.
+ * Return true if we can get cookie safely
+ * Return false if not
+ */
+static inline bool rt6_get_cookie_safe(const struct rt6_info *rt,
+				       u32 *cookie)
+{
+	struct fib6_node *fn;
+	bool status = false;
+
+	rcu_read_lock();
+	fn = rcu_dereference(rt->rt6i_node);
+
+	if (fn) {
+		*cookie = fn->fn_sernum;
+		status = true;
+	}
+
+	rcu_read_unlock();
+	return status;
+}
+
 static inline u32 rt6_get_cookie(const struct rt6_info *rt)
 {
+	u32 cookie = 0;
+
 	if (rt->rt6i_flags & RTF_PCPU ||
 	    (unlikely(rt->dst.flags & DST_NOCACHE) && rt->dst.from))
 		rt = (struct rt6_info *)(rt->dst.from);
 
-	return rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0;
+	rt6_get_cookie_safe(rt, &cookie);
+
+	return cookie;
 }
 
 static inline void ip6_rt_put(struct rt6_info *rt)
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index ff389591a340..ed832b3d9b70 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -148,11 +148,23 @@ static struct fib6_node *node_alloc(void)
 	return fn;
 }
 
-static void node_free(struct fib6_node *fn)
+static void node_free_immediate(struct fib6_node *fn)
+{
+	kmem_cache_free(fib6_node_kmem, fn);
+}
+
+static void node_free_rcu(struct rcu_head *head)
 {
+	struct fib6_node *fn = container_of(head, struct fib6_node, rcu);
+
 	kmem_cache_free(fib6_node_kmem, fn);
 }
 
+static void node_free(struct fib6_node *fn)
+{
+	call_rcu(&fn->rcu, node_free_rcu);
+}
+
 static void rt6_rcu_free(struct rt6_info *rt)
 {
 	call_rcu(&rt->dst.rcu_head, dst_rcu_free);
@@ -589,9 +601,9 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root,
 
 		if (!in || !ln) {
 			if (in)
-				node_free(in);
+				node_free_immediate(in);
 			if (ln)
-				node_free(ln);
+				node_free_immediate(ln);
 			return ERR_PTR(-ENOMEM);
 		}
 
@@ -1020,7 +1032,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 				   root, and then (in failure) stale node
 				   in main tree.
 				 */
-				node_free(sfn);
+				node_free_immediate(sfn);
 				err = PTR_ERR(sn);
 				goto failure;
 			}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 5764a84465f8..632987ffc07d 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1267,7 +1267,9 @@ static void rt6_dst_from_metrics_check(struct rt6_info *rt)
 
 static struct dst_entry *rt6_check(struct rt6_info *rt, u32 cookie)
 {
-	if (!rt->rt6i_node || (rt->rt6i_node->fn_sernum != cookie))
+	u32 rt_cookie;
+
+	if (!rt6_get_cookie_safe(rt, &rt_cookie) || rt_cookie != cookie)
 		return NULL;
 
 	if (rt6_check_expired(rt))
@@ -1335,8 +1337,14 @@ static void ip6_link_failure(struct sk_buff *skb)
 		if (rt->rt6i_flags & RTF_CACHE) {
 			dst_hold(&rt->dst);
 			ip6_del_rt(rt);
-		} else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT)) {
-			rt->rt6i_node->fn_sernum = -1;
+		} else {
+			struct fib6_node *fn;
+
+			rcu_read_lock();
+			fn = rcu_dereference(rt->rt6i_node);
+			if (fn && (rt->rt6i_flags & RTF_DEFAULT))
+				fn->fn_sernum = -1;
+			rcu_read_unlock();
 		}
 	}
 }
-- 
2.13.5


From e7c04b0c06fa4d01537880aa5220edff48de3873 Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Fri, 25 Aug 2017 15:03:10 -0700
Subject: [PATCH 03/25] ipv6: fix sparse warning on rt6i_node

[ Upstream commit 4e587ea71bf924f7dac621f1351653bd41e446cb ]

Commit c5cff8561d2d adds rcu grace period before freeing fib6_node. This
generates a new sparse warning on rt->rt6i_node related code:
  net/ipv6/route.c:1394:30: error: incompatible types in comparison
  expression (different address spaces)
  ./include/net/ip6_fib.h:187:14: error: incompatible types in comparison
  expression (different address spaces)

This commit adds "__rcu" tag for rt6i_node and makes sure corresponding
rcu API is used for it.
After this fix, sparse no longer generates the above warning.

Fixes: c5cff8561d2d ("ipv6: add rcu grace period before freeing fib6_node")
Signed-off-by: Wei Wang <weiwan@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h |  2 +-
 net/ipv6/addrconf.c   |  2 +-
 net/ipv6/ip6_fib.c    | 11 +++++++----
 net/ipv6/route.c      |  3 ++-
 4 files changed, 11 insertions(+), 7 deletions(-)

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index c17180118897..a6bcb18ac4c3 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -103,7 +103,7 @@ struct rt6_info {
 	 * the same cache line.
 	 */
 	struct fib6_table		*rt6i_table;
-	struct fib6_node		*rt6i_node;
+	struct fib6_node __rcu		*rt6i_node;
 
 	struct in6_addr			rt6i_gateway;
 
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index b2cabda72320..cc101b1be903 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5443,7 +5443,7 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
 		 * our DAD process, so we don't need
 		 * to do it again
 		 */
-		if (!(ifp->rt->rt6i_node))
+		if (!rcu_access_pointer(ifp->rt->rt6i_node))
 			ip6_ins_rt(ifp->rt);
 		if (ifp->idev->cnf.forwarding)
 			addrconf_join_anycast(ifp);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index ed832b3d9b70..af7442211ffb 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -874,7 +874,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 
 		rt->dst.rt6_next = iter;
 		*ins = rt;
-		rt->rt6i_node = fn;
+		rcu_assign_pointer(rt->rt6i_node, fn);
 		atomic_inc(&rt->rt6i_ref);
 		inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags);
 		info->nl_net->ipv6.rt6_stats->fib_rt_entries++;
@@ -899,7 +899,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 			return err;
 
 		*ins = rt;
-		rt->rt6i_node = fn;
+		rcu_assign_pointer(rt->rt6i_node, fn);
 		rt->dst.rt6_next = iter->dst.rt6_next;
 		atomic_inc(&rt->rt6i_ref);
 		inet6_rt_notify(RTM_NEWROUTE, rt, info, NLM_F_REPLACE);
@@ -1459,8 +1459,9 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp,
 
 int fib6_del(struct rt6_info *rt, struct nl_info *info)
 {
+	struct fib6_node *fn = rcu_dereference_protected(rt->rt6i_node,
+				    lockdep_is_held(&rt->rt6i_table->tb6_lock));
 	struct net *net = info->nl_net;
-	struct fib6_node *fn = rt->rt6i_node;
 	struct rt6_info **rtp;
 
 #if RT6_DEBUG >= 2
@@ -1649,7 +1650,9 @@ static int fib6_clean_node(struct fib6_walker *w)
 			if (res) {
 #if RT6_DEBUG >= 2
 				pr_debug("%s: del failed: rt=%p@%p err=%d\n",
-					 __func__, rt, rt->rt6i_node, res);
+					 __func__, rt,
+					 rcu_access_pointer(rt->rt6i_node),
+					 res);
 #endif
 				continue;
 			}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 632987ffc07d..9c2dd3f77cdb 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1361,7 +1361,8 @@ static void rt6_do_update_pmtu(struct rt6_info *rt, u32 mtu)
 static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt)
 {
 	return !(rt->rt6i_flags & RTF_CACHE) &&
-		(rt->rt6i_flags & RTF_PCPU || rt->rt6i_node);
+		(rt->rt6i_flags & RTF_PCPU ||
+		 rcu_access_pointer(rt->rt6i_node));
 }
 
 static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
-- 
2.13.5


From fd2c1a5abc39e9d2c3c500dd770db7f7ce922bdf Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 22 Aug 2017 15:36:08 +0200
Subject: [PATCH 04/25] macsec: add genl family module alias

[ Upstream commit 78362998f58c7c271e2719dcd0aaced435c801f9 ]

This helps tools such as wpa_supplicant can start even if the macsec
module isn't loaded yet.

Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macsec.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index a5d66e205bb2..2caac0c37059 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -3510,6 +3510,7 @@ module_init(macsec_init);
 module_exit(macsec_exit);
 
 MODULE_ALIAS_RTNL_LINK("macsec");
+MODULE_ALIAS_GENL_FAMILY("macsec");
 
 MODULE_DESCRIPTION("MACsec IEEE 802.1AE");
 MODULE_LICENSE("GPL v2");
-- 
2.13.5


From da56090ed51d1d7a7b2d5eaf1471ea0046b201e8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 22 Aug 2017 09:39:28 -0700
Subject: [PATCH 05/25] udp: on peeking bad csum, drop packets even if not at
 head

[ Upstream commit fd6055a806edc4019be1b9fb7d25262599bca5b1 ]

When peeking, if a bad csum is discovered, the skb is unlinked from
the queue with __sk_queue_drop_skb and the peek operation restarted.

__sk_queue_drop_skb only drops packets that match the queue head.

This fails if the skb was found after the head, using SO_PEEK_OFF
socket option. This causes an infinite loop.

We MUST drop this problematic skb, and we can simply check if skb was
already removed by another thread, by looking at skb->next :

This pointer is set to NULL by the  __skb_unlink() operation, that might
have happened only under the spinlock protection.

Many thanks to syzkaller team (and particularly Dmitry Vyukov who
provided us nice C reproducers exhibiting the lockup) and Willem de
Bruijn who provided first version for this patch and a test program.

Fixes: 627d2d6b5500 ("udp: enable MSG_PEEK at non-zero offset")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/datagram.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/datagram.c b/net/core/datagram.c
index 58dfa23d12ca..4fa4011feec1 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -351,7 +351,7 @@ int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags)
 	if (flags & MSG_PEEK) {
 		err = -ENOENT;
 		spin_lock_bh(&sk->sk_receive_queue.lock);
-		if (skb == skb_peek(&sk->sk_receive_queue)) {
+		if (skb->next) {
 			__skb_unlink(skb, &sk->sk_receive_queue);
 			atomic_dec(&skb->users);
 			err = 0;
-- 
2.13.5


From f2ca9e1d5e01ed904e8297d93293fe31b2a11faf Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 22 Aug 2017 15:24:47 -0700
Subject: [PATCH 06/25] fsl/man: Inherit parent device and of_node

[ Upstream commit a1a50c8e4c241a505b7270e1a3c6e50d94e794b1 ]

Junote Cai reported that he was not able to get a DSA setup involving the
Freescale DPAA/FMAN driver to work and narrowed it down to
of_find_net_device_by_node(). This function requires the network device's
device reference to be correctly set which is the case here, though we have
lost any device_node association there.

The problem is that dpaa_eth_add_device() allocates a "dpaa-ethernet" platform
device, and later on dpaa_eth_probe() is called but SET_NETDEV_DEV() won't be
propagating &pdev->dev.of_node properly. Fix this by inherenting both the parent
device and the of_node when dpaa_eth_add_device() creates the platform device.

Fixes: 3933961682a3 ("fsl/fman: Add FMan MAC driver")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fman/mac.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c
index 736db9d9b0ad..81021f87e4f3 100644
--- a/drivers/net/ethernet/freescale/fman/mac.c
+++ b/drivers/net/ethernet/freescale/fman/mac.c
@@ -622,6 +622,9 @@ static struct platform_device *dpaa_eth_add_device(int fman_id,
 		goto no_mem;
 	}
 
+	pdev->dev.of_node = node;
+	pdev->dev.parent = priv->dev;
+
 	ret = platform_device_add_data(pdev, &data, sizeof(data));
 	if (ret)
 		goto err;
-- 
2.13.5


From 0d2cfe87faa3a5936bbf5cebf17a0b33e1738323 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Wed, 23 Aug 2017 13:27:13 +0200
Subject: [PATCH 07/25] sctp: Avoid out-of-bounds reads from address storage

[ Upstream commit ee6c88bb754e3d363e568da78086adfedb692447 ]

inet_diag_msg_sctp{,l}addr_fill() and sctp_get_sctp_info() copy
sizeof(sockaddr_storage) bytes to fill in sockaddr structs used
to export diagnostic information to userspace.

However, the memory allocated to store sockaddr information is
smaller than that and depends on the address family, so we leak
up to 100 uninitialized bytes to userspace. Just use the size of
the source structs instead, in all the three cases this is what
userspace expects. Zero out the remaining memory.

Unused bytes (i.e. when IPv4 addresses are used) in source
structs sctp_sockaddr_entry and sctp_transport are already
cleared by sctp_add_bind_addr() and sctp_transport_new(),
respectively.

Noticed while testing KASAN-enabled kernel with 'ss':

[ 2326.885243] BUG: KASAN: slab-out-of-bounds in inet_sctp_diag_fill+0x42c/0x6c0 [sctp_diag] at addr ffff881be8779800
[ 2326.896800] Read of size 128 by task ss/9527
[ 2326.901564] CPU: 0 PID: 9527 Comm: ss Not tainted 4.11.0-22.el7a.x86_64 #1
[ 2326.909236] Hardware name: Dell Inc. PowerEdge R730/072T6D, BIOS 2.4.3 01/17/2017
[ 2326.917585] Call Trace:
[ 2326.920312]  dump_stack+0x63/0x8d
[ 2326.924014]  kasan_object_err+0x21/0x70
[ 2326.928295]  kasan_report+0x288/0x540
[ 2326.932380]  ? inet_sctp_diag_fill+0x42c/0x6c0 [sctp_diag]
[ 2326.938500]  ? skb_put+0x8b/0xd0
[ 2326.942098]  ? memset+0x31/0x40
[ 2326.945599]  check_memory_region+0x13c/0x1a0
[ 2326.950362]  memcpy+0x23/0x50
[ 2326.953669]  inet_sctp_diag_fill+0x42c/0x6c0 [sctp_diag]
[ 2326.959596]  ? inet_diag_msg_sctpasoc_fill+0x460/0x460 [sctp_diag]
[ 2326.966495]  ? __lock_sock+0x102/0x150
[ 2326.970671]  ? sock_def_wakeup+0x60/0x60
[ 2326.975048]  ? remove_wait_queue+0xc0/0xc0
[ 2326.979619]  sctp_diag_dump+0x44a/0x760 [sctp_diag]
[ 2326.985063]  ? sctp_ep_dump+0x280/0x280 [sctp_diag]
[ 2326.990504]  ? memset+0x31/0x40
[ 2326.994007]  ? mutex_lock+0x12/0x40
[ 2326.997900]  __inet_diag_dump+0x57/0xb0 [inet_diag]
[ 2327.003340]  ? __sys_sendmsg+0x150/0x150
[ 2327.007715]  inet_diag_dump+0x4d/0x80 [inet_diag]
[ 2327.012979]  netlink_dump+0x1e6/0x490
[ 2327.017064]  __netlink_dump_start+0x28e/0x2c0
[ 2327.021924]  inet_diag_handler_cmd+0x189/0x1a0 [inet_diag]
[ 2327.028045]  ? inet_diag_rcv_msg_compat+0x1b0/0x1b0 [inet_diag]
[ 2327.034651]  ? inet_diag_dump_compat+0x190/0x190 [inet_diag]
[ 2327.040965]  ? __netlink_lookup+0x1b9/0x260
[ 2327.045631]  sock_diag_rcv_msg+0x18b/0x1e0
[ 2327.050199]  netlink_rcv_skb+0x14b/0x180
[ 2327.054574]  ? sock_diag_bind+0x60/0x60
[ 2327.058850]  sock_diag_rcv+0x28/0x40
[ 2327.062837]  netlink_unicast+0x2e7/0x3b0
[ 2327.067212]  ? netlink_attachskb+0x330/0x330
[ 2327.071975]  ? kasan_check_write+0x14/0x20
[ 2327.076544]  netlink_sendmsg+0x5be/0x730
[ 2327.080918]  ? netlink_unicast+0x3b0/0x3b0
[ 2327.085486]  ? kasan_check_write+0x14/0x20
[ 2327.090057]  ? selinux_socket_sendmsg+0x24/0x30
[ 2327.095109]  ? netlink_unicast+0x3b0/0x3b0
[ 2327.099678]  sock_sendmsg+0x74/0x80
[ 2327.103567]  ___sys_sendmsg+0x520/0x530
[ 2327.107844]  ? __get_locked_pte+0x178/0x200
[ 2327.112510]  ? copy_msghdr_from_user+0x270/0x270
[ 2327.117660]  ? vm_insert_page+0x360/0x360
[ 2327.122133]  ? vm_insert_pfn_prot+0xb4/0x150
[ 2327.126895]  ? vm_insert_pfn+0x32/0x40
[ 2327.131077]  ? vvar_fault+0x71/0xd0
[ 2327.134968]  ? special_mapping_fault+0x69/0x110
[ 2327.140022]  ? __do_fault+0x42/0x120
[ 2327.144008]  ? __handle_mm_fault+0x1062/0x17a0
[ 2327.148965]  ? __fget_light+0xa7/0xc0
[ 2327.153049]  __sys_sendmsg+0xcb/0x150
[ 2327.157133]  ? __sys_sendmsg+0xcb/0x150
[ 2327.161409]  ? SyS_shutdown+0x140/0x140
[ 2327.165688]  ? exit_to_usermode_loop+0xd0/0xd0
[ 2327.170646]  ? __do_page_fault+0x55d/0x620
[ 2327.175216]  ? __sys_sendmsg+0x150/0x150
[ 2327.179591]  SyS_sendmsg+0x12/0x20
[ 2327.183384]  do_syscall_64+0xe3/0x230
[ 2327.187471]  entry_SYSCALL64_slow_path+0x25/0x25
[ 2327.192622] RIP: 0033:0x7f41d18fa3b0
[ 2327.196608] RSP: 002b:00007ffc3b731218 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
[ 2327.205055] RAX: ffffffffffffffda RBX: 00007ffc3b731380 RCX: 00007f41d18fa3b0
[ 2327.213017] RDX: 0000000000000000 RSI: 00007ffc3b731340 RDI: 0000000000000003
[ 2327.220978] RBP: 0000000000000002 R08: 0000000000000004 R09: 0000000000000040
[ 2327.228939] R10: 00007ffc3b730f30 R11: 0000000000000246 R12: 0000000000000003
[ 2327.236901] R13: 00007ffc3b731340 R14: 00007ffc3b7313d0 R15: 0000000000000084
[ 2327.244865] Object at ffff881be87797e0, in cache kmalloc-64 size: 64
[ 2327.251953] Allocated:
[ 2327.254581] PID = 9484
[ 2327.257215]  save_stack_trace+0x1b/0x20
[ 2327.261485]  save_stack+0x46/0xd0
[ 2327.265179]  kasan_kmalloc+0xad/0xe0
[ 2327.269165]  kmem_cache_alloc_trace+0xe6/0x1d0
[ 2327.274138]  sctp_add_bind_addr+0x58/0x180 [sctp]
[ 2327.279400]  sctp_do_bind+0x208/0x310 [sctp]
[ 2327.284176]  sctp_bind+0x61/0xa0 [sctp]
[ 2327.288455]  inet_bind+0x5f/0x3a0
[ 2327.292151]  SYSC_bind+0x1a4/0x1e0
[ 2327.295944]  SyS_bind+0xe/0x10
[ 2327.299349]  do_syscall_64+0xe3/0x230
[ 2327.303433]  return_from_SYSCALL_64+0x0/0x6a
[ 2327.308194] Freed:
[ 2327.310434] PID = 4131
[ 2327.313065]  save_stack_trace+0x1b/0x20
[ 2327.317344]  save_stack+0x46/0xd0
[ 2327.321040]  kasan_slab_free+0x73/0xc0
[ 2327.325220]  kfree+0x96/0x1a0
[ 2327.328530]  dynamic_kobj_release+0x15/0x40
[ 2327.333195]  kobject_release+0x99/0x1e0
[ 2327.337472]  kobject_put+0x38/0x70
[ 2327.341266]  free_notes_attrs+0x66/0x80
[ 2327.345545]  mod_sysfs_teardown+0x1a5/0x270
[ 2327.350211]  free_module+0x20/0x2a0
[ 2327.354099]  SyS_delete_module+0x2cb/0x2f0
[ 2327.358667]  do_syscall_64+0xe3/0x230
[ 2327.362750]  return_from_SYSCALL_64+0x0/0x6a
[ 2327.367510] Memory state around the buggy address:
[ 2327.372855]  ffff881be8779700: fc fc fc fc 00 00 00 00 00 00 00 00 fc fc fc fc
[ 2327.380914]  ffff881be8779780: fb fb fb fb fb fb fb fb fc fc fc fc 00 00 00 00
[ 2327.388972] >ffff881be8779800: 00 00 00 00 fc fc fc fc fb fb fb fb fb fb fb fb
[ 2327.397031]                                ^
[ 2327.401792]  ffff881be8779880: fc fc fc fc fb fb fb fb fb fb fb fb fc fc fc fc
[ 2327.409850]  ffff881be8779900: 00 00 00 00 00 04 fc fc fc fc fc fc 00 00 00 00
[ 2327.417907] ==================================================================

This fixes CVE-2017-7558.

References: https://bugzilla.redhat.com/show_bug.cgi?id=1480266
Fixes: 8f840e47f190 ("sctp: add the sctp_diag.c file")
Cc: Xin Long <lucien.xin@gmail.com>
Cc: Vlad Yasevich <vyasevich@gmail.com>
Cc: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sctp_diag.c | 7 +++++--
 net/sctp/socket.c    | 3 +--
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/net/sctp/sctp_diag.c b/net/sctp/sctp_diag.c
index 048954eee984..e8f56b7c5afb 100644
--- a/net/sctp/sctp_diag.c
+++ b/net/sctp/sctp_diag.c
@@ -70,7 +70,8 @@ static int inet_diag_msg_sctpladdrs_fill(struct sk_buff *skb,
 
 	info = nla_data(attr);
 	list_for_each_entry_rcu(laddr, address_list, list) {
-		memcpy(info, &laddr->a, addrlen);
+		memcpy(info, &laddr->a, sizeof(laddr->a));
+		memset(info + sizeof(laddr->a), 0, addrlen - sizeof(laddr->a));
 		info += addrlen;
 	}
 
@@ -93,7 +94,9 @@ static int inet_diag_msg_sctpaddrs_fill(struct sk_buff *skb,
 	info = nla_data(attr);
 	list_for_each_entry(from, &asoc->peer.transport_addr_list,
 			    transports) {
-		memcpy(info, &from->ipaddr, addrlen);
+		memcpy(info, &from->ipaddr, sizeof(from->ipaddr));
+		memset(info + sizeof(from->ipaddr), 0,
+		       addrlen - sizeof(from->ipaddr));
 		info += addrlen;
 	}
 
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 9647e314d4fc..3ef725229449 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4373,8 +4373,7 @@ int sctp_get_sctp_info(struct sock *sk, struct sctp_association *asoc,
 	info->sctpi_ictrlchunks = asoc->stats.ictrlchunks;
 
 	prim = asoc->peer.primary_path;
-	memcpy(&info->sctpi_p_address, &prim->ipaddr,
-	       sizeof(struct sockaddr_storage));
+	memcpy(&info->sctpi_p_address, &prim->ipaddr, sizeof(prim->ipaddr));
 	info->sctpi_p_state = prim->state;
 	info->sctpi_p_cwnd = prim->cwnd;
 	info->sctpi_p_srtt = prim->srtt;
-- 
2.13.5


From 8d8b12ee38a4ca81dc5416bdbc3d8641c42b4efd Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 23 Aug 2017 15:59:49 +0200
Subject: [PATCH 08/25] qlge: avoid memcpy buffer overflow

[ Upstream commit e58f95831e7468d25eb6e41f234842ecfe6f014f ]

gcc-8.0.0 (snapshot) points out that we copy a variable-length string
into a fixed length field using memcpy() with the destination length,
and that ends up copying whatever follows the string:

    inlined from 'ql_core_dump' at drivers/net/ethernet/qlogic/qlge/qlge_dbg.c:1106:2:
drivers/net/ethernet/qlogic/qlge/qlge_dbg.c:708:2: error: 'memcpy' reading 15 bytes from a region of size 14 [-Werror=stringop-overflow=]
  memcpy(seg_hdr->description, desc, (sizeof(seg_hdr->description)) - 1);

Changing it to use strncpy() will instead zero-pad the destination,
which seems to be the right thing to do here.

The bug is probably harmless, but it seems like a good idea to address
it in stable kernels as well, if only for the purpose of building with
gcc-8 without warnings.

Fixes: a61f80261306 ("qlge: Add ethtool register dump function.")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qlge/qlge_dbg.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_dbg.c b/drivers/net/ethernet/qlogic/qlge/qlge_dbg.c
index 829be21f97b2..be258d90de9e 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_dbg.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_dbg.c
@@ -724,7 +724,7 @@ static void ql_build_coredump_seg_header(
 	seg_hdr->cookie = MPI_COREDUMP_COOKIE;
 	seg_hdr->segNum = seg_number;
 	seg_hdr->segSize = seg_size;
-	memcpy(seg_hdr->description, desc, (sizeof(seg_hdr->description)) - 1);
+	strncpy(seg_hdr->description, desc, (sizeof(seg_hdr->description)) - 1);
 }
 
 /*
-- 
2.13.5


From 171525fa8c633ff5d61f836bd7d61016b176c5a4 Mon Sep 17 00:00:00 2001
From: stephen hemminger <stephen@networkplumber.org>
Date: Thu, 24 Aug 2017 16:49:16 -0700
Subject: [PATCH 09/25] netvsc: fix deadlock betwen link status and removal

[ Upstream commit 9b4e946ce14e20d7addbfb7d9139e604f9fda107 ]

There is a deadlock possible when canceling the link status
delayed work queue. The removal process is run with RTNL held,
and the link status callback is acquring RTNL.

Resolve the issue by using trylock and rescheduling.
If cancel is in process, that block it from happening.

Fixes: 122a5f6410f4 ("staging: hv: use delayed_work for netvsc_send_garp()")
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/netvsc_drv.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index ff038e507fd6..36a04e182af1 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -1084,7 +1084,12 @@ static void netvsc_link_change(struct work_struct *w)
 	bool notify = false, reschedule = false;
 	unsigned long flags, next_reconfig, delay;
 
-	rtnl_lock();
+	/* if changes are happening, comeback later */
+	if (!rtnl_trylock()) {
+		schedule_delayed_work(&ndev_ctx->dwork, LINKCHANGE_INT);
+		return;
+	}
+
 	if (ndev_ctx->start_remove)
 		goto out_unlock;
 
-- 
2.13.5


From e43b267eae581e9bc3a89209fa21349c09e4eca8 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Fri, 25 Aug 2017 22:48:48 +0200
Subject: [PATCH 10/25] cxgb4: Fix stack out-of-bounds read due to wrong size
 to t4_record_mbox()

[ Upstream commit 0f3086868e8889a823a6e0f3d299102aa895d947 ]

Passing commands for logging to t4_record_mbox() with size
MBOX_LEN, when the actual command size is actually smaller,
causes out-of-bounds stack accesses in t4_record_mbox() while
copying command words here:

	for (i = 0; i < size / 8; i++)
		entry->cmd[i] = be64_to_cpu(cmd[i]);

Up to 48 bytes from the stack are then leaked to debugfs.

This happens whenever we send (and log) commands described by
structs fw_sched_cmd (32 bytes leaked), fw_vi_rxmode_cmd (48),
fw_hello_cmd (48), fw_bye_cmd (48), fw_initialize_cmd (48),
fw_reset_cmd (48), fw_pfvf_cmd (32), fw_eq_eth_cmd (16),
fw_eq_ctrl_cmd (32), fw_eq_ofld_cmd (32), fw_acl_mac_cmd(16),
fw_rss_glb_config_cmd(32), fw_rss_vi_config_cmd(32),
fw_devlog_cmd(32), fw_vi_enable_cmd(48), fw_port_cmd(32),
fw_sched_cmd(32), fw_devlog_cmd(32).

The cxgb4vf driver got this right instead.

When we call t4_record_mbox() to log a command reply, a MBOX_LEN
size can be used though, as get_mbox_rpl() will fill cmd_rpl up
completely.

Fixes: 7f080c3f2ff0 ("cxgb4: Add support to enable logging of firmware mailbox commands")
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/t4_hw.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index e8139514d32c..9e073fb6870a 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -317,12 +317,12 @@ int t4_wr_mbox_meat_timeout(struct adapter *adap, int mbox, const void *cmd,
 
 	if (v != MBOX_OWNER_DRV) {
 		ret = (v == MBOX_OWNER_FW) ? -EBUSY : -ETIMEDOUT;
-		t4_record_mbox(adap, cmd, MBOX_LEN, access, ret);
+		t4_record_mbox(adap, cmd, size, access, ret);
 		return ret;
 	}
 
 	/* Copy in the new mailbox command and send it on its way ... */
-	t4_record_mbox(adap, cmd, MBOX_LEN, access, 0);
+	t4_record_mbox(adap, cmd, size, access, 0);
 	for (i = 0; i < size; i += 8)
 		t4_write_reg64(adap, data_reg + i, be64_to_cpu(*p++));
 
@@ -371,7 +371,7 @@ int t4_wr_mbox_meat_timeout(struct adapter *adap, int mbox, const void *cmd,
 	}
 
 	ret = (pcie_fw & PCIE_FW_ERR_F) ? -ENXIO : -ETIMEDOUT;
-	t4_record_mbox(adap, cmd, MBOX_LEN, access, ret);
+	t4_record_mbox(adap, cmd, size, access, ret);
 	dev_err(adap->pdev_dev, "command %#x in mailbox %d timed out\n",
 		*(const u8 *)cmd, mbox);
 	t4_report_fw_error(adap);
-- 
2.13.5


From 955924d7b43f38b151db1695d8b03a73a28edd32 Mon Sep 17 00:00:00 2001
From: Benjamin Poirier <bpoirier@suse.com>
Date: Mon, 28 Aug 2017 14:29:41 -0400
Subject: [PATCH 11/25] packet: Don't write vnet header beyond end of buffer

[ Upstream commit edbd58be15a957f6a760c4a514cd475217eb97fd ]

... which may happen with certain values of tp_reserve and maclen.

Fixes: 58d19b19cd99 ("packet: vnet_hdr support for tpacket_rcv")
Signed-off-by: Benjamin Poirier <bpoirier@suse.com>
Cc: Willem de Bruijn <willemb@google.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index ae7bfd26cd91..35ba4b60d927 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2151,6 +2151,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	struct timespec ts;
 	__u32 ts_status;
 	bool is_drop_n_account = false;
+	bool do_vnet = false;
 
 	/* struct tpacket{2,3}_hdr is aligned to a multiple of TPACKET_ALIGNMENT.
 	 * We may add members to them until current aligned size without forcing
@@ -2201,8 +2202,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 		netoff = TPACKET_ALIGN(po->tp_hdrlen +
 				       (maclen < 16 ? 16 : maclen)) +
 				       po->tp_reserve;
-		if (po->has_vnet_hdr)
+		if (po->has_vnet_hdr) {
 			netoff += sizeof(struct virtio_net_hdr);
+			do_vnet = true;
+		}
 		macoff = netoff - maclen;
 	}
 	if (po->tp_version <= TPACKET_V2) {
@@ -2219,8 +2222,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 					skb_set_owner_r(copy_skb, sk);
 			}
 			snaplen = po->rx_ring.frame_size - macoff;
-			if ((int)snaplen < 0)
+			if ((int)snaplen < 0) {
 				snaplen = 0;
+				do_vnet = false;
+			}
 		}
 	} else if (unlikely(macoff + snaplen >
 			    GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len)) {
@@ -2233,6 +2238,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 		if (unlikely((int)snaplen < 0)) {
 			snaplen = 0;
 			macoff = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len;
+			do_vnet = false;
 		}
 	}
 	spin_lock(&sk->sk_receive_queue.lock);
@@ -2258,7 +2264,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	}
 	spin_unlock(&sk->sk_receive_queue.lock);
 
-	if (po->has_vnet_hdr) {
+	if (do_vnet) {
 		if (__packet_rcv_vnet(skb, h.raw + macoff -
 					   sizeof(struct virtio_net_hdr))) {
 			spin_lock(&sk->sk_receive_queue.lock);
-- 
2.13.5


From 4a81112a71dca57748939c0e309d8321a366810e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 30 Aug 2017 09:29:31 -0700
Subject: [PATCH 12/25] kcm: do not attach PF_KCM sockets to avoid deadlock

[ Upstream commit 351050ecd6523374b370341cc29fe61e2201556b ]

syzkaller had no problem to trigger a deadlock, attaching a KCM socket
to another one (or itself). (original syzkaller report was a very
confusing lockdep splat during a sendmsg())

It seems KCM claims to only support TCP, but no enforcement is done,
so we might need to add additional checks.

Fixes: ab7ac4eb9832 ("kcm: Kernel Connection Multiplexor module")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Acked-by: Tom Herbert <tom@quantonium.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/kcm/kcmsock.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index fecad1098cf8..7eb0e8fe3ca8 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -1381,6 +1381,10 @@ static int kcm_attach(struct socket *sock, struct socket *csock,
 	if (!csk)
 		return -EINVAL;
 
+	/* We must prevent loops or risk deadlock ! */
+	if (csk->sk_family == PF_KCM)
+		return -EOPNOTSUPP;
+
 	psock = kmem_cache_zalloc(kcm_psockp, GFP_KERNEL);
 	if (!psock)
 		return -ENOMEM;
-- 
2.13.5


From 1f6d32cd6f882fc980c8e9828395aaf7fb584948 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 30 Aug 2017 17:49:29 -0700
Subject: [PATCH 13/25] Revert "net: phy: Correctly process PHY_HALTED in
 phy_stop_machine()"

[ Upstream commit ebc8254aeae34226d0bc8fda309fd9790d4dccfe ]

This reverts commit 7ad813f208533cebfcc32d3d7474dc1677d1b09a ("net: phy:
Correctly process PHY_HALTED in phy_stop_machine()") because it is
creating the possibility for a NULL pointer dereference.

David Daney provide the following call trace and diagram of events:

When ndo_stop() is called we call:

 phy_disconnect()
    +---> phy_stop_interrupts() implies: phydev->irq = PHY_POLL;
    +---> phy_stop_machine()
    |      +---> phy_state_machine()
    |              +----> queue_delayed_work(): Work queued.
    +--->phy_detach() implies: phydev->attached_dev = NULL;

Now at a later time the queued work does:

 phy_state_machine()
    +---->netif_carrier_off(phydev->attached_dev): Oh no! It is NULL:

 CPU 12 Unable to handle kernel paging request at virtual address
0000000000000048, epc == ffffffff80de37ec, ra == ffffffff80c7c
Oops[#1]:
CPU: 12 PID: 1502 Comm: kworker/12:1 Not tainted 4.9.43-Cavium-Octeon+ #1
Workqueue: events_power_efficient phy_state_machine
task: 80000004021ed100 task.stack: 8000000409d70000
$ 0   : 0000000000000000 ffffffff84720060 0000000000000048 0000000000000004
$ 4   : 0000000000000000 0000000000000001 0000000000000004 0000000000000000
$ 8   : 0000000000000000 0000000000000000 00000000ffff98f3 0000000000000000
$12   : 8000000409d73fe0 0000000000009c00 ffffffff846547c8 000000000000af3b
$16   : 80000004096bab68 80000004096babd0 0000000000000000 80000004096ba800
$20   : 0000000000000000 0000000000000000 ffffffff81090000 0000000000000008
$24   : 0000000000000061 ffffffff808637b0
$28   : 8000000409d70000 8000000409d73cf0 80000000271bd300 ffffffff80c7804c
Hi    : 000000000000002a
Lo    : 000000000000003f
epc   : ffffffff80de37ec netif_carrier_off+0xc/0x58
ra    : ffffffff80c7804c phy_state_machine+0x48c/0x4f8
Status: 14009ce3        KX SX UX KERNEL EXL IE
Cause : 00800008 (ExcCode 02)
BadVA : 0000000000000048
PrId  : 000d9501 (Cavium Octeon III)
Modules linked in:
Process kworker/12:1 (pid: 1502, threadinfo=8000000409d70000,
task=80000004021ed100, tls=0000000000000000)
Stack : 8000000409a54000 80000004096bab68 80000000271bd300 80000000271c1e00
        0000000000000000 ffffffff808a1708 8000000409a54000 80000000271bd300
        80000000271bd320 8000000409a54030 ffffffff80ff0f00 0000000000000001
        ffffffff81090000 ffffffff808a1ac0 8000000402182080 ffffffff84650000
        8000000402182080 ffffffff84650000 ffffffff80ff0000 8000000409a54000
        ffffffff808a1970 0000000000000000 80000004099e8000 8000000402099240
        0000000000000000 ffffffff808a8598 0000000000000000 8000000408eeeb00
        8000000409a54000 00000000810a1d00 0000000000000000 8000000409d73de8
        8000000409d73de8 0000000000000088 000000000c009c00 8000000409d73e08
        8000000409d73e08 8000000402182080 ffffffff808a84d0 8000000402182080
        ...
Call Trace:
[<ffffffff80de37ec>] netif_carrier_off+0xc/0x58
[<ffffffff80c7804c>] phy_state_machine+0x48c/0x4f8
[<ffffffff808a1708>] process_one_work+0x158/0x368
[<ffffffff808a1ac0>] worker_thread+0x150/0x4c0
[<ffffffff808a8598>] kthread+0xc8/0xe0
[<ffffffff808617f0>] ret_from_kernel_thread+0x14/0x1c

The original motivation for this change originated from Marc Gonzales
indicating that his network driver did not have its adjust_link callback
executing with phydev->link = 0 while he was expecting it.

PHYLIB has never made any such guarantees ever because phy_stop() merely just
tells the workqueue to move into PHY_HALTED state which will happen
asynchronously.

Reported-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reported-by: David Daney <ddaney.cavm@gmail.com>
Fixes: 7ad813f20853 ("net: phy: Correctly process PHY_HALTED in phy_stop_machine()")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 775a6e1fdef9..6e12401b5102 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -674,9 +674,6 @@ void phy_stop_machine(struct phy_device *phydev)
 	if (phydev->state > PHY_UP && phydev->state != PHY_HALTED)
 		phydev->state = PHY_UP;
 	mutex_unlock(&phydev->lock);
-
-	/* Now we can run the state machine synchronously */
-	phy_state_machine(&phydev->state_queue.work);
 }
 
 /**
-- 
2.13.5


From c1c82f3c932ae97beb044d96cd02ee96d4640e1e Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Thu, 18 May 2017 11:22:33 -0700
Subject: [PATCH 14/25] tcp: initialize rcv_mss to TCP_MIN_MSS instead of 0

[ Upstream commit 499350a5a6e7512d9ed369ed63a4244b6536f4f8 ]

When tcp_disconnect() is called, inet_csk_delack_init() sets
icsk->icsk_ack.rcv_mss to 0.
This could potentially cause tcp_recvmsg() => tcp_cleanup_rbuf() =>
__tcp_select_window() call path to have division by 0 issue.
So this patch initializes rcv_mss to TCP_MIN_MSS instead of 0.

Reported-by: Andrey Konovalov  <andreyknvl@google.com>
Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 1a4db27f5833..6b3d27e50317 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2297,6 +2297,10 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tcp_set_ca_state(sk, TCP_CA_Open);
 	tcp_clear_retrans(tp);
 	inet_csk_delack_init(sk);
+	/* Initialize rcv_mss to TCP_MIN_MSS to avoid division by 0
+	 * issue in __tcp_select_window()
+	 */
+	icsk->icsk_ack.rcv_mss = TCP_MIN_MSS;
 	tcp_init_send_head(sk);
 	memset(&tp->rx_opt, 0, sizeof(tp->rx_opt));
 	__sk_dst_reset(sk);
-- 
2.13.5


From 351c99dd20f06fcfc6bf22d6ac441a35a0f7496f Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Fri, 1 Sep 2017 10:52:31 +0200
Subject: [PATCH 15/25] mlxsw: spectrum: Forbid linking to devices that have
 uppers

[ Upstream commit 25cc72a33835ed8a6f53180a822cadab855852ac ]

The mlxsw driver relies on NETDEV_CHANGEUPPER events to configure the
device in case a port is enslaved to a master netdev such as bridge or
bond.

Since the driver ignores events unrelated to its ports and their
uppers, it's possible to engineer situations in which the device's data
path differs from the kernel's.

One example to such a situation is when a port is enslaved to a bond
that is already enslaved to a bridge. When the bond was enslaved the
driver ignored the event - as the bond wasn't one of its uppers - and
therefore a bridge port instance isn't created in the device.

Until such configurations are supported forbid them by checking that the
upper device doesn't have uppers of its own.

Fixes: 0d65fc13042f ("mlxsw: spectrum: Implement LAG port join/leave")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Nogah Frankel <nogahf@mellanox.com>
Tested-by: Nogah Frankel <nogahf@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 6 ++++++
 include/linux/netdevice.h                      | 2 ++
 net/core/dev.c                                 | 3 ++-
 3 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index f902c4d3de99..1806b1fc6e4c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4172,6 +4172,8 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev,
 			return -EINVAL;
 		if (!info->linking)
 			break;
+		if (netdev_has_any_upper_dev(upper_dev))
+			return -EINVAL;
 		/* HW limitation forbids to put ports to multiple bridges. */
 		if (netif_is_bridge_master(upper_dev) &&
 		    !mlxsw_sp_master_bridge_check(mlxsw_sp, upper_dev))
@@ -4185,6 +4187,10 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev,
 		if (netif_is_lag_port(dev) && is_vlan_dev(upper_dev) &&
 		    !netif_is_lag_master(vlan_dev_real_dev(upper_dev)))
 			return -EINVAL;
+		if (!info->linking)
+			break;
+		if (netdev_has_any_upper_dev(upper_dev))
+			return -EINVAL;
 		break;
 	case NETDEV_CHANGEUPPER:
 		upper_dev = info->upper_dev;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 780e7171f548..23db1ae37464 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3901,6 +3901,8 @@ struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev,
 	     updev; \
 	     updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter)))
 
+bool netdev_has_any_upper_dev(struct net_device *dev);
+
 void *netdev_lower_get_next_private(struct net_device *dev,
 				    struct list_head **iter);
 void *netdev_lower_get_next_private_rcu(struct net_device *dev,
diff --git a/net/core/dev.c b/net/core/dev.c
index 1d0a7369d5a2..ba7b8121a414 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5337,12 +5337,13 @@ EXPORT_SYMBOL(netdev_has_upper_dev);
  * Find out if a device is linked to an upper device and return true in case
  * it is. The caller must hold the RTNL lock.
  */
-static bool netdev_has_any_upper_dev(struct net_device *dev)
+bool netdev_has_any_upper_dev(struct net_device *dev)
 {
 	ASSERT_RTNL();
 
 	return !list_empty(&dev->all_adj_list.upper);
 }
+EXPORT_SYMBOL(netdev_has_any_upper_dev);
 
 /**
  * netdev_master_upper_dev_get - Get master upper device
-- 
2.13.5


From 971808fd321a2280c7cc215b2414af7ea4ec9979 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Fri, 1 Sep 2017 12:22:25 +0300
Subject: [PATCH 16/25] bridge: switchdev: Clear forward mark when transmitting
 packet

[ Upstream commit 79e99bdd60b484af9afe0147e85a13e66d5c1cdb ]

Commit 6bc506b4fb06 ("bridge: switchdev: Add forward mark support for
stacked devices") added the 'offload_fwd_mark' bit to the skb in order
to allow drivers to indicate to the bridge driver that they already
forwarded the packet in L2.

In case the bit is set, before transmitting the packet from each port,
the port's mark is compared with the mark stored in the skb's control
block. If both marks are equal, we know the packet arrived from a switch
device that already forwarded the packet and it's not re-transmitted.

However, if the packet is transmitted from the bridge device itself
(e.g., br0), we should clear the 'offload_fwd_mark' bit as the mark
stored in the skb's control block isn't valid.

This scenario can happen in rare cases where a packet was trapped during
L3 forwarding and forwarded by the kernel to a bridge device.

Fixes: 6bc506b4fb06 ("bridge: switchdev: Add forward mark support for stacked devices")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Yotam Gigi <yotamg@mellanox.com>
Tested-by: Yotam Gigi <yotamg@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_device.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 89a687f3c0a3..5f5e28f210e0 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -53,6 +53,9 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 	brstats->tx_bytes += skb->len;
 	u64_stats_update_end(&brstats->syncp);
 
+#ifdef CONFIG_NET_SWITCHDEV
+	skb->offload_fwd_mark = 0;
+#endif
 	BR_INPUT_SKB_CB(skb)->brdev = dev;
 
 	skb_reset_mac_header(skb);
-- 
2.13.5


From e7b49f489425c908781528b22750858103489390 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Fri, 1 Sep 2017 11:26:08 +0200
Subject: [PATCH 17/25] Revert "net: use lib/percpu_counter API for
 fragmentation mem accounting"

[ Upstream commit fb452a1aa3fd4034d7999e309c5466ff2d7005aa ]

This reverts commit 6d7b857d541ecd1d9bd997c97242d4ef94b19de2.

There is a bug in fragmentation codes use of the percpu_counter API,
that can cause issues on systems with many CPUs.

The frag_mem_limit() just reads the global counter (fbc->count),
without considering other CPUs can have upto batch size (130K) that
haven't been subtracted yet.  Due to the 3MBytes lower thresh limit,
this become dangerous at >=24 CPUs (3*1024*1024/130000=24).

The correct API usage would be to use __percpu_counter_compare() which
does the right thing, and takes into account the number of (online)
CPUs and batch size, to account for this and call __percpu_counter_sum()
when needed.

We choose to revert the use of the lib/percpu_counter API for frag
memory accounting for several reasons:

1) On systems with CPUs > 24, the heavier fully locked
   __percpu_counter_sum() is always invoked, which will be more
   expensive than the atomic_t that is reverted to.

Given systems with more than 24 CPUs are becoming common this doesn't
seem like a good option.  To mitigate this, the batch size could be
decreased and thresh be increased.

2) The add_frag_mem_limit+sub_frag_mem_limit pairs happen on the RX
   CPU, before SKBs are pushed into sockets on remote CPUs.  Given
   NICs can only hash on L2 part of the IP-header, the NIC-RXq's will
   likely be limited.  Thus, a fair chance that atomic add+dec happen
   on the same CPU.

Revert note that commit 1d6119baf061 ("net: fix percpu memory leaks")
removed init_frag_mem_limit() and instead use inet_frags_init_net().
After this revert, inet_frags_uninit_net() becomes empty.

Fixes: 6d7b857d541e ("net: use lib/percpu_counter API for fragmentation mem accounting")
Fixes: 1d6119baf061 ("net: fix percpu memory leaks")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_frag.h  | 36 +++++++++---------------------------
 net/ipv4/inet_fragment.c |  4 +---
 2 files changed, 10 insertions(+), 30 deletions(-)

diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 909972aa3acd..3bb8dfec7725 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -1,14 +1,9 @@
 #ifndef __NET_FRAG_H__
 #define __NET_FRAG_H__
 
-#include <linux/percpu_counter.h>
-
 struct netns_frags {
-	/* The percpu_counter "mem" need to be cacheline aligned.
-	 *  mem.count must not share cacheline with other writers
-	 */
-	struct percpu_counter   mem ____cacheline_aligned_in_smp;
-
+	/* Keep atomic mem on separate cachelines in structs that include it */
+	atomic_t		mem ____cacheline_aligned_in_smp;
 	/* sysctls */
 	int			timeout;
 	int			high_thresh;
@@ -110,11 +105,11 @@ void inet_frags_fini(struct inet_frags *);
 
 static inline int inet_frags_init_net(struct netns_frags *nf)
 {
-	return percpu_counter_init(&nf->mem, 0, GFP_KERNEL);
+	atomic_set(&nf->mem, 0);
+	return 0;
 }
 static inline void inet_frags_uninit_net(struct netns_frags *nf)
 {
-	percpu_counter_destroy(&nf->mem);
 }
 
 void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f);
@@ -140,37 +135,24 @@ static inline bool inet_frag_evicting(struct inet_frag_queue *q)
 
 /* Memory Tracking Functions. */
 
-/* The default percpu_counter batch size is not big enough to scale to
- * fragmentation mem acct sizes.
- * The mem size of a 64K fragment is approx:
- *  (44 fragments * 2944 truesize) + frag_queue struct(200) = 129736 bytes
- */
-static unsigned int frag_percpu_counter_batch = 130000;
-
 static inline int frag_mem_limit(struct netns_frags *nf)
 {
-	return percpu_counter_read(&nf->mem);
+	return atomic_read(&nf->mem);
 }
 
 static inline void sub_frag_mem_limit(struct netns_frags *nf, int i)
 {
-	__percpu_counter_add(&nf->mem, -i, frag_percpu_counter_batch);
+	atomic_sub(i, &nf->mem);
 }
 
 static inline void add_frag_mem_limit(struct netns_frags *nf, int i)
 {
-	__percpu_counter_add(&nf->mem, i, frag_percpu_counter_batch);
+	atomic_add(i, &nf->mem);
 }
 
-static inline unsigned int sum_frag_mem_limit(struct netns_frags *nf)
+static inline int sum_frag_mem_limit(struct netns_frags *nf)
 {
-	unsigned int res;
-
-	local_bh_disable();
-	res = percpu_counter_sum_positive(&nf->mem);
-	local_bh_enable();
-
-	return res;
+	return atomic_read(&nf->mem);
 }
 
 /* RFC 3168 support :
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index b5e9317eaf9e..631c0d0d7cf8 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -234,10 +234,8 @@ void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f)
 	cond_resched();
 
 	if (read_seqretry(&f->rnd_seqlock, seq) ||
-	    percpu_counter_sum(&nf->mem))
+	    sum_frag_mem_limit(nf))
 		goto evict_again;
-
-	percpu_counter_destroy(&nf->mem);
 }
 EXPORT_SYMBOL(inet_frags_exit_net);
 
-- 
2.13.5


From f14fbf92a36a5b2b373e386cacee6bc820795e1e Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Fri, 1 Sep 2017 11:26:13 +0200
Subject: [PATCH 18/25] Revert "net: fix percpu memory leaks"

[ Upstream commit 5a63643e583b6a9789d7a225ae076fb4e603991c ]

This reverts commit 1d6119baf0610f813eb9d9580eb4fd16de5b4ceb.

After reverting commit 6d7b857d541e ("net: use lib/percpu_counter API
for fragmentation mem accounting") then here is no need for this
fix-up patch.  As percpu_counter is no longer used, it cannot
memory leak it any-longer.

Fixes: 6d7b857d541e ("net: use lib/percpu_counter API for fragmentation mem accounting")
Fixes: 1d6119baf061 ("net: fix percpu memory leaks")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_frag.h                 |  7 +------
 net/ieee802154/6lowpan/reassembly.c     | 11 +++--------
 net/ipv4/ip_fragment.c                  | 12 +++---------
 net/ipv6/netfilter/nf_conntrack_reasm.c | 12 +++---------
 net/ipv6/reassembly.c                   | 12 +++---------
 5 files changed, 13 insertions(+), 41 deletions(-)

diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 3bb8dfec7725..634d19203e7d 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -103,15 +103,10 @@ struct inet_frags {
 int inet_frags_init(struct inet_frags *);
 void inet_frags_fini(struct inet_frags *);
 
-static inline int inet_frags_init_net(struct netns_frags *nf)
+static inline void inet_frags_init_net(struct netns_frags *nf)
 {
 	atomic_set(&nf->mem, 0);
-	return 0;
 }
-static inline void inet_frags_uninit_net(struct netns_frags *nf)
-{
-}
-
 void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f);
 
 void inet_frag_kill(struct inet_frag_queue *q, struct inet_frags *f);
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index 30d875dff6b5..f85b08baff16 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -580,19 +580,14 @@ static int __net_init lowpan_frags_init_net(struct net *net)
 {
 	struct netns_ieee802154_lowpan *ieee802154_lowpan =
 		net_ieee802154_lowpan(net);
-	int res;
 
 	ieee802154_lowpan->frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
 	ieee802154_lowpan->frags.low_thresh = IPV6_FRAG_LOW_THRESH;
 	ieee802154_lowpan->frags.timeout = IPV6_FRAG_TIMEOUT;
 
-	res = inet_frags_init_net(&ieee802154_lowpan->frags);
-	if (res)
-		return res;
-	res = lowpan_frags_ns_sysctl_register(net);
-	if (res)
-		inet_frags_uninit_net(&ieee802154_lowpan->frags);
-	return res;
+	inet_frags_init_net(&ieee802154_lowpan->frags);
+
+	return lowpan_frags_ns_sysctl_register(net);
 }
 
 static void __net_exit lowpan_frags_exit_net(struct net *net)
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index bbe7f72db9c1..453db950dc9f 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -835,8 +835,6 @@ static void __init ip4_frags_ctl_register(void)
 
 static int __net_init ipv4_frags_init_net(struct net *net)
 {
-	int res;
-
 	/* Fragment cache limits.
 	 *
 	 * The fragment memory accounting code, (tries to) account for
@@ -862,13 +860,9 @@ static int __net_init ipv4_frags_init_net(struct net *net)
 
 	net->ipv4.frags.max_dist = 64;
 
-	res = inet_frags_init_net(&net->ipv4.frags);
-	if (res)
-		return res;
-	res = ip4_frags_ns_ctl_register(net);
-	if (res)
-		inet_frags_uninit_net(&net->ipv4.frags);
-	return res;
+	inet_frags_init_net(&net->ipv4.frags);
+
+	return ip4_frags_ns_ctl_register(net);
 }
 
 static void __net_exit ipv4_frags_exit_net(struct net *net)
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 986d4ca38832..b263bf3a19f7 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -622,18 +622,12 @@ EXPORT_SYMBOL_GPL(nf_ct_frag6_gather);
 
 static int nf_ct_net_init(struct net *net)
 {
-	int res;
-
 	net->nf_frag.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
 	net->nf_frag.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
 	net->nf_frag.frags.timeout = IPV6_FRAG_TIMEOUT;
-	res = inet_frags_init_net(&net->nf_frag.frags);
-	if (res)
-		return res;
-	res = nf_ct_frag6_sysctl_register(net);
-	if (res)
-		inet_frags_uninit_net(&net->nf_frag.frags);
-	return res;
+	inet_frags_init_net(&net->nf_frag.frags);
+
+	return nf_ct_frag6_sysctl_register(net);
 }
 
 static void nf_ct_net_exit(struct net *net)
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 3815e8505ed2..e585c0a2591c 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -709,19 +709,13 @@ static void ip6_frags_sysctl_unregister(void)
 
 static int __net_init ipv6_frags_init_net(struct net *net)
 {
-	int res;
-
 	net->ipv6.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
 	net->ipv6.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
 	net->ipv6.frags.timeout = IPV6_FRAG_TIMEOUT;
 
-	res = inet_frags_init_net(&net->ipv6.frags);
-	if (res)
-		return res;
-	res = ip6_frags_ns_sysctl_register(net);
-	if (res)
-		inet_frags_uninit_net(&net->ipv6.frags);
-	return res;
+	inet_frags_init_net(&net->ipv6.frags);
+
+	return ip6_frags_ns_sysctl_register(net);
 }
 
 static void __net_exit ipv6_frags_exit_net(struct net *net)
-- 
2.13.5


From b72c28b5363aa64f6533fdc09f3f7459fe7665ed Mon Sep 17 00:00:00 2001
From: Claudiu Manoil <claudiu.manoil@nxp.com>
Date: Mon, 4 Sep 2017 10:45:28 +0300
Subject: [PATCH 19/25] gianfar: Fix Tx flow control deactivation

[ Upstream commit 5d621672bc1a1e5090c1ac5432a18c79e0e13e03 ]

The wrong register is checked for the Tx flow control bit,
it should have been maccfg1 not maccfg2.
This went unnoticed for so long probably because the impact is
hardly visible, not to mention the tangled code from adjust_link().
First, link flow control (i.e. handling of Rx/Tx link level pause frames)
is disabled by default (needs to be enabled via 'ethtool -A').
Secondly, maccfg2 always returns 0 for tx_flow_oldval (except for a few
old boards), which results in Tx flow control remaining always on
once activated.

Fixes: 45b679c9a3ccd9e34f28e6ec677b812a860eb8eb ("gianfar: Implement PAUSE frame generation support")
Signed-off-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/gianfar.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 3f4e71148808..fd206889a433 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -3690,7 +3690,7 @@ static noinline void gfar_update_link_state(struct gfar_private *priv)
 		u32 tempval1 = gfar_read(&regs->maccfg1);
 		u32 tempval = gfar_read(&regs->maccfg2);
 		u32 ecntrl = gfar_read(&regs->ecntrl);
-		u32 tx_flow_oldval = (tempval & MACCFG1_TX_FLOW);
+		u32 tx_flow_oldval = (tempval1 & MACCFG1_TX_FLOW);
 
 		if (phydev->duplex != priv->oldduplex) {
 			if (!(phydev->duplex))
-- 
2.13.5


From b126400fa69b854ef9453610bea55de01eb73e29 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Tue, 5 Sep 2017 09:22:05 +0800
Subject: [PATCH 20/25] vhost_net: correctly check tx avail during rx busy
 polling

[ Upstream commit 8b949bef9172ca69d918e93509a4ecb03d0355e0 ]

We check tx avail through vhost_enable_notify() in the past which is
wrong since it only checks whether or not guest has filled more
available buffer since last avail idx synchronization which was just
done by vhost_vq_avail_empty() before. What we really want is checking
pending buffers in the avail ring. Fix this by calling
vhost_vq_avail_empty() instead.

This issue could be noticed by doing netperf TCP_RR benchmark as
client from guest (but not host). With this fix, TCP_RR from guest to
localhost restores from 1375.91 trans per sec to 55235.28 trans per
sec on my laptop (Intel(R) Core(TM) i7-5600U CPU @ 2.60GHz).

Fixes: 030881372460 ("vhost_net: basic polling support")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/net.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 5dc128a8da83..96a0661011fd 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -537,8 +537,13 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk)
 
 		preempt_enable();
 
-		if (vhost_enable_notify(&net->dev, vq))
+		if (!vhost_vq_avail_empty(&net->dev, vq))
 			vhost_poll_queue(&vq->poll);
+		else if (unlikely(vhost_enable_notify(&net->dev, vq))) {
+			vhost_disable_notify(&net->dev, vq);
+			vhost_poll_queue(&vq->poll);
+		}
+
 		mutex_unlock(&vq->mutex);
 
 		len = peek_head_len(sk);
-- 
2.13.5


From a1763a0c2eed9c0e8cf657b95ea0776f9fc0dff8 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 5 Sep 2017 17:26:33 +0800
Subject: [PATCH 21/25] ip6_gre: update mtu properly in ip6gre_err

[ Upstream commit 5c25f30c93fdc5bf25e62101aeaae7a4f9b421b3 ]

Now when probessing ICMPV6_PKT_TOOBIG, ip6gre_err only subtracts the
offset of gre header from mtu info. The expected mtu of gre device
should also subtract gre header. Otherwise, the next packets still
can't be sent out.

Jianlin found this issue when using the topo:
  client(ip6gre)<---->(nic1)route(nic2)<----->(ip6gre)server

and reducing nic2's mtu, then both tcp and sctp's performance with
big size data became 0.

This patch is to fix it by also subtracting grehdr (tun->tun_hlen)
from mtu info when updating gre device's mtu in ip6gre_err(). It
also needs to subtract ETH_HLEN if gre dev'type is ARPHRD_ETHER.

Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index d2844ee469cb..f78afe43bdff 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -432,7 +432,9 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		}
 		break;
 	case ICMPV6_PKT_TOOBIG:
-		mtu = be32_to_cpu(info) - offset;
+		mtu = be32_to_cpu(info) - offset - t->tun_hlen;
+		if (t->dev->type == ARPHRD_ETHER)
+			mtu -= ETH_HLEN;
 		if (mtu < IPV6_MIN_MTU)
 			mtu = IPV6_MIN_MTU;
 		t->dev->mtu = mtu;
-- 
2.13.5


From d61b10fda66cc6fcdf8fbe7423dc23199274321d Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 8 Sep 2017 10:26:19 +0200
Subject: [PATCH 22/25] ipv6: fix memory leak with multiple tables during netns
 destruction

[ Upstream commit ba1cc08d9488c94cb8d94f545305688b72a2a300 ]

fib6_net_exit only frees the main and local tables. If another table was
created with fib6_alloc_table, we leak it when the netns is destroyed.

Fix this in the same way ip_fib_net_exit cleans up tables, by walking
through the whole hashtable of fib6_table's. We can get rid of the
special cases for local and main, since they're also part of the
hashtable.

Reproducer:
    ip netns add x
    ip -net x -6 rule add from 6003:1::/64 table 100
    ip netns del x

Reported-by: Jianlin Shi <jishi@redhat.com>
Fixes: 58f09b78b730 ("[NETNS][IPV6] ip6_fib - make it per network namespace")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_fib.c | 25 +++++++++++++++++++------
 1 file changed, 19 insertions(+), 6 deletions(-)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index af7442211ffb..291ec5e2d3cb 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -201,6 +201,12 @@ static void rt6_release(struct rt6_info *rt)
 	}
 }
 
+static void fib6_free_table(struct fib6_table *table)
+{
+	inetpeer_invalidate_tree(&table->tb6_peers);
+	kfree(table);
+}
+
 static void fib6_link_table(struct net *net, struct fib6_table *tb)
 {
 	unsigned int h;
@@ -1893,15 +1899,22 @@ static int __net_init fib6_net_init(struct net *net)
 
 static void fib6_net_exit(struct net *net)
 {
+	unsigned int i;
+
 	rt6_ifdown(net, NULL);
 	del_timer_sync(&net->ipv6.ip6_fib_timer);
 
-#ifdef CONFIG_IPV6_MULTIPLE_TABLES
-	inetpeer_invalidate_tree(&net->ipv6.fib6_local_tbl->tb6_peers);
-	kfree(net->ipv6.fib6_local_tbl);
-#endif
-	inetpeer_invalidate_tree(&net->ipv6.fib6_main_tbl->tb6_peers);
-	kfree(net->ipv6.fib6_main_tbl);
+	for (i = 0; i < FIB_TABLE_HASHSZ; i++) {
+		struct hlist_head *head = &net->ipv6.fib_table_hash[i];
+		struct hlist_node *tmp;
+		struct fib6_table *tb;
+
+		hlist_for_each_entry_safe(tb, tmp, head, tb6_hlist) {
+			hlist_del(&tb->tb6_hlist);
+			fib6_free_table(tb);
+		}
+	}
+
 	kfree(net->ipv6.fib_table_hash);
 	kfree(net->ipv6.rt6_stats);
 }
-- 
2.13.5


From 4d1a1afca953accced98b8019ad2a2a69fbf384b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 8 Sep 2017 15:48:47 -0700
Subject: [PATCH 23/25] ipv6: fix typo in fib6_net_exit()

[ Upstream commit 32a805baf0fb70b6dbedefcd7249ac7f580f9e3b ]

IPv6 FIB should use FIB6_TABLE_HASHSZ, not FIB_TABLE_HASHSZ.

Fixes: ba1cc08d9488 ("ipv6: fix memory leak with multiple tables during netns destruction")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_fib.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 291ec5e2d3cb..5da864997495 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1904,7 +1904,7 @@ static void fib6_net_exit(struct net *net)
 	rt6_ifdown(net, NULL);
 	del_timer_sync(&net->ipv6.ip6_fib_timer);
 
-	for (i = 0; i < FIB_TABLE_HASHSZ; i++) {
+	for (i = 0; i < FIB6_TABLE_HASHSZ; i++) {
 		struct hlist_head *head = &net->ipv6.fib_table_hash[i];
 		struct hlist_node *tmp;
 		struct fib6_table *tb;
-- 
2.13.5


From e503df3fc46612cf7b9a1c86daae33b79d07c19a Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Fri, 8 Sep 2017 11:35:21 -0300
Subject: [PATCH 24/25] sctp: fix missing wake ups in some situations

[ Upstream commit 7906b00f5cd1cd484fced7fcda892176e3202c8a ]

Commit fb586f25300f ("sctp: delay calls to sk_data_ready() as much as
possible") minimized the number of wake ups that are triggered in case
the association receives a packet with multiple data chunks on it and/or
when io_events are enabled and then commit 0970f5b36659 ("sctp: signal
sk_data_ready earlier on data chunks reception") moved the wake up to as
soon as possible. It thus relies on the state machine running later to
clean the flag that the event was already generated.

The issue is that there are 2 call paths that calls
sctp_ulpq_tail_event() outside of the state machine, causing the flag to
linger and possibly omitting a needed wake up in the sequence.

One of the call paths is when enabling SCTP_SENDER_DRY_EVENTS via
setsockopt(SCTP_EVENTS), as noticed by Harald Welte. The other is when
partial reliability triggers removal of chunks from the send queue when
the application calls sendmsg().

This commit fixes it by not setting the flag in case the socket is not
owned by the user, as it won't be cleaned later. This works for
user-initiated calls and also for rx path processing.

Fixes: fb586f25300f ("sctp: delay calls to sk_data_ready() as much as possible")
Reported-by: Harald Welte <laforge@gnumonks.org>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ulpqueue.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c
index 84d0fdaf7de9..d3cfbf2f407d 100644
--- a/net/sctp/ulpqueue.c
+++ b/net/sctp/ulpqueue.c
@@ -265,7 +265,8 @@ int sctp_ulpq_tail_event(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event)
 		sctp_ulpq_clear_pd(ulpq);
 
 	if (queue == &sk->sk_receive_queue && !sp->data_ready_signalled) {
-		sp->data_ready_signalled = 1;
+		if (!sock_owned_by_user(sk))
+			sp->data_ready_signalled = 1;
 		sk->sk_data_ready(sk);
 	}
 	return 1;
-- 
2.13.5


From 964f77fe5786519f86ce155c769b5c55608039b0 Mon Sep 17 00:00:00 2001
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Thu, 7 Sep 2017 14:08:34 +0800
Subject: [PATCH 25/25] ip_tunnel: fix setting ttl and tos value in collect_md
 mode

[ Upstream commit 0f693f1995cf002432b70f43ce73f79bf8d0b6c9 ]

ttl and tos variables are declared and assigned, but are not used in
iptunnel_xmit() function.

Fixes: cfc7381b3002 ("ip_tunnel: add collect_md mode to IPIP tunnel")
Cc: Alexei Starovoitov <ast@fb.com>
Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_tunnel.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 5719d6ba0824..bd7f1836bb70 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -609,8 +609,8 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto)
 		ip_rt_put(rt);
 		goto tx_dropped;
 	}
-	iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, proto, key->tos,
-		      key->ttl, df, !net_eq(tunnel->net, dev_net(dev)));
+	iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, proto, tos, ttl,
+		      df, !net_eq(tunnel->net, dev_net(dev)));
 	return;
 tx_error:
 	dev->stats.tx_errors++;
-- 
2.13.5


[-- Attachment #3: net_412.mbox --]
[-- Type: Application/Octet-Stream, Size: 109712 bytes --]

From 569e95da23a05964687bb6ac2e4d8764fb60c518 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Fri, 18 Aug 2017 14:40:53 +0200
Subject: [PATCH 01/43] ipv6: accept 64k - 1 packet length in
 ip6_find_1stfragopt()

[ Upstream commit 3de33e1ba0506723ab25734e098cf280ecc34756 ]

A packet length of exactly IPV6_MAXPLEN is allowed, we should
refuse parsing options only if the size is 64KiB or more.

While at it, remove one extra variable and one assignment which
were also introduced by the commit that introduced the size
check. Checking the sum 'offset + len' and only later adding
'len' to 'offset' doesn't provide any advantage over directly
summing to 'offset' and checking it.

Fixes: 6399f1fae4ec ("ipv6: avoid overflow of offset in ip6_find_1stfragopt")
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/output_core.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index abb2c307fbe8..a338bbc33cf3 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -86,7 +86,6 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 
 	while (offset <= packet_len) {
 		struct ipv6_opt_hdr *exthdr;
-		unsigned int len;
 
 		switch (**nexthdr) {
 
@@ -112,10 +111,9 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 
 		exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) +
 						 offset);
-		len = ipv6_optlen(exthdr);
-		if (len + offset >= IPV6_MAXPLEN)
+		offset += ipv6_optlen(exthdr);
+		if (offset > IPV6_MAXPLEN)
 			return -EINVAL;
-		offset += len;
 		*nexthdr = &exthdr->nexthdr;
 	}
 
-- 
2.13.5


From c9fc520c2cb4374776a2167834d2a81d52c60015 Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Mon, 21 Aug 2017 09:47:10 -0700
Subject: [PATCH 02/43] ipv6: add rcu grace period before freeing fib6_node

[ Upstream commit c5cff8561d2d0006e972bd114afd51f082fee77c ]

We currently keep rt->rt6i_node pointing to the fib6_node for the route.
And some functions make use of this pointer to dereference the fib6_node
from rt structure, e.g. rt6_check(). However, as there is neither
refcount nor rcu taken when dereferencing rt->rt6i_node, it could
potentially cause crashes as rt->rt6i_node could be set to NULL by other
CPUs when doing a route deletion.
This patch introduces an rcu grace period before freeing fib6_node and
makes sure the functions that dereference it takes rcu_read_lock().

Note: there is no "Fixes" tag because this bug was there in a very
early stage.

Signed-off-by: Wei Wang <weiwan@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h | 29 ++++++++++++++++++++++++++++-
 net/ipv6/ip6_fib.c    | 20 ++++++++++++++++----
 net/ipv6/route.c      | 14 +++++++++++---
 3 files changed, 55 insertions(+), 8 deletions(-)

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index c979c878df1c..dc4301266a89 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -70,6 +70,7 @@ struct fib6_node {
 	__u16			fn_flags;
 	int			fn_sernum;
 	struct rt6_info		*rr_ptr;
+	struct rcu_head		rcu;
 };
 
 #ifndef CONFIG_IPV6_SUBTREES
@@ -167,13 +168,39 @@ static inline void rt6_update_expires(struct rt6_info *rt0, int timeout)
 	rt0->rt6i_flags |= RTF_EXPIRES;
 }
 
+/* Function to safely get fn->sernum for passed in rt
+ * and store result in passed in cookie.
+ * Return true if we can get cookie safely
+ * Return false if not
+ */
+static inline bool rt6_get_cookie_safe(const struct rt6_info *rt,
+				       u32 *cookie)
+{
+	struct fib6_node *fn;
+	bool status = false;
+
+	rcu_read_lock();
+	fn = rcu_dereference(rt->rt6i_node);
+
+	if (fn) {
+		*cookie = fn->fn_sernum;
+		status = true;
+	}
+
+	rcu_read_unlock();
+	return status;
+}
+
 static inline u32 rt6_get_cookie(const struct rt6_info *rt)
 {
+	u32 cookie = 0;
+
 	if (rt->rt6i_flags & RTF_PCPU ||
 	    (unlikely(rt->dst.flags & DST_NOCACHE) && rt->dst.from))
 		rt = (struct rt6_info *)(rt->dst.from);
+	rt6_get_cookie_safe(rt, &cookie);
 
-	return rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0;
+	return cookie;
 }
 
 static inline void ip6_rt_put(struct rt6_info *rt)
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index cd8dd8c4e819..cafcfeef0e53 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -148,11 +148,23 @@ static struct fib6_node *node_alloc(void)
 	return fn;
 }
 
-static void node_free(struct fib6_node *fn)
+static void node_free_immediate(struct fib6_node *fn)
+{
+	kmem_cache_free(fib6_node_kmem, fn);
+}
+
+static void node_free_rcu(struct rcu_head *head)
 {
+	struct fib6_node *fn = container_of(head, struct fib6_node, rcu);
+
 	kmem_cache_free(fib6_node_kmem, fn);
 }
 
+static void node_free(struct fib6_node *fn)
+{
+	call_rcu(&fn->rcu, node_free_rcu);
+}
+
 static void rt6_rcu_free(struct rt6_info *rt)
 {
 	call_rcu(&rt->dst.rcu_head, dst_rcu_free);
@@ -599,9 +611,9 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root,
 
 		if (!in || !ln) {
 			if (in)
-				node_free(in);
+				node_free_immediate(in);
 			if (ln)
-				node_free(ln);
+				node_free_immediate(ln);
 			return ERR_PTR(-ENOMEM);
 		}
 
@@ -1035,7 +1047,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 				   root, and then (in failure) stale node
 				   in main tree.
 				 */
-				node_free(sfn);
+				node_free_immediate(sfn);
 				err = PTR_ERR(sn);
 				goto failure;
 			}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index aeb7097acc0a..502f84bfd762 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1289,7 +1289,9 @@ static void rt6_dst_from_metrics_check(struct rt6_info *rt)
 
 static struct dst_entry *rt6_check(struct rt6_info *rt, u32 cookie)
 {
-	if (!rt->rt6i_node || (rt->rt6i_node->fn_sernum != cookie))
+	u32 rt_cookie;
+
+	if (!rt6_get_cookie_safe(rt, &rt_cookie) || rt_cookie != cookie)
 		return NULL;
 
 	if (rt6_check_expired(rt))
@@ -1357,8 +1359,14 @@ static void ip6_link_failure(struct sk_buff *skb)
 		if (rt->rt6i_flags & RTF_CACHE) {
 			dst_hold(&rt->dst);
 			ip6_del_rt(rt);
-		} else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT)) {
-			rt->rt6i_node->fn_sernum = -1;
+		} else {
+			struct fib6_node *fn;
+
+			rcu_read_lock();
+			fn = rcu_dereference(rt->rt6i_node);
+			if (fn && (rt->rt6i_flags & RTF_DEFAULT))
+				fn->fn_sernum = -1;
+			rcu_read_unlock();
 		}
 	}
 }
-- 
2.13.5


From f41dbbb5fc9430521298d10244bb0f60504d9084 Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Fri, 25 Aug 2017 15:03:10 -0700
Subject: [PATCH 03/43] ipv6: fix sparse warning on rt6i_node

[ Upstream commit 4e587ea71bf924f7dac621f1351653bd41e446cb ]

Commit c5cff8561d2d adds rcu grace period before freeing fib6_node. This
generates a new sparse warning on rt->rt6i_node related code:
  net/ipv6/route.c:1394:30: error: incompatible types in comparison
  expression (different address spaces)
  ./include/net/ip6_fib.h:187:14: error: incompatible types in comparison
  expression (different address spaces)

This commit adds "__rcu" tag for rt6i_node and makes sure corresponding
rcu API is used for it.
After this fix, sparse no longer generates the above warning.

Fixes: c5cff8561d2d ("ipv6: add rcu grace period before freeing fib6_node")
Signed-off-by: Wei Wang <weiwan@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h |  2 +-
 net/ipv6/addrconf.c   |  2 +-
 net/ipv6/ip6_fib.c    | 11 +++++++----
 net/ipv6/route.c      |  3 ++-
 4 files changed, 11 insertions(+), 7 deletions(-)

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index dc4301266a89..0f29ea1bc7bf 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -105,7 +105,7 @@ struct rt6_info {
 	 * the same cache line.
 	 */
 	struct fib6_table		*rt6i_table;
-	struct fib6_node		*rt6i_node;
+	struct fib6_node __rcu		*rt6i_node;
 
 	struct in6_addr			rt6i_gateway;
 
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 39a44c0598f7..d16d642ea322 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5541,7 +5541,7 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
 		 * our DAD process, so we don't need
 		 * to do it again
 		 */
-		if (!(ifp->rt->rt6i_node))
+		if (!rcu_access_pointer(ifp->rt->rt6i_node))
 			ip6_ins_rt(ifp->rt);
 		if (ifp->idev->cnf.forwarding)
 			addrconf_join_anycast(ifp);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index cafcfeef0e53..846648ea3bcc 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -887,7 +887,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 
 		rt->dst.rt6_next = iter;
 		*ins = rt;
-		rt->rt6i_node = fn;
+		rcu_assign_pointer(rt->rt6i_node, fn);
 		atomic_inc(&rt->rt6i_ref);
 		if (!info->skip_notify)
 			inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags);
@@ -913,7 +913,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 			return err;
 
 		*ins = rt;
-		rt->rt6i_node = fn;
+		rcu_assign_pointer(rt->rt6i_node, fn);
 		rt->dst.rt6_next = iter->dst.rt6_next;
 		atomic_inc(&rt->rt6i_ref);
 		if (!info->skip_notify)
@@ -1475,8 +1475,9 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp,
 
 int fib6_del(struct rt6_info *rt, struct nl_info *info)
 {
+	struct fib6_node *fn = rcu_dereference_protected(rt->rt6i_node,
+				    lockdep_is_held(&rt->rt6i_table->tb6_lock));
 	struct net *net = info->nl_net;
-	struct fib6_node *fn = rt->rt6i_node;
 	struct rt6_info **rtp;
 
 #if RT6_DEBUG >= 2
@@ -1665,7 +1666,9 @@ static int fib6_clean_node(struct fib6_walker *w)
 			if (res) {
 #if RT6_DEBUG >= 2
 				pr_debug("%s: del failed: rt=%p@%p err=%d\n",
-					 __func__, rt, rt->rt6i_node, res);
+					 __func__, rt,
+					 rcu_access_pointer(rt->rt6i_node),
+					 res);
 #endif
 				continue;
 			}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 502f84bfd762..cd2fb18d9f8d 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1383,7 +1383,8 @@ static void rt6_do_update_pmtu(struct rt6_info *rt, u32 mtu)
 static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt)
 {
 	return !(rt->rt6i_flags & RTF_CACHE) &&
-		(rt->rt6i_flags & RTF_PCPU || rt->rt6i_node);
+		(rt->rt6i_flags & RTF_PCPU ||
+		 rcu_access_pointer(rt->rt6i_node));
 }
 
 static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
-- 
2.13.5


From 2955e802e09af74c8d4a21ed1111b19a8519ee8e Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 22 Aug 2017 15:36:08 +0200
Subject: [PATCH 04/43] macsec: add genl family module alias

[ Upstream commit 78362998f58c7c271e2719dcd0aaced435c801f9 ]

This helps tools such as wpa_supplicant can start even if the macsec
module isn't loaded yet.

Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macsec.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 79411675f0e6..d16ce61b3696 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -3518,6 +3518,7 @@ module_init(macsec_init);
 module_exit(macsec_exit);
 
 MODULE_ALIAS_RTNL_LINK("macsec");
+MODULE_ALIAS_GENL_FAMILY("macsec");
 
 MODULE_DESCRIPTION("MACsec IEEE 802.1AE");
 MODULE_LICENSE("GPL v2");
-- 
2.13.5


From 5cb0755c08c2fb3f2f17842dbb153ef4f0551771 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 22 Aug 2017 09:39:28 -0700
Subject: [PATCH 05/43] udp: on peeking bad csum, drop packets even if not at
 head

[ Upstream commit fd6055a806edc4019be1b9fb7d25262599bca5b1 ]

When peeking, if a bad csum is discovered, the skb is unlinked from
the queue with __sk_queue_drop_skb and the peek operation restarted.

__sk_queue_drop_skb only drops packets that match the queue head.

This fails if the skb was found after the head, using SO_PEEK_OFF
socket option. This causes an infinite loop.

We MUST drop this problematic skb, and we can simply check if skb was
already removed by another thread, by looking at skb->next :

This pointer is set to NULL by the  __skb_unlink() operation, that might
have happened only under the spinlock protection.

Many thanks to syzkaller team (and particularly Dmitry Vyukov who
provided us nice C reproducers exhibiting the lockup) and Willem de
Bruijn who provided first version for this patch and a test program.

Fixes: 627d2d6b5500 ("udp: enable MSG_PEEK at non-zero offset")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/datagram.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/datagram.c b/net/core/datagram.c
index db1866f2ffcf..25c803e520da 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -345,7 +345,7 @@ int __sk_queue_drop_skb(struct sock *sk, struct sk_buff *skb,
 	if (flags & MSG_PEEK) {
 		err = -ENOENT;
 		spin_lock_bh(&sk->sk_receive_queue.lock);
-		if (skb == skb_peek(&sk->sk_receive_queue)) {
+		if (skb->next) {
 			__skb_unlink(skb, &sk->sk_receive_queue);
 			atomic_dec(&skb->users);
 			if (destructor)
-- 
2.13.5


From af085e144a1b31342e44c9bc2fc838451f39b49e Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 23 Aug 2017 00:06:09 +0200
Subject: [PATCH 06/43] bpf: fix map value attribute for hash of maps

[ Upstream commit 33ba43ed0afc13a29b1314e3e45a9938d310ba13 ]

Currently, iproute2's BPF ELF loader works fine with array of maps
when retrieving the fd from a pinned node and doing a selfcheck
against the provided map attributes from the object file, but we
fail to do the same for hash of maps and thus refuse to get the
map from pinned node.

Reason is that when allocating hash of maps, fd_htab_map_alloc() will
set the value size to sizeof(void *), and any user space map creation
requests are forced to set 4 bytes as value size. Thus, selfcheck
will complain about exposed 8 bytes on 64 bit archs vs. 4 bytes from
object file as value size. Contract is that fdinfo or BPF_MAP_GET_FD_BY_ID
returns the value size used to create the map.

Fix it by handling it the same way as we do for array of maps, which
means that we leave value size at 4 bytes and in the allocation phase
round up value size to 8 bytes. alloc_htab_elem() needs an adjustment
in order to copy rounded up 8 bytes due to bpf_fd_htab_map_update_elem()
calling into htab_map_update_elem() with the pointer of the map
pointer as value. Unlike array of maps where we just xchg(), we're
using the generic htab_map_update_elem() callback also used from helper
calls, which published the key/value already on return, so we need
to ensure to memcpy() the right size.

Fixes: bcc6b1b7ebf8 ("bpf: Add hash of maps support")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/hashtab.c | 30 +++++++++++++++++-------------
 1 file changed, 17 insertions(+), 13 deletions(-)

diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 004334ea13ba..06c55ac15b07 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -652,12 +652,27 @@ static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr,
 	}
 }
 
+static bool fd_htab_map_needs_adjust(const struct bpf_htab *htab)
+{
+	return htab->map.map_type == BPF_MAP_TYPE_HASH_OF_MAPS &&
+	       BITS_PER_LONG == 64;
+}
+
+static u32 htab_size_value(const struct bpf_htab *htab, bool percpu)
+{
+	u32 size = htab->map.value_size;
+
+	if (percpu || fd_htab_map_needs_adjust(htab))
+		size = round_up(size, 8);
+	return size;
+}
+
 static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 					 void *value, u32 key_size, u32 hash,
 					 bool percpu, bool onallcpus,
 					 struct htab_elem *old_elem)
 {
-	u32 size = htab->map.value_size;
+	u32 size = htab_size_value(htab, percpu);
 	bool prealloc = htab_is_prealloc(htab);
 	struct htab_elem *l_new, **pl_new;
 	void __percpu *pptr;
@@ -696,9 +711,6 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 
 	memcpy(l_new->key, key, key_size);
 	if (percpu) {
-		/* round up value_size to 8 bytes */
-		size = round_up(size, 8);
-
 		if (prealloc) {
 			pptr = htab_elem_get_ptr(l_new, key_size);
 		} else {
@@ -1209,17 +1221,9 @@ const struct bpf_map_ops htab_lru_percpu_map_ops = {
 
 static struct bpf_map *fd_htab_map_alloc(union bpf_attr *attr)
 {
-	struct bpf_map *map;
-
 	if (attr->value_size != sizeof(u32))
 		return ERR_PTR(-EINVAL);
-
-	/* pointer is stored internally */
-	attr->value_size = sizeof(void *);
-	map = htab_map_alloc(attr);
-	attr->value_size = sizeof(u32);
-
-	return map;
+	return htab_map_alloc(attr);
 }
 
 static void fd_htab_map_free(struct bpf_map *map)
-- 
2.13.5


From 13b7f6ea7476b8eb976c25f9f0b84e73bf886e56 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 22 Aug 2017 15:24:47 -0700
Subject: [PATCH 07/43] fsl/man: Inherit parent device and of_node

[ Upstream commit a1a50c8e4c241a505b7270e1a3c6e50d94e794b1 ]

Junote Cai reported that he was not able to get a DSA setup involving the
Freescale DPAA/FMAN driver to work and narrowed it down to
of_find_net_device_by_node(). This function requires the network device's
device reference to be correctly set which is the case here, though we have
lost any device_node association there.

The problem is that dpaa_eth_add_device() allocates a "dpaa-ethernet" platform
device, and later on dpaa_eth_probe() is called but SET_NETDEV_DEV() won't be
propagating &pdev->dev.of_node properly. Fix this by inherenting both the parent
device and the of_node when dpaa_eth_add_device() creates the platform device.

Fixes: 3933961682a3 ("fsl/fman: Add FMan MAC driver")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fman/mac.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c
index 6e67d22fd0d5..1c7da16ad0ff 100644
--- a/drivers/net/ethernet/freescale/fman/mac.c
+++ b/drivers/net/ethernet/freescale/fman/mac.c
@@ -623,6 +623,8 @@ static struct platform_device *dpaa_eth_add_device(int fman_id,
 		goto no_mem;
 	}
 
+	pdev->dev.of_node = node;
+	pdev->dev.parent = priv->dev;
 	set_dma_ops(&pdev->dev, get_dma_ops(priv->dev));
 
 	ret = platform_device_add_data(pdev, &data, sizeof(data));
-- 
2.13.5


From c34cafe95d4da1774658fc4e59a9289e2e452634 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Wed, 23 Aug 2017 13:27:13 +0200
Subject: [PATCH 08/43] sctp: Avoid out-of-bounds reads from address storage

[ Upstream commit ee6c88bb754e3d363e568da78086adfedb692447 ]

inet_diag_msg_sctp{,l}addr_fill() and sctp_get_sctp_info() copy
sizeof(sockaddr_storage) bytes to fill in sockaddr structs used
to export diagnostic information to userspace.

However, the memory allocated to store sockaddr information is
smaller than that and depends on the address family, so we leak
up to 100 uninitialized bytes to userspace. Just use the size of
the source structs instead, in all the three cases this is what
userspace expects. Zero out the remaining memory.

Unused bytes (i.e. when IPv4 addresses are used) in source
structs sctp_sockaddr_entry and sctp_transport are already
cleared by sctp_add_bind_addr() and sctp_transport_new(),
respectively.

Noticed while testing KASAN-enabled kernel with 'ss':

[ 2326.885243] BUG: KASAN: slab-out-of-bounds in inet_sctp_diag_fill+0x42c/0x6c0 [sctp_diag] at addr ffff881be8779800
[ 2326.896800] Read of size 128 by task ss/9527
[ 2326.901564] CPU: 0 PID: 9527 Comm: ss Not tainted 4.11.0-22.el7a.x86_64 #1
[ 2326.909236] Hardware name: Dell Inc. PowerEdge R730/072T6D, BIOS 2.4.3 01/17/2017
[ 2326.917585] Call Trace:
[ 2326.920312]  dump_stack+0x63/0x8d
[ 2326.924014]  kasan_object_err+0x21/0x70
[ 2326.928295]  kasan_report+0x288/0x540
[ 2326.932380]  ? inet_sctp_diag_fill+0x42c/0x6c0 [sctp_diag]
[ 2326.938500]  ? skb_put+0x8b/0xd0
[ 2326.942098]  ? memset+0x31/0x40
[ 2326.945599]  check_memory_region+0x13c/0x1a0
[ 2326.950362]  memcpy+0x23/0x50
[ 2326.953669]  inet_sctp_diag_fill+0x42c/0x6c0 [sctp_diag]
[ 2326.959596]  ? inet_diag_msg_sctpasoc_fill+0x460/0x460 [sctp_diag]
[ 2326.966495]  ? __lock_sock+0x102/0x150
[ 2326.970671]  ? sock_def_wakeup+0x60/0x60
[ 2326.975048]  ? remove_wait_queue+0xc0/0xc0
[ 2326.979619]  sctp_diag_dump+0x44a/0x760 [sctp_diag]
[ 2326.985063]  ? sctp_ep_dump+0x280/0x280 [sctp_diag]
[ 2326.990504]  ? memset+0x31/0x40
[ 2326.994007]  ? mutex_lock+0x12/0x40
[ 2326.997900]  __inet_diag_dump+0x57/0xb0 [inet_diag]
[ 2327.003340]  ? __sys_sendmsg+0x150/0x150
[ 2327.007715]  inet_diag_dump+0x4d/0x80 [inet_diag]
[ 2327.012979]  netlink_dump+0x1e6/0x490
[ 2327.017064]  __netlink_dump_start+0x28e/0x2c0
[ 2327.021924]  inet_diag_handler_cmd+0x189/0x1a0 [inet_diag]
[ 2327.028045]  ? inet_diag_rcv_msg_compat+0x1b0/0x1b0 [inet_diag]
[ 2327.034651]  ? inet_diag_dump_compat+0x190/0x190 [inet_diag]
[ 2327.040965]  ? __netlink_lookup+0x1b9/0x260
[ 2327.045631]  sock_diag_rcv_msg+0x18b/0x1e0
[ 2327.050199]  netlink_rcv_skb+0x14b/0x180
[ 2327.054574]  ? sock_diag_bind+0x60/0x60
[ 2327.058850]  sock_diag_rcv+0x28/0x40
[ 2327.062837]  netlink_unicast+0x2e7/0x3b0
[ 2327.067212]  ? netlink_attachskb+0x330/0x330
[ 2327.071975]  ? kasan_check_write+0x14/0x20
[ 2327.076544]  netlink_sendmsg+0x5be/0x730
[ 2327.080918]  ? netlink_unicast+0x3b0/0x3b0
[ 2327.085486]  ? kasan_check_write+0x14/0x20
[ 2327.090057]  ? selinux_socket_sendmsg+0x24/0x30
[ 2327.095109]  ? netlink_unicast+0x3b0/0x3b0
[ 2327.099678]  sock_sendmsg+0x74/0x80
[ 2327.103567]  ___sys_sendmsg+0x520/0x530
[ 2327.107844]  ? __get_locked_pte+0x178/0x200
[ 2327.112510]  ? copy_msghdr_from_user+0x270/0x270
[ 2327.117660]  ? vm_insert_page+0x360/0x360
[ 2327.122133]  ? vm_insert_pfn_prot+0xb4/0x150
[ 2327.126895]  ? vm_insert_pfn+0x32/0x40
[ 2327.131077]  ? vvar_fault+0x71/0xd0
[ 2327.134968]  ? special_mapping_fault+0x69/0x110
[ 2327.140022]  ? __do_fault+0x42/0x120
[ 2327.144008]  ? __handle_mm_fault+0x1062/0x17a0
[ 2327.148965]  ? __fget_light+0xa7/0xc0
[ 2327.153049]  __sys_sendmsg+0xcb/0x150
[ 2327.157133]  ? __sys_sendmsg+0xcb/0x150
[ 2327.161409]  ? SyS_shutdown+0x140/0x140
[ 2327.165688]  ? exit_to_usermode_loop+0xd0/0xd0
[ 2327.170646]  ? __do_page_fault+0x55d/0x620
[ 2327.175216]  ? __sys_sendmsg+0x150/0x150
[ 2327.179591]  SyS_sendmsg+0x12/0x20
[ 2327.183384]  do_syscall_64+0xe3/0x230
[ 2327.187471]  entry_SYSCALL64_slow_path+0x25/0x25
[ 2327.192622] RIP: 0033:0x7f41d18fa3b0
[ 2327.196608] RSP: 002b:00007ffc3b731218 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
[ 2327.205055] RAX: ffffffffffffffda RBX: 00007ffc3b731380 RCX: 00007f41d18fa3b0
[ 2327.213017] RDX: 0000000000000000 RSI: 00007ffc3b731340 RDI: 0000000000000003
[ 2327.220978] RBP: 0000000000000002 R08: 0000000000000004 R09: 0000000000000040
[ 2327.228939] R10: 00007ffc3b730f30 R11: 0000000000000246 R12: 0000000000000003
[ 2327.236901] R13: 00007ffc3b731340 R14: 00007ffc3b7313d0 R15: 0000000000000084
[ 2327.244865] Object at ffff881be87797e0, in cache kmalloc-64 size: 64
[ 2327.251953] Allocated:
[ 2327.254581] PID = 9484
[ 2327.257215]  save_stack_trace+0x1b/0x20
[ 2327.261485]  save_stack+0x46/0xd0
[ 2327.265179]  kasan_kmalloc+0xad/0xe0
[ 2327.269165]  kmem_cache_alloc_trace+0xe6/0x1d0
[ 2327.274138]  sctp_add_bind_addr+0x58/0x180 [sctp]
[ 2327.279400]  sctp_do_bind+0x208/0x310 [sctp]
[ 2327.284176]  sctp_bind+0x61/0xa0 [sctp]
[ 2327.288455]  inet_bind+0x5f/0x3a0
[ 2327.292151]  SYSC_bind+0x1a4/0x1e0
[ 2327.295944]  SyS_bind+0xe/0x10
[ 2327.299349]  do_syscall_64+0xe3/0x230
[ 2327.303433]  return_from_SYSCALL_64+0x0/0x6a
[ 2327.308194] Freed:
[ 2327.310434] PID = 4131
[ 2327.313065]  save_stack_trace+0x1b/0x20
[ 2327.317344]  save_stack+0x46/0xd0
[ 2327.321040]  kasan_slab_free+0x73/0xc0
[ 2327.325220]  kfree+0x96/0x1a0
[ 2327.328530]  dynamic_kobj_release+0x15/0x40
[ 2327.333195]  kobject_release+0x99/0x1e0
[ 2327.337472]  kobject_put+0x38/0x70
[ 2327.341266]  free_notes_attrs+0x66/0x80
[ 2327.345545]  mod_sysfs_teardown+0x1a5/0x270
[ 2327.350211]  free_module+0x20/0x2a0
[ 2327.354099]  SyS_delete_module+0x2cb/0x2f0
[ 2327.358667]  do_syscall_64+0xe3/0x230
[ 2327.362750]  return_from_SYSCALL_64+0x0/0x6a
[ 2327.367510] Memory state around the buggy address:
[ 2327.372855]  ffff881be8779700: fc fc fc fc 00 00 00 00 00 00 00 00 fc fc fc fc
[ 2327.380914]  ffff881be8779780: fb fb fb fb fb fb fb fb fc fc fc fc 00 00 00 00
[ 2327.388972] >ffff881be8779800: 00 00 00 00 fc fc fc fc fb fb fb fb fb fb fb fb
[ 2327.397031]                                ^
[ 2327.401792]  ffff881be8779880: fc fc fc fc fb fb fb fb fb fb fb fb fc fc fc fc
[ 2327.409850]  ffff881be8779900: 00 00 00 00 00 04 fc fc fc fc fc fc 00 00 00 00
[ 2327.417907] ==================================================================

This fixes CVE-2017-7558.

References: https://bugzilla.redhat.com/show_bug.cgi?id=1480266
Fixes: 8f840e47f190 ("sctp: add the sctp_diag.c file")
Cc: Xin Long <lucien.xin@gmail.com>
Cc: Vlad Yasevich <vyasevich@gmail.com>
Cc: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sctp_diag.c | 7 +++++--
 net/sctp/socket.c    | 3 +--
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/net/sctp/sctp_diag.c b/net/sctp/sctp_diag.c
index 9a647214a91e..e99518e79b52 100644
--- a/net/sctp/sctp_diag.c
+++ b/net/sctp/sctp_diag.c
@@ -70,7 +70,8 @@ static int inet_diag_msg_sctpladdrs_fill(struct sk_buff *skb,
 
 	info = nla_data(attr);
 	list_for_each_entry_rcu(laddr, address_list, list) {
-		memcpy(info, &laddr->a, addrlen);
+		memcpy(info, &laddr->a, sizeof(laddr->a));
+		memset(info + sizeof(laddr->a), 0, addrlen - sizeof(laddr->a));
 		info += addrlen;
 	}
 
@@ -93,7 +94,9 @@ static int inet_diag_msg_sctpaddrs_fill(struct sk_buff *skb,
 	info = nla_data(attr);
 	list_for_each_entry(from, &asoc->peer.transport_addr_list,
 			    transports) {
-		memcpy(info, &from->ipaddr, addrlen);
+		memcpy(info, &from->ipaddr, sizeof(from->ipaddr));
+		memset(info + sizeof(from->ipaddr), 0,
+		       addrlen - sizeof(from->ipaddr));
 		info += addrlen;
 	}
 
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 3a8318e518f1..51532a1da8c6 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4538,8 +4538,7 @@ int sctp_get_sctp_info(struct sock *sk, struct sctp_association *asoc,
 	info->sctpi_ictrlchunks = asoc->stats.ictrlchunks;
 
 	prim = asoc->peer.primary_path;
-	memcpy(&info->sctpi_p_address, &prim->ipaddr,
-	       sizeof(struct sockaddr_storage));
+	memcpy(&info->sctpi_p_address, &prim->ipaddr, sizeof(prim->ipaddr));
 	info->sctpi_p_state = prim->state;
 	info->sctpi_p_cwnd = prim->cwnd;
 	info->sctpi_p_srtt = prim->srtt;
-- 
2.13.5


From 5612c7597b6ad3b508dea96966f92e7de5271fff Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 23 Aug 2017 15:59:49 +0200
Subject: [PATCH 09/43] qlge: avoid memcpy buffer overflow

[ Upstream commit e58f95831e7468d25eb6e41f234842ecfe6f014f ]

gcc-8.0.0 (snapshot) points out that we copy a variable-length string
into a fixed length field using memcpy() with the destination length,
and that ends up copying whatever follows the string:

    inlined from 'ql_core_dump' at drivers/net/ethernet/qlogic/qlge/qlge_dbg.c:1106:2:
drivers/net/ethernet/qlogic/qlge/qlge_dbg.c:708:2: error: 'memcpy' reading 15 bytes from a region of size 14 [-Werror=stringop-overflow=]
  memcpy(seg_hdr->description, desc, (sizeof(seg_hdr->description)) - 1);

Changing it to use strncpy() will instead zero-pad the destination,
which seems to be the right thing to do here.

The bug is probably harmless, but it seems like a good idea to address
it in stable kernels as well, if only for the purpose of building with
gcc-8 without warnings.

Fixes: a61f80261306 ("qlge: Add ethtool register dump function.")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qlge/qlge_dbg.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_dbg.c b/drivers/net/ethernet/qlogic/qlge/qlge_dbg.c
index 28ea0af89aef..e3223f2fe2ff 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_dbg.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_dbg.c
@@ -724,7 +724,7 @@ static void ql_build_coredump_seg_header(
 	seg_hdr->cookie = MPI_COREDUMP_COOKIE;
 	seg_hdr->segNum = seg_number;
 	seg_hdr->segSize = seg_size;
-	memcpy(seg_hdr->description, desc, (sizeof(seg_hdr->description)) - 1);
+	strncpy(seg_hdr->description, desc, (sizeof(seg_hdr->description)) - 1);
 }
 
 /*
-- 
2.13.5


From dfc7cbca9e5c570c27274ae82f893820ff843ec5 Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Wed, 23 Aug 2017 10:43:02 -0400
Subject: [PATCH 10/43] tipc: Fix tipc_sk_reinit handling of -EAGAIN

[ Upstream commit 6c7e983b220f89e03286dc70a41c7ef3a8b409df ]

In 9dbbfb0ab6680c6a85609041011484e6658e7d3c function tipc_sk_reinit
had additional logic added to loop in the event that function
rhashtable_walk_next() returned -EAGAIN. No worries.

However, if rhashtable_walk_start returns -EAGAIN, it does "continue",
and therefore skips the call to rhashtable_walk_stop(). That has
the effect of calling rcu_read_lock() without its paired call to
rcu_read_unlock(). Since rcu_read_lock() may be nested, the problem
may not be apparent for a while, especially since resize events may
be rare. But the comments to rhashtable_walk_start() state:

 * ...Note that we take the RCU lock in all
 * cases including when we return an error.  So you must always call
 * rhashtable_walk_stop to clean up.

This patch replaces the continue with a goto and label to ensure a
matching call to rhashtable_walk_stop().

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/socket.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 1b92b72e812f..a0f50278901b 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2255,8 +2255,8 @@ void tipc_sk_reinit(struct net *net)
 
 	do {
 		tsk = ERR_PTR(rhashtable_walk_start(&iter));
-		if (tsk)
-			continue;
+		if (IS_ERR(tsk))
+			goto walk_stop;
 
 		while ((tsk = rhashtable_walk_next(&iter)) && !IS_ERR(tsk)) {
 			spin_lock_bh(&tsk->sk.sk_lock.slock);
@@ -2265,7 +2265,7 @@ void tipc_sk_reinit(struct net *net)
 			msg_set_orignode(msg, tn->own_addr);
 			spin_unlock_bh(&tsk->sk.sk_lock.slock);
 		}
-
+walk_stop:
 		rhashtable_walk_stop(&iter);
 	} while (tsk == ERR_PTR(-EAGAIN));
 }
-- 
2.13.5


From 9f261441036828c6b54966e11e71db6d9735f6df Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 24 Aug 2017 15:20:41 -0700
Subject: [PATCH 11/43] net: systemport: Be drop monitor friendly

[ Upstream commit c45182eb967af11e9482168be5be41aa22e5d321 ]

Utilize dev_consume_skb_any(cb->skb) in bcm_sysport_free_cb() which is
used when a TX packet is completed, as well as when the RX ring is
cleaned on shutdown. None of these two cases are packet drops, so be
drop monitor friendly.

Suggested-by: Eric Dumazet <edumazet@gmail.com>
Fixes: 80105befdb4b ("net: systemport: add Broadcom SYSTEMPORT Ethernet MAC driver")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bcmsysport.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 5274501428e4..a2c8086c19ca 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -593,7 +593,7 @@ static int bcm_sysport_set_coalesce(struct net_device *dev,
 
 static void bcm_sysport_free_cb(struct bcm_sysport_cb *cb)
 {
-	dev_kfree_skb_any(cb->skb);
+	dev_consume_skb_any(cb->skb);
 	cb->skb = NULL;
 	dma_unmap_addr_set(cb, dma_addr, 0);
 }
-- 
2.13.5


From c3ba171e40dea3c98651298fafd9b2234797935f Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 24 Aug 2017 15:56:29 -0700
Subject: [PATCH 12/43] net: bcmgenet: Be drop monitor friendly

[ Upstream commit d4fec855905fa8bd5fb1c59f73ad2d74a944876a ]

There are 3 spots where we call dev_kfree_skb() but we are actually
just doing a normal SKB consumption: __bcmgenet_tx_reclaim() for normal
TX reclamation, bcmgenet_alloc_rx_buffers() during the initial RX ring
setup and bcmgenet_free_rx_buffers() during RX ring cleanup.

Fixes: d6707bec5986 ("net: bcmgenet: rewrite bcmgenet_rx_refill()")
Fixes: f48bed16a756 ("net: bcmgenet: Free skb after last Tx frag")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index a205a9ff9e17..ccb325cf03b5 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -1203,7 +1203,7 @@ static struct enet_cb *bcmgenet_get_txcb(struct bcmgenet_priv *priv,
 /* Simple helper to free a control block's resources */
 static void bcmgenet_free_cb(struct enet_cb *cb)
 {
-	dev_kfree_skb_any(cb->skb);
+	dev_consume_skb_any(cb->skb);
 	cb->skb = NULL;
 	dma_unmap_addr_set(cb, dma_addr, 0);
 }
@@ -1868,7 +1868,7 @@ static int bcmgenet_alloc_rx_buffers(struct bcmgenet_priv *priv,
 		cb = ring->cbs + i;
 		skb = bcmgenet_rx_refill(priv, cb);
 		if (skb)
-			dev_kfree_skb_any(skb);
+			dev_consume_skb_any(skb);
 		if (!cb->skb)
 			return -ENOMEM;
 	}
-- 
2.13.5


From bb6419d8c193e56ca2c16e69121d5e104131d74f Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 24 Aug 2017 16:01:13 -0700
Subject: [PATCH 13/43] net: systemport: Free DMA coherent descriptors on
 errors

[ Upstream commit c2062ee3d9615828109ffe8089fbf69bed394d05 ]

In case bcm_sysport_init_tx_ring() is not able to allocate ring->cbs, we
would return with an error, and call bcm_sysport_fini_tx_ring() and it
would see that ring->cbs is NULL and do nothing. This would leak the
coherent DMA descriptor area, so we need to free it on error before
returning.

Reported-by: Eric Dumazet <edumazet@gmail.com>
Fixes: 80105befdb4b ("net: systemport: add Broadcom SYSTEMPORT Ethernet MAC driver")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bcmsysport.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index a2c8086c19ca..f328b3d86c13 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -1342,6 +1342,8 @@ static int bcm_sysport_init_tx_ring(struct bcm_sysport_priv *priv,
 
 	ring->cbs = kcalloc(size, sizeof(struct bcm_sysport_cb), GFP_KERNEL);
 	if (!ring->cbs) {
+		dma_free_coherent(kdev, sizeof(struct dma_desc),
+				  ring->desc_cpu, ring->desc_dma);
 		netif_err(priv, hw, priv->netdev, "CB allocation failed\n");
 		return -ENOMEM;
 	}
-- 
2.13.5


From c32212c38bd3a95686d892d987d4fdb8c0ab5336 Mon Sep 17 00:00:00 2001
From: stephen hemminger <stephen@networkplumber.org>
Date: Thu, 24 Aug 2017 16:49:16 -0700
Subject: [PATCH 14/43] netvsc: fix deadlock betwen link status and removal

[ Upstream commit 9b4e946ce14e20d7addbfb7d9139e604f9fda107 ]

There is a deadlock possible when canceling the link status
delayed work queue. The removal process is run with RTNL held,
and the link status callback is acquring RTNL.

Resolve the issue by using trylock and rescheduling.
If cancel is in process, that block it from happening.

Fixes: 122a5f6410f4 ("staging: hv: use delayed_work for netvsc_send_garp()")
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/netvsc_drv.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 643c539a08ba..39293638d18e 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -1270,7 +1270,12 @@ static void netvsc_link_change(struct work_struct *w)
 	bool notify = false, reschedule = false;
 	unsigned long flags, next_reconfig, delay;
 
-	rtnl_lock();
+	/* if changes are happening, comeback later */
+	if (!rtnl_trylock()) {
+		schedule_delayed_work(&ndev_ctx->dwork, LINKCHANGE_INT);
+		return;
+	}
+
 	net_device = rtnl_dereference(ndev_ctx->nvdev);
 	if (!net_device)
 		goto out_unlock;
-- 
2.13.5


From 0cadc2e2b44fc7543a7833ab286951cbdb237a2d Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 25 Aug 2017 14:31:01 +0200
Subject: [PATCH 15/43] udp6: set rx_dst_cookie on rx_dst updates

[ Upstream commit 64f0f5d18a47c703c85576375cc010e83dac6a48 ]

Currently, in the udp6 code, the dst cookie is not initialized/updated
concurrently with the RX dst used by early demux.

As a result, the dst_check() in the early_demux path always fails,
the rx dst cache is always invalidated, and we can't really
leverage significant gain from the demux lookup.

Fix it adding udp6 specific variant of sk_rx_dst_set() and use it
to set the dst cookie when the dst entry is really changed.

The issue is there since the introduction of early demux for ipv6.

Fixes: 5425077d73e0 ("net: ipv6: Add early demux handler for UDP unicast")
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/udp.h |  2 +-
 net/ipv4/udp.c    |  3 ++-
 net/ipv6/udp.c    | 11 ++++++++++-
 3 files changed, 13 insertions(+), 3 deletions(-)

diff --git a/include/net/udp.h b/include/net/udp.h
index 1933442cf1a6..a1bc3e7934d6 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -265,7 +265,7 @@ static inline struct sk_buff *skb_recv_udp(struct sock *sk, unsigned int flags,
 }
 
 void udp_v4_early_demux(struct sk_buff *skb);
-void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst);
+bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst);
 int udp_get_port(struct sock *sk, unsigned short snum,
 		 int (*saddr_cmp)(const struct sock *,
 				  const struct sock *));
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index c991b97cbb28..2a7bff749764 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1762,13 +1762,14 @@ static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 /* For TCP sockets, sk_rx_dst is protected by socket lock
  * For UDP, we use xchg() to guard against concurrent changes.
  */
-void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
+bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
 {
 	struct dst_entry *old;
 
 	dst_hold(dst);
 	old = xchg(&sk->sk_rx_dst, dst);
 	dst_release(old);
+	return old != dst;
 }
 
 /*
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 592270c310f4..5c7b2a94e358 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -752,6 +752,15 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
 	return 0;
 }
 
+static void udp6_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
+{
+	if (udp_sk_rx_dst_set(sk, dst)) {
+		const struct rt6_info *rt = (const struct rt6_info *)dst;
+
+		inet6_sk(sk)->rx_dst_cookie = rt6_get_cookie(rt);
+	}
+}
+
 int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 		   int proto)
 {
@@ -801,7 +810,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 		int ret;
 
 		if (unlikely(sk->sk_rx_dst != dst))
-			udp_sk_rx_dst_set(sk, dst);
+			udp6_sk_rx_dst_set(sk, dst);
 
 		ret = udpv6_queue_rcv_skb(sk, skb);
 		sock_put(sk);
-- 
2.13.5


From 2ae184f9e2b9ff128440917d9272897f7068fcdd Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@free-electrons.com>
Date: Fri, 25 Aug 2017 16:14:17 +0200
Subject: [PATCH 16/43] net: mvpp2: fix the mac address used when using PPv2.2

[ Upstream commit 4c22868264516fe0c42817a87f37efb44254e7a9 ]

The mac address is only retrieved from h/w when using PPv2.1. Otherwise
the variable holding it is still checked and used if it contains a valid
value. As the variable isn't initialized to an invalid mac address
value, we end up with random mac addresses which can be the same for all
the ports handled by this PPv2 driver.

Fixes this by initializing the h/w mac address variable to {0}, which is
an invalid mac address value. This way the random assignation fallback
is called and all ports end up with their own addresses.

Signed-off-by: Antoine Tenart <antoine.tenart@free-electrons.com>
Fixes: 2697582144dd ("net: mvpp2: handle misc PPv2.1/PPv2.2 differences")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c
index 33c901622ed5..2ad48150b826 100644
--- a/drivers/net/ethernet/marvell/mvpp2.c
+++ b/drivers/net/ethernet/marvell/mvpp2.c
@@ -6465,7 +6465,7 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 	struct resource *res;
 	const char *dt_mac_addr;
 	const char *mac_from;
-	char hw_mac_addr[ETH_ALEN];
+	char hw_mac_addr[ETH_ALEN] = {0};
 	u32 id;
 	int features;
 	int phy_mode;
-- 
2.13.5


From ed5a65f276bab41753679fc52d574b63bc333ed4 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Fri, 25 Aug 2017 22:48:48 +0200
Subject: [PATCH 17/43] cxgb4: Fix stack out-of-bounds read due to wrong size
 to t4_record_mbox()

[ Upstream commit 0f3086868e8889a823a6e0f3d299102aa895d947 ]

Passing commands for logging to t4_record_mbox() with size
MBOX_LEN, when the actual command size is actually smaller,
causes out-of-bounds stack accesses in t4_record_mbox() while
copying command words here:

	for (i = 0; i < size / 8; i++)
		entry->cmd[i] = be64_to_cpu(cmd[i]);

Up to 48 bytes from the stack are then leaked to debugfs.

This happens whenever we send (and log) commands described by
structs fw_sched_cmd (32 bytes leaked), fw_vi_rxmode_cmd (48),
fw_hello_cmd (48), fw_bye_cmd (48), fw_initialize_cmd (48),
fw_reset_cmd (48), fw_pfvf_cmd (32), fw_eq_eth_cmd (16),
fw_eq_ctrl_cmd (32), fw_eq_ofld_cmd (32), fw_acl_mac_cmd(16),
fw_rss_glb_config_cmd(32), fw_rss_vi_config_cmd(32),
fw_devlog_cmd(32), fw_vi_enable_cmd(48), fw_port_cmd(32),
fw_sched_cmd(32), fw_devlog_cmd(32).

The cxgb4vf driver got this right instead.

When we call t4_record_mbox() to log a command reply, a MBOX_LEN
size can be used though, as get_mbox_rpl() will fill cmd_rpl up
completely.

Fixes: 7f080c3f2ff0 ("cxgb4: Add support to enable logging of firmware mailbox commands")
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/t4_hw.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index 3a34aa629f7d..f5d7eee6d420 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -369,12 +369,12 @@ int t4_wr_mbox_meat_timeout(struct adapter *adap, int mbox, const void *cmd,
 		list_del(&entry.list);
 		spin_unlock(&adap->mbox_lock);
 		ret = (v == MBOX_OWNER_FW) ? -EBUSY : -ETIMEDOUT;
-		t4_record_mbox(adap, cmd, MBOX_LEN, access, ret);
+		t4_record_mbox(adap, cmd, size, access, ret);
 		return ret;
 	}
 
 	/* Copy in the new mailbox command and send it on its way ... */
-	t4_record_mbox(adap, cmd, MBOX_LEN, access, 0);
+	t4_record_mbox(adap, cmd, size, access, 0);
 	for (i = 0; i < size; i += 8)
 		t4_write_reg64(adap, data_reg + i, be64_to_cpu(*p++));
 
@@ -426,7 +426,7 @@ int t4_wr_mbox_meat_timeout(struct adapter *adap, int mbox, const void *cmd,
 	}
 
 	ret = (pcie_fw & PCIE_FW_ERR_F) ? -ENXIO : -ETIMEDOUT;
-	t4_record_mbox(adap, cmd, MBOX_LEN, access, ret);
+	t4_record_mbox(adap, cmd, size, access, ret);
 	dev_err(adap->pdev_dev, "command %#x in mailbox %d timed out\n",
 		*(const u8 *)cmd, mbox);
 	t4_report_fw_error(adap);
-- 
2.13.5


From 9594c06c11ea73b8467a78fde66750b8ecad092f Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sat, 26 Aug 2017 20:10:10 +0800
Subject: [PATCH 18/43] ipv6: set dst.obsolete when a cached route has expired

[ Upstream commit 1e2ea8ad37be25a7cdcc974945935829d534d5d3 ]

Now it doesn't check for the cached route expiration in ipv6's
dst_ops->check(), because it trusts dst_gc that would clean the
cached route up when it's expired.

The problem is in dst_gc, it would clean the cached route only
when it's refcount is 1. If some other module (like xfrm) keeps
holding it and the module only release it when dst_ops->check()
fails.

But without checking for the cached route expiration, .check()
may always return true. Meanwhile, without releasing the cached
route, dst_gc couldn't del it. It will cause this cached route
never to expire.

This patch is to set dst.obsolete with DST_OBSOLETE_KILL in .gc
when it's expired, and check obsolete != DST_OBSOLETE_FORCE_CHK
in .check.

Note that this is even needed when ipv6 dst_gc timer is removed
one day. It would set dst.obsolete in .redirect and .update_pmtu
instead, and check for cached route expiration when getting it,
just like what ipv4 route does.

Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_fib.c | 4 +++-
 net/ipv6/route.c   | 3 ++-
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 846648ea3bcc..76cdaa9d4a51 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1790,8 +1790,10 @@ static int fib6_age(struct rt6_info *rt, void *arg)
 		}
 		gc_args->more++;
 	} else if (rt->rt6i_flags & RTF_CACHE) {
+		if (time_after_eq(now, rt->dst.lastuse + gc_args->timeout))
+			rt->dst.obsolete = DST_OBSOLETE_KILL;
 		if (atomic_read(&rt->dst.__refcnt) == 0 &&
-		    time_after_eq(now, rt->dst.lastuse + gc_args->timeout)) {
+		    rt->dst.obsolete == DST_OBSOLETE_KILL) {
 			RT6_TRACE("aging clone %p\n", rt);
 			return -1;
 		} else if (rt->rt6i_flags & RTF_GATEWAY) {
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index cd2fb18d9f8d..b75f79a07962 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -444,7 +444,8 @@ static bool rt6_check_expired(const struct rt6_info *rt)
 		if (time_after(jiffies, rt->dst.expires))
 			return true;
 	} else if (rt->dst.from) {
-		return rt6_check_expired((struct rt6_info *) rt->dst.from);
+		return rt->dst.obsolete != DST_OBSOLETE_FORCE_CHK ||
+		       rt6_check_expired((struct rt6_info *)rt->dst.from);
 	}
 	return false;
 }
-- 
2.13.5


From 1c17cf40c7cbcbd7e5bfe30172cb8a43bf0f5e64 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 28 Aug 2017 10:45:01 +0800
Subject: [PATCH 19/43] ipv6: do not set sk_destruct in IPV6_ADDRFORM sockopt

[ Upstream commit e8d411d2980723b8f8ba8e4dd78b694c5fd9ea3e ]

ChunYu found a kernel warn_on during syzkaller fuzzing:

[40226.038539] WARNING: CPU: 5 PID: 23720 at net/ipv4/af_inet.c:152 inet_sock_destruct+0x78d/0x9a0
[40226.144849] Call Trace:
[40226.147590]  <IRQ>
[40226.149859]  dump_stack+0xe2/0x186
[40226.176546]  __warn+0x1a4/0x1e0
[40226.180066]  warn_slowpath_null+0x31/0x40
[40226.184555]  inet_sock_destruct+0x78d/0x9a0
[40226.246355]  __sk_destruct+0xfa/0x8c0
[40226.290612]  rcu_process_callbacks+0xaa0/0x18a0
[40226.336816]  __do_softirq+0x241/0x75e
[40226.367758]  irq_exit+0x1f6/0x220
[40226.371458]  smp_apic_timer_interrupt+0x7b/0xa0
[40226.376507]  apic_timer_interrupt+0x93/0xa0

The warn_on happned when sk->sk_rmem_alloc wasn't 0 in inet_sock_destruct.
As after commit f970bd9e3a06 ("udp: implement memory accounting helpers"),
udp has changed to use udp_destruct_sock as sk_destruct where it would
udp_rmem_release all rmem.

But IPV6_ADDRFORM sockopt sets sk_destruct with inet_sock_destruct after
changing family to PF_INET. If rmem is not 0 at that time, and there is
no place to release rmem before calling inet_sock_destruct, the warn_on
will be triggered.

This patch is to fix it by not setting sk_destruct in IPV6_ADDRFORM sockopt
any more. As IPV6_ADDRFORM sockopt only works for tcp and udp. TCP sock has
already set it's sk_destruct with inet_sock_destruct and UDP has set with
udp_destruct_sock since they're created.

Fixes: f970bd9e3a06 ("udp: implement memory accounting helpers")
Reported-by: ChunYu Wang <chunwang@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ipv6_sockglue.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index a531ba032b85..f78478fdbfb9 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -242,7 +242,6 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 			pktopt = xchg(&np->pktoptions, NULL);
 			kfree_skb(pktopt);
 
-			sk->sk_destruct = inet_sock_destruct;
 			/*
 			 * ... and add it to the refcnt debug socks count
 			 * in the new family. -acme
-- 
2.13.5


From 0c92402cab3219aeb061a8b5a8518f6820236a84 Mon Sep 17 00:00:00 2001
From: Benjamin Poirier <bpoirier@suse.com>
Date: Mon, 28 Aug 2017 14:29:41 -0400
Subject: [PATCH 20/43] packet: Don't write vnet header beyond end of buffer

[ Upstream commit edbd58be15a957f6a760c4a514cd475217eb97fd ]

... which may happen with certain values of tp_reserve and maclen.

Fixes: 58d19b19cd99 ("packet: vnet_hdr support for tpacket_rcv")
Signed-off-by: Benjamin Poirier <bpoirier@suse.com>
Cc: Willem de Bruijn <willemb@google.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index aa2d4000bafc..2b31a69d42a5 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2192,6 +2192,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	struct timespec ts;
 	__u32 ts_status;
 	bool is_drop_n_account = false;
+	bool do_vnet = false;
 
 	/* struct tpacket{2,3}_hdr is aligned to a multiple of TPACKET_ALIGNMENT.
 	 * We may add members to them until current aligned size without forcing
@@ -2242,8 +2243,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 		netoff = TPACKET_ALIGN(po->tp_hdrlen +
 				       (maclen < 16 ? 16 : maclen)) +
 				       po->tp_reserve;
-		if (po->has_vnet_hdr)
+		if (po->has_vnet_hdr) {
 			netoff += sizeof(struct virtio_net_hdr);
+			do_vnet = true;
+		}
 		macoff = netoff - maclen;
 	}
 	if (po->tp_version <= TPACKET_V2) {
@@ -2260,8 +2263,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 					skb_set_owner_r(copy_skb, sk);
 			}
 			snaplen = po->rx_ring.frame_size - macoff;
-			if ((int)snaplen < 0)
+			if ((int)snaplen < 0) {
 				snaplen = 0;
+				do_vnet = false;
+			}
 		}
 	} else if (unlikely(macoff + snaplen >
 			    GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len)) {
@@ -2274,6 +2279,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 		if (unlikely((int)snaplen < 0)) {
 			snaplen = 0;
 			macoff = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len;
+			do_vnet = false;
 		}
 	}
 	spin_lock(&sk->sk_receive_queue.lock);
@@ -2299,7 +2305,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	}
 	spin_unlock(&sk->sk_receive_queue.lock);
 
-	if (po->has_vnet_hdr) {
+	if (do_vnet) {
 		if (virtio_net_hdr_from_skb(skb, h.raw + macoff -
 					    sizeof(struct virtio_net_hdr),
 					    vio_le(), true)) {
-- 
2.13.5


From 3d1c8e1b361fee4fca9a38dd6b70c39e136f3e9f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 30 Aug 2017 09:29:31 -0700
Subject: [PATCH 21/43] kcm: do not attach PF_KCM sockets to avoid deadlock

[ Upstream commit 351050ecd6523374b370341cc29fe61e2201556b ]

syzkaller had no problem to trigger a deadlock, attaching a KCM socket
to another one (or itself). (original syzkaller report was a very
confusing lockdep splat during a sendmsg())

It seems KCM claims to only support TCP, but no enforcement is done,
so we might need to add additional checks.

Fixes: ab7ac4eb9832 ("kcm: Kernel Connection Multiplexor module")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Acked-by: Tom Herbert <tom@quantonium.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/kcm/kcmsock.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index deca20fb2ce2..0ddcb209bea6 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -1383,6 +1383,10 @@ static int kcm_attach(struct socket *sock, struct socket *csock,
 	if (!csk)
 		return -EINVAL;
 
+	/* We must prevent loops or risk deadlock ! */
+	if (csk->sk_family == PF_KCM)
+		return -EOPNOTSUPP;
+
 	psock = kmem_cache_zalloc(kcm_psockp, GFP_KERNEL);
 	if (!psock)
 		return -ENOMEM;
-- 
2.13.5


From 63bfe0edc3f9120d1a19b0f30986f043a9a2b6b5 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 30 Aug 2017 12:39:33 -0700
Subject: [PATCH 22/43] net: dsa: bcm_sf2: Fix number of CFP entries for
 BCM7278

[ Upstream commit df191632f814357ee4d646421662d866028b569d ]

BCM7278 has only 128 entries while BCM7445 has the full 256 entries set,
fix that.

Fixes: 7318166cacad ("net: dsa: bcm_sf2: Add support for ethtool::rxnfc")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2.c     | 4 ++++
 drivers/net/dsa/bcm_sf2.h     | 1 +
 drivers/net/dsa/bcm_sf2_cfp.c | 8 ++++----
 3 files changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 2be963252ca5..e0e14f7cd208 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -1055,6 +1055,7 @@ struct bcm_sf2_of_data {
 	u32 type;
 	const u16 *reg_offsets;
 	unsigned int core_reg_align;
+	unsigned int num_cfp_rules;
 };
 
 /* Register offsets for the SWITCH_REG_* block */
@@ -1078,6 +1079,7 @@ static const struct bcm_sf2_of_data bcm_sf2_7445_data = {
 	.type		= BCM7445_DEVICE_ID,
 	.core_reg_align	= 0,
 	.reg_offsets	= bcm_sf2_7445_reg_offsets,
+	.num_cfp_rules	= 256,
 };
 
 static const u16 bcm_sf2_7278_reg_offsets[] = {
@@ -1100,6 +1102,7 @@ static const struct bcm_sf2_of_data bcm_sf2_7278_data = {
 	.type		= BCM7278_DEVICE_ID,
 	.core_reg_align	= 1,
 	.reg_offsets	= bcm_sf2_7278_reg_offsets,
+	.num_cfp_rules	= 128,
 };
 
 static const struct of_device_id bcm_sf2_of_match[] = {
@@ -1156,6 +1159,7 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev)
 	priv->type = data->type;
 	priv->reg_offsets = data->reg_offsets;
 	priv->core_reg_align = data->core_reg_align;
+	priv->num_cfp_rules = data->num_cfp_rules;
 
 	/* Auto-detection using standard registers will not work, so
 	 * provide an indication of what kind of device we are for
diff --git a/drivers/net/dsa/bcm_sf2.h b/drivers/net/dsa/bcm_sf2.h
index 7d3030e04f11..7f9125eef3df 100644
--- a/drivers/net/dsa/bcm_sf2.h
+++ b/drivers/net/dsa/bcm_sf2.h
@@ -72,6 +72,7 @@ struct bcm_sf2_priv {
 	u32 				type;
 	const u16			*reg_offsets;
 	unsigned int			core_reg_align;
+	unsigned int			num_cfp_rules;
 
 	/* spinlock protecting access to the indirect registers */
 	spinlock_t			indir_lock;
diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c
index 2fb32d67065f..8a1da7e67707 100644
--- a/drivers/net/dsa/bcm_sf2_cfp.c
+++ b/drivers/net/dsa/bcm_sf2_cfp.c
@@ -98,7 +98,7 @@ static inline void bcm_sf2_cfp_rule_addr_set(struct bcm_sf2_priv *priv,
 {
 	u32 reg;
 
-	WARN_ON(addr >= CFP_NUM_RULES);
+	WARN_ON(addr >= priv->num_cfp_rules);
 
 	reg = core_readl(priv, CORE_CFP_ACC);
 	reg &= ~(XCESS_ADDR_MASK << XCESS_ADDR_SHIFT);
@@ -109,7 +109,7 @@ static inline void bcm_sf2_cfp_rule_addr_set(struct bcm_sf2_priv *priv,
 static inline unsigned int bcm_sf2_cfp_rule_size(struct bcm_sf2_priv *priv)
 {
 	/* Entry #0 is reserved */
-	return CFP_NUM_RULES - 1;
+	return priv->num_cfp_rules - 1;
 }
 
 static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
@@ -523,7 +523,7 @@ static int bcm_sf2_cfp_rule_get_all(struct bcm_sf2_priv *priv,
 		if (!(reg & OP_STR_DONE))
 			break;
 
-	} while (index < CFP_NUM_RULES);
+	} while (index < priv->num_cfp_rules);
 
 	/* Put the TCAM size here */
 	nfc->data = bcm_sf2_cfp_rule_size(priv);
@@ -544,7 +544,7 @@ int bcm_sf2_get_rxnfc(struct dsa_switch *ds, int port,
 	case ETHTOOL_GRXCLSRLCNT:
 		/* Subtract the default, unusable rule */
 		nfc->rule_cnt = bitmap_weight(priv->cfp.used,
-					      CFP_NUM_RULES) - 1;
+					      priv->num_cfp_rules) - 1;
 		/* We support specifying rule locations */
 		nfc->data |= RX_CLS_LOC_SPECIAL;
 		break;
-- 
2.13.5


From 8f73d831c44fa9bfd8121535f93cd99f295abc15 Mon Sep 17 00:00:00 2001
From: Huy Nguyen <huyn@mellanox.com>
Date: Thu, 13 Jul 2017 13:45:11 -0500
Subject: [PATCH 23/43] net/mlx5e: Check for qos capability in dcbnl_initialize

[ Upstream commit 33c52b6718d2a6cb414440c98560818910d896dc ]

qos capability is the master capability bit that determines
if the DCBX is supported for the PCI function. If this bit is off,
driver cannot run any dcbx code.

Fixes: e207b7e99176 ("net/mlx5e: ConnectX-4 firmware support for DCBX")
Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index 2eb54d36e16e..810b51029c7f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -754,6 +754,9 @@ void mlx5e_dcbnl_initialize(struct mlx5e_priv *priv)
 {
 	struct mlx5e_dcbx *dcbx = &priv->dcbx;
 
+	if (!MLX5_CAP_GEN(priv->mdev, qos))
+		return;
+
 	if (MLX5_CAP_GEN(priv->mdev, dcbx))
 		mlx5e_dcbnl_query_dcbx_mode(priv, &dcbx->mode);
 
-- 
2.13.5


From cea70f64f13e96d0651cd6216366c87bbdd587ec Mon Sep 17 00:00:00 2001
From: Huy Nguyen <huyn@mellanox.com>
Date: Mon, 10 Jul 2017 14:00:23 -0500
Subject: [PATCH 24/43] net/mlx5e: Fix DCB_CAP_ATTR_DCBX capability for DCBNL
 getcap.

[ Upstream commit 9e10bf1d349787f373484d835efe2dbb5f9c5614 ]

Current code doesn't report DCB_CAP_DCBX_HOST capability when query
through getcap. User space lldptool expects capability to have HOST mode
set when it wants to configure DCBX CEE mode. In absence of HOST mode
capability, lldptool fails to switch to CEE mode.

This fix returns DCB_CAP_DCBX_HOST capability when port's DCBX
controlled mode is under software control.

Fixes: 3a6a931dfb8e ("net/mlx5e: Support DCBX CEE API")
Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |  1 +
 drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c | 21 ++++++++++++---------
 2 files changed, 13 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 3b39dbd97e57..5a1b85c18e60 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -258,6 +258,7 @@ struct mlx5e_dcbx {
 
 	/* The only setting that cannot be read from FW */
 	u8                         tc_tsa[IEEE_8021QAZ_MAX_TCS];
+	u8                         cap;
 };
 #endif
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index 810b51029c7f..c1d384fca4dc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -288,13 +288,8 @@ static int mlx5e_dcbnl_ieee_setpfc(struct net_device *dev,
 static u8 mlx5e_dcbnl_getdcbx(struct net_device *dev)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	struct mlx5e_dcbx *dcbx = &priv->dcbx;
-	u8 mode = DCB_CAP_DCBX_VER_IEEE | DCB_CAP_DCBX_VER_CEE;
-
-	if (dcbx->mode == MLX5E_DCBX_PARAM_VER_OPER_HOST)
-		mode |= DCB_CAP_DCBX_HOST;
 
-	return mode;
+	return priv->dcbx.cap;
 }
 
 static u8 mlx5e_dcbnl_setdcbx(struct net_device *dev, u8 mode)
@@ -312,6 +307,7 @@ static u8 mlx5e_dcbnl_setdcbx(struct net_device *dev, u8 mode)
 		/* set dcbx to fw controlled */
 		if (!mlx5e_dcbnl_set_dcbx_mode(priv, MLX5E_DCBX_PARAM_VER_OPER_AUTO)) {
 			dcbx->mode = MLX5E_DCBX_PARAM_VER_OPER_AUTO;
+			dcbx->cap &= ~DCB_CAP_DCBX_HOST;
 			return 0;
 		}
 
@@ -324,6 +320,8 @@ static u8 mlx5e_dcbnl_setdcbx(struct net_device *dev, u8 mode)
 	if (mlx5e_dcbnl_switch_to_host_mode(netdev_priv(dev)))
 		return 1;
 
+	dcbx->cap = mode;
+
 	return 0;
 }
 
@@ -628,9 +626,9 @@ static u8 mlx5e_dcbnl_getcap(struct net_device *netdev,
 		*cap = false;
 		break;
 	case DCB_CAP_ATTR_DCBX:
-		*cap = (DCB_CAP_DCBX_LLD_MANAGED |
-			DCB_CAP_DCBX_VER_CEE |
-			DCB_CAP_DCBX_STATIC);
+		*cap = priv->dcbx.cap |
+		       DCB_CAP_DCBX_VER_CEE |
+		       DCB_CAP_DCBX_VER_IEEE;
 		break;
 	default:
 		*cap = 0;
@@ -760,5 +758,10 @@ void mlx5e_dcbnl_initialize(struct mlx5e_priv *priv)
 	if (MLX5_CAP_GEN(priv->mdev, dcbx))
 		mlx5e_dcbnl_query_dcbx_mode(priv, &dcbx->mode);
 
+	priv->dcbx.cap = DCB_CAP_DCBX_VER_CEE |
+			 DCB_CAP_DCBX_VER_IEEE;
+	if (priv->dcbx.mode == MLX5E_DCBX_PARAM_VER_OPER_HOST)
+		priv->dcbx.cap |= DCB_CAP_DCBX_HOST;
+
 	mlx5e_ets_init(priv);
 }
-- 
2.13.5


From 8fa3dd11584c6209f11a924d0c7acb8726594bf8 Mon Sep 17 00:00:00 2001
From: Noa Osherovich <noaos@mellanox.com>
Date: Sun, 30 Jul 2017 13:55:48 +0300
Subject: [PATCH 25/43] net/mlx5: Fix arm SRQ command for ISSI version 0

[ Upstream commit 672d0880b7798a917bcc622308f25a0fbb991dab ]

Support for ISSI version 0 was recently broken as the arm_srq_cmd
command, which is used only for ISSI version 0, was given the opcode
for ISSI version 1 instead of ISSI version 0.

Change arm_srq_cmd to use the correct command opcode for ISSI version
0.

Fixes: af1ba291c5e4 ('{net, IB}/mlx5: Refactor internal SRQ API')
Signed-off-by: Noa Osherovich <noaos@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/srq.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/srq.c b/drivers/net/ethernet/mellanox/mlx5/core/srq.c
index 3099630015d7..75a14547ee39 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/srq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/srq.c
@@ -201,13 +201,13 @@ static int destroy_srq_cmd(struct mlx5_core_dev *dev,
 static int arm_srq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
 		       u16 lwm, int is_srq)
 {
-	/* arm_srq structs missing using identical xrc ones */
-	u32 srq_in[MLX5_ST_SZ_DW(arm_xrc_srq_in)] = {0};
-	u32 srq_out[MLX5_ST_SZ_DW(arm_xrc_srq_out)] = {0};
+	u32 srq_in[MLX5_ST_SZ_DW(arm_rq_in)] = {0};
+	u32 srq_out[MLX5_ST_SZ_DW(arm_rq_out)] = {0};
 
-	MLX5_SET(arm_xrc_srq_in, srq_in, opcode,   MLX5_CMD_OP_ARM_XRC_SRQ);
-	MLX5_SET(arm_xrc_srq_in, srq_in, xrc_srqn, srq->srqn);
-	MLX5_SET(arm_xrc_srq_in, srq_in, lwm,      lwm);
+	MLX5_SET(arm_rq_in, srq_in, opcode, MLX5_CMD_OP_ARM_RQ);
+	MLX5_SET(arm_rq_in, srq_in, op_mod, MLX5_ARM_RQ_IN_OP_MOD_SRQ);
+	MLX5_SET(arm_rq_in, srq_in, srq_number, srq->srqn);
+	MLX5_SET(arm_rq_in, srq_in, lwm,      lwm);
 
 	return  mlx5_cmd_exec(dev, srq_in, sizeof(srq_in),
 			      srq_out, sizeof(srq_out));
-- 
2.13.5


From 58ebfa7f4453f867c69d7f519866ab6343a32cc7 Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Wed, 16 Aug 2017 14:37:11 +0300
Subject: [PATCH 26/43] net/mlx5e: Fix dangling page pointer on DMA mapping
 error

[ Upstream commit 0556ce72ab16156af6c94cdc7964e4310acc97c0 ]

Function mlx5e_dealloc_rx_wqe is using page pointer value as an
indication to valid DMA mapping. In case that the mapping failed, we
released the page but kept the dangling pointer. Store the page pointer
only after the DMA mapping passed to avoid invalid page DMA unmap.

Fixes: bc77b240b3c5 ("net/mlx5e: Add fragmented memory support for RX multi packet WQE")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 66b5fec15313..f70029d5eea1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -216,13 +216,13 @@ static inline int mlx5e_page_alloc_mapped(struct mlx5e_rq *rq,
 	if (unlikely(!page))
 		return -ENOMEM;
 
-	dma_info->page = page;
 	dma_info->addr = dma_map_page(rq->pdev, page, 0,
 				      RQ_PAGE_SIZE(rq), rq->buff.map_dir);
 	if (unlikely(dma_mapping_error(rq->pdev, dma_info->addr))) {
 		put_page(page);
 		return -ENOMEM;
 	}
+	dma_info->page = page;
 
 	return 0;
 }
-- 
2.13.5


From f929fc4745a7f40d9aa413c4e6897d98a8e37706 Mon Sep 17 00:00:00 2001
From: Inbar Karmy <inbark@mellanox.com>
Date: Mon, 14 Aug 2017 16:12:16 +0300
Subject: [PATCH 27/43] net/mlx5e: Don't override user RSS upon set channels

[ Upstream commit 5a8e12678c767ccf8bb16d6237569e4a707d655b ]

Currently, increasing the number of combined channels is changing
the RSS spread to use the new created channels.
Prevent the RSS spread change in case the user explicitly declare it,
to avoid overriding user configuration.

Tested:
when RSS default:

# ethtool -L ens8 combined 4
RSS spread will change and point to 4 channels.

# ethtool -X ens8 equal 4
# ethtool -L ens8 combined 6
RSS will not change after increasing the number of the channels.

Fixes: 8bf368620486 ('ethtool: ensure channel counts are within bounds during SCHANNELS')
Signed-off-by: Inbar Karmy <inbark@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 16486dff1493..a60f6f2fa4e4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -580,8 +580,10 @@ static int mlx5e_set_channels(struct net_device *dev,
 
 	new_channels.params = priv->channels.params;
 	new_channels.params.num_channels = count;
-	mlx5e_build_default_indir_rqt(priv->mdev, new_channels.params.indirection_rqt,
-				      MLX5E_INDIR_RQT_SIZE, count);
+	if (!netif_is_rxfh_configured(priv->netdev))
+		mlx5e_build_default_indir_rqt(priv->mdev,
+					      new_channels.params.indirection_rqt,
+					      MLX5E_INDIR_RQT_SIZE, count);
 
 	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
 		priv->channels.params = new_channels.params;
-- 
2.13.5


From a8c63c29ec8d79f28442bbff66b33addade999b1 Mon Sep 17 00:00:00 2001
From: Paul Blakey <paulb@mellanox.com>
Date: Tue, 22 Aug 2017 13:51:56 +0300
Subject: [PATCH 28/43] net/mlx5e: Properly resolve TC offloaded ipv6 vxlan
 tunnel source address

[ Upstream commit 08820528c9d3ff0d0eda047d7ef5ecac2da1ef6c ]

Currently if vxlan tunnel ipv6 src isn't supplied the driver fails to
resolve it as part of the route lookup. The resulting encap header
is left with a zeroed out ipv6 src address so the packets are sent
with this src ip.

Use an appropriate route lookup API that also resolves the source
ipv6 address if it's not supplied.

Fixes: ce99f6b97fcd ('net/mlx5e: Support SRIOV TC encapsulation offloads for IPv6 tunnels')
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 9df9fc0d26f5..558a8841c9a5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1262,12 +1262,10 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	int ret;
 
-	dst = ip6_route_output(dev_net(mirred_dev), NULL, fl6);
-	ret = dst->error;
-	if (ret) {
-		dst_release(dst);
+	ret = ipv6_stub->ipv6_dst_lookup(dev_net(mirred_dev), NULL, &dst,
+					 fl6);
+	if (ret < 0)
 		return ret;
-	}
 
 	*out_ttl = ip6_dst_hoplimit(dst);
 
-- 
2.13.5


From 5bf991dcaeca89c83a149a5e444ff866a8f119d9 Mon Sep 17 00:00:00 2001
From: Shahar Klein <shahark@mellanox.com>
Date: Tue, 1 Aug 2017 15:29:55 +0300
Subject: [PATCH 29/43] net/mlx5: E-Switch, Unload the representors in the
 correct order

[ Upstream commit 191220396db840822fc818edf03c49f0c02eb237 ]

When changing from switchdev to legacy mode, all the representor port
devices (uplink nic and reps) are cleaned up. Part of this cleaning
process is removing the neigh entries and the hash table containing them.
However, a representor neigh entry might be linked to the uplink port
hash table and if the uplink nic is cleaned first the cleaning of the
representor will end up in null deref.
Fix that by unloading the representors in the opposite order of load.

Fixes: cb67b832921c ("net/mlx5e: Introduce SRIOV VF representors")
Signed-off-by: Shahar Klein <shahark@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index a53e982a6863..f28750bb56d6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -818,7 +818,7 @@ void esw_offloads_cleanup(struct mlx5_eswitch *esw, int nvports)
 	struct mlx5_eswitch_rep *rep;
 	int vport;
 
-	for (vport = 0; vport < nvports; vport++) {
+	for (vport = nvports - 1; vport >= 0; vport--) {
 		rep = &esw->offloads.vport_reps[vport];
 		if (!rep->valid)
 			continue;
-- 
2.13.5


From 0726992c1c1055e9c2c47cdfbe97a13f501c9aa7 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Tue, 8 Aug 2017 15:56:37 +0300
Subject: [PATCH 30/43] net/mlx5e: Fix inline header size for small packets

[ Upstream commit 6aace17e64f4aa1c49802c46bd10688968b3787f ]

Fix inline header size, make sure it is not greater than skb len.
This bug effects small packets, for example L2 packets with size < 18.

Fixes: ae76715d153e ("net/mlx5e: Check the minimum inline header mode before xmit")
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index ab3bb026ff9e..091f03f0d8f0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -127,10 +127,10 @@ static inline int mlx5e_skb_l3_header_offset(struct sk_buff *skb)
 		return mlx5e_skb_l2_header_offset(skb);
 }
 
-static inline unsigned int mlx5e_calc_min_inline(enum mlx5_inline_modes mode,
-						 struct sk_buff *skb)
+static inline u16 mlx5e_calc_min_inline(enum mlx5_inline_modes mode,
+					struct sk_buff *skb)
 {
-	int hlen;
+	u16 hlen;
 
 	switch (mode) {
 	case MLX5_INLINE_MODE_NONE:
@@ -139,19 +139,22 @@ static inline unsigned int mlx5e_calc_min_inline(enum mlx5_inline_modes mode,
 		hlen = eth_get_headlen(skb->data, skb_headlen(skb));
 		if (hlen == ETH_HLEN && !skb_vlan_tag_present(skb))
 			hlen += VLAN_HLEN;
-		return hlen;
+		break;
 	case MLX5_INLINE_MODE_IP:
 		/* When transport header is set to zero, it means no transport
 		 * header. When transport header is set to 0xff's, it means
 		 * transport header wasn't set.
 		 */
-		if (skb_transport_offset(skb))
-			return mlx5e_skb_l3_header_offset(skb);
+		if (skb_transport_offset(skb)) {
+			hlen = mlx5e_skb_l3_header_offset(skb);
+			break;
+		}
 		/* fall through */
 	case MLX5_INLINE_MODE_L2:
 	default:
-		return mlx5e_skb_l2_header_offset(skb);
+		hlen = mlx5e_skb_l2_header_offset(skb);
 	}
+	return min_t(u16, hlen, skb->len);
 }
 
 static inline void mlx5e_tx_skb_pull_inline(unsigned char **skb_data,
-- 
2.13.5


From 68d76d436a3079d9e5874f74c81862cfe736b4a1 Mon Sep 17 00:00:00 2001
From: Tal Gilboa <talgi@mellanox.com>
Date: Mon, 28 Aug 2017 18:45:08 +0300
Subject: [PATCH 31/43] net/mlx5e: Fix CQ moderation mode not set properly

[ Upstream commit 1213ad28f9595a08e3877248bbba1a25c40225d6 ]

cq_period_mode assignment was mistakenly removed so it was always set to "0",
which is EQE based moderation, regardless of the device CAPs and
requested value in ethtool.

Fixes: 6a9764efb255 ("net/mlx5e: Isolate open_channels from priv->params")
Signed-off-by: Tal Gilboa <talgi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 072aa8a13a0a..00b51252b803 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1936,6 +1936,7 @@ static void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv,
 	}
 
 	mlx5e_build_common_cq_param(priv, param);
+	param->cq_period_mode = params->rx_cq_period_mode;
 }
 
 static void mlx5e_build_tx_cq_param(struct mlx5e_priv *priv,
-- 
2.13.5


From f67e9ef59ed1f45942bfe2f2cbb5a78f6ab41707 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 30 Aug 2017 17:49:29 -0700
Subject: [PATCH 32/43] Revert "net: phy: Correctly process PHY_HALTED in
 phy_stop_machine()"

[ Upstream commit ebc8254aeae34226d0bc8fda309fd9790d4dccfe ]

This reverts commit 7ad813f208533cebfcc32d3d7474dc1677d1b09a ("net: phy:
Correctly process PHY_HALTED in phy_stop_machine()") because it is
creating the possibility for a NULL pointer dereference.

David Daney provide the following call trace and diagram of events:

When ndo_stop() is called we call:

 phy_disconnect()
    +---> phy_stop_interrupts() implies: phydev->irq = PHY_POLL;
    +---> phy_stop_machine()
    |      +---> phy_state_machine()
    |              +----> queue_delayed_work(): Work queued.
    +--->phy_detach() implies: phydev->attached_dev = NULL;

Now at a later time the queued work does:

 phy_state_machine()
    +---->netif_carrier_off(phydev->attached_dev): Oh no! It is NULL:

 CPU 12 Unable to handle kernel paging request at virtual address
0000000000000048, epc == ffffffff80de37ec, ra == ffffffff80c7c
Oops[#1]:
CPU: 12 PID: 1502 Comm: kworker/12:1 Not tainted 4.9.43-Cavium-Octeon+ #1
Workqueue: events_power_efficient phy_state_machine
task: 80000004021ed100 task.stack: 8000000409d70000
$ 0   : 0000000000000000 ffffffff84720060 0000000000000048 0000000000000004
$ 4   : 0000000000000000 0000000000000001 0000000000000004 0000000000000000
$ 8   : 0000000000000000 0000000000000000 00000000ffff98f3 0000000000000000
$12   : 8000000409d73fe0 0000000000009c00 ffffffff846547c8 000000000000af3b
$16   : 80000004096bab68 80000004096babd0 0000000000000000 80000004096ba800
$20   : 0000000000000000 0000000000000000 ffffffff81090000 0000000000000008
$24   : 0000000000000061 ffffffff808637b0
$28   : 8000000409d70000 8000000409d73cf0 80000000271bd300 ffffffff80c7804c
Hi    : 000000000000002a
Lo    : 000000000000003f
epc   : ffffffff80de37ec netif_carrier_off+0xc/0x58
ra    : ffffffff80c7804c phy_state_machine+0x48c/0x4f8
Status: 14009ce3        KX SX UX KERNEL EXL IE
Cause : 00800008 (ExcCode 02)
BadVA : 0000000000000048
PrId  : 000d9501 (Cavium Octeon III)
Modules linked in:
Process kworker/12:1 (pid: 1502, threadinfo=8000000409d70000,
task=80000004021ed100, tls=0000000000000000)
Stack : 8000000409a54000 80000004096bab68 80000000271bd300 80000000271c1e00
        0000000000000000 ffffffff808a1708 8000000409a54000 80000000271bd300
        80000000271bd320 8000000409a54030 ffffffff80ff0f00 0000000000000001
        ffffffff81090000 ffffffff808a1ac0 8000000402182080 ffffffff84650000
        8000000402182080 ffffffff84650000 ffffffff80ff0000 8000000409a54000
        ffffffff808a1970 0000000000000000 80000004099e8000 8000000402099240
        0000000000000000 ffffffff808a8598 0000000000000000 8000000408eeeb00
        8000000409a54000 00000000810a1d00 0000000000000000 8000000409d73de8
        8000000409d73de8 0000000000000088 000000000c009c00 8000000409d73e08
        8000000409d73e08 8000000402182080 ffffffff808a84d0 8000000402182080
        ...
Call Trace:
[<ffffffff80de37ec>] netif_carrier_off+0xc/0x58
[<ffffffff80c7804c>] phy_state_machine+0x48c/0x4f8
[<ffffffff808a1708>] process_one_work+0x158/0x368
[<ffffffff808a1ac0>] worker_thread+0x150/0x4c0
[<ffffffff808a8598>] kthread+0xc8/0xe0
[<ffffffff808617f0>] ret_from_kernel_thread+0x14/0x1c

The original motivation for this change originated from Marc Gonzales
indicating that his network driver did not have its adjust_link callback
executing with phydev->link = 0 while he was expecting it.

PHYLIB has never made any such guarantees ever because phy_stop() merely just
tells the workqueue to move into PHY_HALTED state which will happen
asynchronously.

Reported-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reported-by: David Daney <ddaney.cavm@gmail.com>
Fixes: 7ad813f20853 ("net: phy: Correctly process PHY_HALTED in phy_stop_machine()")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index b30d9ceee8bc..eebb0e1c70ff 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -749,9 +749,6 @@ void phy_stop_machine(struct phy_device *phydev)
 	if (phydev->state > PHY_UP && phydev->state != PHY_HALTED)
 		phydev->state = PHY_UP;
 	mutex_unlock(&phydev->lock);
-
-	/* Now we can run the state machine synchronously */
-	phy_state_machine(&phydev->state_queue.work);
 }
 
 /**
-- 
2.13.5


From e3cd52be88a132b3a9172faaf6abd154afc87d62 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sun, 30 Jul 2017 19:36:05 +0200
Subject: [PATCH 33/43] net: fec: Allow reception of frames bigger than 1522
 bytes

[ Upstream commit fbbeefdd21049fcf9437c809da3828b210577f36 ]

The FEC Receive Control Register has a 14 bit field indicating the
longest frame that may be received. It is being set to 1522. Frames
longer than this are discarded, but counted as being in error.

When using DSA, frames from the switch has an additional header,
either 4 or 8 bytes if a Marvell switch is used. Thus a full MTU frame
of 1522 bytes received by the switch on a port becomes 1530 bytes when
passed to the host via the FEC interface.

Change the maximum receive size to 2048 - 64, where 64 is the maximum
rx_alignment applied on the receive buffer for AVB capable FEC
cores. Use this value also for the maximum receive buffer size. The
driver is already allocating a receive SKB of 2048 bytes, so this
change should not have any significant effects.

Tested on imx51, imx6, vf610.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_main.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index f7c8649fd28f..01084cd4a5c1 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -173,10 +173,12 @@ MODULE_PARM_DESC(macaddr, "FEC Ethernet MAC address");
 #endif /* CONFIG_M5272 */
 
 /* The FEC stores dest/src/type/vlan, data, and checksum for receive packets.
+ *
+ * 2048 byte skbufs are allocated. However, alignment requirements
+ * varies between FEC variants. Worst case is 64, so round down by 64.
  */
-#define PKT_MAXBUF_SIZE		1522
+#define PKT_MAXBUF_SIZE		(round_down(2048 - 64, 64))
 #define PKT_MINBUF_SIZE		64
-#define PKT_MAXBLR_SIZE		1536
 
 /* FEC receive acceleration */
 #define FEC_RACC_IPDIS		(1 << 1)
@@ -848,7 +850,7 @@ static void fec_enet_enable_ring(struct net_device *ndev)
 	for (i = 0; i < fep->num_rx_queues; i++) {
 		rxq = fep->rx_queue[i];
 		writel(rxq->bd.dma, fep->hwp + FEC_R_DES_START(i));
-		writel(PKT_MAXBLR_SIZE, fep->hwp + FEC_R_BUFF_SIZE(i));
+		writel(PKT_MAXBUF_SIZE, fep->hwp + FEC_R_BUFF_SIZE(i));
 
 		/* enable DMA1/2 */
 		if (i)
-- 
2.13.5


From 3e8af1dd212555f2ab9657a02b3db9c0ed06cd7d Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Fri, 1 Sep 2017 10:52:31 +0200
Subject: [PATCH 34/43] mlxsw: spectrum: Forbid linking to devices that have
 uppers

[ Upstream commit 25cc72a33835ed8a6f53180a822cadab855852ac ]

The mlxsw driver relies on NETDEV_CHANGEUPPER events to configure the
device in case a port is enslaved to a master netdev such as bridge or
bond.

Since the driver ignores events unrelated to its ports and their
uppers, it's possible to engineer situations in which the device's data
path differs from the kernel's.

One example to such a situation is when a port is enslaved to a bond
that is already enslaved to a bridge. When the bond was enslaved the
driver ignored the event - as the bond wasn't one of its uppers - and
therefore a bridge port instance isn't created in the device.

Until such configurations are supported forbid them by checking that the
upper device doesn't have uppers of its own.

Fixes: 0d65fc13042f ("mlxsw: spectrum: Implement LAG port join/leave")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Nogah Frankel <nogahf@mellanox.com>
Tested-by: Nogah Frankel <nogahf@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 6 ++++++
 include/linux/netdevice.h                      | 2 ++
 net/core/dev.c                                 | 3 ++-
 3 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 88357cee7679..940d61159b56 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4110,6 +4110,8 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev,
 			return -EINVAL;
 		if (!info->linking)
 			break;
+		if (netdev_has_any_upper_dev(upper_dev))
+			return -EINVAL;
 		/* HW limitation forbids to put ports to multiple bridges. */
 		if (netif_is_bridge_master(upper_dev) &&
 		    !mlxsw_sp_master_bridge_check(mlxsw_sp, upper_dev))
@@ -4274,6 +4276,10 @@ static int mlxsw_sp_netdevice_bridge_event(struct net_device *br_dev,
 		if (is_vlan_dev(upper_dev) &&
 		    br_dev != mlxsw_sp->master_bridge.dev)
 			return -EINVAL;
+		if (!info->linking)
+			break;
+		if (netdev_has_any_upper_dev(upper_dev))
+			return -EINVAL;
 		break;
 	case NETDEV_CHANGEUPPER:
 		upper_dev = info->upper_dev;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 4ed952c17fc7..663c46ee0658 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3868,6 +3868,8 @@ int netdev_walk_all_upper_dev_rcu(struct net_device *dev,
 bool netdev_has_upper_dev_all_rcu(struct net_device *dev,
 				  struct net_device *upper_dev);
 
+bool netdev_has_any_upper_dev(struct net_device *dev);
+
 void *netdev_lower_get_next_private(struct net_device *dev,
 				    struct list_head **iter);
 void *netdev_lower_get_next_private_rcu(struct net_device *dev,
diff --git a/net/core/dev.c b/net/core/dev.c
index 528edc68a64a..3a40e30c8388 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5590,12 +5590,13 @@ EXPORT_SYMBOL(netdev_has_upper_dev_all_rcu);
  * Find out if a device is linked to an upper device and return true in case
  * it is. The caller must hold the RTNL lock.
  */
-static bool netdev_has_any_upper_dev(struct net_device *dev)
+bool netdev_has_any_upper_dev(struct net_device *dev)
 {
 	ASSERT_RTNL();
 
 	return !list_empty(&dev->adj_list.upper);
 }
+EXPORT_SYMBOL(netdev_has_any_upper_dev);
 
 /**
  * netdev_master_upper_dev_get - Get master upper device
-- 
2.13.5


From 0c7881207c38eb9a50680cccded9bc2d02ee287c Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Fri, 1 Sep 2017 12:22:25 +0300
Subject: [PATCH 35/43] bridge: switchdev: Clear forward mark when transmitting
 packet

[ Upstream commit 79e99bdd60b484af9afe0147e85a13e66d5c1cdb ]

Commit 6bc506b4fb06 ("bridge: switchdev: Add forward mark support for
stacked devices") added the 'offload_fwd_mark' bit to the skb in order
to allow drivers to indicate to the bridge driver that they already
forwarded the packet in L2.

In case the bit is set, before transmitting the packet from each port,
the port's mark is compared with the mark stored in the skb's control
block. If both marks are equal, we know the packet arrived from a switch
device that already forwarded the packet and it's not re-transmitted.

However, if the packet is transmitted from the bridge device itself
(e.g., br0), we should clear the 'offload_fwd_mark' bit as the mark
stored in the skb's control block isn't valid.

This scenario can happen in rare cases where a packet was trapped during
L3 forwarding and forwarded by the kernel to a bridge device.

Fixes: 6bc506b4fb06 ("bridge: switchdev: Add forward mark support for stacked devices")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Yotam Gigi <yotamg@mellanox.com>
Tested-by: Yotam Gigi <yotamg@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_device.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index f0f3447e8aa4..b5d76bcb2d43 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -53,6 +53,9 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 	brstats->tx_bytes += skb->len;
 	u64_stats_update_end(&brstats->syncp);
 
+#ifdef CONFIG_NET_SWITCHDEV
+	skb->offload_fwd_mark = 0;
+#endif
 	BR_INPUT_SKB_CB(skb)->brdev = dev;
 
 	skb_reset_mac_header(skb);
-- 
2.13.5


From 1c0162830ef95ca3a37ef354a09d8f2ca750bd1b Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Fri, 1 Sep 2017 11:26:08 +0200
Subject: [PATCH 36/43] Revert "net: use lib/percpu_counter API for
 fragmentation mem accounting"

[ Upstream commit fb452a1aa3fd4034d7999e309c5466ff2d7005aa ]

This reverts commit 6d7b857d541ecd1d9bd997c97242d4ef94b19de2.

There is a bug in fragmentation codes use of the percpu_counter API,
that can cause issues on systems with many CPUs.

The frag_mem_limit() just reads the global counter (fbc->count),
without considering other CPUs can have upto batch size (130K) that
haven't been subtracted yet.  Due to the 3MBytes lower thresh limit,
this become dangerous at >=24 CPUs (3*1024*1024/130000=24).

The correct API usage would be to use __percpu_counter_compare() which
does the right thing, and takes into account the number of (online)
CPUs and batch size, to account for this and call __percpu_counter_sum()
when needed.

We choose to revert the use of the lib/percpu_counter API for frag
memory accounting for several reasons:

1) On systems with CPUs > 24, the heavier fully locked
   __percpu_counter_sum() is always invoked, which will be more
   expensive than the atomic_t that is reverted to.

Given systems with more than 24 CPUs are becoming common this doesn't
seem like a good option.  To mitigate this, the batch size could be
decreased and thresh be increased.

2) The add_frag_mem_limit+sub_frag_mem_limit pairs happen on the RX
   CPU, before SKBs are pushed into sockets on remote CPUs.  Given
   NICs can only hash on L2 part of the IP-header, the NIC-RXq's will
   likely be limited.  Thus, a fair chance that atomic add+dec happen
   on the same CPU.

Revert note that commit 1d6119baf061 ("net: fix percpu memory leaks")
removed init_frag_mem_limit() and instead use inet_frags_init_net().
After this revert, inet_frags_uninit_net() becomes empty.

Fixes: 6d7b857d541e ("net: use lib/percpu_counter API for fragmentation mem accounting")
Fixes: 1d6119baf061 ("net: fix percpu memory leaks")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_frag.h  | 30 +++++++++---------------------
 net/ipv4/inet_fragment.c |  4 +---
 2 files changed, 10 insertions(+), 24 deletions(-)

diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 5932e6de8fc0..3bb8dfec7725 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -1,14 +1,9 @@
 #ifndef __NET_FRAG_H__
 #define __NET_FRAG_H__
 
-#include <linux/percpu_counter.h>
-
 struct netns_frags {
-	/* The percpu_counter "mem" need to be cacheline aligned.
-	 *  mem.count must not share cacheline with other writers
-	 */
-	struct percpu_counter   mem ____cacheline_aligned_in_smp;
-
+	/* Keep atomic mem on separate cachelines in structs that include it */
+	atomic_t		mem ____cacheline_aligned_in_smp;
 	/* sysctls */
 	int			timeout;
 	int			high_thresh;
@@ -110,11 +105,11 @@ void inet_frags_fini(struct inet_frags *);
 
 static inline int inet_frags_init_net(struct netns_frags *nf)
 {
-	return percpu_counter_init(&nf->mem, 0, GFP_KERNEL);
+	atomic_set(&nf->mem, 0);
+	return 0;
 }
 static inline void inet_frags_uninit_net(struct netns_frags *nf)
 {
-	percpu_counter_destroy(&nf->mem);
 }
 
 void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f);
@@ -140,31 +135,24 @@ static inline bool inet_frag_evicting(struct inet_frag_queue *q)
 
 /* Memory Tracking Functions. */
 
-/* The default percpu_counter batch size is not big enough to scale to
- * fragmentation mem acct sizes.
- * The mem size of a 64K fragment is approx:
- *  (44 fragments * 2944 truesize) + frag_queue struct(200) = 129736 bytes
- */
-static unsigned int frag_percpu_counter_batch = 130000;
-
 static inline int frag_mem_limit(struct netns_frags *nf)
 {
-	return percpu_counter_read(&nf->mem);
+	return atomic_read(&nf->mem);
 }
 
 static inline void sub_frag_mem_limit(struct netns_frags *nf, int i)
 {
-	percpu_counter_add_batch(&nf->mem, -i, frag_percpu_counter_batch);
+	atomic_sub(i, &nf->mem);
 }
 
 static inline void add_frag_mem_limit(struct netns_frags *nf, int i)
 {
-	percpu_counter_add_batch(&nf->mem, i, frag_percpu_counter_batch);
+	atomic_add(i, &nf->mem);
 }
 
-static inline unsigned int sum_frag_mem_limit(struct netns_frags *nf)
+static inline int sum_frag_mem_limit(struct netns_frags *nf)
 {
-	return percpu_counter_sum_positive(&nf->mem);
+	return atomic_read(&nf->mem);
 }
 
 /* RFC 3168 support :
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index b5e9317eaf9e..631c0d0d7cf8 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -234,10 +234,8 @@ void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f)
 	cond_resched();
 
 	if (read_seqretry(&f->rnd_seqlock, seq) ||
-	    percpu_counter_sum(&nf->mem))
+	    sum_frag_mem_limit(nf))
 		goto evict_again;
-
-	percpu_counter_destroy(&nf->mem);
 }
 EXPORT_SYMBOL(inet_frags_exit_net);
 
-- 
2.13.5


From 130a65b03fb9da9b44a2abd4e9426615726cc8d4 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Fri, 1 Sep 2017 11:26:13 +0200
Subject: [PATCH 37/43] Revert "net: fix percpu memory leaks"

[ Upstream commit 5a63643e583b6a9789d7a225ae076fb4e603991c ]

This reverts commit 1d6119baf0610f813eb9d9580eb4fd16de5b4ceb.

After reverting commit 6d7b857d541e ("net: use lib/percpu_counter API
for fragmentation mem accounting") then here is no need for this
fix-up patch.  As percpu_counter is no longer used, it cannot
memory leak it any-longer.

Fixes: 6d7b857d541e ("net: use lib/percpu_counter API for fragmentation mem accounting")
Fixes: 1d6119baf061 ("net: fix percpu memory leaks")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_frag.h                 |  7 +------
 net/ieee802154/6lowpan/reassembly.c     | 11 +++--------
 net/ipv4/ip_fragment.c                  | 12 +++---------
 net/ipv6/netfilter/nf_conntrack_reasm.c | 12 +++---------
 net/ipv6/reassembly.c                   | 12 +++---------
 5 files changed, 13 insertions(+), 41 deletions(-)

diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 3bb8dfec7725..634d19203e7d 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -103,15 +103,10 @@ struct inet_frags {
 int inet_frags_init(struct inet_frags *);
 void inet_frags_fini(struct inet_frags *);
 
-static inline int inet_frags_init_net(struct netns_frags *nf)
+static inline void inet_frags_init_net(struct netns_frags *nf)
 {
 	atomic_set(&nf->mem, 0);
-	return 0;
 }
-static inline void inet_frags_uninit_net(struct netns_frags *nf)
-{
-}
-
 void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f);
 
 void inet_frag_kill(struct inet_frag_queue *q, struct inet_frags *f);
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index 30d875dff6b5..f85b08baff16 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -580,19 +580,14 @@ static int __net_init lowpan_frags_init_net(struct net *net)
 {
 	struct netns_ieee802154_lowpan *ieee802154_lowpan =
 		net_ieee802154_lowpan(net);
-	int res;
 
 	ieee802154_lowpan->frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
 	ieee802154_lowpan->frags.low_thresh = IPV6_FRAG_LOW_THRESH;
 	ieee802154_lowpan->frags.timeout = IPV6_FRAG_TIMEOUT;
 
-	res = inet_frags_init_net(&ieee802154_lowpan->frags);
-	if (res)
-		return res;
-	res = lowpan_frags_ns_sysctl_register(net);
-	if (res)
-		inet_frags_uninit_net(&ieee802154_lowpan->frags);
-	return res;
+	inet_frags_init_net(&ieee802154_lowpan->frags);
+
+	return lowpan_frags_ns_sysctl_register(net);
 }
 
 static void __net_exit lowpan_frags_exit_net(struct net *net)
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index b3cdeec85f1f..4bf3b8af0257 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -844,8 +844,6 @@ static void __init ip4_frags_ctl_register(void)
 
 static int __net_init ipv4_frags_init_net(struct net *net)
 {
-	int res;
-
 	/* Fragment cache limits.
 	 *
 	 * The fragment memory accounting code, (tries to) account for
@@ -871,13 +869,9 @@ static int __net_init ipv4_frags_init_net(struct net *net)
 
 	net->ipv4.frags.max_dist = 64;
 
-	res = inet_frags_init_net(&net->ipv4.frags);
-	if (res)
-		return res;
-	res = ip4_frags_ns_ctl_register(net);
-	if (res)
-		inet_frags_uninit_net(&net->ipv4.frags);
-	return res;
+	inet_frags_init_net(&net->ipv4.frags);
+
+	return ip4_frags_ns_ctl_register(net);
 }
 
 static void __net_exit ipv4_frags_exit_net(struct net *net)
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 986d4ca38832..b263bf3a19f7 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -622,18 +622,12 @@ EXPORT_SYMBOL_GPL(nf_ct_frag6_gather);
 
 static int nf_ct_net_init(struct net *net)
 {
-	int res;
-
 	net->nf_frag.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
 	net->nf_frag.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
 	net->nf_frag.frags.timeout = IPV6_FRAG_TIMEOUT;
-	res = inet_frags_init_net(&net->nf_frag.frags);
-	if (res)
-		return res;
-	res = nf_ct_frag6_sysctl_register(net);
-	if (res)
-		inet_frags_uninit_net(&net->nf_frag.frags);
-	return res;
+	inet_frags_init_net(&net->nf_frag.frags);
+
+	return nf_ct_frag6_sysctl_register(net);
 }
 
 static void nf_ct_net_exit(struct net *net)
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index e1da5b888cc4..846012eae526 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -714,19 +714,13 @@ static void ip6_frags_sysctl_unregister(void)
 
 static int __net_init ipv6_frags_init_net(struct net *net)
 {
-	int res;
-
 	net->ipv6.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
 	net->ipv6.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
 	net->ipv6.frags.timeout = IPV6_FRAG_TIMEOUT;
 
-	res = inet_frags_init_net(&net->ipv6.frags);
-	if (res)
-		return res;
-	res = ip6_frags_ns_sysctl_register(net);
-	if (res)
-		inet_frags_uninit_net(&net->ipv6.frags);
-	return res;
+	inet_frags_init_net(&net->ipv6.frags);
+
+	return ip6_frags_ns_sysctl_register(net);
 }
 
 static void __net_exit ipv6_frags_exit_net(struct net *net)
-- 
2.13.5


From 446929f867b4a7c771a8f6f5ac128f6fa3d8a58a Mon Sep 17 00:00:00 2001
From: Claudiu Manoil <claudiu.manoil@nxp.com>
Date: Mon, 4 Sep 2017 10:45:28 +0300
Subject: [PATCH 38/43] gianfar: Fix Tx flow control deactivation

[ Upstream commit 5d621672bc1a1e5090c1ac5432a18c79e0e13e03 ]

The wrong register is checked for the Tx flow control bit,
it should have been maccfg1 not maccfg2.
This went unnoticed for so long probably because the impact is
hardly visible, not to mention the tangled code from adjust_link().
First, link flow control (i.e. handling of Rx/Tx link level pause frames)
is disabled by default (needs to be enabled via 'ethtool -A').
Secondly, maccfg2 always returns 0 for tx_flow_oldval (except for a few
old boards), which results in Tx flow control remaining always on
once activated.

Fixes: 45b679c9a3ccd9e34f28e6ec677b812a860eb8eb ("gianfar: Implement PAUSE frame generation support")
Signed-off-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/gianfar.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 0ff166ec3e7e..aac8490c910a 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -3687,7 +3687,7 @@ static noinline void gfar_update_link_state(struct gfar_private *priv)
 		u32 tempval1 = gfar_read(&regs->maccfg1);
 		u32 tempval = gfar_read(&regs->maccfg2);
 		u32 ecntrl = gfar_read(&regs->ecntrl);
-		u32 tx_flow_oldval = (tempval & MACCFG1_TX_FLOW);
+		u32 tx_flow_oldval = (tempval1 & MACCFG1_TX_FLOW);
 
 		if (phydev->duplex != priv->oldduplex) {
 			if (!(phydev->duplex))
-- 
2.13.5


From e1de9ba829a335f38823d8e763f704b5f1c696d1 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Tue, 5 Sep 2017 09:22:05 +0800
Subject: [PATCH 39/43] vhost_net: correctly check tx avail during rx busy
 polling

[ Upstream commit 8b949bef9172ca69d918e93509a4ecb03d0355e0 ]

We check tx avail through vhost_enable_notify() in the past which is
wrong since it only checks whether or not guest has filled more
available buffer since last avail idx synchronization which was just
done by vhost_vq_avail_empty() before. What we really want is checking
pending buffers in the avail ring. Fix this by calling
vhost_vq_avail_empty() instead.

This issue could be noticed by doing netperf TCP_RR benchmark as
client from guest (but not host). With this fix, TCP_RR from guest to
localhost restores from 1375.91 trans per sec to 55235.28 trans per
sec on my laptop (Intel(R) Core(TM) i7-5600U CPU @ 2.60GHz).

Fixes: 030881372460 ("vhost_net: basic polling support")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/net.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index f61f852d6cfd..83ad2ac0cbea 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -557,8 +557,13 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk)
 
 		preempt_enable();
 
-		if (vhost_enable_notify(&net->dev, vq))
+		if (!vhost_vq_avail_empty(&net->dev, vq))
 			vhost_poll_queue(&vq->poll);
+		else if (unlikely(vhost_enable_notify(&net->dev, vq))) {
+			vhost_disable_notify(&net->dev, vq);
+			vhost_poll_queue(&vq->poll);
+		}
+
 		mutex_unlock(&vq->mutex);
 
 		len = peek_head_len(sk);
-- 
2.13.5


From 7fec3a723422915a15097fe17c925c5518698f48 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 5 Sep 2017 17:26:33 +0800
Subject: [PATCH 40/43] ip6_gre: update mtu properly in ip6gre_err

[ Upstream commit 5c25f30c93fdc5bf25e62101aeaae7a4f9b421b3 ]

Now when probessing ICMPV6_PKT_TOOBIG, ip6gre_err only subtracts the
offset of gre header from mtu info. The expected mtu of gre device
should also subtract gre header. Otherwise, the next packets still
can't be sent out.

Jianlin found this issue when using the topo:
  client(ip6gre)<---->(nic1)route(nic2)<----->(ip6gre)server

and reducing nic2's mtu, then both tcp and sctp's performance with
big size data became 0.

This patch is to fix it by also subtracting grehdr (tun->tun_hlen)
from mtu info when updating gre device's mtu in ip6gre_err(). It
also needs to subtract ETH_HLEN if gre dev'type is ARPHRD_ETHER.

Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 64eea3962733..ca2a45134c6b 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -432,7 +432,9 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		}
 		break;
 	case ICMPV6_PKT_TOOBIG:
-		mtu = be32_to_cpu(info) - offset;
+		mtu = be32_to_cpu(info) - offset - t->tun_hlen;
+		if (t->dev->type == ARPHRD_ETHER)
+			mtu -= ETH_HLEN;
 		if (mtu < IPV6_MIN_MTU)
 			mtu = IPV6_MIN_MTU;
 		t->dev->mtu = mtu;
-- 
2.13.5


From 9974f1b4b992edb663cd6a40f171662e12b6c375 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 8 Sep 2017 10:26:19 +0200
Subject: [PATCH 41/43] ipv6: fix memory leak with multiple tables during netns
 destruction

[ Upstream commit ba1cc08d9488c94cb8d94f545305688b72a2a300 ]

fib6_net_exit only frees the main and local tables. If another table was
created with fib6_alloc_table, we leak it when the netns is destroyed.

Fix this in the same way ip_fib_net_exit cleans up tables, by walking
through the whole hashtable of fib6_table's. We can get rid of the
special cases for local and main, since they're also part of the
hashtable.

Reproducer:
    ip netns add x
    ip -net x -6 rule add from 6003:1::/64 table 100
    ip netns del x

Reported-by: Jianlin Shi <jishi@redhat.com>
Fixes: 58f09b78b730 ("[NETNS][IPV6] ip6_fib - make it per network namespace")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_fib.c | 25 +++++++++++++++++++------
 1 file changed, 19 insertions(+), 6 deletions(-)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 76cdaa9d4a51..4c4dd79724e7 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -201,6 +201,12 @@ static void rt6_release(struct rt6_info *rt)
 	}
 }
 
+static void fib6_free_table(struct fib6_table *table)
+{
+	inetpeer_invalidate_tree(&table->tb6_peers);
+	kfree(table);
+}
+
 static void fib6_link_table(struct net *net, struct fib6_table *tb)
 {
 	unsigned int h;
@@ -1911,15 +1917,22 @@ static int __net_init fib6_net_init(struct net *net)
 
 static void fib6_net_exit(struct net *net)
 {
+	unsigned int i;
+
 	rt6_ifdown(net, NULL);
 	del_timer_sync(&net->ipv6.ip6_fib_timer);
 
-#ifdef CONFIG_IPV6_MULTIPLE_TABLES
-	inetpeer_invalidate_tree(&net->ipv6.fib6_local_tbl->tb6_peers);
-	kfree(net->ipv6.fib6_local_tbl);
-#endif
-	inetpeer_invalidate_tree(&net->ipv6.fib6_main_tbl->tb6_peers);
-	kfree(net->ipv6.fib6_main_tbl);
+	for (i = 0; i < FIB_TABLE_HASHSZ; i++) {
+		struct hlist_head *head = &net->ipv6.fib_table_hash[i];
+		struct hlist_node *tmp;
+		struct fib6_table *tb;
+
+		hlist_for_each_entry_safe(tb, tmp, head, tb6_hlist) {
+			hlist_del(&tb->tb6_hlist);
+			fib6_free_table(tb);
+		}
+	}
+
 	kfree(net->ipv6.fib_table_hash);
 	kfree(net->ipv6.rt6_stats);
 }
-- 
2.13.5


From 4ccb983c90edffa3bf9e126a70903bf20a547609 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 8 Sep 2017 15:48:47 -0700
Subject: [PATCH 42/43] ipv6: fix typo in fib6_net_exit()

[ Upstream commit 32a805baf0fb70b6dbedefcd7249ac7f580f9e3b ]

IPv6 FIB should use FIB6_TABLE_HASHSZ, not FIB_TABLE_HASHSZ.

Fixes: ba1cc08d9488 ("ipv6: fix memory leak with multiple tables during netns destruction")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_fib.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 4c4dd79724e7..fa03fa469f92 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1922,7 +1922,7 @@ static void fib6_net_exit(struct net *net)
 	rt6_ifdown(net, NULL);
 	del_timer_sync(&net->ipv6.ip6_fib_timer);
 
-	for (i = 0; i < FIB_TABLE_HASHSZ; i++) {
+	for (i = 0; i < FIB6_TABLE_HASHSZ; i++) {
 		struct hlist_head *head = &net->ipv6.fib_table_hash[i];
 		struct hlist_node *tmp;
 		struct fib6_table *tb;
-- 
2.13.5


From f196cbed864d001202b449e2810d0860f86efbe6 Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Fri, 8 Sep 2017 11:35:21 -0300
Subject: [PATCH 43/43] sctp: fix missing wake ups in some situations

[ Upstream commit 7906b00f5cd1cd484fced7fcda892176e3202c8a ]

Commit fb586f25300f ("sctp: delay calls to sk_data_ready() as much as
possible") minimized the number of wake ups that are triggered in case
the association receives a packet with multiple data chunks on it and/or
when io_events are enabled and then commit 0970f5b36659 ("sctp: signal
sk_data_ready earlier on data chunks reception") moved the wake up to as
soon as possible. It thus relies on the state machine running later to
clean the flag that the event was already generated.

The issue is that there are 2 call paths that calls
sctp_ulpq_tail_event() outside of the state machine, causing the flag to
linger and possibly omitting a needed wake up in the sequence.

One of the call paths is when enabling SCTP_SENDER_DRY_EVENTS via
setsockopt(SCTP_EVENTS), as noticed by Harald Welte. The other is when
partial reliability triggers removal of chunks from the send queue when
the application calls sendmsg().

This commit fixes it by not setting the flag in case the socket is not
owned by the user, as it won't be cleaned later. This works for
user-initiated calls and also for rx path processing.

Fixes: fb586f25300f ("sctp: delay calls to sk_data_ready() as much as possible")
Reported-by: Harald Welte <laforge@gnumonks.org>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ulpqueue.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c
index aa3624d50278..8354479178b9 100644
--- a/net/sctp/ulpqueue.c
+++ b/net/sctp/ulpqueue.c
@@ -265,7 +265,8 @@ int sctp_ulpq_tail_event(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event)
 		sctp_ulpq_clear_pd(ulpq);
 
 	if (queue == &sk->sk_receive_queue && !sp->data_ready_signalled) {
-		sp->data_ready_signalled = 1;
+		if (!sock_owned_by_user(sk))
+			sp->data_ready_signalled = 1;
 		sk->sk_data_ready(sk);
 	}
 	return 1;
-- 
2.13.5


[-- Attachment #4: net_413.mbox --]
[-- Type: Application/Octet-Stream, Size: 27421 bytes --]

From fa078a743f806ab6fe67a717aa6ad140d9758e07 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Fri, 1 Sep 2017 11:26:08 +0200
Subject: [PATCH 01/11] Revert "net: use lib/percpu_counter API for
 fragmentation mem accounting"

[ Upstream commit fb452a1aa3fd4034d7999e309c5466ff2d7005aa ]

This reverts commit 6d7b857d541ecd1d9bd997c97242d4ef94b19de2.

There is a bug in fragmentation codes use of the percpu_counter API,
that can cause issues on systems with many CPUs.

The frag_mem_limit() just reads the global counter (fbc->count),
without considering other CPUs can have upto batch size (130K) that
haven't been subtracted yet.  Due to the 3MBytes lower thresh limit,
this become dangerous at >=24 CPUs (3*1024*1024/130000=24).

The correct API usage would be to use __percpu_counter_compare() which
does the right thing, and takes into account the number of (online)
CPUs and batch size, to account for this and call __percpu_counter_sum()
when needed.

We choose to revert the use of the lib/percpu_counter API for frag
memory accounting for several reasons:

1) On systems with CPUs > 24, the heavier fully locked
   __percpu_counter_sum() is always invoked, which will be more
   expensive than the atomic_t that is reverted to.

Given systems with more than 24 CPUs are becoming common this doesn't
seem like a good option.  To mitigate this, the batch size could be
decreased and thresh be increased.

2) The add_frag_mem_limit+sub_frag_mem_limit pairs happen on the RX
   CPU, before SKBs are pushed into sockets on remote CPUs.  Given
   NICs can only hash on L2 part of the IP-header, the NIC-RXq's will
   likely be limited.  Thus, a fair chance that atomic add+dec happen
   on the same CPU.

Revert note that commit 1d6119baf061 ("net: fix percpu memory leaks")
removed init_frag_mem_limit() and instead use inet_frags_init_net().
After this revert, inet_frags_uninit_net() becomes empty.

Fixes: 6d7b857d541e ("net: use lib/percpu_counter API for fragmentation mem accounting")
Fixes: 1d6119baf061 ("net: fix percpu memory leaks")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_frag.h  | 30 +++++++++---------------------
 net/ipv4/inet_fragment.c |  4 +---
 2 files changed, 10 insertions(+), 24 deletions(-)

diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 6fdcd2427776..fa635aa6d0b9 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -1,14 +1,9 @@
 #ifndef __NET_FRAG_H__
 #define __NET_FRAG_H__
 
-#include <linux/percpu_counter.h>
-
 struct netns_frags {
-	/* The percpu_counter "mem" need to be cacheline aligned.
-	 *  mem.count must not share cacheline with other writers
-	 */
-	struct percpu_counter   mem ____cacheline_aligned_in_smp;
-
+	/* Keep atomic mem on separate cachelines in structs that include it */
+	atomic_t		mem ____cacheline_aligned_in_smp;
 	/* sysctls */
 	int			timeout;
 	int			high_thresh;
@@ -110,11 +105,11 @@ void inet_frags_fini(struct inet_frags *);
 
 static inline int inet_frags_init_net(struct netns_frags *nf)
 {
-	return percpu_counter_init(&nf->mem, 0, GFP_KERNEL);
+	atomic_set(&nf->mem, 0);
+	return 0;
 }
 static inline void inet_frags_uninit_net(struct netns_frags *nf)
 {
-	percpu_counter_destroy(&nf->mem);
 }
 
 void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f);
@@ -140,31 +135,24 @@ static inline bool inet_frag_evicting(struct inet_frag_queue *q)
 
 /* Memory Tracking Functions. */
 
-/* The default percpu_counter batch size is not big enough to scale to
- * fragmentation mem acct sizes.
- * The mem size of a 64K fragment is approx:
- *  (44 fragments * 2944 truesize) + frag_queue struct(200) = 129736 bytes
- */
-static unsigned int frag_percpu_counter_batch = 130000;
-
 static inline int frag_mem_limit(struct netns_frags *nf)
 {
-	return percpu_counter_read(&nf->mem);
+	return atomic_read(&nf->mem);
 }
 
 static inline void sub_frag_mem_limit(struct netns_frags *nf, int i)
 {
-	percpu_counter_add_batch(&nf->mem, -i, frag_percpu_counter_batch);
+	atomic_sub(i, &nf->mem);
 }
 
 static inline void add_frag_mem_limit(struct netns_frags *nf, int i)
 {
-	percpu_counter_add_batch(&nf->mem, i, frag_percpu_counter_batch);
+	atomic_add(i, &nf->mem);
 }
 
-static inline unsigned int sum_frag_mem_limit(struct netns_frags *nf)
+static inline int sum_frag_mem_limit(struct netns_frags *nf)
 {
-	return percpu_counter_sum_positive(&nf->mem);
+	return atomic_read(&nf->mem);
 }
 
 /* RFC 3168 support :
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 96e95e83cc61..af74d0433453 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -234,10 +234,8 @@ void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f)
 	cond_resched();
 
 	if (read_seqretry(&f->rnd_seqlock, seq) ||
-	    percpu_counter_sum(&nf->mem))
+	    sum_frag_mem_limit(nf))
 		goto evict_again;
-
-	percpu_counter_destroy(&nf->mem);
 }
 EXPORT_SYMBOL(inet_frags_exit_net);
 
-- 
2.13.5


From c0360248582d85e738354be8e1108990b4e21dbe Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Fri, 1 Sep 2017 11:26:13 +0200
Subject: [PATCH 02/11] Revert "net: fix percpu memory leaks"

[ Upstream commit 5a63643e583b6a9789d7a225ae076fb4e603991c ]

This reverts commit 1d6119baf0610f813eb9d9580eb4fd16de5b4ceb.

After reverting commit 6d7b857d541e ("net: use lib/percpu_counter API
for fragmentation mem accounting") then here is no need for this
fix-up patch.  As percpu_counter is no longer used, it cannot
memory leak it any-longer.

Fixes: 6d7b857d541e ("net: use lib/percpu_counter API for fragmentation mem accounting")
Fixes: 1d6119baf061 ("net: fix percpu memory leaks")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_frag.h                 |  7 +------
 net/ieee802154/6lowpan/reassembly.c     | 11 +++--------
 net/ipv4/ip_fragment.c                  | 12 +++---------
 net/ipv6/netfilter/nf_conntrack_reasm.c | 12 +++---------
 net/ipv6/reassembly.c                   | 12 +++---------
 5 files changed, 13 insertions(+), 41 deletions(-)

diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index fa635aa6d0b9..fc59e0775e00 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -103,15 +103,10 @@ struct inet_frags {
 int inet_frags_init(struct inet_frags *);
 void inet_frags_fini(struct inet_frags *);
 
-static inline int inet_frags_init_net(struct netns_frags *nf)
+static inline void inet_frags_init_net(struct netns_frags *nf)
 {
 	atomic_set(&nf->mem, 0);
-	return 0;
 }
-static inline void inet_frags_uninit_net(struct netns_frags *nf)
-{
-}
-
 void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f);
 
 void inet_frag_kill(struct inet_frag_queue *q, struct inet_frags *f);
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index 30d875dff6b5..f85b08baff16 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -580,19 +580,14 @@ static int __net_init lowpan_frags_init_net(struct net *net)
 {
 	struct netns_ieee802154_lowpan *ieee802154_lowpan =
 		net_ieee802154_lowpan(net);
-	int res;
 
 	ieee802154_lowpan->frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
 	ieee802154_lowpan->frags.low_thresh = IPV6_FRAG_LOW_THRESH;
 	ieee802154_lowpan->frags.timeout = IPV6_FRAG_TIMEOUT;
 
-	res = inet_frags_init_net(&ieee802154_lowpan->frags);
-	if (res)
-		return res;
-	res = lowpan_frags_ns_sysctl_register(net);
-	if (res)
-		inet_frags_uninit_net(&ieee802154_lowpan->frags);
-	return res;
+	inet_frags_init_net(&ieee802154_lowpan->frags);
+
+	return lowpan_frags_ns_sysctl_register(net);
 }
 
 static void __net_exit lowpan_frags_exit_net(struct net *net)
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 9a8cfac503dc..46408c220d9d 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -844,8 +844,6 @@ static void __init ip4_frags_ctl_register(void)
 
 static int __net_init ipv4_frags_init_net(struct net *net)
 {
-	int res;
-
 	/* Fragment cache limits.
 	 *
 	 * The fragment memory accounting code, (tries to) account for
@@ -871,13 +869,9 @@ static int __net_init ipv4_frags_init_net(struct net *net)
 
 	net->ipv4.frags.max_dist = 64;
 
-	res = inet_frags_init_net(&net->ipv4.frags);
-	if (res)
-		return res;
-	res = ip4_frags_ns_ctl_register(net);
-	if (res)
-		inet_frags_uninit_net(&net->ipv4.frags);
-	return res;
+	inet_frags_init_net(&net->ipv4.frags);
+
+	return ip4_frags_ns_ctl_register(net);
 }
 
 static void __net_exit ipv4_frags_exit_net(struct net *net)
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 986d4ca38832..b263bf3a19f7 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -622,18 +622,12 @@ EXPORT_SYMBOL_GPL(nf_ct_frag6_gather);
 
 static int nf_ct_net_init(struct net *net)
 {
-	int res;
-
 	net->nf_frag.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
 	net->nf_frag.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
 	net->nf_frag.frags.timeout = IPV6_FRAG_TIMEOUT;
-	res = inet_frags_init_net(&net->nf_frag.frags);
-	if (res)
-		return res;
-	res = nf_ct_frag6_sysctl_register(net);
-	if (res)
-		inet_frags_uninit_net(&net->nf_frag.frags);
-	return res;
+	inet_frags_init_net(&net->nf_frag.frags);
+
+	return nf_ct_frag6_sysctl_register(net);
 }
 
 static void nf_ct_net_exit(struct net *net)
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index e1da5b888cc4..846012eae526 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -714,19 +714,13 @@ static void ip6_frags_sysctl_unregister(void)
 
 static int __net_init ipv6_frags_init_net(struct net *net)
 {
-	int res;
-
 	net->ipv6.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
 	net->ipv6.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
 	net->ipv6.frags.timeout = IPV6_FRAG_TIMEOUT;
 
-	res = inet_frags_init_net(&net->ipv6.frags);
-	if (res)
-		return res;
-	res = ip6_frags_ns_sysctl_register(net);
-	if (res)
-		inet_frags_uninit_net(&net->ipv6.frags);
-	return res;
+	inet_frags_init_net(&net->ipv6.frags);
+
+	return ip6_frags_ns_sysctl_register(net);
 }
 
 static void __net_exit ipv6_frags_exit_net(struct net *net)
-- 
2.13.5


From ad6d23ded47ddd26003b0054700dc46b65901da8 Mon Sep 17 00:00:00 2001
From: Claudiu Manoil <claudiu.manoil@nxp.com>
Date: Mon, 4 Sep 2017 10:45:28 +0300
Subject: [PATCH 03/11] gianfar: Fix Tx flow control deactivation

[ Upstream commit 5d621672bc1a1e5090c1ac5432a18c79e0e13e03 ]

The wrong register is checked for the Tx flow control bit,
it should have been maccfg1 not maccfg2.
This went unnoticed for so long probably because the impact is
hardly visible, not to mention the tangled code from adjust_link().
First, link flow control (i.e. handling of Rx/Tx link level pause frames)
is disabled by default (needs to be enabled via 'ethtool -A').
Secondly, maccfg2 always returns 0 for tx_flow_oldval (except for a few
old boards), which results in Tx flow control remaining always on
once activated.

Fixes: 45b679c9a3ccd9e34f28e6ec677b812a860eb8eb ("gianfar: Implement PAUSE frame generation support")
Signed-off-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/gianfar.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index c4b4b0a1bbf0..5be52d89b182 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -3687,7 +3687,7 @@ static noinline void gfar_update_link_state(struct gfar_private *priv)
 		u32 tempval1 = gfar_read(&regs->maccfg1);
 		u32 tempval = gfar_read(&regs->maccfg2);
 		u32 ecntrl = gfar_read(&regs->ecntrl);
-		u32 tx_flow_oldval = (tempval & MACCFG1_TX_FLOW);
+		u32 tx_flow_oldval = (tempval1 & MACCFG1_TX_FLOW);
 
 		if (phydev->duplex != priv->oldduplex) {
 			if (!(phydev->duplex))
-- 
2.13.5


From 4665f7b778bb5d97c009ee7b7439c6467014a175 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Tue, 5 Sep 2017 09:22:05 +0800
Subject: [PATCH 04/11] vhost_net: correctly check tx avail during rx busy
 polling

[ Upstream commit 8b949bef9172ca69d918e93509a4ecb03d0355e0 ]

We check tx avail through vhost_enable_notify() in the past which is
wrong since it only checks whether or not guest has filled more
available buffer since last avail idx synchronization which was just
done by vhost_vq_avail_empty() before. What we really want is checking
pending buffers in the avail ring. Fix this by calling
vhost_vq_avail_empty() instead.

This issue could be noticed by doing netperf TCP_RR benchmark as
client from guest (but not host). With this fix, TCP_RR from guest to
localhost restores from 1375.91 trans per sec to 55235.28 trans per
sec on my laptop (Intel(R) Core(TM) i7-5600U CPU @ 2.60GHz).

Fixes: 030881372460 ("vhost_net: basic polling support")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/net.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 06d044862e58..1c75572f5a3f 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -634,8 +634,13 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk)
 
 		preempt_enable();
 
-		if (vhost_enable_notify(&net->dev, vq))
+		if (!vhost_vq_avail_empty(&net->dev, vq))
 			vhost_poll_queue(&vq->poll);
+		else if (unlikely(vhost_enable_notify(&net->dev, vq))) {
+			vhost_disable_notify(&net->dev, vq);
+			vhost_poll_queue(&vq->poll);
+		}
+
 		mutex_unlock(&vq->mutex);
 
 		len = peek_head_len(rvq, sk);
-- 
2.13.5


From 56a5d6edbd5b85afcee10097e7ec590f75a64111 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 5 Sep 2017 17:26:33 +0800
Subject: [PATCH 05/11] ip6_gre: update mtu properly in ip6gre_err

[ Upstream commit 5c25f30c93fdc5bf25e62101aeaae7a4f9b421b3 ]

Now when probessing ICMPV6_PKT_TOOBIG, ip6gre_err only subtracts the
offset of gre header from mtu info. The expected mtu of gre device
should also subtract gre header. Otherwise, the next packets still
can't be sent out.

Jianlin found this issue when using the topo:
  client(ip6gre)<---->(nic1)route(nic2)<----->(ip6gre)server

and reducing nic2's mtu, then both tcp and sctp's performance with
big size data became 0.

This patch is to fix it by also subtracting grehdr (tun->tun_hlen)
from mtu info when updating gre device's mtu in ip6gre_err(). It
also needs to subtract ETH_HLEN if gre dev'type is ARPHRD_ETHER.

Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 67ff2aaf5dcb..b7a72d409334 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -432,7 +432,9 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		}
 		break;
 	case ICMPV6_PKT_TOOBIG:
-		mtu = be32_to_cpu(info) - offset;
+		mtu = be32_to_cpu(info) - offset - t->tun_hlen;
+		if (t->dev->type == ARPHRD_ETHER)
+			mtu -= ETH_HLEN;
 		if (mtu < IPV6_MIN_MTU)
 			mtu = IPV6_MIN_MTU;
 		t->dev->mtu = mtu;
-- 
2.13.5


From 9f14f9437f5fc483010b7b8a70c2b0ec2438c267 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 6 Sep 2017 14:44:36 +0200
Subject: [PATCH 06/11] udp: drop head states only when all skb references are
 gone

[ Upstream commit ca2c1418efe9f7fe37aa1f355efdf4eb293673ce ]

After commit 0ddf3fb2c43d ("udp: preserve skb->dst if required
for IP options processing") we clear the skb head state as soon
as the skb carrying them is first processed.

Since the same skb can be processed several times when MSG_PEEK
is used, we can end up lacking the required head states, and
eventually oopsing.

Fix this clearing the skb head state only when processing the
last skb reference.

Reported-by: Eric Dumazet <edumazet@google.com>
Fixes: 0ddf3fb2c43d ("udp: preserve skb->dst if required for IP options processing")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 2 +-
 net/core/skbuff.c      | 9 +++------
 net/ipv4/udp.c         | 5 ++++-
 3 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index d67a8182e5eb..63df75ae70ee 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -885,7 +885,7 @@ void kfree_skb(struct sk_buff *skb);
 void kfree_skb_list(struct sk_buff *segs);
 void skb_tx_error(struct sk_buff *skb);
 void consume_skb(struct sk_buff *skb);
-void consume_stateless_skb(struct sk_buff *skb);
+void __consume_stateless_skb(struct sk_buff *skb);
 void  __kfree_skb(struct sk_buff *skb);
 extern struct kmem_cache *skbuff_head_cache;
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index e07556606284..72eb23d2426f 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -753,14 +753,11 @@ EXPORT_SYMBOL(consume_skb);
  *	consume_stateless_skb - free an skbuff, assuming it is stateless
  *	@skb: buffer to free
  *
- *	Works like consume_skb(), but this variant assumes that all the head
- *	states have been already dropped.
+ *	Alike consume_skb(), but this variant assumes that this is the last
+ *	skb reference and all the head states have been already dropped
  */
-void consume_stateless_skb(struct sk_buff *skb)
+void __consume_stateless_skb(struct sk_buff *skb)
 {
-	if (!skb_unref(skb))
-		return;
-
 	trace_consume_skb(skb);
 	if (likely(skb->head))
 		skb_release_data(skb);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 62344804baae..979e4d8526ba 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1386,12 +1386,15 @@ void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len)
 		unlock_sock_fast(sk, slow);
 	}
 
+	if (!skb_unref(skb))
+		return;
+
 	/* In the more common cases we cleared the head states previously,
 	 * see __udp_queue_rcv_skb().
 	 */
 	if (unlikely(udp_skb_has_head_state(skb)))
 		skb_release_head_state(skb);
-	consume_stateless_skb(skb);
+	__consume_stateless_skb(skb);
 }
 EXPORT_SYMBOL_GPL(skb_consume_udp);
 
-- 
2.13.5


From 89f376a2fa02bec7fb14774fcd614e9e9219f02f Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 8 Sep 2017 10:26:19 +0200
Subject: [PATCH 07/11] ipv6: fix memory leak with multiple tables during netns
 destruction

[ Upstream commit ba1cc08d9488c94cb8d94f545305688b72a2a300 ]

fib6_net_exit only frees the main and local tables. If another table was
created with fib6_alloc_table, we leak it when the netns is destroyed.

Fix this in the same way ip_fib_net_exit cleans up tables, by walking
through the whole hashtable of fib6_table's. We can get rid of the
special cases for local and main, since they're also part of the
hashtable.

Reproducer:
    ip netns add x
    ip -net x -6 rule add from 6003:1::/64 table 100
    ip netns del x

Reported-by: Jianlin Shi <jishi@redhat.com>
Fixes: 58f09b78b730 ("[NETNS][IPV6] ip6_fib - make it per network namespace")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_fib.c | 25 +++++++++++++++++++------
 1 file changed, 19 insertions(+), 6 deletions(-)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index e1c85bb4eac0..452898ae24f1 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -198,6 +198,12 @@ static void rt6_release(struct rt6_info *rt)
 	}
 }
 
+static void fib6_free_table(struct fib6_table *table)
+{
+	inetpeer_invalidate_tree(&table->tb6_peers);
+	kfree(table);
+}
+
 static void fib6_link_table(struct net *net, struct fib6_table *tb)
 {
 	unsigned int h;
@@ -1915,15 +1921,22 @@ static int __net_init fib6_net_init(struct net *net)
 
 static void fib6_net_exit(struct net *net)
 {
+	unsigned int i;
+
 	rt6_ifdown(net, NULL);
 	del_timer_sync(&net->ipv6.ip6_fib_timer);
 
-#ifdef CONFIG_IPV6_MULTIPLE_TABLES
-	inetpeer_invalidate_tree(&net->ipv6.fib6_local_tbl->tb6_peers);
-	kfree(net->ipv6.fib6_local_tbl);
-#endif
-	inetpeer_invalidate_tree(&net->ipv6.fib6_main_tbl->tb6_peers);
-	kfree(net->ipv6.fib6_main_tbl);
+	for (i = 0; i < FIB_TABLE_HASHSZ; i++) {
+		struct hlist_head *head = &net->ipv6.fib_table_hash[i];
+		struct hlist_node *tmp;
+		struct fib6_table *tb;
+
+		hlist_for_each_entry_safe(tb, tmp, head, tb6_hlist) {
+			hlist_del(&tb->tb6_hlist);
+			fib6_free_table(tb);
+		}
+	}
+
 	kfree(net->ipv6.fib_table_hash);
 	kfree(net->ipv6.rt6_stats);
 }
-- 
2.13.5


From 8a15256068292a7bc022ab2d76ae18b42c44cb39 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 8 Sep 2017 15:48:47 -0700
Subject: [PATCH 08/11] ipv6: fix typo in fib6_net_exit()

[ Upstream commit 32a805baf0fb70b6dbedefcd7249ac7f580f9e3b ]

IPv6 FIB should use FIB6_TABLE_HASHSZ, not FIB_TABLE_HASHSZ.

Fixes: ba1cc08d9488 ("ipv6: fix memory leak with multiple tables during netns destruction")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_fib.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 452898ae24f1..1792bbfd80e1 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1926,7 +1926,7 @@ static void fib6_net_exit(struct net *net)
 	rt6_ifdown(net, NULL);
 	del_timer_sync(&net->ipv6.ip6_fib_timer);
 
-	for (i = 0; i < FIB_TABLE_HASHSZ; i++) {
+	for (i = 0; i < FIB6_TABLE_HASHSZ; i++) {
 		struct hlist_head *head = &net->ipv6.fib_table_hash[i];
 		struct hlist_node *tmp;
 		struct fib6_table *tb;
-- 
2.13.5


From 92294037bc1d4c68c736474d1c46a99a8bad1ad0 Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Fri, 8 Sep 2017 11:35:21 -0300
Subject: [PATCH 09/11] sctp: fix missing wake ups in some situations

[ Upstream commit 7906b00f5cd1cd484fced7fcda892176e3202c8a ]

Commit fb586f25300f ("sctp: delay calls to sk_data_ready() as much as
possible") minimized the number of wake ups that are triggered in case
the association receives a packet with multiple data chunks on it and/or
when io_events are enabled and then commit 0970f5b36659 ("sctp: signal
sk_data_ready earlier on data chunks reception") moved the wake up to as
soon as possible. It thus relies on the state machine running later to
clean the flag that the event was already generated.

The issue is that there are 2 call paths that calls
sctp_ulpq_tail_event() outside of the state machine, causing the flag to
linger and possibly omitting a needed wake up in the sequence.

One of the call paths is when enabling SCTP_SENDER_DRY_EVENTS via
setsockopt(SCTP_EVENTS), as noticed by Harald Welte. The other is when
partial reliability triggers removal of chunks from the send queue when
the application calls sendmsg().

This commit fixes it by not setting the flag in case the socket is not
owned by the user, as it won't be cleaned later. This works for
user-initiated calls and also for rx path processing.

Fixes: fb586f25300f ("sctp: delay calls to sk_data_ready() as much as possible")
Reported-by: Harald Welte <laforge@gnumonks.org>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ulpqueue.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c
index 0225d62a869f..a71be33f3afe 100644
--- a/net/sctp/ulpqueue.c
+++ b/net/sctp/ulpqueue.c
@@ -265,7 +265,8 @@ int sctp_ulpq_tail_event(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event)
 		sctp_ulpq_clear_pd(ulpq);
 
 	if (queue == &sk->sk_receive_queue && !sp->data_ready_signalled) {
-		sp->data_ready_signalled = 1;
+		if (!sock_owned_by_user(sk))
+			sp->data_ready_signalled = 1;
 		sk->sk_data_ready(sk);
 	}
 	return 1;
-- 
2.13.5


From 1a6496d6b633a6940624ead6363a8edc8988711f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 8 Sep 2017 12:44:47 -0700
Subject: [PATCH 10/11] tcp: fix a request socket leak

[ Upstream commit 1f3b359f1004bd34b7b0bad70b93e3c7af92a37b ]

While the cited commit fixed a possible deadlock, it added a leak
of the request socket, since reqsk_put() must be called if the BPF
filter decided the ACK packet must be dropped.

Fixes: d624d276d1dd ("tcp: fix possible deadlock in TCP stack vs BPF filter")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c | 6 +++---
 net/ipv6/tcp_ipv6.c | 6 +++---
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index e9252c7df809..21022db7a2a6 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1722,9 +1722,9 @@ int tcp_v4_rcv(struct sk_buff *skb)
 		 */
 		sock_hold(sk);
 		refcounted = true;
-		if (tcp_filter(sk, skb))
-			goto discard_and_relse;
-		nsk = tcp_check_req(sk, skb, req, false);
+		nsk = NULL;
+		if (!tcp_filter(sk, skb))
+			nsk = tcp_check_req(sk, skb, req, false);
 		if (!nsk) {
 			reqsk_put(req);
 			goto discard_and_relse;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 206210125fd7..660b9b2a8a25 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1456,9 +1456,9 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 		}
 		sock_hold(sk);
 		refcounted = true;
-		if (tcp_filter(sk, skb))
-			goto discard_and_relse;
-		nsk = tcp_check_req(sk, skb, req, false);
+		nsk = NULL;
+		if (!tcp_filter(sk, skb))
+			nsk = tcp_check_req(sk, skb, req, false);
 		if (!nsk) {
 			reqsk_put(req);
 			goto discard_and_relse;
-- 
2.13.5


From c79594901ffc672cc7441b1ee0e7fa3f2084c813 Mon Sep 17 00:00:00 2001
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Thu, 7 Sep 2017 14:08:34 +0800
Subject: [PATCH 11/11] ip_tunnel: fix setting ttl and tos value in collect_md
 mode

[ Upstream commit 0f693f1995cf002432b70f43ce73f79bf8d0b6c9 ]

ttl and tos variables are declared and assigned, but are not used in
iptunnel_xmit() function.

Fixes: cfc7381b3002 ("ip_tunnel: add collect_md mode to IPIP tunnel")
Cc: Alexei Starovoitov <ast@fb.com>
Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_tunnel.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 129d1a3616f8..e1856bfa753d 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -618,8 +618,8 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto)
 		ip_rt_put(rt);
 		goto tx_dropped;
 	}
-	iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, proto, key->tos,
-		      key->ttl, df, !net_eq(tunnel->net, dev_net(dev)));
+	iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, proto, tos, ttl,
+		      df, !net_eq(tunnel->net, dev_net(dev)));
 	return;
 tx_error:
 	dev->stats.tx_errors++;
-- 
2.13.5

Re: [PATCHES] Networking

[Greg KH]

On Thu, Sep 14, 2017 at 09:57:40PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.9, v4.12, and
> v4.13 -stable, respectively.

Many thanks for these, all now queued up.

No need to worry about 4.12 anymore, I'll only be doing one more release
of it.

thanks,

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 73 bytes --]


Please queue up the following bug fixes for 4.13.x -stable.

Thank you!

[-- Attachment #2: net_413.mbox --]
[-- Type: Application/Octet-Stream, Size: 117776 bytes --]

From ad9b873b67326e3792e215a79cf757ef1db4725d Mon Sep 17 00:00:00 2001
From: Arkadi Sharshevsky <arkadis@mellanox.com>
Date: Mon, 11 Sep 2017 09:42:26 +0200
Subject: [PATCH 01/48] mlxsw: spectrum: Fix EEPROM access in case of SFP/SFP+

[ Upstream commit 4400081b631af69abc63cea3352680e3d85e0c39 ]

The current code does not handle correctly the access to the upper page
in case of SFP/SFP+ EEPROM. In that case the offset should be local
and the I2C address should be changed.

Fixes: 2ea109039cd3 ("mlxsw: spectrum: Add support for access cable info via ethtool")
Reported-by: Florian Klink <flokli@flokli.de>
Signed-off-by: Arkadi Sharshevsky <arkadis@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index c6a3e61b53bd..aca4ca18608d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -2519,7 +2519,9 @@ static int mlxsw_sp_flash_device(struct net_device *dev,
 	return err;
 }
 
-#define MLXSW_SP_QSFP_I2C_ADDR 0x50
+#define MLXSW_SP_I2C_ADDR_LOW 0x50
+#define MLXSW_SP_I2C_ADDR_HIGH 0x51
+#define MLXSW_SP_EEPROM_PAGE_LENGTH 256
 
 static int mlxsw_sp_query_module_eeprom(struct mlxsw_sp_port *mlxsw_sp_port,
 					u16 offset, u16 size, void *data,
@@ -2528,12 +2530,25 @@ static int mlxsw_sp_query_module_eeprom(struct mlxsw_sp_port *mlxsw_sp_port,
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	char eeprom_tmp[MLXSW_SP_REG_MCIA_EEPROM_SIZE];
 	char mcia_pl[MLXSW_REG_MCIA_LEN];
+	u16 i2c_addr;
 	int status;
 	int err;
 
 	size = min_t(u16, size, MLXSW_SP_REG_MCIA_EEPROM_SIZE);
+
+	if (offset < MLXSW_SP_EEPROM_PAGE_LENGTH &&
+	    offset + size > MLXSW_SP_EEPROM_PAGE_LENGTH)
+		/* Cross pages read, read until offset 256 in low page */
+		size = MLXSW_SP_EEPROM_PAGE_LENGTH - offset;
+
+	i2c_addr = MLXSW_SP_I2C_ADDR_LOW;
+	if (offset >= MLXSW_SP_EEPROM_PAGE_LENGTH) {
+		i2c_addr = MLXSW_SP_I2C_ADDR_HIGH;
+		offset -= MLXSW_SP_EEPROM_PAGE_LENGTH;
+	}
+
 	mlxsw_reg_mcia_pack(mcia_pl, mlxsw_sp_port->mapping.module,
-			    0, 0, offset, size, MLXSW_SP_QSFP_I2C_ADDR);
+			    0, 0, offset, size, i2c_addr);
 
 	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(mcia), mcia_pl);
 	if (err)
-- 
2.13.6


From 0aba2365a43460a00446ed4e204ce159f8749878 Mon Sep 17 00:00:00 2001
From: Kosuke Tatsukawa <tatsu@ab.jp.nec.com>
Date: Wed, 6 Sep 2017 22:47:59 +0000
Subject: [PATCH 02/48] net: bonding: Fix transmit load balancing in
 balance-alb mode if specified by sysfs

[ Upstream commit c6644d07eff6588b2dedf881279fb0d1c7783970 ]

Commit cbf5ecb30560 ("net: bonding: Fix transmit load balancing in
balance-alb mode") tried to fix transmit dynamic load balancing in
balance-alb mode, which wasn't working after commit 8b426dc54cf4
("bonding: remove hardcoded value").

It turned out that my previous patch only fixed the case when
balance-alb was specified as bonding module parameter, and not when
balance-alb mode was set using /sys/class/net/*/bonding/mode (the most
common usage).  In the latter case, tlb_dynamic_lb was set up according
to the default mode of the bonding interface, which happens to be
balance-rr.

This additional patch addresses this issue by setting up tlb_dynamic_lb
to 1 if "mode" is set to balance-alb through the sysfs interface.

I didn't add code to change tlb_balance_lb back to the default value for
other modes, because "mode" is usually set up only once during
initialization, and it's not worthwhile to change the static variable
bonding_defaults in bond_main.c to a global variable just for this
purpose.

Commit 8b426dc54cf4 also changes the value of tlb_dynamic_lb for
balance-tlb mode if it is set up using the sysfs interface.  I didn't
change that behavior, because the value of tlb_balance_lb can be changed
using the sysfs interface for balance-tlb, and I didn't like changing
the default value back and forth for balance-tlb.

As for balance-alb, /sys/class/net/*/bonding/tlb_balance_lb cannot be
written to.  However, I think balance-alb with tlb_dynamic_lb set to 0
is not an intended usage, so there is little use making it writable at
this moment.

Fixes: 8b426dc54cf4 ("bonding: remove hardcoded value")
Reported-by: Reinis Rozitis <r@roze.lv>
Signed-off-by: Kosuke Tatsukawa <tatsu@ab.jp.nec.com>
Cc: stable@vger.kernel.org  # v4.12+
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Acked-by: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_options.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index a12d603d41c6..5931aa2fe997 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -754,6 +754,9 @@ static int bond_option_mode_set(struct bonding *bond,
 			   bond->params.miimon);
 	}
 
+	if (newval->value == BOND_MODE_ALB)
+		bond->params.tlb_dynamic_lb = 1;
+
 	/* don't cache arp_validate between modes */
 	bond->params.arp_validate = BOND_ARP_VALIDATE_NONE;
 	bond->params.mode = newval->value;
-- 
2.13.6


From a6d2afa51a687238c1ea3ff246bf28727be1635f Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Mon, 11 Sep 2017 21:56:20 +0200
Subject: [PATCH 03/48] openvswitch: Fix an error handling path in
 'ovs_nla_init_match_and_action()'

[ Upstream commit 5829e62ac17a40ab08c1b905565604a4b5fa7af6 ]

All other error handling paths in this function go through the 'error'
label. This one should do the same.

Fixes: 9cc9a5cb176c ("datapath: Avoid using stack larger than 1024.")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/datapath.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 6b44fe405282..294444bb075c 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -1126,7 +1126,8 @@ static int ovs_nla_init_match_and_action(struct net *net,
 		if (!a[OVS_FLOW_ATTR_KEY]) {
 			OVS_NLERR(log,
 				  "Flow key attribute not present in set flow.");
-			return -EINVAL;
+			error = -EINVAL;
+			goto error;
 		}
 
 		*acts = get_flow_actions(net, a[OVS_FLOW_ATTR_ACTIONS], key,
-- 
2.13.6


From adcb4b0d10d636291a573ee1ff656266efe25453 Mon Sep 17 00:00:00 2001
From: Yuval Mintz <yuvalm@mellanox.com>
Date: Tue, 12 Sep 2017 08:50:53 +0200
Subject: [PATCH 04/48] mlxsw: spectrum: Prevent mirred-related crash on
 removal

[ Upstream commit 6399ebcccffa12e65bc15eda039d37673264ebce ]

When removing the offloading of mirred actions under
matchall classifiers, mlxsw would find the destination port
associated with the offloaded action and utilize it for undoing
the configuration.

Depending on the order by which ports are removed, it's possible that
the destination port would get removed before the source port.
In such a scenario, when actions would be flushed for the source port
mlxsw would perform an illegal dereference as the destination port is
no longer listed.

Since the only item necessary for undoing the configuration on the
destination side is the port-id and that in turn is already maintained
by mlxsw on the source-port, simply stop trying to access the
destination port and use the port-id directly instead.

Fixes: 763b4b70af ("mlxsw: spectrum: Add support in matchall mirror TC offloading")
Signed-off-by: Yuval Mintz <yuvalm@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index aca4ca18608d..73390f90b581 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -572,15 +572,14 @@ static void mlxsw_sp_span_entry_destroy(struct mlxsw_sp *mlxsw_sp,
 }
 
 static struct mlxsw_sp_span_entry *
-mlxsw_sp_span_entry_find(struct mlxsw_sp_port *port)
+mlxsw_sp_span_entry_find(struct mlxsw_sp *mlxsw_sp, u8 local_port)
 {
-	struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp;
 	int i;
 
 	for (i = 0; i < mlxsw_sp->span.entries_count; i++) {
 		struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i];
 
-		if (curr->used && curr->local_port == port->local_port)
+		if (curr->used && curr->local_port == local_port)
 			return curr;
 	}
 	return NULL;
@@ -591,7 +590,8 @@ static struct mlxsw_sp_span_entry
 {
 	struct mlxsw_sp_span_entry *span_entry;
 
-	span_entry = mlxsw_sp_span_entry_find(port);
+	span_entry = mlxsw_sp_span_entry_find(port->mlxsw_sp,
+					      port->local_port);
 	if (span_entry) {
 		/* Already exists, just take a reference */
 		span_entry->ref_count++;
@@ -780,12 +780,13 @@ static int mlxsw_sp_span_mirror_add(struct mlxsw_sp_port *from,
 }
 
 static void mlxsw_sp_span_mirror_remove(struct mlxsw_sp_port *from,
-					struct mlxsw_sp_port *to,
+					u8 destination_port,
 					enum mlxsw_sp_span_type type)
 {
 	struct mlxsw_sp_span_entry *span_entry;
 
-	span_entry = mlxsw_sp_span_entry_find(to);
+	span_entry = mlxsw_sp_span_entry_find(from->mlxsw_sp,
+					      destination_port);
 	if (!span_entry) {
 		netdev_err(from->dev, "no span entry found\n");
 		return;
@@ -1560,14 +1561,12 @@ static void
 mlxsw_sp_port_del_cls_matchall_mirror(struct mlxsw_sp_port *mlxsw_sp_port,
 				      struct mlxsw_sp_port_mall_mirror_tc_entry *mirror)
 {
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	enum mlxsw_sp_span_type span_type;
-	struct mlxsw_sp_port *to_port;
 
-	to_port = mlxsw_sp->ports[mirror->to_local_port];
 	span_type = mirror->ingress ?
 			MLXSW_SP_SPAN_INGRESS : MLXSW_SP_SPAN_EGRESS;
-	mlxsw_sp_span_mirror_remove(mlxsw_sp_port, to_port, span_type);
+	mlxsw_sp_span_mirror_remove(mlxsw_sp_port, mirror->to_local_port,
+				    span_type);
 }
 
 static int
-- 
2.13.6


From f56015c59b3b5ba40d972751a9d1280ce2efc4ee Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Tue, 12 Sep 2017 15:10:05 +0300
Subject: [PATCH 05/48] net: bonding: fix tlb_dynamic_lb default value

[ Upstream commit f13ad104b4e886a03e75f130daf579ef9bf33dfc ]

Commit 8b426dc54cf4 ("bonding: remove hardcoded value") changed the
default value for tlb_dynamic_lb which lead to either broken ALB mode
(since tlb_dynamic_lb can be changed only in TLB) or setting TLB mode
with tlb_dynamic_lb equal to 0.
The first issue was recently fixed by setting tlb_dynamic_lb to 1 always
when switching to ALB mode, but the default value is still wrong and
we'll enter TLB mode with tlb_dynamic_lb equal to 0 if the mode is
changed via netlink or sysfs. In order to restore the previous behaviour
and default value simply remove the mode check around the default param
initialization for tlb_dynamic_lb which will always set it to 1 as
before.

Fixes: 8b426dc54cf4 ("bonding: remove hardcoded value")
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Acked-by: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 17 +++++++----------
 1 file changed, 7 insertions(+), 10 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index fc63992ab0e0..c99dc59d729b 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -4289,7 +4289,7 @@ static int bond_check_params(struct bond_params *params)
 	int bond_mode	= BOND_MODE_ROUNDROBIN;
 	int xmit_hashtype = BOND_XMIT_POLICY_LAYER2;
 	int lacp_fast = 0;
-	int tlb_dynamic_lb = 0;
+	int tlb_dynamic_lb;
 
 	/* Convert string parameters. */
 	if (mode) {
@@ -4601,16 +4601,13 @@ static int bond_check_params(struct bond_params *params)
 	}
 	ad_user_port_key = valptr->value;
 
-	if ((bond_mode == BOND_MODE_TLB) || (bond_mode == BOND_MODE_ALB)) {
-		bond_opt_initstr(&newval, "default");
-		valptr = bond_opt_parse(bond_opt_get(BOND_OPT_TLB_DYNAMIC_LB),
-					&newval);
-		if (!valptr) {
-			pr_err("Error: No tlb_dynamic_lb default value");
-			return -EINVAL;
-		}
-		tlb_dynamic_lb = valptr->value;
+	bond_opt_initstr(&newval, "default");
+	valptr = bond_opt_parse(bond_opt_get(BOND_OPT_TLB_DYNAMIC_LB), &newval);
+	if (!valptr) {
+		pr_err("Error: No tlb_dynamic_lb default value");
+		return -EINVAL;
 	}
+	tlb_dynamic_lb = valptr->value;
 
 	if (lp_interval == 0) {
 		pr_warn("Warning: ip_interval must be between 1 and %d, so it was reset to %d\n",
-- 
2.13.6


From 61f9fd29df7cb28dcf00243a19880e383085625b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 13 Sep 2017 11:16:45 -0700
Subject: [PATCH 06/48] net_sched: gen_estimator: fix scaling error in
 bytes/packets samples

[ Upstream commit ca558e185972d8ecd308760abf972f5d408bcff0 ]

Denys reported wrong rate estimations with HTB classes.

It appears the bug was added in linux-4.10, since my tests
where using intervals of one second only.

HTB using 4 sec default rate estimators, reported rates
were 4x higher.

We need to properly scale the bytes/packets samples before
integrating them in EWMA.

Tested:
 echo 1 >/sys/module/sch_htb/parameters/htb_rate_est

 Setup HTB with one class with a rate/cail of 5Gbit

 Generate traffic on this class

 tc -s -d cl sh dev eth0 classid 7002:11
class htb 7002:11 parent 7002:1 prio 5 quantum 200000 rate 5Gbit ceil
5Gbit linklayer ethernet burst 80000b/1 mpu 0b cburst 80000b/1 mpu 0b
level 0 rate_handle 1
 Sent 1488215421648 bytes 982969243 pkt (dropped 0, overlimits 0
requeues 0)
 rate 5Gbit 412814pps backlog 136260b 2p requeues 0
 TCP pkts/rtx 982969327/45 bytes 1488215557414/68130
 lended: 22732826 borrowed: 0 giants: 0
 tokens: -1684 ctokens: -1684

Fixes: 1c0d32fde5bd ("net_sched: gen_estimator: complete rewrite of rate estimators")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Denys Fedoryshchenko <nuclearcat@nuclearcat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/gen_estimator.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c
index 0385dece1f6f..7c1ffd6f9501 100644
--- a/net/core/gen_estimator.c
+++ b/net/core/gen_estimator.c
@@ -83,10 +83,10 @@ static void est_timer(unsigned long arg)
 	u64 rate, brate;
 
 	est_fetch_counters(est, &b);
-	brate = (b.bytes - est->last_bytes) << (8 - est->ewma_log);
+	brate = (b.bytes - est->last_bytes) << (10 - est->ewma_log - est->intvl_log);
 	brate -= (est->avbps >> est->ewma_log);
 
-	rate = (u64)(b.packets - est->last_packets) << (8 - est->ewma_log);
+	rate = (u64)(b.packets - est->last_packets) << (10 - est->ewma_log - est->intvl_log);
 	rate -= (est->avpps >> est->ewma_log);
 
 	write_seqcount_begin(&est->seq);
-- 
2.13.6


From 0fd4b36c82c70e5137a7e48c28be92362880f50a Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 13 Sep 2017 17:32:37 +0200
Subject: [PATCH 07/48] net: sched: fix use-after-free in tcf_action_destroy
 and tcf_del_walker

[ Upstream commit 255cd50f207ae8ec7b22663246c833407744e634 ]

Recent commit d7fb60b9cafb ("net_sched: get rid of tcfa_rcu") removed
freeing in call_rcu, which changed already existing hard-to-hit
race condition into 100% hit:

[  598.599825] BUG: unable to handle kernel NULL pointer dereference at 0000000000000030
[  598.607782] IP: tcf_action_destroy+0xc0/0x140

Or:

[   40.858924] BUG: unable to handle kernel NULL pointer dereference at 0000000000000030
[   40.862840] IP: tcf_generic_walker+0x534/0x820

Fix this by storing the ops and use them directly for module_put call.

Fixes: a85a970af265 ("net_sched: move tc_action into tcf_common")
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_api.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index f2e9ed34a963..0c5dbb172437 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -174,7 +174,7 @@ static int tcf_del_walker(struct tcf_hashinfo *hinfo, struct sk_buff *skb,
 		hlist_for_each_entry_safe(p, n, head, tcfa_head) {
 			ret = __tcf_hash_release(p, false, true);
 			if (ret == ACT_P_DELETED) {
-				module_put(p->ops->owner);
+				module_put(ops->owner);
 				n_i++;
 			} else if (ret < 0)
 				goto nla_put_failure;
@@ -506,13 +506,15 @@ EXPORT_SYMBOL(tcf_action_exec);
 
 int tcf_action_destroy(struct list_head *actions, int bind)
 {
+	const struct tc_action_ops *ops;
 	struct tc_action *a, *tmp;
 	int ret = 0;
 
 	list_for_each_entry_safe(a, tmp, actions, list) {
+		ops = a->ops;
 		ret = __tcf_hash_release(a, bind, true);
 		if (ret == ACT_P_DELETED)
-			module_put(a->ops->owner);
+			module_put(ops->owner);
 		else if (ret < 0)
 			return ret;
 	}
-- 
2.13.6


From b94d684780fe4d0490d770b7850dc1bcd0d0a104 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Thu, 14 Sep 2017 02:00:54 +0300
Subject: [PATCH 08/48] sctp: potential read out of bounds in
 sctp_ulpevent_type_enabled()

[ Upstream commit fa5f7b51fc3080c2b195fa87c7eca7c05e56f673 ]

This code causes a static checker warning because Smatch doesn't trust
anything that comes from skb->data.  I've reviewed this code and I do
think skb->data can be controlled by the user here.

The sctp_event_subscribe struct has 13 __u8 fields and we want to see
if ours is non-zero.  sn_type can be any value in the 0-USHRT_MAX range.
We're subtracting SCTP_SN_TYPE_BASE which is 1 << 15 so we could read
either before the start of the struct or after the end.

This is a very old bug and it's surprising that it would go undetected
for so long but my theory is that it just doesn't have a big impact so
it would be hard to notice.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/ulpevent.h | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/include/net/sctp/ulpevent.h b/include/net/sctp/ulpevent.h
index 1060494ac230..b8c86ec1a8f5 100644
--- a/include/net/sctp/ulpevent.h
+++ b/include/net/sctp/ulpevent.h
@@ -153,8 +153,12 @@ __u16 sctp_ulpevent_get_notification_type(const struct sctp_ulpevent *event);
 static inline int sctp_ulpevent_type_enabled(__u16 sn_type,
 					     struct sctp_event_subscribe *mask)
 {
+	int offset = sn_type - SCTP_SN_TYPE_BASE;
 	char *amask = (char *) mask;
-	return amask[sn_type - SCTP_SN_TYPE_BASE];
+
+	if (offset >= sizeof(struct sctp_event_subscribe))
+		return 0;
+	return amask[offset];
 }
 
 /* Given an event subscription, is this event enabled? */
-- 
2.13.6


From a985dabeebd385b24597e4d1aa9221c1704d7ee5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@googl.com>
Date: Wed, 13 Sep 2017 20:30:39 -0700
Subject: [PATCH 09/48] tcp: update skb->skb_mstamp more carefully

[ Upstream commit 8c72c65b426b47b3c166a8fef0d8927fe5e8a28d ]

liujian reported a problem in TCP_USER_TIMEOUT processing with a patch
in tcp_probe_timer() :
      https://www.spinics.net/lists/netdev/msg454496.html

After investigations, the root cause of the problem is that we update
skb->skb_mstamp of skbs in write queue, even if the attempt to send a
clone or copy of it failed. One reason being a routing problem.

This patch prevents this, solving liujian issue.

It also removes a potential RTT miscalculation, since
__tcp_retransmit_skb() is not OR-ing TCP_SKB_CB(skb)->sacked with
TCPCB_EVER_RETRANS if a failure happens, but skb->skb_mstamp has
been changed.

A future ACK would then lead to a very small RTT sample and min_rtt
would then be lowered to this too small value.

Tested:

# cat user_timeout.pkt
--local_ip=192.168.102.64

    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
   +0 bind(3, ..., ...) = 0
   +0 listen(3, 1) = 0

   +0 `ifconfig tun0 192.168.102.64/16; ip ro add 192.0.2.1 dev tun0`

   +0 < S 0:0(0) win 0 <mss 1460>
   +0 > S. 0:0(0) ack 1 <mss 1460>

  +.1 < . 1:1(0) ack 1 win 65530
   +0 accept(3, ..., ...) = 4

   +0 setsockopt(4, SOL_TCP, TCP_USER_TIMEOUT, [3000], 4) = 0
   +0 write(4, ..., 24) = 24
   +0 > P. 1:25(24) ack 1 win 29200
   +.1 < . 1:1(0) ack 25 win 65530

//change the ipaddress
   +1 `ifconfig tun0 192.168.0.10/16`

   +1 write(4, ..., 24) = 24
   +1 write(4, ..., 24) = 24
   +1 write(4, ..., 24) = 24
   +1 write(4, ..., 24) = 24

   +0 `ifconfig tun0 192.168.102.64/16`
   +0 < . 1:2(1) ack 25 win 65530
   +0 `ifconfig tun0 192.168.0.10/16`

   +3 write(4, ..., 24) = -1

# ./packetdrill user_timeout.pkt

Signed-off-by: Eric Dumazet <edumazet@googl.com>
Reported-by: liujian <liujian56@huawei.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index b7661a68d498..c99905666c33 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -991,6 +991,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	struct tcp_skb_cb *tcb;
 	struct tcp_out_options opts;
 	unsigned int tcp_options_size, tcp_header_size;
+	struct sk_buff *oskb = NULL;
 	struct tcp_md5sig_key *md5;
 	struct tcphdr *th;
 	int err;
@@ -998,12 +999,12 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	BUG_ON(!skb || !tcp_skb_pcount(skb));
 	tp = tcp_sk(sk);
 
-	skb->skb_mstamp = tp->tcp_mstamp;
 	if (clone_it) {
 		TCP_SKB_CB(skb)->tx.in_flight = TCP_SKB_CB(skb)->end_seq
 			- tp->snd_una;
 		tcp_rate_skb_sent(sk, skb);
 
+		oskb = skb;
 		if (unlikely(skb_cloned(skb)))
 			skb = pskb_copy(skb, gfp_mask);
 		else
@@ -1011,6 +1012,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 		if (unlikely(!skb))
 			return -ENOBUFS;
 	}
+	skb->skb_mstamp = tp->tcp_mstamp;
 
 	inet = inet_sk(sk);
 	tcb = TCP_SKB_CB(skb);
@@ -1122,12 +1124,14 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 
 	err = icsk->icsk_af_ops->queue_xmit(sk, skb, &inet->cork.fl);
 
-	if (likely(err <= 0))
-		return err;
-
-	tcp_enter_cwr(sk);
+	if (unlikely(err > 0)) {
+		tcp_enter_cwr(sk);
+		err = net_xmit_eval(err);
+	}
+	if (!err && oskb)
+		oskb->skb_mstamp = tp->tcp_mstamp;
 
-	return net_xmit_eval(err);
+	return err;
 }
 
 /* This routine just queues the buffer for sending.
@@ -2866,10 +2870,11 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 		     skb_headroom(skb) >= 0xFFFF)) {
 		struct sk_buff *nskb;
 
-		skb->skb_mstamp = tp->tcp_mstamp;
 		nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC);
 		err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
 			     -ENOBUFS;
+		if (!err)
+			skb->skb_mstamp = tp->tcp_mstamp;
 	} else {
 		err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
 	}
-- 
2.13.6


From 682b584f990d971c0f916d8a63bd63c3dc5fe1d1 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Fri, 15 Sep 2017 14:37:38 +0100
Subject: [PATCH 10/48] bpf/verifier: reject BPF_ALU64|BPF_END

[ Upstream commit e67b8a685c7c984e834e3181ef4619cd7025a136 ]

Neither ___bpf_prog_run nor the JITs accept it.
Also adds a new test case.

Fixes: 17a5267067f3 ("bpf: verifier (add verifier core)")
Signed-off-by: Edward Cree <ecree@solarflare.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c                       |  3 ++-
 tools/testing/selftests/bpf/test_verifier.c | 16 ++++++++++++++++
 2 files changed, 18 insertions(+), 1 deletion(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 664d93972373..3940019b9740 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1978,7 +1978,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 			}
 		} else {
 			if (insn->src_reg != BPF_REG_0 || insn->off != 0 ||
-			    (insn->imm != 16 && insn->imm != 32 && insn->imm != 64)) {
+			    (insn->imm != 16 && insn->imm != 32 && insn->imm != 64) ||
+			    BPF_CLASS(insn->code) == BPF_ALU64) {
 				verbose("BPF_END uses reserved fields\n");
 				return -EINVAL;
 			}
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index d3ed7324105e..48c145eeeaf7 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -6009,6 +6009,22 @@ static struct bpf_test tests[] = {
 		.result = REJECT,
 		.result_unpriv = REJECT,
 	},
+	{
+		"invalid 64-bit BPF_END",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_0, 0),
+			{
+				.code  = BPF_ALU64 | BPF_END | BPF_TO_LE,
+				.dst_reg = BPF_REG_0,
+				.src_reg = 0,
+				.off   = 0,
+				.imm   = 32,
+			},
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "BPF_END uses reserved fields",
+		.result = REJECT,
+	},
 };
 
 static int probe_filter_length(const struct bpf_insn *fp)
-- 
2.13.6


From 06d9107500f602e23e51f61b0b3d431e76d44159 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 15 Sep 2017 16:47:42 -0700
Subject: [PATCH 11/48] tcp: fix data delivery rate

[ Upstream commit fc22579917eb7e13433448a342f1cb1592920940 ]

Now skb->mstamp_skb is updated later, we also need to call
tcp_rate_skb_sent() after the update is done.

Fixes: 8c72c65b426b ("tcp: update skb->skb_mstamp more carefully")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index c99905666c33..292857be98ba 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1002,8 +1002,6 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	if (clone_it) {
 		TCP_SKB_CB(skb)->tx.in_flight = TCP_SKB_CB(skb)->end_seq
 			- tp->snd_una;
-		tcp_rate_skb_sent(sk, skb);
-
 		oskb = skb;
 		if (unlikely(skb_cloned(skb)))
 			skb = pskb_copy(skb, gfp_mask);
@@ -1128,9 +1126,10 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 		tcp_enter_cwr(sk);
 		err = net_xmit_eval(err);
 	}
-	if (!err && oskb)
+	if (!err && oskb) {
 		oskb->skb_mstamp = tp->tcp_mstamp;
-
+		tcp_rate_skb_sent(sk, oskb);
+	}
 	return err;
 }
 
-- 
2.13.6


From a2146a465461dd1e935519ef35dd9213d3bae156 Mon Sep 17 00:00:00 2001
From: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Date: Wed, 13 Sep 2017 19:30:51 -0600
Subject: [PATCH 12/48] udpv6: Fix the checksum computation when HW checksum
 does not apply

[ Upstream commit 63ecc3d9436f8012e49dc846d6cb0a85a3433517 ]

While trying an ESP transport mode encryption for UDPv6 packets of
datagram size 1436 with MTU 1500, checksum error was observed in
the secondary fragment.

This error occurs due to the UDP payload checksum being missed out
when computing the full checksum for these packets in
udp6_hwcsum_outgoing().

Fixes: d39d938c8228 ("ipv6: Introduce udpv6_send_skb()")
Signed-off-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/udp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index d6886228e1d0..30b4d55e88f3 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1011,6 +1011,7 @@ static void udp6_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb,
 		 */
 		offset = skb_transport_offset(skb);
 		skb->csum = skb_checksum(skb, offset, skb->len - offset, 0);
+		csum = skb->csum;
 
 		skb->ip_summed = CHECKSUM_NONE;
 
-- 
2.13.6


From 1a35a7d6db4e673f740795d9d945173200bad303 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Fri, 15 Sep 2017 12:00:07 +0800
Subject: [PATCH 13/48] ip6_gre: skb_push ipv6hdr before packing the header in
 ip6gre_header

[ Upstream commit 76cc0d3282d4b933fa144fa41fbc5318e0fdca24 ]

Now in ip6gre_header before packing the ipv6 header, it skb_push t->hlen
which only includes encap_hlen + tun_hlen. It means greh and inner header
would be over written by ipv6 stuff and ipv6h might have no chance to set
up.

Jianlin found this issue when using remote any on ip6_gre, the packets he
captured on gre dev are truncated:

22:50:26.210866 Out ethertype IPv6 (0x86dd), length 120: truncated-ip6 -\
8128 bytes missing!(flowlabel 0x92f40, hlim 0, next-header Options (0)  \
payload length: 8192) ::1:2000:0 > ::1:0:86dd: HBH [trunc] ip-proto-128 \
8184

It should also skb_push ipv6hdr so that ipv6h points to the right position
to set ipv6 stuff up.

This patch is to skb_push hlen + sizeof(*ipv6h) and also fix some indents
in ip6gre_header.

Fixes: c12b395a4664 ("gre: Support GRE over IPv6")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index b7a72d409334..20f66f4c9460 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -940,24 +940,25 @@ static int ip6gre_tunnel_ioctl(struct net_device *dev,
 }
 
 static int ip6gre_header(struct sk_buff *skb, struct net_device *dev,
-			unsigned short type,
-			const void *daddr, const void *saddr, unsigned int len)
+			 unsigned short type, const void *daddr,
+			 const void *saddr, unsigned int len)
 {
 	struct ip6_tnl *t = netdev_priv(dev);
-	struct ipv6hdr *ipv6h = skb_push(skb, t->hlen);
-	__be16 *p = (__be16 *)(ipv6h+1);
+	struct ipv6hdr *ipv6h;
+	__be16 *p;
 
-	ip6_flow_hdr(ipv6h, 0,
-		     ip6_make_flowlabel(dev_net(dev), skb,
-					t->fl.u.ip6.flowlabel, true,
-					&t->fl.u.ip6));
+	ipv6h = skb_push(skb, t->hlen + sizeof(*ipv6h));
+	ip6_flow_hdr(ipv6h, 0, ip6_make_flowlabel(dev_net(dev), skb,
+						  t->fl.u.ip6.flowlabel,
+						  true, &t->fl.u.ip6));
 	ipv6h->hop_limit = t->parms.hop_limit;
 	ipv6h->nexthdr = NEXTHDR_GRE;
 	ipv6h->saddr = t->parms.laddr;
 	ipv6h->daddr = t->parms.raddr;
 
-	p[0]		= t->parms.o_flags;
-	p[1]		= htons(type);
+	p = (__be16 *)(ipv6h + 1);
+	p[0] = t->parms.o_flags;
+	p[1] = htons(type);
 
 	/*
 	 *	Set the source hardware address.
-- 
2.13.6


From e04a903adf82da446e9deeab7a0ecd71ab42d91f Mon Sep 17 00:00:00 2001
From: Fahad Kunnathadi <fahad.kunnathadi@dexceldesigns.com>
Date: Fri, 15 Sep 2017 12:01:58 +0530
Subject: [PATCH 14/48] net: phy: Fix mask value write on gmii2rgmii converter
 speed register

[ Upstream commit f2654a4781318dc7ab8d6cde66f1fa39eab980a9 ]

To clear Speed Selection in MDIO control register(0x10),
ie, clear bits 6 and 13 to zero while keeping other bits same.
Before AND operation,The Mask value has to be perform with bitwise NOT
operation (ie, ~ operator)

This patch clears current speed selection before writing the
new speed settings to gmii2rgmii converter

Fixes: f411a6160bd4 ("net: phy: Add gmiitorgmii converter support")

Signed-off-by: Fahad Kunnathadi <fahad.kunnathadi@dexceldesigns.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/xilinx_gmii2rgmii.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/xilinx_gmii2rgmii.c b/drivers/net/phy/xilinx_gmii2rgmii.c
index d15dd3938ba8..2e5150b0b8d5 100644
--- a/drivers/net/phy/xilinx_gmii2rgmii.c
+++ b/drivers/net/phy/xilinx_gmii2rgmii.c
@@ -44,7 +44,7 @@ static int xgmiitorgmii_read_status(struct phy_device *phydev)
 	priv->phy_drv->read_status(phydev);
 
 	val = mdiobus_read(phydev->mdio.bus, priv->addr, XILINX_GMII2RGMII_REG);
-	val &= XILINX_GMII2RGMII_SPEED_MASK;
+	val &= ~XILINX_GMII2RGMII_SPEED_MASK;
 
 	if (phydev->speed == SPEED_1000)
 		val |= BMCR_SPEED1000;
-- 
2.13.6


From 44a83e7bb963af3e014c673608409b47c0b42d37 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Fri, 15 Sep 2017 15:58:33 +0800
Subject: [PATCH 15/48] ip6_tunnel: do not allow loading ip6_tunnel if ipv6 is
 disabled in cmdline

[ Upstream commit 8c22dab03ad072e45060c299c70d02a4f6fc4aab ]

If ipv6 has been disabled from cmdline since kernel started, it makes
no sense to allow users to create any ip6 tunnel. Otherwise, it could
some potential problem.

Jianlin found a kernel crash caused by this in ip6_gre when he set
ipv6.disable=1 in grub:

[  209.588865] Unable to handle kernel paging request for data at address 0x00000080
[  209.588872] Faulting instruction address: 0xc000000000a3aa6c
[  209.588879] Oops: Kernel access of bad area, sig: 11 [#1]
[  209.589062] NIP [c000000000a3aa6c] fib_rules_lookup+0x4c/0x260
[  209.589071] LR [c000000000b9ad90] fib6_rule_lookup+0x50/0xb0
[  209.589076] Call Trace:
[  209.589097] fib6_rule_lookup+0x50/0xb0
[  209.589106] rt6_lookup+0xc4/0x110
[  209.589116] ip6gre_tnl_link_config+0x214/0x2f0 [ip6_gre]
[  209.589125] ip6gre_newlink+0x138/0x3a0 [ip6_gre]
[  209.589134] rtnl_newlink+0x798/0xb80
[  209.589142] rtnetlink_rcv_msg+0xec/0x390
[  209.589151] netlink_rcv_skb+0x138/0x150
[  209.589159] rtnetlink_rcv+0x48/0x70
[  209.589169] netlink_unicast+0x538/0x640
[  209.589175] netlink_sendmsg+0x40c/0x480
[  209.589184] ___sys_sendmsg+0x384/0x4e0
[  209.589194] SyS_sendmsg+0xd4/0x140
[  209.589201] SyS_socketcall+0x3e0/0x4f0
[  209.589209] system_call+0x38/0xe0

This patch is to return -EOPNOTSUPP in ip6_tunnel_init if ipv6 has been
disabled from cmdline.

Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 3a0ba2ae4b0f..98647402b339 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -2258,6 +2258,9 @@ static int __init ip6_tunnel_init(void)
 {
 	int  err;
 
+	if (!ipv6_mod_enabled())
+		return -EOPNOTSUPP;
+
 	err = register_pernet_device(&ip6_tnl_net_ops);
 	if (err < 0)
 		goto out_pernet;
-- 
2.13.6


From 7e748a4dd5776fc327ecd0dd421fadc0341a9058 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Sat, 16 Sep 2017 14:02:21 +0200
Subject: [PATCH 16/48] net/sched: cls_matchall: fix crash when used with
 classful qdisc

[ Upstream commit 3ff4cbec87da48b0ec1f7b6196607b034de0c680 ]

this script, edited from Linux Advanced Routing and Traffic Control guide

tc q a dev en0 root handle 1: htb default a
tc c a dev en0 parent 1:  classid 1:1 htb rate 6mbit burst 15k
tc c a dev en0 parent 1:1 classid 1:a htb rate 5mbit ceil 6mbit burst 15k
tc c a dev en0 parent 1:1 classid 1:b htb rate 1mbit ceil 6mbit burst 15k
tc f a dev en0 parent 1:0 prio 1 $clsname $clsargs classid 1:b
ping $address -c1
tc -s c s dev en0

classifies traffic to 1:b or 1:a, depending on whether the packet matches
or not the pattern $clsargs of filter $clsname. However, when $clsname is
'matchall', a systematic crash can be observed in htb_classify(). HTB and
classful qdiscs don't assign initial value to struct tcf_result, but then
they expect it to contain valid values after filters have been run. Thus,
current 'matchall' ignores the TCA_MATCHALL_CLASSID attribute, configured
by user, and makes HTB (and classful qdiscs) dereference random pointers.

By assigning head->res to *res in mall_classify(), before the actions are
invoked, we fix this crash and enable TCA_MATCHALL_CLASSID functionality,
that had no effect on 'matchall' classifier since its first introduction.

BugLink: https://bugzilla.redhat.com/show_bug.cgi?id=1460213
Reported-by: Jiri Benc <jbenc@redhat.com>
Fixes: b87f7936a932 ("net/sched: introduce Match-all classifier")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Yotam Gigi <yotamg@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_matchall.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index 9dc26c32cf32..d720f9376add 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -32,6 +32,7 @@ static int mall_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 	if (tc_skip_sw(head->flags))
 		return -1;
 
+	*res = head->res;
 	return tcf_exts_exec(skb, &head->exts, res);
 }
 
-- 
2.13.6


From 4f91c0d74d829b46a0e53d1483fa9146d923cc16 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 18 Sep 2017 13:03:43 -0700
Subject: [PATCH 17/48] 8139too: revisit napi_complete_done() usage
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 129c6cda2de2a8ac44fab096152469999b727faf ]

It seems we have to be more careful in napi_complete_done()
use. This patch is not a revert, as it seems we can
avoid bug that Ville reported by moving the napi_complete_done()
test in the spinlock section.

Many thanks to Ville for detective work and all tests.

Fixes: 617f01211baf ("8139too: use napi_complete_done()")
Reported-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Tested-by: Ville Syrjälä <ville.syrjala@linux.intel.com>

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/8139too.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c
index ca22f2898664..d24b47b8e0b2 100644
--- a/drivers/net/ethernet/realtek/8139too.c
+++ b/drivers/net/ethernet/realtek/8139too.c
@@ -2135,11 +2135,12 @@ static int rtl8139_poll(struct napi_struct *napi, int budget)
 	if (likely(RTL_R16(IntrStatus) & RxAckBits))
 		work_done += rtl8139_rx(dev, tp, budget);
 
-	if (work_done < budget && napi_complete_done(napi, work_done)) {
+	if (work_done < budget) {
 		unsigned long flags;
 
 		spin_lock_irqsave(&tp->lock, flags);
-		RTL_W16_F(IntrMask, rtl8139_intr_mask);
+		if (napi_complete_done(napi, work_done))
+			RTL_W16_F(IntrMask, rtl8139_intr_mask);
 		spin_unlock_irqrestore(&tp->lock, flags);
 	}
 	spin_unlock(&tp->rx_lock);
-- 
2.13.6


From 8f8c7f5a8fe1800bc84bd49fed27c4deb6f8b4a7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 19 Sep 2017 09:15:59 -0700
Subject: [PATCH 18/48] bpf: do not disable/enable BH in bpf_map_free_id()

[ Upstream commit 930651a75bf1ba6893a8b8475270664ebdb6cf4a ]

syzkaller reported following splat [1]

Since hard irq are disabled by the caller, bpf_map_free_id()
should not try to enable/disable BH.

Another solution would be to change htab_map_delete_elem() to
defer the free_htab_elem() call after
raw_spin_unlock_irqrestore(&b->lock, flags), but this might be not
enough to cover other code paths.

[1]
WARNING: CPU: 1 PID: 8052 at kernel/softirq.c:161 __local_bh_enable_ip
+0x1e/0x160 kernel/softirq.c:161
Kernel panic - not syncing: panic_on_warn set ...

CPU: 1 PID: 8052 Comm: syz-executor1 Not tainted 4.13.0-next-20170915+
#23
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:16 [inline]
 dump_stack+0x194/0x257 lib/dump_stack.c:52
 panic+0x1e4/0x417 kernel/panic.c:181
 __warn+0x1c4/0x1d9 kernel/panic.c:542
 report_bug+0x211/0x2d0 lib/bug.c:183
 fixup_bug+0x40/0x90 arch/x86/kernel/traps.c:178
 do_trap_no_signal arch/x86/kernel/traps.c:212 [inline]
 do_trap+0x260/0x390 arch/x86/kernel/traps.c:261
 do_error_trap+0x120/0x390 arch/x86/kernel/traps.c:298
 do_invalid_op+0x1b/0x20 arch/x86/kernel/traps.c:311
 invalid_op+0x18/0x20 arch/x86/entry/entry_64.S:905
RIP: 0010:__local_bh_enable_ip+0x1e/0x160 kernel/softirq.c:161
RSP: 0018:ffff8801cdcd7748 EFLAGS: 00010046
RAX: 0000000000000082 RBX: 0000000000000201 RCX: 0000000000000000
RDX: 1ffffffff0b5933c RSI: 0000000000000201 RDI: ffffffff85ac99e0
RBP: ffff8801cdcd7758 R08: ffffffff85b87158 R09: 1ffff10039b9aec6
R10: ffff8801c99f24c0 R11: 0000000000000002 R12: ffffffff817b0b47
R13: dffffc0000000000 R14: ffff8801cdcd77e8 R15: 0000000000000001
 __raw_spin_unlock_bh include/linux/spinlock_api_smp.h:176 [inline]
 _raw_spin_unlock_bh+0x30/0x40 kernel/locking/spinlock.c:207
 spin_unlock_bh include/linux/spinlock.h:361 [inline]
 bpf_map_free_id kernel/bpf/syscall.c:197 [inline]
 __bpf_map_put+0x267/0x320 kernel/bpf/syscall.c:227
 bpf_map_put+0x1a/0x20 kernel/bpf/syscall.c:235
 bpf_map_fd_put_ptr+0x15/0x20 kernel/bpf/map_in_map.c:96
 free_htab_elem+0xc3/0x1b0 kernel/bpf/hashtab.c:658
 htab_map_delete_elem+0x74d/0x970 kernel/bpf/hashtab.c:1063
 map_delete_elem kernel/bpf/syscall.c:633 [inline]
 SYSC_bpf kernel/bpf/syscall.c:1479 [inline]
 SyS_bpf+0x2188/0x46a0 kernel/bpf/syscall.c:1451
 entry_SYSCALL_64_fastpath+0x1f/0xbe

Fixes: f3f1c054c288 ("bpf: Introduce bpf_map ID")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Martin KaFai Lau <kafai@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/syscall.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 6c772adabad2..1939d91da1f8 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -144,15 +144,17 @@ static int bpf_map_alloc_id(struct bpf_map *map)
 
 static void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock)
 {
+	unsigned long flags;
+
 	if (do_idr_lock)
-		spin_lock_bh(&map_idr_lock);
+		spin_lock_irqsave(&map_idr_lock, flags);
 	else
 		__acquire(&map_idr_lock);
 
 	idr_remove(&map_idr, map->id);
 
 	if (do_idr_lock)
-		spin_unlock_bh(&map_idr_lock);
+		spin_unlock_irqrestore(&map_idr_lock, flags);
 	else
 		__release(&map_idr_lock);
 }
-- 
2.13.6


From 655bda45e9779a5ee11b7a13fbb6881dd1fe81aa Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 19 Sep 2017 10:05:57 -0700
Subject: [PATCH 19/48] tcp: fastopen: fix on syn-data transmit failure

[ Upstream commit b5b7db8d680464b1d631fd016f5e093419f0bfd9 ]

Our recent change exposed a bug in TCP Fastopen Client that syzkaller
found right away [1]

When we prepare skb with SYN+DATA, we attempt to transmit it,
and we update socket state as if the transmit was a success.

In socket RTX queue we have two skbs, one with the SYN alone,
and a second one containing the DATA.

When (malicious) ACK comes in, we now complain that second one had no
skb_mstamp.

The proper fix is to make sure that if the transmit failed, we do not
pretend we sent the DATA skb, and make it our send_head.

When 3WHS completes, we can now send the DATA right away, without having
to wait for a timeout.

[1]
WARNING: CPU: 0 PID: 100189 at net/ipv4/tcp_input.c:3117 tcp_clean_rtx_queue+0x2057/0x2ab0 net/ipv4/tcp_input.c:3117()

 WARN_ON_ONCE(last_ackt == 0);

Modules linked in:
CPU: 0 PID: 100189 Comm: syz-executor1 Not tainted
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
 0000000000000000 ffff8800b35cb1d8 ffffffff81cad00d 0000000000000000
 ffffffff828a4347 ffff88009f86c080 ffffffff8316eb20 0000000000000d7f
 ffff8800b35cb220 ffffffff812c33c2 ffff8800baad2440 00000009d46575c0
Call Trace:
 [<ffffffff81cad00d>] __dump_stack
 [<ffffffff81cad00d>] dump_stack+0xc1/0x124
 [<ffffffff812c33c2>] warn_slowpath_common+0xe2/0x150
 [<ffffffff812c361e>] warn_slowpath_null+0x2e/0x40
 [<ffffffff828a4347>] tcp_clean_rtx_queue+0x2057/0x2ab0 n
 [<ffffffff828ae6fd>] tcp_ack+0x151d/0x3930
 [<ffffffff828baa09>] tcp_rcv_state_process+0x1c69/0x4fd0
 [<ffffffff828efb7f>] tcp_v4_do_rcv+0x54f/0x7c0
 [<ffffffff8258aacb>] sk_backlog_rcv
 [<ffffffff8258aacb>] __release_sock+0x12b/0x3a0
 [<ffffffff8258ad9e>] release_sock+0x5e/0x1c0
 [<ffffffff8294a785>] inet_wait_for_connect
 [<ffffffff8294a785>] __inet_stream_connect+0x545/0xc50
 [<ffffffff82886f08>] tcp_sendmsg_fastopen
 [<ffffffff82886f08>] tcp_sendmsg+0x2298/0x35a0
 [<ffffffff82952515>] inet_sendmsg+0xe5/0x520
 [<ffffffff8257152f>] sock_sendmsg_nosec
 [<ffffffff8257152f>] sock_sendmsg+0xcf/0x110

Fixes: 8c72c65b426b ("tcp: update skb->skb_mstamp more carefully")
Fixes: 783237e8daf1 ("net-tcp: Fast Open client - sending SYN-data")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 292857be98ba..40f7c8ee9ba6 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3420,6 +3420,10 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 		goto done;
 	}
 
+	/* data was not sent, this is our new send_head */
+	sk->sk_send_head = syn_data;
+	tp->packets_out -= tcp_skb_pcount(syn_data);
+
 fallback:
 	/* Send a regular SYN with Fast Open cookie request option */
 	if (fo->cookie.len > 0)
@@ -3472,6 +3476,11 @@ int tcp_connect(struct sock *sk)
 	 */
 	tp->snd_nxt = tp->write_seq;
 	tp->pushed_seq = tp->write_seq;
+	buff = tcp_send_head(sk);
+	if (unlikely(buff)) {
+		tp->snd_nxt	= TCP_SKB_CB(buff)->seq;
+		tp->pushed_seq	= TCP_SKB_CB(buff)->seq;
+	}
 	TCP_INC_STATS(sock_net(sk), TCP_MIB_ACTIVEOPENS);
 
 	/* Timer for repeating the SYN until an answer. */
-- 
2.13.6


From 152fc7f6bd9adea602bc9863f31905a7eaddd18b Mon Sep 17 00:00:00 2001
From: Christian Lamparter <chunkeey@googlemail.com>
Date: Tue, 19 Sep 2017 19:35:18 +0200
Subject: [PATCH 20/48] net: emac: Fix napi poll list corruption

[ Upstream commit f55956065ec94e3e9371463d693a1029c4cc3007 ]

This patch is pretty much a carbon copy of
commit 3079c652141f ("caif: Fix napi poll list corruption")
with "caif" replaced by "emac".

The commit d75b1ade567f ("net: less interrupt masking in NAPI")
breaks emac.

It is now required that if the entire budget is consumed when poll
returns, the napi poll_list must remain empty.  However, like some
other drivers emac tries to do a last-ditch check and if there is
more work it will call napi_reschedule and then immediately process
some of this new work.  Should the entire budget be consumed while
processing such new work then we will violate the new caller
contract.

This patch fixes this by not touching any work when we reschedule
in emac.

Signed-off-by: Christian Lamparter <chunkeey@googlemail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ibm/emac/mal.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/ibm/emac/mal.c b/drivers/net/ethernet/ibm/emac/mal.c
index 91b1a558f37d..248888328232 100644
--- a/drivers/net/ethernet/ibm/emac/mal.c
+++ b/drivers/net/ethernet/ibm/emac/mal.c
@@ -402,7 +402,7 @@ static int mal_poll(struct napi_struct *napi, int budget)
 	unsigned long flags;
 
 	MAL_DBG2(mal, "poll(%d)" NL, budget);
- again:
+
 	/* Process TX skbs */
 	list_for_each(l, &mal->poll_list) {
 		struct mal_commac *mc =
@@ -451,7 +451,6 @@ static int mal_poll(struct napi_struct *napi, int budget)
 			spin_lock_irqsave(&mal->lock, flags);
 			mal_disable_eob_irq(mal);
 			spin_unlock_irqrestore(&mal->lock, flags);
-			goto again;
 		}
 		mc->ops->poll_tx(mc->dev);
 	}
-- 
2.13.6


From df01982dfacfa6e87a766f73ed39880a200272fa Mon Sep 17 00:00:00 2001
From: Mike Manning <mmanning@brocade.com>
Date: Mon, 4 Sep 2017 15:52:55 +0100
Subject: [PATCH 21/48] net: ipv6: fix regression of no RTM_DELADDR sent after
 DAD failure

[ Upstream commit 6819a14ecbe2e089e5c5bb74edecafdde2028a00 ]

Commit f784ad3d79e5 ("ipv6: do not send RTM_DELADDR for tentative
addresses") incorrectly assumes that no RTM_NEWADDR are sent for
addresses in tentative state, as this does happen for the standard
IPv6 use-case of DAD failure, see the call to ipv6_ifa_notify() in
addconf_dad_stop(). So as a result of this change, no RTM_DELADDR is
sent after DAD failure for a link-local when strict DAD (accept_dad=2)
is configured, or on the next admin down in other cases. The absence
of this notification breaks backwards compatibility and causes problems
after DAD failure if this notification was being relied on. The
solution is to allow RTM_DELADDR to still be sent after DAD failure.

Fixes: f784ad3d79e5 ("ipv6: do not send RTM_DELADDR for tentative addresses")
Signed-off-by: Mike Manning <mmanning@brocade.com>
Cc: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 936e9ab4dda5..ba757c28a301 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -4982,9 +4982,10 @@ static void inet6_ifa_notify(int event, struct inet6_ifaddr *ifa)
 
 	/* Don't send DELADDR notification for TENTATIVE address,
 	 * since NEWADDR notification is sent only after removing
-	 * TENTATIVE flag.
+	 * TENTATIVE flag, if DAD has not failed.
 	 */
-	if (ifa->flags & IFA_F_TENTATIVE && event == RTM_DELADDR)
+	if (ifa->flags & IFA_F_TENTATIVE && !(ifa->flags & IFA_F_DADFAILED) &&
+	    event == RTM_DELADDR)
 		return;
 
 	skb = nlmsg_new(inet6_ifaddr_msgsize(), GFP_ATOMIC);
-- 
2.13.6


From 19d2a73fbda5ba3ac04d86e9b889ea63590cb4d0 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Thu, 14 Sep 2017 17:14:41 -0400
Subject: [PATCH 22/48] packet: hold bind lock when rebinding to fanout hook

[ Upstream commit 008ba2a13f2d04c947adc536d19debb8fe66f110 ]

Packet socket bind operations must hold the po->bind_lock. This keeps
po->running consistent with whether the socket is actually on a ptype
list to receive packets.

fanout_add unbinds a socket and its packet_rcv/tpacket_rcv call, then
binds the fanout object to receive through packet_rcv_fanout.

Make it hold the po->bind_lock when testing po->running and rebinding.
Else, it can race with other rebind operations, such as that in
packet_set_ring from packet_rcv to tpacket_rcv. Concurrent updates
can result in a socket being added to a fanout group twice, causing
use-after-free KASAN bug reports, among others.

Reported independently by both trinity and syzkaller.
Verified that the syzkaller reproducer passes after this patch.

Fixes: dc99f600698d ("packet: Add fanout support.")
Reported-by: nixioaming <nixiaoming@huawei.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 1c61af9af67d..52f5f160ad2c 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1686,10 +1686,6 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 
 	mutex_lock(&fanout_mutex);
 
-	err = -EINVAL;
-	if (!po->running)
-		goto out;
-
 	err = -EALREADY;
 	if (po->fanout)
 		goto out;
@@ -1751,7 +1747,10 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		list_add(&match->list, &fanout_list);
 	}
 	err = -EINVAL;
-	if (match->type == type &&
+
+	spin_lock(&po->bind_lock);
+	if (po->running &&
+	    match->type == type &&
 	    match->prot_hook.type == po->prot_hook.type &&
 	    match->prot_hook.dev == po->prot_hook.dev) {
 		err = -ENOSPC;
@@ -1763,6 +1762,13 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 			err = 0;
 		}
 	}
+	spin_unlock(&po->bind_lock);
+
+	if (err && !refcount_read(&match->sk_ref)) {
+		list_del(&match->list);
+		kfree(match);
+	}
+
 out:
 	if (err && rollover) {
 		kfree(rollover);
-- 
2.13.6


From 901a5413c4f271374ac3d9395ef171aa21360772 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Mon, 18 Sep 2017 16:38:36 -0700
Subject: [PATCH 23/48] bpf: one perf event close won't free bpf program
 attached by another perf event

[ Upstream commit ec9dd352d591f0c90402ec67a317c1ed4fb2e638 ]

This patch fixes a bug exhibited by the following scenario:
  1. fd1 = perf_event_open with attr.config = ID1
  2. attach bpf program prog1 to fd1
  3. fd2 = perf_event_open with attr.config = ID1
     <this will be successful>
  4. user program closes fd2 and prog1 is detached from the tracepoint.
  5. user program with fd1 does not work properly as tracepoint
     no output any more.

The issue happens at step 4. Multiple perf_event_open can be called
successfully, but only one bpf prog pointer in the tp_event. In the
current logic, any fd release for the same tp_event will free
the tp_event->prog.

The fix is to free tp_event->prog only when the closing fd
corresponds to the one which registered the program.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/trace_events.h | 1 +
 kernel/events/core.c         | 3 ++-
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 5012b524283d..60248d644b6f 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -277,6 +277,7 @@ struct trace_event_call {
 	int				perf_refcount;
 	struct hlist_head __percpu	*perf_events;
 	struct bpf_prog			*prog;
+	struct perf_event		*bpf_prog_owner;
 
 	int	(*perf_perm)(struct trace_event_call *,
 			     struct perf_event *);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 03ac9c8b02fb..7242a6e1ec76 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8121,6 +8121,7 @@ static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd)
 		}
 	}
 	event->tp_event->prog = prog;
+	event->tp_event->bpf_prog_owner = event;
 
 	return 0;
 }
@@ -8135,7 +8136,7 @@ static void perf_event_free_bpf_prog(struct perf_event *event)
 		return;
 
 	prog = event->tp_event->prog;
-	if (prog) {
+	if (prog && event->tp_event->bpf_prog_owner == event) {
 		event->tp_event->prog = NULL;
 		bpf_prog_put(prog);
 	}
-- 
2.13.6


From cf07dc679e702106af99a25837192003b6569921 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Tue, 19 Sep 2017 18:45:56 +0100
Subject: [PATCH 24/48] net: change skb->mac_header when Generic XDP calls
 adjust_head

[ Upstream commit 92dd5452c1be873a1193561f4f691763103d22ac ]

Since XDP's view of the packet includes the MAC header, moving the start-
 of-packet with bpf_xdp_adjust_head needs to also update the offset of the
 MAC header (which is relative to skb->head, not to the skb->data that was
 changed).
Without this, tcpdump sees packets starting from the old MAC header rather
 than the new one, at least in my tests on the loopback device.

Fixes: b5cdae3291f7 ("net: Generic XDP")
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/core/dev.c b/net/core/dev.c
index 86b4b0a79e7a..6fa30a4c60ef 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4408,6 +4408,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 		__skb_pull(skb, off);
 	else if (off < 0)
 		__skb_push(skb, -off);
+	skb->mac_header += off;
 
 	switch (act) {
 	case XDP_TX:
-- 
2.13.6


From 36c7e4372a8921c0953ce2bd7be8aa4682a0d9b0 Mon Sep 17 00:00:00 2001
From: Meng Xu <mengxu.gatech@gmail.com>
Date: Tue, 19 Sep 2017 21:49:55 -0400
Subject: [PATCH 25/48] isdn/i4l: fetch the ppp_write buffer in one shot

[ Upstream commit 02388bf87f72e1d47174cd8f81c34443920eb5a0 ]

In isdn_ppp_write(), the header (i.e., protobuf) of the buffer is
fetched twice from userspace. The first fetch is used to peek at the
protocol of the message and reset the huptimer if necessary; while the
second fetch copies in the whole buffer. However, given that buf resides
in userspace memory, a user process can race to change its memory content
across fetches. By doing so, we can either avoid resetting the huptimer
for any type of packets (by first setting proto to PPP_LCP and later
change to the actual type) or force resetting the huptimer for LCP
packets.

This patch changes this double-fetch behavior into two single fetches
decided by condition (lp->isdn_device < 0 || lp->isdn_channel <0).
A more detailed discussion can be found at
https://marc.info/?l=linux-kernel&m=150586376926123&w=2

Signed-off-by: Meng Xu <mengxu.gatech@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/i4l/isdn_ppp.c | 37 +++++++++++++++++++++++++------------
 1 file changed, 25 insertions(+), 12 deletions(-)

diff --git a/drivers/isdn/i4l/isdn_ppp.c b/drivers/isdn/i4l/isdn_ppp.c
index 6c44609fd83a..cd2b3c69771a 100644
--- a/drivers/isdn/i4l/isdn_ppp.c
+++ b/drivers/isdn/i4l/isdn_ppp.c
@@ -825,7 +825,6 @@ isdn_ppp_write(int min, struct file *file, const char __user *buf, int count)
 	isdn_net_local *lp;
 	struct ippp_struct *is;
 	int proto;
-	unsigned char protobuf[4];
 
 	is = file->private_data;
 
@@ -839,24 +838,28 @@ isdn_ppp_write(int min, struct file *file, const char __user *buf, int count)
 	if (!lp)
 		printk(KERN_DEBUG "isdn_ppp_write: lp == NULL\n");
 	else {
-		/*
-		 * Don't reset huptimer for
-		 * LCP packets. (Echo requests).
-		 */
-		if (copy_from_user(protobuf, buf, 4))
-			return -EFAULT;
-		proto = PPP_PROTOCOL(protobuf);
-		if (proto != PPP_LCP)
-			lp->huptimer = 0;
+		if (lp->isdn_device < 0 || lp->isdn_channel < 0) {
+			unsigned char protobuf[4];
+			/*
+			 * Don't reset huptimer for
+			 * LCP packets. (Echo requests).
+			 */
+			if (copy_from_user(protobuf, buf, 4))
+				return -EFAULT;
+
+			proto = PPP_PROTOCOL(protobuf);
+			if (proto != PPP_LCP)
+				lp->huptimer = 0;
 
-		if (lp->isdn_device < 0 || lp->isdn_channel < 0)
 			return 0;
+		}
 
 		if ((dev->drv[lp->isdn_device]->flags & DRV_FLAG_RUNNING) &&
 		    lp->dialstate == 0 &&
 		    (lp->flags & ISDN_NET_CONNECTED)) {
 			unsigned short hl;
 			struct sk_buff *skb;
+			unsigned char *cpy_buf;
 			/*
 			 * we need to reserve enough space in front of
 			 * sk_buff. old call to dev_alloc_skb only reserved
@@ -869,11 +872,21 @@ isdn_ppp_write(int min, struct file *file, const char __user *buf, int count)
 				return count;
 			}
 			skb_reserve(skb, hl);
-			if (copy_from_user(skb_put(skb, count), buf, count))
+			cpy_buf = skb_put(skb, count);
+			if (copy_from_user(cpy_buf, buf, count))
 			{
 				kfree_skb(skb);
 				return -EFAULT;
 			}
+
+			/*
+			 * Don't reset huptimer for
+			 * LCP packets. (Echo requests).
+			 */
+			proto = PPP_PROTOCOL(cpy_buf);
+			if (proto != PPP_LCP)
+				lp->huptimer = 0;
+
 			if (is->debug & 0x40) {
 				printk(KERN_DEBUG "ppp xmit: len %d\n", (int) skb->len);
 				isdn_ppp_frame_log("xmit", skb->data, skb->len, 32, is->unit, lp->ppp_slot);
-- 
2.13.6


From 2f65f6886ec0e770f34e02ae8bfeef73ecf6b984 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Date: Wed, 20 Sep 2017 15:45:36 +0300
Subject: [PATCH 26/48] net_sched: always reset qdisc backlog in qdisc_reset()

[ Upstream commit c8e1812960eeae42e2183154927028511c4bc566 ]

SKB stored in qdisc->gso_skb also counted into backlog.

Some qdiscs don't reset backlog to zero in ->reset(),
for example sfq just dequeue and free all queued skb.

Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Fixes: 2ccccf5fb43f ("net_sched: update hierarchical backlog too")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_generic.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 4ba6da5fb254..ff49421ee48a 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -681,6 +681,7 @@ void qdisc_reset(struct Qdisc *qdisc)
 		qdisc->gso_skb = NULL;
 	}
 	qdisc->q.qlen = 0;
+	qdisc->qstats.backlog = 0;
 }
 EXPORT_SYMBOL(qdisc_reset);
 
-- 
2.13.6


From 9066b30d818caf6f172e7284a70b2bae8b510713 Mon Sep 17 00:00:00 2001
From: Thomas Meyer <thomas@m3y3r.de>
Date: Thu, 21 Sep 2017 08:24:27 +0200
Subject: [PATCH 27/48] net: stmmac: Cocci spatch "of_table"

[ Upstream commit f0ef1f4f2b772c0a1c8b35a6ae3edf974cc110dd ]

Make sure (of/i2c/platform)_device_id tables are NULL terminated.
Found by coccinelle spatch "misc/of_table.cocci"

Signed-off-by: Thomas Meyer <thomas@m3y3r.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index a366b3747eeb..8a280b48e3a9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -315,6 +315,7 @@ static int stmmac_dt_phy(struct plat_stmmacenet_data *plat,
 		{ .compatible = "allwinner,sun8i-h3-emac" },
 		{ .compatible = "allwinner,sun8i-v3s-emac" },
 		{ .compatible = "allwinner,sun50i-a64-emac" },
+		{},
 	};
 
 	/* If phy-handle property is passed from DT, use it as the PHY */
-- 
2.13.6


From a4e74e993de508d60c57b58ee781b41c503bfbcf Mon Sep 17 00:00:00 2001
From: Timur Tabi <timur@codeaurora.org>
Date: Fri, 22 Sep 2017 15:32:44 -0500
Subject: [PATCH 28/48] net: qcom/emac: specify the correct size when mapping a
 DMA buffer

[ Upstream commit a93ad944f4ff9a797abff17c73fc4b1e4a1d9141 ]

When mapping the RX DMA buffers, the driver was accidentally specifying
zero for the buffer length.  Under normal circumstances, SWIOTLB does not
need to allocate a bounce buffer, so the address is just mapped without
checking the size field.  This is why the error was not detected earlier.

Fixes: b9b17debc69d ("net: emac: emac gigabit ethernet controller driver")
Cc: stable@vger.kernel.org
Signed-off-by: Timur Tabi <timur@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qualcomm/emac/emac-mac.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.c b/drivers/net/ethernet/qualcomm/emac/emac-mac.c
index bcd4708b3745..97f18cdc9516 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac-mac.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.c
@@ -876,7 +876,8 @@ static void emac_mac_rx_descs_refill(struct emac_adapter *adpt,
 
 		curr_rxbuf->dma_addr =
 			dma_map_single(adpt->netdev->dev.parent, skb->data,
-				       curr_rxbuf->length, DMA_FROM_DEVICE);
+				       adpt->rxbuf_size, DMA_FROM_DEVICE);
+
 		ret = dma_mapping_error(adpt->netdev->dev.parent,
 					curr_rxbuf->dma_addr);
 		if (ret) {
-- 
2.13.6


From 27eb1e9071a782422732a55ae35b58e60da74fbf Mon Sep 17 00:00:00 2001
From: Alexey Kodanev <alexey.kodanev@oracle.com>
Date: Tue, 26 Sep 2017 15:14:29 +0300
Subject: [PATCH 29/48] vti: fix use after free in
 vti_tunnel_xmit/vti6_tnl_xmit

[ Upstream commit 36f6ee22d2d66046e369757ec6bbe1c482957ba6 ]

When running LTP IPsec tests, KASan might report:

BUG: KASAN: use-after-free in vti_tunnel_xmit+0xeee/0xff0 [ip_vti]
Read of size 4 at addr ffff880dc6ad1980 by task swapper/0/0
...
Call Trace:
  <IRQ>
  dump_stack+0x63/0x89
  print_address_description+0x7c/0x290
  kasan_report+0x28d/0x370
  ? vti_tunnel_xmit+0xeee/0xff0 [ip_vti]
  __asan_report_load4_noabort+0x19/0x20
  vti_tunnel_xmit+0xeee/0xff0 [ip_vti]
  ? vti_init_net+0x190/0x190 [ip_vti]
  ? save_stack_trace+0x1b/0x20
  ? save_stack+0x46/0xd0
  dev_hard_start_xmit+0x147/0x510
  ? icmp_echo.part.24+0x1f0/0x210
  __dev_queue_xmit+0x1394/0x1c60
...
Freed by task 0:
  save_stack_trace+0x1b/0x20
  save_stack+0x46/0xd0
  kasan_slab_free+0x70/0xc0
  kmem_cache_free+0x81/0x1e0
  kfree_skbmem+0xb1/0xe0
  kfree_skb+0x75/0x170
  kfree_skb_list+0x3e/0x60
  __dev_queue_xmit+0x1298/0x1c60
  dev_queue_xmit+0x10/0x20
  neigh_resolve_output+0x3a8/0x740
  ip_finish_output2+0x5c0/0xe70
  ip_finish_output+0x4ba/0x680
  ip_output+0x1c1/0x3a0
  xfrm_output_resume+0xc65/0x13d0
  xfrm_output+0x1e4/0x380
  xfrm4_output_finish+0x5c/0x70

Can be fixed if we get skb->len before dst_output().

Fixes: b9959fd3b0fa ("vti: switch to new ip tunnel code")
Fixes: 22e1b23dafa8 ("vti6: Support inter address family tunneling.")
Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_vti.c  | 3 ++-
 net/ipv6/ip6_vti.c | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 0192c255e508..74bd46c5bda7 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -168,6 +168,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
 	struct ip_tunnel_parm *parms = &tunnel->parms;
 	struct dst_entry *dst = skb_dst(skb);
 	struct net_device *tdev;	/* Device to other host */
+	int pkt_len = skb->len;
 	int err;
 	int mtu;
 
@@ -229,7 +230,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
 
 	err = dst_output(tunnel->net, skb->sk, skb);
 	if (net_xmit_eval(err) == 0)
-		err = skb->len;
+		err = pkt_len;
 	iptunnel_xmit_stats(dev, err);
 	return NETDEV_TX_OK;
 
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 486c2305f53c..e3e3ea655464 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -445,6 +445,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 	struct dst_entry *dst = skb_dst(skb);
 	struct net_device *tdev;
 	struct xfrm_state *x;
+	int pkt_len = skb->len;
 	int err = -1;
 	int mtu;
 
@@ -502,7 +503,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 		struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
 
 		u64_stats_update_begin(&tstats->syncp);
-		tstats->tx_bytes += skb->len;
+		tstats->tx_bytes += pkt_len;
 		tstats->tx_packets++;
 		u64_stats_update_end(&tstats->syncp);
 	} else {
-- 
2.13.6


From 49d17a9910600c521887887cf1e87bb58c7da983 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 26 Sep 2017 16:16:43 +0200
Subject: [PATCH 30/48] l2tp: fix race condition in l2tp_tunnel_delete

[ Upstream commit 62b982eeb4589b2e6d7c01a90590e3a4c2b2ca19 ]

If we try to delete the same tunnel twice, the first delete operation
does a lookup (l2tp_tunnel_get), finds the tunnel, calls
l2tp_tunnel_delete, which queues it for deletion by
l2tp_tunnel_del_work.

The second delete operation also finds the tunnel and calls
l2tp_tunnel_delete. If the workqueue has already fired and started
running l2tp_tunnel_del_work, then l2tp_tunnel_delete will queue the
same tunnel a second time, and try to free the socket again.

Add a dead flag to prevent firing the workqueue twice. Then we can
remove the check of queue_work's result that was meant to prevent that
race but doesn't.

Reproducer:

    ip l2tp add tunnel tunnel_id 3000 peer_tunnel_id 4000 local 192.168.0.2 remote 192.168.0.1 encap udp udp_sport 5000 udp_dport 6000
    ip l2tp add session name l2tp1 tunnel_id 3000 session_id 1000 peer_session_id 2000
    ip link set l2tp1 up
    ip l2tp del tunnel tunnel_id 3000
    ip l2tp del tunnel tunnel_id 3000

Fixes: f8ccac0e4493 ("l2tp: put tunnel socket release on a workqueue")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Acked-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 10 ++++------
 net/l2tp/l2tp_core.h |  5 ++++-
 2 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 90165a6874bc..525c66f1121a 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1665,14 +1665,12 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_create);
 
 /* This function is used by the netlink TUNNEL_DELETE command.
  */
-int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel)
+void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel)
 {
-	l2tp_tunnel_inc_refcount(tunnel);
-	if (false == queue_work(l2tp_wq, &tunnel->del_work)) {
-		l2tp_tunnel_dec_refcount(tunnel);
-		return 1;
+	if (!test_and_set_bit(0, &tunnel->dead)) {
+		l2tp_tunnel_inc_refcount(tunnel);
+		queue_work(l2tp_wq, &tunnel->del_work);
 	}
-	return 0;
 }
 EXPORT_SYMBOL_GPL(l2tp_tunnel_delete);
 
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 9101297f27ad..7c5a51f62afc 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -160,6 +160,9 @@ struct l2tp_tunnel_cfg {
 
 struct l2tp_tunnel {
 	int			magic;		/* Should be L2TP_TUNNEL_MAGIC */
+
+	unsigned long		dead;
+
 	struct rcu_head rcu;
 	rwlock_t		hlist_lock;	/* protect session_hlist */
 	struct hlist_head	session_hlist[L2TP_HASH_SIZE];
@@ -248,7 +251,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id,
 		       u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg,
 		       struct l2tp_tunnel **tunnelp);
 void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel);
-int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel);
+void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel);
 struct l2tp_session *l2tp_session_create(int priv_size,
 					 struct l2tp_tunnel *tunnel,
 					 u32 session_id, u32 peer_session_id,
-- 
2.13.6


From 37e0629c943d5bbe48861d4c1a61495653d3aa7b Mon Sep 17 00:00:00 2001
From: Alexander Potapenko <glider@google.com>
Date: Thu, 28 Sep 2017 11:32:37 +0200
Subject: [PATCH 31/48] tun: bail out from tun_get_user() if the skb is empty

[ Upstream commit 2580c4c17aee3ad58e9751012bad278dd074ccae ]

KMSAN (https://github.com/google/kmsan) reported accessing uninitialized
skb->data[0] in the case the skb is empty (i.e. skb->len is 0):

================================================
BUG: KMSAN: use of uninitialized memory in tun_get_user+0x19ba/0x3770
CPU: 0 PID: 3051 Comm: probe Not tainted 4.13.0+ #3140
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
Call Trace:
...
 __msan_warning_32+0x66/0xb0 mm/kmsan/kmsan_instr.c:477
 tun_get_user+0x19ba/0x3770 drivers/net/tun.c:1301
 tun_chr_write_iter+0x19f/0x300 drivers/net/tun.c:1365
 call_write_iter ./include/linux/fs.h:1743
 new_sync_write fs/read_write.c:457
 __vfs_write+0x6c3/0x7f0 fs/read_write.c:470
 vfs_write+0x3e4/0x770 fs/read_write.c:518
 SYSC_write+0x12f/0x2b0 fs/read_write.c:565
 SyS_write+0x55/0x80 fs/read_write.c:557
 do_syscall_64+0x242/0x330 arch/x86/entry/common.c:284
 entry_SYSCALL64_slow_path+0x25/0x25 arch/x86/entry/entry_64.S:245
...
origin:
...
 kmsan_poison_shadow+0x6e/0xc0 mm/kmsan/kmsan.c:211
 slab_alloc_node mm/slub.c:2732
 __kmalloc_node_track_caller+0x351/0x370 mm/slub.c:4351
 __kmalloc_reserve net/core/skbuff.c:138
 __alloc_skb+0x26a/0x810 net/core/skbuff.c:231
 alloc_skb ./include/linux/skbuff.h:903
 alloc_skb_with_frags+0x1d7/0xc80 net/core/skbuff.c:4756
 sock_alloc_send_pskb+0xabf/0xfe0 net/core/sock.c:2037
 tun_alloc_skb drivers/net/tun.c:1144
 tun_get_user+0x9a8/0x3770 drivers/net/tun.c:1274
 tun_chr_write_iter+0x19f/0x300 drivers/net/tun.c:1365
 call_write_iter ./include/linux/fs.h:1743
 new_sync_write fs/read_write.c:457
 __vfs_write+0x6c3/0x7f0 fs/read_write.c:470
 vfs_write+0x3e4/0x770 fs/read_write.c:518
 SYSC_write+0x12f/0x2b0 fs/read_write.c:565
 SyS_write+0x55/0x80 fs/read_write.c:557
 do_syscall_64+0x242/0x330 arch/x86/entry/common.c:284
 return_from_SYSCALL_64+0x0/0x6a arch/x86/entry/entry_64.S:245
================================================

Make sure tun_get_user() doesn't touch skb->data[0] unless there is
actual data.

C reproducer below:
==========================
    // autogenerated by syzkaller (http://github.com/google/syzkaller)

    #define _GNU_SOURCE

    #include <fcntl.h>
    #include <linux/if_tun.h>
    #include <netinet/ip.h>
    #include <net/if.h>
    #include <string.h>
    #include <sys/ioctl.h>

    int main()
    {
      int sock = socket(PF_INET, SOCK_STREAM, IPPROTO_IP);
      int tun_fd = open("/dev/net/tun", O_RDWR);
      struct ifreq req;
      memset(&req, 0, sizeof(struct ifreq));
      strcpy((char*)&req.ifr_name, "gre0");
      req.ifr_flags = IFF_UP | IFF_MULTICAST;
      ioctl(tun_fd, TUNSETIFF, &req);
      ioctl(sock, SIOCSIFFLAGS, "gre0");
      write(tun_fd, "hi", 0);
      return 0;
    }
==========================

Signed-off-by: Alexander Potapenko <glider@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 0a2c0a42283f..cb1f7747adad 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1298,11 +1298,13 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	switch (tun->flags & TUN_TYPE_MASK) {
 	case IFF_TUN:
 		if (tun->flags & IFF_NO_PI) {
-			switch (skb->data[0] & 0xf0) {
-			case 0x40:
+			u8 ip_version = skb->len ? (skb->data[0] >> 4) : 0;
+
+			switch (ip_version) {
+			case 4:
 				pi.proto = htons(ETH_P_IP);
 				break;
-			case 0x60:
+			case 6:
 				pi.proto = htons(ETH_P_IPV6);
 				break;
 			default:
-- 
2.13.6


From 7e9d060bdb47cf28a261edaf6bff34841fe31ca4 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Mon, 25 Sep 2017 23:32:20 +0200
Subject: [PATCH 32/48] net: dsa: mv88e6xxx: Allow dsa and cpu ports in
 multiple vlans

[ Upstream commit db06ae41945b14feb7f696dcafe8048cc37e8a20 ]

Ports with the same VLAN must all be in the same bridge. However the
CPU and DSA ports need to be in multiple VLANs spread over multiple
bridges. So exclude them when performing this test.

Fixes: b2f81d304cee ("net: dsa: add CPU and DSA ports as VLAN members")
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 5bcdd33101b0..74e72fdea9a2 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -1184,6 +1184,10 @@ static int mv88e6xxx_port_check_hw_vlan(struct dsa_switch *ds, int port,
 	};
 	int i, err;
 
+	/* DSA and CPU ports have to be members of multiple vlans */
+	if (dsa_is_dsa_port(ds, port) || dsa_is_cpu_port(ds, port))
+		return 0;
+
 	if (!vid_begin)
 		return -EOPNOTSUPP;
 
-- 
2.13.6


From aecfb098d06f2a879a4fc354b5cb12cfb3d26034 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Mon, 25 Sep 2017 15:55:53 -0700
Subject: [PATCH 33/48] net: dsa: Fix network device registration order

[ Upstream commit e804441cfe0b60f6c430901946a69c01eac09df1 ]

We cannot be registering the network device first, then setting its
carrier off and finally connecting it to a PHY, doing that leaves a
window during which the carrier is at best inconsistent, and at worse
the device is not usable without a down/up sequence since the network
device is visible to user space with possibly no PHY device attached.

Re-order steps so that they make logical sense. This fixes some devices
where the port was not usable after e.g: an unbind then bind of the
driver.

Fixes: 0071f56e46da ("dsa: Register netdev before phy")
Fixes: 91da11f870f0 ("net: Distributed Switch Architecture protocol support")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/slave.c | 28 +++++++++++++++++-----------
 1 file changed, 17 insertions(+), 11 deletions(-)

diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 9507bd38cf04..07677540129a 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -1180,26 +1180,32 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent,
 	p->old_duplex = -1;
 
 	ds->ports[port].netdev = slave_dev;
-	ret = register_netdev(slave_dev);
-	if (ret) {
-		netdev_err(master, "error %d registering interface %s\n",
-			   ret, slave_dev->name);
-		ds->ports[port].netdev = NULL;
-		free_netdev(slave_dev);
-		return ret;
-	}
 
 	netif_carrier_off(slave_dev);
 
 	ret = dsa_slave_phy_setup(p, slave_dev);
 	if (ret) {
 		netdev_err(master, "error %d setting up slave phy\n", ret);
-		unregister_netdev(slave_dev);
-		free_netdev(slave_dev);
-		return ret;
+		goto out_free;
+	}
+
+	ret = register_netdev(slave_dev);
+	if (ret) {
+		netdev_err(master, "error %d registering interface %s\n",
+			   ret, slave_dev->name);
+		goto out_phy;
 	}
 
 	return 0;
+
+out_phy:
+	phy_disconnect(p->phy);
+	if (of_phy_is_fixed_link(p->dp->dn))
+		of_phy_deregister_fixed_link(p->dp->dn);
+out_free:
+	free_netdev(slave_dev);
+	ds->ports[port].netdev = NULL;
+	return ret;
 }
 
 void dsa_slave_destroy(struct net_device *slave_dev)
-- 
2.13.6


From 2d845fb480bce2fa2b33cdc7f638976386b435e8 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Tue, 26 Sep 2017 12:19:37 -0400
Subject: [PATCH 34/48] packet: in packet_do_bind, test fanout with bind_lock
 held

[ Upstream commit 4971613c1639d8e5f102c4e797c3bf8f83a5a69e ]

Once a socket has po->fanout set, it remains a member of the group
until it is destroyed. The prot_hook must be constant and identical
across sockets in the group.

If fanout_add races with packet_do_bind between the test of po->fanout
and taking the lock, the bind call may make type or dev inconsistent
with that of the fanout group.

Hold po->bind_lock when testing po->fanout to avoid this race.

I had to introduce artificial delay (local_bh_enable) to actually
observe the race.

Fixes: dc99f600698d ("packet: Add fanout support.")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 52f5f160ad2c..79362d8d3a8e 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3071,13 +3071,15 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex,
 	int ret = 0;
 	bool unlisted = false;
 
-	if (po->fanout)
-		return -EINVAL;
-
 	lock_sock(sk);
 	spin_lock(&po->bind_lock);
 	rcu_read_lock();
 
+	if (po->fanout) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
 	if (name) {
 		dev = dev_get_by_name_rcu(sock_net(sk), name);
 		if (!dev) {
-- 
2.13.6


From 911c29317f6198cf0b7a693171ed4d508b80f2d1 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Tue, 26 Sep 2017 12:20:17 -0400
Subject: [PATCH 35/48] packet: only test po->has_vnet_hdr once in packet_snd

[ Upstream commit da7c9561015e93d10fe6aab73e9288e0d09d65a6 ]

Packet socket option po->has_vnet_hdr can be updated concurrently with
other operations if no ring is attached.

Do not test the option twice in packet_snd, as the value may change in
between calls. A race on setsockopt disable may cause a packet > mtu
to be sent without having GSO options set.

Fixes: bfd5f4a3d605 ("packet: Add GSO/csum offload support.")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 79362d8d3a8e..29d7b7e5b128 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2842,6 +2842,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	struct virtio_net_hdr vnet_hdr = { 0 };
 	int offset = 0;
 	struct packet_sock *po = pkt_sk(sk);
+	bool has_vnet_hdr = false;
 	int hlen, tlen, linear;
 	int extra_len = 0;
 
@@ -2885,6 +2886,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		err = packet_snd_vnet_parse(msg, &len, &vnet_hdr);
 		if (err)
 			goto out_unlock;
+		has_vnet_hdr = true;
 	}
 
 	if (unlikely(sock_flag(sk, SOCK_NOFCS))) {
@@ -2943,7 +2945,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	skb->priority = sk->sk_priority;
 	skb->mark = sockc.mark;
 
-	if (po->has_vnet_hdr) {
+	if (has_vnet_hdr) {
 		err = virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le());
 		if (err)
 			goto out_free;
-- 
2.13.6


From 04d88152fe0bf34c3fe5e79217fef199331df732 Mon Sep 17 00:00:00 2001
From: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Date: Tue, 26 Sep 2017 14:57:21 -0400
Subject: [PATCH 36/48] net: dsa: mv88e6xxx: lock mutex when freeing IRQs

[ Upstream commit b32ca44a88def4bf92626d8777494c6f14638c42 ]

mv88e6xxx_g2_irq_free locks the registers mutex, but not
mv88e6xxx_g1_irq_free, which results in a stack trace from
assert_reg_lock when unloading the mv88e6xxx module. Fix this.

Fixes: 3460a5770ce9 ("net: dsa: mv88e6xxx: Mask g1 interrupts and free interrupt")
Signed-off-by: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 74e72fdea9a2..c75271c722a7 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -4019,7 +4019,9 @@ static void mv88e6xxx_remove(struct mdio_device *mdiodev)
 	if (chip->irq > 0) {
 		if (mv88e6xxx_has(chip, MV88E6XXX_FLAG_G2_INT))
 			mv88e6xxx_g2_irq_free(chip);
+		mutex_lock(&chip->reg_lock);
 		mv88e6xxx_g1_irq_free(chip);
+		mutex_unlock(&chip->reg_lock);
 	}
 }
 
-- 
2.13.6


From 82179ab3d3e8d1892b2fa2b48b4f935daa36d4aa Mon Sep 17 00:00:00 2001
From: Christoph Paasch <cpaasch@apple.com>
Date: Tue, 26 Sep 2017 17:38:50 -0700
Subject: [PATCH 37/48] net: Set sk_prot_creator when cloning sockets to the
 right proto

[ Upstream commit 9d538fa60bad4f7b23193c89e843797a1cf71ef3 ]

sk->sk_prot and sk->sk_prot_creator can differ when the app uses
IPV6_ADDRFORM (transforming an IPv6-socket to an IPv4-one).
Which is why sk_prot_creator is there to make sure that sk_prot_free()
does the kmem_cache_free() on the right kmem_cache slab.

Now, if such a socket gets transformed back to a listening socket (using
connect() with AF_UNSPEC) we will allocate an IPv4 tcp_sock through
sk_clone_lock() when a new connection comes in. But sk_prot_creator will
still point to the IPv6 kmem_cache (as everything got copied in
sk_clone_lock()). When freeing, we will thus put this
memory back into the IPv6 kmem_cache although it was allocated in the
IPv4 cache. I have seen memory corruption happening because of this.

With slub-debugging and MEMCG_KMEM enabled this gives the warning
	"cache_from_obj: Wrong slab cache. TCPv6 but object is from TCP"

A C-program to trigger this:

void main(void)
{
        int fd = socket(AF_INET6, SOCK_STREAM, IPPROTO_TCP);
        int new_fd, newest_fd, client_fd;
        struct sockaddr_in6 bind_addr;
        struct sockaddr_in bind_addr4, client_addr1, client_addr2;
        struct sockaddr unsp;
        int val;

        memset(&bind_addr, 0, sizeof(bind_addr));
        bind_addr.sin6_family = AF_INET6;
        bind_addr.sin6_port = ntohs(42424);

        memset(&client_addr1, 0, sizeof(client_addr1));
        client_addr1.sin_family = AF_INET;
        client_addr1.sin_port = ntohs(42424);
        client_addr1.sin_addr.s_addr = inet_addr("127.0.0.1");

        memset(&client_addr2, 0, sizeof(client_addr2));
        client_addr2.sin_family = AF_INET;
        client_addr2.sin_port = ntohs(42421);
        client_addr2.sin_addr.s_addr = inet_addr("127.0.0.1");

        memset(&unsp, 0, sizeof(unsp));
        unsp.sa_family = AF_UNSPEC;

        bind(fd, (struct sockaddr *)&bind_addr, sizeof(bind_addr));

        listen(fd, 5);

        client_fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
        connect(client_fd, (struct sockaddr *)&client_addr1, sizeof(client_addr1));
        new_fd = accept(fd, NULL, NULL);
        close(fd);

        val = AF_INET;
        setsockopt(new_fd, SOL_IPV6, IPV6_ADDRFORM, &val, sizeof(val));

        connect(new_fd, &unsp, sizeof(unsp));

        memset(&bind_addr4, 0, sizeof(bind_addr4));
        bind_addr4.sin_family = AF_INET;
        bind_addr4.sin_port = ntohs(42421);
        bind(new_fd, (struct sockaddr *)&bind_addr4, sizeof(bind_addr4));

        listen(new_fd, 5);

        client_fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
        connect(client_fd, (struct sockaddr *)&client_addr2, sizeof(client_addr2));

        newest_fd = accept(new_fd, NULL, NULL);
        close(new_fd);

        close(client_fd);
        close(new_fd);
}

As far as I can see, this bug has been there since the beginning of the
git-days.

Signed-off-by: Christoph Paasch <cpaasch@apple.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/core/sock.c b/net/core/sock.c
index ac2a404c73eb..b22228901a11 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1646,6 +1646,8 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 
 		sock_copy(newsk, sk);
 
+		newsk->sk_prot_creator = sk->sk_prot;
+
 		/* SANITY */
 		if (likely(newsk->sk_net_refcnt))
 			get_net(sock_net(newsk));
-- 
2.13.6


From 47bc37e5e9ca01100d97ffacc257f96b9e50481e Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@mellanox.com>
Date: Mon, 21 Aug 2017 12:04:50 +0300
Subject: [PATCH 38/48] net/mlx5e: IPoIB, Fix access to invalid memory address

[ Upstream commit 38e8a5c040d3ec99a8351c688dcdf0f549611565 ]

When cleaning rdma netdevice we need to save the mdev pointer
because priv is released when we release netdev.

This bug was found using the kernel address sanitizer (KASAN).
use-after-free in mlx5_rdma_netdev_free+0xe3/0x100 [mlx5_core]

Fixes: 48935bbb7ae8 ("net/mlx5e: IPoIB, Add netdevice profile skeleton")
Signed-off-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 85298051a3e4..145e392ab849 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -572,12 +572,13 @@ void mlx5_rdma_netdev_free(struct net_device *netdev)
 {
 	struct mlx5e_priv          *priv    = mlx5i_epriv(netdev);
 	const struct mlx5e_profile *profile = priv->profile;
+	struct mlx5_core_dev       *mdev    = priv->mdev;
 
 	mlx5e_detach_netdev(priv);
 	profile->cleanup(priv);
 	destroy_workqueue(priv->wq);
 	free_netdev(netdev);
 
-	mlx5e_destroy_mdev_resources(priv->mdev);
+	mlx5e_destroy_mdev_resources(mdev);
 }
 EXPORT_SYMBOL(mlx5_rdma_netdev_free);
-- 
2.13.6


From 7bfa451510cb44d5ef8f4c19079ccda4f6e947bb Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Thu, 28 Sep 2017 00:41:44 +0200
Subject: [PATCH 39/48] netlink: do not proceed if dump's start() errs

[ Upstream commit fef0035c0f31322d417d1954bba5ab959bf91183 ]

Drivers that use the start method for netlink dumping rely on dumpit not
being called if start fails. For example, ila_xlat.c allocates memory
and assigns it to cb->args[0] in its start() function. It might fail to
do that and return -ENOMEM instead. However, even when returning an
error, dumpit will be called, which, in the example above, quickly
dereferences the memory in cb->args[0], which will OOPS the kernel. This
is but one example of how this goes wrong.

Since start() has always been a function with an int return type, it
therefore makes sense to use it properly, rather than ignoring it. This
patch thus returns early and does not call dumpit() when start() fails.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
Reviewed-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 5acee49db90b..7e794ad50cb0 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2262,10 +2262,13 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 
 	mutex_unlock(nlk->cb_mutex);
 
+	ret = 0;
 	if (cb->start)
-		cb->start(cb);
+		ret = cb->start(cb);
+
+	if (!ret)
+		ret = netlink_dump(sk);
 
-	ret = netlink_dump(sk);
 	sock_put(sk);
 
 	if (ret)
-- 
2.13.6


From 0ff31950f95da44c583a6c4cfa5d1e6cf1343f03 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 28 Sep 2017 13:23:50 +0800
Subject: [PATCH 40/48] ip6_gre: ip6gre_tap device should keep dst

[ Upstream commit 2d40557cc702ed8e5edd9bd422233f86652d932e ]

The patch 'ip_gre: ipgre_tap device should keep dst' fixed
a issue that ipgre_tap mtu couldn't be updated in tx path.

The same fix is needed for ip6gre_tap as well.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 20f66f4c9460..1602b491b281 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1311,6 +1311,7 @@ static void ip6gre_tap_setup(struct net_device *dev)
 	dev->features |= NETIF_F_NETNS_LOCAL;
 	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
+	netif_keep_dst(dev);
 }
 
 static bool ip6gre_netlink_encap_parms(struct nlattr *data[],
-- 
2.13.6


From 8b415c80c294688b520fab21b2c25cb9db0de647 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 28 Sep 2017 13:24:07 +0800
Subject: [PATCH 41/48] ip6_tunnel: update mtu properly for ARPHRD_ETHER tunnel
 device in tx path

[ Upstream commit d41bb33ba33b8f8debe54ed36be6925eb496e354 ]

Now when updating mtu in tx path, it doesn't consider ARPHRD_ETHER tunnel
device, like ip6gre_tap tunnel, for which it should also subtract ether
header to get the correct mtu.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 98647402b339..4425b4411bb9 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1043,6 +1043,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 	struct dst_entry *dst = NULL, *ndst = NULL;
 	struct net_device *tdev;
 	int mtu;
+	unsigned int eth_hlen = t->dev->type == ARPHRD_ETHER ? ETH_HLEN : 0;
 	unsigned int psh_hlen = sizeof(struct ipv6hdr) + t->encap_hlen;
 	unsigned int max_headroom = psh_hlen;
 	bool use_cache = false;
@@ -1124,7 +1125,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 				     t->parms.name);
 		goto tx_err_dst_release;
 	}
-	mtu = dst_mtu(dst) - psh_hlen - t->tun_hlen;
+	mtu = dst_mtu(dst) - eth_hlen - psh_hlen - t->tun_hlen;
 	if (encap_limit >= 0) {
 		max_headroom += 8;
 		mtu -= 8;
@@ -1133,7 +1134,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 		mtu = IPV6_MIN_MTU;
 	if (skb_dst(skb) && !t->parms.collect_md)
 		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
-	if (skb->len - t->tun_hlen > mtu && !skb_is_gso(skb)) {
+	if (skb->len - t->tun_hlen - eth_hlen > mtu && !skb_is_gso(skb)) {
 		*pmtu = mtu;
 		err = -EMSGSIZE;
 		goto tx_err_dst_release;
-- 
2.13.6


From 795b504efdbd8f48fdb4d4f8dd65f051574aafb6 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 28 Sep 2017 15:51:36 +0200
Subject: [PATCH 42/48] IPv4: early demux can return an error code

[ Upstream commit 7487449c86c65202b3b725c4524cb48dd65e4e6f ]

Currently no error is emitted, but this infrastructure will
used by the next patch to allow source address validation
for mcast sockets.
Since early demux can do a route lookup and an ipv4 route
lookup can return an error code this is consistent with the
current ipv4 route infrastructure.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/protocol.h |  4 ++--
 include/net/tcp.h      |  2 +-
 include/net/udp.h      |  2 +-
 net/ipv4/ip_input.c    | 25 +++++++++++++++----------
 net/ipv4/tcp_ipv4.c    |  9 +++++----
 net/ipv4/udp.c         | 11 ++++++-----
 6 files changed, 30 insertions(+), 23 deletions(-)

diff --git a/include/net/protocol.h b/include/net/protocol.h
index 65ba335b0e7e..4fc75f7ae23b 100644
--- a/include/net/protocol.h
+++ b/include/net/protocol.h
@@ -39,8 +39,8 @@
 
 /* This is used to register protocols. */
 struct net_protocol {
-	void			(*early_demux)(struct sk_buff *skb);
-	void                    (*early_demux_handler)(struct sk_buff *skb);
+	int			(*early_demux)(struct sk_buff *skb);
+	int			(*early_demux_handler)(struct sk_buff *skb);
 	int			(*handler)(struct sk_buff *skb);
 	void			(*err_handler)(struct sk_buff *skb, u32 info);
 	unsigned int		no_policy:1,
diff --git a/include/net/tcp.h b/include/net/tcp.h
index f642a39f9eee..48978125947b 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -347,7 +347,7 @@ void tcp_v4_err(struct sk_buff *skb, u32);
 
 void tcp_shutdown(struct sock *sk, int how);
 
-void tcp_v4_early_demux(struct sk_buff *skb);
+int tcp_v4_early_demux(struct sk_buff *skb);
 int tcp_v4_rcv(struct sk_buff *skb);
 
 int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw);
diff --git a/include/net/udp.h b/include/net/udp.h
index 626c2d8a70c5..1e6b2476d427 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -259,7 +259,7 @@ static inline struct sk_buff *skb_recv_udp(struct sock *sk, unsigned int flags,
 	return __skb_recv_udp(sk, flags, noblock, &peeked, &off, err);
 }
 
-void udp_v4_early_demux(struct sk_buff *skb);
+int udp_v4_early_demux(struct sk_buff *skb);
 bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst);
 int udp_get_port(struct sock *sk, unsigned short snum,
 		 int (*saddr_cmp)(const struct sock *,
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index fa2dc8f692c6..57fc13c6ab2b 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -311,9 +311,10 @@ static inline bool ip_rcv_options(struct sk_buff *skb)
 static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	const struct iphdr *iph = ip_hdr(skb);
-	struct rtable *rt;
+	int (*edemux)(struct sk_buff *skb);
 	struct net_device *dev = skb->dev;
-	void (*edemux)(struct sk_buff *skb);
+	struct rtable *rt;
+	int err;
 
 	/* if ingress device is enslaved to an L3 master device pass the
 	 * skb to its handler for processing
@@ -331,7 +332,9 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 
 		ipprot = rcu_dereference(inet_protos[protocol]);
 		if (ipprot && (edemux = READ_ONCE(ipprot->early_demux))) {
-			edemux(skb);
+			err = edemux(skb);
+			if (unlikely(err))
+				goto drop_error;
 			/* must reload iph, skb->head might have changed */
 			iph = ip_hdr(skb);
 		}
@@ -342,13 +345,10 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 	 *	how the packet travels inside Linux networking.
 	 */
 	if (!skb_valid_dst(skb)) {
-		int err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
-					       iph->tos, dev);
-		if (unlikely(err)) {
-			if (err == -EXDEV)
-				__NET_INC_STATS(net, LINUX_MIB_IPRPFILTER);
-			goto drop;
-		}
+		err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
+					   iph->tos, dev);
+		if (unlikely(err))
+			goto drop_error;
 	}
 
 #ifdef CONFIG_IP_ROUTE_CLASSID
@@ -399,6 +399,11 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 drop:
 	kfree_skb(skb);
 	return NET_RX_DROP;
+
+drop_error:
+	if (err == -EXDEV)
+		__NET_INC_STATS(net, LINUX_MIB_IPRPFILTER);
+	goto drop;
 }
 
 /*
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 21022db7a2a6..b1441bc8192f 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1504,23 +1504,23 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(tcp_v4_do_rcv);
 
-void tcp_v4_early_demux(struct sk_buff *skb)
+int tcp_v4_early_demux(struct sk_buff *skb)
 {
 	const struct iphdr *iph;
 	const struct tcphdr *th;
 	struct sock *sk;
 
 	if (skb->pkt_type != PACKET_HOST)
-		return;
+		return 0;
 
 	if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct tcphdr)))
-		return;
+		return 0;
 
 	iph = ip_hdr(skb);
 	th = tcp_hdr(skb);
 
 	if (th->doff < sizeof(struct tcphdr) / 4)
-		return;
+		return 0;
 
 	sk = __inet_lookup_established(dev_net(skb->dev), &tcp_hashinfo,
 				       iph->saddr, th->source,
@@ -1539,6 +1539,7 @@ void tcp_v4_early_demux(struct sk_buff *skb)
 				skb_dst_set_noref(skb, dst);
 		}
 	}
+	return 0;
 }
 
 /* Packet is added to VJ-style prequeue for processing in process
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 979e4d8526ba..ae437e123b83 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2217,7 +2217,7 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net,
 	return NULL;
 }
 
-void udp_v4_early_demux(struct sk_buff *skb)
+int udp_v4_early_demux(struct sk_buff *skb)
 {
 	struct net *net = dev_net(skb->dev);
 	const struct iphdr *iph;
@@ -2229,7 +2229,7 @@ void udp_v4_early_demux(struct sk_buff *skb)
 
 	/* validate the packet */
 	if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr)))
-		return;
+		return 0;
 
 	iph = ip_hdr(skb);
 	uh = udp_hdr(skb);
@@ -2239,14 +2239,14 @@ void udp_v4_early_demux(struct sk_buff *skb)
 		struct in_device *in_dev = __in_dev_get_rcu(skb->dev);
 
 		if (!in_dev)
-			return;
+			return 0;
 
 		/* we are supposed to accept bcast packets */
 		if (skb->pkt_type == PACKET_MULTICAST) {
 			ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr,
 					       iph->protocol);
 			if (!ours)
-				return;
+				return 0;
 		}
 
 		sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr,
@@ -2257,7 +2257,7 @@ void udp_v4_early_demux(struct sk_buff *skb)
 	}
 
 	if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt))
-		return;
+		return 0;
 
 	skb->sk = sk;
 	skb->destructor = sock_efree;
@@ -2272,6 +2272,7 @@ void udp_v4_early_demux(struct sk_buff *skb)
 		 */
 		skb_dst_set_noref(skb, dst);
 	}
+	return 0;
 }
 
 int udp_rcv(struct sk_buff *skb)
-- 
2.13.6


From 371c3e3f200c1d4240e8b4caf372517c50d45071 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 28 Sep 2017 15:51:37 +0200
Subject: [PATCH 43/48] udp: perform source validation for mcast early demux

[ Upstream commit bc044e8db7962e727a75b591b9851ff2ac5cf846 ]

The UDP early demux can leverate the rx dst cache even for
multicast unconnected sockets.

In such scenario the ipv4 source address is validated only on
the first packet in the given flow. After that, when we fetch
the dst entry  from the socket rx cache, we stop enforcing
the rp_filter and we even start accepting any kind of martian
addresses.

Disabling the dst cache for unconnected multicast socket will
cause large performace regression, nearly reducing by half the
max ingress tput.

Instead we factor out a route helper to completely validate an
skb source address for multicast packets and we call it from
the UDP early demux for mcast packets landing on unconnected
sockets, after successful fetching the related cached dst entry.

This still gives a measurable, but limited performance
regression:

		rp_filter = 0		rp_filter = 1
edmux disabled:	1182 Kpps		1127 Kpps
edmux before:	2238 Kpps		2238 Kpps
edmux after:	2037 Kpps		2019 Kpps

The above figures are on top of current net tree.
Applying the net-next commit 6e617de84e87 ("net: avoid a full
fib lookup when rp_filter is disabled.") the delta with
rp_filter == 0 will decrease even more.

Fixes: 421b3885bf6d ("udp: ipv4: Add udp early demux")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/route.h |  4 +++-
 net/ipv4/route.c    | 46 ++++++++++++++++++++++++++--------------------
 net/ipv4/udp.c      | 13 ++++++++++++-
 3 files changed, 41 insertions(+), 22 deletions(-)

diff --git a/include/net/route.h b/include/net/route.h
index cb0a76d9dde1..58458966e31e 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -175,7 +175,9 @@ static inline struct rtable *ip_route_output_gre(struct net *net, struct flowi4
 	fl4->fl4_gre_key = gre_key;
 	return ip_route_output_key(net, fl4);
 }
-
+int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr,
+			  u8 tos, struct net_device *dev,
+			  struct in_device *in_dev, u32 *itag);
 int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 src,
 			 u8 tos, struct net_device *devin);
 int ip_route_input_rcu(struct sk_buff *skb, __be32 dst, __be32 src,
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 2331de20ca50..c5aa25be7108 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1520,43 +1520,56 @@ struct rtable *rt_dst_alloc(struct net_device *dev,
 EXPORT_SYMBOL(rt_dst_alloc);
 
 /* called in rcu_read_lock() section */
-static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
-				u8 tos, struct net_device *dev, int our)
+int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr,
+			  u8 tos, struct net_device *dev,
+			  struct in_device *in_dev, u32 *itag)
 {
-	struct rtable *rth;
-	struct in_device *in_dev = __in_dev_get_rcu(dev);
-	unsigned int flags = RTCF_MULTICAST;
-	u32 itag = 0;
 	int err;
 
 	/* Primary sanity checks. */
-
 	if (!in_dev)
 		return -EINVAL;
 
 	if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) ||
 	    skb->protocol != htons(ETH_P_IP))
-		goto e_inval;
+		return -EINVAL;
 
 	if (ipv4_is_loopback(saddr) && !IN_DEV_ROUTE_LOCALNET(in_dev))
-		goto e_inval;
+		return -EINVAL;
 
 	if (ipv4_is_zeronet(saddr)) {
 		if (!ipv4_is_local_multicast(daddr))
-			goto e_inval;
+			return -EINVAL;
 	} else {
 		err = fib_validate_source(skb, saddr, 0, tos, 0, dev,
-					  in_dev, &itag);
+					  in_dev, itag);
 		if (err < 0)
-			goto e_err;
+			return err;
 	}
+	return 0;
+}
+
+/* called in rcu_read_lock() section */
+static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
+			     u8 tos, struct net_device *dev, int our)
+{
+	struct in_device *in_dev = __in_dev_get_rcu(dev);
+	unsigned int flags = RTCF_MULTICAST;
+	struct rtable *rth;
+	u32 itag = 0;
+	int err;
+
+	err = ip_mc_validate_source(skb, daddr, saddr, tos, dev, in_dev, &itag);
+	if (err)
+		return err;
+
 	if (our)
 		flags |= RTCF_LOCAL;
 
 	rth = rt_dst_alloc(dev_net(dev)->loopback_dev, flags, RTN_MULTICAST,
 			   IN_DEV_CONF_GET(in_dev, NOPOLICY), false, false);
 	if (!rth)
-		goto e_nobufs;
+		return -ENOBUFS;
 
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	rth->dst.tclassid = itag;
@@ -1572,13 +1585,6 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 
 	skb_dst_set(skb, &rth->dst);
 	return 0;
-
-e_nobufs:
-	return -ENOBUFS;
-e_inval:
-	return -EINVAL;
-e_err:
-	return err;
 }
 
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index ae437e123b83..781be33a9c2e 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2220,6 +2220,7 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net,
 int udp_v4_early_demux(struct sk_buff *skb)
 {
 	struct net *net = dev_net(skb->dev);
+	struct in_device *in_dev = NULL;
 	const struct iphdr *iph;
 	const struct udphdr *uh;
 	struct sock *sk = NULL;
@@ -2236,7 +2237,7 @@ int udp_v4_early_demux(struct sk_buff *skb)
 
 	if (skb->pkt_type == PACKET_BROADCAST ||
 	    skb->pkt_type == PACKET_MULTICAST) {
-		struct in_device *in_dev = __in_dev_get_rcu(skb->dev);
+		in_dev = __in_dev_get_rcu(skb->dev);
 
 		if (!in_dev)
 			return 0;
@@ -2266,11 +2267,21 @@ int udp_v4_early_demux(struct sk_buff *skb)
 	if (dst)
 		dst = dst_check(dst, 0);
 	if (dst) {
+		u32 itag = 0;
+
 		/* set noref for now.
 		 * any place which wants to hold dst has to call
 		 * dst_hold_safe()
 		 */
 		skb_dst_set_noref(skb, dst);
+
+		/* for unconnected multicast sockets we need to validate
+		 * the source on each packet
+		 */
+		if (!inet_sk(sk)->inet_daddr && in_dev)
+			return ip_mc_validate_source(skb, iph->daddr,
+						     iph->saddr, iph->tos,
+						     skb->dev, in_dev, &itag);
 	}
 	return 0;
 }
-- 
2.13.6


From 8a3a9bf8bf98a2736ec6be846732ddb5ee3def4e Mon Sep 17 00:00:00 2001
From: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
Date: Fri, 29 Sep 2017 10:02:54 +0200
Subject: [PATCH 44/48] tipc: use only positive error codes in messages

[ Upstream commit aad06212d36cf34859428a0a279e5c14ee5c9e26 ]

In commit e3a77561e7d32 ("tipc: split up function tipc_msg_eval()"),
we have updated the function tipc_msg_lookup_dest() to set the error
codes to negative values at destination lookup failures. Thus when
the function sets the error code to -TIPC_ERR_NO_NAME, its inserted
into the 4 bit error field of the message header as 0xf instead of
TIPC_ERR_NO_NAME (1). The value 0xf is an unknown error code.

In this commit, we set only positive error code.

Fixes: e3a77561e7d32 ("tipc: split up function tipc_msg_eval()")
Signed-off-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/msg.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index 6ef379f004ac..121e59a1d0e7 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -551,7 +551,7 @@ bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err)
 		return false;
 	if (msg_errcode(msg))
 		return false;
-	*err = -TIPC_ERR_NO_NAME;
+	*err = TIPC_ERR_NO_NAME;
 	if (skb_linearize(skb))
 		return false;
 	msg = buf_msg(skb);
-- 
2.13.6


From 60f6aa136da343a6352ddde903fc13bbd986c5e4 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Thu, 28 Sep 2017 15:44:38 +0200
Subject: [PATCH 45/48] l2tp: fix l2tp_eth module loading

[ Upstream commit 9f775ead5e570e7e19015b9e4e2f3dd6e71a5935 ]

The l2tp_eth module crashes if its netlink callbacks are run when the
pernet data aren't initialised.

We should normally register_pernet_device() before the genl callbacks.
However, the pernet data only maintain a list of l2tpeth interfaces,
and this list is never used. So let's just drop pernet handling
instead.

Fixes: d9e31d17ceba ("l2tp: Add L2TP ethernet pseudowire support")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_eth.c | 51 ++-------------------------------------------------
 1 file changed, 2 insertions(+), 49 deletions(-)

diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index 4de2ec94b08c..cf456720930c 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -44,7 +44,6 @@ struct l2tp_eth {
 	struct net_device	*dev;
 	struct sock		*tunnel_sock;
 	struct l2tp_session	*session;
-	struct list_head	list;
 	atomic_long_t		tx_bytes;
 	atomic_long_t		tx_packets;
 	atomic_long_t		tx_dropped;
@@ -58,17 +57,6 @@ struct l2tp_eth_sess {
 	struct net_device	*dev;
 };
 
-/* per-net private data for this module */
-static unsigned int l2tp_eth_net_id;
-struct l2tp_eth_net {
-	struct list_head l2tp_eth_dev_list;
-	spinlock_t l2tp_eth_lock;
-};
-
-static inline struct l2tp_eth_net *l2tp_eth_pernet(struct net *net)
-{
-	return net_generic(net, l2tp_eth_net_id);
-}
 
 static int l2tp_eth_dev_init(struct net_device *dev)
 {
@@ -84,12 +72,6 @@ static int l2tp_eth_dev_init(struct net_device *dev)
 
 static void l2tp_eth_dev_uninit(struct net_device *dev)
 {
-	struct l2tp_eth *priv = netdev_priv(dev);
-	struct l2tp_eth_net *pn = l2tp_eth_pernet(dev_net(dev));
-
-	spin_lock(&pn->l2tp_eth_lock);
-	list_del_init(&priv->list);
-	spin_unlock(&pn->l2tp_eth_lock);
 	dev_put(dev);
 }
 
@@ -272,7 +254,6 @@ static int l2tp_eth_create(struct net *net, u32 tunnel_id, u32 session_id, u32 p
 	struct l2tp_eth *priv;
 	struct l2tp_eth_sess *spriv;
 	int rc;
-	struct l2tp_eth_net *pn;
 
 	tunnel = l2tp_tunnel_find(net, tunnel_id);
 	if (!tunnel) {
@@ -310,7 +291,6 @@ static int l2tp_eth_create(struct net *net, u32 tunnel_id, u32 session_id, u32 p
 	priv = netdev_priv(dev);
 	priv->dev = dev;
 	priv->session = session;
-	INIT_LIST_HEAD(&priv->list);
 
 	priv->tunnel_sock = tunnel->sock;
 	session->recv_skb = l2tp_eth_dev_recv;
@@ -331,10 +311,6 @@ static int l2tp_eth_create(struct net *net, u32 tunnel_id, u32 session_id, u32 p
 	strlcpy(session->ifname, dev->name, IFNAMSIZ);
 
 	dev_hold(dev);
-	pn = l2tp_eth_pernet(dev_net(dev));
-	spin_lock(&pn->l2tp_eth_lock);
-	list_add(&priv->list, &pn->l2tp_eth_dev_list);
-	spin_unlock(&pn->l2tp_eth_lock);
 
 	return 0;
 
@@ -347,22 +323,6 @@ static int l2tp_eth_create(struct net *net, u32 tunnel_id, u32 session_id, u32 p
 	return rc;
 }
 
-static __net_init int l2tp_eth_init_net(struct net *net)
-{
-	struct l2tp_eth_net *pn = net_generic(net, l2tp_eth_net_id);
-
-	INIT_LIST_HEAD(&pn->l2tp_eth_dev_list);
-	spin_lock_init(&pn->l2tp_eth_lock);
-
-	return 0;
-}
-
-static struct pernet_operations l2tp_eth_net_ops = {
-	.init = l2tp_eth_init_net,
-	.id   = &l2tp_eth_net_id,
-	.size = sizeof(struct l2tp_eth_net),
-};
-
 
 static const struct l2tp_nl_cmd_ops l2tp_eth_nl_cmd_ops = {
 	.session_create	= l2tp_eth_create,
@@ -376,25 +336,18 @@ static int __init l2tp_eth_init(void)
 
 	err = l2tp_nl_register_ops(L2TP_PWTYPE_ETH, &l2tp_eth_nl_cmd_ops);
 	if (err)
-		goto out;
-
-	err = register_pernet_device(&l2tp_eth_net_ops);
-	if (err)
-		goto out_unreg;
+		goto err;
 
 	pr_info("L2TP ethernet pseudowire support (L2TPv3)\n");
 
 	return 0;
 
-out_unreg:
-	l2tp_nl_unregister_ops(L2TP_PWTYPE_ETH);
-out:
+err:
 	return err;
 }
 
 static void __exit l2tp_eth_exit(void)
 {
-	unregister_pernet_device(&l2tp_eth_net_ops);
 	l2tp_nl_unregister_ops(L2TP_PWTYPE_ETH);
 }
 
-- 
2.13.6


From 053e7be971ff6bdd759017bb8dc173073d8c838d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 2 Oct 2017 12:20:51 -0700
Subject: [PATCH 46/48] socket, bpf: fix possible use after free

[ Upstream commit eefca20eb20c66b06cf5ed09b49b1a7caaa27b7b ]

Starting from linux-4.4, 3WHS no longer takes the listener lock.

Since this time, we might hit a use-after-free in sk_filter_charge(),
if the filter we got in the memcpy() of the listener content
just happened to be replaced by a thread changing listener BPF filter.

To fix this, we need to make sure the filter refcount is not already
zero before incrementing it again.

Fixes: e994b2f0fb92 ("tcp: do not lock listener to process SYN packets")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/filter.c | 12 ++++++++----
 net/core/sock.c   |  5 ++++-
 2 files changed, 12 insertions(+), 5 deletions(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index 169974998c76..18d591f1ae5a 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -975,10 +975,14 @@ static bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp)
 
 bool sk_filter_charge(struct sock *sk, struct sk_filter *fp)
 {
-	bool ret = __sk_filter_charge(sk, fp);
-	if (ret)
-		refcount_inc(&fp->refcnt);
-	return ret;
+	if (!refcount_inc_not_zero(&fp->refcnt))
+		return false;
+
+	if (!__sk_filter_charge(sk, fp)) {
+		sk_filter_release(fp);
+		return false;
+	}
+	return true;
 }
 
 static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp)
diff --git a/net/core/sock.c b/net/core/sock.c
index b22228901a11..0967da925022 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1675,13 +1675,16 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 
 		sock_reset_flag(newsk, SOCK_DONE);
 
-		filter = rcu_dereference_protected(newsk->sk_filter, 1);
+		rcu_read_lock();
+		filter = rcu_dereference(sk->sk_filter);
 		if (filter != NULL)
 			/* though it's an empty new sock, the charging may fail
 			 * if sysctl_optmem_max was changed between creation of
 			 * original socket and cloning
 			 */
 			is_charged = sk_filter_charge(newsk, filter);
+		RCU_INIT_POINTER(newsk->sk_filter, filter);
+		rcu_read_unlock();
 
 		if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) {
 			/* We need to make sure that we don't uncharge the new
-- 
2.13.6


From 001bae2e9ce581327e2a0dbc994a06adecd9a2d0 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Tue, 3 Oct 2017 13:20:48 +0300
Subject: [PATCH 47/48] net: rtnetlink: fix info leak in RTM_GETSTATS call

[ Upstream commit ce024f42c2e28b6bce4ecc1e891b42f57f753892 ]

When RTM_GETSTATS was added the fields of its header struct were not all
initialized when returning the result thus leaking 4 bytes of information
to user-space per rtnl_fill_statsinfo call, so initialize them now. Thanks
to Alexander Potapenko for the detailed report and bisection.

Reported-by: Alexander Potapenko <glider@google.com>
Fixes: 10c9ead9f3c6 ("rtnetlink: add new RTM_GETSTATS message to dump link stats")
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Acked-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 9201e3621351..e07c8847c6cf 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3867,6 +3867,9 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev,
 		return -EMSGSIZE;
 
 	ifsm = nlmsg_data(nlh);
+	ifsm->family = PF_UNSPEC;
+	ifsm->pad1 = 0;
+	ifsm->pad2 = 0;
 	ifsm->ifindex = dev->ifindex;
 	ifsm->filter_mask = filter_mask;
 
-- 
2.13.6


From cde90c8182cef1298754044781f7cea3d83faf48 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@fb.com>
Date: Tue, 3 Oct 2017 15:37:20 -0700
Subject: [PATCH 48/48] bpf: fix bpf_tail_call() x64 JIT

[ Upstream commit 90caccdd8cc0215705f18b92771b449b01e2474a ]

- bpf prog_array just like all other types of bpf array accepts 32-bit index.
  Clarify that in the comment.
- fix x64 JIT of bpf_tail_call which was incorrectly loading 8 instead of 4 bytes
- tighten corresponding check in the interpreter to stay consistent

The JIT bug can be triggered after introduction of BPF_F_NUMA_NODE flag
in commit 96eabe7a40aa in 4.14. Before that the map_flags would stay zero and
though JIT code is wrong it will check bounds correctly.
Hence two fixes tags. All other JITs don't have this problem.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Fixes: 96eabe7a40aa ("bpf: Allow selecting numa node during map creation")
Fixes: b52f00e6a715 ("x86: bpf_jit: implement bpf_tail_call() helper")
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/x86/net/bpf_jit_comp.c | 4 ++--
 include/uapi/linux/bpf.h    | 2 +-
 kernel/bpf/core.c           | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index e1324f280e06..4d50ced94686 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -282,9 +282,9 @@ static void emit_bpf_tail_call(u8 **pprog)
 	/* if (index >= array->map.max_entries)
 	 *   goto out;
 	 */
-	EMIT4(0x48, 0x8B, 0x46,                   /* mov rax, qword ptr [rsi + 16] */
+	EMIT2(0x89, 0xD2);                        /* mov edx, edx */
+	EMIT3(0x39, 0x56,                         /* cmp dword ptr [rsi + 16], edx */
 	      offsetof(struct bpf_array, map.max_entries));
-	EMIT3(0x48, 0x39, 0xD0);                  /* cmp rax, rdx */
 #define OFFSET1 47 /* number of bytes to jump */
 	EMIT2(X86_JBE, OFFSET1);                  /* jbe out */
 	label1 = cnt;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index e99e3e6f8b37..f0add86219f0 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -294,7 +294,7 @@ union bpf_attr {
  *     jump into another BPF program
  *     @ctx: context pointer passed to next program
  *     @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY
- *     @index: index inside array that selects specific program to run
+ *     @index: 32-bit index inside array that selects specific program to run
  *     Return: 0 on success or negative error
  *
  * int bpf_clone_redirect(skb, ifindex, flags)
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index ad5f55922a13..9a1bed1f3029 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1010,7 +1010,7 @@ static unsigned int ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn,
 		struct bpf_map *map = (struct bpf_map *) (unsigned long) BPF_R2;
 		struct bpf_array *array = container_of(map, struct bpf_array, map);
 		struct bpf_prog *prog;
-		u64 index = BPF_R3;
+		u32 index = BPF_R3;
 
 		if (unlikely(index >= array->map.max_entries))
 			goto out;
-- 
2.13.6

Re: [PATCHES] Networking

[Greg KH]

On Sun, Oct 08, 2017 at 09:02:19PM -0700, David Miller wrote:
> 
> Please queue up the following bug fixes for 4.13.x -stable.

Thanks for the patches, all now queued up.

greg k-h

Re: [PATCHES] Networking

[Greg KH]

On Mon, Oct 09, 2017 at 09:34:06AM +0200, Greg KH wrote:
> On Sun, Oct 08, 2017 at 09:02:19PM -0700, David Miller wrote:
> > 
> > Please queue up the following bug fixes for 4.13.x -stable.
> 
> Thanks for the patches, all now queued up.

Oh, just curious, are you going to have a mbox of patches for 4.9-stable
as well?  If not, no worries, I'll do the backporting, just didn't want
to duplicate any work here.

thanks,

greg k-h

Re: [PATCHES] Networking

[David Miller]

From: Greg KH <greg@kroah.com>
Date: Mon, 9 Oct 2017 09:56:48 +0200

> On Mon, Oct 09, 2017 at 09:34:06AM +0200, Greg KH wrote:
>> On Sun, Oct 08, 2017 at 09:02:19PM -0700, David Miller wrote:
>> > 
>> > Please queue up the following bug fixes for 4.13.x -stable.
>> 
>> Thanks for the patches, all now queued up.
> 
> Oh, just curious, are you going to have a mbox of patches for 4.9-stable
> as well?  If not, no worries, I'll do the backporting, just didn't want
> to duplicate any work here.

Let me see if I can cook that up today, otherwise I'll let you know that
I won't be able to do it.

You know what actually happened?  I got confused by the ordering of the
stable trees on www.kernel.org, I think it should be ordered by release
number rather than trying to group 'stable' vs. 'longterm'.

Re: [PATCHES] Networking

[Greg KH]

On Mon, Oct 09, 2017 at 09:55:02AM -0700, David Miller wrote:
> From: Greg KH <greg@kroah.com>
> Date: Mon, 9 Oct 2017 09:56:48 +0200
> 
> > On Mon, Oct 09, 2017 at 09:34:06AM +0200, Greg KH wrote:
> >> On Sun, Oct 08, 2017 at 09:02:19PM -0700, David Miller wrote:
> >> > 
> >> > Please queue up the following bug fixes for 4.13.x -stable.
> >> 
> >> Thanks for the patches, all now queued up.
> > 
> > Oh, just curious, are you going to have a mbox of patches for 4.9-stable
> > as well?  If not, no worries, I'll do the backporting, just didn't want
> > to duplicate any work here.
> 
> Let me see if I can cook that up today, otherwise I'll let you know that
> I won't be able to do it.
> 
> You know what actually happened?  I got confused by the ordering of the
> stable trees on www.kernel.org, I think it should be ordered by release
> number rather than trying to group 'stable' vs. 'longterm'.

Ah, crap, that's my fault, let me go fix the website, it should be
ordered that way, I messed up when I marked 3.4 as EOL, but forgot to do
it in the scripts so the front page would be correct.

Should be resolved in 30 minutes or so, whenever the backend syncs to
the front-facing servers.

thanks,

greg k-h

Re: [PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 1367 bytes --]

From: Greg KH <greg@kroah.com>
Date: Mon, 9 Oct 2017 21:04:20 +0200

> On Mon, Oct 09, 2017 at 09:55:02AM -0700, David Miller wrote:
>> From: Greg KH <greg@kroah.com>
>> Date: Mon, 9 Oct 2017 09:56:48 +0200
>> 
>> > On Mon, Oct 09, 2017 at 09:34:06AM +0200, Greg KH wrote:
>> >> On Sun, Oct 08, 2017 at 09:02:19PM -0700, David Miller wrote:
>> >> > 
>> >> > Please queue up the following bug fixes for 4.13.x -stable.
>> >> 
>> >> Thanks for the patches, all now queued up.
>> > 
>> > Oh, just curious, are you going to have a mbox of patches for 4.9-stable
>> > as well?  If not, no worries, I'll do the backporting, just didn't want
>> > to duplicate any work here.
>> 
>> Let me see if I can cook that up today, otherwise I'll let you know that
>> I won't be able to do it.
>> 
>> You know what actually happened?  I got confused by the ordering of the
>> stable trees on www.kernel.org, I think it should be ordered by release
>> number rather than trying to group 'stable' vs. 'longterm'.
> 
> Ah, crap, that's my fault, let me go fix the website, it should be
> ordered that way, I messed up when I marked 3.4 as EOL, but forgot to do
> it in the scripts so the front page would be correct.
> 
> Should be resolved in 30 minutes or so, whenever the backend syncs to
> the front-facing servers.

Thanks a lot.

Attached are the 4.9 networking -stable backports:

[-- Attachment #2: net_49.mbox --]
[-- Type: Application/Octet-Stream, Size: 76262 bytes --]

From 2a78f944c2ccf34fcce0e2b784292b860caa1cb2 Mon Sep 17 00:00:00 2001
From: Yuval Mintz <yuvalm@mellanox.com>
Date: Tue, 12 Sep 2017 08:50:53 +0200
Subject: [PATCH 01/32] mlxsw: spectrum: Prevent mirred-related crash on
 removal

[ Upstream commit 6399ebcccffa12e65bc15eda039d37673264ebce ]

When removing the offloading of mirred actions under
matchall classifiers, mlxsw would find the destination port
associated with the offloaded action and utilize it for undoing
the configuration.

Depending on the order by which ports are removed, it's possible that
the destination port would get removed before the source port.
In such a scenario, when actions would be flushed for the source port
mlxsw would perform an illegal dereference as the destination port is
no longer listed.

Since the only item necessary for undoing the configuration on the
destination side is the port-id and that in turn is already maintained
by mlxsw on the source-port, simply stop trying to access the
destination port and use the port-id directly instead.

Fixes: 763b4b70af ("mlxsw: spectrum: Add support in matchall mirror TC offloading")
Signed-off-by: Yuval Mintz <yuvalm@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 1806b1fc6e4c..d50350c7adc4 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -249,15 +249,14 @@ static void mlxsw_sp_span_entry_destroy(struct mlxsw_sp *mlxsw_sp,
 }
 
 static struct mlxsw_sp_span_entry *
-mlxsw_sp_span_entry_find(struct mlxsw_sp_port *port)
+mlxsw_sp_span_entry_find(struct mlxsw_sp *mlxsw_sp, u8 local_port)
 {
-	struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp;
 	int i;
 
 	for (i = 0; i < mlxsw_sp->span.entries_count; i++) {
 		struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i];
 
-		if (curr->used && curr->local_port == port->local_port)
+		if (curr->used && curr->local_port == local_port)
 			return curr;
 	}
 	return NULL;
@@ -268,7 +267,8 @@ static struct mlxsw_sp_span_entry
 {
 	struct mlxsw_sp_span_entry *span_entry;
 
-	span_entry = mlxsw_sp_span_entry_find(port);
+	span_entry = mlxsw_sp_span_entry_find(port->mlxsw_sp,
+					      port->local_port);
 	if (span_entry) {
 		/* Already exists, just take a reference */
 		span_entry->ref_count++;
@@ -453,12 +453,13 @@ static int mlxsw_sp_span_mirror_add(struct mlxsw_sp_port *from,
 }
 
 static void mlxsw_sp_span_mirror_remove(struct mlxsw_sp_port *from,
-					struct mlxsw_sp_port *to,
+					u8 destination_port,
 					enum mlxsw_sp_span_type type)
 {
 	struct mlxsw_sp_span_entry *span_entry;
 
-	span_entry = mlxsw_sp_span_entry_find(to);
+	span_entry = mlxsw_sp_span_entry_find(from->mlxsw_sp,
+					      destination_port);
 	if (!span_entry) {
 		netdev_err(from->dev, "no span entry found\n");
 		return;
@@ -1255,10 +1256,8 @@ static int mlxsw_sp_port_add_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port,
 static void mlxsw_sp_port_del_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port,
 					   struct tc_cls_matchall_offload *cls)
 {
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	struct mlxsw_sp_port_mall_tc_entry *mall_tc_entry;
 	enum mlxsw_sp_span_type span_type;
-	struct mlxsw_sp_port *to_port;
 
 	mall_tc_entry = mlxsw_sp_port_mirror_entry_find(mlxsw_sp_port,
 							cls->cookie);
@@ -1269,11 +1268,12 @@ static void mlxsw_sp_port_del_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port,
 
 	switch (mall_tc_entry->type) {
 	case MLXSW_SP_PORT_MALL_MIRROR:
-		to_port = mlxsw_sp->ports[mall_tc_entry->mirror.to_local_port];
 		span_type = mall_tc_entry->mirror.ingress ?
 				MLXSW_SP_SPAN_INGRESS : MLXSW_SP_SPAN_EGRESS;
 
-		mlxsw_sp_span_mirror_remove(mlxsw_sp_port, to_port, span_type);
+		mlxsw_sp_span_mirror_remove(mlxsw_sp_port,
+					    mall_tc_entry->mirror.to_local_port,
+					    span_type);
 		break;
 	default:
 		WARN_ON(1);
-- 
2.13.6


From b68c6389bf2e6f8f463f68e4303421f53373d491 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 13 Sep 2017 17:32:37 +0200
Subject: [PATCH 02/32] net: sched: fix use-after-free in tcf_action_destroy
 and tcf_del_walker

[ Upstream commit 255cd50f207ae8ec7b22663246c833407744e634 ]

Recent commit d7fb60b9cafb ("net_sched: get rid of tcfa_rcu") removed
freeing in call_rcu, which changed already existing hard-to-hit
race condition into 100% hit:

[  598.599825] BUG: unable to handle kernel NULL pointer dereference at 0000000000000030
[  598.607782] IP: tcf_action_destroy+0xc0/0x140

Or:

[   40.858924] BUG: unable to handle kernel NULL pointer dereference at 0000000000000030
[   40.862840] IP: tcf_generic_walker+0x534/0x820

Fix this by storing the ops and use them directly for module_put call.

Fixes: a85a970af265 ("net_sched: move tc_action into tcf_common")
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_api.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index c651cfce9be6..f3117324146a 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -141,7 +141,7 @@ static int tcf_del_walker(struct tcf_hashinfo *hinfo, struct sk_buff *skb,
 		hlist_for_each_entry_safe(p, n, head, tcfa_head) {
 			ret = __tcf_hash_release(p, false, true);
 			if (ret == ACT_P_DELETED) {
-				module_put(p->ops->owner);
+				module_put(ops->owner);
 				n_i++;
 			} else if (ret < 0)
 				goto nla_put_failure;
@@ -450,13 +450,15 @@ EXPORT_SYMBOL(tcf_action_exec);
 
 int tcf_action_destroy(struct list_head *actions, int bind)
 {
+	const struct tc_action_ops *ops;
 	struct tc_action *a, *tmp;
 	int ret = 0;
 
 	list_for_each_entry_safe(a, tmp, actions, list) {
+		ops = a->ops;
 		ret = __tcf_hash_release(a, bind, true);
 		if (ret == ACT_P_DELETED)
-			module_put(a->ops->owner);
+			module_put(ops->owner);
 		else if (ret < 0)
 			return ret;
 	}
-- 
2.13.6


From 39dacc53eac24ceb5da92dde074f16a1fc6433d0 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Thu, 14 Sep 2017 02:00:54 +0300
Subject: [PATCH 03/32] sctp: potential read out of bounds in
 sctp_ulpevent_type_enabled()

[ Upstream commit fa5f7b51fc3080c2b195fa87c7eca7c05e56f673 ]

This code causes a static checker warning because Smatch doesn't trust
anything that comes from skb->data.  I've reviewed this code and I do
think skb->data can be controlled by the user here.

The sctp_event_subscribe struct has 13 __u8 fields and we want to see
if ours is non-zero.  sn_type can be any value in the 0-USHRT_MAX range.
We're subtracting SCTP_SN_TYPE_BASE which is 1 << 15 so we could read
either before the start of the struct or after the end.

This is a very old bug and it's surprising that it would go undetected
for so long but my theory is that it just doesn't have a big impact so
it would be hard to notice.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/ulpevent.h | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/include/net/sctp/ulpevent.h b/include/net/sctp/ulpevent.h
index 2c098cd7e7e2..231df4fc8423 100644
--- a/include/net/sctp/ulpevent.h
+++ b/include/net/sctp/ulpevent.h
@@ -141,8 +141,12 @@ __u16 sctp_ulpevent_get_notification_type(const struct sctp_ulpevent *event);
 static inline int sctp_ulpevent_type_enabled(__u16 sn_type,
 					     struct sctp_event_subscribe *mask)
 {
+	int offset = sn_type - SCTP_SN_TYPE_BASE;
 	char *amask = (char *) mask;
-	return amask[sn_type - SCTP_SN_TYPE_BASE];
+
+	if (offset >= sizeof(struct sctp_event_subscribe))
+		return 0;
+	return amask[offset];
 }
 
 /* Given an event subscription, is this event enabled? */
-- 
2.13.6


From a884b02ca434dec1f395f1b0313411633c12a275 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@googl.com>
Date: Wed, 13 Sep 2017 20:30:39 -0700
Subject: [PATCH 04/32] tcp: update skb->skb_mstamp more carefully

[ Upstream commit 8c72c65b426b47b3c166a8fef0d8927fe5e8a28d ]

liujian reported a problem in TCP_USER_TIMEOUT processing with a patch
in tcp_probe_timer() :
      https://www.spinics.net/lists/netdev/msg454496.html

After investigations, the root cause of the problem is that we update
skb->skb_mstamp of skbs in write queue, even if the attempt to send a
clone or copy of it failed. One reason being a routing problem.

This patch prevents this, solving liujian issue.

It also removes a potential RTT miscalculation, since
__tcp_retransmit_skb() is not OR-ing TCP_SKB_CB(skb)->sacked with
TCPCB_EVER_RETRANS if a failure happens, but skb->skb_mstamp has
been changed.

A future ACK would then lead to a very small RTT sample and min_rtt
would then be lowered to this too small value.

Tested:

# cat user_timeout.pkt
--local_ip=192.168.102.64

    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
   +0 bind(3, ..., ...) = 0
   +0 listen(3, 1) = 0

   +0 `ifconfig tun0 192.168.102.64/16; ip ro add 192.0.2.1 dev tun0`

   +0 < S 0:0(0) win 0 <mss 1460>
   +0 > S. 0:0(0) ack 1 <mss 1460>

  +.1 < . 1:1(0) ack 1 win 65530
   +0 accept(3, ..., ...) = 4

   +0 setsockopt(4, SOL_TCP, TCP_USER_TIMEOUT, [3000], 4) = 0
   +0 write(4, ..., 24) = 24
   +0 > P. 1:25(24) ack 1 win 29200
   +.1 < . 1:1(0) ack 25 win 65530

//change the ipaddress
   +1 `ifconfig tun0 192.168.0.10/16`

   +1 write(4, ..., 24) = 24
   +1 write(4, ..., 24) = 24
   +1 write(4, ..., 24) = 24
   +1 write(4, ..., 24) = 24

   +0 `ifconfig tun0 192.168.102.64/16`
   +0 < . 1:2(1) ack 25 win 65530
   +0 `ifconfig tun0 192.168.0.10/16`

   +3 write(4, ..., 24) = -1

# ./packetdrill user_timeout.pkt

Signed-off-by: Eric Dumazet <edumazet@googl.com>
Reported-by: liujian <liujian56@huawei.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 5d836b037442..bb2f00b5f200 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -914,6 +914,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	struct tcp_skb_cb *tcb;
 	struct tcp_out_options opts;
 	unsigned int tcp_options_size, tcp_header_size;
+	struct sk_buff *oskb = NULL;
 	struct tcp_md5sig_key *md5;
 	struct tcphdr *th;
 	int err;
@@ -922,11 +923,11 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	tp = tcp_sk(sk);
 
 	if (clone_it) {
-		skb_mstamp_get(&skb->skb_mstamp);
 		TCP_SKB_CB(skb)->tx.in_flight = TCP_SKB_CB(skb)->end_seq
 			- tp->snd_una;
 		tcp_rate_skb_sent(sk, skb);
 
+		oskb = skb;
 		if (unlikely(skb_cloned(skb)))
 			skb = pskb_copy(skb, gfp_mask);
 		else
@@ -934,6 +935,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 		if (unlikely(!skb))
 			return -ENOBUFS;
 	}
+	skb_mstamp_get(&skb->skb_mstamp);
 
 	inet = inet_sk(sk);
 	tcb = TCP_SKB_CB(skb);
@@ -1035,12 +1037,14 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 
 	err = icsk->icsk_af_ops->queue_xmit(sk, skb, &inet->cork.fl);
 
-	if (likely(err <= 0))
-		return err;
-
-	tcp_enter_cwr(sk);
+	if (unlikely(err > 0)) {
+		tcp_enter_cwr(sk);
+		err = net_xmit_eval(err);
+	}
+	if (!err && oskb)
+		skb_mstamp_get(&oskb->skb_mstamp);
 
-	return net_xmit_eval(err);
+	return err;
 }
 
 /* This routine just queues the buffer for sending.
@@ -2709,10 +2713,11 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 		     skb_headroom(skb) >= 0xFFFF)) {
 		struct sk_buff *nskb;
 
-		skb_mstamp_get(&skb->skb_mstamp);
 		nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC);
 		err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
 			     -ENOBUFS;
+		if (!err)
+			skb_mstamp_get(&skb->skb_mstamp);
 	} else {
 		err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
 	}
-- 
2.13.6


From f77d768cab0ce4161753cc5829a7ece1f3b0d47e Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Fri, 15 Sep 2017 14:37:38 +0100
Subject: [PATCH 05/32] bpf/verifier: reject BPF_ALU64|BPF_END

[ Upstream commit e67b8a685c7c984e834e3181ef4619cd7025a136 ]

Neither ___bpf_prog_run nor the JITs accept it.
Also adds a new test case.

Fixes: 17a5267067f3 ("bpf: verifier (add verifier core)")
Signed-off-by: Edward Cree <ecree@solarflare.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/bpf/verifier.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 779c871c5dcd..372454aa7f37 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1720,7 +1720,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 			}
 		} else {
 			if (insn->src_reg != BPF_REG_0 || insn->off != 0 ||
-			    (insn->imm != 16 && insn->imm != 32 && insn->imm != 64)) {
+			    (insn->imm != 16 && insn->imm != 32 && insn->imm != 64) ||
+			    BPF_CLASS(insn->code) == BPF_ALU64) {
 				verbose("BPF_END uses reserved fields\n");
 				return -EINVAL;
 			}
-- 
2.13.6


From 0921de99eea17d322bb2a6810759817417d6ae5a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 15 Sep 2017 16:47:42 -0700
Subject: [PATCH 06/32] tcp: fix data delivery rate

[ Upstream commit fc22579917eb7e13433448a342f1cb1592920940 ]

Now skb->mstamp_skb is updated later, we also need to call
tcp_rate_skb_sent() after the update is done.

Fixes: 8c72c65b426b ("tcp: update skb->skb_mstamp more carefully")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index bb2f00b5f200..b44abddf942c 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -925,8 +925,6 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	if (clone_it) {
 		TCP_SKB_CB(skb)->tx.in_flight = TCP_SKB_CB(skb)->end_seq
 			- tp->snd_una;
-		tcp_rate_skb_sent(sk, skb);
-
 		oskb = skb;
 		if (unlikely(skb_cloned(skb)))
 			skb = pskb_copy(skb, gfp_mask);
@@ -1041,9 +1039,10 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 		tcp_enter_cwr(sk);
 		err = net_xmit_eval(err);
 	}
-	if (!err && oskb)
+	if (!err && oskb) {
 		skb_mstamp_get(&oskb->skb_mstamp);
-
+		tcp_rate_skb_sent(sk, oskb);
+	}
 	return err;
 }
 
-- 
2.13.6


From 4d37010e240626012bd27f6fc9300f27051beb9e Mon Sep 17 00:00:00 2001
From: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Date: Wed, 13 Sep 2017 19:30:51 -0600
Subject: [PATCH 07/32] udpv6: Fix the checksum computation when HW checksum
 does not apply

[ Upstream commit 63ecc3d9436f8012e49dc846d6cb0a85a3433517 ]

While trying an ESP transport mode encryption for UDPv6 packets of
datagram size 1436 with MTU 1500, checksum error was observed in
the secondary fragment.

This error occurs due to the UDP payload checksum being missed out
when computing the full checksum for these packets in
udp6_hwcsum_outgoing().

Fixes: d39d938c8228 ("ipv6: Introduce udpv6_send_skb()")
Signed-off-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/udp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 2497f62fa4c2..4db5f541bca6 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -915,6 +915,7 @@ static void udp6_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb,
 		 */
 		offset = skb_transport_offset(skb);
 		skb->csum = skb_checksum(skb, offset, skb->len - offset, 0);
+		csum = skb->csum;
 
 		skb->ip_summed = CHECKSUM_NONE;
 
-- 
2.13.6


From 8a097bf347742b49ab2f10f7b9cee5365c35171b Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Fri, 15 Sep 2017 12:00:07 +0800
Subject: [PATCH 08/32] ip6_gre: skb_push ipv6hdr before packing the header in
 ip6gre_header

[ Upstream commit 76cc0d3282d4b933fa144fa41fbc5318e0fdca24 ]

Now in ip6gre_header before packing the ipv6 header, it skb_push t->hlen
which only includes encap_hlen + tun_hlen. It means greh and inner header
would be over written by ipv6 stuff and ipv6h might have no chance to set
up.

Jianlin found this issue when using remote any on ip6_gre, the packets he
captured on gre dev are truncated:

22:50:26.210866 Out ethertype IPv6 (0x86dd), length 120: truncated-ip6 -\
8128 bytes missing!(flowlabel 0x92f40, hlim 0, next-header Options (0)  \
payload length: 8192) ::1:2000:0 > ::1:0:86dd: HBH [trunc] ip-proto-128 \
8184

It should also skb_push ipv6hdr so that ipv6h points to the right position
to set ipv6 stuff up.

This patch is to skb_push hlen + sizeof(*ipv6h) and also fix some indents
in ip6gre_header.

Fixes: c12b395a4664 ("gre: Support GRE over IPv6")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index f78afe43bdff..b19a0966a5fe 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -936,24 +936,25 @@ static int ip6gre_tunnel_ioctl(struct net_device *dev,
 }
 
 static int ip6gre_header(struct sk_buff *skb, struct net_device *dev,
-			unsigned short type,
-			const void *daddr, const void *saddr, unsigned int len)
+			 unsigned short type, const void *daddr,
+			 const void *saddr, unsigned int len)
 {
 	struct ip6_tnl *t = netdev_priv(dev);
-	struct ipv6hdr *ipv6h = (struct ipv6hdr *)skb_push(skb, t->hlen);
-	__be16 *p = (__be16 *)(ipv6h+1);
+	struct ipv6hdr *ipv6h;
+	__be16 *p;
 
-	ip6_flow_hdr(ipv6h, 0,
-		     ip6_make_flowlabel(dev_net(dev), skb,
-					t->fl.u.ip6.flowlabel, true,
-					&t->fl.u.ip6));
+	ipv6h = (struct ipv6hdr *)skb_push(skb, t->hlen + sizeof(*ipv6h));
+	ip6_flow_hdr(ipv6h, 0, ip6_make_flowlabel(dev_net(dev), skb,
+						  t->fl.u.ip6.flowlabel,
+						  true, &t->fl.u.ip6));
 	ipv6h->hop_limit = t->parms.hop_limit;
 	ipv6h->nexthdr = NEXTHDR_GRE;
 	ipv6h->saddr = t->parms.laddr;
 	ipv6h->daddr = t->parms.raddr;
 
-	p[0]		= t->parms.o_flags;
-	p[1]		= htons(type);
+	p = (__be16 *)(ipv6h + 1);
+	p[0] = t->parms.o_flags;
+	p[1] = htons(type);
 
 	/*
 	 *	Set the source hardware address.
-- 
2.13.6


From 74f8b8faa4cd29ba2b10542e7960c8a621bf3792 Mon Sep 17 00:00:00 2001
From: Fahad Kunnathadi <fahad.kunnathadi@dexceldesigns.com>
Date: Fri, 15 Sep 2017 12:01:58 +0530
Subject: [PATCH 09/32] net: phy: Fix mask value write on gmii2rgmii converter
 speed register

[ Upstream commit f2654a4781318dc7ab8d6cde66f1fa39eab980a9 ]

To clear Speed Selection in MDIO control register(0x10),
ie, clear bits 6 and 13 to zero while keeping other bits same.
Before AND operation,The Mask value has to be perform with bitwise NOT
operation (ie, ~ operator)

This patch clears current speed selection before writing the
new speed settings to gmii2rgmii converter

Fixes: f411a6160bd4 ("net: phy: Add gmiitorgmii converter support")

Signed-off-by: Fahad Kunnathadi <fahad.kunnathadi@dexceldesigns.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/xilinx_gmii2rgmii.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/xilinx_gmii2rgmii.c b/drivers/net/phy/xilinx_gmii2rgmii.c
index d15dd3938ba8..2e5150b0b8d5 100644
--- a/drivers/net/phy/xilinx_gmii2rgmii.c
+++ b/drivers/net/phy/xilinx_gmii2rgmii.c
@@ -44,7 +44,7 @@ static int xgmiitorgmii_read_status(struct phy_device *phydev)
 	priv->phy_drv->read_status(phydev);
 
 	val = mdiobus_read(phydev->mdio.bus, priv->addr, XILINX_GMII2RGMII_REG);
-	val &= XILINX_GMII2RGMII_SPEED_MASK;
+	val &= ~XILINX_GMII2RGMII_SPEED_MASK;
 
 	if (phydev->speed == SPEED_1000)
 		val |= BMCR_SPEED1000;
-- 
2.13.6


From 005e2e4fc81df8258ba48f5a19e6de3d5805ec72 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Fri, 15 Sep 2017 15:58:33 +0800
Subject: [PATCH 10/32] ip6_tunnel: do not allow loading ip6_tunnel if ipv6 is
 disabled in cmdline

[ Upstream commit 8c22dab03ad072e45060c299c70d02a4f6fc4aab ]

If ipv6 has been disabled from cmdline since kernel started, it makes
no sense to allow users to create any ip6 tunnel. Otherwise, it could
some potential problem.

Jianlin found a kernel crash caused by this in ip6_gre when he set
ipv6.disable=1 in grub:

[  209.588865] Unable to handle kernel paging request for data at address 0x00000080
[  209.588872] Faulting instruction address: 0xc000000000a3aa6c
[  209.588879] Oops: Kernel access of bad area, sig: 11 [#1]
[  209.589062] NIP [c000000000a3aa6c] fib_rules_lookup+0x4c/0x260
[  209.589071] LR [c000000000b9ad90] fib6_rule_lookup+0x50/0xb0
[  209.589076] Call Trace:
[  209.589097] fib6_rule_lookup+0x50/0xb0
[  209.589106] rt6_lookup+0xc4/0x110
[  209.589116] ip6gre_tnl_link_config+0x214/0x2f0 [ip6_gre]
[  209.589125] ip6gre_newlink+0x138/0x3a0 [ip6_gre]
[  209.589134] rtnl_newlink+0x798/0xb80
[  209.589142] rtnetlink_rcv_msg+0xec/0x390
[  209.589151] netlink_rcv_skb+0x138/0x150
[  209.589159] rtnetlink_rcv+0x48/0x70
[  209.589169] netlink_unicast+0x538/0x640
[  209.589175] netlink_sendmsg+0x40c/0x480
[  209.589184] ___sys_sendmsg+0x384/0x4e0
[  209.589194] SyS_sendmsg+0xd4/0x140
[  209.589201] SyS_socketcall+0x3e0/0x4f0
[  209.589209] system_call+0x38/0xe0

This patch is to return -EOPNOTSUPP in ip6_tunnel_init if ipv6 has been
disabled from cmdline.

Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 1fc9daa7b1d6..a39f28ffbd63 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -2231,6 +2231,9 @@ static int __init ip6_tunnel_init(void)
 {
 	int  err;
 
+	if (!ipv6_mod_enabled())
+		return -EOPNOTSUPP;
+
 	err = register_pernet_device(&ip6_tnl_net_ops);
 	if (err < 0)
 		goto out_pernet;
-- 
2.13.6


From 6c718790748aa8c6f3a4c4ed5214335e87b8301f Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Sat, 16 Sep 2017 14:02:21 +0200
Subject: [PATCH 11/32] net/sched: cls_matchall: fix crash when used with
 classful qdisc

[ Upstream commit 3ff4cbec87da48b0ec1f7b6196607b034de0c680 ]

this script, edited from Linux Advanced Routing and Traffic Control guide

tc q a dev en0 root handle 1: htb default a
tc c a dev en0 parent 1:  classid 1:1 htb rate 6mbit burst 15k
tc c a dev en0 parent 1:1 classid 1:a htb rate 5mbit ceil 6mbit burst 15k
tc c a dev en0 parent 1:1 classid 1:b htb rate 1mbit ceil 6mbit burst 15k
tc f a dev en0 parent 1:0 prio 1 $clsname $clsargs classid 1:b
ping $address -c1
tc -s c s dev en0

classifies traffic to 1:b or 1:a, depending on whether the packet matches
or not the pattern $clsargs of filter $clsname. However, when $clsname is
'matchall', a systematic crash can be observed in htb_classify(). HTB and
classful qdiscs don't assign initial value to struct tcf_result, but then
they expect it to contain valid values after filters have been run. Thus,
current 'matchall' ignores the TCA_MATCHALL_CLASSID attribute, configured
by user, and makes HTB (and classful qdiscs) dereference random pointers.

By assigning head->res to *res in mall_classify(), before the actions are
invoked, we fix this crash and enable TCA_MATCHALL_CLASSID functionality,
that had no effect on 'matchall' classifier since its first introduction.

BugLink: https://bugzilla.redhat.com/show_bug.cgi?id=1460213
Reported-by: Jiri Benc <jbenc@redhat.com>
Fixes: b87f7936a932 ("net/sched: introduce Match-all classifier")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Yotam Gigi <yotamg@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_matchall.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index b12bc2abea93..e75fb65037d7 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -32,6 +32,7 @@ static int mall_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 	if (tc_skip_sw(head->flags))
 		return -1;
 
+	*res = head->res;
 	return tcf_exts_exec(skb, &head->exts, res);
 }
 
-- 
2.13.6


From e08467e809c37fbedd34ede8bdc906746cb59a30 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 19 Sep 2017 10:05:57 -0700
Subject: [PATCH 12/32] tcp: fastopen: fix on syn-data transmit failure

[ Upstream commit b5b7db8d680464b1d631fd016f5e093419f0bfd9 ]

Our recent change exposed a bug in TCP Fastopen Client that syzkaller
found right away [1]

When we prepare skb with SYN+DATA, we attempt to transmit it,
and we update socket state as if the transmit was a success.

In socket RTX queue we have two skbs, one with the SYN alone,
and a second one containing the DATA.

When (malicious) ACK comes in, we now complain that second one had no
skb_mstamp.

The proper fix is to make sure that if the transmit failed, we do not
pretend we sent the DATA skb, and make it our send_head.

When 3WHS completes, we can now send the DATA right away, without having
to wait for a timeout.

[1]
WARNING: CPU: 0 PID: 100189 at net/ipv4/tcp_input.c:3117 tcp_clean_rtx_queue+0x2057/0x2ab0 net/ipv4/tcp_input.c:3117()

 WARN_ON_ONCE(last_ackt == 0);

Modules linked in:
CPU: 0 PID: 100189 Comm: syz-executor1 Not tainted
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
 0000000000000000 ffff8800b35cb1d8 ffffffff81cad00d 0000000000000000
 ffffffff828a4347 ffff88009f86c080 ffffffff8316eb20 0000000000000d7f
 ffff8800b35cb220 ffffffff812c33c2 ffff8800baad2440 00000009d46575c0
Call Trace:
 [<ffffffff81cad00d>] __dump_stack
 [<ffffffff81cad00d>] dump_stack+0xc1/0x124
 [<ffffffff812c33c2>] warn_slowpath_common+0xe2/0x150
 [<ffffffff812c361e>] warn_slowpath_null+0x2e/0x40
 [<ffffffff828a4347>] tcp_clean_rtx_queue+0x2057/0x2ab0 n
 [<ffffffff828ae6fd>] tcp_ack+0x151d/0x3930
 [<ffffffff828baa09>] tcp_rcv_state_process+0x1c69/0x4fd0
 [<ffffffff828efb7f>] tcp_v4_do_rcv+0x54f/0x7c0
 [<ffffffff8258aacb>] sk_backlog_rcv
 [<ffffffff8258aacb>] __release_sock+0x12b/0x3a0
 [<ffffffff8258ad9e>] release_sock+0x5e/0x1c0
 [<ffffffff8294a785>] inet_wait_for_connect
 [<ffffffff8294a785>] __inet_stream_connect+0x545/0xc50
 [<ffffffff82886f08>] tcp_sendmsg_fastopen
 [<ffffffff82886f08>] tcp_sendmsg+0x2298/0x35a0
 [<ffffffff82952515>] inet_sendmsg+0xe5/0x520
 [<ffffffff8257152f>] sock_sendmsg_nosec
 [<ffffffff8257152f>] sock_sendmsg+0xcf/0x110

Fixes: 8c72c65b426b ("tcp: update skb->skb_mstamp more carefully")
Fixes: 783237e8daf1 ("net-tcp: Fast Open client - sending SYN-data")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index b44abddf942c..85920707c4d3 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3329,6 +3329,10 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 		goto done;
 	}
 
+	/* data was not sent, this is our new send_head */
+	sk->sk_send_head = syn_data;
+	tp->packets_out -= tcp_skb_pcount(syn_data);
+
 fallback:
 	/* Send a regular SYN with Fast Open cookie request option */
 	if (fo->cookie.len > 0)
@@ -3378,6 +3382,11 @@ int tcp_connect(struct sock *sk)
 	 */
 	tp->snd_nxt = tp->write_seq;
 	tp->pushed_seq = tp->write_seq;
+	buff = tcp_send_head(sk);
+	if (unlikely(buff)) {
+		tp->snd_nxt	= TCP_SKB_CB(buff)->seq;
+		tp->pushed_seq	= TCP_SKB_CB(buff)->seq;
+	}
 	TCP_INC_STATS(sock_net(sk), TCP_MIB_ACTIVEOPENS);
 
 	/* Timer for repeating the SYN until an answer. */
-- 
2.13.6


From 319ffa91da584f237eb017f58283d2278b9f57e1 Mon Sep 17 00:00:00 2001
From: Christian Lamparter <chunkeey@googlemail.com>
Date: Tue, 19 Sep 2017 19:35:18 +0200
Subject: [PATCH 13/32] net: emac: Fix napi poll list corruption

[ Upstream commit f55956065ec94e3e9371463d693a1029c4cc3007 ]

This patch is pretty much a carbon copy of
commit 3079c652141f ("caif: Fix napi poll list corruption")
with "caif" replaced by "emac".

The commit d75b1ade567f ("net: less interrupt masking in NAPI")
breaks emac.

It is now required that if the entire budget is consumed when poll
returns, the napi poll_list must remain empty.  However, like some
other drivers emac tries to do a last-ditch check and if there is
more work it will call napi_reschedule and then immediately process
some of this new work.  Should the entire budget be consumed while
processing such new work then we will violate the new caller
contract.

This patch fixes this by not touching any work when we reschedule
in emac.

Signed-off-by: Christian Lamparter <chunkeey@googlemail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ibm/emac/mal.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/ibm/emac/mal.c b/drivers/net/ethernet/ibm/emac/mal.c
index aaf6fec566b5..3660a3d51731 100644
--- a/drivers/net/ethernet/ibm/emac/mal.c
+++ b/drivers/net/ethernet/ibm/emac/mal.c
@@ -402,7 +402,7 @@ static int mal_poll(struct napi_struct *napi, int budget)
 	unsigned long flags;
 
 	MAL_DBG2(mal, "poll(%d)" NL, budget);
- again:
+
 	/* Process TX skbs */
 	list_for_each(l, &mal->poll_list) {
 		struct mal_commac *mc =
@@ -451,7 +451,6 @@ static int mal_poll(struct napi_struct *napi, int budget)
 			spin_lock_irqsave(&mal->lock, flags);
 			mal_disable_eob_irq(mal);
 			spin_unlock_irqrestore(&mal->lock, flags);
-			goto again;
 		}
 		mc->ops->poll_tx(mc->dev);
 	}
-- 
2.13.6


From 826034744dc7c7231c74585953d5eb857e791fb0 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Thu, 14 Sep 2017 17:14:41 -0400
Subject: [PATCH 14/32] packet: hold bind lock when rebinding to fanout hook

[ Upstream commit 008ba2a13f2d04c947adc536d19debb8fe66f110 ]

Packet socket bind operations must hold the po->bind_lock. This keeps
po->running consistent with whether the socket is actually on a ptype
list to receive packets.

fanout_add unbinds a socket and its packet_rcv/tpacket_rcv call, then
binds the fanout object to receive through packet_rcv_fanout.

Make it hold the po->bind_lock when testing po->running and rebinding.
Else, it can race with other rebind operations, such as that in
packet_set_ring from packet_rcv to tpacket_rcv. Concurrent updates
can result in a socket being added to a fanout group twice, causing
use-after-free KASAN bug reports, among others.

Reported independently by both trinity and syzkaller.
Verified that the syzkaller reproducer passes after this patch.

Fixes: dc99f600698d ("packet: Add fanout support.")
Reported-by: nixioaming <nixiaoming@huawei.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 9c92c6cb6a4f..29d5fa508667 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1648,10 +1648,6 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 
 	mutex_lock(&fanout_mutex);
 
-	err = -EINVAL;
-	if (!po->running)
-		goto out;
-
 	err = -EALREADY;
 	if (po->fanout)
 		goto out;
@@ -1700,7 +1696,10 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		list_add(&match->list, &fanout_list);
 	}
 	err = -EINVAL;
-	if (match->type == type &&
+
+	spin_lock(&po->bind_lock);
+	if (po->running &&
+	    match->type == type &&
 	    match->prot_hook.type == po->prot_hook.type &&
 	    match->prot_hook.dev == po->prot_hook.dev) {
 		err = -ENOSPC;
@@ -1712,6 +1711,13 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 			err = 0;
 		}
 	}
+	spin_unlock(&po->bind_lock);
+
+	if (err && !refcount_read(&match->sk_ref)) {
+		list_del(&match->list);
+		kfree(match);
+	}
+
 out:
 	if (err && rollover) {
 		kfree(rollover);
-- 
2.13.6


From b209d1093d59c8435565445def837f6504ab156d Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Mon, 18 Sep 2017 16:38:36 -0700
Subject: [PATCH 15/32] bpf: one perf event close won't free bpf program
 attached by another perf event

[ Upstream commit ec9dd352d591f0c90402ec67a317c1ed4fb2e638 ]

This patch fixes a bug exhibited by the following scenario:
  1. fd1 = perf_event_open with attr.config = ID1
  2. attach bpf program prog1 to fd1
  3. fd2 = perf_event_open with attr.config = ID1
     <this will be successful>
  4. user program closes fd2 and prog1 is detached from the tracepoint.
  5. user program with fd1 does not work properly as tracepoint
     no output any more.

The issue happens at step 4. Multiple perf_event_open can be called
successfully, but only one bpf prog pointer in the tp_event. In the
current logic, any fd release for the same tp_event will free
the tp_event->prog.

The fix is to free tp_event->prog only when the closing fd
corresponds to the one which registered the program.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/trace_events.h | 1 +
 kernel/events/core.c         | 3 ++-
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index be007610ceb0..ba57266d9e80 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -273,6 +273,7 @@ struct trace_event_call {
 	int				perf_refcount;
 	struct hlist_head __percpu	*perf_events;
 	struct bpf_prog			*prog;
+	struct perf_event		*bpf_prog_owner;
 
 	int	(*perf_perm)(struct trace_event_call *,
 			     struct perf_event *);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index c774773ac3a4..36ff2d93f222 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7871,6 +7871,7 @@ static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd)
 		}
 	}
 	event->tp_event->prog = prog;
+	event->tp_event->bpf_prog_owner = event;
 
 	return 0;
 }
@@ -7885,7 +7886,7 @@ static void perf_event_free_bpf_prog(struct perf_event *event)
 		return;
 
 	prog = event->tp_event->prog;
-	if (prog) {
+	if (prog && event->tp_event->bpf_prog_owner == event) {
 		event->tp_event->prog = NULL;
 		bpf_prog_put(prog);
 	}
-- 
2.13.6


From bde381c40a4fc5ebe59269e9b5f4f09455c6f7e9 Mon Sep 17 00:00:00 2001
From: Meng Xu <mengxu.gatech@gmail.com>
Date: Tue, 19 Sep 2017 21:49:55 -0400
Subject: [PATCH 16/32] isdn/i4l: fetch the ppp_write buffer in one shot

[ Upstream commit 02388bf87f72e1d47174cd8f81c34443920eb5a0 ]

In isdn_ppp_write(), the header (i.e., protobuf) of the buffer is
fetched twice from userspace. The first fetch is used to peek at the
protocol of the message and reset the huptimer if necessary; while the
second fetch copies in the whole buffer. However, given that buf resides
in userspace memory, a user process can race to change its memory content
across fetches. By doing so, we can either avoid resetting the huptimer
for any type of packets (by first setting proto to PPP_LCP and later
change to the actual type) or force resetting the huptimer for LCP
packets.

This patch changes this double-fetch behavior into two single fetches
decided by condition (lp->isdn_device < 0 || lp->isdn_channel <0).
A more detailed discussion can be found at
https://marc.info/?l=linux-kernel&m=150586376926123&w=2

Signed-off-by: Meng Xu <mengxu.gatech@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/i4l/isdn_ppp.c | 37 +++++++++++++++++++++++++------------
 1 file changed, 25 insertions(+), 12 deletions(-)

diff --git a/drivers/isdn/i4l/isdn_ppp.c b/drivers/isdn/i4l/isdn_ppp.c
index bf3fbd00a091..64b586458d3d 100644
--- a/drivers/isdn/i4l/isdn_ppp.c
+++ b/drivers/isdn/i4l/isdn_ppp.c
@@ -828,7 +828,6 @@ isdn_ppp_write(int min, struct file *file, const char __user *buf, int count)
 	isdn_net_local *lp;
 	struct ippp_struct *is;
 	int proto;
-	unsigned char protobuf[4];
 
 	is = file->private_data;
 
@@ -842,24 +841,28 @@ isdn_ppp_write(int min, struct file *file, const char __user *buf, int count)
 	if (!lp)
 		printk(KERN_DEBUG "isdn_ppp_write: lp == NULL\n");
 	else {
-		/*
-		 * Don't reset huptimer for
-		 * LCP packets. (Echo requests).
-		 */
-		if (copy_from_user(protobuf, buf, 4))
-			return -EFAULT;
-		proto = PPP_PROTOCOL(protobuf);
-		if (proto != PPP_LCP)
-			lp->huptimer = 0;
+		if (lp->isdn_device < 0 || lp->isdn_channel < 0) {
+			unsigned char protobuf[4];
+			/*
+			 * Don't reset huptimer for
+			 * LCP packets. (Echo requests).
+			 */
+			if (copy_from_user(protobuf, buf, 4))
+				return -EFAULT;
+
+			proto = PPP_PROTOCOL(protobuf);
+			if (proto != PPP_LCP)
+				lp->huptimer = 0;
 
-		if (lp->isdn_device < 0 || lp->isdn_channel < 0)
 			return 0;
+		}
 
 		if ((dev->drv[lp->isdn_device]->flags & DRV_FLAG_RUNNING) &&
 		    lp->dialstate == 0 &&
 		    (lp->flags & ISDN_NET_CONNECTED)) {
 			unsigned short hl;
 			struct sk_buff *skb;
+			unsigned char *cpy_buf;
 			/*
 			 * we need to reserve enough space in front of
 			 * sk_buff. old call to dev_alloc_skb only reserved
@@ -872,11 +875,21 @@ isdn_ppp_write(int min, struct file *file, const char __user *buf, int count)
 				return count;
 			}
 			skb_reserve(skb, hl);
-			if (copy_from_user(skb_put(skb, count), buf, count))
+			cpy_buf = skb_put(skb, count);
+			if (copy_from_user(cpy_buf, buf, count))
 			{
 				kfree_skb(skb);
 				return -EFAULT;
 			}
+
+			/*
+			 * Don't reset huptimer for
+			 * LCP packets. (Echo requests).
+			 */
+			proto = PPP_PROTOCOL(cpy_buf);
+			if (proto != PPP_LCP)
+				lp->huptimer = 0;
+
 			if (is->debug & 0x40) {
 				printk(KERN_DEBUG "ppp xmit: len %d\n", (int) skb->len);
 				isdn_ppp_frame_log("xmit", skb->data, skb->len, 32, is->unit, lp->ppp_slot);
-- 
2.13.6


From effafba884f037b5ce73dc1c706cda7d501c6569 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Date: Wed, 20 Sep 2017 15:45:36 +0300
Subject: [PATCH 17/32] net_sched: always reset qdisc backlog in qdisc_reset()

[ Upstream commit c8e1812960eeae42e2183154927028511c4bc566 ]

SKB stored in qdisc->gso_skb also counted into backlog.

Some qdiscs don't reset backlog to zero in ->reset(),
for example sfq just dequeue and free all queued skb.

Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Fixes: 2ccccf5fb43f ("net_sched: update hierarchical backlog too")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_generic.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 6cfb6e9038c2..9016c8baf2aa 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -681,6 +681,7 @@ void qdisc_reset(struct Qdisc *qdisc)
 		qdisc->gso_skb = NULL;
 	}
 	qdisc->q.qlen = 0;
+	qdisc->qstats.backlog = 0;
 }
 EXPORT_SYMBOL(qdisc_reset);
 
-- 
2.13.6


From 3ef0c01251b3049cc3a166a16e3dfd48d8559867 Mon Sep 17 00:00:00 2001
From: Timur Tabi <timur@codeaurora.org>
Date: Fri, 22 Sep 2017 15:32:44 -0500
Subject: [PATCH 18/32] net: qcom/emac: specify the correct size when mapping a
 DMA buffer

[ Upstream commit a93ad944f4ff9a797abff17c73fc4b1e4a1d9141 ]

When mapping the RX DMA buffers, the driver was accidentally specifying
zero for the buffer length.  Under normal circumstances, SWIOTLB does not
need to allocate a bounce buffer, so the address is just mapped without
checking the size field.  This is why the error was not detected earlier.

Fixes: b9b17debc69d ("net: emac: emac gigabit ethernet controller driver")
Cc: stable@vger.kernel.org
Signed-off-by: Timur Tabi <timur@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qualcomm/emac/emac-mac.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.c b/drivers/net/ethernet/qualcomm/emac/emac-mac.c
index 0b4deb31e742..f683bfbd9986 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac-mac.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.c
@@ -932,7 +932,8 @@ static void emac_mac_rx_descs_refill(struct emac_adapter *adpt,
 
 		curr_rxbuf->dma_addr =
 			dma_map_single(adpt->netdev->dev.parent, skb->data,
-				       curr_rxbuf->length, DMA_FROM_DEVICE);
+				       adpt->rxbuf_size, DMA_FROM_DEVICE);
+
 		ret = dma_mapping_error(adpt->netdev->dev.parent,
 					curr_rxbuf->dma_addr);
 		if (ret) {
-- 
2.13.6


From 32d475d75ec04500924f73a4768d878f8bb61dfe Mon Sep 17 00:00:00 2001
From: Alexey Kodanev <alexey.kodanev@oracle.com>
Date: Tue, 26 Sep 2017 15:14:29 +0300
Subject: [PATCH 19/32] vti: fix use after free in
 vti_tunnel_xmit/vti6_tnl_xmit

[ Upstream commit 36f6ee22d2d66046e369757ec6bbe1c482957ba6 ]

When running LTP IPsec tests, KASan might report:

BUG: KASAN: use-after-free in vti_tunnel_xmit+0xeee/0xff0 [ip_vti]
Read of size 4 at addr ffff880dc6ad1980 by task swapper/0/0
...
Call Trace:
  <IRQ>
  dump_stack+0x63/0x89
  print_address_description+0x7c/0x290
  kasan_report+0x28d/0x370
  ? vti_tunnel_xmit+0xeee/0xff0 [ip_vti]
  __asan_report_load4_noabort+0x19/0x20
  vti_tunnel_xmit+0xeee/0xff0 [ip_vti]
  ? vti_init_net+0x190/0x190 [ip_vti]
  ? save_stack_trace+0x1b/0x20
  ? save_stack+0x46/0xd0
  dev_hard_start_xmit+0x147/0x510
  ? icmp_echo.part.24+0x1f0/0x210
  __dev_queue_xmit+0x1394/0x1c60
...
Freed by task 0:
  save_stack_trace+0x1b/0x20
  save_stack+0x46/0xd0
  kasan_slab_free+0x70/0xc0
  kmem_cache_free+0x81/0x1e0
  kfree_skbmem+0xb1/0xe0
  kfree_skb+0x75/0x170
  kfree_skb_list+0x3e/0x60
  __dev_queue_xmit+0x1298/0x1c60
  dev_queue_xmit+0x10/0x20
  neigh_resolve_output+0x3a8/0x740
  ip_finish_output2+0x5c0/0xe70
  ip_finish_output+0x4ba/0x680
  ip_output+0x1c1/0x3a0
  xfrm_output_resume+0xc65/0x13d0
  xfrm_output+0x1e4/0x380
  xfrm4_output_finish+0x5c/0x70

Can be fixed if we get skb->len before dst_output().

Fixes: b9959fd3b0fa ("vti: switch to new ip tunnel code")
Fixes: 22e1b23dafa8 ("vti6: Support inter address family tunneling.")
Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_vti.c  | 3 ++-
 net/ipv6/ip6_vti.c | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 5d7944f394d9..b120b9b11402 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -168,6 +168,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
 	struct ip_tunnel_parm *parms = &tunnel->parms;
 	struct dst_entry *dst = skb_dst(skb);
 	struct net_device *tdev;	/* Device to other host */
+	int pkt_len = skb->len;
 	int err;
 	int mtu;
 
@@ -229,7 +230,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
 
 	err = dst_output(tunnel->net, skb->sk, skb);
 	if (net_xmit_eval(err) == 0)
-		err = skb->len;
+		err = pkt_len;
 	iptunnel_xmit_stats(dev, err);
 	return NETDEV_TX_OK;
 
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 66c2b4b41793..816f79d1a8a3 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -445,6 +445,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 	struct dst_entry *dst = skb_dst(skb);
 	struct net_device *tdev;
 	struct xfrm_state *x;
+	int pkt_len = skb->len;
 	int err = -1;
 	int mtu;
 
@@ -498,7 +499,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 		struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
 
 		u64_stats_update_begin(&tstats->syncp);
-		tstats->tx_bytes += skb->len;
+		tstats->tx_bytes += pkt_len;
 		tstats->tx_packets++;
 		u64_stats_update_end(&tstats->syncp);
 	} else {
-- 
2.13.6


From 4db30cf4f61aeb912b33bb4e3525ee4cfa2f5047 Mon Sep 17 00:00:00 2001
From: Ridge Kennedy <ridge.kennedy@alliedtelesis.co.nz>
Date: Wed, 22 Feb 2017 14:59:49 +1300
Subject: [PATCH 20/32] l2tp: Avoid schedule while atomic in exit_net

[ Upstream commit 12d656af4e3d2781b9b9f52538593e1717e7c979 ]

While destroying a network namespace that contains a L2TP tunnel a
"BUG: scheduling while atomic" can be observed.

Enabling lockdep shows that this is happening because l2tp_exit_net()
is calling l2tp_tunnel_closeall() (via l2tp_tunnel_delete()) from
within an RCU critical section.

l2tp_exit_net() takes rcu_read_lock_bh()
  << list_for_each_entry_rcu() >>
  l2tp_tunnel_delete()
    l2tp_tunnel_closeall()
      __l2tp_session_unhash()
        synchronize_rcu() << Illegal inside RCU critical section >>

BUG: sleeping function called from invalid context
in_atomic(): 1, irqs_disabled(): 0, pid: 86, name: kworker/u16:2
INFO: lockdep is turned off.
CPU: 2 PID: 86 Comm: kworker/u16:2 Tainted: G        W  O    4.4.6-at1 #2
Hardware name: Xen HVM domU, BIOS 4.6.1-xs125300 05/09/2016
Workqueue: netns cleanup_net
 0000000000000000 ffff880202417b90 ffffffff812b0013 ffff880202410ac0
 ffffffff81870de8 ffff880202417bb8 ffffffff8107aee8 ffffffff81870de8
 0000000000000c51 0000000000000000 ffff880202417be0 ffffffff8107b024
Call Trace:
 [<ffffffff812b0013>] dump_stack+0x85/0xc2
 [<ffffffff8107aee8>] ___might_sleep+0x148/0x240
 [<ffffffff8107b024>] __might_sleep+0x44/0x80
 [<ffffffff810b21bd>] synchronize_sched+0x2d/0xe0
 [<ffffffff8109be6d>] ? trace_hardirqs_on+0xd/0x10
 [<ffffffff8105c7bb>] ? __local_bh_enable_ip+0x6b/0xc0
 [<ffffffff816a1b00>] ? _raw_spin_unlock_bh+0x30/0x40
 [<ffffffff81667482>] __l2tp_session_unhash+0x172/0x220
 [<ffffffff81667397>] ? __l2tp_session_unhash+0x87/0x220
 [<ffffffff8166888b>] l2tp_tunnel_closeall+0x9b/0x140
 [<ffffffff81668c74>] l2tp_tunnel_delete+0x14/0x60
 [<ffffffff81668dd0>] l2tp_exit_net+0x110/0x270
 [<ffffffff81668d5c>] ? l2tp_exit_net+0x9c/0x270
 [<ffffffff815001c3>] ops_exit_list.isra.6+0x33/0x60
 [<ffffffff81501166>] cleanup_net+0x1b6/0x280
 ...

This bug can easily be reproduced with a few steps:

 $ sudo unshare -n bash  # Create a shell in a new namespace
 # ip link set lo up
 # ip addr add 127.0.0.1 dev lo
 # ip l2tp add tunnel remote 127.0.0.1 local 127.0.0.1 tunnel_id 1 \
    peer_tunnel_id 1 udp_sport 50000 udp_dport 50000
 # ip l2tp add session name foo tunnel_id 1 session_id 1 \
    peer_session_id 1
 # ip link set foo up
 # exit  # Exit the shell, in turn exiting the namespace
 $ dmesg
 ...
 [942121.089216] BUG: scheduling while atomic: kworker/u16:3/13872/0x00000200
 ...

To fix this, move the call to l2tp_tunnel_closeall() out of the RCU
critical section, and instead call it from l2tp_tunnel_del_work(), which
is running from the l2tp_wq workqueue.

Fixes: 2b551c6e7d5b ("l2tp: close sessions before initiating tunnel delete")
Signed-off-by: Ridge Kennedy <ridge.kennedy@alliedtelesis.co.nz>
Acked-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 3bce65183c95..3415e20f0065 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1415,6 +1415,9 @@ static void l2tp_tunnel_del_work(struct work_struct *work)
 	struct sock *sk = NULL;
 
 	tunnel = container_of(work, struct l2tp_tunnel, del_work);
+
+	l2tp_tunnel_closeall(tunnel);
+
 	sk = l2tp_tunnel_sock_lookup(tunnel);
 	if (!sk)
 		goto out;
@@ -1737,7 +1740,6 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_create);
 int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel)
 {
 	l2tp_tunnel_inc_refcount(tunnel);
-	l2tp_tunnel_closeall(tunnel);
 	if (false == queue_work(l2tp_wq, &tunnel->del_work)) {
 		l2tp_tunnel_dec_refcount(tunnel);
 		return 1;
-- 
2.13.6


From f773a38ca6d6c5895d89869c5c60b8a8b2bf5c4b Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 26 Sep 2017 16:16:43 +0200
Subject: [PATCH 21/32] l2tp: fix race condition in l2tp_tunnel_delete

[ Upstream commit 62b982eeb4589b2e6d7c01a90590e3a4c2b2ca19 ]

If we try to delete the same tunnel twice, the first delete operation
does a lookup (l2tp_tunnel_get), finds the tunnel, calls
l2tp_tunnel_delete, which queues it for deletion by
l2tp_tunnel_del_work.

The second delete operation also finds the tunnel and calls
l2tp_tunnel_delete. If the workqueue has already fired and started
running l2tp_tunnel_del_work, then l2tp_tunnel_delete will queue the
same tunnel a second time, and try to free the socket again.

Add a dead flag to prevent firing the workqueue twice. Then we can
remove the check of queue_work's result that was meant to prevent that
race but doesn't.

Reproducer:

    ip l2tp add tunnel tunnel_id 3000 peer_tunnel_id 4000 local 192.168.0.2 remote 192.168.0.1 encap udp udp_sport 5000 udp_dport 6000
    ip l2tp add session name l2tp1 tunnel_id 3000 session_id 1000 peer_session_id 2000
    ip link set l2tp1 up
    ip l2tp del tunnel tunnel_id 3000
    ip l2tp del tunnel tunnel_id 3000

Fixes: f8ccac0e4493 ("l2tp: put tunnel socket release on a workqueue")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Acked-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 10 ++++------
 net/l2tp/l2tp_core.h |  5 ++++-
 2 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 3415e20f0065..b06acd0f400d 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1737,14 +1737,12 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_create);
 
 /* This function is used by the netlink TUNNEL_DELETE command.
  */
-int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel)
+void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel)
 {
-	l2tp_tunnel_inc_refcount(tunnel);
-	if (false == queue_work(l2tp_wq, &tunnel->del_work)) {
-		l2tp_tunnel_dec_refcount(tunnel);
-		return 1;
+	if (!test_and_set_bit(0, &tunnel->dead)) {
+		l2tp_tunnel_inc_refcount(tunnel);
+		queue_work(l2tp_wq, &tunnel->del_work);
 	}
-	return 0;
 }
 EXPORT_SYMBOL_GPL(l2tp_tunnel_delete);
 
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 0095012509ac..42419f1c24cf 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -169,6 +169,9 @@ struct l2tp_tunnel_cfg {
 
 struct l2tp_tunnel {
 	int			magic;		/* Should be L2TP_TUNNEL_MAGIC */
+
+	unsigned long		dead;
+
 	struct rcu_head rcu;
 	rwlock_t		hlist_lock;	/* protect session_hlist */
 	struct hlist_head	session_hlist[L2TP_HASH_SIZE];
@@ -257,7 +260,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id,
 		       u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg,
 		       struct l2tp_tunnel **tunnelp);
 void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel);
-int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel);
+void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel);
 struct l2tp_session *l2tp_session_create(int priv_size,
 					 struct l2tp_tunnel *tunnel,
 					 u32 session_id, u32 peer_session_id,
-- 
2.13.6


From ca96e4f0cd2cad59f1c657f8ca8e802932163f01 Mon Sep 17 00:00:00 2001
From: Alexander Potapenko <glider@google.com>
Date: Thu, 28 Sep 2017 11:32:37 +0200
Subject: [PATCH 22/32] tun: bail out from tun_get_user() if the skb is empty

[ Upstream commit 2580c4c17aee3ad58e9751012bad278dd074ccae ]

KMSAN (https://github.com/google/kmsan) reported accessing uninitialized
skb->data[0] in the case the skb is empty (i.e. skb->len is 0):

================================================
BUG: KMSAN: use of uninitialized memory in tun_get_user+0x19ba/0x3770
CPU: 0 PID: 3051 Comm: probe Not tainted 4.13.0+ #3140
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
Call Trace:
...
 __msan_warning_32+0x66/0xb0 mm/kmsan/kmsan_instr.c:477
 tun_get_user+0x19ba/0x3770 drivers/net/tun.c:1301
 tun_chr_write_iter+0x19f/0x300 drivers/net/tun.c:1365
 call_write_iter ./include/linux/fs.h:1743
 new_sync_write fs/read_write.c:457
 __vfs_write+0x6c3/0x7f0 fs/read_write.c:470
 vfs_write+0x3e4/0x770 fs/read_write.c:518
 SYSC_write+0x12f/0x2b0 fs/read_write.c:565
 SyS_write+0x55/0x80 fs/read_write.c:557
 do_syscall_64+0x242/0x330 arch/x86/entry/common.c:284
 entry_SYSCALL64_slow_path+0x25/0x25 arch/x86/entry/entry_64.S:245
...
origin:
...
 kmsan_poison_shadow+0x6e/0xc0 mm/kmsan/kmsan.c:211
 slab_alloc_node mm/slub.c:2732
 __kmalloc_node_track_caller+0x351/0x370 mm/slub.c:4351
 __kmalloc_reserve net/core/skbuff.c:138
 __alloc_skb+0x26a/0x810 net/core/skbuff.c:231
 alloc_skb ./include/linux/skbuff.h:903
 alloc_skb_with_frags+0x1d7/0xc80 net/core/skbuff.c:4756
 sock_alloc_send_pskb+0xabf/0xfe0 net/core/sock.c:2037
 tun_alloc_skb drivers/net/tun.c:1144
 tun_get_user+0x9a8/0x3770 drivers/net/tun.c:1274
 tun_chr_write_iter+0x19f/0x300 drivers/net/tun.c:1365
 call_write_iter ./include/linux/fs.h:1743
 new_sync_write fs/read_write.c:457
 __vfs_write+0x6c3/0x7f0 fs/read_write.c:470
 vfs_write+0x3e4/0x770 fs/read_write.c:518
 SYSC_write+0x12f/0x2b0 fs/read_write.c:565
 SyS_write+0x55/0x80 fs/read_write.c:557
 do_syscall_64+0x242/0x330 arch/x86/entry/common.c:284
 return_from_SYSCALL_64+0x0/0x6a arch/x86/entry/entry_64.S:245
================================================

Make sure tun_get_user() doesn't touch skb->data[0] unless there is
actual data.

C reproducer below:
==========================
    // autogenerated by syzkaller (http://github.com/google/syzkaller)

    #define _GNU_SOURCE

    #include <fcntl.h>
    #include <linux/if_tun.h>
    #include <netinet/ip.h>
    #include <net/if.h>
    #include <string.h>
    #include <sys/ioctl.h>

    int main()
    {
      int sock = socket(PF_INET, SOCK_STREAM, IPPROTO_IP);
      int tun_fd = open("/dev/net/tun", O_RDWR);
      struct ifreq req;
      memset(&req, 0, sizeof(struct ifreq));
      strcpy((char*)&req.ifr_name, "gre0");
      req.ifr_flags = IFF_UP | IFF_MULTICAST;
      ioctl(tun_fd, TUNSETIFF, &req);
      ioctl(sock, SIOCSIFFLAGS, "gre0");
      write(tun_fd, "hi", 0);
      return 0;
    }
==========================

Signed-off-by: Alexander Potapenko <glider@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index a931b73393c8..ba7f9e054c4a 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1279,11 +1279,13 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	switch (tun->flags & TUN_TYPE_MASK) {
 	case IFF_TUN:
 		if (tun->flags & IFF_NO_PI) {
-			switch (skb->data[0] & 0xf0) {
-			case 0x40:
+			u8 ip_version = skb->len ? (skb->data[0] >> 4) : 0;
+
+			switch (ip_version) {
+			case 4:
 				pi.proto = htons(ETH_P_IP);
 				break;
-			case 0x60:
+			case 6:
 				pi.proto = htons(ETH_P_IPV6);
 				break;
 			default:
-- 
2.13.6


From 0c7d2e298cfb1ccb4f0f2538ad5f091eacb6dd78 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Mon, 25 Sep 2017 15:55:53 -0700
Subject: [PATCH 23/32] net: dsa: Fix network device registration order

[ Upstream commit e804441cfe0b60f6c430901946a69c01eac09df1 ]

We cannot be registering the network device first, then setting its
carrier off and finally connecting it to a PHY, doing that leaves a
window during which the carrier is at best inconsistent, and at worse
the device is not usable without a down/up sequence since the network
device is visible to user space with possibly no PHY device attached.

Re-order steps so that they make logical sense. This fixes some devices
where the port was not usable after e.g: an unbind then bind of the
driver.

Fixes: 0071f56e46da ("dsa: Register netdev before phy")
Fixes: 91da11f870f0 ("net: Distributed Switch Architecture protocol support")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/slave.c | 28 +++++++++++++++++-----------
 1 file changed, 17 insertions(+), 11 deletions(-)

diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 079d76bc204c..5000e6f20f4a 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -1269,26 +1269,32 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent,
 	p->old_duplex = -1;
 
 	ds->ports[port].netdev = slave_dev;
-	ret = register_netdev(slave_dev);
-	if (ret) {
-		netdev_err(master, "error %d registering interface %s\n",
-			   ret, slave_dev->name);
-		ds->ports[port].netdev = NULL;
-		free_netdev(slave_dev);
-		return ret;
-	}
 
 	netif_carrier_off(slave_dev);
 
 	ret = dsa_slave_phy_setup(p, slave_dev);
 	if (ret) {
 		netdev_err(master, "error %d setting up slave phy\n", ret);
-		unregister_netdev(slave_dev);
-		free_netdev(slave_dev);
-		return ret;
+		goto out_free;
+	}
+
+	ret = register_netdev(slave_dev);
+	if (ret) {
+		netdev_err(master, "error %d registering interface %s\n",
+			   ret, slave_dev->name);
+		goto out_phy;
 	}
 
 	return 0;
+
+out_phy:
+	phy_disconnect(p->phy);
+	if (of_phy_is_fixed_link(ds->ports[port].dn))
+		of_phy_deregister_fixed_link(ds->ports[port].dn);
+out_free:
+	free_netdev(slave_dev);
+	ds->ports[port].netdev = NULL;
+	return ret;
 }
 
 void dsa_slave_destroy(struct net_device *slave_dev)
-- 
2.13.6


From 94878679b735b421fc70707d274af7bb1b05a0ef Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Tue, 26 Sep 2017 12:19:37 -0400
Subject: [PATCH 24/32] packet: in packet_do_bind, test fanout with bind_lock
 held

[ Upstream commit 4971613c1639d8e5f102c4e797c3bf8f83a5a69e ]

Once a socket has po->fanout set, it remains a member of the group
until it is destroyed. The prot_hook must be constant and identical
across sockets in the group.

If fanout_add races with packet_do_bind between the test of po->fanout
and taking the lock, the bind call may make type or dev inconsistent
with that of the fanout group.

Hold po->bind_lock when testing po->fanout to avoid this race.

I had to introduce artificial delay (local_bh_enable) to actually
observe the race.

Fixes: dc99f600698d ("packet: Add fanout support.")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 29d5fa508667..0856c125b06d 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3069,13 +3069,15 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex,
 	int ret = 0;
 	bool unlisted = false;
 
-	if (po->fanout)
-		return -EINVAL;
-
 	lock_sock(sk);
 	spin_lock(&po->bind_lock);
 	rcu_read_lock();
 
+	if (po->fanout) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
 	if (name) {
 		dev = dev_get_by_name_rcu(sock_net(sk), name);
 		if (!dev) {
-- 
2.13.6


From 9b58ad668b655a0790be7d7178cc6de05399b5a3 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Tue, 26 Sep 2017 12:20:17 -0400
Subject: [PATCH 25/32] packet: only test po->has_vnet_hdr once in packet_snd

[ Upstream commit da7c9561015e93d10fe6aab73e9288e0d09d65a6 ]

Packet socket option po->has_vnet_hdr can be updated concurrently with
other operations if no ring is attached.

Do not test the option twice in packet_snd, as the value may change in
between calls. A race on setsockopt disable may cause a packet > mtu
to be sent without having GSO options set.

Fixes: bfd5f4a3d605 ("packet: Add GSO/csum offload support.")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 0856c125b06d..b17f9097c6fe 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1713,7 +1713,7 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 	}
 	spin_unlock(&po->bind_lock);
 
-	if (err && !refcount_read(&match->sk_ref)) {
+	if (err && !atomic_read(&match->sk_ref)) {
 		list_del(&match->list);
 		kfree(match);
 	}
@@ -2838,6 +2838,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	struct virtio_net_hdr vnet_hdr = { 0 };
 	int offset = 0;
 	struct packet_sock *po = pkt_sk(sk);
+	bool has_vnet_hdr = false;
 	int hlen, tlen, linear;
 	int extra_len = 0;
 
@@ -2881,6 +2882,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		err = packet_snd_vnet_parse(msg, &len, &vnet_hdr);
 		if (err)
 			goto out_unlock;
+		has_vnet_hdr = true;
 	}
 
 	if (unlikely(sock_flag(sk, SOCK_NOFCS))) {
@@ -2941,7 +2943,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 
 	packet_pick_tx_queue(dev, skb);
 
-	if (po->has_vnet_hdr) {
+	if (has_vnet_hdr) {
 		err = packet_snd_vnet_gso(skb, &vnet_hdr);
 		if (err)
 			goto out_free;
-- 
2.13.6


From 6ed905c415a13e7067315f924cad11bb5a111cf3 Mon Sep 17 00:00:00 2001
From: Christoph Paasch <cpaasch@apple.com>
Date: Tue, 26 Sep 2017 17:38:50 -0700
Subject: [PATCH 26/32] net: Set sk_prot_creator when cloning sockets to the
 right proto

[ Upstream commit 9d538fa60bad4f7b23193c89e843797a1cf71ef3 ]

sk->sk_prot and sk->sk_prot_creator can differ when the app uses
IPV6_ADDRFORM (transforming an IPv6-socket to an IPv4-one).
Which is why sk_prot_creator is there to make sure that sk_prot_free()
does the kmem_cache_free() on the right kmem_cache slab.

Now, if such a socket gets transformed back to a listening socket (using
connect() with AF_UNSPEC) we will allocate an IPv4 tcp_sock through
sk_clone_lock() when a new connection comes in. But sk_prot_creator will
still point to the IPv6 kmem_cache (as everything got copied in
sk_clone_lock()). When freeing, we will thus put this
memory back into the IPv6 kmem_cache although it was allocated in the
IPv4 cache. I have seen memory corruption happening because of this.

With slub-debugging and MEMCG_KMEM enabled this gives the warning
	"cache_from_obj: Wrong slab cache. TCPv6 but object is from TCP"

A C-program to trigger this:

void main(void)
{
        int fd = socket(AF_INET6, SOCK_STREAM, IPPROTO_TCP);
        int new_fd, newest_fd, client_fd;
        struct sockaddr_in6 bind_addr;
        struct sockaddr_in bind_addr4, client_addr1, client_addr2;
        struct sockaddr unsp;
        int val;

        memset(&bind_addr, 0, sizeof(bind_addr));
        bind_addr.sin6_family = AF_INET6;
        bind_addr.sin6_port = ntohs(42424);

        memset(&client_addr1, 0, sizeof(client_addr1));
        client_addr1.sin_family = AF_INET;
        client_addr1.sin_port = ntohs(42424);
        client_addr1.sin_addr.s_addr = inet_addr("127.0.0.1");

        memset(&client_addr2, 0, sizeof(client_addr2));
        client_addr2.sin_family = AF_INET;
        client_addr2.sin_port = ntohs(42421);
        client_addr2.sin_addr.s_addr = inet_addr("127.0.0.1");

        memset(&unsp, 0, sizeof(unsp));
        unsp.sa_family = AF_UNSPEC;

        bind(fd, (struct sockaddr *)&bind_addr, sizeof(bind_addr));

        listen(fd, 5);

        client_fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
        connect(client_fd, (struct sockaddr *)&client_addr1, sizeof(client_addr1));
        new_fd = accept(fd, NULL, NULL);
        close(fd);

        val = AF_INET;
        setsockopt(new_fd, SOL_IPV6, IPV6_ADDRFORM, &val, sizeof(val));

        connect(new_fd, &unsp, sizeof(unsp));

        memset(&bind_addr4, 0, sizeof(bind_addr4));
        bind_addr4.sin_family = AF_INET;
        bind_addr4.sin_port = ntohs(42421);
        bind(new_fd, (struct sockaddr *)&bind_addr4, sizeof(bind_addr4));

        listen(new_fd, 5);

        client_fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
        connect(client_fd, (struct sockaddr *)&client_addr2, sizeof(client_addr2));

        newest_fd = accept(new_fd, NULL, NULL);
        close(new_fd);

        close(client_fd);
        close(new_fd);
}

As far as I can see, this bug has been there since the beginning of the
git-days.

Signed-off-by: Christoph Paasch <cpaasch@apple.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/core/sock.c b/net/core/sock.c
index 1989b3dd6d17..231c38d91855 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1493,6 +1493,8 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 
 		sock_copy(newsk, sk);
 
+		newsk->sk_prot_creator = sk->sk_prot;
+
 		/* SANITY */
 		if (likely(newsk->sk_net_refcnt))
 			get_net(sock_net(newsk));
-- 
2.13.6


From bfe2110a283384374fee3ad6a143e5ffbfa1bd7b Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Thu, 28 Sep 2017 00:41:44 +0200
Subject: [PATCH 27/32] netlink: do not proceed if dump's start() errs

[ Upstream commit fef0035c0f31322d417d1954bba5ab959bf91183 ]

Drivers that use the start method for netlink dumping rely on dumpit not
being called if start fails. For example, ila_xlat.c allocates memory
and assigns it to cb->args[0] in its start() function. It might fail to
do that and return -ENOMEM instead. However, even when returning an
error, dumpit will be called, which, in the example above, quickly
dereferences the memory in cb->args[0], which will OOPS the kernel. This
is but one example of how this goes wrong.

Since start() has always been a function with an int return type, it
therefore makes sense to use it properly, rather than ignoring it. This
patch thus returns early and does not call dumpit() when start() fails.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
Reviewed-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 246f29d365c0..2a5775f8a6ca 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2211,10 +2211,13 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 
 	mutex_unlock(nlk->cb_mutex);
 
+	ret = 0;
 	if (cb->start)
-		cb->start(cb);
+		ret = cb->start(cb);
+
+	if (!ret)
+		ret = netlink_dump(sk);
 
-	ret = netlink_dump(sk);
 	sock_put(sk);
 
 	if (ret)
-- 
2.13.6


From 27f3300f390e9d316557bbf608f9991b7fb6b64a Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 28 Sep 2017 13:23:50 +0800
Subject: [PATCH 28/32] ip6_gre: ip6gre_tap device should keep dst

[ Upstream commit 2d40557cc702ed8e5edd9bd422233f86652d932e ]

The patch 'ip_gre: ipgre_tap device should keep dst' fixed
a issue that ipgre_tap mtu couldn't be updated in tx path.

The same fix is needed for ip6gre_tap as well.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index b19a0966a5fe..41c10486cf7e 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1298,6 +1298,7 @@ static void ip6gre_tap_setup(struct net_device *dev)
 	dev->features |= NETIF_F_NETNS_LOCAL;
 	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
+	netif_keep_dst(dev);
 }
 
 static bool ip6gre_netlink_encap_parms(struct nlattr *data[],
-- 
2.13.6


From 1a4dec15e08fc6642d400de92ef1bc7929908afb Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 28 Sep 2017 13:24:07 +0800
Subject: [PATCH 29/32] ip6_tunnel: update mtu properly for ARPHRD_ETHER tunnel
 device in tx path

[ Upstream commit d41bb33ba33b8f8debe54ed36be6925eb496e354 ]

Now when updating mtu in tx path, it doesn't consider ARPHRD_ETHER tunnel
device, like ip6gre_tap tunnel, for which it should also subtract ether
header to get the correct mtu.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index a39f28ffbd63..12b2fd512f32 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1042,6 +1042,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 	struct dst_entry *dst = NULL, *ndst = NULL;
 	struct net_device *tdev;
 	int mtu;
+	unsigned int eth_hlen = t->dev->type == ARPHRD_ETHER ? ETH_HLEN : 0;
 	unsigned int psh_hlen = sizeof(struct ipv6hdr) + t->encap_hlen;
 	unsigned int max_headroom = psh_hlen;
 	bool use_cache = false;
@@ -1120,7 +1121,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 				     t->parms.name);
 		goto tx_err_dst_release;
 	}
-	mtu = dst_mtu(dst) - psh_hlen - t->tun_hlen;
+	mtu = dst_mtu(dst) - eth_hlen - psh_hlen - t->tun_hlen;
 	if (encap_limit >= 0) {
 		max_headroom += 8;
 		mtu -= 8;
@@ -1129,7 +1130,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 		mtu = IPV6_MIN_MTU;
 	if (skb_dst(skb) && !t->parms.collect_md)
 		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
-	if (skb->len - t->tun_hlen > mtu && !skb_is_gso(skb)) {
+	if (skb->len - t->tun_hlen - eth_hlen > mtu && !skb_is_gso(skb)) {
 		*pmtu = mtu;
 		err = -EMSGSIZE;
 		goto tx_err_dst_release;
-- 
2.13.6


From baa2828121e5b6fb42ef8762be2009db8d06f631 Mon Sep 17 00:00:00 2001
From: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
Date: Fri, 29 Sep 2017 10:02:54 +0200
Subject: [PATCH 30/32] tipc: use only positive error codes in messages

[ Upstream commit aad06212d36cf34859428a0a279e5c14ee5c9e26 ]

In commit e3a77561e7d32 ("tipc: split up function tipc_msg_eval()"),
we have updated the function tipc_msg_lookup_dest() to set the error
codes to negative values at destination lookup failures. Thus when
the function sets the error code to -TIPC_ERR_NO_NAME, its inserted
into the 4 bit error field of the message header as 0xf instead of
TIPC_ERR_NO_NAME (1). The value 0xf is an unknown error code.

In this commit, we set only positive error code.

Fixes: e3a77561e7d32 ("tipc: split up function tipc_msg_eval()")
Signed-off-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/msg.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index 56ea0adcd285..912f1fb97c06 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -547,7 +547,7 @@ bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err)
 		return false;
 	if (msg_errcode(msg))
 		return false;
-	*err = -TIPC_ERR_NO_NAME;
+	*err = TIPC_ERR_NO_NAME;
 	if (skb_linearize(skb))
 		return false;
 	msg = buf_msg(skb);
-- 
2.13.6


From 3c7dae064b30dff5607814686a3fddf574abfbcb Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Tue, 3 Oct 2017 13:20:48 +0300
Subject: [PATCH 31/32] net: rtnetlink: fix info leak in RTM_GETSTATS call

[ Upstream commit ce024f42c2e28b6bce4ecc1e891b42f57f753892 ]

When RTM_GETSTATS was added the fields of its header struct were not all
initialized when returning the result thus leaking 4 bytes of information
to user-space per rtnl_fill_statsinfo call, so initialize them now. Thanks
to Alexander Potapenko for the detailed report and bisection.

Reported-by: Alexander Potapenko <glider@google.com>
Fixes: 10c9ead9f3c6 ("rtnetlink: add new RTM_GETSTATS message to dump link stats")
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Acked-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 4d2629781e8b..c2339b865164 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3758,6 +3758,9 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev,
 		return -EMSGSIZE;
 
 	ifsm = nlmsg_data(nlh);
+	ifsm->family = PF_UNSPEC;
+	ifsm->pad1 = 0;
+	ifsm->pad2 = 0;
 	ifsm->ifindex = dev->ifindex;
 	ifsm->filter_mask = filter_mask;
 
-- 
2.13.6


From 3b0f3109fa95647a4a7d2f6b90cbf432a81cc31e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 2 Oct 2017 12:20:51 -0700
Subject: [PATCH 32/32] socket, bpf: fix possible use after free

[ Upstream commit eefca20eb20c66b06cf5ed09b49b1a7caaa27b7b ]

Starting from linux-4.4, 3WHS no longer takes the listener lock.

Since this time, we might hit a use-after-free in sk_filter_charge(),
if the filter we got in the memcpy() of the listener content
just happened to be replaced by a thread changing listener BPF filter.

To fix this, we need to make sure the filter refcount is not already
zero before incrementing it again.

Fixes: e994b2f0fb92 ("tcp: do not lock listener to process SYN packets")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/filter.c | 15 +++++++++++++--
 net/core/sock.c   |  5 ++++-
 2 files changed, 17 insertions(+), 3 deletions(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index 4eb4ce0aeef4..bfeedbbde214 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -937,20 +937,31 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
 /* try to charge the socket memory if there is space available
  * return true on success
  */
-bool sk_filter_charge(struct sock *sk, struct sk_filter *fp)
+static bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp)
 {
 	u32 filter_size = bpf_prog_size(fp->prog->len);
 
 	/* same check as in sock_kmalloc() */
 	if (filter_size <= sysctl_optmem_max &&
 	    atomic_read(&sk->sk_omem_alloc) + filter_size < sysctl_optmem_max) {
-		atomic_inc(&fp->refcnt);
 		atomic_add(filter_size, &sk->sk_omem_alloc);
 		return true;
 	}
 	return false;
 }
 
+bool sk_filter_charge(struct sock *sk, struct sk_filter *fp)
+{
+	if (!atomic_inc_not_zero(&fp->refcnt))
+		return false;
+
+	if (!__sk_filter_charge(sk, fp)) {
+		sk_filter_release(fp);
+		return false;
+	}
+	return true;
+}
+
 static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp)
 {
 	struct sock_filter *old_prog;
diff --git a/net/core/sock.c b/net/core/sock.c
index 231c38d91855..2a77cc50f021 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1528,13 +1528,16 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		sock_reset_flag(newsk, SOCK_DONE);
 		skb_queue_head_init(&newsk->sk_error_queue);
 
-		filter = rcu_dereference_protected(newsk->sk_filter, 1);
+		rcu_read_lock();
+		filter = rcu_dereference(sk->sk_filter);
 		if (filter != NULL)
 			/* though it's an empty new sock, the charging may fail
 			 * if sysctl_optmem_max was changed between creation of
 			 * original socket and cloning
 			 */
 			is_charged = sk_filter_charge(newsk, filter);
+		RCU_INIT_POINTER(newsk->sk_filter, filter);
+		rcu_read_unlock();
 
 		if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) {
 			/* We need to make sure that we don't uncharge the new
-- 
2.13.6

Re: [PATCHES] Networking

[Greg KH]

On Mon, Oct 09, 2017 at 03:54:34PM -0700, David Miller wrote:
> From: Greg KH <greg@kroah.com>
> Date: Mon, 9 Oct 2017 21:04:20 +0200
> 
> > On Mon, Oct 09, 2017 at 09:55:02AM -0700, David Miller wrote:
> >> From: Greg KH <greg@kroah.com>
> >> Date: Mon, 9 Oct 2017 09:56:48 +0200
> >> 
> >> > On Mon, Oct 09, 2017 at 09:34:06AM +0200, Greg KH wrote:
> >> >> On Sun, Oct 08, 2017 at 09:02:19PM -0700, David Miller wrote:
> >> >> > 
> >> >> > Please queue up the following bug fixes for 4.13.x -stable.
> >> >> 
> >> >> Thanks for the patches, all now queued up.
> >> > 
> >> > Oh, just curious, are you going to have a mbox of patches for 4.9-stable
> >> > as well?  If not, no worries, I'll do the backporting, just didn't want
> >> > to duplicate any work here.
> >> 
> >> Let me see if I can cook that up today, otherwise I'll let you know that
> >> I won't be able to do it.
> >> 
> >> You know what actually happened?  I got confused by the ordering of the
> >> stable trees on www.kernel.org, I think it should be ordered by release
> >> number rather than trying to group 'stable' vs. 'longterm'.
> > 
> > Ah, crap, that's my fault, let me go fix the website, it should be
> > ordered that way, I messed up when I marked 3.4 as EOL, but forgot to do
> > it in the scripts so the front page would be correct.
> > 
> > Should be resolved in 30 minutes or so, whenever the backend syncs to
> > the front-facing servers.
> 
> Thanks a lot.
> 
> Attached are the 4.9 networking -stable backports:

Many thanks for these, all now queued up.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 96 bytes --]


Please queue up the following bug fixes to 4.9.x and
4.13.x -stable, respectively.

Thank you!

[-- Attachment #2: net_49.mbox --]
[-- Type: Application/Octet-Stream, Size: 80884 bytes --]

From 2b8233fdc2b9eb721fdfc7471fb7fda0a48c8eee Mon Sep 17 00:00:00 2001
From: Alexey Kodanev <alexey.kodanev@oracle.com>
Date: Fri, 6 Oct 2017 19:02:35 +0300
Subject: [PATCH 01/25] gso: fix payload length when gso_size is zero

[ Upstream commit 3d0241d57c7b25bb75ac9d7a62753642264fdbce ]

When gso_size reset to zero for the tail segment in skb_segment(), later
in ipv6_gso_segment(), __skb_udp_tunnel_segment() and gre_gso_segment()
we will get incorrect results (payload length, pcsum) for that segment.
inet_gso_segment() already has a check for gso_size before calculating
payload.

The issue was found with LTP vxlan & gre tests over ixgbe NIC.

Fixes: 07b26c9454a2 ("gso: Support partial splitting at the frag_list pointer")
Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Acked-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/gre_offload.c | 2 +-
 net/ipv4/udp_offload.c | 2 +-
 net/ipv6/ip6_offload.c | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index d5cac99170b1..8c72034df28e 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -98,7 +98,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 		greh = (struct gre_base_hdr *)skb_transport_header(skb);
 		pcsum = (__sum16 *)(greh + 1);
 
-		if (gso_partial) {
+		if (gso_partial && skb_is_gso(skb)) {
 			unsigned int partial_adj;
 
 			/* Adjust checksum to account for the fact that
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 0932c85b42af..6401574cd638 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -122,7 +122,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 		 * will be using a length value equal to only one MSS sized
 		 * segment instead of the entire frame.
 		 */
-		if (gso_partial) {
+		if (gso_partial && skb_is_gso(skb)) {
 			uh->len = htons(skb_shinfo(skb)->gso_size +
 					SKB_GSO_CB(skb)->data_offset +
 					skb->head - (unsigned char *)uh);
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 424fbe1f8978..649f4d87b318 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -105,7 +105,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 
 	for (skb = segs; skb; skb = skb->next) {
 		ipv6h = (struct ipv6hdr *)(skb_mac_header(skb) + nhoff);
-		if (gso_partial)
+		if (gso_partial && skb_is_gso(skb))
 			payload_len = skb_shinfo(skb)->gso_size +
 				      SKB_GSO_CB(skb)->data_offset +
 				      skb->head - (unsigned char *)(ipv6h + 1);
-- 
2.13.6


From 7b1f6bec7b82c66ff09f320ac4052a3b9fb51ad2 Mon Sep 17 00:00:00 2001
From: Craig Gallek <kraig@google.com>
Date: Mon, 30 Oct 2017 18:50:11 -0400
Subject: [PATCH 02/25] tun/tap: sanitize TUNSETSNDBUF input

[ Upstream commit 93161922c658c714715686cd0cf69b090cb9bf1d ]

Syzkaller found several variants of the lockup below by setting negative
values with the TUNSETSNDBUF ioctl.  This patch adds a sanity check
to both the tun and tap versions of this ioctl.

  watchdog: BUG: soft lockup - CPU#0 stuck for 22s! [repro:2389]
  Modules linked in:
  irq event stamp: 329692056
  hardirqs last  enabled at (329692055): [<ffffffff824b8381>] _raw_spin_unlock_irqrestore+0x31/0x75
  hardirqs last disabled at (329692056): [<ffffffff824b9e58>] apic_timer_interrupt+0x98/0xb0
  softirqs last  enabled at (35659740): [<ffffffff824bc958>] __do_softirq+0x328/0x48c
  softirqs last disabled at (35659731): [<ffffffff811c796c>] irq_exit+0xbc/0xd0
  CPU: 0 PID: 2389 Comm: repro Not tainted 4.14.0-rc7 #23
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
  task: ffff880009452140 task.stack: ffff880006a20000
  RIP: 0010:_raw_spin_lock_irqsave+0x11/0x80
  RSP: 0018:ffff880006a27c50 EFLAGS: 00000282 ORIG_RAX: ffffffffffffff10
  RAX: ffff880009ac68d0 RBX: ffff880006a27ce0 RCX: 0000000000000000
  RDX: 0000000000000001 RSI: ffff880006a27ce0 RDI: ffff880009ac6900
  RBP: ffff880006a27c60 R08: 0000000000000000 R09: 0000000000000000
  R10: 0000000000000001 R11: 000000000063ff00 R12: ffff880009ac6900
  R13: ffff880006a27cf8 R14: 0000000000000001 R15: ffff880006a27cf8
  FS:  00007f4be4838700(0000) GS:ffff88000cc00000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 0000000020101000 CR3: 0000000009616000 CR4: 00000000000006f0
  Call Trace:
   prepare_to_wait+0x26/0xc0
   sock_alloc_send_pskb+0x14e/0x270
   ? remove_wait_queue+0x60/0x60
   tun_get_user+0x2cc/0x19d0
   ? __tun_get+0x60/0x1b0
   tun_chr_write_iter+0x57/0x86
   __vfs_write+0x156/0x1e0
   vfs_write+0xf7/0x230
   SyS_write+0x57/0xd0
   entry_SYSCALL_64_fastpath+0x1f/0xbe
  RIP: 0033:0x7f4be4356df9
  RSP: 002b:00007ffc18101c08 EFLAGS: 00000293 ORIG_RAX: 0000000000000001
  RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f4be4356df9
  RDX: 0000000000000046 RSI: 0000000020101000 RDI: 0000000000000005
  RBP: 00007ffc18101c40 R08: 0000000000000001 R09: 0000000000000001
  R10: 0000000000000001 R11: 0000000000000293 R12: 0000559c75f64780
  R13: 00007ffc18101d30 R14: 0000000000000000 R15: 0000000000000000

Fixes: 33dccbb050bb ("tun: Limit amount of queued packets per device")
Fixes: 20d29d7a916a ("net: macvtap driver")
Signed-off-by: Craig Gallek <kraig@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macvtap.c | 2 ++
 drivers/net/tun.c     | 4 ++++
 2 files changed, 6 insertions(+)

diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index adea6f5a4d71..0da292e9a25c 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -1077,6 +1077,8 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd,
 	case TUNSETSNDBUF:
 		if (get_user(s, sp))
 			return -EFAULT;
+		if (s <= 0)
+			return -EINVAL;
 
 		q->sk.sk_sndbuf = s;
 		return 0;
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index ba7f9e054c4a..01aee6eff25b 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -2180,6 +2180,10 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 			ret = -EFAULT;
 			break;
 		}
+		if (sndbuf <= 0) {
+			ret = -EINVAL;
+			break;
+		}
 
 		tun->sndbuf = sndbuf;
 		tun_set_sndbuf(tun);
-- 
2.13.6


From 002c71a456fa606bc23bff468cc9190c487835cd Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 30 Oct 2017 22:47:09 -0700
Subject: [PATCH 03/25] ipv6: addrconf: increment ifp refcount before
 ipv6_del_addr()

[ Upstream commit e669b86945478b3d90d2d87e3793a6eed06d332f ]

In the (unlikely) event fixup_permanent_addr() returns a failure,
addrconf_permanent_addr() calls ipv6_del_addr() without the
mandatory call to in6_ifa_hold(), leading to a refcount error,
spotted by syzkaller :

WARNING: CPU: 1 PID: 3142 at lib/refcount.c:227 refcount_dec+0x4c/0x50
lib/refcount.c:227
Kernel panic - not syncing: panic_on_warn set ...

CPU: 1 PID: 3142 Comm: ip Not tainted 4.14.0-rc4-next-20171009+ #33
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:16 [inline]
 dump_stack+0x194/0x257 lib/dump_stack.c:52
 panic+0x1e4/0x41c kernel/panic.c:181
 __warn+0x1c4/0x1e0 kernel/panic.c:544
 report_bug+0x211/0x2d0 lib/bug.c:183
 fixup_bug+0x40/0x90 arch/x86/kernel/traps.c:178
 do_trap_no_signal arch/x86/kernel/traps.c:212 [inline]
 do_trap+0x260/0x390 arch/x86/kernel/traps.c:261
 do_error_trap+0x120/0x390 arch/x86/kernel/traps.c:298
 do_invalid_op+0x1b/0x20 arch/x86/kernel/traps.c:311
 invalid_op+0x18/0x20 arch/x86/entry/entry_64.S:905
RIP: 0010:refcount_dec+0x4c/0x50 lib/refcount.c:227
RSP: 0018:ffff8801ca49e680 EFLAGS: 00010286
RAX: 000000000000002c RBX: ffff8801d07cfcdc RCX: 0000000000000000
RDX: 000000000000002c RSI: 1ffff10039493c90 RDI: ffffed0039493cc4
RBP: ffff8801ca49e688 R08: ffff8801ca49dd70 R09: 0000000000000000
R10: ffff8801ca49df58 R11: 0000000000000000 R12: 1ffff10039493cd9
R13: ffff8801ca49e6e8 R14: ffff8801ca49e7e8 R15: ffff8801d07cfcdc
 __in6_ifa_put include/net/addrconf.h:369 [inline]
 ipv6_del_addr+0x42b/0xb60 net/ipv6/addrconf.c:1208
 addrconf_permanent_addr net/ipv6/addrconf.c:3327 [inline]
 addrconf_notify+0x1c66/0x2190 net/ipv6/addrconf.c:3393
 notifier_call_chain+0x136/0x2c0 kernel/notifier.c:93
 __raw_notifier_call_chain kernel/notifier.c:394 [inline]
 raw_notifier_call_chain+0x2d/0x40 kernel/notifier.c:401
 call_netdevice_notifiers_info+0x32/0x60 net/core/dev.c:1697
 call_netdevice_notifiers net/core/dev.c:1715 [inline]
 __dev_notify_flags+0x15d/0x430 net/core/dev.c:6843
 dev_change_flags+0xf5/0x140 net/core/dev.c:6879
 do_setlink+0xa1b/0x38e0 net/core/rtnetlink.c:2113
 rtnl_newlink+0xf0d/0x1a40 net/core/rtnetlink.c:2661
 rtnetlink_rcv_msg+0x733/0x1090 net/core/rtnetlink.c:4301
 netlink_rcv_skb+0x216/0x440 net/netlink/af_netlink.c:2408
 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:4313
 netlink_unicast_kernel net/netlink/af_netlink.c:1273 [inline]
 netlink_unicast+0x4e8/0x6f0 net/netlink/af_netlink.c:1299
 netlink_sendmsg+0xa4a/0xe70 net/netlink/af_netlink.c:1862
 sock_sendmsg_nosec net/socket.c:633 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:643
 ___sys_sendmsg+0x75b/0x8a0 net/socket.c:2049
 __sys_sendmsg+0xe5/0x210 net/socket.c:2083
 SYSC_sendmsg net/socket.c:2094 [inline]
 SyS_sendmsg+0x2d/0x50 net/socket.c:2090
 entry_SYSCALL_64_fastpath+0x1f/0xbe
RIP: 0033:0x7fa9174d3320
RSP: 002b:00007ffe302ae9e8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 00007ffe302b2ae0 RCX: 00007fa9174d3320
RDX: 0000000000000000 RSI: 00007ffe302aea20 RDI: 0000000000000016
RBP: 0000000000000082 R08: 0000000000000000 R09: 000000000000000f
R10: 0000000000000000 R11: 0000000000000246 R12: 00007ffe302b32a0
R13: 0000000000000000 R14: 00007ffe302b2ab8 R15: 00007ffe302b32b8

Fixes: f1705ec197e7 ("net: ipv6: Make address flushing on ifdown optional")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: David Ahern <dsahern@gmail.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index cc101b1be903..a4fb90c4819f 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3299,6 +3299,7 @@ static void addrconf_permanent_addr(struct net_device *dev)
 		if ((ifp->flags & IFA_F_PERMANENT) &&
 		    fixup_permanent_addr(idev, ifp) < 0) {
 			write_unlock_bh(&idev->lock);
+			in6_ifa_hold(ifp);
 			ipv6_del_addr(ifp);
 			write_lock_bh(&idev->lock);
 
-- 
2.13.6


From 359711ee842d59e6107ee64ae3275597a95c307b Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Mon, 9 Oct 2017 14:14:51 +0200
Subject: [PATCH 04/25] netlink: do not set cb_running if dump's start() errs

[ Upstream commit 41c87425a1ac9b633e0fcc78eb1f19640c8fb5a0 ]

It turns out that multiple places can call netlink_dump(), which means
it's still possible to dereference partially initialized values in
dump() that were the result of a faulty returned start().

This fixes the issue by calling start() _before_ setting cb_running to
true, so that there's no chance at all of hitting the dump() function
through any indirect paths.

It also moves the call to start() to be when the mutex is held. This has
the nice side effect of serializing invocations to start(), which is
likely desirable anyway. It also prevents any possible other races that
might come out of this logic.

In testing this with several different pieces of tricky code to trigger
these issues, this commit fixes all avenues that I'm aware of.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
Reviewed-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 2a5775f8a6ca..a1dca3b169a1 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2207,16 +2207,17 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 	cb->min_dump_alloc = control->min_dump_alloc;
 	cb->skb = skb;
 
+	if (cb->start) {
+		ret = cb->start(cb);
+		if (ret)
+			goto error_unlock;
+	}
+
 	nlk->cb_running = true;
 
 	mutex_unlock(nlk->cb_mutex);
 
-	ret = 0;
-	if (cb->start)
-		ret = cb->start(cb);
-
-	if (!ret)
-		ret = netlink_dump(sk);
+	ret = netlink_dump(sk);
 
 	sock_put(sk);
 
-- 
2.13.6


From 74d1377e0ff26f0f69626c1fe4b4c3773677dea1 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 10 Oct 2017 19:12:33 -0700
Subject: [PATCH 05/25] net: call cgroup_sk_alloc() earlier in sk_clone_lock()

[ Upstream commit c0576e3975084d4699b7bfef578613fb8e1144f6 ]

If for some reason, the newly allocated child need to be freed,
we will call cgroup_put() (via sk_free_unlock_clone()) while the
corresponding cgroup_get() was not yet done, and we will free memory
too soon.

Fixes: d979a39d7242 ("cgroup: duplicate cgroup reference when cloning sockets")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index 231c38d91855..e3b60460dc9c 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1526,6 +1526,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		newsk->sk_userlocks	= sk->sk_userlocks & ~SOCK_BINDPORT_LOCK;
 
 		sock_reset_flag(newsk, SOCK_DONE);
+		cgroup_sk_alloc(&newsk->sk_cgrp_data);
 		skb_queue_head_init(&newsk->sk_error_queue);
 
 		filter = rcu_dereference_protected(newsk->sk_filter, 1);
@@ -1560,8 +1561,6 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		atomic64_set(&newsk->sk_cookie, 0);
 
 		mem_cgroup_sk_alloc(newsk);
-		cgroup_sk_alloc(&newsk->sk_cgrp_data);
-
 		/*
 		 * Before updating sk_refcnt, we must commit prior changes to memory
 		 * (Documentation/RCU/rculist_nulls.txt for details)
-- 
2.13.6


From 657143bba54b8e57a880c022ff812d54816eb0ea Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 30 Oct 2017 23:08:20 -0700
Subject: [PATCH 06/25] tcp: fix tcp_mtu_probe() vs highest_sack

[ Upstream commit 2b7cda9c35d3b940eb9ce74b30bbd5eb30db493d ]

Based on SNMP values provided by Roman, Yuchung made the observation
that some crashes in tcp_sacktag_walk() might be caused by MTU probing.

Looking at tcp_mtu_probe(), I found that when a new skb was placed
in front of the write queue, we were not updating tcp highest sack.

If one skb is freed because all its content was copied to the new skb
(for MTU probing), then tp->highest_sack could point to a now freed skb.

Bad things would then happen, including infinite loops.

This patch renames tcp_highest_sack_combine() and uses it
from tcp_mtu_probe() to fix the bug.

Note that I also removed one test against tp->sacked_out,
since we want to replace tp->highest_sack regardless of whatever
condition, since keeping a stale pointer to freed skb is a recipe
for disaster.

Fixes: a47e5a988a57 ("[TCP]: Convert highest_sack to sk_buff to allow direct access")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Reported-by: Roman Gushchin <guro@fb.com>
Reported-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h     | 6 +++---
 net/ipv4/tcp_output.c | 3 ++-
 2 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 123979fe12bf..fba4fc46871d 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1681,12 +1681,12 @@ static inline void tcp_highest_sack_reset(struct sock *sk)
 	tcp_sk(sk)->highest_sack = tcp_write_queue_head(sk);
 }
 
-/* Called when old skb is about to be deleted (to be combined with new skb) */
-static inline void tcp_highest_sack_combine(struct sock *sk,
+/* Called when old skb is about to be deleted and replaced by new skb */
+static inline void tcp_highest_sack_replace(struct sock *sk,
 					    struct sk_buff *old,
 					    struct sk_buff *new)
 {
-	if (tcp_sk(sk)->sacked_out && (old == tcp_sk(sk)->highest_sack))
+	if (old == tcp_highest_sack(sk))
 		tcp_sk(sk)->highest_sack = new;
 }
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 85920707c4d3..566b43afe378 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1996,6 +1996,7 @@ static int tcp_mtu_probe(struct sock *sk)
 	nskb->ip_summed = skb->ip_summed;
 
 	tcp_insert_write_queue_before(nskb, skb, sk);
+	tcp_highest_sack_replace(sk, skb, nskb);
 
 	len = 0;
 	tcp_for_write_queue_from_safe(skb, next, sk) {
@@ -2535,7 +2536,7 @@ static void tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
 
 	BUG_ON(tcp_skb_pcount(skb) != 1 || tcp_skb_pcount(next_skb) != 1);
 
-	tcp_highest_sack_combine(sk, next_skb, skb);
+	tcp_highest_sack_replace(sk, next_skb, skb);
 
 	tcp_unlink_write_queue(next_skb, sk);
 
-- 
2.13.6


From 8a3589498fe86f8bc026f416ae0e8b7b292125f9 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Fri, 13 Oct 2017 19:22:35 +0200
Subject: [PATCH 07/25] l2tp: check ps->sock before running
 pppol2tp_session_ioctl()

[ Upstream commit 5903f594935a3841137c86b9d5b75143a5b7121c ]

When pppol2tp_session_ioctl() is called by pppol2tp_tunnel_ioctl(),
the session may be unconnected. That is, it was created by
pppol2tp_session_create() and hasn't been connected with
pppol2tp_connect(). In this case, ps->sock is NULL, so we need to check
for this case in order to avoid dereferencing a NULL pointer.

Fixes: 309795f4bec2 ("l2tp: Add netlink control API for L2TP")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ppp.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 1696f1fd5877..163f1fa53917 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -993,6 +993,9 @@ static int pppol2tp_session_ioctl(struct l2tp_session *session,
 		 session->name, cmd, arg);
 
 	sk = ps->sock;
+	if (!sk)
+		return -EBADR;
+
 	sock_hold(sk);
 
 	switch (cmd) {
-- 
2.13.6


From a02c791990ae7f840a6c76075cdc8efa27cb4556 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Fri, 13 Oct 2017 11:58:53 -0700
Subject: [PATCH 08/25] tun: call dev_get_valid_name() before
 register_netdevice()

[ Upstream commit 0ad646c81b2182f7fa67ec0c8c825e0ee165696d ]

register_netdevice() could fail early when we have an invalid
dev name, in which case ->ndo_uninit() is not called. For tun
device, this is a problem because a timer etc. are already
initialized and it expects ->ndo_uninit() to clean them up.

We could move these initializations into a ->ndo_init() so
that register_netdevice() knows better, however this is still
complicated due to the logic in tun_detach().

Therefore, I choose to just call dev_get_valid_name() before
register_netdevice(), which is quicker and much easier to audit.
And for this specific case, it is already enough.

Fixes: 96442e42429e ("tuntap: choose the txq based on rxq")
Reported-by: Dmitry Alexeev <avekceeb@gmail.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c         | 3 +++
 include/linux/netdevice.h | 3 +++
 net/core/dev.c            | 6 +++---
 3 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 01aee6eff25b..a774c827a414 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1787,6 +1787,9 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 
 		if (!dev)
 			return -ENOMEM;
+		err = dev_get_valid_name(net, dev, name);
+		if (err)
+			goto err_free_dev;
 
 		dev_net_set(dev, net);
 		dev->rtnl_link_ops = &tun_link_ops;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 23db1ae37464..47c7f5b8f675 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3742,6 +3742,9 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 				    unsigned char name_assign_type,
 				    void (*setup)(struct net_device *),
 				    unsigned int txqs, unsigned int rxqs);
+int dev_get_valid_name(struct net *net, struct net_device *dev,
+		       const char *name);
+
 #define alloc_netdev(sizeof_priv, name, name_assign_type, setup) \
 	alloc_netdev_mqs(sizeof_priv, name, name_assign_type, setup, 1, 1)
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 7f2caad46a3d..c37891828e4e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1115,9 +1115,8 @@ static int dev_alloc_name_ns(struct net *net,
 	return ret;
 }
 
-static int dev_get_valid_name(struct net *net,
-			      struct net_device *dev,
-			      const char *name)
+int dev_get_valid_name(struct net *net, struct net_device *dev,
+		       const char *name)
 {
 	BUG_ON(!net);
 
@@ -1133,6 +1132,7 @@ static int dev_get_valid_name(struct net *net,
 
 	return 0;
 }
+EXPORT_SYMBOL(dev_get_valid_name);
 
 /**
  *	dev_change_name - change name of a device
-- 
2.13.6


From 05c8f7c660862b7374bd44037125e42e563a253a Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 18 Oct 2017 21:37:49 +0800
Subject: [PATCH 09/25] sctp: add the missing sock_owned_by_user check in
 sctp_icmp_redirect

[ Upstream commit 1cc276cec9ec574d41cf47dfc0f51406b6f26ab4 ]

Now sctp processes icmp redirect packet in sctp_icmp_redirect where
it calls sctp_transport_dst_check in which tp->dst can be released.

The problem is before calling sctp_transport_dst_check, it doesn't
check sock_owned_by_user, which means tp->dst could be freed while
a process is accessing it with owning the socket.

An use-after-free issue could be triggered by this.

This patch is to fix it by checking sock_owned_by_user before calling
sctp_transport_dst_check in sctp_icmp_redirect, so that it would not
release tp->dst if users still hold sock lock.

Besides, the same issue fixed in commit 45caeaa5ac0b ("dccp/tcp: fix
routing redirect race") on sctp also needs this check.

Fixes: 55be7a9c6074 ("ipv4: Add redirect support to all protocol icmp error handlers")
Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/input.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sctp/input.c b/net/sctp/input.c
index 6c79915c7dbc..68b84d3a7cac 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -421,7 +421,7 @@ void sctp_icmp_redirect(struct sock *sk, struct sctp_transport *t,
 {
 	struct dst_entry *dst;
 
-	if (!t)
+	if (sock_owned_by_user(sk) || !t)
 		return;
 	dst = sctp_transport_dst_check(t);
 	if (dst)
-- 
2.13.6


From ec4223e8f9baee1873646cbb4fddb8e10157ab4d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 20 Oct 2017 09:04:13 -0700
Subject: [PATCH 10/25] tcp/dccp: fix ireq->opt races

[ Upstream commit c92e8c02fe664155ac4234516e32544bec0f113d ]

syzkaller found another bug in DCCP/TCP stacks [1]

For the reasons explained in commit ce1050089c96 ("tcp/dccp: fix
ireq->pktopts race"), we need to make sure we do not access
ireq->opt unless we own the request sock.

Note the opt field is renamed to ireq_opt to ease grep games.

[1]
BUG: KASAN: use-after-free in ip_queue_xmit+0x1687/0x18e0 net/ipv4/ip_output.c:474
Read of size 1 at addr ffff8801c951039c by task syz-executor5/3295

CPU: 1 PID: 3295 Comm: syz-executor5 Not tainted 4.14.0-rc4+ #80
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:16 [inline]
 dump_stack+0x194/0x257 lib/dump_stack.c:52
 print_address_description+0x73/0x250 mm/kasan/report.c:252
 kasan_report_error mm/kasan/report.c:351 [inline]
 kasan_report+0x25b/0x340 mm/kasan/report.c:409
 __asan_report_load1_noabort+0x14/0x20 mm/kasan/report.c:427
 ip_queue_xmit+0x1687/0x18e0 net/ipv4/ip_output.c:474
 tcp_transmit_skb+0x1ab7/0x3840 net/ipv4/tcp_output.c:1135
 tcp_send_ack.part.37+0x3bb/0x650 net/ipv4/tcp_output.c:3587
 tcp_send_ack+0x49/0x60 net/ipv4/tcp_output.c:3557
 __tcp_ack_snd_check+0x2c6/0x4b0 net/ipv4/tcp_input.c:5072
 tcp_ack_snd_check net/ipv4/tcp_input.c:5085 [inline]
 tcp_rcv_state_process+0x2eff/0x4850 net/ipv4/tcp_input.c:6071
 tcp_child_process+0x342/0x990 net/ipv4/tcp_minisocks.c:816
 tcp_v4_rcv+0x1827/0x2f80 net/ipv4/tcp_ipv4.c:1682
 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216
 NF_HOOK include/linux/netfilter.h:249 [inline]
 ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257
 dst_input include/net/dst.h:464 [inline]
 ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397
 NF_HOOK include/linux/netfilter.h:249 [inline]
 ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493
 __netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476
 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514
 netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587
 netif_receive_skb+0xae/0x390 net/core/dev.c:4611
 tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372
 tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766
 tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792
 call_write_iter include/linux/fs.h:1770 [inline]
 new_sync_write fs/read_write.c:468 [inline]
 __vfs_write+0x68a/0x970 fs/read_write.c:481
 vfs_write+0x18f/0x510 fs/read_write.c:543
 SYSC_write fs/read_write.c:588 [inline]
 SyS_write+0xef/0x220 fs/read_write.c:580
 entry_SYSCALL_64_fastpath+0x1f/0xbe
RIP: 0033:0x40c341
RSP: 002b:00007f469523ec10 EFLAGS: 00000293 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 0000000000718000 RCX: 000000000040c341
RDX: 0000000000000037 RSI: 0000000020004000 RDI: 0000000000000015
RBP: 0000000000000086 R08: 0000000000000000 R09: 0000000000000000
R10: 00000000000f4240 R11: 0000000000000293 R12: 00000000004b7fd1
R13: 00000000ffffffff R14: 0000000020000000 R15: 0000000000025000

Allocated by task 3295:
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
 save_stack+0x43/0xd0 mm/kasan/kasan.c:447
 set_track mm/kasan/kasan.c:459 [inline]
 kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:551
 __do_kmalloc mm/slab.c:3725 [inline]
 __kmalloc+0x162/0x760 mm/slab.c:3734
 kmalloc include/linux/slab.h:498 [inline]
 tcp_v4_save_options include/net/tcp.h:1962 [inline]
 tcp_v4_init_req+0x2d3/0x3e0 net/ipv4/tcp_ipv4.c:1271
 tcp_conn_request+0xf6d/0x3410 net/ipv4/tcp_input.c:6283
 tcp_v4_conn_request+0x157/0x210 net/ipv4/tcp_ipv4.c:1313
 tcp_rcv_state_process+0x8ea/0x4850 net/ipv4/tcp_input.c:5857
 tcp_v4_do_rcv+0x55c/0x7d0 net/ipv4/tcp_ipv4.c:1482
 tcp_v4_rcv+0x2d10/0x2f80 net/ipv4/tcp_ipv4.c:1711
 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216
 NF_HOOK include/linux/netfilter.h:249 [inline]
 ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257
 dst_input include/net/dst.h:464 [inline]
 ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397
 NF_HOOK include/linux/netfilter.h:249 [inline]
 ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493
 __netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476
 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514
 netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587
 netif_receive_skb+0xae/0x390 net/core/dev.c:4611
 tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372
 tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766
 tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792
 call_write_iter include/linux/fs.h:1770 [inline]
 new_sync_write fs/read_write.c:468 [inline]
 __vfs_write+0x68a/0x970 fs/read_write.c:481
 vfs_write+0x18f/0x510 fs/read_write.c:543
 SYSC_write fs/read_write.c:588 [inline]
 SyS_write+0xef/0x220 fs/read_write.c:580
 entry_SYSCALL_64_fastpath+0x1f/0xbe

Freed by task 3306:
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
 save_stack+0x43/0xd0 mm/kasan/kasan.c:447
 set_track mm/kasan/kasan.c:459 [inline]
 kasan_slab_free+0x71/0xc0 mm/kasan/kasan.c:524
 __cache_free mm/slab.c:3503 [inline]
 kfree+0xca/0x250 mm/slab.c:3820
 inet_sock_destruct+0x59d/0x950 net/ipv4/af_inet.c:157
 __sk_destruct+0xfd/0x910 net/core/sock.c:1560
 sk_destruct+0x47/0x80 net/core/sock.c:1595
 __sk_free+0x57/0x230 net/core/sock.c:1603
 sk_free+0x2a/0x40 net/core/sock.c:1614
 sock_put include/net/sock.h:1652 [inline]
 inet_csk_complete_hashdance+0xd5/0xf0 net/ipv4/inet_connection_sock.c:959
 tcp_check_req+0xf4d/0x1620 net/ipv4/tcp_minisocks.c:765
 tcp_v4_rcv+0x17f6/0x2f80 net/ipv4/tcp_ipv4.c:1675
 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216
 NF_HOOK include/linux/netfilter.h:249 [inline]
 ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257
 dst_input include/net/dst.h:464 [inline]
 ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397
 NF_HOOK include/linux/netfilter.h:249 [inline]
 ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493
 __netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476
 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514
 netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587
 netif_receive_skb+0xae/0x390 net/core/dev.c:4611
 tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372
 tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766
 tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792
 call_write_iter include/linux/fs.h:1770 [inline]
 new_sync_write fs/read_write.c:468 [inline]
 __vfs_write+0x68a/0x970 fs/read_write.c:481
 vfs_write+0x18f/0x510 fs/read_write.c:543
 SYSC_write fs/read_write.c:588 [inline]
 SyS_write+0xef/0x220 fs/read_write.c:580
 entry_SYSCALL_64_fastpath+0x1f/0xbe

Fixes: e994b2f0fb92 ("tcp: do not lock listener to process SYN packets")
Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_sock.h         |  2 +-
 net/dccp/ipv4.c                 | 13 ++++++++-----
 net/ipv4/cipso_ipv4.c           | 24 +++++++-----------------
 net/ipv4/inet_connection_sock.c |  8 +++-----
 net/ipv4/syncookies.c           |  2 +-
 net/ipv4/tcp_input.c            |  2 +-
 net/ipv4/tcp_ipv4.c             | 21 ++++++++++++---------
 7 files changed, 33 insertions(+), 39 deletions(-)

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 236a81034fef..6213a90a8cec 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -96,7 +96,7 @@ struct inet_request_sock {
 	kmemcheck_bitfield_end(flags);
 	u32                     ir_mark;
 	union {
-		struct ip_options_rcu	*opt;
+		struct ip_options_rcu __rcu	*ireq_opt;
 #if IS_ENABLED(CONFIG_IPV6)
 		struct {
 			struct ipv6_txoptions	*ipv6_opt;
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 8fc160098e11..77f5e3524ebc 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -414,8 +414,7 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk,
 	sk_daddr_set(newsk, ireq->ir_rmt_addr);
 	sk_rcv_saddr_set(newsk, ireq->ir_loc_addr);
 	newinet->inet_saddr	= ireq->ir_loc_addr;
-	newinet->inet_opt	= ireq->opt;
-	ireq->opt	   = NULL;
+	RCU_INIT_POINTER(newinet->inet_opt, rcu_dereference(ireq->ireq_opt));
 	newinet->mc_index  = inet_iif(skb);
 	newinet->mc_ttl	   = ip_hdr(skb)->ttl;
 	newinet->inet_id   = jiffies;
@@ -430,7 +429,10 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk,
 	if (__inet_inherit_port(sk, newsk) < 0)
 		goto put_and_exit;
 	*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
-
+	if (*own_req)
+		ireq->ireq_opt = NULL;
+	else
+		newinet->inet_opt = NULL;
 	return newsk;
 
 exit_overflow:
@@ -441,6 +443,7 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk,
 	__NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENDROPS);
 	return NULL;
 put_and_exit:
+	newinet->inet_opt = NULL;
 	inet_csk_prepare_forced_close(newsk);
 	dccp_done(newsk);
 	goto exit;
@@ -492,7 +495,7 @@ static int dccp_v4_send_response(const struct sock *sk, struct request_sock *req
 							      ireq->ir_rmt_addr);
 		err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
 					    ireq->ir_rmt_addr,
-					    ireq->opt);
+					    rcu_dereference(ireq->ireq_opt));
 		err = net_xmit_eval(err);
 	}
 
@@ -548,7 +551,7 @@ static void dccp_v4_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb)
 static void dccp_v4_reqsk_destructor(struct request_sock *req)
 {
 	dccp_feat_list_purge(&dccp_rsk(req)->dreq_featneg);
-	kfree(inet_rsk(req)->opt);
+	kfree(rcu_dereference_protected(inet_rsk(req)->ireq_opt, 1));
 }
 
 void dccp_syn_ack_timeout(const struct request_sock *req)
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index ae206163c273..972353cd1778 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -1943,7 +1943,7 @@ int cipso_v4_req_setattr(struct request_sock *req,
 	buf = NULL;
 
 	req_inet = inet_rsk(req);
-	opt = xchg(&req_inet->opt, opt);
+	opt = xchg((__force struct ip_options_rcu **)&req_inet->ireq_opt, opt);
 	if (opt)
 		kfree_rcu(opt, rcu);
 
@@ -1965,11 +1965,13 @@ int cipso_v4_req_setattr(struct request_sock *req,
  * values on failure.
  *
  */
-static int cipso_v4_delopt(struct ip_options_rcu **opt_ptr)
+static int cipso_v4_delopt(struct ip_options_rcu __rcu **opt_ptr)
 {
+	struct ip_options_rcu *opt = rcu_dereference_protected(*opt_ptr, 1);
 	int hdr_delta = 0;
-	struct ip_options_rcu *opt = *opt_ptr;
 
+	if (!opt || opt->opt.cipso == 0)
+		return 0;
 	if (opt->opt.srr || opt->opt.rr || opt->opt.ts || opt->opt.router_alert) {
 		u8 cipso_len;
 		u8 cipso_off;
@@ -2031,14 +2033,10 @@ static int cipso_v4_delopt(struct ip_options_rcu **opt_ptr)
  */
 void cipso_v4_sock_delattr(struct sock *sk)
 {
-	int hdr_delta;
-	struct ip_options_rcu *opt;
 	struct inet_sock *sk_inet;
+	int hdr_delta;
 
 	sk_inet = inet_sk(sk);
-	opt = rcu_dereference_protected(sk_inet->inet_opt, 1);
-	if (!opt || opt->opt.cipso == 0)
-		return;
 
 	hdr_delta = cipso_v4_delopt(&sk_inet->inet_opt);
 	if (sk_inet->is_icsk && hdr_delta > 0) {
@@ -2058,15 +2056,7 @@ void cipso_v4_sock_delattr(struct sock *sk)
  */
 void cipso_v4_req_delattr(struct request_sock *req)
 {
-	struct ip_options_rcu *opt;
-	struct inet_request_sock *req_inet;
-
-	req_inet = inet_rsk(req);
-	opt = req_inet->opt;
-	if (!opt || opt->opt.cipso == 0)
-		return;
-
-	cipso_v4_delopt(&req_inet->opt);
+	cipso_v4_delopt(&inet_rsk(req)->ireq_opt);
 }
 
 /**
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index cf3d5674846a..8d7cc4e53205 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -407,9 +407,10 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk,
 {
 	const struct inet_request_sock *ireq = inet_rsk(req);
 	struct net *net = read_pnet(&ireq->ireq_net);
-	struct ip_options_rcu *opt = ireq->opt;
+	struct ip_options_rcu *opt;
 	struct rtable *rt;
 
+	opt = rcu_dereference(ireq->ireq_opt);
 	flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
 			   sk->sk_protocol, inet_sk_flowi_flags(sk),
@@ -443,10 +444,9 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
 	struct flowi4 *fl4;
 	struct rtable *rt;
 
+	opt = rcu_dereference(ireq->ireq_opt);
 	fl4 = &newinet->cork.fl.u.ip4;
 
-	rcu_read_lock();
-	opt = rcu_dereference(newinet->inet_opt);
 	flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
 			   sk->sk_protocol, inet_sk_flowi_flags(sk),
@@ -459,13 +459,11 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
 		goto no_route;
 	if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway)
 		goto route_err;
-	rcu_read_unlock();
 	return &rt->dst;
 
 route_err:
 	ip_rt_put(rt);
 no_route:
-	rcu_read_unlock();
 	__IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
 	return NULL;
 }
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index b6f710d515d0..0597ad73a1fa 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -354,7 +354,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	/* We throwed the options of the initial SYN away, so we hope
 	 * the ACK carries the same options again (see RFC1122 4.2.3.8)
 	 */
-	ireq->opt = tcp_v4_save_options(skb);
+	RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(skb));
 
 	if (security_inet_conn_request(sk, skb, req)) {
 		reqsk_free(req);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index c03850771a4e..8fcd0c642742 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6237,7 +6237,7 @@ struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops,
 		struct inet_request_sock *ireq = inet_rsk(req);
 
 		kmemcheck_annotate_bitfield(ireq, flags);
-		ireq->opt = NULL;
+		ireq->ireq_opt = NULL;
 #if IS_ENABLED(CONFIG_IPV6)
 		ireq->pktopts = NULL;
 #endif
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 6988566dc72f..c96b9dcce323 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -861,7 +861,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
 
 		err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
 					    ireq->ir_rmt_addr,
-					    ireq->opt);
+					    rcu_dereference(ireq->ireq_opt));
 		err = net_xmit_eval(err);
 	}
 
@@ -873,7 +873,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
  */
 static void tcp_v4_reqsk_destructor(struct request_sock *req)
 {
-	kfree(inet_rsk(req)->opt);
+	kfree(rcu_dereference_protected(inet_rsk(req)->ireq_opt, 1));
 }
 
 #ifdef CONFIG_TCP_MD5SIG
@@ -1199,7 +1199,7 @@ static void tcp_v4_init_req(struct request_sock *req,
 
 	sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr);
 	sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr);
-	ireq->opt = tcp_v4_save_options(skb);
+	RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(skb));
 }
 
 static struct dst_entry *tcp_v4_route_req(const struct sock *sk,
@@ -1295,10 +1295,9 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 	sk_daddr_set(newsk, ireq->ir_rmt_addr);
 	sk_rcv_saddr_set(newsk, ireq->ir_loc_addr);
 	newsk->sk_bound_dev_if = ireq->ir_iif;
-	newinet->inet_saddr	      = ireq->ir_loc_addr;
-	inet_opt	      = ireq->opt;
-	rcu_assign_pointer(newinet->inet_opt, inet_opt);
-	ireq->opt	      = NULL;
+	newinet->inet_saddr   = ireq->ir_loc_addr;
+	inet_opt	      = rcu_dereference(ireq->ireq_opt);
+	RCU_INIT_POINTER(newinet->inet_opt, inet_opt);
 	newinet->mc_index     = inet_iif(skb);
 	newinet->mc_ttl	      = ip_hdr(skb)->ttl;
 	newinet->rcv_tos      = ip_hdr(skb)->tos;
@@ -1346,9 +1345,12 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 	if (__inet_inherit_port(sk, newsk) < 0)
 		goto put_and_exit;
 	*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
-	if (*own_req)
+	if (likely(*own_req)) {
 		tcp_move_syn(newtp, req);
-
+		ireq->ireq_opt = NULL;
+	} else {
+		newinet->inet_opt = NULL;
+	}
 	return newsk;
 
 exit_overflow:
@@ -1359,6 +1361,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 	tcp_listendrop(sk);
 	return NULL;
 put_and_exit:
+	newinet->inet_opt = NULL;
 	inet_csk_prepare_forced_close(newsk);
 	tcp_done(newsk);
 	goto exit;
-- 
2.13.6


From 02da3d182928035ea47d05ff5787f19b227fcb88 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 18 Oct 2017 16:14:52 -0700
Subject: [PATCH 11/25] packet: avoid panic in packet_getsockopt()

[ Upstream commit 509c7a1ecc8601f94ffba8a00889fefb239c00c6 ]

syzkaller got crashes in packet_getsockopt() processing
PACKET_ROLLOVER_STATS command while another thread was managing
to change po->rollover

Using RCU will fix this bug. We might later add proper RCU annotations
for sparse sake.

In v2: I replaced kfree(rollover) in fanout_add() to kfree_rcu()
variant, as spotted by John.

Fixes: a9b6391814d5 ("packet: rollover statistics")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Cc: John Sperbeck <jsperbeck@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 24 ++++++++++++++++--------
 1 file changed, 16 insertions(+), 8 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index b17f9097c6fe..e7f6657269e0 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1720,7 +1720,7 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 
 out:
 	if (err && rollover) {
-		kfree(rollover);
+		kfree_rcu(rollover, rcu);
 		po->rollover = NULL;
 	}
 	mutex_unlock(&fanout_mutex);
@@ -1747,8 +1747,10 @@ static struct packet_fanout *fanout_release(struct sock *sk)
 		else
 			f = NULL;
 
-		if (po->rollover)
+		if (po->rollover) {
 			kfree_rcu(po->rollover, rcu);
+			po->rollover = NULL;
+		}
 	}
 	mutex_unlock(&fanout_mutex);
 
@@ -3851,6 +3853,7 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
 	void *data = &val;
 	union tpacket_stats_u st;
 	struct tpacket_rollover_stats rstats;
+	struct packet_rollover *rollover;
 
 	if (level != SOL_PACKET)
 		return -ENOPROTOOPT;
@@ -3929,13 +3932,18 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
 		       0);
 		break;
 	case PACKET_ROLLOVER_STATS:
-		if (!po->rollover)
+		rcu_read_lock();
+		rollover = rcu_dereference(po->rollover);
+		if (rollover) {
+			rstats.tp_all = atomic_long_read(&rollover->num);
+			rstats.tp_huge = atomic_long_read(&rollover->num_huge);
+			rstats.tp_failed = atomic_long_read(&rollover->num_failed);
+			data = &rstats;
+			lv = sizeof(rstats);
+		}
+		rcu_read_unlock();
+		if (!rollover)
 			return -EINVAL;
-		rstats.tp_all = atomic_long_read(&po->rollover->num);
-		rstats.tp_huge = atomic_long_read(&po->rollover->num_huge);
-		rstats.tp_failed = atomic_long_read(&po->rollover->num_failed);
-		data = &rstats;
-		lv = sizeof(rstats);
 		break;
 	case PACKET_TX_HAS_OFF:
 		val = po->tp_tx_has_off;
-- 
2.13.6


From 8b9cb14f65960f25159230fc09e8b4aacaa1dc55 Mon Sep 17 00:00:00 2001
From: Craig Gallek <kraig@google.com>
Date: Thu, 19 Oct 2017 15:00:29 -0400
Subject: [PATCH 12/25] soreuseport: fix initialization race

[ Upstream commit 1b5f962e71bfad6284574655c406597535c3ea7a ]

Syzkaller stumbled upon a way to trigger
WARNING: CPU: 1 PID: 13881 at net/core/sock_reuseport.c:41
reuseport_alloc+0x306/0x3b0 net/core/sock_reuseport.c:39

There are two initialization paths for the sock_reuseport structure in a
socket: Through the udp/tcp bind paths of SO_REUSEPORT sockets or through
SO_ATTACH_REUSEPORT_[CE]BPF before bind.  The existing implementation
assumedthat the socket lock protected both of these paths when it actually
only protects the SO_ATTACH_REUSEPORT path.  Syzkaller triggered this
double allocation by running these paths concurrently.

This patch moves the check for double allocation into the reuseport_alloc
function which is protected by a global spin lock.

Fixes: e32ea7e74727 ("soreuseport: fast reuseport UDP socket selection")
Fixes: c125e80b8868 ("soreuseport: fast reuseport TCP socket selection")
Signed-off-by: Craig Gallek <kraig@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock_reuseport.c  | 12 +++++++++---
 net/ipv4/inet_hashtables.c |  5 +----
 net/ipv4/udp.c             |  5 +----
 3 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index 9a1a352fd1eb..77f396b679ce 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -36,9 +36,14 @@ int reuseport_alloc(struct sock *sk)
 	 * soft irq of receive path or setsockopt from process context
 	 */
 	spin_lock_bh(&reuseport_lock);
-	WARN_ONCE(rcu_dereference_protected(sk->sk_reuseport_cb,
-					    lockdep_is_held(&reuseport_lock)),
-		  "multiple allocations for the same socket");
+
+	/* Allocation attempts can occur concurrently via the setsockopt path
+	 * and the bind/hash path.  Nothing to do when we lose the race.
+	 */
+	if (rcu_dereference_protected(sk->sk_reuseport_cb,
+				      lockdep_is_held(&reuseport_lock)))
+		goto out;
+
 	reuse = __reuseport_alloc(INIT_SOCKS);
 	if (!reuse) {
 		spin_unlock_bh(&reuseport_lock);
@@ -49,6 +54,7 @@ int reuseport_alloc(struct sock *sk)
 	reuse->num_socks = 1;
 	rcu_assign_pointer(sk->sk_reuseport_cb, reuse);
 
+out:
 	spin_unlock_bh(&reuseport_lock);
 
 	return 0;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index ca97835bfec4..b9bcf3db3af9 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -455,10 +455,7 @@ static int inet_reuseport_add_sock(struct sock *sk,
 			return reuseport_add_sock(sk, sk2);
 	}
 
-	/* Initial allocation may have already happened via setsockopt */
-	if (!rcu_access_pointer(sk->sk_reuseport_cb))
-		return reuseport_alloc(sk);
-	return 0;
+	return reuseport_alloc(sk);
 }
 
 int __inet_hash(struct sock *sk, struct sock *osk,
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 4363b1e89bdf..bef4a94ce1a0 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -222,10 +222,7 @@ static int udp_reuseport_add_sock(struct sock *sk, struct udp_hslot *hslot,
 		}
 	}
 
-	/* Initial allocation may have already happened via setsockopt */
-	if (!rcu_access_pointer(sk->sk_reuseport_cb))
-		return reuseport_alloc(sk);
-	return 0;
+	return reuseport_alloc(sk);
 }
 
 /**
-- 
2.13.6


From 63c447f7f2d4d6b72a03d3604747471ea781d378 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 21 Oct 2017 12:26:23 -0700
Subject: [PATCH 13/25] ipv6: flowlabel: do not leave opt->tot_len with garbage

[ Upstream commit 864e2a1f8aac05effac6063ce316b480facb46ff ]

When syzkaller team brought us a C repro for the crash [1] that
had been reported many times in the past, I finally could find
the root cause.

If FlowLabel info is merged by fl6_merge_options(), we leave
part of the opt_space storage provided by udp/raw/l2tp with random value
in opt_space.tot_len, unless a control message was provided at sendmsg()
time.

Then ip6_setup_cork() would use this random value to perform a kzalloc()
call. Undefined behavior and crashes.

Fix is to properly set tot_len in fl6_merge_options()

At the same time, we can also avoid consuming memory and cpu cycles
to clear it, if every option is copied via a kmemdup(). This is the
change in ip6_setup_cork().

[1]
kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] SMP KASAN
Dumping ftrace buffer:
   (ftrace buffer empty)
Modules linked in:
CPU: 0 PID: 6613 Comm: syz-executor0 Not tainted 4.14.0-rc4+ #127
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
task: ffff8801cb64a100 task.stack: ffff8801cc350000
RIP: 0010:ip6_setup_cork+0x274/0x15c0 net/ipv6/ip6_output.c:1168
RSP: 0018:ffff8801cc357550 EFLAGS: 00010203
RAX: dffffc0000000000 RBX: ffff8801cc357748 RCX: 0000000000000010
RDX: 0000000000000002 RSI: ffffffff842bd1d9 RDI: 0000000000000014
RBP: ffff8801cc357620 R08: ffff8801cb17f380 R09: ffff8801cc357b10
R10: ffff8801cb64a100 R11: 0000000000000000 R12: ffff8801cc357ab0
R13: ffff8801cc357b10 R14: 0000000000000000 R15: ffff8801c3bbf0c0
FS:  00007f9c5c459700(0000) GS:ffff8801db200000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000020324000 CR3: 00000001d1cf2000 CR4: 00000000001406f0
DR0: 0000000020001010 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000600
Call Trace:
 ip6_make_skb+0x282/0x530 net/ipv6/ip6_output.c:1729
 udpv6_sendmsg+0x2769/0x3380 net/ipv6/udp.c:1340
 inet_sendmsg+0x11f/0x5e0 net/ipv4/af_inet.c:762
 sock_sendmsg_nosec net/socket.c:633 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:643
 SYSC_sendto+0x358/0x5a0 net/socket.c:1750
 SyS_sendto+0x40/0x50 net/socket.c:1718
 entry_SYSCALL_64_fastpath+0x1f/0xbe
RIP: 0033:0x4520a9
RSP: 002b:00007f9c5c458c08 EFLAGS: 00000216 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 0000000000718000 RCX: 00000000004520a9
RDX: 0000000000000001 RSI: 0000000020fd1000 RDI: 0000000000000016
RBP: 0000000000000086 R08: 0000000020e0afe4 R09: 000000000000001c
R10: 0000000000000000 R11: 0000000000000216 R12: 00000000004bb1ee
R13: 00000000ffffffff R14: 0000000000000016 R15: 0000000000000029
Code: e0 07 83 c0 03 38 d0 7c 08 84 d2 0f 85 ea 0f 00 00 48 8d 79 04 48 b8 00 00 00 00 00 fc ff df 45 8b 74 24 04 48 89 fa 48 c1 ea 03 <0f> b6 14 02 48 89 f8 83 e0 07 83 c0 03 38 d0 7c 08 84 d2 0f 85
RIP: ip6_setup_cork+0x274/0x15c0 net/ipv6/ip6_output.c:1168 RSP: ffff8801cc357550

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_flowlabel.c | 1 +
 net/ipv6/ip6_output.c    | 4 ++--
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index b912f0dbaf72..b82e439804d1 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -315,6 +315,7 @@ struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space,
 	}
 	opt_space->dst1opt = fopt->dst1opt;
 	opt_space->opt_flen = fopt->opt_flen;
+	opt_space->tot_len = fopt->tot_len;
 	return opt_space;
 }
 EXPORT_SYMBOL_GPL(fl6_merge_options);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index e0236e902ea7..6e01c9a8dfd3 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1215,11 +1215,11 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
 		if (WARN_ON(v6_cork->opt))
 			return -EINVAL;
 
-		v6_cork->opt = kzalloc(opt->tot_len, sk->sk_allocation);
+		v6_cork->opt = kzalloc(sizeof(*opt), sk->sk_allocation);
 		if (unlikely(!v6_cork->opt))
 			return -ENOBUFS;
 
-		v6_cork->opt->tot_len = opt->tot_len;
+		v6_cork->opt->tot_len = sizeof(*opt);
 		v6_cork->opt->opt_flen = opt->opt_flen;
 		v6_cork->opt->opt_nflen = opt->opt_nflen;
 
-- 
2.13.6


From dda54145beb1a9aa878273441da6ae4f693be832 Mon Sep 17 00:00:00 2001
From: Laszlo Toth <laszlth@gmail.com>
Date: Mon, 23 Oct 2017 19:19:33 +0200
Subject: [PATCH 14/25] sctp: full support for ipv6 ip_nonlocal_bind &
 IP_FREEBIND

[ Upstream commit b71d21c274eff20a9db8158882b545b141b73ab8 ]

Commit 9b9742022888 ("sctp: support ipv6 nonlocal bind")
introduced support for the above options as v4 sctp did,
so patched sctp_v6_available().

In the v4 implementation it's enough, because
sctp_inet_bind_verify() just returns with sctp_v4_available().
However sctp_inet6_bind_verify() has an extra check before that
for link-local scope_id, which won't respect the above options.

Added the checks before calling ipv6_chk_addr(), but
not before the validation of scope_id.

before (w/ both options):
 ./v6test fe80::10 sctp
 bind failed, errno: 99 (Cannot assign requested address)
 ./v6test fe80::10 tcp
 bind success, errno: 0 (Success)

after (w/ both options):
 ./v6test fe80::10 sctp
 bind success, errno: 0 (Success)

Signed-off-by: Laszlo Toth <laszlth@gmail.com>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ipv6.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index ca4a63e3eadd..f7f00d012888 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -881,8 +881,10 @@ static int sctp_inet6_bind_verify(struct sctp_sock *opt, union sctp_addr *addr)
 			net = sock_net(&opt->inet.sk);
 			rcu_read_lock();
 			dev = dev_get_by_index_rcu(net, addr->v6.sin6_scope_id);
-			if (!dev ||
-			    !ipv6_chk_addr(net, &addr->v6.sin6_addr, dev, 0)) {
+			if (!dev || !(opt->inet.freebind ||
+				      net->ipv6.sysctl.ip_nonlocal_bind ||
+				      ipv6_chk_addr(net, &addr->v6.sin6_addr,
+						    dev, 0))) {
 				rcu_read_unlock();
 				return 0;
 			}
-- 
2.13.6


From 2caaf39eccf04c27f12b70f7dc29bb956fb67faf Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 22 Oct 2017 12:33:57 -0700
Subject: [PATCH 15/25] tcp/dccp: fix lockdep splat in inet_csk_route_req()

[ Upstream commit a6ca7abe53633d08eea1c6756cb49c9b2d4c90bf ]

This patch fixes the following lockdep splat in inet_csk_route_req()

  lockdep_rcu_suspicious
  inet_csk_route_req
  tcp_v4_send_synack
  tcp_rtx_synack
  inet_rtx_syn_ack
  tcp_fastopen_synack_time
  tcp_retransmit_timer
  tcp_write_timer_handler
  tcp_write_timer
  call_timer_fn

Thread running inet_csk_route_req() owns a reference on the request
socket, so we have the guarantee ireq->ireq_opt wont be changed or
freed.

lockdep can enforce this invariant for us.

Fixes: c92e8c02fe66 ("tcp/dccp: fix ireq->opt races")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/inet_connection_sock.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 8d7cc4e53205..af060ccc30e7 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -410,7 +410,8 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk,
 	struct ip_options_rcu *opt;
 	struct rtable *rt;
 
-	opt = rcu_dereference(ireq->ireq_opt);
+	opt = rcu_dereference_protected(ireq->ireq_opt,
+					atomic_read(&req->rsk_refcnt) > 0);
 	flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
 			   sk->sk_protocol, inet_sk_flowi_flags(sk),
-- 
2.13.6


From d348abd79274d6b12aaba6c50380213b90f42d78 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 24 Oct 2017 08:20:31 -0700
Subject: [PATCH 16/25] tcp/dccp: fix other lockdep splats accessing ireq_opt
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 06f877d613be3621604c2520ec0351d9fbdca15f ]

In my first attempt to fix the lockdep splat, I forgot we could
enter inet_csk_route_req() with a freshly allocated request socket,
for which refcount has not yet been elevated, due to complex
SLAB_TYPESAFE_BY_RCU rules.

We either are in rcu_read_lock() section _or_ we own a refcount on the
request.

Correct RCU verb to use here is rcu_dereference_check(), although it is
not possible to prove we actually own a reference on a shared
refcount :/

In v2, I added ireq_opt_deref() helper and use in three places, to fix other
possible splats.

[   49.844590]  lockdep_rcu_suspicious+0xea/0xf3
[   49.846487]  inet_csk_route_req+0x53/0x14d
[   49.848334]  tcp_v4_route_req+0xe/0x10
[   49.850174]  tcp_conn_request+0x31c/0x6a0
[   49.851992]  ? __lock_acquire+0x614/0x822
[   49.854015]  tcp_v4_conn_request+0x5a/0x79
[   49.855957]  ? tcp_v4_conn_request+0x5a/0x79
[   49.858052]  tcp_rcv_state_process+0x98/0xdcc
[   49.859990]  ? sk_filter_trim_cap+0x2f6/0x307
[   49.862085]  tcp_v4_do_rcv+0xfc/0x145
[   49.864055]  ? tcp_v4_do_rcv+0xfc/0x145
[   49.866173]  tcp_v4_rcv+0x5ab/0xaf9
[   49.868029]  ip_local_deliver_finish+0x1af/0x2e7
[   49.870064]  ip_local_deliver+0x1b2/0x1c5
[   49.871775]  ? inet_del_offload+0x45/0x45
[   49.873916]  ip_rcv_finish+0x3f7/0x471
[   49.875476]  ip_rcv+0x3f1/0x42f
[   49.876991]  ? ip_local_deliver_finish+0x2e7/0x2e7
[   49.878791]  __netif_receive_skb_core+0x6d3/0x950
[   49.880701]  ? process_backlog+0x7e/0x216
[   49.882589]  __netif_receive_skb+0x1d/0x5e
[   49.884122]  process_backlog+0x10c/0x216
[   49.885812]  net_rx_action+0x147/0x3df

Fixes: a6ca7abe53633 ("tcp/dccp: fix lockdep splat in inet_csk_route_req()")
Fixes: c92e8c02fe66 ("tcp/dccp: fix ireq->opt races")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: kernel test robot <fengguang.wu@intel.com>
Reported-by: Maciej Żenczykowski <maze@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_sock.h         | 6 ++++++
 net/dccp/ipv4.c                 | 2 +-
 net/ipv4/inet_connection_sock.c | 4 ++--
 net/ipv4/tcp_ipv4.c             | 2 +-
 4 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 6213a90a8cec..0464b207d0cf 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -132,6 +132,12 @@ static inline int inet_request_bound_dev_if(const struct sock *sk,
 	return sk->sk_bound_dev_if;
 }
 
+static inline struct ip_options_rcu *ireq_opt_deref(const struct inet_request_sock *ireq)
+{
+	return rcu_dereference_check(ireq->ireq_opt,
+				     atomic_read(&ireq->req.rsk_refcnt) > 0);
+}
+
 struct inet_cork {
 	unsigned int		flags;
 	__be32			addr;
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 77f5e3524ebc..8c7799cdd3cf 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -495,7 +495,7 @@ static int dccp_v4_send_response(const struct sock *sk, struct request_sock *req
 							      ireq->ir_rmt_addr);
 		err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
 					    ireq->ir_rmt_addr,
-					    rcu_dereference(ireq->ireq_opt));
+					    ireq_opt_deref(ireq));
 		err = net_xmit_eval(err);
 	}
 
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index af060ccc30e7..d1cab49393e2 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -410,8 +410,8 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk,
 	struct ip_options_rcu *opt;
 	struct rtable *rt;
 
-	opt = rcu_dereference_protected(ireq->ireq_opt,
-					atomic_read(&req->rsk_refcnt) > 0);
+	opt = ireq_opt_deref(ireq);
+
 	flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
 			   sk->sk_protocol, inet_sk_flowi_flags(sk),
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index c96b9dcce323..d577ec07a0d8 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -861,7 +861,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
 
 		err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
 					    ireq->ir_rmt_addr,
-					    rcu_dereference(ireq->ireq_opt));
+					    ireq_opt_deref(ireq));
 		err = net_xmit_eval(err);
 	}
 
-- 
2.13.6


From f712dc28c142cc2f110d90328e2ee062802df562 Mon Sep 17 00:00:00 2001
From: Andrei Vagin <avagin@openvz.org>
Date: Wed, 25 Oct 2017 10:16:42 -0700
Subject: [PATCH 17/25] net/unix: don't show information about sockets from
 other namespaces

[ Upstream commit 0f5da659d8f1810f44de14acf2c80cd6499623a0 ]

socket_diag shows information only about sockets from a namespace where
a diag socket lives.

But if we request information about one unix socket, the kernel don't
check that its netns is matched with a diag socket namespace, so any
user can get information about any unix socket in a system. This looks
like a bug.

v2: add a Fixes tag

Fixes: 51d7cccf0723 ("net: make sock diag per-namespace")
Signed-off-by: Andrei Vagin <avagin@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/diag.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/unix/diag.c b/net/unix/diag.c
index 4d9679701a6d..384c84e83462 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -257,6 +257,8 @@ static int unix_diag_get_exact(struct sk_buff *in_skb,
 	err = -ENOENT;
 	if (sk == NULL)
 		goto out_nosk;
+	if (!net_eq(sock_net(sk), net))
+		goto out;
 
 	err = sock_diag_check_cookie(sk, req->udiag_cookie);
 	if (err)
-- 
2.13.6


From 42f34a8d5c8505b259b243a7e135093b346c7392 Mon Sep 17 00:00:00 2001
From: Girish Moodalbail <girish.moodalbail@oracle.com>
Date: Wed, 25 Oct 2017 00:23:04 -0700
Subject: [PATCH 18/25] tap: double-free in error path in tap_open()

[ Upstream commit 78e0ea6791d7baafb8a0ca82b1bd0c7b3453c919 ]

Double free of skb_array in tap module is causing kernel panic. When
tap_set_queue() fails we free skb_array right away by calling
skb_array_cleanup(). However, later on skb_array_cleanup() is called
again by tap_sock_destruct through sock_put(). This patch fixes that
issue.

Fixes: 362899b8725b35e3 (macvtap: switch to use skb array)
Signed-off-by: Girish Moodalbail <girish.moodalbail@oracle.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macvtap.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 0da292e9a25c..9da9db17fc36 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -559,6 +559,10 @@ static int macvtap_open(struct inode *inode, struct file *file)
 					     &macvtap_proto, 0);
 	if (!q)
 		goto err;
+	if (skb_array_init(&q->skb_array, dev->tx_queue_len, GFP_KERNEL)) {
+		sk_free(&q->sk);
+		goto err;
+	}
 
 	RCU_INIT_POINTER(q->sock.wq, &q->wq);
 	init_waitqueue_head(&q->wq.wait);
@@ -582,22 +586,18 @@ static int macvtap_open(struct inode *inode, struct file *file)
 	if ((dev->features & NETIF_F_HIGHDMA) && (dev->features & NETIF_F_SG))
 		sock_set_flag(&q->sk, SOCK_ZEROCOPY);
 
-	err = -ENOMEM;
-	if (skb_array_init(&q->skb_array, dev->tx_queue_len, GFP_KERNEL))
-		goto err_array;
-
 	err = macvtap_set_queue(dev, file, q);
-	if (err)
-		goto err_queue;
+	if (err) {
+		/* macvtap_sock_destruct() will take care of freeing skb_array */
+		goto err_put;
+	}
 
 	dev_put(dev);
 
 	rtnl_unlock();
 	return err;
 
-err_queue:
-	skb_array_cleanup(&q->skb_array);
-err_array:
+err_put:
 	sock_put(&q->sk);
 err:
 	if (dev)
-- 
2.13.6


From edc9ce379e1d4befd248720ebf5c84593abb5912 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 26 Oct 2017 19:19:56 +0800
Subject: [PATCH 19/25] ipip: only increase err_count for some certain type
 icmp in ipip_err

[ Upstream commit f3594f0a7ea36661d7fd942facd7f31a64245f1a ]

t->err_count is used to count the link failure on tunnel and an err
will be reported to user socket in tx path if t->err_count is not 0.
udp socket could even return EHOSTUNREACH to users.

Since commit fd58156e456d ("IPIP: Use ip-tunneling code.") removed
the 'switch check' for icmp type in ipip_err(), err_count would be
increased by the icmp packet with ICMP_EXC_FRAGTIME code. an link
failure would be reported out due to this.

In Jianlin's case, when receiving ICMP_EXC_FRAGTIME a icmp packet,
udp netperf failed with the err:
  send_data: data send error: No route to host (errno 113)

We expect this error reported from tunnel to socket when receiving
some certain type icmp, but not ICMP_EXC_FRAGTIME, ICMP_SR_FAILED
or ICMP_PARAMETERPROB ones.

This patch is to bring 'switch check' for icmp type back to ipip_err
so that it only reports link failure for the right type icmp, just as
in ipgre_err() and ipip6_err().

Fixes: fd58156e456d ("IPIP: Use ip-tunneling code.")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ipip.c | 59 ++++++++++++++++++++++++++++++++++++++++-----------------
 1 file changed, 42 insertions(+), 17 deletions(-)

diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index c9392589c415..56d71a004dce 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -128,43 +128,68 @@ static struct rtnl_link_ops ipip_link_ops __read_mostly;
 
 static int ipip_err(struct sk_buff *skb, u32 info)
 {
-
-/* All the routers (except for Linux) return only
-   8 bytes of packet payload. It means, that precise relaying of
-   ICMP in the real Internet is absolutely infeasible.
- */
+	/* All the routers (except for Linux) return only
+	 * 8 bytes of packet payload. It means, that precise relaying of
+	 * ICMP in the real Internet is absolutely infeasible.
+	 */
 	struct net *net = dev_net(skb->dev);
 	struct ip_tunnel_net *itn = net_generic(net, ipip_net_id);
 	const struct iphdr *iph = (const struct iphdr *)skb->data;
-	struct ip_tunnel *t;
-	int err;
 	const int type = icmp_hdr(skb)->type;
 	const int code = icmp_hdr(skb)->code;
+	struct ip_tunnel *t;
+	int err = 0;
+
+	switch (type) {
+	case ICMP_DEST_UNREACH:
+		switch (code) {
+		case ICMP_SR_FAILED:
+			/* Impossible event. */
+			goto out;
+		default:
+			/* All others are translated to HOST_UNREACH.
+			 * rfc2003 contains "deep thoughts" about NET_UNREACH,
+			 * I believe they are just ether pollution. --ANK
+			 */
+			break;
+		}
+		break;
+
+	case ICMP_TIME_EXCEEDED:
+		if (code != ICMP_EXC_TTL)
+			goto out;
+		break;
+
+	case ICMP_REDIRECT:
+		break;
+
+	default:
+		goto out;
+	}
 
-	err = -ENOENT;
 	t = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
 			     iph->daddr, iph->saddr, 0);
-	if (!t)
+	if (!t) {
+		err = -ENOENT;
 		goto out;
+	}
 
 	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
-		ipv4_update_pmtu(skb, dev_net(skb->dev), info,
-				 t->parms.link, 0, iph->protocol, 0);
-		err = 0;
+		ipv4_update_pmtu(skb, net, info, t->parms.link, 0,
+				 iph->protocol, 0);
 		goto out;
 	}
 
 	if (type == ICMP_REDIRECT) {
-		ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0,
-			      iph->protocol, 0);
-		err = 0;
+		ipv4_redirect(skb, net, t->parms.link, 0, iph->protocol, 0);
 		goto out;
 	}
 
-	if (t->parms.iph.daddr == 0)
+	if (t->parms.iph.daddr == 0) {
+		err = -ENOENT;
 		goto out;
+	}
 
-	err = 0;
 	if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
 		goto out;
 
-- 
2.13.6


From 9b706b0478b711ad85229f036aee4b3674e09a29 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 26 Oct 2017 19:23:27 +0800
Subject: [PATCH 20/25] ip6_gre: only increase err_count for some certain type
 icmpv6 in ip6gre_err

[ Upstream commit f8d20b46ce55cf40afb30dcef6d9288f7ef46d9b ]

The similar fix in patch 'ipip: only increase err_count for some
certain type icmp in ipip_err' is needed for ip6gre_err.

In Jianlin's case, udp netperf broke even when receiving a TooBig
icmpv6 packet.

Fixes: c12b395a4664 ("gre: Support GRE over IPv6")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 41c10486cf7e..d083d3c25475 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -408,13 +408,16 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	case ICMPV6_DEST_UNREACH:
 		net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n",
 				    t->parms.name);
-		break;
+		if (code != ICMPV6_PORT_UNREACH)
+			break;
+		return;
 	case ICMPV6_TIME_EXCEED:
 		if (code == ICMPV6_EXC_HOPLIMIT) {
 			net_dbg_ratelimited("%s: Too small hop limit or routing loop in tunnel!\n",
 					    t->parms.name);
+			break;
 		}
-		break;
+		return;
 	case ICMPV6_PARAMPROB:
 		teli = 0;
 		if (code == ICMPV6_HDR_FIELD)
@@ -430,7 +433,7 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 			net_dbg_ratelimited("%s: Recipient unable to parse tunneled packet!\n",
 					    t->parms.name);
 		}
-		break;
+		return;
 	case ICMPV6_PKT_TOOBIG:
 		mtu = be32_to_cpu(info) - offset - t->tun_hlen;
 		if (t->dev->type == ARPHRD_ETHER)
@@ -438,7 +441,7 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		if (mtu < IPV6_MIN_MTU)
 			mtu = IPV6_MIN_MTU;
 		t->dev->mtu = mtu;
-		break;
+		return;
 	}
 
 	if (time_before(jiffies, t->err_time + IP6TUNNEL_ERR_TIMEO))
-- 
2.13.6


From 49658d7ba4ebb7e9925c1a3147f3e50e23fe520e Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 26 Oct 2017 19:27:17 +0800
Subject: [PATCH 21/25] ip6_gre: update dst pmtu if dev mtu has been updated by
 toobig in __gre6_xmit

[ Upstream commit 8aec4959d832bae0889a8e2f348973b5e4abffef ]

When receiving a Toobig icmpv6 packet, ip6gre_err would just set
tunnel dev's mtu, that's not enough. For skb_dst(skb)'s pmtu may
still be using the old value, it has no chance to be updated with
tunnel dev's mtu.

Jianlin found this issue by reducing route's mtu while running
netperf, the performance went to 0.

ip6ip6 and ip4ip6 tunnel can work well with this, as they lookup
the upper dst and update_pmtu it's pmtu or icmpv6_send a Toobig
to upper socket after setting tunnel dev's mtu.

We couldn't do that for ip6_gre, as gre's inner packet could be
any protocol, it's difficult to handle them (like lookup upper
dst) in a good way.

So this patch is to fix it by updating skb_dst(skb)'s pmtu when
dev->mtu < skb_dst(skb)'s pmtu in tx path. It's safe to do this
update there, as usually dev->mtu <= skb_dst(skb)'s pmtu and no
performance regression can be caused by this.

Fixes: c12b395a4664 ("gre: Support GRE over IPv6")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index d083d3c25475..e9b14e3493f2 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -508,8 +508,8 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb,
 			       __u32 *pmtu, __be16 proto)
 {
 	struct ip6_tnl *tunnel = netdev_priv(dev);
-	__be16 protocol = (dev->type == ARPHRD_ETHER) ?
-			  htons(ETH_P_TEB) : proto;
+	struct dst_entry *dst = skb_dst(skb);
+	__be16 protocol;
 
 	if (dev->type == ARPHRD_ETHER)
 		IPCB(skb)->flags = 0;
@@ -523,9 +523,14 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb,
 		tunnel->o_seqno++;
 
 	/* Push GRE header. */
+	protocol = (dev->type == ARPHRD_ETHER) ? htons(ETH_P_TEB) : proto;
 	gre_build_header(skb, tunnel->tun_hlen, tunnel->parms.o_flags,
 			 protocol, tunnel->parms.o_key, htonl(tunnel->o_seqno));
 
+	/* TooBig packet may have updated dst->dev's mtu */
+	if (dst && dst_mtu(dst) > dst->dev->mtu)
+		dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu);
+
 	return ip6_tnl_xmit(skb, dev, dsfield, fl6, encap_limit, pmtu,
 			    NEXTHDR_GRE);
 }
-- 
2.13.6


From d280a3c0feeebdc25a2843bfa16216e1aaaa2dd1 Mon Sep 17 00:00:00 2001
From: Julien Gomes <julien@arista.com>
Date: Wed, 25 Oct 2017 11:50:50 -0700
Subject: [PATCH 22/25] tun: allow positive return values on
 dev_get_valid_name() call

[ Upstream commit 5c25f65fd1e42685f7ccd80e0621829c105785d9 ]

If the name argument of dev_get_valid_name() contains "%d", it will try
to assign it a unit number in __dev__alloc_name() and return either the
unit number (>= 0) or an error code (< 0).
Considering positive values as error values prevent tun device creations
relying this mechanism, therefor we should only consider negative values
as errors here.

Signed-off-by: Julien Gomes <julien@arista.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index a774c827a414..518cbfbc8b65 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1788,7 +1788,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 		if (!dev)
 			return -ENOMEM;
 		err = dev_get_valid_name(net, dev, name);
-		if (err)
+		if (err < 0)
 			goto err_free_dev;
 
 		dev_net_set(dev, net);
-- 
2.13.6


From 69f62c6a1532035b210cac9997a9bebd8ca188d3 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sat, 28 Oct 2017 02:13:29 +0800
Subject: [PATCH 23/25] sctp: reset owner sk for data chunks on out queues when
 migrating a sock

[ Upstream commit d04adf1b355181e737b6b1e23d801b07f0b7c4c0 ]

Now when migrating sock to another one in sctp_sock_migrate(), it only
resets owner sk for the data in receive queues, not the chunks on out
queues.

It would cause that data chunks length on the sock is not consistent
with sk sk_wmem_alloc. When closing the sock or freeing these chunks,
the old sk would never be freed, and the new sock may crash due to
the overflow sk_wmem_alloc.

syzbot found this issue with this series:

  r0 = socket$inet_sctp()
  sendto$inet(r0)
  listen(r0)
  accept4(r0)
  close(r0)

Although listen() should have returned error when one TCP-style socket
is in connecting (I may fix this one in another patch), it could also
be reproduced by peeling off an assoc.

This issue is there since very beginning.

This patch is to reset owner sk for the chunks on out queues so that
sk sk_wmem_alloc has correct value after accept one sock or peeloff
an assoc to one sock.

Note that when resetting owner sk for chunks on outqueue, it has to
sctp_clear_owner_w/skb_orphan chunks before changing assoc->base.sk
first and then sctp_set_owner_w them after changing assoc->base.sk,
due to that sctp_wfree and it's callees are using assoc->base.sk.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 3ef725229449..ffcc8aa78db7 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -168,6 +168,36 @@ static inline void sctp_set_owner_w(struct sctp_chunk *chunk)
 	sk_mem_charge(sk, chunk->skb->truesize);
 }
 
+static void sctp_clear_owner_w(struct sctp_chunk *chunk)
+{
+	skb_orphan(chunk->skb);
+}
+
+static void sctp_for_each_tx_datachunk(struct sctp_association *asoc,
+				       void (*cb)(struct sctp_chunk *))
+
+{
+	struct sctp_outq *q = &asoc->outqueue;
+	struct sctp_transport *t;
+	struct sctp_chunk *chunk;
+
+	list_for_each_entry(t, &asoc->peer.transport_addr_list, transports)
+		list_for_each_entry(chunk, &t->transmitted, transmitted_list)
+			cb(chunk);
+
+	list_for_each_entry(chunk, &q->retransmit, list)
+		cb(chunk);
+
+	list_for_each_entry(chunk, &q->sacked, list)
+		cb(chunk);
+
+	list_for_each_entry(chunk, &q->abandoned, list)
+		cb(chunk);
+
+	list_for_each_entry(chunk, &q->out_chunk_list, list)
+		cb(chunk);
+}
+
 /* Verify that this is a valid address. */
 static inline int sctp_verify_addr(struct sock *sk, union sctp_addr *addr,
 				   int len)
@@ -7826,7 +7856,9 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
 	 * paths won't try to lock it and then oldsk.
 	 */
 	lock_sock_nested(newsk, SINGLE_DEPTH_NESTING);
+	sctp_for_each_tx_datachunk(assoc, sctp_clear_owner_w);
 	sctp_assoc_migrate(assoc, newsk);
+	sctp_for_each_tx_datachunk(assoc, sctp_set_owner_w);
 
 	/* If the association on the newsk is already closed before accept()
 	 * is called, set RCV_SHUTDOWN flag.
-- 
2.13.6


From f6c4a3d305decd0ab200e0066cae22f80fc96a1f Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Fri, 27 Oct 2017 22:08:56 -0700
Subject: [PATCH 24/25] net_sched: avoid matching qdisc with zero handle

[ Upstream commit 50317fce2cc70a2bbbc4b42c31bbad510382a53c ]

Davide found the following script triggers a NULL pointer
dereference:

ip l a name eth0 type dummy
tc q a dev eth0 parent :1 handle 1: htb

This is because for a freshly created netdevice noop_qdisc
is attached and when passing 'parent :1', kernel actually
tries to match the major handle which is 0 and noop_qdisc
has handle 0 so is matched by mistake. Commit 69012ae425d7
tries to fix a similar bug but still misses this case.

Handle 0 is not a valid one, should be just skipped. In
fact, kernel uses it as TC_H_UNSPEC.

Fixes: 69012ae425d7 ("net: sched: fix handling of singleton qdiscs with qdisc_hash")
Fixes: 59cc1f61f09c ("net: sched:convert qdisc linked list to hashtable")
Reported-by: Davide Caratti <dcaratti@redhat.com>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_api.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 195a3b2d9afc..ea13df1be067 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -296,6 +296,8 @@ struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle)
 {
 	struct Qdisc *q;
 
+	if (!handle)
+		return NULL;
 	q = qdisc_match_from_root(dev->qdisc, handle);
 	if (q)
 		goto out;
-- 
2.13.6


From 5718af67e4bd0ab15817a2dabfd6f7d6ea6e8250 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Fri, 6 Oct 2017 17:05:49 +0200
Subject: [PATCH 25/25] ppp: fix race in ppp device destruction

[ Upstream commit 6151b8b37b119e8e3a8401b080d532520c95faf4 ]

ppp_release() tries to ensure that netdevices are unregistered before
decrementing the unit refcount and running ppp_destroy_interface().

This is all fine as long as the the device is unregistered by
ppp_release(): the unregister_netdevice() call, followed by
rtnl_unlock(), guarantee that the unregistration process completes
before rtnl_unlock() returns.

However, the device may be unregistered by other means (like
ppp_nl_dellink()). If this happens right before ppp_release() calling
rtnl_lock(), then ppp_release() has to wait for the concurrent
unregistration code to release the lock.
But rtnl_unlock() releases the lock before completing the device
unregistration process. This allows ppp_release() to proceed and
eventually call ppp_destroy_interface() before the unregistration
process completes. Calling free_netdev() on this partially unregistered
device will BUG():

 ------------[ cut here ]------------
 kernel BUG at net/core/dev.c:8141!
 invalid opcode: 0000 [#1] SMP

 CPU: 1 PID: 1557 Comm: pppd Not tainted 4.14.0-rc2+ #4
 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1.fc26 04/01/2014

 Call Trace:
  ppp_destroy_interface+0xd8/0xe0 [ppp_generic]
  ppp_disconnect_channel+0xda/0x110 [ppp_generic]
  ppp_unregister_channel+0x5e/0x110 [ppp_generic]
  pppox_unbind_sock+0x23/0x30 [pppox]
  pppoe_connect+0x130/0x440 [pppoe]
  SYSC_connect+0x98/0x110
  ? do_fcntl+0x2c0/0x5d0
  SyS_connect+0xe/0x10
  entry_SYSCALL_64_fastpath+0x1a/0xa5

 RIP: free_netdev+0x107/0x110 RSP: ffffc28a40573d88
 ---[ end trace ed294ff0cc40eeff ]---

We could set the ->needs_free_netdev flag on PPP devices and move the
ppp_destroy_interface() logic in the ->priv_destructor() callback. But
that'd be quite intrusive as we'd first need to unlink from the other
channels and units that depend on the device (the ones that used the
PPPIOCCONNECT and PPPIOCATTACH ioctls).

Instead, we can just let the netdevice hold a reference on its
ppp_file. This reference is dropped in ->priv_destructor(), at the very
end of the unregistration process, so that neither ppp_release() nor
ppp_disconnect_channel() can call ppp_destroy_interface() in the interim.

Reported-by: Beniamino Galvani <bgalvani@redhat.com>
Fixes: 8cb775bc0a34 ("ppp: fix device unregistration upon netns deletion")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/ppp_generic.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 96fa0e61d3af..440d5f42810f 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -1338,7 +1338,17 @@ ppp_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats64)
 
 static int ppp_dev_init(struct net_device *dev)
 {
+	struct ppp *ppp;
+
 	netdev_lockdep_set_classes(dev);
+
+	ppp = netdev_priv(dev);
+	/* Let the netdevice take a reference on the ppp file. This ensures
+	 * that ppp_destroy_interface() won't run before the device gets
+	 * unregistered.
+	 */
+	atomic_inc(&ppp->file.refcnt);
+
 	return 0;
 }
 
@@ -1361,6 +1371,15 @@ static void ppp_dev_uninit(struct net_device *dev)
 	wake_up_interruptible(&ppp->file.rwait);
 }
 
+static void ppp_dev_priv_destructor(struct net_device *dev)
+{
+	struct ppp *ppp;
+
+	ppp = netdev_priv(dev);
+	if (atomic_dec_and_test(&ppp->file.refcnt))
+		ppp_destroy_interface(ppp);
+}
+
 static const struct net_device_ops ppp_netdev_ops = {
 	.ndo_init	 = ppp_dev_init,
 	.ndo_uninit      = ppp_dev_uninit,
@@ -1386,6 +1405,7 @@ static void ppp_setup(struct net_device *dev)
 	dev->tx_queue_len = 3;
 	dev->type = ARPHRD_PPP;
 	dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST;
+	dev->destructor = ppp_dev_priv_destructor;
 	netif_keep_dst(dev);
 }
 
-- 
2.13.6


[-- Attachment #3: net_413.mbox --]
[-- Type: Application/Octet-Stream, Size: 110300 bytes --]

From 856d250e8c5cf6f8f4f2a15175583530c05868ee Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Fri, 6 Oct 2017 17:05:49 +0200
Subject: [PATCH 01/37] ppp: fix race in ppp device destruction

[ Upstream commit 6151b8b37b119e8e3a8401b080d532520c95faf4 ]

ppp_release() tries to ensure that netdevices are unregistered before
decrementing the unit refcount and running ppp_destroy_interface().

This is all fine as long as the the device is unregistered by
ppp_release(): the unregister_netdevice() call, followed by
rtnl_unlock(), guarantee that the unregistration process completes
before rtnl_unlock() returns.

However, the device may be unregistered by other means (like
ppp_nl_dellink()). If this happens right before ppp_release() calling
rtnl_lock(), then ppp_release() has to wait for the concurrent
unregistration code to release the lock.
But rtnl_unlock() releases the lock before completing the device
unregistration process. This allows ppp_release() to proceed and
eventually call ppp_destroy_interface() before the unregistration
process completes. Calling free_netdev() on this partially unregistered
device will BUG():

 ------------[ cut here ]------------
 kernel BUG at net/core/dev.c:8141!
 invalid opcode: 0000 [#1] SMP

 CPU: 1 PID: 1557 Comm: pppd Not tainted 4.14.0-rc2+ #4
 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1.fc26 04/01/2014

 Call Trace:
  ppp_destroy_interface+0xd8/0xe0 [ppp_generic]
  ppp_disconnect_channel+0xda/0x110 [ppp_generic]
  ppp_unregister_channel+0x5e/0x110 [ppp_generic]
  pppox_unbind_sock+0x23/0x30 [pppox]
  pppoe_connect+0x130/0x440 [pppoe]
  SYSC_connect+0x98/0x110
  ? do_fcntl+0x2c0/0x5d0
  SyS_connect+0xe/0x10
  entry_SYSCALL_64_fastpath+0x1a/0xa5

 RIP: free_netdev+0x107/0x110 RSP: ffffc28a40573d88
 ---[ end trace ed294ff0cc40eeff ]---

We could set the ->needs_free_netdev flag on PPP devices and move the
ppp_destroy_interface() logic in the ->priv_destructor() callback. But
that'd be quite intrusive as we'd first need to unlink from the other
channels and units that depend on the device (the ones that used the
PPPIOCCONNECT and PPPIOCATTACH ioctls).

Instead, we can just let the netdevice hold a reference on its
ppp_file. This reference is dropped in ->priv_destructor(), at the very
end of the unregistration process, so that neither ppp_release() nor
ppp_disconnect_channel() can call ppp_destroy_interface() in the interim.

Reported-by: Beniamino Galvani <bgalvani@redhat.com>
Fixes: 8cb775bc0a34 ("ppp: fix device unregistration upon netns deletion")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/ppp_generic.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index a404552555d4..6722b8354618 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -1339,7 +1339,17 @@ ppp_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats64)
 
 static int ppp_dev_init(struct net_device *dev)
 {
+	struct ppp *ppp;
+
 	netdev_lockdep_set_classes(dev);
+
+	ppp = netdev_priv(dev);
+	/* Let the netdevice take a reference on the ppp file. This ensures
+	 * that ppp_destroy_interface() won't run before the device gets
+	 * unregistered.
+	 */
+	atomic_inc(&ppp->file.refcnt);
+
 	return 0;
 }
 
@@ -1362,6 +1372,15 @@ static void ppp_dev_uninit(struct net_device *dev)
 	wake_up_interruptible(&ppp->file.rwait);
 }
 
+static void ppp_dev_priv_destructor(struct net_device *dev)
+{
+	struct ppp *ppp;
+
+	ppp = netdev_priv(dev);
+	if (atomic_dec_and_test(&ppp->file.refcnt))
+		ppp_destroy_interface(ppp);
+}
+
 static const struct net_device_ops ppp_netdev_ops = {
 	.ndo_init	 = ppp_dev_init,
 	.ndo_uninit      = ppp_dev_uninit,
@@ -1387,6 +1406,7 @@ static void ppp_setup(struct net_device *dev)
 	dev->tx_queue_len = 3;
 	dev->type = ARPHRD_PPP;
 	dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST;
+	dev->priv_destructor = ppp_dev_priv_destructor;
 	netif_keep_dst(dev);
 }
 
-- 
2.13.6


From fd0ed9a7a367ede8f4846910732e717855012d17 Mon Sep 17 00:00:00 2001
From: Alexey Kodanev <alexey.kodanev@oracle.com>
Date: Fri, 6 Oct 2017 19:02:35 +0300
Subject: [PATCH 02/37] gso: fix payload length when gso_size is zero

[ Upstream commit 3d0241d57c7b25bb75ac9d7a62753642264fdbce ]

When gso_size reset to zero for the tail segment in skb_segment(), later
in ipv6_gso_segment(), __skb_udp_tunnel_segment() and gre_gso_segment()
we will get incorrect results (payload length, pcsum) for that segment.
inet_gso_segment() already has a check for gso_size before calculating
payload.

The issue was found with LTP vxlan & gre tests over ixgbe NIC.

Fixes: 07b26c9454a2 ("gso: Support partial splitting at the frag_list pointer")
Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Acked-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/gre_offload.c | 2 +-
 net/ipv4/udp_offload.c | 2 +-
 net/ipv6/ip6_offload.c | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index d5cac99170b1..8c72034df28e 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -98,7 +98,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 		greh = (struct gre_base_hdr *)skb_transport_header(skb);
 		pcsum = (__sum16 *)(greh + 1);
 
-		if (gso_partial) {
+		if (gso_partial && skb_is_gso(skb)) {
 			unsigned int partial_adj;
 
 			/* Adjust checksum to account for the fact that
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 0932c85b42af..6401574cd638 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -122,7 +122,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 		 * will be using a length value equal to only one MSS sized
 		 * segment instead of the entire frame.
 		 */
-		if (gso_partial) {
+		if (gso_partial && skb_is_gso(skb)) {
 			uh->len = htons(skb_shinfo(skb)->gso_size +
 					SKB_GSO_CB(skb)->data_offset +
 					skb->head - (unsigned char *)uh);
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index cdb3728faca7..4a87f9428ca5 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -105,7 +105,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 
 	for (skb = segs; skb; skb = skb->next) {
 		ipv6h = (struct ipv6hdr *)(skb_mac_header(skb) + nhoff);
-		if (gso_partial)
+		if (gso_partial && skb_is_gso(skb))
 			payload_len = skb_shinfo(skb)->gso_size +
 				      SKB_GSO_CB(skb)->data_offset +
 				      skb->head - (unsigned char *)(ipv6h + 1);
-- 
2.13.6


From c0f5e56ae9264471aa1c92ed287c0332e9896e22 Mon Sep 17 00:00:00 2001
From: Steffen Klassert <steffen.klassert@secunet.com>
Date: Mon, 9 Oct 2017 08:43:55 +0200
Subject: [PATCH 03/37] ipv4: Fix traffic triggered IPsec connections.

[ Upstream commit 6c0e7284d89995877740d8a26c3e99a937312a3c ]

A recent patch removed the dst_free() on the allocated
dst_entry in ipv4_blackhole_route(). The dst_free() marked the
dst_entry as dead and added it to the gc list. I.e. it was setup
for a one time usage. As a result we may now have a blackhole
route cached at a socket on some IPsec scenarios. This makes the
connection unusable.

Fix this by marking the dst_entry directly at allocation time
as 'dead', so it is used only once.

Fixes: b838d5e1c5b6 ("ipv4: mark DST_NOGC and remove the operation of dst_free()")
Reported-by: Tobias Brunner <tobias@strongswan.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index c5aa25be7108..72afa4cfb022 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2507,7 +2507,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
 	struct rtable *ort = (struct rtable *) dst_orig;
 	struct rtable *rt;
 
-	rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, DST_OBSOLETE_NONE, 0);
+	rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, DST_OBSOLETE_DEAD, 0);
 	if (rt) {
 		struct dst_entry *new = &rt->dst;
 
-- 
2.13.6


From c7bdff028a13ff43a68c9616e1983d8391f29baa Mon Sep 17 00:00:00 2001
From: Steffen Klassert <steffen.klassert@secunet.com>
Date: Mon, 9 Oct 2017 08:39:43 +0200
Subject: [PATCH 04/37] ipv6: Fix traffic triggered IPsec connections.

[ Upstream commit 62cf27e52b8c9a39066172ca6b6134cb5eaa9450 ]

A recent patch removed the dst_free() on the allocated
dst_entry in ipv6_blackhole_route(). The dst_free() marked
the dst_entry as dead and added it to the gc list. I.e. it
was setup for a one time usage. As a result we may now have
a blackhole route cached at a socket on some IPsec scenarios.
This makes the connection unusable.

Fix this by marking the dst_entry directly at allocation time
as 'dead', so it is used only once.

Fixes: 587fea741134 ("ipv6: mark DST_NOGC and remove the operation of dst_free()")
Reported-by: Tobias Brunner <tobias@strongswan.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 2d0e7798c793..44eebe738c09 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1251,7 +1251,7 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
 	struct dst_entry *new = NULL;
 
 	rt = dst_alloc(&ip6_dst_blackhole_ops, loopback_dev, 1,
-		       DST_OBSOLETE_NONE, 0);
+		       DST_OBSOLETE_DEAD, 0);
 	if (rt) {
 		rt6_info_init(rt);
 
-- 
2.13.6


From 1b34ddefd00bb203e0155d1486525d9f91a7b808 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Mon, 9 Oct 2017 14:14:51 +0200
Subject: [PATCH 05/37] netlink: do not set cb_running if dump's start() errs

[ Upstream commit 41c87425a1ac9b633e0fcc78eb1f19640c8fb5a0 ]

It turns out that multiple places can call netlink_dump(), which means
it's still possible to dereference partially initialized values in
dump() that were the result of a faulty returned start().

This fixes the issue by calling start() _before_ setting cb_running to
true, so that there's no chance at all of hitting the dump() function
through any indirect paths.

It also moves the call to start() to be when the mutex is held. This has
the nice side effect of serializing invocations to start(), which is
likely desirable anyway. It also prevents any possible other races that
might come out of this logic.

In testing this with several different pieces of tricky code to trigger
these issues, this commit fixes all avenues that I'm aware of.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
Reviewed-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 7e794ad50cb0..56527e37ffdd 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2258,16 +2258,17 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 	cb->min_dump_alloc = control->min_dump_alloc;
 	cb->skb = skb;
 
+	if (cb->start) {
+		ret = cb->start(cb);
+		if (ret)
+			goto error_unlock;
+	}
+
 	nlk->cb_running = true;
 
 	mutex_unlock(nlk->cb_mutex);
 
-	ret = 0;
-	if (cb->start)
-		ret = cb->start(cb);
-
-	if (!ret)
-		ret = netlink_dump(sk);
+	ret = netlink_dump(sk);
 
 	sock_put(sk);
 
-- 
2.13.6


From 77bb2fe0c423ccaef3cbea8cf113b4d0d5339198 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 10 Oct 2017 19:12:33 -0700
Subject: [PATCH 06/37] net: call cgroup_sk_alloc() earlier in sk_clone_lock()

[ Upstream commit c0576e3975084d4699b7bfef578613fb8e1144f6 ]

If for some reason, the newly allocated child need to be freed,
we will call cgroup_put() (via sk_free_unlock_clone()) while the
corresponding cgroup_get() was not yet done, and we will free memory
too soon.

Fixes: d979a39d7242 ("cgroup: duplicate cgroup reference when cloning sockets")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index 0967da925022..e48424ddbc6b 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1674,6 +1674,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		newsk->sk_userlocks	= sk->sk_userlocks & ~SOCK_BINDPORT_LOCK;
 
 		sock_reset_flag(newsk, SOCK_DONE);
+		cgroup_sk_alloc(&newsk->sk_cgrp_data);
 
 		rcu_read_lock();
 		filter = rcu_dereference(sk->sk_filter);
@@ -1706,8 +1707,6 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		atomic64_set(&newsk->sk_cookie, 0);
 
 		mem_cgroup_sk_alloc(newsk);
-		cgroup_sk_alloc(&newsk->sk_cgrp_data);
-
 		/*
 		 * Before updating sk_refcnt, we must commit prior changes to memory
 		 * (Documentation/RCU/rculist_nulls.txt for details)
-- 
2.13.6


From a2d4c80d7e748507b42a52701ec1dee412148e76 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 10 Oct 2017 17:07:12 +0200
Subject: [PATCH 07/37] macsec: fix memory leaks when skb_to_sgvec fails

[ Upstream commit 5aba2ba5030b66a6f8c93049b718556f9aacd7c6 ]

Fixes: cda7ea690350 ("macsec: check return value of skb_to_sgvec always")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macsec.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 98e4deaa3a6a..5ab1b8849c30 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -742,6 +742,7 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb,
 	sg_init_table(sg, ret);
 	ret = skb_to_sgvec(skb, sg, 0, skb->len);
 	if (unlikely(ret < 0)) {
+		aead_request_free(req);
 		macsec_txsa_put(tx_sa);
 		kfree_skb(skb);
 		return ERR_PTR(ret);
@@ -954,6 +955,7 @@ static struct sk_buff *macsec_decrypt(struct sk_buff *skb,
 	sg_init_table(sg, ret);
 	ret = skb_to_sgvec(skb, sg, 0, skb->len);
 	if (unlikely(ret < 0)) {
+		aead_request_free(req);
 		kfree_skb(skb);
 		return ERR_PTR(ret);
 	}
-- 
2.13.6


From 92a1c5b7ce4bb18c8e353c1ce7b4d301a99d9af4 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Fri, 13 Oct 2017 19:22:35 +0200
Subject: [PATCH 08/37] l2tp: check ps->sock before running
 pppol2tp_session_ioctl()

[ Upstream commit 5903f594935a3841137c86b9d5b75143a5b7121c ]

When pppol2tp_session_ioctl() is called by pppol2tp_tunnel_ioctl(),
the session may be unconnected. That is, it was created by
pppol2tp_session_create() and hasn't been connected with
pppol2tp_connect(). In this case, ps->sock is NULL, so we need to check
for this case in order to avoid dereferencing a NULL pointer.

Fixes: 309795f4bec2 ("l2tp: Add netlink control API for L2TP")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ppp.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index f0edb7209079..e8ec4f3e54fb 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -993,6 +993,9 @@ static int pppol2tp_session_ioctl(struct l2tp_session *session,
 		 session->name, cmd, arg);
 
 	sk = ps->sock;
+	if (!sk)
+		return -EBADR;
+
 	sock_hold(sk);
 
 	switch (cmd) {
-- 
2.13.6


From f599b54dc09892d520e95a59aa9baa616a6e743c Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Fri, 13 Oct 2017 11:58:53 -0700
Subject: [PATCH 09/37] tun: call dev_get_valid_name() before
 register_netdevice()

[ Upstream commit 0ad646c81b2182f7fa67ec0c8c825e0ee165696d ]

register_netdevice() could fail early when we have an invalid
dev name, in which case ->ndo_uninit() is not called. For tun
device, this is a problem because a timer etc. are already
initialized and it expects ->ndo_uninit() to clean them up.

We could move these initializations into a ->ndo_init() so
that register_netdevice() knows better, however this is still
complicated due to the logic in tun_detach().

Therefore, I choose to just call dev_get_valid_name() before
register_netdevice(), which is quicker and much easier to audit.
And for this specific case, it is already enough.

Fixes: 96442e42429e ("tuntap: choose the txq based on rxq")
Reported-by: Dmitry Alexeev <avekceeb@gmail.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c         | 3 +++
 include/linux/netdevice.h | 3 +++
 net/core/dev.c            | 6 +++---
 3 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index cb1f7747adad..9e7b4e7d3f97 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1813,6 +1813,9 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 
 		if (!dev)
 			return -ENOMEM;
+		err = dev_get_valid_name(net, dev, name);
+		if (err)
+			goto err_free_dev;
 
 		dev_net_set(dev, net);
 		dev->rtnl_link_ops = &tun_link_ops;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index c99ba7914c0a..a6d3c8b6cb93 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3702,6 +3702,9 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 				    unsigned char name_assign_type,
 				    void (*setup)(struct net_device *),
 				    unsigned int txqs, unsigned int rxqs);
+int dev_get_valid_name(struct net *net, struct net_device *dev,
+		       const char *name);
+
 #define alloc_netdev(sizeof_priv, name, name_assign_type, setup) \
 	alloc_netdev_mqs(sizeof_priv, name, name_assign_type, setup, 1, 1)
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 6fa30a4c60ef..4f9ec923d21b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1146,9 +1146,8 @@ static int dev_alloc_name_ns(struct net *net,
 	return ret;
 }
 
-static int dev_get_valid_name(struct net *net,
-			      struct net_device *dev,
-			      const char *name)
+int dev_get_valid_name(struct net *net, struct net_device *dev,
+		       const char *name)
 {
 	BUG_ON(!net);
 
@@ -1164,6 +1163,7 @@ static int dev_get_valid_name(struct net *net,
 
 	return 0;
 }
+EXPORT_SYMBOL(dev_get_valid_name);
 
 /**
  *	dev_change_name - change name of a device
-- 
2.13.6


From 5395e3525c2e9d87ed9771a91955e9ab99fcc1a1 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 16 Oct 2017 17:09:53 +0200
Subject: [PATCH 10/37] netlink: fix netlink_ack() extack race

[ Upstream commit 48044eb490be71c203e14dd89e8bae87209eab52 ]

It seems that it's possible to toggle NETLINK_F_EXT_ACK
through setsockopt() while another thread/CPU is building
a message inside netlink_ack(), which could then trigger
the WARN_ON()s I added since if it goes from being turned
off to being turned on between allocating and filling the
message, the skb could end up being too small.

Avoid this whole situation by storing the value of this
flag in a separate variable and using that throughout the
function instead.

Fixes: 2d4bc93368f5 ("netlink: extended ACK reporting")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 56527e37ffdd..09c8dbbd2d70 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2299,6 +2299,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err,
 	size_t tlvlen = 0;
 	struct netlink_sock *nlk = nlk_sk(NETLINK_CB(in_skb).sk);
 	unsigned int flags = 0;
+	bool nlk_has_extack = nlk->flags & NETLINK_F_EXT_ACK;
 
 	/* Error messages get the original request appened, unless the user
 	 * requests to cap the error message, and get extra error data if
@@ -2309,7 +2310,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err,
 			payload += nlmsg_len(nlh);
 		else
 			flags |= NLM_F_CAPPED;
-		if (nlk->flags & NETLINK_F_EXT_ACK && extack) {
+		if (nlk_has_extack && extack) {
 			if (extack->_msg)
 				tlvlen += nla_total_size(strlen(extack->_msg) + 1);
 			if (extack->bad_attr)
@@ -2318,8 +2319,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err,
 	} else {
 		flags |= NLM_F_CAPPED;
 
-		if (nlk->flags & NETLINK_F_EXT_ACK &&
-		    extack && extack->cookie_len)
+		if (nlk_has_extack && extack && extack->cookie_len)
 			tlvlen += nla_total_size(extack->cookie_len);
 	}
 
@@ -2347,7 +2347,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err,
 	errmsg->error = err;
 	memcpy(&errmsg->msg, nlh, payload > sizeof(*errmsg) ? nlh->nlmsg_len : sizeof(*nlh));
 
-	if (nlk->flags & NETLINK_F_EXT_ACK && extack) {
+	if (nlk_has_extack && extack) {
 		if (err) {
 			if (extack->_msg)
 				WARN_ON(nla_put_string(skb, NLMSGERR_ATTR_MSG,
-- 
2.13.6


From 07ae98322cdb9942abaa6e684de315bb4e0b53bf Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 18 Oct 2017 21:37:49 +0800
Subject: [PATCH 11/37] sctp: add the missing sock_owned_by_user check in
 sctp_icmp_redirect

[ Upstream commit 1cc276cec9ec574d41cf47dfc0f51406b6f26ab4 ]

Now sctp processes icmp redirect packet in sctp_icmp_redirect where
it calls sctp_transport_dst_check in which tp->dst can be released.

The problem is before calling sctp_transport_dst_check, it doesn't
check sock_owned_by_user, which means tp->dst could be freed while
a process is accessing it with owning the socket.

An use-after-free issue could be triggered by this.

This patch is to fix it by checking sock_owned_by_user before calling
sctp_transport_dst_check in sctp_icmp_redirect, so that it would not
release tp->dst if users still hold sock lock.

Besides, the same issue fixed in commit 45caeaa5ac0b ("dccp/tcp: fix
routing redirect race") on sctp also needs this check.

Fixes: 55be7a9c6074 ("ipv4: Add redirect support to all protocol icmp error handlers")
Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/input.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sctp/input.c b/net/sctp/input.c
index 41eb2ec10460..1678d9ea7740 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -421,7 +421,7 @@ void sctp_icmp_redirect(struct sock *sk, struct sctp_transport *t,
 {
 	struct dst_entry *dst;
 
-	if (!t)
+	if (sock_owned_by_user(sk) || !t)
 		return;
 	dst = sctp_transport_dst_check(t);
 	if (dst)
-- 
2.13.6


From 8156b79dcd9e582956d3889da20a9558919cb409 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 20 Oct 2017 09:04:13 -0700
Subject: [PATCH 12/37] tcp/dccp: fix ireq->opt races

[ Upstream commit c92e8c02fe664155ac4234516e32544bec0f113d ]

syzkaller found another bug in DCCP/TCP stacks [1]

For the reasons explained in commit ce1050089c96 ("tcp/dccp: fix
ireq->pktopts race"), we need to make sure we do not access
ireq->opt unless we own the request sock.

Note the opt field is renamed to ireq_opt to ease grep games.

[1]
BUG: KASAN: use-after-free in ip_queue_xmit+0x1687/0x18e0 net/ipv4/ip_output.c:474
Read of size 1 at addr ffff8801c951039c by task syz-executor5/3295

CPU: 1 PID: 3295 Comm: syz-executor5 Not tainted 4.14.0-rc4+ #80
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:16 [inline]
 dump_stack+0x194/0x257 lib/dump_stack.c:52
 print_address_description+0x73/0x250 mm/kasan/report.c:252
 kasan_report_error mm/kasan/report.c:351 [inline]
 kasan_report+0x25b/0x340 mm/kasan/report.c:409
 __asan_report_load1_noabort+0x14/0x20 mm/kasan/report.c:427
 ip_queue_xmit+0x1687/0x18e0 net/ipv4/ip_output.c:474
 tcp_transmit_skb+0x1ab7/0x3840 net/ipv4/tcp_output.c:1135
 tcp_send_ack.part.37+0x3bb/0x650 net/ipv4/tcp_output.c:3587
 tcp_send_ack+0x49/0x60 net/ipv4/tcp_output.c:3557
 __tcp_ack_snd_check+0x2c6/0x4b0 net/ipv4/tcp_input.c:5072
 tcp_ack_snd_check net/ipv4/tcp_input.c:5085 [inline]
 tcp_rcv_state_process+0x2eff/0x4850 net/ipv4/tcp_input.c:6071
 tcp_child_process+0x342/0x990 net/ipv4/tcp_minisocks.c:816
 tcp_v4_rcv+0x1827/0x2f80 net/ipv4/tcp_ipv4.c:1682
 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216
 NF_HOOK include/linux/netfilter.h:249 [inline]
 ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257
 dst_input include/net/dst.h:464 [inline]
 ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397
 NF_HOOK include/linux/netfilter.h:249 [inline]
 ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493
 __netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476
 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514
 netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587
 netif_receive_skb+0xae/0x390 net/core/dev.c:4611
 tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372
 tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766
 tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792
 call_write_iter include/linux/fs.h:1770 [inline]
 new_sync_write fs/read_write.c:468 [inline]
 __vfs_write+0x68a/0x970 fs/read_write.c:481
 vfs_write+0x18f/0x510 fs/read_write.c:543
 SYSC_write fs/read_write.c:588 [inline]
 SyS_write+0xef/0x220 fs/read_write.c:580
 entry_SYSCALL_64_fastpath+0x1f/0xbe
RIP: 0033:0x40c341
RSP: 002b:00007f469523ec10 EFLAGS: 00000293 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 0000000000718000 RCX: 000000000040c341
RDX: 0000000000000037 RSI: 0000000020004000 RDI: 0000000000000015
RBP: 0000000000000086 R08: 0000000000000000 R09: 0000000000000000
R10: 00000000000f4240 R11: 0000000000000293 R12: 00000000004b7fd1
R13: 00000000ffffffff R14: 0000000020000000 R15: 0000000000025000

Allocated by task 3295:
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
 save_stack+0x43/0xd0 mm/kasan/kasan.c:447
 set_track mm/kasan/kasan.c:459 [inline]
 kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:551
 __do_kmalloc mm/slab.c:3725 [inline]
 __kmalloc+0x162/0x760 mm/slab.c:3734
 kmalloc include/linux/slab.h:498 [inline]
 tcp_v4_save_options include/net/tcp.h:1962 [inline]
 tcp_v4_init_req+0x2d3/0x3e0 net/ipv4/tcp_ipv4.c:1271
 tcp_conn_request+0xf6d/0x3410 net/ipv4/tcp_input.c:6283
 tcp_v4_conn_request+0x157/0x210 net/ipv4/tcp_ipv4.c:1313
 tcp_rcv_state_process+0x8ea/0x4850 net/ipv4/tcp_input.c:5857
 tcp_v4_do_rcv+0x55c/0x7d0 net/ipv4/tcp_ipv4.c:1482
 tcp_v4_rcv+0x2d10/0x2f80 net/ipv4/tcp_ipv4.c:1711
 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216
 NF_HOOK include/linux/netfilter.h:249 [inline]
 ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257
 dst_input include/net/dst.h:464 [inline]
 ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397
 NF_HOOK include/linux/netfilter.h:249 [inline]
 ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493
 __netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476
 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514
 netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587
 netif_receive_skb+0xae/0x390 net/core/dev.c:4611
 tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372
 tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766
 tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792
 call_write_iter include/linux/fs.h:1770 [inline]
 new_sync_write fs/read_write.c:468 [inline]
 __vfs_write+0x68a/0x970 fs/read_write.c:481
 vfs_write+0x18f/0x510 fs/read_write.c:543
 SYSC_write fs/read_write.c:588 [inline]
 SyS_write+0xef/0x220 fs/read_write.c:580
 entry_SYSCALL_64_fastpath+0x1f/0xbe

Freed by task 3306:
 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
 save_stack+0x43/0xd0 mm/kasan/kasan.c:447
 set_track mm/kasan/kasan.c:459 [inline]
 kasan_slab_free+0x71/0xc0 mm/kasan/kasan.c:524
 __cache_free mm/slab.c:3503 [inline]
 kfree+0xca/0x250 mm/slab.c:3820
 inet_sock_destruct+0x59d/0x950 net/ipv4/af_inet.c:157
 __sk_destruct+0xfd/0x910 net/core/sock.c:1560
 sk_destruct+0x47/0x80 net/core/sock.c:1595
 __sk_free+0x57/0x230 net/core/sock.c:1603
 sk_free+0x2a/0x40 net/core/sock.c:1614
 sock_put include/net/sock.h:1652 [inline]
 inet_csk_complete_hashdance+0xd5/0xf0 net/ipv4/inet_connection_sock.c:959
 tcp_check_req+0xf4d/0x1620 net/ipv4/tcp_minisocks.c:765
 tcp_v4_rcv+0x17f6/0x2f80 net/ipv4/tcp_ipv4.c:1675
 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216
 NF_HOOK include/linux/netfilter.h:249 [inline]
 ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257
 dst_input include/net/dst.h:464 [inline]
 ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397
 NF_HOOK include/linux/netfilter.h:249 [inline]
 ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493
 __netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476
 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514
 netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587
 netif_receive_skb+0xae/0x390 net/core/dev.c:4611
 tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372
 tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766
 tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792
 call_write_iter include/linux/fs.h:1770 [inline]
 new_sync_write fs/read_write.c:468 [inline]
 __vfs_write+0x68a/0x970 fs/read_write.c:481
 vfs_write+0x18f/0x510 fs/read_write.c:543
 SYSC_write fs/read_write.c:588 [inline]
 SyS_write+0xef/0x220 fs/read_write.c:580
 entry_SYSCALL_64_fastpath+0x1f/0xbe

Fixes: e994b2f0fb92 ("tcp: do not lock listener to process SYN packets")
Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_sock.h         |  2 +-
 net/dccp/ipv4.c                 | 13 ++++++++-----
 net/ipv4/cipso_ipv4.c           | 24 +++++++-----------------
 net/ipv4/inet_connection_sock.c |  8 +++-----
 net/ipv4/syncookies.c           |  2 +-
 net/ipv4/tcp_input.c            |  2 +-
 net/ipv4/tcp_ipv4.c             | 21 ++++++++++++---------
 7 files changed, 33 insertions(+), 39 deletions(-)

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index aa95053dfc78..425752f768d2 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -96,7 +96,7 @@ struct inet_request_sock {
 	kmemcheck_bitfield_end(flags);
 	u32                     ir_mark;
 	union {
-		struct ip_options_rcu	*opt;
+		struct ip_options_rcu __rcu	*ireq_opt;
 #if IS_ENABLED(CONFIG_IPV6)
 		struct {
 			struct ipv6_txoptions	*ipv6_opt;
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 1b202f16531f..5877f4408fc6 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -414,8 +414,7 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk,
 	sk_daddr_set(newsk, ireq->ir_rmt_addr);
 	sk_rcv_saddr_set(newsk, ireq->ir_loc_addr);
 	newinet->inet_saddr	= ireq->ir_loc_addr;
-	newinet->inet_opt	= ireq->opt;
-	ireq->opt	   = NULL;
+	RCU_INIT_POINTER(newinet->inet_opt, rcu_dereference(ireq->ireq_opt));
 	newinet->mc_index  = inet_iif(skb);
 	newinet->mc_ttl	   = ip_hdr(skb)->ttl;
 	newinet->inet_id   = jiffies;
@@ -430,7 +429,10 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk,
 	if (__inet_inherit_port(sk, newsk) < 0)
 		goto put_and_exit;
 	*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
-
+	if (*own_req)
+		ireq->ireq_opt = NULL;
+	else
+		newinet->inet_opt = NULL;
 	return newsk;
 
 exit_overflow:
@@ -441,6 +443,7 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk,
 	__NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENDROPS);
 	return NULL;
 put_and_exit:
+	newinet->inet_opt = NULL;
 	inet_csk_prepare_forced_close(newsk);
 	dccp_done(newsk);
 	goto exit;
@@ -492,7 +495,7 @@ static int dccp_v4_send_response(const struct sock *sk, struct request_sock *req
 							      ireq->ir_rmt_addr);
 		err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
 					    ireq->ir_rmt_addr,
-					    ireq->opt);
+					    rcu_dereference(ireq->ireq_opt));
 		err = net_xmit_eval(err);
 	}
 
@@ -548,7 +551,7 @@ static void dccp_v4_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb)
 static void dccp_v4_reqsk_destructor(struct request_sock *req)
 {
 	dccp_feat_list_purge(&dccp_rsk(req)->dreq_featneg);
-	kfree(inet_rsk(req)->opt);
+	kfree(rcu_dereference_protected(inet_rsk(req)->ireq_opt, 1));
 }
 
 void dccp_syn_ack_timeout(const struct request_sock *req)
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 2ae8f54cb321..82178cc69c96 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -1951,7 +1951,7 @@ int cipso_v4_req_setattr(struct request_sock *req,
 	buf = NULL;
 
 	req_inet = inet_rsk(req);
-	opt = xchg(&req_inet->opt, opt);
+	opt = xchg((__force struct ip_options_rcu **)&req_inet->ireq_opt, opt);
 	if (opt)
 		kfree_rcu(opt, rcu);
 
@@ -1973,11 +1973,13 @@ int cipso_v4_req_setattr(struct request_sock *req,
  * values on failure.
  *
  */
-static int cipso_v4_delopt(struct ip_options_rcu **opt_ptr)
+static int cipso_v4_delopt(struct ip_options_rcu __rcu **opt_ptr)
 {
+	struct ip_options_rcu *opt = rcu_dereference_protected(*opt_ptr, 1);
 	int hdr_delta = 0;
-	struct ip_options_rcu *opt = *opt_ptr;
 
+	if (!opt || opt->opt.cipso == 0)
+		return 0;
 	if (opt->opt.srr || opt->opt.rr || opt->opt.ts || opt->opt.router_alert) {
 		u8 cipso_len;
 		u8 cipso_off;
@@ -2039,14 +2041,10 @@ static int cipso_v4_delopt(struct ip_options_rcu **opt_ptr)
  */
 void cipso_v4_sock_delattr(struct sock *sk)
 {
-	int hdr_delta;
-	struct ip_options_rcu *opt;
 	struct inet_sock *sk_inet;
+	int hdr_delta;
 
 	sk_inet = inet_sk(sk);
-	opt = rcu_dereference_protected(sk_inet->inet_opt, 1);
-	if (!opt || opt->opt.cipso == 0)
-		return;
 
 	hdr_delta = cipso_v4_delopt(&sk_inet->inet_opt);
 	if (sk_inet->is_icsk && hdr_delta > 0) {
@@ -2066,15 +2064,7 @@ void cipso_v4_sock_delattr(struct sock *sk)
  */
 void cipso_v4_req_delattr(struct request_sock *req)
 {
-	struct ip_options_rcu *opt;
-	struct inet_request_sock *req_inet;
-
-	req_inet = inet_rsk(req);
-	opt = req_inet->opt;
-	if (!opt || opt->opt.cipso == 0)
-		return;
-
-	cipso_v4_delopt(&req_inet->opt);
+	cipso_v4_delopt(&inet_rsk(req)->ireq_opt);
 }
 
 /**
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 4089c013cb03..ce4709b2818d 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -537,9 +537,10 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk,
 {
 	const struct inet_request_sock *ireq = inet_rsk(req);
 	struct net *net = read_pnet(&ireq->ireq_net);
-	struct ip_options_rcu *opt = ireq->opt;
+	struct ip_options_rcu *opt;
 	struct rtable *rt;
 
+	opt = rcu_dereference(ireq->ireq_opt);
 	flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
 			   sk->sk_protocol, inet_sk_flowi_flags(sk),
@@ -573,10 +574,9 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
 	struct flowi4 *fl4;
 	struct rtable *rt;
 
+	opt = rcu_dereference(ireq->ireq_opt);
 	fl4 = &newinet->cork.fl.u.ip4;
 
-	rcu_read_lock();
-	opt = rcu_dereference(newinet->inet_opt);
 	flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
 			   sk->sk_protocol, inet_sk_flowi_flags(sk),
@@ -589,13 +589,11 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
 		goto no_route;
 	if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway)
 		goto route_err;
-	rcu_read_unlock();
 	return &rt->dst;
 
 route_err:
 	ip_rt_put(rt);
 no_route:
-	rcu_read_unlock();
 	__IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
 	return NULL;
 }
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 03ad8778c395..0f914fda5bf3 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -355,7 +355,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	/* We throwed the options of the initial SYN away, so we hope
 	 * the ACK carries the same options again (see RFC1122 4.2.3.8)
 	 */
-	ireq->opt = tcp_v4_save_options(skb);
+	RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(skb));
 
 	if (security_inet_conn_request(sk, skb, req)) {
 		reqsk_free(req);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index bab7f0493098..e92e5dbcb3d6 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6235,7 +6235,7 @@ struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops,
 		struct inet_request_sock *ireq = inet_rsk(req);
 
 		kmemcheck_annotate_bitfield(ireq, flags);
-		ireq->opt = NULL;
+		ireq->ireq_opt = NULL;
 #if IS_ENABLED(CONFIG_IPV6)
 		ireq->pktopts = NULL;
 #endif
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index b1441bc8192f..d7ed8dbde85e 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -878,7 +878,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
 
 		err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
 					    ireq->ir_rmt_addr,
-					    ireq->opt);
+					    rcu_dereference(ireq->ireq_opt));
 		err = net_xmit_eval(err);
 	}
 
@@ -890,7 +890,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
  */
 static void tcp_v4_reqsk_destructor(struct request_sock *req)
 {
-	kfree(inet_rsk(req)->opt);
+	kfree(rcu_dereference_protected(inet_rsk(req)->ireq_opt, 1));
 }
 
 #ifdef CONFIG_TCP_MD5SIG
@@ -1269,7 +1269,7 @@ static void tcp_v4_init_req(struct request_sock *req,
 
 	sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr);
 	sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr);
-	ireq->opt = tcp_v4_save_options(skb);
+	RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(skb));
 }
 
 static struct dst_entry *tcp_v4_route_req(const struct sock *sk,
@@ -1356,10 +1356,9 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 	sk_daddr_set(newsk, ireq->ir_rmt_addr);
 	sk_rcv_saddr_set(newsk, ireq->ir_loc_addr);
 	newsk->sk_bound_dev_if = ireq->ir_iif;
-	newinet->inet_saddr	      = ireq->ir_loc_addr;
-	inet_opt	      = ireq->opt;
-	rcu_assign_pointer(newinet->inet_opt, inet_opt);
-	ireq->opt	      = NULL;
+	newinet->inet_saddr   = ireq->ir_loc_addr;
+	inet_opt	      = rcu_dereference(ireq->ireq_opt);
+	RCU_INIT_POINTER(newinet->inet_opt, inet_opt);
 	newinet->mc_index     = inet_iif(skb);
 	newinet->mc_ttl	      = ip_hdr(skb)->ttl;
 	newinet->rcv_tos      = ip_hdr(skb)->tos;
@@ -1404,9 +1403,12 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 	if (__inet_inherit_port(sk, newsk) < 0)
 		goto put_and_exit;
 	*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
-	if (*own_req)
+	if (likely(*own_req)) {
 		tcp_move_syn(newtp, req);
-
+		ireq->ireq_opt = NULL;
+	} else {
+		newinet->inet_opt = NULL;
+	}
 	return newsk;
 
 exit_overflow:
@@ -1417,6 +1419,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 	tcp_listendrop(sk);
 	return NULL;
 put_and_exit:
+	newinet->inet_opt = NULL;
 	inet_csk_prepare_forced_close(newsk);
 	tcp_done(newsk);
 	goto exit;
-- 
2.13.6


From 3b382e3acaa73d566efcd1ba24acf3979870d49a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 18 Oct 2017 16:14:52 -0700
Subject: [PATCH 13/37] packet: avoid panic in packet_getsockopt()

[ Upstream commit 509c7a1ecc8601f94ffba8a00889fefb239c00c6 ]

syzkaller got crashes in packet_getsockopt() processing
PACKET_ROLLOVER_STATS command while another thread was managing
to change po->rollover

Using RCU will fix this bug. We might later add proper RCU annotations
for sparse sake.

In v2: I replaced kfree(rollover) in fanout_add() to kfree_rcu()
variant, as spotted by John.

Fixes: a9b6391814d5 ("packet: rollover statistics")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Cc: John Sperbeck <jsperbeck@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 24 ++++++++++++++++--------
 1 file changed, 16 insertions(+), 8 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 29d7b7e5b128..b0c8fee3d53d 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1771,7 +1771,7 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 
 out:
 	if (err && rollover) {
-		kfree(rollover);
+		kfree_rcu(rollover, rcu);
 		po->rollover = NULL;
 	}
 	mutex_unlock(&fanout_mutex);
@@ -1798,8 +1798,10 @@ static struct packet_fanout *fanout_release(struct sock *sk)
 		else
 			f = NULL;
 
-		if (po->rollover)
+		if (po->rollover) {
 			kfree_rcu(po->rollover, rcu);
+			po->rollover = NULL;
+		}
 	}
 	mutex_unlock(&fanout_mutex);
 
@@ -3853,6 +3855,7 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
 	void *data = &val;
 	union tpacket_stats_u st;
 	struct tpacket_rollover_stats rstats;
+	struct packet_rollover *rollover;
 
 	if (level != SOL_PACKET)
 		return -ENOPROTOOPT;
@@ -3931,13 +3934,18 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
 		       0);
 		break;
 	case PACKET_ROLLOVER_STATS:
-		if (!po->rollover)
+		rcu_read_lock();
+		rollover = rcu_dereference(po->rollover);
+		if (rollover) {
+			rstats.tp_all = atomic_long_read(&rollover->num);
+			rstats.tp_huge = atomic_long_read(&rollover->num_huge);
+			rstats.tp_failed = atomic_long_read(&rollover->num_failed);
+			data = &rstats;
+			lv = sizeof(rstats);
+		}
+		rcu_read_unlock();
+		if (!rollover)
 			return -EINVAL;
-		rstats.tp_all = atomic_long_read(&po->rollover->num);
-		rstats.tp_huge = atomic_long_read(&po->rollover->num_huge);
-		rstats.tp_failed = atomic_long_read(&po->rollover->num_failed);
-		data = &rstats;
-		lv = sizeof(rstats);
 		break;
 	case PACKET_TX_HAS_OFF:
 		val = po->tp_tx_has_off;
-- 
2.13.6


From 520d15b4fa9082e1e0bd4ffee2cb5950f5c4ae39 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Thu, 19 Oct 2017 13:31:28 +0200
Subject: [PATCH 14/37] geneve: Fix function matching VNI and tunnel ID on
 big-endian

[ Upstream commit 772e97b57a4aa00170ad505a40ffad31d987ce1d ]

On big-endian machines, functions converting between tunnel ID
and VNI use the three LSBs of tunnel ID storage to map VNI.

The comparison function eq_tun_id_and_vni(), on the other hand,
attempted to map the VNI from the three MSBs. Fix it by using
the same check implemented on LE, which maps VNI from the three
LSBs of tunnel ID.

Fixes: 2e0b26e10352 ("geneve: Optimize geneve device lookup.")
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Jakub Sitnicki <jkbs@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 2bbda71818ad..e0a7176e1d39 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -113,13 +113,7 @@ static void tunnel_id_to_vni(__be64 tun_id, __u8 *vni)
 
 static bool eq_tun_id_and_vni(u8 *tun_id, u8 *vni)
 {
-#ifdef __BIG_ENDIAN
-	return (vni[0] == tun_id[2]) &&
-	       (vni[1] == tun_id[1]) &&
-	       (vni[2] == tun_id[0]);
-#else
 	return !memcmp(vni, &tun_id[5], 3);
-#endif
 }
 
 static sa_family_t geneve_get_sk_family(struct geneve_sock *gs)
-- 
2.13.6


From 8198774a3dd75d200f61d22d62c6cc0637375efa Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Thu, 19 Oct 2017 20:17:32 +0300
Subject: [PATCH 15/37] net: bridge: fix returning of vlan range op errors

[ Upstream commit 66c54517540cedf5a22911c6b7f5c7d8b5d1e1be ]

When vlan tunnels were introduced, vlan range errors got silently
dropped and instead 0 was returned always. Restore the previous
behaviour and return errors to user-space.

Fixes: efa5356b0d97 ("bridge: per vlan dst_metadata netlink support")
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Acked-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_netlink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 3bc890716c89..de2152730809 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -573,7 +573,7 @@ static int br_process_vlan_info(struct net_bridge *br,
 		}
 		*vinfo_last = NULL;
 
-		return 0;
+		return err;
 	}
 
 	return br_vlan_info(br, p, cmd, vinfo_curr);
-- 
2.13.6


From 83ca417bac2793f5df771808db76aeea6b5b5e9f Mon Sep 17 00:00:00 2001
From: Craig Gallek <kraig@google.com>
Date: Thu, 19 Oct 2017 15:00:29 -0400
Subject: [PATCH 16/37] soreuseport: fix initialization race

[ Upstream commit 1b5f962e71bfad6284574655c406597535c3ea7a ]

Syzkaller stumbled upon a way to trigger
WARNING: CPU: 1 PID: 13881 at net/core/sock_reuseport.c:41
reuseport_alloc+0x306/0x3b0 net/core/sock_reuseport.c:39

There are two initialization paths for the sock_reuseport structure in a
socket: Through the udp/tcp bind paths of SO_REUSEPORT sockets or through
SO_ATTACH_REUSEPORT_[CE]BPF before bind.  The existing implementation
assumedthat the socket lock protected both of these paths when it actually
only protects the SO_ATTACH_REUSEPORT path.  Syzkaller triggered this
double allocation by running these paths concurrently.

This patch moves the check for double allocation into the reuseport_alloc
function which is protected by a global spin lock.

Fixes: e32ea7e74727 ("soreuseport: fast reuseport UDP socket selection")
Fixes: c125e80b8868 ("soreuseport: fast reuseport TCP socket selection")
Signed-off-by: Craig Gallek <kraig@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock_reuseport.c  | 12 +++++++++---
 net/ipv4/inet_hashtables.c |  5 +----
 net/ipv4/udp.c             |  5 +----
 3 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index eed1ebf7f29d..b1e0dbea1e8c 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -36,9 +36,14 @@ int reuseport_alloc(struct sock *sk)
 	 * soft irq of receive path or setsockopt from process context
 	 */
 	spin_lock_bh(&reuseport_lock);
-	WARN_ONCE(rcu_dereference_protected(sk->sk_reuseport_cb,
-					    lockdep_is_held(&reuseport_lock)),
-		  "multiple allocations for the same socket");
+
+	/* Allocation attempts can occur concurrently via the setsockopt path
+	 * and the bind/hash path.  Nothing to do when we lose the race.
+	 */
+	if (rcu_dereference_protected(sk->sk_reuseport_cb,
+				      lockdep_is_held(&reuseport_lock)))
+		goto out;
+
 	reuse = __reuseport_alloc(INIT_SOCKS);
 	if (!reuse) {
 		spin_unlock_bh(&reuseport_lock);
@@ -49,6 +54,7 @@ int reuseport_alloc(struct sock *sk)
 	reuse->num_socks = 1;
 	rcu_assign_pointer(sk->sk_reuseport_cb, reuse);
 
+out:
 	spin_unlock_bh(&reuseport_lock);
 
 	return 0;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 2e3389d614d1..3eeecee0b21f 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -449,10 +449,7 @@ static int inet_reuseport_add_sock(struct sock *sk,
 			return reuseport_add_sock(sk, sk2);
 	}
 
-	/* Initial allocation may have already happened via setsockopt */
-	if (!rcu_access_pointer(sk->sk_reuseport_cb))
-		return reuseport_alloc(sk);
-	return 0;
+	return reuseport_alloc(sk);
 }
 
 int __inet_hash(struct sock *sk, struct sock *osk)
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 84861d71face..f9e1bcfb6e2d 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -231,10 +231,7 @@ static int udp_reuseport_add_sock(struct sock *sk, struct udp_hslot *hslot)
 		}
 	}
 
-	/* Initial allocation may have already happened via setsockopt */
-	if (!rcu_access_pointer(sk->sk_reuseport_cb))
-		return reuseport_alloc(sk);
-	return 0;
+	return reuseport_alloc(sk);
 }
 
 /**
-- 
2.13.6


From dcf4478841b3e86b32c82572fcecde2e9ed23eb8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 21 Oct 2017 12:26:23 -0700
Subject: [PATCH 17/37] ipv6: flowlabel: do not leave opt->tot_len with garbage

[ Upstream commit 864e2a1f8aac05effac6063ce316b480facb46ff ]

When syzkaller team brought us a C repro for the crash [1] that
had been reported many times in the past, I finally could find
the root cause.

If FlowLabel info is merged by fl6_merge_options(), we leave
part of the opt_space storage provided by udp/raw/l2tp with random value
in opt_space.tot_len, unless a control message was provided at sendmsg()
time.

Then ip6_setup_cork() would use this random value to perform a kzalloc()
call. Undefined behavior and crashes.

Fix is to properly set tot_len in fl6_merge_options()

At the same time, we can also avoid consuming memory and cpu cycles
to clear it, if every option is copied via a kmemdup(). This is the
change in ip6_setup_cork().

[1]
kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] SMP KASAN
Dumping ftrace buffer:
   (ftrace buffer empty)
Modules linked in:
CPU: 0 PID: 6613 Comm: syz-executor0 Not tainted 4.14.0-rc4+ #127
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
task: ffff8801cb64a100 task.stack: ffff8801cc350000
RIP: 0010:ip6_setup_cork+0x274/0x15c0 net/ipv6/ip6_output.c:1168
RSP: 0018:ffff8801cc357550 EFLAGS: 00010203
RAX: dffffc0000000000 RBX: ffff8801cc357748 RCX: 0000000000000010
RDX: 0000000000000002 RSI: ffffffff842bd1d9 RDI: 0000000000000014
RBP: ffff8801cc357620 R08: ffff8801cb17f380 R09: ffff8801cc357b10
R10: ffff8801cb64a100 R11: 0000000000000000 R12: ffff8801cc357ab0
R13: ffff8801cc357b10 R14: 0000000000000000 R15: ffff8801c3bbf0c0
FS:  00007f9c5c459700(0000) GS:ffff8801db200000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000020324000 CR3: 00000001d1cf2000 CR4: 00000000001406f0
DR0: 0000000020001010 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000600
Call Trace:
 ip6_make_skb+0x282/0x530 net/ipv6/ip6_output.c:1729
 udpv6_sendmsg+0x2769/0x3380 net/ipv6/udp.c:1340
 inet_sendmsg+0x11f/0x5e0 net/ipv4/af_inet.c:762
 sock_sendmsg_nosec net/socket.c:633 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:643
 SYSC_sendto+0x358/0x5a0 net/socket.c:1750
 SyS_sendto+0x40/0x50 net/socket.c:1718
 entry_SYSCALL_64_fastpath+0x1f/0xbe
RIP: 0033:0x4520a9
RSP: 002b:00007f9c5c458c08 EFLAGS: 00000216 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 0000000000718000 RCX: 00000000004520a9
RDX: 0000000000000001 RSI: 0000000020fd1000 RDI: 0000000000000016
RBP: 0000000000000086 R08: 0000000020e0afe4 R09: 000000000000001c
R10: 0000000000000000 R11: 0000000000000216 R12: 00000000004bb1ee
R13: 00000000ffffffff R14: 0000000000000016 R15: 0000000000000029
Code: e0 07 83 c0 03 38 d0 7c 08 84 d2 0f 85 ea 0f 00 00 48 8d 79 04 48 b8 00 00 00 00 00 fc ff df 45 8b 74 24 04 48 89 fa 48 c1 ea 03 <0f> b6 14 02 48 89 f8 83 e0 07 83 c0 03 38 d0 7c 08 84 d2 0f 85
RIP: ip6_setup_cork+0x274/0x15c0 net/ipv6/ip6_output.c:1168 RSP: ffff8801cc357550

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_flowlabel.c | 1 +
 net/ipv6/ip6_output.c    | 4 ++--
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 8081bafe441b..15535ee327c5 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -315,6 +315,7 @@ struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space,
 	}
 	opt_space->dst1opt = fopt->dst1opt;
 	opt_space->opt_flen = fopt->opt_flen;
+	opt_space->tot_len = fopt->tot_len;
 	return opt_space;
 }
 EXPORT_SYMBOL_GPL(fl6_merge_options);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 2dfe50d8d609..3ce9ab29bd37 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1224,11 +1224,11 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
 		if (WARN_ON(v6_cork->opt))
 			return -EINVAL;
 
-		v6_cork->opt = kzalloc(opt->tot_len, sk->sk_allocation);
+		v6_cork->opt = kzalloc(sizeof(*opt), sk->sk_allocation);
 		if (unlikely(!v6_cork->opt))
 			return -ENOBUFS;
 
-		v6_cork->opt->tot_len = opt->tot_len;
+		v6_cork->opt->tot_len = sizeof(*opt);
 		v6_cork->opt->opt_flen = opt->opt_flen;
 		v6_cork->opt->opt_nflen = opt->opt_nflen;
 
-- 
2.13.6


From 229ae06292d5eb63f56bbf66cc84e8802e9014f6 Mon Sep 17 00:00:00 2001
From: Laszlo Toth <laszlth@gmail.com>
Date: Mon, 23 Oct 2017 19:19:33 +0200
Subject: [PATCH 18/37] sctp: full support for ipv6 ip_nonlocal_bind &
 IP_FREEBIND

[ Upstream commit b71d21c274eff20a9db8158882b545b141b73ab8 ]

Commit 9b9742022888 ("sctp: support ipv6 nonlocal bind")
introduced support for the above options as v4 sctp did,
so patched sctp_v6_available().

In the v4 implementation it's enough, because
sctp_inet_bind_verify() just returns with sctp_v4_available().
However sctp_inet6_bind_verify() has an extra check before that
for link-local scope_id, which won't respect the above options.

Added the checks before calling ipv6_chk_addr(), but
not before the validation of scope_id.

before (w/ both options):
 ./v6test fe80::10 sctp
 bind failed, errno: 99 (Cannot assign requested address)
 ./v6test fe80::10 tcp
 bind success, errno: 0 (Success)

after (w/ both options):
 ./v6test fe80::10 sctp
 bind success, errno: 0 (Success)

Signed-off-by: Laszlo Toth <laszlth@gmail.com>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ipv6.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index a4b6ffb61495..1344e3a411ae 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -882,8 +882,10 @@ static int sctp_inet6_bind_verify(struct sctp_sock *opt, union sctp_addr *addr)
 			net = sock_net(&opt->inet.sk);
 			rcu_read_lock();
 			dev = dev_get_by_index_rcu(net, addr->v6.sin6_scope_id);
-			if (!dev ||
-			    !ipv6_chk_addr(net, &addr->v6.sin6_addr, dev, 0)) {
+			if (!dev || !(opt->inet.freebind ||
+				      net->ipv6.sysctl.ip_nonlocal_bind ||
+				      ipv6_chk_addr(net, &addr->v6.sin6_addr,
+						    dev, 0))) {
 				rcu_read_unlock();
 				return 0;
 			}
-- 
2.13.6


From aeaadddbf7f9ccf8c7880db01a9db10327c27732 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 22 Oct 2017 12:33:57 -0700
Subject: [PATCH 19/37] tcp/dccp: fix lockdep splat in inet_csk_route_req()

[ Upstream commit a6ca7abe53633d08eea1c6756cb49c9b2d4c90bf ]

This patch fixes the following lockdep splat in inet_csk_route_req()

  lockdep_rcu_suspicious
  inet_csk_route_req
  tcp_v4_send_synack
  tcp_rtx_synack
  inet_rtx_syn_ack
  tcp_fastopen_synack_time
  tcp_retransmit_timer
  tcp_write_timer_handler
  tcp_write_timer
  call_timer_fn

Thread running inet_csk_route_req() owns a reference on the request
socket, so we have the guarantee ireq->ireq_opt wont be changed or
freed.

lockdep can enforce this invariant for us.

Fixes: c92e8c02fe66 ("tcp/dccp: fix ireq->opt races")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/inet_connection_sock.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index ce4709b2818d..498323216fd0 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -540,7 +540,8 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk,
 	struct ip_options_rcu *opt;
 	struct rtable *rt;
 
-	opt = rcu_dereference(ireq->ireq_opt);
+	opt = rcu_dereference_protected(ireq->ireq_opt,
+					refcount_read(&req->rsk_refcnt) > 0);
 	flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
 			   sk->sk_protocol, inet_sk_flowi_flags(sk),
-- 
2.13.6


From 55f26cc446516df252464bd84466dc78e9a40cdb Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 24 Oct 2017 08:20:31 -0700
Subject: [PATCH 20/37] tcp/dccp: fix other lockdep splats accessing ireq_opt
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 06f877d613be3621604c2520ec0351d9fbdca15f ]

In my first attempt to fix the lockdep splat, I forgot we could
enter inet_csk_route_req() with a freshly allocated request socket,
for which refcount has not yet been elevated, due to complex
SLAB_TYPESAFE_BY_RCU rules.

We either are in rcu_read_lock() section _or_ we own a refcount on the
request.

Correct RCU verb to use here is rcu_dereference_check(), although it is
not possible to prove we actually own a reference on a shared
refcount :/

In v2, I added ireq_opt_deref() helper and use in three places, to fix other
possible splats.

[   49.844590]  lockdep_rcu_suspicious+0xea/0xf3
[   49.846487]  inet_csk_route_req+0x53/0x14d
[   49.848334]  tcp_v4_route_req+0xe/0x10
[   49.850174]  tcp_conn_request+0x31c/0x6a0
[   49.851992]  ? __lock_acquire+0x614/0x822
[   49.854015]  tcp_v4_conn_request+0x5a/0x79
[   49.855957]  ? tcp_v4_conn_request+0x5a/0x79
[   49.858052]  tcp_rcv_state_process+0x98/0xdcc
[   49.859990]  ? sk_filter_trim_cap+0x2f6/0x307
[   49.862085]  tcp_v4_do_rcv+0xfc/0x145
[   49.864055]  ? tcp_v4_do_rcv+0xfc/0x145
[   49.866173]  tcp_v4_rcv+0x5ab/0xaf9
[   49.868029]  ip_local_deliver_finish+0x1af/0x2e7
[   49.870064]  ip_local_deliver+0x1b2/0x1c5
[   49.871775]  ? inet_del_offload+0x45/0x45
[   49.873916]  ip_rcv_finish+0x3f7/0x471
[   49.875476]  ip_rcv+0x3f1/0x42f
[   49.876991]  ? ip_local_deliver_finish+0x2e7/0x2e7
[   49.878791]  __netif_receive_skb_core+0x6d3/0x950
[   49.880701]  ? process_backlog+0x7e/0x216
[   49.882589]  __netif_receive_skb+0x1d/0x5e
[   49.884122]  process_backlog+0x10c/0x216
[   49.885812]  net_rx_action+0x147/0x3df

Fixes: a6ca7abe53633 ("tcp/dccp: fix lockdep splat in inet_csk_route_req()")
Fixes: c92e8c02fe66 ("tcp/dccp: fix ireq->opt races")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: kernel test robot <fengguang.wu@intel.com>
Reported-by: Maciej Żenczykowski <maze@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_sock.h         | 6 ++++++
 net/dccp/ipv4.c                 | 2 +-
 net/ipv4/inet_connection_sock.c | 4 ++--
 net/ipv4/tcp_ipv4.c             | 2 +-
 4 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 425752f768d2..db8162dd8c0b 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -132,6 +132,12 @@ static inline int inet_request_bound_dev_if(const struct sock *sk,
 	return sk->sk_bound_dev_if;
 }
 
+static inline struct ip_options_rcu *ireq_opt_deref(const struct inet_request_sock *ireq)
+{
+	return rcu_dereference_check(ireq->ireq_opt,
+				     refcount_read(&ireq->req.rsk_refcnt) > 0);
+}
+
 struct inet_cork {
 	unsigned int		flags;
 	__be32			addr;
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 5877f4408fc6..bc70d96d762a 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -495,7 +495,7 @@ static int dccp_v4_send_response(const struct sock *sk, struct request_sock *req
 							      ireq->ir_rmt_addr);
 		err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
 					    ireq->ir_rmt_addr,
-					    rcu_dereference(ireq->ireq_opt));
+					    ireq_opt_deref(ireq));
 		err = net_xmit_eval(err);
 	}
 
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 498323216fd0..4438990cf65e 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -540,8 +540,8 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk,
 	struct ip_options_rcu *opt;
 	struct rtable *rt;
 
-	opt = rcu_dereference_protected(ireq->ireq_opt,
-					refcount_read(&req->rsk_refcnt) > 0);
+	opt = ireq_opt_deref(ireq);
+
 	flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
 			   sk->sk_protocol, inet_sk_flowi_flags(sk),
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index d7ed8dbde85e..78835f681538 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -878,7 +878,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
 
 		err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
 					    ireq->ir_rmt_addr,
-					    rcu_dereference(ireq->ireq_opt));
+					    ireq_opt_deref(ireq));
 		err = net_xmit_eval(err);
 	}
 
-- 
2.13.6


From bdcb5707d7b43737d27ddbe6c061010bccc06d22 Mon Sep 17 00:00:00 2001
From: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Date: Tue, 24 Oct 2017 16:37:19 -0400
Subject: [PATCH 21/37] net: dsa: check master device before put

[ Upstream commit 3eb8feeb1708c7dbfd2e97df92a2a407c116606e ]

In the case of pdata, the dsa_cpu_parse function calls dev_put() before
making sure it isn't NULL. Fix this.

Fixes: 71e0bbde0d88 ("net: dsa: Add support for platform data")
Signed-off-by: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/dsa2.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index 20bc9c56fca0..278b48d70bd9 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -496,14 +496,15 @@ static int dsa_cpu_parse(struct dsa_port *port, u32 index,
 		if (!ethernet)
 			return -EINVAL;
 		ethernet_dev = of_find_net_device_by_node(ethernet);
+		if (!ethernet_dev)
+			return -EPROBE_DEFER;
 	} else {
 		ethernet_dev = dsa_dev_to_net_device(ds->cd->netdev[index]);
+		if (!ethernet_dev)
+			return -EPROBE_DEFER;
 		dev_put(ethernet_dev);
 	}
 
-	if (!ethernet_dev)
-		return -EPROBE_DEFER;
-
 	if (!dst->cpu_dp) {
 		dst->cpu_dp = port;
 		dst->cpu_dp->netdev = ethernet_dev;
-- 
2.13.6


From b92352dd1b9309d8aee652ed61d0096a68c5bb46 Mon Sep 17 00:00:00 2001
From: Andrei Vagin <avagin@openvz.org>
Date: Wed, 25 Oct 2017 10:16:42 -0700
Subject: [PATCH 22/37] net/unix: don't show information about sockets from
 other namespaces

[ Upstream commit 0f5da659d8f1810f44de14acf2c80cd6499623a0 ]

socket_diag shows information only about sockets from a namespace where
a diag socket lives.

But if we request information about one unix socket, the kernel don't
check that its netns is matched with a diag socket namespace, so any
user can get information about any unix socket in a system. This looks
like a bug.

v2: add a Fixes tag

Fixes: 51d7cccf0723 ("net: make sock diag per-namespace")
Signed-off-by: Andrei Vagin <avagin@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/diag.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/unix/diag.c b/net/unix/diag.c
index 4d9679701a6d..384c84e83462 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -257,6 +257,8 @@ static int unix_diag_get_exact(struct sk_buff *in_skb,
 	err = -ENOENT;
 	if (sk == NULL)
 		goto out_nosk;
+	if (!net_eq(sock_net(sk), net))
+		goto out;
 
 	err = sock_diag_check_cookie(sk, req->udiag_cookie);
 	if (err)
-- 
2.13.6


From a7208e94608d96fef51b563fb125c6dba641b12f Mon Sep 17 00:00:00 2001
From: Girish Moodalbail <girish.moodalbail@oracle.com>
Date: Wed, 25 Oct 2017 00:23:04 -0700
Subject: [PATCH 23/37] tap: double-free in error path in tap_open()

[ Upstream commit 78e0ea6791d7baafb8a0ca82b1bd0c7b3453c919 ]

Double free of skb_array in tap module is causing kernel panic. When
tap_set_queue() fails we free skb_array right away by calling
skb_array_cleanup(). However, later on skb_array_cleanup() is called
again by tap_sock_destruct through sock_put(). This patch fixes that
issue.

Fixes: 362899b8725b35e3 (macvtap: switch to use skb array)
Signed-off-by: Girish Moodalbail <girish.moodalbail@oracle.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tap.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index 3570c7576993..ce4d8d768824 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -517,6 +517,10 @@ static int tap_open(struct inode *inode, struct file *file)
 					     &tap_proto, 0);
 	if (!q)
 		goto err;
+	if (skb_array_init(&q->skb_array, tap->dev->tx_queue_len, GFP_KERNEL)) {
+		sk_free(&q->sk);
+		goto err;
+	}
 
 	RCU_INIT_POINTER(q->sock.wq, &q->wq);
 	init_waitqueue_head(&q->wq.wait);
@@ -540,22 +544,18 @@ static int tap_open(struct inode *inode, struct file *file)
 	if ((tap->dev->features & NETIF_F_HIGHDMA) && (tap->dev->features & NETIF_F_SG))
 		sock_set_flag(&q->sk, SOCK_ZEROCOPY);
 
-	err = -ENOMEM;
-	if (skb_array_init(&q->skb_array, tap->dev->tx_queue_len, GFP_KERNEL))
-		goto err_array;
-
 	err = tap_set_queue(tap, file, q);
-	if (err)
-		goto err_queue;
+	if (err) {
+		/* tap_sock_destruct() will take care of freeing skb_array */
+		goto err_put;
+	}
 
 	dev_put(tap->dev);
 
 	rtnl_unlock();
 	return err;
 
-err_queue:
-	skb_array_cleanup(&q->skb_array);
-err_array:
+err_put:
 	sock_put(&q->sk);
 err:
 	if (tap)
-- 
2.13.6


From 1a7c0459ee81f7c351c0f58faa6027573253a927 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Thu, 19 Oct 2017 14:14:29 +0300
Subject: [PATCH 24/37] net/mlx5: Fix health work queue spin lock to IRQ safe

[ Upstream commit 6377ed0bbae6fa28853e1679d068a9106c8a8908 ]

spin_lock/unlock of health->wq_lock should be IRQ safe.
It was changed to spin_lock_irqsave since adding commit 0179720d6be2
("net/mlx5: Introduce trigger_health_work function") which uses
spin_lock from asynchronous event (IRQ) context.
Thus, all spin_lock/unlock of health->wq_lock should have been moved
to IRQ safe mode.
However, one occurrence on new code using this lock missed that
change, resulting in possible deadlock:
  kernel: Possible unsafe locking scenario:
  kernel:       CPU0
  kernel:       ----
  kernel:  lock(&(&health->wq_lock)->rlock);
  kernel:  <Interrupt>
  kernel:    lock(&(&health->wq_lock)->rlock);
  kernel: #012 *** DEADLOCK ***

Fixes: 2a0165a034ac ("net/mlx5: Cancel delayed recovery work when unloading the driver")
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/health.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 4b6b03d6297f..8ccb68a49c65 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -356,10 +356,11 @@ void mlx5_drain_health_wq(struct mlx5_core_dev *dev)
 void mlx5_drain_health_recovery(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_health *health = &dev->priv.health;
+	unsigned long flags;
 
-	spin_lock(&health->wq_lock);
+	spin_lock_irqsave(&health->wq_lock, flags);
 	set_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags);
-	spin_unlock(&health->wq_lock);
+	spin_unlock_irqrestore(&health->wq_lock, flags);
 	cancel_delayed_work_sync(&dev->priv.health.recover_work);
 }
 
-- 
2.13.6


From c4128a6f92d8971bb76acedff1d4a4d331707bb5 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Tue, 17 Oct 2017 12:33:43 +0200
Subject: [PATCH 25/37] net/mlx5e: Properly deal with encap flows add/del under
 neigh update

[ Upstream commit 3c37745ec614ff048d5dce38f976804b05d307ee ]

Currently, the encap action offload is handled in the actions parse
function and not in mlx5e_tc_add_fdb_flow() where we deal with all
the other aspects of offloading actions (vlan, modify header) and
the rule itself.

When the neigh update code (mlx5e_tc_encap_flows_add()) recreates the
encap entry and offloads the related flows, we wrongly call again into
mlx5e_tc_add_fdb_flow(), this for itself would cause us to handle
again the offloading of vlans and header re-write which puts things
in non consistent state and step on freed memory (e.g the modify
header parse buffer which is already freed).

Since on error, mlx5e_tc_add_fdb_flow() detaches and may release the
encap entry, it causes a corruption at the neigh update code which goes
over the list of flows associated with this encap entry, or double free
when the tc flow is later deleted by user-space.

When neigh update (mlx5e_tc_encap_flows_del()) unoffloads the flows related
to an encap entry which is now invalid, we do a partial repeat of the eswitch
flow removal code which is wrong too.

To fix things up we do the following:

(1) handle the encap action offload in the eswitch flow add function
    mlx5e_tc_add_fdb_flow() as done for the other actions and the rule itself.

(2) modify the neigh update code (mlx5e_tc_encap_flows_add/del) to only
    deal with the encap entry and rules delete/add and not with any of
    the other offloaded actions.

Fixes: 232c001398ae ('net/mlx5e: Add support to neighbour update flow')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Paul Blakey <paulb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 89 +++++++++++++++----------
 1 file changed, 54 insertions(+), 35 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 7f282e8f4e7f..dc7f952e341f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -78,9 +78,11 @@ struct mlx5e_tc_flow {
 };
 
 struct mlx5e_tc_flow_parse_attr {
+	struct ip_tunnel_info tun_info;
 	struct mlx5_flow_spec spec;
 	int num_mod_hdr_actions;
 	void *mod_hdr_actions;
+	int mirred_ifindex;
 };
 
 enum {
@@ -322,6 +324,12 @@ static void mlx5e_tc_del_nic_flow(struct mlx5e_priv *priv,
 static void mlx5e_detach_encap(struct mlx5e_priv *priv,
 			       struct mlx5e_tc_flow *flow);
 
+static int mlx5e_attach_encap(struct mlx5e_priv *priv,
+			      struct ip_tunnel_info *tun_info,
+			      struct net_device *mirred_dev,
+			      struct net_device **encap_dev,
+			      struct mlx5e_tc_flow *flow);
+
 static struct mlx5_flow_handle *
 mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 		      struct mlx5e_tc_flow_parse_attr *parse_attr,
@@ -329,9 +337,27 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
-	struct mlx5_flow_handle *rule;
+	struct net_device *out_dev, *encap_dev = NULL;
+	struct mlx5_flow_handle *rule = NULL;
+	struct mlx5e_rep_priv *rpriv;
+	struct mlx5e_priv *out_priv;
 	int err;
 
+	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP) {
+		out_dev = __dev_get_by_index(dev_net(priv->netdev),
+					     attr->parse_attr->mirred_ifindex);
+		err = mlx5e_attach_encap(priv, &parse_attr->tun_info,
+					 out_dev, &encap_dev, flow);
+		if (err) {
+			rule = ERR_PTR(err);
+			if (err != -EAGAIN)
+				goto err_attach_encap;
+		}
+		out_priv = netdev_priv(encap_dev);
+		rpriv = out_priv->ppriv;
+		attr->out_rep = rpriv->rep;
+	}
+
 	err = mlx5_eswitch_add_vlan_action(esw, attr);
 	if (err) {
 		rule = ERR_PTR(err);
@@ -347,10 +373,14 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 		}
 	}
 
-	rule = mlx5_eswitch_add_offloaded_rule(esw, &parse_attr->spec, attr);
-	if (IS_ERR(rule))
-		goto err_add_rule;
-
+	/* we get here if (1) there's no error (rule being null) or when
+	 * (2) there's an encap action and we're on -EAGAIN (no valid neigh)
+	 */
+	if (rule != ERR_PTR(-EAGAIN)) {
+		rule = mlx5_eswitch_add_offloaded_rule(esw, &parse_attr->spec, attr);
+		if (IS_ERR(rule))
+			goto err_add_rule;
+	}
 	return rule;
 
 err_add_rule:
@@ -361,6 +391,7 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 err_add_vlan:
 	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP)
 		mlx5e_detach_encap(priv, flow);
+err_attach_encap:
 	return rule;
 }
 
@@ -389,6 +420,8 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
 			      struct mlx5e_encap_entry *e)
 {
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	struct mlx5_esw_flow_attr *esw_attr;
 	struct mlx5e_tc_flow *flow;
 	int err;
 
@@ -404,10 +437,9 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
 	mlx5e_rep_queue_neigh_stats_work(priv);
 
 	list_for_each_entry(flow, &e->flows, encap) {
-		flow->esw_attr->encap_id = e->encap_id;
-		flow->rule = mlx5e_tc_add_fdb_flow(priv,
-						   flow->esw_attr->parse_attr,
-						   flow);
+		esw_attr = flow->esw_attr;
+		esw_attr->encap_id = e->encap_id;
+		flow->rule = mlx5_eswitch_add_offloaded_rule(esw, &esw_attr->parse_attr->spec, esw_attr);
 		if (IS_ERR(flow->rule)) {
 			err = PTR_ERR(flow->rule);
 			mlx5_core_warn(priv->mdev, "Failed to update cached encapsulation flow, %d\n",
@@ -421,15 +453,13 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
 void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv,
 			      struct mlx5e_encap_entry *e)
 {
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	struct mlx5e_tc_flow *flow;
-	struct mlx5_fc *counter;
 
 	list_for_each_entry(flow, &e->flows, encap) {
 		if (flow->flags & MLX5E_TC_FLOW_OFFLOADED) {
 			flow->flags &= ~MLX5E_TC_FLOW_OFFLOADED;
-			counter = mlx5_flow_rule_counter(flow->rule);
-			mlx5_del_flow_rules(flow->rule);
-			mlx5_fc_destroy(priv->mdev, counter);
+			mlx5_eswitch_del_offloaded_rule(esw, flow->rule, flow->esw_attr);
 		}
 	}
 
@@ -1871,7 +1901,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 
 		if (is_tcf_mirred_egress_redirect(a)) {
 			int ifindex = tcf_mirred_ifindex(a);
-			struct net_device *out_dev, *encap_dev = NULL;
+			struct net_device *out_dev;
 			struct mlx5e_priv *out_priv;
 
 			out_dev = __dev_get_by_index(dev_net(priv->netdev), ifindex);
@@ -1884,17 +1914,13 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 				rpriv = out_priv->ppriv;
 				attr->out_rep = rpriv->rep;
 			} else if (encap) {
-				err = mlx5e_attach_encap(priv, info,
-							 out_dev, &encap_dev, flow);
-				if (err && err != -EAGAIN)
-					return err;
+				parse_attr->mirred_ifindex = ifindex;
+				parse_attr->tun_info = *info;
+				attr->parse_attr = parse_attr;
 				attr->action |= MLX5_FLOW_CONTEXT_ACTION_ENCAP |
 					MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
 					MLX5_FLOW_CONTEXT_ACTION_COUNT;
-				out_priv = netdev_priv(encap_dev);
-				rpriv = out_priv->ppriv;
-				attr->out_rep = rpriv->rep;
-				attr->parse_attr = parse_attr;
+				/* attr->out_rep is resolved when we handle encap */
 			} else {
 				pr_err("devices %s %s not on same switch HW, can't offload forwarding\n",
 				       priv->netdev->name, out_dev->name);
@@ -1972,7 +1998,7 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol,
 	if (flow->flags & MLX5E_TC_FLOW_ESWITCH) {
 		err = parse_tc_fdb_actions(priv, f->exts, parse_attr, flow);
 		if (err < 0)
-			goto err_handle_encap_flow;
+			goto err_free;
 		flow->rule = mlx5e_tc_add_fdb_flow(priv, parse_attr, flow);
 	} else {
 		err = parse_tc_nic_actions(priv, f->exts, parse_attr, flow);
@@ -1983,10 +2009,13 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol,
 
 	if (IS_ERR(flow->rule)) {
 		err = PTR_ERR(flow->rule);
-		goto err_free;
+		if (err != -EAGAIN)
+			goto err_free;
 	}
 
-	flow->flags |= MLX5E_TC_FLOW_OFFLOADED;
+	if (err != -EAGAIN)
+		flow->flags |= MLX5E_TC_FLOW_OFFLOADED;
+
 	err = rhashtable_insert_fast(&tc->ht, &flow->node,
 				     tc->ht_params);
 	if (err)
@@ -2000,16 +2029,6 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol,
 err_del_rule:
 	mlx5e_tc_del_flow(priv, flow);
 
-err_handle_encap_flow:
-	if (err == -EAGAIN) {
-		err = rhashtable_insert_fast(&tc->ht, &flow->node,
-					     tc->ht_params);
-		if (err)
-			mlx5e_tc_del_flow(priv, flow);
-		else
-			return 0;
-	}
-
 err_free:
 	kvfree(parse_attr);
 	kfree(flow);
-- 
2.13.6


From 2a191f9e0c121a33a5dd6aac7a97553f13a6e9a8 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 26 Oct 2017 19:19:56 +0800
Subject: [PATCH 26/37] ipip: only increase err_count for some certain type
 icmp in ipip_err

[ Upstream commit f3594f0a7ea36661d7fd942facd7f31a64245f1a ]

t->err_count is used to count the link failure on tunnel and an err
will be reported to user socket in tx path if t->err_count is not 0.
udp socket could even return EHOSTUNREACH to users.

Since commit fd58156e456d ("IPIP: Use ip-tunneling code.") removed
the 'switch check' for icmp type in ipip_err(), err_count would be
increased by the icmp packet with ICMP_EXC_FRAGTIME code. an link
failure would be reported out due to this.

In Jianlin's case, when receiving ICMP_EXC_FRAGTIME a icmp packet,
udp netperf failed with the err:
  send_data: data send error: No route to host (errno 113)

We expect this error reported from tunnel to socket when receiving
some certain type icmp, but not ICMP_EXC_FRAGTIME, ICMP_SR_FAILED
or ICMP_PARAMETERPROB ones.

This patch is to bring 'switch check' for icmp type back to ipip_err
so that it only reports link failure for the right type icmp, just as
in ipgre_err() and ipip6_err().

Fixes: fd58156e456d ("IPIP: Use ip-tunneling code.")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ipip.c | 59 ++++++++++++++++++++++++++++++++++++++++-----------------
 1 file changed, 42 insertions(+), 17 deletions(-)

diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index fb1ad22b5e29..cdd627355ed1 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -128,43 +128,68 @@ static struct rtnl_link_ops ipip_link_ops __read_mostly;
 
 static int ipip_err(struct sk_buff *skb, u32 info)
 {
-
-/* All the routers (except for Linux) return only
-   8 bytes of packet payload. It means, that precise relaying of
-   ICMP in the real Internet is absolutely infeasible.
- */
+	/* All the routers (except for Linux) return only
+	 * 8 bytes of packet payload. It means, that precise relaying of
+	 * ICMP in the real Internet is absolutely infeasible.
+	 */
 	struct net *net = dev_net(skb->dev);
 	struct ip_tunnel_net *itn = net_generic(net, ipip_net_id);
 	const struct iphdr *iph = (const struct iphdr *)skb->data;
-	struct ip_tunnel *t;
-	int err;
 	const int type = icmp_hdr(skb)->type;
 	const int code = icmp_hdr(skb)->code;
+	struct ip_tunnel *t;
+	int err = 0;
+
+	switch (type) {
+	case ICMP_DEST_UNREACH:
+		switch (code) {
+		case ICMP_SR_FAILED:
+			/* Impossible event. */
+			goto out;
+		default:
+			/* All others are translated to HOST_UNREACH.
+			 * rfc2003 contains "deep thoughts" about NET_UNREACH,
+			 * I believe they are just ether pollution. --ANK
+			 */
+			break;
+		}
+		break;
+
+	case ICMP_TIME_EXCEEDED:
+		if (code != ICMP_EXC_TTL)
+			goto out;
+		break;
+
+	case ICMP_REDIRECT:
+		break;
+
+	default:
+		goto out;
+	}
 
-	err = -ENOENT;
 	t = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
 			     iph->daddr, iph->saddr, 0);
-	if (!t)
+	if (!t) {
+		err = -ENOENT;
 		goto out;
+	}
 
 	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
-		ipv4_update_pmtu(skb, dev_net(skb->dev), info,
-				 t->parms.link, 0, iph->protocol, 0);
-		err = 0;
+		ipv4_update_pmtu(skb, net, info, t->parms.link, 0,
+				 iph->protocol, 0);
 		goto out;
 	}
 
 	if (type == ICMP_REDIRECT) {
-		ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0,
-			      iph->protocol, 0);
-		err = 0;
+		ipv4_redirect(skb, net, t->parms.link, 0, iph->protocol, 0);
 		goto out;
 	}
 
-	if (t->parms.iph.daddr == 0)
+	if (t->parms.iph.daddr == 0) {
+		err = -ENOENT;
 		goto out;
+	}
 
-	err = 0;
 	if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
 		goto out;
 
-- 
2.13.6


From 409c547d66c43e0f309ae870a029a5d5a180861c Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 26 Oct 2017 19:23:27 +0800
Subject: [PATCH 27/37] ip6_gre: only increase err_count for some certain type
 icmpv6 in ip6gre_err

[ Upstream commit f8d20b46ce55cf40afb30dcef6d9288f7ef46d9b ]

The similar fix in patch 'ipip: only increase err_count for some
certain type icmp in ipip_err' is needed for ip6gre_err.

In Jianlin's case, udp netperf broke even when receiving a TooBig
icmpv6 packet.

Fixes: c12b395a4664 ("gre: Support GRE over IPv6")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 1602b491b281..fb595e8dc15b 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -408,13 +408,16 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	case ICMPV6_DEST_UNREACH:
 		net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n",
 				    t->parms.name);
-		break;
+		if (code != ICMPV6_PORT_UNREACH)
+			break;
+		return;
 	case ICMPV6_TIME_EXCEED:
 		if (code == ICMPV6_EXC_HOPLIMIT) {
 			net_dbg_ratelimited("%s: Too small hop limit or routing loop in tunnel!\n",
 					    t->parms.name);
+			break;
 		}
-		break;
+		return;
 	case ICMPV6_PARAMPROB:
 		teli = 0;
 		if (code == ICMPV6_HDR_FIELD)
@@ -430,7 +433,7 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 			net_dbg_ratelimited("%s: Recipient unable to parse tunneled packet!\n",
 					    t->parms.name);
 		}
-		break;
+		return;
 	case ICMPV6_PKT_TOOBIG:
 		mtu = be32_to_cpu(info) - offset - t->tun_hlen;
 		if (t->dev->type == ARPHRD_ETHER)
@@ -438,7 +441,7 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		if (mtu < IPV6_MIN_MTU)
 			mtu = IPV6_MIN_MTU;
 		t->dev->mtu = mtu;
-		break;
+		return;
 	}
 
 	if (time_before(jiffies, t->err_time + IP6TUNNEL_ERR_TIMEO))
-- 
2.13.6


From cd076fe4b406bfa22dfec05673aa467394e20ad5 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 26 Oct 2017 19:27:17 +0800
Subject: [PATCH 28/37] ip6_gre: update dst pmtu if dev mtu has been updated by
 toobig in __gre6_xmit

[ Upstream commit 8aec4959d832bae0889a8e2f348973b5e4abffef ]

When receiving a Toobig icmpv6 packet, ip6gre_err would just set
tunnel dev's mtu, that's not enough. For skb_dst(skb)'s pmtu may
still be using the old value, it has no chance to be updated with
tunnel dev's mtu.

Jianlin found this issue by reducing route's mtu while running
netperf, the performance went to 0.

ip6ip6 and ip4ip6 tunnel can work well with this, as they lookup
the upper dst and update_pmtu it's pmtu or icmpv6_send a Toobig
to upper socket after setting tunnel dev's mtu.

We couldn't do that for ip6_gre, as gre's inner packet could be
any protocol, it's difficult to handle them (like lookup upper
dst) in a good way.

So this patch is to fix it by updating skb_dst(skb)'s pmtu when
dev->mtu < skb_dst(skb)'s pmtu in tx path. It's safe to do this
update there, as usually dev->mtu <= skb_dst(skb)'s pmtu and no
performance regression can be caused by this.

Fixes: c12b395a4664 ("gre: Support GRE over IPv6")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index fb595e8dc15b..59c121b932ac 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -503,8 +503,8 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb,
 			       __u32 *pmtu, __be16 proto)
 {
 	struct ip6_tnl *tunnel = netdev_priv(dev);
-	__be16 protocol = (dev->type == ARPHRD_ETHER) ?
-			  htons(ETH_P_TEB) : proto;
+	struct dst_entry *dst = skb_dst(skb);
+	__be16 protocol;
 
 	if (dev->type == ARPHRD_ETHER)
 		IPCB(skb)->flags = 0;
@@ -518,9 +518,14 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb,
 		tunnel->o_seqno++;
 
 	/* Push GRE header. */
+	protocol = (dev->type == ARPHRD_ETHER) ? htons(ETH_P_TEB) : proto;
 	gre_build_header(skb, tunnel->tun_hlen, tunnel->parms.o_flags,
 			 protocol, tunnel->parms.o_key, htonl(tunnel->o_seqno));
 
+	/* TooBig packet may have updated dst->dev's mtu */
+	if (dst && dst_mtu(dst) > dst->dev->mtu)
+		dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu);
+
 	return ip6_tnl_xmit(skb, dev, dsfield, fl6, encap_limit, pmtu,
 			    NEXTHDR_GRE);
 }
-- 
2.13.6


From 9ae7f48b67ec15368e3460726d6c2ef8b21171c8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 26 Oct 2017 21:21:40 -0700
Subject: [PATCH 29/37] tcp: refresh tp timestamp before tcp_mtu_probe()

[ Upstream commit ee1836aec4f5a977c1699a311db4d9027ef21ac8 ]

In the unlikely event tcp_mtu_probe() is sending a packet, we
want tp->tcp_mstamp being as accurate as possible.

This means we need to call tcp_mstamp_refresh() a bit earlier in
tcp_write_xmit().

Fixes: 385e20706fac ("tcp: use tp->tcp_mstamp in output path")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 40f7c8ee9ba6..9798460b61ab 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2271,6 +2271,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 
 	sent_pkts = 0;
 
+	tcp_mstamp_refresh(tp);
 	if (!push_one) {
 		/* Do MTU probing. */
 		result = tcp_mtu_probe(sk);
@@ -2282,7 +2283,6 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 	}
 
 	max_segs = tcp_tso_segs(sk, mss_now);
-	tcp_mstamp_refresh(tp);
 	while ((skb = tcp_send_head(sk))) {
 		unsigned int limit;
 
-- 
2.13.6


From 1b08a7d1e8196220c2d8d19b918159252e8edfef Mon Sep 17 00:00:00 2001
From: Girish Moodalbail <girish.moodalbail@oracle.com>
Date: Fri, 27 Oct 2017 00:00:16 -0700
Subject: [PATCH 30/37] tap: reference to KVA of an unloaded module causes
 kernel panic

[ Upstream commit dea6e19f4ef746aa18b4c33d1a7fed54356796ed ]

The commit 9a393b5d5988 ("tap: tap as an independent module") created a
separate tap module that implements tap functionality and exports
interfaces that will be used by macvtap and ipvtap modules to create
create respective tap devices.

However, that patch introduced a regression wherein the modules macvtap
and ipvtap can be removed (through modprobe -r) while there are
applications using the respective /dev/tapX devices. These applications
cause kernel to hold reference to /dev/tapX through 'struct cdev
macvtap_cdev' and 'struct cdev ipvtap_dev' defined in macvtap and ipvtap
modules respectively. So,  when the application is later closed the
kernel panics because we are referencing KVA that is present in the
unloaded modules.

----------8<------- Example ----------8<----------
$ sudo ip li add name mv0 link enp7s0 type macvtap
$ sudo ip li show mv0 |grep mv0| awk -e '{print $1 $2}'
  14:mv0@enp7s0:
$ cat /dev/tap14 &
$ lsmod |egrep -i 'tap|vlan'
macvtap                16384  0
macvlan                24576  1 macvtap
tap                    24576  3 macvtap
$ sudo modprobe -r macvtap
$ fg
cat /dev/tap14
^C

<...system panics...>
BUG: unable to handle kernel paging request at ffffffffa038c500
IP: cdev_put+0xf/0x30
----------8<-----------------8<----------

The fix is to set cdev.owner to the module that creates the tap device
(either macvtap or ipvtap). With this set, the operations (in
fs/char_dev.c) on char device holds and releases the module through
cdev_get() and cdev_put() and will not allow the module to unload
prematurely.

Fixes: 9a393b5d5988ea4e (tap: tap as an independent module)
Signed-off-by: Girish Moodalbail <girish.moodalbail@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ipvlan/ipvtap.c | 4 ++--
 drivers/net/macvtap.c       | 4 ++--
 drivers/net/tap.c           | 5 +++--
 include/linux/if_tap.h      | 4 ++--
 4 files changed, 9 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ipvlan/ipvtap.c b/drivers/net/ipvlan/ipvtap.c
index 22f133ea8d7b..2bdd71c4fcd1 100644
--- a/drivers/net/ipvlan/ipvtap.c
+++ b/drivers/net/ipvlan/ipvtap.c
@@ -197,8 +197,8 @@ static int ipvtap_init(void)
 {
 	int err;
 
-	err = tap_create_cdev(&ipvtap_cdev, &ipvtap_major, "ipvtap");
-
+	err = tap_create_cdev(&ipvtap_cdev, &ipvtap_major, "ipvtap",
+			      THIS_MODULE);
 	if (err)
 		goto out1;
 
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 91e7b19bbf86..a84691bd75a7 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -204,8 +204,8 @@ static int macvtap_init(void)
 {
 	int err;
 
-	err = tap_create_cdev(&macvtap_cdev, &macvtap_major, "macvtap");
-
+	err = tap_create_cdev(&macvtap_cdev, &macvtap_major, "macvtap",
+			      THIS_MODULE);
 	if (err)
 		goto out1;
 
diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index ce4d8d768824..0fcf0bb290ac 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -1252,8 +1252,8 @@ static int tap_list_add(dev_t major, const char *device_name)
 	return 0;
 }
 
-int tap_create_cdev(struct cdev *tap_cdev,
-		    dev_t *tap_major, const char *device_name)
+int tap_create_cdev(struct cdev *tap_cdev, dev_t *tap_major,
+		    const char *device_name, struct module *module)
 {
 	int err;
 
@@ -1262,6 +1262,7 @@ int tap_create_cdev(struct cdev *tap_cdev,
 		goto out1;
 
 	cdev_init(tap_cdev, &tap_fops);
+	tap_cdev->owner = module;
 	err = cdev_add(tap_cdev, *tap_major, TAP_NUM_DEVS);
 	if (err)
 		goto out2;
diff --git a/include/linux/if_tap.h b/include/linux/if_tap.h
index 4837157da0dc..9ae41cdd0d4c 100644
--- a/include/linux/if_tap.h
+++ b/include/linux/if_tap.h
@@ -73,8 +73,8 @@ void tap_del_queues(struct tap_dev *tap);
 int tap_get_minor(dev_t major, struct tap_dev *tap);
 void tap_free_minor(dev_t major, struct tap_dev *tap);
 int tap_queue_resize(struct tap_dev *tap);
-int tap_create_cdev(struct cdev *tap_cdev,
-		    dev_t *tap_major, const char *device_name);
+int tap_create_cdev(struct cdev *tap_cdev, dev_t *tap_major,
+		    const char *device_name, struct module *module);
 void tap_destroy_cdev(dev_t major, struct cdev *tap_cdev);
 
 #endif /*_LINUX_IF_TAP_H_*/
-- 
2.13.6


From ea91c54e407f8794b1f34b6677a6b9e6e5ee876a Mon Sep 17 00:00:00 2001
From: Julien Gomes <julien@arista.com>
Date: Wed, 25 Oct 2017 11:50:50 -0700
Subject: [PATCH 31/37] tun: allow positive return values on
 dev_get_valid_name() call

[ Upstream commit 5c25f65fd1e42685f7ccd80e0621829c105785d9 ]

If the name argument of dev_get_valid_name() contains "%d", it will try
to assign it a unit number in __dev__alloc_name() and return either the
unit number (>= 0) or an error code (< 0).
Considering positive values as error values prevent tun device creations
relying this mechanism, therefor we should only consider negative values
as errors here.

Signed-off-by: Julien Gomes <julien@arista.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 9e7b4e7d3f97..87d18f313ebc 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1814,7 +1814,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 		if (!dev)
 			return -ENOMEM;
 		err = dev_get_valid_name(net, dev, name);
-		if (err)
+		if (err < 0)
 			goto err_free_dev;
 
 		dev_net_set(dev, net);
-- 
2.13.6


From 96c435b2fdb80a098b11866c3011220de858f425 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sat, 28 Oct 2017 02:13:29 +0800
Subject: [PATCH 32/37] sctp: reset owner sk for data chunks on out queues when
 migrating a sock

[ Upstream commit d04adf1b355181e737b6b1e23d801b07f0b7c4c0 ]

Now when migrating sock to another one in sctp_sock_migrate(), it only
resets owner sk for the data in receive queues, not the chunks on out
queues.

It would cause that data chunks length on the sock is not consistent
with sk sk_wmem_alloc. When closing the sock or freeing these chunks,
the old sk would never be freed, and the new sock may crash due to
the overflow sk_wmem_alloc.

syzbot found this issue with this series:

  r0 = socket$inet_sctp()
  sendto$inet(r0)
  listen(r0)
  accept4(r0)
  close(r0)

Although listen() should have returned error when one TCP-style socket
is in connecting (I may fix this one in another patch), it could also
be reproduced by peeling off an assoc.

This issue is there since very beginning.

This patch is to reset owner sk for the chunks on out queues so that
sk sk_wmem_alloc has correct value after accept one sock or peeloff
an assoc to one sock.

Note that when resetting owner sk for chunks on outqueue, it has to
sctp_clear_owner_w/skb_orphan chunks before changing assoc->base.sk
first and then sctp_set_owner_w them after changing assoc->base.sk,
due to that sctp_wfree and it's callees are using assoc->base.sk.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 8d760863bc41..3d79085eb4e0 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -169,6 +169,36 @@ static inline void sctp_set_owner_w(struct sctp_chunk *chunk)
 	sk_mem_charge(sk, chunk->skb->truesize);
 }
 
+static void sctp_clear_owner_w(struct sctp_chunk *chunk)
+{
+	skb_orphan(chunk->skb);
+}
+
+static void sctp_for_each_tx_datachunk(struct sctp_association *asoc,
+				       void (*cb)(struct sctp_chunk *))
+
+{
+	struct sctp_outq *q = &asoc->outqueue;
+	struct sctp_transport *t;
+	struct sctp_chunk *chunk;
+
+	list_for_each_entry(t, &asoc->peer.transport_addr_list, transports)
+		list_for_each_entry(chunk, &t->transmitted, transmitted_list)
+			cb(chunk);
+
+	list_for_each_entry(chunk, &q->retransmit, list)
+		cb(chunk);
+
+	list_for_each_entry(chunk, &q->sacked, list)
+		cb(chunk);
+
+	list_for_each_entry(chunk, &q->abandoned, list)
+		cb(chunk);
+
+	list_for_each_entry(chunk, &q->out_chunk_list, list)
+		cb(chunk);
+}
+
 /* Verify that this is a valid address. */
 static inline int sctp_verify_addr(struct sock *sk, union sctp_addr *addr,
 				   int len)
@@ -8196,7 +8226,9 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
 	 * paths won't try to lock it and then oldsk.
 	 */
 	lock_sock_nested(newsk, SINGLE_DEPTH_NESTING);
+	sctp_for_each_tx_datachunk(assoc, sctp_clear_owner_w);
 	sctp_assoc_migrate(assoc, newsk);
+	sctp_for_each_tx_datachunk(assoc, sctp_set_owner_w);
 
 	/* If the association on the newsk is already closed before accept()
 	 * is called, set RCV_SHUTDOWN flag.
-- 
2.13.6


From 7f2fa4ae7468f068c5d5e519d31e3dd16d2d9e5b Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Fri, 27 Oct 2017 22:08:56 -0700
Subject: [PATCH 33/37] net_sched: avoid matching qdisc with zero handle

[ Upstream commit 50317fce2cc70a2bbbc4b42c31bbad510382a53c ]

Davide found the following script triggers a NULL pointer
dereference:

ip l a name eth0 type dummy
tc q a dev eth0 parent :1 handle 1: htb

This is because for a freshly created netdevice noop_qdisc
is attached and when passing 'parent :1', kernel actually
tries to match the major handle which is 0 and noop_qdisc
has handle 0 so is matched by mistake. Commit 69012ae425d7
tries to fix a similar bug but still misses this case.

Handle 0 is not a valid one, should be just skipped. In
fact, kernel uses it as TC_H_UNSPEC.

Fixes: 69012ae425d7 ("net: sched: fix handling of singleton qdiscs with qdisc_hash")
Fixes: 59cc1f61f09c ("net: sched:convert qdisc linked list to hashtable")
Reported-by: Davide Caratti <dcaratti@redhat.com>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_api.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 4fb5a3222d0d..7935db0d787c 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -307,6 +307,8 @@ struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle)
 {
 	struct Qdisc *q;
 
+	if (!handle)
+		return NULL;
 	q = qdisc_match_from_root(dev->qdisc, handle);
 	if (q)
 		goto out;
-- 
2.13.6


From 1b20b9d2fdfd67fb305b0d353fffa9d58947a5b7 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Mon, 30 Oct 2017 17:58:58 +0100
Subject: [PATCH 34/37] l2tp: hold tunnel in pppol2tp_connect()

[ Upstream commit f9e56baf03f9d36043a78f16e3e8b2cfd211e09e ]

Use l2tp_tunnel_get() in pppol2tp_connect() to ensure the tunnel isn't
going to disappear while processing the rest of the function.

Fixes: fd558d186df2 ("l2tp: Split pppol2tp patch into separate l2tp and ppp parts")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ppp.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index e8ec4f3e54fb..412c513d69b3 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -584,6 +584,7 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 	u32 tunnel_id, peer_tunnel_id;
 	u32 session_id, peer_session_id;
 	bool drop_refcnt = false;
+	bool drop_tunnel = false;
 	int ver = 2;
 	int fd;
 
@@ -652,7 +653,9 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 	if (tunnel_id == 0)
 		goto end;
 
-	tunnel = l2tp_tunnel_find(sock_net(sk), tunnel_id);
+	tunnel = l2tp_tunnel_get(sock_net(sk), tunnel_id);
+	if (tunnel)
+		drop_tunnel = true;
 
 	/* Special case: create tunnel context if session_id and
 	 * peer_session_id is 0. Otherwise look up tunnel using supplied
@@ -781,6 +784,8 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 end:
 	if (drop_refcnt)
 		l2tp_session_dec_refcount(session);
+	if (drop_tunnel)
+		l2tp_tunnel_dec_refcount(tunnel);
 	release_sock(sk);
 
 	return error;
-- 
2.13.6


From 4226b7befa1a201ed2636007e62d72677a547a24 Mon Sep 17 00:00:00 2001
From: Craig Gallek <kraig@google.com>
Date: Mon, 30 Oct 2017 18:50:11 -0400
Subject: [PATCH 35/37] tun/tap: sanitize TUNSETSNDBUF input

[ Upstream commit 93161922c658c714715686cd0cf69b090cb9bf1d ]

Syzkaller found several variants of the lockup below by setting negative
values with the TUNSETSNDBUF ioctl.  This patch adds a sanity check
to both the tun and tap versions of this ioctl.

  watchdog: BUG: soft lockup - CPU#0 stuck for 22s! [repro:2389]
  Modules linked in:
  irq event stamp: 329692056
  hardirqs last  enabled at (329692055): [<ffffffff824b8381>] _raw_spin_unlock_irqrestore+0x31/0x75
  hardirqs last disabled at (329692056): [<ffffffff824b9e58>] apic_timer_interrupt+0x98/0xb0
  softirqs last  enabled at (35659740): [<ffffffff824bc958>] __do_softirq+0x328/0x48c
  softirqs last disabled at (35659731): [<ffffffff811c796c>] irq_exit+0xbc/0xd0
  CPU: 0 PID: 2389 Comm: repro Not tainted 4.14.0-rc7 #23
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
  task: ffff880009452140 task.stack: ffff880006a20000
  RIP: 0010:_raw_spin_lock_irqsave+0x11/0x80
  RSP: 0018:ffff880006a27c50 EFLAGS: 00000282 ORIG_RAX: ffffffffffffff10
  RAX: ffff880009ac68d0 RBX: ffff880006a27ce0 RCX: 0000000000000000
  RDX: 0000000000000001 RSI: ffff880006a27ce0 RDI: ffff880009ac6900
  RBP: ffff880006a27c60 R08: 0000000000000000 R09: 0000000000000000
  R10: 0000000000000001 R11: 000000000063ff00 R12: ffff880009ac6900
  R13: ffff880006a27cf8 R14: 0000000000000001 R15: ffff880006a27cf8
  FS:  00007f4be4838700(0000) GS:ffff88000cc00000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 0000000020101000 CR3: 0000000009616000 CR4: 00000000000006f0
  Call Trace:
   prepare_to_wait+0x26/0xc0
   sock_alloc_send_pskb+0x14e/0x270
   ? remove_wait_queue+0x60/0x60
   tun_get_user+0x2cc/0x19d0
   ? __tun_get+0x60/0x1b0
   tun_chr_write_iter+0x57/0x86
   __vfs_write+0x156/0x1e0
   vfs_write+0xf7/0x230
   SyS_write+0x57/0xd0
   entry_SYSCALL_64_fastpath+0x1f/0xbe
  RIP: 0033:0x7f4be4356df9
  RSP: 002b:00007ffc18101c08 EFLAGS: 00000293 ORIG_RAX: 0000000000000001
  RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f4be4356df9
  RDX: 0000000000000046 RSI: 0000000020101000 RDI: 0000000000000005
  RBP: 00007ffc18101c40 R08: 0000000000000001 R09: 0000000000000001
  R10: 0000000000000001 R11: 0000000000000293 R12: 0000559c75f64780
  R13: 00007ffc18101d30 R14: 0000000000000000 R15: 0000000000000000

Fixes: 33dccbb050bb ("tun: Limit amount of queued packets per device")
Fixes: 20d29d7a916a ("net: macvtap driver")
Signed-off-by: Craig Gallek <kraig@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tap.c | 2 ++
 drivers/net/tun.c | 4 ++++
 2 files changed, 6 insertions(+)

diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index 0fcf0bb290ac..38edfcfd3c3a 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -1035,6 +1035,8 @@ static long tap_ioctl(struct file *file, unsigned int cmd,
 	case TUNSETSNDBUF:
 		if (get_user(s, sp))
 			return -EFAULT;
+		if (s <= 0)
+			return -EINVAL;
 
 		q->sk.sk_sndbuf = s;
 		return 0;
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 87d18f313ebc..d1cb1ff83251 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -2219,6 +2219,10 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 			ret = -EFAULT;
 			break;
 		}
+		if (sndbuf <= 0) {
+			ret = -EINVAL;
+			break;
+		}
 
 		tun->sndbuf = sndbuf;
 		tun_set_sndbuf(tun);
-- 
2.13.6


From 363494dd2e021569a211ebfc7a6a259ebd6f8c4d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 30 Oct 2017 22:47:09 -0700
Subject: [PATCH 36/37] ipv6: addrconf: increment ifp refcount before
 ipv6_del_addr()

[ Upstream commit e669b86945478b3d90d2d87e3793a6eed06d332f ]

In the (unlikely) event fixup_permanent_addr() returns a failure,
addrconf_permanent_addr() calls ipv6_del_addr() without the
mandatory call to in6_ifa_hold(), leading to a refcount error,
spotted by syzkaller :

WARNING: CPU: 1 PID: 3142 at lib/refcount.c:227 refcount_dec+0x4c/0x50
lib/refcount.c:227
Kernel panic - not syncing: panic_on_warn set ...

CPU: 1 PID: 3142 Comm: ip Not tainted 4.14.0-rc4-next-20171009+ #33
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:16 [inline]
 dump_stack+0x194/0x257 lib/dump_stack.c:52
 panic+0x1e4/0x41c kernel/panic.c:181
 __warn+0x1c4/0x1e0 kernel/panic.c:544
 report_bug+0x211/0x2d0 lib/bug.c:183
 fixup_bug+0x40/0x90 arch/x86/kernel/traps.c:178
 do_trap_no_signal arch/x86/kernel/traps.c:212 [inline]
 do_trap+0x260/0x390 arch/x86/kernel/traps.c:261
 do_error_trap+0x120/0x390 arch/x86/kernel/traps.c:298
 do_invalid_op+0x1b/0x20 arch/x86/kernel/traps.c:311
 invalid_op+0x18/0x20 arch/x86/entry/entry_64.S:905
RIP: 0010:refcount_dec+0x4c/0x50 lib/refcount.c:227
RSP: 0018:ffff8801ca49e680 EFLAGS: 00010286
RAX: 000000000000002c RBX: ffff8801d07cfcdc RCX: 0000000000000000
RDX: 000000000000002c RSI: 1ffff10039493c90 RDI: ffffed0039493cc4
RBP: ffff8801ca49e688 R08: ffff8801ca49dd70 R09: 0000000000000000
R10: ffff8801ca49df58 R11: 0000000000000000 R12: 1ffff10039493cd9
R13: ffff8801ca49e6e8 R14: ffff8801ca49e7e8 R15: ffff8801d07cfcdc
 __in6_ifa_put include/net/addrconf.h:369 [inline]
 ipv6_del_addr+0x42b/0xb60 net/ipv6/addrconf.c:1208
 addrconf_permanent_addr net/ipv6/addrconf.c:3327 [inline]
 addrconf_notify+0x1c66/0x2190 net/ipv6/addrconf.c:3393
 notifier_call_chain+0x136/0x2c0 kernel/notifier.c:93
 __raw_notifier_call_chain kernel/notifier.c:394 [inline]
 raw_notifier_call_chain+0x2d/0x40 kernel/notifier.c:401
 call_netdevice_notifiers_info+0x32/0x60 net/core/dev.c:1697
 call_netdevice_notifiers net/core/dev.c:1715 [inline]
 __dev_notify_flags+0x15d/0x430 net/core/dev.c:6843
 dev_change_flags+0xf5/0x140 net/core/dev.c:6879
 do_setlink+0xa1b/0x38e0 net/core/rtnetlink.c:2113
 rtnl_newlink+0xf0d/0x1a40 net/core/rtnetlink.c:2661
 rtnetlink_rcv_msg+0x733/0x1090 net/core/rtnetlink.c:4301
 netlink_rcv_skb+0x216/0x440 net/netlink/af_netlink.c:2408
 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:4313
 netlink_unicast_kernel net/netlink/af_netlink.c:1273 [inline]
 netlink_unicast+0x4e8/0x6f0 net/netlink/af_netlink.c:1299
 netlink_sendmsg+0xa4a/0xe70 net/netlink/af_netlink.c:1862
 sock_sendmsg_nosec net/socket.c:633 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:643
 ___sys_sendmsg+0x75b/0x8a0 net/socket.c:2049
 __sys_sendmsg+0xe5/0x210 net/socket.c:2083
 SYSC_sendmsg net/socket.c:2094 [inline]
 SyS_sendmsg+0x2d/0x50 net/socket.c:2090
 entry_SYSCALL_64_fastpath+0x1f/0xbe
RIP: 0033:0x7fa9174d3320
RSP: 002b:00007ffe302ae9e8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 00007ffe302b2ae0 RCX: 00007fa9174d3320
RDX: 0000000000000000 RSI: 00007ffe302aea20 RDI: 0000000000000016
RBP: 0000000000000082 R08: 0000000000000000 R09: 000000000000000f
R10: 0000000000000000 R11: 0000000000000246 R12: 00007ffe302b32a0
R13: 0000000000000000 R14: 00007ffe302b2ab8 R15: 00007ffe302b32b8

Fixes: f1705ec197e7 ("net: ipv6: Make address flushing on ifdown optional")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: David Ahern <dsahern@gmail.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index ba757c28a301..bdc93e51427d 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3367,6 +3367,7 @@ static void addrconf_permanent_addr(struct net_device *dev)
 		if ((ifp->flags & IFA_F_PERMANENT) &&
 		    fixup_permanent_addr(idev, ifp) < 0) {
 			write_unlock_bh(&idev->lock);
+			in6_ifa_hold(ifp);
 			ipv6_del_addr(ifp);
 			write_lock_bh(&idev->lock);
 
-- 
2.13.6


From 635923116357016864d26c6660ec78fa33d59551 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 30 Oct 2017 23:08:20 -0700
Subject: [PATCH 37/37] tcp: fix tcp_mtu_probe() vs highest_sack

[ Upstream commit 2b7cda9c35d3b940eb9ce74b30bbd5eb30db493d ]

Based on SNMP values provided by Roman, Yuchung made the observation
that some crashes in tcp_sacktag_walk() might be caused by MTU probing.

Looking at tcp_mtu_probe(), I found that when a new skb was placed
in front of the write queue, we were not updating tcp highest sack.

If one skb is freed because all its content was copied to the new skb
(for MTU probing), then tp->highest_sack could point to a now freed skb.

Bad things would then happen, including infinite loops.

This patch renames tcp_highest_sack_combine() and uses it
from tcp_mtu_probe() to fix the bug.

Note that I also removed one test against tp->sacked_out,
since we want to replace tp->highest_sack regardless of whatever
condition, since keeping a stale pointer to freed skb is a recipe
for disaster.

Fixes: a47e5a988a57 ("[TCP]: Convert highest_sack to sk_buff to allow direct access")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Reported-by: Roman Gushchin <guro@fb.com>
Reported-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h     | 6 +++---
 net/ipv4/tcp_output.c | 3 ++-
 2 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 48978125947b..150c2c66897a 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1750,12 +1750,12 @@ static inline void tcp_highest_sack_reset(struct sock *sk)
 	tcp_sk(sk)->highest_sack = tcp_write_queue_head(sk);
 }
 
-/* Called when old skb is about to be deleted (to be combined with new skb) */
-static inline void tcp_highest_sack_combine(struct sock *sk,
+/* Called when old skb is about to be deleted and replaced by new skb */
+static inline void tcp_highest_sack_replace(struct sock *sk,
 					    struct sk_buff *old,
 					    struct sk_buff *new)
 {
-	if (tcp_sk(sk)->sacked_out && (old == tcp_sk(sk)->highest_sack))
+	if (old == tcp_highest_sack(sk))
 		tcp_sk(sk)->highest_sack = new;
 }
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 9798460b61ab..58587b0e2b5d 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2094,6 +2094,7 @@ static int tcp_mtu_probe(struct sock *sk)
 	nskb->ip_summed = skb->ip_summed;
 
 	tcp_insert_write_queue_before(nskb, skb, sk);
+	tcp_highest_sack_replace(sk, skb, nskb);
 
 	len = 0;
 	tcp_for_write_queue_from_safe(skb, next, sk) {
@@ -2694,7 +2695,7 @@ static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
 		else if (!skb_shift(skb, next_skb, next_skb_size))
 			return false;
 	}
-	tcp_highest_sack_combine(sk, next_skb, skb);
+	tcp_highest_sack_replace(sk, next_skb, skb);
 
 	tcp_unlink_write_queue(next_skb, sk);
 
-- 
2.13.6

Re: [PATCHES] Networking

[Greg KH]

On Tue, Nov 14, 2017 at 03:36:24PM +0900, David Miller wrote:
> 
> Please queue up the following bug fixes to 4.9.x and
> 4.13.x -stable, respectively.

All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 113 bytes --]


Please queue up the following networking fixes for 4.9.x,
4.13.x, and 4.14.x -stable, respectively.

Thank you.

[-- Attachment #2: net_49.mbox --]
[-- Type: Application/Octet-Stream, Size: 32991 bytes --]

From 1142409cac8dc35e8917ca247c59101497a3a5e2 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Date: Wed, 1 Nov 2017 16:32:15 +0300
Subject: [PATCH 01/14] tcp_nv: fix division by zero in tcpnv_acked()

[ Upstream commit 4eebff27ca4182bbf5f039dd60d79e2d7c0a707e ]

Average RTT could become zero. This happened in real life at least twice.
This patch treats zero as 1us.

Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Acked-by: Lawrence Brakmo <Brakmo@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_nv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_nv.c b/net/ipv4/tcp_nv.c
index 5de82a8d4d87..e45e2c41c7bd 100644
--- a/net/ipv4/tcp_nv.c
+++ b/net/ipv4/tcp_nv.c
@@ -263,7 +263,7 @@ static void tcpnv_acked(struct sock *sk, const struct ack_sample *sample)
 
 	/* rate in 100's bits per second */
 	rate64 = ((u64)sample->in_flight) * 8000000;
-	rate = (u32)div64_u64(rate64, (u64)(avg_rtt * 100));
+	rate = (u32)div64_u64(rate64, (u64)(avg_rtt ?: 1) * 100);
 
 	/* Remember the maximum rate seen during this RTT
 	 * Note: It may be more than one RTT. This function should be
-- 
2.13.6


From ec8b2762dd6a5b25c19ba3a515cf2ae7a39d7d4f Mon Sep 17 00:00:00 2001
From: Jeff Barnhill <0xeffeff@gmail.com>
Date: Wed, 1 Nov 2017 14:58:09 +0000
Subject: [PATCH 02/14] net: vrf: correct FRA_L3MDEV encode type

[ Upstream commit 18129a24983906eaf2a2d448ce4b83e27091ebe2 ]

FRA_L3MDEV is defined as U8, but is being added as a U32 attribute. On
big endian architecture, this results in the l3mdev entry not being
added to the FIB rules.

Fixes: 1aa6c4f6b8cd8 ("net: vrf: Add l3mdev rules on first device create")
Signed-off-by: Jeff Barnhill <0xeffeff@gmail.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 578bd5001d93..346e48698555 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -1129,7 +1129,7 @@ static int vrf_fib_rule(const struct net_device *dev, __u8 family, bool add_it)
 	frh->family = family;
 	frh->action = FR_ACT_TO_TBL;
 
-	if (nla_put_u32(skb, FRA_L3MDEV, 1))
+	if (nla_put_u8(skb, FRA_L3MDEV, 1))
 		goto nla_put_failure;
 
 	if (nla_put_u32(skb, FRA_PRIORITY, FIB_RULE_PREF))
-- 
2.13.6


From db8ef715fdf187dcb74f3e7ef4ef8d78520d7e0f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 2 Nov 2017 12:30:25 -0700
Subject: [PATCH 03/14] tcp: do not mangle skb->cb[] in tcp_make_synack()

[ Upstream commit 3b11775033dc87c3d161996c54507b15ba26414a ]

Christoph Paasch sent a patch to address the following issue :

tcp_make_synack() is leaving some TCP private info in skb->cb[],
then send the packet by other means than tcp_transmit_skb()

tcp_transmit_skb() makes sure to clear skb->cb[] to not confuse
IPv4/IPV6 stacks, but we have no such cleanup for SYNACK.

tcp_make_synack() should not use tcp_init_nondata_skb() :

tcp_init_nondata_skb() really should be limited to skbs put in write/rtx
queues (the ones that are only sent via tcp_transmit_skb())

This patch fixes the issue and should even save few cpu cycles ;)

Fixes: 971f10eca186 ("tcp: better TCP_SKB_CB layout to reduce cache line misses")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Christoph Paasch <cpaasch@apple.com>
Reviewed-by: Christoph Paasch <cpaasch@apple.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 566b43afe378..3d7b59ecc76c 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3110,13 +3110,8 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	tcp_ecn_make_synack(req, th);
 	th->source = htons(ireq->ir_num);
 	th->dest = ireq->ir_rmt_port;
-	/* Setting of flags are superfluous here for callers (and ECE is
-	 * not even correctly set)
-	 */
-	tcp_init_nondata_skb(skb, tcp_rsk(req)->snt_isn,
-			     TCPHDR_SYN | TCPHDR_ACK);
-
-	th->seq = htonl(TCP_SKB_CB(skb)->seq);
+	skb->ip_summed = CHECKSUM_PARTIAL;
+	th->seq = htonl(tcp_rsk(req)->snt_isn);
 	/* XXX data is queued and acked as is. No buffer/window check */
 	th->ack_seq = htonl(tcp_rsk(req)->rcv_nxt);
 
-- 
2.13.6


From 5a37587718e06e47346604a2dff8e3d2825359bf Mon Sep 17 00:00:00 2001
From: Ye Yin <hustcat@gmail.com>
Date: Thu, 26 Oct 2017 16:57:05 +0800
Subject: [PATCH 04/14] netfilter/ipvs: clear ipvs_property flag when SKB net
 namespace changed

[ Upstream commit 2b5ec1a5f9738ee7bf8f5ec0526e75e00362c48f ]

When run ipvs in two different network namespace at the same host, and one
ipvs transport network traffic to the other network namespace ipvs.
'ipvs_property' flag will make the second ipvs take no effect. So we should
clear 'ipvs_property' when SKB network namespace changed.

Fixes: 621e84d6f373 ("dev: introduce skb_scrub_packet()")
Signed-off-by: Ye Yin <hustcat@gmail.com>
Signed-off-by: Wei Zhou <chouryzhou@gmail.com>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 7 +++++++
 net/core/skbuff.c      | 1 +
 2 files changed, 8 insertions(+)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 32810f279f8e..601dfa849d30 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3584,6 +3584,13 @@ static inline void nf_reset_trace(struct sk_buff *skb)
 #endif
 }
 
+static inline void ipvs_reset(struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_IP_VS)
+	skb->ipvs_property = 0;
+#endif
+}
+
 /* Note: This doesn't put any conntrack and bridge info in dst. */
 static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src,
 			     bool copy)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index fe008f1bd930..aec5605944d3 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4375,6 +4375,7 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet)
 	if (!xnet)
 		return;
 
+	ipvs_reset(skb);
 	skb_orphan(skb);
 	skb->mark = 0;
 }
-- 
2.13.6


From ed77dda626a9e8b08fdada8f3914f7793a6133ab Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Mon, 6 Nov 2017 09:01:57 +0800
Subject: [PATCH 05/14] bonding: discard lowest hash bit for 802.3ad layer3+4

[ Upstream commit b5f862180d7011d9575d0499fa37f0f25b423b12 ]

After commit 07f4c90062f8 ("tcp/dccp: try to not exhaust ip_local_port_range
in connect()"), we will try to use even ports for connect(). Then if an
application (seen clearly with iperf) opens multiple streams to the same
destination IP and port, each stream will be given an even source port.

So the bonding driver's simple xmit_hash_policy based on layer3+4 addressing
will always hash all these streams to the same interface. And the total
throughput will limited to a single slave.

Change the tcp code will impact the whole tcp behavior, only for bonding
usage. Paolo Abeni suggested fix this by changing the bonding code only,
which should be more reasonable, and less impact.

Fix this by discarding the lowest hash bit because it contains little entropy.
After the fix we can re-balance between slaves.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 5fa36ebc0640..63d61c084815 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3217,7 +3217,7 @@ u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb)
 	hash ^= (hash >> 16);
 	hash ^= (hash >> 8);
 
-	return hash;
+	return hash >> 1;
 }
 
 /*-------------------------- Device entry points ----------------------------*/
-- 
2.13.6


From 139fa41889b9e0ae1690d161467f4ac707b692a4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Mon, 6 Nov 2017 15:37:22 +0100
Subject: [PATCH 06/14] net: cdc_ether: fix divide by 0 on bad descriptors
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 2cb80187ba065d7decad7c6614e35e07aec8a974 ]

Setting dev->hard_mtu to 0 will cause a divide error in
usbnet_probe. Protect against devices with bogus CDC Ethernet
functional descriptors by ignoring a zero wMaxSegmentSize.

Signed-off-by: Bjørn Mork <bjorn@mork.no>
Acked-by: Oliver Neukum <oneukum@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ether.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index b82be816256c..1fca0024f294 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -221,7 +221,7 @@ int usbnet_generic_cdc_bind(struct usbnet *dev, struct usb_interface *intf)
 			goto bad_desc;
 	}
 
-	if (header.usb_cdc_ether_desc) {
+	if (header.usb_cdc_ether_desc && info->ether->wMaxSegmentSize) {
 		dev->hard_mtu = le16_to_cpu(info->ether->wMaxSegmentSize);
 		/* because of Zaurus, we may be ignoring the host
 		 * side link address we were given.
-- 
2.13.6


From 75da78bf50ddd465838c5e288cb5fc042cdf7c73 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Mon, 6 Nov 2017 15:32:18 +0100
Subject: [PATCH 07/14] net: qmi_wwan: fix divide by 0 on bad descriptors
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 7fd078337201cf7468f53c3d9ef81ff78cb6df3b ]

A CDC Ethernet functional descriptor with wMaxSegmentSize = 0 will
cause a divide error in usbnet_probe:

divide error: 0000 [#1] PREEMPT SMP KASAN
Modules linked in:
CPU: 0 PID: 24 Comm: kworker/0:1 Not tainted 4.14.0-rc8-44453-g1fdc1a82c34f #56
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
Workqueue: usb_hub_wq hub_event
task: ffff88006bef5c00 task.stack: ffff88006bf60000
RIP: 0010:usbnet_update_max_qlen+0x24d/0x390 drivers/net/usb/usbnet.c:355
RSP: 0018:ffff88006bf67508 EFLAGS: 00010246
RAX: 00000000000163c8 RBX: ffff8800621fce40 RCX: ffff8800621fcf34
RDX: 0000000000000000 RSI: ffffffff837ecb7a RDI: ffff8800621fcf34
RBP: ffff88006bf67520 R08: ffff88006bef5c00 R09: ffffed000c43f881
R10: ffffed000c43f880 R11: ffff8800621fc406 R12: 0000000000000003
R13: ffffffff85c71de0 R14: 0000000000000000 R15: 0000000000000000
FS:  0000000000000000(0000) GS:ffff88006ca00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007ffe9c0d6dac CR3: 00000000614f4000 CR4: 00000000000006f0
Call Trace:
 usbnet_probe+0x18b5/0x2790 drivers/net/usb/usbnet.c:1783
 qmi_wwan_probe+0x133/0x220 drivers/net/usb/qmi_wwan.c:1338
 usb_probe_interface+0x324/0x940 drivers/usb/core/driver.c:361
 really_probe drivers/base/dd.c:413
 driver_probe_device+0x522/0x740 drivers/base/dd.c:557

Fix by simply ignoring the bogus descriptor, as it is optional
for QMI devices anyway.

Fixes: 423ce8caab7e ("net: usb: qmi_wwan: New driver for Huawei QMI based WWAN devices")
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 49a27dc46e5e..cce36e0df2eb 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -386,7 +386,7 @@ static int qmi_wwan_bind(struct usbnet *dev, struct usb_interface *intf)
 	}
 
 	/* errors aren't fatal - we can live with the dynamic address */
-	if (cdc_ether) {
+	if (cdc_ether && cdc_ether->wMaxSegmentSize) {
 		dev->hard_mtu = le16_to_cpu(cdc_ether->wMaxSegmentSize);
 		usbnet_get_ethernet_addr(dev, cdc_ether->iMACAddress);
 	}
-- 
2.13.6


From bbc7a2f2d86f285ad59a73f866568e933da2210c Mon Sep 17 00:00:00 2001
From: Kristian Evensen <kristian.evensen@gmail.com>
Date: Tue, 7 Nov 2017 13:47:56 +0100
Subject: [PATCH 08/14] qmi_wwan: Add missing skb_reset_mac_header-call
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 0de0add10e587effa880c741c9413c874f16be91 ]

When we receive a packet on a QMI device in raw IP mode, we should call
skb_reset_mac_header() to ensure that skb->mac_header contains a valid
offset in the packet. While it shouldn't really matter, the packets have
no MAC header and the interface is configured as-such, it seems certain
parts of the network stack expects a "good" value in skb->mac_header.

Without the skb_reset_mac_header() call added in this patch, for example
shaping traffic (using tc) triggers the following oops on the first
received packet:

[  303.642957] skbuff: skb_under_panic: text:8f137918 len:177 put:67 head:8e4b0f00 data:8e4b0eff tail:0x8e4b0fb0 end:0x8e4b1520 dev:wwan0
[  303.655045] Kernel bug detected[#1]:
[  303.658622] CPU: 1 PID: 1002 Comm: logd Not tainted 4.9.58 #0
[  303.664339] task: 8fdf05e0 task.stack: 8f15c000
[  303.668844] $ 0   : 00000000 00000001 0000007a 00000000
[  303.674062] $ 4   : 8149a2fc 8149a2fc 8149ce20 00000000
[  303.679284] $ 8   : 00000030 3878303a 31623465 20303235
[  303.684510] $12   : ded731e3 2626a277 00000000 03bd0000
[  303.689747] $16   : 8ef62b40 00000043 8f137918 804db5fc
[  303.694978] $20   : 00000001 00000004 8fc13800 00000003
[  303.700215] $24   : 00000001 8024ab10
[  303.705442] $28   : 8f15c000 8fc19cf0 00000043 802cc920
[  303.710664] Hi    : 00000000
[  303.713533] Lo    : 74e58000
[  303.716436] epc   : 802cc920 skb_panic+0x58/0x5c
[  303.721046] ra    : 802cc920 skb_panic+0x58/0x5c
[  303.725639] Status: 11007c03 KERNEL EXL IE
[  303.729823] Cause : 50800024 (ExcCode 09)
[  303.733817] PrId  : 0001992f (MIPS 1004Kc)
[  303.737892] Modules linked in: rt2800pci rt2800mmio rt2800lib qcserial ppp_async option usb_wwan rt2x00pci rt2x00mmio rt2x00lib rndis_host qmi_wwan ppp_generic nf_nat_pptp nf_conntrack_pptp nf_conntrack_ipv6 mt76x2i
Process logd (pid: 1002, threadinfo=8f15c000, task=8fdf05e0, tls=77b3eee4)
[  303.962509] Stack : 00000000 80408990 8f137918 000000b1 00000043 8e4b0f00 8e4b0eff 8e4b0fb0
[  303.970871]         8e4b1520 8fec1800 00000043 802cd2a4 6e000045 00000043 00000000 8ef62000
[  303.979219]         8eef5d00 8ef62b40 8fea7300 8f137918 00000000 00000000 0002bb01 793e5664
[  303.987568]         8ef08884 00000001 8fea7300 00000002 8fc19e80 8eef5d00 00000006 00000003
[  303.995934]         00000000 8030ba90 00000003 77ab3fd0 8149dc80 8004d1bc 8f15c000 8f383700
[  304.004324]         ...
[  304.006767] Call Trace:
[  304.009241] [<802cc920>] skb_panic+0x58/0x5c
[  304.013504] [<802cd2a4>] skb_push+0x78/0x90
[  304.017783] [<8f137918>] 0x8f137918
[  304.021269] Code: 00602825  0c02a3b4  24842888 <000c000d> 8c870060  8c8200a0  0007382b  00070336  8c88005c
[  304.031034]
[  304.032805] ---[ end trace b778c482b3f0bda9 ]---
[  304.041384] Kernel panic - not syncing: Fatal exception in interrupt
[  304.051975] Rebooting in 3 seconds..

While the oops is for a 4.9-kernel, I was able to trigger the same oops with
net-next as of yesterday.

Fixes: 32f7adf633b9 ("net: qmi_wwan: support "raw IP" mode")
Signed-off-by: Kristian Evensen <kristian.evensen@gmail.com>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index cce36e0df2eb..9cf11c83993a 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -205,6 +205,7 @@ static int qmi_wwan_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 		return 1;
 	}
 	if (rawip) {
+		skb_reset_mac_header(skb);
 		skb->dev = dev->net; /* normally set by eth_type_trans */
 		skb->protocol = proto;
 		return 1;
-- 
2.13.6


From a4d3c42adda582ebb5b3ff8df40fde647620e3c4 Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Mon, 6 Nov 2017 13:26:46 +0100
Subject: [PATCH 09/14] net: usb: asix: fill null-ptr-deref in asix_suspend

[ Upstream commit 8f5624629105589bcc23d0e51cc01bd8103d09a5 ]

When asix_suspend() is called dev->driver_priv might not have been
assigned a value, so we need to check that it's not NULL.

Similar issue is present in asix_resume(), this patch fixes it as well.

Found by syzkaller.

kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] PREEMPT SMP KASAN
Modules linked in:
CPU: 0 PID: 24 Comm: kworker/0:1 Not tainted 4.14.0-rc4-43422-geccacdd69a8c #400
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
Workqueue: usb_hub_wq hub_event
task: ffff88006bb36300 task.stack: ffff88006bba8000
RIP: 0010:asix_suspend+0x76/0xc0 drivers/net/usb/asix_devices.c:629
RSP: 0018:ffff88006bbae718 EFLAGS: 00010202
RAX: dffffc0000000000 RBX: ffff880061ba3b80 RCX: 1ffff1000c34d644
RDX: 0000000000000001 RSI: 0000000000000402 RDI: 0000000000000008
RBP: ffff88006bbae738 R08: 1ffff1000d775cad R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: ffff8800630a8b40
R13: 0000000000000000 R14: 0000000000000402 R15: ffff880061ba3b80
FS:  0000000000000000(0000) GS:ffff88006c600000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007ff33cf89000 CR3: 0000000061c0a000 CR4: 00000000000006f0
Call Trace:
 usb_suspend_interface drivers/usb/core/driver.c:1209
 usb_suspend_both+0x27f/0x7e0 drivers/usb/core/driver.c:1314
 usb_runtime_suspend+0x41/0x120 drivers/usb/core/driver.c:1852
 __rpm_callback+0x339/0xb60 drivers/base/power/runtime.c:334
 rpm_callback+0x106/0x220 drivers/base/power/runtime.c:461
 rpm_suspend+0x465/0x1980 drivers/base/power/runtime.c:596
 __pm_runtime_suspend+0x11e/0x230 drivers/base/power/runtime.c:1009
 pm_runtime_put_sync_autosuspend ./include/linux/pm_runtime.h:251
 usb_new_device+0xa37/0x1020 drivers/usb/core/hub.c:2487
 hub_port_connect drivers/usb/core/hub.c:4903
 hub_port_connect_change drivers/usb/core/hub.c:5009
 port_event drivers/usb/core/hub.c:5115
 hub_event+0x194d/0x3740 drivers/usb/core/hub.c:5195
 process_one_work+0xc7f/0x1db0 kernel/workqueue.c:2119
 worker_thread+0x221/0x1850 kernel/workqueue.c:2253
 kthread+0x3a1/0x470 kernel/kthread.c:231
 ret_from_fork+0x2a/0x40 arch/x86/entry/entry_64.S:431
Code: 8d 7c 24 20 48 89 fa 48 c1 ea 03 80 3c 02 00 75 5b 48 b8 00 00
00 00 00 fc ff df 4d 8b 6c 24 20 49 8d 7d 08 48 89 fa 48 c1 ea 03 <80>
3c 02 00 75 34 4d 8b 6d 08 4d 85 ed 74 0b e8 26 2b 51 fd 4c
RIP: asix_suspend+0x76/0xc0 RSP: ffff88006bbae718
---[ end trace dfc4f5649284342c ]---

Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/asix_devices.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c
index 50737def774c..32e9ec8f1521 100644
--- a/drivers/net/usb/asix_devices.c
+++ b/drivers/net/usb/asix_devices.c
@@ -624,7 +624,7 @@ static int asix_suspend(struct usb_interface *intf, pm_message_t message)
 	struct usbnet *dev = usb_get_intfdata(intf);
 	struct asix_common_private *priv = dev->driver_priv;
 
-	if (priv->suspend)
+	if (priv && priv->suspend)
 		priv->suspend(dev);
 
 	return usbnet_suspend(intf, message);
@@ -676,7 +676,7 @@ static int asix_resume(struct usb_interface *intf)
 	struct usbnet *dev = usb_get_intfdata(intf);
 	struct asix_common_private *priv = dev->driver_priv;
 
-	if (priv->resume)
+	if (priv && priv->resume)
 		priv->resume(dev);
 
 	return usbnet_resume(intf);
-- 
2.13.6


From 45e24cb40bb6975e0904881739064af8c6d4b76d Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 9 Nov 2017 16:43:13 -0800
Subject: [PATCH 10/14] vlan: fix a use-after-free in vlan_device_event()

[ Upstream commit 052d41c01b3a2e3371d66de569717353af489d63 ]

After refcnt reaches zero, vlan_vid_del() could free
dev->vlan_info via RCU:

	RCU_INIT_POINTER(dev->vlan_info, NULL);
	call_rcu(&vlan_info->rcu, vlan_info_rcu_free);

However, the pointer 'grp' still points to that memory
since it is set before vlan_vid_del():

        vlan_info = rtnl_dereference(dev->vlan_info);
        if (!vlan_info)
                goto out;
        grp = &vlan_info->grp;

Depends on when that RCU callback is scheduled, we could
trigger a use-after-free in vlan_group_for_each_dev()
right following this vlan_vid_del().

Fix it by moving vlan_vid_del() before setting grp. This
is also symmetric to the vlan_vid_add() we call in
vlan_device_event().

Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Fixes: efc73f4bbc23 ("net: Fix memory leak - vlan_info struct")
Cc: Alexander Duyck <alexander.duyck@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Girish Moodalbail <girish.moodalbail@oracle.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Reviewed-by: Girish Moodalbail <girish.moodalbail@oracle.com>
Tested-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/8021q/vlan.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 8d213f974448..4a47074d1d7f 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -376,6 +376,9 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
 			dev->name);
 		vlan_vid_add(dev, htons(ETH_P_8021Q), 0);
 	}
+	if (event == NETDEV_DOWN &&
+	    (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER))
+		vlan_vid_del(dev, htons(ETH_P_8021Q), 0);
 
 	vlan_info = rtnl_dereference(dev->vlan_info);
 	if (!vlan_info)
@@ -423,9 +426,6 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
 		struct net_device *tmp;
 		LIST_HEAD(close_list);
 
-		if (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)
-			vlan_vid_del(dev, htons(ETH_P_8021Q), 0);
-
 		/* Put all VLANs for this dev in the down state too.  */
 		vlan_group_for_each_dev(grp, i, vlandev) {
 			flgs = vlandev->flags;
-- 
2.13.6


From 3a740621b87ffba5ef3bab5e599a1937fdfd32db Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Thu, 9 Nov 2017 13:04:44 +0900
Subject: [PATCH 11/14] af_netlink: ensure that NLMSG_DONE never fails in dumps

[ Upstream commit 0642840b8bb008528dbdf929cec9f65ac4231ad0 ]

The way people generally use netlink_dump is that they fill in the skb
as much as possible, breaking when nla_put returns an error. Then, they
get called again and start filling out the next skb, and again, and so
forth. The mechanism at work here is the ability for the iterative
dumping function to detect when the skb is filled up and not fill it
past the brim, waiting for a fresh skb for the rest of the data.

However, if the attributes are small and nicely packed, it is possible
that a dump callback function successfully fills in attributes until the
skb is of size 4080 (libmnl's default page-sized receive buffer size).
The dump function completes, satisfied, and then, if it happens to be
that this is actually the last skb, and no further ones are to be sent,
then netlink_dump will add on the NLMSG_DONE part:

  nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE, sizeof(len), NLM_F_MULTI);

It is very important that netlink_dump does this, of course. However, in
this example, that call to nlmsg_put_answer will fail, because the
previous filling by the dump function did not leave it enough room. And
how could it possibly have done so? All of the nla_put variety of
functions simply check to see if the skb has enough tailroom,
independent of the context it is in.

In order to keep the important assumptions of all netlink dump users, it
is therefore important to give them an skb that has this end part of the
tail already reserved, so that the call to nlmsg_put_answer does not
fail. Otherwise, library authors are forced to find some bizarre sized
receive buffer that has a large modulo relative to the common sizes of
messages received, which is ugly and buggy.

This patch thus saves the NLMSG_DONE for an additional message, for the
case that things are dangerously close to the brim. This requires
keeping track of the errno from ->dump() across calls.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 17 +++++++++++------
 net/netlink/af_netlink.h |  1 +
 2 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index a1dca3b169a1..c9fac08a53b1 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2077,7 +2077,7 @@ static int netlink_dump(struct sock *sk)
 	struct sk_buff *skb = NULL;
 	struct nlmsghdr *nlh;
 	struct module *module;
-	int len, err = -ENOBUFS;
+	int err = -ENOBUFS;
 	int alloc_min_size;
 	int alloc_size;
 
@@ -2124,9 +2124,11 @@ static int netlink_dump(struct sock *sk)
 	skb_reserve(skb, skb_tailroom(skb) - alloc_size);
 	netlink_skb_set_owner_r(skb, sk);
 
-	len = cb->dump(skb, cb);
+	if (nlk->dump_done_errno > 0)
+		nlk->dump_done_errno = cb->dump(skb, cb);
 
-	if (len > 0) {
+	if (nlk->dump_done_errno > 0 ||
+	    skb_tailroom(skb) < nlmsg_total_size(sizeof(nlk->dump_done_errno))) {
 		mutex_unlock(nlk->cb_mutex);
 
 		if (sk_filter(sk, skb))
@@ -2136,13 +2138,15 @@ static int netlink_dump(struct sock *sk)
 		return 0;
 	}
 
-	nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE, sizeof(len), NLM_F_MULTI);
-	if (!nlh)
+	nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE,
+			       sizeof(nlk->dump_done_errno), NLM_F_MULTI);
+	if (WARN_ON(!nlh))
 		goto errout_skb;
 
 	nl_dump_check_consistent(cb, nlh);
 
-	memcpy(nlmsg_data(nlh), &len, sizeof(len));
+	memcpy(nlmsg_data(nlh), &nlk->dump_done_errno,
+	       sizeof(nlk->dump_done_errno));
 
 	if (sk_filter(sk, skb))
 		kfree_skb(skb);
@@ -2214,6 +2218,7 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 	}
 
 	nlk->cb_running = true;
+	nlk->dump_done_errno = INT_MAX;
 
 	mutex_unlock(nlk->cb_mutex);
 
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index 4fdb38318977..bae961cfa3ad 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -24,6 +24,7 @@ struct netlink_sock {
 	wait_queue_head_t	wait;
 	bool			bound;
 	bool			cb_running;
+	int			dump_done_errno;
 	struct netlink_callback	cb;
 	struct mutex		*cb_mutex;
 	struct mutex		cb_def_mutex;
-- 
2.13.6


From 3ff329e8c1168f3341f21ce083516593399cfae5 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 17 Oct 2017 23:26:10 +0800
Subject: [PATCH 12/14] sctp: do not peel off an assoc from one netns to
 another one

[ Upstream commit df80cd9b28b9ebaa284a41df611dbf3a2d05ca74 ]

Now when peeling off an association to the sock in another netns, all
transports in this assoc are not to be rehashed and keep use the old
key in hashtable.

As a transport uses sk->net as the hash key to insert into hashtable,
it would miss removing these transports from hashtable due to the new
netns when closing the sock and all transports are being freeed, then
later an use-after-free issue could be caused when looking up an asoc
and dereferencing those transports.

This is a very old issue since very beginning, ChunYu found it with
syzkaller fuzz testing with this series:

  socket$inet6_sctp()
  bind$inet6()
  sendto$inet6()
  unshare(0x40000000)
  getsockopt$inet_sctp6_SCTP_GET_ASSOC_ID_LIST()
  getsockopt$inet_sctp6_SCTP_SOCKOPT_PEELOFF()

This patch is to block this call when peeling one assoc off from one
netns to another one, so that the netns of all transport would not
go out-sync with the key in hashtable.

Note that this patch didn't fix it by rehashing transports, as it's
difficult to handle the situation when the tuple is already in use
in the new netns. Besides, no one would like to peel off one assoc
to another netns, considering ipaddrs, ifaces, etc. are usually
different.

Reported-by: ChunYu Wang <chunwang@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index ffcc8aa78db7..c062ceae19e6 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4764,6 +4764,10 @@ int sctp_do_peeloff(struct sock *sk, sctp_assoc_t id, struct socket **sockp)
 	struct socket *sock;
 	int err = 0;
 
+	/* Do not peel off from one netns to another one. */
+	if (!net_eq(current->nsproxy->net_ns, sock_net(sk)))
+		return -EINVAL;
+
 	if (!asoc)
 		return -EINVAL;
 
-- 
2.13.6


From 8572b2696a3f29fa0e3b20f775cf4694cc77ce43 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhc@lemote.com>
Date: Thu, 16 Nov 2017 11:07:15 +0800
Subject: [PATCH 13/14] fealnx: Fix building error on MIPS

[ Upstream commit cc54c1d32e6a4bb3f116721abf900513173e4d02 ]

This patch try to fix the building error on MIPS. The reason is MIPS
has already defined the LONG macro, which conflicts with the LONG enum
in drivers/net/ethernet/fealnx.c.

Signed-off-by: Huacai Chen <chenhc@lemote.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/fealnx.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/fealnx.c b/drivers/net/ethernet/fealnx.c
index c08bd763172a..a300ed48a7d8 100644
--- a/drivers/net/ethernet/fealnx.c
+++ b/drivers/net/ethernet/fealnx.c
@@ -257,8 +257,8 @@ enum rx_desc_status_bits {
 	RXFSD = 0x00000800,	/* first descriptor */
 	RXLSD = 0x00000400,	/* last descriptor */
 	ErrorSummary = 0x80,	/* error summary */
-	RUNT = 0x40,		/* runt packet received */
-	LONG = 0x20,		/* long packet received */
+	RUNTPKT = 0x40,		/* runt packet received */
+	LONGPKT = 0x20,		/* long packet received */
 	FAE = 0x10,		/* frame align error */
 	CRC = 0x08,		/* crc error */
 	RXER = 0x04,		/* receive error */
@@ -1633,7 +1633,7 @@ static int netdev_rx(struct net_device *dev)
 					       dev->name, rx_status);
 
 				dev->stats.rx_errors++;	/* end of a packet. */
-				if (rx_status & (LONG | RUNT))
+				if (rx_status & (LONGPKT | RUNTPKT))
 					dev->stats.rx_length_errors++;
 				if (rx_status & RXER)
 					dev->stats.rx_frame_errors++;
-- 
2.13.6


From 1eb31171074b566918cb9b5791f73c1c99b29d13 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Wed, 15 Nov 2017 22:17:48 -0600
Subject: [PATCH 14/14] net/sctp: Always set scope_id in sctp_inet6_skb_msgname

[ Upstream commit 7c8a61d9ee1df0fb4747879fa67a99614eb62fec ]

Alexandar Potapenko while testing the kernel with KMSAN and syzkaller
discovered that in some configurations sctp would leak 4 bytes of
kernel stack.

Working with his reproducer I discovered that those 4 bytes that
are leaked is the scope id of an ipv6 address returned by recvmsg.

With a little code inspection and a shrewd guess I discovered that
sctp_inet6_skb_msgname only initializes the scope_id field for link
local ipv6 addresses to the interface index the link local address
pertains to instead of initializing the scope_id field for all ipv6
addresses.

That is almost reasonable as scope_id's are meaniningful only for link
local addresses.  Set the scope_id in all other cases to 0 which is
not a valid interface index to make it clear there is nothing useful
in the scope_id field.

There should be no danger of breaking userspace as the stack leak
guaranteed that previously meaningless random data was being returned.

Fixes: 372f525b495c ("SCTP:  Resync with LKSCTP tree.")
History-tree: https://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git
Reported-by: Alexander Potapenko <glider@google.com>
Tested-by: Alexander Potapenko <glider@google.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ipv6.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index f7f00d012888..5d015270e454 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -806,9 +806,10 @@ static void sctp_inet6_skb_msgname(struct sk_buff *skb, char *msgname,
 		addr->v6.sin6_flowinfo = 0;
 		addr->v6.sin6_port = sh->source;
 		addr->v6.sin6_addr = ipv6_hdr(skb)->saddr;
-		if (ipv6_addr_type(&addr->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) {
+		if (ipv6_addr_type(&addr->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL)
 			addr->v6.sin6_scope_id = sctp_v6_skb_iif(skb);
-		}
+		else
+			addr->v6.sin6_scope_id = 0;
 	}
 
 	*addr_len = sctp_v6_addr_to_user(sctp_sk(skb->sk), addr);
-- 
2.13.6


[-- Attachment #3: net_413.mbox --]
[-- Type: Application/Octet-Stream, Size: 56871 bytes --]

From f9e984d3d5bffafb59fe02f575d79e467291dc97 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Date: Wed, 1 Nov 2017 16:32:15 +0300
Subject: [PATCH 01/22] tcp_nv: fix division by zero in tcpnv_acked()

[ Upstream commit 4eebff27ca4182bbf5f039dd60d79e2d7c0a707e ]

Average RTT could become zero. This happened in real life at least twice.
This patch treats zero as 1us.

Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Acked-by: Lawrence Brakmo <Brakmo@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_nv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_nv.c b/net/ipv4/tcp_nv.c
index 6d650ed3cb59..5c871666c561 100644
--- a/net/ipv4/tcp_nv.c
+++ b/net/ipv4/tcp_nv.c
@@ -263,7 +263,7 @@ static void tcpnv_acked(struct sock *sk, const struct ack_sample *sample)
 
 	/* rate in 100's bits per second */
 	rate64 = ((u64)sample->in_flight) * 8000000;
-	rate = (u32)div64_u64(rate64, (u64)(avg_rtt * 100));
+	rate = (u32)div64_u64(rate64, (u64)(avg_rtt ?: 1) * 100);
 
 	/* Remember the maximum rate seen during this RTT
 	 * Note: It may be more than one RTT. This function should be
-- 
2.13.6


From 16f0a7ec6d6375443438f4c614220b4af4dc0bcc Mon Sep 17 00:00:00 2001
From: Jeff Barnhill <0xeffeff@gmail.com>
Date: Wed, 1 Nov 2017 14:58:09 +0000
Subject: [PATCH 02/22] net: vrf: correct FRA_L3MDEV encode type

[ Upstream commit 18129a24983906eaf2a2d448ce4b83e27091ebe2 ]

FRA_L3MDEV is defined as U8, but is being added as a U32 attribute. On
big endian architecture, this results in the l3mdev entry not being
added to the FIB rules.

Fixes: 1aa6c4f6b8cd8 ("net: vrf: Add l3mdev rules on first device create")
Signed-off-by: Jeff Barnhill <0xeffeff@gmail.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 8a1eaf3c302a..e91ef5e236cc 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -1271,7 +1271,7 @@ static int vrf_fib_rule(const struct net_device *dev, __u8 family, bool add_it)
 	frh->family = family;
 	frh->action = FR_ACT_TO_TBL;
 
-	if (nla_put_u32(skb, FRA_L3MDEV, 1))
+	if (nla_put_u8(skb, FRA_L3MDEV, 1))
 		goto nla_put_failure;
 
 	if (nla_put_u32(skb, FRA_PRIORITY, FIB_RULE_PREF))
-- 
2.13.6


From 9851d9f706a6b98669dea17bafbfc786300da84c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 2 Nov 2017 12:30:25 -0700
Subject: [PATCH 03/22] tcp: do not mangle skb->cb[] in tcp_make_synack()

[ Upstream commit 3b11775033dc87c3d161996c54507b15ba26414a ]

Christoph Paasch sent a patch to address the following issue :

tcp_make_synack() is leaving some TCP private info in skb->cb[],
then send the packet by other means than tcp_transmit_skb()

tcp_transmit_skb() makes sure to clear skb->cb[] to not confuse
IPv4/IPV6 stacks, but we have no such cleanup for SYNACK.

tcp_make_synack() should not use tcp_init_nondata_skb() :

tcp_init_nondata_skb() really should be limited to skbs put in write/rtx
queues (the ones that are only sent via tcp_transmit_skb())

This patch fixes the issue and should even save few cpu cycles ;)

Fixes: 971f10eca186 ("tcp: better TCP_SKB_CB layout to reduce cache line misses")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Christoph Paasch <cpaasch@apple.com>
Reviewed-by: Christoph Paasch <cpaasch@apple.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 58587b0e2b5d..e359840f46c0 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3207,13 +3207,8 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	th->source = htons(ireq->ir_num);
 	th->dest = ireq->ir_rmt_port;
 	skb->mark = ireq->ir_mark;
-	/* Setting of flags are superfluous here for callers (and ECE is
-	 * not even correctly set)
-	 */
-	tcp_init_nondata_skb(skb, tcp_rsk(req)->snt_isn,
-			     TCPHDR_SYN | TCPHDR_ACK);
-
-	th->seq = htonl(TCP_SKB_CB(skb)->seq);
+	skb->ip_summed = CHECKSUM_PARTIAL;
+	th->seq = htonl(tcp_rsk(req)->snt_isn);
 	/* XXX data is queued and acked as is. No buffer/window check */
 	th->ack_seq = htonl(tcp_rsk(req)->rcv_nxt);
 
-- 
2.13.6


From 01e81a4a103906e2c09571c9f74e75cb66b34934 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 2 Nov 2017 16:08:40 -0700
Subject: [PATCH 04/22] net: systemport: Correct IPG length settings

[ Upstream commit 93824c80bf47ebe087414b3a40ca0ff9aab7d1fb ]

Due to a documentation mistake, the IPG length was set to 0x12 while it
should have been 12 (decimal). This would affect short packet (64B
typically) performance since the IPG was bigger than necessary.

Fixes: 44a4524c54af ("net: systemport: Add support for SYSTEMPORT Lite")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bcmsysport.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index c28fa5a8734c..ba15eeadfe21 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -1743,15 +1743,17 @@ static inline void bcm_sysport_mask_all_intrs(struct bcm_sysport_priv *priv)
 
 static inline void gib_set_pad_extension(struct bcm_sysport_priv *priv)
 {
-	u32 __maybe_unused reg;
+	u32 reg;
 
-	/* Include Broadcom tag in pad extension */
+	reg = gib_readl(priv, GIB_CONTROL);
+	/* Include Broadcom tag in pad extension and fix up IPG_LENGTH */
 	if (netdev_uses_dsa(priv->netdev)) {
-		reg = gib_readl(priv, GIB_CONTROL);
 		reg &= ~(GIB_PAD_EXTENSION_MASK << GIB_PAD_EXTENSION_SHIFT);
 		reg |= ENET_BRCM_TAG_LEN << GIB_PAD_EXTENSION_SHIFT;
-		gib_writel(priv, reg, GIB_CONTROL);
 	}
+	reg &= ~(GIB_IPG_LEN_MASK << GIB_IPG_LEN_SHIFT);
+	reg |= 12 << GIB_IPG_LEN_SHIFT;
+	gib_writel(priv, reg, GIB_CONTROL);
 }
 
 static int bcm_sysport_open(struct net_device *dev)
-- 
2.13.6


From 20f79b8f848775dc42738c83ffe90397a8821ed8 Mon Sep 17 00:00:00 2001
From: Ye Yin <hustcat@gmail.com>
Date: Thu, 26 Oct 2017 16:57:05 +0800
Subject: [PATCH 05/22] netfilter/ipvs: clear ipvs_property flag when SKB net
 namespace changed

[ Upstream commit 2b5ec1a5f9738ee7bf8f5ec0526e75e00362c48f ]

When run ipvs in two different network namespace at the same host, and one
ipvs transport network traffic to the other network namespace ipvs.
'ipvs_property' flag will make the second ipvs take no effect. So we should
clear 'ipvs_property' when SKB network namespace changed.

Fixes: 621e84d6f373 ("dev: introduce skb_scrub_packet()")
Signed-off-by: Ye Yin <hustcat@gmail.com>
Signed-off-by: Wei Zhou <chouryzhou@gmail.com>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 7 +++++++
 net/core/skbuff.c      | 1 +
 2 files changed, 8 insertions(+)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 63df75ae70ee..baf2dd102686 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3655,6 +3655,13 @@ static inline void nf_reset_trace(struct sk_buff *skb)
 #endif
 }
 
+static inline void ipvs_reset(struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_IP_VS)
+	skb->ipvs_property = 0;
+#endif
+}
+
 /* Note: This doesn't put any conntrack and bridge info in dst. */
 static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src,
 			     bool copy)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 72eb23d2426f..a0155578e951 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4476,6 +4476,7 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet)
 	if (!xnet)
 		return;
 
+	ipvs_reset(skb);
 	skb_orphan(skb);
 	skb->mark = 0;
 }
-- 
2.13.6


From bc8f92ef76c43499c369205fc9c8d3c9001f4830 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Fri, 3 Nov 2017 16:49:00 +0100
Subject: [PATCH 06/22] l2tp: don't use l2tp_tunnel_find() in l2tp_ip and
 l2tp_ip6

[ Upstream commit 8f7dc9ae4a7aece9fbc3e6637bdfa38b36bcdf09 ]

Using l2tp_tunnel_find() in l2tp_ip_recv() is wrong for two reasons:

  * It doesn't take a reference on the returned tunnel, which makes the
    call racy wrt. concurrent tunnel deletion.

  * The lookup is only based on the tunnel identifier, so it can return
    a tunnel that doesn't match the packet's addresses or protocol.

For example, a packet sent to an L2TPv3 over IPv6 tunnel can be
delivered to an L2TPv2 over UDPv4 tunnel. This is worse than a simple
cross-talk: when delivering the packet to an L2TP over UDP tunnel, the
corresponding socket is UDP, where ->sk_backlog_rcv() is NULL. Calling
sk_receive_skb() will then crash the kernel by trying to execute this
callback.

And l2tp_tunnel_find() isn't even needed here. __l2tp_ip_bind_lookup()
properly checks the socket binding and connection settings. It was used
as a fallback mechanism for finding tunnels that didn't have their data
path registered yet. But it's not limited to this case and can be used
to replace l2tp_tunnel_find() in the general case.

Fix l2tp_ip6 in the same way.

Fixes: 0d76751fad77 ("l2tp: Add L2TPv3 IP encapsulation (no UDP) support")
Fixes: a32e0eec7042 ("l2tp: introduce L2TPv3 IP encapsulation support for IPv6")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ip.c  | 24 +++++++++---------------
 net/l2tp/l2tp_ip6.c | 24 +++++++++---------------
 2 files changed, 18 insertions(+), 30 deletions(-)

diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 4d322c1b7233..e4280b6568b4 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -123,6 +123,7 @@ static int l2tp_ip_recv(struct sk_buff *skb)
 	unsigned char *ptr, *optr;
 	struct l2tp_session *session;
 	struct l2tp_tunnel *tunnel = NULL;
+	struct iphdr *iph;
 	int length;
 
 	if (!pskb_may_pull(skb, 4))
@@ -178,24 +179,17 @@ static int l2tp_ip_recv(struct sk_buff *skb)
 		goto discard;
 
 	tunnel_id = ntohl(*(__be32 *) &skb->data[4]);
-	tunnel = l2tp_tunnel_find(net, tunnel_id);
-	if (tunnel) {
-		sk = tunnel->sock;
-		sock_hold(sk);
-	} else {
-		struct iphdr *iph = (struct iphdr *) skb_network_header(skb);
-
-		read_lock_bh(&l2tp_ip_lock);
-		sk = __l2tp_ip_bind_lookup(net, iph->daddr, iph->saddr,
-					   inet_iif(skb), tunnel_id);
-		if (!sk) {
-			read_unlock_bh(&l2tp_ip_lock);
-			goto discard;
-		}
+	iph = (struct iphdr *)skb_network_header(skb);
 
-		sock_hold(sk);
+	read_lock_bh(&l2tp_ip_lock);
+	sk = __l2tp_ip_bind_lookup(net, iph->daddr, iph->saddr, inet_iif(skb),
+				   tunnel_id);
+	if (!sk) {
 		read_unlock_bh(&l2tp_ip_lock);
+		goto discard;
 	}
+	sock_hold(sk);
+	read_unlock_bh(&l2tp_ip_lock);
 
 	if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
 		goto discard_put;
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 88b397c30d86..8bcaa975b432 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -136,6 +136,7 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
 	unsigned char *ptr, *optr;
 	struct l2tp_session *session;
 	struct l2tp_tunnel *tunnel = NULL;
+	struct ipv6hdr *iph;
 	int length;
 
 	if (!pskb_may_pull(skb, 4))
@@ -192,24 +193,17 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
 		goto discard;
 
 	tunnel_id = ntohl(*(__be32 *) &skb->data[4]);
-	tunnel = l2tp_tunnel_find(net, tunnel_id);
-	if (tunnel) {
-		sk = tunnel->sock;
-		sock_hold(sk);
-	} else {
-		struct ipv6hdr *iph = ipv6_hdr(skb);
-
-		read_lock_bh(&l2tp_ip6_lock);
-		sk = __l2tp_ip6_bind_lookup(net, &iph->daddr, &iph->saddr,
-					    inet6_iif(skb), tunnel_id);
-		if (!sk) {
-			read_unlock_bh(&l2tp_ip6_lock);
-			goto discard;
-		}
+	iph = ipv6_hdr(skb);
 
-		sock_hold(sk);
+	read_lock_bh(&l2tp_ip6_lock);
+	sk = __l2tp_ip6_bind_lookup(net, &iph->daddr, &iph->saddr,
+				    inet6_iif(skb), tunnel_id);
+	if (!sk) {
 		read_unlock_bh(&l2tp_ip6_lock);
+		goto discard;
 	}
+	sock_hold(sk);
+	read_unlock_bh(&l2tp_ip6_lock);
 
 	if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
 		goto discard_put;
-- 
2.13.6


From c56d8bed719420cc2784dd8ef3a32aa1fbd91d7b Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Mon, 6 Nov 2017 09:01:57 +0800
Subject: [PATCH 07/22] bonding: discard lowest hash bit for 802.3ad layer3+4

[ Upstream commit b5f862180d7011d9575d0499fa37f0f25b423b12 ]

After commit 07f4c90062f8 ("tcp/dccp: try to not exhaust ip_local_port_range
in connect()"), we will try to use even ports for connect(). Then if an
application (seen clearly with iperf) opens multiple streams to the same
destination IP and port, each stream will be given an even source port.

So the bonding driver's simple xmit_hash_policy based on layer3+4 addressing
will always hash all these streams to the same interface. And the total
throughput will limited to a single slave.

Change the tcp code will impact the whole tcp behavior, only for bonding
usage. Paolo Abeni suggested fix this by changing the bonding code only,
which should be more reasonable, and less impact.

Fix this by discarding the lowest hash bit because it contains little entropy.
After the fix we can re-balance between slaves.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index c99dc59d729b..76e8054bfc4e 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3253,7 +3253,7 @@ u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb)
 	hash ^= (hash >> 16);
 	hash ^= (hash >> 8);
 
-	return hash;
+	return hash >> 1;
 }
 
 /*-------------------------- Device entry points ----------------------------*/
-- 
2.13.6


From 48016e8cf82e4b536f9a60d5138fc8a009e4596d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Mon, 6 Nov 2017 15:37:22 +0100
Subject: [PATCH 08/22] net: cdc_ether: fix divide by 0 on bad descriptors
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 2cb80187ba065d7decad7c6614e35e07aec8a974 ]

Setting dev->hard_mtu to 0 will cause a divide error in
usbnet_probe. Protect against devices with bogus CDC Ethernet
functional descriptors by ignoring a zero wMaxSegmentSize.

Signed-off-by: Bjørn Mork <bjorn@mork.no>
Acked-by: Oliver Neukum <oneukum@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ether.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index 8ab281b478f2..4f88f64cccb4 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -221,7 +221,7 @@ int usbnet_generic_cdc_bind(struct usbnet *dev, struct usb_interface *intf)
 			goto bad_desc;
 	}
 
-	if (header.usb_cdc_ether_desc) {
+	if (header.usb_cdc_ether_desc && info->ether->wMaxSegmentSize) {
 		dev->hard_mtu = le16_to_cpu(info->ether->wMaxSegmentSize);
 		/* because of Zaurus, we may be ignoring the host
 		 * side link address we were given.
-- 
2.13.6


From 2855746203c8dc2a653c7ce63713f8cc45ceb265 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Mon, 6 Nov 2017 15:32:18 +0100
Subject: [PATCH 09/22] net: qmi_wwan: fix divide by 0 on bad descriptors
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 7fd078337201cf7468f53c3d9ef81ff78cb6df3b ]

A CDC Ethernet functional descriptor with wMaxSegmentSize = 0 will
cause a divide error in usbnet_probe:

divide error: 0000 [#1] PREEMPT SMP KASAN
Modules linked in:
CPU: 0 PID: 24 Comm: kworker/0:1 Not tainted 4.14.0-rc8-44453-g1fdc1a82c34f #56
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
Workqueue: usb_hub_wq hub_event
task: ffff88006bef5c00 task.stack: ffff88006bf60000
RIP: 0010:usbnet_update_max_qlen+0x24d/0x390 drivers/net/usb/usbnet.c:355
RSP: 0018:ffff88006bf67508 EFLAGS: 00010246
RAX: 00000000000163c8 RBX: ffff8800621fce40 RCX: ffff8800621fcf34
RDX: 0000000000000000 RSI: ffffffff837ecb7a RDI: ffff8800621fcf34
RBP: ffff88006bf67520 R08: ffff88006bef5c00 R09: ffffed000c43f881
R10: ffffed000c43f880 R11: ffff8800621fc406 R12: 0000000000000003
R13: ffffffff85c71de0 R14: 0000000000000000 R15: 0000000000000000
FS:  0000000000000000(0000) GS:ffff88006ca00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007ffe9c0d6dac CR3: 00000000614f4000 CR4: 00000000000006f0
Call Trace:
 usbnet_probe+0x18b5/0x2790 drivers/net/usb/usbnet.c:1783
 qmi_wwan_probe+0x133/0x220 drivers/net/usb/qmi_wwan.c:1338
 usb_probe_interface+0x324/0x940 drivers/usb/core/driver.c:361
 really_probe drivers/base/dd.c:413
 driver_probe_device+0x522/0x740 drivers/base/dd.c:557

Fix by simply ignoring the bogus descriptor, as it is optional
for QMI devices anyway.

Fixes: 423ce8caab7e ("net: usb: qmi_wwan: New driver for Huawei QMI based WWAN devices")
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 8c3733608271..a4f229edcceb 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -681,7 +681,7 @@ static int qmi_wwan_bind(struct usbnet *dev, struct usb_interface *intf)
 	}
 
 	/* errors aren't fatal - we can live with the dynamic address */
-	if (cdc_ether) {
+	if (cdc_ether && cdc_ether->wMaxSegmentSize) {
 		dev->hard_mtu = le16_to_cpu(cdc_ether->wMaxSegmentSize);
 		usbnet_get_ethernet_addr(dev, cdc_ether->iMACAddress);
 	}
-- 
2.13.6


From 7392f2ad8f9c05be22d87a9e8e4bf247eb09fee8 Mon Sep 17 00:00:00 2001
From: Kristian Evensen <kristian.evensen@gmail.com>
Date: Tue, 7 Nov 2017 13:47:56 +0100
Subject: [PATCH 10/22] qmi_wwan: Add missing skb_reset_mac_header-call
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 0de0add10e587effa880c741c9413c874f16be91 ]

When we receive a packet on a QMI device in raw IP mode, we should call
skb_reset_mac_header() to ensure that skb->mac_header contains a valid
offset in the packet. While it shouldn't really matter, the packets have
no MAC header and the interface is configured as-such, it seems certain
parts of the network stack expects a "good" value in skb->mac_header.

Without the skb_reset_mac_header() call added in this patch, for example
shaping traffic (using tc) triggers the following oops on the first
received packet:

[  303.642957] skbuff: skb_under_panic: text:8f137918 len:177 put:67 head:8e4b0f00 data:8e4b0eff tail:0x8e4b0fb0 end:0x8e4b1520 dev:wwan0
[  303.655045] Kernel bug detected[#1]:
[  303.658622] CPU: 1 PID: 1002 Comm: logd Not tainted 4.9.58 #0
[  303.664339] task: 8fdf05e0 task.stack: 8f15c000
[  303.668844] $ 0   : 00000000 00000001 0000007a 00000000
[  303.674062] $ 4   : 8149a2fc 8149a2fc 8149ce20 00000000
[  303.679284] $ 8   : 00000030 3878303a 31623465 20303235
[  303.684510] $12   : ded731e3 2626a277 00000000 03bd0000
[  303.689747] $16   : 8ef62b40 00000043 8f137918 804db5fc
[  303.694978] $20   : 00000001 00000004 8fc13800 00000003
[  303.700215] $24   : 00000001 8024ab10
[  303.705442] $28   : 8f15c000 8fc19cf0 00000043 802cc920
[  303.710664] Hi    : 00000000
[  303.713533] Lo    : 74e58000
[  303.716436] epc   : 802cc920 skb_panic+0x58/0x5c
[  303.721046] ra    : 802cc920 skb_panic+0x58/0x5c
[  303.725639] Status: 11007c03 KERNEL EXL IE
[  303.729823] Cause : 50800024 (ExcCode 09)
[  303.733817] PrId  : 0001992f (MIPS 1004Kc)
[  303.737892] Modules linked in: rt2800pci rt2800mmio rt2800lib qcserial ppp_async option usb_wwan rt2x00pci rt2x00mmio rt2x00lib rndis_host qmi_wwan ppp_generic nf_nat_pptp nf_conntrack_pptp nf_conntrack_ipv6 mt76x2i
Process logd (pid: 1002, threadinfo=8f15c000, task=8fdf05e0, tls=77b3eee4)
[  303.962509] Stack : 00000000 80408990 8f137918 000000b1 00000043 8e4b0f00 8e4b0eff 8e4b0fb0
[  303.970871]         8e4b1520 8fec1800 00000043 802cd2a4 6e000045 00000043 00000000 8ef62000
[  303.979219]         8eef5d00 8ef62b40 8fea7300 8f137918 00000000 00000000 0002bb01 793e5664
[  303.987568]         8ef08884 00000001 8fea7300 00000002 8fc19e80 8eef5d00 00000006 00000003
[  303.995934]         00000000 8030ba90 00000003 77ab3fd0 8149dc80 8004d1bc 8f15c000 8f383700
[  304.004324]         ...
[  304.006767] Call Trace:
[  304.009241] [<802cc920>] skb_panic+0x58/0x5c
[  304.013504] [<802cd2a4>] skb_push+0x78/0x90
[  304.017783] [<8f137918>] 0x8f137918
[  304.021269] Code: 00602825  0c02a3b4  24842888 <000c000d> 8c870060  8c8200a0  0007382b  00070336  8c88005c
[  304.031034]
[  304.032805] ---[ end trace b778c482b3f0bda9 ]---
[  304.041384] Kernel panic - not syncing: Fatal exception in interrupt
[  304.051975] Rebooting in 3 seconds..

While the oops is for a 4.9-kernel, I was able to trigger the same oops with
net-next as of yesterday.

Fixes: 32f7adf633b9 ("net: qmi_wwan: support "raw IP" mode")
Signed-off-by: Kristian Evensen <kristian.evensen@gmail.com>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index a4f229edcceb..8d4a6f7cba61 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -499,6 +499,7 @@ static int qmi_wwan_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 		return 1;
 	}
 	if (rawip) {
+		skb_reset_mac_header(skb);
 		skb->dev = dev->net; /* normally set by eth_type_trans */
 		skb->protocol = proto;
 		return 1;
-- 
2.13.6


From 679f77816181633f1cc2f0597062e4764b152eed Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Mon, 6 Nov 2017 13:26:46 +0100
Subject: [PATCH 11/22] net: usb: asix: fill null-ptr-deref in asix_suspend

[ Upstream commit 8f5624629105589bcc23d0e51cc01bd8103d09a5 ]

When asix_suspend() is called dev->driver_priv might not have been
assigned a value, so we need to check that it's not NULL.

Similar issue is present in asix_resume(), this patch fixes it as well.

Found by syzkaller.

kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] PREEMPT SMP KASAN
Modules linked in:
CPU: 0 PID: 24 Comm: kworker/0:1 Not tainted 4.14.0-rc4-43422-geccacdd69a8c #400
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
Workqueue: usb_hub_wq hub_event
task: ffff88006bb36300 task.stack: ffff88006bba8000
RIP: 0010:asix_suspend+0x76/0xc0 drivers/net/usb/asix_devices.c:629
RSP: 0018:ffff88006bbae718 EFLAGS: 00010202
RAX: dffffc0000000000 RBX: ffff880061ba3b80 RCX: 1ffff1000c34d644
RDX: 0000000000000001 RSI: 0000000000000402 RDI: 0000000000000008
RBP: ffff88006bbae738 R08: 1ffff1000d775cad R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: ffff8800630a8b40
R13: 0000000000000000 R14: 0000000000000402 R15: ffff880061ba3b80
FS:  0000000000000000(0000) GS:ffff88006c600000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007ff33cf89000 CR3: 0000000061c0a000 CR4: 00000000000006f0
Call Trace:
 usb_suspend_interface drivers/usb/core/driver.c:1209
 usb_suspend_both+0x27f/0x7e0 drivers/usb/core/driver.c:1314
 usb_runtime_suspend+0x41/0x120 drivers/usb/core/driver.c:1852
 __rpm_callback+0x339/0xb60 drivers/base/power/runtime.c:334
 rpm_callback+0x106/0x220 drivers/base/power/runtime.c:461
 rpm_suspend+0x465/0x1980 drivers/base/power/runtime.c:596
 __pm_runtime_suspend+0x11e/0x230 drivers/base/power/runtime.c:1009
 pm_runtime_put_sync_autosuspend ./include/linux/pm_runtime.h:251
 usb_new_device+0xa37/0x1020 drivers/usb/core/hub.c:2487
 hub_port_connect drivers/usb/core/hub.c:4903
 hub_port_connect_change drivers/usb/core/hub.c:5009
 port_event drivers/usb/core/hub.c:5115
 hub_event+0x194d/0x3740 drivers/usb/core/hub.c:5195
 process_one_work+0xc7f/0x1db0 kernel/workqueue.c:2119
 worker_thread+0x221/0x1850 kernel/workqueue.c:2253
 kthread+0x3a1/0x470 kernel/kthread.c:231
 ret_from_fork+0x2a/0x40 arch/x86/entry/entry_64.S:431
Code: 8d 7c 24 20 48 89 fa 48 c1 ea 03 80 3c 02 00 75 5b 48 b8 00 00
00 00 00 fc ff df 4d 8b 6c 24 20 49 8d 7d 08 48 89 fa 48 c1 ea 03 <80>
3c 02 00 75 34 4d 8b 6d 08 4d 85 ed 74 0b e8 26 2b 51 fd 4c
RIP: asix_suspend+0x76/0xc0 RSP: ffff88006bbae718
---[ end trace dfc4f5649284342c ]---

Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/asix_devices.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c
index b2ff88e69a81..3d4f7959dabb 100644
--- a/drivers/net/usb/asix_devices.c
+++ b/drivers/net/usb/asix_devices.c
@@ -626,7 +626,7 @@ static int asix_suspend(struct usb_interface *intf, pm_message_t message)
 	struct usbnet *dev = usb_get_intfdata(intf);
 	struct asix_common_private *priv = dev->driver_priv;
 
-	if (priv->suspend)
+	if (priv && priv->suspend)
 		priv->suspend(dev);
 
 	return usbnet_suspend(intf, message);
@@ -678,7 +678,7 @@ static int asix_resume(struct usb_interface *intf)
 	struct usbnet *dev = usb_get_intfdata(intf);
 	struct asix_common_private *priv = dev->driver_priv;
 
-	if (priv->resume)
+	if (priv && priv->resume)
 		priv->resume(dev);
 
 	return usbnet_resume(intf);
-- 
2.13.6


From f5cb3d6bbc9bc9e23c9bc2b4fd797f25f98fd330 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 7 Nov 2017 15:15:04 -0800
Subject: [PATCH 12/22] tcp: gso: avoid refcount_t warning from
 tcp_gso_segment()

[ Upstream commit 7ec318feeed10a64c0359ec4d10889cb4defa39a ]

When a GSO skb of truesize O is segmented into 2 new skbs of truesize N1
and N2, we want to transfer socket ownership to the new fresh skbs.

In order to avoid expensive atomic operations on a cache line subject to
cache bouncing, we replace the sequence :

refcount_add(N1, &sk->sk_wmem_alloc);
refcount_add(N2, &sk->sk_wmem_alloc); // repeated by number of segments

refcount_sub(O, &sk->sk_wmem_alloc);

by a single

refcount_add(sum_of(N) - O, &sk->sk_wmem_alloc);

Problem is :

In some pathological cases, sum(N) - O might be a negative number, and
syzkaller bot was apparently able to trigger this trace [1]

atomic_t was ok with this construct, but we need to take care of the
negative delta with refcount_t

[1]
refcount_t: saturated; leaking memory.
------------[ cut here ]------------
WARNING: CPU: 0 PID: 8404 at lib/refcount.c:77 refcount_add_not_zero+0x198/0x200 lib/refcount.c:77
Kernel panic - not syncing: panic_on_warn set ...

CPU: 0 PID: 8404 Comm: syz-executor2 Not tainted 4.14.0-rc5-mm1+ #20
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:16 [inline]
 dump_stack+0x194/0x257 lib/dump_stack.c:52
 panic+0x1e4/0x41c kernel/panic.c:183
 __warn+0x1c4/0x1e0 kernel/panic.c:546
 report_bug+0x211/0x2d0 lib/bug.c:183
 fixup_bug+0x40/0x90 arch/x86/kernel/traps.c:177
 do_trap_no_signal arch/x86/kernel/traps.c:211 [inline]
 do_trap+0x260/0x390 arch/x86/kernel/traps.c:260
 do_error_trap+0x120/0x390 arch/x86/kernel/traps.c:297
 do_invalid_op+0x1b/0x20 arch/x86/kernel/traps.c:310
 invalid_op+0x18/0x20 arch/x86/entry/entry_64.S:905
RIP: 0010:refcount_add_not_zero+0x198/0x200 lib/refcount.c:77
RSP: 0018:ffff8801c606e3a0 EFLAGS: 00010282
RAX: 0000000000000026 RBX: 0000000000001401 RCX: 0000000000000000
RDX: 0000000000000026 RSI: ffffc900036fc000 RDI: ffffed0038c0dc68
RBP: ffff8801c606e430 R08: 0000000000000001 R09: 0000000000000000
R10: ffff8801d97f5eba R11: 0000000000000000 R12: ffff8801d5acf73c
R13: 1ffff10038c0dc75 R14: 00000000ffffffff R15: 00000000fffff72f
 refcount_add+0x1b/0x60 lib/refcount.c:101
 tcp_gso_segment+0x10d0/0x16b0 net/ipv4/tcp_offload.c:155
 tcp4_gso_segment+0xd4/0x310 net/ipv4/tcp_offload.c:51
 inet_gso_segment+0x60c/0x11c0 net/ipv4/af_inet.c:1271
 skb_mac_gso_segment+0x33f/0x660 net/core/dev.c:2749
 __skb_gso_segment+0x35f/0x7f0 net/core/dev.c:2821
 skb_gso_segment include/linux/netdevice.h:3971 [inline]
 validate_xmit_skb+0x4ba/0xb20 net/core/dev.c:3074
 __dev_queue_xmit+0xe49/0x2070 net/core/dev.c:3497
 dev_queue_xmit+0x17/0x20 net/core/dev.c:3538
 neigh_hh_output include/net/neighbour.h:471 [inline]
 neigh_output include/net/neighbour.h:479 [inline]
 ip_finish_output2+0xece/0x1460 net/ipv4/ip_output.c:229
 ip_finish_output+0x85e/0xd10 net/ipv4/ip_output.c:317
 NF_HOOK_COND include/linux/netfilter.h:238 [inline]
 ip_output+0x1cc/0x860 net/ipv4/ip_output.c:405
 dst_output include/net/dst.h:459 [inline]
 ip_local_out+0x95/0x160 net/ipv4/ip_output.c:124
 ip_queue_xmit+0x8c6/0x18e0 net/ipv4/ip_output.c:504
 tcp_transmit_skb+0x1ab7/0x3840 net/ipv4/tcp_output.c:1137
 tcp_write_xmit+0x663/0x4de0 net/ipv4/tcp_output.c:2341
 __tcp_push_pending_frames+0xa0/0x250 net/ipv4/tcp_output.c:2513
 tcp_push_pending_frames include/net/tcp.h:1722 [inline]
 tcp_data_snd_check net/ipv4/tcp_input.c:5050 [inline]
 tcp_rcv_established+0x8c7/0x18a0 net/ipv4/tcp_input.c:5497
 tcp_v4_do_rcv+0x2ab/0x7d0 net/ipv4/tcp_ipv4.c:1460
 sk_backlog_rcv include/net/sock.h:909 [inline]
 __release_sock+0x124/0x360 net/core/sock.c:2264
 release_sock+0xa4/0x2a0 net/core/sock.c:2776
 tcp_sendmsg+0x3a/0x50 net/ipv4/tcp.c:1462
 inet_sendmsg+0x11f/0x5e0 net/ipv4/af_inet.c:763
 sock_sendmsg_nosec net/socket.c:632 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:642
 ___sys_sendmsg+0x31c/0x890 net/socket.c:2048
 __sys_sendmmsg+0x1e6/0x5f0 net/socket.c:2138

Fixes: 14afee4b6092 ("net: convert sock.sk_wmem_alloc from atomic_t to refcount_t")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_offload.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 11f69bbf9307..b6a2aa1dcf56 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -149,11 +149,19 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 	 * is freed by GSO engine
 	 */
 	if (copy_destructor) {
+		int delta;
+
 		swap(gso_skb->sk, skb->sk);
 		swap(gso_skb->destructor, skb->destructor);
 		sum_truesize += skb->truesize;
-		refcount_add(sum_truesize - gso_skb->truesize,
-			   &skb->sk->sk_wmem_alloc);
+		delta = sum_truesize - gso_skb->truesize;
+		/* In some pathological cases, delta can be negative.
+		 * We need to either use refcount_add() or refcount_sub_and_test()
+		 */
+		if (likely(delta >= 0))
+			refcount_add(delta, &skb->sk->sk_wmem_alloc);
+		else
+			WARN_ON_ONCE(refcount_sub_and_test(-delta, &skb->sk->sk_wmem_alloc));
 	}
 
 	delta = htonl(oldlen + (skb_tail_pointer(skb) -
-- 
2.13.6


From 5a49f6dc25e43e1f57808d094934cfa6d18fe686 Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Tue, 7 Nov 2017 15:33:43 -0800
Subject: [PATCH 13/22] tcp: fix tcp_fastretrans_alert warning

[ Upstream commit 0eb96bf754d7fa6635aa0b0f6650c74b8a6b1cc9 ]

This patch fixes the cause of an WARNING indicatng TCP has pending
retransmission in Open state in tcp_fastretrans_alert().

The root cause is a bad interaction between path mtu probing,
if enabled, and the RACK loss detection. Upong receiving a SACK
above the sequence of the MTU probing packet, RACK could mark the
probe packet lost in tcp_fastretrans_alert(), prior to calling
tcp_simple_retransmit().

tcp_simple_retransmit() only enters Loss state if it newly marks
the probe packet lost. If the probe packet is already identified as
lost by RACK, the sender remains in Open state with some packets
marked lost and retransmitted. Then the next SACK would trigger
the warning. The likely scenario is that the probe packet was
lost due to its size or network congestion. The actual impact of
this warning is small by potentially entering fast recovery an
ACK later.

The simple fix is always entering recovery (Loss) state if some
packet is marked lost during path MTU probing.

Fixes: a0370b3f3f2c ("tcp: enable RACK loss detection to trigger recovery")
Reported-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Reported-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Reported-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e92e5dbcb3d6..ffe96de8a079 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2613,7 +2613,6 @@ void tcp_simple_retransmit(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
 	unsigned int mss = tcp_current_mss(sk);
-	u32 prior_lost = tp->lost_out;
 
 	tcp_for_write_queue(skb, sk) {
 		if (skb == tcp_send_head(sk))
@@ -2630,7 +2629,7 @@ void tcp_simple_retransmit(struct sock *sk)
 
 	tcp_clear_retrans_hints_partial(tp);
 
-	if (prior_lost == tp->lost_out)
+	if (!tp->lost_out)
 		return;
 
 	if (tcp_is_reno(tp))
-- 
2.13.6


From 04fa97e05215e7cf4b4cefb101d05527cd55f7d4 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 9 Nov 2017 16:43:13 -0800
Subject: [PATCH 14/22] vlan: fix a use-after-free in vlan_device_event()

[ Upstream commit 052d41c01b3a2e3371d66de569717353af489d63 ]

After refcnt reaches zero, vlan_vid_del() could free
dev->vlan_info via RCU:

	RCU_INIT_POINTER(dev->vlan_info, NULL);
	call_rcu(&vlan_info->rcu, vlan_info_rcu_free);

However, the pointer 'grp' still points to that memory
since it is set before vlan_vid_del():

        vlan_info = rtnl_dereference(dev->vlan_info);
        if (!vlan_info)
                goto out;
        grp = &vlan_info->grp;

Depends on when that RCU callback is scheduled, we could
trigger a use-after-free in vlan_group_for_each_dev()
right following this vlan_vid_del().

Fix it by moving vlan_vid_del() before setting grp. This
is also symmetric to the vlan_vid_add() we call in
vlan_device_event().

Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Fixes: efc73f4bbc23 ("net: Fix memory leak - vlan_info struct")
Cc: Alexander Duyck <alexander.duyck@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Girish Moodalbail <girish.moodalbail@oracle.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Reviewed-by: Girish Moodalbail <girish.moodalbail@oracle.com>
Tested-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/8021q/vlan.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 9649579b5b9f..4a72ee4e2ae9 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -376,6 +376,9 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
 			dev->name);
 		vlan_vid_add(dev, htons(ETH_P_8021Q), 0);
 	}
+	if (event == NETDEV_DOWN &&
+	    (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER))
+		vlan_vid_del(dev, htons(ETH_P_8021Q), 0);
 
 	vlan_info = rtnl_dereference(dev->vlan_info);
 	if (!vlan_info)
@@ -423,9 +426,6 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
 		struct net_device *tmp;
 		LIST_HEAD(close_list);
 
-		if (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)
-			vlan_vid_del(dev, htons(ETH_P_8021Q), 0);
-
 		/* Put all VLANs for this dev in the down state too.  */
 		vlan_group_for_each_dev(grp, i, vlandev) {
 			flgs = vlandev->flags;
-- 
2.13.6


From cad25fc9a0bc7ea01cc28f36a9d1b8083c60f079 Mon Sep 17 00:00:00 2001
From: Huy Nguyen <huyn@mellanox.com>
Date: Tue, 26 Sep 2017 15:11:56 -0500
Subject: [PATCH 15/22] net/mlx5: Cancel health poll before sending panic
 teardown command

[ Upstream commit d2aa060d40fa060e963f9a356d43481e43ba3dac ]

After the panic teardown firmware command, health_care detects the error
in PCI bus and calls the mlx5_pci_err_detected. This health_care flow is
no longer needed because the panic teardown firmware command will bring
down the PCI bus communication with the HCA.

The solution is to cancel the health care timer and its pending
workqueue request before sending panic teardown firmware command.

Kernel trace:
mlx5_core 0033:01:00.0: Shutdown was called
mlx5_core 0033:01:00.0: health_care:154:(pid 9304): handling bad device here
mlx5_core 0033:01:00.0: mlx5_handle_bad_state:114:(pid 9304): NIC state 1
mlx5_core 0033:01:00.0: mlx5_pci_err_detected was called
mlx5_core 0033:01:00.0: mlx5_enter_error_state:96:(pid 9304): start
mlx5_3:mlx5_ib_event:3061:(pid 9304): warning: event on port 0
mlx5_core 0033:01:00.0: mlx5_enter_error_state:104:(pid 9304): end
Unable to handle kernel paging request for data at address 0x0000003f
Faulting instruction address: 0xc0080000434b8c80

Fixes: 8812c24d28f4 ('net/mlx5: Add fast unload support in shutdown flow')
Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 16885827367b..553bc230d70d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1545,9 +1545,16 @@ static int mlx5_try_fast_unload(struct mlx5_core_dev *dev)
 		return -EAGAIN;
 	}
 
+	/* Panic tear down fw command will stop the PCI bus communication
+	 * with the HCA, so the health polll is no longer needed.
+	 */
+	mlx5_drain_health_wq(dev);
+	mlx5_stop_health_poll(dev);
+
 	ret = mlx5_cmd_force_teardown_hca(dev);
 	if (ret) {
 		mlx5_core_dbg(dev, "Firmware couldn't do fast unload error: %d\n", ret);
+		mlx5_start_health_poll(dev);
 		return ret;
 	}
 
-- 
2.13.6


From 8c06d28dde26c8baf8112cab287d424e3a561730 Mon Sep 17 00:00:00 2001
From: Inbar Karmy <inbark@mellanox.com>
Date: Sun, 15 Oct 2017 17:30:59 +0300
Subject: [PATCH 16/22] net/mlx5e: Set page to null in case dma mapping fails

[ Upstream commit 2e50b2619538ea0224c037f6fa746023089e0654 ]

Currently, when dma mapping fails, put_page is called,
but the page is not set to null. Later, in the page_reuse treatment in
mlx5e_free_rx_descs(), mlx5e_page_release() is called for the second time,
improperly doing dma_unmap (for a non-mapped address) and an extra put_page.
Prevent this by nullifying the page pointer when dma_map fails.

Fixes: accd58833237 ("net/mlx5e: Introduce RX Page-Reuse")
Signed-off-by: Inbar Karmy <inbark@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Cc: kernel-team@fb.com
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 7344433259fc..1c513dc0105e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -213,22 +213,20 @@ static inline bool mlx5e_rx_cache_get(struct mlx5e_rq *rq,
 static inline int mlx5e_page_alloc_mapped(struct mlx5e_rq *rq,
 					  struct mlx5e_dma_info *dma_info)
 {
-	struct page *page;
-
 	if (mlx5e_rx_cache_get(rq, dma_info))
 		return 0;
 
-	page = dev_alloc_pages(rq->buff.page_order);
-	if (unlikely(!page))
+	dma_info->page = dev_alloc_pages(rq->buff.page_order);
+	if (unlikely(!dma_info->page))
 		return -ENOMEM;
 
-	dma_info->addr = dma_map_page(rq->pdev, page, 0,
+	dma_info->addr = dma_map_page(rq->pdev, dma_info->page, 0,
 				      RQ_PAGE_SIZE(rq), rq->buff.map_dir);
 	if (unlikely(dma_mapping_error(rq->pdev, dma_info->addr))) {
-		put_page(page);
+		put_page(dma_info->page);
+		dma_info->page = NULL;
 		return -ENOMEM;
 	}
-	dma_info->page = page;
 
 	return 0;
 }
-- 
2.13.6


From 0e242b199119b33eb1d61632f75c163a2dff2d18 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Thu, 9 Nov 2017 13:04:44 +0900
Subject: [PATCH 17/22] af_netlink: ensure that NLMSG_DONE never fails in dumps

[ Upstream commit 0642840b8bb008528dbdf929cec9f65ac4231ad0 ]

The way people generally use netlink_dump is that they fill in the skb
as much as possible, breaking when nla_put returns an error. Then, they
get called again and start filling out the next skb, and again, and so
forth. The mechanism at work here is the ability for the iterative
dumping function to detect when the skb is filled up and not fill it
past the brim, waiting for a fresh skb for the rest of the data.

However, if the attributes are small and nicely packed, it is possible
that a dump callback function successfully fills in attributes until the
skb is of size 4080 (libmnl's default page-sized receive buffer size).
The dump function completes, satisfied, and then, if it happens to be
that this is actually the last skb, and no further ones are to be sent,
then netlink_dump will add on the NLMSG_DONE part:

  nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE, sizeof(len), NLM_F_MULTI);

It is very important that netlink_dump does this, of course. However, in
this example, that call to nlmsg_put_answer will fail, because the
previous filling by the dump function did not leave it enough room. And
how could it possibly have done so? All of the nla_put variety of
functions simply check to see if the skb has enough tailroom,
independent of the context it is in.

In order to keep the important assumptions of all netlink dump users, it
is therefore important to give them an skb that has this end part of the
tail already reserved, so that the call to nlmsg_put_answer does not
fail. Otherwise, library authors are forced to find some bizarre sized
receive buffer that has a large modulo relative to the common sizes of
messages received, which is ugly and buggy.

This patch thus saves the NLMSG_DONE for an additional message, for the
case that things are dangerously close to the brim. This requires
keeping track of the errno from ->dump() across calls.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 17 +++++++++++------
 net/netlink/af_netlink.h |  1 +
 2 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 09c8dbbd2d70..2939a6b87c27 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2128,7 +2128,7 @@ static int netlink_dump(struct sock *sk)
 	struct sk_buff *skb = NULL;
 	struct nlmsghdr *nlh;
 	struct module *module;
-	int len, err = -ENOBUFS;
+	int err = -ENOBUFS;
 	int alloc_min_size;
 	int alloc_size;
 
@@ -2175,9 +2175,11 @@ static int netlink_dump(struct sock *sk)
 	skb_reserve(skb, skb_tailroom(skb) - alloc_size);
 	netlink_skb_set_owner_r(skb, sk);
 
-	len = cb->dump(skb, cb);
+	if (nlk->dump_done_errno > 0)
+		nlk->dump_done_errno = cb->dump(skb, cb);
 
-	if (len > 0) {
+	if (nlk->dump_done_errno > 0 ||
+	    skb_tailroom(skb) < nlmsg_total_size(sizeof(nlk->dump_done_errno))) {
 		mutex_unlock(nlk->cb_mutex);
 
 		if (sk_filter(sk, skb))
@@ -2187,13 +2189,15 @@ static int netlink_dump(struct sock *sk)
 		return 0;
 	}
 
-	nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE, sizeof(len), NLM_F_MULTI);
-	if (!nlh)
+	nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE,
+			       sizeof(nlk->dump_done_errno), NLM_F_MULTI);
+	if (WARN_ON(!nlh))
 		goto errout_skb;
 
 	nl_dump_check_consistent(cb, nlh);
 
-	memcpy(nlmsg_data(nlh), &len, sizeof(len));
+	memcpy(nlmsg_data(nlh), &nlk->dump_done_errno,
+	       sizeof(nlk->dump_done_errno));
 
 	if (sk_filter(sk, skb))
 		kfree_skb(skb);
@@ -2265,6 +2269,7 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 	}
 
 	nlk->cb_running = true;
+	nlk->dump_done_errno = INT_MAX;
 
 	mutex_unlock(nlk->cb_mutex);
 
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index 3490f2430532..8908fc2d3de0 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -33,6 +33,7 @@ struct netlink_sock {
 	wait_queue_head_t	wait;
 	bool			bound;
 	bool			cb_running;
+	int			dump_done_errno;
 	struct netlink_callback	cb;
 	struct mutex		*cb_mutex;
 	struct mutex		cb_def_mutex;
-- 
2.13.6


From 50587c57bd7ac492787b7465d1bb1ed20b07f29c Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sat, 11 Nov 2017 19:58:50 +0800
Subject: [PATCH 18/22] vxlan: fix the issue that neigh proxy blocks all icmpv6
 packets

[ Upstream commit 8bff3685a4bbf175a96bc6a528f13455d8d38244 ]

Commit f1fb08f6337c ("vxlan: fix ND proxy when skb doesn't have transport
header offset") removed icmp6_code and icmp6_type check before calling
neigh_reduce when doing neigh proxy.

It means all icmpv6 packets would be blocked by this, not only ns packet.
In Jianlin's env, even ping6 couldn't work through it.

This patch is to bring the icmp6_code and icmp6_type check back and also
removed the same check from neigh_reduce().

Fixes: f1fb08f6337c ("vxlan: fix ND proxy when skb doesn't have transport header offset")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Reviewed-by: Vincent Bernat <vincent@bernat.im>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 31 +++++++++++++------------------
 1 file changed, 13 insertions(+), 18 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index e17baac70f43..436154720bf8 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1632,26 +1632,19 @@ static struct sk_buff *vxlan_na_create(struct sk_buff *request,
 static int neigh_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
-	struct nd_msg *msg;
-	const struct ipv6hdr *iphdr;
 	const struct in6_addr *daddr;
-	struct neighbour *n;
+	const struct ipv6hdr *iphdr;
 	struct inet6_dev *in6_dev;
+	struct neighbour *n;
+	struct nd_msg *msg;
 
 	in6_dev = __in6_dev_get(dev);
 	if (!in6_dev)
 		goto out;
 
-	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr) + sizeof(struct nd_msg)))
-		goto out;
-
 	iphdr = ipv6_hdr(skb);
 	daddr = &iphdr->daddr;
-
 	msg = (struct nd_msg *)(iphdr + 1);
-	if (msg->icmph.icmp6_code != 0 ||
-	    msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION)
-		goto out;
 
 	if (ipv6_addr_loopback(daddr) ||
 	    ipv6_addr_is_multicast(&msg->target))
@@ -2258,11 +2251,11 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_rdst *rdst, *fdst = NULL;
 	const struct ip_tunnel_info *info;
-	struct ethhdr *eth;
 	bool did_rsc = false;
-	struct vxlan_rdst *rdst, *fdst = NULL;
 	struct vxlan_fdb *f;
+	struct ethhdr *eth;
 	__be32 vni = 0;
 
 	info = skb_tunnel_info(skb);
@@ -2287,12 +2280,14 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 		if (ntohs(eth->h_proto) == ETH_P_ARP)
 			return arp_reduce(dev, skb, vni);
 #if IS_ENABLED(CONFIG_IPV6)
-		else if (ntohs(eth->h_proto) == ETH_P_IPV6) {
-			struct ipv6hdr *hdr, _hdr;
-			if ((hdr = skb_header_pointer(skb,
-						      skb_network_offset(skb),
-						      sizeof(_hdr), &_hdr)) &&
-			    hdr->nexthdr == IPPROTO_ICMPV6)
+		else if (ntohs(eth->h_proto) == ETH_P_IPV6 &&
+			 pskb_may_pull(skb, sizeof(struct ipv6hdr) +
+					    sizeof(struct nd_msg)) &&
+			 ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) {
+			struct nd_msg *m = (struct nd_msg *)(ipv6_hdr(skb) + 1);
+
+			if (m->icmph.icmp6_code == 0 &&
+			    m->icmph.icmp6_type == NDISC_NEIGHBOUR_SOLICITATION)
 				return neigh_reduce(dev, skb, vni);
 		}
 #endif
-- 
2.13.6


From a43eb8c8be253a3a7ef8482eb46c3c99dd29332e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Wed, 15 Nov 2017 09:35:02 +0100
Subject: [PATCH 19/22] net: cdc_ncm: GetNtbFormat endian fix
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 6314dab4b8fb8493d810e175cb340376052c69b6 ]

The GetNtbFormat and SetNtbFormat requests operate on 16 bit little
endian values. We get away with ignoring this most of the time, because
we only care about USB_CDC_NCM_NTB16_FORMAT which is 0x0000.  This
fails for USB_CDC_NCM_NTB32_FORMAT.

Fix comparison between LE value from device and constant by converting
the constant to LE.

Reported-by: Ben Hutchings <ben.hutchings@codethink.co.uk>
Fixes: 2b02c20ce0c2 ("cdc_ncm: Set NTB format again after altsetting switch for Huawei devices")
Cc: Enrico Mioso <mrkiko.rs@gmail.com>
Cc: Christian Panton <christian@panton.org>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Acked-By: Enrico Mioso <mrkiko.rs@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ncm.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 9c80e80c5493..8d5e97251efe 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -771,7 +771,7 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_
 	int err;
 	u8 iface_no;
 	struct usb_cdc_parsed_header hdr;
-	u16 curr_ntb_format;
+	__le16 curr_ntb_format;
 
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
@@ -889,7 +889,7 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_
 			goto error2;
 		}
 
-		if (curr_ntb_format == USB_CDC_NCM_NTB32_FORMAT) {
+		if (curr_ntb_format == cpu_to_le16(USB_CDC_NCM_NTB32_FORMAT)) {
 			dev_info(&intf->dev, "resetting NTB format to 16-bit");
 			err = usbnet_write_cmd(dev, USB_CDC_SET_NTB_FORMAT,
 					       USB_TYPE_CLASS | USB_DIR_OUT
-- 
2.13.6


From b5a63c8735a6f088c29549a86dd54f5bab3a31b4 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 17 Oct 2017 23:26:10 +0800
Subject: [PATCH 20/22] sctp: do not peel off an assoc from one netns to
 another one

[ Upstream commit df80cd9b28b9ebaa284a41df611dbf3a2d05ca74 ]

Now when peeling off an association to the sock in another netns, all
transports in this assoc are not to be rehashed and keep use the old
key in hashtable.

As a transport uses sk->net as the hash key to insert into hashtable,
it would miss removing these transports from hashtable due to the new
netns when closing the sock and all transports are being freeed, then
later an use-after-free issue could be caused when looking up an asoc
and dereferencing those transports.

This is a very old issue since very beginning, ChunYu found it with
syzkaller fuzz testing with this series:

  socket$inet6_sctp()
  bind$inet6()
  sendto$inet6()
  unshare(0x40000000)
  getsockopt$inet_sctp6_SCTP_GET_ASSOC_ID_LIST()
  getsockopt$inet_sctp6_SCTP_SOCKOPT_PEELOFF()

This patch is to block this call when peeling one assoc off from one
netns to another one, so that the netns of all transport would not
go out-sync with the key in hashtable.

Note that this patch didn't fix it by rehashing transports, as it's
difficult to handle the situation when the tuple is already in use
in the new netns. Besides, no one would like to peel off one assoc
to another netns, considering ipaddrs, ifaces, etc. are usually
different.

Reported-by: ChunYu Wang <chunwang@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 3d79085eb4e0..083da13e1af4 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4924,6 +4924,10 @@ int sctp_do_peeloff(struct sock *sk, sctp_assoc_t id, struct socket **sockp)
 	struct socket *sock;
 	int err = 0;
 
+	/* Do not peel off from one netns to another one. */
+	if (!net_eq(current->nsproxy->net_ns, sock_net(sk)))
+		return -EINVAL;
+
 	if (!asoc)
 		return -EINVAL;
 
-- 
2.13.6


From dd26b1eae61a45eecaa76e0b624dacbd55749d75 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhc@lemote.com>
Date: Thu, 16 Nov 2017 11:07:15 +0800
Subject: [PATCH 21/22] fealnx: Fix building error on MIPS

[ Upstream commit cc54c1d32e6a4bb3f116721abf900513173e4d02 ]

This patch try to fix the building error on MIPS. The reason is MIPS
has already defined the LONG macro, which conflicts with the LONG enum
in drivers/net/ethernet/fealnx.c.

Signed-off-by: Huacai Chen <chenhc@lemote.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/fealnx.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/fealnx.c b/drivers/net/ethernet/fealnx.c
index e92859dab7ae..e191c4ebeaf4 100644
--- a/drivers/net/ethernet/fealnx.c
+++ b/drivers/net/ethernet/fealnx.c
@@ -257,8 +257,8 @@ enum rx_desc_status_bits {
 	RXFSD = 0x00000800,	/* first descriptor */
 	RXLSD = 0x00000400,	/* last descriptor */
 	ErrorSummary = 0x80,	/* error summary */
-	RUNT = 0x40,		/* runt packet received */
-	LONG = 0x20,		/* long packet received */
+	RUNTPKT = 0x40,		/* runt packet received */
+	LONGPKT = 0x20,		/* long packet received */
 	FAE = 0x10,		/* frame align error */
 	CRC = 0x08,		/* crc error */
 	RXER = 0x04,		/* receive error */
@@ -1632,7 +1632,7 @@ static int netdev_rx(struct net_device *dev)
 					       dev->name, rx_status);
 
 				dev->stats.rx_errors++;	/* end of a packet. */
-				if (rx_status & (LONG | RUNT))
+				if (rx_status & (LONGPKT | RUNTPKT))
 					dev->stats.rx_length_errors++;
 				if (rx_status & RXER)
 					dev->stats.rx_frame_errors++;
-- 
2.13.6


From 481a3dd8ca718cd72bd07b38a3b49b65d04843eb Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Wed, 15 Nov 2017 22:17:48 -0600
Subject: [PATCH 22/22] net/sctp: Always set scope_id in sctp_inet6_skb_msgname

[ Upstream commit 7c8a61d9ee1df0fb4747879fa67a99614eb62fec ]

Alexandar Potapenko while testing the kernel with KMSAN and syzkaller
discovered that in some configurations sctp would leak 4 bytes of
kernel stack.

Working with his reproducer I discovered that those 4 bytes that
are leaked is the scope id of an ipv6 address returned by recvmsg.

With a little code inspection and a shrewd guess I discovered that
sctp_inet6_skb_msgname only initializes the scope_id field for link
local ipv6 addresses to the interface index the link local address
pertains to instead of initializing the scope_id field for all ipv6
addresses.

That is almost reasonable as scope_id's are meaniningful only for link
local addresses.  Set the scope_id in all other cases to 0 which is
not a valid interface index to make it clear there is nothing useful
in the scope_id field.

There should be no danger of breaking userspace as the stack leak
guaranteed that previously meaningless random data was being returned.

Fixes: 372f525b495c ("SCTP:  Resync with LKSCTP tree.")
History-tree: https://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git
Reported-by: Alexander Potapenko <glider@google.com>
Tested-by: Alexander Potapenko <glider@google.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ipv6.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 1344e3a411ae..edb462b0b73b 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -807,9 +807,10 @@ static void sctp_inet6_skb_msgname(struct sk_buff *skb, char *msgname,
 		addr->v6.sin6_flowinfo = 0;
 		addr->v6.sin6_port = sh->source;
 		addr->v6.sin6_addr = ipv6_hdr(skb)->saddr;
-		if (ipv6_addr_type(&addr->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) {
+		if (ipv6_addr_type(&addr->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL)
 			addr->v6.sin6_scope_id = sctp_v6_skb_iif(skb);
-		}
+		else
+			addr->v6.sin6_scope_id = 0;
 	}
 
 	*addr_len = sctp_v6_addr_to_user(sctp_sk(skb->sk), addr);
-- 
2.13.6


[-- Attachment #4: net_414.mbox --]
[-- Type: Application/Octet-Stream, Size: 13827 bytes --]

From b0ccc2b20c9e1dcdf6a9e9dbe0d2bb94a4db388f Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Thu, 9 Nov 2017 13:04:44 +0900
Subject: [PATCH 1/5] af_netlink: ensure that NLMSG_DONE never fails in dumps

[ Upstream commit 0642840b8bb008528dbdf929cec9f65ac4231ad0 ]

The way people generally use netlink_dump is that they fill in the skb
as much as possible, breaking when nla_put returns an error. Then, they
get called again and start filling out the next skb, and again, and so
forth. The mechanism at work here is the ability for the iterative
dumping function to detect when the skb is filled up and not fill it
past the brim, waiting for a fresh skb for the rest of the data.

However, if the attributes are small and nicely packed, it is possible
that a dump callback function successfully fills in attributes until the
skb is of size 4080 (libmnl's default page-sized receive buffer size).
The dump function completes, satisfied, and then, if it happens to be
that this is actually the last skb, and no further ones are to be sent,
then netlink_dump will add on the NLMSG_DONE part:

  nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE, sizeof(len), NLM_F_MULTI);

It is very important that netlink_dump does this, of course. However, in
this example, that call to nlmsg_put_answer will fail, because the
previous filling by the dump function did not leave it enough room. And
how could it possibly have done so? All of the nla_put variety of
functions simply check to see if the skb has enough tailroom,
independent of the context it is in.

In order to keep the important assumptions of all netlink dump users, it
is therefore important to give them an skb that has this end part of the
tail already reserved, so that the call to nlmsg_put_answer does not
fail. Otherwise, library authors are forced to find some bizarre sized
receive buffer that has a large modulo relative to the common sizes of
messages received, which is ugly and buggy.

This patch thus saves the NLMSG_DONE for an additional message, for the
case that things are dangerously close to the brim. This requires
keeping track of the errno from ->dump() across calls.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 17 +++++++++++------
 net/netlink/af_netlink.h |  1 +
 2 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index b93148e8e9fb..15c99dfa3d72 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2136,7 +2136,7 @@ static int netlink_dump(struct sock *sk)
 	struct sk_buff *skb = NULL;
 	struct nlmsghdr *nlh;
 	struct module *module;
-	int len, err = -ENOBUFS;
+	int err = -ENOBUFS;
 	int alloc_min_size;
 	int alloc_size;
 
@@ -2183,9 +2183,11 @@ static int netlink_dump(struct sock *sk)
 	skb_reserve(skb, skb_tailroom(skb) - alloc_size);
 	netlink_skb_set_owner_r(skb, sk);
 
-	len = cb->dump(skb, cb);
+	if (nlk->dump_done_errno > 0)
+		nlk->dump_done_errno = cb->dump(skb, cb);
 
-	if (len > 0) {
+	if (nlk->dump_done_errno > 0 ||
+	    skb_tailroom(skb) < nlmsg_total_size(sizeof(nlk->dump_done_errno))) {
 		mutex_unlock(nlk->cb_mutex);
 
 		if (sk_filter(sk, skb))
@@ -2195,13 +2197,15 @@ static int netlink_dump(struct sock *sk)
 		return 0;
 	}
 
-	nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE, sizeof(len), NLM_F_MULTI);
-	if (!nlh)
+	nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE,
+			       sizeof(nlk->dump_done_errno), NLM_F_MULTI);
+	if (WARN_ON(!nlh))
 		goto errout_skb;
 
 	nl_dump_check_consistent(cb, nlh);
 
-	memcpy(nlmsg_data(nlh), &len, sizeof(len));
+	memcpy(nlmsg_data(nlh), &nlk->dump_done_errno,
+	       sizeof(nlk->dump_done_errno));
 
 	if (sk_filter(sk, skb))
 		kfree_skb(skb);
@@ -2273,6 +2277,7 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 	}
 
 	nlk->cb_running = true;
+	nlk->dump_done_errno = INT_MAX;
 
 	mutex_unlock(nlk->cb_mutex);
 
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index 028188597eaa..962de7b3c023 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -34,6 +34,7 @@ struct netlink_sock {
 	wait_queue_head_t	wait;
 	bool			bound;
 	bool			cb_running;
+	int			dump_done_errno;
 	struct netlink_callback	cb;
 	struct mutex		*cb_mutex;
 	struct mutex		cb_def_mutex;
-- 
2.13.6


From 581e2af4c34bb8999615a53cb03b46b001f5609c Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sat, 11 Nov 2017 19:58:50 +0800
Subject: [PATCH 2/5] vxlan: fix the issue that neigh proxy blocks all icmpv6
 packets

[ Upstream commit 8bff3685a4bbf175a96bc6a528f13455d8d38244 ]

Commit f1fb08f6337c ("vxlan: fix ND proxy when skb doesn't have transport
header offset") removed icmp6_code and icmp6_type check before calling
neigh_reduce when doing neigh proxy.

It means all icmpv6 packets would be blocked by this, not only ns packet.
In Jianlin's env, even ping6 couldn't work through it.

This patch is to bring the icmp6_code and icmp6_type check back and also
removed the same check from neigh_reduce().

Fixes: f1fb08f6337c ("vxlan: fix ND proxy when skb doesn't have transport header offset")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Reviewed-by: Vincent Bernat <vincent@bernat.im>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 31 +++++++++++++------------------
 1 file changed, 13 insertions(+), 18 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index d7c49cf1d5e9..a2f4e52fadb5 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1623,26 +1623,19 @@ static struct sk_buff *vxlan_na_create(struct sk_buff *request,
 static int neigh_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
-	struct nd_msg *msg;
-	const struct ipv6hdr *iphdr;
 	const struct in6_addr *daddr;
-	struct neighbour *n;
+	const struct ipv6hdr *iphdr;
 	struct inet6_dev *in6_dev;
+	struct neighbour *n;
+	struct nd_msg *msg;
 
 	in6_dev = __in6_dev_get(dev);
 	if (!in6_dev)
 		goto out;
 
-	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr) + sizeof(struct nd_msg)))
-		goto out;
-
 	iphdr = ipv6_hdr(skb);
 	daddr = &iphdr->daddr;
-
 	msg = (struct nd_msg *)(iphdr + 1);
-	if (msg->icmph.icmp6_code != 0 ||
-	    msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION)
-		goto out;
 
 	if (ipv6_addr_loopback(daddr) ||
 	    ipv6_addr_is_multicast(&msg->target))
@@ -2240,11 +2233,11 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_rdst *rdst, *fdst = NULL;
 	const struct ip_tunnel_info *info;
-	struct ethhdr *eth;
 	bool did_rsc = false;
-	struct vxlan_rdst *rdst, *fdst = NULL;
 	struct vxlan_fdb *f;
+	struct ethhdr *eth;
 	__be32 vni = 0;
 
 	info = skb_tunnel_info(skb);
@@ -2269,12 +2262,14 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 		if (ntohs(eth->h_proto) == ETH_P_ARP)
 			return arp_reduce(dev, skb, vni);
 #if IS_ENABLED(CONFIG_IPV6)
-		else if (ntohs(eth->h_proto) == ETH_P_IPV6) {
-			struct ipv6hdr *hdr, _hdr;
-			if ((hdr = skb_header_pointer(skb,
-						      skb_network_offset(skb),
-						      sizeof(_hdr), &_hdr)) &&
-			    hdr->nexthdr == IPPROTO_ICMPV6)
+		else if (ntohs(eth->h_proto) == ETH_P_IPV6 &&
+			 pskb_may_pull(skb, sizeof(struct ipv6hdr) +
+					    sizeof(struct nd_msg)) &&
+			 ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) {
+			struct nd_msg *m = (struct nd_msg *)(ipv6_hdr(skb) + 1);
+
+			if (m->icmph.icmp6_code == 0 &&
+			    m->icmph.icmp6_type == NDISC_NEIGHBOUR_SOLICITATION)
 				return neigh_reduce(dev, skb, vni);
 		}
 #endif
-- 
2.13.6


From 66b586497ce3ea74b6837334f7bdf34e634aa6d9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Wed, 15 Nov 2017 09:35:02 +0100
Subject: [PATCH 3/5] net: cdc_ncm: GetNtbFormat endian fix
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 6314dab4b8fb8493d810e175cb340376052c69b6 ]

The GetNtbFormat and SetNtbFormat requests operate on 16 bit little
endian values. We get away with ignoring this most of the time, because
we only care about USB_CDC_NCM_NTB16_FORMAT which is 0x0000.  This
fails for USB_CDC_NCM_NTB32_FORMAT.

Fix comparison between LE value from device and constant by converting
the constant to LE.

Reported-by: Ben Hutchings <ben.hutchings@codethink.co.uk>
Fixes: 2b02c20ce0c2 ("cdc_ncm: Set NTB format again after altsetting switch for Huawei devices")
Cc: Enrico Mioso <mrkiko.rs@gmail.com>
Cc: Christian Panton <christian@panton.org>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Acked-By: Enrico Mioso <mrkiko.rs@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ncm.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 47cab1bde065..9e1b74590682 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -771,7 +771,7 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_
 	int err;
 	u8 iface_no;
 	struct usb_cdc_parsed_header hdr;
-	u16 curr_ntb_format;
+	__le16 curr_ntb_format;
 
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
@@ -889,7 +889,7 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_
 			goto error2;
 		}
 
-		if (curr_ntb_format == USB_CDC_NCM_NTB32_FORMAT) {
+		if (curr_ntb_format == cpu_to_le16(USB_CDC_NCM_NTB32_FORMAT)) {
 			dev_info(&intf->dev, "resetting NTB format to 16-bit");
 			err = usbnet_write_cmd(dev, USB_CDC_SET_NTB_FORMAT,
 					       USB_TYPE_CLASS | USB_DIR_OUT
-- 
2.13.6


From 8240fc7b75178976fc35515d0319c4b486e6371f Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhc@lemote.com>
Date: Thu, 16 Nov 2017 11:07:15 +0800
Subject: [PATCH 4/5] fealnx: Fix building error on MIPS

[ Upstream commit cc54c1d32e6a4bb3f116721abf900513173e4d02 ]

This patch try to fix the building error on MIPS. The reason is MIPS
has already defined the LONG macro, which conflicts with the LONG enum
in drivers/net/ethernet/fealnx.c.

Signed-off-by: Huacai Chen <chenhc@lemote.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/fealnx.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/fealnx.c b/drivers/net/ethernet/fealnx.c
index e92859dab7ae..e191c4ebeaf4 100644
--- a/drivers/net/ethernet/fealnx.c
+++ b/drivers/net/ethernet/fealnx.c
@@ -257,8 +257,8 @@ enum rx_desc_status_bits {
 	RXFSD = 0x00000800,	/* first descriptor */
 	RXLSD = 0x00000400,	/* last descriptor */
 	ErrorSummary = 0x80,	/* error summary */
-	RUNT = 0x40,		/* runt packet received */
-	LONG = 0x20,		/* long packet received */
+	RUNTPKT = 0x40,		/* runt packet received */
+	LONGPKT = 0x20,		/* long packet received */
 	FAE = 0x10,		/* frame align error */
 	CRC = 0x08,		/* crc error */
 	RXER = 0x04,		/* receive error */
@@ -1632,7 +1632,7 @@ static int netdev_rx(struct net_device *dev)
 					       dev->name, rx_status);
 
 				dev->stats.rx_errors++;	/* end of a packet. */
-				if (rx_status & (LONG | RUNT))
+				if (rx_status & (LONGPKT | RUNTPKT))
 					dev->stats.rx_length_errors++;
 				if (rx_status & RXER)
 					dev->stats.rx_frame_errors++;
-- 
2.13.6


From 5c2a8c410d140724f381e4173b09f15a6579b9ab Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Wed, 15 Nov 2017 22:17:48 -0600
Subject: [PATCH 5/5] net/sctp: Always set scope_id in sctp_inet6_skb_msgname

[ Upstream commit 7c8a61d9ee1df0fb4747879fa67a99614eb62fec ]

Alexandar Potapenko while testing the kernel with KMSAN and syzkaller
discovered that in some configurations sctp would leak 4 bytes of
kernel stack.

Working with his reproducer I discovered that those 4 bytes that
are leaked is the scope id of an ipv6 address returned by recvmsg.

With a little code inspection and a shrewd guess I discovered that
sctp_inet6_skb_msgname only initializes the scope_id field for link
local ipv6 addresses to the interface index the link local address
pertains to instead of initializing the scope_id field for all ipv6
addresses.

That is almost reasonable as scope_id's are meaniningful only for link
local addresses.  Set the scope_id in all other cases to 0 which is
not a valid interface index to make it clear there is nothing useful
in the scope_id field.

There should be no danger of breaking userspace as the stack leak
guaranteed that previously meaningless random data was being returned.

Fixes: 372f525b495c ("SCTP:  Resync with LKSCTP tree.")
History-tree: https://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git
Reported-by: Alexander Potapenko <glider@google.com>
Tested-by: Alexander Potapenko <glider@google.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ipv6.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index a6dfa86c0201..3b18085e3b10 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -807,9 +807,10 @@ static void sctp_inet6_skb_msgname(struct sk_buff *skb, char *msgname,
 		addr->v6.sin6_flowinfo = 0;
 		addr->v6.sin6_port = sh->source;
 		addr->v6.sin6_addr = ipv6_hdr(skb)->saddr;
-		if (ipv6_addr_type(&addr->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) {
+		if (ipv6_addr_type(&addr->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL)
 			addr->v6.sin6_scope_id = sctp_v6_skb_iif(skb);
-		}
+		else
+			addr->v6.sin6_scope_id = 0;
 	}
 
 	*addr_len = sctp_v6_addr_to_user(sctp_sk(skb->sk), addr);
-- 
2.13.6

Re: [PATCHES] Networking

[Greg KH]

On Mon, Nov 20, 2017 at 08:47:27PM +0900, David Miller wrote:
> 
> Please queue up the following networking fixes for 4.9.x,
> 4.13.x, and 4.14.x -stable, respectively.

Wonderful, thanks for these, they are all now queued up.

Note, you don't have to do anything for 4.13.x anymore, I'll be marking
it end-of-life in a few days or so.

thanks again,

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 106 bytes --]


Please queue up the following networking bug fixes for v4.9 and v4.14 -stable,
respectively.

Thank you!

[-- Attachment #2: net_49.mbox --]
[-- Type: Application/Octet-Stream, Size: 48430 bytes --]

From a4abd0064a6854a33c43f3401528a199add50cb2 Mon Sep 17 00:00:00 2001
From: Sebastian Sjoholm <ssjoholm@mac.com>
Date: Mon, 20 Nov 2017 19:05:17 +0100
Subject: [PATCH 01/15] net: qmi_wwan: add Quectel BG96 2c7c:0296
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit f9409e7f086fa6c4623769b4b2f4f17a024d8143 ]

Quectel BG96 is an Qualcomm MDM9206 based IoT modem, supporting both
CAT-M and NB-IoT. Tested hardware is BG96 mounted on Quectel development
board (EVB). The USB id is added to qmi_wwan.c to allow QMI
communication with the BG96.

Signed-off-by: Sebastian Sjoholm <ssjoholm@mac.com>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 9cf11c83993a..97a16e23c19a 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -936,6 +936,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1e0e, 0x9001, 5)},	/* SIMCom 7230E */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0125, 4)},	/* Quectel EC25, EC20 R2.0  Mini PCIe */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0121, 4)},	/* Quectel EC21 Mini PCIe */
+	{QMI_FIXED_INTF(0x2c7c, 0x0296, 4)},	/* Quectel BG96 */
 
 	/* 4. Gobi 1000 devices */
 	{QMI_GOBI1K_DEVICE(0x05c6, 0x9212)},	/* Acer Gobi Modem Device */
-- 
2.14.3


From a9e2040430b849146d8ec231486ca540162415b1 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Wed, 18 Oct 2017 17:40:17 +0200
Subject: [PATCH 02/15] s390/qeth: fix early exit from error path

[ Upstream commit 83cf79a2fec3cf499eb6cb9eb608656fc2a82776 ]

When the allocation of the addr buffer fails, we need to free
our refcount on the inetdevice before returning.

Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_l3_main.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 03a2619166ca..204edb0b69a5 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -1593,7 +1593,7 @@ static void qeth_l3_free_vlan_addresses4(struct qeth_card *card,
 
 	addr = qeth_l3_get_addr_buffer(QETH_PROT_IPV4);
 	if (!addr)
-		return;
+		goto out;
 
 	spin_lock_bh(&card->ip_lock);
 
@@ -1607,6 +1607,7 @@ static void qeth_l3_free_vlan_addresses4(struct qeth_card *card,
 	spin_unlock_bh(&card->ip_lock);
 
 	kfree(addr);
+out:
 	in_dev_put(in_dev);
 }
 
@@ -1631,7 +1632,7 @@ static void qeth_l3_free_vlan_addresses6(struct qeth_card *card,
 
 	addr = qeth_l3_get_addr_buffer(QETH_PROT_IPV6);
 	if (!addr)
-		return;
+		goto out;
 
 	spin_lock_bh(&card->ip_lock);
 
@@ -1646,6 +1647,7 @@ static void qeth_l3_free_vlan_addresses6(struct qeth_card *card,
 	spin_unlock_bh(&card->ip_lock);
 
 	kfree(addr);
+out:
 	in6_dev_put(in6_dev);
 #endif /* CONFIG_QETH_IPV6 */
 }
-- 
2.14.3


From 296253a86f521e1dc269db014e7e321bcff85833 Mon Sep 17 00:00:00 2001
From: Jon Maloy <jon.maloy@ericsson.com>
Date: Mon, 4 Dec 2017 22:00:20 +0100
Subject: [PATCH 03/15] tipc: fix memory leak in tipc_accept_from_sock()

[ Upstream commit a7d5f107b4978e08eeab599ee7449af34d034053 ]

When the function tipc_accept_from_sock() fails to create an instance of
struct tipc_subscriber it omits to free the already created instance of
struct tipc_conn instance before it returns.

We fix that with this commit.

Reported-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/server.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/tipc/server.c b/net/tipc/server.c
index 3cd6402e812c..f4c1b18c5fb0 100644
--- a/net/tipc/server.c
+++ b/net/tipc/server.c
@@ -313,6 +313,7 @@ static int tipc_accept_from_sock(struct tipc_conn *con)
 	newcon->usr_data = s->tipc_conn_new(newcon->conid);
 	if (!newcon->usr_data) {
 		sock_release(newsock);
+		conn_put(newcon);
 		return -ENOMEM;
 	}
 
-- 
2.14.3


From 5456f030cc4564d7558064f45231dd32413e7e5b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?H=C3=A5kon=20Bugge?= <Haakon.Bugge@oracle.com>
Date: Wed, 6 Dec 2017 17:18:28 +0100
Subject: [PATCH 04/15] rds: Fix NULL pointer dereference in __rds_rdma_map
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit f3069c6d33f6ae63a1668737bc78aaaa51bff7ca ]

This is a fix for syzkaller719569, where memory registration was
attempted without any underlying transport being loaded.

Analysis of the case reveals that it is the setsockopt() RDS_GET_MR
(2) and RDS_GET_MR_FOR_DEST (7) that are vulnerable.

Here is an example stack trace when the bug is hit:

BUG: unable to handle kernel NULL pointer dereference at 00000000000000c0
IP: __rds_rdma_map+0x36/0x440 [rds]
PGD 2f93d03067 P4D 2f93d03067 PUD 2f93d02067 PMD 0
Oops: 0000 [#1] SMP
Modules linked in: bridge stp llc tun rpcsec_gss_krb5 nfsv4
dns_resolver nfs fscache rds binfmt_misc sb_edac intel_powerclamp
coretemp kvm_intel kvm irqbypass crct10dif_pclmul c rc32_pclmul
ghash_clmulni_intel pcbc aesni_intel crypto_simd glue_helper cryptd
iTCO_wdt mei_me sg iTCO_vendor_support ipmi_si mei ipmi_devintf nfsd
shpchp pcspkr i2c_i801 ioatd ma ipmi_msghandler wmi lpc_ich mfd_core
auth_rpcgss nfs_acl lockd grace sunrpc ip_tables ext4 mbcache jbd2
mgag200 i2c_algo_bit drm_kms_helper ixgbe syscopyarea ahci sysfillrect
sysimgblt libahci mdio fb_sys_fops ttm ptp libata sd_mod mlx4_core drm
crc32c_intel pps_core megaraid_sas i2c_core dca dm_mirror
dm_region_hash dm_log dm_mod
CPU: 48 PID: 45787 Comm: repro_set2 Not tainted 4.14.2-3.el7uek.x86_64 #2
Hardware name: Oracle Corporation ORACLE SERVER X5-2L/ASM,MOBO TRAY,2U, BIOS 31110000 03/03/2017
task: ffff882f9190db00 task.stack: ffffc9002b994000
RIP: 0010:__rds_rdma_map+0x36/0x440 [rds]
RSP: 0018:ffffc9002b997df0 EFLAGS: 00010202
RAX: 0000000000000000 RBX: ffff882fa2182580 RCX: 0000000000000000
RDX: 0000000000000000 RSI: ffffc9002b997e40 RDI: ffff882fa2182580
RBP: ffffc9002b997e30 R08: 0000000000000000 R09: 0000000000000002
R10: ffff885fb29e3838 R11: 0000000000000000 R12: ffff882fa2182580
R13: ffff882fa2182580 R14: 0000000000000002 R15: 0000000020000ffc
FS:  00007fbffa20b700(0000) GS:ffff882fbfb80000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000000000c0 CR3: 0000002f98a66006 CR4: 00000000001606e0
Call Trace:
 rds_get_mr+0x56/0x80 [rds]
 rds_setsockopt+0x172/0x340 [rds]
 ? __fget_light+0x25/0x60
 ? __fdget+0x13/0x20
 SyS_setsockopt+0x80/0xe0
 do_syscall_64+0x67/0x1b0
 entry_SYSCALL64_slow_path+0x25/0x25
RIP: 0033:0x7fbff9b117f9
RSP: 002b:00007fbffa20aed8 EFLAGS: 00000293 ORIG_RAX: 0000000000000036
RAX: ffffffffffffffda RBX: 00000000000c84a4 RCX: 00007fbff9b117f9
RDX: 0000000000000002 RSI: 0000400000000114 RDI: 000000000000109b
RBP: 00007fbffa20af10 R08: 0000000000000020 R09: 00007fbff9dd7860
R10: 0000000020000ffc R11: 0000000000000293 R12: 0000000000000000
R13: 00007fbffa20b9c0 R14: 00007fbffa20b700 R15: 0000000000000021

Code: 41 56 41 55 49 89 fd 41 54 53 48 83 ec 18 8b 87 f0 02 00 00 48
89 55 d0 48 89 4d c8 85 c0 0f 84 2d 03 00 00 48 8b 87 00 03 00 00 <48>
83 b8 c0 00 00 00 00 0f 84 25 03 00 0 0 48 8b 06 48 8b 56 08

The fix is to check the existence of an underlying transport in
__rds_rdma_map().

Signed-off-by: Håkon Bugge <haakon.bugge@oracle.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/rdma.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/rds/rdma.c b/net/rds/rdma.c
index 60e90f761838..de8496e60735 100644
--- a/net/rds/rdma.c
+++ b/net/rds/rdma.c
@@ -183,7 +183,7 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args,
 	long i;
 	int ret;
 
-	if (rs->rs_bound_addr == 0) {
+	if (rs->rs_bound_addr == 0 || !rs->rs_transport) {
 		ret = -ENOTCONN; /* XXX not a great errno */
 		goto out;
 	}
-- 
2.14.3


From 45b5ae6e0fcc2cc51022ef832b611cba38e54880 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Thu, 30 Nov 2017 10:41:14 +0800
Subject: [PATCH 05/15] sit: update frag_off info

[ Upstream commit f859b4af1c52493ec21173ccc73d0b60029b5b88 ]

After parsing the sit netlink change info, we forget to update frag_off in
ipip6_tunnel_update(). Fix it by assigning frag_off with new value.

Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 40d740572354..db6d437002a6 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1085,6 +1085,7 @@ static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p)
 	ipip6_tunnel_link(sitn, t);
 	t->parms.iph.ttl = p->iph.ttl;
 	t->parms.iph.tos = p->iph.tos;
+	t->parms.iph.frag_off = p->iph.frag_off;
 	if (t->parms.link != p->link) {
 		t->parms.link = p->link;
 		ipip6_tunnel_bind_dev(t->dev);
-- 
2.14.3


From 92c8b47a060747114b47044c43feb03a08031234 Mon Sep 17 00:00:00 2001
From: Mike Maloney <maloney@google.com>
Date: Tue, 28 Nov 2017 10:44:29 -0500
Subject: [PATCH 06/15] packet: fix crash in fanout_demux_rollover()

syzkaller found a race condition fanout_demux_rollover() while removing
a packet socket from a fanout group.

po->rollover is read and operated on during packet_rcv_fanout(), via
fanout_demux_rollover(), but the pointer is currently cleared before the
synchronization in packet_release().   It is safer to delay the cleanup
until after synchronize_net() has been called, ensuring all calls to
packet_rcv_fanout() for this socket have finished.

To further simplify synchronization around the rollover structure, set
po->rollover in fanout_add() only if there are no errors.  This removes
the need for rcu in the struct and in the call to
packet_getsockopt(..., PACKET_ROLLOVER_STATS, ...).

Crashing stack trace:
 fanout_demux_rollover+0xb6/0x4d0 net/packet/af_packet.c:1392
 packet_rcv_fanout+0x649/0x7c8 net/packet/af_packet.c:1487
 dev_queue_xmit_nit+0x835/0xc10 net/core/dev.c:1953
 xmit_one net/core/dev.c:2975 [inline]
 dev_hard_start_xmit+0x16b/0xac0 net/core/dev.c:2995
 __dev_queue_xmit+0x17a4/0x2050 net/core/dev.c:3476
 dev_queue_xmit+0x17/0x20 net/core/dev.c:3509
 neigh_connected_output+0x489/0x720 net/core/neighbour.c:1379
 neigh_output include/net/neighbour.h:482 [inline]
 ip6_finish_output2+0xad1/0x22a0 net/ipv6/ip6_output.c:120
 ip6_finish_output+0x2f9/0x920 net/ipv6/ip6_output.c:146
 NF_HOOK_COND include/linux/netfilter.h:239 [inline]
 ip6_output+0x1f4/0x850 net/ipv6/ip6_output.c:163
 dst_output include/net/dst.h:459 [inline]
 NF_HOOK.constprop.35+0xff/0x630 include/linux/netfilter.h:250
 mld_sendpack+0x6a8/0xcc0 net/ipv6/mcast.c:1660
 mld_send_initial_cr.part.24+0x103/0x150 net/ipv6/mcast.c:2072
 mld_send_initial_cr net/ipv6/mcast.c:2056 [inline]
 ipv6_mc_dad_complete+0x99/0x130 net/ipv6/mcast.c:2079
 addrconf_dad_completed+0x595/0x970 net/ipv6/addrconf.c:4039
 addrconf_dad_work+0xac9/0x1160 net/ipv6/addrconf.c:3971
 process_one_work+0xbf0/0x1bc0 kernel/workqueue.c:2113
 worker_thread+0x223/0x1990 kernel/workqueue.c:2247
 kthread+0x35e/0x430 kernel/kthread.c:231
 ret_from_fork+0x2a/0x40 arch/x86/entry/entry_64.S:432

Fixes: 0648ab70afe6 ("packet: rollover prepare: per-socket state")
Fixes: 509c7a1ecc860 ("packet: avoid panic in packet_getsockopt()")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Mike Maloney <maloney@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 32 ++++++++++----------------------
 net/packet/internal.h  |  1 -
 2 files changed, 10 insertions(+), 23 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index e7f6657269e0..036d77a69595 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1661,7 +1661,6 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		atomic_long_set(&rollover->num, 0);
 		atomic_long_set(&rollover->num_huge, 0);
 		atomic_long_set(&rollover->num_failed, 0);
-		po->rollover = rollover;
 	}
 
 	match = NULL;
@@ -1706,6 +1705,8 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		if (atomic_read(&match->sk_ref) < PACKET_FANOUT_MAX) {
 			__dev_remove_pack(&po->prot_hook);
 			po->fanout = match;
+			po->rollover = rollover;
+			rollover = NULL;
 			atomic_inc(&match->sk_ref);
 			__fanout_link(sk, po);
 			err = 0;
@@ -1719,10 +1720,7 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 	}
 
 out:
-	if (err && rollover) {
-		kfree_rcu(rollover, rcu);
-		po->rollover = NULL;
-	}
+	kfree(rollover);
 	mutex_unlock(&fanout_mutex);
 	return err;
 }
@@ -1746,11 +1744,6 @@ static struct packet_fanout *fanout_release(struct sock *sk)
 			list_del(&f->list);
 		else
 			f = NULL;
-
-		if (po->rollover) {
-			kfree_rcu(po->rollover, rcu);
-			po->rollover = NULL;
-		}
 	}
 	mutex_unlock(&fanout_mutex);
 
@@ -3039,6 +3032,7 @@ static int packet_release(struct socket *sock)
 	synchronize_net();
 
 	if (f) {
+		kfree(po->rollover);
 		fanout_release_data(f);
 		kfree(f);
 	}
@@ -3853,7 +3847,6 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
 	void *data = &val;
 	union tpacket_stats_u st;
 	struct tpacket_rollover_stats rstats;
-	struct packet_rollover *rollover;
 
 	if (level != SOL_PACKET)
 		return -ENOPROTOOPT;
@@ -3932,18 +3925,13 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
 		       0);
 		break;
 	case PACKET_ROLLOVER_STATS:
-		rcu_read_lock();
-		rollover = rcu_dereference(po->rollover);
-		if (rollover) {
-			rstats.tp_all = atomic_long_read(&rollover->num);
-			rstats.tp_huge = atomic_long_read(&rollover->num_huge);
-			rstats.tp_failed = atomic_long_read(&rollover->num_failed);
-			data = &rstats;
-			lv = sizeof(rstats);
-		}
-		rcu_read_unlock();
-		if (!rollover)
+		if (!po->rollover)
 			return -EINVAL;
+		rstats.tp_all = atomic_long_read(&po->rollover->num);
+		rstats.tp_huge = atomic_long_read(&po->rollover->num_huge);
+		rstats.tp_failed = atomic_long_read(&po->rollover->num_failed);
+		data = &rstats;
+		lv = sizeof(rstats);
 		break;
 	case PACKET_TX_HAS_OFF:
 		val = po->tp_tx_has_off;
diff --git a/net/packet/internal.h b/net/packet/internal.h
index 9ee46314b7d7..d55bfc34d6b3 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -92,7 +92,6 @@ struct packet_fanout {
 
 struct packet_rollover {
 	int			sock;
-	struct rcu_head		rcu;
 	atomic_long_t		num;
 	atomic_long_t		num_huge;
 	atomic_long_t		num_failed;
-- 
2.14.3


From c4aaca1c2947683b3258f08af75a33bec78ad559 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 28 Nov 2017 08:03:30 -0800
Subject: [PATCH 07/15] net/packet: fix a race in packet_bind() and
 packet_notifier()

[ Upstream commit 15fe076edea787807a7cdc168df832544b58eba6 ]

syzbot reported crashes [1] and provided a C repro easing bug hunting.

When/if packet_do_bind() calls __unregister_prot_hook() and releases
po->bind_lock, another thread can run packet_notifier() and process an
NETDEV_UP event.

This calls register_prot_hook() and hooks again the socket right before
first thread is able to grab again po->bind_lock.

Fixes this issue by temporarily setting po->num to 0, as suggested by
David Miller.

[1]
dev_remove_pack: ffff8801bf16fa80 not found
------------[ cut here ]------------
kernel BUG at net/core/dev.c:7945!  ( BUG_ON(!list_empty(&dev->ptype_all)); )
invalid opcode: 0000 [#1] SMP KASAN
Dumping ftrace buffer:
   (ftrace buffer empty)
Modules linked in:
device syz0 entered promiscuous mode
CPU: 0 PID: 3161 Comm: syzkaller404108 Not tainted 4.14.0+ #190
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
task: ffff8801cc57a500 task.stack: ffff8801cc588000
RIP: 0010:netdev_run_todo+0x772/0xae0 net/core/dev.c:7945
RSP: 0018:ffff8801cc58f598 EFLAGS: 00010293
RAX: ffff8801cc57a500 RBX: dffffc0000000000 RCX: ffffffff841f75b2
RDX: 0000000000000000 RSI: 1ffff100398b1ede RDI: ffff8801bf1f8810
device syz0 entered promiscuous mode
RBP: ffff8801cc58f898 R08: 0000000000000001 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: ffff8801bf1f8cd8
R13: ffff8801cc58f870 R14: ffff8801bf1f8780 R15: ffff8801cc58f7f0
FS:  0000000001716880(0000) GS:ffff8801db400000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000020b13000 CR3: 0000000005e25000 CR4: 00000000001406f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 rtnl_unlock+0xe/0x10 net/core/rtnetlink.c:106
 tun_detach drivers/net/tun.c:670 [inline]
 tun_chr_close+0x49/0x60 drivers/net/tun.c:2845
 __fput+0x333/0x7f0 fs/file_table.c:210
 ____fput+0x15/0x20 fs/file_table.c:244
 task_work_run+0x199/0x270 kernel/task_work.c:113
 exit_task_work include/linux/task_work.h:22 [inline]
 do_exit+0x9bb/0x1ae0 kernel/exit.c:865
 do_group_exit+0x149/0x400 kernel/exit.c:968
 SYSC_exit_group kernel/exit.c:979 [inline]
 SyS_exit_group+0x1d/0x20 kernel/exit.c:977
 entry_SYSCALL_64_fastpath+0x1f/0x96
RIP: 0033:0x44ad19

Fixes: 30f7ea1c2b5f ("packet: race condition in packet_bind")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Francesco Ruggeri <fruggeri@aristanetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 036d77a69595..267db0d603bc 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3101,6 +3101,10 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex,
 	if (need_rehook) {
 		if (po->running) {
 			rcu_read_unlock();
+			/* prevents packet_notifier() from calling
+			 * register_prot_hook()
+			 */
+			po->num = 0;
 			__unregister_prot_hook(sk, true);
 			rcu_read_lock();
 			dev_curr = po->prot_hook.dev;
@@ -3109,6 +3113,7 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex,
 								 dev->ifindex);
 		}
 
+		BUG_ON(po->running);
 		po->num = proto;
 		po->prot_hook.type = proto;
 
-- 
2.14.3


From 0fbfa5f2a051461e10696047194d71b59aba4096 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Wed, 6 Dec 2017 20:21:24 +0100
Subject: [PATCH 08/15] usbnet: fix alignment for frames with no ethernet
 header
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit a4abd7a80addb4a9547f7dfc7812566b60ec505c ]

The qmi_wwan minidriver support a 'raw-ip' mode where frames are
received without any ethernet header. This causes alignment issues
because the skbs allocated by usbnet are "IP aligned".

Fix by allowing minidrivers to disable the additional alignment
offset. This is implemented using a per-device flag, since the same
minidriver also supports 'ethernet' mode.

Fixes: 32f7adf633b9 ("net: qmi_wwan: support "raw IP" mode")
Reported-and-tested-by: Jay Foster <jay@systech.com>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 2 ++
 drivers/net/usb/usbnet.c   | 5 ++++-
 include/linux/usb/usbnet.h | 1 +
 3 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 97a16e23c19a..62725655d8e4 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -74,9 +74,11 @@ static void qmi_wwan_netdev_setup(struct net_device *net)
 		net->hard_header_len = 0;
 		net->addr_len        = 0;
 		net->flags           = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST;
+		set_bit(EVENT_NO_IP_ALIGN, &dev->flags);
 		netdev_dbg(net, "mode: raw IP\n");
 	} else if (!net->header_ops) { /* don't bother if already set */
 		ether_setup(net);
+		clear_bit(EVENT_NO_IP_ALIGN, &dev->flags);
 		netdev_dbg(net, "mode: Ethernet\n");
 	}
 
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index d5071e364d40..4ab82b998a0f 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -485,7 +485,10 @@ static int rx_submit (struct usbnet *dev, struct urb *urb, gfp_t flags)
 		return -ENOLINK;
 	}
 
-	skb = __netdev_alloc_skb_ip_align(dev->net, size, flags);
+	if (test_bit(EVENT_NO_IP_ALIGN, &dev->flags))
+		skb = __netdev_alloc_skb(dev->net, size, flags);
+	else
+		skb = __netdev_alloc_skb_ip_align(dev->net, size, flags);
 	if (!skb) {
 		netif_dbg(dev, rx_err, dev->net, "no rx skb\n");
 		usbnet_defer_kevent (dev, EVENT_RX_MEMORY);
diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index 6e0ce8c7b8cb..fde7550754df 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -79,6 +79,7 @@ struct usbnet {
 #		define EVENT_RX_KILL	10
 #		define EVENT_LINK_CHANGE	11
 #		define EVENT_SET_RX_MODE	12
+#		define EVENT_NO_IP_ALIGN	13
 };
 
 static inline struct usb_driver *driver_of(struct usb_interface *intf)
-- 
2.14.3


From d19be8c111e09e179805b0c3d5a2f96dd63039f3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 5 Dec 2017 12:45:56 -0800
Subject: [PATCH 09/15] net: remove hlist_nulls_add_tail_rcu()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit d7efc6c11b277d9d80b99b1334a78bfe7d7edf10 ]

Alexander Potapenko reported use of uninitialized memory [1]

This happens when inserting a request socket into TCP ehash,
in __sk_nulls_add_node_rcu(), since sk_reuseport is not initialized.

Bug was added by commit d894ba18d4e4 ("soreuseport: fix ordering for
mixed v4/v6 sockets")

Note that d296ba60d8e2 ("soreuseport: Resolve merge conflict for v4/v6
ordering fix") missed the opportunity to get rid of
hlist_nulls_add_tail_rcu() :

Both UDP sockets and TCP/DCCP listeners no longer use
__sk_nulls_add_node_rcu() for their hash insertion.

Since all other sockets have unique 4-tuple, the reuseport status
has no special meaning, so we can always use hlist_nulls_add_head_rcu()
for them and save few cycles/instructions.

[1]

==================================================================
BUG: KMSAN: use of uninitialized memory in inet_ehash_insert+0xd40/0x1050
CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.13.0+ #3288
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:16
 dump_stack+0x185/0x1d0 lib/dump_stack.c:52
 kmsan_report+0x13f/0x1c0 mm/kmsan/kmsan.c:1016
 __msan_warning_32+0x69/0xb0 mm/kmsan/kmsan_instr.c:766
 __sk_nulls_add_node_rcu ./include/net/sock.h:684
 inet_ehash_insert+0xd40/0x1050 net/ipv4/inet_hashtables.c:413
 reqsk_queue_hash_req net/ipv4/inet_connection_sock.c:754
 inet_csk_reqsk_queue_hash_add+0x1cc/0x300 net/ipv4/inet_connection_sock.c:765
 tcp_conn_request+0x31e7/0x36f0 net/ipv4/tcp_input.c:6414
 tcp_v4_conn_request+0x16d/0x220 net/ipv4/tcp_ipv4.c:1314
 tcp_rcv_state_process+0x42a/0x7210 net/ipv4/tcp_input.c:5917
 tcp_v4_do_rcv+0xa6a/0xcd0 net/ipv4/tcp_ipv4.c:1483
 tcp_v4_rcv+0x3de0/0x4ab0 net/ipv4/tcp_ipv4.c:1763
 ip_local_deliver_finish+0x6bb/0xcb0 net/ipv4/ip_input.c:216
 NF_HOOK ./include/linux/netfilter.h:248
 ip_local_deliver+0x3fa/0x480 net/ipv4/ip_input.c:257
 dst_input ./include/net/dst.h:477
 ip_rcv_finish+0x6fb/0x1540 net/ipv4/ip_input.c:397
 NF_HOOK ./include/linux/netfilter.h:248
 ip_rcv+0x10f6/0x15c0 net/ipv4/ip_input.c:488
 __netif_receive_skb_core+0x36f6/0x3f60 net/core/dev.c:4298
 __netif_receive_skb net/core/dev.c:4336
 netif_receive_skb_internal+0x63c/0x19c0 net/core/dev.c:4497
 napi_skb_finish net/core/dev.c:4858
 napi_gro_receive+0x629/0xa50 net/core/dev.c:4889
 e1000_receive_skb drivers/net/ethernet/intel/e1000/e1000_main.c:4018
 e1000_clean_rx_irq+0x1492/0x1d30
drivers/net/ethernet/intel/e1000/e1000_main.c:4474
 e1000_clean+0x43aa/0x5970 drivers/net/ethernet/intel/e1000/e1000_main.c:3819
 napi_poll net/core/dev.c:5500
 net_rx_action+0x73c/0x1820 net/core/dev.c:5566
 __do_softirq+0x4b4/0x8dd kernel/softirq.c:284
 invoke_softirq kernel/softirq.c:364
 irq_exit+0x203/0x240 kernel/softirq.c:405
 exiting_irq+0xe/0x10 ./arch/x86/include/asm/apic.h:638
 do_IRQ+0x15e/0x1a0 arch/x86/kernel/irq.c:263
 common_interrupt+0x86/0x86

Fixes: d894ba18d4e4 ("soreuseport: fix ordering for mixed v4/v6 sockets")
Fixes: d296ba60d8e2 ("soreuseport: Resolve merge conflict for v4/v6 ordering fix")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Alexander Potapenko <glider@google.com>
Acked-by: Craig Gallek <kraig@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rculist_nulls.h | 38 --------------------------------------
 include/net/sock.h            |  6 +-----
 2 files changed, 1 insertion(+), 43 deletions(-)

diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h
index 4ae95f7e8597..6224a0ab0b1e 100644
--- a/include/linux/rculist_nulls.h
+++ b/include/linux/rculist_nulls.h
@@ -99,44 +99,6 @@ static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n,
 		first->pprev = &n->next;
 }
 
-/**
- * hlist_nulls_add_tail_rcu
- * @n: the element to add to the hash list.
- * @h: the list to add to.
- *
- * Description:
- * Adds the specified element to the end of the specified hlist_nulls,
- * while permitting racing traversals.  NOTE: tail insertion requires
- * list traversal.
- *
- * The caller must take whatever precautions are necessary
- * (such as holding appropriate locks) to avoid racing
- * with another list-mutation primitive, such as hlist_nulls_add_head_rcu()
- * or hlist_nulls_del_rcu(), running on this same list.
- * However, it is perfectly legal to run concurrently with
- * the _rcu list-traversal primitives, such as
- * hlist_nulls_for_each_entry_rcu(), used to prevent memory-consistency
- * problems on Alpha CPUs.  Regardless of the type of CPU, the
- * list-traversal primitive must be guarded by rcu_read_lock().
- */
-static inline void hlist_nulls_add_tail_rcu(struct hlist_nulls_node *n,
-					struct hlist_nulls_head *h)
-{
-	struct hlist_nulls_node *i, *last = NULL;
-
-	for (i = hlist_nulls_first_rcu(h); !is_a_nulls(i);
-	     i = hlist_nulls_next_rcu(i))
-		last = i;
-
-	if (last) {
-		n->next = last->next;
-		n->pprev = &last->next;
-		rcu_assign_pointer(hlist_nulls_next_rcu(last), n);
-	} else {
-		hlist_nulls_add_head_rcu(n, h);
-	}
-}
-
 /**
  * hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type
  * @tpos:	the type * to use as a loop cursor.
diff --git a/include/net/sock.h b/include/net/sock.h
index 92b269709b9a..6d42ed883bf9 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -648,11 +648,7 @@ static inline void sk_add_node_rcu(struct sock *sk, struct hlist_head *list)
 
 static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
 {
-	if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport &&
-	    sk->sk_family == AF_INET6)
-		hlist_nulls_add_tail_rcu(&sk->sk_nulls_node, list);
-	else
-		hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list);
+	hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list);
 }
 
 static inline void sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
-- 
2.14.3


From fe7bbbc089b69a4af256d363e94b4713f067e41b Mon Sep 17 00:00:00 2001
From: Lars Persson <lars.persson@axis.com>
Date: Fri, 1 Dec 2017 11:12:44 +0100
Subject: [PATCH 10/15] stmmac: reset last TSO segment size after device open

[ Upstream commit 45ab4b13e46325d00f4acdb365d406e941a15f81 ]

The mss variable tracks the last max segment size sent to the TSO
engine. We do not update the hardware as long as we receive skb:s with
the same value in gso_size.

During a network device down/up cycle (mapped to stmmac_release() and
stmmac_open() callbacks) we issue a reset to the hardware and it
forgets the setting for mss. However we did not zero out our mss
variable so the next transmission of a gso packet happens with an
undefined hardware setting.

This triggers a hang in the TSO engine and eventuelly the netdev
watchdog will bark.

Fixes: f748be531d70 ("stmmac: support new GMAC4")
Signed-off-by: Lars Persson <larper@axis.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index ef6bff820cf6..adf61a7b1b01 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1795,6 +1795,7 @@ static int stmmac_open(struct net_device *dev)
 
 	priv->dma_buf_sz = STMMAC_ALIGN(buf_sz);
 	priv->rx_copybreak = STMMAC_RX_COPYBREAK;
+	priv->mss = 0;
 
 	ret = alloc_dma_desc_resources(priv);
 	if (ret < 0) {
-- 
2.14.3


From d3aa8a9e36925075a988b6227e8c9c01a42a6f90 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 1 Dec 2017 10:06:56 -0800
Subject: [PATCH 11/15] tcp/dccp: block bh before arming time_wait timer
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit cfac7f836a715b91f08c851df915d401a4d52783 ]

Maciej Żenczykowski reported some panics in tcp_twsk_destructor()
that might be caused by the following bug.

timewait timer is pinned to the cpu, because we want to transition
timwewait refcount from 0 to 4 in one go, once everything has been
initialized.

At the time commit ed2e92394589 ("tcp/dccp: fix timewait races in timer
handling") was merged, TCP was always running from BH habdler.

After commit 5413d1babe8f ("net: do not block BH while processing
socket backlog") we definitely can run tcp_time_wait() from process
context.

We need to block BH in the critical section so that the pinned timer
has still its purpose.

This bug is more likely to happen under stress and when very small RTO
are used in datacenter flows.

Fixes: 5413d1babe8f ("net: do not block BH while processing socket backlog")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Maciej Żenczykowski <maze@google.com>
Acked-by: Maciej Żenczykowski <maze@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/minisocks.c     | 6 ++++++
 net/ipv4/tcp_minisocks.c | 6 ++++++
 2 files changed, 12 insertions(+)

diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index 39e7e2bca8db..62522b8d2f97 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -57,10 +57,16 @@ void dccp_time_wait(struct sock *sk, int state, int timeo)
 		if (state == DCCP_TIME_WAIT)
 			timeo = DCCP_TIMEWAIT_LEN;
 
+		/* tw_timer is pinned, so we need to make sure BH are disabled
+		 * in following section, otherwise timer handler could run before
+		 * we complete the initialization.
+		 */
+		local_bh_disable();
 		inet_twsk_schedule(tw, timeo);
 		/* Linkage updates. */
 		__inet_twsk_hashdance(tw, sk, &dccp_hashinfo);
 		inet_twsk_put(tw);
+		local_bh_enable();
 	} else {
 		/* Sorry, if we're out of memory, just CLOSE this
 		 * socket up.  We've got bigger problems than
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 64e1ba49c3e2..830a5645d8c1 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -328,10 +328,16 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 				timeo = TCP_TIMEWAIT_LEN;
 		}
 
+		/* tw_timer is pinned, so we need to make sure BH are disabled
+		 * in following section, otherwise timer handler could run before
+		 * we complete the initialization.
+		 */
+		local_bh_disable();
 		inet_twsk_schedule(tw, timeo);
 		/* Linkage updates. */
 		__inet_twsk_hashdance(tw, sk, &tcp_hashinfo);
 		inet_twsk_put(tw);
+		local_bh_enable();
 	} else {
 		/* Sorry, if we're out of memory, just CLOSE this
 		 * socket up.  We've got bigger problems than
-- 
2.14.3


From 24ac3f46b7dca0bb00dbf3ca8108cabbc9416bab Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Fri, 1 Dec 2017 10:14:51 +0100
Subject: [PATCH 12/15] s390/qeth: build max size GSO skbs on L2 devices

[ Upstream commit 0cbff6d4546613330a1c5f139f5c368e4ce33ca1 ]

The current GSO skb size limit was copy&pasted over from the L3 path,
where it is needed due to a TSO limitation.
As L2 devices don't offer TSO support (and thus all GSO skbs are
segmented before they reach the driver), there's no reason to restrict
the stack in how large it may build the GSO skbs.

Fixes: d52aec97e5bc ("qeth: enable scatter/gather in layer 2 mode")
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_l2_main.c | 2 --
 drivers/s390/net/qeth_l3_main.c | 4 ++--
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 8530477caab8..8ac76074c9ec 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -1140,8 +1140,6 @@ static int qeth_l2_setup_netdev(struct qeth_card *card)
 	}
 	card->info.broadcast_capable = 1;
 	qeth_l2_request_initial_mac(card);
-	card->dev->gso_max_size = (QETH_MAX_BUFFER_ELEMENTS(card) - 1) *
-				  PAGE_SIZE;
 	SET_NETDEV_DEV(card->dev, &card->gdev->dev);
 	netif_napi_add(card->dev, &card->napi, qeth_l2_poll, QETH_NAPI_WEIGHT);
 	netif_carrier_off(card->dev);
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 204edb0b69a5..50a2dda53b8a 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -3147,8 +3147,8 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
 				NETIF_F_HW_VLAN_CTAG_RX |
 				NETIF_F_HW_VLAN_CTAG_FILTER;
 	netif_keep_dst(card->dev);
-	card->dev->gso_max_size = (QETH_MAX_BUFFER_ELEMENTS(card) - 1) *
-				  PAGE_SIZE;
+	netif_set_gso_max_size(card->dev, (QETH_MAX_BUFFER_ELEMENTS(card) - 1) *
+					  PAGE_SIZE);
 
 	SET_NETDEV_DEV(card->dev, &card->gdev->dev);
 	netif_napi_add(card->dev, &card->napi, qeth_l3_poll, QETH_NAPI_WEIGHT);
-- 
2.14.3


From 146eb7e541475cccefb1b61ee34763c79499f4d7 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Fri, 1 Dec 2017 10:14:50 +0100
Subject: [PATCH 13/15] s390/qeth: fix GSO throughput regression

[ Upstream commit 6d69b1f1eb7a2edf8a3547f361c61f2538e054bb ]

Using GSO with small MTUs currently results in a substantial throughput
regression - which is caused by how qeth needs to map non-linear skbs
into its IO buffer elements:
compared to a linear skb, each GSO-segmented skb effectively consumes
twice as many buffer elements (ie two instead of one) due to the
additional header-only part. This causes the Output Queue to be
congested with low-utilized IO buffers.

Fix this as follows:
If the MSS is low enough so that a non-SG GSO segmentation produces
order-0 skbs (currently ~3500 byte), opt out from NETIF_F_SG. This is
where we anticipate the biggest savings, since an SG-enabled
GSO segmentation produces skbs that always consume at least two
buffer elements.

Larger MSS values continue to get a SG-enabled GSO segmentation, since
1) the relative overhead of the additional header-only buffer element
becomes less noticeable, and
2) the linearization overhead increases.

With the throughput regression fixed, re-enable NETIF_F_SG by default to
reap the significant CPU savings of GSO.

Fixes: 5722963a8e83 ("qeth: do not turn on SG per default")
Reported-by: Nils Hoppmann <niho@de.ibm.com>
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core.h      |  3 +++
 drivers/s390/net/qeth_core_main.c | 31 +++++++++++++++++++++++++++++++
 drivers/s390/net/qeth_l2_main.c   |  2 ++
 drivers/s390/net/qeth_l3_main.c   |  2 ++
 4 files changed, 38 insertions(+)

diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index d55e6438bb5e..e2bd2ad01b15 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -1004,6 +1004,9 @@ struct qeth_cmd_buffer *qeth_get_setassparms_cmd(struct qeth_card *,
 int qeth_set_features(struct net_device *, netdev_features_t);
 int qeth_recover_features(struct net_device *);
 netdev_features_t qeth_fix_features(struct net_device *, netdev_features_t);
+netdev_features_t qeth_features_check(struct sk_buff *skb,
+				      struct net_device *dev,
+				      netdev_features_t features);
 
 /* exports for OSN */
 int qeth_osn_assist(struct net_device *, void *, int);
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 21ef8023430f..b5fa6bb56b29 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -19,6 +19,11 @@
 #include <linux/mii.h>
 #include <linux/kthread.h>
 #include <linux/slab.h>
+#include <linux/if_vlan.h>
+#include <linux/netdevice.h>
+#include <linux/netdev_features.h>
+#include <linux/skbuff.h>
+
 #include <net/iucv/af_iucv.h>
 #include <net/dsfield.h>
 
@@ -6240,6 +6245,32 @@ netdev_features_t qeth_fix_features(struct net_device *dev,
 }
 EXPORT_SYMBOL_GPL(qeth_fix_features);
 
+netdev_features_t qeth_features_check(struct sk_buff *skb,
+				      struct net_device *dev,
+				      netdev_features_t features)
+{
+	/* GSO segmentation builds skbs with
+	 *	a (small) linear part for the headers, and
+	 *	page frags for the data.
+	 * Compared to a linear skb, the header-only part consumes an
+	 * additional buffer element. This reduces buffer utilization, and
+	 * hurts throughput. So compress small segments into one element.
+	 */
+	if (netif_needs_gso(skb, features)) {
+		/* match skb_segment(): */
+		unsigned int doffset = skb->data - skb_mac_header(skb);
+		unsigned int hsize = skb_shinfo(skb)->gso_size;
+		unsigned int hroom = skb_headroom(skb);
+
+		/* linearize only if resulting skb allocations are order-0: */
+		if (SKB_DATA_ALIGN(hroom + doffset + hsize) <= SKB_MAX_HEAD(0))
+			features &= ~NETIF_F_SG;
+	}
+
+	return vlan_features_check(skb, features);
+}
+EXPORT_SYMBOL_GPL(qeth_features_check);
+
 static int __init qeth_core_init(void)
 {
 	int rc;
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 8ac76074c9ec..ac33f6c999b1 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -1084,6 +1084,7 @@ static const struct net_device_ops qeth_l2_netdev_ops = {
 	.ndo_stop		= qeth_l2_stop,
 	.ndo_get_stats		= qeth_get_stats,
 	.ndo_start_xmit		= qeth_l2_hard_start_xmit,
+	.ndo_features_check	= qeth_features_check,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_rx_mode	= qeth_l2_set_rx_mode,
 	.ndo_do_ioctl	   	= qeth_l2_do_ioctl,
@@ -1128,6 +1129,7 @@ static int qeth_l2_setup_netdev(struct qeth_card *card)
 	if (card->info.type == QETH_CARD_TYPE_OSD && !card->info.guestlan) {
 		card->dev->hw_features = NETIF_F_SG;
 		card->dev->vlan_features = NETIF_F_SG;
+		card->dev->features |= NETIF_F_SG;
 		/* OSA 3S and earlier has no RX/TX support */
 		if (qeth_is_supported(card, IPA_OUTBOUND_CHECKSUM)) {
 			card->dev->hw_features |= NETIF_F_IP_CSUM;
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 50a2dda53b8a..07555a24fade 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -3066,6 +3066,7 @@ static const struct net_device_ops qeth_l3_netdev_ops = {
 	.ndo_stop		= qeth_l3_stop,
 	.ndo_get_stats		= qeth_get_stats,
 	.ndo_start_xmit		= qeth_l3_hard_start_xmit,
+	.ndo_features_check	= qeth_features_check,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_rx_mode	= qeth_l3_set_multicast_list,
 	.ndo_do_ioctl		= qeth_l3_do_ioctl,
@@ -3122,6 +3123,7 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
 				card->dev->vlan_features = NETIF_F_SG |
 					NETIF_F_RXCSUM | NETIF_F_IP_CSUM |
 					NETIF_F_TSO;
+				card->dev->features |= NETIF_F_SG;
 			}
 		}
 	} else if (card->info.type == QETH_CARD_TYPE_IQD) {
-- 
2.14.3


From 63072cfe6716d97cbaca55aad1472a25c5fd09f2 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Fri, 1 Dec 2017 10:14:49 +0100
Subject: [PATCH 14/15] s390/qeth: fix thinko in IPv4 multicast address
 tracking

[ Upsteam commit bc3ab70584696cb798b9e1e0ac8e6ced5fd4c3b8 ]

Commit 5f78e29ceebf ("qeth: optimize IP handling in rx_mode callback")
reworked how secondary addresses are managed for qeth devices.
Instead of dropping & subsequently re-adding all addresses on every
ndo_set_rx_mode() call, qeth now keeps track of the addresses that are
currently registered with the HW.
On a ndo_set_rx_mode(), we thus only need to do (de-)registration
requests for the addresses that have actually changed.

On L3 devices, the lookup for IPv4 Multicast addresses checks the wrong
hashtable - and thus never finds a match. As a result, we first delete
*all* such addresses, and then re-add them again. So each set_rx_mode()
causes a short period where the IPv4 Multicast addresses are not
registered, and the card stops forwarding inbound traffic for them.

Fix this by setting the ->is_multicast flag on the lookup object, thus
enabling qeth_l3_ip_from_hash() to search the correct hashtable and
find a match there.

Fixes: 5f78e29ceebf ("qeth: optimize IP handling in rx_mode callback")
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_l3_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 07555a24fade..5735fc3be6c7 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -1416,6 +1416,7 @@ qeth_l3_add_mc_to_hash(struct qeth_card *card, struct in_device *in4_dev)
 
 		tmp->u.a4.addr = im4->multiaddr;
 		memcpy(tmp->mac, buf, sizeof(tmp->mac));
+		tmp->is_multicast = 1;
 
 		ipm = qeth_l3_ip_from_hash(card, tmp);
 		if (ipm) {
-- 
2.14.3


From 4f032bdd7e47aa6960507a8de414385cf5c1e83b Mon Sep 17 00:00:00 2001
From: Tommi Rantala <tommi.t.rantala@nokia.com>
Date: Wed, 29 Nov 2017 12:48:42 +0200
Subject: [PATCH 15/15] tipc: call tipc_rcv() only if bearer is up in
 tipc_udp_recv()

[ Upstream commit c7799c067c2ae33e348508c8afec354f3257ff25 ]

Remove the second tipc_rcv() call in tipc_udp_recv(). We have just
checked that the bearer is not up, and calling tipc_rcv() with a bearer
that is not up leads to a TIPC div-by-zero crash in
tipc_node_calculate_timer(). The crash is rare in practice, but can
happen like this:

  We're enabling a bearer, but it's not yet up and fully initialized.
  At the same time we receive a discovery packet, and in tipc_udp_recv()
  we end up calling tipc_rcv() with the not-yet-initialized bearer,
  causing later the div-by-zero crash in tipc_node_calculate_timer().

Jon Maloy explains the impact of removing the second tipc_rcv() call:
  "link setup in the worst case will be delayed until the next arriving
   discovery messages, 1 sec later, and this is an acceptable delay."

As the tipc_rcv() call is removed, just leave the function via the
rcu_out label, so that we will kfree_skb().

[   12.590450] Own node address <1.1.1>, network identity 1
[   12.668088] divide error: 0000 [#1] SMP
[   12.676952] CPU: 2 PID: 0 Comm: swapper/2 Not tainted 4.14.2-dirty #1
[   12.679225] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-2.fc27 04/01/2014
[   12.682095] task: ffff8c2a761edb80 task.stack: ffffa41cc0cac000
[   12.684087] RIP: 0010:tipc_node_calculate_timer.isra.12+0x45/0x60 [tipc]
[   12.686486] RSP: 0018:ffff8c2a7fc838a0 EFLAGS: 00010246
[   12.688451] RAX: 0000000000000000 RBX: ffff8c2a5b382600 RCX: 0000000000000000
[   12.691197] RDX: 0000000000000000 RSI: ffff8c2a5b382600 RDI: ffff8c2a5b382600
[   12.693945] RBP: ffff8c2a7fc838b0 R08: 0000000000000001 R09: 0000000000000001
[   12.696632] R10: 0000000000000000 R11: 0000000000000000 R12: ffff8c2a5d8949d8
[   12.699491] R13: ffffffff95ede400 R14: 0000000000000000 R15: ffff8c2a5d894800
[   12.702338] FS:  0000000000000000(0000) GS:ffff8c2a7fc80000(0000) knlGS:0000000000000000
[   12.705099] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   12.706776] CR2: 0000000001bb9440 CR3: 00000000bd009001 CR4: 00000000003606e0
[   12.708847] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[   12.711016] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[   12.712627] Call Trace:
[   12.713390]  <IRQ>
[   12.714011]  tipc_node_check_dest+0x2e8/0x350 [tipc]
[   12.715286]  tipc_disc_rcv+0x14d/0x1d0 [tipc]
[   12.716370]  tipc_rcv+0x8b0/0xd40 [tipc]
[   12.717396]  ? minmax_running_min+0x2f/0x60
[   12.718248]  ? dst_alloc+0x4c/0xa0
[   12.718964]  ? tcp_ack+0xaf1/0x10b0
[   12.719658]  ? tipc_udp_is_known_peer+0xa0/0xa0 [tipc]
[   12.720634]  tipc_udp_recv+0x71/0x1d0 [tipc]
[   12.721459]  ? dst_alloc+0x4c/0xa0
[   12.722130]  udp_queue_rcv_skb+0x264/0x490
[   12.722924]  __udp4_lib_rcv+0x21e/0x990
[   12.723670]  ? ip_route_input_rcu+0x2dd/0xbf0
[   12.724442]  ? tcp_v4_rcv+0x958/0xa40
[   12.725039]  udp_rcv+0x1a/0x20
[   12.725587]  ip_local_deliver_finish+0x97/0x1d0
[   12.726323]  ip_local_deliver+0xaf/0xc0
[   12.726959]  ? ip_route_input_noref+0x19/0x20
[   12.727689]  ip_rcv_finish+0xdd/0x3b0
[   12.728307]  ip_rcv+0x2ac/0x360
[   12.728839]  __netif_receive_skb_core+0x6fb/0xa90
[   12.729580]  ? udp4_gro_receive+0x1a7/0x2c0
[   12.730274]  __netif_receive_skb+0x1d/0x60
[   12.730953]  ? __netif_receive_skb+0x1d/0x60
[   12.731637]  netif_receive_skb_internal+0x37/0xd0
[   12.732371]  napi_gro_receive+0xc7/0xf0
[   12.732920]  receive_buf+0x3c3/0xd40
[   12.733441]  virtnet_poll+0xb1/0x250
[   12.733944]  net_rx_action+0x23e/0x370
[   12.734476]  __do_softirq+0xc5/0x2f8
[   12.734922]  irq_exit+0xfa/0x100
[   12.735315]  do_IRQ+0x4f/0xd0
[   12.735680]  common_interrupt+0xa2/0xa2
[   12.736126]  </IRQ>
[   12.736416] RIP: 0010:native_safe_halt+0x6/0x10
[   12.736925] RSP: 0018:ffffa41cc0cafe90 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff4d
[   12.737756] RAX: 0000000000000000 RBX: ffff8c2a761edb80 RCX: 0000000000000000
[   12.738504] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
[   12.739258] RBP: ffffa41cc0cafe90 R08: 0000014b5b9795e5 R09: ffffa41cc12c7e88
[   12.740118] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000002
[   12.740964] R13: ffff8c2a761edb80 R14: 0000000000000000 R15: 0000000000000000
[   12.741831]  default_idle+0x2a/0x100
[   12.742323]  arch_cpu_idle+0xf/0x20
[   12.742796]  default_idle_call+0x28/0x40
[   12.743312]  do_idle+0x179/0x1f0
[   12.743761]  cpu_startup_entry+0x1d/0x20
[   12.744291]  start_secondary+0x112/0x120
[   12.744816]  secondary_startup_64+0xa5/0xa5
[   12.745367] Code: b9 f4 01 00 00 48 89 c2 48 c1 ea 02 48 3d d3 07 00
00 48 0f 47 d1 49 8b 0c 24 48 39 d1 76 07 49 89 14 24 48 89 d1 31 d2 48
89 df <48> f7 f1 89 c6 e8 81 6e ff ff 5b 41 5c 5d c3 66 90 66 2e 0f 1f
[   12.747527] RIP: tipc_node_calculate_timer.isra.12+0x45/0x60 [tipc] RSP: ffff8c2a7fc838a0
[   12.748555] ---[ end trace 1399ab83390650fd ]---
[   12.749296] Kernel panic - not syncing: Fatal exception in interrupt
[   12.750123] Kernel Offset: 0x13200000 from 0xffffffff82000000
(relocation range: 0xffffffff80000000-0xffffffffbfffffff)
[   12.751215] Rebooting in 60 seconds..

Fixes: c9b64d492b1f ("tipc: add replicast peer discovery")
Signed-off-by: Tommi Rantala <tommi.t.rantala@nokia.com>
Cc: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/udp_media.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index b58dc95f3d35..107375d80c70 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -371,10 +371,6 @@ static int tipc_udp_recv(struct sock *sk, struct sk_buff *skb)
 			goto rcu_out;
 	}
 
-	tipc_rcv(sock_net(sk), skb, b);
-	rcu_read_unlock();
-	return 0;
-
 rcu_out:
 	rcu_read_unlock();
 out:
-- 
2.14.3


[-- Attachment #3: net_414.mbox --]
[-- Type: Application/Octet-Stream, Size: 111700 bytes --]

From 64b4d2f12725dda86465aaa3dbfd9a337cb0adb8 Mon Sep 17 00:00:00 2001
From: Sebastian Sjoholm <ssjoholm@mac.com>
Date: Mon, 20 Nov 2017 19:05:17 +0100
Subject: [PATCH 01/33] net: qmi_wwan: add Quectel BG96 2c7c:0296
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit f9409e7f086fa6c4623769b4b2f4f17a024d8143 ]

Quectel BG96 is an Qualcomm MDM9206 based IoT modem, supporting both
CAT-M and NB-IoT. Tested hardware is BG96 mounted on Quectel development
board (EVB). The USB id is added to qmi_wwan.c to allow QMI
communication with the BG96.

Signed-off-by: Sebastian Sjoholm <ssjoholm@mac.com>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 8d4a6f7cba61..f4ed553929f0 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1239,6 +1239,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1e0e, 0x9001, 5)},	/* SIMCom 7230E */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0125, 4)},	/* Quectel EC25, EC20 R2.0  Mini PCIe */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0121, 4)},	/* Quectel EC21 Mini PCIe */
+	{QMI_FIXED_INTF(0x2c7c, 0x0296, 4)},	/* Quectel BG96 */
 
 	/* 4. Gobi 1000 devices */
 	{QMI_GOBI1K_DEVICE(0x05c6, 0x9212)},	/* Acer Gobi Modem Device */
-- 
2.14.3


From c97b207a9e74fe54374419a6514071f1eed916a5 Mon Sep 17 00:00:00 2001
From: Sunil Goutham <sgoutham@cavium.com>
Date: Thu, 23 Nov 2017 22:34:31 +0300
Subject: [PATCH 02/33] net: thunderx: Fix TCP/UDP checksum offload for IPv6
 pkts

[ Upstream commit fa6d7cb5d76cf0467c61420fc9238045aedfd379 ]

Don't offload IP header checksum to NIC.

This fixes a previous patch which enabled checksum offloading
for both IPv4 and IPv6 packets.  So L3 checksum offload was
getting enabled for IPv6 pkts.  And HW is dropping these pkts
as it assumes the pkt is IPv4 when IP csum offload is set
in the SQ descriptor.

Fixes:  3a9024f52c2e ("net: thunderx: Enable TSO and checksum offloads for ipv6")
Signed-off-by: Sunil Goutham <sgoutham@cavium.com>
Signed-off-by: Aleksey Makarov <aleksey.makarov@auriga.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/thunder/nicvf_queues.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index d4496e9afcdf..8b2c31e2a2b0 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -1355,7 +1355,6 @@ nicvf_sq_add_hdr_subdesc(struct nicvf *nic, struct snd_queue *sq, int qentry,
 
 	/* Offload checksum calculation to HW */
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
-		hdr->csum_l3 = 1; /* Enable IP csum calculation */
 		hdr->l3_offset = skb_network_offset(skb);
 		hdr->l4_offset = skb_transport_offset(skb);
 
-- 
2.14.3


From eef375929bb350bbff5b3777fc7307f0b27d391d Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 6 Dec 2017 01:04:50 +0100
Subject: [PATCH 03/33] net: thunderx: Fix TCP/UDP checksum offload for IPv4
 pkts

[ Upstream commit 134059fd2775be79e26c2dff87d25cc2f6ea5626 ]

Offload IP header checksum to NIC.

This fixes a previous patch which disabled checksum offloading
for both IPv4 and IPv6 packets.  So L3 checksum offload was
getting disabled for IPv4 pkts.  And HW is dropping these pkts
for some reason.

Without this patch, IPv4 TSO appears to be broken:

WIthout this patch I get ~16kbyte/s, with patch close to 2mbyte/s
when copying files via scp from test box to my home workstation.

Looking at tcpdump on sender it looks like hardware drops IPv4 TSO skbs.
This patch restores performance for me, ipv6 looks good too.

Fixes: fa6d7cb5d76c ("net: thunderx: Fix TCP/UDP checksum offload for IPv6 pkts")
Cc: Sunil Goutham <sgoutham@cavium.com>
Cc: Aleksey Makarov <aleksey.makarov@auriga.com>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/thunder/nicvf_queues.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index 8b2c31e2a2b0..a3d12dbde95b 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -1355,6 +1355,8 @@ nicvf_sq_add_hdr_subdesc(struct nicvf *nic, struct snd_queue *sq, int qentry,
 
 	/* Offload checksum calculation to HW */
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
+		if (ip.v4->version == 4)
+			hdr->csum_l3 = 1; /* Enable IP csum calculation */
 		hdr->l3_offset = skb_network_offset(skb);
 		hdr->l4_offset = skb_transport_offset(skb);
 
-- 
2.14.3


From c02f49bee82889e0fac2e789054b055f7cd200a4 Mon Sep 17 00:00:00 2001
From: Tobias Jakobi <tjakobi@math.uni-bielefeld.de>
Date: Tue, 21 Nov 2017 16:15:57 +0100
Subject: [PATCH 04/33] net: realtek: r8169: implement set_link_ksettings()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 9e77d7a5549dc4d4999a60676373ab3fd1dae4db ]

Commit 6fa1ba61520576cf1346c4ff09a056f2950cb3bf partially
implemented the new ethtool API, by replacing get_settings()
with get_link_ksettings(). This breaks ethtool, since the
userspace tool (according to the new API specs) never tries
the legacy set() call, when the new get() call succeeds.

All attempts to chance some setting from userspace result in:
> Cannot set new settings: Operation not supported

Implement the missing set() call.

Signed-off-by: Tobias Jakobi <tjakobi@math.uni-bielefeld.de>
Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 38 +++++++++++++++++++++---------------
 1 file changed, 22 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index a3c949ea7d1a..9541465e43e9 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -2025,21 +2025,6 @@ static int rtl8169_set_speed(struct net_device *dev,
 	return ret;
 }
 
-static int rtl8169_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
-{
-	struct rtl8169_private *tp = netdev_priv(dev);
-	int ret;
-
-	del_timer_sync(&tp->timer);
-
-	rtl_lock_work(tp);
-	ret = rtl8169_set_speed(dev, cmd->autoneg, ethtool_cmd_speed(cmd),
-				cmd->duplex, cmd->advertising);
-	rtl_unlock_work(tp);
-
-	return ret;
-}
-
 static netdev_features_t rtl8169_fix_features(struct net_device *dev,
 	netdev_features_t features)
 {
@@ -2166,6 +2151,27 @@ static int rtl8169_get_link_ksettings(struct net_device *dev,
 	return rc;
 }
 
+static int rtl8169_set_link_ksettings(struct net_device *dev,
+				      const struct ethtool_link_ksettings *cmd)
+{
+	struct rtl8169_private *tp = netdev_priv(dev);
+	int rc;
+	u32 advertising;
+
+	if (!ethtool_convert_link_mode_to_legacy_u32(&advertising,
+	    cmd->link_modes.advertising))
+		return -EINVAL;
+
+	del_timer_sync(&tp->timer);
+
+	rtl_lock_work(tp);
+	rc = rtl8169_set_speed(dev, cmd->base.autoneg, cmd->base.speed,
+			       cmd->base.duplex, advertising);
+	rtl_unlock_work(tp);
+
+	return rc;
+}
+
 static void rtl8169_get_regs(struct net_device *dev, struct ethtool_regs *regs,
 			     void *p)
 {
@@ -2367,7 +2373,6 @@ static const struct ethtool_ops rtl8169_ethtool_ops = {
 	.get_drvinfo		= rtl8169_get_drvinfo,
 	.get_regs_len		= rtl8169_get_regs_len,
 	.get_link		= ethtool_op_get_link,
-	.set_settings		= rtl8169_set_settings,
 	.get_msglevel		= rtl8169_get_msglevel,
 	.set_msglevel		= rtl8169_set_msglevel,
 	.get_regs		= rtl8169_get_regs,
@@ -2379,6 +2384,7 @@ static const struct ethtool_ops rtl8169_ethtool_ops = {
 	.get_ts_info		= ethtool_op_get_ts_info,
 	.nway_reset		= rtl8169_nway_reset,
 	.get_link_ksettings	= rtl8169_get_link_ksettings,
+	.set_link_ksettings	= rtl8169_set_link_ksettings,
 };
 
 static void rtl8169_get_mac_version(struct rtl8169_private *tp,
-- 
2.14.3


From 371b3b2943ea398900ca4d8b3e5801b8d1067223 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Wed, 18 Oct 2017 17:40:17 +0200
Subject: [PATCH 05/33] s390/qeth: fix early exit from error path

[ Upstream commit 83cf79a2fec3cf499eb6cb9eb608656fc2a82776 ]

When the allocation of the addr buffer fails, we need to free
our refcount on the inetdevice before returning.

Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_l3_main.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index ab661a431f7c..1d8c317553ba 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -1553,7 +1553,7 @@ static void qeth_l3_free_vlan_addresses4(struct qeth_card *card,
 
 	addr = qeth_l3_get_addr_buffer(QETH_PROT_IPV4);
 	if (!addr)
-		return;
+		goto out;
 
 	spin_lock_bh(&card->ip_lock);
 
@@ -1567,6 +1567,7 @@ static void qeth_l3_free_vlan_addresses4(struct qeth_card *card,
 	spin_unlock_bh(&card->ip_lock);
 
 	kfree(addr);
+out:
 	in_dev_put(in_dev);
 }
 
@@ -1591,7 +1592,7 @@ static void qeth_l3_free_vlan_addresses6(struct qeth_card *card,
 
 	addr = qeth_l3_get_addr_buffer(QETH_PROT_IPV6);
 	if (!addr)
-		return;
+		goto out;
 
 	spin_lock_bh(&card->ip_lock);
 
@@ -1606,6 +1607,7 @@ static void qeth_l3_free_vlan_addresses6(struct qeth_card *card,
 	spin_unlock_bh(&card->ip_lock);
 
 	kfree(addr);
+out:
 	in6_dev_put(in6_dev);
 #endif /* CONFIG_QETH_IPV6 */
 }
-- 
2.14.3


From 51f81fcc0054bd54c19a0e53bc1d1b32601bcfac Mon Sep 17 00:00:00 2001
From: Jon Maloy <jon.maloy@ericsson.com>
Date: Mon, 4 Dec 2017 22:00:20 +0100
Subject: [PATCH 06/33] tipc: fix memory leak in tipc_accept_from_sock()

[ Upstream commit a7d5f107b4978e08eeab599ee7449af34d034053 ]

When the function tipc_accept_from_sock() fails to create an instance of
struct tipc_subscriber it omits to free the already created instance of
struct tipc_conn instance before it returns.

We fix that with this commit.

Reported-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/server.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/tipc/server.c b/net/tipc/server.c
index 3cd6402e812c..f4c1b18c5fb0 100644
--- a/net/tipc/server.c
+++ b/net/tipc/server.c
@@ -313,6 +313,7 @@ static int tipc_accept_from_sock(struct tipc_conn *con)
 	newcon->usr_data = s->tipc_conn_new(newcon->conid);
 	if (!newcon->usr_data) {
 		sock_release(newsock);
+		conn_put(newcon);
 		return -ENOMEM;
 	}
 
-- 
2.14.3


From a16d1226ebfd647b4ad49cef2bc34ca7cc5d5877 Mon Sep 17 00:00:00 2001
From: Wei Xu <wexu@redhat.com>
Date: Fri, 1 Dec 2017 05:10:36 -0500
Subject: [PATCH 07/33] vhost: fix skb leak in handle_rx()

[ Upstream commit 6e474083f3daf3a3546737f5d7d502ad12eb257c ]

Matthew found a roughly 40% tcp throughput regression with commit
c67df11f(vhost_net: try batch dequing from skb array) as discussed
in the following thread:
https://www.mail-archive.com/netdev@vger.kernel.org/msg187936.html

Eventually we figured out that it was a skb leak in handle_rx()
when sending packets to the VM. This usually happens when a guest
can not drain out vq as fast as vhost fills in, afterwards it sets
off the traffic jam and leaks skb(s) which occurs as no headcount
to send on the vq from vhost side.

This can be avoided by making sure we have got enough headcount
before actually consuming a skb from the batched rx array while
transmitting, which is simply done by moving checking the zero
headcount a bit ahead.

Signed-off-by: Wei Xu <wexu@redhat.com>
Reported-by: Matthew Rosato <mjrosato@linux.vnet.ibm.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/net.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 58585ec8699e..bd15309ac5f1 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -782,16 +782,6 @@ static void handle_rx(struct vhost_net *net)
 		/* On error, stop handling until the next kick. */
 		if (unlikely(headcount < 0))
 			goto out;
-		if (nvq->rx_array)
-			msg.msg_control = vhost_net_buf_consume(&nvq->rxq);
-		/* On overrun, truncate and discard */
-		if (unlikely(headcount > UIO_MAXIOV)) {
-			iov_iter_init(&msg.msg_iter, READ, vq->iov, 1, 1);
-			err = sock->ops->recvmsg(sock, &msg,
-						 1, MSG_DONTWAIT | MSG_TRUNC);
-			pr_debug("Discarded rx packet: len %zd\n", sock_len);
-			continue;
-		}
 		/* OK, now we need to know about added descriptors. */
 		if (!headcount) {
 			if (unlikely(vhost_enable_notify(&net->dev, vq))) {
@@ -804,6 +794,16 @@ static void handle_rx(struct vhost_net *net)
 			 * they refilled. */
 			goto out;
 		}
+		if (nvq->rx_array)
+			msg.msg_control = vhost_net_buf_consume(&nvq->rxq);
+		/* On overrun, truncate and discard */
+		if (unlikely(headcount > UIO_MAXIOV)) {
+			iov_iter_init(&msg.msg_iter, READ, vq->iov, 1, 1);
+			err = sock->ops->recvmsg(sock, &msg,
+						 1, MSG_DONTWAIT | MSG_TRUNC);
+			pr_debug("Discarded rx packet: len %zd\n", sock_len);
+			continue;
+		}
 		/* We don't need to be notified again. */
 		iov_iter_init(&msg.msg_iter, READ, vq->iov, in, vhost_len);
 		fixup = msg.msg_iter;
-- 
2.14.3


From 75b018d32fe98ad885da1a39317bae2d1f212355 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?H=C3=A5kon=20Bugge?= <Haakon.Bugge@oracle.com>
Date: Wed, 6 Dec 2017 17:18:28 +0100
Subject: [PATCH 08/33] rds: Fix NULL pointer dereference in __rds_rdma_map
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit f3069c6d33f6ae63a1668737bc78aaaa51bff7ca ]

This is a fix for syzkaller719569, where memory registration was
attempted without any underlying transport being loaded.

Analysis of the case reveals that it is the setsockopt() RDS_GET_MR
(2) and RDS_GET_MR_FOR_DEST (7) that are vulnerable.

Here is an example stack trace when the bug is hit:

BUG: unable to handle kernel NULL pointer dereference at 00000000000000c0
IP: __rds_rdma_map+0x36/0x440 [rds]
PGD 2f93d03067 P4D 2f93d03067 PUD 2f93d02067 PMD 0
Oops: 0000 [#1] SMP
Modules linked in: bridge stp llc tun rpcsec_gss_krb5 nfsv4
dns_resolver nfs fscache rds binfmt_misc sb_edac intel_powerclamp
coretemp kvm_intel kvm irqbypass crct10dif_pclmul c rc32_pclmul
ghash_clmulni_intel pcbc aesni_intel crypto_simd glue_helper cryptd
iTCO_wdt mei_me sg iTCO_vendor_support ipmi_si mei ipmi_devintf nfsd
shpchp pcspkr i2c_i801 ioatd ma ipmi_msghandler wmi lpc_ich mfd_core
auth_rpcgss nfs_acl lockd grace sunrpc ip_tables ext4 mbcache jbd2
mgag200 i2c_algo_bit drm_kms_helper ixgbe syscopyarea ahci sysfillrect
sysimgblt libahci mdio fb_sys_fops ttm ptp libata sd_mod mlx4_core drm
crc32c_intel pps_core megaraid_sas i2c_core dca dm_mirror
dm_region_hash dm_log dm_mod
CPU: 48 PID: 45787 Comm: repro_set2 Not tainted 4.14.2-3.el7uek.x86_64 #2
Hardware name: Oracle Corporation ORACLE SERVER X5-2L/ASM,MOBO TRAY,2U, BIOS 31110000 03/03/2017
task: ffff882f9190db00 task.stack: ffffc9002b994000
RIP: 0010:__rds_rdma_map+0x36/0x440 [rds]
RSP: 0018:ffffc9002b997df0 EFLAGS: 00010202
RAX: 0000000000000000 RBX: ffff882fa2182580 RCX: 0000000000000000
RDX: 0000000000000000 RSI: ffffc9002b997e40 RDI: ffff882fa2182580
RBP: ffffc9002b997e30 R08: 0000000000000000 R09: 0000000000000002
R10: ffff885fb29e3838 R11: 0000000000000000 R12: ffff882fa2182580
R13: ffff882fa2182580 R14: 0000000000000002 R15: 0000000020000ffc
FS:  00007fbffa20b700(0000) GS:ffff882fbfb80000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000000000c0 CR3: 0000002f98a66006 CR4: 00000000001606e0
Call Trace:
 rds_get_mr+0x56/0x80 [rds]
 rds_setsockopt+0x172/0x340 [rds]
 ? __fget_light+0x25/0x60
 ? __fdget+0x13/0x20
 SyS_setsockopt+0x80/0xe0
 do_syscall_64+0x67/0x1b0
 entry_SYSCALL64_slow_path+0x25/0x25
RIP: 0033:0x7fbff9b117f9
RSP: 002b:00007fbffa20aed8 EFLAGS: 00000293 ORIG_RAX: 0000000000000036
RAX: ffffffffffffffda RBX: 00000000000c84a4 RCX: 00007fbff9b117f9
RDX: 0000000000000002 RSI: 0000400000000114 RDI: 000000000000109b
RBP: 00007fbffa20af10 R08: 0000000000000020 R09: 00007fbff9dd7860
R10: 0000000020000ffc R11: 0000000000000293 R12: 0000000000000000
R13: 00007fbffa20b9c0 R14: 00007fbffa20b700 R15: 0000000000000021

Code: 41 56 41 55 49 89 fd 41 54 53 48 83 ec 18 8b 87 f0 02 00 00 48
89 55 d0 48 89 4d c8 85 c0 0f 84 2d 03 00 00 48 8b 87 00 03 00 00 <48>
83 b8 c0 00 00 00 00 0f 84 25 03 00 0 0 48 8b 06 48 8b 56 08

The fix is to check the existence of an underlying transport in
__rds_rdma_map().

Signed-off-by: Håkon Bugge <haakon.bugge@oracle.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/rdma.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/rds/rdma.c b/net/rds/rdma.c
index 8886f15abe90..bc2f1e0977d6 100644
--- a/net/rds/rdma.c
+++ b/net/rds/rdma.c
@@ -183,7 +183,7 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args,
 	long i;
 	int ret;
 
-	if (rs->rs_bound_addr == 0) {
+	if (rs->rs_bound_addr == 0 || !rs->rs_transport) {
 		ret = -ENOTCONN; /* XXX not a great errno */
 		goto out;
 	}
-- 
2.14.3


From 5676f91d5d58051a21b799c16a84887ff3a61c7c Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Thu, 30 Nov 2017 10:41:14 +0800
Subject: [PATCH 09/33] sit: update frag_off info

[ Upstream commit f859b4af1c52493ec21173ccc73d0b60029b5b88 ]

After parsing the sit netlink change info, we forget to update frag_off in
ipip6_tunnel_update(). Fix it by assigning frag_off with new value.

Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index ac912bb21747..e79854cc5790 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1087,6 +1087,7 @@ static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p,
 	ipip6_tunnel_link(sitn, t);
 	t->parms.iph.ttl = p->iph.ttl;
 	t->parms.iph.tos = p->iph.tos;
+	t->parms.iph.frag_off = p->iph.frag_off;
 	if (t->parms.link != p->link || t->fwmark != fwmark) {
 		t->parms.link = p->link;
 		t->fwmark = fwmark;
-- 
2.14.3


From 616b8a959db544b10ba706bcbd6dc0670fa6f255 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 3 Dec 2017 09:32:59 -0800
Subject: [PATCH 10/33] tcp: add tcp_v4_fill_cb()/tcp_v4_restore_cb()

[ Upstream commit eeea10b83a139451130df1594f26710c8fa390c8 ]

James Morris reported kernel stack corruption bug [1] while
running the SELinux testsuite, and bisected to a recent
commit bffa72cf7f9d ("net: sk_buff rbnode reorg")

We believe this commit is fine, but exposes an older bug.

SELinux code runs from tcp_filter() and might send an ICMP,
expecting IP options to be found in skb->cb[] using regular IPCB placement.

We need to defer TCP mangling of skb->cb[] after tcp_filter() calls.

This patch adds tcp_v4_fill_cb()/tcp_v4_restore_cb() in a very
similar way we added them for IPv6.

[1]
[  339.806024] SELinux: failure in selinux_parse_skb(), unable to parse packet
[  339.822505] Kernel panic - not syncing: stack-protector: Kernel stack is corrupted in: ffffffff81745af5
[  339.822505]
[  339.852250] CPU: 4 PID: 3642 Comm: client Not tainted 4.15.0-rc1-test #15
[  339.868498] Hardware name: LENOVO 10FGS0VA1L/30BC, BIOS FWKT68A   01/19/2017
[  339.885060] Call Trace:
[  339.896875]  <IRQ>
[  339.908103]  dump_stack+0x63/0x87
[  339.920645]  panic+0xe8/0x248
[  339.932668]  ? ip_push_pending_frames+0x33/0x40
[  339.946328]  ? icmp_send+0x525/0x530
[  339.958861]  ? kfree_skbmem+0x60/0x70
[  339.971431]  __stack_chk_fail+0x1b/0x20
[  339.984049]  icmp_send+0x525/0x530
[  339.996205]  ? netlbl_skbuff_err+0x36/0x40
[  340.008997]  ? selinux_netlbl_err+0x11/0x20
[  340.021816]  ? selinux_socket_sock_rcv_skb+0x211/0x230
[  340.035529]  ? security_sock_rcv_skb+0x3b/0x50
[  340.048471]  ? sk_filter_trim_cap+0x44/0x1c0
[  340.061246]  ? tcp_v4_inbound_md5_hash+0x69/0x1b0
[  340.074562]  ? tcp_filter+0x2c/0x40
[  340.086400]  ? tcp_v4_rcv+0x820/0xa20
[  340.098329]  ? ip_local_deliver_finish+0x71/0x1a0
[  340.111279]  ? ip_local_deliver+0x6f/0xe0
[  340.123535]  ? ip_rcv_finish+0x3a0/0x3a0
[  340.135523]  ? ip_rcv_finish+0xdb/0x3a0
[  340.147442]  ? ip_rcv+0x27c/0x3c0
[  340.158668]  ? inet_del_offload+0x40/0x40
[  340.170580]  ? __netif_receive_skb_core+0x4ac/0x900
[  340.183285]  ? rcu_accelerate_cbs+0x5b/0x80
[  340.195282]  ? __netif_receive_skb+0x18/0x60
[  340.207288]  ? process_backlog+0x95/0x140
[  340.218948]  ? net_rx_action+0x26c/0x3b0
[  340.230416]  ? __do_softirq+0xc9/0x26a
[  340.241625]  ? do_softirq_own_stack+0x2a/0x40
[  340.253368]  </IRQ>
[  340.262673]  ? do_softirq+0x50/0x60
[  340.273450]  ? __local_bh_enable_ip+0x57/0x60
[  340.285045]  ? ip_finish_output2+0x175/0x350
[  340.296403]  ? ip_finish_output+0x127/0x1d0
[  340.307665]  ? nf_hook_slow+0x3c/0xb0
[  340.318230]  ? ip_output+0x72/0xe0
[  340.328524]  ? ip_fragment.constprop.54+0x80/0x80
[  340.340070]  ? ip_local_out+0x35/0x40
[  340.350497]  ? ip_queue_xmit+0x15c/0x3f0
[  340.361060]  ? __kmalloc_reserve.isra.40+0x31/0x90
[  340.372484]  ? __skb_clone+0x2e/0x130
[  340.382633]  ? tcp_transmit_skb+0x558/0xa10
[  340.393262]  ? tcp_connect+0x938/0xad0
[  340.403370]  ? ktime_get_with_offset+0x4c/0xb0
[  340.414206]  ? tcp_v4_connect+0x457/0x4e0
[  340.424471]  ? __inet_stream_connect+0xb3/0x300
[  340.435195]  ? inet_stream_connect+0x3b/0x60
[  340.445607]  ? SYSC_connect+0xd9/0x110
[  340.455455]  ? __audit_syscall_entry+0xaf/0x100
[  340.466112]  ? syscall_trace_enter+0x1d0/0x2b0
[  340.476636]  ? __audit_syscall_exit+0x209/0x290
[  340.487151]  ? SyS_connect+0xe/0x10
[  340.496453]  ? do_syscall_64+0x67/0x1b0
[  340.506078]  ? entry_SYSCALL64_slow_path+0x25/0x25

Fixes: 971f10eca186 ("tcp: better TCP_SKB_CB layout to reduce cache line misses")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: James Morris <james.l.morris@oracle.com>
Tested-by: James Morris <james.l.morris@oracle.com>
Tested-by: Casey Schaufler <casey@schaufler-ca.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c | 59 ++++++++++++++++++++++++++++++++++++-----------------
 net/ipv6/tcp_ipv6.c | 10 +++++----
 2 files changed, 46 insertions(+), 23 deletions(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 5b027c69cbc5..5a5ed4f14678 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1587,6 +1587,34 @@ int tcp_filter(struct sock *sk, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(tcp_filter);
 
+static void tcp_v4_restore_cb(struct sk_buff *skb)
+{
+	memmove(IPCB(skb), &TCP_SKB_CB(skb)->header.h4,
+		sizeof(struct inet_skb_parm));
+}
+
+static void tcp_v4_fill_cb(struct sk_buff *skb, const struct iphdr *iph,
+			   const struct tcphdr *th)
+{
+	/* This is tricky : We move IPCB at its correct location into TCP_SKB_CB()
+	 * barrier() makes sure compiler wont play fool^Waliasing games.
+	 */
+	memmove(&TCP_SKB_CB(skb)->header.h4, IPCB(skb),
+		sizeof(struct inet_skb_parm));
+	barrier();
+
+	TCP_SKB_CB(skb)->seq = ntohl(th->seq);
+	TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
+				    skb->len - th->doff * 4);
+	TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
+	TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
+	TCP_SKB_CB(skb)->tcp_tw_isn = 0;
+	TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph);
+	TCP_SKB_CB(skb)->sacked	 = 0;
+	TCP_SKB_CB(skb)->has_rxtstamp =
+			skb->tstamp || skb_hwtstamps(skb)->hwtstamp;
+}
+
 /*
  *	From tcp_input.c
  */
@@ -1627,24 +1655,6 @@ int tcp_v4_rcv(struct sk_buff *skb)
 
 	th = (const struct tcphdr *)skb->data;
 	iph = ip_hdr(skb);
-	/* This is tricky : We move IPCB at its correct location into TCP_SKB_CB()
-	 * barrier() makes sure compiler wont play fool^Waliasing games.
-	 */
-	memmove(&TCP_SKB_CB(skb)->header.h4, IPCB(skb),
-		sizeof(struct inet_skb_parm));
-	barrier();
-
-	TCP_SKB_CB(skb)->seq = ntohl(th->seq);
-	TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
-				    skb->len - th->doff * 4);
-	TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
-	TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
-	TCP_SKB_CB(skb)->tcp_tw_isn = 0;
-	TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph);
-	TCP_SKB_CB(skb)->sacked	 = 0;
-	TCP_SKB_CB(skb)->has_rxtstamp =
-			skb->tstamp || skb_hwtstamps(skb)->hwtstamp;
-
 lookup:
 	sk = __inet_lookup_skb(&tcp_hashinfo, skb, __tcp_hdrlen(th), th->source,
 			       th->dest, sdif, &refcounted);
@@ -1675,14 +1685,19 @@ int tcp_v4_rcv(struct sk_buff *skb)
 		sock_hold(sk);
 		refcounted = true;
 		nsk = NULL;
-		if (!tcp_filter(sk, skb))
+		if (!tcp_filter(sk, skb)) {
+			th = (const struct tcphdr *)skb->data;
+			iph = ip_hdr(skb);
+			tcp_v4_fill_cb(skb, iph, th);
 			nsk = tcp_check_req(sk, skb, req, false);
+		}
 		if (!nsk) {
 			reqsk_put(req);
 			goto discard_and_relse;
 		}
 		if (nsk == sk) {
 			reqsk_put(req);
+			tcp_v4_restore_cb(skb);
 		} else if (tcp_child_process(sk, nsk, skb)) {
 			tcp_v4_send_reset(nsk, skb);
 			goto discard_and_relse;
@@ -1708,6 +1723,7 @@ int tcp_v4_rcv(struct sk_buff *skb)
 		goto discard_and_relse;
 	th = (const struct tcphdr *)skb->data;
 	iph = ip_hdr(skb);
+	tcp_v4_fill_cb(skb, iph, th);
 
 	skb->dev = NULL;
 
@@ -1738,6 +1754,8 @@ int tcp_v4_rcv(struct sk_buff *skb)
 	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
 		goto discard_it;
 
+	tcp_v4_fill_cb(skb, iph, th);
+
 	if (tcp_checksum_complete(skb)) {
 csum_error:
 		__TCP_INC_STATS(net, TCP_MIB_CSUMERRORS);
@@ -1764,6 +1782,8 @@ int tcp_v4_rcv(struct sk_buff *skb)
 		goto discard_it;
 	}
 
+	tcp_v4_fill_cb(skb, iph, th);
+
 	if (tcp_checksum_complete(skb)) {
 		inet_twsk_put(inet_twsk(sk));
 		goto csum_error;
@@ -1780,6 +1800,7 @@ int tcp_v4_rcv(struct sk_buff *skb)
 		if (sk2) {
 			inet_twsk_deschedule_put(inet_twsk(sk));
 			sk = sk2;
+			tcp_v4_restore_cb(skb);
 			refcounted = false;
 			goto process;
 		}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 64d94afa427f..067350ac843a 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1448,7 +1448,6 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 		struct sock *nsk;
 
 		sk = req->rsk_listener;
-		tcp_v6_fill_cb(skb, hdr, th);
 		if (tcp_v6_inbound_md5_hash(sk, skb)) {
 			sk_drops_add(sk, skb);
 			reqsk_put(req);
@@ -1461,8 +1460,12 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 		sock_hold(sk);
 		refcounted = true;
 		nsk = NULL;
-		if (!tcp_filter(sk, skb))
+		if (!tcp_filter(sk, skb)) {
+			th = (const struct tcphdr *)skb->data;
+			hdr = ipv6_hdr(skb);
+			tcp_v6_fill_cb(skb, hdr, th);
 			nsk = tcp_check_req(sk, skb, req, false);
+		}
 		if (!nsk) {
 			reqsk_put(req);
 			goto discard_and_relse;
@@ -1486,8 +1489,6 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 	if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
 		goto discard_and_relse;
 
-	tcp_v6_fill_cb(skb, hdr, th);
-
 	if (tcp_v6_inbound_md5_hash(sk, skb))
 		goto discard_and_relse;
 
@@ -1495,6 +1496,7 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 		goto discard_and_relse;
 	th = (const struct tcphdr *)skb->data;
 	hdr = ipv6_hdr(skb);
+	tcp_v6_fill_cb(skb, hdr, th);
 
 	skb->dev = NULL;
 
-- 
2.14.3


From 4362bc56455bc906696b6be86ee9172cb5924091 Mon Sep 17 00:00:00 2001
From: Mike Maloney <maloney@google.com>
Date: Tue, 28 Nov 2017 10:44:29 -0500
Subject: [PATCH 11/33] packet: fix crash in fanout_demux_rollover()

syzkaller found a race condition fanout_demux_rollover() while removing
a packet socket from a fanout group.

po->rollover is read and operated on during packet_rcv_fanout(), via
fanout_demux_rollover(), but the pointer is currently cleared before the
synchronization in packet_release().   It is safer to delay the cleanup
until after synchronize_net() has been called, ensuring all calls to
packet_rcv_fanout() for this socket have finished.

To further simplify synchronization around the rollover structure, set
po->rollover in fanout_add() only if there are no errors.  This removes
the need for rcu in the struct and in the call to
packet_getsockopt(..., PACKET_ROLLOVER_STATS, ...).

Crashing stack trace:
 fanout_demux_rollover+0xb6/0x4d0 net/packet/af_packet.c:1392
 packet_rcv_fanout+0x649/0x7c8 net/packet/af_packet.c:1487
 dev_queue_xmit_nit+0x835/0xc10 net/core/dev.c:1953
 xmit_one net/core/dev.c:2975 [inline]
 dev_hard_start_xmit+0x16b/0xac0 net/core/dev.c:2995
 __dev_queue_xmit+0x17a4/0x2050 net/core/dev.c:3476
 dev_queue_xmit+0x17/0x20 net/core/dev.c:3509
 neigh_connected_output+0x489/0x720 net/core/neighbour.c:1379
 neigh_output include/net/neighbour.h:482 [inline]
 ip6_finish_output2+0xad1/0x22a0 net/ipv6/ip6_output.c:120
 ip6_finish_output+0x2f9/0x920 net/ipv6/ip6_output.c:146
 NF_HOOK_COND include/linux/netfilter.h:239 [inline]
 ip6_output+0x1f4/0x850 net/ipv6/ip6_output.c:163
 dst_output include/net/dst.h:459 [inline]
 NF_HOOK.constprop.35+0xff/0x630 include/linux/netfilter.h:250
 mld_sendpack+0x6a8/0xcc0 net/ipv6/mcast.c:1660
 mld_send_initial_cr.part.24+0x103/0x150 net/ipv6/mcast.c:2072
 mld_send_initial_cr net/ipv6/mcast.c:2056 [inline]
 ipv6_mc_dad_complete+0x99/0x130 net/ipv6/mcast.c:2079
 addrconf_dad_completed+0x595/0x970 net/ipv6/addrconf.c:4039
 addrconf_dad_work+0xac9/0x1160 net/ipv6/addrconf.c:3971
 process_one_work+0xbf0/0x1bc0 kernel/workqueue.c:2113
 worker_thread+0x223/0x1990 kernel/workqueue.c:2247
 kthread+0x35e/0x430 kernel/kthread.c:231
 ret_from_fork+0x2a/0x40 arch/x86/entry/entry_64.S:432

Fixes: 0648ab70afe6 ("packet: rollover prepare: per-socket state")
Fixes: 509c7a1ecc860 ("packet: avoid panic in packet_getsockopt()")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Mike Maloney <maloney@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 32 ++++++++++----------------------
 net/packet/internal.h  |  1 -
 2 files changed, 10 insertions(+), 23 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 2986941164b1..2eb4f1e5b861 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1697,7 +1697,6 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		atomic_long_set(&rollover->num, 0);
 		atomic_long_set(&rollover->num_huge, 0);
 		atomic_long_set(&rollover->num_failed, 0);
-		po->rollover = rollover;
 	}
 
 	if (type_flags & PACKET_FANOUT_FLAG_UNIQUEID) {
@@ -1755,6 +1754,8 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		if (refcount_read(&match->sk_ref) < PACKET_FANOUT_MAX) {
 			__dev_remove_pack(&po->prot_hook);
 			po->fanout = match;
+			po->rollover = rollover;
+			rollover = NULL;
 			refcount_set(&match->sk_ref, refcount_read(&match->sk_ref) + 1);
 			__fanout_link(sk, po);
 			err = 0;
@@ -1768,10 +1769,7 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 	}
 
 out:
-	if (err && rollover) {
-		kfree_rcu(rollover, rcu);
-		po->rollover = NULL;
-	}
+	kfree(rollover);
 	mutex_unlock(&fanout_mutex);
 	return err;
 }
@@ -1795,11 +1793,6 @@ static struct packet_fanout *fanout_release(struct sock *sk)
 			list_del(&f->list);
 		else
 			f = NULL;
-
-		if (po->rollover) {
-			kfree_rcu(po->rollover, rcu);
-			po->rollover = NULL;
-		}
 	}
 	mutex_unlock(&fanout_mutex);
 
@@ -3039,6 +3032,7 @@ static int packet_release(struct socket *sock)
 	synchronize_net();
 
 	if (f) {
+		kfree(po->rollover);
 		fanout_release_data(f);
 		kfree(f);
 	}
@@ -3853,7 +3847,6 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
 	void *data = &val;
 	union tpacket_stats_u st;
 	struct tpacket_rollover_stats rstats;
-	struct packet_rollover *rollover;
 
 	if (level != SOL_PACKET)
 		return -ENOPROTOOPT;
@@ -3932,18 +3925,13 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
 		       0);
 		break;
 	case PACKET_ROLLOVER_STATS:
-		rcu_read_lock();
-		rollover = rcu_dereference(po->rollover);
-		if (rollover) {
-			rstats.tp_all = atomic_long_read(&rollover->num);
-			rstats.tp_huge = atomic_long_read(&rollover->num_huge);
-			rstats.tp_failed = atomic_long_read(&rollover->num_failed);
-			data = &rstats;
-			lv = sizeof(rstats);
-		}
-		rcu_read_unlock();
-		if (!rollover)
+		if (!po->rollover)
 			return -EINVAL;
+		rstats.tp_all = atomic_long_read(&po->rollover->num);
+		rstats.tp_huge = atomic_long_read(&po->rollover->num_huge);
+		rstats.tp_failed = atomic_long_read(&po->rollover->num_failed);
+		data = &rstats;
+		lv = sizeof(rstats);
 		break;
 	case PACKET_TX_HAS_OFF:
 		val = po->tp_tx_has_off;
diff --git a/net/packet/internal.h b/net/packet/internal.h
index 562fbc155006..a1d2b2319ae9 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -95,7 +95,6 @@ struct packet_fanout {
 
 struct packet_rollover {
 	int			sock;
-	struct rcu_head		rcu;
 	atomic_long_t		num;
 	atomic_long_t		num_huge;
 	atomic_long_t		num_failed;
-- 
2.14.3


From ff80c760c75845bd2c678967701e71198928591e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 28 Nov 2017 08:03:30 -0800
Subject: [PATCH 12/33] net/packet: fix a race in packet_bind() and
 packet_notifier()

[ Upstream commit 15fe076edea787807a7cdc168df832544b58eba6 ]

syzbot reported crashes [1] and provided a C repro easing bug hunting.

When/if packet_do_bind() calls __unregister_prot_hook() and releases
po->bind_lock, another thread can run packet_notifier() and process an
NETDEV_UP event.

This calls register_prot_hook() and hooks again the socket right before
first thread is able to grab again po->bind_lock.

Fixes this issue by temporarily setting po->num to 0, as suggested by
David Miller.

[1]
dev_remove_pack: ffff8801bf16fa80 not found
------------[ cut here ]------------
kernel BUG at net/core/dev.c:7945!  ( BUG_ON(!list_empty(&dev->ptype_all)); )
invalid opcode: 0000 [#1] SMP KASAN
Dumping ftrace buffer:
   (ftrace buffer empty)
Modules linked in:
device syz0 entered promiscuous mode
CPU: 0 PID: 3161 Comm: syzkaller404108 Not tainted 4.14.0+ #190
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
task: ffff8801cc57a500 task.stack: ffff8801cc588000
RIP: 0010:netdev_run_todo+0x772/0xae0 net/core/dev.c:7945
RSP: 0018:ffff8801cc58f598 EFLAGS: 00010293
RAX: ffff8801cc57a500 RBX: dffffc0000000000 RCX: ffffffff841f75b2
RDX: 0000000000000000 RSI: 1ffff100398b1ede RDI: ffff8801bf1f8810
device syz0 entered promiscuous mode
RBP: ffff8801cc58f898 R08: 0000000000000001 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: ffff8801bf1f8cd8
R13: ffff8801cc58f870 R14: ffff8801bf1f8780 R15: ffff8801cc58f7f0
FS:  0000000001716880(0000) GS:ffff8801db400000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000020b13000 CR3: 0000000005e25000 CR4: 00000000001406f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 rtnl_unlock+0xe/0x10 net/core/rtnetlink.c:106
 tun_detach drivers/net/tun.c:670 [inline]
 tun_chr_close+0x49/0x60 drivers/net/tun.c:2845
 __fput+0x333/0x7f0 fs/file_table.c:210
 ____fput+0x15/0x20 fs/file_table.c:244
 task_work_run+0x199/0x270 kernel/task_work.c:113
 exit_task_work include/linux/task_work.h:22 [inline]
 do_exit+0x9bb/0x1ae0 kernel/exit.c:865
 do_group_exit+0x149/0x400 kernel/exit.c:968
 SYSC_exit_group kernel/exit.c:979 [inline]
 SyS_exit_group+0x1d/0x20 kernel/exit.c:977
 entry_SYSCALL_64_fastpath+0x1f/0x96
RIP: 0033:0x44ad19

Fixes: 30f7ea1c2b5f ("packet: race condition in packet_bind")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Francesco Ruggeri <fruggeri@aristanetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 2eb4f1e5b861..f4a0587b7d5e 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3101,6 +3101,10 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex,
 	if (need_rehook) {
 		if (po->running) {
 			rcu_read_unlock();
+			/* prevents packet_notifier() from calling
+			 * register_prot_hook()
+			 */
+			po->num = 0;
 			__unregister_prot_hook(sk, true);
 			rcu_read_lock();
 			dev_curr = po->prot_hook.dev;
@@ -3109,6 +3113,7 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex,
 								 dev->ifindex);
 		}
 
+		BUG_ON(po->running);
 		po->num = proto;
 		po->prot_hook.type = proto;
 
-- 
2.14.3


From 4fb8792084c9a3a82c7ff89d100cf8ea35007503 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 29 Nov 2017 17:43:57 -0800
Subject: [PATCH 13/33] tcp: remove buggy call to tcp_v6_restore_cb()

[ Upstream commit 3016dad75b48279e579117ee3ed566ba90a3b023 ]

tcp_v6_send_reset() expects to receive an skb with skb->cb[] layout as
used in TCP stack.
MD5 lookup uses tcp_v6_iif() and tcp_v6_sdif() and thus
TCP_SKB_CB(skb)->header.h6

This patch probably fixes RST packets sent on behalf of a timewait md5
ipv6 socket.

Before Florian patch, tcp_v6_restore_cb() was needed before jumping to
no_tcp_socket label.

Fixes: 271c3b9b7bda ("tcp: honour SO_BINDTODEVICE for TW_RST case too")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Florian Westphal <fw@strlen.de>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/tcp_ipv6.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 067350ac843a..32ded300633d 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1585,7 +1585,6 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 		tcp_v6_timewait_ack(sk, skb);
 		break;
 	case TCP_TW_RST:
-		tcp_v6_restore_cb(skb);
 		tcp_v6_send_reset(sk, skb);
 		inet_twsk_deschedule_put(inet_twsk(sk));
 		goto discard_it;
-- 
2.14.3


From e07bfc3e58a8233d64236c21ad7e0e78eb5be4e5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Wed, 6 Dec 2017 20:21:24 +0100
Subject: [PATCH 14/33] usbnet: fix alignment for frames with no ethernet
 header
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit a4abd7a80addb4a9547f7dfc7812566b60ec505c ]

The qmi_wwan minidriver support a 'raw-ip' mode where frames are
received without any ethernet header. This causes alignment issues
because the skbs allocated by usbnet are "IP aligned".

Fix by allowing minidrivers to disable the additional alignment
offset. This is implemented using a per-device flag, since the same
minidriver also supports 'ethernet' mode.

Fixes: 32f7adf633b9 ("net: qmi_wwan: support "raw IP" mode")
Reported-and-tested-by: Jay Foster <jay@systech.com>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 2 ++
 drivers/net/usb/usbnet.c   | 5 ++++-
 include/linux/usb/usbnet.h | 1 +
 3 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index f4ed553929f0..81394a4b2803 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -261,9 +261,11 @@ static void qmi_wwan_netdev_setup(struct net_device *net)
 		net->hard_header_len = 0;
 		net->addr_len        = 0;
 		net->flags           = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST;
+		set_bit(EVENT_NO_IP_ALIGN, &dev->flags);
 		netdev_dbg(net, "mode: raw IP\n");
 	} else if (!net->header_ops) { /* don't bother if already set */
 		ether_setup(net);
+		clear_bit(EVENT_NO_IP_ALIGN, &dev->flags);
 		netdev_dbg(net, "mode: Ethernet\n");
 	}
 
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 6510e5cc1817..42baad125a7d 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -484,7 +484,10 @@ static int rx_submit (struct usbnet *dev, struct urb *urb, gfp_t flags)
 		return -ENOLINK;
 	}
 
-	skb = __netdev_alloc_skb_ip_align(dev->net, size, flags);
+	if (test_bit(EVENT_NO_IP_ALIGN, &dev->flags))
+		skb = __netdev_alloc_skb(dev->net, size, flags);
+	else
+		skb = __netdev_alloc_skb_ip_align(dev->net, size, flags);
 	if (!skb) {
 		netif_dbg(dev, rx_err, dev->net, "no rx skb\n");
 		usbnet_defer_kevent (dev, EVENT_RX_MEMORY);
diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index 97116379db5f..e87a805cbfef 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -81,6 +81,7 @@ struct usbnet {
 #		define EVENT_RX_KILL	10
 #		define EVENT_LINK_CHANGE	11
 #		define EVENT_SET_RX_MODE	12
+#		define EVENT_NO_IP_ALIGN	13
 };
 
 static inline struct usb_driver *driver_of(struct usb_interface *intf)
-- 
2.14.3


From c6fc279706d1b8a2ff03c2e5c0953eb6f092545c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 5 Dec 2017 12:45:56 -0800
Subject: [PATCH 15/33] net: remove hlist_nulls_add_tail_rcu()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit d7efc6c11b277d9d80b99b1334a78bfe7d7edf10 ]

Alexander Potapenko reported use of uninitialized memory [1]

This happens when inserting a request socket into TCP ehash,
in __sk_nulls_add_node_rcu(), since sk_reuseport is not initialized.

Bug was added by commit d894ba18d4e4 ("soreuseport: fix ordering for
mixed v4/v6 sockets")

Note that d296ba60d8e2 ("soreuseport: Resolve merge conflict for v4/v6
ordering fix") missed the opportunity to get rid of
hlist_nulls_add_tail_rcu() :

Both UDP sockets and TCP/DCCP listeners no longer use
__sk_nulls_add_node_rcu() for their hash insertion.

Since all other sockets have unique 4-tuple, the reuseport status
has no special meaning, so we can always use hlist_nulls_add_head_rcu()
for them and save few cycles/instructions.

[1]

==================================================================
BUG: KMSAN: use of uninitialized memory in inet_ehash_insert+0xd40/0x1050
CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.13.0+ #3288
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:16
 dump_stack+0x185/0x1d0 lib/dump_stack.c:52
 kmsan_report+0x13f/0x1c0 mm/kmsan/kmsan.c:1016
 __msan_warning_32+0x69/0xb0 mm/kmsan/kmsan_instr.c:766
 __sk_nulls_add_node_rcu ./include/net/sock.h:684
 inet_ehash_insert+0xd40/0x1050 net/ipv4/inet_hashtables.c:413
 reqsk_queue_hash_req net/ipv4/inet_connection_sock.c:754
 inet_csk_reqsk_queue_hash_add+0x1cc/0x300 net/ipv4/inet_connection_sock.c:765
 tcp_conn_request+0x31e7/0x36f0 net/ipv4/tcp_input.c:6414
 tcp_v4_conn_request+0x16d/0x220 net/ipv4/tcp_ipv4.c:1314
 tcp_rcv_state_process+0x42a/0x7210 net/ipv4/tcp_input.c:5917
 tcp_v4_do_rcv+0xa6a/0xcd0 net/ipv4/tcp_ipv4.c:1483
 tcp_v4_rcv+0x3de0/0x4ab0 net/ipv4/tcp_ipv4.c:1763
 ip_local_deliver_finish+0x6bb/0xcb0 net/ipv4/ip_input.c:216
 NF_HOOK ./include/linux/netfilter.h:248
 ip_local_deliver+0x3fa/0x480 net/ipv4/ip_input.c:257
 dst_input ./include/net/dst.h:477
 ip_rcv_finish+0x6fb/0x1540 net/ipv4/ip_input.c:397
 NF_HOOK ./include/linux/netfilter.h:248
 ip_rcv+0x10f6/0x15c0 net/ipv4/ip_input.c:488
 __netif_receive_skb_core+0x36f6/0x3f60 net/core/dev.c:4298
 __netif_receive_skb net/core/dev.c:4336
 netif_receive_skb_internal+0x63c/0x19c0 net/core/dev.c:4497
 napi_skb_finish net/core/dev.c:4858
 napi_gro_receive+0x629/0xa50 net/core/dev.c:4889
 e1000_receive_skb drivers/net/ethernet/intel/e1000/e1000_main.c:4018
 e1000_clean_rx_irq+0x1492/0x1d30
drivers/net/ethernet/intel/e1000/e1000_main.c:4474
 e1000_clean+0x43aa/0x5970 drivers/net/ethernet/intel/e1000/e1000_main.c:3819
 napi_poll net/core/dev.c:5500
 net_rx_action+0x73c/0x1820 net/core/dev.c:5566
 __do_softirq+0x4b4/0x8dd kernel/softirq.c:284
 invoke_softirq kernel/softirq.c:364
 irq_exit+0x203/0x240 kernel/softirq.c:405
 exiting_irq+0xe/0x10 ./arch/x86/include/asm/apic.h:638
 do_IRQ+0x15e/0x1a0 arch/x86/kernel/irq.c:263
 common_interrupt+0x86/0x86

Fixes: d894ba18d4e4 ("soreuseport: fix ordering for mixed v4/v6 sockets")
Fixes: d296ba60d8e2 ("soreuseport: Resolve merge conflict for v4/v6 ordering fix")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Alexander Potapenko <glider@google.com>
Acked-by: Craig Gallek <kraig@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rculist_nulls.h | 38 --------------------------------------
 include/net/sock.h            |  6 +-----
 2 files changed, 1 insertion(+), 43 deletions(-)

diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h
index a328e8181e49..e4b257ff881b 100644
--- a/include/linux/rculist_nulls.h
+++ b/include/linux/rculist_nulls.h
@@ -100,44 +100,6 @@ static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n,
 		first->pprev = &n->next;
 }
 
-/**
- * hlist_nulls_add_tail_rcu
- * @n: the element to add to the hash list.
- * @h: the list to add to.
- *
- * Description:
- * Adds the specified element to the end of the specified hlist_nulls,
- * while permitting racing traversals.  NOTE: tail insertion requires
- * list traversal.
- *
- * The caller must take whatever precautions are necessary
- * (such as holding appropriate locks) to avoid racing
- * with another list-mutation primitive, such as hlist_nulls_add_head_rcu()
- * or hlist_nulls_del_rcu(), running on this same list.
- * However, it is perfectly legal to run concurrently with
- * the _rcu list-traversal primitives, such as
- * hlist_nulls_for_each_entry_rcu(), used to prevent memory-consistency
- * problems on Alpha CPUs.  Regardless of the type of CPU, the
- * list-traversal primitive must be guarded by rcu_read_lock().
- */
-static inline void hlist_nulls_add_tail_rcu(struct hlist_nulls_node *n,
-					struct hlist_nulls_head *h)
-{
-	struct hlist_nulls_node *i, *last = NULL;
-
-	for (i = hlist_nulls_first_rcu(h); !is_a_nulls(i);
-	     i = hlist_nulls_next_rcu(i))
-		last = i;
-
-	if (last) {
-		n->next = last->next;
-		n->pprev = &last->next;
-		rcu_assign_pointer(hlist_nulls_next_rcu(last), n);
-	} else {
-		hlist_nulls_add_head_rcu(n, h);
-	}
-}
-
 /**
  * hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type
  * @tpos:	the type * to use as a loop cursor.
diff --git a/include/net/sock.h b/include/net/sock.h
index a6b9a8d1a6df..006580155a87 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -683,11 +683,7 @@ static inline void sk_add_node_rcu(struct sock *sk, struct hlist_head *list)
 
 static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
 {
-	if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport &&
-	    sk->sk_family == AF_INET6)
-		hlist_nulls_add_tail_rcu(&sk->sk_nulls_node, list);
-	else
-		hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list);
+	hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list);
 }
 
 static inline void sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
-- 
2.14.3


From c889856a615131825f88467e91d8089590cd0123 Mon Sep 17 00:00:00 2001
From: Lars Persson <lars.persson@axis.com>
Date: Fri, 1 Dec 2017 11:12:44 +0100
Subject: [PATCH 16/33] stmmac: reset last TSO segment size after device open

[ Upstream commit 45ab4b13e46325d00f4acdb365d406e941a15f81 ]

The mss variable tracks the last max segment size sent to the TSO
engine. We do not update the hardware as long as we receive skb:s with
the same value in gso_size.

During a network device down/up cycle (mapped to stmmac_release() and
stmmac_open() callbacks) we issue a reset to the hardware and it
forgets the setting for mss. However we did not zero out our mss
variable so the next transmission of a gso packet happens with an
undefined hardware setting.

This triggers a hang in the TSO engine and eventuelly the netdev
watchdog will bark.

Fixes: f748be531d70 ("stmmac: support new GMAC4")
Signed-off-by: Lars Persson <larper@axis.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 16bd50929084..28c4d6fa096c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2564,6 +2564,7 @@ static int stmmac_open(struct net_device *dev)
 
 	priv->dma_buf_sz = STMMAC_ALIGN(buf_sz);
 	priv->rx_copybreak = STMMAC_RX_COPYBREAK;
+	priv->mss = 0;
 
 	ret = alloc_dma_desc_resources(priv);
 	if (ret < 0) {
-- 
2.14.3


From a658f69eb93742e3f5e0109d5f212eb3bc3e1585 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 1 Dec 2017 10:06:56 -0800
Subject: [PATCH 17/33] tcp/dccp: block bh before arming time_wait timer
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit cfac7f836a715b91f08c851df915d401a4d52783 ]

Maciej Żenczykowski reported some panics in tcp_twsk_destructor()
that might be caused by the following bug.

timewait timer is pinned to the cpu, because we want to transition
timwewait refcount from 0 to 4 in one go, once everything has been
initialized.

At the time commit ed2e92394589 ("tcp/dccp: fix timewait races in timer
handling") was merged, TCP was always running from BH habdler.

After commit 5413d1babe8f ("net: do not block BH while processing
socket backlog") we definitely can run tcp_time_wait() from process
context.

We need to block BH in the critical section so that the pinned timer
has still its purpose.

This bug is more likely to happen under stress and when very small RTO
are used in datacenter flows.

Fixes: 5413d1babe8f ("net: do not block BH while processing socket backlog")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Maciej Żenczykowski <maze@google.com>
Acked-by: Maciej Żenczykowski <maze@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/minisocks.c     | 6 ++++++
 net/ipv4/tcp_minisocks.c | 6 ++++++
 2 files changed, 12 insertions(+)

diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index abd07a443219..178bb9833311 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -57,10 +57,16 @@ void dccp_time_wait(struct sock *sk, int state, int timeo)
 		if (state == DCCP_TIME_WAIT)
 			timeo = DCCP_TIMEWAIT_LEN;
 
+		/* tw_timer is pinned, so we need to make sure BH are disabled
+		 * in following section, otherwise timer handler could run before
+		 * we complete the initialization.
+		 */
+		local_bh_disable();
 		inet_twsk_schedule(tw, timeo);
 		/* Linkage updates. */
 		__inet_twsk_hashdance(tw, sk, &dccp_hashinfo);
 		inet_twsk_put(tw);
+		local_bh_enable();
 	} else {
 		/* Sorry, if we're out of memory, just CLOSE this
 		 * socket up.  We've got bigger problems than
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 188a6f31356d..420fecbb98fe 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -312,10 +312,16 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 		if (state == TCP_TIME_WAIT)
 			timeo = TCP_TIMEWAIT_LEN;
 
+		/* tw_timer is pinned, so we need to make sure BH are disabled
+		 * in following section, otherwise timer handler could run before
+		 * we complete the initialization.
+		 */
+		local_bh_disable();
 		inet_twsk_schedule(tw, timeo);
 		/* Linkage updates. */
 		__inet_twsk_hashdance(tw, sk, &tcp_hashinfo);
 		inet_twsk_put(tw);
+		local_bh_enable();
 	} else {
 		/* Sorry, if we're out of memory, just CLOSE this
 		 * socket up.  We've got bigger problems than
-- 
2.14.3


From 9bd23d386b16df048b928a5c97eae3a4444c3ac4 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Fri, 1 Dec 2017 10:14:51 +0100
Subject: [PATCH 18/33] s390/qeth: build max size GSO skbs on L2 devices

[ Upstream commit 0cbff6d4546613330a1c5f139f5c368e4ce33ca1 ]

The current GSO skb size limit was copy&pasted over from the L3 path,
where it is needed due to a TSO limitation.
As L2 devices don't offer TSO support (and thus all GSO skbs are
segmented before they reach the driver), there's no reason to restrict
the stack in how large it may build the GSO skbs.

Fixes: d52aec97e5bc ("qeth: enable scatter/gather in layer 2 mode")
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_l2_main.c | 2 --
 drivers/s390/net/qeth_l3_main.c | 4 ++--
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 760b023eae95..1c977ab10aa7 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -1027,8 +1027,6 @@ static int qeth_l2_setup_netdev(struct qeth_card *card)
 
 	card->info.broadcast_capable = 1;
 	qeth_l2_request_initial_mac(card);
-	card->dev->gso_max_size = (QETH_MAX_BUFFER_ELEMENTS(card) - 1) *
-				  PAGE_SIZE;
 	SET_NETDEV_DEV(card->dev, &card->gdev->dev);
 	netif_napi_add(card->dev, &card->napi, qeth_poll, QETH_NAPI_WEIGHT);
 	netif_carrier_off(card->dev);
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 1d8c317553ba..75005bbd80b9 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -2989,8 +2989,8 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
 				NETIF_F_HW_VLAN_CTAG_RX |
 				NETIF_F_HW_VLAN_CTAG_FILTER;
 	netif_keep_dst(card->dev);
-	card->dev->gso_max_size = (QETH_MAX_BUFFER_ELEMENTS(card) - 1) *
-				  PAGE_SIZE;
+	netif_set_gso_max_size(card->dev, (QETH_MAX_BUFFER_ELEMENTS(card) - 1) *
+					  PAGE_SIZE);
 
 	SET_NETDEV_DEV(card->dev, &card->gdev->dev);
 	netif_napi_add(card->dev, &card->napi, qeth_poll, QETH_NAPI_WEIGHT);
-- 
2.14.3


From d5a390ca899447bff63bb510c47bae194dbb1925 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Fri, 1 Dec 2017 10:14:49 +0100
Subject: [PATCH 19/33] s390/qeth: fix thinko in IPv4 multicast address
 tracking

[ Upsteam commit bc3ab70584696cb798b9e1e0ac8e6ced5fd4c3b8 ]

Commit 5f78e29ceebf ("qeth: optimize IP handling in rx_mode callback")
reworked how secondary addresses are managed for qeth devices.
Instead of dropping & subsequently re-adding all addresses on every
ndo_set_rx_mode() call, qeth now keeps track of the addresses that are
currently registered with the HW.
On a ndo_set_rx_mode(), we thus only need to do (de-)registration
requests for the addresses that have actually changed.

On L3 devices, the lookup for IPv4 Multicast addresses checks the wrong
hashtable - and thus never finds a match. As a result, we first delete
*all* such addresses, and then re-add them again. So each set_rx_mode()
causes a short period where the IPv4 Multicast addresses are not
registered, and the card stops forwarding inbound traffic for them.

Fix this by setting the ->is_multicast flag on the lookup object, thus
enabling qeth_l3_ip_from_hash() to search the correct hashtable and
find a match there.

Fixes: 5f78e29ceebf ("qeth: optimize IP handling in rx_mode callback")
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_l3_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 75005bbd80b9..11f65b879322 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -1376,6 +1376,7 @@ qeth_l3_add_mc_to_hash(struct qeth_card *card, struct in_device *in4_dev)
 
 		tmp->u.a4.addr = be32_to_cpu(im4->multiaddr);
 		memcpy(tmp->mac, buf, sizeof(tmp->mac));
+		tmp->is_multicast = 1;
 
 		ipm = qeth_l3_ip_from_hash(card, tmp);
 		if (ipm) {
-- 
2.14.3


From 728b9e3e634b66374ae3beedaa13f8a05ccbc53c Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Fri, 1 Dec 2017 10:14:50 +0100
Subject: [PATCH 20/33] s390/qeth: fix GSO throughput regression

[ Upstream commit 6d69b1f1eb7a2edf8a3547f361c61f2538e054bb ]

Using GSO with small MTUs currently results in a substantial throughput
regression - which is caused by how qeth needs to map non-linear skbs
into its IO buffer elements:
compared to a linear skb, each GSO-segmented skb effectively consumes
twice as many buffer elements (ie two instead of one) due to the
additional header-only part. This causes the Output Queue to be
congested with low-utilized IO buffers.

Fix this as follows:
If the MSS is low enough so that a non-SG GSO segmentation produces
order-0 skbs (currently ~3500 byte), opt out from NETIF_F_SG. This is
where we anticipate the biggest savings, since an SG-enabled
GSO segmentation produces skbs that always consume at least two
buffer elements.

Larger MSS values continue to get a SG-enabled GSO segmentation, since
1) the relative overhead of the additional header-only buffer element
becomes less noticeable, and
2) the linearization overhead increases.

With the throughput regression fixed, re-enable NETIF_F_SG by default to
reap the significant CPU savings of GSO.

Fixes: 5722963a8e83 ("qeth: do not turn on SG per default")
Reported-by: Nils Hoppmann <niho@de.ibm.com>
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core.h      |  3 +++
 drivers/s390/net/qeth_core_main.c | 31 +++++++++++++++++++++++++++++++
 drivers/s390/net/qeth_l2_main.c   |  2 ++
 drivers/s390/net/qeth_l3_main.c   |  2 ++
 4 files changed, 38 insertions(+)

diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 47a13c5723c6..5340efc673a9 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -985,6 +985,9 @@ struct qeth_cmd_buffer *qeth_get_setassparms_cmd(struct qeth_card *,
 int qeth_set_features(struct net_device *, netdev_features_t);
 int qeth_recover_features(struct net_device *);
 netdev_features_t qeth_fix_features(struct net_device *, netdev_features_t);
+netdev_features_t qeth_features_check(struct sk_buff *skb,
+				      struct net_device *dev,
+				      netdev_features_t features);
 int qeth_vm_request_mac(struct qeth_card *card);
 int qeth_push_hdr(struct sk_buff *skb, struct qeth_hdr **hdr, unsigned int len);
 
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index bae7440abc01..330e5d3dadf3 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -19,6 +19,11 @@
 #include <linux/mii.h>
 #include <linux/kthread.h>
 #include <linux/slab.h>
+#include <linux/if_vlan.h>
+#include <linux/netdevice.h>
+#include <linux/netdev_features.h>
+#include <linux/skbuff.h>
+
 #include <net/iucv/af_iucv.h>
 #include <net/dsfield.h>
 
@@ -6505,6 +6510,32 @@ netdev_features_t qeth_fix_features(struct net_device *dev,
 }
 EXPORT_SYMBOL_GPL(qeth_fix_features);
 
+netdev_features_t qeth_features_check(struct sk_buff *skb,
+				      struct net_device *dev,
+				      netdev_features_t features)
+{
+	/* GSO segmentation builds skbs with
+	 *	a (small) linear part for the headers, and
+	 *	page frags for the data.
+	 * Compared to a linear skb, the header-only part consumes an
+	 * additional buffer element. This reduces buffer utilization, and
+	 * hurts throughput. So compress small segments into one element.
+	 */
+	if (netif_needs_gso(skb, features)) {
+		/* match skb_segment(): */
+		unsigned int doffset = skb->data - skb_mac_header(skb);
+		unsigned int hsize = skb_shinfo(skb)->gso_size;
+		unsigned int hroom = skb_headroom(skb);
+
+		/* linearize only if resulting skb allocations are order-0: */
+		if (SKB_DATA_ALIGN(hroom + doffset + hsize) <= SKB_MAX_HEAD(0))
+			features &= ~NETIF_F_SG;
+	}
+
+	return vlan_features_check(skb, features);
+}
+EXPORT_SYMBOL_GPL(qeth_features_check);
+
 static int __init qeth_core_init(void)
 {
 	int rc;
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 1c977ab10aa7..5a973ebcb13c 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -963,6 +963,7 @@ static const struct net_device_ops qeth_l2_netdev_ops = {
 	.ndo_stop		= qeth_l2_stop,
 	.ndo_get_stats		= qeth_get_stats,
 	.ndo_start_xmit		= qeth_l2_hard_start_xmit,
+	.ndo_features_check	= qeth_features_check,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_rx_mode	= qeth_l2_set_rx_mode,
 	.ndo_do_ioctl		= qeth_do_ioctl,
@@ -1009,6 +1010,7 @@ static int qeth_l2_setup_netdev(struct qeth_card *card)
 	if (card->info.type == QETH_CARD_TYPE_OSD && !card->info.guestlan) {
 		card->dev->hw_features = NETIF_F_SG;
 		card->dev->vlan_features = NETIF_F_SG;
+		card->dev->features |= NETIF_F_SG;
 		/* OSA 3S and earlier has no RX/TX support */
 		if (qeth_is_supported(card, IPA_OUTBOUND_CHECKSUM)) {
 			card->dev->hw_features |= NETIF_F_IP_CSUM;
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 11f65b879322..27185ab38136 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -2923,6 +2923,7 @@ static const struct net_device_ops qeth_l3_osa_netdev_ops = {
 	.ndo_stop		= qeth_l3_stop,
 	.ndo_get_stats		= qeth_get_stats,
 	.ndo_start_xmit		= qeth_l3_hard_start_xmit,
+	.ndo_features_check	= qeth_features_check,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_rx_mode	= qeth_l3_set_multicast_list,
 	.ndo_do_ioctl		= qeth_do_ioctl,
@@ -2963,6 +2964,7 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
 				card->dev->vlan_features = NETIF_F_SG |
 					NETIF_F_RXCSUM | NETIF_F_IP_CSUM |
 					NETIF_F_TSO;
+				card->dev->features |= NETIF_F_SG;
 			}
 		}
 	} else if (card->info.type == QETH_CARD_TYPE_IQD) {
-- 
2.14.3


From 56ed07aa2d0ddb9c67dc505a97c17f21ef146dae Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Sun, 3 Dec 2017 09:33:00 -0800
Subject: [PATCH 21/33] tcp: use IPCB instead of TCP_SKB_CB in
 inet_exact_dif_match()

[ Usptream commit b4d1605a8ea608fd7dc45b926a05d75d340bde4b ]

After this fix : ("tcp: add tcp_v4_fill_cb()/tcp_v4_restore_cb()"),
socket lookups happen while skb->cb[] has not been mangled yet by TCP.

Fixes: a04a480d4392 ("net: Require exact match for TCP socket lookups if dif is l3mdev")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index e6d0002a1b0b..5dfc92ff9ffd 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -874,12 +874,11 @@ static inline int tcp_v6_sdif(const struct sk_buff *skb)
 }
 #endif
 
-/* TCP_SKB_CB reference means this can not be used from early demux */
 static inline bool inet_exact_dif_match(struct net *net, struct sk_buff *skb)
 {
 #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
 	if (!net->ipv4.sysctl_tcp_l3mdev_accept &&
-	    skb && ipv4_l3mdev_skb(TCP_SKB_CB(skb)->header.h4.flags))
+	    skb && ipv4_l3mdev_skb(IPCB(skb)->flags))
 		return true;
 #endif
 	return false;
-- 
2.14.3


From 12c305c796046d41dfcf2247ec380f32bb5cac49 Mon Sep 17 00:00:00 2001
From: Tommi Rantala <tommi.t.rantala@nokia.com>
Date: Wed, 29 Nov 2017 12:48:42 +0200
Subject: [PATCH 22/33] tipc: call tipc_rcv() only if bearer is up in
 tipc_udp_recv()

[ Upstream commit c7799c067c2ae33e348508c8afec354f3257ff25 ]

Remove the second tipc_rcv() call in tipc_udp_recv(). We have just
checked that the bearer is not up, and calling tipc_rcv() with a bearer
that is not up leads to a TIPC div-by-zero crash in
tipc_node_calculate_timer(). The crash is rare in practice, but can
happen like this:

  We're enabling a bearer, but it's not yet up and fully initialized.
  At the same time we receive a discovery packet, and in tipc_udp_recv()
  we end up calling tipc_rcv() with the not-yet-initialized bearer,
  causing later the div-by-zero crash in tipc_node_calculate_timer().

Jon Maloy explains the impact of removing the second tipc_rcv() call:
  "link setup in the worst case will be delayed until the next arriving
   discovery messages, 1 sec later, and this is an acceptable delay."

As the tipc_rcv() call is removed, just leave the function via the
rcu_out label, so that we will kfree_skb().

[   12.590450] Own node address <1.1.1>, network identity 1
[   12.668088] divide error: 0000 [#1] SMP
[   12.676952] CPU: 2 PID: 0 Comm: swapper/2 Not tainted 4.14.2-dirty #1
[   12.679225] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-2.fc27 04/01/2014
[   12.682095] task: ffff8c2a761edb80 task.stack: ffffa41cc0cac000
[   12.684087] RIP: 0010:tipc_node_calculate_timer.isra.12+0x45/0x60 [tipc]
[   12.686486] RSP: 0018:ffff8c2a7fc838a0 EFLAGS: 00010246
[   12.688451] RAX: 0000000000000000 RBX: ffff8c2a5b382600 RCX: 0000000000000000
[   12.691197] RDX: 0000000000000000 RSI: ffff8c2a5b382600 RDI: ffff8c2a5b382600
[   12.693945] RBP: ffff8c2a7fc838b0 R08: 0000000000000001 R09: 0000000000000001
[   12.696632] R10: 0000000000000000 R11: 0000000000000000 R12: ffff8c2a5d8949d8
[   12.699491] R13: ffffffff95ede400 R14: 0000000000000000 R15: ffff8c2a5d894800
[   12.702338] FS:  0000000000000000(0000) GS:ffff8c2a7fc80000(0000) knlGS:0000000000000000
[   12.705099] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   12.706776] CR2: 0000000001bb9440 CR3: 00000000bd009001 CR4: 00000000003606e0
[   12.708847] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[   12.711016] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[   12.712627] Call Trace:
[   12.713390]  <IRQ>
[   12.714011]  tipc_node_check_dest+0x2e8/0x350 [tipc]
[   12.715286]  tipc_disc_rcv+0x14d/0x1d0 [tipc]
[   12.716370]  tipc_rcv+0x8b0/0xd40 [tipc]
[   12.717396]  ? minmax_running_min+0x2f/0x60
[   12.718248]  ? dst_alloc+0x4c/0xa0
[   12.718964]  ? tcp_ack+0xaf1/0x10b0
[   12.719658]  ? tipc_udp_is_known_peer+0xa0/0xa0 [tipc]
[   12.720634]  tipc_udp_recv+0x71/0x1d0 [tipc]
[   12.721459]  ? dst_alloc+0x4c/0xa0
[   12.722130]  udp_queue_rcv_skb+0x264/0x490
[   12.722924]  __udp4_lib_rcv+0x21e/0x990
[   12.723670]  ? ip_route_input_rcu+0x2dd/0xbf0
[   12.724442]  ? tcp_v4_rcv+0x958/0xa40
[   12.725039]  udp_rcv+0x1a/0x20
[   12.725587]  ip_local_deliver_finish+0x97/0x1d0
[   12.726323]  ip_local_deliver+0xaf/0xc0
[   12.726959]  ? ip_route_input_noref+0x19/0x20
[   12.727689]  ip_rcv_finish+0xdd/0x3b0
[   12.728307]  ip_rcv+0x2ac/0x360
[   12.728839]  __netif_receive_skb_core+0x6fb/0xa90
[   12.729580]  ? udp4_gro_receive+0x1a7/0x2c0
[   12.730274]  __netif_receive_skb+0x1d/0x60
[   12.730953]  ? __netif_receive_skb+0x1d/0x60
[   12.731637]  netif_receive_skb_internal+0x37/0xd0
[   12.732371]  napi_gro_receive+0xc7/0xf0
[   12.732920]  receive_buf+0x3c3/0xd40
[   12.733441]  virtnet_poll+0xb1/0x250
[   12.733944]  net_rx_action+0x23e/0x370
[   12.734476]  __do_softirq+0xc5/0x2f8
[   12.734922]  irq_exit+0xfa/0x100
[   12.735315]  do_IRQ+0x4f/0xd0
[   12.735680]  common_interrupt+0xa2/0xa2
[   12.736126]  </IRQ>
[   12.736416] RIP: 0010:native_safe_halt+0x6/0x10
[   12.736925] RSP: 0018:ffffa41cc0cafe90 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff4d
[   12.737756] RAX: 0000000000000000 RBX: ffff8c2a761edb80 RCX: 0000000000000000
[   12.738504] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
[   12.739258] RBP: ffffa41cc0cafe90 R08: 0000014b5b9795e5 R09: ffffa41cc12c7e88
[   12.740118] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000002
[   12.740964] R13: ffff8c2a761edb80 R14: 0000000000000000 R15: 0000000000000000
[   12.741831]  default_idle+0x2a/0x100
[   12.742323]  arch_cpu_idle+0xf/0x20
[   12.742796]  default_idle_call+0x28/0x40
[   12.743312]  do_idle+0x179/0x1f0
[   12.743761]  cpu_startup_entry+0x1d/0x20
[   12.744291]  start_secondary+0x112/0x120
[   12.744816]  secondary_startup_64+0xa5/0xa5
[   12.745367] Code: b9 f4 01 00 00 48 89 c2 48 c1 ea 02 48 3d d3 07 00
00 48 0f 47 d1 49 8b 0c 24 48 39 d1 76 07 49 89 14 24 48 89 d1 31 d2 48
89 df <48> f7 f1 89 c6 e8 81 6e ff ff 5b 41 5c 5d c3 66 90 66 2e 0f 1f
[   12.747527] RIP: tipc_node_calculate_timer.isra.12+0x45/0x60 [tipc] RSP: ffff8c2a7fc838a0
[   12.748555] ---[ end trace 1399ab83390650fd ]---
[   12.749296] Kernel panic - not syncing: Fatal exception in interrupt
[   12.750123] Kernel Offset: 0x13200000 from 0xffffffff82000000
(relocation range: 0xffffffff80000000-0xffffffffbfffffff)
[   12.751215] Rebooting in 60 seconds..

Fixes: c9b64d492b1f ("tipc: add replicast peer discovery")
Signed-off-by: Tommi Rantala <tommi.t.rantala@nokia.com>
Cc: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/udp_media.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index ecca64fc6a6f..3deabcab4882 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -371,10 +371,6 @@ static int tipc_udp_recv(struct sock *sk, struct sk_buff *skb)
 			goto rcu_out;
 	}
 
-	tipc_rcv(sock_net(sk), skb, b);
-	rcu_read_unlock();
-	return 0;
-
 rcu_out:
 	rcu_read_unlock();
 out:
-- 
2.14.3


From 9d83dad40374a7e490e787d7ddde2f1111662a23 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 6 Dec 2017 11:08:19 -0800
Subject: [PATCH 23/33] tcp: use current time in tcp_rcv_space_adjust()

[ Upstream commit 8632385022f2b05a6ca0b9e0f95575865de0e2ce ]

When I switched rcv_rtt_est to high resolution timestamps, I forgot
that tp->tcp_mstamp needed to be refreshed in tcp_rcv_space_adjust()

Using an old timestamp leads to autotuning lags.

Fixes: 645f4c6f2ebd ("tcp: switch rcv_rtt_est and rcvq_space to high resolution timestamps")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Wei Wang <weiwan@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index b6bb3cdfad09..4b10e79210aa 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -592,6 +592,7 @@ void tcp_rcv_space_adjust(struct sock *sk)
 	int time;
 	int copied;
 
+	tcp_mstamp_refresh(tp);
 	time = tcp_stamp_us_delta(tp->tcp_mstamp, tp->rcvq_space.time);
 	if (time < (tp->rcv_rtt_est.rtt_us >> 3) || tp->rcv_rtt_est.rtt_us == 0)
 		return;
-- 
2.14.3


From 576ea52cac4e446d05685382f629e2de9f9c2b3c Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Mon, 27 Nov 2017 18:37:21 +0100
Subject: [PATCH 24/33] net: sched: cbq: create block for q->link.block

[ Upstream commit d51aae68b142f48232257e96ce317db25445418d ]

q->link.block is not initialized, that leads to EINVAL when one tries to
add filter there. So initialize it properly.

This can be reproduced by:
$ tc qdisc add dev eth0 root handle 1: cbq avpkt 1000 rate 1000Mbit bandwidth 1000Mbit
$ tc filter add dev eth0 parent 1: protocol ip prio 100 u32 match ip protocol 0 0x00 flowid 1:1

Reported-by: Jaroslav Aster <jaster@redhat.com>
Reported-by: Ivan Vecera <ivecera@redhat.com>
Fixes: 6529eaba33f0 ("net: sched: introduce tcf block infractructure")
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Eelco Chaudron <echaudro@redhat.com>
Reviewed-by: Ivan Vecera <ivecera@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_cbq.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index dcef97fa8047..aeffa320429d 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1157,9 +1157,13 @@ static int cbq_init(struct Qdisc *sch, struct nlattr *opt)
 	if ((q->link.R_tab = qdisc_get_rtab(r, tb[TCA_CBQ_RTAB])) == NULL)
 		return -EINVAL;
 
+	err = tcf_block_get(&q->link.block, &q->link.filter_list);
+	if (err)
+		goto put_rtab;
+
 	err = qdisc_class_hash_init(&q->clhash);
 	if (err < 0)
-		goto put_rtab;
+		goto put_block;
 
 	q->link.sibling = &q->link;
 	q->link.common.classid = sch->handle;
@@ -1193,6 +1197,9 @@ static int cbq_init(struct Qdisc *sch, struct nlattr *opt)
 	cbq_addprio(q, &q->link);
 	return 0;
 
+put_block:
+	tcf_block_put(q->link.block);
+
 put_rtab:
 	qdisc_put_rtab(q->link.R_tab);
 	return err;
-- 
2.14.3


From 2359c37998727beb358c0d896d0ab452fe1699ba Mon Sep 17 00:00:00 2001
From: Wei Xu <wexu@redhat.com>
Date: Fri, 1 Dec 2017 05:10:38 -0500
Subject: [PATCH 25/33] tap: free skb if flags error

[ Upstream commit 61d78537843e676e7f56ac6db333db0c0529b892 ]

tap_recvmsg() supports accepting skb by msg_control after
commit 3b4ba04acca8 ("tap: support receiving skb from msg_control"),
the skb if presented should be freed within the function, otherwise
it would be leaked.

Signed-off-by: Wei Xu <wexu@redhat.com>
Reported-by: Matthew Rosato <mjrosato@linux.vnet.ibm.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tap.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index 6c0c84c33e1f..e4c6c78fab3b 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -829,8 +829,11 @@ static ssize_t tap_do_read(struct tap_queue *q,
 	DEFINE_WAIT(wait);
 	ssize_t ret = 0;
 
-	if (!iov_iter_count(to))
+	if (!iov_iter_count(to)) {
+		if (skb)
+			kfree_skb(skb);
 		return 0;
+	}
 
 	if (skb)
 		goto put;
@@ -1154,11 +1157,14 @@ static int tap_recvmsg(struct socket *sock, struct msghdr *m,
 		       size_t total_len, int flags)
 {
 	struct tap_queue *q = container_of(sock, struct tap_queue, sock);
+	struct sk_buff *skb = m->msg_control;
 	int ret;
-	if (flags & ~(MSG_DONTWAIT|MSG_TRUNC))
+	if (flags & ~(MSG_DONTWAIT|MSG_TRUNC)) {
+		if (skb)
+			kfree_skb(skb);
 		return -EINVAL;
-	ret = tap_do_read(q, &m->msg_iter, flags & MSG_DONTWAIT,
-			  m->msg_control);
+	}
+	ret = tap_do_read(q, &m->msg_iter, flags & MSG_DONTWAIT, skb);
 	if (ret > total_len) {
 		m->msg_flags |= MSG_TRUNC;
 		ret = flags & MSG_TRUNC ? ret : total_len;
-- 
2.14.3


From dcc248cf099b1dd3848afe76dd63427a47f1dd90 Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Fri, 17 Nov 2017 21:06:14 -0500
Subject: [PATCH 26/33] tcp: when scheduling TLP, time of RTO should account
 for current ACK

[ Upstream commit ed66dfaf236c04d414de1d218441296e57fb2bd2 ]

Fix the TLP scheduling logic so that when scheduling a TLP probe, we
ensure that the estimated time at which an RTO would fire accounts for
the fact that ACKs indicating forward progress should push back RTO
times.

After the following fix:

df92c8394e6e ("tcp: fix xmit timer to only be reset if data ACKed/SACKed")

we had an unintentional behavior change in the following kind of
scenario: suppose the RTT variance has been very low recently. Then
suppose we send out a flight of N packets and our RTT is 100ms:

t=0: send a flight of N packets
t=100ms: receive an ACK for N-1 packets

The response before df92c8394e6e that was:
  -> schedule a TLP for now + RTO_interval

The response after df92c8394e6e is:
  -> schedule a TLP for t=0 + RTO_interval

Since RTO_interval = srtt + RTT_variance, this means that we have
scheduled a TLP timer at a point in the future that only accounts for
RTT_variance. If the RTT_variance term is small, this means that the
timer fires soon.

Before df92c8394e6e this would not happen, because in that code, when
we receive an ACK for a prefix of flight, we did:

    1) Near the top of tcp_ack(), switch from TLP timer to RTO
       at write_queue_head->paket_tx_time + RTO_interval:
            if (icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)
                   tcp_rearm_rto(sk);

    2) In tcp_clean_rtx_queue(), update the RTO to now + RTO_interval:
            if (flag & FLAG_ACKED) {
                   tcp_rearm_rto(sk);

    3) In tcp_ack() after tcp_fastretrans_alert() switch from RTO
       to TLP at now + RTO_interval:
            if (icsk->icsk_pending == ICSK_TIME_RETRANS)
                   tcp_schedule_loss_probe(sk);

In df92c8394e6e we removed that 3-phase dance, and instead directly
set the TLP timer once: we set the TLP timer in cases like this to
write_queue_head->packet_tx_time + RTO_interval. So if the RTT
variance is small, then this means that this is setting the TLP timer
to fire quite soon. This means if the ACK for the tail of the flight
takes longer than an RTT to arrive (often due to delayed ACKs), then
the TLP timer fires too quickly.

Fixes: df92c8394e6e ("tcp: fix xmit timer to only be reset if data ACKed/SACKed")
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h     | 2 +-
 net/ipv4/tcp_input.c  | 2 +-
 net/ipv4/tcp_output.c | 8 +++++---
 3 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 5dfc92ff9ffd..6ced69940f5c 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -563,7 +563,7 @@ void tcp_push_one(struct sock *, unsigned int mss_now);
 void tcp_send_ack(struct sock *sk);
 void tcp_send_delayed_ack(struct sock *sk);
 void tcp_send_loss_probe(struct sock *sk);
-bool tcp_schedule_loss_probe(struct sock *sk);
+bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto);
 void tcp_skb_collapse_tstamp(struct sk_buff *skb,
 			     const struct sk_buff *next_skb);
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 4b10e79210aa..c5447b9f8517 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3021,7 +3021,7 @@ void tcp_rearm_rto(struct sock *sk)
 /* Try to schedule a loss probe; if that doesn't work, then schedule an RTO. */
 static void tcp_set_xmit_timer(struct sock *sk)
 {
-	if (!tcp_schedule_loss_probe(sk))
+	if (!tcp_schedule_loss_probe(sk, true))
 		tcp_rearm_rto(sk);
 }
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 478909f4694d..cd3d60bb7cc8 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2337,7 +2337,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 
 		/* Send one loss probe per tail loss episode. */
 		if (push_one != 2)
-			tcp_schedule_loss_probe(sk);
+			tcp_schedule_loss_probe(sk, false);
 		is_cwnd_limited |= (tcp_packets_in_flight(tp) >= tp->snd_cwnd);
 		tcp_cwnd_validate(sk, is_cwnd_limited);
 		return false;
@@ -2345,7 +2345,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 	return !tp->packets_out && tcp_send_head(sk);
 }
 
-bool tcp_schedule_loss_probe(struct sock *sk)
+bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -2384,7 +2384,9 @@ bool tcp_schedule_loss_probe(struct sock *sk)
 	}
 
 	/* If the RTO formula yields an earlier time, then use that time. */
-	rto_delta_us = tcp_rto_delta_us(sk);  /* How far in future is RTO? */
+	rto_delta_us = advancing_rto ?
+			jiffies_to_usecs(inet_csk(sk)->icsk_rto) :
+			tcp_rto_delta_us(sk);  /* How far in future is RTO? */
 	if (rto_delta_us > 0)
 		timeout = min_t(u32, timeout, usecs_to_jiffies(rto_delta_us));
 
-- 
2.14.3


From 60208d6c7b26edf719e5b207ff6ab7159f757b0a Mon Sep 17 00:00:00 2001
From: Wei Xu <wexu@redhat.com>
Date: Fri, 1 Dec 2017 05:10:37 -0500
Subject: [PATCH 27/33] tun: free skb in early errors

[ Upstream commit c33ee15b3820a03cf8229ba9415084197b827f8c ]

tun_recvmsg() supports accepting skb by msg_control after
commit ac77cfd4258f ("tun: support receiving skb through msg_control"),
the skb if presented should be freed no matter how far it can go
along, otherwise it would be leaked.

This patch fixes several missed cases.

Signed-off-by: Wei Xu <wexu@redhat.com>
Reported-by: Matthew Rosato <mjrosato@linux.vnet.ibm.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 24 ++++++++++++++++++------
 1 file changed, 18 insertions(+), 6 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 42bb820a56c9..a5c47db94846 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1734,8 +1734,11 @@ static ssize_t tun_do_read(struct tun_struct *tun, struct tun_file *tfile,
 
 	tun_debug(KERN_INFO, tun, "tun_do_read\n");
 
-	if (!iov_iter_count(to))
+	if (!iov_iter_count(to)) {
+		if (skb)
+			kfree_skb(skb);
 		return 0;
+	}
 
 	if (!skb) {
 		/* Read frames from ring */
@@ -1851,22 +1854,24 @@ static int tun_recvmsg(struct socket *sock, struct msghdr *m, size_t total_len,
 {
 	struct tun_file *tfile = container_of(sock, struct tun_file, socket);
 	struct tun_struct *tun = __tun_get(tfile);
+	struct sk_buff *skb = m->msg_control;
 	int ret;
 
-	if (!tun)
-		return -EBADFD;
+	if (!tun) {
+		ret = -EBADFD;
+		goto out_free_skb;
+	}
 
 	if (flags & ~(MSG_DONTWAIT|MSG_TRUNC|MSG_ERRQUEUE)) {
 		ret = -EINVAL;
-		goto out;
+		goto out_put_tun;
 	}
 	if (flags & MSG_ERRQUEUE) {
 		ret = sock_recv_errqueue(sock->sk, m, total_len,
 					 SOL_PACKET, TUN_TX_TIMESTAMP);
 		goto out;
 	}
-	ret = tun_do_read(tun, tfile, &m->msg_iter, flags & MSG_DONTWAIT,
-			  m->msg_control);
+	ret = tun_do_read(tun, tfile, &m->msg_iter, flags & MSG_DONTWAIT, skb);
 	if (ret > (ssize_t)total_len) {
 		m->msg_flags |= MSG_TRUNC;
 		ret = flags & MSG_TRUNC ? ret : total_len;
@@ -1874,6 +1879,13 @@ static int tun_recvmsg(struct socket *sock, struct msghdr *m, size_t total_len,
 out:
 	tun_put(tun);
 	return ret;
+
+out_put_tun:
+	tun_put(tun);
+out_free_skb:
+	if (skb)
+		kfree_skb(skb);
+	return ret;
 }
 
 static int tun_peek_len(struct socket *sock)
-- 
2.14.3


From 1b122157de0829b7c1a7f7cba5775d36138ba503 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 21 Nov 2017 07:08:57 -0800
Subject: [PATCH 28/33] net: ipv6: Fixup device for anycast routes during copy

[ Upstream commit 98d11291d189cb5adf49694d0ad1b971c0212697 ]

Florian reported a breakage with anycast routes due to commit
4832c30d5458 ("net: ipv6: put host and anycast routes on device with
address"). Prior to this commit anycast routes were added against the
loopback device causing repetitive route entries with no insight into
why they existed. e.g.:
  $ ip -6 ro ls  table local type anycast
  anycast 2001:db8:1:: dev lo proto kernel metric 0 pref medium
  anycast 2001:db8:2:: dev lo proto kernel metric 0 pref medium
  anycast fe80:: dev lo proto kernel metric 0 pref medium
  anycast fe80:: dev lo proto kernel metric 0 pref medium

The point of commit 4832c30d5458 is to add the routes using the device
with the address which is causing the route to be added. e.g.,:
  $ ip -6 ro ls  table local type anycast
  anycast 2001:db8:1:: dev eth1 proto kernel metric 0 pref medium
  anycast 2001:db8:2:: dev eth2 proto kernel metric 0 pref medium
  anycast fe80:: dev eth2 proto kernel metric 0 pref medium
  anycast fe80:: dev eth1 proto kernel metric 0 pref medium

For traffic to work as it did before, the dst device needs to be switched
to the loopback when the copy is created similar to local routes.

Fixes: 4832c30d5458 ("net: ipv6: put host and anycast routes on device with address")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index a96d5b385d8f..598efa8cfe25 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -960,7 +960,7 @@ static struct net_device *ip6_rt_get_dev_rcu(struct rt6_info *rt)
 {
 	struct net_device *dev = rt->dst.dev;
 
-	if (rt->rt6i_flags & RTF_LOCAL) {
+	if (rt->rt6i_flags & (RTF_LOCAL | RTF_ANYCAST)) {
 		/* for copies of local routes, dst->dev needs to be the
 		 * device if it is a master device, the master device if
 		 * device is enslaved, and the loopback as the default
-- 
2.14.3


From 171cb5eda2828d3ac30aa813c9b571f35e0504ee Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 19 Nov 2017 19:31:04 +0800
Subject: [PATCH 29/33] tun: fix rcu_read_lock imbalance in tun_build_skb

[ Upstream commit 654d573845f35017dc397840fa03610fef3d08b0 ]

rcu_read_lock in tun_build_skb is used to rcu_dereference tun->xdp_prog
safely, rcu_read_unlock should be done in every return path.

Now I could see one place missing it, where it returns NULL in switch-case
XDP_REDIRECT,  another palce using rcu_read_lock wrongly, where it returns
NULL in if (xdp_xmit) chunk.

So fix both in this patch.

Fixes: 761876c857cb ("tap: XDP support")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index a5c47db94846..d06f88312e1e 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1326,6 +1326,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 			err = xdp_do_redirect(tun->dev, &xdp, xdp_prog);
 			if (err)
 				goto err_redirect;
+			rcu_read_unlock();
 			return NULL;
 		case XDP_TX:
 			xdp_xmit = true;
@@ -1358,7 +1359,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 	if (xdp_xmit) {
 		skb->dev = tun->dev;
 		generic_xdp_tx(skb, xdp_prog);
-		rcu_read_lock();
+		rcu_read_unlock();
 		return NULL;
 	}
 
-- 
2.14.3


From a29b4f4df0dac4c64f15d118e3116638f86cd647 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Tue, 21 Nov 2017 10:22:25 -0500
Subject: [PATCH 30/33] net: accept UFO datagrams from tuntap and packet

[ Upstream commit 0c19f846d582af919db66a5914a0189f9f92c936 ]

Tuntap and similar devices can inject GSO packets. Accept type
VIRTIO_NET_HDR_GSO_UDP, even though not generating UFO natively.

Processes are expected to use feature negotiation such as TUNSETOFFLOAD
to detect supported offload types and refrain from injecting other
packets. This process breaks down with live migration: guest kernels
do not renegotiate flags, so destination hosts need to expose all
features that the source host does.

Partially revert the UFO removal from 182e0b6b5846~1..d9d30adf5677.
This patch introduces nearly(*) no new code to simplify verification.
It brings back verbatim tuntap UFO negotiation, VIRTIO_NET_HDR_GSO_UDP
insertion and software UFO segmentation.

It does not reinstate protocol stack support, hardware offload
(NETIF_F_UFO), SKB_GSO_UDP tunneling in SKB_GSO_SOFTWARE or reception
of VIRTIO_NET_HDR_GSO_UDP packets in tuntap.

To support SKB_GSO_UDP reappearing in the stack, also reinstate
logic in act_csum and openvswitch. Achieve equivalence with v4.13 HEAD
by squashing in commit 939912216fa8 ("net: skb_needs_check() removes
CHECKSUM_UNNECESSARY check for tx.") and reverting commit 8d63bee643f1
("net: avoid skb_warn_bad_offload false positives on UFO").

(*) To avoid having to bring back skb_shinfo(skb)->ip6_frag_id,
ipv6_proxy_select_ident is changed to return a __be32 and this is
assigned directly to the frag_hdr. Also, SKB_GSO_UDP is inserted
at the end of the enum to minimize code churn.

Tested
  Booted a v4.13 guest kernel with QEMU. On a host kernel before this
  patch `ethtool -k eth0` shows UFO disabled. After the patch, it is
  enabled, same as on a v4.13 host kernel.

  A UFO packet sent from the guest appears on the tap device:
    host:
      nc -l -p -u 8000 &
      tcpdump -n -i tap0

    guest:
      dd if=/dev/zero of=payload.txt bs=1 count=2000
      nc -u 192.16.1.1 8000 < payload.txt

  Direct tap to tap transmission of VIRTIO_NET_HDR_GSO_UDP succeeds,
  packets arriving fragmented:

    ./with_tap_pair.sh ./tap_send_ufo tap0 tap1
    (from https://github.com/wdebruij/kerneltools/tree/master/tests)

Changes
  v1 -> v2
    - simplified set_offload change (review comment)
    - documented test procedure

Link: http://lkml.kernel.org/r/<CAF=yD-LuUeDuL9YWPJD9ykOZ0QCjNeznPDr6whqZ9NGMNF12Mw@mail.gmail.com>
Fixes: fb652fdfe837 ("macvlan/macvtap: Remove NETIF_F_UFO advertisement.")
Reported-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tap.c               |  2 +-
 drivers/net/tun.c               |  2 +
 include/linux/netdev_features.h |  4 +-
 include/linux/netdevice.h       |  1 +
 include/linux/skbuff.h          |  2 +
 include/linux/virtio_net.h      |  5 ++-
 include/net/ipv6.h              |  2 +-
 net/core/dev.c                  |  3 +-
 net/ipv4/af_inet.c              | 12 +++++-
 net/ipv4/udp_offload.c          | 49 ++++++++++++++++++++++--
 net/ipv6/output_core.c          |  6 +--
 net/ipv6/udp_offload.c          | 85 +++++++++++++++++++++++++++++++++++++++--
 net/openvswitch/datapath.c      | 14 +++++++
 net/openvswitch/flow.c          |  6 ++-
 net/sched/act_csum.c            |  6 +++
 15 files changed, 181 insertions(+), 18 deletions(-)

diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index e4c6c78fab3b..bfd4ded0a53f 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -1080,7 +1080,7 @@ static long tap_ioctl(struct file *file, unsigned int cmd,
 	case TUNSETOFFLOAD:
 		/* let the user check for future flags */
 		if (arg & ~(TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 |
-			    TUN_F_TSO_ECN))
+			    TUN_F_TSO_ECN | TUN_F_UFO))
 			return -EINVAL;
 
 		rtnl_lock();
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index d06f88312e1e..c91b110f2169 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -2157,6 +2157,8 @@ static int set_offload(struct tun_struct *tun, unsigned long arg)
 				features |= NETIF_F_TSO6;
 			arg &= ~(TUN_F_TSO4|TUN_F_TSO6);
 		}
+
+		arg &= ~TUN_F_UFO;
 	}
 
 	/* This gives the user a way to test for new features in future by
diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index dc8b4896b77b..b1b0ca7ccb2b 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -54,8 +54,9 @@ enum {
 	NETIF_F_GSO_TUNNEL_REMCSUM_BIT, /* ... TUNNEL with TSO & REMCSUM */
 	NETIF_F_GSO_SCTP_BIT,		/* ... SCTP fragmentation */
 	NETIF_F_GSO_ESP_BIT,		/* ... ESP with TSO */
+	NETIF_F_GSO_UDP_BIT,		/* ... UFO, deprecated except tuntap */
 	/**/NETIF_F_GSO_LAST =		/* last bit, see GSO_MASK */
-		NETIF_F_GSO_ESP_BIT,
+		NETIF_F_GSO_UDP_BIT,
 
 	NETIF_F_FCOE_CRC_BIT,		/* FCoE CRC32 */
 	NETIF_F_SCTP_CRC_BIT,		/* SCTP checksum offload */
@@ -132,6 +133,7 @@ enum {
 #define NETIF_F_GSO_TUNNEL_REMCSUM __NETIF_F(GSO_TUNNEL_REMCSUM)
 #define NETIF_F_GSO_SCTP	__NETIF_F(GSO_SCTP)
 #define NETIF_F_GSO_ESP		__NETIF_F(GSO_ESP)
+#define NETIF_F_GSO_UDP		__NETIF_F(GSO_UDP)
 #define NETIF_F_HW_VLAN_STAG_FILTER __NETIF_F(HW_VLAN_STAG_FILTER)
 #define NETIF_F_HW_VLAN_STAG_RX	__NETIF_F(HW_VLAN_STAG_RX)
 #define NETIF_F_HW_VLAN_STAG_TX	__NETIF_F(HW_VLAN_STAG_TX)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 2eaac7d75af4..46bf7cc7d5d5 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4101,6 +4101,7 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type)
 	BUILD_BUG_ON(SKB_GSO_TUNNEL_REMCSUM != (NETIF_F_GSO_TUNNEL_REMCSUM >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_SCTP    != (NETIF_F_GSO_SCTP >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_ESP != (NETIF_F_GSO_ESP >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_UDP != (NETIF_F_GSO_UDP >> NETIF_F_GSO_SHIFT));
 
 	return (features & feature) == feature;
 }
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index d448a4804aea..051e0939ec19 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -569,6 +569,8 @@ enum {
 	SKB_GSO_SCTP = 1 << 14,
 
 	SKB_GSO_ESP = 1 << 15,
+
+	SKB_GSO_UDP = 1 << 16,
 };
 
 #if BITS_PER_LONG > 32
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 210034c896e3..f144216febc6 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -9,7 +9,7 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 					const struct virtio_net_hdr *hdr,
 					bool little_endian)
 {
-	unsigned short gso_type = 0;
+	unsigned int gso_type = 0;
 
 	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
 		switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
@@ -19,6 +19,9 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 		case VIRTIO_NET_HDR_GSO_TCPV6:
 			gso_type = SKB_GSO_TCPV6;
 			break;
+		case VIRTIO_NET_HDR_GSO_UDP:
+			gso_type = SKB_GSO_UDP;
+			break;
 		default:
 			return -EINVAL;
 		}
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 6eac5cf8f1e6..35e9dd2d18ba 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -727,7 +727,7 @@ static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_add
 __be32 ipv6_select_ident(struct net *net,
 			 const struct in6_addr *daddr,
 			 const struct in6_addr *saddr);
-void ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb);
+__be32 ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb);
 
 int ip6_dst_hoplimit(struct dst_entry *dst);
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 11596a302a26..27357fc1730b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2735,7 +2735,8 @@ EXPORT_SYMBOL(skb_mac_gso_segment);
 static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path)
 {
 	if (tx_path)
-		return skb->ip_summed != CHECKSUM_PARTIAL;
+		return skb->ip_summed != CHECKSUM_PARTIAL &&
+		       skb->ip_summed != CHECKSUM_UNNECESSARY;
 
 	return skb->ip_summed == CHECKSUM_NONE;
 }
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index e31108e5ef79..b9d9a2b8792c 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1221,9 +1221,10 @@ EXPORT_SYMBOL(inet_sk_rebuild_header);
 struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 				 netdev_features_t features)
 {
-	bool fixedid = false, gso_partial, encap;
+	bool udpfrag = false, fixedid = false, gso_partial, encap;
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	const struct net_offload *ops;
+	unsigned int offset = 0;
 	struct iphdr *iph;
 	int proto, tot_len;
 	int nhoff;
@@ -1258,6 +1259,7 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 	segs = ERR_PTR(-EPROTONOSUPPORT);
 
 	if (!skb->encapsulation || encap) {
+		udpfrag = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP);
 		fixedid = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TCP_FIXEDID);
 
 		/* fixed ID is invalid if DF bit is not set */
@@ -1277,7 +1279,13 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 	skb = segs;
 	do {
 		iph = (struct iphdr *)(skb_mac_header(skb) + nhoff);
-		if (skb_is_gso(skb)) {
+		if (udpfrag) {
+			iph->frag_off = htons(offset >> 3);
+			if (skb->next)
+				iph->frag_off |= htons(IP_MF);
+			offset += skb->len - nhoff - ihl;
+			tot_len = skb->len - nhoff;
+		} else if (skb_is_gso(skb)) {
 			if (!fixedid) {
 				iph->id = htons(id);
 				id += skb_shinfo(skb)->gso_segs;
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index e360d55be555..01801b77bd0d 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -187,16 +187,57 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
 }
 EXPORT_SYMBOL(skb_udp_tunnel_segment);
 
-static struct sk_buff *udp4_tunnel_segment(struct sk_buff *skb,
-					   netdev_features_t features)
+static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
+					 netdev_features_t features)
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
+	unsigned int mss;
+	__wsum csum;
+	struct udphdr *uh;
+	struct iphdr *iph;
 
 	if (skb->encapsulation &&
 	    (skb_shinfo(skb)->gso_type &
-	     (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM)))
+	     (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))) {
 		segs = skb_udp_tunnel_segment(skb, features, false);
+		goto out;
+	}
+
+	if (!pskb_may_pull(skb, sizeof(struct udphdr)))
+		goto out;
+
+	mss = skb_shinfo(skb)->gso_size;
+	if (unlikely(skb->len <= mss))
+		goto out;
+
+	/* Do software UFO. Complete and fill in the UDP checksum as
+	 * HW cannot do checksum of UDP packets sent as multiple
+	 * IP fragments.
+	 */
 
+	uh = udp_hdr(skb);
+	iph = ip_hdr(skb);
+
+	uh->check = 0;
+	csum = skb_checksum(skb, 0, skb->len, 0);
+	uh->check = udp_v4_check(skb->len, iph->saddr, iph->daddr, csum);
+	if (uh->check == 0)
+		uh->check = CSUM_MANGLED_0;
+
+	skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+	/* If there is no outer header we can fake a checksum offload
+	 * due to the fact that we have already done the checksum in
+	 * software prior to segmenting the frame.
+	 */
+	if (!skb->encap_hdr_csum)
+		features |= NETIF_F_HW_CSUM;
+
+	/* Fragment the skb. IP headers of the fragments are updated in
+	 * inet_gso_segment()
+	 */
+	segs = skb_segment(skb, features);
+out:
 	return segs;
 }
 
@@ -330,7 +371,7 @@ static int udp4_gro_complete(struct sk_buff *skb, int nhoff)
 
 static const struct net_offload udpv4_offload = {
 	.callbacks = {
-		.gso_segment = udp4_tunnel_segment,
+		.gso_segment = udp4_ufo_fragment,
 		.gro_receive  =	udp4_gro_receive,
 		.gro_complete =	udp4_gro_complete,
 	},
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index a338bbc33cf3..4fe7c90962dd 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -39,7 +39,7 @@ static u32 __ipv6_select_ident(struct net *net, u32 hashrnd,
  *
  * The network header must be set before calling this.
  */
-void ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb)
+__be32 ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb)
 {
 	static u32 ip6_proxy_idents_hashrnd __read_mostly;
 	struct in6_addr buf[2];
@@ -51,14 +51,14 @@ void ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb)
 				   offsetof(struct ipv6hdr, saddr),
 				   sizeof(buf), buf);
 	if (!addrs)
-		return;
+		return 0;
 
 	net_get_random_once(&ip6_proxy_idents_hashrnd,
 			    sizeof(ip6_proxy_idents_hashrnd));
 
 	id = __ipv6_select_ident(net, ip6_proxy_idents_hashrnd,
 				 &addrs[1], &addrs[0]);
-	skb_shinfo(skb)->ip6_frag_id = htonl(id);
+	return htonl(id);
 }
 EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident);
 
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 455fd4e39333..a0f89ad76f9d 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -17,15 +17,94 @@
 #include <net/ip6_checksum.h>
 #include "ip6_offload.h"
 
-static struct sk_buff *udp6_tunnel_segment(struct sk_buff *skb,
-					   netdev_features_t features)
+static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
+					 netdev_features_t features)
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
+	unsigned int mss;
+	unsigned int unfrag_ip6hlen, unfrag_len;
+	struct frag_hdr *fptr;
+	u8 *packet_start, *prevhdr;
+	u8 nexthdr;
+	u8 frag_hdr_sz = sizeof(struct frag_hdr);
+	__wsum csum;
+	int tnl_hlen;
+	int err;
+
+	mss = skb_shinfo(skb)->gso_size;
+	if (unlikely(skb->len <= mss))
+		goto out;
 
 	if (skb->encapsulation && skb_shinfo(skb)->gso_type &
 	    (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))
 		segs = skb_udp_tunnel_segment(skb, features, true);
+	else {
+		const struct ipv6hdr *ipv6h;
+		struct udphdr *uh;
+
+		if (!pskb_may_pull(skb, sizeof(struct udphdr)))
+			goto out;
+
+		/* Do software UFO. Complete and fill in the UDP checksum as HW cannot
+		 * do checksum of UDP packets sent as multiple IP fragments.
+		 */
+
+		uh = udp_hdr(skb);
+		ipv6h = ipv6_hdr(skb);
+
+		uh->check = 0;
+		csum = skb_checksum(skb, 0, skb->len, 0);
+		uh->check = udp_v6_check(skb->len, &ipv6h->saddr,
+					  &ipv6h->daddr, csum);
+		if (uh->check == 0)
+			uh->check = CSUM_MANGLED_0;
+
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+		/* If there is no outer header we can fake a checksum offload
+		 * due to the fact that we have already done the checksum in
+		 * software prior to segmenting the frame.
+		 */
+		if (!skb->encap_hdr_csum)
+			features |= NETIF_F_HW_CSUM;
+
+		/* Check if there is enough headroom to insert fragment header. */
+		tnl_hlen = skb_tnl_header_len(skb);
+		if (skb->mac_header < (tnl_hlen + frag_hdr_sz)) {
+			if (gso_pskb_expand_head(skb, tnl_hlen + frag_hdr_sz))
+				goto out;
+		}
+
+		/* Find the unfragmentable header and shift it left by frag_hdr_sz
+		 * bytes to insert fragment header.
+		 */
+		err = ip6_find_1stfragopt(skb, &prevhdr);
+		if (err < 0)
+			return ERR_PTR(err);
+		unfrag_ip6hlen = err;
+		nexthdr = *prevhdr;
+		*prevhdr = NEXTHDR_FRAGMENT;
+		unfrag_len = (skb_network_header(skb) - skb_mac_header(skb)) +
+			     unfrag_ip6hlen + tnl_hlen;
+		packet_start = (u8 *) skb->head + SKB_GSO_CB(skb)->mac_offset;
+		memmove(packet_start-frag_hdr_sz, packet_start, unfrag_len);
+
+		SKB_GSO_CB(skb)->mac_offset -= frag_hdr_sz;
+		skb->mac_header -= frag_hdr_sz;
+		skb->network_header -= frag_hdr_sz;
+
+		fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen);
+		fptr->nexthdr = nexthdr;
+		fptr->reserved = 0;
+		fptr->identification = ipv6_proxy_select_ident(dev_net(skb->dev), skb);
+
+		/* Fragment the skb. ipv6 header and the remaining fields of the
+		 * fragment header are updated in ipv6_gso_segment()
+		 */
+		segs = skb_segment(skb, features);
+	}
 
+out:
 	return segs;
 }
 
@@ -75,7 +154,7 @@ static int udp6_gro_complete(struct sk_buff *skb, int nhoff)
 
 static const struct net_offload udpv6_offload = {
 	.callbacks = {
-		.gso_segment	=	udp6_tunnel_segment,
+		.gso_segment	=	udp6_ufo_fragment,
 		.gro_receive	=	udp6_gro_receive,
 		.gro_complete	=	udp6_gro_complete,
 	},
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index c3aec6227c91..294444bb075c 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -335,6 +335,8 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
 			     const struct dp_upcall_info *upcall_info,
 				 uint32_t cutlen)
 {
+	unsigned short gso_type = skb_shinfo(skb)->gso_type;
+	struct sw_flow_key later_key;
 	struct sk_buff *segs, *nskb;
 	int err;
 
@@ -345,9 +347,21 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
 	if (segs == NULL)
 		return -EINVAL;
 
+	if (gso_type & SKB_GSO_UDP) {
+		/* The initial flow key extracted by ovs_flow_key_extract()
+		 * in this case is for a first fragment, so we need to
+		 * properly mark later fragments.
+		 */
+		later_key = *key;
+		later_key.ip.frag = OVS_FRAG_TYPE_LATER;
+	}
+
 	/* Queue all of the segments. */
 	skb = segs;
 	do {
+		if (gso_type & SKB_GSO_UDP && skb != segs)
+			key = &later_key;
+
 		err = queue_userspace_packet(dp, skb, key, upcall_info, cutlen);
 		if (err)
 			break;
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 8c94cef25a72..cfb652a4e007 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -584,7 +584,8 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 			key->ip.frag = OVS_FRAG_TYPE_LATER;
 			return 0;
 		}
-		if (nh->frag_off & htons(IP_MF))
+		if (nh->frag_off & htons(IP_MF) ||
+			skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
 			key->ip.frag = OVS_FRAG_TYPE_FIRST;
 		else
 			key->ip.frag = OVS_FRAG_TYPE_NONE;
@@ -700,6 +701,9 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 
 		if (key->ip.frag == OVS_FRAG_TYPE_LATER)
 			return 0;
+		if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
+			key->ip.frag = OVS_FRAG_TYPE_FIRST;
+
 		/* Transport layer. */
 		if (key->ip.proto == NEXTHDR_TCP) {
 			if (tcphdr_ok(skb)) {
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 1c40caadcff9..d836f998117b 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -229,6 +229,9 @@ static int tcf_csum_ipv4_udp(struct sk_buff *skb, unsigned int ihl,
 	const struct iphdr *iph;
 	u16 ul;
 
+	if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
+		return 1;
+
 	/*
 	 * Support both UDP and UDPLITE checksum algorithms, Don't use
 	 * udph->len to get the real length without any protocol check,
@@ -282,6 +285,9 @@ static int tcf_csum_ipv6_udp(struct sk_buff *skb, unsigned int ihl,
 	const struct ipv6hdr *ip6h;
 	u16 ul;
 
+	if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
+		return 1;
+
 	/*
 	 * Support both UDP and UDPLITE checksum algorithms, Don't use
 	 * udph->len to get the real length without any protocol check,
-- 
2.14.3


From cecbec556cc7d36f86ba5181633604aa9869f80f Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <garsilva@embeddedor.com>
Date: Sat, 25 Nov 2017 13:14:40 -0600
Subject: [PATCH 31/33] net: openvswitch: datapath: fix data type in
 queue_gso_packets

[ Upstream commit 2734166e89639c973c6e125ac8bcfc2d9db72b70 ]

gso_type is being used in binary AND operations together with SKB_GSO_UDP.
The issue is that variable gso_type is of type unsigned short and
SKB_GSO_UDP expands to more than 16 bits:

SKB_GSO_UDP = 1 << 16

this makes any binary AND operation between gso_type and SKB_GSO_UDP to
be always zero, hence making some code unreachable and likely causing
undesired behavior.

Fix this by changing the data type of variable gso_type to unsigned int.

Addresses-Coverity-ID: 1462223
Fixes: 0c19f846d582 ("net: accept UFO datagrams from tuntap and packet")
Signed-off-by: Gustavo A. R. Silva <garsilva@embeddedor.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/datapath.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 294444bb075c..363dd904733d 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -335,7 +335,7 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
 			     const struct dp_upcall_info *upcall_info,
 				 uint32_t cutlen)
 {
-	unsigned short gso_type = skb_shinfo(skb)->gso_type;
+	unsigned int gso_type = skb_shinfo(skb)->gso_type;
 	struct sw_flow_key later_key;
 	struct sk_buff *segs, *nskb;
 	int err;
-- 
2.14.3


From 194ab2055f6262672656b43fb23c2d465657a82c Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 27 Nov 2017 11:11:41 -0800
Subject: [PATCH 32/33] cls_bpf: don't decrement net's refcount when offload
 fails

[ Upstream commit 25415cec502a1232b19fffc85465882b19a90415 ]

When cls_bpf offload was added it seemed like a good idea to
call cls_bpf_delete_prog() instead of extending the error
handling path, since the software state is fully initialized
at that point.  This handling of errors without jumping to
the end of the function is error prone, as proven by later
commit missing that extra call to __cls_bpf_delete_prog().

__cls_bpf_delete_prog() is now expected to be invoked with
a reference on exts->net or the field zeroed out.  The call
on the offload's error patch does not fullfil this requirement,
leading to each error stealing a reference on net namespace.

Create a function undoing what cls_bpf_set_parms() did and
use it from __cls_bpf_delete_prog() and the error path.

Fixes: aae2c35ec892 ("cls_bpf: use tcf_exts_get_net() before call_rcu()")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_bpf.c | 21 +++++++++++++--------
 1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 990eb4d91d54..3a499530f321 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -246,11 +246,8 @@ static int cls_bpf_init(struct tcf_proto *tp)
 	return 0;
 }
 
-static void __cls_bpf_delete_prog(struct cls_bpf_prog *prog)
+static void cls_bpf_free_parms(struct cls_bpf_prog *prog)
 {
-	tcf_exts_destroy(&prog->exts);
-	tcf_exts_put_net(&prog->exts);
-
 	if (cls_bpf_is_ebpf(prog))
 		bpf_prog_put(prog->filter);
 	else
@@ -258,6 +255,14 @@ static void __cls_bpf_delete_prog(struct cls_bpf_prog *prog)
 
 	kfree(prog->bpf_name);
 	kfree(prog->bpf_ops);
+}
+
+static void __cls_bpf_delete_prog(struct cls_bpf_prog *prog)
+{
+	tcf_exts_destroy(&prog->exts);
+	tcf_exts_put_net(&prog->exts);
+
+	cls_bpf_free_parms(prog);
 	kfree(prog);
 }
 
@@ -509,10 +514,8 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
 		goto errout;
 
 	ret = cls_bpf_offload(tp, prog, oldprog);
-	if (ret) {
-		__cls_bpf_delete_prog(prog);
-		return ret;
-	}
+	if (ret)
+		goto errout_parms;
 
 	if (!tc_in_hw(prog->gen_flags))
 		prog->gen_flags |= TCA_CLS_FLAGS_NOT_IN_HW;
@@ -529,6 +532,8 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
 	*arg = prog;
 	return 0;
 
+errout_parms:
+	cls_bpf_free_parms(prog);
 errout:
 	tcf_exts_destroy(&prog->exts);
 	kfree(prog);
-- 
2.14.3


From 257181e070d4f380a452faccccb4ab434914077e Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 26 Nov 2017 20:56:07 +0800
Subject: [PATCH 33/33] sctp: use right member as the param of
 list_for_each_entry

[ Upstream commit a8dd397903a6e57157f6265911f7d35681364427 ]

Commit d04adf1b3551 ("sctp: reset owner sk for data chunks on out queues
when migrating a sock") made a mistake that using 'list' as the param of
list_for_each_entry to traverse the retransmit, sacked and abandoned
queues, while chunks are using 'transmitted_list' to link into these
queues.

It could cause NULL dereference panic if there are chunks in any of these
queues when peeling off one asoc.

So use the chunk member 'transmitted_list' instead in this patch.

Fixes: d04adf1b3551 ("sctp: reset owner sk for data chunks on out queues when migrating a sock")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 6f45d1713452..f475711ebc61 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -187,13 +187,13 @@ static void sctp_for_each_tx_datachunk(struct sctp_association *asoc,
 		list_for_each_entry(chunk, &t->transmitted, transmitted_list)
 			cb(chunk);
 
-	list_for_each_entry(chunk, &q->retransmit, list)
+	list_for_each_entry(chunk, &q->retransmit, transmitted_list)
 		cb(chunk);
 
-	list_for_each_entry(chunk, &q->sacked, list)
+	list_for_each_entry(chunk, &q->sacked, transmitted_list)
 		cb(chunk);
 
-	list_for_each_entry(chunk, &q->abandoned, list)
+	list_for_each_entry(chunk, &q->abandoned, transmitted_list)
 		cb(chunk);
 
 	list_for_each_entry(chunk, &q->out_chunk_list, list)
-- 
2.14.3

Re: [PATCHES] Networking

[Greg KH]

On Tue, Dec 12, 2017 at 10:44:45AM -0500, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.9 and v4.14 -stable,
> respectively.

Now both applied, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 196 bytes --]


Thought you'd make it into 2018 without some more networking
bug fixes?  Think again! :-)

Please queue up the following networking bug fixes for 4.9.x
and 4.14.x -stable, respectively.

Thanks!

[-- Attachment #2: net_49.mbox --]
[-- Type: Application/Octet-Stream, Size: 98232 bytes --]

From aa9a0ec61c193a44e33f0e392a8b92886bd81974 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 11 Dec 2017 07:17:39 -0800
Subject: [PATCH 01/33] ipv4: igmp: guard against silly MTU values
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit b5476022bbada3764609368f03329ca287528dc8 ]

IPv4 stack reacts to changes to small MTU, by disabling itself under
RTNL.

But there is a window where threads not using RTNL can see a wrong
device mtu. This can lead to surprises, in igmp code where it is
assumed the mtu is suitable.

Fix this by reading device mtu once and checking IPv4 minimal MTU.

This patch adds missing IPV4_MIN_MTU define, to not abuse
ETH_MIN_MTU anymore.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h     |  2 ++
 net/ipv4/devinet.c   |  2 +-
 net/ipv4/igmp.c      | 24 +++++++++++++++---------
 net/ipv4/ip_tunnel.c |  4 ++--
 4 files changed, 20 insertions(+), 12 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index 51c6b97..0e3dcd5 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -33,6 +33,8 @@
 #include <net/flow.h>
 #include <net/flow_dissector.h>
 
+#define IPV4_MIN_MTU		68			/* RFC 791 */
+
 struct sock;
 
 struct inet_skb_parm {
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 062a67c..f08f984 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1380,7 +1380,7 @@ static void inetdev_changename(struct net_device *dev, struct in_device *in_dev)
 
 static bool inetdev_valid_mtu(unsigned int mtu)
 {
-	return mtu >= 68;
+	return mtu >= IPV4_MIN_MTU;
 }
 
 static void inetdev_send_gratuitous_arp(struct net_device *dev,
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 08575e3..49e0704 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -404,16 +404,17 @@ static int grec_size(struct ip_mc_list *pmc, int type, int gdel, int sdel)
 }
 
 static struct sk_buff *add_grhead(struct sk_buff *skb, struct ip_mc_list *pmc,
-	int type, struct igmpv3_grec **ppgr)
+	int type, struct igmpv3_grec **ppgr, unsigned int mtu)
 {
 	struct net_device *dev = pmc->interface->dev;
 	struct igmpv3_report *pih;
 	struct igmpv3_grec *pgr;
 
-	if (!skb)
-		skb = igmpv3_newpack(dev, dev->mtu);
-	if (!skb)
-		return NULL;
+	if (!skb) {
+		skb = igmpv3_newpack(dev, mtu);
+		if (!skb)
+			return NULL;
+	}
 	pgr = (struct igmpv3_grec *)skb_put(skb, sizeof(struct igmpv3_grec));
 	pgr->grec_type = type;
 	pgr->grec_auxwords = 0;
@@ -436,12 +437,17 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
 	struct igmpv3_grec *pgr = NULL;
 	struct ip_sf_list *psf, *psf_next, *psf_prev, **psf_list;
 	int scount, stotal, first, isquery, truncate;
+	unsigned int mtu;
 
 	if (pmc->multiaddr == IGMP_ALL_HOSTS)
 		return skb;
 	if (ipv4_is_local_multicast(pmc->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports)
 		return skb;
 
+	mtu = READ_ONCE(dev->mtu);
+	if (mtu < IPV4_MIN_MTU)
+		return skb;
+
 	isquery = type == IGMPV3_MODE_IS_INCLUDE ||
 		  type == IGMPV3_MODE_IS_EXCLUDE;
 	truncate = type == IGMPV3_MODE_IS_EXCLUDE ||
@@ -462,7 +468,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
 		    AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) {
 			if (skb)
 				igmpv3_sendpack(skb);
-			skb = igmpv3_newpack(dev, dev->mtu);
+			skb = igmpv3_newpack(dev, mtu);
 		}
 	}
 	first = 1;
@@ -498,12 +504,12 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
 				pgr->grec_nsrcs = htons(scount);
 			if (skb)
 				igmpv3_sendpack(skb);
-			skb = igmpv3_newpack(dev, dev->mtu);
+			skb = igmpv3_newpack(dev, mtu);
 			first = 1;
 			scount = 0;
 		}
 		if (first) {
-			skb = add_grhead(skb, pmc, type, &pgr);
+			skb = add_grhead(skb, pmc, type, &pgr, mtu);
 			first = 0;
 		}
 		if (!skb)
@@ -538,7 +544,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
 				igmpv3_sendpack(skb);
 				skb = NULL; /* add_grhead will get a new one */
 			}
-			skb = add_grhead(skb, pmc, type, &pgr);
+			skb = add_grhead(skb, pmc, type, &pgr, mtu);
 		}
 	}
 	if (pgr)
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index bd7f183..96536a0 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -346,8 +346,8 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
 	dev->needed_headroom = t_hlen + hlen;
 	mtu -= (dev->hard_header_len + t_hlen);
 
-	if (mtu < 68)
-		mtu = 68;
+	if (mtu < IPV4_MIN_MTU)
+		mtu = IPV4_MIN_MTU;
 
 	return mtu;
 }
-- 
2.9.5


From 771cda90739e947bf0dd1a2911757f4e95c04239 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 11 Dec 2017 07:03:38 -0800
Subject: [PATCH 02/33] ipv6: mcast: better catch silly mtu values

[ Upstream commit b9b312a7a451e9c098921856e7cfbc201120e1a7 ]

syzkaller reported crashes in IPv6 stack [1]

Xin Long found that lo MTU was set to silly values.

IPv6 stack reacts to changes to small MTU, by disabling itself under
RTNL.

But there is a window where threads not using RTNL can see a wrong
device mtu. This can lead to surprises, in mld code where it is assumed
the mtu is suitable.

Fix this by reading device mtu once and checking IPv6 minimal MTU.

[1]
 skbuff: skb_over_panic: text:0000000010b86b8d len:196 put:20
 head:000000003b477e60 data:000000000e85441e tail:0xd4 end:0xc0 dev:lo
 ------------[ cut here ]------------
 kernel BUG at net/core/skbuff.c:104!
 invalid opcode: 0000 [#1] SMP KASAN
 Dumping ftrace buffer:
    (ftrace buffer empty)
 Modules linked in:
 CPU: 1 PID: 0 Comm: swapper/1 Not tainted 4.15.0-rc2-mm1+ #39
 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
 Google 01/01/2011
 RIP: 0010:skb_panic+0x15c/0x1f0 net/core/skbuff.c:100
 RSP: 0018:ffff8801db307508 EFLAGS: 00010286
 RAX: 0000000000000082 RBX: ffff8801c517e840 RCX: 0000000000000000
 RDX: 0000000000000082 RSI: 1ffff1003b660e61 RDI: ffffed003b660e95
 RBP: ffff8801db307570 R08: 1ffff1003b660e23 R09: 0000000000000000
 R10: 0000000000000000 R11: 0000000000000000 R12: ffffffff85bd4020
 R13: ffffffff84754ed2 R14: 0000000000000014 R15: ffff8801c4e26540
 FS:  0000000000000000(0000) GS:ffff8801db300000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000463610 CR3: 00000001c6698000 CR4: 00000000001406e0
 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
 Call Trace:
  <IRQ>
  skb_over_panic net/core/skbuff.c:109 [inline]
  skb_put+0x181/0x1c0 net/core/skbuff.c:1694
  add_grhead.isra.24+0x42/0x3b0 net/ipv6/mcast.c:1695
  add_grec+0xa55/0x1060 net/ipv6/mcast.c:1817
  mld_send_cr net/ipv6/mcast.c:1903 [inline]
  mld_ifc_timer_expire+0x4d2/0x770 net/ipv6/mcast.c:2448
  call_timer_fn+0x23b/0x840 kernel/time/timer.c:1320
  expire_timers kernel/time/timer.c:1357 [inline]
  __run_timers+0x7e1/0xb60 kernel/time/timer.c:1660
  run_timer_softirq+0x4c/0xb0 kernel/time/timer.c:1686
  __do_softirq+0x29d/0xbb2 kernel/softirq.c:285
  invoke_softirq kernel/softirq.c:365 [inline]
  irq_exit+0x1d3/0x210 kernel/softirq.c:405
  exiting_irq arch/x86/include/asm/apic.h:540 [inline]
  smp_apic_timer_interrupt+0x16b/0x700 arch/x86/kernel/apic/apic.c:1052
  apic_timer_interrupt+0xa9/0xb0 arch/x86/entry/entry_64.S:920

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Tested-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/mcast.c | 25 +++++++++++++++----------
 1 file changed, 15 insertions(+), 10 deletions(-)

diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 1bdc703..ca8fac6 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1682,16 +1682,16 @@ static int grec_size(struct ifmcaddr6 *pmc, int type, int gdel, int sdel)
 }
 
 static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc,
-	int type, struct mld2_grec **ppgr)
+	int type, struct mld2_grec **ppgr, unsigned int mtu)
 {
-	struct net_device *dev = pmc->idev->dev;
 	struct mld2_report *pmr;
 	struct mld2_grec *pgr;
 
-	if (!skb)
-		skb = mld_newpack(pmc->idev, dev->mtu);
-	if (!skb)
-		return NULL;
+	if (!skb) {
+		skb = mld_newpack(pmc->idev, mtu);
+		if (!skb)
+			return NULL;
+	}
 	pgr = (struct mld2_grec *)skb_put(skb, sizeof(struct mld2_grec));
 	pgr->grec_type = type;
 	pgr->grec_auxwords = 0;
@@ -1714,10 +1714,15 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
 	struct mld2_grec *pgr = NULL;
 	struct ip6_sf_list *psf, *psf_next, *psf_prev, **psf_list;
 	int scount, stotal, first, isquery, truncate;
+	unsigned int mtu;
 
 	if (pmc->mca_flags & MAF_NOREPORT)
 		return skb;
 
+	mtu = READ_ONCE(dev->mtu);
+	if (mtu < IPV6_MIN_MTU)
+		return skb;
+
 	isquery = type == MLD2_MODE_IS_INCLUDE ||
 		  type == MLD2_MODE_IS_EXCLUDE;
 	truncate = type == MLD2_MODE_IS_EXCLUDE ||
@@ -1738,7 +1743,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
 		    AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) {
 			if (skb)
 				mld_sendpack(skb);
-			skb = mld_newpack(idev, dev->mtu);
+			skb = mld_newpack(idev, mtu);
 		}
 	}
 	first = 1;
@@ -1774,12 +1779,12 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
 				pgr->grec_nsrcs = htons(scount);
 			if (skb)
 				mld_sendpack(skb);
-			skb = mld_newpack(idev, dev->mtu);
+			skb = mld_newpack(idev, mtu);
 			first = 1;
 			scount = 0;
 		}
 		if (first) {
-			skb = add_grhead(skb, pmc, type, &pgr);
+			skb = add_grhead(skb, pmc, type, &pgr, mtu);
 			first = 0;
 		}
 		if (!skb)
@@ -1814,7 +1819,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
 				mld_sendpack(skb);
 				skb = NULL; /* add_grhead will get a new one */
 			}
-			skb = add_grhead(skb, pmc, type, &pgr);
+			skb = add_grhead(skb, pmc, type, &pgr, mtu);
 		}
 	}
 	if (pgr)
-- 
2.9.5


From bd94834fd9e8d5a8777531880a5b5a7ec3f30440 Mon Sep 17 00:00:00 2001
From: Fugang Duan <fugang.duan@nxp.com>
Date: Fri, 22 Dec 2017 17:12:09 +0800
Subject: [PATCH 03/33] net: fec: unmap the xmit buffer that are not
 transferred by DMA

[ Upstream commit 178e5f57a8d8f8fc5799a624b96fc31ef9a29ffa ]

The enet IP only support 32 bit, it will use swiotlb buffer to do dma
mapping when xmit buffer DMA memory address is bigger than 4G in i.MX
platform. After stress suspend/resume test, it will print out:

log:
[12826.352864] fec 5b040000.ethernet: swiotlb buffer is full (sz: 191 bytes)
[12826.359676] DMA: Out of SW-IOMMU space for 191 bytes at device 5b040000.ethernet
[12826.367110] fec 5b040000.ethernet eth0: Tx DMA memory map failed

The issue is that the ready xmit buffers that are dma mapped but DMA still
don't copy them into fifo, once MAC restart, these DMA buffers are not unmapped.
So it should check the dma mapping buffer and unmap them.

Signed-off-by: Fugang Duan <fugang.duan@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_main.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 849b871..60f6866 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -813,6 +813,12 @@ static void fec_enet_bd_init(struct net_device *dev)
 		for (i = 0; i < txq->bd.ring_size; i++) {
 			/* Initialize the BD for every fragment in the page. */
 			bdp->cbd_sc = cpu_to_fec16(0);
+			if (bdp->cbd_bufaddr &&
+			    !IS_TSO_HEADER(txq, fec32_to_cpu(bdp->cbd_bufaddr)))
+				dma_unmap_single(&fep->pdev->dev,
+						 fec32_to_cpu(bdp->cbd_bufaddr),
+						 fec16_to_cpu(bdp->cbd_datlen),
+						 DMA_TO_DEVICE);
 			if (txq->tx_skbuff[i]) {
 				dev_kfree_skb_any(txq->tx_skbuff[i]);
 				txq->tx_skbuff[i] = NULL;
-- 
2.9.5


From bcbff192d6de360b8ff41f1ce7df35fcc414366e Mon Sep 17 00:00:00 2001
From: Kevin Cernekee <cernekee@chromium.org>
Date: Mon, 11 Dec 2017 11:13:45 -0800
Subject: [PATCH 04/33] net: igmp: Use correct source address on IGMPv3 reports

[ Upstream commit a46182b00290839fa3fa159d54fd3237bd8669f0 ]

Closing a multicast socket after the final IPv4 address is deleted
from an interface can generate a membership report that uses the
source IP from a different interface.  The following test script, run
from an isolated netns, reproduces the issue:

    #!/bin/bash

    ip link add dummy0 type dummy
    ip link add dummy1 type dummy
    ip link set dummy0 up
    ip link set dummy1 up
    ip addr add 10.1.1.1/24 dev dummy0
    ip addr add 192.168.99.99/24 dev dummy1

    tcpdump -U -i dummy0 &
    socat EXEC:"sleep 2" \
        UDP4-DATAGRAM:239.101.1.68:8889,ip-add-membership=239.0.1.68:10.1.1.1 &

    sleep 1
    ip addr del 10.1.1.1/24 dev dummy0
    sleep 5
    kill %tcpdump

RFC 3376 specifies that the report must be sent with a valid IP source
address from the destination subnet, or from address 0.0.0.0.  Add an
extra check to make sure this is the case.

Signed-off-by: Kevin Cernekee <cernekee@chromium.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/igmp.c | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 49e0704..7bff0c6 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -89,6 +89,7 @@
 #include <linux/rtnetlink.h>
 #include <linux/times.h>
 #include <linux/pkt_sched.h>
+#include <linux/byteorder/generic.h>
 
 #include <net/net_namespace.h>
 #include <net/arp.h>
@@ -321,6 +322,23 @@ igmp_scount(struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted)
 	return scount;
 }
 
+/* source address selection per RFC 3376 section 4.2.13 */
+static __be32 igmpv3_get_srcaddr(struct net_device *dev,
+				 const struct flowi4 *fl4)
+{
+	struct in_device *in_dev = __in_dev_get_rcu(dev);
+
+	if (!in_dev)
+		return htonl(INADDR_ANY);
+
+	for_ifa(in_dev) {
+		if (inet_ifa_match(fl4->saddr, ifa))
+			return fl4->saddr;
+	} endfor_ifa(in_dev);
+
+	return htonl(INADDR_ANY);
+}
+
 static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu)
 {
 	struct sk_buff *skb;
@@ -368,7 +386,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu)
 	pip->frag_off = htons(IP_DF);
 	pip->ttl      = 1;
 	pip->daddr    = fl4.daddr;
-	pip->saddr    = fl4.saddr;
+	pip->saddr    = igmpv3_get_srcaddr(dev, &fl4);
 	pip->protocol = IPPROTO_IGMP;
 	pip->tot_len  = 0;	/* filled in later */
 	ip_select_ident(net, skb, NULL);
-- 
2.9.5


From 4cd8e7ae6075135b19c09d916c7f7f6c2e657cc0 Mon Sep 17 00:00:00 2001
From: Kevin Cernekee <cernekee@chromium.org>
Date: Wed, 6 Dec 2017 12:12:27 -0800
Subject: [PATCH 05/33] netlink: Add netns check on taps

[ Upstream commit 93c647643b48f0131f02e45da3bd367d80443291 ]

Currently, a nlmon link inside a child namespace can observe systemwide
netlink activity.  Filter the traffic so that nlmon can only sniff
netlink messages from its own netns.

Test case:

    vpnns -- bash -c "ip link add nlmon0 type nlmon; \
                      ip link set nlmon0 up; \
                      tcpdump -i nlmon0 -q -w /tmp/nlmon.pcap -U" &
    sudo ip xfrm state add src 10.1.1.1 dst 10.1.1.2 proto esp \
        spi 0x1 mode transport \
        auth sha1 0x6162633132330000000000000000000000000000 \
        enc aes 0x00000000000000000000000000000000
    grep --binary abc123 /tmp/nlmon.pcap

Signed-off-by: Kevin Cernekee <cernekee@chromium.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 1ff497b..e1c123d 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -261,6 +261,9 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb,
 	struct sock *sk = skb->sk;
 	int ret = -ENOMEM;
 
+	if (!net_eq(dev_net(dev), sock_net(sk)))
+		return 0;
+
 	dev_hold(dev);
 
 	if (is_vmalloc_addr(skb->head))
-- 
2.9.5


From a8ab3455737183e3dd274d0c860121af6c4565f1 Mon Sep 17 00:00:00 2001
From: Sebastian Sjoholm <ssjoholm@mac.com>
Date: Mon, 11 Dec 2017 21:51:14 +0100
Subject: [PATCH 06/33] net: qmi_wwan: add Sierra EM7565 1199:9091
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit aceef61ee56898cfa7b6960fb60b9326c3860441 ]

Sierra Wireless EM7565 is an Qualcomm MDM9x50 based M.2 modem.
The USB id is added to qmi_wwan.c to allow QMI communication
with the EM7565.

Signed-off-by: Sebastian Sjoholm <ssjoholm@mac.com>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 105fbfb..db65d9a 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -907,6 +907,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1199, 0x9079, 10)},	/* Sierra Wireless EM74xx */
 	{QMI_FIXED_INTF(0x1199, 0x907b, 8)},	/* Sierra Wireless EM74xx */
 	{QMI_FIXED_INTF(0x1199, 0x907b, 10)},	/* Sierra Wireless EM74xx */
+	{QMI_FIXED_INTF(0x1199, 0x9091, 8)},	/* Sierra Wireless EM7565 */
 	{QMI_FIXED_INTF(0x1bbb, 0x011e, 4)},	/* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */
 	{QMI_FIXED_INTF(0x1bbb, 0x0203, 2)},	/* Alcatel L800MA */
 	{QMI_FIXED_INTF(0x2357, 0x0201, 4)},	/* TP-LINK HSUPA Modem MA180 */
-- 
2.9.5


From ef54c7a303cc3565a98b06ef3c07d845ccbdd9d8 Mon Sep 17 00:00:00 2001
From: Shaohua Li <shli@fb.com>
Date: Wed, 20 Dec 2017 12:10:21 -0800
Subject: [PATCH 07/33] net: reevalulate autoflowlabel setting after sysctl
 setting

[ Upstream commit 513674b5a2c9c7a67501506419da5c3c77ac6f08 ]

sysctl.ip6.auto_flowlabels is default 1. In our hosts, we set it to 2.
If sockopt doesn't set autoflowlabel, outcome packets from the hosts are
supposed to not include flowlabel. This is true for normal packet, but
not for reset packet.

The reason is ipv6_pinfo.autoflowlabel is set in sock creation. Later if
we change sysctl.ip6.auto_flowlabels, the ipv6_pinfo.autoflowlabel isn't
changed, so the sock will keep the old behavior in terms of auto
flowlabel. Reset packet is suffering from this problem, because reset
packet is sent from a special control socket, which is created at boot
time. Since sysctl.ipv6.auto_flowlabels is 1 by default, the control
socket will always have its ipv6_pinfo.autoflowlabel set, even after
user set sysctl.ipv6.auto_flowlabels to 1, so reset packset will always
have flowlabel. Normal sock created before sysctl setting suffers from
the same issue. We can't even turn off autoflowlabel unless we kill all
socks in the hosts.

To fix this, if IPV6_AUTOFLOWLABEL sockopt is used, we use the
autoflowlabel setting from user, otherwise we always call
ip6_default_np_autolabel() which has the new settings of sysctl.

Note, this changes behavior a little bit. Before commit 42240901f7c4
(ipv6: Implement different admin modes for automatic flow labels), the
autoflowlabel behavior of a sock isn't sticky, eg, if sysctl changes,
existing connection will change autoflowlabel behavior. After that
commit, autoflowlabel behavior is sticky in the whole life of the sock.
With this patch, the behavior isn't sticky again.

Cc: Martin KaFai Lau <kafai@fb.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Tom Herbert <tom@quantonium.net>
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ipv6.h     |  3 ++-
 net/ipv6/af_inet6.c      |  1 -
 net/ipv6/ip6_output.c    | 12 ++++++++++--
 net/ipv6/ipv6_sockglue.c |  1 +
 4 files changed, 13 insertions(+), 4 deletions(-)

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index a064997..b9dfca55 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -246,7 +246,8 @@ struct ipv6_pinfo {
 						 * 100: prefer care-of address
 						 */
 				dontfrag:1,
-				autoflowlabel:1;
+				autoflowlabel:1,
+				autoflowlabel_set:1;
 	__u8			min_hopcount;
 	__u8			tclass;
 	__be32			rcv_flowinfo;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 8285a1c..5cad76f 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -209,7 +209,6 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol,
 	np->mcast_hops	= IPV6_DEFAULT_MCASTHOPS;
 	np->mc_loop	= 1;
 	np->pmtudisc	= IPV6_PMTUDISC_WANT;
-	np->autoflowlabel = ip6_default_np_autolabel(sock_net(sk));
 	sk->sk_ipv6only	= net->ipv6.sysctl.bindv6only;
 
 	/* Init the ipv4 part of the socket since we can have sockets
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 6e01c9a..506efba 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -156,6 +156,14 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 			    !(IP6CB(skb)->flags & IP6SKB_REROUTED));
 }
 
+static bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np)
+{
+	if (!np->autoflowlabel_set)
+		return ip6_default_np_autolabel(net);
+	else
+		return np->autoflowlabel;
+}
+
 /*
  * xmit an sk_buff (used by TCP, SCTP and DCCP)
  * Note : socket lock is not held for SYNACK packets, but might be modified
@@ -219,7 +227,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 		hlimit = ip6_dst_hoplimit(dst);
 
 	ip6_flow_hdr(hdr, tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel,
-						     np->autoflowlabel, fl6));
+				ip6_autoflowlabel(net, np), fl6));
 
 	hdr->payload_len = htons(seg_len);
 	hdr->nexthdr = proto;
@@ -1691,7 +1699,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
 
 	ip6_flow_hdr(hdr, v6_cork->tclass,
 		     ip6_make_flowlabel(net, skb, fl6->flowlabel,
-					np->autoflowlabel, fl6));
+					ip6_autoflowlabel(net, np), fl6));
 	hdr->hop_limit = v6_cork->hop_limit;
 	hdr->nexthdr = proto;
 	hdr->saddr = fl6->saddr;
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 38bee17..6e3871c 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -874,6 +874,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 		break;
 	case IPV6_AUTOFLOWLABEL:
 		np->autoflowlabel = valbool;
+		np->autoflowlabel_set = 1;
 		retv = 0;
 		break;
 	}
-- 
2.9.5


From 58448b47d3a5d897b779234bf1958a7bde2a928b Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Tue, 5 Dec 2017 21:29:37 +0200
Subject: [PATCH 08/33] ptr_ring: add barriers

[ Upstream commit a8ceb5dbfde1092b466936bca0ff3be127ecf38e ]

Users of ptr_ring expect that it's safe to give the
data structure a pointer and have it be available
to consumers, but that actually requires an smb_wmb
or a stronger barrier.

In absence of such barriers and on architectures that reorder writes,
consumer might read an un=initialized value from an skb pointer stored
in the skb array.  This was observed causing crashes.

To fix, add memory barriers.  The barrier we use is a wmb, the
assumption being that producers do not need to read the value so we do
not need to order these reads.

Reported-by: George Cherian <george.cherian@cavium.com>
Suggested-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ptr_ring.h | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h
index b83507c..e38f471 100644
--- a/include/linux/ptr_ring.h
+++ b/include/linux/ptr_ring.h
@@ -99,12 +99,18 @@ static inline bool ptr_ring_full_bh(struct ptr_ring *r)
 
 /* Note: callers invoking this in a loop must use a compiler barrier,
  * for example cpu_relax(). Callers must hold producer_lock.
+ * Callers are responsible for making sure pointer that is being queued
+ * points to a valid data.
  */
 static inline int __ptr_ring_produce(struct ptr_ring *r, void *ptr)
 {
 	if (unlikely(!r->size) || r->queue[r->producer])
 		return -ENOSPC;
 
+	/* Make sure the pointer we are storing points to a valid data. */
+	/* Pairs with smp_read_barrier_depends in __ptr_ring_consume. */
+	smp_wmb();
+
 	r->queue[r->producer++] = ptr;
 	if (unlikely(r->producer >= r->size))
 		r->producer = 0;
@@ -244,6 +250,9 @@ static inline void *__ptr_ring_consume(struct ptr_ring *r)
 	if (ptr)
 		__ptr_ring_discard_one(r);
 
+	/* Make sure anyone accessing data through the pointer is up to date. */
+	/* Pairs with smp_wmb in __ptr_ring_produce. */
+	smp_read_barrier_depends();
 	return ptr;
 }
 
-- 
2.9.5


From e3d6cb5c812b9dd5bf10651c82e3b35a5237ce5a Mon Sep 17 00:00:00 2001
From: Avinash Repaka <avinash.repaka@oracle.com>
Date: Thu, 21 Dec 2017 20:17:04 -0800
Subject: [PATCH 09/33] RDS: Check cmsg_len before dereferencing CMSG_DATA

[ Upstream commit 14e138a86f6347c6199f610576d2e11c03bec5f0 ]

RDS currently doesn't check if the length of the control message is
large enough to hold the required data, before dereferencing the control
message data. This results in following crash:

BUG: KASAN: stack-out-of-bounds in rds_rdma_bytes net/rds/send.c:1013
[inline]
BUG: KASAN: stack-out-of-bounds in rds_sendmsg+0x1f02/0x1f90
net/rds/send.c:1066
Read of size 8 at addr ffff8801c928fb70 by task syzkaller455006/3157

CPU: 0 PID: 3157 Comm: syzkaller455006 Not tainted 4.15.0-rc3+ #161
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x194/0x257 lib/dump_stack.c:53
 print_address_description+0x73/0x250 mm/kasan/report.c:252
 kasan_report_error mm/kasan/report.c:351 [inline]
 kasan_report+0x25b/0x340 mm/kasan/report.c:409
 __asan_report_load8_noabort+0x14/0x20 mm/kasan/report.c:430
 rds_rdma_bytes net/rds/send.c:1013 [inline]
 rds_sendmsg+0x1f02/0x1f90 net/rds/send.c:1066
 sock_sendmsg_nosec net/socket.c:628 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:638
 ___sys_sendmsg+0x320/0x8b0 net/socket.c:2018
 __sys_sendmmsg+0x1ee/0x620 net/socket.c:2108
 SYSC_sendmmsg net/socket.c:2139 [inline]
 SyS_sendmmsg+0x35/0x60 net/socket.c:2134
 entry_SYSCALL_64_fastpath+0x1f/0x96
RIP: 0033:0x43fe49
RSP: 002b:00007fffbe244ad8 EFLAGS: 00000217 ORIG_RAX: 0000000000000133
RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 000000000043fe49
RDX: 0000000000000001 RSI: 000000002020c000 RDI: 0000000000000003
RBP: 00000000006ca018 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000217 R12: 00000000004017b0
R13: 0000000000401840 R14: 0000000000000000 R15: 0000000000000000

To fix this, we verify that the cmsg_len is large enough to hold the
data to be read, before proceeding further.

Reported-by: syzbot <syzkaller-bugs@googlegroups.com>
Signed-off-by: Avinash Repaka <avinash.repaka@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Reviewed-by: Yuval Shaia <yuval.shaia@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/send.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/rds/send.c b/net/rds/send.c
index ad247dc..ef53d164 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -1006,6 +1006,9 @@ static int rds_rdma_bytes(struct msghdr *msg, size_t *rdma_bytes)
 			continue;
 
 		if (cmsg->cmsg_type == RDS_CMSG_RDMA_ARGS) {
+			if (cmsg->cmsg_len <
+			    CMSG_LEN(sizeof(struct rds_rdma_args)))
+				return -EINVAL;
 			args = CMSG_DATA(cmsg);
 			*rdma_bytes += args->remote_vec.bytes;
 		}
-- 
2.9.5


From 3532c5729346cc8b5559f2716fcdf40d4ae25d2c Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Thu, 7 Dec 2017 12:43:30 -0500
Subject: [PATCH 10/33] tcp_bbr: record "full bw reached" decision in new
 full_bw_reached bit

[ Upstream commit c589e69b508d29ed8e644dfecda453f71c02ec27 ]

This commit records the "full bw reached" decision in a new
full_bw_reached bit. This is a pure refactor that does not change the
current behavior, but enables subsequent fixes and improvements.

In particular, this enables simple and clean fixes because the full_bw
and full_bw_cnt can be unconditionally zeroed without worrying about
forgetting that we estimated we filled the pipe in Startup. And it
enables future improvements because multiple code paths can be used
for estimating that we filled the pipe in Startup; any new code paths
only need to set this bit when they think the pipe is full.

Note that this fix intentionally reduces the width of the full_bw_cnt
counter, since we have never used the most significant bit.

Signed-off-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_bbr.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index cb8db34..97f9cac 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -81,7 +81,8 @@ struct bbr {
 	u32	lt_last_lost;	     /* LT intvl start: tp->lost */
 	u32	pacing_gain:10,	/* current gain for setting pacing rate */
 		cwnd_gain:10,	/* current gain for setting cwnd */
-		full_bw_cnt:3,	/* number of rounds without large bw gains */
+		full_bw_reached:1,   /* reached full bw in Startup? */
+		full_bw_cnt:2,	/* number of rounds without large bw gains */
 		cycle_idx:3,	/* current index in pacing_gain cycle array */
 		has_seen_rtt:1, /* have we seen an RTT sample yet? */
 		unused_b:5;
@@ -151,7 +152,7 @@ static bool bbr_full_bw_reached(const struct sock *sk)
 {
 	const struct bbr *bbr = inet_csk_ca(sk);
 
-	return bbr->full_bw_cnt >= bbr_full_bw_cnt;
+	return bbr->full_bw_reached;
 }
 
 /* Return the windowed max recent bandwidth sample, in pkts/uS << BW_SCALE. */
@@ -688,6 +689,7 @@ static void bbr_check_full_bw_reached(struct sock *sk,
 		return;
 	}
 	++bbr->full_bw_cnt;
+	bbr->full_bw_reached = bbr->full_bw_cnt >= bbr_full_bw_cnt;
 }
 
 /* If pipe is probably full, drain the queue and then enter steady-state. */
@@ -821,6 +823,7 @@ static void bbr_init(struct sock *sk)
 	bbr->restore_cwnd = 0;
 	bbr->round_start = 0;
 	bbr->idle_restart = 0;
+	bbr->full_bw_reached = 0;
 	bbr->full_bw = 0;
 	bbr->full_bw_cnt = 0;
 	bbr->cycle_mstamp.v64 = 0;
-- 
2.9.5


From 510499fc1c8a833bb55f2b719453cc9481813102 Mon Sep 17 00:00:00 2001
From: Christoph Paasch <cpaasch@apple.com>
Date: Mon, 11 Dec 2017 00:05:46 -0800
Subject: [PATCH 11/33] tcp md5sig: Use skb's saddr when replying to an
 incoming segment

[ Upstream commit 30791ac41927ebd3e75486f9504b6d2280463bf0 ]

The MD5-key that belongs to a connection is identified by the peer's
IP-address. When we are in tcp_v4(6)_reqsk_send_ack(), we are replying
to an incoming segment from tcp_check_req() that failed the seq-number
checks.

Thus, to find the correct key, we need to use the skb's saddr and not
the daddr.

This bug seems to have been there since quite a while, but probably got
unnoticed because the consequences are not catastrophic. We will call
tcp_v4_reqsk_send_ack only to send a challenge-ACK back to the peer,
thus the connection doesn't really fail.

Fixes: 9501f9722922 ("tcp md5sig: Let the caller pass appropriate key for tcp_v{4,6}_do_calc_md5_hash().")
Signed-off-by: Christoph Paasch <cpaasch@apple.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c | 2 +-
 net/ipv6/tcp_ipv6.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index d577ec0..b396073 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -828,7 +828,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
 			tcp_time_stamp,
 			req->ts_recent,
 			0,
-			tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr,
+			tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->saddr,
 					  AF_INET),
 			inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0,
 			ip_hdr(skb)->tos);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 7ac2365..eb62454 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -962,7 +962,7 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
 			tcp_rsk(req)->rcv_nxt,
 			req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale,
 			tcp_time_stamp, req->ts_recent, sk->sk_bound_dev_if,
-			tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr),
+			tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr),
 			0, 0);
 }
 
-- 
2.9.5


From decb1eb1bd6e450997f1bc025e2647fcb6625841 Mon Sep 17 00:00:00 2001
From: Brian King <brking@linux.vnet.ibm.com>
Date: Fri, 15 Dec 2017 15:21:50 -0600
Subject: [PATCH 12/33] tg3: Fix rx hang on MTU change with 5717/5719

[ Upstream commit 748a240c589824e9121befb1cba5341c319885bc ]

This fixes a hang issue seen when changing the MTU size from 1500 MTU
to 9000 MTU on both 5717 and 5719 chips. In discussion with Broadcom,
they've indicated that these chipsets have the same phy as the 57766
chipset, so the same workarounds apply. This has been tested by IBM
on both Power 8 and Power 9 systems as well as by Broadcom on x86
hardware and has been confirmed to resolve the hang issue.

Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/tg3.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index edae2dc..bb22d32 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -14226,7 +14226,9 @@ static int tg3_change_mtu(struct net_device *dev, int new_mtu)
 	/* Reset PHY, otherwise the read DMA engine will be in a mode that
 	 * breaks all requests to 256 bytes.
 	 */
-	if (tg3_asic_rev(tp) == ASIC_REV_57766)
+	if (tg3_asic_rev(tp) == ASIC_REV_57766 ||
+	    tg3_asic_rev(tp) == ASIC_REV_5717 ||
+	    tg3_asic_rev(tp) == ASIC_REV_5719)
 		reset_phy = true;
 
 	err = tg3_restart_hw(tp, reset_phy);
-- 
2.9.5


From 8085aa1df8476f1f71082afe73ca8579c981aaba Mon Sep 17 00:00:00 2001
From: Mohamed Ghannam <simo.ghannam@gmail.com>
Date: Sun, 10 Dec 2017 03:50:58 +0000
Subject: [PATCH 13/33] net: ipv4: fix for a race condition in raw_sendmsg

[ Upstream commit 8f659a03a0ba9289b9aeb9b4470e6fb263d6f483 ]

inet->hdrincl is racy, and could lead to uninitialized stack pointer
usage, so its value should be read only once.

Fixes: c008ba5bdc9f ("ipv4: Avoid reading user iov twice after raw_probe_proto_opt")
Signed-off-by: Mohamed Ghannam <simo.ghannam@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/raw.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 9879b73..59d8770 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -502,11 +502,16 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	int err;
 	struct ip_options_data opt_copy;
 	struct raw_frag_vec rfv;
+	int hdrincl;
 
 	err = -EMSGSIZE;
 	if (len > 0xFFFF)
 		goto out;
 
+	/* hdrincl should be READ_ONCE(inet->hdrincl)
+	 * but READ_ONCE() doesn't work with bit fields
+	 */
+	hdrincl = inet->hdrincl;
 	/*
 	 *	Check the flags.
 	 */
@@ -582,7 +587,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		/* Linux does not mangle headers on raw sockets,
 		 * so that IP options + IP_HDRINCL is non-sense.
 		 */
-		if (inet->hdrincl)
+		if (hdrincl)
 			goto done;
 		if (ipc.opt->opt.srr) {
 			if (!daddr)
@@ -604,12 +609,12 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos,
 			   RT_SCOPE_UNIVERSE,
-			   inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
+			   hdrincl ? IPPROTO_RAW : sk->sk_protocol,
 			   inet_sk_flowi_flags(sk) |
-			    (inet->hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
+			    (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
 			   daddr, saddr, 0, 0);
 
-	if (!inet->hdrincl) {
+	if (!hdrincl) {
 		rfv.msg = msg;
 		rfv.hlen = 0;
 
@@ -634,7 +639,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		goto do_confirm;
 back_from_confirm:
 
-	if (inet->hdrincl)
+	if (hdrincl)
 		err = raw_send_hdrinc(sk, &fl4, msg, len,
 				      &rt, msg->msg_flags, &ipc.sockc);
 
-- 
2.9.5


From ece99c49e7241f9392007894b9b9a288c45c9a76 Mon Sep 17 00:00:00 2001
From: Tobias Jordan <Tobias.Jordan@elektrobit.com>
Date: Wed, 6 Dec 2017 15:23:23 +0100
Subject: [PATCH 14/33] net: mvmdio: disable/unprepare clocks in EPROBE_DEFER
 case

[ Upstream commit 589bf32f09852041fbd3b7ce1a9e703f95c230ba ]

add appropriate calls to clk_disable_unprepare() by jumping to out_mdio
in case orion_mdio_probe() returns -EPROBE_DEFER.

Found by Linux Driver Verification project (linuxtesting.org).

Fixes: 3d604da1e954 ("net: mvmdio: get and enable optional clock")
Signed-off-by: Tobias Jordan <Tobias.Jordan@elektrobit.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvmdio.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c
index a0d1b08..7aeb7fe 100644
--- a/drivers/net/ethernet/marvell/mvmdio.c
+++ b/drivers/net/ethernet/marvell/mvmdio.c
@@ -232,7 +232,8 @@ static int orion_mdio_probe(struct platform_device *pdev)
 			dev->regs + MVMDIO_ERR_INT_MASK);
 
 	} else if (dev->err_interrupt == -EPROBE_DEFER) {
-		return -EPROBE_DEFER;
+		ret = -EPROBE_DEFER;
+		goto out_mdio;
 	}
 
 	mutex_init(&dev->lock);
-- 
2.9.5


From 7baed18c08fc1d5cb10696606c341aed812ac10a Mon Sep 17 00:00:00 2001
From: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Date: Fri, 22 Dec 2017 10:15:20 -0800
Subject: [PATCH 15/33] sctp: Replace use of sockets_allocated with specified
 macro.

[ Upstream commit 8cb38a602478e9f806571f6920b0a3298aabf042 ]

The patch(180d8cd942ce) replaces all uses of struct sock fields'
memory_pressure, memory_allocated, sockets_allocated, and sysctl_mem
to accessor macros. But the sockets_allocated field of sctp sock is
not replaced at all. Then replace it now for unifying the code.

Fixes: 180d8cd942ce ("foundations of per-cgroup memory pressure controlling.")
Cc: Glauber Costa <glommer@parallels.com>
Signed-off-by: Tonghao Zhang <zhangtonghao@didichuxing.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index c2ab864..7181ce6 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4246,7 +4246,7 @@ static int sctp_init_sock(struct sock *sk)
 	SCTP_DBG_OBJCNT_INC(sock);
 
 	local_bh_disable();
-	percpu_counter_inc(&sctp_sockets_allocated);
+	sk_sockets_allocated_inc(sk);
 	sock_prot_inuse_add(net, sk->sk_prot, 1);
 
 	/* Nothing can fail after this block, otherwise
@@ -4290,7 +4290,7 @@ static void sctp_destroy_sock(struct sock *sk)
 	}
 	sctp_endpoint_free(sp->ep);
 	local_bh_disable();
-	percpu_counter_dec(&sctp_sockets_allocated);
+	sk_sockets_allocated_dec(sk);
 	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
 	local_bh_enable();
 }
-- 
2.9.5


From 3e6665dc214ded92c70822233a554d14c74bc2cd Mon Sep 17 00:00:00 2001
From: "Nikita V. Shirokov" <tehnerd@fb.com>
Date: Wed, 6 Dec 2017 17:15:43 -0800
Subject: [PATCH 16/33] adding missing rcu_read_unlock in ipxip6_rcv

[ Upstream commit 74c4b656c3d92ec4c824ea1a4afd726b7b6568c8 ]

commit 8d79266bc48c ("ip6_tunnel: add collect_md mode to IPv6 tunnels")
introduced new exit point in  ipxip6_rcv. however rcu_read_unlock is
missing there. this diff is fixing this

v1->v2:
 instead of doing rcu_read_unlock in place, we are going to "drop"
 section (to prevent skb leakage)

Fixes: 8d79266bc48c ("ip6_tunnel: add collect_md mode to IPv6 tunnels")
Signed-off-by: Nikita V. Shirokov <tehnerd@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 12b2fd5..11d22d6 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -911,7 +911,7 @@ static int ipxip6_rcv(struct sk_buff *skb, u8 ipproto,
 		if (t->parms.collect_md) {
 			tun_dst = ipv6_tun_rx_dst(skb, 0, 0, 0);
 			if (!tun_dst)
-				return 0;
+				goto drop;
 		}
 		ret = __ip6_tnl_rcv(t, skb, tpi, tun_dst, dscp_ecn_decapsulate,
 				    log_ecn_error);
-- 
2.9.5


From 5a66ef92068ea4c2f18ee267e9c43db39a22b786 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 20 Dec 2017 19:34:19 +0200
Subject: [PATCH 17/33] ipv4: Fix use-after-free when flushing FIB tables

[ Upstream commit b4681c2829e24943aadd1a7bb3a30d41d0a20050 ]

Since commit 0ddcf43d5d4a ("ipv4: FIB Local/MAIN table collapse") the
local table uses the same trie allocated for the main table when custom
rules are not in use.

When a net namespace is dismantled, the main table is flushed and freed
(via an RCU callback) before the local table. In case the callback is
invoked before the local table is iterated, a use-after-free can occur.

Fix this by iterating over the FIB tables in reverse order, so that the
main table is always freed after the local table.

v3: Reworded comment according to Alex's suggestion.
v2: Add a comment to make the fix more explicit per Dave's and Alex's
feedback.

Fixes: 0ddcf43d5d4a ("ipv4: FIB Local/MAIN table collapse")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Acked-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_frontend.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 968d8e1..ffae472 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1253,14 +1253,19 @@ static int __net_init ip_fib_net_init(struct net *net)
 
 static void ip_fib_net_exit(struct net *net)
 {
-	unsigned int i;
+	int i;
 
 	rtnl_lock();
 #ifdef CONFIG_IP_MULTIPLE_TABLES
 	RCU_INIT_POINTER(net->ipv4.fib_main, NULL);
 	RCU_INIT_POINTER(net->ipv4.fib_default, NULL);
 #endif
-	for (i = 0; i < FIB_TABLE_HASHSZ; i++) {
+	/* Destroy the tables in reverse order to guarantee that the
+	 * local table, ID 255, is destroyed before the main table, ID
+	 * 254. This is necessary as the local table may contain
+	 * references to data contained in the main table.
+	 */
+	for (i = FIB_TABLE_HASHSZ - 1; i >= 0; i--) {
 		struct hlist_head *head = &net->ipv4.fib_table_hash[i];
 		struct hlist_node *tmp;
 		struct fib_table *tb;
-- 
2.9.5


From 574df788536567e3acbc4c675fbc3389ca61503d Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Mon, 18 Dec 2017 17:35:09 +0200
Subject: [PATCH 18/33] net: bridge: fix early call to br_stp_change_bridge_id
 and plug newlink leaks

[ Upstream commit 84aeb437ab98a2bce3d4b2111c79723aedfceb33 ]

The early call to br_stp_change_bridge_id in bridge's newlink can cause
a memory leak if an error occurs during the newlink because the fdb
entries are not cleaned up if a different lladdr was specified, also
another minor issue is that it generates fdb notifications with
ifindex = 0. Another unrelated memory leak is the bridge sysfs entries
which get added on NETDEV_REGISTER event, but are not cleaned up in the
newlink error path. To remove this special case the call to
br_stp_change_bridge_id is done after netdev register and we cleanup the
bridge on changelink error via br_dev_delete to plug all leaks.

This patch makes netlink bridge destruction on newlink error the same as
dellink and ioctl del which is necessary since at that point we have a
fully initialized bridge device.

To reproduce the issue:
$ ip l add br0 address 00:11:22:33:44:55 type bridge group_fwd_mask 1
RTNETLINK answers: Invalid argument

$ rmmod bridge
[ 1822.142525] =============================================================================
[ 1822.143640] BUG bridge_fdb_cache (Tainted: G           O    ): Objects remaining in bridge_fdb_cache on __kmem_cache_shutdown()
[ 1822.144821] -----------------------------------------------------------------------------

[ 1822.145990] Disabling lock debugging due to kernel taint
[ 1822.146732] INFO: Slab 0x0000000092a844b2 objects=32 used=2 fp=0x00000000fef011b0 flags=0x1ffff8000000100
[ 1822.147700] CPU: 2 PID: 13584 Comm: rmmod Tainted: G    B      O     4.15.0-rc2+ #87
[ 1822.148578] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.7.5-20140531_083030-gandalf 04/01/2014
[ 1822.150008] Call Trace:
[ 1822.150510]  dump_stack+0x78/0xa9
[ 1822.151156]  slab_err+0xb1/0xd3
[ 1822.151834]  ? __kmalloc+0x1bb/0x1ce
[ 1822.152546]  __kmem_cache_shutdown+0x151/0x28b
[ 1822.153395]  shutdown_cache+0x13/0x144
[ 1822.154126]  kmem_cache_destroy+0x1c0/0x1fb
[ 1822.154669]  SyS_delete_module+0x194/0x244
[ 1822.155199]  ? trace_hardirqs_on_thunk+0x1a/0x1c
[ 1822.155773]  entry_SYSCALL_64_fastpath+0x23/0x9a
[ 1822.156343] RIP: 0033:0x7f929bd38b17
[ 1822.156859] RSP: 002b:00007ffd160e9a98 EFLAGS: 00000202 ORIG_RAX: 00000000000000b0
[ 1822.157728] RAX: ffffffffffffffda RBX: 00005578316ba090 RCX: 00007f929bd38b17
[ 1822.158422] RDX: 00007f929bd9ec60 RSI: 0000000000000800 RDI: 00005578316ba0f0
[ 1822.159114] RBP: 0000000000000003 R08: 00007f929bff5f20 R09: 00007ffd160e8a11
[ 1822.159808] R10: 00007ffd160e9860 R11: 0000000000000202 R12: 00007ffd160e8a80
[ 1822.160513] R13: 0000000000000000 R14: 0000000000000000 R15: 00005578316ba090
[ 1822.161278] INFO: Object 0x000000007645de29 @offset=0
[ 1822.161666] INFO: Object 0x00000000d5df2ab5 @offset=128

Fixes: 30313a3d5794 ("bridge: Handle IFLA_ADDRESS correctly when creating bridge device")
Fixes: 5b8d5429daa0 ("bridge: netlink: register netdevice before executing changelink")
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_netlink.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 5d4006e..4f83122 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -1092,19 +1092,20 @@ static int br_dev_newlink(struct net *src_net, struct net_device *dev,
 	struct net_bridge *br = netdev_priv(dev);
 	int err;
 
+	err = register_netdevice(dev);
+	if (err)
+		return err;
+
 	if (tb[IFLA_ADDRESS]) {
 		spin_lock_bh(&br->lock);
 		br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS]));
 		spin_unlock_bh(&br->lock);
 	}
 
-	err = register_netdevice(dev);
-	if (err)
-		return err;
-
 	err = br_changelink(dev, tb, data);
 	if (err)
-		unregister_netdevice(dev);
+		br_dev_delete(dev, NULL);
+
 	return err;
 }
 
-- 
2.9.5


From 1c6f7fb6a0dc50e4051c68e6b9b566206f99046d Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sun, 30 Jul 2017 19:36:05 +0200
Subject: [PATCH 19/33] net: fec: Allow reception of frames bigger than 1522
 bytes

[ Upstream commit fbbeefdd21049fcf9437c809da3828b210577f36 ]

The FEC Receive Control Register has a 14 bit field indicating the
longest frame that may be received. It is being set to 1522. Frames
longer than this are discarded, but counted as being in error.

When using DSA, frames from the switch has an additional header,
either 4 or 8 bytes if a Marvell switch is used. Thus a full MTU frame
of 1522 bytes received by the switch on a port becomes 1530 bytes when
passed to the host via the FEC interface.

Change the maximum receive size to 2048 - 64, where 64 is the maximum
rx_alignment applied on the receive buffer for AVB capable FEC
cores. Use this value also for the maximum receive buffer size. The
driver is already allocating a receive SKB of 2048 bytes, so this
change should not have any significant effects.

Tested on imx51, imx6, vf610.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_main.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 60f6866..9170918 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -172,10 +172,12 @@ MODULE_PARM_DESC(macaddr, "FEC Ethernet MAC address");
 #endif /* CONFIG_M5272 */
 
 /* The FEC stores dest/src/type/vlan, data, and checksum for receive packets.
+ *
+ * 2048 byte skbufs are allocated. However, alignment requirements
+ * varies between FEC variants. Worst case is 64, so round down by 64.
  */
-#define PKT_MAXBUF_SIZE		1522
+#define PKT_MAXBUF_SIZE		(round_down(2048 - 64, 64))
 #define PKT_MINBUF_SIZE		64
-#define PKT_MAXBLR_SIZE		1536
 
 /* FEC receive acceleration */
 #define FEC_RACC_IPDIS		(1 << 1)
@@ -853,7 +855,7 @@ static void fec_enet_enable_ring(struct net_device *ndev)
 	for (i = 0; i < fep->num_rx_queues; i++) {
 		rxq = fep->rx_queue[i];
 		writel(rxq->bd.dma, fep->hwp + FEC_R_DES_START(i));
-		writel(PKT_MAXBLR_SIZE, fep->hwp + FEC_R_BUFF_SIZE(i));
+		writel(PKT_MAXBUF_SIZE, fep->hwp + FEC_R_BUFF_SIZE(i));
 
 		/* enable DMA1/2 */
 		if (i)
-- 
2.9.5


From bb09c733715749a050026c4481a004f8c20c2631 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Tue, 19 Dec 2017 11:27:56 -0600
Subject: [PATCH 20/33] net: Fix double free and memory corruption in
 get_net_ns_by_id()

[ Upstream commit 21b5944350052d2583e82dd59b19a9ba94a007f0 ]

(I can trivially verify that that idr_remove in cleanup_net happens
 after the network namespace count has dropped to zero --EWB)

Function get_net_ns_by_id() does not check for net::count
after it has found a peer in netns_ids idr.

It may dereference a peer, after its count has already been
finaly decremented. This leads to double free and memory
corruption:

put_net(peer)                                   rtnl_lock()
atomic_dec_and_test(&peer->count) [count=0]     ...
__put_net(peer)                                 get_net_ns_by_id(net, id)
  spin_lock(&cleanup_list_lock)
  list_add(&net->cleanup_list, &cleanup_list)
  spin_unlock(&cleanup_list_lock)
queue_work()                                      peer = idr_find(&net->netns_ids, id)
  |                                               get_net(peer) [count=1]
  |                                               ...
  |                                               (use after final put)
  v                                               ...
  cleanup_net()                                   ...
    spin_lock(&cleanup_list_lock)                 ...
    list_replace_init(&cleanup_list, ..)          ...
    spin_unlock(&cleanup_list_lock)               ...
    ...                                           ...
    ...                                           put_net(peer)
    ...                                             atomic_dec_and_test(&peer->count) [count=0]
    ...                                               spin_lock(&cleanup_list_lock)
    ...                                               list_add(&net->cleanup_list, &cleanup_list)
    ...                                               spin_unlock(&cleanup_list_lock)
    ...                                             queue_work()
    ...                                           rtnl_unlock()
    rtnl_lock()                                   ...
    for_each_net(tmp) {                           ...
      id = __peernet2id(tmp, peer)                ...
      spin_lock_irq(&tmp->nsid_lock)              ...
      idr_remove(&tmp->netns_ids, id)             ...
      ...                                         ...
      net_drop_ns()                               ...
	net_free(peer)                            ...
    }                                             ...
  |
  v
  cleanup_net()
    ...
    (Second free of peer)

Also, put_net() on the right cpu may reorder with left's cpu
list_replace_init(&cleanup_list, ..), and then cleanup_list
will be corrupted.

Since cleanup_net() is executed in worker thread, while
put_net(peer) can happen everywhere, there should be
enough time for concurrent get_net_ns_by_id() to pick
the peer up, and the race does not seem to be unlikely.
The patch fixes the problem in standard way.

(Also, there is possible problem in peernet2id_alloc(), which requires
check for net::count under nsid_lock and maybe_get_net(peer), but
in current stable kernel it's used under rtnl_lock() and it has to be
safe. Openswitch begun to use peernet2id_alloc(), and possibly it should
be fixed too. While this is not in stable kernel yet, so I'll send
a separate message to netdev@ later).

Cc: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Fixes: 0c7aecd4bde4 "netns: add rtnl cmd to add and get peer netns ids"
Reviewed-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
Reviewed-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/net_namespace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 7001da9..b7efe2f 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -263,7 +263,7 @@ struct net *get_net_ns_by_id(struct net *net, int id)
 	spin_lock_irqsave(&net->nsid_lock, flags);
 	peer = idr_find(&net->netns_ids, id);
 	if (peer)
-		get_net(peer);
+		peer = maybe_get_net(peer);
 	spin_unlock_irqrestore(&net->nsid_lock, flags);
 	rcu_read_unlock();
 
-- 
2.9.5


From 6f5c67c6d3e0fefd2ceb1c0a9e9f030b724b2e50 Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Wed, 20 Dec 2017 18:45:10 -0600
Subject: [PATCH 21/33] net: phy: micrel: ksz9031: reconfigure autoneg after
 phy autoneg workaround

[ Upstream commit c1a8d0a3accf64a014d605e6806ce05d1c17adf1 ]

Under some circumstances driver will perform PHY reset in
ksz9031_read_status() to fix autoneg failure case (idle error count =
0xFF). When this happens ksz9031 will not detect link status change any
more when connecting to Netgear 1G switch (link can be recovered sometimes by
restarting netdevice "ifconfig down up"). Reproduced with TI am572x board
equipped with ksz9031 PHY while connecting to Netgear 1G switch.

Fix the issue by reconfiguring autonegotiation after PHY reset in
ksz9031_read_status().

Fixes: d2fd719bcb0e ("net/phy: micrel: Add workaround for bad autoneg")
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/micrel.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index fbf5945..2032a6d 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -624,6 +624,7 @@ static int ksz9031_read_status(struct phy_device *phydev)
 		phydev->link = 0;
 		if (phydev->drv->config_intr && phy_interrupt_is_valid(phydev))
 			phydev->drv->config_intr(phydev);
+		return genphy_config_aneg(phydev);
 	}
 
 	return 0;
-- 
2.9.5


From b8ddfc5de595a34789ebc4878c2906e4b8346438 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 13 Dec 2017 14:41:06 -0500
Subject: [PATCH 22/33] sock: free skb in skb_complete_tx_timestamp on error

[ Upstream commit 35b99dffc3f710cafceee6c8c6ac6a98eb2cb4bf ]

skb_complete_tx_timestamp must ingest the skb it is passed. Call
kfree_skb if the skb cannot be enqueued.

Fixes: b245be1f4db1 ("net-timestamp: no-payload only sysctl")
Fixes: 9ac25fc06375 ("net: fix socket refcounting in skb_complete_tx_timestamp()")
Reported-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index aec5605..a645155 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3823,7 +3823,7 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
 	struct sock *sk = skb->sk;
 
 	if (!skb_may_tx_timestamp(sk, false))
-		return;
+		goto err;
 
 	/* Take a reference to prevent skb_orphan() from freeing the socket,
 	 * but only if the socket refcount is not zero.
@@ -3832,7 +3832,11 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
 		*skb_hwtstamps(skb) = *hwtstamps;
 		__skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND);
 		sock_put(sk);
+		return;
 	}
+
+err:
+	kfree_skb(skb);
 }
 EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp);
 
-- 
2.9.5


From 130e6feffc9a69de53e607214387981ae42474f7 Mon Sep 17 00:00:00 2001
From: Yousuk Seung <ysseung@google.com>
Date: Thu, 7 Dec 2017 13:41:34 -0800
Subject: [PATCH 23/33] tcp: invalidate rate samples during SACK reneging

[ Upstream commit d4761754b4fb2ef8d9a1e9d121c4bec84e1fe292 ]

Mark tcp_sock during a SACK reneging event and invalidate rate samples
while marked. Such rate samples may overestimate bw by including packets
that were SACKed before reneging.

< ack 6001 win 10000 sack 7001:38001
< ack 7001 win 0 sack 8001:38001 // Reneg detected
> seq 7001:8001 // RTO, SACK cleared.
< ack 38001 win 10000

In above example the rate sample taken after the last ack will count
7001-38001 as delivered while the actual delivery rate likely could
be much lower i.e. 7001-8001.

This patch adds a new field tcp_sock.sack_reneg and marks it when we
declare SACK reneging and entering TCP_CA_Loss, and unmarks it after
the last rate sample was taken before moving back to TCP_CA_Open. This
patch also invalidates rate samples taken while tcp_sock.is_sack_reneg
is set.

Fixes: b9f64820fb22 ("tcp: track data delivery rate for a TCP connection")
Signed-off-by: Yousuk Seung <ysseung@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Priyaranjan Jha <priyarjha@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h  |  3 ++-
 include/net/tcp.h    |  2 +-
 net/ipv4/tcp.c       |  1 +
 net/ipv4/tcp_input.c | 10 ++++++++--
 net/ipv4/tcp_rate.c  | 10 +++++++---
 5 files changed, 19 insertions(+), 7 deletions(-)

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 647532b..f50b717c 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -219,7 +219,8 @@ struct tcp_sock {
 	} rack;
 	u16	advmss;		/* Advertised MSS			*/
 	u8	rate_app_limited:1,  /* rate_{delivered,interval_us} limited? */
-		unused:7;
+		is_sack_reneg:1,    /* in recovery from loss with SACK reneg? */
+		unused:6;
 	u8	nonagle     : 4,/* Disable Nagle algorithm?             */
 		thin_lto    : 1,/* Use linear timeouts for thin streams */
 		thin_dupack : 1,/* Fast retransmit on first dupack      */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index fba4fc4..caf35e0 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1001,7 +1001,7 @@ void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb);
 void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb,
 			    struct rate_sample *rs);
 void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost,
-		  struct skb_mstamp *now, struct rate_sample *rs);
+		  bool is_sack_reneg, struct skb_mstamp *now, struct rate_sample *rs);
 void tcp_rate_check_app_limited(struct sock *sk);
 
 /* These functions determine how the current flow behaves in respect of SACK
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index dd33c78..05d2bde 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2297,6 +2297,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tp->snd_cwnd_cnt = 0;
 	tp->window_clamp = 0;
 	tcp_set_ca_state(sk, TCP_CA_Open);
+	tp->is_sack_reneg = 0;
 	tcp_clear_retrans(tp);
 	inet_csk_delack_init(sk);
 	/* Initialize rcv_mss to TCP_MIN_MSS to avoid division by 0
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 05255a2..2f107e4 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1966,6 +1966,8 @@ void tcp_enter_loss(struct sock *sk)
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSACKRENEGING);
 		tp->sacked_out = 0;
 		tp->fackets_out = 0;
+		/* Mark SACK reneging until we recover from this loss event. */
+		tp->is_sack_reneg = 1;
 	}
 	tcp_clear_all_retrans_hints(tp);
 
@@ -2463,6 +2465,7 @@ static bool tcp_try_undo_recovery(struct sock *sk)
 		return true;
 	}
 	tcp_set_ca_state(sk, TCP_CA_Open);
+	tp->is_sack_reneg = 0;
 	return false;
 }
 
@@ -2494,8 +2497,10 @@ static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo)
 			NET_INC_STATS(sock_net(sk),
 					LINUX_MIB_TCPSPURIOUSRTOS);
 		inet_csk(sk)->icsk_retransmits = 0;
-		if (frto_undo || tcp_is_sack(tp))
+		if (frto_undo || tcp_is_sack(tp)) {
 			tcp_set_ca_state(sk, TCP_CA_Open);
+			tp->is_sack_reneg = 0;
+		}
 		return true;
 	}
 	return false;
@@ -3589,6 +3594,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	struct tcp_sacktag_state sack_state;
 	struct rate_sample rs = { .prior_delivered = 0 };
 	u32 prior_snd_una = tp->snd_una;
+	bool is_sack_reneg = tp->is_sack_reneg;
 	u32 ack_seq = TCP_SKB_CB(skb)->seq;
 	u32 ack = TCP_SKB_CB(skb)->ack_seq;
 	bool is_dupack = false;
@@ -3711,7 +3717,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 		tcp_schedule_loss_probe(sk);
 	delivered = tp->delivered - delivered;	/* freshly ACKed or SACKed */
 	lost = tp->lost - lost;			/* freshly marked lost */
-	tcp_rate_gen(sk, delivered, lost, &now, &rs);
+	tcp_rate_gen(sk, delivered, lost, is_sack_reneg, &now, &rs);
 	tcp_cong_control(sk, ack, delivered, flag, &rs);
 	tcp_xmit_recovery(sk, rexmit);
 	return 1;
diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c
index 9be1581..18309f5 100644
--- a/net/ipv4/tcp_rate.c
+++ b/net/ipv4/tcp_rate.c
@@ -106,7 +106,7 @@ void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb,
 
 /* Update the connection delivery information and generate a rate sample. */
 void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost,
-		  struct skb_mstamp *now, struct rate_sample *rs)
+		  bool is_sack_reneg, struct skb_mstamp *now, struct rate_sample *rs)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	u32 snd_us, ack_us;
@@ -124,8 +124,12 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost,
 
 	rs->acked_sacked = delivered;	/* freshly ACKed or SACKed */
 	rs->losses = lost;		/* freshly marked lost */
-	/* Return an invalid sample if no timing information is available. */
-	if (!rs->prior_mstamp.v64) {
+	/* Return an invalid sample if no timing information is available or
+	 * in recovery from loss with SACK reneging. Rate samples taken during
+	 * a SACK reneging event may overestimate bw by including packets that
+	 * were SACKed before the reneg.
+	 */
+	if (!rs->prior_mstamp.v64 || is_sack_reneg) {
 		rs->delivered = -1;
 		rs->interval_us = -1;
 		return;
-- 
2.9.5


From 939ebf4b73d5097cfc3386c864fdbd076666d5bd Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Mon, 13 Nov 2017 10:11:27 +0200
Subject: [PATCH 24/33] net/mlx5: Fix rate limit packet pacing naming and
 struct

[ Upstream commit 37e92a9d4fe38dc3e7308913575983a6a088c8d4 ]

In mlx5_ifc, struct size was not complete, and thus driver was sending
garbage after the last defined field. Fixed it by adding reserved field
to complete the struct size.

In addition, rename all set_rate_limit to set_pp_rate_limit to be
compliant with the Firmware <-> Driver definition.

Fixes: 7486216b3a0b ("{net,IB}/mlx5: mlx5_ifc updates")
Fixes: 1466cc5b23d1 ("net/mlx5: Rate limit tables support")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c |  4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/rl.c  | 22 +++++++++++-----------
 include/linux/mlx5/mlx5_ifc.h                 |  8 +++++---
 3 files changed, 18 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index f7fabec..4c3f1cb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -367,7 +367,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_QUERY_VPORT_COUNTER:
 	case MLX5_CMD_OP_ALLOC_Q_COUNTER:
 	case MLX5_CMD_OP_QUERY_Q_COUNTER:
-	case MLX5_CMD_OP_SET_RATE_LIMIT:
+	case MLX5_CMD_OP_SET_PP_RATE_LIMIT:
 	case MLX5_CMD_OP_QUERY_RATE_LIMIT:
 	case MLX5_CMD_OP_ALLOC_PD:
 	case MLX5_CMD_OP_ALLOC_UAR:
@@ -502,7 +502,7 @@ const char *mlx5_command_str(int command)
 	MLX5_COMMAND_STR_CASE(ALLOC_Q_COUNTER);
 	MLX5_COMMAND_STR_CASE(DEALLOC_Q_COUNTER);
 	MLX5_COMMAND_STR_CASE(QUERY_Q_COUNTER);
-	MLX5_COMMAND_STR_CASE(SET_RATE_LIMIT);
+	MLX5_COMMAND_STR_CASE(SET_PP_RATE_LIMIT);
 	MLX5_COMMAND_STR_CASE(QUERY_RATE_LIMIT);
 	MLX5_COMMAND_STR_CASE(ALLOC_PD);
 	MLX5_COMMAND_STR_CASE(DEALLOC_PD);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rl.c b/drivers/net/ethernet/mellanox/mlx5/core/rl.c
index 104902a..2be9ec5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/rl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rl.c
@@ -60,16 +60,16 @@ static struct mlx5_rl_entry *find_rl_entry(struct mlx5_rl_table *table,
 	return ret_entry;
 }
 
-static int mlx5_set_rate_limit_cmd(struct mlx5_core_dev *dev,
+static int mlx5_set_pp_rate_limit_cmd(struct mlx5_core_dev *dev,
 				   u32 rate, u16 index)
 {
-	u32 in[MLX5_ST_SZ_DW(set_rate_limit_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(set_rate_limit_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(set_pp_rate_limit_in)]   = {0};
+	u32 out[MLX5_ST_SZ_DW(set_pp_rate_limit_out)] = {0};
 
-	MLX5_SET(set_rate_limit_in, in, opcode,
-		 MLX5_CMD_OP_SET_RATE_LIMIT);
-	MLX5_SET(set_rate_limit_in, in, rate_limit_index, index);
-	MLX5_SET(set_rate_limit_in, in, rate_limit, rate);
+	MLX5_SET(set_pp_rate_limit_in, in, opcode,
+		 MLX5_CMD_OP_SET_PP_RATE_LIMIT);
+	MLX5_SET(set_pp_rate_limit_in, in, rate_limit_index, index);
+	MLX5_SET(set_pp_rate_limit_in, in, rate_limit, rate);
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 }
 
@@ -108,7 +108,7 @@ int mlx5_rl_add_rate(struct mlx5_core_dev *dev, u32 rate, u16 *index)
 		entry->refcount++;
 	} else {
 		/* new rate limit */
-		err = mlx5_set_rate_limit_cmd(dev, rate, entry->index);
+		err = mlx5_set_pp_rate_limit_cmd(dev, rate, entry->index);
 		if (err) {
 			mlx5_core_err(dev, "Failed configuring rate: %u (%d)\n",
 				      rate, err);
@@ -144,7 +144,7 @@ void mlx5_rl_remove_rate(struct mlx5_core_dev *dev, u32 rate)
 	entry->refcount--;
 	if (!entry->refcount) {
 		/* need to remove rate */
-		mlx5_set_rate_limit_cmd(dev, 0, entry->index);
+		mlx5_set_pp_rate_limit_cmd(dev, 0, entry->index);
 		entry->rate = 0;
 	}
 
@@ -197,8 +197,8 @@ void mlx5_cleanup_rl_table(struct mlx5_core_dev *dev)
 	/* Clear all configured rates */
 	for (i = 0; i < table->max_size; i++)
 		if (table->rl_entry[i].rate)
-			mlx5_set_rate_limit_cmd(dev, 0,
-						table->rl_entry[i].index);
+			mlx5_set_pp_rate_limit_cmd(dev, 0,
+						   table->rl_entry[i].index);
 
 	kfree(dev->priv.rl_table.rl_entry);
 }
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 6045d4d..25ed105 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -143,7 +143,7 @@ enum {
 	MLX5_CMD_OP_ALLOC_Q_COUNTER               = 0x771,
 	MLX5_CMD_OP_DEALLOC_Q_COUNTER             = 0x772,
 	MLX5_CMD_OP_QUERY_Q_COUNTER               = 0x773,
-	MLX5_CMD_OP_SET_RATE_LIMIT                = 0x780,
+	MLX5_CMD_OP_SET_PP_RATE_LIMIT             = 0x780,
 	MLX5_CMD_OP_QUERY_RATE_LIMIT              = 0x781,
 	MLX5_CMD_OP_ALLOC_PD                      = 0x800,
 	MLX5_CMD_OP_DEALLOC_PD                    = 0x801,
@@ -6689,7 +6689,7 @@ struct mlx5_ifc_add_vxlan_udp_dport_in_bits {
 	u8         vxlan_udp_port[0x10];
 };
 
-struct mlx5_ifc_set_rate_limit_out_bits {
+struct mlx5_ifc_set_pp_rate_limit_out_bits {
 	u8         status[0x8];
 	u8         reserved_at_8[0x18];
 
@@ -6698,7 +6698,7 @@ struct mlx5_ifc_set_rate_limit_out_bits {
 	u8         reserved_at_40[0x40];
 };
 
-struct mlx5_ifc_set_rate_limit_in_bits {
+struct mlx5_ifc_set_pp_rate_limit_in_bits {
 	u8         opcode[0x10];
 	u8         reserved_at_10[0x10];
 
@@ -6711,6 +6711,8 @@ struct mlx5_ifc_set_rate_limit_in_bits {
 	u8         reserved_at_60[0x20];
 
 	u8         rate_limit[0x20];
+
+	u8         reserved_at_a0[0x160];
 };
 
 struct mlx5_ifc_access_register_out_bits {
-- 
2.9.5


From 9a4239e5ae908b31bea732907ecfaf61ab37ee0b Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Tue, 21 Nov 2017 17:49:36 +0200
Subject: [PATCH 25/33] net/mlx5e: Fix features check of IPv6 traffic

[ Upstream commit 2989ad1ec03021ee6d2193c35414f1d970a243de ]

The assumption that the next header field contains the transport
protocol is wrong for IPv6 packets with extension headers.
Instead, we should look the inner-most next header field in the buffer.
This will fix TSO offload for tunnels over IPv6 with extension headers.

Performance testing: 19.25x improvement, cool!
Measuring bandwidth of 16 threads TCP traffic over IPv6 GRE tap.
CPU: Intel(R) Xeon(R) CPU E5-2660 v2 @ 2.20GHz
NIC: Mellanox Technologies MT28800 Family [ConnectX-5 Ex]
TSO: Enabled
Before: 4,926.24  Mbps
Now   : 94,827.91 Mbps

Fixes: b3f63c3d5e2c ("net/mlx5e: Add netdev support for VXLAN tunneling")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 9d37229..38981db 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3038,6 +3038,7 @@ static netdev_features_t mlx5e_vxlan_features_check(struct mlx5e_priv *priv,
 						    struct sk_buff *skb,
 						    netdev_features_t features)
 {
+	unsigned int offset = 0;
 	struct udphdr *udph;
 	u16 proto;
 	u16 port = 0;
@@ -3047,7 +3048,7 @@ static netdev_features_t mlx5e_vxlan_features_check(struct mlx5e_priv *priv,
 		proto = ip_hdr(skb)->protocol;
 		break;
 	case htons(ETH_P_IPV6):
-		proto = ipv6_hdr(skb)->nexthdr;
+		proto = ipv6_find_hdr(skb, &offset, -1, NULL, NULL);
 		break;
 	default:
 		goto out;
-- 
2.9.5


From c2bfa625babd89ec359b7a9d98192706dae523a8 Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Thu, 23 Nov 2017 13:52:28 +0200
Subject: [PATCH 26/33] net/mlx5e: Fix possible deadlock of VXLAN lock

[ Upstream commit 6323514116404cc651df1b7fffa1311ddf8ce647 ]

mlx5e_vxlan_lookup_port is called both from mlx5e_add_vxlan_port (user
context) and mlx5e_features_check (softirq), but the lock acquired does
not disable bottom half and might result in deadlock. Fix it by simply
replacing spin_lock() with spin_lock_bh().
While at it, replace all unnecessary spin_lock_irq() to spin_lock_bh().

lockdep's WARNING: inconsistent lock state
[  654.028136] inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage.
[  654.028229] swapper/5/0 [HC0[0]:SC1[9]:HE1:SE0] takes:
[  654.028321]  (&(&vxlan_db->lock)->rlock){+.?.}, at: [<ffffffffa06e7f0e>] mlx5e_vxlan_lookup_port+0x1e/0x50 [mlx5_core]
[  654.028528] {SOFTIRQ-ON-W} state was registered at:
[  654.028607]   _raw_spin_lock+0x3c/0x70
[  654.028689]   mlx5e_vxlan_lookup_port+0x1e/0x50 [mlx5_core]
[  654.028794]   mlx5e_vxlan_add_port+0x2e/0x120 [mlx5_core]
[  654.028878]   process_one_work+0x1e9/0x640
[  654.028942]   worker_thread+0x4a/0x3f0
[  654.029002]   kthread+0x141/0x180
[  654.029056]   ret_from_fork+0x24/0x30
[  654.029114] irq event stamp: 579088
[  654.029174] hardirqs last  enabled at (579088): [<ffffffff818f475a>] ip6_finish_output2+0x49a/0x8c0
[  654.029309] hardirqs last disabled at (579087): [<ffffffff818f470e>] ip6_finish_output2+0x44e/0x8c0
[  654.029446] softirqs last  enabled at (579030): [<ffffffff810b3b3d>] irq_enter+0x6d/0x80
[  654.029567] softirqs last disabled at (579031): [<ffffffff810b3c05>] irq_exit+0xb5/0xc0
[  654.029684] other info that might help us debug this:
[  654.029781]  Possible unsafe locking scenario:

[  654.029868]        CPU0
[  654.029908]        ----
[  654.029947]   lock(&(&vxlan_db->lock)->rlock);
[  654.030045]   <Interrupt>
[  654.030090]     lock(&(&vxlan_db->lock)->rlock);
[  654.030162]
 *** DEADLOCK ***

Fixes: b3f63c3d5e2c ("net/mlx5e: Add netdev support for VXLAN tunneling")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/vxlan.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
index 07a9ba6..f823827 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
@@ -71,9 +71,9 @@ struct mlx5e_vxlan *mlx5e_vxlan_lookup_port(struct mlx5e_priv *priv, u16 port)
 	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
 	struct mlx5e_vxlan *vxlan;
 
-	spin_lock(&vxlan_db->lock);
+	spin_lock_bh(&vxlan_db->lock);
 	vxlan = radix_tree_lookup(&vxlan_db->tree, port);
-	spin_unlock(&vxlan_db->lock);
+	spin_unlock_bh(&vxlan_db->lock);
 
 	return vxlan;
 }
@@ -100,9 +100,9 @@ static void mlx5e_vxlan_add_port(struct work_struct *work)
 
 	vxlan->udp_port = port;
 
-	spin_lock_irq(&vxlan_db->lock);
+	spin_lock_bh(&vxlan_db->lock);
 	err = radix_tree_insert(&vxlan_db->tree, vxlan->udp_port, vxlan);
-	spin_unlock_irq(&vxlan_db->lock);
+	spin_unlock_bh(&vxlan_db->lock);
 	if (err)
 		goto err_free;
 
@@ -121,9 +121,9 @@ static void __mlx5e_vxlan_core_del_port(struct mlx5e_priv *priv, u16 port)
 	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
 	struct mlx5e_vxlan *vxlan;
 
-	spin_lock_irq(&vxlan_db->lock);
+	spin_lock_bh(&vxlan_db->lock);
 	vxlan = radix_tree_delete(&vxlan_db->tree, port);
-	spin_unlock_irq(&vxlan_db->lock);
+	spin_unlock_bh(&vxlan_db->lock);
 
 	if (!vxlan)
 		return;
@@ -171,12 +171,12 @@ void mlx5e_vxlan_cleanup(struct mlx5e_priv *priv)
 	struct mlx5e_vxlan *vxlan;
 	unsigned int port = 0;
 
-	spin_lock_irq(&vxlan_db->lock);
+	spin_lock_bh(&vxlan_db->lock);
 	while (radix_tree_gang_lookup(&vxlan_db->tree, (void **)&vxlan, port, 1)) {
 		port = vxlan->udp_port;
-		spin_unlock_irq(&vxlan_db->lock);
+		spin_unlock_bh(&vxlan_db->lock);
 		__mlx5e_vxlan_core_del_port(priv, (u16)port);
-		spin_lock_irq(&vxlan_db->lock);
+		spin_lock_bh(&vxlan_db->lock);
 	}
-	spin_unlock_irq(&vxlan_db->lock);
+	spin_unlock_bh(&vxlan_db->lock);
 }
-- 
2.9.5


From 0861924d669001921649a74b81dadee6feaa52fa Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Sun, 3 Dec 2017 13:58:50 +0200
Subject: [PATCH 27/33] net/mlx5e: Add refcount to VXLAN structure

[ Upstream commit 23f4cc2cd9ed92570647220aca60d0197d8c1fa9 ]

A refcount mechanism must be implemented in order to prevent unwanted
scenarios such as:
- Open an IPv4 VXLAN interface
- Open an IPv6 VXLAN interface (different socket)
- Remove one of the interfaces

With current implementation, the UDP port will be removed from our VXLAN
database and turn off the offloads for the other interface, which is
still active.
The reference count mechanism will only allow UDP port removals once all
consumers are gone.

Fixes: b3f63c3d5e2c ("net/mlx5e: Add netdev support for VXLAN tunneling")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/vxlan.c | 50 +++++++++++++------------
 drivers/net/ethernet/mellanox/mlx5/core/vxlan.h |  1 +
 2 files changed, 28 insertions(+), 23 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
index f823827..25f7823 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
@@ -88,8 +88,11 @@ static void mlx5e_vxlan_add_port(struct work_struct *work)
 	struct mlx5e_vxlan *vxlan;
 	int err;
 
-	if (mlx5e_vxlan_lookup_port(priv, port))
+	vxlan = mlx5e_vxlan_lookup_port(priv, port);
+	if (vxlan) {
+		atomic_inc(&vxlan->refcount);
 		goto free_work;
+	}
 
 	if (mlx5e_vxlan_core_add_port_cmd(priv->mdev, port))
 		goto free_work;
@@ -99,6 +102,7 @@ static void mlx5e_vxlan_add_port(struct work_struct *work)
 		goto err_delete_port;
 
 	vxlan->udp_port = port;
+	atomic_set(&vxlan->refcount, 1);
 
 	spin_lock_bh(&vxlan_db->lock);
 	err = radix_tree_insert(&vxlan_db->tree, vxlan->udp_port, vxlan);
@@ -116,32 +120,33 @@ static void mlx5e_vxlan_add_port(struct work_struct *work)
 	kfree(vxlan_work);
 }
 
-static void __mlx5e_vxlan_core_del_port(struct mlx5e_priv *priv, u16 port)
+static void mlx5e_vxlan_del_port(struct work_struct *work)
 {
+	struct mlx5e_vxlan_work *vxlan_work =
+		container_of(work, struct mlx5e_vxlan_work, work);
+	struct mlx5e_priv *priv         = vxlan_work->priv;
 	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
+	u16 port = vxlan_work->port;
 	struct mlx5e_vxlan *vxlan;
+	bool remove = false;
 
 	spin_lock_bh(&vxlan_db->lock);
-	vxlan = radix_tree_delete(&vxlan_db->tree, port);
-	spin_unlock_bh(&vxlan_db->lock);
-
+	vxlan = radix_tree_lookup(&vxlan_db->tree, port);
 	if (!vxlan)
-		return;
-
-	mlx5e_vxlan_core_del_port_cmd(priv->mdev, vxlan->udp_port);
-
-	kfree(vxlan);
-}
+		goto out_unlock;
 
-static void mlx5e_vxlan_del_port(struct work_struct *work)
-{
-	struct mlx5e_vxlan_work *vxlan_work =
-		container_of(work, struct mlx5e_vxlan_work, work);
-	struct mlx5e_priv *priv = vxlan_work->priv;
-	u16 port = vxlan_work->port;
+	if (atomic_dec_and_test(&vxlan->refcount)) {
+		radix_tree_delete(&vxlan_db->tree, port);
+		remove = true;
+	}
 
-	__mlx5e_vxlan_core_del_port(priv, port);
+out_unlock:
+	spin_unlock_bh(&vxlan_db->lock);
 
+	if (remove) {
+		mlx5e_vxlan_core_del_port_cmd(priv->mdev, port);
+		kfree(vxlan);
+	}
 	kfree(vxlan_work);
 }
 
@@ -171,12 +176,11 @@ void mlx5e_vxlan_cleanup(struct mlx5e_priv *priv)
 	struct mlx5e_vxlan *vxlan;
 	unsigned int port = 0;
 
-	spin_lock_bh(&vxlan_db->lock);
+	/* Lockless since we are the only radix-tree consumers, wq is disabled */
 	while (radix_tree_gang_lookup(&vxlan_db->tree, (void **)&vxlan, port, 1)) {
 		port = vxlan->udp_port;
-		spin_unlock_bh(&vxlan_db->lock);
-		__mlx5e_vxlan_core_del_port(priv, (u16)port);
-		spin_lock_bh(&vxlan_db->lock);
+		radix_tree_delete(&vxlan_db->tree, port);
+		mlx5e_vxlan_core_del_port_cmd(priv->mdev, port);
+		kfree(vxlan);
 	}
-	spin_unlock_bh(&vxlan_db->lock);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
index 5def12c..5ef6ae7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
@@ -36,6 +36,7 @@
 #include "en.h"
 
 struct mlx5e_vxlan {
+	atomic_t refcount;
 	u16 udp_port;
 };
 
-- 
2.9.5


From 3fbe211102f66d2fd367e43e524a6c00f5d50017 Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Mon, 4 Dec 2017 09:57:43 +0200
Subject: [PATCH 28/33] net/mlx5e: Prevent possible races in VXLAN control flow

[ Upstream commit 0c1cc8b2215f5122ca614b5adca60346018758c3 ]

When calling add/remove VXLAN port, a lock must be held in order to
prevent race scenarios when more than one add/remove happens at the
same time.
Fix by holding our state_lock (mutex) as done by all other parts of the
driver.
Note that the spinlock protecting the radix-tree is still needed in
order to synchronize radix-tree access from softirq context.

Fixes: b3f63c3d5e2c ("net/mlx5e: Add netdev support for VXLAN tunneling")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/vxlan.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
index 25f7823..2f74953 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
@@ -88,6 +88,7 @@ static void mlx5e_vxlan_add_port(struct work_struct *work)
 	struct mlx5e_vxlan *vxlan;
 	int err;
 
+	mutex_lock(&priv->state_lock);
 	vxlan = mlx5e_vxlan_lookup_port(priv, port);
 	if (vxlan) {
 		atomic_inc(&vxlan->refcount);
@@ -117,6 +118,7 @@ static void mlx5e_vxlan_add_port(struct work_struct *work)
 err_delete_port:
 	mlx5e_vxlan_core_del_port_cmd(priv->mdev, port);
 free_work:
+	mutex_unlock(&priv->state_lock);
 	kfree(vxlan_work);
 }
 
@@ -130,6 +132,7 @@ static void mlx5e_vxlan_del_port(struct work_struct *work)
 	struct mlx5e_vxlan *vxlan;
 	bool remove = false;
 
+	mutex_lock(&priv->state_lock);
 	spin_lock_bh(&vxlan_db->lock);
 	vxlan = radix_tree_lookup(&vxlan_db->tree, port);
 	if (!vxlan)
@@ -147,6 +150,7 @@ static void mlx5e_vxlan_del_port(struct work_struct *work)
 		mlx5e_vxlan_core_del_port_cmd(priv->mdev, port);
 		kfree(vxlan);
 	}
+	mutex_unlock(&priv->state_lock);
 	kfree(vxlan_work);
 }
 
-- 
2.9.5


From e573c8c323a26536de64da4ed294f05f29283cce Mon Sep 17 00:00:00 2001
From: Moni Shoua <monis@mellanox.com>
Date: Mon, 4 Dec 2017 08:59:25 +0200
Subject: [PATCH 29/33] net/mlx5: Fix error flow in CREATE_QP command

[ Upstream commit dbff26e44dc3ec4de6578733b054a0114652a764 ]

In error flow, when DESTROY_QP command should be executed, the wrong
mailbox was set with data, not the one that is written to hardware,
Fix that.

Fixes: 09a7d9eca1a6 '{net,IB}/mlx5: QP/XRCD commands via mlx5 ifc'
Signed-off-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/qp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
index d0a4005..9346f39 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
@@ -303,8 +303,8 @@ int mlx5_core_create_qp(struct mlx5_core_dev *dev,
 err_cmd:
 	memset(din, 0, sizeof(din));
 	memset(dout, 0, sizeof(dout));
-	MLX5_SET(destroy_qp_in, in, opcode, MLX5_CMD_OP_DESTROY_QP);
-	MLX5_SET(destroy_qp_in, in, qpn, qp->qpn);
+	MLX5_SET(destroy_qp_in, din, opcode, MLX5_CMD_OP_DESTROY_QP);
+	MLX5_SET(destroy_qp_in, din, qpn, qp->qpn);
 	mlx5_cmd_exec(dev, din, sizeof(din), dout, sizeof(dout));
 	return err;
 }
-- 
2.9.5


From 781956506664ee975a2d9b51cc580770ecaf444f Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Wed, 13 Dec 2017 18:56:29 +0100
Subject: [PATCH 30/33] s390/qeth: apply takeover changes when mode is toggled

[ Upstream commit 7fbd9493f0eeae8cef58300505a9ef5c8fce6313 ]

Just as for an explicit enable/disable, toggling the takeover mode also
requires that the IP addresses get updated. Otherwise all IPs that were
added to the table before the mode-toggle, get registered with the old
settings.

Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core.h      |  2 +-
 drivers/s390/net/qeth_core_main.c |  2 +-
 drivers/s390/net/qeth_l3_sys.c    | 35 +++++++++++++++++------------------
 3 files changed, 19 insertions(+), 20 deletions(-)

diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index e72234e..48eee3c 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -576,7 +576,7 @@ enum qeth_cq {
 };
 
 struct qeth_ipato {
-	int enabled;
+	bool enabled;
 	int invert4;
 	int invert6;
 	struct list_head entries;
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 838ed62..606b506 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -1475,7 +1475,7 @@ static int qeth_setup_card(struct qeth_card *card)
 	qeth_set_intial_options(card);
 	/* IP address takeover */
 	INIT_LIST_HEAD(&card->ipato.entries);
-	card->ipato.enabled = 0;
+	card->ipato.enabled = false;
 	card->ipato.invert4 = 0;
 	card->ipato.invert6 = 0;
 	/* init QDIO stuff */
diff --git a/drivers/s390/net/qeth_l3_sys.c b/drivers/s390/net/qeth_l3_sys.c
index cffe42f..b595a2b 100644
--- a/drivers/s390/net/qeth_l3_sys.c
+++ b/drivers/s390/net/qeth_l3_sys.c
@@ -374,6 +374,7 @@ static ssize_t qeth_l3_dev_ipato_enable_store(struct device *dev,
 	struct qeth_card *card = dev_get_drvdata(dev);
 	struct qeth_ipaddr *addr;
 	int i, rc = 0;
+	bool enable;
 
 	if (!card)
 		return -EINVAL;
@@ -386,25 +387,23 @@ static ssize_t qeth_l3_dev_ipato_enable_store(struct device *dev,
 	}
 
 	if (sysfs_streq(buf, "toggle")) {
-		card->ipato.enabled = (card->ipato.enabled)? 0 : 1;
-	} else if (sysfs_streq(buf, "1")) {
-		card->ipato.enabled = 1;
-		hash_for_each(card->ip_htable, i, addr, hnode) {
-				if ((addr->type == QETH_IP_TYPE_NORMAL) &&
-				qeth_l3_is_addr_covered_by_ipato(card, addr))
-					addr->set_flags |=
-					QETH_IPA_SETIP_TAKEOVER_FLAG;
-			}
-	} else if (sysfs_streq(buf, "0")) {
-		card->ipato.enabled = 0;
-		hash_for_each(card->ip_htable, i, addr, hnode) {
-			if (addr->set_flags &
-			QETH_IPA_SETIP_TAKEOVER_FLAG)
-				addr->set_flags &=
-				~QETH_IPA_SETIP_TAKEOVER_FLAG;
-			}
-	} else
+		enable = !card->ipato.enabled;
+	} else if (kstrtobool(buf, &enable)) {
 		rc = -EINVAL;
+		goto out;
+	}
+
+	if (card->ipato.enabled == enable)
+		goto out;
+	card->ipato.enabled = enable;
+
+	hash_for_each(card->ip_htable, i, addr, hnode) {
+		if (!enable)
+			addr->set_flags &= ~QETH_IPA_SETIP_TAKEOVER_FLAG;
+		else if (addr->type == QETH_IP_TYPE_NORMAL &&
+			 qeth_l3_is_addr_covered_by_ipato(card, addr))
+			addr->set_flags |= QETH_IPA_SETIP_TAKEOVER_FLAG;
+	}
 out:
 	mutex_unlock(&card->conf_mutex);
 	return rc ? rc : count;
-- 
2.9.5


From f9a32100ff20464141304091bf02e4b3fb3cbc46 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Wed, 13 Dec 2017 18:56:30 +0100
Subject: [PATCH 31/33] s390/qeth: don't apply takeover changes to RXIP

[ Upstream commit b22d73d6689fd902a66c08ebe71ab2f3b351e22f ]

When takeover is switched off, current code clears the 'TAKEOVER' flag on
all IPs. But the flag is also used for RXIP addresses, and those should
not be affected by the takeover mode.
Fix the behaviour by consistenly applying takover logic to NORMAL
addresses only.

Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_l3_main.c | 5 +++--
 drivers/s390/net/qeth_l3_sys.c  | 5 +++--
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index f91e70c..04240cc 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -178,6 +178,8 @@ int qeth_l3_is_addr_covered_by_ipato(struct qeth_card *card,
 
 	if (!card->ipato.enabled)
 		return 0;
+	if (addr->type != QETH_IP_TYPE_NORMAL)
+		return 0;
 
 	qeth_l3_convert_addr_to_bits((u8 *) &addr->u, addr_bits,
 				  (addr->proto == QETH_PROT_IPV4)? 4:16);
@@ -293,8 +295,7 @@ int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
 		memcpy(addr, tmp_addr, sizeof(struct qeth_ipaddr));
 		addr->ref_counter = 1;
 
-		if (addr->type == QETH_IP_TYPE_NORMAL  &&
-				qeth_l3_is_addr_covered_by_ipato(card, addr)) {
+		if (qeth_l3_is_addr_covered_by_ipato(card, addr)) {
 			QETH_CARD_TEXT(card, 2, "tkovaddr");
 			addr->set_flags |= QETH_IPA_SETIP_TAKEOVER_FLAG;
 		}
diff --git a/drivers/s390/net/qeth_l3_sys.c b/drivers/s390/net/qeth_l3_sys.c
index b595a2b..8521443 100644
--- a/drivers/s390/net/qeth_l3_sys.c
+++ b/drivers/s390/net/qeth_l3_sys.c
@@ -398,10 +398,11 @@ static ssize_t qeth_l3_dev_ipato_enable_store(struct device *dev,
 	card->ipato.enabled = enable;
 
 	hash_for_each(card->ip_htable, i, addr, hnode) {
+		if (addr->type != QETH_IP_TYPE_NORMAL)
+			continue;
 		if (!enable)
 			addr->set_flags &= ~QETH_IPA_SETIP_TAKEOVER_FLAG;
-		else if (addr->type == QETH_IP_TYPE_NORMAL &&
-			 qeth_l3_is_addr_covered_by_ipato(card, addr))
+		else if (qeth_l3_is_addr_covered_by_ipato(card, addr))
 			addr->set_flags |= QETH_IPA_SETIP_TAKEOVER_FLAG;
 	}
 out:
-- 
2.9.5


From 5956edded75fccd5aca4e0f305229ae0b6d45b89 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Wed, 13 Dec 2017 18:56:31 +0100
Subject: [PATCH 32/33] s390/qeth: lock IP table while applying takeover
 changes

[ Upstream commit 8a03a3692b100d84785ee7a834e9215e304c9e00 ]

Modifying the flags of an IP addr object needs to be protected against
eg. concurrent removal of the same object from the IP table.

Fixes: 5f78e29ceebf ("qeth: optimize IP handling in rx_mode callback")
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_l3_sys.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/s390/net/qeth_l3_sys.c b/drivers/s390/net/qeth_l3_sys.c
index 8521443..f95135f 100644
--- a/drivers/s390/net/qeth_l3_sys.c
+++ b/drivers/s390/net/qeth_l3_sys.c
@@ -397,6 +397,7 @@ static ssize_t qeth_l3_dev_ipato_enable_store(struct device *dev,
 		goto out;
 	card->ipato.enabled = enable;
 
+	spin_lock_bh(&card->ip_lock);
 	hash_for_each(card->ip_htable, i, addr, hnode) {
 		if (addr->type != QETH_IP_TYPE_NORMAL)
 			continue;
@@ -405,6 +406,7 @@ static ssize_t qeth_l3_dev_ipato_enable_store(struct device *dev,
 		else if (qeth_l3_is_addr_covered_by_ipato(card, addr))
 			addr->set_flags |= QETH_IPA_SETIP_TAKEOVER_FLAG;
 	}
+	spin_unlock_bh(&card->ip_lock);
 out:
 	mutex_unlock(&card->conf_mutex);
 	return rc ? rc : count;
-- 
2.9.5


From a314a55614a99aec2f01949871e95e8d95685cb4 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Wed, 13 Dec 2017 18:56:32 +0100
Subject: [PATCH 33/33] s390/qeth: update takeover IPs after configuration
 change

[ Upstream commit 02f510f326501470348a5df341e8232c3497bbbb ]

Any modification to the takeover IP-ranges requires that we re-evaluate
which IP addresses are takeover-eligible. Otherwise we might do takeover
for some addresses when we no longer should, or vice-versa.

Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core.h      |  4 +--
 drivers/s390/net/qeth_core_main.c |  4 +--
 drivers/s390/net/qeth_l3.h        |  2 +-
 drivers/s390/net/qeth_l3_main.c   | 31 +++++++++++++++++--
 drivers/s390/net/qeth_l3_sys.c    | 63 +++++++++++++++++++++------------------
 5 files changed, 67 insertions(+), 37 deletions(-)

diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 48eee3c..9b5fc50 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -577,8 +577,8 @@ enum qeth_cq {
 
 struct qeth_ipato {
 	bool enabled;
-	int invert4;
-	int invert6;
+	bool invert4;
+	bool invert6;
 	struct list_head entries;
 };
 
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 606b506..df8f74c 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -1476,8 +1476,8 @@ static int qeth_setup_card(struct qeth_card *card)
 	/* IP address takeover */
 	INIT_LIST_HEAD(&card->ipato.entries);
 	card->ipato.enabled = false;
-	card->ipato.invert4 = 0;
-	card->ipato.invert6 = 0;
+	card->ipato.invert4 = false;
+	card->ipato.invert6 = false;
 	/* init QDIO stuff */
 	qeth_init_qdio_info(card);
 	INIT_DELAYED_WORK(&card->buffer_reclaim_work, qeth_buffer_reclaim_work);
diff --git a/drivers/s390/net/qeth_l3.h b/drivers/s390/net/qeth_l3.h
index 26f7953..eedf9b0 100644
--- a/drivers/s390/net/qeth_l3.h
+++ b/drivers/s390/net/qeth_l3.h
@@ -80,7 +80,7 @@ void qeth_l3_del_vipa(struct qeth_card *, enum qeth_prot_versions, const u8 *);
 int qeth_l3_add_rxip(struct qeth_card *, enum qeth_prot_versions, const u8 *);
 void qeth_l3_del_rxip(struct qeth_card *card, enum qeth_prot_versions,
 			const u8 *);
-int qeth_l3_is_addr_covered_by_ipato(struct qeth_card *, struct qeth_ipaddr *);
+void qeth_l3_update_ipato(struct qeth_card *card);
 struct qeth_ipaddr *qeth_l3_get_addr_buffer(enum qeth_prot_versions);
 int qeth_l3_add_ip(struct qeth_card *, struct qeth_ipaddr *);
 int qeth_l3_delete_ip(struct qeth_card *, struct qeth_ipaddr *);
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 04240cc..1487f8a 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -168,8 +168,8 @@ static void qeth_l3_convert_addr_to_bits(u8 *addr, u8 *bits, int len)
 	}
 }
 
-int qeth_l3_is_addr_covered_by_ipato(struct qeth_card *card,
-						struct qeth_ipaddr *addr)
+static bool qeth_l3_is_addr_covered_by_ipato(struct qeth_card *card,
+					     struct qeth_ipaddr *addr)
 {
 	struct qeth_ipato_entry *ipatoe;
 	u8 addr_bits[128] = {0, };
@@ -608,6 +608,27 @@ int qeth_l3_setrouting_v6(struct qeth_card *card)
 /*
  * IP address takeover related functions
  */
+
+/**
+ * qeth_l3_update_ipato() - Update 'takeover' property, for all NORMAL IPs.
+ *
+ * Caller must hold ip_lock.
+ */
+void qeth_l3_update_ipato(struct qeth_card *card)
+{
+	struct qeth_ipaddr *addr;
+	unsigned int i;
+
+	hash_for_each(card->ip_htable, i, addr, hnode) {
+		if (addr->type != QETH_IP_TYPE_NORMAL)
+			continue;
+		if (qeth_l3_is_addr_covered_by_ipato(card, addr))
+			addr->set_flags |= QETH_IPA_SETIP_TAKEOVER_FLAG;
+		else
+			addr->set_flags &= ~QETH_IPA_SETIP_TAKEOVER_FLAG;
+	}
+}
+
 static void qeth_l3_clear_ipato_list(struct qeth_card *card)
 {
 	struct qeth_ipato_entry *ipatoe, *tmp;
@@ -619,6 +640,7 @@ static void qeth_l3_clear_ipato_list(struct qeth_card *card)
 		kfree(ipatoe);
 	}
 
+	qeth_l3_update_ipato(card);
 	spin_unlock_bh(&card->ip_lock);
 }
 
@@ -643,8 +665,10 @@ int qeth_l3_add_ipato_entry(struct qeth_card *card,
 		}
 	}
 
-	if (!rc)
+	if (!rc) {
 		list_add_tail(&new->entry, &card->ipato.entries);
+		qeth_l3_update_ipato(card);
+	}
 
 	spin_unlock_bh(&card->ip_lock);
 
@@ -667,6 +691,7 @@ void qeth_l3_del_ipato_entry(struct qeth_card *card,
 			    (proto == QETH_PROT_IPV4)? 4:16) &&
 		    (ipatoe->mask_bits == mask_bits)) {
 			list_del(&ipatoe->entry);
+			qeth_l3_update_ipato(card);
 			kfree(ipatoe);
 		}
 	}
diff --git a/drivers/s390/net/qeth_l3_sys.c b/drivers/s390/net/qeth_l3_sys.c
index f95135f..d6bdfc6 100644
--- a/drivers/s390/net/qeth_l3_sys.c
+++ b/drivers/s390/net/qeth_l3_sys.c
@@ -372,9 +372,8 @@ static ssize_t qeth_l3_dev_ipato_enable_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t count)
 {
 	struct qeth_card *card = dev_get_drvdata(dev);
-	struct qeth_ipaddr *addr;
-	int i, rc = 0;
 	bool enable;
+	int rc = 0;
 
 	if (!card)
 		return -EINVAL;
@@ -393,20 +392,12 @@ static ssize_t qeth_l3_dev_ipato_enable_store(struct device *dev,
 		goto out;
 	}
 
-	if (card->ipato.enabled == enable)
-		goto out;
-	card->ipato.enabled = enable;
-
-	spin_lock_bh(&card->ip_lock);
-	hash_for_each(card->ip_htable, i, addr, hnode) {
-		if (addr->type != QETH_IP_TYPE_NORMAL)
-			continue;
-		if (!enable)
-			addr->set_flags &= ~QETH_IPA_SETIP_TAKEOVER_FLAG;
-		else if (qeth_l3_is_addr_covered_by_ipato(card, addr))
-			addr->set_flags |= QETH_IPA_SETIP_TAKEOVER_FLAG;
+	if (card->ipato.enabled != enable) {
+		card->ipato.enabled = enable;
+		spin_lock_bh(&card->ip_lock);
+		qeth_l3_update_ipato(card);
+		spin_unlock_bh(&card->ip_lock);
 	}
-	spin_unlock_bh(&card->ip_lock);
 out:
 	mutex_unlock(&card->conf_mutex);
 	return rc ? rc : count;
@@ -432,20 +423,27 @@ static ssize_t qeth_l3_dev_ipato_invert4_store(struct device *dev,
 				const char *buf, size_t count)
 {
 	struct qeth_card *card = dev_get_drvdata(dev);
+	bool invert;
 	int rc = 0;
 
 	if (!card)
 		return -EINVAL;
 
 	mutex_lock(&card->conf_mutex);
-	if (sysfs_streq(buf, "toggle"))
-		card->ipato.invert4 = (card->ipato.invert4)? 0 : 1;
-	else if (sysfs_streq(buf, "1"))
-		card->ipato.invert4 = 1;
-	else if (sysfs_streq(buf, "0"))
-		card->ipato.invert4 = 0;
-	else
+	if (sysfs_streq(buf, "toggle")) {
+		invert = !card->ipato.invert4;
+	} else if (kstrtobool(buf, &invert)) {
 		rc = -EINVAL;
+		goto out;
+	}
+
+	if (card->ipato.invert4 != invert) {
+		card->ipato.invert4 = invert;
+		spin_lock_bh(&card->ip_lock);
+		qeth_l3_update_ipato(card);
+		spin_unlock_bh(&card->ip_lock);
+	}
+out:
 	mutex_unlock(&card->conf_mutex);
 	return rc ? rc : count;
 }
@@ -611,20 +609,27 @@ static ssize_t qeth_l3_dev_ipato_invert6_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t count)
 {
 	struct qeth_card *card = dev_get_drvdata(dev);
+	bool invert;
 	int rc = 0;
 
 	if (!card)
 		return -EINVAL;
 
 	mutex_lock(&card->conf_mutex);
-	if (sysfs_streq(buf, "toggle"))
-		card->ipato.invert6 = (card->ipato.invert6)? 0 : 1;
-	else if (sysfs_streq(buf, "1"))
-		card->ipato.invert6 = 1;
-	else if (sysfs_streq(buf, "0"))
-		card->ipato.invert6 = 0;
-	else
+	if (sysfs_streq(buf, "toggle")) {
+		invert = !card->ipato.invert6;
+	} else if (kstrtobool(buf, &invert)) {
 		rc = -EINVAL;
+		goto out;
+	}
+
+	if (card->ipato.invert6 != invert) {
+		card->ipato.invert6 = invert;
+		spin_lock_bh(&card->ip_lock);
+		qeth_l3_update_ipato(card);
+		spin_unlock_bh(&card->ip_lock);
+	}
+out:
 	mutex_unlock(&card->conf_mutex);
 	return rc ? rc : count;
 }
-- 
2.9.5


[-- Attachment #3: net_414.mbox --]
[-- Type: Application/Octet-Stream, Size: 157183 bytes --]

From fc9ac9fc10f5a8fc6505da3c79ee62816e13c453 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 11 Dec 2017 07:17:39 -0800
Subject: [PATCH 01/58] ipv4: igmp: guard against silly MTU values
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit b5476022bbada3764609368f03329ca287528dc8 ]

IPv4 stack reacts to changes to small MTU, by disabling itself under
RTNL.

But there is a window where threads not using RTNL can see a wrong
device mtu. This can lead to surprises, in igmp code where it is
assumed the mtu is suitable.

Fix this by reading device mtu once and checking IPv4 minimal MTU.

This patch adds missing IPV4_MIN_MTU define, to not abuse
ETH_MIN_MTU anymore.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h     |  1 +
 net/ipv4/devinet.c   |  2 +-
 net/ipv4/igmp.c      | 24 +++++++++++++++---------
 net/ipv4/ip_tunnel.c |  4 ++--
 4 files changed, 19 insertions(+), 12 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index 9896f46..af8addb 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -34,6 +34,7 @@
 #include <net/flow_dissector.h>
 
 #define IPV4_MAX_PMTU		65535U		/* RFC 2675, Section 5.1 */
+#define IPV4_MIN_MTU		68			/* RFC 791 */
 
 struct sock;
 
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index d7adc06..bffa88e 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1420,7 +1420,7 @@ static void inetdev_changename(struct net_device *dev, struct in_device *in_dev)
 
 static bool inetdev_valid_mtu(unsigned int mtu)
 {
-	return mtu >= 68;
+	return mtu >= IPV4_MIN_MTU;
 }
 
 static void inetdev_send_gratuitous_arp(struct net_device *dev,
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index ab183af..86f1786 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -404,16 +404,17 @@ static int grec_size(struct ip_mc_list *pmc, int type, int gdel, int sdel)
 }
 
 static struct sk_buff *add_grhead(struct sk_buff *skb, struct ip_mc_list *pmc,
-	int type, struct igmpv3_grec **ppgr)
+	int type, struct igmpv3_grec **ppgr, unsigned int mtu)
 {
 	struct net_device *dev = pmc->interface->dev;
 	struct igmpv3_report *pih;
 	struct igmpv3_grec *pgr;
 
-	if (!skb)
-		skb = igmpv3_newpack(dev, dev->mtu);
-	if (!skb)
-		return NULL;
+	if (!skb) {
+		skb = igmpv3_newpack(dev, mtu);
+		if (!skb)
+			return NULL;
+	}
 	pgr = skb_put(skb, sizeof(struct igmpv3_grec));
 	pgr->grec_type = type;
 	pgr->grec_auxwords = 0;
@@ -436,12 +437,17 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
 	struct igmpv3_grec *pgr = NULL;
 	struct ip_sf_list *psf, *psf_next, *psf_prev, **psf_list;
 	int scount, stotal, first, isquery, truncate;
+	unsigned int mtu;
 
 	if (pmc->multiaddr == IGMP_ALL_HOSTS)
 		return skb;
 	if (ipv4_is_local_multicast(pmc->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports)
 		return skb;
 
+	mtu = READ_ONCE(dev->mtu);
+	if (mtu < IPV4_MIN_MTU)
+		return skb;
+
 	isquery = type == IGMPV3_MODE_IS_INCLUDE ||
 		  type == IGMPV3_MODE_IS_EXCLUDE;
 	truncate = type == IGMPV3_MODE_IS_EXCLUDE ||
@@ -462,7 +468,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
 		    AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) {
 			if (skb)
 				igmpv3_sendpack(skb);
-			skb = igmpv3_newpack(dev, dev->mtu);
+			skb = igmpv3_newpack(dev, mtu);
 		}
 	}
 	first = 1;
@@ -498,12 +504,12 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
 				pgr->grec_nsrcs = htons(scount);
 			if (skb)
 				igmpv3_sendpack(skb);
-			skb = igmpv3_newpack(dev, dev->mtu);
+			skb = igmpv3_newpack(dev, mtu);
 			first = 1;
 			scount = 0;
 		}
 		if (first) {
-			skb = add_grhead(skb, pmc, type, &pgr);
+			skb = add_grhead(skb, pmc, type, &pgr, mtu);
 			first = 0;
 		}
 		if (!skb)
@@ -538,7 +544,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
 				igmpv3_sendpack(skb);
 				skb = NULL; /* add_grhead will get a new one */
 			}
-			skb = add_grhead(skb, pmc, type, &pgr);
+			skb = add_grhead(skb, pmc, type, &pgr, mtu);
 		}
 	}
 	if (pgr)
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index e9805ad..4e90082 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -349,8 +349,8 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
 	dev->needed_headroom = t_hlen + hlen;
 	mtu -= (dev->hard_header_len + t_hlen);
 
-	if (mtu < 68)
-		mtu = 68;
+	if (mtu < IPV4_MIN_MTU)
+		mtu = IPV4_MIN_MTU;
 
 	return mtu;
 }
-- 
2.9.5


From ad7e3d645e20a0628145046597db4794ca92f261 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 11 Dec 2017 07:03:38 -0800
Subject: [PATCH 02/58] ipv6: mcast: better catch silly mtu values

[ Upstream commit b9b312a7a451e9c098921856e7cfbc201120e1a7 ]

syzkaller reported crashes in IPv6 stack [1]

Xin Long found that lo MTU was set to silly values.

IPv6 stack reacts to changes to small MTU, by disabling itself under
RTNL.

But there is a window where threads not using RTNL can see a wrong
device mtu. This can lead to surprises, in mld code where it is assumed
the mtu is suitable.

Fix this by reading device mtu once and checking IPv6 minimal MTU.

[1]
 skbuff: skb_over_panic: text:0000000010b86b8d len:196 put:20
 head:000000003b477e60 data:000000000e85441e tail:0xd4 end:0xc0 dev:lo
 ------------[ cut here ]------------
 kernel BUG at net/core/skbuff.c:104!
 invalid opcode: 0000 [#1] SMP KASAN
 Dumping ftrace buffer:
    (ftrace buffer empty)
 Modules linked in:
 CPU: 1 PID: 0 Comm: swapper/1 Not tainted 4.15.0-rc2-mm1+ #39
 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
 Google 01/01/2011
 RIP: 0010:skb_panic+0x15c/0x1f0 net/core/skbuff.c:100
 RSP: 0018:ffff8801db307508 EFLAGS: 00010286
 RAX: 0000000000000082 RBX: ffff8801c517e840 RCX: 0000000000000000
 RDX: 0000000000000082 RSI: 1ffff1003b660e61 RDI: ffffed003b660e95
 RBP: ffff8801db307570 R08: 1ffff1003b660e23 R09: 0000000000000000
 R10: 0000000000000000 R11: 0000000000000000 R12: ffffffff85bd4020
 R13: ffffffff84754ed2 R14: 0000000000000014 R15: ffff8801c4e26540
 FS:  0000000000000000(0000) GS:ffff8801db300000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000463610 CR3: 00000001c6698000 CR4: 00000000001406e0
 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
 Call Trace:
  <IRQ>
  skb_over_panic net/core/skbuff.c:109 [inline]
  skb_put+0x181/0x1c0 net/core/skbuff.c:1694
  add_grhead.isra.24+0x42/0x3b0 net/ipv6/mcast.c:1695
  add_grec+0xa55/0x1060 net/ipv6/mcast.c:1817
  mld_send_cr net/ipv6/mcast.c:1903 [inline]
  mld_ifc_timer_expire+0x4d2/0x770 net/ipv6/mcast.c:2448
  call_timer_fn+0x23b/0x840 kernel/time/timer.c:1320
  expire_timers kernel/time/timer.c:1357 [inline]
  __run_timers+0x7e1/0xb60 kernel/time/timer.c:1660
  run_timer_softirq+0x4c/0xb0 kernel/time/timer.c:1686
  __do_softirq+0x29d/0xbb2 kernel/softirq.c:285
  invoke_softirq kernel/softirq.c:365 [inline]
  irq_exit+0x1d3/0x210 kernel/softirq.c:405
  exiting_irq arch/x86/include/asm/apic.h:540 [inline]
  smp_apic_timer_interrupt+0x16b/0x700 arch/x86/kernel/apic/apic.c:1052
  apic_timer_interrupt+0xa9/0xb0 arch/x86/entry/entry_64.S:920

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Tested-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/mcast.c | 25 +++++++++++++++----------
 1 file changed, 15 insertions(+), 10 deletions(-)

diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 12b7c27..9a38a2c 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1682,16 +1682,16 @@ static int grec_size(struct ifmcaddr6 *pmc, int type, int gdel, int sdel)
 }
 
 static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc,
-	int type, struct mld2_grec **ppgr)
+	int type, struct mld2_grec **ppgr, unsigned int mtu)
 {
-	struct net_device *dev = pmc->idev->dev;
 	struct mld2_report *pmr;
 	struct mld2_grec *pgr;
 
-	if (!skb)
-		skb = mld_newpack(pmc->idev, dev->mtu);
-	if (!skb)
-		return NULL;
+	if (!skb) {
+		skb = mld_newpack(pmc->idev, mtu);
+		if (!skb)
+			return NULL;
+	}
 	pgr = skb_put(skb, sizeof(struct mld2_grec));
 	pgr->grec_type = type;
 	pgr->grec_auxwords = 0;
@@ -1714,10 +1714,15 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
 	struct mld2_grec *pgr = NULL;
 	struct ip6_sf_list *psf, *psf_next, *psf_prev, **psf_list;
 	int scount, stotal, first, isquery, truncate;
+	unsigned int mtu;
 
 	if (pmc->mca_flags & MAF_NOREPORT)
 		return skb;
 
+	mtu = READ_ONCE(dev->mtu);
+	if (mtu < IPV6_MIN_MTU)
+		return skb;
+
 	isquery = type == MLD2_MODE_IS_INCLUDE ||
 		  type == MLD2_MODE_IS_EXCLUDE;
 	truncate = type == MLD2_MODE_IS_EXCLUDE ||
@@ -1738,7 +1743,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
 		    AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) {
 			if (skb)
 				mld_sendpack(skb);
-			skb = mld_newpack(idev, dev->mtu);
+			skb = mld_newpack(idev, mtu);
 		}
 	}
 	first = 1;
@@ -1774,12 +1779,12 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
 				pgr->grec_nsrcs = htons(scount);
 			if (skb)
 				mld_sendpack(skb);
-			skb = mld_newpack(idev, dev->mtu);
+			skb = mld_newpack(idev, mtu);
 			first = 1;
 			scount = 0;
 		}
 		if (first) {
-			skb = add_grhead(skb, pmc, type, &pgr);
+			skb = add_grhead(skb, pmc, type, &pgr, mtu);
 			first = 0;
 		}
 		if (!skb)
@@ -1814,7 +1819,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
 				mld_sendpack(skb);
 				skb = NULL; /* add_grhead will get a new one */
 			}
-			skb = add_grhead(skb, pmc, type, &pgr);
+			skb = add_grhead(skb, pmc, type, &pgr, mtu);
 		}
 	}
 	if (pgr)
-- 
2.9.5


From fddd40673bb884eadf4ee5d32a50186b52ac8a3c Mon Sep 17 00:00:00 2001
From: Fugang Duan <fugang.duan@nxp.com>
Date: Fri, 22 Dec 2017 17:12:09 +0800
Subject: [PATCH 03/58] net: fec: unmap the xmit buffer that are not
 transferred by DMA

[ Upstream commit 178e5f57a8d8f8fc5799a624b96fc31ef9a29ffa ]

The enet IP only support 32 bit, it will use swiotlb buffer to do dma
mapping when xmit buffer DMA memory address is bigger than 4G in i.MX
platform. After stress suspend/resume test, it will print out:

log:
[12826.352864] fec 5b040000.ethernet: swiotlb buffer is full (sz: 191 bytes)
[12826.359676] DMA: Out of SW-IOMMU space for 191 bytes at device 5b040000.ethernet
[12826.367110] fec 5b040000.ethernet eth0: Tx DMA memory map failed

The issue is that the ready xmit buffers that are dma mapped but DMA still
don't copy them into fifo, once MAC restart, these DMA buffers are not unmapped.
So it should check the dma mapping buffer and unmap them.

Signed-off-by: Fugang Duan <fugang.duan@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_main.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 3dc2d77..faf7cdc 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -818,6 +818,12 @@ static void fec_enet_bd_init(struct net_device *dev)
 		for (i = 0; i < txq->bd.ring_size; i++) {
 			/* Initialize the BD for every fragment in the page. */
 			bdp->cbd_sc = cpu_to_fec16(0);
+			if (bdp->cbd_bufaddr &&
+			    !IS_TSO_HEADER(txq, fec32_to_cpu(bdp->cbd_bufaddr)))
+				dma_unmap_single(&fep->pdev->dev,
+						 fec32_to_cpu(bdp->cbd_bufaddr),
+						 fec16_to_cpu(bdp->cbd_datlen),
+						 DMA_TO_DEVICE);
 			if (txq->tx_skbuff[i]) {
 				dev_kfree_skb_any(txq->tx_skbuff[i]);
 				txq->tx_skbuff[i] = NULL;
-- 
2.9.5


From 153384787084904c1fd1e892b1218b668bd89080 Mon Sep 17 00:00:00 2001
From: Kevin Cernekee <cernekee@chromium.org>
Date: Mon, 11 Dec 2017 11:13:45 -0800
Subject: [PATCH 04/58] net: igmp: Use correct source address on IGMPv3 reports

[ Upstream commit a46182b00290839fa3fa159d54fd3237bd8669f0 ]

Closing a multicast socket after the final IPv4 address is deleted
from an interface can generate a membership report that uses the
source IP from a different interface.  The following test script, run
from an isolated netns, reproduces the issue:

    #!/bin/bash

    ip link add dummy0 type dummy
    ip link add dummy1 type dummy
    ip link set dummy0 up
    ip link set dummy1 up
    ip addr add 10.1.1.1/24 dev dummy0
    ip addr add 192.168.99.99/24 dev dummy1

    tcpdump -U -i dummy0 &
    socat EXEC:"sleep 2" \
        UDP4-DATAGRAM:239.101.1.68:8889,ip-add-membership=239.0.1.68:10.1.1.1 &

    sleep 1
    ip addr del 10.1.1.1/24 dev dummy0
    sleep 5
    kill %tcpdump

RFC 3376 specifies that the report must be sent with a valid IP source
address from the destination subnet, or from address 0.0.0.0.  Add an
extra check to make sure this is the case.

Signed-off-by: Kevin Cernekee <cernekee@chromium.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/igmp.c | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 86f1786..c621266 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -89,6 +89,7 @@
 #include <linux/rtnetlink.h>
 #include <linux/times.h>
 #include <linux/pkt_sched.h>
+#include <linux/byteorder/generic.h>
 
 #include <net/net_namespace.h>
 #include <net/arp.h>
@@ -321,6 +322,23 @@ igmp_scount(struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted)
 	return scount;
 }
 
+/* source address selection per RFC 3376 section 4.2.13 */
+static __be32 igmpv3_get_srcaddr(struct net_device *dev,
+				 const struct flowi4 *fl4)
+{
+	struct in_device *in_dev = __in_dev_get_rcu(dev);
+
+	if (!in_dev)
+		return htonl(INADDR_ANY);
+
+	for_ifa(in_dev) {
+		if (inet_ifa_match(fl4->saddr, ifa))
+			return fl4->saddr;
+	} endfor_ifa(in_dev);
+
+	return htonl(INADDR_ANY);
+}
+
 static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu)
 {
 	struct sk_buff *skb;
@@ -368,7 +386,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu)
 	pip->frag_off = htons(IP_DF);
 	pip->ttl      = 1;
 	pip->daddr    = fl4.daddr;
-	pip->saddr    = fl4.saddr;
+	pip->saddr    = igmpv3_get_srcaddr(dev, &fl4);
 	pip->protocol = IPPROTO_IGMP;
 	pip->tot_len  = 0;	/* filled in later */
 	ip_select_ident(net, skb, NULL);
-- 
2.9.5


From 304ac898a193aab8df1ab75cab1c789155e524fa Mon Sep 17 00:00:00 2001
From: Kevin Cernekee <cernekee@chromium.org>
Date: Wed, 6 Dec 2017 12:12:27 -0800
Subject: [PATCH 05/58] netlink: Add netns check on taps

[ Upstream commit 93c647643b48f0131f02e45da3bd367d80443291 ]

Currently, a nlmon link inside a child namespace can observe systemwide
netlink activity.  Filter the traffic so that nlmon can only sniff
netlink messages from its own netns.

Test case:

    vpnns -- bash -c "ip link add nlmon0 type nlmon; \
                      ip link set nlmon0 up; \
                      tcpdump -i nlmon0 -q -w /tmp/nlmon.pcap -U" &
    sudo ip xfrm state add src 10.1.1.1 dst 10.1.1.2 proto esp \
        spi 0x1 mode transport \
        auth sha1 0x6162633132330000000000000000000000000000 \
        enc aes 0x00000000000000000000000000000000
    grep --binary abc123 /tmp/nlmon.pcap

Signed-off-by: Kevin Cernekee <cernekee@chromium.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 15c99df..aac9d68b 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -254,6 +254,9 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb,
 	struct sock *sk = skb->sk;
 	int ret = -ENOMEM;
 
+	if (!net_eq(dev_net(dev), sock_net(sk)))
+		return 0;
+
 	dev_hold(dev);
 
 	if (is_vmalloc_addr(skb->head))
-- 
2.9.5


From 2fe7ed273331aadeecc58d22367ea7f08b410a3b Mon Sep 17 00:00:00 2001
From: Sebastian Sjoholm <ssjoholm@mac.com>
Date: Mon, 11 Dec 2017 21:51:14 +0100
Subject: [PATCH 06/58] net: qmi_wwan: add Sierra EM7565 1199:9091
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit aceef61ee56898cfa7b6960fb60b9326c3860441 ]

Sierra Wireless EM7565 is an Qualcomm MDM9x50 based M.2 modem.
The USB id is added to qmi_wwan.c to allow QMI communication
with the EM7565.

Signed-off-by: Sebastian Sjoholm <ssjoholm@mac.com>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 81394a4..2092feb 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1204,6 +1204,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1199, 0x9079, 10)},	/* Sierra Wireless EM74xx */
 	{QMI_FIXED_INTF(0x1199, 0x907b, 8)},	/* Sierra Wireless EM74xx */
 	{QMI_FIXED_INTF(0x1199, 0x907b, 10)},	/* Sierra Wireless EM74xx */
+	{QMI_FIXED_INTF(0x1199, 0x9091, 8)},	/* Sierra Wireless EM7565 */
 	{QMI_FIXED_INTF(0x1bbb, 0x011e, 4)},	/* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */
 	{QMI_FIXED_INTF(0x1bbb, 0x0203, 2)},	/* Alcatel L800MA */
 	{QMI_FIXED_INTF(0x2357, 0x0201, 4)},	/* TP-LINK HSUPA Modem MA180 */
-- 
2.9.5


From 27a27081c381963a21d2b22869ba13339e33a528 Mon Sep 17 00:00:00 2001
From: Shaohua Li <shli@fb.com>
Date: Wed, 20 Dec 2017 12:10:21 -0800
Subject: [PATCH 07/58] net: reevalulate autoflowlabel setting after sysctl
 setting

[ Upstream commit 513674b5a2c9c7a67501506419da5c3c77ac6f08 ]

sysctl.ip6.auto_flowlabels is default 1. In our hosts, we set it to 2.
If sockopt doesn't set autoflowlabel, outcome packets from the hosts are
supposed to not include flowlabel. This is true for normal packet, but
not for reset packet.

The reason is ipv6_pinfo.autoflowlabel is set in sock creation. Later if
we change sysctl.ip6.auto_flowlabels, the ipv6_pinfo.autoflowlabel isn't
changed, so the sock will keep the old behavior in terms of auto
flowlabel. Reset packet is suffering from this problem, because reset
packet is sent from a special control socket, which is created at boot
time. Since sysctl.ipv6.auto_flowlabels is 1 by default, the control
socket will always have its ipv6_pinfo.autoflowlabel set, even after
user set sysctl.ipv6.auto_flowlabels to 1, so reset packset will always
have flowlabel. Normal sock created before sysctl setting suffers from
the same issue. We can't even turn off autoflowlabel unless we kill all
socks in the hosts.

To fix this, if IPV6_AUTOFLOWLABEL sockopt is used, we use the
autoflowlabel setting from user, otherwise we always call
ip6_default_np_autolabel() which has the new settings of sysctl.

Note, this changes behavior a little bit. Before commit 42240901f7c4
(ipv6: Implement different admin modes for automatic flow labels), the
autoflowlabel behavior of a sock isn't sticky, eg, if sysctl changes,
existing connection will change autoflowlabel behavior. After that
commit, autoflowlabel behavior is sticky in the whole life of the sock.
With this patch, the behavior isn't sticky again.

Cc: Martin KaFai Lau <kafai@fb.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Tom Herbert <tom@quantonium.net>
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ipv6.h     |  3 ++-
 net/ipv6/af_inet6.c      |  1 -
 net/ipv6/ip6_output.c    | 12 ++++++++++--
 net/ipv6/ipv6_sockglue.c |  1 +
 4 files changed, 13 insertions(+), 4 deletions(-)

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index ea04ca0..067a6fa 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -272,7 +272,8 @@ struct ipv6_pinfo {
 						 * 100: prefer care-of address
 						 */
 				dontfrag:1,
-				autoflowlabel:1;
+				autoflowlabel:1,
+				autoflowlabel_set:1;
 	__u8			min_hopcount;
 	__u8			tclass;
 	__be32			rcv_flowinfo;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index fe5262f..bcbd5f3 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -210,7 +210,6 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol,
 	np->mcast_hops	= IPV6_DEFAULT_MCASTHOPS;
 	np->mc_loop	= 1;
 	np->pmtudisc	= IPV6_PMTUDISC_WANT;
-	np->autoflowlabel = ip6_default_np_autolabel(net);
 	np->repflow	= net->ipv6.sysctl.flowlabel_reflect;
 	sk->sk_ipv6only	= net->ipv6.sysctl.bindv6only;
 
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 5110a41..f7dd51c 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -166,6 +166,14 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 			    !(IP6CB(skb)->flags & IP6SKB_REROUTED));
 }
 
+static bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np)
+{
+	if (!np->autoflowlabel_set)
+		return ip6_default_np_autolabel(net);
+	else
+		return np->autoflowlabel;
+}
+
 /*
  * xmit an sk_buff (used by TCP, SCTP and DCCP)
  * Note : socket lock is not held for SYNACK packets, but might be modified
@@ -230,7 +238,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 		hlimit = ip6_dst_hoplimit(dst);
 
 	ip6_flow_hdr(hdr, tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel,
-						     np->autoflowlabel, fl6));
+				ip6_autoflowlabel(net, np), fl6));
 
 	hdr->payload_len = htons(seg_len);
 	hdr->nexthdr = proto;
@@ -1626,7 +1634,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
 
 	ip6_flow_hdr(hdr, v6_cork->tclass,
 		     ip6_make_flowlabel(net, skb, fl6->flowlabel,
-					np->autoflowlabel, fl6));
+					ip6_autoflowlabel(net, np), fl6));
 	hdr->hop_limit = v6_cork->hop_limit;
 	hdr->nexthdr = proto;
 	hdr->saddr = fl6->saddr;
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index a5e466d..90dbfa7 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -878,6 +878,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 		break;
 	case IPV6_AUTOFLOWLABEL:
 		np->autoflowlabel = valbool;
+		np->autoflowlabel_set = 1;
 		retv = 0;
 		break;
 	case IPV6_RECVFRAGSIZE:
-- 
2.9.5


From 506fe481a90b62cb2368e2368bde85e44d01c214 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Tue, 5 Dec 2017 21:29:37 +0200
Subject: [PATCH 08/58] ptr_ring: add barriers

[ Upstream commit a8ceb5dbfde1092b466936bca0ff3be127ecf38e ]

Users of ptr_ring expect that it's safe to give the
data structure a pointer and have it be available
to consumers, but that actually requires an smb_wmb
or a stronger barrier.

In absence of such barriers and on architectures that reorder writes,
consumer might read an un=initialized value from an skb pointer stored
in the skb array.  This was observed causing crashes.

To fix, add memory barriers.  The barrier we use is a wmb, the
assumption being that producers do not need to read the value so we do
not need to order these reads.

Reported-by: George Cherian <george.cherian@cavium.com>
Suggested-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ptr_ring.h | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h
index 37b4bb2..6866df4 100644
--- a/include/linux/ptr_ring.h
+++ b/include/linux/ptr_ring.h
@@ -101,12 +101,18 @@ static inline bool ptr_ring_full_bh(struct ptr_ring *r)
 
 /* Note: callers invoking this in a loop must use a compiler barrier,
  * for example cpu_relax(). Callers must hold producer_lock.
+ * Callers are responsible for making sure pointer that is being queued
+ * points to a valid data.
  */
 static inline int __ptr_ring_produce(struct ptr_ring *r, void *ptr)
 {
 	if (unlikely(!r->size) || r->queue[r->producer])
 		return -ENOSPC;
 
+	/* Make sure the pointer we are storing points to a valid data. */
+	/* Pairs with smp_read_barrier_depends in __ptr_ring_consume. */
+	smp_wmb();
+
 	r->queue[r->producer++] = ptr;
 	if (unlikely(r->producer >= r->size))
 		r->producer = 0;
@@ -275,6 +281,9 @@ static inline void *__ptr_ring_consume(struct ptr_ring *r)
 	if (ptr)
 		__ptr_ring_discard_one(r);
 
+	/* Make sure anyone accessing data through the pointer is up to date. */
+	/* Pairs with smp_wmb in __ptr_ring_produce. */
+	smp_read_barrier_depends();
 	return ptr;
 }
 
-- 
2.9.5


From de93e32228e847bb6c4505c73bac190dc1119675 Mon Sep 17 00:00:00 2001
From: Avinash Repaka <avinash.repaka@oracle.com>
Date: Thu, 21 Dec 2017 20:17:04 -0800
Subject: [PATCH 09/58] RDS: Check cmsg_len before dereferencing CMSG_DATA

[ Upstream commit 14e138a86f6347c6199f610576d2e11c03bec5f0 ]

RDS currently doesn't check if the length of the control message is
large enough to hold the required data, before dereferencing the control
message data. This results in following crash:

BUG: KASAN: stack-out-of-bounds in rds_rdma_bytes net/rds/send.c:1013
[inline]
BUG: KASAN: stack-out-of-bounds in rds_sendmsg+0x1f02/0x1f90
net/rds/send.c:1066
Read of size 8 at addr ffff8801c928fb70 by task syzkaller455006/3157

CPU: 0 PID: 3157 Comm: syzkaller455006 Not tainted 4.15.0-rc3+ #161
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x194/0x257 lib/dump_stack.c:53
 print_address_description+0x73/0x250 mm/kasan/report.c:252
 kasan_report_error mm/kasan/report.c:351 [inline]
 kasan_report+0x25b/0x340 mm/kasan/report.c:409
 __asan_report_load8_noabort+0x14/0x20 mm/kasan/report.c:430
 rds_rdma_bytes net/rds/send.c:1013 [inline]
 rds_sendmsg+0x1f02/0x1f90 net/rds/send.c:1066
 sock_sendmsg_nosec net/socket.c:628 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:638
 ___sys_sendmsg+0x320/0x8b0 net/socket.c:2018
 __sys_sendmmsg+0x1ee/0x620 net/socket.c:2108
 SYSC_sendmmsg net/socket.c:2139 [inline]
 SyS_sendmmsg+0x35/0x60 net/socket.c:2134
 entry_SYSCALL_64_fastpath+0x1f/0x96
RIP: 0033:0x43fe49
RSP: 002b:00007fffbe244ad8 EFLAGS: 00000217 ORIG_RAX: 0000000000000133
RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 000000000043fe49
RDX: 0000000000000001 RSI: 000000002020c000 RDI: 0000000000000003
RBP: 00000000006ca018 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000217 R12: 00000000004017b0
R13: 0000000000401840 R14: 0000000000000000 R15: 0000000000000000

To fix this, we verify that the cmsg_len is large enough to hold the
data to be read, before proceeding further.

Reported-by: syzbot <syzkaller-bugs@googlegroups.com>
Signed-off-by: Avinash Repaka <avinash.repaka@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Reviewed-by: Yuval Shaia <yuval.shaia@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/send.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/rds/send.c b/net/rds/send.c
index b52cdc8..f72466c 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -1009,6 +1009,9 @@ static int rds_rdma_bytes(struct msghdr *msg, size_t *rdma_bytes)
 			continue;
 
 		if (cmsg->cmsg_type == RDS_CMSG_RDMA_ARGS) {
+			if (cmsg->cmsg_len <
+			    CMSG_LEN(sizeof(struct rds_rdma_args)))
+				return -EINVAL;
 			args = CMSG_DATA(cmsg);
 			*rdma_bytes += args->remote_vec.bytes;
 		}
-- 
2.9.5


From 4ec8d151a5da132cea023d8c0af523de720e1141 Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Thu, 7 Dec 2017 12:43:30 -0500
Subject: [PATCH 10/58] tcp_bbr: record "full bw reached" decision in new
 full_bw_reached bit

[ Upstream commit c589e69b508d29ed8e644dfecda453f71c02ec27 ]

This commit records the "full bw reached" decision in a new
full_bw_reached bit. This is a pure refactor that does not change the
current behavior, but enables subsequent fixes and improvements.

In particular, this enables simple and clean fixes because the full_bw
and full_bw_cnt can be unconditionally zeroed without worrying about
forgetting that we estimated we filled the pipe in Startup. And it
enables future improvements because multiple code paths can be used
for estimating that we filled the pipe in Startup; any new code paths
only need to set this bit when they think the pipe is full.

Note that this fix intentionally reduces the width of the full_bw_cnt
counter, since we have never used the most significant bit.

Signed-off-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_bbr.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 69ee877..3089c95 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -110,7 +110,8 @@ struct bbr {
 	u32	lt_last_lost;	     /* LT intvl start: tp->lost */
 	u32	pacing_gain:10,	/* current gain for setting pacing rate */
 		cwnd_gain:10,	/* current gain for setting cwnd */
-		full_bw_cnt:3,	/* number of rounds without large bw gains */
+		full_bw_reached:1,   /* reached full bw in Startup? */
+		full_bw_cnt:2,	/* number of rounds without large bw gains */
 		cycle_idx:3,	/* current index in pacing_gain cycle array */
 		has_seen_rtt:1, /* have we seen an RTT sample yet? */
 		unused_b:5;
@@ -180,7 +181,7 @@ static bool bbr_full_bw_reached(const struct sock *sk)
 {
 	const struct bbr *bbr = inet_csk_ca(sk);
 
-	return bbr->full_bw_cnt >= bbr_full_bw_cnt;
+	return bbr->full_bw_reached;
 }
 
 /* Return the windowed max recent bandwidth sample, in pkts/uS << BW_SCALE. */
@@ -717,6 +718,7 @@ static void bbr_check_full_bw_reached(struct sock *sk,
 		return;
 	}
 	++bbr->full_bw_cnt;
+	bbr->full_bw_reached = bbr->full_bw_cnt >= bbr_full_bw_cnt;
 }
 
 /* If pipe is probably full, drain the queue and then enter steady-state. */
@@ -850,6 +852,7 @@ static void bbr_init(struct sock *sk)
 	bbr->restore_cwnd = 0;
 	bbr->round_start = 0;
 	bbr->idle_restart = 0;
+	bbr->full_bw_reached = 0;
 	bbr->full_bw = 0;
 	bbr->full_bw_cnt = 0;
 	bbr->cycle_mstamp = 0;
-- 
2.9.5


From 9dd6bf837ae3224a4947f09fcb98f1971c387952 Mon Sep 17 00:00:00 2001
From: Christoph Paasch <cpaasch@apple.com>
Date: Mon, 11 Dec 2017 00:05:46 -0800
Subject: [PATCH 11/58] tcp md5sig: Use skb's saddr when replying to an
 incoming segment

[ Upstream commit 30791ac41927ebd3e75486f9504b6d2280463bf0 ]

The MD5-key that belongs to a connection is identified by the peer's
IP-address. When we are in tcp_v4(6)_reqsk_send_ack(), we are replying
to an incoming segment from tcp_check_req() that failed the seq-number
checks.

Thus, to find the correct key, we need to use the skb's saddr and not
the daddr.

This bug seems to have been there since quite a while, but probably got
unnoticed because the consequences are not catastrophic. We will call
tcp_v4_reqsk_send_ack only to send a challenge-ACK back to the peer,
thus the connection doesn't really fail.

Fixes: 9501f9722922 ("tcp md5sig: Let the caller pass appropriate key for tcp_v{4,6}_do_calc_md5_hash().")
Signed-off-by: Christoph Paasch <cpaasch@apple.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c | 2 +-
 net/ipv6/tcp_ipv6.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 5a5ed4f..cab4b93 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -844,7 +844,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
 			tcp_time_stamp_raw() + tcp_rsk(req)->ts_off,
 			req->ts_recent,
 			0,
-			tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr,
+			tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->saddr,
 					  AF_INET),
 			inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0,
 			ip_hdr(skb)->tos);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 32ded30..237cc61 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -988,7 +988,7 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
 			req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale,
 			tcp_time_stamp_raw() + tcp_rsk(req)->ts_off,
 			req->ts_recent, sk->sk_bound_dev_if,
-			tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr),
+			tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr),
 			0, 0);
 }
 
-- 
2.9.5


From b55cb405c0bc29e3072ef6438b3dd85c7458de1c Mon Sep 17 00:00:00 2001
From: Brian King <brking@linux.vnet.ibm.com>
Date: Fri, 15 Dec 2017 15:21:50 -0600
Subject: [PATCH 12/58] tg3: Fix rx hang on MTU change with 5717/5719

[ Upstream commit 748a240c589824e9121befb1cba5341c319885bc ]

This fixes a hang issue seen when changing the MTU size from 1500 MTU
to 9000 MTU on both 5717 and 5719 chips. In discussion with Broadcom,
they've indicated that these chipsets have the same phy as the 57766
chipset, so the same workarounds apply. This has been tested by IBM
on both Power 8 and Power 9 systems as well as by Broadcom on x86
hardware and has been confirmed to resolve the hang issue.

Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/tg3.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 656e6af..aef3fcf 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -14227,7 +14227,9 @@ static int tg3_change_mtu(struct net_device *dev, int new_mtu)
 	/* Reset PHY, otherwise the read DMA engine will be in a mode that
 	 * breaks all requests to 256 bytes.
 	 */
-	if (tg3_asic_rev(tp) == ASIC_REV_57766)
+	if (tg3_asic_rev(tp) == ASIC_REV_57766 ||
+	    tg3_asic_rev(tp) == ASIC_REV_5717 ||
+	    tg3_asic_rev(tp) == ASIC_REV_5719)
 		reset_phy = true;
 
 	err = tg3_restart_hw(tp, reset_phy);
-- 
2.9.5


From a133b66ce29509048c248321a5badb70ac54207b Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Thu, 7 Dec 2017 12:43:31 -0500
Subject: [PATCH 13/58] tcp_bbr: reset full pipe detection on loss recovery
 undo

[ Upstream commit 2f6c498e4f15d27852c04ed46d804a39137ba364 ]

Fix BBR so that upon notification of a loss recovery undo BBR resets
the full pipe detection (STARTUP exit) state machine.

Under high reordering, reordering events can be interpreted as loss.
If the reordering and spurious loss estimates are high enough, this
could previously cause BBR to spuriously estimate that the pipe is
full.

Since spurious loss recovery means that our overall sending will have
slowed down spuriously, this commit gives a flow more time to probe
robustly for bandwidth and decide the pipe is really full.

Signed-off-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_bbr.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 3089c95..ab3ff14 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -874,6 +874,10 @@ static u32 bbr_sndbuf_expand(struct sock *sk)
  */
 static u32 bbr_undo_cwnd(struct sock *sk)
 {
+	struct bbr *bbr = inet_csk_ca(sk);
+
+	bbr->full_bw = 0;   /* spurious slow-down; reset full pipe detection */
+	bbr->full_bw_cnt = 0;
 	return tcp_sk(sk)->snd_cwnd;
 }
 
-- 
2.9.5


From aab17abcea6a00f18e0dce976334e8ad0408bac6 Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Thu, 7 Dec 2017 12:43:32 -0500
Subject: [PATCH 14/58] tcp_bbr: reset long-term bandwidth sampling on loss
 recovery undo

[ Upstream commit 600647d467c6d04b3954b41a6ee1795b5ae00550 ]

Fix BBR so that upon notification of a loss recovery undo BBR resets
long-term bandwidth sampling.

Under high reordering, reordering events can be interpreted as loss.
If the reordering and spurious loss estimates are high enough, this
can cause BBR to spuriously estimate that we are seeing loss rates
high enough to trigger long-term bandwidth estimation. To avoid that
problem, this commit resets long-term bandwidth sampling on loss
recovery undo events.

Signed-off-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_bbr.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index ab3ff14..8322f26 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -878,6 +878,7 @@ static u32 bbr_undo_cwnd(struct sock *sk)
 
 	bbr->full_bw = 0;   /* spurious slow-down; reset full pipe detection */
 	bbr->full_bw_cnt = 0;
+	bbr_reset_lt_bw_sampling(sk);
 	return tcp_sk(sk)->snd_cwnd;
 }
 
-- 
2.9.5


From b06f679607b5510ff8a79f403be4c22af4bf6089 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Wed, 13 Dec 2017 18:56:29 +0100
Subject: [PATCH 15/58] s390/qeth: apply takeover changes when mode is toggled

[ Upstream commit 7fbd9493f0eeae8cef58300505a9ef5c8fce6313 ]

Just as for an explicit enable/disable, toggling the takeover mode also
requires that the IP addresses get updated. Otherwise all IPs that were
added to the table before the mode-toggle, get registered with the old
settings.

Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core.h      |  2 +-
 drivers/s390/net/qeth_core_main.c |  2 +-
 drivers/s390/net/qeth_l3_sys.c    | 35 +++++++++++++++++------------------
 3 files changed, 19 insertions(+), 20 deletions(-)

diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 5340efc..0a7bf3c 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -564,7 +564,7 @@ enum qeth_cq {
 };
 
 struct qeth_ipato {
-	int enabled;
+	bool enabled;
 	int invert4;
 	int invert6;
 	struct list_head entries;
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 330e5d3..be95f8c 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -1479,7 +1479,7 @@ static int qeth_setup_card(struct qeth_card *card)
 	qeth_set_intial_options(card);
 	/* IP address takeover */
 	INIT_LIST_HEAD(&card->ipato.entries);
-	card->ipato.enabled = 0;
+	card->ipato.enabled = false;
 	card->ipato.invert4 = 0;
 	card->ipato.invert6 = 0;
 	/* init QDIO stuff */
diff --git a/drivers/s390/net/qeth_l3_sys.c b/drivers/s390/net/qeth_l3_sys.c
index 7a829ad..30bfeb1 100644
--- a/drivers/s390/net/qeth_l3_sys.c
+++ b/drivers/s390/net/qeth_l3_sys.c
@@ -372,6 +372,7 @@ static ssize_t qeth_l3_dev_ipato_enable_store(struct device *dev,
 	struct qeth_card *card = dev_get_drvdata(dev);
 	struct qeth_ipaddr *addr;
 	int i, rc = 0;
+	bool enable;
 
 	if (!card)
 		return -EINVAL;
@@ -384,25 +385,23 @@ static ssize_t qeth_l3_dev_ipato_enable_store(struct device *dev,
 	}
 
 	if (sysfs_streq(buf, "toggle")) {
-		card->ipato.enabled = (card->ipato.enabled)? 0 : 1;
-	} else if (sysfs_streq(buf, "1")) {
-		card->ipato.enabled = 1;
-		hash_for_each(card->ip_htable, i, addr, hnode) {
-				if ((addr->type == QETH_IP_TYPE_NORMAL) &&
-				qeth_l3_is_addr_covered_by_ipato(card, addr))
-					addr->set_flags |=
-					QETH_IPA_SETIP_TAKEOVER_FLAG;
-			}
-	} else if (sysfs_streq(buf, "0")) {
-		card->ipato.enabled = 0;
-		hash_for_each(card->ip_htable, i, addr, hnode) {
-			if (addr->set_flags &
-			QETH_IPA_SETIP_TAKEOVER_FLAG)
-				addr->set_flags &=
-				~QETH_IPA_SETIP_TAKEOVER_FLAG;
-			}
-	} else
+		enable = !card->ipato.enabled;
+	} else if (kstrtobool(buf, &enable)) {
 		rc = -EINVAL;
+		goto out;
+	}
+
+	if (card->ipato.enabled == enable)
+		goto out;
+	card->ipato.enabled = enable;
+
+	hash_for_each(card->ip_htable, i, addr, hnode) {
+		if (!enable)
+			addr->set_flags &= ~QETH_IPA_SETIP_TAKEOVER_FLAG;
+		else if (addr->type == QETH_IP_TYPE_NORMAL &&
+			 qeth_l3_is_addr_covered_by_ipato(card, addr))
+			addr->set_flags |= QETH_IPA_SETIP_TAKEOVER_FLAG;
+	}
 out:
 	mutex_unlock(&card->conf_mutex);
 	return rc ? rc : count;
-- 
2.9.5


From 05ead7c062f4241602259330a12edc4b13d8bd9a Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Wed, 13 Dec 2017 18:56:30 +0100
Subject: [PATCH 16/58] s390/qeth: don't apply takeover changes to RXIP

[ Upstream commit b22d73d6689fd902a66c08ebe71ab2f3b351e22f ]

When takeover is switched off, current code clears the 'TAKEOVER' flag on
all IPs. But the flag is also used for RXIP addresses, and those should
not be affected by the takeover mode.
Fix the behaviour by consistenly applying takover logic to NORMAL
addresses only.

Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_l3_main.c | 5 +++--
 drivers/s390/net/qeth_l3_sys.c  | 5 +++--
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 27185ab..56d1c756 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -173,6 +173,8 @@ int qeth_l3_is_addr_covered_by_ipato(struct qeth_card *card,
 
 	if (!card->ipato.enabled)
 		return 0;
+	if (addr->type != QETH_IP_TYPE_NORMAL)
+		return 0;
 
 	qeth_l3_convert_addr_to_bits((u8 *) &addr->u, addr_bits,
 				  (addr->proto == QETH_PROT_IPV4)? 4:16);
@@ -289,8 +291,7 @@ int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
 		memcpy(addr, tmp_addr, sizeof(struct qeth_ipaddr));
 		addr->ref_counter = 1;
 
-		if (addr->type == QETH_IP_TYPE_NORMAL  &&
-				qeth_l3_is_addr_covered_by_ipato(card, addr)) {
+		if (qeth_l3_is_addr_covered_by_ipato(card, addr)) {
 			QETH_CARD_TEXT(card, 2, "tkovaddr");
 			addr->set_flags |= QETH_IPA_SETIP_TAKEOVER_FLAG;
 		}
diff --git a/drivers/s390/net/qeth_l3_sys.c b/drivers/s390/net/qeth_l3_sys.c
index 30bfeb1..aada072 100644
--- a/drivers/s390/net/qeth_l3_sys.c
+++ b/drivers/s390/net/qeth_l3_sys.c
@@ -396,10 +396,11 @@ static ssize_t qeth_l3_dev_ipato_enable_store(struct device *dev,
 	card->ipato.enabled = enable;
 
 	hash_for_each(card->ip_htable, i, addr, hnode) {
+		if (addr->type != QETH_IP_TYPE_NORMAL)
+			continue;
 		if (!enable)
 			addr->set_flags &= ~QETH_IPA_SETIP_TAKEOVER_FLAG;
-		else if (addr->type == QETH_IP_TYPE_NORMAL &&
-			 qeth_l3_is_addr_covered_by_ipato(card, addr))
+		else if (qeth_l3_is_addr_covered_by_ipato(card, addr))
 			addr->set_flags |= QETH_IPA_SETIP_TAKEOVER_FLAG;
 	}
 out:
-- 
2.9.5


From f5ac7ab1810fa6d614b0439a43fd62ec6dc58f74 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Wed, 13 Dec 2017 18:56:31 +0100
Subject: [PATCH 17/58] s390/qeth: lock IP table while applying takeover
 changes

[ Upstream commit 8a03a3692b100d84785ee7a834e9215e304c9e00 ]

Modifying the flags of an IP addr object needs to be protected against
eg. concurrent removal of the same object from the IP table.

Fixes: 5f78e29ceebf ("qeth: optimize IP handling in rx_mode callback")
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_l3_sys.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/s390/net/qeth_l3_sys.c b/drivers/s390/net/qeth_l3_sys.c
index aada072..a263483 100644
--- a/drivers/s390/net/qeth_l3_sys.c
+++ b/drivers/s390/net/qeth_l3_sys.c
@@ -395,6 +395,7 @@ static ssize_t qeth_l3_dev_ipato_enable_store(struct device *dev,
 		goto out;
 	card->ipato.enabled = enable;
 
+	spin_lock_bh(&card->ip_lock);
 	hash_for_each(card->ip_htable, i, addr, hnode) {
 		if (addr->type != QETH_IP_TYPE_NORMAL)
 			continue;
@@ -403,6 +404,7 @@ static ssize_t qeth_l3_dev_ipato_enable_store(struct device *dev,
 		else if (qeth_l3_is_addr_covered_by_ipato(card, addr))
 			addr->set_flags |= QETH_IPA_SETIP_TAKEOVER_FLAG;
 	}
+	spin_unlock_bh(&card->ip_lock);
 out:
 	mutex_unlock(&card->conf_mutex);
 	return rc ? rc : count;
-- 
2.9.5


From 24ba3e68a9e5e5b9e885bf89d5507a2177008a0a Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Wed, 13 Dec 2017 18:56:32 +0100
Subject: [PATCH 18/58] s390/qeth: update takeover IPs after configuration
 change

[ Upstream commit 02f510f326501470348a5df341e8232c3497bbbb ]

Any modification to the takeover IP-ranges requires that we re-evaluate
which IP addresses are takeover-eligible. Otherwise we might do takeover
for some addresses when we no longer should, or vice-versa.

Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core.h      |  4 +--
 drivers/s390/net/qeth_core_main.c |  4 +--
 drivers/s390/net/qeth_l3.h        |  2 +-
 drivers/s390/net/qeth_l3_main.c   | 31 +++++++++++++++++--
 drivers/s390/net/qeth_l3_sys.c    | 63 +++++++++++++++++++++------------------
 5 files changed, 67 insertions(+), 37 deletions(-)

diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 0a7bf3c..92dd4ae 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -565,8 +565,8 @@ enum qeth_cq {
 
 struct qeth_ipato {
 	bool enabled;
-	int invert4;
-	int invert6;
+	bool invert4;
+	bool invert6;
 	struct list_head entries;
 };
 
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index be95f8c..291eb89 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -1480,8 +1480,8 @@ static int qeth_setup_card(struct qeth_card *card)
 	/* IP address takeover */
 	INIT_LIST_HEAD(&card->ipato.entries);
 	card->ipato.enabled = false;
-	card->ipato.invert4 = 0;
-	card->ipato.invert6 = 0;
+	card->ipato.invert4 = false;
+	card->ipato.invert6 = false;
 	/* init QDIO stuff */
 	qeth_init_qdio_info(card);
 	INIT_DELAYED_WORK(&card->buffer_reclaim_work, qeth_buffer_reclaim_work);
diff --git a/drivers/s390/net/qeth_l3.h b/drivers/s390/net/qeth_l3.h
index 194ae9b..e583383 100644
--- a/drivers/s390/net/qeth_l3.h
+++ b/drivers/s390/net/qeth_l3.h
@@ -82,7 +82,7 @@ void qeth_l3_del_vipa(struct qeth_card *, enum qeth_prot_versions, const u8 *);
 int qeth_l3_add_rxip(struct qeth_card *, enum qeth_prot_versions, const u8 *);
 void qeth_l3_del_rxip(struct qeth_card *card, enum qeth_prot_versions,
 			const u8 *);
-int qeth_l3_is_addr_covered_by_ipato(struct qeth_card *, struct qeth_ipaddr *);
+void qeth_l3_update_ipato(struct qeth_card *card);
 struct qeth_ipaddr *qeth_l3_get_addr_buffer(enum qeth_prot_versions);
 int qeth_l3_add_ip(struct qeth_card *, struct qeth_ipaddr *);
 int qeth_l3_delete_ip(struct qeth_card *, struct qeth_ipaddr *);
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 56d1c756..36dee17 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -163,8 +163,8 @@ static void qeth_l3_convert_addr_to_bits(u8 *addr, u8 *bits, int len)
 	}
 }
 
-int qeth_l3_is_addr_covered_by_ipato(struct qeth_card *card,
-						struct qeth_ipaddr *addr)
+static bool qeth_l3_is_addr_covered_by_ipato(struct qeth_card *card,
+					     struct qeth_ipaddr *addr)
 {
 	struct qeth_ipato_entry *ipatoe;
 	u8 addr_bits[128] = {0, };
@@ -605,6 +605,27 @@ int qeth_l3_setrouting_v6(struct qeth_card *card)
 /*
  * IP address takeover related functions
  */
+
+/**
+ * qeth_l3_update_ipato() - Update 'takeover' property, for all NORMAL IPs.
+ *
+ * Caller must hold ip_lock.
+ */
+void qeth_l3_update_ipato(struct qeth_card *card)
+{
+	struct qeth_ipaddr *addr;
+	unsigned int i;
+
+	hash_for_each(card->ip_htable, i, addr, hnode) {
+		if (addr->type != QETH_IP_TYPE_NORMAL)
+			continue;
+		if (qeth_l3_is_addr_covered_by_ipato(card, addr))
+			addr->set_flags |= QETH_IPA_SETIP_TAKEOVER_FLAG;
+		else
+			addr->set_flags &= ~QETH_IPA_SETIP_TAKEOVER_FLAG;
+	}
+}
+
 static void qeth_l3_clear_ipato_list(struct qeth_card *card)
 {
 	struct qeth_ipato_entry *ipatoe, *tmp;
@@ -616,6 +637,7 @@ static void qeth_l3_clear_ipato_list(struct qeth_card *card)
 		kfree(ipatoe);
 	}
 
+	qeth_l3_update_ipato(card);
 	spin_unlock_bh(&card->ip_lock);
 }
 
@@ -640,8 +662,10 @@ int qeth_l3_add_ipato_entry(struct qeth_card *card,
 		}
 	}
 
-	if (!rc)
+	if (!rc) {
 		list_add_tail(&new->entry, &card->ipato.entries);
+		qeth_l3_update_ipato(card);
+	}
 
 	spin_unlock_bh(&card->ip_lock);
 
@@ -664,6 +688,7 @@ void qeth_l3_del_ipato_entry(struct qeth_card *card,
 			    (proto == QETH_PROT_IPV4)? 4:16) &&
 		    (ipatoe->mask_bits == mask_bits)) {
 			list_del(&ipatoe->entry);
+			qeth_l3_update_ipato(card);
 			kfree(ipatoe);
 		}
 	}
diff --git a/drivers/s390/net/qeth_l3_sys.c b/drivers/s390/net/qeth_l3_sys.c
index a263483..1295dd8 100644
--- a/drivers/s390/net/qeth_l3_sys.c
+++ b/drivers/s390/net/qeth_l3_sys.c
@@ -370,9 +370,8 @@ static ssize_t qeth_l3_dev_ipato_enable_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t count)
 {
 	struct qeth_card *card = dev_get_drvdata(dev);
-	struct qeth_ipaddr *addr;
-	int i, rc = 0;
 	bool enable;
+	int rc = 0;
 
 	if (!card)
 		return -EINVAL;
@@ -391,20 +390,12 @@ static ssize_t qeth_l3_dev_ipato_enable_store(struct device *dev,
 		goto out;
 	}
 
-	if (card->ipato.enabled == enable)
-		goto out;
-	card->ipato.enabled = enable;
-
-	spin_lock_bh(&card->ip_lock);
-	hash_for_each(card->ip_htable, i, addr, hnode) {
-		if (addr->type != QETH_IP_TYPE_NORMAL)
-			continue;
-		if (!enable)
-			addr->set_flags &= ~QETH_IPA_SETIP_TAKEOVER_FLAG;
-		else if (qeth_l3_is_addr_covered_by_ipato(card, addr))
-			addr->set_flags |= QETH_IPA_SETIP_TAKEOVER_FLAG;
+	if (card->ipato.enabled != enable) {
+		card->ipato.enabled = enable;
+		spin_lock_bh(&card->ip_lock);
+		qeth_l3_update_ipato(card);
+		spin_unlock_bh(&card->ip_lock);
 	}
-	spin_unlock_bh(&card->ip_lock);
 out:
 	mutex_unlock(&card->conf_mutex);
 	return rc ? rc : count;
@@ -430,20 +421,27 @@ static ssize_t qeth_l3_dev_ipato_invert4_store(struct device *dev,
 				const char *buf, size_t count)
 {
 	struct qeth_card *card = dev_get_drvdata(dev);
+	bool invert;
 	int rc = 0;
 
 	if (!card)
 		return -EINVAL;
 
 	mutex_lock(&card->conf_mutex);
-	if (sysfs_streq(buf, "toggle"))
-		card->ipato.invert4 = (card->ipato.invert4)? 0 : 1;
-	else if (sysfs_streq(buf, "1"))
-		card->ipato.invert4 = 1;
-	else if (sysfs_streq(buf, "0"))
-		card->ipato.invert4 = 0;
-	else
+	if (sysfs_streq(buf, "toggle")) {
+		invert = !card->ipato.invert4;
+	} else if (kstrtobool(buf, &invert)) {
 		rc = -EINVAL;
+		goto out;
+	}
+
+	if (card->ipato.invert4 != invert) {
+		card->ipato.invert4 = invert;
+		spin_lock_bh(&card->ip_lock);
+		qeth_l3_update_ipato(card);
+		spin_unlock_bh(&card->ip_lock);
+	}
+out:
 	mutex_unlock(&card->conf_mutex);
 	return rc ? rc : count;
 }
@@ -609,20 +607,27 @@ static ssize_t qeth_l3_dev_ipato_invert6_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t count)
 {
 	struct qeth_card *card = dev_get_drvdata(dev);
+	bool invert;
 	int rc = 0;
 
 	if (!card)
 		return -EINVAL;
 
 	mutex_lock(&card->conf_mutex);
-	if (sysfs_streq(buf, "toggle"))
-		card->ipato.invert6 = (card->ipato.invert6)? 0 : 1;
-	else if (sysfs_streq(buf, "1"))
-		card->ipato.invert6 = 1;
-	else if (sysfs_streq(buf, "0"))
-		card->ipato.invert6 = 0;
-	else
+	if (sysfs_streq(buf, "toggle")) {
+		invert = !card->ipato.invert6;
+	} else if (kstrtobool(buf, &invert)) {
 		rc = -EINVAL;
+		goto out;
+	}
+
+	if (card->ipato.invert6 != invert) {
+		card->ipato.invert6 = invert;
+		spin_lock_bh(&card->ip_lock);
+		qeth_l3_update_ipato(card);
+		spin_unlock_bh(&card->ip_lock);
+	}
+out:
 	mutex_unlock(&card->conf_mutex);
 	return rc ? rc : count;
 }
-- 
2.9.5


From 0c4c1b887aa795d3e8647bf9a2965f37334c3eb7 Mon Sep 17 00:00:00 2001
From: Mohamed Ghannam <simo.ghannam@gmail.com>
Date: Sun, 10 Dec 2017 03:50:58 +0000
Subject: [PATCH 19/58] net: ipv4: fix for a race condition in raw_sendmsg

[ Upstream commit 8f659a03a0ba9289b9aeb9b4470e6fb263d6f483 ]

inet->hdrincl is racy, and could lead to uninitialized stack pointer
usage, so its value should be read only once.

Fixes: c008ba5bdc9f ("ipv4: Avoid reading user iov twice after raw_probe_proto_opt")
Signed-off-by: Mohamed Ghannam <simo.ghannam@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/raw.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 33b70bf..125c1ea 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -513,11 +513,16 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	int err;
 	struct ip_options_data opt_copy;
 	struct raw_frag_vec rfv;
+	int hdrincl;
 
 	err = -EMSGSIZE;
 	if (len > 0xFFFF)
 		goto out;
 
+	/* hdrincl should be READ_ONCE(inet->hdrincl)
+	 * but READ_ONCE() doesn't work with bit fields
+	 */
+	hdrincl = inet->hdrincl;
 	/*
 	 *	Check the flags.
 	 */
@@ -593,7 +598,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		/* Linux does not mangle headers on raw sockets,
 		 * so that IP options + IP_HDRINCL is non-sense.
 		 */
-		if (inet->hdrincl)
+		if (hdrincl)
 			goto done;
 		if (ipc.opt->opt.srr) {
 			if (!daddr)
@@ -615,12 +620,12 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos,
 			   RT_SCOPE_UNIVERSE,
-			   inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
+			   hdrincl ? IPPROTO_RAW : sk->sk_protocol,
 			   inet_sk_flowi_flags(sk) |
-			    (inet->hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
+			    (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
 			   daddr, saddr, 0, 0, sk->sk_uid);
 
-	if (!inet->hdrincl) {
+	if (!hdrincl) {
 		rfv.msg = msg;
 		rfv.hlen = 0;
 
@@ -645,7 +650,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		goto do_confirm;
 back_from_confirm:
 
-	if (inet->hdrincl)
+	if (hdrincl)
 		err = raw_send_hdrinc(sk, &fl4, msg, len,
 				      &rt, msg->msg_flags, &ipc.sockc);
 
-- 
2.9.5


From 8d5c51149b7d493bd872cafac5e887f55cacb5ba Mon Sep 17 00:00:00 2001
From: Tobias Jordan <Tobias.Jordan@elektrobit.com>
Date: Wed, 6 Dec 2017 15:23:23 +0100
Subject: [PATCH 20/58] net: mvmdio: disable/unprepare clocks in EPROBE_DEFER
 case

[ Upstream commit 589bf32f09852041fbd3b7ce1a9e703f95c230ba ]

add appropriate calls to clk_disable_unprepare() by jumping to out_mdio
in case orion_mdio_probe() returns -EPROBE_DEFER.

Found by Linux Driver Verification project (linuxtesting.org).

Fixes: 3d604da1e954 ("net: mvmdio: get and enable optional clock")
Signed-off-by: Tobias Jordan <Tobias.Jordan@elektrobit.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvmdio.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c
index c979821..0495487 100644
--- a/drivers/net/ethernet/marvell/mvmdio.c
+++ b/drivers/net/ethernet/marvell/mvmdio.c
@@ -344,7 +344,8 @@ static int orion_mdio_probe(struct platform_device *pdev)
 			dev->regs + MVMDIO_ERR_INT_MASK);
 
 	} else if (dev->err_interrupt == -EPROBE_DEFER) {
-		return -EPROBE_DEFER;
+		ret = -EPROBE_DEFER;
+		goto out_mdio;
 	}
 
 	if (pdev->dev.of_node)
-- 
2.9.5


From 878f664032572ebad084fab4c4ee6baa1b7c526e Mon Sep 17 00:00:00 2001
From: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Date: Fri, 22 Dec 2017 10:15:20 -0800
Subject: [PATCH 21/58] sctp: Replace use of sockets_allocated with specified
 macro.

[ Upstream commit 8cb38a602478e9f806571f6920b0a3298aabf042 ]

The patch(180d8cd942ce) replaces all uses of struct sock fields'
memory_pressure, memory_allocated, sockets_allocated, and sysctl_mem
to accessor macros. But the sockets_allocated field of sctp sock is
not replaced at all. Then replace it now for unifying the code.

Fixes: 180d8cd942ce ("foundations of per-cgroup memory pressure controlling.")
Cc: Glauber Costa <glommer@parallels.com>
Signed-off-by: Tonghao Zhang <zhangtonghao@didichuxing.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index d6163f7..1977238 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4413,7 +4413,7 @@ static int sctp_init_sock(struct sock *sk)
 	SCTP_DBG_OBJCNT_INC(sock);
 
 	local_bh_disable();
-	percpu_counter_inc(&sctp_sockets_allocated);
+	sk_sockets_allocated_inc(sk);
 	sock_prot_inuse_add(net, sk->sk_prot, 1);
 
 	/* Nothing can fail after this block, otherwise
@@ -4457,7 +4457,7 @@ static void sctp_destroy_sock(struct sock *sk)
 	}
 	sctp_endpoint_free(sp->ep);
 	local_bh_disable();
-	percpu_counter_dec(&sctp_sockets_allocated);
+	sk_sockets_allocated_dec(sk);
 	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
 	local_bh_enable();
 }
-- 
2.9.5


From 8b491845a3110929185437de3852be2da1142e32 Mon Sep 17 00:00:00 2001
From: "Nikita V. Shirokov" <tehnerd@fb.com>
Date: Wed, 6 Dec 2017 17:15:43 -0800
Subject: [PATCH 22/58] adding missing rcu_read_unlock in ipxip6_rcv

[ Upstream commit 74c4b656c3d92ec4c824ea1a4afd726b7b6568c8 ]

commit 8d79266bc48c ("ip6_tunnel: add collect_md mode to IPv6 tunnels")
introduced new exit point in  ipxip6_rcv. however rcu_read_unlock is
missing there. this diff is fixing this

v1->v2:
 instead of doing rcu_read_unlock in place, we are going to "drop"
 section (to prevent skb leakage)

Fixes: 8d79266bc48c ("ip6_tunnel: add collect_md mode to IPv6 tunnels")
Signed-off-by: Nikita V. Shirokov <tehnerd@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index a1c2444..ef958d5 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -912,7 +912,7 @@ static int ipxip6_rcv(struct sk_buff *skb, u8 ipproto,
 		if (t->parms.collect_md) {
 			tun_dst = ipv6_tun_rx_dst(skb, 0, 0, 0);
 			if (!tun_dst)
-				return 0;
+				goto drop;
 		}
 		ret = __ip6_tnl_rcv(t, skb, tpi, tun_dst, dscp_ecn_decapsulate,
 				    log_ecn_error);
-- 
2.9.5


From 538f95493bd6624042072d21f88283796cceb927 Mon Sep 17 00:00:00 2001
From: Alexey Kodanev <alexey.kodanev@oracle.com>
Date: Wed, 20 Dec 2017 19:36:03 +0300
Subject: [PATCH 23/58] ip6_gre: fix device features for ioctl setup

[ Upstream commit e5a9336adb317db55eb3fe8200856096f3c71109 ]

When ip6gre is created using ioctl, its features, such as
scatter-gather, GSO and tx-checksumming will be turned off:

  # ip -f inet6 tunnel add gre6 mode ip6gre remote fd00::1
  # ethtool -k gre6 (truncated output)
    tx-checksumming: off
    scatter-gather: off
    tcp-segmentation-offload: off
    generic-segmentation-offload: off [requested on]

But when netlink is used, they will be enabled:
  # ip link add gre6 type ip6gre remote fd00::1
  # ethtool -k gre6 (truncated output)
    tx-checksumming: on
    scatter-gather: on
    tcp-segmentation-offload: on
    generic-segmentation-offload: on

This results in a loss of performance when gre6 is created via ioctl.
The issue was found with LTP/gre tests.

Fix it by moving the setup of device features to a separate function
and invoke it with ndo_init callback because both netlink and ioctl
will eventually call it via register_netdevice():

   register_netdevice()
       - ndo_init() callback -> ip6gre_tunnel_init() or ip6gre_tap_init()
           - ip6gre_tunnel_init_common()
                - ip6gre_tnl_init_features()

The moved code also contains two minor style fixes:
  * removed needless tab from GRE6_FEATURES on NETIF_F_HIGHDMA line.
  * fixed the issue reported by checkpatch: "Unnecessary parentheses around
    'nt->encap.type == TUNNEL_ENCAP_NONE'"

Fixes: ac4eb009e477 ("ip6gre: Add support for basic offloads offloads excluding GSO")
Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 57 ++++++++++++++++++++++++++++++------------------------
 1 file changed, 32 insertions(+), 25 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 5d6bee0..7a2df66 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1020,6 +1020,36 @@ static void ip6gre_tunnel_setup(struct net_device *dev)
 	eth_random_addr(dev->perm_addr);
 }
 
+#define GRE6_FEATURES (NETIF_F_SG |		\
+		       NETIF_F_FRAGLIST |	\
+		       NETIF_F_HIGHDMA |	\
+		       NETIF_F_HW_CSUM)
+
+static void ip6gre_tnl_init_features(struct net_device *dev)
+{
+	struct ip6_tnl *nt = netdev_priv(dev);
+
+	dev->features		|= GRE6_FEATURES;
+	dev->hw_features	|= GRE6_FEATURES;
+
+	if (!(nt->parms.o_flags & TUNNEL_SEQ)) {
+		/* TCP offload with GRE SEQ is not supported, nor
+		 * can we support 2 levels of outer headers requiring
+		 * an update.
+		 */
+		if (!(nt->parms.o_flags & TUNNEL_CSUM) ||
+		    nt->encap.type == TUNNEL_ENCAP_NONE) {
+			dev->features    |= NETIF_F_GSO_SOFTWARE;
+			dev->hw_features |= NETIF_F_GSO_SOFTWARE;
+		}
+
+		/* Can use a lockless transmit, unless we generate
+		 * output sequences
+		 */
+		dev->features |= NETIF_F_LLTX;
+	}
+}
+
 static int ip6gre_tunnel_init_common(struct net_device *dev)
 {
 	struct ip6_tnl *tunnel;
@@ -1054,6 +1084,8 @@ static int ip6gre_tunnel_init_common(struct net_device *dev)
 	if (!(tunnel->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
 		dev->mtu -= 8;
 
+	ip6gre_tnl_init_features(dev);
+
 	return 0;
 }
 
@@ -1302,11 +1334,6 @@ static const struct net_device_ops ip6gre_tap_netdev_ops = {
 	.ndo_get_iflink = ip6_tnl_get_iflink,
 };
 
-#define GRE6_FEATURES (NETIF_F_SG |		\
-		       NETIF_F_FRAGLIST |	\
-		       NETIF_F_HIGHDMA |		\
-		       NETIF_F_HW_CSUM)
-
 static void ip6gre_tap_setup(struct net_device *dev)
 {
 
@@ -1386,26 +1413,6 @@ static int ip6gre_newlink(struct net *src_net, struct net_device *dev,
 	nt->net = dev_net(dev);
 	ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]);
 
-	dev->features		|= GRE6_FEATURES;
-	dev->hw_features	|= GRE6_FEATURES;
-
-	if (!(nt->parms.o_flags & TUNNEL_SEQ)) {
-		/* TCP offload with GRE SEQ is not supported, nor
-		 * can we support 2 levels of outer headers requiring
-		 * an update.
-		 */
-		if (!(nt->parms.o_flags & TUNNEL_CSUM) ||
-		    (nt->encap.type == TUNNEL_ENCAP_NONE)) {
-			dev->features    |= NETIF_F_GSO_SOFTWARE;
-			dev->hw_features |= NETIF_F_GSO_SOFTWARE;
-		}
-
-		/* Can use a lockless transmit, unless we generate
-		 * output sequences
-		 */
-		dev->features |= NETIF_F_LLTX;
-	}
-
 	err = register_netdevice(dev);
 	if (err)
 		goto out;
-- 
2.9.5


From 2d5889468f907ec4a9205dbcc9b1cc56cce160d8 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 20 Dec 2017 19:34:19 +0200
Subject: [PATCH 24/58] ipv4: Fix use-after-free when flushing FIB tables

[ Upstream commit b4681c2829e24943aadd1a7bb3a30d41d0a20050 ]

Since commit 0ddcf43d5d4a ("ipv4: FIB Local/MAIN table collapse") the
local table uses the same trie allocated for the main table when custom
rules are not in use.

When a net namespace is dismantled, the main table is flushed and freed
(via an RCU callback) before the local table. In case the callback is
invoked before the local table is iterated, a use-after-free can occur.

Fix this by iterating over the FIB tables in reverse order, so that the
main table is always freed after the local table.

v3: Reworded comment according to Alex's suggestion.
v2: Add a comment to make the fix more explicit per Dave's and Alex's
feedback.

Fixes: 0ddcf43d5d4a ("ipv4: FIB Local/MAIN table collapse")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Acked-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_frontend.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 37819ab..d728741 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1274,14 +1274,19 @@ static int __net_init ip_fib_net_init(struct net *net)
 
 static void ip_fib_net_exit(struct net *net)
 {
-	unsigned int i;
+	int i;
 
 	rtnl_lock();
 #ifdef CONFIG_IP_MULTIPLE_TABLES
 	RCU_INIT_POINTER(net->ipv4.fib_main, NULL);
 	RCU_INIT_POINTER(net->ipv4.fib_default, NULL);
 #endif
-	for (i = 0; i < FIB_TABLE_HASHSZ; i++) {
+	/* Destroy the tables in reverse order to guarantee that the
+	 * local table, ID 255, is destroyed before the main table, ID
+	 * 254. This is necessary as the local table may contain
+	 * references to data contained in the main table.
+	 */
+	for (i = FIB_TABLE_HASHSZ - 1; i >= 0; i--) {
 		struct hlist_head *head = &net->ipv4.fib_table_hash[i];
 		struct hlist_node *tmp;
 		struct fib_table *tb;
-- 
2.9.5


From 33cd66681a508fa5a5e06cf505c7e3deeb1c1826 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Mon, 18 Dec 2017 17:35:09 +0200
Subject: [PATCH 25/58] net: bridge: fix early call to br_stp_change_bridge_id
 and plug newlink leaks

[ Upstream commit 84aeb437ab98a2bce3d4b2111c79723aedfceb33 ]

The early call to br_stp_change_bridge_id in bridge's newlink can cause
a memory leak if an error occurs during the newlink because the fdb
entries are not cleaned up if a different lladdr was specified, also
another minor issue is that it generates fdb notifications with
ifindex = 0. Another unrelated memory leak is the bridge sysfs entries
which get added on NETDEV_REGISTER event, but are not cleaned up in the
newlink error path. To remove this special case the call to
br_stp_change_bridge_id is done after netdev register and we cleanup the
bridge on changelink error via br_dev_delete to plug all leaks.

This patch makes netlink bridge destruction on newlink error the same as
dellink and ioctl del which is necessary since at that point we have a
fully initialized bridge device.

To reproduce the issue:
$ ip l add br0 address 00:11:22:33:44:55 type bridge group_fwd_mask 1
RTNETLINK answers: Invalid argument

$ rmmod bridge
[ 1822.142525] =============================================================================
[ 1822.143640] BUG bridge_fdb_cache (Tainted: G           O    ): Objects remaining in bridge_fdb_cache on __kmem_cache_shutdown()
[ 1822.144821] -----------------------------------------------------------------------------

[ 1822.145990] Disabling lock debugging due to kernel taint
[ 1822.146732] INFO: Slab 0x0000000092a844b2 objects=32 used=2 fp=0x00000000fef011b0 flags=0x1ffff8000000100
[ 1822.147700] CPU: 2 PID: 13584 Comm: rmmod Tainted: G    B      O     4.15.0-rc2+ #87
[ 1822.148578] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.7.5-20140531_083030-gandalf 04/01/2014
[ 1822.150008] Call Trace:
[ 1822.150510]  dump_stack+0x78/0xa9
[ 1822.151156]  slab_err+0xb1/0xd3
[ 1822.151834]  ? __kmalloc+0x1bb/0x1ce
[ 1822.152546]  __kmem_cache_shutdown+0x151/0x28b
[ 1822.153395]  shutdown_cache+0x13/0x144
[ 1822.154126]  kmem_cache_destroy+0x1c0/0x1fb
[ 1822.154669]  SyS_delete_module+0x194/0x244
[ 1822.155199]  ? trace_hardirqs_on_thunk+0x1a/0x1c
[ 1822.155773]  entry_SYSCALL_64_fastpath+0x23/0x9a
[ 1822.156343] RIP: 0033:0x7f929bd38b17
[ 1822.156859] RSP: 002b:00007ffd160e9a98 EFLAGS: 00000202 ORIG_RAX: 00000000000000b0
[ 1822.157728] RAX: ffffffffffffffda RBX: 00005578316ba090 RCX: 00007f929bd38b17
[ 1822.158422] RDX: 00007f929bd9ec60 RSI: 0000000000000800 RDI: 00005578316ba0f0
[ 1822.159114] RBP: 0000000000000003 R08: 00007f929bff5f20 R09: 00007ffd160e8a11
[ 1822.159808] R10: 00007ffd160e9860 R11: 0000000000000202 R12: 00007ffd160e8a80
[ 1822.160513] R13: 0000000000000000 R14: 0000000000000000 R15: 00005578316ba090
[ 1822.161278] INFO: Object 0x000000007645de29 @offset=0
[ 1822.161666] INFO: Object 0x00000000d5df2ab5 @offset=128

Fixes: 30313a3d5794 ("bridge: Handle IFLA_ADDRESS correctly when creating bridge device")
Fixes: 5b8d5429daa0 ("bridge: netlink: register netdevice before executing changelink")
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_netlink.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index de21527..08190db 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -1223,19 +1223,20 @@ static int br_dev_newlink(struct net *src_net, struct net_device *dev,
 	struct net_bridge *br = netdev_priv(dev);
 	int err;
 
+	err = register_netdevice(dev);
+	if (err)
+		return err;
+
 	if (tb[IFLA_ADDRESS]) {
 		spin_lock_bh(&br->lock);
 		br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS]));
 		spin_unlock_bh(&br->lock);
 	}
 
-	err = register_netdevice(dev);
-	if (err)
-		return err;
-
 	err = br_changelink(dev, tb, data, extack);
 	if (err)
-		unregister_netdevice(dev);
+		br_dev_delete(dev, NULL);
+
 	return err;
 }
 
-- 
2.9.5


From 7d3e470bf0213f2390a8b021fb28dca049290632 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Tue, 19 Dec 2017 11:27:56 -0600
Subject: [PATCH 26/58] net: Fix double free and memory corruption in
 get_net_ns_by_id()

[ Upstream commit 21b5944350052d2583e82dd59b19a9ba94a007f0 ]

(I can trivially verify that that idr_remove in cleanup_net happens
 after the network namespace count has dropped to zero --EWB)

Function get_net_ns_by_id() does not check for net::count
after it has found a peer in netns_ids idr.

It may dereference a peer, after its count has already been
finaly decremented. This leads to double free and memory
corruption:

put_net(peer)                                   rtnl_lock()
atomic_dec_and_test(&peer->count) [count=0]     ...
__put_net(peer)                                 get_net_ns_by_id(net, id)
  spin_lock(&cleanup_list_lock)
  list_add(&net->cleanup_list, &cleanup_list)
  spin_unlock(&cleanup_list_lock)
queue_work()                                      peer = idr_find(&net->netns_ids, id)
  |                                               get_net(peer) [count=1]
  |                                               ...
  |                                               (use after final put)
  v                                               ...
  cleanup_net()                                   ...
    spin_lock(&cleanup_list_lock)                 ...
    list_replace_init(&cleanup_list, ..)          ...
    spin_unlock(&cleanup_list_lock)               ...
    ...                                           ...
    ...                                           put_net(peer)
    ...                                             atomic_dec_and_test(&peer->count) [count=0]
    ...                                               spin_lock(&cleanup_list_lock)
    ...                                               list_add(&net->cleanup_list, &cleanup_list)
    ...                                               spin_unlock(&cleanup_list_lock)
    ...                                             queue_work()
    ...                                           rtnl_unlock()
    rtnl_lock()                                   ...
    for_each_net(tmp) {                           ...
      id = __peernet2id(tmp, peer)                ...
      spin_lock_irq(&tmp->nsid_lock)              ...
      idr_remove(&tmp->netns_ids, id)             ...
      ...                                         ...
      net_drop_ns()                               ...
	net_free(peer)                            ...
    }                                             ...
  |
  v
  cleanup_net()
    ...
    (Second free of peer)

Also, put_net() on the right cpu may reorder with left's cpu
list_replace_init(&cleanup_list, ..), and then cleanup_list
will be corrupted.

Since cleanup_net() is executed in worker thread, while
put_net(peer) can happen everywhere, there should be
enough time for concurrent get_net_ns_by_id() to pick
the peer up, and the race does not seem to be unlikely.
The patch fixes the problem in standard way.

(Also, there is possible problem in peernet2id_alloc(), which requires
check for net::count under nsid_lock and maybe_get_net(peer), but
in current stable kernel it's used under rtnl_lock() and it has to be
safe. Openswitch begun to use peernet2id_alloc(), and possibly it should
be fixed too. While this is not in stable kernel yet, so I'll send
a separate message to netdev@ later).

Cc: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Fixes: 0c7aecd4bde4 "netns: add rtnl cmd to add and get peer netns ids"
Reviewed-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
Reviewed-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/net_namespace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 6cfdc7c..0dd6359 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -266,7 +266,7 @@ struct net *get_net_ns_by_id(struct net *net, int id)
 	spin_lock_bh(&net->nsid_lock);
 	peer = idr_find(&net->netns_ids, id);
 	if (peer)
-		get_net(peer);
+		peer = maybe_get_net(peer);
 	spin_unlock_bh(&net->nsid_lock);
 	rcu_read_unlock();
 
-- 
2.9.5


From 9c7f4f8e5455e211163a0afdfb78056515d528db Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Wed, 20 Dec 2017 18:45:10 -0600
Subject: [PATCH 27/58] net: phy: micrel: ksz9031: reconfigure autoneg after
 phy autoneg workaround

[ Upstream commit c1a8d0a3accf64a014d605e6806ce05d1c17adf1 ]

Under some circumstances driver will perform PHY reset in
ksz9031_read_status() to fix autoneg failure case (idle error count =
0xFF). When this happens ksz9031 will not detect link status change any
more when connecting to Netgear 1G switch (link can be recovered sometimes by
restarting netdevice "ifconfig down up"). Reproduced with TI am572x board
equipped with ksz9031 PHY while connecting to Netgear 1G switch.

Fix the issue by reconfiguring autonegotiation after PHY reset in
ksz9031_read_status().

Fixes: d2fd719bcb0e ("net/phy: micrel: Add workaround for bad autoneg")
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/micrel.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index fdb43dd..6c45ff6 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -622,6 +622,7 @@ static int ksz9031_read_status(struct phy_device *phydev)
 		phydev->link = 0;
 		if (phydev->drv->config_intr && phy_interrupt_is_valid(phydev))
 			phydev->drv->config_intr(phydev);
+		return genphy_config_aneg(phydev);
 	}
 
 	return 0;
-- 
2.9.5


From 471a03cff762c3802ff7c2be11781e885b9835ba Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 13 Dec 2017 14:41:06 -0500
Subject: [PATCH 28/58] sock: free skb in skb_complete_tx_timestamp on error

[ Upstream commit 35b99dffc3f710cafceee6c8c6ac6a98eb2cb4bf ]

skb_complete_tx_timestamp must ingest the skb it is passed. Call
kfree_skb if the skb cannot be enqueued.

Fixes: b245be1f4db1 ("net-timestamp: no-payload only sysctl")
Fixes: 9ac25fc06375 ("net: fix socket refcounting in skb_complete_tx_timestamp()")
Reported-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index e140ba4..623143d7 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4296,7 +4296,7 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
 	struct sock *sk = skb->sk;
 
 	if (!skb_may_tx_timestamp(sk, false))
-		return;
+		goto err;
 
 	/* Take a reference to prevent skb_orphan() from freeing the socket,
 	 * but only if the socket refcount is not zero.
@@ -4305,7 +4305,11 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
 		*skb_hwtstamps(skb) = *hwtstamps;
 		__skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND, false);
 		sock_put(sk);
+		return;
 	}
+
+err:
+	kfree_skb(skb);
 }
 EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp);
 
-- 
2.9.5


From f54906cd4856bdc4613c2d3fea0b69aff734a7c0 Mon Sep 17 00:00:00 2001
From: Yousuk Seung <ysseung@google.com>
Date: Thu, 7 Dec 2017 13:41:34 -0800
Subject: [PATCH 29/58] tcp: invalidate rate samples during SACK reneging

[ Upstream commit d4761754b4fb2ef8d9a1e9d121c4bec84e1fe292 ]

Mark tcp_sock during a SACK reneging event and invalidate rate samples
while marked. Such rate samples may overestimate bw by including packets
that were SACKed before reneging.

< ack 6001 win 10000 sack 7001:38001
< ack 7001 win 0 sack 8001:38001 // Reneg detected
> seq 7001:8001 // RTO, SACK cleared.
< ack 38001 win 10000

In above example the rate sample taken after the last ack will count
7001-38001 as delivered while the actual delivery rate likely could
be much lower i.e. 7001-8001.

This patch adds a new field tcp_sock.sack_reneg and marks it when we
declare SACK reneging and entering TCP_CA_Loss, and unmarks it after
the last rate sample was taken before moving back to TCP_CA_Open. This
patch also invalidates rate samples taken while tcp_sock.is_sack_reneg
is set.

Fixes: b9f64820fb22 ("tcp: track data delivery rate for a TCP connection")
Signed-off-by: Yousuk Seung <ysseung@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Priyaranjan Jha <priyarjha@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h  |  3 ++-
 include/net/tcp.h    |  2 +-
 net/ipv4/tcp.c       |  1 +
 net/ipv4/tcp_input.c | 10 ++++++++--
 net/ipv4/tcp_rate.c  | 10 +++++++---
 5 files changed, 19 insertions(+), 7 deletions(-)

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 4aa40ef..e8418fc 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -214,7 +214,8 @@ struct tcp_sock {
 	u8	chrono_type:2,	/* current chronograph type */
 		rate_app_limited:1,  /* rate_{delivered,interval_us} limited? */
 		fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */
-		unused:4;
+		is_sack_reneg:1,    /* in recovery from loss with SACK reneg? */
+		unused:3;
 	u8	nonagle     : 4,/* Disable Nagle algorithm?             */
 		thin_lto    : 1,/* Use linear timeouts for thin streams */
 		unused1	    : 1,
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 6ced699..0a135741 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1085,7 +1085,7 @@ void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb);
 void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb,
 			    struct rate_sample *rs);
 void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost,
-		  struct rate_sample *rs);
+		  bool is_sack_reneg, struct rate_sample *rs);
 void tcp_rate_check_app_limited(struct sock *sk);
 
 /* These functions determine how the current flow behaves in respect of SACK
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 5091402..a0c72b0 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2356,6 +2356,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tp->snd_cwnd_cnt = 0;
 	tp->window_clamp = 0;
 	tcp_set_ca_state(sk, TCP_CA_Open);
+	tp->is_sack_reneg = 0;
 	tcp_clear_retrans(tp);
 	inet_csk_delack_init(sk);
 	/* Initialize rcv_mss to TCP_MIN_MSS to avoid division by 0
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index c5447b9..a965a38 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1975,6 +1975,8 @@ void tcp_enter_loss(struct sock *sk)
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSACKRENEGING);
 		tp->sacked_out = 0;
 		tp->fackets_out = 0;
+		/* Mark SACK reneging until we recover from this loss event. */
+		tp->is_sack_reneg = 1;
 	}
 	tcp_clear_all_retrans_hints(tp);
 
@@ -2428,6 +2430,7 @@ static bool tcp_try_undo_recovery(struct sock *sk)
 		return true;
 	}
 	tcp_set_ca_state(sk, TCP_CA_Open);
+	tp->is_sack_reneg = 0;
 	return false;
 }
 
@@ -2459,8 +2462,10 @@ static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo)
 			NET_INC_STATS(sock_net(sk),
 					LINUX_MIB_TCPSPURIOUSRTOS);
 		inet_csk(sk)->icsk_retransmits = 0;
-		if (frto_undo || tcp_is_sack(tp))
+		if (frto_undo || tcp_is_sack(tp)) {
 			tcp_set_ca_state(sk, TCP_CA_Open);
+			tp->is_sack_reneg = 0;
+		}
 		return true;
 	}
 	return false;
@@ -3551,6 +3556,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	struct tcp_sacktag_state sack_state;
 	struct rate_sample rs = { .prior_delivered = 0 };
 	u32 prior_snd_una = tp->snd_una;
+	bool is_sack_reneg = tp->is_sack_reneg;
 	u32 ack_seq = TCP_SKB_CB(skb)->seq;
 	u32 ack = TCP_SKB_CB(skb)->ack_seq;
 	bool is_dupack = false;
@@ -3666,7 +3672,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 
 	delivered = tp->delivered - delivered;	/* freshly ACKed or SACKed */
 	lost = tp->lost - lost;			/* freshly marked lost */
-	tcp_rate_gen(sk, delivered, lost, sack_state.rate);
+	tcp_rate_gen(sk, delivered, lost, is_sack_reneg, sack_state.rate);
 	tcp_cong_control(sk, ack, delivered, flag, sack_state.rate);
 	tcp_xmit_recovery(sk, rexmit);
 	return 1;
diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c
index 3330a37..c61240e 100644
--- a/net/ipv4/tcp_rate.c
+++ b/net/ipv4/tcp_rate.c
@@ -106,7 +106,7 @@ void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb,
 
 /* Update the connection delivery information and generate a rate sample. */
 void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost,
-		  struct rate_sample *rs)
+		  bool is_sack_reneg, struct rate_sample *rs)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	u32 snd_us, ack_us;
@@ -124,8 +124,12 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost,
 
 	rs->acked_sacked = delivered;	/* freshly ACKed or SACKed */
 	rs->losses = lost;		/* freshly marked lost */
-	/* Return an invalid sample if no timing information is available. */
-	if (!rs->prior_mstamp) {
+	/* Return an invalid sample if no timing information is available or
+	 * in recovery from loss with SACK reneging. Rate samples taken during
+	 * a SACK reneging event may overestimate bw by including packets that
+	 * were SACKed before the reneg.
+	 */
+	if (!rs->prior_mstamp || is_sack_reneg) {
 		rs->delivered = -1;
 		rs->interval_us = -1;
 		return;
-- 
2.9.5


From 1dd07f954c69168013dff74f9a3e0b8910c0fbd9 Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Mon, 13 Nov 2017 10:11:27 +0200
Subject: [PATCH 30/58] net/mlx5: Fix rate limit packet pacing naming and
 struct

[ Upstream commit 37e92a9d4fe38dc3e7308913575983a6a088c8d4 ]

In mlx5_ifc, struct size was not complete, and thus driver was sending
garbage after the last defined field. Fixed it by adding reserved field
to complete the struct size.

In addition, rename all set_rate_limit to set_pp_rate_limit to be
compliant with the Firmware <-> Driver definition.

Fixes: 7486216b3a0b ("{net,IB}/mlx5: mlx5_ifc updates")
Fixes: 1466cc5b23d1 ("net/mlx5: Rate limit tables support")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c |  4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/rl.c  | 22 +++++++++++-----------
 include/linux/mlx5/mlx5_ifc.h                 |  8 +++++---
 3 files changed, 18 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 1fffdeb..e9a1fbc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -362,7 +362,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_QUERY_VPORT_COUNTER:
 	case MLX5_CMD_OP_ALLOC_Q_COUNTER:
 	case MLX5_CMD_OP_QUERY_Q_COUNTER:
-	case MLX5_CMD_OP_SET_RATE_LIMIT:
+	case MLX5_CMD_OP_SET_PP_RATE_LIMIT:
 	case MLX5_CMD_OP_QUERY_RATE_LIMIT:
 	case MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT:
 	case MLX5_CMD_OP_QUERY_SCHEDULING_ELEMENT:
@@ -505,7 +505,7 @@ const char *mlx5_command_str(int command)
 	MLX5_COMMAND_STR_CASE(ALLOC_Q_COUNTER);
 	MLX5_COMMAND_STR_CASE(DEALLOC_Q_COUNTER);
 	MLX5_COMMAND_STR_CASE(QUERY_Q_COUNTER);
-	MLX5_COMMAND_STR_CASE(SET_RATE_LIMIT);
+	MLX5_COMMAND_STR_CASE(SET_PP_RATE_LIMIT);
 	MLX5_COMMAND_STR_CASE(QUERY_RATE_LIMIT);
 	MLX5_COMMAND_STR_CASE(CREATE_SCHEDULING_ELEMENT);
 	MLX5_COMMAND_STR_CASE(DESTROY_SCHEDULING_ELEMENT);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rl.c b/drivers/net/ethernet/mellanox/mlx5/core/rl.c
index e651e4c..d3c33e9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/rl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rl.c
@@ -125,16 +125,16 @@ static struct mlx5_rl_entry *find_rl_entry(struct mlx5_rl_table *table,
 	return ret_entry;
 }
 
-static int mlx5_set_rate_limit_cmd(struct mlx5_core_dev *dev,
+static int mlx5_set_pp_rate_limit_cmd(struct mlx5_core_dev *dev,
 				   u32 rate, u16 index)
 {
-	u32 in[MLX5_ST_SZ_DW(set_rate_limit_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(set_rate_limit_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(set_pp_rate_limit_in)]   = {0};
+	u32 out[MLX5_ST_SZ_DW(set_pp_rate_limit_out)] = {0};
 
-	MLX5_SET(set_rate_limit_in, in, opcode,
-		 MLX5_CMD_OP_SET_RATE_LIMIT);
-	MLX5_SET(set_rate_limit_in, in, rate_limit_index, index);
-	MLX5_SET(set_rate_limit_in, in, rate_limit, rate);
+	MLX5_SET(set_pp_rate_limit_in, in, opcode,
+		 MLX5_CMD_OP_SET_PP_RATE_LIMIT);
+	MLX5_SET(set_pp_rate_limit_in, in, rate_limit_index, index);
+	MLX5_SET(set_pp_rate_limit_in, in, rate_limit, rate);
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 }
 
@@ -173,7 +173,7 @@ int mlx5_rl_add_rate(struct mlx5_core_dev *dev, u32 rate, u16 *index)
 		entry->refcount++;
 	} else {
 		/* new rate limit */
-		err = mlx5_set_rate_limit_cmd(dev, rate, entry->index);
+		err = mlx5_set_pp_rate_limit_cmd(dev, rate, entry->index);
 		if (err) {
 			mlx5_core_err(dev, "Failed configuring rate: %u (%d)\n",
 				      rate, err);
@@ -209,7 +209,7 @@ void mlx5_rl_remove_rate(struct mlx5_core_dev *dev, u32 rate)
 	entry->refcount--;
 	if (!entry->refcount) {
 		/* need to remove rate */
-		mlx5_set_rate_limit_cmd(dev, 0, entry->index);
+		mlx5_set_pp_rate_limit_cmd(dev, 0, entry->index);
 		entry->rate = 0;
 	}
 
@@ -262,8 +262,8 @@ void mlx5_cleanup_rl_table(struct mlx5_core_dev *dev)
 	/* Clear all configured rates */
 	for (i = 0; i < table->max_size; i++)
 		if (table->rl_entry[i].rate)
-			mlx5_set_rate_limit_cmd(dev, 0,
-						table->rl_entry[i].index);
+			mlx5_set_pp_rate_limit_cmd(dev, 0,
+						   table->rl_entry[i].index);
 
 	kfree(dev->priv.rl_table.rl_entry);
 }
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 6977234..c8091f06 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -147,7 +147,7 @@ enum {
 	MLX5_CMD_OP_ALLOC_Q_COUNTER               = 0x771,
 	MLX5_CMD_OP_DEALLOC_Q_COUNTER             = 0x772,
 	MLX5_CMD_OP_QUERY_Q_COUNTER               = 0x773,
-	MLX5_CMD_OP_SET_RATE_LIMIT                = 0x780,
+	MLX5_CMD_OP_SET_PP_RATE_LIMIT             = 0x780,
 	MLX5_CMD_OP_QUERY_RATE_LIMIT              = 0x781,
 	MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT      = 0x782,
 	MLX5_CMD_OP_DESTROY_SCHEDULING_ELEMENT     = 0x783,
@@ -7233,7 +7233,7 @@ struct mlx5_ifc_add_vxlan_udp_dport_in_bits {
 	u8         vxlan_udp_port[0x10];
 };
 
-struct mlx5_ifc_set_rate_limit_out_bits {
+struct mlx5_ifc_set_pp_rate_limit_out_bits {
 	u8         status[0x8];
 	u8         reserved_at_8[0x18];
 
@@ -7242,7 +7242,7 @@ struct mlx5_ifc_set_rate_limit_out_bits {
 	u8         reserved_at_40[0x40];
 };
 
-struct mlx5_ifc_set_rate_limit_in_bits {
+struct mlx5_ifc_set_pp_rate_limit_in_bits {
 	u8         opcode[0x10];
 	u8         reserved_at_10[0x10];
 
@@ -7255,6 +7255,8 @@ struct mlx5_ifc_set_rate_limit_in_bits {
 	u8         reserved_at_60[0x20];
 
 	u8         rate_limit[0x20];
+
+	u8         reserved_at_a0[0x160];
 };
 
 struct mlx5_ifc_access_register_out_bits {
-- 
2.9.5


From 54712c450fadd6d4be77eefbb640c62854bca4a9 Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Thu, 23 Nov 2017 13:52:28 +0200
Subject: [PATCH 31/58] net/mlx5e: Fix possible deadlock of VXLAN lock

[ Upstream commit 6323514116404cc651df1b7fffa1311ddf8ce647 ]

mlx5e_vxlan_lookup_port is called both from mlx5e_add_vxlan_port (user
context) and mlx5e_features_check (softirq), but the lock acquired does
not disable bottom half and might result in deadlock. Fix it by simply
replacing spin_lock() with spin_lock_bh().
While at it, replace all unnecessary spin_lock_irq() to spin_lock_bh().

lockdep's WARNING: inconsistent lock state
[  654.028136] inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage.
[  654.028229] swapper/5/0 [HC0[0]:SC1[9]:HE1:SE0] takes:
[  654.028321]  (&(&vxlan_db->lock)->rlock){+.?.}, at: [<ffffffffa06e7f0e>] mlx5e_vxlan_lookup_port+0x1e/0x50 [mlx5_core]
[  654.028528] {SOFTIRQ-ON-W} state was registered at:
[  654.028607]   _raw_spin_lock+0x3c/0x70
[  654.028689]   mlx5e_vxlan_lookup_port+0x1e/0x50 [mlx5_core]
[  654.028794]   mlx5e_vxlan_add_port+0x2e/0x120 [mlx5_core]
[  654.028878]   process_one_work+0x1e9/0x640
[  654.028942]   worker_thread+0x4a/0x3f0
[  654.029002]   kthread+0x141/0x180
[  654.029056]   ret_from_fork+0x24/0x30
[  654.029114] irq event stamp: 579088
[  654.029174] hardirqs last  enabled at (579088): [<ffffffff818f475a>] ip6_finish_output2+0x49a/0x8c0
[  654.029309] hardirqs last disabled at (579087): [<ffffffff818f470e>] ip6_finish_output2+0x44e/0x8c0
[  654.029446] softirqs last  enabled at (579030): [<ffffffff810b3b3d>] irq_enter+0x6d/0x80
[  654.029567] softirqs last disabled at (579031): [<ffffffff810b3c05>] irq_exit+0xb5/0xc0
[  654.029684] other info that might help us debug this:
[  654.029781]  Possible unsafe locking scenario:

[  654.029868]        CPU0
[  654.029908]        ----
[  654.029947]   lock(&(&vxlan_db->lock)->rlock);
[  654.030045]   <Interrupt>
[  654.030090]     lock(&(&vxlan_db->lock)->rlock);
[  654.030162]
 *** DEADLOCK ***

Fixes: b3f63c3d5e2c ("net/mlx5e: Add netdev support for VXLAN tunneling")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/vxlan.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
index 07a9ba6..f823827 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
@@ -71,9 +71,9 @@ struct mlx5e_vxlan *mlx5e_vxlan_lookup_port(struct mlx5e_priv *priv, u16 port)
 	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
 	struct mlx5e_vxlan *vxlan;
 
-	spin_lock(&vxlan_db->lock);
+	spin_lock_bh(&vxlan_db->lock);
 	vxlan = radix_tree_lookup(&vxlan_db->tree, port);
-	spin_unlock(&vxlan_db->lock);
+	spin_unlock_bh(&vxlan_db->lock);
 
 	return vxlan;
 }
@@ -100,9 +100,9 @@ static void mlx5e_vxlan_add_port(struct work_struct *work)
 
 	vxlan->udp_port = port;
 
-	spin_lock_irq(&vxlan_db->lock);
+	spin_lock_bh(&vxlan_db->lock);
 	err = radix_tree_insert(&vxlan_db->tree, vxlan->udp_port, vxlan);
-	spin_unlock_irq(&vxlan_db->lock);
+	spin_unlock_bh(&vxlan_db->lock);
 	if (err)
 		goto err_free;
 
@@ -121,9 +121,9 @@ static void __mlx5e_vxlan_core_del_port(struct mlx5e_priv *priv, u16 port)
 	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
 	struct mlx5e_vxlan *vxlan;
 
-	spin_lock_irq(&vxlan_db->lock);
+	spin_lock_bh(&vxlan_db->lock);
 	vxlan = radix_tree_delete(&vxlan_db->tree, port);
-	spin_unlock_irq(&vxlan_db->lock);
+	spin_unlock_bh(&vxlan_db->lock);
 
 	if (!vxlan)
 		return;
@@ -171,12 +171,12 @@ void mlx5e_vxlan_cleanup(struct mlx5e_priv *priv)
 	struct mlx5e_vxlan *vxlan;
 	unsigned int port = 0;
 
-	spin_lock_irq(&vxlan_db->lock);
+	spin_lock_bh(&vxlan_db->lock);
 	while (radix_tree_gang_lookup(&vxlan_db->tree, (void **)&vxlan, port, 1)) {
 		port = vxlan->udp_port;
-		spin_unlock_irq(&vxlan_db->lock);
+		spin_unlock_bh(&vxlan_db->lock);
 		__mlx5e_vxlan_core_del_port(priv, (u16)port);
-		spin_lock_irq(&vxlan_db->lock);
+		spin_lock_bh(&vxlan_db->lock);
 	}
-	spin_unlock_irq(&vxlan_db->lock);
+	spin_unlock_bh(&vxlan_db->lock);
 }
-- 
2.9.5


From 0d2faf91fc1f5cea3fc3e04baa14ed13993812e1 Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Tue, 21 Nov 2017 17:49:36 +0200
Subject: [PATCH 32/58] net/mlx5e: Fix features check of IPv6 traffic

[ Upstream commit 2989ad1ec03021ee6d2193c35414f1d970a243de ]

The assumption that the next header field contains the transport
protocol is wrong for IPv6 packets with extension headers.
Instead, we should look the inner-most next header field in the buffer.
This will fix TSO offload for tunnels over IPv6 with extension headers.

Performance testing: 19.25x improvement, cool!
Measuring bandwidth of 16 threads TCP traffic over IPv6 GRE tap.
CPU: Intel(R) Xeon(R) CPU E5-2660 v2 @ 2.20GHz
NIC: Mellanox Technologies MT28800 Family [ConnectX-5 Ex]
TSO: Enabled
Before: 4,926.24  Mbps
Now   : 94,827.91 Mbps

Fixes: b3f63c3d5e2c ("net/mlx5e: Add netdev support for VXLAN tunneling")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index cc11bbb..517727f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3554,6 +3554,7 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv,
 						     struct sk_buff *skb,
 						     netdev_features_t features)
 {
+	unsigned int offset = 0;
 	struct udphdr *udph;
 	u8 proto;
 	u16 port;
@@ -3563,7 +3564,7 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv,
 		proto = ip_hdr(skb)->protocol;
 		break;
 	case htons(ETH_P_IPV6):
-		proto = ipv6_hdr(skb)->nexthdr;
+		proto = ipv6_find_hdr(skb, &offset, -1, NULL, NULL);
 		break;
 	default:
 		goto out;
-- 
2.9.5


From 2ceb441aa548569ac92879b4dd9b9c697d479d5d Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Sun, 3 Dec 2017 13:58:50 +0200
Subject: [PATCH 33/58] net/mlx5e: Add refcount to VXLAN structure

[ Upstream commit 23f4cc2cd9ed92570647220aca60d0197d8c1fa9 ]

A refcount mechanism must be implemented in order to prevent unwanted
scenarios such as:
- Open an IPv4 VXLAN interface
- Open an IPv6 VXLAN interface (different socket)
- Remove one of the interfaces

With current implementation, the UDP port will be removed from our VXLAN
database and turn off the offloads for the other interface, which is
still active.
The reference count mechanism will only allow UDP port removals once all
consumers are gone.

Fixes: b3f63c3d5e2c ("net/mlx5e: Add netdev support for VXLAN tunneling")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/vxlan.c | 50 +++++++++++++------------
 drivers/net/ethernet/mellanox/mlx5/core/vxlan.h |  1 +
 2 files changed, 28 insertions(+), 23 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
index f823827..25f7823 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
@@ -88,8 +88,11 @@ static void mlx5e_vxlan_add_port(struct work_struct *work)
 	struct mlx5e_vxlan *vxlan;
 	int err;
 
-	if (mlx5e_vxlan_lookup_port(priv, port))
+	vxlan = mlx5e_vxlan_lookup_port(priv, port);
+	if (vxlan) {
+		atomic_inc(&vxlan->refcount);
 		goto free_work;
+	}
 
 	if (mlx5e_vxlan_core_add_port_cmd(priv->mdev, port))
 		goto free_work;
@@ -99,6 +102,7 @@ static void mlx5e_vxlan_add_port(struct work_struct *work)
 		goto err_delete_port;
 
 	vxlan->udp_port = port;
+	atomic_set(&vxlan->refcount, 1);
 
 	spin_lock_bh(&vxlan_db->lock);
 	err = radix_tree_insert(&vxlan_db->tree, vxlan->udp_port, vxlan);
@@ -116,32 +120,33 @@ static void mlx5e_vxlan_add_port(struct work_struct *work)
 	kfree(vxlan_work);
 }
 
-static void __mlx5e_vxlan_core_del_port(struct mlx5e_priv *priv, u16 port)
+static void mlx5e_vxlan_del_port(struct work_struct *work)
 {
+	struct mlx5e_vxlan_work *vxlan_work =
+		container_of(work, struct mlx5e_vxlan_work, work);
+	struct mlx5e_priv *priv         = vxlan_work->priv;
 	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
+	u16 port = vxlan_work->port;
 	struct mlx5e_vxlan *vxlan;
+	bool remove = false;
 
 	spin_lock_bh(&vxlan_db->lock);
-	vxlan = radix_tree_delete(&vxlan_db->tree, port);
-	spin_unlock_bh(&vxlan_db->lock);
-
+	vxlan = radix_tree_lookup(&vxlan_db->tree, port);
 	if (!vxlan)
-		return;
-
-	mlx5e_vxlan_core_del_port_cmd(priv->mdev, vxlan->udp_port);
-
-	kfree(vxlan);
-}
+		goto out_unlock;
 
-static void mlx5e_vxlan_del_port(struct work_struct *work)
-{
-	struct mlx5e_vxlan_work *vxlan_work =
-		container_of(work, struct mlx5e_vxlan_work, work);
-	struct mlx5e_priv *priv = vxlan_work->priv;
-	u16 port = vxlan_work->port;
+	if (atomic_dec_and_test(&vxlan->refcount)) {
+		radix_tree_delete(&vxlan_db->tree, port);
+		remove = true;
+	}
 
-	__mlx5e_vxlan_core_del_port(priv, port);
+out_unlock:
+	spin_unlock_bh(&vxlan_db->lock);
 
+	if (remove) {
+		mlx5e_vxlan_core_del_port_cmd(priv->mdev, port);
+		kfree(vxlan);
+	}
 	kfree(vxlan_work);
 }
 
@@ -171,12 +176,11 @@ void mlx5e_vxlan_cleanup(struct mlx5e_priv *priv)
 	struct mlx5e_vxlan *vxlan;
 	unsigned int port = 0;
 
-	spin_lock_bh(&vxlan_db->lock);
+	/* Lockless since we are the only radix-tree consumers, wq is disabled */
 	while (radix_tree_gang_lookup(&vxlan_db->tree, (void **)&vxlan, port, 1)) {
 		port = vxlan->udp_port;
-		spin_unlock_bh(&vxlan_db->lock);
-		__mlx5e_vxlan_core_del_port(priv, (u16)port);
-		spin_lock_bh(&vxlan_db->lock);
+		radix_tree_delete(&vxlan_db->tree, port);
+		mlx5e_vxlan_core_del_port_cmd(priv->mdev, port);
+		kfree(vxlan);
 	}
-	spin_unlock_bh(&vxlan_db->lock);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
index 5def12c..5ef6ae7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
@@ -36,6 +36,7 @@
 #include "en.h"
 
 struct mlx5e_vxlan {
+	atomic_t refcount;
 	u16 udp_port;
 };
 
-- 
2.9.5


From 476d24959975039b0cfbe8144e157644cf20e069 Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Mon, 4 Dec 2017 09:57:43 +0200
Subject: [PATCH 34/58] net/mlx5e: Prevent possible races in VXLAN control flow

[ Upstream commit 0c1cc8b2215f5122ca614b5adca60346018758c3 ]

When calling add/remove VXLAN port, a lock must be held in order to
prevent race scenarios when more than one add/remove happens at the
same time.
Fix by holding our state_lock (mutex) as done by all other parts of the
driver.
Note that the spinlock protecting the radix-tree is still needed in
order to synchronize radix-tree access from softirq context.

Fixes: b3f63c3d5e2c ("net/mlx5e: Add netdev support for VXLAN tunneling")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/vxlan.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
index 25f7823..2f74953 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
@@ -88,6 +88,7 @@ static void mlx5e_vxlan_add_port(struct work_struct *work)
 	struct mlx5e_vxlan *vxlan;
 	int err;
 
+	mutex_lock(&priv->state_lock);
 	vxlan = mlx5e_vxlan_lookup_port(priv, port);
 	if (vxlan) {
 		atomic_inc(&vxlan->refcount);
@@ -117,6 +118,7 @@ static void mlx5e_vxlan_add_port(struct work_struct *work)
 err_delete_port:
 	mlx5e_vxlan_core_del_port_cmd(priv->mdev, port);
 free_work:
+	mutex_unlock(&priv->state_lock);
 	kfree(vxlan_work);
 }
 
@@ -130,6 +132,7 @@ static void mlx5e_vxlan_del_port(struct work_struct *work)
 	struct mlx5e_vxlan *vxlan;
 	bool remove = false;
 
+	mutex_lock(&priv->state_lock);
 	spin_lock_bh(&vxlan_db->lock);
 	vxlan = radix_tree_lookup(&vxlan_db->tree, port);
 	if (!vxlan)
@@ -147,6 +150,7 @@ static void mlx5e_vxlan_del_port(struct work_struct *work)
 		mlx5e_vxlan_core_del_port_cmd(priv->mdev, port);
 		kfree(vxlan);
 	}
+	mutex_unlock(&priv->state_lock);
 	kfree(vxlan_work);
 }
 
-- 
2.9.5


From 34f10ec2b9365c3097ed7535f414608eafaccae5 Mon Sep 17 00:00:00 2001
From: Moni Shoua <monis@mellanox.com>
Date: Mon, 4 Dec 2017 08:59:25 +0200
Subject: [PATCH 35/58] net/mlx5: Fix error flow in CREATE_QP command

[ Upstream commit dbff26e44dc3ec4de6578733b054a0114652a764 ]

In error flow, when DESTROY_QP command should be executed, the wrong
mailbox was set with data, not the one that is written to hardware,
Fix that.

Fixes: 09a7d9eca1a6 '{net,IB}/mlx5: QP/XRCD commands via mlx5 ifc'
Signed-off-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/qp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
index db9e665..889130e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
@@ -213,8 +213,8 @@ int mlx5_core_create_qp(struct mlx5_core_dev *dev,
 err_cmd:
 	memset(din, 0, sizeof(din));
 	memset(dout, 0, sizeof(dout));
-	MLX5_SET(destroy_qp_in, in, opcode, MLX5_CMD_OP_DESTROY_QP);
-	MLX5_SET(destroy_qp_in, in, qpn, qp->qpn);
+	MLX5_SET(destroy_qp_in, din, opcode, MLX5_CMD_OP_DESTROY_QP);
+	MLX5_SET(destroy_qp_in, din, qpn, qp->qpn);
 	mlx5_cmd_exec(dev, din, sizeof(din), dout, sizeof(dout));
 	return err;
 }
-- 
2.9.5


From 616546f27b21e83d580f0ba4c14632bac3566cd6 Mon Sep 17 00:00:00 2001
From: Eric Garver <e@erig.me>
Date: Wed, 20 Dec 2017 15:09:22 -0500
Subject: [PATCH 36/58] openvswitch: Fix pop_vlan action for double tagged
 frames

[ Upstream commit c48e74736fccf25fb32bb015426359e1c2016e3b ]

skb_vlan_pop() expects skb->protocol to be a valid TPID for double
tagged frames. So set skb->protocol to the TPID and let skb_vlan_pop()
shift the true ethertype into position for us.

Fixes: 5108bbaddc37 ("openvswitch: add processing of L3 packets")
Signed-off-by: Eric Garver <e@erig.me>
Reviewed-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/flow.c | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index cfb652a..dbe1079 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -532,6 +532,7 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 			return -EINVAL;
 
 		skb_reset_network_header(skb);
+		key->eth.type = skb->protocol;
 	} else {
 		eth = eth_hdr(skb);
 		ether_addr_copy(key->eth.src, eth->h_source);
@@ -545,15 +546,23 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 		if (unlikely(parse_vlan(skb, key)))
 			return -ENOMEM;
 
-		skb->protocol = parse_ethertype(skb);
-		if (unlikely(skb->protocol == htons(0)))
+		key->eth.type = parse_ethertype(skb);
+		if (unlikely(key->eth.type == htons(0)))
 			return -ENOMEM;
 
+		/* Multiple tagged packets need to retain TPID to satisfy
+		 * skb_vlan_pop(), which will later shift the ethertype into
+		 * skb->protocol.
+		 */
+		if (key->eth.cvlan.tci & htons(VLAN_TAG_PRESENT))
+			skb->protocol = key->eth.cvlan.tpid;
+		else
+			skb->protocol = key->eth.type;
+
 		skb_reset_network_header(skb);
 		__skb_push(skb, skb->data - skb_mac_header(skb));
 	}
 	skb_reset_mac_len(skb);
-	key->eth.type = skb->protocol;
 
 	/* Network layer. */
 	if (key->eth.type == htons(ETH_P_IP)) {
-- 
2.9.5


From 4e764f44e251f5fbd5c3d8956dfe8ab4599e5e4a Mon Sep 17 00:00:00 2001
From: Bert Kenward <bkenward@solarflare.com>
Date: Thu, 7 Dec 2017 17:18:58 +0000
Subject: [PATCH 37/58] sfc: pass valid pointers from efx_enqueue_unwind

[ Upstream commit d4a7a8893d4cdbc89d79ac4aa704bf8d4b67b368 ]

The bytes_compl and pkts_compl pointers passed to efx_dequeue_buffers
cannot be NULL. Add a paranoid warning to check this condition and fix
the one case where they were NULL.

efx_enqueue_unwind() is called very rarely, during error handling.
Without this fix it would fail with a NULL pointer dereference in
efx_dequeue_buffer, with efx_enqueue_skb in the call stack.

Fixes: e9117e5099ea ("sfc: Firmware-Assisted TSO version 2")
Reported-by: Jarod Wilson <jarod@redhat.com>
Signed-off-by: Bert Kenward <bkenward@solarflare.com>
Tested-by: Jarod Wilson <jarod@redhat.com>
Acked-by: Jarod Wilson <jarod@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/tx.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c
index 32bf1fe..9b85cbd 100644
--- a/drivers/net/ethernet/sfc/tx.c
+++ b/drivers/net/ethernet/sfc/tx.c
@@ -77,6 +77,7 @@ static void efx_dequeue_buffer(struct efx_tx_queue *tx_queue,
 	}
 
 	if (buffer->flags & EFX_TX_BUF_SKB) {
+		EFX_WARN_ON_PARANOID(!pkts_compl || !bytes_compl);
 		(*pkts_compl)++;
 		(*bytes_compl) += buffer->skb->len;
 		dev_consume_skb_any((struct sk_buff *)buffer->skb);
@@ -426,12 +427,14 @@ static int efx_tx_map_data(struct efx_tx_queue *tx_queue, struct sk_buff *skb,
 static void efx_enqueue_unwind(struct efx_tx_queue *tx_queue)
 {
 	struct efx_tx_buffer *buffer;
+	unsigned int bytes_compl = 0;
+	unsigned int pkts_compl = 0;
 
 	/* Work backwards until we hit the original insert pointer value */
 	while (tx_queue->insert_count != tx_queue->write_count) {
 		--tx_queue->insert_count;
 		buffer = __efx_tx_queue_get_insert_buffer(tx_queue);
-		efx_dequeue_buffer(tx_queue, buffer, NULL, NULL);
+		efx_dequeue_buffer(tx_queue, buffer, &pkts_compl, &bytes_compl);
 	}
 }
 
-- 
2.9.5


From 3cfae7ee5ae7708a31a0a2f6a893b22f3a951493 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 21 Nov 2017 17:37:46 -0800
Subject: [PATCH 38/58] net: dsa: bcm_sf2: Clear IDDQ_GLOBAL_PWR bit for PHY

[ Upstream commit 4b52d010113e11006a389f2a8315167ede9e0b10 ]

The PHY on BCM7278 has an additional bit that needs to be cleared:
IDDQ_GLOBAL_PWR, without doing this, the PHY remains stuck in reset out
of suspend/resume cycles.

Fixes: 0fe9933804eb ("net: dsa: bcm_sf2: Add support for BCM7278 integrated switch")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index d7b53d5..72d6ffb 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -167,7 +167,7 @@ static void bcm_sf2_gphy_enable_set(struct dsa_switch *ds, bool enable)
 	reg = reg_readl(priv, REG_SPHY_CNTRL);
 	if (enable) {
 		reg |= PHY_RESET;
-		reg &= ~(EXT_PWR_DOWN | IDDQ_BIAS | CK25_DIS);
+		reg &= ~(EXT_PWR_DOWN | IDDQ_BIAS | IDDQ_GLOBAL_PWR | CK25_DIS);
 		reg_writel(priv, reg, REG_SPHY_CNTRL);
 		udelay(21);
 		reg = reg_readl(priv, REG_SPHY_CNTRL);
-- 
2.9.5


From 9f696c8c6d107528fb0d2314cfd4b1e5b3488741 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Wed, 20 Dec 2017 18:07:18 +0100
Subject: [PATCH 39/58] s390/qeth: fix error handling in checksum cmd callback

[ Upstream commit ad3cbf61332914711e5f506972b1dc9af8d62146 ]

Make sure to check both return code fields before processing the
response. Otherwise we risk operating on invalid data.

Fixes: c9475369bd2b ("s390/qeth: rework RX/TX checksum offload")
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 291eb89..7c7a244 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -5445,6 +5445,13 @@ int qeth_poll(struct napi_struct *napi, int budget)
 }
 EXPORT_SYMBOL_GPL(qeth_poll);
 
+static int qeth_setassparms_inspect_rc(struct qeth_ipa_cmd *cmd)
+{
+	if (!cmd->hdr.return_code)
+		cmd->hdr.return_code = cmd->data.setassparms.hdr.return_code;
+	return cmd->hdr.return_code;
+}
+
 int qeth_setassparms_cb(struct qeth_card *card,
 			struct qeth_reply *reply, unsigned long data)
 {
@@ -6304,7 +6311,7 @@ static int qeth_ipa_checksum_run_cmd_cb(struct qeth_card *card,
 				(struct qeth_checksum_cmd *)reply->param;
 
 	QETH_CARD_TEXT(card, 4, "chkdoccb");
-	if (cmd->hdr.return_code)
+	if (qeth_setassparms_inspect_rc(cmd))
 		return 0;
 
 	memset(chksum_cb, 0, sizeof(*chksum_cb));
-- 
2.9.5


From 5caec85c5178dd0f07621cfcfc1a1e3e59f23608 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 10 Dec 2017 15:40:51 +0800
Subject: [PATCH 40/58] sctp: make sure stream nums can match optlen in
 sctp_setsockopt_reset_streams

[ Upstream commit 2342b8d95bcae5946e1b9b8d58645f37500ef2e7 ]

Now in sctp_setsockopt_reset_streams, it only does the check
optlen < sizeof(*params) for optlen. But it's not enough, as
params->srs_number_streams should also match optlen.

If the streams in params->srs_stream_list are less than stream
nums in params->srs_number_streams, later when dereferencing
the stream list, it could cause a slab-out-of-bounds crash, as
reported by syzbot.

This patch is to fix it by also checking the stream numbers in
sctp_setsockopt_reset_streams to make sure at least it's not
greater than the streams in the list.

Fixes: 7f9d68ac944e ("sctp: implement sender-side procedures for SSN Reset Request Parameter")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 1977238..df806b8 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -3874,13 +3874,17 @@ static int sctp_setsockopt_reset_streams(struct sock *sk,
 	struct sctp_association *asoc;
 	int retval = -EINVAL;
 
-	if (optlen < sizeof(struct sctp_reset_streams))
+	if (optlen < sizeof(*params))
 		return -EINVAL;
 
 	params = memdup_user(optval, optlen);
 	if (IS_ERR(params))
 		return PTR_ERR(params);
 
+	if (params->srs_number_streams * sizeof(__u16) >
+	    optlen - sizeof(*params))
+		goto out;
+
 	asoc = sctp_id2assoc(sk, params->srs_assoc_id);
 	if (!asoc)
 		goto out;
-- 
2.9.5


From cb9cd59aa828c219b1f43422d9c13503bcad47cb Mon Sep 17 00:00:00 2001
From: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@gmail.com>
Date: Thu, 28 Dec 2017 12:03:06 +0100
Subject: [PATCH 41/58] tipc: fix hanging poll() for stream sockets

[ Upstream commit 517d7c79bdb39864e617960504bdc1aa560c75c6 ]

In commit 42b531de17d2f6 ("tipc: Fix missing connection request
handling"), we replaced unconditional wakeup() with condtional
wakeup for clients with flags POLLIN | POLLRDNORM | POLLRDBAND.

This breaks the applications which do a connect followed by poll
with POLLOUT flag. These applications are not woken when the
connection is ESTABLISHED and hence sleep forever.

In this commit, we fix it by including the POLLOUT event for
sockets in TIPC_CONNECTING state.

Fixes: 42b531de17d2f6 ("tipc: Fix missing connection request handling")
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/socket.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index d50edd6..98a44ec 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -709,11 +709,11 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock,
 
 	switch (sk->sk_state) {
 	case TIPC_ESTABLISHED:
+	case TIPC_CONNECTING:
 		if (!tsk->cong_link_cnt && !tsk_conn_cong(tsk))
 			mask |= POLLOUT;
 		/* fall thru' */
 	case TIPC_LISTEN:
-	case TIPC_CONNECTING:
 		if (!skb_queue_empty(&sk->sk_receive_queue))
 			mask |= (POLLIN | POLLRDNORM);
 		break;
-- 
2.9.5


From 008f8adc8c035945378686997758ca494f2510d7 Mon Sep 17 00:00:00 2001
From: Yuval Mintz <yuvalm@mellanox.com>
Date: Fri, 15 Dec 2017 08:44:21 +0100
Subject: [PATCH 42/58] mlxsw: spectrum: Disable MAC learning for ovs port

[ Upstream commit fccff0862838908d21eaf956d57e09c6c189f7c5 ]

Learning is currently enabled for ports which are OVS slaves -
even though OVS doesn't need this indication.
Since we're not associating a fid with the port, HW would continuously
notify driver of learned [& aged] MACs which would be logged as errors.

Fixes: 2b94e58df58c ("mlxsw: spectrum: Allow ports to work under OVS master")
Signed-off-by: Yuval Mintz <yuvalm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index db38880..3ead743 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4164,6 +4164,7 @@ static int mlxsw_sp_port_stp_set(struct mlxsw_sp_port *mlxsw_sp_port,
 
 static int mlxsw_sp_port_ovs_join(struct mlxsw_sp_port *mlxsw_sp_port)
 {
+	u16 vid = 1;
 	int err;
 
 	err = mlxsw_sp_port_vp_mode_set(mlxsw_sp_port, true);
@@ -4176,8 +4177,19 @@ static int mlxsw_sp_port_ovs_join(struct mlxsw_sp_port *mlxsw_sp_port)
 				     true, false);
 	if (err)
 		goto err_port_vlan_set;
+
+	for (; vid <= VLAN_N_VID - 1; vid++) {
+		err = mlxsw_sp_port_vid_learning_set(mlxsw_sp_port,
+						     vid, false);
+		if (err)
+			goto err_vid_learning_set;
+	}
+
 	return 0;
 
+err_vid_learning_set:
+	for (vid--; vid >= 1; vid--)
+		mlxsw_sp_port_vid_learning_set(mlxsw_sp_port, vid, true);
 err_port_vlan_set:
 	mlxsw_sp_port_stp_set(mlxsw_sp_port, false);
 err_port_stp_set:
@@ -4187,6 +4199,12 @@ static int mlxsw_sp_port_ovs_join(struct mlxsw_sp_port *mlxsw_sp_port)
 
 static void mlxsw_sp_port_ovs_leave(struct mlxsw_sp_port *mlxsw_sp_port)
 {
+	u16 vid;
+
+	for (vid = VLAN_N_VID - 1; vid >= 1; vid--)
+		mlxsw_sp_port_vid_learning_set(mlxsw_sp_port,
+					       vid, true);
+
 	mlxsw_sp_port_vlan_set(mlxsw_sp_port, 2, VLAN_N_VID - 1,
 			       false, false);
 	mlxsw_sp_port_stp_set(mlxsw_sp_port, false);
-- 
2.9.5


From 399cd0255a8dab108fe6b3fbde2867b542698572 Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Tue, 12 Dec 2017 16:28:58 -0800
Subject: [PATCH 43/58] tcp: fix potential underestimation on rcv_rtt

[ Upstream commit 9ee11bd03cb1a5c3ca33c2bb70e7ed325f68890f ]

When ms timestamp is used, current logic uses 1us in
tcp_rcv_rtt_update() when the real rcv_rtt is within 1 - 999us.
This could cause rcv_rtt underestimation.
Fix it by always using a min value of 1ms if ms timestamp is used.

Fixes: 645f4c6f2ebd ("tcp: switch rcv_rtt_est and rcvq_space to high resolution timestamps")
Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a965a38..ff48ac6 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -521,9 +521,6 @@ static void tcp_rcv_rtt_update(struct tcp_sock *tp, u32 sample, int win_dep)
 	u32 new_sample = tp->rcv_rtt_est.rtt_us;
 	long m = sample;
 
-	if (m == 0)
-		m = 1;
-
 	if (new_sample != 0) {
 		/* If we sample in larger samples in the non-timestamp
 		 * case, we could grossly overestimate the RTT especially
@@ -560,6 +557,8 @@ static inline void tcp_rcv_rtt_measure(struct tcp_sock *tp)
 	if (before(tp->rcv_nxt, tp->rcv_rtt_est.seq))
 		return;
 	delta_us = tcp_stamp_us_delta(tp->tcp_mstamp, tp->rcv_rtt_est.time);
+	if (!delta_us)
+		delta_us = 1;
 	tcp_rcv_rtt_update(tp, delta_us, 1);
 
 new_measure:
@@ -576,8 +575,11 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk,
 	    (TCP_SKB_CB(skb)->end_seq -
 	     TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss)) {
 		u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr;
-		u32 delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
+		u32 delta_us;
 
+		if (!delta)
+			delta = 1;
+		delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
 		tcp_rcv_rtt_update(tp, delta_us, 0);
 	}
 }
-- 
2.9.5


From 7573306a6e640a7bb05fb5312c5068209ce604ce Mon Sep 17 00:00:00 2001
From: Zhao Qiang <qiang.zhao@nxp.com>
Date: Mon, 18 Dec 2017 10:26:43 +0800
Subject: [PATCH 44/58] net: phy: marvell: Limit 88m1101 autoneg errata to
 88E1145 as well.

[ Upstream commit c505873eaece2b4aefd07d339dc7e1400e0235ac ]

88E1145 also need this autoneg errata.

Fixes: f2899788353c ("net: phy: marvell: Limit errata to 88m1101")
Signed-off-by: Zhao Qiang <qiang.zhao@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/marvell.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index 4d02b27..a3f456b 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -2069,7 +2069,7 @@ static struct phy_driver marvell_drivers[] = {
 		.flags = PHY_HAS_INTERRUPT,
 		.probe = marvell_probe,
 		.config_init = &m88e1145_config_init,
-		.config_aneg = &marvell_config_aneg,
+		.config_aneg = &m88e1101_config_aneg,
 		.read_status = &genphy_read_status,
 		.ack_interrupt = &marvell_ack_interrupt,
 		.config_intr = &marvell_config_intr,
-- 
2.9.5


From fcd0b5bc80fa731e7160503d87d678ce72cdeeee Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 20 Dec 2017 12:28:25 +0200
Subject: [PATCH 45/58] ipv6: Honor specified parameters in fibmatch lookup

[ Upstream commit 58acfd714e6b02e8617448b431c2b64a2f1f0792 ]

Currently, parameters such as oif and source address are not taken into
account during fibmatch lookup. Example (IPv4 for reference) before
patch:

$ ip -4 route show
192.0.2.0/24 dev dummy0 proto kernel scope link src 192.0.2.1
198.51.100.0/24 dev dummy1 proto kernel scope link src 198.51.100.1

$ ip -6 route show
2001:db8:1::/64 dev dummy0 proto kernel metric 256 pref medium
2001:db8:2::/64 dev dummy1 proto kernel metric 256 pref medium
fe80::/64 dev dummy0 proto kernel metric 256 pref medium
fe80::/64 dev dummy1 proto kernel metric 256 pref medium

$ ip -4 route get fibmatch 192.0.2.2 oif dummy0
192.0.2.0/24 dev dummy0 proto kernel scope link src 192.0.2.1
$ ip -4 route get fibmatch 192.0.2.2 oif dummy1
RTNETLINK answers: No route to host

$ ip -6 route get fibmatch 2001:db8:1::2 oif dummy0
2001:db8:1::/64 dev dummy0 proto kernel metric 256 pref medium
$ ip -6 route get fibmatch 2001:db8:1::2 oif dummy1
2001:db8:1::/64 dev dummy0 proto kernel metric 256 pref medium

After:

$ ip -6 route get fibmatch 2001:db8:1::2 oif dummy0
2001:db8:1::/64 dev dummy0 proto kernel metric 256 pref medium
$ ip -6 route get fibmatch 2001:db8:1::2 oif dummy1
RTNETLINK answers: Network is unreachable

The problem stems from the fact that the necessary route lookup flags
are not set based on these parameters.

Instead of duplicating the same logic for fibmatch, we can simply
resolve the original route from its copy and dump it instead.

Fixes: 18c3a61c4264 ("net: ipv6: RTM_GETROUTE: return matched fib result when requested")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 598efa8..ca8d326 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3700,19 +3700,13 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 		if (!ipv6_addr_any(&fl6.saddr))
 			flags |= RT6_LOOKUP_F_HAS_SADDR;
 
-		if (!fibmatch)
-			dst = ip6_route_input_lookup(net, dev, &fl6, flags);
-		else
-			dst = ip6_route_lookup(net, &fl6, 0);
+		dst = ip6_route_input_lookup(net, dev, &fl6, flags);
 
 		rcu_read_unlock();
 	} else {
 		fl6.flowi6_oif = oif;
 
-		if (!fibmatch)
-			dst = ip6_route_output(net, NULL, &fl6);
-		else
-			dst = ip6_route_lookup(net, &fl6, 0);
+		dst = ip6_route_output(net, NULL, &fl6);
 	}
 
 
@@ -3729,6 +3723,15 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 		goto errout;
 	}
 
+	if (fibmatch && rt->dst.from) {
+		struct rt6_info *ort = container_of(rt->dst.from,
+						    struct rt6_info, dst);
+
+		dst_hold(&ort->dst);
+		ip6_rt_put(rt);
+		rt = ort;
+	}
+
 	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (!skb) {
 		ip6_rt_put(rt);
-- 
2.9.5


From a513265a8849dd89f628c2e0ca25fd7d025beb4d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 12 Dec 2017 18:22:52 -0800
Subject: [PATCH 46/58] tcp: refresh tcp_mstamp from timers callbacks

[ Upstream commit 4688eb7cf3ae2c2721d1dacff5c1384cba47d176 ]

Only the retransmit timer currently refreshes tcp_mstamp

We should do the same for delayed acks and keepalives.

Even if RFC 7323 does not request it, this is consistent to what linux
did in the past, when TS values were based on jiffies.

Fixes: 385e20706fac ("tcp: use tp->tcp_mstamp in output path")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Cc: Mike Maloney <maloney@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by:  Mike Maloney <maloney@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_timer.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 655dd8d..e9af187 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -264,6 +264,7 @@ void tcp_delack_timer_handler(struct sock *sk)
 			icsk->icsk_ack.pingpong = 0;
 			icsk->icsk_ack.ato      = TCP_ATO_MIN;
 		}
+		tcp_mstamp_refresh(tcp_sk(sk));
 		tcp_send_ack(sk);
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKS);
 	}
@@ -627,6 +628,7 @@ static void tcp_keepalive_timer (unsigned long data)
 		goto out;
 	}
 
+	tcp_mstamp_refresh(tp);
 	if (sk->sk_state == TCP_FIN_WAIT2 && sock_flag(sk, SOCK_DEAD)) {
 		if (tp->linger2 >= 0) {
 			const int tmo = tcp_fin_time(sk) - TCP_TIMEWAIT_LEN;
-- 
2.9.5


From 41c77733c8f0dcd4c73a0a59e1755836ced8141d Mon Sep 17 00:00:00 2001
From: Kamal Heib <kamalh@mellanox.com>
Date: Sun, 29 Oct 2017 04:03:37 +0200
Subject: [PATCH 47/58] net/mlx5: FPGA, return -EINVAL if size is zero

[ Upstream commit bae115a2bb479142605726e6aa130f43f50e801a ]

Currently, if a size of zero is passed to
mlx5_fpga_mem_{read|write}_i2c()
the "err" return value will not be initialized, which triggers gcc
warnings:

[..]/mlx5/core/fpga/sdk.c:87 mlx5_fpga_mem_read_i2c() error:
uninitialized symbol 'err'.
[..]/mlx5/core/fpga/sdk.c:115 mlx5_fpga_mem_write_i2c() error:
uninitialized symbol 'err'.

fix that.

Fixes: a9956d35d199 ('net/mlx5: FPGA, Add SBU infrastructure')
Signed-off-by: Kamal Heib <kamalh@mellanox.com>
Reviewed-by: Yevgeny Kliteynik <kliteyn@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.c
index 3c11d6e..1496296 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.c
@@ -66,6 +66,9 @@ static int mlx5_fpga_mem_read_i2c(struct mlx5_fpga_device *fdev, size_t size,
 	u8 actual_size;
 	int err;
 
+	if (!size)
+		return -EINVAL;
+
 	if (!fdev->mdev)
 		return -ENOTCONN;
 
@@ -95,6 +98,9 @@ static int mlx5_fpga_mem_write_i2c(struct mlx5_fpga_device *fdev, size_t size,
 	u8 actual_size;
 	int err;
 
+	if (!size)
+		return -EINVAL;
+
 	if (!fdev->mdev)
 		return -ENOTCONN;
 
-- 
2.9.5


From 1a2d4ba7c04515463d1e88e9c1f22048874d1154 Mon Sep 17 00:00:00 2001
From: Alexey Kodanev <alexey.kodanev@oracle.com>
Date: Thu, 14 Dec 2017 20:20:00 +0300
Subject: [PATCH 48/58] vxlan: restore dev->mtu setting based on lower device

[ Upstream commit f870c1ff65a6d1f3a083f277280802ee09a5b44d ]

Stefano Brivio says:
    Commit a985343ba906 ("vxlan: refactor verification and
    application of configuration") introduced a change in the
    behaviour of initial MTU setting: earlier, the MTU for a link
    created on top of a given lower device, without an initial MTU
    specification, was set to the MTU of the lower device minus
    headroom as a result of this path in vxlan_dev_configure():

	if (!conf->mtu)
		dev->mtu = lowerdev->mtu -
			   (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);

    which is now gone. Now, the initial MTU, in absence of a
    configured value, is simply set by ether_setup() to ETH_DATA_LEN
    (1500 bytes).

    This breaks userspace expectations in case the MTU of
    the lower device is higher than 1500 bytes minus headroom.

This patch restores the previous behaviour on newlink operation. Since
max_mtu can be negative and we update dev->mtu directly, also check it
for valid minimum.

Reported-by: Junhan Yan <juyan@redhat.com>
Fixes: a985343ba906 ("vxlan: refactor verification and application of configuration")
Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Acked-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index a2f4e52..9e9202b 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -3105,6 +3105,11 @@ static void vxlan_config_apply(struct net_device *dev,
 
 		max_mtu = lowerdev->mtu - (use_ipv6 ? VXLAN6_HEADROOM :
 					   VXLAN_HEADROOM);
+		if (max_mtu < ETH_MIN_MTU)
+			max_mtu = ETH_MIN_MTU;
+
+		if (!changelink && !conf->mtu)
+			dev->mtu = max_mtu;
 	}
 
 	if (dev->mtu > max_mtu)
-- 
2.9.5


From e3fc8ab403a71f166b1773eb3a34f68d2e7330ae Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Fri, 15 Dec 2017 12:40:13 +0100
Subject: [PATCH 49/58] net: sched: fix static key imbalance in case of
 ingress/clsact_init error

[ Upstream commit b59e6979a86384e68b0ab6ffeab11f0034fba82d ]

Move static key increments to the beginning of the init function
so they pair 1:1 with decrements in ingress/clsact_destroy,
which is called in case ingress/clsact_init fails.

Fixes: 6529eaba33f0 ("net: sched: introduce tcf block infractructure")
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_ingress.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c
index 44de4ee..a08a32f 100644
--- a/net/sched/sch_ingress.c
+++ b/net/sched/sch_ingress.c
@@ -59,11 +59,12 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt)
 	struct net_device *dev = qdisc_dev(sch);
 	int err;
 
+	net_inc_ingress_queue();
+
 	err = tcf_block_get(&q->block, &dev->ingress_cl_list);
 	if (err)
 		return err;
 
-	net_inc_ingress_queue();
 	sch->flags |= TCQ_F_CPUSTATS;
 
 	return 0;
@@ -153,6 +154,9 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt)
 	struct net_device *dev = qdisc_dev(sch);
 	int err;
 
+	net_inc_ingress_queue();
+	net_inc_egress_queue();
+
 	err = tcf_block_get(&q->ingress_block, &dev->ingress_cl_list);
 	if (err)
 		return err;
@@ -161,9 +165,6 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt)
 	if (err)
 		return err;
 
-	net_inc_ingress_queue();
-	net_inc_egress_queue();
-
 	sch->flags |= TCQ_F_CPUSTATS;
 
 	return 0;
-- 
2.9.5


From 0e2a5697773a36010f9086fbaf75d2c4064a1e6a Mon Sep 17 00:00:00 2001
From: Calvin Owens <calvinowens@fb.com>
Date: Fri, 8 Dec 2017 09:05:26 -0800
Subject: [PATCH 50/58] bnxt_en: Fix sources of spurious netpoll warnings

[ Upstream commit 2edbdb3159d6f6bd3a9b6e7f789f2b879699a519 ]

After applying 2270bc5da3497945 ("bnxt_en: Fix netpoll handling") and
903649e718f80da2 ("bnxt_en: Improve -ENOMEM logic in NAPI poll loop."),
we still see the following WARN fire:

  ------------[ cut here ]------------
  WARNING: CPU: 0 PID: 1875170 at net/core/netpoll.c:165 netpoll_poll_dev+0x15a/0x160
  bnxt_poll+0x0/0xd0 exceeded budget in poll
  <snip>
  Call Trace:
   [<ffffffff814be5cd>] dump_stack+0x4d/0x70
   [<ffffffff8107e013>] __warn+0xd3/0xf0
   [<ffffffff8107e07f>] warn_slowpath_fmt+0x4f/0x60
   [<ffffffff8179519a>] netpoll_poll_dev+0x15a/0x160
   [<ffffffff81795f38>] netpoll_send_skb_on_dev+0x168/0x250
   [<ffffffff817962fc>] netpoll_send_udp+0x2dc/0x440
   [<ffffffff815fa9be>] write_ext_msg+0x20e/0x250
   [<ffffffff810c8125>] call_console_drivers.constprop.23+0xa5/0x110
   [<ffffffff810c9549>] console_unlock+0x339/0x5b0
   [<ffffffff810c9a88>] vprintk_emit+0x2c8/0x450
   [<ffffffff810c9d5f>] vprintk_default+0x1f/0x30
   [<ffffffff81173df5>] printk+0x48/0x50
   [<ffffffffa0197713>] edac_raw_mc_handle_error+0x563/0x5c0 [edac_core]
   [<ffffffffa0197b9b>] edac_mc_handle_error+0x42b/0x6e0 [edac_core]
   [<ffffffffa01c3a60>] sbridge_mce_output_error+0x410/0x10d0 [sb_edac]
   [<ffffffffa01c47cc>] sbridge_check_error+0xac/0x130 [sb_edac]
   [<ffffffffa0197f3c>] edac_mc_workq_function+0x3c/0x90 [edac_core]
   [<ffffffff81095f8b>] process_one_work+0x19b/0x480
   [<ffffffff810967ca>] worker_thread+0x6a/0x520
   [<ffffffff8109c7c4>] kthread+0xe4/0x100
   [<ffffffff81884c52>] ret_from_fork+0x22/0x40

This happens because we increment rx_pkts on -ENOMEM and -EIO, resulting
in rx_pkts > 0. Fix this by only bumping rx_pkts if we were actually
given a non-zero budget.

Signed-off-by: Calvin Owens <calvinowens@fb.com>
Acked-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index dc5de27..aa764c5 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1875,7 +1875,7 @@ static int bnxt_poll_work(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
 			 * here forever if we consistently cannot allocate
 			 * buffers.
 			 */
-			else if (rc == -ENOMEM)
+			else if (rc == -ENOMEM && budget)
 				rx_pkts++;
 			else if (rc == -EBUSY)	/* partial completion */
 				break;
@@ -1961,7 +1961,7 @@ static int bnxt_poll_nitroa0(struct napi_struct *napi, int budget)
 				cpu_to_le32(RX_CMPL_ERRORS_CRC_ERROR);
 
 			rc = bnxt_rx_pkt(bp, bnapi, &raw_cons, &event);
-			if (likely(rc == -EIO))
+			if (likely(rc == -EIO) && budget)
 				rx_pkts++;
 			else if (rc == -EBUSY)	/* partial completion */
 				break;
-- 
2.9.5


From ea5bc82e82014e3a606636df6f5204f8a4385781 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Wed, 20 Dec 2017 23:21:28 +0000
Subject: [PATCH 51/58] phylink: ensure the PHY interface mode is appropriately
 set

[ Upstream commit 182088aa3c6c7f7c20a2c1dcc9ded4a3fc631f38 ]

When setting the ethtool settings, ensure that the validated PHY
interface mode is propagated to the current link settings, so that
2500BaseX can be selected.

Fixes: 9525ae83959b ("phylink: add phylink infrastructure")
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phylink.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index bcb4755..38d8117 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -948,6 +948,7 @@ int phylink_ethtool_ksettings_set(struct phylink *pl,
 	mutex_lock(&pl->state_mutex);
 	/* Configure the MAC to match the new settings */
 	linkmode_copy(pl->link_config.advertising, our_kset.link_modes.advertising);
+	pl->link_config.interface = config.interface;
 	pl->link_config.speed = our_kset.base.speed;
 	pl->link_config.duplex = our_kset.base.duplex;
 	pl->link_config.an_enabled = our_kset.base.autoneg != AUTONEG_DISABLE;
-- 
2.9.5


From d879f15bdcf5719918ab4cfdc40bc12e00bf57c8 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Wed, 20 Dec 2017 23:21:34 +0000
Subject: [PATCH 52/58] phylink: ensure AN is enabled

[ Upstream commit 74ee0e8c1bf9925c59cc8f1c65c29adf6e4cf603 ]

Ensure that we mark AN as enabled at boot time, rather than leaving
it disabled.  This is noticable if your SFP module is fiber, and
it supports faster speeds than 1G with 2.5G support in place.

Fixes: 9525ae83959b ("phylink: add phylink infrastructure")
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phylink.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 38d8117..4b377b9 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -525,6 +525,7 @@ struct phylink *phylink_create(struct net_device *ndev, struct device_node *np,
 	pl->link_config.pause = MLO_PAUSE_AN;
 	pl->link_config.speed = SPEED_UNKNOWN;
 	pl->link_config.duplex = DUPLEX_UNKNOWN;
+	pl->link_config.an_enabled = true;
 	pl->ops = ops;
 	__set_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state);
 
-- 
2.9.5


From 469c06cbc253fa7a8ef51af3f80ff87e1fe07204 Mon Sep 17 00:00:00 2001
From: Phil Sutter <phil@nwl.cc>
Date: Tue, 19 Dec 2017 15:17:13 +0100
Subject: [PATCH 53/58] ipv4: fib: Fix metrics match when deleting a route

[ Upstream commit d03a45572efa068fa64db211d6d45222660e76c5 ]

The recently added fib_metrics_match() causes a regression for routes
with both RTAX_FEATURES and RTAX_CC_ALGO if the latter has
TCP_CONG_NEEDS_ECN flag set:

| # ip link add d0 type dummy
| # ip link set d0 up
| # ip route add 172.29.29.0/24 dev d0 features ecn congctl dctcp
| # ip route del 172.29.29.0/24 dev d0 features ecn congctl dctcp
| RTNETLINK answers: No such process

During route insertion, fib_convert_metrics() detects that the given CC
algo requires ECN and hence sets DST_FEATURE_ECN_CA bit in
RTAX_FEATURES.

During route deletion though, fib_metrics_match() compares stored
RTAX_FEATURES value with that from userspace (which obviously has no
knowledge about DST_FEATURE_ECN_CA) and fails.

Fixes: 5f9ae3d9e7e4a ("ipv4: do metrics match when looking up and deleting a route")
Signed-off-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_semantics.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 01ed221..aff3751 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -706,7 +706,7 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi)
 
 	nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {
 		int type = nla_type(nla);
-		u32 val;
+		u32 fi_val, val;
 
 		if (!type)
 			continue;
@@ -723,7 +723,11 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi)
 			val = nla_get_u32(nla);
 		}
 
-		if (fi->fib_metrics->metrics[type - 1] != val)
+		fi_val = fi->fib_metrics->metrics[type - 1];
+		if (type == RTAX_FEATURES)
+			fi_val &= ~DST_FEATURE_ECN_CA;
+
+		if (fi_val != val)
 			return false;
 	}
 
-- 
2.9.5


From c345230ef8cfb88b96577cea661c797248e87c87 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Tue, 14 Nov 2017 14:21:32 +0100
Subject: [PATCH 54/58] ipv6: set all.accept_dad to 0 by default

[ Upstream commit 094009531612246d9e13f9e0c3ae2205d7f63a0a ]

With commits 35e015e1f577 and a2d3f3e33853, the global 'accept_dad' flag
is also taken into account (default value is 1). If either global or
per-interface flag is non-zero, DAD will be enabled on a given interface.

This is not backward compatible: before those patches, the user could
disable DAD just by setting the per-interface flag to 0. Now, the
user instead needs to set both flags to 0 to actually disable DAD.

Restore the previous behaviour by setting the default for the global
'accept_dad' flag to 0. This way, DAD is still enabled by default,
as per-interface flags are set to 1 on device creation, but setting
them to 0 is enough to disable DAD on a given interface.

- Before 35e015e1f57a7 and a2d3f3e33853:
          global    per-interface    DAD enabled
[default]   1             1              yes
            X             0              no
            X             1              yes

- After 35e015e1f577 and a2d3f3e33853:
          global    per-interface    DAD enabled
[default]   1             1              yes
            0             0              no
            0             1              yes
            1             0              yes

- After this fix:
          global    per-interface    DAD enabled
            1             1              yes
            0             0              no
[default]   0             1              yes
            1             0              yes

Fixes: 35e015e1f577 ("ipv6: fix net.ipv6.conf.all interface DAD handlers")
Fixes: a2d3f3e33853 ("ipv6: fix net.ipv6.conf.all.accept_dad behaviour for real")
CC: Stefano Brivio <sbrivio@redhat.com>
CC: Matteo Croce <mcroce@redhat.com>
CC: Erik Kline <ek@google.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Acked-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 2ec3940..c5318f5 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -231,7 +231,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
 	.proxy_ndp		= 0,
 	.accept_source_route	= 0,	/* we do not accept RH0 by default. */
 	.disable_ipv6		= 0,
-	.accept_dad		= 1,
+	.accept_dad		= 0,
 	.suppress_frag_ndisc	= 1,
 	.accept_ra_mtu		= 1,
 	.stable_secret		= {
-- 
2.9.5


From ca40baab7bfde13614d7497ca29a411611deb3c7 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Fri, 10 Nov 2017 15:59:52 +0900
Subject: [PATCH 55/58] Revert "mlx5: move affinity hints assignments to
 generic code"

[ Upstream commit 231243c82793428467524227ae02ca451e6a98e7 ]

Before the offending commit, mlx5 core did the IRQ affinity itself,
and it seems that the new generic code have some drawbacks and one
of them is the lack for user ability to modify irq affinity after
the initial affinity values got assigned.

The issue is still being discussed and a solution in the new generic code
is required, until then we need to revert this patch.

This fixes the following issue:
echo <new affinity> > /proc/irq/<x>/smp_affinity
fails with  -EIO

This reverts commit a435393acafbf0ecff4deb3e3cb554b34f0d0664.
Note: kept mlx5_get_vector_affinity in include/linux/mlx5/driver.h since
it is used in mlx5_ib driver.

Fixes: a435393acafb ("mlx5: move affinity hints assignments to generic code")
Cc: Sagi Grimberg <sagi@grimberg.me>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Jes Sorensen <jsorensen@fb.com>
Reported-by: Jes Sorensen <jsorensen@fb.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      |  1 +
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 45 +++++++-------
 drivers/net/ethernet/mellanox/mlx5/core/main.c    | 75 +++++++++++++++++++++--
 include/linux/mlx5/driver.h                       |  1 +
 4 files changed, 93 insertions(+), 29 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 13b5ef9..5fa0716 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -590,6 +590,7 @@ struct mlx5e_channel {
 	struct mlx5_core_dev      *mdev;
 	struct mlx5e_tstamp       *tstamp;
 	int                        ix;
+	int                        cpu;
 };
 
 struct mlx5e_channels {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 517727f..3cdb932 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -71,11 +71,6 @@ struct mlx5e_channel_param {
 	struct mlx5e_cq_param      icosq_cq;
 };
 
-static int mlx5e_get_node(struct mlx5e_priv *priv, int ix)
-{
-	return pci_irq_get_node(priv->mdev->pdev, MLX5_EQ_VEC_COMP_BASE + ix);
-}
-
 static bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
 {
 	return MLX5_CAP_GEN(mdev, striding_rq) &&
@@ -452,17 +447,16 @@ static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq,
 	int wq_sz = mlx5_wq_ll_get_size(&rq->wq);
 	int mtt_sz = mlx5e_get_wqe_mtt_sz();
 	int mtt_alloc = mtt_sz + MLX5_UMR_ALIGN - 1;
-	int node = mlx5e_get_node(c->priv, c->ix);
 	int i;
 
 	rq->mpwqe.info = kzalloc_node(wq_sz * sizeof(*rq->mpwqe.info),
-					GFP_KERNEL, node);
+				      GFP_KERNEL, cpu_to_node(c->cpu));
 	if (!rq->mpwqe.info)
 		goto err_out;
 
 	/* We allocate more than mtt_sz as we will align the pointer */
-	rq->mpwqe.mtt_no_align = kzalloc_node(mtt_alloc * wq_sz,
-					GFP_KERNEL, node);
+	rq->mpwqe.mtt_no_align = kzalloc_node(mtt_alloc * wq_sz, GFP_KERNEL,
+					cpu_to_node(c->cpu));
 	if (unlikely(!rq->mpwqe.mtt_no_align))
 		goto err_free_wqe_info;
 
@@ -570,7 +564,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	int err;
 	int i;
 
-	rqp->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix);
+	rqp->wq.db_numa_node = cpu_to_node(c->cpu);
 
 	err = mlx5_wq_ll_create(mdev, &rqp->wq, rqc_wq, &rq->wq,
 				&rq->wq_ctrl);
@@ -636,8 +630,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	default: /* MLX5_WQ_TYPE_LINKED_LIST */
 		rq->wqe.frag_info =
 			kzalloc_node(wq_sz * sizeof(*rq->wqe.frag_info),
-				     GFP_KERNEL,
-				     mlx5e_get_node(c->priv, c->ix));
+				     GFP_KERNEL, cpu_to_node(c->cpu));
 		if (!rq->wqe.frag_info) {
 			err = -ENOMEM;
 			goto err_rq_wq_destroy;
@@ -1007,13 +1000,13 @@ static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c,
 	sq->uar_map   = mdev->mlx5e_res.bfreg.map;
 	sq->min_inline_mode = params->tx_min_inline_mode;
 
-	param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix);
+	param->wq.db_numa_node = cpu_to_node(c->cpu);
 	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, &sq->wq, &sq->wq_ctrl);
 	if (err)
 		return err;
 	sq->wq.db = &sq->wq.db[MLX5_SND_DBR];
 
-	err = mlx5e_alloc_xdpsq_db(sq, mlx5e_get_node(c->priv, c->ix));
+	err = mlx5e_alloc_xdpsq_db(sq, cpu_to_node(c->cpu));
 	if (err)
 		goto err_sq_wq_destroy;
 
@@ -1060,13 +1053,13 @@ static int mlx5e_alloc_icosq(struct mlx5e_channel *c,
 	sq->channel   = c;
 	sq->uar_map   = mdev->mlx5e_res.bfreg.map;
 
-	param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix);
+	param->wq.db_numa_node = cpu_to_node(c->cpu);
 	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, &sq->wq, &sq->wq_ctrl);
 	if (err)
 		return err;
 	sq->wq.db = &sq->wq.db[MLX5_SND_DBR];
 
-	err = mlx5e_alloc_icosq_db(sq, mlx5e_get_node(c->priv, c->ix));
+	err = mlx5e_alloc_icosq_db(sq, cpu_to_node(c->cpu));
 	if (err)
 		goto err_sq_wq_destroy;
 
@@ -1132,13 +1125,13 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 	if (MLX5_IPSEC_DEV(c->priv->mdev))
 		set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state);
 
-	param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix);
+	param->wq.db_numa_node = cpu_to_node(c->cpu);
 	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, &sq->wq, &sq->wq_ctrl);
 	if (err)
 		return err;
 	sq->wq.db    = &sq->wq.db[MLX5_SND_DBR];
 
-	err = mlx5e_alloc_txqsq_db(sq, mlx5e_get_node(c->priv, c->ix));
+	err = mlx5e_alloc_txqsq_db(sq, cpu_to_node(c->cpu));
 	if (err)
 		goto err_sq_wq_destroy;
 
@@ -1510,8 +1503,8 @@ static int mlx5e_alloc_cq(struct mlx5e_channel *c,
 	struct mlx5_core_dev *mdev = c->priv->mdev;
 	int err;
 
-	param->wq.buf_numa_node = mlx5e_get_node(c->priv, c->ix);
-	param->wq.db_numa_node  = mlx5e_get_node(c->priv, c->ix);
+	param->wq.buf_numa_node = cpu_to_node(c->cpu);
+	param->wq.db_numa_node  = cpu_to_node(c->cpu);
 	param->eq_ix   = c->ix;
 
 	err = mlx5e_alloc_cq_common(mdev, param, cq);
@@ -1610,6 +1603,11 @@ static void mlx5e_close_cq(struct mlx5e_cq *cq)
 	mlx5e_free_cq(cq);
 }
 
+static int mlx5e_get_cpu(struct mlx5e_priv *priv, int ix)
+{
+	return cpumask_first(priv->mdev->priv.irq_info[ix].mask);
+}
+
 static int mlx5e_open_tx_cqs(struct mlx5e_channel *c,
 			     struct mlx5e_params *params,
 			     struct mlx5e_channel_param *cparam)
@@ -1758,12 +1756,13 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 {
 	struct mlx5e_cq_moder icocq_moder = {0, 0};
 	struct net_device *netdev = priv->netdev;
+	int cpu = mlx5e_get_cpu(priv, ix);
 	struct mlx5e_channel *c;
 	unsigned int irq;
 	int err;
 	int eqn;
 
-	c = kzalloc_node(sizeof(*c), GFP_KERNEL, mlx5e_get_node(priv, ix));
+	c = kzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
 	if (!c)
 		return -ENOMEM;
 
@@ -1771,6 +1770,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	c->mdev     = priv->mdev;
 	c->tstamp   = &priv->tstamp;
 	c->ix       = ix;
+	c->cpu      = cpu;
 	c->pdev     = &priv->mdev->pdev->dev;
 	c->netdev   = priv->netdev;
 	c->mkey_be  = cpu_to_be32(priv->mdev->mlx5e_res.mkey.key);
@@ -1859,8 +1859,7 @@ static void mlx5e_activate_channel(struct mlx5e_channel *c)
 	for (tc = 0; tc < c->num_tc; tc++)
 		mlx5e_activate_txqsq(&c->sq[tc]);
 	mlx5e_activate_rq(&c->rq);
-	netif_set_xps_queue(c->netdev,
-		mlx5_get_vector_affinity(c->priv->mdev, c->ix), c->ix);
+	netif_set_xps_queue(c->netdev, get_cpu_mask(c->cpu), c->ix);
 }
 
 static void mlx5e_deactivate_channel(struct mlx5e_channel *c)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 06562c9..8bfc37e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -316,9 +316,6 @@ static int mlx5_alloc_irq_vectors(struct mlx5_core_dev *dev)
 {
 	struct mlx5_priv *priv = &dev->priv;
 	struct mlx5_eq_table *table = &priv->eq_table;
-	struct irq_affinity irqdesc = {
-		.pre_vectors = MLX5_EQ_VEC_COMP_BASE,
-	};
 	int num_eqs = 1 << MLX5_CAP_GEN(dev, log_max_eq);
 	int nvec;
 
@@ -332,10 +329,9 @@ static int mlx5_alloc_irq_vectors(struct mlx5_core_dev *dev)
 	if (!priv->irq_info)
 		goto err_free_msix;
 
-	nvec = pci_alloc_irq_vectors_affinity(dev->pdev,
+	nvec = pci_alloc_irq_vectors(dev->pdev,
 			MLX5_EQ_VEC_COMP_BASE + 1, nvec,
-			PCI_IRQ_MSIX | PCI_IRQ_AFFINITY,
-			&irqdesc);
+			PCI_IRQ_MSIX);
 	if (nvec < 0)
 		return nvec;
 
@@ -621,6 +617,63 @@ u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev)
 	return (u64)timer_l | (u64)timer_h1 << 32;
 }
 
+static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i)
+{
+	struct mlx5_priv *priv  = &mdev->priv;
+	int irq = pci_irq_vector(mdev->pdev, MLX5_EQ_VEC_COMP_BASE + i);
+
+	if (!zalloc_cpumask_var(&priv->irq_info[i].mask, GFP_KERNEL)) {
+		mlx5_core_warn(mdev, "zalloc_cpumask_var failed");
+		return -ENOMEM;
+	}
+
+	cpumask_set_cpu(cpumask_local_spread(i, priv->numa_node),
+			priv->irq_info[i].mask);
+
+	if (IS_ENABLED(CONFIG_SMP) &&
+	    irq_set_affinity_hint(irq, priv->irq_info[i].mask))
+		mlx5_core_warn(mdev, "irq_set_affinity_hint failed, irq 0x%.4x", irq);
+
+	return 0;
+}
+
+static void mlx5_irq_clear_affinity_hint(struct mlx5_core_dev *mdev, int i)
+{
+	struct mlx5_priv *priv  = &mdev->priv;
+	int irq = pci_irq_vector(mdev->pdev, MLX5_EQ_VEC_COMP_BASE + i);
+
+	irq_set_affinity_hint(irq, NULL);
+	free_cpumask_var(priv->irq_info[i].mask);
+}
+
+static int mlx5_irq_set_affinity_hints(struct mlx5_core_dev *mdev)
+{
+	int err;
+	int i;
+
+	for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++) {
+		err = mlx5_irq_set_affinity_hint(mdev, i);
+		if (err)
+			goto err_out;
+	}
+
+	return 0;
+
+err_out:
+	for (i--; i >= 0; i--)
+		mlx5_irq_clear_affinity_hint(mdev, i);
+
+	return err;
+}
+
+static void mlx5_irq_clear_affinity_hints(struct mlx5_core_dev *mdev)
+{
+	int i;
+
+	for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++)
+		mlx5_irq_clear_affinity_hint(mdev, i);
+}
+
 int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn,
 		    unsigned int *irqn)
 {
@@ -1093,6 +1146,12 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 		goto err_stop_eqs;
 	}
 
+	err = mlx5_irq_set_affinity_hints(dev);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to alloc affinity hint cpumask\n");
+		goto err_affinity_hints;
+	}
+
 	err = mlx5_init_fs(dev);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to init flow steering\n");
@@ -1150,6 +1209,9 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 	mlx5_cleanup_fs(dev);
 
 err_fs:
+	mlx5_irq_clear_affinity_hints(dev);
+
+err_affinity_hints:
 	free_comp_eqs(dev);
 
 err_stop_eqs:
@@ -1218,6 +1280,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 
 	mlx5_sriov_detach(dev);
 	mlx5_cleanup_fs(dev);
+	mlx5_irq_clear_affinity_hints(dev);
 	free_comp_eqs(dev);
 	mlx5_stop_eqs(dev);
 	mlx5_put_uars_page(dev, priv->uar);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 401c897..8b3d010 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -546,6 +546,7 @@ struct mlx5_core_sriov {
 };
 
 struct mlx5_irq_info {
+	cpumask_var_t mask;
 	char name[MLX5_MAX_IRQ_NAME];
 };
 
-- 
2.9.5


From d648ca57dd0663704240840909b98d9bcd5510db Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 20 Dec 2017 17:37:49 -0500
Subject: [PATCH 56/58] skbuff: orphan frags before zerocopy clone

[ Upstream commit 268b790679422a89e9ab0685d9f291edae780c98 ]

Call skb_zerocopy_clone after skb_orphan_frags, to avoid duplicate
calls to skb_uarg(skb)->callback for the same data.

skb_zerocopy_clone associates skb_shinfo(skb)->uarg from frag_skb
with each segment. This is only safe for uargs that do refcounting,
which is those that pass skb_orphan_frags without dropping their
shared frags. For others, skb_orphan_frags drops the user frags and
sets the uarg to NULL, after which sock_zerocopy_clone has no effect.

Qemu hangs were reported due to duplicate vhost_net_zerocopy_callback
calls for the same data causing the vhost_net_ubuf_ref_>refcount to
drop below zero.

Link: http://lkml.kernel.org/r/<CAF=yD-LWyCD4Y0aJ9O0e_CHLR+3JOeKicRRTEVCPxgw4XOcqGQ@mail.gmail.com>
Fixes: 1f8b977ab32d ("sock: enable MSG_ZEROCOPY")
Reported-by: Andreas Hartmann <andihartmann@01019freenet.de>
Reported-by: David Hill <dhill@redhat.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 623143d7..3c2e1db 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3657,8 +3657,6 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 
 		skb_shinfo(nskb)->tx_flags |= skb_shinfo(head_skb)->tx_flags &
 					      SKBTX_SHARED_FRAG;
-		if (skb_zerocopy_clone(nskb, head_skb, GFP_ATOMIC))
-			goto err;
 
 		while (pos < offset + len) {
 			if (i >= nfrags) {
@@ -3684,6 +3682,8 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 
 			if (unlikely(skb_orphan_frags(frag_skb, GFP_ATOMIC)))
 				goto err;
+			if (skb_zerocopy_clone(nskb, frag_skb, GFP_ATOMIC))
+				goto err;
 
 			*nskb_frag = *frag;
 			__skb_frag_ref(nskb_frag);
-- 
2.9.5


From 3f8664a346aa918d80f07e49a49873d11809d6d3 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 20 Dec 2017 17:37:50 -0500
Subject: [PATCH 57/58] skbuff: skb_copy_ubufs must release uarg even without
 user frags

[ Upstream commit b90ddd568792bcb0054eaf0f61785c8f80c3bd1c ]

skb_copy_ubufs creates a private copy of frags[] to release its hold
on user frags, then calls uarg->callback to notify the owner.

Call uarg->callback even when no frags exist. This edge case can
happen when zerocopy_sg_from_iter finds enough room in skb_headlen
to copy all the data.

Fixes: 3ece782693c4 ("sock: skb_copy_ubufs support for compound pages")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 3c2e1db..4a10e96 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1182,7 +1182,7 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask)
 	u32 d_off;
 
 	if (!num_frags)
-		return 0;
+		goto release;
 
 	if (skb_shared(skb) || skb_unclone(skb, gfp_mask))
 		return -EINVAL;
@@ -1242,6 +1242,7 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask)
 	__skb_fill_page_desc(skb, new_frags - 1, head, 0, d_off);
 	skb_shinfo(skb)->nr_frags = new_frags;
 
+release:
 	skb_zcopy_clear(skb, false);
 	return 0;
 }
-- 
2.9.5


From 0252746b53c2d95d42fe4589fa15c0e5b47f235d Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Thu, 28 Dec 2017 12:38:13 -0500
Subject: [PATCH 58/58] skbuff: in skb_copy_ubufs unclone before releasing
 zerocopy

skb_copy_ubufs must unclone before it is safe to modify its
skb_shared_info with skb_zcopy_clear.

Commit b90ddd568792 ("skbuff: skb_copy_ubufs must release uarg even
without user frags") ensures that all skbs release their zerocopy
state, even those without frags.

But I forgot an edge case where such an skb arrives that is cloned.

The stack does not build such packets. Vhost/tun skbs have their
frags orphaned before cloning. TCP skbs only attach zerocopy state
when a frag is added.

But if TCP packets can be trimmed or linearized, this might occur.
Tracing the code I found no instance so far (e.g., skb_linearize
ends up calling skb_zcopy_clear if !skb->data_len).

Still, it is non-obvious that no path exists. And it is fragile to
rely on this.

Fixes: b90ddd568792 ("skbuff: skb_copy_ubufs must release uarg even without user frags")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 4a10e96..15fa5ba 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1181,12 +1181,12 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask)
 	int i, new_frags;
 	u32 d_off;
 
-	if (!num_frags)
-		goto release;
-
 	if (skb_shared(skb) || skb_unclone(skb, gfp_mask))
 		return -EINVAL;
 
+	if (!num_frags)
+		goto release;
+
 	new_frags = (__skb_pagelen(skb) + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	for (i = 0; i < new_frags; i++) {
 		page = alloc_page(gfp_mask);
-- 
2.9.5

Re: [PATCHES] Networking

[Greg KH]

On Sat, Dec 30, 2017 at 11:15:02PM -0500, David Miller wrote:
> 
> Thought you'd make it into 2018 without some more networking
> bug fixes?  Think again! :-)
> 
> Please queue up the following networking bug fixes for 4.9.x
> and 4.14.x -stable, respectively.

Nice!

Thanks for all of these, now queued up.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 107 bytes --]


Please queue up the following networking bug fixes for v4.9 and
v4.14 -stable, respecetively.

Thank you!

[-- Attachment #2: net_49.mbox --]
[-- Type: Application/Octet-Stream, Size: 21035 bytes --]

From 664863e6200ae61c2beb615203dc104e9470f580 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Tue, 9 Jan 2018 13:40:41 -0800
Subject: [PATCH 01/12] 8021q: fix a memory leak for VLAN 0 device

[ Upstream commit 78bbb15f2239bc8e663aa20bbe1987c91a0b75f6 ]

A vlan device with vid 0 is allow to creat by not able to be fully
cleaned up by unregister_vlan_dev() which checks for vlan_id!=0.

Also, VLAN 0 is probably not a valid number and it is kinda
"reserved" for HW accelerating devices, but it is probably too
late to reject it from creation even if makes sense. Instead,
just remove the check in unregister_vlan_dev().

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Fixes: ad1afb003939 ("vlan_dev: VLAN 0 should be treated as "no vlan tag" (802.1p packet)")
Cc: Vlad Yasevich <vyasevich@gmail.com>
Cc: Ben Hutchings <ben.hutchings@codethink.co.uk>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/8021q/vlan.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 4a47074d1d7f..c8ea3cf9db85 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -111,12 +111,7 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head)
 		vlan_gvrp_uninit_applicant(real_dev);
 	}
 
-	/* Take it out of our own structures, but be sure to interlock with
-	 * HW accelerating devices or SW vlan input packet processing if
-	 * VLAN is not 0 (leave it there for 802.1p).
-	 */
-	if (vlan_id)
-		vlan_vid_del(real_dev, vlan->vlan_proto, vlan_id);
+	vlan_vid_del(real_dev, vlan->vlan_proto, vlan_id);
 
 	/* Get rid of the vlan's reference to real_dev */
 	dev_put(real_dev);
-- 
2.14.3


From d27fdae03f23f96aab43fac60dbb04397716fb8f Mon Sep 17 00:00:00 2001
From: Eli Cooper <elicooper@gmx.com>
Date: Mon, 25 Dec 2017 10:43:49 +0800
Subject: [PATCH 02/12] ip6_tunnel: disable dst caching if tunnel is dual-stack

[ Upstream commit 23263ec86a5f44312d2899323872468752324107 ]

When an ip6_tunnel is in mode 'any', where the transport layer
protocol can be either 4 or 41, dst_cache must be disabled.

This is because xfrm policies might apply to only one of the two
protocols. Caching dst would cause xfrm policies for one protocol
incorrectly used for the other.

Signed-off-by: Eli Cooper <elicooper@gmx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 11d22d642488..131e6aa954bc 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1080,10 +1080,11 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 			memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr));
 			neigh_release(neigh);
 		}
-	} else if (!(t->parms.flags &
-		     (IP6_TNL_F_USE_ORIG_TCLASS | IP6_TNL_F_USE_ORIG_FWMARK))) {
-		/* enable the cache only only if the routing decision does
-		 * not depend on the current inner header value
+	} else if (t->parms.proto != 0 && !(t->parms.flags &
+					    (IP6_TNL_F_USE_ORIG_TCLASS |
+					     IP6_TNL_F_USE_ORIG_FWMARK))) {
+		/* enable the cache only if neither the outer protocol nor the
+		 * routing decision depends on the current inner header value
 		 */
 		use_cache = true;
 	}
-- 
2.14.3


From 96cec8e98db08940840351981b630177e9f7217e Mon Sep 17 00:00:00 2001
From: Andrii Vladyka <tulup@mail.ru>
Date: Thu, 4 Jan 2018 13:09:17 +0200
Subject: [PATCH 03/12] net: core: fix module type in sock_diag_bind

[ Upstream commit b8fd0823e0770c2d5fdbd865bccf0d5e058e5287 ]

Use AF_INET6 instead of AF_INET in IPv6-related code path

Signed-off-by: Andrii Vladyka <tulup@mail.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock_diag.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index 6b10573cc9fa..d1d9faf3046b 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -295,7 +295,7 @@ static int sock_diag_bind(struct net *net, int group)
 	case SKNLGRP_INET6_UDP_DESTROY:
 		if (!sock_diag_handlers[AF_INET6])
 			request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK,
-				       NETLINK_SOCK_DIAG, AF_INET);
+				       NETLINK_SOCK_DIAG, AF_INET6);
 		break;
 	}
 	return 0;
-- 
2.14.3


From cb9af781659bddfc476354bca47b7794416e0da4 Mon Sep 17 00:00:00 2001
From: Mohamed Ghannam <simo.ghannam@gmail.com>
Date: Tue, 2 Jan 2018 19:44:34 +0000
Subject: [PATCH 04/12] RDS: Heap OOB write in rds_message_alloc_sgs()

[ Upstream commit c095508770aebf1b9218e77026e48345d719b17c ]

When args->nr_local is 0, nr_pages gets also 0 due some size
calculation via rds_rm_size(), which is later used to allocate
pages for DMA, this bug produces a heap Out-Of-Bound write access
to a specific memory region.

Signed-off-by: Mohamed Ghannam <simo.ghannam@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/rdma.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/rds/rdma.c b/net/rds/rdma.c
index de8496e60735..4880f9a2d356 100644
--- a/net/rds/rdma.c
+++ b/net/rds/rdma.c
@@ -524,6 +524,9 @@ int rds_rdma_extra_size(struct rds_rdma_args *args)
 
 	local_vec = (struct rds_iovec __user *)(unsigned long) args->local_vec_addr;
 
+	if (args->nr_local == 0)
+		return -EINVAL;
+
 	/* figure out the number of pages in the vector */
 	for (i = 0; i < args->nr_local; i++) {
 		if (copy_from_user(&vec, &local_vec[i],
-- 
2.14.3


From 171830e6b9f526a00bb62a6404e46ebe24be13bd Mon Sep 17 00:00:00 2001
From: Mohamed Ghannam <simo.ghannam@gmail.com>
Date: Wed, 3 Jan 2018 21:06:06 +0000
Subject: [PATCH 05/12] RDS: null pointer dereference in rds_atomic_free_op

[ Upstream commit 7d11f77f84b27cef452cee332f4e469503084737 ]

set rm->atomic.op_active to 0 when rds_pin_pages() fails
or the user supplied address is invalid,
this prevents a NULL pointer usage in rds_atomic_free_op()

Signed-off-by: Mohamed Ghannam <simo.ghannam@gmail.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/rdma.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/rds/rdma.c b/net/rds/rdma.c
index 4880f9a2d356..f6027f41cd34 100644
--- a/net/rds/rdma.c
+++ b/net/rds/rdma.c
@@ -876,6 +876,7 @@ int rds_cmsg_atomic(struct rds_sock *rs, struct rds_message *rm,
 err:
 	if (page)
 		put_page(page);
+	rm->atomic.op_active = 0;
 	kfree(rm->atomic.op_notifier);
 
 	return ret;
-- 
2.14.3


From 9d182455c87b7ecfec81e83df9874bb6b1783db1 Mon Sep 17 00:00:00 2001
From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Date: Wed, 3 Jan 2018 20:09:49 +0300
Subject: [PATCH 06/12] sh_eth: fix TSU resource handling

[ Upstream commit dfe8266b8dd10e12a731c985b725fcf7f0e537f0 ]

When switching  the driver to the managed device API,  I managed to break
the  case of a  dual Ether devices sharing a single TSU: the 2nd Ether port
wouldn't probe. Iwamatsu-san has tried to fix this but his patch was buggy
and he then dropped the ball...

The solution is to  limit calling devm_request_mem_region() to the first
of  the two  ports  sharing the same TSU, so devm_ioremap_resource() can't
be used anymore for the TSU resource...

Fixes: d5e07e69218f ("sh_eth: use managed device API")
Reported-by: Nobuhiro Iwamatsu <nobuhiro.iwamatsu.yj@renesas.com>
Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/sh_eth.c | 25 ++++++++++++++++++++++---
 1 file changed, 22 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 2140dedab712..dc39958537c7 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -3087,10 +3087,29 @@ static int sh_eth_drv_probe(struct platform_device *pdev)
 	/* ioremap the TSU registers */
 	if (mdp->cd->tsu) {
 		struct resource *rtsu;
+
 		rtsu = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-		mdp->tsu_addr = devm_ioremap_resource(&pdev->dev, rtsu);
-		if (IS_ERR(mdp->tsu_addr)) {
-			ret = PTR_ERR(mdp->tsu_addr);
+		if (!rtsu) {
+			dev_err(&pdev->dev, "no TSU resource\n");
+			ret = -ENODEV;
+			goto out_release;
+		}
+		/* We can only request the  TSU region  for the first port
+		 * of the two  sharing this TSU for the probe to succeed...
+		 */
+		if (devno % 2 == 0 &&
+		    !devm_request_mem_region(&pdev->dev, rtsu->start,
+					     resource_size(rtsu),
+					     dev_name(&pdev->dev))) {
+			dev_err(&pdev->dev, "can't request TSU resource.\n");
+			ret = -EBUSY;
+			goto out_release;
+		}
+		mdp->tsu_addr = devm_ioremap(&pdev->dev, rtsu->start,
+					     resource_size(rtsu));
+		if (!mdp->tsu_addr) {
+			dev_err(&pdev->dev, "TSU region ioremap() failed.\n");
+			ret = -ENOMEM;
 			goto out_release;
 		}
 		mdp->port = devno % 2;
-- 
2.14.3


From c2fa1b8356b84fbf54605d9d1c9c9b847232a722 Mon Sep 17 00:00:00 2001
From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Date: Thu, 4 Jan 2018 21:06:49 +0300
Subject: [PATCH 07/12] sh_eth: fix SH7757 GEther initialization

[ Upstream commit 5133550296d43236439494aa955bfb765a89f615 ]

Renesas  SH7757 has 2 Fast and 2 Gigabit Ether controllers, while the
'sh_eth' driver can only reset and initialize TSU of the first controller
pair. Shimoda-san tried to solve that adding the 'needs_init' member to the
'struct sh_eth_plat_data', however the platform code still never sets this
flag. I think  that we can infer this information from the 'devno' variable
(set  to 'platform_device::id') and reset/init the Ether controller pair
only for an even 'devno'; therefore 'sh_eth_plat_data::needs_init' can be
removed...

Fixes: 150647fb2c31 ("net: sh_eth: change the condition of initialization")
Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/sh_eth.c | 4 ++--
 include/linux/sh_eth.h                | 1 -
 2 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index dc39958537c7..b6816ae00b7a 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -3116,8 +3116,8 @@ static int sh_eth_drv_probe(struct platform_device *pdev)
 		ndev->features = NETIF_F_HW_VLAN_CTAG_FILTER;
 	}
 
-	/* initialize first or needed device */
-	if (!devno || pd->needs_init) {
+	/* Need to init only the first port of the two sharing a TSU */
+	if (devno % 2 == 0) {
 		if (mdp->cd->chip_reset)
 			mdp->cd->chip_reset(ndev);
 
diff --git a/include/linux/sh_eth.h b/include/linux/sh_eth.h
index f2e27e078362..01b3778ba6da 100644
--- a/include/linux/sh_eth.h
+++ b/include/linux/sh_eth.h
@@ -16,7 +16,6 @@ struct sh_eth_plat_data {
 	unsigned char mac_addr[ETH_ALEN];
 	unsigned no_ether_link:1;
 	unsigned ether_link_active_low:1;
-	unsigned needs_init:1;
 };
 
 #endif
-- 
2.14.3


From 3c9091b690efc770759365cdb2a4d874e3cc2bdd Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Wed, 3 Jan 2018 16:46:29 +0100
Subject: [PATCH 08/12] net: stmmac: enable EEE in MII, GMII or RGMII only

[ Upstream commit 879626e3a52630316d817cbda7cec9a5446d1d82 ]

Note in the databook - Section 4.4 - EEE :
" The EEE feature is not supported when the MAC is configured to use the
TBI, RTBI, SMII, RMII or SGMII single PHY interface. Even if the MAC
supports multiple PHY interfaces, you should activate the EEE mode only
when the MAC is operating with GMII, MII, or RGMII interface."

Applying this restriction solves a stability issue observed on Amlogic
gxl platforms operating with RMII interface and the internal PHY.

Fixes: 83bf79b6bb64 ("stmmac: disable at run-time the EEE if not supported")
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Tested-by: Arnaud Patard <arnaud.patard@rtp-net.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c |  6 ++++++
 include/linux/phy.h                               | 11 +++++++++++
 2 files changed, 17 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index adf61a7b1b01..98bbb91336e4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -280,8 +280,14 @@ static void stmmac_eee_ctrl_timer(unsigned long arg)
 bool stmmac_eee_init(struct stmmac_priv *priv)
 {
 	unsigned long flags;
+	int interface = priv->plat->interface;
 	bool ret = false;
 
+	if ((interface != PHY_INTERFACE_MODE_MII) &&
+	    (interface != PHY_INTERFACE_MODE_GMII) &&
+	    !phy_interface_mode_is_rgmii(interface))
+		goto out;
+
 	/* Using PCS we cannot dial with the phy registers at this stage
 	 * so we do not support extra feature like EEE.
 	 */
diff --git a/include/linux/phy.h b/include/linux/phy.h
index a04d69ab7c34..867110c9d707 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -683,6 +683,17 @@ static inline bool phy_is_internal(struct phy_device *phydev)
 	return phydev->is_internal;
 }
 
+/**
+ * phy_interface_mode_is_rgmii - Convenience function for testing if a
+ * PHY interface mode is RGMII (all variants)
+ * @mode: the phy_interface_t enum
+ */
+static inline bool phy_interface_mode_is_rgmii(phy_interface_t mode)
+{
+	return mode >= PHY_INTERFACE_MODE_RGMII &&
+		mode <= PHY_INTERFACE_MODE_RGMII_TXID;
+};
+
 /**
  * phy_interface_is_rgmii - Convenience function for testing if a PHY interface
  * is RGMII (all variants)
-- 
2.14.3


From fc2c37c7a97cac2c49b656e1a56f2998650c53f0 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 10 Jan 2018 03:45:49 -0800
Subject: [PATCH 09/12] ipv6: fix possible mem leaks in ipv6_make_skb()

[ Upstream commit 862c03ee1deb7e19e0f9931682e0294ecd1fcaf9 ]

ip6_setup_cork() might return an error, while memory allocations have
been done and must be rolled back.

Fixes: 6422398c2ab0 ("ipv6: introduce ipv6_make_skb")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Vlad Yasevich <vyasevich@gmail.com>
Reported-by: Mike Maloney <maloney@google.com>
Acked-by:  Mike Maloney <maloney@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_output.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 506efba33a89..388584b8ff31 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1800,9 +1800,10 @@ struct sk_buff *ip6_make_skb(struct sock *sk,
 	cork.base.opt = NULL;
 	v6_cork.opt = NULL;
 	err = ip6_setup_cork(sk, &cork, &v6_cork, ipc6, rt, fl6);
-	if (err)
+	if (err) {
+		ip6_cork_release(&cork, &v6_cork);
 		return ERR_PTR(err);
-
+	}
 	if (ipc6->dontfrag < 0)
 		ipc6->dontfrag = inet6_sk(sk)->dontfrag;
 
-- 
2.14.3


From 6ca851f69251c45da71168f8c1e17b1509c44bfd Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Fri, 29 Dec 2017 10:02:52 -0800
Subject: [PATCH 10/12] ethtool: do not print warning for applications using
 legacy API

[ Upstream commit 71891e2dab6b55a870f8f7735e44a2963860b5c6 ]

In kernel log ths message appears on every boot:
 "warning: `NetworkChangeNo' uses legacy ethtool link settings API,
  link modes are only partially reported"

When ethtool link settings API changed, it started complaining about
usages of old API. Ironically, the original patch was from google but
the application using the legacy API is chrome.

Linux ABI is fixed as much as possible. The kernel must not break it
and should not complain about applications using legacy API's.
This patch just removes the warning since using legacy API's
in Linux is perfectly acceptable.

Fixes: 3f1ac7a700d0 ("net: ethtool: add new ETHTOOL_xLINKSETTINGS API")
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David Decotigny <decot@googlers.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/ethtool.c | 15 ++-------------
 1 file changed, 2 insertions(+), 13 deletions(-)

diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index e9989b835a66..7913771ec474 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -742,15 +742,6 @@ static int ethtool_set_link_ksettings(struct net_device *dev,
 	return dev->ethtool_ops->set_link_ksettings(dev, &link_ksettings);
 }
 
-static void
-warn_incomplete_ethtool_legacy_settings_conversion(const char *details)
-{
-	char name[sizeof(current->comm)];
-
-	pr_info_once("warning: `%s' uses legacy ethtool link settings API, %s\n",
-		     get_task_comm(name, current), details);
-}
-
 /* Query device for its ethtool_cmd settings.
  *
  * Backward compatibility note: for compatibility with legacy ethtool,
@@ -777,10 +768,8 @@ static int ethtool_get_settings(struct net_device *dev, void __user *useraddr)
 							   &link_ksettings);
 		if (err < 0)
 			return err;
-		if (!convert_link_ksettings_to_legacy_settings(&cmd,
-							       &link_ksettings))
-			warn_incomplete_ethtool_legacy_settings_conversion(
-				"link modes are only partially reported");
+		convert_link_ksettings_to_legacy_settings(&cmd,
+							  &link_ksettings);
 
 		/* send a sensible cmd tag back to user */
 		cmd.cmd = ETHTOOL_GSET;
-- 
2.14.3


From d3bf19177bd0b0b403561fbf5a7a3fdd2a3e8dd3 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Mon, 25 Dec 2017 08:57:35 +0100
Subject: [PATCH 11/12] mlxsw: spectrum_router: Fix NULL pointer deref

[ Upstream commit 8764a8267b128405cf383157d5e9a4a3735d2409 ]

When we remove the neighbour associated with a nexthop we should always
refuse to write the nexthop to the adjacency table. Regardless if it is
already present in the table or not.

Otherwise, we risk dereferencing the NULL pointer that was set instead
of the neighbour.

Fixes: a7ff87acd995 ("mlxsw: spectrum_router: Implement next-hop routing")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Alexander Petrovskiy <alexpe@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 9e31a3390154..8aa91ddff287 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -1328,9 +1328,9 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
 static void __mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp_nexthop *nh,
 					    bool removing)
 {
-	if (!removing && !nh->should_offload)
+	if (!removing)
 		nh->should_offload = 1;
-	else if (removing && nh->offloaded)
+	else
 		nh->should_offload = 0;
 	nh->update = 1;
 }
-- 
2.14.3


From 1c048047329a120856ab9c3fb6c902661b623b27 Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@mellanox.com>
Date: Tue, 26 Dec 2017 07:48:51 +0200
Subject: [PATCH 12/12] net/sched: Fix update of lastuse in act modules
 implementing stats_update

[ Upstream commit 3bb23421a504f01551b7cb9dff0e41dbf16656b0 ]

We need to update lastuse to to the most updated value between what
is already set and the new value.
If HW matching fails, i.e. because of an issue, the stats are not updated
but it could be that software did match and updated lastuse.

Fixes: 5712bf9c5c30 ("net/sched: act_mirred: Use passed lastuse argument")
Fixes: 9fea47d93bcc ("net/sched: act_gact: Update statistics when offloaded to hardware")
Signed-off-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Paul Blakey <paulb@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_gact.c   | 2 +-
 net/sched/act_mirred.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index e0aa30f83c6c..9617b42aaf20 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -161,7 +161,7 @@ static void tcf_gact_stats_update(struct tc_action *a, u64 bytes, u32 packets,
 	if (action == TC_ACT_SHOT)
 		this_cpu_ptr(gact->common.cpu_qstats)->drops += packets;
 
-	tm->lastuse = lastuse;
+	tm->lastuse = max_t(u64, tm->lastuse, lastuse);
 }
 
 static int tcf_gact_dump(struct sk_buff *skb, struct tc_action *a,
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 6b07fba5770b..fc3650b06192 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -211,7 +211,7 @@ static void tcf_stats_update(struct tc_action *a, u64 bytes, u32 packets,
 	struct tcf_t *tm = &m->tcf_tm;
 
 	_bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets);
-	tm->lastuse = lastuse;
+	tm->lastuse = max_t(u64, tm->lastuse, lastuse);
 }
 
 static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind,
-- 
2.14.3


[-- Attachment #3: net_414.mbox --]
[-- Type: Application/Octet-Stream, Size: 42218 bytes --]

From 3f2cc7a528029787bf3111019dfe5ac73be9089a Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Tue, 9 Jan 2018 13:40:41 -0800
Subject: [PATCH 01/22] 8021q: fix a memory leak for VLAN 0 device

[ Upstream commit 78bbb15f2239bc8e663aa20bbe1987c91a0b75f6 ]

A vlan device with vid 0 is allow to creat by not able to be fully
cleaned up by unregister_vlan_dev() which checks for vlan_id!=0.

Also, VLAN 0 is probably not a valid number and it is kinda
"reserved" for HW accelerating devices, but it is probably too
late to reject it from creation even if makes sense. Instead,
just remove the check in unregister_vlan_dev().

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Fixes: ad1afb003939 ("vlan_dev: VLAN 0 should be treated as "no vlan tag" (802.1p packet)")
Cc: Vlad Yasevich <vyasevich@gmail.com>
Cc: Ben Hutchings <ben.hutchings@codethink.co.uk>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/8021q/vlan.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 4a72ee4e2ae9..cf2e70003a53 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -111,12 +111,7 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head)
 		vlan_gvrp_uninit_applicant(real_dev);
 	}
 
-	/* Take it out of our own structures, but be sure to interlock with
-	 * HW accelerating devices or SW vlan input packet processing if
-	 * VLAN is not 0 (leave it there for 802.1p).
-	 */
-	if (vlan_id)
-		vlan_vid_del(real_dev, vlan->vlan_proto, vlan_id);
+	vlan_vid_del(real_dev, vlan->vlan_proto, vlan_id);
 
 	/* Get rid of the vlan's reference to real_dev */
 	dev_put(real_dev);
-- 
2.14.3


From ce817079902074dacb6814c8863944b66ffa265b Mon Sep 17 00:00:00 2001
From: Eli Cooper <elicooper@gmx.com>
Date: Mon, 25 Dec 2017 10:43:49 +0800
Subject: [PATCH 02/22] ip6_tunnel: disable dst caching if tunnel is dual-stack

[ Upstream commit 23263ec86a5f44312d2899323872468752324107 ]

When an ip6_tunnel is in mode 'any', where the transport layer
protocol can be either 4 or 41, dst_cache must be disabled.

This is because xfrm policies might apply to only one of the two
protocols. Caching dst would cause xfrm policies for one protocol
incorrectly used for the other.

Signed-off-by: Eli Cooper <elicooper@gmx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index ef958d50746b..3f46121ad139 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1081,10 +1081,11 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 			memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr));
 			neigh_release(neigh);
 		}
-	} else if (!(t->parms.flags &
-		     (IP6_TNL_F_USE_ORIG_TCLASS | IP6_TNL_F_USE_ORIG_FWMARK))) {
-		/* enable the cache only only if the routing decision does
-		 * not depend on the current inner header value
+	} else if (t->parms.proto != 0 && !(t->parms.flags &
+					    (IP6_TNL_F_USE_ORIG_TCLASS |
+					     IP6_TNL_F_USE_ORIG_FWMARK))) {
+		/* enable the cache only if neither the outer protocol nor the
+		 * routing decision depends on the current inner header value
 		 */
 		use_cache = true;
 	}
-- 
2.14.3


From 1a6f34fe0caabc71b59a70fc3328f30bccc36ff2 Mon Sep 17 00:00:00 2001
From: Andrii Vladyka <tulup@mail.ru>
Date: Thu, 4 Jan 2018 13:09:17 +0200
Subject: [PATCH 03/22] net: core: fix module type in sock_diag_bind

[ Upstream commit b8fd0823e0770c2d5fdbd865bccf0d5e058e5287 ]

Use AF_INET6 instead of AF_INET in IPv6-related code path

Signed-off-by: Andrii Vladyka <tulup@mail.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock_diag.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index 217f4e3b82f6..146b50e30659 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -288,7 +288,7 @@ static int sock_diag_bind(struct net *net, int group)
 	case SKNLGRP_INET6_UDP_DESTROY:
 		if (!sock_diag_handlers[AF_INET6])
 			request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK,
-				       NETLINK_SOCK_DIAG, AF_INET);
+				       NETLINK_SOCK_DIAG, AF_INET6);
 		break;
 	}
 	return 0;
-- 
2.14.3


From e4aec99f6a4447083365ed083b584de3c19d8d8a Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Tue, 26 Dec 2017 23:15:12 +0000
Subject: [PATCH 04/22] phylink: ensure we report link down when LOS asserted

[ Upstream commit ac817f5ad066697e4d4d35ec68c974eba2c5f17a ]

Although we disable the netdev carrier, we fail to report in the kernel
log that the link went down.  Fix this.

Fixes: 9525ae83959b ("phylink: add phylink infrastructure")
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phylink.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 4b377b978a0b..cb85307f125b 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -1428,9 +1428,8 @@ static void phylink_sfp_link_down(void *upstream)
 	WARN_ON(!lockdep_rtnl_is_held());
 
 	set_bit(PHYLINK_DISABLE_LINK, &pl->phylink_disable_state);
+	queue_work(system_power_efficient_wq, &pl->resolve);
 	flush_work(&pl->resolve);
-
-	netif_carrier_off(pl->netdev);
 }
 
 static void phylink_sfp_link_up(void *upstream)
-- 
2.14.3


From 4467b6b0afb5d934d0e4a38dd27cbe780f84beee Mon Sep 17 00:00:00 2001
From: Mohamed Ghannam <simo.ghannam@gmail.com>
Date: Tue, 2 Jan 2018 19:44:34 +0000
Subject: [PATCH 05/22] RDS: Heap OOB write in rds_message_alloc_sgs()

[ Upstream commit c095508770aebf1b9218e77026e48345d719b17c ]

When args->nr_local is 0, nr_pages gets also 0 due some size
calculation via rds_rm_size(), which is later used to allocate
pages for DMA, this bug produces a heap Out-Of-Bound write access
to a specific memory region.

Signed-off-by: Mohamed Ghannam <simo.ghannam@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/rdma.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/rds/rdma.c b/net/rds/rdma.c
index bc2f1e0977d6..94729d9da437 100644
--- a/net/rds/rdma.c
+++ b/net/rds/rdma.c
@@ -525,6 +525,9 @@ int rds_rdma_extra_size(struct rds_rdma_args *args)
 
 	local_vec = (struct rds_iovec __user *)(unsigned long) args->local_vec_addr;
 
+	if (args->nr_local == 0)
+		return -EINVAL;
+
 	/* figure out the number of pages in the vector */
 	for (i = 0; i < args->nr_local; i++) {
 		if (copy_from_user(&vec, &local_vec[i],
-- 
2.14.3


From 85ca64f7416b0974dc33bb1be9b91c2d7ae888b7 Mon Sep 17 00:00:00 2001
From: Mohamed Ghannam <simo.ghannam@gmail.com>
Date: Wed, 3 Jan 2018 21:06:06 +0000
Subject: [PATCH 06/22] RDS: null pointer dereference in rds_atomic_free_op

[ Upstream commit 7d11f77f84b27cef452cee332f4e469503084737 ]

set rm->atomic.op_active to 0 when rds_pin_pages() fails
or the user supplied address is invalid,
this prevents a NULL pointer usage in rds_atomic_free_op()

Signed-off-by: Mohamed Ghannam <simo.ghannam@gmail.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/rdma.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/rds/rdma.c b/net/rds/rdma.c
index 94729d9da437..634cfcb7bba6 100644
--- a/net/rds/rdma.c
+++ b/net/rds/rdma.c
@@ -877,6 +877,7 @@ int rds_cmsg_atomic(struct rds_sock *rs, struct rds_message *rm,
 err:
 	if (page)
 		put_page(page);
+	rm->atomic.op_active = 0;
 	kfree(rm->atomic.op_notifier);
 
 	return ret;
-- 
2.14.3


From b17d317d58409f40529ae5ebb2d3971646693f03 Mon Sep 17 00:00:00 2001
From: Fugang Duan <fugang.duan@nxp.com>
Date: Wed, 3 Jan 2018 10:39:29 +0800
Subject: [PATCH 07/22] net: fec: restore dev_id in the cases of probe error

[ Upstream commit e90f686b4358d7d7e5dbaa48b8e78c9a4e41826e ]

The static variable dev_id always plus one before netdev registerred.
It should restore the dev_id value in the cases of probe error.

Signed-off-by: Fugang Duan <fugang.duan@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index faf7cdc97ebf..2250639beef0 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -3543,6 +3543,7 @@ fec_probe(struct platform_device *pdev)
 	of_node_put(phy_node);
 failed_ioremap:
 	free_netdev(ndev);
+	dev_id--;
 
 	return ret;
 }
-- 
2.14.3


From 2bb597933335868634aea23861dfd2279769d748 Mon Sep 17 00:00:00 2001
From: Fugang Duan <fugang.duan@nxp.com>
Date: Wed, 3 Jan 2018 10:39:30 +0800
Subject: [PATCH 08/22] net: fec: defer probe if regulator is not ready

[ Upstream commit 3f38c683033a9a0a2738e7067f449deefabfa3ef ]

Defer probe if regulator is not ready. E.g. some regulator is fixed
regulator controlled by i2c expander gpio, the i2c device may be probed
after the driver, then it should handle the case of defer probe error.

Signed-off-by: Fugang Duan <fugang.duan@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_main.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 2250639beef0..768f031a27d8 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -3458,6 +3458,10 @@ fec_probe(struct platform_device *pdev)
 			goto failed_regulator;
 		}
 	} else {
+		if (PTR_ERR(fep->reg_phy) == -EPROBE_DEFER) {
+			ret = -EPROBE_DEFER;
+			goto failed_regulator;
+		}
 		fep->reg_phy = NULL;
 	}
 
-- 
2.14.3


From 1fbdbe760a9b7100d3cf780f7eab2c07f05a6713 Mon Sep 17 00:00:00 2001
From: Fugang Duan <fugang.duan@nxp.com>
Date: Thu, 4 Jan 2018 10:47:20 +0800
Subject: [PATCH 09/22] net: fec: free/restore resource in related probe error
 pathes

[ Upstream commit d1616f07e8f1a4a490d1791316d4a68906b284aa ]

Fixes in probe error path:
- Restore dev_id before failed_ioremap path.
  Fixes: ("net: fec: restore dev_id in the cases of probe error")
- Call of_node_put(phy_node) before failed_phy path.
  Fixes: ("net: fec: Support phys probed from devicetree and fixed-link")

Signed-off-by: Fugang Duan <fugang.duan@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 768f031a27d8..311539c6625f 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -3543,11 +3543,11 @@ fec_probe(struct platform_device *pdev)
 failed_clk:
 	if (of_phy_is_fixed_link(np))
 		of_phy_deregister_fixed_link(np);
-failed_phy:
 	of_node_put(phy_node);
+failed_phy:
+	dev_id--;
 failed_ioremap:
 	free_netdev(ndev);
-	dev_id--;
 
 	return ret;
 }
-- 
2.14.3


From 9f2bc0471b0f9f07650fc2a35e43586db52e5303 Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Fri, 5 Jan 2018 11:17:17 -0200
Subject: [PATCH 10/22] sctp: do not retransmit upon FragNeeded if PMTU
 discovery is disabled

[ Upstream commit cc35c3d1edf7a8373a1a5daa80a912dec96a9cd5 ]

Currently, if PMTU discovery is disabled on a given transport, but the
configured value is higher than the actual PMTU, it is likely that we
will get some icmp Frag Needed. The issue is, if PMTU discovery is
disabled, we won't update the information and will issue a
retransmission immediately, which may very well trigger another ICMP,
and another retransmission, leading to a loop.

The fix is to simply not trigger immediate retransmissions if PMTU
discovery is disabled on the given transport.

Changes from v2:
- updated stale comment, noticed by Xin Long

Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/input.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/net/sctp/input.c b/net/sctp/input.c
index 621b5ca3fd1c..9320661cc41d 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -399,20 +399,20 @@ void sctp_icmp_frag_needed(struct sock *sk, struct sctp_association *asoc,
 		return;
 	}
 
-	if (t->param_flags & SPP_PMTUD_ENABLE) {
-		/* Update transports view of the MTU */
-		sctp_transport_update_pmtu(t, pmtu);
+	if (!(t->param_flags & SPP_PMTUD_ENABLE))
+		/* We can't allow retransmitting in such case, as the
+		 * retransmission would be sized just as before, and thus we
+		 * would get another icmp, and retransmit again.
+		 */
+		return;
 
-		/* Update association pmtu. */
-		sctp_assoc_sync_pmtu(asoc);
-	}
+	/* Update transports view of the MTU */
+	sctp_transport_update_pmtu(t, pmtu);
 
-	/* Retransmit with the new pmtu setting.
-	 * Normally, if PMTU discovery is disabled, an ICMP Fragmentation
-	 * Needed will never be sent, but if a message was sent before
-	 * PMTU discovery was disabled that was larger than the PMTU, it
-	 * would not be fragmented, so it must be re-transmitted fragmented.
-	 */
+	/* Update association pmtu. */
+	sctp_assoc_sync_pmtu(asoc);
+
+	/* Retransmit with the new pmtu setting. */
 	sctp_retransmit(&asoc->outqueue, t, SCTP_RTXR_PMTUD);
 }
 
-- 
2.14.3


From 2921eff8551e8d7513c15c3cae8dae836adf0598 Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Fri, 5 Jan 2018 11:17:18 -0200
Subject: [PATCH 11/22] sctp: fix the handling of ICMP Frag Needed for too
 small MTUs

[ Upstream commit b6c5734db07079c9410147b32407f2366d584e6c ]

syzbot reported a hang involving SCTP, on which it kept flooding dmesg
with the message:
[  246.742374] sctp: sctp_transport_update_pmtu: Reported pmtu 508 too
low, using default minimum of 512

That happened because whenever SCTP hits an ICMP Frag Needed, it tries
to adjust to the new MTU and triggers an immediate retransmission. But
it didn't consider the fact that MTUs smaller than the SCTP minimum MTU
allowed (512) would not cause the PMTU to change, and issued the
retransmission anyway (thus leading to another ICMP Frag Needed, and so
on).

As IPv4 (ip_rt_min_pmtu=556) and IPv6 (IPV6_MIN_MTU=1280) minimum MTU
are higher than that, sctp_transport_update_pmtu() is changed to
re-fetch the PMTU that got set after our request, and with that, detect
if there was an actual change or not.

The fix, thus, skips the immediate retransmission if the received ICMP
resulted in no change, in the hope that SCTP will select another path.

Note: The value being used for the minimum MTU (512,
SCTP_DEFAULT_MINSEGMENT) is not right and instead it should be (576,
SCTP_MIN_PMTU), but such change belongs to another patch.

Changes from v1:
- do not disable PMTU discovery, in the light of commit
06ad391919b2 ("[SCTP] Don't disable PMTU discovery when mtu is small")
and as suggested by Xin Long.
- changed the way to break the rtx loop by detecting if the icmp
  resulted in a change or not
Changes from v2:
none

See-also: https://lkml.org/lkml/2017/12/22/811
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/structs.h |  2 +-
 net/sctp/input.c           |  8 ++++++--
 net/sctp/transport.c       | 29 +++++++++++++++++++----------
 3 files changed, 26 insertions(+), 13 deletions(-)

diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 0477945de1a3..8e1e1dc490fd 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -955,7 +955,7 @@ void sctp_transport_burst_limited(struct sctp_transport *);
 void sctp_transport_burst_reset(struct sctp_transport *);
 unsigned long sctp_transport_timeout(struct sctp_transport *);
 void sctp_transport_reset(struct sctp_transport *t);
-void sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu);
+bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu);
 void sctp_transport_immediate_rtx(struct sctp_transport *);
 void sctp_transport_dst_release(struct sctp_transport *t);
 void sctp_transport_dst_confirm(struct sctp_transport *t);
diff --git a/net/sctp/input.c b/net/sctp/input.c
index 9320661cc41d..141c9c466ec1 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -406,8 +406,12 @@ void sctp_icmp_frag_needed(struct sock *sk, struct sctp_association *asoc,
 		 */
 		return;
 
-	/* Update transports view of the MTU */
-	sctp_transport_update_pmtu(t, pmtu);
+	/* Update transports view of the MTU. Return if no update was needed.
+	 * If an update wasn't needed/possible, it also doesn't make sense to
+	 * try to retransmit now.
+	 */
+	if (!sctp_transport_update_pmtu(t, pmtu))
+		return;
 
 	/* Update association pmtu. */
 	sctp_assoc_sync_pmtu(asoc);
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index 2d9bd3776bc8..7ef77fd7b52a 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -251,28 +251,37 @@ void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk)
 		transport->pathmtu = SCTP_DEFAULT_MAXSEGMENT;
 }
 
-void sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu)
+bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu)
 {
 	struct dst_entry *dst = sctp_transport_dst_check(t);
+	bool change = true;
 
 	if (unlikely(pmtu < SCTP_DEFAULT_MINSEGMENT)) {
-		pr_warn("%s: Reported pmtu %d too low, using default minimum of %d\n",
-			__func__, pmtu, SCTP_DEFAULT_MINSEGMENT);
-		/* Use default minimum segment size and disable
-		 * pmtu discovery on this transport.
-		 */
-		t->pathmtu = SCTP_DEFAULT_MINSEGMENT;
-	} else {
-		t->pathmtu = pmtu;
+		pr_warn_ratelimited("%s: Reported pmtu %d too low, using default minimum of %d\n",
+				    __func__, pmtu, SCTP_DEFAULT_MINSEGMENT);
+		/* Use default minimum segment instead */
+		pmtu = SCTP_DEFAULT_MINSEGMENT;
 	}
+	pmtu = SCTP_TRUNC4(pmtu);
 
 	if (dst) {
 		dst->ops->update_pmtu(dst, t->asoc->base.sk, NULL, pmtu);
 		dst = sctp_transport_dst_check(t);
 	}
 
-	if (!dst)
+	if (!dst) {
 		t->af_specific->get_dst(t, &t->saddr, &t->fl, t->asoc->base.sk);
+		dst = t->dst;
+	}
+
+	if (dst) {
+		/* Re-fetch, as under layers may have a higher minimum size */
+		pmtu = SCTP_TRUNC4(dst_mtu(dst));
+		change = t->pathmtu != pmtu;
+	}
+	t->pathmtu = pmtu;
+
+	return change;
 }
 
 /* Caches the dst entry and source address for a transport's destination
-- 
2.14.3


From 02753bf8b987336ac48a492f4ed827e028590d3b Mon Sep 17 00:00:00 2001
From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Date: Wed, 3 Jan 2018 20:09:49 +0300
Subject: [PATCH 12/22] sh_eth: fix TSU resource handling

[ Upstream commit dfe8266b8dd10e12a731c985b725fcf7f0e537f0 ]

When switching  the driver to the managed device API,  I managed to break
the  case of a  dual Ether devices sharing a single TSU: the 2nd Ether port
wouldn't probe. Iwamatsu-san has tried to fix this but his patch was buggy
and he then dropped the ball...

The solution is to  limit calling devm_request_mem_region() to the first
of  the two  ports  sharing the same TSU, so devm_ioremap_resource() can't
be used anymore for the TSU resource...

Fixes: d5e07e69218f ("sh_eth: use managed device API")
Reported-by: Nobuhiro Iwamatsu <nobuhiro.iwamatsu.yj@renesas.com>
Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/sh_eth.c | 25 ++++++++++++++++++++++---
 1 file changed, 22 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index d2e88a30f57b..f0513fcce13c 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -3212,10 +3212,29 @@ static int sh_eth_drv_probe(struct platform_device *pdev)
 	/* ioremap the TSU registers */
 	if (mdp->cd->tsu) {
 		struct resource *rtsu;
+
 		rtsu = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-		mdp->tsu_addr = devm_ioremap_resource(&pdev->dev, rtsu);
-		if (IS_ERR(mdp->tsu_addr)) {
-			ret = PTR_ERR(mdp->tsu_addr);
+		if (!rtsu) {
+			dev_err(&pdev->dev, "no TSU resource\n");
+			ret = -ENODEV;
+			goto out_release;
+		}
+		/* We can only request the  TSU region  for the first port
+		 * of the two  sharing this TSU for the probe to succeed...
+		 */
+		if (devno % 2 == 0 &&
+		    !devm_request_mem_region(&pdev->dev, rtsu->start,
+					     resource_size(rtsu),
+					     dev_name(&pdev->dev))) {
+			dev_err(&pdev->dev, "can't request TSU resource.\n");
+			ret = -EBUSY;
+			goto out_release;
+		}
+		mdp->tsu_addr = devm_ioremap(&pdev->dev, rtsu->start,
+					     resource_size(rtsu));
+		if (!mdp->tsu_addr) {
+			dev_err(&pdev->dev, "TSU region ioremap() failed.\n");
+			ret = -ENOMEM;
 			goto out_release;
 		}
 		mdp->port = devno % 2;
-- 
2.14.3


From 86ce1f0a26b6fbc01c77194e09b905b1aa13d323 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Wed, 3 Jan 2018 16:46:29 +0100
Subject: [PATCH 13/22] net: stmmac: enable EEE in MII, GMII or RGMII only

[ Upstream commit 879626e3a52630316d817cbda7cec9a5446d1d82 ]

Note in the databook - Section 4.4 - EEE :
" The EEE feature is not supported when the MAC is configured to use the
TBI, RTBI, SMII, RMII or SGMII single PHY interface. Even if the MAC
supports multiple PHY interfaces, you should activate the EEE mode only
when the MAC is operating with GMII, MII, or RGMII interface."

Applying this restriction solves a stability issue observed on Amlogic
gxl platforms operating with RMII interface and the internal PHY.

Fixes: 83bf79b6bb64 ("stmmac: disable at run-time the EEE if not supported")
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Tested-by: Arnaud Patard <arnaud.patard@rtp-net.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 28c4d6fa096c..0ad12c81a9e4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -364,9 +364,15 @@ static void stmmac_eee_ctrl_timer(unsigned long arg)
 bool stmmac_eee_init(struct stmmac_priv *priv)
 {
 	struct net_device *ndev = priv->dev;
+	int interface = priv->plat->interface;
 	unsigned long flags;
 	bool ret = false;
 
+	if ((interface != PHY_INTERFACE_MODE_MII) &&
+	    (interface != PHY_INTERFACE_MODE_GMII) &&
+	    !phy_interface_mode_is_rgmii(interface))
+		goto out;
+
 	/* Using PCS we cannot dial with the phy registers at this stage
 	 * so we do not support extra feature like EEE.
 	 */
-- 
2.14.3


From d322b6929b96dd7a2694effb509cb3a1ec6741f0 Mon Sep 17 00:00:00 2001
From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Date: Thu, 4 Jan 2018 21:06:49 +0300
Subject: [PATCH 14/22] sh_eth: fix SH7757 GEther initialization

[ Upstream commit 5133550296d43236439494aa955bfb765a89f615 ]

Renesas  SH7757 has 2 Fast and 2 Gigabit Ether controllers, while the
'sh_eth' driver can only reset and initialize TSU of the first controller
pair. Shimoda-san tried to solve that adding the 'needs_init' member to the
'struct sh_eth_plat_data', however the platform code still never sets this
flag. I think  that we can infer this information from the 'devno' variable
(set  to 'platform_device::id') and reset/init the Ether controller pair
only for an even 'devno'; therefore 'sh_eth_plat_data::needs_init' can be
removed...

Fixes: 150647fb2c31 ("net: sh_eth: change the condition of initialization")
Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/sh_eth.c | 4 ++--
 include/linux/sh_eth.h                | 1 -
 2 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index f0513fcce13c..db31963c5d9d 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -3241,8 +3241,8 @@ static int sh_eth_drv_probe(struct platform_device *pdev)
 		ndev->features = NETIF_F_HW_VLAN_CTAG_FILTER;
 	}
 
-	/* initialize first or needed device */
-	if (!devno || pd->needs_init) {
+	/* Need to init only the first port of the two sharing a TSU */
+	if (devno % 2 == 0) {
 		if (mdp->cd->chip_reset)
 			mdp->cd->chip_reset(ndev);
 
diff --git a/include/linux/sh_eth.h b/include/linux/sh_eth.h
index ff3642d267f7..94081e9a5010 100644
--- a/include/linux/sh_eth.h
+++ b/include/linux/sh_eth.h
@@ -17,7 +17,6 @@ struct sh_eth_plat_data {
 	unsigned char mac_addr[ETH_ALEN];
 	unsigned no_ether_link:1;
 	unsigned ether_link_active_low:1;
-	unsigned needs_init:1;
 };
 
 #endif
-- 
2.14.3


From c7755c564d4fc3111692afd72b1838b73f13383f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 10 Jan 2018 03:45:49 -0800
Subject: [PATCH 15/22] ipv6: fix possible mem leaks in ipv6_make_skb()

[ Upstream commit 862c03ee1deb7e19e0f9931682e0294ecd1fcaf9 ]

ip6_setup_cork() might return an error, while memory allocations have
been done and must be rolled back.

Fixes: 6422398c2ab0 ("ipv6: introduce ipv6_make_skb")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Vlad Yasevich <vyasevich@gmail.com>
Reported-by: Mike Maloney <maloney@google.com>
Acked-by:  Mike Maloney <maloney@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_output.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index f7dd51c42314..688ba5f7516b 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1735,9 +1735,10 @@ struct sk_buff *ip6_make_skb(struct sock *sk,
 	cork.base.opt = NULL;
 	v6_cork.opt = NULL;
 	err = ip6_setup_cork(sk, &cork, &v6_cork, ipc6, rt, fl6);
-	if (err)
+	if (err) {
+		ip6_cork_release(&cork, &v6_cork);
 		return ERR_PTR(err);
-
+	}
 	if (ipc6->dontfrag < 0)
 		ipc6->dontfrag = inet6_sk(sk)->dontfrag;
 
-- 
2.14.3


From 0bd0de5988fa97a468ed2dc68ec6947a4a48b329 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Fri, 29 Dec 2017 10:02:52 -0800
Subject: [PATCH 16/22] ethtool: do not print warning for applications using
 legacy API

[ Upstream commit 71891e2dab6b55a870f8f7735e44a2963860b5c6 ]

In kernel log ths message appears on every boot:
 "warning: `NetworkChangeNo' uses legacy ethtool link settings API,
  link modes are only partially reported"

When ethtool link settings API changed, it started complaining about
usages of old API. Ironically, the original patch was from google but
the application using the legacy API is chrome.

Linux ABI is fixed as much as possible. The kernel must not break it
and should not complain about applications using legacy API's.
This patch just removes the warning since using legacy API's
in Linux is perfectly acceptable.

Fixes: 3f1ac7a700d0 ("net: ethtool: add new ETHTOOL_xLINKSETTINGS API")
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David Decotigny <decot@googlers.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/ethtool.c | 15 ++-------------
 1 file changed, 2 insertions(+), 13 deletions(-)

diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 9a9a3d77e327..d374a904f1b1 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -754,15 +754,6 @@ static int ethtool_set_link_ksettings(struct net_device *dev,
 	return dev->ethtool_ops->set_link_ksettings(dev, &link_ksettings);
 }
 
-static void
-warn_incomplete_ethtool_legacy_settings_conversion(const char *details)
-{
-	char name[sizeof(current->comm)];
-
-	pr_info_once("warning: `%s' uses legacy ethtool link settings API, %s\n",
-		     get_task_comm(name, current), details);
-}
-
 /* Query device for its ethtool_cmd settings.
  *
  * Backward compatibility note: for compatibility with legacy ethtool,
@@ -789,10 +780,8 @@ static int ethtool_get_settings(struct net_device *dev, void __user *useraddr)
 							   &link_ksettings);
 		if (err < 0)
 			return err;
-		if (!convert_link_ksettings_to_legacy_settings(&cmd,
-							       &link_ksettings))
-			warn_incomplete_ethtool_legacy_settings_conversion(
-				"link modes are only partially reported");
+		convert_link_ksettings_to_legacy_settings(&cmd,
+							  &link_ksettings);
 
 		/* send a sensible cmd tag back to user */
 		cmd.cmd = ETHTOOL_GSET;
-- 
2.14.3


From e84e232bcf8b924bb532ea38cbaad586a5e7b0b1 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Mon, 25 Dec 2017 08:57:35 +0100
Subject: [PATCH 17/22] mlxsw: spectrum_router: Fix NULL pointer deref

[ Upstream commit 8764a8267b128405cf383157d5e9a4a3735d2409 ]

When we remove the neighbour associated with a nexthop we should always
refuse to write the nexthop to the adjacency table. Regardless if it is
already present in the table or not.

Otherwise, we risk dereferencing the NULL pointer that was set instead
of the neighbour.

Fixes: a7ff87acd995 ("mlxsw: spectrum_router: Implement next-hop routing")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Alexander Petrovskiy <alexpe@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 5189022a1c8c..c23cc51bb5a5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -2536,7 +2536,7 @@ static void __mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp_nexthop *nh,
 {
 	if (!removing)
 		nh->should_offload = 1;
-	else if (nh->offloaded)
+	else
 		nh->should_offload = 0;
 	nh->update = 1;
 }
-- 
2.14.3


From fa9a868f6da52b408fcded10dff605dd63434975 Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@mellanox.com>
Date: Tue, 26 Dec 2017 07:48:51 +0200
Subject: [PATCH 18/22] net/sched: Fix update of lastuse in act modules
 implementing stats_update

[ Upstream commit 3bb23421a504f01551b7cb9dff0e41dbf16656b0 ]

We need to update lastuse to to the most updated value between what
is already set and the new value.
If HW matching fails, i.e. because of an issue, the stats are not updated
but it could be that software did match and updated lastuse.

Fixes: 5712bf9c5c30 ("net/sched: act_mirred: Use passed lastuse argument")
Fixes: 9fea47d93bcc ("net/sched: act_gact: Update statistics when offloaded to hardware")
Signed-off-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Paul Blakey <paulb@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_gact.c   | 2 +-
 net/sched/act_mirred.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index e29a48ef7fc3..a0ac42b3ed06 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -159,7 +159,7 @@ static void tcf_gact_stats_update(struct tc_action *a, u64 bytes, u32 packets,
 	if (action == TC_ACT_SHOT)
 		this_cpu_ptr(gact->common.cpu_qstats)->drops += packets;
 
-	tm->lastuse = lastuse;
+	tm->lastuse = max_t(u64, tm->lastuse, lastuse);
 }
 
 static int tcf_gact_dump(struct sk_buff *skb, struct tc_action *a,
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 416627c66f08..6ce8de373f83 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -238,7 +238,7 @@ static void tcf_stats_update(struct tc_action *a, u64 bytes, u32 packets,
 	struct tcf_t *tm = &m->tcf_tm;
 
 	_bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets);
-	tm->lastuse = lastuse;
+	tm->lastuse = max_t(u64, tm->lastuse, lastuse);
 }
 
 static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind,
-- 
2.14.3


From 3923e1d06ce996839c010cfe2aa921506f129ab4 Mon Sep 17 00:00:00 2001
From: Mathieu Xhonneux <m.xhonneux@gmail.com>
Date: Wed, 10 Jan 2018 13:35:49 +0000
Subject: [PATCH 19/22] ipv6: sr: fix TLVs not being copied using setsockopt

[ Upstream commit ccc12b11c5332c84442ef120dcd631523be75089 ]

Function ipv6_push_rthdr4 allows to add an IPv6 Segment Routing Header
to a socket through setsockopt, but the current implementation doesn't
copy possible TLVs at the end of the SRH received from userspace.

Therefore, the execution of the following branch if (sr_has_hmac(sr_phdr))
{ ... } will never complete since the len and type fields of a possible
HMAC TLV are not copied, hence seg6_get_tlv_hmac will return an error,
and the HMAC will not be computed.

This commit adds a memcpy in case TLVs have been appended to the SRH.

Fixes: a149e7c7ce81 ("ipv6: sr: add support for SRH injection through setsockopt")
Acked-by: David Lebrun <dlebrun@google.com>
Signed-off-by: Mathieu Xhonneux <m.xhonneux@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/exthdrs.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 95516138e861..d6189c2a35e4 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -884,6 +884,15 @@ static void ipv6_push_rthdr4(struct sk_buff *skb, u8 *proto,
 	sr_phdr->segments[0] = **addr_p;
 	*addr_p = &sr_ihdr->segments[sr_ihdr->segments_left];
 
+	if (sr_ihdr->hdrlen > hops * 2) {
+		int tlvs_offset, tlvs_length;
+
+		tlvs_offset = (1 + hops * 2) << 3;
+		tlvs_length = (sr_ihdr->hdrlen - hops * 2) << 3;
+		memcpy((char *)sr_phdr + tlvs_offset,
+		       (char *)sr_ihdr + tlvs_offset, tlvs_length);
+	}
+
 #ifdef CONFIG_IPV6_SEG6_HMAC
 	if (sr_has_hmac(sr_phdr)) {
 		struct net *net = NULL;
-- 
2.14.3


From 779b121a72747e11bb5f7cf8dbaaf15e13489ef7 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Mon, 25 Dec 2017 09:05:33 +0100
Subject: [PATCH 20/22] mlxsw: spectrum: Relax sanity checks during enslavement

[ Upstream commit 90045fc9c78855bdc625a0ab185d97b72a937613 ]

Since commit 25cc72a33835 ("mlxsw: spectrum: Forbid linking to devices that
have uppers") the driver forbids enslavement to netdevs that already
have uppers of their own, as this can result in various ordering
problems.

This requirement proved to be too strict for some users who need to be
able to enslave ports to a bridge that already has uppers. In this case,
we can allow the enslavement if the bridge is already known to us, as
any configuration performed on top of the bridge was already reflected
to the device.

Fixes: 25cc72a33835 ("mlxsw: spectrum: Forbid linking to devices that have uppers")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Alexander Petrovskiy <alexpe@mellanox.com>
Tested-by: Alexander Petrovskiy <alexpe@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c           | 11 +++++++++--
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h           |  2 ++
 drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c |  6 ++++++
 3 files changed, 17 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 3ead7439821c..99bd6e88ebc7 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4235,7 +4235,10 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev,
 			return -EINVAL;
 		if (!info->linking)
 			break;
-		if (netdev_has_any_upper_dev(upper_dev))
+		if (netdev_has_any_upper_dev(upper_dev) &&
+		    (!netif_is_bridge_master(upper_dev) ||
+		     !mlxsw_sp_bridge_device_is_offloaded(mlxsw_sp,
+							  upper_dev)))
 			return -EINVAL;
 		if (netif_is_lag_master(upper_dev) &&
 		    !mlxsw_sp_master_lag_check(mlxsw_sp, upper_dev,
@@ -4347,6 +4350,7 @@ static int mlxsw_sp_netdevice_port_vlan_event(struct net_device *vlan_dev,
 					      u16 vid)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	struct netdev_notifier_changeupper_info *info = ptr;
 	struct net_device *upper_dev;
 	int err = 0;
@@ -4358,7 +4362,10 @@ static int mlxsw_sp_netdevice_port_vlan_event(struct net_device *vlan_dev,
 			return -EINVAL;
 		if (!info->linking)
 			break;
-		if (netdev_has_any_upper_dev(upper_dev))
+		if (netdev_has_any_upper_dev(upper_dev) &&
+		    (!netif_is_bridge_master(upper_dev) ||
+		     !mlxsw_sp_bridge_device_is_offloaded(mlxsw_sp,
+							  upper_dev)))
 			return -EINVAL;
 		break;
 	case NETDEV_CHANGEUPPER:
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 84ce83acdc19..88892d47acae 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -326,6 +326,8 @@ int mlxsw_sp_port_bridge_join(struct mlxsw_sp_port *mlxsw_sp_port,
 void mlxsw_sp_port_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_port,
 				struct net_device *brport_dev,
 				struct net_device *br_dev);
+bool mlxsw_sp_bridge_device_is_offloaded(const struct mlxsw_sp *mlxsw_sp,
+					 const struct net_device *br_dev);
 
 /* spectrum.c */
 int mlxsw_sp_port_ets_set(struct mlxsw_sp_port *mlxsw_sp_port,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index d39ffbfcc436..f5863e5bec81 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -134,6 +134,12 @@ mlxsw_sp_bridge_device_find(const struct mlxsw_sp_bridge *bridge,
 	return NULL;
 }
 
+bool mlxsw_sp_bridge_device_is_offloaded(const struct mlxsw_sp *mlxsw_sp,
+					 const struct net_device *br_dev)
+{
+	return !!mlxsw_sp_bridge_device_find(mlxsw_sp->bridge, br_dev);
+}
+
 static struct mlxsw_sp_bridge_device *
 mlxsw_sp_bridge_device_create(struct mlxsw_sp_bridge *bridge,
 			      struct net_device *br_dev)
-- 
2.14.3


From 2351b9c5726f7815f0738c6d46b54b67480d3e07 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Tue, 26 Dec 2017 23:15:17 +0000
Subject: [PATCH 21/22] sfp: fix sfp-bus oops when removing socket/upstream

[ Upstream commit 0b2122e4934c7783d336397864e34ee53aad0965 ]

When we remove a socket or upstream, and the other side isn't
registered, we dereference a NULL pointer, causing a kernel oops.
Fix this.

Fixes: ce0aa27ff3f6 ("sfp: add sfp-bus to bridge between network devices and sfp cages")
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/sfp-bus.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c
index 5cb5384697ea..7ae815bee52d 100644
--- a/drivers/net/phy/sfp-bus.c
+++ b/drivers/net/phy/sfp-bus.c
@@ -359,7 +359,8 @@ EXPORT_SYMBOL_GPL(sfp_register_upstream);
 void sfp_unregister_upstream(struct sfp_bus *bus)
 {
 	rtnl_lock();
-	sfp_unregister_bus(bus);
+	if (bus->sfp)
+		sfp_unregister_bus(bus);
 	bus->upstream = NULL;
 	bus->netdev = NULL;
 	rtnl_unlock();
@@ -464,7 +465,8 @@ EXPORT_SYMBOL_GPL(sfp_register_socket);
 void sfp_unregister_socket(struct sfp_bus *bus)
 {
 	rtnl_lock();
-	sfp_unregister_bus(bus);
+	if (bus->netdev)
+		sfp_unregister_bus(bus);
 	bus->sfp_dev = NULL;
 	bus->sfp = NULL;
 	bus->socket_ops = NULL;
-- 
2.14.3


From 03c69b85da067c815dbd1043e5e54548c8ca8e4e Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 12 Jan 2018 16:09:58 -0500
Subject: [PATCH 22/22] Revert "Revert "xfrm: Fix stack-out-of-bounds read in
 xfrm_state_find.""

This reverts commit 94802151894d482e82c324edf2c658f8e6b96508.

It breaks transport mode when the policy template has
wildcard addresses configured.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/xfrm/xfrm_policy.c | 29 +++++++++++------------------
 1 file changed, 11 insertions(+), 18 deletions(-)

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 6bc16bb61b55..2a6093840e7e 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1362,36 +1362,29 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl,
 	struct net *net = xp_net(policy);
 	int nx;
 	int i, error;
-	xfrm_address_t *daddr = xfrm_flowi_daddr(fl, family);
-	xfrm_address_t *saddr = xfrm_flowi_saddr(fl, family);
 	xfrm_address_t tmp;
 
 	for (nx = 0, i = 0; i < policy->xfrm_nr; i++) {
 		struct xfrm_state *x;
-		xfrm_address_t *remote = daddr;
-		xfrm_address_t *local  = saddr;
+		xfrm_address_t *local;
+		xfrm_address_t *remote;
 		struct xfrm_tmpl *tmpl = &policy->xfrm_vec[i];
 
-		if (tmpl->mode == XFRM_MODE_TUNNEL ||
-		    tmpl->mode == XFRM_MODE_BEET) {
-			remote = &tmpl->id.daddr;
-			local = &tmpl->saddr;
-			if (xfrm_addr_any(local, tmpl->encap_family)) {
-				error = xfrm_get_saddr(net, fl->flowi_oif,
-						       &tmp, remote,
-						       tmpl->encap_family, 0);
-				if (error)
-					goto fail;
-				local = &tmp;
-			}
+		remote = &tmpl->id.daddr;
+		local = &tmpl->saddr;
+		if (xfrm_addr_any(local, tmpl->encap_family)) {
+			error = xfrm_get_saddr(net, fl->flowi_oif,
+					       &tmp, remote,
+					       tmpl->encap_family, 0);
+			if (error)
+				goto fail;
+			local = &tmp;
 		}
 
 		x = xfrm_state_find(remote, local, fl, tmpl, policy, &error, family);
 
 		if (x && x->km.state == XFRM_STATE_VALID) {
 			xfrm[nx++] = x;
-			daddr = remote;
-			saddr = local;
 			continue;
 		}
 		if (x) {
-- 
2.14.3

Re: [PATCHES] Networking

[Greg KH]

On Fri, Jan 12, 2018 at 04:12:07PM -0500, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.9 and
> v4.14 -stable, respecetively.

Thanks for these, now all queued up.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 106 bytes --]


Please queue up the following networking bug fixes for v4.9
and v4.14 -stable, respectively.

Thank you.

[-- Attachment #2: net_49.mbox --]
[-- Type: Application/Octet-Stream, Size: 57900 bytes --]

From ac81f45d2e3dae761d383d5c05718d0c0404dd2b Mon Sep 17 00:00:00 2001
From: Alexey Kodanev <alexey.kodanev@oracle.com>
Date: Fri, 26 Jan 2018 15:14:16 +0300
Subject: [PATCH 01/23] dccp: don't restart ccid2_hc_tx_rto_expire() if sk in
 closed state

[ Upstream commit dd5684ecae3bd8e44b644f50e2c12c7e57fdfef5 ]

ccid2_hc_tx_rto_expire() timer callback always restarts the timer
again and can run indefinitely (unless it is stopped outside), and after
commit 120e9dabaf55 ("dccp: defer ccid_hc_tx_delete() at dismantle time"),
which moved ccid_hc_tx_delete() (also includes sk_stop_timer()) from
dccp_destroy_sock() to sk_destruct(), this started to happen quite often.
The timer prevents releasing the socket, as a result, sk_destruct() won't
be called.

Found with LTP/dccp_ipsec tests running on the bonding device,
which later couldn't be unloaded after the tests were completed:

  unregister_netdevice: waiting for bond0 to become free. Usage count = 148

Fixes: 2a91aa396739 ("[DCCP] CCID2: Initial CCID2 (TCP-Like) implementation")
Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ccids/ccid2.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c
index 5e3a7302f774..7753681195c1 100644
--- a/net/dccp/ccids/ccid2.c
+++ b/net/dccp/ccids/ccid2.c
@@ -140,6 +140,9 @@ static void ccid2_hc_tx_rto_expire(unsigned long data)
 
 	ccid2_pr_debug("RTO_EXPIRE\n");
 
+	if (sk->sk_state == DCCP_CLOSED)
+		goto out;
+
 	/* back-off timer */
 	hc->tx_rto <<= 1;
 	if (hc->tx_rto > DCCP_RTO_MAX)
-- 
2.14.3


From f14e18e1fffedd6fbc789fbeac7e6298987873f4 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben.hutchings@codethink.co.uk>
Date: Mon, 22 Jan 2018 20:06:42 +0000
Subject: [PATCH 02/23] ipv6: Fix getsockopt() for sockets with default
 IPV6_AUTOFLOWLABEL

[ Upstream commit e9191ffb65d8e159680ce0ad2224e1acbde6985c ]

Commit 513674b5a2c9 ("net: reevalulate autoflowlabel setting after
sysctl setting") removed the initialisation of
ipv6_pinfo::autoflowlabel and added a second flag to indicate
whether this field or the net namespace default should be used.

The getsockopt() handling for this case was not updated, so it
currently returns 0 for all sockets for which IPV6_AUTOFLOWLABEL is
not explicitly enabled.  Fix it to return the effective value, whether
that has been set at the socket or net namespace level.

Fixes: 513674b5a2c9 ("net: reevalulate autoflowlabel setting after sysctl ...")
Signed-off-by: Ben Hutchings <ben.hutchings@codethink.co.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h       | 1 +
 net/ipv6/ip6_output.c    | 2 +-
 net/ipv6/ipv6_sockglue.c | 2 +-
 3 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 615ce0abba9c..e64210c98c2b 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -290,6 +290,7 @@ int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq,
 			   int flags);
 int ip6_flowlabel_init(void);
 void ip6_flowlabel_cleanup(void);
+bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np);
 
 static inline void fl6_sock_release(struct ip6_flowlabel *fl)
 {
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 388584b8ff31..6d000c0001fa 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -156,7 +156,7 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 			    !(IP6CB(skb)->flags & IP6SKB_REROUTED));
 }
 
-static bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np)
+bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np)
 {
 	if (!np->autoflowlabel_set)
 		return ip6_default_np_autolabel(net);
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 6e3871c7f8f7..bcea985dd76b 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -1316,7 +1316,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case IPV6_AUTOFLOWLABEL:
-		val = np->autoflowlabel;
+		val = ip6_autoflowlabel(sock_net(sk), np);
 		break;
 
 	default:
-- 
2.14.3


From 819ccc1028b0cfa3753b9d19f0819db6bf022d6e Mon Sep 17 00:00:00 2001
From: Mike Maloney <maloney@google.com>
Date: Wed, 10 Jan 2018 12:45:10 -0500
Subject: [PATCH 03/23] ipv6: fix udpv6 sendmsg crash caused by too small MTU

[ Upstream commit 749439bfac6e1a2932c582e2699f91d329658196 ]

The logic in __ip6_append_data() assumes that the MTU is at least large
enough for the headers.  A device's MTU may be adjusted after being
added while sendmsg() is processing data, resulting in
__ip6_append_data() seeing any MTU.  For an mtu smaller than the size of
the fragmentation header, the math results in a negative 'maxfraglen',
which causes problems when refragmenting any previous skb in the
skb_write_queue, leaving it possibly malformed.

Instead sendmsg returns EINVAL when the mtu is calculated to be less
than IPV6_MIN_MTU.

Found by syzkaller:
kernel BUG at ./include/linux/skbuff.h:2064!
invalid opcode: 0000 [#1] SMP KASAN
Dumping ftrace buffer:
   (ftrace buffer empty)
Modules linked in:
CPU: 1 PID: 14216 Comm: syz-executor5 Not tainted 4.13.0-rc4+ #2
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
task: ffff8801d0b68580 task.stack: ffff8801ac6b8000
RIP: 0010:__skb_pull include/linux/skbuff.h:2064 [inline]
RIP: 0010:__ip6_make_skb+0x18cf/0x1f70 net/ipv6/ip6_output.c:1617
RSP: 0018:ffff8801ac6bf570 EFLAGS: 00010216
RAX: 0000000000010000 RBX: 0000000000000028 RCX: ffffc90003cce000
RDX: 00000000000001b8 RSI: ffffffff839df06f RDI: ffff8801d9478ca0
RBP: ffff8801ac6bf780 R08: ffff8801cc3f1dbc R09: 0000000000000000
R10: ffff8801ac6bf7a0 R11: 43cb4b7b1948a9e7 R12: ffff8801cc3f1dc8
R13: ffff8801cc3f1d40 R14: 0000000000001036 R15: dffffc0000000000
FS:  00007f43d740c700(0000) GS:ffff8801dc100000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f7834984000 CR3: 00000001d79b9000 CR4: 00000000001406e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 ip6_finish_skb include/net/ipv6.h:911 [inline]
 udp_v6_push_pending_frames+0x255/0x390 net/ipv6/udp.c:1093
 udpv6_sendmsg+0x280d/0x31a0 net/ipv6/udp.c:1363
 inet_sendmsg+0x11f/0x5e0 net/ipv4/af_inet.c:762
 sock_sendmsg_nosec net/socket.c:633 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:643
 SYSC_sendto+0x352/0x5a0 net/socket.c:1750
 SyS_sendto+0x40/0x50 net/socket.c:1718
 entry_SYSCALL_64_fastpath+0x1f/0xbe
RIP: 0033:0x4512e9
RSP: 002b:00007f43d740bc08 EFLAGS: 00000216 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 00000000007180a8 RCX: 00000000004512e9
RDX: 000000000000002e RSI: 0000000020d08000 RDI: 0000000000000005
RBP: 0000000000000086 R08: 00000000209c1000 R09: 000000000000001c
R10: 0000000000040800 R11: 0000000000000216 R12: 00000000004b9c69
R13: 00000000ffffffff R14: 0000000000000005 R15: 00000000202c2000
Code: 9e 01 fe e9 c5 e8 ff ff e8 7f 9e 01 fe e9 4a ea ff ff 48 89 f7 e8 52 9e 01 fe e9 aa eb ff ff e8 a8 b6 cf fd 0f 0b e8 a1 b6 cf fd <0f> 0b 49 8d 45 78 4d 8d 45 7c 48 89 85 78 fe ff ff 49 8d 85 ba
RIP: __skb_pull include/linux/skbuff.h:2064 [inline] RSP: ffff8801ac6bf570
RIP: __ip6_make_skb+0x18cf/0x1f70 net/ipv6/ip6_output.c:1617 RSP: ffff8801ac6bf570

Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Mike Maloney <maloney@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_output.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 6d000c0001fa..af98bbe7af0f 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1260,14 +1260,16 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
 	v6_cork->tclass = ipc6->tclass;
 	if (rt->dst.flags & DST_XFRM_TUNNEL)
 		mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
-		      rt->dst.dev->mtu : dst_mtu(&rt->dst);
+		      READ_ONCE(rt->dst.dev->mtu) : dst_mtu(&rt->dst);
 	else
 		mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
-		      rt->dst.dev->mtu : dst_mtu(rt->dst.path);
+		      READ_ONCE(rt->dst.dev->mtu) : dst_mtu(rt->dst.path);
 	if (np->frag_size < mtu) {
 		if (np->frag_size)
 			mtu = np->frag_size;
 	}
+	if (mtu < IPV6_MIN_MTU)
+		return -EINVAL;
 	cork->base.fragsize = mtu;
 	if (dst_allfrag(rt->dst.path))
 		cork->base.flags |= IPCORK_ALLFRAG;
-- 
2.14.3


From d143ed41c1ad0c35039f711af9dfa5b4f349d92b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 11 Jan 2018 22:31:18 -0800
Subject: [PATCH 04/23] ipv6: ip6_make_skb() needs to clear cork.base.dst

[ Upstream commit 95ef498d977bf44ac094778fd448b98af158a3e6 ]

In my last patch, I missed fact that cork.base.dst was not initialized
in ip6_make_skb() :

If ip6_setup_cork() returns an error, we might attempt a dst_release()
on some random pointer.

Fixes: 862c03ee1deb ("ipv6: fix possible mem leaks in ipv6_make_skb()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_output.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index af98bbe7af0f..2e3db3619858 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1800,6 +1800,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk,
 	cork.base.flags = 0;
 	cork.base.addr = 0;
 	cork.base.opt = NULL;
+	cork.base.dst = NULL;
 	v6_cork.opt = NULL;
 	err = ip6_setup_cork(sk, &cork, &v6_cork, ipc6, rt, fl6);
 	if (err) {
-- 
2.14.3


From 72f89df9a4038a17bf6318822df837a2b6ae960b Mon Sep 17 00:00:00 2001
From: Yuiko Oshino <yuiko.oshino@microchip.com>
Date: Mon, 15 Jan 2018 13:24:28 -0500
Subject: [PATCH 05/23] lan78xx: Fix failure in USB Full Speed

[ Upstream commit a5b1379afbfabf91e3a689e82ac619a7157336b3 ]

Fix initialize the uninitialized tx_qlen to an appropriate value when USB
Full Speed is used.

Fixes: 55d7de9de6c3 ("Microchip's LAN7800 family USB 2/3 to 10/100/1000 Ethernet device driver")
Signed-off-by: Yuiko Oshino <yuiko.oshino@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/lan78xx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 9c257ffedb15..c53385a0052f 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -2197,6 +2197,7 @@ static int lan78xx_reset(struct lan78xx_net *dev)
 		buf = DEFAULT_BURST_CAP_SIZE / FS_USB_PKT_SIZE;
 		dev->rx_urb_size = DEFAULT_BURST_CAP_SIZE;
 		dev->rx_qlen = 4;
+		dev->tx_qlen = 4;
 	}
 
 	ret = lan78xx_write_reg(dev, BURST_CAP, buf);
-- 
2.14.3


From 0f1eba118f756f72ce5d4cedfb48979e67e0be03 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Fri, 19 Jan 2018 11:50:46 +0100
Subject: [PATCH 06/23] net: igmp: fix source address check for IGMPv3 reports

[ Upstream commit ad23b750933ea7bf962678972a286c78a8fa36aa ]

Commit "net: igmp: Use correct source address on IGMPv3 reports"
introduced a check to validate the source address of locally generated
IGMPv3 packets.
Instead of checking the local interface address directly, it uses
inet_ifa_match(fl4->saddr, ifa), which checks if the address is on the
local subnet (or equal to the point-to-point address if used).

This breaks for point-to-point interfaces, so check against
ifa->ifa_local directly.

Cc: Kevin Cernekee <cernekee@chromium.org>
Fixes: a46182b00290 ("net: igmp: Use correct source address on IGMPv3 reports")
Reported-by: Sebastian Gottschall <s.gottschall@dd-wrt.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/igmp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 7bff0c65046f..9c7a4cea1628 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -332,7 +332,7 @@ static __be32 igmpv3_get_srcaddr(struct net_device *dev,
 		return htonl(INADDR_ANY);
 
 	for_ifa(in_dev) {
-		if (inet_ifa_match(fl4->saddr, ifa))
+		if (fl4->saddr == ifa->ifa_local)
 			return fl4->saddr;
 	} endfor_ifa(in_dev);
 
-- 
2.14.3


From 1b46775e3896273d3c37e78cde145b18bbc46b7c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 18 Jan 2018 19:59:19 -0800
Subject: [PATCH 07/23] net: qdisc_pkt_len_init() should be more robust

[ Upstream commit 7c68d1a6b4db9012790af7ac0f0fdc0d2083422a ]

Without proper validation of DODGY packets, we might very well
feed qdisc_pkt_len_init() with invalid GSO packets.

tcp_hdrlen() might access out-of-bound data, so let's use
skb_header_pointer() and proper checks.

Whole story is described in commit d0c081b49137 ("flow_dissector:
properly cap thoff field")

We have the goal of validating DODGY packets earlier in the stack,
so we might very well revert this fix in the future.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Jason Wang <jasowang@redhat.com>
Reported-by: syzbot+9da69ebac7dddd804552@syzkaller.appspotmail.com
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 19 +++++++++++++++----
 1 file changed, 15 insertions(+), 4 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 09007a71c8dd..67b5d4d8acb1 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3083,10 +3083,21 @@ static void qdisc_pkt_len_init(struct sk_buff *skb)
 		hdr_len = skb_transport_header(skb) - skb_mac_header(skb);
 
 		/* + transport layer */
-		if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)))
-			hdr_len += tcp_hdrlen(skb);
-		else
-			hdr_len += sizeof(struct udphdr);
+		if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) {
+			const struct tcphdr *th;
+			struct tcphdr _tcphdr;
+
+			th = skb_header_pointer(skb, skb_transport_offset(skb),
+						sizeof(_tcphdr), &_tcphdr);
+			if (likely(th))
+				hdr_len += __tcp_hdrlen(th);
+		} else {
+			struct udphdr _udphdr;
+
+			if (skb_header_pointer(skb, skb_transport_offset(skb),
+					       sizeof(_udphdr), &_udphdr))
+				hdr_len += sizeof(struct udphdr);
+		}
 
 		if (shinfo->gso_type & SKB_GSO_DODGY)
 			gso_segs = DIV_ROUND_UP(skb->len - hdr_len,
-- 
2.14.3


From 865753d765c23683eee75f5a7f06ed7b1ea101ee Mon Sep 17 00:00:00 2001
From: Dan Streetman <ddstreet@ieee.org>
Date: Thu, 18 Jan 2018 16:14:26 -0500
Subject: [PATCH 08/23] net: tcp: close sock if net namespace is exiting

[ Upstream commit 4ee806d51176ba7b8ff1efd81f271d7252e03a1d ]

When a tcp socket is closed, if it detects that its net namespace is
exiting, close immediately and do not wait for FIN sequence.

For normal sockets, a reference is taken to their net namespace, so it will
never exit while the socket is open.  However, kernel sockets do not take a
reference to their net namespace, so it may begin exiting while the kernel
socket is still open.  In this case if the kernel socket is a tcp socket,
it will stay open trying to complete its close sequence.  The sock's dst(s)
hold a reference to their interface, which are all transferred to the
namespace's loopback interface when the real interfaces are taken down.
When the namespace tries to take down its loopback interface, it hangs
waiting for all references to the loopback interface to release, which
results in messages like:

unregister_netdevice: waiting for lo to become free. Usage count = 1

These messages continue until the socket finally times out and closes.
Since the net namespace cleanup holds the net_mutex while calling its
registered pernet callbacks, any new net namespace initialization is
blocked until the current net namespace finishes exiting.

After this change, the tcp socket notices the exiting net namespace, and
closes immediately, releasing its dst(s) and their reference to the
loopback interface, which lets the net namespace continue exiting.

Link: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1711407
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=97811
Signed-off-by: Dan Streetman <ddstreet@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/net_namespace.h | 10 ++++++++++
 net/ipv4/tcp.c              |  3 +++
 net/ipv4/tcp_timer.c        | 15 +++++++++++++++
 3 files changed, 28 insertions(+)

diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 0940598c002f..23102da24dd9 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -213,6 +213,11 @@ int net_eq(const struct net *net1, const struct net *net2)
 	return net1 == net2;
 }
 
+static inline int check_net(const struct net *net)
+{
+	return atomic_read(&net->count) != 0;
+}
+
 void net_drop_ns(void *);
 
 #else
@@ -237,6 +242,11 @@ int net_eq(const struct net *net1, const struct net *net2)
 	return 1;
 }
 
+static inline int check_net(const struct net *net)
+{
+	return 1;
+}
+
 #define net_drop_ns NULL
 #endif
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 05d2bde00864..7efa6b062049 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2215,6 +2215,9 @@ void tcp_close(struct sock *sk, long timeout)
 			tcp_send_active_reset(sk, GFP_ATOMIC);
 			__NET_INC_STATS(sock_net(sk),
 					LINUX_MIB_TCPABORTONMEMORY);
+		} else if (!check_net(sock_net(sk))) {
+			/* Not possible to send reset; just close */
+			tcp_set_state(sk, TCP_CLOSE);
 		}
 	}
 
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 74db43b47917..69523389f067 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -50,11 +50,19 @@ static void tcp_write_err(struct sock *sk)
  *  to prevent DoS attacks. It is called when a retransmission timeout
  *  or zero probe timeout occurs on orphaned socket.
  *
+ *  Also close if our net namespace is exiting; in that case there is no
+ *  hope of ever communicating again since all netns interfaces are already
+ *  down (or about to be down), and we need to release our dst references,
+ *  which have been moved to the netns loopback interface, so the namespace
+ *  can finish exiting.  This condition is only possible if we are a kernel
+ *  socket, as those do not hold references to the namespace.
+ *
  *  Criteria is still not confirmed experimentally and may change.
  *  We kill the socket, if:
  *  1. If number of orphaned sockets exceeds an administratively configured
  *     limit.
  *  2. If we have strong memory pressure.
+ *  3. If our net namespace is exiting.
  */
 static int tcp_out_of_resources(struct sock *sk, bool do_reset)
 {
@@ -83,6 +91,13 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset)
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY);
 		return 1;
 	}
+
+	if (!check_net(sock_net(sk))) {
+		/* Not possible to send reset; just close */
+		tcp_done(sk);
+		return 1;
+	}
+
 	return 0;
 }
 
-- 
2.14.3


From e18f9929f1c592612ae2cb89e468a4590625202c Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Mon, 22 Jan 2018 18:06:37 +0100
Subject: [PATCH 09/23] pppoe: take ->needed_headroom of lower device into
 account on xmit

[ Upstream commit 02612bb05e51df8489db5e94d0cf8d1c81f87b0c ]

In pppoe_sendmsg(), reserving dev->hard_header_len bytes of headroom
was probably fine before the introduction of ->needed_headroom in
commit f5184d267c1a ("net: Allow netdevices to specify needed head/tailroom").

But now, virtual devices typically advertise the size of their overhead
in dev->needed_headroom, so we must also take it into account in
skb_reserve().
Allocation size of skb is also updated to take dev->needed_tailroom
into account and replace the arbitrary 32 bytes with the real size of
a PPPoE header.

This issue was discovered by syzbot, who connected a pppoe socket to a
gre device which had dev->header_ops->create == ipgre_header and
dev->hard_header_len == 0. Therefore, PPPoE didn't reserve any
headroom, and dev_hard_header() crashed when ipgre_header() tried to
prepend its header to skb->data.

skbuff: skb_under_panic: text:000000001d390b3a len:31 put:24
head:00000000d8ed776f data:000000008150e823 tail:0x7 end:0xc0 dev:gre0
------------[ cut here ]------------
kernel BUG at net/core/skbuff.c:104!
invalid opcode: 0000 [#1] SMP KASAN
Dumping ftrace buffer:
    (ftrace buffer empty)
Modules linked in:
CPU: 1 PID: 3670 Comm: syzkaller801466 Not tainted
4.15.0-rc7-next-20180115+ #97
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
RIP: 0010:skb_panic+0x162/0x1f0 net/core/skbuff.c:100
RSP: 0018:ffff8801d9bd7840 EFLAGS: 00010282
RAX: 0000000000000083 RBX: ffff8801d4f083c0 RCX: 0000000000000000
RDX: 0000000000000083 RSI: 1ffff1003b37ae92 RDI: ffffed003b37aefc
RBP: ffff8801d9bd78a8 R08: 1ffff1003b37ae8a R09: 0000000000000000
R10: 0000000000000001 R11: 0000000000000000 R12: ffffffff86200de0
R13: ffffffff84a981ad R14: 0000000000000018 R15: ffff8801d2d34180
FS:  00000000019c4880(0000) GS:ffff8801db300000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000208bc000 CR3: 00000001d9111001 CR4: 00000000001606e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
  skb_under_panic net/core/skbuff.c:114 [inline]
  skb_push+0xce/0xf0 net/core/skbuff.c:1714
  ipgre_header+0x6d/0x4e0 net/ipv4/ip_gre.c:879
  dev_hard_header include/linux/netdevice.h:2723 [inline]
  pppoe_sendmsg+0x58e/0x8b0 drivers/net/ppp/pppoe.c:890
  sock_sendmsg_nosec net/socket.c:630 [inline]
  sock_sendmsg+0xca/0x110 net/socket.c:640
  sock_write_iter+0x31a/0x5d0 net/socket.c:909
  call_write_iter include/linux/fs.h:1775 [inline]
  do_iter_readv_writev+0x525/0x7f0 fs/read_write.c:653
  do_iter_write+0x154/0x540 fs/read_write.c:932
  vfs_writev+0x18a/0x340 fs/read_write.c:977
  do_writev+0xfc/0x2a0 fs/read_write.c:1012
  SYSC_writev fs/read_write.c:1085 [inline]
  SyS_writev+0x27/0x30 fs/read_write.c:1082
  entry_SYSCALL_64_fastpath+0x29/0xa0

Admittedly PPPoE shouldn't be allowed to run on non Ethernet-like
interfaces, but reserving space for ->needed_headroom is a more
fundamental issue that needs to be addressed first.

Same problem exists for __pppoe_xmit(), which also needs to take
dev->needed_headroom into account in skb_cow_head().

Fixes: f5184d267c1a ("net: Allow netdevices to specify needed head/tailroom")
Reported-by: syzbot+ed0838d0fa4c4f2b528e20286e6dc63effc7c14d@syzkaller.appspotmail.com
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pppoe.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 4ddae8118c85..dc36c2ec1d10 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -842,6 +842,7 @@ static int pppoe_sendmsg(struct socket *sock, struct msghdr *m,
 	struct pppoe_hdr *ph;
 	struct net_device *dev;
 	char *start;
+	int hlen;
 
 	lock_sock(sk);
 	if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED)) {
@@ -860,16 +861,16 @@ static int pppoe_sendmsg(struct socket *sock, struct msghdr *m,
 	if (total_len > (dev->mtu + dev->hard_header_len))
 		goto end;
 
-
-	skb = sock_wmalloc(sk, total_len + dev->hard_header_len + 32,
-			   0, GFP_KERNEL);
+	hlen = LL_RESERVED_SPACE(dev);
+	skb = sock_wmalloc(sk, hlen + sizeof(*ph) + total_len +
+			   dev->needed_tailroom, 0, GFP_KERNEL);
 	if (!skb) {
 		error = -ENOMEM;
 		goto end;
 	}
 
 	/* Reserve space for headers. */
-	skb_reserve(skb, dev->hard_header_len);
+	skb_reserve(skb, hlen);
 	skb_reset_network_header(skb);
 
 	skb->dev = dev;
@@ -930,7 +931,7 @@ static int __pppoe_xmit(struct sock *sk, struct sk_buff *skb)
 	/* Copy the data if there is no space for the header or if it's
 	 * read-only.
 	 */
-	if (skb_cow_head(skb, sizeof(*ph) + dev->hard_header_len))
+	if (skb_cow_head(skb, LL_RESERVED_SPACE(dev) + sizeof(*ph)))
 		goto abort;
 
 	__skb_push(skb, sizeof(*ph));
-- 
2.14.3


From 5c930fdb9ca65bf5fe6528d40a27d4ece0b86424 Mon Sep 17 00:00:00 2001
From: Francois Romieu <romieu@fr.zoreil.com>
Date: Fri, 26 Jan 2018 01:53:26 +0100
Subject: [PATCH 10/23] r8169: fix memory corruption on retrieval of hardware
 statistics.

[ Upstream commit a78e93661c5fd30b9e1dee464b2f62f966883ef7 ]

Hardware statistics retrieval hurts in tight invocation loops.

Avoid extraneous write and enforce strict ordering of writes targeted to
the tally counters dump area address registers.

Signed-off-by: Francois Romieu <romieu@fr.zoreil.com>
Tested-by: Oliver Freyermuth <o.freyermuth@googlemail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 2c4350a1c629..298b74ebc1e9 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -2222,19 +2222,14 @@ static bool rtl8169_do_counters(struct net_device *dev, u32 counter_cmd)
 	void __iomem *ioaddr = tp->mmio_addr;
 	dma_addr_t paddr = tp->counters_phys_addr;
 	u32 cmd;
-	bool ret;
 
 	RTL_W32(CounterAddrHigh, (u64)paddr >> 32);
+	RTL_R32(CounterAddrHigh);
 	cmd = (u64)paddr & DMA_BIT_MASK(32);
 	RTL_W32(CounterAddrLow, cmd);
 	RTL_W32(CounterAddrLow, cmd | counter_cmd);
 
-	ret = rtl_udelay_loop_wait_low(tp, &rtl_counters_cond, 10, 1000);
-
-	RTL_W32(CounterAddrLow, 0);
-	RTL_W32(CounterAddrHigh, 0);
-
-	return ret;
+	return rtl_udelay_loop_wait_low(tp, &rtl_counters_cond, 10, 1000);
 }
 
 static bool rtl8169_reset_counters(struct net_device *dev)
-- 
2.14.3


From 8bd44f95cc210a13daea4c4f18465b8fb91511eb Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 15 Jan 2018 17:02:00 +0800
Subject: [PATCH 11/23] sctp: do not allow the v4 socket to bind a v4mapped v6
 address

[ Upstream commit c5006b8aa74599ce19104b31d322d2ea9ff887cc ]

The check in sctp_sockaddr_af is not robust enough to forbid binding a
v4mapped v6 addr on a v4 socket.

The worse thing is that v4 socket's bind_verify would not convert this
v4mapped v6 addr to a v4 addr. syzbot even reported a crash as the v4
socket bound a v6 addr.

This patch is to fix it by doing the common sa.sa_family check first,
then AF_INET check for v4mapped v6 addrs.

Fixes: 7dab83de50c7 ("sctp: Support ipv6only AF_INET6 sockets.")
Reported-by: syzbot+7b7b518b1228d2743963@syzkaller.appspotmail.com
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 7181ce6c62bf..b9260d4029d8 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -332,16 +332,14 @@ static struct sctp_af *sctp_sockaddr_af(struct sctp_sock *opt,
 	if (len < sizeof (struct sockaddr))
 		return NULL;
 
+	if (!opt->pf->af_supported(addr->sa.sa_family, opt))
+		return NULL;
+
 	/* V4 mapped address are really of AF_INET family */
 	if (addr->sa.sa_family == AF_INET6 &&
-	    ipv6_addr_v4mapped(&addr->v6.sin6_addr)) {
-		if (!opt->pf->af_supported(AF_INET, opt))
-			return NULL;
-	} else {
-		/* Does this PF support this AF? */
-		if (!opt->pf->af_supported(addr->sa.sa_family, opt))
-			return NULL;
-	}
+	    ipv6_addr_v4mapped(&addr->v6.sin6_addr) &&
+	    !opt->pf->af_supported(AF_INET, opt))
+		return NULL;
 
 	/* If we get this far, af is valid. */
 	af = sctp_get_af_specific(addr->sa.sa_family);
-- 
2.14.3


From 8d97f6df2f93691a59f39d2bace21abc824142d3 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 15 Jan 2018 17:01:36 +0800
Subject: [PATCH 12/23] sctp: return error if the asoc has been peeled off in
 sctp_wait_for_sndbuf

[ Upstream commit a0ff660058b88d12625a783ce9e5c1371c87951f ]

After commit cea0cc80a677 ("sctp: use the right sk after waking up from
wait_buf sleep"), it may change to lock another sk if the asoc has been
peeled off in sctp_wait_for_sndbuf.

However, the asoc's new sk could be already closed elsewhere, as it's in
the sendmsg context of the old sk that can't avoid the new sk's closing.
If the sk's last one refcnt is held by this asoc, later on after putting
this asoc, the new sk will be freed, while under it's own lock.

This patch is to revert that commit, but fix the old issue by returning
error under the old sk's lock.

Fixes: cea0cc80a677 ("sctp: use the right sk after waking up from wait_buf sleep")
Reported-by: syzbot+ac6ea7baa4432811eb50@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 16 ++++++----------
 1 file changed, 6 insertions(+), 10 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index b9260d4029d8..c472b8391dde 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -83,7 +83,7 @@
 static int sctp_writeable(struct sock *sk);
 static void sctp_wfree(struct sk_buff *skb);
 static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p,
-				size_t msg_len, struct sock **orig_sk);
+				size_t msg_len);
 static int sctp_wait_for_packet(struct sock *sk, int *err, long *timeo_p);
 static int sctp_wait_for_connect(struct sctp_association *, long *timeo_p);
 static int sctp_wait_for_accept(struct sock *sk, long timeo);
@@ -1956,7 +1956,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len)
 	timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
 	if (!sctp_wspace(asoc)) {
 		/* sk can be changed by peel off when waiting for buf. */
-		err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len, &sk);
+		err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len);
 		if (err) {
 			if (err == -ESRCH) {
 				/* asoc is already dead. */
@@ -7439,12 +7439,12 @@ void sctp_sock_rfree(struct sk_buff *skb)
 
 /* Helper function to wait for space in the sndbuf.  */
 static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p,
-				size_t msg_len, struct sock **orig_sk)
+				size_t msg_len)
 {
 	struct sock *sk = asoc->base.sk;
-	int err = 0;
 	long current_timeo = *timeo_p;
 	DEFINE_WAIT(wait);
+	int err = 0;
 
 	pr_debug("%s: asoc:%p, timeo:%ld, msg_len:%zu\n", __func__, asoc,
 		 *timeo_p, msg_len);
@@ -7473,17 +7473,13 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p,
 		release_sock(sk);
 		current_timeo = schedule_timeout(current_timeo);
 		lock_sock(sk);
-		if (sk != asoc->base.sk) {
-			release_sock(sk);
-			sk = asoc->base.sk;
-			lock_sock(sk);
-		}
+		if (sk != asoc->base.sk)
+			goto do_error;
 
 		*timeo_p = current_timeo;
 	}
 
 out:
-	*orig_sk = sk;
 	finish_wait(&asoc->wait, &wait);
 
 	/* Release the association's refcnt.  */
-- 
2.14.3


From 5288673bd899ea5da8be349b8f44609089cb65f4 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Wed, 10 Jan 2018 12:50:25 -0800
Subject: [PATCH 13/23] tipc: fix a memory leak in tipc_nl_node_get_link()

[ Upstream commit 59b36613e85fb16ebf9feaf914570879cd5c2a21 ]

When tipc_node_find_by_name() fails, the nlmsg is not
freed.

While on it, switch to a goto label to properly
free it.

Fixes: be9c086715c ("tipc: narrow down exposure of struct tipc_node")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Jon Maloy <jon.maloy@ericsson.com>
Cc: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/node.c | 26 ++++++++++++++------------
 1 file changed, 14 insertions(+), 12 deletions(-)

diff --git a/net/tipc/node.c b/net/tipc/node.c
index 27753325e06e..5b3e1ea37b6d 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -1848,36 +1848,38 @@ int tipc_nl_node_get_link(struct sk_buff *skb, struct genl_info *info)
 
 	if (strcmp(name, tipc_bclink_name) == 0) {
 		err = tipc_nl_add_bc_link(net, &msg);
-		if (err) {
-			nlmsg_free(msg.skb);
-			return err;
-		}
+		if (err)
+			goto err_free;
 	} else {
 		int bearer_id;
 		struct tipc_node *node;
 		struct tipc_link *link;
 
 		node = tipc_node_find_by_name(net, name, &bearer_id);
-		if (!node)
-			return -EINVAL;
+		if (!node) {
+			err = -EINVAL;
+			goto err_free;
+		}
 
 		tipc_node_read_lock(node);
 		link = node->links[bearer_id].link;
 		if (!link) {
 			tipc_node_read_unlock(node);
-			nlmsg_free(msg.skb);
-			return -EINVAL;
+			err = -EINVAL;
+			goto err_free;
 		}
 
 		err = __tipc_nl_add_link(net, &msg, link, 0);
 		tipc_node_read_unlock(node);
-		if (err) {
-			nlmsg_free(msg.skb);
-			return err;
-		}
+		if (err)
+			goto err_free;
 	}
 
 	return genlmsg_reply(msg.skb, info);
+
+err_free:
+	nlmsg_free(msg.skb);
+	return err;
 }
 
 int tipc_nl_node_reset_link_stats(struct sk_buff *skb, struct genl_info *info)
-- 
2.14.3


From 8f0d81fabb5ebccabf36c9ec7a4afdd4f7b1c194 Mon Sep 17 00:00:00 2001
From: Neil Horman <nhorman@tuxdriver.com>
Date: Mon, 22 Jan 2018 16:06:37 -0500
Subject: [PATCH 14/23] vmxnet3: repair memory leak

[ Upstream commit 848b159835ddef99cc4193083f7e786c3992f580 ]

with the introduction of commit
b0eb57cb97e7837ebb746404c2c58c6f536f23fa, it appears that rq->buf_info
is improperly handled.  While it is heap allocated when an rx queue is
setup, and freed when torn down, an old line of code in
vmxnet3_rq_destroy was not properly removed, leading to rq->buf_info[0]
being set to NULL prior to its being freed, causing a memory leak, which
eventually exhausts the system on repeated create/destroy operations
(for example, when  the mtu of a vmxnet3 interface is changed
frequently.

Fix is pretty straight forward, just move the NULL set to after the
free.

Tested by myself with successful results

Applies to net, and should likely be queued for stable, please

Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Reported-By: boyang@redhat.com
CC: boyang@redhat.com
CC: Shrikrishna Khare <skhare@vmware.com>
CC: "VMware, Inc." <pv-drivers@vmware.com>
CC: David S. Miller <davem@davemloft.net>
Acked-by: Shrikrishna Khare <skhare@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vmxnet3/vmxnet3_drv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index ef83ae3b0a44..4afba17e2403 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -1616,7 +1616,6 @@ static void vmxnet3_rq_destroy(struct vmxnet3_rx_queue *rq,
 					  rq->rx_ring[i].basePA);
 			rq->rx_ring[i].base = NULL;
 		}
-		rq->buf_info[i] = NULL;
 	}
 
 	if (rq->data_ring.base) {
@@ -1638,6 +1637,7 @@ static void vmxnet3_rq_destroy(struct vmxnet3_rx_queue *rq,
 			(rq->rx_ring[0].size + rq->rx_ring[1].size);
 		dma_free_coherent(&adapter->pdev->dev, sz, rq->buf_info[0],
 				  rq->buf_info_pa);
+		rq->buf_info[0] = rq->buf_info[1] = NULL;
 	}
 }
 
-- 
2.14.3


From c9c52b4fd0552d17af45dd0456507171aca57775 Mon Sep 17 00:00:00 2001
From: Jim Westfall <jwestfall@surrealistic.net>
Date: Sun, 14 Jan 2018 04:18:50 -0800
Subject: [PATCH 15/23] net: Allow neigh contructor functions ability to modify
 the primary_key

[ Upstream commit 096b9854c04df86f03b38a97d40b6506e5730919 ]

Use n->primary_key instead of pkey to account for the possibility that a neigh
constructor function may have modified the primary_key value.

Signed-off-by: Jim Westfall <jwestfall@surrealistic.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index f45f6198851f..7b315663f840 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -496,7 +496,7 @@ struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey,
 	if (atomic_read(&tbl->entries) > (1 << nht->hash_shift))
 		nht = neigh_hash_grow(tbl, nht->hash_shift + 1);
 
-	hash_val = tbl->hash(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift);
+	hash_val = tbl->hash(n->primary_key, dev, nht->hash_rnd) >> (32 - nht->hash_shift);
 
 	if (n->parms->dead) {
 		rc = ERR_PTR(-EINVAL);
@@ -508,7 +508,7 @@ struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey,
 	     n1 != NULL;
 	     n1 = rcu_dereference_protected(n1->next,
 			lockdep_is_held(&tbl->lock))) {
-		if (dev == n1->dev && !memcmp(n1->primary_key, pkey, key_len)) {
+		if (dev == n1->dev && !memcmp(n1->primary_key, n->primary_key, key_len)) {
 			if (want_ref)
 				neigh_hold(n1);
 			rc = n1;
-- 
2.14.3


From 94e7e43592316ae2359c42781a4128893766a471 Mon Sep 17 00:00:00 2001
From: Jim Westfall <jwestfall@surrealistic.net>
Date: Sun, 14 Jan 2018 04:18:51 -0800
Subject: [PATCH 16/23] ipv4: Make neigh lookup keys for
 loopback/point-to-point devices be INADDR_ANY

[ Upstream commit cd9ff4de0107c65d69d02253bb25d6db93c3dbc1 ]

Map all lookup neigh keys to INADDR_ANY for loopback/point-to-point devices
to avoid making an entry for every remote ip the device needs to talk to.

This used the be the old behavior but became broken in a263b3093641f
(ipv4: Make neigh lookups directly in output packet path) and later removed
in 0bb4087cbec0 (ipv4: Fix neigh lookup keying over loopback/point-to-point
devices) because it was broken.

Signed-off-by: Jim Westfall <jwestfall@surrealistic.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/arp.h | 3 +++
 net/ipv4/arp.c    | 7 ++++++-
 2 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/include/net/arp.h b/include/net/arp.h
index 5e0f891d476c..1b3f86981757 100644
--- a/include/net/arp.h
+++ b/include/net/arp.h
@@ -19,6 +19,9 @@ static inline u32 arp_hashfn(const void *pkey, const struct net_device *dev, u32
 
 static inline struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev, u32 key)
 {
+	if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT))
+		key = INADDR_ANY;
+
 	return ___neigh_lookup_noref(&arp_tbl, neigh_key_eq32, arp_hashfn, &key, dev);
 }
 
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 51b27ae09fbd..e60517eb1c3a 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -223,11 +223,16 @@ static bool arp_key_eq(const struct neighbour *neigh, const void *pkey)
 
 static int arp_constructor(struct neighbour *neigh)
 {
-	__be32 addr = *(__be32 *)neigh->primary_key;
+	__be32 addr;
 	struct net_device *dev = neigh->dev;
 	struct in_device *in_dev;
 	struct neigh_parms *parms;
+	u32 inaddr_any = INADDR_ANY;
 
+	if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT))
+		memcpy(neigh->primary_key, &inaddr_any, arp_tbl.key_len);
+
+	addr = *(__be32 *)neigh->primary_key;
 	rcu_read_lock();
 	in_dev = __in_dev_get_rcu(dev);
 	if (!in_dev) {
-- 
2.14.3


From 26a58328acaa46a21a4d0ff1d5bcf5a780313382 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Wed, 10 Jan 2018 16:24:45 +0100
Subject: [PATCH 17/23] ppp: unlock all_ppp_mutex before registering device

[ Upstream commit 0171c41835591e9aa2e384b703ef9a6ae367c610 ]

ppp_dev_uninit(), which is the .ndo_uninit() handler of PPP devices,
needs to lock pn->all_ppp_mutex. Therefore we mustn't call
register_netdevice() with pn->all_ppp_mutex already locked, or we'd
deadlock in case register_netdevice() fails and calls .ndo_uninit().

Fortunately, we can unlock pn->all_ppp_mutex before calling
register_netdevice(). This lock protects pn->units_idr, which isn't
used in the device registration process.

However, keeping pn->all_ppp_mutex locked during device registration
did ensure that no device in transient state would be published in
pn->units_idr. In practice, unlocking it before calling
register_netdevice() doesn't change this property: ppp_unit_register()
is called with 'ppp_mutex' locked and all searches done in
pn->units_idr hold this lock too.

Fixes: 8cb775bc0a34 ("ppp: fix device unregistration upon netns deletion")
Reported-and-tested-by: syzbot+367889b9c9e279219175@syzkaller.appspotmail.com
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/ppp_generic.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index b883af93929c..fc4c2ccc3d22 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -1002,17 +1002,18 @@ static int ppp_unit_register(struct ppp *ppp, int unit, bool ifname_is_set)
 	if (!ifname_is_set)
 		snprintf(ppp->dev->name, IFNAMSIZ, "ppp%i", ppp->file.index);
 
+	mutex_unlock(&pn->all_ppp_mutex);
+
 	ret = register_netdevice(ppp->dev);
 	if (ret < 0)
 		goto err_unit;
 
 	atomic_inc(&ppp_unit_count);
 
-	mutex_unlock(&pn->all_ppp_mutex);
-
 	return 0;
 
 err_unit:
+	mutex_lock(&pn->all_ppp_mutex);
 	unit_put(&pn->units_idr, ppp->file.index);
 err:
 	mutex_unlock(&pn->all_ppp_mutex);
-- 
2.14.3


From b54ba533e427eab3116fcd7db6d03338fcb8a5e2 Mon Sep 17 00:00:00 2001
From: Ivan Vecera <cera@cera.cz>
Date: Fri, 19 Jan 2018 20:23:50 +0100
Subject: [PATCH 18/23] be2net: restore properly promisc mode after queues
 reconfiguration

[ Upstream commit 52acf06451930eb4cefabd5ecea56e2d46c32f76 ]

The commit 622190669403 ("be2net: Request RSS capability of Rx interface
depending on number of Rx rings") modified be_update_queues() so the
IFACE (HW representation of the netdevice) is destroyed and then
re-created. This causes a regression because potential promiscuous mode
is not restored properly during be_open() because the driver thinks
that the HW has promiscuous mode already enabled.

Note that Lancer is not affected by this bug because RX-filter flags are
disabled during be_close() for this chipset.

Cc: Sathya Perla <sathya.perla@broadcom.com>
Cc: Ajit Khaparde <ajit.khaparde@broadcom.com>
Cc: Sriharsha Basavapatna <sriharsha.basavapatna@broadcom.com>
Cc: Somnath Kotur <somnath.kotur@broadcom.com>

Fixes: 622190669403 ("be2net: Request RSS capability of Rx interface depending on number of Rx rings")
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/emulex/benet/be_main.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 1644896568c4..b2eeecb26939 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -4733,6 +4733,15 @@ int be_update_queues(struct be_adapter *adapter)
 
 	be_schedule_worker(adapter);
 
+	/*
+	 * The IF was destroyed and re-created. We need to clear
+	 * all promiscuous flags valid for the destroyed IF.
+	 * Without this promisc mode is not restored during
+	 * be_open() because the driver thinks that it is
+	 * already enabled in HW.
+	 */
+	adapter->if_flags &= ~BE_IF_FLAGS_ALL_PROMISCUOUS;
+
 	if (netif_running(netdev))
 		status = be_open(netdev);
 
-- 
2.14.3


From b7da2fffa2a33fd1549f6b23f059e8f7df9d09d8 Mon Sep 17 00:00:00 2001
From: Alexey Kodanev <alexey.kodanev@oracle.com>
Date: Thu, 18 Jan 2018 20:51:12 +0300
Subject: [PATCH 19/23] ip6_gre: init dev->mtu and dev->hard_header_len
 correctly

[ Upstream commit 128bb975dc3c25d00de04e503e2fe0a780d04459 ]

Commit b05229f44228 ("gre6: Cleanup GREv6 transmit path,
call common GRE functions") moved dev->mtu initialization
from ip6gre_tunnel_setup() to ip6gre_tunnel_init(), as a
result, the previously set values, before ndo_init(), are
reset in the following cases:

* rtnl_create_link() can update dev->mtu from IFLA_MTU
  parameter.

* ip6gre_tnl_link_config() is invoked before ndo_init() in
  netlink and ioctl setup, so ndo_init() can reset MTU
  adjustments with the lower device MTU as well, dev->mtu
  and dev->hard_header_len.

  Not applicable for ip6gretap because it has one more call
  to ip6gre_tnl_link_config(tunnel, 1) in ip6gre_tap_init().

Fix the first case by updating dev->mtu with 'tb[IFLA_MTU]'
parameter if a user sets it manually on a device creation,
and fix the second one by moving ip6gre_tnl_link_config()
call after register_netdevice().

Fixes: b05229f44228 ("gre6: Cleanup GREv6 transmit path, call common GRE functions")
Fixes: db2ec95d1ba4 ("ip6_gre: Fix MTU setting")
Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index c46066c5dc27..db2613b4a049 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -337,11 +337,12 @@ static struct ip6_tnl *ip6gre_tunnel_locate(struct net *net,
 
 	nt->dev = dev;
 	nt->net = dev_net(dev);
-	ip6gre_tnl_link_config(nt, 1);
 
 	if (register_netdevice(dev) < 0)
 		goto failed_free;
 
+	ip6gre_tnl_link_config(nt, 1);
+
 	/* Can use a lockless transmit, unless we generate output sequences */
 	if (!(nt->parms.o_flags & TUNNEL_SEQ))
 		dev->features |= NETIF_F_LLTX;
@@ -1263,7 +1264,6 @@ static void ip6gre_netlink_parms(struct nlattr *data[],
 
 static int ip6gre_tap_init(struct net_device *dev)
 {
-	struct ip6_tnl *tunnel;
 	int ret;
 
 	ret = ip6gre_tunnel_init_common(dev);
@@ -1272,10 +1272,6 @@ static int ip6gre_tap_init(struct net_device *dev)
 
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 
-	tunnel = netdev_priv(dev);
-
-	ip6gre_tnl_link_config(tunnel, 1);
-
 	return 0;
 }
 
@@ -1370,7 +1366,6 @@ static int ip6gre_newlink(struct net *src_net, struct net_device *dev,
 
 	nt->dev = dev;
 	nt->net = dev_net(dev);
-	ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]);
 
 	dev->features		|= GRE6_FEATURES;
 	dev->hw_features	|= GRE6_FEATURES;
@@ -1396,6 +1391,11 @@ static int ip6gre_newlink(struct net *src_net, struct net_device *dev,
 	if (err)
 		goto out;
 
+	ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]);
+
+	if (tb[IFLA_MTU])
+		ip6_tnl_change_mtu(dev, nla_get_u32(tb[IFLA_MTU]));
+
 	dev_hold(dev);
 	ip6gre_tunnel_link(ign, nt);
 
-- 
2.14.3


From 8da7bfc438b30949f9622866523bff373bff9112 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 19 Jan 2018 09:29:18 -0500
Subject: [PATCH 20/23] gso: validate gso_type in GSO handlers

[ Upstream commit 121d57af308d0cf943f08f4738d24d3966c38cd9 ]

Validate gso_type during segmentation as SKB_GSO_DODGY sources
may pass packets where the gso_type does not match the contents.

Syzkaller was able to enter the SCTP gso handler with a packet of
gso_type SKB_GSO_TCPV4.

On entry of transport layer gso handlers, verify that the gso_type
matches the transport protocol.

Fixes: 90017accff61 ("sctp: Add GSO support")
Link: http://lkml.kernel.org/r/<001a1137452496ffc305617e5fe0@google.com>
Reported-by: syzbot+fee64147a25aecd48055@syzkaller.appspotmail.com
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_offload.c   | 3 +++
 net/ipv4/udp_offload.c   | 3 +++
 net/ipv6/tcpv6_offload.c | 3 +++
 net/ipv6/udp_offload.c   | 3 +++
 net/sctp/offload.c       | 3 +++
 5 files changed, 15 insertions(+)

diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index bc68da38ea86..366b1becff9d 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -32,6 +32,9 @@ static void tcp_gso_tstamp(struct sk_buff *skb, unsigned int ts_seq,
 static struct sk_buff *tcp4_gso_segment(struct sk_buff *skb,
 					netdev_features_t features)
 {
+	if (!(skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4))
+		return ERR_PTR(-EINVAL);
+
 	if (!pskb_may_pull(skb, sizeof(struct tcphdr)))
 		return ERR_PTR(-EINVAL);
 
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 6401574cd638..f4f616eaaeb8 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -205,6 +205,9 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 		goto out;
 	}
 
+	if (!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP))
+		goto out;
+
 	if (!pskb_may_pull(skb, sizeof(struct udphdr)))
 		goto out;
 
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index d883c9204c01..278e49cd67d4 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -46,6 +46,9 @@ static struct sk_buff *tcp6_gso_segment(struct sk_buff *skb,
 {
 	struct tcphdr *th;
 
+	if (!(skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6))
+		return ERR_PTR(-EINVAL);
+
 	if (!pskb_may_pull(skb, sizeof(*th)))
 		return ERR_PTR(-EINVAL);
 
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index e7d378c032cb..2bd2087bd105 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -55,6 +55,9 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 		const struct ipv6hdr *ipv6h;
 		struct udphdr *uh;
 
+		if (!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP))
+			goto out;
+
 		if (!pskb_may_pull(skb, sizeof(struct udphdr)))
 			goto out;
 
diff --git a/net/sctp/offload.c b/net/sctp/offload.c
index 4f5a2b580aa5..6300f28c9588 100644
--- a/net/sctp/offload.c
+++ b/net/sctp/offload.c
@@ -44,6 +44,9 @@ static struct sk_buff *sctp_gso_segment(struct sk_buff *skb,
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	struct sctphdr *sh;
 
+	if (!(skb_shinfo(skb)->gso_type & SKB_GSO_SCTP))
+		goto out;
+
 	sh = sctp_hdr(skb);
 	if (!pskb_may_pull(skb, sizeof(*sh)))
 		goto out;
-- 
2.14.3


From 82c74f1d8c542de078e4db9c49cac165d39a98fe Mon Sep 17 00:00:00 2001
From: Yuval Mintz <yuvalm@mellanox.com>
Date: Wed, 24 Jan 2018 10:02:09 +0100
Subject: [PATCH 21/23] mlxsw: spectrum_router: Don't log an error on missing
 neighbor

[ Upstream commit 1ecdaea02ca6bfacf2ecda500dc1af51e9780c42 ]

Driver periodically samples all neighbors configured in device
in order to update the kernel regarding their state. When finding
an entry configured in HW that doesn't show in neigh_lookup()
driver logs an error message.
This introduces a race when removing multiple neighbors -
it's possible that a given entry would still be configured in HW
as its removal is still being processed but is already removed
from the kernel's neighbor tables.

Simply remove the error message and gracefully accept such events.

Fixes: c723c735fa6b ("mlxsw: spectrum_router: Periodically update the kernel's neigh table")
Fixes: 60f040ca11b9 ("mlxsw: spectrum_router: Periodically dump active IPv6 neighbours")
Signed-off-by: Yuval Mintz <yuvalm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 8aa91ddff287..16556011d571 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -765,11 +765,8 @@ static void mlxsw_sp_router_neigh_ent_ipv4_process(struct mlxsw_sp *mlxsw_sp,
 	dipn = htonl(dip);
 	dev = mlxsw_sp->rifs[rif]->dev;
 	n = neigh_lookup(&arp_tbl, &dipn, dev);
-	if (!n) {
-		netdev_err(dev, "Failed to find matching neighbour for IP=%pI4h\n",
-			   &dip);
+	if (!n)
 		return;
-	}
 
 	netdev_dbg(dev, "Updating neighbour with IP=%pI4h\n", &dip);
 	neigh_event_send(n, NULL);
-- 
2.14.3


From e09d5c3150f66275e6472d4e0268c3555961fd41 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 15 Jan 2018 11:37:29 -0800
Subject: [PATCH 22/23] tun: fix a memory leak for tfile->tx_array

[ Upstream commit 4df0bfc79904b7169dc77dcce44598b1545721f9 ]

tfile->tun could be detached before we close the tun fd,
via tun_detach_all(), so it should not be used to check for
tfile->tx_array.

As Jason suggested, we probably have to clean it up
unconditionally both in __tun_deatch() and tun_detach_all(),
but this requires to check if it is initialized or not.
Currently skb_array_cleanup() doesn't have such a check,
so I check it in the caller and introduce a helper function,
it is a bit ugly but we can always improve it in net-next.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Fixes: 1576d9860599 ("tun: switch to use skb array for tx")
Cc: Jason Wang <jasowang@redhat.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 518cbfbc8b65..eb6dc28e5e52 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -525,6 +525,14 @@ static void tun_queue_purge(struct tun_file *tfile)
 	skb_queue_purge(&tfile->sk.sk_error_queue);
 }
 
+static void tun_cleanup_tx_array(struct tun_file *tfile)
+{
+	if (tfile->tx_array.ring.queue) {
+		skb_array_cleanup(&tfile->tx_array);
+		memset(&tfile->tx_array, 0, sizeof(tfile->tx_array));
+	}
+}
+
 static void __tun_detach(struct tun_file *tfile, bool clean)
 {
 	struct tun_file *ntfile;
@@ -566,8 +574,7 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
 			    tun->dev->reg_state == NETREG_REGISTERED)
 				unregister_netdevice(tun->dev);
 		}
-		if (tun)
-			skb_array_cleanup(&tfile->tx_array);
+		tun_cleanup_tx_array(tfile);
 		sock_put(&tfile->sk);
 	}
 }
@@ -606,11 +613,13 @@ static void tun_detach_all(struct net_device *dev)
 		/* Drop read queue */
 		tun_queue_purge(tfile);
 		sock_put(&tfile->sk);
+		tun_cleanup_tx_array(tfile);
 	}
 	list_for_each_entry_safe(tfile, tmp, &tun->disabled, next) {
 		tun_enable_queue(tfile);
 		tun_queue_purge(tfile);
 		sock_put(&tfile->sk);
+		tun_cleanup_tx_array(tfile);
 	}
 	BUG_ON(tun->numdisabled != 0);
 
@@ -2363,6 +2372,8 @@ static int tun_chr_open(struct inode *inode, struct file * file)
 
 	sock_set_flag(&tfile->sk, SOCK_ZEROCOPY);
 
+	memset(&tfile->tx_array, 0, sizeof(tfile->tx_array));
+
 	return 0;
 }
 
-- 
2.14.3


From 131234b51ec6915a807dce43c65ec79bbc05aa33 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 17 Jan 2018 14:21:13 -0800
Subject: [PATCH 23/23] flow_dissector: properly cap thoff field

[ Upstream commit d0c081b49137cd3200f2023c0875723be66e7ce5 ]

syzbot reported yet another crash [1] that is caused by
insufficient validation of DODGY packets.

Two bugs are happening here to trigger the crash.

1) Flow dissection leaves with incorrect thoff field.

2) skb_probe_transport_header() sets transport header to this invalid
thoff, even if pointing after skb valid data.

3) qdisc_pkt_len_init() reads out-of-bound data because it
trusts tcp_hdrlen(skb)

Possible fixes :

- Full flow dissector validation before injecting bad DODGY packets in
the stack.
 This approach was attempted here : https://patchwork.ozlabs.org/patch/
861874/

- Have more robust functions in the core.
  This might be needed anyway for stable versions.

This patch fixes the flow dissection issue.

[1]
CPU: 1 PID: 3144 Comm: syzkaller271204 Not tainted 4.15.0-rc4-mm1+ #49
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x194/0x257 lib/dump_stack.c:53
 print_address_description+0x73/0x250 mm/kasan/report.c:256
 kasan_report_error mm/kasan/report.c:355 [inline]
 kasan_report+0x23b/0x360 mm/kasan/report.c:413
 __asan_report_load2_noabort+0x14/0x20 mm/kasan/report.c:432
 __tcp_hdrlen include/linux/tcp.h:35 [inline]
 tcp_hdrlen include/linux/tcp.h:40 [inline]
 qdisc_pkt_len_init net/core/dev.c:3160 [inline]
 __dev_queue_xmit+0x20d3/0x2200 net/core/dev.c:3465
 dev_queue_xmit+0x17/0x20 net/core/dev.c:3554
 packet_snd net/packet/af_packet.c:2943 [inline]
 packet_sendmsg+0x3ad5/0x60a0 net/packet/af_packet.c:2968
 sock_sendmsg_nosec net/socket.c:628 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:638
 sock_write_iter+0x31a/0x5d0 net/socket.c:907
 call_write_iter include/linux/fs.h:1776 [inline]
 new_sync_write fs/read_write.c:469 [inline]
 __vfs_write+0x684/0x970 fs/read_write.c:482
 vfs_write+0x189/0x510 fs/read_write.c:544
 SYSC_write fs/read_write.c:589 [inline]
 SyS_write+0xef/0x220 fs/read_write.c:581
 entry_SYSCALL_64_fastpath+0x1f/0x96

Fixes: 34fad54c2537 ("net: __skb_flow_dissect() must cap its return value")
Fixes: a6e544b0a88b ("flow_dissector: Jump to exit code in __skb_flow_dissect")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/flow_dissector.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 32e4e0158846..862d63ec56e4 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -550,8 +550,8 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
 out_good:
 	ret = true;
 
-	key_control->thoff = (u16)nhoff;
 out:
+	key_control->thoff = min_t(u16, nhoff, skb ? skb->len : hlen);
 	key_basic->n_proto = proto;
 	key_basic->ip_proto = ip_proto;
 
@@ -559,7 +559,6 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
 
 out_bad:
 	ret = false;
-	key_control->thoff = min_t(u16, nhoff, skb ? skb->len : hlen);
 	goto out;
 }
 EXPORT_SYMBOL(__skb_flow_dissect);
-- 
2.14.3


[-- Attachment #3: net_414.mbox --]
[-- Type: Application/Octet-Stream, Size: 88875 bytes --]

From 88ae940fd4e8e0506cc6a11cd2f34dfffbf83110 Mon Sep 17 00:00:00 2001
From: Jim Westfall <jwestfall@surrealistic.net>
Date: Sun, 14 Jan 2018 04:18:50 -0800
Subject: [PATCH 01/37] net: Allow neigh contructor functions ability to modify
 the primary_key

[ Upstream commit 096b9854c04df86f03b38a97d40b6506e5730919 ]

Use n->primary_key instead of pkey to account for the possibility that a neigh
constructor function may have modified the primary_key value.

Signed-off-by: Jim Westfall <jwestfall@surrealistic.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 16a1a4c4eb57..741ae2554190 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -532,7 +532,7 @@ struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey,
 	if (atomic_read(&tbl->entries) > (1 << nht->hash_shift))
 		nht = neigh_hash_grow(tbl, nht->hash_shift + 1);
 
-	hash_val = tbl->hash(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift);
+	hash_val = tbl->hash(n->primary_key, dev, nht->hash_rnd) >> (32 - nht->hash_shift);
 
 	if (n->parms->dead) {
 		rc = ERR_PTR(-EINVAL);
@@ -544,7 +544,7 @@ struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey,
 	     n1 != NULL;
 	     n1 = rcu_dereference_protected(n1->next,
 			lockdep_is_held(&tbl->lock))) {
-		if (dev == n1->dev && !memcmp(n1->primary_key, pkey, key_len)) {
+		if (dev == n1->dev && !memcmp(n1->primary_key, n->primary_key, key_len)) {
 			if (want_ref)
 				neigh_hold(n1);
 			rc = n1;
-- 
2.14.3


From 7cb838dc638ad4961c3ac734442fb035e1152e69 Mon Sep 17 00:00:00 2001
From: Jim Westfall <jwestfall@surrealistic.net>
Date: Sun, 14 Jan 2018 04:18:51 -0800
Subject: [PATCH 02/37] ipv4: Make neigh lookup keys for
 loopback/point-to-point devices be INADDR_ANY

[ Upstream commit cd9ff4de0107c65d69d02253bb25d6db93c3dbc1 ]

Map all lookup neigh keys to INADDR_ANY for loopback/point-to-point devices
to avoid making an entry for every remote ip the device needs to talk to.

This used the be the old behavior but became broken in a263b3093641f
(ipv4: Make neigh lookups directly in output packet path) and later removed
in 0bb4087cbec0 (ipv4: Fix neigh lookup keying over loopback/point-to-point
devices) because it was broken.

Signed-off-by: Jim Westfall <jwestfall@surrealistic.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/arp.h | 3 +++
 net/ipv4/arp.c    | 7 ++++++-
 2 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/include/net/arp.h b/include/net/arp.h
index dc8cd47f883b..977aabfcdc03 100644
--- a/include/net/arp.h
+++ b/include/net/arp.h
@@ -20,6 +20,9 @@ static inline u32 arp_hashfn(const void *pkey, const struct net_device *dev, u32
 
 static inline struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev, u32 key)
 {
+	if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT))
+		key = INADDR_ANY;
+
 	return ___neigh_lookup_noref(&arp_tbl, neigh_key_eq32, arp_hashfn, &key, dev);
 }
 
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 7c45b8896709..a1d1f50e0e19 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -223,11 +223,16 @@ static bool arp_key_eq(const struct neighbour *neigh, const void *pkey)
 
 static int arp_constructor(struct neighbour *neigh)
 {
-	__be32 addr = *(__be32 *)neigh->primary_key;
+	__be32 addr;
 	struct net_device *dev = neigh->dev;
 	struct in_device *in_dev;
 	struct neigh_parms *parms;
+	u32 inaddr_any = INADDR_ANY;
 
+	if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT))
+		memcpy(neigh->primary_key, &inaddr_any, arp_tbl.key_len);
+
+	addr = *(__be32 *)neigh->primary_key;
 	rcu_read_lock();
 	in_dev = __in_dev_get_rcu(dev);
 	if (!in_dev) {
-- 
2.14.3


From b8030fc22ef6423d454ee39e8176eb8c00748027 Mon Sep 17 00:00:00 2001
From: Alexey Kodanev <alexey.kodanev@oracle.com>
Date: Fri, 26 Jan 2018 15:14:16 +0300
Subject: [PATCH 03/37] dccp: don't restart ccid2_hc_tx_rto_expire() if sk in
 closed state

[ Upstream commit dd5684ecae3bd8e44b644f50e2c12c7e57fdfef5 ]

ccid2_hc_tx_rto_expire() timer callback always restarts the timer
again and can run indefinitely (unless it is stopped outside), and after
commit 120e9dabaf55 ("dccp: defer ccid_hc_tx_delete() at dismantle time"),
which moved ccid_hc_tx_delete() (also includes sk_stop_timer()) from
dccp_destroy_sock() to sk_destruct(), this started to happen quite often.
The timer prevents releasing the socket, as a result, sk_destruct() won't
be called.

Found with LTP/dccp_ipsec tests running on the bonding device,
which later couldn't be unloaded after the tests were completed:

  unregister_netdevice: waiting for bond0 to become free. Usage count = 148

Fixes: 2a91aa396739 ("[DCCP] CCID2: Initial CCID2 (TCP-Like) implementation")
Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ccids/ccid2.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c
index e1295d5f2c56..97791b0b1b51 100644
--- a/net/dccp/ccids/ccid2.c
+++ b/net/dccp/ccids/ccid2.c
@@ -140,6 +140,9 @@ static void ccid2_hc_tx_rto_expire(unsigned long data)
 
 	ccid2_pr_debug("RTO_EXPIRE\n");
 
+	if (sk->sk_state == DCCP_CLOSED)
+		goto out;
+
 	/* back-off timer */
 	hc->tx_rto <<= 1;
 	if (hc->tx_rto > DCCP_RTO_MAX)
-- 
2.14.3


From 2af2e2923c874086cbabf4b29b588defdfaef886 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben.hutchings@codethink.co.uk>
Date: Mon, 22 Jan 2018 20:06:42 +0000
Subject: [PATCH 04/37] ipv6: Fix getsockopt() for sockets with default
 IPV6_AUTOFLOWLABEL

[ Upstream commit e9191ffb65d8e159680ce0ad2224e1acbde6985c ]

Commit 513674b5a2c9 ("net: reevalulate autoflowlabel setting after
sysctl setting") removed the initialisation of
ipv6_pinfo::autoflowlabel and added a second flag to indicate
whether this field or the net namespace default should be used.

The getsockopt() handling for this case was not updated, so it
currently returns 0 for all sockets for which IPV6_AUTOFLOWLABEL is
not explicitly enabled.  Fix it to return the effective value, whether
that has been set at the socket or net namespace level.

Fixes: 513674b5a2c9 ("net: reevalulate autoflowlabel setting after sysctl ...")
Signed-off-by: Ben Hutchings <ben.hutchings@codethink.co.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h       | 1 +
 net/ipv6/ip6_output.c    | 2 +-
 net/ipv6/ipv6_sockglue.c | 2 +-
 3 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 35e9dd2d18ba..9596aa93d6ef 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -291,6 +291,7 @@ int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq,
 			   int flags);
 int ip6_flowlabel_init(void);
 void ip6_flowlabel_cleanup(void);
+bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np);
 
 static inline void fl6_sock_release(struct ip6_flowlabel *fl)
 {
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 688ba5f7516b..08446e0ca411 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -166,7 +166,7 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 			    !(IP6CB(skb)->flags & IP6SKB_REROUTED));
 }
 
-static bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np)
+bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np)
 {
 	if (!np->autoflowlabel_set)
 		return ip6_default_np_autolabel(net);
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 90dbfa78a390..3b251760cb8c 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -1324,7 +1324,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case IPV6_AUTOFLOWLABEL:
-		val = np->autoflowlabel;
+		val = ip6_autoflowlabel(sock_net(sk), np);
 		break;
 
 	case IPV6_RECVFRAGSIZE:
-- 
2.14.3


From 2384e14a733e021decb30acf9c2e74ea28b76f14 Mon Sep 17 00:00:00 2001
From: Mike Maloney <maloney@google.com>
Date: Wed, 10 Jan 2018 12:45:10 -0500
Subject: [PATCH 05/37] ipv6: fix udpv6 sendmsg crash caused by too small MTU

[ Upstream commit 749439bfac6e1a2932c582e2699f91d329658196 ]

The logic in __ip6_append_data() assumes that the MTU is at least large
enough for the headers.  A device's MTU may be adjusted after being
added while sendmsg() is processing data, resulting in
__ip6_append_data() seeing any MTU.  For an mtu smaller than the size of
the fragmentation header, the math results in a negative 'maxfraglen',
which causes problems when refragmenting any previous skb in the
skb_write_queue, leaving it possibly malformed.

Instead sendmsg returns EINVAL when the mtu is calculated to be less
than IPV6_MIN_MTU.

Found by syzkaller:
kernel BUG at ./include/linux/skbuff.h:2064!
invalid opcode: 0000 [#1] SMP KASAN
Dumping ftrace buffer:
   (ftrace buffer empty)
Modules linked in:
CPU: 1 PID: 14216 Comm: syz-executor5 Not tainted 4.13.0-rc4+ #2
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
task: ffff8801d0b68580 task.stack: ffff8801ac6b8000
RIP: 0010:__skb_pull include/linux/skbuff.h:2064 [inline]
RIP: 0010:__ip6_make_skb+0x18cf/0x1f70 net/ipv6/ip6_output.c:1617
RSP: 0018:ffff8801ac6bf570 EFLAGS: 00010216
RAX: 0000000000010000 RBX: 0000000000000028 RCX: ffffc90003cce000
RDX: 00000000000001b8 RSI: ffffffff839df06f RDI: ffff8801d9478ca0
RBP: ffff8801ac6bf780 R08: ffff8801cc3f1dbc R09: 0000000000000000
R10: ffff8801ac6bf7a0 R11: 43cb4b7b1948a9e7 R12: ffff8801cc3f1dc8
R13: ffff8801cc3f1d40 R14: 0000000000001036 R15: dffffc0000000000
FS:  00007f43d740c700(0000) GS:ffff8801dc100000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f7834984000 CR3: 00000001d79b9000 CR4: 00000000001406e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 ip6_finish_skb include/net/ipv6.h:911 [inline]
 udp_v6_push_pending_frames+0x255/0x390 net/ipv6/udp.c:1093
 udpv6_sendmsg+0x280d/0x31a0 net/ipv6/udp.c:1363
 inet_sendmsg+0x11f/0x5e0 net/ipv4/af_inet.c:762
 sock_sendmsg_nosec net/socket.c:633 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:643
 SYSC_sendto+0x352/0x5a0 net/socket.c:1750
 SyS_sendto+0x40/0x50 net/socket.c:1718
 entry_SYSCALL_64_fastpath+0x1f/0xbe
RIP: 0033:0x4512e9
RSP: 002b:00007f43d740bc08 EFLAGS: 00000216 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 00000000007180a8 RCX: 00000000004512e9
RDX: 000000000000002e RSI: 0000000020d08000 RDI: 0000000000000005
RBP: 0000000000000086 R08: 00000000209c1000 R09: 000000000000001c
R10: 0000000000040800 R11: 0000000000000216 R12: 00000000004b9c69
R13: 00000000ffffffff R14: 0000000000000005 R15: 00000000202c2000
Code: 9e 01 fe e9 c5 e8 ff ff e8 7f 9e 01 fe e9 4a ea ff ff 48 89 f7 e8 52 9e 01 fe e9 aa eb ff ff e8 a8 b6 cf fd 0f 0b e8 a1 b6 cf fd <0f> 0b 49 8d 45 78 4d 8d 45 7c 48 89 85 78 fe ff ff 49 8d 85 ba
RIP: __skb_pull include/linux/skbuff.h:2064 [inline] RSP: ffff8801ac6bf570
RIP: __ip6_make_skb+0x18cf/0x1f70 net/ipv6/ip6_output.c:1617 RSP: ffff8801ac6bf570

Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Mike Maloney <maloney@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_output.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 08446e0ca411..7ef142706d14 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1206,14 +1206,16 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
 	v6_cork->tclass = ipc6->tclass;
 	if (rt->dst.flags & DST_XFRM_TUNNEL)
 		mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
-		      rt->dst.dev->mtu : dst_mtu(&rt->dst);
+		      READ_ONCE(rt->dst.dev->mtu) : dst_mtu(&rt->dst);
 	else
 		mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
-		      rt->dst.dev->mtu : dst_mtu(rt->dst.path);
+		      READ_ONCE(rt->dst.dev->mtu) : dst_mtu(rt->dst.path);
 	if (np->frag_size < mtu) {
 		if (np->frag_size)
 			mtu = np->frag_size;
 	}
+	if (mtu < IPV6_MIN_MTU)
+		return -EINVAL;
 	cork->base.fragsize = mtu;
 	if (dst_allfrag(rt->dst.path))
 		cork->base.flags |= IPCORK_ALLFRAG;
-- 
2.14.3


From 4056b922913c33150acfac82cde7740d58771d7b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 11 Jan 2018 22:31:18 -0800
Subject: [PATCH 06/37] ipv6: ip6_make_skb() needs to clear cork.base.dst

[ Upstream commit 95ef498d977bf44ac094778fd448b98af158a3e6 ]

In my last patch, I missed fact that cork.base.dst was not initialized
in ip6_make_skb() :

If ip6_setup_cork() returns an error, we might attempt a dst_release()
on some random pointer.

Fixes: 862c03ee1deb ("ipv6: fix possible mem leaks in ipv6_make_skb()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_output.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 7ef142706d14..3763dc01e374 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1735,6 +1735,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk,
 	cork.base.flags = 0;
 	cork.base.addr = 0;
 	cork.base.opt = NULL;
+	cork.base.dst = NULL;
 	v6_cork.opt = NULL;
 	err = ip6_setup_cork(sk, &cork, &v6_cork, ipc6, rt, fl6);
 	if (err) {
-- 
2.14.3


From aefece9d1ca251c27d2b9898569449d2e65f7eb5 Mon Sep 17 00:00:00 2001
From: Yuiko Oshino <yuiko.oshino@microchip.com>
Date: Mon, 15 Jan 2018 13:24:28 -0500
Subject: [PATCH 07/37] lan78xx: Fix failure in USB Full Speed

[ Upstream commit a5b1379afbfabf91e3a689e82ac619a7157336b3 ]

Fix initialize the uninitialized tx_qlen to an appropriate value when USB
Full Speed is used.

Fixes: 55d7de9de6c3 ("Microchip's LAN7800 family USB 2/3 to 10/100/1000 Ethernet device driver")
Signed-off-by: Yuiko Oshino <yuiko.oshino@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/lan78xx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 0161f77641fa..a8dd1c7a08cb 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -2396,6 +2396,7 @@ static int lan78xx_reset(struct lan78xx_net *dev)
 		buf = DEFAULT_BURST_CAP_SIZE / FS_USB_PKT_SIZE;
 		dev->rx_urb_size = DEFAULT_BURST_CAP_SIZE;
 		dev->rx_qlen = 4;
+		dev->tx_qlen = 4;
 	}
 
 	ret = lan78xx_write_reg(dev, BURST_CAP, buf);
-- 
2.14.3


From ee391b7768a93531d55edc21979dc8f593ef1a04 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Fri, 19 Jan 2018 11:50:46 +0100
Subject: [PATCH 08/37] net: igmp: fix source address check for IGMPv3 reports

[ Upstream commit ad23b750933ea7bf962678972a286c78a8fa36aa ]

Commit "net: igmp: Use correct source address on IGMPv3 reports"
introduced a check to validate the source address of locally generated
IGMPv3 packets.
Instead of checking the local interface address directly, it uses
inet_ifa_match(fl4->saddr, ifa), which checks if the address is on the
local subnet (or equal to the point-to-point address if used).

This breaks for point-to-point interfaces, so check against
ifa->ifa_local directly.

Cc: Kevin Cernekee <cernekee@chromium.org>
Fixes: a46182b00290 ("net: igmp: Use correct source address on IGMPv3 reports")
Reported-by: Sebastian Gottschall <s.gottschall@dd-wrt.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/igmp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index c621266e0306..013fed55b610 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -332,7 +332,7 @@ static __be32 igmpv3_get_srcaddr(struct net_device *dev,
 		return htonl(INADDR_ANY);
 
 	for_ifa(in_dev) {
-		if (inet_ifa_match(fl4->saddr, ifa))
+		if (fl4->saddr == ifa->ifa_local)
 			return fl4->saddr;
 	} endfor_ifa(in_dev);
 
-- 
2.14.3


From b1d813d9001be9c2efdaa1289e1ff459fb189af9 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 18 Jan 2018 19:59:19 -0800
Subject: [PATCH 09/37] net: qdisc_pkt_len_init() should be more robust

[ Upstream commit 7c68d1a6b4db9012790af7ac0f0fdc0d2083422a ]

Without proper validation of DODGY packets, we might very well
feed qdisc_pkt_len_init() with invalid GSO packets.

tcp_hdrlen() might access out-of-bound data, so let's use
skb_header_pointer() and proper checks.

Whole story is described in commit d0c081b49137 ("flow_dissector:
properly cap thoff field")

We have the goal of validating DODGY packets earlier in the stack,
so we might very well revert this fix in the future.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Jason Wang <jasowang@redhat.com>
Reported-by: syzbot+9da69ebac7dddd804552@syzkaller.appspotmail.com
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 19 +++++++++++++++----
 1 file changed, 15 insertions(+), 4 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 27357fc1730b..ffee085f0357 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3128,10 +3128,21 @@ static void qdisc_pkt_len_init(struct sk_buff *skb)
 		hdr_len = skb_transport_header(skb) - skb_mac_header(skb);
 
 		/* + transport layer */
-		if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)))
-			hdr_len += tcp_hdrlen(skb);
-		else
-			hdr_len += sizeof(struct udphdr);
+		if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) {
+			const struct tcphdr *th;
+			struct tcphdr _tcphdr;
+
+			th = skb_header_pointer(skb, skb_transport_offset(skb),
+						sizeof(_tcphdr), &_tcphdr);
+			if (likely(th))
+				hdr_len += __tcp_hdrlen(th);
+		} else {
+			struct udphdr _udphdr;
+
+			if (skb_header_pointer(skb, skb_transport_offset(skb),
+					       sizeof(_udphdr), &_udphdr))
+				hdr_len += sizeof(struct udphdr);
+		}
 
 		if (shinfo->gso_type & SKB_GSO_DODGY)
 			gso_segs = DIV_ROUND_UP(skb->len - hdr_len,
-- 
2.14.3


From dc3ef99b1986664ee77e2c470a938d2061810693 Mon Sep 17 00:00:00 2001
From: Dan Streetman <ddstreet@ieee.org>
Date: Thu, 18 Jan 2018 16:14:26 -0500
Subject: [PATCH 10/37] net: tcp: close sock if net namespace is exiting

[ Upstream commit 4ee806d51176ba7b8ff1efd81f271d7252e03a1d ]

When a tcp socket is closed, if it detects that its net namespace is
exiting, close immediately and do not wait for FIN sequence.

For normal sockets, a reference is taken to their net namespace, so it will
never exit while the socket is open.  However, kernel sockets do not take a
reference to their net namespace, so it may begin exiting while the kernel
socket is still open.  In this case if the kernel socket is a tcp socket,
it will stay open trying to complete its close sequence.  The sock's dst(s)
hold a reference to their interface, which are all transferred to the
namespace's loopback interface when the real interfaces are taken down.
When the namespace tries to take down its loopback interface, it hangs
waiting for all references to the loopback interface to release, which
results in messages like:

unregister_netdevice: waiting for lo to become free. Usage count = 1

These messages continue until the socket finally times out and closes.
Since the net namespace cleanup holds the net_mutex while calling its
registered pernet callbacks, any new net namespace initialization is
blocked until the current net namespace finishes exiting.

After this change, the tcp socket notices the exiting net namespace, and
closes immediately, releasing its dst(s) and their reference to the
loopback interface, which lets the net namespace continue exiting.

Link: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1711407
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=97811
Signed-off-by: Dan Streetman <ddstreet@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/net_namespace.h | 10 ++++++++++
 net/ipv4/tcp.c              |  3 +++
 net/ipv4/tcp_timer.c        | 15 +++++++++++++++
 3 files changed, 28 insertions(+)

diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 10f99dafd5ac..049008493faf 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -223,6 +223,11 @@ int net_eq(const struct net *net1, const struct net *net2)
 	return net1 == net2;
 }
 
+static inline int check_net(const struct net *net)
+{
+	return atomic_read(&net->count) != 0;
+}
+
 void net_drop_ns(void *);
 
 #else
@@ -247,6 +252,11 @@ int net_eq(const struct net *net1, const struct net *net2)
 	return 1;
 }
 
+static inline int check_net(const struct net *net)
+{
+	return 1;
+}
+
 #define net_drop_ns NULL
 #endif
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index a0c72b09cefc..2a65d806b562 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2273,6 +2273,9 @@ void tcp_close(struct sock *sk, long timeout)
 			tcp_send_active_reset(sk, GFP_ATOMIC);
 			__NET_INC_STATS(sock_net(sk),
 					LINUX_MIB_TCPABORTONMEMORY);
+		} else if (!check_net(sock_net(sk))) {
+			/* Not possible to send reset; just close */
+			tcp_set_state(sk, TCP_CLOSE);
 		}
 	}
 
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index e9af1879cd53..14ac7df95380 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -50,11 +50,19 @@ static void tcp_write_err(struct sock *sk)
  *  to prevent DoS attacks. It is called when a retransmission timeout
  *  or zero probe timeout occurs on orphaned socket.
  *
+ *  Also close if our net namespace is exiting; in that case there is no
+ *  hope of ever communicating again since all netns interfaces are already
+ *  down (or about to be down), and we need to release our dst references,
+ *  which have been moved to the netns loopback interface, so the namespace
+ *  can finish exiting.  This condition is only possible if we are a kernel
+ *  socket, as those do not hold references to the namespace.
+ *
  *  Criteria is still not confirmed experimentally and may change.
  *  We kill the socket, if:
  *  1. If number of orphaned sockets exceeds an administratively configured
  *     limit.
  *  2. If we have strong memory pressure.
+ *  3. If our net namespace is exiting.
  */
 static int tcp_out_of_resources(struct sock *sk, bool do_reset)
 {
@@ -83,6 +91,13 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset)
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY);
 		return 1;
 	}
+
+	if (!check_net(sock_net(sk))) {
+		/* Not possible to send reset; just close */
+		tcp_done(sk);
+		return 1;
+	}
+
 	return 0;
 }
 
-- 
2.14.3


From 521bf9f2e2fef6307516af456f0701205ad14700 Mon Sep 17 00:00:00 2001
From: "r.hering@avm.de" <r.hering@avm.de>
Date: Fri, 12 Jan 2018 15:42:06 +0100
Subject: [PATCH 11/37] net/tls: Fix inverted error codes to avoid endless loop

[ Upstream commit 30be8f8dba1bd2aff73e8447d59228471233a3d4 ]

sendfile() calls can hang endless with using Kernel TLS if a socket error occurs.
Socket error codes must be inverted by Kernel TLS before returning because
they are stored with positive sign. If returned non-inverted they are
interpreted as number of bytes sent, causing endless looping of the
splice mechanic behind sendfile().

Signed-off-by: Robert Hering <r.hering@avm.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h | 2 +-
 net/tls/tls_sw.c  | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/net/tls.h b/include/net/tls.h
index c06db1eadac2..df950383b8c1 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -168,7 +168,7 @@ static inline bool tls_is_pending_open_record(struct tls_context *tls_ctx)
 
 static inline void tls_err_abort(struct sock *sk)
 {
-	sk->sk_err = -EBADMSG;
+	sk->sk_err = EBADMSG;
 	sk->sk_error_report(sk);
 }
 
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index f00383a37622..81cc4325682f 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -407,7 +407,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 
 	while (msg_data_left(msg)) {
 		if (sk->sk_err) {
-			ret = sk->sk_err;
+			ret = -sk->sk_err;
 			goto send_end;
 		}
 
@@ -560,7 +560,7 @@ int tls_sw_sendpage(struct sock *sk, struct page *page,
 		size_t copy, required_size;
 
 		if (sk->sk_err) {
-			ret = sk->sk_err;
+			ret = -sk->sk_err;
 			goto sendpage_end;
 		}
 
-- 
2.14.3


From 44c8029c26be54b005b3813ab8e85f9b0ab804e6 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 24 Jan 2018 19:37:37 -0800
Subject: [PATCH 12/37] net: vrf: Add support for sends to local broadcast
 address

[ Upstream commit 1e19c4d689dc1e95bafd23ef68fbc0c6b9e05180 ]

Sukumar reported that sends to the local broadcast address
(255.255.255.255) are broken. Check for the address in vrf driver
and do not redirect to the VRF device - similar to multicast
packets.

With this change sockets can use SO_BINDTODEVICE to specify an
egress interface and receive responses. Note: the egress interface
can not be a VRF device but needs to be the enslaved device.

https://bugzilla.kernel.org/show_bug.cgi?id=198521

Reported-by: Sukumar Gopalakrishnan <sukumarg1973@gmail.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 7dc3bcac3506..67ecf2425b88 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -674,8 +674,9 @@ static struct sk_buff *vrf_ip_out(struct net_device *vrf_dev,
 				  struct sock *sk,
 				  struct sk_buff *skb)
 {
-	/* don't divert multicast */
-	if (ipv4_is_multicast(ip_hdr(skb)->daddr))
+	/* don't divert multicast or local broadcast */
+	if (ipv4_is_multicast(ip_hdr(skb)->daddr) ||
+	    ipv4_is_lbcast(ip_hdr(skb)->daddr))
 		return skb;
 
 	if (qdisc_tx_is_default(vrf_dev))
-- 
2.14.3


From 42d122fd6d6d1d2a2e8e0802fe731a1b01ebb699 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Mon, 22 Jan 2018 18:06:37 +0100
Subject: [PATCH 13/37] pppoe: take ->needed_headroom of lower device into
 account on xmit

[ Upstream commit 02612bb05e51df8489db5e94d0cf8d1c81f87b0c ]

In pppoe_sendmsg(), reserving dev->hard_header_len bytes of headroom
was probably fine before the introduction of ->needed_headroom in
commit f5184d267c1a ("net: Allow netdevices to specify needed head/tailroom").

But now, virtual devices typically advertise the size of their overhead
in dev->needed_headroom, so we must also take it into account in
skb_reserve().
Allocation size of skb is also updated to take dev->needed_tailroom
into account and replace the arbitrary 32 bytes with the real size of
a PPPoE header.

This issue was discovered by syzbot, who connected a pppoe socket to a
gre device which had dev->header_ops->create == ipgre_header and
dev->hard_header_len == 0. Therefore, PPPoE didn't reserve any
headroom, and dev_hard_header() crashed when ipgre_header() tried to
prepend its header to skb->data.

skbuff: skb_under_panic: text:000000001d390b3a len:31 put:24
head:00000000d8ed776f data:000000008150e823 tail:0x7 end:0xc0 dev:gre0
------------[ cut here ]------------
kernel BUG at net/core/skbuff.c:104!
invalid opcode: 0000 [#1] SMP KASAN
Dumping ftrace buffer:
    (ftrace buffer empty)
Modules linked in:
CPU: 1 PID: 3670 Comm: syzkaller801466 Not tainted
4.15.0-rc7-next-20180115+ #97
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
RIP: 0010:skb_panic+0x162/0x1f0 net/core/skbuff.c:100
RSP: 0018:ffff8801d9bd7840 EFLAGS: 00010282
RAX: 0000000000000083 RBX: ffff8801d4f083c0 RCX: 0000000000000000
RDX: 0000000000000083 RSI: 1ffff1003b37ae92 RDI: ffffed003b37aefc
RBP: ffff8801d9bd78a8 R08: 1ffff1003b37ae8a R09: 0000000000000000
R10: 0000000000000001 R11: 0000000000000000 R12: ffffffff86200de0
R13: ffffffff84a981ad R14: 0000000000000018 R15: ffff8801d2d34180
FS:  00000000019c4880(0000) GS:ffff8801db300000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000208bc000 CR3: 00000001d9111001 CR4: 00000000001606e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
  skb_under_panic net/core/skbuff.c:114 [inline]
  skb_push+0xce/0xf0 net/core/skbuff.c:1714
  ipgre_header+0x6d/0x4e0 net/ipv4/ip_gre.c:879
  dev_hard_header include/linux/netdevice.h:2723 [inline]
  pppoe_sendmsg+0x58e/0x8b0 drivers/net/ppp/pppoe.c:890
  sock_sendmsg_nosec net/socket.c:630 [inline]
  sock_sendmsg+0xca/0x110 net/socket.c:640
  sock_write_iter+0x31a/0x5d0 net/socket.c:909
  call_write_iter include/linux/fs.h:1775 [inline]
  do_iter_readv_writev+0x525/0x7f0 fs/read_write.c:653
  do_iter_write+0x154/0x540 fs/read_write.c:932
  vfs_writev+0x18a/0x340 fs/read_write.c:977
  do_writev+0xfc/0x2a0 fs/read_write.c:1012
  SYSC_writev fs/read_write.c:1085 [inline]
  SyS_writev+0x27/0x30 fs/read_write.c:1082
  entry_SYSCALL_64_fastpath+0x29/0xa0

Admittedly PPPoE shouldn't be allowed to run on non Ethernet-like
interfaces, but reserving space for ->needed_headroom is a more
fundamental issue that needs to be addressed first.

Same problem exists for __pppoe_xmit(), which also needs to take
dev->needed_headroom into account in skb_cow_head().

Fixes: f5184d267c1a ("net: Allow netdevices to specify needed head/tailroom")
Reported-by: syzbot+ed0838d0fa4c4f2b528e20286e6dc63effc7c14d@syzkaller.appspotmail.com
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pppoe.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 4e1da1645b15..5aa59f41bf8c 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -842,6 +842,7 @@ static int pppoe_sendmsg(struct socket *sock, struct msghdr *m,
 	struct pppoe_hdr *ph;
 	struct net_device *dev;
 	char *start;
+	int hlen;
 
 	lock_sock(sk);
 	if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED)) {
@@ -860,16 +861,16 @@ static int pppoe_sendmsg(struct socket *sock, struct msghdr *m,
 	if (total_len > (dev->mtu + dev->hard_header_len))
 		goto end;
 
-
-	skb = sock_wmalloc(sk, total_len + dev->hard_header_len + 32,
-			   0, GFP_KERNEL);
+	hlen = LL_RESERVED_SPACE(dev);
+	skb = sock_wmalloc(sk, hlen + sizeof(*ph) + total_len +
+			   dev->needed_tailroom, 0, GFP_KERNEL);
 	if (!skb) {
 		error = -ENOMEM;
 		goto end;
 	}
 
 	/* Reserve space for headers. */
-	skb_reserve(skb, dev->hard_header_len);
+	skb_reserve(skb, hlen);
 	skb_reset_network_header(skb);
 
 	skb->dev = dev;
@@ -930,7 +931,7 @@ static int __pppoe_xmit(struct sock *sk, struct sk_buff *skb)
 	/* Copy the data if there is no space for the header or if it's
 	 * read-only.
 	 */
-	if (skb_cow_head(skb, sizeof(*ph) + dev->hard_header_len))
+	if (skb_cow_head(skb, LL_RESERVED_SPACE(dev) + sizeof(*ph)))
 		goto abort;
 
 	__skb_push(skb, sizeof(*ph));
-- 
2.14.3


From 72a94c0565fdda749a3872bad5cdd941628f0f02 Mon Sep 17 00:00:00 2001
From: Francois Romieu <romieu@fr.zoreil.com>
Date: Fri, 26 Jan 2018 01:53:26 +0100
Subject: [PATCH 14/37] r8169: fix memory corruption on retrieval of hardware
 statistics.

[ Upstream commit a78e93661c5fd30b9e1dee464b2f62f966883ef7 ]

Hardware statistics retrieval hurts in tight invocation loops.

Avoid extraneous write and enforce strict ordering of writes targeted to
the tally counters dump area address registers.

Signed-off-by: Francois Romieu <romieu@fr.zoreil.com>
Tested-by: Oliver Freyermuth <o.freyermuth@googlemail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 9541465e43e9..958ff931e790 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -2239,19 +2239,14 @@ static bool rtl8169_do_counters(struct net_device *dev, u32 counter_cmd)
 	void __iomem *ioaddr = tp->mmio_addr;
 	dma_addr_t paddr = tp->counters_phys_addr;
 	u32 cmd;
-	bool ret;
 
 	RTL_W32(CounterAddrHigh, (u64)paddr >> 32);
+	RTL_R32(CounterAddrHigh);
 	cmd = (u64)paddr & DMA_BIT_MASK(32);
 	RTL_W32(CounterAddrLow, cmd);
 	RTL_W32(CounterAddrLow, cmd | counter_cmd);
 
-	ret = rtl_udelay_loop_wait_low(tp, &rtl_counters_cond, 10, 1000);
-
-	RTL_W32(CounterAddrLow, 0);
-	RTL_W32(CounterAddrHigh, 0);
-
-	return ret;
+	return rtl_udelay_loop_wait_low(tp, &rtl_counters_cond, 10, 1000);
 }
 
 static bool rtl8169_reset_counters(struct net_device *dev)
-- 
2.14.3


From 628a0e1991343859c4bb1b69e3bb84867c32d1ac Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 15 Jan 2018 17:02:00 +0800
Subject: [PATCH 15/37] sctp: do not allow the v4 socket to bind a v4mapped v6
 address

[ Upstream commit c5006b8aa74599ce19104b31d322d2ea9ff887cc ]

The check in sctp_sockaddr_af is not robust enough to forbid binding a
v4mapped v6 addr on a v4 socket.

The worse thing is that v4 socket's bind_verify would not convert this
v4mapped v6 addr to a v4 addr. syzbot even reported a crash as the v4
socket bound a v6 addr.

This patch is to fix it by doing the common sa.sa_family check first,
then AF_INET check for v4mapped v6 addrs.

Fixes: 7dab83de50c7 ("sctp: Support ipv6only AF_INET6 sockets.")
Reported-by: syzbot+7b7b518b1228d2743963@syzkaller.appspotmail.com
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index df806b8819aa..7b258bf60eca 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -334,16 +334,14 @@ static struct sctp_af *sctp_sockaddr_af(struct sctp_sock *opt,
 	if (len < sizeof (struct sockaddr))
 		return NULL;
 
+	if (!opt->pf->af_supported(addr->sa.sa_family, opt))
+		return NULL;
+
 	/* V4 mapped address are really of AF_INET family */
 	if (addr->sa.sa_family == AF_INET6 &&
-	    ipv6_addr_v4mapped(&addr->v6.sin6_addr)) {
-		if (!opt->pf->af_supported(AF_INET, opt))
-			return NULL;
-	} else {
-		/* Does this PF support this AF? */
-		if (!opt->pf->af_supported(addr->sa.sa_family, opt))
-			return NULL;
-	}
+	    ipv6_addr_v4mapped(&addr->v6.sin6_addr) &&
+	    !opt->pf->af_supported(AF_INET, opt))
+		return NULL;
 
 	/* If we get this far, af is valid. */
 	af = sctp_get_af_specific(addr->sa.sa_family);
-- 
2.14.3


From 7e2aceceda0e82e70911d319f728afcc4217b89f Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 15 Jan 2018 17:01:36 +0800
Subject: [PATCH 16/37] sctp: return error if the asoc has been peeled off in
 sctp_wait_for_sndbuf

[ Upstream commit a0ff660058b88d12625a783ce9e5c1371c87951f ]

After commit cea0cc80a677 ("sctp: use the right sk after waking up from
wait_buf sleep"), it may change to lock another sk if the asoc has been
peeled off in sctp_wait_for_sndbuf.

However, the asoc's new sk could be already closed elsewhere, as it's in
the sendmsg context of the old sk that can't avoid the new sk's closing.
If the sk's last one refcnt is held by this asoc, later on after putting
this asoc, the new sk will be freed, while under it's own lock.

This patch is to revert that commit, but fix the old issue by returning
error under the old sk's lock.

Fixes: cea0cc80a677 ("sctp: use the right sk after waking up from wait_buf sleep")
Reported-by: syzbot+ac6ea7baa4432811eb50@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 16 ++++++----------
 1 file changed, 6 insertions(+), 10 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 7b258bf60eca..7d432266645c 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -84,7 +84,7 @@
 static int sctp_writeable(struct sock *sk);
 static void sctp_wfree(struct sk_buff *skb);
 static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p,
-				size_t msg_len, struct sock **orig_sk);
+				size_t msg_len);
 static int sctp_wait_for_packet(struct sock *sk, int *err, long *timeo_p);
 static int sctp_wait_for_connect(struct sctp_association *, long *timeo_p);
 static int sctp_wait_for_accept(struct sock *sk, long timeo);
@@ -1961,7 +1961,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len)
 	timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
 	if (!sctp_wspace(asoc)) {
 		/* sk can be changed by peel off when waiting for buf. */
-		err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len, &sk);
+		err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len);
 		if (err) {
 			if (err == -ESRCH) {
 				/* asoc is already dead. */
@@ -7825,12 +7825,12 @@ void sctp_sock_rfree(struct sk_buff *skb)
 
 /* Helper function to wait for space in the sndbuf.  */
 static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p,
-				size_t msg_len, struct sock **orig_sk)
+				size_t msg_len)
 {
 	struct sock *sk = asoc->base.sk;
-	int err = 0;
 	long current_timeo = *timeo_p;
 	DEFINE_WAIT(wait);
+	int err = 0;
 
 	pr_debug("%s: asoc:%p, timeo:%ld, msg_len:%zu\n", __func__, asoc,
 		 *timeo_p, msg_len);
@@ -7859,17 +7859,13 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p,
 		release_sock(sk);
 		current_timeo = schedule_timeout(current_timeo);
 		lock_sock(sk);
-		if (sk != asoc->base.sk) {
-			release_sock(sk);
-			sk = asoc->base.sk;
-			lock_sock(sk);
-		}
+		if (sk != asoc->base.sk)
+			goto do_error;
 
 		*timeo_p = current_timeo;
 	}
 
 out:
-	*orig_sk = sk;
 	finish_wait(&asoc->wait, &wait);
 
 	/* Release the association's refcnt.  */
-- 
2.14.3


From afa2e86079a015c626268899f476e94f3c4338a6 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Wed, 10 Jan 2018 12:50:25 -0800
Subject: [PATCH 17/37] tipc: fix a memory leak in tipc_nl_node_get_link()

[ Upstream commit 59b36613e85fb16ebf9feaf914570879cd5c2a21 ]

When tipc_node_find_by_name() fails, the nlmsg is not
freed.

While on it, switch to a goto label to properly
free it.

Fixes: be9c086715c ("tipc: narrow down exposure of struct tipc_node")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Jon Maloy <jon.maloy@ericsson.com>
Cc: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/node.c | 26 ++++++++++++++------------
 1 file changed, 14 insertions(+), 12 deletions(-)

diff --git a/net/tipc/node.c b/net/tipc/node.c
index 198dbc7adbe1..f6c5743c170e 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -1848,36 +1848,38 @@ int tipc_nl_node_get_link(struct sk_buff *skb, struct genl_info *info)
 
 	if (strcmp(name, tipc_bclink_name) == 0) {
 		err = tipc_nl_add_bc_link(net, &msg);
-		if (err) {
-			nlmsg_free(msg.skb);
-			return err;
-		}
+		if (err)
+			goto err_free;
 	} else {
 		int bearer_id;
 		struct tipc_node *node;
 		struct tipc_link *link;
 
 		node = tipc_node_find_by_name(net, name, &bearer_id);
-		if (!node)
-			return -EINVAL;
+		if (!node) {
+			err = -EINVAL;
+			goto err_free;
+		}
 
 		tipc_node_read_lock(node);
 		link = node->links[bearer_id].link;
 		if (!link) {
 			tipc_node_read_unlock(node);
-			nlmsg_free(msg.skb);
-			return -EINVAL;
+			err = -EINVAL;
+			goto err_free;
 		}
 
 		err = __tipc_nl_add_link(net, &msg, link, 0);
 		tipc_node_read_unlock(node);
-		if (err) {
-			nlmsg_free(msg.skb);
-			return err;
-		}
+		if (err)
+			goto err_free;
 	}
 
 	return genlmsg_reply(msg.skb, info);
+
+err_free:
+	nlmsg_free(msg.skb);
+	return err;
 }
 
 int tipc_nl_node_reset_link_stats(struct sk_buff *skb, struct genl_info *info)
-- 
2.14.3


From f02768ad4004f7ffc36e66cae89277a3a5a13a90 Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Tue, 9 Jan 2018 11:41:10 +0200
Subject: [PATCH 18/37] {net,ib}/mlx5: Don't disable local loopback multicast
 traffic when needed

[ Upstream commit 8978cc921fc7fad3f4d6f91f1da01352aeeeff25 ]

There are systems platform information management interfaces (such as
HOST2BMC) for which we cannot disable local loopback multicast traffic.

Separate disable_local_lb_mc and disable_local_lb_uc capability bits so
driver will not disable multicast loopback traffic if not supported.
(It is expected that Firmware will not set disable_local_lb_mc if
HOST2BMC is running for example.)

Function mlx5_nic_vport_update_local_lb will do best effort to
disable/enable UC/MC loopback traffic and return success only in case it
succeeded to changed all allowed by Firmware.

Adapt mlx5_ib and mlx5e to support the new cap bits.

Fixes: 2c43c5a036be ("net/mlx5e: Enable local loopback in loopback selftest")
Fixes: c85023e153e3 ("IB/mlx5: Add raw ethernet local loopback support")
Fixes: bded747bb432 ("net/mlx5: Add raw ethernet local loopback firmware command")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Cc: kernel-team@fb.com
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/infiniband/hw/mlx5/main.c                  |  9 +++++---
 .../net/ethernet/mellanox/mlx5/core/en_selftest.c  | 27 ++++++++++++++--------
 drivers/net/ethernet/mellanox/mlx5/core/main.c     |  3 +--
 drivers/net/ethernet/mellanox/mlx5/core/vport.c    | 22 +++++++++++++-----
 include/linux/mlx5/mlx5_ifc.h                      |  5 ++--
 5 files changed, 44 insertions(+), 22 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 30d479f87cb8..fb5302ee57c7 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1276,7 +1276,8 @@ static int mlx5_ib_alloc_transport_domain(struct mlx5_ib_dev *dev, u32 *tdn)
 		return err;
 
 	if ((MLX5_CAP_GEN(dev->mdev, port_type) != MLX5_CAP_PORT_TYPE_ETH) ||
-	    !MLX5_CAP_GEN(dev->mdev, disable_local_lb))
+	    (!MLX5_CAP_GEN(dev->mdev, disable_local_lb_uc) &&
+	     !MLX5_CAP_GEN(dev->mdev, disable_local_lb_mc)))
 		return err;
 
 	mutex_lock(&dev->lb_mutex);
@@ -1294,7 +1295,8 @@ static void mlx5_ib_dealloc_transport_domain(struct mlx5_ib_dev *dev, u32 tdn)
 	mlx5_core_dealloc_transport_domain(dev->mdev, tdn);
 
 	if ((MLX5_CAP_GEN(dev->mdev, port_type) != MLX5_CAP_PORT_TYPE_ETH) ||
-	    !MLX5_CAP_GEN(dev->mdev, disable_local_lb))
+	    (!MLX5_CAP_GEN(dev->mdev, disable_local_lb_uc) &&
+	     !MLX5_CAP_GEN(dev->mdev, disable_local_lb_mc)))
 		return;
 
 	mutex_lock(&dev->lb_mutex);
@@ -4161,7 +4163,8 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	}
 
 	if ((MLX5_CAP_GEN(mdev, port_type) == MLX5_CAP_PORT_TYPE_ETH) &&
-	    MLX5_CAP_GEN(mdev, disable_local_lb))
+	    (MLX5_CAP_GEN(mdev, disable_local_lb_uc) ||
+	     MLX5_CAP_GEN(mdev, disable_local_lb_mc)))
 		mutex_init(&dev->lb_mutex);
 
 	dev->ib_active = true;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
index 1f1f8af87d4d..5a4608281f38 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
@@ -238,15 +238,19 @@ static int mlx5e_test_loopback_setup(struct mlx5e_priv *priv,
 	int err = 0;
 
 	/* Temporarily enable local_lb */
-	if (MLX5_CAP_GEN(priv->mdev, disable_local_lb)) {
-		mlx5_nic_vport_query_local_lb(priv->mdev, &lbtp->local_lb);
-		if (!lbtp->local_lb)
-			mlx5_nic_vport_update_local_lb(priv->mdev, true);
+	err = mlx5_nic_vport_query_local_lb(priv->mdev, &lbtp->local_lb);
+	if (err)
+		return err;
+
+	if (!lbtp->local_lb) {
+		err = mlx5_nic_vport_update_local_lb(priv->mdev, true);
+		if (err)
+			return err;
 	}
 
 	err = mlx5e_refresh_tirs(priv, true);
 	if (err)
-		return err;
+		goto out;
 
 	lbtp->loopback_ok = false;
 	init_completion(&lbtp->comp);
@@ -256,16 +260,21 @@ static int mlx5e_test_loopback_setup(struct mlx5e_priv *priv,
 	lbtp->pt.dev = priv->netdev;
 	lbtp->pt.af_packet_priv = lbtp;
 	dev_add_pack(&lbtp->pt);
+
+	return 0;
+
+out:
+	if (!lbtp->local_lb)
+		mlx5_nic_vport_update_local_lb(priv->mdev, false);
+
 	return err;
 }
 
 static void mlx5e_test_loopback_cleanup(struct mlx5e_priv *priv,
 					struct mlx5e_lbt_priv *lbtp)
 {
-	if (MLX5_CAP_GEN(priv->mdev, disable_local_lb)) {
-		if (!lbtp->local_lb)
-			mlx5_nic_vport_update_local_lb(priv->mdev, false);
-	}
+	if (!lbtp->local_lb)
+		mlx5_nic_vport_update_local_lb(priv->mdev, false);
 
 	dev_remove_pack(&lbtp->pt);
 	mlx5e_refresh_tirs(priv, false);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 8bfc37e4ec87..4ddd632d10f9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -577,8 +577,7 @@ static int mlx5_core_set_hca_defaults(struct mlx5_core_dev *dev)
 	int ret = 0;
 
 	/* Disable local_lb by default */
-	if ((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_ETH) &&
-	    MLX5_CAP_GEN(dev, disable_local_lb))
+	if (MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_ETH)
 		ret = mlx5_nic_vport_update_local_lb(dev, false);
 
 	return ret;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index d653b0025b13..a1296a62497d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -908,23 +908,33 @@ int mlx5_nic_vport_update_local_lb(struct mlx5_core_dev *mdev, bool enable)
 	void *in;
 	int err;
 
-	mlx5_core_dbg(mdev, "%s local_lb\n", enable ? "enable" : "disable");
+	if (!MLX5_CAP_GEN(mdev, disable_local_lb_mc) &&
+	    !MLX5_CAP_GEN(mdev, disable_local_lb_uc))
+		return 0;
+
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if (!in)
 		return -ENOMEM;
 
-	MLX5_SET(modify_nic_vport_context_in, in,
-		 field_select.disable_mc_local_lb, 1);
 	MLX5_SET(modify_nic_vport_context_in, in,
 		 nic_vport_context.disable_mc_local_lb, !enable);
-
-	MLX5_SET(modify_nic_vport_context_in, in,
-		 field_select.disable_uc_local_lb, 1);
 	MLX5_SET(modify_nic_vport_context_in, in,
 		 nic_vport_context.disable_uc_local_lb, !enable);
 
+	if (MLX5_CAP_GEN(mdev, disable_local_lb_mc))
+		MLX5_SET(modify_nic_vport_context_in, in,
+			 field_select.disable_mc_local_lb, 1);
+
+	if (MLX5_CAP_GEN(mdev, disable_local_lb_uc))
+		MLX5_SET(modify_nic_vport_context_in, in,
+			 field_select.disable_uc_local_lb, 1);
+
 	err = mlx5_modify_nic_vport_context(mdev, in, inlen);
 
+	if (!err)
+		mlx5_core_dbg(mdev, "%s local_lb\n",
+			      enable ? "enable" : "disable");
+
 	kvfree(in);
 	return err;
 }
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index c8091f06eaa4..f3765155fa4d 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1023,8 +1023,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         log_max_wq_sz[0x5];
 
 	u8         nic_vport_change_event[0x1];
-	u8         disable_local_lb[0x1];
-	u8         reserved_at_3e2[0x9];
+	u8         disable_local_lb_uc[0x1];
+	u8         disable_local_lb_mc[0x1];
+	u8         reserved_at_3e3[0x8];
 	u8         log_max_vlan_list[0x5];
 	u8         reserved_at_3f0[0x3];
 	u8         log_max_current_mc_list[0x5];
-- 
2.14.3


From 8d6faa3bee449366aa916e84b1fff702da5e0535 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Thu, 4 Jan 2018 04:35:51 +0200
Subject: [PATCH 19/37] net/mlx5: Fix get vector affinity helper function

[ Upstream commit 05e0cc84e00c54fb152d1f4b86bc211823a83d0c ]

mlx5_get_vector_affinity used to call pci_irq_get_affinity and after
reverting the patch that sets the device affinity via PCI_IRQ_AFFINITY
API, calling pci_irq_get_affinity becomes useless and it breaks RDMA
mlx5 users.  To fix this, this patch provides an alternative way to
retrieve IRQ vector affinity using legacy IRQ API, following
smp_affinity read procfs implementation.

Fixes: 231243c82793 ("Revert mlx5: move affinity hints assignments to generic code")
Fixes: a435393acafb ("mlx5: move affinity hints assignments to generic code")
Cc: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 include/linux/mlx5/driver.h | 19 ++++++++++++++++++-
 1 file changed, 18 insertions(+), 1 deletion(-)

diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 8b3d0103c03a..a13525daf09b 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -36,6 +36,7 @@
 #include <linux/kernel.h>
 #include <linux/completion.h>
 #include <linux/pci.h>
+#include <linux/irq.h>
 #include <linux/spinlock_types.h>
 #include <linux/semaphore.h>
 #include <linux/slab.h>
@@ -1194,7 +1195,23 @@ enum {
 static inline const struct cpumask *
 mlx5_get_vector_affinity(struct mlx5_core_dev *dev, int vector)
 {
-	return pci_irq_get_affinity(dev->pdev, MLX5_EQ_VEC_COMP_BASE + vector);
+	const struct cpumask *mask;
+	struct irq_desc *desc;
+	unsigned int irq;
+	int eqn;
+	int err;
+
+	err = mlx5_vector2eqn(dev, vector, &eqn, &irq);
+	if (err)
+		return NULL;
+
+	desc = irq_to_desc(irq);
+#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
+	mask = irq_data_get_effective_affinity_mask(&desc->irq_data);
+#else
+	mask = desc->irq_common_data.affinity;
+#endif
+	return mask;
 }
 
 #endif /* MLX5_DRIVER_H */
-- 
2.14.3


From 6c5b2e5598df7896f7f4fba1e466f81493e5eaac Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Wed, 10 Jan 2018 16:24:45 +0100
Subject: [PATCH 20/37] ppp: unlock all_ppp_mutex before registering device

[ Upstream commit 0171c41835591e9aa2e384b703ef9a6ae367c610 ]

ppp_dev_uninit(), which is the .ndo_uninit() handler of PPP devices,
needs to lock pn->all_ppp_mutex. Therefore we mustn't call
register_netdevice() with pn->all_ppp_mutex already locked, or we'd
deadlock in case register_netdevice() fails and calls .ndo_uninit().

Fortunately, we can unlock pn->all_ppp_mutex before calling
register_netdevice(). This lock protects pn->units_idr, which isn't
used in the device registration process.

However, keeping pn->all_ppp_mutex locked during device registration
did ensure that no device in transient state would be published in
pn->units_idr. In practice, unlocking it before calling
register_netdevice() doesn't change this property: ppp_unit_register()
is called with 'ppp_mutex' locked and all searches done in
pn->units_idr hold this lock too.

Fixes: 8cb775bc0a34 ("ppp: fix device unregistration upon netns deletion")
Reported-and-tested-by: syzbot+367889b9c9e279219175@syzkaller.appspotmail.com
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/ppp_generic.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index bf14c51f35e1..8c6b8918ec31 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -1003,17 +1003,18 @@ static int ppp_unit_register(struct ppp *ppp, int unit, bool ifname_is_set)
 	if (!ifname_is_set)
 		snprintf(ppp->dev->name, IFNAMSIZ, "ppp%i", ppp->file.index);
 
+	mutex_unlock(&pn->all_ppp_mutex);
+
 	ret = register_netdevice(ppp->dev);
 	if (ret < 0)
 		goto err_unit;
 
 	atomic_inc(&ppp_unit_count);
 
-	mutex_unlock(&pn->all_ppp_mutex);
-
 	return 0;
 
 err_unit:
+	mutex_lock(&pn->all_ppp_mutex);
 	unit_put(&pn->units_idr, ppp->file.index);
 err:
 	mutex_unlock(&pn->all_ppp_mutex);
-- 
2.14.3


From 528a555a2aca08e4a7cb357341665bbb939e6eb9 Mon Sep 17 00:00:00 2001
From: Ivan Vecera <cera@cera.cz>
Date: Fri, 19 Jan 2018 20:23:50 +0100
Subject: [PATCH 21/37] be2net: restore properly promisc mode after queues
 reconfiguration

[ Upstream commit 52acf06451930eb4cefabd5ecea56e2d46c32f76 ]

The commit 622190669403 ("be2net: Request RSS capability of Rx interface
depending on number of Rx rings") modified be_update_queues() so the
IFACE (HW representation of the netdevice) is destroyed and then
re-created. This causes a regression because potential promiscuous mode
is not restored properly during be_open() because the driver thinks
that the HW has promiscuous mode already enabled.

Note that Lancer is not affected by this bug because RX-filter flags are
disabled during be_close() for this chipset.

Cc: Sathya Perla <sathya.perla@broadcom.com>
Cc: Ajit Khaparde <ajit.khaparde@broadcom.com>
Cc: Sriharsha Basavapatna <sriharsha.basavapatna@broadcom.com>
Cc: Somnath Kotur <somnath.kotur@broadcom.com>

Fixes: 622190669403 ("be2net: Request RSS capability of Rx interface depending on number of Rx rings")
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/emulex/benet/be_main.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 0e3d9f39a807..1b03c32afc1f 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -4634,6 +4634,15 @@ int be_update_queues(struct be_adapter *adapter)
 
 	be_schedule_worker(adapter);
 
+	/*
+	 * The IF was destroyed and re-created. We need to clear
+	 * all promiscuous flags valid for the destroyed IF.
+	 * Without this promisc mode is not restored during
+	 * be_open() because the driver thinks that it is
+	 * already enabled in HW.
+	 */
+	adapter->if_flags &= ~BE_IF_FLAGS_ALL_PROMISCUOUS;
+
 	if (netif_running(netdev))
 		status = be_open(netdev);
 
-- 
2.14.3


From a1ab92e8b25aa4d83232fa4ab7f0616497994671 Mon Sep 17 00:00:00 2001
From: Alexey Kodanev <alexey.kodanev@oracle.com>
Date: Thu, 18 Jan 2018 20:51:12 +0300
Subject: [PATCH 22/37] ip6_gre: init dev->mtu and dev->hard_header_len
 correctly

[ Upstream commit 128bb975dc3c25d00de04e503e2fe0a780d04459 ]

Commit b05229f44228 ("gre6: Cleanup GREv6 transmit path,
call common GRE functions") moved dev->mtu initialization
from ip6gre_tunnel_setup() to ip6gre_tunnel_init(), as a
result, the previously set values, before ndo_init(), are
reset in the following cases:

* rtnl_create_link() can update dev->mtu from IFLA_MTU
  parameter.

* ip6gre_tnl_link_config() is invoked before ndo_init() in
  netlink and ioctl setup, so ndo_init() can reset MTU
  adjustments with the lower device MTU as well, dev->mtu
  and dev->hard_header_len.

  Not applicable for ip6gretap because it has one more call
  to ip6gre_tnl_link_config(tunnel, 1) in ip6gre_tap_init().

Fix the first case by updating dev->mtu with 'tb[IFLA_MTU]'
parameter if a user sets it manually on a device creation,
and fix the second one by moving ip6gre_tnl_link_config()
call after register_netdevice().

Fixes: b05229f44228 ("gre6: Cleanup GREv6 transmit path, call common GRE functions")
Fixes: db2ec95d1ba4 ("ip6_gre: Fix MTU setting")
Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 7a2df6646486..5b4870caf268 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -337,11 +337,12 @@ static struct ip6_tnl *ip6gre_tunnel_locate(struct net *net,
 
 	nt->dev = dev;
 	nt->net = dev_net(dev);
-	ip6gre_tnl_link_config(nt, 1);
 
 	if (register_netdevice(dev) < 0)
 		goto failed_free;
 
+	ip6gre_tnl_link_config(nt, 1);
+
 	/* Can use a lockless transmit, unless we generate output sequences */
 	if (!(nt->parms.o_flags & TUNNEL_SEQ))
 		dev->features |= NETIF_F_LLTX;
@@ -1307,7 +1308,6 @@ static void ip6gre_netlink_parms(struct nlattr *data[],
 
 static int ip6gre_tap_init(struct net_device *dev)
 {
-	struct ip6_tnl *tunnel;
 	int ret;
 
 	ret = ip6gre_tunnel_init_common(dev);
@@ -1316,10 +1316,6 @@ static int ip6gre_tap_init(struct net_device *dev)
 
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 
-	tunnel = netdev_priv(dev);
-
-	ip6gre_tnl_link_config(tunnel, 1);
-
 	return 0;
 }
 
@@ -1411,12 +1407,16 @@ static int ip6gre_newlink(struct net *src_net, struct net_device *dev,
 
 	nt->dev = dev;
 	nt->net = dev_net(dev);
-	ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]);
 
 	err = register_netdevice(dev);
 	if (err)
 		goto out;
 
+	ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]);
+
+	if (tb[IFLA_MTU])
+		ip6_tnl_change_mtu(dev, nla_get_u32(tb[IFLA_MTU]));
+
 	dev_hold(dev);
 	ip6gre_tunnel_link(ign, nt);
 
-- 
2.14.3


From 077f7eb2f8ae33387d0bfad8e8cfdd5de60ab38b Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 19 Jan 2018 09:29:18 -0500
Subject: [PATCH 23/37] gso: validate gso_type in GSO handlers

[ Upstream commit 121d57af308d0cf943f08f4738d24d3966c38cd9 ]

Validate gso_type during segmentation as SKB_GSO_DODGY sources
may pass packets where the gso_type does not match the contents.

Syzkaller was able to enter the SCTP gso handler with a packet of
gso_type SKB_GSO_TCPV4.

On entry of transport layer gso handlers, verify that the gso_type
matches the transport protocol.

Fixes: 90017accff61 ("sctp: Add GSO support")
Link: http://lkml.kernel.org/r/<001a1137452496ffc305617e5fe0@google.com>
Reported-by: syzbot+fee64147a25aecd48055@syzkaller.appspotmail.com
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/esp4_offload.c  | 3 +++
 net/ipv4/tcp_offload.c   | 3 +++
 net/ipv4/udp_offload.c   | 3 +++
 net/ipv6/esp6_offload.c  | 3 +++
 net/ipv6/tcpv6_offload.c | 3 +++
 net/ipv6/udp_offload.c   | 3 +++
 net/sctp/offload.c       | 3 +++
 7 files changed, 21 insertions(+)

diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index f8b918c766b0..56c49623bb9d 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -121,6 +121,9 @@ static struct sk_buff *esp4_gso_segment(struct sk_buff *skb,
 	if (!xo)
 		goto out;
 
+	if (!(skb_shinfo(skb)->gso_type & SKB_GSO_ESP))
+		goto out;
+
 	seq = xo->seq.low;
 
 	x = skb->sp->xvec[skb->sp->len - 1];
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index b6a2aa1dcf56..4d58e2ce0b5b 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -32,6 +32,9 @@ static void tcp_gso_tstamp(struct sk_buff *skb, unsigned int ts_seq,
 static struct sk_buff *tcp4_gso_segment(struct sk_buff *skb,
 					netdev_features_t features)
 {
+	if (!(skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4))
+		return ERR_PTR(-EINVAL);
+
 	if (!pskb_may_pull(skb, sizeof(struct tcphdr)))
 		return ERR_PTR(-EINVAL);
 
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 01801b77bd0d..ea6e6e7df0ee 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -203,6 +203,9 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 		goto out;
 	}
 
+	if (!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP))
+		goto out;
+
 	if (!pskb_may_pull(skb, sizeof(struct udphdr)))
 		goto out;
 
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index 333a478aa161..1ea9d794447e 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -148,6 +148,9 @@ static struct sk_buff *esp6_gso_segment(struct sk_buff *skb,
 	if (!xo)
 		goto out;
 
+	if (!(skb_shinfo(skb)->gso_type & SKB_GSO_ESP))
+		goto out;
+
 	seq = xo->seq.low;
 
 	x = skb->sp->xvec[skb->sp->len - 1];
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index d883c9204c01..278e49cd67d4 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -46,6 +46,9 @@ static struct sk_buff *tcp6_gso_segment(struct sk_buff *skb,
 {
 	struct tcphdr *th;
 
+	if (!(skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6))
+		return ERR_PTR(-EINVAL);
+
 	if (!pskb_may_pull(skb, sizeof(*th)))
 		return ERR_PTR(-EINVAL);
 
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index a0f89ad76f9d..2a04dc9c781b 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -42,6 +42,9 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 		const struct ipv6hdr *ipv6h;
 		struct udphdr *uh;
 
+		if (!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP))
+			goto out;
+
 		if (!pskb_may_pull(skb, sizeof(struct udphdr)))
 			goto out;
 
diff --git a/net/sctp/offload.c b/net/sctp/offload.c
index 275925b93b29..35bc7106d182 100644
--- a/net/sctp/offload.c
+++ b/net/sctp/offload.c
@@ -45,6 +45,9 @@ static struct sk_buff *sctp_gso_segment(struct sk_buff *skb,
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	struct sctphdr *sh;
 
+	if (!(skb_shinfo(skb)->gso_type & SKB_GSO_SCTP))
+		goto out;
+
 	sh = sctp_hdr(skb);
 	if (!pskb_may_pull(skb, sizeof(*sh)))
 		goto out;
-- 
2.14.3


From 4629464d5d5afda23eb202bb6b8efc25080c895b Mon Sep 17 00:00:00 2001
From: Yuval Mintz <yuvalm@mellanox.com>
Date: Wed, 24 Jan 2018 10:02:09 +0100
Subject: [PATCH 24/37] mlxsw: spectrum_router: Don't log an error on missing
 neighbor

[ Upstream commit 1ecdaea02ca6bfacf2ecda500dc1af51e9780c42 ]

Driver periodically samples all neighbors configured in device
in order to update the kernel regarding their state. When finding
an entry configured in HW that doesn't show in neigh_lookup()
driver logs an error message.
This introduces a race when removing multiple neighbors -
it's possible that a given entry would still be configured in HW
as its removal is still being processed but is already removed
from the kernel's neighbor tables.

Simply remove the error message and gracefully accept such events.

Fixes: c723c735fa6b ("mlxsw: spectrum_router: Periodically update the kernel's neigh table")
Fixes: 60f040ca11b9 ("mlxsw: spectrum_router: Periodically dump active IPv6 neighbours")
Signed-off-by: Yuval Mintz <yuvalm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index c23cc51bb5a5..7bef80676464 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -1531,11 +1531,8 @@ static void mlxsw_sp_router_neigh_ent_ipv4_process(struct mlxsw_sp *mlxsw_sp,
 	dipn = htonl(dip);
 	dev = mlxsw_sp->router->rifs[rif]->dev;
 	n = neigh_lookup(&arp_tbl, &dipn, dev);
-	if (!n) {
-		netdev_err(dev, "Failed to find matching neighbour for IP=%pI4h\n",
-			   &dip);
+	if (!n)
 		return;
-	}
 
 	netdev_dbg(dev, "Updating neighbour with IP=%pI4h\n", &dip);
 	neigh_event_send(n, NULL);
@@ -1562,11 +1559,8 @@ static void mlxsw_sp_router_neigh_ent_ipv6_process(struct mlxsw_sp *mlxsw_sp,
 
 	dev = mlxsw_sp->router->rifs[rif]->dev;
 	n = neigh_lookup(&nd_tbl, &dip, dev);
-	if (!n) {
-		netdev_err(dev, "Failed to find matching neighbour for IP=%pI6c\n",
-			   &dip);
+	if (!n)
 		return;
-	}
 
 	netdev_dbg(dev, "Updating neighbour with IP=%pI6c\n", &dip);
 	neigh_event_send(n, NULL);
-- 
2.14.3


From 3d4f93fbb5dfe876f4ac56f4125feea590587ec9 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 15 Jan 2018 11:37:29 -0800
Subject: [PATCH 25/37] tun: fix a memory leak for tfile->tx_array

[ Upstream commit 4df0bfc79904b7169dc77dcce44598b1545721f9 ]

tfile->tun could be detached before we close the tun fd,
via tun_detach_all(), so it should not be used to check for
tfile->tx_array.

As Jason suggested, we probably have to clean it up
unconditionally both in __tun_deatch() and tun_detach_all(),
but this requires to check if it is initialized or not.
Currently skb_array_cleanup() doesn't have such a check,
so I check it in the caller and introduce a helper function,
it is a bit ugly but we can always improve it in net-next.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Fixes: 1576d9860599 ("tun: switch to use skb array for tx")
Cc: Jason Wang <jasowang@redhat.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index c91b110f2169..fa51b7b0e9ea 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -534,6 +534,14 @@ static void tun_queue_purge(struct tun_file *tfile)
 	skb_queue_purge(&tfile->sk.sk_error_queue);
 }
 
+static void tun_cleanup_tx_array(struct tun_file *tfile)
+{
+	if (tfile->tx_array.ring.queue) {
+		skb_array_cleanup(&tfile->tx_array);
+		memset(&tfile->tx_array, 0, sizeof(tfile->tx_array));
+	}
+}
+
 static void __tun_detach(struct tun_file *tfile, bool clean)
 {
 	struct tun_file *ntfile;
@@ -575,8 +583,7 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
 			    tun->dev->reg_state == NETREG_REGISTERED)
 				unregister_netdevice(tun->dev);
 		}
-		if (tun)
-			skb_array_cleanup(&tfile->tx_array);
+		tun_cleanup_tx_array(tfile);
 		sock_put(&tfile->sk);
 	}
 }
@@ -616,11 +623,13 @@ static void tun_detach_all(struct net_device *dev)
 		/* Drop read queue */
 		tun_queue_purge(tfile);
 		sock_put(&tfile->sk);
+		tun_cleanup_tx_array(tfile);
 	}
 	list_for_each_entry_safe(tfile, tmp, &tun->disabled, next) {
 		tun_enable_queue(tfile);
 		tun_queue_purge(tfile);
 		sock_put(&tfile->sk);
+		tun_cleanup_tx_array(tfile);
 	}
 	BUG_ON(tun->numdisabled != 0);
 
@@ -2624,6 +2633,8 @@ static int tun_chr_open(struct inode *inode, struct file * file)
 
 	sock_set_flag(&tfile->sk, SOCK_ZEROCOPY);
 
+	memset(&tfile->tx_array, 0, sizeof(tfile->tx_array));
+
 	return 0;
 }
 
-- 
2.14.3


From d699289b05fc98fa2ade4ee5d3072241aed92bcc Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 17 Jan 2018 14:21:13 -0800
Subject: [PATCH 26/37] flow_dissector: properly cap thoff field

[ Upstream commit d0c081b49137cd3200f2023c0875723be66e7ce5 ]

syzbot reported yet another crash [1] that is caused by
insufficient validation of DODGY packets.

Two bugs are happening here to trigger the crash.

1) Flow dissection leaves with incorrect thoff field.

2) skb_probe_transport_header() sets transport header to this invalid
thoff, even if pointing after skb valid data.

3) qdisc_pkt_len_init() reads out-of-bound data because it
trusts tcp_hdrlen(skb)

Possible fixes :

- Full flow dissector validation before injecting bad DODGY packets in
the stack.
 This approach was attempted here : https://patchwork.ozlabs.org/patch/
861874/

- Have more robust functions in the core.
  This might be needed anyway for stable versions.

This patch fixes the flow dissection issue.

[1]
CPU: 1 PID: 3144 Comm: syzkaller271204 Not tainted 4.15.0-rc4-mm1+ #49
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x194/0x257 lib/dump_stack.c:53
 print_address_description+0x73/0x250 mm/kasan/report.c:256
 kasan_report_error mm/kasan/report.c:355 [inline]
 kasan_report+0x23b/0x360 mm/kasan/report.c:413
 __asan_report_load2_noabort+0x14/0x20 mm/kasan/report.c:432
 __tcp_hdrlen include/linux/tcp.h:35 [inline]
 tcp_hdrlen include/linux/tcp.h:40 [inline]
 qdisc_pkt_len_init net/core/dev.c:3160 [inline]
 __dev_queue_xmit+0x20d3/0x2200 net/core/dev.c:3465
 dev_queue_xmit+0x17/0x20 net/core/dev.c:3554
 packet_snd net/packet/af_packet.c:2943 [inline]
 packet_sendmsg+0x3ad5/0x60a0 net/packet/af_packet.c:2968
 sock_sendmsg_nosec net/socket.c:628 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:638
 sock_write_iter+0x31a/0x5d0 net/socket.c:907
 call_write_iter include/linux/fs.h:1776 [inline]
 new_sync_write fs/read_write.c:469 [inline]
 __vfs_write+0x684/0x970 fs/read_write.c:482
 vfs_write+0x189/0x510 fs/read_write.c:544
 SYSC_write fs/read_write.c:589 [inline]
 SyS_write+0xef/0x220 fs/read_write.c:581
 entry_SYSCALL_64_fastpath+0x1f/0x96

Fixes: 34fad54c2537 ("net: __skb_flow_dissect() must cap its return value")
Fixes: a6e544b0a88b ("flow_dissector: Jump to exit code in __skb_flow_dissect")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/flow_dissector.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 0a977373d003..f950b80c0dd1 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -876,8 +876,8 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
 out_good:
 	ret = true;
 
-	key_control->thoff = (u16)nhoff;
 out:
+	key_control->thoff = min_t(u16, nhoff, skb ? skb->len : hlen);
 	key_basic->n_proto = proto;
 	key_basic->ip_proto = ip_proto;
 
@@ -885,7 +885,6 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
 
 out_bad:
 	ret = false;
-	key_control->thoff = min_t(u16, nhoff, skb ? skb->len : hlen);
 	goto out;
 }
 EXPORT_SYMBOL(__skb_flow_dissect);
-- 
2.14.3


From c72a1a54bf44754eed36c8a1d483153479b66daf Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 15 Jan 2018 17:01:19 +0800
Subject: [PATCH 27/37] sctp: reinit stream if stream outcnt has been change by
 sinit in sendmsg

[ Upstream commit 625637bf4afa45204bd87e4218645182a919485a ]

After introducing sctp_stream structure, sctp uses stream->outcnt as the
out stream nums instead of c.sinit_num_ostreams.

However when users use sinit in cmsg, it only updates c.sinit_num_ostreams
in sctp_sendmsg. At that moment, stream->outcnt is still using previous
value. If it's value is not updated, the sinit_num_ostreams of sinit could
not really work.

This patch is to fix it by updating stream->outcnt and reiniting stream
if stream outcnt has been change by sinit in sendmsg.

Fixes: a83863174a61 ("sctp: prepare asoc stream for stream reconf")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 7d432266645c..1c08d86efe94 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1880,8 +1880,14 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len)
 		 */
 		if (sinit) {
 			if (sinit->sinit_num_ostreams) {
-				asoc->c.sinit_num_ostreams =
-					sinit->sinit_num_ostreams;
+				__u16 outcnt = sinit->sinit_num_ostreams;
+
+				asoc->c.sinit_num_ostreams = outcnt;
+				/* outcnt has been changed, so re-init stream */
+				err = sctp_stream_init(&asoc->stream, outcnt, 0,
+						       GFP_KERNEL);
+				if (err)
+					goto out_free;
 			}
 			if (sinit->sinit_max_instreams) {
 				asoc->c.sinit_max_instreams =
-- 
2.14.3


From ecd6e05108602ce98c7347f73d034e1df5dc27a7 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 10 Jan 2018 13:00:39 -0800
Subject: [PATCH 28/37] netlink: extack needs to be reset each time through
 loop

[ Upstream commit cbbdf8433a5f117b1a2119ea30fc651b61ef7570 ]

syzbot triggered the WARN_ON in netlink_ack testing the bad_attr value.
The problem is that netlink_rcv_skb loops over the skb repeatedly invoking
the callback and without resetting the extack leaving potentially stale
data. Initializing each time through avoids the WARN_ON.

Fixes: 2d4bc93368f5a ("netlink: extended ACK reporting")
Reported-by: syzbot+315fa6766d0f7c359327@syzkaller.appspotmail.com
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index aac9d68b4636..f4eb3fe59fe5 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2393,7 +2393,7 @@ int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *,
 						   struct nlmsghdr *,
 						   struct netlink_ext_ack *))
 {
-	struct netlink_ext_ack extack = {};
+	struct netlink_ext_ack extack;
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -2414,6 +2414,7 @@ int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *,
 		if (nlh->nlmsg_type < NLMSG_MIN_TYPE)
 			goto ack;
 
+		memset(&extack, 0, sizeof(extack));
 		err = cb(skb, nlh, &extack);
 		if (err == -EINTR)
 			goto skip;
-- 
2.14.3


From 0eb6b30b05f0197d1194431594ee55e2800fd5f4 Mon Sep 17 00:00:00 2001
From: Talat Batheesh <talatb@mellanox.com>
Date: Sun, 21 Jan 2018 05:30:42 +0200
Subject: [PATCH 29/37] net/mlx5e: Fix fixpoint divide exception in
 mlx5e_am_stats_compare

[ Upstream commit e58edaa4863583b54409444f11b4f80dff0af1cd ]

Helmut reported a bug about division by zero while
running traffic and doing physical cable pull test.

When the cable unplugged the ppms become zero, so when
dividing the current ppms by the previous ppms in the
next dim iteration there is division by zero.

This patch prevent this division for both ppms and epms.

Fixes: c3164d2fc48f ("net/mlx5e: Added BW check for DIM decision mechanism")
Reported-by: Helmut Grauer <helmut.grauer@de.ibm.com>
Signed-off-by: Talat Batheesh <talatb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c
index acf32fe952cd..3d3b1f97dc27 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c
@@ -197,9 +197,15 @@ static int mlx5e_am_stats_compare(struct mlx5e_rx_am_stats *curr,
 		return (curr->bpms > prev->bpms) ? MLX5E_AM_STATS_BETTER :
 						   MLX5E_AM_STATS_WORSE;
 
+	if (!prev->ppms)
+		return curr->ppms ? MLX5E_AM_STATS_BETTER :
+				    MLX5E_AM_STATS_SAME;
+
 	if (IS_SIGNIFICANT_DIFF(curr->ppms, prev->ppms))
 		return (curr->ppms > prev->ppms) ? MLX5E_AM_STATS_BETTER :
 						   MLX5E_AM_STATS_WORSE;
+	if (!prev->epms)
+		return MLX5E_AM_STATS_SAME;
 
 	if (IS_SIGNIFICANT_DIFF(curr->epms, prev->epms))
 		return (curr->epms < prev->epms) ? MLX5E_AM_STATS_BETTER :
-- 
2.14.3


From 546f2f23d23f65389243eda5f2c1f3cc8680d76a Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 15 Jan 2018 11:47:53 -0800
Subject: [PATCH 30/37] nfp: use the correct index for link speed table

[ Upstream commit 0d9c9f0f40ca262b67fc06a702b85f3976f5e1a1 ]

sts variable is holding link speed as well as state.  We should
be using ls to index into ls_to_ethtool.

Fixes: 265aeb511bd5 ("nfp: add support for .get_link_ksettings()")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
index dc016dfec64d..8e623d8fa78e 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
@@ -306,7 +306,7 @@ nfp_net_get_link_ksettings(struct net_device *netdev,
 	    ls >= ARRAY_SIZE(ls_to_ethtool))
 		return 0;
 
-	cmd->base.speed = ls_to_ethtool[sts];
+	cmd->base.speed = ls_to_ethtool[ls];
 	cmd->base.duplex = DUPLEX_FULL;
 
 	return 0;
-- 
2.14.3


From 61a7b725cbbc6640629bb6b702fcf7769d6a6168 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 18 Jan 2018 14:48:03 +0800
Subject: [PATCH 31/37] netlink: reset extack earlier in netlink_rcv_skb

[ Upstream commit cd443f1e91ca600a092e780e8250cd6a2954b763 ]

Move up the extack reset/initialization in netlink_rcv_skb, so that
those 'goto ack' will not skip it. Otherwise, later on netlink_ack
may use the uninitialized extack and cause kernel crash.

Fixes: cbbdf8433a5f ("netlink: extack needs to be reset each time through loop")
Reported-by: syzbot+03bee3680a37466775e7@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index f4eb3fe59fe5..533fd0503ba0 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2400,6 +2400,7 @@ int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *,
 	while (skb->len >= nlmsg_total_size(0)) {
 		int msglen;
 
+		memset(&extack, 0, sizeof(extack));
 		nlh = nlmsg_hdr(skb);
 		err = 0;
 
@@ -2414,7 +2415,6 @@ int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *,
 		if (nlh->nlmsg_type < NLMSG_MIN_TYPE)
 			goto ack;
 
-		memset(&extack, 0, sizeof(extack));
 		err = cb(skb, nlh, &extack);
 		if (err == -EINTR)
 			goto skip;
-- 
2.14.3


From 4df4e296d2883583f917b9d075817362c938f94b Mon Sep 17 00:00:00 2001
From: Ilya Lesokhin <ilyal@mellanox.com>
Date: Tue, 16 Jan 2018 15:31:52 +0200
Subject: [PATCH 32/37] net/tls: Only attach to sockets in ESTABLISHED state

[ Upstream commit d91c3e17f75f218022140dee18cf515292184a8f ]

Calling accept on a TCP socket with a TLS ulp attached results
in two sockets that share the same ulp context.
The ulp context is freed while a socket is destroyed, so
after one of the sockets is released, the second second will
trigger a use after free when it tries to access the ulp context
attached to it.
We restrict the TLS ulp to sockets in ESTABLISHED state
to prevent the scenario above.

Fixes: 3c4d7559159b ("tls: kernel TLS support")
Reported-by: syzbot+904e7cd6c5c741609228@syzkaller.appspotmail.com
Signed-off-by: Ilya Lesokhin <ilyal@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_main.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 60aff60e30ad..70757098f79b 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -444,6 +444,15 @@ static int tls_init(struct sock *sk)
 	struct tls_context *ctx;
 	int rc = 0;
 
+	/* The TLS ulp is currently supported only for TCP sockets
+	 * in ESTABLISHED state.
+	 * Supporting sockets in LISTEN state will require us
+	 * to modify the accept implementation to clone rather then
+	 * share the ulp context.
+	 */
+	if (sk->sk_state != TCP_ESTABLISHED)
+		return -ENOTSUPP;
+
 	/* allocate tls context */
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
 	if (!ctx) {
-- 
2.14.3


From 0df56741594f9f719fd5c36adf030a472f0a84b0 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 16 Jan 2018 16:04:26 +0100
Subject: [PATCH 33/37] tls: fix sw_ctx leak

[ Upstream commit cf6d43ef66f416282121f436ce1bee9a25199d52 ]

During setsockopt(SOL_TCP, TLS_TX), if initialization of the software
context fails in tls_set_sw_offload(), we leak sw_ctx. We also don't
reassign ctx->priv_ctx to NULL, so we can't even do another attempt to
set it up on the same socket, as it will fail with -EEXIST.

Fixes: 3c4d7559159b ('tls: kernel TLS support')
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 81cc4325682f..83f886d7c1f8 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -697,18 +697,17 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx)
 	}
 	default:
 		rc = -EINVAL;
-		goto out;
+		goto free_priv;
 	}
 
 	ctx->prepend_size = TLS_HEADER_SIZE + nonce_size;
 	ctx->tag_size = tag_size;
 	ctx->overhead_size = ctx->prepend_size + ctx->tag_size;
 	ctx->iv_size = iv_size;
-	ctx->iv = kmalloc(iv_size + TLS_CIPHER_AES_GCM_128_SALT_SIZE,
-			  GFP_KERNEL);
+	ctx->iv = kmalloc(iv_size + TLS_CIPHER_AES_GCM_128_SALT_SIZE, GFP_KERNEL);
 	if (!ctx->iv) {
 		rc = -ENOMEM;
-		goto out;
+		goto free_priv;
 	}
 	memcpy(ctx->iv, gcm_128_info->salt, TLS_CIPHER_AES_GCM_128_SALT_SIZE);
 	memcpy(ctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv, iv_size);
@@ -756,7 +755,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx)
 
 	rc = crypto_aead_setauthsize(sw_ctx->aead_send, ctx->tag_size);
 	if (!rc)
-		goto out;
+		return 0;
 
 free_aead:
 	crypto_free_aead(sw_ctx->aead_send);
@@ -767,6 +766,9 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx)
 free_iv:
 	kfree(ctx->iv);
 	ctx->iv = NULL;
+free_priv:
+	kfree(ctx->priv_ctx);
+	ctx->priv_ctx = NULL;
 out:
 	return rc;
 }
-- 
2.14.3


From f043c4c82c0cec21d8cea70e1c00bbdfa7dcdce4 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 16 Jan 2018 16:04:27 +0100
Subject: [PATCH 34/37] tls: return -EBUSY if crypto_info is already set

[ Upstream commit 877d17c79b66466942a836403773276e34fe3614 ]

do_tls_setsockopt_tx returns 0 without doing anything when crypto_info
is already set. Silent failure is confusing for users.

Fixes: 3c4d7559159b ("tls: kernel TLS support")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_main.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 70757098f79b..06688edb6855 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -364,8 +364,10 @@ static int do_tls_setsockopt_tx(struct sock *sk, char __user *optval,
 	crypto_info = &ctx->crypto_send;
 
 	/* Currently we don't support set crypto info more than one time */
-	if (TLS_CRYPTO_INFO_READY(crypto_info))
+	if (TLS_CRYPTO_INFO_READY(crypto_info)) {
+		rc = -EBUSY;
 		goto out;
+	}
 
 	switch (tmp_crypto_info.cipher_type) {
 	case TLS_CIPHER_AES_GCM_128: {
-- 
2.14.3


From 0333795e467e646583d48419e1656515d40a5c89 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 16 Jan 2018 16:04:28 +0100
Subject: [PATCH 35/37] tls: reset crypto_info when do_tls_setsockopt_tx fails

[ Upstream commit 6db959c82eb039a151d95a0f8b7dea643657327a ]

The current code copies directly from userspace to ctx->crypto_send, but
doesn't always reinitialize it to 0 on failure. This causes any
subsequent attempt to use this setsockopt to fail because of the
TLS_CRYPTO_INFO_READY check, eventhough crypto_info is not actually
ready.

This should result in a correctly set up socket after the 3rd call, but
currently it does not:

    size_t s = sizeof(struct tls12_crypto_info_aes_gcm_128);
    struct tls12_crypto_info_aes_gcm_128 crypto_good = {
        .info.version = TLS_1_2_VERSION,
        .info.cipher_type = TLS_CIPHER_AES_GCM_128,
    };

    struct tls12_crypto_info_aes_gcm_128 crypto_bad_type = crypto_good;
    crypto_bad_type.info.cipher_type = 42;

    setsockopt(sock, SOL_TLS, TLS_TX, &crypto_bad_type, s);
    setsockopt(sock, SOL_TLS, TLS_TX, &crypto_good, s - 1);
    setsockopt(sock, SOL_TLS, TLS_TX, &crypto_good, s);

Fixes: 3c4d7559159b ("tls: kernel TLS support")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 06688edb6855..282361ac0263 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -373,7 +373,7 @@ static int do_tls_setsockopt_tx(struct sock *sk, char __user *optval,
 	case TLS_CIPHER_AES_GCM_128: {
 		if (optlen != sizeof(struct tls12_crypto_info_aes_gcm_128)) {
 			rc = -EINVAL;
-			goto out;
+			goto err_crypto_info;
 		}
 		rc = copy_from_user(
 		  crypto_info,
@@ -388,7 +388,7 @@ static int do_tls_setsockopt_tx(struct sock *sk, char __user *optval,
 	}
 	default:
 		rc = -EINVAL;
-		goto out;
+		goto err_crypto_info;
 	}
 
 	ctx->sk_write_space = sk->sk_write_space;
-- 
2.14.3


From 5b0bcb20d4e0b7b383a1c801c651259924b5e809 Mon Sep 17 00:00:00 2001
From: Lorenzo Colitti <lorenzo@google.com>
Date: Thu, 11 Jan 2018 18:36:26 +0900
Subject: [PATCH 36/37] net: ipv4: Make "ip route get" match iif lo rules
 again.

[ Upstream commit 6503a30440962f1e1ccb8868816b4e18201218d4 ]

Commit 3765d35ed8b9 ("net: ipv4: Convert inet_rtm_getroute to rcu
versions of route lookup") broke "ip route get" in the presence
of rules that specify iif lo.

Host-originated traffic always has iif lo, because
ip_route_output_key_hash and ip6_route_output_flags set the flow
iif to LOOPBACK_IFINDEX. Thus, putting "iif lo" in an ip rule is a
convenient way to select only originated traffic and not forwarded
traffic.

inet_rtm_getroute used to match these rules correctly because
even though it sets the flow iif to 0, it called
ip_route_output_key which overwrites iif with LOOPBACK_IFINDEX.
But now that it calls ip_route_output_key_hash_rcu, the ifindex
will remain 0 and not match the iif lo in the rule. As a result,
"ip route get" will return ENETUNREACH.

Fixes: 3765d35ed8b9 ("net: ipv4: Convert inet_rtm_getroute to rcu versions of route lookup")
Tested: https://android.googlesource.com/kernel/tests/+/master/net/test/multinetwork_test.py passes again
Signed-off-by: Lorenzo Colitti <lorenzo@google.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 804bead564db..0ba88efca7ad 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2762,6 +2762,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 		if (err == 0 && rt->dst.error)
 			err = -rt->dst.error;
 	} else {
+		fl4.flowi4_iif = LOOPBACK_IFINDEX;
 		rt = ip_route_output_key_hash_rcu(net, &fl4, &res, skb);
 		err = 0;
 		if (IS_ERR(rt))
-- 
2.14.3


From f7c7dfeeb221bcd4a731ad6a1f50dd24db3a3412 Mon Sep 17 00:00:00 2001
From: Neil Horman <nhorman@tuxdriver.com>
Date: Mon, 22 Jan 2018 16:06:37 -0500
Subject: [PATCH 37/37] vmxnet3: repair memory leak

[ Upstream commit 848b159835ddef99cc4193083f7e786c3992f580 ]

with the introduction of commit
b0eb57cb97e7837ebb746404c2c58c6f536f23fa, it appears that rq->buf_info
is improperly handled.  While it is heap allocated when an rx queue is
setup, and freed when torn down, an old line of code in
vmxnet3_rq_destroy was not properly removed, leading to rq->buf_info[0]
being set to NULL prior to its being freed, causing a memory leak, which
eventually exhausts the system on repeated create/destroy operations
(for example, when  the mtu of a vmxnet3 interface is changed
frequently.

Fix is pretty straight forward, just move the NULL set to after the
free.

Tested by myself with successful results

Applies to net, and should likely be queued for stable, please

Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Reported-By: boyang@redhat.com
CC: boyang@redhat.com
CC: Shrikrishna Khare <skhare@vmware.com>
CC: "VMware, Inc." <pv-drivers@vmware.com>
CC: David S. Miller <davem@davemloft.net>
Acked-by: Shrikrishna Khare <skhare@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vmxnet3/vmxnet3_drv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index d1c7029ded7c..cf95290b160c 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -1616,7 +1616,6 @@ static void vmxnet3_rq_destroy(struct vmxnet3_rx_queue *rq,
 					  rq->rx_ring[i].basePA);
 			rq->rx_ring[i].base = NULL;
 		}
-		rq->buf_info[i] = NULL;
 	}
 
 	if (rq->data_ring.base) {
@@ -1638,6 +1637,7 @@ static void vmxnet3_rq_destroy(struct vmxnet3_rx_queue *rq,
 			(rq->rx_ring[0].size + rq->rx_ring[1].size);
 		dma_free_coherent(&adapter->pdev->dev, sz, rq->buf_info[0],
 				  rq->buf_info_pa);
+		rq->buf_info[0] = rq->buf_info[1] = NULL;
 	}
 }
 
-- 
2.14.3

Re: [PATCHES] Networking

[Greg KH]

On Sun, Jan 28, 2018 at 11:22:33AM -0500, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.9
> and v4.14 -stable, respectively.

Thanks so much, all now queued up.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 114 bytes --]


Please queue up the following networking bug fixes for 4.9.x, 4.14.x,
and 4.15.x -stable, respectively.

Thanks!

[-- Attachment #2: net_49.mbox --]
[-- Type: Application/Octet-Stream, Size: 36882 bytes --]

From 37dce711e593645bacff3d9376862ebf4eeaa07e Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Wed, 31 Jan 2018 16:29:30 +0200
Subject: [PATCH 01/11] ip6mr: fix stale iterator

[ Upstream commit 4adfa79fc254efb7b0eb3cd58f62c2c3f805f1ba ]

When we dump the ip6mr mfc entries via proc, we initialize an iterator
with the table to dump but we don't clear the cache pointer which might
be initialized from a prior read on the same descriptor that ended. This
can result in lock imbalance (an unnecessary unlock) leading to other
crashes and hangs. Clear the cache pointer like ipmr does to fix the issue.
Thanks for the reliable reproducer.

Here's syzbot's trace:
 WARNING: bad unlock balance detected!
 4.15.0-rc3+ #128 Not tainted
 syzkaller971460/3195 is trying to release lock (mrt_lock) at:
 [<000000006898068d>] ipmr_mfc_seq_stop+0xe1/0x130 net/ipv6/ip6mr.c:553
 but there are no more locks to release!

 other info that might help us debug this:
 1 lock held by syzkaller971460/3195:
  #0:  (&p->lock){+.+.}, at: [<00000000744a6565>] seq_read+0xd5/0x13d0
 fs/seq_file.c:165

 stack backtrace:
 CPU: 1 PID: 3195 Comm: syzkaller971460 Not tainted 4.15.0-rc3+ #128
 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
 Google 01/01/2011
 Call Trace:
  __dump_stack lib/dump_stack.c:17 [inline]
  dump_stack+0x194/0x257 lib/dump_stack.c:53
  print_unlock_imbalance_bug+0x12f/0x140 kernel/locking/lockdep.c:3561
  __lock_release kernel/locking/lockdep.c:3775 [inline]
  lock_release+0x5f9/0xda0 kernel/locking/lockdep.c:4023
  __raw_read_unlock include/linux/rwlock_api_smp.h:225 [inline]
  _raw_read_unlock+0x1a/0x30 kernel/locking/spinlock.c:255
  ipmr_mfc_seq_stop+0xe1/0x130 net/ipv6/ip6mr.c:553
  traverse+0x3bc/0xa00 fs/seq_file.c:135
  seq_read+0x96a/0x13d0 fs/seq_file.c:189
  proc_reg_read+0xef/0x170 fs/proc/inode.c:217
  do_loop_readv_writev fs/read_write.c:673 [inline]
  do_iter_read+0x3db/0x5b0 fs/read_write.c:897
  compat_readv+0x1bf/0x270 fs/read_write.c:1140
  do_compat_preadv64+0xdc/0x100 fs/read_write.c:1189
  C_SYSC_preadv fs/read_write.c:1209 [inline]
  compat_SyS_preadv+0x3b/0x50 fs/read_write.c:1203
  do_syscall_32_irqs_on arch/x86/entry/common.c:327 [inline]
  do_fast_syscall_32+0x3ee/0xf9d arch/x86/entry/common.c:389
  entry_SYSENTER_compat+0x51/0x60 arch/x86/entry/entry_64_compat.S:125
 RIP: 0023:0xf7f73c79
 RSP: 002b:00000000e574a15c EFLAGS: 00000292 ORIG_RAX: 000000000000014d
 RAX: ffffffffffffffda RBX: 000000000000000f RCX: 0000000020a3afb0
 RDX: 0000000000000001 RSI: 0000000000000067 RDI: 0000000000000000
 RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000
 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
 BUG: sleeping function called from invalid context at lib/usercopy.c:25
 in_atomic(): 1, irqs_disabled(): 0, pid: 3195, name: syzkaller971460
 INFO: lockdep is turned off.
 CPU: 1 PID: 3195 Comm: syzkaller971460 Not tainted 4.15.0-rc3+ #128
 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
 Google 01/01/2011
 Call Trace:
  __dump_stack lib/dump_stack.c:17 [inline]
  dump_stack+0x194/0x257 lib/dump_stack.c:53
  ___might_sleep+0x2b2/0x470 kernel/sched/core.c:6060
  __might_sleep+0x95/0x190 kernel/sched/core.c:6013
  __might_fault+0xab/0x1d0 mm/memory.c:4525
  _copy_to_user+0x2c/0xc0 lib/usercopy.c:25
  copy_to_user include/linux/uaccess.h:155 [inline]
  seq_read+0xcb4/0x13d0 fs/seq_file.c:279
  proc_reg_read+0xef/0x170 fs/proc/inode.c:217
  do_loop_readv_writev fs/read_write.c:673 [inline]
  do_iter_read+0x3db/0x5b0 fs/read_write.c:897
  compat_readv+0x1bf/0x270 fs/read_write.c:1140
  do_compat_preadv64+0xdc/0x100 fs/read_write.c:1189
  C_SYSC_preadv fs/read_write.c:1209 [inline]
  compat_SyS_preadv+0x3b/0x50 fs/read_write.c:1203
  do_syscall_32_irqs_on arch/x86/entry/common.c:327 [inline]
  do_fast_syscall_32+0x3ee/0xf9d arch/x86/entry/common.c:389
  entry_SYSENTER_compat+0x51/0x60 arch/x86/entry/entry_64_compat.S:125
 RIP: 0023:0xf7f73c79
 RSP: 002b:00000000e574a15c EFLAGS: 00000292 ORIG_RAX: 000000000000014d
 RAX: ffffffffffffffda RBX: 000000000000000f RCX: 0000000020a3afb0
 RDX: 0000000000000001 RSI: 0000000000000067 RDI: 0000000000000000
 RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000
 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
 WARNING: CPU: 1 PID: 3195 at lib/usercopy.c:26 _copy_to_user+0xb5/0xc0
 lib/usercopy.c:26

Reported-by: syzbot <bot+eceb3204562c41a438fa1f2335e0fe4f6886d669@syzkaller.appspotmail.com>
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6mr.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 117405dd07a3..a30e7e925c9b 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -495,6 +495,7 @@ static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos)
 		return ERR_PTR(-ENOENT);
 
 	it->mrt = mrt;
+	it->cache = NULL;
 	return *pos ? ipmr_mfc_seq_idx(net, seq->private, *pos - 1)
 		: SEQ_START_TOKEN;
 }
-- 
2.14.3


From e7bc0f010199983e82a932fe45662e4ace82ab54 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 1 Feb 2018 10:26:57 -0800
Subject: [PATCH 02/11] net: igmp: add a missing rcu locking section

[ Upstream commit e7aadb27a5415e8125834b84a74477bfbee4eff5 ]

Newly added igmpv3_get_srcaddr() needs to be called under rcu lock.

Timer callbacks do not ensure this locking.

=============================
WARNING: suspicious RCU usage
4.15.0+ #200 Not tainted
-----------------------------
./include/linux/inetdevice.h:216 suspicious rcu_dereference_check() usage!

other info that might help us debug this:

rcu_scheduler_active = 2, debug_locks = 1
3 locks held by syzkaller616973/4074:
 #0:  (&mm->mmap_sem){++++}, at: [<00000000bfce669e>] __do_page_fault+0x32d/0xc90 arch/x86/mm/fault.c:1355
 #1:  ((&im->timer)){+.-.}, at: [<00000000619d2f71>] lockdep_copy_map include/linux/lockdep.h:178 [inline]
 #1:  ((&im->timer)){+.-.}, at: [<00000000619d2f71>] call_timer_fn+0x1c6/0x820 kernel/time/timer.c:1316
 #2:  (&(&im->lock)->rlock){+.-.}, at: [<000000005f833c5c>] spin_lock_bh include/linux/spinlock.h:315 [inline]
 #2:  (&(&im->lock)->rlock){+.-.}, at: [<000000005f833c5c>] igmpv3_send_report+0x98/0x5b0 net/ipv4/igmp.c:600

stack backtrace:
CPU: 0 PID: 4074 Comm: syzkaller616973 Not tainted 4.15.0+ #200
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x194/0x257 lib/dump_stack.c:53
 lockdep_rcu_suspicious+0x123/0x170 kernel/locking/lockdep.c:4592
 __in_dev_get_rcu include/linux/inetdevice.h:216 [inline]
 igmpv3_get_srcaddr net/ipv4/igmp.c:329 [inline]
 igmpv3_newpack+0xeef/0x12e0 net/ipv4/igmp.c:389
 add_grhead.isra.27+0x235/0x300 net/ipv4/igmp.c:432
 add_grec+0xbd3/0x1170 net/ipv4/igmp.c:565
 igmpv3_send_report+0xd5/0x5b0 net/ipv4/igmp.c:605
 igmp_send_report+0xc43/0x1050 net/ipv4/igmp.c:722
 igmp_timer_expire+0x322/0x5c0 net/ipv4/igmp.c:831
 call_timer_fn+0x228/0x820 kernel/time/timer.c:1326
 expire_timers kernel/time/timer.c:1363 [inline]
 __run_timers+0x7ee/0xb70 kernel/time/timer.c:1666
 run_timer_softirq+0x4c/0x70 kernel/time/timer.c:1692
 __do_softirq+0x2d7/0xb85 kernel/softirq.c:285
 invoke_softirq kernel/softirq.c:365 [inline]
 irq_exit+0x1cc/0x200 kernel/softirq.c:405
 exiting_irq arch/x86/include/asm/apic.h:541 [inline]
 smp_apic_timer_interrupt+0x16b/0x700 arch/x86/kernel/apic/apic.c:1052
 apic_timer_interrupt+0xa9/0xb0 arch/x86/entry/entry_64.S:938

Fixes: a46182b00290 ("net: igmp: Use correct source address on IGMPv3 reports")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/igmp.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 9c7a4cea1628..7f5fe07d0b13 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -386,7 +386,11 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu)
 	pip->frag_off = htons(IP_DF);
 	pip->ttl      = 1;
 	pip->daddr    = fl4.daddr;
+
+	rcu_read_lock();
 	pip->saddr    = igmpv3_get_srcaddr(dev, &fl4);
+	rcu_read_unlock();
+
 	pip->protocol = IPPROTO_IGMP;
 	pip->tot_len  = 0;	/* filled in later */
 	ip_select_ident(net, skb, NULL);
-- 
2.14.3


From 0362ae745928fa24425f547fec08d01a72ab715b Mon Sep 17 00:00:00 2001
From: Junxiao Bi <junxiao.bi@oracle.com>
Date: Mon, 29 Jan 2018 17:53:42 +0800
Subject: [PATCH 03/11] qlcnic: fix deadlock bug

[ Upstream commit 233ac3891607f501f08879134d623b303838f478 ]

The following soft lockup was caught. This is a deadlock caused by
recusive locking.

Process kworker/u40:1:28016 was holding spin lock "mbx->queue_lock" in
qlcnic_83xx_mailbox_worker(), while a softirq came in and ask the same spin
lock in qlcnic_83xx_enqueue_mbx_cmd(). This lock should be hold by disable
bh..

[161846.962125] NMI watchdog: BUG: soft lockup - CPU#1 stuck for 22s! [kworker/u40:1:28016]
[161846.962367] Modules linked in: tun ocfs2 xen_netback xen_blkback xen_gntalloc xen_gntdev xen_evtchn xenfs xen_privcmd autofs4 ocfs2_dlmfs ocfs2_stack_o2cb ocfs2_dlm ocfs2_nodemanager ocfs2_stackglue configfs bnx2fc fcoe libfcoe libfc sunrpc 8021q mrp garp bridge stp llc bonding dm_round_robin dm_multipath iTCO_wdt iTCO_vendor_support pcspkr sb_edac edac_core i2c_i801 shpchp lpc_ich mfd_core ioatdma ipmi_devintf ipmi_si ipmi_msghandler sg ext4 jbd2 mbcache2 sr_mod cdrom sd_mod igb i2c_algo_bit i2c_core ahci libahci megaraid_sas ixgbe dca ptp pps_core vxlan udp_tunnel ip6_udp_tunnel qla2xxx scsi_transport_fc qlcnic crc32c_intel be2iscsi bnx2i cnic uio cxgb4i cxgb4 cxgb3i libcxgbi ipv6 cxgb3 mdio libiscsi_tcp qla4xxx iscsi_boot_sysfs libiscsi scsi_transport_iscsi dm_mirror dm_region_hash dm_log dm_mod
[161846.962454]
[161846.962460] CPU: 1 PID: 28016 Comm: kworker/u40:1 Not tainted 4.1.12-94.5.9.el6uek.x86_64 #2
[161846.962463] Hardware name: Oracle Corporation SUN SERVER X4-2L      /ASSY,MB,X4-2L         , BIOS 26050100 09/19/2017
[161846.962489] Workqueue: qlcnic_mailbox qlcnic_83xx_mailbox_worker [qlcnic]
[161846.962493] task: ffff8801f2e34600 ti: ffff88004ca5c000 task.ti: ffff88004ca5c000
[161846.962496] RIP: e030:[<ffffffff810013aa>]  [<ffffffff810013aa>] xen_hypercall_sched_op+0xa/0x20
[161846.962506] RSP: e02b:ffff880202e43388  EFLAGS: 00000206
[161846.962509] RAX: 0000000000000000 RBX: ffff8801f6996b70 RCX: ffffffff810013aa
[161846.962511] RDX: ffff880202e433cc RSI: ffff880202e433b0 RDI: 0000000000000003
[161846.962513] RBP: ffff880202e433d0 R08: 0000000000000000 R09: ffff8801fe893200
[161846.962516] R10: ffff8801fe400538 R11: 0000000000000206 R12: ffff880202e4b000
[161846.962518] R13: 0000000000000050 R14: 0000000000000001 R15: 000000000000020d
[161846.962528] FS:  0000000000000000(0000) GS:ffff880202e40000(0000) knlGS:ffff880202e40000
[161846.962531] CS:  e033 DS: 0000 ES: 0000 CR0: 0000000080050033
[161846.962533] CR2: 0000000002612640 CR3: 00000001bb796000 CR4: 0000000000042660
[161846.962536] Stack:
[161846.962538]  ffff880202e43608 0000000000000000 ffffffff813f0442 ffff880202e433b0
[161846.962543]  0000000000000000 ffff880202e433cc ffffffff00000001 0000000000000000
[161846.962547]  00000009813f03d6 ffff880202e433e0 ffffffff813f0460 ffff880202e43440
[161846.962552] Call Trace:
[161846.962555]  <IRQ>
[161846.962565]  [<ffffffff813f0442>] ? xen_poll_irq_timeout+0x42/0x50
[161846.962570]  [<ffffffff813f0460>] xen_poll_irq+0x10/0x20
[161846.962578]  [<ffffffff81014222>] xen_lock_spinning+0xe2/0x110
[161846.962583]  [<ffffffff81013f01>] __raw_callee_save_xen_lock_spinning+0x11/0x20
[161846.962592]  [<ffffffff816e5c57>] ? _raw_spin_lock+0x57/0x80
[161846.962609]  [<ffffffffa028acfc>] qlcnic_83xx_enqueue_mbx_cmd+0x7c/0xe0 [qlcnic]
[161846.962623]  [<ffffffffa028e008>] qlcnic_83xx_issue_cmd+0x58/0x210 [qlcnic]
[161846.962636]  [<ffffffffa028caf2>] qlcnic_83xx_sre_macaddr_change+0x162/0x1d0 [qlcnic]
[161846.962649]  [<ffffffffa028cb8b>] qlcnic_83xx_change_l2_filter+0x2b/0x30 [qlcnic]
[161846.962657]  [<ffffffff8160248b>] ? __skb_flow_dissect+0x18b/0x650
[161846.962670]  [<ffffffffa02856e5>] qlcnic_send_filter+0x205/0x250 [qlcnic]
[161846.962682]  [<ffffffffa0285c77>] qlcnic_xmit_frame+0x547/0x7b0 [qlcnic]
[161846.962691]  [<ffffffff8160ac22>] xmit_one+0x82/0x1a0
[161846.962696]  [<ffffffff8160ad90>] dev_hard_start_xmit+0x50/0xa0
[161846.962701]  [<ffffffff81630112>] sch_direct_xmit+0x112/0x220
[161846.962706]  [<ffffffff8160b80f>] __dev_queue_xmit+0x1df/0x5e0
[161846.962710]  [<ffffffff8160bc33>] dev_queue_xmit_sk+0x13/0x20
[161846.962721]  [<ffffffffa0575bd5>] bond_dev_queue_xmit+0x35/0x80 [bonding]
[161846.962729]  [<ffffffffa05769fb>] __bond_start_xmit+0x1cb/0x210 [bonding]
[161846.962736]  [<ffffffffa0576a71>] bond_start_xmit+0x31/0x60 [bonding]
[161846.962740]  [<ffffffff8160ac22>] xmit_one+0x82/0x1a0
[161846.962745]  [<ffffffff8160ad90>] dev_hard_start_xmit+0x50/0xa0
[161846.962749]  [<ffffffff8160bb1e>] __dev_queue_xmit+0x4ee/0x5e0
[161846.962754]  [<ffffffff8160bc33>] dev_queue_xmit_sk+0x13/0x20
[161846.962760]  [<ffffffffa05cfa72>] vlan_dev_hard_start_xmit+0xb2/0x150 [8021q]
[161846.962764]  [<ffffffff8160ac22>] xmit_one+0x82/0x1a0
[161846.962769]  [<ffffffff8160ad90>] dev_hard_start_xmit+0x50/0xa0
[161846.962773]  [<ffffffff8160bb1e>] __dev_queue_xmit+0x4ee/0x5e0
[161846.962777]  [<ffffffff8160bc33>] dev_queue_xmit_sk+0x13/0x20
[161846.962789]  [<ffffffffa05adf74>] br_dev_queue_push_xmit+0x54/0xa0 [bridge]
[161846.962797]  [<ffffffffa05ae4ff>] br_forward_finish+0x2f/0x90 [bridge]
[161846.962807]  [<ffffffff810b0dad>] ? ttwu_do_wakeup+0x1d/0x100
[161846.962811]  [<ffffffff815f929b>] ? __alloc_skb+0x8b/0x1f0
[161846.962818]  [<ffffffffa05ae04d>] __br_forward+0x8d/0x120 [bridge]
[161846.962822]  [<ffffffff815f613b>] ? __kmalloc_reserve+0x3b/0xa0
[161846.962829]  [<ffffffff810be55e>] ? update_rq_runnable_avg+0xee/0x230
[161846.962836]  [<ffffffffa05ae176>] br_forward+0x96/0xb0 [bridge]
[161846.962845]  [<ffffffffa05af85e>] br_handle_frame_finish+0x1ae/0x420 [bridge]
[161846.962853]  [<ffffffffa05afc4f>] br_handle_frame+0x17f/0x260 [bridge]
[161846.962862]  [<ffffffffa05afad0>] ? br_handle_frame_finish+0x420/0x420 [bridge]
[161846.962867]  [<ffffffff8160d057>] __netif_receive_skb_core+0x1f7/0x870
[161846.962872]  [<ffffffff8160d6f2>] __netif_receive_skb+0x22/0x70
[161846.962877]  [<ffffffff8160d913>] netif_receive_skb_internal+0x23/0x90
[161846.962884]  [<ffffffffa07512ea>] ? xenvif_idx_release+0xea/0x100 [xen_netback]
[161846.962889]  [<ffffffff816e5a10>] ? _raw_spin_unlock_irqrestore+0x20/0x50
[161846.962893]  [<ffffffff8160e624>] netif_receive_skb_sk+0x24/0x90
[161846.962899]  [<ffffffffa075269a>] xenvif_tx_submit+0x2ca/0x3f0 [xen_netback]
[161846.962906]  [<ffffffffa0753f0c>] xenvif_tx_action+0x9c/0xd0 [xen_netback]
[161846.962915]  [<ffffffffa07567f5>] xenvif_poll+0x35/0x70 [xen_netback]
[161846.962920]  [<ffffffff8160e01b>] napi_poll+0xcb/0x1e0
[161846.962925]  [<ffffffff8160e1c0>] net_rx_action+0x90/0x1c0
[161846.962931]  [<ffffffff8108aaba>] __do_softirq+0x10a/0x350
[161846.962938]  [<ffffffff8108ae75>] irq_exit+0x125/0x130
[161846.962943]  [<ffffffff813f03a9>] xen_evtchn_do_upcall+0x39/0x50
[161846.962950]  [<ffffffff816e7ffe>] xen_do_hypervisor_callback+0x1e/0x40
[161846.962952]  <EOI>
[161846.962959]  [<ffffffff816e5c4a>] ? _raw_spin_lock+0x4a/0x80
[161846.962964]  [<ffffffff816e5b1e>] ? _raw_spin_lock_irqsave+0x1e/0xa0
[161846.962978]  [<ffffffffa028e279>] ? qlcnic_83xx_mailbox_worker+0xb9/0x2a0 [qlcnic]
[161846.962991]  [<ffffffff810a14e1>] ? process_one_work+0x151/0x4b0
[161846.962995]  [<ffffffff8100c3f2>] ? check_events+0x12/0x20
[161846.963001]  [<ffffffff810a1960>] ? worker_thread+0x120/0x480
[161846.963005]  [<ffffffff816e187b>] ? __schedule+0x30b/0x890
[161846.963010]  [<ffffffff810a1840>] ? process_one_work+0x4b0/0x4b0
[161846.963015]  [<ffffffff810a1840>] ? process_one_work+0x4b0/0x4b0
[161846.963021]  [<ffffffff810a6b3e>] ? kthread+0xce/0xf0
[161846.963025]  [<ffffffff810a6a70>] ? kthread_freezable_should_stop+0x70/0x70
[161846.963031]  [<ffffffff816e6522>] ? ret_from_fork+0x42/0x70
[161846.963035]  [<ffffffff810a6a70>] ? kthread_freezable_should_stop+0x70/0x70
[161846.963037] Code: cc 51 41 53 b8 1c 00 00 00 0f 05 41 5b 59 c3 cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc 51 41 53 b8 1d 00 00 00 0f 05 <41> 5b 59 c3 cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc

Signed-off-by: Junxiao Bi <junxiao.bi@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
index bdbcd2b088a0..c3c28f0960e5 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
@@ -3849,7 +3849,7 @@ static void qlcnic_83xx_flush_mbx_queue(struct qlcnic_adapter *adapter)
 	struct list_head *head = &mbx->cmd_q;
 	struct qlcnic_cmd_args *cmd = NULL;
 
-	spin_lock(&mbx->queue_lock);
+	spin_lock_bh(&mbx->queue_lock);
 
 	while (!list_empty(head)) {
 		cmd = list_entry(head->next, struct qlcnic_cmd_args, list);
@@ -3860,7 +3860,7 @@ static void qlcnic_83xx_flush_mbx_queue(struct qlcnic_adapter *adapter)
 		qlcnic_83xx_notify_cmd_completion(adapter, cmd);
 	}
 
-	spin_unlock(&mbx->queue_lock);
+	spin_unlock_bh(&mbx->queue_lock);
 }
 
 static int qlcnic_83xx_check_mbx_status(struct qlcnic_adapter *adapter)
@@ -3896,12 +3896,12 @@ static void qlcnic_83xx_dequeue_mbx_cmd(struct qlcnic_adapter *adapter,
 {
 	struct qlcnic_mailbox *mbx = adapter->ahw->mailbox;
 
-	spin_lock(&mbx->queue_lock);
+	spin_lock_bh(&mbx->queue_lock);
 
 	list_del(&cmd->list);
 	mbx->num_cmds--;
 
-	spin_unlock(&mbx->queue_lock);
+	spin_unlock_bh(&mbx->queue_lock);
 
 	qlcnic_83xx_notify_cmd_completion(adapter, cmd);
 }
@@ -3966,7 +3966,7 @@ static int qlcnic_83xx_enqueue_mbx_cmd(struct qlcnic_adapter *adapter,
 		init_completion(&cmd->completion);
 		cmd->rsp_opcode = QLC_83XX_MBX_RESPONSE_UNKNOWN;
 
-		spin_lock(&mbx->queue_lock);
+		spin_lock_bh(&mbx->queue_lock);
 
 		list_add_tail(&cmd->list, &mbx->cmd_q);
 		mbx->num_cmds++;
@@ -3974,7 +3974,7 @@ static int qlcnic_83xx_enqueue_mbx_cmd(struct qlcnic_adapter *adapter,
 		*timeout = cmd->total_cmds * QLC_83XX_MBX_TIMEOUT;
 		queue_work(mbx->work_q, &mbx->work);
 
-		spin_unlock(&mbx->queue_lock);
+		spin_unlock_bh(&mbx->queue_lock);
 
 		return 0;
 	}
@@ -4070,15 +4070,15 @@ static void qlcnic_83xx_mailbox_worker(struct work_struct *work)
 		mbx->rsp_status = QLC_83XX_MBX_RESPONSE_WAIT;
 		spin_unlock_irqrestore(&mbx->aen_lock, flags);
 
-		spin_lock(&mbx->queue_lock);
+		spin_lock_bh(&mbx->queue_lock);
 
 		if (list_empty(head)) {
-			spin_unlock(&mbx->queue_lock);
+			spin_unlock_bh(&mbx->queue_lock);
 			return;
 		}
 		cmd = list_entry(head->next, struct qlcnic_cmd_args, list);
 
-		spin_unlock(&mbx->queue_lock);
+		spin_unlock_bh(&mbx->queue_lock);
 
 		mbx_ops->encode_cmd(adapter, cmd);
 		mbx_ops->nofity_fw(adapter, QLC_83XX_MBX_REQUEST);
-- 
2.14.3


From 6dec790761beb9f9afaa52cfaa5bc265ff8d27c9 Mon Sep 17 00:00:00 2001
From: Kristian Evensen <kristian.evensen@gmail.com>
Date: Tue, 30 Jan 2018 14:12:55 +0100
Subject: [PATCH 04/11] qmi_wwan: Add support for Quectel EP06
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit c0b91a56a2e57a5a370655b25d677ae0ebf8a2d0 ]

The Quectel EP06 is a Cat. 6 LTE modem. It uses the same interface as
the EC20/EC25 for QMI, and requires the same "set DTR"-quirk to work.

Signed-off-by: Kristian Evensen <kristian.evensen@gmail.com>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index db65d9ad4488..e1e5e8438457 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -944,6 +944,7 @@ static const struct usb_device_id products[] = {
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0125, 4)},	/* Quectel EC25, EC20 R2.0  Mini PCIe */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0121, 4)},	/* Quectel EC21 Mini PCIe */
 	{QMI_FIXED_INTF(0x2c7c, 0x0296, 4)},	/* Quectel BG96 */
+	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0306, 4)},	/* Quectel EP06 Mini PCIe */
 
 	/* 4. Gobi 1000 devices */
 	{QMI_GOBI1K_DEVICE(0x05c6, 0x9212)},	/* Acer Gobi Modem Device */
-- 
2.14.3


From aadad4d86fc9342929693b6cf9f1cf9989b22c5a Mon Sep 17 00:00:00 2001
From: Chunhao Lin <hau@realtek.com>
Date: Wed, 31 Jan 2018 01:32:36 +0800
Subject: [PATCH 05/11] r8169: fix RTL8168EP take too long to complete driver
 initialization.

[ Upstream commit 086ca23d03c0d2f4088f472386778d293e15c5f6 ]

Driver check the wrong register bit in rtl_ocp_tx_cond() that keep driver
waiting until timeout.

Fix this by waiting for the right register bit.

Signed-off-by: Chunhao Lin <hau@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 298b74ebc1e9..18e68c91e651 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -1387,7 +1387,7 @@ DECLARE_RTL_COND(rtl_ocp_tx_cond)
 {
 	void __iomem *ioaddr = tp->mmio_addr;
 
-	return RTL_R8(IBISR0) & 0x02;
+	return RTL_R8(IBISR0) & 0x20;
 }
 
 static void rtl8168ep_stop_cmac(struct rtl8169_private *tp)
@@ -1395,7 +1395,7 @@ static void rtl8168ep_stop_cmac(struct rtl8169_private *tp)
 	void __iomem *ioaddr = tp->mmio_addr;
 
 	RTL_W8(IBCR2, RTL_R8(IBCR2) & ~0x01);
-	rtl_msleep_loop_wait_low(tp, &rtl_ocp_tx_cond, 50, 2000);
+	rtl_msleep_loop_wait_high(tp, &rtl_ocp_tx_cond, 50, 2000);
 	RTL_W8(IBISR0, RTL_R8(IBISR0) | 0x20);
 	RTL_W8(IBCR0, RTL_R8(IBCR0) & ~0x01);
 }
-- 
2.14.3


From f84953a27220aac8a2fd972c70d407a746a47796 Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Fri, 26 Jan 2018 16:40:41 +0800
Subject: [PATCH 06/11] tcp: release sk_frag.page in tcp_disconnect

[ Upstream commit 9b42d55a66d388e4dd5550107df051a9637564fc ]

socket can be disconnected and gets transformed back to a listening
socket, if sk_frag.page is not released, which will be cloned into
a new socket by sk_clone_lock, but the reference count of this page
is increased, lead to a use after free or double free issue

Signed-off-by: Li RongQing <lirongqing@baidu.com>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 7efa6b062049..0d1a767db1bb 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2316,6 +2316,12 @@ int tcp_disconnect(struct sock *sk, int flags)
 
 	WARN_ON(inet->inet_num && !icsk->icsk_bind_hash);
 
+	if (sk->sk_frag.page) {
+		put_page(sk->sk_frag.page);
+		sk->sk_frag.page = NULL;
+		sk->sk_frag.offset = 0;
+	}
+
 	sk->sk_error_report(sk);
 	return err;
 }
-- 
2.14.3


From 90b52894b6ffc521ab0d995a9b6f345fdcabcd2a Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Thu, 25 Jan 2018 22:03:52 +0800
Subject: [PATCH 07/11] vhost_net: stop device during reset owner

[ Upstream commit 4cd879515d686849eec5f718aeac62a70b067d82 ]

We don't stop device before reset owner, this means we could try to
serve any virtqueue kick before reset dev->worker. This will result a
warn since the work was pending at llist during owner resetting. Fix
this by stopping device during owner reset.

Reported-by: syzbot+eb17c6162478cc50632c@syzkaller.appspotmail.com
Fixes: 3a4d5c94e9593 ("vhost_net: a kernel-level virtio server")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/net.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 96a0661011fd..e5b7652234fc 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -1078,6 +1078,7 @@ static long vhost_net_reset_owner(struct vhost_net *n)
 	}
 	vhost_net_stop(n, &tx_sock, &rx_sock);
 	vhost_net_flush(n);
+	vhost_dev_stop(&n->dev);
 	vhost_dev_reset_owner(&n->dev, umem);
 	vhost_net_vq_reset(n);
 done:
-- 
2.14.3


From f78fcfc3eacb0df7bfbfff1e4ec8202f122370a7 Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Wed, 31 Jan 2018 15:43:05 -0500
Subject: [PATCH 08/11] tcp_bbr: fix pacing_gain to always be unity when using
 lt_bw

[ Upstream commit 3aff3b4b986e51bcf4ab249e5d48d39596e0df6a ]

This commit fixes the pacing_gain to remain at BBR_UNIT (1.0) when
using lt_bw and returning from the PROBE_RTT state to PROBE_BW.

Previously, when using lt_bw, upon exiting PROBE_RTT and entering
PROBE_BW the bbr_reset_probe_bw_mode() code could sometimes randomly
end up with a cycle_idx of 0 and hence have bbr_advance_cycle_phase()
set a pacing gain above 1.0. In such cases this would result in a
pacing rate that is 1.25x higher than intended, potentially resulting
in a high loss rate for a little while until we stop using the lt_bw a
bit later.

This commit is a stable candidate for kernels back as far as 4.9.

Fixes: 0f8782ea1497 ("tcp_bbr: add BBR congestion control")
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Reported-by: Beyers Cronje <bcronje@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_bbr.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index e86a34fd5484..8ec60532be2b 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -452,7 +452,8 @@ static void bbr_advance_cycle_phase(struct sock *sk)
 
 	bbr->cycle_idx = (bbr->cycle_idx + 1) & (CYCLE_LEN - 1);
 	bbr->cycle_mstamp = tp->delivered_mstamp;
-	bbr->pacing_gain = bbr_pacing_gain[bbr->cycle_idx];
+	bbr->pacing_gain = bbr->lt_use_bw ? BBR_UNIT :
+					    bbr_pacing_gain[bbr->cycle_idx];
 }
 
 /* Gain cycling: cycle pacing gain to converge to fair share of available bw. */
@@ -461,8 +462,7 @@ static void bbr_update_cycle_phase(struct sock *sk,
 {
 	struct bbr *bbr = inet_csk_ca(sk);
 
-	if ((bbr->mode == BBR_PROBE_BW) && !bbr->lt_use_bw &&
-	    bbr_is_next_cycle_phase(sk, rs))
+	if (bbr->mode == BBR_PROBE_BW && bbr_is_next_cycle_phase(sk, rs))
 		bbr_advance_cycle_phase(sk);
 }
 
-- 
2.14.3


From 5c28a20e7fcdece0da31e187e8d263254aeda253 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 2 Feb 2018 16:02:22 +0100
Subject: [PATCH 09/11] cls_u32: add missing RCU annotation.

[ Upstream commit 058a6c033488494a6b1477b05fe8e1a16e344462 ]

In a couple of points of the control path, n->ht_down is currently
accessed without the required RCU annotation. The accesses are
safe, but sparse complaints. Since we already held the
rtnl lock, let use rtnl_dereference().

Fixes: a1b7c5fd7fe9 ("net: sched: add cls_u32 offload hooks for netdevs")
Fixes: de5df63228fc ("net: sched: cls_u32 changes to knode must appear atomic to readers")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_u32.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index ae83c3aec308..da574a16e7b3 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -496,6 +496,7 @@ static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h)
 static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n,
 				u32 flags)
 {
+	struct tc_u_hnode *ht = rtnl_dereference(n->ht_down);
 	struct net_device *dev = tp->q->dev_queue->dev;
 	struct tc_cls_u32_offload u32_offload = {0};
 	struct tc_to_netdev offload;
@@ -520,7 +521,7 @@ static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n,
 	offload.cls_u32->knode.sel = &n->sel;
 	offload.cls_u32->knode.exts = &n->exts;
 	if (n->ht_down)
-		offload.cls_u32->knode.link_handle = n->ht_down->handle;
+		offload.cls_u32->knode.link_handle = ht->handle;
 
 	err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle,
 					    tp->protocol, &offload);
@@ -788,8 +789,9 @@ static void u32_replace_knode(struct tcf_proto *tp, struct tc_u_common *tp_c,
 static struct tc_u_knode *u32_init_knode(struct tcf_proto *tp,
 					 struct tc_u_knode *n)
 {
-	struct tc_u_knode *new;
+	struct tc_u_hnode *ht = rtnl_dereference(n->ht_down);
 	struct tc_u32_sel *s = &n->sel;
+	struct tc_u_knode *new;
 
 	new = kzalloc(sizeof(*n) + s->nkeys*sizeof(struct tc_u32_key),
 		      GFP_KERNEL);
@@ -807,11 +809,11 @@ static struct tc_u_knode *u32_init_knode(struct tcf_proto *tp,
 	new->fshift = n->fshift;
 	new->res = n->res;
 	new->flags = n->flags;
-	RCU_INIT_POINTER(new->ht_down, n->ht_down);
+	RCU_INIT_POINTER(new->ht_down, ht);
 
 	/* bump reference count as long as we hold pointer to structure */
-	if (new->ht_down)
-		new->ht_down->refcnt++;
+	if (ht)
+		ht->refcnt++;
 
 #ifdef CONFIG_CLS_U32_PERF
 	/* Statistics may be incremented by readers during update
-- 
2.14.3


From 0d4e792cd683fa8b8461af4117622c10b4049f9e Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 24 Jan 2018 23:15:27 -0800
Subject: [PATCH 10/11] ipv6: Fix SO_REUSEPORT UDP socket with implicit
 sk_ipv6only

[ Upstream commit 7ece54a60ee2ba7a386308cae73c790bd580589c ]

If a sk_v6_rcv_saddr is !IPV6_ADDR_ANY and !IPV6_ADDR_MAPPED, it
implicitly implies it is an ipv6only socket.  However, in inet6_bind(),
this addr_type checking and setting sk->sk_ipv6only to 1 are only done
after sk->sk_prot->get_port(sk, snum) has been completed successfully.

This inconsistency between sk_v6_rcv_saddr and sk_ipv6only confuses
the 'get_port()'.

In particular, when binding SO_REUSEPORT UDP sockets,
udp_reuseport_add_sock(sk,...) is called.  udp_reuseport_add_sock()
checks "ipv6_only_sock(sk2) == ipv6_only_sock(sk)" before adding sk to
sk2->sk_reuseport_cb.  In this case, ipv6_only_sock(sk2) could be
1 while ipv6_only_sock(sk) is still 0 here.  The end result is,
reuseport_alloc(sk) is called instead of adding sk to the existing
sk2->sk_reuseport_cb.

It can be reproduced by binding two SO_REUSEPORT UDP sockets on an
IPv6 address (!ANY and !MAPPED).  Only one of the socket will
receive packet.

The fix is to set the implicit sk_ipv6only before calling get_port().
The original sk_ipv6only has to be saved such that it can be restored
in case get_port() failed.  The situation is similar to the
inet_reset_saddr(sk) after get_port() has failed.

Thanks to Calvin Owens <calvinowens@fb.com> who created an easy
reproduction which leads to a fix.

Fixes: e32ea7e74727 ("soreuseport: fast reuseport UDP socket selection")
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/af_inet6.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 5cad76f87536..421379014995 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -274,6 +274,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	struct net *net = sock_net(sk);
 	__be32 v4addr = 0;
 	unsigned short snum;
+	bool saved_ipv6only;
 	int addr_type = 0;
 	int err = 0;
 
@@ -378,19 +379,21 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	if (!(addr_type & IPV6_ADDR_MULTICAST))
 		np->saddr = addr->sin6_addr;
 
+	saved_ipv6only = sk->sk_ipv6only;
+	if (addr_type != IPV6_ADDR_ANY && addr_type != IPV6_ADDR_MAPPED)
+		sk->sk_ipv6only = 1;
+
 	/* Make sure we are allowed to bind here. */
 	if ((snum || !inet->bind_address_no_port) &&
 	    sk->sk_prot->get_port(sk, snum)) {
+		sk->sk_ipv6only = saved_ipv6only;
 		inet_reset_saddr(sk);
 		err = -EADDRINUSE;
 		goto out;
 	}
 
-	if (addr_type != IPV6_ADDR_ANY) {
+	if (addr_type != IPV6_ADDR_ANY)
 		sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
-		if (addr_type != IPV6_ADDR_MAPPED)
-			sk->sk_ipv6only = 1;
-	}
 	if (snum)
 		sk->sk_userlocks |= SOCK_BINDPORT_LOCK;
 	inet->inet_sport = htons(inet->inet_num);
-- 
2.14.3


From 703a3c2954796438e126baac2fb2ede0fc1e9eb6 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 2 Feb 2018 10:27:27 -0800
Subject: [PATCH 11/11] soreuseport: fix mem leak in reuseport_add_sock()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 4db428a7c9ab07e08783e0fcdc4ca0f555da0567 ]

reuseport_add_sock() needs to deal with attaching a socket having
its own sk_reuseport_cb, after a prior
setsockopt(SO_ATTACH_REUSEPORT_?BPF)

Without this fix, not only a WARN_ONCE() was issued, but we were also
leaking memory.

Thanks to sysbot and Eric Biggers for providing us nice C repros.

------------[ cut here ]------------
socket already in reuseport group
WARNING: CPU: 0 PID: 3496 at net/core/sock_reuseport.c:119  
reuseport_add_sock+0x742/0x9b0 net/core/sock_reuseport.c:117
Kernel panic - not syncing: panic_on_warn set ...

CPU: 0 PID: 3496 Comm: syzkaller869503 Not tainted 4.15.0-rc6+ #245
Hardware name: Google Google Compute Engine/Google Compute Engine,
BIOS  
Google 01/01/2011
Call Trace:
  __dump_stack lib/dump_stack.c:17 [inline]
  dump_stack+0x194/0x257 lib/dump_stack.c:53
  panic+0x1e4/0x41c kernel/panic.c:183
  __warn+0x1dc/0x200 kernel/panic.c:547
  report_bug+0x211/0x2d0 lib/bug.c:184
  fixup_bug.part.11+0x37/0x80 arch/x86/kernel/traps.c:178
  fixup_bug arch/x86/kernel/traps.c:247 [inline]
  do_error_trap+0x2d7/0x3e0 arch/x86/kernel/traps.c:296
  do_invalid_op+0x1b/0x20 arch/x86/kernel/traps.c:315
  invalid_op+0x22/0x40 arch/x86/entry/entry_64.S:1079

Fixes: ef456144da8e ("soreuseport: define reuseport groups")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot+c0ea2226f77a42936bf7@syzkaller.appspotmail.com
Acked-by: Craig Gallek <kraig@google.com>

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock_reuseport.c | 35 ++++++++++++++++++++---------------
 1 file changed, 20 insertions(+), 15 deletions(-)

diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index 77f396b679ce..5dce4291f0ed 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -93,6 +93,16 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse)
 	return more_reuse;
 }
 
+static void reuseport_free_rcu(struct rcu_head *head)
+{
+	struct sock_reuseport *reuse;
+
+	reuse = container_of(head, struct sock_reuseport, rcu);
+	if (reuse->prog)
+		bpf_prog_destroy(reuse->prog);
+	kfree(reuse);
+}
+
 /**
  *  reuseport_add_sock - Add a socket to the reuseport group of another.
  *  @sk:  New socket to add to the group.
@@ -101,7 +111,7 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse)
  */
 int reuseport_add_sock(struct sock *sk, struct sock *sk2)
 {
-	struct sock_reuseport *reuse;
+	struct sock_reuseport *old_reuse, *reuse;
 
 	if (!rcu_access_pointer(sk2->sk_reuseport_cb)) {
 		int err = reuseport_alloc(sk2);
@@ -112,10 +122,13 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2)
 
 	spin_lock_bh(&reuseport_lock);
 	reuse = rcu_dereference_protected(sk2->sk_reuseport_cb,
-					  lockdep_is_held(&reuseport_lock)),
-	WARN_ONCE(rcu_dereference_protected(sk->sk_reuseport_cb,
-					    lockdep_is_held(&reuseport_lock)),
-		  "socket already in reuseport group");
+					  lockdep_is_held(&reuseport_lock));
+	old_reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
+					     lockdep_is_held(&reuseport_lock));
+	if (old_reuse && old_reuse->num_socks != 1) {
+		spin_unlock_bh(&reuseport_lock);
+		return -EBUSY;
+	}
 
 	if (reuse->num_socks == reuse->max_socks) {
 		reuse = reuseport_grow(reuse);
@@ -133,19 +146,11 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2)
 
 	spin_unlock_bh(&reuseport_lock);
 
+	if (old_reuse)
+		call_rcu(&old_reuse->rcu, reuseport_free_rcu);
 	return 0;
 }
 
-static void reuseport_free_rcu(struct rcu_head *head)
-{
-	struct sock_reuseport *reuse;
-
-	reuse = container_of(head, struct sock_reuseport, rcu);
-	if (reuse->prog)
-		bpf_prog_destroy(reuse->prog);
-	kfree(reuse);
-}
-
 void reuseport_detach_sock(struct sock *sk)
 {
 	struct sock_reuseport *reuse;
-- 
2.14.3


[-- Attachment #3: net_414.mbox --]
[-- Type: Application/Octet-Stream, Size: 44815 bytes --]

From 00843d45dd3923e4ada48b48ae8d76997da16015 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Wed, 31 Jan 2018 16:29:30 +0200
Subject: [PATCH 01/13] ip6mr: fix stale iterator

[ Upstream commit 4adfa79fc254efb7b0eb3cd58f62c2c3f805f1ba ]

When we dump the ip6mr mfc entries via proc, we initialize an iterator
with the table to dump but we don't clear the cache pointer which might
be initialized from a prior read on the same descriptor that ended. This
can result in lock imbalance (an unnecessary unlock) leading to other
crashes and hangs. Clear the cache pointer like ipmr does to fix the issue.
Thanks for the reliable reproducer.

Here's syzbot's trace:
 WARNING: bad unlock balance detected!
 4.15.0-rc3+ #128 Not tainted
 syzkaller971460/3195 is trying to release lock (mrt_lock) at:
 [<000000006898068d>] ipmr_mfc_seq_stop+0xe1/0x130 net/ipv6/ip6mr.c:553
 but there are no more locks to release!

 other info that might help us debug this:
 1 lock held by syzkaller971460/3195:
  #0:  (&p->lock){+.+.}, at: [<00000000744a6565>] seq_read+0xd5/0x13d0
 fs/seq_file.c:165

 stack backtrace:
 CPU: 1 PID: 3195 Comm: syzkaller971460 Not tainted 4.15.0-rc3+ #128
 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
 Google 01/01/2011
 Call Trace:
  __dump_stack lib/dump_stack.c:17 [inline]
  dump_stack+0x194/0x257 lib/dump_stack.c:53
  print_unlock_imbalance_bug+0x12f/0x140 kernel/locking/lockdep.c:3561
  __lock_release kernel/locking/lockdep.c:3775 [inline]
  lock_release+0x5f9/0xda0 kernel/locking/lockdep.c:4023
  __raw_read_unlock include/linux/rwlock_api_smp.h:225 [inline]
  _raw_read_unlock+0x1a/0x30 kernel/locking/spinlock.c:255
  ipmr_mfc_seq_stop+0xe1/0x130 net/ipv6/ip6mr.c:553
  traverse+0x3bc/0xa00 fs/seq_file.c:135
  seq_read+0x96a/0x13d0 fs/seq_file.c:189
  proc_reg_read+0xef/0x170 fs/proc/inode.c:217
  do_loop_readv_writev fs/read_write.c:673 [inline]
  do_iter_read+0x3db/0x5b0 fs/read_write.c:897
  compat_readv+0x1bf/0x270 fs/read_write.c:1140
  do_compat_preadv64+0xdc/0x100 fs/read_write.c:1189
  C_SYSC_preadv fs/read_write.c:1209 [inline]
  compat_SyS_preadv+0x3b/0x50 fs/read_write.c:1203
  do_syscall_32_irqs_on arch/x86/entry/common.c:327 [inline]
  do_fast_syscall_32+0x3ee/0xf9d arch/x86/entry/common.c:389
  entry_SYSENTER_compat+0x51/0x60 arch/x86/entry/entry_64_compat.S:125
 RIP: 0023:0xf7f73c79
 RSP: 002b:00000000e574a15c EFLAGS: 00000292 ORIG_RAX: 000000000000014d
 RAX: ffffffffffffffda RBX: 000000000000000f RCX: 0000000020a3afb0
 RDX: 0000000000000001 RSI: 0000000000000067 RDI: 0000000000000000
 RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000
 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
 BUG: sleeping function called from invalid context at lib/usercopy.c:25
 in_atomic(): 1, irqs_disabled(): 0, pid: 3195, name: syzkaller971460
 INFO: lockdep is turned off.
 CPU: 1 PID: 3195 Comm: syzkaller971460 Not tainted 4.15.0-rc3+ #128
 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
 Google 01/01/2011
 Call Trace:
  __dump_stack lib/dump_stack.c:17 [inline]
  dump_stack+0x194/0x257 lib/dump_stack.c:53
  ___might_sleep+0x2b2/0x470 kernel/sched/core.c:6060
  __might_sleep+0x95/0x190 kernel/sched/core.c:6013
  __might_fault+0xab/0x1d0 mm/memory.c:4525
  _copy_to_user+0x2c/0xc0 lib/usercopy.c:25
  copy_to_user include/linux/uaccess.h:155 [inline]
  seq_read+0xcb4/0x13d0 fs/seq_file.c:279
  proc_reg_read+0xef/0x170 fs/proc/inode.c:217
  do_loop_readv_writev fs/read_write.c:673 [inline]
  do_iter_read+0x3db/0x5b0 fs/read_write.c:897
  compat_readv+0x1bf/0x270 fs/read_write.c:1140
  do_compat_preadv64+0xdc/0x100 fs/read_write.c:1189
  C_SYSC_preadv fs/read_write.c:1209 [inline]
  compat_SyS_preadv+0x3b/0x50 fs/read_write.c:1203
  do_syscall_32_irqs_on arch/x86/entry/common.c:327 [inline]
  do_fast_syscall_32+0x3ee/0xf9d arch/x86/entry/common.c:389
  entry_SYSENTER_compat+0x51/0x60 arch/x86/entry/entry_64_compat.S:125
 RIP: 0023:0xf7f73c79
 RSP: 002b:00000000e574a15c EFLAGS: 00000292 ORIG_RAX: 000000000000014d
 RAX: ffffffffffffffda RBX: 000000000000000f RCX: 0000000020a3afb0
 RDX: 0000000000000001 RSI: 0000000000000067 RDI: 0000000000000000
 RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000
 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
 WARNING: CPU: 1 PID: 3195 at lib/usercopy.c:26 _copy_to_user+0xb5/0xc0
 lib/usercopy.c:26

Reported-by: syzbot <bot+eceb3204562c41a438fa1f2335e0fe4f6886d669@syzkaller.appspotmail.com>
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6mr.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index f5500f5444e9..e1060f28410d 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -496,6 +496,7 @@ static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos)
 		return ERR_PTR(-ENOENT);
 
 	it->mrt = mrt;
+	it->cache = NULL;
 	return *pos ? ipmr_mfc_seq_idx(net, seq->private, *pos - 1)
 		: SEQ_START_TOKEN;
 }
-- 
2.14.3


From 7f2a68d31c55ab09a36aaa49a7824365e7ee2f54 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 1 Feb 2018 10:26:57 -0800
Subject: [PATCH 02/13] net: igmp: add a missing rcu locking section

[ Upstream commit e7aadb27a5415e8125834b84a74477bfbee4eff5 ]

Newly added igmpv3_get_srcaddr() needs to be called under rcu lock.

Timer callbacks do not ensure this locking.

=============================
WARNING: suspicious RCU usage
4.15.0+ #200 Not tainted
-----------------------------
./include/linux/inetdevice.h:216 suspicious rcu_dereference_check() usage!

other info that might help us debug this:

rcu_scheduler_active = 2, debug_locks = 1
3 locks held by syzkaller616973/4074:
 #0:  (&mm->mmap_sem){++++}, at: [<00000000bfce669e>] __do_page_fault+0x32d/0xc90 arch/x86/mm/fault.c:1355
 #1:  ((&im->timer)){+.-.}, at: [<00000000619d2f71>] lockdep_copy_map include/linux/lockdep.h:178 [inline]
 #1:  ((&im->timer)){+.-.}, at: [<00000000619d2f71>] call_timer_fn+0x1c6/0x820 kernel/time/timer.c:1316
 #2:  (&(&im->lock)->rlock){+.-.}, at: [<000000005f833c5c>] spin_lock_bh include/linux/spinlock.h:315 [inline]
 #2:  (&(&im->lock)->rlock){+.-.}, at: [<000000005f833c5c>] igmpv3_send_report+0x98/0x5b0 net/ipv4/igmp.c:600

stack backtrace:
CPU: 0 PID: 4074 Comm: syzkaller616973 Not tainted 4.15.0+ #200
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x194/0x257 lib/dump_stack.c:53
 lockdep_rcu_suspicious+0x123/0x170 kernel/locking/lockdep.c:4592
 __in_dev_get_rcu include/linux/inetdevice.h:216 [inline]
 igmpv3_get_srcaddr net/ipv4/igmp.c:329 [inline]
 igmpv3_newpack+0xeef/0x12e0 net/ipv4/igmp.c:389
 add_grhead.isra.27+0x235/0x300 net/ipv4/igmp.c:432
 add_grec+0xbd3/0x1170 net/ipv4/igmp.c:565
 igmpv3_send_report+0xd5/0x5b0 net/ipv4/igmp.c:605
 igmp_send_report+0xc43/0x1050 net/ipv4/igmp.c:722
 igmp_timer_expire+0x322/0x5c0 net/ipv4/igmp.c:831
 call_timer_fn+0x228/0x820 kernel/time/timer.c:1326
 expire_timers kernel/time/timer.c:1363 [inline]
 __run_timers+0x7ee/0xb70 kernel/time/timer.c:1666
 run_timer_softirq+0x4c/0x70 kernel/time/timer.c:1692
 __do_softirq+0x2d7/0xb85 kernel/softirq.c:285
 invoke_softirq kernel/softirq.c:365 [inline]
 irq_exit+0x1cc/0x200 kernel/softirq.c:405
 exiting_irq arch/x86/include/asm/apic.h:541 [inline]
 smp_apic_timer_interrupt+0x16b/0x700 arch/x86/kernel/apic/apic.c:1052
 apic_timer_interrupt+0xa9/0xb0 arch/x86/entry/entry_64.S:938

Fixes: a46182b00290 ("net: igmp: Use correct source address on IGMPv3 reports")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/igmp.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 013fed55b610..fbeb35ad804b 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -386,7 +386,11 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu)
 	pip->frag_off = htons(IP_DF);
 	pip->ttl      = 1;
 	pip->daddr    = fl4.daddr;
+
+	rcu_read_lock();
 	pip->saddr    = igmpv3_get_srcaddr(dev, &fl4);
+	rcu_read_unlock();
+
 	pip->protocol = IPPROTO_IGMP;
 	pip->tot_len  = 0;	/* filled in later */
 	ip_select_ident(net, skb, NULL);
-- 
2.14.3


From a68b7e2d456396386e2963ea929152899ead0b37 Mon Sep 17 00:00:00 2001
From: Junxiao Bi <junxiao.bi@oracle.com>
Date: Mon, 29 Jan 2018 17:53:42 +0800
Subject: [PATCH 03/13] qlcnic: fix deadlock bug

[ Upstream commit 233ac3891607f501f08879134d623b303838f478 ]

The following soft lockup was caught. This is a deadlock caused by
recusive locking.

Process kworker/u40:1:28016 was holding spin lock "mbx->queue_lock" in
qlcnic_83xx_mailbox_worker(), while a softirq came in and ask the same spin
lock in qlcnic_83xx_enqueue_mbx_cmd(). This lock should be hold by disable
bh..

[161846.962125] NMI watchdog: BUG: soft lockup - CPU#1 stuck for 22s! [kworker/u40:1:28016]
[161846.962367] Modules linked in: tun ocfs2 xen_netback xen_blkback xen_gntalloc xen_gntdev xen_evtchn xenfs xen_privcmd autofs4 ocfs2_dlmfs ocfs2_stack_o2cb ocfs2_dlm ocfs2_nodemanager ocfs2_stackglue configfs bnx2fc fcoe libfcoe libfc sunrpc 8021q mrp garp bridge stp llc bonding dm_round_robin dm_multipath iTCO_wdt iTCO_vendor_support pcspkr sb_edac edac_core i2c_i801 shpchp lpc_ich mfd_core ioatdma ipmi_devintf ipmi_si ipmi_msghandler sg ext4 jbd2 mbcache2 sr_mod cdrom sd_mod igb i2c_algo_bit i2c_core ahci libahci megaraid_sas ixgbe dca ptp pps_core vxlan udp_tunnel ip6_udp_tunnel qla2xxx scsi_transport_fc qlcnic crc32c_intel be2iscsi bnx2i cnic uio cxgb4i cxgb4 cxgb3i libcxgbi ipv6 cxgb3 mdio libiscsi_tcp qla4xxx iscsi_boot_sysfs libiscsi scsi_transport_iscsi dm_mirror dm_region_hash dm_log dm_mod
[161846.962454]
[161846.962460] CPU: 1 PID: 28016 Comm: kworker/u40:1 Not tainted 4.1.12-94.5.9.el6uek.x86_64 #2
[161846.962463] Hardware name: Oracle Corporation SUN SERVER X4-2L      /ASSY,MB,X4-2L         , BIOS 26050100 09/19/2017
[161846.962489] Workqueue: qlcnic_mailbox qlcnic_83xx_mailbox_worker [qlcnic]
[161846.962493] task: ffff8801f2e34600 ti: ffff88004ca5c000 task.ti: ffff88004ca5c000
[161846.962496] RIP: e030:[<ffffffff810013aa>]  [<ffffffff810013aa>] xen_hypercall_sched_op+0xa/0x20
[161846.962506] RSP: e02b:ffff880202e43388  EFLAGS: 00000206
[161846.962509] RAX: 0000000000000000 RBX: ffff8801f6996b70 RCX: ffffffff810013aa
[161846.962511] RDX: ffff880202e433cc RSI: ffff880202e433b0 RDI: 0000000000000003
[161846.962513] RBP: ffff880202e433d0 R08: 0000000000000000 R09: ffff8801fe893200
[161846.962516] R10: ffff8801fe400538 R11: 0000000000000206 R12: ffff880202e4b000
[161846.962518] R13: 0000000000000050 R14: 0000000000000001 R15: 000000000000020d
[161846.962528] FS:  0000000000000000(0000) GS:ffff880202e40000(0000) knlGS:ffff880202e40000
[161846.962531] CS:  e033 DS: 0000 ES: 0000 CR0: 0000000080050033
[161846.962533] CR2: 0000000002612640 CR3: 00000001bb796000 CR4: 0000000000042660
[161846.962536] Stack:
[161846.962538]  ffff880202e43608 0000000000000000 ffffffff813f0442 ffff880202e433b0
[161846.962543]  0000000000000000 ffff880202e433cc ffffffff00000001 0000000000000000
[161846.962547]  00000009813f03d6 ffff880202e433e0 ffffffff813f0460 ffff880202e43440
[161846.962552] Call Trace:
[161846.962555]  <IRQ>
[161846.962565]  [<ffffffff813f0442>] ? xen_poll_irq_timeout+0x42/0x50
[161846.962570]  [<ffffffff813f0460>] xen_poll_irq+0x10/0x20
[161846.962578]  [<ffffffff81014222>] xen_lock_spinning+0xe2/0x110
[161846.962583]  [<ffffffff81013f01>] __raw_callee_save_xen_lock_spinning+0x11/0x20
[161846.962592]  [<ffffffff816e5c57>] ? _raw_spin_lock+0x57/0x80
[161846.962609]  [<ffffffffa028acfc>] qlcnic_83xx_enqueue_mbx_cmd+0x7c/0xe0 [qlcnic]
[161846.962623]  [<ffffffffa028e008>] qlcnic_83xx_issue_cmd+0x58/0x210 [qlcnic]
[161846.962636]  [<ffffffffa028caf2>] qlcnic_83xx_sre_macaddr_change+0x162/0x1d0 [qlcnic]
[161846.962649]  [<ffffffffa028cb8b>] qlcnic_83xx_change_l2_filter+0x2b/0x30 [qlcnic]
[161846.962657]  [<ffffffff8160248b>] ? __skb_flow_dissect+0x18b/0x650
[161846.962670]  [<ffffffffa02856e5>] qlcnic_send_filter+0x205/0x250 [qlcnic]
[161846.962682]  [<ffffffffa0285c77>] qlcnic_xmit_frame+0x547/0x7b0 [qlcnic]
[161846.962691]  [<ffffffff8160ac22>] xmit_one+0x82/0x1a0
[161846.962696]  [<ffffffff8160ad90>] dev_hard_start_xmit+0x50/0xa0
[161846.962701]  [<ffffffff81630112>] sch_direct_xmit+0x112/0x220
[161846.962706]  [<ffffffff8160b80f>] __dev_queue_xmit+0x1df/0x5e0
[161846.962710]  [<ffffffff8160bc33>] dev_queue_xmit_sk+0x13/0x20
[161846.962721]  [<ffffffffa0575bd5>] bond_dev_queue_xmit+0x35/0x80 [bonding]
[161846.962729]  [<ffffffffa05769fb>] __bond_start_xmit+0x1cb/0x210 [bonding]
[161846.962736]  [<ffffffffa0576a71>] bond_start_xmit+0x31/0x60 [bonding]
[161846.962740]  [<ffffffff8160ac22>] xmit_one+0x82/0x1a0
[161846.962745]  [<ffffffff8160ad90>] dev_hard_start_xmit+0x50/0xa0
[161846.962749]  [<ffffffff8160bb1e>] __dev_queue_xmit+0x4ee/0x5e0
[161846.962754]  [<ffffffff8160bc33>] dev_queue_xmit_sk+0x13/0x20
[161846.962760]  [<ffffffffa05cfa72>] vlan_dev_hard_start_xmit+0xb2/0x150 [8021q]
[161846.962764]  [<ffffffff8160ac22>] xmit_one+0x82/0x1a0
[161846.962769]  [<ffffffff8160ad90>] dev_hard_start_xmit+0x50/0xa0
[161846.962773]  [<ffffffff8160bb1e>] __dev_queue_xmit+0x4ee/0x5e0
[161846.962777]  [<ffffffff8160bc33>] dev_queue_xmit_sk+0x13/0x20
[161846.962789]  [<ffffffffa05adf74>] br_dev_queue_push_xmit+0x54/0xa0 [bridge]
[161846.962797]  [<ffffffffa05ae4ff>] br_forward_finish+0x2f/0x90 [bridge]
[161846.962807]  [<ffffffff810b0dad>] ? ttwu_do_wakeup+0x1d/0x100
[161846.962811]  [<ffffffff815f929b>] ? __alloc_skb+0x8b/0x1f0
[161846.962818]  [<ffffffffa05ae04d>] __br_forward+0x8d/0x120 [bridge]
[161846.962822]  [<ffffffff815f613b>] ? __kmalloc_reserve+0x3b/0xa0
[161846.962829]  [<ffffffff810be55e>] ? update_rq_runnable_avg+0xee/0x230
[161846.962836]  [<ffffffffa05ae176>] br_forward+0x96/0xb0 [bridge]
[161846.962845]  [<ffffffffa05af85e>] br_handle_frame_finish+0x1ae/0x420 [bridge]
[161846.962853]  [<ffffffffa05afc4f>] br_handle_frame+0x17f/0x260 [bridge]
[161846.962862]  [<ffffffffa05afad0>] ? br_handle_frame_finish+0x420/0x420 [bridge]
[161846.962867]  [<ffffffff8160d057>] __netif_receive_skb_core+0x1f7/0x870
[161846.962872]  [<ffffffff8160d6f2>] __netif_receive_skb+0x22/0x70
[161846.962877]  [<ffffffff8160d913>] netif_receive_skb_internal+0x23/0x90
[161846.962884]  [<ffffffffa07512ea>] ? xenvif_idx_release+0xea/0x100 [xen_netback]
[161846.962889]  [<ffffffff816e5a10>] ? _raw_spin_unlock_irqrestore+0x20/0x50
[161846.962893]  [<ffffffff8160e624>] netif_receive_skb_sk+0x24/0x90
[161846.962899]  [<ffffffffa075269a>] xenvif_tx_submit+0x2ca/0x3f0 [xen_netback]
[161846.962906]  [<ffffffffa0753f0c>] xenvif_tx_action+0x9c/0xd0 [xen_netback]
[161846.962915]  [<ffffffffa07567f5>] xenvif_poll+0x35/0x70 [xen_netback]
[161846.962920]  [<ffffffff8160e01b>] napi_poll+0xcb/0x1e0
[161846.962925]  [<ffffffff8160e1c0>] net_rx_action+0x90/0x1c0
[161846.962931]  [<ffffffff8108aaba>] __do_softirq+0x10a/0x350
[161846.962938]  [<ffffffff8108ae75>] irq_exit+0x125/0x130
[161846.962943]  [<ffffffff813f03a9>] xen_evtchn_do_upcall+0x39/0x50
[161846.962950]  [<ffffffff816e7ffe>] xen_do_hypervisor_callback+0x1e/0x40
[161846.962952]  <EOI>
[161846.962959]  [<ffffffff816e5c4a>] ? _raw_spin_lock+0x4a/0x80
[161846.962964]  [<ffffffff816e5b1e>] ? _raw_spin_lock_irqsave+0x1e/0xa0
[161846.962978]  [<ffffffffa028e279>] ? qlcnic_83xx_mailbox_worker+0xb9/0x2a0 [qlcnic]
[161846.962991]  [<ffffffff810a14e1>] ? process_one_work+0x151/0x4b0
[161846.962995]  [<ffffffff8100c3f2>] ? check_events+0x12/0x20
[161846.963001]  [<ffffffff810a1960>] ? worker_thread+0x120/0x480
[161846.963005]  [<ffffffff816e187b>] ? __schedule+0x30b/0x890
[161846.963010]  [<ffffffff810a1840>] ? process_one_work+0x4b0/0x4b0
[161846.963015]  [<ffffffff810a1840>] ? process_one_work+0x4b0/0x4b0
[161846.963021]  [<ffffffff810a6b3e>] ? kthread+0xce/0xf0
[161846.963025]  [<ffffffff810a6a70>] ? kthread_freezable_should_stop+0x70/0x70
[161846.963031]  [<ffffffff816e6522>] ? ret_from_fork+0x42/0x70
[161846.963035]  [<ffffffff810a6a70>] ? kthread_freezable_should_stop+0x70/0x70
[161846.963037] Code: cc 51 41 53 b8 1c 00 00 00 0f 05 41 5b 59 c3 cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc 51 41 53 b8 1d 00 00 00 0f 05 <41> 5b 59 c3 cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc

Signed-off-by: Junxiao Bi <junxiao.bi@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
index f7080d0ab874..46b0372dd032 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
@@ -3891,7 +3891,7 @@ static void qlcnic_83xx_flush_mbx_queue(struct qlcnic_adapter *adapter)
 	struct list_head *head = &mbx->cmd_q;
 	struct qlcnic_cmd_args *cmd = NULL;
 
-	spin_lock(&mbx->queue_lock);
+	spin_lock_bh(&mbx->queue_lock);
 
 	while (!list_empty(head)) {
 		cmd = list_entry(head->next, struct qlcnic_cmd_args, list);
@@ -3902,7 +3902,7 @@ static void qlcnic_83xx_flush_mbx_queue(struct qlcnic_adapter *adapter)
 		qlcnic_83xx_notify_cmd_completion(adapter, cmd);
 	}
 
-	spin_unlock(&mbx->queue_lock);
+	spin_unlock_bh(&mbx->queue_lock);
 }
 
 static int qlcnic_83xx_check_mbx_status(struct qlcnic_adapter *adapter)
@@ -3938,12 +3938,12 @@ static void qlcnic_83xx_dequeue_mbx_cmd(struct qlcnic_adapter *adapter,
 {
 	struct qlcnic_mailbox *mbx = adapter->ahw->mailbox;
 
-	spin_lock(&mbx->queue_lock);
+	spin_lock_bh(&mbx->queue_lock);
 
 	list_del(&cmd->list);
 	mbx->num_cmds--;
 
-	spin_unlock(&mbx->queue_lock);
+	spin_unlock_bh(&mbx->queue_lock);
 
 	qlcnic_83xx_notify_cmd_completion(adapter, cmd);
 }
@@ -4008,7 +4008,7 @@ static int qlcnic_83xx_enqueue_mbx_cmd(struct qlcnic_adapter *adapter,
 		init_completion(&cmd->completion);
 		cmd->rsp_opcode = QLC_83XX_MBX_RESPONSE_UNKNOWN;
 
-		spin_lock(&mbx->queue_lock);
+		spin_lock_bh(&mbx->queue_lock);
 
 		list_add_tail(&cmd->list, &mbx->cmd_q);
 		mbx->num_cmds++;
@@ -4016,7 +4016,7 @@ static int qlcnic_83xx_enqueue_mbx_cmd(struct qlcnic_adapter *adapter,
 		*timeout = cmd->total_cmds * QLC_83XX_MBX_TIMEOUT;
 		queue_work(mbx->work_q, &mbx->work);
 
-		spin_unlock(&mbx->queue_lock);
+		spin_unlock_bh(&mbx->queue_lock);
 
 		return 0;
 	}
@@ -4112,15 +4112,15 @@ static void qlcnic_83xx_mailbox_worker(struct work_struct *work)
 		mbx->rsp_status = QLC_83XX_MBX_RESPONSE_WAIT;
 		spin_unlock_irqrestore(&mbx->aen_lock, flags);
 
-		spin_lock(&mbx->queue_lock);
+		spin_lock_bh(&mbx->queue_lock);
 
 		if (list_empty(head)) {
-			spin_unlock(&mbx->queue_lock);
+			spin_unlock_bh(&mbx->queue_lock);
 			return;
 		}
 		cmd = list_entry(head->next, struct qlcnic_cmd_args, list);
 
-		spin_unlock(&mbx->queue_lock);
+		spin_unlock_bh(&mbx->queue_lock);
 
 		mbx_ops->encode_cmd(adapter, cmd);
 		mbx_ops->nofity_fw(adapter, QLC_83XX_MBX_REQUEST);
-- 
2.14.3


From a6c8254193420b28681dd693e45bfd262cfb39c5 Mon Sep 17 00:00:00 2001
From: Kristian Evensen <kristian.evensen@gmail.com>
Date: Tue, 30 Jan 2018 14:12:55 +0100
Subject: [PATCH 04/13] qmi_wwan: Add support for Quectel EP06
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit c0b91a56a2e57a5a370655b25d677ae0ebf8a2d0 ]

The Quectel EP06 is a Cat. 6 LTE modem. It uses the same interface as
the EC20/EC25 for QMI, and requires the same "set DTR"-quirk to work.

Signed-off-by: Kristian Evensen <kristian.evensen@gmail.com>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 2092febfcb42..8d9f02b7a71f 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1243,6 +1243,7 @@ static const struct usb_device_id products[] = {
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0125, 4)},	/* Quectel EC25, EC20 R2.0  Mini PCIe */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0121, 4)},	/* Quectel EC21 Mini PCIe */
 	{QMI_FIXED_INTF(0x2c7c, 0x0296, 4)},	/* Quectel BG96 */
+	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0306, 4)},	/* Quectel EP06 Mini PCIe */
 
 	/* 4. Gobi 1000 devices */
 	{QMI_GOBI1K_DEVICE(0x05c6, 0x9212)},	/* Acer Gobi Modem Device */
-- 
2.14.3


From 4f7a601ceecbb8d3788f7fde3be5cd822b1b8770 Mon Sep 17 00:00:00 2001
From: Chunhao Lin <hau@realtek.com>
Date: Wed, 31 Jan 2018 01:32:36 +0800
Subject: [PATCH 05/13] r8169: fix RTL8168EP take too long to complete driver
 initialization.

[ Upstream commit 086ca23d03c0d2f4088f472386778d293e15c5f6 ]

Driver check the wrong register bit in rtl_ocp_tx_cond() that keep driver
waiting until timeout.

Fix this by waiting for the right register bit.

Signed-off-by: Chunhao Lin <hau@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 958ff931e790..619a1b7281a0 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -1388,7 +1388,7 @@ DECLARE_RTL_COND(rtl_ocp_tx_cond)
 {
 	void __iomem *ioaddr = tp->mmio_addr;
 
-	return RTL_R8(IBISR0) & 0x02;
+	return RTL_R8(IBISR0) & 0x20;
 }
 
 static void rtl8168ep_stop_cmac(struct rtl8169_private *tp)
@@ -1396,7 +1396,7 @@ static void rtl8168ep_stop_cmac(struct rtl8169_private *tp)
 	void __iomem *ioaddr = tp->mmio_addr;
 
 	RTL_W8(IBCR2, RTL_R8(IBCR2) & ~0x01);
-	rtl_msleep_loop_wait_low(tp, &rtl_ocp_tx_cond, 50, 2000);
+	rtl_msleep_loop_wait_high(tp, &rtl_ocp_tx_cond, 50, 2000);
 	RTL_W8(IBISR0, RTL_R8(IBISR0) | 0x20);
 	RTL_W8(IBCR0, RTL_R8(IBCR0) & ~0x01);
 }
-- 
2.14.3


From eb6ccaa07edeeab672378c0a4cfa4471a244171c Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Fri, 26 Jan 2018 16:40:41 +0800
Subject: [PATCH 06/13] tcp: release sk_frag.page in tcp_disconnect

[ Upstream commit 9b42d55a66d388e4dd5550107df051a9637564fc ]

socket can be disconnected and gets transformed back to a listening
socket, if sk_frag.page is not released, which will be cloned into
a new socket by sk_clone_lock, but the reference count of this page
is increased, lead to a use after free or double free issue

Signed-off-by: Li RongQing <lirongqing@baidu.com>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 2a65d806b562..fe11128d7df4 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2379,6 +2379,12 @@ int tcp_disconnect(struct sock *sk, int flags)
 
 	WARN_ON(inet->inet_num && !icsk->icsk_bind_hash);
 
+	if (sk->sk_frag.page) {
+		put_page(sk->sk_frag.page);
+		sk->sk_frag.page = NULL;
+		sk->sk_frag.offset = 0;
+	}
+
 	sk->sk_error_report(sk);
 	return err;
 }
-- 
2.14.3


From 36b3f611dadc8a6a45a5655705158c925d022c83 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Thu, 25 Jan 2018 22:03:52 +0800
Subject: [PATCH 07/13] vhost_net: stop device during reset owner

[ Upstream commit 4cd879515d686849eec5f718aeac62a70b067d82 ]

We don't stop device before reset owner, this means we could try to
serve any virtqueue kick before reset dev->worker. This will result a
warn since the work was pending at llist during owner resetting. Fix
this by stopping device during owner reset.

Reported-by: syzbot+eb17c6162478cc50632c@syzkaller.appspotmail.com
Fixes: 3a4d5c94e9593 ("vhost_net: a kernel-level virtio server")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/net.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index bd15309ac5f1..082891dffd9d 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -1212,6 +1212,7 @@ static long vhost_net_reset_owner(struct vhost_net *n)
 	}
 	vhost_net_stop(n, &tx_sock, &rx_sock);
 	vhost_net_flush(n);
+	vhost_dev_stop(&n->dev);
 	vhost_dev_reset_owner(&n->dev, umem);
 	vhost_net_vq_reset(n);
 done:
-- 
2.14.3


From 827b4836587a32944e553e6d35110fb78ff8cb31 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Fri, 2 Feb 2018 15:26:57 +0000
Subject: [PATCH 08/13] Revert "defer call to mem_cgroup_sk_alloc()"

[ Upstream commit edbe69ef2c90fc86998a74b08319a01c508bd497 ]

This patch effectively reverts commit 9f1c2674b328 ("net: memcontrol:
defer call to mem_cgroup_sk_alloc()").

Moving mem_cgroup_sk_alloc() to the inet_csk_accept() completely breaks
memcg socket memory accounting, as packets received before memcg
pointer initialization are not accounted and are causing refcounting
underflow on socket release.

Actually the free-after-use problem was fixed by
commit c0576e397508 ("net: call cgroup_sk_alloc() earlier in
sk_clone_lock()") for the cgroup pointer.

So, let's revert it and call mem_cgroup_sk_alloc() just before
cgroup_sk_alloc(). This is safe, as we hold a reference to the socket
we're cloning, and it holds a reference to the memcg.

Also, let's drop BUG_ON(mem_cgroup_is_root()) check from
mem_cgroup_sk_alloc(). I see no reasons why bumping the root
memcg counter is a good reason to panic, and there are no realistic
ways to hit it.

Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 mm/memcontrol.c                 | 14 ++++++++++++++
 net/core/sock.c                 |  5 +----
 net/ipv4/inet_connection_sock.c |  1 -
 3 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 53f7c919b916..66e7efabf0a1 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5828,6 +5828,20 @@ void mem_cgroup_sk_alloc(struct sock *sk)
 	if (!mem_cgroup_sockets_enabled)
 		return;
 
+	/*
+	 * Socket cloning can throw us here with sk_memcg already
+	 * filled. It won't however, necessarily happen from
+	 * process context. So the test for root memcg given
+	 * the current task's memcg won't help us in this case.
+	 *
+	 * Respecting the original socket's memcg is a better
+	 * decision in this case.
+	 */
+	if (sk->sk_memcg) {
+		css_get(&sk->sk_memcg->css);
+		return;
+	}
+
 	rcu_read_lock();
 	memcg = mem_cgroup_from_task(current);
 	if (memcg == root_mem_cgroup)
diff --git a/net/core/sock.c b/net/core/sock.c
index 415f441c63b9..beb1e299fed3 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1677,16 +1677,13 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		newsk->sk_dst_pending_confirm = 0;
 		newsk->sk_wmem_queued	= 0;
 		newsk->sk_forward_alloc = 0;
-
-		/* sk->sk_memcg will be populated at accept() time */
-		newsk->sk_memcg = NULL;
-
 		atomic_set(&newsk->sk_drops, 0);
 		newsk->sk_send_head	= NULL;
 		newsk->sk_userlocks	= sk->sk_userlocks & ~SOCK_BINDPORT_LOCK;
 		atomic_set(&newsk->sk_zckey, 0);
 
 		sock_reset_flag(newsk, SOCK_DONE);
+		mem_cgroup_sk_alloc(newsk);
 		cgroup_sk_alloc(&newsk->sk_cgrp_data);
 
 		rcu_read_lock();
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index b47a59cb3573..0cc08c512202 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -475,7 +475,6 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern)
 		}
 		spin_unlock_bh(&queue->fastopenq.lock);
 	}
-	mem_cgroup_sk_alloc(newsk);
 out:
 	release_sock(sk);
 	if (req)
-- 
2.14.3


From 7230dd7bfaa00fce14985a2ac1838f0a5a9336ed Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Thu, 25 Jan 2018 20:16:29 -0800
Subject: [PATCH 09/13] net: ipv6: send unsolicited NA after DAD

[ Upstream commit c76fe2d98c726224a975a0d0198c3fb50406d325 ]

Unsolicited IPv6 neighbor advertisements should be sent after DAD
completes. Update ndisc_send_unsol_na to skip tentative, non-optimistic
addresses and have those sent by addrconf_dad_completed after DAD.

Fixes: 4a6e3c5def13c ("net: ipv6: send unsolicited NA on admin up")
Reported-by: Vivek Venkatraman <vivek@cumulusnetworks.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 30 ++++++++++++++++++++++++++----
 net/ipv6/ndisc.c    |  5 +++++
 2 files changed, 31 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index c5318f5f6a14..6a76e41e6d51 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -184,7 +184,8 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
 
 static void addrconf_dad_start(struct inet6_ifaddr *ifp);
 static void addrconf_dad_work(struct work_struct *w);
-static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id);
+static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id,
+				   bool send_na);
 static void addrconf_dad_run(struct inet6_dev *idev);
 static void addrconf_rs_timer(unsigned long data);
 static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa);
@@ -3825,12 +3826,17 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
 	     idev->cnf.accept_dad < 1) ||
 	    !(ifp->flags&IFA_F_TENTATIVE) ||
 	    ifp->flags & IFA_F_NODAD) {
+		bool send_na = false;
+
+		if (ifp->flags & IFA_F_TENTATIVE &&
+		    !(ifp->flags & IFA_F_OPTIMISTIC))
+			send_na = true;
 		bump_id = ifp->flags & IFA_F_TENTATIVE;
 		ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED);
 		spin_unlock(&ifp->lock);
 		read_unlock_bh(&idev->lock);
 
-		addrconf_dad_completed(ifp, bump_id);
+		addrconf_dad_completed(ifp, bump_id, send_na);
 		return;
 	}
 
@@ -3959,16 +3965,21 @@ static void addrconf_dad_work(struct work_struct *w)
 	}
 
 	if (ifp->dad_probes == 0) {
+		bool send_na = false;
+
 		/*
 		 * DAD was successful
 		 */
 
+		if (ifp->flags & IFA_F_TENTATIVE &&
+		    !(ifp->flags & IFA_F_OPTIMISTIC))
+			send_na = true;
 		bump_id = ifp->flags & IFA_F_TENTATIVE;
 		ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED);
 		spin_unlock(&ifp->lock);
 		write_unlock_bh(&idev->lock);
 
-		addrconf_dad_completed(ifp, bump_id);
+		addrconf_dad_completed(ifp, bump_id, send_na);
 
 		goto out;
 	}
@@ -4006,7 +4017,8 @@ static bool ipv6_lonely_lladdr(struct inet6_ifaddr *ifp)
 	return true;
 }
 
-static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id)
+static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id,
+				   bool send_na)
 {
 	struct net_device *dev = ifp->idev->dev;
 	struct in6_addr lladdr;
@@ -4038,6 +4050,16 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id)
 	if (send_mld)
 		ipv6_mc_dad_complete(ifp->idev);
 
+	/* send unsolicited NA if enabled */
+	if (send_na &&
+	    (ifp->idev->cnf.ndisc_notify ||
+	     dev_net(dev)->ipv6.devconf_all->ndisc_notify)) {
+		ndisc_send_na(dev, &in6addr_linklocal_allnodes, &ifp->addr,
+			      /*router=*/ !!ifp->idev->cnf.forwarding,
+			      /*solicited=*/ false, /*override=*/ true,
+			      /*inc_opt=*/ true);
+	}
+
 	if (send_rs) {
 		/*
 		 *	If a host as already performed a random delay
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 266a530414d7..2a937c8d19e9 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -558,6 +558,11 @@ static void ndisc_send_unsol_na(struct net_device *dev)
 
 	read_lock_bh(&idev->lock);
 	list_for_each_entry(ifa, &idev->addr_list, if_list) {
+		/* skip tentative addresses until dad completes */
+		if (ifa->flags & IFA_F_TENTATIVE &&
+		    !(ifa->flags & IFA_F_OPTIMISTIC))
+			continue;
+
 		ndisc_send_na(dev, &in6addr_linklocal_allnodes, &ifa->addr,
 			      /*router=*/ !!idev->cnf.forwarding,
 			      /*solicited=*/ false, /*override=*/ true,
-- 
2.14.3


From bcee11cfdc25761afc37df9dc468585193126eb4 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Thu, 1 Feb 2018 12:21:15 +0100
Subject: [PATCH 10/13] rocker: fix possible null pointer dereference in
 rocker_router_fib_event_work

[ Upstream commit a83165f00f16c0e0ef5b7cec3cbd0d4788699265 ]

Currently, rocker user may experience following null pointer
derefence bug:

[    3.062141] BUG: unable to handle kernel NULL pointer dereference at 00000000000000d0
[    3.065163] IP: rocker_router_fib_event_work+0x36/0x110 [rocker]

The problem is uninitialized rocker->wops pointer that is initialized
only with the first initialized port. So move the port initialization
before registering the fib events.

Fixes: 936bd486564a ("rocker: use FIB notifications instead of switchdev calls")
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/rocker/rocker_main.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index fc8f8bdf6579..056cb6093630 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -2902,6 +2902,12 @@ static int rocker_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto err_alloc_ordered_workqueue;
 	}
 
+	err = rocker_probe_ports(rocker);
+	if (err) {
+		dev_err(&pdev->dev, "failed to probe ports\n");
+		goto err_probe_ports;
+	}
+
 	/* Only FIBs pointing to our own netdevs are programmed into
 	 * the device, so no need to pass a callback.
 	 */
@@ -2918,22 +2924,16 @@ static int rocker_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	rocker->hw.id = rocker_read64(rocker, SWITCH_ID);
 
-	err = rocker_probe_ports(rocker);
-	if (err) {
-		dev_err(&pdev->dev, "failed to probe ports\n");
-		goto err_probe_ports;
-	}
-
 	dev_info(&pdev->dev, "Rocker switch with id %*phN\n",
 		 (int)sizeof(rocker->hw.id), &rocker->hw.id);
 
 	return 0;
 
-err_probe_ports:
-	unregister_switchdev_notifier(&rocker_switchdev_notifier);
 err_register_switchdev_notifier:
 	unregister_fib_notifier(&rocker->fib_nb);
 err_register_fib_notifier:
+	rocker_remove_ports(rocker);
+err_probe_ports:
 	destroy_workqueue(rocker->rocker_owq);
 err_alloc_ordered_workqueue:
 	free_irq(rocker_msix_vector(rocker, ROCKER_MSIX_VEC_EVENT), rocker);
@@ -2961,9 +2961,9 @@ static void rocker_remove(struct pci_dev *pdev)
 {
 	struct rocker *rocker = pci_get_drvdata(pdev);
 
-	rocker_remove_ports(rocker);
 	unregister_switchdev_notifier(&rocker_switchdev_notifier);
 	unregister_fib_notifier(&rocker->fib_nb);
+	rocker_remove_ports(rocker);
 	rocker_write32(rocker, CONTROL, ROCKER_CONTROL_RESET);
 	destroy_workqueue(rocker->rocker_owq);
 	free_irq(rocker_msix_vector(rocker, ROCKER_MSIX_VEC_EVENT), rocker);
-- 
2.14.3


From 51a2867dc0e65d051503ca7a0ff829095c0d69f8 Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Wed, 31 Jan 2018 15:43:05 -0500
Subject: [PATCH 11/13] tcp_bbr: fix pacing_gain to always be unity when using
 lt_bw

[ Upstream commit 3aff3b4b986e51bcf4ab249e5d48d39596e0df6a ]

This commit fixes the pacing_gain to remain at BBR_UNIT (1.0) when
using lt_bw and returning from the PROBE_RTT state to PROBE_BW.

Previously, when using lt_bw, upon exiting PROBE_RTT and entering
PROBE_BW the bbr_reset_probe_bw_mode() code could sometimes randomly
end up with a cycle_idx of 0 and hence have bbr_advance_cycle_phase()
set a pacing gain above 1.0. In such cases this would result in a
pacing rate that is 1.25x higher than intended, potentially resulting
in a high loss rate for a little while until we stop using the lt_bw a
bit later.

This commit is a stable candidate for kernels back as far as 4.9.

Fixes: 0f8782ea1497 ("tcp_bbr: add BBR congestion control")
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Reported-by: Beyers Cronje <bcronje@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_bbr.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 8322f26e770e..25c5a0b60cfc 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -481,7 +481,8 @@ static void bbr_advance_cycle_phase(struct sock *sk)
 
 	bbr->cycle_idx = (bbr->cycle_idx + 1) & (CYCLE_LEN - 1);
 	bbr->cycle_mstamp = tp->delivered_mstamp;
-	bbr->pacing_gain = bbr_pacing_gain[bbr->cycle_idx];
+	bbr->pacing_gain = bbr->lt_use_bw ? BBR_UNIT :
+					    bbr_pacing_gain[bbr->cycle_idx];
 }
 
 /* Gain cycling: cycle pacing gain to converge to fair share of available bw. */
@@ -490,8 +491,7 @@ static void bbr_update_cycle_phase(struct sock *sk,
 {
 	struct bbr *bbr = inet_csk_ca(sk);
 
-	if ((bbr->mode == BBR_PROBE_BW) && !bbr->lt_use_bw &&
-	    bbr_is_next_cycle_phase(sk, rs))
+	if (bbr->mode == BBR_PROBE_BW && bbr_is_next_cycle_phase(sk, rs))
 		bbr_advance_cycle_phase(sk);
 }
 
-- 
2.14.3


From dd4e993e5fa80b31da9683e97c3b872a909456a2 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 24 Jan 2018 23:15:27 -0800
Subject: [PATCH 12/13] ipv6: Fix SO_REUSEPORT UDP socket with implicit
 sk_ipv6only

[ Upstream commit 7ece54a60ee2ba7a386308cae73c790bd580589c ]

If a sk_v6_rcv_saddr is !IPV6_ADDR_ANY and !IPV6_ADDR_MAPPED, it
implicitly implies it is an ipv6only socket.  However, in inet6_bind(),
this addr_type checking and setting sk->sk_ipv6only to 1 are only done
after sk->sk_prot->get_port(sk, snum) has been completed successfully.

This inconsistency between sk_v6_rcv_saddr and sk_ipv6only confuses
the 'get_port()'.

In particular, when binding SO_REUSEPORT UDP sockets,
udp_reuseport_add_sock(sk,...) is called.  udp_reuseport_add_sock()
checks "ipv6_only_sock(sk2) == ipv6_only_sock(sk)" before adding sk to
sk2->sk_reuseport_cb.  In this case, ipv6_only_sock(sk2) could be
1 while ipv6_only_sock(sk) is still 0 here.  The end result is,
reuseport_alloc(sk) is called instead of adding sk to the existing
sk2->sk_reuseport_cb.

It can be reproduced by binding two SO_REUSEPORT UDP sockets on an
IPv6 address (!ANY and !MAPPED).  Only one of the socket will
receive packet.

The fix is to set the implicit sk_ipv6only before calling get_port().
The original sk_ipv6only has to be saved such that it can be restored
in case get_port() failed.  The situation is similar to the
inet_reset_saddr(sk) after get_port() has failed.

Thanks to Calvin Owens <calvinowens@fb.com> who created an easy
reproduction which leads to a fix.

Fixes: e32ea7e74727 ("soreuseport: fast reuseport UDP socket selection")
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/af_inet6.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index bcbd5f3bf8bd..9ccbf74deb99 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -284,6 +284,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	struct net *net = sock_net(sk);
 	__be32 v4addr = 0;
 	unsigned short snum;
+	bool saved_ipv6only;
 	int addr_type = 0;
 	int err = 0;
 
@@ -389,19 +390,21 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	if (!(addr_type & IPV6_ADDR_MULTICAST))
 		np->saddr = addr->sin6_addr;
 
+	saved_ipv6only = sk->sk_ipv6only;
+	if (addr_type != IPV6_ADDR_ANY && addr_type != IPV6_ADDR_MAPPED)
+		sk->sk_ipv6only = 1;
+
 	/* Make sure we are allowed to bind here. */
 	if ((snum || !inet->bind_address_no_port) &&
 	    sk->sk_prot->get_port(sk, snum)) {
+		sk->sk_ipv6only = saved_ipv6only;
 		inet_reset_saddr(sk);
 		err = -EADDRINUSE;
 		goto out;
 	}
 
-	if (addr_type != IPV6_ADDR_ANY) {
+	if (addr_type != IPV6_ADDR_ANY)
 		sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
-		if (addr_type != IPV6_ADDR_MAPPED)
-			sk->sk_ipv6only = 1;
-	}
 	if (snum)
 		sk->sk_userlocks |= SOCK_BINDPORT_LOCK;
 	inet->inet_sport = htons(inet->inet_num);
-- 
2.14.3


From 61c981f5b05109ab9f12faf8c18c649aab12fb0f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 2 Feb 2018 10:27:27 -0800
Subject: [PATCH 13/13] soreuseport: fix mem leak in reuseport_add_sock()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 4db428a7c9ab07e08783e0fcdc4ca0f555da0567 ]

reuseport_add_sock() needs to deal with attaching a socket having
its own sk_reuseport_cb, after a prior
setsockopt(SO_ATTACH_REUSEPORT_?BPF)

Without this fix, not only a WARN_ONCE() was issued, but we were also
leaking memory.

Thanks to sysbot and Eric Biggers for providing us nice C repros.

------------[ cut here ]------------
socket already in reuseport group
WARNING: CPU: 0 PID: 3496 at net/core/sock_reuseport.c:119  
reuseport_add_sock+0x742/0x9b0 net/core/sock_reuseport.c:117
Kernel panic - not syncing: panic_on_warn set ...

CPU: 0 PID: 3496 Comm: syzkaller869503 Not tainted 4.15.0-rc6+ #245
Hardware name: Google Google Compute Engine/Google Compute Engine,
BIOS  
Google 01/01/2011
Call Trace:
  __dump_stack lib/dump_stack.c:17 [inline]
  dump_stack+0x194/0x257 lib/dump_stack.c:53
  panic+0x1e4/0x41c kernel/panic.c:183
  __warn+0x1dc/0x200 kernel/panic.c:547
  report_bug+0x211/0x2d0 lib/bug.c:184
  fixup_bug.part.11+0x37/0x80 arch/x86/kernel/traps.c:178
  fixup_bug arch/x86/kernel/traps.c:247 [inline]
  do_error_trap+0x2d7/0x3e0 arch/x86/kernel/traps.c:296
  do_invalid_op+0x1b/0x20 arch/x86/kernel/traps.c:315
  invalid_op+0x22/0x40 arch/x86/entry/entry_64.S:1079

Fixes: ef456144da8e ("soreuseport: define reuseport groups")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot+c0ea2226f77a42936bf7@syzkaller.appspotmail.com
Acked-by: Craig Gallek <kraig@google.com>

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock_reuseport.c | 35 ++++++++++++++++++++---------------
 1 file changed, 20 insertions(+), 15 deletions(-)

diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index 5eeb1d20cc38..676092d7bd81 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -94,6 +94,16 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse)
 	return more_reuse;
 }
 
+static void reuseport_free_rcu(struct rcu_head *head)
+{
+	struct sock_reuseport *reuse;
+
+	reuse = container_of(head, struct sock_reuseport, rcu);
+	if (reuse->prog)
+		bpf_prog_destroy(reuse->prog);
+	kfree(reuse);
+}
+
 /**
  *  reuseport_add_sock - Add a socket to the reuseport group of another.
  *  @sk:  New socket to add to the group.
@@ -102,7 +112,7 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse)
  */
 int reuseport_add_sock(struct sock *sk, struct sock *sk2)
 {
-	struct sock_reuseport *reuse;
+	struct sock_reuseport *old_reuse, *reuse;
 
 	if (!rcu_access_pointer(sk2->sk_reuseport_cb)) {
 		int err = reuseport_alloc(sk2);
@@ -113,10 +123,13 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2)
 
 	spin_lock_bh(&reuseport_lock);
 	reuse = rcu_dereference_protected(sk2->sk_reuseport_cb,
-					  lockdep_is_held(&reuseport_lock)),
-	WARN_ONCE(rcu_dereference_protected(sk->sk_reuseport_cb,
-					    lockdep_is_held(&reuseport_lock)),
-		  "socket already in reuseport group");
+					  lockdep_is_held(&reuseport_lock));
+	old_reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
+					     lockdep_is_held(&reuseport_lock));
+	if (old_reuse && old_reuse->num_socks != 1) {
+		spin_unlock_bh(&reuseport_lock);
+		return -EBUSY;
+	}
 
 	if (reuse->num_socks == reuse->max_socks) {
 		reuse = reuseport_grow(reuse);
@@ -134,19 +147,11 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2)
 
 	spin_unlock_bh(&reuseport_lock);
 
+	if (old_reuse)
+		call_rcu(&old_reuse->rcu, reuseport_free_rcu);
 	return 0;
 }
 
-static void reuseport_free_rcu(struct rcu_head *head)
-{
-	struct sock_reuseport *reuse;
-
-	reuse = container_of(head, struct sock_reuseport, rcu);
-	if (reuse->prog)
-		bpf_prog_destroy(reuse->prog);
-	kfree(reuse);
-}
-
 void reuseport_detach_sock(struct sock *sk)
 {
 	struct sock_reuseport *reuse;
-- 
2.14.3


[-- Attachment #4: net_415.mbox --]
[-- Type: Application/Octet-Stream, Size: 62943 bytes --]

From e2dc2a06d9059af9fe3ea1bda0a996364b6780ed Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Wed, 31 Jan 2018 16:29:30 +0200
Subject: [PATCH 01/18] ip6mr: fix stale iterator

[ Upstream commit 4adfa79fc254efb7b0eb3cd58f62c2c3f805f1ba ]

When we dump the ip6mr mfc entries via proc, we initialize an iterator
with the table to dump but we don't clear the cache pointer which might
be initialized from a prior read on the same descriptor that ended. This
can result in lock imbalance (an unnecessary unlock) leading to other
crashes and hangs. Clear the cache pointer like ipmr does to fix the issue.
Thanks for the reliable reproducer.

Here's syzbot's trace:
 WARNING: bad unlock balance detected!
 4.15.0-rc3+ #128 Not tainted
 syzkaller971460/3195 is trying to release lock (mrt_lock) at:
 [<000000006898068d>] ipmr_mfc_seq_stop+0xe1/0x130 net/ipv6/ip6mr.c:553
 but there are no more locks to release!

 other info that might help us debug this:
 1 lock held by syzkaller971460/3195:
  #0:  (&p->lock){+.+.}, at: [<00000000744a6565>] seq_read+0xd5/0x13d0
 fs/seq_file.c:165

 stack backtrace:
 CPU: 1 PID: 3195 Comm: syzkaller971460 Not tainted 4.15.0-rc3+ #128
 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
 Google 01/01/2011
 Call Trace:
  __dump_stack lib/dump_stack.c:17 [inline]
  dump_stack+0x194/0x257 lib/dump_stack.c:53
  print_unlock_imbalance_bug+0x12f/0x140 kernel/locking/lockdep.c:3561
  __lock_release kernel/locking/lockdep.c:3775 [inline]
  lock_release+0x5f9/0xda0 kernel/locking/lockdep.c:4023
  __raw_read_unlock include/linux/rwlock_api_smp.h:225 [inline]
  _raw_read_unlock+0x1a/0x30 kernel/locking/spinlock.c:255
  ipmr_mfc_seq_stop+0xe1/0x130 net/ipv6/ip6mr.c:553
  traverse+0x3bc/0xa00 fs/seq_file.c:135
  seq_read+0x96a/0x13d0 fs/seq_file.c:189
  proc_reg_read+0xef/0x170 fs/proc/inode.c:217
  do_loop_readv_writev fs/read_write.c:673 [inline]
  do_iter_read+0x3db/0x5b0 fs/read_write.c:897
  compat_readv+0x1bf/0x270 fs/read_write.c:1140
  do_compat_preadv64+0xdc/0x100 fs/read_write.c:1189
  C_SYSC_preadv fs/read_write.c:1209 [inline]
  compat_SyS_preadv+0x3b/0x50 fs/read_write.c:1203
  do_syscall_32_irqs_on arch/x86/entry/common.c:327 [inline]
  do_fast_syscall_32+0x3ee/0xf9d arch/x86/entry/common.c:389
  entry_SYSENTER_compat+0x51/0x60 arch/x86/entry/entry_64_compat.S:125
 RIP: 0023:0xf7f73c79
 RSP: 002b:00000000e574a15c EFLAGS: 00000292 ORIG_RAX: 000000000000014d
 RAX: ffffffffffffffda RBX: 000000000000000f RCX: 0000000020a3afb0
 RDX: 0000000000000001 RSI: 0000000000000067 RDI: 0000000000000000
 RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000
 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
 BUG: sleeping function called from invalid context at lib/usercopy.c:25
 in_atomic(): 1, irqs_disabled(): 0, pid: 3195, name: syzkaller971460
 INFO: lockdep is turned off.
 CPU: 1 PID: 3195 Comm: syzkaller971460 Not tainted 4.15.0-rc3+ #128
 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
 Google 01/01/2011
 Call Trace:
  __dump_stack lib/dump_stack.c:17 [inline]
  dump_stack+0x194/0x257 lib/dump_stack.c:53
  ___might_sleep+0x2b2/0x470 kernel/sched/core.c:6060
  __might_sleep+0x95/0x190 kernel/sched/core.c:6013
  __might_fault+0xab/0x1d0 mm/memory.c:4525
  _copy_to_user+0x2c/0xc0 lib/usercopy.c:25
  copy_to_user include/linux/uaccess.h:155 [inline]
  seq_read+0xcb4/0x13d0 fs/seq_file.c:279
  proc_reg_read+0xef/0x170 fs/proc/inode.c:217
  do_loop_readv_writev fs/read_write.c:673 [inline]
  do_iter_read+0x3db/0x5b0 fs/read_write.c:897
  compat_readv+0x1bf/0x270 fs/read_write.c:1140
  do_compat_preadv64+0xdc/0x100 fs/read_write.c:1189
  C_SYSC_preadv fs/read_write.c:1209 [inline]
  compat_SyS_preadv+0x3b/0x50 fs/read_write.c:1203
  do_syscall_32_irqs_on arch/x86/entry/common.c:327 [inline]
  do_fast_syscall_32+0x3ee/0xf9d arch/x86/entry/common.c:389
  entry_SYSENTER_compat+0x51/0x60 arch/x86/entry/entry_64_compat.S:125
 RIP: 0023:0xf7f73c79
 RSP: 002b:00000000e574a15c EFLAGS: 00000292 ORIG_RAX: 000000000000014d
 RAX: ffffffffffffffda RBX: 000000000000000f RCX: 0000000020a3afb0
 RDX: 0000000000000001 RSI: 0000000000000067 RDI: 0000000000000000
 RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000
 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
 WARNING: CPU: 1 PID: 3195 at lib/usercopy.c:26 _copy_to_user+0xb5/0xc0
 lib/usercopy.c:26

Reported-by: syzbot <bot+eceb3204562c41a438fa1f2335e0fe4f6886d669@syzkaller.appspotmail.com>
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6mr.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index a2e1a864eb46..4fc566ec7e79 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -495,6 +495,7 @@ static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos)
 		return ERR_PTR(-ENOENT);
 
 	it->mrt = mrt;
+	it->cache = NULL;
 	return *pos ? ipmr_mfc_seq_idx(net, seq->private, *pos - 1)
 		: SEQ_START_TOKEN;
 }
-- 
2.14.3


From a0a7dc8d04dd1df7071c59d1a3d8694f702b3d3e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 1 Feb 2018 10:26:57 -0800
Subject: [PATCH 02/18] net: igmp: add a missing rcu locking section

[ Upstream commit e7aadb27a5415e8125834b84a74477bfbee4eff5 ]

Newly added igmpv3_get_srcaddr() needs to be called under rcu lock.

Timer callbacks do not ensure this locking.

=============================
WARNING: suspicious RCU usage
4.15.0+ #200 Not tainted
-----------------------------
./include/linux/inetdevice.h:216 suspicious rcu_dereference_check() usage!

other info that might help us debug this:

rcu_scheduler_active = 2, debug_locks = 1
3 locks held by syzkaller616973/4074:
 #0:  (&mm->mmap_sem){++++}, at: [<00000000bfce669e>] __do_page_fault+0x32d/0xc90 arch/x86/mm/fault.c:1355
 #1:  ((&im->timer)){+.-.}, at: [<00000000619d2f71>] lockdep_copy_map include/linux/lockdep.h:178 [inline]
 #1:  ((&im->timer)){+.-.}, at: [<00000000619d2f71>] call_timer_fn+0x1c6/0x820 kernel/time/timer.c:1316
 #2:  (&(&im->lock)->rlock){+.-.}, at: [<000000005f833c5c>] spin_lock_bh include/linux/spinlock.h:315 [inline]
 #2:  (&(&im->lock)->rlock){+.-.}, at: [<000000005f833c5c>] igmpv3_send_report+0x98/0x5b0 net/ipv4/igmp.c:600

stack backtrace:
CPU: 0 PID: 4074 Comm: syzkaller616973 Not tainted 4.15.0+ #200
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x194/0x257 lib/dump_stack.c:53
 lockdep_rcu_suspicious+0x123/0x170 kernel/locking/lockdep.c:4592
 __in_dev_get_rcu include/linux/inetdevice.h:216 [inline]
 igmpv3_get_srcaddr net/ipv4/igmp.c:329 [inline]
 igmpv3_newpack+0xeef/0x12e0 net/ipv4/igmp.c:389
 add_grhead.isra.27+0x235/0x300 net/ipv4/igmp.c:432
 add_grec+0xbd3/0x1170 net/ipv4/igmp.c:565
 igmpv3_send_report+0xd5/0x5b0 net/ipv4/igmp.c:605
 igmp_send_report+0xc43/0x1050 net/ipv4/igmp.c:722
 igmp_timer_expire+0x322/0x5c0 net/ipv4/igmp.c:831
 call_timer_fn+0x228/0x820 kernel/time/timer.c:1326
 expire_timers kernel/time/timer.c:1363 [inline]
 __run_timers+0x7ee/0xb70 kernel/time/timer.c:1666
 run_timer_softirq+0x4c/0x70 kernel/time/timer.c:1692
 __do_softirq+0x2d7/0xb85 kernel/softirq.c:285
 invoke_softirq kernel/softirq.c:365 [inline]
 irq_exit+0x1cc/0x200 kernel/softirq.c:405
 exiting_irq arch/x86/include/asm/apic.h:541 [inline]
 smp_apic_timer_interrupt+0x16b/0x700 arch/x86/kernel/apic/apic.c:1052
 apic_timer_interrupt+0xa9/0xb0 arch/x86/entry/entry_64.S:938

Fixes: a46182b00290 ("net: igmp: Use correct source address on IGMPv3 reports")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/igmp.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 2d49717a7421..f0b1fc35dde1 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -386,7 +386,11 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu)
 	pip->frag_off = htons(IP_DF);
 	pip->ttl      = 1;
 	pip->daddr    = fl4.daddr;
+
+	rcu_read_lock();
 	pip->saddr    = igmpv3_get_srcaddr(dev, &fl4);
+	rcu_read_unlock();
+
 	pip->protocol = IPPROTO_IGMP;
 	pip->tot_len  = 0;	/* filled in later */
 	ip_select_ident(net, skb, NULL);
-- 
2.14.3


From 3cc6eab104cc6454ed483d4c3f2e4d4c81162d02 Mon Sep 17 00:00:00 2001
From: Junxiao Bi <junxiao.bi@oracle.com>
Date: Mon, 29 Jan 2018 17:53:42 +0800
Subject: [PATCH 03/18] qlcnic: fix deadlock bug

[ Upstream commit 233ac3891607f501f08879134d623b303838f478 ]

The following soft lockup was caught. This is a deadlock caused by
recusive locking.

Process kworker/u40:1:28016 was holding spin lock "mbx->queue_lock" in
qlcnic_83xx_mailbox_worker(), while a softirq came in and ask the same spin
lock in qlcnic_83xx_enqueue_mbx_cmd(). This lock should be hold by disable
bh..

[161846.962125] NMI watchdog: BUG: soft lockup - CPU#1 stuck for 22s! [kworker/u40:1:28016]
[161846.962367] Modules linked in: tun ocfs2 xen_netback xen_blkback xen_gntalloc xen_gntdev xen_evtchn xenfs xen_privcmd autofs4 ocfs2_dlmfs ocfs2_stack_o2cb ocfs2_dlm ocfs2_nodemanager ocfs2_stackglue configfs bnx2fc fcoe libfcoe libfc sunrpc 8021q mrp garp bridge stp llc bonding dm_round_robin dm_multipath iTCO_wdt iTCO_vendor_support pcspkr sb_edac edac_core i2c_i801 shpchp lpc_ich mfd_core ioatdma ipmi_devintf ipmi_si ipmi_msghandler sg ext4 jbd2 mbcache2 sr_mod cdrom sd_mod igb i2c_algo_bit i2c_core ahci libahci megaraid_sas ixgbe dca ptp pps_core vxlan udp_tunnel ip6_udp_tunnel qla2xxx scsi_transport_fc qlcnic crc32c_intel be2iscsi bnx2i cnic uio cxgb4i cxgb4 cxgb3i libcxgbi ipv6 cxgb3 mdio libiscsi_tcp qla4xxx iscsi_boot_sysfs libiscsi scsi_transport_iscsi dm_mirror dm_region_hash dm_log dm_mod
[161846.962454]
[161846.962460] CPU: 1 PID: 28016 Comm: kworker/u40:1 Not tainted 4.1.12-94.5.9.el6uek.x86_64 #2
[161846.962463] Hardware name: Oracle Corporation SUN SERVER X4-2L      /ASSY,MB,X4-2L         , BIOS 26050100 09/19/2017
[161846.962489] Workqueue: qlcnic_mailbox qlcnic_83xx_mailbox_worker [qlcnic]
[161846.962493] task: ffff8801f2e34600 ti: ffff88004ca5c000 task.ti: ffff88004ca5c000
[161846.962496] RIP: e030:[<ffffffff810013aa>]  [<ffffffff810013aa>] xen_hypercall_sched_op+0xa/0x20
[161846.962506] RSP: e02b:ffff880202e43388  EFLAGS: 00000206
[161846.962509] RAX: 0000000000000000 RBX: ffff8801f6996b70 RCX: ffffffff810013aa
[161846.962511] RDX: ffff880202e433cc RSI: ffff880202e433b0 RDI: 0000000000000003
[161846.962513] RBP: ffff880202e433d0 R08: 0000000000000000 R09: ffff8801fe893200
[161846.962516] R10: ffff8801fe400538 R11: 0000000000000206 R12: ffff880202e4b000
[161846.962518] R13: 0000000000000050 R14: 0000000000000001 R15: 000000000000020d
[161846.962528] FS:  0000000000000000(0000) GS:ffff880202e40000(0000) knlGS:ffff880202e40000
[161846.962531] CS:  e033 DS: 0000 ES: 0000 CR0: 0000000080050033
[161846.962533] CR2: 0000000002612640 CR3: 00000001bb796000 CR4: 0000000000042660
[161846.962536] Stack:
[161846.962538]  ffff880202e43608 0000000000000000 ffffffff813f0442 ffff880202e433b0
[161846.962543]  0000000000000000 ffff880202e433cc ffffffff00000001 0000000000000000
[161846.962547]  00000009813f03d6 ffff880202e433e0 ffffffff813f0460 ffff880202e43440
[161846.962552] Call Trace:
[161846.962555]  <IRQ>
[161846.962565]  [<ffffffff813f0442>] ? xen_poll_irq_timeout+0x42/0x50
[161846.962570]  [<ffffffff813f0460>] xen_poll_irq+0x10/0x20
[161846.962578]  [<ffffffff81014222>] xen_lock_spinning+0xe2/0x110
[161846.962583]  [<ffffffff81013f01>] __raw_callee_save_xen_lock_spinning+0x11/0x20
[161846.962592]  [<ffffffff816e5c57>] ? _raw_spin_lock+0x57/0x80
[161846.962609]  [<ffffffffa028acfc>] qlcnic_83xx_enqueue_mbx_cmd+0x7c/0xe0 [qlcnic]
[161846.962623]  [<ffffffffa028e008>] qlcnic_83xx_issue_cmd+0x58/0x210 [qlcnic]
[161846.962636]  [<ffffffffa028caf2>] qlcnic_83xx_sre_macaddr_change+0x162/0x1d0 [qlcnic]
[161846.962649]  [<ffffffffa028cb8b>] qlcnic_83xx_change_l2_filter+0x2b/0x30 [qlcnic]
[161846.962657]  [<ffffffff8160248b>] ? __skb_flow_dissect+0x18b/0x650
[161846.962670]  [<ffffffffa02856e5>] qlcnic_send_filter+0x205/0x250 [qlcnic]
[161846.962682]  [<ffffffffa0285c77>] qlcnic_xmit_frame+0x547/0x7b0 [qlcnic]
[161846.962691]  [<ffffffff8160ac22>] xmit_one+0x82/0x1a0
[161846.962696]  [<ffffffff8160ad90>] dev_hard_start_xmit+0x50/0xa0
[161846.962701]  [<ffffffff81630112>] sch_direct_xmit+0x112/0x220
[161846.962706]  [<ffffffff8160b80f>] __dev_queue_xmit+0x1df/0x5e0
[161846.962710]  [<ffffffff8160bc33>] dev_queue_xmit_sk+0x13/0x20
[161846.962721]  [<ffffffffa0575bd5>] bond_dev_queue_xmit+0x35/0x80 [bonding]
[161846.962729]  [<ffffffffa05769fb>] __bond_start_xmit+0x1cb/0x210 [bonding]
[161846.962736]  [<ffffffffa0576a71>] bond_start_xmit+0x31/0x60 [bonding]
[161846.962740]  [<ffffffff8160ac22>] xmit_one+0x82/0x1a0
[161846.962745]  [<ffffffff8160ad90>] dev_hard_start_xmit+0x50/0xa0
[161846.962749]  [<ffffffff8160bb1e>] __dev_queue_xmit+0x4ee/0x5e0
[161846.962754]  [<ffffffff8160bc33>] dev_queue_xmit_sk+0x13/0x20
[161846.962760]  [<ffffffffa05cfa72>] vlan_dev_hard_start_xmit+0xb2/0x150 [8021q]
[161846.962764]  [<ffffffff8160ac22>] xmit_one+0x82/0x1a0
[161846.962769]  [<ffffffff8160ad90>] dev_hard_start_xmit+0x50/0xa0
[161846.962773]  [<ffffffff8160bb1e>] __dev_queue_xmit+0x4ee/0x5e0
[161846.962777]  [<ffffffff8160bc33>] dev_queue_xmit_sk+0x13/0x20
[161846.962789]  [<ffffffffa05adf74>] br_dev_queue_push_xmit+0x54/0xa0 [bridge]
[161846.962797]  [<ffffffffa05ae4ff>] br_forward_finish+0x2f/0x90 [bridge]
[161846.962807]  [<ffffffff810b0dad>] ? ttwu_do_wakeup+0x1d/0x100
[161846.962811]  [<ffffffff815f929b>] ? __alloc_skb+0x8b/0x1f0
[161846.962818]  [<ffffffffa05ae04d>] __br_forward+0x8d/0x120 [bridge]
[161846.962822]  [<ffffffff815f613b>] ? __kmalloc_reserve+0x3b/0xa0
[161846.962829]  [<ffffffff810be55e>] ? update_rq_runnable_avg+0xee/0x230
[161846.962836]  [<ffffffffa05ae176>] br_forward+0x96/0xb0 [bridge]
[161846.962845]  [<ffffffffa05af85e>] br_handle_frame_finish+0x1ae/0x420 [bridge]
[161846.962853]  [<ffffffffa05afc4f>] br_handle_frame+0x17f/0x260 [bridge]
[161846.962862]  [<ffffffffa05afad0>] ? br_handle_frame_finish+0x420/0x420 [bridge]
[161846.962867]  [<ffffffff8160d057>] __netif_receive_skb_core+0x1f7/0x870
[161846.962872]  [<ffffffff8160d6f2>] __netif_receive_skb+0x22/0x70
[161846.962877]  [<ffffffff8160d913>] netif_receive_skb_internal+0x23/0x90
[161846.962884]  [<ffffffffa07512ea>] ? xenvif_idx_release+0xea/0x100 [xen_netback]
[161846.962889]  [<ffffffff816e5a10>] ? _raw_spin_unlock_irqrestore+0x20/0x50
[161846.962893]  [<ffffffff8160e624>] netif_receive_skb_sk+0x24/0x90
[161846.962899]  [<ffffffffa075269a>] xenvif_tx_submit+0x2ca/0x3f0 [xen_netback]
[161846.962906]  [<ffffffffa0753f0c>] xenvif_tx_action+0x9c/0xd0 [xen_netback]
[161846.962915]  [<ffffffffa07567f5>] xenvif_poll+0x35/0x70 [xen_netback]
[161846.962920]  [<ffffffff8160e01b>] napi_poll+0xcb/0x1e0
[161846.962925]  [<ffffffff8160e1c0>] net_rx_action+0x90/0x1c0
[161846.962931]  [<ffffffff8108aaba>] __do_softirq+0x10a/0x350
[161846.962938]  [<ffffffff8108ae75>] irq_exit+0x125/0x130
[161846.962943]  [<ffffffff813f03a9>] xen_evtchn_do_upcall+0x39/0x50
[161846.962950]  [<ffffffff816e7ffe>] xen_do_hypervisor_callback+0x1e/0x40
[161846.962952]  <EOI>
[161846.962959]  [<ffffffff816e5c4a>] ? _raw_spin_lock+0x4a/0x80
[161846.962964]  [<ffffffff816e5b1e>] ? _raw_spin_lock_irqsave+0x1e/0xa0
[161846.962978]  [<ffffffffa028e279>] ? qlcnic_83xx_mailbox_worker+0xb9/0x2a0 [qlcnic]
[161846.962991]  [<ffffffff810a14e1>] ? process_one_work+0x151/0x4b0
[161846.962995]  [<ffffffff8100c3f2>] ? check_events+0x12/0x20
[161846.963001]  [<ffffffff810a1960>] ? worker_thread+0x120/0x480
[161846.963005]  [<ffffffff816e187b>] ? __schedule+0x30b/0x890
[161846.963010]  [<ffffffff810a1840>] ? process_one_work+0x4b0/0x4b0
[161846.963015]  [<ffffffff810a1840>] ? process_one_work+0x4b0/0x4b0
[161846.963021]  [<ffffffff810a6b3e>] ? kthread+0xce/0xf0
[161846.963025]  [<ffffffff810a6a70>] ? kthread_freezable_should_stop+0x70/0x70
[161846.963031]  [<ffffffff816e6522>] ? ret_from_fork+0x42/0x70
[161846.963035]  [<ffffffff810a6a70>] ? kthread_freezable_should_stop+0x70/0x70
[161846.963037] Code: cc 51 41 53 b8 1c 00 00 00 0f 05 41 5b 59 c3 cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc 51 41 53 b8 1d 00 00 00 0f 05 <41> 5b 59 c3 cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc

Signed-off-by: Junxiao Bi <junxiao.bi@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
index f7080d0ab874..46b0372dd032 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
@@ -3891,7 +3891,7 @@ static void qlcnic_83xx_flush_mbx_queue(struct qlcnic_adapter *adapter)
 	struct list_head *head = &mbx->cmd_q;
 	struct qlcnic_cmd_args *cmd = NULL;
 
-	spin_lock(&mbx->queue_lock);
+	spin_lock_bh(&mbx->queue_lock);
 
 	while (!list_empty(head)) {
 		cmd = list_entry(head->next, struct qlcnic_cmd_args, list);
@@ -3902,7 +3902,7 @@ static void qlcnic_83xx_flush_mbx_queue(struct qlcnic_adapter *adapter)
 		qlcnic_83xx_notify_cmd_completion(adapter, cmd);
 	}
 
-	spin_unlock(&mbx->queue_lock);
+	spin_unlock_bh(&mbx->queue_lock);
 }
 
 static int qlcnic_83xx_check_mbx_status(struct qlcnic_adapter *adapter)
@@ -3938,12 +3938,12 @@ static void qlcnic_83xx_dequeue_mbx_cmd(struct qlcnic_adapter *adapter,
 {
 	struct qlcnic_mailbox *mbx = adapter->ahw->mailbox;
 
-	spin_lock(&mbx->queue_lock);
+	spin_lock_bh(&mbx->queue_lock);
 
 	list_del(&cmd->list);
 	mbx->num_cmds--;
 
-	spin_unlock(&mbx->queue_lock);
+	spin_unlock_bh(&mbx->queue_lock);
 
 	qlcnic_83xx_notify_cmd_completion(adapter, cmd);
 }
@@ -4008,7 +4008,7 @@ static int qlcnic_83xx_enqueue_mbx_cmd(struct qlcnic_adapter *adapter,
 		init_completion(&cmd->completion);
 		cmd->rsp_opcode = QLC_83XX_MBX_RESPONSE_UNKNOWN;
 
-		spin_lock(&mbx->queue_lock);
+		spin_lock_bh(&mbx->queue_lock);
 
 		list_add_tail(&cmd->list, &mbx->cmd_q);
 		mbx->num_cmds++;
@@ -4016,7 +4016,7 @@ static int qlcnic_83xx_enqueue_mbx_cmd(struct qlcnic_adapter *adapter,
 		*timeout = cmd->total_cmds * QLC_83XX_MBX_TIMEOUT;
 		queue_work(mbx->work_q, &mbx->work);
 
-		spin_unlock(&mbx->queue_lock);
+		spin_unlock_bh(&mbx->queue_lock);
 
 		return 0;
 	}
@@ -4112,15 +4112,15 @@ static void qlcnic_83xx_mailbox_worker(struct work_struct *work)
 		mbx->rsp_status = QLC_83XX_MBX_RESPONSE_WAIT;
 		spin_unlock_irqrestore(&mbx->aen_lock, flags);
 
-		spin_lock(&mbx->queue_lock);
+		spin_lock_bh(&mbx->queue_lock);
 
 		if (list_empty(head)) {
-			spin_unlock(&mbx->queue_lock);
+			spin_unlock_bh(&mbx->queue_lock);
 			return;
 		}
 		cmd = list_entry(head->next, struct qlcnic_cmd_args, list);
 
-		spin_unlock(&mbx->queue_lock);
+		spin_unlock_bh(&mbx->queue_lock);
 
 		mbx_ops->encode_cmd(adapter, cmd);
 		mbx_ops->nofity_fw(adapter, QLC_83XX_MBX_REQUEST);
-- 
2.14.3


From d3ef8694cd16b5da1a18d494c2e060db3d3a14b3 Mon Sep 17 00:00:00 2001
From: Kristian Evensen <kristian.evensen@gmail.com>
Date: Tue, 30 Jan 2018 14:12:55 +0100
Subject: [PATCH 04/18] qmi_wwan: Add support for Quectel EP06
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit c0b91a56a2e57a5a370655b25d677ae0ebf8a2d0 ]

The Quectel EP06 is a Cat. 6 LTE modem. It uses the same interface as
the EC20/EC25 for QMI, and requires the same "set DTR"-quirk to work.

Signed-off-by: Kristian Evensen <kristian.evensen@gmail.com>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 728819feab44..e7114c34fe4b 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1245,6 +1245,7 @@ static const struct usb_device_id products[] = {
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0125, 4)},	/* Quectel EC25, EC20 R2.0  Mini PCIe */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0121, 4)},	/* Quectel EC21 Mini PCIe */
 	{QMI_FIXED_INTF(0x2c7c, 0x0296, 4)},	/* Quectel BG96 */
+	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0306, 4)},	/* Quectel EP06 Mini PCIe */
 
 	/* 4. Gobi 1000 devices */
 	{QMI_GOBI1K_DEVICE(0x05c6, 0x9212)},	/* Acer Gobi Modem Device */
-- 
2.14.3


From abbf11503cc7d981fc0b2a4e5454e9312699ba15 Mon Sep 17 00:00:00 2001
From: Chunhao Lin <hau@realtek.com>
Date: Wed, 31 Jan 2018 01:32:36 +0800
Subject: [PATCH 05/18] r8169: fix RTL8168EP take too long to complete driver
 initialization.

[ Upstream commit 086ca23d03c0d2f4088f472386778d293e15c5f6 ]

Driver check the wrong register bit in rtl_ocp_tx_cond() that keep driver
waiting until timeout.

Fix this by waiting for the right register bit.

Signed-off-by: Chunhao Lin <hau@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 734286ebe5ef..dd713dff8d22 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -1395,7 +1395,7 @@ DECLARE_RTL_COND(rtl_ocp_tx_cond)
 {
 	void __iomem *ioaddr = tp->mmio_addr;
 
-	return RTL_R8(IBISR0) & 0x02;
+	return RTL_R8(IBISR0) & 0x20;
 }
 
 static void rtl8168ep_stop_cmac(struct rtl8169_private *tp)
@@ -1403,7 +1403,7 @@ static void rtl8168ep_stop_cmac(struct rtl8169_private *tp)
 	void __iomem *ioaddr = tp->mmio_addr;
 
 	RTL_W8(IBCR2, RTL_R8(IBCR2) & ~0x01);
-	rtl_msleep_loop_wait_low(tp, &rtl_ocp_tx_cond, 50, 2000);
+	rtl_msleep_loop_wait_high(tp, &rtl_ocp_tx_cond, 50, 2000);
 	RTL_W8(IBISR0, RTL_R8(IBISR0) | 0x20);
 	RTL_W8(IBCR0, RTL_R8(IBCR0) & ~0x01);
 }
-- 
2.14.3


From cfd70baf0743783e1e8aad6c78d324e00b5c9537 Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Fri, 26 Jan 2018 16:40:41 +0800
Subject: [PATCH 06/18] tcp: release sk_frag.page in tcp_disconnect

[ Upstream commit 9b42d55a66d388e4dd5550107df051a9637564fc ]

socket can be disconnected and gets transformed back to a listening
socket, if sk_frag.page is not released, which will be cloned into
a new socket by sk_clone_lock, but the reference count of this page
is increased, lead to a use after free or double free issue

Signed-off-by: Li RongQing <lirongqing@baidu.com>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 8e053ad7cae2..c821f5d68720 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2434,6 +2434,12 @@ int tcp_disconnect(struct sock *sk, int flags)
 
 	WARN_ON(inet->inet_num && !icsk->icsk_bind_hash);
 
+	if (sk->sk_frag.page) {
+		put_page(sk->sk_frag.page);
+		sk->sk_frag.page = NULL;
+		sk->sk_frag.offset = 0;
+	}
+
 	sk->sk_error_report(sk);
 	return err;
 }
-- 
2.14.3


From 0d1f98ff465f8cd3f7c40635adb42c6a14d62be9 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Thu, 25 Jan 2018 22:03:52 +0800
Subject: [PATCH 07/18] vhost_net: stop device during reset owner

[ Upstream commit 4cd879515d686849eec5f718aeac62a70b067d82 ]

We don't stop device before reset owner, this means we could try to
serve any virtqueue kick before reset dev->worker. This will result a
warn since the work was pending at llist during owner resetting. Fix
this by stopping device during owner reset.

Reported-by: syzbot+eb17c6162478cc50632c@syzkaller.appspotmail.com
Fixes: 3a4d5c94e9593 ("vhost_net: a kernel-level virtio server")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/net.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index c7bdeb655646..5636c7ca8eba 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -1208,6 +1208,7 @@ static long vhost_net_reset_owner(struct vhost_net *n)
 	}
 	vhost_net_stop(n, &tx_sock, &rx_sock);
 	vhost_net_flush(n);
+	vhost_dev_stop(&n->dev);
 	vhost_dev_reset_owner(&n->dev, umem);
 	vhost_net_vq_reset(n);
 done:
-- 
2.14.3


From 4fc600aac4749d327fd21c9964f466b0e9762d83 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 26 Jan 2018 16:10:43 -0800
Subject: [PATCH 08/18] ipv6: addrconf: break critical section in
 addrconf_verify_rtnl()

[ Upstream commit e64e469b9a2c22d41b3dd7172118760cec22d473 ]

Heiner reported a lockdep splat [1]

This is caused by attempting GFP_KERNEL allocation while RCU lock is
held and BH blocked.

We believe that addrconf_verify_rtnl() could run for a long period,
so instead of using GFP_ATOMIC here as Ido suggested, we should break
the critical section and restart it after the allocation.

[1]
[86220.125562] =============================
[86220.125586] WARNING: suspicious RCU usage
[86220.125612] 4.15.0-rc7-next-20180110+ #7 Not tainted
[86220.125641] -----------------------------
[86220.125666] kernel/sched/core.c:6026 Illegal context switch in RCU-bh read-side critical section!
[86220.125711]
               other info that might help us debug this:

[86220.125755]
               rcu_scheduler_active = 2, debug_locks = 1
[86220.125792] 4 locks held by kworker/0:2/1003:
[86220.125817]  #0:  ((wq_completion)"%s"("ipv6_addrconf")){+.+.}, at: [<00000000da8e9b73>] process_one_work+0x1de/0x680
[86220.125895]  #1:  ((addr_chk_work).work){+.+.}, at: [<00000000da8e9b73>] process_one_work+0x1de/0x680
[86220.125959]  #2:  (rtnl_mutex){+.+.}, at: [<00000000b06d9510>] rtnl_lock+0x12/0x20
[86220.126017]  #3:  (rcu_read_lock_bh){....}, at: [<00000000aef52299>] addrconf_verify_rtnl+0x1e/0x510 [ipv6]
[86220.126111]
               stack backtrace:
[86220.126142] CPU: 0 PID: 1003 Comm: kworker/0:2 Not tainted 4.15.0-rc7-next-20180110+ #7
[86220.126185] Hardware name: ZOTAC ZBOX-CI321NANO/ZBOX-CI321NANO, BIOS B246P105 06/01/2015
[86220.126250] Workqueue: ipv6_addrconf addrconf_verify_work [ipv6]
[86220.126288] Call Trace:
[86220.126312]  dump_stack+0x70/0x9e
[86220.126337]  lockdep_rcu_suspicious+0xce/0xf0
[86220.126365]  ___might_sleep+0x1d3/0x240
[86220.126390]  __might_sleep+0x45/0x80
[86220.126416]  kmem_cache_alloc_trace+0x53/0x250
[86220.126458]  ? ipv6_add_addr+0xfe/0x6e0 [ipv6]
[86220.126498]  ipv6_add_addr+0xfe/0x6e0 [ipv6]
[86220.126538]  ipv6_create_tempaddr+0x24d/0x430 [ipv6]
[86220.126580]  ? ipv6_create_tempaddr+0x24d/0x430 [ipv6]
[86220.126623]  addrconf_verify_rtnl+0x339/0x510 [ipv6]
[86220.126664]  ? addrconf_verify_rtnl+0x339/0x510 [ipv6]
[86220.126708]  addrconf_verify_work+0xe/0x20 [ipv6]
[86220.126738]  process_one_work+0x258/0x680
[86220.126765]  worker_thread+0x35/0x3f0
[86220.126790]  kthread+0x124/0x140
[86220.126813]  ? process_one_work+0x680/0x680
[86220.126839]  ? kthread_create_worker_on_cpu+0x40/0x40
[86220.126869]  ? umh_complete+0x40/0x40
[86220.126893]  ? call_usermodehelper_exec_async+0x12a/0x160
[86220.126926]  ret_from_fork+0x4b/0x60
[86220.126999] BUG: sleeping function called from invalid context at mm/slab.h:420
[86220.127041] in_atomic(): 1, irqs_disabled(): 0, pid: 1003, name: kworker/0:2
[86220.127082] 4 locks held by kworker/0:2/1003:
[86220.127107]  #0:  ((wq_completion)"%s"("ipv6_addrconf")){+.+.}, at: [<00000000da8e9b73>] process_one_work+0x1de/0x680
[86220.127179]  #1:  ((addr_chk_work).work){+.+.}, at: [<00000000da8e9b73>] process_one_work+0x1de/0x680
[86220.127242]  #2:  (rtnl_mutex){+.+.}, at: [<00000000b06d9510>] rtnl_lock+0x12/0x20
[86220.127300]  #3:  (rcu_read_lock_bh){....}, at: [<00000000aef52299>] addrconf_verify_rtnl+0x1e/0x510 [ipv6]
[86220.127414] CPU: 0 PID: 1003 Comm: kworker/0:2 Not tainted 4.15.0-rc7-next-20180110+ #7
[86220.127463] Hardware name: ZOTAC ZBOX-CI321NANO/ZBOX-CI321NANO, BIOS B246P105 06/01/2015
[86220.127528] Workqueue: ipv6_addrconf addrconf_verify_work [ipv6]
[86220.127568] Call Trace:
[86220.127591]  dump_stack+0x70/0x9e
[86220.127616]  ___might_sleep+0x14d/0x240
[86220.127644]  __might_sleep+0x45/0x80
[86220.127672]  kmem_cache_alloc_trace+0x53/0x250
[86220.127717]  ? ipv6_add_addr+0xfe/0x6e0 [ipv6]
[86220.127762]  ipv6_add_addr+0xfe/0x6e0 [ipv6]
[86220.127807]  ipv6_create_tempaddr+0x24d/0x430 [ipv6]
[86220.127854]  ? ipv6_create_tempaddr+0x24d/0x430 [ipv6]
[86220.127903]  addrconf_verify_rtnl+0x339/0x510 [ipv6]
[86220.127950]  ? addrconf_verify_rtnl+0x339/0x510 [ipv6]
[86220.127998]  addrconf_verify_work+0xe/0x20 [ipv6]
[86220.128032]  process_one_work+0x258/0x680
[86220.128063]  worker_thread+0x35/0x3f0
[86220.128091]  kthread+0x124/0x140
[86220.128117]  ? process_one_work+0x680/0x680
[86220.128146]  ? kthread_create_worker_on_cpu+0x40/0x40
[86220.128180]  ? umh_complete+0x40/0x40
[86220.128207]  ? call_usermodehelper_exec_async+0x12a/0x160
[86220.128243]  ret_from_fork+0x4b/0x60

Fixes: f3d9832e56c4 ("ipv6: addrconf: cleanup locking in ipv6_add_addr")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index f49bd7897e95..10facd174210 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -4352,9 +4352,11 @@ static void addrconf_verify_rtnl(void)
 						spin_lock(&ifpub->lock);
 						ifpub->regen_count = 0;
 						spin_unlock(&ifpub->lock);
+						rcu_read_unlock_bh();
 						ipv6_create_tempaddr(ifpub, ifp, true);
 						in6_ifa_put(ifpub);
 						in6_ifa_put(ifp);
+						rcu_read_lock_bh();
 						goto restart;
 					}
 				} else if (time_before(ifp->tstamp + ifp->prefered_lft * HZ - regen_advance * HZ, next))
-- 
2.14.3


From 8bc95452564e1c266806435383d9bb6f6af4ef6e Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Fri, 26 Jan 2018 11:40:17 -0800
Subject: [PATCH 09/18] ipv6: change route cache aging logic

[ Upstream commit 31afeb425f7fad8bcf9561aeb0b8405479f97a98 ]

In current route cache aging logic, if a route has both RTF_EXPIRE and
RTF_GATEWAY set, the route will only be removed if the neighbor cache
has no NTF_ROUTER flag. Otherwise, even if the route has expired, it
won't get deleted.
Fix this logic to always check if the route has expired first and then
do the gateway neighbor cache check if previous check decide to not
remove the exception entry.

Fixes: 1859bac04fb6 ("ipv6: remove from fib tree aged out RTF_CACHE dst")
Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 0458b761f3c5..a560fb1d0230 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1586,12 +1586,19 @@ static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket,
 	 * EXPIRES exceptions - e.g. pmtu-generated ones are pruned when
 	 * expired, independently from their aging, as per RFC 8201 section 4
 	 */
-	if (!(rt->rt6i_flags & RTF_EXPIRES) &&
-	    time_after_eq(now, rt->dst.lastuse + gc_args->timeout)) {
-		RT6_TRACE("aging clone %p\n", rt);
+	if (!(rt->rt6i_flags & RTF_EXPIRES)) {
+		if (time_after_eq(now, rt->dst.lastuse + gc_args->timeout)) {
+			RT6_TRACE("aging clone %p\n", rt);
+			rt6_remove_exception(bucket, rt6_ex);
+			return;
+		}
+	} else if (time_after(jiffies, rt->dst.expires)) {
+		RT6_TRACE("purging expired route %p\n", rt);
 		rt6_remove_exception(bucket, rt6_ex);
 		return;
-	} else if (rt->rt6i_flags & RTF_GATEWAY) {
+	}
+
+	if (rt->rt6i_flags & RTF_GATEWAY) {
 		struct neighbour *neigh;
 		__u8 neigh_flags = 0;
 
@@ -1606,11 +1613,8 @@ static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket,
 			rt6_remove_exception(bucket, rt6_ex);
 			return;
 		}
-	} else if (__rt6_check_expired(rt)) {
-		RT6_TRACE("purging expired route %p\n", rt);
-		rt6_remove_exception(bucket, rt6_ex);
-		return;
 	}
+
 	gc_args->more++;
 }
 
-- 
2.14.3


From 7fd71d93eefc7b2e197a523d1bf322875d060b6d Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Fri, 2 Feb 2018 15:26:57 +0000
Subject: [PATCH 10/18] Revert "defer call to mem_cgroup_sk_alloc()"

[ Upstream commit edbe69ef2c90fc86998a74b08319a01c508bd497 ]

This patch effectively reverts commit 9f1c2674b328 ("net: memcontrol:
defer call to mem_cgroup_sk_alloc()").

Moving mem_cgroup_sk_alloc() to the inet_csk_accept() completely breaks
memcg socket memory accounting, as packets received before memcg
pointer initialization are not accounted and are causing refcounting
underflow on socket release.

Actually the free-after-use problem was fixed by
commit c0576e397508 ("net: call cgroup_sk_alloc() earlier in
sk_clone_lock()") for the cgroup pointer.

So, let's revert it and call mem_cgroup_sk_alloc() just before
cgroup_sk_alloc(). This is safe, as we hold a reference to the socket
we're cloning, and it holds a reference to the memcg.

Also, let's drop BUG_ON(mem_cgroup_is_root()) check from
mem_cgroup_sk_alloc(). I see no reasons why bumping the root
memcg counter is a good reason to panic, and there are no realistic
ways to hit it.

Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 mm/memcontrol.c                 | 14 ++++++++++++++
 net/core/sock.c                 |  5 +----
 net/ipv4/inet_connection_sock.c |  1 -
 3 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ac2ffd5e02b9..0a78ce57872d 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5828,6 +5828,20 @@ void mem_cgroup_sk_alloc(struct sock *sk)
 	if (!mem_cgroup_sockets_enabled)
 		return;
 
+	/*
+	 * Socket cloning can throw us here with sk_memcg already
+	 * filled. It won't however, necessarily happen from
+	 * process context. So the test for root memcg given
+	 * the current task's memcg won't help us in this case.
+	 *
+	 * Respecting the original socket's memcg is a better
+	 * decision in this case.
+	 */
+	if (sk->sk_memcg) {
+		css_get(&sk->sk_memcg->css);
+		return;
+	}
+
 	rcu_read_lock();
 	memcg = mem_cgroup_from_task(current);
 	if (memcg == root_mem_cgroup)
diff --git a/net/core/sock.c b/net/core/sock.c
index c0b5b2f17412..7571dabfc4cf 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1675,16 +1675,13 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		newsk->sk_dst_pending_confirm = 0;
 		newsk->sk_wmem_queued	= 0;
 		newsk->sk_forward_alloc = 0;
-
-		/* sk->sk_memcg will be populated at accept() time */
-		newsk->sk_memcg = NULL;
-
 		atomic_set(&newsk->sk_drops, 0);
 		newsk->sk_send_head	= NULL;
 		newsk->sk_userlocks	= sk->sk_userlocks & ~SOCK_BINDPORT_LOCK;
 		atomic_set(&newsk->sk_zckey, 0);
 
 		sock_reset_flag(newsk, SOCK_DONE);
+		mem_cgroup_sk_alloc(newsk);
 		cgroup_sk_alloc(&newsk->sk_cgrp_data);
 
 		rcu_read_lock();
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 4ca46dc08e63..3668c4182655 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -475,7 +475,6 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern)
 		}
 		spin_unlock_bh(&queue->fastopenq.lock);
 	}
-	mem_cgroup_sk_alloc(newsk);
 out:
 	release_sock(sk);
 	if (req)
-- 
2.14.3


From 92cbbfbb2cdf822d62581a19e17c12c413167ded Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Thu, 25 Jan 2018 20:16:29 -0800
Subject: [PATCH 11/18] net: ipv6: send unsolicited NA after DAD

[ Upstream commit c76fe2d98c726224a975a0d0198c3fb50406d325 ]

Unsolicited IPv6 neighbor advertisements should be sent after DAD
completes. Update ndisc_send_unsol_na to skip tentative, non-optimistic
addresses and have those sent by addrconf_dad_completed after DAD.

Fixes: 4a6e3c5def13c ("net: ipv6: send unsolicited NA on admin up")
Reported-by: Vivek Venkatraman <vivek@cumulusnetworks.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 30 ++++++++++++++++++++++++++----
 net/ipv6/ndisc.c    |  5 +++++
 2 files changed, 31 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 10facd174210..2547222589fe 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -186,7 +186,8 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
 
 static void addrconf_dad_start(struct inet6_ifaddr *ifp);
 static void addrconf_dad_work(struct work_struct *w);
-static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id);
+static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id,
+				   bool send_na);
 static void addrconf_dad_run(struct inet6_dev *idev);
 static void addrconf_rs_timer(struct timer_list *t);
 static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa);
@@ -3833,12 +3834,17 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
 	     idev->cnf.accept_dad < 1) ||
 	    !(ifp->flags&IFA_F_TENTATIVE) ||
 	    ifp->flags & IFA_F_NODAD) {
+		bool send_na = false;
+
+		if (ifp->flags & IFA_F_TENTATIVE &&
+		    !(ifp->flags & IFA_F_OPTIMISTIC))
+			send_na = true;
 		bump_id = ifp->flags & IFA_F_TENTATIVE;
 		ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED);
 		spin_unlock(&ifp->lock);
 		read_unlock_bh(&idev->lock);
 
-		addrconf_dad_completed(ifp, bump_id);
+		addrconf_dad_completed(ifp, bump_id, send_na);
 		return;
 	}
 
@@ -3967,16 +3973,21 @@ static void addrconf_dad_work(struct work_struct *w)
 	}
 
 	if (ifp->dad_probes == 0) {
+		bool send_na = false;
+
 		/*
 		 * DAD was successful
 		 */
 
+		if (ifp->flags & IFA_F_TENTATIVE &&
+		    !(ifp->flags & IFA_F_OPTIMISTIC))
+			send_na = true;
 		bump_id = ifp->flags & IFA_F_TENTATIVE;
 		ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED);
 		spin_unlock(&ifp->lock);
 		write_unlock_bh(&idev->lock);
 
-		addrconf_dad_completed(ifp, bump_id);
+		addrconf_dad_completed(ifp, bump_id, send_na);
 
 		goto out;
 	}
@@ -4014,7 +4025,8 @@ static bool ipv6_lonely_lladdr(struct inet6_ifaddr *ifp)
 	return true;
 }
 
-static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id)
+static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id,
+				   bool send_na)
 {
 	struct net_device *dev = ifp->idev->dev;
 	struct in6_addr lladdr;
@@ -4046,6 +4058,16 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id)
 	if (send_mld)
 		ipv6_mc_dad_complete(ifp->idev);
 
+	/* send unsolicited NA if enabled */
+	if (send_na &&
+	    (ifp->idev->cnf.ndisc_notify ||
+	     dev_net(dev)->ipv6.devconf_all->ndisc_notify)) {
+		ndisc_send_na(dev, &in6addr_linklocal_allnodes, &ifp->addr,
+			      /*router=*/ !!ifp->idev->cnf.forwarding,
+			      /*solicited=*/ false, /*override=*/ true,
+			      /*inc_opt=*/ true);
+	}
+
 	if (send_rs) {
 		/*
 		 *	If a host as already performed a random delay
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index b3cea200c85e..f61a5b613b52 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -566,6 +566,11 @@ static void ndisc_send_unsol_na(struct net_device *dev)
 
 	read_lock_bh(&idev->lock);
 	list_for_each_entry(ifa, &idev->addr_list, if_list) {
+		/* skip tentative addresses until dad completes */
+		if (ifa->flags & IFA_F_TENTATIVE &&
+		    !(ifa->flags & IFA_F_OPTIMISTIC))
+			continue;
+
 		ndisc_send_na(dev, &in6addr_linklocal_allnodes, &ifa->addr,
 			      /*router=*/ !!idev->cnf.forwarding,
 			      /*solicited=*/ false, /*override=*/ true,
-- 
2.14.3


From e92aa794935c804a4b2801230073c0ad7837dd0f Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Thu, 1 Feb 2018 12:21:15 +0100
Subject: [PATCH 12/18] rocker: fix possible null pointer dereference in
 rocker_router_fib_event_work

[ Upstream commit a83165f00f16c0e0ef5b7cec3cbd0d4788699265 ]

Currently, rocker user may experience following null pointer
derefence bug:

[    3.062141] BUG: unable to handle kernel NULL pointer dereference at 00000000000000d0
[    3.065163] IP: rocker_router_fib_event_work+0x36/0x110 [rocker]

The problem is uninitialized rocker->wops pointer that is initialized
only with the first initialized port. So move the port initialization
before registering the fib events.

Fixes: 936bd486564a ("rocker: use FIB notifications instead of switchdev calls")
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/rocker/rocker_main.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index fc8f8bdf6579..056cb6093630 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -2902,6 +2902,12 @@ static int rocker_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto err_alloc_ordered_workqueue;
 	}
 
+	err = rocker_probe_ports(rocker);
+	if (err) {
+		dev_err(&pdev->dev, "failed to probe ports\n");
+		goto err_probe_ports;
+	}
+
 	/* Only FIBs pointing to our own netdevs are programmed into
 	 * the device, so no need to pass a callback.
 	 */
@@ -2918,22 +2924,16 @@ static int rocker_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	rocker->hw.id = rocker_read64(rocker, SWITCH_ID);
 
-	err = rocker_probe_ports(rocker);
-	if (err) {
-		dev_err(&pdev->dev, "failed to probe ports\n");
-		goto err_probe_ports;
-	}
-
 	dev_info(&pdev->dev, "Rocker switch with id %*phN\n",
 		 (int)sizeof(rocker->hw.id), &rocker->hw.id);
 
 	return 0;
 
-err_probe_ports:
-	unregister_switchdev_notifier(&rocker_switchdev_notifier);
 err_register_switchdev_notifier:
 	unregister_fib_notifier(&rocker->fib_nb);
 err_register_fib_notifier:
+	rocker_remove_ports(rocker);
+err_probe_ports:
 	destroy_workqueue(rocker->rocker_owq);
 err_alloc_ordered_workqueue:
 	free_irq(rocker_msix_vector(rocker, ROCKER_MSIX_VEC_EVENT), rocker);
@@ -2961,9 +2961,9 @@ static void rocker_remove(struct pci_dev *pdev)
 {
 	struct rocker *rocker = pci_get_drvdata(pdev);
 
-	rocker_remove_ports(rocker);
 	unregister_switchdev_notifier(&rocker_switchdev_notifier);
 	unregister_fib_notifier(&rocker->fib_nb);
+	rocker_remove_ports(rocker);
 	rocker_write32(rocker, CONTROL, ROCKER_CONTROL_RESET);
 	destroy_workqueue(rocker->rocker_owq);
 	free_irq(rocker_msix_vector(rocker, ROCKER_MSIX_VEC_EVENT), rocker);
-- 
2.14.3


From 7eb2e129392086d951b7fa13cd15a37b685f70c9 Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Wed, 31 Jan 2018 15:43:05 -0500
Subject: [PATCH 13/18] tcp_bbr: fix pacing_gain to always be unity when using
 lt_bw

[ Upstream commit 3aff3b4b986e51bcf4ab249e5d48d39596e0df6a ]

This commit fixes the pacing_gain to remain at BBR_UNIT (1.0) when
using lt_bw and returning from the PROBE_RTT state to PROBE_BW.

Previously, when using lt_bw, upon exiting PROBE_RTT and entering
PROBE_BW the bbr_reset_probe_bw_mode() code could sometimes randomly
end up with a cycle_idx of 0 and hence have bbr_advance_cycle_phase()
set a pacing gain above 1.0. In such cases this would result in a
pacing rate that is 1.25x higher than intended, potentially resulting
in a high loss rate for a little while until we stop using the lt_bw a
bit later.

This commit is a stable candidate for kernels back as far as 4.9.

Fixes: 0f8782ea1497 ("tcp_bbr: add BBR congestion control")
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Reported-by: Beyers Cronje <bcronje@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_bbr.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 8322f26e770e..25c5a0b60cfc 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -481,7 +481,8 @@ static void bbr_advance_cycle_phase(struct sock *sk)
 
 	bbr->cycle_idx = (bbr->cycle_idx + 1) & (CYCLE_LEN - 1);
 	bbr->cycle_mstamp = tp->delivered_mstamp;
-	bbr->pacing_gain = bbr_pacing_gain[bbr->cycle_idx];
+	bbr->pacing_gain = bbr->lt_use_bw ? BBR_UNIT :
+					    bbr_pacing_gain[bbr->cycle_idx];
 }
 
 /* Gain cycling: cycle pacing gain to converge to fair share of available bw. */
@@ -490,8 +491,7 @@ static void bbr_update_cycle_phase(struct sock *sk,
 {
 	struct bbr *bbr = inet_csk_ca(sk);
 
-	if ((bbr->mode == BBR_PROBE_BW) && !bbr->lt_use_bw &&
-	    bbr_is_next_cycle_phase(sk, rs))
+	if (bbr->mode == BBR_PROBE_BW && bbr_is_next_cycle_phase(sk, rs))
 		bbr_advance_cycle_phase(sk);
 }
 
-- 
2.14.3


From 15d02b9e4fa7d1621a2ab5cd9ed684fb18aaca4d Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 2 Feb 2018 16:02:22 +0100
Subject: [PATCH 14/18] cls_u32: add missing RCU annotation.

[ Upstream commit 058a6c033488494a6b1477b05fe8e1a16e344462 ]

In a couple of points of the control path, n->ht_down is currently
accessed without the required RCU annotation. The accesses are
safe, but sparse complaints. Since we already held the
rtnl lock, let use rtnl_dereference().

Fixes: a1b7c5fd7fe9 ("net: sched: add cls_u32 offload hooks for netdevs")
Fixes: de5df63228fc ("net: sched: cls_u32 changes to knode must appear atomic to readers")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_u32.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 507859cdd1cb..33294b5b2c6a 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -544,6 +544,7 @@ static void u32_remove_hw_knode(struct tcf_proto *tp, u32 handle)
 static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n,
 				u32 flags)
 {
+	struct tc_u_hnode *ht = rtnl_dereference(n->ht_down);
 	struct tcf_block *block = tp->chain->block;
 	struct tc_cls_u32_offload cls_u32 = {};
 	bool skip_sw = tc_skip_sw(flags);
@@ -563,7 +564,7 @@ static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n,
 	cls_u32.knode.sel = &n->sel;
 	cls_u32.knode.exts = &n->exts;
 	if (n->ht_down)
-		cls_u32.knode.link_handle = n->ht_down->handle;
+		cls_u32.knode.link_handle = ht->handle;
 
 	err = tc_setup_cb_call(block, NULL, TC_SETUP_CLSU32, &cls_u32, skip_sw);
 	if (err < 0) {
@@ -840,8 +841,9 @@ static void u32_replace_knode(struct tcf_proto *tp, struct tc_u_common *tp_c,
 static struct tc_u_knode *u32_init_knode(struct tcf_proto *tp,
 					 struct tc_u_knode *n)
 {
-	struct tc_u_knode *new;
+	struct tc_u_hnode *ht = rtnl_dereference(n->ht_down);
 	struct tc_u32_sel *s = &n->sel;
+	struct tc_u_knode *new;
 
 	new = kzalloc(sizeof(*n) + s->nkeys*sizeof(struct tc_u32_key),
 		      GFP_KERNEL);
@@ -859,11 +861,11 @@ static struct tc_u_knode *u32_init_knode(struct tcf_proto *tp,
 	new->fshift = n->fshift;
 	new->res = n->res;
 	new->flags = n->flags;
-	RCU_INIT_POINTER(new->ht_down, n->ht_down);
+	RCU_INIT_POINTER(new->ht_down, ht);
 
 	/* bump reference count as long as we hold pointer to structure */
-	if (new->ht_down)
-		new->ht_down->refcnt++;
+	if (ht)
+		ht->refcnt++;
 
 #ifdef CONFIG_CLS_U32_PERF
 	/* Statistics may be incremented by readers during update
-- 
2.14.3


From 3cd751a45f59c2ab5dea4e54361c3bae91f5f5af Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 24 Jan 2018 23:15:27 -0800
Subject: [PATCH 15/18] ipv6: Fix SO_REUSEPORT UDP socket with implicit
 sk_ipv6only

[ Upstream commit 7ece54a60ee2ba7a386308cae73c790bd580589c ]

If a sk_v6_rcv_saddr is !IPV6_ADDR_ANY and !IPV6_ADDR_MAPPED, it
implicitly implies it is an ipv6only socket.  However, in inet6_bind(),
this addr_type checking and setting sk->sk_ipv6only to 1 are only done
after sk->sk_prot->get_port(sk, snum) has been completed successfully.

This inconsistency between sk_v6_rcv_saddr and sk_ipv6only confuses
the 'get_port()'.

In particular, when binding SO_REUSEPORT UDP sockets,
udp_reuseport_add_sock(sk,...) is called.  udp_reuseport_add_sock()
checks "ipv6_only_sock(sk2) == ipv6_only_sock(sk)" before adding sk to
sk2->sk_reuseport_cb.  In this case, ipv6_only_sock(sk2) could be
1 while ipv6_only_sock(sk) is still 0 here.  The end result is,
reuseport_alloc(sk) is called instead of adding sk to the existing
sk2->sk_reuseport_cb.

It can be reproduced by binding two SO_REUSEPORT UDP sockets on an
IPv6 address (!ANY and !MAPPED).  Only one of the socket will
receive packet.

The fix is to set the implicit sk_ipv6only before calling get_port().
The original sk_ipv6only has to be saved such that it can be restored
in case get_port() failed.  The situation is similar to the
inet_reset_saddr(sk) after get_port() has failed.

Thanks to Calvin Owens <calvinowens@fb.com> who created an easy
reproduction which leads to a fix.

Fixes: e32ea7e74727 ("soreuseport: fast reuseport UDP socket selection")
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/af_inet6.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index c9441ca45399..416917719a6f 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -284,6 +284,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	struct net *net = sock_net(sk);
 	__be32 v4addr = 0;
 	unsigned short snum;
+	bool saved_ipv6only;
 	int addr_type = 0;
 	int err = 0;
 
@@ -389,19 +390,21 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	if (!(addr_type & IPV6_ADDR_MULTICAST))
 		np->saddr = addr->sin6_addr;
 
+	saved_ipv6only = sk->sk_ipv6only;
+	if (addr_type != IPV6_ADDR_ANY && addr_type != IPV6_ADDR_MAPPED)
+		sk->sk_ipv6only = 1;
+
 	/* Make sure we are allowed to bind here. */
 	if ((snum || !inet->bind_address_no_port) &&
 	    sk->sk_prot->get_port(sk, snum)) {
+		sk->sk_ipv6only = saved_ipv6only;
 		inet_reset_saddr(sk);
 		err = -EADDRINUSE;
 		goto out;
 	}
 
-	if (addr_type != IPV6_ADDR_ANY) {
+	if (addr_type != IPV6_ADDR_ANY)
 		sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
-		if (addr_type != IPV6_ADDR_MAPPED)
-			sk->sk_ipv6only = 1;
-	}
 	if (snum)
 		sk->sk_userlocks |= SOCK_BINDPORT_LOCK;
 	inet->inet_sport = htons(inet->inet_num);
-- 
2.14.3


From 4654b1a465b7e2e8eefcff929bd710826f87197c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 2 Feb 2018 10:27:27 -0800
Subject: [PATCH 16/18] soreuseport: fix mem leak in reuseport_add_sock()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 4db428a7c9ab07e08783e0fcdc4ca0f555da0567 ]

reuseport_add_sock() needs to deal with attaching a socket having
its own sk_reuseport_cb, after a prior
setsockopt(SO_ATTACH_REUSEPORT_?BPF)

Without this fix, not only a WARN_ONCE() was issued, but we were also
leaking memory.

Thanks to sysbot and Eric Biggers for providing us nice C repros.

------------[ cut here ]------------
socket already in reuseport group
WARNING: CPU: 0 PID: 3496 at net/core/sock_reuseport.c:119  
reuseport_add_sock+0x742/0x9b0 net/core/sock_reuseport.c:117
Kernel panic - not syncing: panic_on_warn set ...

CPU: 0 PID: 3496 Comm: syzkaller869503 Not tainted 4.15.0-rc6+ #245
Hardware name: Google Google Compute Engine/Google Compute Engine,
BIOS  
Google 01/01/2011
Call Trace:
  __dump_stack lib/dump_stack.c:17 [inline]
  dump_stack+0x194/0x257 lib/dump_stack.c:53
  panic+0x1e4/0x41c kernel/panic.c:183
  __warn+0x1dc/0x200 kernel/panic.c:547
  report_bug+0x211/0x2d0 lib/bug.c:184
  fixup_bug.part.11+0x37/0x80 arch/x86/kernel/traps.c:178
  fixup_bug arch/x86/kernel/traps.c:247 [inline]
  do_error_trap+0x2d7/0x3e0 arch/x86/kernel/traps.c:296
  do_invalid_op+0x1b/0x20 arch/x86/kernel/traps.c:315
  invalid_op+0x22/0x40 arch/x86/entry/entry_64.S:1079

Fixes: ef456144da8e ("soreuseport: define reuseport groups")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot+c0ea2226f77a42936bf7@syzkaller.appspotmail.com
Acked-by: Craig Gallek <kraig@google.com>

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock_reuseport.c | 35 ++++++++++++++++++++---------------
 1 file changed, 20 insertions(+), 15 deletions(-)

diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index 5eeb1d20cc38..676092d7bd81 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -94,6 +94,16 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse)
 	return more_reuse;
 }
 
+static void reuseport_free_rcu(struct rcu_head *head)
+{
+	struct sock_reuseport *reuse;
+
+	reuse = container_of(head, struct sock_reuseport, rcu);
+	if (reuse->prog)
+		bpf_prog_destroy(reuse->prog);
+	kfree(reuse);
+}
+
 /**
  *  reuseport_add_sock - Add a socket to the reuseport group of another.
  *  @sk:  New socket to add to the group.
@@ -102,7 +112,7 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse)
  */
 int reuseport_add_sock(struct sock *sk, struct sock *sk2)
 {
-	struct sock_reuseport *reuse;
+	struct sock_reuseport *old_reuse, *reuse;
 
 	if (!rcu_access_pointer(sk2->sk_reuseport_cb)) {
 		int err = reuseport_alloc(sk2);
@@ -113,10 +123,13 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2)
 
 	spin_lock_bh(&reuseport_lock);
 	reuse = rcu_dereference_protected(sk2->sk_reuseport_cb,
-					  lockdep_is_held(&reuseport_lock)),
-	WARN_ONCE(rcu_dereference_protected(sk->sk_reuseport_cb,
-					    lockdep_is_held(&reuseport_lock)),
-		  "socket already in reuseport group");
+					  lockdep_is_held(&reuseport_lock));
+	old_reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
+					     lockdep_is_held(&reuseport_lock));
+	if (old_reuse && old_reuse->num_socks != 1) {
+		spin_unlock_bh(&reuseport_lock);
+		return -EBUSY;
+	}
 
 	if (reuse->num_socks == reuse->max_socks) {
 		reuse = reuseport_grow(reuse);
@@ -134,19 +147,11 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2)
 
 	spin_unlock_bh(&reuseport_lock);
 
+	if (old_reuse)
+		call_rcu(&old_reuse->rcu, reuseport_free_rcu);
 	return 0;
 }
 
-static void reuseport_free_rcu(struct rcu_head *head)
-{
-	struct sock_reuseport *reuse;
-
-	reuse = container_of(head, struct sock_reuseport, rcu);
-	if (reuse->prog)
-		bpf_prog_destroy(reuse->prog);
-	kfree(reuse);
-}
-
 void reuseport_detach_sock(struct sock *sk)
 {
 	struct sock_reuseport *reuse;
-- 
2.14.3


From 7528b48d76d63f9405cdfce6200dd184eb39c674 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 4 Dec 2017 10:48:18 -0800
Subject: [PATCH 17/18] net_sched: get rid of rcu_barrier() in
 tcf_block_put_ext()

[ Upstream commit efbf78973978b0d25af59bc26c8013a942af6e64 ]

Both Eric and Paolo noticed the rcu_barrier() we use in
tcf_block_put_ext() could be a performance bottleneck when
we have a lot of tc classes.

Paolo provided the following to demonstrate the issue:

tc qdisc add dev lo root htb
for I in `seq 1 1000`; do
        tc class add dev lo parent 1: classid 1:$I htb rate 100kbit
        tc qdisc add dev lo parent 1:$I handle $((I + 1)): htb
        for J in `seq 1 10`; do
                tc filter add dev lo parent $((I + 1)): u32 match ip src 1.1.1.$J
        done
done
time tc qdisc del dev root

real    0m54.764s
user    0m0.023s
sys     0m0.000s

The rcu_barrier() there is to ensure we free the block after all chains
are gone, that is, to queue tcf_block_put_final() at the tail of workqueue.
We can achieve this ordering requirement by refcnt'ing tcf block instead,
that is, the tcf block is freed only when the last chain in this block is
gone. This also simplifies the code.

Paolo reported after this patch we get:

real    0m0.017s
user    0m0.000s
sys     0m0.017s

Tested-by: Paolo Abeni <pabeni@redhat.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jiri Pirko <jiri@mellanox.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h |  1 -
 net/sched/cls_api.c       | 30 +++++++++---------------------
 2 files changed, 9 insertions(+), 22 deletions(-)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index becf86aa4ac6..d6ec5a5a6782 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -280,7 +280,6 @@ struct tcf_block {
 	struct net *net;
 	struct Qdisc *q;
 	struct list_head cb_list;
-	struct work_struct work;
 };
 
 static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz)
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index b9d63d2246e6..2f8bf4ac8d6f 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -217,8 +217,12 @@ static void tcf_chain_flush(struct tcf_chain *chain)
 
 static void tcf_chain_destroy(struct tcf_chain *chain)
 {
+	struct tcf_block *block = chain->block;
+
 	list_del(&chain->list);
 	kfree(chain);
+	if (list_empty(&block->chain_list))
+		kfree(block);
 }
 
 static void tcf_chain_hold(struct tcf_chain *chain)
@@ -329,27 +333,13 @@ int tcf_block_get(struct tcf_block **p_block,
 }
 EXPORT_SYMBOL(tcf_block_get);
 
-static void tcf_block_put_final(struct work_struct *work)
-{
-	struct tcf_block *block = container_of(work, struct tcf_block, work);
-	struct tcf_chain *chain, *tmp;
-
-	rtnl_lock();
-
-	/* At this point, all the chains should have refcnt == 1. */
-	list_for_each_entry_safe(chain, tmp, &block->chain_list, list)
-		tcf_chain_put(chain);
-	rtnl_unlock();
-	kfree(block);
-}
-
 /* XXX: Standalone actions are not allowed to jump to any chain, and bound
  * actions should be all removed after flushing.
  */
 void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
 		       struct tcf_block_ext_info *ei)
 {
-	struct tcf_chain *chain;
+	struct tcf_chain *chain, *tmp;
 
 	if (!block)
 		return;
@@ -365,13 +355,11 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
 
 	tcf_block_offload_unbind(block, q, ei);
 
-	INIT_WORK(&block->work, tcf_block_put_final);
-	/* Wait for existing RCU callbacks to cool down, make sure their works
-	 * have been queued before this. We can not flush pending works here
-	 * because we are holding the RTNL lock.
+	/* At this point, all the chains should have refcnt >= 1. Block will be
+	 * freed after all chains are gone.
 	 */
-	rcu_barrier();
-	tcf_queue_work(&block->work);
+	list_for_each_entry_safe(chain, tmp, &block->chain_list, list)
+		tcf_chain_put(chain);
 }
 EXPORT_SYMBOL(tcf_block_put_ext);
 
-- 
2.14.3


From bd5b3318e4a0db9eba301aaa2a0b9005e2681994 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Fri, 8 Dec 2017 19:27:27 +0100
Subject: [PATCH 18/18] net: sched: fix use-after-free in tcf_block_put_ext

[ Upstream commit df45bf84e4f5a48f23d4b1a07d21d566e8b587b2 ]

Since the block is freed with last chain being put, once we reach the
end of iteration of list_for_each_entry_safe, the block may be
already freed. I'm hitting this only by creating and deleting clsact:

[  202.171952] ==================================================================
[  202.180182] BUG: KASAN: use-after-free in tcf_block_put_ext+0x240/0x390
[  202.187590] Read of size 8 at addr ffff880225539a80 by task tc/796
[  202.194508]
[  202.196185] CPU: 0 PID: 796 Comm: tc Not tainted 4.15.0-rc2jiri+ #5
[  202.203200] Hardware name: Mellanox Technologies Ltd. "MSN2100-CB2F"/"SA001017", BIOS 5.6.5 06/07/2016
[  202.213613] Call Trace:
[  202.216369]  dump_stack+0xda/0x169
[  202.220192]  ? dma_virt_map_sg+0x147/0x147
[  202.224790]  ? show_regs_print_info+0x54/0x54
[  202.229691]  ? tcf_chain_destroy+0x1dc/0x250
[  202.234494]  print_address_description+0x83/0x3d0
[  202.239781]  ? tcf_block_put_ext+0x240/0x390
[  202.244575]  kasan_report+0x1ba/0x460
[  202.248707]  ? tcf_block_put_ext+0x240/0x390
[  202.253518]  tcf_block_put_ext+0x240/0x390
[  202.258117]  ? tcf_chain_flush+0x290/0x290
[  202.262708]  ? qdisc_hash_del+0x82/0x1a0
[  202.267111]  ? qdisc_hash_add+0x50/0x50
[  202.271411]  ? __lock_is_held+0x5f/0x1a0
[  202.275843]  clsact_destroy+0x3d/0x80 [sch_ingress]
[  202.281323]  qdisc_destroy+0xcb/0x240
[  202.285445]  qdisc_graft+0x216/0x7b0
[  202.289497]  tc_get_qdisc+0x260/0x560

Fix this by holding the block also by chain 0 and put chain 0
explicitly, out of the list_for_each_entry_safe loop at the very
end of tcf_block_put_ext.

Fixes: efbf78973978 ("net_sched: get rid of rcu_barrier() in tcf_block_put_ext()")
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 2f8bf4ac8d6f..e6b853f0ee4f 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -343,23 +343,24 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
 
 	if (!block)
 		return;
-	/* Hold a refcnt for all chains, except 0, so that they don't disappear
+	/* Hold a refcnt for all chains, so that they don't disappear
 	 * while we are iterating.
 	 */
 	list_for_each_entry(chain, &block->chain_list, list)
-		if (chain->index)
-			tcf_chain_hold(chain);
+		tcf_chain_hold(chain);
 
 	list_for_each_entry(chain, &block->chain_list, list)
 		tcf_chain_flush(chain);
 
 	tcf_block_offload_unbind(block, q, ei);
 
-	/* At this point, all the chains should have refcnt >= 1. Block will be
-	 * freed after all chains are gone.
-	 */
+	/* At this point, all the chains should have refcnt >= 1. */
 	list_for_each_entry_safe(chain, tmp, &block->chain_list, list)
 		tcf_chain_put(chain);
+
+	/* Finally, put chain 0 and allow block to be freed. */
+	chain = list_first_entry(&block->chain_list, struct tcf_chain, list);
+	tcf_chain_put(chain);
 }
 EXPORT_SYMBOL(tcf_block_put_ext);
 
-- 
2.14.3

Re: [PATCHES] Networking

[Greg KH]

On Tue, Feb 06, 2018 at 03:19:49PM -0500, David Miller wrote:
> 
> Please queue up the following networking bug fixes for 4.9.x, 4.14.x,
> and 4.15.x -stable, respectively.

Many thanks for all of these, now queued up.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 107 bytes --]


Please queue up the following networking bug fixes for v4.14 and
v4.15 -stable, respectively.

Thank you.

[-- Attachment #2: net_414.mbox --]
[-- Type: Application/Octet-Stream, Size: 116820 bytes --]

From 2f8f65d8588b9566a654f4aeb931748d3c186397 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 12 Feb 2018 17:15:40 +0800
Subject: [PATCH 01/49] bridge: check brport attr show in brport_show

[ Upstream commit 1b12580af1d0677c3c3a19e35bfe5d59b03f737f ]

Now br_sysfs_if file flush doesn't have attr show. To read it will
cause kernel panic after users chmod u+r this file.

Xiong found this issue when running the commands:

  ip link add br0 type bridge
  ip link add type veth
  ip link set veth0 master br0
  chmod u+r /sys/devices/virtual/net/veth0/brport/flush
  timeout 3 cat /sys/devices/virtual/net/veth0/brport/flush

kernel crashed with NULL a pointer dereference call trace.

This patch is to fix it by return -EINVAL when brport_attr->show
is null, just the same as the check for brport_attr->store in
brport_store().

Fixes: 9cf637473c85 ("bridge: add sysfs hook to flush forwarding table")
Reported-by: Xiong Zhou <xzhou@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_sysfs_if.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c
index 5d5d413a6cf8..a097a8613a02 100644
--- a/net/bridge/br_sysfs_if.c
+++ b/net/bridge/br_sysfs_if.c
@@ -235,6 +235,9 @@ static ssize_t brport_show(struct kobject *kobj,
 	struct brport_attribute *brport_attr = to_brport_attr(attr);
 	struct net_bridge_port *p = to_brport(kobj);
 
+	if (!brport_attr->show)
+		return -EINVAL;
+
 	return brport_attr->show(p, buf);
 }
 
-- 
2.14.3


From fce66d2ea74caf97509f0f81b659dbf7e1bd4cae Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Thu, 15 Feb 2018 09:46:03 +0100
Subject: [PATCH 02/49] fib_semantics: Don't match route with mismatching
 tclassid

[ Upstream commit a8c6db1dfd1b1d18359241372bb204054f2c3174 ]

In fib_nh_match(), if output interface or gateway are passed in
the FIB configuration, we don't have to check next hops of
multipath routes to conclude whether we have a match or not.

However, we might still have routes with different realms
matching the same output interface and gateway configuration,
and this needs to cause the match to fail. Otherwise the first
route inserted in the FIB will match, regardless of the realms:

 # ip route add 1.1.1.1 dev eth0 table 1234 realms 1/2
 # ip route append 1.1.1.1 dev eth0 table 1234 realms 3/4
 # ip route list table 1234
 1.1.1.1 dev eth0 scope link realms 1/2
 1.1.1.1 dev eth0 scope link realms 3/4
 # ip route del 1.1.1.1 dev ens3 table 1234 realms 3/4
 # ip route list table 1234
 1.1.1.1 dev ens3 scope link realms 3/4

whereas route with realms 3/4 should have been deleted instead.

Explicitly check for fc_flow passed in the FIB configuration
(this comes from RTA_FLOW extracted by rtm_to_fib_config()) and
fail matching if it differs from nh_tclassid.

The handling of RTA_FLOW for multipath routes later in
fib_nh_match() is still needed, as we can have multiple RTA_FLOW
attributes that need to be matched against the tclassid of each
next hop.

v2: Check that fc_flow is set before discarding the match, so
    that the user can still select the first matching rule by
    not specifying any realm, as suggested by David Ahern.

Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_semantics.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index aff3751df950..1ee6c0d8dde4 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -654,6 +654,11 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi,
 					    fi->fib_nh, cfg, extack))
 				return 1;
 		}
+#ifdef CONFIG_IP_ROUTE_CLASSID
+		if (cfg->fc_flow &&
+		    cfg->fc_flow != fi->fib_nh->nh_tclassid)
+			return 1;
+#endif
 		if ((!cfg->fc_oif || cfg->fc_oif == fi->fib_nh->nh_oif) &&
 		    (!cfg->fc_gw  || cfg->fc_gw == fi->fib_nh->nh_gw))
 			return 0;
-- 
2.14.3


From d58ff81be34a5728ed5f30d7d655407451057c32 Mon Sep 17 00:00:00 2001
From: Denis Du <dudenis2000@yahoo.ca>
Date: Sat, 24 Feb 2018 16:51:42 -0500
Subject: [PATCH 03/49] hdlc_ppp: carrier detect ok, don't turn off negotiation

[ Upstream commit b6c3bad1ba83af1062a7ff6986d9edc4f3d7fc8e ]

Sometimes when physical lines have a just good noise to make the protocol
handshaking fail, but the carrier detect still good. Then after remove of
the noise, nobody will trigger this protocol to be start again to cause
the link to never come back. The fix is when the carrier is still on, not
terminate the protocol handshaking.

Signed-off-by: Denis Du <dudenis2000@yahoo.ca>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wan/hdlc_ppp.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wan/hdlc_ppp.c b/drivers/net/wan/hdlc_ppp.c
index 0d2e00ece804..f3c1d5245978 100644
--- a/drivers/net/wan/hdlc_ppp.c
+++ b/drivers/net/wan/hdlc_ppp.c
@@ -574,7 +574,10 @@ static void ppp_timer(unsigned long arg)
 			ppp_cp_event(proto->dev, proto->pid, TO_GOOD, 0, 0,
 				     0, NULL);
 			proto->restart_counter--;
-		} else
+		} else if (netif_carrier_ok(proto->dev))
+			ppp_cp_event(proto->dev, proto->pid, TO_GOOD, 0, 0,
+				     0, NULL);
+		else
 			ppp_cp_event(proto->dev, proto->pid, TO_BAD, 0, 0,
 				     0, NULL);
 		break;
-- 
2.14.3


From b379799aa875f0c4a53984c86bc2381d5ec43a31 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 22 Feb 2018 16:55:34 +0100
Subject: [PATCH 04/49] ipv6 sit: work around bogus gcc-8 -Wrestrict warning

[ Upstream commit ca79bec237f5809a7c3c59bd41cd0880aa889966 ]

gcc-8 has a new warning that detects overlapping input and output arguments
in memcpy(). It triggers for sit_init_net() calling ipip6_tunnel_clone_6rd(),
which is actually correct:

net/ipv6/sit.c: In function 'sit_init_net':
net/ipv6/sit.c:192:3: error: 'memcpy' source argument is the same as destination [-Werror=restrict]

The problem here is that the logic detecting the memcpy() arguments finds them
to be the same, but the conditional that tests for the input and output of
ipip6_tunnel_clone_6rd() to be identical is not a compile-time constant.

We know that netdev_priv(t->dev) is the same as t for a tunnel device,
and comparing "dev" directly here lets the compiler figure out as well
that 'dev == sitn->fb_tunnel_dev' when called from sit_init_net(), so
it no longer warns.

This code is old, so Cc stable to make sure that we don't get the warning
for older kernels built with new gcc.

Cc: Martin Sebor <msebor@gmail.com>
Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=83456
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index e79854cc5790..cac815cc8600 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -176,7 +176,7 @@ static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn)
 #ifdef CONFIG_IPV6_SIT_6RD
 	struct ip_tunnel *t = netdev_priv(dev);
 
-	if (t->dev == sitn->fb_tunnel_dev) {
+	if (dev == sitn->fb_tunnel_dev) {
 		ipv6_addr_set(&t->ip6rd.prefix, htonl(0x20020000), 0, 0, 0);
 		t->ip6rd.relay_prefix = 0;
 		t->ip6rd.prefixlen = 16;
-- 
2.14.3


From 75357379dd792b591e6f5528ce502129e1ccce7d Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Mon, 5 Feb 2018 21:10:01 +0100
Subject: [PATCH 05/49] net: amd-xgbe: fix comparison to bitshift when dealing
 with a mask

[ Upstream commit a3276892db7a588bedc33168e502572008f714a9 ]

Due to a typo, the mask was destroyed by a comparison instead of a bit
shift.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Acked-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe-drv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 608693d11bd7..75c4455e2271 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -595,7 +595,7 @@ static void xgbe_isr_task(unsigned long data)
 
 		reissue_mask = 1 << 0;
 		if (!pdata->per_channel_irq)
-			reissue_mask |= 0xffff < 4;
+			reissue_mask |= 0xffff << 4;
 
 		XP_IOWRITE(pdata, XP_INT_REISSUE_EN, reissue_mask);
 	}
-- 
2.14.3


From 66a687442547235fd0ac78aeea5d214e7818efa2 Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Tue, 6 Feb 2018 19:17:06 -0600
Subject: [PATCH 06/49] net: ethernet: ti: cpsw: fix net watchdog timeout

[ Upstream commit 62f94c2101f35cd45775df00ba09bde77580e26a ]

It was discovered that simple program which indefinitely sends 200b UDP
packets and runs on TI AM574x SoC (SMP) under RT Kernel triggers network
watchdog timeout in TI CPSW driver (<6 hours run). The network watchdog
timeout is triggered due to race between cpsw_ndo_start_xmit() and
cpsw_tx_handler() [NAPI]

cpsw_ndo_start_xmit()
	if (unlikely(!cpdma_check_free_tx_desc(txch))) {
		txq = netdev_get_tx_queue(ndev, q_idx);
		netif_tx_stop_queue(txq);

^^ as per [1] barier has to be used after set_bit() otherwise new value
might not be visible to other cpus
	}

cpsw_tx_handler()
	if (unlikely(netif_tx_queue_stopped(txq)))
		netif_tx_wake_queue(txq);

and when it happens ndev TX queue became disabled forever while driver's HW
TX queue is empty.

Fix this, by adding smp_mb__after_atomic() after netif_tx_stop_queue()
calls and double check for free TX descriptors after stopping ndev TX queue
- if there are free TX descriptors wake up ndev TX queue.

[1] https://www.kernel.org/doc/html/latest/core-api/atomic_ops.html
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Reviewed-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index db8a4bcfc6c7..14b646b3b084 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -1618,6 +1618,7 @@ static netdev_tx_t cpsw_ndo_start_xmit(struct sk_buff *skb,
 		q_idx = q_idx % cpsw->tx_ch_num;
 
 	txch = cpsw->txv[q_idx].ch;
+	txq = netdev_get_tx_queue(ndev, q_idx);
 	ret = cpsw_tx_packet_submit(priv, skb, txch);
 	if (unlikely(ret != 0)) {
 		cpsw_err(priv, tx_err, "desc submit failed\n");
@@ -1628,15 +1629,26 @@ static netdev_tx_t cpsw_ndo_start_xmit(struct sk_buff *skb,
 	 * tell the kernel to stop sending us tx frames.
 	 */
 	if (unlikely(!cpdma_check_free_tx_desc(txch))) {
-		txq = netdev_get_tx_queue(ndev, q_idx);
 		netif_tx_stop_queue(txq);
+
+		/* Barrier, so that stop_queue visible to other cpus */
+		smp_mb__after_atomic();
+
+		if (cpdma_check_free_tx_desc(txch))
+			netif_tx_wake_queue(txq);
 	}
 
 	return NETDEV_TX_OK;
 fail:
 	ndev->stats.tx_dropped++;
-	txq = netdev_get_tx_queue(ndev, skb_get_queue_mapping(skb));
 	netif_tx_stop_queue(txq);
+
+	/* Barrier, so that stop_queue visible to other cpus */
+	smp_mb__after_atomic();
+
+	if (cpdma_check_free_tx_desc(txch))
+		netif_tx_wake_queue(txq);
+
 	return NETDEV_TX_BUSY;
 }
 
-- 
2.14.3


From 130097c1c86ece0154bff01a12ec8043c31939d0 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 12 Feb 2018 21:35:31 -0800
Subject: [PATCH 07/49] net: fix race on decreasing number of TX queues

[ Upstream commit ac5b70198adc25c73fba28de4f78adcee8f6be0b ]

netif_set_real_num_tx_queues() can be called when netdev is up.
That usually happens when user requests change of number of
channels/rings with ethtool -L.  The procedure for changing
the number of queues involves resetting the qdiscs and setting
dev->num_tx_queues to the new value.  When the new value is
lower than the old one, extra care has to be taken to ensure
ordering of accesses to the number of queues vs qdisc reset.

Currently the queues are reset before new dev->num_tx_queues
is assigned, leaving a window of time where packets can be
enqueued onto the queues going down, leading to a likely
crash in the drivers, since most drivers don't check if TX
skbs are assigned to an active queue.

Fixes: e6484930d7c7 ("net: allocate tx queues in register_netdevice")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index d33bbed640b1..c75ef9d8105a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2343,8 +2343,11 @@ EXPORT_SYMBOL(netdev_set_num_tc);
  */
 int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq)
 {
+	bool disabling;
 	int rc;
 
+	disabling = txq < dev->real_num_tx_queues;
+
 	if (txq < 1 || txq > dev->num_tx_queues)
 		return -EINVAL;
 
@@ -2360,15 +2363,19 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq)
 		if (dev->num_tc)
 			netif_setup_tc(dev, txq);
 
-		if (txq < dev->real_num_tx_queues) {
+		dev->real_num_tx_queues = txq;
+
+		if (disabling) {
+			synchronize_net();
 			qdisc_reset_all_tx_gt(dev, txq);
 #ifdef CONFIG_XPS
 			netif_reset_xps_queues_gt(dev, txq);
 #endif
 		}
+	} else {
+		dev->real_num_tx_queues = txq;
 	}
 
-	dev->real_num_tx_queues = txq;
 	return 0;
 }
 EXPORT_SYMBOL(netif_set_real_num_tx_queues);
-- 
2.14.3


From 356362d21324a696dc7af49a7684606fcfdfc7dc Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Mon, 26 Feb 2018 16:13:43 +0100
Subject: [PATCH 08/49] net: ipv4: don't allow setting net.ipv4.route.min_pmtu
 below 68

[ Upstream commit c7272c2f1229125f74f22dcdd59de9bbd804f1c8 ]

According to RFC 1191 sections 3 and 4, ICMP frag-needed messages
indicating an MTU below 68 should be rejected:

    A host MUST never reduce its estimate of the Path MTU below 68
    octets.

and (talking about ICMP frag-needed's Next-Hop MTU field):

    This field will never contain a value less than 68, since every
    router "must be able to forward a datagram of 68 octets without
    fragmentation".

Furthermore, by letting net.ipv4.route.min_pmtu be set to negative
values, we can end up with a very large PMTU when (-1) is cast into u32.

Let's also make ip_rt_min_pmtu a u32, since it's only ever compared to
unsigned ints.

Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 0ba88efca7ad..f4ad8fda8d9a 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -128,10 +128,13 @@ static int ip_rt_redirect_silence __read_mostly	= ((HZ / 50) << (9 + 1));
 static int ip_rt_error_cost __read_mostly	= HZ;
 static int ip_rt_error_burst __read_mostly	= 5 * HZ;
 static int ip_rt_mtu_expires __read_mostly	= 10 * 60 * HZ;
-static int ip_rt_min_pmtu __read_mostly		= 512 + 20 + 20;
+static u32 ip_rt_min_pmtu __read_mostly		= 512 + 20 + 20;
 static int ip_rt_min_advmss __read_mostly	= 256;
 
 static int ip_rt_gc_timeout __read_mostly	= RT_GC_TIMEOUT;
+
+static int ip_min_valid_pmtu __read_mostly	= IPV4_MIN_MTU;
+
 /*
  *	Interface to generic destination cache.
  */
@@ -2934,7 +2937,8 @@ static struct ctl_table ipv4_route_table[] = {
 		.data		= &ip_rt_min_pmtu,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &ip_min_valid_pmtu,
 	},
 	{
 		.procname	= "min_adv_mss",
-- 
2.14.3


From ec0410cfd41ac9cac4f3dbbb9bad719b90cf2a3d Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Tue, 6 Feb 2018 14:48:32 +0100
Subject: [PATCH 09/49] netlink: ensure to loop over all netns in
 genlmsg_multicast_allns()

[ Upstream commit cb9f7a9a5c96a773bbc9c70660dc600cfff82f82 ]

Nowadays, nlmsg_multicast() returns only 0 or -ESRCH but this was not the
case when commit 134e63756d5f was pushed.
However, there was no reason to stop the loop if a netns does not have
listeners.
Returns -ESRCH only if there was no listeners in all netns.

To avoid having the same problem in the future, I didn't take the
assumption that nlmsg_multicast() returns only 0 or -ESRCH.

Fixes: 134e63756d5f ("genetlink: make netns aware")
CC: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/genetlink.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index d444daf1ac04..6f02499ef007 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -1081,6 +1081,7 @@ static int genlmsg_mcast(struct sk_buff *skb, u32 portid, unsigned long group,
 {
 	struct sk_buff *tmp;
 	struct net *net, *prev = NULL;
+	bool delivered = false;
 	int err;
 
 	for_each_net_rcu(net) {
@@ -1092,14 +1093,21 @@ static int genlmsg_mcast(struct sk_buff *skb, u32 portid, unsigned long group,
 			}
 			err = nlmsg_multicast(prev->genl_sock, tmp,
 					      portid, group, flags);
-			if (err)
+			if (!err)
+				delivered = true;
+			else if (err != -ESRCH)
 				goto error;
 		}
 
 		prev = net;
 	}
 
-	return nlmsg_multicast(prev->genl_sock, skb, portid, group, flags);
+	err = nlmsg_multicast(prev->genl_sock, skb, portid, group, flags);
+	if (!err)
+		delivered = true;
+	else if (err != -ESRCH)
+		goto error;
+	return delivered ? 0 : -ESRCH;
  error:
 	kfree_skb(skb);
 	return err;
-- 
2.14.3


From 2c242ef058aac98bed5078b70071e2a896780c5c Mon Sep 17 00:00:00 2001
From: Roman Kapl <code@rkapl.cz>
Date: Mon, 19 Feb 2018 21:32:51 +0100
Subject: [PATCH 10/49] net: sched: report if filter is too large to dump

[ Upstream commit 5ae437ad5a2ed573b1ebb04e0afa70b8869f88dd ]

So far, if the filter was too large to fit in the allocated skb, the
kernel did not return any error and stopped dumping. Modify the dumper
so that it returns -EMSGSIZE when a filter fails to dump and it is the
first filter in the skb. If we are not first, we will get a next chance
with more room.

I understand this is pretty near to being an API change, but the
original design (silent truncation) can be considered a bug.

Note: The error case can happen pretty easily if you create a filter
with 32 actions and have 4kb pages. Also recent versions of iproute try
to be clever with their buffer allocation size, which in turn leads to

Signed-off-by: Roman Kapl <code@rkapl.cz>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 934c239cf98d..c2fab4bcb8be 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -871,13 +871,18 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
 		if (tca[TCA_CHAIN] &&
 		    nla_get_u32(tca[TCA_CHAIN]) != chain->index)
 			continue;
-		if (!tcf_chain_dump(chain, skb, cb, index_start, &index))
+		if (!tcf_chain_dump(chain, skb, cb, index_start, &index)) {
+			err = -EMSGSIZE;
 			break;
+		}
 	}
 
 	cb->args[0] = index;
 
 out:
+	/* If we did no progress, the error (EMSGSIZE) is real */
+	if (skb->len == 0 && err)
+		return err;
 	return skb->len;
 }
 
-- 
2.14.3


From 72c4949ae06b0875ad312e699323f970682f7d9f Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Fri, 2 Mar 2018 18:41:16 +0100
Subject: [PATCH 11/49] ppp: prevent unregistered channels from connecting to
 PPP units

[ Upstream commit 77f840e3e5f09c6d7d727e85e6e08276dd813d11 ]

PPP units don't hold any reference on the channels connected to it.
It is the channel's responsibility to ensure that it disconnects from
its unit before being destroyed.
In practice, this is ensured by ppp_unregister_channel() disconnecting
the channel from the unit before dropping a reference on the channel.

However, it is possible for an unregistered channel to connect to a PPP
unit: register a channel with ppp_register_net_channel(), attach a
/dev/ppp file to it with ioctl(PPPIOCATTCHAN), unregister the channel
with ppp_unregister_channel() and finally connect the /dev/ppp file to
a PPP unit with ioctl(PPPIOCCONNECT).

Once in this situation, the channel is only held by the /dev/ppp file,
which can be released at anytime and free the channel without letting
the parent PPP unit know. Then the ppp structure ends up with dangling
pointers in its ->channels list.

Prevent this scenario by forbidding unregistered channels from
connecting to PPP units. This maintains the code logic by keeping
ppp_unregister_channel() responsible from disconnecting the channel if
necessary and avoids modification on the reference counting mechanism.

This issue seems to predate git history (successfully reproduced on
Linux 2.6.26 and earlier PPP commits are unrelated).

Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/ppp_generic.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 8c6b8918ec31..38cd2e8fae23 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -3158,6 +3158,15 @@ ppp_connect_channel(struct channel *pch, int unit)
 		goto outl;
 
 	ppp_lock(ppp);
+	spin_lock_bh(&pch->downl);
+	if (!pch->chan) {
+		/* Don't connect unregistered channels */
+		spin_unlock_bh(&pch->downl);
+		ppp_unlock(ppp);
+		ret = -ENOTCONN;
+		goto outl;
+	}
+	spin_unlock_bh(&pch->downl);
 	if (pch->file.hdrlen > ppp->file.hdrlen)
 		ppp->file.hdrlen = pch->file.hdrlen;
 	hdrlen = pch->file.hdrlen + 2;	/* for protocol bytes */
-- 
2.14.3


From e9bf7130ebad4bc15c2dcaabc845d11b8eb67891 Mon Sep 17 00:00:00 2001
From: Alexey Kodanev <alexey.kodanev@oracle.com>
Date: Fri, 9 Feb 2018 17:35:23 +0300
Subject: [PATCH 12/49] sctp: verify size of a new chunk in _sctp_make_chunk()

[ Upstream commit 07f2c7ab6f8d0a7e7c5764c4e6cc9c52951b9d9c ]

When SCTP makes INIT or INIT_ACK packet the total chunk length
can exceed SCTP_MAX_CHUNK_LEN which leads to kernel panic when
transmitting these packets, e.g. the crash on sending INIT_ACK:

[  597.804948] skbuff: skb_over_panic: text:00000000ffae06e4 len:120168
               put:120156 head:000000007aa47635 data:00000000d991c2de
               tail:0x1d640 end:0xfec0 dev:<NULL>
...
[  597.976970] ------------[ cut here ]------------
[  598.033408] kernel BUG at net/core/skbuff.c:104!
[  600.314841] Call Trace:
[  600.345829]  <IRQ>
[  600.371639]  ? sctp_packet_transmit+0x2095/0x26d0 [sctp]
[  600.436934]  skb_put+0x16c/0x200
[  600.477295]  sctp_packet_transmit+0x2095/0x26d0 [sctp]
[  600.540630]  ? sctp_packet_config+0x890/0x890 [sctp]
[  600.601781]  ? __sctp_packet_append_chunk+0x3b4/0xd00 [sctp]
[  600.671356]  ? sctp_cmp_addr_exact+0x3f/0x90 [sctp]
[  600.731482]  sctp_outq_flush+0x663/0x30d0 [sctp]
[  600.788565]  ? sctp_make_init+0xbf0/0xbf0 [sctp]
[  600.845555]  ? sctp_check_transmitted+0x18f0/0x18f0 [sctp]
[  600.912945]  ? sctp_outq_tail+0x631/0x9d0 [sctp]
[  600.969936]  sctp_cmd_interpreter.isra.22+0x3be1/0x5cb0 [sctp]
[  601.041593]  ? sctp_sf_do_5_1B_init+0x85f/0xc30 [sctp]
[  601.104837]  ? sctp_generate_t1_cookie_event+0x20/0x20 [sctp]
[  601.175436]  ? sctp_eat_data+0x1710/0x1710 [sctp]
[  601.233575]  sctp_do_sm+0x182/0x560 [sctp]
[  601.284328]  ? sctp_has_association+0x70/0x70 [sctp]
[  601.345586]  ? sctp_rcv+0xef4/0x32f0 [sctp]
[  601.397478]  ? sctp6_rcv+0xa/0x20 [sctp]
...

Here the chunk size for INIT_ACK packet becomes too big, mostly
because of the state cookie (INIT packet has large size with
many address parameters), plus additional server parameters.

Later this chunk causes the panic in skb_put_data():

  skb_packet_transmit()
      sctp_packet_pack()
          skb_put_data(nskb, chunk->skb->data, chunk->skb->len);

'nskb' (head skb) was previously allocated with packet->size
from u16 'chunk->chunk_hdr->length'.

As suggested by Marcelo we should check the chunk's length in
_sctp_make_chunk() before trying to allocate skb for it and
discard a chunk if its size bigger than SCTP_MAX_CHUNK_LEN.

Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leinter@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sm_make_chunk.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 514465b03829..e4a400f88168 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -1378,9 +1378,14 @@ static struct sctp_chunk *_sctp_make_chunk(const struct sctp_association *asoc,
 	struct sctp_chunk *retval;
 	struct sk_buff *skb;
 	struct sock *sk;
+	int chunklen;
+
+	chunklen = SCTP_PAD4(sizeof(*chunk_hdr) + paylen);
+	if (chunklen > SCTP_MAX_CHUNK_LEN)
+		goto nodata;
 
 	/* No need to allocate LL here, as this is only a chunk. */
-	skb = alloc_skb(SCTP_PAD4(sizeof(*chunk_hdr) + paylen), gfp);
+	skb = alloc_skb(chunklen, gfp);
 	if (!skb)
 		goto nodata;
 
-- 
2.14.3


From d171cfc9b757cd194edd6bed18b41316fc11917e Mon Sep 17 00:00:00 2001
From: Alexey Kodanev <alexey.kodanev@oracle.com>
Date: Thu, 15 Feb 2018 20:18:43 +0300
Subject: [PATCH 13/49] udplite: fix partial checksum initialization

[ Upstream commit 15f35d49c93f4fa9875235e7bf3e3783d2dd7a1b ]

Since UDP-Lite is always using checksum, the following path is
triggered when calculating pseudo header for it:

  udp4_csum_init() or udp6_csum_init()
    skb_checksum_init_zero_check()
      __skb_checksum_validate_complete()

The problem can appear if skb->len is less than CHECKSUM_BREAK. In
this particular case __skb_checksum_validate_complete() also invokes
__skb_checksum_complete(skb). If UDP-Lite is using partial checksum
that covers only part of a packet, the function will return bad
checksum and the packet will be dropped.

It can be fixed if we skip skb_checksum_init_zero_check() and only
set the required pseudo header checksum for UDP-Lite with partial
checksum before udp4_csum_init()/udp6_csum_init() functions return.

Fixes: ed70fcfcee95 ("net: Call skb_checksum_init in IPv4")
Fixes: e4f45b7f40bd ("net: Call skb_checksum_init in IPv6")
Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/udplite.h   | 1 +
 net/ipv4/udp.c          | 5 +++++
 net/ipv6/ip6_checksum.c | 5 +++++
 3 files changed, 11 insertions(+)

diff --git a/include/net/udplite.h b/include/net/udplite.h
index 81bdbf97319b..9185e45b997f 100644
--- a/include/net/udplite.h
+++ b/include/net/udplite.h
@@ -64,6 +64,7 @@ static inline int udplite_checksum_init(struct sk_buff *skb, struct udphdr *uh)
 		UDP_SKB_CB(skb)->cscov = cscov;
 		if (skb->ip_summed == CHECKSUM_COMPLETE)
 			skb->ip_summed = CHECKSUM_NONE;
+		skb->csum_valid = 0;
         }
 
 	return 0;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index ebfbccae62fd..c79fa6f6b758 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2032,6 +2032,11 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh,
 		err = udplite_checksum_init(skb, uh);
 		if (err)
 			return err;
+
+		if (UDP_SKB_CB(skb)->partial_cov) {
+			skb->csum = inet_compute_pseudo(skb, proto);
+			return 0;
+		}
 	}
 
 	/* Note, we are only interested in != 0 or == 0, thus the
diff --git a/net/ipv6/ip6_checksum.c b/net/ipv6/ip6_checksum.c
index ec43d18b5ff9..547515e8450a 100644
--- a/net/ipv6/ip6_checksum.c
+++ b/net/ipv6/ip6_checksum.c
@@ -73,6 +73,11 @@ int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto)
 		err = udplite_checksum_init(skb, uh);
 		if (err)
 			return err;
+
+		if (UDP_SKB_CB(skb)->partial_cov) {
+			skb->csum = ip6_compute_pseudo(skb, proto);
+			return 0;
+		}
 	}
 
 	/* To support RFC 6936 (allow zero checksum in UDP/IPV6 for tunnels)
-- 
2.14.3


From 8a3d2cf81fb7ba196362a57da0599db837aea89b Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Wed, 20 Dec 2017 08:48:24 +0200
Subject: [PATCH 14/49] net/mlx5e: Fix TCP checksum in LRO buffers

[ Upstream commit 8babd44d2079079f9d5a4aca7005aed80236efe0 ]

When receiving an LRO packet, the checksum field is set by the hardware
to the checksum of the first coalesced packet. Obviously, this checksum
is not valid for the merged LRO packet and should be fixed.  We can use
the CQE checksum which covers the checksum of the entire merged packet
TCP payload to help us calculate the checksum incrementally.

Tested by sending IPv4/6 traffic with LRO enabled, RX checksum disabled
and watching nstat checksum error counters (in addition to the obvious
bandwidth drop caused by checksum errors).

This bug is usually "hidden" since LRO packets would go through the
CHECKSUM_UNNECESSARY flow which does not validate the packet checksum.

It's important to note that previous to this patch, LRO packets provided
with CHECKSUM_UNNECESSARY are indeed packets with a correct validated
checksum (even though the checksum inside the TCP header is incorrect),
since the hardware LRO aggregation is terminated upon receiving a packet
with bad checksum.

Fixes: e586b3b0baee ("net/mlx5: Ethernet Datapath files")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 49 ++++++++++++++++++-------
 1 file changed, 35 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 91b1b0938931..3476f594c195 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -36,6 +36,7 @@
 #include <linux/tcp.h>
 #include <linux/bpf_trace.h>
 #include <net/busy_poll.h>
+#include <net/ip6_checksum.h>
 #include "en.h"
 #include "en_tc.h"
 #include "eswitch.h"
@@ -546,20 +547,33 @@ bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq)
 	return true;
 }
 
+static void mlx5e_lro_update_tcp_hdr(struct mlx5_cqe64 *cqe, struct tcphdr *tcp)
+{
+	u8 l4_hdr_type = get_cqe_l4_hdr_type(cqe);
+	u8 tcp_ack     = (l4_hdr_type == CQE_L4_HDR_TYPE_TCP_ACK_NO_DATA) ||
+			 (l4_hdr_type == CQE_L4_HDR_TYPE_TCP_ACK_AND_DATA);
+
+	tcp->check                      = 0;
+	tcp->psh                        = get_cqe_lro_tcppsh(cqe);
+
+	if (tcp_ack) {
+		tcp->ack                = 1;
+		tcp->ack_seq            = cqe->lro_ack_seq_num;
+		tcp->window             = cqe->lro_tcp_win;
+	}
+}
+
 static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe,
 				 u32 cqe_bcnt)
 {
 	struct ethhdr	*eth = (struct ethhdr *)(skb->data);
 	struct tcphdr	*tcp;
 	int network_depth = 0;
+	__wsum check;
 	__be16 proto;
 	u16 tot_len;
 	void *ip_p;
 
-	u8 l4_hdr_type = get_cqe_l4_hdr_type(cqe);
-	u8 tcp_ack = (l4_hdr_type == CQE_L4_HDR_TYPE_TCP_ACK_NO_DATA) ||
-		(l4_hdr_type == CQE_L4_HDR_TYPE_TCP_ACK_AND_DATA);
-
 	skb->mac_len = ETH_HLEN;
 	proto = __vlan_get_protocol(skb, eth->h_proto, &network_depth);
 
@@ -577,23 +591,30 @@ static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe,
 		ipv4->check             = 0;
 		ipv4->check             = ip_fast_csum((unsigned char *)ipv4,
 						       ipv4->ihl);
+
+		mlx5e_lro_update_tcp_hdr(cqe, tcp);
+		check = csum_partial(tcp, tcp->doff * 4,
+				     csum_unfold((__force __sum16)cqe->check_sum));
+		/* Almost done, don't forget the pseudo header */
+		tcp->check = csum_tcpudp_magic(ipv4->saddr, ipv4->daddr,
+					       tot_len - sizeof(struct iphdr),
+					       IPPROTO_TCP, check);
 	} else {
+		u16 payload_len = tot_len - sizeof(struct ipv6hdr);
 		struct ipv6hdr *ipv6 = ip_p;
 
 		tcp = ip_p + sizeof(struct ipv6hdr);
 		skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
 
 		ipv6->hop_limit         = cqe->lro_min_ttl;
-		ipv6->payload_len       = cpu_to_be16(tot_len -
-						      sizeof(struct ipv6hdr));
-	}
-
-	tcp->psh = get_cqe_lro_tcppsh(cqe);
-
-	if (tcp_ack) {
-		tcp->ack                = 1;
-		tcp->ack_seq            = cqe->lro_ack_seq_num;
-		tcp->window             = cqe->lro_tcp_win;
+		ipv6->payload_len       = cpu_to_be16(payload_len);
+
+		mlx5e_lro_update_tcp_hdr(cqe, tcp);
+		check = csum_partial(tcp, tcp->doff * 4,
+				     csum_unfold((__force __sum16)cqe->check_sum));
+		/* Almost done, don't forget the pseudo header */
+		tcp->check = csum_ipv6_magic(&ipv6->saddr, &ipv6->daddr, payload_len,
+					     IPPROTO_TCP, check);
 	}
 }
 
-- 
2.14.3


From 43636fa56e7ced852734fa1dec210cab1494bdbc Mon Sep 17 00:00:00 2001
From: Tommi Rantala <tommi.t.rantala@nokia.com>
Date: Mon, 5 Feb 2018 21:48:14 +0200
Subject: [PATCH 15/49] sctp: fix dst refcnt leak in sctp_v4_get_dst

[ Upstream commit 4a31a6b19f9ddf498c81f5c9b089742b7472a6f8 ]

Fix dst reference count leak in sctp_v4_get_dst() introduced in commit
410f03831 ("sctp: add routing output fallback"):

When walking the address_list, successive ip_route_output_key() calls
may return the same rt->dst with the reference incremented on each call.

The code would not decrement the dst refcount when the dst pointer was
identical from the previous iteration, causing the dst refcnt leak.

Testcase:
  ip netns add TEST
  ip netns exec TEST ip link set lo up
  ip link add dummy0 type dummy
  ip link add dummy1 type dummy
  ip link add dummy2 type dummy
  ip link set dev dummy0 netns TEST
  ip link set dev dummy1 netns TEST
  ip link set dev dummy2 netns TEST
  ip netns exec TEST ip addr add 192.168.1.1/24 dev dummy0
  ip netns exec TEST ip link set dummy0 up
  ip netns exec TEST ip addr add 192.168.1.2/24 dev dummy1
  ip netns exec TEST ip link set dummy1 up
  ip netns exec TEST ip addr add 192.168.1.3/24 dev dummy2
  ip netns exec TEST ip link set dummy2 up
  ip netns exec TEST sctp_test -H 192.168.1.2 -P 20002 -h 192.168.1.1 -p 20000 -s -B 192.168.1.3
  ip netns del TEST

In 4.4 and 4.9 kernels this results to:
  [  354.179591] unregister_netdevice: waiting for lo to become free. Usage count = 1
  [  364.419674] unregister_netdevice: waiting for lo to become free. Usage count = 1
  [  374.663664] unregister_netdevice: waiting for lo to become free. Usage count = 1
  [  384.903717] unregister_netdevice: waiting for lo to become free. Usage count = 1
  [  395.143724] unregister_netdevice: waiting for lo to become free. Usage count = 1
  [  405.383645] unregister_netdevice: waiting for lo to become free. Usage count = 1
  ...

Fixes: 410f03831 ("sctp: add routing output fallback")
Fixes: 0ca50d12f ("sctp: fix src address selection if using secondary addresses")
Signed-off-by: Tommi Rantala <tommi.t.rantala@nokia.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/protocol.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index fcd80feb293f..df22a9c352ad 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -514,22 +514,20 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 		if (IS_ERR(rt))
 			continue;
 
-		if (!dst)
-			dst = &rt->dst;
-
 		/* Ensure the src address belongs to the output
 		 * interface.
 		 */
 		odev = __ip_dev_find(sock_net(sk), laddr->a.v4.sin_addr.s_addr,
 				     false);
 		if (!odev || odev->ifindex != fl4->flowi4_oif) {
-			if (&rt->dst != dst)
+			if (!dst)
+				dst = &rt->dst;
+			else
 				dst_release(&rt->dst);
 			continue;
 		}
 
-		if (dst != &rt->dst)
-			dst_release(dst);
+		dst_release(dst);
 		dst = &rt->dst;
 		break;
 	}
-- 
2.14.3


From 7b21fae6d3877cdb9826344acbacf56a1db646fe Mon Sep 17 00:00:00 2001
From: Shalom Toledo <shalomt@mellanox.com>
Date: Thu, 1 Mar 2018 11:37:05 +0100
Subject: [PATCH 16/49] mlxsw: spectrum_switchdev: Check success of FDB add
 operation

[ Upstream commit 0a8a1bf17e3af34f1f8d2368916a6327f8b3bfd5 ]

Until now, we assumed that in case of error when adding FDB entries, the
write operation will fail, but this is not the case. Instead, we need to
check that the number of entries reported in the response is equal to
the number of entries specified in the request.

Fixes: 56ade8fe3fe1 ("mlxsw: spectrum: Add initial support for Spectrum ASIC")
Reported-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Shalom Toledo <shalomt@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/spectrum_switchdev.c   | 29 ++++++++++++++++++++--
 1 file changed, 27 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index f5863e5bec81..42a6afcaae03 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -1098,6 +1098,7 @@ static int __mlxsw_sp_port_fdb_uc_op(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 				     bool dynamic)
 {
 	char *sfd_pl;
+	u8 num_rec;
 	int err;
 
 	sfd_pl = kmalloc(MLXSW_REG_SFD_LEN, GFP_KERNEL);
@@ -1107,9 +1108,16 @@ static int __mlxsw_sp_port_fdb_uc_op(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 	mlxsw_reg_sfd_pack(sfd_pl, mlxsw_sp_sfd_op(adding), 0);
 	mlxsw_reg_sfd_uc_pack(sfd_pl, 0, mlxsw_sp_sfd_rec_policy(dynamic),
 			      mac, fid, action, local_port);
+	num_rec = mlxsw_reg_sfd_num_rec_get(sfd_pl);
 	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfd), sfd_pl);
-	kfree(sfd_pl);
+	if (err)
+		goto out;
+
+	if (num_rec != mlxsw_reg_sfd_num_rec_get(sfd_pl))
+		err = -EBUSY;
 
+out:
+	kfree(sfd_pl);
 	return err;
 }
 
@@ -1134,6 +1142,7 @@ static int mlxsw_sp_port_fdb_uc_lag_op(struct mlxsw_sp *mlxsw_sp, u16 lag_id,
 				       bool adding, bool dynamic)
 {
 	char *sfd_pl;
+	u8 num_rec;
 	int err;
 
 	sfd_pl = kmalloc(MLXSW_REG_SFD_LEN, GFP_KERNEL);
@@ -1144,9 +1153,16 @@ static int mlxsw_sp_port_fdb_uc_lag_op(struct mlxsw_sp *mlxsw_sp, u16 lag_id,
 	mlxsw_reg_sfd_uc_lag_pack(sfd_pl, 0, mlxsw_sp_sfd_rec_policy(dynamic),
 				  mac, fid, MLXSW_REG_SFD_REC_ACTION_NOP,
 				  lag_vid, lag_id);
+	num_rec = mlxsw_reg_sfd_num_rec_get(sfd_pl);
 	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfd), sfd_pl);
-	kfree(sfd_pl);
+	if (err)
+		goto out;
+
+	if (num_rec != mlxsw_reg_sfd_num_rec_get(sfd_pl))
+		err = -EBUSY;
 
+out:
+	kfree(sfd_pl);
 	return err;
 }
 
@@ -1191,6 +1207,7 @@ static int mlxsw_sp_port_mdb_op(struct mlxsw_sp *mlxsw_sp, const char *addr,
 				u16 fid, u16 mid, bool adding)
 {
 	char *sfd_pl;
+	u8 num_rec;
 	int err;
 
 	sfd_pl = kmalloc(MLXSW_REG_SFD_LEN, GFP_KERNEL);
@@ -1200,7 +1217,15 @@ static int mlxsw_sp_port_mdb_op(struct mlxsw_sp *mlxsw_sp, const char *addr,
 	mlxsw_reg_sfd_pack(sfd_pl, mlxsw_sp_sfd_op(adding), 0);
 	mlxsw_reg_sfd_mc_pack(sfd_pl, 0, addr, fid,
 			      MLXSW_REG_SFD_REC_ACTION_NOP, mid);
+	num_rec = mlxsw_reg_sfd_num_rec_get(sfd_pl);
 	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfd), sfd_pl);
+	if (err)
+		goto out;
+
+	if (num_rec != mlxsw_reg_sfd_num_rec_get(sfd_pl))
+		err = -EBUSY;
+
+out:
 	kfree(sfd_pl);
 	return err;
 }
-- 
2.14.3


From b08415397ae689f9b38735a17d146a0b8b8a1956 Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Thu, 25 Jan 2018 18:00:41 +0200
Subject: [PATCH 17/49] net/mlx5e: Specify numa node when allocating drop rq

[ Upstream commit 2f0db87901698cd73d828cc6fb1957b8916fc911 ]

When allocating a drop rq, no numa node is explicitly set which means
allocations are done on node zero. This is not necessarily the nearest
numa node to the HCA, and even worse, might even be a memoryless numa
node.

Choose the numa_node given to us by the pci device in order to properly
allocate the coherent dma memory instead of assuming zero is valid.

Fixes: 556dd1b9c313 ("net/mlx5e: Set drop RQ's necessary parameters only")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 3cdb932cae76..a863572882b2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1918,13 +1918,16 @@ static void mlx5e_build_rq_param(struct mlx5e_priv *priv,
 	param->wq.linear = 1;
 }
 
-static void mlx5e_build_drop_rq_param(struct mlx5e_rq_param *param)
+static void mlx5e_build_drop_rq_param(struct mlx5_core_dev *mdev,
+				      struct mlx5e_rq_param *param)
 {
 	void *rqc = param->rqc;
 	void *wq = MLX5_ADDR_OF(rqc, rqc, wq);
 
 	MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_LINKED_LIST);
 	MLX5_SET(wq, wq, log_wq_stride,    ilog2(sizeof(struct mlx5e_rx_wqe)));
+
+	param->wq.buf_numa_node = dev_to_node(&mdev->pdev->dev);
 }
 
 static void mlx5e_build_sq_param_common(struct mlx5e_priv *priv,
@@ -2778,6 +2781,9 @@ static int mlx5e_alloc_drop_cq(struct mlx5_core_dev *mdev,
 			       struct mlx5e_cq *cq,
 			       struct mlx5e_cq_param *param)
 {
+	param->wq.buf_numa_node = dev_to_node(&mdev->pdev->dev);
+	param->wq.db_numa_node  = dev_to_node(&mdev->pdev->dev);
+
 	return mlx5e_alloc_cq_common(mdev, param, cq);
 }
 
@@ -2789,7 +2795,7 @@ static int mlx5e_open_drop_rq(struct mlx5_core_dev *mdev,
 	struct mlx5e_cq *cq = &drop_rq->cq;
 	int err;
 
-	mlx5e_build_drop_rq_param(&rq_param);
+	mlx5e_build_drop_rq_param(mdev, &rq_param);
 
 	err = mlx5e_alloc_drop_cq(mdev, cq, &cq_param);
 	if (err)
-- 
2.14.3


From fa96954966d7080b77a34ecadd1f79fda6285f5f Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 8 Feb 2018 21:01:48 +0100
Subject: [PATCH 18/49] net: phy: fix phy_start to consider
 PHY_IGNORE_INTERRUPT

[ Upstream commit 08f5138512180a479ce6b9d23b825c9f4cd3be77 ]

This condition wasn't adjusted when PHY_IGNORE_INTERRUPT (-2) was added
long ago. In case of PHY_IGNORE_INTERRUPT the MAC interrupt indicates
also PHY state changes and we should do what the symbol says.

Fixes: 84a527a41f38 ("net: phylib: fix interrupts re-enablement in phy_start")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 2b1e67bc1e73..3d860de5e342 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -842,7 +842,7 @@ void phy_start(struct phy_device *phydev)
 		break;
 	case PHY_HALTED:
 		/* make sure interrupts are re-enabled for the PHY */
-		if (phydev->irq != PHY_POLL) {
+		if (phy_interrupt_is_valid(phydev)) {
 			err = phy_enable_interrupts(phydev);
 			if (err < 0)
 				break;
-- 
2.14.3


From 4526f3a5e96c6a7cfbc8c0d509db449646078e76 Mon Sep 17 00:00:00 2001
From: Ilya Lesokhin <ilyal@mellanox.com>
Date: Mon, 12 Feb 2018 12:57:04 +0200
Subject: [PATCH 19/49] tcp: Honor the eor bit in tcp_mtu_probe

[ Upstream commit 808cf9e38cd7923036a99f459ccc8cf2955e47af ]

Avoid SKB coalescing if eor bit is set in one of the relevant
SKBs.

Fixes: c134ecb87817 ("tcp: Make use of MSG_EOR in tcp_sendmsg")
Signed-off-by: Ilya Lesokhin <ilyal@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index cd3d60bb7cc8..7c1456bfa50e 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1973,6 +1973,24 @@ static inline void tcp_mtu_check_reprobe(struct sock *sk)
 	}
 }
 
+static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len)
+{
+	struct sk_buff *skb, *next;
+
+	skb = tcp_send_head(sk);
+	tcp_for_write_queue_from_safe(skb, next, sk) {
+		if (len <= skb->len)
+			break;
+
+		if (unlikely(TCP_SKB_CB(skb)->eor))
+			return false;
+
+		len -= skb->len;
+	}
+
+	return true;
+}
+
 /* Create a new MTU probe if we are ready.
  * MTU probe is regularly attempting to increase the path MTU by
  * deliberately sending larger packets.  This discovers routing
@@ -2045,6 +2063,9 @@ static int tcp_mtu_probe(struct sock *sk)
 			return 0;
 	}
 
+	if (!tcp_can_coalesce_send_queue_head(sk, probe_size))
+		return -1;
+
 	/* We're allowed to probe.  Build it now. */
 	nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC, false);
 	if (!nskb)
@@ -2080,6 +2101,10 @@ static int tcp_mtu_probe(struct sock *sk)
 			/* We've eaten all the data from this skb.
 			 * Throw it away. */
 			TCP_SKB_CB(nskb)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags;
+			/* If this is the last SKB we copy and eor is set
+			 * we need to propagate it to the new skb.
+			 */
+			TCP_SKB_CB(nskb)->eor = TCP_SKB_CB(skb)->eor;
 			tcp_unlink_write_queue(skb, sk);
 			sk_wmem_free_skb(sk, skb);
 		} else {
-- 
2.14.3


From f29bdfa2ff8abcc1bfaec1c3ca3fce5116073357 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 22 Feb 2018 14:38:14 +0000
Subject: [PATCH 20/49] rxrpc: Fix send in rxrpc_send_data_packet()

[ Upstream commit 93c62c45ed5fad1b87e3a45835b251cd68de9c46 ]

All the kernel_sendmsg() calls in rxrpc_send_data_packet() need to send
both parts of the iov[] buffer, but one of them does not.  Fix it so that
it does.

Without this, short IPv6 rxrpc DATA packets may be seen that have the rxrpc
header included, but no payload.

Fixes: 5a924b8951f8 ("rxrpc: Don't store the rxrpc header in the Tx queue sk_buffs")
Reported-by: Marc Dionne <marc.dionne@auristor.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/output.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index 71e6f713fbe7..5b67cb5d47f0 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -395,7 +395,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
 					(char *)&opt, sizeof(opt));
 		if (ret == 0) {
 			ret = kernel_sendmsg(conn->params.local->socket, &msg,
-					     iov, 1, iov[0].iov_len);
+					     iov, 2, len);
 
 			opt = IPV6_PMTUDISC_DO;
 			kernel_setsockopt(conn->params.local->socket,
-- 
2.14.3


From 53490d6be58587cc910ae76ce8acc6aac09e3c31 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 21 Feb 2018 06:43:03 -0800
Subject: [PATCH 21/49] tcp_bbr: better deal with suboptimal GSO
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 350c9f484bde93ef229682eedd98cd5f74350f7f ]

BBR uses tcp_tso_autosize() in an attempt to probe what would be the
burst sizes and to adjust cwnd in bbr_target_cwnd() with following
gold formula :

/* Allow enough full-sized skbs in flight to utilize end systems. */
cwnd += 3 * bbr->tso_segs_goal;

But GSO can be lacking or be constrained to very small
units (ip link set dev ... gso_max_segs 2)

What we really want is to have enough packets in flight so that both
GSO and GRO are efficient.

So in the case GSO is off or downgraded, we still want to have the same
number of packets in flight as if GSO/TSO was fully operational, so
that GRO can hopefully be working efficiently.

To fix this issue, we make tcp_tso_autosize() unaware of
sk->sk_gso_max_segs

Only tcp_tso_segs() has to enforce the gso_max_segs limit.

Tested:

ethtool -K eth0 tso off gso off
tc qd replace dev eth0 root pfifo_fast

Before patch:
for f in {1..5}; do ./super_netperf 1 -H lpaa24 -- -K bbr; done
    691  (ss -temoi shows cwnd is stuck around 6 )
    667
    651
    631
    517

After patch :
# for f in {1..5}; do ./super_netperf 1 -H lpaa24 -- -K bbr; done
   1733 (ss -temoi shows cwnd is around 386 )
   1778
   1746
   1781
   1718

Fixes: 0f8782ea1497 ("tcp_bbr: add BBR congestion control")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 7c1456bfa50e..83d11cd2eb65 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1681,7 +1681,7 @@ u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now,
 	 */
 	segs = max_t(u32, bytes / mss_now, min_tso_segs);
 
-	return min_t(u32, segs, sk->sk_gso_max_segs);
+	return segs;
 }
 EXPORT_SYMBOL(tcp_tso_autosize);
 
@@ -1693,8 +1693,10 @@ static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now)
 	const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops;
 	u32 tso_segs = ca_ops->tso_segs_goal ? ca_ops->tso_segs_goal(sk) : 0;
 
-	return tso_segs ? :
-		tcp_tso_autosize(sk, mss_now, sysctl_tcp_min_tso_segs);
+	if (!tso_segs)
+		tso_segs = tcp_tso_autosize(sk, mss_now,
+					    sysctl_tcp_min_tso_segs);
+	return min_t(u32, tso_segs, sk->sk_gso_max_segs);
 }
 
 /* Returns the portion of skb which can be sent right away */
-- 
2.14.3


From 2ecceeecc279348fcba5744d315967e54964ab61 Mon Sep 17 00:00:00 2001
From: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Date: Sun, 4 Feb 2018 18:07:10 -0800
Subject: [PATCH 22/49] doc: Change the min default value of tcp_wmem/tcp_rmem.

[ Upstream commit a61a86f8db92923a2a4c857c49a795bcae754497 ]

The SK_MEM_QUANTUM was changed from PAGE_SIZE to 4096. And the
tcp_wmem/tcp_rmem min default values are 4096.

Fixes: bd68a2a854ad ("net: set SK_MEM_QUANTUM to 4096")
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 77f4de59dc9c..d499676890d8 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -508,7 +508,7 @@ tcp_rmem - vector of 3 INTEGERs: min, default, max
 	min: Minimal size of receive buffer used by TCP sockets.
 	It is guaranteed to each TCP socket, even under moderate memory
 	pressure.
-	Default: 1 page
+	Default: 4K
 
 	default: initial size of receive buffer used by TCP sockets.
 	This value overrides net.core.rmem_default used by other protocols.
@@ -666,7 +666,7 @@ tcp_window_scaling - BOOLEAN
 tcp_wmem - vector of 3 INTEGERs: min, default, max
 	min: Amount of memory reserved for send buffers for TCP sockets.
 	Each TCP socket has rights to use it due to fact of its birth.
-	Default: 1 page
+	Default: 4K
 
 	default: initial size of send buffer used by TCP sockets.  This
 	value overrides net.core.wmem_default used by other protocols.
-- 
2.14.3


From f88c09f3ddb63e5d6813cb6a587734bffd1e052b Mon Sep 17 00:00:00 2001
From: Inbar Karmy <inbark@mellanox.com>
Date: Thu, 7 Dec 2017 17:26:33 +0200
Subject: [PATCH 23/49] net/mlx5e: Fix loopback self test when GRO is off

[ Upstream commit ef7a3518f7dd4f4cf5e5b5358c93d1eb78df28fb ]

When GRO is off, the transport header pointer in sk_buff is
initialized to network's header.

To find the udp header, instead of using udp_hdr() which assumes
skb_network_header was set, manually calculate the udp header offset.

Fixes: 0952da791c97 ("net/mlx5e: Add support for loopback selftest")
Signed-off-by: Inbar Karmy <inbark@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
index 5a4608281f38..707976482c09 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
@@ -216,7 +216,8 @@ mlx5e_test_loopback_validate(struct sk_buff *skb,
 	if (iph->protocol != IPPROTO_UDP)
 		goto out;
 
-	udph = udp_hdr(skb);
+	/* Don't assume skb_transport_header() was set */
+	udph = (struct udphdr *)((u8 *)iph + 4 * iph->ihl);
 	if (udph->dest != htons(9))
 		goto out;
 
-- 
2.14.3


From 965ca04938a4abcfa8be6fdef6a7bca32d85c073 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 22 Feb 2018 19:45:27 -0800
Subject: [PATCH 24/49] net_sched: gen_estimator: fix broken estimators based
 on percpu stats

[ Upstream commit a5f7add332b4ea6d4b9480971b3b0f5e66466ae9 ]

pfifo_fast got percpu stats lately, uncovering a bug I introduced last
year in linux-4.10.

I missed the fact that we have to clear our temporary storage
before calling __gnet_stats_copy_basic() in the case of percpu stats.

Without this fix, rate estimators (tc qd replace dev xxx root est 1sec
4sec pfifo_fast) are utterly broken.

Fixes: 1c0d32fde5bd ("net_sched: gen_estimator: complete rewrite of rate estimators")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/gen_estimator.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c
index 00ecec4891f3..7f980bd7426e 100644
--- a/net/core/gen_estimator.c
+++ b/net/core/gen_estimator.c
@@ -66,6 +66,7 @@ struct net_rate_estimator {
 static void est_fetch_counters(struct net_rate_estimator *e,
 			       struct gnet_stats_basic_packed *b)
 {
+	memset(b, 0, sizeof(*b));
 	if (e->stats_lock)
 		spin_lock(e->stats_lock);
 
-- 
2.14.3


From ba5b3cc07c41eeda831f74ef9f384db74ec61de4 Mon Sep 17 00:00:00 2001
From: Ivan Vecera <ivecera@redhat.com>
Date: Thu, 8 Feb 2018 16:10:39 +0100
Subject: [PATCH 25/49] net/sched: cls_u32: fix cls_u32 on filter replace

[ Upstream commit eb53f7af6f15285e2f6ada97285395343ce9f433 ]

The following sequence is currently broken:

 # tc qdisc add dev foo ingress
 # tc filter replace dev foo protocol all ingress \
   u32 match u8 0 0 action mirred egress mirror dev bar1
 # tc filter replace dev foo protocol all ingress \
   handle 800::800 pref 49152 \
   u32 match u8 0 0 action mirred egress mirror dev bar2
 Error: cls_u32: Key node flags do not match passed flags.
 We have an error talking to the kernel, -1

The error comes from u32_change() when comparing new and
existing flags. The existing ones always contains one of
TCA_CLS_FLAGS_{,NOT}_IN_HW flag depending on offloading state.
These flags cannot be passed from userspace so the condition
(n->flags != flags) in u32_change() always fails.

Fix the condition so the flags TCA_CLS_FLAGS_NOT_IN_HW and
TCA_CLS_FLAGS_IN_HW are not taken into account.

Fixes: 24d3dc6d27ea ("net/sched: cls_u32: Reflect HW offload status")
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_u32.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index b58eccb21f03..1ce7c1763e81 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -927,7 +927,8 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 		if (TC_U32_KEY(n->handle) == 0)
 			return -EINVAL;
 
-		if (n->flags != flags)
+		if ((n->flags ^ flags) &
+		    ~(TCA_CLS_FLAGS_IN_HW | TCA_CLS_FLAGS_NOT_IN_HW))
 			return -EINVAL;
 
 		new = u32_init_knode(tp, n);
-- 
2.14.3


From a5cb6a9ce26c4235406e66a0a1af1746aeebcf0d Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 12 Feb 2018 18:29:06 +0800
Subject: [PATCH 26/49] sctp: do not pr_err for the duplicated node in
 transport rhlist

[ Upstream commit 27af86bb038d9c8b8066cd17854ddaf2ea92bce1 ]

The pr_err in sctp_hash_transport was supposed to report a sctp bug
for using rhashtable/rhlist.

The err '-EEXIST' introduced in Commit cd2b70875058 ("sctp: check
duplicate node before inserting a new transport") doesn't belong
to that case.

So just return -EEXIST back without pr_err any kmsg.

Fixes: cd2b70875058 ("sctp: check duplicate node before inserting a new transport")
Reported-by: Wei Chen <weichen@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/input.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/net/sctp/input.c b/net/sctp/input.c
index 141c9c466ec1..0247cc432e02 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -897,15 +897,12 @@ int sctp_hash_transport(struct sctp_transport *t)
 	rhl_for_each_entry_rcu(transport, tmp, list, node)
 		if (transport->asoc->ep == t->asoc->ep) {
 			rcu_read_unlock();
-			err = -EEXIST;
-			goto out;
+			return -EEXIST;
 		}
 	rcu_read_unlock();
 
 	err = rhltable_insert_key(&sctp_transport_hashtable, &arg,
 				  &t->node, sctp_hash_params);
-
-out:
 	if (err)
 		pr_err_once("insert transport fail, errno %d\n", err);
 
-- 
2.14.3


From a245dc6b555e529f8119c115d788c2c062fe96eb Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Tue, 27 Feb 2018 14:15:01 -0800
Subject: [PATCH 27/49] tcp: revert F-RTO middle-box workaround

[ Upstream commit d4131f09770d9b7471c9da65e6ecd2477746ac5c ]

This reverts commit cc663f4d4c97b7297fb45135ab23cfd508b35a77. While fixing
some broken middle-boxes that modifies receive window fields, it does not
address middle-boxes that strip off SACK options. The best solution is
to fully revert this patch and the root F-RTO enhancement.

Fixes: cc663f4d4c97 ("tcp: restrict F-RTO to work-around broken middle-boxes")
Reported-by: Teodor Milkov <tm@del.bg>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 17 +++++++----------
 1 file changed, 7 insertions(+), 10 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index d9d215e27b8a..1b50a392711b 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1947,7 +1947,6 @@ void tcp_enter_loss(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct net *net = sock_net(sk);
 	struct sk_buff *skb;
-	bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery;
 	bool is_reneg;			/* is receiver reneging on SACKs? */
 	bool mark_lost;
 
@@ -2010,17 +2009,15 @@ void tcp_enter_loss(struct sock *sk)
 	tp->high_seq = tp->snd_nxt;
 	tcp_ecn_queue_cwr(tp);
 
-	/* F-RTO RFC5682 sec 3.1 step 1: retransmit SND.UNA if no previous
-	 * loss recovery is underway except recurring timeout(s) on
-	 * the same SND.UNA (sec 3.2). Disable F-RTO on path MTU probing
-	 *
-	 * In theory F-RTO can be used repeatedly during loss recovery.
-	 * In practice this interacts badly with broken middle-boxes that
-	 * falsely raise the receive window, which results in repeated
-	 * timeouts and stop-and-go behavior.
+	/* F-RTO RFC5682 sec 3.1 step 1 mandates to disable F-RTO
+	 * if a previous recovery is underway, otherwise it may incorrectly
+	 * call a timeout spurious if some previously retransmitted packets
+	 * are s/acked (sec 3.2). We do not apply that retriction since
+	 * retransmitted skbs are permanently tagged with TCPCB_EVER_RETRANS
+	 * so FLAG_ORIG_SACK_ACKED is always correct. But we do disable F-RTO
+	 * on PTMU discovery to avoid sending new data.
 	 */
 	tp->frto = sysctl_tcp_frto &&
-		   (new_recovery || icsk->icsk_retransmits) &&
 		   !inet_csk(sk)->icsk_mtup.probe_size;
 }
 
-- 
2.14.3


From f6b5adaa38d8c1acd9ebf44634345e756e6cf4e4 Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Tue, 27 Feb 2018 14:15:02 -0800
Subject: [PATCH 28/49] tcp: revert F-RTO extension to detect more spurious
 timeouts

[ Upstream commit fc68e171d376c322e6777a3d7ac2f0278b68b17f ]

This reverts commit 89fe18e44f7ee5ab1c90d0dff5835acee7751427.

While the patch could detect more spurious timeouts, it could cause
poor TCP performance on broken middle-boxes that modifies TCP packets
(e.g. receive window, SACK options). Since the performance gain is
much smaller compared to the potential loss. The best solution is
to fully revert the change.

Fixes: 89fe18e44f7e ("tcp: extend F-RTO to catch more spurious timeouts")
Reported-by: Teodor Milkov <tm@del.bg>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 30 ++++++++++++------------------
 1 file changed, 12 insertions(+), 18 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 1b50a392711b..93c614138f0f 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1947,6 +1947,7 @@ void tcp_enter_loss(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct net *net = sock_net(sk);
 	struct sk_buff *skb;
+	bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery;
 	bool is_reneg;			/* is receiver reneging on SACKs? */
 	bool mark_lost;
 
@@ -2009,15 +2010,12 @@ void tcp_enter_loss(struct sock *sk)
 	tp->high_seq = tp->snd_nxt;
 	tcp_ecn_queue_cwr(tp);
 
-	/* F-RTO RFC5682 sec 3.1 step 1 mandates to disable F-RTO
-	 * if a previous recovery is underway, otherwise it may incorrectly
-	 * call a timeout spurious if some previously retransmitted packets
-	 * are s/acked (sec 3.2). We do not apply that retriction since
-	 * retransmitted skbs are permanently tagged with TCPCB_EVER_RETRANS
-	 * so FLAG_ORIG_SACK_ACKED is always correct. But we do disable F-RTO
-	 * on PTMU discovery to avoid sending new data.
+	/* F-RTO RFC5682 sec 3.1 step 1: retransmit SND.UNA if no previous
+	 * loss recovery is underway except recurring timeout(s) on
+	 * the same SND.UNA (sec 3.2). Disable F-RTO on path MTU probing
 	 */
 	tp->frto = sysctl_tcp_frto &&
+		   (new_recovery || icsk->icsk_retransmits) &&
 		   !inet_csk(sk)->icsk_mtup.probe_size;
 }
 
@@ -2696,18 +2694,14 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack,
 	    tcp_try_undo_loss(sk, false))
 		return;
 
-	/* The ACK (s)acks some never-retransmitted data meaning not all
-	 * the data packets before the timeout were lost. Therefore we
-	 * undo the congestion window and state. This is essentially
-	 * the operation in F-RTO (RFC5682 section 3.1 step 3.b). Since
-	 * a retransmitted skb is permantly marked, we can apply such an
-	 * operation even if F-RTO was not used.
-	 */
-	if ((flag & FLAG_ORIG_SACK_ACKED) &&
-	    tcp_try_undo_loss(sk, tp->undo_marker))
-		return;
-
 	if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */
+		/* Step 3.b. A timeout is spurious if not all data are
+		 * lost, i.e., never-retransmitted data are (s)acked.
+		 */
+		if ((flag & FLAG_ORIG_SACK_ACKED) &&
+		    tcp_try_undo_loss(sk, true))
+			return;
+
 		if (after(tp->snd_nxt, tp->high_seq)) {
 			if (flag & FLAG_DATA_SACKED || is_dupack)
 				tp->frto = 0; /* Step 3.a. loss was real */
-- 
2.14.3


From 820d4b285c531872fc58bf4f339432ab053f0803 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Tue, 13 Feb 2018 11:22:42 +0100
Subject: [PATCH 29/49] mlxsw: spectrum_router: Fix error path in
 mlxsw_sp_vr_create

[ Upstream commit 0f2d2b2736b08dafa3bde31d048750fbc8df3a31 ]

Since mlxsw_sp_fib_create() and mlxsw_sp_mr_table_create()
use ERR_PTR macro to propagate int err through return of a pointer,
the return value is not NULL in case of failure. So if one
of the calls fails, one of vr->fib4, vr->fib6 or vr->mr4_table
is not NULL and mlxsw_sp_vr_is_used wrongly assumes
that vr is in use which leads to crash like following one:

[ 1293.949291] BUG: unable to handle kernel NULL pointer dereference at 00000000000006c9
[ 1293.952729] IP: mlxsw_sp_mr_table_flush+0x15/0x70 [mlxsw_spectrum]

Fix this by using local variables to hold the pointers and set vr->*
only in case everything went fine.

Fixes: 76610ebbde18 ("mlxsw: spectrum_router: Refactor virtual router handling")
Fixes: a3d9bc506d64 ("mlxsw: spectrum_router: Extend virtual routers with IPv6 support")
Fixes: d42b0965b1d4 ("mlxsw: spectrum_router: Add multicast routes notification handling functionality")
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 7bef80676464..c6eceb8f788b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -729,26 +729,29 @@ static struct mlxsw_sp_fib *mlxsw_sp_vr_fib(const struct mlxsw_sp_vr *vr,
 static struct mlxsw_sp_vr *mlxsw_sp_vr_create(struct mlxsw_sp *mlxsw_sp,
 					      u32 tb_id)
 {
+	struct mlxsw_sp_fib *fib4;
+	struct mlxsw_sp_fib *fib6;
 	struct mlxsw_sp_vr *vr;
 	int err;
 
 	vr = mlxsw_sp_vr_find_unused(mlxsw_sp);
 	if (!vr)
 		return ERR_PTR(-EBUSY);
-	vr->fib4 = mlxsw_sp_fib_create(vr, MLXSW_SP_L3_PROTO_IPV4);
-	if (IS_ERR(vr->fib4))
-		return ERR_CAST(vr->fib4);
-	vr->fib6 = mlxsw_sp_fib_create(vr, MLXSW_SP_L3_PROTO_IPV6);
-	if (IS_ERR(vr->fib6)) {
-		err = PTR_ERR(vr->fib6);
+	fib4 = mlxsw_sp_fib_create(vr, MLXSW_SP_L3_PROTO_IPV4);
+	if (IS_ERR(fib4))
+		return ERR_CAST(fib4);
+	fib6 = mlxsw_sp_fib_create(vr, MLXSW_SP_L3_PROTO_IPV6);
+	if (IS_ERR(fib6)) {
+		err = PTR_ERR(fib6);
 		goto err_fib6_create;
 	}
+	vr->fib4 = fib4;
+	vr->fib6 = fib6;
 	vr->tb_id = tb_id;
 	return vr;
 
 err_fib6_create:
-	mlxsw_sp_fib_destroy(vr->fib4);
-	vr->fib4 = NULL;
+	mlxsw_sp_fib_destroy(fib4);
 	return ERR_PTR(err);
 }
 
-- 
2.14.3


From d1810e632d1c21c180abd08fcc02059c470ba488 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 21 Feb 2018 11:00:54 -0800
Subject: [PATCH 30/49] net: ipv4: Set addr_type in hash_keys for forwarded
 case

[ Upstream commit 1fe4b1184c2ae2bfbf9e8b14c9c0c1945c98f205 ]

The result of the skb flow dissect is copied from keys to hash_keys to
ensure only the intended data is hashed. The original L4 hash patch
overlooked setting the addr_type for this case; add it.

Fixes: bf4e0a3db97eb ("net: ipv4: add support for ECMP hash policy choice")
Reported-by: Ido Schimmel <idosch@idosch.org>
Signed-off-by: David Ahern <dsahern@gmail.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index f4ad8fda8d9a..9ff06c5051ae 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1832,6 +1832,8 @@ int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4,
 				return skb_get_hash_raw(skb) >> 1;
 			memset(&hash_keys, 0, sizeof(hash_keys));
 			skb_flow_dissect_flow_keys(skb, &keys, flag);
+
+			hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
 			hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src;
 			hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst;
 			hash_keys.ports.src = keys.ports.src;
-- 
2.14.3


From a4c05ef53b83f00a9611f4f8eb8c3ccf853bc55b Mon Sep 17 00:00:00 2001
From: Alexey Kodanev <alexey.kodanev@oracle.com>
Date: Mon, 5 Feb 2018 15:10:35 +0300
Subject: [PATCH 31/49] sctp: fix dst refcnt leak in sctp_v6_get_dst()

[ Upstream commit 957d761cf91cdbb175ad7d8f5472336a4d54dbf2 ]

When going through the bind address list in sctp_v6_get_dst() and
the previously found address is better ('matchlen > bmatchlen'),
the code continues to the next iteration without releasing currently
held destination.

Fix it by releasing 'bdst' before continue to the next iteration, and
instead of introducing one more '!IS_ERR(bdst)' check for dst_release(),
move the already existed one right after ip6_dst_lookup_flow(), i.e. we
shouldn't proceed further if we get an error for the route lookup.

Fixes: dbc2b5e9a09e ("sctp: fix src address selection if using secondary addresses for ipv6")
Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ipv6.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 3b18085e3b10..f27a9718554c 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -326,8 +326,10 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 		final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
 		bdst = ip6_dst_lookup_flow(sk, fl6, final_p);
 
-		if (!IS_ERR(bdst) &&
-		    ipv6_chk_addr(dev_net(bdst->dev),
+		if (IS_ERR(bdst))
+			continue;
+
+		if (ipv6_chk_addr(dev_net(bdst->dev),
 				  &laddr->a.v6.sin6_addr, bdst->dev, 1)) {
 			if (!IS_ERR_OR_NULL(dst))
 				dst_release(dst);
@@ -336,8 +338,10 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 		}
 
 		bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a);
-		if (matchlen > bmatchlen)
+		if (matchlen > bmatchlen) {
+			dst_release(bdst);
 			continue;
+		}
 
 		if (!IS_ERR_OR_NULL(dst))
 			dst_release(dst);
-- 
2.14.3


From 33c5465e545e124702d544cf2fcc6a7bc022e287 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Sun, 25 Feb 2018 21:59:06 +0200
Subject: [PATCH 32/49] bridge: Fix VLAN reference count problem

[ Upstream commit 0e5a82efda872c2469c210957d7d4161ef8f4391 ]

When a VLAN is added on a port, a reference is taken on the
corresponding master VLAN entry. If it does not already exist, then it
is created and a reference taken.

However, in the second case a reference is not really taken when
CONFIG_REFCOUNT_FULL is enabled as refcount_inc() is replaced by
refcount_inc_not_zero().

Fix this by using refcount_set() on a newly created master VLAN entry.

Fixes: 251277598596 ("net, bridge: convert net_bridge_vlan.refcnt from atomic_t to refcount_t")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_vlan.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 233a30040c91..9b8a53568b0f 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -157,6 +157,8 @@ static struct net_bridge_vlan *br_vlan_get_master(struct net_bridge *br, u16 vid
 		masterv = br_vlan_find(vg, vid);
 		if (WARN_ON(!masterv))
 			return NULL;
+		refcount_set(&masterv->refcnt, 1);
+		return masterv;
 	}
 	refcount_inc(&masterv->refcnt);
 
-- 
2.14.3


From b5f8dfadc96d9defded97cbfc06e4da53d0b5a11 Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Thu, 25 Jan 2018 11:18:09 +0200
Subject: [PATCH 33/49] net/mlx5e: Verify inline header size do not exceed SKB
 linear size

[ Upstream commit f600c6088018d1dbc5777d18daa83660f7ea4a64 ]

Driver tries to copy at least MLX5E_MIN_INLINE bytes into the control
segment of the WQE. It assumes that the linear part contains at least
MLX5E_MIN_INLINE bytes, which can be wrong.

Cited commit verified that driver will not copy more bytes into the
inline header part that the actual size of the packet. Re-factor this
check to make sure we do not exceed the linear part as well.

This fix is aligned with the current driver's assumption that the entire
L2 will be present in the linear part of the SKB.

Fixes: 6aace17e64f4 ("net/mlx5e: Fix inline header size for small packets")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 1d6925d4369a..eea7f931cad3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -155,7 +155,7 @@ static inline u16 mlx5e_calc_min_inline(enum mlx5_inline_modes mode,
 	default:
 		hlen = mlx5e_skb_l2_header_offset(skb);
 	}
-	return min_t(u16, hlen, skb->len);
+	return min_t(u16, hlen, skb_headlen(skb));
 }
 
 static inline void mlx5e_tx_skb_pull_inline(unsigned char **skb_data,
-- 
2.14.3


From a35e972864adf3fbe829dc13352c2be3be9ec4d8 Mon Sep 17 00:00:00 2001
From: Tom Lendacky <thomas.lendacky@amd.com>
Date: Tue, 20 Feb 2018 15:22:05 -0600
Subject: [PATCH 34/49] amd-xgbe: Restore PCI interrupt enablement setting on
 resume

[ Upstream commit cfd092f2db8b4b6727e1c03ef68a7842e1023573 ]

After resuming from suspend, the PCI device support must re-enable the
interrupt setting so that interrupts are actually delivered.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe-pci.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
index 3e5833cf1fab..eb23f9ba1a9a 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
@@ -426,6 +426,8 @@ static int xgbe_pci_resume(struct pci_dev *pdev)
 	struct net_device *netdev = pdata->netdev;
 	int ret = 0;
 
+	XP_IOWRITE(pdata, XP_INT_EN, 0x1fffff);
+
 	pdata->lpm_ctrl &= ~MDIO_CTRL1_LPOWER;
 	XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL1, pdata->lpm_ctrl);
 
-- 
2.14.3


From 30963282cda31e2fc17b1effcd364ee15b3e73fe Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 5 Feb 2018 22:23:01 +0100
Subject: [PATCH 35/49] cls_u32: fix use after free in u32_destroy_key()

[ Upstream commit d7cdee5ea8d28ae1b6922deb0c1badaa3aa0ef8c ]

Li Shuang reported an Oops with cls_u32 due to an use-after-free
in u32_destroy_key(). The use-after-free can be triggered with:

dev=lo
tc qdisc add dev $dev root handle 1: htb default 10
tc filter add dev $dev parent 1: prio 5 handle 1: protocol ip u32 divisor 256
tc filter add dev $dev protocol ip parent 1: prio 5 u32 ht 800:: match ip dst\
 10.0.0.0/8 hashkey mask 0x0000ff00 at 16 link 1:
tc qdisc del dev $dev root

Which causes the following kasan splat:

 ==================================================================
 BUG: KASAN: use-after-free in u32_destroy_key.constprop.21+0x117/0x140 [cls_u32]
 Read of size 4 at addr ffff881b83dae618 by task kworker/u48:5/571

 CPU: 17 PID: 571 Comm: kworker/u48:5 Not tainted 4.15.0+ #87
 Hardware name: Dell Inc. PowerEdge R730/072T6D, BIOS 2.1.7 06/16/2016
 Workqueue: tc_filter_workqueue u32_delete_key_freepf_work [cls_u32]
 Call Trace:
  dump_stack+0xd6/0x182
  ? dma_virt_map_sg+0x22e/0x22e
  print_address_description+0x73/0x290
  kasan_report+0x277/0x360
  ? u32_destroy_key.constprop.21+0x117/0x140 [cls_u32]
  u32_destroy_key.constprop.21+0x117/0x140 [cls_u32]
  u32_delete_key_freepf_work+0x1c/0x30 [cls_u32]
  process_one_work+0xae0/0x1c80
  ? sched_clock+0x5/0x10
  ? pwq_dec_nr_in_flight+0x3c0/0x3c0
  ? _raw_spin_unlock_irq+0x29/0x40
  ? trace_hardirqs_on_caller+0x381/0x570
  ? _raw_spin_unlock_irq+0x29/0x40
  ? finish_task_switch+0x1e5/0x760
  ? finish_task_switch+0x208/0x760
  ? preempt_notifier_dec+0x20/0x20
  ? __schedule+0x839/0x1ee0
  ? check_noncircular+0x20/0x20
  ? firmware_map_remove+0x73/0x73
  ? find_held_lock+0x39/0x1c0
  ? worker_thread+0x434/0x1820
  ? lock_contended+0xee0/0xee0
  ? lock_release+0x1100/0x1100
  ? init_rescuer.part.16+0x150/0x150
  ? retint_kernel+0x10/0x10
  worker_thread+0x216/0x1820
  ? process_one_work+0x1c80/0x1c80
  ? lock_acquire+0x1a5/0x540
  ? lock_downgrade+0x6b0/0x6b0
  ? sched_clock+0x5/0x10
  ? lock_release+0x1100/0x1100
  ? compat_start_thread+0x80/0x80
  ? do_raw_spin_trylock+0x190/0x190
  ? _raw_spin_unlock_irq+0x29/0x40
  ? trace_hardirqs_on_caller+0x381/0x570
  ? _raw_spin_unlock_irq+0x29/0x40
  ? finish_task_switch+0x1e5/0x760
  ? finish_task_switch+0x208/0x760
  ? preempt_notifier_dec+0x20/0x20
  ? __schedule+0x839/0x1ee0
  ? kmem_cache_alloc_trace+0x143/0x320
  ? firmware_map_remove+0x73/0x73
  ? sched_clock+0x5/0x10
  ? sched_clock_cpu+0x18/0x170
  ? find_held_lock+0x39/0x1c0
  ? schedule+0xf3/0x3b0
  ? lock_downgrade+0x6b0/0x6b0
  ? __schedule+0x1ee0/0x1ee0
  ? do_wait_intr_irq+0x340/0x340
  ? do_raw_spin_trylock+0x190/0x190
  ? _raw_spin_unlock_irqrestore+0x32/0x60
  ? process_one_work+0x1c80/0x1c80
  ? process_one_work+0x1c80/0x1c80
  kthread+0x312/0x3d0
  ? kthread_create_worker_on_cpu+0xc0/0xc0
  ret_from_fork+0x3a/0x50

 Allocated by task 1688:
  kasan_kmalloc+0xa0/0xd0
  __kmalloc+0x162/0x380
  u32_change+0x1220/0x3c9e [cls_u32]
  tc_ctl_tfilter+0x1ba6/0x2f80
  rtnetlink_rcv_msg+0x4f0/0x9d0
  netlink_rcv_skb+0x124/0x320
  netlink_unicast+0x430/0x600
  netlink_sendmsg+0x8fa/0xd60
  sock_sendmsg+0xb1/0xe0
  ___sys_sendmsg+0x678/0x980
  __sys_sendmsg+0xc4/0x210
  do_syscall_64+0x232/0x7f0
  return_from_SYSCALL_64+0x0/0x75

 Freed by task 112:
  kasan_slab_free+0x71/0xc0
  kfree+0x114/0x320
  rcu_process_callbacks+0xc3f/0x1600
  __do_softirq+0x2bf/0xc06

 The buggy address belongs to the object at ffff881b83dae600
  which belongs to the cache kmalloc-4096 of size 4096
 The buggy address is located 24 bytes inside of
  4096-byte region [ffff881b83dae600, ffff881b83daf600)
 The buggy address belongs to the page:
 page:ffffea006e0f6a00 count:1 mapcount:0 mapping:          (null) index:0x0 compound_mapcount: 0
 flags: 0x17ffffc0008100(slab|head)
 raw: 0017ffffc0008100 0000000000000000 0000000000000000 0000000100070007
 raw: dead000000000100 dead000000000200 ffff880187c0e600 0000000000000000
 page dumped because: kasan: bad access detected

 Memory state around the buggy address:
  ffff881b83dae500: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
  ffff881b83dae580: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 >ffff881b83dae600: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                             ^
  ffff881b83dae680: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
  ffff881b83dae700: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ==================================================================

The problem is that the htnode is freed before the linked knodes and the
latter will try to access the first at u32_destroy_key() time.
This change addresses the issue using the htnode refcnt to guarantee
the correct free order. While at it also add a RCU annotation,
to keep sparse happy.

v1 -> v2: use rtnl_derefence() instead of RCU read locks
v2 -> v3:
  - don't check refcnt in u32_destroy_hnode()
  - cleaned-up u32_destroy() implementation
  - cleaned-up code comment
v3 -> v4:
  - dropped unneeded comment

Reported-by: Li Shuang <shuali@redhat.com>
Fixes: c0d378ef1266 ("net_sched: use tcf_queue_work() in u32 filter")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_u32.c | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 1ce7c1763e81..ba37d8f57e68 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -398,10 +398,12 @@ static int u32_init(struct tcf_proto *tp)
 static int u32_destroy_key(struct tcf_proto *tp, struct tc_u_knode *n,
 			   bool free_pf)
 {
+	struct tc_u_hnode *ht = rtnl_dereference(n->ht_down);
+
 	tcf_exts_destroy(&n->exts);
 	tcf_exts_put_net(&n->exts);
-	if (n->ht_down)
-		n->ht_down->refcnt--;
+	if (ht && --ht->refcnt == 0)
+		kfree(ht);
 #ifdef CONFIG_CLS_U32_PERF
 	if (free_pf)
 		free_percpu(n->pf);
@@ -649,16 +651,15 @@ static void u32_destroy(struct tcf_proto *tp)
 
 		hlist_del(&tp_c->hnode);
 
-		for (ht = rtnl_dereference(tp_c->hlist);
-		     ht;
-		     ht = rtnl_dereference(ht->next)) {
-			ht->refcnt--;
-			u32_clear_hnode(tp, ht);
-		}
-
 		while ((ht = rtnl_dereference(tp_c->hlist)) != NULL) {
+			u32_clear_hnode(tp, ht);
 			RCU_INIT_POINTER(tp_c->hlist, ht->next);
-			kfree_rcu(ht, rcu);
+
+			/* u32_destroy_key() will later free ht for us, if it's
+			 * still referenced by some knode
+			 */
+			if (--ht->refcnt == 0)
+				kfree_rcu(ht, rcu);
 		}
 
 		kfree(tp_c);
-- 
2.14.3


From 8deb69b2677517127af5f0ff2c7427aba67b258e Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Sat, 17 Feb 2018 00:30:44 +0100
Subject: [PATCH 36/49] mlxsw: spectrum_router: Do not unconditionally clear
 route offload indication

[ Upstream commit d1c95af366961101819f07e3c64d44f3be7f0367 ]

When mlxsw replaces (or deletes) a route it removes the offload
indication from the replaced route. This is problematic for IPv4 routes,
as the offload indication is stored in the fib_info which is usually
shared between multiple routes.

Instead of unconditionally clearing the offload indication, only clear
it if no other route is using the fib_info.

Fixes: 3984d1a89fe7 ("mlxsw: spectrum_router: Provide offload indication using nexthop flags")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Alexander Petrovskiy <alexpe@mellanox.com>
Tested-by: Alexander Petrovskiy <alexpe@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index c6eceb8f788b..516e63244606 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -3032,6 +3032,9 @@ mlxsw_sp_fib4_entry_offload_unset(struct mlxsw_sp_fib_entry *fib_entry)
 	struct mlxsw_sp_nexthop_group *nh_grp = fib_entry->nh_group;
 	int i;
 
+	if (!list_is_singular(&nh_grp->fib_list))
+		return;
+
 	for (i = 0; i < nh_grp->count; i++) {
 		struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i];
 
-- 
2.14.3


From 9ead70d20cd6f96d008308566a32cd6c2cfb54c7 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Wed, 21 Feb 2018 04:41:59 +0100
Subject: [PATCH 37/49] netlink: put module reference if dump start fails

[ Upstream commit b87b6194be631c94785fe93398651e804ed43e28 ]

Before, if cb->start() failed, the module reference would never be put,
because cb->cb_running is intentionally false at this point. Users are
generally annoyed by this because they can no longer unload modules that
leak references. Also, it may be possible to tediously wrap a reference
counter back to zero, especially since module.c still uses atomic_inc
instead of refcount_inc.

This patch expands the error path to simply call module_put if
cb->start() fails.

Fixes: 41c87425a1ac ("netlink: do not set cb_running if dump's start() errs")
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 533fd0503ba0..9219bc134109 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2276,7 +2276,7 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 	if (cb->start) {
 		ret = cb->start(cb);
 		if (ret)
-			goto error_unlock;
+			goto error_put;
 	}
 
 	nlk->cb_running = true;
@@ -2296,6 +2296,8 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 	 */
 	return -EINTR;
 
+error_put:
+	module_put(control->module);
 error_unlock:
 	sock_put(sk);
 	mutex_unlock(nlk->cb_mutex);
-- 
2.14.3


From 33c233bc4d4bcfedefd0349831218910b7cf4d88 Mon Sep 17 00:00:00 2001
From: Soheil Hassas Yeganeh <soheil@google.com>
Date: Tue, 27 Feb 2018 18:32:18 -0500
Subject: [PATCH 38/49] tcp: purge write queue upon RST

[ Upstream commit a27fd7a8ed3856faaf5a2ff1c8c5f00c0667aaa0 ]

When the connection is reset, there is no point in
keeping the packets on the write queue until the connection
is closed.

RFC 793 (page 70) and RFC 793-bis (page 64) both suggest
purging the write queue upon RST:
https://tools.ietf.org/html/draft-ietf-tcpm-rfc793bis-07

Moreover, this is essential for a correct MSG_ZEROCOPY
implementation, because userspace cannot call close(fd)
before receiving zerocopy signals even when the connection
is reset.

Fixes: f214f915e7db ("tcp: enable MSG_ZEROCOPY")
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 93c614138f0f..14474acea0bb 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4011,6 +4011,7 @@ void tcp_reset(struct sock *sk)
 	/* This barrier is coupled with smp_rmb() in tcp_poll() */
 	smp_wmb();
 
+	tcp_write_queue_purge(sk);
 	tcp_done(sk);
 
 	if (!sock_flag(sk, SOCK_DEAD))
-- 
2.14.3


From c05ce4070258442a9285bfe3dee148a379a34cf7 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Sat, 24 Feb 2018 11:32:26 +0800
Subject: [PATCH 39/49] tuntap: correctly add the missing XDP flush

[ Upstream commit 1bb4f2e868a2891ab8bc668b8173d6ccb8c4ce6f ]

We don't flush batched XDP packets through xdp_do_flush_map(), this
will cause packets stall at TX queue. Consider we don't do XDP on NAPI
poll(), the only possible fix is to call xdp_do_flush_map()
immediately after xdp_do_redirect().

Note, this in fact won't try to batch packets through devmap, we could
address in the future.

Reported-by: Christoffer Dall <christoffer.dall@linaro.org>
Fixes: 761876c857cb ("tap: XDP support")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index fa51b7b0e9ea..ca55f808b7a9 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1333,6 +1333,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 			get_page(alloc_frag->page);
 			alloc_frag->offset += buflen;
 			err = xdp_do_redirect(tun->dev, &xdp, xdp_prog);
+			xdp_do_flush_map();
 			if (err)
 				goto err_redirect;
 			rcu_read_unlock();
-- 
2.14.3


From 441a07caeaef95f1c48c9c7db4b431f6a7bdb89d Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Sat, 24 Feb 2018 11:32:25 +0800
Subject: [PATCH 40/49] tuntap: disable preemption during XDP processing

[ Upstream commit 23e43f07f896f8578318cfcc9466f1e8b8ab21b6 ]

Except for tuntap, all other drivers' XDP was implemented at NAPI
poll() routine in a bh. This guarantees all XDP operation were done at
the same CPU which is required by e.g BFP_MAP_TYPE_PERCPU_ARRAY. But
for tuntap, we do it in process context and we try to protect XDP
processing by RCU reader lock. This is insufficient since
CONFIG_PREEMPT_RCU can preempt the RCU reader critical section which
breaks the assumption that all XDP were processed in the same CPU.

Fixing this by simply disabling preemption during XDP processing.

Fixes: 761876c857cb ("tap: XDP support")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index ca55f808b7a9..bc38d54e37b9 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1315,6 +1315,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 	else
 		*skb_xdp = 0;
 
+	preempt_disable();
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(tun->xdp_prog);
 	if (xdp_prog && !*skb_xdp) {
@@ -1337,6 +1338,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 			if (err)
 				goto err_redirect;
 			rcu_read_unlock();
+			preempt_enable();
 			return NULL;
 		case XDP_TX:
 			xdp_xmit = true;
@@ -1358,6 +1360,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 	skb = build_skb(buf, buflen);
 	if (!skb) {
 		rcu_read_unlock();
+		preempt_enable();
 		return ERR_PTR(-ENOMEM);
 	}
 
@@ -1370,10 +1373,12 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 		skb->dev = tun->dev;
 		generic_xdp_tx(skb, xdp_prog);
 		rcu_read_unlock();
+		preempt_enable();
 		return NULL;
 	}
 
 	rcu_read_unlock();
+	preempt_enable();
 
 	return skb;
 
@@ -1381,6 +1386,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 	put_page(alloc_frag->page);
 err_xdp:
 	rcu_read_unlock();
+	preempt_enable();
 	this_cpu_inc(tun->pcpu_stats->rx_dropped);
 	return NULL;
 }
-- 
2.14.3


From 94f44f9710321d1b3da6ac4d0a9f64153a239956 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Wed, 28 Feb 2018 18:20:04 +0800
Subject: [PATCH 41/49] virtio-net: disable NAPI only when enabled during XDP
 set

[ Upstream commit 4e09ff5362843dff3accfa84c805c7f3a99de9cd ]

We try to disable NAPI to prevent a single XDP TX queue being used by
multiple cpus. But we don't check if device is up (NAPI is enabled),
this could result stall because of infinite wait in
napi_disable(). Fixing this by checking device state through
netif_running() before.

Fixes: 4941d472bf95b ("virtio-net: do not reset during XDP set")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 7927e28f5336..6a785595b9b8 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1995,8 +1995,9 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 	}
 
 	/* Make sure NAPI is not using any XDP TX queues for RX. */
-	for (i = 0; i < vi->max_queue_pairs; i++)
-		napi_disable(&vi->rq[i].napi);
+	if (netif_running(dev))
+		for (i = 0; i < vi->max_queue_pairs; i++)
+			napi_disable(&vi->rq[i].napi);
 
 	netif_set_real_num_rx_queues(dev, curr_qp + xdp_qp);
 	err = _virtnet_set_queues(vi, curr_qp + xdp_qp);
@@ -2015,7 +2016,8 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 		}
 		if (old_prog)
 			bpf_prog_put(old_prog);
-		virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
+		if (netif_running(dev))
+			virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
 	}
 
 	return 0;
-- 
2.14.3


From 3f251802f7856bddbd738c930ac02e49f7f8df56 Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.vnet.ibm.com>
Date: Fri, 9 Feb 2018 11:03:49 +0100
Subject: [PATCH 42/49] s390/qeth: fix underestimated count of buffer elements

[ Upstream commit 89271c65edd599207dd982007900506283c90ae3 ]

For a memory range/skb where the last byte falls onto a page boundary
(ie. 'end' is of the form xxx...xxx001), the PFN_UP() part of the
calculation currently doesn't round up to the next PFN due to an
off-by-one error.
Thus qeth believes that the skb occupies one page less than it
actually does, and may select a IO buffer that doesn't have enough spare
buffer elements to fit all of the skb's data.
HW detects this as a malformed buffer descriptor, and raises an
exception which then triggers device recovery.

Fixes: 2863c61334aa ("qeth: refactor calculation of SBALE count")
Signed-off-by: Ursula Braun <ubraun@linux.vnet.ibm.com>
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 92dd4aef21a3..22b07046e44a 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -834,7 +834,7 @@ struct qeth_trap_id {
  */
 static inline int qeth_get_elements_for_range(addr_t start, addr_t end)
 {
-	return PFN_UP(end - 1) - PFN_DOWN(start);
+	return PFN_UP(end) - PFN_DOWN(start);
 }
 
 static inline int qeth_get_micros(void)
-- 
2.14.3


From 4c822d96dfd6cf940b57a7a267cad4e63fc554bb Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Fri, 9 Feb 2018 11:03:50 +0100
Subject: [PATCH 43/49] s390/qeth: fix SETIP command handling

[ Upstream commit 1c5b2216fbb973a9410e0b06389740b5c1289171 ]

send_control_data() applies some special handling to SETIP v4 IPA
commands. But current code parses *all* command types for the SETIP
command code. Limit the command code check to IPA commands.

Fixes: 5b54e16f1a54 ("qeth: do not spin for SETIP ip assist command")
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core.h      |  5 +++++
 drivers/s390/net/qeth_core_main.c | 14 ++++++++------
 2 files changed, 13 insertions(+), 6 deletions(-)

diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 22b07046e44a..6b1e83539a9d 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -580,6 +580,11 @@ struct qeth_cmd_buffer {
 	void (*callback) (struct qeth_channel *, struct qeth_cmd_buffer *);
 };
 
+static inline struct qeth_ipa_cmd *__ipa_cmd(struct qeth_cmd_buffer *iob)
+{
+	return (struct qeth_ipa_cmd *)(iob->data + IPA_PDU_HEADER_SIZE);
+}
+
 /**
  * definition of a qeth channel, used for read and write
  */
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 7c7a244b6684..b60e81dd30d2 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -2073,7 +2073,7 @@ int qeth_send_control_data(struct qeth_card *card, int len,
 	unsigned long flags;
 	struct qeth_reply *reply = NULL;
 	unsigned long timeout, event_timeout;
-	struct qeth_ipa_cmd *cmd;
+	struct qeth_ipa_cmd *cmd = NULL;
 
 	QETH_CARD_TEXT(card, 2, "sendctl");
 
@@ -2100,10 +2100,13 @@ int qeth_send_control_data(struct qeth_card *card, int len,
 	while (atomic_cmpxchg(&card->write.irq_pending, 0, 1)) ;
 	qeth_prepare_control_data(card, len, iob);
 
-	if (IS_IPA(iob->data))
+	if (IS_IPA(iob->data)) {
+		cmd = __ipa_cmd(iob);
 		event_timeout = QETH_IPA_TIMEOUT;
-	else
+	} else {
 		event_timeout = QETH_TIMEOUT;
+	}
+
 	timeout = jiffies + event_timeout;
 
 	QETH_CARD_TEXT(card, 6, "noirqpnd");
@@ -2128,9 +2131,8 @@ int qeth_send_control_data(struct qeth_card *card, int len,
 
 	/* we have only one long running ipassist, since we can ensure
 	   process context of this command we can sleep */
-	cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE);
-	if ((cmd->hdr.command == IPA_CMD_SETIP) &&
-	    (cmd->hdr.prot_version == QETH_PROT_IPV4)) {
+	if (cmd && cmd->hdr.command == IPA_CMD_SETIP &&
+	    cmd->hdr.prot_version == QETH_PROT_IPV4) {
 		if (!wait_event_timeout(reply->wait_q,
 		    atomic_read(&reply->received), event_timeout))
 			goto time_err;
-- 
2.14.3


From c454d57cb534d02dd3b351ff7ffe3f06a9f84547 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Tue, 27 Feb 2018 18:58:12 +0100
Subject: [PATCH 44/49] s390/qeth: fix overestimated count of buffer elements

[ Upstream commit 12472af89632beb1ed8dea29d4efe208ca05b06a ]

qeth_get_elements_for_range() doesn't know how to handle a 0-length
range (ie. start == end), and returns 1 when it should return 0.
Such ranges occur on TSO skbs, where the L2/L3/L4 headers (and thus all
of the skb's linear data) are skipped when mapping the skb into regular
buffer elements.

This overestimation may cause several performance-related issues:
1. sub-optimal IO buffer selection, where the next buffer gets selected
   even though the skb would actually still fit into the current buffer.
2. forced linearization, if the element count for a non-linear skb
   exceeds QETH_MAX_BUFFER_ELEMENTS.

Rather than modifying qeth_get_elements_for_range() and adding overhead
to every caller, fix up those callers that are in risk of passing a
0-length range.

Fixes: 2863c61334aa ("qeth: refactor calculation of SBALE count")
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 10 ++++++----
 drivers/s390/net/qeth_l3_main.c   | 11 ++++++-----
 2 files changed, 12 insertions(+), 9 deletions(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index b60e81dd30d2..33f682a3443f 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -3861,10 +3861,12 @@ EXPORT_SYMBOL_GPL(qeth_get_elements_for_frags);
 int qeth_get_elements_no(struct qeth_card *card,
 		     struct sk_buff *skb, int extra_elems, int data_offset)
 {
-	int elements = qeth_get_elements_for_range(
-				(addr_t)skb->data + data_offset,
-				(addr_t)skb->data + skb_headlen(skb)) +
-			qeth_get_elements_for_frags(skb);
+	addr_t end = (addr_t)skb->data + skb_headlen(skb);
+	int elements = qeth_get_elements_for_frags(skb);
+	addr_t start = (addr_t)skb->data + data_offset;
+
+	if (start != end)
+		elements += qeth_get_elements_for_range(start, end);
 
 	if ((elements + extra_elems) > QETH_MAX_BUFFER_ELEMENTS(card)) {
 		QETH_DBF_MESSAGE(2, "Invalid size of IP packet "
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 36dee176f8e2..2ec62317da58 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -2633,11 +2633,12 @@ static void qeth_tso_fill_header(struct qeth_card *card,
 static int qeth_l3_get_elements_no_tso(struct qeth_card *card,
 			struct sk_buff *skb, int extra_elems)
 {
-	addr_t tcpdptr = (addr_t)tcp_hdr(skb) + tcp_hdrlen(skb);
-	int elements = qeth_get_elements_for_range(
-				tcpdptr,
-				(addr_t)skb->data + skb_headlen(skb)) +
-				qeth_get_elements_for_frags(skb);
+	addr_t start = (addr_t)tcp_hdr(skb) + tcp_hdrlen(skb);
+	addr_t end = (addr_t)skb->data + skb_headlen(skb);
+	int elements = qeth_get_elements_for_frags(skb);
+
+	if (start != end)
+		elements += qeth_get_elements_for_range(start, end);
 
 	if ((elements + extra_elems) > QETH_MAX_BUFFER_ELEMENTS(card)) {
 		QETH_DBF_MESSAGE(2,
-- 
2.14.3


From b93f2dabe894f77818fe13cea3b1582e5a3ad6d0 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Tue, 27 Feb 2018 18:58:13 +0100
Subject: [PATCH 45/49] s390/qeth: fix IP removal on offline cards

[ Upstream commit 98d823ab1fbdcb13abc25b420f9bb71bade42056 ]

If the HW is not reachable, then none of the IPs in qeth's internal
table has been registered with the HW yet. So when deleting such an IP,
there's no need to stage it for deregistration - just drop it from
the table.

This fixes the "add-delete-add" scenario on an offline card, where the
the second "add" merely increments the IP's use count. But as the IP is
still set to DISP_ADDR_DELETE from the previous "delete" step,
l3_recover_ip() won't register it with the HW when the card goes online.

Fixes: 5f78e29ceebf ("qeth: optimize IP handling in rx_mode callback")
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_l3_main.c | 14 +++-----------
 1 file changed, 3 insertions(+), 11 deletions(-)

diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 2ec62317da58..a283dec014f3 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -255,12 +255,8 @@ int qeth_l3_delete_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
 	if (addr->in_progress)
 		return -EINPROGRESS;
 
-	if (!qeth_card_hw_is_reachable(card)) {
-		addr->disp_flag = QETH_DISP_ADDR_DELETE;
-		return 0;
-	}
-
-	rc = qeth_l3_deregister_addr_entry(card, addr);
+	if (qeth_card_hw_is_reachable(card))
+		rc = qeth_l3_deregister_addr_entry(card, addr);
 
 	hash_del(&addr->hnode);
 	kfree(addr);
@@ -403,11 +399,7 @@ static void qeth_l3_recover_ip(struct qeth_card *card)
 	spin_lock_bh(&card->ip_lock);
 
 	hash_for_each_safe(card->ip_htable, i, tmp, addr, hnode) {
-		if (addr->disp_flag == QETH_DISP_ADDR_DELETE) {
-			qeth_l3_deregister_addr_entry(card, addr);
-			hash_del(&addr->hnode);
-			kfree(addr);
-		} else if (addr->disp_flag == QETH_DISP_ADDR_ADD) {
+		if (addr->disp_flag == QETH_DISP_ADDR_ADD) {
 			if (addr->proto == QETH_PROT_IPV4) {
 				addr->in_progress = 1;
 				spin_unlock_bh(&card->ip_lock);
-- 
2.14.3


From 4ca240985e6b9b204c332e5281fe1050bb12b543 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Tue, 27 Feb 2018 18:58:14 +0100
Subject: [PATCH 46/49] s390/qeth: fix double-free on IP add/remove race

[ Upstream commit 14d066c3531a87f727968cacd85bd95c75f59843 ]

Registering an IPv4 address with the HW takes quite a while, so we
temporarily drop the ip_htable lock. Any concurrent add/remove of the
same IP adjusts the IP's use count, and (on remove) is then blocked by
addr->in_progress.
After the register call has completed, we check the use count for
concurrently attempted add/remove calls - and possibly straight-away
deregister the IP again. This happens via l3_delete_ip(), which
1) looks up the queried IP in the htable (getting a reference to the
   *same* queried object),
2) deregisters the IP from the HW, and
3) frees the IP object.

The caller in l3_add_ip() then does a second free on the same object.

For this case, skip all the extra checks and lookups in l3_delete_ip()
and just deregister & free the IP object ourselves.

Fixes: 5f78e29ceebf ("qeth: optimize IP handling in rx_mode callback")
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_l3_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index a283dec014f3..91650e8adcc4 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -319,7 +319,8 @@ int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
 				(rc == IPA_RC_LAN_OFFLINE)) {
 			addr->disp_flag = QETH_DISP_ADDR_DO_NOTHING;
 			if (addr->ref_counter < 1) {
-				qeth_l3_delete_ip(card, addr);
+				qeth_l3_deregister_addr_entry(card, addr);
+				hash_del(&addr->hnode);
 				kfree(addr);
 			}
 		} else {
-- 
2.14.3


From efd1e9c91a307861e5a42eaa9f97686a721485fe Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Tue, 27 Feb 2018 18:58:15 +0100
Subject: [PATCH 47/49] Revert "s390/qeth: fix using of ref counter for rxip
 addresses"

[ Upstream commit 4964c66fd49b2e2342da35358f2ff74614bcbaee ]

This reverts commit cb816192d986f7596009dedcf2201fe2e5bc2aa7.

The issue this attempted to fix never actually occurs.
l3_add_rxip() checks (via l3_ip_from_hash()) if the requested address
was previously added to the card. If so, it returns -EEXIST and doesn't
call l3_add_ip().
As a result, the "address exists" path in l3_add_ip() is never taken
for rxip addresses, and this patch had no effect.

Fixes: cb816192d986 ("s390/qeth: fix using of ref counter for rxip addresses")
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_l3_main.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 91650e8adcc4..7472a0931341 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -249,8 +249,7 @@ int qeth_l3_delete_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
 		return -ENOENT;
 
 	addr->ref_counter--;
-	if (addr->ref_counter > 0 && (addr->type == QETH_IP_TYPE_NORMAL ||
-				      addr->type == QETH_IP_TYPE_RXIP))
+	if (addr->type == QETH_IP_TYPE_NORMAL && addr->ref_counter > 0)
 		return rc;
 	if (addr->in_progress)
 		return -EINPROGRESS;
@@ -328,9 +327,8 @@ int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
 			kfree(addr);
 		}
 	} else {
-		if (addr->type == QETH_IP_TYPE_NORMAL ||
-		    addr->type == QETH_IP_TYPE_RXIP)
-			addr->ref_counter++;
+			if (addr->type == QETH_IP_TYPE_NORMAL)
+				addr->ref_counter++;
 	}
 
 	return rc;
-- 
2.14.3


From 18e8ad06c46dbbad67f2093d00aea003219e51de Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Tue, 27 Feb 2018 18:58:16 +0100
Subject: [PATCH 48/49] s390/qeth: fix IP address lookup for L3 devices

[ Upstream commit c5c48c58b259bb8f0482398370ee539d7a12df3e ]

Current code ("qeth_l3_ip_from_hash()") matches a queried address object
against objects in the IP table by IP address, Mask/Prefix Length and
MAC address ("qeth_l3_ipaddrs_is_equal()"). But what callers actually
require is either
a) "is this IP address registered" (ie. match by IP address only),
before adding a new address.
b) or "is this address object registered" (ie. match all relevant
   attributes), before deleting an address.

Right now
1. the ADD path is too strict in its lookup, and eg. doesn't detect
conflicts between an existing NORMAL address and a new VIPA address
(because the NORMAL address will have mask != 0, while VIPA has
a mask == 0),
2. the DELETE path is not strict enough, and eg. allows del_rxip() to
delete a VIPA address as long as the IP address matches.

Fix all this by adding helpers (_addr_match_ip() and _addr_match_all())
that do the appropriate checking.

Note that the ADD path for NORMAL addresses is special, as qeth keeps
track of how many times such an address is in use (and there is no
immediate way of returning errors to the caller). So when a requested
NORMAL address _fully_ matches an existing one, it's not considered a
conflict and we merely increment the refcount.

Fixes: 5f78e29ceebf ("qeth: optimize IP handling in rx_mode callback")
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_l3.h      | 34 ++++++++++++++-
 drivers/s390/net/qeth_l3_main.c | 91 +++++++++++++++++++----------------------
 2 files changed, 74 insertions(+), 51 deletions(-)

diff --git a/drivers/s390/net/qeth_l3.h b/drivers/s390/net/qeth_l3.h
index e5833837b799..8727b9517de8 100644
--- a/drivers/s390/net/qeth_l3.h
+++ b/drivers/s390/net/qeth_l3.h
@@ -40,8 +40,40 @@ struct qeth_ipaddr {
 			unsigned int pfxlen;
 		} a6;
 	} u;
-
 };
+
+static inline bool qeth_l3_addr_match_ip(struct qeth_ipaddr *a1,
+					 struct qeth_ipaddr *a2)
+{
+	if (a1->proto != a2->proto)
+		return false;
+	if (a1->proto == QETH_PROT_IPV6)
+		return ipv6_addr_equal(&a1->u.a6.addr, &a2->u.a6.addr);
+	return a1->u.a4.addr == a2->u.a4.addr;
+}
+
+static inline bool qeth_l3_addr_match_all(struct qeth_ipaddr *a1,
+					  struct qeth_ipaddr *a2)
+{
+	/* Assumes that the pair was obtained via qeth_l3_addr_find_by_ip(),
+	 * so 'proto' and 'addr' match for sure.
+	 *
+	 * For ucast:
+	 * -	'mac' is always 0.
+	 * -	'mask'/'pfxlen' for RXIP/VIPA is always 0. For NORMAL, matching
+	 *	values are required to avoid mixups in takeover eligibility.
+	 *
+	 * For mcast,
+	 * -	'mac' is mapped from the IP, and thus always matches.
+	 * -	'mask'/'pfxlen' is always 0.
+	 */
+	if (a1->type != a2->type)
+		return false;
+	if (a1->proto == QETH_PROT_IPV6)
+		return a1->u.a6.pfxlen == a2->u.a6.pfxlen;
+	return a1->u.a4.mask == a2->u.a4.mask;
+}
+
 static inline  u64 qeth_l3_ipaddr_hash(struct qeth_ipaddr *addr)
 {
 	u64  ret = 0;
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 7472a0931341..96576e729222 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -149,6 +149,24 @@ int qeth_l3_string_to_ipaddr(const char *buf, enum qeth_prot_versions proto,
 		return -EINVAL;
 }
 
+static struct qeth_ipaddr *qeth_l3_find_addr_by_ip(struct qeth_card *card,
+						   struct qeth_ipaddr *query)
+{
+	u64 key = qeth_l3_ipaddr_hash(query);
+	struct qeth_ipaddr *addr;
+
+	if (query->is_multicast) {
+		hash_for_each_possible(card->ip_mc_htable, addr, hnode, key)
+			if (qeth_l3_addr_match_ip(addr, query))
+				return addr;
+	} else {
+		hash_for_each_possible(card->ip_htable,  addr, hnode, key)
+			if (qeth_l3_addr_match_ip(addr, query))
+				return addr;
+	}
+	return NULL;
+}
+
 static void qeth_l3_convert_addr_to_bits(u8 *addr, u8 *bits, int len)
 {
 	int i, j;
@@ -202,34 +220,6 @@ static bool qeth_l3_is_addr_covered_by_ipato(struct qeth_card *card,
 	return rc;
 }
 
-inline int
-qeth_l3_ipaddrs_is_equal(struct qeth_ipaddr *addr1, struct qeth_ipaddr *addr2)
-{
-	return addr1->proto == addr2->proto &&
-		!memcmp(&addr1->u, &addr2->u, sizeof(addr1->u))  &&
-		!memcmp(&addr1->mac, &addr2->mac, sizeof(addr1->mac));
-}
-
-static struct qeth_ipaddr *
-qeth_l3_ip_from_hash(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
-{
-	struct qeth_ipaddr *addr;
-
-	if (tmp_addr->is_multicast) {
-		hash_for_each_possible(card->ip_mc_htable,  addr,
-				hnode, qeth_l3_ipaddr_hash(tmp_addr))
-			if (qeth_l3_ipaddrs_is_equal(tmp_addr, addr))
-				return addr;
-	} else {
-		hash_for_each_possible(card->ip_htable,  addr,
-				hnode, qeth_l3_ipaddr_hash(tmp_addr))
-			if (qeth_l3_ipaddrs_is_equal(tmp_addr, addr))
-				return addr;
-	}
-
-	return NULL;
-}
-
 int qeth_l3_delete_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
 {
 	int rc = 0;
@@ -244,8 +234,8 @@ int qeth_l3_delete_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
 		QETH_CARD_HEX(card, 4, ((char *)&tmp_addr->u.a6.addr) + 8, 8);
 	}
 
-	addr = qeth_l3_ip_from_hash(card, tmp_addr);
-	if (!addr)
+	addr = qeth_l3_find_addr_by_ip(card, tmp_addr);
+	if (!addr || !qeth_l3_addr_match_all(addr, tmp_addr))
 		return -ENOENT;
 
 	addr->ref_counter--;
@@ -267,6 +257,7 @@ int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
 {
 	int rc = 0;
 	struct qeth_ipaddr *addr;
+	char buf[40];
 
 	QETH_CARD_TEXT(card, 4, "addip");
 
@@ -277,8 +268,20 @@ int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
 		QETH_CARD_HEX(card, 4, ((char *)&tmp_addr->u.a6.addr) + 8, 8);
 	}
 
-	addr = qeth_l3_ip_from_hash(card, tmp_addr);
-	if (!addr) {
+	addr = qeth_l3_find_addr_by_ip(card, tmp_addr);
+	if (addr) {
+		if (tmp_addr->type != QETH_IP_TYPE_NORMAL)
+			return -EADDRINUSE;
+		if (qeth_l3_addr_match_all(addr, tmp_addr)) {
+			addr->ref_counter++;
+			return 0;
+		}
+		qeth_l3_ipaddr_to_string(tmp_addr->proto, (u8 *)&tmp_addr->u,
+					 buf);
+		dev_warn(&card->gdev->dev,
+			 "Registering IP address %s failed\n", buf);
+		return -EADDRINUSE;
+	} else {
 		addr = qeth_l3_get_addr_buffer(tmp_addr->proto);
 		if (!addr)
 			return -ENOMEM;
@@ -326,11 +329,7 @@ int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
 			hash_del(&addr->hnode);
 			kfree(addr);
 		}
-	} else {
-			if (addr->type == QETH_IP_TYPE_NORMAL)
-				addr->ref_counter++;
 	}
-
 	return rc;
 }
 
@@ -714,12 +713,7 @@ int qeth_l3_add_vipa(struct qeth_card *card, enum qeth_prot_versions proto,
 		return -ENOMEM;
 
 	spin_lock_bh(&card->ip_lock);
-
-	if (qeth_l3_ip_from_hash(card, ipaddr))
-		rc = -EEXIST;
-	else
-		qeth_l3_add_ip(card, ipaddr);
-
+	rc = qeth_l3_add_ip(card, ipaddr);
 	spin_unlock_bh(&card->ip_lock);
 
 	kfree(ipaddr);
@@ -782,12 +776,7 @@ int qeth_l3_add_rxip(struct qeth_card *card, enum qeth_prot_versions proto,
 		return -ENOMEM;
 
 	spin_lock_bh(&card->ip_lock);
-
-	if (qeth_l3_ip_from_hash(card, ipaddr))
-		rc = -EEXIST;
-	else
-		qeth_l3_add_ip(card, ipaddr);
-
+	rc = qeth_l3_add_ip(card, ipaddr);
 	spin_unlock_bh(&card->ip_lock);
 
 	kfree(ipaddr);
@@ -1395,8 +1384,9 @@ qeth_l3_add_mc_to_hash(struct qeth_card *card, struct in_device *in4_dev)
 		memcpy(tmp->mac, buf, sizeof(tmp->mac));
 		tmp->is_multicast = 1;
 
-		ipm = qeth_l3_ip_from_hash(card, tmp);
+		ipm = qeth_l3_find_addr_by_ip(card, tmp);
 		if (ipm) {
+			/* for mcast, by-IP match means full match */
 			ipm->disp_flag = QETH_DISP_ADDR_DO_NOTHING;
 		} else {
 			ipm = qeth_l3_get_addr_buffer(QETH_PROT_IPV4);
@@ -1479,8 +1469,9 @@ qeth_l3_add_mc6_to_hash(struct qeth_card *card, struct inet6_dev *in6_dev)
 		       sizeof(struct in6_addr));
 		tmp->is_multicast = 1;
 
-		ipm = qeth_l3_ip_from_hash(card, tmp);
+		ipm = qeth_l3_find_addr_by_ip(card, tmp);
 		if (ipm) {
+			/* for mcast, by-IP match means full match */
 			ipm->disp_flag = QETH_DISP_ADDR_DO_NOTHING;
 			continue;
 		}
-- 
2.14.3


From 1898a9217d60040172405dd1f7da899f9011fe94 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Tue, 27 Feb 2018 18:58:17 +0100
Subject: [PATCH 49/49] s390/qeth: fix IPA command submission race

[ Upstream commit d22ffb5a712f9211ffd104c38fc17cbfb1b5e2b0 ]

If multiple IPA commands are build & sent out concurrently,
fill_ipacmd_header() may assign a seqno value to a command that's
different from what send_control_data() later assigns to this command's
reply.
This is due to other commands passing through send_control_data(),
and incrementing card->seqno.ipa along the way.

So one IPA command has no reply that's waiting for its seqno, while some
other IPA command has multiple reply objects waiting for it.
Only one of those waiting replies wins, and the other(s) times out and
triggers a recovery via send_ipa_cmd().

Fix this by making sure that the same seqno value is assigned to
a command and its reply object.
Do so immediately before submitting the command & while holding the
irq_pending "lock", to produce nicely ascending seqnos.

As a side effect, *all* IPA commands now use a reply object that's
waiting for its actual seqno. Previously, early IPA commands that were
submitted while the card was still DOWN used the "catch-all" IDX seqno.

Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 33f682a3443f..145b57762d8f 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -2087,25 +2087,26 @@ int qeth_send_control_data(struct qeth_card *card, int len,
 	}
 	reply->callback = reply_cb;
 	reply->param = reply_param;
-	if (card->state == CARD_STATE_DOWN)
-		reply->seqno = QETH_IDX_COMMAND_SEQNO;
-	else
-		reply->seqno = card->seqno.ipa++;
+
 	init_waitqueue_head(&reply->wait_q);
-	spin_lock_irqsave(&card->lock, flags);
-	list_add_tail(&reply->list, &card->cmd_waiter_list);
-	spin_unlock_irqrestore(&card->lock, flags);
 	QETH_DBF_HEX(CTRL, 2, iob->data, QETH_DBF_CTRL_LEN);
 
 	while (atomic_cmpxchg(&card->write.irq_pending, 0, 1)) ;
-	qeth_prepare_control_data(card, len, iob);
 
 	if (IS_IPA(iob->data)) {
 		cmd = __ipa_cmd(iob);
+		cmd->hdr.seqno = card->seqno.ipa++;
+		reply->seqno = cmd->hdr.seqno;
 		event_timeout = QETH_IPA_TIMEOUT;
 	} else {
+		reply->seqno = QETH_IDX_COMMAND_SEQNO;
 		event_timeout = QETH_TIMEOUT;
 	}
+	qeth_prepare_control_data(card, len, iob);
+
+	spin_lock_irqsave(&card->lock, flags);
+	list_add_tail(&reply->list, &card->cmd_waiter_list);
+	spin_unlock_irqrestore(&card->lock, flags);
 
 	timeout = jiffies + event_timeout;
 
@@ -2896,7 +2897,7 @@ static void qeth_fill_ipacmd_header(struct qeth_card *card,
 	memset(cmd, 0, sizeof(struct qeth_ipa_cmd));
 	cmd->hdr.command = command;
 	cmd->hdr.initiator = IPA_CMD_INITIATOR_HOST;
-	cmd->hdr.seqno = card->seqno.ipa;
+	/* cmd->hdr.seqno is set by qeth_send_control_data() */
 	cmd->hdr.adapter_type = qeth_get_ipa_adp_type(card->info.link_type);
 	cmd->hdr.rel_adapter_no = (__u8) card->info.portno;
 	if (card->options.layer2)
-- 
2.14.3


[-- Attachment #3: net_415.mbox --]
[-- Type: Application/Octet-Stream, Size: 163008 bytes --]

From cdbd2c23c52d9f7b5312bb1f7b80f90b49ae29f2 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 12 Feb 2018 17:15:40 +0800
Subject: [PATCH 01/59] bridge: check brport attr show in brport_show

[ Upstream commit 1b12580af1d0677c3c3a19e35bfe5d59b03f737f ]

Now br_sysfs_if file flush doesn't have attr show. To read it will
cause kernel panic after users chmod u+r this file.

Xiong found this issue when running the commands:

  ip link add br0 type bridge
  ip link add type veth
  ip link set veth0 master br0
  chmod u+r /sys/devices/virtual/net/veth0/brport/flush
  timeout 3 cat /sys/devices/virtual/net/veth0/brport/flush

kernel crashed with NULL a pointer dereference call trace.

This patch is to fix it by return -EINVAL when brport_attr->show
is null, just the same as the check for brport_attr->store in
brport_store().

Fixes: 9cf637473c85 ("bridge: add sysfs hook to flush forwarding table")
Reported-by: Xiong Zhou <xzhou@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_sysfs_if.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c
index 0254c35b2bf0..126a8ea73c96 100644
--- a/net/bridge/br_sysfs_if.c
+++ b/net/bridge/br_sysfs_if.c
@@ -255,6 +255,9 @@ static ssize_t brport_show(struct kobject *kobj,
 	struct brport_attribute *brport_attr = to_brport_attr(attr);
 	struct net_bridge_port *p = to_brport(kobj);
 
+	if (!brport_attr->show)
+		return -EINVAL;
+
 	return brport_attr->show(p, buf);
 }
 
-- 
2.14.3


From 9f74a8fb398b9488f95bac39888ffad50efa040c Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Thu, 15 Feb 2018 09:46:03 +0100
Subject: [PATCH 02/59] fib_semantics: Don't match route with mismatching
 tclassid

[ Upstream commit a8c6db1dfd1b1d18359241372bb204054f2c3174 ]

In fib_nh_match(), if output interface or gateway are passed in
the FIB configuration, we don't have to check next hops of
multipath routes to conclude whether we have a match or not.

However, we might still have routes with different realms
matching the same output interface and gateway configuration,
and this needs to cause the match to fail. Otherwise the first
route inserted in the FIB will match, regardless of the realms:

 # ip route add 1.1.1.1 dev eth0 table 1234 realms 1/2
 # ip route append 1.1.1.1 dev eth0 table 1234 realms 3/4
 # ip route list table 1234
 1.1.1.1 dev eth0 scope link realms 1/2
 1.1.1.1 dev eth0 scope link realms 3/4
 # ip route del 1.1.1.1 dev ens3 table 1234 realms 3/4
 # ip route list table 1234
 1.1.1.1 dev ens3 scope link realms 3/4

whereas route with realms 3/4 should have been deleted instead.

Explicitly check for fc_flow passed in the FIB configuration
(this comes from RTA_FLOW extracted by rtm_to_fib_config()) and
fail matching if it differs from nh_tclassid.

The handling of RTA_FLOW for multipath routes later in
fib_nh_match() is still needed, as we can have multiple RTA_FLOW
attributes that need to be matched against the tclassid of each
next hop.

v2: Check that fc_flow is set before discarding the match, so
    that the user can still select the first matching rule by
    not specifying any realm, as suggested by David Ahern.

Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_semantics.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index c586597da20d..7d36a950d961 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -646,6 +646,11 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi,
 					    fi->fib_nh, cfg, extack))
 				return 1;
 		}
+#ifdef CONFIG_IP_ROUTE_CLASSID
+		if (cfg->fc_flow &&
+		    cfg->fc_flow != fi->fib_nh->nh_tclassid)
+			return 1;
+#endif
 		if ((!cfg->fc_oif || cfg->fc_oif == fi->fib_nh->nh_oif) &&
 		    (!cfg->fc_gw  || cfg->fc_gw == fi->fib_nh->nh_gw))
 			return 0;
-- 
2.14.3


From f96c6343a8a8d36a697ebf5cbf0e3a47f105301f Mon Sep 17 00:00:00 2001
From: Denis Du <dudenis2000@yahoo.ca>
Date: Sat, 24 Feb 2018 16:51:42 -0500
Subject: [PATCH 03/59] hdlc_ppp: carrier detect ok, don't turn off negotiation

[ Upstream commit b6c3bad1ba83af1062a7ff6986d9edc4f3d7fc8e ]

Sometimes when physical lines have a just good noise to make the protocol
handshaking fail, but the carrier detect still good. Then after remove of
the noise, nobody will trigger this protocol to be start again to cause
the link to never come back. The fix is when the carrier is still on, not
terminate the protocol handshaking.

Signed-off-by: Denis Du <dudenis2000@yahoo.ca>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wan/hdlc_ppp.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wan/hdlc_ppp.c b/drivers/net/wan/hdlc_ppp.c
index afeca6bcdade..ab8b3cbbb205 100644
--- a/drivers/net/wan/hdlc_ppp.c
+++ b/drivers/net/wan/hdlc_ppp.c
@@ -574,7 +574,10 @@ static void ppp_timer(struct timer_list *t)
 			ppp_cp_event(proto->dev, proto->pid, TO_GOOD, 0, 0,
 				     0, NULL);
 			proto->restart_counter--;
-		} else
+		} else if (netif_carrier_ok(proto->dev))
+			ppp_cp_event(proto->dev, proto->pid, TO_GOOD, 0, 0,
+				     0, NULL);
+		else
 			ppp_cp_event(proto->dev, proto->pid, TO_BAD, 0, 0,
 				     0, NULL);
 		break;
-- 
2.14.3


From ab12222db34d81cbe69624bf4193406a346f5210 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 22 Feb 2018 16:55:34 +0100
Subject: [PATCH 04/59] ipv6 sit: work around bogus gcc-8 -Wrestrict warning

[ Upstream commit ca79bec237f5809a7c3c59bd41cd0880aa889966 ]

gcc-8 has a new warning that detects overlapping input and output arguments
in memcpy(). It triggers for sit_init_net() calling ipip6_tunnel_clone_6rd(),
which is actually correct:

net/ipv6/sit.c: In function 'sit_init_net':
net/ipv6/sit.c:192:3: error: 'memcpy' source argument is the same as destination [-Werror=restrict]

The problem here is that the logic detecting the memcpy() arguments finds them
to be the same, but the conditional that tests for the input and output of
ipip6_tunnel_clone_6rd() to be identical is not a compile-time constant.

We know that netdev_priv(t->dev) is the same as t for a tunnel device,
and comparing "dev" directly here lets the compiler figure out as well
that 'dev == sitn->fb_tunnel_dev' when called from sit_init_net(), so
it no longer warns.

This code is old, so Cc stable to make sure that we don't get the warning
for older kernels built with new gcc.

Cc: Martin Sebor <msebor@gmail.com>
Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=83456
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 3873d3877135..3a1775a62973 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -182,7 +182,7 @@ static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn)
 #ifdef CONFIG_IPV6_SIT_6RD
 	struct ip_tunnel *t = netdev_priv(dev);
 
-	if (t->dev == sitn->fb_tunnel_dev) {
+	if (dev == sitn->fb_tunnel_dev) {
 		ipv6_addr_set(&t->ip6rd.prefix, htonl(0x20020000), 0, 0, 0);
 		t->ip6rd.relay_prefix = 0;
 		t->ip6rd.prefixlen = 16;
-- 
2.14.3


From 348a68740c83f0fdccc81a3460fabbfc2b51d2b2 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Mon, 5 Feb 2018 21:10:01 +0100
Subject: [PATCH 05/59] net: amd-xgbe: fix comparison to bitshift when dealing
 with a mask

[ Upstream commit a3276892db7a588bedc33168e502572008f714a9 ]

Due to a typo, the mask was destroyed by a comparison instead of a bit
shift.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Acked-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe-drv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index a74a8fbad53a..2e6075ce5dca 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -595,7 +595,7 @@ static void xgbe_isr_task(unsigned long data)
 
 		reissue_mask = 1 << 0;
 		if (!pdata->per_channel_irq)
-			reissue_mask |= 0xffff < 4;
+			reissue_mask |= 0xffff << 4;
 
 		XP_IOWRITE(pdata, XP_INT_REISSUE_EN, reissue_mask);
 	}
-- 
2.14.3


From 23f669193d9e5ee60a656a0e81fdf1f3693288fa Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Tue, 6 Feb 2018 19:17:06 -0600
Subject: [PATCH 06/59] net: ethernet: ti: cpsw: fix net watchdog timeout

[ Upstream commit 62f94c2101f35cd45775df00ba09bde77580e26a ]

It was discovered that simple program which indefinitely sends 200b UDP
packets and runs on TI AM574x SoC (SMP) under RT Kernel triggers network
watchdog timeout in TI CPSW driver (<6 hours run). The network watchdog
timeout is triggered due to race between cpsw_ndo_start_xmit() and
cpsw_tx_handler() [NAPI]

cpsw_ndo_start_xmit()
	if (unlikely(!cpdma_check_free_tx_desc(txch))) {
		txq = netdev_get_tx_queue(ndev, q_idx);
		netif_tx_stop_queue(txq);

^^ as per [1] barier has to be used after set_bit() otherwise new value
might not be visible to other cpus
	}

cpsw_tx_handler()
	if (unlikely(netif_tx_queue_stopped(txq)))
		netif_tx_wake_queue(txq);

and when it happens ndev TX queue became disabled forever while driver's HW
TX queue is empty.

Fix this, by adding smp_mb__after_atomic() after netif_tx_stop_queue()
calls and double check for free TX descriptors after stopping ndev TX queue
- if there are free TX descriptors wake up ndev TX queue.

[1] https://www.kernel.org/doc/html/latest/core-api/atomic_ops.html
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Reviewed-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index a73600dceb8b..a1ffc3ed77f9 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -1618,6 +1618,7 @@ static netdev_tx_t cpsw_ndo_start_xmit(struct sk_buff *skb,
 		q_idx = q_idx % cpsw->tx_ch_num;
 
 	txch = cpsw->txv[q_idx].ch;
+	txq = netdev_get_tx_queue(ndev, q_idx);
 	ret = cpsw_tx_packet_submit(priv, skb, txch);
 	if (unlikely(ret != 0)) {
 		cpsw_err(priv, tx_err, "desc submit failed\n");
@@ -1628,15 +1629,26 @@ static netdev_tx_t cpsw_ndo_start_xmit(struct sk_buff *skb,
 	 * tell the kernel to stop sending us tx frames.
 	 */
 	if (unlikely(!cpdma_check_free_tx_desc(txch))) {
-		txq = netdev_get_tx_queue(ndev, q_idx);
 		netif_tx_stop_queue(txq);
+
+		/* Barrier, so that stop_queue visible to other cpus */
+		smp_mb__after_atomic();
+
+		if (cpdma_check_free_tx_desc(txch))
+			netif_tx_wake_queue(txq);
 	}
 
 	return NETDEV_TX_OK;
 fail:
 	ndev->stats.tx_dropped++;
-	txq = netdev_get_tx_queue(ndev, skb_get_queue_mapping(skb));
 	netif_tx_stop_queue(txq);
+
+	/* Barrier, so that stop_queue visible to other cpus */
+	smp_mb__after_atomic();
+
+	if (cpdma_check_free_tx_desc(txch))
+		netif_tx_wake_queue(txq);
+
 	return NETDEV_TX_BUSY;
 }
 
-- 
2.14.3


From 9e513be73c5b5d527d95ea546405f316a139a0ce Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 12 Feb 2018 21:35:31 -0800
Subject: [PATCH 07/59] net: fix race on decreasing number of TX queues

[ Upstream commit ac5b70198adc25c73fba28de4f78adcee8f6be0b ]

netif_set_real_num_tx_queues() can be called when netdev is up.
That usually happens when user requests change of number of
channels/rings with ethtool -L.  The procedure for changing
the number of queues involves resetting the qdiscs and setting
dev->num_tx_queues to the new value.  When the new value is
lower than the old one, extra care has to be taken to ensure
ordering of accesses to the number of queues vs qdisc reset.

Currently the queues are reset before new dev->num_tx_queues
is assigned, leaving a window of time where packets can be
enqueued onto the queues going down, leading to a likely
crash in the drivers, since most drivers don't check if TX
skbs are assigned to an active queue.

Fixes: e6484930d7c7 ("net: allocate tx queues in register_netdevice")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index c8c102a3467f..a2a89acd0de8 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2366,8 +2366,11 @@ EXPORT_SYMBOL(netdev_set_num_tc);
  */
 int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq)
 {
+	bool disabling;
 	int rc;
 
+	disabling = txq < dev->real_num_tx_queues;
+
 	if (txq < 1 || txq > dev->num_tx_queues)
 		return -EINVAL;
 
@@ -2383,15 +2386,19 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq)
 		if (dev->num_tc)
 			netif_setup_tc(dev, txq);
 
-		if (txq < dev->real_num_tx_queues) {
+		dev->real_num_tx_queues = txq;
+
+		if (disabling) {
+			synchronize_net();
 			qdisc_reset_all_tx_gt(dev, txq);
 #ifdef CONFIG_XPS
 			netif_reset_xps_queues_gt(dev, txq);
 #endif
 		}
+	} else {
+		dev->real_num_tx_queues = txq;
 	}
 
-	dev->real_num_tx_queues = txq;
 	return 0;
 }
 EXPORT_SYMBOL(netif_set_real_num_tx_queues);
-- 
2.14.3


From 61f06070e8f96952c5915cd1db75c03bfa7106d0 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Mon, 26 Feb 2018 16:13:43 +0100
Subject: [PATCH 08/59] net: ipv4: don't allow setting net.ipv4.route.min_pmtu
 below 68

[ Upstream commit c7272c2f1229125f74f22dcdd59de9bbd804f1c8 ]

According to RFC 1191 sections 3 and 4, ICMP frag-needed messages
indicating an MTU below 68 should be rejected:

    A host MUST never reduce its estimate of the Path MTU below 68
    octets.

and (talking about ICMP frag-needed's Next-Hop MTU field):

    This field will never contain a value less than 68, since every
    router "must be able to forward a datagram of 68 octets without
    fragmentation".

Furthermore, by letting net.ipv4.route.min_pmtu be set to negative
values, we can end up with a very large PMTU when (-1) is cast into u32.

Let's also make ip_rt_min_pmtu a u32, since it's only ever compared to
unsigned ints.

Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 4e153b23bcec..239a89be8e41 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -128,10 +128,13 @@ static int ip_rt_redirect_silence __read_mostly	= ((HZ / 50) << (9 + 1));
 static int ip_rt_error_cost __read_mostly	= HZ;
 static int ip_rt_error_burst __read_mostly	= 5 * HZ;
 static int ip_rt_mtu_expires __read_mostly	= 10 * 60 * HZ;
-static int ip_rt_min_pmtu __read_mostly		= 512 + 20 + 20;
+static u32 ip_rt_min_pmtu __read_mostly		= 512 + 20 + 20;
 static int ip_rt_min_advmss __read_mostly	= 256;
 
 static int ip_rt_gc_timeout __read_mostly	= RT_GC_TIMEOUT;
+
+static int ip_min_valid_pmtu __read_mostly	= IPV4_MIN_MTU;
+
 /*
  *	Interface to generic destination cache.
  */
@@ -2934,7 +2937,8 @@ static struct ctl_table ipv4_route_table[] = {
 		.data		= &ip_rt_min_pmtu,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &ip_min_valid_pmtu,
 	},
 	{
 		.procname	= "min_adv_mss",
-- 
2.14.3


From d7d751c3a41e3eaed5fcb8b8ffccc33660639991 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Tue, 6 Feb 2018 14:48:32 +0100
Subject: [PATCH 09/59] netlink: ensure to loop over all netns in
 genlmsg_multicast_allns()

[ Upstream commit cb9f7a9a5c96a773bbc9c70660dc600cfff82f82 ]

Nowadays, nlmsg_multicast() returns only 0 or -ESRCH but this was not the
case when commit 134e63756d5f was pushed.
However, there was no reason to stop the loop if a netns does not have
listeners.
Returns -ESRCH only if there was no listeners in all netns.

To avoid having the same problem in the future, I didn't take the
assumption that nlmsg_multicast() returns only 0 or -ESRCH.

Fixes: 134e63756d5f ("genetlink: make netns aware")
CC: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/genetlink.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index d444daf1ac04..6f02499ef007 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -1081,6 +1081,7 @@ static int genlmsg_mcast(struct sk_buff *skb, u32 portid, unsigned long group,
 {
 	struct sk_buff *tmp;
 	struct net *net, *prev = NULL;
+	bool delivered = false;
 	int err;
 
 	for_each_net_rcu(net) {
@@ -1092,14 +1093,21 @@ static int genlmsg_mcast(struct sk_buff *skb, u32 portid, unsigned long group,
 			}
 			err = nlmsg_multicast(prev->genl_sock, tmp,
 					      portid, group, flags);
-			if (err)
+			if (!err)
+				delivered = true;
+			else if (err != -ESRCH)
 				goto error;
 		}
 
 		prev = net;
 	}
 
-	return nlmsg_multicast(prev->genl_sock, skb, portid, group, flags);
+	err = nlmsg_multicast(prev->genl_sock, skb, portid, group, flags);
+	if (!err)
+		delivered = true;
+	else if (err != -ESRCH)
+		goto error;
+	return delivered ? 0 : -ESRCH;
  error:
 	kfree_skb(skb);
 	return err;
-- 
2.14.3


From e1722cad1b4ab30c5825573945ef730841f5f073 Mon Sep 17 00:00:00 2001
From: Roman Kapl <code@rkapl.cz>
Date: Mon, 19 Feb 2018 21:32:51 +0100
Subject: [PATCH 10/59] net: sched: report if filter is too large to dump

[ Upstream commit 5ae437ad5a2ed573b1ebb04e0afa70b8869f88dd ]

So far, if the filter was too large to fit in the allocated skb, the
kernel did not return any error and stopped dumping. Modify the dumper
so that it returns -EMSGSIZE when a filter fails to dump and it is the
first filter in the skb. If we are not first, we will get a next chance
with more room.

I understand this is pretty near to being an API change, but the
original design (silent truncation) can be considered a bug.

Note: The error case can happen pretty easily if you create a filter
with 32 actions and have 4kb pages. Also recent versions of iproute try
to be clever with their buffer allocation size, which in turn leads to

Signed-off-by: Roman Kapl <code@rkapl.cz>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index e6b853f0ee4f..2e437bbd3358 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1054,13 +1054,18 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
 		    nla_get_u32(tca[TCA_CHAIN]) != chain->index)
 			continue;
 		if (!tcf_chain_dump(chain, q, parent, skb, cb,
-				    index_start, &index))
+				    index_start, &index)) {
+			err = -EMSGSIZE;
 			break;
+		}
 	}
 
 	cb->args[0] = index;
 
 out:
+	/* If we did no progress, the error (EMSGSIZE) is real */
+	if (skb->len == 0 && err)
+		return err;
 	return skb->len;
 }
 
-- 
2.14.3


From d34a513ba30f0fe28c175c6bf50f6b7dacdf42cb Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Fri, 2 Mar 2018 18:41:16 +0100
Subject: [PATCH 11/59] ppp: prevent unregistered channels from connecting to
 PPP units

[ Upstream commit 77f840e3e5f09c6d7d727e85e6e08276dd813d11 ]

PPP units don't hold any reference on the channels connected to it.
It is the channel's responsibility to ensure that it disconnects from
its unit before being destroyed.
In practice, this is ensured by ppp_unregister_channel() disconnecting
the channel from the unit before dropping a reference on the channel.

However, it is possible for an unregistered channel to connect to a PPP
unit: register a channel with ppp_register_net_channel(), attach a
/dev/ppp file to it with ioctl(PPPIOCATTCHAN), unregister the channel
with ppp_unregister_channel() and finally connect the /dev/ppp file to
a PPP unit with ioctl(PPPIOCCONNECT).

Once in this situation, the channel is only held by the /dev/ppp file,
which can be released at anytime and free the channel without letting
the parent PPP unit know. Then the ppp structure ends up with dangling
pointers in its ->channels list.

Prevent this scenario by forbidding unregistered channels from
connecting to PPP units. This maintains the code logic by keeping
ppp_unregister_channel() responsible from disconnecting the channel if
necessary and avoids modification on the reference counting mechanism.

This issue seems to predate git history (successfully reproduced on
Linux 2.6.26 and earlier PPP commits are unrelated).

Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/ppp_generic.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 264d4af0bf69..9f79f9274c50 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -3161,6 +3161,15 @@ ppp_connect_channel(struct channel *pch, int unit)
 		goto outl;
 
 	ppp_lock(ppp);
+	spin_lock_bh(&pch->downl);
+	if (!pch->chan) {
+		/* Don't connect unregistered channels */
+		spin_unlock_bh(&pch->downl);
+		ppp_unlock(ppp);
+		ret = -ENOTCONN;
+		goto outl;
+	}
+	spin_unlock_bh(&pch->downl);
 	if (pch->file.hdrlen > ppp->file.hdrlen)
 		ppp->file.hdrlen = pch->file.hdrlen;
 	hdrlen = pch->file.hdrlen + 2;	/* for protocol bytes */
-- 
2.14.3


From 113cf7babeb2a8bb5e21f2c0e56fe845557bed5c Mon Sep 17 00:00:00 2001
From: Alexey Kodanev <alexey.kodanev@oracle.com>
Date: Fri, 9 Feb 2018 17:35:23 +0300
Subject: [PATCH 12/59] sctp: verify size of a new chunk in _sctp_make_chunk()

[ Upstream commit 07f2c7ab6f8d0a7e7c5764c4e6cc9c52951b9d9c ]

When SCTP makes INIT or INIT_ACK packet the total chunk length
can exceed SCTP_MAX_CHUNK_LEN which leads to kernel panic when
transmitting these packets, e.g. the crash on sending INIT_ACK:

[  597.804948] skbuff: skb_over_panic: text:00000000ffae06e4 len:120168
               put:120156 head:000000007aa47635 data:00000000d991c2de
               tail:0x1d640 end:0xfec0 dev:<NULL>
...
[  597.976970] ------------[ cut here ]------------
[  598.033408] kernel BUG at net/core/skbuff.c:104!
[  600.314841] Call Trace:
[  600.345829]  <IRQ>
[  600.371639]  ? sctp_packet_transmit+0x2095/0x26d0 [sctp]
[  600.436934]  skb_put+0x16c/0x200
[  600.477295]  sctp_packet_transmit+0x2095/0x26d0 [sctp]
[  600.540630]  ? sctp_packet_config+0x890/0x890 [sctp]
[  600.601781]  ? __sctp_packet_append_chunk+0x3b4/0xd00 [sctp]
[  600.671356]  ? sctp_cmp_addr_exact+0x3f/0x90 [sctp]
[  600.731482]  sctp_outq_flush+0x663/0x30d0 [sctp]
[  600.788565]  ? sctp_make_init+0xbf0/0xbf0 [sctp]
[  600.845555]  ? sctp_check_transmitted+0x18f0/0x18f0 [sctp]
[  600.912945]  ? sctp_outq_tail+0x631/0x9d0 [sctp]
[  600.969936]  sctp_cmd_interpreter.isra.22+0x3be1/0x5cb0 [sctp]
[  601.041593]  ? sctp_sf_do_5_1B_init+0x85f/0xc30 [sctp]
[  601.104837]  ? sctp_generate_t1_cookie_event+0x20/0x20 [sctp]
[  601.175436]  ? sctp_eat_data+0x1710/0x1710 [sctp]
[  601.233575]  sctp_do_sm+0x182/0x560 [sctp]
[  601.284328]  ? sctp_has_association+0x70/0x70 [sctp]
[  601.345586]  ? sctp_rcv+0xef4/0x32f0 [sctp]
[  601.397478]  ? sctp6_rcv+0xa/0x20 [sctp]
...

Here the chunk size for INIT_ACK packet becomes too big, mostly
because of the state cookie (INIT packet has large size with
many address parameters), plus additional server parameters.

Later this chunk causes the panic in skb_put_data():

  skb_packet_transmit()
      sctp_packet_pack()
          skb_put_data(nskb, chunk->skb->data, chunk->skb->len);

'nskb' (head skb) was previously allocated with packet->size
from u16 'chunk->chunk_hdr->length'.

As suggested by Marcelo we should check the chunk's length in
_sctp_make_chunk() before trying to allocate skb for it and
discard a chunk if its size bigger than SCTP_MAX_CHUNK_LEN.

Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leinter@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sm_make_chunk.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 9bf575f2e8ed..ea4226e382f9 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -1378,9 +1378,14 @@ static struct sctp_chunk *_sctp_make_chunk(const struct sctp_association *asoc,
 	struct sctp_chunk *retval;
 	struct sk_buff *skb;
 	struct sock *sk;
+	int chunklen;
+
+	chunklen = SCTP_PAD4(sizeof(*chunk_hdr) + paylen);
+	if (chunklen > SCTP_MAX_CHUNK_LEN)
+		goto nodata;
 
 	/* No need to allocate LL here, as this is only a chunk. */
-	skb = alloc_skb(SCTP_PAD4(sizeof(*chunk_hdr) + paylen), gfp);
+	skb = alloc_skb(chunklen, gfp);
 	if (!skb)
 		goto nodata;
 
-- 
2.14.3


From 239990216d2379d19ecd717391925ac643526396 Mon Sep 17 00:00:00 2001
From: Alexey Kodanev <alexey.kodanev@oracle.com>
Date: Thu, 15 Feb 2018 20:18:43 +0300
Subject: [PATCH 13/59] udplite: fix partial checksum initialization

[ Upstream commit 15f35d49c93f4fa9875235e7bf3e3783d2dd7a1b ]

Since UDP-Lite is always using checksum, the following path is
triggered when calculating pseudo header for it:

  udp4_csum_init() or udp6_csum_init()
    skb_checksum_init_zero_check()
      __skb_checksum_validate_complete()

The problem can appear if skb->len is less than CHECKSUM_BREAK. In
this particular case __skb_checksum_validate_complete() also invokes
__skb_checksum_complete(skb). If UDP-Lite is using partial checksum
that covers only part of a packet, the function will return bad
checksum and the packet will be dropped.

It can be fixed if we skip skb_checksum_init_zero_check() and only
set the required pseudo header checksum for UDP-Lite with partial
checksum before udp4_csum_init()/udp6_csum_init() functions return.

Fixes: ed70fcfcee95 ("net: Call skb_checksum_init in IPv4")
Fixes: e4f45b7f40bd ("net: Call skb_checksum_init in IPv6")
Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/udplite.h   | 1 +
 net/ipv4/udp.c          | 5 +++++
 net/ipv6/ip6_checksum.c | 5 +++++
 3 files changed, 11 insertions(+)

diff --git a/include/net/udplite.h b/include/net/udplite.h
index 81bdbf97319b..9185e45b997f 100644
--- a/include/net/udplite.h
+++ b/include/net/udplite.h
@@ -64,6 +64,7 @@ static inline int udplite_checksum_init(struct sk_buff *skb, struct udphdr *uh)
 		UDP_SKB_CB(skb)->cscov = cscov;
 		if (skb->ip_summed == CHECKSUM_COMPLETE)
 			skb->ip_summed = CHECKSUM_NONE;
+		skb->csum_valid = 0;
         }
 
 	return 0;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index e4ff25c947c5..590f9ed90c1f 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2031,6 +2031,11 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh,
 		err = udplite_checksum_init(skb, uh);
 		if (err)
 			return err;
+
+		if (UDP_SKB_CB(skb)->partial_cov) {
+			skb->csum = inet_compute_pseudo(skb, proto);
+			return 0;
+		}
 	}
 
 	/* Note, we are only interested in != 0 or == 0, thus the
diff --git a/net/ipv6/ip6_checksum.c b/net/ipv6/ip6_checksum.c
index ec43d18b5ff9..547515e8450a 100644
--- a/net/ipv6/ip6_checksum.c
+++ b/net/ipv6/ip6_checksum.c
@@ -73,6 +73,11 @@ int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto)
 		err = udplite_checksum_init(skb, uh);
 		if (err)
 			return err;
+
+		if (UDP_SKB_CB(skb)->partial_cov) {
+			skb->csum = ip6_compute_pseudo(skb, proto);
+			return 0;
+		}
 	}
 
 	/* To support RFC 6936 (allow zero checksum in UDP/IPV6 for tunnels)
-- 
2.14.3


From 7fd6b94d5c2a8c132fd661c8606eff64d9aa0b9c Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Wed, 20 Dec 2017 08:48:24 +0200
Subject: [PATCH 14/59] net/mlx5e: Fix TCP checksum in LRO buffers

[ Upstream commit 8babd44d2079079f9d5a4aca7005aed80236efe0 ]

When receiving an LRO packet, the checksum field is set by the hardware
to the checksum of the first coalesced packet. Obviously, this checksum
is not valid for the merged LRO packet and should be fixed.  We can use
the CQE checksum which covers the checksum of the entire merged packet
TCP payload to help us calculate the checksum incrementally.

Tested by sending IPv4/6 traffic with LRO enabled, RX checksum disabled
and watching nstat checksum error counters (in addition to the obvious
bandwidth drop caused by checksum errors).

This bug is usually "hidden" since LRO packets would go through the
CHECKSUM_UNNECESSARY flow which does not validate the packet checksum.

It's important to note that previous to this patch, LRO packets provided
with CHECKSUM_UNNECESSARY are indeed packets with a correct validated
checksum (even though the checksum inside the TCP header is incorrect),
since the hardware LRO aggregation is terminated upon receiving a packet
with bad checksum.

Fixes: e586b3b0baee ("net/mlx5: Ethernet Datapath files")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 49 ++++++++++++++++++-------
 1 file changed, 35 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 5b499c7a698f..36611b64a91c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -36,6 +36,7 @@
 #include <linux/tcp.h>
 #include <linux/bpf_trace.h>
 #include <net/busy_poll.h>
+#include <net/ip6_checksum.h>
 #include "en.h"
 #include "en_tc.h"
 #include "eswitch.h"
@@ -547,20 +548,33 @@ bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq)
 	return true;
 }
 
+static void mlx5e_lro_update_tcp_hdr(struct mlx5_cqe64 *cqe, struct tcphdr *tcp)
+{
+	u8 l4_hdr_type = get_cqe_l4_hdr_type(cqe);
+	u8 tcp_ack     = (l4_hdr_type == CQE_L4_HDR_TYPE_TCP_ACK_NO_DATA) ||
+			 (l4_hdr_type == CQE_L4_HDR_TYPE_TCP_ACK_AND_DATA);
+
+	tcp->check                      = 0;
+	tcp->psh                        = get_cqe_lro_tcppsh(cqe);
+
+	if (tcp_ack) {
+		tcp->ack                = 1;
+		tcp->ack_seq            = cqe->lro_ack_seq_num;
+		tcp->window             = cqe->lro_tcp_win;
+	}
+}
+
 static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe,
 				 u32 cqe_bcnt)
 {
 	struct ethhdr	*eth = (struct ethhdr *)(skb->data);
 	struct tcphdr	*tcp;
 	int network_depth = 0;
+	__wsum check;
 	__be16 proto;
 	u16 tot_len;
 	void *ip_p;
 
-	u8 l4_hdr_type = get_cqe_l4_hdr_type(cqe);
-	u8 tcp_ack = (l4_hdr_type == CQE_L4_HDR_TYPE_TCP_ACK_NO_DATA) ||
-		(l4_hdr_type == CQE_L4_HDR_TYPE_TCP_ACK_AND_DATA);
-
 	proto = __vlan_get_protocol(skb, eth->h_proto, &network_depth);
 
 	tot_len = cqe_bcnt - network_depth;
@@ -577,23 +591,30 @@ static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe,
 		ipv4->check             = 0;
 		ipv4->check             = ip_fast_csum((unsigned char *)ipv4,
 						       ipv4->ihl);
+
+		mlx5e_lro_update_tcp_hdr(cqe, tcp);
+		check = csum_partial(tcp, tcp->doff * 4,
+				     csum_unfold((__force __sum16)cqe->check_sum));
+		/* Almost done, don't forget the pseudo header */
+		tcp->check = csum_tcpudp_magic(ipv4->saddr, ipv4->daddr,
+					       tot_len - sizeof(struct iphdr),
+					       IPPROTO_TCP, check);
 	} else {
+		u16 payload_len = tot_len - sizeof(struct ipv6hdr);
 		struct ipv6hdr *ipv6 = ip_p;
 
 		tcp = ip_p + sizeof(struct ipv6hdr);
 		skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
 
 		ipv6->hop_limit         = cqe->lro_min_ttl;
-		ipv6->payload_len       = cpu_to_be16(tot_len -
-						      sizeof(struct ipv6hdr));
-	}
-
-	tcp->psh = get_cqe_lro_tcppsh(cqe);
-
-	if (tcp_ack) {
-		tcp->ack                = 1;
-		tcp->ack_seq            = cqe->lro_ack_seq_num;
-		tcp->window             = cqe->lro_tcp_win;
+		ipv6->payload_len       = cpu_to_be16(payload_len);
+
+		mlx5e_lro_update_tcp_hdr(cqe, tcp);
+		check = csum_partial(tcp, tcp->doff * 4,
+				     csum_unfold((__force __sum16)cqe->check_sum));
+		/* Almost done, don't forget the pseudo header */
+		tcp->check = csum_ipv6_magic(&ipv6->saddr, &ipv6->daddr, payload_len,
+					     IPPROTO_TCP, check);
 	}
 }
 
-- 
2.14.3


From a35b0fdeae2e12a9326124a3b099211a08b37730 Mon Sep 17 00:00:00 2001
From: Tommi Rantala <tommi.t.rantala@nokia.com>
Date: Mon, 5 Feb 2018 21:48:14 +0200
Subject: [PATCH 15/59] sctp: fix dst refcnt leak in sctp_v4_get_dst

[ Upstream commit 4a31a6b19f9ddf498c81f5c9b089742b7472a6f8 ]

Fix dst reference count leak in sctp_v4_get_dst() introduced in commit
410f03831 ("sctp: add routing output fallback"):

When walking the address_list, successive ip_route_output_key() calls
may return the same rt->dst with the reference incremented on each call.

The code would not decrement the dst refcount when the dst pointer was
identical from the previous iteration, causing the dst refcnt leak.

Testcase:
  ip netns add TEST
  ip netns exec TEST ip link set lo up
  ip link add dummy0 type dummy
  ip link add dummy1 type dummy
  ip link add dummy2 type dummy
  ip link set dev dummy0 netns TEST
  ip link set dev dummy1 netns TEST
  ip link set dev dummy2 netns TEST
  ip netns exec TEST ip addr add 192.168.1.1/24 dev dummy0
  ip netns exec TEST ip link set dummy0 up
  ip netns exec TEST ip addr add 192.168.1.2/24 dev dummy1
  ip netns exec TEST ip link set dummy1 up
  ip netns exec TEST ip addr add 192.168.1.3/24 dev dummy2
  ip netns exec TEST ip link set dummy2 up
  ip netns exec TEST sctp_test -H 192.168.1.2 -P 20002 -h 192.168.1.1 -p 20000 -s -B 192.168.1.3
  ip netns del TEST

In 4.4 and 4.9 kernels this results to:
  [  354.179591] unregister_netdevice: waiting for lo to become free. Usage count = 1
  [  364.419674] unregister_netdevice: waiting for lo to become free. Usage count = 1
  [  374.663664] unregister_netdevice: waiting for lo to become free. Usage count = 1
  [  384.903717] unregister_netdevice: waiting for lo to become free. Usage count = 1
  [  395.143724] unregister_netdevice: waiting for lo to become free. Usage count = 1
  [  405.383645] unregister_netdevice: waiting for lo to become free. Usage count = 1
  ...

Fixes: 410f03831 ("sctp: add routing output fallback")
Fixes: 0ca50d12f ("sctp: fix src address selection if using secondary addresses")
Signed-off-by: Tommi Rantala <tommi.t.rantala@nokia.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/protocol.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 6a38c2503649..91813e686c67 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -514,22 +514,20 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 		if (IS_ERR(rt))
 			continue;
 
-		if (!dst)
-			dst = &rt->dst;
-
 		/* Ensure the src address belongs to the output
 		 * interface.
 		 */
 		odev = __ip_dev_find(sock_net(sk), laddr->a.v4.sin_addr.s_addr,
 				     false);
 		if (!odev || odev->ifindex != fl4->flowi4_oif) {
-			if (&rt->dst != dst)
+			if (!dst)
+				dst = &rt->dst;
+			else
 				dst_release(&rt->dst);
 			continue;
 		}
 
-		if (dst != &rt->dst)
-			dst_release(dst);
+		dst_release(dst);
 		dst = &rt->dst;
 		break;
 	}
-- 
2.14.3


From 9baff0c32ba6aa7c3f687c2d82242410b483a2d1 Mon Sep 17 00:00:00 2001
From: Shalom Toledo <shalomt@mellanox.com>
Date: Thu, 1 Mar 2018 11:37:05 +0100
Subject: [PATCH 16/59] mlxsw: spectrum_switchdev: Check success of FDB add
 operation

[ Upstream commit 0a8a1bf17e3af34f1f8d2368916a6327f8b3bfd5 ]

Until now, we assumed that in case of error when adding FDB entries, the
write operation will fail, but this is not the case. Instead, we need to
check that the number of entries reported in the response is equal to
the number of entries specified in the request.

Fixes: 56ade8fe3fe1 ("mlxsw: spectrum: Add initial support for Spectrum ASIC")
Reported-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Shalom Toledo <shalomt@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/spectrum_switchdev.c   | 29 ++++++++++++++++++++--
 1 file changed, 27 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 593ad31be749..161bcdc012f0 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -1203,6 +1203,7 @@ static int __mlxsw_sp_port_fdb_uc_op(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 				     bool dynamic)
 {
 	char *sfd_pl;
+	u8 num_rec;
 	int err;
 
 	sfd_pl = kmalloc(MLXSW_REG_SFD_LEN, GFP_KERNEL);
@@ -1212,9 +1213,16 @@ static int __mlxsw_sp_port_fdb_uc_op(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 	mlxsw_reg_sfd_pack(sfd_pl, mlxsw_sp_sfd_op(adding), 0);
 	mlxsw_reg_sfd_uc_pack(sfd_pl, 0, mlxsw_sp_sfd_rec_policy(dynamic),
 			      mac, fid, action, local_port);
+	num_rec = mlxsw_reg_sfd_num_rec_get(sfd_pl);
 	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfd), sfd_pl);
-	kfree(sfd_pl);
+	if (err)
+		goto out;
+
+	if (num_rec != mlxsw_reg_sfd_num_rec_get(sfd_pl))
+		err = -EBUSY;
 
+out:
+	kfree(sfd_pl);
 	return err;
 }
 
@@ -1239,6 +1247,7 @@ static int mlxsw_sp_port_fdb_uc_lag_op(struct mlxsw_sp *mlxsw_sp, u16 lag_id,
 				       bool adding, bool dynamic)
 {
 	char *sfd_pl;
+	u8 num_rec;
 	int err;
 
 	sfd_pl = kmalloc(MLXSW_REG_SFD_LEN, GFP_KERNEL);
@@ -1249,9 +1258,16 @@ static int mlxsw_sp_port_fdb_uc_lag_op(struct mlxsw_sp *mlxsw_sp, u16 lag_id,
 	mlxsw_reg_sfd_uc_lag_pack(sfd_pl, 0, mlxsw_sp_sfd_rec_policy(dynamic),
 				  mac, fid, MLXSW_REG_SFD_REC_ACTION_NOP,
 				  lag_vid, lag_id);
+	num_rec = mlxsw_reg_sfd_num_rec_get(sfd_pl);
 	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfd), sfd_pl);
-	kfree(sfd_pl);
+	if (err)
+		goto out;
+
+	if (num_rec != mlxsw_reg_sfd_num_rec_get(sfd_pl))
+		err = -EBUSY;
 
+out:
+	kfree(sfd_pl);
 	return err;
 }
 
@@ -1296,6 +1312,7 @@ static int mlxsw_sp_port_mdb_op(struct mlxsw_sp *mlxsw_sp, const char *addr,
 				u16 fid, u16 mid_idx, bool adding)
 {
 	char *sfd_pl;
+	u8 num_rec;
 	int err;
 
 	sfd_pl = kmalloc(MLXSW_REG_SFD_LEN, GFP_KERNEL);
@@ -1305,7 +1322,15 @@ static int mlxsw_sp_port_mdb_op(struct mlxsw_sp *mlxsw_sp, const char *addr,
 	mlxsw_reg_sfd_pack(sfd_pl, mlxsw_sp_sfd_op(adding), 0);
 	mlxsw_reg_sfd_mc_pack(sfd_pl, 0, addr, fid,
 			      MLXSW_REG_SFD_REC_ACTION_NOP, mid_idx);
+	num_rec = mlxsw_reg_sfd_num_rec_get(sfd_pl);
 	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfd), sfd_pl);
+	if (err)
+		goto out;
+
+	if (num_rec != mlxsw_reg_sfd_num_rec_get(sfd_pl))
+		err = -EBUSY;
+
+out:
 	kfree(sfd_pl);
 	return err;
 }
-- 
2.14.3


From 1f9f68c2e33053f1eb2b61e0876bd47bf4f0eef4 Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Thu, 25 Jan 2018 18:00:41 +0200
Subject: [PATCH 17/59] net/mlx5e: Specify numa node when allocating drop rq

[ Upstream commit 2f0db87901698cd73d828cc6fb1957b8916fc911 ]

When allocating a drop rq, no numa node is explicitly set which means
allocations are done on node zero. This is not necessarily the nearest
numa node to the HCA, and even worse, might even be a memoryless numa
node.

Choose the numa_node given to us by the pci device in order to properly
allocate the coherent dma memory instead of assuming zero is valid.

Fixes: 556dd1b9c313 ("net/mlx5e: Set drop RQ's necessary parameters only")
Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index d8aefeed124d..0d352d4cf48c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1911,13 +1911,16 @@ static void mlx5e_build_rq_param(struct mlx5e_priv *priv,
 	param->wq.linear = 1;
 }
 
-static void mlx5e_build_drop_rq_param(struct mlx5e_rq_param *param)
+static void mlx5e_build_drop_rq_param(struct mlx5_core_dev *mdev,
+				      struct mlx5e_rq_param *param)
 {
 	void *rqc = param->rqc;
 	void *wq = MLX5_ADDR_OF(rqc, rqc, wq);
 
 	MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_LINKED_LIST);
 	MLX5_SET(wq, wq, log_wq_stride,    ilog2(sizeof(struct mlx5e_rx_wqe)));
+
+	param->wq.buf_numa_node = dev_to_node(&mdev->pdev->dev);
 }
 
 static void mlx5e_build_sq_param_common(struct mlx5e_priv *priv,
@@ -2774,6 +2777,9 @@ static int mlx5e_alloc_drop_cq(struct mlx5_core_dev *mdev,
 			       struct mlx5e_cq *cq,
 			       struct mlx5e_cq_param *param)
 {
+	param->wq.buf_numa_node = dev_to_node(&mdev->pdev->dev);
+	param->wq.db_numa_node  = dev_to_node(&mdev->pdev->dev);
+
 	return mlx5e_alloc_cq_common(mdev, param, cq);
 }
 
@@ -2785,7 +2791,7 @@ static int mlx5e_open_drop_rq(struct mlx5_core_dev *mdev,
 	struct mlx5e_cq *cq = &drop_rq->cq;
 	int err;
 
-	mlx5e_build_drop_rq_param(&rq_param);
+	mlx5e_build_drop_rq_param(mdev, &rq_param);
 
 	err = mlx5e_alloc_drop_cq(mdev, cq, &cq_param);
 	if (err)
-- 
2.14.3


From b9785c251cca1fbecbc78d344f5740fff0fe063b Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 8 Feb 2018 21:01:48 +0100
Subject: [PATCH 18/59] net: phy: fix phy_start to consider
 PHY_IGNORE_INTERRUPT

[ Upstream commit 08f5138512180a479ce6b9d23b825c9f4cd3be77 ]

This condition wasn't adjusted when PHY_IGNORE_INTERRUPT (-2) was added
long ago. In case of PHY_IGNORE_INTERRUPT the MAC interrupt indicates
also PHY state changes and we should do what the symbol says.

Fixes: 84a527a41f38 ("net: phylib: fix interrupts re-enablement in phy_start")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index ed10d1fc8f59..26ad88f09795 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -844,7 +844,7 @@ void phy_start(struct phy_device *phydev)
 		phy_resume(phydev);
 
 		/* make sure interrupts are re-enabled for the PHY */
-		if (phydev->irq != PHY_POLL) {
+		if (phy_interrupt_is_valid(phydev)) {
 			err = phy_enable_interrupts(phydev);
 			if (err < 0)
 				break;
-- 
2.14.3


From 46966750cbf4bad147ac5e471fdf2eeb0a591140 Mon Sep 17 00:00:00 2001
From: Ilya Lesokhin <ilyal@mellanox.com>
Date: Mon, 12 Feb 2018 12:57:04 +0200
Subject: [PATCH 19/59] tcp: Honor the eor bit in tcp_mtu_probe

[ Upstream commit 808cf9e38cd7923036a99f459ccc8cf2955e47af ]

Avoid SKB coalescing if eor bit is set in one of the relevant
SKBs.

Fixes: c134ecb87817 ("tcp: Make use of MSG_EOR in tcp_sendmsg")
Signed-off-by: Ilya Lesokhin <ilyal@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index a4d214c7b506..3aa89f13cf93 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2026,6 +2026,24 @@ static inline void tcp_mtu_check_reprobe(struct sock *sk)
 	}
 }
 
+static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len)
+{
+	struct sk_buff *skb, *next;
+
+	skb = tcp_send_head(sk);
+	tcp_for_write_queue_from_safe(skb, next, sk) {
+		if (len <= skb->len)
+			break;
+
+		if (unlikely(TCP_SKB_CB(skb)->eor))
+			return false;
+
+		len -= skb->len;
+	}
+
+	return true;
+}
+
 /* Create a new MTU probe if we are ready.
  * MTU probe is regularly attempting to increase the path MTU by
  * deliberately sending larger packets.  This discovers routing
@@ -2098,6 +2116,9 @@ static int tcp_mtu_probe(struct sock *sk)
 			return 0;
 	}
 
+	if (!tcp_can_coalesce_send_queue_head(sk, probe_size))
+		return -1;
+
 	/* We're allowed to probe.  Build it now. */
 	nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC, false);
 	if (!nskb)
@@ -2133,6 +2154,10 @@ static int tcp_mtu_probe(struct sock *sk)
 			/* We've eaten all the data from this skb.
 			 * Throw it away. */
 			TCP_SKB_CB(nskb)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags;
+			/* If this is the last SKB we copy and eor is set
+			 * we need to propagate it to the new skb.
+			 */
+			TCP_SKB_CB(nskb)->eor = TCP_SKB_CB(skb)->eor;
 			tcp_unlink_write_queue(skb, sk);
 			sk_wmem_free_skb(sk, skb);
 		} else {
-- 
2.14.3


From bfe4e79ed96bc02178f6e5cc9df75aa0b9bfdb8d Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 22 Feb 2018 14:38:14 +0000
Subject: [PATCH 20/59] rxrpc: Fix send in rxrpc_send_data_packet()

[ Upstream commit 93c62c45ed5fad1b87e3a45835b251cd68de9c46 ]

All the kernel_sendmsg() calls in rxrpc_send_data_packet() need to send
both parts of the iov[] buffer, but one of them does not.  Fix it so that
it does.

Without this, short IPv6 rxrpc DATA packets may be seen that have the rxrpc
header included, but no payload.

Fixes: 5a924b8951f8 ("rxrpc: Don't store the rxrpc header in the Tx queue sk_buffs")
Reported-by: Marc Dionne <marc.dionne@auristor.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/output.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index 42410e910aff..cf73dc006c3b 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -445,7 +445,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
 					(char *)&opt, sizeof(opt));
 		if (ret == 0) {
 			ret = kernel_sendmsg(conn->params.local->socket, &msg,
-					     iov, 1, iov[0].iov_len);
+					     iov, 2, len);
 
 			opt = IPV6_PMTUDISC_DO;
 			kernel_setsockopt(conn->params.local->socket,
-- 
2.14.3


From 6ebf76bb88ff67f46ae195f468697bd4202ecbef Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 21 Feb 2018 06:43:03 -0800
Subject: [PATCH 21/59] tcp_bbr: better deal with suboptimal GSO
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 350c9f484bde93ef229682eedd98cd5f74350f7f ]

BBR uses tcp_tso_autosize() in an attempt to probe what would be the
burst sizes and to adjust cwnd in bbr_target_cwnd() with following
gold formula :

/* Allow enough full-sized skbs in flight to utilize end systems. */
cwnd += 3 * bbr->tso_segs_goal;

But GSO can be lacking or be constrained to very small
units (ip link set dev ... gso_max_segs 2)

What we really want is to have enough packets in flight so that both
GSO and GRO are efficient.

So in the case GSO is off or downgraded, we still want to have the same
number of packets in flight as if GSO/TSO was fully operational, so
that GRO can hopefully be working efficiently.

To fix this issue, we make tcp_tso_autosize() unaware of
sk->sk_gso_max_segs

Only tcp_tso_segs() has to enforce the gso_max_segs limit.

Tested:

ethtool -K eth0 tso off gso off
tc qd replace dev eth0 root pfifo_fast

Before patch:
for f in {1..5}; do ./super_netperf 1 -H lpaa24 -- -K bbr; done
    691  (ss -temoi shows cwnd is stuck around 6 )
    667
    651
    631
    517

After patch :
# for f in {1..5}; do ./super_netperf 1 -H lpaa24 -- -K bbr; done
   1733 (ss -temoi shows cwnd is around 386 )
   1778
   1746
   1781
   1718

Fixes: 0f8782ea1497 ("tcp_bbr: add BBR congestion control")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 3aa89f13cf93..580912de16c2 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1730,7 +1730,7 @@ u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now,
 	 */
 	segs = max_t(u32, bytes / mss_now, min_tso_segs);
 
-	return min_t(u32, segs, sk->sk_gso_max_segs);
+	return segs;
 }
 EXPORT_SYMBOL(tcp_tso_autosize);
 
@@ -1742,9 +1742,10 @@ static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now)
 	const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops;
 	u32 tso_segs = ca_ops->tso_segs_goal ? ca_ops->tso_segs_goal(sk) : 0;
 
-	return tso_segs ? :
-		tcp_tso_autosize(sk, mss_now,
-				 sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs);
+	if (!tso_segs)
+		tso_segs = tcp_tso_autosize(sk, mss_now,
+				sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs);
+	return min_t(u32, tso_segs, sk->sk_gso_max_segs);
 }
 
 /* Returns the portion of skb which can be sent right away */
-- 
2.14.3


From 0c90a3335aef758de4787f0b2647b302b5e0fa70 Mon Sep 17 00:00:00 2001
From: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Date: Sun, 4 Feb 2018 18:07:10 -0800
Subject: [PATCH 22/59] doc: Change the min default value of tcp_wmem/tcp_rmem.

[ Upstream commit a61a86f8db92923a2a4c857c49a795bcae754497 ]

The SK_MEM_QUANTUM was changed from PAGE_SIZE to 4096. And the
tcp_wmem/tcp_rmem min default values are 4096.

Fixes: bd68a2a854ad ("net: set SK_MEM_QUANTUM to 4096")
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 46c7e1085efc..e269541a7d10 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -508,7 +508,7 @@ tcp_rmem - vector of 3 INTEGERs: min, default, max
 	min: Minimal size of receive buffer used by TCP sockets.
 	It is guaranteed to each TCP socket, even under moderate memory
 	pressure.
-	Default: 1 page
+	Default: 4K
 
 	default: initial size of receive buffer used by TCP sockets.
 	This value overrides net.core.rmem_default used by other protocols.
@@ -666,7 +666,7 @@ tcp_window_scaling - BOOLEAN
 tcp_wmem - vector of 3 INTEGERs: min, default, max
 	min: Amount of memory reserved for send buffers for TCP sockets.
 	Each TCP socket has rights to use it due to fact of its birth.
-	Default: 1 page
+	Default: 4K
 
 	default: initial size of send buffer used by TCP sockets.  This
 	value overrides net.core.wmem_default used by other protocols.
-- 
2.14.3


From 458371e5225d0d3732039dcf5711177d0707ca37 Mon Sep 17 00:00:00 2001
From: Inbar Karmy <inbark@mellanox.com>
Date: Thu, 7 Dec 2017 17:26:33 +0200
Subject: [PATCH 23/59] net/mlx5e: Fix loopback self test when GRO is off

[ Upstream commit ef7a3518f7dd4f4cf5e5b5358c93d1eb78df28fb ]

When GRO is off, the transport header pointer in sk_buff is
initialized to network's header.

To find the udp header, instead of using udp_hdr() which assumes
skb_network_header was set, manually calculate the udp header offset.

Fixes: 0952da791c97 ("net/mlx5e: Add support for loopback selftest")
Signed-off-by: Inbar Karmy <inbark@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
index 5a4608281f38..707976482c09 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
@@ -216,7 +216,8 @@ mlx5e_test_loopback_validate(struct sk_buff *skb,
 	if (iph->protocol != IPPROTO_UDP)
 		goto out;
 
-	udph = udp_hdr(skb);
+	/* Don't assume skb_transport_header() was set */
+	udph = (struct udphdr *)((u8 *)iph + 4 * iph->ihl);
 	if (udph->dest != htons(9))
 		goto out;
 
-- 
2.14.3


From e3606ab9649e36583640fa99f7fba87edc44b598 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 22 Feb 2018 19:45:27 -0800
Subject: [PATCH 24/59] net_sched: gen_estimator: fix broken estimators based
 on percpu stats

[ Upstream commit a5f7add332b4ea6d4b9480971b3b0f5e66466ae9 ]

pfifo_fast got percpu stats lately, uncovering a bug I introduced last
year in linux-4.10.

I missed the fact that we have to clear our temporary storage
before calling __gnet_stats_copy_basic() in the case of percpu stats.

Without this fix, rate estimators (tc qd replace dev xxx root est 1sec
4sec pfifo_fast) are utterly broken.

Fixes: 1c0d32fde5bd ("net_sched: gen_estimator: complete rewrite of rate estimators")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/gen_estimator.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c
index 0a3f88f08727..98fd12721221 100644
--- a/net/core/gen_estimator.c
+++ b/net/core/gen_estimator.c
@@ -66,6 +66,7 @@ struct net_rate_estimator {
 static void est_fetch_counters(struct net_rate_estimator *e,
 			       struct gnet_stats_basic_packed *b)
 {
+	memset(b, 0, sizeof(*b));
 	if (e->stats_lock)
 		spin_lock(e->stats_lock);
 
-- 
2.14.3


From deb2f89ee267d2e5b68a257902029950b80dec15 Mon Sep 17 00:00:00 2001
From: Ivan Vecera <ivecera@redhat.com>
Date: Thu, 8 Feb 2018 16:10:39 +0100
Subject: [PATCH 25/59] net/sched: cls_u32: fix cls_u32 on filter replace

[ Upstream commit eb53f7af6f15285e2f6ada97285395343ce9f433 ]

The following sequence is currently broken:

 # tc qdisc add dev foo ingress
 # tc filter replace dev foo protocol all ingress \
   u32 match u8 0 0 action mirred egress mirror dev bar1
 # tc filter replace dev foo protocol all ingress \
   handle 800::800 pref 49152 \
   u32 match u8 0 0 action mirred egress mirror dev bar2
 Error: cls_u32: Key node flags do not match passed flags.
 We have an error talking to the kernel, -1

The error comes from u32_change() when comparing new and
existing flags. The existing ones always contains one of
TCA_CLS_FLAGS_{,NOT}_IN_HW flag depending on offloading state.
These flags cannot be passed from userspace so the condition
(n->flags != flags) in u32_change() always fails.

Fix the condition so the flags TCA_CLS_FLAGS_NOT_IN_HW and
TCA_CLS_FLAGS_IN_HW are not taken into account.

Fixes: 24d3dc6d27ea ("net/sched: cls_u32: Reflect HW offload status")
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_u32.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 33294b5b2c6a..e5378b2247bb 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -928,7 +928,8 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 		if (TC_U32_KEY(n->handle) == 0)
 			return -EINVAL;
 
-		if (n->flags != flags)
+		if ((n->flags ^ flags) &
+		    ~(TCA_CLS_FLAGS_IN_HW | TCA_CLS_FLAGS_NOT_IN_HW))
 			return -EINVAL;
 
 		new = u32_init_knode(tp, n);
-- 
2.14.3


From 60b8a2c7697db8a7597f873b0b01d0daed6755a8 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 12 Feb 2018 18:29:06 +0800
Subject: [PATCH 26/59] sctp: do not pr_err for the duplicated node in
 transport rhlist

[ Upstream commit 27af86bb038d9c8b8066cd17854ddaf2ea92bce1 ]

The pr_err in sctp_hash_transport was supposed to report a sctp bug
for using rhashtable/rhlist.

The err '-EEXIST' introduced in Commit cd2b70875058 ("sctp: check
duplicate node before inserting a new transport") doesn't belong
to that case.

So just return -EEXIST back without pr_err any kmsg.

Fixes: cd2b70875058 ("sctp: check duplicate node before inserting a new transport")
Reported-by: Wei Chen <weichen@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/input.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/net/sctp/input.c b/net/sctp/input.c
index 141c9c466ec1..0247cc432e02 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -897,15 +897,12 @@ int sctp_hash_transport(struct sctp_transport *t)
 	rhl_for_each_entry_rcu(transport, tmp, list, node)
 		if (transport->asoc->ep == t->asoc->ep) {
 			rcu_read_unlock();
-			err = -EEXIST;
-			goto out;
+			return -EEXIST;
 		}
 	rcu_read_unlock();
 
 	err = rhltable_insert_key(&sctp_transport_hashtable, &arg,
 				  &t->node, sctp_hash_params);
-
-out:
 	if (err)
 		pr_err_once("insert transport fail, errno %d\n", err);
 
-- 
2.14.3


From 72ac4a4c120cf41b1493323d738aeba768714b88 Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Tue, 27 Feb 2018 14:15:01 -0800
Subject: [PATCH 27/59] tcp: revert F-RTO middle-box workaround

[ Upstream commit d4131f09770d9b7471c9da65e6ecd2477746ac5c ]

This reverts commit cc663f4d4c97b7297fb45135ab23cfd508b35a77. While fixing
some broken middle-boxes that modifies receive window fields, it does not
address middle-boxes that strip off SACK options. The best solution is
to fully revert this patch and the root F-RTO enhancement.

Fixes: cc663f4d4c97 ("tcp: restrict F-RTO to work-around broken middle-boxes")
Reported-by: Teodor Milkov <tm@del.bg>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 17 +++++++----------
 1 file changed, 7 insertions(+), 10 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 45f750e85714..50963f92a67d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1915,7 +1915,6 @@ void tcp_enter_loss(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct net *net = sock_net(sk);
 	struct sk_buff *skb;
-	bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery;
 	bool is_reneg;			/* is receiver reneging on SACKs? */
 	bool mark_lost;
 
@@ -1974,17 +1973,15 @@ void tcp_enter_loss(struct sock *sk)
 	tp->high_seq = tp->snd_nxt;
 	tcp_ecn_queue_cwr(tp);
 
-	/* F-RTO RFC5682 sec 3.1 step 1: retransmit SND.UNA if no previous
-	 * loss recovery is underway except recurring timeout(s) on
-	 * the same SND.UNA (sec 3.2). Disable F-RTO on path MTU probing
-	 *
-	 * In theory F-RTO can be used repeatedly during loss recovery.
-	 * In practice this interacts badly with broken middle-boxes that
-	 * falsely raise the receive window, which results in repeated
-	 * timeouts and stop-and-go behavior.
+	/* F-RTO RFC5682 sec 3.1 step 1 mandates to disable F-RTO
+	 * if a previous recovery is underway, otherwise it may incorrectly
+	 * call a timeout spurious if some previously retransmitted packets
+	 * are s/acked (sec 3.2). We do not apply that retriction since
+	 * retransmitted skbs are permanently tagged with TCPCB_EVER_RETRANS
+	 * so FLAG_ORIG_SACK_ACKED is always correct. But we do disable F-RTO
+	 * on PTMU discovery to avoid sending new data.
 	 */
 	tp->frto = net->ipv4.sysctl_tcp_frto &&
-		   (new_recovery || icsk->icsk_retransmits) &&
 		   !inet_csk(sk)->icsk_mtup.probe_size;
 }
 
-- 
2.14.3


From f18d57ce6b0ef32aaebfa7af34a8e3578cb020ad Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Tue, 27 Feb 2018 14:15:02 -0800
Subject: [PATCH 28/59] tcp: revert F-RTO extension to detect more spurious
 timeouts

[ Upstream commit fc68e171d376c322e6777a3d7ac2f0278b68b17f ]

This reverts commit 89fe18e44f7ee5ab1c90d0dff5835acee7751427.

While the patch could detect more spurious timeouts, it could cause
poor TCP performance on broken middle-boxes that modifies TCP packets
(e.g. receive window, SACK options). Since the performance gain is
much smaller compared to the potential loss. The best solution is
to fully revert the change.

Fixes: 89fe18e44f7e ("tcp: extend F-RTO to catch more spurious timeouts")
Reported-by: Teodor Milkov <tm@del.bg>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 30 ++++++++++++------------------
 1 file changed, 12 insertions(+), 18 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 50963f92a67d..8bb4eecca5df 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1915,6 +1915,7 @@ void tcp_enter_loss(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct net *net = sock_net(sk);
 	struct sk_buff *skb;
+	bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery;
 	bool is_reneg;			/* is receiver reneging on SACKs? */
 	bool mark_lost;
 
@@ -1973,15 +1974,12 @@ void tcp_enter_loss(struct sock *sk)
 	tp->high_seq = tp->snd_nxt;
 	tcp_ecn_queue_cwr(tp);
 
-	/* F-RTO RFC5682 sec 3.1 step 1 mandates to disable F-RTO
-	 * if a previous recovery is underway, otherwise it may incorrectly
-	 * call a timeout spurious if some previously retransmitted packets
-	 * are s/acked (sec 3.2). We do not apply that retriction since
-	 * retransmitted skbs are permanently tagged with TCPCB_EVER_RETRANS
-	 * so FLAG_ORIG_SACK_ACKED is always correct. But we do disable F-RTO
-	 * on PTMU discovery to avoid sending new data.
+	/* F-RTO RFC5682 sec 3.1 step 1: retransmit SND.UNA if no previous
+	 * loss recovery is underway except recurring timeout(s) on
+	 * the same SND.UNA (sec 3.2). Disable F-RTO on path MTU probing
 	 */
 	tp->frto = net->ipv4.sysctl_tcp_frto &&
+		   (new_recovery || icsk->icsk_retransmits) &&
 		   !inet_csk(sk)->icsk_mtup.probe_size;
 }
 
@@ -2634,18 +2632,14 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack,
 	    tcp_try_undo_loss(sk, false))
 		return;
 
-	/* The ACK (s)acks some never-retransmitted data meaning not all
-	 * the data packets before the timeout were lost. Therefore we
-	 * undo the congestion window and state. This is essentially
-	 * the operation in F-RTO (RFC5682 section 3.1 step 3.b). Since
-	 * a retransmitted skb is permantly marked, we can apply such an
-	 * operation even if F-RTO was not used.
-	 */
-	if ((flag & FLAG_ORIG_SACK_ACKED) &&
-	    tcp_try_undo_loss(sk, tp->undo_marker))
-		return;
-
 	if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */
+		/* Step 3.b. A timeout is spurious if not all data are
+		 * lost, i.e., never-retransmitted data are (s)acked.
+		 */
+		if ((flag & FLAG_ORIG_SACK_ACKED) &&
+		    tcp_try_undo_loss(sk, true))
+			return;
+
 		if (after(tp->snd_nxt, tp->high_seq)) {
 			if (flag & FLAG_DATA_SACKED || is_dupack)
 				tp->frto = 0; /* Step 3.a. loss was real */
-- 
2.14.3


From df4e4bbfd10c0984066c272d77c2c0afdb21ccf2 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Tue, 13 Feb 2018 11:22:42 +0100
Subject: [PATCH 29/59] mlxsw: spectrum_router: Fix error path in
 mlxsw_sp_vr_create

[ Upstream commit 0f2d2b2736b08dafa3bde31d048750fbc8df3a31 ]

Since mlxsw_sp_fib_create() and mlxsw_sp_mr_table_create()
use ERR_PTR macro to propagate int err through return of a pointer,
the return value is not NULL in case of failure. So if one
of the calls fails, one of vr->fib4, vr->fib6 or vr->mr4_table
is not NULL and mlxsw_sp_vr_is_used wrongly assumes
that vr is in use which leads to crash like following one:

[ 1293.949291] BUG: unable to handle kernel NULL pointer dereference at 00000000000006c9
[ 1293.952729] IP: mlxsw_sp_mr_table_flush+0x15/0x70 [mlxsw_spectrum]

Fix this by using local variables to hold the pointers and set vr->*
only in case everything went fine.

Fixes: 76610ebbde18 ("mlxsw: spectrum_router: Refactor virtual router handling")
Fixes: a3d9bc506d64 ("mlxsw: spectrum_router: Extend virtual routers with IPv6 support")
Fixes: d42b0965b1d4 ("mlxsw: spectrum_router: Add multicast routes notification handling functionality")
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_router.c  | 32 ++++++++++++----------
 1 file changed, 18 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 7042c855a5d6..1110e2d33f00 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -737,6 +737,9 @@ static struct mlxsw_sp_vr *mlxsw_sp_vr_create(struct mlxsw_sp *mlxsw_sp,
 					      u32 tb_id,
 					      struct netlink_ext_ack *extack)
 {
+	struct mlxsw_sp_mr_table *mr4_table;
+	struct mlxsw_sp_fib *fib4;
+	struct mlxsw_sp_fib *fib6;
 	struct mlxsw_sp_vr *vr;
 	int err;
 
@@ -745,29 +748,30 @@ static struct mlxsw_sp_vr *mlxsw_sp_vr_create(struct mlxsw_sp *mlxsw_sp,
 		NL_SET_ERR_MSG(extack, "spectrum: Exceeded number of supported virtual routers");
 		return ERR_PTR(-EBUSY);
 	}
-	vr->fib4 = mlxsw_sp_fib_create(vr, MLXSW_SP_L3_PROTO_IPV4);
-	if (IS_ERR(vr->fib4))
-		return ERR_CAST(vr->fib4);
-	vr->fib6 = mlxsw_sp_fib_create(vr, MLXSW_SP_L3_PROTO_IPV6);
-	if (IS_ERR(vr->fib6)) {
-		err = PTR_ERR(vr->fib6);
+	fib4 = mlxsw_sp_fib_create(vr, MLXSW_SP_L3_PROTO_IPV4);
+	if (IS_ERR(fib4))
+		return ERR_CAST(fib4);
+	fib6 = mlxsw_sp_fib_create(vr, MLXSW_SP_L3_PROTO_IPV6);
+	if (IS_ERR(fib6)) {
+		err = PTR_ERR(fib6);
 		goto err_fib6_create;
 	}
-	vr->mr4_table = mlxsw_sp_mr_table_create(mlxsw_sp, vr->id,
-						 MLXSW_SP_L3_PROTO_IPV4);
-	if (IS_ERR(vr->mr4_table)) {
-		err = PTR_ERR(vr->mr4_table);
+	mr4_table = mlxsw_sp_mr_table_create(mlxsw_sp, vr->id,
+					     MLXSW_SP_L3_PROTO_IPV4);
+	if (IS_ERR(mr4_table)) {
+		err = PTR_ERR(mr4_table);
 		goto err_mr_table_create;
 	}
+	vr->fib4 = fib4;
+	vr->fib6 = fib6;
+	vr->mr4_table = mr4_table;
 	vr->tb_id = tb_id;
 	return vr;
 
 err_mr_table_create:
-	mlxsw_sp_fib_destroy(vr->fib6);
-	vr->fib6 = NULL;
+	mlxsw_sp_fib_destroy(fib6);
 err_fib6_create:
-	mlxsw_sp_fib_destroy(vr->fib4);
-	vr->fib4 = NULL;
+	mlxsw_sp_fib_destroy(fib4);
 	return ERR_PTR(err);
 }
 
-- 
2.14.3


From a8cc7747d9f43689e35d61e4d82bc25ea9666c50 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 21 Feb 2018 11:00:54 -0800
Subject: [PATCH 30/59] net: ipv4: Set addr_type in hash_keys for forwarded
 case

[ Upstream commit 1fe4b1184c2ae2bfbf9e8b14c9c0c1945c98f205 ]

The result of the skb flow dissect is copied from keys to hash_keys to
ensure only the intended data is hashed. The original L4 hash patch
overlooked setting the addr_type for this case; add it.

Fixes: bf4e0a3db97eb ("net: ipv4: add support for ECMP hash policy choice")
Reported-by: Ido Schimmel <idosch@idosch.org>
Signed-off-by: David Ahern <dsahern@gmail.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 239a89be8e41..f746e49dd585 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1832,6 +1832,8 @@ int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4,
 				return skb_get_hash_raw(skb) >> 1;
 			memset(&hash_keys, 0, sizeof(hash_keys));
 			skb_flow_dissect_flow_keys(skb, &keys, flag);
+
+			hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
 			hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src;
 			hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst;
 			hash_keys.ports.src = keys.ports.src;
-- 
2.14.3


From b75e8e72d0c8a3238fa3e2d35c124df0c17bd03d Mon Sep 17 00:00:00 2001
From: Alexey Kodanev <alexey.kodanev@oracle.com>
Date: Mon, 5 Feb 2018 15:10:35 +0300
Subject: [PATCH 31/59] sctp: fix dst refcnt leak in sctp_v6_get_dst()

[ Upstream commit 957d761cf91cdbb175ad7d8f5472336a4d54dbf2 ]

When going through the bind address list in sctp_v6_get_dst() and
the previously found address is better ('matchlen > bmatchlen'),
the code continues to the next iteration without releasing currently
held destination.

Fix it by releasing 'bdst' before continue to the next iteration, and
instead of introducing one more '!IS_ERR(bdst)' check for dst_release(),
move the already existed one right after ip6_dst_lookup_flow(), i.e. we
shouldn't proceed further if we get an error for the route lookup.

Fixes: dbc2b5e9a09e ("sctp: fix src address selection if using secondary addresses for ipv6")
Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ipv6.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 5d4c15bf66d2..e35d4f73d2df 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -326,8 +326,10 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 		final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
 		bdst = ip6_dst_lookup_flow(sk, fl6, final_p);
 
-		if (!IS_ERR(bdst) &&
-		    ipv6_chk_addr(dev_net(bdst->dev),
+		if (IS_ERR(bdst))
+			continue;
+
+		if (ipv6_chk_addr(dev_net(bdst->dev),
 				  &laddr->a.v6.sin6_addr, bdst->dev, 1)) {
 			if (!IS_ERR_OR_NULL(dst))
 				dst_release(dst);
@@ -336,8 +338,10 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 		}
 
 		bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a);
-		if (matchlen > bmatchlen)
+		if (matchlen > bmatchlen) {
+			dst_release(bdst);
 			continue;
+		}
 
 		if (!IS_ERR_OR_NULL(dst))
 			dst_release(dst);
-- 
2.14.3


From b940eb838bf51613394363c32223e1d2daaae9ed Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Sun, 25 Feb 2018 21:59:06 +0200
Subject: [PATCH 32/59] bridge: Fix VLAN reference count problem

[ Upstream commit 0e5a82efda872c2469c210957d7d4161ef8f4391 ]

When a VLAN is added on a port, a reference is taken on the
corresponding master VLAN entry. If it does not already exist, then it
is created and a reference taken.

However, in the second case a reference is not really taken when
CONFIG_REFCOUNT_FULL is enabled as refcount_inc() is replaced by
refcount_inc_not_zero().

Fix this by using refcount_set() on a newly created master VLAN entry.

Fixes: 251277598596 ("net, bridge: convert net_bridge_vlan.refcnt from atomic_t to refcount_t")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_vlan.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 51935270c651..9896f4975353 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -168,6 +168,8 @@ static struct net_bridge_vlan *br_vlan_get_master(struct net_bridge *br, u16 vid
 		masterv = br_vlan_find(vg, vid);
 		if (WARN_ON(!masterv))
 			return NULL;
+		refcount_set(&masterv->refcnt, 1);
+		return masterv;
 	}
 	refcount_inc(&masterv->refcnt);
 
-- 
2.14.3


From 279d797bf2d81815dc60c25ca9e55936ab1a2872 Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Thu, 25 Jan 2018 11:18:09 +0200
Subject: [PATCH 33/59] net/mlx5e: Verify inline header size do not exceed SKB
 linear size

[ Upstream commit f600c6088018d1dbc5777d18daa83660f7ea4a64 ]

Driver tries to copy at least MLX5E_MIN_INLINE bytes into the control
segment of the WQE. It assumes that the linear part contains at least
MLX5E_MIN_INLINE bytes, which can be wrong.

Cited commit verified that driver will not copy more bytes into the
inline header part that the actual size of the packet. Re-factor this
check to make sure we do not exceed the linear part as well.

This fix is aligned with the current driver's assumption that the entire
L2 will be present in the linear part of the SKB.

Fixes: 6aace17e64f4 ("net/mlx5e: Fix inline header size for small packets")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 569b42a01026..11b4f1089d1c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -176,7 +176,7 @@ static inline u16 mlx5e_calc_min_inline(enum mlx5_inline_modes mode,
 	default:
 		hlen = mlx5e_skb_l2_header_offset(skb);
 	}
-	return min_t(u16, hlen, skb->len);
+	return min_t(u16, hlen, skb_headlen(skb));
 }
 
 static inline void mlx5e_tx_skb_pull_inline(unsigned char **skb_data,
-- 
2.14.3


From 3987f8a62305ea5be60e92fe1fc88d4a922bbc42 Mon Sep 17 00:00:00 2001
From: Boris Pismenny <borisp@mellanox.com>
Date: Tue, 27 Feb 2018 14:18:39 +0200
Subject: [PATCH 34/59] tls: Use correct sk->sk_prot for IPV6

[ Upstream commit c113187d38ff85dc302a1bb55864b203ebb2ba10 ]

The tls ulp overrides sk->prot with a new tls specific proto structs.
The tls specific structs were previously based on the ipv4 specific
tcp_prot sturct.
As a result, attaching the tls ulp to an ipv6 tcp socket replaced
some ipv6 callback with the ipv4 equivalents.

This patch adds ipv6 tls proto structs and uses them when
attached to ipv6 sockets.

Fixes: 3c4d7559159b ('tls: kernel TLS support')
Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Ilya Lesokhin <ilyal@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_main.c | 52 +++++++++++++++++++++++++++++++++++++---------------
 1 file changed, 37 insertions(+), 15 deletions(-)

diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 736719c8314e..3a780337c393 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -45,17 +45,27 @@ MODULE_AUTHOR("Mellanox Technologies");
 MODULE_DESCRIPTION("Transport Layer Security Support");
 MODULE_LICENSE("Dual BSD/GPL");
 
+enum {
+	TLSV4,
+	TLSV6,
+	TLS_NUM_PROTS,
+};
+
 enum {
 	TLS_BASE_TX,
 	TLS_SW_TX,
 	TLS_NUM_CONFIG,
 };
 
-static struct proto tls_prots[TLS_NUM_CONFIG];
+static struct proto *saved_tcpv6_prot;
+static DEFINE_MUTEX(tcpv6_prot_mutex);
+static struct proto tls_prots[TLS_NUM_PROTS][TLS_NUM_CONFIG];
 
 static inline void update_sk_prot(struct sock *sk, struct tls_context *ctx)
 {
-	sk->sk_prot = &tls_prots[ctx->tx_conf];
+	int ip_ver = sk->sk_family == AF_INET6 ? TLSV6 : TLSV4;
+
+	sk->sk_prot = &tls_prots[ip_ver][ctx->tx_conf];
 }
 
 int wait_on_pending_writer(struct sock *sk, long *timeo)
@@ -450,8 +460,21 @@ static int tls_setsockopt(struct sock *sk, int level, int optname,
 	return do_tls_setsockopt(sk, optname, optval, optlen);
 }
 
+static void build_protos(struct proto *prot, struct proto *base)
+{
+	prot[TLS_BASE_TX] = *base;
+	prot[TLS_BASE_TX].setsockopt	= tls_setsockopt;
+	prot[TLS_BASE_TX].getsockopt	= tls_getsockopt;
+	prot[TLS_BASE_TX].close		= tls_sk_proto_close;
+
+	prot[TLS_SW_TX] = prot[TLS_BASE_TX];
+	prot[TLS_SW_TX].sendmsg		= tls_sw_sendmsg;
+	prot[TLS_SW_TX].sendpage	= tls_sw_sendpage;
+}
+
 static int tls_init(struct sock *sk)
 {
+	int ip_ver = sk->sk_family == AF_INET6 ? TLSV6 : TLSV4;
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tls_context *ctx;
 	int rc = 0;
@@ -476,6 +499,17 @@ static int tls_init(struct sock *sk)
 	ctx->getsockopt = sk->sk_prot->getsockopt;
 	ctx->sk_proto_close = sk->sk_prot->close;
 
+	/* Build IPv6 TLS whenever the address of tcpv6_prot changes */
+	if (ip_ver == TLSV6 &&
+	    unlikely(sk->sk_prot != smp_load_acquire(&saved_tcpv6_prot))) {
+		mutex_lock(&tcpv6_prot_mutex);
+		if (likely(sk->sk_prot != saved_tcpv6_prot)) {
+			build_protos(tls_prots[TLSV6], sk->sk_prot);
+			smp_store_release(&saved_tcpv6_prot, sk->sk_prot);
+		}
+		mutex_unlock(&tcpv6_prot_mutex);
+	}
+
 	ctx->tx_conf = TLS_BASE_TX;
 	update_sk_prot(sk, ctx);
 out:
@@ -488,21 +522,9 @@ static struct tcp_ulp_ops tcp_tls_ulp_ops __read_mostly = {
 	.init			= tls_init,
 };
 
-static void build_protos(struct proto *prot, struct proto *base)
-{
-	prot[TLS_BASE_TX] = *base;
-	prot[TLS_BASE_TX].setsockopt	= tls_setsockopt;
-	prot[TLS_BASE_TX].getsockopt	= tls_getsockopt;
-	prot[TLS_BASE_TX].close		= tls_sk_proto_close;
-
-	prot[TLS_SW_TX] = prot[TLS_BASE_TX];
-	prot[TLS_SW_TX].sendmsg		= tls_sw_sendmsg;
-	prot[TLS_SW_TX].sendpage	= tls_sw_sendpage;
-}
-
 static int __init tls_register(void)
 {
-	build_protos(tls_prots, &tcp_prot);
+	build_protos(tls_prots[TLSV4], &tcp_prot);
 
 	tcp_register_ulp(&tcp_tls_ulp_ops);
 
-- 
2.14.3


From cac6e4dd7de99ea65369e13e88c12eb8872f77eb Mon Sep 17 00:00:00 2001
From: Tom Lendacky <thomas.lendacky@amd.com>
Date: Tue, 20 Feb 2018 15:22:05 -0600
Subject: [PATCH 35/59] amd-xgbe: Restore PCI interrupt enablement setting on
 resume

[ Upstream commit cfd092f2db8b4b6727e1c03ef68a7842e1023573 ]

After resuming from suspend, the PCI device support must re-enable the
interrupt setting so that interrupts are actually delivered.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe-pci.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
index 3e5833cf1fab..eb23f9ba1a9a 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
@@ -426,6 +426,8 @@ static int xgbe_pci_resume(struct pci_dev *pdev)
 	struct net_device *netdev = pdata->netdev;
 	int ret = 0;
 
+	XP_IOWRITE(pdata, XP_INT_EN, 0x1fffff);
+
 	pdata->lpm_ctrl &= ~MDIO_CTRL1_LPOWER;
 	XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL1, pdata->lpm_ctrl);
 
-- 
2.14.3


From a346c55671ef19b3c2ca822a7665bd88a325f22a Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 5 Feb 2018 22:23:01 +0100
Subject: [PATCH 36/59] cls_u32: fix use after free in u32_destroy_key()

[ Upstream commit d7cdee5ea8d28ae1b6922deb0c1badaa3aa0ef8c ]

Li Shuang reported an Oops with cls_u32 due to an use-after-free
in u32_destroy_key(). The use-after-free can be triggered with:

dev=lo
tc qdisc add dev $dev root handle 1: htb default 10
tc filter add dev $dev parent 1: prio 5 handle 1: protocol ip u32 divisor 256
tc filter add dev $dev protocol ip parent 1: prio 5 u32 ht 800:: match ip dst\
 10.0.0.0/8 hashkey mask 0x0000ff00 at 16 link 1:
tc qdisc del dev $dev root

Which causes the following kasan splat:

 ==================================================================
 BUG: KASAN: use-after-free in u32_destroy_key.constprop.21+0x117/0x140 [cls_u32]
 Read of size 4 at addr ffff881b83dae618 by task kworker/u48:5/571

 CPU: 17 PID: 571 Comm: kworker/u48:5 Not tainted 4.15.0+ #87
 Hardware name: Dell Inc. PowerEdge R730/072T6D, BIOS 2.1.7 06/16/2016
 Workqueue: tc_filter_workqueue u32_delete_key_freepf_work [cls_u32]
 Call Trace:
  dump_stack+0xd6/0x182
  ? dma_virt_map_sg+0x22e/0x22e
  print_address_description+0x73/0x290
  kasan_report+0x277/0x360
  ? u32_destroy_key.constprop.21+0x117/0x140 [cls_u32]
  u32_destroy_key.constprop.21+0x117/0x140 [cls_u32]
  u32_delete_key_freepf_work+0x1c/0x30 [cls_u32]
  process_one_work+0xae0/0x1c80
  ? sched_clock+0x5/0x10
  ? pwq_dec_nr_in_flight+0x3c0/0x3c0
  ? _raw_spin_unlock_irq+0x29/0x40
  ? trace_hardirqs_on_caller+0x381/0x570
  ? _raw_spin_unlock_irq+0x29/0x40
  ? finish_task_switch+0x1e5/0x760
  ? finish_task_switch+0x208/0x760
  ? preempt_notifier_dec+0x20/0x20
  ? __schedule+0x839/0x1ee0
  ? check_noncircular+0x20/0x20
  ? firmware_map_remove+0x73/0x73
  ? find_held_lock+0x39/0x1c0
  ? worker_thread+0x434/0x1820
  ? lock_contended+0xee0/0xee0
  ? lock_release+0x1100/0x1100
  ? init_rescuer.part.16+0x150/0x150
  ? retint_kernel+0x10/0x10
  worker_thread+0x216/0x1820
  ? process_one_work+0x1c80/0x1c80
  ? lock_acquire+0x1a5/0x540
  ? lock_downgrade+0x6b0/0x6b0
  ? sched_clock+0x5/0x10
  ? lock_release+0x1100/0x1100
  ? compat_start_thread+0x80/0x80
  ? do_raw_spin_trylock+0x190/0x190
  ? _raw_spin_unlock_irq+0x29/0x40
  ? trace_hardirqs_on_caller+0x381/0x570
  ? _raw_spin_unlock_irq+0x29/0x40
  ? finish_task_switch+0x1e5/0x760
  ? finish_task_switch+0x208/0x760
  ? preempt_notifier_dec+0x20/0x20
  ? __schedule+0x839/0x1ee0
  ? kmem_cache_alloc_trace+0x143/0x320
  ? firmware_map_remove+0x73/0x73
  ? sched_clock+0x5/0x10
  ? sched_clock_cpu+0x18/0x170
  ? find_held_lock+0x39/0x1c0
  ? schedule+0xf3/0x3b0
  ? lock_downgrade+0x6b0/0x6b0
  ? __schedule+0x1ee0/0x1ee0
  ? do_wait_intr_irq+0x340/0x340
  ? do_raw_spin_trylock+0x190/0x190
  ? _raw_spin_unlock_irqrestore+0x32/0x60
  ? process_one_work+0x1c80/0x1c80
  ? process_one_work+0x1c80/0x1c80
  kthread+0x312/0x3d0
  ? kthread_create_worker_on_cpu+0xc0/0xc0
  ret_from_fork+0x3a/0x50

 Allocated by task 1688:
  kasan_kmalloc+0xa0/0xd0
  __kmalloc+0x162/0x380
  u32_change+0x1220/0x3c9e [cls_u32]
  tc_ctl_tfilter+0x1ba6/0x2f80
  rtnetlink_rcv_msg+0x4f0/0x9d0
  netlink_rcv_skb+0x124/0x320
  netlink_unicast+0x430/0x600
  netlink_sendmsg+0x8fa/0xd60
  sock_sendmsg+0xb1/0xe0
  ___sys_sendmsg+0x678/0x980
  __sys_sendmsg+0xc4/0x210
  do_syscall_64+0x232/0x7f0
  return_from_SYSCALL_64+0x0/0x75

 Freed by task 112:
  kasan_slab_free+0x71/0xc0
  kfree+0x114/0x320
  rcu_process_callbacks+0xc3f/0x1600
  __do_softirq+0x2bf/0xc06

 The buggy address belongs to the object at ffff881b83dae600
  which belongs to the cache kmalloc-4096 of size 4096
 The buggy address is located 24 bytes inside of
  4096-byte region [ffff881b83dae600, ffff881b83daf600)
 The buggy address belongs to the page:
 page:ffffea006e0f6a00 count:1 mapcount:0 mapping:          (null) index:0x0 compound_mapcount: 0
 flags: 0x17ffffc0008100(slab|head)
 raw: 0017ffffc0008100 0000000000000000 0000000000000000 0000000100070007
 raw: dead000000000100 dead000000000200 ffff880187c0e600 0000000000000000
 page dumped because: kasan: bad access detected

 Memory state around the buggy address:
  ffff881b83dae500: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
  ffff881b83dae580: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 >ffff881b83dae600: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                             ^
  ffff881b83dae680: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
  ffff881b83dae700: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ==================================================================

The problem is that the htnode is freed before the linked knodes and the
latter will try to access the first at u32_destroy_key() time.
This change addresses the issue using the htnode refcnt to guarantee
the correct free order. While at it also add a RCU annotation,
to keep sparse happy.

v1 -> v2: use rtnl_derefence() instead of RCU read locks
v2 -> v3:
  - don't check refcnt in u32_destroy_hnode()
  - cleaned-up u32_destroy() implementation
  - cleaned-up code comment
v3 -> v4:
  - dropped unneeded comment

Reported-by: Li Shuang <shuali@redhat.com>
Fixes: c0d378ef1266 ("net_sched: use tcf_queue_work() in u32 filter")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_u32.c | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index e5378b2247bb..425cc341fd41 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -397,10 +397,12 @@ static int u32_init(struct tcf_proto *tp)
 static int u32_destroy_key(struct tcf_proto *tp, struct tc_u_knode *n,
 			   bool free_pf)
 {
+	struct tc_u_hnode *ht = rtnl_dereference(n->ht_down);
+
 	tcf_exts_destroy(&n->exts);
 	tcf_exts_put_net(&n->exts);
-	if (n->ht_down)
-		n->ht_down->refcnt--;
+	if (ht && --ht->refcnt == 0)
+		kfree(ht);
 #ifdef CONFIG_CLS_U32_PERF
 	if (free_pf)
 		free_percpu(n->pf);
@@ -653,16 +655,15 @@ static void u32_destroy(struct tcf_proto *tp)
 
 		hlist_del(&tp_c->hnode);
 
-		for (ht = rtnl_dereference(tp_c->hlist);
-		     ht;
-		     ht = rtnl_dereference(ht->next)) {
-			ht->refcnt--;
-			u32_clear_hnode(tp, ht);
-		}
-
 		while ((ht = rtnl_dereference(tp_c->hlist)) != NULL) {
+			u32_clear_hnode(tp, ht);
 			RCU_INIT_POINTER(tp_c->hlist, ht->next);
-			kfree_rcu(ht, rcu);
+
+			/* u32_destroy_key() will later free ht for us, if it's
+			 * still referenced by some knode
+			 */
+			if (--ht->refcnt == 0)
+				kfree_rcu(ht, rcu);
 		}
 
 		idr_destroy(&tp_c->handle_idr);
-- 
2.14.3


From 5a4ce300b61d9d66d4151d258452ce01d4c5e535 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Sat, 17 Feb 2018 00:30:44 +0100
Subject: [PATCH 37/59] mlxsw: spectrum_router: Do not unconditionally clear
 route offload indication

[ Upstream commit d1c95af366961101819f07e3c64d44f3be7f0367 ]

When mlxsw replaces (or deletes) a route it removes the offload
indication from the replaced route. This is problematic for IPv4 routes,
as the offload indication is stored in the fib_info which is usually
shared between multiple routes.

Instead of unconditionally clearing the offload indication, only clear
it if no other route is using the fib_info.

Fixes: 3984d1a89fe7 ("mlxsw: spectrum_router: Provide offload indication using nexthop flags")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Alexander Petrovskiy <alexpe@mellanox.com>
Tested-by: Alexander Petrovskiy <alexpe@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 1110e2d33f00..7e50dbc8282c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -3765,6 +3765,9 @@ mlxsw_sp_fib4_entry_offload_unset(struct mlxsw_sp_fib_entry *fib_entry)
 	struct mlxsw_sp_nexthop_group *nh_grp = fib_entry->nh_group;
 	int i;
 
+	if (!list_is_singular(&nh_grp->fib_list))
+		return;
+
 	for (i = 0; i < nh_grp->count; i++) {
 		struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i];
 
-- 
2.14.3


From 440a88f560b1a266cd5636db60251f0a484b3c34 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Wed, 21 Feb 2018 04:41:59 +0100
Subject: [PATCH 38/59] netlink: put module reference if dump start fails

[ Upstream commit b87b6194be631c94785fe93398651e804ed43e28 ]

Before, if cb->start() failed, the module reference would never be put,
because cb->cb_running is intentionally false at this point. Users are
generally annoyed by this because they can no longer unload modules that
leak references. Also, it may be possible to tediously wrap a reference
counter back to zero, especially since module.c still uses atomic_inc
instead of refcount_inc.

This patch expands the error path to simply call module_put if
cb->start() fails.

Fixes: 41c87425a1ac ("netlink: do not set cb_running if dump's start() errs")
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 84a4e4c3be4b..ca9c0544c856 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2275,7 +2275,7 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 	if (cb->start) {
 		ret = cb->start(cb);
 		if (ret)
-			goto error_unlock;
+			goto error_put;
 	}
 
 	nlk->cb_running = true;
@@ -2295,6 +2295,8 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 	 */
 	return -EINTR;
 
+error_put:
+	module_put(control->module);
 error_unlock:
 	sock_put(sk);
 	mutex_unlock(nlk->cb_mutex);
-- 
2.14.3


From 60ba8b1376cc1541a5eef09fb78df4e9c304784e Mon Sep 17 00:00:00 2001
From: Soheil Hassas Yeganeh <soheil@google.com>
Date: Tue, 27 Feb 2018 18:32:18 -0500
Subject: [PATCH 39/59] tcp: purge write queue upon RST

[ Upstream commit a27fd7a8ed3856faaf5a2ff1c8c5f00c0667aaa0 ]

When the connection is reset, there is no point in
keeping the packets on the write queue until the connection
is closed.

RFC 793 (page 70) and RFC 793-bis (page 64) both suggest
purging the write queue upon RST:
https://tools.ietf.org/html/draft-ietf-tcpm-rfc793bis-07

Moreover, this is essential for a correct MSG_ZEROCOPY
implementation, because userspace cannot call close(fd)
before receiving zerocopy signals even when the connection
is reset.

Fixes: f214f915e7db ("tcp: enable MSG_ZEROCOPY")
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 8bb4eecca5df..0228f494b0a5 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3979,6 +3979,7 @@ void tcp_reset(struct sock *sk)
 	/* This barrier is coupled with smp_rmb() in tcp_poll() */
 	smp_wmb();
 
+	tcp_write_queue_purge(sk);
 	tcp_done(sk);
 
 	if (!sock_flag(sk, SOCK_DEAD))
-- 
2.14.3


From b4e3037e32ca050f8146a94bfc5bd2dcc68fb9fb Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Sat, 24 Feb 2018 11:32:26 +0800
Subject: [PATCH 40/59] tuntap: correctly add the missing XDP flush

[ Upstream commit 1bb4f2e868a2891ab8bc668b8173d6ccb8c4ce6f ]

We don't flush batched XDP packets through xdp_do_flush_map(), this
will cause packets stall at TX queue. Consider we don't do XDP on NAPI
poll(), the only possible fix is to call xdp_do_flush_map()
immediately after xdp_do_redirect().

Note, this in fact won't try to batch packets through devmap, we could
address in the future.

Reported-by: Christoffer Dall <christoffer.dall@linaro.org>
Fixes: 761876c857cb ("tap: XDP support")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index e29cd5c7d39f..5f04f784bc97 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1490,6 +1490,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 			get_page(alloc_frag->page);
 			alloc_frag->offset += buflen;
 			err = xdp_do_redirect(tun->dev, &xdp, xdp_prog);
+			xdp_do_flush_map();
 			if (err)
 				goto err_redirect;
 			rcu_read_unlock();
-- 
2.14.3


From 0e567e23fe85e51e0967917586ed8e4ed9e467bd Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Sat, 24 Feb 2018 11:32:25 +0800
Subject: [PATCH 41/59] tuntap: disable preemption during XDP processing

[ Upstream commit 23e43f07f896f8578318cfcc9466f1e8b8ab21b6 ]

Except for tuntap, all other drivers' XDP was implemented at NAPI
poll() routine in a bh. This guarantees all XDP operation were done at
the same CPU which is required by e.g BFP_MAP_TYPE_PERCPU_ARRAY. But
for tuntap, we do it in process context and we try to protect XDP
processing by RCU reader lock. This is insufficient since
CONFIG_PREEMPT_RCU can preempt the RCU reader critical section which
breaks the assumption that all XDP were processed in the same CPU.

Fixing this by simply disabling preemption during XDP processing.

Fixes: 761876c857cb ("tap: XDP support")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 5f04f784bc97..f50cf06c9353 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1471,6 +1471,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 	else
 		*skb_xdp = 0;
 
+	preempt_disable();
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(tun->xdp_prog);
 	if (xdp_prog && !*skb_xdp) {
@@ -1494,6 +1495,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 			if (err)
 				goto err_redirect;
 			rcu_read_unlock();
+			preempt_enable();
 			return NULL;
 		case XDP_TX:
 			xdp_xmit = true;
@@ -1515,6 +1517,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 	skb = build_skb(buf, buflen);
 	if (!skb) {
 		rcu_read_unlock();
+		preempt_enable();
 		return ERR_PTR(-ENOMEM);
 	}
 
@@ -1527,10 +1530,12 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 		skb->dev = tun->dev;
 		generic_xdp_tx(skb, xdp_prog);
 		rcu_read_unlock();
+		preempt_enable();
 		return NULL;
 	}
 
 	rcu_read_unlock();
+	preempt_enable();
 
 	return skb;
 
@@ -1538,6 +1543,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 	put_page(alloc_frag->page);
 err_xdp:
 	rcu_read_unlock();
+	preempt_enable();
 	this_cpu_inc(tun->pcpu_stats->rx_dropped);
 	return NULL;
 }
-- 
2.14.3


From cd91f05d994e4c23f77df73041685b516711097e Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Wed, 28 Feb 2018 18:20:04 +0800
Subject: [PATCH 42/59] virtio-net: disable NAPI only when enabled during XDP
 set

[ Upstream commit 4e09ff5362843dff3accfa84c805c7f3a99de9cd ]

We try to disable NAPI to prevent a single XDP TX queue being used by
multiple cpus. But we don't check if device is up (NAPI is enabled),
this could result stall because of infinite wait in
napi_disable(). Fixing this by checking device state through
netif_running() before.

Fixes: 4941d472bf95b ("virtio-net: do not reset during XDP set")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 559b215c0169..5907a8d0e921 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2040,8 +2040,9 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 	}
 
 	/* Make sure NAPI is not using any XDP TX queues for RX. */
-	for (i = 0; i < vi->max_queue_pairs; i++)
-		napi_disable(&vi->rq[i].napi);
+	if (netif_running(dev))
+		for (i = 0; i < vi->max_queue_pairs; i++)
+			napi_disable(&vi->rq[i].napi);
 
 	netif_set_real_num_rx_queues(dev, curr_qp + xdp_qp);
 	err = _virtnet_set_queues(vi, curr_qp + xdp_qp);
@@ -2060,7 +2061,8 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 		}
 		if (old_prog)
 			bpf_prog_put(old_prog);
-		virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
+		if (netif_running(dev))
+			virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
 	}
 
 	return 0;
-- 
2.14.3


From 9a5d39fe7ff5c9fa06f62868bdefb37f4599c797 Mon Sep 17 00:00:00 2001
From: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Date: Thu, 15 Feb 2018 18:20:01 +0530
Subject: [PATCH 43/59] cxgb4: fix trailing zero in CIM LA dump

[ Upstream commit e6f02a4d57cc438099bc8abfba43ba1400d77b38 ]

Set correct size of the CIM LA dump for T6.

Fixes: 27887bc7cb7f ("cxgb4: collect hardware LA dumps")
Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c   | 2 +-
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
index d699bf88d18f..6044fdcf6056 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
@@ -156,7 +156,7 @@ int cudbg_collect_cim_la(struct cudbg_init *pdbg_init,
 
 	if (is_t6(padap->params.chip)) {
 		size = padap->params.cim_la_size / 10 + 1;
-		size *= 11 * sizeof(u32);
+		size *= 10 * sizeof(u32);
 	} else {
 		size = padap->params.cim_la_size / 8;
 		size *= 8 * sizeof(u32);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c
index 29cc625e9833..97465101e0b9 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c
@@ -97,7 +97,7 @@ static u32 cxgb4_get_entity_length(struct adapter *adap, u32 entity)
 	case CUDBG_CIM_LA:
 		if (is_t6(adap->params.chip)) {
 			len = adap->params.cim_la_size / 10 + 1;
-			len *= 11 * sizeof(u32);
+			len *= 10 * sizeof(u32);
 		} else {
 			len = adap->params.cim_la_size / 8;
 			len *= 8 * sizeof(u32);
-- 
2.14.3


From cdbe1860d5c077e60a400bc49d3ddb19b1d5cca0 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Tue, 6 Feb 2018 10:52:19 +0200
Subject: [PATCH 44/59] net/mlx5: Fix error handling when adding flow rules

[ Upstream commit 9238e380e823a39983ee8d6b6ee8d1a9c4ba8a65 ]

If building match list or adding existing fg fails when
node is locked, function returned without unlocking it.
This happened if node version changed or adding existing fg
returned with EAGAIN after jumping to search_again_locked label.

Fixes: bd71b08ec2ee ("net/mlx5: Support multiple updates of steering rules in parallel")
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index dfaad9ecb2b8..a681693631aa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -1755,8 +1755,11 @@ _mlx5_add_flow_rules(struct mlx5_flow_table *ft,
 
 	/* Collect all fgs which has a matching match_criteria */
 	err = build_match_list(&match_head, ft, spec);
-	if (err)
+	if (err) {
+		if (take_write)
+			up_write_ref_node(&ft->node);
 		return ERR_PTR(err);
+	}
 
 	if (!take_write)
 		up_read_ref_node(&ft->node);
@@ -1765,8 +1768,11 @@ _mlx5_add_flow_rules(struct mlx5_flow_table *ft,
 				      dest_num, version);
 	free_match_list(&match_head);
 	if (!IS_ERR(rule) ||
-	    (PTR_ERR(rule) != -ENOENT && PTR_ERR(rule) != -EAGAIN))
+	    (PTR_ERR(rule) != -ENOENT && PTR_ERR(rule) != -EAGAIN)) {
+		if (take_write)
+			up_write_ref_node(&ft->node);
 		return rule;
+	}
 
 	if (!take_write) {
 		nested_down_write_ref_node(&ft->node, FS_LOCK_GRANDPARENT);
-- 
2.14.3


From 9b6139e0986c88d0169ed11305110a08ec10173a Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Tue, 27 Feb 2018 01:56:06 +0100
Subject: [PATCH 45/59] net: phy: Restore phy_resume() locking assumption

[ Upstream commit 9c2c2e62df3fa30fb13fbeb7512a4eede729383b ]

commit f5e64032a799 ("net: phy: fix resume handling") changes the
locking semantics for phy_resume() such that the caller now needs to
hold the phy mutex. Not all call sites were adopted to this new
semantic, resulting in warnings from the added
WARN_ON(!mutex_is_locked(&phydev->lock)).  Rather than change the
semantics, add a __phy_resume() and restore the old behavior of
phy_resume().

Reported-by: Heiner Kallweit <hkallweit1@gmail.com>
Fixes: f5e64032a799 ("net: phy: fix resume handling")
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c        |  2 +-
 drivers/net/phy/phy_device.c | 18 +++++++++++++-----
 include/linux/phy.h          |  1 +
 3 files changed, 15 insertions(+), 6 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 26ad88f09795..39de77a8bb63 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -841,7 +841,7 @@ void phy_start(struct phy_device *phydev)
 		break;
 	case PHY_HALTED:
 		/* if phy was suspended, bring the physical link up again */
-		phy_resume(phydev);
+		__phy_resume(phydev);
 
 		/* make sure interrupts are re-enabled for the PHY */
 		if (phy_interrupt_is_valid(phydev)) {
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index b15b31ca2618..d312b314825e 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -135,9 +135,7 @@ static int mdio_bus_phy_resume(struct device *dev)
 	if (!mdio_bus_phy_may_suspend(phydev))
 		goto no_resume;
 
-	mutex_lock(&phydev->lock);
 	ret = phy_resume(phydev);
-	mutex_unlock(&phydev->lock);
 	if (ret < 0)
 		return ret;
 
@@ -1028,9 +1026,7 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
 	if (err)
 		goto error;
 
-	mutex_lock(&phydev->lock);
 	phy_resume(phydev);
-	mutex_unlock(&phydev->lock);
 	phy_led_triggers_register(phydev);
 
 	return err;
@@ -1156,7 +1152,7 @@ int phy_suspend(struct phy_device *phydev)
 }
 EXPORT_SYMBOL(phy_suspend);
 
-int phy_resume(struct phy_device *phydev)
+int __phy_resume(struct phy_device *phydev)
 {
 	struct phy_driver *phydrv = to_phy_driver(phydev->mdio.dev.driver);
 	int ret = 0;
@@ -1173,6 +1169,18 @@ int phy_resume(struct phy_device *phydev)
 
 	return ret;
 }
+EXPORT_SYMBOL(__phy_resume);
+
+int phy_resume(struct phy_device *phydev)
+{
+	int ret;
+
+	mutex_lock(&phydev->lock);
+	ret = __phy_resume(phydev);
+	mutex_unlock(&phydev->lock);
+
+	return ret;
+}
 EXPORT_SYMBOL(phy_resume);
 
 int phy_loopback(struct phy_device *phydev, bool enable)
diff --git a/include/linux/phy.h b/include/linux/phy.h
index dc82a07cb4fd..123cd703741d 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -819,6 +819,7 @@ void phy_device_remove(struct phy_device *phydev);
 int phy_init_hw(struct phy_device *phydev);
 int phy_suspend(struct phy_device *phydev);
 int phy_resume(struct phy_device *phydev);
+int __phy_resume(struct phy_device *phydev);
 int phy_loopback(struct phy_device *phydev, bool enable);
 struct phy_device *phy_attach(struct net_device *dev, const char *bus_id,
 			      phy_interface_t interface);
-- 
2.14.3


From d439ca30f5e5b6e1384ae828dc03373d599e7398 Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Tue, 6 Feb 2018 20:50:23 -0800
Subject: [PATCH 46/59] tcp: tracepoint: only call trace_tcp_send_reset with
 full socket

[ Upstream commit 5c487bb9adddbc1d23433e09d2548759375c2b52 ]

tracepoint tcp_send_reset requires a full socket to work. However, it
may be called when in TCP_TIME_WAIT:

        case TCP_TW_RST:
                tcp_v6_send_reset(sk, skb);
                inet_twsk_deschedule_put(inet_twsk(sk));
                goto discard_it;

To avoid this problem, this patch checks the socket with sk_fullsock()
before calling trace_tcp_send_reset().

Fixes: c24b14c46bb8 ("tcp: add tracepoint trace_tcp_send_reset")
Signed-off-by: Song Liu <songliubraving@fb.com>
Reviewed-by: Lawrence Brakmo <brakmo@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c | 3 ++-
 net/ipv6/tcp_ipv6.c | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 94e28350f420..3b051b9b3743 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -705,7 +705,8 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 	 */
 	if (sk) {
 		arg.bound_dev_if = sk->sk_bound_dev_if;
-		trace_tcp_send_reset(sk, skb);
+		if (sk_fullsock(sk))
+			trace_tcp_send_reset(sk, skb);
 	}
 
 	BUILD_BUG_ON(offsetof(struct sock, sk_bound_dev_if) !=
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 7178476b3d2f..6378f6fbc89f 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -943,7 +943,8 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
 
 	if (sk) {
 		oif = sk->sk_bound_dev_if;
-		trace_tcp_send_reset(sk, skb);
+		if (sk_fullsock(sk))
+			trace_tcp_send_reset(sk, skb);
 	}
 
 	tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0, 0);
-- 
2.14.3


From f990686326eafd0949193b2aff60e1fae0742849 Mon Sep 17 00:00:00 2001
From: James Chapman <jchapman@katalix.com>
Date: Fri, 23 Feb 2018 17:45:43 +0000
Subject: [PATCH 47/59] l2tp: don't use inet_shutdown on tunnel destroy

[ Upstream commit 76a6abdb2513ad4ea0ded55d2c66160491f2e848 ]

Previously, if a tunnel was closed, we called inet_shutdown to mark
the socket as unconnected such that userspace would get errors and
then close the socket. This could race with userspace closing the
socket. Instead, leave userspace to close the socket in its own time
(our tunnel will be detached anyway).

BUG: unable to handle kernel NULL pointer dereference at 00000000000000a0
IP: __lock_acquire+0x263/0x1630
PGD 0 P4D 0
Oops: 0000 [#1] SMP KASAN
Modules linked in:
CPU: 2 PID: 42 Comm: kworker/u8:2 Not tainted 4.15.0-rc7+ #129
Workqueue: l2tp l2tp_tunnel_del_work
RIP: 0010:__lock_acquire+0x263/0x1630
RSP: 0018:ffff88001a37fc70 EFLAGS: 00010002
RAX: 0000000000000001 RBX: 0000000000000088 RCX: 0000000000000000
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
RBP: ffff88001a37fd18 R08: 0000000000000001 R09: 0000000000000000
R10: 0000000000000000 R11: 00000000000076fd R12: 00000000000000a0
R13: ffff88001a3722c0 R14: 0000000000000001 R15: 0000000000000000
FS:  0000000000000000(0000) GS:ffff88001ad00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000000000a0 CR3: 000000001730b000 CR4: 00000000000006e0
Call Trace:
 ? __lock_acquire+0xc77/0x1630
 ? console_trylock+0x11/0xa0
 lock_acquire+0x117/0x230
 ? lock_sock_nested+0x3a/0xa0
 _raw_spin_lock_bh+0x3a/0x50
 ? lock_sock_nested+0x3a/0xa0
 lock_sock_nested+0x3a/0xa0
 inet_shutdown+0x33/0xf0
 l2tp_tunnel_del_work+0x60/0xef
 process_one_work+0x1ea/0x5f0
 ? process_one_work+0x162/0x5f0
 worker_thread+0x48/0x3e0
 ? trace_hardirqs_on+0xd/0x10
 kthread+0x108/0x140
 ? process_one_work+0x5f0/0x5f0
 ? kthread_stop+0x2a0/0x2a0
 ret_from_fork+0x24/0x30
Code: 00 41 81 ff ff 1f 00 00 0f 87 7a 13 00 00 45 85 f6 49 8b 85
68 08 00 00 0f 84 ae 03 00 00 c7 44 24 18 00 00 00 00 e9 f0 00 00 00 <49> 81 3c
24 80 93 3f 83 b8 00 00 00 00 44 0f 44 c0 83 fe 01 0f
RIP: __lock_acquire+0x263/0x1630 RSP: ffff88001a37fc70
CR2: 00000000000000a0

Fixes: 309795f4bec2d ("l2tp: Add netlink control API for L2TP")
Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 115918ad8eca..ddce62044191 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1336,17 +1336,10 @@ static void l2tp_tunnel_del_work(struct work_struct *work)
 
 	sock = sk->sk_socket;
 
-	/* If the tunnel socket was created by userspace, then go through the
-	 * inet layer to shut the socket down, and let userspace close it.
-	 * Otherwise, if we created the socket directly within the kernel, use
+	/* If the tunnel socket was created within the kernel, use
 	 * the sk API to release it here.
-	 * In either case the tunnel resources are freed in the socket
-	 * destructor when the tunnel socket goes away.
 	 */
-	if (tunnel->fd >= 0) {
-		if (sock)
-			inet_shutdown(sock, 2);
-	} else {
+	if (tunnel->fd < 0) {
 		if (sock) {
 			kernel_sock_shutdown(sock, SHUT_RDWR);
 			sock_release(sock);
-- 
2.14.3


From b8020683f97da7e8a5d8ccd11e8af8f98736b264 Mon Sep 17 00:00:00 2001
From: James Chapman <jchapman@katalix.com>
Date: Fri, 23 Feb 2018 17:45:44 +0000
Subject: [PATCH 48/59] l2tp: don't use inet_shutdown on ppp session destroy

[ Upstream commit 225eb26489d05c679a4c4197ffcb81c81e9dcaf4 ]

Previously, if a ppp session was closed, we called inet_shutdown to mark
the socket as unconnected such that userspace would get errors and
then close the socket. This could race with userspace closing the
socket. Instead, leave userspace to close the socket in its own time
(our session will be detached anyway).

BUG: KASAN: use-after-free in inet_shutdown+0x5d/0x1c0
Read of size 4 at addr ffff880010ea3ac0 by task syzbot_347bd5ac/8296

CPU: 3 PID: 8296 Comm: syzbot_347bd5ac Not tainted 4.16.0-rc1+ #91
Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
Call Trace:
 dump_stack+0x101/0x157
 ? inet_shutdown+0x5d/0x1c0
 print_address_description+0x78/0x260
 ? inet_shutdown+0x5d/0x1c0
 kasan_report+0x240/0x360
 __asan_load4+0x78/0x80
 inet_shutdown+0x5d/0x1c0
 ? pppol2tp_show+0x80/0x80
 pppol2tp_session_close+0x68/0xb0
 l2tp_tunnel_closeall+0x199/0x210
 ? udp_v6_flush_pending_frames+0x90/0x90
 l2tp_udp_encap_destroy+0x6b/0xc0
 ? l2tp_tunnel_del_work+0x2e0/0x2e0
 udpv6_destroy_sock+0x8c/0x90
 sk_common_release+0x47/0x190
 udp_lib_close+0x15/0x20
 inet_release+0x85/0xd0
 inet6_release+0x43/0x60
 sock_release+0x53/0x100
 ? sock_alloc_file+0x260/0x260
 sock_close+0x1b/0x20
 __fput+0x19f/0x380
 ____fput+0x1a/0x20
 task_work_run+0xd2/0x110
 exit_to_usermode_loop+0x18d/0x190
 do_syscall_64+0x389/0x3b0
 entry_SYSCALL_64_after_hwframe+0x26/0x9b
RIP: 0033:0x7fe240a45259
RSP: 002b:00007fe241132df8 EFLAGS: 00000297 ORIG_RAX: 0000000000000003
RAX: 0000000000000000 RBX: 0000000000000000 RCX: 00007fe240a45259
RDX: 00007fe240a45259 RSI: 0000000000000000 RDI: 00000000000000a5
RBP: 00007fe241132e20 R08: 00007fe241133700 R09: 0000000000000000
R10: 00007fe241133700 R11: 0000000000000297 R12: 0000000000000000
R13: 00007ffc49aff84f R14: 0000000000000000 R15: 00007fe241141040

Allocated by task 8331:
 save_stack+0x43/0xd0
 kasan_kmalloc+0xad/0xe0
 kasan_slab_alloc+0x12/0x20
 kmem_cache_alloc+0x144/0x3e0
 sock_alloc_inode+0x22/0x130
 alloc_inode+0x3d/0xf0
 new_inode_pseudo+0x1c/0x90
 sock_alloc+0x30/0x110
 __sock_create+0xaa/0x4c0
 SyS_socket+0xbe/0x130
 do_syscall_64+0x128/0x3b0
 entry_SYSCALL_64_after_hwframe+0x26/0x9b

Freed by task 8314:
 save_stack+0x43/0xd0
 __kasan_slab_free+0x11a/0x170
 kasan_slab_free+0xe/0x10
 kmem_cache_free+0x88/0x2b0
 sock_destroy_inode+0x49/0x50
 destroy_inode+0x77/0xb0
 evict+0x285/0x340
 iput+0x429/0x530
 dentry_unlink_inode+0x28c/0x2c0
 __dentry_kill+0x1e3/0x2f0
 dput.part.21+0x500/0x560
 dput+0x24/0x30
 __fput+0x2aa/0x380
 ____fput+0x1a/0x20
 task_work_run+0xd2/0x110
 exit_to_usermode_loop+0x18d/0x190
 do_syscall_64+0x389/0x3b0
 entry_SYSCALL_64_after_hwframe+0x26/0x9b

Fixes: fd558d186df2c ("l2tp: Split pppol2tp patch into separate l2tp and ppp parts")
Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ppp.c | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index b412fc3351dc..3b033c8fe736 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -420,16 +420,6 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
  */
 static void pppol2tp_session_close(struct l2tp_session *session)
 {
-	struct sock *sk;
-
-	BUG_ON(session->magic != L2TP_SESSION_MAGIC);
-
-	sk = pppol2tp_session_get_sock(session);
-	if (sk) {
-		if (sk->sk_socket)
-			inet_shutdown(sk->sk_socket, SEND_SHUTDOWN);
-		sock_put(sk);
-	}
 }
 
 /* Really kill the session socket. (Called from sock_put() if
-- 
2.14.3


From 110af2c831a4b2f2157993c23695044c0b026909 Mon Sep 17 00:00:00 2001
From: James Chapman <jchapman@katalix.com>
Date: Fri, 23 Feb 2018 17:45:45 +0000
Subject: [PATCH 49/59] l2tp: fix races with tunnel socket close

[ Upstream commit d00fa9adc528c1b0e64d532556764852df8bd7b9 ]

The tunnel socket tunnel->sock (struct sock) is accessed when
preparing a new ppp session on a tunnel at pppol2tp_session_init. If
the socket is closed by a thread while another is creating a new
session, the threads race. In pppol2tp_connect, the tunnel object may
be created if the pppol2tp socket is associated with the special
session_id 0 and the tunnel socket is looked up using the provided
fd. When handling this, pppol2tp_connect cannot sock_hold the tunnel
socket to prevent it being destroyed during pppol2tp_connect since
this may itself may race with the socket being destroyed. Doing
sockfd_lookup in pppol2tp_connect isn't sufficient to prevent
tunnel->sock going away either because a given tunnel socket fd may be
reused between calls to pppol2tp_connect. Instead, have
l2tp_tunnel_create sock_hold the tunnel socket before it does
sockfd_put. This ensures that the tunnel's socket is always extant
while the tunnel object exists. Hold a ref on the socket until the
tunnel is destroyed and ensure that all tunnel destroy paths go
through a common function (l2tp_tunnel_delete) since this will do the
final sock_put to release the tunnel socket.

Since the tunnel's socket is now guaranteed to exist if the tunnel
exists, we no longer need to use sockfd_lookup via l2tp_sock_to_tunnel
to derive the tunnel from the socket since this is always
sk_user_data.

Also, sessions no longer sock_hold the tunnel socket since sessions
already hold a tunnel ref and the tunnel sock will not be freed until
the tunnel is freed. Removing these sock_holds in
l2tp_session_register avoids a possible sock leak in the
pppol2tp_connect error path if l2tp_session_register succeeds but
attaching a ppp channel fails. The pppol2tp_connect error path could
have been fixed instead and have the sock ref dropped when the session
is freed, but doing a sock_put of the tunnel socket when the session
is freed would require a new session_free callback. It is simpler to
just remove the sock_hold of the tunnel socket in
l2tp_session_register, now that the tunnel socket lifetime is
guaranteed.

Finally, some init code in l2tp_tunnel_create is reordered to ensure
that the new tunnel object's refcount is set and the tunnel socket ref
is taken before the tunnel socket destructor callbacks are set.

kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] SMP KASAN
Modules linked in:
CPU: 0 PID: 4360 Comm: syzbot_19c09769 Not tainted 4.16.0-rc2+ #34
Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
RIP: 0010:pppol2tp_session_init+0x1d6/0x500
RSP: 0018:ffff88001377fb40 EFLAGS: 00010212
RAX: dffffc0000000000 RBX: ffff88001636a940 RCX: ffffffff84836c1d
RDX: 0000000000000045 RSI: 0000000055976744 RDI: 0000000000000228
RBP: ffff88001377fb60 R08: ffffffff84836bc8 R09: 0000000000000002
R10: ffff88001377fab8 R11: 0000000000000001 R12: 0000000000000000
R13: ffff88001636aac8 R14: ffff8800160f81c0 R15: 1ffff100026eff76
FS:  00007ffb3ea66700(0000) GS:ffff88001a400000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000020e77000 CR3: 0000000016261000 CR4: 00000000000006f0
Call Trace:
 pppol2tp_connect+0xd18/0x13c0
 ? pppol2tp_session_create+0x170/0x170
 ? __might_fault+0x115/0x1d0
 ? lock_downgrade+0x860/0x860
 ? __might_fault+0xe5/0x1d0
 ? security_socket_connect+0x8e/0xc0
 SYSC_connect+0x1b6/0x310
 ? SYSC_bind+0x280/0x280
 ? __do_page_fault+0x5d1/0xca0
 ? up_read+0x1f/0x40
 ? __do_page_fault+0x3c8/0xca0
 SyS_connect+0x29/0x30
 ? SyS_accept+0x40/0x40
 do_syscall_64+0x1e0/0x730
 ? trace_hardirqs_off_thunk+0x1a/0x1c
 entry_SYSCALL_64_after_hwframe+0x42/0xb7
RIP: 0033:0x7ffb3e376259
RSP: 002b:00007ffeda4f6508 EFLAGS: 00000202 ORIG_RAX: 000000000000002a
RAX: ffffffffffffffda RBX: 0000000020e77012 RCX: 00007ffb3e376259
RDX: 000000000000002e RSI: 0000000020e77000 RDI: 0000000000000004
RBP: 00007ffeda4f6540 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000202 R12: 0000000000400b60
R13: 00007ffeda4f6660 R14: 0000000000000000 R15: 0000000000000000
Code: 80 3d b0 ff 06 02 00 0f 84 07 02 00 00 e8 13 d6 db fc 49 8d bc 24 28 02 00 00 48 b8 00 00 00 00 00 fc ff df 48 89 f
a 48 c1 ea 03 <80> 3c 02 00 0f 85 ed 02 00 00 4d 8b a4 24 28 02 00 00 e8 13 16

Fixes: 80d84ef3ff1dd ("l2tp: prevent l2tp_tunnel_delete racing with userspace close")
Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 117 +++++++++++++++------------------------------------
 net/l2tp/l2tp_core.h |  23 +---------
 net/l2tp/l2tp_ip.c   |  10 ++---
 net/l2tp/l2tp_ip6.c  |   8 ++--
 4 files changed, 42 insertions(+), 116 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index ddce62044191..a8126d9a1645 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -136,51 +136,6 @@ l2tp_session_id_hash_2(struct l2tp_net *pn, u32 session_id)
 
 }
 
-/* Lookup the tunnel socket, possibly involving the fs code if the socket is
- * owned by userspace.  A struct sock returned from this function must be
- * released using l2tp_tunnel_sock_put once you're done with it.
- */
-static struct sock *l2tp_tunnel_sock_lookup(struct l2tp_tunnel *tunnel)
-{
-	int err = 0;
-	struct socket *sock = NULL;
-	struct sock *sk = NULL;
-
-	if (!tunnel)
-		goto out;
-
-	if (tunnel->fd >= 0) {
-		/* Socket is owned by userspace, who might be in the process
-		 * of closing it.  Look the socket up using the fd to ensure
-		 * consistency.
-		 */
-		sock = sockfd_lookup(tunnel->fd, &err);
-		if (sock)
-			sk = sock->sk;
-	} else {
-		/* Socket is owned by kernelspace */
-		sk = tunnel->sock;
-		sock_hold(sk);
-	}
-
-out:
-	return sk;
-}
-
-/* Drop a reference to a tunnel socket obtained via. l2tp_tunnel_sock_put */
-static void l2tp_tunnel_sock_put(struct sock *sk)
-{
-	struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk);
-	if (tunnel) {
-		if (tunnel->fd >= 0) {
-			/* Socket is owned by userspace */
-			sockfd_put(sk->sk_socket);
-		}
-		sock_put(sk);
-	}
-	sock_put(sk);
-}
-
 /* Session hash list.
  * The session_id SHOULD be random according to RFC2661, but several
  * L2TP implementations (Cisco and Microsoft) use incrementing
@@ -193,6 +148,13 @@ l2tp_session_id_hash(struct l2tp_tunnel *tunnel, u32 session_id)
 	return &tunnel->session_hlist[hash_32(session_id, L2TP_HASH_BITS)];
 }
 
+void l2tp_tunnel_free(struct l2tp_tunnel *tunnel)
+{
+	sock_put(tunnel->sock);
+	/* the tunnel is freed in the socket destructor */
+}
+EXPORT_SYMBOL(l2tp_tunnel_free);
+
 /* Lookup a tunnel. A new reference is held on the returned tunnel. */
 struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id)
 {
@@ -345,13 +307,11 @@ int l2tp_session_register(struct l2tp_session *session,
 			}
 
 		l2tp_tunnel_inc_refcount(tunnel);
-		sock_hold(tunnel->sock);
 		hlist_add_head_rcu(&session->global_hlist, g_head);
 
 		spin_unlock_bh(&pn->l2tp_session_hlist_lock);
 	} else {
 		l2tp_tunnel_inc_refcount(tunnel);
-		sock_hold(tunnel->sock);
 	}
 
 	hlist_add_head(&session->hlist, head);
@@ -975,7 +935,7 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 {
 	struct l2tp_tunnel *tunnel;
 
-	tunnel = l2tp_sock_to_tunnel(sk);
+	tunnel = l2tp_tunnel(sk);
 	if (tunnel == NULL)
 		goto pass_up;
 
@@ -983,13 +943,10 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 		 tunnel->name, skb->len);
 
 	if (l2tp_udp_recv_core(tunnel, skb, tunnel->recv_payload_hook))
-		goto pass_up_put;
+		goto pass_up;
 
-	sock_put(sk);
 	return 0;
 
-pass_up_put:
-	sock_put(sk);
 pass_up:
 	return 1;
 }
@@ -1223,7 +1180,6 @@ static void l2tp_tunnel_destruct(struct sock *sk)
 
 	l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: closing...\n", tunnel->name);
 
-
 	/* Disable udp encapsulation */
 	switch (tunnel->encap) {
 	case L2TP_ENCAPTYPE_UDP:
@@ -1246,12 +1202,11 @@ static void l2tp_tunnel_destruct(struct sock *sk)
 	list_del_rcu(&tunnel->list);
 	spin_unlock_bh(&pn->l2tp_tunnel_list_lock);
 
-	tunnel->sock = NULL;
-	l2tp_tunnel_dec_refcount(tunnel);
-
 	/* Call the original destructor */
 	if (sk->sk_destruct)
 		(*sk->sk_destruct)(sk);
+
+	kfree_rcu(tunnel, rcu);
 end:
 	return;
 }
@@ -1312,30 +1267,22 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_closeall);
 /* Tunnel socket destroy hook for UDP encapsulation */
 static void l2tp_udp_encap_destroy(struct sock *sk)
 {
-	struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk);
-	if (tunnel) {
-		l2tp_tunnel_closeall(tunnel);
-		sock_put(sk);
-	}
+	struct l2tp_tunnel *tunnel = l2tp_tunnel(sk);
+
+	if (tunnel)
+		l2tp_tunnel_delete(tunnel);
 }
 
 /* Workqueue tunnel deletion function */
 static void l2tp_tunnel_del_work(struct work_struct *work)
 {
-	struct l2tp_tunnel *tunnel = NULL;
-	struct socket *sock = NULL;
-	struct sock *sk = NULL;
-
-	tunnel = container_of(work, struct l2tp_tunnel, del_work);
+	struct l2tp_tunnel *tunnel = container_of(work, struct l2tp_tunnel,
+						  del_work);
+	struct sock *sk = tunnel->sock;
+	struct socket *sock = sk->sk_socket;
 
 	l2tp_tunnel_closeall(tunnel);
 
-	sk = l2tp_tunnel_sock_lookup(tunnel);
-	if (!sk)
-		goto out;
-
-	sock = sk->sk_socket;
-
 	/* If the tunnel socket was created within the kernel, use
 	 * the sk API to release it here.
 	 */
@@ -1346,8 +1293,10 @@ static void l2tp_tunnel_del_work(struct work_struct *work)
 		}
 	}
 
-	l2tp_tunnel_sock_put(sk);
-out:
+	/* drop initial ref */
+	l2tp_tunnel_dec_refcount(tunnel);
+
+	/* drop workqueue ref */
 	l2tp_tunnel_dec_refcount(tunnel);
 }
 
@@ -1600,13 +1549,22 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
 		sk->sk_user_data = tunnel;
 	}
 
+	/* Bump the reference count. The tunnel context is deleted
+	 * only when this drops to zero. A reference is also held on
+	 * the tunnel socket to ensure that it is not released while
+	 * the tunnel is extant. Must be done before sk_destruct is
+	 * set.
+	 */
+	refcount_set(&tunnel->ref_count, 1);
+	sock_hold(sk);
+	tunnel->sock = sk;
+	tunnel->fd = fd;
+
 	/* Hook on the tunnel socket destructor so that we can cleanup
 	 * if the tunnel socket goes away.
 	 */
 	tunnel->old_sk_destruct = sk->sk_destruct;
 	sk->sk_destruct = &l2tp_tunnel_destruct;
-	tunnel->sock = sk;
-	tunnel->fd = fd;
 	lockdep_set_class_and_name(&sk->sk_lock.slock, &l2tp_socket_class, "l2tp_sock");
 
 	sk->sk_allocation = GFP_ATOMIC;
@@ -1616,11 +1574,6 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
 
 	/* Add tunnel to our list */
 	INIT_LIST_HEAD(&tunnel->list);
-
-	/* Bump the reference count. The tunnel context is deleted
-	 * only when this drops to zero. Must be done before list insertion
-	 */
-	refcount_set(&tunnel->ref_count, 1);
 	spin_lock_bh(&pn->l2tp_tunnel_list_lock);
 	list_add_rcu(&tunnel->list, &pn->l2tp_tunnel_list);
 	spin_unlock_bh(&pn->l2tp_tunnel_list_lock);
@@ -1661,8 +1614,6 @@ void l2tp_session_free(struct l2tp_session *session)
 
 	if (tunnel) {
 		BUG_ON(tunnel->magic != L2TP_TUNNEL_MAGIC);
-		sock_put(tunnel->sock);
-		session->tunnel = NULL;
 		l2tp_tunnel_dec_refcount(tunnel);
 	}
 
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 9534e16965cc..8ecb1d357445 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -219,27 +219,8 @@ static inline void *l2tp_session_priv(struct l2tp_session *session)
 	return &session->priv[0];
 }
 
-static inline struct l2tp_tunnel *l2tp_sock_to_tunnel(struct sock *sk)
-{
-	struct l2tp_tunnel *tunnel;
-
-	if (sk == NULL)
-		return NULL;
-
-	sock_hold(sk);
-	tunnel = (struct l2tp_tunnel *)(sk->sk_user_data);
-	if (tunnel == NULL) {
-		sock_put(sk);
-		goto out;
-	}
-
-	BUG_ON(tunnel->magic != L2TP_TUNNEL_MAGIC);
-
-out:
-	return tunnel;
-}
-
 struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id);
+void l2tp_tunnel_free(struct l2tp_tunnel *tunnel);
 
 struct l2tp_session *l2tp_session_get(const struct net *net,
 				      struct l2tp_tunnel *tunnel,
@@ -288,7 +269,7 @@ static inline void l2tp_tunnel_inc_refcount(struct l2tp_tunnel *tunnel)
 static inline void l2tp_tunnel_dec_refcount(struct l2tp_tunnel *tunnel)
 {
 	if (refcount_dec_and_test(&tunnel->ref_count))
-		kfree_rcu(tunnel, rcu);
+		l2tp_tunnel_free(tunnel);
 }
 
 /* Session reference counts. Incremented when code obtains a reference
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index ff61124fdf59..3428fba6f2b7 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -234,17 +234,13 @@ static void l2tp_ip_close(struct sock *sk, long timeout)
 static void l2tp_ip_destroy_sock(struct sock *sk)
 {
 	struct sk_buff *skb;
-	struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk);
+	struct l2tp_tunnel *tunnel = sk->sk_user_data;
 
 	while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL)
 		kfree_skb(skb);
 
-	if (tunnel) {
-		l2tp_tunnel_closeall(tunnel);
-		sock_put(sk);
-	}
-
-	sk_refcnt_debug_dec(sk);
+	if (tunnel)
+		l2tp_tunnel_delete(tunnel);
 }
 
 static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 192344688c06..6f009eaa5fbe 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -248,16 +248,14 @@ static void l2tp_ip6_close(struct sock *sk, long timeout)
 
 static void l2tp_ip6_destroy_sock(struct sock *sk)
 {
-	struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk);
+	struct l2tp_tunnel *tunnel = sk->sk_user_data;
 
 	lock_sock(sk);
 	ip6_flush_pending_frames(sk);
 	release_sock(sk);
 
-	if (tunnel) {
-		l2tp_tunnel_closeall(tunnel);
-		sock_put(sk);
-	}
+	if (tunnel)
+		l2tp_tunnel_delete(tunnel);
 
 	inet6_destroy_sock(sk);
 }
-- 
2.14.3


From ad9a706a273f6ed4cca59ff2ae7e7dd0d5eed4ed Mon Sep 17 00:00:00 2001
From: James Chapman <jchapman@katalix.com>
Date: Fri, 23 Feb 2018 17:45:46 +0000
Subject: [PATCH 50/59] l2tp: fix race in pppol2tp_release with session object
 destroy

[ Upstream commit d02ba2a6110c530a32926af8ad441111774d2893 ]

pppol2tp_release uses call_rcu to put the final ref on its socket. But
the session object doesn't hold a ref on the session socket so may be
freed while the pppol2tp_put_sk RCU callback is scheduled. Fix this by
having the session hold a ref on its socket until the session is
destroyed. It is this ref that is dropped via call_rcu.

Sessions are also deleted via l2tp_tunnel_closeall. This must now also put
the final ref via call_rcu. So move the call_rcu call site into
pppol2tp_session_close so that this happens in both destroy paths. A
common destroy path should really be implemented, perhaps with
l2tp_tunnel_closeall calling l2tp_session_delete like pppol2tp_release
does, but this will be looked at later.

ODEBUG: activate active (active state 1) object type: rcu_head hint:           (null)
WARNING: CPU: 3 PID: 13407 at lib/debugobjects.c:291 debug_print_object+0x166/0x220
Modules linked in:
CPU: 3 PID: 13407 Comm: syzbot_19c09769 Not tainted 4.16.0-rc2+ #38
Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
RIP: 0010:debug_print_object+0x166/0x220
RSP: 0018:ffff880013647a00 EFLAGS: 00010082
RAX: dffffc0000000008 RBX: 0000000000000003 RCX: ffffffff814d3333
RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff88001a59f6d0
RBP: ffff880013647a40 R08: 0000000000000000 R09: 0000000000000001
R10: ffff8800136479a8 R11: 0000000000000000 R12: 0000000000000001
R13: ffffffff86161420 R14: ffffffff85648b60 R15: 0000000000000000
FS:  0000000000000000(0000) GS:ffff88001a580000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000020e77000 CR3: 0000000006022000 CR4: 00000000000006e0
Call Trace:
 debug_object_activate+0x38b/0x530
 ? debug_object_assert_init+0x3b0/0x3b0
 ? __mutex_unlock_slowpath+0x85/0x8b0
 ? pppol2tp_session_destruct+0x110/0x110
 __call_rcu.constprop.66+0x39/0x890
 ? __call_rcu.constprop.66+0x39/0x890
 call_rcu_sched+0x17/0x20
 pppol2tp_release+0x2c7/0x440
 ? fcntl_setlk+0xca0/0xca0
 ? sock_alloc_file+0x340/0x340
 sock_release+0x92/0x1e0
 sock_close+0x1b/0x20
 __fput+0x296/0x6e0
 ____fput+0x1a/0x20
 task_work_run+0x127/0x1a0
 do_exit+0x7f9/0x2ce0
 ? SYSC_connect+0x212/0x310
 ? mm_update_next_owner+0x690/0x690
 ? up_read+0x1f/0x40
 ? __do_page_fault+0x3c8/0xca0
 do_group_exit+0x10d/0x330
 ? do_group_exit+0x330/0x330
 SyS_exit_group+0x22/0x30
 do_syscall_64+0x1e0/0x730
 ? trace_hardirqs_off_thunk+0x1a/0x1c
 entry_SYSCALL_64_after_hwframe+0x42/0xb7
RIP: 0033:0x7f362e471259
RSP: 002b:00007ffe389abe08 EFLAGS: 00000202 ORIG_RAX: 00000000000000e7
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f362e471259
RDX: 00007f362e471259 RSI: 000000000000002e RDI: 0000000000000000
RBP: 00007ffe389abe30 R08: 0000000000000000 R09: 00007f362e944270
R10: 0000000000000000 R11: 0000000000000202 R12: 0000000000400b60
R13: 00007ffe389abf50 R14: 0000000000000000 R15: 0000000000000000
Code: 8d 3c dd a0 8f 64 85 48 89 fa 48 c1 ea 03 80 3c 02 00 75 7b 48 8b 14 dd a0 8f 64 85 4c 89 f6 48 c7 c7 20 85 64 85 e
8 2a 55 14 ff <0f> 0b 83 05 ad 2a 68 04 01 48 83 c4 18 5b 41 5c 41 5d 41 5e 41

Fixes: ee40fb2e1eb5b ("l2tp: protect sock pointer of struct pppol2tp_session with RCU")
Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ppp.c | 52 +++++++++++++++++++++++++++-------------------------
 1 file changed, 27 insertions(+), 25 deletions(-)

diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 3b033c8fe736..5ea718609fe8 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -416,10 +416,28 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
  * Session (and tunnel control) socket create/destroy.
  *****************************************************************************/
 
+static void pppol2tp_put_sk(struct rcu_head *head)
+{
+	struct pppol2tp_session *ps;
+
+	ps = container_of(head, typeof(*ps), rcu);
+	sock_put(ps->__sk);
+}
+
 /* Called by l2tp_core when a session socket is being closed.
  */
 static void pppol2tp_session_close(struct l2tp_session *session)
 {
+	struct pppol2tp_session *ps;
+
+	ps = l2tp_session_priv(session);
+	mutex_lock(&ps->sk_lock);
+	ps->__sk = rcu_dereference_protected(ps->sk,
+					     lockdep_is_held(&ps->sk_lock));
+	RCU_INIT_POINTER(ps->sk, NULL);
+	if (ps->__sk)
+		call_rcu(&ps->rcu, pppol2tp_put_sk);
+	mutex_unlock(&ps->sk_lock);
 }
 
 /* Really kill the session socket. (Called from sock_put() if
@@ -439,14 +457,6 @@ static void pppol2tp_session_destruct(struct sock *sk)
 	}
 }
 
-static void pppol2tp_put_sk(struct rcu_head *head)
-{
-	struct pppol2tp_session *ps;
-
-	ps = container_of(head, typeof(*ps), rcu);
-	sock_put(ps->__sk);
-}
-
 /* Called when the PPPoX socket (session) is closed.
  */
 static int pppol2tp_release(struct socket *sock)
@@ -470,26 +480,17 @@ static int pppol2tp_release(struct socket *sock)
 	sock_orphan(sk);
 	sock->sk = NULL;
 
+	/* If the socket is associated with a session,
+	 * l2tp_session_delete will call pppol2tp_session_close which
+	 * will drop the session's ref on the socket.
+	 */
 	session = pppol2tp_sock_to_session(sk);
-
-	if (session != NULL) {
-		struct pppol2tp_session *ps;
-
+	if (session) {
 		l2tp_session_delete(session);
-
-		ps = l2tp_session_priv(session);
-		mutex_lock(&ps->sk_lock);
-		ps->__sk = rcu_dereference_protected(ps->sk,
-						     lockdep_is_held(&ps->sk_lock));
-		RCU_INIT_POINTER(ps->sk, NULL);
-		mutex_unlock(&ps->sk_lock);
-		call_rcu(&ps->rcu, pppol2tp_put_sk);
-
-		/* Rely on the sock_put() call at the end of the function for
-		 * dropping the reference held by pppol2tp_sock_to_session().
-		 * The last reference will be dropped by pppol2tp_put_sk().
-		 */
+		/* drop the ref obtained by pppol2tp_sock_to_session */
+		sock_put(sk);
 	}
+
 	release_sock(sk);
 
 	/* This will delete the session context via
@@ -786,6 +787,7 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 
 out_no_ppp:
 	/* This is how we get the session context from the socket. */
+	sock_hold(sk);
 	sk->sk_user_data = session;
 	rcu_assign_pointer(ps->sk, sk);
 	mutex_unlock(&ps->sk_lock);
-- 
2.14.3


From f8dd90af2a2b9071da57051d819873beaafb9cae Mon Sep 17 00:00:00 2001
From: James Chapman <jchapman@katalix.com>
Date: Fri, 23 Feb 2018 17:45:47 +0000
Subject: [PATCH 51/59] l2tp: fix tunnel lookup use-after-free race

[ Upstream commit 28f5bfb819195ad9c2eb9486babe7b0e4efe925f ]

l2tp_tunnel_get walks the tunnel list to find a matching tunnel
instance and if a match is found, its refcount is increased before
returning the tunnel pointer. But when tunnel objects are destroyed,
they are on the tunnel list after their refcount hits zero. Fix this
by moving the code that removes the tunnel from the tunnel list from
the tunnel socket destructor into in the l2tp_tunnel_delete path,
before the tunnel refcount is decremented.

refcount_t: increment on 0; use-after-free.
WARNING: CPU: 3 PID: 13507 at lib/refcount.c:153 refcount_inc+0x47/0x50
Modules linked in:
CPU: 3 PID: 13507 Comm: syzbot_6e6a5ec8 Not tainted 4.16.0-rc2+ #36
Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
RIP: 0010:refcount_inc+0x47/0x50
RSP: 0018:ffff8800136ffb20 EFLAGS: 00010286
RAX: dffffc0000000008 RBX: ffff880017068e68 RCX: ffffffff814d3333
RDX: 0000000000000000 RSI: ffff88001a59f6d8 RDI: ffff88001a59f6d8
RBP: ffff8800136ffb28 R08: 0000000000000000 R09: 0000000000000000
R10: ffff8800136ffab0 R11: 0000000000000000 R12: ffff880017068e50
R13: 0000000000000000 R14: ffff8800174da800 R15: 0000000000000004
FS:  00007f403ab1e700(0000) GS:ffff88001a580000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000205fafd2 CR3: 0000000016770000 CR4: 00000000000006e0
Call Trace:
 l2tp_tunnel_get+0x2dd/0x4e0
 pppol2tp_connect+0x428/0x13c0
 ? pppol2tp_session_create+0x170/0x170
 ? __might_fault+0x115/0x1d0
 ? lock_downgrade+0x860/0x860
 ? __might_fault+0xe5/0x1d0
 ? security_socket_connect+0x8e/0xc0
 SYSC_connect+0x1b6/0x310
 ? SYSC_bind+0x280/0x280
 ? __do_page_fault+0x5d1/0xca0
 ? up_read+0x1f/0x40
 ? __do_page_fault+0x3c8/0xca0
 SyS_connect+0x29/0x30
 ? SyS_accept+0x40/0x40
 do_syscall_64+0x1e0/0x730
 ? trace_hardirqs_off_thunk+0x1a/0x1c
 entry_SYSCALL_64_after_hwframe+0x42/0xb7
RIP: 0033:0x7f403a42f259
RSP: 002b:00007f403ab1dee8 EFLAGS: 00000296 ORIG_RAX: 000000000000002a
RAX: ffffffffffffffda RBX: 00000000205fafe4 RCX: 00007f403a42f259
RDX: 000000000000002e RSI: 00000000205fafd2 RDI: 0000000000000004
RBP: 00007f403ab1df20 R08: 00007f403ab1e700 R09: 0000000000000000
R10: 00007f403ab1e700 R11: 0000000000000296 R12: 0000000000000000
R13: 00007ffc81906cbf R14: 0000000000000000 R15: 00007f403ab2b040
Code: 3b ff 5b 5d c3 e8 ca 5f 3b ff 80 3d 49 8e 66 04 00 75 ea e8 bc 5f 3b ff 48 c7 c7 60 69 64 85 c6 05 34 8e 66 04 01 e8 59 49 15 ff <0f> 0b eb ce 0f 1f 44 00 00 55 48 89 e5 41 56 41 55 41 54 53 49

Fixes: f8ccac0e44934 ("l2tp: put tunnel socket release on a workqueue")
Reported-and-tested-by: syzbot+19c09769f14b48810113@syzkaller.appspotmail.com
Reported-and-tested-by: syzbot+347bd5acde002e353a36@syzkaller.appspotmail.com
Reported-and-tested-by: syzbot+6e6a5ec8de31a94cd015@syzkaller.appspotmail.com
Reported-and-tested-by: syzbot+9df43faf09bd400f2993@syzkaller.appspotmail.com
Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index a8126d9a1645..861b67c34191 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1173,7 +1173,6 @@ EXPORT_SYMBOL_GPL(l2tp_xmit_skb);
 static void l2tp_tunnel_destruct(struct sock *sk)
 {
 	struct l2tp_tunnel *tunnel = l2tp_tunnel(sk);
-	struct l2tp_net *pn;
 
 	if (tunnel == NULL)
 		goto end;
@@ -1196,12 +1195,6 @@ static void l2tp_tunnel_destruct(struct sock *sk)
 	sk->sk_destruct = tunnel->old_sk_destruct;
 	sk->sk_user_data = NULL;
 
-	/* Remove the tunnel struct from the tunnel list */
-	pn = l2tp_pernet(tunnel->l2tp_net);
-	spin_lock_bh(&pn->l2tp_tunnel_list_lock);
-	list_del_rcu(&tunnel->list);
-	spin_unlock_bh(&pn->l2tp_tunnel_list_lock);
-
 	/* Call the original destructor */
 	if (sk->sk_destruct)
 		(*sk->sk_destruct)(sk);
@@ -1280,6 +1273,7 @@ static void l2tp_tunnel_del_work(struct work_struct *work)
 						  del_work);
 	struct sock *sk = tunnel->sock;
 	struct socket *sock = sk->sk_socket;
+	struct l2tp_net *pn;
 
 	l2tp_tunnel_closeall(tunnel);
 
@@ -1293,6 +1287,12 @@ static void l2tp_tunnel_del_work(struct work_struct *work)
 		}
 	}
 
+	/* Remove the tunnel struct from the tunnel list */
+	pn = l2tp_pernet(tunnel->l2tp_net);
+	spin_lock_bh(&pn->l2tp_tunnel_list_lock);
+	list_del_rcu(&tunnel->list);
+	spin_unlock_bh(&pn->l2tp_tunnel_list_lock);
+
 	/* drop initial ref */
 	l2tp_tunnel_dec_refcount(tunnel);
 
-- 
2.14.3


From b4c8b3286486a929b43e3f2e42080e1fa46957e1 Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.vnet.ibm.com>
Date: Fri, 9 Feb 2018 11:03:49 +0100
Subject: [PATCH 52/59] s390/qeth: fix underestimated count of buffer elements

[ Upstream commit 89271c65edd599207dd982007900506283c90ae3 ]

For a memory range/skb where the last byte falls onto a page boundary
(ie. 'end' is of the form xxx...xxx001), the PFN_UP() part of the
calculation currently doesn't round up to the next PFN due to an
off-by-one error.
Thus qeth believes that the skb occupies one page less than it
actually does, and may select a IO buffer that doesn't have enough spare
buffer elements to fit all of the skb's data.
HW detects this as a malformed buffer descriptor, and raises an
exception which then triggers device recovery.

Fixes: 2863c61334aa ("qeth: refactor calculation of SBALE count")
Signed-off-by: Ursula Braun <ubraun@linux.vnet.ibm.com>
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index badf42acbf95..351f1ce5cd3d 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -836,7 +836,7 @@ struct qeth_trap_id {
  */
 static inline int qeth_get_elements_for_range(addr_t start, addr_t end)
 {
-	return PFN_UP(end - 1) - PFN_DOWN(start);
+	return PFN_UP(end) - PFN_DOWN(start);
 }
 
 static inline int qeth_get_micros(void)
-- 
2.14.3


From 6da123de3caf84da075f4711830359a1c581f2ae Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Fri, 9 Feb 2018 11:03:50 +0100
Subject: [PATCH 53/59] s390/qeth: fix SETIP command handling

[ Upstream commit 1c5b2216fbb973a9410e0b06389740b5c1289171 ]

send_control_data() applies some special handling to SETIP v4 IPA
commands. But current code parses *all* command types for the SETIP
command code. Limit the command code check to IPA commands.

Fixes: 5b54e16f1a54 ("qeth: do not spin for SETIP ip assist command")
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core.h      |  5 +++++
 drivers/s390/net/qeth_core_main.c | 14 ++++++++------
 2 files changed, 13 insertions(+), 6 deletions(-)

diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 351f1ce5cd3d..185b3cd48b88 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -581,6 +581,11 @@ struct qeth_cmd_buffer {
 	void (*callback) (struct qeth_channel *, struct qeth_cmd_buffer *);
 };
 
+static inline struct qeth_ipa_cmd *__ipa_cmd(struct qeth_cmd_buffer *iob)
+{
+	return (struct qeth_ipa_cmd *)(iob->data + IPA_PDU_HEADER_SIZE);
+}
+
 /**
  * definition of a qeth channel, used for read and write
  */
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 3614df68830f..48af6c1df02b 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -2057,7 +2057,7 @@ int qeth_send_control_data(struct qeth_card *card, int len,
 	unsigned long flags;
 	struct qeth_reply *reply = NULL;
 	unsigned long timeout, event_timeout;
-	struct qeth_ipa_cmd *cmd;
+	struct qeth_ipa_cmd *cmd = NULL;
 
 	QETH_CARD_TEXT(card, 2, "sendctl");
 
@@ -2083,10 +2083,13 @@ int qeth_send_control_data(struct qeth_card *card, int len,
 	while (atomic_cmpxchg(&card->write.irq_pending, 0, 1)) ;
 	qeth_prepare_control_data(card, len, iob);
 
-	if (IS_IPA(iob->data))
+	if (IS_IPA(iob->data)) {
+		cmd = __ipa_cmd(iob);
 		event_timeout = QETH_IPA_TIMEOUT;
-	else
+	} else {
 		event_timeout = QETH_TIMEOUT;
+	}
+
 	timeout = jiffies + event_timeout;
 
 	QETH_CARD_TEXT(card, 6, "noirqpnd");
@@ -2111,9 +2114,8 @@ int qeth_send_control_data(struct qeth_card *card, int len,
 
 	/* we have only one long running ipassist, since we can ensure
 	   process context of this command we can sleep */
-	cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE);
-	if ((cmd->hdr.command == IPA_CMD_SETIP) &&
-	    (cmd->hdr.prot_version == QETH_PROT_IPV4)) {
+	if (cmd && cmd->hdr.command == IPA_CMD_SETIP &&
+	    cmd->hdr.prot_version == QETH_PROT_IPV4) {
 		if (!wait_event_timeout(reply->wait_q,
 		    atomic_read(&reply->received), event_timeout))
 			goto time_err;
-- 
2.14.3


From 4cb89d6f13b7e881af43c7681c95348ee866c5ad Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Tue, 27 Feb 2018 18:58:12 +0100
Subject: [PATCH 54/59] s390/qeth: fix overestimated count of buffer elements

[ Upstream commit 12472af89632beb1ed8dea29d4efe208ca05b06a ]

qeth_get_elements_for_range() doesn't know how to handle a 0-length
range (ie. start == end), and returns 1 when it should return 0.
Such ranges occur on TSO skbs, where the L2/L3/L4 headers (and thus all
of the skb's linear data) are skipped when mapping the skb into regular
buffer elements.

This overestimation may cause several performance-related issues:
1. sub-optimal IO buffer selection, where the next buffer gets selected
   even though the skb would actually still fit into the current buffer.
2. forced linearization, if the element count for a non-linear skb
   exceeds QETH_MAX_BUFFER_ELEMENTS.

Rather than modifying qeth_get_elements_for_range() and adding overhead
to every caller, fix up those callers that are in risk of passing a
0-length range.

Fixes: 2863c61334aa ("qeth: refactor calculation of SBALE count")
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 10 ++++++----
 drivers/s390/net/qeth_l3_main.c   | 11 ++++++-----
 2 files changed, 12 insertions(+), 9 deletions(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 48af6c1df02b..c9b632e8ab5e 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -3835,10 +3835,12 @@ EXPORT_SYMBOL_GPL(qeth_get_elements_for_frags);
 int qeth_get_elements_no(struct qeth_card *card,
 		     struct sk_buff *skb, int extra_elems, int data_offset)
 {
-	int elements = qeth_get_elements_for_range(
-				(addr_t)skb->data + data_offset,
-				(addr_t)skb->data + skb_headlen(skb)) +
-			qeth_get_elements_for_frags(skb);
+	addr_t end = (addr_t)skb->data + skb_headlen(skb);
+	int elements = qeth_get_elements_for_frags(skb);
+	addr_t start = (addr_t)skb->data + data_offset;
+
+	if (start != end)
+		elements += qeth_get_elements_for_range(start, end);
 
 	if ((elements + extra_elems) > QETH_MAX_BUFFER_ELEMENTS(card)) {
 		QETH_DBF_MESSAGE(2, "Invalid size of IP packet "
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index ef0961e18686..c67c9cea9234 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -2629,11 +2629,12 @@ static void qeth_tso_fill_header(struct qeth_card *card,
 static int qeth_l3_get_elements_no_tso(struct qeth_card *card,
 			struct sk_buff *skb, int extra_elems)
 {
-	addr_t tcpdptr = (addr_t)tcp_hdr(skb) + tcp_hdrlen(skb);
-	int elements = qeth_get_elements_for_range(
-				tcpdptr,
-				(addr_t)skb->data + skb_headlen(skb)) +
-				qeth_get_elements_for_frags(skb);
+	addr_t start = (addr_t)tcp_hdr(skb) + tcp_hdrlen(skb);
+	addr_t end = (addr_t)skb->data + skb_headlen(skb);
+	int elements = qeth_get_elements_for_frags(skb);
+
+	if (start != end)
+		elements += qeth_get_elements_for_range(start, end);
 
 	if ((elements + extra_elems) > QETH_MAX_BUFFER_ELEMENTS(card)) {
 		QETH_DBF_MESSAGE(2,
-- 
2.14.3


From f63262d63217db414afd797b69436820fbad5d64 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Tue, 27 Feb 2018 18:58:13 +0100
Subject: [PATCH 55/59] s390/qeth: fix IP removal on offline cards

[ Upstream commit 98d823ab1fbdcb13abc25b420f9bb71bade42056 ]

If the HW is not reachable, then none of the IPs in qeth's internal
table has been registered with the HW yet. So when deleting such an IP,
there's no need to stage it for deregistration - just drop it from
the table.

This fixes the "add-delete-add" scenario on an offline card, where the
the second "add" merely increments the IP's use count. But as the IP is
still set to DISP_ADDR_DELETE from the previous "delete" step,
l3_recover_ip() won't register it with the HW when the card goes online.

Fixes: 5f78e29ceebf ("qeth: optimize IP handling in rx_mode callback")
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_l3_main.c | 14 +++-----------
 1 file changed, 3 insertions(+), 11 deletions(-)

diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index c67c9cea9234..9ddd12e974ab 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -256,12 +256,8 @@ int qeth_l3_delete_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
 	if (addr->in_progress)
 		return -EINPROGRESS;
 
-	if (!qeth_card_hw_is_reachable(card)) {
-		addr->disp_flag = QETH_DISP_ADDR_DELETE;
-		return 0;
-	}
-
-	rc = qeth_l3_deregister_addr_entry(card, addr);
+	if (qeth_card_hw_is_reachable(card))
+		rc = qeth_l3_deregister_addr_entry(card, addr);
 
 	hash_del(&addr->hnode);
 	kfree(addr);
@@ -404,11 +400,7 @@ static void qeth_l3_recover_ip(struct qeth_card *card)
 	spin_lock_bh(&card->ip_lock);
 
 	hash_for_each_safe(card->ip_htable, i, tmp, addr, hnode) {
-		if (addr->disp_flag == QETH_DISP_ADDR_DELETE) {
-			qeth_l3_deregister_addr_entry(card, addr);
-			hash_del(&addr->hnode);
-			kfree(addr);
-		} else if (addr->disp_flag == QETH_DISP_ADDR_ADD) {
+		if (addr->disp_flag == QETH_DISP_ADDR_ADD) {
 			if (addr->proto == QETH_PROT_IPV4) {
 				addr->in_progress = 1;
 				spin_unlock_bh(&card->ip_lock);
-- 
2.14.3


From 04a4da2658c614192b08a4b012f2d1e7de27c43b Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Tue, 27 Feb 2018 18:58:14 +0100
Subject: [PATCH 56/59] s390/qeth: fix double-free on IP add/remove race

[ Upstream commit 14d066c3531a87f727968cacd85bd95c75f59843 ]

Registering an IPv4 address with the HW takes quite a while, so we
temporarily drop the ip_htable lock. Any concurrent add/remove of the
same IP adjusts the IP's use count, and (on remove) is then blocked by
addr->in_progress.
After the register call has completed, we check the use count for
concurrently attempted add/remove calls - and possibly straight-away
deregister the IP again. This happens via l3_delete_ip(), which
1) looks up the queried IP in the htable (getting a reference to the
   *same* queried object),
2) deregisters the IP from the HW, and
3) frees the IP object.

The caller in l3_add_ip() then does a second free on the same object.

For this case, skip all the extra checks and lookups in l3_delete_ip()
and just deregister & free the IP object ourselves.

Fixes: 5f78e29ceebf ("qeth: optimize IP handling in rx_mode callback")
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_l3_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 9ddd12e974ab..f770a3bee5fc 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -320,7 +320,8 @@ int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
 				(rc == IPA_RC_LAN_OFFLINE)) {
 			addr->disp_flag = QETH_DISP_ADDR_DO_NOTHING;
 			if (addr->ref_counter < 1) {
-				qeth_l3_delete_ip(card, addr);
+				qeth_l3_deregister_addr_entry(card, addr);
+				hash_del(&addr->hnode);
 				kfree(addr);
 			}
 		} else {
-- 
2.14.3


From 6b13cc850308c0a7d0dc5cf47dc5d6d3b94b5946 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Tue, 27 Feb 2018 18:58:15 +0100
Subject: [PATCH 57/59] Revert "s390/qeth: fix using of ref counter for rxip
 addresses"

[ Upstream commit 4964c66fd49b2e2342da35358f2ff74614bcbaee ]

This reverts commit cb816192d986f7596009dedcf2201fe2e5bc2aa7.

The issue this attempted to fix never actually occurs.
l3_add_rxip() checks (via l3_ip_from_hash()) if the requested address
was previously added to the card. If so, it returns -EEXIST and doesn't
call l3_add_ip().
As a result, the "address exists" path in l3_add_ip() is never taken
for rxip addresses, and this patch had no effect.

Fixes: cb816192d986 ("s390/qeth: fix using of ref counter for rxip addresses")
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_l3_main.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index f770a3bee5fc..4ed3c623aff2 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -250,8 +250,7 @@ int qeth_l3_delete_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
 		return -ENOENT;
 
 	addr->ref_counter--;
-	if (addr->ref_counter > 0 && (addr->type == QETH_IP_TYPE_NORMAL ||
-				      addr->type == QETH_IP_TYPE_RXIP))
+	if (addr->type == QETH_IP_TYPE_NORMAL && addr->ref_counter > 0)
 		return rc;
 	if (addr->in_progress)
 		return -EINPROGRESS;
@@ -329,9 +328,8 @@ int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
 			kfree(addr);
 		}
 	} else {
-		if (addr->type == QETH_IP_TYPE_NORMAL ||
-		    addr->type == QETH_IP_TYPE_RXIP)
-			addr->ref_counter++;
+			if (addr->type == QETH_IP_TYPE_NORMAL)
+				addr->ref_counter++;
 	}
 
 	return rc;
-- 
2.14.3


From 6e9d0481cf0bb67a1c215cc33f900c5c9f7ac15d Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Tue, 27 Feb 2018 18:58:16 +0100
Subject: [PATCH 58/59] s390/qeth: fix IP address lookup for L3 devices

[ Upstream commit c5c48c58b259bb8f0482398370ee539d7a12df3e ]

Current code ("qeth_l3_ip_from_hash()") matches a queried address object
against objects in the IP table by IP address, Mask/Prefix Length and
MAC address ("qeth_l3_ipaddrs_is_equal()"). But what callers actually
require is either
a) "is this IP address registered" (ie. match by IP address only),
before adding a new address.
b) or "is this address object registered" (ie. match all relevant
   attributes), before deleting an address.

Right now
1. the ADD path is too strict in its lookup, and eg. doesn't detect
conflicts between an existing NORMAL address and a new VIPA address
(because the NORMAL address will have mask != 0, while VIPA has
a mask == 0),
2. the DELETE path is not strict enough, and eg. allows del_rxip() to
delete a VIPA address as long as the IP address matches.

Fix all this by adding helpers (_addr_match_ip() and _addr_match_all())
that do the appropriate checking.

Note that the ADD path for NORMAL addresses is special, as qeth keeps
track of how many times such an address is in use (and there is no
immediate way of returning errors to the caller). So when a requested
NORMAL address _fully_ matches an existing one, it's not considered a
conflict and we merely increment the refcount.

Fixes: 5f78e29ceebf ("qeth: optimize IP handling in rx_mode callback")
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_l3.h      | 34 ++++++++++++++-
 drivers/s390/net/qeth_l3_main.c | 91 +++++++++++++++++++----------------------
 2 files changed, 74 insertions(+), 51 deletions(-)

diff --git a/drivers/s390/net/qeth_l3.h b/drivers/s390/net/qeth_l3.h
index e5833837b799..8727b9517de8 100644
--- a/drivers/s390/net/qeth_l3.h
+++ b/drivers/s390/net/qeth_l3.h
@@ -40,8 +40,40 @@ struct qeth_ipaddr {
 			unsigned int pfxlen;
 		} a6;
 	} u;
-
 };
+
+static inline bool qeth_l3_addr_match_ip(struct qeth_ipaddr *a1,
+					 struct qeth_ipaddr *a2)
+{
+	if (a1->proto != a2->proto)
+		return false;
+	if (a1->proto == QETH_PROT_IPV6)
+		return ipv6_addr_equal(&a1->u.a6.addr, &a2->u.a6.addr);
+	return a1->u.a4.addr == a2->u.a4.addr;
+}
+
+static inline bool qeth_l3_addr_match_all(struct qeth_ipaddr *a1,
+					  struct qeth_ipaddr *a2)
+{
+	/* Assumes that the pair was obtained via qeth_l3_addr_find_by_ip(),
+	 * so 'proto' and 'addr' match for sure.
+	 *
+	 * For ucast:
+	 * -	'mac' is always 0.
+	 * -	'mask'/'pfxlen' for RXIP/VIPA is always 0. For NORMAL, matching
+	 *	values are required to avoid mixups in takeover eligibility.
+	 *
+	 * For mcast,
+	 * -	'mac' is mapped from the IP, and thus always matches.
+	 * -	'mask'/'pfxlen' is always 0.
+	 */
+	if (a1->type != a2->type)
+		return false;
+	if (a1->proto == QETH_PROT_IPV6)
+		return a1->u.a6.pfxlen == a2->u.a6.pfxlen;
+	return a1->u.a4.mask == a2->u.a4.mask;
+}
+
 static inline  u64 qeth_l3_ipaddr_hash(struct qeth_ipaddr *addr)
 {
 	u64  ret = 0;
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 4ed3c623aff2..33131c594627 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -150,6 +150,24 @@ int qeth_l3_string_to_ipaddr(const char *buf, enum qeth_prot_versions proto,
 		return -EINVAL;
 }
 
+static struct qeth_ipaddr *qeth_l3_find_addr_by_ip(struct qeth_card *card,
+						   struct qeth_ipaddr *query)
+{
+	u64 key = qeth_l3_ipaddr_hash(query);
+	struct qeth_ipaddr *addr;
+
+	if (query->is_multicast) {
+		hash_for_each_possible(card->ip_mc_htable, addr, hnode, key)
+			if (qeth_l3_addr_match_ip(addr, query))
+				return addr;
+	} else {
+		hash_for_each_possible(card->ip_htable,  addr, hnode, key)
+			if (qeth_l3_addr_match_ip(addr, query))
+				return addr;
+	}
+	return NULL;
+}
+
 static void qeth_l3_convert_addr_to_bits(u8 *addr, u8 *bits, int len)
 {
 	int i, j;
@@ -203,34 +221,6 @@ static bool qeth_l3_is_addr_covered_by_ipato(struct qeth_card *card,
 	return rc;
 }
 
-inline int
-qeth_l3_ipaddrs_is_equal(struct qeth_ipaddr *addr1, struct qeth_ipaddr *addr2)
-{
-	return addr1->proto == addr2->proto &&
-		!memcmp(&addr1->u, &addr2->u, sizeof(addr1->u))  &&
-		!memcmp(&addr1->mac, &addr2->mac, sizeof(addr1->mac));
-}
-
-static struct qeth_ipaddr *
-qeth_l3_ip_from_hash(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
-{
-	struct qeth_ipaddr *addr;
-
-	if (tmp_addr->is_multicast) {
-		hash_for_each_possible(card->ip_mc_htable,  addr,
-				hnode, qeth_l3_ipaddr_hash(tmp_addr))
-			if (qeth_l3_ipaddrs_is_equal(tmp_addr, addr))
-				return addr;
-	} else {
-		hash_for_each_possible(card->ip_htable,  addr,
-				hnode, qeth_l3_ipaddr_hash(tmp_addr))
-			if (qeth_l3_ipaddrs_is_equal(tmp_addr, addr))
-				return addr;
-	}
-
-	return NULL;
-}
-
 int qeth_l3_delete_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
 {
 	int rc = 0;
@@ -245,8 +235,8 @@ int qeth_l3_delete_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
 		QETH_CARD_HEX(card, 4, ((char *)&tmp_addr->u.a6.addr) + 8, 8);
 	}
 
-	addr = qeth_l3_ip_from_hash(card, tmp_addr);
-	if (!addr)
+	addr = qeth_l3_find_addr_by_ip(card, tmp_addr);
+	if (!addr || !qeth_l3_addr_match_all(addr, tmp_addr))
 		return -ENOENT;
 
 	addr->ref_counter--;
@@ -268,6 +258,7 @@ int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
 {
 	int rc = 0;
 	struct qeth_ipaddr *addr;
+	char buf[40];
 
 	QETH_CARD_TEXT(card, 4, "addip");
 
@@ -278,8 +269,20 @@ int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
 		QETH_CARD_HEX(card, 4, ((char *)&tmp_addr->u.a6.addr) + 8, 8);
 	}
 
-	addr = qeth_l3_ip_from_hash(card, tmp_addr);
-	if (!addr) {
+	addr = qeth_l3_find_addr_by_ip(card, tmp_addr);
+	if (addr) {
+		if (tmp_addr->type != QETH_IP_TYPE_NORMAL)
+			return -EADDRINUSE;
+		if (qeth_l3_addr_match_all(addr, tmp_addr)) {
+			addr->ref_counter++;
+			return 0;
+		}
+		qeth_l3_ipaddr_to_string(tmp_addr->proto, (u8 *)&tmp_addr->u,
+					 buf);
+		dev_warn(&card->gdev->dev,
+			 "Registering IP address %s failed\n", buf);
+		return -EADDRINUSE;
+	} else {
 		addr = qeth_l3_get_addr_buffer(tmp_addr->proto);
 		if (!addr)
 			return -ENOMEM;
@@ -327,11 +330,7 @@ int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
 			hash_del(&addr->hnode);
 			kfree(addr);
 		}
-	} else {
-			if (addr->type == QETH_IP_TYPE_NORMAL)
-				addr->ref_counter++;
 	}
-
 	return rc;
 }
 
@@ -715,12 +714,7 @@ int qeth_l3_add_vipa(struct qeth_card *card, enum qeth_prot_versions proto,
 		return -ENOMEM;
 
 	spin_lock_bh(&card->ip_lock);
-
-	if (qeth_l3_ip_from_hash(card, ipaddr))
-		rc = -EEXIST;
-	else
-		qeth_l3_add_ip(card, ipaddr);
-
+	rc = qeth_l3_add_ip(card, ipaddr);
 	spin_unlock_bh(&card->ip_lock);
 
 	kfree(ipaddr);
@@ -783,12 +777,7 @@ int qeth_l3_add_rxip(struct qeth_card *card, enum qeth_prot_versions proto,
 		return -ENOMEM;
 
 	spin_lock_bh(&card->ip_lock);
-
-	if (qeth_l3_ip_from_hash(card, ipaddr))
-		rc = -EEXIST;
-	else
-		qeth_l3_add_ip(card, ipaddr);
-
+	rc = qeth_l3_add_ip(card, ipaddr);
 	spin_unlock_bh(&card->ip_lock);
 
 	kfree(ipaddr);
@@ -1396,8 +1385,9 @@ qeth_l3_add_mc_to_hash(struct qeth_card *card, struct in_device *in4_dev)
 		memcpy(tmp->mac, buf, sizeof(tmp->mac));
 		tmp->is_multicast = 1;
 
-		ipm = qeth_l3_ip_from_hash(card, tmp);
+		ipm = qeth_l3_find_addr_by_ip(card, tmp);
 		if (ipm) {
+			/* for mcast, by-IP match means full match */
 			ipm->disp_flag = QETH_DISP_ADDR_DO_NOTHING;
 		} else {
 			ipm = qeth_l3_get_addr_buffer(QETH_PROT_IPV4);
@@ -1480,8 +1470,9 @@ qeth_l3_add_mc6_to_hash(struct qeth_card *card, struct inet6_dev *in6_dev)
 		       sizeof(struct in6_addr));
 		tmp->is_multicast = 1;
 
-		ipm = qeth_l3_ip_from_hash(card, tmp);
+		ipm = qeth_l3_find_addr_by_ip(card, tmp);
 		if (ipm) {
+			/* for mcast, by-IP match means full match */
 			ipm->disp_flag = QETH_DISP_ADDR_DO_NOTHING;
 			continue;
 		}
-- 
2.14.3


From 130409af7cfb0773163e0b3fa5551db0974ac63b Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Tue, 27 Feb 2018 18:58:17 +0100
Subject: [PATCH 59/59] s390/qeth: fix IPA command submission race

[ Upstream commit d22ffb5a712f9211ffd104c38fc17cbfb1b5e2b0 ]

If multiple IPA commands are build & sent out concurrently,
fill_ipacmd_header() may assign a seqno value to a command that's
different from what send_control_data() later assigns to this command's
reply.
This is due to other commands passing through send_control_data(),
and incrementing card->seqno.ipa along the way.

So one IPA command has no reply that's waiting for its seqno, while some
other IPA command has multiple reply objects waiting for it.
Only one of those waiting replies wins, and the other(s) times out and
triggers a recovery via send_ipa_cmd().

Fix this by making sure that the same seqno value is assigned to
a command and its reply object.
Do so immediately before submitting the command & while holding the
irq_pending "lock", to produce nicely ascending seqnos.

As a side effect, *all* IPA commands now use a reply object that's
waiting for its actual seqno. Previously, early IPA commands that were
submitted while the card was still DOWN used the "catch-all" IDX seqno.

Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index c9b632e8ab5e..61e9d0bca197 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -2071,24 +2071,25 @@ int qeth_send_control_data(struct qeth_card *card, int len,
 	}
 	reply->callback = reply_cb;
 	reply->param = reply_param;
-	if (card->state == CARD_STATE_DOWN)
-		reply->seqno = QETH_IDX_COMMAND_SEQNO;
-	else
-		reply->seqno = card->seqno.ipa++;
+
 	init_waitqueue_head(&reply->wait_q);
-	spin_lock_irqsave(&card->lock, flags);
-	list_add_tail(&reply->list, &card->cmd_waiter_list);
-	spin_unlock_irqrestore(&card->lock, flags);
 
 	while (atomic_cmpxchg(&card->write.irq_pending, 0, 1)) ;
-	qeth_prepare_control_data(card, len, iob);
 
 	if (IS_IPA(iob->data)) {
 		cmd = __ipa_cmd(iob);
+		cmd->hdr.seqno = card->seqno.ipa++;
+		reply->seqno = cmd->hdr.seqno;
 		event_timeout = QETH_IPA_TIMEOUT;
 	} else {
+		reply->seqno = QETH_IDX_COMMAND_SEQNO;
 		event_timeout = QETH_TIMEOUT;
 	}
+	qeth_prepare_control_data(card, len, iob);
+
+	spin_lock_irqsave(&card->lock, flags);
+	list_add_tail(&reply->list, &card->cmd_waiter_list);
+	spin_unlock_irqrestore(&card->lock, flags);
 
 	timeout = jiffies + event_timeout;
 
@@ -2870,7 +2871,7 @@ static void qeth_fill_ipacmd_header(struct qeth_card *card,
 	memset(cmd, 0, sizeof(struct qeth_ipa_cmd));
 	cmd->hdr.command = command;
 	cmd->hdr.initiator = IPA_CMD_INITIATOR_HOST;
-	cmd->hdr.seqno = card->seqno.ipa;
+	/* cmd->hdr.seqno is set by qeth_send_control_data() */
 	cmd->hdr.adapter_type = qeth_get_ipa_adp_type(card->info.link_type);
 	cmd->hdr.rel_adapter_no = (__u8) card->info.portno;
 	if (card->options.layer2)
-- 
2.14.3

Re: [PATCHES] Networking

[Greg KH]

On Tue, Mar 06, 2018 at 09:28:33PM -0500, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.14 and
> v4.15 -stable, respectively.

Many thanks for these, all now queued up.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 108 bytes --]


Please queue up the following networking bug fixes for v4.14 and v4.15
-stable, respecetively.

Thank you!

[-- Attachment #2: net_414.mbox --]
[-- Type: Application/Octet-Stream, Size: 105642 bytes --]

From 891dcea0c2cd02504f9ce8d27db286366f439fc1 Mon Sep 17 00:00:00 2001
From: Soheil Hassas Yeganeh <soheil@google.com>
Date: Thu, 15 Mar 2018 12:09:13 -0400
Subject: [PATCH 01/43] tcp: reset sk_send_head in tcp_write_queue_purge

tcp_write_queue_purge clears all the SKBs in the write queue
but does not reset the sk_send_head. As a result, we can have
a NULL pointer dereference anywhere that we use tcp_send_head
instead of the tcp_write_queue_tail.

For example, after 27fid7a8ed38 (tcp: purge write queue upon RST),
we can purge the write queue on RST. Prior to
75c119afe14f (tcp: implement rb-tree based retransmit queue),
tcp_push will only check tcp_send_head and then accesses
tcp_write_queue_tail to send the actual SKB. As a result, it will
dereference a NULL pointer.

This has been reported twice for 4.14 where we don't have
75c119afe14f:

By Timofey Titovets:

[  422.081094] BUG: unable to handle kernel NULL pointer dereference
at 0000000000000038
[  422.081254] IP: tcp_push+0x42/0x110
[  422.081314] PGD 0 P4D 0
[  422.081364] Oops: 0002 [#1] SMP PTI

By Yongjian Xu:

BUG: unable to handle kernel NULL pointer dereference at 0000000000000038
IP: tcp_push+0x48/0x120
PGD 80000007ff77b067 P4D 80000007ff77b067 PUD 7fd989067 PMD 0
Oops: 0002 [#18] SMP PTI
Modules linked in: tcp_diag inet_diag tcp_bbr sch_fq iTCO_wdt
iTCO_vendor_support pcspkr ixgbe mdio i2c_i801 lpc_ich joydev input_leds shpchp
e1000e igb dca ptp pps_core hwmon mei_me mei ipmi_si ipmi_msghandler sg ses
scsi_transport_sas enclosure ext4 jbd2 mbcache sd_mod ahci libahci megaraid_sas
wmi ast ttm dm_mirror dm_region_hash dm_log dm_mod dax
CPU: 6 PID: 14156 Comm: [ET_NET 6] Tainted: G D 4.14.26-1.el6.x86_64 #1
Hardware name: LENOVO ThinkServer RD440 /ThinkServer RD440, BIOS A0TS80A
09/22/2014
task: ffff8807d78d8140 task.stack: ffffc9000e944000
RIP: 0010:tcp_push+0x48/0x120
RSP: 0018:ffffc9000e947a88 EFLAGS: 00010246
RAX: 00000000000005b4 RBX: ffff880f7cce9c00 RCX: 0000000000000000
RDX: 0000000000000000 RSI: 0000000000000040 RDI: ffff8807d00f5000
RBP: ffffc9000e947aa8 R08: 0000000000001c84 R09: 0000000000000000
R10: ffff8807d00f5158 R11: 0000000000000000 R12: ffff8807d00f5000
R13: 0000000000000020 R14: 00000000000256d4 R15: 0000000000000000
FS: 00007f5916de9700(0000) GS:ffff88107fd00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000038 CR3: 00000007f8226004 CR4: 00000000001606e0
Call Trace:
tcp_sendmsg_locked+0x33d/0xe50
tcp_sendmsg+0x37/0x60
inet_sendmsg+0x39/0xc0
sock_sendmsg+0x49/0x60
sock_write_iter+0xb6/0x100
do_iter_readv_writev+0xec/0x130
? rw_verify_area+0x49/0xb0
do_iter_write+0x97/0xd0
vfs_writev+0x7e/0xe0
? __wake_up_common_lock+0x80/0xa0
? __fget_light+0x2c/0x70
? __do_page_fault+0x1e7/0x530
do_writev+0x60/0xf0
? inet_shutdown+0xac/0x110
SyS_writev+0x10/0x20
do_syscall_64+0x6f/0x140
? prepare_exit_to_usermode+0x8b/0xa0
entry_SYSCALL_64_after_hwframe+0x3d/0xa2
RIP: 0033:0x3135ce0c57
RSP: 002b:00007f5916de4b00 EFLAGS: 00000293 ORIG_RAX: 0000000000000014
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 0000003135ce0c57
RDX: 0000000000000002 RSI: 00007f5916de4b90 RDI: 000000000000606f
RBP: 0000000000000000 R08: 0000000000000000 R09: 00007f5916de8c38
R10: 0000000000000000 R11: 0000000000000293 R12: 00000000000464cc
R13: 00007f5916de8c30 R14: 00007f58d8bef080 R15: 0000000000000002
Code: 48 8b 97 60 01 00 00 4c 8d 97 58 01 00 00 41 b9 00 00 00 00 41 89 f3 4c 39
d2 49 0f 44 d1 41 81 e3 00 80 00 00 0f 85 b0 00 00 00 <80> 4a 38 08 44 8b 8f 74
06 00 00 44 89 8f 7c 06 00 00 83 e6 01
RIP: tcp_push+0x48/0x120 RSP: ffffc9000e947a88
CR2: 0000000000000038
---[ end trace 8d545c2e93515549 ]---

Fixes: a27fid7a8ed38 (tcp: purge write queue upon RST)
Reported-by: Timofey Titovets <nefelim4ag@gmail.com>
Reported-by: Yongjian Xu <yongjianchn@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Tested-by: Yongjian Xu <yongjianchn@gmail.com>

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 0a13574134b8..d323d4fa742c 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1600,6 +1600,11 @@ enum tcp_chrono {
 void tcp_chrono_start(struct sock *sk, const enum tcp_chrono type);
 void tcp_chrono_stop(struct sock *sk, const enum tcp_chrono type);
 
+static inline void tcp_init_send_head(struct sock *sk)
+{
+	sk->sk_send_head = NULL;
+}
+
 /* write queue abstraction */
 static inline void tcp_write_queue_purge(struct sock *sk)
 {
@@ -1610,6 +1615,7 @@ static inline void tcp_write_queue_purge(struct sock *sk)
 		sk_wmem_free_skb(sk, skb);
 	sk_mem_reclaim(sk);
 	tcp_clear_all_retrans_hints(tcp_sk(sk));
+	tcp_init_send_head(sk);
 }
 
 static inline struct sk_buff *tcp_write_queue_head(const struct sock *sk)
@@ -1672,11 +1678,6 @@ static inline void tcp_check_send_head(struct sock *sk, struct sk_buff *skb_unli
 		tcp_sk(sk)->highest_sack = NULL;
 }
 
-static inline void tcp_init_send_head(struct sock *sk)
-{
-	sk->sk_send_head = NULL;
-}
-
 static inline void __tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb)
 {
 	__skb_queue_tail(&sk->sk_write_queue, skb);
-- 
2.14.3


From 86d5523a09c606a28985a1bb565c74a2e26b07e9 Mon Sep 17 00:00:00 2001
From: Soheil Hassas Yeganeh <soheil@google.com>
Date: Tue, 6 Mar 2018 17:15:12 -0500
Subject: [PATCH 02/43] tcp: purge write queue upon aborting the connection

[ Upstream commit e05836ac07c77dd90377f8c8140bce2a44af5fe7 ]

When the connection is aborted, there is no point in
keeping the packets on the write queue until the connection
is closed.

Similar to a27fd7a8ed38 ('tcp: purge write queue upon RST'),
this is essential for a correct MSG_ZEROCOPY implementation,
because userspace cannot call close(fd) before receiving
zerocopy signals even when the connection is aborted.

Fixes: f214f915e7db ("tcp: enable MSG_ZEROCOPY")
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c       | 1 +
 net/ipv4/tcp_timer.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index fe11128d7df4..38b9a6276a9d 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3445,6 +3445,7 @@ int tcp_abort(struct sock *sk, int err)
 
 	bh_unlock_sock(sk);
 	local_bh_enable();
+	tcp_write_queue_purge(sk);
 	release_sock(sk);
 	return 0;
 }
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 14ac7df95380..a845b7692c1b 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -36,6 +36,7 @@ static void tcp_write_err(struct sock *sk)
 	sk->sk_err = sk->sk_err_soft ? : ETIMEDOUT;
 	sk->sk_error_report(sk);
 
+	tcp_write_queue_purge(sk);
 	tcp_done(sk);
 	__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONTIMEOUT);
 }
-- 
2.14.3


From a1960b8fc38963d9c21906e58b621bd1982fd811 Mon Sep 17 00:00:00 2001
From: Michal Kalderon <Michal.Kalderon@cavium.com>
Date: Wed, 14 Mar 2018 14:49:28 +0200
Subject: [PATCH 03/43] qed: Fix non TCP packets should be dropped on iWARP ll2
 connection

[ Upstream commit 16da09047d3fb991dc48af41f6d255fd578e8ca2 ]

FW workaround. The iWARP LL2 connection did not expect TCP packets
to arrive on it's connection. The fix drops any non-tcp packets

Fixes b5c29ca ("qed: iWARP CM - setup a ll2 connection for handling
SYN packets")

Signed-off-by: Michal Kalderon <Michal.Kalderon@cavium.com>
Signed-off-by: Ariel Elior <Ariel.Elior@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_iwarp.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
index 9d989c96278c..e41f28602535 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
@@ -1663,6 +1663,13 @@ qed_iwarp_parse_rx_pkt(struct qed_hwfn *p_hwfn,
 	iph = (struct iphdr *)((u8 *)(ethh) + eth_hlen);
 
 	if (eth_type == ETH_P_IP) {
+		if (iph->protocol != IPPROTO_TCP) {
+			DP_NOTICE(p_hwfn,
+				  "Unexpected ip protocol on ll2 %x\n",
+				  iph->protocol);
+			return -EINVAL;
+		}
+
 		cm_info->local_ip[0] = ntohl(iph->daddr);
 		cm_info->remote_ip[0] = ntohl(iph->saddr);
 		cm_info->ip_version = TCP_IPV4;
@@ -1671,6 +1678,14 @@ qed_iwarp_parse_rx_pkt(struct qed_hwfn *p_hwfn,
 		*payload_len = ntohs(iph->tot_len) - ip_hlen;
 	} else if (eth_type == ETH_P_IPV6) {
 		ip6h = (struct ipv6hdr *)iph;
+
+		if (ip6h->nexthdr != IPPROTO_TCP) {
+			DP_NOTICE(p_hwfn,
+				  "Unexpected ip protocol on ll2 %x\n",
+				  iph->protocol);
+			return -EINVAL;
+		}
+
 		for (i = 0; i < 4; i++) {
 			cm_info->local_ip[i] =
 			    ntohl(ip6h->daddr.in6_u.u6_addr32[i]);
-- 
2.14.3


From 755b58ef2c430a91ed9d29068e03f1c5c9edb37a Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Fri, 16 Mar 2018 17:08:34 -0500
Subject: [PATCH 04/43] sysfs: symlink: export sysfs_create_link_nowarn()

[ Upstream commit 2399ac42e762ab25c58420e25359b2921afdc55f ]

The sysfs_create_link_nowarn() is going to be used in phylib framework in
subsequent patch which can be built as module. Hence, export
sysfs_create_link_nowarn() to avoid build errors.

Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: Andrew Lunn <andrew@lunn.ch>
Fixes: a3995460491d ("net: phy: Relax error checking on sysfs_create_link()")
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 fs/sysfs/symlink.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/sysfs/symlink.c b/fs/sysfs/symlink.c
index aecb15f84557..808f018fa976 100644
--- a/fs/sysfs/symlink.c
+++ b/fs/sysfs/symlink.c
@@ -107,6 +107,7 @@ int sysfs_create_link_nowarn(struct kobject *kobj, struct kobject *target,
 {
 	return sysfs_do_create_link(kobj, target, name, 0);
 }
+EXPORT_SYMBOL_GPL(sysfs_create_link_nowarn);
 
 /**
  *	sysfs_delete_link - remove symlink in object's directory.
-- 
2.14.3


From 90d8b025f56f6847987e1fffe764b56042699193 Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Fri, 16 Mar 2018 17:08:35 -0500
Subject: [PATCH 05/43] net: phy: relax error checking when creating sysfs link
 netdev->phydev

[ Upstream commit 4414b3ed74be0e205e04e12cd83542a727d88255 ]

Some ethernet drivers (like TI CPSW) may connect and manage >1 Net PHYs per
one netdevice, as result such drivers will produce warning during system
boot and fail to connect second phy to netdevice when PHYLIB framework
will try to create sysfs link netdev->phydev for second PHY
in phy_attach_direct(), because sysfs link with the same name has been
created already for the first PHY. As result, second CPSW external
port will became unusable.

Fix it by relaxing error checking when PHYLIB framework is creating sysfs
link netdev->phydev in phy_attach_direct(), suppressing warning by using
sysfs_create_link_nowarn() and adding error message instead.
After this change links (phy->netdev and netdev->phy) creation failure is not
fatal any more and system can continue working, which fixes TI CPSW issue.

Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: Andrew Lunn <andrew@lunn.ch>
Fixes: a3995460491d ("net: phy: Relax error checking on sysfs_create_link()")
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index d312b314825e..a1e7ea4d4b16 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -999,10 +999,17 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
 	err = sysfs_create_link(&phydev->mdio.dev.kobj, &dev->dev.kobj,
 				"attached_dev");
 	if (!err) {
-		err = sysfs_create_link(&dev->dev.kobj, &phydev->mdio.dev.kobj,
-					"phydev");
-		if (err)
-			goto error;
+		err = sysfs_create_link_nowarn(&dev->dev.kobj,
+					       &phydev->mdio.dev.kobj,
+					       "phydev");
+		if (err) {
+			dev_err(&dev->dev, "could not add device link to %s err %d\n",
+				kobject_name(&phydev->mdio.dev.kobj),
+				err);
+			/* non-fatal - some net drivers can use one netdevice
+			 * with more then one phy
+			 */
+		}
 
 		phydev->sysfs_links = true;
 	}
-- 
2.14.3


From 11a2dbd483711b8c0bbd2993f540ecbabe9e6164 Mon Sep 17 00:00:00 2001
From: Arkadi Sharshevsky <arkadis@mellanox.com>
Date: Sun, 18 Mar 2018 17:37:22 +0200
Subject: [PATCH 06/43] devlink: Remove redundant free on error path

[ Upstream commit 7fe4d6dcbcb43fe0282d4213fc52be178bb30e91 ]

The current code performs unneeded free. Remove the redundant skb freeing
during the error path.

Fixes: 1555d204e743 ("devlink: Support for pipeline debug (dpipe)")
Signed-off-by: Arkadi Sharshevsky <arkadis@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/devlink.c | 16 ++++------------
 1 file changed, 4 insertions(+), 12 deletions(-)

diff --git a/net/core/devlink.c b/net/core/devlink.c
index 7d430c1d9c3e..5ba973311025 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -1776,7 +1776,7 @@ static int devlink_dpipe_tables_fill(struct genl_info *info,
 	if (!nlh) {
 		err = devlink_dpipe_send_and_alloc_skb(&skb, info);
 		if (err)
-			goto err_skb_send_alloc;
+			return err;
 		goto send_done;
 	}
 
@@ -1785,7 +1785,6 @@ static int devlink_dpipe_tables_fill(struct genl_info *info,
 nla_put_failure:
 	err = -EMSGSIZE;
 err_table_put:
-err_skb_send_alloc:
 	genlmsg_cancel(skb, hdr);
 	nlmsg_free(skb);
 	return err;
@@ -2051,7 +2050,7 @@ static int devlink_dpipe_entries_fill(struct genl_info *info,
 					     table->counters_enabled,
 					     &dump_ctx);
 	if (err)
-		goto err_entries_dump;
+		return err;
 
 send_done:
 	nlh = nlmsg_put(dump_ctx.skb, info->snd_portid, info->snd_seq,
@@ -2059,16 +2058,10 @@ static int devlink_dpipe_entries_fill(struct genl_info *info,
 	if (!nlh) {
 		err = devlink_dpipe_send_and_alloc_skb(&dump_ctx.skb, info);
 		if (err)
-			goto err_skb_send_alloc;
+			return err;
 		goto send_done;
 	}
 	return genlmsg_reply(dump_ctx.skb, info);
-
-err_entries_dump:
-err_skb_send_alloc:
-	genlmsg_cancel(dump_ctx.skb, dump_ctx.hdr);
-	nlmsg_free(dump_ctx.skb);
-	return err;
 }
 
 static int devlink_nl_cmd_dpipe_entries_get(struct sk_buff *skb,
@@ -2207,7 +2200,7 @@ static int devlink_dpipe_headers_fill(struct genl_info *info,
 	if (!nlh) {
 		err = devlink_dpipe_send_and_alloc_skb(&skb, info);
 		if (err)
-			goto err_skb_send_alloc;
+			return err;
 		goto send_done;
 	}
 	return genlmsg_reply(skb, info);
@@ -2215,7 +2208,6 @@ static int devlink_dpipe_headers_fill(struct genl_info *info,
 nla_put_failure:
 	err = -EMSGSIZE;
 err_table_put:
-err_skb_send_alloc:
 	genlmsg_cancel(skb, hdr);
 	nlmsg_free(skb);
 	return err;
-- 
2.14.3


From a6de1b913fb21f950d866494bf66bee00250a786 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@oracle.com>
Date: Thu, 8 Mar 2018 16:17:23 -0800
Subject: [PATCH 07/43] macvlan: filter out unsupported feature flags

[ Upstream commit 13fbcc8dc573482dd3f27568257fd7087f8935f4 ]

Adding a macvlan device on top of a lowerdev that supports
the xfrm offloads fails with a new regression:
  # ip link add link ens1f0 mv0 type macvlan
  RTNETLINK answers: Operation not permitted

Tracing down the failure shows that the macvlan device inherits
the NETIF_F_HW_ESP and NETIF_F_HW_ESP_TX_CSUM feature flags
from the lowerdev, but with no dev->xfrmdev_ops API filled
in, it doesn't actually support xfrm.  When the request is
made to add the new macvlan device, the XFRM listener for
NETDEV_REGISTER calls xfrm_api_check() which fails the new
registration because dev->xfrmdev_ops is NULL.

The macvlan creation succeeds when we filter out the ESP
feature flags in macvlan_fix_features(), so let's filter them
out like we're already filtering out ~NETIF_F_NETNS_LOCAL.
When XFRM support is added in the future, we can add the flags
into MACVLAN_FEATURES.

This same problem could crop up in the future with any other
new feature flags, so let's filter out any flags that aren't
defined as supported in macvlan.

Fixes: d77e38e612a0 ("xfrm: Add an IPsec hardware offloading API")
Reported-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Signed-off-by: Shannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macvlan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 176fc0906bfe..0f35597553f4 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -1037,7 +1037,7 @@ static netdev_features_t macvlan_fix_features(struct net_device *dev,
 	lowerdev_features &= (features | ~NETIF_F_LRO);
 	features = netdev_increment_features(lowerdev_features, features, mask);
 	features |= ALWAYS_ON_FEATURES;
-	features &= ~NETIF_F_NETNS_LOCAL;
+	features &= (ALWAYS_ON_FEATURES | MACVLAN_FEATURES);
 
 	return features;
 }
-- 
2.14.3


From a14d306e62866462bdd0d595ef74e9449e3cfefb Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 12 Mar 2018 14:54:23 +0100
Subject: [PATCH 08/43] net: ipv6: keep sk status consistent after datagram
 connect failure

[ Upstream commit 2f987a76a97773beafbc615b9c4d8fe79129a7f4 ]

On unsuccesful ip6_datagram_connect(), if the failure is caused by
ip6_datagram_dst_update(), the sk peer information are cleared, but
the sk->sk_state is preserved.

If the socket was already in an established status, the overall sk
status is inconsistent and fouls later checks in datagram code.

Fix this saving the old peer information and restoring them in
case of failure. This also aligns ipv6 datagram connect() behavior
with ipv4.

v1 -> v2:
 - added missing Fixes tag

Fixes: 85cb73ff9b74 ("net: ipv6: reset daddr and dport in sk if connect() fails")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/datagram.c | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index a1f918713006..29da4b6c9dd6 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -146,10 +146,12 @@ int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr,
 	struct sockaddr_in6	*usin = (struct sockaddr_in6 *) uaddr;
 	struct inet_sock	*inet = inet_sk(sk);
 	struct ipv6_pinfo	*np = inet6_sk(sk);
-	struct in6_addr		*daddr;
+	struct in6_addr		*daddr, old_daddr;
+	__be32			fl6_flowlabel = 0;
+	__be32			old_fl6_flowlabel;
+	__be32			old_dport;
 	int			addr_type;
 	int			err;
-	__be32			fl6_flowlabel = 0;
 
 	if (usin->sin6_family == AF_INET) {
 		if (__ipv6_only_sock(sk))
@@ -239,9 +241,13 @@ int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr,
 		}
 	}
 
+	/* save the current peer information before updating it */
+	old_daddr = sk->sk_v6_daddr;
+	old_fl6_flowlabel = np->flow_label;
+	old_dport = inet->inet_dport;
+
 	sk->sk_v6_daddr = *daddr;
 	np->flow_label = fl6_flowlabel;
-
 	inet->inet_dport = usin->sin6_port;
 
 	/*
@@ -251,11 +257,12 @@ int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr,
 
 	err = ip6_datagram_dst_update(sk, true);
 	if (err) {
-		/* Reset daddr and dport so that udp_v6_early_demux()
-		 * fails to find this socket
+		/* Restore the socket peer info, to keep it consistent with
+		 * the old socket state
 		 */
-		memset(&sk->sk_v6_daddr, 0, sizeof(sk->sk_v6_daddr));
-		inet->inet_dport = 0;
+		sk->sk_v6_daddr = old_daddr;
+		np->flow_label = old_fl6_flowlabel;
+		inet->inet_dport = old_dport;
 		goto out;
 	}
 
-- 
2.14.3


From d206acff5c20b20e5b317b67fde7557a6405e2d5 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Mon, 19 Mar 2018 11:24:58 +0100
Subject: [PATCH 09/43] ipv6: old_dport should be a __be16 in
 __ip6_datagram_connect()

[ Upstream commit 5f2fb802eee1df0810b47ea251942fe3fd36589a ]

Fixes: 2f987a76a977 ("net: ipv6: keep sk status consistent after datagram connect failure")
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/datagram.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 29da4b6c9dd6..287112da3c06 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -149,7 +149,7 @@ int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr,
 	struct in6_addr		*daddr, old_daddr;
 	__be32			fl6_flowlabel = 0;
 	__be32			old_fl6_flowlabel;
-	__be32			old_dport;
+	__be16			old_dport;
 	int			addr_type;
 	int			err;
 
-- 
2.14.3


From 95fbfc2cb2899cd7fbe9f7b53d104855da3bedb4 Mon Sep 17 00:00:00 2001
From: David Lebrun <dlebrun@google.com>
Date: Tue, 20 Mar 2018 14:44:56 +0000
Subject: [PATCH 10/43] ipv6: sr: fix NULL pointer dereference when setting
 encap source address

[ Upstream commit 8936ef7604c11b5d701580d779e0f5684abc7b68 ]

When using seg6 in encap mode, we call ipv6_dev_get_saddr() to set the
source address of the outer IPv6 header, in case none was specified.
Using skb->dev can lead to BUG() when it is in an inconsistent state.
This patch uses the net_device attached to the skb's dst instead.

[940807.667429] BUG: unable to handle kernel NULL pointer dereference at 000000000000047c
[940807.762427] IP: ipv6_dev_get_saddr+0x8b/0x1d0
[940807.815725] PGD 0 P4D 0
[940807.847173] Oops: 0000 [#1] SMP PTI
[940807.890073] Modules linked in:
[940807.927765] CPU: 6 PID: 0 Comm: swapper/6 Tainted: G        W        4.16.0-rc1-seg6bpf+ #2
[940808.028988] Hardware name: HP ProLiant DL120 G6/ProLiant DL120 G6, BIOS O26    09/06/2010
[940808.128128] RIP: 0010:ipv6_dev_get_saddr+0x8b/0x1d0
[940808.187667] RSP: 0018:ffff88043fd836b0 EFLAGS: 00010206
[940808.251366] RAX: 0000000000000005 RBX: ffff88042cb1c860 RCX: 00000000000000fe
[940808.338025] RDX: 00000000000002c0 RSI: ffff88042cb1c860 RDI: 0000000000004500
[940808.424683] RBP: ffff88043fd83740 R08: 0000000000000000 R09: ffffffffffffffff
[940808.511342] R10: 0000000000000040 R11: 0000000000000000 R12: ffff88042cb1c850
[940808.598012] R13: ffffffff8208e380 R14: ffff88042ac8da00 R15: 0000000000000002
[940808.684675] FS:  0000000000000000(0000) GS:ffff88043fd80000(0000) knlGS:0000000000000000
[940808.783036] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[940808.852975] CR2: 000000000000047c CR3: 00000004255fe000 CR4: 00000000000006e0
[940808.939634] Call Trace:
[940808.970041]  <IRQ>
[940808.995250]  ? ip6t_do_table+0x265/0x640
[940809.043341]  seg6_do_srh_encap+0x28f/0x300
[940809.093516]  ? seg6_do_srh+0x1a0/0x210
[940809.139528]  seg6_do_srh+0x1a0/0x210
[940809.183462]  seg6_output+0x28/0x1e0
[940809.226358]  lwtunnel_output+0x3f/0x70
[940809.272370]  ip6_xmit+0x2b8/0x530
[940809.313185]  ? ac6_proc_exit+0x20/0x20
[940809.359197]  inet6_csk_xmit+0x7d/0xc0
[940809.404173]  tcp_transmit_skb+0x548/0x9a0
[940809.453304]  __tcp_retransmit_skb+0x1a8/0x7a0
[940809.506603]  ? ip6_default_advmss+0x40/0x40
[940809.557824]  ? tcp_current_mss+0x24/0x90
[940809.605925]  tcp_retransmit_skb+0xd/0x80
[940809.654016]  tcp_xmit_retransmit_queue.part.17+0xf9/0x210
[940809.719797]  tcp_ack+0xa47/0x1110
[940809.760612]  tcp_rcv_established+0x13c/0x570
[940809.812865]  tcp_v6_do_rcv+0x151/0x3d0
[940809.858879]  tcp_v6_rcv+0xa5c/0xb10
[940809.901770]  ? seg6_output+0xdd/0x1e0
[940809.946745]  ip6_input_finish+0xbb/0x460
[940809.994837]  ip6_input+0x74/0x80
[940810.034612]  ? ip6_rcv_finish+0xb0/0xb0
[940810.081663]  ipv6_rcv+0x31c/0x4c0
...

Fixes: 6c8702c60b886 ("ipv6: sr: add support for SRH encapsulation and injection with lwtunnels")
Reported-by: Tom Herbert <tom@quantonium.net>
Signed-off-by: David Lebrun <dlebrun@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/seg6_iptunnel.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index bd6cc688bd19..37e76ca7b7cb 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -93,7 +93,8 @@ static void set_tun_src(struct net *net, struct net_device *dev,
 /* encapsulate an IPv6 packet within an outer IPv6 header with a given SRH */
 int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
 {
-	struct net *net = dev_net(skb_dst(skb)->dev);
+	struct dst_entry *dst = skb_dst(skb);
+	struct net *net = dev_net(dst->dev);
 	struct ipv6hdr *hdr, *inner_hdr;
 	struct ipv6_sr_hdr *isrh;
 	int hdrlen, tot_len, err;
@@ -134,7 +135,7 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
 	isrh->nexthdr = proto;
 
 	hdr->daddr = isrh->segments[isrh->first_segment];
-	set_tun_src(net, skb->dev, &hdr->daddr, &hdr->saddr);
+	set_tun_src(net, ip6_dst_idev(dst)->dev, &hdr->daddr, &hdr->saddr);
 
 #ifdef CONFIG_IPV6_SEG6_HMAC
 	if (sr_has_hmac(isrh)) {
-- 
2.14.3


From 9eede1d2c89e7543bfd2a8f27fe3dc79e39d932f Mon Sep 17 00:00:00 2001
From: David Lebrun <dlebrun@google.com>
Date: Tue, 20 Mar 2018 14:44:55 +0000
Subject: [PATCH 11/43] ipv6: sr: fix scheduling in RCU when creating seg6
 lwtunnel state

[ Upstream commit 191f86ca8ef27f7a492fd1c03620498c6e94f0ac ]

The seg6_build_state() function is called with RCU read lock held,
so we cannot use GFP_KERNEL. This patch uses GFP_ATOMIC instead.

[   92.770271] =============================
[   92.770628] WARNING: suspicious RCU usage
[   92.770921] 4.16.0-rc4+ #12 Not tainted
[   92.771277] -----------------------------
[   92.771585] ./include/linux/rcupdate.h:302 Illegal context switch in RCU read-side critical section!
[   92.772279]
[   92.772279] other info that might help us debug this:
[   92.772279]
[   92.773067]
[   92.773067] rcu_scheduler_active = 2, debug_locks = 1
[   92.773514] 2 locks held by ip/2413:
[   92.773765]  #0:  (rtnl_mutex){+.+.}, at: [<00000000e5461720>] rtnetlink_rcv_msg+0x441/0x4d0
[   92.774377]  #1:  (rcu_read_lock){....}, at: [<00000000df4f161e>] lwtunnel_build_state+0x59/0x210
[   92.775065]
[   92.775065] stack backtrace:
[   92.775371] CPU: 0 PID: 2413 Comm: ip Not tainted 4.16.0-rc4+ #12
[   92.775791] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1.fc27 04/01/2014
[   92.776608] Call Trace:
[   92.776852]  dump_stack+0x7d/0xbc
[   92.777130]  __schedule+0x133/0xf00
[   92.777393]  ? unwind_get_return_address_ptr+0x50/0x50
[   92.777783]  ? __sched_text_start+0x8/0x8
[   92.778073]  ? rcu_is_watching+0x19/0x30
[   92.778383]  ? kernel_text_address+0x49/0x60
[   92.778800]  ? __kernel_text_address+0x9/0x30
[   92.779241]  ? unwind_get_return_address+0x29/0x40
[   92.779727]  ? pcpu_alloc+0x102/0x8f0
[   92.780101]  _cond_resched+0x23/0x50
[   92.780459]  __mutex_lock+0xbd/0xad0
[   92.780818]  ? pcpu_alloc+0x102/0x8f0
[   92.781194]  ? seg6_build_state+0x11d/0x240
[   92.781611]  ? save_stack+0x9b/0xb0
[   92.781965]  ? __ww_mutex_wakeup_for_backoff+0xf0/0xf0
[   92.782480]  ? seg6_build_state+0x11d/0x240
[   92.782925]  ? lwtunnel_build_state+0x1bd/0x210
[   92.783393]  ? ip6_route_info_create+0x687/0x1640
[   92.783846]  ? ip6_route_add+0x74/0x110
[   92.784236]  ? inet6_rtm_newroute+0x8a/0xd0

Fixes: 6c8702c60b886 ("ipv6: sr: add support for SRH encapsulation and injection with lwtunnels")
Signed-off-by: David Lebrun <dlebrun@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/seg6_iptunnel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 37e76ca7b7cb..7a78dcfda68a 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -419,7 +419,7 @@ static int seg6_build_state(struct nlattr *nla,
 
 	slwt = seg6_lwt_lwtunnel(newts);
 
-	err = dst_cache_init(&slwt->cache, GFP_KERNEL);
+	err = dst_cache_init(&slwt->cache, GFP_ATOMIC);
 	if (err) {
 		kfree(newts);
 		return err;
-- 
2.14.3


From 2532fc025304d5bb4b21cd5da10ecbb8ed46fb91 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Thu, 15 Mar 2018 14:49:56 +0200
Subject: [PATCH 12/43] mlxsw: spectrum_buffers: Set a minimum quota for CPU
 port traffic

[ Upstream commit bcdd5de80a2275f7879dc278bfc747f1caf94442 ]

In commit 9ffcc3725f09 ("mlxsw: spectrum: Allow packets to be trapped
from any PG") I fixed a problem where packets could not be trapped to
the CPU due to exceeded shared buffer quotas. The mentioned commit
explains the problem in detail.

The problem was fixed by assigning a minimum quota for the CPU port and
the traffic class used for scheduling traffic to the CPU.

However, commit 117b0dad2d54 ("mlxsw: Create a different trap group list
for each device") assigned different traffic classes to different
packet types and rendered the fix useless.

Fix the problem by assigning a minimum quota for the CPU port and all
the traffic classes that are currently in use.

Fixes: 117b0dad2d54 ("mlxsw: Create a different trap group list for each device")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Eddie Shklaer <eddies@mellanox.com>
Tested-by: Eddie Shklaer <eddies@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
index 93728c694e6d..0a9adc5962fb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
@@ -385,13 +385,13 @@ static const struct mlxsw_sp_sb_cm mlxsw_sp_sb_cms_egress[] = {
 
 static const struct mlxsw_sp_sb_cm mlxsw_sp_cpu_port_sb_cms[] = {
 	MLXSW_SP_CPU_PORT_SB_CM,
+	MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 0),
+	MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 0),
+	MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 0),
+	MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 0),
+	MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 0),
 	MLXSW_SP_CPU_PORT_SB_CM,
-	MLXSW_SP_CPU_PORT_SB_CM,
-	MLXSW_SP_CPU_PORT_SB_CM,
-	MLXSW_SP_CPU_PORT_SB_CM,
-	MLXSW_SP_CPU_PORT_SB_CM,
-	MLXSW_SP_CPU_PORT_SB_CM,
-	MLXSW_SP_SB_CM(10000, 0, 0),
+	MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 0),
 	MLXSW_SP_CPU_PORT_SB_CM,
 	MLXSW_SP_CPU_PORT_SB_CM,
 	MLXSW_SP_CPU_PORT_SB_CM,
-- 
2.14.3


From b5b1aefadb26ccc5eb85c4a9985a3497b38d92e2 Mon Sep 17 00:00:00 2001
From: Brad Mouring <brad.mouring@ni.com>
Date: Thu, 8 Mar 2018 16:23:03 -0600
Subject: [PATCH 13/43] net: phy: Tell caller result of phy_change()

[ Upstream commit a2c054a896b8ac794ddcfc7c92e2dc7ec4ed4ed5 ]

In 664fcf123a30e (net: phy: Threaded interrupts allow some simplification)
the phy_interrupt system was changed to use a traditional threaded
interrupt scheme instead of a workqueue approach.

With this change, the phy status check moved into phy_change, which
did not report back to the caller whether or not the interrupt was
handled. This means that, in the case of a shared phy interrupt,
only the first phydev's interrupt registers are checked (since
phy_interrupt() would always return IRQ_HANDLED). This leads to
interrupt storms when it is a secondary device that's actually the
interrupt source.

Signed-off-by: Brad Mouring <brad.mouring@ni.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 173 +++++++++++++++++++++++++-------------------------
 include/linux/phy.h   |   1 -
 2 files changed, 86 insertions(+), 88 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 39de77a8bb63..dba6d17ad885 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -614,6 +614,91 @@ static void phy_error(struct phy_device *phydev)
 	phy_trigger_machine(phydev, false);
 }
 
+/**
+ * phy_disable_interrupts - Disable the PHY interrupts from the PHY side
+ * @phydev: target phy_device struct
+ */
+static int phy_disable_interrupts(struct phy_device *phydev)
+{
+	int err;
+
+	/* Disable PHY interrupts */
+	err = phy_config_interrupt(phydev, PHY_INTERRUPT_DISABLED);
+	if (err)
+		goto phy_err;
+
+	/* Clear the interrupt */
+	err = phy_clear_interrupt(phydev);
+	if (err)
+		goto phy_err;
+
+	return 0;
+
+phy_err:
+	phy_error(phydev);
+
+	return err;
+}
+
+/**
+ * phy_change - Called by the phy_interrupt to handle PHY changes
+ * @phydev: phy_device struct that interrupted
+ */
+static irqreturn_t phy_change(struct phy_device *phydev)
+{
+	if (phy_interrupt_is_valid(phydev)) {
+		if (phydev->drv->did_interrupt &&
+		    !phydev->drv->did_interrupt(phydev))
+			goto ignore;
+
+		if (phy_disable_interrupts(phydev))
+			goto phy_err;
+	}
+
+	mutex_lock(&phydev->lock);
+	if ((PHY_RUNNING == phydev->state) || (PHY_NOLINK == phydev->state))
+		phydev->state = PHY_CHANGELINK;
+	mutex_unlock(&phydev->lock);
+
+	if (phy_interrupt_is_valid(phydev)) {
+		atomic_dec(&phydev->irq_disable);
+		enable_irq(phydev->irq);
+
+		/* Reenable interrupts */
+		if (PHY_HALTED != phydev->state &&
+		    phy_config_interrupt(phydev, PHY_INTERRUPT_ENABLED))
+			goto irq_enable_err;
+	}
+
+	/* reschedule state queue work to run as soon as possible */
+	phy_trigger_machine(phydev, true);
+	return IRQ_HANDLED;
+
+ignore:
+	atomic_dec(&phydev->irq_disable);
+	enable_irq(phydev->irq);
+	return IRQ_NONE;
+
+irq_enable_err:
+	disable_irq(phydev->irq);
+	atomic_inc(&phydev->irq_disable);
+phy_err:
+	phy_error(phydev);
+	return IRQ_NONE;
+}
+
+/**
+ * phy_change_work - Scheduled by the phy_mac_interrupt to handle PHY changes
+ * @work: work_struct that describes the work to be done
+ */
+void phy_change_work(struct work_struct *work)
+{
+	struct phy_device *phydev =
+		container_of(work, struct phy_device, phy_queue);
+
+	phy_change(phydev);
+}
+
 /**
  * phy_interrupt - PHY interrupt handler
  * @irq: interrupt line
@@ -632,9 +717,7 @@ static irqreturn_t phy_interrupt(int irq, void *phy_dat)
 	disable_irq_nosync(irq);
 	atomic_inc(&phydev->irq_disable);
 
-	phy_change(phydev);
-
-	return IRQ_HANDLED;
+	return phy_change(phydev);
 }
 
 /**
@@ -651,32 +734,6 @@ static int phy_enable_interrupts(struct phy_device *phydev)
 	return phy_config_interrupt(phydev, PHY_INTERRUPT_ENABLED);
 }
 
-/**
- * phy_disable_interrupts - Disable the PHY interrupts from the PHY side
- * @phydev: target phy_device struct
- */
-static int phy_disable_interrupts(struct phy_device *phydev)
-{
-	int err;
-
-	/* Disable PHY interrupts */
-	err = phy_config_interrupt(phydev, PHY_INTERRUPT_DISABLED);
-	if (err)
-		goto phy_err;
-
-	/* Clear the interrupt */
-	err = phy_clear_interrupt(phydev);
-	if (err)
-		goto phy_err;
-
-	return 0;
-
-phy_err:
-	phy_error(phydev);
-
-	return err;
-}
-
 /**
  * phy_start_interrupts - request and enable interrupts for a PHY device
  * @phydev: target phy_device struct
@@ -727,64 +784,6 @@ int phy_stop_interrupts(struct phy_device *phydev)
 }
 EXPORT_SYMBOL(phy_stop_interrupts);
 
-/**
- * phy_change - Called by the phy_interrupt to handle PHY changes
- * @phydev: phy_device struct that interrupted
- */
-void phy_change(struct phy_device *phydev)
-{
-	if (phy_interrupt_is_valid(phydev)) {
-		if (phydev->drv->did_interrupt &&
-		    !phydev->drv->did_interrupt(phydev))
-			goto ignore;
-
-		if (phy_disable_interrupts(phydev))
-			goto phy_err;
-	}
-
-	mutex_lock(&phydev->lock);
-	if ((PHY_RUNNING == phydev->state) || (PHY_NOLINK == phydev->state))
-		phydev->state = PHY_CHANGELINK;
-	mutex_unlock(&phydev->lock);
-
-	if (phy_interrupt_is_valid(phydev)) {
-		atomic_dec(&phydev->irq_disable);
-		enable_irq(phydev->irq);
-
-		/* Reenable interrupts */
-		if (PHY_HALTED != phydev->state &&
-		    phy_config_interrupt(phydev, PHY_INTERRUPT_ENABLED))
-			goto irq_enable_err;
-	}
-
-	/* reschedule state queue work to run as soon as possible */
-	phy_trigger_machine(phydev, true);
-	return;
-
-ignore:
-	atomic_dec(&phydev->irq_disable);
-	enable_irq(phydev->irq);
-	return;
-
-irq_enable_err:
-	disable_irq(phydev->irq);
-	atomic_inc(&phydev->irq_disable);
-phy_err:
-	phy_error(phydev);
-}
-
-/**
- * phy_change_work - Scheduled by the phy_mac_interrupt to handle PHY changes
- * @work: work_struct that describes the work to be done
- */
-void phy_change_work(struct work_struct *work)
-{
-	struct phy_device *phydev =
-		container_of(work, struct phy_device, phy_queue);
-
-	phy_change(phydev);
-}
-
 /**
  * phy_stop - Bring down the PHY link, and stop checking the status
  * @phydev: target phy_device struct
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 600076e1ce84..dca9e926b88f 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -895,7 +895,6 @@ int phy_driver_register(struct phy_driver *new_driver, struct module *owner);
 int phy_drivers_register(struct phy_driver *new_driver, int n,
 			 struct module *owner);
 void phy_state_machine(struct work_struct *work);
-void phy_change(struct phy_device *phydev);
 void phy_change_work(struct work_struct *work);
 void phy_mac_interrupt(struct phy_device *phydev, int new_link);
 void phy_start_machine(struct phy_device *phydev);
-- 
2.14.3


From 89fbcf6b7217f2bf65eb30da2929e9dcda2ba6f8 Mon Sep 17 00:00:00 2001
From: Roman Mashak <mrv@mojatatu.com>
Date: Mon, 12 Mar 2018 16:20:58 -0400
Subject: [PATCH 14/43] net sched actions: return explicit error when
 tunnel_key mode is not specified

[ Upstream commit 51d4740f88affd85d49c04e3c9cd129c0e33bcb9 ]

If set/unset mode of the tunnel_key action is not provided, ->init() still
returns 0, and the caller proceeds with bogus 'struct tc_action *' object,
this results in crash:

% tc actions add action tunnel_key src_ip 1.1.1.1 dst_ip 2.2.2.1 id 7 index 1

[   35.805515] general protection fault: 0000 [#1] SMP PTI
[   35.806161] Modules linked in: act_tunnel_key kvm_intel kvm irqbypass
crct10dif_pclmul crc32_pclmul ghash_clmulni_intel pcbc aesni_intel aes_x86_64
crypto_simd glue_helper cryptd serio_raw
[   35.808233] CPU: 1 PID: 428 Comm: tc Not tainted 4.16.0-rc4+ #286
[   35.808929] RIP: 0010:tcf_action_init+0x90/0x190
[   35.809457] RSP: 0018:ffffb8edc068b9a0 EFLAGS: 00010206
[   35.810053] RAX: 1320c000000a0003 RBX: 0000000000000001 RCX: 0000000000000000
[   35.810866] RDX: 0000000000000070 RSI: 0000000000007965 RDI: ffffb8edc068b910
[   35.811660] RBP: ffffb8edc068b9d0 R08: 0000000000000000 R09: ffffb8edc068b808
[   35.812463] R10: ffffffffc02bf040 R11: 0000000000000040 R12: ffffb8edc068bb38
[   35.813235] R13: 0000000000000000 R14: 0000000000000000 R15: ffffb8edc068b910
[   35.814006] FS:  00007f3d0d8556c0(0000) GS:ffff91d1dbc40000(0000)
knlGS:0000000000000000
[   35.814881] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   35.815540] CR2: 000000000043f720 CR3: 0000000019248001 CR4: 00000000001606a0
[   35.816457] Call Trace:
[   35.817158]  tc_ctl_action+0x11a/0x220
[   35.817795]  rtnetlink_rcv_msg+0x23d/0x2e0
[   35.818457]  ? __slab_alloc+0x1c/0x30
[   35.819079]  ? __kmalloc_node_track_caller+0xb1/0x2b0
[   35.819544]  ? rtnl_calcit.isra.30+0xe0/0xe0
[   35.820231]  netlink_rcv_skb+0xce/0x100
[   35.820744]  netlink_unicast+0x164/0x220
[   35.821500]  netlink_sendmsg+0x293/0x370
[   35.822040]  sock_sendmsg+0x30/0x40
[   35.822508]  ___sys_sendmsg+0x2c5/0x2e0
[   35.823149]  ? pagecache_get_page+0x27/0x220
[   35.823714]  ? filemap_fault+0xa2/0x640
[   35.824423]  ? page_add_file_rmap+0x108/0x200
[   35.825065]  ? alloc_set_pte+0x2aa/0x530
[   35.825585]  ? finish_fault+0x4e/0x70
[   35.826140]  ? __handle_mm_fault+0xbc1/0x10d0
[   35.826723]  ? __sys_sendmsg+0x41/0x70
[   35.827230]  __sys_sendmsg+0x41/0x70
[   35.827710]  do_syscall_64+0x68/0x120
[   35.828195]  entry_SYSCALL_64_after_hwframe+0x3d/0xa2
[   35.828859] RIP: 0033:0x7f3d0ca4da67
[   35.829331] RSP: 002b:00007ffc9f284338 EFLAGS: 00000246 ORIG_RAX:
000000000000002e
[   35.830304] RAX: ffffffffffffffda RBX: 00007ffc9f284460 RCX: 00007f3d0ca4da67
[   35.831247] RDX: 0000000000000000 RSI: 00007ffc9f2843b0 RDI: 0000000000000003
[   35.832167] RBP: 000000005aa6a7a9 R08: 0000000000000001 R09: 0000000000000000
[   35.833075] R10: 00000000000005f1 R11: 0000000000000246 R12: 0000000000000000
[   35.833997] R13: 00007ffc9f2884c0 R14: 0000000000000001 R15: 0000000000674640
[   35.834923] Code: 24 30 bb 01 00 00 00 45 31 f6 eb 5e 8b 50 08 83 c2 07 83 e2
fc 83 c2 70 49 8b 07 48 8b 40 70 48 85 c0 74 10 48 89 14 24 4c 89 ff <ff> d0 48
8b 14 24 48 01 c2 49 01 d6 45 85 ed 74 05 41 83 47 2c
[   35.837442] RIP: tcf_action_init+0x90/0x190 RSP: ffffb8edc068b9a0
[   35.838291] ---[ end trace a095c06ee4b97a26 ]---

Fixes: d0f6dd8a914f ("net/sched: Introduce act_tunnel_key")
Signed-off-by: Roman Mashak <mrv@mojatatu.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_tunnel_key.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 30c96274c638..22bf1a376b91 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -153,6 +153,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 		metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX;
 		break;
 	default:
+		ret = -EINVAL;
 		goto err_out;
 	}
 
-- 
2.14.3


From dae055711298cdba89e3da7dc0999fc65c8052d7 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Tue, 20 Mar 2018 16:49:26 +0100
Subject: [PATCH 15/43] ppp: avoid loop in xmit recursion detection code

[ Upstream commit 6d066734e9f09cdea4a3b9cb76136db3f29cfb02 ]

We already detect situations where a PPP channel sends packets back to
its upper PPP device. While this is enough to avoid deadlocking on xmit
locks, this doesn't prevent packets from looping between the channel
and the unit.

The problem is that ppp_start_xmit() enqueues packets in ppp->file.xq
before checking for xmit recursion. Therefore, __ppp_xmit_process()
might dequeue a packet from ppp->file.xq and send it on the channel
which, in turn, loops it back on the unit. Then ppp_start_xmit()
queues the packet back to ppp->file.xq and __ppp_xmit_process() picks
it up and sends it again through the channel. Therefore, the packet
will loop between __ppp_xmit_process() and ppp_start_xmit() until some
other part of the xmit path drops it.

For L2TP, we rapidly fill the skb's headroom and pppol2tp_xmit() drops
the packet after a few iterations. But PPTP reallocates the headroom
if necessary, letting the loop run and exhaust the machine resources
(as reported in https://bugzilla.kernel.org/show_bug.cgi?id=199109).

Fix this by letting __ppp_xmit_process() enqueue the skb to
ppp->file.xq, so that we can check for recursion before adding it to
the queue. Now ppp_xmit_process() can drop the packet when recursion is
detected.

__ppp_channel_push() is a bit special. It calls __ppp_xmit_process()
without having any actual packet to send. This is used by
ppp_output_wakeup() to re-enable transmission on the parent unit (for
implementations like ppp_async.c, where the .start_xmit() function
might not consume the skb, leaving it in ppp->xmit_pending and
disabling transmission).
Therefore, __ppp_xmit_process() needs to handle the case where skb is
NULL, dequeuing as many packets as possible from ppp->file.xq.

Reported-by: xu heng <xuheng333@zoho.com>
Fixes: 55454a565836 ("ppp: avoid dealock on recursive xmit")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/ppp_generic.c | 26 ++++++++++++++------------
 1 file changed, 14 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 38cd2e8fae23..34b24d7e1e2f 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -256,7 +256,7 @@ struct ppp_net {
 /* Prototypes. */
 static int ppp_unattached_ioctl(struct net *net, struct ppp_file *pf,
 			struct file *file, unsigned int cmd, unsigned long arg);
-static void ppp_xmit_process(struct ppp *ppp);
+static void ppp_xmit_process(struct ppp *ppp, struct sk_buff *skb);
 static void ppp_send_frame(struct ppp *ppp, struct sk_buff *skb);
 static void ppp_push(struct ppp *ppp);
 static void ppp_channel_push(struct channel *pch);
@@ -512,13 +512,12 @@ static ssize_t ppp_write(struct file *file, const char __user *buf,
 		goto out;
 	}
 
-	skb_queue_tail(&pf->xq, skb);
-
 	switch (pf->kind) {
 	case INTERFACE:
-		ppp_xmit_process(PF_TO_PPP(pf));
+		ppp_xmit_process(PF_TO_PPP(pf), skb);
 		break;
 	case CHANNEL:
+		skb_queue_tail(&pf->xq, skb);
 		ppp_channel_push(PF_TO_CHANNEL(pf));
 		break;
 	}
@@ -1264,8 +1263,8 @@ ppp_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	put_unaligned_be16(proto, pp);
 
 	skb_scrub_packet(skb, !net_eq(ppp->ppp_net, dev_net(dev)));
-	skb_queue_tail(&ppp->file.xq, skb);
-	ppp_xmit_process(ppp);
+	ppp_xmit_process(ppp, skb);
+
 	return NETDEV_TX_OK;
 
  outf:
@@ -1417,13 +1416,14 @@ static void ppp_setup(struct net_device *dev)
  */
 
 /* Called to do any work queued up on the transmit side that can now be done */
-static void __ppp_xmit_process(struct ppp *ppp)
+static void __ppp_xmit_process(struct ppp *ppp, struct sk_buff *skb)
 {
-	struct sk_buff *skb;
-
 	ppp_xmit_lock(ppp);
 	if (!ppp->closing) {
 		ppp_push(ppp);
+
+		if (skb)
+			skb_queue_tail(&ppp->file.xq, skb);
 		while (!ppp->xmit_pending &&
 		       (skb = skb_dequeue(&ppp->file.xq)))
 			ppp_send_frame(ppp, skb);
@@ -1437,7 +1437,7 @@ static void __ppp_xmit_process(struct ppp *ppp)
 	ppp_xmit_unlock(ppp);
 }
 
-static void ppp_xmit_process(struct ppp *ppp)
+static void ppp_xmit_process(struct ppp *ppp, struct sk_buff *skb)
 {
 	local_bh_disable();
 
@@ -1445,7 +1445,7 @@ static void ppp_xmit_process(struct ppp *ppp)
 		goto err;
 
 	(*this_cpu_ptr(ppp->xmit_recursion))++;
-	__ppp_xmit_process(ppp);
+	__ppp_xmit_process(ppp, skb);
 	(*this_cpu_ptr(ppp->xmit_recursion))--;
 
 	local_bh_enable();
@@ -1455,6 +1455,8 @@ static void ppp_xmit_process(struct ppp *ppp)
 err:
 	local_bh_enable();
 
+	kfree_skb(skb);
+
 	if (net_ratelimit())
 		netdev_err(ppp->dev, "recursion detected\n");
 }
@@ -1939,7 +1941,7 @@ static void __ppp_channel_push(struct channel *pch)
 	if (skb_queue_empty(&pch->file.xq)) {
 		ppp = pch->ppp;
 		if (ppp)
-			__ppp_xmit_process(ppp);
+			__ppp_xmit_process(ppp, NULL);
 	}
 }
 
-- 
2.14.3


From db75f5501a480acd3b876a0fbfe441938340fe3d Mon Sep 17 00:00:00 2001
From: Paul Blakey <paulb@mellanox.com>
Date: Sun, 4 Mar 2018 17:29:48 +0200
Subject: [PATCH 16/43] rhashtable: Fix rhlist duplicates insertion

[ Upstream commit d3dcf8eb615537526bd42ff27a081d46d337816e ]

When inserting duplicate objects (those with the same key),
current rhlist implementation messes up the chain pointers by
updating the bucket pointer instead of prev next pointer to the
newly inserted node. This causes missing elements on removal and
travesal.

Fix that by properly updating pprev pointer to point to
the correct rhash_head next pointer.

Issue: 1241076
Change-Id: I86b2c140bcb4aeb10b70a72a267ff590bb2b17e7
Fixes: ca26893f05e8 ('rhashtable: Add rhlist interface')
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable.h | 4 +++-
 lib/rhashtable.c           | 4 +++-
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 361c08e35dbc..7fd514f36e74 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -750,8 +750,10 @@ static inline void *__rhashtable_insert_fast(
 		if (!key ||
 		    (params.obj_cmpfn ?
 		     params.obj_cmpfn(&arg, rht_obj(ht, head)) :
-		     rhashtable_compare(&arg, rht_obj(ht, head))))
+		     rhashtable_compare(&arg, rht_obj(ht, head)))) {
+			pprev = &head->next;
 			continue;
+		}
 
 		data = rht_obj(ht, head);
 
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index ddd7dde87c3c..b734ce731a7a 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -537,8 +537,10 @@ static void *rhashtable_lookup_one(struct rhashtable *ht,
 		if (!key ||
 		    (ht->p.obj_cmpfn ?
 		     ht->p.obj_cmpfn(&arg, rht_obj(ht, head)) :
-		     rhashtable_compare(&arg, rht_obj(ht, head))))
+		     rhashtable_compare(&arg, rht_obj(ht, head)))) {
+			pprev = &head->next;
 			continue;
+		}
 
 		if (!ht->rhlist)
 			return rht_obj(ht, head);
-- 
2.14.3


From f5465daa55065f20a0a421b4aa4b4632ebf981fc Mon Sep 17 00:00:00 2001
From: Tom Herbert <tom@quantonium.net>
Date: Tue, 13 Mar 2018 12:01:43 -0700
Subject: [PATCH 17/43] kcm: lock lower socket in kcm_attach

[ Upstream commit 2cc683e88c0c993ac3721d9b702cb0630abe2879 ]

Need to lock lower socket in order to provide mutual exclusion
with kcm_unattach.

v2: Add Reported-by for syzbot

Fixes: ab7ac4eb9832e32a09f4e804 ("kcm: Kernel Connection Multiplexor module")
Reported-by: syzbot+ea75c0ffcd353d32515f064aaebefc5279e6161e@syzkaller.appspotmail.com
Signed-off-by: Tom Herbert <tom@quantonium.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/kcm/kcmsock.c | 33 +++++++++++++++++++++++----------
 1 file changed, 23 insertions(+), 10 deletions(-)

diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 58d53b907d53..9db49805b7be 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -1381,24 +1381,32 @@ static int kcm_attach(struct socket *sock, struct socket *csock,
 		.parse_msg = kcm_parse_func_strparser,
 		.read_sock_done = kcm_read_sock_done,
 	};
-	int err;
+	int err = 0;
 
 	csk = csock->sk;
 	if (!csk)
 		return -EINVAL;
 
+	lock_sock(csk);
+
 	/* Only allow TCP sockets to be attached for now */
 	if ((csk->sk_family != AF_INET && csk->sk_family != AF_INET6) ||
-	    csk->sk_protocol != IPPROTO_TCP)
-		return -EOPNOTSUPP;
+	    csk->sk_protocol != IPPROTO_TCP) {
+		err = -EOPNOTSUPP;
+		goto out;
+	}
 
 	/* Don't allow listeners or closed sockets */
-	if (csk->sk_state == TCP_LISTEN || csk->sk_state == TCP_CLOSE)
-		return -EOPNOTSUPP;
+	if (csk->sk_state == TCP_LISTEN || csk->sk_state == TCP_CLOSE) {
+		err = -EOPNOTSUPP;
+		goto out;
+	}
 
 	psock = kmem_cache_zalloc(kcm_psockp, GFP_KERNEL);
-	if (!psock)
-		return -ENOMEM;
+	if (!psock) {
+		err = -ENOMEM;
+		goto out;
+	}
 
 	psock->mux = mux;
 	psock->sk = csk;
@@ -1407,7 +1415,7 @@ static int kcm_attach(struct socket *sock, struct socket *csock,
 	err = strp_init(&psock->strp, csk, &cb);
 	if (err) {
 		kmem_cache_free(kcm_psockp, psock);
-		return err;
+		goto out;
 	}
 
 	write_lock_bh(&csk->sk_callback_lock);
@@ -1419,7 +1427,8 @@ static int kcm_attach(struct socket *sock, struct socket *csock,
 		write_unlock_bh(&csk->sk_callback_lock);
 		strp_done(&psock->strp);
 		kmem_cache_free(kcm_psockp, psock);
-		return -EALREADY;
+		err = -EALREADY;
+		goto out;
 	}
 
 	psock->save_data_ready = csk->sk_data_ready;
@@ -1455,7 +1464,10 @@ static int kcm_attach(struct socket *sock, struct socket *csock,
 	/* Schedule RX work in case there are already bytes queued */
 	strp_check_rcv(&psock->strp);
 
-	return 0;
+out:
+	release_sock(csk);
+
+	return err;
 }
 
 static int kcm_attach_ioctl(struct socket *sock, struct kcm_attach *info)
@@ -1507,6 +1519,7 @@ static void kcm_unattach(struct kcm_psock *psock)
 
 	if (WARN_ON(psock->rx_kcm)) {
 		write_unlock_bh(&csk->sk_callback_lock);
+		release_sock(csk);
 		return;
 	}
 
-- 
2.14.3


From bc46a5d98483dd9d4a8901304407ff3e403a09ce Mon Sep 17 00:00:00 2001
From: Alexey Kodanev <alexey.kodanev@oracle.com>
Date: Mon, 5 Mar 2018 20:52:54 +0300
Subject: [PATCH 18/43] sch_netem: fix skb leak in netem_enqueue()

[ Upstream commit 35d889d10b649fda66121891ec05eca88150059d ]

When we exceed current packets limit and we have more than one
segment in the list returned by skb_gso_segment(), netem drops
only the first one, skipping the rest, hence kmemleak reports:

unreferenced object 0xffff880b5d23b600 (size 1024):
  comm "softirq", pid 0, jiffies 4384527763 (age 2770.629s)
  hex dump (first 32 bytes):
    00 80 23 5d 0b 88 ff ff 00 00 00 00 00 00 00 00  ..#]............
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<00000000d8a19b9d>] __alloc_skb+0xc9/0x520
    [<000000001709b32f>] skb_segment+0x8c8/0x3710
    [<00000000c7b9bb88>] tcp_gso_segment+0x331/0x1830
    [<00000000c921cba1>] inet_gso_segment+0x476/0x1370
    [<000000008b762dd4>] skb_mac_gso_segment+0x1f9/0x510
    [<000000002182660a>] __skb_gso_segment+0x1dd/0x620
    [<00000000412651b9>] netem_enqueue+0x1536/0x2590 [sch_netem]
    [<0000000005d3b2a9>] __dev_queue_xmit+0x1167/0x2120
    [<00000000fc5f7327>] ip_finish_output2+0x998/0xf00
    [<00000000d309e9d3>] ip_output+0x1aa/0x2c0
    [<000000007ecbd3a4>] tcp_transmit_skb+0x18db/0x3670
    [<0000000042d2a45f>] tcp_write_xmit+0x4d4/0x58c0
    [<0000000056a44199>] tcp_tasklet_func+0x3d9/0x540
    [<0000000013d06d02>] tasklet_action+0x1ca/0x250
    [<00000000fcde0b8b>] __do_softirq+0x1b4/0x5a3
    [<00000000e7ed027c>] irq_exit+0x1e2/0x210

Fix it by adding the rest of the segments, if any, to skb 'to_free'
list. Add new __qdisc_drop_all() and qdisc_drop_all() functions
because they can be useful in the future if we need to drop segmented
GSO packets in other places.

Fixes: 6071bd1aa13e ("netem: Segment GSO packets on enqueue")
Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h | 19 +++++++++++++++++++
 net/sched/sch_netem.c     |  2 +-
 2 files changed, 20 insertions(+), 1 deletion(-)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 6073e8bae025..f59acacaa265 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -723,6 +723,16 @@ static inline void __qdisc_drop(struct sk_buff *skb, struct sk_buff **to_free)
 	*to_free = skb;
 }
 
+static inline void __qdisc_drop_all(struct sk_buff *skb,
+				    struct sk_buff **to_free)
+{
+	if (skb->prev)
+		skb->prev->next = *to_free;
+	else
+		skb->next = *to_free;
+	*to_free = skb;
+}
+
 static inline unsigned int __qdisc_queue_drop_head(struct Qdisc *sch,
 						   struct qdisc_skb_head *qh,
 						   struct sk_buff **to_free)
@@ -843,6 +853,15 @@ static inline int qdisc_drop(struct sk_buff *skb, struct Qdisc *sch,
 	return NET_XMIT_DROP;
 }
 
+static inline int qdisc_drop_all(struct sk_buff *skb, struct Qdisc *sch,
+				 struct sk_buff **to_free)
+{
+	__qdisc_drop_all(skb, to_free);
+	qdisc_qstats_drop(sch);
+
+	return NET_XMIT_DROP;
+}
+
 /* Length to Time (L2T) lookup in a qdisc_rate_table, to determine how
    long it will take to send a packet given its size.
  */
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index b1266e75ca43..8c8df75dbead 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -513,7 +513,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	}
 
 	if (unlikely(sch->q.qlen >= sch->limit))
-		return qdisc_drop(skb, sch, to_free);
+		return qdisc_drop_all(skb, sch, to_free);
 
 	qdisc_qstats_backlog_inc(sch, skb);
 
-- 
2.14.3


From f505e34a48a88ce937d2dc1434c5001fb6b7dc2a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 5 Mar 2018 08:51:03 -0800
Subject: [PATCH 19/43] ieee802154: 6lowpan: fix possible NULL deref in
 lowpan_device_event()

[ Upstream commit ca0edb131bdf1e6beaeb2b8289fd6b374b74147d ]

A tun device type can trivially be set to arbitrary value using
TUNSETLINK ioctl().

Therefore, lowpan_device_event() must really check that ieee802154_ptr
is not NULL.

Fixes: 2c88b5283f60d ("ieee802154: 6lowpan: remove check on null")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Alexander Aring <alex.aring@gmail.com>
Cc: Stefan Schmidt <stefan@osg.samsung.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: Stefan Schmidt <stefan@osg.samsung.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ieee802154/6lowpan/core.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c
index 974765b7d92a..e9f0489e4229 100644
--- a/net/ieee802154/6lowpan/core.c
+++ b/net/ieee802154/6lowpan/core.c
@@ -206,9 +206,13 @@ static inline void lowpan_netlink_fini(void)
 static int lowpan_device_event(struct notifier_block *unused,
 			       unsigned long event, void *ptr)
 {
-	struct net_device *wdev = netdev_notifier_info_to_dev(ptr);
+	struct net_device *ndev = netdev_notifier_info_to_dev(ptr);
+	struct wpan_dev *wpan_dev;
 
-	if (wdev->type != ARPHRD_IEEE802154)
+	if (ndev->type != ARPHRD_IEEE802154)
+		return NOTIFY_DONE;
+	wpan_dev = ndev->ieee802154_ptr;
+	if (!wpan_dev)
 		return NOTIFY_DONE;
 
 	switch (event) {
@@ -217,8 +221,8 @@ static int lowpan_device_event(struct notifier_block *unused,
 		 * also delete possible lowpan interfaces which belongs
 		 * to the wpan interface.
 		 */
-		if (wdev->ieee802154_ptr->lowpan_dev)
-			lowpan_dellink(wdev->ieee802154_ptr->lowpan_dev, NULL);
+		if (wpan_dev->lowpan_dev)
+			lowpan_dellink(wpan_dev->lowpan_dev, NULL);
 		break;
 	default:
 		return NOTIFY_DONE;
-- 
2.14.3


From e6cbdd3c16c48ce6c5beba2574dddc65de503253 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 14 Mar 2018 09:04:16 -0700
Subject: [PATCH 20/43] net: use skb_to_full_sk() in skb_update_prio()

[ Upstream commit 4dcb31d4649df36297296b819437709f5407059c ]

Andrei Vagin reported a KASAN: slab-out-of-bounds error in
skb_update_prio()

Since SYNACK might be attached to a request socket, we need to
get back to the listener socket.
Since this listener is manipulated without locks, add const
qualifiers to sock_cgroup_prioidx() so that the const can also
be used in skb_update_prio()

Also add the const qualifier to sock_cgroup_classid() for consistency.

Fixes: ca6fb0651883 ("tcp: attach SYNACK messages to request sockets instead of listener")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrei Vagin <avagin@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/cgroup-defs.h |  4 ++--
 net/core/dev.c              | 22 +++++++++++++++-------
 2 files changed, 17 insertions(+), 9 deletions(-)

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 1dff0a478b45..4e8f77504a57 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -696,13 +696,13 @@ struct sock_cgroup_data {
  * updaters and return part of the previous pointer as the prioidx or
  * classid.  Such races are short-lived and the result isn't critical.
  */
-static inline u16 sock_cgroup_prioidx(struct sock_cgroup_data *skcd)
+static inline u16 sock_cgroup_prioidx(const struct sock_cgroup_data *skcd)
 {
 	/* fallback to 1 which is always the ID of the root cgroup */
 	return (skcd->is_data & 1) ? skcd->prioidx : 1;
 }
 
-static inline u32 sock_cgroup_classid(struct sock_cgroup_data *skcd)
+static inline u32 sock_cgroup_classid(const struct sock_cgroup_data *skcd)
 {
 	/* fallback to 0 which is the unconfigured default classid */
 	return (skcd->is_data & 1) ? skcd->classid : 0;
diff --git a/net/core/dev.c b/net/core/dev.c
index c75ef9d8105a..387af3415385 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3224,15 +3224,23 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO)
 static void skb_update_prio(struct sk_buff *skb)
 {
-	struct netprio_map *map = rcu_dereference_bh(skb->dev->priomap);
+	const struct netprio_map *map;
+	const struct sock *sk;
+	unsigned int prioidx;
 
-	if (!skb->priority && skb->sk && map) {
-		unsigned int prioidx =
-			sock_cgroup_prioidx(&skb->sk->sk_cgrp_data);
+	if (skb->priority)
+		return;
+	map = rcu_dereference_bh(skb->dev->priomap);
+	if (!map)
+		return;
+	sk = skb_to_full_sk(skb);
+	if (!sk)
+		return;
 
-		if (prioidx < map->priomap_len)
-			skb->priority = map->priomap[prioidx];
-	}
+	prioidx = sock_cgroup_prioidx(&sk->sk_cgrp_data);
+
+	if (prioidx < map->priomap_len)
+		skb->priority = map->priomap[prioidx];
 }
 #else
 #define skb_update_prio(skb)
-- 
2.14.3


From 4f8d3bcbed75378ae85b368047ef2677c17a0626 Mon Sep 17 00:00:00 2001
From: Kirill Tkhai <ktkhai@virtuozzo.com>
Date: Tue, 6 Mar 2018 18:46:39 +0300
Subject: [PATCH 21/43] net: Fix hlist corruptions in inet_evict_bucket()

[ Upstream commit a560002437d3646dafccecb1bf32d1685112ddda ]

inet_evict_bucket() iterates global list, and
several tasks may call it in parallel. All of
them hash the same fq->list_evictor to different
lists, which leads to list corruption.

This patch makes fq be hashed to expired list
only if this has not been made yet by another
task. Since inet_frag_alloc() allocates fq
using kmem_cache_zalloc(), we may rely on
list_evictor is initially unhashed.

The problem seems to exist before async
pernet_operations, as there was possible to have
exit method to be executed in parallel with
inet_frags::frags_work, so I add two Fixes tags.
This also may go to stable.

Fixes: d1fe19444d82 "inet: frag: don't re-use chainlist for evictor"
Fixes: f84c6821aa54 "net: Convert pernet_subsys, registered from inet_init()"
Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/inet_fragment.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index af74d0433453..e691705f0a85 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -119,6 +119,9 @@ static void inet_frag_secret_rebuild(struct inet_frags *f)
 
 static bool inet_fragq_should_evict(const struct inet_frag_queue *q)
 {
+	if (!hlist_unhashed(&q->list_evictor))
+		return false;
+
 	return q->net->low_thresh == 0 ||
 	       frag_mem_limit(q->net) >= q->net->low_thresh;
 }
-- 
2.14.3


From 32f639ffbe4477e9c67c4e8796f328c13f36a4f7 Mon Sep 17 00:00:00 2001
From: Alexey Kodanev <alexey.kodanev@oracle.com>
Date: Tue, 6 Mar 2018 22:57:01 +0300
Subject: [PATCH 22/43] dccp: check sk for closed state in dccp_sendmsg()

[ Upstream commit 67f93df79aeefc3add4e4b31a752600f834236e2 ]

dccp_disconnect() sets 'dp->dccps_hc_tx_ccid' tx handler to NULL,
therefore if DCCP socket is disconnected and dccp_sendmsg() is
called after it, it will cause a NULL pointer dereference in
dccp_write_xmit().

This crash and the reproducer was reported by syzbot. Looks like
it is reproduced if commit 69c64866ce07 ("dccp: CVE-2017-8824:
use-after-free in DCCP code") is applied.

Reported-by: syzbot+f99ab3887ab65d70f816@syzkaller.appspotmail.com
Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/proto.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 9d43c1f40274..ff3b058cf58c 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -789,6 +789,11 @@ int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	if (skb == NULL)
 		goto out_release;
 
+	if (sk->sk_state == DCCP_CLOSED) {
+		rc = -ENOTCONN;
+		goto out_discard;
+	}
+
 	skb_reserve(skb, sk->sk_prot->max_header);
 	rc = memcpy_from_msg(skb_put(skb, len), msg, len);
 	if (rc != 0)
-- 
2.14.3


From 8e2db9eb4dd124817ac299b41a52298ddb9fddb9 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Thu, 8 Mar 2018 17:00:02 +0100
Subject: [PATCH 23/43] ipv6: fix access to non-linear packet in
 ndisc_fill_redirect_hdr_option()

[ Upstream commit 9f62c15f28b0d1d746734666d88a79f08ba1e43e ]

Fix the following slab-out-of-bounds kasan report in
ndisc_fill_redirect_hdr_option when the incoming ipv6 packet is not
linear and the accessed data are not in the linear data region of orig_skb.

[ 1503.122508] ==================================================================
[ 1503.122832] BUG: KASAN: slab-out-of-bounds in ndisc_send_redirect+0x94e/0x990
[ 1503.123036] Read of size 1184 at addr ffff8800298ab6b0 by task netperf/1932

[ 1503.123220] CPU: 0 PID: 1932 Comm: netperf Not tainted 4.16.0-rc2+ #124
[ 1503.123347] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.10.2-2.fc27 04/01/2014
[ 1503.123527] Call Trace:
[ 1503.123579]  <IRQ>
[ 1503.123638]  print_address_description+0x6e/0x280
[ 1503.123849]  kasan_report+0x233/0x350
[ 1503.123946]  memcpy+0x1f/0x50
[ 1503.124037]  ndisc_send_redirect+0x94e/0x990
[ 1503.125150]  ip6_forward+0x1242/0x13b0
[...]
[ 1503.153890] Allocated by task 1932:
[ 1503.153982]  kasan_kmalloc+0x9f/0xd0
[ 1503.154074]  __kmalloc_track_caller+0xb5/0x160
[ 1503.154198]  __kmalloc_reserve.isra.41+0x24/0x70
[ 1503.154324]  __alloc_skb+0x130/0x3e0
[ 1503.154415]  sctp_packet_transmit+0x21a/0x1810
[ 1503.154533]  sctp_outq_flush+0xc14/0x1db0
[ 1503.154624]  sctp_do_sm+0x34e/0x2740
[ 1503.154715]  sctp_primitive_SEND+0x57/0x70
[ 1503.154807]  sctp_sendmsg+0xaa6/0x1b10
[ 1503.154897]  sock_sendmsg+0x68/0x80
[ 1503.154987]  ___sys_sendmsg+0x431/0x4b0
[ 1503.155078]  __sys_sendmsg+0xa4/0x130
[ 1503.155168]  do_syscall_64+0x171/0x3f0
[ 1503.155259]  entry_SYSCALL_64_after_hwframe+0x42/0xb7

[ 1503.155436] Freed by task 1932:
[ 1503.155527]  __kasan_slab_free+0x134/0x180
[ 1503.155618]  kfree+0xbc/0x180
[ 1503.155709]  skb_release_data+0x27f/0x2c0
[ 1503.155800]  consume_skb+0x94/0xe0
[ 1503.155889]  sctp_chunk_put+0x1aa/0x1f0
[ 1503.155979]  sctp_inq_pop+0x2f8/0x6e0
[ 1503.156070]  sctp_assoc_bh_rcv+0x6a/0x230
[ 1503.156164]  sctp_inq_push+0x117/0x150
[ 1503.156255]  sctp_backlog_rcv+0xdf/0x4a0
[ 1503.156346]  __release_sock+0x142/0x250
[ 1503.156436]  release_sock+0x80/0x180
[ 1503.156526]  sctp_sendmsg+0xbb0/0x1b10
[ 1503.156617]  sock_sendmsg+0x68/0x80
[ 1503.156708]  ___sys_sendmsg+0x431/0x4b0
[ 1503.156799]  __sys_sendmsg+0xa4/0x130
[ 1503.156889]  do_syscall_64+0x171/0x3f0
[ 1503.156980]  entry_SYSCALL_64_after_hwframe+0x42/0xb7

[ 1503.157158] The buggy address belongs to the object at ffff8800298ab600
                which belongs to the cache kmalloc-1024 of size 1024
[ 1503.157444] The buggy address is located 176 bytes inside of
                1024-byte region [ffff8800298ab600, ffff8800298aba00)
[ 1503.157702] The buggy address belongs to the page:
[ 1503.157820] page:ffffea0000a62a00 count:1 mapcount:0 mapping:0000000000000000 index:0x0 compound_mapcount: 0
[ 1503.158053] flags: 0x4000000000008100(slab|head)
[ 1503.158171] raw: 4000000000008100 0000000000000000 0000000000000000 00000001800e000e
[ 1503.158350] raw: dead000000000100 dead000000000200 ffff880036002600 0000000000000000
[ 1503.158523] page dumped because: kasan: bad access detected

[ 1503.158698] Memory state around the buggy address:
[ 1503.158816]  ffff8800298ab900: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[ 1503.158988]  ffff8800298ab980: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[ 1503.159165] >ffff8800298aba00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[ 1503.159338]                    ^
[ 1503.159436]  ffff8800298aba80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[ 1503.159610]  ffff8800298abb00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[ 1503.159785] ==================================================================
[ 1503.159964] Disabling lock debugging due to kernel taint

The test scenario to trigger the issue consists of 4 devices:
- H0: data sender, connected to LAN0
- H1: data receiver, connected to LAN1
- GW0 and GW1: routers between LAN0 and LAN1. Both of them have an
  ethernet connection on LAN0 and LAN1
On H{0,1} set GW0 as default gateway while on GW0 set GW1 as next hop for
data from LAN0 to LAN1.
Moreover create an ip6ip6 tunnel between H0 and H1 and send 3 concurrent
data streams (TCP/UDP/SCTP) from H0 to H1 through ip6ip6 tunnel (send
buffer size is set to 16K). While data streams are active flush the route
cache on HA multiple times.
I have not been able to identify a given commit that introduced the issue
since, using the reproducer described above, the kasan report has been
triggered from 4.14 and I have not gone back further.

Reported-by: Jianlin Shi <jishi@redhat.com>
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ndisc.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 2a937c8d19e9..dd28005efb97 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1546,7 +1546,8 @@ static void ndisc_fill_redirect_hdr_option(struct sk_buff *skb,
 	*(opt++) = (rd_len >> 3);
 	opt += 6;
 
-	memcpy(opt, ipv6_hdr(orig_skb), rd_len - 8);
+	skb_copy_bits(orig_skb, skb_network_offset(orig_skb), opt,
+		      rd_len - 8);
 }
 
 void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
-- 
2.14.3


From a44358e4de31019754e3edaa35ca9aad7a148b98 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 6 Mar 2018 07:54:53 -0800
Subject: [PATCH 24/43] l2tp: do not accept arbitrary sockets

[ Upstream commit 17cfe79a65f98abe535261856c5aef14f306dff7 ]

syzkaller found an issue caused by lack of sufficient checks
in l2tp_tunnel_create()

RAW sockets can not be considered as UDP ones for instance.

In another patch, we shall replace all pr_err() by less intrusive
pr_debug() so that syzkaller can find other bugs faster.
Acked-by: Guillaume Nault <g.nault@alphalink.fr>
Acked-by: James Chapman <jchapman@katalix.com>

==================================================================
BUG: KASAN: slab-out-of-bounds in setup_udp_tunnel_sock+0x3ee/0x5f0 net/ipv4/udp_tunnel.c:69
dst_release: dst:00000000d53d0d0f refcnt:-1
Write of size 1 at addr ffff8801d013b798 by task syz-executor3/6242

CPU: 1 PID: 6242 Comm: syz-executor3 Not tainted 4.16.0-rc2+ #253
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x194/0x24d lib/dump_stack.c:53
 print_address_description+0x73/0x250 mm/kasan/report.c:256
 kasan_report_error mm/kasan/report.c:354 [inline]
 kasan_report+0x23b/0x360 mm/kasan/report.c:412
 __asan_report_store1_noabort+0x17/0x20 mm/kasan/report.c:435
 setup_udp_tunnel_sock+0x3ee/0x5f0 net/ipv4/udp_tunnel.c:69
 l2tp_tunnel_create+0x1354/0x17f0 net/l2tp/l2tp_core.c:1596
 pppol2tp_connect+0x14b1/0x1dd0 net/l2tp/l2tp_ppp.c:707
 SYSC_connect+0x213/0x4a0 net/socket.c:1640
 SyS_connect+0x24/0x30 net/socket.c:1621
 do_syscall_64+0x280/0x940 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x42/0xb7

Fixes: fd558d186df2 ("l2tp: Split pppol2tp patch into separate l2tp and ppp parts")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index af22aa8ae35b..490d7360222e 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1562,9 +1562,14 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
 		encap = cfg->encap;
 
 	/* Quick sanity checks */
+	err = -EPROTONOSUPPORT;
+	if (sk->sk_type != SOCK_DGRAM) {
+		pr_debug("tunl %hu: fd %d wrong socket type\n",
+			 tunnel_id, fd);
+		goto err;
+	}
 	switch (encap) {
 	case L2TP_ENCAPTYPE_UDP:
-		err = -EPROTONOSUPPORT;
 		if (sk->sk_protocol != IPPROTO_UDP) {
 			pr_err("tunl %hu: fd %d wrong protocol, got %d, expected %d\n",
 			       tunnel_id, fd, sk->sk_protocol, IPPROTO_UDP);
@@ -1572,7 +1577,6 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
 		}
 		break;
 	case L2TP_ENCAPTYPE_IP:
-		err = -EPROTONOSUPPORT;
 		if (sk->sk_protocol != IPPROTO_L2TP) {
 			pr_err("tunl %hu: fd %d wrong protocol, got %d, expected %d\n",
 			       tunnel_id, fd, sk->sk_protocol, IPPROTO_L2TP);
-- 
2.14.3


From 30dcaf91de2c027b30e0b5e6a142199b8515e7d1 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 18 Mar 2018 23:59:36 +0100
Subject: [PATCH 25/43] net: ethernet: arc: Fix a potential memory leak if an
 optional regulator is deferred

[ Upstream commit 00777fac28ba3e126b9e63e789a613e8bd2cab25 ]

If the optional regulator is deferred, we must release some resources.
They will be re-allocated when the probe function will be called again.

Fixes: 6eacf31139bf ("ethernet: arc: Add support for Rockchip SoC layer device tree bindings")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/arc/emac_rockchip.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/arc/emac_rockchip.c b/drivers/net/ethernet/arc/emac_rockchip.c
index c6163874e4e7..c770ca37c9b2 100644
--- a/drivers/net/ethernet/arc/emac_rockchip.c
+++ b/drivers/net/ethernet/arc/emac_rockchip.c
@@ -169,8 +169,10 @@ static int emac_rockchip_probe(struct platform_device *pdev)
 	/* Optional regulator for PHY */
 	priv->regulator = devm_regulator_get_optional(dev, "phy");
 	if (IS_ERR(priv->regulator)) {
-		if (PTR_ERR(priv->regulator) == -EPROBE_DEFER)
-			return -EPROBE_DEFER;
+		if (PTR_ERR(priv->regulator) == -EPROBE_DEFER) {
+			err = -EPROBE_DEFER;
+			goto out_clk_disable;
+		}
 		dev_err(dev, "no regulator found\n");
 		priv->regulator = NULL;
 	}
-- 
2.14.3


From bdd17f49071cff8cba0551dd5da926291aceeab2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?SZ=20Lin=20=28=E6=9E=97=E4=B8=8A=E6=99=BA=29?=
 <sz.lin@moxa.com>
Date: Fri, 16 Mar 2018 00:56:01 +0800
Subject: [PATCH 26/43] net: ethernet: ti: cpsw: add check for in-band mode
 setting with RGMII PHY interface
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit f9db50691db4a7d860fce985f080bb3fc23a7ede ]

According to AM335x TRM[1] 14.3.6.2, AM437x TRM[2] 15.3.6.2 and
DRA7 TRM[3] 24.11.4.8.7.3.3, in-band mode in EXT_EN(bit18) register is only
available when PHY is configured in RGMII mode with 10Mbps speed. It will
cause some networking issues without RGMII mode, such as carrier sense
errors and low throughput. TI also mentioned this issue in their forum[4].

This patch adds the check mechanism for PHY interface with RGMII interface
type, the in-band mode can only be set in RGMII mode with 10Mbps speed.

References:
[1]: https://www.ti.com/lit/ug/spruh73p/spruh73p.pdf
[2]: http://www.ti.com/lit/ug/spruhl7h/spruhl7h.pdf
[3]: http://www.ti.com/lit/ug/spruic2b/spruic2b.pdf
[4]: https://e2e.ti.com/support/arm/sitara_arm/f/791/p/640765/2392155

Suggested-by: Holsety Chen (陳憲輝) <Holsety.Chen@moxa.com>
Signed-off-by: SZ Lin (林上智) <sz.lin@moxa.com>
Signed-off-by: Schuyler Patton <spatton@ti.com>
Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 14b646b3b084..a5bb7b19040e 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -996,7 +996,8 @@ static void _cpsw_adjust_link(struct cpsw_slave *slave,
 		/* set speed_in input in case RMII mode is used in 100Mbps */
 		if (phy->speed == 100)
 			mac_control |= BIT(15);
-		else if (phy->speed == 10)
+		/* in band mode only works in 10Mbps RGMII mode */
+		else if ((phy->speed == 10) && phy_interface_is_rgmii(phy))
 			mac_control |= BIT(18); /* In Band mode */
 
 		if (priv->rx_pause)
-- 
2.14.3


From a2b33c908c615aa8807640fe9768680ae3f652ad Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Sun, 18 Mar 2018 12:49:51 -0700
Subject: [PATCH 27/43] net: fec: Fix unbalanced PM runtime calls

[ Upstream commit a069215cf5985f3aa1bba550264907d6bd05c5f7 ]

When unbinding/removing the driver, we will run into the following warnings:

[  259.655198] fec 400d1000.ethernet: 400d1000.ethernet supply phy not found, using dummy regulator
[  259.665065] fec 400d1000.ethernet: Unbalanced pm_runtime_enable!
[  259.672770] fec 400d1000.ethernet (unnamed net_device) (uninitialized): Invalid MAC address: 00:00:00:00:00:00
[  259.683062] fec 400d1000.ethernet (unnamed net_device) (uninitialized): Using random MAC address: f2:3e:93:b7:29:c1
[  259.696239] libphy: fec_enet_mii_bus: probed

Avoid these warnings by balancing the runtime PM calls during fec_drv_remove().

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 311539c6625f..eb2ea231c7ca 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -3565,6 +3565,8 @@ fec_drv_remove(struct platform_device *pdev)
 	fec_enet_mii_remove(fep);
 	if (fep->reg_phy)
 		regulator_disable(fep->reg_phy);
+	pm_runtime_put(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
 	if (of_phy_is_fixed_link(np))
 		of_phy_deregister_fixed_link(np);
 	of_node_put(fep->phy_node);
-- 
2.14.3


From 2d073df9f4d4f7b314415682f9b824971e785597 Mon Sep 17 00:00:00 2001
From: Arvind Yadav <arvind.yadav.cs@gmail.com>
Date: Tue, 13 Mar 2018 16:50:06 +0100
Subject: [PATCH 28/43] net/iucv: Free memory obtained by kzalloc

[ Upstream commit fa6a91e9b907231d2e38ea5ed89c537b3525df3d ]

Free memory by calling put_device(), if afiucv_iucv_init is not
successful.

Signed-off-by: Arvind Yadav <arvind.yadav.cs@gmail.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Signed-off-by: Ursula Braun <ursula.braun@de.ibm.com>
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/iucv/af_iucv.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 148533169b1d..ca98276c2709 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -2433,9 +2433,11 @@ static int afiucv_iucv_init(void)
 	af_iucv_dev->driver = &af_iucv_driver;
 	err = device_register(af_iucv_dev);
 	if (err)
-		goto out_driver;
+		goto out_iucv_dev;
 	return 0;
 
+out_iucv_dev:
+	put_device(af_iucv_dev);
 out_driver:
 	driver_unregister(&af_iucv_driver);
 out_iucv:
-- 
2.14.3


From d7f50f09b84e32371b064e4b2e1d6f89831c9141 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Wed, 14 Mar 2018 21:10:23 +0100
Subject: [PATCH 29/43] netlink: avoid a double skb free in genlmsg_mcast()

[ Upstream commit 02a2385f37a7c6594c9d89b64c4a1451276f08eb ]

nlmsg_multicast() consumes always the skb, thus the original skb must be
freed only when this function is called with a clone.

Fixes: cb9f7a9a5c96 ("netlink: ensure to loop over all netns in genlmsg_multicast_allns()")
Reported-by: Ben Hutchings <ben.hutchings@codethink.co.uk>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/genetlink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 6f02499ef007..b9ce82c9440f 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -1106,7 +1106,7 @@ static int genlmsg_mcast(struct sk_buff *skb, u32 portid, unsigned long group,
 	if (!err)
 		delivered = true;
 	else if (err != -ESRCH)
-		goto error;
+		return err;
 	return delivered ? 0 : -ESRCH;
  error:
 	kfree_skb(skb);
-- 
2.14.3


From 90206cd6b31007cdc86efe8ac870dc46c44bf378 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Fri, 16 Feb 2018 11:03:03 -0800
Subject: [PATCH 30/43] net: Only honor ifindex in IP_PKTINFO if non-0

[ Upstream commit 2cbb4ea7de167b02ffa63e9cdfdb07a7e7094615 ]

Only allow ifindex from IP_PKTINFO to override SO_BINDTODEVICE settings
if the index is actually set in the message.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_sockglue.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index f56aab54e0c8..1e70ed5244ea 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -258,7 +258,8 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc,
 			src_info = (struct in6_pktinfo *)CMSG_DATA(cmsg);
 			if (!ipv6_addr_v4mapped(&src_info->ipi6_addr))
 				return -EINVAL;
-			ipc->oif = src_info->ipi6_ifindex;
+			if (src_info->ipi6_ifindex)
+				ipc->oif = src_info->ipi6_ifindex;
 			ipc->addr = src_info->ipi6_addr.s6_addr32[3];
 			continue;
 		}
@@ -288,7 +289,8 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc,
 			if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct in_pktinfo)))
 				return -EINVAL;
 			info = (struct in_pktinfo *)CMSG_DATA(cmsg);
-			ipc->oif = info->ipi_ifindex;
+			if (info->ipi_ifindex)
+				ipc->oif = info->ipi_ifindex;
 			ipc->addr = info->ipi_spec_dst.s_addr;
 			break;
 		}
-- 
2.14.3


From 176c1152bab9d7006c9f66e359c96dbe62cfe132 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 13 Mar 2018 14:45:07 -0700
Subject: [PATCH 31/43] net: systemport: Rewrite __bcm_sysport_tx_reclaim()

[ Upstream commit 484d802d0f2f29c335563fcac2a8facf174a1bbc ]

There is no need for complex checking between the last consumed index
and current consumed index, a simple subtraction will do.

This also eliminates the possibility of a permanent transmit queue stall
under the following conditions:

- one CPU bursts ring->size worth of traffic (up to 256 buffers), to the
  point where we run out of free descriptors, so we stop the transmit
  queue at the end of bcm_sysport_xmit()

- because of our locking, we have the transmit process disable
  interrupts which means we can be blocking the TX reclamation process

- when TX reclamation finally runs, we will be computing the difference
  between ring->c_index (last consumed index by SW) and what the HW
  reports through its register

- this register is masked with (ring->size - 1) = 0xff, which will lead
  to stripping the upper bits of the index (register is 16-bits wide)

- we will be computing last_tx_cn as 0, which means there is no work to
  be done, and we never wake-up the transmit queue, leaving it
  permanently disabled

A practical example is e.g: ring->c_index aka last_c_index = 12, we
pushed 256 entries, HW consumer index = 268, we mask it with 0xff = 12,
so last_tx_cn == 0, nothing happens.

Fixes: 80105befdb4b ("net: systemport: add Broadcom SYSTEMPORT Ethernet MAC driver")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bcmsysport.c | 33 ++++++++++++++----------------
 drivers/net/ethernet/broadcom/bcmsysport.h |  2 +-
 2 files changed, 16 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index eb441e5e2cd8..1e856e8b9a92 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -855,10 +855,12 @@ static void bcm_sysport_tx_reclaim_one(struct bcm_sysport_tx_ring *ring,
 static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv,
 					     struct bcm_sysport_tx_ring *ring)
 {
-	unsigned int c_index, last_c_index, last_tx_cn, num_tx_cbs;
 	unsigned int pkts_compl = 0, bytes_compl = 0;
 	struct net_device *ndev = priv->netdev;
+	unsigned int txbds_processed = 0;
 	struct bcm_sysport_cb *cb;
+	unsigned int txbds_ready;
+	unsigned int c_index;
 	u32 hw_ind;
 
 	/* Clear status before servicing to reduce spurious interrupts */
@@ -871,29 +873,23 @@ static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv,
 	/* Compute how many descriptors have been processed since last call */
 	hw_ind = tdma_readl(priv, TDMA_DESC_RING_PROD_CONS_INDEX(ring->index));
 	c_index = (hw_ind >> RING_CONS_INDEX_SHIFT) & RING_CONS_INDEX_MASK;
-	ring->p_index = (hw_ind & RING_PROD_INDEX_MASK);
-
-	last_c_index = ring->c_index;
-	num_tx_cbs = ring->size;
-
-	c_index &= (num_tx_cbs - 1);
-
-	if (c_index >= last_c_index)
-		last_tx_cn = c_index - last_c_index;
-	else
-		last_tx_cn = num_tx_cbs - last_c_index + c_index;
+	txbds_ready = (c_index - ring->c_index) & RING_CONS_INDEX_MASK;
 
 	netif_dbg(priv, tx_done, ndev,
-		  "ring=%d c_index=%d last_tx_cn=%d last_c_index=%d\n",
-		  ring->index, c_index, last_tx_cn, last_c_index);
+		  "ring=%d old_c_index=%u c_index=%u txbds_ready=%u\n",
+		  ring->index, ring->c_index, c_index, txbds_ready);
 
-	while (last_tx_cn-- > 0) {
-		cb = ring->cbs + last_c_index;
+	while (txbds_processed < txbds_ready) {
+		cb = &ring->cbs[ring->clean_index];
 		bcm_sysport_tx_reclaim_one(ring, cb, &bytes_compl, &pkts_compl);
 
 		ring->desc_count++;
-		last_c_index++;
-		last_c_index &= (num_tx_cbs - 1);
+		txbds_processed++;
+
+		if (likely(ring->clean_index < ring->size - 1))
+			ring->clean_index++;
+		else
+			ring->clean_index = 0;
 	}
 
 	u64_stats_update_begin(&priv->syncp);
@@ -1406,6 +1402,7 @@ static int bcm_sysport_init_tx_ring(struct bcm_sysport_priv *priv,
 	netif_tx_napi_add(priv->netdev, &ring->napi, bcm_sysport_tx_poll, 64);
 	ring->index = index;
 	ring->size = size;
+	ring->clean_index = 0;
 	ring->alloc_size = ring->size;
 	ring->desc_cpu = p;
 	ring->desc_count = ring->size;
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h
index 82e401df199e..a2006f5fc26f 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.h
+++ b/drivers/net/ethernet/broadcom/bcmsysport.h
@@ -706,7 +706,7 @@ struct bcm_sysport_tx_ring {
 	unsigned int	desc_count;	/* Number of descriptors */
 	unsigned int	curr_desc;	/* Current descriptor */
 	unsigned int	c_index;	/* Last consumer index */
-	unsigned int	p_index;	/* Current producer index */
+	unsigned int	clean_index;	/* Current clean index */
 	struct bcm_sysport_cb *cbs;	/* Transmit control blocks */
 	struct dma_desc	*desc_cpu;	/* CPU view of the descriptor */
 	struct bcm_sysport_priv *priv;	/* private context backpointer */
-- 
2.14.3


From ce93898b0165557d22d3613bbeb9a4228ec7f24f Mon Sep 17 00:00:00 2001
From: Michal Kalderon <Michal.Kalderon@cavium.com>
Date: Wed, 14 Mar 2018 14:56:53 +0200
Subject: [PATCH 32/43] qede: Fix qedr link update

[ Upstream commit 4609adc27175839408359822523de7247d56c87f ]

Link updates were not reported to qedr correctly.
Leading to cases where a link could be down, but qedr
would see it as up.
In addition, once qede was loaded, link state would be up,
regardless of the actual link state.

Signed-off-by: Michal Kalderon <michal.kalderon@cavium.com>
Signed-off-by: Ariel Elior <ariel.elior@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qede/qede_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index e5ee9f274a71..6eab2c632c75 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -2066,8 +2066,6 @@ static int qede_load(struct qede_dev *edev, enum qede_load_mode mode,
 	link_params.link_up = true;
 	edev->ops->common->set_link(edev->cdev, &link_params);
 
-	qede_rdma_dev_event_open(edev);
-
 	edev->state = QEDE_STATE_OPEN;
 
 	DP_INFO(edev, "Ending successfully qede load\n");
@@ -2168,12 +2166,14 @@ static void qede_link_update(void *dev, struct qed_link_output *link)
 			DP_NOTICE(edev, "Link is up\n");
 			netif_tx_start_all_queues(edev->ndev);
 			netif_carrier_on(edev->ndev);
+			qede_rdma_dev_event_open(edev);
 		}
 	} else {
 		if (netif_carrier_ok(edev->ndev)) {
 			DP_NOTICE(edev, "Link is down\n");
 			netif_tx_disable(edev->ndev);
 			netif_carrier_off(edev->ndev);
+			qede_rdma_dev_event_close(edev);
 		}
 	}
 }
-- 
2.14.3


From 04c51bd3c17914b951155a592b28d7b8c0f7023c Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Wed, 14 Mar 2018 13:32:09 -0700
Subject: [PATCH 33/43] skbuff: Fix not waking applications when errors are
 enqueued

[ Upstream commit 6e5d58fdc9bedd0255a8781b258f10bbdc63e975 ]

When errors are enqueued to the error queue via sock_queue_err_skb()
function, it is possible that the waiting application is not notified.

Calling 'sk->sk_data_ready()' would not notify applications that
selected only POLLERR events in poll() (for example).

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: Randy E. Witt <randy.e.witt@intel.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index cc811add68c6..564beb7e6d1c 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4171,7 +4171,7 @@ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
 
 	skb_queue_tail(&sk->sk_error_queue, skb);
 	if (!sock_flag(sk, SOCK_DEAD))
-		sk->sk_data_ready(sk);
+		sk->sk_error_report(sk);
 	return 0;
 }
 EXPORT_SYMBOL(sock_queue_err_skb);
-- 
2.14.3


From 88c96d5b0812b0ca418f32effe7457bda90f4c03 Mon Sep 17 00:00:00 2001
From: Arkadi Sharshevsky <arkadis@mellanox.com>
Date: Thu, 8 Mar 2018 12:42:10 +0200
Subject: [PATCH 34/43] team: Fix double free in error path

[ Upstream commit cbcc607e18422555db569b593608aec26111cb0b ]

The __send_and_alloc_skb() receives a skb ptr as a parameter but in
case it fails the skb is not valid:
- Send failed and released the skb internally.
- Allocation failed.

The current code tries to release the skb in case of failure which
causes redundant freeing.

Fixes: 9b00cf2d1024 ("team: implement multipart netlink messages for options transfers")
Signed-off-by: Arkadi Sharshevsky <arkadis@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index ae53e899259f..23cd41c82210 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -2394,7 +2394,7 @@ static int team_nl_send_options_get(struct team *team, u32 portid, u32 seq,
 	if (!nlh) {
 		err = __send_and_alloc_skb(&skb, team, portid, send_func);
 		if (err)
-			goto errout;
+			return err;
 		goto send_done;
 	}
 
@@ -2680,7 +2680,7 @@ static int team_nl_send_port_list_get(struct team *team, u32 portid, u32 seq,
 	if (!nlh) {
 		err = __send_and_alloc_skb(&skb, team, portid, send_func);
 		if (err)
-			goto errout;
+			return err;
 		goto send_done;
 	}
 
-- 
2.14.3


From 37446addd600cf8a77ab448c2777d1c62f2b3cf5 Mon Sep 17 00:00:00 2001
From: Madalin Bucur <madalin.bucur@nxp.com>
Date: Wed, 14 Mar 2018 08:37:28 -0500
Subject: [PATCH 35/43] soc/fsl/qbman: fix issue in qman_delete_cgr_safe()

[ Upstream commit 96f413f47677366e0ae03797409bfcc4151dbf9e ]

The wait_for_completion() call in qman_delete_cgr_safe()
was triggering a scheduling while atomic bug, replacing the
kthread with a smp_call_function_single() call to fix it.

Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: Roy Pledge <roy.pledge@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/soc/fsl/qbman/qman.c | 28 +++++-----------------------
 1 file changed, 5 insertions(+), 23 deletions(-)

diff --git a/drivers/soc/fsl/qbman/qman.c b/drivers/soc/fsl/qbman/qman.c
index 18eefc3f1abe..0c6065dba48a 100644
--- a/drivers/soc/fsl/qbman/qman.c
+++ b/drivers/soc/fsl/qbman/qman.c
@@ -2414,39 +2414,21 @@ struct cgr_comp {
 	struct completion completion;
 };
 
-static int qman_delete_cgr_thread(void *p)
+static void qman_delete_cgr_smp_call(void *p)
 {
-	struct cgr_comp *cgr_comp = (struct cgr_comp *)p;
-	int ret;
-
-	ret = qman_delete_cgr(cgr_comp->cgr);
-	complete(&cgr_comp->completion);
-
-	return ret;
+	qman_delete_cgr((struct qman_cgr *)p);
 }
 
 void qman_delete_cgr_safe(struct qman_cgr *cgr)
 {
-	struct task_struct *thread;
-	struct cgr_comp cgr_comp;
-
 	preempt_disable();
 	if (qman_cgr_cpus[cgr->cgrid] != smp_processor_id()) {
-		init_completion(&cgr_comp.completion);
-		cgr_comp.cgr = cgr;
-		thread = kthread_create(qman_delete_cgr_thread, &cgr_comp,
-					"cgr_del");
-
-		if (IS_ERR(thread))
-			goto out;
-
-		kthread_bind(thread, qman_cgr_cpus[cgr->cgrid]);
-		wake_up_process(thread);
-		wait_for_completion(&cgr_comp.completion);
+		smp_call_function_single(qman_cgr_cpus[cgr->cgrid],
+					 qman_delete_cgr_smp_call, cgr, true);
 		preempt_enable();
 		return;
 	}
-out:
+
 	qman_delete_cgr(cgr);
 	preempt_enable();
 }
-- 
2.14.3


From b28018f4203b1da3da233505a034e6743f546482 Mon Sep 17 00:00:00 2001
From: Madalin Bucur <madalin.bucur@nxp.com>
Date: Wed, 14 Mar 2018 08:37:29 -0500
Subject: [PATCH 36/43] dpaa_eth: fix error in dpaa_remove()

[ Upstream commit 88075256ee817041d68c2387f29065b5cb2b342a ]

The recent changes that make the driver probing compatible with DSA
were not propagated in the dpa_remove() function, breaking the
module unload function. Using the proper device to address the issue.

Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 42258060f142..786052c91fbc 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -2860,7 +2860,7 @@ static int dpaa_remove(struct platform_device *pdev)
 	struct device *dev;
 	int err;
 
-	dev = &pdev->dev;
+	dev = pdev->dev.parent;
 	net_dev = dev_get_drvdata(dev);
 
 	priv = netdev_priv(net_dev);
-- 
2.14.3


From 8f2a0a2d6e2b9d710707fef99c99467f1be98f7c Mon Sep 17 00:00:00 2001
From: Camelia Groza <camelia.groza@nxp.com>
Date: Wed, 14 Mar 2018 08:37:30 -0500
Subject: [PATCH 37/43] dpaa_eth: remove duplicate initialization

[ Upstream commit 565186362b73226a288830abe595f05f0cec0bbc ]

The fd_format has already been initialized at this point.

Signed-off-by: Camelia Groza <camelia.groza@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 786052c91fbc..6b92d47af1f7 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -2292,7 +2292,6 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal,
 	vaddr = phys_to_virt(addr);
 	prefetch(vaddr + qm_fd_get_offset(fd));
 
-	fd_format = qm_fd_get_format(fd);
 	/* The only FD types that we may receive are contig and S/G */
 	WARN_ON((fd_format != qm_fd_contig) && (fd_format != qm_fd_sg));
 
-- 
2.14.3


From 3b414bda1a95850ccaff77cc85376f6aeb82ecf0 Mon Sep 17 00:00:00 2001
From: Camelia Groza <camelia.groza@nxp.com>
Date: Wed, 14 Mar 2018 08:37:31 -0500
Subject: [PATCH 38/43] dpaa_eth: increment the RX dropped counter when needed

[ Upstream commit e4d1b37c17d000a3da9368a3e260fb9ea4927c25 ]

Signed-off-by: Camelia Groza <camelia.groza@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 6b92d47af1f7..68cbf4cfd4d4 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -2324,8 +2324,10 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal,
 
 	skb_len = skb->len;
 
-	if (unlikely(netif_receive_skb(skb) == NET_RX_DROP))
+	if (unlikely(netif_receive_skb(skb) == NET_RX_DROP)) {
+		percpu_stats->rx_dropped++;
 		return qman_cb_dqrr_consume;
+	}
 
 	percpu_stats->rx_packets++;
 	percpu_stats->rx_bytes += skb_len;
-- 
2.14.3


From c10225c5de290431d7d80d89a4359bc378670e1c Mon Sep 17 00:00:00 2001
From: Camelia Groza <camelia.groza@nxp.com>
Date: Wed, 14 Mar 2018 08:37:32 -0500
Subject: [PATCH 39/43] dpaa_eth: remove duplicate increment of the tx_errors
 counter

[ Upstream commit 82d141cd19d088ee41feafde4a6f86eeb40d93c5 ]

The tx_errors counter is incremented by the dpaa_xmit caller.

Signed-off-by: Camelia Groza <camelia.groza@nxp.com>
Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 68cbf4cfd4d4..4f6e9d3470d5 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -2022,7 +2022,6 @@ static inline int dpaa_xmit(struct dpaa_priv *priv,
 	}
 
 	if (unlikely(err < 0)) {
-		percpu_stats->tx_errors++;
 		percpu_stats->tx_fifo_errors++;
 		return err;
 	}
-- 
2.14.3


From 5c75aa7bc2a9ddd4387db940c1a2c4126983c1f3 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Tue, 20 Mar 2018 07:59:12 +0100
Subject: [PATCH 40/43] s390/qeth: free netdevice when removing a card

[ Upstream commit 6be687395b3124f002a653c1a50b3260222b3cd7 ]

On removal, a qeth card's netdevice is currently not properly freed
because the call chain looks as follows:

qeth_core_remove_device(card)
	lx_remove_device(card)
		unregister_netdev(card->dev)
		card->dev = NULL			!!!
	qeth_core_free_card(card)
		if (card->dev)				!!!
			free_netdev(card->dev)

Fix it by free'ing the netdev straight after unregistering. This also
fixes the sysfs-driven layer switch case (qeth_dev_layer2_store()),
where the need to free the current netdevice was not considered at all.

Note that free_netdev() takes care of the netif_napi_del() for us too.

Fixes: 4a71df50047f ("qeth: new qeth device driver")
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Reviewed-by: Ursula Braun <ubraun@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 2 --
 drivers/s390/net/qeth_l2_main.c   | 2 +-
 drivers/s390/net/qeth_l3_main.c   | 2 +-
 3 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 145b57762d8f..c97cddf31a70 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -5061,8 +5061,6 @@ static void qeth_core_free_card(struct qeth_card *card)
 	QETH_DBF_HEX(SETUP, 2, &card, sizeof(void *));
 	qeth_clean_channel(&card->read);
 	qeth_clean_channel(&card->write);
-	if (card->dev)
-		free_netdev(card->dev);
 	qeth_free_qdio_buffers(card);
 	unregister_service_level(&card->qeth_service_level);
 	kfree(card);
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 5a973ebcb13c..521293b1f4fa 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -935,8 +935,8 @@ static void qeth_l2_remove_device(struct ccwgroup_device *cgdev)
 		qeth_l2_set_offline(cgdev);
 
 	if (card->dev) {
-		netif_napi_del(&card->napi);
 		unregister_netdev(card->dev);
+		free_netdev(card->dev);
 		card->dev = NULL;
 	}
 	return;
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 96576e729222..1c62cbbaa66f 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -3046,8 +3046,8 @@ static void qeth_l3_remove_device(struct ccwgroup_device *cgdev)
 		qeth_l3_set_offline(cgdev);
 
 	if (card->dev) {
-		netif_napi_del(&card->napi);
 		unregister_netdev(card->dev);
+		free_netdev(card->dev);
 		card->dev = NULL;
 	}
 
-- 
2.14.3


From d473f89a921adb1b05096efa7b5ae368db231fe4 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Tue, 20 Mar 2018 07:59:13 +0100
Subject: [PATCH 41/43] s390/qeth: when thread completes, wake up all waiters

[ Upstream commit 1063e432bb45be209427ed3f1ca3908e4aa3c7d7 ]

qeth_wait_for_threads() is potentially called by multiple users, make
sure to notify all of them after qeth_clear_thread_running_bit()
adjusted the thread_running_mask. With no timeout, callers would
otherwise stall.

Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index c97cddf31a70..36cc9b6d3513 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -961,7 +961,7 @@ void qeth_clear_thread_running_bit(struct qeth_card *card, unsigned long thread)
 	spin_lock_irqsave(&card->thread_mask_lock, flags);
 	card->thread_running_mask &= ~thread;
 	spin_unlock_irqrestore(&card->thread_mask_lock, flags);
-	wake_up(&card->wait_q);
+	wake_up_all(&card->wait_q);
 }
 EXPORT_SYMBOL_GPL(qeth_clear_thread_running_bit);
 
-- 
2.14.3


From cd247ae89e7cce8a7eca64fa4a4ca3b793bf0c23 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Tue, 20 Mar 2018 07:59:14 +0100
Subject: [PATCH 42/43] s390/qeth: lock read device while queueing next buffer

[ Upstream commit 17bf8c9b3d499d5168537c98b61eb7a1fcbca6c2 ]

For calling ccw_device_start(), issue_next_read() needs to hold the
device's ccwlock.
This is satisfied for the IRQ handler path (where qeth_irq() gets called
under the ccwlock), but we need explicit locking for the initial call by
the MPC initialization.

Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 36cc9b6d3513..cb69f2d674ae 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -526,8 +526,7 @@ static inline int qeth_is_cq(struct qeth_card *card, unsigned int queue)
 	    queue == card->qdio.no_in_queues - 1;
 }
 
-
-static int qeth_issue_next_read(struct qeth_card *card)
+static int __qeth_issue_next_read(struct qeth_card *card)
 {
 	int rc;
 	struct qeth_cmd_buffer *iob;
@@ -558,6 +557,17 @@ static int qeth_issue_next_read(struct qeth_card *card)
 	return rc;
 }
 
+static int qeth_issue_next_read(struct qeth_card *card)
+{
+	int ret;
+
+	spin_lock_irq(get_ccwdev_lock(CARD_RDEV(card)));
+	ret = __qeth_issue_next_read(card);
+	spin_unlock_irq(get_ccwdev_lock(CARD_RDEV(card)));
+
+	return ret;
+}
+
 static struct qeth_reply *qeth_alloc_reply(struct qeth_card *card)
 {
 	struct qeth_reply *reply;
@@ -1183,7 +1193,7 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm,
 		return;
 	if (channel == &card->read &&
 	    channel->state == CH_STATE_UP)
-		qeth_issue_next_read(card);
+		__qeth_issue_next_read(card);
 
 	iob = channel->iob;
 	index = channel->buf_no;
-- 
2.14.3


From 594c2a491af58cf76a2499f4c5cd10c33753e474 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Tue, 20 Mar 2018 07:59:15 +0100
Subject: [PATCH 43/43] s390/qeth: on channel error, reject further cmd
 requests

[ Upstream commit a6c3d93963e4b333c764fde69802c3ea9eaa9d5c ]

When the IRQ handler determines that one of the cmd IO channels has
failed and schedules recovery, block any further cmd requests from
being submitted. The request would inevitably stall, and prevent the
recovery from making progress until the request times out.

This sort of error was observed after Live Guest Relocation, where
the pending IO on the READ channel intentionally gets terminated to
kick-start recovery. Simultaneously the guest executed SIOCETHTOOL,
triggering qeth to issue a QUERY CARD INFO command. The command
then stalled in the inoperabel WRITE channel.

Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index cb69f2d674ae..939b5b5e97ef 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -1175,6 +1175,7 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm,
 		}
 		rc = qeth_get_problem(cdev, irb);
 		if (rc) {
+			card->read_or_write_problem = 1;
 			qeth_clear_ipacmd_list(card);
 			qeth_schedule_recovery(card);
 			goto out;
-- 
2.14.3


[-- Attachment #3: net_415.mbox --]
[-- Type: Application/Octet-Stream, Size: 116494 bytes --]

From 7c1feab129d114890cd4fa754133cc765c68c357 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Mon, 12 Mar 2018 16:00:40 -0700
Subject: [PATCH 01/53] net: dsa: Fix dsa_is_user_port() test inversion

[ Upstream commit 5a9f8df68ee6927f21dd3f2c75c16feb8b53a9e8 ]

During the conversion to dsa_is_user_port(), a condition ended up being
reversed, which would prevent the creation of any user port when using
the legacy binding and/or platform data, fix that.

Fixes: 4a5b85ffe2a0 ("net: dsa: use dsa_is_user_port everywhere")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/legacy.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/dsa/legacy.c b/net/dsa/legacy.c
index 84611d7fcfa2..3c9cee268b8a 100644
--- a/net/dsa/legacy.c
+++ b/net/dsa/legacy.c
@@ -194,7 +194,7 @@ static int dsa_switch_setup_one(struct dsa_switch *ds,
 		ds->ports[i].dn = cd->port_dn[i];
 		ds->ports[i].cpu_dp = dst->cpu_dp;
 
-		if (dsa_is_user_port(ds, i))
+		if (!dsa_is_user_port(ds, i))
 			continue;
 
 		ret = dsa_slave_create(&ds->ports[i]);
-- 
2.14.3


From 8f36463049f5ea064c5a233ad8bc0f609af3f14f Mon Sep 17 00:00:00 2001
From: zhangliping <zhangliping02@baidu.com>
Date: Fri, 9 Mar 2018 10:08:50 +0800
Subject: [PATCH 02/53] openvswitch: meter: fix the incorrect calculation of
 max delta_t

[ Usptream commit ddc502dfed600bff0b61d899f70d95b76223fdfc ]

Max delat_t should be the full_bucket/rate instead of the full_bucket.
Also report EINVAL if the rate is zero.

Fixes: 96fbc13d7e77 ("openvswitch: Add meter infrastructure")
Cc: Andy Zhou <azhou@ovn.org>
Signed-off-by: zhangliping <zhangliping02@baidu.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/meter.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c
index 3fbfc78991ac..0d961f09d0c7 100644
--- a/net/openvswitch/meter.c
+++ b/net/openvswitch/meter.c
@@ -242,14 +242,20 @@ static struct dp_meter *dp_meter_create(struct nlattr **a)
 
 		band->type = nla_get_u32(attr[OVS_BAND_ATTR_TYPE]);
 		band->rate = nla_get_u32(attr[OVS_BAND_ATTR_RATE]);
+		if (band->rate == 0) {
+			err = -EINVAL;
+			goto exit_free_meter;
+		}
+
 		band->burst_size = nla_get_u32(attr[OVS_BAND_ATTR_BURST]);
 		/* Figure out max delta_t that is enough to fill any bucket.
 		 * Keep max_delta_t size to the bucket units:
 		 * pkts => 1/1000 packets, kilobits => bits.
+		 *
+		 * Start with a full bucket.
 		 */
-		band_max_delta_t = (band->burst_size + band->rate) * 1000;
-		/* Start with a full bucket. */
-		band->bucket = band_max_delta_t;
+		band->bucket = (band->burst_size + band->rate) * 1000;
+		band_max_delta_t = band->bucket / band->rate;
 		if (band_max_delta_t > meter->max_delta_t)
 			meter->max_delta_t = band_max_delta_t;
 		band++;
-- 
2.14.3


From 3a4535422443fee6bc271be5bd5908171a10dfb4 Mon Sep 17 00:00:00 2001
From: Michal Kalderon <Michal.Kalderon@cavium.com>
Date: Wed, 14 Mar 2018 14:49:27 +0200
Subject: [PATCH 03/53] qed: Fix MPA unalign flow in case header is split
 across two packets.

[ Upstream commit 933e8c91b9f5a2f504f6da1f069c410449b9f4b9 ]

There is a corner case in the MPA unalign flow where a FPDU header is
split over two tcp segments. The length of the first fragment in this
case was not initialized properly and should be '1'

Fixes: c7d1d839 ("qed: Add support for MPA header being split over two tcp packets")

Signed-off-by: Michal Kalderon <Michal.Kalderon@cavium.com>
Signed-off-by: Ariel Elior <Ariel.Elior@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_iwarp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
index 409041eab189..a71339ca23e5 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
@@ -1906,8 +1906,8 @@ qed_iwarp_update_fpdu_length(struct qed_hwfn *p_hwfn,
 		/* Missing lower byte is now available */
 		mpa_len = fpdu->fpdu_length | *mpa_data;
 		fpdu->fpdu_length = QED_IWARP_FPDU_LEN_WITH_PAD(mpa_len);
-		fpdu->mpa_frag_len = fpdu->fpdu_length;
 		/* one byte of hdr */
+		fpdu->mpa_frag_len = 1;
 		fpdu->incomplete_bytes = fpdu->fpdu_length - 1;
 		DP_VERBOSE(p_hwfn,
 			   QED_MSG_RDMA,
-- 
2.14.3


From eef74ecf2a6a7f4ac681ce48647c8f5a6e171a9f Mon Sep 17 00:00:00 2001
From: Soheil Hassas Yeganeh <soheil@google.com>
Date: Tue, 6 Mar 2018 17:15:12 -0500
Subject: [PATCH 04/53] tcp: purge write queue upon aborting the connection

[ Upstream commit e05836ac07c77dd90377f8c8140bce2a44af5fe7 ]

When the connection is aborted, there is no point in
keeping the packets on the write queue until the connection
is closed.

Similar to a27fd7a8ed38 ('tcp: purge write queue upon RST'),
this is essential for a correct MSG_ZEROCOPY implementation,
because userspace cannot call close(fd) before receiving
zerocopy signals even when the connection is aborted.

Fixes: f214f915e7db ("tcp: enable MSG_ZEROCOPY")
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c       | 1 +
 net/ipv4/tcp_timer.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index c821f5d68720..2eb91b97a062 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3542,6 +3542,7 @@ int tcp_abort(struct sock *sk, int err)
 
 	bh_unlock_sock(sk);
 	local_bh_enable();
+	tcp_write_queue_purge(sk);
 	release_sock(sk);
 	return 0;
 }
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 388158c9d9f6..c721140a7d79 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -34,6 +34,7 @@ static void tcp_write_err(struct sock *sk)
 	sk->sk_err = sk->sk_err_soft ? : ETIMEDOUT;
 	sk->sk_error_report(sk);
 
+	tcp_write_queue_purge(sk);
 	tcp_done(sk);
 	__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONTIMEOUT);
 }
-- 
2.14.3


From 16bb63d1887c0688d510acad66479241009bc41a Mon Sep 17 00:00:00 2001
From: Michal Kalderon <Michal.Kalderon@cavium.com>
Date: Wed, 14 Mar 2018 14:49:28 +0200
Subject: [PATCH 05/53] qed: Fix non TCP packets should be dropped on iWARP ll2
 connection

[ Upstream commit 16da09047d3fb991dc48af41f6d255fd578e8ca2 ]

FW workaround. The iWARP LL2 connection did not expect TCP packets
to arrive on it's connection. The fix drops any non-tcp packets

Fixes b5c29ca ("qed: iWARP CM - setup a ll2 connection for handling
SYN packets")

Signed-off-by: Michal Kalderon <Michal.Kalderon@cavium.com>
Signed-off-by: Ariel Elior <Ariel.Elior@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_iwarp.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
index a71339ca23e5..fba7f5c34b85 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
@@ -1681,6 +1681,13 @@ qed_iwarp_parse_rx_pkt(struct qed_hwfn *p_hwfn,
 	iph = (struct iphdr *)((u8 *)(ethh) + eth_hlen);
 
 	if (eth_type == ETH_P_IP) {
+		if (iph->protocol != IPPROTO_TCP) {
+			DP_NOTICE(p_hwfn,
+				  "Unexpected ip protocol on ll2 %x\n",
+				  iph->protocol);
+			return -EINVAL;
+		}
+
 		cm_info->local_ip[0] = ntohl(iph->daddr);
 		cm_info->remote_ip[0] = ntohl(iph->saddr);
 		cm_info->ip_version = TCP_IPV4;
@@ -1689,6 +1696,14 @@ qed_iwarp_parse_rx_pkt(struct qed_hwfn *p_hwfn,
 		*payload_len = ntohs(iph->tot_len) - ip_hlen;
 	} else if (eth_type == ETH_P_IPV6) {
 		ip6h = (struct ipv6hdr *)iph;
+
+		if (ip6h->nexthdr != IPPROTO_TCP) {
+			DP_NOTICE(p_hwfn,
+				  "Unexpected ip protocol on ll2 %x\n",
+				  iph->protocol);
+			return -EINVAL;
+		}
+
 		for (i = 0; i < 4; i++) {
 			cm_info->local_ip[i] =
 			    ntohl(ip6h->daddr.in6_u.u6_addr32[i]);
-- 
2.14.3


From 568e3d0118d5265d211ab8a93476dc97737ef509 Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Fri, 16 Mar 2018 17:08:34 -0500
Subject: [PATCH 06/53] sysfs: symlink: export sysfs_create_link_nowarn()

[ Upstream commit 2399ac42e762ab25c58420e25359b2921afdc55f ]

The sysfs_create_link_nowarn() is going to be used in phylib framework in
subsequent patch which can be built as module. Hence, export
sysfs_create_link_nowarn() to avoid build errors.

Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: Andrew Lunn <andrew@lunn.ch>
Fixes: a3995460491d ("net: phy: Relax error checking on sysfs_create_link()")
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 fs/sysfs/symlink.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/sysfs/symlink.c b/fs/sysfs/symlink.c
index aecb15f84557..808f018fa976 100644
--- a/fs/sysfs/symlink.c
+++ b/fs/sysfs/symlink.c
@@ -107,6 +107,7 @@ int sysfs_create_link_nowarn(struct kobject *kobj, struct kobject *target,
 {
 	return sysfs_do_create_link(kobj, target, name, 0);
 }
+EXPORT_SYMBOL_GPL(sysfs_create_link_nowarn);
 
 /**
  *	sysfs_delete_link - remove symlink in object's directory.
-- 
2.14.3


From 1f486dad326664a82e3795762fa726cfecd4401c Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Fri, 16 Mar 2018 17:08:35 -0500
Subject: [PATCH 07/53] net: phy: relax error checking when creating sysfs link
 netdev->phydev

[ Upstream commit 4414b3ed74be0e205e04e12cd83542a727d88255 ]

Some ethernet drivers (like TI CPSW) may connect and manage >1 Net PHYs per
one netdevice, as result such drivers will produce warning during system
boot and fail to connect second phy to netdevice when PHYLIB framework
will try to create sysfs link netdev->phydev for second PHY
in phy_attach_direct(), because sysfs link with the same name has been
created already for the first PHY. As result, second CPSW external
port will became unusable.

Fix it by relaxing error checking when PHYLIB framework is creating sysfs
link netdev->phydev in phy_attach_direct(), suppressing warning by using
sysfs_create_link_nowarn() and adding error message instead.
After this change links (phy->netdev and netdev->phy) creation failure is not
fatal any more and system can continue working, which fixes TI CPSW issue.

Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: Andrew Lunn <andrew@lunn.ch>
Fixes: a3995460491d ("net: phy: Relax error checking on sysfs_create_link()")
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index d312b314825e..a1e7ea4d4b16 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -999,10 +999,17 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
 	err = sysfs_create_link(&phydev->mdio.dev.kobj, &dev->dev.kobj,
 				"attached_dev");
 	if (!err) {
-		err = sysfs_create_link(&dev->dev.kobj, &phydev->mdio.dev.kobj,
-					"phydev");
-		if (err)
-			goto error;
+		err = sysfs_create_link_nowarn(&dev->dev.kobj,
+					       &phydev->mdio.dev.kobj,
+					       "phydev");
+		if (err) {
+			dev_err(&dev->dev, "could not add device link to %s err %d\n",
+				kobject_name(&phydev->mdio.dev.kobj),
+				err);
+			/* non-fatal - some net drivers can use one netdevice
+			 * with more then one phy
+			 */
+		}
 
 		phydev->sysfs_links = true;
 	}
-- 
2.14.3


From 91789a1195bda7812242160e4a857d4bbd66d916 Mon Sep 17 00:00:00 2001
From: Arkadi Sharshevsky <arkadis@mellanox.com>
Date: Sun, 18 Mar 2018 17:37:22 +0200
Subject: [PATCH 08/53] devlink: Remove redundant free on error path

[ Upstream commit 7fe4d6dcbcb43fe0282d4213fc52be178bb30e91 ]

The current code performs unneeded free. Remove the redundant skb freeing
during the error path.

Fixes: 1555d204e743 ("devlink: Support for pipeline debug (dpipe)")
Signed-off-by: Arkadi Sharshevsky <arkadis@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/devlink.c | 16 ++++------------
 1 file changed, 4 insertions(+), 12 deletions(-)

diff --git a/net/core/devlink.c b/net/core/devlink.c
index 7d430c1d9c3e..5ba973311025 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -1776,7 +1776,7 @@ static int devlink_dpipe_tables_fill(struct genl_info *info,
 	if (!nlh) {
 		err = devlink_dpipe_send_and_alloc_skb(&skb, info);
 		if (err)
-			goto err_skb_send_alloc;
+			return err;
 		goto send_done;
 	}
 
@@ -1785,7 +1785,6 @@ static int devlink_dpipe_tables_fill(struct genl_info *info,
 nla_put_failure:
 	err = -EMSGSIZE;
 err_table_put:
-err_skb_send_alloc:
 	genlmsg_cancel(skb, hdr);
 	nlmsg_free(skb);
 	return err;
@@ -2051,7 +2050,7 @@ static int devlink_dpipe_entries_fill(struct genl_info *info,
 					     table->counters_enabled,
 					     &dump_ctx);
 	if (err)
-		goto err_entries_dump;
+		return err;
 
 send_done:
 	nlh = nlmsg_put(dump_ctx.skb, info->snd_portid, info->snd_seq,
@@ -2059,16 +2058,10 @@ static int devlink_dpipe_entries_fill(struct genl_info *info,
 	if (!nlh) {
 		err = devlink_dpipe_send_and_alloc_skb(&dump_ctx.skb, info);
 		if (err)
-			goto err_skb_send_alloc;
+			return err;
 		goto send_done;
 	}
 	return genlmsg_reply(dump_ctx.skb, info);
-
-err_entries_dump:
-err_skb_send_alloc:
-	genlmsg_cancel(dump_ctx.skb, dump_ctx.hdr);
-	nlmsg_free(dump_ctx.skb);
-	return err;
 }
 
 static int devlink_nl_cmd_dpipe_entries_get(struct sk_buff *skb,
@@ -2207,7 +2200,7 @@ static int devlink_dpipe_headers_fill(struct genl_info *info,
 	if (!nlh) {
 		err = devlink_dpipe_send_and_alloc_skb(&skb, info);
 		if (err)
-			goto err_skb_send_alloc;
+			return err;
 		goto send_done;
 	}
 	return genlmsg_reply(skb, info);
@@ -2215,7 +2208,6 @@ static int devlink_dpipe_headers_fill(struct genl_info *info,
 nla_put_failure:
 	err = -EMSGSIZE;
 err_table_put:
-err_skb_send_alloc:
 	genlmsg_cancel(skb, hdr);
 	nlmsg_free(skb);
 	return err;
-- 
2.14.3


From 275ac8a305524c544f2ddbc4284d997d85dc2823 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@oracle.com>
Date: Thu, 8 Mar 2018 16:17:23 -0800
Subject: [PATCH 09/53] macvlan: filter out unsupported feature flags

[ Upstream commit 13fbcc8dc573482dd3f27568257fd7087f8935f4 ]

Adding a macvlan device on top of a lowerdev that supports
the xfrm offloads fails with a new regression:
  # ip link add link ens1f0 mv0 type macvlan
  RTNETLINK answers: Operation not permitted

Tracing down the failure shows that the macvlan device inherits
the NETIF_F_HW_ESP and NETIF_F_HW_ESP_TX_CSUM feature flags
from the lowerdev, but with no dev->xfrmdev_ops API filled
in, it doesn't actually support xfrm.  When the request is
made to add the new macvlan device, the XFRM listener for
NETDEV_REGISTER calls xfrm_api_check() which fails the new
registration because dev->xfrmdev_ops is NULL.

The macvlan creation succeeds when we filter out the ESP
feature flags in macvlan_fix_features(), so let's filter them
out like we're already filtering out ~NETIF_F_NETNS_LOCAL.
When XFRM support is added in the future, we can add the flags
into MACVLAN_FEATURES.

This same problem could crop up in the future with any other
new feature flags, so let's filter out any flags that aren't
defined as supported in macvlan.

Fixes: d77e38e612a0 ("xfrm: Add an IPsec hardware offloading API")
Reported-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Signed-off-by: Shannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macvlan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index a0f2be81d52e..4884f6149b0a 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -1036,7 +1036,7 @@ static netdev_features_t macvlan_fix_features(struct net_device *dev,
 	lowerdev_features &= (features | ~NETIF_F_LRO);
 	features = netdev_increment_features(lowerdev_features, features, mask);
 	features |= ALWAYS_ON_FEATURES;
-	features &= ~NETIF_F_NETNS_LOCAL;
+	features &= (ALWAYS_ON_FEATURES | MACVLAN_FEATURES);
 
 	return features;
 }
-- 
2.14.3


From 7c73120c8c300eb2d75b4ed18a67e5454e8ec53a Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 12 Mar 2018 14:54:23 +0100
Subject: [PATCH 10/53] net: ipv6: keep sk status consistent after datagram
 connect failure

[ Upstream commit 2f987a76a97773beafbc615b9c4d8fe79129a7f4 ]

On unsuccesful ip6_datagram_connect(), if the failure is caused by
ip6_datagram_dst_update(), the sk peer information are cleared, but
the sk->sk_state is preserved.

If the socket was already in an established status, the overall sk
status is inconsistent and fouls later checks in datagram code.

Fix this saving the old peer information and restoring them in
case of failure. This also aligns ipv6 datagram connect() behavior
with ipv4.

v1 -> v2:
 - added missing Fixes tag

Fixes: 85cb73ff9b74 ("net: ipv6: reset daddr and dport in sk if connect() fails")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/datagram.c | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index a1f918713006..29da4b6c9dd6 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -146,10 +146,12 @@ int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr,
 	struct sockaddr_in6	*usin = (struct sockaddr_in6 *) uaddr;
 	struct inet_sock	*inet = inet_sk(sk);
 	struct ipv6_pinfo	*np = inet6_sk(sk);
-	struct in6_addr		*daddr;
+	struct in6_addr		*daddr, old_daddr;
+	__be32			fl6_flowlabel = 0;
+	__be32			old_fl6_flowlabel;
+	__be32			old_dport;
 	int			addr_type;
 	int			err;
-	__be32			fl6_flowlabel = 0;
 
 	if (usin->sin6_family == AF_INET) {
 		if (__ipv6_only_sock(sk))
@@ -239,9 +241,13 @@ int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr,
 		}
 	}
 
+	/* save the current peer information before updating it */
+	old_daddr = sk->sk_v6_daddr;
+	old_fl6_flowlabel = np->flow_label;
+	old_dport = inet->inet_dport;
+
 	sk->sk_v6_daddr = *daddr;
 	np->flow_label = fl6_flowlabel;
-
 	inet->inet_dport = usin->sin6_port;
 
 	/*
@@ -251,11 +257,12 @@ int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr,
 
 	err = ip6_datagram_dst_update(sk, true);
 	if (err) {
-		/* Reset daddr and dport so that udp_v6_early_demux()
-		 * fails to find this socket
+		/* Restore the socket peer info, to keep it consistent with
+		 * the old socket state
 		 */
-		memset(&sk->sk_v6_daddr, 0, sizeof(sk->sk_v6_daddr));
-		inet->inet_dport = 0;
+		sk->sk_v6_daddr = old_daddr;
+		np->flow_label = old_fl6_flowlabel;
+		inet->inet_dport = old_dport;
 		goto out;
 	}
 
-- 
2.14.3


From f603cbc18bf3c5e09cd1ae7f21a831c8298cc163 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Mon, 19 Mar 2018 11:24:58 +0100
Subject: [PATCH 11/53] ipv6: old_dport should be a __be16 in
 __ip6_datagram_connect()

[ Upstream commit 5f2fb802eee1df0810b47ea251942fe3fd36589a ]

Fixes: 2f987a76a977 ("net: ipv6: keep sk status consistent after datagram connect failure")
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/datagram.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 29da4b6c9dd6..287112da3c06 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -149,7 +149,7 @@ int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr,
 	struct in6_addr		*daddr, old_daddr;
 	__be32			fl6_flowlabel = 0;
 	__be32			old_fl6_flowlabel;
-	__be32			old_dport;
+	__be16			old_dport;
 	int			addr_type;
 	int			err;
 
-- 
2.14.3


From 009056681ec36caadf692afc1c2a67ebb81e12f7 Mon Sep 17 00:00:00 2001
From: David Lebrun <dlebrun@google.com>
Date: Tue, 20 Mar 2018 14:44:56 +0000
Subject: [PATCH 12/53] ipv6: sr: fix NULL pointer dereference when setting
 encap source address

[ Upstream commit 8936ef7604c11b5d701580d779e0f5684abc7b68 ]

When using seg6 in encap mode, we call ipv6_dev_get_saddr() to set the
source address of the outer IPv6 header, in case none was specified.
Using skb->dev can lead to BUG() when it is in an inconsistent state.
This patch uses the net_device attached to the skb's dst instead.

[940807.667429] BUG: unable to handle kernel NULL pointer dereference at 000000000000047c
[940807.762427] IP: ipv6_dev_get_saddr+0x8b/0x1d0
[940807.815725] PGD 0 P4D 0
[940807.847173] Oops: 0000 [#1] SMP PTI
[940807.890073] Modules linked in:
[940807.927765] CPU: 6 PID: 0 Comm: swapper/6 Tainted: G        W        4.16.0-rc1-seg6bpf+ #2
[940808.028988] Hardware name: HP ProLiant DL120 G6/ProLiant DL120 G6, BIOS O26    09/06/2010
[940808.128128] RIP: 0010:ipv6_dev_get_saddr+0x8b/0x1d0
[940808.187667] RSP: 0018:ffff88043fd836b0 EFLAGS: 00010206
[940808.251366] RAX: 0000000000000005 RBX: ffff88042cb1c860 RCX: 00000000000000fe
[940808.338025] RDX: 00000000000002c0 RSI: ffff88042cb1c860 RDI: 0000000000004500
[940808.424683] RBP: ffff88043fd83740 R08: 0000000000000000 R09: ffffffffffffffff
[940808.511342] R10: 0000000000000040 R11: 0000000000000000 R12: ffff88042cb1c850
[940808.598012] R13: ffffffff8208e380 R14: ffff88042ac8da00 R15: 0000000000000002
[940808.684675] FS:  0000000000000000(0000) GS:ffff88043fd80000(0000) knlGS:0000000000000000
[940808.783036] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[940808.852975] CR2: 000000000000047c CR3: 00000004255fe000 CR4: 00000000000006e0
[940808.939634] Call Trace:
[940808.970041]  <IRQ>
[940808.995250]  ? ip6t_do_table+0x265/0x640
[940809.043341]  seg6_do_srh_encap+0x28f/0x300
[940809.093516]  ? seg6_do_srh+0x1a0/0x210
[940809.139528]  seg6_do_srh+0x1a0/0x210
[940809.183462]  seg6_output+0x28/0x1e0
[940809.226358]  lwtunnel_output+0x3f/0x70
[940809.272370]  ip6_xmit+0x2b8/0x530
[940809.313185]  ? ac6_proc_exit+0x20/0x20
[940809.359197]  inet6_csk_xmit+0x7d/0xc0
[940809.404173]  tcp_transmit_skb+0x548/0x9a0
[940809.453304]  __tcp_retransmit_skb+0x1a8/0x7a0
[940809.506603]  ? ip6_default_advmss+0x40/0x40
[940809.557824]  ? tcp_current_mss+0x24/0x90
[940809.605925]  tcp_retransmit_skb+0xd/0x80
[940809.654016]  tcp_xmit_retransmit_queue.part.17+0xf9/0x210
[940809.719797]  tcp_ack+0xa47/0x1110
[940809.760612]  tcp_rcv_established+0x13c/0x570
[940809.812865]  tcp_v6_do_rcv+0x151/0x3d0
[940809.858879]  tcp_v6_rcv+0xa5c/0xb10
[940809.901770]  ? seg6_output+0xdd/0x1e0
[940809.946745]  ip6_input_finish+0xbb/0x460
[940809.994837]  ip6_input+0x74/0x80
[940810.034612]  ? ip6_rcv_finish+0xb0/0xb0
[940810.081663]  ipv6_rcv+0x31c/0x4c0
...

Fixes: 6c8702c60b886 ("ipv6: sr: add support for SRH encapsulation and injection with lwtunnels")
Reported-by: Tom Herbert <tom@quantonium.net>
Signed-off-by: David Lebrun <dlebrun@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/seg6_iptunnel.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index bd6cc688bd19..37e76ca7b7cb 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -93,7 +93,8 @@ static void set_tun_src(struct net *net, struct net_device *dev,
 /* encapsulate an IPv6 packet within an outer IPv6 header with a given SRH */
 int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
 {
-	struct net *net = dev_net(skb_dst(skb)->dev);
+	struct dst_entry *dst = skb_dst(skb);
+	struct net *net = dev_net(dst->dev);
 	struct ipv6hdr *hdr, *inner_hdr;
 	struct ipv6_sr_hdr *isrh;
 	int hdrlen, tot_len, err;
@@ -134,7 +135,7 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
 	isrh->nexthdr = proto;
 
 	hdr->daddr = isrh->segments[isrh->first_segment];
-	set_tun_src(net, skb->dev, &hdr->daddr, &hdr->saddr);
+	set_tun_src(net, ip6_dst_idev(dst)->dev, &hdr->daddr, &hdr->saddr);
 
 #ifdef CONFIG_IPV6_SEG6_HMAC
 	if (sr_has_hmac(isrh)) {
-- 
2.14.3


From 7c7255bcb91938b1dd53e1b6ca54e60b66aa9c92 Mon Sep 17 00:00:00 2001
From: David Lebrun <dlebrun@google.com>
Date: Tue, 20 Mar 2018 14:44:55 +0000
Subject: [PATCH 13/53] ipv6: sr: fix scheduling in RCU when creating seg6
 lwtunnel state

[ Upstream commit 191f86ca8ef27f7a492fd1c03620498c6e94f0ac ]

The seg6_build_state() function is called with RCU read lock held,
so we cannot use GFP_KERNEL. This patch uses GFP_ATOMIC instead.

[   92.770271] =============================
[   92.770628] WARNING: suspicious RCU usage
[   92.770921] 4.16.0-rc4+ #12 Not tainted
[   92.771277] -----------------------------
[   92.771585] ./include/linux/rcupdate.h:302 Illegal context switch in RCU read-side critical section!
[   92.772279]
[   92.772279] other info that might help us debug this:
[   92.772279]
[   92.773067]
[   92.773067] rcu_scheduler_active = 2, debug_locks = 1
[   92.773514] 2 locks held by ip/2413:
[   92.773765]  #0:  (rtnl_mutex){+.+.}, at: [<00000000e5461720>] rtnetlink_rcv_msg+0x441/0x4d0
[   92.774377]  #1:  (rcu_read_lock){....}, at: [<00000000df4f161e>] lwtunnel_build_state+0x59/0x210
[   92.775065]
[   92.775065] stack backtrace:
[   92.775371] CPU: 0 PID: 2413 Comm: ip Not tainted 4.16.0-rc4+ #12
[   92.775791] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1.fc27 04/01/2014
[   92.776608] Call Trace:
[   92.776852]  dump_stack+0x7d/0xbc
[   92.777130]  __schedule+0x133/0xf00
[   92.777393]  ? unwind_get_return_address_ptr+0x50/0x50
[   92.777783]  ? __sched_text_start+0x8/0x8
[   92.778073]  ? rcu_is_watching+0x19/0x30
[   92.778383]  ? kernel_text_address+0x49/0x60
[   92.778800]  ? __kernel_text_address+0x9/0x30
[   92.779241]  ? unwind_get_return_address+0x29/0x40
[   92.779727]  ? pcpu_alloc+0x102/0x8f0
[   92.780101]  _cond_resched+0x23/0x50
[   92.780459]  __mutex_lock+0xbd/0xad0
[   92.780818]  ? pcpu_alloc+0x102/0x8f0
[   92.781194]  ? seg6_build_state+0x11d/0x240
[   92.781611]  ? save_stack+0x9b/0xb0
[   92.781965]  ? __ww_mutex_wakeup_for_backoff+0xf0/0xf0
[   92.782480]  ? seg6_build_state+0x11d/0x240
[   92.782925]  ? lwtunnel_build_state+0x1bd/0x210
[   92.783393]  ? ip6_route_info_create+0x687/0x1640
[   92.783846]  ? ip6_route_add+0x74/0x110
[   92.784236]  ? inet6_rtm_newroute+0x8a/0xd0

Fixes: 6c8702c60b886 ("ipv6: sr: add support for SRH encapsulation and injection with lwtunnels")
Signed-off-by: David Lebrun <dlebrun@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/seg6_iptunnel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 37e76ca7b7cb..7a78dcfda68a 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -419,7 +419,7 @@ static int seg6_build_state(struct nlattr *nla,
 
 	slwt = seg6_lwt_lwtunnel(newts);
 
-	err = dst_cache_init(&slwt->cache, GFP_KERNEL);
+	err = dst_cache_init(&slwt->cache, GFP_ATOMIC);
 	if (err) {
 		kfree(newts);
 		return err;
-- 
2.14.3


From b4cfe4ee0874b99204884c70b7eff73ca9b18cc4 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Thu, 15 Mar 2018 14:49:56 +0200
Subject: [PATCH 14/53] mlxsw: spectrum_buffers: Set a minimum quota for CPU
 port traffic

[ Upstream commit bcdd5de80a2275f7879dc278bfc747f1caf94442 ]

In commit 9ffcc3725f09 ("mlxsw: spectrum: Allow packets to be trapped
from any PG") I fixed a problem where packets could not be trapped to
the CPU due to exceeded shared buffer quotas. The mentioned commit
explains the problem in detail.

The problem was fixed by assigning a minimum quota for the CPU port and
the traffic class used for scheduling traffic to the CPU.

However, commit 117b0dad2d54 ("mlxsw: Create a different trap group list
for each device") assigned different traffic classes to different
packet types and rendered the fix useless.

Fix the problem by assigning a minimum quota for the CPU port and all
the traffic classes that are currently in use.

Fixes: 117b0dad2d54 ("mlxsw: Create a different trap group list for each device")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Eddie Shklaer <eddies@mellanox.com>
Tested-by: Eddie Shklaer <eddies@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
index 93728c694e6d..0a9adc5962fb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
@@ -385,13 +385,13 @@ static const struct mlxsw_sp_sb_cm mlxsw_sp_sb_cms_egress[] = {
 
 static const struct mlxsw_sp_sb_cm mlxsw_sp_cpu_port_sb_cms[] = {
 	MLXSW_SP_CPU_PORT_SB_CM,
+	MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 0),
+	MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 0),
+	MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 0),
+	MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 0),
+	MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 0),
 	MLXSW_SP_CPU_PORT_SB_CM,
-	MLXSW_SP_CPU_PORT_SB_CM,
-	MLXSW_SP_CPU_PORT_SB_CM,
-	MLXSW_SP_CPU_PORT_SB_CM,
-	MLXSW_SP_CPU_PORT_SB_CM,
-	MLXSW_SP_CPU_PORT_SB_CM,
-	MLXSW_SP_SB_CM(10000, 0, 0),
+	MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 0),
 	MLXSW_SP_CPU_PORT_SB_CM,
 	MLXSW_SP_CPU_PORT_SB_CM,
 	MLXSW_SP_CPU_PORT_SB_CM,
-- 
2.14.3


From 65bb4b029383d333714491f193307b96998173c7 Mon Sep 17 00:00:00 2001
From: Brad Mouring <brad.mouring@ni.com>
Date: Thu, 8 Mar 2018 16:23:03 -0600
Subject: [PATCH 15/53] net: phy: Tell caller result of phy_change()

[ Upstream commit a2c054a896b8ac794ddcfc7c92e2dc7ec4ed4ed5 ]

In 664fcf123a30e (net: phy: Threaded interrupts allow some simplification)
the phy_interrupt system was changed to use a traditional threaded
interrupt scheme instead of a workqueue approach.

With this change, the phy status check moved into phy_change, which
did not report back to the caller whether or not the interrupt was
handled. This means that, in the case of a shared phy interrupt,
only the first phydev's interrupt registers are checked (since
phy_interrupt() would always return IRQ_HANDLED). This leads to
interrupt storms when it is a secondary device that's actually the
interrupt source.

Signed-off-by: Brad Mouring <brad.mouring@ni.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 173 +++++++++++++++++++++++++-------------------------
 include/linux/phy.h   |   1 -
 2 files changed, 86 insertions(+), 88 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 39de77a8bb63..dba6d17ad885 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -614,6 +614,91 @@ static void phy_error(struct phy_device *phydev)
 	phy_trigger_machine(phydev, false);
 }
 
+/**
+ * phy_disable_interrupts - Disable the PHY interrupts from the PHY side
+ * @phydev: target phy_device struct
+ */
+static int phy_disable_interrupts(struct phy_device *phydev)
+{
+	int err;
+
+	/* Disable PHY interrupts */
+	err = phy_config_interrupt(phydev, PHY_INTERRUPT_DISABLED);
+	if (err)
+		goto phy_err;
+
+	/* Clear the interrupt */
+	err = phy_clear_interrupt(phydev);
+	if (err)
+		goto phy_err;
+
+	return 0;
+
+phy_err:
+	phy_error(phydev);
+
+	return err;
+}
+
+/**
+ * phy_change - Called by the phy_interrupt to handle PHY changes
+ * @phydev: phy_device struct that interrupted
+ */
+static irqreturn_t phy_change(struct phy_device *phydev)
+{
+	if (phy_interrupt_is_valid(phydev)) {
+		if (phydev->drv->did_interrupt &&
+		    !phydev->drv->did_interrupt(phydev))
+			goto ignore;
+
+		if (phy_disable_interrupts(phydev))
+			goto phy_err;
+	}
+
+	mutex_lock(&phydev->lock);
+	if ((PHY_RUNNING == phydev->state) || (PHY_NOLINK == phydev->state))
+		phydev->state = PHY_CHANGELINK;
+	mutex_unlock(&phydev->lock);
+
+	if (phy_interrupt_is_valid(phydev)) {
+		atomic_dec(&phydev->irq_disable);
+		enable_irq(phydev->irq);
+
+		/* Reenable interrupts */
+		if (PHY_HALTED != phydev->state &&
+		    phy_config_interrupt(phydev, PHY_INTERRUPT_ENABLED))
+			goto irq_enable_err;
+	}
+
+	/* reschedule state queue work to run as soon as possible */
+	phy_trigger_machine(phydev, true);
+	return IRQ_HANDLED;
+
+ignore:
+	atomic_dec(&phydev->irq_disable);
+	enable_irq(phydev->irq);
+	return IRQ_NONE;
+
+irq_enable_err:
+	disable_irq(phydev->irq);
+	atomic_inc(&phydev->irq_disable);
+phy_err:
+	phy_error(phydev);
+	return IRQ_NONE;
+}
+
+/**
+ * phy_change_work - Scheduled by the phy_mac_interrupt to handle PHY changes
+ * @work: work_struct that describes the work to be done
+ */
+void phy_change_work(struct work_struct *work)
+{
+	struct phy_device *phydev =
+		container_of(work, struct phy_device, phy_queue);
+
+	phy_change(phydev);
+}
+
 /**
  * phy_interrupt - PHY interrupt handler
  * @irq: interrupt line
@@ -632,9 +717,7 @@ static irqreturn_t phy_interrupt(int irq, void *phy_dat)
 	disable_irq_nosync(irq);
 	atomic_inc(&phydev->irq_disable);
 
-	phy_change(phydev);
-
-	return IRQ_HANDLED;
+	return phy_change(phydev);
 }
 
 /**
@@ -651,32 +734,6 @@ static int phy_enable_interrupts(struct phy_device *phydev)
 	return phy_config_interrupt(phydev, PHY_INTERRUPT_ENABLED);
 }
 
-/**
- * phy_disable_interrupts - Disable the PHY interrupts from the PHY side
- * @phydev: target phy_device struct
- */
-static int phy_disable_interrupts(struct phy_device *phydev)
-{
-	int err;
-
-	/* Disable PHY interrupts */
-	err = phy_config_interrupt(phydev, PHY_INTERRUPT_DISABLED);
-	if (err)
-		goto phy_err;
-
-	/* Clear the interrupt */
-	err = phy_clear_interrupt(phydev);
-	if (err)
-		goto phy_err;
-
-	return 0;
-
-phy_err:
-	phy_error(phydev);
-
-	return err;
-}
-
 /**
  * phy_start_interrupts - request and enable interrupts for a PHY device
  * @phydev: target phy_device struct
@@ -727,64 +784,6 @@ int phy_stop_interrupts(struct phy_device *phydev)
 }
 EXPORT_SYMBOL(phy_stop_interrupts);
 
-/**
- * phy_change - Called by the phy_interrupt to handle PHY changes
- * @phydev: phy_device struct that interrupted
- */
-void phy_change(struct phy_device *phydev)
-{
-	if (phy_interrupt_is_valid(phydev)) {
-		if (phydev->drv->did_interrupt &&
-		    !phydev->drv->did_interrupt(phydev))
-			goto ignore;
-
-		if (phy_disable_interrupts(phydev))
-			goto phy_err;
-	}
-
-	mutex_lock(&phydev->lock);
-	if ((PHY_RUNNING == phydev->state) || (PHY_NOLINK == phydev->state))
-		phydev->state = PHY_CHANGELINK;
-	mutex_unlock(&phydev->lock);
-
-	if (phy_interrupt_is_valid(phydev)) {
-		atomic_dec(&phydev->irq_disable);
-		enable_irq(phydev->irq);
-
-		/* Reenable interrupts */
-		if (PHY_HALTED != phydev->state &&
-		    phy_config_interrupt(phydev, PHY_INTERRUPT_ENABLED))
-			goto irq_enable_err;
-	}
-
-	/* reschedule state queue work to run as soon as possible */
-	phy_trigger_machine(phydev, true);
-	return;
-
-ignore:
-	atomic_dec(&phydev->irq_disable);
-	enable_irq(phydev->irq);
-	return;
-
-irq_enable_err:
-	disable_irq(phydev->irq);
-	atomic_inc(&phydev->irq_disable);
-phy_err:
-	phy_error(phydev);
-}
-
-/**
- * phy_change_work - Scheduled by the phy_mac_interrupt to handle PHY changes
- * @work: work_struct that describes the work to be done
- */
-void phy_change_work(struct work_struct *work)
-{
-	struct phy_device *phydev =
-		container_of(work, struct phy_device, phy_queue);
-
-	phy_change(phydev);
-}
-
 /**
  * phy_stop - Bring down the PHY link, and stop checking the status
  * @phydev: target phy_device struct
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 123cd703741d..ea0cbd6d9556 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -897,7 +897,6 @@ int phy_driver_register(struct phy_driver *new_driver, struct module *owner);
 int phy_drivers_register(struct phy_driver *new_driver, int n,
 			 struct module *owner);
 void phy_state_machine(struct work_struct *work);
-void phy_change(struct phy_device *phydev);
 void phy_change_work(struct work_struct *work);
 void phy_mac_interrupt(struct phy_device *phydev, int new_link);
 void phy_start_machine(struct phy_device *phydev);
-- 
2.14.3


From 5c2806a1f1b5067bb8f06796870f4719eb102be6 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Tue, 6 Mar 2018 11:10:19 +0100
Subject: [PATCH 16/53] ipv6: Reflect MTU changes on PMTU of exceptions for
 MTU-less routes

[ Upstream commit e9fa1495d738e34fcec88a3d2ec9101a9ee5b310 ]

Currently, administrative MTU changes on a given netdevice are
not reflected on route exceptions for MTU-less routes, with a
set PMTU value, for that device:

 # ip -6 route get 2001:db8::b
 2001:db8::b from :: dev vti_a proto kernel src 2001:db8::a metric 256 pref medium
 # ping6 -c 1 -q -s10000 2001:db8::b > /dev/null
 # ip netns exec a ip -6 route get 2001:db8::b
 2001:db8::b from :: dev vti_a src 2001:db8::a metric 0
     cache expires 571sec mtu 4926 pref medium
 # ip link set dev vti_a mtu 3000
 # ip -6 route get 2001:db8::b
 2001:db8::b from :: dev vti_a src 2001:db8::a metric 0
     cache expires 571sec mtu 4926 pref medium
 # ip link set dev vti_a mtu 9000
 # ip -6 route get 2001:db8::b
 2001:db8::b from :: dev vti_a src 2001:db8::a metric 0
     cache expires 571sec mtu 4926 pref medium

The first issue is that since commit fb56be83e43d ("net-ipv6: on
device mtu change do not add mtu to mtu-less routes") we don't
call rt6_exceptions_update_pmtu() from rt6_mtu_change_route(),
which handles administrative MTU changes, if the regular route
is MTU-less.

However, PMTU exceptions should be always updated, as long as
RTAX_MTU is not locked. Keep the check for MTU-less main route,
as introduced by that commit, but, for exceptions,
call rt6_exceptions_update_pmtu() regardless of that check.

Once that is fixed, one problem remains: MTU changes are not
reflected if the new MTU is higher than the previous one,
because rt6_exceptions_update_pmtu() doesn't allow that. We
should instead allow PMTU increase if the old PMTU matches the
local MTU, as that implies that the old MTU was the lowest in the
path, and PMTU discovery might lead to different results.

The existing check in rt6_mtu_change_route() correctly took that
case into account (for regular routes only), so factor it out
and re-use it also in rt6_exceptions_update_pmtu().

While at it, fix comments style and grammar, and try to be a bit
more descriptive.

Reported-by: Xiumei Mu <xmu@redhat.com>
Fixes: fb56be83e43d ("net-ipv6: on device mtu change do not add mtu to mtu-less routes")
Fixes: f5bbe7ee79c2 ("ipv6: prepare rt6_mtu_change() for exception table")
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 71 +++++++++++++++++++++++++++++++++-----------------------
 1 file changed, 42 insertions(+), 29 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index a560fb1d0230..08a2a65d3304 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1510,7 +1510,30 @@ static void rt6_exceptions_remove_prefsrc(struct rt6_info *rt)
 	}
 }
 
-static void rt6_exceptions_update_pmtu(struct rt6_info *rt, int mtu)
+static bool rt6_mtu_change_route_allowed(struct inet6_dev *idev,
+					 struct rt6_info *rt, int mtu)
+{
+	/* If the new MTU is lower than the route PMTU, this new MTU will be the
+	 * lowest MTU in the path: always allow updating the route PMTU to
+	 * reflect PMTU decreases.
+	 *
+	 * If the new MTU is higher, and the route PMTU is equal to the local
+	 * MTU, this means the old MTU is the lowest in the path, so allow
+	 * updating it: if other nodes now have lower MTUs, PMTU discovery will
+	 * handle this.
+	 */
+
+	if (dst_mtu(&rt->dst) >= mtu)
+		return true;
+
+	if (dst_mtu(&rt->dst) == idev->cnf.mtu6)
+		return true;
+
+	return false;
+}
+
+static void rt6_exceptions_update_pmtu(struct inet6_dev *idev,
+				       struct rt6_info *rt, int mtu)
 {
 	struct rt6_exception_bucket *bucket;
 	struct rt6_exception *rt6_ex;
@@ -1519,20 +1542,22 @@ static void rt6_exceptions_update_pmtu(struct rt6_info *rt, int mtu)
 	bucket = rcu_dereference_protected(rt->rt6i_exception_bucket,
 					lockdep_is_held(&rt6_exception_lock));
 
-	if (bucket) {
-		for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) {
-			hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) {
-				struct rt6_info *entry = rt6_ex->rt6i;
-				/* For RTF_CACHE with rt6i_pmtu == 0
-				 * (i.e. a redirected route),
-				 * the metrics of its rt->dst.from has already
-				 * been updated.
-				 */
-				if (entry->rt6i_pmtu && entry->rt6i_pmtu > mtu)
-					entry->rt6i_pmtu = mtu;
-			}
-			bucket++;
+	if (!bucket)
+		return;
+
+	for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) {
+		hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) {
+			struct rt6_info *entry = rt6_ex->rt6i;
+
+			/* For RTF_CACHE with rt6i_pmtu == 0 (i.e. a redirected
+			 * route), the metrics of its rt->dst.from have already
+			 * been updated.
+			 */
+			if (entry->rt6i_pmtu &&
+			    rt6_mtu_change_route_allowed(idev, entry, mtu))
+				entry->rt6i_pmtu = mtu;
 		}
+		bucket++;
 	}
 }
 
@@ -3521,25 +3546,13 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg)
 	   Since RFC 1981 doesn't include administrative MTU increase
 	   update PMTU increase is a MUST. (i.e. jumbo frame)
 	 */
-	/*
-	   If new MTU is less than route PMTU, this new MTU will be the
-	   lowest MTU in the path, update the route PMTU to reflect PMTU
-	   decreases; if new MTU is greater than route PMTU, and the
-	   old MTU is the lowest MTU in the path, update the route PMTU
-	   to reflect the increase. In this case if the other nodes' MTU
-	   also have the lowest MTU, TOO BIG MESSAGE will be lead to
-	   PMTU discovery.
-	 */
 	if (rt->dst.dev == arg->dev &&
-	    dst_metric_raw(&rt->dst, RTAX_MTU) &&
 	    !dst_metric_locked(&rt->dst, RTAX_MTU)) {
 		spin_lock_bh(&rt6_exception_lock);
-		if (dst_mtu(&rt->dst) >= arg->mtu ||
-		    (dst_mtu(&rt->dst) < arg->mtu &&
-		     dst_mtu(&rt->dst) == idev->cnf.mtu6)) {
+		if (dst_metric_raw(&rt->dst, RTAX_MTU) &&
+		    rt6_mtu_change_route_allowed(idev, rt, arg->mtu))
 			dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu);
-		}
-		rt6_exceptions_update_pmtu(rt, arg->mtu);
+		rt6_exceptions_update_pmtu(idev, rt, arg->mtu);
 		spin_unlock_bh(&rt6_exception_lock);
 	}
 	return 0;
-- 
2.14.3


From 23cb798b5d228bcbce9e96c802f7ab7759f5033c Mon Sep 17 00:00:00 2001
From: Roman Mashak <mrv@mojatatu.com>
Date: Mon, 12 Mar 2018 16:20:58 -0400
Subject: [PATCH 17/53] net sched actions: return explicit error when
 tunnel_key mode is not specified

[ Upstream commit 51d4740f88affd85d49c04e3c9cd129c0e33bcb9 ]

If set/unset mode of the tunnel_key action is not provided, ->init() still
returns 0, and the caller proceeds with bogus 'struct tc_action *' object,
this results in crash:

% tc actions add action tunnel_key src_ip 1.1.1.1 dst_ip 2.2.2.1 id 7 index 1

[   35.805515] general protection fault: 0000 [#1] SMP PTI
[   35.806161] Modules linked in: act_tunnel_key kvm_intel kvm irqbypass
crct10dif_pclmul crc32_pclmul ghash_clmulni_intel pcbc aesni_intel aes_x86_64
crypto_simd glue_helper cryptd serio_raw
[   35.808233] CPU: 1 PID: 428 Comm: tc Not tainted 4.16.0-rc4+ #286
[   35.808929] RIP: 0010:tcf_action_init+0x90/0x190
[   35.809457] RSP: 0018:ffffb8edc068b9a0 EFLAGS: 00010206
[   35.810053] RAX: 1320c000000a0003 RBX: 0000000000000001 RCX: 0000000000000000
[   35.810866] RDX: 0000000000000070 RSI: 0000000000007965 RDI: ffffb8edc068b910
[   35.811660] RBP: ffffb8edc068b9d0 R08: 0000000000000000 R09: ffffb8edc068b808
[   35.812463] R10: ffffffffc02bf040 R11: 0000000000000040 R12: ffffb8edc068bb38
[   35.813235] R13: 0000000000000000 R14: 0000000000000000 R15: ffffb8edc068b910
[   35.814006] FS:  00007f3d0d8556c0(0000) GS:ffff91d1dbc40000(0000)
knlGS:0000000000000000
[   35.814881] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   35.815540] CR2: 000000000043f720 CR3: 0000000019248001 CR4: 00000000001606a0
[   35.816457] Call Trace:
[   35.817158]  tc_ctl_action+0x11a/0x220
[   35.817795]  rtnetlink_rcv_msg+0x23d/0x2e0
[   35.818457]  ? __slab_alloc+0x1c/0x30
[   35.819079]  ? __kmalloc_node_track_caller+0xb1/0x2b0
[   35.819544]  ? rtnl_calcit.isra.30+0xe0/0xe0
[   35.820231]  netlink_rcv_skb+0xce/0x100
[   35.820744]  netlink_unicast+0x164/0x220
[   35.821500]  netlink_sendmsg+0x293/0x370
[   35.822040]  sock_sendmsg+0x30/0x40
[   35.822508]  ___sys_sendmsg+0x2c5/0x2e0
[   35.823149]  ? pagecache_get_page+0x27/0x220
[   35.823714]  ? filemap_fault+0xa2/0x640
[   35.824423]  ? page_add_file_rmap+0x108/0x200
[   35.825065]  ? alloc_set_pte+0x2aa/0x530
[   35.825585]  ? finish_fault+0x4e/0x70
[   35.826140]  ? __handle_mm_fault+0xbc1/0x10d0
[   35.826723]  ? __sys_sendmsg+0x41/0x70
[   35.827230]  __sys_sendmsg+0x41/0x70
[   35.827710]  do_syscall_64+0x68/0x120
[   35.828195]  entry_SYSCALL_64_after_hwframe+0x3d/0xa2
[   35.828859] RIP: 0033:0x7f3d0ca4da67
[   35.829331] RSP: 002b:00007ffc9f284338 EFLAGS: 00000246 ORIG_RAX:
000000000000002e
[   35.830304] RAX: ffffffffffffffda RBX: 00007ffc9f284460 RCX: 00007f3d0ca4da67
[   35.831247] RDX: 0000000000000000 RSI: 00007ffc9f2843b0 RDI: 0000000000000003
[   35.832167] RBP: 000000005aa6a7a9 R08: 0000000000000001 R09: 0000000000000000
[   35.833075] R10: 00000000000005f1 R11: 0000000000000246 R12: 0000000000000000
[   35.833997] R13: 00007ffc9f2884c0 R14: 0000000000000001 R15: 0000000000674640
[   35.834923] Code: 24 30 bb 01 00 00 00 45 31 f6 eb 5e 8b 50 08 83 c2 07 83 e2
fc 83 c2 70 49 8b 07 48 8b 40 70 48 85 c0 74 10 48 89 14 24 4c 89 ff <ff> d0 48
8b 14 24 48 01 c2 49 01 d6 45 85 ed 74 05 41 83 47 2c
[   35.837442] RIP: tcf_action_init+0x90/0x190 RSP: ffffb8edc068b9a0
[   35.838291] ---[ end trace a095c06ee4b97a26 ]---

Fixes: d0f6dd8a914f ("net/sched: Introduce act_tunnel_key")
Signed-off-by: Roman Mashak <mrv@mojatatu.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_tunnel_key.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 30c96274c638..22bf1a376b91 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -153,6 +153,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 		metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX;
 		break;
 	default:
+		ret = -EINVAL;
 		goto err_out;
 	}
 
-- 
2.14.3


From 601b8bdefb000da9603b1c60a4d98ed06485cb04 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Tue, 20 Mar 2018 16:49:26 +0100
Subject: [PATCH 18/53] ppp: avoid loop in xmit recursion detection code

[ Upstream commit 6d066734e9f09cdea4a3b9cb76136db3f29cfb02 ]

We already detect situations where a PPP channel sends packets back to
its upper PPP device. While this is enough to avoid deadlocking on xmit
locks, this doesn't prevent packets from looping between the channel
and the unit.

The problem is that ppp_start_xmit() enqueues packets in ppp->file.xq
before checking for xmit recursion. Therefore, __ppp_xmit_process()
might dequeue a packet from ppp->file.xq and send it on the channel
which, in turn, loops it back on the unit. Then ppp_start_xmit()
queues the packet back to ppp->file.xq and __ppp_xmit_process() picks
it up and sends it again through the channel. Therefore, the packet
will loop between __ppp_xmit_process() and ppp_start_xmit() until some
other part of the xmit path drops it.

For L2TP, we rapidly fill the skb's headroom and pppol2tp_xmit() drops
the packet after a few iterations. But PPTP reallocates the headroom
if necessary, letting the loop run and exhaust the machine resources
(as reported in https://bugzilla.kernel.org/show_bug.cgi?id=199109).

Fix this by letting __ppp_xmit_process() enqueue the skb to
ppp->file.xq, so that we can check for recursion before adding it to
the queue. Now ppp_xmit_process() can drop the packet when recursion is
detected.

__ppp_channel_push() is a bit special. It calls __ppp_xmit_process()
without having any actual packet to send. This is used by
ppp_output_wakeup() to re-enable transmission on the parent unit (for
implementations like ppp_async.c, where the .start_xmit() function
might not consume the skb, leaving it in ppp->xmit_pending and
disabling transmission).
Therefore, __ppp_xmit_process() needs to handle the case where skb is
NULL, dequeuing as many packets as possible from ppp->file.xq.

Reported-by: xu heng <xuheng333@zoho.com>
Fixes: 55454a565836 ("ppp: avoid dealock on recursive xmit")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/ppp_generic.c | 26 ++++++++++++++------------
 1 file changed, 14 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 9f79f9274c50..d37183aec313 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -257,7 +257,7 @@ struct ppp_net {
 /* Prototypes. */
 static int ppp_unattached_ioctl(struct net *net, struct ppp_file *pf,
 			struct file *file, unsigned int cmd, unsigned long arg);
-static void ppp_xmit_process(struct ppp *ppp);
+static void ppp_xmit_process(struct ppp *ppp, struct sk_buff *skb);
 static void ppp_send_frame(struct ppp *ppp, struct sk_buff *skb);
 static void ppp_push(struct ppp *ppp);
 static void ppp_channel_push(struct channel *pch);
@@ -513,13 +513,12 @@ static ssize_t ppp_write(struct file *file, const char __user *buf,
 		goto out;
 	}
 
-	skb_queue_tail(&pf->xq, skb);
-
 	switch (pf->kind) {
 	case INTERFACE:
-		ppp_xmit_process(PF_TO_PPP(pf));
+		ppp_xmit_process(PF_TO_PPP(pf), skb);
 		break;
 	case CHANNEL:
+		skb_queue_tail(&pf->xq, skb);
 		ppp_channel_push(PF_TO_CHANNEL(pf));
 		break;
 	}
@@ -1267,8 +1266,8 @@ ppp_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	put_unaligned_be16(proto, pp);
 
 	skb_scrub_packet(skb, !net_eq(ppp->ppp_net, dev_net(dev)));
-	skb_queue_tail(&ppp->file.xq, skb);
-	ppp_xmit_process(ppp);
+	ppp_xmit_process(ppp, skb);
+
 	return NETDEV_TX_OK;
 
  outf:
@@ -1420,13 +1419,14 @@ static void ppp_setup(struct net_device *dev)
  */
 
 /* Called to do any work queued up on the transmit side that can now be done */
-static void __ppp_xmit_process(struct ppp *ppp)
+static void __ppp_xmit_process(struct ppp *ppp, struct sk_buff *skb)
 {
-	struct sk_buff *skb;
-
 	ppp_xmit_lock(ppp);
 	if (!ppp->closing) {
 		ppp_push(ppp);
+
+		if (skb)
+			skb_queue_tail(&ppp->file.xq, skb);
 		while (!ppp->xmit_pending &&
 		       (skb = skb_dequeue(&ppp->file.xq)))
 			ppp_send_frame(ppp, skb);
@@ -1440,7 +1440,7 @@ static void __ppp_xmit_process(struct ppp *ppp)
 	ppp_xmit_unlock(ppp);
 }
 
-static void ppp_xmit_process(struct ppp *ppp)
+static void ppp_xmit_process(struct ppp *ppp, struct sk_buff *skb)
 {
 	local_bh_disable();
 
@@ -1448,7 +1448,7 @@ static void ppp_xmit_process(struct ppp *ppp)
 		goto err;
 
 	(*this_cpu_ptr(ppp->xmit_recursion))++;
-	__ppp_xmit_process(ppp);
+	__ppp_xmit_process(ppp, skb);
 	(*this_cpu_ptr(ppp->xmit_recursion))--;
 
 	local_bh_enable();
@@ -1458,6 +1458,8 @@ static void ppp_xmit_process(struct ppp *ppp)
 err:
 	local_bh_enable();
 
+	kfree_skb(skb);
+
 	if (net_ratelimit())
 		netdev_err(ppp->dev, "recursion detected\n");
 }
@@ -1942,7 +1944,7 @@ static void __ppp_channel_push(struct channel *pch)
 	if (skb_queue_empty(&pch->file.xq)) {
 		ppp = pch->ppp;
 		if (ppp)
-			__ppp_xmit_process(ppp);
+			__ppp_xmit_process(ppp, NULL);
 	}
 }
 
-- 
2.14.3


From fb276da733a8a32bf6076da0efd69b50833eb710 Mon Sep 17 00:00:00 2001
From: Paul Blakey <paulb@mellanox.com>
Date: Sun, 4 Mar 2018 17:29:48 +0200
Subject: [PATCH 19/53] rhashtable: Fix rhlist duplicates insertion

[ Upstream commit d3dcf8eb615537526bd42ff27a081d46d337816e ]

When inserting duplicate objects (those with the same key),
current rhlist implementation messes up the chain pointers by
updating the bucket pointer instead of prev next pointer to the
newly inserted node. This causes missing elements on removal and
travesal.

Fix that by properly updating pprev pointer to point to
the correct rhash_head next pointer.

Issue: 1241076
Change-Id: I86b2c140bcb4aeb10b70a72a267ff590bb2b17e7
Fixes: ca26893f05e8 ('rhashtable: Add rhlist interface')
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable.h | 4 +++-
 lib/rhashtable.c           | 4 +++-
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 361c08e35dbc..7fd514f36e74 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -750,8 +750,10 @@ static inline void *__rhashtable_insert_fast(
 		if (!key ||
 		    (params.obj_cmpfn ?
 		     params.obj_cmpfn(&arg, rht_obj(ht, head)) :
-		     rhashtable_compare(&arg, rht_obj(ht, head))))
+		     rhashtable_compare(&arg, rht_obj(ht, head)))) {
+			pprev = &head->next;
 			continue;
+		}
 
 		data = rht_obj(ht, head);
 
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index ddd7dde87c3c..b734ce731a7a 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -537,8 +537,10 @@ static void *rhashtable_lookup_one(struct rhashtable *ht,
 		if (!key ||
 		    (ht->p.obj_cmpfn ?
 		     ht->p.obj_cmpfn(&arg, rht_obj(ht, head)) :
-		     rhashtable_compare(&arg, rht_obj(ht, head))))
+		     rhashtable_compare(&arg, rht_obj(ht, head)))) {
+			pprev = &head->next;
 			continue;
+		}
 
 		if (!ht->rhlist)
 			return rht_obj(ht, head);
-- 
2.14.3


From 065d0444a3caf428cbad1c716c7e33e2651df5c1 Mon Sep 17 00:00:00 2001
From: Paul Blakey <paulb@mellanox.com>
Date: Sun, 4 Mar 2018 17:29:49 +0200
Subject: [PATCH 20/53] test_rhashtable: add test case for rhltable with
 duplicate objects

[ Upstream commit 499ac3b60f657dae82055fc81c7b01e6242ac9bc ]

Tries to insert duplicates in the middle of bucket's chain:
bucket 1:  [[val 21 (tid=1)]] -> [[ val 1 (tid=2),  val 1 (tid=0) ]]

Reuses tid to distinguish the elements insertion order.

Signed-off-by: Paul Blakey <paulb@mellanox.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 lib/test_rhashtable.c | 134 ++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 134 insertions(+)

diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c
index 8e83cbdc049c..6f2e3dc44a80 100644
--- a/lib/test_rhashtable.c
+++ b/lib/test_rhashtable.c
@@ -79,6 +79,21 @@ struct thread_data {
 	struct test_obj *objs;
 };
 
+static u32 my_hashfn(const void *data, u32 len, u32 seed)
+{
+	const struct test_obj_rhl *obj = data;
+
+	return (obj->value.id % 10) << RHT_HASH_RESERVED_SPACE;
+}
+
+static int my_cmpfn(struct rhashtable_compare_arg *arg, const void *obj)
+{
+	const struct test_obj_rhl *test_obj = obj;
+	const struct test_obj_val *val = arg->key;
+
+	return test_obj->value.id - val->id;
+}
+
 static struct rhashtable_params test_rht_params = {
 	.head_offset = offsetof(struct test_obj, node),
 	.key_offset = offsetof(struct test_obj, value),
@@ -87,6 +102,17 @@ static struct rhashtable_params test_rht_params = {
 	.nulls_base = (3U << RHT_BASE_SHIFT),
 };
 
+static struct rhashtable_params test_rht_params_dup = {
+	.head_offset = offsetof(struct test_obj_rhl, list_node),
+	.key_offset = offsetof(struct test_obj_rhl, value),
+	.key_len = sizeof(struct test_obj_val),
+	.hashfn = jhash,
+	.obj_hashfn = my_hashfn,
+	.obj_cmpfn = my_cmpfn,
+	.nelem_hint = 128,
+	.automatic_shrinking = false,
+};
+
 static struct semaphore prestart_sem;
 static struct semaphore startup_sem = __SEMAPHORE_INITIALIZER(startup_sem, 0);
 
@@ -469,6 +495,112 @@ static int __init test_rhashtable_max(struct test_obj *array,
 	return err;
 }
 
+static unsigned int __init print_ht(struct rhltable *rhlt)
+{
+	struct rhashtable *ht;
+	const struct bucket_table *tbl;
+	char buff[512] = "";
+	unsigned int i, cnt = 0;
+
+	ht = &rhlt->ht;
+	tbl = rht_dereference(ht->tbl, ht);
+	for (i = 0; i < tbl->size; i++) {
+		struct rhash_head *pos, *next;
+		struct test_obj_rhl *p;
+
+		pos = rht_dereference(tbl->buckets[i], ht);
+		next = !rht_is_a_nulls(pos) ? rht_dereference(pos->next, ht) : NULL;
+
+		if (!rht_is_a_nulls(pos)) {
+			sprintf(buff, "%s\nbucket[%d] -> ", buff, i);
+		}
+
+		while (!rht_is_a_nulls(pos)) {
+			struct rhlist_head *list = container_of(pos, struct rhlist_head, rhead);
+			sprintf(buff, "%s[[", buff);
+			do {
+				pos = &list->rhead;
+				list = rht_dereference(list->next, ht);
+				p = rht_obj(ht, pos);
+
+				sprintf(buff, "%s val %d (tid=%d)%s", buff, p->value.id, p->value.tid,
+					list? ", " : " ");
+				cnt++;
+			} while (list);
+
+			pos = next,
+			next = !rht_is_a_nulls(pos) ?
+				rht_dereference(pos->next, ht) : NULL;
+
+			sprintf(buff, "%s]]%s", buff, !rht_is_a_nulls(pos) ? " -> " : "");
+		}
+	}
+	printk(KERN_ERR "\n---- ht: ----%s\n-------------\n", buff);
+
+	return cnt;
+}
+
+static int __init test_insert_dup(struct test_obj_rhl *rhl_test_objects,
+				  int cnt, bool slow)
+{
+	struct rhltable rhlt;
+	unsigned int i, ret;
+	const char *key;
+	int err = 0;
+
+	err = rhltable_init(&rhlt, &test_rht_params_dup);
+	if (WARN_ON(err))
+		return err;
+
+	for (i = 0; i < cnt; i++) {
+		rhl_test_objects[i].value.tid = i;
+		key = rht_obj(&rhlt.ht, &rhl_test_objects[i].list_node.rhead);
+		key += test_rht_params_dup.key_offset;
+
+		if (slow) {
+			err = PTR_ERR(rhashtable_insert_slow(&rhlt.ht, key,
+							     &rhl_test_objects[i].list_node.rhead));
+			if (err == -EAGAIN)
+				err = 0;
+		} else
+			err = rhltable_insert(&rhlt,
+					      &rhl_test_objects[i].list_node,
+					      test_rht_params_dup);
+		if (WARN(err, "error %d on element %d/%d (%s)\n", err, i, cnt, slow? "slow" : "fast"))
+			goto skip_print;
+	}
+
+	ret = print_ht(&rhlt);
+	WARN(ret != cnt, "missing rhltable elements (%d != %d, %s)\n", ret, cnt, slow? "slow" : "fast");
+
+skip_print:
+	rhltable_destroy(&rhlt);
+
+	return 0;
+}
+
+static int __init test_insert_duplicates_run(void)
+{
+	struct test_obj_rhl rhl_test_objects[3] = {};
+
+	pr_info("test inserting duplicates\n");
+
+	/* two different values that map to same bucket */
+	rhl_test_objects[0].value.id = 1;
+	rhl_test_objects[1].value.id = 21;
+
+	/* and another duplicate with same as [0] value
+	 * which will be second on the bucket list */
+	rhl_test_objects[2].value.id = rhl_test_objects[0].value.id;
+
+	test_insert_dup(rhl_test_objects, 2, false);
+	test_insert_dup(rhl_test_objects, 3, false);
+	test_insert_dup(rhl_test_objects, 2, true);
+	test_insert_dup(rhl_test_objects, 3, true);
+
+	return 0;
+}
+
 static int thread_lookup_test(struct thread_data *tdata)
 {
 	unsigned int entries = tdata->entries;
@@ -617,6 +749,8 @@ static int __init test_rht_init(void)
 	do_div(total_time, runs);
 	pr_info("Average test time: %llu\n", total_time);
 
+	test_insert_duplicates_run();
+
 	if (!tcount)
 		return 0;
 
-- 
2.14.3


From 8bea78250af25dfa0725ea86169db61ae6290b7c Mon Sep 17 00:00:00 2001
From: Tom Herbert <tom@quantonium.net>
Date: Tue, 13 Mar 2018 12:01:43 -0700
Subject: [PATCH 21/53] kcm: lock lower socket in kcm_attach

[ Upstream commit 2cc683e88c0c993ac3721d9b702cb0630abe2879 ]

Need to lock lower socket in order to provide mutual exclusion
with kcm_unattach.

v2: Add Reported-by for syzbot

Fixes: ab7ac4eb9832e32a09f4e804 ("kcm: Kernel Connection Multiplexor module")
Reported-by: syzbot+ea75c0ffcd353d32515f064aaebefc5279e6161e@syzkaller.appspotmail.com
Signed-off-by: Tom Herbert <tom@quantonium.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/kcm/kcmsock.c | 33 +++++++++++++++++++++++----------
 1 file changed, 23 insertions(+), 10 deletions(-)

diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 4a8d407f8902..3f15ffd356da 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -1381,24 +1381,32 @@ static int kcm_attach(struct socket *sock, struct socket *csock,
 		.parse_msg = kcm_parse_func_strparser,
 		.read_sock_done = kcm_read_sock_done,
 	};
-	int err;
+	int err = 0;
 
 	csk = csock->sk;
 	if (!csk)
 		return -EINVAL;
 
+	lock_sock(csk);
+
 	/* Only allow TCP sockets to be attached for now */
 	if ((csk->sk_family != AF_INET && csk->sk_family != AF_INET6) ||
-	    csk->sk_protocol != IPPROTO_TCP)
-		return -EOPNOTSUPP;
+	    csk->sk_protocol != IPPROTO_TCP) {
+		err = -EOPNOTSUPP;
+		goto out;
+	}
 
 	/* Don't allow listeners or closed sockets */
-	if (csk->sk_state == TCP_LISTEN || csk->sk_state == TCP_CLOSE)
-		return -EOPNOTSUPP;
+	if (csk->sk_state == TCP_LISTEN || csk->sk_state == TCP_CLOSE) {
+		err = -EOPNOTSUPP;
+		goto out;
+	}
 
 	psock = kmem_cache_zalloc(kcm_psockp, GFP_KERNEL);
-	if (!psock)
-		return -ENOMEM;
+	if (!psock) {
+		err = -ENOMEM;
+		goto out;
+	}
 
 	psock->mux = mux;
 	psock->sk = csk;
@@ -1407,7 +1415,7 @@ static int kcm_attach(struct socket *sock, struct socket *csock,
 	err = strp_init(&psock->strp, csk, &cb);
 	if (err) {
 		kmem_cache_free(kcm_psockp, psock);
-		return err;
+		goto out;
 	}
 
 	write_lock_bh(&csk->sk_callback_lock);
@@ -1419,7 +1427,8 @@ static int kcm_attach(struct socket *sock, struct socket *csock,
 		write_unlock_bh(&csk->sk_callback_lock);
 		strp_done(&psock->strp);
 		kmem_cache_free(kcm_psockp, psock);
-		return -EALREADY;
+		err = -EALREADY;
+		goto out;
 	}
 
 	psock->save_data_ready = csk->sk_data_ready;
@@ -1455,7 +1464,10 @@ static int kcm_attach(struct socket *sock, struct socket *csock,
 	/* Schedule RX work in case there are already bytes queued */
 	strp_check_rcv(&psock->strp);
 
-	return 0;
+out:
+	release_sock(csk);
+
+	return err;
 }
 
 static int kcm_attach_ioctl(struct socket *sock, struct kcm_attach *info)
@@ -1507,6 +1519,7 @@ static void kcm_unattach(struct kcm_psock *psock)
 
 	if (WARN_ON(psock->rx_kcm)) {
 		write_unlock_bh(&csk->sk_callback_lock);
+		release_sock(csk);
 		return;
 	}
 
-- 
2.14.3


From 6a7458295b408924e16b3cba2959382e6e667fb6 Mon Sep 17 00:00:00 2001
From: Alexey Kodanev <alexey.kodanev@oracle.com>
Date: Mon, 5 Mar 2018 20:52:54 +0300
Subject: [PATCH 22/53] sch_netem: fix skb leak in netem_enqueue()

[ Upstream commit 35d889d10b649fda66121891ec05eca88150059d ]

When we exceed current packets limit and we have more than one
segment in the list returned by skb_gso_segment(), netem drops
only the first one, skipping the rest, hence kmemleak reports:

unreferenced object 0xffff880b5d23b600 (size 1024):
  comm "softirq", pid 0, jiffies 4384527763 (age 2770.629s)
  hex dump (first 32 bytes):
    00 80 23 5d 0b 88 ff ff 00 00 00 00 00 00 00 00  ..#]............
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<00000000d8a19b9d>] __alloc_skb+0xc9/0x520
    [<000000001709b32f>] skb_segment+0x8c8/0x3710
    [<00000000c7b9bb88>] tcp_gso_segment+0x331/0x1830
    [<00000000c921cba1>] inet_gso_segment+0x476/0x1370
    [<000000008b762dd4>] skb_mac_gso_segment+0x1f9/0x510
    [<000000002182660a>] __skb_gso_segment+0x1dd/0x620
    [<00000000412651b9>] netem_enqueue+0x1536/0x2590 [sch_netem]
    [<0000000005d3b2a9>] __dev_queue_xmit+0x1167/0x2120
    [<00000000fc5f7327>] ip_finish_output2+0x998/0xf00
    [<00000000d309e9d3>] ip_output+0x1aa/0x2c0
    [<000000007ecbd3a4>] tcp_transmit_skb+0x18db/0x3670
    [<0000000042d2a45f>] tcp_write_xmit+0x4d4/0x58c0
    [<0000000056a44199>] tcp_tasklet_func+0x3d9/0x540
    [<0000000013d06d02>] tasklet_action+0x1ca/0x250
    [<00000000fcde0b8b>] __do_softirq+0x1b4/0x5a3
    [<00000000e7ed027c>] irq_exit+0x1e2/0x210

Fix it by adding the rest of the segments, if any, to skb 'to_free'
list. Add new __qdisc_drop_all() and qdisc_drop_all() functions
because they can be useful in the future if we need to drop segmented
GSO packets in other places.

Fixes: 6071bd1aa13e ("netem: Segment GSO packets on enqueue")
Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h | 19 +++++++++++++++++++
 net/sched/sch_netem.c     |  2 +-
 2 files changed, 20 insertions(+), 1 deletion(-)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index d6ec5a5a6782..d794aebb3157 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -735,6 +735,16 @@ static inline void __qdisc_drop(struct sk_buff *skb, struct sk_buff **to_free)
 	*to_free = skb;
 }
 
+static inline void __qdisc_drop_all(struct sk_buff *skb,
+				    struct sk_buff **to_free)
+{
+	if (skb->prev)
+		skb->prev->next = *to_free;
+	else
+		skb->next = *to_free;
+	*to_free = skb;
+}
+
 static inline unsigned int __qdisc_queue_drop_head(struct Qdisc *sch,
 						   struct qdisc_skb_head *qh,
 						   struct sk_buff **to_free)
@@ -855,6 +865,15 @@ static inline int qdisc_drop(struct sk_buff *skb, struct Qdisc *sch,
 	return NET_XMIT_DROP;
 }
 
+static inline int qdisc_drop_all(struct sk_buff *skb, struct Qdisc *sch,
+				 struct sk_buff **to_free)
+{
+	__qdisc_drop_all(skb, to_free);
+	qdisc_qstats_drop(sch);
+
+	return NET_XMIT_DROP;
+}
+
 /* Length to Time (L2T) lookup in a qdisc_rate_table, to determine how
    long it will take to send a packet given its size.
  */
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index dd70924cbcdf..2aeca57f9bd0 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -509,7 +509,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	}
 
 	if (unlikely(sch->q.qlen >= sch->limit))
-		return qdisc_drop(skb, sch, to_free);
+		return qdisc_drop_all(skb, sch, to_free);
 
 	qdisc_qstats_backlog_inc(sch, skb);
 
-- 
2.14.3


From 6c09e0934670227b157480a604abb4875a377193 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 5 Mar 2018 08:51:03 -0800
Subject: [PATCH 23/53] ieee802154: 6lowpan: fix possible NULL deref in
 lowpan_device_event()

[ Upstream commit ca0edb131bdf1e6beaeb2b8289fd6b374b74147d ]

A tun device type can trivially be set to arbitrary value using
TUNSETLINK ioctl().

Therefore, lowpan_device_event() must really check that ieee802154_ptr
is not NULL.

Fixes: 2c88b5283f60d ("ieee802154: 6lowpan: remove check on null")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Alexander Aring <alex.aring@gmail.com>
Cc: Stefan Schmidt <stefan@osg.samsung.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: Stefan Schmidt <stefan@osg.samsung.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ieee802154/6lowpan/core.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c
index 974765b7d92a..e9f0489e4229 100644
--- a/net/ieee802154/6lowpan/core.c
+++ b/net/ieee802154/6lowpan/core.c
@@ -206,9 +206,13 @@ static inline void lowpan_netlink_fini(void)
 static int lowpan_device_event(struct notifier_block *unused,
 			       unsigned long event, void *ptr)
 {
-	struct net_device *wdev = netdev_notifier_info_to_dev(ptr);
+	struct net_device *ndev = netdev_notifier_info_to_dev(ptr);
+	struct wpan_dev *wpan_dev;
 
-	if (wdev->type != ARPHRD_IEEE802154)
+	if (ndev->type != ARPHRD_IEEE802154)
+		return NOTIFY_DONE;
+	wpan_dev = ndev->ieee802154_ptr;
+	if (!wpan_dev)
 		return NOTIFY_DONE;
 
 	switch (event) {
@@ -217,8 +221,8 @@ static int lowpan_device_event(struct notifier_block *unused,
 		 * also delete possible lowpan interfaces which belongs
 		 * to the wpan interface.
 		 */
-		if (wdev->ieee802154_ptr->lowpan_dev)
-			lowpan_dellink(wdev->ieee802154_ptr->lowpan_dev, NULL);
+		if (wpan_dev->lowpan_dev)
+			lowpan_dellink(wpan_dev->lowpan_dev, NULL);
 		break;
 	default:
 		return NOTIFY_DONE;
-- 
2.14.3


From f5fffafd7301d80750fbcb8b776600ff9b6a694e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 14 Mar 2018 09:04:16 -0700
Subject: [PATCH 24/53] net: use skb_to_full_sk() in skb_update_prio()

[ Upstream commit 4dcb31d4649df36297296b819437709f5407059c ]

Andrei Vagin reported a KASAN: slab-out-of-bounds error in
skb_update_prio()

Since SYNACK might be attached to a request socket, we need to
get back to the listener socket.
Since this listener is manipulated without locks, add const
qualifiers to sock_cgroup_prioidx() so that the const can also
be used in skb_update_prio()

Also add the const qualifier to sock_cgroup_classid() for consistency.

Fixes: ca6fb0651883 ("tcp: attach SYNACK messages to request sockets instead of listener")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrei Vagin <avagin@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/cgroup-defs.h |  4 ++--
 net/core/dev.c              | 22 +++++++++++++++-------
 2 files changed, 17 insertions(+), 9 deletions(-)

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 8b7fd8eeccee..cb8a9ce149de 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -755,13 +755,13 @@ struct sock_cgroup_data {
  * updaters and return part of the previous pointer as the prioidx or
  * classid.  Such races are short-lived and the result isn't critical.
  */
-static inline u16 sock_cgroup_prioidx(struct sock_cgroup_data *skcd)
+static inline u16 sock_cgroup_prioidx(const struct sock_cgroup_data *skcd)
 {
 	/* fallback to 1 which is always the ID of the root cgroup */
 	return (skcd->is_data & 1) ? skcd->prioidx : 1;
 }
 
-static inline u32 sock_cgroup_classid(struct sock_cgroup_data *skcd)
+static inline u32 sock_cgroup_classid(const struct sock_cgroup_data *skcd)
 {
 	/* fallback to 0 which is the unconfigured default classid */
 	return (skcd->is_data & 1) ? skcd->classid : 0;
diff --git a/net/core/dev.c b/net/core/dev.c
index a2a89acd0de8..f3fbd10a0632 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3247,15 +3247,23 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO)
 static void skb_update_prio(struct sk_buff *skb)
 {
-	struct netprio_map *map = rcu_dereference_bh(skb->dev->priomap);
+	const struct netprio_map *map;
+	const struct sock *sk;
+	unsigned int prioidx;
 
-	if (!skb->priority && skb->sk && map) {
-		unsigned int prioidx =
-			sock_cgroup_prioidx(&skb->sk->sk_cgrp_data);
+	if (skb->priority)
+		return;
+	map = rcu_dereference_bh(skb->dev->priomap);
+	if (!map)
+		return;
+	sk = skb_to_full_sk(skb);
+	if (!sk)
+		return;
 
-		if (prioidx < map->priomap_len)
-			skb->priority = map->priomap[prioidx];
-	}
+	prioidx = sock_cgroup_prioidx(&sk->sk_cgrp_data);
+
+	if (prioidx < map->priomap_len)
+		skb->priority = map->priomap[prioidx];
 }
 #else
 #define skb_update_prio(skb)
-- 
2.14.3


From 9a62abbeede468c5c1213757c92f03bde460eb0c Mon Sep 17 00:00:00 2001
From: Kirill Tkhai <ktkhai@virtuozzo.com>
Date: Tue, 6 Mar 2018 18:46:39 +0300
Subject: [PATCH 25/53] net: Fix hlist corruptions in inet_evict_bucket()

[ Upstream commit a560002437d3646dafccecb1bf32d1685112ddda ]

inet_evict_bucket() iterates global list, and
several tasks may call it in parallel. All of
them hash the same fq->list_evictor to different
lists, which leads to list corruption.

This patch makes fq be hashed to expired list
only if this has not been made yet by another
task. Since inet_frag_alloc() allocates fq
using kmem_cache_zalloc(), we may rely on
list_evictor is initially unhashed.

The problem seems to exist before async
pernet_operations, as there was possible to have
exit method to be executed in parallel with
inet_frags::frags_work, so I add two Fixes tags.
This also may go to stable.

Fixes: d1fe19444d82 "inet: frag: don't re-use chainlist for evictor"
Fixes: f84c6821aa54 "net: Convert pernet_subsys, registered from inet_init()"
Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/inet_fragment.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 26a3d0315728..e8ec28999f5c 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -119,6 +119,9 @@ static void inet_frag_secret_rebuild(struct inet_frags *f)
 
 static bool inet_fragq_should_evict(const struct inet_frag_queue *q)
 {
+	if (!hlist_unhashed(&q->list_evictor))
+		return false;
+
 	return q->net->low_thresh == 0 ||
 	       frag_mem_limit(q->net) >= q->net->low_thresh;
 }
-- 
2.14.3


From bccbc8aa05137f35ba7be7f8cf19e611c53866ad Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Tue, 20 Mar 2018 07:59:12 +0100
Subject: [PATCH 30/53] s390/qeth: free netdevice when removing a card

[ Upstream commit 6be687395b3124f002a653c1a50b3260222b3cd7 ]

On removal, a qeth card's netdevice is currently not properly freed
because the call chain looks as follows:

qeth_core_remove_device(card)
	lx_remove_device(card)
		unregister_netdev(card->dev)
		card->dev = NULL			!!!
	qeth_core_free_card(card)
		if (card->dev)				!!!
			free_netdev(card->dev)

Fix it by free'ing the netdev straight after unregistering. This also
fixes the sysfs-driven layer switch case (qeth_dev_layer2_store()),
where the need to free the current netdevice was not considered at all.

Note that free_netdev() takes care of the netif_napi_del() for us too.

Fixes: 4a71df50047f ("qeth: new qeth device driver")
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Reviewed-by: Ursula Braun <ubraun@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 2 --
 drivers/s390/net/qeth_l2_main.c   | 2 +-
 drivers/s390/net/qeth_l3_main.c   | 2 +-
 3 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 61e9d0bca197..d4b154f047e4 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -5022,8 +5022,6 @@ static void qeth_core_free_card(struct qeth_card *card)
 	QETH_DBF_HEX(SETUP, 2, &card, sizeof(void *));
 	qeth_clean_channel(&card->read);
 	qeth_clean_channel(&card->write);
-	if (card->dev)
-		free_netdev(card->dev);
 	qeth_free_qdio_buffers(card);
 	unregister_service_level(&card->qeth_service_level);
 	kfree(card);
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 5863ea170ff2..42d56b3bed82 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -933,8 +933,8 @@ static void qeth_l2_remove_device(struct ccwgroup_device *cgdev)
 		qeth_l2_set_offline(cgdev);
 
 	if (card->dev) {
-		netif_napi_del(&card->napi);
 		unregister_netdev(card->dev);
+		free_netdev(card->dev);
 		card->dev = NULL;
 	}
 	return;
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 33131c594627..5287eab5c600 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -3042,8 +3042,8 @@ static void qeth_l3_remove_device(struct ccwgroup_device *cgdev)
 		qeth_l3_set_offline(cgdev);
 
 	if (card->dev) {
-		netif_napi_del(&card->napi);
 		unregister_netdev(card->dev);
+		free_netdev(card->dev);
 		card->dev = NULL;
 	}
 
-- 
2.14.3


From 336915b1b9cb5f0f2cfa16e1f9053a8aec4396b6 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Tue, 20 Mar 2018 07:59:13 +0100
Subject: [PATCH 31/53] s390/qeth: when thread completes, wake up all waiters

[ Upstream commit 1063e432bb45be209427ed3f1ca3908e4aa3c7d7 ]

qeth_wait_for_threads() is potentially called by multiple users, make
sure to notify all of them after qeth_clear_thread_running_bit()
adjusted the thread_running_mask. With no timeout, callers would
otherwise stall.

Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index d4b154f047e4..d91a52dacaf5 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -961,7 +961,7 @@ void qeth_clear_thread_running_bit(struct qeth_card *card, unsigned long thread)
 	spin_lock_irqsave(&card->thread_mask_lock, flags);
 	card->thread_running_mask &= ~thread;
 	spin_unlock_irqrestore(&card->thread_mask_lock, flags);
-	wake_up(&card->wait_q);
+	wake_up_all(&card->wait_q);
 }
 EXPORT_SYMBOL_GPL(qeth_clear_thread_running_bit);
 
-- 
2.14.3


From 5f50d372624f9638cc01bdfd8ec17d8c6e6b9f3b Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Tue, 20 Mar 2018 07:59:14 +0100
Subject: [PATCH 32/53] s390/qeth: lock read device while queueing next buffer

[ Upstream commit 17bf8c9b3d499d5168537c98b61eb7a1fcbca6c2 ]

For calling ccw_device_start(), issue_next_read() needs to hold the
device's ccwlock.
This is satisfied for the IRQ handler path (where qeth_irq() gets called
under the ccwlock), but we need explicit locking for the initial call by
the MPC initialization.

Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index d91a52dacaf5..aec8ba8b9e35 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -526,8 +526,7 @@ static inline int qeth_is_cq(struct qeth_card *card, unsigned int queue)
 	    queue == card->qdio.no_in_queues - 1;
 }
 
-
-static int qeth_issue_next_read(struct qeth_card *card)
+static int __qeth_issue_next_read(struct qeth_card *card)
 {
 	int rc;
 	struct qeth_cmd_buffer *iob;
@@ -558,6 +557,17 @@ static int qeth_issue_next_read(struct qeth_card *card)
 	return rc;
 }
 
+static int qeth_issue_next_read(struct qeth_card *card)
+{
+	int ret;
+
+	spin_lock_irq(get_ccwdev_lock(CARD_RDEV(card)));
+	ret = __qeth_issue_next_read(card);
+	spin_unlock_irq(get_ccwdev_lock(CARD_RDEV(card)));
+
+	return ret;
+}
+
 static struct qeth_reply *qeth_alloc_reply(struct qeth_card *card)
 {
 	struct qeth_reply *reply;
@@ -1183,7 +1193,7 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm,
 		return;
 	if (channel == &card->read &&
 	    channel->state == CH_STATE_UP)
-		qeth_issue_next_read(card);
+		__qeth_issue_next_read(card);
 
 	iob = channel->iob;
 	index = channel->buf_no;
-- 
2.14.3


From 46a1d035ed9d9974768304b1f884fd6e4bd25556 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Tue, 20 Mar 2018 07:59:15 +0100
Subject: [PATCH 33/53] s390/qeth: on channel error, reject further cmd
 requests

[ Upstream commit a6c3d93963e4b333c764fde69802c3ea9eaa9d5c ]

When the IRQ handler determines that one of the cmd IO channels has
failed and schedules recovery, block any further cmd requests from
being submitted. The request would inevitably stall, and prevent the
recovery from making progress until the request times out.

This sort of error was observed after Live Guest Relocation, where
the pending IO on the READ channel intentionally gets terminated to
kick-start recovery. Simultaneously the guest executed SIOCETHTOOL,
triggering qeth to issue a QUERY CARD INFO command. The command
then stalled in the inoperabel WRITE channel.

Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index aec8ba8b9e35..eeabbcf7a4e2 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -1175,6 +1175,7 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm,
 		}
 		rc = qeth_get_problem(cdev, irb);
 		if (rc) {
+			card->read_or_write_problem = 1;
 			qeth_clear_ipacmd_list(card);
 			qeth_schedule_recovery(card);
 			goto out;
-- 
2.14.3


From 0a679254b9e8b9dc6bec296e59e145541f7b2609 Mon Sep 17 00:00:00 2001
From: Madalin Bucur <madalin.bucur@nxp.com>
Date: Wed, 14 Mar 2018 08:37:28 -0500
Subject: [PATCH 34/53] soc/fsl/qbman: fix issue in qman_delete_cgr_safe()

[ Upstream commit 96f413f47677366e0ae03797409bfcc4151dbf9e ]

The wait_for_completion() call in qman_delete_cgr_safe()
was triggering a scheduling while atomic bug, replacing the
kthread with a smp_call_function_single() call to fix it.

Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: Roy Pledge <roy.pledge@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/soc/fsl/qbman/qman.c | 28 +++++-----------------------
 1 file changed, 5 insertions(+), 23 deletions(-)

diff --git a/drivers/soc/fsl/qbman/qman.c b/drivers/soc/fsl/qbman/qman.c
index e4f5bb056fd2..ba3cfa8e279b 100644
--- a/drivers/soc/fsl/qbman/qman.c
+++ b/drivers/soc/fsl/qbman/qman.c
@@ -2443,39 +2443,21 @@ struct cgr_comp {
 	struct completion completion;
 };
 
-static int qman_delete_cgr_thread(void *p)
+static void qman_delete_cgr_smp_call(void *p)
 {
-	struct cgr_comp *cgr_comp = (struct cgr_comp *)p;
-	int ret;
-
-	ret = qman_delete_cgr(cgr_comp->cgr);
-	complete(&cgr_comp->completion);
-
-	return ret;
+	qman_delete_cgr((struct qman_cgr *)p);
 }
 
 void qman_delete_cgr_safe(struct qman_cgr *cgr)
 {
-	struct task_struct *thread;
-	struct cgr_comp cgr_comp;
-
 	preempt_disable();
 	if (qman_cgr_cpus[cgr->cgrid] != smp_processor_id()) {
-		init_completion(&cgr_comp.completion);
-		cgr_comp.cgr = cgr;
-		thread = kthread_create(qman_delete_cgr_thread, &cgr_comp,
-					"cgr_del");
-
-		if (IS_ERR(thread))
-			goto out;
-
-		kthread_bind(thread, qman_cgr_cpus[cgr->cgrid]);
-		wake_up_process(thread);
-		wait_for_completion(&cgr_comp.completion);
+		smp_call_function_single(qman_cgr_cpus[cgr->cgrid],
+					 qman_delete_cgr_smp_call, cgr, true);
 		preempt_enable();
 		return;
 	}
-out:
+
 	qman_delete_cgr(cgr);
 	preempt_enable();
 }
-- 
2.14.3


From c3a34eab90c0a4ea6c06cb55feca4c4f543dfae3 Mon Sep 17 00:00:00 2001
From: Madalin Bucur <madalin.bucur@nxp.com>
Date: Wed, 14 Mar 2018 08:37:29 -0500
Subject: [PATCH 35/53] dpaa_eth: fix error in dpaa_remove()

[ Upstream commit 88075256ee817041d68c2387f29065b5cb2b342a ]

The recent changes that make the driver probing compatible with DSA
were not propagated in the dpa_remove() function, breaking the
module unload function. Using the proper device to address the issue.

Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 7caa8da48421..3af5e0c08233 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -2860,7 +2860,7 @@ static int dpaa_remove(struct platform_device *pdev)
 	struct device *dev;
 	int err;
 
-	dev = &pdev->dev;
+	dev = pdev->dev.parent;
 	net_dev = dev_get_drvdata(dev);
 
 	priv = netdev_priv(net_dev);
-- 
2.14.3


From 3b79f8db6d8645f0a0c71958d19841349f312e21 Mon Sep 17 00:00:00 2001
From: Camelia Groza <camelia.groza@nxp.com>
Date: Wed, 14 Mar 2018 08:37:30 -0500
Subject: [PATCH 36/53] dpaa_eth: remove duplicate initialization

[ Upstream commit 565186362b73226a288830abe595f05f0cec0bbc ]

The fd_format has already been initialized at this point.

Signed-off-by: Camelia Groza <camelia.groza@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 3af5e0c08233..627f7f714b18 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -2278,7 +2278,6 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal,
 	vaddr = phys_to_virt(addr);
 	prefetch(vaddr + qm_fd_get_offset(fd));
 
-	fd_format = qm_fd_get_format(fd);
 	/* The only FD types that we may receive are contig and S/G */
 	WARN_ON((fd_format != qm_fd_contig) && (fd_format != qm_fd_sg));
 
-- 
2.14.3


From 833cdb91f33c878f5cdda4f061bc5aa249b92b29 Mon Sep 17 00:00:00 2001
From: Camelia Groza <camelia.groza@nxp.com>
Date: Wed, 14 Mar 2018 08:37:31 -0500
Subject: [PATCH 37/53] dpaa_eth: increment the RX dropped counter when needed

[ Upstream commit e4d1b37c17d000a3da9368a3e260fb9ea4927c25 ]

Signed-off-by: Camelia Groza <camelia.groza@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 627f7f714b18..6c0679fd78b8 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -2310,8 +2310,10 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal,
 
 	skb_len = skb->len;
 
-	if (unlikely(netif_receive_skb(skb) == NET_RX_DROP))
+	if (unlikely(netif_receive_skb(skb) == NET_RX_DROP)) {
+		percpu_stats->rx_dropped++;
 		return qman_cb_dqrr_consume;
+	}
 
 	percpu_stats->rx_packets++;
 	percpu_stats->rx_bytes += skb_len;
-- 
2.14.3


From 0893ea543cb3ae6c30ad04de6e2bf305e1559653 Mon Sep 17 00:00:00 2001
From: Camelia Groza <camelia.groza@nxp.com>
Date: Wed, 14 Mar 2018 08:37:32 -0500
Subject: [PATCH 38/53] dpaa_eth: remove duplicate increment of the tx_errors
 counter

[ Upstream commit 82d141cd19d088ee41feafde4a6f86eeb40d93c5 ]

The tx_errors counter is incremented by the dpaa_xmit caller.

Signed-off-by: Camelia Groza <camelia.groza@nxp.com>
Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 6c0679fd78b8..e4ec32a9ca15 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -2008,7 +2008,6 @@ static inline int dpaa_xmit(struct dpaa_priv *priv,
 	}
 
 	if (unlikely(err < 0)) {
-		percpu_stats->tx_errors++;
 		percpu_stats->tx_fifo_errors++;
 		return err;
 	}
-- 
2.14.3


From 61cf30d20f64a7778b284e05120e5f3e31388644 Mon Sep 17 00:00:00 2001
From: Alexey Kodanev <alexey.kodanev@oracle.com>
Date: Tue, 6 Mar 2018 22:57:01 +0300
Subject: [PATCH 39/53] dccp: check sk for closed state in dccp_sendmsg()

[ Upstream commit 67f93df79aeefc3add4e4b31a752600f834236e2 ]

dccp_disconnect() sets 'dp->dccps_hc_tx_ccid' tx handler to NULL,
therefore if DCCP socket is disconnected and dccp_sendmsg() is
called after it, it will cause a NULL pointer dereference in
dccp_write_xmit().

This crash and the reproducer was reported by syzbot. Looks like
it is reproduced if commit 69c64866ce07 ("dccp: CVE-2017-8824:
use-after-free in DCCP code") is applied.

Reported-by: syzbot+f99ab3887ab65d70f816@syzkaller.appspotmail.com
Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/proto.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 9d43c1f40274..ff3b058cf58c 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -789,6 +789,11 @@ int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	if (skb == NULL)
 		goto out_release;
 
+	if (sk->sk_state == DCCP_CLOSED) {
+		rc = -ENOTCONN;
+		goto out_discard;
+	}
+
 	skb_reserve(skb, sk->sk_prot->max_header);
 	rc = memcpy_from_msg(skb_put(skb, len), msg, len);
 	if (rc != 0)
-- 
2.14.3


From 819d388e0311f0f3d7ac301ef59459d6cb105fdb Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Thu, 8 Mar 2018 17:00:02 +0100
Subject: [PATCH 40/53] ipv6: fix access to non-linear packet in
 ndisc_fill_redirect_hdr_option()

[ Upstream commit 9f62c15f28b0d1d746734666d88a79f08ba1e43e ]

Fix the following slab-out-of-bounds kasan report in
ndisc_fill_redirect_hdr_option when the incoming ipv6 packet is not
linear and the accessed data are not in the linear data region of orig_skb.

[ 1503.122508] ==================================================================
[ 1503.122832] BUG: KASAN: slab-out-of-bounds in ndisc_send_redirect+0x94e/0x990
[ 1503.123036] Read of size 1184 at addr ffff8800298ab6b0 by task netperf/1932

[ 1503.123220] CPU: 0 PID: 1932 Comm: netperf Not tainted 4.16.0-rc2+ #124
[ 1503.123347] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.10.2-2.fc27 04/01/2014
[ 1503.123527] Call Trace:
[ 1503.123579]  <IRQ>
[ 1503.123638]  print_address_description+0x6e/0x280
[ 1503.123849]  kasan_report+0x233/0x350
[ 1503.123946]  memcpy+0x1f/0x50
[ 1503.124037]  ndisc_send_redirect+0x94e/0x990
[ 1503.125150]  ip6_forward+0x1242/0x13b0
[...]
[ 1503.153890] Allocated by task 1932:
[ 1503.153982]  kasan_kmalloc+0x9f/0xd0
[ 1503.154074]  __kmalloc_track_caller+0xb5/0x160
[ 1503.154198]  __kmalloc_reserve.isra.41+0x24/0x70
[ 1503.154324]  __alloc_skb+0x130/0x3e0
[ 1503.154415]  sctp_packet_transmit+0x21a/0x1810
[ 1503.154533]  sctp_outq_flush+0xc14/0x1db0
[ 1503.154624]  sctp_do_sm+0x34e/0x2740
[ 1503.154715]  sctp_primitive_SEND+0x57/0x70
[ 1503.154807]  sctp_sendmsg+0xaa6/0x1b10
[ 1503.154897]  sock_sendmsg+0x68/0x80
[ 1503.154987]  ___sys_sendmsg+0x431/0x4b0
[ 1503.155078]  __sys_sendmsg+0xa4/0x130
[ 1503.155168]  do_syscall_64+0x171/0x3f0
[ 1503.155259]  entry_SYSCALL_64_after_hwframe+0x42/0xb7

[ 1503.155436] Freed by task 1932:
[ 1503.155527]  __kasan_slab_free+0x134/0x180
[ 1503.155618]  kfree+0xbc/0x180
[ 1503.155709]  skb_release_data+0x27f/0x2c0
[ 1503.155800]  consume_skb+0x94/0xe0
[ 1503.155889]  sctp_chunk_put+0x1aa/0x1f0
[ 1503.155979]  sctp_inq_pop+0x2f8/0x6e0
[ 1503.156070]  sctp_assoc_bh_rcv+0x6a/0x230
[ 1503.156164]  sctp_inq_push+0x117/0x150
[ 1503.156255]  sctp_backlog_rcv+0xdf/0x4a0
[ 1503.156346]  __release_sock+0x142/0x250
[ 1503.156436]  release_sock+0x80/0x180
[ 1503.156526]  sctp_sendmsg+0xbb0/0x1b10
[ 1503.156617]  sock_sendmsg+0x68/0x80
[ 1503.156708]  ___sys_sendmsg+0x431/0x4b0
[ 1503.156799]  __sys_sendmsg+0xa4/0x130
[ 1503.156889]  do_syscall_64+0x171/0x3f0
[ 1503.156980]  entry_SYSCALL_64_after_hwframe+0x42/0xb7

[ 1503.157158] The buggy address belongs to the object at ffff8800298ab600
                which belongs to the cache kmalloc-1024 of size 1024
[ 1503.157444] The buggy address is located 176 bytes inside of
                1024-byte region [ffff8800298ab600, ffff8800298aba00)
[ 1503.157702] The buggy address belongs to the page:
[ 1503.157820] page:ffffea0000a62a00 count:1 mapcount:0 mapping:0000000000000000 index:0x0 compound_mapcount: 0
[ 1503.158053] flags: 0x4000000000008100(slab|head)
[ 1503.158171] raw: 4000000000008100 0000000000000000 0000000000000000 00000001800e000e
[ 1503.158350] raw: dead000000000100 dead000000000200 ffff880036002600 0000000000000000
[ 1503.158523] page dumped because: kasan: bad access detected

[ 1503.158698] Memory state around the buggy address:
[ 1503.158816]  ffff8800298ab900: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[ 1503.158988]  ffff8800298ab980: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[ 1503.159165] >ffff8800298aba00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[ 1503.159338]                    ^
[ 1503.159436]  ffff8800298aba80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[ 1503.159610]  ffff8800298abb00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[ 1503.159785] ==================================================================
[ 1503.159964] Disabling lock debugging due to kernel taint

The test scenario to trigger the issue consists of 4 devices:
- H0: data sender, connected to LAN0
- H1: data receiver, connected to LAN1
- GW0 and GW1: routers between LAN0 and LAN1. Both of them have an
  ethernet connection on LAN0 and LAN1
On H{0,1} set GW0 as default gateway while on GW0 set GW1 as next hop for
data from LAN0 to LAN1.
Moreover create an ip6ip6 tunnel between H0 and H1 and send 3 concurrent
data streams (TCP/UDP/SCTP) from H0 to H1 through ip6ip6 tunnel (send
buffer size is set to 16K). While data streams are active flush the route
cache on HA multiple times.
I have not been able to identify a given commit that introduced the issue
since, using the reproducer described above, the kasan report has been
triggered from 4.14 and I have not gone back further.

Reported-by: Jianlin Shi <jishi@redhat.com>
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ndisc.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index f61a5b613b52..ba5e04c6ae17 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1554,7 +1554,8 @@ static void ndisc_fill_redirect_hdr_option(struct sk_buff *skb,
 	*(opt++) = (rd_len >> 3);
 	opt += 6;
 
-	memcpy(opt, ipv6_hdr(orig_skb), rd_len - 8);
+	skb_copy_bits(orig_skb, skb_network_offset(orig_skb), opt,
+		      rd_len - 8);
 }
 
 void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
-- 
2.14.3


From a7d2c78c6900b4df78fc0b45e6d67c5c123ef61a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 6 Mar 2018 07:54:53 -0800
Subject: [PATCH 41/53] l2tp: do not accept arbitrary sockets

[ Upstream commit 17cfe79a65f98abe535261856c5aef14f306dff7 ]

syzkaller found an issue caused by lack of sufficient checks
in l2tp_tunnel_create()

RAW sockets can not be considered as UDP ones for instance.

In another patch, we shall replace all pr_err() by less intrusive
pr_debug() so that syzkaller can find other bugs faster.
Acked-by: Guillaume Nault <g.nault@alphalink.fr>
Acked-by: James Chapman <jchapman@katalix.com>

==================================================================
BUG: KASAN: slab-out-of-bounds in setup_udp_tunnel_sock+0x3ee/0x5f0 net/ipv4/udp_tunnel.c:69
dst_release: dst:00000000d53d0d0f refcnt:-1
Write of size 1 at addr ffff8801d013b798 by task syz-executor3/6242

CPU: 1 PID: 6242 Comm: syz-executor3 Not tainted 4.16.0-rc2+ #253
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x194/0x24d lib/dump_stack.c:53
 print_address_description+0x73/0x250 mm/kasan/report.c:256
 kasan_report_error mm/kasan/report.c:354 [inline]
 kasan_report+0x23b/0x360 mm/kasan/report.c:412
 __asan_report_store1_noabort+0x17/0x20 mm/kasan/report.c:435
 setup_udp_tunnel_sock+0x3ee/0x5f0 net/ipv4/udp_tunnel.c:69
 l2tp_tunnel_create+0x1354/0x17f0 net/l2tp/l2tp_core.c:1596
 pppol2tp_connect+0x14b1/0x1dd0 net/l2tp/l2tp_ppp.c:707
 SYSC_connect+0x213/0x4a0 net/socket.c:1640
 SyS_connect+0x24/0x30 net/socket.c:1621
 do_syscall_64+0x280/0x940 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x42/0xb7

Fixes: fd558d186df2 ("l2tp: Split pppol2tp patch into separate l2tp and ppp parts")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 861b67c34191..e8b26afeb194 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1466,9 +1466,14 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
 		encap = cfg->encap;
 
 	/* Quick sanity checks */
+	err = -EPROTONOSUPPORT;
+	if (sk->sk_type != SOCK_DGRAM) {
+		pr_debug("tunl %hu: fd %d wrong socket type\n",
+			 tunnel_id, fd);
+		goto err;
+	}
 	switch (encap) {
 	case L2TP_ENCAPTYPE_UDP:
-		err = -EPROTONOSUPPORT;
 		if (sk->sk_protocol != IPPROTO_UDP) {
 			pr_err("tunl %hu: fd %d wrong protocol, got %d, expected %d\n",
 			       tunnel_id, fd, sk->sk_protocol, IPPROTO_UDP);
@@ -1476,7 +1481,6 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
 		}
 		break;
 	case L2TP_ENCAPTYPE_IP:
-		err = -EPROTONOSUPPORT;
 		if (sk->sk_protocol != IPPROTO_L2TP) {
 			pr_err("tunl %hu: fd %d wrong protocol, got %d, expected %d\n",
 			       tunnel_id, fd, sk->sk_protocol, IPPROTO_L2TP);
-- 
2.14.3


From dccfc0ff1c48e7fd23264a874a2fd13eb8a22cc6 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 18 Mar 2018 23:59:36 +0100
Subject: [PATCH 42/53] net: ethernet: arc: Fix a potential memory leak if an
 optional regulator is deferred

[ Upstream commit 00777fac28ba3e126b9e63e789a613e8bd2cab25 ]

If the optional regulator is deferred, we must release some resources.
They will be re-allocated when the probe function will be called again.

Fixes: 6eacf31139bf ("ethernet: arc: Add support for Rockchip SoC layer device tree bindings")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/arc/emac_rockchip.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/arc/emac_rockchip.c b/drivers/net/ethernet/arc/emac_rockchip.c
index 16f9bee992fe..0f6576802607 100644
--- a/drivers/net/ethernet/arc/emac_rockchip.c
+++ b/drivers/net/ethernet/arc/emac_rockchip.c
@@ -169,8 +169,10 @@ static int emac_rockchip_probe(struct platform_device *pdev)
 	/* Optional regulator for PHY */
 	priv->regulator = devm_regulator_get_optional(dev, "phy");
 	if (IS_ERR(priv->regulator)) {
-		if (PTR_ERR(priv->regulator) == -EPROBE_DEFER)
-			return -EPROBE_DEFER;
+		if (PTR_ERR(priv->regulator) == -EPROBE_DEFER) {
+			err = -EPROBE_DEFER;
+			goto out_clk_disable;
+		}
 		dev_err(dev, "no regulator found\n");
 		priv->regulator = NULL;
 	}
-- 
2.14.3


From f4893adb91418402c18f8700edfb924d11ed509d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?SZ=20Lin=20=28=E6=9E=97=E4=B8=8A=E6=99=BA=29?=
 <sz.lin@moxa.com>
Date: Fri, 16 Mar 2018 00:56:01 +0800
Subject: [PATCH 43/53] net: ethernet: ti: cpsw: add check for in-band mode
 setting with RGMII PHY interface
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit f9db50691db4a7d860fce985f080bb3fc23a7ede ]

According to AM335x TRM[1] 14.3.6.2, AM437x TRM[2] 15.3.6.2 and
DRA7 TRM[3] 24.11.4.8.7.3.3, in-band mode in EXT_EN(bit18) register is only
available when PHY is configured in RGMII mode with 10Mbps speed. It will
cause some networking issues without RGMII mode, such as carrier sense
errors and low throughput. TI also mentioned this issue in their forum[4].

This patch adds the check mechanism for PHY interface with RGMII interface
type, the in-band mode can only be set in RGMII mode with 10Mbps speed.

References:
[1]: https://www.ti.com/lit/ug/spruh73p/spruh73p.pdf
[2]: http://www.ti.com/lit/ug/spruhl7h/spruhl7h.pdf
[3]: http://www.ti.com/lit/ug/spruic2b/spruic2b.pdf
[4]: https://e2e.ti.com/support/arm/sitara_arm/f/791/p/640765/2392155

Suggested-by: Holsety Chen (陳憲輝) <Holsety.Chen@moxa.com>
Signed-off-by: SZ Lin (林上智) <sz.lin@moxa.com>
Signed-off-by: Schuyler Patton <spatton@ti.com>
Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index a1ffc3ed77f9..c08d74cd1fd2 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -996,7 +996,8 @@ static void _cpsw_adjust_link(struct cpsw_slave *slave,
 		/* set speed_in input in case RMII mode is used in 100Mbps */
 		if (phy->speed == 100)
 			mac_control |= BIT(15);
-		else if (phy->speed == 10)
+		/* in band mode only works in 10Mbps RGMII mode */
+		else if ((phy->speed == 10) && phy_interface_is_rgmii(phy))
 			mac_control |= BIT(18); /* In Band mode */
 
 		if (priv->rx_pause)
-- 
2.14.3


From 1315605f9e25bfc9beac35b74c547052f264448a Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Sun, 18 Mar 2018 12:49:51 -0700
Subject: [PATCH 44/53] net: fec: Fix unbalanced PM runtime calls

[ Upstream commit a069215cf5985f3aa1bba550264907d6bd05c5f7 ]

When unbinding/removing the driver, we will run into the following warnings:

[  259.655198] fec 400d1000.ethernet: 400d1000.ethernet supply phy not found, using dummy regulator
[  259.665065] fec 400d1000.ethernet: Unbalanced pm_runtime_enable!
[  259.672770] fec 400d1000.ethernet (unnamed net_device) (uninitialized): Invalid MAC address: 00:00:00:00:00:00
[  259.683062] fec 400d1000.ethernet (unnamed net_device) (uninitialized): Using random MAC address: f2:3e:93:b7:29:c1
[  259.696239] libphy: fec_enet_mii_bus: probed

Avoid these warnings by balancing the runtime PM calls during fec_drv_remove().

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index a74300a4459c..febadd39e29a 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -3578,6 +3578,8 @@ fec_drv_remove(struct platform_device *pdev)
 	fec_enet_mii_remove(fep);
 	if (fep->reg_phy)
 		regulator_disable(fep->reg_phy);
+	pm_runtime_put(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
 	if (of_phy_is_fixed_link(np))
 		of_phy_deregister_fixed_link(np);
 	of_node_put(fep->phy_node);
-- 
2.14.3


From fce25887e03cd4229904f83326b772c735538acf Mon Sep 17 00:00:00 2001
From: Arvind Yadav <arvind.yadav.cs@gmail.com>
Date: Tue, 13 Mar 2018 16:50:06 +0100
Subject: [PATCH 45/53] net/iucv: Free memory obtained by kzalloc

[ Upstream commit fa6a91e9b907231d2e38ea5ed89c537b3525df3d ]

Free memory by calling put_device(), if afiucv_iucv_init is not
successful.

Signed-off-by: Arvind Yadav <arvind.yadav.cs@gmail.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Signed-off-by: Ursula Braun <ursula.braun@de.ibm.com>
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/iucv/af_iucv.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 148533169b1d..ca98276c2709 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -2433,9 +2433,11 @@ static int afiucv_iucv_init(void)
 	af_iucv_dev->driver = &af_iucv_driver;
 	err = device_register(af_iucv_dev);
 	if (err)
-		goto out_driver;
+		goto out_iucv_dev;
 	return 0;
 
+out_iucv_dev:
+	put_device(af_iucv_dev);
 out_driver:
 	driver_unregister(&af_iucv_driver);
 out_iucv:
-- 
2.14.3


From ce243078804024491208766690b1b577d51438f2 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Wed, 14 Mar 2018 21:10:23 +0100
Subject: [PATCH 46/53] netlink: avoid a double skb free in genlmsg_mcast()

[ Upstream commit 02a2385f37a7c6594c9d89b64c4a1451276f08eb ]

nlmsg_multicast() consumes always the skb, thus the original skb must be
freed only when this function is called with a clone.

Fixes: cb9f7a9a5c96 ("netlink: ensure to loop over all netns in genlmsg_multicast_allns()")
Reported-by: Ben Hutchings <ben.hutchings@codethink.co.uk>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/genetlink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 6f02499ef007..b9ce82c9440f 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -1106,7 +1106,7 @@ static int genlmsg_mcast(struct sk_buff *skb, u32 portid, unsigned long group,
 	if (!err)
 		delivered = true;
 	else if (err != -ESRCH)
-		goto error;
+		return err;
 	return delivered ? 0 : -ESRCH;
  error:
 	kfree_skb(skb);
-- 
2.14.3


From 1e781dc6b00e71f5fb9c522100c376bdf84a255a Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Fri, 16 Feb 2018 11:03:03 -0800
Subject: [PATCH 47/53] net: Only honor ifindex in IP_PKTINFO if non-0

[ Upstream commit 2cbb4ea7de167b02ffa63e9cdfdb07a7e7094615 ]

Only allow ifindex from IP_PKTINFO to override SO_BINDTODEVICE settings
if the index is actually set in the message.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_sockglue.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index f56aab54e0c8..1e70ed5244ea 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -258,7 +258,8 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc,
 			src_info = (struct in6_pktinfo *)CMSG_DATA(cmsg);
 			if (!ipv6_addr_v4mapped(&src_info->ipi6_addr))
 				return -EINVAL;
-			ipc->oif = src_info->ipi6_ifindex;
+			if (src_info->ipi6_ifindex)
+				ipc->oif = src_info->ipi6_ifindex;
 			ipc->addr = src_info->ipi6_addr.s6_addr32[3];
 			continue;
 		}
@@ -288,7 +289,8 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc,
 			if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct in_pktinfo)))
 				return -EINVAL;
 			info = (struct in_pktinfo *)CMSG_DATA(cmsg);
-			ipc->oif = info->ipi_ifindex;
+			if (info->ipi_ifindex)
+				ipc->oif = info->ipi_ifindex;
 			ipc->addr = info->ipi_spec_dst.s_addr;
 			break;
 		}
-- 
2.14.3


From 834e35a13603c71924ead3b7bc897fa8f414a17d Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 13 Mar 2018 14:45:07 -0700
Subject: [PATCH 48/53] net: systemport: Rewrite __bcm_sysport_tx_reclaim()

[ Upstream commit 484d802d0f2f29c335563fcac2a8facf174a1bbc ]

There is no need for complex checking between the last consumed index
and current consumed index, a simple subtraction will do.

This also eliminates the possibility of a permanent transmit queue stall
under the following conditions:

- one CPU bursts ring->size worth of traffic (up to 256 buffers), to the
  point where we run out of free descriptors, so we stop the transmit
  queue at the end of bcm_sysport_xmit()

- because of our locking, we have the transmit process disable
  interrupts which means we can be blocking the TX reclamation process

- when TX reclamation finally runs, we will be computing the difference
  between ring->c_index (last consumed index by SW) and what the HW
  reports through its register

- this register is masked with (ring->size - 1) = 0xff, which will lead
  to stripping the upper bits of the index (register is 16-bits wide)

- we will be computing last_tx_cn as 0, which means there is no work to
  be done, and we never wake-up the transmit queue, leaving it
  permanently disabled

A practical example is e.g: ring->c_index aka last_c_index = 12, we
pushed 256 entries, HW consumer index = 268, we mask it with 0xff = 12,
so last_tx_cn == 0, nothing happens.

Fixes: 80105befdb4b ("net: systemport: add Broadcom SYSTEMPORT Ethernet MAC driver")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bcmsysport.c | 33 ++++++++++++++----------------
 drivers/net/ethernet/broadcom/bcmsysport.h |  2 +-
 2 files changed, 16 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 087f01b4dc3a..f239ef2e6f23 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -855,10 +855,12 @@ static void bcm_sysport_tx_reclaim_one(struct bcm_sysport_tx_ring *ring,
 static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv,
 					     struct bcm_sysport_tx_ring *ring)
 {
-	unsigned int c_index, last_c_index, last_tx_cn, num_tx_cbs;
 	unsigned int pkts_compl = 0, bytes_compl = 0;
 	struct net_device *ndev = priv->netdev;
+	unsigned int txbds_processed = 0;
 	struct bcm_sysport_cb *cb;
+	unsigned int txbds_ready;
+	unsigned int c_index;
 	u32 hw_ind;
 
 	/* Clear status before servicing to reduce spurious interrupts */
@@ -871,29 +873,23 @@ static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv,
 	/* Compute how many descriptors have been processed since last call */
 	hw_ind = tdma_readl(priv, TDMA_DESC_RING_PROD_CONS_INDEX(ring->index));
 	c_index = (hw_ind >> RING_CONS_INDEX_SHIFT) & RING_CONS_INDEX_MASK;
-	ring->p_index = (hw_ind & RING_PROD_INDEX_MASK);
-
-	last_c_index = ring->c_index;
-	num_tx_cbs = ring->size;
-
-	c_index &= (num_tx_cbs - 1);
-
-	if (c_index >= last_c_index)
-		last_tx_cn = c_index - last_c_index;
-	else
-		last_tx_cn = num_tx_cbs - last_c_index + c_index;
+	txbds_ready = (c_index - ring->c_index) & RING_CONS_INDEX_MASK;
 
 	netif_dbg(priv, tx_done, ndev,
-		  "ring=%d c_index=%d last_tx_cn=%d last_c_index=%d\n",
-		  ring->index, c_index, last_tx_cn, last_c_index);
+		  "ring=%d old_c_index=%u c_index=%u txbds_ready=%u\n",
+		  ring->index, ring->c_index, c_index, txbds_ready);
 
-	while (last_tx_cn-- > 0) {
-		cb = ring->cbs + last_c_index;
+	while (txbds_processed < txbds_ready) {
+		cb = &ring->cbs[ring->clean_index];
 		bcm_sysport_tx_reclaim_one(ring, cb, &bytes_compl, &pkts_compl);
 
 		ring->desc_count++;
-		last_c_index++;
-		last_c_index &= (num_tx_cbs - 1);
+		txbds_processed++;
+
+		if (likely(ring->clean_index < ring->size - 1))
+			ring->clean_index++;
+		else
+			ring->clean_index = 0;
 	}
 
 	u64_stats_update_begin(&priv->syncp);
@@ -1406,6 +1402,7 @@ static int bcm_sysport_init_tx_ring(struct bcm_sysport_priv *priv,
 	netif_tx_napi_add(priv->netdev, &ring->napi, bcm_sysport_tx_poll, 64);
 	ring->index = index;
 	ring->size = size;
+	ring->clean_index = 0;
 	ring->alloc_size = ring->size;
 	ring->desc_cpu = p;
 	ring->desc_count = ring->size;
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h
index f5a984c1c986..19c91c76e327 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.h
+++ b/drivers/net/ethernet/broadcom/bcmsysport.h
@@ -706,7 +706,7 @@ struct bcm_sysport_tx_ring {
 	unsigned int	desc_count;	/* Number of descriptors */
 	unsigned int	curr_desc;	/* Current descriptor */
 	unsigned int	c_index;	/* Last consumer index */
-	unsigned int	p_index;	/* Current producer index */
+	unsigned int	clean_index;	/* Current clean index */
 	struct bcm_sysport_cb *cbs;	/* Transmit control blocks */
 	struct dma_desc	*desc_cpu;	/* CPU view of the descriptor */
 	struct bcm_sysport_priv *priv;	/* private context backpointer */
-- 
2.14.3


From de82b623b4958c061edbe39f6557b0da1fda075a Mon Sep 17 00:00:00 2001
From: Michal Kalderon <Michal.Kalderon@cavium.com>
Date: Wed, 14 Mar 2018 14:56:53 +0200
Subject: [PATCH 49/53] qede: Fix qedr link update

[ Upstream commit 4609adc27175839408359822523de7247d56c87f ]

Link updates were not reported to qedr correctly.
Leading to cases where a link could be down, but qedr
would see it as up.
In addition, once qede was loaded, link state would be up,
regardless of the actual link state.

Signed-off-by: Michal Kalderon <michal.kalderon@cavium.com>
Signed-off-by: Ariel Elior <ariel.elior@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qede/qede_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 8f9b3eb82137..cdcccecfc24a 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -2066,8 +2066,6 @@ static int qede_load(struct qede_dev *edev, enum qede_load_mode mode,
 	link_params.link_up = true;
 	edev->ops->common->set_link(edev->cdev, &link_params);
 
-	qede_rdma_dev_event_open(edev);
-
 	edev->state = QEDE_STATE_OPEN;
 
 	DP_INFO(edev, "Ending successfully qede load\n");
@@ -2168,12 +2166,14 @@ static void qede_link_update(void *dev, struct qed_link_output *link)
 			DP_NOTICE(edev, "Link is up\n");
 			netif_tx_start_all_queues(edev->ndev);
 			netif_carrier_on(edev->ndev);
+			qede_rdma_dev_event_open(edev);
 		}
 	} else {
 		if (netif_carrier_ok(edev->ndev)) {
 			DP_NOTICE(edev, "Link is down\n");
 			netif_tx_disable(edev->ndev);
 			netif_carrier_off(edev->ndev);
+			qede_rdma_dev_event_close(edev);
 		}
 	}
 }
-- 
2.14.3


From a83aa28cc97498fd95e6a8b2a6ec1f1178edf39f Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Wed, 14 Mar 2018 13:32:09 -0700
Subject: [PATCH 50/53] skbuff: Fix not waking applications when errors are
 enqueued

[ Upstream commit 6e5d58fdc9bedd0255a8781b258f10bbdc63e975 ]

When errors are enqueued to the error queue via sock_queue_err_skb()
function, it is possible that the waiting application is not notified.

Calling 'sk->sk_data_ready()' would not notify applications that
selected only POLLERR events in poll() (for example).

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: Randy E. Witt <randy.e.witt@intel.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 08f574081315..3538ba8771e9 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4173,7 +4173,7 @@ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
 
 	skb_queue_tail(&sk->sk_error_queue, skb);
 	if (!sock_flag(sk, SOCK_DEAD))
-		sk->sk_data_ready(sk);
+		sk->sk_error_report(sk);
 	return 0;
 }
 EXPORT_SYMBOL(sock_queue_err_skb);
-- 
2.14.3


From 419a07522a6a8c10827b306786ed42af5138ca84 Mon Sep 17 00:00:00 2001
From: Arkadi Sharshevsky <arkadis@mellanox.com>
Date: Thu, 8 Mar 2018 12:42:10 +0200
Subject: [PATCH 51/53] team: Fix double free in error path

[ Upstream commit cbcc607e18422555db569b593608aec26111cb0b ]

The __send_and_alloc_skb() receives a skb ptr as a parameter but in
case it fails the skb is not valid:
- Send failed and released the skb internally.
- Allocation failed.

The current code tries to release the skb in case of failure which
causes redundant freeing.

Fixes: 9b00cf2d1024 ("team: implement multipart netlink messages for options transfers")
Signed-off-by: Arkadi Sharshevsky <arkadis@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index a468439969df..56c701b73c12 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -2395,7 +2395,7 @@ static int team_nl_send_options_get(struct team *team, u32 portid, u32 seq,
 	if (!nlh) {
 		err = __send_and_alloc_skb(&skb, team, portid, send_func);
 		if (err)
-			goto errout;
+			return err;
 		goto send_done;
 	}
 
@@ -2681,7 +2681,7 @@ static int team_nl_send_port_list_get(struct team *team, u32 portid, u32 seq,
 	if (!nlh) {
 		err = __send_and_alloc_skb(&skb, team, portid, send_func);
 		if (err)
-			goto errout;
+			return err;
 		goto send_done;
 	}
 
-- 
2.14.3

Re: [PATCHES] Networking

[Willy Tarreau]

Hi David,

On Wed, Mar 28, 2018 at 11:35:10AM -0400, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.14 and v4.15
> -stable, respecetively.

I don't know if you saw my e-mail last week about this patch that's
part of the 4.14 queue :

   [linux-stable-4.14] tcp: reset sk_send_head in tcp_write_queue_purge

There are some typos in commit IDs referenced in the commit message
which I think should be edited before being merged (especially since
this one is stable-only and not in mainline) :

    "27fid7a8ed38"  => "a27fd7a8ed38"
    "a27fid7a8ed38" => "a27fd7a8ed38"  (Fixes: line)

Greg, maybe it's better to edit this before applying ?

Thanks,
Willy

Re: [PATCHES] Networking

[David Miller]

From: Willy Tarreau <w@1wt.eu>
Date: Wed, 28 Mar 2018 17:40:15 +0200

> Hi David,
> 
> On Wed, Mar 28, 2018 at 11:35:10AM -0400, David Miller wrote:
>> 
>> Please queue up the following networking bug fixes for v4.14 and v4.15
>> -stable, respecetively.
> 
> I don't know if you saw my e-mail last week about this patch that's
> part of the 4.14 queue :
> 
>    [linux-stable-4.14] tcp: reset sk_send_head in tcp_write_queue_purge
> 
> There are some typos in commit IDs referenced in the commit message
> which I think should be edited before being merged (especially since
> this one is stable-only and not in mainline) :
> 
>     "27fid7a8ed38"  => "a27fd7a8ed38"
>     "a27fid7a8ed38" => "a27fd7a8ed38"  (Fixes: line)
> 
> Greg, maybe it's better to edit this before applying ?

Greg, feel free to correct this.

Thanks Willy.

Re: [PATCHES] Networking

[Greg KH]

On Wed, Mar 28, 2018 at 11:46:05AM -0400, David Miller wrote:
> From: Willy Tarreau <w@1wt.eu>
> Date: Wed, 28 Mar 2018 17:40:15 +0200
> 
> > Hi David,
> > 
> > On Wed, Mar 28, 2018 at 11:35:10AM -0400, David Miller wrote:
> >> 
> >> Please queue up the following networking bug fixes for v4.14 and v4.15
> >> -stable, respecetively.
> > 
> > I don't know if you saw my e-mail last week about this patch that's
> > part of the 4.14 queue :
> > 
> >    [linux-stable-4.14] tcp: reset sk_send_head in tcp_write_queue_purge
> > 
> > There are some typos in commit IDs referenced in the commit message
> > which I think should be edited before being merged (especially since
> > this one is stable-only and not in mainline) :
> > 
> >     "27fid7a8ed38"  => "a27fd7a8ed38"
> >     "a27fid7a8ed38" => "a27fd7a8ed38"  (Fixes: line)
> > 
> > Greg, maybe it's better to edit this before applying ?
> 
> Greg, feel free to correct this.

Now fixed up, thanks.

greg k-h

Re: [PATCHES] Networking

[Greg KH]

On Wed, Mar 28, 2018 at 11:35:10AM -0400, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.14 and v4.15
> -stable, respecetively.

Thanks so much for these, now queued up.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 115 bytes --]


Please queue up the following networking bug fixes for v4.14,
v4.15, and v4.16 -stable, respectively.

Thank you!

[-- Attachment #2: net_414.mbox --]
[-- Type: Application/Octet-Stream, Size: 110394 bytes --]

From e50aee799b2f06172b157b6d1b1a25d93051862c Mon Sep 17 00:00:00 2001
From: Miguel Fadon Perlines <mfadon@teldat.com>
Date: Thu, 5 Apr 2018 10:25:38 +0200
Subject: [PATCH 01/42] arp: fix arp_filter on l3slave devices

[ Upstream commit 58b35f27689b5eb514fc293c332966c226b1b6e4 ]

arp_filter performs an ip_route_output search for arp source address and
checks if output device is the same where the arp request was received,
if it is not, the arp request is not answered.

This route lookup is always done on main route table so l3slave devices
never find the proper route and arp is not answered.

Passing l3mdev_master_ifindex_rcu(dev) return value as oif fixes the
lookup for l3slave devices while maintaining same behavior for non
l3slave devices as this function returns 0 in that case.

Fixes: 613d09b30f8b ("net: Use VRF device index for lookups on TX")
Signed-off-by: Miguel Fadon Perlines <mfadon@teldat.com>
Acked-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/arp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index a1d1f50e0e19..7d9cf26f4bb1 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -437,7 +437,7 @@ static int arp_filter(__be32 sip, __be32 tip, struct net_device *dev)
 	/*unsigned long now; */
 	struct net *net = dev_net(dev);
 
-	rt = ip_route_output(net, sip, tip, 0, 0);
+	rt = ip_route_output(net, sip, tip, 0, l3mdev_master_ifindex_rcu(dev));
 	if (IS_ERR(rt))
 		return 1;
 	if (rt->dst.dev != dev) {
-- 
2.14.3


From bf9bd0eea21d1176b656c4f9258e1f8af2d28367 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 23 Mar 2018 14:47:30 +0100
Subject: [PATCH 02/42] ipv6: the entire IPv6 header chain must fit the first
 fragment

[ Upstream commit 10b8a3de603df7b96004179b1b33b1708c76d144 ]

While building ipv6 datagram we currently allow arbitrary large
extheaders, even beyond pmtu size. The syzbot has found a way
to exploit the above to trigger the following splat:

kernel BUG at ./include/linux/skbuff.h:2073!
invalid opcode: 0000 [#1] SMP KASAN
Dumping ftrace buffer:
    (ftrace buffer empty)
Modules linked in:
CPU: 1 PID: 4230 Comm: syzkaller672661 Not tainted 4.16.0-rc2+ #326
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
RIP: 0010:__skb_pull include/linux/skbuff.h:2073 [inline]
RIP: 0010:__ip6_make_skb+0x1ac8/0x2190 net/ipv6/ip6_output.c:1636
RSP: 0018:ffff8801bc18f0f0 EFLAGS: 00010293
RAX: ffff8801b17400c0 RBX: 0000000000000738 RCX: ffffffff84f01828
RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff8801b415ac18
RBP: ffff8801bc18f360 R08: ffff8801b4576844 R09: 0000000000000000
R10: ffff8801bc18f380 R11: ffffed00367aee4e R12: 00000000000000d6
R13: ffff8801b415a740 R14: dffffc0000000000 R15: ffff8801b45767c0
FS:  0000000001535880(0000) GS:ffff8801db300000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000000002000b000 CR3: 00000001b4123001 CR4: 00000000001606e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
  ip6_finish_skb include/net/ipv6.h:969 [inline]
  udp_v6_push_pending_frames+0x269/0x3b0 net/ipv6/udp.c:1073
  udpv6_sendmsg+0x2a96/0x3400 net/ipv6/udp.c:1343
  inet_sendmsg+0x11f/0x5e0 net/ipv4/af_inet.c:764
  sock_sendmsg_nosec net/socket.c:630 [inline]
  sock_sendmsg+0xca/0x110 net/socket.c:640
  ___sys_sendmsg+0x320/0x8b0 net/socket.c:2046
  __sys_sendmmsg+0x1ee/0x620 net/socket.c:2136
  SYSC_sendmmsg net/socket.c:2167 [inline]
  SyS_sendmmsg+0x35/0x60 net/socket.c:2162
  do_syscall_64+0x280/0x940 arch/x86/entry/common.c:287
  entry_SYSCALL_64_after_hwframe+0x42/0xb7
RIP: 0033:0x4404c9
RSP: 002b:00007ffdce35f948 EFLAGS: 00000217 ORIG_RAX: 0000000000000133
RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 00000000004404c9
RDX: 0000000000000003 RSI: 0000000020001f00 RDI: 0000000000000003
RBP: 00000000006cb018 R08: 00000000004002c8 R09: 00000000004002c8
R10: 0000000020000080 R11: 0000000000000217 R12: 0000000000401df0
R13: 0000000000401e80 R14: 0000000000000000 R15: 0000000000000000
Code: ff e8 1d 5e b9 fc e9 15 e9 ff ff e8 13 5e b9 fc e9 44 e8 ff ff e8 29
5e b9 fc e9 c0 e6 ff ff e8 3f f3 80 fc 0f 0b e8 38 f3 80 fc <0f> 0b 49 8d
87 80 00 00 00 4d 8d 87 84 00 00 00 48 89 85 20 fe
RIP: __skb_pull include/linux/skbuff.h:2073 [inline] RSP: ffff8801bc18f0f0
RIP: __ip6_make_skb+0x1ac8/0x2190 net/ipv6/ip6_output.c:1636 RSP:
ffff8801bc18f0f0

As stated by RFC 7112 section 5:

   When a host fragments an IPv6 datagram, it MUST include the entire
   IPv6 Header Chain in the First Fragment.

So this patch addresses the issue dropping datagrams with excessive
extheader length. It also updates the error path to report to the
calling socket nonnegative pmtu values.

The issue apparently predates git history.

v1 -> v2: cleanup error path, as per Eric's suggestion

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzbot+91e6f9932ff122fa4410@syzkaller.appspotmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_output.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 3763dc01e374..ef22ee9f3443 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1237,7 +1237,7 @@ static int __ip6_append_data(struct sock *sk,
 			     const struct sockcm_cookie *sockc)
 {
 	struct sk_buff *skb, *skb_prev = NULL;
-	unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu;
+	unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu, pmtu;
 	int exthdrlen = 0;
 	int dst_exthdrlen = 0;
 	int hh_len;
@@ -1273,6 +1273,12 @@ static int __ip6_append_data(struct sock *sk,
 		      sizeof(struct frag_hdr) : 0) +
 		     rt->rt6i_nfheader_len;
 
+	/* as per RFC 7112 section 5, the entire IPv6 Header Chain must fit
+	 * the first fragment
+	 */
+	if (headersize + transhdrlen > mtu)
+		goto emsgsize;
+
 	if (cork->length + length > mtu - headersize && ipc6->dontfrag &&
 	    (sk->sk_protocol == IPPROTO_UDP ||
 	     sk->sk_protocol == IPPROTO_RAW)) {
@@ -1288,9 +1294,8 @@ static int __ip6_append_data(struct sock *sk,
 
 	if (cork->length + length > maxnonfragsize - headersize) {
 emsgsize:
-		ipv6_local_error(sk, EMSGSIZE, fl6,
-				 mtu - headersize +
-				 sizeof(struct ipv6hdr));
+		pmtu = max_t(int, mtu - headersize + sizeof(struct ipv6hdr), 0);
+		ipv6_local_error(sk, EMSGSIZE, fl6, pmtu);
 		return -EMSGSIZE;
 	}
 
-- 
2.14.3


From 96d8854d1527e2d69c1cd460fedec42c72e5a912 Mon Sep 17 00:00:00 2001
From: Raghuram Chary J <raghuramchary.jallipalli@microchip.com>
Date: Tue, 27 Mar 2018 14:51:16 +0530
Subject: [PATCH 03/42] lan78xx: Crash in lan78xx_writ_reg (Workqueue: events
 lan78xx_deferred_multicast_write)

[ Upstream commit 2d2d99ec13f62d5d2cecb6169dfdb6bbe05356d0 ]

Description:
Crash was reported with syzkaller pointing to lan78xx_write_reg routine.

Root-cause:
Proper cleanup of workqueues and init/setup routines was not happening
in failure conditions.

Fix:
Handled the error conditions by cleaning up the queues and init/setup
routines.

Fixes: 55d7de9de6c3 ("Microchip's LAN7800 family USB 2/3 to 10/100/1000 Ethernet device driver")
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Raghuram Chary J <raghuramchary.jallipalli@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/lan78xx.c | 23 +++++++++++++++++++++--
 1 file changed, 21 insertions(+), 2 deletions(-)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index a8dd1c7a08cb..89d82c4ee8df 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -2863,8 +2863,7 @@ static int lan78xx_bind(struct lan78xx_net *dev, struct usb_interface *intf)
 	if (ret < 0) {
 		netdev_warn(dev->net,
 			    "lan78xx_setup_irq_domain() failed : %d", ret);
-		kfree(pdata);
-		return ret;
+		goto out1;
 	}
 
 	dev->net->hard_header_len += TX_OVERHEAD;
@@ -2872,14 +2871,32 @@ static int lan78xx_bind(struct lan78xx_net *dev, struct usb_interface *intf)
 
 	/* Init all registers */
 	ret = lan78xx_reset(dev);
+	if (ret) {
+		netdev_warn(dev->net, "Registers INIT FAILED....");
+		goto out2;
+	}
 
 	ret = lan78xx_mdio_init(dev);
+	if (ret) {
+		netdev_warn(dev->net, "MDIO INIT FAILED.....");
+		goto out2;
+	}
 
 	dev->net->flags |= IFF_MULTICAST;
 
 	pdata->wol = WAKE_MAGIC;
 
 	return ret;
+
+out2:
+	lan78xx_remove_irq_domain(dev);
+
+out1:
+	netdev_warn(dev->net, "Bind routine FAILED");
+	cancel_work_sync(&pdata->set_multicast);
+	cancel_work_sync(&pdata->set_vlan);
+	kfree(pdata);
+	return ret;
 }
 
 static void lan78xx_unbind(struct lan78xx_net *dev, struct usb_interface *intf)
@@ -2891,6 +2908,8 @@ static void lan78xx_unbind(struct lan78xx_net *dev, struct usb_interface *intf)
 	lan78xx_remove_mdio(dev);
 
 	if (pdata) {
+		cancel_work_sync(&pdata->set_multicast);
+		cancel_work_sync(&pdata->set_vlan);
 		netif_dbg(dev, ifdown, dev->net, "free pdata");
 		kfree(pdata);
 		pdata = NULL;
-- 
2.14.3


From 30a6a387010f4967729a111348af41c761d17073 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 26 Mar 2018 08:08:07 -0700
Subject: [PATCH 04/42] net: fix possible out-of-bound read in
 skb_network_protocol()

[ Upstream commit 1dfe82ebd7d8fd43dba9948fdfb31f145014baa0 ]

skb mac header is not necessarily set at the time skb_network_protocol()
is called. Use skb->data instead.

BUG: KASAN: slab-out-of-bounds in skb_network_protocol+0x46b/0x4b0 net/core/dev.c:2739
Read of size 2 at addr ffff8801b3097a0b by task syz-executor5/14242

CPU: 1 PID: 14242 Comm: syz-executor5 Not tainted 4.16.0-rc6+ #280
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x194/0x24d lib/dump_stack.c:53
 print_address_description+0x73/0x250 mm/kasan/report.c:256
 kasan_report_error mm/kasan/report.c:354 [inline]
 kasan_report+0x23c/0x360 mm/kasan/report.c:412
 __asan_report_load_n_noabort+0xf/0x20 mm/kasan/report.c:443
 skb_network_protocol+0x46b/0x4b0 net/core/dev.c:2739
 harmonize_features net/core/dev.c:2924 [inline]
 netif_skb_features+0x509/0x9b0 net/core/dev.c:3011
 validate_xmit_skb+0x81/0xb00 net/core/dev.c:3084
 validate_xmit_skb_list+0xbf/0x120 net/core/dev.c:3142
 packet_direct_xmit+0x117/0x790 net/packet/af_packet.c:256
 packet_snd net/packet/af_packet.c:2944 [inline]
 packet_sendmsg+0x3aed/0x60b0 net/packet/af_packet.c:2969
 sock_sendmsg_nosec net/socket.c:629 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:639
 ___sys_sendmsg+0x767/0x8b0 net/socket.c:2047
 __sys_sendmsg+0xe5/0x210 net/socket.c:2081

Fixes: 19acc327258a ("gso: Handle Trans-Ether-Bridging protocol in skb_network_protocol()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Pravin B Shelar <pshelar@ovn.org>
Reported-by: Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 387af3415385..ef3337bb71a2 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2696,7 +2696,7 @@ __be16 skb_network_protocol(struct sk_buff *skb, int *depth)
 		if (unlikely(!pskb_may_pull(skb, sizeof(struct ethhdr))))
 			return 0;
 
-		eth = (struct ethhdr *)skb_mac_header(skb);
+		eth = (struct ethhdr *)skb->data;
 		type = eth->h_proto;
 	}
 
-- 
2.14.3


From 950bc63ec1b919bda281b199e8b81ba307f55c42 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Thu, 29 Mar 2018 17:44:57 -0700
Subject: [PATCH 05/42] net/ipv6: Fix route leaking between VRFs

[ Upstream commit b6cdbc85234b072340b8923e69f49ec293f905dc ]

Donald reported that IPv6 route leaking between VRFs is not working.
The root cause is the strict argument in the call to rt6_lookup when
validating the nexthop spec.

ip6_route_check_nh validates the gateway and device (if given) of a
route spec. It in turn could call rt6_lookup (e.g., lookup in a given
table did not succeed so it falls back to a full lookup) and if so
sets the strict argument to 1. That means if the egress device is given,
the route lookup needs to return a result with the same device. This
strict requirement does not work with VRFs (IPv4 or IPv6) because the
oif in the flow struct is overridden with the index of the VRF device
to trigger a match on the l3mdev rule and force the lookup to its table.

The right long term solution is to add an l3mdev index to the flow
struct such that the oif is not overridden. That solution will not
backport well, so this patch aims for a simpler solution to relax the
strict argument if the route spec device is an l3mdev slave. As done
in other places, use the FLOWI_FLAG_SKIP_NH_OIF to know that the
RT6_LOOKUP_F_IFACE flag needs to be removed.

Fixes: ca254490c8df ("net: Add VRF support to IPv6 stack")
Reported-by: Donald Sharp <sharpd@cumulusnetworks.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index a4a865c8a23c..0126d9bfa670 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -871,6 +871,9 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net,
 	struct fib6_node *fn;
 	struct rt6_info *rt;
 
+	if (fl6->flowi6_flags & FLOWI_FLAG_SKIP_NH_OIF)
+		flags &= ~RT6_LOOKUP_F_IFACE;
+
 	read_lock_bh(&table->tb6_lock);
 	fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
 restart:
-- 
2.14.3


From e2b20f54ae4e5df8da49134bb4efe364da2db92a Mon Sep 17 00:00:00 2001
From: Jeff Barnhill <0xeffeff@gmail.com>
Date: Thu, 5 Apr 2018 21:29:47 +0000
Subject: [PATCH 06/42] net/ipv6: Increment OUTxxx counters after netfilter
 hook

[ Upstream commit 71a1c915238c970cd9bdd5bf158b1279d6b6d55b ]

At the end of ip6_forward(), IPSTATS_MIB_OUTFORWDATAGRAMS and
IPSTATS_MIB_OUTOCTETS are incremented immediately before the NF_HOOK call
for NFPROTO_IPV6 / NF_INET_FORWARD.  As a result, these counters get
incremented regardless of whether or not the netfilter hook allows the
packet to continue being processed.  This change increments the counters
in ip6_forward_finish() so that it will not happen if the netfilter hook
chooses to terminate the packet, which is similar to how IPv4 works.

Signed-off-by: Jeff Barnhill <0xeffeff@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_output.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index ef22ee9f3443..1cf7459f1a73 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -367,6 +367,11 @@ static int ip6_forward_proxy_check(struct sk_buff *skb)
 static inline int ip6_forward_finish(struct net *net, struct sock *sk,
 				     struct sk_buff *skb)
 {
+	struct dst_entry *dst = skb_dst(skb);
+
+	__IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS);
+	__IP6_ADD_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTOCTETS, skb->len);
+
 	return dst_output(net, sk, skb);
 }
 
@@ -560,8 +565,6 @@ int ip6_forward(struct sk_buff *skb)
 
 	hdr->hop_limit--;
 
-	__IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS);
-	__IP6_ADD_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTOCTETS, skb->len);
 	return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD,
 		       net, NULL, skb, skb->dev, dst->dev,
 		       ip6_forward_finish);
-- 
2.14.3


From bf3c24245c4f4ab9269cf4d59d46f3f8716a0d85 Mon Sep 17 00:00:00 2001
From: Alexander Potapenko <glider@google.com>
Date: Fri, 23 Mar 2018 13:49:02 +0100
Subject: [PATCH 07/42] netlink: make sure nladdr has correct size in
 netlink_connect()

[ Upstream commit 7880287981b60a6808f39f297bb66936e8bdf57a ]

KMSAN reports use of uninitialized memory in the case when |alen| is
smaller than sizeof(struct sockaddr_nl), and therefore |nladdr| isn't
fully copied from the userspace.

Signed-off-by: Alexander Potapenko <glider@google.com>
Fixes: 1da177e4c3f41524 ("Linux-2.6.12-rc2")
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 9219bc134109..1b86eccf94b6 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1053,6 +1053,9 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr,
 	if (addr->sa_family != AF_NETLINK)
 		return -EINVAL;
 
+	if (alen < sizeof(struct sockaddr_nl))
+		return -EINVAL;
+
 	if ((nladdr->nl_groups || nladdr->nl_pid) &&
 	    !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
 		return -EPERM;
-- 
2.14.3


From d8512c95c4a38ecabc1687c532a40213bd20f75a Mon Sep 17 00:00:00 2001
From: Craig Dillabaugh <cdillaba@mojatatu.com>
Date: Mon, 26 Mar 2018 14:58:32 -0400
Subject: [PATCH 08/42] net sched actions: fix dumping which requires several
 messages to user space

[ Upstream commit 734549eb550c0c720bc89e50501f1b1e98cdd841 ]

Fixes a bug in the tcf_dump_walker function that can cause some actions
to not be reported when dumping a large number of actions. This issue
became more aggrevated when cookies feature was added. In particular
this issue is manifest when large cookie values are assigned to the
actions and when enough actions are created that the resulting table
must be dumped in multiple batches.

The number of actions returned in each batch is limited by the total
number of actions and the memory buffer size.  With small cookies
the numeric limit is reached before the buffer size limit, which avoids
the code path triggering this bug. When large cookies are used buffer
fills before the numeric limit, and the erroneous code path is hit.

For example after creating 32 csum actions with the cookie
aaaabbbbccccdddd

$ tc actions ls action csum
total acts 26

    action order 0: csum (tcp) action continue
    index 1 ref 1 bind 0
    cookie aaaabbbbccccdddd

    .....

    action order 25: csum (tcp) action continue
    index 26 ref 1 bind 0
    cookie aaaabbbbccccdddd
total acts 6

    action order 0: csum (tcp) action continue
    index 28 ref 1 bind 0
    cookie aaaabbbbccccdddd

    ......

    action order 5: csum (tcp) action continue
    index 32 ref 1 bind 0
    cookie aaaabbbbccccdddd

Note that the action with index 27 is omitted from the report.

Fixes: 4b3550ef530c ("[NET_SCHED]: Use nla_nest_start/nla_nest_end")"
Signed-off-by: Craig Dillabaugh <cdillaba@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_api.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 8f2c63514956..4444d7e755e6 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -133,8 +133,10 @@ static int tcf_dump_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb,
 			continue;
 
 		nest = nla_nest_start(skb, n_i);
-		if (!nest)
+		if (!nest) {
+			index--;
 			goto nla_put_failure;
+		}
 		err = tcf_action_dump_1(skb, p, 0, 0);
 		if (err < 0) {
 			index--;
-- 
2.14.3


From 1768bdccd96498c1c796c215a6397e38665f5906 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Fri, 6 Apr 2018 01:19:37 +0200
Subject: [PATCH 09/42] net/sched: fix NULL dereference in the error path of
 tcf_bpf_init()

[ Upstream commit 3239534a79ee6f20cffd974173a1e62e0730e8ac ]

when tcf_bpf_init_from_ops() fails (e.g. because of program having invalid
number of instructions), tcf_bpf_cfg_cleanup() calls bpf_prog_put(NULL) or
bpf_prog_destroy(NULL). Unless CONFIG_BPF_SYSCALL is unset, this causes
the following error:

 BUG: unable to handle kernel NULL pointer dereference at 0000000000000020
 PGD 800000007345a067 P4D 800000007345a067 PUD 340e1067 PMD 0
 Oops: 0000 [#1] SMP PTI
 Modules linked in: act_bpf(E) ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 mbcache jbd2 crct10dif_pclmul crc32_pclmul ghash_clmulni_intel snd_hda_codec_generic pcbc snd_hda_intel snd_hda_codec snd_hda_core snd_hwdep snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd glue_helper cryptd joydev snd_timer snd virtio_balloon pcspkr soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm virtio_blk drm virtio_net virtio_console i2c_core crc32c_intel serio_raw virtio_pci ata_piix libata virtio_ring floppy virtio dm_mirror dm_region_hash dm_log dm_mod [last unloaded: act_bpf]
 CPU: 3 PID: 5654 Comm: tc Tainted: G            E    4.16.0.bpf_test+ #408
 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
 RIP: 0010:__bpf_prog_put+0xc/0xc0
 RSP: 0018:ffff9594003ef728 EFLAGS: 00010202
 RAX: 0000000000000000 RBX: ffff9594003ef758 RCX: 0000000000000024
 RDX: 0000000000000000 RSI: 0000000000000001 RDI: 0000000000000000
 RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000044
 R10: 0000000000000220 R11: ffff8a7ab9f17131 R12: 0000000000000000
 R13: ffff8a7ab7c3c8e0 R14: 0000000000000001 R15: ffff8a7ab88f1054
 FS:  00007fcb2f17c740(0000) GS:ffff8a7abfd80000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000000020 CR3: 000000007c888006 CR4: 00000000001606e0
 Call Trace:
  tcf_bpf_cfg_cleanup+0x2f/0x40 [act_bpf]
  tcf_bpf_cleanup+0x4c/0x70 [act_bpf]
  __tcf_idr_release+0x79/0x140
  tcf_bpf_init+0x125/0x330 [act_bpf]
  tcf_action_init_1+0x2cc/0x430
  ? get_page_from_freelist+0x3f0/0x11b0
  tcf_action_init+0xd3/0x1b0
  tc_ctl_action+0x18b/0x240
  rtnetlink_rcv_msg+0x29c/0x310
  ? _cond_resched+0x15/0x30
  ? __kmalloc_node_track_caller+0x1b9/0x270
  ? rtnl_calcit.isra.29+0x100/0x100
  netlink_rcv_skb+0xd2/0x110
  netlink_unicast+0x17c/0x230
  netlink_sendmsg+0x2cd/0x3c0
  sock_sendmsg+0x30/0x40
  ___sys_sendmsg+0x27a/0x290
  ? mem_cgroup_commit_charge+0x80/0x130
  ? page_add_new_anon_rmap+0x73/0xc0
  ? do_anonymous_page+0x2a2/0x560
  ? __handle_mm_fault+0xc75/0xe20
  __sys_sendmsg+0x58/0xa0
  do_syscall_64+0x6e/0x1a0
  entry_SYSCALL_64_after_hwframe+0x3d/0xa2
 RIP: 0033:0x7fcb2e58eba0
 RSP: 002b:00007ffc93c496c8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
 RAX: ffffffffffffffda RBX: 00007ffc93c497f0 RCX: 00007fcb2e58eba0
 RDX: 0000000000000000 RSI: 00007ffc93c49740 RDI: 0000000000000003
 RBP: 000000005ac6a646 R08: 0000000000000002 R09: 0000000000000000
 R10: 00007ffc93c49120 R11: 0000000000000246 R12: 0000000000000000
 R13: 00007ffc93c49804 R14: 0000000000000001 R15: 000000000066afa0
 Code: 5f 00 48 8b 43 20 48 c7 c7 70 2f 7c b8 c7 40 10 00 00 00 00 5b e9 a5 8b 61 00 0f 1f 44 00 00 0f 1f 44 00 00 41 54 55 48 89 fd 53 <48> 8b 47 20 f0 ff 08 74 05 5b 5d 41 5c c3 41 89 f4 0f 1f 44 00
 RIP: __bpf_prog_put+0xc/0xc0 RSP: ffff9594003ef728
 CR2: 0000000000000020

Fix it in tcf_bpf_cfg_cleanup(), ensuring that bpf_prog_{put,destroy}(f)
is called only when f is not NULL.

Fixes: bbc09e7842a5 ("net/sched: fix idr leak on the error path of tcf_bpf_init()")
Reported-by: Lucas Bates <lucasb@mojatatu.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_bpf.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index c0c707eb2c96..2b087623fb1d 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -248,10 +248,14 @@ static int tcf_bpf_init_from_efd(struct nlattr **tb, struct tcf_bpf_cfg *cfg)
 
 static void tcf_bpf_cfg_cleanup(const struct tcf_bpf_cfg *cfg)
 {
-	if (cfg->is_ebpf)
-		bpf_prog_put(cfg->filter);
-	else
-		bpf_prog_destroy(cfg->filter);
+	struct bpf_prog *filter = cfg->filter;
+
+	if (filter) {
+		if (cfg->is_ebpf)
+			bpf_prog_put(filter);
+		else
+			bpf_prog_destroy(filter);
+	}
 
 	kfree(cfg->bpf_ops);
 	kfree(cfg->bpf_name);
-- 
2.14.3


From e7116be1fdbaf55e7965c9e85bd7e9fe40e2041a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 2 Apr 2018 18:48:37 -0700
Subject: [PATCH 10/42] pptp: remove a buggy dst release in pptp_connect()

[ Upstream commit bfacfb457b36911a10140b8cb3ce76a74883ac5a ]

Once dst has been cached in socket via sk_setup_caps(),
it is illegal to call ip_rt_put() (or dst_release()),
since sk_setup_caps() did not change dst refcount.

We can still dereference it since we hold socket lock.

Caugth by syzbot :

BUG: KASAN: use-after-free in atomic_dec_return include/asm-generic/atomic-instrumented.h:198 [inline]
BUG: KASAN: use-after-free in dst_release+0x27/0xa0 net/core/dst.c:185
Write of size 4 at addr ffff8801c54dc040 by task syz-executor4/20088

CPU: 1 PID: 20088 Comm: syz-executor4 Not tainted 4.16.0+ #376
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x1a7/0x27d lib/dump_stack.c:53
 print_address_description+0x73/0x250 mm/kasan/report.c:256
 kasan_report_error mm/kasan/report.c:354 [inline]
 kasan_report+0x23c/0x360 mm/kasan/report.c:412
 check_memory_region_inline mm/kasan/kasan.c:260 [inline]
 check_memory_region+0x137/0x190 mm/kasan/kasan.c:267
 kasan_check_write+0x14/0x20 mm/kasan/kasan.c:278
 atomic_dec_return include/asm-generic/atomic-instrumented.h:198 [inline]
 dst_release+0x27/0xa0 net/core/dst.c:185
 sk_dst_set include/net/sock.h:1812 [inline]
 sk_dst_reset include/net/sock.h:1824 [inline]
 sock_setbindtodevice net/core/sock.c:610 [inline]
 sock_setsockopt+0x431/0x1b20 net/core/sock.c:707
 SYSC_setsockopt net/socket.c:1845 [inline]
 SyS_setsockopt+0x2ff/0x360 net/socket.c:1828
 do_syscall_64+0x281/0x940 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x42/0xb7
RIP: 0033:0x4552d9
RSP: 002b:00007f4878126c68 EFLAGS: 00000246 ORIG_RAX: 0000000000000036
RAX: ffffffffffffffda RBX: 00007f48781276d4 RCX: 00000000004552d9
RDX: 0000000000000019 RSI: 0000000000000001 RDI: 0000000000000013
RBP: 000000000072bea0 R08: 0000000000000010 R09: 0000000000000000
R10: 00000000200010c0 R11: 0000000000000246 R12: 00000000ffffffff
R13: 0000000000000526 R14: 00000000006fac30 R15: 0000000000000000

Allocated by task 20088:
 save_stack+0x43/0xd0 mm/kasan/kasan.c:447
 set_track mm/kasan/kasan.c:459 [inline]
 kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:552
 kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:489
 kmem_cache_alloc+0x12e/0x760 mm/slab.c:3542
 dst_alloc+0x11f/0x1a0 net/core/dst.c:104
 rt_dst_alloc+0xe9/0x540 net/ipv4/route.c:1520
 __mkroute_output net/ipv4/route.c:2265 [inline]
 ip_route_output_key_hash_rcu+0xa49/0x2c60 net/ipv4/route.c:2493
 ip_route_output_key_hash+0x20b/0x370 net/ipv4/route.c:2322
 __ip_route_output_key include/net/route.h:126 [inline]
 ip_route_output_flow+0x26/0xa0 net/ipv4/route.c:2577
 ip_route_output_ports include/net/route.h:163 [inline]
 pptp_connect+0xa84/0x1170 drivers/net/ppp/pptp.c:453
 SYSC_connect+0x213/0x4a0 net/socket.c:1639
 SyS_connect+0x24/0x30 net/socket.c:1620
 do_syscall_64+0x281/0x940 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x42/0xb7

Freed by task 20082:
 save_stack+0x43/0xd0 mm/kasan/kasan.c:447
 set_track mm/kasan/kasan.c:459 [inline]
 __kasan_slab_free+0x11a/0x170 mm/kasan/kasan.c:520
 kasan_slab_free+0xe/0x10 mm/kasan/kasan.c:527
 __cache_free mm/slab.c:3486 [inline]
 kmem_cache_free+0x83/0x2a0 mm/slab.c:3744
 dst_destroy+0x266/0x380 net/core/dst.c:140
 dst_destroy_rcu+0x16/0x20 net/core/dst.c:153
 __rcu_reclaim kernel/rcu/rcu.h:178 [inline]
 rcu_do_batch kernel/rcu/tree.c:2675 [inline]
 invoke_rcu_callbacks kernel/rcu/tree.c:2930 [inline]
 __rcu_process_callbacks kernel/rcu/tree.c:2897 [inline]
 rcu_process_callbacks+0xd6c/0x17b0 kernel/rcu/tree.c:2914
 __do_softirq+0x2d7/0xb85 kernel/softirq.c:285

The buggy address belongs to the object at ffff8801c54dc000
 which belongs to the cache ip_dst_cache of size 168
The buggy address is located 64 bytes inside of
 168-byte region [ffff8801c54dc000, ffff8801c54dc0a8)
The buggy address belongs to the page:
page:ffffea0007153700 count:1 mapcount:0 mapping:ffff8801c54dc000 index:0x0
flags: 0x2fffc0000000100(slab)
raw: 02fffc0000000100 ffff8801c54dc000 0000000000000000 0000000100000010
raw: ffffea0006b34b20 ffffea0006b6c1e0 ffff8801d674a1c0 0000000000000000
page dumped because: kasan: bad access detected

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pptp.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index 6dde9a0cfe76..9b70a3af678e 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -464,7 +464,6 @@ static int pptp_connect(struct socket *sock, struct sockaddr *uservaddr,
 	po->chan.mtu = dst_mtu(&rt->dst);
 	if (!po->chan.mtu)
 		po->chan.mtu = PPP_MRU;
-	ip_rt_put(rt);
 	po->chan.mtu -= PPTP_HEADER_OVERHEAD;
 
 	po->chan.hdrlen = 2 + sizeof(struct pptp_gre_header);
-- 
2.14.3


From fd46b67af9037580d1248f2c08765cfcb7cc2963 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 26 Mar 2018 19:19:30 +0200
Subject: [PATCH 11/42] r8169: fix setting driver_data after register_netdev

[ Upstream commit 19c9ea363a244f85f90a424f9936e6d56449e33c ]

pci_set_drvdata() is called only after registering the net_device,
therefore we could run into a NPE if one of the functions using
driver_data is called before it's set.

Fix this by calling pci_set_drvdata() before registering the
net_device.

This fix is a candidate for stable. As far as I can see the
bug has been there in kernel version 3.2 already, therefore
I can't provide a reference which commit is fixed by it.

The fix may need small adjustments per kernel version because
due to other changes the label which is jumped to if
register_netdev() fails has changed over time.

Reported-by: David Miller <davem@davemloft.net>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 619a1b7281a0..db553d4e8d22 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -8466,12 +8466,12 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_out_msi_5;
 	}
 
+	pci_set_drvdata(pdev, dev);
+
 	rc = register_netdev(dev);
 	if (rc < 0)
 		goto err_out_cnt_6;
 
-	pci_set_drvdata(pdev, dev);
-
 	netif_info(tp, probe, dev, "%s at 0x%p, %pM, XID %08x IRQ %d\n",
 		   rtl_chip_infos[chipset].name, ioaddr, dev->dev_addr,
 		   (u32)(RTL_R32(TxConfig) & 0x9cf0f8ff), pdev->irq);
-- 
2.14.3


From 80b97d2f551c29c2a68aa510b136d31937bf5952 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 7 Apr 2018 17:15:22 -0700
Subject: [PATCH 12/42] sctp: do not leak kernel memory to user space

[ Upstream commit 6780db244d6b1537d139dea0ec8aad10cf9e4adb ]

syzbot produced a nice report [1]

Issue here is that a recvmmsg() managed to leak 8 bytes of kernel memory
to user space, because sin_zero (padding field) was not properly cleared.

[1]
BUG: KMSAN: uninit-value in copy_to_user include/linux/uaccess.h:184 [inline]
BUG: KMSAN: uninit-value in move_addr_to_user+0x32e/0x530 net/socket.c:227
CPU: 1 PID: 3586 Comm: syzkaller481044 Not tainted 4.16.0+ #82
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x185/0x1d0 lib/dump_stack.c:53
 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067
 kmsan_internal_check_memory+0x164/0x1d0 mm/kmsan/kmsan.c:1176
 kmsan_copy_to_user+0x69/0x160 mm/kmsan/kmsan.c:1199
 copy_to_user include/linux/uaccess.h:184 [inline]
 move_addr_to_user+0x32e/0x530 net/socket.c:227
 ___sys_recvmsg+0x4e2/0x810 net/socket.c:2211
 __sys_recvmmsg+0x54e/0xdb0 net/socket.c:2313
 SYSC_recvmmsg+0x29b/0x3e0 net/socket.c:2394
 SyS_recvmmsg+0x76/0xa0 net/socket.c:2378
 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x3d/0xa2
RIP: 0033:0x4401c9
RSP: 002b:00007ffc56f73098 EFLAGS: 00000217 ORIG_RAX: 000000000000012b
RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 00000000004401c9
RDX: 0000000000000001 RSI: 0000000020003ac0 RDI: 0000000000000003
RBP: 00000000006ca018 R08: 0000000020003bc0 R09: 0000000000000010
R10: 0000000000000000 R11: 0000000000000217 R12: 0000000000401af0
R13: 0000000000401b80 R14: 0000000000000000 R15: 0000000000000000

Local variable description: ----addr@___sys_recvmsg
Variable was created at:
 ___sys_recvmsg+0xd5/0x810 net/socket.c:2172
 __sys_recvmmsg+0x54e/0xdb0 net/socket.c:2313

Bytes 8-15 of 16 are uninitialized

==================================================================
Kernel panic - not syncing: panic_on_warn set ...

CPU: 1 PID: 3586 Comm: syzkaller481044 Tainted: G    B            4.16.0+ #82
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x185/0x1d0 lib/dump_stack.c:53
 panic+0x39d/0x940 kernel/panic.c:183
 kmsan_report+0x238/0x240 mm/kmsan/kmsan.c:1083
 kmsan_internal_check_memory+0x164/0x1d0 mm/kmsan/kmsan.c:1176
 kmsan_copy_to_user+0x69/0x160 mm/kmsan/kmsan.c:1199
 copy_to_user include/linux/uaccess.h:184 [inline]
 move_addr_to_user+0x32e/0x530 net/socket.c:227
 ___sys_recvmsg+0x4e2/0x810 net/socket.c:2211
 __sys_recvmmsg+0x54e/0xdb0 net/socket.c:2313
 SYSC_recvmmsg+0x29b/0x3e0 net/socket.c:2394
 SyS_recvmmsg+0x76/0xa0 net/socket.c:2378
 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x3d/0xa2

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc:	Vlad Yasevich <vyasevich@gmail.com>
Cc:	Neil Horman <nhorman@tuxdriver.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ipv6.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index f27a9718554c..08b5705e7381 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -728,8 +728,10 @@ static int sctp_v6_addr_to_user(struct sctp_sock *sp, union sctp_addr *addr)
 			sctp_v6_map_v4(addr);
 	}
 
-	if (addr->sa.sa_family == AF_INET)
+	if (addr->sa.sa_family == AF_INET) {
+		memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
 		return sizeof(struct sockaddr_in);
+	}
 	return sizeof(struct sockaddr_in6);
 }
 
-- 
2.14.3


From d677583164f99f3d6a64ed1a66f4dfeba12176d8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 8 Apr 2018 07:52:08 -0700
Subject: [PATCH 13/42] sctp: sctp_sockaddr_af must check minimal addr length
 for AF_INET6

[ Upstream commit 81e98370293afcb58340ce8bd71af7b97f925c26 ]

Check must happen before call to ipv6_addr_v4mapped()

syzbot report was :

BUG: KMSAN: uninit-value in sctp_sockaddr_af net/sctp/socket.c:359 [inline]
BUG: KMSAN: uninit-value in sctp_do_bind+0x60f/0xdc0 net/sctp/socket.c:384
CPU: 0 PID: 3576 Comm: syzkaller968804 Not tainted 4.16.0+ #82
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x185/0x1d0 lib/dump_stack.c:53
 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067
 __msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:676
 sctp_sockaddr_af net/sctp/socket.c:359 [inline]
 sctp_do_bind+0x60f/0xdc0 net/sctp/socket.c:384
 sctp_bind+0x149/0x190 net/sctp/socket.c:332
 inet6_bind+0x1fd/0x1820 net/ipv6/af_inet6.c:293
 SYSC_bind+0x3f2/0x4b0 net/socket.c:1474
 SyS_bind+0x54/0x80 net/socket.c:1460
 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x3d/0xa2
RIP: 0033:0x43fd49
RSP: 002b:00007ffe99df3d28 EFLAGS: 00000213 ORIG_RAX: 0000000000000031
RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 000000000043fd49
RDX: 0000000000000010 RSI: 0000000020000000 RDI: 0000000000000003
RBP: 00000000006ca018 R08: 00000000004002c8 R09: 00000000004002c8
R10: 00000000004002c8 R11: 0000000000000213 R12: 0000000000401670
R13: 0000000000401700 R14: 0000000000000000 R15: 0000000000000000

Local variable description: ----address@SYSC_bind
Variable was created at:
 SYSC_bind+0x6f/0x4b0 net/socket.c:1461
 SyS_bind+0x54/0x80 net/socket.c:1460

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Vlad Yasevich <vyasevich@gmail.com>
Cc: Neil Horman <nhorman@tuxdriver.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 6b3a862706de..2d6f612f32c3 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -337,11 +337,14 @@ static struct sctp_af *sctp_sockaddr_af(struct sctp_sock *opt,
 	if (!opt->pf->af_supported(addr->sa.sa_family, opt))
 		return NULL;
 
-	/* V4 mapped address are really of AF_INET family */
-	if (addr->sa.sa_family == AF_INET6 &&
-	    ipv6_addr_v4mapped(&addr->v6.sin6_addr) &&
-	    !opt->pf->af_supported(AF_INET, opt))
-		return NULL;
+	if (addr->sa.sa_family == AF_INET6) {
+		if (len < SIN6_LEN_RFC2133)
+			return NULL;
+		/* V4 mapped address are really of AF_INET family */
+		if (ipv6_addr_v4mapped(&addr->v6.sin6_addr) &&
+		    !opt->pf->af_supported(AF_INET, opt))
+			return NULL;
+	}
 
 	/* If we get this far, af is valid. */
 	af = sctp_get_af_specific(addr->sa.sa_family);
-- 
2.14.3


From c2c53851f5ceb217c82be0e4a116a3421e5e5006 Mon Sep 17 00:00:00 2001
From: Kai-Heng Feng <kai.heng.feng@canonical.com>
Date: Sat, 31 Mar 2018 23:42:03 +0800
Subject: [PATCH 14/42] sky2: Increase D3 delay to sky2 stops working after
 suspend

[ Upstream commit afb133637071be6deeb8b3d0e55593ffbf63c527 ]

The sky2 ethernet stops working after system resume from suspend:
[ 582.852065] sky2 0000:04:00.0: Refused to change power state, currently in D3

The current 150ms delay is not enough, change it to 200ms can solve the
issue.

BugLink: https://bugs.launchpad.net/bugs/1758507
Cc: Stable <stable@vger.kernel.org>
Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/sky2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index 1145cde2274a..b12e3a4f9439 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -5087,7 +5087,7 @@ static int sky2_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	INIT_WORK(&hw->restart_work, sky2_restart);
 
 	pci_set_drvdata(pdev, hw);
-	pdev->d3_delay = 150;
+	pdev->d3_delay = 200;
 
 	return 0;
 
-- 
2.14.3


From 6387177949387fccab4e5faffc7bff70025c0c1a Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Tue, 27 Mar 2018 20:50:52 +0800
Subject: [PATCH 15/42] vhost: correctly remove wait queue during poll failure

[ Upstream commit dc6455a71c7fc5117977e197f67f71b49f27baba ]

We tried to remove vq poll from wait queue, but do not check whether
or not it was in a list before. This will lead double free. Fixing
this by switching to use vhost_poll_stop() which zeros poll->wqh after
removing poll from waitqueue to make sure it won't be freed twice.

Cc: Darren Kenny <darren.kenny@oracle.com>
Reported-by: syzbot+c0272972b01b872e604a@syzkaller.appspotmail.com
Fixes: 2b8b328b61c79 ("vhost_net: handle polling errors when setting backend")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Darren Kenny <darren.kenny@oracle.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/vhost.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index a827c1a684a9..c1033dc0e3f5 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -213,8 +213,7 @@ int vhost_poll_start(struct vhost_poll *poll, struct file *file)
 	if (mask)
 		vhost_poll_wakeup(&poll->wait, 0, 0, (void *)mask);
 	if (mask & POLLERR) {
-		if (poll->wqh)
-			remove_wait_queue(poll->wqh, &poll->wait);
+		vhost_poll_stop(poll);
 		ret = -EINVAL;
 	}
 
-- 
2.14.3


From 98895473c289c968e7f2e35a6a6cf46e09de1605 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Fri, 30 Mar 2018 09:44:00 +0800
Subject: [PATCH 16/42] vlan: also check phy_driver ts_info for vlan's real
 device

[ Upstream commit ec1d8ccb07deaf30fd0508af6755364ac47dc08d ]

Just like function ethtool_get_ts_info(), we should also consider the
phy_driver ts_info call back. For example, driver dp83640.

Fixes: 37dd9255b2f6 ("vlan: Pass ethtool get_ts_info queries to real device.")
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/8021q/vlan_dev.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index f7e83f6d2e64..236452ebbd9e 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -29,6 +29,7 @@
 #include <linux/net_tstamp.h>
 #include <linux/etherdevice.h>
 #include <linux/ethtool.h>
+#include <linux/phy.h>
 #include <net/arp.h>
 #include <net/switchdev.h>
 
@@ -665,8 +666,11 @@ static int vlan_ethtool_get_ts_info(struct net_device *dev,
 {
 	const struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
 	const struct ethtool_ops *ops = vlan->real_dev->ethtool_ops;
+	struct phy_device *phydev = vlan->real_dev->phydev;
 
-	if (ops->get_ts_info) {
+	if (phydev && phydev->drv && phydev->drv->ts_info) {
+		 return phydev->drv->ts_info(phydev, info);
+	} else if (ops->get_ts_info) {
 		return ops->get_ts_info(vlan->real_dev, info);
 	} else {
 		info->so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE |
-- 
2.14.3


From 0bcec66365405e0c7eccd9e63c14fbff914f8592 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Thu, 29 Mar 2018 12:49:52 -0700
Subject: [PATCH 17/42] vrf: Fix use after free and double free in
 vrf_finish_output

[ Upstream commit 82dd0d2a9a76fc8fa2b18d80b987d455728bf83a ]

Miguel reported an skb use after free / double free in vrf_finish_output
when neigh_output returns an error. The vrf driver should return after
the call to neigh_output as it takes over the skb on error path as well.

Patch is a simplified version of Miguel's patch which was written for 4.9,
and updated to top of tree.

Fixes: 8f58336d3f78a ("net: Add ethernet header for pass through VRF device")
Signed-off-by: Miguel Fadon Perlines <mfadon@teldat.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 67ecf2425b88..5c6a8ef54aec 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -579,12 +579,13 @@ static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *s
 	if (!IS_ERR(neigh)) {
 		sock_confirm_neigh(skb, neigh);
 		ret = neigh_output(neigh, skb);
+		rcu_read_unlock_bh();
+		return ret;
 	}
 
 	rcu_read_unlock_bh();
 err:
-	if (unlikely(ret < 0))
-		vrf_tx_error(skb->dev, skb);
+	vrf_tx_error(skb->dev, skb);
 	return ret;
 }
 
-- 
2.14.3


From c617a1551b784a98ba39e74a3668095e8c9131c8 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 26 Mar 2018 01:16:45 +0800
Subject: [PATCH 18/42] bonding: fix the err path for dev hwaddr sync in
 bond_enslave

[ Upstream commit 5c78f6bfae2b10ff70e21d343e64584ea6280c26 ]

vlan_vids_add_by_dev is called right after dev hwaddr sync, so on
the err path it should unsync dev hwaddr. Otherwise, the slave
dev's hwaddr will never be unsync when this err happens.

Fixes: 1ff412ad7714 ("bonding: change the bond's vlan syncing functions with the standard ones")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Reviewed-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Acked-by: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index b2db581131b2..5c99c0f1f01d 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1561,7 +1561,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	if (res) {
 		netdev_err(bond_dev, "Couldn't add bond vlan ids to %s\n",
 			   slave_dev->name);
-		goto err_close;
+		goto err_hwaddr_unsync;
 	}
 
 	prev_slave = bond_last_slave(bond);
@@ -1751,9 +1751,6 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	netdev_rx_handler_unregister(slave_dev);
 
 err_detach:
-	if (!bond_uses_primary(bond))
-		bond_hw_addr_flush(bond_dev, slave_dev);
-
 	vlan_vids_del_by_dev(slave_dev, bond_dev);
 	if (rcu_access_pointer(bond->primary_slave) == new_slave)
 		RCU_INIT_POINTER(bond->primary_slave, NULL);
@@ -1767,6 +1764,10 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	synchronize_rcu();
 	slave_disable_netpoll(new_slave);
 
+err_hwaddr_unsync:
+	if (!bond_uses_primary(bond))
+		bond_hw_addr_flush(bond_dev, slave_dev);
+
 err_close:
 	slave_dev->priv_flags &= ~IFF_BONDING;
 	dev_close(slave_dev);
-- 
2.14.3


From 82788223dbdbf3b84107c93ac340c523f248202b Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 26 Mar 2018 01:16:46 +0800
Subject: [PATCH 19/42] bonding: move dev_mc_sync after master_upper_dev_link
 in bond_enslave

[ Upstream commit ae42cc62a9f07f1f6979054ed92606b9c30f4a2e ]

Beniamino found a crash when adding vlan as slave of bond which is also
the parent link:

  ip link add bond1 type bond
  ip link set bond1 up
  ip link add link bond1 vlan1 type vlan id 80
  ip link set vlan1 master bond1

The call trace is as below:

  [<ffffffffa850842a>] queued_spin_lock_slowpath+0xb/0xf
  [<ffffffffa8515680>] _raw_spin_lock+0x20/0x30
  [<ffffffffa83f6f07>] dev_mc_sync+0x37/0x80
  [<ffffffffc08687dc>] vlan_dev_set_rx_mode+0x1c/0x30 [8021q]
  [<ffffffffa83efd2a>] __dev_set_rx_mode+0x5a/0xa0
  [<ffffffffa83f7138>] dev_mc_sync_multiple+0x78/0x80
  [<ffffffffc084127c>] bond_enslave+0x67c/0x1190 [bonding]
  [<ffffffffa8401909>] do_setlink+0x9c9/0xe50
  [<ffffffffa8403bf2>] rtnl_newlink+0x522/0x880
  [<ffffffffa8403ff7>] rtnetlink_rcv_msg+0xa7/0x260
  [<ffffffffa8424ecb>] netlink_rcv_skb+0xab/0xc0
  [<ffffffffa83fe498>] rtnetlink_rcv+0x28/0x30
  [<ffffffffa8424850>] netlink_unicast+0x170/0x210
  [<ffffffffa8424bf8>] netlink_sendmsg+0x308/0x420
  [<ffffffffa83cc396>] sock_sendmsg+0xb6/0xf0

This is actually a dead lock caused by sync slave hwaddr from master when
the master is the slave's 'slave'. This dead loop check is actually done
by netdev_master_upper_dev_link. However, Commit 1f718f0f4f97 ("bonding:
populate neighbour's private on enslave") moved it after dev_mc_sync.

This patch is to fix it by moving dev_mc_sync after master_upper_dev_link,
so that this loop check would be earlier than dev_mc_sync. It also moves
if (mode == BOND_MODE_8023AD) into if (!bond_uses_primary) clause as an
improvement.

Note team driver also has this issue, I will fix it in another patch.

Fixes: 1f718f0f4f97 ("bonding: populate neighbour's private on enslave")
Reported-by: Beniamino Galvani <bgalvani@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 73 ++++++++++++++++++++---------------------
 1 file changed, 35 insertions(+), 38 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 5c99c0f1f01d..b8701a07f4eb 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1524,44 +1524,11 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 			goto err_close;
 	}
 
-	/* If the mode uses primary, then the following is handled by
-	 * bond_change_active_slave().
-	 */
-	if (!bond_uses_primary(bond)) {
-		/* set promiscuity level to new slave */
-		if (bond_dev->flags & IFF_PROMISC) {
-			res = dev_set_promiscuity(slave_dev, 1);
-			if (res)
-				goto err_close;
-		}
-
-		/* set allmulti level to new slave */
-		if (bond_dev->flags & IFF_ALLMULTI) {
-			res = dev_set_allmulti(slave_dev, 1);
-			if (res)
-				goto err_close;
-		}
-
-		netif_addr_lock_bh(bond_dev);
-
-		dev_mc_sync_multiple(slave_dev, bond_dev);
-		dev_uc_sync_multiple(slave_dev, bond_dev);
-
-		netif_addr_unlock_bh(bond_dev);
-	}
-
-	if (BOND_MODE(bond) == BOND_MODE_8023AD) {
-		/* add lacpdu mc addr to mc list */
-		u8 lacpdu_multicast[ETH_ALEN] = MULTICAST_LACPDU_ADDR;
-
-		dev_mc_add(slave_dev, lacpdu_multicast);
-	}
-
 	res = vlan_vids_add_by_dev(slave_dev, bond_dev);
 	if (res) {
 		netdev_err(bond_dev, "Couldn't add bond vlan ids to %s\n",
 			   slave_dev->name);
-		goto err_hwaddr_unsync;
+		goto err_close;
 	}
 
 	prev_slave = bond_last_slave(bond);
@@ -1721,6 +1688,37 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 		goto err_upper_unlink;
 	}
 
+	/* If the mode uses primary, then the following is handled by
+	 * bond_change_active_slave().
+	 */
+	if (!bond_uses_primary(bond)) {
+		/* set promiscuity level to new slave */
+		if (bond_dev->flags & IFF_PROMISC) {
+			res = dev_set_promiscuity(slave_dev, 1);
+			if (res)
+				goto err_sysfs_del;
+		}
+
+		/* set allmulti level to new slave */
+		if (bond_dev->flags & IFF_ALLMULTI) {
+			res = dev_set_allmulti(slave_dev, 1);
+			if (res)
+				goto err_sysfs_del;
+		}
+
+		netif_addr_lock_bh(bond_dev);
+		dev_mc_sync_multiple(slave_dev, bond_dev);
+		dev_uc_sync_multiple(slave_dev, bond_dev);
+		netif_addr_unlock_bh(bond_dev);
+
+		if (BOND_MODE(bond) == BOND_MODE_8023AD) {
+			/* add lacpdu mc addr to mc list */
+			u8 lacpdu_multicast[ETH_ALEN] = MULTICAST_LACPDU_ADDR;
+
+			dev_mc_add(slave_dev, lacpdu_multicast);
+		}
+	}
+
 	bond->slave_cnt++;
 	bond_compute_features(bond);
 	bond_set_carrier(bond);
@@ -1744,6 +1742,9 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	return 0;
 
 /* Undo stages on error */
+err_sysfs_del:
+	bond_sysfs_slave_del(new_slave);
+
 err_upper_unlink:
 	bond_upper_dev_unlink(bond, new_slave);
 
@@ -1764,10 +1765,6 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	synchronize_rcu();
 	slave_disable_netpoll(new_slave);
 
-err_hwaddr_unsync:
-	if (!bond_uses_primary(bond))
-		bond_hw_addr_flush(bond_dev, slave_dev);
-
 err_close:
 	slave_dev->priv_flags &= ~IFF_BONDING;
 	dev_close(slave_dev);
-- 
2.14.3


From efb1935b14a7716f426d1a6dd3e789eed7768dc5 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 26 Mar 2018 01:16:47 +0800
Subject: [PATCH 20/42] bonding: process the err returned by dev_set_allmulti
 properly in bond_enslave

[ Upstream commit 9f5a90c107741b864398f4ac0014711a8c1d8474 ]

When dev_set_promiscuity(1) succeeds but dev_set_allmulti(1) fails,
dev_set_promiscuity(-1) should be done before going to the err path.
Otherwise, dev->promiscuity will leak.

Fixes: 7e1a1ac1fbaa ("bonding: Check return of dev_set_promiscuity/allmulti")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index b8701a07f4eb..82f28ffccddf 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1702,8 +1702,11 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 		/* set allmulti level to new slave */
 		if (bond_dev->flags & IFF_ALLMULTI) {
 			res = dev_set_allmulti(slave_dev, 1);
-			if (res)
+			if (res) {
+				if (bond_dev->flags & IFF_PROMISC)
+					dev_set_promiscuity(slave_dev, -1);
 				goto err_sysfs_del;
+			}
 		}
 
 		netif_addr_lock_bh(bond_dev);
-- 
2.14.3


From ec78dfcf35aaa71e0f711f72be497e3bb4d893ba Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 5 Apr 2018 06:39:26 -0700
Subject: [PATCH 21/42] net: fool proof dev_valid_name()

[ Upstream commit a9d48205d0aedda021fc3728972a9e9934c2b9de ]

We want to use dev_valid_name() to validate tunnel names,
so better use strnlen(name, IFNAMSIZ) than strlen(name) to make
sure to not upset KASAN.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index ef3337bb71a2..4be2a4047640 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1025,7 +1025,7 @@ bool dev_valid_name(const char *name)
 {
 	if (*name == '\0')
 		return false;
-	if (strlen(name) >= IFNAMSIZ)
+	if (strnlen(name, IFNAMSIZ) == IFNAMSIZ)
 		return false;
 	if (!strcmp(name, ".") || !strcmp(name, ".."))
 		return false;
-- 
2.14.3


From cea0aeb56ee591ccb840c1d906ff996630840ebe Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 5 Apr 2018 06:39:27 -0700
Subject: [PATCH 22/42] ip_tunnel: better validate user provided tunnel names

[ Upstream commit 9cb726a212a82c88c98aa9f0037fd04777cd8fe5 ]

Use dev_valid_name() to make sure user does not provide illegal
device name.

syzbot caught the following bug :

BUG: KASAN: stack-out-of-bounds in strlcpy include/linux/string.h:300 [inline]
BUG: KASAN: stack-out-of-bounds in __ip_tunnel_create+0xca/0x6b0 net/ipv4/ip_tunnel.c:257
Write of size 20 at addr ffff8801ac79f810 by task syzkaller268107/4482

CPU: 0 PID: 4482 Comm: syzkaller268107 Not tainted 4.16.0+ #1
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x1b9/0x29f lib/dump_stack.c:53
 print_address_description+0x6c/0x20b mm/kasan/report.c:256
 kasan_report_error mm/kasan/report.c:354 [inline]
 kasan_report.cold.7+0xac/0x2f5 mm/kasan/report.c:412
 check_memory_region_inline mm/kasan/kasan.c:260 [inline]
 check_memory_region+0x13e/0x1b0 mm/kasan/kasan.c:267
 memcpy+0x37/0x50 mm/kasan/kasan.c:303
 strlcpy include/linux/string.h:300 [inline]
 __ip_tunnel_create+0xca/0x6b0 net/ipv4/ip_tunnel.c:257
 ip_tunnel_create net/ipv4/ip_tunnel.c:352 [inline]
 ip_tunnel_ioctl+0x818/0xd40 net/ipv4/ip_tunnel.c:861
 ipip_tunnel_ioctl+0x1c5/0x420 net/ipv4/ipip.c:350
 dev_ifsioc+0x43e/0xb90 net/core/dev_ioctl.c:334
 dev_ioctl+0x69a/0xcc0 net/core/dev_ioctl.c:525
 sock_ioctl+0x47e/0x680 net/socket.c:1015
 vfs_ioctl fs/ioctl.c:46 [inline]
 file_ioctl fs/ioctl.c:500 [inline]
 do_vfs_ioctl+0x1cf/0x1650 fs/ioctl.c:684
 ksys_ioctl+0xa9/0xd0 fs/ioctl.c:701
 SYSC_ioctl fs/ioctl.c:708 [inline]
 SyS_ioctl+0x24/0x30 fs/ioctl.c:706
 do_syscall_64+0x29e/0x9d0 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x42/0xb7

Fixes: c54419321455 ("GRE: Refactor GRE tunneling code.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_tunnel.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 4e90082b23a6..13f7bbc0168d 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -253,13 +253,14 @@ static struct net_device *__ip_tunnel_create(struct net *net,
 	struct net_device *dev;
 	char name[IFNAMSIZ];
 
-	if (parms->name[0])
+	err = -E2BIG;
+	if (parms->name[0]) {
+		if (!dev_valid_name(parms->name))
+			goto failed;
 		strlcpy(name, parms->name, IFNAMSIZ);
-	else {
-		if (strlen(ops->kind) > (IFNAMSIZ - 3)) {
-			err = -E2BIG;
+	} else {
+		if (strlen(ops->kind) > (IFNAMSIZ - 3))
 			goto failed;
-		}
 		strlcpy(name, ops->kind, IFNAMSIZ);
 		strncat(name, "%d", 2);
 	}
-- 
2.14.3


From 0c87516e2cdc98201a19061a2cc02fd333fc59ac Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 5 Apr 2018 06:39:28 -0700
Subject: [PATCH 23/42] ipv6: sit: better validate user provided tunnel names

[ Upstream commit b95211e066fc3494b7c115060b2297b4ba21f025 ]

Use dev_valid_name() to make sure user does not provide illegal
device name.

syzbot caught the following bug :

BUG: KASAN: stack-out-of-bounds in strlcpy include/linux/string.h:300 [inline]
BUG: KASAN: stack-out-of-bounds in ipip6_tunnel_locate+0x63b/0xaa0 net/ipv6/sit.c:254
Write of size 33 at addr ffff8801b64076d8 by task syzkaller932654/4453

CPU: 0 PID: 4453 Comm: syzkaller932654 Not tainted 4.16.0+ #1
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x1b9/0x29f lib/dump_stack.c:53
 print_address_description+0x6c/0x20b mm/kasan/report.c:256
 kasan_report_error mm/kasan/report.c:354 [inline]
 kasan_report.cold.7+0xac/0x2f5 mm/kasan/report.c:412
 check_memory_region_inline mm/kasan/kasan.c:260 [inline]
 check_memory_region+0x13e/0x1b0 mm/kasan/kasan.c:267
 memcpy+0x37/0x50 mm/kasan/kasan.c:303
 strlcpy include/linux/string.h:300 [inline]
 ipip6_tunnel_locate+0x63b/0xaa0 net/ipv6/sit.c:254
 ipip6_tunnel_ioctl+0xe71/0x241b net/ipv6/sit.c:1221
 dev_ifsioc+0x43e/0xb90 net/core/dev_ioctl.c:334
 dev_ioctl+0x69a/0xcc0 net/core/dev_ioctl.c:525
 sock_ioctl+0x47e/0x680 net/socket.c:1015
 vfs_ioctl fs/ioctl.c:46 [inline]
 file_ioctl fs/ioctl.c:500 [inline]
 do_vfs_ioctl+0x1cf/0x1650 fs/ioctl.c:684
 ksys_ioctl+0xa9/0xd0 fs/ioctl.c:701
 SYSC_ioctl fs/ioctl.c:708 [inline]
 SyS_ioctl+0x24/0x30 fs/ioctl.c:706
 do_syscall_64+0x29e/0x9d0 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x42/0xb7

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index cac815cc8600..f03c1a562135 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -244,11 +244,13 @@ static struct ip_tunnel *ipip6_tunnel_locate(struct net *net,
 	if (!create)
 		goto failed;
 
-	if (parms->name[0])
+	if (parms->name[0]) {
+		if (!dev_valid_name(parms->name))
+			goto failed;
 		strlcpy(name, parms->name, IFNAMSIZ);
-	else
+	} else {
 		strcpy(name, "sit%d");
-
+	}
 	dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN,
 			   ipip6_tunnel_setup);
 	if (!dev)
-- 
2.14.3


From 680b79bb8d9961b3c4edbf7bedc96e0d48365896 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 5 Apr 2018 06:39:29 -0700
Subject: [PATCH 24/42] ip6_gre: better validate user provided tunnel names

[ Upstream commit 5f42df013b8bc1b6511af7a04bf93b014884ae2a ]

Use dev_valid_name() to make sure user does not provide illegal
device name.

syzbot caught the following bug :

BUG: KASAN: stack-out-of-bounds in strlcpy include/linux/string.h:300 [inline]
BUG: KASAN: stack-out-of-bounds in ip6gre_tunnel_locate+0x334/0x860 net/ipv6/ip6_gre.c:339
Write of size 20 at addr ffff8801afb9f7b8 by task syzkaller851048/4466

CPU: 1 PID: 4466 Comm: syzkaller851048 Not tainted 4.16.0+ #1
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x1b9/0x29f lib/dump_stack.c:53
 print_address_description+0x6c/0x20b mm/kasan/report.c:256
 kasan_report_error mm/kasan/report.c:354 [inline]
 kasan_report.cold.7+0xac/0x2f5 mm/kasan/report.c:412
 check_memory_region_inline mm/kasan/kasan.c:260 [inline]
 check_memory_region+0x13e/0x1b0 mm/kasan/kasan.c:267
 memcpy+0x37/0x50 mm/kasan/kasan.c:303
 strlcpy include/linux/string.h:300 [inline]
 ip6gre_tunnel_locate+0x334/0x860 net/ipv6/ip6_gre.c:339
 ip6gre_tunnel_ioctl+0x69d/0x12e0 net/ipv6/ip6_gre.c:1195
 dev_ifsioc+0x43e/0xb90 net/core/dev_ioctl.c:334
 dev_ioctl+0x69a/0xcc0 net/core/dev_ioctl.c:525
 sock_ioctl+0x47e/0x680 net/socket.c:1015
 vfs_ioctl fs/ioctl.c:46 [inline]
 file_ioctl fs/ioctl.c:500 [inline]
 do_vfs_ioctl+0x1cf/0x1650 fs/ioctl.c:684
 ksys_ioctl+0xa9/0xd0 fs/ioctl.c:701
 SYSC_ioctl fs/ioctl.c:708 [inline]
 SyS_ioctl+0x24/0x30 fs/ioctl.c:706
 do_syscall_64+0x29e/0x9d0 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x42/0xb7

Fixes: c12b395a4664 ("gre: Support GRE over IPv6")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index e8ab306794d8..4228f3b2f347 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -319,11 +319,13 @@ static struct ip6_tnl *ip6gre_tunnel_locate(struct net *net,
 	if (t || !create)
 		return t;
 
-	if (parms->name[0])
+	if (parms->name[0]) {
+		if (!dev_valid_name(parms->name))
+			return NULL;
 		strlcpy(name, parms->name, IFNAMSIZ);
-	else
+	} else {
 		strcpy(name, "ip6gre%d");
-
+	}
 	dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN,
 			   ip6gre_tunnel_setup);
 	if (!dev)
-- 
2.14.3


From cff29d920216869d5ce2e0ccddf5c155c2399d98 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 5 Apr 2018 06:39:30 -0700
Subject: [PATCH 25/42] ip6_tunnel: better validate user provided tunnel names

[ Upstream commit db7a65e3ab78e5b1c4b17c0870ebee35a4ee3257 ]

Use valid_name() to make sure user does not provide illegal
device name.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 1161fd5630c1..7e11f6a811f5 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -297,13 +297,16 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p)
 	struct net_device *dev;
 	struct ip6_tnl *t;
 	char name[IFNAMSIZ];
-	int err = -ENOMEM;
+	int err = -E2BIG;
 
-	if (p->name[0])
+	if (p->name[0]) {
+		if (!dev_valid_name(p->name))
+			goto failed;
 		strlcpy(name, p->name, IFNAMSIZ);
-	else
+	} else {
 		sprintf(name, "ip6tnl%%d");
-
+	}
+	err = -ENOMEM;
 	dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN,
 			   ip6_tnl_dev_setup);
 	if (!dev)
-- 
2.14.3


From b32b211cc63f9a26b9d69b274afd96ddcf1113fc Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 5 Apr 2018 06:39:31 -0700
Subject: [PATCH 26/42] vti6: better validate user provided tunnel names

[ Upstream commit 537b361fbcbcc3cd6fe2bb47069fd292b9256d16 ]

Use valid_name() to make sure user does not provide illegal
device name.

Fixes: ed1efb2aefbb ("ipv6: Add support for IPsec virtual tunnel interfaces")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_vti.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index bcdc2d557de1..7c0f647b5195 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -212,10 +212,13 @@ static struct ip6_tnl *vti6_tnl_create(struct net *net, struct __ip6_tnl_parm *p
 	char name[IFNAMSIZ];
 	int err;
 
-	if (p->name[0])
+	if (p->name[0]) {
+		if (!dev_valid_name(p->name))
+			goto failed;
 		strlcpy(name, p->name, IFNAMSIZ);
-	else
+	} else {
 		sprintf(name, "ip6_vti%%d");
+	}
 
 	dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN, vti6_dev_setup);
 	if (!dev)
-- 
2.14.3


From 7579f62f4bef10ba18d9f95e898b99217ac36ffc Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Tue, 13 Mar 2018 21:43:43 +0200
Subject: [PATCH 27/42] net/mlx5e: Avoid using the ipv6 stub in the TC offload
 neigh update path

[ Upstream commit 423c9db29943cfc43e3a408192e9efa4178af6a1 ]

Currently we use the global ipv6_stub var to access the ipv6 global
nd table. This practice gets us to troubles when the stub is only partially
set e.g when ipv6 is loaded under the disabled policy. In this case, as of commit
343d60aada5a ("ipv6: change ipv6_stub_impl.ipv6_dst_lookup to take net argument")
the stub is not null, but stub->nd_tbl is and we crash.

As we can access the ipv6 nd_tbl directly, the fix is just to avoid the
reference through the stub. There is one place in the code where we
issue ipv6 route lookup and keep doing it through the stub, but that
mentioned commit makes sure we get -EAFNOSUPPORT from the stack.

Fixes: 232c001398ae ("net/mlx5e: Add support to neighbour update flow")
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Aviv Heller <avivh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 6 +++---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c  | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 45e03c427faf..1db16efa563e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -230,7 +230,7 @@ void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv)
 static void mlx5e_rep_neigh_update_init_interval(struct mlx5e_rep_priv *rpriv)
 {
 #if IS_ENABLED(CONFIG_IPV6)
-	unsigned long ipv6_interval = NEIGH_VAR(&ipv6_stub->nd_tbl->parms,
+	unsigned long ipv6_interval = NEIGH_VAR(&nd_tbl.parms,
 						DELAY_PROBE_TIME);
 #else
 	unsigned long ipv6_interval = ~0UL;
@@ -366,7 +366,7 @@ static int mlx5e_rep_netevent_event(struct notifier_block *nb,
 	case NETEVENT_NEIGH_UPDATE:
 		n = ptr;
 #if IS_ENABLED(CONFIG_IPV6)
-		if (n->tbl != ipv6_stub->nd_tbl && n->tbl != &arp_tbl)
+		if (n->tbl != &nd_tbl && n->tbl != &arp_tbl)
 #else
 		if (n->tbl != &arp_tbl)
 #endif
@@ -414,7 +414,7 @@ static int mlx5e_rep_netevent_event(struct notifier_block *nb,
 		 * done per device delay prob time parameter.
 		 */
 #if IS_ENABLED(CONFIG_IPV6)
-		if (!p->dev || (p->tbl != ipv6_stub->nd_tbl && p->tbl != &arp_tbl))
+		if (!p->dev || (p->tbl != &nd_tbl && p->tbl != &arp_tbl))
 #else
 		if (!p->dev || p->tbl != &arp_tbl)
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 9ba1f72060aa..38c366ebc23b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -484,7 +484,7 @@ void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe)
 		tbl = &arp_tbl;
 #if IS_ENABLED(CONFIG_IPV6)
 	else if (m_neigh->family == AF_INET6)
-		tbl = ipv6_stub->nd_tbl;
+		tbl = &nd_tbl;
 #endif
 	else
 		return;
-- 
2.14.3


From e40a010f340cd21392e666fc3c01ca9340de858d Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@mellanox.com>
Date: Thu, 8 Mar 2018 09:20:55 +0000
Subject: [PATCH 28/42] net/mlx5e: Fix memory usage issues in offloading TC
 flows

[ Upstream commit af1607c37d9d85a66fbcf43b7f11bf3d94b9bb69 ]

For NIC flows, the parsed attributes are not freed when we exit
successfully from mlx5e_configure_flower().

There is possible double free for eswitch flows. If error is returned
from rhashtable_insert_fast(), the parse attrs will be freed in
mlx5e_tc_del_flow(), but they will be freed again before exiting
mlx5e_configure_flower().

To fix both issues we do the following:
(1) change the condition that determines if to issue the free call to
    check if this flow is NIC flow, or it does not have encap action.
(2) reorder the code such that that the check and free calls are done
    before we attempt to add into the hash table.

Fixes: 232c001398ae ('net/mlx5e: Add support to neighbour update flow')
Signed-off-by: Jianbo Liu <jianbol@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 38c366ebc23b..42bab73a9f40 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2091,19 +2091,19 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv,
 	if (err != -EAGAIN)
 		flow->flags |= MLX5E_TC_FLOW_OFFLOADED;
 
+	if (!(flow->flags & MLX5E_TC_FLOW_ESWITCH) ||
+	    !(flow->esw_attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP))
+		kvfree(parse_attr);
+
 	err = rhashtable_insert_fast(&tc->ht, &flow->node,
 				     tc->ht_params);
-	if (err)
-		goto err_del_rule;
+	if (err) {
+		mlx5e_tc_del_flow(priv, flow);
+		kfree(flow);
+	}
 
-	if (flow->flags & MLX5E_TC_FLOW_ESWITCH &&
-	    !(flow->esw_attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP))
-		kvfree(parse_attr);
 	return err;
 
-err_del_rule:
-	mlx5e_tc_del_flow(priv, flow);
-
 err_free:
 	kvfree(parse_attr);
 	kfree(flow);
-- 
2.14.3


From afb74bab989f747307e8b53bb8d2d857b60d0023 Mon Sep 17 00:00:00 2001
From: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Date: Tue, 3 Apr 2018 17:24:23 -0700
Subject: [PATCH 29/42] nfp: use full 40 bits of the NSP buffer address

[ Upstream commit 1489bbd10e16079ce30a53d3c22a431fd47af791 ]

The NSP default buffer is a piece of NFP memory where additional
command data can be placed.  Its format has been copied from
host buffer, but the PCIe selection bits do not make sense in
this case.  If those get masked out from a NFP address - writes
to random place in the chip memory may be issued and crash the
device.

Even in the general NSP buffer case, it doesn't make sense to have the
PCIe selection bits there anymore. These are unused at the moment, and
when it becomes necessary, the PCIe selection bits should rather be
moved to another register to utilise more bits for the buffer address.

This has never been an issue because the buffer used to be
allocated in memory with less-than-38-bit-long address but that
is about to change.

Fixes: 1a64821c6af7 ("nfp: add support for service processor access")
Signed-off-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
index 37364555c42b..f88ff3f4b661 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
@@ -68,10 +68,11 @@
 /* CPP address to retrieve the data from */
 #define NSP_BUFFER		0x10
 #define   NSP_BUFFER_CPP	GENMASK_ULL(63, 40)
-#define   NSP_BUFFER_PCIE	GENMASK_ULL(39, 38)
-#define   NSP_BUFFER_ADDRESS	GENMASK_ULL(37, 0)
+#define   NSP_BUFFER_ADDRESS	GENMASK_ULL(39, 0)
 
 #define NSP_DFLT_BUFFER		0x18
+#define   NSP_DFLT_BUFFER_CPP	GENMASK_ULL(63, 40)
+#define   NSP_DFLT_BUFFER_ADDRESS	GENMASK_ULL(39, 0)
 
 #define NSP_DFLT_BUFFER_CONFIG	0x20
 #define   NSP_DFLT_BUFFER_SIZE_MB	GENMASK_ULL(7, 0)
@@ -412,8 +413,8 @@ static int nfp_nsp_command_buf(struct nfp_nsp *nsp, u16 code, u32 option,
 	if (err < 0)
 		return err;
 
-	cpp_id = FIELD_GET(NSP_BUFFER_CPP, reg) << 8;
-	cpp_buf = FIELD_GET(NSP_BUFFER_ADDRESS, reg);
+	cpp_id = FIELD_GET(NSP_DFLT_BUFFER_CPP, reg) << 8;
+	cpp_buf = FIELD_GET(NSP_DFLT_BUFFER_ADDRESS, reg);
 
 	if (in_buf && in_size) {
 		err = nfp_cpp_write(cpp, cpp_id, cpp_buf, in_buf, in_size);
-- 
2.14.3


From 0e1c8cca7680ef04d978477a3ee1e2362e9b3f76 Mon Sep 17 00:00:00 2001
From: David Lebrun <dlebrun@google.com>
Date: Thu, 29 Mar 2018 17:59:36 +0100
Subject: [PATCH 30/42] ipv6: sr: fix seg6 encap performances with TSO enabled

[ Upstream commit 5807b22c9164a21cd1077a9bc587f0bba361f72d ]

Enabling TSO can lead to abysmal performances when using seg6 in
encap mode, such as with the ixgbe driver. This patch adds a call to
iptunnel_handle_offloads() to remove the encapsulation bit if needed.

Before:
root@comp4-seg6bpf:~# iperf3 -c fc00::55
Connecting to host fc00::55, port 5201
[  4] local fc45::4 port 36592 connected to fc00::55 port 5201
[ ID] Interval           Transfer     Bandwidth       Retr  Cwnd
[  4]   0.00-1.00   sec   196 KBytes  1.60 Mbits/sec   47   6.66 KBytes
[  4]   1.00-2.00   sec   304 KBytes  2.49 Mbits/sec  100   5.33 KBytes
[  4]   2.00-3.00   sec   284 KBytes  2.32 Mbits/sec   92   5.33 KBytes

After:
root@comp4-seg6bpf:~# iperf3 -c fc00::55
Connecting to host fc00::55, port 5201
[  4] local fc45::4 port 43062 connected to fc00::55 port 5201
[ ID] Interval           Transfer     Bandwidth       Retr  Cwnd
[  4]   0.00-1.00   sec  1.03 GBytes  8.89 Gbits/sec    0    743 KBytes
[  4]   1.00-2.00   sec  1.03 GBytes  8.87 Gbits/sec    0    743 KBytes
[  4]   2.00-3.00   sec  1.03 GBytes  8.87 Gbits/sec    0    743 KBytes

Reported-by: Tom Herbert <tom@quantonium.net>
Fixes: 6c8702c60b88 ("ipv6: sr: add support for SRH encapsulation and injection with lwtunnels")
Signed-off-by: David Lebrun <dlebrun@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/seg6_iptunnel.c | 16 +++++++---------
 1 file changed, 7 insertions(+), 9 deletions(-)

diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 7a78dcfda68a..f343e6f0fc95 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -16,6 +16,7 @@
 #include <linux/net.h>
 #include <linux/module.h>
 #include <net/ip.h>
+#include <net/ip_tunnels.h>
 #include <net/lwtunnel.h>
 #include <net/netevent.h>
 #include <net/netns/generic.h>
@@ -211,11 +212,6 @@ static int seg6_do_srh(struct sk_buff *skb)
 
 	tinfo = seg6_encap_lwtunnel(dst->lwtstate);
 
-	if (likely(!skb->encapsulation)) {
-		skb_reset_inner_headers(skb);
-		skb->encapsulation = 1;
-	}
-
 	switch (tinfo->mode) {
 	case SEG6_IPTUN_MODE_INLINE:
 		if (skb->protocol != htons(ETH_P_IPV6))
@@ -224,10 +220,12 @@ static int seg6_do_srh(struct sk_buff *skb)
 		err = seg6_do_srh_inline(skb, tinfo->srh);
 		if (err)
 			return err;
-
-		skb_reset_inner_headers(skb);
 		break;
 	case SEG6_IPTUN_MODE_ENCAP:
+		err = iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6);
+		if (err)
+			return err;
+
 		if (skb->protocol == htons(ETH_P_IPV6))
 			proto = IPPROTO_IPV6;
 		else if (skb->protocol == htons(ETH_P_IP))
@@ -239,6 +237,8 @@ static int seg6_do_srh(struct sk_buff *skb)
 		if (err)
 			return err;
 
+		skb_set_inner_transport_header(skb, skb_transport_offset(skb));
+		skb_set_inner_protocol(skb, skb->protocol);
 		skb->protocol = htons(ETH_P_IPV6);
 		break;
 	case SEG6_IPTUN_MODE_L2ENCAP:
@@ -262,8 +262,6 @@ static int seg6_do_srh(struct sk_buff *skb)
 	ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
 	skb_set_transport_header(skb, sizeof(struct ipv6hdr));
 
-	skb_set_inner_protocol(skb, skb->protocol);
-
 	return 0;
 }
 
-- 
2.14.3


From 8a329766f724e5d252ad82f1f5596727ce9becb4 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@mellanox.com>
Date: Fri, 2 Mar 2018 02:09:08 +0000
Subject: [PATCH 31/42] net/mlx5e: Don't override vport admin link state in
 switchdev mode

The vport admin original link state will be re-applied after returning
back to legacy mode, it is not right to change the admin link state value
when in switchdev mode.

Use direct vport commands to alter logical vport state in netdev
representor open/close flows rather than the administrative eswitch API.

Fixes: 20a1ea674783 ('net/mlx5e: Support VF vport link state control for SRIOV switchdev mode')
Signed-off-by: Jianbo Liu <jianbol@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 1db16efa563e..adf2b7a795e9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -610,7 +610,6 @@ static int mlx5e_rep_open(struct net_device *dev)
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	struct mlx5_eswitch_rep *rep = rpriv->rep;
-	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	int err;
 
 	mutex_lock(&priv->state_lock);
@@ -618,8 +617,9 @@ static int mlx5e_rep_open(struct net_device *dev)
 	if (err)
 		goto unlock;
 
-	if (!mlx5_eswitch_set_vport_state(esw, rep->vport,
-					  MLX5_ESW_VPORT_ADMIN_STATE_UP))
+	if (!mlx5_modify_vport_admin_state(priv->mdev,
+			MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT,
+			rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_UP))
 		netif_carrier_on(dev);
 
 unlock:
@@ -632,11 +632,12 @@ static int mlx5e_rep_close(struct net_device *dev)
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	struct mlx5_eswitch_rep *rep = rpriv->rep;
-	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	int ret;
 
 	mutex_lock(&priv->state_lock);
-	(void)mlx5_eswitch_set_vport_state(esw, rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_DOWN);
+	mlx5_modify_vport_admin_state(priv->mdev,
+			MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT,
+			rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_DOWN);
 	ret = mlx5e_close_locked(dev);
 	mutex_unlock(&priv->state_lock);
 	return ret;
-- 
2.14.3


From fbf07acc8c7229d01e17845e9935f715d54bb1a3 Mon Sep 17 00:00:00 2001
From: Shahar Klein <shahark@mellanox.com>
Date: Tue, 20 Mar 2018 14:44:40 +0200
Subject: [PATCH 32/42] net/mlx5e: Sync netdev vxlan ports at open

[ Upstream commit a117f73dc2430443f23e18367fa545981129c1a6 ]

When mlx5_core is loaded it is expected to sync ports
with all vxlan devices so it can support vxlan encap/decap.
This is done via udp_tunnel_get_rx_info(). Currently this
call is set in mlx5e_nic_enable() and if the netdev is not in
NETREG_REGISTERED state it will not be called.

Normally on load the netdev state is not NETREG_REGISTERED
so udp_tunnel_get_rx_info() will not be called.

Moving udp_tunnel_get_rx_info() to mlx5e_open() so
it will be called on netdev UP event and allow encap/decap.

Fixes: 610e89e05c3f ("net/mlx5e: Don't sync netdev state when not registered")
Signed-off-by: Shahar Klein <shahark@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index a863572882b2..225b2ad3e15f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2718,6 +2718,9 @@ int mlx5e_open(struct net_device *netdev)
 		mlx5_set_port_admin_status(priv->mdev, MLX5_PORT_UP);
 	mutex_unlock(&priv->state_lock);
 
+	if (mlx5e_vxlan_allowed(priv->mdev))
+		udp_tunnel_get_rx_info(netdev);
+
 	return err;
 }
 
@@ -4276,13 +4279,6 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 	if (netdev->reg_state != NETREG_REGISTERED)
 		return;
 
-	/* Device already registered: sync netdev system state */
-	if (mlx5e_vxlan_allowed(mdev)) {
-		rtnl_lock();
-		udp_tunnel_get_rx_info(netdev);
-		rtnl_unlock();
-	}
-
 	queue_work(priv->wq, &priv->set_rx_mode_work);
 
 	rtnl_lock();
-- 
2.14.3


From 097eb5547f9a5e57fa27b63546f0840a2f563ea2 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Fri, 16 Mar 2018 00:00:55 +0100
Subject: [PATCH 33/42] net/sched: fix NULL dereference in the error path of
 tunnel_key_init()

[ Upstream commit abdadd3cfd3e7ea3da61ac774f84777d1f702058 ]

when the following command

 # tc action add action tunnel_key unset index 100

is run for the first time, and tunnel_key_init() fails to allocate struct
tcf_tunnel_key_params, tunnel_key_release() dereferences NULL pointers.
This causes the following error:

 BUG: unable to handle kernel NULL pointer dereference at 0000000000000010
 IP: tunnel_key_release+0xd/0x40 [act_tunnel_key]
 PGD 8000000033787067 P4D 8000000033787067 PUD 74646067 PMD 0
 Oops: 0000 [#1] SMP PTI
 Modules linked in: act_tunnel_key(E) act_csum ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 mbcache jbd2 crct10dif_pclmul crc32_pclmul snd_hda_codec_generic ghash_clmulni_intel snd_hda_intel pcbc snd_hda_codec snd_hda_core snd_hwdep snd_seq aesni_intel snd_seq_device crypto_simd glue_helper snd_pcm cryptd joydev snd_timer pcspkr virtio_balloon snd i2c_piix4 soundcore nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm virtio_net virtio_blk drm virtio_console crc32c_intel ata_piix serio_raw i2c_core virtio_pci libata virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod
 CPU: 2 PID: 3101 Comm: tc Tainted: G            E    4.16.0-rc4.act_vlan.orig+ #403
 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
 RIP: 0010:tunnel_key_release+0xd/0x40 [act_tunnel_key]
 RSP: 0018:ffffba46803b7768 EFLAGS: 00010286
 RAX: ffffffffc09010a0 RBX: 0000000000000000 RCX: 0000000000000024
 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff99ee336d7480
 RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000044
 R10: 0000000000000220 R11: ffff99ee79d73131 R12: 0000000000000000
 R13: ffff99ee32d67610 R14: ffff99ee7671dc38 R15: 00000000fffffff4
 FS:  00007febcb2cd740(0000) GS:ffff99ee7fd00000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000000010 CR3: 000000007c8e4005 CR4: 00000000001606e0
 Call Trace:
  __tcf_idr_release+0x79/0xf0
  tunnel_key_init+0xd9/0x460 [act_tunnel_key]
  tcf_action_init_1+0x2cc/0x430
  tcf_action_init+0xd3/0x1b0
  tc_ctl_action+0x18b/0x240
  rtnetlink_rcv_msg+0x29c/0x310
  ? _cond_resched+0x15/0x30
  ? __kmalloc_node_track_caller+0x1b9/0x270
  ? rtnl_calcit.isra.28+0x100/0x100
  netlink_rcv_skb+0xd2/0x110
  netlink_unicast+0x17c/0x230
  netlink_sendmsg+0x2cd/0x3c0
  sock_sendmsg+0x30/0x40
  ___sys_sendmsg+0x27a/0x290
  __sys_sendmsg+0x51/0x90
  do_syscall_64+0x6e/0x1a0
  entry_SYSCALL_64_after_hwframe+0x3d/0xa2
 RIP: 0033:0x7febca6deba0
 RSP: 002b:00007ffe7b0dd128 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
 RAX: ffffffffffffffda RBX: 00007ffe7b0dd250 RCX: 00007febca6deba0
 RDX: 0000000000000000 RSI: 00007ffe7b0dd1a0 RDI: 0000000000000003
 RBP: 000000005aaa90cb R08: 0000000000000002 R09: 0000000000000000
 R10: 00007ffe7b0dcba0 R11: 0000000000000246 R12: 0000000000000000
 R13: 00007ffe7b0dd264 R14: 0000000000000001 R15: 0000000000669f60
 Code: 44 00 00 8b 0d b5 23 00 00 48 8b 87 48 10 00 00 48 8b 3c c8 e9 a5 e5 d8 c3 0f 1f 44 00 00 0f 1f 44 00 00 53 48 8b 9f b0 00 00 00 <83> 7b 10 01 74 0b 48 89 df 31 f6 5b e9 f2 fa 7f c3 48 8b 7b 18
 RIP: tunnel_key_release+0xd/0x40 [act_tunnel_key] RSP: ffffba46803b7768
 CR2: 0000000000000010

Fix this in tunnel_key_release(), ensuring 'param' is not NULL before
dereferencing it.

Fixes: d0f6dd8a914f ("net/sched: Introduce act_tunnel_key")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_tunnel_key.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 22bf1a376b91..7cb63616805d 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -208,11 +208,12 @@ static void tunnel_key_release(struct tc_action *a, int bind)
 	struct tcf_tunnel_key_params *params;
 
 	params = rcu_dereference_protected(t->params, 1);
+	if (params) {
+		if (params->tcft_action == TCA_TUNNEL_KEY_ACT_SET)
+			dst_release(&params->tcft_enc_metadata->dst);
 
-	if (params->tcft_action == TCA_TUNNEL_KEY_ACT_SET)
-		dst_release(&params->tcft_enc_metadata->dst);
-
-	kfree_rcu(params, rcu);
+		kfree_rcu(params, rcu);
+	}
 }
 
 static int tunnel_key_dump_addresses(struct sk_buff *skb,
-- 
2.14.3


From 4cc900888eba05665116fb0c07f9f6d0ef0bd4a8 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Fri, 16 Mar 2018 00:00:57 +0100
Subject: [PATCH 34/42] net/sched: fix NULL dereference on the error path of
 tcf_skbmod_init()

[ Upstream commit 2d433610176d6569e8b3a28f67bc72235bf69efc ]

when the following command

 # tc action replace action skbmod swap mac index 100

is run for the first time, and tcf_skbmod_init() fails to allocate struct
tcf_skbmod_params, tcf_skbmod_cleanup() calls kfree_rcu(NULL), thus
causing the following error:

 BUG: unable to handle kernel NULL pointer dereference at 0000000000000008
 IP: __call_rcu+0x23/0x2b0
 PGD 8000000034057067 P4D 8000000034057067 PUD 74937067 PMD 0
 Oops: 0002 [#1] SMP PTI
 Modules linked in: act_skbmod(E) psample ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 snd_hda_codec_generic snd_hda_intel snd_hda_codec crct10dif_pclmul mbcache jbd2 crc32_pclmul snd_hda_core ghash_clmulni_intel snd_hwdep pcbc snd_seq snd_seq_device snd_pcm aesni_intel snd_timer crypto_simd glue_helper snd cryptd virtio_balloon joydev soundcore pcspkr i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm drm virtio_console virtio_net virtio_blk ata_piix libata crc32c_intel virtio_pci serio_raw virtio_ring virtio i2c_core floppy dm_mirror dm_region_hash dm_log dm_mod [last unloaded: act_skbmod]
 CPU: 3 PID: 3144 Comm: tc Tainted: G            E    4.16.0-rc4.act_vlan.orig+ #403
 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
 RIP: 0010:__call_rcu+0x23/0x2b0
 RSP: 0018:ffffbd2e403e7798 EFLAGS: 00010246
 RAX: ffffffffc0872080 RBX: ffff981d34bff780 RCX: 00000000ffffffff
 RDX: ffffffff922a5f00 RSI: 0000000000000000 RDI: 0000000000000000
 RBP: 0000000000000000 R08: 0000000000000001 R09: 000000000000021f
 R10: 000000003d003000 R11: 0000000000aaaaaa R12: 0000000000000000
 R13: ffffffff922a5f00 R14: 0000000000000001 R15: ffff981d3b698c2c
 FS:  00007f3678292740(0000) GS:ffff981d3fd80000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000000008 CR3: 000000007c57a006 CR4: 00000000001606e0
 Call Trace:
  __tcf_idr_release+0x79/0xf0
  tcf_skbmod_init+0x1d1/0x210 [act_skbmod]
  tcf_action_init_1+0x2cc/0x430
  tcf_action_init+0xd3/0x1b0
  tc_ctl_action+0x18b/0x240
  rtnetlink_rcv_msg+0x29c/0x310
  ? _cond_resched+0x15/0x30
  ? __kmalloc_node_track_caller+0x1b9/0x270
  ? rtnl_calcit.isra.28+0x100/0x100
  netlink_rcv_skb+0xd2/0x110
  netlink_unicast+0x17c/0x230
  netlink_sendmsg+0x2cd/0x3c0
  sock_sendmsg+0x30/0x40
  ___sys_sendmsg+0x27a/0x290
  ? filemap_map_pages+0x34a/0x3a0
  ? __handle_mm_fault+0xbfd/0xe20
  __sys_sendmsg+0x51/0x90
  do_syscall_64+0x6e/0x1a0
  entry_SYSCALL_64_after_hwframe+0x3d/0xa2
 RIP: 0033:0x7f36776a3ba0
 RSP: 002b:00007fff4703b618 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
 RAX: ffffffffffffffda RBX: 00007fff4703b740 RCX: 00007f36776a3ba0
 RDX: 0000000000000000 RSI: 00007fff4703b690 RDI: 0000000000000003
 RBP: 000000005aaaba36 R08: 0000000000000002 R09: 0000000000000000
 R10: 00007fff4703b0a0 R11: 0000000000000246 R12: 0000000000000000
 R13: 00007fff4703b754 R14: 0000000000000001 R15: 0000000000669f60
 Code: 5d e9 42 da ff ff 66 90 0f 1f 44 00 00 41 57 41 56 41 55 49 89 d5 41 54 55 48 89 fd 53 48 83 ec 08 40 f6 c7 07 0f 85 19 02 00 00 <48> 89 75 08 48 c7 45 00 00 00 00 00 9c 58 0f 1f 44 00 00 49 89
 RIP: __call_rcu+0x23/0x2b0 RSP: ffffbd2e403e7798
 CR2: 0000000000000008

Fix it in tcf_skbmod_cleanup(), ensuring that kfree_rcu(p, ...) is called
only when p is not NULL.

Fixes: 86da71b57383 ("net_sched: Introduce skbmod action")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_skbmod.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index b642ad3d39dd..6d10b3af479b 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -190,7 +190,8 @@ static void tcf_skbmod_cleanup(struct tc_action *a, int bind)
 	struct tcf_skbmod_params  *p;
 
 	p = rcu_dereference_protected(d->skbmod_p, 1);
-	kfree_rcu(p, rcu);
+	if (p)
+		kfree_rcu(p, rcu);
 }
 
 static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a,
-- 
2.14.3


From 59518f099b34f4b4f7689f5d1dfa9eaf8a25db47 Mon Sep 17 00:00:00 2001
From: Dave Watson <davejwatson@fb.com>
Date: Mon, 26 Mar 2018 12:31:21 -0700
Subject: [PATCH 35/42] strparser: Fix sign of err codes

[ Upstream commit cd00edc179863848abab5cc5683de5b7b5f70954 ]

strp_parser_err is called with a negative code everywhere, which then
calls abort_parser with a negative code.  strp_msg_timeout calls
abort_parser directly with a positive code.  Negate ETIMEDOUT
to match signed-ness of other calls.

The default abort_parser callback, strp_abort_strp, sets
sk->sk_err to err.  Also negate the error here so sk_err always
holds a positive value, as the rest of the net code expects.  Currently
a negative sk_err can result in endless loops, or user code that
thinks it actually sent/received err bytes.

Found while testing net/tls_sw recv path.

Fixes: 43a0c6751a322847 ("strparser: Stream parser for messages")
Signed-off-by: Dave Watson <davejwatson@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/strparser/strparser.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index c5fda15ba319..4a3a3f1331ee 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -60,7 +60,7 @@ static void strp_abort_strp(struct strparser *strp, int err)
 		struct sock *sk = strp->sk;
 
 		/* Report an error on the lower socket */
-		sk->sk_err = err;
+		sk->sk_err = -err;
 		sk->sk_error_report(sk);
 	}
 }
@@ -458,7 +458,7 @@ static void strp_msg_timeout(struct work_struct *w)
 	/* Message assembly timed out */
 	STRP_STATS_INCR(strp->stats.msg_timeouts);
 	strp->cb.lock(strp);
-	strp->cb.abort_parser(strp, ETIMEDOUT);
+	strp->cb.abort_parser(strp, -ETIMEDOUT);
 	strp->cb.unlock(strp);
 }
 
-- 
2.14.3


From 0d8bca725483357fea249e9d474d25cd06d87c8c Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Tue, 27 Mar 2018 14:41:18 +0300
Subject: [PATCH 36/42] net/mlx4_en: Fix mixed PFC and Global pause user
 control requests

[ Upstream commit 6e8814ceb7e8f468659ef9253bd212c07ae19584 ]

Global pause and PFC configuration should be mutually exclusive (i.e. only
one of them at most can be set). However, once PFC was turned off,
driver automatically turned Global pause on. This is a bug.

Fix the driver behaviour to turn off PFC/Global once the user turned the
other on.

This also fixed a weird behaviour that at a current time, the profile
had both PFC and global pause configuration turned on, which is
Hardware-wise impossible and caused returning false positive indication
to query tools.

In addition, fix error code when setting global pause or PFC to change
metadata only upon successful change.

Also, removed useless debug print.

Fixes: af7d51852631 ("net/mlx4_en: Add DCB PFC support through CEE netlink commands")
Fixes: c27a02cd94d6 ("mlx4_en: Add driver for Mellanox ConnectX 10GbE NIC")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c  | 72 ++++++++++++++-----------
 drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 33 +++++++-----
 drivers/net/ethernet/mellanox/mlx4/en_main.c    |  4 +-
 3 files changed, 62 insertions(+), 47 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
index 5f41dc92aa68..6e05d996b256 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
@@ -156,57 +156,63 @@ static int mlx4_en_dcbnl_getnumtcs(struct net_device *netdev, int tcid, u8 *num)
 static u8 mlx4_en_dcbnl_set_all(struct net_device *netdev)
 {
 	struct mlx4_en_priv *priv = netdev_priv(netdev);
+	struct mlx4_en_port_profile *prof = priv->prof;
 	struct mlx4_en_dev *mdev = priv->mdev;
+	u8 tx_pause, tx_ppp, rx_pause, rx_ppp;
 
 	if (!(priv->dcbx_cap & DCB_CAP_DCBX_VER_CEE))
 		return 1;
 
 	if (priv->cee_config.pfc_state) {
 		int tc;
+		rx_ppp = prof->rx_ppp;
+		tx_ppp = prof->tx_ppp;
 
-		priv->prof->rx_pause = 0;
-		priv->prof->tx_pause = 0;
 		for (tc = 0; tc < CEE_DCBX_MAX_PRIO; tc++) {
 			u8 tc_mask = 1 << tc;
 
 			switch (priv->cee_config.dcb_pfc[tc]) {
 			case pfc_disabled:
-				priv->prof->tx_ppp &= ~tc_mask;
-				priv->prof->rx_ppp &= ~tc_mask;
+				tx_ppp &= ~tc_mask;
+				rx_ppp &= ~tc_mask;
 				break;
 			case pfc_enabled_full:
-				priv->prof->tx_ppp |= tc_mask;
-				priv->prof->rx_ppp |= tc_mask;
+				tx_ppp |= tc_mask;
+				rx_ppp |= tc_mask;
 				break;
 			case pfc_enabled_tx:
-				priv->prof->tx_ppp |= tc_mask;
-				priv->prof->rx_ppp &= ~tc_mask;
+				tx_ppp |= tc_mask;
+				rx_ppp &= ~tc_mask;
 				break;
 			case pfc_enabled_rx:
-				priv->prof->tx_ppp &= ~tc_mask;
-				priv->prof->rx_ppp |= tc_mask;
+				tx_ppp &= ~tc_mask;
+				rx_ppp |= tc_mask;
 				break;
 			default:
 				break;
 			}
 		}
-		en_dbg(DRV, priv, "Set pfc on\n");
+		rx_pause = !!(rx_ppp || tx_ppp) ? 0 : prof->rx_pause;
+		tx_pause = !!(rx_ppp || tx_ppp) ? 0 : prof->tx_pause;
 	} else {
-		priv->prof->rx_pause = 1;
-		priv->prof->tx_pause = 1;
-		en_dbg(DRV, priv, "Set pfc off\n");
+		rx_ppp = 0;
+		tx_ppp = 0;
+		rx_pause = prof->rx_pause;
+		tx_pause = prof->tx_pause;
 	}
 
 	if (mlx4_SET_PORT_general(mdev->dev, priv->port,
 				  priv->rx_skb_size + ETH_FCS_LEN,
-				  priv->prof->tx_pause,
-				  priv->prof->tx_ppp,
-				  priv->prof->rx_pause,
-				  priv->prof->rx_ppp)) {
+				  tx_pause, tx_ppp, rx_pause, rx_ppp)) {
 		en_err(priv, "Failed setting pause params\n");
 		return 1;
 	}
 
+	prof->tx_ppp = tx_ppp;
+	prof->rx_ppp = rx_ppp;
+	prof->tx_pause = tx_pause;
+	prof->rx_pause = rx_pause;
+
 	return 0;
 }
 
@@ -403,6 +409,7 @@ static int mlx4_en_dcbnl_ieee_setpfc(struct net_device *dev,
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_port_profile *prof = priv->prof;
 	struct mlx4_en_dev *mdev = priv->mdev;
+	u32 tx_pause, tx_ppp, rx_pause, rx_ppp;
 	int err;
 
 	en_dbg(DRV, priv, "cap: 0x%x en: 0x%x mbc: 0x%x delay: %d\n",
@@ -411,23 +418,26 @@ static int mlx4_en_dcbnl_ieee_setpfc(struct net_device *dev,
 			pfc->mbc,
 			pfc->delay);
 
-	prof->rx_pause = !pfc->pfc_en;
-	prof->tx_pause = !pfc->pfc_en;
-	prof->rx_ppp = pfc->pfc_en;
-	prof->tx_ppp = pfc->pfc_en;
+	rx_pause = prof->rx_pause && !pfc->pfc_en;
+	tx_pause = prof->tx_pause && !pfc->pfc_en;
+	rx_ppp = pfc->pfc_en;
+	tx_ppp = pfc->pfc_en;
 
 	err = mlx4_SET_PORT_general(mdev->dev, priv->port,
 				    priv->rx_skb_size + ETH_FCS_LEN,
-				    prof->tx_pause,
-				    prof->tx_ppp,
-				    prof->rx_pause,
-				    prof->rx_ppp);
-	if (err)
+				    tx_pause, tx_ppp, rx_pause, rx_ppp);
+	if (err) {
 		en_err(priv, "Failed setting pause params\n");
-	else
-		mlx4_en_update_pfc_stats_bitmap(mdev->dev, &priv->stats_bitmap,
-						prof->rx_ppp, prof->rx_pause,
-						prof->tx_ppp, prof->tx_pause);
+		return err;
+	}
+
+	mlx4_en_update_pfc_stats_bitmap(mdev->dev, &priv->stats_bitmap,
+					rx_ppp, rx_pause, tx_ppp, tx_pause);
+
+	prof->tx_ppp = tx_ppp;
+	prof->rx_ppp = rx_ppp;
+	prof->rx_pause = rx_pause;
+	prof->tx_pause = tx_pause;
 
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 3d4e4a5d00d1..67f74fcb265e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1046,27 +1046,32 @@ static int mlx4_en_set_pauseparam(struct net_device *dev,
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
+	u8 tx_pause, tx_ppp, rx_pause, rx_ppp;
 	int err;
 
 	if (pause->autoneg)
 		return -EINVAL;
 
-	priv->prof->tx_pause = pause->tx_pause != 0;
-	priv->prof->rx_pause = pause->rx_pause != 0;
+	tx_pause = !!(pause->tx_pause);
+	rx_pause = !!(pause->rx_pause);
+	rx_ppp = priv->prof->rx_ppp && !(tx_pause || rx_pause);
+	tx_ppp = priv->prof->tx_ppp && !(tx_pause || rx_pause);
+
 	err = mlx4_SET_PORT_general(mdev->dev, priv->port,
 				    priv->rx_skb_size + ETH_FCS_LEN,
-				    priv->prof->tx_pause,
-				    priv->prof->tx_ppp,
-				    priv->prof->rx_pause,
-				    priv->prof->rx_ppp);
-	if (err)
-		en_err(priv, "Failed setting pause params\n");
-	else
-		mlx4_en_update_pfc_stats_bitmap(mdev->dev, &priv->stats_bitmap,
-						priv->prof->rx_ppp,
-						priv->prof->rx_pause,
-						priv->prof->tx_ppp,
-						priv->prof->tx_pause);
+				    tx_pause, tx_ppp, rx_pause, rx_ppp);
+	if (err) {
+		en_err(priv, "Failed setting pause params, err = %d\n", err);
+		return err;
+	}
+
+	mlx4_en_update_pfc_stats_bitmap(mdev->dev, &priv->stats_bitmap,
+					rx_ppp, rx_pause, tx_ppp, tx_pause);
+
+	priv->prof->tx_pause = tx_pause;
+	priv->prof->rx_pause = rx_pause;
+	priv->prof->tx_ppp = tx_ppp;
+	priv->prof->rx_ppp = rx_ppp;
 
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c
index 686e18de9a97..6b2f7122b3ab 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c
@@ -163,9 +163,9 @@ static void mlx4_en_get_profile(struct mlx4_en_dev *mdev)
 		params->udp_rss = 0;
 	}
 	for (i = 1; i <= MLX4_MAX_PORTS; i++) {
-		params->prof[i].rx_pause = 1;
+		params->prof[i].rx_pause = !(pfcrx || pfctx);
 		params->prof[i].rx_ppp = pfcrx;
-		params->prof[i].tx_pause = 1;
+		params->prof[i].tx_pause = !(pfcrx || pfctx);
 		params->prof[i].tx_ppp = pfctx;
 		params->prof[i].tx_ring_size = MLX4_EN_DEF_TX_RING_SIZE;
 		params->prof[i].rx_ring_size = MLX4_EN_DEF_RX_RING_SIZE;
-- 
2.14.3


From 4b66f06f2c402503c23a8f06948162ae83a90bdb Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@mellanox.com>
Date: Wed, 28 Feb 2018 12:56:42 +0200
Subject: [PATCH 37/42] net/mlx5e: Fix traffic being dropped on VF representor

[ Upstream commit 4246f698dd58e3c6246fa919ef0b0a1d29a57e4a ]

Increase representor netdev RQ size to avoid dropped packets.
The current size (two) is just too small to keep up with
conventional slow path traffic patterns.
Also match the SQ size to the RQ size.

Fixes: cb67b832921c ("net/mlx5e: Introduce SRIOV VF representors")
Signed-off-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Paul Blakey <paulb@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index adf2b7a795e9..5ffd1db4e797 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -43,6 +43,11 @@
 #include "en_tc.h"
 #include "fs_core.h"
 
+#define MLX5E_REP_PARAMS_LOG_SQ_SIZE \
+	max(0x6, MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE)
+#define MLX5E_REP_PARAMS_LOG_RQ_SIZE \
+	max(0x6, MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE)
+
 static const char mlx5e_rep_driver_name[] = "mlx5e_rep";
 
 static void mlx5e_rep_get_drvinfo(struct net_device *dev,
@@ -798,9 +803,9 @@ static void mlx5e_build_rep_params(struct mlx5_core_dev *mdev,
 					 MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
 					 MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
 
-	params->log_sq_size = MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
+	params->log_sq_size = MLX5E_REP_PARAMS_LOG_SQ_SIZE;
 	params->rq_wq_type  = MLX5_WQ_TYPE_LINKED_LIST;
-	params->log_rq_size = MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE;
+	params->log_rq_size = MLX5E_REP_PARAMS_LOG_RQ_SIZE;
 
 	params->rx_am_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
 	mlx5e_set_rx_cq_mode_params(params, cq_period_mode);
-- 
2.14.3


From 838a1f94d12fffdeff6e85a07a11b039a9628020 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Thu, 29 Mar 2018 16:00:04 +0800
Subject: [PATCH 38/42] vhost: validate log when IOTLB is enabled

[ Upstream commit d65026c6c62e7d9616c8ceb5a53b68bcdc050525 ]

Vq log_base is the userspace address of bitmap which has nothing to do
with IOTLB. So it needs to be validated unconditionally otherwise we
may try use 0 as log_base which may lead to pin pages that will lead
unexpected result (e.g trigger BUG_ON() in set_bit_to_user()).

Fixes: 6b1e6cc7855b0 ("vhost: new device IOTLB API")
Reported-by: syzbot+6304bf97ef436580fede@syzkaller.appspotmail.com
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/vhost.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index c1033dc0e3f5..c692e0b13242 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -1252,14 +1252,12 @@ static int vq_log_access_ok(struct vhost_virtqueue *vq,
 /* Caller should have vq mutex and device mutex */
 int vhost_vq_access_ok(struct vhost_virtqueue *vq)
 {
-	if (vq->iotlb) {
-		/* When device IOTLB was used, the access validation
-		 * will be validated during prefetching.
-		 */
-		return 1;
-	}
-	return vq_access_ok(vq, vq->num, vq->desc, vq->avail, vq->used) &&
-		vq_log_access_ok(vq, vq->log_base);
+	int ret = vq_log_access_ok(vq, vq->log_base);
+
+	if (ret || vq->iotlb)
+		return ret;
+
+	return vq_access_ok(vq, vq->num, vq->desc, vq->avail, vq->used);
 }
 EXPORT_SYMBOL_GPL(vhost_vq_access_ok);
 
-- 
2.14.3


From e239d3fe809d33869e31672d6e4afe3cc6330848 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 1 Apr 2018 22:40:35 +0800
Subject: [PATCH 39/42] route: check sysctl_fib_multipath_use_neigh earlier
 than hash

[ Upstream commit 6174a30df1b902e1fedbd728f5343937e83e64e6 ]

Prior to this patch, when one packet is hashed into path [1]
(hash <= nh_upper_bound) and it's neigh is dead, it will try
path [2]. However, if path [2]'s neigh is alive but it's
hash > nh_upper_bound, it will not return this alive path.
This packet will never be sent even if path [2] is alive.

 3.3.3.1/24:
  nexthop via 1.1.1.254 dev eth1 weight 1 <--[1] (dead neigh)
  nexthop via 2.2.2.254 dev eth2 weight 1 <--[2]

With sysctl_fib_multipath_use_neigh set is supposed to find an
available path respecting to the l3/l4 hash. But if there is
no available route with this hash, it should at least return
an alive route even with other hash.

This patch is to fix it by processing fib_multipath_use_neigh
earlier than the hash check, so that it will at least return
an alive route if there is when fib_multipath_use_neigh is
enabled. It's also compatible with before when there are alive
routes with the l3/l4 hash.

Fixes: a6db4494d218 ("net: ipv4: Consider failed nexthops in multipath routes")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_semantics.c | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 1ee6c0d8dde4..f39955913d3f 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1755,18 +1755,20 @@ void fib_select_multipath(struct fib_result *res, int hash)
 	bool first = false;
 
 	for_nexthops(fi) {
+		if (net->ipv4.sysctl_fib_multipath_use_neigh) {
+			if (!fib_good_nh(nh))
+				continue;
+			if (!first) {
+				res->nh_sel = nhsel;
+				first = true;
+			}
+		}
+
 		if (hash > atomic_read(&nh->nh_upper_bound))
 			continue;
 
-		if (!net->ipv4.sysctl_fib_multipath_use_neigh ||
-		    fib_good_nh(nh)) {
-			res->nh_sel = nhsel;
-			return;
-		}
-		if (!first) {
-			res->nh_sel = nhsel;
-			first = true;
-		}
+		res->nh_sel = nhsel;
+		return;
 	} endfor_nexthops(fi);
 }
 #endif
-- 
2.14.3


From 1265b772ccf9c52c1eb6a78e251624d6855faf20 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 26 Mar 2018 01:25:06 +0800
Subject: [PATCH 40/42] team: move dev_mc_sync after master_upper_dev_link in
 team_port_add

[ Upstream commit 982cf3b3999d39a2eaca0a65542df33c19b5d814 ]

The same fix as in 'bonding: move dev_mc_sync after master_upper_dev_link
in bond_enslave' is needed for team driver.

The panic can be reproduced easily:

  ip link add team1 type team
  ip link set team1 up
  ip link add link team1 vlan1 type vlan id 80
  ip link set vlan1 master team1

Fixes: cb41c997d444 ("team: team should sync the port's uc/mc addrs when add a port")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 23cd41c82210..2a366554c503 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1197,11 +1197,6 @@ static int team_port_add(struct team *team, struct net_device *port_dev)
 		goto err_dev_open;
 	}
 
-	netif_addr_lock_bh(dev);
-	dev_uc_sync_multiple(port_dev, dev);
-	dev_mc_sync_multiple(port_dev, dev);
-	netif_addr_unlock_bh(dev);
-
 	err = vlan_vids_add_by_dev(port_dev, dev);
 	if (err) {
 		netdev_err(dev, "Failed to add vlan ids to device %s\n",
@@ -1241,6 +1236,11 @@ static int team_port_add(struct team *team, struct net_device *port_dev)
 		goto err_option_port_add;
 	}
 
+	netif_addr_lock_bh(dev);
+	dev_uc_sync_multiple(port_dev, dev);
+	dev_mc_sync_multiple(port_dev, dev);
+	netif_addr_unlock_bh(dev);
+
 	port->index = -1;
 	list_add_tail_rcu(&port->list, &team->port_list);
 	team_port_enable(team, port);
@@ -1265,8 +1265,6 @@ static int team_port_add(struct team *team, struct net_device *port_dev)
 	vlan_vids_del_by_dev(port_dev, dev);
 
 err_vids_add:
-	dev_uc_unsync(port_dev, dev);
-	dev_mc_unsync(port_dev, dev);
 	dev_close(port_dev);
 
 err_dev_open:
-- 
2.14.3


From 9c34bd199a034699320a8829f090346f6ddc8898 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Mon, 26 Mar 2018 16:10:23 +0800
Subject: [PATCH 41/42] vhost_net: add missing lock nesting notation

[ Upstream commit aaa3149bbee9ba9b4e6f0bd6e3e7d191edeae942 ]

We try to hold TX virtqueue mutex in vhost_net_rx_peek_head_len()
after RX virtqueue mutex is held in handle_rx(). This requires an
appropriate lock nesting notation to calm down deadlock detector.

Fixes: 0308813724606 ("vhost_net: basic polling support")
Reported-by: syzbot+7f073540b1384a614e09@syzkaller.appspotmail.com
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/net.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 082891dffd9d..b0d606b2d06c 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -622,7 +622,7 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk)
 
 	if (!len && vq->busyloop_timeout) {
 		/* Both tx vq and rx socket were polled here */
-		mutex_lock(&vq->mutex);
+		mutex_lock_nested(&vq->mutex, 1);
 		vhost_disable_notify(&net->dev, vq);
 
 		preempt_disable();
@@ -755,7 +755,7 @@ static void handle_rx(struct vhost_net *net)
 	struct iov_iter fixup;
 	__virtio16 num_buffers;
 
-	mutex_lock(&vq->mutex);
+	mutex_lock_nested(&vq->mutex, 0);
 	sock = vq->private_data;
 	if (!sock)
 		goto out;
-- 
2.14.3


From d7218b1d176301824a8c24d3bf95365e04dc5dd2 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Tue, 27 Mar 2018 14:41:19 +0300
Subject: [PATCH 42/42] net/mlx4_core: Fix memory leak while delete slave's
 resources

[ Upstream commit 461d5f1b59490ce0096dfda45e10038c122a7892 ]

mlx4_delete_all_resources_for_slave in resource tracker should free all
memory allocated for a slave.
While releasing memory of fs_rule, it misses releasing memory of
fs_rule->mirr_mbox.

Fixes: 78efed275117 ('net/mlx4_core: Support mirroring VF DMFS rules on both ports')
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/resource_tracker.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index fabb53379727..a069fcc823c3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -5089,6 +5089,7 @@ static void rem_slave_fs_rule(struct mlx4_dev *dev, int slave)
 						 &tracker->res_tree[RES_FS_RULE]);
 					list_del(&fs_rule->com.list);
 					spin_unlock_irq(mlx4_tlock(dev));
+					kfree(fs_rule->mirr_mbox);
 					kfree(fs_rule);
 					state = 0;
 					break;
-- 
2.14.3


[-- Attachment #3: net_415.mbox --]
[-- Type: Application/Octet-Stream, Size: 127546 bytes --]

From 550fa2ab7c858857ba1dd37a3a9aea3f194cd00e Mon Sep 17 00:00:00 2001
From: Miguel Fadon Perlines <mfadon@teldat.com>
Date: Thu, 5 Apr 2018 10:25:38 +0200
Subject: [PATCH 01/48] arp: fix arp_filter on l3slave devices

[ Upstream commit 58b35f27689b5eb514fc293c332966c226b1b6e4 ]

arp_filter performs an ip_route_output search for arp source address and
checks if output device is the same where the arp request was received,
if it is not, the arp request is not answered.

This route lookup is always done on main route table so l3slave devices
never find the proper route and arp is not answered.

Passing l3mdev_master_ifindex_rcu(dev) return value as oif fixes the
lookup for l3slave devices while maintaining same behavior for non
l3slave devices as this function returns 0 in that case.

Fixes: 613d09b30f8b ("net: Use VRF device index for lookups on TX")
Signed-off-by: Miguel Fadon Perlines <mfadon@teldat.com>
Acked-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/arp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 6c231b43974d..e981e05594c5 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -437,7 +437,7 @@ static int arp_filter(__be32 sip, __be32 tip, struct net_device *dev)
 	/*unsigned long now; */
 	struct net *net = dev_net(dev);
 
-	rt = ip_route_output(net, sip, tip, 0, 0);
+	rt = ip_route_output(net, sip, tip, 0, l3mdev_master_ifindex_rcu(dev));
 	if (IS_ERR(rt))
 		return 1;
 	if (rt->dst.dev != dev) {
-- 
2.14.3


From 50fc6498665601c31f2f12be057847afaaaadac6 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 23 Mar 2018 14:47:30 +0100
Subject: [PATCH 02/48] ipv6: the entire IPv6 header chain must fit the first
 fragment

[ Upstream commit 10b8a3de603df7b96004179b1b33b1708c76d144 ]

While building ipv6 datagram we currently allow arbitrary large
extheaders, even beyond pmtu size. The syzbot has found a way
to exploit the above to trigger the following splat:

kernel BUG at ./include/linux/skbuff.h:2073!
invalid opcode: 0000 [#1] SMP KASAN
Dumping ftrace buffer:
    (ftrace buffer empty)
Modules linked in:
CPU: 1 PID: 4230 Comm: syzkaller672661 Not tainted 4.16.0-rc2+ #326
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
RIP: 0010:__skb_pull include/linux/skbuff.h:2073 [inline]
RIP: 0010:__ip6_make_skb+0x1ac8/0x2190 net/ipv6/ip6_output.c:1636
RSP: 0018:ffff8801bc18f0f0 EFLAGS: 00010293
RAX: ffff8801b17400c0 RBX: 0000000000000738 RCX: ffffffff84f01828
RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff8801b415ac18
RBP: ffff8801bc18f360 R08: ffff8801b4576844 R09: 0000000000000000
R10: ffff8801bc18f380 R11: ffffed00367aee4e R12: 00000000000000d6
R13: ffff8801b415a740 R14: dffffc0000000000 R15: ffff8801b45767c0
FS:  0000000001535880(0000) GS:ffff8801db300000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000000002000b000 CR3: 00000001b4123001 CR4: 00000000001606e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
  ip6_finish_skb include/net/ipv6.h:969 [inline]
  udp_v6_push_pending_frames+0x269/0x3b0 net/ipv6/udp.c:1073
  udpv6_sendmsg+0x2a96/0x3400 net/ipv6/udp.c:1343
  inet_sendmsg+0x11f/0x5e0 net/ipv4/af_inet.c:764
  sock_sendmsg_nosec net/socket.c:630 [inline]
  sock_sendmsg+0xca/0x110 net/socket.c:640
  ___sys_sendmsg+0x320/0x8b0 net/socket.c:2046
  __sys_sendmmsg+0x1ee/0x620 net/socket.c:2136
  SYSC_sendmmsg net/socket.c:2167 [inline]
  SyS_sendmmsg+0x35/0x60 net/socket.c:2162
  do_syscall_64+0x280/0x940 arch/x86/entry/common.c:287
  entry_SYSCALL_64_after_hwframe+0x42/0xb7
RIP: 0033:0x4404c9
RSP: 002b:00007ffdce35f948 EFLAGS: 00000217 ORIG_RAX: 0000000000000133
RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 00000000004404c9
RDX: 0000000000000003 RSI: 0000000020001f00 RDI: 0000000000000003
RBP: 00000000006cb018 R08: 00000000004002c8 R09: 00000000004002c8
R10: 0000000020000080 R11: 0000000000000217 R12: 0000000000401df0
R13: 0000000000401e80 R14: 0000000000000000 R15: 0000000000000000
Code: ff e8 1d 5e b9 fc e9 15 e9 ff ff e8 13 5e b9 fc e9 44 e8 ff ff e8 29
5e b9 fc e9 c0 e6 ff ff e8 3f f3 80 fc 0f 0b e8 38 f3 80 fc <0f> 0b 49 8d
87 80 00 00 00 4d 8d 87 84 00 00 00 48 89 85 20 fe
RIP: __skb_pull include/linux/skbuff.h:2073 [inline] RSP: ffff8801bc18f0f0
RIP: __ip6_make_skb+0x1ac8/0x2190 net/ipv6/ip6_output.c:1636 RSP:
ffff8801bc18f0f0

As stated by RFC 7112 section 5:

   When a host fragments an IPv6 datagram, it MUST include the entire
   IPv6 Header Chain in the First Fragment.

So this patch addresses the issue dropping datagrams with excessive
extheader length. It also updates the error path to report to the
calling socket nonnegative pmtu values.

The issue apparently predates git history.

v1 -> v2: cleanup error path, as per Eric's suggestion

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzbot+91e6f9932ff122fa4410@syzkaller.appspotmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_output.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 3763dc01e374..ef22ee9f3443 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1237,7 +1237,7 @@ static int __ip6_append_data(struct sock *sk,
 			     const struct sockcm_cookie *sockc)
 {
 	struct sk_buff *skb, *skb_prev = NULL;
-	unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu;
+	unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu, pmtu;
 	int exthdrlen = 0;
 	int dst_exthdrlen = 0;
 	int hh_len;
@@ -1273,6 +1273,12 @@ static int __ip6_append_data(struct sock *sk,
 		      sizeof(struct frag_hdr) : 0) +
 		     rt->rt6i_nfheader_len;
 
+	/* as per RFC 7112 section 5, the entire IPv6 Header Chain must fit
+	 * the first fragment
+	 */
+	if (headersize + transhdrlen > mtu)
+		goto emsgsize;
+
 	if (cork->length + length > mtu - headersize && ipc6->dontfrag &&
 	    (sk->sk_protocol == IPPROTO_UDP ||
 	     sk->sk_protocol == IPPROTO_RAW)) {
@@ -1288,9 +1294,8 @@ static int __ip6_append_data(struct sock *sk,
 
 	if (cork->length + length > maxnonfragsize - headersize) {
 emsgsize:
-		ipv6_local_error(sk, EMSGSIZE, fl6,
-				 mtu - headersize +
-				 sizeof(struct ipv6hdr));
+		pmtu = max_t(int, mtu - headersize + sizeof(struct ipv6hdr), 0);
+		ipv6_local_error(sk, EMSGSIZE, fl6, pmtu);
 		return -EMSGSIZE;
 	}
 
-- 
2.14.3


From 0affc91484176e2142589c820b085d9cc87c19eb Mon Sep 17 00:00:00 2001
From: Raghuram Chary J <raghuramchary.jallipalli@microchip.com>
Date: Tue, 27 Mar 2018 14:51:16 +0530
Subject: [PATCH 03/48] lan78xx: Crash in lan78xx_writ_reg (Workqueue: events
 lan78xx_deferred_multicast_write)

[ Upstream commit 2d2d99ec13f62d5d2cecb6169dfdb6bbe05356d0 ]

Description:
Crash was reported with syzkaller pointing to lan78xx_write_reg routine.

Root-cause:
Proper cleanup of workqueues and init/setup routines was not happening
in failure conditions.

Fix:
Handled the error conditions by cleaning up the queues and init/setup
routines.

Fixes: 55d7de9de6c3 ("Microchip's LAN7800 family USB 2/3 to 10/100/1000 Ethernet device driver")
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Raghuram Chary J <raghuramchary.jallipalli@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/lan78xx.c | 23 +++++++++++++++++++++--
 1 file changed, 21 insertions(+), 2 deletions(-)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index ec56ff29aac4..02048263c1fb 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -2863,8 +2863,7 @@ static int lan78xx_bind(struct lan78xx_net *dev, struct usb_interface *intf)
 	if (ret < 0) {
 		netdev_warn(dev->net,
 			    "lan78xx_setup_irq_domain() failed : %d", ret);
-		kfree(pdata);
-		return ret;
+		goto out1;
 	}
 
 	dev->net->hard_header_len += TX_OVERHEAD;
@@ -2872,14 +2871,32 @@ static int lan78xx_bind(struct lan78xx_net *dev, struct usb_interface *intf)
 
 	/* Init all registers */
 	ret = lan78xx_reset(dev);
+	if (ret) {
+		netdev_warn(dev->net, "Registers INIT FAILED....");
+		goto out2;
+	}
 
 	ret = lan78xx_mdio_init(dev);
+	if (ret) {
+		netdev_warn(dev->net, "MDIO INIT FAILED.....");
+		goto out2;
+	}
 
 	dev->net->flags |= IFF_MULTICAST;
 
 	pdata->wol = WAKE_MAGIC;
 
 	return ret;
+
+out2:
+	lan78xx_remove_irq_domain(dev);
+
+out1:
+	netdev_warn(dev->net, "Bind routine FAILED");
+	cancel_work_sync(&pdata->set_multicast);
+	cancel_work_sync(&pdata->set_vlan);
+	kfree(pdata);
+	return ret;
 }
 
 static void lan78xx_unbind(struct lan78xx_net *dev, struct usb_interface *intf)
@@ -2891,6 +2908,8 @@ static void lan78xx_unbind(struct lan78xx_net *dev, struct usb_interface *intf)
 	lan78xx_remove_mdio(dev);
 
 	if (pdata) {
+		cancel_work_sync(&pdata->set_multicast);
+		cancel_work_sync(&pdata->set_vlan);
 		netif_dbg(dev, ifdown, dev->net, "free pdata");
 		kfree(pdata);
 		pdata = NULL;
-- 
2.14.3


From 001b069f7d25b36460cb6e8c53bc936b5c868247 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sat, 7 Apr 2018 20:37:40 +0200
Subject: [PATCH 04/48] net: dsa: Discard frames from unused ports

[ Upstream commit fc5f33768cca7144f8d793205b229d46740d183b ]

The Marvell switches under some conditions will pass a frame to the
host with the port being the CPU port. Such frames are invalid, and
should be dropped. Not dropping them can result in a crash when
incrementing the receive statistics for an invalid port.

Reported-by: Chris Healy <cphealy@gmail.com>
Fixes: 91da11f870f0 ("net: Distributed Switch Architecture protocol support")
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/dsa_priv.h | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index 7d036696e8c4..65292b9fa01a 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -117,6 +117,7 @@ static inline struct net_device *dsa_master_find_slave(struct net_device *dev,
 	struct dsa_port *cpu_dp = dev->dsa_ptr;
 	struct dsa_switch_tree *dst = cpu_dp->dst;
 	struct dsa_switch *ds;
+	struct dsa_port *slave_port;
 
 	if (device < 0 || device >= DSA_MAX_SWITCHES)
 		return NULL;
@@ -128,7 +129,12 @@ static inline struct net_device *dsa_master_find_slave(struct net_device *dev,
 	if (port < 0 || port >= ds->num_ports)
 		return NULL;
 
-	return ds->ports[port].slave;
+	slave_port = &ds->ports[port];
+
+	if (unlikely(slave_port->type != DSA_PORT_TYPE_USER))
+		return NULL;
+
+	return slave_port->slave;
 }
 
 /* port.c */
-- 
2.14.3


From a184de5def23b189b205f1f4e941cc4d555c4eba Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 26 Mar 2018 08:08:07 -0700
Subject: [PATCH 05/48] net: fix possible out-of-bound read in
 skb_network_protocol()

[ Upstream commit 1dfe82ebd7d8fd43dba9948fdfb31f145014baa0 ]

skb mac header is not necessarily set at the time skb_network_protocol()
is called. Use skb->data instead.

BUG: KASAN: slab-out-of-bounds in skb_network_protocol+0x46b/0x4b0 net/core/dev.c:2739
Read of size 2 at addr ffff8801b3097a0b by task syz-executor5/14242

CPU: 1 PID: 14242 Comm: syz-executor5 Not tainted 4.16.0-rc6+ #280
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x194/0x24d lib/dump_stack.c:53
 print_address_description+0x73/0x250 mm/kasan/report.c:256
 kasan_report_error mm/kasan/report.c:354 [inline]
 kasan_report+0x23c/0x360 mm/kasan/report.c:412
 __asan_report_load_n_noabort+0xf/0x20 mm/kasan/report.c:443
 skb_network_protocol+0x46b/0x4b0 net/core/dev.c:2739
 harmonize_features net/core/dev.c:2924 [inline]
 netif_skb_features+0x509/0x9b0 net/core/dev.c:3011
 validate_xmit_skb+0x81/0xb00 net/core/dev.c:3084
 validate_xmit_skb_list+0xbf/0x120 net/core/dev.c:3142
 packet_direct_xmit+0x117/0x790 net/packet/af_packet.c:256
 packet_snd net/packet/af_packet.c:2944 [inline]
 packet_sendmsg+0x3aed/0x60b0 net/packet/af_packet.c:2969
 sock_sendmsg_nosec net/socket.c:629 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:639
 ___sys_sendmsg+0x767/0x8b0 net/socket.c:2047
 __sys_sendmsg+0xe5/0x210 net/socket.c:2081

Fixes: 19acc327258a ("gso: Handle Trans-Ether-Bridging protocol in skb_network_protocol()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Pravin B Shelar <pshelar@ovn.org>
Reported-by: Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index f3fbd10a0632..1d3a0f0dafc4 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2719,7 +2719,7 @@ __be16 skb_network_protocol(struct sk_buff *skb, int *depth)
 		if (unlikely(!pskb_may_pull(skb, sizeof(struct ethhdr))))
 			return 0;
 
-		eth = (struct ethhdr *)skb_mac_header(skb);
+		eth = (struct ethhdr *)skb->data;
 		type = eth->h_proto;
 	}
 
-- 
2.14.3


From d8edf7114a6814d634c1a5a68662dcfe9c4c87ce Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Thu, 29 Mar 2018 17:44:57 -0700
Subject: [PATCH 06/48] net/ipv6: Fix route leaking between VRFs

[ Upstream commit b6cdbc85234b072340b8923e69f49ec293f905dc ]

Donald reported that IPv6 route leaking between VRFs is not working.
The root cause is the strict argument in the call to rt6_lookup when
validating the nexthop spec.

ip6_route_check_nh validates the gateway and device (if given) of a
route spec. It in turn could call rt6_lookup (e.g., lookup in a given
table did not succeed so it falls back to a full lookup) and if so
sets the strict argument to 1. That means if the egress device is given,
the route lookup needs to return a result with the same device. This
strict requirement does not work with VRFs (IPv4 or IPv6) because the
oif in the flow struct is overridden with the index of the VRF device
to trigger a match on the l3mdev rule and force the lookup to its table.

The right long term solution is to add an l3mdev index to the flow
struct such that the oif is not overridden. That solution will not
backport well, so this patch aims for a simpler solution to relax the
strict argument if the route spec device is an l3mdev slave. As done
in other places, use the FLOWI_FLAG_SKIP_NH_OIF to know that the
RT6_LOOKUP_F_IFACE flag needs to be removed.

Fixes: ca254490c8df ("net: Add VRF support to IPv6 stack")
Reported-by: Donald Sharp <sharpd@cumulusnetworks.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 1f0d94439c77..065518620dc2 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -922,6 +922,9 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net,
 	struct rt6_info *rt, *rt_cache;
 	struct fib6_node *fn;
 
+	if (fl6->flowi6_flags & FLOWI_FLAG_SKIP_NH_OIF)
+		flags &= ~RT6_LOOKUP_F_IFACE;
+
 	rcu_read_lock();
 	fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
 restart:
-- 
2.14.3


From 86f487475f3ab16d5c112014f8bd8684489cfa37 Mon Sep 17 00:00:00 2001
From: Jeff Barnhill <0xeffeff@gmail.com>
Date: Thu, 5 Apr 2018 21:29:47 +0000
Subject: [PATCH 07/48] net/ipv6: Increment OUTxxx counters after netfilter
 hook

[ Upstream commit 71a1c915238c970cd9bdd5bf158b1279d6b6d55b ]

At the end of ip6_forward(), IPSTATS_MIB_OUTFORWDATAGRAMS and
IPSTATS_MIB_OUTOCTETS are incremented immediately before the NF_HOOK call
for NFPROTO_IPV6 / NF_INET_FORWARD.  As a result, these counters get
incremented regardless of whether or not the netfilter hook allows the
packet to continue being processed.  This change increments the counters
in ip6_forward_finish() so that it will not happen if the netfilter hook
chooses to terminate the packet, which is similar to how IPv4 works.

Signed-off-by: Jeff Barnhill <0xeffeff@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_output.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index ef22ee9f3443..1cf7459f1a73 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -367,6 +367,11 @@ static int ip6_forward_proxy_check(struct sk_buff *skb)
 static inline int ip6_forward_finish(struct net *net, struct sock *sk,
 				     struct sk_buff *skb)
 {
+	struct dst_entry *dst = skb_dst(skb);
+
+	__IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS);
+	__IP6_ADD_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTOCTETS, skb->len);
+
 	return dst_output(net, sk, skb);
 }
 
@@ -560,8 +565,6 @@ int ip6_forward(struct sk_buff *skb)
 
 	hdr->hop_limit--;
 
-	__IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS);
-	__IP6_ADD_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTOCTETS, skb->len);
 	return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD,
 		       net, NULL, skb, skb->dev, dst->dev,
 		       ip6_forward_finish);
-- 
2.14.3


From 47bceb7a2773760245603f1bb91219e502f1ffea Mon Sep 17 00:00:00 2001
From: Alexander Potapenko <glider@google.com>
Date: Fri, 23 Mar 2018 13:49:02 +0100
Subject: [PATCH 08/48] netlink: make sure nladdr has correct size in
 netlink_connect()

[ Upstream commit 7880287981b60a6808f39f297bb66936e8bdf57a ]

KMSAN reports use of uninitialized memory in the case when |alen| is
smaller than sizeof(struct sockaddr_nl), and therefore |nladdr| isn't
fully copied from the userspace.

Signed-off-by: Alexander Potapenko <glider@google.com>
Fixes: 1da177e4c3f41524 ("Linux-2.6.12-rc2")
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index ca9c0544c856..1245aa1d6e1c 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1052,6 +1052,9 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr,
 	if (addr->sa_family != AF_NETLINK)
 		return -EINVAL;
 
+	if (alen < sizeof(struct sockaddr_nl))
+		return -EINVAL;
+
 	if ((nladdr->nl_groups || nladdr->nl_pid) &&
 	    !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
 		return -EPERM;
-- 
2.14.3


From 022a95b7d167b6f960c19d4e0d90a6de0f110287 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Thu, 15 Feb 2018 12:41:48 +0200
Subject: [PATCH 09/48] net/mlx5e: Verify coalescing parameters in range

[ Upstream commit b392a2078b5e0094ff38aa0c9d2a31b3f607d4ef ]

Add check of coalescing parameters received through ethtool are within
range of values supported by the HW.
Driver gets the coalescing rx/tx-usecs and rx/tx-frames as set by the
users through ethtool. The ethtool support up to 32 bit value for each.
However, mlx5 modify cq limits the coalescing time parameter to 12 bit
and coalescing frames parameters to 16 bits.
Return out of range error if user tries to set these parameters to
higher values.

Fixes: f62b8bb8f2d3 ('net/mlx5: Extend mlx5_core to support ConnectX-4 Ethernet functionality')
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index ea5fff2c3143..f909d0dbae10 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -492,6 +492,9 @@ static int mlx5e_get_coalesce(struct net_device *netdev,
 	return mlx5e_ethtool_get_coalesce(priv, coal);
 }
 
+#define MLX5E_MAX_COAL_TIME		MLX5_MAX_CQ_PERIOD
+#define MLX5E_MAX_COAL_FRAMES		MLX5_MAX_CQ_COUNT
+
 static void
 mlx5e_set_priv_channels_coalesce(struct mlx5e_priv *priv, struct ethtool_coalesce *coal)
 {
@@ -526,6 +529,20 @@ int mlx5e_ethtool_set_coalesce(struct mlx5e_priv *priv,
 	if (!MLX5_CAP_GEN(mdev, cq_moderation))
 		return -EOPNOTSUPP;
 
+	if (coal->tx_coalesce_usecs > MLX5E_MAX_COAL_TIME ||
+	    coal->rx_coalesce_usecs > MLX5E_MAX_COAL_TIME) {
+		netdev_info(priv->netdev, "%s: maximum coalesce time supported is %lu usecs\n",
+			    __func__, MLX5E_MAX_COAL_TIME);
+		return -ERANGE;
+	}
+
+	if (coal->tx_max_coalesced_frames > MLX5E_MAX_COAL_FRAMES ||
+	    coal->rx_max_coalesced_frames > MLX5E_MAX_COAL_FRAMES) {
+		netdev_info(priv->netdev, "%s: maximum coalesced frames supported is %lu\n",
+			    __func__, MLX5E_MAX_COAL_FRAMES);
+		return -ERANGE;
+	}
+
 	mutex_lock(&priv->state_lock);
 	new_channels.params = priv->channels.params;
 
-- 
2.14.3


From 3f0b247a56e9849d80e91df9e7dd0399b9f4a52c Mon Sep 17 00:00:00 2001
From: Craig Dillabaugh <cdillaba@mojatatu.com>
Date: Mon, 26 Mar 2018 14:58:32 -0400
Subject: [PATCH 10/48] net sched actions: fix dumping which requires several
 messages to user space

[ Upstream commit 734549eb550c0c720bc89e50501f1b1e98cdd841 ]

Fixes a bug in the tcf_dump_walker function that can cause some actions
to not be reported when dumping a large number of actions. This issue
became more aggrevated when cookies feature was added. In particular
this issue is manifest when large cookie values are assigned to the
actions and when enough actions are created that the resulting table
must be dumped in multiple batches.

The number of actions returned in each batch is limited by the total
number of actions and the memory buffer size.  With small cookies
the numeric limit is reached before the buffer size limit, which avoids
the code path triggering this bug. When large cookies are used buffer
fills before the numeric limit, and the erroneous code path is hit.

For example after creating 32 csum actions with the cookie
aaaabbbbccccdddd

$ tc actions ls action csum
total acts 26

    action order 0: csum (tcp) action continue
    index 1 ref 1 bind 0
    cookie aaaabbbbccccdddd

    .....

    action order 25: csum (tcp) action continue
    index 26 ref 1 bind 0
    cookie aaaabbbbccccdddd
total acts 6

    action order 0: csum (tcp) action continue
    index 28 ref 1 bind 0
    cookie aaaabbbbccccdddd

    ......

    action order 5: csum (tcp) action continue
    index 32 ref 1 bind 0
    cookie aaaabbbbccccdddd

Note that the action with index 27 is omitted from the report.

Fixes: 4b3550ef530c ("[NET_SCHED]: Use nla_nest_start/nla_nest_end")"
Signed-off-by: Craig Dillabaugh <cdillaba@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_api.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 4d33a50a8a6d..e3386f1f485c 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -135,8 +135,10 @@ static int tcf_dump_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb,
 			continue;
 
 		nest = nla_nest_start(skb, n_i);
-		if (!nest)
+		if (!nest) {
+			index--;
 			goto nla_put_failure;
+		}
 		err = tcf_action_dump_1(skb, p, 0, 0);
 		if (err < 0) {
 			index--;
-- 
2.14.3


From 5a29dbf473c5a5ca4d945474b0153545c8d2a313 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Fri, 6 Apr 2018 01:19:37 +0200
Subject: [PATCH 11/48] net/sched: fix NULL dereference in the error path of
 tcf_bpf_init()

[ Upstream commit 3239534a79ee6f20cffd974173a1e62e0730e8ac ]

when tcf_bpf_init_from_ops() fails (e.g. because of program having invalid
number of instructions), tcf_bpf_cfg_cleanup() calls bpf_prog_put(NULL) or
bpf_prog_destroy(NULL). Unless CONFIG_BPF_SYSCALL is unset, this causes
the following error:

 BUG: unable to handle kernel NULL pointer dereference at 0000000000000020
 PGD 800000007345a067 P4D 800000007345a067 PUD 340e1067 PMD 0
 Oops: 0000 [#1] SMP PTI
 Modules linked in: act_bpf(E) ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 mbcache jbd2 crct10dif_pclmul crc32_pclmul ghash_clmulni_intel snd_hda_codec_generic pcbc snd_hda_intel snd_hda_codec snd_hda_core snd_hwdep snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd glue_helper cryptd joydev snd_timer snd virtio_balloon pcspkr soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm virtio_blk drm virtio_net virtio_console i2c_core crc32c_intel serio_raw virtio_pci ata_piix libata virtio_ring floppy virtio dm_mirror dm_region_hash dm_log dm_mod [last unloaded: act_bpf]
 CPU: 3 PID: 5654 Comm: tc Tainted: G            E    4.16.0.bpf_test+ #408
 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
 RIP: 0010:__bpf_prog_put+0xc/0xc0
 RSP: 0018:ffff9594003ef728 EFLAGS: 00010202
 RAX: 0000000000000000 RBX: ffff9594003ef758 RCX: 0000000000000024
 RDX: 0000000000000000 RSI: 0000000000000001 RDI: 0000000000000000
 RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000044
 R10: 0000000000000220 R11: ffff8a7ab9f17131 R12: 0000000000000000
 R13: ffff8a7ab7c3c8e0 R14: 0000000000000001 R15: ffff8a7ab88f1054
 FS:  00007fcb2f17c740(0000) GS:ffff8a7abfd80000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000000020 CR3: 000000007c888006 CR4: 00000000001606e0
 Call Trace:
  tcf_bpf_cfg_cleanup+0x2f/0x40 [act_bpf]
  tcf_bpf_cleanup+0x4c/0x70 [act_bpf]
  __tcf_idr_release+0x79/0x140
  tcf_bpf_init+0x125/0x330 [act_bpf]
  tcf_action_init_1+0x2cc/0x430
  ? get_page_from_freelist+0x3f0/0x11b0
  tcf_action_init+0xd3/0x1b0
  tc_ctl_action+0x18b/0x240
  rtnetlink_rcv_msg+0x29c/0x310
  ? _cond_resched+0x15/0x30
  ? __kmalloc_node_track_caller+0x1b9/0x270
  ? rtnl_calcit.isra.29+0x100/0x100
  netlink_rcv_skb+0xd2/0x110
  netlink_unicast+0x17c/0x230
  netlink_sendmsg+0x2cd/0x3c0
  sock_sendmsg+0x30/0x40
  ___sys_sendmsg+0x27a/0x290
  ? mem_cgroup_commit_charge+0x80/0x130
  ? page_add_new_anon_rmap+0x73/0xc0
  ? do_anonymous_page+0x2a2/0x560
  ? __handle_mm_fault+0xc75/0xe20
  __sys_sendmsg+0x58/0xa0
  do_syscall_64+0x6e/0x1a0
  entry_SYSCALL_64_after_hwframe+0x3d/0xa2
 RIP: 0033:0x7fcb2e58eba0
 RSP: 002b:00007ffc93c496c8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
 RAX: ffffffffffffffda RBX: 00007ffc93c497f0 RCX: 00007fcb2e58eba0
 RDX: 0000000000000000 RSI: 00007ffc93c49740 RDI: 0000000000000003
 RBP: 000000005ac6a646 R08: 0000000000000002 R09: 0000000000000000
 R10: 00007ffc93c49120 R11: 0000000000000246 R12: 0000000000000000
 R13: 00007ffc93c49804 R14: 0000000000000001 R15: 000000000066afa0
 Code: 5f 00 48 8b 43 20 48 c7 c7 70 2f 7c b8 c7 40 10 00 00 00 00 5b e9 a5 8b 61 00 0f 1f 44 00 00 0f 1f 44 00 00 41 54 55 48 89 fd 53 <48> 8b 47 20 f0 ff 08 74 05 5b 5d 41 5c c3 41 89 f4 0f 1f 44 00
 RIP: __bpf_prog_put+0xc/0xc0 RSP: ffff9594003ef728
 CR2: 0000000000000020

Fix it in tcf_bpf_cfg_cleanup(), ensuring that bpf_prog_{put,destroy}(f)
is called only when f is not NULL.

Fixes: bbc09e7842a5 ("net/sched: fix idr leak on the error path of tcf_bpf_init()")
Reported-by: Lucas Bates <lucasb@mojatatu.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_bpf.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 5ef8ce8c83d4..502159bdded3 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -248,10 +248,14 @@ static int tcf_bpf_init_from_efd(struct nlattr **tb, struct tcf_bpf_cfg *cfg)
 
 static void tcf_bpf_cfg_cleanup(const struct tcf_bpf_cfg *cfg)
 {
-	if (cfg->is_ebpf)
-		bpf_prog_put(cfg->filter);
-	else
-		bpf_prog_destroy(cfg->filter);
+	struct bpf_prog *filter = cfg->filter;
+
+	if (filter) {
+		if (cfg->is_ebpf)
+			bpf_prog_put(filter);
+		else
+			bpf_prog_destroy(filter);
+	}
 
 	kfree(cfg->bpf_ops);
 	kfree(cfg->bpf_name);
-- 
2.14.3


From dbbb4bedd5c7eedffa893cb064b0fc2ebecf4402 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 2 Apr 2018 18:48:37 -0700
Subject: [PATCH 12/48] pptp: remove a buggy dst release in pptp_connect()

[ Upstream commit bfacfb457b36911a10140b8cb3ce76a74883ac5a ]

Once dst has been cached in socket via sk_setup_caps(),
it is illegal to call ip_rt_put() (or dst_release()),
since sk_setup_caps() did not change dst refcount.

We can still dereference it since we hold socket lock.

Caugth by syzbot :

BUG: KASAN: use-after-free in atomic_dec_return include/asm-generic/atomic-instrumented.h:198 [inline]
BUG: KASAN: use-after-free in dst_release+0x27/0xa0 net/core/dst.c:185
Write of size 4 at addr ffff8801c54dc040 by task syz-executor4/20088

CPU: 1 PID: 20088 Comm: syz-executor4 Not tainted 4.16.0+ #376
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x1a7/0x27d lib/dump_stack.c:53
 print_address_description+0x73/0x250 mm/kasan/report.c:256
 kasan_report_error mm/kasan/report.c:354 [inline]
 kasan_report+0x23c/0x360 mm/kasan/report.c:412
 check_memory_region_inline mm/kasan/kasan.c:260 [inline]
 check_memory_region+0x137/0x190 mm/kasan/kasan.c:267
 kasan_check_write+0x14/0x20 mm/kasan/kasan.c:278
 atomic_dec_return include/asm-generic/atomic-instrumented.h:198 [inline]
 dst_release+0x27/0xa0 net/core/dst.c:185
 sk_dst_set include/net/sock.h:1812 [inline]
 sk_dst_reset include/net/sock.h:1824 [inline]
 sock_setbindtodevice net/core/sock.c:610 [inline]
 sock_setsockopt+0x431/0x1b20 net/core/sock.c:707
 SYSC_setsockopt net/socket.c:1845 [inline]
 SyS_setsockopt+0x2ff/0x360 net/socket.c:1828
 do_syscall_64+0x281/0x940 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x42/0xb7
RIP: 0033:0x4552d9
RSP: 002b:00007f4878126c68 EFLAGS: 00000246 ORIG_RAX: 0000000000000036
RAX: ffffffffffffffda RBX: 00007f48781276d4 RCX: 00000000004552d9
RDX: 0000000000000019 RSI: 0000000000000001 RDI: 0000000000000013
RBP: 000000000072bea0 R08: 0000000000000010 R09: 0000000000000000
R10: 00000000200010c0 R11: 0000000000000246 R12: 00000000ffffffff
R13: 0000000000000526 R14: 00000000006fac30 R15: 0000000000000000

Allocated by task 20088:
 save_stack+0x43/0xd0 mm/kasan/kasan.c:447
 set_track mm/kasan/kasan.c:459 [inline]
 kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:552
 kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:489
 kmem_cache_alloc+0x12e/0x760 mm/slab.c:3542
 dst_alloc+0x11f/0x1a0 net/core/dst.c:104
 rt_dst_alloc+0xe9/0x540 net/ipv4/route.c:1520
 __mkroute_output net/ipv4/route.c:2265 [inline]
 ip_route_output_key_hash_rcu+0xa49/0x2c60 net/ipv4/route.c:2493
 ip_route_output_key_hash+0x20b/0x370 net/ipv4/route.c:2322
 __ip_route_output_key include/net/route.h:126 [inline]
 ip_route_output_flow+0x26/0xa0 net/ipv4/route.c:2577
 ip_route_output_ports include/net/route.h:163 [inline]
 pptp_connect+0xa84/0x1170 drivers/net/ppp/pptp.c:453
 SYSC_connect+0x213/0x4a0 net/socket.c:1639
 SyS_connect+0x24/0x30 net/socket.c:1620
 do_syscall_64+0x281/0x940 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x42/0xb7

Freed by task 20082:
 save_stack+0x43/0xd0 mm/kasan/kasan.c:447
 set_track mm/kasan/kasan.c:459 [inline]
 __kasan_slab_free+0x11a/0x170 mm/kasan/kasan.c:520
 kasan_slab_free+0xe/0x10 mm/kasan/kasan.c:527
 __cache_free mm/slab.c:3486 [inline]
 kmem_cache_free+0x83/0x2a0 mm/slab.c:3744
 dst_destroy+0x266/0x380 net/core/dst.c:140
 dst_destroy_rcu+0x16/0x20 net/core/dst.c:153
 __rcu_reclaim kernel/rcu/rcu.h:178 [inline]
 rcu_do_batch kernel/rcu/tree.c:2675 [inline]
 invoke_rcu_callbacks kernel/rcu/tree.c:2930 [inline]
 __rcu_process_callbacks kernel/rcu/tree.c:2897 [inline]
 rcu_process_callbacks+0xd6c/0x17b0 kernel/rcu/tree.c:2914
 __do_softirq+0x2d7/0xb85 kernel/softirq.c:285

The buggy address belongs to the object at ffff8801c54dc000
 which belongs to the cache ip_dst_cache of size 168
The buggy address is located 64 bytes inside of
 168-byte region [ffff8801c54dc000, ffff8801c54dc0a8)
The buggy address belongs to the page:
page:ffffea0007153700 count:1 mapcount:0 mapping:ffff8801c54dc000 index:0x0
flags: 0x2fffc0000000100(slab)
raw: 02fffc0000000100 ffff8801c54dc000 0000000000000000 0000000100000010
raw: ffffea0006b34b20 ffffea0006b6c1e0 ffff8801d674a1c0 0000000000000000
page dumped because: kasan: bad access detected

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pptp.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index 6dde9a0cfe76..9b70a3af678e 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -464,7 +464,6 @@ static int pptp_connect(struct socket *sock, struct sockaddr *uservaddr,
 	po->chan.mtu = dst_mtu(&rt->dst);
 	if (!po->chan.mtu)
 		po->chan.mtu = PPP_MRU;
-	ip_rt_put(rt);
 	po->chan.mtu -= PPTP_HEADER_OVERHEAD;
 
 	po->chan.hdrlen = 2 + sizeof(struct pptp_gre_header);
-- 
2.14.3


From fb45de51d0ce9ac20c1937159589d942f190f29d Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 26 Mar 2018 19:19:30 +0200
Subject: [PATCH 13/48] r8169: fix setting driver_data after register_netdev

[ Upstream commit 19c9ea363a244f85f90a424f9936e6d56449e33c ]

pci_set_drvdata() is called only after registering the net_device,
therefore we could run into a NPE if one of the functions using
driver_data is called before it's set.

Fix this by calling pci_set_drvdata() before registering the
net_device.

This fix is a candidate for stable. As far as I can see the
bug has been there in kernel version 3.2 already, therefore
I can't provide a reference which commit is fixed by it.

The fix may need small adjustments per kernel version because
due to other changes the label which is jumped to if
register_netdev() fails has changed over time.

Reported-by: David Miller <davem@davemloft.net>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index dd713dff8d22..3a0c450552d6 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -8699,12 +8699,12 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_out_msi_5;
 	}
 
+	pci_set_drvdata(pdev, dev);
+
 	rc = register_netdev(dev);
 	if (rc < 0)
 		goto err_out_cnt_6;
 
-	pci_set_drvdata(pdev, dev);
-
 	netif_info(tp, probe, dev, "%s at 0x%p, %pM, XID %08x IRQ %d\n",
 		   rtl_chip_infos[chipset].name, ioaddr, dev->dev_addr,
 		   (u32)(RTL_R32(TxConfig) & 0x9cf0f8ff), pdev->irq);
-- 
2.14.3


From c1251f05205ea93950f790de3b8f6ea4eb2a5d16 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 7 Apr 2018 17:15:22 -0700
Subject: [PATCH 14/48] sctp: do not leak kernel memory to user space

[ Upstream commit 6780db244d6b1537d139dea0ec8aad10cf9e4adb ]

syzbot produced a nice report [1]

Issue here is that a recvmmsg() managed to leak 8 bytes of kernel memory
to user space, because sin_zero (padding field) was not properly cleared.

[1]
BUG: KMSAN: uninit-value in copy_to_user include/linux/uaccess.h:184 [inline]
BUG: KMSAN: uninit-value in move_addr_to_user+0x32e/0x530 net/socket.c:227
CPU: 1 PID: 3586 Comm: syzkaller481044 Not tainted 4.16.0+ #82
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x185/0x1d0 lib/dump_stack.c:53
 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067
 kmsan_internal_check_memory+0x164/0x1d0 mm/kmsan/kmsan.c:1176
 kmsan_copy_to_user+0x69/0x160 mm/kmsan/kmsan.c:1199
 copy_to_user include/linux/uaccess.h:184 [inline]
 move_addr_to_user+0x32e/0x530 net/socket.c:227
 ___sys_recvmsg+0x4e2/0x810 net/socket.c:2211
 __sys_recvmmsg+0x54e/0xdb0 net/socket.c:2313
 SYSC_recvmmsg+0x29b/0x3e0 net/socket.c:2394
 SyS_recvmmsg+0x76/0xa0 net/socket.c:2378
 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x3d/0xa2
RIP: 0033:0x4401c9
RSP: 002b:00007ffc56f73098 EFLAGS: 00000217 ORIG_RAX: 000000000000012b
RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 00000000004401c9
RDX: 0000000000000001 RSI: 0000000020003ac0 RDI: 0000000000000003
RBP: 00000000006ca018 R08: 0000000020003bc0 R09: 0000000000000010
R10: 0000000000000000 R11: 0000000000000217 R12: 0000000000401af0
R13: 0000000000401b80 R14: 0000000000000000 R15: 0000000000000000

Local variable description: ----addr@___sys_recvmsg
Variable was created at:
 ___sys_recvmsg+0xd5/0x810 net/socket.c:2172
 __sys_recvmmsg+0x54e/0xdb0 net/socket.c:2313

Bytes 8-15 of 16 are uninitialized

==================================================================
Kernel panic - not syncing: panic_on_warn set ...

CPU: 1 PID: 3586 Comm: syzkaller481044 Tainted: G    B            4.16.0+ #82
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x185/0x1d0 lib/dump_stack.c:53
 panic+0x39d/0x940 kernel/panic.c:183
 kmsan_report+0x238/0x240 mm/kmsan/kmsan.c:1083
 kmsan_internal_check_memory+0x164/0x1d0 mm/kmsan/kmsan.c:1176
 kmsan_copy_to_user+0x69/0x160 mm/kmsan/kmsan.c:1199
 copy_to_user include/linux/uaccess.h:184 [inline]
 move_addr_to_user+0x32e/0x530 net/socket.c:227
 ___sys_recvmsg+0x4e2/0x810 net/socket.c:2211
 __sys_recvmmsg+0x54e/0xdb0 net/socket.c:2313
 SYSC_recvmmsg+0x29b/0x3e0 net/socket.c:2394
 SyS_recvmmsg+0x76/0xa0 net/socket.c:2378
 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x3d/0xa2

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc:	Vlad Yasevich <vyasevich@gmail.com>
Cc:	Neil Horman <nhorman@tuxdriver.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ipv6.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index e35d4f73d2df..f6d3d0c1e133 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -728,8 +728,10 @@ static int sctp_v6_addr_to_user(struct sctp_sock *sp, union sctp_addr *addr)
 			sctp_v6_map_v4(addr);
 	}
 
-	if (addr->sa.sa_family == AF_INET)
+	if (addr->sa.sa_family == AF_INET) {
+		memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
 		return sizeof(struct sockaddr_in);
+	}
 	return sizeof(struct sockaddr_in6);
 }
 
-- 
2.14.3


From ea6707f7948d2f50398e539ca06b64d817f6814c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 8 Apr 2018 07:52:08 -0700
Subject: [PATCH 15/48] sctp: sctp_sockaddr_af must check minimal addr length
 for AF_INET6

[ Upstream commit 81e98370293afcb58340ce8bd71af7b97f925c26 ]

Check must happen before call to ipv6_addr_v4mapped()

syzbot report was :

BUG: KMSAN: uninit-value in sctp_sockaddr_af net/sctp/socket.c:359 [inline]
BUG: KMSAN: uninit-value in sctp_do_bind+0x60f/0xdc0 net/sctp/socket.c:384
CPU: 0 PID: 3576 Comm: syzkaller968804 Not tainted 4.16.0+ #82
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x185/0x1d0 lib/dump_stack.c:53
 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067
 __msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:676
 sctp_sockaddr_af net/sctp/socket.c:359 [inline]
 sctp_do_bind+0x60f/0xdc0 net/sctp/socket.c:384
 sctp_bind+0x149/0x190 net/sctp/socket.c:332
 inet6_bind+0x1fd/0x1820 net/ipv6/af_inet6.c:293
 SYSC_bind+0x3f2/0x4b0 net/socket.c:1474
 SyS_bind+0x54/0x80 net/socket.c:1460
 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x3d/0xa2
RIP: 0033:0x43fd49
RSP: 002b:00007ffe99df3d28 EFLAGS: 00000213 ORIG_RAX: 0000000000000031
RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 000000000043fd49
RDX: 0000000000000010 RSI: 0000000020000000 RDI: 0000000000000003
RBP: 00000000006ca018 R08: 00000000004002c8 R09: 00000000004002c8
R10: 00000000004002c8 R11: 0000000000000213 R12: 0000000000401670
R13: 0000000000401700 R14: 0000000000000000 R15: 0000000000000000

Local variable description: ----address@SYSC_bind
Variable was created at:
 SYSC_bind+0x6f/0x4b0 net/socket.c:1461
 SyS_bind+0x54/0x80 net/socket.c:1460

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Vlad Yasevich <vyasevich@gmail.com>
Cc: Neil Horman <nhorman@tuxdriver.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 039fcb618c34..5e6ff7ac07d1 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -338,11 +338,14 @@ static struct sctp_af *sctp_sockaddr_af(struct sctp_sock *opt,
 	if (!opt->pf->af_supported(addr->sa.sa_family, opt))
 		return NULL;
 
-	/* V4 mapped address are really of AF_INET family */
-	if (addr->sa.sa_family == AF_INET6 &&
-	    ipv6_addr_v4mapped(&addr->v6.sin6_addr) &&
-	    !opt->pf->af_supported(AF_INET, opt))
-		return NULL;
+	if (addr->sa.sa_family == AF_INET6) {
+		if (len < SIN6_LEN_RFC2133)
+			return NULL;
+		/* V4 mapped address are really of AF_INET family */
+		if (ipv6_addr_v4mapped(&addr->v6.sin6_addr) &&
+		    !opt->pf->af_supported(AF_INET, opt))
+			return NULL;
+	}
 
 	/* If we get this far, af is valid. */
 	af = sctp_get_af_specific(addr->sa.sa_family);
-- 
2.14.3


From 26b74ff5be765a33bb17c5f7ba65b7d71ccf002c Mon Sep 17 00:00:00 2001
From: Kai-Heng Feng <kai.heng.feng@canonical.com>
Date: Sat, 31 Mar 2018 23:42:03 +0800
Subject: [PATCH 16/48] sky2: Increase D3 delay to sky2 stops working after
 suspend

[ Upstream commit afb133637071be6deeb8b3d0e55593ffbf63c527 ]

The sky2 ethernet stops working after system resume from suspend:
[ 582.852065] sky2 0000:04:00.0: Refused to change power state, currently in D3

The current 150ms delay is not enough, change it to 200ms can solve the
issue.

BugLink: https://bugs.launchpad.net/bugs/1758507
Cc: Stable <stable@vger.kernel.org>
Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/sky2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index 9efe1771423c..523e1108c9df 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -5087,7 +5087,7 @@ static int sky2_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	INIT_WORK(&hw->restart_work, sky2_restart);
 
 	pci_set_drvdata(pdev, hw);
-	pdev->d3_delay = 150;
+	pdev->d3_delay = 200;
 
 	return 0;
 
-- 
2.14.3


From 66b98386e017323595fe9c7308ccaef14a7fe7b9 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Tue, 27 Mar 2018 20:50:52 +0800
Subject: [PATCH 17/48] vhost: correctly remove wait queue during poll failure

[ Upstream commit dc6455a71c7fc5117977e197f67f71b49f27baba ]

We tried to remove vq poll from wait queue, but do not check whether
or not it was in a list before. This will lead double free. Fixing
this by switching to use vhost_poll_stop() which zeros poll->wqh after
removing poll from waitqueue to make sure it won't be freed twice.

Cc: Darren Kenny <darren.kenny@oracle.com>
Reported-by: syzbot+c0272972b01b872e604a@syzkaller.appspotmail.com
Fixes: 2b8b328b61c79 ("vhost_net: handle polling errors when setting backend")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Darren Kenny <darren.kenny@oracle.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/vhost.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 5727b186b3ca..f42683578dca 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -213,8 +213,7 @@ int vhost_poll_start(struct vhost_poll *poll, struct file *file)
 	if (mask)
 		vhost_poll_wakeup(&poll->wait, 0, 0, (void *)mask);
 	if (mask & POLLERR) {
-		if (poll->wqh)
-			remove_wait_queue(poll->wqh, &poll->wait);
+		vhost_poll_stop(poll);
 		ret = -EINVAL;
 	}
 
-- 
2.14.3


From e0bdad35e95c7259eb48fa2e620cfb8c4757052a Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Fri, 30 Mar 2018 09:44:00 +0800
Subject: [PATCH 18/48] vlan: also check phy_driver ts_info for vlan's real
 device

[ Upstream commit ec1d8ccb07deaf30fd0508af6755364ac47dc08d ]

Just like function ethtool_get_ts_info(), we should also consider the
phy_driver ts_info call back. For example, driver dp83640.

Fixes: 37dd9255b2f6 ("vlan: Pass ethtool get_ts_info queries to real device.")
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/8021q/vlan_dev.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index f7e83f6d2e64..236452ebbd9e 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -29,6 +29,7 @@
 #include <linux/net_tstamp.h>
 #include <linux/etherdevice.h>
 #include <linux/ethtool.h>
+#include <linux/phy.h>
 #include <net/arp.h>
 #include <net/switchdev.h>
 
@@ -665,8 +666,11 @@ static int vlan_ethtool_get_ts_info(struct net_device *dev,
 {
 	const struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
 	const struct ethtool_ops *ops = vlan->real_dev->ethtool_ops;
+	struct phy_device *phydev = vlan->real_dev->phydev;
 
-	if (ops->get_ts_info) {
+	if (phydev && phydev->drv && phydev->drv->ts_info) {
+		 return phydev->drv->ts_info(phydev, info);
+	} else if (ops->get_ts_info) {
 		return ops->get_ts_info(vlan->real_dev, info);
 	} else {
 		info->so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE |
-- 
2.14.3


From 69b7f1937eeb5009ed1e856bfa6f9d6149347c2a Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Thu, 29 Mar 2018 12:49:52 -0700
Subject: [PATCH 19/48] vrf: Fix use after free and double free in
 vrf_finish_output

[ Upstream commit 82dd0d2a9a76fc8fa2b18d80b987d455728bf83a ]

Miguel reported an skb use after free / double free in vrf_finish_output
when neigh_output returns an error. The vrf driver should return after
the call to neigh_output as it takes over the skb on error path as well.

Patch is a simplified version of Miguel's patch which was written for 4.9,
and updated to top of tree.

Fixes: 8f58336d3f78a ("net: Add ethernet header for pass through VRF device")
Signed-off-by: Miguel Fadon Perlines <mfadon@teldat.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 139c61c8244a..ac40924fe437 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -578,12 +578,13 @@ static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *s
 	if (!IS_ERR(neigh)) {
 		sock_confirm_neigh(skb, neigh);
 		ret = neigh_output(neigh, skb);
+		rcu_read_unlock_bh();
+		return ret;
 	}
 
 	rcu_read_unlock_bh();
 err:
-	if (unlikely(ret < 0))
-		vrf_tx_error(skb->dev, skb);
+	vrf_tx_error(skb->dev, skb);
 	return ret;
 }
 
-- 
2.14.3


From 217ba2a4f770b5296b261533e968bfe73621e7ac Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 26 Mar 2018 01:16:45 +0800
Subject: [PATCH 20/48] bonding: fix the err path for dev hwaddr sync in
 bond_enslave

[ Upstream commit 5c78f6bfae2b10ff70e21d343e64584ea6280c26 ]

vlan_vids_add_by_dev is called right after dev hwaddr sync, so on
the err path it should unsync dev hwaddr. Otherwise, the slave
dev's hwaddr will never be unsync when this err happens.

Fixes: 1ff412ad7714 ("bonding: change the bond's vlan syncing functions with the standard ones")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Reviewed-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Acked-by: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index c669554d70bb..0c299de4f2ef 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1565,7 +1565,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 	if (res) {
 		netdev_err(bond_dev, "Couldn't add bond vlan ids to %s\n",
 			   slave_dev->name);
-		goto err_close;
+		goto err_hwaddr_unsync;
 	}
 
 	prev_slave = bond_last_slave(bond);
@@ -1755,9 +1755,6 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 	netdev_rx_handler_unregister(slave_dev);
 
 err_detach:
-	if (!bond_uses_primary(bond))
-		bond_hw_addr_flush(bond_dev, slave_dev);
-
 	vlan_vids_del_by_dev(slave_dev, bond_dev);
 	if (rcu_access_pointer(bond->primary_slave) == new_slave)
 		RCU_INIT_POINTER(bond->primary_slave, NULL);
@@ -1771,6 +1768,10 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 	synchronize_rcu();
 	slave_disable_netpoll(new_slave);
 
+err_hwaddr_unsync:
+	if (!bond_uses_primary(bond))
+		bond_hw_addr_flush(bond_dev, slave_dev);
+
 err_close:
 	slave_dev->priv_flags &= ~IFF_BONDING;
 	dev_close(slave_dev);
-- 
2.14.3


From 6a59f802191082fa90dc7a35a7afa5f47d6d06b0 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 26 Mar 2018 01:16:46 +0800
Subject: [PATCH 21/48] bonding: move dev_mc_sync after master_upper_dev_link
 in bond_enslave

[ Upstream commit ae42cc62a9f07f1f6979054ed92606b9c30f4a2e ]

Beniamino found a crash when adding vlan as slave of bond which is also
the parent link:

  ip link add bond1 type bond
  ip link set bond1 up
  ip link add link bond1 vlan1 type vlan id 80
  ip link set vlan1 master bond1

The call trace is as below:

  [<ffffffffa850842a>] queued_spin_lock_slowpath+0xb/0xf
  [<ffffffffa8515680>] _raw_spin_lock+0x20/0x30
  [<ffffffffa83f6f07>] dev_mc_sync+0x37/0x80
  [<ffffffffc08687dc>] vlan_dev_set_rx_mode+0x1c/0x30 [8021q]
  [<ffffffffa83efd2a>] __dev_set_rx_mode+0x5a/0xa0
  [<ffffffffa83f7138>] dev_mc_sync_multiple+0x78/0x80
  [<ffffffffc084127c>] bond_enslave+0x67c/0x1190 [bonding]
  [<ffffffffa8401909>] do_setlink+0x9c9/0xe50
  [<ffffffffa8403bf2>] rtnl_newlink+0x522/0x880
  [<ffffffffa8403ff7>] rtnetlink_rcv_msg+0xa7/0x260
  [<ffffffffa8424ecb>] netlink_rcv_skb+0xab/0xc0
  [<ffffffffa83fe498>] rtnetlink_rcv+0x28/0x30
  [<ffffffffa8424850>] netlink_unicast+0x170/0x210
  [<ffffffffa8424bf8>] netlink_sendmsg+0x308/0x420
  [<ffffffffa83cc396>] sock_sendmsg+0xb6/0xf0

This is actually a dead lock caused by sync slave hwaddr from master when
the master is the slave's 'slave'. This dead loop check is actually done
by netdev_master_upper_dev_link. However, Commit 1f718f0f4f97 ("bonding:
populate neighbour's private on enslave") moved it after dev_mc_sync.

This patch is to fix it by moving dev_mc_sync after master_upper_dev_link,
so that this loop check would be earlier than dev_mc_sync. It also moves
if (mode == BOND_MODE_8023AD) into if (!bond_uses_primary) clause as an
improvement.

Note team driver also has this issue, I will fix it in another patch.

Fixes: 1f718f0f4f97 ("bonding: populate neighbour's private on enslave")
Reported-by: Beniamino Galvani <bgalvani@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 73 ++++++++++++++++++++---------------------
 1 file changed, 35 insertions(+), 38 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 0c299de4f2ef..55e198554ec0 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1528,44 +1528,11 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 			goto err_close;
 	}
 
-	/* If the mode uses primary, then the following is handled by
-	 * bond_change_active_slave().
-	 */
-	if (!bond_uses_primary(bond)) {
-		/* set promiscuity level to new slave */
-		if (bond_dev->flags & IFF_PROMISC) {
-			res = dev_set_promiscuity(slave_dev, 1);
-			if (res)
-				goto err_close;
-		}
-
-		/* set allmulti level to new slave */
-		if (bond_dev->flags & IFF_ALLMULTI) {
-			res = dev_set_allmulti(slave_dev, 1);
-			if (res)
-				goto err_close;
-		}
-
-		netif_addr_lock_bh(bond_dev);
-
-		dev_mc_sync_multiple(slave_dev, bond_dev);
-		dev_uc_sync_multiple(slave_dev, bond_dev);
-
-		netif_addr_unlock_bh(bond_dev);
-	}
-
-	if (BOND_MODE(bond) == BOND_MODE_8023AD) {
-		/* add lacpdu mc addr to mc list */
-		u8 lacpdu_multicast[ETH_ALEN] = MULTICAST_LACPDU_ADDR;
-
-		dev_mc_add(slave_dev, lacpdu_multicast);
-	}
-
 	res = vlan_vids_add_by_dev(slave_dev, bond_dev);
 	if (res) {
 		netdev_err(bond_dev, "Couldn't add bond vlan ids to %s\n",
 			   slave_dev->name);
-		goto err_hwaddr_unsync;
+		goto err_close;
 	}
 
 	prev_slave = bond_last_slave(bond);
@@ -1725,6 +1692,37 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 		goto err_upper_unlink;
 	}
 
+	/* If the mode uses primary, then the following is handled by
+	 * bond_change_active_slave().
+	 */
+	if (!bond_uses_primary(bond)) {
+		/* set promiscuity level to new slave */
+		if (bond_dev->flags & IFF_PROMISC) {
+			res = dev_set_promiscuity(slave_dev, 1);
+			if (res)
+				goto err_sysfs_del;
+		}
+
+		/* set allmulti level to new slave */
+		if (bond_dev->flags & IFF_ALLMULTI) {
+			res = dev_set_allmulti(slave_dev, 1);
+			if (res)
+				goto err_sysfs_del;
+		}
+
+		netif_addr_lock_bh(bond_dev);
+		dev_mc_sync_multiple(slave_dev, bond_dev);
+		dev_uc_sync_multiple(slave_dev, bond_dev);
+		netif_addr_unlock_bh(bond_dev);
+
+		if (BOND_MODE(bond) == BOND_MODE_8023AD) {
+			/* add lacpdu mc addr to mc list */
+			u8 lacpdu_multicast[ETH_ALEN] = MULTICAST_LACPDU_ADDR;
+
+			dev_mc_add(slave_dev, lacpdu_multicast);
+		}
+	}
+
 	bond->slave_cnt++;
 	bond_compute_features(bond);
 	bond_set_carrier(bond);
@@ -1748,6 +1746,9 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 	return 0;
 
 /* Undo stages on error */
+err_sysfs_del:
+	bond_sysfs_slave_del(new_slave);
+
 err_upper_unlink:
 	bond_upper_dev_unlink(bond, new_slave);
 
@@ -1768,10 +1769,6 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 	synchronize_rcu();
 	slave_disable_netpoll(new_slave);
 
-err_hwaddr_unsync:
-	if (!bond_uses_primary(bond))
-		bond_hw_addr_flush(bond_dev, slave_dev);
-
 err_close:
 	slave_dev->priv_flags &= ~IFF_BONDING;
 	dev_close(slave_dev);
-- 
2.14.3


From 640c27a81cdd8cb00c2fc8d0ac7e789f33d7c45d Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 26 Mar 2018 01:16:47 +0800
Subject: [PATCH 22/48] bonding: process the err returned by dev_set_allmulti
 properly in bond_enslave

[ Upstream commit 9f5a90c107741b864398f4ac0014711a8c1d8474 ]

When dev_set_promiscuity(1) succeeds but dev_set_allmulti(1) fails,
dev_set_promiscuity(-1) should be done before going to the err path.
Otherwise, dev->promiscuity will leak.

Fixes: 7e1a1ac1fbaa ("bonding: Check return of dev_set_promiscuity/allmulti")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 55e198554ec0..b7b113018853 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1706,8 +1706,11 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 		/* set allmulti level to new slave */
 		if (bond_dev->flags & IFF_ALLMULTI) {
 			res = dev_set_allmulti(slave_dev, 1);
-			if (res)
+			if (res) {
+				if (bond_dev->flags & IFF_PROMISC)
+					dev_set_promiscuity(slave_dev, -1);
 				goto err_sysfs_del;
+			}
 		}
 
 		netif_addr_lock_bh(bond_dev);
-- 
2.14.3


From 111373dbf19a643fe2d54c1902c3646e880d72ca Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 5 Apr 2018 06:39:26 -0700
Subject: [PATCH 23/48] net: fool proof dev_valid_name()

[ Upstream commit a9d48205d0aedda021fc3728972a9e9934c2b9de ]

We want to use dev_valid_name() to validate tunnel names,
so better use strnlen(name, IFNAMSIZ) than strlen(name) to make
sure to not upset KASAN.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 1d3a0f0dafc4..af4d670f5619 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1027,7 +1027,7 @@ bool dev_valid_name(const char *name)
 {
 	if (*name == '\0')
 		return false;
-	if (strlen(name) >= IFNAMSIZ)
+	if (strnlen(name, IFNAMSIZ) == IFNAMSIZ)
 		return false;
 	if (!strcmp(name, ".") || !strcmp(name, ".."))
 		return false;
-- 
2.14.3


From a054cdc2f2b06a363a37c48b9558944a8a018332 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 5 Apr 2018 06:39:27 -0700
Subject: [PATCH 24/48] ip_tunnel: better validate user provided tunnel names

[ Upstream commit 9cb726a212a82c88c98aa9f0037fd04777cd8fe5 ]

Use dev_valid_name() to make sure user does not provide illegal
device name.

syzbot caught the following bug :

BUG: KASAN: stack-out-of-bounds in strlcpy include/linux/string.h:300 [inline]
BUG: KASAN: stack-out-of-bounds in __ip_tunnel_create+0xca/0x6b0 net/ipv4/ip_tunnel.c:257
Write of size 20 at addr ffff8801ac79f810 by task syzkaller268107/4482

CPU: 0 PID: 4482 Comm: syzkaller268107 Not tainted 4.16.0+ #1
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x1b9/0x29f lib/dump_stack.c:53
 print_address_description+0x6c/0x20b mm/kasan/report.c:256
 kasan_report_error mm/kasan/report.c:354 [inline]
 kasan_report.cold.7+0xac/0x2f5 mm/kasan/report.c:412
 check_memory_region_inline mm/kasan/kasan.c:260 [inline]
 check_memory_region+0x13e/0x1b0 mm/kasan/kasan.c:267
 memcpy+0x37/0x50 mm/kasan/kasan.c:303
 strlcpy include/linux/string.h:300 [inline]
 __ip_tunnel_create+0xca/0x6b0 net/ipv4/ip_tunnel.c:257
 ip_tunnel_create net/ipv4/ip_tunnel.c:352 [inline]
 ip_tunnel_ioctl+0x818/0xd40 net/ipv4/ip_tunnel.c:861
 ipip_tunnel_ioctl+0x1c5/0x420 net/ipv4/ipip.c:350
 dev_ifsioc+0x43e/0xb90 net/core/dev_ioctl.c:334
 dev_ioctl+0x69a/0xcc0 net/core/dev_ioctl.c:525
 sock_ioctl+0x47e/0x680 net/socket.c:1015
 vfs_ioctl fs/ioctl.c:46 [inline]
 file_ioctl fs/ioctl.c:500 [inline]
 do_vfs_ioctl+0x1cf/0x1650 fs/ioctl.c:684
 ksys_ioctl+0xa9/0xd0 fs/ioctl.c:701
 SYSC_ioctl fs/ioctl.c:708 [inline]
 SyS_ioctl+0x24/0x30 fs/ioctl.c:706
 do_syscall_64+0x29e/0x9d0 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x42/0xb7

Fixes: c54419321455 ("GRE: Refactor GRE tunneling code.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_tunnel.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 6d21068f9b55..a70a1d6db157 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -253,13 +253,14 @@ static struct net_device *__ip_tunnel_create(struct net *net,
 	struct net_device *dev;
 	char name[IFNAMSIZ];
 
-	if (parms->name[0])
+	err = -E2BIG;
+	if (parms->name[0]) {
+		if (!dev_valid_name(parms->name))
+			goto failed;
 		strlcpy(name, parms->name, IFNAMSIZ);
-	else {
-		if (strlen(ops->kind) > (IFNAMSIZ - 3)) {
-			err = -E2BIG;
+	} else {
+		if (strlen(ops->kind) > (IFNAMSIZ - 3))
 			goto failed;
-		}
 		strlcpy(name, ops->kind, IFNAMSIZ);
 		strncat(name, "%d", 2);
 	}
-- 
2.14.3


From a5e427f76a655b75570b3a10e85ef4f0cd6f8934 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 5 Apr 2018 06:39:28 -0700
Subject: [PATCH 25/48] ipv6: sit: better validate user provided tunnel names

[ Upstream commit b95211e066fc3494b7c115060b2297b4ba21f025 ]

Use dev_valid_name() to make sure user does not provide illegal
device name.

syzbot caught the following bug :

BUG: KASAN: stack-out-of-bounds in strlcpy include/linux/string.h:300 [inline]
BUG: KASAN: stack-out-of-bounds in ipip6_tunnel_locate+0x63b/0xaa0 net/ipv6/sit.c:254
Write of size 33 at addr ffff8801b64076d8 by task syzkaller932654/4453

CPU: 0 PID: 4453 Comm: syzkaller932654 Not tainted 4.16.0+ #1
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x1b9/0x29f lib/dump_stack.c:53
 print_address_description+0x6c/0x20b mm/kasan/report.c:256
 kasan_report_error mm/kasan/report.c:354 [inline]
 kasan_report.cold.7+0xac/0x2f5 mm/kasan/report.c:412
 check_memory_region_inline mm/kasan/kasan.c:260 [inline]
 check_memory_region+0x13e/0x1b0 mm/kasan/kasan.c:267
 memcpy+0x37/0x50 mm/kasan/kasan.c:303
 strlcpy include/linux/string.h:300 [inline]
 ipip6_tunnel_locate+0x63b/0xaa0 net/ipv6/sit.c:254
 ipip6_tunnel_ioctl+0xe71/0x241b net/ipv6/sit.c:1221
 dev_ifsioc+0x43e/0xb90 net/core/dev_ioctl.c:334
 dev_ioctl+0x69a/0xcc0 net/core/dev_ioctl.c:525
 sock_ioctl+0x47e/0x680 net/socket.c:1015
 vfs_ioctl fs/ioctl.c:46 [inline]
 file_ioctl fs/ioctl.c:500 [inline]
 do_vfs_ioctl+0x1cf/0x1650 fs/ioctl.c:684
 ksys_ioctl+0xa9/0xd0 fs/ioctl.c:701
 SYSC_ioctl fs/ioctl.c:708 [inline]
 SyS_ioctl+0x24/0x30 fs/ioctl.c:706
 do_syscall_64+0x29e/0x9d0 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x42/0xb7

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 3a1775a62973..5a0725d7aabc 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -250,11 +250,13 @@ static struct ip_tunnel *ipip6_tunnel_locate(struct net *net,
 	if (!create)
 		goto failed;
 
-	if (parms->name[0])
+	if (parms->name[0]) {
+		if (!dev_valid_name(parms->name))
+			goto failed;
 		strlcpy(name, parms->name, IFNAMSIZ);
-	else
+	} else {
 		strcpy(name, "sit%d");
-
+	}
 	dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN,
 			   ipip6_tunnel_setup);
 	if (!dev)
-- 
2.14.3


From 28ff1f21c92d120a72140393615d990f8a73bb0d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 5 Apr 2018 06:39:29 -0700
Subject: [PATCH 26/48] ip6_gre: better validate user provided tunnel names

[ Upstream commit 5f42df013b8bc1b6511af7a04bf93b014884ae2a ]

Use dev_valid_name() to make sure user does not provide illegal
device name.

syzbot caught the following bug :

BUG: KASAN: stack-out-of-bounds in strlcpy include/linux/string.h:300 [inline]
BUG: KASAN: stack-out-of-bounds in ip6gre_tunnel_locate+0x334/0x860 net/ipv6/ip6_gre.c:339
Write of size 20 at addr ffff8801afb9f7b8 by task syzkaller851048/4466

CPU: 1 PID: 4466 Comm: syzkaller851048 Not tainted 4.16.0+ #1
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x1b9/0x29f lib/dump_stack.c:53
 print_address_description+0x6c/0x20b mm/kasan/report.c:256
 kasan_report_error mm/kasan/report.c:354 [inline]
 kasan_report.cold.7+0xac/0x2f5 mm/kasan/report.c:412
 check_memory_region_inline mm/kasan/kasan.c:260 [inline]
 check_memory_region+0x13e/0x1b0 mm/kasan/kasan.c:267
 memcpy+0x37/0x50 mm/kasan/kasan.c:303
 strlcpy include/linux/string.h:300 [inline]
 ip6gre_tunnel_locate+0x334/0x860 net/ipv6/ip6_gre.c:339
 ip6gre_tunnel_ioctl+0x69d/0x12e0 net/ipv6/ip6_gre.c:1195
 dev_ifsioc+0x43e/0xb90 net/core/dev_ioctl.c:334
 dev_ioctl+0x69a/0xcc0 net/core/dev_ioctl.c:525
 sock_ioctl+0x47e/0x680 net/socket.c:1015
 vfs_ioctl fs/ioctl.c:46 [inline]
 file_ioctl fs/ioctl.c:500 [inline]
 do_vfs_ioctl+0x1cf/0x1650 fs/ioctl.c:684
 ksys_ioctl+0xa9/0xd0 fs/ioctl.c:701
 SYSC_ioctl fs/ioctl.c:708 [inline]
 SyS_ioctl+0x24/0x30 fs/ioctl.c:706
 do_syscall_64+0x29e/0x9d0 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x42/0xb7

Fixes: c12b395a4664 ("gre: Support GRE over IPv6")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 873549228ccb..9f9f38dd6775 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -319,11 +319,13 @@ static struct ip6_tnl *ip6gre_tunnel_locate(struct net *net,
 	if (t || !create)
 		return t;
 
-	if (parms->name[0])
+	if (parms->name[0]) {
+		if (!dev_valid_name(parms->name))
+			return NULL;
 		strlcpy(name, parms->name, IFNAMSIZ);
-	else
+	} else {
 		strcpy(name, "ip6gre%d");
-
+	}
 	dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN,
 			   ip6gre_tunnel_setup);
 	if (!dev)
-- 
2.14.3


From ccaaad89ff0fc56f28dc6f202bbaaf45ba3f305d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 5 Apr 2018 06:39:30 -0700
Subject: [PATCH 27/48] ip6_tunnel: better validate user provided tunnel names

[ Upstream commit db7a65e3ab78e5b1c4b17c0870ebee35a4ee3257 ]

Use valid_name() to make sure user does not provide illegal
device name.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 1ee5584c3555..38e0952e2396 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -297,13 +297,16 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p)
 	struct net_device *dev;
 	struct ip6_tnl *t;
 	char name[IFNAMSIZ];
-	int err = -ENOMEM;
+	int err = -E2BIG;
 
-	if (p->name[0])
+	if (p->name[0]) {
+		if (!dev_valid_name(p->name))
+			goto failed;
 		strlcpy(name, p->name, IFNAMSIZ);
-	else
+	} else {
 		sprintf(name, "ip6tnl%%d");
-
+	}
+	err = -ENOMEM;
 	dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN,
 			   ip6_tnl_dev_setup);
 	if (!dev)
-- 
2.14.3


From c4d74aa069309f7721828bbe821bc3d460d7e1bc Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 5 Apr 2018 06:39:31 -0700
Subject: [PATCH 28/48] vti6: better validate user provided tunnel names

[ Upstream commit 537b361fbcbcc3cd6fe2bb47069fd292b9256d16 ]

Use valid_name() to make sure user does not provide illegal
device name.

Fixes: ed1efb2aefbb ("ipv6: Add support for IPsec virtual tunnel interfaces")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_vti.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 8c184f84f353..15c51686e076 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -212,10 +212,13 @@ static struct ip6_tnl *vti6_tnl_create(struct net *net, struct __ip6_tnl_parm *p
 	char name[IFNAMSIZ];
 	int err;
 
-	if (p->name[0])
+	if (p->name[0]) {
+		if (!dev_valid_name(p->name))
+			goto failed;
 		strlcpy(name, p->name, IFNAMSIZ);
-	else
+	} else {
 		sprintf(name, "ip6_vti%%d");
+	}
 
 	dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN, vti6_dev_setup);
 	if (!dev)
-- 
2.14.3


From 5908d62f55de826f45e1506899de6e36c320312f Mon Sep 17 00:00:00 2001
From: Tal Gilboa <talgi@mellanox.com>
Date: Fri, 30 Mar 2018 15:50:08 -0700
Subject: [PATCH 29/48] net/mlx5e: Set EQE based as default TX interrupt
 moderation mode

[ Upstream commit 48bfc39791b8b4a25f165e711f18b9c1617cefbc ]

The default TX moderation mode was mistakenly set to CQE based. The
intention was to add a control ability in order to improve some specific
use-cases. In general, we prefer to use EQE based moderation as it gives
much better numbers for the common cases.

CQE based causes a degradation in the common case since it resets the
moderation timer on CQE generation. This causes an issue when TSO is
well utilized (large TSO sessions). The timer is set to 16us so traffic
of ~64KB TSO sessions per second would mean timer reset (CQE per TSO
session -> long time between CQEs). In this case we quickly reach the
tcp_limit_output_bytes (256KB by default) and cause a halt in TX traffic.

By setting EQE based moderation we make sure timer would expire after
16us regardless of the packet rate.
This fixes an up to 40% packet rate and up to 23% bandwidth degradtions.

Fixes: 0088cbbc4b66 ("net/mlx5e: Enable CQE based moderation on TX CQ")
Signed-off-by: Tal Gilboa <talgi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 0d352d4cf48c..33faac2b194c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4075,7 +4075,7 @@ void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
 			    struct mlx5e_params *params,
 			    u16 max_channels)
 {
-	u8 cq_period_mode = 0;
+	u8 rx_cq_period_mode;
 	u32 link_speed = 0;
 	u32 pci_bw = 0;
 
@@ -4111,12 +4111,12 @@ void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
 	params->lro_timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT);
 
 	/* CQ moderation params */
-	cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ?
+	rx_cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ?
 			MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
 			MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
 	params->rx_am_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
-	mlx5e_set_rx_cq_mode_params(params, cq_period_mode);
-	mlx5e_set_tx_cq_mode_params(params, cq_period_mode);
+	mlx5e_set_rx_cq_mode_params(params, rx_cq_period_mode);
+	mlx5e_set_tx_cq_mode_params(params, MLX5_CQ_PERIOD_MODE_START_FROM_EQE);
 
 	/* TX inline */
 	params->tx_max_inline = mlx5e_get_max_inline_cap(mdev);
-- 
2.14.3


From f884ed788925c37de4c7615b51cdd85908c7f459 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Fri, 6 Apr 2018 17:19:41 -0700
Subject: [PATCH 30/48] net_sched: fix a missing idr_remove() in
 u32_delete_key()

[ Upstream commit f12c643209db0626f2f54780d86bb93bfa7a9c2d ]

When we delete a u32 key via u32_delete_key(), we forget to
call idr_remove() to remove its handle from IDR.

Fixes: e7614370d6f0 ("net_sched: use idr to allocate u32 filter handles")
Reported-by: Marcin Kabiesz <admin@hostcenter.eu>
Tested-by: Marcin Kabiesz <admin@hostcenter.eu>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_u32.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 425cc341fd41..8d25f38cc1ad 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -478,6 +478,7 @@ static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key)
 				RCU_INIT_POINTER(*kp, key->next);
 
 				tcf_unbind_filter(tp, &key->res);
+				idr_remove(&ht->handle_idr, key->handle);
 				tcf_exts_get_net(&key->exts);
 				call_rcu(&key->rcu, u32_delete_key_freepf_rcu);
 				return 0;
-- 
2.14.3


From 0a9c10adccfed560c26761e352af62b7e9d7cdcd Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Fri, 16 Mar 2018 00:00:53 +0100
Subject: [PATCH 31/48] net/sched: fix NULL dereference in the error path of
 tcf_vlan_init()

[ Upstream commit 1edf8abe04090c4f41a85e42c66638be1ee69156 ]

when the following command

 # tc actions replace action vlan pop index 100

is run for the first time, and tcf_vlan_init() fails allocating struct
tcf_vlan_params, tcf_vlan_cleanup() calls kfree_rcu(NULL, ...). This causes
the following error:

 BUG: unable to handle kernel NULL pointer dereference at 0000000000000018
 IP: __call_rcu+0x23/0x2b0
 PGD 80000000760a2067 P4D 80000000760a2067 PUD 742c1067 PMD 0
 Oops: 0002 [#1] SMP PTI
 Modules linked in: act_vlan(E) ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 snd_hda_codec_generic snd_hda_intel mbcache snd_hda_codec jbd2 snd_hda_core crct10dif_pclmul crc32_pclmul ghash_clmulni_intel pcbc snd_hwdep snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd snd_timer glue_helper snd cryptd joydev soundcore virtio_balloon pcspkr i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm drm virtio_console virtio_blk virtio_net ata_piix crc32c_intel libata virtio_pci i2c_core virtio_ring serio_raw virtio floppy dm_mirror dm_region_hash dm_log dm_mod [last unloaded: act_vlan]
 CPU: 3 PID: 3119 Comm: tc Tainted: G            E    4.16.0-rc4.act_vlan.orig+ #403
 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
 RIP: 0010:__call_rcu+0x23/0x2b0
 RSP: 0018:ffffaac3005fb798 EFLAGS: 00010246
 RAX: ffffffffc0704080 RBX: ffff97f2b4bbe900 RCX: 00000000ffffffff
 RDX: ffffffffabca5f00 RSI: 0000000000000010 RDI: 0000000000000010
 RBP: 0000000000000010 R08: 0000000000000001 R09: 0000000000000044
 R10: 00000000fd003000 R11: ffff97f2faab5b91 R12: 0000000000000000
 R13: ffffffffabca5f00 R14: ffff97f2fb80202c R15: 00000000fffffff4
 FS:  00007f68f75b4740(0000) GS:ffff97f2ffd80000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000000018 CR3: 0000000072b52001 CR4: 00000000001606e0
 Call Trace:
  __tcf_idr_release+0x79/0xf0
  tcf_vlan_init+0x168/0x270 [act_vlan]
  tcf_action_init_1+0x2cc/0x430
  tcf_action_init+0xd3/0x1b0
  tc_ctl_action+0x18b/0x240
  rtnetlink_rcv_msg+0x29c/0x310
  ? _cond_resched+0x15/0x30
  ? __kmalloc_node_track_caller+0x1b9/0x270
  ? rtnl_calcit.isra.28+0x100/0x100
  netlink_rcv_skb+0xd2/0x110
  netlink_unicast+0x17c/0x230
  netlink_sendmsg+0x2cd/0x3c0
  sock_sendmsg+0x30/0x40
  ___sys_sendmsg+0x27a/0x290
  ? filemap_map_pages+0x34a/0x3a0
  ? __handle_mm_fault+0xbfd/0xe20
  __sys_sendmsg+0x51/0x90
  do_syscall_64+0x6e/0x1a0
  entry_SYSCALL_64_after_hwframe+0x3d/0xa2
 RIP: 0033:0x7f68f69c5ba0
 RSP: 002b:00007fffd79c1118 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
 RAX: ffffffffffffffda RBX: 00007fffd79c1240 RCX: 00007f68f69c5ba0
 RDX: 0000000000000000 RSI: 00007fffd79c1190 RDI: 0000000000000003
 RBP: 000000005aaa708e R08: 0000000000000002 R09: 0000000000000000
 R10: 00007fffd79c0ba0 R11: 0000000000000246 R12: 0000000000000000
 R13: 00007fffd79c1254 R14: 0000000000000001 R15: 0000000000669f60
 Code: 5d e9 42 da ff ff 66 90 0f 1f 44 00 00 41 57 41 56 41 55 49 89 d5 41 54 55 48 89 fd 53 48 83 ec 08 40 f6 c7 07 0f 85 19 02 00 00 <48> 89 75 08 48 c7 45 00 00 00 00 00 9c 58 0f 1f 44 00 00 49 89
 RIP: __call_rcu+0x23/0x2b0 RSP: ffffaac3005fb798
 CR2: 0000000000000018

fix this in tcf_vlan_cleanup(), ensuring that kfree_rcu(p, ...) is called
only when p is not NULL.

Fixes: 4c5b9d9642c8 ("act_vlan: VLAN action rewrite to use RCU lock/unlock and update")
Acked-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Manish Kurup <manish.kurup@verizon.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_vlan.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 97f717a13ad5..788a8daf9230 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -225,7 +225,8 @@ static void tcf_vlan_cleanup(struct tc_action *a, int bind)
 	struct tcf_vlan_params *p;
 
 	p = rcu_dereference_protected(v->vlan_p, 1);
-	kfree_rcu(p, rcu);
+	if (p)
+		kfree_rcu(p, rcu);
 }
 
 static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a,
-- 
2.14.3


From 8be5aa3ebe8e559a294547aea41071ae5d927314 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Tue, 13 Mar 2018 21:43:43 +0200
Subject: [PATCH 32/48] net/mlx5e: Avoid using the ipv6 stub in the TC offload
 neigh update path

[ Upstream commit 423c9db29943cfc43e3a408192e9efa4178af6a1 ]

Currently we use the global ipv6_stub var to access the ipv6 global
nd table. This practice gets us to troubles when the stub is only partially
set e.g when ipv6 is loaded under the disabled policy. In this case, as of commit
343d60aada5a ("ipv6: change ipv6_stub_impl.ipv6_dst_lookup to take net argument")
the stub is not null, but stub->nd_tbl is and we crash.

As we can access the ipv6 nd_tbl directly, the fix is just to avoid the
reference through the stub. There is one place in the code where we
issue ipv6 route lookup and keep doing it through the stub, but that
mentioned commit makes sure we get -EAFNOSUPPORT from the stack.

Fixes: 232c001398ae ("net/mlx5e: Add support to neighbour update flow")
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Aviv Heller <avivh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 6 +++---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c  | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 3409d86eb06b..06964ab6c6c6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -231,7 +231,7 @@ void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv)
 static void mlx5e_rep_neigh_update_init_interval(struct mlx5e_rep_priv *rpriv)
 {
 #if IS_ENABLED(CONFIG_IPV6)
-	unsigned long ipv6_interval = NEIGH_VAR(&ipv6_stub->nd_tbl->parms,
+	unsigned long ipv6_interval = NEIGH_VAR(&nd_tbl.parms,
 						DELAY_PROBE_TIME);
 #else
 	unsigned long ipv6_interval = ~0UL;
@@ -367,7 +367,7 @@ static int mlx5e_rep_netevent_event(struct notifier_block *nb,
 	case NETEVENT_NEIGH_UPDATE:
 		n = ptr;
 #if IS_ENABLED(CONFIG_IPV6)
-		if (n->tbl != ipv6_stub->nd_tbl && n->tbl != &arp_tbl)
+		if (n->tbl != &nd_tbl && n->tbl != &arp_tbl)
 #else
 		if (n->tbl != &arp_tbl)
 #endif
@@ -415,7 +415,7 @@ static int mlx5e_rep_netevent_event(struct notifier_block *nb,
 		 * done per device delay prob time parameter.
 		 */
 #if IS_ENABLED(CONFIG_IPV6)
-		if (!p->dev || (p->tbl != ipv6_stub->nd_tbl && p->tbl != &arp_tbl))
+		if (!p->dev || (p->tbl != &nd_tbl && p->tbl != &arp_tbl))
 #else
 		if (!p->dev || p->tbl != &arp_tbl)
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 55979ec2e88a..5d1cd236e04a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -495,7 +495,7 @@ void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe)
 		tbl = &arp_tbl;
 #if IS_ENABLED(CONFIG_IPV6)
 	else if (m_neigh->family == AF_INET6)
-		tbl = ipv6_stub->nd_tbl;
+		tbl = &nd_tbl;
 #endif
 	else
 		return;
-- 
2.14.3


From 62142e8598ca6bb059452c8204f931cf27c3bd0a Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@mellanox.com>
Date: Thu, 8 Mar 2018 09:20:55 +0000
Subject: [PATCH 33/48] net/mlx5e: Fix memory usage issues in offloading TC
 flows

[ Upstream commit af1607c37d9d85a66fbcf43b7f11bf3d94b9bb69 ]

For NIC flows, the parsed attributes are not freed when we exit
successfully from mlx5e_configure_flower().

There is possible double free for eswitch flows. If error is returned
from rhashtable_insert_fast(), the parse attrs will be freed in
mlx5e_tc_del_flow(), but they will be freed again before exiting
mlx5e_configure_flower().

To fix both issues we do the following:
(1) change the condition that determines if to issue the free call to
    check if this flow is NIC flow, or it does not have encap action.
(2) reorder the code such that that the check and free calls are done
    before we attempt to add into the hash table.

Fixes: 232c001398ae ('net/mlx5e: Add support to neighbour update flow')
Signed-off-by: Jianbo Liu <jianbol@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 5d1cd236e04a..dfab6b08db70 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2102,19 +2102,19 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv,
 	if (err != -EAGAIN)
 		flow->flags |= MLX5E_TC_FLOW_OFFLOADED;
 
+	if (!(flow->flags & MLX5E_TC_FLOW_ESWITCH) ||
+	    !(flow->esw_attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP))
+		kvfree(parse_attr);
+
 	err = rhashtable_insert_fast(&tc->ht, &flow->node,
 				     tc->ht_params);
-	if (err)
-		goto err_del_rule;
+	if (err) {
+		mlx5e_tc_del_flow(priv, flow);
+		kfree(flow);
+	}
 
-	if (flow->flags & MLX5E_TC_FLOW_ESWITCH &&
-	    !(flow->esw_attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP))
-		kvfree(parse_attr);
 	return err;
 
-err_del_rule:
-	mlx5e_tc_del_flow(priv, flow);
-
 err_free:
 	kvfree(parse_attr);
 	kfree(flow);
-- 
2.14.3


From fcd823b1d74fbc2a408fe1d8259773deb493ed0d Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Fri, 16 Mar 2018 00:00:56 +0100
Subject: [PATCH 34/48] net/sched: fix NULL dereference in the error path of
 tcf_sample_init()

[ Upstream commit 1f110e7cae09e6c6a144616480d1a9dd99c5208a ]

when the following command

 # tc action add action sample rate 100 group 100 index 100

is run for the first time, and psample_group_get(100) fails to create a
new group, tcf_sample_cleanup() calls psample_group_put(NULL), thus
causing the following error:

 BUG: unable to handle kernel NULL pointer dereference at 000000000000001c
 IP: psample_group_put+0x15/0x71 [psample]
 PGD 8000000075775067 P4D 8000000075775067 PUD 7453c067 PMD 0
 Oops: 0002 [#1] SMP PTI
 Modules linked in: act_sample(E) psample ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hda_core mbcache jbd2 crct10dif_pclmul snd_hwdep crc32_pclmul snd_seq ghash_clmulni_intel pcbc snd_seq_device snd_pcm aesni_intel crypto_simd snd_timer glue_helper snd cryptd joydev pcspkr i2c_piix4 soundcore virtio_balloon nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm drm virtio_net ata_piix virtio_console virtio_blk libata serio_raw crc32c_intel virtio_pci i2c_core virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod [last unloaded: act_tunnel_key]
 CPU: 2 PID: 5740 Comm: tc Tainted: G            E    4.16.0-rc4.act_vlan.orig+ #403
 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
 RIP: 0010:psample_group_put+0x15/0x71 [psample]
 RSP: 0018:ffffb8a80032f7d0 EFLAGS: 00010246
 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000024
 RDX: 0000000000000001 RSI: 0000000000000000 RDI: ffffffffc06d93c0
 RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000044
 R10: 00000000bd003000 R11: ffff979fba04aa59 R12: 0000000000000000
 R13: 0000000000000000 R14: 0000000000000000 R15: ffff979fbba3f22c
 FS:  00007f7638112740(0000) GS:ffff979fbfd00000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 000000000000001c CR3: 00000000734ea001 CR4: 00000000001606e0
 Call Trace:
  __tcf_idr_release+0x79/0xf0
  tcf_sample_init+0x125/0x1d0 [act_sample]
  tcf_action_init_1+0x2cc/0x430
  tcf_action_init+0xd3/0x1b0
  tc_ctl_action+0x18b/0x240
  rtnetlink_rcv_msg+0x29c/0x310
  ? _cond_resched+0x15/0x30
  ? __kmalloc_node_track_caller+0x1b9/0x270
  ? rtnl_calcit.isra.28+0x100/0x100
  netlink_rcv_skb+0xd2/0x110
  netlink_unicast+0x17c/0x230
  netlink_sendmsg+0x2cd/0x3c0
  sock_sendmsg+0x30/0x40
  ___sys_sendmsg+0x27a/0x290
  ? filemap_map_pages+0x34a/0x3a0
  ? __handle_mm_fault+0xbfd/0xe20
  __sys_sendmsg+0x51/0x90
  do_syscall_64+0x6e/0x1a0
  entry_SYSCALL_64_after_hwframe+0x3d/0xa2
 RIP: 0033:0x7f7637523ba0
 RSP: 002b:00007fff0473ef58 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
 RAX: ffffffffffffffda RBX: 00007fff0473f080 RCX: 00007f7637523ba0
 RDX: 0000000000000000 RSI: 00007fff0473efd0 RDI: 0000000000000003
 RBP: 000000005aaaac80 R08: 0000000000000002 R09: 0000000000000000
 R10: 00007fff0473e9e0 R11: 0000000000000246 R12: 0000000000000000
 R13: 00007fff0473f094 R14: 0000000000000001 R15: 0000000000669f60
 Code: be 02 00 00 00 48 89 df e8 a9 fe ff ff e9 7c ff ff ff 0f 1f 40 00 0f 1f 44 00 00 53 48 89 fb 48 c7 c7 c0 93 6d c0 e8 db 20 8c ef <83> 6b 1c 01 74 10 48 c7 c7 c0 93 6d c0 ff 14 25 e8 83 83 b0 5b
 RIP: psample_group_put+0x15/0x71 [psample] RSP: ffffb8a80032f7d0
 CR2: 000000000000001c

Fix it in tcf_sample_cleanup(), ensuring that calls to psample_group_put(p)
are done only when p is not NULL.

Fixes: cadb9c9fdbc6 ("net/sched: act_sample: Fix error path in init")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_sample.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 9438969290a6..2298d91c4c83 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -103,7 +103,8 @@ static void tcf_sample_cleanup(struct tc_action *a, int bind)
 
 	psample_group = rtnl_dereference(s->psample_group);
 	RCU_INIT_POINTER(s->psample_group, NULL);
-	psample_group_put(psample_group);
+	if (psample_group)
+		psample_group_put(psample_group);
 }
 
 static bool tcf_sample_dev_ok_push(struct net_device *dev)
-- 
2.14.3


From 12ade190011c77511d3102b91d28c00533249b63 Mon Sep 17 00:00:00 2001
From: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Date: Tue, 3 Apr 2018 17:24:23 -0700
Subject: [PATCH 35/48] nfp: use full 40 bits of the NSP buffer address

[ Upstream commit 1489bbd10e16079ce30a53d3c22a431fd47af791 ]

The NSP default buffer is a piece of NFP memory where additional
command data can be placed.  Its format has been copied from
host buffer, but the PCIe selection bits do not make sense in
this case.  If those get masked out from a NFP address - writes
to random place in the chip memory may be issued and crash the
device.

Even in the general NSP buffer case, it doesn't make sense to have the
PCIe selection bits there anymore. These are unused at the moment, and
when it becomes necessary, the PCIe selection bits should rather be
moved to another register to utilise more bits for the buffer address.

This has never been an issue because the buffer used to be
allocated in memory with less-than-38-bit-long address but that
is about to change.

Fixes: 1a64821c6af7 ("nfp: add support for service processor access")
Signed-off-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
index 14a6d1ba51a9..54fe044ceef8 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
@@ -68,10 +68,11 @@
 /* CPP address to retrieve the data from */
 #define NSP_BUFFER		0x10
 #define   NSP_BUFFER_CPP	GENMASK_ULL(63, 40)
-#define   NSP_BUFFER_PCIE	GENMASK_ULL(39, 38)
-#define   NSP_BUFFER_ADDRESS	GENMASK_ULL(37, 0)
+#define   NSP_BUFFER_ADDRESS	GENMASK_ULL(39, 0)
 
 #define NSP_DFLT_BUFFER		0x18
+#define   NSP_DFLT_BUFFER_CPP	GENMASK_ULL(63, 40)
+#define   NSP_DFLT_BUFFER_ADDRESS	GENMASK_ULL(39, 0)
 
 #define NSP_DFLT_BUFFER_CONFIG	0x20
 #define   NSP_DFLT_BUFFER_SIZE_MB	GENMASK_ULL(7, 0)
@@ -412,8 +413,8 @@ static int nfp_nsp_command_buf(struct nfp_nsp *nsp, u16 code, u32 option,
 	if (err < 0)
 		return err;
 
-	cpp_id = FIELD_GET(NSP_BUFFER_CPP, reg) << 8;
-	cpp_buf = FIELD_GET(NSP_BUFFER_ADDRESS, reg);
+	cpp_id = FIELD_GET(NSP_DFLT_BUFFER_CPP, reg) << 8;
+	cpp_buf = FIELD_GET(NSP_DFLT_BUFFER_ADDRESS, reg);
 
 	if (in_buf && in_size) {
 		err = nfp_cpp_write(cpp, cpp_id, cpp_buf, in_buf, in_size);
-- 
2.14.3


From 23b1774aa450778dc6c784880b8b24fcf25c55fc Mon Sep 17 00:00:00 2001
From: David Lebrun <dlebrun@google.com>
Date: Thu, 29 Mar 2018 17:59:36 +0100
Subject: [PATCH 36/48] ipv6: sr: fix seg6 encap performances with TSO enabled

[ Upstream commit 5807b22c9164a21cd1077a9bc587f0bba361f72d ]

Enabling TSO can lead to abysmal performances when using seg6 in
encap mode, such as with the ixgbe driver. This patch adds a call to
iptunnel_handle_offloads() to remove the encapsulation bit if needed.

Before:
root@comp4-seg6bpf:~# iperf3 -c fc00::55
Connecting to host fc00::55, port 5201
[  4] local fc45::4 port 36592 connected to fc00::55 port 5201
[ ID] Interval           Transfer     Bandwidth       Retr  Cwnd
[  4]   0.00-1.00   sec   196 KBytes  1.60 Mbits/sec   47   6.66 KBytes
[  4]   1.00-2.00   sec   304 KBytes  2.49 Mbits/sec  100   5.33 KBytes
[  4]   2.00-3.00   sec   284 KBytes  2.32 Mbits/sec   92   5.33 KBytes

After:
root@comp4-seg6bpf:~# iperf3 -c fc00::55
Connecting to host fc00::55, port 5201
[  4] local fc45::4 port 43062 connected to fc00::55 port 5201
[ ID] Interval           Transfer     Bandwidth       Retr  Cwnd
[  4]   0.00-1.00   sec  1.03 GBytes  8.89 Gbits/sec    0    743 KBytes
[  4]   1.00-2.00   sec  1.03 GBytes  8.87 Gbits/sec    0    743 KBytes
[  4]   2.00-3.00   sec  1.03 GBytes  8.87 Gbits/sec    0    743 KBytes

Reported-by: Tom Herbert <tom@quantonium.net>
Fixes: 6c8702c60b88 ("ipv6: sr: add support for SRH encapsulation and injection with lwtunnels")
Signed-off-by: David Lebrun <dlebrun@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/seg6_iptunnel.c | 16 +++++++---------
 1 file changed, 7 insertions(+), 9 deletions(-)

diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 7a78dcfda68a..f343e6f0fc95 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -16,6 +16,7 @@
 #include <linux/net.h>
 #include <linux/module.h>
 #include <net/ip.h>
+#include <net/ip_tunnels.h>
 #include <net/lwtunnel.h>
 #include <net/netevent.h>
 #include <net/netns/generic.h>
@@ -211,11 +212,6 @@ static int seg6_do_srh(struct sk_buff *skb)
 
 	tinfo = seg6_encap_lwtunnel(dst->lwtstate);
 
-	if (likely(!skb->encapsulation)) {
-		skb_reset_inner_headers(skb);
-		skb->encapsulation = 1;
-	}
-
 	switch (tinfo->mode) {
 	case SEG6_IPTUN_MODE_INLINE:
 		if (skb->protocol != htons(ETH_P_IPV6))
@@ -224,10 +220,12 @@ static int seg6_do_srh(struct sk_buff *skb)
 		err = seg6_do_srh_inline(skb, tinfo->srh);
 		if (err)
 			return err;
-
-		skb_reset_inner_headers(skb);
 		break;
 	case SEG6_IPTUN_MODE_ENCAP:
+		err = iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6);
+		if (err)
+			return err;
+
 		if (skb->protocol == htons(ETH_P_IPV6))
 			proto = IPPROTO_IPV6;
 		else if (skb->protocol == htons(ETH_P_IP))
@@ -239,6 +237,8 @@ static int seg6_do_srh(struct sk_buff *skb)
 		if (err)
 			return err;
 
+		skb_set_inner_transport_header(skb, skb_transport_offset(skb));
+		skb_set_inner_protocol(skb, skb->protocol);
 		skb->protocol = htons(ETH_P_IPV6);
 		break;
 	case SEG6_IPTUN_MODE_L2ENCAP:
@@ -262,8 +262,6 @@ static int seg6_do_srh(struct sk_buff *skb)
 	ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
 	skb_set_transport_header(skb, sizeof(struct ipv6hdr));
 
-	skb_set_inner_protocol(skb, skb->protocol);
-
 	return 0;
 }
 
-- 
2.14.3


From 3c092b33d704fc9812d5af4188f91237d8c312f1 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@mellanox.com>
Date: Fri, 2 Mar 2018 02:09:08 +0000
Subject: [PATCH 37/48] net/mlx5e: Don't override vport admin link state in
 switchdev mode

The vport admin original link state will be re-applied after returning
back to legacy mode, it is not right to change the admin link state value
when in switchdev mode.

Use direct vport commands to alter logical vport state in netdev
representor open/close flows rather than the administrative eswitch API.

Fixes: 20a1ea674783 ('net/mlx5e: Support VF vport link state control for SRIOV switchdev mode')
Signed-off-by: Jianbo Liu <jianbol@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 06964ab6c6c6..f78148ffb0ba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -611,7 +611,6 @@ static int mlx5e_rep_open(struct net_device *dev)
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	struct mlx5_eswitch_rep *rep = rpriv->rep;
-	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	int err;
 
 	mutex_lock(&priv->state_lock);
@@ -619,8 +618,9 @@ static int mlx5e_rep_open(struct net_device *dev)
 	if (err)
 		goto unlock;
 
-	if (!mlx5_eswitch_set_vport_state(esw, rep->vport,
-					  MLX5_ESW_VPORT_ADMIN_STATE_UP))
+	if (!mlx5_modify_vport_admin_state(priv->mdev,
+			MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT,
+			rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_UP))
 		netif_carrier_on(dev);
 
 unlock:
@@ -633,11 +633,12 @@ static int mlx5e_rep_close(struct net_device *dev)
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	struct mlx5_eswitch_rep *rep = rpriv->rep;
-	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	int ret;
 
 	mutex_lock(&priv->state_lock);
-	(void)mlx5_eswitch_set_vport_state(esw, rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_DOWN);
+	mlx5_modify_vport_admin_state(priv->mdev,
+			MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT,
+			rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_DOWN);
 	ret = mlx5e_close_locked(dev);
 	mutex_unlock(&priv->state_lock);
 	return ret;
-- 
2.14.3


From a9334a002488d0752d1d4a4fc91388018efcaafe Mon Sep 17 00:00:00 2001
From: Shahar Klein <shahark@mellanox.com>
Date: Tue, 20 Mar 2018 14:44:40 +0200
Subject: [PATCH 38/48] net/mlx5e: Sync netdev vxlan ports at open

[ Upstream commit a117f73dc2430443f23e18367fa545981129c1a6 ]

When mlx5_core is loaded it is expected to sync ports
with all vxlan devices so it can support vxlan encap/decap.
This is done via udp_tunnel_get_rx_info(). Currently this
call is set in mlx5e_nic_enable() and if the netdev is not in
NETREG_REGISTERED state it will not be called.

Normally on load the netdev state is not NETREG_REGISTERED
so udp_tunnel_get_rx_info() will not be called.

Moving udp_tunnel_get_rx_info() to mlx5e_open() so
it will be called on netdev UP event and allow encap/decap.

Fixes: 610e89e05c3f ("net/mlx5e: Don't sync netdev state when not registered")
Signed-off-by: Shahar Klein <shahark@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 33faac2b194c..f5a704c7d143 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2715,6 +2715,9 @@ int mlx5e_open(struct net_device *netdev)
 		mlx5_set_port_admin_status(priv->mdev, MLX5_PORT_UP);
 	mutex_unlock(&priv->state_lock);
 
+	if (mlx5e_vxlan_allowed(priv->mdev))
+		udp_tunnel_get_rx_info(netdev);
+
 	return err;
 }
 
@@ -4428,12 +4431,6 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 	mlx5e_dcbnl_init_app(priv);
 #endif
-	/* Device already registered: sync netdev system state */
-	if (mlx5e_vxlan_allowed(mdev)) {
-		rtnl_lock();
-		udp_tunnel_get_rx_info(netdev);
-		rtnl_unlock();
-	}
 
 	queue_work(priv->wq, &priv->set_rx_mode_work);
 
-- 
2.14.3


From 972bacf9de61186dd31905398d381de9e7af12b2 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Fri, 16 Mar 2018 00:00:55 +0100
Subject: [PATCH 39/48] net/sched: fix NULL dereference in the error path of
 tunnel_key_init()

[ Upstream commit abdadd3cfd3e7ea3da61ac774f84777d1f702058 ]

when the following command

 # tc action add action tunnel_key unset index 100

is run for the first time, and tunnel_key_init() fails to allocate struct
tcf_tunnel_key_params, tunnel_key_release() dereferences NULL pointers.
This causes the following error:

 BUG: unable to handle kernel NULL pointer dereference at 0000000000000010
 IP: tunnel_key_release+0xd/0x40 [act_tunnel_key]
 PGD 8000000033787067 P4D 8000000033787067 PUD 74646067 PMD 0
 Oops: 0000 [#1] SMP PTI
 Modules linked in: act_tunnel_key(E) act_csum ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 mbcache jbd2 crct10dif_pclmul crc32_pclmul snd_hda_codec_generic ghash_clmulni_intel snd_hda_intel pcbc snd_hda_codec snd_hda_core snd_hwdep snd_seq aesni_intel snd_seq_device crypto_simd glue_helper snd_pcm cryptd joydev snd_timer pcspkr virtio_balloon snd i2c_piix4 soundcore nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm virtio_net virtio_blk drm virtio_console crc32c_intel ata_piix serio_raw i2c_core virtio_pci libata virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod
 CPU: 2 PID: 3101 Comm: tc Tainted: G            E    4.16.0-rc4.act_vlan.orig+ #403
 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
 RIP: 0010:tunnel_key_release+0xd/0x40 [act_tunnel_key]
 RSP: 0018:ffffba46803b7768 EFLAGS: 00010286
 RAX: ffffffffc09010a0 RBX: 0000000000000000 RCX: 0000000000000024
 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff99ee336d7480
 RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000044
 R10: 0000000000000220 R11: ffff99ee79d73131 R12: 0000000000000000
 R13: ffff99ee32d67610 R14: ffff99ee7671dc38 R15: 00000000fffffff4
 FS:  00007febcb2cd740(0000) GS:ffff99ee7fd00000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000000010 CR3: 000000007c8e4005 CR4: 00000000001606e0
 Call Trace:
  __tcf_idr_release+0x79/0xf0
  tunnel_key_init+0xd9/0x460 [act_tunnel_key]
  tcf_action_init_1+0x2cc/0x430
  tcf_action_init+0xd3/0x1b0
  tc_ctl_action+0x18b/0x240
  rtnetlink_rcv_msg+0x29c/0x310
  ? _cond_resched+0x15/0x30
  ? __kmalloc_node_track_caller+0x1b9/0x270
  ? rtnl_calcit.isra.28+0x100/0x100
  netlink_rcv_skb+0xd2/0x110
  netlink_unicast+0x17c/0x230
  netlink_sendmsg+0x2cd/0x3c0
  sock_sendmsg+0x30/0x40
  ___sys_sendmsg+0x27a/0x290
  __sys_sendmsg+0x51/0x90
  do_syscall_64+0x6e/0x1a0
  entry_SYSCALL_64_after_hwframe+0x3d/0xa2
 RIP: 0033:0x7febca6deba0
 RSP: 002b:00007ffe7b0dd128 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
 RAX: ffffffffffffffda RBX: 00007ffe7b0dd250 RCX: 00007febca6deba0
 RDX: 0000000000000000 RSI: 00007ffe7b0dd1a0 RDI: 0000000000000003
 RBP: 000000005aaa90cb R08: 0000000000000002 R09: 0000000000000000
 R10: 00007ffe7b0dcba0 R11: 0000000000000246 R12: 0000000000000000
 R13: 00007ffe7b0dd264 R14: 0000000000000001 R15: 0000000000669f60
 Code: 44 00 00 8b 0d b5 23 00 00 48 8b 87 48 10 00 00 48 8b 3c c8 e9 a5 e5 d8 c3 0f 1f 44 00 00 0f 1f 44 00 00 53 48 8b 9f b0 00 00 00 <83> 7b 10 01 74 0b 48 89 df 31 f6 5b e9 f2 fa 7f c3 48 8b 7b 18
 RIP: tunnel_key_release+0xd/0x40 [act_tunnel_key] RSP: ffffba46803b7768
 CR2: 0000000000000010

Fix this in tunnel_key_release(), ensuring 'param' is not NULL before
dereferencing it.

Fixes: d0f6dd8a914f ("net/sched: Introduce act_tunnel_key")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_tunnel_key.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 22bf1a376b91..7cb63616805d 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -208,11 +208,12 @@ static void tunnel_key_release(struct tc_action *a, int bind)
 	struct tcf_tunnel_key_params *params;
 
 	params = rcu_dereference_protected(t->params, 1);
+	if (params) {
+		if (params->tcft_action == TCA_TUNNEL_KEY_ACT_SET)
+			dst_release(&params->tcft_enc_metadata->dst);
 
-	if (params->tcft_action == TCA_TUNNEL_KEY_ACT_SET)
-		dst_release(&params->tcft_enc_metadata->dst);
-
-	kfree_rcu(params, rcu);
+		kfree_rcu(params, rcu);
+	}
 }
 
 static int tunnel_key_dump_addresses(struct sk_buff *skb,
-- 
2.14.3


From c0e10c2fcdcc6714f92e3044148c1ac7c91443c2 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Fri, 16 Mar 2018 00:00:57 +0100
Subject: [PATCH 40/48] net/sched: fix NULL dereference on the error path of
 tcf_skbmod_init()

[ Upstream commit 2d433610176d6569e8b3a28f67bc72235bf69efc ]

when the following command

 # tc action replace action skbmod swap mac index 100

is run for the first time, and tcf_skbmod_init() fails to allocate struct
tcf_skbmod_params, tcf_skbmod_cleanup() calls kfree_rcu(NULL), thus
causing the following error:

 BUG: unable to handle kernel NULL pointer dereference at 0000000000000008
 IP: __call_rcu+0x23/0x2b0
 PGD 8000000034057067 P4D 8000000034057067 PUD 74937067 PMD 0
 Oops: 0002 [#1] SMP PTI
 Modules linked in: act_skbmod(E) psample ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 snd_hda_codec_generic snd_hda_intel snd_hda_codec crct10dif_pclmul mbcache jbd2 crc32_pclmul snd_hda_core ghash_clmulni_intel snd_hwdep pcbc snd_seq snd_seq_device snd_pcm aesni_intel snd_timer crypto_simd glue_helper snd cryptd virtio_balloon joydev soundcore pcspkr i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm drm virtio_console virtio_net virtio_blk ata_piix libata crc32c_intel virtio_pci serio_raw virtio_ring virtio i2c_core floppy dm_mirror dm_region_hash dm_log dm_mod [last unloaded: act_skbmod]
 CPU: 3 PID: 3144 Comm: tc Tainted: G            E    4.16.0-rc4.act_vlan.orig+ #403
 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
 RIP: 0010:__call_rcu+0x23/0x2b0
 RSP: 0018:ffffbd2e403e7798 EFLAGS: 00010246
 RAX: ffffffffc0872080 RBX: ffff981d34bff780 RCX: 00000000ffffffff
 RDX: ffffffff922a5f00 RSI: 0000000000000000 RDI: 0000000000000000
 RBP: 0000000000000000 R08: 0000000000000001 R09: 000000000000021f
 R10: 000000003d003000 R11: 0000000000aaaaaa R12: 0000000000000000
 R13: ffffffff922a5f00 R14: 0000000000000001 R15: ffff981d3b698c2c
 FS:  00007f3678292740(0000) GS:ffff981d3fd80000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000000008 CR3: 000000007c57a006 CR4: 00000000001606e0
 Call Trace:
  __tcf_idr_release+0x79/0xf0
  tcf_skbmod_init+0x1d1/0x210 [act_skbmod]
  tcf_action_init_1+0x2cc/0x430
  tcf_action_init+0xd3/0x1b0
  tc_ctl_action+0x18b/0x240
  rtnetlink_rcv_msg+0x29c/0x310
  ? _cond_resched+0x15/0x30
  ? __kmalloc_node_track_caller+0x1b9/0x270
  ? rtnl_calcit.isra.28+0x100/0x100
  netlink_rcv_skb+0xd2/0x110
  netlink_unicast+0x17c/0x230
  netlink_sendmsg+0x2cd/0x3c0
  sock_sendmsg+0x30/0x40
  ___sys_sendmsg+0x27a/0x290
  ? filemap_map_pages+0x34a/0x3a0
  ? __handle_mm_fault+0xbfd/0xe20
  __sys_sendmsg+0x51/0x90
  do_syscall_64+0x6e/0x1a0
  entry_SYSCALL_64_after_hwframe+0x3d/0xa2
 RIP: 0033:0x7f36776a3ba0
 RSP: 002b:00007fff4703b618 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
 RAX: ffffffffffffffda RBX: 00007fff4703b740 RCX: 00007f36776a3ba0
 RDX: 0000000000000000 RSI: 00007fff4703b690 RDI: 0000000000000003
 RBP: 000000005aaaba36 R08: 0000000000000002 R09: 0000000000000000
 R10: 00007fff4703b0a0 R11: 0000000000000246 R12: 0000000000000000
 R13: 00007fff4703b754 R14: 0000000000000001 R15: 0000000000669f60
 Code: 5d e9 42 da ff ff 66 90 0f 1f 44 00 00 41 57 41 56 41 55 49 89 d5 41 54 55 48 89 fd 53 48 83 ec 08 40 f6 c7 07 0f 85 19 02 00 00 <48> 89 75 08 48 c7 45 00 00 00 00 00 9c 58 0f 1f 44 00 00 49 89
 RIP: __call_rcu+0x23/0x2b0 RSP: ffffbd2e403e7798
 CR2: 0000000000000008

Fix it in tcf_skbmod_cleanup(), ensuring that kfree_rcu(p, ...) is called
only when p is not NULL.

Fixes: 86da71b57383 ("net_sched: Introduce skbmod action")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_skbmod.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index b642ad3d39dd..6d10b3af479b 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -190,7 +190,8 @@ static void tcf_skbmod_cleanup(struct tc_action *a, int bind)
 	struct tcf_skbmod_params  *p;
 
 	p = rcu_dereference_protected(d->skbmod_p, 1);
-	kfree_rcu(p, rcu);
+	if (p)
+		kfree_rcu(p, rcu);
 }
 
 static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a,
-- 
2.14.3


From 71d1427261446e291e8c4b3734dbd16b01e48bd9 Mon Sep 17 00:00:00 2001
From: Dave Watson <davejwatson@fb.com>
Date: Mon, 26 Mar 2018 12:31:21 -0700
Subject: [PATCH 41/48] strparser: Fix sign of err codes

[ Upstream commit cd00edc179863848abab5cc5683de5b7b5f70954 ]

strp_parser_err is called with a negative code everywhere, which then
calls abort_parser with a negative code.  strp_msg_timeout calls
abort_parser directly with a positive code.  Negate ETIMEDOUT
to match signed-ness of other calls.

The default abort_parser callback, strp_abort_strp, sets
sk->sk_err to err.  Also negate the error here so sk_err always
holds a positive value, as the rest of the net code expects.  Currently
a negative sk_err can result in endless loops, or user code that
thinks it actually sent/received err bytes.

Found while testing net/tls_sw recv path.

Fixes: 43a0c6751a322847 ("strparser: Stream parser for messages")
Signed-off-by: Dave Watson <davejwatson@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/strparser/strparser.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index 1fdab5c4eda8..b9283ce5cd85 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -60,7 +60,7 @@ static void strp_abort_strp(struct strparser *strp, int err)
 		struct sock *sk = strp->sk;
 
 		/* Report an error on the lower socket */
-		sk->sk_err = err;
+		sk->sk_err = -err;
 		sk->sk_error_report(sk);
 	}
 }
@@ -458,7 +458,7 @@ static void strp_msg_timeout(struct work_struct *w)
 	/* Message assembly timed out */
 	STRP_STATS_INCR(strp->stats.msg_timeouts);
 	strp->cb.lock(strp);
-	strp->cb.abort_parser(strp, ETIMEDOUT);
+	strp->cb.abort_parser(strp, -ETIMEDOUT);
 	strp->cb.unlock(strp);
 }
 
-- 
2.14.3


From e1004f8afdc79a0dc87511054c9e9a1e708a3e6d Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Tue, 27 Mar 2018 14:41:18 +0300
Subject: [PATCH 42/48] net/mlx4_en: Fix mixed PFC and Global pause user
 control requests

[ Upstream commit 6e8814ceb7e8f468659ef9253bd212c07ae19584 ]

Global pause and PFC configuration should be mutually exclusive (i.e. only
one of them at most can be set). However, once PFC was turned off,
driver automatically turned Global pause on. This is a bug.

Fix the driver behaviour to turn off PFC/Global once the user turned the
other on.

This also fixed a weird behaviour that at a current time, the profile
had both PFC and global pause configuration turned on, which is
Hardware-wise impossible and caused returning false positive indication
to query tools.

In addition, fix error code when setting global pause or PFC to change
metadata only upon successful change.

Also, removed useless debug print.

Fixes: af7d51852631 ("net/mlx4_en: Add DCB PFC support through CEE netlink commands")
Fixes: c27a02cd94d6 ("mlx4_en: Add driver for Mellanox ConnectX 10GbE NIC")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c  | 72 ++++++++++++++-----------
 drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 33 +++++++-----
 drivers/net/ethernet/mellanox/mlx4/en_main.c    |  4 +-
 3 files changed, 62 insertions(+), 47 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
index 5f41dc92aa68..6e05d996b256 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
@@ -156,57 +156,63 @@ static int mlx4_en_dcbnl_getnumtcs(struct net_device *netdev, int tcid, u8 *num)
 static u8 mlx4_en_dcbnl_set_all(struct net_device *netdev)
 {
 	struct mlx4_en_priv *priv = netdev_priv(netdev);
+	struct mlx4_en_port_profile *prof = priv->prof;
 	struct mlx4_en_dev *mdev = priv->mdev;
+	u8 tx_pause, tx_ppp, rx_pause, rx_ppp;
 
 	if (!(priv->dcbx_cap & DCB_CAP_DCBX_VER_CEE))
 		return 1;
 
 	if (priv->cee_config.pfc_state) {
 		int tc;
+		rx_ppp = prof->rx_ppp;
+		tx_ppp = prof->tx_ppp;
 
-		priv->prof->rx_pause = 0;
-		priv->prof->tx_pause = 0;
 		for (tc = 0; tc < CEE_DCBX_MAX_PRIO; tc++) {
 			u8 tc_mask = 1 << tc;
 
 			switch (priv->cee_config.dcb_pfc[tc]) {
 			case pfc_disabled:
-				priv->prof->tx_ppp &= ~tc_mask;
-				priv->prof->rx_ppp &= ~tc_mask;
+				tx_ppp &= ~tc_mask;
+				rx_ppp &= ~tc_mask;
 				break;
 			case pfc_enabled_full:
-				priv->prof->tx_ppp |= tc_mask;
-				priv->prof->rx_ppp |= tc_mask;
+				tx_ppp |= tc_mask;
+				rx_ppp |= tc_mask;
 				break;
 			case pfc_enabled_tx:
-				priv->prof->tx_ppp |= tc_mask;
-				priv->prof->rx_ppp &= ~tc_mask;
+				tx_ppp |= tc_mask;
+				rx_ppp &= ~tc_mask;
 				break;
 			case pfc_enabled_rx:
-				priv->prof->tx_ppp &= ~tc_mask;
-				priv->prof->rx_ppp |= tc_mask;
+				tx_ppp &= ~tc_mask;
+				rx_ppp |= tc_mask;
 				break;
 			default:
 				break;
 			}
 		}
-		en_dbg(DRV, priv, "Set pfc on\n");
+		rx_pause = !!(rx_ppp || tx_ppp) ? 0 : prof->rx_pause;
+		tx_pause = !!(rx_ppp || tx_ppp) ? 0 : prof->tx_pause;
 	} else {
-		priv->prof->rx_pause = 1;
-		priv->prof->tx_pause = 1;
-		en_dbg(DRV, priv, "Set pfc off\n");
+		rx_ppp = 0;
+		tx_ppp = 0;
+		rx_pause = prof->rx_pause;
+		tx_pause = prof->tx_pause;
 	}
 
 	if (mlx4_SET_PORT_general(mdev->dev, priv->port,
 				  priv->rx_skb_size + ETH_FCS_LEN,
-				  priv->prof->tx_pause,
-				  priv->prof->tx_ppp,
-				  priv->prof->rx_pause,
-				  priv->prof->rx_ppp)) {
+				  tx_pause, tx_ppp, rx_pause, rx_ppp)) {
 		en_err(priv, "Failed setting pause params\n");
 		return 1;
 	}
 
+	prof->tx_ppp = tx_ppp;
+	prof->rx_ppp = rx_ppp;
+	prof->tx_pause = tx_pause;
+	prof->rx_pause = rx_pause;
+
 	return 0;
 }
 
@@ -403,6 +409,7 @@ static int mlx4_en_dcbnl_ieee_setpfc(struct net_device *dev,
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_port_profile *prof = priv->prof;
 	struct mlx4_en_dev *mdev = priv->mdev;
+	u32 tx_pause, tx_ppp, rx_pause, rx_ppp;
 	int err;
 
 	en_dbg(DRV, priv, "cap: 0x%x en: 0x%x mbc: 0x%x delay: %d\n",
@@ -411,23 +418,26 @@ static int mlx4_en_dcbnl_ieee_setpfc(struct net_device *dev,
 			pfc->mbc,
 			pfc->delay);
 
-	prof->rx_pause = !pfc->pfc_en;
-	prof->tx_pause = !pfc->pfc_en;
-	prof->rx_ppp = pfc->pfc_en;
-	prof->tx_ppp = pfc->pfc_en;
+	rx_pause = prof->rx_pause && !pfc->pfc_en;
+	tx_pause = prof->tx_pause && !pfc->pfc_en;
+	rx_ppp = pfc->pfc_en;
+	tx_ppp = pfc->pfc_en;
 
 	err = mlx4_SET_PORT_general(mdev->dev, priv->port,
 				    priv->rx_skb_size + ETH_FCS_LEN,
-				    prof->tx_pause,
-				    prof->tx_ppp,
-				    prof->rx_pause,
-				    prof->rx_ppp);
-	if (err)
+				    tx_pause, tx_ppp, rx_pause, rx_ppp);
+	if (err) {
 		en_err(priv, "Failed setting pause params\n");
-	else
-		mlx4_en_update_pfc_stats_bitmap(mdev->dev, &priv->stats_bitmap,
-						prof->rx_ppp, prof->rx_pause,
-						prof->tx_ppp, prof->tx_pause);
+		return err;
+	}
+
+	mlx4_en_update_pfc_stats_bitmap(mdev->dev, &priv->stats_bitmap,
+					rx_ppp, rx_pause, tx_ppp, tx_pause);
+
+	prof->tx_ppp = tx_ppp;
+	prof->rx_ppp = rx_ppp;
+	prof->rx_pause = rx_pause;
+	prof->tx_pause = tx_pause;
 
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index bf1f04164885..c5ab626f4cba 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1046,27 +1046,32 @@ static int mlx4_en_set_pauseparam(struct net_device *dev,
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
+	u8 tx_pause, tx_ppp, rx_pause, rx_ppp;
 	int err;
 
 	if (pause->autoneg)
 		return -EINVAL;
 
-	priv->prof->tx_pause = pause->tx_pause != 0;
-	priv->prof->rx_pause = pause->rx_pause != 0;
+	tx_pause = !!(pause->tx_pause);
+	rx_pause = !!(pause->rx_pause);
+	rx_ppp = priv->prof->rx_ppp && !(tx_pause || rx_pause);
+	tx_ppp = priv->prof->tx_ppp && !(tx_pause || rx_pause);
+
 	err = mlx4_SET_PORT_general(mdev->dev, priv->port,
 				    priv->rx_skb_size + ETH_FCS_LEN,
-				    priv->prof->tx_pause,
-				    priv->prof->tx_ppp,
-				    priv->prof->rx_pause,
-				    priv->prof->rx_ppp);
-	if (err)
-		en_err(priv, "Failed setting pause params\n");
-	else
-		mlx4_en_update_pfc_stats_bitmap(mdev->dev, &priv->stats_bitmap,
-						priv->prof->rx_ppp,
-						priv->prof->rx_pause,
-						priv->prof->tx_ppp,
-						priv->prof->tx_pause);
+				    tx_pause, tx_ppp, rx_pause, rx_ppp);
+	if (err) {
+		en_err(priv, "Failed setting pause params, err = %d\n", err);
+		return err;
+	}
+
+	mlx4_en_update_pfc_stats_bitmap(mdev->dev, &priv->stats_bitmap,
+					rx_ppp, rx_pause, tx_ppp, tx_pause);
+
+	priv->prof->tx_pause = tx_pause;
+	priv->prof->rx_pause = rx_pause;
+	priv->prof->tx_ppp = tx_ppp;
+	priv->prof->rx_ppp = rx_ppp;
 
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c
index 2c2965497ed3..d25e16d2c319 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c
@@ -163,9 +163,9 @@ static void mlx4_en_get_profile(struct mlx4_en_dev *mdev)
 		params->udp_rss = 0;
 	}
 	for (i = 1; i <= MLX4_MAX_PORTS; i++) {
-		params->prof[i].rx_pause = 1;
+		params->prof[i].rx_pause = !(pfcrx || pfctx);
 		params->prof[i].rx_ppp = pfcrx;
-		params->prof[i].tx_pause = 1;
+		params->prof[i].tx_pause = !(pfcrx || pfctx);
 		params->prof[i].tx_ppp = pfctx;
 		params->prof[i].tx_ring_size = MLX4_EN_DEF_TX_RING_SIZE;
 		params->prof[i].rx_ring_size = MLX4_EN_DEF_RX_RING_SIZE;
-- 
2.14.3


From ea0322c38d00a4ba9a00b1ef17f2f47098deb951 Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@mellanox.com>
Date: Wed, 28 Feb 2018 12:56:42 +0200
Subject: [PATCH 43/48] net/mlx5e: Fix traffic being dropped on VF representor

[ Upstream commit 4246f698dd58e3c6246fa919ef0b0a1d29a57e4a ]

Increase representor netdev RQ size to avoid dropped packets.
The current size (two) is just too small to keep up with
conventional slow path traffic patterns.
Also match the SQ size to the RQ size.

Fixes: cb67b832921c ("net/mlx5e: Introduce SRIOV VF representors")
Signed-off-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Paul Blakey <paulb@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index f78148ffb0ba..dfa8c6a28a6c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -44,6 +44,11 @@
 #include "en_tc.h"
 #include "fs_core.h"
 
+#define MLX5E_REP_PARAMS_LOG_SQ_SIZE \
+	max(0x6, MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE)
+#define MLX5E_REP_PARAMS_LOG_RQ_SIZE \
+	max(0x6, MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE)
+
 static const char mlx5e_rep_driver_name[] = "mlx5e_rep";
 
 static void mlx5e_rep_get_drvinfo(struct net_device *dev,
@@ -824,9 +829,9 @@ static void mlx5e_build_rep_params(struct mlx5_core_dev *mdev,
 					 MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
 					 MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
 
-	params->log_sq_size = MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
+	params->log_sq_size = MLX5E_REP_PARAMS_LOG_SQ_SIZE;
 	params->rq_wq_type  = MLX5_WQ_TYPE_LINKED_LIST;
-	params->log_rq_size = MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE;
+	params->log_rq_size = MLX5E_REP_PARAMS_LOG_RQ_SIZE;
 
 	params->rx_am_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
 	mlx5e_set_rx_cq_mode_params(params, cq_period_mode);
-- 
2.14.3


From 21624c65c42f553707bb57c628985cff15097f7b Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Thu, 29 Mar 2018 16:00:04 +0800
Subject: [PATCH 44/48] vhost: validate log when IOTLB is enabled

[ Upstream commit d65026c6c62e7d9616c8ceb5a53b68bcdc050525 ]

Vq log_base is the userspace address of bitmap which has nothing to do
with IOTLB. So it needs to be validated unconditionally otherwise we
may try use 0 as log_base which may lead to pin pages that will lead
unexpected result (e.g trigger BUG_ON() in set_bit_to_user()).

Fixes: 6b1e6cc7855b0 ("vhost: new device IOTLB API")
Reported-by: syzbot+6304bf97ef436580fede@syzkaller.appspotmail.com
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/vhost.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index f42683578dca..a5622a8364cb 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -1256,14 +1256,12 @@ static int vq_log_access_ok(struct vhost_virtqueue *vq,
 /* Caller should have vq mutex and device mutex */
 int vhost_vq_access_ok(struct vhost_virtqueue *vq)
 {
-	if (vq->iotlb) {
-		/* When device IOTLB was used, the access validation
-		 * will be validated during prefetching.
-		 */
-		return 1;
-	}
-	return vq_access_ok(vq, vq->num, vq->desc, vq->avail, vq->used) &&
-		vq_log_access_ok(vq, vq->log_base);
+	int ret = vq_log_access_ok(vq, vq->log_base);
+
+	if (ret || vq->iotlb)
+		return ret;
+
+	return vq_access_ok(vq, vq->num, vq->desc, vq->avail, vq->used);
 }
 EXPORT_SYMBOL_GPL(vhost_vq_access_ok);
 
-- 
2.14.3


From 14857d56d72d9bbf92f1c44896e7e31ad0d18900 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 1 Apr 2018 22:40:35 +0800
Subject: [PATCH 45/48] route: check sysctl_fib_multipath_use_neigh earlier
 than hash

[ Upstream commit 6174a30df1b902e1fedbd728f5343937e83e64e6 ]

Prior to this patch, when one packet is hashed into path [1]
(hash <= nh_upper_bound) and it's neigh is dead, it will try
path [2]. However, if path [2]'s neigh is alive but it's
hash > nh_upper_bound, it will not return this alive path.
This packet will never be sent even if path [2] is alive.

 3.3.3.1/24:
  nexthop via 1.1.1.254 dev eth1 weight 1 <--[1] (dead neigh)
  nexthop via 2.2.2.254 dev eth2 weight 1 <--[2]

With sysctl_fib_multipath_use_neigh set is supposed to find an
available path respecting to the l3/l4 hash. But if there is
no available route with this hash, it should at least return
an alive route even with other hash.

This patch is to fix it by processing fib_multipath_use_neigh
earlier than the hash check, so that it will at least return
an alive route if there is when fib_multipath_use_neigh is
enabled. It's also compatible with before when there are alive
routes with the l3/l4 hash.

Fixes: a6db4494d218 ("net: ipv4: Consider failed nexthops in multipath routes")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_semantics.c | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 7d36a950d961..9d512922243f 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1746,18 +1746,20 @@ void fib_select_multipath(struct fib_result *res, int hash)
 	bool first = false;
 
 	for_nexthops(fi) {
+		if (net->ipv4.sysctl_fib_multipath_use_neigh) {
+			if (!fib_good_nh(nh))
+				continue;
+			if (!first) {
+				res->nh_sel = nhsel;
+				first = true;
+			}
+		}
+
 		if (hash > atomic_read(&nh->nh_upper_bound))
 			continue;
 
-		if (!net->ipv4.sysctl_fib_multipath_use_neigh ||
-		    fib_good_nh(nh)) {
-			res->nh_sel = nhsel;
-			return;
-		}
-		if (!first) {
-			res->nh_sel = nhsel;
-			first = true;
-		}
+		res->nh_sel = nhsel;
+		return;
 	} endfor_nexthops(fi);
 }
 #endif
-- 
2.14.3


From 1fe37a8d2f2967df7b0ca687397a8811d51c4f60 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 26 Mar 2018 01:25:06 +0800
Subject: [PATCH 46/48] team: move dev_mc_sync after master_upper_dev_link in
 team_port_add

[ Upstream commit 982cf3b3999d39a2eaca0a65542df33c19b5d814 ]

The same fix as in 'bonding: move dev_mc_sync after master_upper_dev_link
in bond_enslave' is needed for team driver.

The panic can be reproduced easily:

  ip link add team1 type team
  ip link set team1 up
  ip link add link team1 vlan1 type vlan id 80
  ip link set vlan1 master team1

Fixes: cb41c997d444 ("team: team should sync the port's uc/mc addrs when add a port")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 56c701b73c12..befed2d22bf4 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1197,11 +1197,6 @@ static int team_port_add(struct team *team, struct net_device *port_dev)
 		goto err_dev_open;
 	}
 
-	netif_addr_lock_bh(dev);
-	dev_uc_sync_multiple(port_dev, dev);
-	dev_mc_sync_multiple(port_dev, dev);
-	netif_addr_unlock_bh(dev);
-
 	err = vlan_vids_add_by_dev(port_dev, dev);
 	if (err) {
 		netdev_err(dev, "Failed to add vlan ids to device %s\n",
@@ -1241,6 +1236,11 @@ static int team_port_add(struct team *team, struct net_device *port_dev)
 		goto err_option_port_add;
 	}
 
+	netif_addr_lock_bh(dev);
+	dev_uc_sync_multiple(port_dev, dev);
+	dev_mc_sync_multiple(port_dev, dev);
+	netif_addr_unlock_bh(dev);
+
 	port->index = -1;
 	list_add_tail_rcu(&port->list, &team->port_list);
 	team_port_enable(team, port);
@@ -1265,8 +1265,6 @@ static int team_port_add(struct team *team, struct net_device *port_dev)
 	vlan_vids_del_by_dev(port_dev, dev);
 
 err_vids_add:
-	dev_uc_unsync(port_dev, dev);
-	dev_mc_unsync(port_dev, dev);
 	dev_close(port_dev);
 
 err_dev_open:
-- 
2.14.3


From 3af4eea7e7f7290f4502eb219053a819028a72fe Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Mon, 26 Mar 2018 16:10:23 +0800
Subject: [PATCH 47/48] vhost_net: add missing lock nesting notation

[ Upstream commit aaa3149bbee9ba9b4e6f0bd6e3e7d191edeae942 ]

We try to hold TX virtqueue mutex in vhost_net_rx_peek_head_len()
after RX virtqueue mutex is held in handle_rx(). This requires an
appropriate lock nesting notation to calm down deadlock detector.

Fixes: 0308813724606 ("vhost_net: basic polling support")
Reported-by: syzbot+7f073540b1384a614e09@syzkaller.appspotmail.com
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/net.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 5636c7ca8eba..0020ae906bf9 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -618,7 +618,7 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk)
 
 	if (!len && vq->busyloop_timeout) {
 		/* Both tx vq and rx socket were polled here */
-		mutex_lock(&vq->mutex);
+		mutex_lock_nested(&vq->mutex, 1);
 		vhost_disable_notify(&net->dev, vq);
 
 		preempt_disable();
@@ -751,7 +751,7 @@ static void handle_rx(struct vhost_net *net)
 	struct iov_iter fixup;
 	__virtio16 num_buffers;
 
-	mutex_lock(&vq->mutex);
+	mutex_lock_nested(&vq->mutex, 0);
 	sock = vq->private_data;
 	if (!sock)
 		goto out;
-- 
2.14.3


From 135563401e95a9cdc35ed7d5d215bb3a3c51d38a Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Tue, 27 Mar 2018 14:41:19 +0300
Subject: [PATCH 48/48] net/mlx4_core: Fix memory leak while delete slave's
 resources

[ Upstream commit 461d5f1b59490ce0096dfda45e10038c122a7892 ]

mlx4_delete_all_resources_for_slave in resource tracker should free all
memory allocated for a slave.
While releasing memory of fs_rule, it misses releasing memory of
fs_rule->mirr_mbox.

Fixes: 78efed275117 ('net/mlx4_core: Support mirroring VF DMFS rules on both ports')
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/resource_tracker.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 606a0e0beeae..29e50f787349 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -5088,6 +5088,7 @@ static void rem_slave_fs_rule(struct mlx4_dev *dev, int slave)
 						 &tracker->res_tree[RES_FS_RULE]);
 					list_del(&fs_rule->com.list);
 					spin_unlock_irq(mlx4_tlock(dev));
+					kfree(fs_rule->mirr_mbox);
 					kfree(fs_rule);
 					state = 0;
 					break;
-- 
2.14.3


[-- Attachment #4: net_416.mbox --]
[-- Type: Application/Octet-Stream, Size: 40361 bytes --]

From 45f80d60b5e8b967510047544b2b0eded2322194 Mon Sep 17 00:00:00 2001
From: Miguel Fadon Perlines <mfadon@teldat.com>
Date: Thu, 5 Apr 2018 10:25:38 +0200
Subject: [PATCH 01/17] arp: fix arp_filter on l3slave devices

[ Upstream commit 58b35f27689b5eb514fc293c332966c226b1b6e4 ]

arp_filter performs an ip_route_output search for arp source address and
checks if output device is the same where the arp request was received,
if it is not, the arp request is not answered.

This route lookup is always done on main route table so l3slave devices
never find the proper route and arp is not answered.

Passing l3mdev_master_ifindex_rcu(dev) return value as oif fixes the
lookup for l3slave devices while maintaining same behavior for non
l3slave devices as this function returns 0 in that case.

Fixes: 613d09b30f8b ("net: Use VRF device index for lookups on TX")
Signed-off-by: Miguel Fadon Perlines <mfadon@teldat.com>
Acked-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/arp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index f28f06c91ead..7333db17c581 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -437,7 +437,7 @@ static int arp_filter(__be32 sip, __be32 tip, struct net_device *dev)
 	/*unsigned long now; */
 	struct net *net = dev_net(dev);
 
-	rt = ip_route_output(net, sip, tip, 0, 0);
+	rt = ip_route_output(net, sip, tip, 0, l3mdev_master_ifindex_rcu(dev));
 	if (IS_ERR(rt))
 		return 1;
 	if (rt->dst.dev != dev) {
-- 
2.14.3


From ff06d77b60ee77c51d2581f8ab05b2456ad56c9e Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sat, 7 Apr 2018 20:37:40 +0200
Subject: [PATCH 02/17] net: dsa: Discard frames from unused ports

[ Upstream commit fc5f33768cca7144f8d793205b229d46740d183b ]

The Marvell switches under some conditions will pass a frame to the
host with the port being the CPU port. Such frames are invalid, and
should be dropped. Not dropping them can result in a crash when
incrementing the receive statistics for an invalid port.

Reported-by: Chris Healy <cphealy@gmail.com>
Fixes: 91da11f870f0 ("net: Distributed Switch Architecture protocol support")
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/dsa_priv.h | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index 70de7895e5b8..053731473c99 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -126,6 +126,7 @@ static inline struct net_device *dsa_master_find_slave(struct net_device *dev,
 	struct dsa_port *cpu_dp = dev->dsa_ptr;
 	struct dsa_switch_tree *dst = cpu_dp->dst;
 	struct dsa_switch *ds;
+	struct dsa_port *slave_port;
 
 	if (device < 0 || device >= DSA_MAX_SWITCHES)
 		return NULL;
@@ -137,7 +138,12 @@ static inline struct net_device *dsa_master_find_slave(struct net_device *dev,
 	if (port < 0 || port >= ds->num_ports)
 		return NULL;
 
-	return ds->ports[port].slave;
+	slave_port = &ds->ports[port];
+
+	if (unlikely(slave_port->type != DSA_PORT_TYPE_USER))
+		return NULL;
+
+	return slave_port->slave;
 }
 
 /* port.c */
-- 
2.14.3


From 17f8e5490c0ae1dbb0f78ec229f0d259140c70eb Mon Sep 17 00:00:00 2001
From: Jeff Barnhill <0xeffeff@gmail.com>
Date: Thu, 5 Apr 2018 21:29:47 +0000
Subject: [PATCH 03/17] net/ipv6: Increment OUTxxx counters after netfilter
 hook

[ Upstream commit 71a1c915238c970cd9bdd5bf158b1279d6b6d55b ]

At the end of ip6_forward(), IPSTATS_MIB_OUTFORWDATAGRAMS and
IPSTATS_MIB_OUTOCTETS are incremented immediately before the NF_HOOK call
for NFPROTO_IPV6 / NF_INET_FORWARD.  As a result, these counters get
incremented regardless of whether or not the netfilter hook allows the
packet to continue being processed.  This change increments the counters
in ip6_forward_finish() so that it will not happen if the netfilter hook
chooses to terminate the packet, which is similar to how IPv4 works.

Signed-off-by: Jeff Barnhill <0xeffeff@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_output.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 5cb18c8ba9b2..4065ae0c32a0 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -375,6 +375,11 @@ static int ip6_forward_proxy_check(struct sk_buff *skb)
 static inline int ip6_forward_finish(struct net *net, struct sock *sk,
 				     struct sk_buff *skb)
 {
+	struct dst_entry *dst = skb_dst(skb);
+
+	__IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS);
+	__IP6_ADD_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTOCTETS, skb->len);
+
 	return dst_output(net, sk, skb);
 }
 
@@ -569,8 +574,6 @@ int ip6_forward(struct sk_buff *skb)
 
 	hdr->hop_limit--;
 
-	__IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS);
-	__IP6_ADD_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTOCTETS, skb->len);
 	return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD,
 		       net, NULL, skb, skb->dev, dst->dev,
 		       ip6_forward_finish);
-- 
2.14.3


From 62ab1eb25b4e027313e57de76c11ce727e034cc5 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Fri, 6 Apr 2018 01:19:37 +0200
Subject: [PATCH 04/17] net/sched: fix NULL dereference in the error path of
 tcf_bpf_init()

[ Upstream commit 3239534a79ee6f20cffd974173a1e62e0730e8ac ]

when tcf_bpf_init_from_ops() fails (e.g. because of program having invalid
number of instructions), tcf_bpf_cfg_cleanup() calls bpf_prog_put(NULL) or
bpf_prog_destroy(NULL). Unless CONFIG_BPF_SYSCALL is unset, this causes
the following error:

 BUG: unable to handle kernel NULL pointer dereference at 0000000000000020
 PGD 800000007345a067 P4D 800000007345a067 PUD 340e1067 PMD 0
 Oops: 0000 [#1] SMP PTI
 Modules linked in: act_bpf(E) ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 mbcache jbd2 crct10dif_pclmul crc32_pclmul ghash_clmulni_intel snd_hda_codec_generic pcbc snd_hda_intel snd_hda_codec snd_hda_core snd_hwdep snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd glue_helper cryptd joydev snd_timer snd virtio_balloon pcspkr soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm virtio_blk drm virtio_net virtio_console i2c_core crc32c_intel serio_raw virtio_pci ata_piix libata virtio_ring floppy virtio dm_mirror dm_region_hash dm_log dm_mod [last unloaded: act_bpf]
 CPU: 3 PID: 5654 Comm: tc Tainted: G            E    4.16.0.bpf_test+ #408
 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
 RIP: 0010:__bpf_prog_put+0xc/0xc0
 RSP: 0018:ffff9594003ef728 EFLAGS: 00010202
 RAX: 0000000000000000 RBX: ffff9594003ef758 RCX: 0000000000000024
 RDX: 0000000000000000 RSI: 0000000000000001 RDI: 0000000000000000
 RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000044
 R10: 0000000000000220 R11: ffff8a7ab9f17131 R12: 0000000000000000
 R13: ffff8a7ab7c3c8e0 R14: 0000000000000001 R15: ffff8a7ab88f1054
 FS:  00007fcb2f17c740(0000) GS:ffff8a7abfd80000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000000020 CR3: 000000007c888006 CR4: 00000000001606e0
 Call Trace:
  tcf_bpf_cfg_cleanup+0x2f/0x40 [act_bpf]
  tcf_bpf_cleanup+0x4c/0x70 [act_bpf]
  __tcf_idr_release+0x79/0x140
  tcf_bpf_init+0x125/0x330 [act_bpf]
  tcf_action_init_1+0x2cc/0x430
  ? get_page_from_freelist+0x3f0/0x11b0
  tcf_action_init+0xd3/0x1b0
  tc_ctl_action+0x18b/0x240
  rtnetlink_rcv_msg+0x29c/0x310
  ? _cond_resched+0x15/0x30
  ? __kmalloc_node_track_caller+0x1b9/0x270
  ? rtnl_calcit.isra.29+0x100/0x100
  netlink_rcv_skb+0xd2/0x110
  netlink_unicast+0x17c/0x230
  netlink_sendmsg+0x2cd/0x3c0
  sock_sendmsg+0x30/0x40
  ___sys_sendmsg+0x27a/0x290
  ? mem_cgroup_commit_charge+0x80/0x130
  ? page_add_new_anon_rmap+0x73/0xc0
  ? do_anonymous_page+0x2a2/0x560
  ? __handle_mm_fault+0xc75/0xe20
  __sys_sendmsg+0x58/0xa0
  do_syscall_64+0x6e/0x1a0
  entry_SYSCALL_64_after_hwframe+0x3d/0xa2
 RIP: 0033:0x7fcb2e58eba0
 RSP: 002b:00007ffc93c496c8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
 RAX: ffffffffffffffda RBX: 00007ffc93c497f0 RCX: 00007fcb2e58eba0
 RDX: 0000000000000000 RSI: 00007ffc93c49740 RDI: 0000000000000003
 RBP: 000000005ac6a646 R08: 0000000000000002 R09: 0000000000000000
 R10: 00007ffc93c49120 R11: 0000000000000246 R12: 0000000000000000
 R13: 00007ffc93c49804 R14: 0000000000000001 R15: 000000000066afa0
 Code: 5f 00 48 8b 43 20 48 c7 c7 70 2f 7c b8 c7 40 10 00 00 00 00 5b e9 a5 8b 61 00 0f 1f 44 00 00 0f 1f 44 00 00 41 54 55 48 89 fd 53 <48> 8b 47 20 f0 ff 08 74 05 5b 5d 41 5c c3 41 89 f4 0f 1f 44 00
 RIP: __bpf_prog_put+0xc/0xc0 RSP: ffff9594003ef728
 CR2: 0000000000000020

Fix it in tcf_bpf_cfg_cleanup(), ensuring that bpf_prog_{put,destroy}(f)
is called only when f is not NULL.

Fixes: bbc09e7842a5 ("net/sched: fix idr leak on the error path of tcf_bpf_init()")
Reported-by: Lucas Bates <lucasb@mojatatu.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_bpf.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 9d2cabf1dc7e..f3eee5326307 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -248,10 +248,14 @@ static int tcf_bpf_init_from_efd(struct nlattr **tb, struct tcf_bpf_cfg *cfg)
 
 static void tcf_bpf_cfg_cleanup(const struct tcf_bpf_cfg *cfg)
 {
-	if (cfg->is_ebpf)
-		bpf_prog_put(cfg->filter);
-	else
-		bpf_prog_destroy(cfg->filter);
+	struct bpf_prog *filter = cfg->filter;
+
+	if (filter) {
+		if (cfg->is_ebpf)
+			bpf_prog_put(filter);
+		else
+			bpf_prog_destroy(filter);
+	}
 
 	kfree(cfg->bpf_ops);
 	kfree(cfg->bpf_name);
-- 
2.14.3


From 904f7826ccb999ee1cf708ebed5ab192c8ec1611 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 2 Apr 2018 18:48:37 -0700
Subject: [PATCH 05/17] pptp: remove a buggy dst release in pptp_connect()

[ Upstream commit bfacfb457b36911a10140b8cb3ce76a74883ac5a ]

Once dst has been cached in socket via sk_setup_caps(),
it is illegal to call ip_rt_put() (or dst_release()),
since sk_setup_caps() did not change dst refcount.

We can still dereference it since we hold socket lock.

Caugth by syzbot :

BUG: KASAN: use-after-free in atomic_dec_return include/asm-generic/atomic-instrumented.h:198 [inline]
BUG: KASAN: use-after-free in dst_release+0x27/0xa0 net/core/dst.c:185
Write of size 4 at addr ffff8801c54dc040 by task syz-executor4/20088

CPU: 1 PID: 20088 Comm: syz-executor4 Not tainted 4.16.0+ #376
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x1a7/0x27d lib/dump_stack.c:53
 print_address_description+0x73/0x250 mm/kasan/report.c:256
 kasan_report_error mm/kasan/report.c:354 [inline]
 kasan_report+0x23c/0x360 mm/kasan/report.c:412
 check_memory_region_inline mm/kasan/kasan.c:260 [inline]
 check_memory_region+0x137/0x190 mm/kasan/kasan.c:267
 kasan_check_write+0x14/0x20 mm/kasan/kasan.c:278
 atomic_dec_return include/asm-generic/atomic-instrumented.h:198 [inline]
 dst_release+0x27/0xa0 net/core/dst.c:185
 sk_dst_set include/net/sock.h:1812 [inline]
 sk_dst_reset include/net/sock.h:1824 [inline]
 sock_setbindtodevice net/core/sock.c:610 [inline]
 sock_setsockopt+0x431/0x1b20 net/core/sock.c:707
 SYSC_setsockopt net/socket.c:1845 [inline]
 SyS_setsockopt+0x2ff/0x360 net/socket.c:1828
 do_syscall_64+0x281/0x940 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x42/0xb7
RIP: 0033:0x4552d9
RSP: 002b:00007f4878126c68 EFLAGS: 00000246 ORIG_RAX: 0000000000000036
RAX: ffffffffffffffda RBX: 00007f48781276d4 RCX: 00000000004552d9
RDX: 0000000000000019 RSI: 0000000000000001 RDI: 0000000000000013
RBP: 000000000072bea0 R08: 0000000000000010 R09: 0000000000000000
R10: 00000000200010c0 R11: 0000000000000246 R12: 00000000ffffffff
R13: 0000000000000526 R14: 00000000006fac30 R15: 0000000000000000

Allocated by task 20088:
 save_stack+0x43/0xd0 mm/kasan/kasan.c:447
 set_track mm/kasan/kasan.c:459 [inline]
 kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:552
 kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:489
 kmem_cache_alloc+0x12e/0x760 mm/slab.c:3542
 dst_alloc+0x11f/0x1a0 net/core/dst.c:104
 rt_dst_alloc+0xe9/0x540 net/ipv4/route.c:1520
 __mkroute_output net/ipv4/route.c:2265 [inline]
 ip_route_output_key_hash_rcu+0xa49/0x2c60 net/ipv4/route.c:2493
 ip_route_output_key_hash+0x20b/0x370 net/ipv4/route.c:2322
 __ip_route_output_key include/net/route.h:126 [inline]
 ip_route_output_flow+0x26/0xa0 net/ipv4/route.c:2577
 ip_route_output_ports include/net/route.h:163 [inline]
 pptp_connect+0xa84/0x1170 drivers/net/ppp/pptp.c:453
 SYSC_connect+0x213/0x4a0 net/socket.c:1639
 SyS_connect+0x24/0x30 net/socket.c:1620
 do_syscall_64+0x281/0x940 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x42/0xb7

Freed by task 20082:
 save_stack+0x43/0xd0 mm/kasan/kasan.c:447
 set_track mm/kasan/kasan.c:459 [inline]
 __kasan_slab_free+0x11a/0x170 mm/kasan/kasan.c:520
 kasan_slab_free+0xe/0x10 mm/kasan/kasan.c:527
 __cache_free mm/slab.c:3486 [inline]
 kmem_cache_free+0x83/0x2a0 mm/slab.c:3744
 dst_destroy+0x266/0x380 net/core/dst.c:140
 dst_destroy_rcu+0x16/0x20 net/core/dst.c:153
 __rcu_reclaim kernel/rcu/rcu.h:178 [inline]
 rcu_do_batch kernel/rcu/tree.c:2675 [inline]
 invoke_rcu_callbacks kernel/rcu/tree.c:2930 [inline]
 __rcu_process_callbacks kernel/rcu/tree.c:2897 [inline]
 rcu_process_callbacks+0xd6c/0x17b0 kernel/rcu/tree.c:2914
 __do_softirq+0x2d7/0xb85 kernel/softirq.c:285

The buggy address belongs to the object at ffff8801c54dc000
 which belongs to the cache ip_dst_cache of size 168
The buggy address is located 64 bytes inside of
 168-byte region [ffff8801c54dc000, ffff8801c54dc0a8)
The buggy address belongs to the page:
page:ffffea0007153700 count:1 mapcount:0 mapping:ffff8801c54dc000 index:0x0
flags: 0x2fffc0000000100(slab)
raw: 02fffc0000000100 ffff8801c54dc000 0000000000000000 0000000100000010
raw: ffffea0006b34b20 ffffea0006b6c1e0 ffff8801d674a1c0 0000000000000000
page dumped because: kasan: bad access detected

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pptp.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index 6dde9a0cfe76..9b70a3af678e 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -464,7 +464,6 @@ static int pptp_connect(struct socket *sock, struct sockaddr *uservaddr,
 	po->chan.mtu = dst_mtu(&rt->dst);
 	if (!po->chan.mtu)
 		po->chan.mtu = PPP_MRU;
-	ip_rt_put(rt);
 	po->chan.mtu -= PPTP_HEADER_OVERHEAD;
 
 	po->chan.hdrlen = 2 + sizeof(struct pptp_gre_header);
-- 
2.14.3


From 06e079c65bb32dcb2fb2f71954f1dbd086c2a909 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 7 Apr 2018 17:15:22 -0700
Subject: [PATCH 06/17] sctp: do not leak kernel memory to user space

[ Upstream commit 6780db244d6b1537d139dea0ec8aad10cf9e4adb ]

syzbot produced a nice report [1]

Issue here is that a recvmmsg() managed to leak 8 bytes of kernel memory
to user space, because sin_zero (padding field) was not properly cleared.

[1]
BUG: KMSAN: uninit-value in copy_to_user include/linux/uaccess.h:184 [inline]
BUG: KMSAN: uninit-value in move_addr_to_user+0x32e/0x530 net/socket.c:227
CPU: 1 PID: 3586 Comm: syzkaller481044 Not tainted 4.16.0+ #82
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x185/0x1d0 lib/dump_stack.c:53
 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067
 kmsan_internal_check_memory+0x164/0x1d0 mm/kmsan/kmsan.c:1176
 kmsan_copy_to_user+0x69/0x160 mm/kmsan/kmsan.c:1199
 copy_to_user include/linux/uaccess.h:184 [inline]
 move_addr_to_user+0x32e/0x530 net/socket.c:227
 ___sys_recvmsg+0x4e2/0x810 net/socket.c:2211
 __sys_recvmmsg+0x54e/0xdb0 net/socket.c:2313
 SYSC_recvmmsg+0x29b/0x3e0 net/socket.c:2394
 SyS_recvmmsg+0x76/0xa0 net/socket.c:2378
 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x3d/0xa2
RIP: 0033:0x4401c9
RSP: 002b:00007ffc56f73098 EFLAGS: 00000217 ORIG_RAX: 000000000000012b
RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 00000000004401c9
RDX: 0000000000000001 RSI: 0000000020003ac0 RDI: 0000000000000003
RBP: 00000000006ca018 R08: 0000000020003bc0 R09: 0000000000000010
R10: 0000000000000000 R11: 0000000000000217 R12: 0000000000401af0
R13: 0000000000401b80 R14: 0000000000000000 R15: 0000000000000000

Local variable description: ----addr@___sys_recvmsg
Variable was created at:
 ___sys_recvmsg+0xd5/0x810 net/socket.c:2172
 __sys_recvmmsg+0x54e/0xdb0 net/socket.c:2313

Bytes 8-15 of 16 are uninitialized

==================================================================
Kernel panic - not syncing: panic_on_warn set ...

CPU: 1 PID: 3586 Comm: syzkaller481044 Tainted: G    B            4.16.0+ #82
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x185/0x1d0 lib/dump_stack.c:53
 panic+0x39d/0x940 kernel/panic.c:183
 kmsan_report+0x238/0x240 mm/kmsan/kmsan.c:1083
 kmsan_internal_check_memory+0x164/0x1d0 mm/kmsan/kmsan.c:1176
 kmsan_copy_to_user+0x69/0x160 mm/kmsan/kmsan.c:1199
 copy_to_user include/linux/uaccess.h:184 [inline]
 move_addr_to_user+0x32e/0x530 net/socket.c:227
 ___sys_recvmsg+0x4e2/0x810 net/socket.c:2211
 __sys_recvmmsg+0x54e/0xdb0 net/socket.c:2313
 SYSC_recvmmsg+0x29b/0x3e0 net/socket.c:2394
 SyS_recvmmsg+0x76/0xa0 net/socket.c:2378
 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x3d/0xa2

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc:	Vlad Yasevich <vyasevich@gmail.com>
Cc:	Neil Horman <nhorman@tuxdriver.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ipv6.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index e35d4f73d2df..f6d3d0c1e133 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -728,8 +728,10 @@ static int sctp_v6_addr_to_user(struct sctp_sock *sp, union sctp_addr *addr)
 			sctp_v6_map_v4(addr);
 	}
 
-	if (addr->sa.sa_family == AF_INET)
+	if (addr->sa.sa_family == AF_INET) {
+		memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
 		return sizeof(struct sockaddr_in);
+	}
 	return sizeof(struct sockaddr_in6);
 }
 
-- 
2.14.3


From ad92ef845f2b8ed59b1a14f94df8bf6ff876aae4 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 8 Apr 2018 07:52:08 -0700
Subject: [PATCH 07/17] sctp: sctp_sockaddr_af must check minimal addr length
 for AF_INET6

[ Upstream commit 81e98370293afcb58340ce8bd71af7b97f925c26 ]

Check must happen before call to ipv6_addr_v4mapped()

syzbot report was :

BUG: KMSAN: uninit-value in sctp_sockaddr_af net/sctp/socket.c:359 [inline]
BUG: KMSAN: uninit-value in sctp_do_bind+0x60f/0xdc0 net/sctp/socket.c:384
CPU: 0 PID: 3576 Comm: syzkaller968804 Not tainted 4.16.0+ #82
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x185/0x1d0 lib/dump_stack.c:53
 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067
 __msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:676
 sctp_sockaddr_af net/sctp/socket.c:359 [inline]
 sctp_do_bind+0x60f/0xdc0 net/sctp/socket.c:384
 sctp_bind+0x149/0x190 net/sctp/socket.c:332
 inet6_bind+0x1fd/0x1820 net/ipv6/af_inet6.c:293
 SYSC_bind+0x3f2/0x4b0 net/socket.c:1474
 SyS_bind+0x54/0x80 net/socket.c:1460
 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x3d/0xa2
RIP: 0033:0x43fd49
RSP: 002b:00007ffe99df3d28 EFLAGS: 00000213 ORIG_RAX: 0000000000000031
RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 000000000043fd49
RDX: 0000000000000010 RSI: 0000000020000000 RDI: 0000000000000003
RBP: 00000000006ca018 R08: 00000000004002c8 R09: 00000000004002c8
R10: 00000000004002c8 R11: 0000000000000213 R12: 0000000000401670
R13: 0000000000401700 R14: 0000000000000000 R15: 0000000000000000

Local variable description: ----address@SYSC_bind
Variable was created at:
 SYSC_bind+0x6f/0x4b0 net/socket.c:1461
 SyS_bind+0x54/0x80 net/socket.c:1460

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Vlad Yasevich <vyasevich@gmail.com>
Cc: Neil Horman <nhorman@tuxdriver.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index bf271f8c2dc9..7160c2e9b768 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -354,11 +354,14 @@ static struct sctp_af *sctp_sockaddr_af(struct sctp_sock *opt,
 	if (!opt->pf->af_supported(addr->sa.sa_family, opt))
 		return NULL;
 
-	/* V4 mapped address are really of AF_INET family */
-	if (addr->sa.sa_family == AF_INET6 &&
-	    ipv6_addr_v4mapped(&addr->v6.sin6_addr) &&
-	    !opt->pf->af_supported(AF_INET, opt))
-		return NULL;
+	if (addr->sa.sa_family == AF_INET6) {
+		if (len < SIN6_LEN_RFC2133)
+			return NULL;
+		/* V4 mapped address are really of AF_INET family */
+		if (ipv6_addr_v4mapped(&addr->v6.sin6_addr) &&
+		    !opt->pf->af_supported(AF_INET, opt))
+			return NULL;
+	}
 
 	/* If we get this far, af is valid. */
 	af = sctp_get_af_specific(addr->sa.sa_family);
-- 
2.14.3


From 28e8ba71d327d89c20538527ad327f2a6b516fae Mon Sep 17 00:00:00 2001
From: Kai-Heng Feng <kai.heng.feng@canonical.com>
Date: Sat, 31 Mar 2018 23:42:03 +0800
Subject: [PATCH 08/17] sky2: Increase D3 delay to sky2 stops working after
 suspend

[ Upstream commit afb133637071be6deeb8b3d0e55593ffbf63c527 ]

The sky2 ethernet stops working after system resume from suspend:
[ 582.852065] sky2 0000:04:00.0: Refused to change power state, currently in D3

The current 150ms delay is not enough, change it to 200ms can solve the
issue.

BugLink: https://bugs.launchpad.net/bugs/1758507
Cc: Stable <stable@vger.kernel.org>
Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/sky2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index 9fe85300e7b6..5754116a6a4d 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -5087,7 +5087,7 @@ static int sky2_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	INIT_WORK(&hw->restart_work, sky2_restart);
 
 	pci_set_drvdata(pdev, hw);
-	pdev->d3_delay = 150;
+	pdev->d3_delay = 200;
 
 	return 0;
 
-- 
2.14.3


From 2303f4306f36e878468a45fd943874c5f109b73f Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Fri, 30 Mar 2018 09:44:00 +0800
Subject: [PATCH 09/17] vlan: also check phy_driver ts_info for vlan's real
 device

[ Upstream commit ec1d8ccb07deaf30fd0508af6755364ac47dc08d ]

Just like function ethtool_get_ts_info(), we should also consider the
phy_driver ts_info call back. For example, driver dp83640.

Fixes: 37dd9255b2f6 ("vlan: Pass ethtool get_ts_info queries to real device.")
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/8021q/vlan_dev.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index f7e83f6d2e64..236452ebbd9e 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -29,6 +29,7 @@
 #include <linux/net_tstamp.h>
 #include <linux/etherdevice.h>
 #include <linux/ethtool.h>
+#include <linux/phy.h>
 #include <net/arp.h>
 #include <net/switchdev.h>
 
@@ -665,8 +666,11 @@ static int vlan_ethtool_get_ts_info(struct net_device *dev,
 {
 	const struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
 	const struct ethtool_ops *ops = vlan->real_dev->ethtool_ops;
+	struct phy_device *phydev = vlan->real_dev->phydev;
 
-	if (ops->get_ts_info) {
+	if (phydev && phydev->drv && phydev->drv->ts_info) {
+		 return phydev->drv->ts_info(phydev, info);
+	} else if (ops->get_ts_info) {
 		return ops->get_ts_info(vlan->real_dev, info);
 	} else {
 		info->so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE |
-- 
2.14.3


From b74c7da728362168047fdb1c3bad29add36def34 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 5 Apr 2018 06:39:26 -0700
Subject: [PATCH 10/17] net: fool proof dev_valid_name()

[ Upstream commit a9d48205d0aedda021fc3728972a9e9934c2b9de ]

We want to use dev_valid_name() to validate tunnel names,
so better use strnlen(name, IFNAMSIZ) than strlen(name) to make
sure to not upset KASAN.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index ef0cc6ea5f8d..c4aa2941dbfd 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1027,7 +1027,7 @@ bool dev_valid_name(const char *name)
 {
 	if (*name == '\0')
 		return false;
-	if (strlen(name) >= IFNAMSIZ)
+	if (strnlen(name, IFNAMSIZ) == IFNAMSIZ)
 		return false;
 	if (!strcmp(name, ".") || !strcmp(name, ".."))
 		return false;
-- 
2.14.3


From 2c5d3e92209e7f5b4f29ba6ed9c8d8bfb971bfc5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 5 Apr 2018 06:39:27 -0700
Subject: [PATCH 11/17] ip_tunnel: better validate user provided tunnel names

[ Upstream commit 9cb726a212a82c88c98aa9f0037fd04777cd8fe5 ]

Use dev_valid_name() to make sure user does not provide illegal
device name.

syzbot caught the following bug :

BUG: KASAN: stack-out-of-bounds in strlcpy include/linux/string.h:300 [inline]
BUG: KASAN: stack-out-of-bounds in __ip_tunnel_create+0xca/0x6b0 net/ipv4/ip_tunnel.c:257
Write of size 20 at addr ffff8801ac79f810 by task syzkaller268107/4482

CPU: 0 PID: 4482 Comm: syzkaller268107 Not tainted 4.16.0+ #1
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x1b9/0x29f lib/dump_stack.c:53
 print_address_description+0x6c/0x20b mm/kasan/report.c:256
 kasan_report_error mm/kasan/report.c:354 [inline]
 kasan_report.cold.7+0xac/0x2f5 mm/kasan/report.c:412
 check_memory_region_inline mm/kasan/kasan.c:260 [inline]
 check_memory_region+0x13e/0x1b0 mm/kasan/kasan.c:267
 memcpy+0x37/0x50 mm/kasan/kasan.c:303
 strlcpy include/linux/string.h:300 [inline]
 __ip_tunnel_create+0xca/0x6b0 net/ipv4/ip_tunnel.c:257
 ip_tunnel_create net/ipv4/ip_tunnel.c:352 [inline]
 ip_tunnel_ioctl+0x818/0xd40 net/ipv4/ip_tunnel.c:861
 ipip_tunnel_ioctl+0x1c5/0x420 net/ipv4/ipip.c:350
 dev_ifsioc+0x43e/0xb90 net/core/dev_ioctl.c:334
 dev_ioctl+0x69a/0xcc0 net/core/dev_ioctl.c:525
 sock_ioctl+0x47e/0x680 net/socket.c:1015
 vfs_ioctl fs/ioctl.c:46 [inline]
 file_ioctl fs/ioctl.c:500 [inline]
 do_vfs_ioctl+0x1cf/0x1650 fs/ioctl.c:684
 ksys_ioctl+0xa9/0xd0 fs/ioctl.c:701
 SYSC_ioctl fs/ioctl.c:708 [inline]
 SyS_ioctl+0x24/0x30 fs/ioctl.c:706
 do_syscall_64+0x29e/0x9d0 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x42/0xb7

Fixes: c54419321455 ("GRE: Refactor GRE tunneling code.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_tunnel.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index a7fd1c5a2a14..57478d68248d 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -253,13 +253,14 @@ static struct net_device *__ip_tunnel_create(struct net *net,
 	struct net_device *dev;
 	char name[IFNAMSIZ];
 
-	if (parms->name[0])
+	err = -E2BIG;
+	if (parms->name[0]) {
+		if (!dev_valid_name(parms->name))
+			goto failed;
 		strlcpy(name, parms->name, IFNAMSIZ);
-	else {
-		if (strlen(ops->kind) > (IFNAMSIZ - 3)) {
-			err = -E2BIG;
+	} else {
+		if (strlen(ops->kind) > (IFNAMSIZ - 3))
 			goto failed;
-		}
 		strlcpy(name, ops->kind, IFNAMSIZ);
 		strncat(name, "%d", 2);
 	}
-- 
2.14.3


From 9861149db76c49f1459233ef722da660339bba2c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 5 Apr 2018 06:39:28 -0700
Subject: [PATCH 12/17] ipv6: sit: better validate user provided tunnel names

[ Upstream commit b95211e066fc3494b7c115060b2297b4ba21f025 ]

Use dev_valid_name() to make sure user does not provide illegal
device name.

syzbot caught the following bug :

BUG: KASAN: stack-out-of-bounds in strlcpy include/linux/string.h:300 [inline]
BUG: KASAN: stack-out-of-bounds in ipip6_tunnel_locate+0x63b/0xaa0 net/ipv6/sit.c:254
Write of size 33 at addr ffff8801b64076d8 by task syzkaller932654/4453

CPU: 0 PID: 4453 Comm: syzkaller932654 Not tainted 4.16.0+ #1
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x1b9/0x29f lib/dump_stack.c:53
 print_address_description+0x6c/0x20b mm/kasan/report.c:256
 kasan_report_error mm/kasan/report.c:354 [inline]
 kasan_report.cold.7+0xac/0x2f5 mm/kasan/report.c:412
 check_memory_region_inline mm/kasan/kasan.c:260 [inline]
 check_memory_region+0x13e/0x1b0 mm/kasan/kasan.c:267
 memcpy+0x37/0x50 mm/kasan/kasan.c:303
 strlcpy include/linux/string.h:300 [inline]
 ipip6_tunnel_locate+0x63b/0xaa0 net/ipv6/sit.c:254
 ipip6_tunnel_ioctl+0xe71/0x241b net/ipv6/sit.c:1221
 dev_ifsioc+0x43e/0xb90 net/core/dev_ioctl.c:334
 dev_ioctl+0x69a/0xcc0 net/core/dev_ioctl.c:525
 sock_ioctl+0x47e/0x680 net/socket.c:1015
 vfs_ioctl fs/ioctl.c:46 [inline]
 file_ioctl fs/ioctl.c:500 [inline]
 do_vfs_ioctl+0x1cf/0x1650 fs/ioctl.c:684
 ksys_ioctl+0xa9/0xd0 fs/ioctl.c:701
 SYSC_ioctl fs/ioctl.c:708 [inline]
 SyS_ioctl+0x24/0x30 fs/ioctl.c:706
 do_syscall_64+0x29e/0x9d0 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x42/0xb7

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 0195598f7bb5..e85791854c87 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -250,11 +250,13 @@ static struct ip_tunnel *ipip6_tunnel_locate(struct net *net,
 	if (!create)
 		goto failed;
 
-	if (parms->name[0])
+	if (parms->name[0]) {
+		if (!dev_valid_name(parms->name))
+			goto failed;
 		strlcpy(name, parms->name, IFNAMSIZ);
-	else
+	} else {
 		strcpy(name, "sit%d");
-
+	}
 	dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN,
 			   ipip6_tunnel_setup);
 	if (!dev)
-- 
2.14.3


From e7585284f1990a041cd13822eae001ed27dc11b0 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 5 Apr 2018 06:39:29 -0700
Subject: [PATCH 13/17] ip6_gre: better validate user provided tunnel names

[ Upstream commit 5f42df013b8bc1b6511af7a04bf93b014884ae2a ]

Use dev_valid_name() to make sure user does not provide illegal
device name.

syzbot caught the following bug :

BUG: KASAN: stack-out-of-bounds in strlcpy include/linux/string.h:300 [inline]
BUG: KASAN: stack-out-of-bounds in ip6gre_tunnel_locate+0x334/0x860 net/ipv6/ip6_gre.c:339
Write of size 20 at addr ffff8801afb9f7b8 by task syzkaller851048/4466

CPU: 1 PID: 4466 Comm: syzkaller851048 Not tainted 4.16.0+ #1
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x1b9/0x29f lib/dump_stack.c:53
 print_address_description+0x6c/0x20b mm/kasan/report.c:256
 kasan_report_error mm/kasan/report.c:354 [inline]
 kasan_report.cold.7+0xac/0x2f5 mm/kasan/report.c:412
 check_memory_region_inline mm/kasan/kasan.c:260 [inline]
 check_memory_region+0x13e/0x1b0 mm/kasan/kasan.c:267
 memcpy+0x37/0x50 mm/kasan/kasan.c:303
 strlcpy include/linux/string.h:300 [inline]
 ip6gre_tunnel_locate+0x334/0x860 net/ipv6/ip6_gre.c:339
 ip6gre_tunnel_ioctl+0x69d/0x12e0 net/ipv6/ip6_gre.c:1195
 dev_ifsioc+0x43e/0xb90 net/core/dev_ioctl.c:334
 dev_ioctl+0x69a/0xcc0 net/core/dev_ioctl.c:525
 sock_ioctl+0x47e/0x680 net/socket.c:1015
 vfs_ioctl fs/ioctl.c:46 [inline]
 file_ioctl fs/ioctl.c:500 [inline]
 do_vfs_ioctl+0x1cf/0x1650 fs/ioctl.c:684
 ksys_ioctl+0xa9/0xd0 fs/ioctl.c:701
 SYSC_ioctl fs/ioctl.c:708 [inline]
 SyS_ioctl+0x24/0x30 fs/ioctl.c:706
 do_syscall_64+0x29e/0x9d0 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x42/0xb7

Fixes: c12b395a4664 ("gre: Support GRE over IPv6")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 1bbd0930063e..197fcae855ca 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -335,11 +335,13 @@ static struct ip6_tnl *ip6gre_tunnel_locate(struct net *net,
 	if (t || !create)
 		return t;
 
-	if (parms->name[0])
+	if (parms->name[0]) {
+		if (!dev_valid_name(parms->name))
+			return NULL;
 		strlcpy(name, parms->name, IFNAMSIZ);
-	else
+	} else {
 		strcpy(name, "ip6gre%d");
-
+	}
 	dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN,
 			   ip6gre_tunnel_setup);
 	if (!dev)
-- 
2.14.3


From 62252493f37cf34615d9f6a729dfe3da45079aae Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 5 Apr 2018 06:39:30 -0700
Subject: [PATCH 14/17] ip6_tunnel: better validate user provided tunnel names

[ Upstream commit db7a65e3ab78e5b1c4b17c0870ebee35a4ee3257 ]

Use valid_name() to make sure user does not provide illegal
device name.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 6e0f21eed88a..179313b0926c 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -297,13 +297,16 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p)
 	struct net_device *dev;
 	struct ip6_tnl *t;
 	char name[IFNAMSIZ];
-	int err = -ENOMEM;
+	int err = -E2BIG;
 
-	if (p->name[0])
+	if (p->name[0]) {
+		if (!dev_valid_name(p->name))
+			goto failed;
 		strlcpy(name, p->name, IFNAMSIZ);
-	else
+	} else {
 		sprintf(name, "ip6tnl%%d");
-
+	}
+	err = -ENOMEM;
 	dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN,
 			   ip6_tnl_dev_setup);
 	if (!dev)
-- 
2.14.3


From 2f963579ac0df80d61760a22ecd24bb8e61ed7ba Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 5 Apr 2018 06:39:31 -0700
Subject: [PATCH 15/17] vti6: better validate user provided tunnel names

[ Upstream commit 537b361fbcbcc3cd6fe2bb47069fd292b9256d16 ]

Use valid_name() to make sure user does not provide illegal
device name.

Fixes: ed1efb2aefbb ("ipv6: Add support for IPsec virtual tunnel interfaces")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_vti.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index ce18cd20389d..3726dc797847 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -212,10 +212,13 @@ static struct ip6_tnl *vti6_tnl_create(struct net *net, struct __ip6_tnl_parm *p
 	char name[IFNAMSIZ];
 	int err;
 
-	if (p->name[0])
+	if (p->name[0]) {
+		if (!dev_valid_name(p->name))
+			goto failed;
 		strlcpy(name, p->name, IFNAMSIZ);
-	else
+	} else {
 		sprintf(name, "ip6_vti%%d");
+	}
 
 	dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN, vti6_dev_setup);
 	if (!dev)
-- 
2.14.3


From 31e4b7ffeb8372f584cdb5f060ef1885e3b4fefb Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Fri, 6 Apr 2018 17:19:41 -0700
Subject: [PATCH 16/17] net_sched: fix a missing idr_remove() in
 u32_delete_key()

[ Upstream commit f12c643209db0626f2f54780d86bb93bfa7a9c2d ]

When we delete a u32 key via u32_delete_key(), we forget to
call idr_remove() to remove its handle from IDR.

Fixes: e7614370d6f0 ("net_sched: use idr to allocate u32 filter handles")
Reported-by: Marcin Kabiesz <admin@hostcenter.eu>
Tested-by: Marcin Kabiesz <admin@hostcenter.eu>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_u32.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index ed8b6a24b9e9..bac47b5d18fd 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -489,6 +489,7 @@ static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key)
 				RCU_INIT_POINTER(*kp, key->next);
 
 				tcf_unbind_filter(tp, &key->res);
+				idr_remove(&ht->handle_idr, key->handle);
 				tcf_exts_get_net(&key->exts);
 				call_rcu(&key->rcu, u32_delete_key_freepf_rcu);
 				return 0;
-- 
2.14.3


From 071feedaa83185786bd3e15819bc58dedd6b4a16 Mon Sep 17 00:00:00 2001
From: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Date: Tue, 3 Apr 2018 17:24:23 -0700
Subject: [PATCH 17/17] nfp: use full 40 bits of the NSP buffer address

[ Upstream commit 1489bbd10e16079ce30a53d3c22a431fd47af791 ]

The NSP default buffer is a piece of NFP memory where additional
command data can be placed.  Its format has been copied from
host buffer, but the PCIe selection bits do not make sense in
this case.  If those get masked out from a NFP address - writes
to random place in the chip memory may be issued and crash the
device.

Even in the general NSP buffer case, it doesn't make sense to have the
PCIe selection bits there anymore. These are unused at the moment, and
when it becomes necessary, the PCIe selection bits should rather be
moved to another register to utilise more bits for the buffer address.

This has never been an issue because the buffer used to be
allocated in memory with less-than-38-bit-long address but that
is about to change.

Fixes: 1a64821c6af7 ("nfp: add support for service processor access")
Signed-off-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
index 39abac678b71..99bb679a9801 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
@@ -71,10 +71,11 @@
 /* CPP address to retrieve the data from */
 #define NSP_BUFFER		0x10
 #define   NSP_BUFFER_CPP	GENMASK_ULL(63, 40)
-#define   NSP_BUFFER_PCIE	GENMASK_ULL(39, 38)
-#define   NSP_BUFFER_ADDRESS	GENMASK_ULL(37, 0)
+#define   NSP_BUFFER_ADDRESS	GENMASK_ULL(39, 0)
 
 #define NSP_DFLT_BUFFER		0x18
+#define   NSP_DFLT_BUFFER_CPP	GENMASK_ULL(63, 40)
+#define   NSP_DFLT_BUFFER_ADDRESS	GENMASK_ULL(39, 0)
 
 #define NSP_DFLT_BUFFER_CONFIG	0x20
 #define   NSP_DFLT_BUFFER_SIZE_MB	GENMASK_ULL(7, 0)
@@ -427,8 +428,8 @@ __nfp_nsp_command_buf(struct nfp_nsp *nsp, u16 code, u32 option,
 	if (err < 0)
 		return err;
 
-	cpp_id = FIELD_GET(NSP_BUFFER_CPP, reg) << 8;
-	cpp_buf = FIELD_GET(NSP_BUFFER_ADDRESS, reg);
+	cpp_id = FIELD_GET(NSP_DFLT_BUFFER_CPP, reg) << 8;
+	cpp_buf = FIELD_GET(NSP_DFLT_BUFFER_ADDRESS, reg);
 
 	if (in_buf && in_size) {
 		err = nfp_cpp_write(cpp, cpp_id, cpp_buf, in_buf, in_size);
-- 
2.14.3

Re: [PATCHES] Networking

[Greg KH]

On Tue, Apr 10, 2018 at 03:39:19PM -0400, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.14,
> v4.15, and v4.16 -stable, respectively.

Many thanks for all of these, now queued up.

No need to worry about 4.15 anymore, it will probably go end-of-life
late next week, so unless there is something "major" needed for it, I
wouldn't worry about making patches up for it anymore.

thanks,

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 301 bytes --]


Please queue up the following networking bug fixes for v4.4 and
v4.16 -stable, respectively.

Note, you may wish to take patch "vhost: fix vhost_vq_access_ok() log check"
(upsteam d14d2b78090c7de0557362b26a4ca591aa6a9faa) for v4.15 as well
because the change it is fixing went into v4.15.17

Thanks!

[-- Attachment #2: net_414.mbox --]
[-- Type: Application/Octet-Stream, Size: 11356 bytes --]

From 12b5d735d8579d91fe967beafc0e3fb179151853 Mon Sep 17 00:00:00 2001
From: Bassem Boubaker <bassem.boubaker@actia.fr>
Date: Wed, 11 Apr 2018 13:15:53 +0200
Subject: [PATCH 1/6] cdc_ether: flag the Cinterion AHS8 modem by gemalto as
 WWAN

[ Upstream commit 53765341ee821c0a0f1dec41adc89c9096ad694c ]

The Cinterion AHS8 is a 3G device with one embedded WWAN interface
using cdc_ether as a driver.

The modem is controlled via AT commands through the exposed TTYs.

AT+CGDCONT write command can be used to activate or deactivate a WWAN
connection for a PDP context defined with the same command. UE
supports one WWAN adapter.

Signed-off-by: Bassem Boubaker <bassem.boubaker@actia.fr>
Acked-by: Oliver Neukum <oneukum@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ether.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index 05dca3e5c93d..178b956501a7 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -895,6 +895,12 @@ static const struct usb_device_id	products[] = {
 				      USB_CDC_SUBCLASS_ETHERNET,
 				      USB_CDC_PROTO_NONE),
 	.driver_info = (unsigned long)&wwan_info,
+}, {
+	/* Cinterion AHS3 modem by GEMALTO */
+	USB_DEVICE_AND_INTERFACE_INFO(0x1e2d, 0x0055, USB_CLASS_COMM,
+				      USB_CDC_SUBCLASS_ETHERNET,
+				      USB_CDC_PROTO_NONE),
+	.driver_info = (unsigned long)&wwan_info,
 }, {
 	USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ETHERNET,
 			USB_CDC_PROTO_NONE),
-- 
2.14.3


From 2d1b0dea8f2b828639eafa12384767bc29bde0ae Mon Sep 17 00:00:00 2001
From: Ka-Cheong Poon <ka-cheong.poon@oracle.com>
Date: Wed, 11 Apr 2018 00:57:25 -0700
Subject: [PATCH 2/6] rds: MP-RDS may use an invalid c_path

[ Upstream commit a43cced9a348901f9015f4730b70b69e7c41a9c9 ]

rds_sendmsg() calls rds_send_mprds_hash() to find a c_path to use to
send a message.  Suppose the RDS connection is not yet up.  In
rds_send_mprds_hash(), it does

	if (conn->c_npaths == 0)
		wait_event_interruptible(conn->c_hs_waitq,
					 (conn->c_npaths != 0));

If it is interrupted before the connection is set up,
rds_send_mprds_hash() will return a non-zero hash value.  Hence
rds_sendmsg() will use a non-zero c_path to send the message.  But if
the RDS connection ends up to be non-MP capable, the message will be
lost as only the zero c_path can be used.

Signed-off-by: Ka-Cheong Poon <ka-cheong.poon@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/send.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/net/rds/send.c b/net/rds/send.c
index f72466c63f0c..23f2d81e7967 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -986,10 +986,15 @@ static int rds_send_mprds_hash(struct rds_sock *rs, struct rds_connection *conn)
 	if (conn->c_npaths == 0 && hash != 0) {
 		rds_send_ping(conn, 0);
 
-		if (conn->c_npaths == 0) {
-			wait_event_interruptible(conn->c_hs_waitq,
-						 (conn->c_npaths != 0));
-		}
+		/* The underlying connection is not up yet.  Need to wait
+		 * until it is up to be sure that the non-zero c_path can be
+		 * used.  But if we are interrupted, we have to use the zero
+		 * c_path in case the connection ends up being non-MP capable.
+		 */
+		if (conn->c_npaths == 0)
+			if (wait_event_interruptible(conn->c_hs_waitq,
+						     conn->c_npaths != 0))
+				hash = 0;
 		if (conn->c_npaths == 1)
 			hash = 0;
 	}
-- 
2.14.3


From fe7e272727c3bc2108c6d32a0513066cdf9b649f Mon Sep 17 00:00:00 2001
From: Tejaswi Tanikella <tejaswit@codeaurora.org>
Date: Wed, 11 Apr 2018 16:34:47 +0530
Subject: [PATCH 3/6] slip: Check if rstate is initialized before uncompressing

[ Upstream commit 3f01ddb962dc506916c243f9524e8bef97119b77 ]

On receiving a packet the state index points to the rstate which must be
used to fill up IP and TCP headers. But if the state index points to a
rstate which is unitialized, i.e. filled with zeros, it gets stuck in an
infinite loop inside ip_fast_csum trying to compute the ip checsum of a
header with zero length.

89.666953:   <2> [<ffffff9dd3e94d38>] slhc_uncompress+0x464/0x468
89.666965:   <2> [<ffffff9dd3e87d88>] ppp_receive_nonmp_frame+0x3b4/0x65c
89.666978:   <2> [<ffffff9dd3e89dd4>] ppp_receive_frame+0x64/0x7e0
89.666991:   <2> [<ffffff9dd3e8a708>] ppp_input+0x104/0x198
89.667005:   <2> [<ffffff9dd3e93868>] pppopns_recv_core+0x238/0x370
89.667027:   <2> [<ffffff9dd4428fc8>] __sk_receive_skb+0xdc/0x250
89.667040:   <2> [<ffffff9dd3e939e4>] pppopns_recv+0x44/0x60
89.667053:   <2> [<ffffff9dd4426848>] __sock_queue_rcv_skb+0x16c/0x24c
89.667065:   <2> [<ffffff9dd4426954>] sock_queue_rcv_skb+0x2c/0x38
89.667085:   <2> [<ffffff9dd44f7358>] raw_rcv+0x124/0x154
89.667098:   <2> [<ffffff9dd44f7568>] raw_local_deliver+0x1e0/0x22c
89.667117:   <2> [<ffffff9dd44c8ba0>] ip_local_deliver_finish+0x70/0x24c
89.667131:   <2> [<ffffff9dd44c92f4>] ip_local_deliver+0x100/0x10c

./scripts/faddr2line vmlinux slhc_uncompress+0x464/0x468 output:
 ip_fast_csum at arch/arm64/include/asm/checksum.h:40
 (inlined by) slhc_uncompress at drivers/net/slip/slhc.c:615

Adding a variable to indicate if the current rstate is initialized. If
such a packet arrives, move to toss state.

Signed-off-by: Tejaswi Tanikella <tejaswit@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/slip/slhc.c | 5 +++++
 include/net/slhc_vj.h   | 1 +
 2 files changed, 6 insertions(+)

diff --git a/drivers/net/slip/slhc.c b/drivers/net/slip/slhc.c
index 5782733959f0..f4e93f5fc204 100644
--- a/drivers/net/slip/slhc.c
+++ b/drivers/net/slip/slhc.c
@@ -509,6 +509,10 @@ slhc_uncompress(struct slcompress *comp, unsigned char *icp, int isize)
 		if(x < 0 || x > comp->rslot_limit)
 			goto bad;
 
+		/* Check if the cstate is initialized */
+		if (!comp->rstate[x].initialized)
+			goto bad;
+
 		comp->flags &=~ SLF_TOSS;
 		comp->recv_current = x;
 	} else {
@@ -673,6 +677,7 @@ slhc_remember(struct slcompress *comp, unsigned char *icp, int isize)
 	if (cs->cs_tcp.doff > 5)
 	  memcpy(cs->cs_tcpopt, icp + ihl*4 + sizeof(struct tcphdr), (cs->cs_tcp.doff - 5) * 4);
 	cs->cs_hsize = ihl*2 + cs->cs_tcp.doff*2;
+	cs->initialized = true;
 	/* Put headers back on packet
 	 * Neither header checksum is recalculated
 	 */
diff --git a/include/net/slhc_vj.h b/include/net/slhc_vj.h
index 8716d5942b65..8fcf8908a694 100644
--- a/include/net/slhc_vj.h
+++ b/include/net/slhc_vj.h
@@ -127,6 +127,7 @@ typedef __u32 int32;
  */
 struct cstate {
 	byte_t	cs_this;	/* connection id number (xmit) */
+	bool	initialized;	/* true if initialized */
 	struct cstate *next;	/* next in ring (xmit) */
 	struct iphdr cs_ip;	/* ip/tcp hdr from most recent packet */
 	struct tcphdr cs_tcp;
-- 
2.14.3


From 91d8e890893a12d58e2a61af637999b0e968d63d Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Wed, 11 Apr 2018 10:35:40 +0800
Subject: [PATCH 4/6] vhost: fix vhost_vq_access_ok() log check

[ Upstream commit d14d2b78090c7de0557362b26a4ca591aa6a9faa ]

Commit d65026c6c62e7d9616c8ceb5a53b68bcdc050525 ("vhost: validate log
when IOTLB is enabled") introduced a regression.  The logic was
originally:

  if (vq->iotlb)
      return 1;
  return A && B;

After the patch the short-circuit logic for A was inverted:

  if (A || vq->iotlb)
      return A;
  return B;

This patch fixes the regression by rewriting the checks in the obvious
way, no longer returning A when vq->iotlb is non-NULL (which is hard to
understand).

Reported-by: syzbot+65a84dde0214b0387ccd@syzkaller.appspotmail.com
Cc: Jason Wang <jasowang@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/vhost.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index c692e0b13242..40552a043c86 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -1252,10 +1252,12 @@ static int vq_log_access_ok(struct vhost_virtqueue *vq,
 /* Caller should have vq mutex and device mutex */
 int vhost_vq_access_ok(struct vhost_virtqueue *vq)
 {
-	int ret = vq_log_access_ok(vq, vq->log_base);
+	if (!vq_log_access_ok(vq, vq->log_base))
+		return 0;
 
-	if (ret || vq->iotlb)
-		return ret;
+	/* Access validation occurs at prefetch time with IOTLB */
+	if (vq->iotlb)
+		return 1;
 
 	return vq_access_ok(vq, vq->num, vq->desc, vq->avail, vq->used);
 }
-- 
2.14.3


From f88216d97e305c920f8ae1a93de5fa6d1faf3eb6 Mon Sep 17 00:00:00 2001
From: Eric Auger <eric.auger@redhat.com>
Date: Wed, 11 Apr 2018 15:30:38 +0200
Subject: [PATCH 5/6] vhost: Fix vhost_copy_to_user()

[ Upstream commit 7ced6c98c7ab7a1f6743931e28671b833af79b1e ]

vhost_copy_to_user is used to copy vring used elements to userspace.
We should use VHOST_ADDR_USED instead of VHOST_ADDR_DESC.

Fixes: f88949138058 ("vhost: introduce O(1) vq metadata cache")
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/vhost.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 40552a043c86..8e3ca4400766 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -756,7 +756,7 @@ static int vhost_copy_to_user(struct vhost_virtqueue *vq, void __user *to,
 		struct iov_iter t;
 		void __user *uaddr = vhost_vq_meta_fetch(vq,
 				     (u64)(uintptr_t)to, size,
-				     VHOST_ADDR_DESC);
+				     VHOST_ADDR_USED);
 
 		if (uaddr)
 			return __copy_to_user(uaddr, from, size);
-- 
2.14.3


From 482f9ce44394fc2f29a7d1905d487f3cd75f4678 Mon Sep 17 00:00:00 2001
From: Phil Elwell <phil@raspberrypi.org>
Date: Wed, 11 Apr 2018 10:59:17 +0100
Subject: [PATCH 6/6] lan78xx: Correctly indicate invalid OTP

[ Upstream commit 4bfc33807a9a02764bdd1e42e794b3b401240f27 ]

lan78xx_read_otp tries to return -EINVAL in the event of invalid OTP
content, but the value gets overwritten before it is returned and the
read goes ahead anyway. Make the read conditional as it should be
and preserve the error code.

Fixes: 55d7de9de6c3 ("Microchip's LAN7800 family USB 2/3 to 10/100/1000 Ethernet device driver")
Signed-off-by: Phil Elwell <phil@raspberrypi.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/lan78xx.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 89d82c4ee8df..1fb464837b3e 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -928,7 +928,8 @@ static int lan78xx_read_otp(struct lan78xx_net *dev, u32 offset,
 			offset += 0x100;
 		else
 			ret = -EINVAL;
-		ret = lan78xx_read_raw_otp(dev, offset, length, data);
+		if (!ret)
+			ret = lan78xx_read_raw_otp(dev, offset, length, data);
 	}
 
 	return ret;
-- 
2.14.3


[-- Attachment #3: net_416.mbox --]
[-- Type: Application/Octet-Stream, Size: 27715 bytes --]

From 8b82665b96916e64c0555914a465adcf7c473bec Mon Sep 17 00:00:00 2001
From: Bassem Boubaker <bassem.boubaker@actia.fr>
Date: Wed, 11 Apr 2018 13:15:53 +0200
Subject: [PATCH 1/9] cdc_ether: flag the Cinterion AHS8 modem by gemalto as
 WWAN

[ Upstream commit 53765341ee821c0a0f1dec41adc89c9096ad694c ]

The Cinterion AHS8 is a 3G device with one embedded WWAN interface
using cdc_ether as a driver.

The modem is controlled via AT commands through the exposed TTYs.

AT+CGDCONT write command can be used to activate or deactivate a WWAN
connection for a PDP context defined with the same command. UE
supports one WWAN adapter.

Signed-off-by: Bassem Boubaker <bassem.boubaker@actia.fr>
Acked-by: Oliver Neukum <oneukum@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ether.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index fff4b13eece2..5c42cf81a08b 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -901,6 +901,12 @@ static const struct usb_device_id	products[] = {
 				      USB_CDC_SUBCLASS_ETHERNET,
 				      USB_CDC_PROTO_NONE),
 	.driver_info = (unsigned long)&wwan_info,
+}, {
+	/* Cinterion AHS3 modem by GEMALTO */
+	USB_DEVICE_AND_INTERFACE_INFO(0x1e2d, 0x0055, USB_CLASS_COMM,
+				      USB_CDC_SUBCLASS_ETHERNET,
+				      USB_CDC_PROTO_NONE),
+	.driver_info = (unsigned long)&wwan_info,
 }, {
 	USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ETHERNET,
 			USB_CDC_PROTO_NONE),
-- 
2.14.3


From 107ca1c1ec668d62d44698337441232237203c1e Mon Sep 17 00:00:00 2001
From: Ka-Cheong Poon <ka-cheong.poon@oracle.com>
Date: Wed, 11 Apr 2018 00:57:25 -0700
Subject: [PATCH 2/9] rds: MP-RDS may use an invalid c_path

[ Upstream commit a43cced9a348901f9015f4730b70b69e7c41a9c9 ]

rds_sendmsg() calls rds_send_mprds_hash() to find a c_path to use to
send a message.  Suppose the RDS connection is not yet up.  In
rds_send_mprds_hash(), it does

	if (conn->c_npaths == 0)
		wait_event_interruptible(conn->c_hs_waitq,
					 (conn->c_npaths != 0));

If it is interrupted before the connection is set up,
rds_send_mprds_hash() will return a non-zero hash value.  Hence
rds_sendmsg() will use a non-zero c_path to send the message.  But if
the RDS connection ends up to be non-MP capable, the message will be
lost as only the zero c_path can be used.

Signed-off-by: Ka-Cheong Poon <ka-cheong.poon@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/send.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/net/rds/send.c b/net/rds/send.c
index b1b0022b8370..85734e5a018e 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -997,10 +997,15 @@ static int rds_send_mprds_hash(struct rds_sock *rs, struct rds_connection *conn)
 	if (conn->c_npaths == 0 && hash != 0) {
 		rds_send_ping(conn, 0);
 
-		if (conn->c_npaths == 0) {
-			wait_event_interruptible(conn->c_hs_waitq,
-						 (conn->c_npaths != 0));
-		}
+		/* The underlying connection is not up yet.  Need to wait
+		 * until it is up to be sure that the non-zero c_path can be
+		 * used.  But if we are interrupted, we have to use the zero
+		 * c_path in case the connection ends up being non-MP capable.
+		 */
+		if (conn->c_npaths == 0)
+			if (wait_event_interruptible(conn->c_hs_waitq,
+						     conn->c_npaths != 0))
+				hash = 0;
 		if (conn->c_npaths == 1)
 			hash = 0;
 	}
-- 
2.14.3


From ec1381ffbee7dd8744da32555ff4d0f75b14e66f Mon Sep 17 00:00:00 2001
From: Tejaswi Tanikella <tejaswit@codeaurora.org>
Date: Wed, 11 Apr 2018 16:34:47 +0530
Subject: [PATCH 3/9] slip: Check if rstate is initialized before uncompressing

[ Upstream commit 3f01ddb962dc506916c243f9524e8bef97119b77 ]

On receiving a packet the state index points to the rstate which must be
used to fill up IP and TCP headers. But if the state index points to a
rstate which is unitialized, i.e. filled with zeros, it gets stuck in an
infinite loop inside ip_fast_csum trying to compute the ip checsum of a
header with zero length.

89.666953:   <2> [<ffffff9dd3e94d38>] slhc_uncompress+0x464/0x468
89.666965:   <2> [<ffffff9dd3e87d88>] ppp_receive_nonmp_frame+0x3b4/0x65c
89.666978:   <2> [<ffffff9dd3e89dd4>] ppp_receive_frame+0x64/0x7e0
89.666991:   <2> [<ffffff9dd3e8a708>] ppp_input+0x104/0x198
89.667005:   <2> [<ffffff9dd3e93868>] pppopns_recv_core+0x238/0x370
89.667027:   <2> [<ffffff9dd4428fc8>] __sk_receive_skb+0xdc/0x250
89.667040:   <2> [<ffffff9dd3e939e4>] pppopns_recv+0x44/0x60
89.667053:   <2> [<ffffff9dd4426848>] __sock_queue_rcv_skb+0x16c/0x24c
89.667065:   <2> [<ffffff9dd4426954>] sock_queue_rcv_skb+0x2c/0x38
89.667085:   <2> [<ffffff9dd44f7358>] raw_rcv+0x124/0x154
89.667098:   <2> [<ffffff9dd44f7568>] raw_local_deliver+0x1e0/0x22c
89.667117:   <2> [<ffffff9dd44c8ba0>] ip_local_deliver_finish+0x70/0x24c
89.667131:   <2> [<ffffff9dd44c92f4>] ip_local_deliver+0x100/0x10c

./scripts/faddr2line vmlinux slhc_uncompress+0x464/0x468 output:
 ip_fast_csum at arch/arm64/include/asm/checksum.h:40
 (inlined by) slhc_uncompress at drivers/net/slip/slhc.c:615

Adding a variable to indicate if the current rstate is initialized. If
such a packet arrives, move to toss state.

Signed-off-by: Tejaswi Tanikella <tejaswit@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/slip/slhc.c | 5 +++++
 include/net/slhc_vj.h   | 1 +
 2 files changed, 6 insertions(+)

diff --git a/drivers/net/slip/slhc.c b/drivers/net/slip/slhc.c
index 5782733959f0..f4e93f5fc204 100644
--- a/drivers/net/slip/slhc.c
+++ b/drivers/net/slip/slhc.c
@@ -509,6 +509,10 @@ slhc_uncompress(struct slcompress *comp, unsigned char *icp, int isize)
 		if(x < 0 || x > comp->rslot_limit)
 			goto bad;
 
+		/* Check if the cstate is initialized */
+		if (!comp->rstate[x].initialized)
+			goto bad;
+
 		comp->flags &=~ SLF_TOSS;
 		comp->recv_current = x;
 	} else {
@@ -673,6 +677,7 @@ slhc_remember(struct slcompress *comp, unsigned char *icp, int isize)
 	if (cs->cs_tcp.doff > 5)
 	  memcpy(cs->cs_tcpopt, icp + ihl*4 + sizeof(struct tcphdr), (cs->cs_tcp.doff - 5) * 4);
 	cs->cs_hsize = ihl*2 + cs->cs_tcp.doff*2;
+	cs->initialized = true;
 	/* Put headers back on packet
 	 * Neither header checksum is recalculated
 	 */
diff --git a/include/net/slhc_vj.h b/include/net/slhc_vj.h
index 8716d5942b65..8fcf8908a694 100644
--- a/include/net/slhc_vj.h
+++ b/include/net/slhc_vj.h
@@ -127,6 +127,7 @@ typedef __u32 int32;
  */
 struct cstate {
 	byte_t	cs_this;	/* connection id number (xmit) */
+	bool	initialized;	/* true if initialized */
 	struct cstate *next;	/* next in ring (xmit) */
 	struct iphdr cs_ip;	/* ip/tcp hdr from most recent packet */
 	struct tcphdr cs_tcp;
-- 
2.14.3


From 029de71db59457a1c4dfdc9a4873524d188e7a58 Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Wed, 11 Apr 2018 10:35:40 +0800
Subject: [PATCH 4/9] vhost: fix vhost_vq_access_ok() log check

[ Upstream commit d14d2b78090c7de0557362b26a4ca591aa6a9faa ]

Commit d65026c6c62e7d9616c8ceb5a53b68bcdc050525 ("vhost: validate log
when IOTLB is enabled") introduced a regression.  The logic was
originally:

  if (vq->iotlb)
      return 1;
  return A && B;

After the patch the short-circuit logic for A was inverted:

  if (A || vq->iotlb)
      return A;
  return B;

This patch fixes the regression by rewriting the checks in the obvious
way, no longer returning A when vq->iotlb is non-NULL (which is hard to
understand).

Reported-by: syzbot+65a84dde0214b0387ccd@syzkaller.appspotmail.com
Cc: Jason Wang <jasowang@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/vhost.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 5320039671b7..93fd0c75b0d8 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -1244,10 +1244,12 @@ static int vq_log_access_ok(struct vhost_virtqueue *vq,
 /* Caller should have vq mutex and device mutex */
 int vhost_vq_access_ok(struct vhost_virtqueue *vq)
 {
-	int ret = vq_log_access_ok(vq, vq->log_base);
+	if (!vq_log_access_ok(vq, vq->log_base))
+		return 0;
 
-	if (ret || vq->iotlb)
-		return ret;
+	/* Access validation occurs at prefetch time with IOTLB */
+	if (vq->iotlb)
+		return 1;
 
 	return vq_access_ok(vq, vq->num, vq->desc, vq->avail, vq->used);
 }
-- 
2.14.3


From f25fe26fb2e82e3a79c78559a2e7ec5d5e624942 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Tue, 10 Apr 2018 21:01:12 +0200
Subject: [PATCH 5/9] l2tp: fix races in tunnel creation

[ Upstream commit 6b9f34239b00e6956a267abed2bc559ede556ad6 ]

l2tp_tunnel_create() inserts the new tunnel into the namespace's tunnel
list and sets the socket's ->sk_user_data field, before returning it to
the caller. Therefore, there are two ways the tunnel can be accessed
and freed, before the caller even had the opportunity to take a
reference. In practice, syzbot could crash the module by closing the
socket right after a new tunnel was returned to pppol2tp_create().

This patch moves tunnel registration out of l2tp_tunnel_create(), so
that the caller can safely hold a reference before publishing the
tunnel. This second step is done with the new l2tp_tunnel_register()
function, which is now responsible for associating the tunnel to its
socket and for inserting it into the namespace's list.

While moving the code to l2tp_tunnel_register(), a few modifications
have been done. First, the socket validation tests are done in a helper
function, for clarity. Also, modifying the socket is now done after
having inserted the tunnel to the namespace's tunnels list. This will
allow insertion to fail, without having to revert theses modifications
in the error path (a followup patch will check for duplicate tunnels
before insertion). Either the socket is a kernel socket which we
control, or it is a user-space socket for which we have a reference on
the file descriptor. In any case, the socket isn't going to be closed
from under us.

Reported-by: syzbot+fbeeb5c3b538e8545644@syzkaller.appspotmail.com
Fixes: fd558d186df2 ("l2tp: Split pppol2tp patch into separate l2tp and ppp parts")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c    | 192 +++++++++++++++++++++---------------------------
 net/l2tp/l2tp_core.h    |   3 +
 net/l2tp/l2tp_netlink.c |  16 +++-
 net/l2tp/l2tp_ppp.c     |   9 +++
 4 files changed, 110 insertions(+), 110 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 14b67dfacc4b..afb42d142807 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1436,74 +1436,11 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
 {
 	struct l2tp_tunnel *tunnel = NULL;
 	int err;
-	struct socket *sock = NULL;
-	struct sock *sk = NULL;
-	struct l2tp_net *pn;
 	enum l2tp_encap_type encap = L2TP_ENCAPTYPE_UDP;
 
-	/* Get the tunnel socket from the fd, which was opened by
-	 * the userspace L2TP daemon. If not specified, create a
-	 * kernel socket.
-	 */
-	if (fd < 0) {
-		err = l2tp_tunnel_sock_create(net, tunnel_id, peer_tunnel_id,
-				cfg, &sock);
-		if (err < 0)
-			goto err;
-	} else {
-		sock = sockfd_lookup(fd, &err);
-		if (!sock) {
-			pr_err("tunl %u: sockfd_lookup(fd=%d) returned %d\n",
-			       tunnel_id, fd, err);
-			err = -EBADF;
-			goto err;
-		}
-
-		/* Reject namespace mismatches */
-		if (!net_eq(sock_net(sock->sk), net)) {
-			pr_err("tunl %u: netns mismatch\n", tunnel_id);
-			err = -EINVAL;
-			goto err;
-		}
-	}
-
-	sk = sock->sk;
-
 	if (cfg != NULL)
 		encap = cfg->encap;
 
-	/* Quick sanity checks */
-	err = -EPROTONOSUPPORT;
-	if (sk->sk_type != SOCK_DGRAM) {
-		pr_debug("tunl %hu: fd %d wrong socket type\n",
-			 tunnel_id, fd);
-		goto err;
-	}
-	switch (encap) {
-	case L2TP_ENCAPTYPE_UDP:
-		if (sk->sk_protocol != IPPROTO_UDP) {
-			pr_err("tunl %hu: fd %d wrong protocol, got %d, expected %d\n",
-			       tunnel_id, fd, sk->sk_protocol, IPPROTO_UDP);
-			goto err;
-		}
-		break;
-	case L2TP_ENCAPTYPE_IP:
-		if (sk->sk_protocol != IPPROTO_L2TP) {
-			pr_err("tunl %hu: fd %d wrong protocol, got %d, expected %d\n",
-			       tunnel_id, fd, sk->sk_protocol, IPPROTO_L2TP);
-			goto err;
-		}
-		break;
-	}
-
-	/* Check if this socket has already been prepped */
-	tunnel = l2tp_tunnel(sk);
-	if (tunnel != NULL) {
-		/* This socket has already been prepped */
-		err = -EBUSY;
-		goto err;
-	}
-
 	tunnel = kzalloc(sizeof(struct l2tp_tunnel), GFP_KERNEL);
 	if (tunnel == NULL) {
 		err = -ENOMEM;
@@ -1520,72 +1457,113 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
 	rwlock_init(&tunnel->hlist_lock);
 	tunnel->acpt_newsess = true;
 
-	/* The net we belong to */
-	tunnel->l2tp_net = net;
-	pn = l2tp_pernet(net);
-
 	if (cfg != NULL)
 		tunnel->debug = cfg->debug;
 
-	/* Mark socket as an encapsulation socket. See net/ipv4/udp.c */
 	tunnel->encap = encap;
-	if (encap == L2TP_ENCAPTYPE_UDP) {
-		struct udp_tunnel_sock_cfg udp_cfg = { };
-
-		udp_cfg.sk_user_data = tunnel;
-		udp_cfg.encap_type = UDP_ENCAP_L2TPINUDP;
-		udp_cfg.encap_rcv = l2tp_udp_encap_recv;
-		udp_cfg.encap_destroy = l2tp_udp_encap_destroy;
-
-		setup_udp_tunnel_sock(net, sock, &udp_cfg);
-	} else {
-		sk->sk_user_data = tunnel;
-	}
 
-	/* Bump the reference count. The tunnel context is deleted
-	 * only when this drops to zero. A reference is also held on
-	 * the tunnel socket to ensure that it is not released while
-	 * the tunnel is extant. Must be done before sk_destruct is
-	 * set.
-	 */
 	refcount_set(&tunnel->ref_count, 1);
-	sock_hold(sk);
-	tunnel->sock = sk;
 	tunnel->fd = fd;
 
-	/* Hook on the tunnel socket destructor so that we can cleanup
-	 * if the tunnel socket goes away.
-	 */
-	tunnel->old_sk_destruct = sk->sk_destruct;
-	sk->sk_destruct = &l2tp_tunnel_destruct;
-	lockdep_set_class_and_name(&sk->sk_lock.slock, &l2tp_socket_class, "l2tp_sock");
-
-	sk->sk_allocation = GFP_ATOMIC;
-
 	/* Init delete workqueue struct */
 	INIT_WORK(&tunnel->del_work, l2tp_tunnel_del_work);
 
-	/* Add tunnel to our list */
 	INIT_LIST_HEAD(&tunnel->list);
-	spin_lock_bh(&pn->l2tp_tunnel_list_lock);
-	list_add_rcu(&tunnel->list, &pn->l2tp_tunnel_list);
-	spin_unlock_bh(&pn->l2tp_tunnel_list_lock);
 
 	err = 0;
 err:
 	if (tunnelp)
 		*tunnelp = tunnel;
 
-	/* If tunnel's socket was created by the kernel, it doesn't
-	 *  have a file.
-	 */
-	if (sock && sock->file)
-		sockfd_put(sock);
-
 	return err;
 }
 EXPORT_SYMBOL_GPL(l2tp_tunnel_create);
 
+static int l2tp_validate_socket(const struct sock *sk, const struct net *net,
+				enum l2tp_encap_type encap)
+{
+	if (!net_eq(sock_net(sk), net))
+		return -EINVAL;
+
+	if (sk->sk_type != SOCK_DGRAM)
+		return -EPROTONOSUPPORT;
+
+	if ((encap == L2TP_ENCAPTYPE_UDP && sk->sk_protocol != IPPROTO_UDP) ||
+	    (encap == L2TP_ENCAPTYPE_IP && sk->sk_protocol != IPPROTO_L2TP))
+		return -EPROTONOSUPPORT;
+
+	if (sk->sk_user_data)
+		return -EBUSY;
+
+	return 0;
+}
+
+int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
+			 struct l2tp_tunnel_cfg *cfg)
+{
+	struct l2tp_net *pn;
+	struct socket *sock;
+	struct sock *sk;
+	int ret;
+
+	if (tunnel->fd < 0) {
+		ret = l2tp_tunnel_sock_create(net, tunnel->tunnel_id,
+					      tunnel->peer_tunnel_id, cfg,
+					      &sock);
+		if (ret < 0)
+			goto err;
+	} else {
+		sock = sockfd_lookup(tunnel->fd, &ret);
+		if (!sock)
+			goto err;
+
+		ret = l2tp_validate_socket(sock->sk, net, tunnel->encap);
+		if (ret < 0)
+			goto err_sock;
+	}
+
+	sk = sock->sk;
+
+	sock_hold(sk);
+	tunnel->sock = sk;
+	tunnel->l2tp_net = net;
+
+	pn = l2tp_pernet(net);
+	spin_lock_bh(&pn->l2tp_tunnel_list_lock);
+	list_add_rcu(&tunnel->list, &pn->l2tp_tunnel_list);
+	spin_unlock_bh(&pn->l2tp_tunnel_list_lock);
+
+	if (tunnel->encap == L2TP_ENCAPTYPE_UDP) {
+		struct udp_tunnel_sock_cfg udp_cfg = {
+			.sk_user_data = tunnel,
+			.encap_type = UDP_ENCAP_L2TPINUDP,
+			.encap_rcv = l2tp_udp_encap_recv,
+			.encap_destroy = l2tp_udp_encap_destroy,
+		};
+
+		setup_udp_tunnel_sock(net, sock, &udp_cfg);
+	} else {
+		sk->sk_user_data = tunnel;
+	}
+
+	tunnel->old_sk_destruct = sk->sk_destruct;
+	sk->sk_destruct = &l2tp_tunnel_destruct;
+	lockdep_set_class_and_name(&sk->sk_lock.slock, &l2tp_socket_class,
+				   "l2tp_sock");
+	sk->sk_allocation = GFP_ATOMIC;
+
+	if (tunnel->fd >= 0)
+		sockfd_put(sock);
+
+	return 0;
+
+err_sock:
+	sockfd_put(sock);
+err:
+	return ret;
+}
+EXPORT_SYMBOL_GPL(l2tp_tunnel_register);
+
 /* This function is used by the netlink TUNNEL_DELETE command.
  */
 void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel)
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 2718d0b284d0..12f0fa82f162 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -226,6 +226,9 @@ struct l2tp_tunnel *l2tp_tunnel_find_nth(const struct net *net, int nth);
 int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id,
 		       u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg,
 		       struct l2tp_tunnel **tunnelp);
+int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
+			 struct l2tp_tunnel_cfg *cfg);
+
 void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel);
 void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel);
 struct l2tp_session *l2tp_session_create(int priv_size,
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index e7ea9c4b89ff..45db9b73eb1a 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -251,9 +251,19 @@ static int l2tp_nl_cmd_tunnel_create(struct sk_buff *skb, struct genl_info *info
 		break;
 	}
 
-	if (ret >= 0)
-		ret = l2tp_tunnel_notify(&l2tp_nl_family, info,
-					 tunnel, L2TP_CMD_TUNNEL_CREATE);
+	if (ret < 0)
+		goto out;
+
+	l2tp_tunnel_inc_refcount(tunnel);
+	ret = l2tp_tunnel_register(tunnel, net, &cfg);
+	if (ret < 0) {
+		kfree(tunnel);
+		goto out;
+	}
+	ret = l2tp_tunnel_notify(&l2tp_nl_family, info, tunnel,
+				 L2TP_CMD_TUNNEL_CREATE);
+	l2tp_tunnel_dec_refcount(tunnel);
+
 out:
 	return ret;
 }
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 3b02f24ea9ec..3d7887cc599b 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -698,6 +698,15 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 			error = l2tp_tunnel_create(sock_net(sk), fd, ver, tunnel_id, peer_tunnel_id, &tcfg, &tunnel);
 			if (error < 0)
 				goto end;
+
+			l2tp_tunnel_inc_refcount(tunnel);
+			error = l2tp_tunnel_register(tunnel, sock_net(sk),
+						     &tcfg);
+			if (error < 0) {
+				kfree(tunnel);
+				goto end;
+			}
+			drop_tunnel = true;
 		}
 	} else {
 		/* Error if we can't find the tunnel */
-- 
2.14.3


From 4cd610bdfa3a78547fcc2920ee71084848fe1b88 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Tue, 10 Apr 2018 21:01:13 +0200
Subject: [PATCH 6/9] l2tp: fix race in duplicate tunnel detection

[ Upstream commit f6cd651b056ffd3b4e8496afd44d4ed44bf69136 ]

We can't use l2tp_tunnel_find() to prevent l2tp_nl_cmd_tunnel_create()
from creating a duplicate tunnel. A tunnel can be concurrently
registered after l2tp_tunnel_find() returns. Therefore, searching for
duplicates must be done at registration time.

Finally, remove l2tp_tunnel_find() entirely as it isn't use anywhere
anymore.

Fixes: 309795f4bec2 ("l2tp: Add netlink control API for L2TP")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c    | 35 ++++++++++++++---------------------
 net/l2tp/l2tp_core.h    |  1 -
 net/l2tp/l2tp_netlink.c |  6 ------
 3 files changed, 14 insertions(+), 28 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index afb42d142807..0fbd3ee26165 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -335,26 +335,6 @@ int l2tp_session_register(struct l2tp_session *session,
 }
 EXPORT_SYMBOL_GPL(l2tp_session_register);
 
-/* Lookup a tunnel by id
- */
-struct l2tp_tunnel *l2tp_tunnel_find(const struct net *net, u32 tunnel_id)
-{
-	struct l2tp_tunnel *tunnel;
-	struct l2tp_net *pn = l2tp_pernet(net);
-
-	rcu_read_lock_bh();
-	list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
-		if (tunnel->tunnel_id == tunnel_id) {
-			rcu_read_unlock_bh();
-			return tunnel;
-		}
-	}
-	rcu_read_unlock_bh();
-
-	return NULL;
-}
-EXPORT_SYMBOL_GPL(l2tp_tunnel_find);
-
 struct l2tp_tunnel *l2tp_tunnel_find_nth(const struct net *net, int nth)
 {
 	struct l2tp_net *pn = l2tp_pernet(net);
@@ -1501,6 +1481,7 @@ static int l2tp_validate_socket(const struct sock *sk, const struct net *net,
 int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
 			 struct l2tp_tunnel_cfg *cfg)
 {
+	struct l2tp_tunnel *tunnel_walk;
 	struct l2tp_net *pn;
 	struct socket *sock;
 	struct sock *sk;
@@ -1529,7 +1510,16 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
 	tunnel->l2tp_net = net;
 
 	pn = l2tp_pernet(net);
+
 	spin_lock_bh(&pn->l2tp_tunnel_list_lock);
+	list_for_each_entry(tunnel_walk, &pn->l2tp_tunnel_list, list) {
+		if (tunnel_walk->tunnel_id == tunnel->tunnel_id) {
+			spin_unlock_bh(&pn->l2tp_tunnel_list_lock);
+
+			ret = -EEXIST;
+			goto err_sock;
+		}
+	}
 	list_add_rcu(&tunnel->list, &pn->l2tp_tunnel_list);
 	spin_unlock_bh(&pn->l2tp_tunnel_list_lock);
 
@@ -1558,7 +1548,10 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
 	return 0;
 
 err_sock:
-	sockfd_put(sock);
+	if (tunnel->fd < 0)
+		sock_release(sock);
+	else
+		sockfd_put(sock);
 err:
 	return ret;
 }
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 12f0fa82f162..ba33cbec71eb 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -220,7 +220,6 @@ struct l2tp_session *l2tp_session_get(const struct net *net,
 struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth);
 struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net,
 						const char *ifname);
-struct l2tp_tunnel *l2tp_tunnel_find(const struct net *net, u32 tunnel_id);
 struct l2tp_tunnel *l2tp_tunnel_find_nth(const struct net *net, int nth);
 
 int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id,
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index 45db9b73eb1a..b05dbd9ffcb2 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -236,12 +236,6 @@ static int l2tp_nl_cmd_tunnel_create(struct sk_buff *skb, struct genl_info *info
 	if (info->attrs[L2TP_ATTR_DEBUG])
 		cfg.debug = nla_get_u32(info->attrs[L2TP_ATTR_DEBUG]);
 
-	tunnel = l2tp_tunnel_find(net, tunnel_id);
-	if (tunnel != NULL) {
-		ret = -EEXIST;
-		goto out;
-	}
-
 	ret = -EINVAL;
 	switch (cfg.encap) {
 	case L2TP_ENCAPTYPE_UDP:
-- 
2.14.3


From 6b35de3b368a09506b6b039047e3e2a0035e7327 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 10 Apr 2018 12:57:18 +0200
Subject: [PATCH 7/9] ip_gre: clear feature flags when incompatible o_flags are
 set

[ Upstream commit 1cc5954f44150bb70cac07c3cc5df7cf0dfb61ec ]

Commit dd9d598c6657 ("ip_gre: add the support for i/o_flags update via
netlink") added the ability to change o_flags, but missed that the
GSO/LLTX features are disabled by default, and only enabled some gre
features are unused. Thus we also need to disable the GSO/LLTX features
on the device when the TUNNEL_SEQ or TUNNEL_CSUM flags are set.

These two examples should result in the same features being set:

    ip link add gre_none type gre local 192.168.0.10 remote 192.168.0.20 ttl 255 key 0

    ip link set gre_none type gre seq
    ip link add gre_seq type gre local 192.168.0.10 remote 192.168.0.20 ttl 255 key 1 seq

Fixes: dd9d598c6657 ("ip_gre: add the support for i/o_flags update via netlink")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Acked-by: William Tu <u9012063@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_gre.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 0901de42ed85..586a008b1642 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -778,8 +778,14 @@ static void ipgre_link_update(struct net_device *dev, bool set_mtu)
 		    tunnel->encap.type == TUNNEL_ENCAP_NONE) {
 			dev->features |= NETIF_F_GSO_SOFTWARE;
 			dev->hw_features |= NETIF_F_GSO_SOFTWARE;
+		} else {
+			dev->features &= ~NETIF_F_GSO_SOFTWARE;
+			dev->hw_features &= ~NETIF_F_GSO_SOFTWARE;
 		}
 		dev->features |= NETIF_F_LLTX;
+	} else {
+		dev->hw_features &= ~NETIF_F_GSO_SOFTWARE;
+		dev->features &= ~(NETIF_F_LLTX | NETIF_F_GSO_SOFTWARE);
 	}
 }
 
-- 
2.14.3


From 478587884a0d7140a86ae5e1936c44daba2e708d Mon Sep 17 00:00:00 2001
From: Eric Auger <eric.auger@redhat.com>
Date: Wed, 11 Apr 2018 15:30:38 +0200
Subject: [PATCH 8/9] vhost: Fix vhost_copy_to_user()

[ Upstream commit 7ced6c98c7ab7a1f6743931e28671b833af79b1e ]

vhost_copy_to_user is used to copy vring used elements to userspace.
We should use VHOST_ADDR_USED instead of VHOST_ADDR_DESC.

Fixes: f88949138058 ("vhost: introduce O(1) vq metadata cache")
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/vhost.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 93fd0c75b0d8..be6a4b6a76c6 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -744,7 +744,7 @@ static int vhost_copy_to_user(struct vhost_virtqueue *vq, void __user *to,
 		struct iov_iter t;
 		void __user *uaddr = vhost_vq_meta_fetch(vq,
 				     (u64)(uintptr_t)to, size,
-				     VHOST_ADDR_DESC);
+				     VHOST_ADDR_USED);
 
 		if (uaddr)
 			return __copy_to_user(uaddr, from, size);
-- 
2.14.3


From fd8cf0fb5df03438b5fa4266d3c6325bbc9cdf19 Mon Sep 17 00:00:00 2001
From: Phil Elwell <phil@raspberrypi.org>
Date: Wed, 11 Apr 2018 10:59:17 +0100
Subject: [PATCH 9/9] lan78xx: Correctly indicate invalid OTP

[ Upstream commit 4bfc33807a9a02764bdd1e42e794b3b401240f27 ]

lan78xx_read_otp tries to return -EINVAL in the event of invalid OTP
content, but the value gets overwritten before it is returned and the
read goes ahead anyway. Make the read conditional as it should be
and preserve the error code.

Fixes: 55d7de9de6c3 ("Microchip's LAN7800 family USB 2/3 to 10/100/1000 Ethernet device driver")
Signed-off-by: Phil Elwell <phil@raspberrypi.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/lan78xx.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 55a78eb96961..32cf21716f19 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -928,7 +928,8 @@ static int lan78xx_read_otp(struct lan78xx_net *dev, u32 offset,
 			offset += 0x100;
 		else
 			ret = -EINVAL;
-		ret = lan78xx_read_raw_otp(dev, offset, length, data);
+		if (!ret)
+			ret = lan78xx_read_raw_otp(dev, offset, length, data);
 	}
 
 	return ret;
-- 
2.14.3

Re: [PATCHES] Networking

[Greg KH]

On Fri, Apr 13, 2018 at 01:47:16PM -0400, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.4 and
> v4.16 -stable, respectively.
> 
> Note, you may wish to take patch "vhost: fix vhost_vq_access_ok() log check"
> (upsteam d14d2b78090c7de0557362b26a4ca591aa6a9faa) for v4.15 as well
> because the change it is fixing went into v4.15.17

Thanks, all now queued up.  I threw all of the 4.16 patches into 4.15,
as they looked good :)

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 107 bytes --]


Please queue up the following networking bug fixes for v4.14 and
v4.16 -stable, respectively.

Thank you.

[-- Attachment #2: net_414.mbox --]
[-- Type: Application/Octet-Stream, Size: 112995 bytes --]

From 0f41bedcd4ebea2d4af6e1acb19698e32cb06b63 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 22 Apr 2018 19:11:50 +0800
Subject: [PATCH 01/33] bonding: do not set slave_dev npinfo before
 slave_enable_netpoll in bond_enslave

[ Upstream commit ddea788c63094f7c483783265563dd5b50052e28 ]

After Commit 8a8efa22f51b ("bonding: sync netpoll code with bridge"), it
would set slave_dev npinfo in slave_enable_netpoll when enslaving a dev
if bond->dev->npinfo was set.

However now slave_dev npinfo is set with bond->dev->npinfo before calling
slave_enable_netpoll. With slave_dev npinfo set, __netpoll_setup called
in slave_enable_netpoll will not call slave dev's .ndo_netpoll_setup().
It causes that the lower dev of this slave dev can't set its npinfo.

One way to reproduce it:

  # modprobe bonding
  # brctl addbr br0
  # brctl addif br0 eth1
  # ifconfig bond0 192.168.122.1/24 up
  # ifenslave bond0 eth2
  # systemctl restart netconsole
  # ifenslave bond0 br0
  # ifconfig eth2 down
  # systemctl restart netconsole

The netpoll won't really work.

This patch is to remove that slave_dev npinfo setting in bond_enslave().

Fixes: 8a8efa22f51b ("bonding: sync netpoll code with bridge")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 82f28ffccddf..bf3be2e6d4a8 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1656,8 +1656,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	} /* switch(bond_mode) */
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
-	slave_dev->npinfo = bond->dev->npinfo;
-	if (slave_dev->npinfo) {
+	if (bond->dev->npinfo) {
 		if (slave_enable_netpoll(new_slave)) {
 			netdev_info(bond_dev, "master_dev is using netpoll, but new slave device does not support netpoll\n");
 			res = -EBUSY;
-- 
2.14.3


From 0b0a03a3ddff319d6f0556868101a8fbf649fadc Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 22 Apr 2018 18:29:23 -0700
Subject: [PATCH 02/33] ipv6: add RTA_TABLE and RTA_PREFSRC to rtm_ipv6_policy

[ Upstream commit aa8f8778493c85fff480cdf8b349b1e1dcb5f243 ]

KMSAN reported use of uninit-value that I tracked to lack
of proper size check on RTA_TABLE attribute.

I also believe RTA_PREFSRC lacks a similar check.

Fixes: 86872cb57925 ("[IPv6] route: FIB6 configuration using struct fib6_config")
Fixes: c3968a857a6b ("ipv6: RTA_PREFSRC support for ipv6 route source address selection")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 0126d9bfa670..e04c534b573e 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2959,6 +2959,7 @@ void rt6_mtu_change(struct net_device *dev, unsigned int mtu)
 
 static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
 	[RTA_GATEWAY]           = { .len = sizeof(struct in6_addr) },
+	[RTA_PREFSRC]		= { .len = sizeof(struct in6_addr) },
 	[RTA_OIF]               = { .type = NLA_U32 },
 	[RTA_IIF]		= { .type = NLA_U32 },
 	[RTA_PRIORITY]          = { .type = NLA_U32 },
@@ -2970,6 +2971,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
 	[RTA_EXPIRES]		= { .type = NLA_U32 },
 	[RTA_UID]		= { .type = NLA_U32 },
 	[RTA_MARK]		= { .type = NLA_U32 },
+	[RTA_TABLE]		= { .type = NLA_U32 },
 };
 
 static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
-- 
2.14.3


From 2ccb331449140c7ac08eb9244fa9ef3aa3066f9f Mon Sep 17 00:00:00 2001
From: Ahmed Abdelsalam <amsalam20@gmail.com>
Date: Fri, 20 Apr 2018 15:58:05 +0200
Subject: [PATCH 03/33] ipv6: sr: fix NULL pointer dereference in
 seg6_do_srh_encap()- v4 pkts

[ Upstream commit a957fa190aa9d9168b33d460a5241a6d088c6265 ]

In case of seg6 in encap mode, seg6_do_srh_encap() calls set_tun_src()
in order to set the src addr of outer IPv6 header.

The net_device is required for set_tun_src(). However calling ip6_dst_idev()
on dst_entry in case of IPv4 traffic results on the following bug.

Using just dst->dev should fix this BUG.

[  196.242461] BUG: unable to handle kernel NULL pointer dereference at 0000000000000000
[  196.242975] PGD 800000010f076067 P4D 800000010f076067 PUD 10f060067 PMD 0
[  196.243329] Oops: 0000 [#1] SMP PTI
[  196.243468] Modules linked in: nfsd auth_rpcgss nfs_acl nfs lockd grace fscache sunrpc crct10dif_pclmul crc32_pclmul ghash_clmulni_intel pcbc aesni_intel aes_x86_64 crypto_simd cryptd input_leds glue_helper led_class pcspkr serio_raw mac_hid video autofs4 hid_generic usbhid hid e1000 i2c_piix4 ahci pata_acpi libahci
[  196.244362] CPU: 2 PID: 1089 Comm: ping Not tainted 4.16.0+ #1
[  196.244606] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[  196.244968] RIP: 0010:seg6_do_srh_encap+0x1ac/0x300
[  196.245236] RSP: 0018:ffffb2ce00b23a60 EFLAGS: 00010202
[  196.245464] RAX: 0000000000000000 RBX: ffff8c7f53eea300 RCX: 0000000000000000
[  196.245742] RDX: 0000f10000000000 RSI: ffff8c7f52085a6c RDI: ffff8c7f41166850
[  196.246018] RBP: ffffb2ce00b23aa8 R08: 00000000000261e0 R09: ffff8c7f41166800
[  196.246294] R10: ffffdce5040ac780 R11: ffff8c7f41166828 R12: ffff8c7f41166808
[  196.246570] R13: ffff8c7f52085a44 R14: ffffffffb73211c0 R15: ffff8c7e69e44200
[  196.246846] FS:  00007fc448789700(0000) GS:ffff8c7f59d00000(0000) knlGS:0000000000000000
[  196.247286] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  196.247526] CR2: 0000000000000000 CR3: 000000010f05a000 CR4: 00000000000406e0
[  196.247804] Call Trace:
[  196.247972]  seg6_do_srh+0x15b/0x1c0
[  196.248156]  seg6_output+0x3c/0x220
[  196.248341]  ? prandom_u32+0x14/0x20
[  196.248526]  ? ip_idents_reserve+0x6c/0x80
[  196.248723]  ? __ip_select_ident+0x90/0x100
[  196.248923]  ? ip_append_data.part.50+0x6c/0xd0
[  196.249133]  lwtunnel_output+0x44/0x70
[  196.249328]  ip_send_skb+0x15/0x40
[  196.249515]  raw_sendmsg+0x8c3/0xac0
[  196.249701]  ? _copy_from_user+0x2e/0x60
[  196.249897]  ? rw_copy_check_uvector+0x53/0x110
[  196.250106]  ? _copy_from_user+0x2e/0x60
[  196.250299]  ? copy_msghdr_from_user+0xce/0x140
[  196.250508]  sock_sendmsg+0x36/0x40
[  196.250690]  ___sys_sendmsg+0x292/0x2a0
[  196.250881]  ? _cond_resched+0x15/0x30
[  196.251074]  ? copy_termios+0x1e/0x70
[  196.251261]  ? _copy_to_user+0x22/0x30
[  196.251575]  ? tty_mode_ioctl+0x1c3/0x4e0
[  196.251782]  ? _cond_resched+0x15/0x30
[  196.251972]  ? mutex_lock+0xe/0x30
[  196.252152]  ? vvar_fault+0xd2/0x110
[  196.252337]  ? __do_fault+0x1f/0xc0
[  196.252521]  ? __handle_mm_fault+0xc1f/0x12d0
[  196.252727]  ? __sys_sendmsg+0x63/0xa0
[  196.252919]  __sys_sendmsg+0x63/0xa0
[  196.253107]  do_syscall_64+0x72/0x200
[  196.253305]  entry_SYSCALL_64_after_hwframe+0x3d/0xa2
[  196.253530] RIP: 0033:0x7fc4480b0690
[  196.253715] RSP: 002b:00007ffde9f252f8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
[  196.254053] RAX: ffffffffffffffda RBX: 0000000000000040 RCX: 00007fc4480b0690
[  196.254331] RDX: 0000000000000000 RSI: 000000000060a360 RDI: 0000000000000003
[  196.254608] RBP: 00007ffde9f253f0 R08: 00000000002d1e81 R09: 0000000000000002
[  196.254884] R10: 00007ffde9f250c0 R11: 0000000000000246 R12: 0000000000b22070
[  196.255205] R13: 20c49ba5e353f7cf R14: 431bde82d7b634db R15: 00007ffde9f278fe
[  196.255484] Code: a5 0f b6 45 c0 41 88 41 28 41 0f b6 41 2c 48 c1 e0 04 49 8b 54 01 38 49 8b 44 01 30 49 89 51 20 49 89 41 18 48 8b 83 b0 00 00 00 <48> 8b 30 49 8b 86 08 0b 00 00 48 8b 40 20 48 8b 50 08 48 0b 10
[  196.256190] RIP: seg6_do_srh_encap+0x1ac/0x300 RSP: ffffb2ce00b23a60
[  196.256445] CR2: 0000000000000000
[  196.256676] ---[ end trace 71af7d093603885c ]---

Fixes: 8936ef7604c11 ("ipv6: sr: fix NULL pointer dereference when setting encap source address")
Signed-off-by: Ahmed Abdelsalam <amsalam20@gmail.com>
Acked-by: David Lebrun <dlebrun@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/seg6_iptunnel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index f343e6f0fc95..5fe139484919 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -136,7 +136,7 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
 	isrh->nexthdr = proto;
 
 	hdr->daddr = isrh->segments[isrh->first_segment];
-	set_tun_src(net, ip6_dst_idev(dst)->dev, &hdr->daddr, &hdr->saddr);
+	set_tun_src(net, dst->dev, &hdr->daddr, &hdr->saddr);
 
 #ifdef CONFIG_IPV6_SEG6_HMAC
 	if (sr_has_hmac(isrh)) {
-- 
2.14.3


From c52e938d723a063e89e9c0bed593694fab5f3663 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Tue, 17 Apr 2018 12:07:06 -0700
Subject: [PATCH 04/33] KEYS: DNS: limit the length of option strings

[ Upstream commit 9c438d7a3a52dcc2b9ed095cb87d3a5e83cf7e60 ]

Adding a dns_resolver key whose payload contains a very long option name
resulted in that string being printed in full.  This hit the WARN_ONCE()
in set_precision() during the printk(), because printk() only supports a
precision of up to 32767 bytes:

    precision 1000000 too large
    WARNING: CPU: 0 PID: 752 at lib/vsprintf.c:2189 vsnprintf+0x4bc/0x5b0

Fix it by limiting option strings (combined name + value) to a much more
reasonable 128 bytes.  The exact limit is arbitrary, but currently the
only recognized option is formatted as "dnserror=%lu" which fits well
within this limit.

Also ratelimit the printks.

Reproducer:

    perl -e 'print "#", "A" x 1000000, "\x00"' | keyctl padd dns_resolver desc @s

This bug was found using syzkaller.

Reported-by: Mark Rutland <mark.rutland@arm.com>
Fixes: 4a2d789267e0 ("DNS: If the DNS server returns an error, allow that to be cached [ver #2]")
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dns_resolver/dns_key.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c
index e1d4d898a007..f0252768ecf4 100644
--- a/net/dns_resolver/dns_key.c
+++ b/net/dns_resolver/dns_key.c
@@ -25,6 +25,7 @@
 #include <linux/moduleparam.h>
 #include <linux/slab.h>
 #include <linux/string.h>
+#include <linux/ratelimit.h>
 #include <linux/kernel.h>
 #include <linux/keyctl.h>
 #include <linux/err.h>
@@ -91,9 +92,9 @@ dns_resolver_preparse(struct key_preparsed_payload *prep)
 
 			next_opt = memchr(opt, '#', end - opt) ?: end;
 			opt_len = next_opt - opt;
-			if (!opt_len) {
-				printk(KERN_WARNING
-				       "Empty option to dns_resolver key\n");
+			if (opt_len <= 0 || opt_len > 128) {
+				pr_warn_ratelimited("Invalid option length (%d) for dns_resolver key\n",
+						    opt_len);
 				return -EINVAL;
 			}
 
@@ -127,10 +128,8 @@ dns_resolver_preparse(struct key_preparsed_payload *prep)
 			}
 
 		bad_option_value:
-			printk(KERN_WARNING
-			       "Option '%*.*s' to dns_resolver key:"
-			       " bad/missing value\n",
-			       opt_nlen, opt_nlen, opt);
+			pr_warn_ratelimited("Option '%*.*s' to dns_resolver key: bad/missing value\n",
+					    opt_nlen, opt_nlen, opt);
 			return -EINVAL;
 		} while (opt = next_opt + 1, opt < end);
 	}
-- 
2.14.3


From 2b566dcfedba6a04e85bc70ceace0c40765e34c6 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Mon, 23 Apr 2018 16:15:14 +0200
Subject: [PATCH 05/33] l2tp: check sockaddr length in pppol2tp_connect()

[ Upstream commit eb1c28c05894a4b1f6b56c5bf072205e64cfa280 ]

Check sockaddr_len before dereferencing sp->sa_protocol, to ensure that
it actually points to valid data.

Fixes: fd558d186df2 ("l2tp: Split pppol2tp patch into separate l2tp and ppp parts")
Reported-by: syzbot+a70ac890b23b1bf29f5c@syzkaller.appspotmail.com
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ppp.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 0c2738349442..8bef35aa8786 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -591,6 +591,13 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 	lock_sock(sk);
 
 	error = -EINVAL;
+
+	if (sockaddr_len != sizeof(struct sockaddr_pppol2tp) &&
+	    sockaddr_len != sizeof(struct sockaddr_pppol2tpv3) &&
+	    sockaddr_len != sizeof(struct sockaddr_pppol2tpin6) &&
+	    sockaddr_len != sizeof(struct sockaddr_pppol2tpv3in6))
+		goto end;
+
 	if (sp->sa_protocol != PX_PROTO_OL2TP)
 		goto end;
 
-- 
2.14.3


From 89e84adfedded9fecf6a331891d0f42f090e5600 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 11 Apr 2018 14:46:00 -0700
Subject: [PATCH 06/33] net: validate attribute sizes in neigh_dump_table()

[ Upstream commit 7dd07c143a4b54d050e748bee4b4b9e94a7b1744 ]

Since neigh_dump_table() calls nlmsg_parse() without giving policy
constraints, attributes can have arbirary size that we must validate

Reported by syzbot/KMSAN :

BUG: KMSAN: uninit-value in neigh_master_filtered net/core/neighbour.c:2292 [inline]
BUG: KMSAN: uninit-value in neigh_dump_table net/core/neighbour.c:2348 [inline]
BUG: KMSAN: uninit-value in neigh_dump_info+0x1af0/0x2250 net/core/neighbour.c:2438
CPU: 1 PID: 3575 Comm: syzkaller268891 Not tainted 4.16.0+ #83
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x185/0x1d0 lib/dump_stack.c:53
 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067
 __msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:676
 neigh_master_filtered net/core/neighbour.c:2292 [inline]
 neigh_dump_table net/core/neighbour.c:2348 [inline]
 neigh_dump_info+0x1af0/0x2250 net/core/neighbour.c:2438
 netlink_dump+0x9ad/0x1540 net/netlink/af_netlink.c:2225
 __netlink_dump_start+0x1167/0x12a0 net/netlink/af_netlink.c:2322
 netlink_dump_start include/linux/netlink.h:214 [inline]
 rtnetlink_rcv_msg+0x1435/0x1560 net/core/rtnetlink.c:4598
 netlink_rcv_skb+0x355/0x5f0 net/netlink/af_netlink.c:2447
 rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:4653
 netlink_unicast_kernel net/netlink/af_netlink.c:1311 [inline]
 netlink_unicast+0x1672/0x1750 net/netlink/af_netlink.c:1337
 netlink_sendmsg+0x1048/0x1310 net/netlink/af_netlink.c:1900
 sock_sendmsg_nosec net/socket.c:630 [inline]
 sock_sendmsg net/socket.c:640 [inline]
 ___sys_sendmsg+0xec0/0x1310 net/socket.c:2046
 __sys_sendmsg net/socket.c:2080 [inline]
 SYSC_sendmsg+0x2a3/0x3d0 net/socket.c:2091
 SyS_sendmsg+0x54/0x80 net/socket.c:2087
 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x3d/0xa2
RIP: 0033:0x43fed9
RSP: 002b:00007ffddbee2798 EFLAGS: 00000213 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 000000000043fed9
RDX: 0000000000000000 RSI: 0000000020005000 RDI: 0000000000000003
RBP: 00000000006ca018 R08: 00000000004002c8 R09: 00000000004002c8
R10: 00000000004002c8 R11: 0000000000000213 R12: 0000000000401800
R13: 0000000000401890 R14: 0000000000000000 R15: 0000000000000000

Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:278 [inline]
 kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:188
 kmsan_kmalloc+0x94/0x100 mm/kmsan/kmsan.c:314
 kmsan_slab_alloc+0x11/0x20 mm/kmsan/kmsan.c:321
 slab_post_alloc_hook mm/slab.h:445 [inline]
 slab_alloc_node mm/slub.c:2737 [inline]
 __kmalloc_node_track_caller+0xaed/0x11c0 mm/slub.c:4369
 __kmalloc_reserve net/core/skbuff.c:138 [inline]
 __alloc_skb+0x2cf/0x9f0 net/core/skbuff.c:206
 alloc_skb include/linux/skbuff.h:984 [inline]
 netlink_alloc_large_skb net/netlink/af_netlink.c:1183 [inline]
 netlink_sendmsg+0x9a6/0x1310 net/netlink/af_netlink.c:1875
 sock_sendmsg_nosec net/socket.c:630 [inline]
 sock_sendmsg net/socket.c:640 [inline]
 ___sys_sendmsg+0xec0/0x1310 net/socket.c:2046
 __sys_sendmsg net/socket.c:2080 [inline]
 SYSC_sendmsg+0x2a3/0x3d0 net/socket.c:2091
 SyS_sendmsg+0x54/0x80 net/socket.c:2087
 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x3d/0xa2

Fixes: 21fdd092acc7 ("net: Add support for filtering neigh dump by master device")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: David Ahern <dsa@cumulusnetworks.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 741ae2554190..a209d834daa2 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2323,12 +2323,16 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
 
 	err = nlmsg_parse(nlh, sizeof(struct ndmsg), tb, NDA_MAX, NULL, NULL);
 	if (!err) {
-		if (tb[NDA_IFINDEX])
+		if (tb[NDA_IFINDEX]) {
+			if (nla_len(tb[NDA_IFINDEX]) != sizeof(u32))
+				return -EINVAL;
 			filter_idx = nla_get_u32(tb[NDA_IFINDEX]);
-
-		if (tb[NDA_MASTER])
+		}
+		if (tb[NDA_MASTER]) {
+			if (nla_len(tb[NDA_MASTER]) != sizeof(u32))
+				return -EINVAL;
 			filter_master_idx = nla_get_u32(tb[NDA_MASTER]);
-
+		}
 		if (filter_idx || filter_master_idx)
 			flags |= NLM_F_DUMP_FILTERED;
 	}
-- 
2.14.3


From 99a40e31a7c245452f17bfc43efcf14ee436912b Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 19 Apr 2018 12:25:38 -0700
Subject: [PATCH 07/33] llc: delete timers synchronously in llc_sk_free()

[ Upstream commit b905ef9ab90115d001c1658259af4b1c65088779 ]

The connection timers of an llc sock could be still flying
after we delete them in llc_sk_free(), and even possibly
after we free the sock. We could just wait synchronously
here in case of troubles.

Note, I leave other call paths as they are, since they may
not have to wait, at least we can change them to synchronously
when needed.

Also, move the code to net/llc/llc_conn.c, which is apparently
a better place.

Reported-by: <syzbot+f922284c18ea23a8e457@syzkaller.appspotmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/llc_conn.h |  1 +
 net/llc/llc_c_ac.c     |  9 +--------
 net/llc/llc_conn.c     | 22 +++++++++++++++++++++-
 3 files changed, 23 insertions(+), 9 deletions(-)

diff --git a/include/net/llc_conn.h b/include/net/llc_conn.h
index fe994d2e5286..ea985aa7a6c5 100644
--- a/include/net/llc_conn.h
+++ b/include/net/llc_conn.h
@@ -97,6 +97,7 @@ static __inline__ char llc_backlog_type(struct sk_buff *skb)
 
 struct sock *llc_sk_alloc(struct net *net, int family, gfp_t priority,
 			  struct proto *prot, int kern);
+void llc_sk_stop_all_timers(struct sock *sk, bool sync);
 void llc_sk_free(struct sock *sk);
 
 void llc_sk_reset(struct sock *sk);
diff --git a/net/llc/llc_c_ac.c b/net/llc/llc_c_ac.c
index ea225bd2672c..f8d4ab8ca1a5 100644
--- a/net/llc/llc_c_ac.c
+++ b/net/llc/llc_c_ac.c
@@ -1096,14 +1096,7 @@ int llc_conn_ac_inc_tx_win_size(struct sock *sk, struct sk_buff *skb)
 
 int llc_conn_ac_stop_all_timers(struct sock *sk, struct sk_buff *skb)
 {
-	struct llc_sock *llc = llc_sk(sk);
-
-	del_timer(&llc->pf_cycle_timer.timer);
-	del_timer(&llc->ack_timer.timer);
-	del_timer(&llc->rej_sent_timer.timer);
-	del_timer(&llc->busy_state_timer.timer);
-	llc->ack_must_be_send = 0;
-	llc->ack_pf = 0;
+	llc_sk_stop_all_timers(sk, false);
 	return 0;
 }
 
diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c
index 5e91b47f0d2a..9a42448eb182 100644
--- a/net/llc/llc_conn.c
+++ b/net/llc/llc_conn.c
@@ -951,6 +951,26 @@ struct sock *llc_sk_alloc(struct net *net, int family, gfp_t priority, struct pr
 	return sk;
 }
 
+void llc_sk_stop_all_timers(struct sock *sk, bool sync)
+{
+	struct llc_sock *llc = llc_sk(sk);
+
+	if (sync) {
+		del_timer_sync(&llc->pf_cycle_timer.timer);
+		del_timer_sync(&llc->ack_timer.timer);
+		del_timer_sync(&llc->rej_sent_timer.timer);
+		del_timer_sync(&llc->busy_state_timer.timer);
+	} else {
+		del_timer(&llc->pf_cycle_timer.timer);
+		del_timer(&llc->ack_timer.timer);
+		del_timer(&llc->rej_sent_timer.timer);
+		del_timer(&llc->busy_state_timer.timer);
+	}
+
+	llc->ack_must_be_send = 0;
+	llc->ack_pf = 0;
+}
+
 /**
  *	llc_sk_free - Frees a LLC socket
  *	@sk - socket to free
@@ -963,7 +983,7 @@ void llc_sk_free(struct sock *sk)
 
 	llc->state = LLC_CONN_OUT_OF_SVC;
 	/* Stop all (possibly) running timers */
-	llc_conn_ac_stop_all_timers(sk, NULL);
+	llc_sk_stop_all_timers(sk, true);
 #ifdef DEBUG_LLC_CONN_ALLOC
 	printk(KERN_INFO "%s: unackq=%d, txq=%d\n", __func__,
 		skb_queue_len(&llc->pdu_unack_q),
-- 
2.14.3


From 4f62f59f792fa9cea140486e3baa551d9297eaf8 Mon Sep 17 00:00:00 2001
From: Jann Horn <jannh@google.com>
Date: Fri, 20 Apr 2018 15:57:30 +0200
Subject: [PATCH 08/33] tcp: don't read out-of-bounds opsize

[ Upstream commit 7e5a206ab686f098367b61aca989f5cdfa8114a3 ]

The old code reads the "opsize" variable from out-of-bounds memory (first
byte behind the segment) if a broken TCP segment ends directly after an
opcode that is neither EOL nor NOP.

The result of the read isn't used for anything, so the worst thing that
could theoretically happen is a pagefault; and since the physmap is usually
mostly contiguous, even that seems pretty unlikely.

The following C reproducer triggers the uninitialized read - however, you
can't actually see anything happen unless you put something like a
pr_warn() in tcp_parse_md5sig_option() to print the opsize.

====================================
#define _GNU_SOURCE
#include <arpa/inet.h>
#include <stdlib.h>
#include <errno.h>
#include <stdarg.h>
#include <net/if.h>
#include <linux/if.h>
#include <linux/ip.h>
#include <linux/tcp.h>
#include <linux/in.h>
#include <linux/if_tun.h>
#include <err.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <string.h>
#include <stdio.h>
#include <unistd.h>
#include <sys/ioctl.h>
#include <assert.h>

void systemf(const char *command, ...) {
  char *full_command;
  va_list ap;
  va_start(ap, command);
  if (vasprintf(&full_command, command, ap) == -1)
    err(1, "vasprintf");
  va_end(ap);
  printf("systemf: <<<%s>>>\n", full_command);
  system(full_command);
}

char *devname;

int tun_alloc(char *name) {
  int fd = open("/dev/net/tun", O_RDWR);
  if (fd == -1)
    err(1, "open tun dev");
  static struct ifreq req = { .ifr_flags = IFF_TUN|IFF_NO_PI };
  strcpy(req.ifr_name, name);
  if (ioctl(fd, TUNSETIFF, &req))
    err(1, "TUNSETIFF");
  devname = req.ifr_name;
  printf("device name: %s\n", devname);
  return fd;
}

#define IPADDR(a,b,c,d) (((a)<<0)+((b)<<8)+((c)<<16)+((d)<<24))

void sum_accumulate(unsigned int *sum, void *data, int len) {
  assert((len&2)==0);
  for (int i=0; i<len/2; i++) {
    *sum += ntohs(((unsigned short *)data)[i]);
  }
}

unsigned short sum_final(unsigned int sum) {
  sum = (sum >> 16) + (sum & 0xffff);
  sum = (sum >> 16) + (sum & 0xffff);
  return htons(~sum);
}

void fix_ip_sum(struct iphdr *ip) {
  unsigned int sum = 0;
  sum_accumulate(&sum, ip, sizeof(*ip));
  ip->check = sum_final(sum);
}

void fix_tcp_sum(struct iphdr *ip, struct tcphdr *tcp) {
  unsigned int sum = 0;
  struct {
    unsigned int saddr;
    unsigned int daddr;
    unsigned char pad;
    unsigned char proto_num;
    unsigned short tcp_len;
  } fakehdr = {
    .saddr = ip->saddr,
    .daddr = ip->daddr,
    .proto_num = ip->protocol,
    .tcp_len = htons(ntohs(ip->tot_len) - ip->ihl*4)
  };
  sum_accumulate(&sum, &fakehdr, sizeof(fakehdr));
  sum_accumulate(&sum, tcp, tcp->doff*4);
  tcp->check = sum_final(sum);
}

int main(void) {
  int tun_fd = tun_alloc("inject_dev%d");
  systemf("ip link set %s up", devname);
  systemf("ip addr add 192.168.42.1/24 dev %s", devname);

  struct {
    struct iphdr ip;
    struct tcphdr tcp;
    unsigned char tcp_opts[20];
  } __attribute__((packed)) syn_packet = {
    .ip = {
      .ihl = sizeof(struct iphdr)/4,
      .version = 4,
      .tot_len = htons(sizeof(syn_packet)),
      .ttl = 30,
      .protocol = IPPROTO_TCP,
      /* FIXUP check */
      .saddr = IPADDR(192,168,42,2),
      .daddr = IPADDR(192,168,42,1)
    },
    .tcp = {
      .source = htons(1),
      .dest = htons(1337),
      .seq = 0x12345678,
      .doff = (sizeof(syn_packet.tcp)+sizeof(syn_packet.tcp_opts))/4,
      .syn = 1,
      .window = htons(64),
      .check = 0 /*FIXUP*/
    },
    .tcp_opts = {
      /* INVALID: trailing MD5SIG opcode after NOPs */
      1, 1, 1, 1, 1,
      1, 1, 1, 1, 1,
      1, 1, 1, 1, 1,
      1, 1, 1, 1, 19
    }
  };
  fix_ip_sum(&syn_packet.ip);
  fix_tcp_sum(&syn_packet.ip, &syn_packet.tcp);
  while (1) {
    int write_res = write(tun_fd, &syn_packet, sizeof(syn_packet));
    if (write_res != sizeof(syn_packet))
      err(1, "packet write failed");
  }
}
====================================

Fixes: cfb6eeb4c860 ("[TCP]: MD5 Signature Option (RFC2385) support.")
Signed-off-by: Jann Horn <jannh@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 14474acea0bb..ebbb54bcbcac 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3892,11 +3892,8 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th)
 	int length = (th->doff << 2) - sizeof(*th);
 	const u8 *ptr = (const u8 *)(th + 1);
 
-	/* If the TCP option is too short, we can short cut */
-	if (length < TCPOLEN_MD5SIG)
-		return NULL;
-
-	while (length > 0) {
+	/* If not enough data remaining, we can short cut */
+	while (length >= TCPOLEN_MD5SIG) {
 		int opcode = *ptr++;
 		int opsize;
 
-- 
2.14.3


From 823b572fd268380adcf60207be5a7797bfe7065e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 15 Apr 2018 17:52:04 -0700
Subject: [PATCH 09/33] net: af_packet: fix race in PACKET_{R|T}X_RING

[ Upstream commit 5171b37d959641bbc619781caf62e61f7b940871 ]

In order to remove the race caught by syzbot [1], we need
to lock the socket before using po->tp_version as this could
change under us otherwise.

This means lock_sock() and release_sock() must be done by
packet_set_ring() callers.

[1] :
BUG: KMSAN: uninit-value in packet_set_ring+0x1254/0x3870 net/packet/af_packet.c:4249
CPU: 0 PID: 20195 Comm: syzkaller707632 Not tainted 4.16.0+ #83
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x185/0x1d0 lib/dump_stack.c:53
 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067
 __msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:676
 packet_set_ring+0x1254/0x3870 net/packet/af_packet.c:4249
 packet_setsockopt+0x12c6/0x5a90 net/packet/af_packet.c:3662
 SYSC_setsockopt+0x4b8/0x570 net/socket.c:1849
 SyS_setsockopt+0x76/0xa0 net/socket.c:1828
 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x3d/0xa2
RIP: 0033:0x449099
RSP: 002b:00007f42b5307ce8 EFLAGS: 00000246 ORIG_RAX: 0000000000000036
RAX: ffffffffffffffda RBX: 000000000070003c RCX: 0000000000449099
RDX: 0000000000000005 RSI: 0000000000000107 RDI: 0000000000000003
RBP: 0000000000700038 R08: 000000000000001c R09: 0000000000000000
R10: 00000000200000c0 R11: 0000000000000246 R12: 0000000000000000
R13: 000000000080eecf R14: 00007f42b53089c0 R15: 0000000000000001

Local variable description: ----req_u@packet_setsockopt
Variable was created at:
 packet_setsockopt+0x13f/0x5a90 net/packet/af_packet.c:3612
 SYSC_setsockopt+0x4b8/0x570 net/socket.c:1849

Fixes: f6fb8f100b80 ("af-packet: TPACKET_V3 flexible buffer implementation.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index f4a0587b7d5e..e829f4065dbf 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3017,6 +3017,7 @@ static int packet_release(struct socket *sock)
 
 	packet_flush_mclist(sk);
 
+	lock_sock(sk);
 	if (po->rx_ring.pg_vec) {
 		memset(&req_u, 0, sizeof(req_u));
 		packet_set_ring(sk, &req_u, 1, 0);
@@ -3026,6 +3027,7 @@ static int packet_release(struct socket *sock)
 		memset(&req_u, 0, sizeof(req_u));
 		packet_set_ring(sk, &req_u, 1, 1);
 	}
+	release_sock(sk);
 
 	f = fanout_release(sk);
 
@@ -3654,6 +3656,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 		union tpacket_req_u req_u;
 		int len;
 
+		lock_sock(sk);
 		switch (po->tp_version) {
 		case TPACKET_V1:
 		case TPACKET_V2:
@@ -3664,12 +3667,17 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 			len = sizeof(req_u.req3);
 			break;
 		}
-		if (optlen < len)
-			return -EINVAL;
-		if (copy_from_user(&req_u.req, optval, len))
-			return -EFAULT;
-		return packet_set_ring(sk, &req_u, 0,
-			optname == PACKET_TX_RING);
+		if (optlen < len) {
+			ret = -EINVAL;
+		} else {
+			if (copy_from_user(&req_u.req, optval, len))
+				ret = -EFAULT;
+			else
+				ret = packet_set_ring(sk, &req_u, 0,
+						    optname == PACKET_TX_RING);
+		}
+		release_sock(sk);
+		return ret;
 	}
 	case PACKET_COPY_THRESH:
 	{
@@ -4219,8 +4227,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 	/* Added to avoid minimal code churn */
 	struct tpacket_req *req = &req_u->req;
 
-	lock_sock(sk);
-
 	rb = tx_ring ? &po->tx_ring : &po->rx_ring;
 	rb_queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue;
 
@@ -4358,7 +4364,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 	if (pg_vec)
 		free_pg_vec(pg_vec, order, req->tp_block_nr);
 out:
-	release_sock(sk);
 	return err;
 }
 
-- 
2.14.3


From 80420d8f253d07532e645642df17babe950a734a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 11 Apr 2018 14:36:28 -0700
Subject: [PATCH 10/33] tcp: md5: reject TCP_MD5SIG or TCP_MD5SIG_EXT on
 established sockets

[ Upstream commit 7212303268918b9a203aebeacfdbd83b5e87b20d ]

syzbot/KMSAN reported an uninit-value in tcp_parse_options() [1]

I believe this was caused by a TCP_MD5SIG being set on live
flow.

This is highly unexpected, since TCP option space is limited.

For instance, presence of TCP MD5 option automatically disables
TCP TimeStamp option at SYN/SYNACK time, which we can not do
once flow has been established.

Really, adding/deleting an MD5 key only makes sense on sockets
in CLOSE or LISTEN state.

[1]
BUG: KMSAN: uninit-value in tcp_parse_options+0xd74/0x1a30 net/ipv4/tcp_input.c:3720
CPU: 1 PID: 6177 Comm: syzkaller192004 Not tainted 4.16.0+ #83
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x185/0x1d0 lib/dump_stack.c:53
 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067
 __msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:676
 tcp_parse_options+0xd74/0x1a30 net/ipv4/tcp_input.c:3720
 tcp_fast_parse_options net/ipv4/tcp_input.c:3858 [inline]
 tcp_validate_incoming+0x4f1/0x2790 net/ipv4/tcp_input.c:5184
 tcp_rcv_established+0xf60/0x2bb0 net/ipv4/tcp_input.c:5453
 tcp_v4_do_rcv+0x6cd/0xd90 net/ipv4/tcp_ipv4.c:1469
 sk_backlog_rcv include/net/sock.h:908 [inline]
 __release_sock+0x2d6/0x680 net/core/sock.c:2271
 release_sock+0x97/0x2a0 net/core/sock.c:2786
 tcp_sendmsg+0xd6/0x100 net/ipv4/tcp.c:1464
 inet_sendmsg+0x48d/0x740 net/ipv4/af_inet.c:764
 sock_sendmsg_nosec net/socket.c:630 [inline]
 sock_sendmsg net/socket.c:640 [inline]
 SYSC_sendto+0x6c3/0x7e0 net/socket.c:1747
 SyS_sendto+0x8a/0xb0 net/socket.c:1715
 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x3d/0xa2
RIP: 0033:0x448fe9
RSP: 002b:00007fd472c64d38 EFLAGS: 00000216 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 00000000006e5a30 RCX: 0000000000448fe9
RDX: 000000000000029f RSI: 0000000020a88f88 RDI: 0000000000000004
RBP: 00000000006e5a34 R08: 0000000020e68000 R09: 0000000000000010
R10: 00000000200007fd R11: 0000000000000216 R12: 0000000000000000
R13: 00007fff074899ef R14: 00007fd472c659c0 R15: 0000000000000009

Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:278 [inline]
 kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:188
 kmsan_kmalloc+0x94/0x100 mm/kmsan/kmsan.c:314
 kmsan_slab_alloc+0x11/0x20 mm/kmsan/kmsan.c:321
 slab_post_alloc_hook mm/slab.h:445 [inline]
 slab_alloc_node mm/slub.c:2737 [inline]
 __kmalloc_node_track_caller+0xaed/0x11c0 mm/slub.c:4369
 __kmalloc_reserve net/core/skbuff.c:138 [inline]
 __alloc_skb+0x2cf/0x9f0 net/core/skbuff.c:206
 alloc_skb include/linux/skbuff.h:984 [inline]
 tcp_send_ack+0x18c/0x910 net/ipv4/tcp_output.c:3624
 __tcp_ack_snd_check net/ipv4/tcp_input.c:5040 [inline]
 tcp_ack_snd_check net/ipv4/tcp_input.c:5053 [inline]
 tcp_rcv_established+0x2103/0x2bb0 net/ipv4/tcp_input.c:5469
 tcp_v4_do_rcv+0x6cd/0xd90 net/ipv4/tcp_ipv4.c:1469
 sk_backlog_rcv include/net/sock.h:908 [inline]
 __release_sock+0x2d6/0x680 net/core/sock.c:2271
 release_sock+0x97/0x2a0 net/core/sock.c:2786
 tcp_sendmsg+0xd6/0x100 net/ipv4/tcp.c:1464
 inet_sendmsg+0x48d/0x740 net/ipv4/af_inet.c:764
 sock_sendmsg_nosec net/socket.c:630 [inline]
 sock_sendmsg net/socket.c:640 [inline]
 SYSC_sendto+0x6c3/0x7e0 net/socket.c:1747
 SyS_sendto+0x8a/0xb0 net/socket.c:1715
 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x3d/0xa2

Fixes: cfb6eeb4c860 ("[TCP]: MD5 Signature Option (RFC2385) support.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 38b9a6276a9d..e8d8140cd33f 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2742,8 +2742,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 #ifdef CONFIG_TCP_MD5SIG
 	case TCP_MD5SIG:
 	case TCP_MD5SIG_EXT:
-		/* Read the IP->Key mappings from userspace */
-		err = tp->af_specific->md5_parse(sk, optname, optval, optlen);
+		if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))
+			err = tp->af_specific->md5_parse(sk, optname, optval, optlen);
+		else
+			err = -EINVAL;
 		break;
 #endif
 	case TCP_USER_TIMEOUT:
-- 
2.14.3


From 53979b376e60f8cedfad7a8adeff6efa33fc022d Mon Sep 17 00:00:00 2001
From: Wolfgang Bumiller <w.bumiller@proxmox.com>
Date: Thu, 12 Apr 2018 10:46:55 +0200
Subject: [PATCH 11/33] net: fix deadlock while clearing neighbor proxy table

[ Upstream commit 53b76cdf7e8fecec1d09e38aad2f8579882591a8 ]

When coming from ndisc_netdev_event() in net/ipv6/ndisc.c,
neigh_ifdown() is called with &nd_tbl, locking this while
clearing the proxy neighbor entries when eg. deleting an
interface. Calling the table's pndisc_destructor() with the
lock still held, however, can cause a deadlock: When a
multicast listener is available an IGMP packet of type
ICMPV6_MGM_REDUCTION may be sent out. When reaching
ip6_finish_output2(), if no neighbor entry for the target
address is found, __neigh_create() is called with &nd_tbl,
which it'll want to lock.

Move the elements into their own list, then unlock the table
and perform the destruction.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=199289
Fixes: 6fd6ce2056de ("ipv6: Do not depend on rt->n in ip6_finish_output2().")
Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 28 ++++++++++++++++++----------
 1 file changed, 18 insertions(+), 10 deletions(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index a209d834daa2..514d697d4691 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -55,7 +55,8 @@ static void neigh_timer_handler(unsigned long arg);
 static void __neigh_notify(struct neighbour *n, int type, int flags,
 			   u32 pid);
 static void neigh_update_notify(struct neighbour *neigh, u32 nlmsg_pid);
-static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev);
+static int pneigh_ifdown_and_unlock(struct neigh_table *tbl,
+				    struct net_device *dev);
 
 #ifdef CONFIG_PROC_FS
 static const struct file_operations neigh_stat_seq_fops;
@@ -291,8 +292,7 @@ int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev)
 {
 	write_lock_bh(&tbl->lock);
 	neigh_flush_dev(tbl, dev);
-	pneigh_ifdown(tbl, dev);
-	write_unlock_bh(&tbl->lock);
+	pneigh_ifdown_and_unlock(tbl, dev);
 
 	del_timer_sync(&tbl->proxy_timer);
 	pneigh_queue_purge(&tbl->proxy_queue);
@@ -681,9 +681,10 @@ int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *pkey,
 	return -ENOENT;
 }
 
-static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev)
+static int pneigh_ifdown_and_unlock(struct neigh_table *tbl,
+				    struct net_device *dev)
 {
-	struct pneigh_entry *n, **np;
+	struct pneigh_entry *n, **np, *freelist = NULL;
 	u32 h;
 
 	for (h = 0; h <= PNEIGH_HASHMASK; h++) {
@@ -691,16 +692,23 @@ static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev)
 		while ((n = *np) != NULL) {
 			if (!dev || n->dev == dev) {
 				*np = n->next;
-				if (tbl->pdestructor)
-					tbl->pdestructor(n);
-				if (n->dev)
-					dev_put(n->dev);
-				kfree(n);
+				n->next = freelist;
+				freelist = n;
 				continue;
 			}
 			np = &n->next;
 		}
 	}
+	write_unlock_bh(&tbl->lock);
+	while ((n = freelist)) {
+		freelist = n->next;
+		n->next = NULL;
+		if (tbl->pdestructor)
+			tbl->pdestructor(n);
+		if (n->dev)
+			dev_put(n->dev);
+		kfree(n);
+	}
 	return -ENOENT;
 }
 
-- 
2.14.3


From d50bdc53151e33ede3068aeabab651e96dbccc81 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 13 Apr 2018 13:59:25 +0200
Subject: [PATCH 12/33] team: avoid adding twice the same option to the event
 list

[ Upstream commit 4fb0534fb7bbc2346ba7d3a072b538007f4135a5 ]

When parsing the options provided by the user space,
team_nl_cmd_options_set() insert them in a temporary list to send
multiple events with a single message.
While each option's attribute is correctly validated, the code does
not check for duplicate entries before inserting into the event
list.

Exploiting the above, the syzbot was able to trigger the following
splat:

kernel BUG at lib/list_debug.c:31!
invalid opcode: 0000 [#1] SMP KASAN
Dumping ftrace buffer:
    (ftrace buffer empty)
Modules linked in:
CPU: 0 PID: 4466 Comm: syzkaller556835 Not tainted 4.16.0+ #17
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
RIP: 0010:__list_add_valid+0xaa/0xb0 lib/list_debug.c:29
RSP: 0018:ffff8801b04bf248 EFLAGS: 00010286
RAX: 0000000000000058 RBX: ffff8801c8fc7a90 RCX: 0000000000000000
RDX: 0000000000000058 RSI: ffffffff815fbf41 RDI: ffffed0036097e3f
RBP: ffff8801b04bf260 R08: ffff8801b0b2a700 R09: ffffed003b604f90
R10: ffffed003b604f90 R11: ffff8801db027c87 R12: ffff8801c8fc7a90
R13: ffff8801c8fc7a90 R14: dffffc0000000000 R15: 0000000000000000
FS:  0000000000b98880(0000) GS:ffff8801db000000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000000000043fc30 CR3: 00000001afe8e000 CR4: 00000000001406f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
  __list_add include/linux/list.h:60 [inline]
  list_add include/linux/list.h:79 [inline]
  team_nl_cmd_options_set+0x9ff/0x12b0 drivers/net/team/team.c:2571
  genl_family_rcv_msg+0x889/0x1120 net/netlink/genetlink.c:599
  genl_rcv_msg+0xc6/0x170 net/netlink/genetlink.c:624
  netlink_rcv_skb+0x172/0x440 net/netlink/af_netlink.c:2448
  genl_rcv+0x28/0x40 net/netlink/genetlink.c:635
  netlink_unicast_kernel net/netlink/af_netlink.c:1310 [inline]
  netlink_unicast+0x58b/0x740 net/netlink/af_netlink.c:1336
  netlink_sendmsg+0x9f0/0xfa0 net/netlink/af_netlink.c:1901
  sock_sendmsg_nosec net/socket.c:629 [inline]
  sock_sendmsg+0xd5/0x120 net/socket.c:639
  ___sys_sendmsg+0x805/0x940 net/socket.c:2117
  __sys_sendmsg+0x115/0x270 net/socket.c:2155
  SYSC_sendmsg net/socket.c:2164 [inline]
  SyS_sendmsg+0x29/0x30 net/socket.c:2162
  do_syscall_64+0x29e/0x9d0 arch/x86/entry/common.c:287
  entry_SYSCALL_64_after_hwframe+0x42/0xb7
RIP: 0033:0x4458b9
RSP: 002b:00007ffd1d4a7278 EFLAGS: 00000213 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 000000000000001b RCX: 00000000004458b9
RDX: 0000000000000010 RSI: 0000000020000d00 RDI: 0000000000000004
RBP: 00000000004a74ed R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000213 R12: 00007ffd1d4a7348
R13: 0000000000402a60 R14: 0000000000000000 R15: 0000000000000000
Code: 75 e8 eb a9 48 89 f7 48 89 75 e8 e8 d1 85 7b fe 48 8b 75 e8 eb bb 48
89 f2 48 89 d9 4c 89 e6 48 c7 c7 a0 84 d8 87 e8 ea 67 28 fe <0f> 0b 0f 1f
40 00 48 b8 00 00 00 00 00 fc ff df 55 48 89 e5 41
RIP: __list_add_valid+0xaa/0xb0 lib/list_debug.c:29 RSP: ffff8801b04bf248

This changeset addresses the avoiding list_add() if the current
option is already present in the event list.

Reported-and-tested-by: syzbot+4d4af685432dc0e56c91@syzkaller.appspotmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Fixes: 2fcdb2c9e659 ("team: allow to send multiple set events in one message")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 2a366554c503..91a0209756d5 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -261,6 +261,17 @@ static void __team_option_inst_mark_removed_port(struct team *team,
 	}
 }
 
+static bool __team_option_inst_tmp_find(const struct list_head *opts,
+					const struct team_option_inst *needle)
+{
+	struct team_option_inst *opt_inst;
+
+	list_for_each_entry(opt_inst, opts, tmp_list)
+		if (opt_inst == needle)
+			return true;
+	return false;
+}
+
 static int __team_options_register(struct team *team,
 				   const struct team_option *option,
 				   size_t option_count)
@@ -2561,6 +2572,14 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info)
 			if (err)
 				goto team_put;
 			opt_inst->changed = true;
+
+			/* dumb/evil user-space can send us duplicate opt,
+			 * keep only the last one
+			 */
+			if (__team_option_inst_tmp_find(&opt_inst_list,
+							opt_inst))
+				continue;
+
 			list_add(&opt_inst->tmp_list, &opt_inst_list);
 		}
 		if (!opt_found) {
-- 
2.14.3


From 86ebbd49923a1558295f5f26d08274e3530342cc Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.vnet.ibm.com>
Date: Thu, 19 Apr 2018 15:56:40 +0200
Subject: [PATCH 13/33] net/smc: fix shutdown in state SMC_LISTEN

[ Upstream commit 1255fcb2a655f05e02f3a74675a6d6525f187afd ]

Calling shutdown with SHUT_RD and SHUT_RDWR for a listening SMC socket
crashes, because
   commit 127f49705823 ("net/smc: release clcsock from tcp_listen_worker")
releases the internal clcsock in smc_close_active() and sets smc->clcsock
to NULL.
For SHUT_RD the smc_close_active() call is removed.
For SHUT_RDWR the kernel_sock_shutdown() call is omitted, since the
clcsock is already released.

Fixes: 127f49705823 ("net/smc: release clcsock from tcp_listen_worker")
Signed-off-by: Ursula Braun <ubraun@linux.vnet.ibm.com>
Reported-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/af_smc.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index a6d604fd9695..f9c289e05707 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1203,14 +1203,12 @@ static int smc_shutdown(struct socket *sock, int how)
 		rc = smc_close_shutdown_write(smc);
 		break;
 	case SHUT_RD:
-		if (sk->sk_state == SMC_LISTEN)
-			rc = smc_close_active(smc);
-		else
-			rc = 0;
-			/* nothing more to do because peer is not involved */
+		rc = 0;
+		/* nothing more to do because peer is not involved */
 		break;
 	}
-	rc1 = kernel_sock_shutdown(smc->clcsock, how);
+	if (smc->clcsock)
+		rc1 = kernel_sock_shutdown(smc->clcsock, how);
 	/* map sock_shutdown_cmd constants to sk_shutdown value range */
 	sk->sk_shutdown |= how + 1;
 
-- 
2.14.3


From ce48a9c76359d43a7fa011502a2f032caf2ea47d Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 24 Apr 2018 14:33:37 +0800
Subject: [PATCH 14/33] team: fix netconsole setup over team
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 9cf2f437ca5b39828984064fad213e68fc17ef11 ]

The same fix in Commit dbe173079ab5 ("bridge: fix netconsole
setup over bridge") is also needed for team driver.

While at it, remove the unnecessary parameter *team from
team_port_enable_netpoll().

v1->v2:
  - fix it in a better way, as does bridge.

Fixes: 0fb52a27a04a ("team: cleanup netpoll clode")
Reported-by: João Avelino Bellomo Filho <jbellomo@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 91a0209756d5..8a222ae5950e 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1072,14 +1072,11 @@ static void team_port_leave(struct team *team, struct team_port *port)
 }
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
-static int team_port_enable_netpoll(struct team *team, struct team_port *port)
+static int __team_port_enable_netpoll(struct team_port *port)
 {
 	struct netpoll *np;
 	int err;
 
-	if (!team->dev->npinfo)
-		return 0;
-
 	np = kzalloc(sizeof(*np), GFP_KERNEL);
 	if (!np)
 		return -ENOMEM;
@@ -1093,6 +1090,14 @@ static int team_port_enable_netpoll(struct team *team, struct team_port *port)
 	return err;
 }
 
+static int team_port_enable_netpoll(struct team_port *port)
+{
+	if (!port->team->dev->npinfo)
+		return 0;
+
+	return __team_port_enable_netpoll(port);
+}
+
 static void team_port_disable_netpoll(struct team_port *port)
 {
 	struct netpoll *np = port->np;
@@ -1107,7 +1112,7 @@ static void team_port_disable_netpoll(struct team_port *port)
 	kfree(np);
 }
 #else
-static int team_port_enable_netpoll(struct team *team, struct team_port *port)
+static int team_port_enable_netpoll(struct team_port *port)
 {
 	return 0;
 }
@@ -1215,7 +1220,7 @@ static int team_port_add(struct team *team, struct net_device *port_dev)
 		goto err_vids_add;
 	}
 
-	err = team_port_enable_netpoll(team, port);
+	err = team_port_enable_netpoll(port);
 	if (err) {
 		netdev_err(dev, "Failed to enable netpoll on device %s\n",
 			   portname);
@@ -1912,7 +1917,7 @@ static int team_netpoll_setup(struct net_device *dev,
 
 	mutex_lock(&team->lock);
 	list_for_each_entry(port, &team->port_list, list) {
-		err = team_port_enable_netpoll(team, port);
+		err = __team_port_enable_netpoll(port);
 		if (err) {
 			__team_netpoll_cleanup(team);
 			break;
-- 
2.14.3


From e8d5d257c7d14c562fcb8a11e29822d25c421bec Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Mon, 23 Apr 2018 17:37:03 -0400
Subject: [PATCH 15/33] packet: fix bitfield update race

[ Upstream commit a6361f0ca4b25460f2cdf3235ebe8115f622901e ]

Updates to the bitfields in struct packet_sock are not atomic.
Serialize these read-modify-write cycles.

Move po->running into a separate variable. Its writes are protected by
po->bind_lock (except for one startup case at packet_create). Also
replace a textual precondition warning with lockdep annotation.

All others are set only in packet_setsockopt. Serialize these
updates by holding the socket lock. Analogous to other field updates,
also hold the lock when testing whether a ring is active (pg_vec).

Fixes: 8dc419447415 ("[PACKET]: Add optional checksum computation for recvmsg")
Reported-by: DaeRyong Jeong <threeearcat@gmail.com>
Reported-by: Byoungyoung Lee <byoungyoung@purdue.edu>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 60 ++++++++++++++++++++++++++++++++++++--------------
 net/packet/internal.h  | 10 ++++-----
 2 files changed, 49 insertions(+), 21 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index e829f4065dbf..3994b71f8197 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -331,11 +331,11 @@ static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb)
 	skb_set_queue_mapping(skb, queue_index);
 }
 
-/* register_prot_hook must be invoked with the po->bind_lock held,
+/* __register_prot_hook must be invoked through register_prot_hook
  * or from a context in which asynchronous accesses to the packet
  * socket is not possible (packet_create()).
  */
-static void register_prot_hook(struct sock *sk)
+static void __register_prot_hook(struct sock *sk)
 {
 	struct packet_sock *po = pkt_sk(sk);
 
@@ -350,8 +350,13 @@ static void register_prot_hook(struct sock *sk)
 	}
 }
 
-/* {,__}unregister_prot_hook() must be invoked with the po->bind_lock
- * held.   If the sync parameter is true, we will temporarily drop
+static void register_prot_hook(struct sock *sk)
+{
+	lockdep_assert_held_once(&pkt_sk(sk)->bind_lock);
+	__register_prot_hook(sk);
+}
+
+/* If the sync parameter is true, we will temporarily drop
  * the po->bind_lock and do a synchronize_net to make sure no
  * asynchronous packet processing paths still refer to the elements
  * of po->prot_hook.  If the sync parameter is false, it is the
@@ -361,6 +366,8 @@ static void __unregister_prot_hook(struct sock *sk, bool sync)
 {
 	struct packet_sock *po = pkt_sk(sk);
 
+	lockdep_assert_held_once(&po->bind_lock);
+
 	po->running = 0;
 
 	if (po->fanout)
@@ -3261,7 +3268,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol,
 
 	if (proto) {
 		po->prot_hook.type = proto;
-		register_prot_hook(sk);
+		__register_prot_hook(sk);
 	}
 
 	mutex_lock(&net->packet.sklist_lock);
@@ -3743,12 +3750,18 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 
 		if (optlen != sizeof(val))
 			return -EINVAL;
-		if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
-			return -EBUSY;
 		if (copy_from_user(&val, optval, sizeof(val)))
 			return -EFAULT;
-		po->tp_loss = !!val;
-		return 0;
+
+		lock_sock(sk);
+		if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+			ret = -EBUSY;
+		} else {
+			po->tp_loss = !!val;
+			ret = 0;
+		}
+		release_sock(sk);
+		return ret;
 	}
 	case PACKET_AUXDATA:
 	{
@@ -3759,7 +3772,9 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 		if (copy_from_user(&val, optval, sizeof(val)))
 			return -EFAULT;
 
+		lock_sock(sk);
 		po->auxdata = !!val;
+		release_sock(sk);
 		return 0;
 	}
 	case PACKET_ORIGDEV:
@@ -3771,7 +3786,9 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 		if (copy_from_user(&val, optval, sizeof(val)))
 			return -EFAULT;
 
+		lock_sock(sk);
 		po->origdev = !!val;
+		release_sock(sk);
 		return 0;
 	}
 	case PACKET_VNET_HDR:
@@ -3780,15 +3797,20 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 
 		if (sock->type != SOCK_RAW)
 			return -EINVAL;
-		if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
-			return -EBUSY;
 		if (optlen < sizeof(val))
 			return -EINVAL;
 		if (copy_from_user(&val, optval, sizeof(val)))
 			return -EFAULT;
 
-		po->has_vnet_hdr = !!val;
-		return 0;
+		lock_sock(sk);
+		if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+			ret = -EBUSY;
+		} else {
+			po->has_vnet_hdr = !!val;
+			ret = 0;
+		}
+		release_sock(sk);
+		return ret;
 	}
 	case PACKET_TIMESTAMP:
 	{
@@ -3826,11 +3848,17 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 
 		if (optlen != sizeof(val))
 			return -EINVAL;
-		if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
-			return -EBUSY;
 		if (copy_from_user(&val, optval, sizeof(val)))
 			return -EFAULT;
-		po->tp_tx_has_off = !!val;
+
+		lock_sock(sk);
+		if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+			ret = -EBUSY;
+		} else {
+			po->tp_tx_has_off = !!val;
+			ret = 0;
+		}
+		release_sock(sk);
 		return 0;
 	}
 	case PACKET_QDISC_BYPASS:
diff --git a/net/packet/internal.h b/net/packet/internal.h
index a1d2b2319ae9..3bb7c5fb3bff 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -112,10 +112,12 @@ struct packet_sock {
 	int			copy_thresh;
 	spinlock_t		bind_lock;
 	struct mutex		pg_vec_lock;
-	unsigned int		running:1,	/* prot_hook is attached*/
-				auxdata:1,
+	unsigned int		running;	/* bind_lock must be held */
+	unsigned int		auxdata:1,	/* writer must hold sock lock */
 				origdev:1,
-				has_vnet_hdr:1;
+				has_vnet_hdr:1,
+				tp_loss:1,
+				tp_tx_has_off:1;
 	int			pressure;
 	int			ifindex;	/* bound device		*/
 	__be16			num;
@@ -125,8 +127,6 @@ struct packet_sock {
 	enum tpacket_versions	tp_version;
 	unsigned int		tp_hdrlen;
 	unsigned int		tp_reserve;
-	unsigned int		tp_loss:1;
-	unsigned int		tp_tx_has_off:1;
 	unsigned int		tp_tstamp;
 	struct net_device __rcu	*cached_dev;
 	int			(*xmit)(struct sk_buff *skb);
-- 
2.14.3


From 8689a2f272f3975e6f45aa9182560722396195e1 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 16 Apr 2018 08:29:42 -0700
Subject: [PATCH 16/33] tipc: add policy for TIPC_NLA_NET_ADDR

[ Upstream commit ec518f21cb1a1b1f8a516499ea05c60299e04963 ]

Before syzbot/KMSAN bites, add the missing policy for TIPC_NLA_NET_ADDR

Fixes: 27c21416727a ("tipc: add net set to new netlink api")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jon Maloy <jon.maloy@ericsson.com>
Cc: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/netlink.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index b76f13f6fea1..d4e0bbeee727 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -79,7 +79,8 @@ const struct nla_policy tipc_nl_sock_policy[TIPC_NLA_SOCK_MAX + 1] = {
 
 const struct nla_policy tipc_nl_net_policy[TIPC_NLA_NET_MAX + 1] = {
 	[TIPC_NLA_NET_UNSPEC]		= { .type = NLA_UNSPEC },
-	[TIPC_NLA_NET_ID]		= { .type = NLA_U32 }
+	[TIPC_NLA_NET_ID]		= { .type = NLA_U32 },
+	[TIPC_NLA_NET_ADDR]		= { .type = NLA_U32 },
 };
 
 const struct nla_policy tipc_nl_link_policy[TIPC_NLA_LINK_MAX + 1] = {
-- 
2.14.3


From 69f0b01bc35ca918cc897dafe9d502cc0fd42458 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Mon, 23 Apr 2018 16:38:27 +0200
Subject: [PATCH 17/33] pppoe: check sockaddr length in pppoe_connect()

[ Upstream commit a49e2f5d5fb141884452ddb428f551b123d436b5 ]

We must validate sockaddr_len, otherwise userspace can pass fewer data
than we expect and we end up accessing invalid data.

Fixes: 224cf5ad14c0 ("ppp: Move the PPP drivers")
Reported-by: syzbot+4f03bdf92fdf9ef5ddab@syzkaller.appspotmail.com
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pppoe.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 5aa59f41bf8c..71e2aef6b7a1 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -620,6 +620,10 @@ static int pppoe_connect(struct socket *sock, struct sockaddr *uservaddr,
 	lock_sock(sk);
 
 	error = -EINVAL;
+
+	if (sockaddr_len != sizeof(struct sockaddr_pppox))
+		goto end;
+
 	if (sp->sa_protocol != PX_PROTO_OE)
 		goto end;
 
-- 
2.14.3


From d9f57759f1be077579edb14c54265a38288a72fe Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Tue, 17 Apr 2018 18:46:14 +0900
Subject: [PATCH 18/33] vlan: Fix reading memory beyond skb->tail in
 skb_vlan_tagged_multi

[ Upstream commit 7ce2367254e84753bceb07327aaf5c953cfce117 ]

Syzkaller spotted an old bug which leads to reading skb beyond tail by 4
bytes on vlan tagged packets.
This is caused because skb_vlan_tagged_multi() did not check
skb_headlen.

BUG: KMSAN: uninit-value in eth_type_vlan include/linux/if_vlan.h:283 [inline]
BUG: KMSAN: uninit-value in skb_vlan_tagged_multi include/linux/if_vlan.h:656 [inline]
BUG: KMSAN: uninit-value in vlan_features_check include/linux/if_vlan.h:672 [inline]
BUG: KMSAN: uninit-value in dflt_features_check net/core/dev.c:2949 [inline]
BUG: KMSAN: uninit-value in netif_skb_features+0xd1b/0xdc0 net/core/dev.c:3009
CPU: 1 PID: 3582 Comm: syzkaller435149 Not tainted 4.16.0+ #82
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
  __dump_stack lib/dump_stack.c:17 [inline]
  dump_stack+0x185/0x1d0 lib/dump_stack.c:53
  kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067
  __msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:676
  eth_type_vlan include/linux/if_vlan.h:283 [inline]
  skb_vlan_tagged_multi include/linux/if_vlan.h:656 [inline]
  vlan_features_check include/linux/if_vlan.h:672 [inline]
  dflt_features_check net/core/dev.c:2949 [inline]
  netif_skb_features+0xd1b/0xdc0 net/core/dev.c:3009
  validate_xmit_skb+0x89/0x1320 net/core/dev.c:3084
  __dev_queue_xmit+0x1cb2/0x2b60 net/core/dev.c:3549
  dev_queue_xmit+0x4b/0x60 net/core/dev.c:3590
  packet_snd net/packet/af_packet.c:2944 [inline]
  packet_sendmsg+0x7c57/0x8a10 net/packet/af_packet.c:2969
  sock_sendmsg_nosec net/socket.c:630 [inline]
  sock_sendmsg net/socket.c:640 [inline]
  sock_write_iter+0x3b9/0x470 net/socket.c:909
  do_iter_readv_writev+0x7bb/0x970 include/linux/fs.h:1776
  do_iter_write+0x30d/0xd40 fs/read_write.c:932
  vfs_writev fs/read_write.c:977 [inline]
  do_writev+0x3c9/0x830 fs/read_write.c:1012
  SYSC_writev+0x9b/0xb0 fs/read_write.c:1085
  SyS_writev+0x56/0x80 fs/read_write.c:1082
  do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
  entry_SYSCALL_64_after_hwframe+0x3d/0xa2
RIP: 0033:0x43ffa9
RSP: 002b:00007fff2cff3948 EFLAGS: 00000217 ORIG_RAX: 0000000000000014
RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 000000000043ffa9
RDX: 0000000000000001 RSI: 0000000020000080 RDI: 0000000000000003
RBP: 00000000006cb018 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000217 R12: 00000000004018d0
R13: 0000000000401960 R14: 0000000000000000 R15: 0000000000000000

Uninit was created at:
  kmsan_save_stack_with_flags mm/kmsan/kmsan.c:278 [inline]
  kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:188
  kmsan_kmalloc+0x94/0x100 mm/kmsan/kmsan.c:314
  kmsan_slab_alloc+0x11/0x20 mm/kmsan/kmsan.c:321
  slab_post_alloc_hook mm/slab.h:445 [inline]
  slab_alloc_node mm/slub.c:2737 [inline]
  __kmalloc_node_track_caller+0xaed/0x11c0 mm/slub.c:4369
  __kmalloc_reserve net/core/skbuff.c:138 [inline]
  __alloc_skb+0x2cf/0x9f0 net/core/skbuff.c:206
  alloc_skb include/linux/skbuff.h:984 [inline]
  alloc_skb_with_frags+0x1d4/0xb20 net/core/skbuff.c:5234
  sock_alloc_send_pskb+0xb56/0x1190 net/core/sock.c:2085
  packet_alloc_skb net/packet/af_packet.c:2803 [inline]
  packet_snd net/packet/af_packet.c:2894 [inline]
  packet_sendmsg+0x6444/0x8a10 net/packet/af_packet.c:2969
  sock_sendmsg_nosec net/socket.c:630 [inline]
  sock_sendmsg net/socket.c:640 [inline]
  sock_write_iter+0x3b9/0x470 net/socket.c:909
  do_iter_readv_writev+0x7bb/0x970 include/linux/fs.h:1776
  do_iter_write+0x30d/0xd40 fs/read_write.c:932
  vfs_writev fs/read_write.c:977 [inline]
  do_writev+0x3c9/0x830 fs/read_write.c:1012
  SYSC_writev+0x9b/0xb0 fs/read_write.c:1085
  SyS_writev+0x56/0x80 fs/read_write.c:1082
  do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
  entry_SYSCALL_64_after_hwframe+0x3d/0xa2

Fixes: 58e998c6d239 ("offloading: Force software GSO for multiple vlan tags.")
Reported-and-tested-by: syzbot+0bbe42c764feafa82c5a@syzkaller.appspotmail.com
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_vlan.h | 7 +++++--
 net/core/dev.c          | 2 +-
 2 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 5e6a2d4dc366..ab927383c99d 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -584,7 +584,7 @@ static inline bool skb_vlan_tagged(const struct sk_buff *skb)
  * Returns true if the skb is tagged with multiple vlan headers, regardless
  * of whether it is hardware accelerated or not.
  */
-static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb)
+static inline bool skb_vlan_tagged_multi(struct sk_buff *skb)
 {
 	__be16 protocol = skb->protocol;
 
@@ -594,6 +594,9 @@ static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb)
 		if (likely(!eth_type_vlan(protocol)))
 			return false;
 
+		if (unlikely(!pskb_may_pull(skb, VLAN_ETH_HLEN)))
+			return false;
+
 		veh = (struct vlan_ethhdr *)skb->data;
 		protocol = veh->h_vlan_encapsulated_proto;
 	}
@@ -611,7 +614,7 @@ static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb)
  *
  * Returns features without unsafe ones if the skb has multiple tags.
  */
-static inline netdev_features_t vlan_features_check(const struct sk_buff *skb,
+static inline netdev_features_t vlan_features_check(struct sk_buff *skb,
 						    netdev_features_t features)
 {
 	if (skb_vlan_tagged_multi(skb)) {
diff --git a/net/core/dev.c b/net/core/dev.c
index 4be2a4047640..e7d56c5adde6 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2903,7 +2903,7 @@ netdev_features_t passthru_features_check(struct sk_buff *skb,
 }
 EXPORT_SYMBOL(passthru_features_check);
 
-static netdev_features_t dflt_features_check(const struct sk_buff *skb,
+static netdev_features_t dflt_features_check(struct sk_buff *skb,
 					     struct net_device *dev,
 					     netdev_features_t features)
 {
-- 
2.14.3


From fbe15968a850f6df3fb1c7202b69f4ea2ffab17b Mon Sep 17 00:00:00 2001
From: Tom Lendacky <thomas.lendacky@amd.com>
Date: Mon, 23 Apr 2018 11:43:08 -0500
Subject: [PATCH 19/33] amd-xgbe: Add pre/post auto-negotiation phy hooks

[ Upstream commit 4d945663a6a0acf3cbe45940503f2eb9584bfee7 ]

Add hooks to the driver auto-negotiation (AN) flow to allow the different
phy implementations to perform any steps necessary to improve AN.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe-mdio.c | 16 ++++++++++++++--
 drivers/net/ethernet/amd/xgbe/xgbe.h      |  5 +++++
 2 files changed, 19 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
index 072b9f664597..e3d361e242aa 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
@@ -437,6 +437,9 @@ static void xgbe_an73_disable(struct xgbe_prv_data *pdata)
 
 static void xgbe_an_restart(struct xgbe_prv_data *pdata)
 {
+	if (pdata->phy_if.phy_impl.an_pre)
+		pdata->phy_if.phy_impl.an_pre(pdata);
+
 	switch (pdata->an_mode) {
 	case XGBE_AN_MODE_CL73:
 	case XGBE_AN_MODE_CL73_REDRV:
@@ -453,6 +456,9 @@ static void xgbe_an_restart(struct xgbe_prv_data *pdata)
 
 static void xgbe_an_disable(struct xgbe_prv_data *pdata)
 {
+	if (pdata->phy_if.phy_impl.an_post)
+		pdata->phy_if.phy_impl.an_post(pdata);
+
 	switch (pdata->an_mode) {
 	case XGBE_AN_MODE_CL73:
 	case XGBE_AN_MODE_CL73_REDRV:
@@ -637,11 +643,11 @@ static enum xgbe_an xgbe_an73_incompat_link(struct xgbe_prv_data *pdata)
 			return XGBE_AN_NO_LINK;
 	}
 
-	xgbe_an73_disable(pdata);
+	xgbe_an_disable(pdata);
 
 	xgbe_switch_mode(pdata);
 
-	xgbe_an73_restart(pdata);
+	xgbe_an_restart(pdata);
 
 	return XGBE_AN_INCOMPAT_LINK;
 }
@@ -820,6 +826,9 @@ static void xgbe_an37_state_machine(struct xgbe_prv_data *pdata)
 		pdata->an_result = pdata->an_state;
 		pdata->an_state = XGBE_AN_READY;
 
+		if (pdata->phy_if.phy_impl.an_post)
+			pdata->phy_if.phy_impl.an_post(pdata);
+
 		netif_dbg(pdata, link, pdata->netdev, "CL37 AN result: %s\n",
 			  xgbe_state_as_string(pdata->an_result));
 	}
@@ -903,6 +912,9 @@ static void xgbe_an73_state_machine(struct xgbe_prv_data *pdata)
 		pdata->kx_state = XGBE_RX_BPA;
 		pdata->an_start = 0;
 
+		if (pdata->phy_if.phy_impl.an_post)
+			pdata->phy_if.phy_impl.an_post(pdata);
+
 		netif_dbg(pdata, link, pdata->netdev, "CL73 AN result: %s\n",
 			  xgbe_state_as_string(pdata->an_result));
 	}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h
index ad102c8bac7b..fa0b51ea1b95 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe.h
@@ -833,6 +833,7 @@ struct xgbe_hw_if {
 /* This structure represents implementation specific routines for an
  * implementation of a PHY. All routines are required unless noted below.
  *   Optional routines:
+ *     an_pre, an_post
  *     kr_training_pre, kr_training_post
  */
 struct xgbe_phy_impl_if {
@@ -875,6 +876,10 @@ struct xgbe_phy_impl_if {
 	/* Process results of auto-negotiation */
 	enum xgbe_mode (*an_outcome)(struct xgbe_prv_data *);
 
+	/* Pre/Post auto-negotiation support */
+	void (*an_pre)(struct xgbe_prv_data *);
+	void (*an_post)(struct xgbe_prv_data *);
+
 	/* Pre/Post KR training enablement support */
 	void (*kr_training_pre)(struct xgbe_prv_data *);
 	void (*kr_training_post)(struct xgbe_prv_data *);
-- 
2.14.3


From 0407ee4dbb753a97459488083f7d00ead7a7d776 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 12 Apr 2018 14:24:31 +0800
Subject: [PATCH 20/33] sctp: do not check port in sctp_inet6_cmp_addr

[ Upstream commit 1071ec9d453a38023579714b64a951a2fb982071 ]

pf->cmp_addr() is called before binding a v6 address to the sock. It
should not check ports, like in sctp_inet_cmp_addr.

But sctp_inet6_cmp_addr checks the addr by invoking af(6)->cmp_addr,
sctp_v6_cmp_addr where it also compares the ports.

This would cause that setsockopt(SCTP_SOCKOPT_BINDX_ADD) could bind
multiple duplicated IPv6 addresses after Commit 40b4f0fd74e4 ("sctp:
lack the check for ports in sctp_v6_cmp_addr").

This patch is to remove af->cmp_addr called in sctp_inet6_cmp_addr,
but do the proper check for both v6 addrs and v4mapped addrs.

v1->v2:
  - define __sctp_v6_cmp_addr to do the common address comparison
    used for both pf and af v6 cmp_addr.

Fixes: 40b4f0fd74e4 ("sctp: lack the check for ports in sctp_v6_cmp_addr")
Reported-by: Jianwen Ji <jiji@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ipv6.c | 60 ++++++++++++++++++++++++++++-----------------------------
 1 file changed, 30 insertions(+), 30 deletions(-)

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 08b5705e7381..7219a1c041f7 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -521,46 +521,49 @@ static void sctp_v6_to_addr(union sctp_addr *addr, struct in6_addr *saddr,
 	addr->v6.sin6_scope_id = 0;
 }
 
-/* Compare addresses exactly.
- * v4-mapped-v6 is also in consideration.
- */
-static int sctp_v6_cmp_addr(const union sctp_addr *addr1,
-			    const union sctp_addr *addr2)
+static int __sctp_v6_cmp_addr(const union sctp_addr *addr1,
+			      const union sctp_addr *addr2)
 {
 	if (addr1->sa.sa_family != addr2->sa.sa_family) {
 		if (addr1->sa.sa_family == AF_INET &&
 		    addr2->sa.sa_family == AF_INET6 &&
-		    ipv6_addr_v4mapped(&addr2->v6.sin6_addr)) {
-			if (addr2->v6.sin6_port == addr1->v4.sin_port &&
-			    addr2->v6.sin6_addr.s6_addr32[3] ==
-			    addr1->v4.sin_addr.s_addr)
-				return 1;
-		}
+		    ipv6_addr_v4mapped(&addr2->v6.sin6_addr) &&
+		    addr2->v6.sin6_addr.s6_addr32[3] ==
+		    addr1->v4.sin_addr.s_addr)
+			return 1;
+
 		if (addr2->sa.sa_family == AF_INET &&
 		    addr1->sa.sa_family == AF_INET6 &&
-		    ipv6_addr_v4mapped(&addr1->v6.sin6_addr)) {
-			if (addr1->v6.sin6_port == addr2->v4.sin_port &&
-			    addr1->v6.sin6_addr.s6_addr32[3] ==
-			    addr2->v4.sin_addr.s_addr)
-				return 1;
-		}
+		    ipv6_addr_v4mapped(&addr1->v6.sin6_addr) &&
+		    addr1->v6.sin6_addr.s6_addr32[3] ==
+		    addr2->v4.sin_addr.s_addr)
+			return 1;
+
 		return 0;
 	}
-	if (addr1->v6.sin6_port != addr2->v6.sin6_port)
-		return 0;
+
 	if (!ipv6_addr_equal(&addr1->v6.sin6_addr, &addr2->v6.sin6_addr))
 		return 0;
+
 	/* If this is a linklocal address, compare the scope_id. */
-	if (ipv6_addr_type(&addr1->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) {
-		if (addr1->v6.sin6_scope_id && addr2->v6.sin6_scope_id &&
-		    (addr1->v6.sin6_scope_id != addr2->v6.sin6_scope_id)) {
-			return 0;
-		}
-	}
+	if ((ipv6_addr_type(&addr1->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) &&
+	    addr1->v6.sin6_scope_id && addr2->v6.sin6_scope_id &&
+	    addr1->v6.sin6_scope_id != addr2->v6.sin6_scope_id)
+		return 0;
 
 	return 1;
 }
 
+/* Compare addresses exactly.
+ * v4-mapped-v6 is also in consideration.
+ */
+static int sctp_v6_cmp_addr(const union sctp_addr *addr1,
+			    const union sctp_addr *addr2)
+{
+	return __sctp_v6_cmp_addr(addr1, addr2) &&
+	       addr1->v6.sin6_port == addr2->v6.sin6_port;
+}
+
 /* Initialize addr struct to INADDR_ANY. */
 static void sctp_v6_inaddr_any(union sctp_addr *addr, __be16 port)
 {
@@ -845,8 +848,8 @@ static int sctp_inet6_cmp_addr(const union sctp_addr *addr1,
 			       const union sctp_addr *addr2,
 			       struct sctp_sock *opt)
 {
-	struct sctp_af *af1, *af2;
 	struct sock *sk = sctp_opt2sk(opt);
+	struct sctp_af *af1, *af2;
 
 	af1 = sctp_get_af_specific(addr1->sa.sa_family);
 	af2 = sctp_get_af_specific(addr2->sa.sa_family);
@@ -862,10 +865,7 @@ static int sctp_inet6_cmp_addr(const union sctp_addr *addr1,
 	if (sctp_is_any(sk, addr1) || sctp_is_any(sk, addr2))
 		return 1;
 
-	if (addr1->sa.sa_family != addr2->sa.sa_family)
-		return 0;
-
-	return af1->cmp_addr(addr1, addr2);
+	return __sctp_v6_cmp_addr(addr1, addr2);
 }
 
 /* Verify that the provided sockaddr looks bindable.   Common verification,
-- 
2.14.3


From 6ef5ae8ff07cb4b80818887917d8178cb699c9b6 Mon Sep 17 00:00:00 2001
From: Tom Lendacky <thomas.lendacky@amd.com>
Date: Mon, 23 Apr 2018 11:43:17 -0500
Subject: [PATCH 21/33] amd-xgbe: Improve KR auto-negotiation and training

[ Upstream commit 96f4d430c507ed4856048c2dc9c1a2ea5b5e74e4 ]

Update xgbe-phy-v2.c to make use of the auto-negotiation (AN) phy hooks
to improve the ability to successfully complete Clause 73 AN when running
at 10gbps.  Hardware can sometimes have issues with CDR lock when the
AN DME page exchange is being performed.

The AN and KR training hooks are used as follows:
- The pre AN hook is used to disable CDR tracking in the PHY so that the
  DME page exchange can be successfully and consistently completed.
- The post KR training hook is used to re-enable the CDR tracking so that
  KR training can successfully complete.
- The post AN hook is used to check for an unsuccessful AN which will
  increase a CDR tracking enablement delay (up to a maximum value).

Add two debugfs entries to allow control over use of the CDR tracking
workaround.  The debugfs entries allow the CDR tracking workaround to
be disabled and determine whether to re-enable CDR tracking before or
after link training has been initiated.

Also, with these changes the receiver reset cycle that is performed during
the link status check can be performed less often.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe-common.h  |   8 ++
 drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c |  16 ++++
 drivers/net/ethernet/amd/xgbe/xgbe-main.c    |   1 +
 drivers/net/ethernet/amd/xgbe/xgbe-mdio.c    |   8 +-
 drivers/net/ethernet/amd/xgbe/xgbe-pci.c     |   2 +
 drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c  | 125 ++++++++++++++++++++++++++-
 drivers/net/ethernet/amd/xgbe/xgbe.h         |   4 +
 7 files changed, 160 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
index 7ea72ef11a55..d272dc6984ac 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
@@ -1321,6 +1321,10 @@
 #define MDIO_VEND2_AN_STAT		0x8002
 #endif
 
+#ifndef MDIO_VEND2_PMA_CDR_CONTROL
+#define MDIO_VEND2_PMA_CDR_CONTROL	0x8056
+#endif
+
 #ifndef MDIO_CTRL1_SPEED1G
 #define MDIO_CTRL1_SPEED1G		(MDIO_CTRL1_SPEED10G & ~BMCR_SPEED100)
 #endif
@@ -1369,6 +1373,10 @@
 #define XGBE_AN_CL37_TX_CONFIG_MASK	0x08
 #define XGBE_AN_CL37_MII_CTRL_8BIT	0x0100
 
+#define XGBE_PMA_CDR_TRACK_EN_MASK	0x01
+#define XGBE_PMA_CDR_TRACK_EN_OFF	0x00
+#define XGBE_PMA_CDR_TRACK_EN_ON	0x01
+
 /* Bit setting and getting macros
  *  The get macro will extract the current bit field value from within
  *  the variable
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c
index 7d128be61310..b91143947ed2 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c
@@ -519,6 +519,22 @@ void xgbe_debugfs_init(struct xgbe_prv_data *pdata)
 				   "debugfs_create_file failed\n");
 	}
 
+	if (pdata->vdata->an_cdr_workaround) {
+		pfile = debugfs_create_bool("an_cdr_workaround", 0600,
+					    pdata->xgbe_debugfs,
+					    &pdata->debugfs_an_cdr_workaround);
+		if (!pfile)
+			netdev_err(pdata->netdev,
+				   "debugfs_create_bool failed\n");
+
+		pfile = debugfs_create_bool("an_cdr_track_early", 0600,
+					    pdata->xgbe_debugfs,
+					    &pdata->debugfs_an_cdr_track_early);
+		if (!pfile)
+			netdev_err(pdata->netdev,
+				   "debugfs_create_bool failed\n");
+	}
+
 	kfree(buf);
 }
 
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-main.c b/drivers/net/ethernet/amd/xgbe/xgbe-main.c
index d91fa595be98..e31d9d1fb6a6 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-main.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-main.c
@@ -349,6 +349,7 @@ int xgbe_config_netdev(struct xgbe_prv_data *pdata)
 	XGMAC_SET_BITS(pdata->rss_options, MAC_RSSCR, UDP4TE, 1);
 
 	/* Call MDIO/PHY initialization routine */
+	pdata->debugfs_an_cdr_workaround = pdata->vdata->an_cdr_workaround;
 	ret = pdata->phy_if.phy_init(pdata);
 	if (ret)
 		return ret;
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
index e3d361e242aa..1b45cd73a258 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
@@ -432,6 +432,8 @@ static void xgbe_an73_disable(struct xgbe_prv_data *pdata)
 	xgbe_an73_set(pdata, false, false);
 	xgbe_an73_disable_interrupts(pdata);
 
+	pdata->an_start = 0;
+
 	netif_dbg(pdata, link, pdata->netdev, "CL73 AN disabled\n");
 }
 
@@ -511,11 +513,11 @@ static enum xgbe_an xgbe_an73_tx_training(struct xgbe_prv_data *pdata,
 		XMDIO_WRITE(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL,
 			    reg);
 
-		if (pdata->phy_if.phy_impl.kr_training_post)
-			pdata->phy_if.phy_impl.kr_training_post(pdata);
-
 		netif_dbg(pdata, link, pdata->netdev,
 			  "KR training initiated\n");
+
+		if (pdata->phy_if.phy_impl.kr_training_post)
+			pdata->phy_if.phy_impl.kr_training_post(pdata);
 	}
 
 	return XGBE_AN_PAGE_RECEIVED;
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
index eb23f9ba1a9a..82d1f416ee2a 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
@@ -456,6 +456,7 @@ static const struct xgbe_version_data xgbe_v2a = {
 	.irq_reissue_support		= 1,
 	.tx_desc_prefetch		= 5,
 	.rx_desc_prefetch		= 5,
+	.an_cdr_workaround		= 1,
 };
 
 static const struct xgbe_version_data xgbe_v2b = {
@@ -470,6 +471,7 @@ static const struct xgbe_version_data xgbe_v2b = {
 	.irq_reissue_support		= 1,
 	.tx_desc_prefetch		= 5,
 	.rx_desc_prefetch		= 5,
+	.an_cdr_workaround		= 1,
 };
 
 static const struct pci_device_id xgbe_pci_table[] = {
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
index 3304a291aa96..b48efc04c4da 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
@@ -147,6 +147,14 @@
 /* Rate-change complete wait/retry count */
 #define XGBE_RATECHANGE_COUNT		500
 
+/* CDR delay values for KR support (in usec) */
+#define XGBE_CDR_DELAY_INIT		10000
+#define XGBE_CDR_DELAY_INC		10000
+#define XGBE_CDR_DELAY_MAX		100000
+
+/* RRC frequency during link status check */
+#define XGBE_RRC_FREQUENCY		10
+
 enum xgbe_port_mode {
 	XGBE_PORT_MODE_RSVD = 0,
 	XGBE_PORT_MODE_BACKPLANE,
@@ -355,6 +363,10 @@ struct xgbe_phy_data {
 	unsigned int redrv_addr;
 	unsigned int redrv_lane;
 	unsigned int redrv_model;
+
+	/* KR AN support */
+	unsigned int phy_cdr_notrack;
+	unsigned int phy_cdr_delay;
 };
 
 /* I2C, MDIO and GPIO lines are muxed, so only one device at a time */
@@ -2361,7 +2373,7 @@ static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart)
 		return 1;
 
 	/* No link, attempt a receiver reset cycle */
-	if (phy_data->rrc_count++) {
+	if (phy_data->rrc_count++ > XGBE_RRC_FREQUENCY) {
 		phy_data->rrc_count = 0;
 		xgbe_phy_rrc(pdata);
 	}
@@ -2669,6 +2681,103 @@ static bool xgbe_phy_port_enabled(struct xgbe_prv_data *pdata)
 	return true;
 }
 
+static void xgbe_phy_cdr_track(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+	if (!pdata->debugfs_an_cdr_workaround)
+		return;
+
+	if (!phy_data->phy_cdr_notrack)
+		return;
+
+	usleep_range(phy_data->phy_cdr_delay,
+		     phy_data->phy_cdr_delay + 500);
+
+	XMDIO_WRITE_BITS(pdata, MDIO_MMD_PMAPMD, MDIO_VEND2_PMA_CDR_CONTROL,
+			 XGBE_PMA_CDR_TRACK_EN_MASK,
+			 XGBE_PMA_CDR_TRACK_EN_ON);
+
+	phy_data->phy_cdr_notrack = 0;
+}
+
+static void xgbe_phy_cdr_notrack(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+	if (!pdata->debugfs_an_cdr_workaround)
+		return;
+
+	if (phy_data->phy_cdr_notrack)
+		return;
+
+	XMDIO_WRITE_BITS(pdata, MDIO_MMD_PMAPMD, MDIO_VEND2_PMA_CDR_CONTROL,
+			 XGBE_PMA_CDR_TRACK_EN_MASK,
+			 XGBE_PMA_CDR_TRACK_EN_OFF);
+
+	xgbe_phy_rrc(pdata);
+
+	phy_data->phy_cdr_notrack = 1;
+}
+
+static void xgbe_phy_kr_training_post(struct xgbe_prv_data *pdata)
+{
+	if (!pdata->debugfs_an_cdr_track_early)
+		xgbe_phy_cdr_track(pdata);
+}
+
+static void xgbe_phy_kr_training_pre(struct xgbe_prv_data *pdata)
+{
+	if (pdata->debugfs_an_cdr_track_early)
+		xgbe_phy_cdr_track(pdata);
+}
+
+static void xgbe_phy_an_post(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+	switch (pdata->an_mode) {
+	case XGBE_AN_MODE_CL73:
+	case XGBE_AN_MODE_CL73_REDRV:
+		if (phy_data->cur_mode != XGBE_MODE_KR)
+			break;
+
+		xgbe_phy_cdr_track(pdata);
+
+		switch (pdata->an_result) {
+		case XGBE_AN_READY:
+		case XGBE_AN_COMPLETE:
+			break;
+		default:
+			if (phy_data->phy_cdr_delay < XGBE_CDR_DELAY_MAX)
+				phy_data->phy_cdr_delay += XGBE_CDR_DELAY_INC;
+			else
+				phy_data->phy_cdr_delay = XGBE_CDR_DELAY_INIT;
+			break;
+		}
+		break;
+	default:
+		break;
+	}
+}
+
+static void xgbe_phy_an_pre(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+	switch (pdata->an_mode) {
+	case XGBE_AN_MODE_CL73:
+	case XGBE_AN_MODE_CL73_REDRV:
+		if (phy_data->cur_mode != XGBE_MODE_KR)
+			break;
+
+		xgbe_phy_cdr_notrack(pdata);
+		break;
+	default:
+		break;
+	}
+}
+
 static void xgbe_phy_stop(struct xgbe_prv_data *pdata)
 {
 	struct xgbe_phy_data *phy_data = pdata->phy_data;
@@ -2680,6 +2789,9 @@ static void xgbe_phy_stop(struct xgbe_prv_data *pdata)
 	xgbe_phy_sfp_reset(phy_data);
 	xgbe_phy_sfp_mod_absent(pdata);
 
+	/* Reset CDR support */
+	xgbe_phy_cdr_track(pdata);
+
 	/* Power off the PHY */
 	xgbe_phy_power_off(pdata);
 
@@ -2712,6 +2824,9 @@ static int xgbe_phy_start(struct xgbe_prv_data *pdata)
 	/* Start in highest supported mode */
 	xgbe_phy_set_mode(pdata, phy_data->start_mode);
 
+	/* Reset CDR support */
+	xgbe_phy_cdr_track(pdata);
+
 	/* After starting the I2C controller, we can check for an SFP */
 	switch (phy_data->port_mode) {
 	case XGBE_PORT_MODE_SFP:
@@ -3019,6 +3134,8 @@ static int xgbe_phy_init(struct xgbe_prv_data *pdata)
 		}
 	}
 
+	phy_data->phy_cdr_delay = XGBE_CDR_DELAY_INIT;
+
 	/* Register for driving external PHYs */
 	mii = devm_mdiobus_alloc(pdata->dev);
 	if (!mii) {
@@ -3071,4 +3188,10 @@ void xgbe_init_function_ptrs_phy_v2(struct xgbe_phy_if *phy_if)
 	phy_impl->an_advertising	= xgbe_phy_an_advertising;
 
 	phy_impl->an_outcome		= xgbe_phy_an_outcome;
+
+	phy_impl->an_pre		= xgbe_phy_an_pre;
+	phy_impl->an_post		= xgbe_phy_an_post;
+
+	phy_impl->kr_training_pre	= xgbe_phy_kr_training_pre;
+	phy_impl->kr_training_post	= xgbe_phy_kr_training_post;
 }
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h
index fa0b51ea1b95..95d4b56448c6 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe.h
@@ -994,6 +994,7 @@ struct xgbe_version_data {
 	unsigned int irq_reissue_support;
 	unsigned int tx_desc_prefetch;
 	unsigned int rx_desc_prefetch;
+	unsigned int an_cdr_workaround;
 };
 
 struct xgbe_vxlan_data {
@@ -1262,6 +1263,9 @@ struct xgbe_prv_data {
 	unsigned int debugfs_xprop_reg;
 
 	unsigned int debugfs_xi2c_reg;
+
+	bool debugfs_an_cdr_workaround;
+	bool debugfs_an_cdr_track_early;
 };
 
 /* Function prototypes*/
-- 
2.14.3


From b363ff5316f334777236e7dd428c5f885b1b89bf Mon Sep 17 00:00:00 2001
From: Doron Roberts-Kedes <doronrk@fb.com>
Date: Fri, 20 Apr 2018 12:11:11 -0700
Subject: [PATCH 22/33] strparser: Do not call mod_delayed_work with a timeout
 of LONG_MAX

[ Upstream commit 7c5aba211dd61f41d737a2c51729eb9fdcd3edf4 ]

struct sock's sk_rcvtimeo is initialized to
LONG_MAX/MAX_SCHEDULE_TIMEOUT in sock_init_data. Calling
mod_delayed_work with a timeout of LONG_MAX causes spurious execution of
the work function. timer->expires is set equal to jiffies + LONG_MAX.
When timer_base->clk falls behind the current value of jiffies,
the delta between timer_base->clk and jiffies + LONG_MAX causes the
expiration to be in the past. Returning early from strp_start_timer if
timeo == LONG_MAX solves this problem.

Found while testing net/tls_sw recv path.

Fixes: 43a0c6751a322847 ("strparser: Stream parser for messages")
Reviewed-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Doron Roberts-Kedes <doronrk@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/strparser/strparser.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index 4a3a3f1331ee..6b5a7fffc62c 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -67,7 +67,7 @@ static void strp_abort_strp(struct strparser *strp, int err)
 
 static void strp_start_timer(struct strparser *strp, long timeo)
 {
-	if (timeo)
+	if (timeo && timeo != LONG_MAX)
 		mod_delayed_work(strp_wq, &strp->msg_timer_work, timeo);
 }
 
-- 
2.14.3


From 8b549d4fc15b4d9d83b387ade57506615e80f544 Mon Sep 17 00:00:00 2001
From: Tom Lendacky <thomas.lendacky@amd.com>
Date: Mon, 23 Apr 2018 11:43:34 -0500
Subject: [PATCH 23/33] amd-xgbe: Only use the SFP supported transceiver
 signals

[ Upstream commit 117df655f8ed51adb6e6b163812a06ebeae9f453 ]

The SFP eeprom indicates the transceiver signals (Rx LOS, Tx Fault, etc.)
that it supports.  Update the driver to include checking the eeprom data
when deciding whether to use a transceiver signal.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c | 71 ++++++++++++++++++++++-------
 1 file changed, 54 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
index b48efc04c4da..aac884314000 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
@@ -253,6 +253,10 @@ enum xgbe_sfp_speed {
 #define XGBE_SFP_BASE_VENDOR_SN			4
 #define XGBE_SFP_BASE_VENDOR_SN_LEN		16
 
+#define XGBE_SFP_EXTD_OPT1			1
+#define XGBE_SFP_EXTD_OPT1_RX_LOS		BIT(1)
+#define XGBE_SFP_EXTD_OPT1_TX_FAULT		BIT(3)
+
 #define XGBE_SFP_EXTD_DIAG			28
 #define XGBE_SFP_EXTD_DIAG_ADDR_CHANGE		BIT(2)
 
@@ -332,6 +336,7 @@ struct xgbe_phy_data {
 
 	unsigned int sfp_gpio_address;
 	unsigned int sfp_gpio_mask;
+	unsigned int sfp_gpio_inputs;
 	unsigned int sfp_gpio_rx_los;
 	unsigned int sfp_gpio_tx_fault;
 	unsigned int sfp_gpio_mod_absent;
@@ -986,6 +991,49 @@ static void xgbe_phy_sfp_external_phy(struct xgbe_prv_data *pdata)
 	phy_data->sfp_phy_avail = 1;
 }
 
+static bool xgbe_phy_check_sfp_rx_los(struct xgbe_phy_data *phy_data)
+{
+	u8 *sfp_extd = phy_data->sfp_eeprom.extd;
+
+	if (!(sfp_extd[XGBE_SFP_EXTD_OPT1] & XGBE_SFP_EXTD_OPT1_RX_LOS))
+		return false;
+
+	if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_RX_LOS)
+		return false;
+
+	if (phy_data->sfp_gpio_inputs & (1 << phy_data->sfp_gpio_rx_los))
+		return true;
+
+	return false;
+}
+
+static bool xgbe_phy_check_sfp_tx_fault(struct xgbe_phy_data *phy_data)
+{
+	u8 *sfp_extd = phy_data->sfp_eeprom.extd;
+
+	if (!(sfp_extd[XGBE_SFP_EXTD_OPT1] & XGBE_SFP_EXTD_OPT1_TX_FAULT))
+		return false;
+
+	if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_TX_FAULT)
+		return false;
+
+	if (phy_data->sfp_gpio_inputs & (1 << phy_data->sfp_gpio_tx_fault))
+		return true;
+
+	return false;
+}
+
+static bool xgbe_phy_check_sfp_mod_absent(struct xgbe_phy_data *phy_data)
+{
+	if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_MOD_ABSENT)
+		return false;
+
+	if (phy_data->sfp_gpio_inputs & (1 << phy_data->sfp_gpio_mod_absent))
+		return true;
+
+	return false;
+}
+
 static bool xgbe_phy_belfuse_parse_quirks(struct xgbe_prv_data *pdata)
 {
 	struct xgbe_phy_data *phy_data = pdata->phy_data;
@@ -1031,6 +1079,10 @@ static void xgbe_phy_sfp_parse_eeprom(struct xgbe_prv_data *pdata)
 	if (sfp_base[XGBE_SFP_BASE_EXT_ID] != XGBE_SFP_EXT_ID_SFP)
 		return;
 
+	/* Update transceiver signals (eeprom extd/options) */
+	phy_data->sfp_tx_fault = xgbe_phy_check_sfp_tx_fault(phy_data);
+	phy_data->sfp_rx_los = xgbe_phy_check_sfp_rx_los(phy_data);
+
 	if (xgbe_phy_sfp_parse_quirks(pdata))
 		return;
 
@@ -1196,7 +1248,6 @@ static int xgbe_phy_sfp_read_eeprom(struct xgbe_prv_data *pdata)
 static void xgbe_phy_sfp_signals(struct xgbe_prv_data *pdata)
 {
 	struct xgbe_phy_data *phy_data = pdata->phy_data;
-	unsigned int gpio_input;
 	u8 gpio_reg, gpio_ports[2];
 	int ret;
 
@@ -1211,23 +1262,9 @@ static void xgbe_phy_sfp_signals(struct xgbe_prv_data *pdata)
 		return;
 	}
 
-	gpio_input = (gpio_ports[1] << 8) | gpio_ports[0];
-
-	if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_MOD_ABSENT) {
-		/* No GPIO, just assume the module is present for now */
-		phy_data->sfp_mod_absent = 0;
-	} else {
-		if (!(gpio_input & (1 << phy_data->sfp_gpio_mod_absent)))
-			phy_data->sfp_mod_absent = 0;
-	}
-
-	if (!(phy_data->sfp_gpio_mask & XGBE_GPIO_NO_RX_LOS) &&
-	    (gpio_input & (1 << phy_data->sfp_gpio_rx_los)))
-		phy_data->sfp_rx_los = 1;
+	phy_data->sfp_gpio_inputs = (gpio_ports[1] << 8) | gpio_ports[0];
 
-	if (!(phy_data->sfp_gpio_mask & XGBE_GPIO_NO_TX_FAULT) &&
-	    (gpio_input & (1 << phy_data->sfp_gpio_tx_fault)))
-		phy_data->sfp_tx_fault = 1;
+	phy_data->sfp_mod_absent = xgbe_phy_check_sfp_mod_absent(phy_data);
 }
 
 static void xgbe_phy_sfp_mod_absent(struct xgbe_prv_data *pdata)
-- 
2.14.3


From 79d8b3c61e2dd7c6b500d0145cb45379ebcb06a1 Mon Sep 17 00:00:00 2001
From: Doron Roberts-Kedes <doronrk@fb.com>
Date: Wed, 11 Apr 2018 15:05:16 -0700
Subject: [PATCH 24/33] strparser: Fix incorrect strp->need_bytes value.

[ Upstream commit 9d0c75bf6e03d9bf80c55b0f677dc9b982958fd5 ]

strp_data_ready resets strp->need_bytes to 0 if strp_peek_len indicates
that the remainder of the message has been received. However,
do_strp_work does not reset strp->need_bytes to 0. If do_strp_work
completes a partial message, the value of strp->need_bytes will continue
to reflect the needed bytes of the previous message, causing
future invocations of strp_data_ready to return early if
strp->need_bytes is less than strp_peek_len. Resetting strp->need_bytes
to 0 in __strp_recv on handing a full message to the upper layer solves
this problem.

__strp_recv also calculates strp->need_bytes using stm->accum_len before
stm->accum_len has been incremented by cand_len. This can cause
strp->need_bytes to be equal to the full length of the message instead
of the full length minus the accumulated length. This, in turn, causes
strp_data_ready to return early, even when there is sufficient data to
complete the partial message. Incrementing stm->accum_len before using
it to calculate strp->need_bytes solves this problem.

Found while testing net/tls_sw recv path.

Fixes: 43a0c6751a322847 ("strparser: Stream parser for messages")
Signed-off-by: Doron Roberts-Kedes <doronrk@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/strparser/strparser.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index 6b5a7fffc62c..c741365f77da 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -296,9 +296,9 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb,
 					strp_start_timer(strp, timeo);
 				}
 
+				stm->accum_len += cand_len;
 				strp->need_bytes = stm->strp.full_len -
 						       stm->accum_len;
-				stm->accum_len += cand_len;
 				stm->early_eaten = cand_len;
 				STRP_STATS_ADD(strp->stats.bytes, cand_len);
 				desc->count = 0; /* Stop reading socket */
@@ -321,6 +321,7 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb,
 		/* Hurray, we have a new message! */
 		cancel_delayed_work(&strp->msg_timer_work);
 		strp->skb_head = NULL;
+		strp->need_bytes = 0;
 		STRP_STATS_INCR(strp->stats.msgs);
 
 		/* Give skb to upper layer */
@@ -410,9 +411,7 @@ void strp_data_ready(struct strparser *strp)
 		return;
 
 	if (strp->need_bytes) {
-		if (strp_peek_len(strp) >= strp->need_bytes)
-			strp->need_bytes = 0;
-		else
+		if (strp_peek_len(strp) < strp->need_bytes)
 			return;
 	}
 
-- 
2.14.3


From b5e16d864bdff4badb26b6e9eeca443e797b0c2b Mon Sep 17 00:00:00 2001
From: Alexander Aring <aring@mojatatu.com>
Date: Fri, 20 Apr 2018 15:15:03 -0400
Subject: [PATCH 25/33] net: sched: ife: signal not finding metaid

[ Upstream commit f6cd14537ff9919081be19b9c53b9b19c0d3ea97 ]

We need to record stats for received metadata that we dont know how
to process. Have find_decode_metaid() return -ENOENT to capture this.

Signed-off-by: Alexander Aring <aring@mojatatu.com>
Reviewed-by: Yotam Gigi <yotam.gi@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ife.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 8ccd35825b6b..4b4e4d490f42 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -605,7 +605,7 @@ static int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife,
 		}
 	}
 
-	return 0;
+	return -ENOENT;
 }
 
 static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a,
-- 
2.14.3


From 589282abaf79d2e031835e5c78381163d7e43b68 Mon Sep 17 00:00:00 2001
From: Soheil Hassas Yeganeh <soheil@google.com>
Date: Sat, 14 Apr 2018 20:45:20 -0400
Subject: [PATCH 26/33] tcp: clear tp->packets_out when purging write queue

Clear tp->packets_out when purging the write queue, otherwise
tcp_rearm_rto() mistakenly assumes TCP write queue is not empty.
This results in NULL pointer dereference.

Also, remove the redundant `tp->packets_out = 0` from
tcp_disconnect(), since tcp_disconnect() calls
tcp_write_queue_purge().

Fixes: a27fd7a8ed38 (tcp: purge write queue upon RST)
Reported-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Reported-by: Sami Farin <hvtaifwkbgefbaei@gmail.com>
Tested-by: Sami Farin <hvtaifwkbgefbaei@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
---
 include/net/tcp.h | 1 +
 net/ipv4/tcp.c    | 1 -
 2 files changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index d323d4fa742c..fb653736f335 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1616,6 +1616,7 @@ static inline void tcp_write_queue_purge(struct sock *sk)
 	sk_mem_reclaim(sk);
 	tcp_clear_all_retrans_hints(tcp_sk(sk));
 	tcp_init_send_head(sk);
+	tcp_sk(sk)->packets_out = 0;
 }
 
 static inline struct sk_buff *tcp_write_queue_head(const struct sock *sk)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e8d8140cd33f..d023f879e7bb 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2354,7 +2354,6 @@ int tcp_disconnect(struct sock *sk, int flags)
 	icsk->icsk_backoff = 0;
 	tp->snd_cwnd = 2;
 	icsk->icsk_probes_out = 0;
-	tp->packets_out = 0;
 	tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
 	tp->snd_cwnd_cnt = 0;
 	tp->window_clamp = 0;
-- 
2.14.3


From 8de1c00b2f638406f831e187f9a2d4e194a423cc Mon Sep 17 00:00:00 2001
From: Alexander Aring <aring@mojatatu.com>
Date: Fri, 20 Apr 2018 15:15:04 -0400
Subject: [PATCH 27/33] net: sched: ife: handle malformed tlv length

[ Upstream commit cc74eddd0ff325d57373cea99f642b787d7f76f5 ]

There is currently no handling to check on a invalid tlv length. This
patch adds such handling to avoid killing the kernel with a malformed
ife packet.

Signed-off-by: Alexander Aring <aring@mojatatu.com>
Reviewed-by: Yotam Gigi <yotam.gi@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ife.h   |  3 ++-
 net/ife/ife.c       | 35 +++++++++++++++++++++++++++++++++--
 net/sched/act_ife.c |  7 ++++++-
 3 files changed, 41 insertions(+), 4 deletions(-)

diff --git a/include/net/ife.h b/include/net/ife.h
index 44b9c00f7223..e117617e3c34 100644
--- a/include/net/ife.h
+++ b/include/net/ife.h
@@ -12,7 +12,8 @@
 void *ife_encode(struct sk_buff *skb, u16 metalen);
 void *ife_decode(struct sk_buff *skb, u16 *metalen);
 
-void *ife_tlv_meta_decode(void *skbdata, u16 *attrtype, u16 *dlen, u16 *totlen);
+void *ife_tlv_meta_decode(void *skbdata, const void *ifehdr_end, u16 *attrtype,
+			  u16 *dlen, u16 *totlen);
 int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen,
 			const void *dval);
 
diff --git a/net/ife/ife.c b/net/ife/ife.c
index 7d1ec76e7f43..7fbe70a0af4b 100644
--- a/net/ife/ife.c
+++ b/net/ife/ife.c
@@ -92,12 +92,43 @@ struct meta_tlvhdr {
 	__be16 len;
 };
 
+static bool __ife_tlv_meta_valid(const unsigned char *skbdata,
+				 const unsigned char *ifehdr_end)
+{
+	const struct meta_tlvhdr *tlv;
+	u16 tlvlen;
+
+	if (unlikely(skbdata + sizeof(*tlv) > ifehdr_end))
+		return false;
+
+	tlv = (const struct meta_tlvhdr *)skbdata;
+	tlvlen = ntohs(tlv->len);
+
+	/* tlv length field is inc header, check on minimum */
+	if (tlvlen < NLA_HDRLEN)
+		return false;
+
+	/* overflow by NLA_ALIGN check */
+	if (NLA_ALIGN(tlvlen) < tlvlen)
+		return false;
+
+	if (unlikely(skbdata + NLA_ALIGN(tlvlen) > ifehdr_end))
+		return false;
+
+	return true;
+}
+
 /* Caller takes care of presenting data in network order
  */
-void *ife_tlv_meta_decode(void *skbdata, u16 *attrtype, u16 *dlen, u16 *totlen)
+void *ife_tlv_meta_decode(void *skbdata, const void *ifehdr_end, u16 *attrtype,
+			  u16 *dlen, u16 *totlen)
 {
-	struct meta_tlvhdr *tlv = (struct meta_tlvhdr *) skbdata;
+	struct meta_tlvhdr *tlv;
+
+	if (!__ife_tlv_meta_valid(skbdata, ifehdr_end))
+		return NULL;
 
+	tlv = (struct meta_tlvhdr *)skbdata;
 	*dlen = ntohs(tlv->len) - NLA_HDRLEN;
 	*attrtype = ntohs(tlv->type);
 
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 4b4e4d490f42..85757af7f150 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -639,7 +639,12 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a,
 		u16 mtype;
 		u16 dlen;
 
-		curr_data = ife_tlv_meta_decode(tlv_data, &mtype, &dlen, NULL);
+		curr_data = ife_tlv_meta_decode(tlv_data, ifehdr_end, &mtype,
+						&dlen, NULL);
+		if (!curr_data) {
+			qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats));
+			return TC_ACT_SHOT;
+		}
 
 		if (find_decode_metaid(skb, ife, mtype, dlen, curr_data)) {
 			/* abuse overlimits to count when we receive metadata
-- 
2.14.3


From 4fcbc47231764affb7c4a4f2974c2189dac037e4 Mon Sep 17 00:00:00 2001
From: Alexander Aring <aring@mojatatu.com>
Date: Fri, 20 Apr 2018 15:15:05 -0400
Subject: [PATCH 28/33] net: sched: ife: check on metadata length

[ Upstream commit d57493d6d1be26c8ac8516a4463bfe24956978eb ]

This patch checks if sk buffer is available to dererence ife header. If
not then NULL will returned to signal an malformed ife packet. This
avoids to crashing the kernel from outside.

Signed-off-by: Alexander Aring <aring@mojatatu.com>
Reviewed-by: Yotam Gigi <yotam.gi@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ife/ife.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ife/ife.c b/net/ife/ife.c
index 7fbe70a0af4b..13bbf8cb6a39 100644
--- a/net/ife/ife.c
+++ b/net/ife/ife.c
@@ -69,6 +69,9 @@ void *ife_decode(struct sk_buff *skb, u16 *metalen)
 	int total_pull;
 	u16 ifehdrln;
 
+	if (!pskb_may_pull(skb, skb->dev->hard_header_len + IFE_METAHDRLEN))
+		return NULL;
+
 	ifehdr = (struct ifeheadr *) (skb->data + skb->dev->hard_header_len);
 	ifehdrln = ntohs(ifehdr->metalen);
 	total_pull = skb->dev->hard_header_len + ifehdrln;
-- 
2.14.3


From 61b133bcdff0e35598f855ff1d1b2647be94cc85 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Wed, 18 Apr 2018 11:51:56 -0700
Subject: [PATCH 29/33] llc: hold llc_sap before release_sock()

[ Upstream commit f7e43672683b097bb074a8fe7af9bc600a23f231 ]

syzbot reported we still access llc->sap in llc_backlog_rcv()
after it is freed in llc_sap_remove_socket():

Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1b9/0x294 lib/dump_stack.c:113
 print_address_description+0x6c/0x20b mm/kasan/report.c:256
 kasan_report_error mm/kasan/report.c:354 [inline]
 kasan_report.cold.7+0x242/0x2fe mm/kasan/report.c:412
 __asan_report_load1_noabort+0x14/0x20 mm/kasan/report.c:430
 llc_conn_ac_send_sabme_cmd_p_set_x+0x3a8/0x460 net/llc/llc_c_ac.c:785
 llc_exec_conn_trans_actions net/llc/llc_conn.c:475 [inline]
 llc_conn_service net/llc/llc_conn.c:400 [inline]
 llc_conn_state_process+0x4e1/0x13a0 net/llc/llc_conn.c:75
 llc_backlog_rcv+0x195/0x1e0 net/llc/llc_conn.c:891
 sk_backlog_rcv include/net/sock.h:909 [inline]
 __release_sock+0x12f/0x3a0 net/core/sock.c:2335
 release_sock+0xa4/0x2b0 net/core/sock.c:2850
 llc_ui_release+0xc8/0x220 net/llc/af_llc.c:204

llc->sap is refcount'ed and llc_sap_remove_socket() is paired
with llc_sap_add_socket(). This can be amended by holding its refcount
before llc_sap_remove_socket() and releasing it after release_sock().

Reported-by: <syzbot+6e181fc95081c2cf9051@syzkaller.appspotmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/llc/af_llc.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index c38d16f22d2a..c8950d88a695 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -189,6 +189,7 @@ static int llc_ui_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
 	struct llc_sock *llc;
+	struct llc_sap *sap;
 
 	if (unlikely(sk == NULL))
 		goto out;
@@ -199,9 +200,15 @@ static int llc_ui_release(struct socket *sock)
 		llc->laddr.lsap, llc->daddr.lsap);
 	if (!llc_send_disc(sk))
 		llc_ui_wait_for_disc(sk, sk->sk_rcvtimeo);
+	sap = llc->sap;
+	/* Hold this for release_sock(), so that llc_backlog_rcv() could still
+	 * use it.
+	 */
+	llc_sap_hold(sap);
 	if (!sock_flag(sk, SOCK_ZAPPED))
 		llc_sap_remove_socket(llc->sap, sk);
 	release_sock(sk);
+	llc_sap_put(sap);
 	if (llc->dev)
 		dev_put(llc->dev);
 	sock_put(sk);
-- 
2.14.3


From b9dcfb57501053a4eaa182fa4b78bbb01b439e36 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 19 Apr 2018 21:54:34 -0700
Subject: [PATCH 30/33] llc: fix NULL pointer deref for SOCK_ZAPPED

[ Upstream commit 3a04ce7130a7e5dad4e78d45d50313747f8c830f ]

For SOCK_ZAPPED socket, we don't need to care about llc->sap,
so we should just skip these refcount functions in this case.

Fixes: f7e43672683b ("llc: hold llc_sap before release_sock()")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/llc/af_llc.c | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index c8950d88a695..cf41d9b4a0b8 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -189,7 +189,6 @@ static int llc_ui_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
 	struct llc_sock *llc;
-	struct llc_sap *sap;
 
 	if (unlikely(sk == NULL))
 		goto out;
@@ -200,15 +199,19 @@ static int llc_ui_release(struct socket *sock)
 		llc->laddr.lsap, llc->daddr.lsap);
 	if (!llc_send_disc(sk))
 		llc_ui_wait_for_disc(sk, sk->sk_rcvtimeo);
-	sap = llc->sap;
-	/* Hold this for release_sock(), so that llc_backlog_rcv() could still
-	 * use it.
-	 */
-	llc_sap_hold(sap);
-	if (!sock_flag(sk, SOCK_ZAPPED))
+	if (!sock_flag(sk, SOCK_ZAPPED)) {
+		struct llc_sap *sap = llc->sap;
+
+		/* Hold this for release_sock(), so that llc_backlog_rcv()
+		 * could still use it.
+		 */
+		llc_sap_hold(sap);
 		llc_sap_remove_socket(llc->sap, sk);
-	release_sock(sk);
-	llc_sap_put(sap);
+		release_sock(sk);
+		llc_sap_put(sap);
+	} else {
+		release_sock(sk);
+	}
 	if (llc->dev)
 		dev_put(llc->dev);
 	sock_put(sk);
-- 
2.14.3


From f42442ae5628cd7fd6b52deff7a952355a81be9e Mon Sep 17 00:00:00 2001
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Thu, 19 Apr 2018 22:49:09 +0300
Subject: [PATCH 31/33] net: ethernet: ti: cpsw: fix tx vlan priority mapping

[ Upstream commit 5e391dc5a8d801a2410d0032ad4a428d1d61800c ]

The CPDMA_TX_PRIORITY_MAP in real is vlan pcp field priority mapping
register and basically replaces vlan pcp field for tagged packets.
So, set it to be 1:1 mapping. Otherwise, it will cause unexpected
change of egress vlan tagged packets, like prio 2 -> prio 5.

Fixes: e05107e6b747 ("net: ethernet: ti: cpsw: add multi queue support")
Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index a5bb7b19040e..992c43b1868f 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -124,7 +124,7 @@ do {								\
 
 #define RX_PRIORITY_MAPPING	0x76543210
 #define TX_PRIORITY_MAPPING	0x33221100
-#define CPDMA_TX_PRIORITY_MAP	0x01234567
+#define CPDMA_TX_PRIORITY_MAP	0x76543210
 
 #define CPSW_VLAN_AWARE		BIT(1)
 #define CPSW_ALE_VLAN_AWARE	1
-- 
2.14.3


From ddad4ef8904cabd725a3b05f8ce6f32053688f36 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Thu, 19 Apr 2018 08:30:48 +0300
Subject: [PATCH 32/33] virtio_net: split out ctrl buffer

[ Upstream commit 12e571693837d6164bda61e316b1944972ee0d97 ]

When sending control commands, virtio net sets up several buffers for
DMA. The buffers are all part of the net device which means it's
actually allocated by kvmalloc so it's in theory (on extreme memory
pressure) possible to get a vmalloc'ed buffer which on some platforms
means we can't DMA there.

Fix up by moving the DMA buffers into a separate structure.

Reported-by: Mikulas Patocka <mpatocka@redhat.com>
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 68 +++++++++++++++++++++++++++---------------------
 1 file changed, 39 insertions(+), 29 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index b0a038e6fda0..63b096c47f1e 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -116,6 +116,17 @@ struct receive_queue {
 	char name[40];
 };
 
+/* Control VQ buffers: protected by the rtnl lock */
+struct control_buf {
+	struct virtio_net_ctrl_hdr hdr;
+	virtio_net_ctrl_ack status;
+	struct virtio_net_ctrl_mq mq;
+	u8 promisc;
+	u8 allmulti;
+	u16 vid;
+	u64 offloads;
+};
+
 struct virtnet_info {
 	struct virtio_device *vdev;
 	struct virtqueue *cvq;
@@ -164,14 +175,7 @@ struct virtnet_info {
 	struct hlist_node node;
 	struct hlist_node node_dead;
 
-	/* Control VQ buffers: protected by the rtnl lock */
-	struct virtio_net_ctrl_hdr ctrl_hdr;
-	virtio_net_ctrl_ack ctrl_status;
-	struct virtio_net_ctrl_mq ctrl_mq;
-	u8 ctrl_promisc;
-	u8 ctrl_allmulti;
-	u16 ctrl_vid;
-	u64 ctrl_offloads;
+	struct control_buf *ctrl;
 
 	/* Ethtool settings */
 	u8 duplex;
@@ -1340,25 +1344,25 @@ static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd,
 	/* Caller should know better */
 	BUG_ON(!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ));
 
-	vi->ctrl_status = ~0;
-	vi->ctrl_hdr.class = class;
-	vi->ctrl_hdr.cmd = cmd;
+	vi->ctrl->status = ~0;
+	vi->ctrl->hdr.class = class;
+	vi->ctrl->hdr.cmd = cmd;
 	/* Add header */
-	sg_init_one(&hdr, &vi->ctrl_hdr, sizeof(vi->ctrl_hdr));
+	sg_init_one(&hdr, &vi->ctrl->hdr, sizeof(vi->ctrl->hdr));
 	sgs[out_num++] = &hdr;
 
 	if (out)
 		sgs[out_num++] = out;
 
 	/* Add return status. */
-	sg_init_one(&stat, &vi->ctrl_status, sizeof(vi->ctrl_status));
+	sg_init_one(&stat, &vi->ctrl->status, sizeof(vi->ctrl->status));
 	sgs[out_num] = &stat;
 
 	BUG_ON(out_num + 1 > ARRAY_SIZE(sgs));
 	virtqueue_add_sgs(vi->cvq, sgs, out_num, 1, vi, GFP_ATOMIC);
 
 	if (unlikely(!virtqueue_kick(vi->cvq)))
-		return vi->ctrl_status == VIRTIO_NET_OK;
+		return vi->ctrl->status == VIRTIO_NET_OK;
 
 	/* Spin for a response, the kick causes an ioport write, trapping
 	 * into the hypervisor, so the request should be handled immediately.
@@ -1367,7 +1371,7 @@ static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd,
 	       !virtqueue_is_broken(vi->cvq))
 		cpu_relax();
 
-	return vi->ctrl_status == VIRTIO_NET_OK;
+	return vi->ctrl->status == VIRTIO_NET_OK;
 }
 
 static int virtnet_set_mac_address(struct net_device *dev, void *p)
@@ -1478,8 +1482,8 @@ static int _virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs)
 	if (!vi->has_cvq || !virtio_has_feature(vi->vdev, VIRTIO_NET_F_MQ))
 		return 0;
 
-	vi->ctrl_mq.virtqueue_pairs = cpu_to_virtio16(vi->vdev, queue_pairs);
-	sg_init_one(&sg, &vi->ctrl_mq, sizeof(vi->ctrl_mq));
+	vi->ctrl->mq.virtqueue_pairs = cpu_to_virtio16(vi->vdev, queue_pairs);
+	sg_init_one(&sg, &vi->ctrl->mq, sizeof(vi->ctrl->mq));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MQ,
 				  VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET, &sg)) {
@@ -1537,22 +1541,22 @@ static void virtnet_set_rx_mode(struct net_device *dev)
 	if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_RX))
 		return;
 
-	vi->ctrl_promisc = ((dev->flags & IFF_PROMISC) != 0);
-	vi->ctrl_allmulti = ((dev->flags & IFF_ALLMULTI) != 0);
+	vi->ctrl->promisc = ((dev->flags & IFF_PROMISC) != 0);
+	vi->ctrl->allmulti = ((dev->flags & IFF_ALLMULTI) != 0);
 
-	sg_init_one(sg, &vi->ctrl_promisc, sizeof(vi->ctrl_promisc));
+	sg_init_one(sg, &vi->ctrl->promisc, sizeof(vi->ctrl->promisc));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX,
 				  VIRTIO_NET_CTRL_RX_PROMISC, sg))
 		dev_warn(&dev->dev, "Failed to %sable promisc mode.\n",
-			 vi->ctrl_promisc ? "en" : "dis");
+			 vi->ctrl->promisc ? "en" : "dis");
 
-	sg_init_one(sg, &vi->ctrl_allmulti, sizeof(vi->ctrl_allmulti));
+	sg_init_one(sg, &vi->ctrl->allmulti, sizeof(vi->ctrl->allmulti));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX,
 				  VIRTIO_NET_CTRL_RX_ALLMULTI, sg))
 		dev_warn(&dev->dev, "Failed to %sable allmulti mode.\n",
-			 vi->ctrl_allmulti ? "en" : "dis");
+			 vi->ctrl->allmulti ? "en" : "dis");
 
 	uc_count = netdev_uc_count(dev);
 	mc_count = netdev_mc_count(dev);
@@ -1598,8 +1602,8 @@ static int virtnet_vlan_rx_add_vid(struct net_device *dev,
 	struct virtnet_info *vi = netdev_priv(dev);
 	struct scatterlist sg;
 
-	vi->ctrl_vid = vid;
-	sg_init_one(&sg, &vi->ctrl_vid, sizeof(vi->ctrl_vid));
+	vi->ctrl->vid = vid;
+	sg_init_one(&sg, &vi->ctrl->vid, sizeof(vi->ctrl->vid));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN,
 				  VIRTIO_NET_CTRL_VLAN_ADD, &sg))
@@ -1613,8 +1617,8 @@ static int virtnet_vlan_rx_kill_vid(struct net_device *dev,
 	struct virtnet_info *vi = netdev_priv(dev);
 	struct scatterlist sg;
 
-	vi->ctrl_vid = vid;
-	sg_init_one(&sg, &vi->ctrl_vid, sizeof(vi->ctrl_vid));
+	vi->ctrl->vid = vid;
+	sg_init_one(&sg, &vi->ctrl->vid, sizeof(vi->ctrl->vid));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN,
 				  VIRTIO_NET_CTRL_VLAN_DEL, &sg))
@@ -1912,9 +1916,9 @@ static int virtnet_restore_up(struct virtio_device *vdev)
 static int virtnet_set_guest_offloads(struct virtnet_info *vi, u64 offloads)
 {
 	struct scatterlist sg;
-	vi->ctrl_offloads = cpu_to_virtio64(vi->vdev, offloads);
+	vi->ctrl->offloads = cpu_to_virtio64(vi->vdev, offloads);
 
-	sg_init_one(&sg, &vi->ctrl_offloads, sizeof(vi->ctrl_offloads));
+	sg_init_one(&sg, &vi->ctrl->offloads, sizeof(vi->ctrl->offloads));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_GUEST_OFFLOADS,
 				  VIRTIO_NET_CTRL_GUEST_OFFLOADS_SET, &sg)) {
@@ -2134,6 +2138,7 @@ static void virtnet_free_queues(struct virtnet_info *vi)
 
 	kfree(vi->rq);
 	kfree(vi->sq);
+	kfree(vi->ctrl);
 }
 
 static void _free_receive_bufs(struct virtnet_info *vi)
@@ -2326,6 +2331,9 @@ static int virtnet_alloc_queues(struct virtnet_info *vi)
 {
 	int i;
 
+	vi->ctrl = kzalloc(sizeof(*vi->ctrl), GFP_KERNEL);
+	if (!vi->ctrl)
+		goto err_ctrl;
 	vi->sq = kzalloc(sizeof(*vi->sq) * vi->max_queue_pairs, GFP_KERNEL);
 	if (!vi->sq)
 		goto err_sq;
@@ -2351,6 +2359,8 @@ static int virtnet_alloc_queues(struct virtnet_info *vi)
 err_rq:
 	kfree(vi->sq);
 err_sq:
+	kfree(vi->ctrl);
+err_ctrl:
 	return -ENOMEM;
 }
 
-- 
2.14.3


From 7feb36d308ae629b9470458590b4a1c0362d2315 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Thu, 19 Apr 2018 08:30:49 +0300
Subject: [PATCH 33/33] virtio_net: fix adding vids on big-endian

[ Upstream commit d7fad4c840f33a6bd333dd7fbb3006edbcf0017a ]

Programming vids (adding or removing them) still passes
guest-endian values in the DMA buffer. That's wrong
if guest is big-endian and when virtio 1 is enabled.

Note: this is on top of a previous patch:
	virtio_net: split out ctrl buffer

Fixes: 9465a7a6f ("virtio_net: enable v1.0 support")
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 63b096c47f1e..bb15b3012aa5 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -123,7 +123,7 @@ struct control_buf {
 	struct virtio_net_ctrl_mq mq;
 	u8 promisc;
 	u8 allmulti;
-	u16 vid;
+	__virtio16 vid;
 	u64 offloads;
 };
 
@@ -1602,7 +1602,7 @@ static int virtnet_vlan_rx_add_vid(struct net_device *dev,
 	struct virtnet_info *vi = netdev_priv(dev);
 	struct scatterlist sg;
 
-	vi->ctrl->vid = vid;
+	vi->ctrl->vid = cpu_to_virtio16(vi->vdev, vid);
 	sg_init_one(&sg, &vi->ctrl->vid, sizeof(vi->ctrl->vid));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN,
@@ -1617,7 +1617,7 @@ static int virtnet_vlan_rx_kill_vid(struct net_device *dev,
 	struct virtnet_info *vi = netdev_priv(dev);
 	struct scatterlist sg;
 
-	vi->ctrl->vid = vid;
+	vi->ctrl->vid = cpu_to_virtio16(vi->vdev, vid);
 	sg_init_one(&sg, &vi->ctrl->vid, sizeof(vi->ctrl->vid));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN,
-- 
2.14.3


[-- Attachment #3: net_416.mbox --]
[-- Type: Application/Octet-Stream, Size: 170289 bytes --]

From e86f8717907274fba14fbc0d31beec7e907d1f83 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 22 Apr 2018 19:11:50 +0800
Subject: [PATCH 01/52] bonding: do not set slave_dev npinfo before
 slave_enable_netpoll in bond_enslave

[ Upstream commit ddea788c63094f7c483783265563dd5b50052e28 ]

After Commit 8a8efa22f51b ("bonding: sync netpoll code with bridge"), it
would set slave_dev npinfo in slave_enable_netpoll when enslaving a dev
if bond->dev->npinfo was set.

However now slave_dev npinfo is set with bond->dev->npinfo before calling
slave_enable_netpoll. With slave_dev npinfo set, __netpoll_setup called
in slave_enable_netpoll will not call slave dev's .ndo_netpoll_setup().
It causes that the lower dev of this slave dev can't set its npinfo.

One way to reproduce it:

  # modprobe bonding
  # brctl addbr br0
  # brctl addif br0 eth1
  # ifconfig bond0 192.168.122.1/24 up
  # ifenslave bond0 eth2
  # systemctl restart netconsole
  # ifenslave bond0 br0
  # ifconfig eth2 down
  # systemctl restart netconsole

The netpoll won't really work.

This patch is to remove that slave_dev npinfo setting in bond_enslave().

Fixes: 8a8efa22f51b ("bonding: sync netpoll code with bridge")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index b7b113018853..718e4914e3a0 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1660,8 +1660,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 	} /* switch(bond_mode) */
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
-	slave_dev->npinfo = bond->dev->npinfo;
-	if (slave_dev->npinfo) {
+	if (bond->dev->npinfo) {
 		if (slave_enable_netpoll(new_slave)) {
 			netdev_info(bond_dev, "master_dev is using netpoll, but new slave device does not support netpoll\n");
 			res = -EBUSY;
-- 
2.14.3


From 32a4c23d2263624258b04a23b588ebdbfaa46d15 Mon Sep 17 00:00:00 2001
From: Olivier Gayot <olivier.gayot@sigexec.com>
Date: Wed, 18 Apr 2018 22:03:06 +0200
Subject: [PATCH 02/52] docs: ip-sysctl.txt: fix name of some ipv6 variables

[ Upstream commit ab913455dd59b81204b6a0d387a44697b0e0bd85 ]

The name of the following proc/sysctl entries were incorrectly
documented:

    /proc/sys/net/ipv6/conf/<interface>/max_dst_opts_number
    /proc/sys/net/ipv6/conf/<interface>/max_hbt_opts_number
    /proc/sys/net/ipv6/conf/<interface>/max_dst_opts_length
    /proc/sys/net/ipv6/conf/<interface>/max_hbt_length

Their name was set to the name of the symbol in the .data field of the
control table instead of their .proc name.

Signed-off-by: Olivier Gayot <olivier.gayot@sigexec.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index a553d4e4a0fb..f778901c4297 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1386,26 +1386,26 @@ mld_qrv - INTEGER
 	Default: 2 (as specified by RFC3810 9.1)
 	Minimum: 1 (as specified by RFC6636 4.5)
 
-max_dst_opts_cnt - INTEGER
+max_dst_opts_number - INTEGER
 	Maximum number of non-padding TLVs allowed in a Destination
 	options extension header. If this value is less than zero
 	then unknown options are disallowed and the number of known
 	TLVs allowed is the absolute value of this number.
 	Default: 8
 
-max_hbh_opts_cnt - INTEGER
+max_hbh_opts_number - INTEGER
 	Maximum number of non-padding TLVs allowed in a Hop-by-Hop
 	options extension header. If this value is less than zero
 	then unknown options are disallowed and the number of known
 	TLVs allowed is the absolute value of this number.
 	Default: 8
 
-max dst_opts_len - INTEGER
+max_dst_opts_length - INTEGER
 	Maximum length allowed for a Destination options extension
 	header.
 	Default: INT_MAX (unlimited)
 
-max hbh_opts_len - INTEGER
+max_hbh_length - INTEGER
 	Maximum length allowed for a Hop-by-Hop options extension
 	header.
 	Default: INT_MAX (unlimited)
-- 
2.14.3


From 2fbea7337be736e70f0a204774f667a29f41464a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 22 Apr 2018 18:29:23 -0700
Subject: [PATCH 03/52] ipv6: add RTA_TABLE and RTA_PREFSRC to rtm_ipv6_policy

[ Upstream commit aa8f8778493c85fff480cdf8b349b1e1dcb5f243 ]

KMSAN reported use of uninit-value that I tracked to lack
of proper size check on RTA_TABLE attribute.

I also believe RTA_PREFSRC lacks a similar check.

Fixes: 86872cb57925 ("[IPv6] route: FIB6 configuration using struct fib6_config")
Fixes: c3968a857a6b ("ipv6: RTA_PREFSRC support for ipv6 route source address selection")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index fc74352fac12..74a2e37412b2 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3862,6 +3862,7 @@ void rt6_mtu_change(struct net_device *dev, unsigned int mtu)
 
 static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
 	[RTA_GATEWAY]           = { .len = sizeof(struct in6_addr) },
+	[RTA_PREFSRC]		= { .len = sizeof(struct in6_addr) },
 	[RTA_OIF]               = { .type = NLA_U32 },
 	[RTA_IIF]		= { .type = NLA_U32 },
 	[RTA_PRIORITY]          = { .type = NLA_U32 },
@@ -3873,6 +3874,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
 	[RTA_EXPIRES]		= { .type = NLA_U32 },
 	[RTA_UID]		= { .type = NLA_U32 },
 	[RTA_MARK]		= { .type = NLA_U32 },
+	[RTA_TABLE]		= { .type = NLA_U32 },
 };
 
 static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
-- 
2.14.3


From 7ffaf45d34621cad340c65a87104a01277525e20 Mon Sep 17 00:00:00 2001
From: Ahmed Abdelsalam <amsalam20@gmail.com>
Date: Fri, 20 Apr 2018 15:58:05 +0200
Subject: [PATCH 04/52] ipv6: sr: fix NULL pointer dereference in
 seg6_do_srh_encap()- v4 pkts

[ Upstream commit a957fa190aa9d9168b33d460a5241a6d088c6265 ]

In case of seg6 in encap mode, seg6_do_srh_encap() calls set_tun_src()
in order to set the src addr of outer IPv6 header.

The net_device is required for set_tun_src(). However calling ip6_dst_idev()
on dst_entry in case of IPv4 traffic results on the following bug.

Using just dst->dev should fix this BUG.

[  196.242461] BUG: unable to handle kernel NULL pointer dereference at 0000000000000000
[  196.242975] PGD 800000010f076067 P4D 800000010f076067 PUD 10f060067 PMD 0
[  196.243329] Oops: 0000 [#1] SMP PTI
[  196.243468] Modules linked in: nfsd auth_rpcgss nfs_acl nfs lockd grace fscache sunrpc crct10dif_pclmul crc32_pclmul ghash_clmulni_intel pcbc aesni_intel aes_x86_64 crypto_simd cryptd input_leds glue_helper led_class pcspkr serio_raw mac_hid video autofs4 hid_generic usbhid hid e1000 i2c_piix4 ahci pata_acpi libahci
[  196.244362] CPU: 2 PID: 1089 Comm: ping Not tainted 4.16.0+ #1
[  196.244606] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[  196.244968] RIP: 0010:seg6_do_srh_encap+0x1ac/0x300
[  196.245236] RSP: 0018:ffffb2ce00b23a60 EFLAGS: 00010202
[  196.245464] RAX: 0000000000000000 RBX: ffff8c7f53eea300 RCX: 0000000000000000
[  196.245742] RDX: 0000f10000000000 RSI: ffff8c7f52085a6c RDI: ffff8c7f41166850
[  196.246018] RBP: ffffb2ce00b23aa8 R08: 00000000000261e0 R09: ffff8c7f41166800
[  196.246294] R10: ffffdce5040ac780 R11: ffff8c7f41166828 R12: ffff8c7f41166808
[  196.246570] R13: ffff8c7f52085a44 R14: ffffffffb73211c0 R15: ffff8c7e69e44200
[  196.246846] FS:  00007fc448789700(0000) GS:ffff8c7f59d00000(0000) knlGS:0000000000000000
[  196.247286] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  196.247526] CR2: 0000000000000000 CR3: 000000010f05a000 CR4: 00000000000406e0
[  196.247804] Call Trace:
[  196.247972]  seg6_do_srh+0x15b/0x1c0
[  196.248156]  seg6_output+0x3c/0x220
[  196.248341]  ? prandom_u32+0x14/0x20
[  196.248526]  ? ip_idents_reserve+0x6c/0x80
[  196.248723]  ? __ip_select_ident+0x90/0x100
[  196.248923]  ? ip_append_data.part.50+0x6c/0xd0
[  196.249133]  lwtunnel_output+0x44/0x70
[  196.249328]  ip_send_skb+0x15/0x40
[  196.249515]  raw_sendmsg+0x8c3/0xac0
[  196.249701]  ? _copy_from_user+0x2e/0x60
[  196.249897]  ? rw_copy_check_uvector+0x53/0x110
[  196.250106]  ? _copy_from_user+0x2e/0x60
[  196.250299]  ? copy_msghdr_from_user+0xce/0x140
[  196.250508]  sock_sendmsg+0x36/0x40
[  196.250690]  ___sys_sendmsg+0x292/0x2a0
[  196.250881]  ? _cond_resched+0x15/0x30
[  196.251074]  ? copy_termios+0x1e/0x70
[  196.251261]  ? _copy_to_user+0x22/0x30
[  196.251575]  ? tty_mode_ioctl+0x1c3/0x4e0
[  196.251782]  ? _cond_resched+0x15/0x30
[  196.251972]  ? mutex_lock+0xe/0x30
[  196.252152]  ? vvar_fault+0xd2/0x110
[  196.252337]  ? __do_fault+0x1f/0xc0
[  196.252521]  ? __handle_mm_fault+0xc1f/0x12d0
[  196.252727]  ? __sys_sendmsg+0x63/0xa0
[  196.252919]  __sys_sendmsg+0x63/0xa0
[  196.253107]  do_syscall_64+0x72/0x200
[  196.253305]  entry_SYSCALL_64_after_hwframe+0x3d/0xa2
[  196.253530] RIP: 0033:0x7fc4480b0690
[  196.253715] RSP: 002b:00007ffde9f252f8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
[  196.254053] RAX: ffffffffffffffda RBX: 0000000000000040 RCX: 00007fc4480b0690
[  196.254331] RDX: 0000000000000000 RSI: 000000000060a360 RDI: 0000000000000003
[  196.254608] RBP: 00007ffde9f253f0 R08: 00000000002d1e81 R09: 0000000000000002
[  196.254884] R10: 00007ffde9f250c0 R11: 0000000000000246 R12: 0000000000b22070
[  196.255205] R13: 20c49ba5e353f7cf R14: 431bde82d7b634db R15: 00007ffde9f278fe
[  196.255484] Code: a5 0f b6 45 c0 41 88 41 28 41 0f b6 41 2c 48 c1 e0 04 49 8b 54 01 38 49 8b 44 01 30 49 89 51 20 49 89 41 18 48 8b 83 b0 00 00 00 <48> 8b 30 49 8b 86 08 0b 00 00 48 8b 40 20 48 8b 50 08 48 0b 10
[  196.256190] RIP: seg6_do_srh_encap+0x1ac/0x300 RSP: ffffb2ce00b23a60
[  196.256445] CR2: 0000000000000000
[  196.256676] ---[ end trace 71af7d093603885c ]---

Fixes: 8936ef7604c11 ("ipv6: sr: fix NULL pointer dereference when setting encap source address")
Signed-off-by: Ahmed Abdelsalam <amsalam20@gmail.com>
Acked-by: David Lebrun <dlebrun@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/seg6_iptunnel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index f343e6f0fc95..5fe139484919 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -136,7 +136,7 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
 	isrh->nexthdr = proto;
 
 	hdr->daddr = isrh->segments[isrh->first_segment];
-	set_tun_src(net, ip6_dst_idev(dst)->dev, &hdr->daddr, &hdr->saddr);
+	set_tun_src(net, dst->dev, &hdr->daddr, &hdr->saddr);
 
 #ifdef CONFIG_IPV6_SEG6_HMAC
 	if (sr_has_hmac(isrh)) {
-- 
2.14.3


From 7c218e33e819c1c86f98913779d47b8ef1df96b0 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Tue, 17 Apr 2018 12:07:06 -0700
Subject: [PATCH 05/52] KEYS: DNS: limit the length of option strings

[ Upstream commit 9c438d7a3a52dcc2b9ed095cb87d3a5e83cf7e60 ]

Adding a dns_resolver key whose payload contains a very long option name
resulted in that string being printed in full.  This hit the WARN_ONCE()
in set_precision() during the printk(), because printk() only supports a
precision of up to 32767 bytes:

    precision 1000000 too large
    WARNING: CPU: 0 PID: 752 at lib/vsprintf.c:2189 vsnprintf+0x4bc/0x5b0

Fix it by limiting option strings (combined name + value) to a much more
reasonable 128 bytes.  The exact limit is arbitrary, but currently the
only recognized option is formatted as "dnserror=%lu" which fits well
within this limit.

Also ratelimit the printks.

Reproducer:

    perl -e 'print "#", "A" x 1000000, "\x00"' | keyctl padd dns_resolver desc @s

This bug was found using syzkaller.

Reported-by: Mark Rutland <mark.rutland@arm.com>
Fixes: 4a2d789267e0 ("DNS: If the DNS server returns an error, allow that to be cached [ver #2]")
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dns_resolver/dns_key.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c
index e1d4d898a007..ed372d550137 100644
--- a/net/dns_resolver/dns_key.c
+++ b/net/dns_resolver/dns_key.c
@@ -91,9 +91,9 @@ dns_resolver_preparse(struct key_preparsed_payload *prep)
 
 			next_opt = memchr(opt, '#', end - opt) ?: end;
 			opt_len = next_opt - opt;
-			if (!opt_len) {
-				printk(KERN_WARNING
-				       "Empty option to dns_resolver key\n");
+			if (opt_len <= 0 || opt_len > 128) {
+				pr_warn_ratelimited("Invalid option length (%d) for dns_resolver key\n",
+						    opt_len);
 				return -EINVAL;
 			}
 
@@ -127,10 +127,8 @@ dns_resolver_preparse(struct key_preparsed_payload *prep)
 			}
 
 		bad_option_value:
-			printk(KERN_WARNING
-			       "Option '%*.*s' to dns_resolver key:"
-			       " bad/missing value\n",
-			       opt_nlen, opt_nlen, opt);
+			pr_warn_ratelimited("Option '%*.*s' to dns_resolver key: bad/missing value\n",
+					    opt_nlen, opt_nlen, opt);
 			return -EINVAL;
 		} while (opt = next_opt + 1, opt < end);
 	}
-- 
2.14.3


From c9f914c82f047bbdec34c810e1d943dc24ef4783 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Mon, 23 Apr 2018 16:15:14 +0200
Subject: [PATCH 06/52] l2tp: check sockaddr length in pppol2tp_connect()

[ Upstream commit eb1c28c05894a4b1f6b56c5bf072205e64cfa280 ]

Check sockaddr_len before dereferencing sp->sa_protocol, to ensure that
it actually points to valid data.

Fixes: fd558d186df2 ("l2tp: Split pppol2tp patch into separate l2tp and ppp parts")
Reported-by: syzbot+a70ac890b23b1bf29f5c@syzkaller.appspotmail.com
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ppp.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 3d7887cc599b..fc3b8b8fe1c4 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -619,6 +619,13 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 	lock_sock(sk);
 
 	error = -EINVAL;
+
+	if (sockaddr_len != sizeof(struct sockaddr_pppol2tp) &&
+	    sockaddr_len != sizeof(struct sockaddr_pppol2tpv3) &&
+	    sockaddr_len != sizeof(struct sockaddr_pppol2tpin6) &&
+	    sockaddr_len != sizeof(struct sockaddr_pppol2tpv3in6))
+		goto end;
+
 	if (sp->sa_protocol != PX_PROTO_OL2TP)
 		goto end;
 
-- 
2.14.3


From 06165dc633470e3c05e5a12fb7a735cb57fadb1a Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 19 Apr 2018 12:25:38 -0700
Subject: [PATCH 07/52] llc: delete timers synchronously in llc_sk_free()

[ Upstream commit b905ef9ab90115d001c1658259af4b1c65088779 ]

The connection timers of an llc sock could be still flying
after we delete them in llc_sk_free(), and even possibly
after we free the sock. We could just wait synchronously
here in case of troubles.

Note, I leave other call paths as they are, since they may
not have to wait, at least we can change them to synchronously
when needed.

Also, move the code to net/llc/llc_conn.c, which is apparently
a better place.

Reported-by: <syzbot+f922284c18ea23a8e457@syzkaller.appspotmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/llc_conn.h |  1 +
 net/llc/llc_c_ac.c     |  9 +--------
 net/llc/llc_conn.c     | 22 +++++++++++++++++++++-
 3 files changed, 23 insertions(+), 9 deletions(-)

diff --git a/include/net/llc_conn.h b/include/net/llc_conn.h
index 5c40f118c0fa..df528a623548 100644
--- a/include/net/llc_conn.h
+++ b/include/net/llc_conn.h
@@ -97,6 +97,7 @@ static __inline__ char llc_backlog_type(struct sk_buff *skb)
 
 struct sock *llc_sk_alloc(struct net *net, int family, gfp_t priority,
 			  struct proto *prot, int kern);
+void llc_sk_stop_all_timers(struct sock *sk, bool sync);
 void llc_sk_free(struct sock *sk);
 
 void llc_sk_reset(struct sock *sk);
diff --git a/net/llc/llc_c_ac.c b/net/llc/llc_c_ac.c
index 163121192aca..4d78375f9872 100644
--- a/net/llc/llc_c_ac.c
+++ b/net/llc/llc_c_ac.c
@@ -1099,14 +1099,7 @@ int llc_conn_ac_inc_tx_win_size(struct sock *sk, struct sk_buff *skb)
 
 int llc_conn_ac_stop_all_timers(struct sock *sk, struct sk_buff *skb)
 {
-	struct llc_sock *llc = llc_sk(sk);
-
-	del_timer(&llc->pf_cycle_timer.timer);
-	del_timer(&llc->ack_timer.timer);
-	del_timer(&llc->rej_sent_timer.timer);
-	del_timer(&llc->busy_state_timer.timer);
-	llc->ack_must_be_send = 0;
-	llc->ack_pf = 0;
+	llc_sk_stop_all_timers(sk, false);
 	return 0;
 }
 
diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c
index 110e32bcb399..c0ac522b48a1 100644
--- a/net/llc/llc_conn.c
+++ b/net/llc/llc_conn.c
@@ -961,6 +961,26 @@ struct sock *llc_sk_alloc(struct net *net, int family, gfp_t priority, struct pr
 	return sk;
 }
 
+void llc_sk_stop_all_timers(struct sock *sk, bool sync)
+{
+	struct llc_sock *llc = llc_sk(sk);
+
+	if (sync) {
+		del_timer_sync(&llc->pf_cycle_timer.timer);
+		del_timer_sync(&llc->ack_timer.timer);
+		del_timer_sync(&llc->rej_sent_timer.timer);
+		del_timer_sync(&llc->busy_state_timer.timer);
+	} else {
+		del_timer(&llc->pf_cycle_timer.timer);
+		del_timer(&llc->ack_timer.timer);
+		del_timer(&llc->rej_sent_timer.timer);
+		del_timer(&llc->busy_state_timer.timer);
+	}
+
+	llc->ack_must_be_send = 0;
+	llc->ack_pf = 0;
+}
+
 /**
  *	llc_sk_free - Frees a LLC socket
  *	@sk - socket to free
@@ -973,7 +993,7 @@ void llc_sk_free(struct sock *sk)
 
 	llc->state = LLC_CONN_OUT_OF_SVC;
 	/* Stop all (possibly) running timers */
-	llc_conn_ac_stop_all_timers(sk, NULL);
+	llc_sk_stop_all_timers(sk, true);
 #ifdef DEBUG_LLC_CONN_ALLOC
 	printk(KERN_INFO "%s: unackq=%d, txq=%d\n", __func__,
 		skb_queue_len(&llc->pdu_unack_q),
-- 
2.14.3


From 2a8778dca6dbb619bf4b877e26f722aaa5f8e73f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 15 Apr 2018 17:52:04 -0700
Subject: [PATCH 08/52] net: af_packet: fix race in PACKET_{R|T}X_RING

[ Upstream commit 5171b37d959641bbc619781caf62e61f7b940871 ]

In order to remove the race caught by syzbot [1], we need
to lock the socket before using po->tp_version as this could
change under us otherwise.

This means lock_sock() and release_sock() must be done by
packet_set_ring() callers.

[1] :
BUG: KMSAN: uninit-value in packet_set_ring+0x1254/0x3870 net/packet/af_packet.c:4249
CPU: 0 PID: 20195 Comm: syzkaller707632 Not tainted 4.16.0+ #83
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x185/0x1d0 lib/dump_stack.c:53
 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067
 __msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:676
 packet_set_ring+0x1254/0x3870 net/packet/af_packet.c:4249
 packet_setsockopt+0x12c6/0x5a90 net/packet/af_packet.c:3662
 SYSC_setsockopt+0x4b8/0x570 net/socket.c:1849
 SyS_setsockopt+0x76/0xa0 net/socket.c:1828
 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x3d/0xa2
RIP: 0033:0x449099
RSP: 002b:00007f42b5307ce8 EFLAGS: 00000246 ORIG_RAX: 0000000000000036
RAX: ffffffffffffffda RBX: 000000000070003c RCX: 0000000000449099
RDX: 0000000000000005 RSI: 0000000000000107 RDI: 0000000000000003
RBP: 0000000000700038 R08: 000000000000001c R09: 0000000000000000
R10: 00000000200000c0 R11: 0000000000000246 R12: 0000000000000000
R13: 000000000080eecf R14: 00007f42b53089c0 R15: 0000000000000001

Local variable description: ----req_u@packet_setsockopt
Variable was created at:
 packet_setsockopt+0x13f/0x5a90 net/packet/af_packet.c:3612
 SYSC_setsockopt+0x4b8/0x570 net/socket.c:1849

Fixes: f6fb8f100b80 ("af-packet: TPACKET_V3 flexible buffer implementation.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index e0f3f4aeeb4f..19e5875fce89 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3008,6 +3008,7 @@ static int packet_release(struct socket *sock)
 
 	packet_flush_mclist(sk);
 
+	lock_sock(sk);
 	if (po->rx_ring.pg_vec) {
 		memset(&req_u, 0, sizeof(req_u));
 		packet_set_ring(sk, &req_u, 1, 0);
@@ -3017,6 +3018,7 @@ static int packet_release(struct socket *sock)
 		memset(&req_u, 0, sizeof(req_u));
 		packet_set_ring(sk, &req_u, 1, 1);
 	}
+	release_sock(sk);
 
 	f = fanout_release(sk);
 
@@ -3645,6 +3647,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 		union tpacket_req_u req_u;
 		int len;
 
+		lock_sock(sk);
 		switch (po->tp_version) {
 		case TPACKET_V1:
 		case TPACKET_V2:
@@ -3655,12 +3658,17 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 			len = sizeof(req_u.req3);
 			break;
 		}
-		if (optlen < len)
-			return -EINVAL;
-		if (copy_from_user(&req_u.req, optval, len))
-			return -EFAULT;
-		return packet_set_ring(sk, &req_u, 0,
-			optname == PACKET_TX_RING);
+		if (optlen < len) {
+			ret = -EINVAL;
+		} else {
+			if (copy_from_user(&req_u.req, optval, len))
+				ret = -EFAULT;
+			else
+				ret = packet_set_ring(sk, &req_u, 0,
+						    optname == PACKET_TX_RING);
+		}
+		release_sock(sk);
+		return ret;
 	}
 	case PACKET_COPY_THRESH:
 	{
@@ -4210,8 +4218,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 	/* Added to avoid minimal code churn */
 	struct tpacket_req *req = &req_u->req;
 
-	lock_sock(sk);
-
 	rb = tx_ring ? &po->tx_ring : &po->rx_ring;
 	rb_queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue;
 
@@ -4349,7 +4355,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 	if (pg_vec)
 		free_pg_vec(pg_vec, order, req->tp_block_nr);
 out:
-	release_sock(sk);
 	return err;
 }
 
-- 
2.14.3


From 744a265e08f085cbf31c7d8337de26b2c3dddfeb Mon Sep 17 00:00:00 2001
From: Wolfgang Bumiller <w.bumiller@proxmox.com>
Date: Thu, 12 Apr 2018 10:46:55 +0200
Subject: [PATCH 09/52] net: fix deadlock while clearing neighbor proxy table

[ Upstream commit 53b76cdf7e8fecec1d09e38aad2f8579882591a8 ]

When coming from ndisc_netdev_event() in net/ipv6/ndisc.c,
neigh_ifdown() is called with &nd_tbl, locking this while
clearing the proxy neighbor entries when eg. deleting an
interface. Calling the table's pndisc_destructor() with the
lock still held, however, can cause a deadlock: When a
multicast listener is available an IGMP packet of type
ICMPV6_MGM_REDUCTION may be sent out. When reaching
ip6_finish_output2(), if no neighbor entry for the target
address is found, __neigh_create() is called with &nd_tbl,
which it'll want to lock.

Move the elements into their own list, then unlock the table
and perform the destruction.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=199289
Fixes: 6fd6ce2056de ("ipv6: Do not depend on rt->n in ip6_finish_output2().")
Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 28 ++++++++++++++++++----------
 1 file changed, 18 insertions(+), 10 deletions(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 7b7a14abba28..e22d2aefbd78 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -55,7 +55,8 @@ static void neigh_timer_handler(struct timer_list *t);
 static void __neigh_notify(struct neighbour *n, int type, int flags,
 			   u32 pid);
 static void neigh_update_notify(struct neighbour *neigh, u32 nlmsg_pid);
-static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev);
+static int pneigh_ifdown_and_unlock(struct neigh_table *tbl,
+				    struct net_device *dev);
 
 #ifdef CONFIG_PROC_FS
 static const struct file_operations neigh_stat_seq_fops;
@@ -291,8 +292,7 @@ int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev)
 {
 	write_lock_bh(&tbl->lock);
 	neigh_flush_dev(tbl, dev);
-	pneigh_ifdown(tbl, dev);
-	write_unlock_bh(&tbl->lock);
+	pneigh_ifdown_and_unlock(tbl, dev);
 
 	del_timer_sync(&tbl->proxy_timer);
 	pneigh_queue_purge(&tbl->proxy_queue);
@@ -681,9 +681,10 @@ int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *pkey,
 	return -ENOENT;
 }
 
-static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev)
+static int pneigh_ifdown_and_unlock(struct neigh_table *tbl,
+				    struct net_device *dev)
 {
-	struct pneigh_entry *n, **np;
+	struct pneigh_entry *n, **np, *freelist = NULL;
 	u32 h;
 
 	for (h = 0; h <= PNEIGH_HASHMASK; h++) {
@@ -691,16 +692,23 @@ static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev)
 		while ((n = *np) != NULL) {
 			if (!dev || n->dev == dev) {
 				*np = n->next;
-				if (tbl->pdestructor)
-					tbl->pdestructor(n);
-				if (n->dev)
-					dev_put(n->dev);
-				kfree(n);
+				n->next = freelist;
+				freelist = n;
 				continue;
 			}
 			np = &n->next;
 		}
 	}
+	write_unlock_bh(&tbl->lock);
+	while ((n = freelist)) {
+		freelist = n->next;
+		n->next = NULL;
+		if (tbl->pdestructor)
+			tbl->pdestructor(n);
+		if (n->dev)
+			dev_put(n->dev);
+		kfree(n);
+	}
 	return -ENOENT;
 }
 
-- 
2.14.3


From 301cd2e890168886e6aaf5c4122c5a96e01f4259 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Wed, 18 Apr 2018 11:14:44 +0200
Subject: [PATCH 10/52] net: mvpp2: Fix DMA address mask size

[ Upstream commit da42bb271305d68df6cbf99eed90542f1f1ee1c9 ]

PPv2 TX/RX descriptors uses 40bits DMA addresses, but 41 bits masks were
used (GENMASK_ULL(40, 0)).

This commit fixes that by using the correct mask.

Fixes: e7c5359f2eed ("net: mvpp2: introduce PPv2.2 HW descriptors and adapt accessors")
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c
index 5a1668cdb461..7f1083ce23da 100644
--- a/drivers/net/ethernet/marvell/mvpp2.c
+++ b/drivers/net/ethernet/marvell/mvpp2.c
@@ -838,6 +838,8 @@ enum mvpp2_bm_type {
 
 #define MVPP2_MIB_COUNTERS_STATS_DELAY		(1 * HZ)
 
+#define MVPP2_DESC_DMA_MASK	DMA_BIT_MASK(40)
+
 /* Definitions */
 
 /* Shared Packet Processor resources */
@@ -1336,7 +1338,7 @@ static dma_addr_t mvpp2_txdesc_dma_addr_get(struct mvpp2_port *port,
 	if (port->priv->hw_version == MVPP21)
 		return tx_desc->pp21.buf_dma_addr;
 	else
-		return tx_desc->pp22.buf_dma_addr_ptp & GENMASK_ULL(40, 0);
+		return tx_desc->pp22.buf_dma_addr_ptp & MVPP2_DESC_DMA_MASK;
 }
 
 static void mvpp2_txdesc_dma_addr_set(struct mvpp2_port *port,
@@ -1354,7 +1356,7 @@ static void mvpp2_txdesc_dma_addr_set(struct mvpp2_port *port,
 	} else {
 		u64 val = (u64)addr;
 
-		tx_desc->pp22.buf_dma_addr_ptp &= ~GENMASK_ULL(40, 0);
+		tx_desc->pp22.buf_dma_addr_ptp &= ~MVPP2_DESC_DMA_MASK;
 		tx_desc->pp22.buf_dma_addr_ptp |= val;
 		tx_desc->pp22.packet_offset = offset;
 	}
@@ -1414,7 +1416,7 @@ static dma_addr_t mvpp2_rxdesc_dma_addr_get(struct mvpp2_port *port,
 	if (port->priv->hw_version == MVPP21)
 		return rx_desc->pp21.buf_dma_addr;
 	else
-		return rx_desc->pp22.buf_dma_addr_key_hash & GENMASK_ULL(40, 0);
+		return rx_desc->pp22.buf_dma_addr_key_hash & MVPP2_DESC_DMA_MASK;
 }
 
 static unsigned long mvpp2_rxdesc_cookie_get(struct mvpp2_port *port,
@@ -1423,7 +1425,7 @@ static unsigned long mvpp2_rxdesc_cookie_get(struct mvpp2_port *port,
 	if (port->priv->hw_version == MVPP21)
 		return rx_desc->pp21.buf_cookie;
 	else
-		return rx_desc->pp22.buf_cookie_misc & GENMASK_ULL(40, 0);
+		return rx_desc->pp22.buf_cookie_misc & MVPP2_DESC_DMA_MASK;
 }
 
 static size_t mvpp2_rxdesc_size_get(struct mvpp2_port *port,
@@ -8347,7 +8349,7 @@ static int mvpp2_probe(struct platform_device *pdev)
 	}
 
 	if (priv->hw_version == MVPP22) {
-		err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(40));
+		err = dma_set_mask(&pdev->dev, MVPP2_DESC_DMA_MASK);
 		if (err)
 			goto err_mg_clk;
 		/* Sadly, the BM pools all share the same register to
-- 
2.14.3


From d33374833e8f9556904a4e13ed26f1259ae93ceb Mon Sep 17 00:00:00 2001
From: Pawel Dembicki <paweldembicki@gmail.com>
Date: Wed, 18 Apr 2018 16:03:24 +0200
Subject: [PATCH 11/52] net: qmi_wwan: add Wistron Neweb D19Q1
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 4ec7eb3ff6eb5c9af3a84288a8d808a857fbc22b ]

This modem is embedded on dlink dwr-960 router.
The oem configuration states:

T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 2 Spd=480 MxCh= 0
D: Ver= 2.10 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1
P: Vendor=1435 ProdID=d191 Rev=ff.ff
S: Manufacturer=Android
S: Product=Android
S: SerialNumber=0123456789ABCDEF
C:* #Ifs= 6 Cfg#= 1 Atr=80 MxPwr=500mA
I:* If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none)
E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 1 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=(none)
E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=(none)
E: Ad=84(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
E: Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=(none)
E: Ad=86(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
E: Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
E: Ad=88(I) Atr=03(Int.) MxPS= 8 Ivl=32ms
E: Ad=87(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 5 Alt= 0 #EPs= 2 Cls=08(stor.) Sub=06 Prot=50 Driver=(none)
E: Ad=89(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=06(O) Atr=02(Bulk) MxPS= 512 Ivl=125us

Tested on openwrt distribution

Signed-off-by: Pawel Dembicki <paweldembicki@gmail.com>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index ca066b785e9f..c853e7410f5a 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1107,6 +1107,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1435, 0xd181, 3)},	/* Wistron NeWeb D18Q1 */
 	{QMI_FIXED_INTF(0x1435, 0xd181, 4)},	/* Wistron NeWeb D18Q1 */
 	{QMI_FIXED_INTF(0x1435, 0xd181, 5)},	/* Wistron NeWeb D18Q1 */
+	{QMI_FIXED_INTF(0x1435, 0xd191, 4)},	/* Wistron NeWeb D19Q1 */
 	{QMI_FIXED_INTF(0x16d8, 0x6003, 0)},	/* CMOTech 6003 */
 	{QMI_FIXED_INTF(0x16d8, 0x6007, 0)},	/* CMOTech CHE-628S */
 	{QMI_FIXED_INTF(0x16d8, 0x6008, 0)},	/* CMOTech CMU-301 */
-- 
2.14.3


From a1ae1071cc833782c2d11c03430f0ac1dba40b75 Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.vnet.ibm.com>
Date: Thu, 19 Apr 2018 15:56:40 +0200
Subject: [PATCH 12/52] net/smc: fix shutdown in state SMC_LISTEN

[ Upstream commit 1255fcb2a655f05e02f3a74675a6d6525f187afd ]

Calling shutdown with SHUT_RD and SHUT_RDWR for a listening SMC socket
crashes, because
   commit 127f49705823 ("net/smc: release clcsock from tcp_listen_worker")
releases the internal clcsock in smc_close_active() and sets smc->clcsock
to NULL.
For SHUT_RD the smc_close_active() call is removed.
For SHUT_RDWR the kernel_sock_shutdown() call is omitted, since the
clcsock is already released.

Fixes: 127f49705823 ("net/smc: release clcsock from tcp_listen_worker")
Signed-off-by: Ursula Braun <ubraun@linux.vnet.ibm.com>
Reported-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/af_smc.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 1e0d780855c3..afd5a935bbcb 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1254,14 +1254,12 @@ static int smc_shutdown(struct socket *sock, int how)
 		rc = smc_close_shutdown_write(smc);
 		break;
 	case SHUT_RD:
-		if (sk->sk_state == SMC_LISTEN)
-			rc = smc_close_active(smc);
-		else
-			rc = 0;
-			/* nothing more to do because peer is not involved */
+		rc = 0;
+		/* nothing more to do because peer is not involved */
 		break;
 	}
-	rc1 = kernel_sock_shutdown(smc->clcsock, how);
+	if (smc->clcsock)
+		rc1 = kernel_sock_shutdown(smc->clcsock, how);
 	/* map sock_shutdown_cmd constants to sk_shutdown value range */
 	sk->sk_shutdown |= how + 1;
 
-- 
2.14.3


From de508e9e83f758fefa0f33b8c138d9bf32f5c482 Mon Sep 17 00:00:00 2001
From: Jose Abreu <Jose.Abreu@synopsys.com>
Date: Wed, 18 Apr 2018 10:57:55 +0100
Subject: [PATCH 13/52] net: stmmac: Disable ACS Feature for GMAC >= 4

[ Upstream commit 565020aaeebfa7c8b3ec077bee38f4c15acc9905 ]

ACS Feature is currently enabled for GMAC >= 4 but the llc_snap status
is never checked in descriptor rx_status callback. This will cause
stmmac to always strip packets even that ACS feature is already
stripping them.

Lets be safe and disable the ACS feature for GMAC >= 4 and always strip
the packets for this GMAC version.

Fixes: 477286b53f55 ("stmmac: add GMAC4 core support")
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac4.h      | 2 +-
 drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c | 7 -------
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 7 ++++++-
 3 files changed, 7 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
index 7761a26ec9c5..e7565416639b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
@@ -343,7 +343,7 @@ enum power_event {
 #define MTL_RX_OVERFLOW_INT		BIT(16)
 
 /* Default operating mode of the MAC */
-#define GMAC_CORE_INIT (GMAC_CONFIG_JD | GMAC_CONFIG_PS | GMAC_CONFIG_ACS | \
+#define GMAC_CORE_INIT (GMAC_CONFIG_JD | GMAC_CONFIG_PS | \
 			GMAC_CONFIG_BE | GMAC_CONFIG_DCRS)
 
 /* To dump the core regs excluding  the Address Registers */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index 63795ecafc8d..26dfb75e927a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -30,13 +30,6 @@ static void dwmac4_core_init(struct mac_device_info *hw,
 
 	value |= GMAC_CORE_INIT;
 
-	/* Clear ACS bit because Ethernet switch tagging formats such as
-	 * Broadcom tags can look like invalid LLC/SNAP packets and cause the
-	 * hardware to truncate packets on reception.
-	 */
-	if (netdev_uses_dsa(dev))
-		value &= ~GMAC_CONFIG_ACS;
-
 	if (mtu > 1500)
 		value |= GMAC_CONFIG_2K;
 	if (mtu > 2000)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 7ad841434ec8..3ea343b45d93 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3435,8 +3435,13 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 
 			/* ACS is set; GMAC core strips PAD/FCS for IEEE 802.3
 			 * Type frames (LLC/LLC-SNAP)
+			 *
+			 * llc_snap is never checked in GMAC >= 4, so this ACS
+			 * feature is always disabled and packets need to be
+			 * stripped manually.
 			 */
-			if (unlikely(status != llc_snap))
+			if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00) ||
+			    unlikely(status != llc_snap))
 				frame_len -= ETH_FCS_LEN;
 
 			if (netif_msg_rx_status(priv)) {
-- 
2.14.3


From 498507ae4b92a783be680ef9df3d10a737a8253a Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Mon, 23 Apr 2018 17:37:03 -0400
Subject: [PATCH 14/52] packet: fix bitfield update race

[ Upstream commit a6361f0ca4b25460f2cdf3235ebe8115f622901e ]

Updates to the bitfields in struct packet_sock are not atomic.
Serialize these read-modify-write cycles.

Move po->running into a separate variable. Its writes are protected by
po->bind_lock (except for one startup case at packet_create). Also
replace a textual precondition warning with lockdep annotation.

All others are set only in packet_setsockopt. Serialize these
updates by holding the socket lock. Analogous to other field updates,
also hold the lock when testing whether a ring is active (pg_vec).

Fixes: 8dc419447415 ("[PACKET]: Add optional checksum computation for recvmsg")
Reported-by: DaeRyong Jeong <threeearcat@gmail.com>
Reported-by: Byoungyoung Lee <byoungyoung@purdue.edu>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 60 ++++++++++++++++++++++++++++++++++++--------------
 net/packet/internal.h  | 10 ++++-----
 2 files changed, 49 insertions(+), 21 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 19e5875fce89..3b43b1fcd618 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -329,11 +329,11 @@ static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb)
 	skb_set_queue_mapping(skb, queue_index);
 }
 
-/* register_prot_hook must be invoked with the po->bind_lock held,
+/* __register_prot_hook must be invoked through register_prot_hook
  * or from a context in which asynchronous accesses to the packet
  * socket is not possible (packet_create()).
  */
-static void register_prot_hook(struct sock *sk)
+static void __register_prot_hook(struct sock *sk)
 {
 	struct packet_sock *po = pkt_sk(sk);
 
@@ -348,8 +348,13 @@ static void register_prot_hook(struct sock *sk)
 	}
 }
 
-/* {,__}unregister_prot_hook() must be invoked with the po->bind_lock
- * held.   If the sync parameter is true, we will temporarily drop
+static void register_prot_hook(struct sock *sk)
+{
+	lockdep_assert_held_once(&pkt_sk(sk)->bind_lock);
+	__register_prot_hook(sk);
+}
+
+/* If the sync parameter is true, we will temporarily drop
  * the po->bind_lock and do a synchronize_net to make sure no
  * asynchronous packet processing paths still refer to the elements
  * of po->prot_hook.  If the sync parameter is false, it is the
@@ -359,6 +364,8 @@ static void __unregister_prot_hook(struct sock *sk, bool sync)
 {
 	struct packet_sock *po = pkt_sk(sk);
 
+	lockdep_assert_held_once(&po->bind_lock);
+
 	po->running = 0;
 
 	if (po->fanout)
@@ -3252,7 +3259,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol,
 
 	if (proto) {
 		po->prot_hook.type = proto;
-		register_prot_hook(sk);
+		__register_prot_hook(sk);
 	}
 
 	mutex_lock(&net->packet.sklist_lock);
@@ -3734,12 +3741,18 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 
 		if (optlen != sizeof(val))
 			return -EINVAL;
-		if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
-			return -EBUSY;
 		if (copy_from_user(&val, optval, sizeof(val)))
 			return -EFAULT;
-		po->tp_loss = !!val;
-		return 0;
+
+		lock_sock(sk);
+		if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+			ret = -EBUSY;
+		} else {
+			po->tp_loss = !!val;
+			ret = 0;
+		}
+		release_sock(sk);
+		return ret;
 	}
 	case PACKET_AUXDATA:
 	{
@@ -3750,7 +3763,9 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 		if (copy_from_user(&val, optval, sizeof(val)))
 			return -EFAULT;
 
+		lock_sock(sk);
 		po->auxdata = !!val;
+		release_sock(sk);
 		return 0;
 	}
 	case PACKET_ORIGDEV:
@@ -3762,7 +3777,9 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 		if (copy_from_user(&val, optval, sizeof(val)))
 			return -EFAULT;
 
+		lock_sock(sk);
 		po->origdev = !!val;
+		release_sock(sk);
 		return 0;
 	}
 	case PACKET_VNET_HDR:
@@ -3771,15 +3788,20 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 
 		if (sock->type != SOCK_RAW)
 			return -EINVAL;
-		if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
-			return -EBUSY;
 		if (optlen < sizeof(val))
 			return -EINVAL;
 		if (copy_from_user(&val, optval, sizeof(val)))
 			return -EFAULT;
 
-		po->has_vnet_hdr = !!val;
-		return 0;
+		lock_sock(sk);
+		if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+			ret = -EBUSY;
+		} else {
+			po->has_vnet_hdr = !!val;
+			ret = 0;
+		}
+		release_sock(sk);
+		return ret;
 	}
 	case PACKET_TIMESTAMP:
 	{
@@ -3817,11 +3839,17 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 
 		if (optlen != sizeof(val))
 			return -EINVAL;
-		if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
-			return -EBUSY;
 		if (copy_from_user(&val, optval, sizeof(val)))
 			return -EFAULT;
-		po->tp_tx_has_off = !!val;
+
+		lock_sock(sk);
+		if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+			ret = -EBUSY;
+		} else {
+			po->tp_tx_has_off = !!val;
+			ret = 0;
+		}
+		release_sock(sk);
 		return 0;
 	}
 	case PACKET_QDISC_BYPASS:
diff --git a/net/packet/internal.h b/net/packet/internal.h
index a1d2b2319ae9..3bb7c5fb3bff 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -112,10 +112,12 @@ struct packet_sock {
 	int			copy_thresh;
 	spinlock_t		bind_lock;
 	struct mutex		pg_vec_lock;
-	unsigned int		running:1,	/* prot_hook is attached*/
-				auxdata:1,
+	unsigned int		running;	/* bind_lock must be held */
+	unsigned int		auxdata:1,	/* writer must hold sock lock */
 				origdev:1,
-				has_vnet_hdr:1;
+				has_vnet_hdr:1,
+				tp_loss:1,
+				tp_tx_has_off:1;
 	int			pressure;
 	int			ifindex;	/* bound device		*/
 	__be16			num;
@@ -125,8 +127,6 @@ struct packet_sock {
 	enum tpacket_versions	tp_version;
 	unsigned int		tp_hdrlen;
 	unsigned int		tp_reserve;
-	unsigned int		tp_loss:1;
-	unsigned int		tp_tx_has_off:1;
 	unsigned int		tp_tstamp;
 	struct net_device __rcu	*cached_dev;
 	int			(*xmit)(struct sk_buff *skb);
-- 
2.14.3


From 65719bc47ebd0c536e648c3c27a3b015bc033d92 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Mon, 23 Apr 2018 16:38:27 +0200
Subject: [PATCH 15/52] pppoe: check sockaddr length in pppoe_connect()

[ Upstream commit a49e2f5d5fb141884452ddb428f551b123d436b5 ]

We must validate sockaddr_len, otherwise userspace can pass fewer data
than we expect and we end up accessing invalid data.

Fixes: 224cf5ad14c0 ("ppp: Move the PPP drivers")
Reported-by: syzbot+4f03bdf92fdf9ef5ddab@syzkaller.appspotmail.com
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pppoe.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 5aa59f41bf8c..71e2aef6b7a1 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -620,6 +620,10 @@ static int pppoe_connect(struct socket *sock, struct sockaddr *uservaddr,
 	lock_sock(sk);
 
 	error = -EINVAL;
+
+	if (sockaddr_len != sizeof(struct sockaddr_pppox))
+		goto end;
+
 	if (sp->sa_protocol != PX_PROTO_OE)
 		goto end;
 
-- 
2.14.3


From aca388e7d1b01598375ec96e62e1e4f35f55524c Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Mon, 16 Apr 2018 13:17:50 +0300
Subject: [PATCH 16/52] Revert "macsec: missing dev_put() on error in
 macsec_newlink()"

[ Upstream commit bd28899dd34f9283c567f7eeb31bb546f10820b5 ]

This patch is just wrong, sorry.  I was trying to fix a static checker
warning and misread the code.  The reference taken in macsec_newlink()
is released in macsec_free_netdev() when the netdevice is destroyed.

This reverts commit 5dcd8400884cc4a043a6d4617e042489e5d566a9.

Reported-by: Laura Abbott <labbott@redhat.com>
Fixes: 5dcd8400884c ("macsec: missing dev_put() on error in macsec_newlink()")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macsec.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 9cbb0c8a896a..7de88b33d5b9 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -3277,7 +3277,7 @@ static int macsec_newlink(struct net *net, struct net_device *dev,
 
 	err = netdev_upper_dev_link(real_dev, dev, extack);
 	if (err < 0)
-		goto put_dev;
+		goto unregister;
 
 	/* need to be already registered so that ->init has run and
 	 * the MAC addr is set
@@ -3316,8 +3316,7 @@ static int macsec_newlink(struct net *net, struct net_device *dev,
 	macsec_del_dev(macsec);
 unlink:
 	netdev_upper_dev_unlink(real_dev, dev);
-put_dev:
-	dev_put(real_dev);
+unregister:
 	unregister_netdevice(dev);
 	return err;
 }
-- 
2.14.3


From b11149153fb18bc177045720b25104b17655f787 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 12 Apr 2018 14:24:31 +0800
Subject: [PATCH 17/52] sctp: do not check port in sctp_inet6_cmp_addr

[ Upstream commit 1071ec9d453a38023579714b64a951a2fb982071 ]

pf->cmp_addr() is called before binding a v6 address to the sock. It
should not check ports, like in sctp_inet_cmp_addr.

But sctp_inet6_cmp_addr checks the addr by invoking af(6)->cmp_addr,
sctp_v6_cmp_addr where it also compares the ports.

This would cause that setsockopt(SCTP_SOCKOPT_BINDX_ADD) could bind
multiple duplicated IPv6 addresses after Commit 40b4f0fd74e4 ("sctp:
lack the check for ports in sctp_v6_cmp_addr").

This patch is to remove af->cmp_addr called in sctp_inet6_cmp_addr,
but do the proper check for both v6 addrs and v4mapped addrs.

v1->v2:
  - define __sctp_v6_cmp_addr to do the common address comparison
    used for both pf and af v6 cmp_addr.

Fixes: 40b4f0fd74e4 ("sctp: lack the check for ports in sctp_v6_cmp_addr")
Reported-by: Jianwen Ji <jiji@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ipv6.c | 60 ++++++++++++++++++++++++++++-----------------------------
 1 file changed, 30 insertions(+), 30 deletions(-)

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index f6d3d0c1e133..07b64719d1bc 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -521,46 +521,49 @@ static void sctp_v6_to_addr(union sctp_addr *addr, struct in6_addr *saddr,
 	addr->v6.sin6_scope_id = 0;
 }
 
-/* Compare addresses exactly.
- * v4-mapped-v6 is also in consideration.
- */
-static int sctp_v6_cmp_addr(const union sctp_addr *addr1,
-			    const union sctp_addr *addr2)
+static int __sctp_v6_cmp_addr(const union sctp_addr *addr1,
+			      const union sctp_addr *addr2)
 {
 	if (addr1->sa.sa_family != addr2->sa.sa_family) {
 		if (addr1->sa.sa_family == AF_INET &&
 		    addr2->sa.sa_family == AF_INET6 &&
-		    ipv6_addr_v4mapped(&addr2->v6.sin6_addr)) {
-			if (addr2->v6.sin6_port == addr1->v4.sin_port &&
-			    addr2->v6.sin6_addr.s6_addr32[3] ==
-			    addr1->v4.sin_addr.s_addr)
-				return 1;
-		}
+		    ipv6_addr_v4mapped(&addr2->v6.sin6_addr) &&
+		    addr2->v6.sin6_addr.s6_addr32[3] ==
+		    addr1->v4.sin_addr.s_addr)
+			return 1;
+
 		if (addr2->sa.sa_family == AF_INET &&
 		    addr1->sa.sa_family == AF_INET6 &&
-		    ipv6_addr_v4mapped(&addr1->v6.sin6_addr)) {
-			if (addr1->v6.sin6_port == addr2->v4.sin_port &&
-			    addr1->v6.sin6_addr.s6_addr32[3] ==
-			    addr2->v4.sin_addr.s_addr)
-				return 1;
-		}
+		    ipv6_addr_v4mapped(&addr1->v6.sin6_addr) &&
+		    addr1->v6.sin6_addr.s6_addr32[3] ==
+		    addr2->v4.sin_addr.s_addr)
+			return 1;
+
 		return 0;
 	}
-	if (addr1->v6.sin6_port != addr2->v6.sin6_port)
-		return 0;
+
 	if (!ipv6_addr_equal(&addr1->v6.sin6_addr, &addr2->v6.sin6_addr))
 		return 0;
+
 	/* If this is a linklocal address, compare the scope_id. */
-	if (ipv6_addr_type(&addr1->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) {
-		if (addr1->v6.sin6_scope_id && addr2->v6.sin6_scope_id &&
-		    (addr1->v6.sin6_scope_id != addr2->v6.sin6_scope_id)) {
-			return 0;
-		}
-	}
+	if ((ipv6_addr_type(&addr1->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) &&
+	    addr1->v6.sin6_scope_id && addr2->v6.sin6_scope_id &&
+	    addr1->v6.sin6_scope_id != addr2->v6.sin6_scope_id)
+		return 0;
 
 	return 1;
 }
 
+/* Compare addresses exactly.
+ * v4-mapped-v6 is also in consideration.
+ */
+static int sctp_v6_cmp_addr(const union sctp_addr *addr1,
+			    const union sctp_addr *addr2)
+{
+	return __sctp_v6_cmp_addr(addr1, addr2) &&
+	       addr1->v6.sin6_port == addr2->v6.sin6_port;
+}
+
 /* Initialize addr struct to INADDR_ANY. */
 static void sctp_v6_inaddr_any(union sctp_addr *addr, __be16 port)
 {
@@ -846,8 +849,8 @@ static int sctp_inet6_cmp_addr(const union sctp_addr *addr1,
 			       const union sctp_addr *addr2,
 			       struct sctp_sock *opt)
 {
-	struct sctp_af *af1, *af2;
 	struct sock *sk = sctp_opt2sk(opt);
+	struct sctp_af *af1, *af2;
 
 	af1 = sctp_get_af_specific(addr1->sa.sa_family);
 	af2 = sctp_get_af_specific(addr2->sa.sa_family);
@@ -863,10 +866,7 @@ static int sctp_inet6_cmp_addr(const union sctp_addr *addr1,
 	if (sctp_is_any(sk, addr1) || sctp_is_any(sk, addr2))
 		return 1;
 
-	if (addr1->sa.sa_family != addr2->sa.sa_family)
-		return 0;
-
-	return af1->cmp_addr(addr1, addr2);
+	return __sctp_v6_cmp_addr(addr1, addr2);
 }
 
 /* Verify that the provided sockaddr looks bindable.   Common verification,
-- 
2.14.3


From ab82cd30093b5c0b818a9288d07e49794b3c6fc8 Mon Sep 17 00:00:00 2001
From: Doron Roberts-Kedes <doronrk@fb.com>
Date: Fri, 20 Apr 2018 12:11:11 -0700
Subject: [PATCH 18/52] strparser: Do not call mod_delayed_work with a timeout
 of LONG_MAX

[ Upstream commit 7c5aba211dd61f41d737a2c51729eb9fdcd3edf4 ]

struct sock's sk_rcvtimeo is initialized to
LONG_MAX/MAX_SCHEDULE_TIMEOUT in sock_init_data. Calling
mod_delayed_work with a timeout of LONG_MAX causes spurious execution of
the work function. timer->expires is set equal to jiffies + LONG_MAX.
When timer_base->clk falls behind the current value of jiffies,
the delta between timer_base->clk and jiffies + LONG_MAX causes the
expiration to be in the past. Returning early from strp_start_timer if
timeo == LONG_MAX solves this problem.

Found while testing net/tls_sw recv path.

Fixes: 43a0c6751a322847 ("strparser: Stream parser for messages")
Reviewed-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Doron Roberts-Kedes <doronrk@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/strparser/strparser.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index b9283ce5cd85..8d177506901c 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -67,7 +67,7 @@ static void strp_abort_strp(struct strparser *strp, int err)
 
 static void strp_start_timer(struct strparser *strp, long timeo)
 {
-	if (timeo)
+	if (timeo && timeo != LONG_MAX)
 		mod_delayed_work(strp_wq, &strp->msg_timer_work, timeo);
 }
 
-- 
2.14.3


From 1351b051b050a83d344bbf7212e41e2fbbd8c439 Mon Sep 17 00:00:00 2001
From: Doron Roberts-Kedes <doronrk@fb.com>
Date: Wed, 11 Apr 2018 15:05:16 -0700
Subject: [PATCH 19/52] strparser: Fix incorrect strp->need_bytes value.

[ Upstream commit 9d0c75bf6e03d9bf80c55b0f677dc9b982958fd5 ]

strp_data_ready resets strp->need_bytes to 0 if strp_peek_len indicates
that the remainder of the message has been received. However,
do_strp_work does not reset strp->need_bytes to 0. If do_strp_work
completes a partial message, the value of strp->need_bytes will continue
to reflect the needed bytes of the previous message, causing
future invocations of strp_data_ready to return early if
strp->need_bytes is less than strp_peek_len. Resetting strp->need_bytes
to 0 in __strp_recv on handing a full message to the upper layer solves
this problem.

__strp_recv also calculates strp->need_bytes using stm->accum_len before
stm->accum_len has been incremented by cand_len. This can cause
strp->need_bytes to be equal to the full length of the message instead
of the full length minus the accumulated length. This, in turn, causes
strp_data_ready to return early, even when there is sufficient data to
complete the partial message. Incrementing stm->accum_len before using
it to calculate strp->need_bytes solves this problem.

Found while testing net/tls_sw recv path.

Fixes: 43a0c6751a322847 ("strparser: Stream parser for messages")
Signed-off-by: Doron Roberts-Kedes <doronrk@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/strparser/strparser.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index 8d177506901c..092bebc70048 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -296,9 +296,9 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb,
 					strp_start_timer(strp, timeo);
 				}
 
+				stm->accum_len += cand_len;
 				strp->need_bytes = stm->strp.full_len -
 						       stm->accum_len;
-				stm->accum_len += cand_len;
 				stm->early_eaten = cand_len;
 				STRP_STATS_ADD(strp->stats.bytes, cand_len);
 				desc->count = 0; /* Stop reading socket */
@@ -321,6 +321,7 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb,
 		/* Hurray, we have a new message! */
 		cancel_delayed_work(&strp->msg_timer_work);
 		strp->skb_head = NULL;
+		strp->need_bytes = 0;
 		STRP_STATS_INCR(strp->stats.msgs);
 
 		/* Give skb to upper layer */
@@ -410,9 +411,7 @@ void strp_data_ready(struct strparser *strp)
 		return;
 
 	if (strp->need_bytes) {
-		if (strp_peek_len(strp) >= strp->need_bytes)
-			strp->need_bytes = 0;
-		else
+		if (strp_peek_len(strp) < strp->need_bytes)
 			return;
 	}
 
-- 
2.14.3


From 5b3d401fff61174f7bf2031ef9a9a34d2426aa86 Mon Sep 17 00:00:00 2001
From: Soheil Hassas Yeganeh <soheil@google.com>
Date: Sat, 14 Apr 2018 20:44:46 -0400
Subject: [PATCH 20/52] tcp: clear tp->packets_out when purging write queue

[ Upstream commit bffd168c3fc5cc7d2bad4c668fa90e7a9010db4b ]

Clear tp->packets_out when purging the write queue, otherwise
tcp_rearm_rto() mistakenly assumes TCP write queue is not empty.
This results in NULL pointer dereference.

Also, remove the redundant `tp->packets_out = 0` from
tcp_disconnect(), since tcp_disconnect() calls
tcp_write_queue_purge().

Fixes: a27fd7a8ed38 (tcp: purge write queue upon RST)
Reported-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Reported-by: Sami Farin <hvtaifwkbgefbaei@gmail.com>
Tested-by: Sami Farin <hvtaifwkbgefbaei@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 8b8059b7af4d..bb48cd142b92 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2385,6 +2385,7 @@ void tcp_write_queue_purge(struct sock *sk)
 	INIT_LIST_HEAD(&tcp_sk(sk)->tsorted_sent_queue);
 	sk_mem_reclaim(sk);
 	tcp_clear_all_retrans_hints(tcp_sk(sk));
+	tcp_sk(sk)->packets_out = 0;
 }
 
 int tcp_disconnect(struct sock *sk, int flags)
@@ -2434,7 +2435,6 @@ int tcp_disconnect(struct sock *sk, int flags)
 	icsk->icsk_backoff = 0;
 	tp->snd_cwnd = 2;
 	icsk->icsk_probes_out = 0;
-	tp->packets_out = 0;
 	tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
 	tp->snd_cwnd_cnt = 0;
 	tp->window_clamp = 0;
-- 
2.14.3


From ae7fbd1857dee4b878e3b3087d0a8481d751b9d3 Mon Sep 17 00:00:00 2001
From: Jann Horn <jannh@google.com>
Date: Fri, 20 Apr 2018 15:57:30 +0200
Subject: [PATCH 21/52] tcp: don't read out-of-bounds opsize

[ Upstream commit 7e5a206ab686f098367b61aca989f5cdfa8114a3 ]

The old code reads the "opsize" variable from out-of-bounds memory (first
byte behind the segment) if a broken TCP segment ends directly after an
opcode that is neither EOL nor NOP.

The result of the read isn't used for anything, so the worst thing that
could theoretically happen is a pagefault; and since the physmap is usually
mostly contiguous, even that seems pretty unlikely.

The following C reproducer triggers the uninitialized read - however, you
can't actually see anything happen unless you put something like a
pr_warn() in tcp_parse_md5sig_option() to print the opsize.

====================================
#define _GNU_SOURCE
#include <arpa/inet.h>
#include <stdlib.h>
#include <errno.h>
#include <stdarg.h>
#include <net/if.h>
#include <linux/if.h>
#include <linux/ip.h>
#include <linux/tcp.h>
#include <linux/in.h>
#include <linux/if_tun.h>
#include <err.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <string.h>
#include <stdio.h>
#include <unistd.h>
#include <sys/ioctl.h>
#include <assert.h>

void systemf(const char *command, ...) {
  char *full_command;
  va_list ap;
  va_start(ap, command);
  if (vasprintf(&full_command, command, ap) == -1)
    err(1, "vasprintf");
  va_end(ap);
  printf("systemf: <<<%s>>>\n", full_command);
  system(full_command);
}

char *devname;

int tun_alloc(char *name) {
  int fd = open("/dev/net/tun", O_RDWR);
  if (fd == -1)
    err(1, "open tun dev");
  static struct ifreq req = { .ifr_flags = IFF_TUN|IFF_NO_PI };
  strcpy(req.ifr_name, name);
  if (ioctl(fd, TUNSETIFF, &req))
    err(1, "TUNSETIFF");
  devname = req.ifr_name;
  printf("device name: %s\n", devname);
  return fd;
}

#define IPADDR(a,b,c,d) (((a)<<0)+((b)<<8)+((c)<<16)+((d)<<24))

void sum_accumulate(unsigned int *sum, void *data, int len) {
  assert((len&2)==0);
  for (int i=0; i<len/2; i++) {
    *sum += ntohs(((unsigned short *)data)[i]);
  }
}

unsigned short sum_final(unsigned int sum) {
  sum = (sum >> 16) + (sum & 0xffff);
  sum = (sum >> 16) + (sum & 0xffff);
  return htons(~sum);
}

void fix_ip_sum(struct iphdr *ip) {
  unsigned int sum = 0;
  sum_accumulate(&sum, ip, sizeof(*ip));
  ip->check = sum_final(sum);
}

void fix_tcp_sum(struct iphdr *ip, struct tcphdr *tcp) {
  unsigned int sum = 0;
  struct {
    unsigned int saddr;
    unsigned int daddr;
    unsigned char pad;
    unsigned char proto_num;
    unsigned short tcp_len;
  } fakehdr = {
    .saddr = ip->saddr,
    .daddr = ip->daddr,
    .proto_num = ip->protocol,
    .tcp_len = htons(ntohs(ip->tot_len) - ip->ihl*4)
  };
  sum_accumulate(&sum, &fakehdr, sizeof(fakehdr));
  sum_accumulate(&sum, tcp, tcp->doff*4);
  tcp->check = sum_final(sum);
}

int main(void) {
  int tun_fd = tun_alloc("inject_dev%d");
  systemf("ip link set %s up", devname);
  systemf("ip addr add 192.168.42.1/24 dev %s", devname);

  struct {
    struct iphdr ip;
    struct tcphdr tcp;
    unsigned char tcp_opts[20];
  } __attribute__((packed)) syn_packet = {
    .ip = {
      .ihl = sizeof(struct iphdr)/4,
      .version = 4,
      .tot_len = htons(sizeof(syn_packet)),
      .ttl = 30,
      .protocol = IPPROTO_TCP,
      /* FIXUP check */
      .saddr = IPADDR(192,168,42,2),
      .daddr = IPADDR(192,168,42,1)
    },
    .tcp = {
      .source = htons(1),
      .dest = htons(1337),
      .seq = 0x12345678,
      .doff = (sizeof(syn_packet.tcp)+sizeof(syn_packet.tcp_opts))/4,
      .syn = 1,
      .window = htons(64),
      .check = 0 /*FIXUP*/
    },
    .tcp_opts = {
      /* INVALID: trailing MD5SIG opcode after NOPs */
      1, 1, 1, 1, 1,
      1, 1, 1, 1, 1,
      1, 1, 1, 1, 1,
      1, 1, 1, 1, 19
    }
  };
  fix_ip_sum(&syn_packet.ip);
  fix_tcp_sum(&syn_packet.ip, &syn_packet.tcp);
  while (1) {
    int write_res = write(tun_fd, &syn_packet, sizeof(syn_packet));
    if (write_res != sizeof(syn_packet))
      err(1, "packet write failed");
  }
}
====================================

Fixes: cfb6eeb4c860 ("[TCP]: MD5 Signature Option (RFC2385) support.")
Signed-off-by: Jann Horn <jannh@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index ff6cd98ce8d5..31ca27fdde66 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3871,11 +3871,8 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th)
 	int length = (th->doff << 2) - sizeof(*th);
 	const u8 *ptr = (const u8 *)(th + 1);
 
-	/* If the TCP option is too short, we can short cut */
-	if (length < TCPOLEN_MD5SIG)
-		return NULL;
-
-	while (length > 0) {
+	/* If not enough data remaining, we can short cut */
+	while (length >= TCPOLEN_MD5SIG) {
 		int opcode = *ptr++;
 		int opsize;
 
-- 
2.14.3


From a1c88dab7ea2feddfe1465666d766bf7eb913ce6 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 11 Apr 2018 14:36:28 -0700
Subject: [PATCH 22/52] tcp: md5: reject TCP_MD5SIG or TCP_MD5SIG_EXT on
 established sockets

[ Upstream commit 7212303268918b9a203aebeacfdbd83b5e87b20d ]

syzbot/KMSAN reported an uninit-value in tcp_parse_options() [1]

I believe this was caused by a TCP_MD5SIG being set on live
flow.

This is highly unexpected, since TCP option space is limited.

For instance, presence of TCP MD5 option automatically disables
TCP TimeStamp option at SYN/SYNACK time, which we can not do
once flow has been established.

Really, adding/deleting an MD5 key only makes sense on sockets
in CLOSE or LISTEN state.

[1]
BUG: KMSAN: uninit-value in tcp_parse_options+0xd74/0x1a30 net/ipv4/tcp_input.c:3720
CPU: 1 PID: 6177 Comm: syzkaller192004 Not tainted 4.16.0+ #83
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x185/0x1d0 lib/dump_stack.c:53
 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067
 __msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:676
 tcp_parse_options+0xd74/0x1a30 net/ipv4/tcp_input.c:3720
 tcp_fast_parse_options net/ipv4/tcp_input.c:3858 [inline]
 tcp_validate_incoming+0x4f1/0x2790 net/ipv4/tcp_input.c:5184
 tcp_rcv_established+0xf60/0x2bb0 net/ipv4/tcp_input.c:5453
 tcp_v4_do_rcv+0x6cd/0xd90 net/ipv4/tcp_ipv4.c:1469
 sk_backlog_rcv include/net/sock.h:908 [inline]
 __release_sock+0x2d6/0x680 net/core/sock.c:2271
 release_sock+0x97/0x2a0 net/core/sock.c:2786
 tcp_sendmsg+0xd6/0x100 net/ipv4/tcp.c:1464
 inet_sendmsg+0x48d/0x740 net/ipv4/af_inet.c:764
 sock_sendmsg_nosec net/socket.c:630 [inline]
 sock_sendmsg net/socket.c:640 [inline]
 SYSC_sendto+0x6c3/0x7e0 net/socket.c:1747
 SyS_sendto+0x8a/0xb0 net/socket.c:1715
 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x3d/0xa2
RIP: 0033:0x448fe9
RSP: 002b:00007fd472c64d38 EFLAGS: 00000216 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 00000000006e5a30 RCX: 0000000000448fe9
RDX: 000000000000029f RSI: 0000000020a88f88 RDI: 0000000000000004
RBP: 00000000006e5a34 R08: 0000000020e68000 R09: 0000000000000010
R10: 00000000200007fd R11: 0000000000000216 R12: 0000000000000000
R13: 00007fff074899ef R14: 00007fd472c659c0 R15: 0000000000000009

Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:278 [inline]
 kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:188
 kmsan_kmalloc+0x94/0x100 mm/kmsan/kmsan.c:314
 kmsan_slab_alloc+0x11/0x20 mm/kmsan/kmsan.c:321
 slab_post_alloc_hook mm/slab.h:445 [inline]
 slab_alloc_node mm/slub.c:2737 [inline]
 __kmalloc_node_track_caller+0xaed/0x11c0 mm/slub.c:4369
 __kmalloc_reserve net/core/skbuff.c:138 [inline]
 __alloc_skb+0x2cf/0x9f0 net/core/skbuff.c:206
 alloc_skb include/linux/skbuff.h:984 [inline]
 tcp_send_ack+0x18c/0x910 net/ipv4/tcp_output.c:3624
 __tcp_ack_snd_check net/ipv4/tcp_input.c:5040 [inline]
 tcp_ack_snd_check net/ipv4/tcp_input.c:5053 [inline]
 tcp_rcv_established+0x2103/0x2bb0 net/ipv4/tcp_input.c:5469
 tcp_v4_do_rcv+0x6cd/0xd90 net/ipv4/tcp_ipv4.c:1469
 sk_backlog_rcv include/net/sock.h:908 [inline]
 __release_sock+0x2d6/0x680 net/core/sock.c:2271
 release_sock+0x97/0x2a0 net/core/sock.c:2786
 tcp_sendmsg+0xd6/0x100 net/ipv4/tcp.c:1464
 inet_sendmsg+0x48d/0x740 net/ipv4/af_inet.c:764
 sock_sendmsg_nosec net/socket.c:630 [inline]
 sock_sendmsg net/socket.c:640 [inline]
 SYSC_sendto+0x6c3/0x7e0 net/socket.c:1747
 SyS_sendto+0x8a/0xb0 net/socket.c:1715
 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x3d/0xa2

Fixes: cfb6eeb4c860 ("[TCP]: MD5 Signature Option (RFC2385) support.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index bb48cd142b92..1ab8733dac5f 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2830,8 +2830,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 #ifdef CONFIG_TCP_MD5SIG
 	case TCP_MD5SIG:
 	case TCP_MD5SIG_EXT:
-		/* Read the IP->Key mappings from userspace */
-		err = tp->af_specific->md5_parse(sk, optname, optval, optlen);
+		if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))
+			err = tp->af_specific->md5_parse(sk, optname, optval, optlen);
+		else
+			err = -EINVAL;
 		break;
 #endif
 	case TCP_USER_TIMEOUT:
-- 
2.14.3


From 97c9b9642efbd260679e7eb52558ade9fb64b045 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 13 Apr 2018 13:59:25 +0200
Subject: [PATCH 23/52] team: avoid adding twice the same option to the event
 list

[ Upstream commit 4fb0534fb7bbc2346ba7d3a072b538007f4135a5 ]

When parsing the options provided by the user space,
team_nl_cmd_options_set() insert them in a temporary list to send
multiple events with a single message.
While each option's attribute is correctly validated, the code does
not check for duplicate entries before inserting into the event
list.

Exploiting the above, the syzbot was able to trigger the following
splat:

kernel BUG at lib/list_debug.c:31!
invalid opcode: 0000 [#1] SMP KASAN
Dumping ftrace buffer:
    (ftrace buffer empty)
Modules linked in:
CPU: 0 PID: 4466 Comm: syzkaller556835 Not tainted 4.16.0+ #17
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
RIP: 0010:__list_add_valid+0xaa/0xb0 lib/list_debug.c:29
RSP: 0018:ffff8801b04bf248 EFLAGS: 00010286
RAX: 0000000000000058 RBX: ffff8801c8fc7a90 RCX: 0000000000000000
RDX: 0000000000000058 RSI: ffffffff815fbf41 RDI: ffffed0036097e3f
RBP: ffff8801b04bf260 R08: ffff8801b0b2a700 R09: ffffed003b604f90
R10: ffffed003b604f90 R11: ffff8801db027c87 R12: ffff8801c8fc7a90
R13: ffff8801c8fc7a90 R14: dffffc0000000000 R15: 0000000000000000
FS:  0000000000b98880(0000) GS:ffff8801db000000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000000000043fc30 CR3: 00000001afe8e000 CR4: 00000000001406f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
  __list_add include/linux/list.h:60 [inline]
  list_add include/linux/list.h:79 [inline]
  team_nl_cmd_options_set+0x9ff/0x12b0 drivers/net/team/team.c:2571
  genl_family_rcv_msg+0x889/0x1120 net/netlink/genetlink.c:599
  genl_rcv_msg+0xc6/0x170 net/netlink/genetlink.c:624
  netlink_rcv_skb+0x172/0x440 net/netlink/af_netlink.c:2448
  genl_rcv+0x28/0x40 net/netlink/genetlink.c:635
  netlink_unicast_kernel net/netlink/af_netlink.c:1310 [inline]
  netlink_unicast+0x58b/0x740 net/netlink/af_netlink.c:1336
  netlink_sendmsg+0x9f0/0xfa0 net/netlink/af_netlink.c:1901
  sock_sendmsg_nosec net/socket.c:629 [inline]
  sock_sendmsg+0xd5/0x120 net/socket.c:639
  ___sys_sendmsg+0x805/0x940 net/socket.c:2117
  __sys_sendmsg+0x115/0x270 net/socket.c:2155
  SYSC_sendmsg net/socket.c:2164 [inline]
  SyS_sendmsg+0x29/0x30 net/socket.c:2162
  do_syscall_64+0x29e/0x9d0 arch/x86/entry/common.c:287
  entry_SYSCALL_64_after_hwframe+0x42/0xb7
RIP: 0033:0x4458b9
RSP: 002b:00007ffd1d4a7278 EFLAGS: 00000213 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 000000000000001b RCX: 00000000004458b9
RDX: 0000000000000010 RSI: 0000000020000d00 RDI: 0000000000000004
RBP: 00000000004a74ed R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000213 R12: 00007ffd1d4a7348
R13: 0000000000402a60 R14: 0000000000000000 R15: 0000000000000000
Code: 75 e8 eb a9 48 89 f7 48 89 75 e8 e8 d1 85 7b fe 48 8b 75 e8 eb bb 48
89 f2 48 89 d9 4c 89 e6 48 c7 c7 a0 84 d8 87 e8 ea 67 28 fe <0f> 0b 0f 1f
40 00 48 b8 00 00 00 00 00 fc ff df 55 48 89 e5 41
RIP: __list_add_valid+0xaa/0xb0 lib/list_debug.c:29 RSP: ffff8801b04bf248

This changeset addresses the avoiding list_add() if the current
option is already present in the event list.

Reported-and-tested-by: syzbot+4d4af685432dc0e56c91@syzkaller.appspotmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Fixes: 2fcdb2c9e659 ("team: allow to send multiple set events in one message")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index befed2d22bf4..13eaae7005e8 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -261,6 +261,17 @@ static void __team_option_inst_mark_removed_port(struct team *team,
 	}
 }
 
+static bool __team_option_inst_tmp_find(const struct list_head *opts,
+					const struct team_option_inst *needle)
+{
+	struct team_option_inst *opt_inst;
+
+	list_for_each_entry(opt_inst, opts, tmp_list)
+		if (opt_inst == needle)
+			return true;
+	return false;
+}
+
 static int __team_options_register(struct team *team,
 				   const struct team_option *option,
 				   size_t option_count)
@@ -2562,6 +2573,14 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info)
 			if (err)
 				goto team_put;
 			opt_inst->changed = true;
+
+			/* dumb/evil user-space can send us duplicate opt,
+			 * keep only the last one
+			 */
+			if (__team_option_inst_tmp_find(&opt_inst_list,
+							opt_inst))
+				continue;
+
 			list_add(&opt_inst->tmp_list, &opt_inst_list);
 		}
 		if (!opt_found) {
-- 
2.14.3


From e85b25a45eefcc0e488d0a7364aa6736173865d7 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 24 Apr 2018 14:33:37 +0800
Subject: [PATCH 24/52] team: fix netconsole setup over team
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 9cf2f437ca5b39828984064fad213e68fc17ef11 ]

The same fix in Commit dbe173079ab5 ("bridge: fix netconsole
setup over bridge") is also needed for team driver.

While at it, remove the unnecessary parameter *team from
team_port_enable_netpoll().

v1->v2:
  - fix it in a better way, as does bridge.

Fixes: 0fb52a27a04a ("team: cleanup netpoll clode")
Reported-by: João Avelino Bellomo Filho <jbellomo@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 13eaae7005e8..3175f7410baf 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1072,14 +1072,11 @@ static void team_port_leave(struct team *team, struct team_port *port)
 }
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
-static int team_port_enable_netpoll(struct team *team, struct team_port *port)
+static int __team_port_enable_netpoll(struct team_port *port)
 {
 	struct netpoll *np;
 	int err;
 
-	if (!team->dev->npinfo)
-		return 0;
-
 	np = kzalloc(sizeof(*np), GFP_KERNEL);
 	if (!np)
 		return -ENOMEM;
@@ -1093,6 +1090,14 @@ static int team_port_enable_netpoll(struct team *team, struct team_port *port)
 	return err;
 }
 
+static int team_port_enable_netpoll(struct team_port *port)
+{
+	if (!port->team->dev->npinfo)
+		return 0;
+
+	return __team_port_enable_netpoll(port);
+}
+
 static void team_port_disable_netpoll(struct team_port *port)
 {
 	struct netpoll *np = port->np;
@@ -1107,7 +1112,7 @@ static void team_port_disable_netpoll(struct team_port *port)
 	kfree(np);
 }
 #else
-static int team_port_enable_netpoll(struct team *team, struct team_port *port)
+static int team_port_enable_netpoll(struct team_port *port)
 {
 	return 0;
 }
@@ -1215,7 +1220,7 @@ static int team_port_add(struct team *team, struct net_device *port_dev)
 		goto err_vids_add;
 	}
 
-	err = team_port_enable_netpoll(team, port);
+	err = team_port_enable_netpoll(port);
 	if (err) {
 		netdev_err(dev, "Failed to enable netpoll on device %s\n",
 			   portname);
@@ -1912,7 +1917,7 @@ static int team_netpoll_setup(struct net_device *dev,
 
 	mutex_lock(&team->lock);
 	list_for_each_entry(port, &team->port_list, list) {
-		err = team_port_enable_netpoll(team, port);
+		err = __team_port_enable_netpoll(port);
 		if (err) {
 			__team_netpoll_cleanup(team);
 			break;
-- 
2.14.3


From 0d041d2cbf9e1d21ef724ee068eb59d5270f594a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 16 Apr 2018 08:29:42 -0700
Subject: [PATCH 25/52] tipc: add policy for TIPC_NLA_NET_ADDR

[ Upstream commit ec518f21cb1a1b1f8a516499ea05c60299e04963 ]

Before syzbot/KMSAN bites, add the missing policy for TIPC_NLA_NET_ADDR

Fixes: 27c21416727a ("tipc: add net set to new netlink api")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jon Maloy <jon.maloy@ericsson.com>
Cc: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/netlink.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index b76f13f6fea1..d4e0bbeee727 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -79,7 +79,8 @@ const struct nla_policy tipc_nl_sock_policy[TIPC_NLA_SOCK_MAX + 1] = {
 
 const struct nla_policy tipc_nl_net_policy[TIPC_NLA_NET_MAX + 1] = {
 	[TIPC_NLA_NET_UNSPEC]		= { .type = NLA_UNSPEC },
-	[TIPC_NLA_NET_ID]		= { .type = NLA_U32 }
+	[TIPC_NLA_NET_ID]		= { .type = NLA_U32 },
+	[TIPC_NLA_NET_ADDR]		= { .type = NLA_U32 },
 };
 
 const struct nla_policy tipc_nl_link_policy[TIPC_NLA_LINK_MAX + 1] = {
-- 
2.14.3


From c20a56e9ae8c4545dafcbd64f658cebe6a61dbf2 Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Tue, 17 Apr 2018 18:46:14 +0900
Subject: [PATCH 26/52] vlan: Fix reading memory beyond skb->tail in
 skb_vlan_tagged_multi

[ Upstream commit 7ce2367254e84753bceb07327aaf5c953cfce117 ]

Syzkaller spotted an old bug which leads to reading skb beyond tail by 4
bytes on vlan tagged packets.
This is caused because skb_vlan_tagged_multi() did not check
skb_headlen.

BUG: KMSAN: uninit-value in eth_type_vlan include/linux/if_vlan.h:283 [inline]
BUG: KMSAN: uninit-value in skb_vlan_tagged_multi include/linux/if_vlan.h:656 [inline]
BUG: KMSAN: uninit-value in vlan_features_check include/linux/if_vlan.h:672 [inline]
BUG: KMSAN: uninit-value in dflt_features_check net/core/dev.c:2949 [inline]
BUG: KMSAN: uninit-value in netif_skb_features+0xd1b/0xdc0 net/core/dev.c:3009
CPU: 1 PID: 3582 Comm: syzkaller435149 Not tainted 4.16.0+ #82
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
  __dump_stack lib/dump_stack.c:17 [inline]
  dump_stack+0x185/0x1d0 lib/dump_stack.c:53
  kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067
  __msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:676
  eth_type_vlan include/linux/if_vlan.h:283 [inline]
  skb_vlan_tagged_multi include/linux/if_vlan.h:656 [inline]
  vlan_features_check include/linux/if_vlan.h:672 [inline]
  dflt_features_check net/core/dev.c:2949 [inline]
  netif_skb_features+0xd1b/0xdc0 net/core/dev.c:3009
  validate_xmit_skb+0x89/0x1320 net/core/dev.c:3084
  __dev_queue_xmit+0x1cb2/0x2b60 net/core/dev.c:3549
  dev_queue_xmit+0x4b/0x60 net/core/dev.c:3590
  packet_snd net/packet/af_packet.c:2944 [inline]
  packet_sendmsg+0x7c57/0x8a10 net/packet/af_packet.c:2969
  sock_sendmsg_nosec net/socket.c:630 [inline]
  sock_sendmsg net/socket.c:640 [inline]
  sock_write_iter+0x3b9/0x470 net/socket.c:909
  do_iter_readv_writev+0x7bb/0x970 include/linux/fs.h:1776
  do_iter_write+0x30d/0xd40 fs/read_write.c:932
  vfs_writev fs/read_write.c:977 [inline]
  do_writev+0x3c9/0x830 fs/read_write.c:1012
  SYSC_writev+0x9b/0xb0 fs/read_write.c:1085
  SyS_writev+0x56/0x80 fs/read_write.c:1082
  do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
  entry_SYSCALL_64_after_hwframe+0x3d/0xa2
RIP: 0033:0x43ffa9
RSP: 002b:00007fff2cff3948 EFLAGS: 00000217 ORIG_RAX: 0000000000000014
RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 000000000043ffa9
RDX: 0000000000000001 RSI: 0000000020000080 RDI: 0000000000000003
RBP: 00000000006cb018 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000217 R12: 00000000004018d0
R13: 0000000000401960 R14: 0000000000000000 R15: 0000000000000000

Uninit was created at:
  kmsan_save_stack_with_flags mm/kmsan/kmsan.c:278 [inline]
  kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:188
  kmsan_kmalloc+0x94/0x100 mm/kmsan/kmsan.c:314
  kmsan_slab_alloc+0x11/0x20 mm/kmsan/kmsan.c:321
  slab_post_alloc_hook mm/slab.h:445 [inline]
  slab_alloc_node mm/slub.c:2737 [inline]
  __kmalloc_node_track_caller+0xaed/0x11c0 mm/slub.c:4369
  __kmalloc_reserve net/core/skbuff.c:138 [inline]
  __alloc_skb+0x2cf/0x9f0 net/core/skbuff.c:206
  alloc_skb include/linux/skbuff.h:984 [inline]
  alloc_skb_with_frags+0x1d4/0xb20 net/core/skbuff.c:5234
  sock_alloc_send_pskb+0xb56/0x1190 net/core/sock.c:2085
  packet_alloc_skb net/packet/af_packet.c:2803 [inline]
  packet_snd net/packet/af_packet.c:2894 [inline]
  packet_sendmsg+0x6444/0x8a10 net/packet/af_packet.c:2969
  sock_sendmsg_nosec net/socket.c:630 [inline]
  sock_sendmsg net/socket.c:640 [inline]
  sock_write_iter+0x3b9/0x470 net/socket.c:909
  do_iter_readv_writev+0x7bb/0x970 include/linux/fs.h:1776
  do_iter_write+0x30d/0xd40 fs/read_write.c:932
  vfs_writev fs/read_write.c:977 [inline]
  do_writev+0x3c9/0x830 fs/read_write.c:1012
  SYSC_writev+0x9b/0xb0 fs/read_write.c:1085
  SyS_writev+0x56/0x80 fs/read_write.c:1082
  do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
  entry_SYSCALL_64_after_hwframe+0x3d/0xa2

Fixes: 58e998c6d239 ("offloading: Force software GSO for multiple vlan tags.")
Reported-and-tested-by: syzbot+0bbe42c764feafa82c5a@syzkaller.appspotmail.com
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_vlan.h | 7 +++++--
 net/core/dev.c          | 2 +-
 2 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 7d30892da064..87b8c20d5b27 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -639,7 +639,7 @@ static inline bool skb_vlan_tagged(const struct sk_buff *skb)
  * Returns true if the skb is tagged with multiple vlan headers, regardless
  * of whether it is hardware accelerated or not.
  */
-static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb)
+static inline bool skb_vlan_tagged_multi(struct sk_buff *skb)
 {
 	__be16 protocol = skb->protocol;
 
@@ -649,6 +649,9 @@ static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb)
 		if (likely(!eth_type_vlan(protocol)))
 			return false;
 
+		if (unlikely(!pskb_may_pull(skb, VLAN_ETH_HLEN)))
+			return false;
+
 		veh = (struct vlan_ethhdr *)skb->data;
 		protocol = veh->h_vlan_encapsulated_proto;
 	}
@@ -666,7 +669,7 @@ static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb)
  *
  * Returns features without unsafe ones if the skb has multiple tags.
  */
-static inline netdev_features_t vlan_features_check(const struct sk_buff *skb,
+static inline netdev_features_t vlan_features_check(struct sk_buff *skb,
 						    netdev_features_t features)
 {
 	if (skb_vlan_tagged_multi(skb)) {
diff --git a/net/core/dev.c b/net/core/dev.c
index c4aa2941dbfd..3e550507e9f0 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2942,7 +2942,7 @@ netdev_features_t passthru_features_check(struct sk_buff *skb,
 }
 EXPORT_SYMBOL(passthru_features_check);
 
-static netdev_features_t dflt_features_check(const struct sk_buff *skb,
+static netdev_features_t dflt_features_check(struct sk_buff *skb,
 					     struct net_device *dev,
 					     netdev_features_t features)
 {
-- 
2.14.3


From ab29416f31d6c071732f17fe2a123ba83c86e49b Mon Sep 17 00:00:00 2001
From: Ronak Doshi <doshir@vmware.com>
Date: Wed, 18 Apr 2018 12:48:04 -0700
Subject: [PATCH 27/52] vmxnet3: fix incorrect dereference when rxvlan is
 disabled

[ Upstream commit 65ec0bd1c7c14522670a5294de35710fb577a7fd ]

vmxnet3_get_hdr_len() is used to calculate the header length which in
turn is used to calculate the gso_size for skb. When rxvlan offload is
disabled, vlan tag is present in the header and the function references
ip header from sizeof(ethhdr) and leads to incorrect pointer reference.

This patch fixes this issue by taking sizeof(vlan_ethhdr) into account
if vlan tag is present and correctly references the ip hdr.

Signed-off-by: Ronak Doshi <doshir@vmware.com>
Acked-by: Guolin Yang <gyang@vmware.com>
Acked-by: Louis Luo <llouis@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vmxnet3/vmxnet3_drv.c | 17 +++++++++++++----
 drivers/net/vmxnet3/vmxnet3_int.h |  4 ++--
 2 files changed, 15 insertions(+), 6 deletions(-)

diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index e04937f44f33..9ebe2a689966 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -1218,6 +1218,7 @@ vmxnet3_get_hdr_len(struct vmxnet3_adapter *adapter, struct sk_buff *skb,
 	union {
 		void *ptr;
 		struct ethhdr *eth;
+		struct vlan_ethhdr *veth;
 		struct iphdr *ipv4;
 		struct ipv6hdr *ipv6;
 		struct tcphdr *tcp;
@@ -1228,16 +1229,24 @@ vmxnet3_get_hdr_len(struct vmxnet3_adapter *adapter, struct sk_buff *skb,
 	if (unlikely(sizeof(struct iphdr) + sizeof(struct tcphdr) > maplen))
 		return 0;
 
+	if (skb->protocol == cpu_to_be16(ETH_P_8021Q) ||
+	    skb->protocol == cpu_to_be16(ETH_P_8021AD))
+		hlen = sizeof(struct vlan_ethhdr);
+	else
+		hlen = sizeof(struct ethhdr);
+
 	hdr.eth = eth_hdr(skb);
 	if (gdesc->rcd.v4) {
-		BUG_ON(hdr.eth->h_proto != htons(ETH_P_IP));
-		hdr.ptr += sizeof(struct ethhdr);
+		BUG_ON(hdr.eth->h_proto != htons(ETH_P_IP) &&
+		       hdr.veth->h_vlan_encapsulated_proto != htons(ETH_P_IP));
+		hdr.ptr += hlen;
 		BUG_ON(hdr.ipv4->protocol != IPPROTO_TCP);
 		hlen = hdr.ipv4->ihl << 2;
 		hdr.ptr += hdr.ipv4->ihl << 2;
 	} else if (gdesc->rcd.v6) {
-		BUG_ON(hdr.eth->h_proto != htons(ETH_P_IPV6));
-		hdr.ptr += sizeof(struct ethhdr);
+		BUG_ON(hdr.eth->h_proto != htons(ETH_P_IPV6) &&
+		       hdr.veth->h_vlan_encapsulated_proto != htons(ETH_P_IPV6));
+		hdr.ptr += hlen;
 		/* Use an estimated value, since we also need to handle
 		 * TSO case.
 		 */
diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h
index 59ec34052a65..a3326463b71f 100644
--- a/drivers/net/vmxnet3/vmxnet3_int.h
+++ b/drivers/net/vmxnet3/vmxnet3_int.h
@@ -69,10 +69,10 @@
 /*
  * Version numbers
  */
-#define VMXNET3_DRIVER_VERSION_STRING   "1.4.13.0-k"
+#define VMXNET3_DRIVER_VERSION_STRING   "1.4.14.0-k"
 
 /* a 32-bit int, each byte encode a verion number in VMXNET3_DRIVER_VERSION */
-#define VMXNET3_DRIVER_VERSION_NUM      0x01040d00
+#define VMXNET3_DRIVER_VERSION_NUM      0x01040e00
 
 #if defined(CONFIG_PCI_MSI)
 	/* RSS only makes sense if MSI-X is supported. */
-- 
2.14.3


From 2a05c7ffe02cc331cea7bc510822dd6e44166761 Mon Sep 17 00:00:00 2001
From: Tom Lendacky <thomas.lendacky@amd.com>
Date: Mon, 23 Apr 2018 11:43:08 -0500
Subject: [PATCH 28/52] amd-xgbe: Add pre/post auto-negotiation phy hooks

[ Upstream commit 4d945663a6a0acf3cbe45940503f2eb9584bfee7 ]

Add hooks to the driver auto-negotiation (AN) flow to allow the different
phy implementations to perform any steps necessary to improve AN.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe-mdio.c | 16 ++++++++++++++--
 drivers/net/ethernet/amd/xgbe/xgbe.h      |  5 +++++
 2 files changed, 19 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
index 072b9f664597..e3d361e242aa 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
@@ -437,6 +437,9 @@ static void xgbe_an73_disable(struct xgbe_prv_data *pdata)
 
 static void xgbe_an_restart(struct xgbe_prv_data *pdata)
 {
+	if (pdata->phy_if.phy_impl.an_pre)
+		pdata->phy_if.phy_impl.an_pre(pdata);
+
 	switch (pdata->an_mode) {
 	case XGBE_AN_MODE_CL73:
 	case XGBE_AN_MODE_CL73_REDRV:
@@ -453,6 +456,9 @@ static void xgbe_an_restart(struct xgbe_prv_data *pdata)
 
 static void xgbe_an_disable(struct xgbe_prv_data *pdata)
 {
+	if (pdata->phy_if.phy_impl.an_post)
+		pdata->phy_if.phy_impl.an_post(pdata);
+
 	switch (pdata->an_mode) {
 	case XGBE_AN_MODE_CL73:
 	case XGBE_AN_MODE_CL73_REDRV:
@@ -637,11 +643,11 @@ static enum xgbe_an xgbe_an73_incompat_link(struct xgbe_prv_data *pdata)
 			return XGBE_AN_NO_LINK;
 	}
 
-	xgbe_an73_disable(pdata);
+	xgbe_an_disable(pdata);
 
 	xgbe_switch_mode(pdata);
 
-	xgbe_an73_restart(pdata);
+	xgbe_an_restart(pdata);
 
 	return XGBE_AN_INCOMPAT_LINK;
 }
@@ -820,6 +826,9 @@ static void xgbe_an37_state_machine(struct xgbe_prv_data *pdata)
 		pdata->an_result = pdata->an_state;
 		pdata->an_state = XGBE_AN_READY;
 
+		if (pdata->phy_if.phy_impl.an_post)
+			pdata->phy_if.phy_impl.an_post(pdata);
+
 		netif_dbg(pdata, link, pdata->netdev, "CL37 AN result: %s\n",
 			  xgbe_state_as_string(pdata->an_result));
 	}
@@ -903,6 +912,9 @@ static void xgbe_an73_state_machine(struct xgbe_prv_data *pdata)
 		pdata->kx_state = XGBE_RX_BPA;
 		pdata->an_start = 0;
 
+		if (pdata->phy_if.phy_impl.an_post)
+			pdata->phy_if.phy_impl.an_post(pdata);
+
 		netif_dbg(pdata, link, pdata->netdev, "CL73 AN result: %s\n",
 			  xgbe_state_as_string(pdata->an_result));
 	}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h
index ad102c8bac7b..fa0b51ea1b95 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe.h
@@ -833,6 +833,7 @@ struct xgbe_hw_if {
 /* This structure represents implementation specific routines for an
  * implementation of a PHY. All routines are required unless noted below.
  *   Optional routines:
+ *     an_pre, an_post
  *     kr_training_pre, kr_training_post
  */
 struct xgbe_phy_impl_if {
@@ -875,6 +876,10 @@ struct xgbe_phy_impl_if {
 	/* Process results of auto-negotiation */
 	enum xgbe_mode (*an_outcome)(struct xgbe_prv_data *);
 
+	/* Pre/Post auto-negotiation support */
+	void (*an_pre)(struct xgbe_prv_data *);
+	void (*an_post)(struct xgbe_prv_data *);
+
 	/* Pre/Post KR training enablement support */
 	void (*kr_training_pre)(struct xgbe_prv_data *);
 	void (*kr_training_post)(struct xgbe_prv_data *);
-- 
2.14.3


From e5e8a2b11dbfc3da0f0ba1f68cdb8a561131a7a2 Mon Sep 17 00:00:00 2001
From: Tom Lendacky <thomas.lendacky@amd.com>
Date: Mon, 23 Apr 2018 11:43:17 -0500
Subject: [PATCH 29/52] amd-xgbe: Improve KR auto-negotiation and training

[ Upstream commit 96f4d430c507ed4856048c2dc9c1a2ea5b5e74e4 ]

Update xgbe-phy-v2.c to make use of the auto-negotiation (AN) phy hooks
to improve the ability to successfully complete Clause 73 AN when running
at 10gbps.  Hardware can sometimes have issues with CDR lock when the
AN DME page exchange is being performed.

The AN and KR training hooks are used as follows:
- The pre AN hook is used to disable CDR tracking in the PHY so that the
  DME page exchange can be successfully and consistently completed.
- The post KR training hook is used to re-enable the CDR tracking so that
  KR training can successfully complete.
- The post AN hook is used to check for an unsuccessful AN which will
  increase a CDR tracking enablement delay (up to a maximum value).

Add two debugfs entries to allow control over use of the CDR tracking
workaround.  The debugfs entries allow the CDR tracking workaround to
be disabled and determine whether to re-enable CDR tracking before or
after link training has been initiated.

Also, with these changes the receiver reset cycle that is performed during
the link status check can be performed less often.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe-common.h  |   8 ++
 drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c |  16 ++++
 drivers/net/ethernet/amd/xgbe/xgbe-main.c    |   1 +
 drivers/net/ethernet/amd/xgbe/xgbe-mdio.c    |   8 +-
 drivers/net/ethernet/amd/xgbe/xgbe-pci.c     |   2 +
 drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c  | 125 ++++++++++++++++++++++++++-
 drivers/net/ethernet/amd/xgbe/xgbe.h         |   4 +
 7 files changed, 160 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
index 7ea72ef11a55..d272dc6984ac 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
@@ -1321,6 +1321,10 @@
 #define MDIO_VEND2_AN_STAT		0x8002
 #endif
 
+#ifndef MDIO_VEND2_PMA_CDR_CONTROL
+#define MDIO_VEND2_PMA_CDR_CONTROL	0x8056
+#endif
+
 #ifndef MDIO_CTRL1_SPEED1G
 #define MDIO_CTRL1_SPEED1G		(MDIO_CTRL1_SPEED10G & ~BMCR_SPEED100)
 #endif
@@ -1369,6 +1373,10 @@
 #define XGBE_AN_CL37_TX_CONFIG_MASK	0x08
 #define XGBE_AN_CL37_MII_CTRL_8BIT	0x0100
 
+#define XGBE_PMA_CDR_TRACK_EN_MASK	0x01
+#define XGBE_PMA_CDR_TRACK_EN_OFF	0x00
+#define XGBE_PMA_CDR_TRACK_EN_ON	0x01
+
 /* Bit setting and getting macros
  *  The get macro will extract the current bit field value from within
  *  the variable
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c
index 7d128be61310..b91143947ed2 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c
@@ -519,6 +519,22 @@ void xgbe_debugfs_init(struct xgbe_prv_data *pdata)
 				   "debugfs_create_file failed\n");
 	}
 
+	if (pdata->vdata->an_cdr_workaround) {
+		pfile = debugfs_create_bool("an_cdr_workaround", 0600,
+					    pdata->xgbe_debugfs,
+					    &pdata->debugfs_an_cdr_workaround);
+		if (!pfile)
+			netdev_err(pdata->netdev,
+				   "debugfs_create_bool failed\n");
+
+		pfile = debugfs_create_bool("an_cdr_track_early", 0600,
+					    pdata->xgbe_debugfs,
+					    &pdata->debugfs_an_cdr_track_early);
+		if (!pfile)
+			netdev_err(pdata->netdev,
+				   "debugfs_create_bool failed\n");
+	}
+
 	kfree(buf);
 }
 
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-main.c b/drivers/net/ethernet/amd/xgbe/xgbe-main.c
index d91fa595be98..e31d9d1fb6a6 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-main.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-main.c
@@ -349,6 +349,7 @@ int xgbe_config_netdev(struct xgbe_prv_data *pdata)
 	XGMAC_SET_BITS(pdata->rss_options, MAC_RSSCR, UDP4TE, 1);
 
 	/* Call MDIO/PHY initialization routine */
+	pdata->debugfs_an_cdr_workaround = pdata->vdata->an_cdr_workaround;
 	ret = pdata->phy_if.phy_init(pdata);
 	if (ret)
 		return ret;
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
index e3d361e242aa..1b45cd73a258 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
@@ -432,6 +432,8 @@ static void xgbe_an73_disable(struct xgbe_prv_data *pdata)
 	xgbe_an73_set(pdata, false, false);
 	xgbe_an73_disable_interrupts(pdata);
 
+	pdata->an_start = 0;
+
 	netif_dbg(pdata, link, pdata->netdev, "CL73 AN disabled\n");
 }
 
@@ -511,11 +513,11 @@ static enum xgbe_an xgbe_an73_tx_training(struct xgbe_prv_data *pdata,
 		XMDIO_WRITE(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL,
 			    reg);
 
-		if (pdata->phy_if.phy_impl.kr_training_post)
-			pdata->phy_if.phy_impl.kr_training_post(pdata);
-
 		netif_dbg(pdata, link, pdata->netdev,
 			  "KR training initiated\n");
+
+		if (pdata->phy_if.phy_impl.kr_training_post)
+			pdata->phy_if.phy_impl.kr_training_post(pdata);
 	}
 
 	return XGBE_AN_PAGE_RECEIVED;
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
index eb23f9ba1a9a..82d1f416ee2a 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
@@ -456,6 +456,7 @@ static const struct xgbe_version_data xgbe_v2a = {
 	.irq_reissue_support		= 1,
 	.tx_desc_prefetch		= 5,
 	.rx_desc_prefetch		= 5,
+	.an_cdr_workaround		= 1,
 };
 
 static const struct xgbe_version_data xgbe_v2b = {
@@ -470,6 +471,7 @@ static const struct xgbe_version_data xgbe_v2b = {
 	.irq_reissue_support		= 1,
 	.tx_desc_prefetch		= 5,
 	.rx_desc_prefetch		= 5,
+	.an_cdr_workaround		= 1,
 };
 
 static const struct pci_device_id xgbe_pci_table[] = {
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
index 3304a291aa96..b48efc04c4da 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
@@ -147,6 +147,14 @@
 /* Rate-change complete wait/retry count */
 #define XGBE_RATECHANGE_COUNT		500
 
+/* CDR delay values for KR support (in usec) */
+#define XGBE_CDR_DELAY_INIT		10000
+#define XGBE_CDR_DELAY_INC		10000
+#define XGBE_CDR_DELAY_MAX		100000
+
+/* RRC frequency during link status check */
+#define XGBE_RRC_FREQUENCY		10
+
 enum xgbe_port_mode {
 	XGBE_PORT_MODE_RSVD = 0,
 	XGBE_PORT_MODE_BACKPLANE,
@@ -355,6 +363,10 @@ struct xgbe_phy_data {
 	unsigned int redrv_addr;
 	unsigned int redrv_lane;
 	unsigned int redrv_model;
+
+	/* KR AN support */
+	unsigned int phy_cdr_notrack;
+	unsigned int phy_cdr_delay;
 };
 
 /* I2C, MDIO and GPIO lines are muxed, so only one device at a time */
@@ -2361,7 +2373,7 @@ static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart)
 		return 1;
 
 	/* No link, attempt a receiver reset cycle */
-	if (phy_data->rrc_count++) {
+	if (phy_data->rrc_count++ > XGBE_RRC_FREQUENCY) {
 		phy_data->rrc_count = 0;
 		xgbe_phy_rrc(pdata);
 	}
@@ -2669,6 +2681,103 @@ static bool xgbe_phy_port_enabled(struct xgbe_prv_data *pdata)
 	return true;
 }
 
+static void xgbe_phy_cdr_track(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+	if (!pdata->debugfs_an_cdr_workaround)
+		return;
+
+	if (!phy_data->phy_cdr_notrack)
+		return;
+
+	usleep_range(phy_data->phy_cdr_delay,
+		     phy_data->phy_cdr_delay + 500);
+
+	XMDIO_WRITE_BITS(pdata, MDIO_MMD_PMAPMD, MDIO_VEND2_PMA_CDR_CONTROL,
+			 XGBE_PMA_CDR_TRACK_EN_MASK,
+			 XGBE_PMA_CDR_TRACK_EN_ON);
+
+	phy_data->phy_cdr_notrack = 0;
+}
+
+static void xgbe_phy_cdr_notrack(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+	if (!pdata->debugfs_an_cdr_workaround)
+		return;
+
+	if (phy_data->phy_cdr_notrack)
+		return;
+
+	XMDIO_WRITE_BITS(pdata, MDIO_MMD_PMAPMD, MDIO_VEND2_PMA_CDR_CONTROL,
+			 XGBE_PMA_CDR_TRACK_EN_MASK,
+			 XGBE_PMA_CDR_TRACK_EN_OFF);
+
+	xgbe_phy_rrc(pdata);
+
+	phy_data->phy_cdr_notrack = 1;
+}
+
+static void xgbe_phy_kr_training_post(struct xgbe_prv_data *pdata)
+{
+	if (!pdata->debugfs_an_cdr_track_early)
+		xgbe_phy_cdr_track(pdata);
+}
+
+static void xgbe_phy_kr_training_pre(struct xgbe_prv_data *pdata)
+{
+	if (pdata->debugfs_an_cdr_track_early)
+		xgbe_phy_cdr_track(pdata);
+}
+
+static void xgbe_phy_an_post(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+	switch (pdata->an_mode) {
+	case XGBE_AN_MODE_CL73:
+	case XGBE_AN_MODE_CL73_REDRV:
+		if (phy_data->cur_mode != XGBE_MODE_KR)
+			break;
+
+		xgbe_phy_cdr_track(pdata);
+
+		switch (pdata->an_result) {
+		case XGBE_AN_READY:
+		case XGBE_AN_COMPLETE:
+			break;
+		default:
+			if (phy_data->phy_cdr_delay < XGBE_CDR_DELAY_MAX)
+				phy_data->phy_cdr_delay += XGBE_CDR_DELAY_INC;
+			else
+				phy_data->phy_cdr_delay = XGBE_CDR_DELAY_INIT;
+			break;
+		}
+		break;
+	default:
+		break;
+	}
+}
+
+static void xgbe_phy_an_pre(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+	switch (pdata->an_mode) {
+	case XGBE_AN_MODE_CL73:
+	case XGBE_AN_MODE_CL73_REDRV:
+		if (phy_data->cur_mode != XGBE_MODE_KR)
+			break;
+
+		xgbe_phy_cdr_notrack(pdata);
+		break;
+	default:
+		break;
+	}
+}
+
 static void xgbe_phy_stop(struct xgbe_prv_data *pdata)
 {
 	struct xgbe_phy_data *phy_data = pdata->phy_data;
@@ -2680,6 +2789,9 @@ static void xgbe_phy_stop(struct xgbe_prv_data *pdata)
 	xgbe_phy_sfp_reset(phy_data);
 	xgbe_phy_sfp_mod_absent(pdata);
 
+	/* Reset CDR support */
+	xgbe_phy_cdr_track(pdata);
+
 	/* Power off the PHY */
 	xgbe_phy_power_off(pdata);
 
@@ -2712,6 +2824,9 @@ static int xgbe_phy_start(struct xgbe_prv_data *pdata)
 	/* Start in highest supported mode */
 	xgbe_phy_set_mode(pdata, phy_data->start_mode);
 
+	/* Reset CDR support */
+	xgbe_phy_cdr_track(pdata);
+
 	/* After starting the I2C controller, we can check for an SFP */
 	switch (phy_data->port_mode) {
 	case XGBE_PORT_MODE_SFP:
@@ -3019,6 +3134,8 @@ static int xgbe_phy_init(struct xgbe_prv_data *pdata)
 		}
 	}
 
+	phy_data->phy_cdr_delay = XGBE_CDR_DELAY_INIT;
+
 	/* Register for driving external PHYs */
 	mii = devm_mdiobus_alloc(pdata->dev);
 	if (!mii) {
@@ -3071,4 +3188,10 @@ void xgbe_init_function_ptrs_phy_v2(struct xgbe_phy_if *phy_if)
 	phy_impl->an_advertising	= xgbe_phy_an_advertising;
 
 	phy_impl->an_outcome		= xgbe_phy_an_outcome;
+
+	phy_impl->an_pre		= xgbe_phy_an_pre;
+	phy_impl->an_post		= xgbe_phy_an_post;
+
+	phy_impl->kr_training_pre	= xgbe_phy_kr_training_pre;
+	phy_impl->kr_training_post	= xgbe_phy_kr_training_post;
 }
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h
index fa0b51ea1b95..95d4b56448c6 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe.h
@@ -994,6 +994,7 @@ struct xgbe_version_data {
 	unsigned int irq_reissue_support;
 	unsigned int tx_desc_prefetch;
 	unsigned int rx_desc_prefetch;
+	unsigned int an_cdr_workaround;
 };
 
 struct xgbe_vxlan_data {
@@ -1262,6 +1263,9 @@ struct xgbe_prv_data {
 	unsigned int debugfs_xprop_reg;
 
 	unsigned int debugfs_xi2c_reg;
+
+	bool debugfs_an_cdr_workaround;
+	bool debugfs_an_cdr_track_early;
 };
 
 /* Function prototypes*/
-- 
2.14.3


From 596ca73bcf0784b2c09e8e246709e6cb52b47a52 Mon Sep 17 00:00:00 2001
From: Tom Lendacky <thomas.lendacky@amd.com>
Date: Mon, 23 Apr 2018 11:43:34 -0500
Subject: [PATCH 30/52] amd-xgbe: Only use the SFP supported transceiver
 signals

[ Upstream commit 117df655f8ed51adb6e6b163812a06ebeae9f453 ]

The SFP eeprom indicates the transceiver signals (Rx LOS, Tx Fault, etc.)
that it supports.  Update the driver to include checking the eeprom data
when deciding whether to use a transceiver signal.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c | 71 ++++++++++++++++++++++-------
 1 file changed, 54 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
index b48efc04c4da..aac884314000 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
@@ -253,6 +253,10 @@ enum xgbe_sfp_speed {
 #define XGBE_SFP_BASE_VENDOR_SN			4
 #define XGBE_SFP_BASE_VENDOR_SN_LEN		16
 
+#define XGBE_SFP_EXTD_OPT1			1
+#define XGBE_SFP_EXTD_OPT1_RX_LOS		BIT(1)
+#define XGBE_SFP_EXTD_OPT1_TX_FAULT		BIT(3)
+
 #define XGBE_SFP_EXTD_DIAG			28
 #define XGBE_SFP_EXTD_DIAG_ADDR_CHANGE		BIT(2)
 
@@ -332,6 +336,7 @@ struct xgbe_phy_data {
 
 	unsigned int sfp_gpio_address;
 	unsigned int sfp_gpio_mask;
+	unsigned int sfp_gpio_inputs;
 	unsigned int sfp_gpio_rx_los;
 	unsigned int sfp_gpio_tx_fault;
 	unsigned int sfp_gpio_mod_absent;
@@ -986,6 +991,49 @@ static void xgbe_phy_sfp_external_phy(struct xgbe_prv_data *pdata)
 	phy_data->sfp_phy_avail = 1;
 }
 
+static bool xgbe_phy_check_sfp_rx_los(struct xgbe_phy_data *phy_data)
+{
+	u8 *sfp_extd = phy_data->sfp_eeprom.extd;
+
+	if (!(sfp_extd[XGBE_SFP_EXTD_OPT1] & XGBE_SFP_EXTD_OPT1_RX_LOS))
+		return false;
+
+	if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_RX_LOS)
+		return false;
+
+	if (phy_data->sfp_gpio_inputs & (1 << phy_data->sfp_gpio_rx_los))
+		return true;
+
+	return false;
+}
+
+static bool xgbe_phy_check_sfp_tx_fault(struct xgbe_phy_data *phy_data)
+{
+	u8 *sfp_extd = phy_data->sfp_eeprom.extd;
+
+	if (!(sfp_extd[XGBE_SFP_EXTD_OPT1] & XGBE_SFP_EXTD_OPT1_TX_FAULT))
+		return false;
+
+	if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_TX_FAULT)
+		return false;
+
+	if (phy_data->sfp_gpio_inputs & (1 << phy_data->sfp_gpio_tx_fault))
+		return true;
+
+	return false;
+}
+
+static bool xgbe_phy_check_sfp_mod_absent(struct xgbe_phy_data *phy_data)
+{
+	if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_MOD_ABSENT)
+		return false;
+
+	if (phy_data->sfp_gpio_inputs & (1 << phy_data->sfp_gpio_mod_absent))
+		return true;
+
+	return false;
+}
+
 static bool xgbe_phy_belfuse_parse_quirks(struct xgbe_prv_data *pdata)
 {
 	struct xgbe_phy_data *phy_data = pdata->phy_data;
@@ -1031,6 +1079,10 @@ static void xgbe_phy_sfp_parse_eeprom(struct xgbe_prv_data *pdata)
 	if (sfp_base[XGBE_SFP_BASE_EXT_ID] != XGBE_SFP_EXT_ID_SFP)
 		return;
 
+	/* Update transceiver signals (eeprom extd/options) */
+	phy_data->sfp_tx_fault = xgbe_phy_check_sfp_tx_fault(phy_data);
+	phy_data->sfp_rx_los = xgbe_phy_check_sfp_rx_los(phy_data);
+
 	if (xgbe_phy_sfp_parse_quirks(pdata))
 		return;
 
@@ -1196,7 +1248,6 @@ static int xgbe_phy_sfp_read_eeprom(struct xgbe_prv_data *pdata)
 static void xgbe_phy_sfp_signals(struct xgbe_prv_data *pdata)
 {
 	struct xgbe_phy_data *phy_data = pdata->phy_data;
-	unsigned int gpio_input;
 	u8 gpio_reg, gpio_ports[2];
 	int ret;
 
@@ -1211,23 +1262,9 @@ static void xgbe_phy_sfp_signals(struct xgbe_prv_data *pdata)
 		return;
 	}
 
-	gpio_input = (gpio_ports[1] << 8) | gpio_ports[0];
-
-	if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_MOD_ABSENT) {
-		/* No GPIO, just assume the module is present for now */
-		phy_data->sfp_mod_absent = 0;
-	} else {
-		if (!(gpio_input & (1 << phy_data->sfp_gpio_mod_absent)))
-			phy_data->sfp_mod_absent = 0;
-	}
-
-	if (!(phy_data->sfp_gpio_mask & XGBE_GPIO_NO_RX_LOS) &&
-	    (gpio_input & (1 << phy_data->sfp_gpio_rx_los)))
-		phy_data->sfp_rx_los = 1;
+	phy_data->sfp_gpio_inputs = (gpio_ports[1] << 8) | gpio_ports[0];
 
-	if (!(phy_data->sfp_gpio_mask & XGBE_GPIO_NO_TX_FAULT) &&
-	    (gpio_input & (1 << phy_data->sfp_gpio_tx_fault)))
-		phy_data->sfp_tx_fault = 1;
+	phy_data->sfp_mod_absent = xgbe_phy_check_sfp_mod_absent(phy_data);
 }
 
 static void xgbe_phy_sfp_mod_absent(struct xgbe_prv_data *pdata)
-- 
2.14.3


From f09b880b6f9c1cbcf1a3be8e2a0a6ce3502e9e6c Mon Sep 17 00:00:00 2001
From: Alexander Aring <aring@mojatatu.com>
Date: Fri, 20 Apr 2018 15:15:03 -0400
Subject: [PATCH 31/52] net: sched: ife: signal not finding metaid

[ Upstream commit f6cd14537ff9919081be19b9c53b9b19c0d3ea97 ]

We need to record stats for received metadata that we dont know how
to process. Have find_decode_metaid() return -ENOENT to capture this.

Signed-off-by: Alexander Aring <aring@mojatatu.com>
Reviewed-by: Yotam Gigi <yotam.gi@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ife.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 5954e992685a..3c046d505e86 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -652,7 +652,7 @@ static int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife,
 		}
 	}
 
-	return 0;
+	return -ENOENT;
 }
 
 static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a,
-- 
2.14.3


From 59640becb4adda781621f7ddf5fe3f0ad05377e8 Mon Sep 17 00:00:00 2001
From: Alexander Aring <aring@mojatatu.com>
Date: Fri, 20 Apr 2018 15:15:04 -0400
Subject: [PATCH 32/52] net: sched: ife: handle malformed tlv length

[ Upstream commit cc74eddd0ff325d57373cea99f642b787d7f76f5 ]

There is currently no handling to check on a invalid tlv length. This
patch adds such handling to avoid killing the kernel with a malformed
ife packet.

Signed-off-by: Alexander Aring <aring@mojatatu.com>
Reviewed-by: Yotam Gigi <yotam.gi@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ife.h   |  3 ++-
 net/ife/ife.c       | 35 +++++++++++++++++++++++++++++++++--
 net/sched/act_ife.c |  7 ++++++-
 3 files changed, 41 insertions(+), 4 deletions(-)

diff --git a/include/net/ife.h b/include/net/ife.h
index 44b9c00f7223..e117617e3c34 100644
--- a/include/net/ife.h
+++ b/include/net/ife.h
@@ -12,7 +12,8 @@
 void *ife_encode(struct sk_buff *skb, u16 metalen);
 void *ife_decode(struct sk_buff *skb, u16 *metalen);
 
-void *ife_tlv_meta_decode(void *skbdata, u16 *attrtype, u16 *dlen, u16 *totlen);
+void *ife_tlv_meta_decode(void *skbdata, const void *ifehdr_end, u16 *attrtype,
+			  u16 *dlen, u16 *totlen);
 int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen,
 			const void *dval);
 
diff --git a/net/ife/ife.c b/net/ife/ife.c
index 7d1ec76e7f43..7fbe70a0af4b 100644
--- a/net/ife/ife.c
+++ b/net/ife/ife.c
@@ -92,12 +92,43 @@ struct meta_tlvhdr {
 	__be16 len;
 };
 
+static bool __ife_tlv_meta_valid(const unsigned char *skbdata,
+				 const unsigned char *ifehdr_end)
+{
+	const struct meta_tlvhdr *tlv;
+	u16 tlvlen;
+
+	if (unlikely(skbdata + sizeof(*tlv) > ifehdr_end))
+		return false;
+
+	tlv = (const struct meta_tlvhdr *)skbdata;
+	tlvlen = ntohs(tlv->len);
+
+	/* tlv length field is inc header, check on minimum */
+	if (tlvlen < NLA_HDRLEN)
+		return false;
+
+	/* overflow by NLA_ALIGN check */
+	if (NLA_ALIGN(tlvlen) < tlvlen)
+		return false;
+
+	if (unlikely(skbdata + NLA_ALIGN(tlvlen) > ifehdr_end))
+		return false;
+
+	return true;
+}
+
 /* Caller takes care of presenting data in network order
  */
-void *ife_tlv_meta_decode(void *skbdata, u16 *attrtype, u16 *dlen, u16 *totlen)
+void *ife_tlv_meta_decode(void *skbdata, const void *ifehdr_end, u16 *attrtype,
+			  u16 *dlen, u16 *totlen)
 {
-	struct meta_tlvhdr *tlv = (struct meta_tlvhdr *) skbdata;
+	struct meta_tlvhdr *tlv;
+
+	if (!__ife_tlv_meta_valid(skbdata, ifehdr_end))
+		return NULL;
 
+	tlv = (struct meta_tlvhdr *)skbdata;
 	*dlen = ntohs(tlv->len) - NLA_HDRLEN;
 	*attrtype = ntohs(tlv->type);
 
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 3c046d505e86..1d477b054f2e 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -682,7 +682,12 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a,
 		u16 mtype;
 		u16 dlen;
 
-		curr_data = ife_tlv_meta_decode(tlv_data, &mtype, &dlen, NULL);
+		curr_data = ife_tlv_meta_decode(tlv_data, ifehdr_end, &mtype,
+						&dlen, NULL);
+		if (!curr_data) {
+			qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats));
+			return TC_ACT_SHOT;
+		}
 
 		if (find_decode_metaid(skb, ife, mtype, dlen, curr_data)) {
 			/* abuse overlimits to count when we receive metadata
-- 
2.14.3


From 925118f1943f48d45424a744907a4f8b9a906971 Mon Sep 17 00:00:00 2001
From: Alexander Aring <aring@mojatatu.com>
Date: Fri, 20 Apr 2018 15:15:05 -0400
Subject: [PATCH 33/52] net: sched: ife: check on metadata length

[ Upstream commit d57493d6d1be26c8ac8516a4463bfe24956978eb ]

This patch checks if sk buffer is available to dererence ife header. If
not then NULL will returned to signal an malformed ife packet. This
avoids to crashing the kernel from outside.

Signed-off-by: Alexander Aring <aring@mojatatu.com>
Reviewed-by: Yotam Gigi <yotam.gi@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ife/ife.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ife/ife.c b/net/ife/ife.c
index 7fbe70a0af4b..13bbf8cb6a39 100644
--- a/net/ife/ife.c
+++ b/net/ife/ife.c
@@ -69,6 +69,9 @@ void *ife_decode(struct sk_buff *skb, u16 *metalen)
 	int total_pull;
 	u16 ifehdrln;
 
+	if (!pskb_may_pull(skb, skb->dev->hard_header_len + IFE_METAHDRLEN))
+		return NULL;
+
 	ifehdr = (struct ifeheadr *) (skb->data + skb->dev->hard_header_len);
 	ifehdrln = ntohs(ifehdr->metalen);
 	total_pull = skb->dev->hard_header_len + ifehdrln;
-- 
2.14.3


From d26b2236a8b444c40ca7777fd3f5692a8d171532 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Thu, 12 Apr 2018 20:50:33 +0200
Subject: [PATCH 34/52] l2tp: hold reference on tunnels in netlink dumps

[ Upstream commit 5846c131c39b6d0add36ec19dc8650700690f930 ]

l2tp_tunnel_find_nth() is unsafe: no reference is held on the returned
tunnel, therefore it can be freed whenever the caller uses it.
This patch defines l2tp_tunnel_get_nth() which works similarly, but
also takes a reference on the returned tunnel. The caller then has to
drop it after it stops using the tunnel.

Convert netlink dumps to make them safe against concurrent tunnel
deletion.

Fixes: 309795f4bec2 ("l2tp: Add netlink control API for L2TP")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c    | 20 ++++++++++++++++++++
 net/l2tp/l2tp_core.h    |  2 ++
 net/l2tp/l2tp_netlink.c | 11 ++++++++---
 3 files changed, 30 insertions(+), 3 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 0fbd3ee26165..c8c4183f0f37 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -183,6 +183,26 @@ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id)
 }
 EXPORT_SYMBOL_GPL(l2tp_tunnel_get);
 
+struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth)
+{
+	const struct l2tp_net *pn = l2tp_pernet(net);
+	struct l2tp_tunnel *tunnel;
+	int count = 0;
+
+	rcu_read_lock_bh();
+	list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
+		if (++count > nth) {
+			l2tp_tunnel_inc_refcount(tunnel);
+			rcu_read_unlock_bh();
+			return tunnel;
+		}
+	}
+	rcu_read_unlock_bh();
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(l2tp_tunnel_get_nth);
+
 /* Lookup a session. A new reference is held on the returned session. */
 struct l2tp_session *l2tp_session_get(const struct net *net,
 				      struct l2tp_tunnel *tunnel,
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index ba33cbec71eb..e4896413b2b6 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -212,6 +212,8 @@ static inline void *l2tp_session_priv(struct l2tp_session *session)
 }
 
 struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id);
+struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth);
+
 void l2tp_tunnel_free(struct l2tp_tunnel *tunnel);
 
 struct l2tp_session *l2tp_session_get(const struct net *net,
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index b05dbd9ffcb2..6616c9fd292f 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -487,14 +487,17 @@ static int l2tp_nl_cmd_tunnel_dump(struct sk_buff *skb, struct netlink_callback
 	struct net *net = sock_net(skb->sk);
 
 	for (;;) {
-		tunnel = l2tp_tunnel_find_nth(net, ti);
+		tunnel = l2tp_tunnel_get_nth(net, ti);
 		if (tunnel == NULL)
 			goto out;
 
 		if (l2tp_nl_tunnel_send(skb, NETLINK_CB(cb->skb).portid,
 					cb->nlh->nlmsg_seq, NLM_F_MULTI,
-					tunnel, L2TP_CMD_TUNNEL_GET) < 0)
+					tunnel, L2TP_CMD_TUNNEL_GET) < 0) {
+			l2tp_tunnel_dec_refcount(tunnel);
 			goto out;
+		}
+		l2tp_tunnel_dec_refcount(tunnel);
 
 		ti++;
 	}
@@ -848,7 +851,7 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback
 
 	for (;;) {
 		if (tunnel == NULL) {
-			tunnel = l2tp_tunnel_find_nth(net, ti);
+			tunnel = l2tp_tunnel_get_nth(net, ti);
 			if (tunnel == NULL)
 				goto out;
 		}
@@ -856,6 +859,7 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback
 		session = l2tp_session_get_nth(tunnel, si);
 		if (session == NULL) {
 			ti++;
+			l2tp_tunnel_dec_refcount(tunnel);
 			tunnel = NULL;
 			si = 0;
 			continue;
@@ -865,6 +869,7 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback
 					 cb->nlh->nlmsg_seq, NLM_F_MULTI,
 					 session, L2TP_CMD_SESSION_GET) < 0) {
 			l2tp_session_dec_refcount(session);
+			l2tp_tunnel_dec_refcount(tunnel);
 			break;
 		}
 		l2tp_session_dec_refcount(session);
-- 
2.14.3


From b90bee037091ffa776057d64055e927496918421 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Thu, 12 Apr 2018 20:50:34 +0200
Subject: [PATCH 35/52] l2tp: hold reference on tunnels printed in pppol2tp
 proc file

[ Upstream commit 0e0c3fee3a59a387aeecc4fca6f3a2e9615a5443 ]

Use l2tp_tunnel_get_nth() instead of l2tp_tunnel_find_nth(), to be safe
against concurrent tunnel deletion.

Unlike sessions, we can't drop the reference held on tunnels in
pppol2tp_seq_show(). Tunnels are reused across several calls to
pppol2tp_seq_start() when iterating over sessions. These iterations
need the tunnel for accessing the next session. Therefore the only safe
moment for dropping the reference is just before searching for the next
tunnel.

Normally, the last invocation of pppol2tp_next_tunnel() doesn't find
any new tunnel, so it drops the last tunnel without taking any new
reference. However, in case of error, pppol2tp_seq_stop() is called
directly, so we have to drop the reference there.

Fixes: fd558d186df2 ("l2tp: Split pppol2tp patch into separate l2tp and ppp parts")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ppp.c | 24 +++++++++++++++++-------
 1 file changed, 17 insertions(+), 7 deletions(-)

diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index fc3b8b8fe1c4..2e59f8efb888 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1559,16 +1559,19 @@ struct pppol2tp_seq_data {
 
 static void pppol2tp_next_tunnel(struct net *net, struct pppol2tp_seq_data *pd)
 {
+	/* Drop reference taken during previous invocation */
+	if (pd->tunnel)
+		l2tp_tunnel_dec_refcount(pd->tunnel);
+
 	for (;;) {
-		pd->tunnel = l2tp_tunnel_find_nth(net, pd->tunnel_idx);
+		pd->tunnel = l2tp_tunnel_get_nth(net, pd->tunnel_idx);
 		pd->tunnel_idx++;
 
-		if (pd->tunnel == NULL)
-			break;
+		/* Only accept L2TPv2 tunnels */
+		if (!pd->tunnel || pd->tunnel->version == 2)
+			return;
 
-		/* Ignore L2TPv3 tunnels */
-		if (pd->tunnel->version < 3)
-			break;
+		l2tp_tunnel_dec_refcount(pd->tunnel);
 	}
 }
 
@@ -1617,7 +1620,14 @@ static void *pppol2tp_seq_next(struct seq_file *m, void *v, loff_t *pos)
 
 static void pppol2tp_seq_stop(struct seq_file *p, void *v)
 {
-	/* nothing to do */
+	struct pppol2tp_seq_data *pd = v;
+
+	if (!pd || pd == SEQ_START_TOKEN)
+		return;
+
+	/* Drop reference taken by last invocation of pppol2tp_next_tunnel() */
+	if (pd->tunnel)
+		l2tp_tunnel_dec_refcount(pd->tunnel);
 }
 
 static void pppol2tp_seq_tunnel_show(struct seq_file *m, void *v)
-- 
2.14.3


From fb2b67b40abdd77f3024f1fa728e5651a7a8523a Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Thu, 12 Apr 2018 20:50:35 +0200
Subject: [PATCH 36/52] l2tp: hold reference on tunnels printed in l2tp/tunnels
 debugfs file

[ Upstream commit f726214d9b23e5fce8c11937577a289a3202498f ]

Use l2tp_tunnel_get_nth() instead of l2tp_tunnel_find_nth(), to be safe
against concurrent tunnel deletion.

Use the same mechanism as in l2tp_ppp.c for dropping the reference
taken by l2tp_tunnel_get_nth(). That is, drop the reference just
before looking up the next tunnel. In case of error, drop the last
accessed tunnel in l2tp_dfs_seq_stop().

That was the last use of l2tp_tunnel_find_nth().

Fixes: 0ad6614048cf ("l2tp: Add debugfs files for dumping l2tp debug info")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c    | 20 --------------------
 net/l2tp/l2tp_core.h    |  1 -
 net/l2tp/l2tp_debugfs.c | 15 +++++++++++++--
 3 files changed, 13 insertions(+), 23 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index c8c4183f0f37..40261cb68e83 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -355,26 +355,6 @@ int l2tp_session_register(struct l2tp_session *session,
 }
 EXPORT_SYMBOL_GPL(l2tp_session_register);
 
-struct l2tp_tunnel *l2tp_tunnel_find_nth(const struct net *net, int nth)
-{
-	struct l2tp_net *pn = l2tp_pernet(net);
-	struct l2tp_tunnel *tunnel;
-	int count = 0;
-
-	rcu_read_lock_bh();
-	list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
-		if (++count > nth) {
-			rcu_read_unlock_bh();
-			return tunnel;
-		}
-	}
-
-	rcu_read_unlock_bh();
-
-	return NULL;
-}
-EXPORT_SYMBOL_GPL(l2tp_tunnel_find_nth);
-
 /*****************************************************************************
  * Receive data handling
  *****************************************************************************/
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index e4896413b2b6..c199020f8a8a 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -222,7 +222,6 @@ struct l2tp_session *l2tp_session_get(const struct net *net,
 struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth);
 struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net,
 						const char *ifname);
-struct l2tp_tunnel *l2tp_tunnel_find_nth(const struct net *net, int nth);
 
 int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id,
 		       u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg,
diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c
index 72e713da4733..b8f9d45bfeb1 100644
--- a/net/l2tp/l2tp_debugfs.c
+++ b/net/l2tp/l2tp_debugfs.c
@@ -47,7 +47,11 @@ struct l2tp_dfs_seq_data {
 
 static void l2tp_dfs_next_tunnel(struct l2tp_dfs_seq_data *pd)
 {
-	pd->tunnel = l2tp_tunnel_find_nth(pd->net, pd->tunnel_idx);
+	/* Drop reference taken during previous invocation */
+	if (pd->tunnel)
+		l2tp_tunnel_dec_refcount(pd->tunnel);
+
+	pd->tunnel = l2tp_tunnel_get_nth(pd->net, pd->tunnel_idx);
 	pd->tunnel_idx++;
 }
 
@@ -96,7 +100,14 @@ static void *l2tp_dfs_seq_next(struct seq_file *m, void *v, loff_t *pos)
 
 static void l2tp_dfs_seq_stop(struct seq_file *p, void *v)
 {
-	/* nothing to do */
+	struct l2tp_dfs_seq_data *pd = v;
+
+	if (!pd || pd == SEQ_START_TOKEN)
+		return;
+
+	/* Drop reference taken by last invocation of l2tp_dfs_next_tunnel() */
+	if (pd->tunnel)
+		l2tp_tunnel_dec_refcount(pd->tunnel);
 }
 
 static void l2tp_dfs_seq_tunnel_show(struct seq_file *m, void *v)
-- 
2.14.3


From 4e1547b645a6adddb70c0353a5174c986f7bd149 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Thu, 19 Apr 2018 16:20:48 +0200
Subject: [PATCH 37/52] l2tp: fix {pppol2tp, l2tp_dfs}_seq_stop() in case of
 seq_file overflow

[ Upstream commit 5411b6187adf62909e3b998ac782e722904c7487 ]

Commit 0e0c3fee3a59 ("l2tp: hold reference on tunnels printed in pppol2tp proc file")
assumed that if pppol2tp_seq_stop() was called with non-NULL private
data (the 'v' pointer), then pppol2tp_seq_start() would not be called
again. It turns out that this isn't guaranteed, and overflowing the
seq_file's buffer in pppol2tp_seq_show() is a way to get into this
situation.

Therefore, pppol2tp_seq_stop() needs to reset pd->tunnel, so that
pppol2tp_seq_start() won't drop a reference again if it gets called.
We also have to clear pd->session, because the rest of the code expects
a non-NULL tunnel when pd->session is set.

The l2tp_debugfs module has the same issue. Fix it in the same way.

Fixes: 0e0c3fee3a59 ("l2tp: hold reference on tunnels printed in pppol2tp proc file")
Fixes: f726214d9b23 ("l2tp: hold reference on tunnels printed in l2tp/tunnels debugfs file")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_debugfs.c | 5 ++++-
 net/l2tp/l2tp_ppp.c     | 5 ++++-
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c
index b8f9d45bfeb1..7f1e842ef05a 100644
--- a/net/l2tp/l2tp_debugfs.c
+++ b/net/l2tp/l2tp_debugfs.c
@@ -106,8 +106,11 @@ static void l2tp_dfs_seq_stop(struct seq_file *p, void *v)
 		return;
 
 	/* Drop reference taken by last invocation of l2tp_dfs_next_tunnel() */
-	if (pd->tunnel)
+	if (pd->tunnel) {
 		l2tp_tunnel_dec_refcount(pd->tunnel);
+		pd->tunnel = NULL;
+		pd->session = NULL;
+	}
 }
 
 static void l2tp_dfs_seq_tunnel_show(struct seq_file *m, void *v)
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 2e59f8efb888..0c4530ad74be 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1626,8 +1626,11 @@ static void pppol2tp_seq_stop(struct seq_file *p, void *v)
 		return;
 
 	/* Drop reference taken by last invocation of pppol2tp_next_tunnel() */
-	if (pd->tunnel)
+	if (pd->tunnel) {
 		l2tp_tunnel_dec_refcount(pd->tunnel);
+		pd->tunnel = NULL;
+		pd->session = NULL;
+	}
 }
 
 static void pppol2tp_seq_tunnel_show(struct seq_file *m, void *v)
-- 
2.14.3


From 5b001dc8735fb25423273a45c95d6a0b22cef29c Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Wed, 18 Apr 2018 11:51:56 -0700
Subject: [PATCH 38/52] llc: hold llc_sap before release_sock()

[ Upstream commit f7e43672683b097bb074a8fe7af9bc600a23f231 ]

syzbot reported we still access llc->sap in llc_backlog_rcv()
after it is freed in llc_sap_remove_socket():

Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1b9/0x294 lib/dump_stack.c:113
 print_address_description+0x6c/0x20b mm/kasan/report.c:256
 kasan_report_error mm/kasan/report.c:354 [inline]
 kasan_report.cold.7+0x242/0x2fe mm/kasan/report.c:412
 __asan_report_load1_noabort+0x14/0x20 mm/kasan/report.c:430
 llc_conn_ac_send_sabme_cmd_p_set_x+0x3a8/0x460 net/llc/llc_c_ac.c:785
 llc_exec_conn_trans_actions net/llc/llc_conn.c:475 [inline]
 llc_conn_service net/llc/llc_conn.c:400 [inline]
 llc_conn_state_process+0x4e1/0x13a0 net/llc/llc_conn.c:75
 llc_backlog_rcv+0x195/0x1e0 net/llc/llc_conn.c:891
 sk_backlog_rcv include/net/sock.h:909 [inline]
 __release_sock+0x12f/0x3a0 net/core/sock.c:2335
 release_sock+0xa4/0x2b0 net/core/sock.c:2850
 llc_ui_release+0xc8/0x220 net/llc/af_llc.c:204

llc->sap is refcount'ed and llc_sap_remove_socket() is paired
with llc_sap_add_socket(). This can be amended by holding its refcount
before llc_sap_remove_socket() and releasing it after release_sock().

Reported-by: <syzbot+6e181fc95081c2cf9051@syzkaller.appspotmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/llc/af_llc.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index c38d16f22d2a..c8950d88a695 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -189,6 +189,7 @@ static int llc_ui_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
 	struct llc_sock *llc;
+	struct llc_sap *sap;
 
 	if (unlikely(sk == NULL))
 		goto out;
@@ -199,9 +200,15 @@ static int llc_ui_release(struct socket *sock)
 		llc->laddr.lsap, llc->daddr.lsap);
 	if (!llc_send_disc(sk))
 		llc_ui_wait_for_disc(sk, sk->sk_rcvtimeo);
+	sap = llc->sap;
+	/* Hold this for release_sock(), so that llc_backlog_rcv() could still
+	 * use it.
+	 */
+	llc_sap_hold(sap);
 	if (!sock_flag(sk, SOCK_ZAPPED))
 		llc_sap_remove_socket(llc->sap, sk);
 	release_sock(sk);
+	llc_sap_put(sap);
 	if (llc->dev)
 		dev_put(llc->dev);
 	sock_put(sk);
-- 
2.14.3


From c7bea639e059b6d7b5e9f9811431253f24d3edd7 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 19 Apr 2018 21:54:34 -0700
Subject: [PATCH 39/52] llc: fix NULL pointer deref for SOCK_ZAPPED

[ Upstream commit 3a04ce7130a7e5dad4e78d45d50313747f8c830f ]

For SOCK_ZAPPED socket, we don't need to care about llc->sap,
so we should just skip these refcount functions in this case.

Fixes: f7e43672683b ("llc: hold llc_sap before release_sock()")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/llc/af_llc.c | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index c8950d88a695..cf41d9b4a0b8 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -189,7 +189,6 @@ static int llc_ui_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
 	struct llc_sock *llc;
-	struct llc_sap *sap;
 
 	if (unlikely(sk == NULL))
 		goto out;
@@ -200,15 +199,19 @@ static int llc_ui_release(struct socket *sock)
 		llc->laddr.lsap, llc->daddr.lsap);
 	if (!llc_send_disc(sk))
 		llc_ui_wait_for_disc(sk, sk->sk_rcvtimeo);
-	sap = llc->sap;
-	/* Hold this for release_sock(), so that llc_backlog_rcv() could still
-	 * use it.
-	 */
-	llc_sap_hold(sap);
-	if (!sock_flag(sk, SOCK_ZAPPED))
+	if (!sock_flag(sk, SOCK_ZAPPED)) {
+		struct llc_sap *sap = llc->sap;
+
+		/* Hold this for release_sock(), so that llc_backlog_rcv()
+		 * could still use it.
+		 */
+		llc_sap_hold(sap);
 		llc_sap_remove_socket(llc->sap, sk);
-	release_sock(sk);
-	llc_sap_put(sap);
+		release_sock(sk);
+		llc_sap_put(sap);
+	} else {
+		release_sock(sk);
+	}
 	if (llc->dev)
 		dev_put(llc->dev);
 	sock_put(sk);
-- 
2.14.3


From 2b71302d432060bbf610da9878c738ef9c3d27cb Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Thu, 19 Apr 2018 12:52:06 +0200
Subject: [PATCH 40/52] s390/qeth: fix error handling in adapter command
 callbacks

[ Upstream commit 686c97ee29c886ee07d17987d0059874c5c3b5af ]

Make sure to check both return code fields before(!) processing the
command response. Otherwise we risk operating on invalid data.

This matches an earlier fix for SETASSPARMS commands, see
commit ad3cbf613329 ("s390/qeth: fix error handling in checksum cmd callback").

Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 85 +++++++++++++++++----------------------
 1 file changed, 37 insertions(+), 48 deletions(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 3653bea38470..edeff29271b3 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -3037,28 +3037,23 @@ static int qeth_send_startlan(struct qeth_card *card)
 	return rc;
 }
 
-static int qeth_default_setadapterparms_cb(struct qeth_card *card,
-		struct qeth_reply *reply, unsigned long data)
+static int qeth_setadpparms_inspect_rc(struct qeth_ipa_cmd *cmd)
 {
-	struct qeth_ipa_cmd *cmd;
-
-	QETH_CARD_TEXT(card, 4, "defadpcb");
-
-	cmd = (struct qeth_ipa_cmd *) data;
-	if (cmd->hdr.return_code == 0)
+	if (!cmd->hdr.return_code)
 		cmd->hdr.return_code =
 			cmd->data.setadapterparms.hdr.return_code;
-	return 0;
+	return cmd->hdr.return_code;
 }
 
 static int qeth_query_setadapterparms_cb(struct qeth_card *card,
 		struct qeth_reply *reply, unsigned long data)
 {
-	struct qeth_ipa_cmd *cmd;
+	struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data;
 
 	QETH_CARD_TEXT(card, 3, "quyadpcb");
+	if (qeth_setadpparms_inspect_rc(cmd))
+		return 0;
 
-	cmd = (struct qeth_ipa_cmd *) data;
 	if (cmd->data.setadapterparms.data.query_cmds_supp.lan_type & 0x7f) {
 		card->info.link_type =
 		      cmd->data.setadapterparms.data.query_cmds_supp.lan_type;
@@ -3066,7 +3061,7 @@ static int qeth_query_setadapterparms_cb(struct qeth_card *card,
 	}
 	card->options.adp.supported_funcs =
 		cmd->data.setadapterparms.data.query_cmds_supp.supported_cmds;
-	return qeth_default_setadapterparms_cb(card, reply, (unsigned long)cmd);
+	return 0;
 }
 
 static struct qeth_cmd_buffer *qeth_get_adapter_cmd(struct qeth_card *card,
@@ -3158,22 +3153,20 @@ EXPORT_SYMBOL_GPL(qeth_query_ipassists);
 static int qeth_query_switch_attributes_cb(struct qeth_card *card,
 				struct qeth_reply *reply, unsigned long data)
 {
-	struct qeth_ipa_cmd *cmd;
-	struct qeth_switch_info *sw_info;
+	struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data;
 	struct qeth_query_switch_attributes *attrs;
+	struct qeth_switch_info *sw_info;
 
 	QETH_CARD_TEXT(card, 2, "qswiatcb");
-	cmd = (struct qeth_ipa_cmd *) data;
-	sw_info = (struct qeth_switch_info *)reply->param;
-	if (cmd->data.setadapterparms.hdr.return_code == 0) {
-		attrs = &cmd->data.setadapterparms.data.query_switch_attributes;
-		sw_info->capabilities = attrs->capabilities;
-		sw_info->settings = attrs->settings;
-		QETH_CARD_TEXT_(card, 2, "%04x%04x", sw_info->capabilities,
-							sw_info->settings);
-	}
-	qeth_default_setadapterparms_cb(card, reply, (unsigned long) cmd);
+	if (qeth_setadpparms_inspect_rc(cmd))
+		return 0;
 
+	sw_info = (struct qeth_switch_info *)reply->param;
+	attrs = &cmd->data.setadapterparms.data.query_switch_attributes;
+	sw_info->capabilities = attrs->capabilities;
+	sw_info->settings = attrs->settings;
+	QETH_CARD_TEXT_(card, 2, "%04x%04x", sw_info->capabilities,
+			sw_info->settings);
 	return 0;
 }
 
@@ -4211,16 +4204,13 @@ EXPORT_SYMBOL_GPL(qeth_do_send_packet);
 static int qeth_setadp_promisc_mode_cb(struct qeth_card *card,
 		struct qeth_reply *reply, unsigned long data)
 {
-	struct qeth_ipa_cmd *cmd;
+	struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data;
 	struct qeth_ipacmd_setadpparms *setparms;
 
 	QETH_CARD_TEXT(card, 4, "prmadpcb");
 
-	cmd = (struct qeth_ipa_cmd *) data;
 	setparms = &(cmd->data.setadapterparms);
-
-	qeth_default_setadapterparms_cb(card, reply, (unsigned long)cmd);
-	if (cmd->hdr.return_code) {
+	if (qeth_setadpparms_inspect_rc(cmd)) {
 		QETH_CARD_TEXT_(card, 4, "prmrc%x", cmd->hdr.return_code);
 		setparms->data.mode = SET_PROMISC_MODE_OFF;
 	}
@@ -4290,18 +4280,18 @@ EXPORT_SYMBOL_GPL(qeth_get_stats);
 static int qeth_setadpparms_change_macaddr_cb(struct qeth_card *card,
 		struct qeth_reply *reply, unsigned long data)
 {
-	struct qeth_ipa_cmd *cmd;
+	struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data;
 
 	QETH_CARD_TEXT(card, 4, "chgmaccb");
+	if (qeth_setadpparms_inspect_rc(cmd))
+		return 0;
 
-	cmd = (struct qeth_ipa_cmd *) data;
 	if (!card->options.layer2 ||
 	    !(card->info.mac_bits & QETH_LAYER2_MAC_READ)) {
 		ether_addr_copy(card->dev->dev_addr,
 				cmd->data.setadapterparms.data.change_addr.addr);
 		card->info.mac_bits |= QETH_LAYER2_MAC_READ;
 	}
-	qeth_default_setadapterparms_cb(card, reply, (unsigned long) cmd);
 	return 0;
 }
 
@@ -4332,13 +4322,15 @@ EXPORT_SYMBOL_GPL(qeth_setadpparms_change_macaddr);
 static int qeth_setadpparms_set_access_ctrl_cb(struct qeth_card *card,
 		struct qeth_reply *reply, unsigned long data)
 {
-	struct qeth_ipa_cmd *cmd;
+	struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data;
 	struct qeth_set_access_ctrl *access_ctrl_req;
 	int fallback = *(int *)reply->param;
 
 	QETH_CARD_TEXT(card, 4, "setaccb");
+	if (cmd->hdr.return_code)
+		return 0;
+	qeth_setadpparms_inspect_rc(cmd);
 
-	cmd = (struct qeth_ipa_cmd *) data;
 	access_ctrl_req = &cmd->data.setadapterparms.data.set_access_ctrl;
 	QETH_DBF_TEXT_(SETUP, 2, "setaccb");
 	QETH_DBF_TEXT_(SETUP, 2, "%s", card->gdev->dev.kobj.name);
@@ -4411,7 +4403,6 @@ static int qeth_setadpparms_set_access_ctrl_cb(struct qeth_card *card,
 			card->options.isolation = card->options.prev_isolation;
 		break;
 	}
-	qeth_default_setadapterparms_cb(card, reply, (unsigned long) cmd);
 	return 0;
 }
 
@@ -4699,14 +4690,15 @@ static int qeth_snmp_command(struct qeth_card *card, char __user *udata)
 static int qeth_setadpparms_query_oat_cb(struct qeth_card *card,
 		struct qeth_reply *reply, unsigned long data)
 {
-	struct qeth_ipa_cmd *cmd;
+	struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *)data;
 	struct qeth_qoat_priv *priv;
 	char *resdata;
 	int resdatalen;
 
 	QETH_CARD_TEXT(card, 3, "qoatcb");
+	if (qeth_setadpparms_inspect_rc(cmd))
+		return 0;
 
-	cmd = (struct qeth_ipa_cmd *)data;
 	priv = (struct qeth_qoat_priv *)reply->param;
 	resdatalen = cmd->data.setadapterparms.hdr.cmdlength;
 	resdata = (char *)data + 28;
@@ -4800,21 +4792,18 @@ static int qeth_query_oat_command(struct qeth_card *card, char __user *udata)
 static int qeth_query_card_info_cb(struct qeth_card *card,
 				   struct qeth_reply *reply, unsigned long data)
 {
-	struct qeth_ipa_cmd *cmd;
+	struct carrier_info *carrier_info = (struct carrier_info *)reply->param;
+	struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *)data;
 	struct qeth_query_card_info *card_info;
-	struct carrier_info *carrier_info;
 
 	QETH_CARD_TEXT(card, 2, "qcrdincb");
-	carrier_info = (struct carrier_info *)reply->param;
-	cmd = (struct qeth_ipa_cmd *)data;
-	card_info = &cmd->data.setadapterparms.data.card_info;
-	if (cmd->data.setadapterparms.hdr.return_code == 0) {
-		carrier_info->card_type = card_info->card_type;
-		carrier_info->port_mode = card_info->port_mode;
-		carrier_info->port_speed = card_info->port_speed;
-	}
+	if (qeth_setadpparms_inspect_rc(cmd))
+		return 0;
 
-	qeth_default_setadapterparms_cb(card, reply, (unsigned long) cmd);
+	card_info = &cmd->data.setadapterparms.data.card_info;
+	carrier_info->card_type = card_info->card_type;
+	carrier_info->port_mode = card_info->port_mode;
+	carrier_info->port_speed = card_info->port_speed;
 	return 0;
 }
 
-- 
2.14.3


From cac8e88617d27c99697d478d4879e8992ea4d050 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Date: Thu, 19 Apr 2018 12:52:07 +0200
Subject: [PATCH 41/52] s390/qeth: avoid control IO completion stalls

[ Upstream commit 901e3f49facbd31b2b3d1786637b4a35e1022e9b ]

For control IO, qeth currently tracks the index of the buffer that it
expects to complete the next IO on each qeth_channel. If the channel
presents an IRQ while this buffer has not yet completed, no completion
processing for _any_ completed buffer takes place.
So if the 'next buffer' is skipped for any sort of reason* (eg. when it
is released due to error conditions, before the IO is started), the
buffer obviously won't switch to PROCESSED until it is eventually
allocated for a _different_ IO and completes.
Until this happens, all completion processing on that channel stalls
and pending requests possibly time out.

As a fix, remove the whole 'next buffer' logic and simply process any
IO buffer right when it completes. A channel will never have more than
one IO pending, so there's no risk of processing out-of-sequence.

*Note: currently just one location in the code really handles this problem,
       by advancing the 'next' index manually.

Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core.h      |  2 --
 drivers/s390/net/qeth_core_main.c | 22 +++++-----------------
 2 files changed, 5 insertions(+), 19 deletions(-)

diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 959c65cf75d9..e338ce823c44 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -565,7 +565,6 @@ enum qeth_ip_types {
 enum qeth_cmd_buffer_state {
 	BUF_STATE_FREE,
 	BUF_STATE_LOCKED,
-	BUF_STATE_PROCESSED,
 };
 
 enum qeth_cq {
@@ -609,7 +608,6 @@ struct qeth_channel {
 	struct qeth_cmd_buffer iob[QETH_CMD_BUFFER_NO];
 	atomic_t irq_pending;
 	int io_buf_no;
-	int buf_no;
 };
 
 /**
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index edeff29271b3..a5953635a998 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -821,7 +821,6 @@ void qeth_clear_cmd_buffers(struct qeth_channel *channel)
 
 	for (cnt = 0; cnt < QETH_CMD_BUFFER_NO; cnt++)
 		qeth_release_buffer(channel, &channel->iob[cnt]);
-	channel->buf_no = 0;
 	channel->io_buf_no = 0;
 }
 EXPORT_SYMBOL_GPL(qeth_clear_cmd_buffers);
@@ -927,7 +926,6 @@ static int qeth_setup_channel(struct qeth_channel *channel)
 			kfree(channel->iob[cnt].data);
 		return -ENOMEM;
 	}
-	channel->buf_no = 0;
 	channel->io_buf_no = 0;
 	atomic_set(&channel->irq_pending, 0);
 	spin_lock_init(&channel->iob_lock);
@@ -1103,11 +1101,9 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm,
 {
 	int rc;
 	int cstat, dstat;
-	struct qeth_cmd_buffer *buffer;
 	struct qeth_channel *channel;
 	struct qeth_card *card;
 	struct qeth_cmd_buffer *iob;
-	__u8 index;
 
 	if (__qeth_check_irb_error(cdev, intparm, irb))
 		return;
@@ -1185,25 +1181,18 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm,
 		channel->state = CH_STATE_RCD_DONE;
 		goto out;
 	}
-	if (intparm) {
-		buffer = (struct qeth_cmd_buffer *) __va((addr_t)intparm);
-		buffer->state = BUF_STATE_PROCESSED;
-	}
 	if (channel == &card->data)
 		return;
 	if (channel == &card->read &&
 	    channel->state == CH_STATE_UP)
 		__qeth_issue_next_read(card);
 
-	iob = channel->iob;
-	index = channel->buf_no;
-	while (iob[index].state == BUF_STATE_PROCESSED) {
-		if (iob[index].callback != NULL)
-			iob[index].callback(channel, iob + index);
-
-		index = (index + 1) % QETH_CMD_BUFFER_NO;
+	if (intparm) {
+		iob = (struct qeth_cmd_buffer *) __va((addr_t)intparm);
+		if (iob->callback)
+			iob->callback(iob->channel, iob);
 	}
-	channel->buf_no = index;
+
 out:
 	wake_up(&card->wait_q);
 	return;
@@ -2217,7 +2206,6 @@ int qeth_send_control_data(struct qeth_card *card, int len,
 error:
 	atomic_set(&card->write.irq_pending, 0);
 	qeth_release_buffer(iob->channel, iob);
-	card->write.buf_no = (card->write.buf_no + 1) % QETH_CMD_BUFFER_NO;
 	rc = reply->rc;
 	qeth_put_reply(reply);
 	return rc;
-- 
2.14.3


From 6b61fd202cbb0f0968f7726f242396d9d9169f4e Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Thu, 19 Apr 2018 12:52:08 +0200
Subject: [PATCH 42/52] s390/qeth: handle failure on workqueue creation

[ Upstream commit a936b1ef37ce1e996533878f4b23944f9444dcdf ]

Creating the global workqueue during driver init may fail, deal with it.
Also, destroy the created workqueue on any subsequent error.

Fixes: 0f54761d167f ("qeth: Support VEPA mode")
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index a5953635a998..c11a083cd956 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -6544,10 +6544,14 @@ static int __init qeth_core_init(void)
 	mutex_init(&qeth_mod_mutex);
 
 	qeth_wq = create_singlethread_workqueue("qeth_wq");
+	if (!qeth_wq) {
+		rc = -ENOMEM;
+		goto out_err;
+	}
 
 	rc = qeth_register_dbf_views();
 	if (rc)
-		goto out_err;
+		goto dbf_err;
 	qeth_core_root_dev = root_device_register("qeth");
 	rc = PTR_ERR_OR_ZERO(qeth_core_root_dev);
 	if (rc)
@@ -6584,6 +6588,8 @@ static int __init qeth_core_init(void)
 	root_device_unregister(qeth_core_root_dev);
 register_err:
 	qeth_unregister_dbf_views();
+dbf_err:
+	destroy_workqueue(qeth_wq);
 out_err:
 	pr_err("Initializing the qeth device driver failed\n");
 	return rc;
-- 
2.14.3


From 1fd9acf660da7141b45c117e56abe0426ee701b8 Mon Sep 17 00:00:00 2001
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Thu, 19 Apr 2018 22:49:09 +0300
Subject: [PATCH 43/52] net: ethernet: ti: cpsw: fix tx vlan priority mapping

[ Upstream commit 5e391dc5a8d801a2410d0032ad4a428d1d61800c ]

The CPDMA_TX_PRIORITY_MAP in real is vlan pcp field priority mapping
register and basically replaces vlan pcp field for tagged packets.
So, set it to be 1:1 mapping. Otherwise, it will cause unexpected
change of egress vlan tagged packets, like prio 2 -> prio 5.

Fixes: e05107e6b747 ("net: ethernet: ti: cpsw: add multi queue support")
Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index b2b30c9df037..33c35b2df7d5 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -125,7 +125,7 @@ do {								\
 
 #define RX_PRIORITY_MAPPING	0x76543210
 #define TX_PRIORITY_MAPPING	0x33221100
-#define CPDMA_TX_PRIORITY_MAP	0x01234567
+#define CPDMA_TX_PRIORITY_MAP	0x76543210
 
 #define CPSW_VLAN_AWARE		BIT(1)
 #define CPSW_ALE_VLAN_AWARE	1
-- 
2.14.3


From ae3806d902d2d1237a521589ade26511fe88447b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 11 Apr 2018 14:46:00 -0700
Subject: [PATCH 44/52] net: validate attribute sizes in neigh_dump_table()

[ Upstream commit 7dd07c143a4b54d050e748bee4b4b9e94a7b1744 ]

Since neigh_dump_table() calls nlmsg_parse() without giving policy
constraints, attributes can have arbirary size that we must validate

Reported by syzbot/KMSAN :

BUG: KMSAN: uninit-value in neigh_master_filtered net/core/neighbour.c:2292 [inline]
BUG: KMSAN: uninit-value in neigh_dump_table net/core/neighbour.c:2348 [inline]
BUG: KMSAN: uninit-value in neigh_dump_info+0x1af0/0x2250 net/core/neighbour.c:2438
CPU: 1 PID: 3575 Comm: syzkaller268891 Not tainted 4.16.0+ #83
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x185/0x1d0 lib/dump_stack.c:53
 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067
 __msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:676
 neigh_master_filtered net/core/neighbour.c:2292 [inline]
 neigh_dump_table net/core/neighbour.c:2348 [inline]
 neigh_dump_info+0x1af0/0x2250 net/core/neighbour.c:2438
 netlink_dump+0x9ad/0x1540 net/netlink/af_netlink.c:2225
 __netlink_dump_start+0x1167/0x12a0 net/netlink/af_netlink.c:2322
 netlink_dump_start include/linux/netlink.h:214 [inline]
 rtnetlink_rcv_msg+0x1435/0x1560 net/core/rtnetlink.c:4598
 netlink_rcv_skb+0x355/0x5f0 net/netlink/af_netlink.c:2447
 rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:4653
 netlink_unicast_kernel net/netlink/af_netlink.c:1311 [inline]
 netlink_unicast+0x1672/0x1750 net/netlink/af_netlink.c:1337
 netlink_sendmsg+0x1048/0x1310 net/netlink/af_netlink.c:1900
 sock_sendmsg_nosec net/socket.c:630 [inline]
 sock_sendmsg net/socket.c:640 [inline]
 ___sys_sendmsg+0xec0/0x1310 net/socket.c:2046
 __sys_sendmsg net/socket.c:2080 [inline]
 SYSC_sendmsg+0x2a3/0x3d0 net/socket.c:2091
 SyS_sendmsg+0x54/0x80 net/socket.c:2087
 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x3d/0xa2
RIP: 0033:0x43fed9
RSP: 002b:00007ffddbee2798 EFLAGS: 00000213 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 000000000043fed9
RDX: 0000000000000000 RSI: 0000000020005000 RDI: 0000000000000003
RBP: 00000000006ca018 R08: 00000000004002c8 R09: 00000000004002c8
R10: 00000000004002c8 R11: 0000000000000213 R12: 0000000000401800
R13: 0000000000401890 R14: 0000000000000000 R15: 0000000000000000

Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:278 [inline]
 kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:188
 kmsan_kmalloc+0x94/0x100 mm/kmsan/kmsan.c:314
 kmsan_slab_alloc+0x11/0x20 mm/kmsan/kmsan.c:321
 slab_post_alloc_hook mm/slab.h:445 [inline]
 slab_alloc_node mm/slub.c:2737 [inline]
 __kmalloc_node_track_caller+0xaed/0x11c0 mm/slub.c:4369
 __kmalloc_reserve net/core/skbuff.c:138 [inline]
 __alloc_skb+0x2cf/0x9f0 net/core/skbuff.c:206
 alloc_skb include/linux/skbuff.h:984 [inline]
 netlink_alloc_large_skb net/netlink/af_netlink.c:1183 [inline]
 netlink_sendmsg+0x9a6/0x1310 net/netlink/af_netlink.c:1875
 sock_sendmsg_nosec net/socket.c:630 [inline]
 sock_sendmsg net/socket.c:640 [inline]
 ___sys_sendmsg+0xec0/0x1310 net/socket.c:2046
 __sys_sendmsg net/socket.c:2080 [inline]
 SYSC_sendmsg+0x2a3/0x3d0 net/socket.c:2091
 SyS_sendmsg+0x54/0x80 net/socket.c:2087
 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x3d/0xa2

Fixes: 21fdd092acc7 ("net: Add support for filtering neigh dump by master device")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: David Ahern <dsa@cumulusnetworks.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index e22d2aefbd78..ce519861be59 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2331,12 +2331,16 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
 
 	err = nlmsg_parse(nlh, sizeof(struct ndmsg), tb, NDA_MAX, NULL, NULL);
 	if (!err) {
-		if (tb[NDA_IFINDEX])
+		if (tb[NDA_IFINDEX]) {
+			if (nla_len(tb[NDA_IFINDEX]) != sizeof(u32))
+				return -EINVAL;
 			filter_idx = nla_get_u32(tb[NDA_IFINDEX]);
-
-		if (tb[NDA_MASTER])
+		}
+		if (tb[NDA_MASTER]) {
+			if (nla_len(tb[NDA_MASTER]) != sizeof(u32))
+				return -EINVAL;
 			filter_master_idx = nla_get_u32(tb[NDA_MASTER]);
-
+		}
 		if (filter_idx || filter_master_idx)
 			flags |= NLM_F_DUMP_FILTERED;
 	}
-- 
2.14.3


From 72fa6ac4402ee994a21ad60f27f95588868cc2f3 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Thu, 19 Apr 2018 03:16:16 -0400
Subject: [PATCH 45/52] bnxt_en: Fix memory fault in bnxt_ethtool_init()

[ Upstream commit a60faa60da891e311e19fd3e88d611863f431130 ]

In some firmware images, the length of BNX_DIR_TYPE_PKG_LOG nvram type
could be greater than the fixed buffer length of 4096 bytes allocated by
the driver.  This was causing HWRM_NVM_READ to copy more data to the buffer
than the allocated size, causing general protection fault.

Fix the issue by allocating the exact buffer length returned by
HWRM_NVM_FIND_DIR_ENTRY, instead of 4096.  Move the kzalloc() call
into the bnxt_get_pkgver() function.

Fixes: 3ebf6f0a09a2 ("bnxt_en: Add installed-package firmware version reporting via Ethtool GDRVINFO")
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c  | 49 ++++++++++++----------
 drivers/net/ethernet/broadcom/bnxt/bnxt_nvm_defs.h |  2 -
 2 files changed, 27 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 1801582076be..9442605f4fd4 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -1874,22 +1874,39 @@ static char *bnxt_parse_pkglog(int desired_field, u8 *data, size_t datalen)
 	return retval;
 }
 
-static char *bnxt_get_pkgver(struct net_device *dev, char *buf, size_t buflen)
+static void bnxt_get_pkgver(struct net_device *dev)
 {
+	struct bnxt *bp = netdev_priv(dev);
 	u16 index = 0;
-	u32 datalen;
+	char *pkgver;
+	u32 pkglen;
+	u8 *pkgbuf;
+	int len;
 
 	if (bnxt_find_nvram_item(dev, BNX_DIR_TYPE_PKG_LOG,
 				 BNX_DIR_ORDINAL_FIRST, BNX_DIR_EXT_NONE,
-				 &index, NULL, &datalen) != 0)
-		return NULL;
+				 &index, NULL, &pkglen) != 0)
+		return;
 
-	memset(buf, 0, buflen);
-	if (bnxt_get_nvram_item(dev, index, 0, datalen, buf) != 0)
-		return NULL;
+	pkgbuf = kzalloc(pkglen, GFP_KERNEL);
+	if (!pkgbuf) {
+		dev_err(&bp->pdev->dev, "Unable to allocate memory for pkg version, length = %u\n",
+			pkglen);
+		return;
+	}
+
+	if (bnxt_get_nvram_item(dev, index, 0, pkglen, pkgbuf))
+		goto err;
 
-	return bnxt_parse_pkglog(BNX_PKG_LOG_FIELD_IDX_PKG_VERSION, buf,
-		datalen);
+	pkgver = bnxt_parse_pkglog(BNX_PKG_LOG_FIELD_IDX_PKG_VERSION, pkgbuf,
+				   pkglen);
+	if (pkgver && *pkgver != 0 && isdigit(*pkgver)) {
+		len = strlen(bp->fw_ver_str);
+		snprintf(bp->fw_ver_str + len, FW_VER_STR_LEN - len - 1,
+			 "/pkg %s", pkgver);
+	}
+err:
+	kfree(pkgbuf);
 }
 
 static int bnxt_get_eeprom(struct net_device *dev,
@@ -2558,22 +2575,10 @@ void bnxt_ethtool_init(struct bnxt *bp)
 	struct hwrm_selftest_qlist_input req = {0};
 	struct bnxt_test_info *test_info;
 	struct net_device *dev = bp->dev;
-	char *pkglog;
 	int i, rc;
 
-	pkglog = kzalloc(BNX_PKG_LOG_MAX_LENGTH, GFP_KERNEL);
-	if (pkglog) {
-		char *pkgver;
-		int len;
+	bnxt_get_pkgver(dev);
 
-		pkgver = bnxt_get_pkgver(dev, pkglog, BNX_PKG_LOG_MAX_LENGTH);
-		if (pkgver && *pkgver != 0 && isdigit(*pkgver)) {
-			len = strlen(bp->fw_ver_str);
-			snprintf(bp->fw_ver_str + len, FW_VER_STR_LEN - len - 1,
-				 "/pkg %s", pkgver);
-		}
-		kfree(pkglog);
-	}
 	if (bp->hwrm_spec_code < 0x10704 || !BNXT_SINGLE_PF(bp))
 		return;
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_nvm_defs.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_nvm_defs.h
index 73f2249555b5..83444811d3c6 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_nvm_defs.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_nvm_defs.h
@@ -59,8 +59,6 @@ enum bnxt_nvm_directory_type {
 #define BNX_DIR_ATTR_NO_CHKSUM			(1 << 0)
 #define BNX_DIR_ATTR_PROP_STREAM		(1 << 1)
 
-#define BNX_PKG_LOG_MAX_LENGTH			4096
-
 enum bnxnvm_pkglog_field_index {
 	BNX_PKG_LOG_FIELD_IDX_INSTALLED_TIMESTAMP	= 0,
 	BNX_PKG_LOG_FIELD_IDX_PKG_DESCRIPTION		= 1,
-- 
2.14.3


From 90b6aae662d735d10a2234ef3b7210855d1dcde8 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Fri, 13 Apr 2018 14:58:25 +0800
Subject: [PATCH 46/52] virtio-net: add missing virtqueue kick when flushing
 packets

[ Upstream commit 9267c430c6b6f4c0120e3c6bb847313d633f02a6 ]

We tends to batch submitting packets during XDP_TX. This requires to
kick virtqueue after a batch, we tried to do it through
xdp_do_flush_map() which only makes sense for devmap not XDP_TX. So
explicitly kick the virtqueue in this case.

Reported-by: Kimitoshi Takahashi <ktaka@nii.ac.jp>
Tested-by: Kimitoshi Takahashi <ktaka@nii.ac.jp>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Fixes: 186b3c998c50 ("virtio-net: support XDP_REDIRECT")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 23374603e4d9..d8e1aeab4341 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1269,7 +1269,9 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
 {
 	struct receive_queue *rq =
 		container_of(napi, struct receive_queue, napi);
-	unsigned int received;
+	struct virtnet_info *vi = rq->vq->vdev->priv;
+	struct send_queue *sq;
+	unsigned int received, qp;
 	bool xdp_xmit = false;
 
 	virtnet_poll_cleantx(rq);
@@ -1280,8 +1282,13 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
 	if (received < budget)
 		virtqueue_napi_complete(napi, rq->vq, received);
 
-	if (xdp_xmit)
+	if (xdp_xmit) {
+		qp = vi->curr_queue_pairs - vi->xdp_queue_pairs +
+		     smp_processor_id();
+		sq = &vi->sq[qp];
+		virtqueue_kick(sq->vq);
 		xdp_do_flush_map();
+	}
 
 	return received;
 }
-- 
2.14.3


From 3568805fd83b56e9c459af3a589c80a007edc5a0 Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Tue, 17 Apr 2018 14:25:58 +0800
Subject: [PATCH 47/52] VSOCK: make af_vsock.ko removable again

[ Upstream commit 05e489b1596f0aa1025a1fa572676631cd9665da ]

Commit c1eef220c1760762753b602c382127bfccee226d ("vsock: always call
vsock_init_tables()") introduced a module_init() function without a
corresponding module_exit() function.

Modules with an init function can only be removed if they also have an
exit function.  Therefore the vsock module was considered "permanent"
and could not be removed.

This patch adds an empty module_exit() function so that "rmmod vsock"
works.  No explicit cleanup is required because:

1. Transports call vsock_core_exit() upon exit and cannot be removed
   while sockets are still alive.
2. vsock_diag.ko does not perform any action that requires cleanup by
   vsock.ko.

Fixes: c1eef220c176 ("vsock: always call vsock_init_tables()")
Reported-by: Xiumei Mu <xmu@redhat.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Jorgen Hansen <jhansen@vmware.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Jorgen Hansen <jhansen@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/vmw_vsock/af_vsock.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index e0fc84daed94..ad17a985f74e 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -2018,7 +2018,13 @@ const struct vsock_transport *vsock_core_get_transport(void)
 }
 EXPORT_SYMBOL_GPL(vsock_core_get_transport);
 
+static void __exit vsock_exit(void)
+{
+	/* Do nothing.  This function makes this module removable. */
+}
+
 module_init(vsock_init_tables);
+module_exit(vsock_exit);
 
 MODULE_AUTHOR("VMware, Inc.");
 MODULE_DESCRIPTION("VMware Virtual Socket Family");
-- 
2.14.3


From 6bfeaae3815960639511ea826da27a7303705d52 Mon Sep 17 00:00:00 2001
From: Igor Russkikh <igor.russkikh@aquantia.com>
Date: Wed, 11 Apr 2018 15:23:24 +0300
Subject: [PATCH 48/52] net: aquantia: Regression on reset with 1.x firmware

[ Upstream commit cce96d1883dae4b79f44890e5118243d806da286 ]

On ASUS XG-C100C with 1.5.44 firmware a special mode called "dirty wake"
is active. With this mode when motherboard gets powered (but no poweron
happens yet), NIC automatically enables powersave link and watches
for WOL packet.
This normally allows to powerup the PC after AC power failures.

Not all motherboards or bios settings gives power to PCI slots,
so this mode is not enabled on all the hardware.

4.16 linux driver introduced full hardware reset sequence
This is required since before that we had no NIC hardware
reset implemented and there were side effects of "not clean start".

But this full reset is incompatible with "dirty wake" WOL feature
it keeps the PHY link in a special mode forever. As a consequence,
driver sees no link and no traffic.

To fix this we forcibly change FW state to idle state before doing
the full reset. This makes FW to restore link state.

Fixes: c8c82eb net: aquantia: Introduce global AQC hardware reset sequence
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
index d3b847ec7465..c58b2c227260 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
@@ -48,6 +48,8 @@
 #define FORCE_FLASHLESS 0
 
 static int hw_atl_utils_ver_match(u32 ver_expected, u32 ver_actual);
+static int hw_atl_utils_mpi_set_state(struct aq_hw_s *self,
+				      enum hal_atl_utils_fw_state_e state);
 
 int hw_atl_utils_initfw(struct aq_hw_s *self, const struct aq_fw_ops **fw_ops)
 {
@@ -247,6 +249,20 @@ int hw_atl_utils_soft_reset(struct aq_hw_s *self)
 
 	self->rbl_enabled = (boot_exit_code != 0);
 
+	/* FW 1.x may bootup in an invalid POWER state (WOL feature).
+	 * We should work around this by forcing its state back to DEINIT
+	 */
+	if (!hw_atl_utils_ver_match(HW_ATL_FW_VER_1X,
+				    aq_hw_read_reg(self,
+						   HW_ATL_MPI_FW_VERSION))) {
+		int err = 0;
+
+		hw_atl_utils_mpi_set_state(self, MPI_DEINIT);
+		AQ_HW_WAIT_FOR((aq_hw_read_reg(self, HW_ATL_MPI_STATE_ADR) &
+			       HW_ATL_MPI_STATE_MSK) == MPI_DEINIT,
+			       10, 1000U);
+	}
+
 	if (self->rbl_enabled)
 		return hw_atl_utils_soft_reset_rbl(self);
 	else
-- 
2.14.3


From bda6d4336167a70055dd4772d682b0b85eae7e6a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Tue, 17 Apr 2018 22:46:38 +0200
Subject: [PATCH 49/52] tun: fix vlan packet truncation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 81c895072d29cd70eea5be1a8587cd6461c3715a ]

Bogus trimming in tun_net_xmit() causes truncated vlan packets.

skb->len is correct whether or not skb_vlan_tag_present() is true. There
is no more reason to adjust the skb length on xmit in this driver than
any other driver. tun_put_user() adds 4 bytes to the total for tagged
packets because it transmits the tag inline to userspace.  This is
similar to a nic transmitting the tag inline on the wire.

Reproducing the bug by sending any tagged packet through back-to-back
connected tap interfaces:

 socat TUN,tun-type=tap,iff-up,tun-name=in TUN,tun-type=tap,iff-up,tun-name=out &
 ip link add link in name in.20 type vlan id 20
 ip addr add 10.9.9.9/24 dev in.20
 ip link set in.20 up
 tshark -nxxi in -f arp -c1 2>/dev/null &
 tshark -nxxi out -f arp -c1 2>/dev/null &
 ping -c 1 10.9.9.5 >/dev/null 2>&1

The output from the 'in' and 'out' interfaces are different when the
bug is present:

 Capturing on 'in'
 0000  ff ff ff ff ff ff 76 cf 76 37 d5 0a 81 00 00 14   ......v.v7......
 0010  08 06 00 01 08 00 06 04 00 01 76 cf 76 37 d5 0a   ..........v.v7..
 0020  0a 09 09 09 00 00 00 00 00 00 0a 09 09 05         ..............

 Capturing on 'out'
 0000  ff ff ff ff ff ff 76 cf 76 37 d5 0a 81 00 00 14   ......v.v7......
 0010  08 06 00 01 08 00 06 04 00 01 76 cf 76 37 d5 0a   ..........v.v7..
 0020  0a 09 09 09 00 00 00 00 00 00                     ..........

Fixes: aff3d70a07ff ("tun: allow to attach ebpf socket filter")
Cc: Jason Wang <jasowang@redhat.com>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 28cfa642e39a..6c7bdd0c361a 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1094,12 +1094,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 		goto drop;
 
 	len = run_ebpf_filter(tun, skb, len);
-
-	/* Trim extra bytes since we may insert vlan proto & TCI
-	 * in tun_put_user().
-	 */
-	len -= skb_vlan_tag_present(skb) ? sizeof(struct veth) : 0;
-	if (len <= 0 || pskb_trim(skb, len))
+	if (len == 0 || pskb_trim(skb, len))
 		goto drop;
 
 	if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC)))
-- 
2.14.3


From 2255c814cccdf75349c4e63fa8131127521a70f9 Mon Sep 17 00:00:00 2001
From: Igor Russkikh <igor.russkikh@aquantia.com>
Date: Wed, 11 Apr 2018 15:23:25 +0300
Subject: [PATCH 50/52] net: aquantia: oops when shutdown on already stopped
 device

[ Upstream commit 9a11aff25fd43d5bd2660ababdc9f564b0ba183a ]

In case netdev is closed at the moment of pci shutdown, aq_nic_stop
gets called second time. napi_disable in that case hangs indefinitely.
In other case, if device was never opened at all, we get oops because
of null pointer access.

We should invoke aq_nic_stop conditionally, only if device is running
at the moment of shutdown.

Reported-by: David Arcari <darcari@redhat.com>
Fixes: 90869ddfefeb ("net: aquantia: Implement pci shutdown callback")
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/aq_nic.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index c96a92118b8b..32f6d2e24d66 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -951,9 +951,11 @@ void aq_nic_shutdown(struct aq_nic_s *self)
 
 	netif_device_detach(self->ndev);
 
-	err = aq_nic_stop(self);
-	if (err < 0)
-		goto err_exit;
+	if (netif_running(self->ndev)) {
+		err = aq_nic_stop(self);
+		if (err < 0)
+			goto err_exit;
+	}
 	aq_nic_deinit(self);
 
 err_exit:
-- 
2.14.3


From e18daf5cca8b97e6a766e7b4bf64e1edf60cdc87 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Thu, 19 Apr 2018 08:30:48 +0300
Subject: [PATCH 51/52] virtio_net: split out ctrl buffer

[ Upstream commit 12e571693837d6164bda61e316b1944972ee0d97 ]

When sending control commands, virtio net sets up several buffers for
DMA. The buffers are all part of the net device which means it's
actually allocated by kvmalloc so it's in theory (on extreme memory
pressure) possible to get a vmalloc'ed buffer which on some platforms
means we can't DMA there.

Fix up by moving the DMA buffers into a separate structure.

Reported-by: Mikulas Patocka <mpatocka@redhat.com>
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 68 +++++++++++++++++++++++++++---------------------
 1 file changed, 39 insertions(+), 29 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index d8e1aeab4341..2e7e187117b5 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -147,6 +147,17 @@ struct receive_queue {
 	struct xdp_rxq_info xdp_rxq;
 };
 
+/* Control VQ buffers: protected by the rtnl lock */
+struct control_buf {
+	struct virtio_net_ctrl_hdr hdr;
+	virtio_net_ctrl_ack status;
+	struct virtio_net_ctrl_mq mq;
+	u8 promisc;
+	u8 allmulti;
+	u16 vid;
+	u64 offloads;
+};
+
 struct virtnet_info {
 	struct virtio_device *vdev;
 	struct virtqueue *cvq;
@@ -192,14 +203,7 @@ struct virtnet_info {
 	struct hlist_node node;
 	struct hlist_node node_dead;
 
-	/* Control VQ buffers: protected by the rtnl lock */
-	struct virtio_net_ctrl_hdr ctrl_hdr;
-	virtio_net_ctrl_ack ctrl_status;
-	struct virtio_net_ctrl_mq ctrl_mq;
-	u8 ctrl_promisc;
-	u8 ctrl_allmulti;
-	u16 ctrl_vid;
-	u64 ctrl_offloads;
+	struct control_buf *ctrl;
 
 	/* Ethtool settings */
 	u8 duplex;
@@ -1461,25 +1465,25 @@ static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd,
 	/* Caller should know better */
 	BUG_ON(!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ));
 
-	vi->ctrl_status = ~0;
-	vi->ctrl_hdr.class = class;
-	vi->ctrl_hdr.cmd = cmd;
+	vi->ctrl->status = ~0;
+	vi->ctrl->hdr.class = class;
+	vi->ctrl->hdr.cmd = cmd;
 	/* Add header */
-	sg_init_one(&hdr, &vi->ctrl_hdr, sizeof(vi->ctrl_hdr));
+	sg_init_one(&hdr, &vi->ctrl->hdr, sizeof(vi->ctrl->hdr));
 	sgs[out_num++] = &hdr;
 
 	if (out)
 		sgs[out_num++] = out;
 
 	/* Add return status. */
-	sg_init_one(&stat, &vi->ctrl_status, sizeof(vi->ctrl_status));
+	sg_init_one(&stat, &vi->ctrl->status, sizeof(vi->ctrl->status));
 	sgs[out_num] = &stat;
 
 	BUG_ON(out_num + 1 > ARRAY_SIZE(sgs));
 	virtqueue_add_sgs(vi->cvq, sgs, out_num, 1, vi, GFP_ATOMIC);
 
 	if (unlikely(!virtqueue_kick(vi->cvq)))
-		return vi->ctrl_status == VIRTIO_NET_OK;
+		return vi->ctrl->status == VIRTIO_NET_OK;
 
 	/* Spin for a response, the kick causes an ioport write, trapping
 	 * into the hypervisor, so the request should be handled immediately.
@@ -1488,7 +1492,7 @@ static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd,
 	       !virtqueue_is_broken(vi->cvq))
 		cpu_relax();
 
-	return vi->ctrl_status == VIRTIO_NET_OK;
+	return vi->ctrl->status == VIRTIO_NET_OK;
 }
 
 static int virtnet_set_mac_address(struct net_device *dev, void *p)
@@ -1600,8 +1604,8 @@ static int _virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs)
 	if (!vi->has_cvq || !virtio_has_feature(vi->vdev, VIRTIO_NET_F_MQ))
 		return 0;
 
-	vi->ctrl_mq.virtqueue_pairs = cpu_to_virtio16(vi->vdev, queue_pairs);
-	sg_init_one(&sg, &vi->ctrl_mq, sizeof(vi->ctrl_mq));
+	vi->ctrl->mq.virtqueue_pairs = cpu_to_virtio16(vi->vdev, queue_pairs);
+	sg_init_one(&sg, &vi->ctrl->mq, sizeof(vi->ctrl->mq));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MQ,
 				  VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET, &sg)) {
@@ -1660,22 +1664,22 @@ static void virtnet_set_rx_mode(struct net_device *dev)
 	if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_RX))
 		return;
 
-	vi->ctrl_promisc = ((dev->flags & IFF_PROMISC) != 0);
-	vi->ctrl_allmulti = ((dev->flags & IFF_ALLMULTI) != 0);
+	vi->ctrl->promisc = ((dev->flags & IFF_PROMISC) != 0);
+	vi->ctrl->allmulti = ((dev->flags & IFF_ALLMULTI) != 0);
 
-	sg_init_one(sg, &vi->ctrl_promisc, sizeof(vi->ctrl_promisc));
+	sg_init_one(sg, &vi->ctrl->promisc, sizeof(vi->ctrl->promisc));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX,
 				  VIRTIO_NET_CTRL_RX_PROMISC, sg))
 		dev_warn(&dev->dev, "Failed to %sable promisc mode.\n",
-			 vi->ctrl_promisc ? "en" : "dis");
+			 vi->ctrl->promisc ? "en" : "dis");
 
-	sg_init_one(sg, &vi->ctrl_allmulti, sizeof(vi->ctrl_allmulti));
+	sg_init_one(sg, &vi->ctrl->allmulti, sizeof(vi->ctrl->allmulti));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX,
 				  VIRTIO_NET_CTRL_RX_ALLMULTI, sg))
 		dev_warn(&dev->dev, "Failed to %sable allmulti mode.\n",
-			 vi->ctrl_allmulti ? "en" : "dis");
+			 vi->ctrl->allmulti ? "en" : "dis");
 
 	uc_count = netdev_uc_count(dev);
 	mc_count = netdev_mc_count(dev);
@@ -1721,8 +1725,8 @@ static int virtnet_vlan_rx_add_vid(struct net_device *dev,
 	struct virtnet_info *vi = netdev_priv(dev);
 	struct scatterlist sg;
 
-	vi->ctrl_vid = vid;
-	sg_init_one(&sg, &vi->ctrl_vid, sizeof(vi->ctrl_vid));
+	vi->ctrl->vid = vid;
+	sg_init_one(&sg, &vi->ctrl->vid, sizeof(vi->ctrl->vid));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN,
 				  VIRTIO_NET_CTRL_VLAN_ADD, &sg))
@@ -1736,8 +1740,8 @@ static int virtnet_vlan_rx_kill_vid(struct net_device *dev,
 	struct virtnet_info *vi = netdev_priv(dev);
 	struct scatterlist sg;
 
-	vi->ctrl_vid = vid;
-	sg_init_one(&sg, &vi->ctrl_vid, sizeof(vi->ctrl_vid));
+	vi->ctrl->vid = vid;
+	sg_init_one(&sg, &vi->ctrl->vid, sizeof(vi->ctrl->vid));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN,
 				  VIRTIO_NET_CTRL_VLAN_DEL, &sg))
@@ -2133,9 +2137,9 @@ static int virtnet_restore_up(struct virtio_device *vdev)
 static int virtnet_set_guest_offloads(struct virtnet_info *vi, u64 offloads)
 {
 	struct scatterlist sg;
-	vi->ctrl_offloads = cpu_to_virtio64(vi->vdev, offloads);
+	vi->ctrl->offloads = cpu_to_virtio64(vi->vdev, offloads);
 
-	sg_init_one(&sg, &vi->ctrl_offloads, sizeof(vi->ctrl_offloads));
+	sg_init_one(&sg, &vi->ctrl->offloads, sizeof(vi->ctrl->offloads));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_GUEST_OFFLOADS,
 				  VIRTIO_NET_CTRL_GUEST_OFFLOADS_SET, &sg)) {
@@ -2358,6 +2362,7 @@ static void virtnet_free_queues(struct virtnet_info *vi)
 
 	kfree(vi->rq);
 	kfree(vi->sq);
+	kfree(vi->ctrl);
 }
 
 static void _free_receive_bufs(struct virtnet_info *vi)
@@ -2550,6 +2555,9 @@ static int virtnet_alloc_queues(struct virtnet_info *vi)
 {
 	int i;
 
+	vi->ctrl = kzalloc(sizeof(*vi->ctrl), GFP_KERNEL);
+	if (!vi->ctrl)
+		goto err_ctrl;
 	vi->sq = kzalloc(sizeof(*vi->sq) * vi->max_queue_pairs, GFP_KERNEL);
 	if (!vi->sq)
 		goto err_sq;
@@ -2578,6 +2586,8 @@ static int virtnet_alloc_queues(struct virtnet_info *vi)
 err_rq:
 	kfree(vi->sq);
 err_sq:
+	kfree(vi->ctrl);
+err_ctrl:
 	return -ENOMEM;
 }
 
-- 
2.14.3


From b36782ab992fe9a1de353752d027e13b7ee34ad5 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Thu, 19 Apr 2018 08:30:49 +0300
Subject: [PATCH 52/52] virtio_net: fix adding vids on big-endian

[ Upstream commit d7fad4c840f33a6bd333dd7fbb3006edbcf0017a ]

Programming vids (adding or removing them) still passes
guest-endian values in the DMA buffer. That's wrong
if guest is big-endian and when virtio 1 is enabled.

Note: this is on top of a previous patch:
	virtio_net: split out ctrl buffer

Fixes: 9465a7a6f ("virtio_net: enable v1.0 support")
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 2e7e187117b5..aa21b2225679 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -154,7 +154,7 @@ struct control_buf {
 	struct virtio_net_ctrl_mq mq;
 	u8 promisc;
 	u8 allmulti;
-	u16 vid;
+	__virtio16 vid;
 	u64 offloads;
 };
 
@@ -1725,7 +1725,7 @@ static int virtnet_vlan_rx_add_vid(struct net_device *dev,
 	struct virtnet_info *vi = netdev_priv(dev);
 	struct scatterlist sg;
 
-	vi->ctrl->vid = vid;
+	vi->ctrl->vid = cpu_to_virtio16(vi->vdev, vid);
 	sg_init_one(&sg, &vi->ctrl->vid, sizeof(vi->ctrl->vid));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN,
@@ -1740,7 +1740,7 @@ static int virtnet_vlan_rx_kill_vid(struct net_device *dev,
 	struct virtnet_info *vi = netdev_priv(dev);
 	struct scatterlist sg;
 
-	vi->ctrl->vid = vid;
+	vi->ctrl->vid = cpu_to_virtio16(vi->vdev, vid);
 	sg_init_one(&sg, &vi->ctrl->vid, sizeof(vi->ctrl->vid));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN,
-- 
2.14.3

Re: [PATCHES] Networking

[Greg KH]

On Thu, Apr 26, 2018 at 02:38:48PM -0400, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.14 and
> v4.16 -stable, respectively.

All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 104 bytes --]


Please queue up the following networking bug fixes for v4.14 and v4.16
-stable, respectively.

Thanks!

[-- Attachment #2: net_414.mbox --]
[-- Type: Application/Octet-Stream, Size: 121278 bytes --]

From eb52c90dcb80efb67488f90e3155ff8067754470 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Wed, 2 May 2018 13:30:57 +0200
Subject: [PATCH 01/41] 8139too: Use disable_irq_nosync() in
 rtl8139_poll_controller()

[ Upstream commit af3e0fcf78879f718c5f73df0814951bd7057d34 ]

Use disable_irq_nosync() instead of disable_irq() as this might be
called in atomic context with netpoll.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/8139too.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c
index d24b47b8e0b2..d118da5a10a2 100644
--- a/drivers/net/ethernet/realtek/8139too.c
+++ b/drivers/net/ethernet/realtek/8139too.c
@@ -2224,7 +2224,7 @@ static void rtl8139_poll_controller(struct net_device *dev)
 	struct rtl8139_private *tp = netdev_priv(dev);
 	const int irq = tp->pci_dev->irq;
 
-	disable_irq(irq);
+	disable_irq_nosync(irq);
 	rtl8139_interrupt(irq, dev);
 	enable_irq(irq);
 }
-- 
2.14.3


From e3e6f1ac598a4edc1b25a17e2c8f8598ca08f776 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Thu, 3 May 2018 13:17:12 -0500
Subject: [PATCH 02/41] atm: zatm: Fix potential Spectre v1

[ Upstream commit 2be147f7459db5bbf292e0a6f135037b55e20b39 ]

pool can be indirectly controlled by user-space, hence leading to
a potential exploitation of the Spectre variant 1 vulnerability.

This issue was detected with the help of Smatch:

drivers/atm/zatm.c:1462 zatm_ioctl() warn: potential spectre issue
'zatm_dev->pool_info' (local cap)

Fix this by sanitizing pool before using it to index
zatm_dev->pool_info

Notice that given that speculation windows are large, the policy is
to kill the speculation on the first load and not worry if it can be
completed with a dependent load/store [1].

[1] https://marc.info/?l=linux-kernel&m=152449131114778&w=2

Cc: stable@vger.kernel.org
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/atm/zatm.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/atm/zatm.c b/drivers/atm/zatm.c
index 1ef67db03c8e..9c9a22958717 100644
--- a/drivers/atm/zatm.c
+++ b/drivers/atm/zatm.c
@@ -28,6 +28,7 @@
 #include <asm/io.h>
 #include <linux/atomic.h>
 #include <linux/uaccess.h>
+#include <linux/nospec.h>
 
 #include "uPD98401.h"
 #include "uPD98402.h"
@@ -1458,6 +1459,8 @@ static int zatm_ioctl(struct atm_dev *dev,unsigned int cmd,void __user *arg)
 					return -EFAULT;
 				if (pool < 0 || pool > ZATM_LAST_POOL)
 					return -EINVAL;
+				pool = array_index_nospec(pool,
+							  ZATM_LAST_POOL + 1);
 				spin_lock_irqsave(&zatm_dev->lock, flags);
 				info = zatm_dev->pool_info[pool];
 				if (cmd == ZATM_GETPOOLZ) {
-- 
2.14.3


From bc9498bb1b2bdb0e957c0ff274505d8aecf7a6e7 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Fri, 27 Apr 2018 20:59:24 +0800
Subject: [PATCH 03/41] bridge: check iface upper dev when setting master via
 ioctl

[ Upstream commit e8238fc2bd7b4c3c7554fa2df067e796610212fc ]

When we set a bond slave's master to bridge via ioctl, we only check
the IFF_BRIDGE_PORT flag. Although we will find the slave's real master
at netdev_master_upper_dev_link() later, it already does some settings
and allocates some resources. It would be better to return as early
as possible.

v1 -> v2:
use netdev_master_upper_dev_get() instead of netdev_has_any_upper_dev()
to check if we have a master, because not all upper devs are masters,
e.g. vlan device.

Reported-by: syzbot+de73361ee4971b6e6f75@syzkaller.appspotmail.com
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_if.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index f3aef22931ab..55a73ef388bf 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -503,8 +503,8 @@ int br_add_if(struct net_bridge *br, struct net_device *dev)
 	if (dev->netdev_ops->ndo_start_xmit == br_dev_xmit)
 		return -ELOOP;
 
-	/* Device is already being bridged */
-	if (br_port_exists(dev))
+	/* Device has master upper dev */
+	if (netdev_master_upper_dev_get(dev))
 		return -EBUSY;
 
 	/* No bridging devices that dislike that (e.g. wireless) */
-- 
2.14.3


From c1f29607c1749305270b0fb286b27b01f756562a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 3 May 2018 09:39:20 -0700
Subject: [PATCH 04/41] dccp: fix tasklet usage

[ Upstream commit a8d7aa17bbc970971ccdf71988ea19230ab368b1 ]

syzbot reported a crash in tasklet_action_common() caused by dccp.

dccp needs to make sure socket wont disappear before tasklet handler
has completed.

This patch takes a reference on the socket when arming the tasklet,
and moves the sock_put() from dccp_write_xmit_timer() to dccp_write_xmitlet()

kernel BUG at kernel/softirq.c:514!
invalid opcode: 0000 [#1] SMP KASAN
Dumping ftrace buffer:
   (ftrace buffer empty)
Modules linked in:
CPU: 1 PID: 17 Comm: ksoftirqd/1 Not tainted 4.17.0-rc3+ #30
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:tasklet_action_common.isra.19+0x6db/0x700 kernel/softirq.c:515
RSP: 0018:ffff8801d9b3faf8 EFLAGS: 00010246
dccp_close: ABORT with 65423 bytes unread
RAX: 1ffff1003b367f6b RBX: ffff8801daf1f3f0 RCX: 0000000000000000
RDX: ffff8801cf895498 RSI: 0000000000000004 RDI: 0000000000000000
RBP: ffff8801d9b3fc40 R08: ffffed0039f12a95 R09: ffffed0039f12a94
dccp_close: ABORT with 65423 bytes unread
R10: ffffed0039f12a94 R11: ffff8801cf8954a3 R12: 0000000000000000
R13: ffff8801d9b3fc18 R14: dffffc0000000000 R15: ffff8801cf895490
FS:  0000000000000000(0000) GS:ffff8801daf00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000001b2bc28000 CR3: 00000001a08a9000 CR4: 00000000001406e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 tasklet_action+0x1d/0x20 kernel/softirq.c:533
 __do_softirq+0x2e0/0xaf5 kernel/softirq.c:285
dccp_close: ABORT with 65423 bytes unread
 run_ksoftirqd+0x86/0x100 kernel/softirq.c:646
 smpboot_thread_fn+0x417/0x870 kernel/smpboot.c:164
 kthread+0x345/0x410 kernel/kthread.c:238
 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:412
Code: 48 8b 85 e8 fe ff ff 48 8b 95 f0 fe ff ff e9 94 fb ff ff 48 89 95 f0 fe ff ff e8 81 53 6e 00 48 8b 95 f0 fe ff ff e9 62 fb ff ff <0f> 0b 48 89 cf 48 89 8d e8 fe ff ff e8 64 53 6e 00 48 8b 8d e8
RIP: tasklet_action_common.isra.19+0x6db/0x700 kernel/softirq.c:515 RSP: ffff8801d9b3faf8

Fixes: dc841e30eaea ("dccp: Extend CCID packet dequeueing interface")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Cc: dccp@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ccids/ccid2.c | 14 ++++++++++++--
 net/dccp/timer.c       |  2 +-
 2 files changed, 13 insertions(+), 3 deletions(-)

diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c
index 97791b0b1b51..3887bc115762 100644
--- a/net/dccp/ccids/ccid2.c
+++ b/net/dccp/ccids/ccid2.c
@@ -126,6 +126,16 @@ static void ccid2_change_l_seq_window(struct sock *sk, u64 val)
 						  DCCPF_SEQ_WMAX));
 }
 
+static void dccp_tasklet_schedule(struct sock *sk)
+{
+	struct tasklet_struct *t = &dccp_sk(sk)->dccps_xmitlet;
+
+	if (!test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) {
+		sock_hold(sk);
+		__tasklet_schedule(t);
+	}
+}
+
 static void ccid2_hc_tx_rto_expire(unsigned long data)
 {
 	struct sock *sk = (struct sock *)data;
@@ -166,7 +176,7 @@ static void ccid2_hc_tx_rto_expire(unsigned long data)
 
 	/* if we were blocked before, we may now send cwnd=1 packet */
 	if (sender_was_blocked)
-		tasklet_schedule(&dccp_sk(sk)->dccps_xmitlet);
+		dccp_tasklet_schedule(sk);
 	/* restart backed-off timer */
 	sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto);
 out:
@@ -706,7 +716,7 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
 done:
 	/* check if incoming Acks allow pending packets to be sent */
 	if (sender_was_blocked && !ccid2_cwnd_network_limited(hc))
-		tasklet_schedule(&dccp_sk(sk)->dccps_xmitlet);
+		dccp_tasklet_schedule(sk);
 	dccp_ackvec_parsed_cleanup(&hc->tx_av_chunks);
 }
 
diff --git a/net/dccp/timer.c b/net/dccp/timer.c
index 3a2c34027758..2a952cbd6efa 100644
--- a/net/dccp/timer.c
+++ b/net/dccp/timer.c
@@ -230,12 +230,12 @@ static void dccp_write_xmitlet(unsigned long data)
 	else
 		dccp_write_xmit(sk);
 	bh_unlock_sock(sk);
+	sock_put(sk);
 }
 
 static void dccp_write_xmit_timer(unsigned long data)
 {
 	dccp_write_xmitlet(data);
-	sock_put((struct sock *)data);
 }
 
 void dccp_init_xmit_timers(struct sock *sk)
-- 
2.14.3


From a228d35d261302ca6827ee6464719cf9ca7b85c2 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Wed, 2 May 2018 09:41:19 +0300
Subject: [PATCH 05/41] ipv4: fix fnhe usage by non-cached routes

[ Upstream commit 94720e3aee6884d8c8beb678001629da60ec6366 ]

Allow some non-cached routes to use non-expired fnhe:

1. ip_del_fnhe: moved above and now called by find_exception.
The 4.5+ commit deed49df7390 expires fnhe only when caching
routes. Change that to:

1.1. use fnhe for non-cached local output routes, with the help
from (2)

1.2. allow __mkroute_input to detect expired fnhe (outdated
fnhe_gw, for example) when do_cache is false, eg. when itag!=0
for unicast destinations.

2. __mkroute_output: keep fi to allow local routes with orig_oif != 0
to use fnhe info even when the new route will not be cached into fnhe.
After commit 839da4d98960 ("net: ipv4: set orig_oif based on fib
result for local traffic") it means all local routes will be affected
because they are not cached. This change is used to solve a PMTU
problem with IPVS (and probably Netfilter DNAT) setups that redirect
local clients from target local IP (local route to Virtual IP)
to new remote IP target, eg. IPVS TUN real server. Loopback has
64K MTU and we need to create fnhe on the local route that will
keep the reduced PMTU for the Virtual IP. Without this change
fnhe_pmtu is updated from ICMP but never exposed to non-cached
local routes. This includes routes with flowi4_oif!=0 for 4.6+ and
with flowi4_oif=any for 4.14+).

3. update_or_create_fnhe: make sure fnhe_expires is not 0 for
new entries

Fixes: 839da4d98960 ("net: ipv4: set orig_oif based on fib result for local traffic")
Fixes: d6d5e999e5df ("route: do not cache fib route info on local routes with oif")
Fixes: deed49df7390 ("route: check and remove route cache when we get route")
Cc: David Ahern <dsahern@gmail.com>
Cc: Xin Long <lucien.xin@gmail.com>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 118 +++++++++++++++++++++++++------------------------------
 1 file changed, 53 insertions(+), 65 deletions(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 9ff06c5051ae..aa1636f745f7 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -711,7 +711,7 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
 		fnhe->fnhe_daddr = daddr;
 		fnhe->fnhe_gw = gw;
 		fnhe->fnhe_pmtu = pmtu;
-		fnhe->fnhe_expires = expires;
+		fnhe->fnhe_expires = max(1UL, expires);
 
 		/* Exception created; mark the cached routes for the nexthop
 		 * stale, so anyone caching it rechecks if this exception
@@ -1286,6 +1286,36 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst)
 	return mtu - lwtunnel_headroom(dst->lwtstate, mtu);
 }
 
+static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
+{
+	struct fnhe_hash_bucket *hash;
+	struct fib_nh_exception *fnhe, __rcu **fnhe_p;
+	u32 hval = fnhe_hashfun(daddr);
+
+	spin_lock_bh(&fnhe_lock);
+
+	hash = rcu_dereference_protected(nh->nh_exceptions,
+					 lockdep_is_held(&fnhe_lock));
+	hash += hval;
+
+	fnhe_p = &hash->chain;
+	fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock));
+	while (fnhe) {
+		if (fnhe->fnhe_daddr == daddr) {
+			rcu_assign_pointer(*fnhe_p, rcu_dereference_protected(
+				fnhe->fnhe_next, lockdep_is_held(&fnhe_lock)));
+			fnhe_flush_routes(fnhe);
+			kfree_rcu(fnhe, rcu);
+			break;
+		}
+		fnhe_p = &fnhe->fnhe_next;
+		fnhe = rcu_dereference_protected(fnhe->fnhe_next,
+						 lockdep_is_held(&fnhe_lock));
+	}
+
+	spin_unlock_bh(&fnhe_lock);
+}
+
 static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr)
 {
 	struct fnhe_hash_bucket *hash = rcu_dereference(nh->nh_exceptions);
@@ -1299,8 +1329,14 @@ static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr)
 
 	for (fnhe = rcu_dereference(hash[hval].chain); fnhe;
 	     fnhe = rcu_dereference(fnhe->fnhe_next)) {
-		if (fnhe->fnhe_daddr == daddr)
+		if (fnhe->fnhe_daddr == daddr) {
+			if (fnhe->fnhe_expires &&
+			    time_after(jiffies, fnhe->fnhe_expires)) {
+				ip_del_fnhe(nh, daddr);
+				break;
+			}
 			return fnhe;
+		}
 	}
 	return NULL;
 }
@@ -1620,36 +1656,6 @@ static void ip_handle_martian_source(struct net_device *dev,
 #endif
 }
 
-static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
-{
-	struct fnhe_hash_bucket *hash;
-	struct fib_nh_exception *fnhe, __rcu **fnhe_p;
-	u32 hval = fnhe_hashfun(daddr);
-
-	spin_lock_bh(&fnhe_lock);
-
-	hash = rcu_dereference_protected(nh->nh_exceptions,
-					 lockdep_is_held(&fnhe_lock));
-	hash += hval;
-
-	fnhe_p = &hash->chain;
-	fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock));
-	while (fnhe) {
-		if (fnhe->fnhe_daddr == daddr) {
-			rcu_assign_pointer(*fnhe_p, rcu_dereference_protected(
-				fnhe->fnhe_next, lockdep_is_held(&fnhe_lock)));
-			fnhe_flush_routes(fnhe);
-			kfree_rcu(fnhe, rcu);
-			break;
-		}
-		fnhe_p = &fnhe->fnhe_next;
-		fnhe = rcu_dereference_protected(fnhe->fnhe_next,
-						 lockdep_is_held(&fnhe_lock));
-	}
-
-	spin_unlock_bh(&fnhe_lock);
-}
-
 static void set_lwt_redirect(struct rtable *rth)
 {
 	if (lwtunnel_output_redirect(rth->dst.lwtstate)) {
@@ -1716,20 +1722,10 @@ static int __mkroute_input(struct sk_buff *skb,
 
 	fnhe = find_exception(&FIB_RES_NH(*res), daddr);
 	if (do_cache) {
-		if (fnhe) {
+		if (fnhe)
 			rth = rcu_dereference(fnhe->fnhe_rth_input);
-			if (rth && rth->dst.expires &&
-			    time_after(jiffies, rth->dst.expires)) {
-				ip_del_fnhe(&FIB_RES_NH(*res), daddr);
-				fnhe = NULL;
-			} else {
-				goto rt_cache;
-			}
-		}
-
-		rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
-
-rt_cache:
+		else
+			rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
 		if (rt_cache_valid(rth)) {
 			skb_dst_set_noref(skb, &rth->dst);
 			goto out;
@@ -2206,39 +2202,31 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 		 * the loopback interface and the IP_PKTINFO ipi_ifindex will
 		 * be set to the loopback interface as well.
 		 */
-		fi = NULL;
+		do_cache = false;
 	}
 
 	fnhe = NULL;
 	do_cache &= fi != NULL;
-	if (do_cache) {
+	if (fi) {
 		struct rtable __rcu **prth;
 		struct fib_nh *nh = &FIB_RES_NH(*res);
 
 		fnhe = find_exception(nh, fl4->daddr);
+		if (!do_cache)
+			goto add;
 		if (fnhe) {
 			prth = &fnhe->fnhe_rth_output;
-			rth = rcu_dereference(*prth);
-			if (rth && rth->dst.expires &&
-			    time_after(jiffies, rth->dst.expires)) {
-				ip_del_fnhe(nh, fl4->daddr);
-				fnhe = NULL;
-			} else {
-				goto rt_cache;
+		} else {
+			if (unlikely(fl4->flowi4_flags &
+				     FLOWI_FLAG_KNOWN_NH &&
+				     !(nh->nh_gw &&
+				       nh->nh_scope == RT_SCOPE_LINK))) {
+				do_cache = false;
+				goto add;
 			}
+			prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
 		}
-
-		if (unlikely(fl4->flowi4_flags &
-			     FLOWI_FLAG_KNOWN_NH &&
-			     !(nh->nh_gw &&
-			       nh->nh_scope == RT_SCOPE_LINK))) {
-			do_cache = false;
-			goto add;
-		}
-		prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
 		rth = rcu_dereference(*prth);
-
-rt_cache:
 		if (rt_cache_valid(rth) && dst_hold_safe(&rth->dst))
 			return rth;
 	}
-- 
2.14.3


From 7c8cd27272f2c909e4d3078fd6abd4f3e5ff99b6 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Thu, 10 May 2018 10:59:34 -0700
Subject: [PATCH 06/41] ipv4: fix memory leaks in udp_sendmsg, ping_v4_sendmsg

[ Upstream commit 1b97013bfb11d66f041de691de6f0fec748ce016 ]

Fix more memory leaks in ip_cmsg_send() callers. Part of them were fixed
earlier in 919483096bfe.

* udp_sendmsg one was there since the beginning when linux sources were
  first added to git;
* ping_v4_sendmsg one was copy/pasted in c319b4d76b9e.

Whenever return happens in udp_sendmsg() or ping_v4_sendmsg() IP options
have to be freed if they were allocated previously.

Add label so that future callers (if any) can use it instead of kfree()
before return that is easy to forget.

Fixes: c319b4d76b9e (net: ipv4: add IPPROTO_ICMP socket kind)
Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ping.c | 7 +++++--
 net/ipv4/udp.c  | 7 +++++--
 2 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index b8f0db54b197..16226d49263d 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -775,8 +775,10 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	ipc.addr = faddr = daddr;
 
 	if (ipc.opt && ipc.opt->opt.srr) {
-		if (!daddr)
-			return -EINVAL;
+		if (!daddr) {
+			err = -EINVAL;
+			goto out_free;
+		}
 		faddr = ipc.opt->opt.faddr;
 	}
 	tos = get_rttos(&ipc, inet);
@@ -842,6 +844,7 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 out:
 	ip_rt_put(rt);
+out_free:
 	if (free)
 		kfree(ipc.opt);
 	if (!err) {
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index c79fa6f6b758..5517f20a9cd9 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -978,8 +978,10 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	sock_tx_timestamp(sk, ipc.sockc.tsflags, &ipc.tx_flags);
 
 	if (ipc.opt && ipc.opt->opt.srr) {
-		if (!daddr)
-			return -EINVAL;
+		if (!daddr) {
+			err = -EINVAL;
+			goto out_free;
+		}
 		faddr = ipc.opt->opt.faddr;
 		connected = 0;
 	}
@@ -1087,6 +1089,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 out:
 	ip_rt_put(rt);
+out_free:
 	if (free)
 		kfree(ipc.opt);
 	if (!err)
-- 
2.14.3


From 4123b30585779a8e5cf6ce49c4a7c64cdb448147 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 7 May 2018 09:02:25 -0700
Subject: [PATCH 07/41] llc: better deal with too small mtu

[ Upstream commit 2c5d5b13c6eb79f5677e206b8aad59b3a2097f60 ]

syzbot loves to set very small mtu on devices, since it brings joy.
We must make llc_ui_sendmsg() fool proof.

usercopy: Kernel memory overwrite attempt detected to wrapped address (offset 0, size 18446612139802320068)!

kernel BUG at mm/usercopy.c:100!
invalid opcode: 0000 [#1] SMP KASAN
Dumping ftrace buffer:
   (ftrace buffer empty)
Modules linked in:
CPU: 0 PID: 17464 Comm: syz-executor1 Not tainted 4.17.0-rc3+ #36
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:usercopy_abort+0xbb/0xbd mm/usercopy.c:88
RSP: 0018:ffff8801868bf800 EFLAGS: 00010282
RAX: 000000000000006c RBX: ffffffff87d2fb00 RCX: 0000000000000000
RDX: 000000000000006c RSI: ffffffff81610731 RDI: ffffed0030d17ef6
RBP: ffff8801868bf858 R08: ffff88018daa4200 R09: ffffed003b5c4fb0
R10: ffffed003b5c4fb0 R11: ffff8801dae27d87 R12: ffffffff87d2f8e0
R13: ffffffff87d2f7a0 R14: ffffffff87d2f7a0 R15: ffffffff87d2f7a0
FS:  00007f56a14ac700(0000) GS:ffff8801dae00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000001b2bc21000 CR3: 00000001abeb1000 CR4: 00000000001426f0
DR0: 0000000020000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000030602
Call Trace:
 check_bogus_address mm/usercopy.c:153 [inline]
 __check_object_size+0x5d9/0x5d9 mm/usercopy.c:256
 check_object_size include/linux/thread_info.h:108 [inline]
 check_copy_size include/linux/thread_info.h:139 [inline]
 copy_from_iter_full include/linux/uio.h:121 [inline]
 memcpy_from_msg include/linux/skbuff.h:3305 [inline]
 llc_ui_sendmsg+0x4b1/0x1530 net/llc/af_llc.c:941
 sock_sendmsg_nosec net/socket.c:629 [inline]
 sock_sendmsg+0xd5/0x120 net/socket.c:639
 __sys_sendto+0x3d7/0x670 net/socket.c:1789
 __do_sys_sendto net/socket.c:1801 [inline]
 __se_sys_sendto net/socket.c:1797 [inline]
 __x64_sys_sendto+0xe1/0x1a0 net/socket.c:1797
 do_syscall_64+0x1b1/0x800 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x455979
RSP: 002b:00007f56a14abc68 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 00007f56a14ac6d4 RCX: 0000000000455979
RDX: 0000000000000000 RSI: 0000000020000000 RDI: 0000000000000018
RBP: 000000000072bea0 R08: 00000000200012c0 R09: 0000000000000010
R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff
R13: 0000000000000548 R14: 00000000006fbf60 R15: 0000000000000000
Code: 55 c0 e8 c0 55 bb ff ff 75 c8 48 8b 55 c0 4d 89 f9 ff 75 d0 4d 89 e8 48 89 d9 4c 89 e6 41 56 48 c7 c7 80 fa d2 87 e8 a0 0b a3 ff <0f> 0b e8 95 55 bb ff e8 c0 a8 f7 ff 8b 95 14 ff ff ff 4d 89 e8
RIP: usercopy_abort+0xbb/0xbd mm/usercopy.c:88 RSP: ffff8801868bf800

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/llc/af_llc.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index cf41d9b4a0b8..b49f5afab405 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -930,6 +930,9 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	if (size > llc->dev->mtu)
 		size = llc->dev->mtu;
 	copied = size - hdrlen;
+	rc = -EINVAL;
+	if (copied < 0)
+		goto release;
 	release_sock(sk);
 	skb = sock_alloc_send_skb(sk, size, noblock, &rc);
 	lock_sock(sk);
-- 
2.14.3


From 551b788e03dd5306c731b25492159ca613621dd8 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Thu, 3 May 2018 13:45:58 -0500
Subject: [PATCH 08/41] net: atm: Fix potential Spectre v1

[ Upstream commit acf784bd0ce257fe43da7ca266f7a10b837479d2 ]

ioc_data.dev_num can be controlled by user-space, hence leading to
a potential exploitation of the Spectre variant 1 vulnerability.

This issue was detected with the help of Smatch:
net/atm/lec.c:702 lec_vcc_attach() warn: potential spectre issue
'dev_lec'

Fix this by sanitizing ioc_data.dev_num before using it to index
dev_lec. Also, notice that there is another instance in which array
dev_lec is being indexed using ioc_data.dev_num at line 705:
lec_vcc_added(netdev_priv(dev_lec[ioc_data.dev_num]),

Notice that given that speculation windows are large, the policy is
to kill the speculation on the first load and not worry if it can be
completed with a dependent load/store [1].

[1] https://marc.info/?l=linux-kernel&m=152449131114778&w=2

Cc: stable@vger.kernel.org
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/atm/lec.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/atm/lec.c b/net/atm/lec.c
index a3d93a1bb133..5741b6474dd9 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -41,6 +41,9 @@ static unsigned char bridge_ula_lec[] = { 0x01, 0x80, 0xc2, 0x00, 0x00 };
 #include <linux/module.h>
 #include <linux/init.h>
 
+/* Hardening for Spectre-v1 */
+#include <linux/nospec.h>
+
 #include "lec.h"
 #include "lec_arpc.h"
 #include "resources.h"
@@ -687,8 +690,10 @@ static int lec_vcc_attach(struct atm_vcc *vcc, void __user *arg)
 	bytes_left = copy_from_user(&ioc_data, arg, sizeof(struct atmlec_ioc));
 	if (bytes_left != 0)
 		pr_info("copy from user failed for %d bytes\n", bytes_left);
-	if (ioc_data.dev_num < 0 || ioc_data.dev_num >= MAX_LEC_ITF ||
-	    !dev_lec[ioc_data.dev_num])
+	if (ioc_data.dev_num < 0 || ioc_data.dev_num >= MAX_LEC_ITF)
+		return -EINVAL;
+	ioc_data.dev_num = array_index_nospec(ioc_data.dev_num, MAX_LEC_ITF);
+	if (!dev_lec[ioc_data.dev_num])
 		return -EINVAL;
 	vpriv = kmalloc(sizeof(struct lec_vcc_priv), GFP_KERNEL);
 	if (!vpriv)
-- 
2.14.3


From adc315e296d4d9abd55c8e1c1213b93b5bc6f676 Mon Sep 17 00:00:00 2001
From: Rob Taglang <rob@taglang.io>
Date: Thu, 3 May 2018 17:13:06 -0400
Subject: [PATCH 09/41] net: ethernet: sun: niu set correct packet size in skb

[ Upstream commit 14224923c3600bae2ac4dcae3bf0c3d4dc2812be ]

Currently, skb->len and skb->data_len are set to the page size, not
the packet size. This causes the frame check sequence to not be
located at the "end" of the packet resulting in ethernet frame check
errors. The driver does work currently, but stricter kernel facing
networking solutions like OpenVSwitch will drop these packets as
invalid.

These changes set the packet size correctly so that these errors no
longer occur. The length does not include the frame check sequence, so
that subtraction was removed.

Tested on Oracle/SUN Multithreaded 10-Gigabit Ethernet Network
Controller [108e:abcd] and validated in wireshark.

Signed-off-by: Rob Taglang <rob@taglang.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sun/niu.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c
index 6a4e8e1bbd90..e92f41d20a2c 100644
--- a/drivers/net/ethernet/sun/niu.c
+++ b/drivers/net/ethernet/sun/niu.c
@@ -3442,7 +3442,7 @@ static int niu_process_rx_pkt(struct napi_struct *napi, struct niu *np,
 
 		len = (val & RCR_ENTRY_L2_LEN) >>
 			RCR_ENTRY_L2_LEN_SHIFT;
-		len -= ETH_FCS_LEN;
+		append_size = len + ETH_HLEN + ETH_FCS_LEN;
 
 		addr = (val & RCR_ENTRY_PKT_BUF_ADDR) <<
 			RCR_ENTRY_PKT_BUF_ADDR_SHIFT;
@@ -3452,7 +3452,6 @@ static int niu_process_rx_pkt(struct napi_struct *napi, struct niu *np,
 					 RCR_ENTRY_PKTBUFSZ_SHIFT];
 
 		off = addr & ~PAGE_MASK;
-		append_size = rcr_size;
 		if (num_rcr == 1) {
 			int ptype;
 
@@ -3465,7 +3464,7 @@ static int niu_process_rx_pkt(struct napi_struct *napi, struct niu *np,
 			else
 				skb_checksum_none_assert(skb);
 		} else if (!(val & RCR_ENTRY_MULTI))
-			append_size = len - skb->len;
+			append_size = append_size - skb->len;
 
 		niu_rx_skb_append(skb, page, off, append_size, rcr_size);
 		if ((page->index + rp->rbr_block_size) - rcr_size == addr) {
-- 
2.14.3


From aa11fd60d3d10505348852fcc5e7143185b95063 Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Tue, 1 May 2018 12:41:22 -0500
Subject: [PATCH 10/41] net: ethernet: ti: cpsw: fix packet leaking in dual_mac
 mode

[ Upstream commit 5e5add172ea81152d518b161ec5706503ad3d799 ]

In dual_mac mode packets arrived on one port should not be forwarded by
switch hw to another port. Only Linux Host can forward packets between
ports. The below test case (reported in [1]) shows that packet arrived on
one port can be leaked to anoter (reproducible with dual port evms):
 - connect port 1 (eth0) to linux Host 0 and run tcpdump or Wireshark
 - connect port 2 (eth1) to linux Host 1 with vlan 1 configured
 - ping <IPx> from Host 1 through vlan 1 interface.
ARP packets will be seen on Host 0.

Issue happens because dual_mac mode is implemnted using two vlans: 1 (Port
1+Port 0) and 2 (Port 2+Port 0), so there are vlan records created for for
each vlan. By default, the ALE will find valid vlan record in its table
when vlan 1 tagged packet arrived on Port 2 and so forwards packet to all
ports which are vlan 1 members (like Port.

To avoid such behaviorr the ALE VLAN ID Ingress Check need to be enabled
for each external CPSW port (ALE_PORTCTLn.VID_INGRESS_CHECK) so ALE will
drop ingress packets if Rx port is not VLAN member.

Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 992c43b1868f..8cb44eabc283 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -1260,6 +1260,8 @@ static inline void cpsw_add_dual_emac_def_ale_entries(
 	cpsw_ale_add_ucast(cpsw->ale, priv->mac_addr,
 			   HOST_PORT_NUM, ALE_VLAN |
 			   ALE_SECURE, slave->port_vlan);
+	cpsw_ale_control_set(cpsw->ale, slave_port,
+			     ALE_PORT_DROP_UNKNOWN_VLAN, 1);
 }
 
 static void soft_reset_slave(struct cpsw_slave *slave)
-- 
2.14.3


From faf5a3d0677eda24155cfd7db663f7934a4a7383 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Thu, 10 May 2018 09:06:04 +0200
Subject: [PATCH 11/41] net/mlx4_en: Fix an error handling path in
 'mlx4_en_init_netdev()'

[ Upstream commit a577d868b768a3baf16cdd4841ab8cfb165521d6 ]

If an error occurs, 'mlx4_en_destroy_netdev()' is called.
It then calls 'mlx4_en_free_resources()' which does the needed resources
cleanup.

So, doing some explicit kfree in the error handling path would lead to
some double kfree.

Simplify code to avoid such a case.

Fixes: 67f8b1dcb9ee ("net/mlx4_en: Refactor the XDP forwarding rings scheme")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index c097eef41a9c..faa4bd21f148 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -3318,12 +3318,11 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 					   MAX_TX_RINGS, GFP_KERNEL);
 		if (!priv->tx_ring[t]) {
 			err = -ENOMEM;
-			goto err_free_tx;
+			goto out;
 		}
 		priv->tx_cq[t] = kzalloc(sizeof(struct mlx4_en_cq *) *
 					 MAX_TX_RINGS, GFP_KERNEL);
 		if (!priv->tx_cq[t]) {
-			kfree(priv->tx_ring[t]);
 			err = -ENOMEM;
 			goto out;
 		}
@@ -3576,11 +3575,6 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 
 	return 0;
 
-err_free_tx:
-	while (t--) {
-		kfree(priv->tx_ring[t]);
-		kfree(priv->tx_cq[t]);
-	}
 out:
 	mlx4_en_destroy_netdev(dev);
 	return err;
-- 
2.14.3


From 3179bc2f5a460d0f5e8564f80c49928cb5babec5 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Wed, 9 May 2018 18:35:13 +0300
Subject: [PATCH 12/41] net/mlx4_en: Verify coalescing parameters are in range

[ Upstream commit 6ad4e91c6d796b38a7f0e724db1de28eeb122bad ]

Add check of coalescing parameters received through ethtool are within
range of values supported by the HW.
Driver gets the coalescing rx/tx-usecs and rx/tx-frames as set by the
users through ethtool. The ethtool support up to 32 bit value for each.
However, mlx4 modify cq limits the coalescing time parameter and
coalescing frames parameters to 16 bits.
Return out of range error if user tries to set these parameters to
higher values.
Change type of sample-interval and adaptive_rx_coal parameters in mlx4
driver to u32 as the ethtool holds them as u32 and these parameters are
not limited due to mlx4 HW.

Fixes: c27a02cd94d6 ('mlx4_en: Add driver for Mellanox ConnectX 10GbE NIC')
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 16 ++++++++++++++++
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h    |  7 +++++--
 2 files changed, 21 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 67f74fcb265e..5fe56dc4cfae 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1013,6 +1013,22 @@ static int mlx4_en_set_coalesce(struct net_device *dev,
 	if (!coal->tx_max_coalesced_frames_irq)
 		return -EINVAL;
 
+	if (coal->tx_coalesce_usecs > MLX4_EN_MAX_COAL_TIME ||
+	    coal->rx_coalesce_usecs > MLX4_EN_MAX_COAL_TIME ||
+	    coal->rx_coalesce_usecs_low > MLX4_EN_MAX_COAL_TIME ||
+	    coal->rx_coalesce_usecs_high > MLX4_EN_MAX_COAL_TIME) {
+		netdev_info(dev, "%s: maximum coalesce time supported is %d usecs\n",
+			    __func__, MLX4_EN_MAX_COAL_TIME);
+		return -ERANGE;
+	}
+
+	if (coal->tx_max_coalesced_frames > MLX4_EN_MAX_COAL_PKTS ||
+	    coal->rx_max_coalesced_frames > MLX4_EN_MAX_COAL_PKTS) {
+		netdev_info(dev, "%s: maximum coalesced frames supported is %d\n",
+			    __func__, MLX4_EN_MAX_COAL_PKTS);
+		return -ERANGE;
+	}
+
 	priv->rx_frames = (coal->rx_max_coalesced_frames ==
 			   MLX4_EN_AUTO_CONF) ?
 				MLX4_EN_RX_COAL_TARGET :
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 2c1a5ff6acfa..09f4764a3f39 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -131,6 +131,9 @@
 #define MLX4_EN_TX_COAL_PKTS	16
 #define MLX4_EN_TX_COAL_TIME	0x10
 
+#define MLX4_EN_MAX_COAL_PKTS	U16_MAX
+#define MLX4_EN_MAX_COAL_TIME	U16_MAX
+
 #define MLX4_EN_RX_RATE_LOW		400000
 #define MLX4_EN_RX_COAL_TIME_LOW	0
 #define MLX4_EN_RX_RATE_HIGH		450000
@@ -547,8 +550,8 @@ struct mlx4_en_priv {
 	u16 rx_usecs_low;
 	u32 pkt_rate_high;
 	u16 rx_usecs_high;
-	u16 sample_interval;
-	u16 adaptive_rx_coal;
+	u32 sample_interval;
+	u32 adaptive_rx_coal;
 	u32 msg_enable;
 	u32 loopback_ok;
 	u32 validate_loopback;
-- 
2.14.3


From 9c1e95c203f848844152c3043661f573f3893b48 Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@mellanox.com>
Date: Thu, 22 Mar 2018 18:51:37 +0200
Subject: [PATCH 13/41] net/mlx5e: Err if asked to offload TC match on frag
 being first

[ Upstream commit f85900c3e13fdb61f040c9feecbcda601e0cdcfb ]

The HW doesn't support matching on frag first/later, return error if we are
asked to offload that.

Fixes: 3f7d0eb42d59 ("net/mlx5e: Offload TC matching on packets being IP fragments")
Signed-off-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 42bab73a9f40..598755529815 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -780,6 +780,10 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 						  f->mask);
 		addr_type = key->addr_type;
 
+		/* the HW doesn't support frag first/later */
+		if (mask->flags & FLOW_DIS_FIRST_FRAG)
+			return -EOPNOTSUPP;
+
 		if (mask->flags & FLOW_DIS_IS_FRAGMENT) {
 			MLX5_SET(fte_match_set_lyr_2_4, headers_c, frag, 1);
 			MLX5_SET(fte_match_set_lyr_2_4, headers_v, frag,
-- 
2.14.3


From b52f78af933c7ba0b7cfc3f4d2e84eb62ef6f1e3 Mon Sep 17 00:00:00 2001
From: Adi Nissim <adin@mellanox.com>
Date: Wed, 25 Apr 2018 11:21:32 +0300
Subject: [PATCH 14/41] net/mlx5: E-Switch, Include VF RDMA stats in vport
 statistics

[ Upstream commit 88d725bbb43cd63a40c8ef70dd373f1d38ead2e3 ]

The host side reporting of VF vport statistics didn't include the VF
RDMA traffic.

Fixes: 3b751a2a418a ("net/mlx5: E-Switch, Introduce get vf statistics")
Signed-off-by: Adi Nissim <adin@mellanox.com>
Reported-by: Ariel Almog <ariela@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index c77f4c0c7769..82e37250ed01 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -2054,26 +2054,35 @@ int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,
 	memset(vf_stats, 0, sizeof(*vf_stats));
 	vf_stats->rx_packets =
 		MLX5_GET_CTR(out, received_eth_unicast.packets) +
+		MLX5_GET_CTR(out, received_ib_unicast.packets) +
 		MLX5_GET_CTR(out, received_eth_multicast.packets) +
+		MLX5_GET_CTR(out, received_ib_multicast.packets) +
 		MLX5_GET_CTR(out, received_eth_broadcast.packets);
 
 	vf_stats->rx_bytes =
 		MLX5_GET_CTR(out, received_eth_unicast.octets) +
+		MLX5_GET_CTR(out, received_ib_unicast.octets) +
 		MLX5_GET_CTR(out, received_eth_multicast.octets) +
+		MLX5_GET_CTR(out, received_ib_multicast.octets) +
 		MLX5_GET_CTR(out, received_eth_broadcast.octets);
 
 	vf_stats->tx_packets =
 		MLX5_GET_CTR(out, transmitted_eth_unicast.packets) +
+		MLX5_GET_CTR(out, transmitted_ib_unicast.packets) +
 		MLX5_GET_CTR(out, transmitted_eth_multicast.packets) +
+		MLX5_GET_CTR(out, transmitted_ib_multicast.packets) +
 		MLX5_GET_CTR(out, transmitted_eth_broadcast.packets);
 
 	vf_stats->tx_bytes =
 		MLX5_GET_CTR(out, transmitted_eth_unicast.octets) +
+		MLX5_GET_CTR(out, transmitted_ib_unicast.octets) +
 		MLX5_GET_CTR(out, transmitted_eth_multicast.octets) +
+		MLX5_GET_CTR(out, transmitted_ib_multicast.octets) +
 		MLX5_GET_CTR(out, transmitted_eth_broadcast.octets);
 
 	vf_stats->multicast =
-		MLX5_GET_CTR(out, received_eth_multicast.packets);
+		MLX5_GET_CTR(out, received_eth_multicast.packets) +
+		MLX5_GET_CTR(out, received_ib_multicast.packets);
 
 	vf_stats->broadcast =
 		MLX5_GET_CTR(out, received_eth_broadcast.packets);
-- 
2.14.3


From b80967a616335efb0c81fcd18d7edbb08c54d171 Mon Sep 17 00:00:00 2001
From: Roman Mashak <mrv@mojatatu.com>
Date: Fri, 11 May 2018 14:35:33 -0400
Subject: [PATCH 15/41] net sched actions: fix refcnt leak in skbmod

[ Upstream commit a52956dfc503f8cc5cfe6454959b7049fddb4413 ]

When application fails to pass flags in netlink TLV when replacing
existing skbmod action, the kernel will leak refcnt:

$ tc actions get action skbmod index 1
total acts 0

        action order 0: skbmod pipe set smac 00:11:22:33:44:55
         index 1 ref 1 bind 0

For example, at this point a buggy application replaces the action with
index 1 with new smac 00:aa:22:33:44:55, it fails because of zero flags,
however refcnt gets bumped:

$ tc actions get actions skbmod index 1
total acts 0

        action order 0: skbmod pipe set smac 00:11:22:33:44:55
         index 1 ref 2 bind 0
$

Tha patch fixes this by calling tcf_idr_release() on existing actions.

Fixes: 86da71b57383d ("net_sched: Introduce skbmod action")
Signed-off-by: Roman Mashak <mrv@mojatatu.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_skbmod.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index 6d10b3af479b..821823b2518a 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -131,8 +131,11 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
 	if (exists && bind)
 		return 0;
 
-	if (!lflags)
+	if (!lflags) {
+		if (exists)
+			tcf_idr_release(*a, bind);
 		return -EINVAL;
+	}
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, parm->index, est, a,
-- 
2.14.3


From 98e8c4dc41ec76a39647b57eed8cab619425d366 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 2 May 2018 10:03:30 -0700
Subject: [PATCH 16/41] net_sched: fq: take care of throttled flows before
 reuse

[ Upstream commit 7df40c2673a1307c3260aab6f9d4b9bf97ca8fd7 ]

Normally, a socket can not be freed/reused unless all its TX packets
left qdisc and were TX-completed. However connect(AF_UNSPEC) allows
this to happen.

With commit fc59d5bdf1e3 ("pkt_sched: fq: clear time_next_packet for
reused flows") we cleared f->time_next_packet but took no special
action if the flow was still in the throttled rb-tree.

Since f->time_next_packet is the key used in the rb-tree searches,
blindly clearing it might break rb-tree integrity. We need to make
sure the flow is no longer in the rb-tree to avoid this problem.

Fixes: fc59d5bdf1e3 ("pkt_sched: fq: clear time_next_packet for reused flows")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_fq.c | 37 +++++++++++++++++++++++++------------
 1 file changed, 25 insertions(+), 12 deletions(-)

diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 263d16e3219e..f50eb87cfe79 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -128,6 +128,28 @@ static bool fq_flow_is_detached(const struct fq_flow *f)
 	return f->next == &detached;
 }
 
+static bool fq_flow_is_throttled(const struct fq_flow *f)
+{
+	return f->next == &throttled;
+}
+
+static void fq_flow_add_tail(struct fq_flow_head *head, struct fq_flow *flow)
+{
+	if (head->first)
+		head->last->next = flow;
+	else
+		head->first = flow;
+	head->last = flow;
+	flow->next = NULL;
+}
+
+static void fq_flow_unset_throttled(struct fq_sched_data *q, struct fq_flow *f)
+{
+	rb_erase(&f->rate_node, &q->delayed);
+	q->throttled_flows--;
+	fq_flow_add_tail(&q->old_flows, f);
+}
+
 static void fq_flow_set_throttled(struct fq_sched_data *q, struct fq_flow *f)
 {
 	struct rb_node **p = &q->delayed.rb_node, *parent = NULL;
@@ -155,15 +177,6 @@ static void fq_flow_set_throttled(struct fq_sched_data *q, struct fq_flow *f)
 
 static struct kmem_cache *fq_flow_cachep __read_mostly;
 
-static void fq_flow_add_tail(struct fq_flow_head *head, struct fq_flow *flow)
-{
-	if (head->first)
-		head->last->next = flow;
-	else
-		head->first = flow;
-	head->last = flow;
-	flow->next = NULL;
-}
 
 /* limit number of collected flows per round */
 #define FQ_GC_MAX 8
@@ -267,6 +280,8 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q)
 				     f->socket_hash != sk->sk_hash)) {
 				f->credit = q->initial_quantum;
 				f->socket_hash = sk->sk_hash;
+				if (fq_flow_is_throttled(f))
+					fq_flow_unset_throttled(q, f);
 				f->time_next_packet = 0ULL;
 			}
 			return f;
@@ -438,9 +453,7 @@ static void fq_check_throttled(struct fq_sched_data *q, u64 now)
 			q->time_next_delayed_flow = f->time_next_packet;
 			break;
 		}
-		rb_erase(p, &q->delayed);
-		q->throttled_flows--;
-		fq_flow_add_tail(&q->old_flows, f);
+		fq_flow_unset_throttled(q, f);
 	}
 }
 
-- 
2.14.3


From fc16cb30a3c3f3085096a8573d68814c6f87119c Mon Sep 17 00:00:00 2001
From: Lance Richardson <lance.richardson.net@gmail.com>
Date: Wed, 25 Apr 2018 10:21:54 -0400
Subject: [PATCH 17/41] net: support compat 64-bit time in {s,g}etsockopt

[ Upstream commit 988bf7243e03ef69238381594e0334a79cef74a6 ]

For the x32 ABI, struct timeval has two 64-bit fields. However
the kernel currently interprets the user-space values used for
the SO_RCVTIMEO and SO_SNDTIMEO socket options as having a pair
of 32-bit fields.

When the seconds portion of the requested timeout is less than 2**32,
the seconds portion of the effective timeout is correct but the
microseconds portion is zero.  When the seconds portion of the
requested timeout is zero and the microseconds portion is non-zero,
the kernel interprets the timeout as zero (never timeout).

Fix by using 64-bit time for SO_RCVTIMEO/SO_SNDTIMEO as required
for the ABI.

The code included below demonstrates the problem.

Results before patch:
    $ gcc -m64 -Wall -O2 -o socktmo socktmo.c && ./socktmo
    recv time: 2.008181 seconds
    send time: 2.015985 seconds

    $ gcc -m32 -Wall -O2 -o socktmo socktmo.c && ./socktmo
    recv time: 2.016763 seconds
    send time: 2.016062 seconds

    $ gcc -mx32 -Wall -O2 -o socktmo socktmo.c && ./socktmo
    recv time: 1.007239 seconds
    send time: 1.023890 seconds

Results after patch:
    $ gcc -m64 -O2 -Wall -o socktmo socktmo.c && ./socktmo
    recv time: 2.010062 seconds
    send time: 2.015836 seconds

    $ gcc -m32 -O2 -Wall -o socktmo socktmo.c && ./socktmo
    recv time: 2.013974 seconds
    send time: 2.015981 seconds

    $ gcc -mx32 -O2 -Wall -o socktmo socktmo.c && ./socktmo
    recv time: 2.030257 seconds
    send time: 2.013383 seconds

 #include <stdio.h>
 #include <stdlib.h>
 #include <sys/socket.h>
 #include <sys/types.h>
 #include <sys/time.h>

 void checkrc(char *str, int rc)
 {
         if (rc >= 0)
                 return;

         perror(str);
         exit(1);
 }

 static char buf[1024];
 int main(int argc, char **argv)
 {
         int rc;
         int socks[2];
         struct timeval tv;
         struct timeval start, end, delta;

         rc = socketpair(AF_UNIX, SOCK_STREAM, 0, socks);
         checkrc("socketpair", rc);

         /* set timeout to 1.999999 seconds */
         tv.tv_sec = 1;
         tv.tv_usec = 999999;
         rc = setsockopt(socks[0], SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof tv);
         rc = setsockopt(socks[0], SOL_SOCKET, SO_SNDTIMEO, &tv, sizeof tv);
         checkrc("setsockopt", rc);

         /* measure actual receive timeout */
         gettimeofday(&start, NULL);
         rc = recv(socks[0], buf, sizeof buf, 0);
         gettimeofday(&end, NULL);
         timersub(&end, &start, &delta);

         printf("recv time: %ld.%06ld seconds\n",
                (long)delta.tv_sec, (long)delta.tv_usec);

         /* fill send buffer */
         do {
                 rc = send(socks[0], buf, sizeof buf, 0);
         } while (rc > 0);

         /* measure actual send timeout */
         gettimeofday(&start, NULL);
         rc = send(socks[0], buf, sizeof buf, 0);
         gettimeofday(&end, NULL);
         timersub(&end, &start, &delta);

         printf("send time: %ld.%06ld seconds\n",
                (long)delta.tv_sec, (long)delta.tv_usec);
         exit(0);
 }

Fixes: 515c7af85ed9 ("x32: Use compat shims for {g,s}etsockopt")
Reported-by: Gopal RajagopalSai <gopalsr83@gmail.com>
Signed-off-by: Lance Richardson <lance.richardson.net@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/compat.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/compat.c b/net/compat.c
index 22381719718c..32ed993588d6 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -377,7 +377,8 @@ static int compat_sock_setsockopt(struct socket *sock, int level, int optname,
 	    optname == SO_ATTACH_REUSEPORT_CBPF)
 		return do_set_attach_filter(sock, level, optname,
 					    optval, optlen);
-	if (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO)
+	if (!COMPAT_USE_64BIT_TIME &&
+	    (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO))
 		return do_set_sock_timeout(sock, level, optname, optval, optlen);
 
 	return sock_setsockopt(sock, level, optname, optval, optlen);
@@ -442,7 +443,8 @@ static int do_get_sock_timeout(struct socket *sock, int level, int optname,
 static int compat_sock_getsockopt(struct socket *sock, int level, int optname,
 				char __user *optval, int __user *optlen)
 {
-	if (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO)
+	if (!COMPAT_USE_64BIT_TIME &&
+	    (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO))
 		return do_get_sock_timeout(sock, level, optname, optval, optlen);
 	return sock_getsockopt(sock, level, optname, optval, optlen);
 }
-- 
2.14.3


From 7b738277825d50dda6b0ce6befa42355949a6a39 Mon Sep 17 00:00:00 2001
From: Dave Watson <davejwatson@fb.com>
Date: Tue, 1 May 2018 13:05:39 -0700
Subject: [PATCH 18/41] net/tls: Don't recursively call push_record during
 tls_write_space callbacks

[ Upstream commit c212d2c7fc4736d49be102fb7a1a545cdc2f1fea ]

It is reported that in some cases, write_space may be called in
do_tcp_sendpages, such that we recursively invoke do_tcp_sendpages again:

[  660.468802]  ? do_tcp_sendpages+0x8d/0x580
[  660.468826]  ? tls_push_sg+0x74/0x130 [tls]
[  660.468852]  ? tls_push_record+0x24a/0x390 [tls]
[  660.468880]  ? tls_write_space+0x6a/0x80 [tls]
...

tls_push_sg already does a loop over all sending sg's, so ignore
any tls_write_space notifications until we are done sending.
We then have to call the previous write_space to wake up
poll() waiters after we are done with the send loop.

Reported-by: Andre Tomt <andre@tomt.net>
Signed-off-by: Dave Watson <davejwatson@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h  | 1 +
 net/tls/tls_main.c | 7 +++++++
 2 files changed, 8 insertions(+)

diff --git a/include/net/tls.h b/include/net/tls.h
index df950383b8c1..48940a883d9a 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -98,6 +98,7 @@ struct tls_context {
 	struct scatterlist *partially_sent_record;
 	u16 partially_sent_offset;
 	unsigned long flags;
+	bool in_tcp_sendpages;
 
 	u16 pending_open_record_frags;
 	int (*push_pending_record)(struct sock *sk, int flags);
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 282361ac0263..c314a66873da 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -87,6 +87,7 @@ int tls_push_sg(struct sock *sk,
 	size = sg->length - offset;
 	offset += sg->offset;
 
+	ctx->in_tcp_sendpages = true;
 	while (1) {
 		if (sg_is_last(sg))
 			sendpage_flags = flags;
@@ -121,6 +122,8 @@ int tls_push_sg(struct sock *sk,
 	}
 
 	clear_bit(TLS_PENDING_CLOSED_RECORD, &ctx->flags);
+	ctx->in_tcp_sendpages = false;
+	ctx->sk_write_space(sk);
 
 	return 0;
 }
@@ -190,6 +193,10 @@ static void tls_write_space(struct sock *sk)
 {
 	struct tls_context *ctx = tls_get_ctx(sk);
 
+	/* We are already sending pages, ignore notification */
+	if (ctx->in_tcp_sendpages)
+		return;
+
 	if (!sk->sk_write_pending && tls_is_pending_closed_record(ctx)) {
 		gfp_t sk_allocation = sk->sk_allocation;
 		int rc;
-- 
2.14.3


From 320117cb975bfc59ecbc78b0b227b6e90467c800 Mon Sep 17 00:00:00 2001
From: Andre Tomt <andre@tomt.net>
Date: Mon, 7 May 2018 04:24:39 +0200
Subject: [PATCH 19/41] net/tls: Fix connection stall on partial tls record

[ Upstream commit 080324c36ade319f57e505633ab54f6f53289b45 ]

In the case of writing a partial tls record we forgot to clear the
ctx->in_tcp_sendpages flag, causing some connections to stall.

Fixes: c212d2c7fc47 ("net/tls: Don't recursively call push_record during tls_write_space callbacks")
Signed-off-by: Andre Tomt <andre@tomt.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index c314a66873da..dfef930d1e50 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -108,6 +108,7 @@ int tls_push_sg(struct sock *sk,
 			offset -= sg->offset;
 			ctx->partially_sent_offset = offset;
 			ctx->partially_sent_record = (void *)sg;
+			ctx->in_tcp_sendpages = false;
 			return ret;
 		}
 
-- 
2.14.3


From 3afdb1b1140424368471328036cbd1bc2324ee4d Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Thu, 3 May 2018 18:13:25 +0200
Subject: [PATCH 20/41] openvswitch: Don't swap table in nlattr_set() after
 OVS_ATTR_NESTED is found

[ Upstream commit 72f17baf2352ded6a1d3f4bb2d15da8c678cd2cb ]

If an OVS_ATTR_NESTED attribute type is found while walking
through netlink attributes, we call nlattr_set() recursively
passing the length table for the following nested attributes, if
different from the current one.

However, once we're done with those sub-nested attributes, we
should continue walking through attributes using the current
table, instead of using the one related to the sub-nested
attributes.

For example, given this sequence:

1  OVS_KEY_ATTR_PRIORITY
2  OVS_KEY_ATTR_TUNNEL
3	OVS_TUNNEL_KEY_ATTR_ID
4	OVS_TUNNEL_KEY_ATTR_IPV4_SRC
5	OVS_TUNNEL_KEY_ATTR_IPV4_DST
6	OVS_TUNNEL_KEY_ATTR_TTL
7	OVS_TUNNEL_KEY_ATTR_TP_SRC
8	OVS_TUNNEL_KEY_ATTR_TP_DST
9  OVS_KEY_ATTR_IN_PORT
10 OVS_KEY_ATTR_SKB_MARK
11 OVS_KEY_ATTR_MPLS

we switch to the 'ovs_tunnel_key_lens' table on attribute #3,
and we don't switch back to 'ovs_key_lens' while setting
attributes #9 to #11 in the sequence. As OVS_KEY_ATTR_MPLS
evaluates to 21, and the array size of 'ovs_tunnel_key_lens' is
15, we also get this kind of KASan splat while accessing the
wrong table:

[ 7654.586496] ==================================================================
[ 7654.594573] BUG: KASAN: global-out-of-bounds in nlattr_set+0x164/0xde9 [openvswitch]
[ 7654.603214] Read of size 4 at addr ffffffffc169ecf0 by task handler29/87430
[ 7654.610983]
[ 7654.612644] CPU: 21 PID: 87430 Comm: handler29 Kdump: loaded Not tainted 3.10.0-866.el7.test.x86_64 #1
[ 7654.623030] Hardware name: Dell Inc. PowerEdge R730/072T6D, BIOS 2.1.7 06/16/2016
[ 7654.631379] Call Trace:
[ 7654.634108]  [<ffffffffb65a7c50>] dump_stack+0x19/0x1b
[ 7654.639843]  [<ffffffffb53ff373>] print_address_description+0x33/0x290
[ 7654.647129]  [<ffffffffc169b37b>] ? nlattr_set+0x164/0xde9 [openvswitch]
[ 7654.654607]  [<ffffffffb53ff812>] kasan_report.part.3+0x242/0x330
[ 7654.661406]  [<ffffffffb53ff9b4>] __asan_report_load4_noabort+0x34/0x40
[ 7654.668789]  [<ffffffffc169b37b>] nlattr_set+0x164/0xde9 [openvswitch]
[ 7654.676076]  [<ffffffffc167ef68>] ovs_nla_get_match+0x10c8/0x1900 [openvswitch]
[ 7654.684234]  [<ffffffffb61e9cc8>] ? genl_rcv+0x28/0x40
[ 7654.689968]  [<ffffffffb61e7733>] ? netlink_unicast+0x3f3/0x590
[ 7654.696574]  [<ffffffffc167dea0>] ? ovs_nla_put_tunnel_info+0xb0/0xb0 [openvswitch]
[ 7654.705122]  [<ffffffffb4f41b50>] ? unwind_get_return_address+0xb0/0xb0
[ 7654.712503]  [<ffffffffb65d9355>] ? system_call_fastpath+0x1c/0x21
[ 7654.719401]  [<ffffffffb4f41d79>] ? update_stack_state+0x229/0x370
[ 7654.726298]  [<ffffffffb4f41d79>] ? update_stack_state+0x229/0x370
[ 7654.733195]  [<ffffffffb53fe4b5>] ? kasan_unpoison_shadow+0x35/0x50
[ 7654.740187]  [<ffffffffb53fe62a>] ? kasan_kmalloc+0xaa/0xe0
[ 7654.746406]  [<ffffffffb53fec32>] ? kasan_slab_alloc+0x12/0x20
[ 7654.752914]  [<ffffffffb53fe711>] ? memset+0x31/0x40
[ 7654.758456]  [<ffffffffc165bf92>] ovs_flow_cmd_new+0x2b2/0xf00 [openvswitch]

[snip]

[ 7655.132484] The buggy address belongs to the variable:
[ 7655.138226]  ovs_tunnel_key_lens+0xf0/0xffffffffffffd400 [openvswitch]
[ 7655.145507]
[ 7655.147166] Memory state around the buggy address:
[ 7655.152514]  ffffffffc169eb80: 00 00 00 00 00 00 00 00 00 00 fa fa fa fa fa fa
[ 7655.160585]  ffffffffc169ec00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[ 7655.168644] >ffffffffc169ec80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 fa fa
[ 7655.176701]                                                              ^
[ 7655.184372]  ffffffffc169ed00: fa fa fa fa 00 00 00 00 fa fa fa fa 00 00 00 05
[ 7655.192431]  ffffffffc169ed80: fa fa fa fa 00 00 00 00 00 00 00 00 00 00 00 00
[ 7655.200490] ==================================================================

Reported-by: Hangbin Liu <liuhangbin@gmail.com>
Fixes: 982b52700482 ("openvswitch: Fix mask generation for nested attributes.")
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/flow_netlink.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 0d9f6afa266c..4c9c9458374a 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -1404,13 +1404,10 @@ static void nlattr_set(struct nlattr *attr, u8 val,
 
 	/* The nlattr stream should already have been validated */
 	nla_for_each_nested(nla, attr, rem) {
-		if (tbl[nla_type(nla)].len == OVS_ATTR_NESTED) {
-			if (tbl[nla_type(nla)].next)
-				tbl = tbl[nla_type(nla)].next;
-			nlattr_set(nla, val, tbl);
-		} else {
+		if (tbl[nla_type(nla)].len == OVS_ATTR_NESTED)
+			nlattr_set(nla, val, tbl[nla_type(nla)].next ? : tbl);
+		else
 			memset(nla_data(nla), val, nla_len(nla));
-		}
 
 		if (nla_type(nla) == OVS_KEY_ATTR_CT_STATE)
 			*(u32 *)nla_data(nla) &= CT_SUPPORTED_MASK;
-- 
2.14.3


From 8afba72a686453183a9a1612b91c3cc26a75eb88 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Wed, 2 May 2018 22:22:54 +0200
Subject: [PATCH 21/41] qmi_wwan: do not steal interfaces from class drivers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 5697db4a696c41601a1d15c1922150b4dbf5726c ]

The USB_DEVICE_INTERFACE_NUMBER matching macro assumes that
the { vendorid, productid, interfacenumber } set uniquely
identifies one specific function.  This has proven to fail
for some configurable devices. One example is the Quectel
EM06/EP06 where the same interface number can be either
QMI or MBIM, without the device ID changing either.

Fix by requiring the vendor-specific class for interface number
based matching.  Functions of other classes can and should use
class based matching instead.

Fixes: 03304bcb5ec4 ("net: qmi_wwan: use fixed interface number matching")
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 1aad0568dcc6..2f828eb9ace6 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1338,6 +1338,18 @@ static int qmi_wwan_probe(struct usb_interface *intf,
 		id->driver_info = (unsigned long)&qmi_wwan_info;
 	}
 
+	/* There are devices where the same interface number can be
+	 * configured as different functions. We should only bind to
+	 * vendor specific functions when matching on interface number
+	 */
+	if (id->match_flags & USB_DEVICE_ID_MATCH_INT_NUMBER &&
+	    desc->bInterfaceClass != USB_CLASS_VENDOR_SPEC) {
+		dev_dbg(&intf->dev,
+			"Rejecting interface number match for class %02x\n",
+			desc->bInterfaceClass);
+		return -ENODEV;
+	}
+
 	/* Quectel EC20 quirk where we've QMI on interface 4 instead of 0 */
 	if (quectel_ec20_detected(intf) && desc->bInterfaceNumber == 0) {
 		dev_dbg(&intf->dev, "Quectel EC20 quirk, skipping interface 0\n");
-- 
2.14.3


From 0287e3ef12b8dc748daf97f66dfb7f10e8df8629 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 7 May 2018 21:11:21 +0200
Subject: [PATCH 22/41] r8169: fix powering up RTL8168h

[ Upstream commit 3148dedfe79e422f448a10250d3e2cdf8b7ee617 ]

Since commit a92a08499b1f "r8169: improve runtime pm in general and
suspend unused ports" interfaces w/o link are runtime-suspended after
10s. On systems where drivers take longer to load this can lead to the
situation that the interface is runtime-suspended already when it's
initially brought up.
This shouldn't be a problem because rtl_open() resumes MAC/PHY.
However with at least one chip version the interface doesn't properly
come up, as reported here:
https://bugzilla.kernel.org/show_bug.cgi?id=199549

The vendor driver uses a delay to give certain chip versions some
time to resume before starting the PHY configuration. So let's do
the same. I don't know which chip versions may be affected,
therefore apply this delay always.

This patch was reported to fix the issue for RTL8168h.
I was able to reproduce the issue on an Asus H310I-Plus which also
uses a RTL8168h. Also in my case the patch fixed the issue.

Reported-by: Slava Kardakov <ojab@ojab.ru>
Tested-by: Slava Kardakov <ojab@ojab.ru>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index db553d4e8d22..b98fcc9e93e5 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -4886,6 +4886,9 @@ static void rtl_pll_power_down(struct rtl8169_private *tp)
 static void rtl_pll_power_up(struct rtl8169_private *tp)
 {
 	rtl_generic_op(tp, tp->pll_power_ops.up);
+
+	/* give MAC/PHY some time to resume */
+	msleep(20);
 }
 
 static void rtl_init_pll_power_ops(struct rtl8169_private *tp)
-- 
2.14.3


From a04a0c18eeeb724c4df4ed4962483f00cbfd0fce Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 2 May 2018 14:53:39 -0700
Subject: [PATCH 23/41] rds: do not leak kernel memory to user land

[ Upstream commit eb80ca476ec11f67a62691a93604b405ffc7d80c ]

syzbot/KMSAN reported an uninit-value in put_cmsg(), originating
from rds_cmsg_recv().

Simply clear the structure, since we have holes there, or since
rx_traces might be smaller than RDS_MSG_RX_DGRAM_TRACE_MAX.

BUG: KMSAN: uninit-value in copy_to_user include/linux/uaccess.h:184 [inline]
BUG: KMSAN: uninit-value in put_cmsg+0x600/0x870 net/core/scm.c:242
CPU: 0 PID: 4459 Comm: syz-executor582 Not tainted 4.16.0+ #87
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x185/0x1d0 lib/dump_stack.c:53
 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067
 kmsan_internal_check_memory+0x135/0x1e0 mm/kmsan/kmsan.c:1157
 kmsan_copy_to_user+0x69/0x160 mm/kmsan/kmsan.c:1199
 copy_to_user include/linux/uaccess.h:184 [inline]
 put_cmsg+0x600/0x870 net/core/scm.c:242
 rds_cmsg_recv net/rds/recv.c:570 [inline]
 rds_recvmsg+0x2db5/0x3170 net/rds/recv.c:657
 sock_recvmsg_nosec net/socket.c:803 [inline]
 sock_recvmsg+0x1d0/0x230 net/socket.c:810
 ___sys_recvmsg+0x3fb/0x810 net/socket.c:2205
 __sys_recvmsg net/socket.c:2250 [inline]
 SYSC_recvmsg+0x298/0x3c0 net/socket.c:2262
 SyS_recvmsg+0x54/0x80 net/socket.c:2257
 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x3d/0xa2

Fixes: 3289025aedc0 ("RDS: add receive message trace used by application")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Cc: linux-rdma <linux-rdma@vger.kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/recv.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/rds/recv.c b/net/rds/recv.c
index b25bcfe411ca..555f07ccf0dc 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -558,6 +558,7 @@ static int rds_cmsg_recv(struct rds_incoming *inc, struct msghdr *msg,
 		struct rds_cmsg_rx_trace t;
 		int i, j;
 
+		memset(&t, 0, sizeof(t));
 		inc->i_rx_lat_trace[RDS_MSG_RX_CMSG] = local_clock();
 		t.rx_traces =  rs->rs_rx_traces;
 		for (i = 0; i < rs->rs_rx_traces; i++) {
-- 
2.14.3


From efafeba7f554dc9392e91d7754fd21f736cf19d9 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sat, 5 May 2018 14:59:47 +0800
Subject: [PATCH 24/41] sctp: delay the authentication for the duplicated
 cookie-echo chunk

[ Upstream commit 59d8d4434f429b4fa8a346fd889058bda427a837 ]

Now sctp only delays the authentication for the normal cookie-echo
chunk by setting chunk->auth_chunk in sctp_endpoint_bh_rcv(). But
for the duplicated one with auth, in sctp_assoc_bh_rcv(), it does
authentication first based on the old asoc, which will definitely
fail due to the different auth info in the old asoc.

The duplicated cookie-echo chunk will create a new asoc with the
auth info from this chunk, and the authentication should also be
done with the new asoc's auth info for all of the collision 'A',
'B' and 'D'. Otherwise, the duplicated cookie-echo chunk with auth
will never pass the authentication and create the new connection.

This issue exists since very beginning, and this fix is to make
sctp_assoc_bh_rcv() follow the way sctp_endpoint_bh_rcv() does
for the normal cookie-echo chunk to delay the authentication.

While at it, remove the unused params from sctp_sf_authenticate()
and define sctp_auth_chunk_verify() used for all the places that
do the delayed authentication.

v1->v2:
  fix the typo in changelog as Marcelo noticed.

Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/associola.c    | 30 ++++++++++++++++-
 net/sctp/sm_statefuns.c | 86 ++++++++++++++++++++++++++-----------------------
 2 files changed, 75 insertions(+), 41 deletions(-)

diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index dfb9651e818b..58f7d8cfd748 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -1025,8 +1025,9 @@ static void sctp_assoc_bh_rcv(struct work_struct *work)
 	struct sctp_endpoint *ep;
 	struct sctp_chunk *chunk;
 	struct sctp_inq *inqueue;
-	int state;
+	int first_time = 1;	/* is this the first time through the loop */
 	int error = 0;
+	int state;
 
 	/* The association should be held so we should be safe. */
 	ep = asoc->ep;
@@ -1037,6 +1038,30 @@ static void sctp_assoc_bh_rcv(struct work_struct *work)
 		state = asoc->state;
 		subtype = SCTP_ST_CHUNK(chunk->chunk_hdr->type);
 
+		/* If the first chunk in the packet is AUTH, do special
+		 * processing specified in Section 6.3 of SCTP-AUTH spec
+		 */
+		if (first_time && subtype.chunk == SCTP_CID_AUTH) {
+			struct sctp_chunkhdr *next_hdr;
+
+			next_hdr = sctp_inq_peek(inqueue);
+			if (!next_hdr)
+				goto normal;
+
+			/* If the next chunk is COOKIE-ECHO, skip the AUTH
+			 * chunk while saving a pointer to it so we can do
+			 * Authentication later (during cookie-echo
+			 * processing).
+			 */
+			if (next_hdr->type == SCTP_CID_COOKIE_ECHO) {
+				chunk->auth_chunk = skb_clone(chunk->skb,
+							      GFP_ATOMIC);
+				chunk->auth = 1;
+				continue;
+			}
+		}
+
+normal:
 		/* SCTP-AUTH, Section 6.3:
 		 *    The receiver has a list of chunk types which it expects
 		 *    to be received only after an AUTH-chunk.  This list has
@@ -1075,6 +1100,9 @@ static void sctp_assoc_bh_rcv(struct work_struct *work)
 		/* If there is an error on chunk, discard this packet. */
 		if (error && chunk)
 			chunk->pdiscard = 1;
+
+		if (first_time)
+			first_time = 0;
 	}
 	sctp_association_put(asoc);
 }
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 8f8ccded13e4..799aae757444 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -150,10 +150,7 @@ static enum sctp_disposition sctp_sf_violation_chunk(
 					struct sctp_cmd_seq *commands);
 
 static enum sctp_ierror sctp_sf_authenticate(
-					struct net *net,
-					const struct sctp_endpoint *ep,
 					const struct sctp_association *asoc,
-					const union sctp_subtype type,
 					struct sctp_chunk *chunk);
 
 static enum sctp_disposition __sctp_sf_do_9_1_abort(
@@ -618,6 +615,38 @@ enum sctp_disposition sctp_sf_do_5_1C_ack(struct net *net,
 	return SCTP_DISPOSITION_CONSUME;
 }
 
+static bool sctp_auth_chunk_verify(struct net *net, struct sctp_chunk *chunk,
+				   const struct sctp_association *asoc)
+{
+	struct sctp_chunk auth;
+
+	if (!chunk->auth_chunk)
+		return true;
+
+	/* SCTP-AUTH:  auth_chunk pointer is only set when the cookie-echo
+	 * is supposed to be authenticated and we have to do delayed
+	 * authentication.  We've just recreated the association using
+	 * the information in the cookie and now it's much easier to
+	 * do the authentication.
+	 */
+
+	/* Make sure that we and the peer are AUTH capable */
+	if (!net->sctp.auth_enable || !asoc->peer.auth_capable)
+		return false;
+
+	/* set-up our fake chunk so that we can process it */
+	auth.skb = chunk->auth_chunk;
+	auth.asoc = chunk->asoc;
+	auth.sctp_hdr = chunk->sctp_hdr;
+	auth.chunk_hdr = (struct sctp_chunkhdr *)
+				skb_push(chunk->auth_chunk,
+					 sizeof(struct sctp_chunkhdr));
+	skb_pull(chunk->auth_chunk, sizeof(struct sctp_chunkhdr));
+	auth.transport = chunk->transport;
+
+	return sctp_sf_authenticate(asoc, &auth) == SCTP_IERROR_NO_ERROR;
+}
+
 /*
  * Respond to a normal COOKIE ECHO chunk.
  * We are the side that is being asked for an association.
@@ -755,37 +784,9 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net,
 	if (error)
 		goto nomem_init;
 
-	/* SCTP-AUTH:  auth_chunk pointer is only set when the cookie-echo
-	 * is supposed to be authenticated and we have to do delayed
-	 * authentication.  We've just recreated the association using
-	 * the information in the cookie and now it's much easier to
-	 * do the authentication.
-	 */
-	if (chunk->auth_chunk) {
-		struct sctp_chunk auth;
-		enum sctp_ierror ret;
-
-		/* Make sure that we and the peer are AUTH capable */
-		if (!net->sctp.auth_enable || !new_asoc->peer.auth_capable) {
-			sctp_association_free(new_asoc);
-			return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
-		}
-
-		/* set-up our fake chunk so that we can process it */
-		auth.skb = chunk->auth_chunk;
-		auth.asoc = chunk->asoc;
-		auth.sctp_hdr = chunk->sctp_hdr;
-		auth.chunk_hdr = (struct sctp_chunkhdr *)
-					skb_push(chunk->auth_chunk,
-						 sizeof(struct sctp_chunkhdr));
-		skb_pull(chunk->auth_chunk, sizeof(struct sctp_chunkhdr));
-		auth.transport = chunk->transport;
-
-		ret = sctp_sf_authenticate(net, ep, new_asoc, type, &auth);
-		if (ret != SCTP_IERROR_NO_ERROR) {
-			sctp_association_free(new_asoc);
-			return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
-		}
+	if (!sctp_auth_chunk_verify(net, chunk, new_asoc)) {
+		sctp_association_free(new_asoc);
+		return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
 	}
 
 	repl = sctp_make_cookie_ack(new_asoc, chunk);
@@ -1755,13 +1756,15 @@ static enum sctp_disposition sctp_sf_do_dupcook_a(
 			       GFP_ATOMIC))
 		goto nomem;
 
+	if (!sctp_auth_chunk_verify(net, chunk, new_asoc))
+		return SCTP_DISPOSITION_DISCARD;
+
 	/* Make sure no new addresses are being added during the
 	 * restart.  Though this is a pretty complicated attack
 	 * since you'd have to get inside the cookie.
 	 */
-	if (!sctp_sf_check_restart_addrs(new_asoc, asoc, chunk, commands)) {
+	if (!sctp_sf_check_restart_addrs(new_asoc, asoc, chunk, commands))
 		return SCTP_DISPOSITION_CONSUME;
-	}
 
 	/* If the endpoint is in the SHUTDOWN-ACK-SENT state and recognizes
 	 * the peer has restarted (Action A), it MUST NOT setup a new
@@ -1867,6 +1870,9 @@ static enum sctp_disposition sctp_sf_do_dupcook_b(
 			       GFP_ATOMIC))
 		goto nomem;
 
+	if (!sctp_auth_chunk_verify(net, chunk, new_asoc))
+		return SCTP_DISPOSITION_DISCARD;
+
 	/* Update the content of current association.  */
 	sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc));
 	sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE,
@@ -1961,6 +1967,9 @@ static enum sctp_disposition sctp_sf_do_dupcook_d(
 	 * a COOKIE ACK.
 	 */
 
+	if (!sctp_auth_chunk_verify(net, chunk, asoc))
+		return SCTP_DISPOSITION_DISCARD;
+
 	/* Don't accidentally move back into established state. */
 	if (asoc->state < SCTP_STATE_ESTABLISHED) {
 		sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP,
@@ -4111,10 +4120,7 @@ enum sctp_disposition sctp_sf_eat_fwd_tsn_fast(
  * The return value is the disposition of the chunk.
  */
 static enum sctp_ierror sctp_sf_authenticate(
-					struct net *net,
-					const struct sctp_endpoint *ep,
 					const struct sctp_association *asoc,
-					const union sctp_subtype type,
 					struct sctp_chunk *chunk)
 {
 	struct sctp_authhdr *auth_hdr;
@@ -4212,7 +4218,7 @@ enum sctp_disposition sctp_sf_eat_auth(struct net *net,
 						  commands);
 
 	auth_hdr = (struct sctp_authhdr *)chunk->skb->data;
-	error = sctp_sf_authenticate(net, ep, asoc, type, chunk);
+	error = sctp_sf_authenticate(asoc, chunk);
 	switch (error) {
 	case SCTP_IERROR_AUTH_BAD_HMAC:
 		/* Generate the ERROR chunk and discard the rest
-- 
2.14.3


From 44d4b4c4a0f47de579fa6c094d4e6baa6f9c3366 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 2 May 2018 13:45:12 +0800
Subject: [PATCH 25/41] sctp: fix the issue that the cookie-ack with auth can't
 get processed

[ Upstream commit ce402f044e4e432c296f90eaabb8dbe8f3624391 ]

When auth is enabled for cookie-ack chunk, in sctp_inq_pop, sctp
processes auth chunk first, then continues to the next chunk in
this packet if chunk_end + chunk_hdr size < skb_tail_pointer().
Otherwise, it will go to the next packet or discard this chunk.

However, it missed the fact that cookie-ack chunk's size is equal
to chunk_hdr size, which couldn't match that check, and thus this
chunk would not get processed.

This patch fixes it by changing the check to chunk_end + chunk_hdr
size <= skb_tail_pointer().

Fixes: 26b87c788100 ("net: sctp: fix remote memory pressure from excessive queueing")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/inqueue.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c
index 48392552ee7c..1aa89d4682f4 100644
--- a/net/sctp/inqueue.c
+++ b/net/sctp/inqueue.c
@@ -217,7 +217,7 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue)
 	skb_pull(chunk->skb, sizeof(*ch));
 	chunk->subh.v = NULL; /* Subheader is no longer valid.  */
 
-	if (chunk->chunk_end + sizeof(*ch) < skb_tail_pointer(chunk->skb)) {
+	if (chunk->chunk_end + sizeof(*ch) <= skb_tail_pointer(chunk->skb)) {
 		/* This is not a singleton */
 		chunk->singleton = 0;
 	} else if (chunk->chunk_end > skb_tail_pointer(chunk->skb)) {
-- 
2.14.3


From 17b80acd45e01499b94e547c83f1891d8fc5496b Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 26 Apr 2018 14:13:57 +0800
Subject: [PATCH 26/41] sctp: handle two v4 addrs comparison in
 sctp_inet6_cmp_addr

[ Upstream commit d625329b06e46bd20baf9ee40847d11982569204 ]

Since sctp ipv6 socket also supports v4 addrs, it's possible to
compare two v4 addrs in pf v6 .cmp_addr, sctp_inet6_cmp_addr.

However after Commit 1071ec9d453a ("sctp: do not check port in
sctp_inet6_cmp_addr"), it no longer calls af1->cmp_addr, which
in this case is sctp_v4_cmp_addr, but calls __sctp_v6_cmp_addr
where it handles them as two v6 addrs. It would cause a out of
bounds crash.

syzbot found this crash when trying to bind two v4 addrs to a
v6 socket.

This patch fixes it by adding the process for two v4 addrs in
sctp_inet6_cmp_addr.

Fixes: 1071ec9d453a ("sctp: do not check port in sctp_inet6_cmp_addr")
Reported-by: syzbot+cd494c1dd681d4d93ebb@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ipv6.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 7219a1c041f7..853fecdf6374 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -865,6 +865,9 @@ static int sctp_inet6_cmp_addr(const union sctp_addr *addr1,
 	if (sctp_is_any(sk, addr1) || sctp_is_any(sk, addr2))
 		return 1;
 
+	if (addr1->sa.sa_family == AF_INET && addr2->sa.sa_family == AF_INET)
+		return addr1->v4.sin_addr.s_addr == addr2->v4.sin_addr.s_addr;
+
 	return __sctp_v6_cmp_addr(addr1, addr2);
 }
 
-- 
2.14.3


From e1a35ea881e60642ab430c03b3feb1f859f16292 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 10 May 2018 17:34:13 +0800
Subject: [PATCH 27/41] sctp: remove sctp_chunk_put from fail_mark err path in
 sctp_ulpevent_make_rcvmsg

[ Upstream commit 6910e25de2257e2c82c7a2d126e3463cd8e50810 ]

In Commit 1f45f78f8e51 ("sctp: allow GSO frags to access the chunk too"),
it held the chunk in sctp_ulpevent_make_rcvmsg to access it safely later
in recvmsg. However, it also added sctp_chunk_put in fail_mark err path,
which is only triggered before holding the chunk.

syzbot reported a use-after-free crash happened on this err path, where
it shouldn't call sctp_chunk_put.

This patch simply removes this call.

Fixes: 1f45f78f8e51 ("sctp: allow GSO frags to access the chunk too")
Reported-by: syzbot+141d898c5f24489db4aa@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ulpevent.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c
index 5447228bf1a0..8538c96c96c1 100644
--- a/net/sctp/ulpevent.c
+++ b/net/sctp/ulpevent.c
@@ -717,7 +717,6 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc,
 	return event;
 
 fail_mark:
-	sctp_chunk_put(chunk);
 	kfree_skb(skb);
 fail:
 	return NULL;
-- 
2.14.3


From efa1a4ddc6673a3fee8d60875e51938cf97b4988 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 2 May 2018 13:39:46 +0800
Subject: [PATCH 28/41] sctp: use the old asoc when making the cookie-ack chunk
 in dupcook_d

[ Upstream commit 46e16d4b956867013e0bbd7f2bad206f4aa55752 ]

When processing a duplicate cookie-echo chunk, for case 'D', sctp will
not process the param from this chunk. It means old asoc has nothing
to be updated, and the new temp asoc doesn't have the complete info.

So there's no reason to use the new asoc when creating the cookie-ack
chunk. Otherwise, like when auth is enabled for cookie-ack, the chunk
can not be set with auth, and it will definitely be dropped by peer.

This issue is there since very beginning, and we fix it by using the
old asoc instead.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sm_statefuns.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 799aae757444..01b078172306 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -2009,7 +2009,7 @@ static enum sctp_disposition sctp_sf_do_dupcook_d(
 		}
 	}
 
-	repl = sctp_make_cookie_ack(new_asoc, chunk);
+	repl = sctp_make_cookie_ack(asoc, chunk);
 	if (!repl)
 		goto nomem;
 
-- 
2.14.3


From 277d0b7afef45965fa965e60b942dc87d816dbf6 Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Tue, 1 May 2018 21:45:41 -0400
Subject: [PATCH 29/41] tcp_bbr: fix to zero idle_restart only upon S/ACKed
 data

[ Upstream commit e6e6a278b1eaffa19d42186bfacd1ffc15a50b3f ]

Previously the bbr->idle_restart tracking was zeroing out the
bbr->idle_restart bit upon ACKs that did not SACK or ACK anything,
e.g. receiving incoming data or receiver window updates. In such
situations BBR would forget that this was a restart-from-idle
situation, and if the min_rtt had expired it would unnecessarily enter
PROBE_RTT (even though we were actually restarting from idle but had
merely forgotten that fact).

The fix is simple: we need to remember we are restarting from idle
until we receive a S/ACK for some data (a S/ACK for the first flight
of data we send as we are restarting).

This commit is a stable candidate for kernels back as far as 4.9.

Fixes: 0f8782ea1497 ("tcp_bbr: add BBR congestion control")
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: Priyaranjan Jha <priyarjha@google.com>
Signed-off-by: Yousuk Seung <ysseung@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_bbr.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 25c5a0b60cfc..9a0b952dd09b 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -802,7 +802,9 @@ static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs)
 			}
 		}
 	}
-	bbr->idle_restart = 0;
+	/* Restart after idle ends only once we process a new S/ACK for data */
+	if (rs->delivered > 0)
+		bbr->idle_restart = 0;
 }
 
 static void bbr_update_model(struct sock *sk, const struct rate_sample *rs)
-- 
2.14.3


From ec2df6c809d37daa94f2709e5ebf83abbb944285 Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Wed, 25 Apr 2018 11:33:08 -0700
Subject: [PATCH 30/41] tcp: ignore Fast Open on repair mode

[ Upstream commit 16ae6aa1705299789f71fdea59bfb119c1fbd9c0 ]

The TCP repair sequence of operation is to first set the socket in
repair mode, then inject the TCP stats into the socket with repair
socket options, then call connect() to re-activate the socket. The
connect syscall simply returns and set state to ESTABLISHED
mode. As a result Fast Open is meaningless for TCP repair.

However allowing sendto() system call with MSG_FASTOPEN flag half-way
during the repair operation could unexpectedly cause data to be
sent, before the operation finishes changing the internal TCP stats
(e.g. MSS).  This in turn triggers TCP warnings on inconsistent
packet accounting.

The fix is to simply disallow Fast Open operation once the socket
is in the repair mode.

Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index d023f879e7bb..f763fa824a93 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1194,7 +1194,8 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 			uarg->zerocopy = 0;
 	}
 
-	if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect)) {
+	if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect) &&
+	    !tp->repair) {
 		err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size);
 		if (err == -EINPROGRESS && copied_syn > 0)
 			goto out;
-- 
2.14.3


From 9ecf9a8a312649fd7dc57429d0f43622e7dc56ea Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Thu, 3 May 2018 20:04:27 -0400
Subject: [PATCH 31/41] tg3: Fix vunmap() BUG_ON() triggered from
 tg3_free_consistent().

[ Upstream commit d89a2adb8bfe6f8949ff389acdb9fa298b6e8e12 ]

tg3_free_consistent() calls dma_free_coherent() to free tp->hw_stats
under spinlock and can trigger BUG_ON() in vunmap() because vunmap()
may sleep.  Fix it by removing the spinlock and relying on the
TG3_FLAG_INIT_COMPLETE flag to prevent race conditions between
tg3_get_stats64() and tg3_free_consistent().  TG3_FLAG_INIT_COMPLETE
is always cleared under tp->lock before tg3_free_consistent()
and therefore tg3_get_stats64() can safely access tp->hw_stats
under tp->lock if TG3_FLAG_INIT_COMPLETE is set.

Fixes: f5992b72ebe0 ("tg3: Fix race condition in tg3_get_stats64().")
Reported-by: Zumeng Chen <zumeng.chen@gmail.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/tg3.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 48738eb27806..9a8ef630466f 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -8723,14 +8723,15 @@ static void tg3_free_consistent(struct tg3 *tp)
 	tg3_mem_rx_release(tp);
 	tg3_mem_tx_release(tp);
 
-	/* Protect tg3_get_stats64() from reading freed tp->hw_stats. */
-	tg3_full_lock(tp, 0);
+	/* tp->hw_stats can be referenced safely:
+	 *     1. under rtnl_lock
+	 *     2. or under tp->lock if TG3_FLAG_INIT_COMPLETE is set.
+	 */
 	if (tp->hw_stats) {
 		dma_free_coherent(&tp->pdev->dev, sizeof(struct tg3_hw_stats),
 				  tp->hw_stats, tp->stats_mapping);
 		tp->hw_stats = NULL;
 	}
-	tg3_full_unlock(tp);
 }
 
 /*
@@ -14167,7 +14168,7 @@ static void tg3_get_stats64(struct net_device *dev,
 	struct tg3 *tp = netdev_priv(dev);
 
 	spin_lock_bh(&tp->lock);
-	if (!tp->hw_stats) {
+	if (!tp->hw_stats || !tg3_flag(tp, INIT_COMPLETE)) {
 		*stats = tp->net_stats_prev;
 		spin_unlock_bh(&tp->lock);
 		return;
-- 
2.14.3


From 4486b8855744df9da293ff8b550320a7cab9c988 Mon Sep 17 00:00:00 2001
From: Debabrata Banerjee <dbanerje@akamai.com>
Date: Wed, 9 May 2018 19:32:10 -0400
Subject: [PATCH 32/41] bonding: do not allow rlb updates to invalid mac

[ Upstream commit 4fa8667ca3989ce14cf66301fa251544fbddbdd0 ]

Make sure multicast, broadcast, and zero mac's cannot be the output of rlb
updates, which should all be directed arps. Receive load balancing will be
collapsed if any of these happen, as the switch will broadcast.

Signed-off-by: Debabrata Banerjee <dbanerje@akamai.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_alb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index c02cc817a490..6dc804e11852 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -450,7 +450,7 @@ static void rlb_update_client(struct rlb_client_info *client_info)
 {
 	int i;
 
-	if (!client_info->slave)
+	if (!client_info->slave || !is_valid_ether_addr(client_info->mac_dst))
 		return;
 
 	for (i = 0; i < RLB_ARP_BURST_SIZE; i++) {
-- 
2.14.3


From a9a4037ea278ebeb6773eaf5cff67c0382105672 Mon Sep 17 00:00:00 2001
From: Debabrata Banerjee <dbanerje@akamai.com>
Date: Wed, 9 May 2018 19:32:11 -0400
Subject: [PATCH 33/41] bonding: send learning packets for vlans on slave

[ Upstream commit 21706ee8a47d3ede7fdae0be6d7c0a0e31a83229 ]

There was a regression at some point from the intended functionality of
commit f60c3704e87d ("bonding: Fix alb mode to only use first level
vlans.")

Given the return value vlan_get_encap_level() we need to store the nest
level of the bond device, and then compare the vlan's encap level to
this. Without this, this check always fails and learning packets are
never sent.

In addition, this same commit caused a regression in the behavior of
balance_alb, which requires learning packets be sent for all interfaces
using the slave's mac in order to load balance properly. For vlan's
that have not set a user mac, we can send after checking one bit.
Otherwise we need send the set mac, albeit defeating rx load balancing
for that vlan.

Signed-off-by: Debabrata Banerjee <dbanerje@akamai.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_alb.c  | 13 ++++++++-----
 drivers/net/bonding/bond_main.c |  2 ++
 include/net/bonding.h           |  1 +
 3 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 6dc804e11852..60666db31886 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -943,6 +943,10 @@ static void alb_send_lp_vid(struct slave *slave, u8 mac_addr[],
 	skb->priority = TC_PRIO_CONTROL;
 	skb->dev = slave->dev;
 
+	netdev_dbg(slave->bond->dev,
+		   "Send learning packet: dev %s mac %pM vlan %d\n",
+		   slave->dev->name, mac_addr, vid);
+
 	if (vid)
 		__vlan_hwaccel_put_tag(skb, vlan_proto, vid);
 
@@ -965,14 +969,13 @@ static int alb_upper_dev_walk(struct net_device *upper, void *_data)
 	u8 *mac_addr = data->mac_addr;
 	struct bond_vlan_tag *tags;
 
-	if (is_vlan_dev(upper) && vlan_get_encap_level(upper) == 0) {
-		if (strict_match &&
-		    ether_addr_equal_64bits(mac_addr,
-					    upper->dev_addr)) {
+	if (is_vlan_dev(upper) &&
+	    bond->nest_level == vlan_get_encap_level(upper) - 1) {
+		if (upper->addr_assign_type == NET_ADDR_STOLEN) {
 			alb_send_lp_vid(slave, mac_addr,
 					vlan_dev_vlan_proto(upper),
 					vlan_dev_vlan_id(upper));
-		} else if (!strict_match) {
+		} else {
 			alb_send_lp_vid(slave, upper->dev_addr,
 					vlan_dev_vlan_proto(upper),
 					vlan_dev_vlan_id(upper));
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index bf3be2e6d4a8..f0aa57222f17 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1734,6 +1734,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	if (bond_mode_uses_xmit_hash(bond))
 		bond_update_slave_arr(bond, NULL);
 
+	bond->nest_level = dev_get_nest_level(bond_dev);
+
 	netdev_info(bond_dev, "Enslaving %s as %s interface with %s link\n",
 		    slave_dev->name,
 		    bond_is_active_slave(new_slave) ? "an active" : "a backup",
diff --git a/include/net/bonding.h b/include/net/bonding.h
index b2e68657a216..73799da57400 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -198,6 +198,7 @@ struct bonding {
 	struct   slave __rcu *primary_slave;
 	struct   bond_up_slave __rcu *slave_arr; /* Array of usable slaves */
 	bool     force_primary;
+	u32      nest_level;
 	s32      slave_cnt; /* never change this value outside the attach/detach wrappers */
 	int     (*recv_probe)(const struct sk_buff *, struct bonding *,
 			      struct slave *);
-- 
2.14.3


From 1921b5bc9be69f62d9bd6536045fd954cd69640e Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Fri, 11 May 2018 17:45:32 +0200
Subject: [PATCH 34/41] net: sched: fix error path in tcf_proto_create() when
 modules are not configured

[ Upstream commit d68d75fdc34b0253c2bded7ed18cd60eb5a9599b ]

In case modules are not configured, error out when tp->ops is null
and prevent later null pointer dereference.

Fixes: 33a48927c193 ("sched: push TC filter protocol creation into a separate function")
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index c2fab4bcb8be..2f4e1483aced 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -151,8 +151,8 @@ static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol,
 		} else {
 			err = -ENOENT;
 		}
-		goto errout;
 #endif
+		goto errout;
 	}
 	tp->classify = tp->ops->classify;
 	tp->protocol = protocol;
-- 
2.14.3


From 4680417bf30c67c225b35e4c0fd85baa4240a177 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Tue, 20 Mar 2018 18:17:25 +0200
Subject: [PATCH 35/41] net/mlx5e: TX, Use correct counter in dma_map error
 flow

[ Upstream commit d9a96ec362e3da878c378854e25321c85bac52c2 ]

In case of a dma_mapping_error, do not use wi->num_dma
as a parameter for dma unmap function because it's yet
to be set, and holds an out-of-date value.
Use actual value (local variable num_dma) instead.

Fixes: 34802a42b352 ("net/mlx5e: Do not modify the TX SKB")
Fixes: e586b3b0baee ("net/mlx5: Ethernet Datapath files")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index eea7f931cad3..d560047c0bf9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -234,7 +234,7 @@ mlx5e_txwqe_build_dsegs(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		dma_addr = dma_map_single(sq->pdev, skb_data, headlen,
 					  DMA_TO_DEVICE);
 		if (unlikely(dma_mapping_error(sq->pdev, dma_addr)))
-			return -ENOMEM;
+			goto dma_unmap_wqe_err;
 
 		dseg->addr       = cpu_to_be64(dma_addr);
 		dseg->lkey       = sq->mkey_be;
@@ -252,7 +252,7 @@ mlx5e_txwqe_build_dsegs(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		dma_addr = skb_frag_dma_map(sq->pdev, frag, 0, fsz,
 					    DMA_TO_DEVICE);
 		if (unlikely(dma_mapping_error(sq->pdev, dma_addr)))
-			return -ENOMEM;
+			goto dma_unmap_wqe_err;
 
 		dseg->addr       = cpu_to_be64(dma_addr);
 		dseg->lkey       = sq->mkey_be;
@@ -264,6 +264,10 @@ mlx5e_txwqe_build_dsegs(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	}
 
 	return num_dma;
+
+dma_unmap_wqe_err:
+	mlx5e_dma_unmap_wqe_err(sq, num_dma);
+	return -ENOMEM;
 }
 
 static inline void
@@ -355,17 +359,15 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb_data, headlen,
 					  (struct mlx5_wqe_data_seg *)cseg + ds_cnt);
 	if (unlikely(num_dma < 0))
-		goto dma_unmap_wqe_err;
+		goto err_drop;
 
 	mlx5e_txwqe_complete(sq, skb, opcode, ds_cnt + num_dma,
 			     num_bytes, num_dma, wi, cseg);
 
 	return NETDEV_TX_OK;
 
-dma_unmap_wqe_err:
+err_drop:
 	sq->stats.dropped++;
-	mlx5e_dma_unmap_wqe_err(sq, wi->num_dma);
-
 	dev_kfree_skb_any(skb);
 
 	return NETDEV_TX_OK;
@@ -594,17 +596,15 @@ netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb_data, headlen,
 					  (struct mlx5_wqe_data_seg *)cseg + ds_cnt);
 	if (unlikely(num_dma < 0))
-		goto dma_unmap_wqe_err;
+		goto err_drop;
 
 	mlx5e_txwqe_complete(sq, skb, opcode, ds_cnt + num_dma,
 			     num_bytes, num_dma, wi, cseg);
 
 	return NETDEV_TX_OK;
 
-dma_unmap_wqe_err:
+err_drop:
 	sq->stats.dropped++;
-	mlx5e_dma_unmap_wqe_err(sq, wi->num_dma);
-
 	dev_kfree_skb_any(skb);
 
 	return NETDEV_TX_OK;
-- 
2.14.3


From 8e60cb8a96f557cc4de36a7e98cc458fbda5aa29 Mon Sep 17 00:00:00 2001
From: Talat Batheesh <talatb@mellanox.com>
Date: Sun, 15 Apr 2018 11:26:19 +0300
Subject: [PATCH 36/41] net/mlx5: Avoid cleaning flow steering table twice
 during error flow

[ Upstream commit 9c26f5f89d01ca21560c6b8a8e4054c271cc3a9c ]

When we fail to initialize the RX root namespace, we need
to clean only that and not the entire flow steering.

Currently the code may try to clean the flow steering twice
on error witch leads to null pointer deference.
Make sure we clean correctly.

Fixes: fba53f7b5719 ("net/mlx5: Introduce mlx5_flow_steering structure")
Signed-off-by: Talat Batheesh <talatb@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 5a7bea688ec8..33e5ff081e36 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -174,6 +174,7 @@ static void del_flow_group(struct fs_node *node);
 static void del_fte(struct fs_node *node);
 static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1,
 				struct mlx5_flow_destination *d2);
+static void cleanup_root_ns(struct mlx5_flow_root_namespace *root_ns);
 static struct mlx5_flow_rule *
 find_flow_rule(struct fs_fte *fte,
 	       struct mlx5_flow_destination *dest);
@@ -2041,23 +2042,27 @@ static int create_anchor_flow_table(struct mlx5_flow_steering *steering)
 
 static int init_root_ns(struct mlx5_flow_steering *steering)
 {
+	int err;
+
 	steering->root_ns = create_root_ns(steering, FS_FT_NIC_RX);
 	if (!steering->root_ns)
-		goto cleanup;
+		return -ENOMEM;
 
-	if (init_root_tree(steering, &root_fs, &steering->root_ns->ns.node))
-		goto cleanup;
+	err = init_root_tree(steering, &root_fs, &steering->root_ns->ns.node);
+	if (err)
+		goto out_err;
 
 	set_prio_attrs(steering->root_ns);
-
-	if (create_anchor_flow_table(steering))
-		goto cleanup;
+	err = create_anchor_flow_table(steering);
+	if (err)
+		goto out_err;
 
 	return 0;
 
-cleanup:
-	mlx5_cleanup_fs(steering->dev);
-	return -ENOMEM;
+out_err:
+	cleanup_root_ns(steering->root_ns);
+	steering->root_ns = NULL;
+	return err;
 }
 
 static void clean_tree(struct fs_node *node)
-- 
2.14.3


From 04e829314760b2e88f58e30dc1e55715fb1446cd Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Wed, 9 May 2018 14:09:04 -0700
Subject: [PATCH 37/41] hv_netvsc: set master device

[ Upstream commit 97f3efb64323beb0690576e9d74e94998ad6e82a ]

The hyper-v transparent bonding should have used master_dev_link.
The netvsc device should look like a master bond device not
like the upper side of a tunnel.

This makes the semantics the same so that userspace applications
looking at network devices see the correct master relationshipship.

Fixes: 0c195567a8f6 ("netvsc: transparent VF management")
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/netvsc_drv.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index c849de3cb046..444e560d928b 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -1742,7 +1742,8 @@ static int netvsc_vf_join(struct net_device *vf_netdev,
 		goto rx_handler_failed;
 	}
 
-	ret = netdev_upper_dev_link(vf_netdev, ndev);
+	ret = netdev_master_upper_dev_link(vf_netdev, ndev,
+					   NULL, NULL);
 	if (ret != 0) {
 		netdev_err(vf_netdev,
 			   "can not set master device %s (err = %d)\n",
-- 
2.14.3


From b1956a950102717dcc2aafbc00c25c3fd17a39d1 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 29 Apr 2018 09:54:59 -0700
Subject: [PATCH 38/41] ipv6: fix uninit-value in ip6_multipath_l3_keys()

[ Upstream commit cea67a2dd6b2419dcc13a39309b9a79a1f773193 ]

syzbot/KMSAN reported an uninit-value in ip6_multipath_l3_keys(),
root caused to a bad assumption of ICMP header being already
pulled in skb->head

ip_multipath_l3_keys() does the correct thing, so it is an IPv6 only bug.

BUG: KMSAN: uninit-value in ip6_multipath_l3_keys net/ipv6/route.c:1830 [inline]
BUG: KMSAN: uninit-value in rt6_multipath_hash+0x5c4/0x640 net/ipv6/route.c:1858
CPU: 0 PID: 4507 Comm: syz-executor661 Not tainted 4.16.0+ #87
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x185/0x1d0 lib/dump_stack.c:53
 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067
 __msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:683
 ip6_multipath_l3_keys net/ipv6/route.c:1830 [inline]
 rt6_multipath_hash+0x5c4/0x640 net/ipv6/route.c:1858
 ip6_route_input+0x65a/0x920 net/ipv6/route.c:1884
 ip6_rcv_finish+0x413/0x6e0 net/ipv6/ip6_input.c:69
 NF_HOOK include/linux/netfilter.h:288 [inline]
 ipv6_rcv+0x1e16/0x2340 net/ipv6/ip6_input.c:208
 __netif_receive_skb_core+0x47df/0x4a90 net/core/dev.c:4562
 __netif_receive_skb net/core/dev.c:4627 [inline]
 netif_receive_skb_internal+0x49d/0x630 net/core/dev.c:4701
 netif_receive_skb+0x230/0x240 net/core/dev.c:4725
 tun_rx_batched drivers/net/tun.c:1555 [inline]
 tun_get_user+0x740f/0x7c60 drivers/net/tun.c:1962
 tun_chr_write_iter+0x1d4/0x330 drivers/net/tun.c:1990
 call_write_iter include/linux/fs.h:1782 [inline]
 new_sync_write fs/read_write.c:469 [inline]
 __vfs_write+0x7fb/0x9f0 fs/read_write.c:482
 vfs_write+0x463/0x8d0 fs/read_write.c:544
 SYSC_write+0x172/0x360 fs/read_write.c:589
 SyS_write+0x55/0x80 fs/read_write.c:581
 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x3d/0xa2

Fixes: 23aebdacb05d ("ipv6: Compute multipath hash for ICMP errors from offending packet")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Jakub Sitnicki <jkbs@redhat.com>
Acked-by: Jakub Sitnicki <jkbs@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index e04c534b573e..7d50d889ab6e 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1222,11 +1222,16 @@ static void ip6_multipath_l3_keys(const struct sk_buff *skb,
 	const struct ipv6hdr *inner_iph;
 	const struct icmp6hdr *icmph;
 	struct ipv6hdr _inner_iph;
+	struct icmp6hdr _icmph;
 
 	if (likely(outer_iph->nexthdr != IPPROTO_ICMPV6))
 		goto out;
 
-	icmph = icmp6_hdr(skb);
+	icmph = skb_header_pointer(skb, skb_transport_offset(skb),
+				   sizeof(_icmph), &_icmph);
+	if (!icmph)
+		goto out;
+
 	if (icmph->icmp6_type != ICMPV6_DEST_UNREACH &&
 	    icmph->icmp6_type != ICMPV6_PKT_TOOBIG &&
 	    icmph->icmp6_type != ICMPV6_TIME_EXCEED &&
-- 
2.14.3


From 0bc34fcfde6f25cec5e5a20d9231dfdf3a825bf8 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@mellanox.com>
Date: Tue, 27 Mar 2018 09:22:16 +0000
Subject: [PATCH 39/41] net/mlx5e: Allow offloading ipv4 header re-write for
 icmp

[ Upstream commit 1ccef350db2f13715040a10df77ae672206004cf ]

For ICMPv4, the checksum is calculated from the ICMP headers and data.
Since the ICMPv4 checksum doesn't cover the IP header, we can allow to
do L3 header re-write for this protocol.

Fixes: bdd66ac0aeed ('net/mlx5e: Disallow TC offloading of unsupported match/action combinations')
Signed-off-by: Jianbo Liu <jianbol@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 598755529815..ede66e6af786 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1387,7 +1387,8 @@ static bool modify_header_match_supported(struct mlx5_flow_spec *spec,
 	}
 
 	ip_proto = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ip_protocol);
-	if (modify_ip_header && ip_proto != IPPROTO_TCP && ip_proto != IPPROTO_UDP) {
+	if (modify_ip_header && ip_proto != IPPROTO_TCP &&
+	    ip_proto != IPPROTO_UDP && ip_proto != IPPROTO_ICMP) {
 		pr_info("can't offload re-write of ip proto %d\n", ip_proto);
 		return false;
 	}
-- 
2.14.3


From eea1eead107a4df4c411efba78fe4fe450cc8152 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 3 May 2018 13:37:54 -0700
Subject: [PATCH 40/41] nsh: fix infinite loop

[ Upstream commit af50e4ba34f4c45e92535364133d4deb5931c1c5 ]

syzbot caught an infinite recursion in nsh_gso_segment().

Problem here is that we need to make sure the NSH header is of
reasonable length.

BUG: MAX_LOCK_DEPTH too low!
turning off the locking correctness validator.
depth: 48  max: 48!
48 locks held by syz-executor0/10189:
 #0:         (ptrval) (rcu_read_lock_bh){....}, at: __dev_queue_xmit+0x30f/0x34c0 net/core/dev.c:3517
 #1:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #1:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #2:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #2:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #3:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #3:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #4:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #4:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #5:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #5:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #6:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #6:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #7:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #7:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #8:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #8:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #9:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #9:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #10:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #10:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #11:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #11:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #12:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #12:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #13:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #13:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #14:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #14:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #15:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #15:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #16:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #16:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #17:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #17:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #18:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #18:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #19:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #19:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #20:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #20:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #21:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #21:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #22:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #22:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #23:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #23:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #24:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #24:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #25:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #25:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #26:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #26:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #27:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #27:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #28:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #28:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #29:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #29:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #30:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #30:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #31:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #31:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
dccp_close: ABORT with 65423 bytes unread
 #32:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #32:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #33:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #33:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #34:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #34:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #35:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #35:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #36:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #36:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #37:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #37:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #38:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #38:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #39:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #39:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #40:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #40:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #41:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #41:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #42:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #42:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #43:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #43:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #44:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #44:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #45:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #45:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #46:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #46:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #47:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #47:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
INFO: lockdep is turned off.
CPU: 1 PID: 10189 Comm: syz-executor0 Not tainted 4.17.0-rc2+ #26
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1b9/0x294 lib/dump_stack.c:113
 __lock_acquire+0x1788/0x5140 kernel/locking/lockdep.c:3449
 lock_acquire+0x1dc/0x520 kernel/locking/lockdep.c:3920
 rcu_lock_acquire include/linux/rcupdate.h:246 [inline]
 rcu_read_lock include/linux/rcupdate.h:632 [inline]
 skb_mac_gso_segment+0x25b/0x720 net/core/dev.c:2789
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 __skb_gso_segment+0x3bb/0x870 net/core/dev.c:2865
 skb_gso_segment include/linux/netdevice.h:4025 [inline]
 validate_xmit_skb+0x54d/0xd90 net/core/dev.c:3118
 validate_xmit_skb_list+0xbf/0x120 net/core/dev.c:3168
 sch_direct_xmit+0x354/0x11e0 net/sched/sch_generic.c:312
 qdisc_restart net/sched/sch_generic.c:399 [inline]
 __qdisc_run+0x741/0x1af0 net/sched/sch_generic.c:410
 __dev_xmit_skb net/core/dev.c:3243 [inline]
 __dev_queue_xmit+0x28ea/0x34c0 net/core/dev.c:3551
 dev_queue_xmit+0x17/0x20 net/core/dev.c:3616
 packet_snd net/packet/af_packet.c:2951 [inline]
 packet_sendmsg+0x40f8/0x6070 net/packet/af_packet.c:2976
 sock_sendmsg_nosec net/socket.c:629 [inline]
 sock_sendmsg+0xd5/0x120 net/socket.c:639
 __sys_sendto+0x3d7/0x670 net/socket.c:1789
 __do_sys_sendto net/socket.c:1801 [inline]
 __se_sys_sendto net/socket.c:1797 [inline]
 __x64_sys_sendto+0xe1/0x1a0 net/socket.c:1797
 do_syscall_64+0x1b1/0x800 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Fixes: c411ed854584 ("nsh: add GSO support")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jiri Benc <jbenc@redhat.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/nsh/nsh.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/nsh/nsh.c b/net/nsh/nsh.c
index 58fb827439a8..6df6f58a8103 100644
--- a/net/nsh/nsh.c
+++ b/net/nsh/nsh.c
@@ -30,6 +30,8 @@ static struct sk_buff *nsh_gso_segment(struct sk_buff *skb,
 	if (unlikely(!pskb_may_pull(skb, NSH_BASE_HDR_LEN)))
 		goto out;
 	nsh_len = nsh_hdr_len(nsh_hdr(skb));
+	if (nsh_len < NSH_BASE_HDR_LEN)
+		goto out;
 	if (unlikely(!pskb_may_pull(skb, nsh_len)))
 		goto out;
 
-- 
2.14.3


From 8bad60aee9261343c2111a69adfe1827572d377a Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 9 May 2018 12:42:34 +0200
Subject: [PATCH 41/41] udp: fix SO_BINDTODEVICE

[ Upstream commit 69678bcd4d2dedbc3e8fcd6d7d99f283d83c531a ]

Damir reported a breakage of SO_BINDTODEVICE for UDP sockets.
In absence of VRF devices, after commit fb74c27735f0 ("net:
ipv4: add second dif to udp socket lookups") the dif mismatch
isn't fatal anymore for UDP socket lookup with non null
sk_bound_dev_if, breaking SO_BINDTODEVICE semantics.

This changeset addresses the issue making the dif match mandatory
again in the above scenario.

Reported-by: Damir Mansurov <dnman@oktetlabs.ru>
Fixes: fb74c27735f0 ("net: ipv4: add second dif to udp socket lookups")
Fixes: 1801b570dd2a ("net: ipv6: add second dif to udp socket lookups")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 4 ++--
 net/ipv6/udp.c | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 5517f20a9cd9..b0ad62bd38f7 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -413,9 +413,9 @@ static int compute_score(struct sock *sk, struct net *net,
 		bool dev_match = (sk->sk_bound_dev_if == dif ||
 				  sk->sk_bound_dev_if == sdif);
 
-		if (exact_dif && !dev_match)
+		if (!dev_match)
 			return -1;
-		if (sk->sk_bound_dev_if && dev_match)
+		if (sk->sk_bound_dev_if)
 			score += 4;
 	}
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 40d7234c27b9..0146dcdc5c40 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -164,9 +164,9 @@ static int compute_score(struct sock *sk, struct net *net,
 		bool dev_match = (sk->sk_bound_dev_if == dif ||
 				  sk->sk_bound_dev_if == sdif);
 
-		if (exact_dif && !dev_match)
+		if (!dev_match)
 			return -1;
-		if (sk->sk_bound_dev_if && dev_match)
+		if (sk->sk_bound_dev_if)
 			score++;
 	}
 
-- 
2.14.3


[-- Attachment #3: net_416.mbox --]
[-- Type: Application/Octet-Stream, Size: 154383 bytes --]

From 53e838e36c407e10a4911106578af2d683e831af Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Wed, 2 May 2018 13:30:57 +0200
Subject: [PATCH 01/55] 8139too: Use disable_irq_nosync() in
 rtl8139_poll_controller()

[ Upstream commit af3e0fcf78879f718c5f73df0814951bd7057d34 ]

Use disable_irq_nosync() instead of disable_irq() as this might be
called in atomic context with netpoll.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/8139too.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c
index d24b47b8e0b2..d118da5a10a2 100644
--- a/drivers/net/ethernet/realtek/8139too.c
+++ b/drivers/net/ethernet/realtek/8139too.c
@@ -2224,7 +2224,7 @@ static void rtl8139_poll_controller(struct net_device *dev)
 	struct rtl8139_private *tp = netdev_priv(dev);
 	const int irq = tp->pci_dev->irq;
 
-	disable_irq(irq);
+	disable_irq_nosync(irq);
 	rtl8139_interrupt(irq, dev);
 	enable_irq(irq);
 }
-- 
2.14.3


From 218a971dd66ec82bdb653cf82c9d9b211f367809 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Thu, 3 May 2018 13:17:12 -0500
Subject: [PATCH 02/55] atm: zatm: Fix potential Spectre v1

[ Upstream commit 2be147f7459db5bbf292e0a6f135037b55e20b39 ]

pool can be indirectly controlled by user-space, hence leading to
a potential exploitation of the Spectre variant 1 vulnerability.

This issue was detected with the help of Smatch:

drivers/atm/zatm.c:1462 zatm_ioctl() warn: potential spectre issue
'zatm_dev->pool_info' (local cap)

Fix this by sanitizing pool before using it to index
zatm_dev->pool_info

Notice that given that speculation windows are large, the policy is
to kill the speculation on the first load and not worry if it can be
completed with a dependent load/store [1].

[1] https://marc.info/?l=linux-kernel&m=152449131114778&w=2

Cc: stable@vger.kernel.org
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/atm/zatm.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/atm/zatm.c b/drivers/atm/zatm.c
index 1ef67db03c8e..9c9a22958717 100644
--- a/drivers/atm/zatm.c
+++ b/drivers/atm/zatm.c
@@ -28,6 +28,7 @@
 #include <asm/io.h>
 #include <linux/atomic.h>
 #include <linux/uaccess.h>
+#include <linux/nospec.h>
 
 #include "uPD98401.h"
 #include "uPD98402.h"
@@ -1458,6 +1459,8 @@ static int zatm_ioctl(struct atm_dev *dev,unsigned int cmd,void __user *arg)
 					return -EFAULT;
 				if (pool < 0 || pool > ZATM_LAST_POOL)
 					return -EINVAL;
+				pool = array_index_nospec(pool,
+							  ZATM_LAST_POOL + 1);
 				spin_lock_irqsave(&zatm_dev->lock, flags);
 				info = zatm_dev->pool_info[pool];
 				if (cmd == ZATM_GETPOOLZ) {
-- 
2.14.3


From d6171a81011ad8afdd44d44d6a9959496ca5f90d Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Fri, 27 Apr 2018 20:59:24 +0800
Subject: [PATCH 03/55] bridge: check iface upper dev when setting master via
 ioctl

[ Upstream commit e8238fc2bd7b4c3c7554fa2df067e796610212fc ]

When we set a bond slave's master to bridge via ioctl, we only check
the IFF_BRIDGE_PORT flag. Although we will find the slave's real master
at netdev_master_upper_dev_link() later, it already does some settings
and allocates some resources. It would be better to return as early
as possible.

v1 -> v2:
use netdev_master_upper_dev_get() instead of netdev_has_any_upper_dev()
to check if we have a master, because not all upper devs are masters,
e.g. vlan device.

Reported-by: syzbot+de73361ee4971b6e6f75@syzkaller.appspotmail.com
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_if.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 9ba4ed65c52b..4be5335407c5 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -509,8 +509,8 @@ int br_add_if(struct net_bridge *br, struct net_device *dev,
 		return -ELOOP;
 	}
 
-	/* Device is already being bridged */
-	if (br_port_exists(dev))
+	/* Device has master upper dev */
+	if (netdev_master_upper_dev_get(dev))
 		return -EBUSY;
 
 	/* No bridging devices that dislike that (e.g. wireless) */
-- 
2.14.3


From b4124e502083fda2e0d0fabf471f5aea5eeb3838 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 3 May 2018 09:39:20 -0700
Subject: [PATCH 04/55] dccp: fix tasklet usage

[ Upstream commit a8d7aa17bbc970971ccdf71988ea19230ab368b1 ]

syzbot reported a crash in tasklet_action_common() caused by dccp.

dccp needs to make sure socket wont disappear before tasklet handler
has completed.

This patch takes a reference on the socket when arming the tasklet,
and moves the sock_put() from dccp_write_xmit_timer() to dccp_write_xmitlet()

kernel BUG at kernel/softirq.c:514!
invalid opcode: 0000 [#1] SMP KASAN
Dumping ftrace buffer:
   (ftrace buffer empty)
Modules linked in:
CPU: 1 PID: 17 Comm: ksoftirqd/1 Not tainted 4.17.0-rc3+ #30
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:tasklet_action_common.isra.19+0x6db/0x700 kernel/softirq.c:515
RSP: 0018:ffff8801d9b3faf8 EFLAGS: 00010246
dccp_close: ABORT with 65423 bytes unread
RAX: 1ffff1003b367f6b RBX: ffff8801daf1f3f0 RCX: 0000000000000000
RDX: ffff8801cf895498 RSI: 0000000000000004 RDI: 0000000000000000
RBP: ffff8801d9b3fc40 R08: ffffed0039f12a95 R09: ffffed0039f12a94
dccp_close: ABORT with 65423 bytes unread
R10: ffffed0039f12a94 R11: ffff8801cf8954a3 R12: 0000000000000000
R13: ffff8801d9b3fc18 R14: dffffc0000000000 R15: ffff8801cf895490
FS:  0000000000000000(0000) GS:ffff8801daf00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000001b2bc28000 CR3: 00000001a08a9000 CR4: 00000000001406e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 tasklet_action+0x1d/0x20 kernel/softirq.c:533
 __do_softirq+0x2e0/0xaf5 kernel/softirq.c:285
dccp_close: ABORT with 65423 bytes unread
 run_ksoftirqd+0x86/0x100 kernel/softirq.c:646
 smpboot_thread_fn+0x417/0x870 kernel/smpboot.c:164
 kthread+0x345/0x410 kernel/kthread.c:238
 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:412
Code: 48 8b 85 e8 fe ff ff 48 8b 95 f0 fe ff ff e9 94 fb ff ff 48 89 95 f0 fe ff ff e8 81 53 6e 00 48 8b 95 f0 fe ff ff e9 62 fb ff ff <0f> 0b 48 89 cf 48 89 8d e8 fe ff ff e8 64 53 6e 00 48 8b 8d e8
RIP: tasklet_action_common.isra.19+0x6db/0x700 kernel/softirq.c:515 RSP: ffff8801d9b3faf8

Fixes: dc841e30eaea ("dccp: Extend CCID packet dequeueing interface")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Cc: dccp@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ccids/ccid2.c | 14 ++++++++++++--
 net/dccp/timer.c       |  2 +-
 2 files changed, 13 insertions(+), 3 deletions(-)

diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c
index 92d016e87816..385f153fe031 100644
--- a/net/dccp/ccids/ccid2.c
+++ b/net/dccp/ccids/ccid2.c
@@ -126,6 +126,16 @@ static void ccid2_change_l_seq_window(struct sock *sk, u64 val)
 						  DCCPF_SEQ_WMAX));
 }
 
+static void dccp_tasklet_schedule(struct sock *sk)
+{
+	struct tasklet_struct *t = &dccp_sk(sk)->dccps_xmitlet;
+
+	if (!test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) {
+		sock_hold(sk);
+		__tasklet_schedule(t);
+	}
+}
+
 static void ccid2_hc_tx_rto_expire(struct timer_list *t)
 {
 	struct ccid2_hc_tx_sock *hc = from_timer(hc, t, tx_rtotimer);
@@ -166,7 +176,7 @@ static void ccid2_hc_tx_rto_expire(struct timer_list *t)
 
 	/* if we were blocked before, we may now send cwnd=1 packet */
 	if (sender_was_blocked)
-		tasklet_schedule(&dccp_sk(sk)->dccps_xmitlet);
+		dccp_tasklet_schedule(sk);
 	/* restart backed-off timer */
 	sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto);
 out:
@@ -706,7 +716,7 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
 done:
 	/* check if incoming Acks allow pending packets to be sent */
 	if (sender_was_blocked && !ccid2_cwnd_network_limited(hc))
-		tasklet_schedule(&dccp_sk(sk)->dccps_xmitlet);
+		dccp_tasklet_schedule(sk);
 	dccp_ackvec_parsed_cleanup(&hc->tx_av_chunks);
 }
 
diff --git a/net/dccp/timer.c b/net/dccp/timer.c
index b50a8732ff43..1501a20a94ca 100644
--- a/net/dccp/timer.c
+++ b/net/dccp/timer.c
@@ -232,6 +232,7 @@ static void dccp_write_xmitlet(unsigned long data)
 	else
 		dccp_write_xmit(sk);
 	bh_unlock_sock(sk);
+	sock_put(sk);
 }
 
 static void dccp_write_xmit_timer(struct timer_list *t)
@@ -240,7 +241,6 @@ static void dccp_write_xmit_timer(struct timer_list *t)
 	struct sock *sk = &dp->dccps_inet_connection.icsk_inet.sk;
 
 	dccp_write_xmitlet((unsigned long)sk);
-	sock_put(sk);
 }
 
 void dccp_init_xmit_timers(struct sock *sk)
-- 
2.14.3


From 1f19fe1cc75c4041796841faba0ebdafe0a6e3c3 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Wed, 2 May 2018 09:41:19 +0300
Subject: [PATCH 05/55] ipv4: fix fnhe usage by non-cached routes

[ Upstream commit 94720e3aee6884d8c8beb678001629da60ec6366 ]

Allow some non-cached routes to use non-expired fnhe:

1. ip_del_fnhe: moved above and now called by find_exception.
The 4.5+ commit deed49df7390 expires fnhe only when caching
routes. Change that to:

1.1. use fnhe for non-cached local output routes, with the help
from (2)

1.2. allow __mkroute_input to detect expired fnhe (outdated
fnhe_gw, for example) when do_cache is false, eg. when itag!=0
for unicast destinations.

2. __mkroute_output: keep fi to allow local routes with orig_oif != 0
to use fnhe info even when the new route will not be cached into fnhe.
After commit 839da4d98960 ("net: ipv4: set orig_oif based on fib
result for local traffic") it means all local routes will be affected
because they are not cached. This change is used to solve a PMTU
problem with IPVS (and probably Netfilter DNAT) setups that redirect
local clients from target local IP (local route to Virtual IP)
to new remote IP target, eg. IPVS TUN real server. Loopback has
64K MTU and we need to create fnhe on the local route that will
keep the reduced PMTU for the Virtual IP. Without this change
fnhe_pmtu is updated from ICMP but never exposed to non-cached
local routes. This includes routes with flowi4_oif!=0 for 4.6+ and
with flowi4_oif=any for 4.14+).

3. update_or_create_fnhe: make sure fnhe_expires is not 0 for
new entries

Fixes: 839da4d98960 ("net: ipv4: set orig_oif based on fib result for local traffic")
Fixes: d6d5e999e5df ("route: do not cache fib route info on local routes with oif")
Fixes: deed49df7390 ("route: check and remove route cache when we get route")
Cc: David Ahern <dsahern@gmail.com>
Cc: Xin Long <lucien.xin@gmail.com>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 118 +++++++++++++++++++++++++------------------------------
 1 file changed, 53 insertions(+), 65 deletions(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 299e247b2032..c5366b290508 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -710,7 +710,7 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
 		fnhe->fnhe_gw = gw;
 		fnhe->fnhe_pmtu = pmtu;
 		fnhe->fnhe_mtu_locked = lock;
-		fnhe->fnhe_expires = expires;
+		fnhe->fnhe_expires = max(1UL, expires);
 
 		/* Exception created; mark the cached routes for the nexthop
 		 * stale, so anyone caching it rechecks if this exception
@@ -1298,6 +1298,36 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst)
 	return mtu - lwtunnel_headroom(dst->lwtstate, mtu);
 }
 
+static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
+{
+	struct fnhe_hash_bucket *hash;
+	struct fib_nh_exception *fnhe, __rcu **fnhe_p;
+	u32 hval = fnhe_hashfun(daddr);
+
+	spin_lock_bh(&fnhe_lock);
+
+	hash = rcu_dereference_protected(nh->nh_exceptions,
+					 lockdep_is_held(&fnhe_lock));
+	hash += hval;
+
+	fnhe_p = &hash->chain;
+	fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock));
+	while (fnhe) {
+		if (fnhe->fnhe_daddr == daddr) {
+			rcu_assign_pointer(*fnhe_p, rcu_dereference_protected(
+				fnhe->fnhe_next, lockdep_is_held(&fnhe_lock)));
+			fnhe_flush_routes(fnhe);
+			kfree_rcu(fnhe, rcu);
+			break;
+		}
+		fnhe_p = &fnhe->fnhe_next;
+		fnhe = rcu_dereference_protected(fnhe->fnhe_next,
+						 lockdep_is_held(&fnhe_lock));
+	}
+
+	spin_unlock_bh(&fnhe_lock);
+}
+
 static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr)
 {
 	struct fnhe_hash_bucket *hash = rcu_dereference(nh->nh_exceptions);
@@ -1311,8 +1341,14 @@ static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr)
 
 	for (fnhe = rcu_dereference(hash[hval].chain); fnhe;
 	     fnhe = rcu_dereference(fnhe->fnhe_next)) {
-		if (fnhe->fnhe_daddr == daddr)
+		if (fnhe->fnhe_daddr == daddr) {
+			if (fnhe->fnhe_expires &&
+			    time_after(jiffies, fnhe->fnhe_expires)) {
+				ip_del_fnhe(nh, daddr);
+				break;
+			}
 			return fnhe;
+		}
 	}
 	return NULL;
 }
@@ -1638,36 +1674,6 @@ static void ip_handle_martian_source(struct net_device *dev,
 #endif
 }
 
-static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
-{
-	struct fnhe_hash_bucket *hash;
-	struct fib_nh_exception *fnhe, __rcu **fnhe_p;
-	u32 hval = fnhe_hashfun(daddr);
-
-	spin_lock_bh(&fnhe_lock);
-
-	hash = rcu_dereference_protected(nh->nh_exceptions,
-					 lockdep_is_held(&fnhe_lock));
-	hash += hval;
-
-	fnhe_p = &hash->chain;
-	fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock));
-	while (fnhe) {
-		if (fnhe->fnhe_daddr == daddr) {
-			rcu_assign_pointer(*fnhe_p, rcu_dereference_protected(
-				fnhe->fnhe_next, lockdep_is_held(&fnhe_lock)));
-			fnhe_flush_routes(fnhe);
-			kfree_rcu(fnhe, rcu);
-			break;
-		}
-		fnhe_p = &fnhe->fnhe_next;
-		fnhe = rcu_dereference_protected(fnhe->fnhe_next,
-						 lockdep_is_held(&fnhe_lock));
-	}
-
-	spin_unlock_bh(&fnhe_lock);
-}
-
 static void set_lwt_redirect(struct rtable *rth)
 {
 	if (lwtunnel_output_redirect(rth->dst.lwtstate)) {
@@ -1734,20 +1740,10 @@ static int __mkroute_input(struct sk_buff *skb,
 
 	fnhe = find_exception(&FIB_RES_NH(*res), daddr);
 	if (do_cache) {
-		if (fnhe) {
+		if (fnhe)
 			rth = rcu_dereference(fnhe->fnhe_rth_input);
-			if (rth && rth->dst.expires &&
-			    time_after(jiffies, rth->dst.expires)) {
-				ip_del_fnhe(&FIB_RES_NH(*res), daddr);
-				fnhe = NULL;
-			} else {
-				goto rt_cache;
-			}
-		}
-
-		rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
-
-rt_cache:
+		else
+			rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
 		if (rt_cache_valid(rth)) {
 			skb_dst_set_noref(skb, &rth->dst);
 			goto out;
@@ -2224,39 +2220,31 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 		 * the loopback interface and the IP_PKTINFO ipi_ifindex will
 		 * be set to the loopback interface as well.
 		 */
-		fi = NULL;
+		do_cache = false;
 	}
 
 	fnhe = NULL;
 	do_cache &= fi != NULL;
-	if (do_cache) {
+	if (fi) {
 		struct rtable __rcu **prth;
 		struct fib_nh *nh = &FIB_RES_NH(*res);
 
 		fnhe = find_exception(nh, fl4->daddr);
+		if (!do_cache)
+			goto add;
 		if (fnhe) {
 			prth = &fnhe->fnhe_rth_output;
-			rth = rcu_dereference(*prth);
-			if (rth && rth->dst.expires &&
-			    time_after(jiffies, rth->dst.expires)) {
-				ip_del_fnhe(nh, fl4->daddr);
-				fnhe = NULL;
-			} else {
-				goto rt_cache;
+		} else {
+			if (unlikely(fl4->flowi4_flags &
+				     FLOWI_FLAG_KNOWN_NH &&
+				     !(nh->nh_gw &&
+				       nh->nh_scope == RT_SCOPE_LINK))) {
+				do_cache = false;
+				goto add;
 			}
+			prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
 		}
-
-		if (unlikely(fl4->flowi4_flags &
-			     FLOWI_FLAG_KNOWN_NH &&
-			     !(nh->nh_gw &&
-			       nh->nh_scope == RT_SCOPE_LINK))) {
-			do_cache = false;
-			goto add;
-		}
-		prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
 		rth = rcu_dereference(*prth);
-
-rt_cache:
 		if (rt_cache_valid(rth) && dst_hold_safe(&rth->dst))
 			return rth;
 	}
-- 
2.14.3


From d9d1b56347c8b549d4915aad8ac8ab0c619ec580 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Thu, 10 May 2018 10:59:34 -0700
Subject: [PATCH 06/55] ipv4: fix memory leaks in udp_sendmsg, ping_v4_sendmsg

[ Upstream commit 1b97013bfb11d66f041de691de6f0fec748ce016 ]

Fix more memory leaks in ip_cmsg_send() callers. Part of them were fixed
earlier in 919483096bfe.

* udp_sendmsg one was there since the beginning when linux sources were
  first added to git;
* ping_v4_sendmsg one was copy/pasted in c319b4d76b9e.

Whenever return happens in udp_sendmsg() or ping_v4_sendmsg() IP options
have to be freed if they were allocated previously.

Add label so that future callers (if any) can use it instead of kfree()
before return that is easy to forget.

Fixes: c319b4d76b9e (net: ipv4: add IPPROTO_ICMP socket kind)
Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ping.c | 7 +++++--
 net/ipv4/udp.c  | 7 +++++--
 2 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index b8f0db54b197..16226d49263d 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -775,8 +775,10 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	ipc.addr = faddr = daddr;
 
 	if (ipc.opt && ipc.opt->opt.srr) {
-		if (!daddr)
-			return -EINVAL;
+		if (!daddr) {
+			err = -EINVAL;
+			goto out_free;
+		}
 		faddr = ipc.opt->opt.faddr;
 	}
 	tos = get_rttos(&ipc, inet);
@@ -842,6 +844,7 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 out:
 	ip_rt_put(rt);
+out_free:
 	if (free)
 		kfree(ipc.opt);
 	if (!err) {
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index e5ef7c38c934..fb5992988450 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -958,8 +958,10 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	sock_tx_timestamp(sk, ipc.sockc.tsflags, &ipc.tx_flags);
 
 	if (ipc.opt && ipc.opt->opt.srr) {
-		if (!daddr)
-			return -EINVAL;
+		if (!daddr) {
+			err = -EINVAL;
+			goto out_free;
+		}
 		faddr = ipc.opt->opt.faddr;
 		connected = 0;
 	}
@@ -1080,6 +1082,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 out:
 	ip_rt_put(rt);
+out_free:
 	if (free)
 		kfree(ipc.opt);
 	if (!err)
-- 
2.14.3


From 70435e531f157754cdf861bd865edb46fddcc661 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 7 May 2018 09:02:25 -0700
Subject: [PATCH 07/55] llc: better deal with too small mtu

[ Upstream commit 2c5d5b13c6eb79f5677e206b8aad59b3a2097f60 ]

syzbot loves to set very small mtu on devices, since it brings joy.
We must make llc_ui_sendmsg() fool proof.

usercopy: Kernel memory overwrite attempt detected to wrapped address (offset 0, size 18446612139802320068)!

kernel BUG at mm/usercopy.c:100!
invalid opcode: 0000 [#1] SMP KASAN
Dumping ftrace buffer:
   (ftrace buffer empty)
Modules linked in:
CPU: 0 PID: 17464 Comm: syz-executor1 Not tainted 4.17.0-rc3+ #36
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:usercopy_abort+0xbb/0xbd mm/usercopy.c:88
RSP: 0018:ffff8801868bf800 EFLAGS: 00010282
RAX: 000000000000006c RBX: ffffffff87d2fb00 RCX: 0000000000000000
RDX: 000000000000006c RSI: ffffffff81610731 RDI: ffffed0030d17ef6
RBP: ffff8801868bf858 R08: ffff88018daa4200 R09: ffffed003b5c4fb0
R10: ffffed003b5c4fb0 R11: ffff8801dae27d87 R12: ffffffff87d2f8e0
R13: ffffffff87d2f7a0 R14: ffffffff87d2f7a0 R15: ffffffff87d2f7a0
FS:  00007f56a14ac700(0000) GS:ffff8801dae00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000001b2bc21000 CR3: 00000001abeb1000 CR4: 00000000001426f0
DR0: 0000000020000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000030602
Call Trace:
 check_bogus_address mm/usercopy.c:153 [inline]
 __check_object_size+0x5d9/0x5d9 mm/usercopy.c:256
 check_object_size include/linux/thread_info.h:108 [inline]
 check_copy_size include/linux/thread_info.h:139 [inline]
 copy_from_iter_full include/linux/uio.h:121 [inline]
 memcpy_from_msg include/linux/skbuff.h:3305 [inline]
 llc_ui_sendmsg+0x4b1/0x1530 net/llc/af_llc.c:941
 sock_sendmsg_nosec net/socket.c:629 [inline]
 sock_sendmsg+0xd5/0x120 net/socket.c:639
 __sys_sendto+0x3d7/0x670 net/socket.c:1789
 __do_sys_sendto net/socket.c:1801 [inline]
 __se_sys_sendto net/socket.c:1797 [inline]
 __x64_sys_sendto+0xe1/0x1a0 net/socket.c:1797
 do_syscall_64+0x1b1/0x800 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x455979
RSP: 002b:00007f56a14abc68 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 00007f56a14ac6d4 RCX: 0000000000455979
RDX: 0000000000000000 RSI: 0000000020000000 RDI: 0000000000000018
RBP: 000000000072bea0 R08: 00000000200012c0 R09: 0000000000000010
R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff
R13: 0000000000000548 R14: 00000000006fbf60 R15: 0000000000000000
Code: 55 c0 e8 c0 55 bb ff ff 75 c8 48 8b 55 c0 4d 89 f9 ff 75 d0 4d 89 e8 48 89 d9 4c 89 e6 41 56 48 c7 c7 80 fa d2 87 e8 a0 0b a3 ff <0f> 0b e8 95 55 bb ff e8 c0 a8 f7 ff 8b 95 14 ff ff ff 4d 89 e8
RIP: usercopy_abort+0xbb/0xbd mm/usercopy.c:88 RSP: ffff8801868bf800

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/llc/af_llc.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index cf41d9b4a0b8..b49f5afab405 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -930,6 +930,9 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	if (size > llc->dev->mtu)
 		size = llc->dev->mtu;
 	copied = size - hdrlen;
+	rc = -EINVAL;
+	if (copied < 0)
+		goto release;
 	release_sock(sk);
 	skb = sock_alloc_send_skb(sk, size, noblock, &rc);
 	lock_sock(sk);
-- 
2.14.3


From f476739d8ae51e88b9bef111ac6b458d491129d3 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Thu, 3 May 2018 13:45:58 -0500
Subject: [PATCH 08/55] net: atm: Fix potential Spectre v1

[ Upstream commit acf784bd0ce257fe43da7ca266f7a10b837479d2 ]

ioc_data.dev_num can be controlled by user-space, hence leading to
a potential exploitation of the Spectre variant 1 vulnerability.

This issue was detected with the help of Smatch:
net/atm/lec.c:702 lec_vcc_attach() warn: potential spectre issue
'dev_lec'

Fix this by sanitizing ioc_data.dev_num before using it to index
dev_lec. Also, notice that there is another instance in which array
dev_lec is being indexed using ioc_data.dev_num at line 705:
lec_vcc_added(netdev_priv(dev_lec[ioc_data.dev_num]),

Notice that given that speculation windows are large, the policy is
to kill the speculation on the first load and not worry if it can be
completed with a dependent load/store [1].

[1] https://marc.info/?l=linux-kernel&m=152449131114778&w=2

Cc: stable@vger.kernel.org
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/atm/lec.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/atm/lec.c b/net/atm/lec.c
index 09a1f056712a..7579e85af531 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -41,6 +41,9 @@ static unsigned char bridge_ula_lec[] = { 0x01, 0x80, 0xc2, 0x00, 0x00 };
 #include <linux/module.h>
 #include <linux/init.h>
 
+/* Hardening for Spectre-v1 */
+#include <linux/nospec.h>
+
 #include "lec.h"
 #include "lec_arpc.h"
 #include "resources.h"
@@ -687,8 +690,10 @@ static int lec_vcc_attach(struct atm_vcc *vcc, void __user *arg)
 	bytes_left = copy_from_user(&ioc_data, arg, sizeof(struct atmlec_ioc));
 	if (bytes_left != 0)
 		pr_info("copy from user failed for %d bytes\n", bytes_left);
-	if (ioc_data.dev_num < 0 || ioc_data.dev_num >= MAX_LEC_ITF ||
-	    !dev_lec[ioc_data.dev_num])
+	if (ioc_data.dev_num < 0 || ioc_data.dev_num >= MAX_LEC_ITF)
+		return -EINVAL;
+	ioc_data.dev_num = array_index_nospec(ioc_data.dev_num, MAX_LEC_ITF);
+	if (!dev_lec[ioc_data.dev_num])
 		return -EINVAL;
 	vpriv = kmalloc(sizeof(struct lec_vcc_priv), GFP_KERNEL);
 	if (!vpriv)
-- 
2.14.3


From 05bfa0f7c5f3b6e1421e6906399f9cf60613850e Mon Sep 17 00:00:00 2001
From: Rob Taglang <rob@taglang.io>
Date: Thu, 3 May 2018 17:13:06 -0400
Subject: [PATCH 09/55] net: ethernet: sun: niu set correct packet size in skb

[ Upstream commit 14224923c3600bae2ac4dcae3bf0c3d4dc2812be ]

Currently, skb->len and skb->data_len are set to the page size, not
the packet size. This causes the frame check sequence to not be
located at the "end" of the packet resulting in ethernet frame check
errors. The driver does work currently, but stricter kernel facing
networking solutions like OpenVSwitch will drop these packets as
invalid.

These changes set the packet size correctly so that these errors no
longer occur. The length does not include the frame check sequence, so
that subtraction was removed.

Tested on Oracle/SUN Multithreaded 10-Gigabit Ethernet Network
Controller [108e:abcd] and validated in wireshark.

Signed-off-by: Rob Taglang <rob@taglang.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sun/niu.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c
index 8dd545fed30d..6c94af263be8 100644
--- a/drivers/net/ethernet/sun/niu.c
+++ b/drivers/net/ethernet/sun/niu.c
@@ -3443,7 +3443,7 @@ static int niu_process_rx_pkt(struct napi_struct *napi, struct niu *np,
 
 		len = (val & RCR_ENTRY_L2_LEN) >>
 			RCR_ENTRY_L2_LEN_SHIFT;
-		len -= ETH_FCS_LEN;
+		append_size = len + ETH_HLEN + ETH_FCS_LEN;
 
 		addr = (val & RCR_ENTRY_PKT_BUF_ADDR) <<
 			RCR_ENTRY_PKT_BUF_ADDR_SHIFT;
@@ -3453,7 +3453,6 @@ static int niu_process_rx_pkt(struct napi_struct *napi, struct niu *np,
 					 RCR_ENTRY_PKTBUFSZ_SHIFT];
 
 		off = addr & ~PAGE_MASK;
-		append_size = rcr_size;
 		if (num_rcr == 1) {
 			int ptype;
 
@@ -3466,7 +3465,7 @@ static int niu_process_rx_pkt(struct napi_struct *napi, struct niu *np,
 			else
 				skb_checksum_none_assert(skb);
 		} else if (!(val & RCR_ENTRY_MULTI))
-			append_size = len - skb->len;
+			append_size = append_size - skb->len;
 
 		niu_rx_skb_append(skb, page, off, append_size, rcr_size);
 		if ((page->index + rp->rbr_block_size) - rcr_size == addr) {
-- 
2.14.3


From bbc84c9cf47fd8dfd584aa01b2d8c262cdf077ba Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Tue, 1 May 2018 12:41:22 -0500
Subject: [PATCH 10/55] net: ethernet: ti: cpsw: fix packet leaking in dual_mac
 mode

[ Upstream commit 5e5add172ea81152d518b161ec5706503ad3d799 ]

In dual_mac mode packets arrived on one port should not be forwarded by
switch hw to another port. Only Linux Host can forward packets between
ports. The below test case (reported in [1]) shows that packet arrived on
one port can be leaked to anoter (reproducible with dual port evms):
 - connect port 1 (eth0) to linux Host 0 and run tcpdump or Wireshark
 - connect port 2 (eth1) to linux Host 1 with vlan 1 configured
 - ping <IPx> from Host 1 through vlan 1 interface.
ARP packets will be seen on Host 0.

Issue happens because dual_mac mode is implemnted using two vlans: 1 (Port
1+Port 0) and 2 (Port 2+Port 0), so there are vlan records created for for
each vlan. By default, the ALE will find valid vlan record in its table
when vlan 1 tagged packet arrived on Port 2 and so forwards packet to all
ports which are vlan 1 members (like Port.

To avoid such behaviorr the ALE VLAN ID Ingress Check need to be enabled
for each external CPSW port (ALE_PORTCTLn.VID_INGRESS_CHECK) so ALE will
drop ingress packets if Rx port is not VLAN member.

Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 33c35b2df7d5..5490c7d09c16 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -1278,6 +1278,8 @@ static inline void cpsw_add_dual_emac_def_ale_entries(
 	cpsw_ale_add_ucast(cpsw->ale, priv->mac_addr,
 			   HOST_PORT_NUM, ALE_VLAN |
 			   ALE_SECURE, slave->port_vlan);
+	cpsw_ale_control_set(cpsw->ale, slave_port,
+			     ALE_PORT_DROP_UNKNOWN_VLAN, 1);
 }
 
 static void soft_reset_slave(struct cpsw_slave *slave)
-- 
2.14.3


From 12b37575e2d93232f6588e7bb4552700c08825f5 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Thu, 10 May 2018 09:06:04 +0200
Subject: [PATCH 11/55] net/mlx4_en: Fix an error handling path in
 'mlx4_en_init_netdev()'

[ Upstream commit a577d868b768a3baf16cdd4841ab8cfb165521d6 ]

If an error occurs, 'mlx4_en_destroy_netdev()' is called.
It then calls 'mlx4_en_free_resources()' which does the needed resources
cleanup.

So, doing some explicit kfree in the error handling path would lead to
some double kfree.

Simplify code to avoid such a case.

Fixes: 67f8b1dcb9ee ("net/mlx4_en: Refactor the XDP forwarding rings scheme")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 8fc51bc29003..41f8fbced11d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -3320,12 +3320,11 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 					   MAX_TX_RINGS, GFP_KERNEL);
 		if (!priv->tx_ring[t]) {
 			err = -ENOMEM;
-			goto err_free_tx;
+			goto out;
 		}
 		priv->tx_cq[t] = kzalloc(sizeof(struct mlx4_en_cq *) *
 					 MAX_TX_RINGS, GFP_KERNEL);
 		if (!priv->tx_cq[t]) {
-			kfree(priv->tx_ring[t]);
 			err = -ENOMEM;
 			goto out;
 		}
@@ -3578,11 +3577,6 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 
 	return 0;
 
-err_free_tx:
-	while (t--) {
-		kfree(priv->tx_ring[t]);
-		kfree(priv->tx_cq[t]);
-	}
 out:
 	mlx4_en_destroy_netdev(dev);
 	return err;
-- 
2.14.3


From 327a92246c0bb676d2c0cef62e50732f25c044bc Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Wed, 9 May 2018 18:35:13 +0300
Subject: [PATCH 12/55] net/mlx4_en: Verify coalescing parameters are in range

[ Upstream commit 6ad4e91c6d796b38a7f0e724db1de28eeb122bad ]

Add check of coalescing parameters received through ethtool are within
range of values supported by the HW.
Driver gets the coalescing rx/tx-usecs and rx/tx-frames as set by the
users through ethtool. The ethtool support up to 32 bit value for each.
However, mlx4 modify cq limits the coalescing time parameter and
coalescing frames parameters to 16 bits.
Return out of range error if user tries to set these parameters to
higher values.
Change type of sample-interval and adaptive_rx_coal parameters in mlx4
driver to u32 as the ethtool holds them as u32 and these parameters are
not limited due to mlx4 HW.

Fixes: c27a02cd94d6 ('mlx4_en: Add driver for Mellanox ConnectX 10GbE NIC')
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 16 ++++++++++++++++
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h    |  7 +++++--
 2 files changed, 21 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index f3302edba8b4..7f87db9734b8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1013,6 +1013,22 @@ static int mlx4_en_set_coalesce(struct net_device *dev,
 	if (!coal->tx_max_coalesced_frames_irq)
 		return -EINVAL;
 
+	if (coal->tx_coalesce_usecs > MLX4_EN_MAX_COAL_TIME ||
+	    coal->rx_coalesce_usecs > MLX4_EN_MAX_COAL_TIME ||
+	    coal->rx_coalesce_usecs_low > MLX4_EN_MAX_COAL_TIME ||
+	    coal->rx_coalesce_usecs_high > MLX4_EN_MAX_COAL_TIME) {
+		netdev_info(dev, "%s: maximum coalesce time supported is %d usecs\n",
+			    __func__, MLX4_EN_MAX_COAL_TIME);
+		return -ERANGE;
+	}
+
+	if (coal->tx_max_coalesced_frames > MLX4_EN_MAX_COAL_PKTS ||
+	    coal->rx_max_coalesced_frames > MLX4_EN_MAX_COAL_PKTS) {
+		netdev_info(dev, "%s: maximum coalesced frames supported is %d\n",
+			    __func__, MLX4_EN_MAX_COAL_PKTS);
+		return -ERANGE;
+	}
+
 	priv->rx_frames = (coal->rx_max_coalesced_frames ==
 			   MLX4_EN_AUTO_CONF) ?
 				MLX4_EN_RX_COAL_TARGET :
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index f470ae37d937..4dabaf025b12 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -132,6 +132,9 @@
 #define MLX4_EN_TX_COAL_PKTS	16
 #define MLX4_EN_TX_COAL_TIME	0x10
 
+#define MLX4_EN_MAX_COAL_PKTS	U16_MAX
+#define MLX4_EN_MAX_COAL_TIME	U16_MAX
+
 #define MLX4_EN_RX_RATE_LOW		400000
 #define MLX4_EN_RX_COAL_TIME_LOW	0
 #define MLX4_EN_RX_RATE_HIGH		450000
@@ -552,8 +555,8 @@ struct mlx4_en_priv {
 	u16 rx_usecs_low;
 	u32 pkt_rate_high;
 	u16 rx_usecs_high;
-	u16 sample_interval;
-	u16 adaptive_rx_coal;
+	u32 sample_interval;
+	u32 adaptive_rx_coal;
 	u32 msg_enable;
 	u32 loopback_ok;
 	u32 validate_loopback;
-- 
2.14.3


From 7de6ea696b14a1f11388b7718842e34822b792fe Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@mellanox.com>
Date: Thu, 22 Mar 2018 18:51:37 +0200
Subject: [PATCH 13/55] net/mlx5e: Err if asked to offload TC match on frag
 being first

[ Upstream commit f85900c3e13fdb61f040c9feecbcda601e0cdcfb ]

The HW doesn't support matching on frag first/later, return error if we are
asked to offload that.

Fixes: 3f7d0eb42d59 ("net/mlx5e: Offload TC matching on packets being IP fragments")
Signed-off-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 43234cabf444..c0b26281d0e2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1260,6 +1260,10 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 						  f->mask);
 		addr_type = key->addr_type;
 
+		/* the HW doesn't support frag first/later */
+		if (mask->flags & FLOW_DIS_FIRST_FRAG)
+			return -EOPNOTSUPP;
+
 		if (mask->flags & FLOW_DIS_IS_FRAGMENT) {
 			MLX5_SET(fte_match_set_lyr_2_4, headers_c, frag, 1);
 			MLX5_SET(fte_match_set_lyr_2_4, headers_v, frag,
-- 
2.14.3


From 81746a65a123d37fafc7a8a334ee7709f0882584 Mon Sep 17 00:00:00 2001
From: Adi Nissim <adin@mellanox.com>
Date: Wed, 25 Apr 2018 11:21:32 +0300
Subject: [PATCH 14/55] net/mlx5: E-Switch, Include VF RDMA stats in vport
 statistics

[ Upstream commit 88d725bbb43cd63a40c8ef70dd373f1d38ead2e3 ]

The host side reporting of VF vport statistics didn't include the VF
RDMA traffic.

Fixes: 3b751a2a418a ("net/mlx5: E-Switch, Introduce get vf statistics")
Signed-off-by: Adi Nissim <adin@mellanox.com>
Reported-by: Ariel Almog <ariela@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index c2b1d7d351fc..0f745df1506c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -2143,26 +2143,35 @@ int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,
 	memset(vf_stats, 0, sizeof(*vf_stats));
 	vf_stats->rx_packets =
 		MLX5_GET_CTR(out, received_eth_unicast.packets) +
+		MLX5_GET_CTR(out, received_ib_unicast.packets) +
 		MLX5_GET_CTR(out, received_eth_multicast.packets) +
+		MLX5_GET_CTR(out, received_ib_multicast.packets) +
 		MLX5_GET_CTR(out, received_eth_broadcast.packets);
 
 	vf_stats->rx_bytes =
 		MLX5_GET_CTR(out, received_eth_unicast.octets) +
+		MLX5_GET_CTR(out, received_ib_unicast.octets) +
 		MLX5_GET_CTR(out, received_eth_multicast.octets) +
+		MLX5_GET_CTR(out, received_ib_multicast.octets) +
 		MLX5_GET_CTR(out, received_eth_broadcast.octets);
 
 	vf_stats->tx_packets =
 		MLX5_GET_CTR(out, transmitted_eth_unicast.packets) +
+		MLX5_GET_CTR(out, transmitted_ib_unicast.packets) +
 		MLX5_GET_CTR(out, transmitted_eth_multicast.packets) +
+		MLX5_GET_CTR(out, transmitted_ib_multicast.packets) +
 		MLX5_GET_CTR(out, transmitted_eth_broadcast.packets);
 
 	vf_stats->tx_bytes =
 		MLX5_GET_CTR(out, transmitted_eth_unicast.octets) +
+		MLX5_GET_CTR(out, transmitted_ib_unicast.octets) +
 		MLX5_GET_CTR(out, transmitted_eth_multicast.octets) +
+		MLX5_GET_CTR(out, transmitted_ib_multicast.octets) +
 		MLX5_GET_CTR(out, transmitted_eth_broadcast.octets);
 
 	vf_stats->multicast =
-		MLX5_GET_CTR(out, received_eth_multicast.packets);
+		MLX5_GET_CTR(out, received_eth_multicast.packets) +
+		MLX5_GET_CTR(out, received_ib_multicast.packets);
 
 	vf_stats->broadcast =
 		MLX5_GET_CTR(out, received_eth_broadcast.packets);
-- 
2.14.3


From 559e2afcfdb3a3d5c0ce581411ae29bdf2576703 Mon Sep 17 00:00:00 2001
From: Roman Mashak <mrv@mojatatu.com>
Date: Fri, 11 May 2018 14:35:33 -0400
Subject: [PATCH 15/55] net sched actions: fix refcnt leak in skbmod

[ Upstream commit a52956dfc503f8cc5cfe6454959b7049fddb4413 ]

When application fails to pass flags in netlink TLV when replacing
existing skbmod action, the kernel will leak refcnt:

$ tc actions get action skbmod index 1
total acts 0

        action order 0: skbmod pipe set smac 00:11:22:33:44:55
         index 1 ref 1 bind 0

For example, at this point a buggy application replaces the action with
index 1 with new smac 00:aa:22:33:44:55, it fails because of zero flags,
however refcnt gets bumped:

$ tc actions get actions skbmod index 1
total acts 0

        action order 0: skbmod pipe set smac 00:11:22:33:44:55
         index 1 ref 2 bind 0
$

Tha patch fixes this by calling tcf_idr_release() on existing actions.

Fixes: 86da71b57383d ("net_sched: Introduce skbmod action")
Signed-off-by: Roman Mashak <mrv@mojatatu.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_skbmod.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index 7b0700f52b50..d87b611046bb 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -131,8 +131,11 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
 	if (exists && bind)
 		return 0;
 
-	if (!lflags)
+	if (!lflags) {
+		if (exists)
+			tcf_idr_release(*a, bind);
 		return -EINVAL;
+	}
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, parm->index, est, a,
-- 
2.14.3


From 5ebcfe39fb8f0b38cf70986612a3dcedd561cf52 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 2 May 2018 10:03:30 -0700
Subject: [PATCH 16/55] net_sched: fq: take care of throttled flows before
 reuse

[ Upstream commit 7df40c2673a1307c3260aab6f9d4b9bf97ca8fd7 ]

Normally, a socket can not be freed/reused unless all its TX packets
left qdisc and were TX-completed. However connect(AF_UNSPEC) allows
this to happen.

With commit fc59d5bdf1e3 ("pkt_sched: fq: clear time_next_packet for
reused flows") we cleared f->time_next_packet but took no special
action if the flow was still in the throttled rb-tree.

Since f->time_next_packet is the key used in the rb-tree searches,
blindly clearing it might break rb-tree integrity. We need to make
sure the flow is no longer in the rb-tree to avoid this problem.

Fixes: fc59d5bdf1e3 ("pkt_sched: fq: clear time_next_packet for reused flows")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_fq.c | 37 +++++++++++++++++++++++++------------
 1 file changed, 25 insertions(+), 12 deletions(-)

diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index a366e4c9413a..4808713c73b9 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -128,6 +128,28 @@ static bool fq_flow_is_detached(const struct fq_flow *f)
 	return f->next == &detached;
 }
 
+static bool fq_flow_is_throttled(const struct fq_flow *f)
+{
+	return f->next == &throttled;
+}
+
+static void fq_flow_add_tail(struct fq_flow_head *head, struct fq_flow *flow)
+{
+	if (head->first)
+		head->last->next = flow;
+	else
+		head->first = flow;
+	head->last = flow;
+	flow->next = NULL;
+}
+
+static void fq_flow_unset_throttled(struct fq_sched_data *q, struct fq_flow *f)
+{
+	rb_erase(&f->rate_node, &q->delayed);
+	q->throttled_flows--;
+	fq_flow_add_tail(&q->old_flows, f);
+}
+
 static void fq_flow_set_throttled(struct fq_sched_data *q, struct fq_flow *f)
 {
 	struct rb_node **p = &q->delayed.rb_node, *parent = NULL;
@@ -155,15 +177,6 @@ static void fq_flow_set_throttled(struct fq_sched_data *q, struct fq_flow *f)
 
 static struct kmem_cache *fq_flow_cachep __read_mostly;
 
-static void fq_flow_add_tail(struct fq_flow_head *head, struct fq_flow *flow)
-{
-	if (head->first)
-		head->last->next = flow;
-	else
-		head->first = flow;
-	head->last = flow;
-	flow->next = NULL;
-}
 
 /* limit number of collected flows per round */
 #define FQ_GC_MAX 8
@@ -267,6 +280,8 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q)
 				     f->socket_hash != sk->sk_hash)) {
 				f->credit = q->initial_quantum;
 				f->socket_hash = sk->sk_hash;
+				if (fq_flow_is_throttled(f))
+					fq_flow_unset_throttled(q, f);
 				f->time_next_packet = 0ULL;
 			}
 			return f;
@@ -438,9 +453,7 @@ static void fq_check_throttled(struct fq_sched_data *q, u64 now)
 			q->time_next_delayed_flow = f->time_next_packet;
 			break;
 		}
-		rb_erase(p, &q->delayed);
-		q->throttled_flows--;
-		fq_flow_add_tail(&q->old_flows, f);
+		fq_flow_unset_throttled(q, f);
 	}
 }
 
-- 
2.14.3


From cc81f589fef1cd5e76254a0a0135c8793152e523 Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.ibm.com>
Date: Wed, 2 May 2018 16:53:56 +0200
Subject: [PATCH 17/55] net/smc: restrict non-blocking connect finish

[ Upstream commit 784813aed6ba24a1f24e7e11d9d0f208cee37a7d ]

The smc_poll code tries to finish connect() if the socket is in
state SMC_INIT and polling of the internal CLC-socket returns with
EPOLLOUT. This makes sense for a select/poll call following a connect
call, but not without preceding connect().
With this patch smc_poll starts connect logic only, if the CLC-socket
is no longer in its initial state TCP_CLOSE.

In addition, a poll error on the internal CLC-socket is always
propagated to the SMC socket.

With this patch the code path mentioned by syzbot
https://syzkaller.appspot.com/bug?extid=03faa2dc16b8b64be396
is no longer possible.

Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Reported-by: syzbot+03faa2dc16b8b64be396@syzkaller.appspotmail.com
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/af_smc.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index afd5a935bbcb..5974ea7a3ef4 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1165,13 +1165,15 @@ static __poll_t smc_poll(struct file *file, struct socket *sock,
 		/* delegate to CLC child sock */
 		release_sock(sk);
 		mask = smc->clcsock->ops->poll(file, smc->clcsock, wait);
-		/* if non-blocking connect finished ... */
 		lock_sock(sk);
-		if ((sk->sk_state == SMC_INIT) && (mask & EPOLLOUT)) {
-			sk->sk_err = smc->clcsock->sk->sk_err;
-			if (sk->sk_err) {
-				mask |= EPOLLERR;
-			} else {
+		sk->sk_err = smc->clcsock->sk->sk_err;
+		if (sk->sk_err) {
+			mask |= EPOLLERR;
+		} else {
+			/* if non-blocking connect finished ... */
+			if (sk->sk_state == SMC_INIT &&
+			    mask & EPOLLOUT &&
+			    smc->clcsock->sk->sk_state != TCP_CLOSE) {
 				rc = smc_connect_rdma(smc);
 				if (rc < 0)
 					mask |= EPOLLERR;
-- 
2.14.3


From 98bd204b38dc06d85808baecc606fd4734413ca4 Mon Sep 17 00:00:00 2001
From: Lance Richardson <lance.richardson.net@gmail.com>
Date: Wed, 25 Apr 2018 10:21:54 -0400
Subject: [PATCH 18/55] net: support compat 64-bit time in {s,g}etsockopt

[ Upstream commit 988bf7243e03ef69238381594e0334a79cef74a6 ]

For the x32 ABI, struct timeval has two 64-bit fields. However
the kernel currently interprets the user-space values used for
the SO_RCVTIMEO and SO_SNDTIMEO socket options as having a pair
of 32-bit fields.

When the seconds portion of the requested timeout is less than 2**32,
the seconds portion of the effective timeout is correct but the
microseconds portion is zero.  When the seconds portion of the
requested timeout is zero and the microseconds portion is non-zero,
the kernel interprets the timeout as zero (never timeout).

Fix by using 64-bit time for SO_RCVTIMEO/SO_SNDTIMEO as required
for the ABI.

The code included below demonstrates the problem.

Results before patch:
    $ gcc -m64 -Wall -O2 -o socktmo socktmo.c && ./socktmo
    recv time: 2.008181 seconds
    send time: 2.015985 seconds

    $ gcc -m32 -Wall -O2 -o socktmo socktmo.c && ./socktmo
    recv time: 2.016763 seconds
    send time: 2.016062 seconds

    $ gcc -mx32 -Wall -O2 -o socktmo socktmo.c && ./socktmo
    recv time: 1.007239 seconds
    send time: 1.023890 seconds

Results after patch:
    $ gcc -m64 -O2 -Wall -o socktmo socktmo.c && ./socktmo
    recv time: 2.010062 seconds
    send time: 2.015836 seconds

    $ gcc -m32 -O2 -Wall -o socktmo socktmo.c && ./socktmo
    recv time: 2.013974 seconds
    send time: 2.015981 seconds

    $ gcc -mx32 -O2 -Wall -o socktmo socktmo.c && ./socktmo
    recv time: 2.030257 seconds
    send time: 2.013383 seconds

 #include <stdio.h>
 #include <stdlib.h>
 #include <sys/socket.h>
 #include <sys/types.h>
 #include <sys/time.h>

 void checkrc(char *str, int rc)
 {
         if (rc >= 0)
                 return;

         perror(str);
         exit(1);
 }

 static char buf[1024];
 int main(int argc, char **argv)
 {
         int rc;
         int socks[2];
         struct timeval tv;
         struct timeval start, end, delta;

         rc = socketpair(AF_UNIX, SOCK_STREAM, 0, socks);
         checkrc("socketpair", rc);

         /* set timeout to 1.999999 seconds */
         tv.tv_sec = 1;
         tv.tv_usec = 999999;
         rc = setsockopt(socks[0], SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof tv);
         rc = setsockopt(socks[0], SOL_SOCKET, SO_SNDTIMEO, &tv, sizeof tv);
         checkrc("setsockopt", rc);

         /* measure actual receive timeout */
         gettimeofday(&start, NULL);
         rc = recv(socks[0], buf, sizeof buf, 0);
         gettimeofday(&end, NULL);
         timersub(&end, &start, &delta);

         printf("recv time: %ld.%06ld seconds\n",
                (long)delta.tv_sec, (long)delta.tv_usec);

         /* fill send buffer */
         do {
                 rc = send(socks[0], buf, sizeof buf, 0);
         } while (rc > 0);

         /* measure actual send timeout */
         gettimeofday(&start, NULL);
         rc = send(socks[0], buf, sizeof buf, 0);
         gettimeofday(&end, NULL);
         timersub(&end, &start, &delta);

         printf("send time: %ld.%06ld seconds\n",
                (long)delta.tv_sec, (long)delta.tv_usec);
         exit(0);
 }

Fixes: 515c7af85ed9 ("x32: Use compat shims for {g,s}etsockopt")
Reported-by: Gopal RajagopalSai <gopalsr83@gmail.com>
Signed-off-by: Lance Richardson <lance.richardson.net@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/compat.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/compat.c b/net/compat.c
index 22381719718c..32ed993588d6 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -377,7 +377,8 @@ static int compat_sock_setsockopt(struct socket *sock, int level, int optname,
 	    optname == SO_ATTACH_REUSEPORT_CBPF)
 		return do_set_attach_filter(sock, level, optname,
 					    optval, optlen);
-	if (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO)
+	if (!COMPAT_USE_64BIT_TIME &&
+	    (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO))
 		return do_set_sock_timeout(sock, level, optname, optval, optlen);
 
 	return sock_setsockopt(sock, level, optname, optval, optlen);
@@ -442,7 +443,8 @@ static int do_get_sock_timeout(struct socket *sock, int level, int optname,
 static int compat_sock_getsockopt(struct socket *sock, int level, int optname,
 				char __user *optval, int __user *optlen)
 {
-	if (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO)
+	if (!COMPAT_USE_64BIT_TIME &&
+	    (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO))
 		return do_get_sock_timeout(sock, level, optname, optval, optlen);
 	return sock_getsockopt(sock, level, optname, optval, optlen);
 }
-- 
2.14.3


From c86254fe1f72e610548b178c13fce880cb490ef7 Mon Sep 17 00:00:00 2001
From: Dave Watson <davejwatson@fb.com>
Date: Tue, 1 May 2018 13:05:39 -0700
Subject: [PATCH 19/55] net/tls: Don't recursively call push_record during
 tls_write_space callbacks

[ Upstream commit c212d2c7fc4736d49be102fb7a1a545cdc2f1fea ]

It is reported that in some cases, write_space may be called in
do_tcp_sendpages, such that we recursively invoke do_tcp_sendpages again:

[  660.468802]  ? do_tcp_sendpages+0x8d/0x580
[  660.468826]  ? tls_push_sg+0x74/0x130 [tls]
[  660.468852]  ? tls_push_record+0x24a/0x390 [tls]
[  660.468880]  ? tls_write_space+0x6a/0x80 [tls]
...

tls_push_sg already does a loop over all sending sg's, so ignore
any tls_write_space notifications until we are done sending.
We then have to call the previous write_space to wake up
poll() waiters after we are done with the send loop.

Reported-by: Andre Tomt <andre@tomt.net>
Signed-off-by: Dave Watson <davejwatson@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h  | 1 +
 net/tls/tls_main.c | 7 +++++++
 2 files changed, 8 insertions(+)

diff --git a/include/net/tls.h b/include/net/tls.h
index 4913430ab807..f5c928a76994 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -102,6 +102,7 @@ struct tls_context {
 	struct scatterlist *partially_sent_record;
 	u16 partially_sent_offset;
 	unsigned long flags;
+	bool in_tcp_sendpages;
 
 	u16 pending_open_record_frags;
 	int (*push_pending_record)(struct sock *sk, int flags);
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index d824d548447e..6f43ba5c647d 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -107,6 +107,7 @@ int tls_push_sg(struct sock *sk,
 	size = sg->length - offset;
 	offset += sg->offset;
 
+	ctx->in_tcp_sendpages = true;
 	while (1) {
 		if (sg_is_last(sg))
 			sendpage_flags = flags;
@@ -141,6 +142,8 @@ int tls_push_sg(struct sock *sk,
 	}
 
 	clear_bit(TLS_PENDING_CLOSED_RECORD, &ctx->flags);
+	ctx->in_tcp_sendpages = false;
+	ctx->sk_write_space(sk);
 
 	return 0;
 }
@@ -210,6 +213,10 @@ static void tls_write_space(struct sock *sk)
 {
 	struct tls_context *ctx = tls_get_ctx(sk);
 
+	/* We are already sending pages, ignore notification */
+	if (ctx->in_tcp_sendpages)
+		return;
+
 	if (!sk->sk_write_pending && tls_is_pending_closed_record(ctx)) {
 		gfp_t sk_allocation = sk->sk_allocation;
 		int rc;
-- 
2.14.3


From bd73032f2710d66ff3ddd899b26925cda60113b4 Mon Sep 17 00:00:00 2001
From: Andre Tomt <andre@tomt.net>
Date: Mon, 7 May 2018 04:24:39 +0200
Subject: [PATCH 20/55] net/tls: Fix connection stall on partial tls record

[ Upstream commit 080324c36ade319f57e505633ab54f6f53289b45 ]

In the case of writing a partial tls record we forgot to clear the
ctx->in_tcp_sendpages flag, causing some connections to stall.

Fixes: c212d2c7fc47 ("net/tls: Don't recursively call push_record during tls_write_space callbacks")
Signed-off-by: Andre Tomt <andre@tomt.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 6f43ba5c647d..b51180c1479a 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -128,6 +128,7 @@ int tls_push_sg(struct sock *sk,
 			offset -= sg->offset;
 			ctx->partially_sent_offset = offset;
 			ctx->partially_sent_record = (void *)sg;
+			ctx->in_tcp_sendpages = false;
 			return ret;
 		}
 
-- 
2.14.3


From 431c80b199146af02149d64ea914e1c74a9b4358 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Thu, 3 May 2018 18:13:25 +0200
Subject: [PATCH 21/55] openvswitch: Don't swap table in nlattr_set() after
 OVS_ATTR_NESTED is found

[ Upstream commit 72f17baf2352ded6a1d3f4bb2d15da8c678cd2cb ]

If an OVS_ATTR_NESTED attribute type is found while walking
through netlink attributes, we call nlattr_set() recursively
passing the length table for the following nested attributes, if
different from the current one.

However, once we're done with those sub-nested attributes, we
should continue walking through attributes using the current
table, instead of using the one related to the sub-nested
attributes.

For example, given this sequence:

1  OVS_KEY_ATTR_PRIORITY
2  OVS_KEY_ATTR_TUNNEL
3	OVS_TUNNEL_KEY_ATTR_ID
4	OVS_TUNNEL_KEY_ATTR_IPV4_SRC
5	OVS_TUNNEL_KEY_ATTR_IPV4_DST
6	OVS_TUNNEL_KEY_ATTR_TTL
7	OVS_TUNNEL_KEY_ATTR_TP_SRC
8	OVS_TUNNEL_KEY_ATTR_TP_DST
9  OVS_KEY_ATTR_IN_PORT
10 OVS_KEY_ATTR_SKB_MARK
11 OVS_KEY_ATTR_MPLS

we switch to the 'ovs_tunnel_key_lens' table on attribute #3,
and we don't switch back to 'ovs_key_lens' while setting
attributes #9 to #11 in the sequence. As OVS_KEY_ATTR_MPLS
evaluates to 21, and the array size of 'ovs_tunnel_key_lens' is
15, we also get this kind of KASan splat while accessing the
wrong table:

[ 7654.586496] ==================================================================
[ 7654.594573] BUG: KASAN: global-out-of-bounds in nlattr_set+0x164/0xde9 [openvswitch]
[ 7654.603214] Read of size 4 at addr ffffffffc169ecf0 by task handler29/87430
[ 7654.610983]
[ 7654.612644] CPU: 21 PID: 87430 Comm: handler29 Kdump: loaded Not tainted 3.10.0-866.el7.test.x86_64 #1
[ 7654.623030] Hardware name: Dell Inc. PowerEdge R730/072T6D, BIOS 2.1.7 06/16/2016
[ 7654.631379] Call Trace:
[ 7654.634108]  [<ffffffffb65a7c50>] dump_stack+0x19/0x1b
[ 7654.639843]  [<ffffffffb53ff373>] print_address_description+0x33/0x290
[ 7654.647129]  [<ffffffffc169b37b>] ? nlattr_set+0x164/0xde9 [openvswitch]
[ 7654.654607]  [<ffffffffb53ff812>] kasan_report.part.3+0x242/0x330
[ 7654.661406]  [<ffffffffb53ff9b4>] __asan_report_load4_noabort+0x34/0x40
[ 7654.668789]  [<ffffffffc169b37b>] nlattr_set+0x164/0xde9 [openvswitch]
[ 7654.676076]  [<ffffffffc167ef68>] ovs_nla_get_match+0x10c8/0x1900 [openvswitch]
[ 7654.684234]  [<ffffffffb61e9cc8>] ? genl_rcv+0x28/0x40
[ 7654.689968]  [<ffffffffb61e7733>] ? netlink_unicast+0x3f3/0x590
[ 7654.696574]  [<ffffffffc167dea0>] ? ovs_nla_put_tunnel_info+0xb0/0xb0 [openvswitch]
[ 7654.705122]  [<ffffffffb4f41b50>] ? unwind_get_return_address+0xb0/0xb0
[ 7654.712503]  [<ffffffffb65d9355>] ? system_call_fastpath+0x1c/0x21
[ 7654.719401]  [<ffffffffb4f41d79>] ? update_stack_state+0x229/0x370
[ 7654.726298]  [<ffffffffb4f41d79>] ? update_stack_state+0x229/0x370
[ 7654.733195]  [<ffffffffb53fe4b5>] ? kasan_unpoison_shadow+0x35/0x50
[ 7654.740187]  [<ffffffffb53fe62a>] ? kasan_kmalloc+0xaa/0xe0
[ 7654.746406]  [<ffffffffb53fec32>] ? kasan_slab_alloc+0x12/0x20
[ 7654.752914]  [<ffffffffb53fe711>] ? memset+0x31/0x40
[ 7654.758456]  [<ffffffffc165bf92>] ovs_flow_cmd_new+0x2b2/0xf00 [openvswitch]

[snip]

[ 7655.132484] The buggy address belongs to the variable:
[ 7655.138226]  ovs_tunnel_key_lens+0xf0/0xffffffffffffd400 [openvswitch]
[ 7655.145507]
[ 7655.147166] Memory state around the buggy address:
[ 7655.152514]  ffffffffc169eb80: 00 00 00 00 00 00 00 00 00 00 fa fa fa fa fa fa
[ 7655.160585]  ffffffffc169ec00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[ 7655.168644] >ffffffffc169ec80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 fa fa
[ 7655.176701]                                                              ^
[ 7655.184372]  ffffffffc169ed00: fa fa fa fa 00 00 00 00 fa fa fa fa 00 00 00 05
[ 7655.192431]  ffffffffc169ed80: fa fa fa fa 00 00 00 00 00 00 00 00 00 00 00 00
[ 7655.200490] ==================================================================

Reported-by: Hangbin Liu <liuhangbin@gmail.com>
Fixes: 982b52700482 ("openvswitch: Fix mask generation for nested attributes.")
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/flow_netlink.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 7322aa1e382e..492ab0c36f7c 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -1712,13 +1712,10 @@ static void nlattr_set(struct nlattr *attr, u8 val,
 
 	/* The nlattr stream should already have been validated */
 	nla_for_each_nested(nla, attr, rem) {
-		if (tbl[nla_type(nla)].len == OVS_ATTR_NESTED) {
-			if (tbl[nla_type(nla)].next)
-				tbl = tbl[nla_type(nla)].next;
-			nlattr_set(nla, val, tbl);
-		} else {
+		if (tbl[nla_type(nla)].len == OVS_ATTR_NESTED)
+			nlattr_set(nla, val, tbl[nla_type(nla)].next ? : tbl);
+		else
 			memset(nla_data(nla), val, nla_len(nla));
-		}
 
 		if (nla_type(nla) == OVS_KEY_ATTR_CT_STATE)
 			*(u32 *)nla_data(nla) &= CT_SUPPORTED_MASK;
-- 
2.14.3


From 3f698bb3852c361e33c0d52fe25866b725167ea6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Wed, 2 May 2018 22:22:54 +0200
Subject: [PATCH 22/55] qmi_wwan: do not steal interfaces from class drivers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 5697db4a696c41601a1d15c1922150b4dbf5726c ]

The USB_DEVICE_INTERFACE_NUMBER matching macro assumes that
the { vendorid, productid, interfacenumber } set uniquely
identifies one specific function.  This has proven to fail
for some configurable devices. One example is the Quectel
EM06/EP06 where the same interface number can be either
QMI or MBIM, without the device ID changing either.

Fix by requiring the vendor-specific class for interface number
based matching.  Functions of other classes can and should use
class based matching instead.

Fixes: 03304bcb5ec4 ("net: qmi_wwan: use fixed interface number matching")
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 51c68fc416fa..42565dd33aa6 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1344,6 +1344,18 @@ static int qmi_wwan_probe(struct usb_interface *intf,
 		id->driver_info = (unsigned long)&qmi_wwan_info;
 	}
 
+	/* There are devices where the same interface number can be
+	 * configured as different functions. We should only bind to
+	 * vendor specific functions when matching on interface number
+	 */
+	if (id->match_flags & USB_DEVICE_ID_MATCH_INT_NUMBER &&
+	    desc->bInterfaceClass != USB_CLASS_VENDOR_SPEC) {
+		dev_dbg(&intf->dev,
+			"Rejecting interface number match for class %02x\n",
+			desc->bInterfaceClass);
+		return -ENODEV;
+	}
+
 	/* Quectel EC20 quirk where we've QMI on interface 4 instead of 0 */
 	if (quectel_ec20_detected(intf) && desc->bInterfaceNumber == 0) {
 		dev_dbg(&intf->dev, "Quectel EC20 quirk, skipping interface 0\n");
-- 
2.14.3


From 5e40f3101965cbb7674413abaf9597788dfbd210 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 7 May 2018 21:11:21 +0200
Subject: [PATCH 23/55] r8169: fix powering up RTL8168h

[ Upstream commit 3148dedfe79e422f448a10250d3e2cdf8b7ee617 ]

Since commit a92a08499b1f "r8169: improve runtime pm in general and
suspend unused ports" interfaces w/o link are runtime-suspended after
10s. On systems where drivers take longer to load this can lead to the
situation that the interface is runtime-suspended already when it's
initially brought up.
This shouldn't be a problem because rtl_open() resumes MAC/PHY.
However with at least one chip version the interface doesn't properly
come up, as reported here:
https://bugzilla.kernel.org/show_bug.cgi?id=199549

The vendor driver uses a delay to give certain chip versions some
time to resume before starting the PHY configuration. So let's do
the same. I don't know which chip versions may be affected,
therefore apply this delay always.

This patch was reported to fix the issue for RTL8168h.
I was able to reproduce the issue on an Asus H310I-Plus which also
uses a RTL8168h. Also in my case the patch fixed the issue.

Reported-by: Slava Kardakov <ojab@ojab.ru>
Tested-by: Slava Kardakov <ojab@ojab.ru>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index b4779acb6b5c..18bb1e226e6d 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -5087,6 +5087,9 @@ static void rtl_pll_power_down(struct rtl8169_private *tp)
 static void rtl_pll_power_up(struct rtl8169_private *tp)
 {
 	rtl_generic_op(tp, tp->pll_power_ops.up);
+
+	/* give MAC/PHY some time to resume */
+	msleep(20);
 }
 
 static void rtl_init_pll_power_ops(struct rtl8169_private *tp)
-- 
2.14.3


From a10d4c1ec190d42246ad79365008c67cf367884e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 2 May 2018 14:53:39 -0700
Subject: [PATCH 24/55] rds: do not leak kernel memory to user land

[ Upstream commit eb80ca476ec11f67a62691a93604b405ffc7d80c ]

syzbot/KMSAN reported an uninit-value in put_cmsg(), originating
from rds_cmsg_recv().

Simply clear the structure, since we have holes there, or since
rx_traces might be smaller than RDS_MSG_RX_DGRAM_TRACE_MAX.

BUG: KMSAN: uninit-value in copy_to_user include/linux/uaccess.h:184 [inline]
BUG: KMSAN: uninit-value in put_cmsg+0x600/0x870 net/core/scm.c:242
CPU: 0 PID: 4459 Comm: syz-executor582 Not tainted 4.16.0+ #87
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x185/0x1d0 lib/dump_stack.c:53
 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067
 kmsan_internal_check_memory+0x135/0x1e0 mm/kmsan/kmsan.c:1157
 kmsan_copy_to_user+0x69/0x160 mm/kmsan/kmsan.c:1199
 copy_to_user include/linux/uaccess.h:184 [inline]
 put_cmsg+0x600/0x870 net/core/scm.c:242
 rds_cmsg_recv net/rds/recv.c:570 [inline]
 rds_recvmsg+0x2db5/0x3170 net/rds/recv.c:657
 sock_recvmsg_nosec net/socket.c:803 [inline]
 sock_recvmsg+0x1d0/0x230 net/socket.c:810
 ___sys_recvmsg+0x3fb/0x810 net/socket.c:2205
 __sys_recvmsg net/socket.c:2250 [inline]
 SYSC_recvmsg+0x298/0x3c0 net/socket.c:2262
 SyS_recvmsg+0x54/0x80 net/socket.c:2257
 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x3d/0xa2

Fixes: 3289025aedc0 ("RDS: add receive message trace used by application")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Cc: linux-rdma <linux-rdma@vger.kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/recv.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/rds/recv.c b/net/rds/recv.c
index b25bcfe411ca..555f07ccf0dc 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -558,6 +558,7 @@ static int rds_cmsg_recv(struct rds_incoming *inc, struct msghdr *msg,
 		struct rds_cmsg_rx_trace t;
 		int i, j;
 
+		memset(&t, 0, sizeof(t));
 		inc->i_rx_lat_trace[RDS_MSG_RX_CMSG] = local_clock();
 		t.rx_traces =  rs->rs_rx_traces;
 		for (i = 0; i < rs->rs_rx_traces; i++) {
-- 
2.14.3


From 46028874c7adc3f709055bf01b6e96c464ca987f Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sat, 5 May 2018 14:59:47 +0800
Subject: [PATCH 25/55] sctp: delay the authentication for the duplicated
 cookie-echo chunk

[ Upstream commit 59d8d4434f429b4fa8a346fd889058bda427a837 ]

Now sctp only delays the authentication for the normal cookie-echo
chunk by setting chunk->auth_chunk in sctp_endpoint_bh_rcv(). But
for the duplicated one with auth, in sctp_assoc_bh_rcv(), it does
authentication first based on the old asoc, which will definitely
fail due to the different auth info in the old asoc.

The duplicated cookie-echo chunk will create a new asoc with the
auth info from this chunk, and the authentication should also be
done with the new asoc's auth info for all of the collision 'A',
'B' and 'D'. Otherwise, the duplicated cookie-echo chunk with auth
will never pass the authentication and create the new connection.

This issue exists since very beginning, and this fix is to make
sctp_assoc_bh_rcv() follow the way sctp_endpoint_bh_rcv() does
for the normal cookie-echo chunk to delay the authentication.

While at it, remove the unused params from sctp_sf_authenticate()
and define sctp_auth_chunk_verify() used for all the places that
do the delayed authentication.

v1->v2:
  fix the typo in changelog as Marcelo noticed.

Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/associola.c    | 30 ++++++++++++++++-
 net/sctp/sm_statefuns.c | 86 ++++++++++++++++++++++++++-----------------------
 2 files changed, 75 insertions(+), 41 deletions(-)

diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 837806dd5799..a47179da24e6 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -1024,8 +1024,9 @@ static void sctp_assoc_bh_rcv(struct work_struct *work)
 	struct sctp_endpoint *ep;
 	struct sctp_chunk *chunk;
 	struct sctp_inq *inqueue;
-	int state;
+	int first_time = 1;	/* is this the first time through the loop */
 	int error = 0;
+	int state;
 
 	/* The association should be held so we should be safe. */
 	ep = asoc->ep;
@@ -1036,6 +1037,30 @@ static void sctp_assoc_bh_rcv(struct work_struct *work)
 		state = asoc->state;
 		subtype = SCTP_ST_CHUNK(chunk->chunk_hdr->type);
 
+		/* If the first chunk in the packet is AUTH, do special
+		 * processing specified in Section 6.3 of SCTP-AUTH spec
+		 */
+		if (first_time && subtype.chunk == SCTP_CID_AUTH) {
+			struct sctp_chunkhdr *next_hdr;
+
+			next_hdr = sctp_inq_peek(inqueue);
+			if (!next_hdr)
+				goto normal;
+
+			/* If the next chunk is COOKIE-ECHO, skip the AUTH
+			 * chunk while saving a pointer to it so we can do
+			 * Authentication later (during cookie-echo
+			 * processing).
+			 */
+			if (next_hdr->type == SCTP_CID_COOKIE_ECHO) {
+				chunk->auth_chunk = skb_clone(chunk->skb,
+							      GFP_ATOMIC);
+				chunk->auth = 1;
+				continue;
+			}
+		}
+
+normal:
 		/* SCTP-AUTH, Section 6.3:
 		 *    The receiver has a list of chunk types which it expects
 		 *    to be received only after an AUTH-chunk.  This list has
@@ -1074,6 +1099,9 @@ static void sctp_assoc_bh_rcv(struct work_struct *work)
 		/* If there is an error on chunk, discard this packet. */
 		if (error && chunk)
 			chunk->pdiscard = 1;
+
+		if (first_time)
+			first_time = 0;
 	}
 	sctp_association_put(asoc);
 }
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index eb7905ffe5f2..e8c9c94f5a05 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -153,10 +153,7 @@ static enum sctp_disposition sctp_sf_violation_chunk(
 					struct sctp_cmd_seq *commands);
 
 static enum sctp_ierror sctp_sf_authenticate(
-					struct net *net,
-					const struct sctp_endpoint *ep,
 					const struct sctp_association *asoc,
-					const union sctp_subtype type,
 					struct sctp_chunk *chunk);
 
 static enum sctp_disposition __sctp_sf_do_9_1_abort(
@@ -621,6 +618,38 @@ enum sctp_disposition sctp_sf_do_5_1C_ack(struct net *net,
 	return SCTP_DISPOSITION_CONSUME;
 }
 
+static bool sctp_auth_chunk_verify(struct net *net, struct sctp_chunk *chunk,
+				   const struct sctp_association *asoc)
+{
+	struct sctp_chunk auth;
+
+	if (!chunk->auth_chunk)
+		return true;
+
+	/* SCTP-AUTH:  auth_chunk pointer is only set when the cookie-echo
+	 * is supposed to be authenticated and we have to do delayed
+	 * authentication.  We've just recreated the association using
+	 * the information in the cookie and now it's much easier to
+	 * do the authentication.
+	 */
+
+	/* Make sure that we and the peer are AUTH capable */
+	if (!net->sctp.auth_enable || !asoc->peer.auth_capable)
+		return false;
+
+	/* set-up our fake chunk so that we can process it */
+	auth.skb = chunk->auth_chunk;
+	auth.asoc = chunk->asoc;
+	auth.sctp_hdr = chunk->sctp_hdr;
+	auth.chunk_hdr = (struct sctp_chunkhdr *)
+				skb_push(chunk->auth_chunk,
+					 sizeof(struct sctp_chunkhdr));
+	skb_pull(chunk->auth_chunk, sizeof(struct sctp_chunkhdr));
+	auth.transport = chunk->transport;
+
+	return sctp_sf_authenticate(asoc, &auth) == SCTP_IERROR_NO_ERROR;
+}
+
 /*
  * Respond to a normal COOKIE ECHO chunk.
  * We are the side that is being asked for an association.
@@ -758,37 +787,9 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net,
 	if (error)
 		goto nomem_init;
 
-	/* SCTP-AUTH:  auth_chunk pointer is only set when the cookie-echo
-	 * is supposed to be authenticated and we have to do delayed
-	 * authentication.  We've just recreated the association using
-	 * the information in the cookie and now it's much easier to
-	 * do the authentication.
-	 */
-	if (chunk->auth_chunk) {
-		struct sctp_chunk auth;
-		enum sctp_ierror ret;
-
-		/* Make sure that we and the peer are AUTH capable */
-		if (!net->sctp.auth_enable || !new_asoc->peer.auth_capable) {
-			sctp_association_free(new_asoc);
-			return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
-		}
-
-		/* set-up our fake chunk so that we can process it */
-		auth.skb = chunk->auth_chunk;
-		auth.asoc = chunk->asoc;
-		auth.sctp_hdr = chunk->sctp_hdr;
-		auth.chunk_hdr = (struct sctp_chunkhdr *)
-					skb_push(chunk->auth_chunk,
-						 sizeof(struct sctp_chunkhdr));
-		skb_pull(chunk->auth_chunk, sizeof(struct sctp_chunkhdr));
-		auth.transport = chunk->transport;
-
-		ret = sctp_sf_authenticate(net, ep, new_asoc, type, &auth);
-		if (ret != SCTP_IERROR_NO_ERROR) {
-			sctp_association_free(new_asoc);
-			return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
-		}
+	if (!sctp_auth_chunk_verify(net, chunk, new_asoc)) {
+		sctp_association_free(new_asoc);
+		return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
 	}
 
 	repl = sctp_make_cookie_ack(new_asoc, chunk);
@@ -1758,13 +1759,15 @@ static enum sctp_disposition sctp_sf_do_dupcook_a(
 			       GFP_ATOMIC))
 		goto nomem;
 
+	if (!sctp_auth_chunk_verify(net, chunk, new_asoc))
+		return SCTP_DISPOSITION_DISCARD;
+
 	/* Make sure no new addresses are being added during the
 	 * restart.  Though this is a pretty complicated attack
 	 * since you'd have to get inside the cookie.
 	 */
-	if (!sctp_sf_check_restart_addrs(new_asoc, asoc, chunk, commands)) {
+	if (!sctp_sf_check_restart_addrs(new_asoc, asoc, chunk, commands))
 		return SCTP_DISPOSITION_CONSUME;
-	}
 
 	/* If the endpoint is in the SHUTDOWN-ACK-SENT state and recognizes
 	 * the peer has restarted (Action A), it MUST NOT setup a new
@@ -1870,6 +1873,9 @@ static enum sctp_disposition sctp_sf_do_dupcook_b(
 			       GFP_ATOMIC))
 		goto nomem;
 
+	if (!sctp_auth_chunk_verify(net, chunk, new_asoc))
+		return SCTP_DISPOSITION_DISCARD;
+
 	/* Update the content of current association.  */
 	sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc));
 	sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE,
@@ -1964,6 +1970,9 @@ static enum sctp_disposition sctp_sf_do_dupcook_d(
 	 * a COOKIE ACK.
 	 */
 
+	if (!sctp_auth_chunk_verify(net, chunk, asoc))
+		return SCTP_DISPOSITION_DISCARD;
+
 	/* Don't accidentally move back into established state. */
 	if (asoc->state < SCTP_STATE_ESTABLISHED) {
 		sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP,
@@ -4108,10 +4117,7 @@ enum sctp_disposition sctp_sf_eat_fwd_tsn_fast(
  * The return value is the disposition of the chunk.
  */
 static enum sctp_ierror sctp_sf_authenticate(
-					struct net *net,
-					const struct sctp_endpoint *ep,
 					const struct sctp_association *asoc,
-					const union sctp_subtype type,
 					struct sctp_chunk *chunk)
 {
 	struct sctp_authhdr *auth_hdr;
@@ -4209,7 +4215,7 @@ enum sctp_disposition sctp_sf_eat_auth(struct net *net,
 						  commands);
 
 	auth_hdr = (struct sctp_authhdr *)chunk->skb->data;
-	error = sctp_sf_authenticate(net, ep, asoc, type, chunk);
+	error = sctp_sf_authenticate(asoc, chunk);
 	switch (error) {
 	case SCTP_IERROR_AUTH_BAD_HMAC:
 		/* Generate the ERROR chunk and discard the rest
-- 
2.14.3


From 670642d1fa8b75740a3f7abf2971be50f1042625 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 2 May 2018 13:45:12 +0800
Subject: [PATCH 26/55] sctp: fix the issue that the cookie-ack with auth can't
 get processed

[ Upstream commit ce402f044e4e432c296f90eaabb8dbe8f3624391 ]

When auth is enabled for cookie-ack chunk, in sctp_inq_pop, sctp
processes auth chunk first, then continues to the next chunk in
this packet if chunk_end + chunk_hdr size < skb_tail_pointer().
Otherwise, it will go to the next packet or discard this chunk.

However, it missed the fact that cookie-ack chunk's size is equal
to chunk_hdr size, which couldn't match that check, and thus this
chunk would not get processed.

This patch fixes it by changing the check to chunk_end + chunk_hdr
size <= skb_tail_pointer().

Fixes: 26b87c788100 ("net: sctp: fix remote memory pressure from excessive queueing")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/inqueue.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c
index 23ebc5318edc..eb93ffe2408b 100644
--- a/net/sctp/inqueue.c
+++ b/net/sctp/inqueue.c
@@ -217,7 +217,7 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue)
 	skb_pull(chunk->skb, sizeof(*ch));
 	chunk->subh.v = NULL; /* Subheader is no longer valid.  */
 
-	if (chunk->chunk_end + sizeof(*ch) < skb_tail_pointer(chunk->skb)) {
+	if (chunk->chunk_end + sizeof(*ch) <= skb_tail_pointer(chunk->skb)) {
 		/* This is not a singleton */
 		chunk->singleton = 0;
 	} else if (chunk->chunk_end > skb_tail_pointer(chunk->skb)) {
-- 
2.14.3


From f8aee735e84b10c5babc0ef94eddd00c222e13aa Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 26 Apr 2018 14:13:57 +0800
Subject: [PATCH 27/55] sctp: handle two v4 addrs comparison in
 sctp_inet6_cmp_addr

[ Upstream commit d625329b06e46bd20baf9ee40847d11982569204 ]

Since sctp ipv6 socket also supports v4 addrs, it's possible to
compare two v4 addrs in pf v6 .cmp_addr, sctp_inet6_cmp_addr.

However after Commit 1071ec9d453a ("sctp: do not check port in
sctp_inet6_cmp_addr"), it no longer calls af1->cmp_addr, which
in this case is sctp_v4_cmp_addr, but calls __sctp_v6_cmp_addr
where it handles them as two v6 addrs. It would cause a out of
bounds crash.

syzbot found this crash when trying to bind two v4 addrs to a
v6 socket.

This patch fixes it by adding the process for two v4 addrs in
sctp_inet6_cmp_addr.

Fixes: 1071ec9d453a ("sctp: do not check port in sctp_inet6_cmp_addr")
Reported-by: syzbot+cd494c1dd681d4d93ebb@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ipv6.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 07b64719d1bc..351e80c59211 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -866,6 +866,9 @@ static int sctp_inet6_cmp_addr(const union sctp_addr *addr1,
 	if (sctp_is_any(sk, addr1) || sctp_is_any(sk, addr2))
 		return 1;
 
+	if (addr1->sa.sa_family == AF_INET && addr2->sa.sa_family == AF_INET)
+		return addr1->v4.sin_addr.s_addr == addr2->v4.sin_addr.s_addr;
+
 	return __sctp_v6_cmp_addr(addr1, addr2);
 }
 
-- 
2.14.3


From 8284ece1a3765962c7b22189aaf124bf8aae1484 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 10 May 2018 17:34:13 +0800
Subject: [PATCH 28/55] sctp: remove sctp_chunk_put from fail_mark err path in
 sctp_ulpevent_make_rcvmsg

[ Upstream commit 6910e25de2257e2c82c7a2d126e3463cd8e50810 ]

In Commit 1f45f78f8e51 ("sctp: allow GSO frags to access the chunk too"),
it held the chunk in sctp_ulpevent_make_rcvmsg to access it safely later
in recvmsg. However, it also added sctp_chunk_put in fail_mark err path,
which is only triggered before holding the chunk.

syzbot reported a use-after-free crash happened on this err path, where
it shouldn't call sctp_chunk_put.

This patch simply removes this call.

Fixes: 1f45f78f8e51 ("sctp: allow GSO frags to access the chunk too")
Reported-by: syzbot+141d898c5f24489db4aa@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ulpevent.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c
index 84207ad33e8e..8cb7d9858270 100644
--- a/net/sctp/ulpevent.c
+++ b/net/sctp/ulpevent.c
@@ -715,7 +715,6 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc,
 	return event;
 
 fail_mark:
-	sctp_chunk_put(chunk);
 	kfree_skb(skb);
 fail:
 	return NULL;
-- 
2.14.3


From d5a0ec9f808701af7fe7539ca4bbac6c78c28e5e Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 2 May 2018 13:39:46 +0800
Subject: [PATCH 29/55] sctp: use the old asoc when making the cookie-ack chunk
 in dupcook_d

[ Upstream commit 46e16d4b956867013e0bbd7f2bad206f4aa55752 ]

When processing a duplicate cookie-echo chunk, for case 'D', sctp will
not process the param from this chunk. It means old asoc has nothing
to be updated, and the new temp asoc doesn't have the complete info.

So there's no reason to use the new asoc when creating the cookie-ack
chunk. Otherwise, like when auth is enabled for cookie-ack, the chunk
can not be set with auth, and it will definitely be dropped by peer.

This issue is there since very beginning, and we fix it by using the
old asoc instead.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sm_statefuns.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index e8c9c94f5a05..88573c57e106 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -2012,7 +2012,7 @@ static enum sctp_disposition sctp_sf_do_dupcook_d(
 		}
 	}
 
-	repl = sctp_make_cookie_ack(new_asoc, chunk);
+	repl = sctp_make_cookie_ack(asoc, chunk);
 	if (!repl)
 		goto nomem;
 
-- 
2.14.3


From b5bfc7f93fb7e7f31b68dba20337e2be2178da7b Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Tue, 1 May 2018 21:45:41 -0400
Subject: [PATCH 30/55] tcp_bbr: fix to zero idle_restart only upon S/ACKed
 data

[ Upstream commit e6e6a278b1eaffa19d42186bfacd1ffc15a50b3f ]

Previously the bbr->idle_restart tracking was zeroing out the
bbr->idle_restart bit upon ACKs that did not SACK or ACK anything,
e.g. receiving incoming data or receiver window updates. In such
situations BBR would forget that this was a restart-from-idle
situation, and if the min_rtt had expired it would unnecessarily enter
PROBE_RTT (even though we were actually restarting from idle but had
merely forgotten that fact).

The fix is simple: we need to remember we are restarting from idle
until we receive a S/ACK for some data (a S/ACK for the first flight
of data we send as we are restarting).

This commit is a stable candidate for kernels back as far as 4.9.

Fixes: 0f8782ea1497 ("tcp_bbr: add BBR congestion control")
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: Priyaranjan Jha <priyarjha@google.com>
Signed-off-by: Yousuk Seung <ysseung@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_bbr.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index a471f696e13c..29478454b527 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -803,7 +803,9 @@ static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs)
 			}
 		}
 	}
-	bbr->idle_restart = 0;
+	/* Restart after idle ends only once we process a new S/ACK for data */
+	if (rs->delivered > 0)
+		bbr->idle_restart = 0;
 }
 
 static void bbr_update_model(struct sock *sk, const struct rate_sample *rs)
-- 
2.14.3


From ea237d4f6c828b5f6ac8f3e9e9b7a9c3133cc9f0 Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Wed, 25 Apr 2018 11:33:08 -0700
Subject: [PATCH 31/55] tcp: ignore Fast Open on repair mode

[ Upstream commit 16ae6aa1705299789f71fdea59bfb119c1fbd9c0 ]

The TCP repair sequence of operation is to first set the socket in
repair mode, then inject the TCP stats into the socket with repair
socket options, then call connect() to re-activate the socket. The
connect syscall simply returns and set state to ESTABLISHED
mode. As a result Fast Open is meaningless for TCP repair.

However allowing sendto() system call with MSG_FASTOPEN flag half-way
during the repair operation could unexpectedly cause data to be
sent, before the operation finishes changing the internal TCP stats
(e.g. MSS).  This in turn triggers TCP warnings on inconsistent
packet accounting.

The fix is to simply disallow Fast Open operation once the socket
is in the repair mode.

Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 1ab8733dac5f..f47e9cd2c4ea 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1210,7 +1210,8 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 			uarg->zerocopy = 0;
 	}
 
-	if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect)) {
+	if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect) &&
+	    !tp->repair) {
 		err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size);
 		if (err == -EINPROGRESS && copied_syn > 0)
 			goto out;
-- 
2.14.3


From 80a062f25c4444137ead44159ced442c25bbe3e7 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Thu, 3 May 2018 20:04:27 -0400
Subject: [PATCH 32/55] tg3: Fix vunmap() BUG_ON() triggered from
 tg3_free_consistent().

[ Upstream commit d89a2adb8bfe6f8949ff389acdb9fa298b6e8e12 ]

tg3_free_consistent() calls dma_free_coherent() to free tp->hw_stats
under spinlock and can trigger BUG_ON() in vunmap() because vunmap()
may sleep.  Fix it by removing the spinlock and relying on the
TG3_FLAG_INIT_COMPLETE flag to prevent race conditions between
tg3_get_stats64() and tg3_free_consistent().  TG3_FLAG_INIT_COMPLETE
is always cleared under tp->lock before tg3_free_consistent()
and therefore tg3_get_stats64() can safely access tp->hw_stats
under tp->lock if TG3_FLAG_INIT_COMPLETE is set.

Fixes: f5992b72ebe0 ("tg3: Fix race condition in tg3_get_stats64().")
Reported-by: Zumeng Chen <zumeng.chen@gmail.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/tg3.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index f2593978ae75..bde98a994e96 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -8733,14 +8733,15 @@ static void tg3_free_consistent(struct tg3 *tp)
 	tg3_mem_rx_release(tp);
 	tg3_mem_tx_release(tp);
 
-	/* Protect tg3_get_stats64() from reading freed tp->hw_stats. */
-	tg3_full_lock(tp, 0);
+	/* tp->hw_stats can be referenced safely:
+	 *     1. under rtnl_lock
+	 *     2. or under tp->lock if TG3_FLAG_INIT_COMPLETE is set.
+	 */
 	if (tp->hw_stats) {
 		dma_free_coherent(&tp->pdev->dev, sizeof(struct tg3_hw_stats),
 				  tp->hw_stats, tp->stats_mapping);
 		tp->hw_stats = NULL;
 	}
-	tg3_full_unlock(tp);
 }
 
 /*
@@ -14178,7 +14179,7 @@ static void tg3_get_stats64(struct net_device *dev,
 	struct tg3 *tp = netdev_priv(dev);
 
 	spin_lock_bh(&tp->lock);
-	if (!tp->hw_stats) {
+	if (!tp->hw_stats || !tg3_flag(tp, INIT_COMPLETE)) {
 		*stats = tp->net_stats_prev;
 		spin_unlock_bh(&tp->lock);
 		return;
-- 
2.14.3


From 4d3222599119613341c7392c54300a460ae74308 Mon Sep 17 00:00:00 2001
From: Debabrata Banerjee <dbanerje@akamai.com>
Date: Wed, 9 May 2018 19:32:10 -0400
Subject: [PATCH 33/55] bonding: do not allow rlb updates to invalid mac

[ Upstream commit 4fa8667ca3989ce14cf66301fa251544fbddbdd0 ]

Make sure multicast, broadcast, and zero mac's cannot be the output of rlb
updates, which should all be directed arps. Receive load balancing will be
collapsed if any of these happen, as the switch will broadcast.

Signed-off-by: Debabrata Banerjee <dbanerje@akamai.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_alb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 1ed9529e7bd1..3f6faa657360 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -450,7 +450,7 @@ static void rlb_update_client(struct rlb_client_info *client_info)
 {
 	int i;
 
-	if (!client_info->slave)
+	if (!client_info->slave || !is_valid_ether_addr(client_info->mac_dst))
 		return;
 
 	for (i = 0; i < RLB_ARP_BURST_SIZE; i++) {
-- 
2.14.3


From caa23585349b444a38b9ba0343214feb43166729 Mon Sep 17 00:00:00 2001
From: Debabrata Banerjee <dbanerje@akamai.com>
Date: Wed, 9 May 2018 19:32:11 -0400
Subject: [PATCH 34/55] bonding: send learning packets for vlans on slave

[ Upstream commit 21706ee8a47d3ede7fdae0be6d7c0a0e31a83229 ]

There was a regression at some point from the intended functionality of
commit f60c3704e87d ("bonding: Fix alb mode to only use first level
vlans.")

Given the return value vlan_get_encap_level() we need to store the nest
level of the bond device, and then compare the vlan's encap level to
this. Without this, this check always fails and learning packets are
never sent.

In addition, this same commit caused a regression in the behavior of
balance_alb, which requires learning packets be sent for all interfaces
using the slave's mac in order to load balance properly. For vlan's
that have not set a user mac, we can send after checking one bit.
Otherwise we need send the set mac, albeit defeating rx load balancing
for that vlan.

Signed-off-by: Debabrata Banerjee <dbanerje@akamai.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_alb.c  | 13 ++++++++-----
 drivers/net/bonding/bond_main.c |  2 ++
 include/net/bonding.h           |  1 +
 3 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 3f6faa657360..5eb0df2e5464 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -943,6 +943,10 @@ static void alb_send_lp_vid(struct slave *slave, u8 mac_addr[],
 	skb->priority = TC_PRIO_CONTROL;
 	skb->dev = slave->dev;
 
+	netdev_dbg(slave->bond->dev,
+		   "Send learning packet: dev %s mac %pM vlan %d\n",
+		   slave->dev->name, mac_addr, vid);
+
 	if (vid)
 		__vlan_hwaccel_put_tag(skb, vlan_proto, vid);
 
@@ -965,14 +969,13 @@ static int alb_upper_dev_walk(struct net_device *upper, void *_data)
 	u8 *mac_addr = data->mac_addr;
 	struct bond_vlan_tag *tags;
 
-	if (is_vlan_dev(upper) && vlan_get_encap_level(upper) == 0) {
-		if (strict_match &&
-		    ether_addr_equal_64bits(mac_addr,
-					    upper->dev_addr)) {
+	if (is_vlan_dev(upper) &&
+	    bond->nest_level == vlan_get_encap_level(upper) - 1) {
+		if (upper->addr_assign_type == NET_ADDR_STOLEN) {
 			alb_send_lp_vid(slave, mac_addr,
 					vlan_dev_vlan_proto(upper),
 					vlan_dev_vlan_id(upper));
-		} else if (!strict_match) {
+		} else {
 			alb_send_lp_vid(slave, upper->dev_addr,
 					vlan_dev_vlan_proto(upper),
 					vlan_dev_vlan_id(upper));
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 718e4914e3a0..1f1e97b26f95 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1738,6 +1738,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 	if (bond_mode_uses_xmit_hash(bond))
 		bond_update_slave_arr(bond, NULL);
 
+	bond->nest_level = dev_get_nest_level(bond_dev);
+
 	netdev_info(bond_dev, "Enslaving %s as %s interface with %s link\n",
 		    slave_dev->name,
 		    bond_is_active_slave(new_slave) ? "an active" : "a backup",
diff --git a/include/net/bonding.h b/include/net/bonding.h
index f801fc940b29..b52235158836 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -198,6 +198,7 @@ struct bonding {
 	struct   slave __rcu *primary_slave;
 	struct   bond_up_slave __rcu *slave_arr; /* Array of usable slaves */
 	bool     force_primary;
+	u32      nest_level;
 	s32      slave_cnt; /* never change this value outside the attach/detach wrappers */
 	int     (*recv_probe)(const struct sk_buff *, struct bonding *,
 			      struct slave *);
-- 
2.14.3


From 2af5eca29b6331829632b0b717f5439781b170b4 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Fri, 11 May 2018 17:45:32 +0200
Subject: [PATCH 35/55] net: sched: fix error path in tcf_proto_create() when
 modules are not configured

[ Upstream commit d68d75fdc34b0253c2bded7ed18cd60eb5a9599b ]

In case modules are not configured, error out when tp->ops is null
and prevent later null pointer dereference.

Fixes: 33a48927c193 ("sched: push TC filter protocol creation into a separate function")
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 247b7cc20c13..c2c732aad87c 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -152,8 +152,8 @@ static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol,
 			NL_SET_ERR_MSG(extack, "TC classifier not found");
 			err = -ENOENT;
 		}
-		goto errout;
 #endif
+		goto errout;
 	}
 	tp->classify = tp->ops->classify;
 	tp->protocol = protocol;
-- 
2.14.3


From 1c62fe2b26b3991a265df80f447fedddcb9e2011 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Tue, 20 Mar 2018 18:17:25 +0200
Subject: [PATCH 36/55] net/mlx5e: TX, Use correct counter in dma_map error
 flow

[ Upstream commit d9a96ec362e3da878c378854e25321c85bac52c2 ]

In case of a dma_mapping_error, do not use wi->num_dma
as a parameter for dma unmap function because it's yet
to be set, and holds an out-of-date value.
Use actual value (local variable num_dma) instead.

Fixes: 34802a42b352 ("net/mlx5e: Do not modify the TX SKB")
Fixes: e586b3b0baee ("net/mlx5: Ethernet Datapath files")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 11b4f1089d1c..ea725664f4f2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -255,7 +255,7 @@ mlx5e_txwqe_build_dsegs(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		dma_addr = dma_map_single(sq->pdev, skb_data, headlen,
 					  DMA_TO_DEVICE);
 		if (unlikely(dma_mapping_error(sq->pdev, dma_addr)))
-			return -ENOMEM;
+			goto dma_unmap_wqe_err;
 
 		dseg->addr       = cpu_to_be64(dma_addr);
 		dseg->lkey       = sq->mkey_be;
@@ -273,7 +273,7 @@ mlx5e_txwqe_build_dsegs(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		dma_addr = skb_frag_dma_map(sq->pdev, frag, 0, fsz,
 					    DMA_TO_DEVICE);
 		if (unlikely(dma_mapping_error(sq->pdev, dma_addr)))
-			return -ENOMEM;
+			goto dma_unmap_wqe_err;
 
 		dseg->addr       = cpu_to_be64(dma_addr);
 		dseg->lkey       = sq->mkey_be;
@@ -285,6 +285,10 @@ mlx5e_txwqe_build_dsegs(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	}
 
 	return num_dma;
+
+dma_unmap_wqe_err:
+	mlx5e_dma_unmap_wqe_err(sq, num_dma);
+	return -ENOMEM;
 }
 
 static inline void
@@ -380,17 +384,15 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb_data, headlen,
 					  (struct mlx5_wqe_data_seg *)cseg + ds_cnt);
 	if (unlikely(num_dma < 0))
-		goto dma_unmap_wqe_err;
+		goto err_drop;
 
 	mlx5e_txwqe_complete(sq, skb, opcode, ds_cnt + num_dma,
 			     num_bytes, num_dma, wi, cseg);
 
 	return NETDEV_TX_OK;
 
-dma_unmap_wqe_err:
+err_drop:
 	sq->stats.dropped++;
-	mlx5e_dma_unmap_wqe_err(sq, wi->num_dma);
-
 	dev_kfree_skb_any(skb);
 
 	return NETDEV_TX_OK;
@@ -620,17 +622,15 @@ netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb_data, headlen,
 					  (struct mlx5_wqe_data_seg *)cseg + ds_cnt);
 	if (unlikely(num_dma < 0))
-		goto dma_unmap_wqe_err;
+		goto err_drop;
 
 	mlx5e_txwqe_complete(sq, skb, opcode, ds_cnt + num_dma,
 			     num_bytes, num_dma, wi, cseg);
 
 	return NETDEV_TX_OK;
 
-dma_unmap_wqe_err:
+err_drop:
 	sq->stats.dropped++;
-	mlx5e_dma_unmap_wqe_err(sq, wi->num_dma);
-
 	dev_kfree_skb_any(skb);
 
 	return NETDEV_TX_OK;
-- 
2.14.3


From a558316c669284285b01e479fd208fb9a0012886 Mon Sep 17 00:00:00 2001
From: Talat Batheesh <talatb@mellanox.com>
Date: Sun, 15 Apr 2018 11:26:19 +0300
Subject: [PATCH 37/55] net/mlx5: Avoid cleaning flow steering table twice
 during error flow

[ Upstream commit 9c26f5f89d01ca21560c6b8a8e4054c271cc3a9c ]

When we fail to initialize the RX root namespace, we need
to clean only that and not the entire flow steering.

Currently the code may try to clean the flow steering twice
on error witch leads to null pointer deference.
Make sure we clean correctly.

Fixes: fba53f7b5719 ("net/mlx5: Introduce mlx5_flow_steering structure")
Signed-off-by: Talat Batheesh <talatb@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 31fc2cfac3b3..4d5b87e0d472 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -185,6 +185,7 @@ static void del_sw_ns(struct fs_node *node);
 static void del_sw_hw_rule(struct fs_node *node);
 static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1,
 				struct mlx5_flow_destination *d2);
+static void cleanup_root_ns(struct mlx5_flow_root_namespace *root_ns);
 static struct mlx5_flow_rule *
 find_flow_rule(struct fs_fte *fte,
 	       struct mlx5_flow_destination *dest);
@@ -2329,23 +2330,27 @@ static int create_anchor_flow_table(struct mlx5_flow_steering *steering)
 
 static int init_root_ns(struct mlx5_flow_steering *steering)
 {
+	int err;
+
 	steering->root_ns = create_root_ns(steering, FS_FT_NIC_RX);
 	if (!steering->root_ns)
-		goto cleanup;
+		return -ENOMEM;
 
-	if (init_root_tree(steering, &root_fs, &steering->root_ns->ns.node))
-		goto cleanup;
+	err = init_root_tree(steering, &root_fs, &steering->root_ns->ns.node);
+	if (err)
+		goto out_err;
 
 	set_prio_attrs(steering->root_ns);
-
-	if (create_anchor_flow_table(steering))
-		goto cleanup;
+	err = create_anchor_flow_table(steering);
+	if (err)
+		goto out_err;
 
 	return 0;
 
-cleanup:
-	mlx5_cleanup_fs(steering->dev);
-	return -ENOMEM;
+out_err:
+	cleanup_root_ns(steering->root_ns);
+	steering->root_ns = NULL;
+	return err;
 }
 
 static void clean_tree(struct fs_node *node)
-- 
2.14.3


From 4a3369edb4cb32042624906103c05ecb7ead3cb4 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Wed, 9 May 2018 14:09:04 -0700
Subject: [PATCH 38/55] hv_netvsc: set master device

[ Upstream commit 97f3efb64323beb0690576e9d74e94998ad6e82a ]

The hyper-v transparent bonding should have used master_dev_link.
The netvsc device should look like a master bond device not
like the upper side of a tunnel.

This makes the semantics the same so that userspace applications
looking at network devices see the correct master relationshipship.

Fixes: 0c195567a8f6 ("netvsc: transparent VF management")
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/netvsc_drv.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index f28c85d212ce..4774766fe20d 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -1840,7 +1840,8 @@ static int netvsc_vf_join(struct net_device *vf_netdev,
 		goto rx_handler_failed;
 	}
 
-	ret = netdev_upper_dev_link(vf_netdev, ndev, NULL);
+	ret = netdev_master_upper_dev_link(vf_netdev, ndev,
+					   NULL, NULL, NULL);
 	if (ret != 0) {
 		netdev_err(vf_netdev,
 			   "can not set master device %s (err = %d)\n",
-- 
2.14.3


From 35030b2950fa837f26452628d741d835c405e1c2 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 29 Apr 2018 09:54:59 -0700
Subject: [PATCH 39/55] ipv6: fix uninit-value in ip6_multipath_l3_keys()

[ Upstream commit cea67a2dd6b2419dcc13a39309b9a79a1f773193 ]

syzbot/KMSAN reported an uninit-value in ip6_multipath_l3_keys(),
root caused to a bad assumption of ICMP header being already
pulled in skb->head

ip_multipath_l3_keys() does the correct thing, so it is an IPv6 only bug.

BUG: KMSAN: uninit-value in ip6_multipath_l3_keys net/ipv6/route.c:1830 [inline]
BUG: KMSAN: uninit-value in rt6_multipath_hash+0x5c4/0x640 net/ipv6/route.c:1858
CPU: 0 PID: 4507 Comm: syz-executor661 Not tainted 4.16.0+ #87
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x185/0x1d0 lib/dump_stack.c:53
 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067
 __msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:683
 ip6_multipath_l3_keys net/ipv6/route.c:1830 [inline]
 rt6_multipath_hash+0x5c4/0x640 net/ipv6/route.c:1858
 ip6_route_input+0x65a/0x920 net/ipv6/route.c:1884
 ip6_rcv_finish+0x413/0x6e0 net/ipv6/ip6_input.c:69
 NF_HOOK include/linux/netfilter.h:288 [inline]
 ipv6_rcv+0x1e16/0x2340 net/ipv6/ip6_input.c:208
 __netif_receive_skb_core+0x47df/0x4a90 net/core/dev.c:4562
 __netif_receive_skb net/core/dev.c:4627 [inline]
 netif_receive_skb_internal+0x49d/0x630 net/core/dev.c:4701
 netif_receive_skb+0x230/0x240 net/core/dev.c:4725
 tun_rx_batched drivers/net/tun.c:1555 [inline]
 tun_get_user+0x740f/0x7c60 drivers/net/tun.c:1962
 tun_chr_write_iter+0x1d4/0x330 drivers/net/tun.c:1990
 call_write_iter include/linux/fs.h:1782 [inline]
 new_sync_write fs/read_write.c:469 [inline]
 __vfs_write+0x7fb/0x9f0 fs/read_write.c:482
 vfs_write+0x463/0x8d0 fs/read_write.c:544
 SYSC_write+0x172/0x360 fs/read_write.c:589
 SyS_write+0x55/0x80 fs/read_write.c:581
 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x3d/0xa2

Fixes: 23aebdacb05d ("ipv6: Compute multipath hash for ICMP errors from offending packet")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Jakub Sitnicki <jkbs@redhat.com>
Acked-by: Jakub Sitnicki <jkbs@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 74a2e37412b2..1aee1a537cb1 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1822,11 +1822,16 @@ static void ip6_multipath_l3_keys(const struct sk_buff *skb,
 	const struct ipv6hdr *inner_iph;
 	const struct icmp6hdr *icmph;
 	struct ipv6hdr _inner_iph;
+	struct icmp6hdr _icmph;
 
 	if (likely(outer_iph->nexthdr != IPPROTO_ICMPV6))
 		goto out;
 
-	icmph = icmp6_hdr(skb);
+	icmph = skb_header_pointer(skb, skb_transport_offset(skb),
+				   sizeof(_icmph), &_icmph);
+	if (!icmph)
+		goto out;
+
 	if (icmph->icmp6_type != ICMPV6_DEST_UNREACH &&
 	    icmph->icmp6_type != ICMPV6_PKT_TOOBIG &&
 	    icmph->icmp6_type != ICMPV6_TIME_EXCEED &&
-- 
2.14.3


From c0256f20078585abb112d0ef5bdb02c41c92ecc6 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@mellanox.com>
Date: Tue, 27 Mar 2018 09:22:16 +0000
Subject: [PATCH 40/55] net/mlx5e: Allow offloading ipv4 header re-write for
 icmp

[ Upstream commit 1ccef350db2f13715040a10df77ae672206004cf ]

For ICMPv4, the checksum is calculated from the ICMP headers and data.
Since the ICMPv4 checksum doesn't cover the IP header, we can allow to
do L3 header re-write for this protocol.

Fixes: bdd66ac0aeed ('net/mlx5e: Disallow TC offloading of unsupported match/action combinations')
Signed-off-by: Jianbo Liu <jianbol@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index c0b26281d0e2..8665670fddbc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1867,7 +1867,8 @@ static bool modify_header_match_supported(struct mlx5_flow_spec *spec,
 	}
 
 	ip_proto = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ip_protocol);
-	if (modify_ip_header && ip_proto != IPPROTO_TCP && ip_proto != IPPROTO_UDP) {
+	if (modify_ip_header && ip_proto != IPPROTO_TCP &&
+	    ip_proto != IPPROTO_UDP && ip_proto != IPPROTO_ICMP) {
 		pr_info("can't offload re-write of ip proto %d\n", ip_proto);
 		return false;
 	}
-- 
2.14.3


From a3d5f1b1b18ac43e2878a6a470382f21b0d0c0a0 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 3 May 2018 13:37:54 -0700
Subject: [PATCH 41/55] nsh: fix infinite loop

[ Upstream commit af50e4ba34f4c45e92535364133d4deb5931c1c5 ]

syzbot caught an infinite recursion in nsh_gso_segment().

Problem here is that we need to make sure the NSH header is of
reasonable length.

BUG: MAX_LOCK_DEPTH too low!
turning off the locking correctness validator.
depth: 48  max: 48!
48 locks held by syz-executor0/10189:
 #0:         (ptrval) (rcu_read_lock_bh){....}, at: __dev_queue_xmit+0x30f/0x34c0 net/core/dev.c:3517
 #1:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #1:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #2:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #2:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #3:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #3:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #4:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #4:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #5:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #5:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #6:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #6:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #7:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #7:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #8:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #8:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #9:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #9:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #10:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #10:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #11:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #11:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #12:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #12:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #13:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #13:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #14:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #14:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #15:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #15:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #16:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #16:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #17:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #17:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #18:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #18:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #19:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #19:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #20:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #20:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #21:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #21:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #22:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #22:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #23:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #23:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #24:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #24:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #25:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #25:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #26:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #26:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #27:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #27:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #28:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #28:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #29:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #29:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #30:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #30:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #31:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #31:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
dccp_close: ABORT with 65423 bytes unread
 #32:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #32:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #33:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #33:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #34:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #34:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #35:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #35:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #36:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #36:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #37:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #37:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #38:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #38:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #39:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #39:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #40:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #40:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #41:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #41:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #42:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #42:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #43:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #43:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #44:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #44:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #45:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #45:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #46:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #46:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
 #47:         (ptrval) (rcu_read_lock){....}, at: __skb_pull include/linux/skbuff.h:2080 [inline]
 #47:         (ptrval) (rcu_read_lock){....}, at: skb_mac_gso_segment+0x221/0x720 net/core/dev.c:2787
INFO: lockdep is turned off.
CPU: 1 PID: 10189 Comm: syz-executor0 Not tainted 4.17.0-rc2+ #26
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1b9/0x294 lib/dump_stack.c:113
 __lock_acquire+0x1788/0x5140 kernel/locking/lockdep.c:3449
 lock_acquire+0x1dc/0x520 kernel/locking/lockdep.c:3920
 rcu_lock_acquire include/linux/rcupdate.h:246 [inline]
 rcu_read_lock include/linux/rcupdate.h:632 [inline]
 skb_mac_gso_segment+0x25b/0x720 net/core/dev.c:2789
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 nsh_gso_segment+0x405/0xb60 net/nsh/nsh.c:107
 skb_mac_gso_segment+0x3ad/0x720 net/core/dev.c:2792
 __skb_gso_segment+0x3bb/0x870 net/core/dev.c:2865
 skb_gso_segment include/linux/netdevice.h:4025 [inline]
 validate_xmit_skb+0x54d/0xd90 net/core/dev.c:3118
 validate_xmit_skb_list+0xbf/0x120 net/core/dev.c:3168
 sch_direct_xmit+0x354/0x11e0 net/sched/sch_generic.c:312
 qdisc_restart net/sched/sch_generic.c:399 [inline]
 __qdisc_run+0x741/0x1af0 net/sched/sch_generic.c:410
 __dev_xmit_skb net/core/dev.c:3243 [inline]
 __dev_queue_xmit+0x28ea/0x34c0 net/core/dev.c:3551
 dev_queue_xmit+0x17/0x20 net/core/dev.c:3616
 packet_snd net/packet/af_packet.c:2951 [inline]
 packet_sendmsg+0x40f8/0x6070 net/packet/af_packet.c:2976
 sock_sendmsg_nosec net/socket.c:629 [inline]
 sock_sendmsg+0xd5/0x120 net/socket.c:639
 __sys_sendto+0x3d7/0x670 net/socket.c:1789
 __do_sys_sendto net/socket.c:1801 [inline]
 __se_sys_sendto net/socket.c:1797 [inline]
 __x64_sys_sendto+0xe1/0x1a0 net/socket.c:1797
 do_syscall_64+0x1b1/0x800 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Fixes: c411ed854584 ("nsh: add GSO support")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jiri Benc <jbenc@redhat.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/nsh/nsh.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/nsh/nsh.c b/net/nsh/nsh.c
index d7da99a0b0b8..9696ef96b719 100644
--- a/net/nsh/nsh.c
+++ b/net/nsh/nsh.c
@@ -57,6 +57,8 @@ int nsh_pop(struct sk_buff *skb)
 		return -ENOMEM;
 	nh = (struct nshhdr *)(skb->data);
 	length = nsh_hdr_len(nh);
+	if (length < NSH_BASE_HDR_LEN)
+		return -EINVAL;
 	inner_proto = tun_p_to_eth_p(nh->np);
 	if (!pskb_may_pull(skb, length))
 		return -ENOMEM;
@@ -90,6 +92,8 @@ static struct sk_buff *nsh_gso_segment(struct sk_buff *skb,
 	if (unlikely(!pskb_may_pull(skb, NSH_BASE_HDR_LEN)))
 		goto out;
 	nsh_len = nsh_hdr_len(nsh_hdr(skb));
+	if (nsh_len < NSH_BASE_HDR_LEN)
+		goto out;
 	if (unlikely(!pskb_may_pull(skb, nsh_len)))
 		goto out;
 
-- 
2.14.3


From 1938b5e5d75a8809cf1abea0cf1f61d289e6755f Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 9 May 2018 12:42:34 +0200
Subject: [PATCH 42/55] udp: fix SO_BINDTODEVICE

[ Upstream commit 69678bcd4d2dedbc3e8fcd6d7d99f283d83c531a ]

Damir reported a breakage of SO_BINDTODEVICE for UDP sockets.
In absence of VRF devices, after commit fb74c27735f0 ("net:
ipv4: add second dif to udp socket lookups") the dif mismatch
isn't fatal anymore for UDP socket lookup with non null
sk_bound_dev_if, breaking SO_BINDTODEVICE semantics.

This changeset addresses the issue making the dif match mandatory
again in the above scenario.

Reported-by: Damir Mansurov <dnman@oktetlabs.ru>
Fixes: fb74c27735f0 ("net: ipv4: add second dif to udp socket lookups")
Fixes: 1801b570dd2a ("net: ipv6: add second dif to udp socket lookups")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 4 ++--
 net/ipv6/udp.c | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index fb5992988450..b6ba51536b37 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -407,9 +407,9 @@ static int compute_score(struct sock *sk, struct net *net,
 		bool dev_match = (sk->sk_bound_dev_if == dif ||
 				  sk->sk_bound_dev_if == sdif);
 
-		if (exact_dif && !dev_match)
+		if (!dev_match)
 			return -1;
-		if (sk->sk_bound_dev_if && dev_match)
+		if (sk->sk_bound_dev_if)
 			score += 4;
 	}
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 52e3ea0e6f50..68d589f8d2b2 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -148,9 +148,9 @@ static int compute_score(struct sock *sk, struct net *net,
 		bool dev_match = (sk->sk_bound_dev_if == dif ||
 				  sk->sk_bound_dev_if == sdif);
 
-		if (exact_dif && !dev_match)
+		if (!dev_match)
 			return -1;
-		if (sk->sk_bound_dev_if && dev_match)
+		if (sk->sk_bound_dev_if)
 			score++;
 	}
 
-- 
2.14.3


From 16941065c2c61b0e70d5d9f9aac11e3970338050 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Thu, 26 Apr 2018 11:46:29 +0300
Subject: [PATCH 43/55] mlxsw: spectrum_switchdev: Do not remove mrouter port
 from MDB's ports list

[ Upstream commit c7f46cca8c73a44311e4164b9196b4d791f59ac7 ]

When IGMP snooping is enabled on a bridge, traffic forwarded by an MDB
entry should be sent to both ports member in the MDB's ports list and
mrouter ports.

In case a port needs to be removed from an MDB's ports list, but this
port is also configured as an mrouter port, then do not update the
device so that it will continue to forward traffic through that port.

Fix a copy-paste error that checked that IGMP snooping is enabled twice
instead of checking the port's mrouter state.

Fixes: ded711c87a04 ("mlxsw: spectrum_switchdev: Consider mrouter status for mdb changes")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Colin King <colin.king@canonical.com>
Reviewed-by: Nogah Frankel <nogahf@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 161bcdc012f0..fd6b86892595 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -1718,13 +1718,11 @@ __mlxsw_sp_port_mdb_del(struct mlxsw_sp_port *mlxsw_sp_port,
 	struct net_device *dev = mlxsw_sp_port->dev;
 	int err;
 
-	if (bridge_port->bridge_device->multicast_enabled) {
-		if (bridge_port->bridge_device->multicast_enabled) {
-			err = mlxsw_sp_port_smid_set(mlxsw_sp_port, mid->mid,
-						     false);
-			if (err)
-				netdev_err(dev, "Unable to remove port from SMID\n");
-		}
+	if (bridge_port->bridge_device->multicast_enabled &&
+	    !bridge_port->mrouter) {
+		err = mlxsw_sp_port_smid_set(mlxsw_sp_port, mid->mid, false);
+		if (err)
+			netdev_err(dev, "Unable to remove port from SMID\n");
 	}
 
 	err = mlxsw_sp_port_remove_from_mid(mlxsw_sp_port, mid);
-- 
2.14.3


From 7f685646277953ea0b54abd8b6321d057500b8bb Mon Sep 17 00:00:00 2001
From: Huy Nguyen <huyn@mellanox.com>
Date: Thu, 21 Dec 2017 15:15:24 -0600
Subject: [PATCH 44/55] net/mlx5e: DCBNL fix min inline header size for dscp

[ Upstream commit 35f80acb24cd53dabd65e0660e46afdf5c45991d ]

When the trust state is set to dscp and the netdev is down, the inline
header size is not updated. When netdev is up, the inline header size
stays at L2 instead of IP.

Fix this issue by updating the private parameter when the netdev is in
down so that when netdev is up, it picks up the right header size.

Fixes: fbcb127e89ba ("net/mlx5e: Support DSCP trust state ...")
Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index 3d46ef48d5b8..c641d5656b2d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -1007,12 +1007,14 @@ static void mlx5e_trust_update_sq_inline_mode(struct mlx5e_priv *priv)
 
 	mutex_lock(&priv->state_lock);
 
-	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
-		goto out;
-
 	new_channels.params = priv->channels.params;
 	mlx5e_trust_update_tx_min_inline_mode(priv, &new_channels.params);
 
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+		priv->channels.params = new_channels.params;
+		goto out;
+	}
+
 	/* Skip if tx_min_inline is the same */
 	if (new_channels.params.tx_min_inline_mode ==
 	    priv->channels.params.tx_min_inline_mode)
-- 
2.14.3


From b16d395fe96f58006143a7cf0eedddd70b75e8f5 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 25 Apr 2018 16:21:51 -0700
Subject: [PATCH 45/55] net: systemport: Correclty disambiguate driver
 instances

[ Upstream commit 1f3ccc3c3fc26468be00392ef0b2c215f9c9d054 ]

While adding the DSA notifier, we will be sending DSA notifications with
info->master that is going to point to a particular net_device instance.

Our logic in bcm_sysport_map_queues() correctly disambiguates net_device
instances that are not covered by our own driver, but it will not make
sure that info->master points to a particular driver instance that we
are interested in. In a system where e.g: two or more SYSTEMPORT
instances are registered, this would lead in programming two or more
times the queue mapping, completely messing with the logic which does
the queue/port allocation and tracking.

Fix this by looking at the notifier_block pointer which is unique per
instance and allows us to go back to our driver private structure, and
in turn to the backing net_device instance.

Fixes: d156576362c0 ("net: systemport: Establish lower/upper queue mapping")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bcmsysport.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 3fc549b88c43..d61e51ebca51 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -2052,14 +2052,21 @@ static const struct net_device_ops bcm_sysport_netdev_ops = {
 	.ndo_select_queue	= bcm_sysport_select_queue,
 };
 
-static int bcm_sysport_map_queues(struct net_device *dev,
+static int bcm_sysport_map_queues(struct notifier_block *nb,
 				  struct dsa_notifier_register_info *info)
 {
-	struct bcm_sysport_priv *priv = netdev_priv(dev);
 	struct bcm_sysport_tx_ring *ring;
+	struct bcm_sysport_priv *priv;
 	struct net_device *slave_dev;
 	unsigned int num_tx_queues;
 	unsigned int q, start, port;
+	struct net_device *dev;
+
+	priv = container_of(nb, struct bcm_sysport_priv, dsa_notifier);
+	if (priv->netdev != info->master)
+		return 0;
+
+	dev = info->master;
 
 	/* We can't be setting up queue inspection for non directly attached
 	 * switches
@@ -2082,6 +2089,7 @@ static int bcm_sysport_map_queues(struct net_device *dev,
 	if (priv->is_lite)
 		netif_set_real_num_tx_queues(slave_dev,
 					     slave_dev->num_tx_queues / 2);
+
 	num_tx_queues = slave_dev->real_num_tx_queues;
 
 	if (priv->per_port_num_tx_queues &&
@@ -2109,7 +2117,7 @@ static int bcm_sysport_map_queues(struct net_device *dev,
 	return 0;
 }
 
-static int bcm_sysport_dsa_notifier(struct notifier_block *unused,
+static int bcm_sysport_dsa_notifier(struct notifier_block *nb,
 				    unsigned long event, void *ptr)
 {
 	struct dsa_notifier_register_info *info;
@@ -2119,7 +2127,7 @@ static int bcm_sysport_dsa_notifier(struct notifier_block *unused,
 
 	info = ptr;
 
-	return notifier_from_errno(bcm_sysport_map_queues(info->master, info));
+	return notifier_from_errno(bcm_sysport_map_queues(nb, info));
 }
 
 #define REV_FMT	"v%2x.%02x"
-- 
2.14.3


From 8995c22ce4f1ebba813eea1383842ca05919b54b Mon Sep 17 00:00:00 2001
From: John Hurley <john.hurley@netronome.com>
Date: Tue, 1 May 2018 15:49:49 -0700
Subject: [PATCH 46/55] nfp: flower: set tunnel ttl value to net default

[ Upstream commit 50a5852a657f793a8482fe3af4a141b460d3499e ]

Firmware requires that the ttl value for an encapsulating ipv4 tunnel
header be included as an action field. Prior to the support of Geneve
tunnel encap (when ttl set was removed completely), ttl value was
extracted from the tunnel key. However, tests have shown that this can
still produce a ttl of 0.

Fix the issue by setting the namespace default value for each new tunnel.
Follow up patch for net-next will do a full route lookup.

Fixes: 3ca3059dc3a9 ("nfp: flower: compile Geneve encap actions")
Fixes: b27d6a95a70d ("nfp: compile flower vxlan tunnel set actions")
Signed-off-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/action.c | 10 ++++++++--
 drivers/net/ethernet/netronome/nfp/flower/cmsg.h   |  5 ++++-
 2 files changed, 12 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c
index b3567a596fc1..80df9a5d4217 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/action.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/action.c
@@ -183,17 +183,21 @@ static int
 nfp_fl_set_ipv4_udp_tun(struct nfp_fl_set_ipv4_udp_tun *set_tun,
 			const struct tc_action *action,
 			struct nfp_fl_pre_tunnel *pre_tun,
-			enum nfp_flower_tun_type tun_type)
+			enum nfp_flower_tun_type tun_type,
+			struct net_device *netdev)
 {
 	size_t act_size = sizeof(struct nfp_fl_set_ipv4_udp_tun);
 	struct ip_tunnel_info *ip_tun = tcf_tunnel_info(action);
 	u32 tmp_set_ip_tun_type_index = 0;
 	/* Currently support one pre-tunnel so index is always 0. */
 	int pretun_idx = 0;
+	struct net *net;
 
 	if (ip_tun->options_len)
 		return -EOPNOTSUPP;
 
+	net = dev_net(netdev);
+
 	set_tun->head.jump_id = NFP_FL_ACTION_OPCODE_SET_IPV4_TUNNEL;
 	set_tun->head.len_lw = act_size >> NFP_FL_LW_SIZ;
 
@@ -204,6 +208,7 @@ nfp_fl_set_ipv4_udp_tun(struct nfp_fl_set_ipv4_udp_tun *set_tun,
 
 	set_tun->tun_type_index = cpu_to_be32(tmp_set_ip_tun_type_index);
 	set_tun->tun_id = ip_tun->key.tun_id;
+	set_tun->ttl = net->ipv4.sysctl_ip_default_ttl;
 
 	/* Complete pre_tunnel action. */
 	pre_tun->ipv4_dst = ip_tun->key.u.ipv4.dst;
@@ -511,7 +516,8 @@ nfp_flower_loop_action(const struct tc_action *a,
 		*a_len += sizeof(struct nfp_fl_pre_tunnel);
 
 		set_tun = (void *)&nfp_fl->action_data[*a_len];
-		err = nfp_fl_set_ipv4_udp_tun(set_tun, a, pre_tun, *tun_type);
+		err = nfp_fl_set_ipv4_udp_tun(set_tun, a, pre_tun, *tun_type,
+					      netdev);
 		if (err)
 			return err;
 		*a_len += sizeof(struct nfp_fl_set_ipv4_udp_tun);
diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
index adfe474c2cf0..329a9b6d453a 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
@@ -178,7 +178,10 @@ struct nfp_fl_set_ipv4_udp_tun {
 	__be16 reserved;
 	__be64 tun_id __packed;
 	__be32 tun_type_index;
-	__be32 extra[3];
+	__be16 reserved2;
+	u8 ttl;
+	u8 reserved3;
+	__be32 extra[2];
 };
 
 /* Metadata with L2 (1W/4B)
-- 
2.14.3


From 3523835ab81f5c7b7ccd3b2af5911656943fcf29 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 26 Apr 2018 15:21:44 +0800
Subject: [PATCH 47/55] sctp: clear the new asoc's stream outcnt in
 sctp_stream_update

[ Upstream commit 6a9a27d5397fc6c52f90c09ddab91e65053584aa ]

When processing a duplicate cookie-echo chunk, sctp moves the new
temp asoc's stream out/in into the old asoc, and later frees this
new temp asoc.

But now after this move, the new temp asoc's stream->outcnt is not
cleared while stream->out is set to NULL, which would cause a same
crash as the one fixed in Commit 79d0895140e9 ("sctp: fix error
path in sctp_stream_init") when freeing this asoc later.

This fix is to clear this outcnt in sctp_stream_update.

Fixes: f952be79cebd ("sctp: introduce struct sctp_stream_out_ext")
Reported-by: Jianwen Ji <jiji@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/stream.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index f799043abec9..f1f1d1b232ba 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -240,6 +240,8 @@ void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new)
 
 	new->out = NULL;
 	new->in  = NULL;
+	new->outcnt = 0;
+	new->incnt  = 0;
 }
 
 static int sctp_send_reconf(struct sctp_association *asoc,
-- 
2.14.3


From e99c54a3d53fe9bf272b3b1e0cbf803697505460 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 2 May 2018 20:25:13 -0700
Subject: [PATCH 48/55] tcp: restore autocorking

[ Upstream commit 114f39feab360e6c7b0c4238697f223444d662a1 ]

When adding rb-tree for TCP retransmit queue, we inadvertently broke
TCP autocorking.

tcp_should_autocork() should really check if the rtx queue is not empty.

Tested:

Before the fix :
$ nstat -n;./netperf -H 10.246.7.152 -Cc -- -m 500;nstat | grep AutoCork
MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.246.7.152 () port 0 AF_INET
Recv   Send    Send                          Utilization       Service Demand
Socket Socket  Message  Elapsed              Send     Recv     Send    Recv
Size   Size    Size     Time     Throughput  local    remote   local   remote
bytes  bytes   bytes    secs.    10^6bits/s  % S      % S      us/KB   us/KB

540000 262144    500    10.00      2682.85   2.47     1.59     3.618   2.329
TcpExtTCPAutoCorking            33                 0.0

// Same test, but forcing TCP_NODELAY
$ nstat -n;./netperf -H 10.246.7.152 -Cc -- -D -m 500;nstat | grep AutoCork
MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.246.7.152 () port 0 AF_INET : nodelay
Recv   Send    Send                          Utilization       Service Demand
Socket Socket  Message  Elapsed              Send     Recv     Send    Recv
Size   Size    Size     Time     Throughput  local    remote   local   remote
bytes  bytes   bytes    secs.    10^6bits/s  % S      % S      us/KB   us/KB

540000 262144    500    10.00      1408.75   2.44     2.96     6.802   8.259
TcpExtTCPAutoCorking            1                  0.0

After the fix :
$ nstat -n;./netperf -H 10.246.7.152 -Cc -- -m 500;nstat | grep AutoCork
MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.246.7.152 () port 0 AF_INET
Recv   Send    Send                          Utilization       Service Demand
Socket Socket  Message  Elapsed              Send     Recv     Send    Recv
Size   Size    Size     Time     Throughput  local    remote   local   remote
bytes  bytes   bytes    secs.    10^6bits/s  % S      % S      us/KB   us/KB

540000 262144    500    10.00      5472.46   2.45     1.43     1.761   1.027
TcpExtTCPAutoCorking            361293             0.0

// With TCP_NODELAY option
$ nstat -n;./netperf -H 10.246.7.152 -Cc -- -D -m 500;nstat | grep AutoCork
MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.246.7.152 () port 0 AF_INET : nodelay
Recv   Send    Send                          Utilization       Service Demand
Socket Socket  Message  Elapsed              Send     Recv     Send    Recv
Size   Size    Size     Time     Throughput  local    remote   local   remote
bytes  bytes   bytes    secs.    10^6bits/s  % S      % S      us/KB   us/KB

540000 262144    500    10.00      5454.96   2.46     1.63     1.775   1.174
TcpExtTCPAutoCorking            315448             0.0

Fixes: 75c119afe14f ("tcp: implement rb-tree based retransmit queue")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Michael Wenig <mwenig@vmware.com>
Tested-by: Michael Wenig <mwenig@vmware.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Michael Wenig <mwenig@vmware.com>
Tested-by: Michael Wenig <mwenig@vmware.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f47e9cd2c4ea..54ec0f8eadd6 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -688,7 +688,7 @@ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb,
 {
 	return skb->len < size_goal &&
 	       sock_net(sk)->ipv4.sysctl_tcp_autocorking &&
-	       skb != tcp_write_queue_head(sk) &&
+	       !tcp_rtx_queue_empty(sk) &&
 	       refcount_read(&sk->sk_wmem_alloc) > skb->truesize;
 }
 
-- 
2.14.3


From a47d57aab616d901a84727f6e812cb1737cb80ec Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 9 May 2018 09:50:22 -0700
Subject: [PATCH 49/55] tipc: fix one byte leak in tipc_sk_set_orig_addr()

[ Upstream commit 09c8b9718a7af674036643fa2e0dbb2f09aba75e ]

sysbot/KMSAN reported an uninit-value in recvmsg() that
I tracked down to tipc_sk_set_orig_addr(), missing
srcaddr->member.scope initialization.

This patches moves srcaddr->sock.scope init to follow
fields order and ease future verifications.

BUG: KMSAN: uninit-value in copy_to_user include/linux/uaccess.h:184 [inline]
BUG: KMSAN: uninit-value in move_addr_to_user+0x32e/0x530 net/socket.c:226
CPU: 0 PID: 4549 Comm: syz-executor287 Not tainted 4.17.0-rc3+ #88
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x185/0x1d0 lib/dump_stack.c:113
 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067
 kmsan_internal_check_memory+0x135/0x1e0 mm/kmsan/kmsan.c:1157
 kmsan_copy_to_user+0x69/0x160 mm/kmsan/kmsan.c:1199
 copy_to_user include/linux/uaccess.h:184 [inline]
 move_addr_to_user+0x32e/0x530 net/socket.c:226
 ___sys_recvmsg+0x4e2/0x810 net/socket.c:2285
 __sys_recvmsg net/socket.c:2328 [inline]
 __do_sys_recvmsg net/socket.c:2338 [inline]
 __se_sys_recvmsg net/socket.c:2335 [inline]
 __x64_sys_recvmsg+0x325/0x460 net/socket.c:2335
 do_syscall_64+0x154/0x220 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x4455e9
RSP: 002b:00007fe3bd36ddb8 EFLAGS: 00000246 ORIG_RAX: 000000000000002f
RAX: ffffffffffffffda RBX: 00000000006dac24 RCX: 00000000004455e9
RDX: 0000000000002002 RSI: 0000000020000400 RDI: 0000000000000003
RBP: 00000000006dac20 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 00007fff98ce4b6f R14: 00007fe3bd36e9c0 R15: 0000000000000003

Local variable description: ----addr@___sys_recvmsg
Variable was created at:
 ___sys_recvmsg+0xd5/0x810 net/socket.c:2246
 __sys_recvmsg net/socket.c:2328 [inline]
 __do_sys_recvmsg net/socket.c:2338 [inline]
 __se_sys_recvmsg net/socket.c:2335 [inline]
 __x64_sys_recvmsg+0x325/0x460 net/socket.c:2335

Byte 19 of 32 is uninitialized

Fixes: 31c82a2d9d51 ("tipc: add second source address to recvmsg()/recvfrom()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Jon Maloy <jon.maloy@ericsson.com>
Cc: Ying Xue <ying.xue@windriver.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/socket.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 7dfa9fc99ec3..df4f504b1fef 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1518,10 +1518,10 @@ static void tipc_sk_set_orig_addr(struct msghdr *m, struct sk_buff *skb)
 
 	srcaddr->sock.family = AF_TIPC;
 	srcaddr->sock.addrtype = TIPC_ADDR_ID;
+	srcaddr->sock.scope = 0;
 	srcaddr->sock.addr.id.ref = msg_origport(hdr);
 	srcaddr->sock.addr.id.node = msg_orignode(hdr);
 	srcaddr->sock.addr.name.domain = 0;
-	srcaddr->sock.scope = 0;
 	m->msg_namelen = sizeof(struct sockaddr_tipc);
 
 	if (!msg_in_group(hdr))
@@ -1530,6 +1530,7 @@ static void tipc_sk_set_orig_addr(struct msghdr *m, struct sk_buff *skb)
 	/* Group message users may also want to know sending member's id */
 	srcaddr->member.family = AF_TIPC;
 	srcaddr->member.addrtype = TIPC_ADDR_NAME;
+	srcaddr->member.scope = 0;
 	srcaddr->member.addr.name.name.type = msg_nametype(hdr);
 	srcaddr->member.addr.name.name.instance = TIPC_SKB_CB(skb)->orig_member;
 	srcaddr->member.addr.name.domain = 0;
-- 
2.14.3


From 1efdc3e6d36e08a54b2f48afc2856b38fb27b55a Mon Sep 17 00:00:00 2001
From: Mohammed Gamal <mgamal@redhat.com>
Date: Wed, 9 May 2018 10:17:34 +0200
Subject: [PATCH 50/55] hv_netvsc: Fix net device attach on older Windows hosts

[ Upstream commit 55be9f25be1ca5bda75c39808fc77e42691bc07f ]

On older windows hosts the net_device instance is returned to
the caller of rndis_filter_device_add() without having the presence
bit set first. This would cause any subsequent calls to network device
operations (e.g. MTU change, channel change) to fail after the device
is detached once, returning -ENODEV.

Instead of returning the device instabce, we take the exit path where
we call netif_device_attach()

Fixes: 7b2ee50c0cd5 ("hv_netvsc: common detach logic")
Signed-off-by: Mohammed Gamal <mgamal@redhat.com>
Reviewed-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/rndis_filter.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 465c42e30508..95846f0321f3 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -1282,7 +1282,7 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
 		   rndis_device->link_state ? "down" : "up");
 
 	if (net_device->nvsp_version < NVSP_PROTOCOL_VERSION_5)
-		return net_device;
+		goto out;
 
 	rndis_filter_query_link_speed(rndis_device, net_device);
 
-- 
2.14.3


From f1065ad2d823c0910fac917274e79e1a5f77a5ba Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Wed, 9 May 2018 18:06:44 +0800
Subject: [PATCH 51/55] ipv4: reset fnhe_mtu_locked after cache route flushed

[ Upstream commit 0e8411e426e277f55bd21e287ec89fab6f8eacae ]

After route cache is flushed via ipv4_sysctl_rtcache_flush(), we forget
to reset fnhe_mtu_locked in rt_bind_exception(). When pmtu is updated
in __ip_rt_update_pmtu(), it will return directly since the pmtu is
still locked. e.g.

+ ip netns exec client ping 10.10.1.1 -c 1 -s 1400 -M do
PING 10.10.1.1 (10.10.1.1) 1400(1428) bytes of data.
>From 10.10.0.254 icmp_seq=1 Frag needed and DF set (mtu = 0)

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index c5366b290508..09bbc6afcbc3 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1376,6 +1376,7 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
 			fnhe->fnhe_gw = 0;
 			fnhe->fnhe_pmtu = 0;
 			fnhe->fnhe_expires = 0;
+			fnhe->fnhe_mtu_locked = false;
 			fnhe_flush_routes(fnhe);
 			orig = NULL;
 		}
-- 
2.14.3


From a5a3056553bb1c19c02bdd374d5927f537b670bf Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Thu, 10 May 2018 13:26:16 +0200
Subject: [PATCH 52/55] mlxsw: core: Fix an error handling path in
 'mlxsw_core_bus_device_register()'

[ Upstream commit 8ccc113172e4c1ebef45c2433f3c32ed6ae1b9c9 ]

Resources are not freed in the reverse order of the allocation.
Labels are also mixed-up.

Fix it and reorder code and labels in the error handling path of
'mlxsw_core_bus_device_register()'

Fixes: ef3116e5403e ("mlxsw: spectrum: Register KVD resources with devlink")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index 3529b545675d..1c09a274c637 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -1099,11 +1099,11 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 err_alloc_lag_mapping:
 	mlxsw_ports_fini(mlxsw_core);
 err_ports_init:
-	mlxsw_bus->fini(bus_priv);
-err_bus_init:
 	if (!reload)
 		devlink_resources_unregister(devlink, NULL);
 err_register_resources:
+	mlxsw_bus->fini(bus_priv);
+err_bus_init:
 	if (!reload)
 		devlink_free(devlink);
 err_devlink_alloc:
-- 
2.14.3


From c59fc531598cf75d21fef85dc04d770c012f5b70 Mon Sep 17 00:00:00 2001
From: Israel Rukshin <israelr@mellanox.com>
Date: Thu, 12 Apr 2018 09:49:11 +0000
Subject: [PATCH 53/55] net/mlx5: Fix mlx5_get_vector_affinity function

[ Upstream commit 6082d9c9c94a408d7409b5f2e4e42ac9e8b16d0d ]

Adding the vector offset when calling to mlx5_vector2eqn() is wrong.
This is because mlx5_vector2eqn() checks if EQ index is equal to vector number
and the fact that the internal completion vectors that mlx5 allocates
don't get an EQ index.

The second problem here is that using effective_affinity_mask gives the same
CPU for different vectors.
This leads to unmapped queues when calling it from blk_mq_rdma_map_queues().
This doesn't happen when using affinity_hint mask.

Fixes: 2572cf57d75a ("mlx5: fix mlx5_get_vector_affinity to start from completion vector 0")
Fixes: 05e0cc84e00c ("net/mlx5: Fix get vector affinity helper function")
Signed-off-by: Israel Rukshin <israelr@mellanox.com>
Reviewed-by: Max Gurtovoy <maxg@mellanox.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
---
 drivers/infiniband/hw/mlx5/main.c |  2 +-
 include/linux/mlx5/driver.h       | 12 +++---------
 2 files changed, 4 insertions(+), 10 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 7f8bda3a2005..0881f7907848 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -4303,7 +4303,7 @@ mlx5_ib_get_vector_affinity(struct ib_device *ibdev, int comp_vector)
 {
 	struct mlx5_ib_dev *dev = to_mdev(ibdev);
 
-	return mlx5_get_vector_affinity(dev->mdev, comp_vector);
+	return mlx5_get_vector_affinity_hint(dev->mdev, comp_vector);
 }
 
 /* The mlx5_ib_multiport_mutex should be held when calling this function */
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 9d3a03364e6e..1352b1b990a7 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1269,25 +1269,19 @@ enum {
 };
 
 static inline const struct cpumask *
-mlx5_get_vector_affinity(struct mlx5_core_dev *dev, int vector)
+mlx5_get_vector_affinity_hint(struct mlx5_core_dev *dev, int vector)
 {
-	const struct cpumask *mask;
 	struct irq_desc *desc;
 	unsigned int irq;
 	int eqn;
 	int err;
 
-	err = mlx5_vector2eqn(dev, MLX5_EQ_VEC_COMP_BASE + vector, &eqn, &irq);
+	err = mlx5_vector2eqn(dev, vector, &eqn, &irq);
 	if (err)
 		return NULL;
 
 	desc = irq_to_desc(irq);
-#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
-	mask = irq_data_get_effective_affinity_mask(&desc->irq_data);
-#else
-	mask = desc->irq_common_data.affinity;
-#endif
-	return mask;
+	return desc->affinity_hint;
 }
 
 #endif /* MLX5_DRIVER_H */
-- 
2.14.3


From e9dbdbb02e234af0bad4a3e99e0a84b79bbe9cf7 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Fri, 4 May 2018 17:10:54 +0200
Subject: [PATCH 54/55] net: phy: sfp: fix the BR,min computation

[ Upstream commit 52c5cd1bf0cecf4b146ca07dc513cbe2f4583bb5 ]

In an SFP EEPROM values can be read to get information about a given SFP
module. One of those is the bitrate, which can be determined using a
nominal bitrate in addition with min and max values (in %). The SFP code
currently compute both BR,min and BR,max values thanks to this nominal
and min,max values.

This patch fixes the BR,min computation as the min value should be
subtracted to the nominal one, not added.

Fixes: 9962acf7fb8c ("sfp: add support for 1000Base-PX and 1000Base-BX10")
Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/sfp-bus.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c
index 8961209ee949..a386138c7255 100644
--- a/drivers/net/phy/sfp-bus.c
+++ b/drivers/net/phy/sfp-bus.c
@@ -190,7 +190,7 @@ void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id,
 	if (id->base.br_nominal) {
 		if (id->base.br_nominal != 255) {
 			br_nom = id->base.br_nominal * 100;
-			br_min = br_nom + id->base.br_nominal * id->ext.br_min;
+			br_min = br_nom - id->base.br_nominal * id->ext.br_min;
 			br_max = br_nom + id->base.br_nominal * id->ext.br_max;
 		} else if (id->ext.br_max) {
 			br_nom = 250 * id->ext.br_max;
-- 
2.14.3


From 97d3ea302ce67190eee6bd25163cb921eaad0a94 Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.ibm.com>
Date: Wed, 25 Apr 2018 12:48:58 +0200
Subject: [PATCH 55/55] net/smc: keep clcsock reference in
 smc_tcp_listen_work()

[ Upstream commit 070204a34884110ac5e19c1e2e036fcfd033f8e3 ]

The internal CLC socket should exist till the SMC-socket is released.
Function tcp_listen_worker() releases the internal CLC socket of a
listen socket, if an smc_close_active() is called. This function
is called for the final release(), but it is called for shutdown
SHUT_RDWR as well. This opens a door for protection faults, if
socket calls using the internal CLC socket are called for a
shutdown listen socket.

With the changes of
commit 3d502067599f ("net/smc: simplify wait when closing listen socket")
there is no need anymore to release the internal CLC socket in
function tcp_listen_worker((). It is sufficient to release it in
smc_release().

Fixes: 127f49705823 ("net/smc: release clcsock from tcp_listen_worker")
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Reported-by: syzbot+9045fc589fcd196ef522@syzkaller.appspotmail.com
Reported-by: syzbot+28a2c86cf19c81d871fa@syzkaller.appspotmail.com
Reported-by: syzbot+9605e6cace1b5efd4a0a@syzkaller.appspotmail.com
Reported-by: syzbot+cf9012c597c8379d535c@syzkaller.appspotmail.com
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/af_smc.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 5974ea7a3ef4..5a983c9bea53 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -973,10 +973,6 @@ static void smc_tcp_listen_work(struct work_struct *work)
 	}
 
 out:
-	if (lsmc->clcsock) {
-		sock_release(lsmc->clcsock);
-		lsmc->clcsock = NULL;
-	}
 	release_sock(lsk);
 	sock_put(&lsmc->sk); /* sock_hold in smc_listen */
 }
-- 
2.14.3

Re: [PATCHES] Networking

[Greg KH]

On Tue, May 15, 2018 at 04:50:36PM -0400, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.14 and v4.16
> -stable, respectively.

Thanks for these, all now queued up.

greg k-h

Re: [PATCHES] Networking

[Jiri Slaby]

On 09/15/2017, 06:57 AM, David Miller wrote:
> Please queue up the following networking bug fixes for v4.9, v4.12, and
> v4.13 -stable, respectively.

Hi,

while walking through some fixes, I wonder, whether backports of
25cc72a33835 (mlxsw: spectrum: Forbid linking to devices that have
 uppers) to 4.9 and 4.12 are correct.

Part of the original commit:
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4139,6 +4139,8 @@ static int
mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev,
                        return -EINVAL;
                if (!info->linking)
                        break;
+               if (netdev_has_any_upper_dev(upper_dev))
+                       return -EINVAL;
                if (netif_is_lag_master(upper_dev) &&
                    !mlxsw_sp_master_lag_check(mlxsw_sp, upper_dev,
                                               info->upper_info))
@@ -4258,6 +4260,10 @@ static int
mlxsw_sp_netdevice_port_vlan_event(struct net_device *vlan_dev,
                upper_dev = info->upper_dev;
                if (!netif_is_bridge_master(upper_dev))
                        return -EINVAL;
+               if (!info->linking)
+                       break;
+               if (netdev_has_any_upper_dev(upper_dev))
+                       return -EINVAL;
                break;
        case NETDEV_CHANGEUPPER:
                upper_dev = info->upper_dev;



It changes mlxsw_sp_netdevice_port_upper_event and
mlxsw_sp_netdevice_port_vlan_event.




4.9 backport (73ee5a73e75):
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4172,6 +4172,8 @@ static int
mlxsw_sp_netdevice_port_upper_event(struct net_device *dev,
                        return -EINVAL;
                if (!info->linking)
                        break;
+               if (netdev_has_any_upper_dev(upper_dev))
+                       return -EINVAL;
                /* HW limitation forbids to put ports to multiple
bridges. */
                if (netif_is_bridge_master(upper_dev) &&
                    !mlxsw_sp_master_bridge_check(mlxsw_sp, upper_dev))
@@ -4185,6 +4187,10 @@ static int
mlxsw_sp_netdevice_port_upper_event(struct net_device *dev,
                if (netif_is_lag_port(dev) && is_vlan_dev(upper_dev) &&
                    !netif_is_lag_master(vlan_dev_real_dev(upper_dev)))
                        return -EINVAL;
+               if (!info->linking)
+                       break;
+               if (netdev_has_any_upper_dev(upper_dev))
+                       return -EINVAL;
                break;
        case NETDEV_CHANGEUPPER:
                upper_dev = info->upper_dev;




It changes mlxsw_sp_netdevice_port_upper_event *twice* instead of
mlxsw_sp_netdevice_port_vlan_event, which was named
mlxsw_sp_netdevice_vport_event in 4.9 yet.





4.12 backport (2f4232ba8001):
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4110,6 +4110,8 @@ static int
mlxsw_sp_netdevice_port_upper_event(struct net_device *dev,
                        return -EINVAL;
                if (!info->linking)
                        break;
+               if (netdev_has_any_upper_dev(upper_dev))
+                       return -EINVAL;
                /* HW limitation forbids to put ports to multiple
bridges. */
                if (netif_is_bridge_master(upper_dev) &&
                    !mlxsw_sp_master_bridge_check(mlxsw_sp, upper_dev))
@@ -4274,6 +4276,10 @@ static int mlxsw_sp_netdevice_bridge_event(struct
net_device *br_dev,
                if (is_vlan_dev(upper_dev) &&
                    br_dev != mlxsw_sp->master_bridge.dev)
                        return -EINVAL;
+               if (!info->linking)
+                       break;
+               if (netdev_has_any_upper_dev(upper_dev))
+                       return -EINVAL;
                break;
        case NETDEV_CHANGEUPPER:
                upper_dev = info->upper_dev;



It changes mlxsw_sp_netdevice_port_upper_event (OK) and
mlxsw_sp_netdevice_bridge_event (not OK) instead of
mlxsw_sp_netdevice_vport_event.


Did I miss something or is this a mistake?

thanks,
-- 
js
suse labs

Re: [PATCHES] Networking

[Greg KH]

On Thu, Jun 07, 2018 at 09:00:12AM +0200, Jiri Slaby wrote:
> On 09/15/2017, 06:57 AM, David Miller wrote:
> > Please queue up the following networking bug fixes for v4.9, v4.12, and
> > v4.13 -stable, respectively.
> 
> Hi,
> 
> while walking through some fixes, I wonder, whether backports of
> 25cc72a33835 (mlxsw: spectrum: Forbid linking to devices that have
>  uppers) to 4.9 and 4.12 are correct.
> 
> Part of the original commit:
> --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
> +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
> @@ -4139,6 +4139,8 @@ static int
> mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev,
>                         return -EINVAL;
>                 if (!info->linking)
>                         break;
> +               if (netdev_has_any_upper_dev(upper_dev))
> +                       return -EINVAL;
>                 if (netif_is_lag_master(upper_dev) &&
>                     !mlxsw_sp_master_lag_check(mlxsw_sp, upper_dev,
>                                                info->upper_info))
> @@ -4258,6 +4260,10 @@ static int
> mlxsw_sp_netdevice_port_vlan_event(struct net_device *vlan_dev,
>                 upper_dev = info->upper_dev;
>                 if (!netif_is_bridge_master(upper_dev))
>                         return -EINVAL;
> +               if (!info->linking)
> +                       break;
> +               if (netdev_has_any_upper_dev(upper_dev))
> +                       return -EINVAL;
>                 break;
>         case NETDEV_CHANGEUPPER:
>                 upper_dev = info->upper_dev;
> 
> 
> 
> It changes mlxsw_sp_netdevice_port_upper_event and
> mlxsw_sp_netdevice_port_vlan_event.
> 
> 
> 
> 
> 4.9 backport (73ee5a73e75):
> --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
> +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
> @@ -4172,6 +4172,8 @@ static int
> mlxsw_sp_netdevice_port_upper_event(struct net_device *dev,
>                         return -EINVAL;
>                 if (!info->linking)
>                         break;
> +               if (netdev_has_any_upper_dev(upper_dev))
> +                       return -EINVAL;
>                 /* HW limitation forbids to put ports to multiple
> bridges. */
>                 if (netif_is_bridge_master(upper_dev) &&
>                     !mlxsw_sp_master_bridge_check(mlxsw_sp, upper_dev))
> @@ -4185,6 +4187,10 @@ static int
> mlxsw_sp_netdevice_port_upper_event(struct net_device *dev,
>                 if (netif_is_lag_port(dev) && is_vlan_dev(upper_dev) &&
>                     !netif_is_lag_master(vlan_dev_real_dev(upper_dev)))
>                         return -EINVAL;
> +               if (!info->linking)
> +                       break;
> +               if (netdev_has_any_upper_dev(upper_dev))
> +                       return -EINVAL;
>                 break;
>         case NETDEV_CHANGEUPPER:
>                 upper_dev = info->upper_dev;
> 
> 
> 
> 
> It changes mlxsw_sp_netdevice_port_upper_event *twice* instead of
> mlxsw_sp_netdevice_port_vlan_event, which was named
> mlxsw_sp_netdevice_vport_event in 4.9 yet.
> 
> 
> 
> 
> 
> 4.12 backport (2f4232ba8001):
> --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
> +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
> @@ -4110,6 +4110,8 @@ static int
> mlxsw_sp_netdevice_port_upper_event(struct net_device *dev,
>                         return -EINVAL;
>                 if (!info->linking)
>                         break;
> +               if (netdev_has_any_upper_dev(upper_dev))
> +                       return -EINVAL;
>                 /* HW limitation forbids to put ports to multiple
> bridges. */
G>                 if (netif_is_bridge_master(upper_dev) &&
>                     !mlxsw_sp_master_bridge_check(mlxsw_sp, upper_dev))
> @@ -4274,6 +4276,10 @@ static int mlxsw_sp_netdevice_bridge_event(struct
> net_device *br_dev,
>                 if (is_vlan_dev(upper_dev) &&
>                     br_dev != mlxsw_sp->master_bridge.dev)
>                         return -EINVAL;
> +               if (!info->linking)
> +                       break;
> +               if (netdev_has_any_upper_dev(upper_dev))
> +                       return -EINVAL;
>                 break;
>         case NETDEV_CHANGEUPPER:
>                 upper_dev = info->upper_dev;
> 
> 
> 
> It changes mlxsw_sp_netdevice_port_upper_event (OK) and
> mlxsw_sp_netdevice_bridge_event (not OK) instead of
> mlxsw_sp_netdevice_vport_event.
> 
> 
> Did I miss something or is this a mistake?

Looks odd to me, want me to revert this from 4.9?  Without the hardware,
I doubt anyone has noticed this issue.

thanks,

greg k-h

Re: [PATCHES] Networking

[Ido Schimmel]

On Thu, Jun 07, 2018 at 09:00:12AM +0200, Jiri Slaby wrote:
> On 09/15/2017, 06:57 AM, David Miller wrote:
> > Please queue up the following networking bug fixes for v4.9, v4.12, and
> > v4.13 -stable, respectively.
> 
> Hi,
> 
> while walking through some fixes, I wonder, whether backports of
> 25cc72a33835 (mlxsw: spectrum: Forbid linking to devices that have
>  uppers) to 4.9 and 4.12 are correct.

[...]

> 
> 
> Did I miss something or is this a mistake?

Your analysis looks correct to me. How do you want to proceed? Do you
want me to send you fixed backports for 4.9.y and 4.12.y?

Thanks for noticing this.

Re: [PATCHES] Networking

[Greg KH]

On Thu, Jun 07, 2018 at 01:47:34PM +0300, Ido Schimmel wrote:
> On Thu, Jun 07, 2018 at 09:00:12AM +0200, Jiri Slaby wrote:
> > On 09/15/2017, 06:57 AM, David Miller wrote:
> > > Please queue up the following networking bug fixes for v4.9, v4.12, and
> > > v4.13 -stable, respectively.
> > 
> > Hi,
> > 
> > while walking through some fixes, I wonder, whether backports of
> > 25cc72a33835 (mlxsw: spectrum: Forbid linking to devices that have
> >  uppers) to 4.9 and 4.12 are correct.
> 
> [...]
> 
> > 
> > 
> > Did I miss something or is this a mistake?
> 
> Your analysis looks correct to me. How do you want to proceed? Do you
> want me to send you fixed backports for 4.9.y and 4.12.y?

4.12.y is long gone end-of-life, so there's nothing we can do there.

But I'll gladly take a fix-up patch for 4.9.y, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 107 bytes --]


Please queue up the following netwokring bug fixes for
v4.16 and v4.17 -stable, respectively.

Thank you.

[-- Attachment #2: net_416.mbox --]
[-- Type: Application/Octet-Stream, Size: 130447 bytes --]

From 1ae00e8844208cb59236d5a6ccc4799bf14cfa4f Mon Sep 17 00:00:00 2001
From: Suresh Reddy <suresh.reddy@broadcom.com>
Date: Mon, 28 May 2018 01:26:06 -0400
Subject: [PATCH 01/43] be2net: Fix error detection logic for BE3

[ Upstream commit d2c2725c2cdbcc108a191f50953d31c7b6556761 ]

Check for 0xE00 (RECOVERABLE_ERR) along with ARMFW UE (0x0)
in be_detect_error() to know whether the error is valid error or not

Fixes: 673c96e5a ("be2net: Fix UE detection logic for BE3")
Signed-off-by: Suresh Reddy <suresh.reddy@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/emulex/benet/be_main.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 5774fb6f8aa0..4d764c3ee155 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -3309,7 +3309,9 @@ void be_detect_error(struct be_adapter *adapter)
 				if ((val & POST_STAGE_FAT_LOG_START)
 				     != POST_STAGE_FAT_LOG_START &&
 				    (val & POST_STAGE_ARMFW_UE)
-				     != POST_STAGE_ARMFW_UE)
+				     != POST_STAGE_ARMFW_UE &&
+				    (val & POST_STAGE_RECOVERABLE_ERR)
+				     != POST_STAGE_RECOVERABLE_ERR)
 					return;
 			}
 
-- 
2.17.1


From 9d3c4f4c0a001fbf2d88a1f369f6bf242ca9b1e2 Mon Sep 17 00:00:00 2001
From: Julia Lawall <Julia.Lawall@lip6.fr>
Date: Wed, 6 Jun 2018 15:03:22 +0200
Subject: [PATCH 02/43] bnx2x: use the right constant

[ Upstream commit dd612f18a49b63af8b3a5f572d999bdb197385bc ]

Nearby code that also tests port suggests that the P0 constant should be
used when port is zero.

The semantic match that finds this problem is as follows:
(http://coccinelle.lip6.fr/)

// <smpl>
@@
expression e,e1;
@@

* e ? e1 : e1
// </smpl>

Fixes: 6c3218c6f7e5 ("bnx2x: Adjust ETS to 578xx")
Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
index 7dd83d0ef0a0..22243c480a05 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
@@ -588,7 +588,7 @@ static void bnx2x_ets_e3b0_nig_disabled(const struct link_params *params,
 	 * slots for the highest priority.
 	 */
 	REG_WR(bp, (port) ? NIG_REG_P1_TX_ARB_NUM_STRICT_ARB_SLOTS :
-		   NIG_REG_P1_TX_ARB_NUM_STRICT_ARB_SLOTS, 0x100);
+		   NIG_REG_P0_TX_ARB_NUM_STRICT_ARB_SLOTS, 0x100);
 	/* Mapping between the CREDIT_WEIGHT registers and actual client
 	 * numbers
 	 */
-- 
2.17.1


From af9b6951f2b84721a1b9b48942bcddbf61e90022 Mon Sep 17 00:00:00 2001
From: Paul Blakey <paulb@mellanox.com>
Date: Wed, 30 May 2018 11:29:15 +0300
Subject: [PATCH 03/43] cls_flower: Fix incorrect idr release when failing to
 modify rule

[ Upstream commit 8258d2da9f9f521dce7019e018360c28d116354e ]

When we fail to modify a rule, we incorrectly release the idr handle
of the unmodified old rule.

Fix that by checking if we need to release it.

Fixes: fe2502e49b58 ("net_sched: remove cls_flower idr on failure")
Reported-by: Vlad Buslov <vladbu@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_flower.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 7d0ce2c40f93..2c0c557c0007 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -974,7 +974,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
 	return 0;
 
 errout_idr:
-	if (fnew->handle)
+	if (!fold)
 		idr_remove(&head->handle_idr, fnew->handle);
 errout:
 	tcf_exts_destroy(&fnew->exts);
-- 
2.17.1


From ff3226c27638c2f31cbfa792d7618610b2b305b9 Mon Sep 17 00:00:00 2001
From: Alexey Kodanev <alexey.kodanev@oracle.com>
Date: Mon, 21 May 2018 19:28:44 +0300
Subject: [PATCH 04/43] dccp: don't free ccid2_hc_tx_sock struct in
 dccp_disconnect()

[ Upstream commit 2677d20677314101293e6da0094ede7b5526d2b1 ]

Syzbot reported the use-after-free in timer_is_static_object() [1].

This can happen because the structure for the rto timer (ccid2_hc_tx_sock)
is removed in dccp_disconnect(), and ccid2_hc_tx_rto_expire() can be
called after that.

The report [1] is similar to the one in commit 120e9dabaf55 ("dccp:
defer ccid_hc_tx_delete() at dismantle time"). And the fix is the same,
delay freeing ccid2_hc_tx_sock structure, so that it is freed in
dccp_sk_destruct().

[1]

==================================================================
BUG: KASAN: use-after-free in timer_is_static_object+0x80/0x90
kernel/time/timer.c:607
Read of size 8 at addr ffff8801bebb5118 by task syz-executor2/25299

CPU: 1 PID: 25299 Comm: syz-executor2 Not tainted 4.17.0-rc5+ #54
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
Call Trace:
  <IRQ>
  __dump_stack lib/dump_stack.c:77 [inline]
  dump_stack+0x1b9/0x294 lib/dump_stack.c:113
  print_address_description+0x6c/0x20b mm/kasan/report.c:256
  kasan_report_error mm/kasan/report.c:354 [inline]
  kasan_report.cold.7+0x242/0x2fe mm/kasan/report.c:412
  __asan_report_load8_noabort+0x14/0x20 mm/kasan/report.c:433
  timer_is_static_object+0x80/0x90 kernel/time/timer.c:607
  debug_object_activate+0x2d9/0x670 lib/debugobjects.c:508
  debug_timer_activate kernel/time/timer.c:709 [inline]
  debug_activate kernel/time/timer.c:764 [inline]
  __mod_timer kernel/time/timer.c:1041 [inline]
  mod_timer+0x4d3/0x13b0 kernel/time/timer.c:1102
  sk_reset_timer+0x22/0x60 net/core/sock.c:2742
  ccid2_hc_tx_rto_expire+0x587/0x680 net/dccp/ccids/ccid2.c:147
  call_timer_fn+0x230/0x940 kernel/time/timer.c:1326
  expire_timers kernel/time/timer.c:1363 [inline]
  __run_timers+0x79e/0xc50 kernel/time/timer.c:1666
  run_timer_softirq+0x4c/0x70 kernel/time/timer.c:1692
  __do_softirq+0x2e0/0xaf5 kernel/softirq.c:285
  invoke_softirq kernel/softirq.c:365 [inline]
  irq_exit+0x1d1/0x200 kernel/softirq.c:405
  exiting_irq arch/x86/include/asm/apic.h:525 [inline]
  smp_apic_timer_interrupt+0x17e/0x710 arch/x86/kernel/apic/apic.c:1052
  apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:863
  </IRQ>
...
Allocated by task 25374:
  save_stack+0x43/0xd0 mm/kasan/kasan.c:448
  set_track mm/kasan/kasan.c:460 [inline]
  kasan_kmalloc+0xc4/0xe0 mm/kasan/kasan.c:553
  kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:490
  kmem_cache_alloc+0x12e/0x760 mm/slab.c:3554
  ccid_new+0x25b/0x3e0 net/dccp/ccid.c:151
  dccp_hdlr_ccid+0x27/0x150 net/dccp/feat.c:44
  __dccp_feat_activate+0x184/0x270 net/dccp/feat.c:344
  dccp_feat_activate_values+0x3a7/0x819 net/dccp/feat.c:1538
  dccp_create_openreq_child+0x472/0x610 net/dccp/minisocks.c:128
  dccp_v4_request_recv_sock+0x12c/0xca0 net/dccp/ipv4.c:408
  dccp_v6_request_recv_sock+0x125d/0x1f10 net/dccp/ipv6.c:415
  dccp_check_req+0x455/0x6a0 net/dccp/minisocks.c:197
  dccp_v4_rcv+0x7b8/0x1f3f net/dccp/ipv4.c:841
  ip_local_deliver_finish+0x2e3/0xd80 net/ipv4/ip_input.c:215
  NF_HOOK include/linux/netfilter.h:288 [inline]
  ip_local_deliver+0x1e1/0x720 net/ipv4/ip_input.c:256
  dst_input include/net/dst.h:450 [inline]
  ip_rcv_finish+0x81b/0x2200 net/ipv4/ip_input.c:396
  NF_HOOK include/linux/netfilter.h:288 [inline]
  ip_rcv+0xb70/0x143d net/ipv4/ip_input.c:492
  __netif_receive_skb_core+0x26f5/0x3630 net/core/dev.c:4592
  __netif_receive_skb+0x2c/0x1e0 net/core/dev.c:4657
  process_backlog+0x219/0x760 net/core/dev.c:5337
  napi_poll net/core/dev.c:5735 [inline]
  net_rx_action+0x7b7/0x1930 net/core/dev.c:5801
  __do_softirq+0x2e0/0xaf5 kernel/softirq.c:285

Freed by task 25374:
  save_stack+0x43/0xd0 mm/kasan/kasan.c:448
  set_track mm/kasan/kasan.c:460 [inline]
  __kasan_slab_free+0x11a/0x170 mm/kasan/kasan.c:521
  kasan_slab_free+0xe/0x10 mm/kasan/kasan.c:528
  __cache_free mm/slab.c:3498 [inline]
  kmem_cache_free+0x86/0x2d0 mm/slab.c:3756
  ccid_hc_tx_delete+0xc3/0x100 net/dccp/ccid.c:190
  dccp_disconnect+0x130/0xc66 net/dccp/proto.c:286
  dccp_close+0x3bc/0xe60 net/dccp/proto.c:1045
  inet_release+0x104/0x1f0 net/ipv4/af_inet.c:427
  inet6_release+0x50/0x70 net/ipv6/af_inet6.c:460
  sock_release+0x96/0x1b0 net/socket.c:594
  sock_close+0x16/0x20 net/socket.c:1149
  __fput+0x34d/0x890 fs/file_table.c:209
  ____fput+0x15/0x20 fs/file_table.c:243
  task_work_run+0x1e4/0x290 kernel/task_work.c:113
  tracehook_notify_resume include/linux/tracehook.h:191 [inline]
  exit_to_usermode_loop+0x2bd/0x310 arch/x86/entry/common.c:166
  prepare_exit_to_usermode arch/x86/entry/common.c:196 [inline]
  syscall_return_slowpath arch/x86/entry/common.c:265 [inline]
  do_syscall_64+0x6ac/0x800 arch/x86/entry/common.c:290
  entry_SYSCALL_64_after_hwframe+0x49/0xbe

The buggy address belongs to the object at ffff8801bebb4cc0
  which belongs to the cache ccid2_hc_tx_sock of size 1240
The buggy address is located 1112 bytes inside of
  1240-byte region [ffff8801bebb4cc0, ffff8801bebb5198)
The buggy address belongs to the page:
page:ffffea0006faed00 count:1 mapcount:0 mapping:ffff8801bebb41c0
index:0xffff8801bebb5240 compound_mapcount: 0
flags: 0x2fffc0000008100(slab|head)
raw: 02fffc0000008100 ffff8801bebb41c0 ffff8801bebb5240 0000000100000003
raw: ffff8801cdba3138 ffffea0007634120 ffff8801cdbaab40 0000000000000000
page dumped because: kasan: bad access detected
...
==================================================================

Reported-by: syzbot+5d47e9ec91a6f15dbd6f@syzkaller.appspotmail.com
Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/proto.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 84cd4e3fd01b..0d56e36a6db7 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -283,9 +283,7 @@ int dccp_disconnect(struct sock *sk, int flags)
 
 	dccp_clear_xmit_timers(sk);
 	ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk);
-	ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk);
 	dp->dccps_hc_rx_ccid = NULL;
-	dp->dccps_hc_tx_ccid = NULL;
 
 	__skb_queue_purge(&sk->sk_receive_queue);
 	__skb_queue_purge(&sk->sk_write_queue);
-- 
2.17.1


From 073ffbbf42d51e44a2fa23b3292aa413178fdc45 Mon Sep 17 00:00:00 2001
From: Govindarajulu Varadarajan <gvaradar@cisco.com>
Date: Wed, 23 May 2018 11:17:39 -0700
Subject: [PATCH 05/43] enic: set DMA mask to 47 bit

[ Upstream commit 322eaa06d55ebc1402a4a8d140945cff536638b4 ]

In commit 624dbf55a359b ("driver/net: enic: Try DMA 64 first, then
failover to DMA") DMA mask was changed from 40 bits to 64 bits.
Hardware actually supports only 47 bits.

Fixes: 624dbf55a359b ("driver/net: enic: Try DMA 64 first, then failover to DMA")
Signed-off-by: Govindarajulu Varadarajan <gvaradar@cisco.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cisco/enic/enic_main.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index b91109d967fa..3179599dd797 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -2704,11 +2704,11 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	pci_set_master(pdev);
 
 	/* Query PCI controller on system for DMA addressing
-	 * limitation for the device.  Try 64-bit first, and
+	 * limitation for the device.  Try 47-bit first, and
 	 * fail to 32-bit.
 	 */
 
-	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
+	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(47));
 	if (err) {
 		err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
 		if (err) {
@@ -2722,10 +2722,10 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 			goto err_out_release_regions;
 		}
 	} else {
-		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
+		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(47));
 		if (err) {
 			dev_err(dev, "Unable to obtain %u-bit DMA "
-				"for consistent allocations, aborting\n", 64);
+				"for consistent allocations, aborting\n", 47);
 			goto err_out_release_regions;
 		}
 		using_dac = 1;
-- 
2.17.1


From 7c1a8581770cdc55121a00f1ac7990f95040f747 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 5 Jun 2018 15:01:59 +0200
Subject: [PATCH 06/43] ip6mr: only set ip6mr_table from setsockopt when
 ip6mr_new_table succeeds

[ Upstream commit 848235edb5c93ed086700584c8ff64f6d7fc778d ]

Currently, raw6_sk(sk)->ip6mr_table is set unconditionally during
ip6_mroute_setsockopt(MRT6_TABLE). A subsequent attempt at the same
setsockopt will fail with -ENOENT, since we haven't actually created
that table.

A similar fix for ipv4 was included in commit 5e1859fbcc3c ("ipv4: ipmr:
various fixes and cleanups").

Fixes: d1db275dd3f6 ("ipv6: ip6mr: support multiple tables")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6mr.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 9f6cace9c817..bab166a6fbb3 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1800,7 +1800,8 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
 		ret = 0;
 		if (!ip6mr_new_table(net, v))
 			ret = -ENOMEM;
-		raw6_sk(sk)->ip6mr_table = v;
+		else
+			raw6_sk(sk)->ip6mr_table = v;
 		rtnl_unlock();
 		return ret;
 	}
-- 
2.17.1


From 4d4451ea2e8fe8407ed95772cf021b9c0b1679cc Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Thu, 31 May 2018 10:59:33 +0200
Subject: [PATCH 07/43] ip6_tunnel: remove magic mtu value 0xFFF8

[ Upstream commit f7ff1fde9441b4fcc8ffb6e66e6e5a00d008937e ]

I don't know where this value comes from (probably a copy and paste and
paste and paste ...).
Let's use standard values which are a bit greater.

Link: https://git.kernel.org/pub/scm/linux/kernel/git/davem/netdev-vger-cvs.git/commit/?id=e5afd356a411a
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 11 ++++++++---
 net/ipv6/sit.c        |  5 +++--
 2 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 179313b0926c..58b4ffd7168e 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1688,8 +1688,13 @@ int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu)
 		if (new_mtu < ETH_MIN_MTU)
 			return -EINVAL;
 	}
-	if (new_mtu > 0xFFF8 - dev->hard_header_len)
-		return -EINVAL;
+	if (tnl->parms.proto == IPPROTO_IPV6 || tnl->parms.proto == 0) {
+		if (new_mtu > IP6_MAX_MTU - dev->hard_header_len)
+			return -EINVAL;
+	} else {
+		if (new_mtu > IP_MAX_MTU - dev->hard_header_len)
+			return -EINVAL;
+	}
 	dev->mtu = new_mtu;
 	return 0;
 }
@@ -1837,7 +1842,7 @@ ip6_tnl_dev_init_gen(struct net_device *dev)
 	if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
 		dev->mtu -= 8;
 	dev->min_mtu = ETH_MIN_MTU;
-	dev->max_mtu = 0xFFF8 - dev->hard_header_len;
+	dev->max_mtu = IP6_MAX_MTU - dev->hard_header_len;
 
 	return 0;
 
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index e85791854c87..5d176c532f0c 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1371,7 +1371,7 @@ static void ipip6_tunnel_setup(struct net_device *dev)
 	dev->hard_header_len	= LL_MAX_HEADER + t_hlen;
 	dev->mtu		= ETH_DATA_LEN - t_hlen;
 	dev->min_mtu		= IPV6_MIN_MTU;
-	dev->max_mtu		= 0xFFF8 - t_hlen;
+	dev->max_mtu		= IP6_MAX_MTU - t_hlen;
 	dev->flags		= IFF_NOARP;
 	netif_keep_dst(dev);
 	dev->addr_len		= 4;
@@ -1583,7 +1583,8 @@ static int ipip6_newlink(struct net *src_net, struct net_device *dev,
 	if (tb[IFLA_MTU]) {
 		u32 mtu = nla_get_u32(tb[IFLA_MTU]);
 
-		if (mtu >= IPV6_MIN_MTU && mtu <= 0xFFF8 - dev->hard_header_len)
+		if (mtu >= IPV6_MIN_MTU &&
+		    mtu <= IP6_MAX_MTU - dev->hard_header_len)
 			dev->mtu = mtu;
 	}
 
-- 
2.17.1


From 3ae7cbd446c5a32dac0aca5e457af1c44da82201 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 21 May 2018 10:51:53 -0700
Subject: [PATCH 08/43] ipmr: properly check rhltable_init() return value

[ Upstream commit 66fb33254f45df4b049f487aff1cbde1ef919390 ]

commit 8fb472c09b9d ("ipmr: improve hash scalability")
added a call to rhltable_init() without checking its return value.

This problem was then later copied to IPv6 and factorized in commit
0bbbf0e7d0e7 ("ipmr, ip6mr: Unite creation of new mr_table")

kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] SMP KASAN
Dumping ftrace buffer:
   (ftrace buffer empty)
Modules linked in:
CPU: 1 PID: 31552 Comm: syz-executor7 Not tainted 4.17.0-rc5+ #60
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:rht_key_hashfn include/linux/rhashtable.h:277 [inline]
RIP: 0010:__rhashtable_lookup include/linux/rhashtable.h:630 [inline]
RIP: 0010:rhltable_lookup include/linux/rhashtable.h:716 [inline]
RIP: 0010:mr_mfc_find_parent+0x2ad/0xbb0 net/ipv4/ipmr_base.c:63
RSP: 0018:ffff8801826aef70 EFLAGS: 00010203
RAX: 0000000000000001 RBX: 0000000000000001 RCX: ffffc90001ea0000
RDX: 0000000000000079 RSI: ffffffff8661e859 RDI: 000000000000000c
RBP: ffff8801826af1c0 R08: ffff8801b2212000 R09: ffffed003b5e46c2
R10: ffffed003b5e46c2 R11: ffff8801daf23613 R12: dffffc0000000000
R13: ffff8801826af198 R14: ffff8801cf8225c0 R15: ffff8801826af658
FS:  00007ff7fa732700(0000) GS:ffff8801daf00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000003ffffff9c CR3: 00000001b0210000 CR4: 00000000001406e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 ip6mr_cache_find_parent net/ipv6/ip6mr.c:981 [inline]
 ip6mr_mfc_delete+0x1fe/0x6b0 net/ipv6/ip6mr.c:1221
 ip6_mroute_setsockopt+0x15c6/0x1d70 net/ipv6/ip6mr.c:1698
 do_ipv6_setsockopt.isra.9+0x422/0x4660 net/ipv6/ipv6_sockglue.c:163
 ipv6_setsockopt+0xbd/0x170 net/ipv6/ipv6_sockglue.c:922
 rawv6_setsockopt+0x59/0x140 net/ipv6/raw.c:1060
 sock_common_setsockopt+0x9a/0xe0 net/core/sock.c:3039
 __sys_setsockopt+0x1bd/0x390 net/socket.c:1903
 __do_sys_setsockopt net/socket.c:1914 [inline]
 __se_sys_setsockopt net/socket.c:1911 [inline]
 __x64_sys_setsockopt+0xbe/0x150 net/socket.c:1911
 do_syscall_64+0x1b1/0x800 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Fixes: 8fb472c09b9d ("ipmr: improve hash scalability")
Fixes: 0bbbf0e7d0e7 ("ipmr, ip6mr: Unite creation of new mr_table")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Cc: Yuval Mintz <yuvalm@mellanox.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ipmr.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index b05689bbba31..9669722f6f57 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -356,6 +356,7 @@ static const struct rhashtable_params ipmr_rht_params = {
 static struct mr_table *ipmr_new_table(struct net *net, u32 id)
 {
 	struct mr_table *mrt;
+	int err;
 
 	/* "pimreg%u" should not exceed 16 bytes (IFNAMSIZ) */
 	if (id != RT_TABLE_DEFAULT && id >= 1000000000)
@@ -371,7 +372,11 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id)
 	write_pnet(&mrt->net, net);
 	mrt->id = id;
 
-	rhltable_init(&mrt->mfc_hash, &ipmr_rht_params);
+	err = rhltable_init(&mrt->mfc_hash, &ipmr_rht_params);
+	if (err) {
+		kfree(mrt);
+		return ERR_PTR(err);
+	}
 	INIT_LIST_HEAD(&mrt->mfc_cache_list);
 	INIT_LIST_HEAD(&mrt->mfc_unres_queue);
 
-- 
2.17.1


From 3a94d3435b697e285e9a9c0f0f06fc6daf7eb85c Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 23 May 2018 14:29:52 -0400
Subject: [PATCH 09/43] ipv4: remove warning in ip_recv_error

[ Upstream commit 730c54d59403658a62af6517338fa8d4922c1b28 ]

A precondition check in ip_recv_error triggered on an otherwise benign
race. Remove the warning.

The warning triggers when passing an ipv6 socket to this ipv4 error
handling function. RaceFuzzer was able to trigger it due to a race
in setsockopt IPV6_ADDRFORM.

  ---
  CPU0
    do_ipv6_setsockopt
      sk->sk_socket->ops = &inet_dgram_ops;

  ---
  CPU1
    sk->sk_prot->recvmsg
      udp_recvmsg
        ip_recv_error
          WARN_ON_ONCE(sk->sk_family == AF_INET6);

  ---
  CPU0
    do_ipv6_setsockopt
      sk->sk_family = PF_INET;

This socket option converts a v6 socket that is connected to a v4 peer
to an v4 socket. It updates the socket on the fly, changing fields in
sk as well as other structs. This is inherently non-atomic. It races
with the lockless udp_recvmsg path.

No other code makes an assumption that these fields are updated
atomically. It is benign here, too, as ip_recv_error cares only about
the protocol of the skbs enqueued on the error queue, for which
sk_family is not a precise predictor (thanks to another isue with
IPV6_ADDRFORM).

Link: http://lkml.kernel.org/r/20180518120826.GA19515@dragonet.kaist.ac.kr
Fixes: 7ce875e5ecb8 ("ipv4: warn once on passing AF_INET6 socket to ip_recv_error")
Reported-by: DaeRyong Jeong <threeearcat@gmail.com>
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_sockglue.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 74c962b9b09c..d89d8c59b5ed 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -511,8 +511,6 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 	int err;
 	int copied;
 
-	WARN_ON_ONCE(sk->sk_family == AF_INET6);
-
 	err = -EAGAIN;
 	skb = sock_dequeue_err_skb(sk);
 	if (!skb)
-- 
2.17.1


From 1ab9f73467d83838b54d30ee64cc64cca475ab0a Mon Sep 17 00:00:00 2001
From: Michal Kubecek <mkubecek@suse.cz>
Date: Mon, 4 Jun 2018 11:36:05 +0200
Subject: [PATCH 10/43] ipv6: omit traffic class when calculating flow hash

[ Upstream commit fa1be7e01ea863e911349e30456706749518eeab ]

Some of the code paths calculating flow hash for IPv6 use flowlabel member
of struct flowi6 which, despite its name, encodes both flow label and
traffic class. If traffic class changes within a TCP connection (as e.g.
ssh does), ECMP route can switch between path. It's also inconsistent with
other code paths where ip6_flowlabel() (returning only flow label) is used
to feed the key.

Use only flow label everywhere, including one place where hash key is set
using ip6_flowinfo().

Fixes: 51ebd3181572 ("ipv6: add support of equal cost multipath (ECMP)")
Fixes: f70ea018da06 ("net: Add functions to get skb->hash based on flow structures")
Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h        | 5 +++++
 net/core/flow_dissector.c | 2 +-
 net/ipv6/route.c          | 2 +-
 3 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 8606c9113d3f..a3339ff732a0 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -918,6 +918,11 @@ static inline __be32 ip6_make_flowinfo(unsigned int tclass, __be32 flowlabel)
 	return htonl(tclass << IPV6_TCLASS_SHIFT) | flowlabel;
 }
 
+static inline __be32 flowi6_get_flowlabel(const struct flowi6 *fl6)
+{
+	return fl6->flowlabel & IPV6_FLOWLABEL_MASK;
+}
+
 /*
  *	Prototypes exported by ipv6
  */
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 559db9ea8d86..ec3d47ebd919 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -1334,7 +1334,7 @@ __u32 __get_hash_from_flowi6(const struct flowi6 *fl6, struct flow_keys *keys)
 	keys->ports.src = fl6->fl6_sport;
 	keys->ports.dst = fl6->fl6_dport;
 	keys->keyid.keyid = fl6->fl6_gre_key;
-	keys->tags.flow_label = (__force u32)fl6->flowlabel;
+	keys->tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6);
 	keys->basic.ip_proto = fl6->flowi6_proto;
 
 	return flow_hash_from_keys(keys);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 1aee1a537cb1..8f749742f11f 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1850,7 +1850,7 @@ static void ip6_multipath_l3_keys(const struct sk_buff *skb,
 	keys->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
 	keys->addrs.v6addrs.src = key_iph->saddr;
 	keys->addrs.v6addrs.dst = key_iph->daddr;
-	keys->tags.flow_label = ip6_flowinfo(key_iph);
+	keys->tags.flow_label = ip6_flowlabel(key_iph);
 	keys->basic.ip_proto = key_iph->nexthdr;
 }
 
-- 
2.17.1


From 5d91cad65dbd52739491a116f04e3d7e069b4a8a Mon Sep 17 00:00:00 2001
From: Wenwen Wang <wang6495@umn.edu>
Date: Mon, 21 May 2018 01:58:07 -0500
Subject: [PATCH 11/43] isdn: eicon: fix a missing-check bug

[ Upstream commit 6009d1fe6ba3bb2dab55921da60465329cc1cd89 ]

In divasmain.c, the function divas_write() firstly invokes the function
diva_xdi_open_adapter() to open the adapter that matches with the adapter
number provided by the user, and then invokes the function diva_xdi_write()
to perform the write operation using the matched adapter. The two functions
diva_xdi_open_adapter() and diva_xdi_write() are located in diva.c.

In diva_xdi_open_adapter(), the user command is copied to the object 'msg'
from the userspace pointer 'src' through the function pointer 'cp_fn',
which eventually calls copy_from_user() to do the copy. Then, the adapter
number 'msg.adapter' is used to find out a matched adapter from the
'adapter_queue'. A matched adapter will be returned if it is found.
Otherwise, NULL is returned to indicate the failure of the verification on
the adapter number.

As mentioned above, if a matched adapter is returned, the function
diva_xdi_write() is invoked to perform the write operation. In this
function, the user command is copied once again from the userspace pointer
'src', which is the same as the 'src' pointer in diva_xdi_open_adapter() as
both of them are from the 'buf' pointer in divas_write(). Similarly, the
copy is achieved through the function pointer 'cp_fn', which finally calls
copy_from_user(). After the successful copy, the corresponding command
processing handler of the matched adapter is invoked to perform the write
operation.

It is obvious that there are two copies here from userspace, one is in
diva_xdi_open_adapter(), and one is in diva_xdi_write(). Plus, both of
these two copies share the same source userspace pointer, i.e., the 'buf'
pointer in divas_write(). Given that a malicious userspace process can race
to change the content pointed by the 'buf' pointer, this can pose potential
security issues. For example, in the first copy, the user provides a valid
adapter number to pass the verification process and a valid adapter can be
found. Then the user can modify the adapter number to an invalid number.
This way, the user can bypass the verification process of the adapter
number and inject inconsistent data.

This patch reuses the data copied in
diva_xdi_open_adapter() and passes it to diva_xdi_write(). This way, the
above issues can be avoided.

Signed-off-by: Wenwen Wang <wang6495@umn.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/hardware/eicon/diva.c      | 22 +++++++++++++++-------
 drivers/isdn/hardware/eicon/diva.h      |  5 +++--
 drivers/isdn/hardware/eicon/divasmain.c | 18 +++++++++++-------
 3 files changed, 29 insertions(+), 16 deletions(-)

diff --git a/drivers/isdn/hardware/eicon/diva.c b/drivers/isdn/hardware/eicon/diva.c
index 944a7f338099..1b25d8bc153a 100644
--- a/drivers/isdn/hardware/eicon/diva.c
+++ b/drivers/isdn/hardware/eicon/diva.c
@@ -388,10 +388,10 @@ void divasa_xdi_driver_unload(void)
 **  Receive and process command from user mode utility
 */
 void *diva_xdi_open_adapter(void *os_handle, const void __user *src,
-			    int length,
+			    int length, void *mptr,
 			    divas_xdi_copy_from_user_fn_t cp_fn)
 {
-	diva_xdi_um_cfg_cmd_t msg;
+	diva_xdi_um_cfg_cmd_t *msg = (diva_xdi_um_cfg_cmd_t *)mptr;
 	diva_os_xdi_adapter_t *a = NULL;
 	diva_os_spin_lock_magic_t old_irql;
 	struct list_head *tmp;
@@ -401,21 +401,21 @@ void *diva_xdi_open_adapter(void *os_handle, const void __user *src,
 			 length, sizeof(diva_xdi_um_cfg_cmd_t)))
 			return NULL;
 	}
-	if ((*cp_fn) (os_handle, &msg, src, sizeof(msg)) <= 0) {
+	if ((*cp_fn) (os_handle, msg, src, sizeof(*msg)) <= 0) {
 		DBG_ERR(("A: A(?) open, write error"))
 			return NULL;
 	}
 	diva_os_enter_spin_lock(&adapter_lock, &old_irql, "open_adapter");
 	list_for_each(tmp, &adapter_queue) {
 		a = list_entry(tmp, diva_os_xdi_adapter_t, link);
-		if (a->controller == (int)msg.adapter)
+		if (a->controller == (int)msg->adapter)
 			break;
 		a = NULL;
 	}
 	diva_os_leave_spin_lock(&adapter_lock, &old_irql, "open_adapter");
 
 	if (!a) {
-		DBG_ERR(("A: A(%d) open, adapter not found", msg.adapter))
+		DBG_ERR(("A: A(%d) open, adapter not found", msg->adapter))
 			}
 
 	return (a);
@@ -437,8 +437,10 @@ void diva_xdi_close_adapter(void *adapter, void *os_handle)
 
 int
 diva_xdi_write(void *adapter, void *os_handle, const void __user *src,
-	       int length, divas_xdi_copy_from_user_fn_t cp_fn)
+	       int length, void *mptr,
+	       divas_xdi_copy_from_user_fn_t cp_fn)
 {
+	diva_xdi_um_cfg_cmd_t *msg = (diva_xdi_um_cfg_cmd_t *)mptr;
 	diva_os_xdi_adapter_t *a = (diva_os_xdi_adapter_t *) adapter;
 	void *data;
 
@@ -459,7 +461,13 @@ diva_xdi_write(void *adapter, void *os_handle, const void __user *src,
 			return (-2);
 	}
 
-	length = (*cp_fn) (os_handle, data, src, length);
+	if (msg) {
+		*(diva_xdi_um_cfg_cmd_t *)data = *msg;
+		length = (*cp_fn) (os_handle, (char *)data + sizeof(*msg),
+				   src + sizeof(*msg), length - sizeof(*msg));
+	} else {
+		length = (*cp_fn) (os_handle, data, src, length);
+	}
 	if (length > 0) {
 		if ((*(a->interface.cmd_proc))
 		    (a, (diva_xdi_um_cfg_cmd_t *) data, length)) {
diff --git a/drivers/isdn/hardware/eicon/diva.h b/drivers/isdn/hardware/eicon/diva.h
index b067032093a8..1ad76650fbf9 100644
--- a/drivers/isdn/hardware/eicon/diva.h
+++ b/drivers/isdn/hardware/eicon/diva.h
@@ -20,10 +20,11 @@ int diva_xdi_read(void *adapter, void *os_handle, void __user *dst,
 		  int max_length, divas_xdi_copy_to_user_fn_t cp_fn);
 
 int diva_xdi_write(void *adapter, void *os_handle, const void __user *src,
-		   int length, divas_xdi_copy_from_user_fn_t cp_fn);
+		   int length, void *msg,
+		   divas_xdi_copy_from_user_fn_t cp_fn);
 
 void *diva_xdi_open_adapter(void *os_handle, const void __user *src,
-			    int length,
+			    int length, void *msg,
 			    divas_xdi_copy_from_user_fn_t cp_fn);
 
 void diva_xdi_close_adapter(void *adapter, void *os_handle);
diff --git a/drivers/isdn/hardware/eicon/divasmain.c b/drivers/isdn/hardware/eicon/divasmain.c
index b9980e84f9db..b6a3950b2564 100644
--- a/drivers/isdn/hardware/eicon/divasmain.c
+++ b/drivers/isdn/hardware/eicon/divasmain.c
@@ -591,19 +591,22 @@ static int divas_release(struct inode *inode, struct file *file)
 static ssize_t divas_write(struct file *file, const char __user *buf,
 			   size_t count, loff_t *ppos)
 {
+	diva_xdi_um_cfg_cmd_t msg;
 	int ret = -EINVAL;
 
 	if (!file->private_data) {
 		file->private_data = diva_xdi_open_adapter(file, buf,
-							   count,
+							   count, &msg,
 							   xdi_copy_from_user);
-	}
-	if (!file->private_data) {
-		return (-ENODEV);
+		if (!file->private_data)
+			return (-ENODEV);
+		ret = diva_xdi_write(file->private_data, file,
+				     buf, count, &msg, xdi_copy_from_user);
+	} else {
+		ret = diva_xdi_write(file->private_data, file,
+				     buf, count, NULL, xdi_copy_from_user);
 	}
 
-	ret = diva_xdi_write(file->private_data, file,
-			     buf, count, xdi_copy_from_user);
 	switch (ret) {
 	case -1:		/* Message should be removed from rx mailbox first */
 		ret = -EBUSY;
@@ -622,11 +625,12 @@ static ssize_t divas_write(struct file *file, const char __user *buf,
 static ssize_t divas_read(struct file *file, char __user *buf,
 			  size_t count, loff_t *ppos)
 {
+	diva_xdi_um_cfg_cmd_t msg;
 	int ret = -EINVAL;
 
 	if (!file->private_data) {
 		file->private_data = diva_xdi_open_adapter(file, buf,
-							   count,
+							   count, &msg,
 							   xdi_copy_from_user);
 	}
 	if (!file->private_data) {
-- 
2.17.1


From 8aeaaf2274ed4a95faa95ec685a8eb7ebdd1b42a Mon Sep 17 00:00:00 2001
From: Kirill Tkhai <ktkhai@virtuozzo.com>
Date: Fri, 1 Jun 2018 14:30:38 +0300
Subject: [PATCH 12/43] kcm: Fix use-after-free caused by clonned sockets

[ Upstream commit eb7f54b90bd8f469834c5e86dcf72ebf9a629811 ]

(resend for properly queueing in patchwork)

kcm_clone() creates kernel socket, which does not take net counter.
Thus, the net may die before the socket is completely destructed,
i.e. kcm_exit_net() is executed before kcm_done().

Reported-by: syzbot+5f1a04e374a635efc426@syzkaller.appspotmail.com
Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/kcm/kcmsock.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index dc76bc346829..d3601d421571 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -1671,7 +1671,7 @@ static struct file *kcm_clone(struct socket *osock)
 	__module_get(newsock->ops->owner);
 
 	newsk = sk_alloc(sock_net(osock->sk), PF_KCM, GFP_KERNEL,
-			 &kcm_proto, true);
+			 &kcm_proto, false);
 	if (!newsk) {
 		sock_release(newsock);
 		return ERR_PTR(-ENOMEM);
-- 
2.17.1


From 90477413d84058614338314978229859fd641214 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Mon, 4 Jun 2018 18:52:19 +0200
Subject: [PATCH 13/43] l2tp: fix refcount leakage on PPPoL2TP sockets

[ Upstream commit 3d609342cc04129ff7568e19316ce3d7451a27e8 ]

Commit d02ba2a6110c ("l2tp: fix race in pppol2tp_release with session
object destroy") tried to fix a race condition where a PPPoL2TP socket
would disappear while the L2TP session was still using it. However, it
missed the root issue which is that an L2TP session may accept to be
reconnected if its associated socket has entered the release process.

The tentative fix makes the session hold the socket it is connected to.
That saves the kernel from crashing, but introduces refcount leakage,
preventing the socket from completing the release process. Once stalled,
everything the socket depends on can't be released anymore, including
the L2TP session and the l2tp_ppp module.

The root issue is that, when releasing a connected PPPoL2TP socket, the
session's ->sk pointer (RCU-protected) is reset to NULL and we have to
wait for a grace period before destroying the socket. The socket drops
the session in its ->sk_destruct callback function, so the session
will exist until the last reference on the socket is dropped.
Therefore, there is a time frame where pppol2tp_connect() may accept
reconnecting a session, as it only checks ->sk to figure out if the
session is connected. This time frame is shortened by the fact that
pppol2tp_release() calls l2tp_session_delete(), making the session
unreachable before resetting ->sk. However, pppol2tp_connect() may
grab the session before it gets unhashed by l2tp_session_delete(), but
it may test ->sk after the later got reset. The race is not so hard to
trigger and syzbot found a pretty reliable reproducer:
https://syzkaller.appspot.com/bug?id=418578d2a4389074524e04d641eacb091961b2cf

Before d02ba2a6110c, another race could let pppol2tp_release()
overwrite the ->__sk pointer of an L2TP session, thus tricking
pppol2tp_put_sk() into calling sock_put() on a socket that is different
than the one for which pppol2tp_release() was originally called. To get
there, we had to trigger the race described above, therefore having one
PPPoL2TP socket being released, while the session it is connected to is
reconnecting to a different PPPoL2TP socket. When releasing this new
socket fast enough, pppol2tp_release() overwrites the session's
->__sk pointer with the address of the new socket, before the first
pppol2tp_put_sk() call gets scheduled. Then the pppol2tp_put_sk() call
invoked by the original socket will sock_put() the new socket,
potentially dropping its last reference. When the second
pppol2tp_put_sk() finally runs, its socket has already been freed.

With d02ba2a6110c, the session takes a reference on both sockets.
Furthermore, the session's ->sk pointer is reset in the
pppol2tp_session_close() callback function rather than in
pppol2tp_release(). Therefore, ->__sk can't be overwritten and
pppol2tp_put_sk() is called only once (l2tp_session_delete() will only
run pppol2tp_session_close() once, to protect the session against
concurrent deletion requests). Now pppol2tp_put_sk() will properly
sock_put() the original socket, but the new socket will remain, as
l2tp_session_delete() prevented the release process from completing.
Here, we don't depend on the ->__sk race to trigger the bug. Getting
into the pppol2tp_connect() race is enough to leak the reference, no
matter when new socket is released.

So it all boils down to pppol2tp_connect() failing to realise that the
session has already been connected. This patch drops the unneeded extra
reference counting (mostly reverting d02ba2a6110c) and checks that
neither ->sk nor ->__sk is set before allowing a session to be
connected.

Fixes: d02ba2a6110c ("l2tp: fix race in pppol2tp_release with session object destroy")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ppp.c | 35 +++++++++++++++++------------------
 1 file changed, 17 insertions(+), 18 deletions(-)

diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 0c4530ad74be..b7185d600844 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -428,16 +428,6 @@ static void pppol2tp_put_sk(struct rcu_head *head)
  */
 static void pppol2tp_session_close(struct l2tp_session *session)
 {
-	struct pppol2tp_session *ps;
-
-	ps = l2tp_session_priv(session);
-	mutex_lock(&ps->sk_lock);
-	ps->__sk = rcu_dereference_protected(ps->sk,
-					     lockdep_is_held(&ps->sk_lock));
-	RCU_INIT_POINTER(ps->sk, NULL);
-	if (ps->__sk)
-		call_rcu(&ps->rcu, pppol2tp_put_sk);
-	mutex_unlock(&ps->sk_lock);
 }
 
 /* Really kill the session socket. (Called from sock_put() if
@@ -480,15 +470,24 @@ static int pppol2tp_release(struct socket *sock)
 	sock_orphan(sk);
 	sock->sk = NULL;
 
-	/* If the socket is associated with a session,
-	 * l2tp_session_delete will call pppol2tp_session_close which
-	 * will drop the session's ref on the socket.
-	 */
 	session = pppol2tp_sock_to_session(sk);
 	if (session) {
+		struct pppol2tp_session *ps;
+
 		l2tp_session_delete(session);
-		/* drop the ref obtained by pppol2tp_sock_to_session */
-		sock_put(sk);
+
+		ps = l2tp_session_priv(session);
+		mutex_lock(&ps->sk_lock);
+		ps->__sk = rcu_dereference_protected(ps->sk,
+						     lockdep_is_held(&ps->sk_lock));
+		RCU_INIT_POINTER(ps->sk, NULL);
+		mutex_unlock(&ps->sk_lock);
+		call_rcu(&ps->rcu, pppol2tp_put_sk);
+
+		/* Rely on the sock_put() call at the end of the function for
+		 * dropping the reference held by pppol2tp_sock_to_session().
+		 * The last reference will be dropped by pppol2tp_put_sk().
+		 */
 	}
 
 	release_sock(sk);
@@ -742,7 +741,8 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 		 */
 		mutex_lock(&ps->sk_lock);
 		if (rcu_dereference_protected(ps->sk,
-					      lockdep_is_held(&ps->sk_lock))) {
+					      lockdep_is_held(&ps->sk_lock)) ||
+		    ps->__sk) {
 			mutex_unlock(&ps->sk_lock);
 			error = -EEXIST;
 			goto end;
@@ -803,7 +803,6 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 
 out_no_ppp:
 	/* This is how we get the session context from the socket. */
-	sock_hold(sk);
 	sk->sk_user_data = session;
 	rcu_assign_pointer(ps->sk, sk);
 	mutex_unlock(&ps->sk_lock);
-- 
2.17.1


From 73ade7133692f553ab61950873ac83779b9f26b6 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Sun, 27 May 2018 09:48:41 +0300
Subject: [PATCH 14/43] mlxsw: spectrum: Forbid creation of VLAN 1 over
 port/LAG

[ Upstream commit 47bf9df2e8201d07c40670e093629f8dfd1b5d9f ]

VLAN 1 is internally used for untagged traffic. Prevent creation of
explicit netdevice for that VLAN, because that currently isn't supported
and leads to the NULL pointer dereference cited below.

Fix by preventing creation of VLAN devices with VID of 1 over mlxsw
devices or LAG devices that involve mlxsw devices.

[  327.175816] ================================================================================
[  327.184544] UBSAN: Undefined behaviour in drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c:200:12
[  327.193667] member access within null pointer of type 'const struct mlxsw_sp_fid'
[  327.201226] CPU: 0 PID: 8983 Comm: ip Not tainted 4.17.0-rc4-petrm_net_ip6gre_headroom-custom-140 #11
[  327.210496] Hardware name: Mellanox Technologies Ltd. "MSN2410-CB2F"/"SA000874", BIOS 4.6.5 03/08/2016
[  327.219872] Call Trace:
[  327.222384]  dump_stack+0xc3/0x12b
[  327.234007]  ubsan_epilogue+0x9/0x49
[  327.237638]  ubsan_type_mismatch_common+0x1f9/0x2d0
[  327.255769]  __ubsan_handle_type_mismatch+0x90/0xa7
[  327.264716]  mlxsw_sp_fid_type+0x35/0x50 [mlxsw_spectrum]
[  327.270255]  mlxsw_sp_port_vlan_router_leave+0x46/0xc0 [mlxsw_spectrum]
[  327.277019]  mlxsw_sp_inetaddr_port_vlan_event+0xe1/0x340 [mlxsw_spectrum]
[  327.315031]  mlxsw_sp_netdevice_vrf_event+0xa8/0x100 [mlxsw_spectrum]
[  327.321626]  mlxsw_sp_netdevice_event+0x276/0x430 [mlxsw_spectrum]
[  327.367863]  notifier_call_chain+0x4c/0x150
[  327.372128]  __netdev_upper_dev_link+0x1b3/0x260
[  327.399450]  vrf_add_slave+0xce/0x170 [vrf]
[  327.403703]  do_setlink+0x658/0x1d70
[  327.508998]  rtnl_newlink+0x908/0xf20
[  327.559128]  rtnetlink_rcv_msg+0x50c/0x720
[  327.571720]  netlink_rcv_skb+0x16a/0x1f0
[  327.583450]  netlink_unicast+0x2ca/0x3e0
[  327.599305]  netlink_sendmsg+0x3e2/0x7f0
[  327.616655]  sock_sendmsg+0x76/0xc0
[  327.620207]  ___sys_sendmsg+0x494/0x5d0
[  327.666117]  __sys_sendmsg+0xc2/0x130
[  327.690953]  do_syscall_64+0x66/0x370
[  327.694677]  entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  327.699782] RIP: 0033:0x7f4c2f3f8037
[  327.703393] RSP: 002b:00007ffe8c389708 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
[  327.711035] RAX: ffffffffffffffda RBX: 000000005b03f53e RCX: 00007f4c2f3f8037
[  327.718229] RDX: 0000000000000000 RSI: 00007ffe8c389760 RDI: 0000000000000003
[  327.725431] RBP: 00007ffe8c389760 R08: 0000000000000000 R09: 00007f4c2f443630
[  327.732632] R10: 00000000000005eb R11: 0000000000000246 R12: 0000000000000000
[  327.739833] R13: 00000000006774e0 R14: 00007ffe8c3897e8 R15: 0000000000000000
[  327.747096] ================================================================================

Fixes: 9589a7b5d7d9 ("mlxsw: spectrum: Handle VLAN devices linking / unlinking")
Suggested-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index bf400c75fcc8..c54762729bdf 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4870,6 +4870,11 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev,
 				       "spectrum: Can not put a VLAN on an OVS port");
 			return -EINVAL;
 		}
+		if (is_vlan_dev(upper_dev) &&
+		    vlan_dev_vlan_id(upper_dev) == 1) {
+			NL_SET_ERR_MSG_MOD(extack, "Creating a VLAN device with VID 1 is unsupported: VLAN 1 carries untagged traffic");
+			return -EINVAL;
+		}
 		break;
 	case NETDEV_CHANGEUPPER:
 		upper_dev = info->upper_dev;
-- 
2.17.1


From b86f52fa85234b2be57fb3457029863fb925710b Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Tue, 5 Jun 2018 09:48:13 -0700
Subject: [PATCH 15/43] netdev-FAQ: clarify DaveM's position for stable
 backports

[ Upstream commit 75d4e704fa8d2cf33ff295e5b441317603d7f9fd ]

Per discussion with David at netconf 2018, let's clarify
DaveM's position of handling stable backports in netdev-FAQ.

This is important for people relying on upstream -stable
releases.

Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/netdev-FAQ.txt | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/Documentation/networking/netdev-FAQ.txt b/Documentation/networking/netdev-FAQ.txt
index 2a3278d5cf35..fa951b820b25 100644
--- a/Documentation/networking/netdev-FAQ.txt
+++ b/Documentation/networking/netdev-FAQ.txt
@@ -179,6 +179,15 @@ A: No.  See above answer.  In short, if you think it really belongs in
    dash marker line as described in Documentation/process/submitting-patches.rst to
    temporarily embed that information into the patch that you send.
 
+Q: Are all networking bug fixes backported to all stable releases?
+
+A: Due to capacity, Dave could only take care of the backports for the last
+   2 stable releases. For earlier stable releases, each stable branch maintainer
+   is supposed to take care of them. If you find any patch is missing from an
+   earlier stable branch, please notify stable@vger.kernel.org with either a
+   commit ID or a formal patch backported, and CC Dave and other relevant
+   networking developers.
+
 Q: Someone said that the comment style and coding convention is different
    for the networking content.  Is this true?
 
-- 
2.17.1


From 4c04306ca362927262e47f8034ff5ffa2cc6f347 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Thu, 31 May 2018 09:44:49 +0300
Subject: [PATCH 16/43] net: ethernet: davinci_emac: fix error handling in
 probe()

[ Upstream commit 8005b09d99fac78e6f5fb9da30b5ae94840af03b ]

The current error handling code has an issue where it does:

	if (priv->txchan)
		cpdma_chan_destroy(priv->txchan);

The problem is that ->txchan is either valid or an error pointer (which
would lead to an Oops).  I've changed it to use multiple error labels so
that the test can be removed.

Also there were some missing calls to netif_napi_del().

Fixes: 3ef0fdb2342c ("net: davinci_emac: switch to new cpdma layer")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/davinci_emac.c | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c
index abceea802ea1..38828ab77eb9 100644
--- a/drivers/net/ethernet/ti/davinci_emac.c
+++ b/drivers/net/ethernet/ti/davinci_emac.c
@@ -1873,7 +1873,7 @@ static int davinci_emac_probe(struct platform_device *pdev)
 	if (IS_ERR(priv->txchan)) {
 		dev_err(&pdev->dev, "error initializing tx dma channel\n");
 		rc = PTR_ERR(priv->txchan);
-		goto no_cpdma_chan;
+		goto err_free_dma;
 	}
 
 	priv->rxchan = cpdma_chan_create(priv->dma, EMAC_DEF_RX_CH,
@@ -1881,14 +1881,14 @@ static int davinci_emac_probe(struct platform_device *pdev)
 	if (IS_ERR(priv->rxchan)) {
 		dev_err(&pdev->dev, "error initializing rx dma channel\n");
 		rc = PTR_ERR(priv->rxchan);
-		goto no_cpdma_chan;
+		goto err_free_txchan;
 	}
 
 	res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
 	if (!res) {
 		dev_err(&pdev->dev, "error getting irq res\n");
 		rc = -ENOENT;
-		goto no_cpdma_chan;
+		goto err_free_rxchan;
 	}
 	ndev->irq = res->start;
 
@@ -1914,7 +1914,7 @@ static int davinci_emac_probe(struct platform_device *pdev)
 		pm_runtime_put_noidle(&pdev->dev);
 		dev_err(&pdev->dev, "%s: failed to get_sync(%d)\n",
 			__func__, rc);
-		goto no_cpdma_chan;
+		goto err_napi_del;
 	}
 
 	/* register the network device */
@@ -1924,7 +1924,7 @@ static int davinci_emac_probe(struct platform_device *pdev)
 		dev_err(&pdev->dev, "error in register_netdev\n");
 		rc = -ENODEV;
 		pm_runtime_put(&pdev->dev);
-		goto no_cpdma_chan;
+		goto err_napi_del;
 	}
 
 
@@ -1937,11 +1937,13 @@ static int davinci_emac_probe(struct platform_device *pdev)
 
 	return 0;
 
-no_cpdma_chan:
-	if (priv->txchan)
-		cpdma_chan_destroy(priv->txchan);
-	if (priv->rxchan)
-		cpdma_chan_destroy(priv->rxchan);
+err_napi_del:
+	netif_napi_del(&priv->napi);
+err_free_rxchan:
+	cpdma_chan_destroy(priv->rxchan);
+err_free_txchan:
+	cpdma_chan_destroy(priv->txchan);
+err_free_dma:
 	cpdma_ctlr_destroy(priv->dma);
 no_pdata:
 	if (of_phy_is_fixed_link(np))
-- 
2.17.1


From 52b701118739f2edf557ec9031879f5afff0315e Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Tue, 22 May 2018 13:44:51 -0700
Subject: [PATCH 17/43] net: ipv4: add missing RTA_TABLE to rtm_ipv4_policy

[ Upstream commit 2eabd764cb5512f1338d06ffc054c8bc9fbe9104 ]

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_frontend.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index f05afaf3235c..aa597b2c1429 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -643,6 +643,7 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = {
 	[RTA_ENCAP]		= { .type = NLA_NESTED },
 	[RTA_UID]		= { .type = NLA_U32 },
 	[RTA_MARK]		= { .type = NLA_U32 },
+	[RTA_TABLE]		= { .type = NLA_U32 },
 };
 
 static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
-- 
2.17.1


From 020db3a6379ab5179d014577fc927fd6e8601d56 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 5 Jun 2018 06:06:19 -0700
Subject: [PATCH 18/43] net: metrics: add proper netlink validation

[ Upstream commit 5b5e7a0de2bbf2a1afcd9f49e940010e9fb80d53 ]

Before using nla_get_u32(), better make sure the attribute
is of the proper size.

Code recently was changed, but bug has been there from beginning
of git.

BUG: KMSAN: uninit-value in rtnetlink_put_metrics+0x553/0x960 net/core/rtnetlink.c:746
CPU: 1 PID: 14139 Comm: syz-executor6 Not tainted 4.17.0-rc5+ #103
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x185/0x1d0 lib/dump_stack.c:113
 kmsan_report+0x149/0x260 mm/kmsan/kmsan.c:1084
 __msan_warning_32+0x6e/0xc0 mm/kmsan/kmsan_instr.c:686
 rtnetlink_put_metrics+0x553/0x960 net/core/rtnetlink.c:746
 fib_dump_info+0xc42/0x2190 net/ipv4/fib_semantics.c:1361
 rtmsg_fib+0x65f/0x8c0 net/ipv4/fib_semantics.c:419
 fib_table_insert+0x2314/0x2b50 net/ipv4/fib_trie.c:1287
 inet_rtm_newroute+0x210/0x340 net/ipv4/fib_frontend.c:779
 rtnetlink_rcv_msg+0xa32/0x1560 net/core/rtnetlink.c:4646
 netlink_rcv_skb+0x378/0x600 net/netlink/af_netlink.c:2448
 rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:4664
 netlink_unicast_kernel net/netlink/af_netlink.c:1310 [inline]
 netlink_unicast+0x1678/0x1750 net/netlink/af_netlink.c:1336
 netlink_sendmsg+0x104f/0x1350 net/netlink/af_netlink.c:1901
 sock_sendmsg_nosec net/socket.c:629 [inline]
 sock_sendmsg net/socket.c:639 [inline]
 ___sys_sendmsg+0xec0/0x1310 net/socket.c:2117
 __sys_sendmsg net/socket.c:2155 [inline]
 __do_sys_sendmsg net/socket.c:2164 [inline]
 __se_sys_sendmsg net/socket.c:2162 [inline]
 __x64_sys_sendmsg+0x331/0x460 net/socket.c:2162
 do_syscall_64+0x152/0x230 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x455a09
RSP: 002b:00007faae5fd8c68 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 00007faae5fd96d4 RCX: 0000000000455a09
RDX: 0000000000000000 RSI: 0000000020000000 RDI: 0000000000000013
RBP: 000000000072bea0 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff
R13: 00000000000005d0 R14: 00000000006fdc20 R15: 0000000000000000

Uninit was stored to memory at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:279 [inline]
 kmsan_save_stack mm/kmsan/kmsan.c:294 [inline]
 kmsan_internal_chain_origin+0x12b/0x210 mm/kmsan/kmsan.c:685
 __msan_chain_origin+0x69/0xc0 mm/kmsan/kmsan_instr.c:529
 fib_convert_metrics net/ipv4/fib_semantics.c:1056 [inline]
 fib_create_info+0x2d46/0x9dc0 net/ipv4/fib_semantics.c:1150
 fib_table_insert+0x3e4/0x2b50 net/ipv4/fib_trie.c:1146
 inet_rtm_newroute+0x210/0x340 net/ipv4/fib_frontend.c:779
 rtnetlink_rcv_msg+0xa32/0x1560 net/core/rtnetlink.c:4646
 netlink_rcv_skb+0x378/0x600 net/netlink/af_netlink.c:2448
 rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:4664
 netlink_unicast_kernel net/netlink/af_netlink.c:1310 [inline]
 netlink_unicast+0x1678/0x1750 net/netlink/af_netlink.c:1336
 netlink_sendmsg+0x104f/0x1350 net/netlink/af_netlink.c:1901
 sock_sendmsg_nosec net/socket.c:629 [inline]
 sock_sendmsg net/socket.c:639 [inline]
 ___sys_sendmsg+0xec0/0x1310 net/socket.c:2117
 __sys_sendmsg net/socket.c:2155 [inline]
 __do_sys_sendmsg net/socket.c:2164 [inline]
 __se_sys_sendmsg net/socket.c:2162 [inline]
 __x64_sys_sendmsg+0x331/0x460 net/socket.c:2162
 do_syscall_64+0x152/0x230 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:279 [inline]
 kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:189
 kmsan_kmalloc+0x94/0x100 mm/kmsan/kmsan.c:315
 kmsan_slab_alloc+0x10/0x20 mm/kmsan/kmsan.c:322
 slab_post_alloc_hook mm/slab.h:446 [inline]
 slab_alloc_node mm/slub.c:2753 [inline]
 __kmalloc_node_track_caller+0xb32/0x11b0 mm/slub.c:4395
 __kmalloc_reserve net/core/skbuff.c:138 [inline]
 __alloc_skb+0x2cb/0x9e0 net/core/skbuff.c:206
 alloc_skb include/linux/skbuff.h:988 [inline]
 netlink_alloc_large_skb net/netlink/af_netlink.c:1182 [inline]
 netlink_sendmsg+0x76e/0x1350 net/netlink/af_netlink.c:1876
 sock_sendmsg_nosec net/socket.c:629 [inline]
 sock_sendmsg net/socket.c:639 [inline]
 ___sys_sendmsg+0xec0/0x1310 net/socket.c:2117
 __sys_sendmsg net/socket.c:2155 [inline]
 __do_sys_sendmsg net/socket.c:2164 [inline]
 __se_sys_sendmsg net/socket.c:2162 [inline]
 __x64_sys_sendmsg+0x331/0x460 net/socket.c:2162
 do_syscall_64+0x152/0x230 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: a919525ad832 ("net: Move fib_convert_metrics to metrics file")
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_semantics.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 7d36a950d961..19f7d8cd4875 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -717,6 +717,8 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi)
 			nla_strlcpy(tmp, nla, sizeof(tmp));
 			val = tcp_ca_get_key_by_name(fi->fib_net, tmp, &ecn_ca);
 		} else {
+			if (nla_len(nla) != sizeof(u32))
+				return false;
 			val = nla_get_u32(nla);
 		}
 
@@ -1043,6 +1045,8 @@ fib_convert_metrics(struct fib_info *fi, const struct fib_config *cfg)
 			if (val == TCP_CA_UNSPEC)
 				return -EINVAL;
 		} else {
+			if (nla_len(nla) != sizeof(u32))
+				return -EINVAL;
 			val = nla_get_u32(nla);
 		}
 		if (type == RTAX_ADVMSS && val > 65535 - 40)
-- 
2.17.1


From 3d1b8e8733fad38627e559a007cd8d49e0df4dc3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 1 Jun 2018 09:23:02 -0700
Subject: [PATCH 19/43] net/packet: refine check for priv area size

[ Upstream commit eb73190f4fbeedf762394e92d6a4ec9ace684c88 ]

syzbot was able to trick af_packet again [1]

Various commits tried to address the problem in the past,
but failed to take into account V3 header size.

[1]

tpacket_rcv: packet too big, clamped from 72 to 4294967224. macoff=96
BUG: KASAN: use-after-free in prb_run_all_ft_ops net/packet/af_packet.c:1016 [inline]
BUG: KASAN: use-after-free in prb_fill_curr_block.isra.59+0x4e5/0x5c0 net/packet/af_packet.c:1039
Write of size 2 at addr ffff8801cb62000e by task kworker/1:2/2106

CPU: 1 PID: 2106 Comm: kworker/1:2 Not tainted 4.17.0-rc7+ #77
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Workqueue: ipv6_addrconf addrconf_dad_work
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1b9/0x294 lib/dump_stack.c:113
 print_address_description+0x6c/0x20b mm/kasan/report.c:256
 kasan_report_error mm/kasan/report.c:354 [inline]
 kasan_report.cold.7+0x242/0x2fe mm/kasan/report.c:412
 __asan_report_store2_noabort+0x17/0x20 mm/kasan/report.c:436
 prb_run_all_ft_ops net/packet/af_packet.c:1016 [inline]
 prb_fill_curr_block.isra.59+0x4e5/0x5c0 net/packet/af_packet.c:1039
 __packet_lookup_frame_in_block net/packet/af_packet.c:1094 [inline]
 packet_current_rx_frame net/packet/af_packet.c:1117 [inline]
 tpacket_rcv+0x1866/0x3340 net/packet/af_packet.c:2282
 dev_queue_xmit_nit+0x891/0xb90 net/core/dev.c:2018
 xmit_one net/core/dev.c:3049 [inline]
 dev_hard_start_xmit+0x16b/0xc10 net/core/dev.c:3069
 __dev_queue_xmit+0x2724/0x34c0 net/core/dev.c:3584
 dev_queue_xmit+0x17/0x20 net/core/dev.c:3617
 neigh_resolve_output+0x679/0xad0 net/core/neighbour.c:1358
 neigh_output include/net/neighbour.h:482 [inline]
 ip6_finish_output2+0xc9c/0x2810 net/ipv6/ip6_output.c:120
 ip6_finish_output+0x5fe/0xbc0 net/ipv6/ip6_output.c:154
 NF_HOOK_COND include/linux/netfilter.h:277 [inline]
 ip6_output+0x227/0x9b0 net/ipv6/ip6_output.c:171
 dst_output include/net/dst.h:444 [inline]
 NF_HOOK include/linux/netfilter.h:288 [inline]
 ndisc_send_skb+0x100d/0x1570 net/ipv6/ndisc.c:491
 ndisc_send_ns+0x3c1/0x8d0 net/ipv6/ndisc.c:633
 addrconf_dad_work+0xbef/0x1340 net/ipv6/addrconf.c:4033
 process_one_work+0xc1e/0x1b50 kernel/workqueue.c:2145
 worker_thread+0x1cc/0x1440 kernel/workqueue.c:2279
 kthread+0x345/0x410 kernel/kthread.c:240
 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:412

The buggy address belongs to the page:
page:ffffea00072d8800 count:0 mapcount:-127 mapping:0000000000000000 index:0xffff8801cb620e80
flags: 0x2fffc0000000000()
raw: 02fffc0000000000 0000000000000000 ffff8801cb620e80 00000000ffffff80
raw: ffffea00072e3820 ffffea0007132d20 0000000000000002 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff8801cb61ff00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
 ffff8801cb61ff80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
>ffff8801cb620000: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
                      ^
 ffff8801cb620080: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
 ffff8801cb620100: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff

Fixes: 2b6867c2ce76 ("net/packet: fix overflow in check for priv area size")
Fixes: dc808110bb62 ("packet: handle too big packets for PACKET_V3")
Fixes: f6fb8f100b80 ("af-packet: TPACKET_V3 flexible buffer implementation.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index c6a2dd890de3..f2ba3b22ba29 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -4284,7 +4284,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 			goto out;
 		if (po->tp_version >= TPACKET_V3 &&
 		    req->tp_block_size <=
-			  BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv))
+		    BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv) + sizeof(struct tpacket3_hdr))
 			goto out;
 		if (unlikely(req->tp_frame_size < po->tp_hdrlen +
 					po->tp_reserve))
-- 
2.17.1


From e46432d710a9029ab09fd4f277ea70412dbd1be5 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 22 May 2018 17:04:49 -0700
Subject: [PATCH 20/43] net: phy: broadcom: Fix bcm_write_exp()

[ Upstream commit 79fb218d97980d4fee9a64f4c8ff05289364ba25 ]

On newer PHYs, we need to select the expansion register to write with
setting bits [11:8] to 0xf. This was done correctly by bcm7xxx.c prior
to being migrated to generic code under bcm-phy-lib.c which
unfortunately used the older implementation from the BCM54xx days.

Fix this by creating an inline stub: bcm_write_exp_sel() which adds the
correct value (MII_BCM54XX_EXP_SEL_ER) and update both the Cygnus PHY
and BCM7xxx PHY drivers which require setting these bits.

broadcom.c is unchanged because some PHYs even use a different selector
method, so let them specify it directly (e.g: SerDes secondary selector).

Fixes: a1cba5613edf ("net: phy: Add Broadcom phy library for common interfaces")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/bcm-cygnus.c  | 6 +++---
 drivers/net/phy/bcm-phy-lib.h | 7 +++++++
 drivers/net/phy/bcm7xxx.c     | 4 ++--
 3 files changed, 12 insertions(+), 5 deletions(-)

diff --git a/drivers/net/phy/bcm-cygnus.c b/drivers/net/phy/bcm-cygnus.c
index 6838129839ca..e757b09f1889 100644
--- a/drivers/net/phy/bcm-cygnus.c
+++ b/drivers/net/phy/bcm-cygnus.c
@@ -61,17 +61,17 @@ static int bcm_cygnus_afe_config(struct phy_device *phydev)
 		return rc;
 
 	/* make rcal=100, since rdb default is 000 */
-	rc = bcm_phy_write_exp(phydev, MII_BRCM_CORE_EXPB1, 0x10);
+	rc = bcm_phy_write_exp_sel(phydev, MII_BRCM_CORE_EXPB1, 0x10);
 	if (rc < 0)
 		return rc;
 
 	/* CORE_EXPB0, Reset R_CAL/RC_CAL Engine */
-	rc = bcm_phy_write_exp(phydev, MII_BRCM_CORE_EXPB0, 0x10);
+	rc = bcm_phy_write_exp_sel(phydev, MII_BRCM_CORE_EXPB0, 0x10);
 	if (rc < 0)
 		return rc;
 
 	/* CORE_EXPB0, Disable Reset R_CAL/RC_CAL Engine */
-	rc = bcm_phy_write_exp(phydev, MII_BRCM_CORE_EXPB0, 0x00);
+	rc = bcm_phy_write_exp_sel(phydev, MII_BRCM_CORE_EXPB0, 0x00);
 
 	return 0;
 }
diff --git a/drivers/net/phy/bcm-phy-lib.h b/drivers/net/phy/bcm-phy-lib.h
index 7c73808cbbde..81cceaa412fe 100644
--- a/drivers/net/phy/bcm-phy-lib.h
+++ b/drivers/net/phy/bcm-phy-lib.h
@@ -14,11 +14,18 @@
 #ifndef _LINUX_BCM_PHY_LIB_H
 #define _LINUX_BCM_PHY_LIB_H
 
+#include <linux/brcmphy.h>
 #include <linux/phy.h>
 
 int bcm_phy_write_exp(struct phy_device *phydev, u16 reg, u16 val);
 int bcm_phy_read_exp(struct phy_device *phydev, u16 reg);
 
+static inline int bcm_phy_write_exp_sel(struct phy_device *phydev,
+					u16 reg, u16 val)
+{
+	return bcm_phy_write_exp(phydev, reg | MII_BCM54XX_EXP_SEL_ER, val);
+}
+
 int bcm54xx_auxctl_write(struct phy_device *phydev, u16 regnum, u16 val);
 int bcm54xx_auxctl_read(struct phy_device *phydev, u16 regnum);
 
diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c
index 421feb8f92fe..90eb3e12a4f8 100644
--- a/drivers/net/phy/bcm7xxx.c
+++ b/drivers/net/phy/bcm7xxx.c
@@ -65,10 +65,10 @@ struct bcm7xxx_phy_priv {
 static void r_rc_cal_reset(struct phy_device *phydev)
 {
 	/* Reset R_CAL/RC_CAL Engine */
-	bcm_phy_write_exp(phydev, 0x00b0, 0x0010);
+	bcm_phy_write_exp_sel(phydev, 0x00b0, 0x0010);
 
 	/* Disable Reset R_AL/RC_CAL Engine */
-	bcm_phy_write_exp(phydev, 0x00b0, 0x0000);
+	bcm_phy_write_exp_sel(phydev, 0x00b0, 0x0000);
 }
 
 static int bcm7xxx_28nm_b0_afe_config_init(struct phy_device *phydev)
-- 
2.17.1


From c41e8f39df8c91a1c36adc5c15b3b4b3c4642d2e Mon Sep 17 00:00:00 2001
From: Daniele Palmas <dnlplm@gmail.com>
Date: Thu, 31 May 2018 11:18:29 +0200
Subject: [PATCH 21/43] net: usb: cdc_mbim: add flag FLAG_SEND_ZLP
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 9f7c728332e8966084242fcd951aa46583bc308c ]

Testing Telit LM940 with ICMP packets > 14552 bytes revealed that
the modem needs FLAG_SEND_ZLP to properly work, otherwise the cdc
mbim data interface won't be anymore responsive.

Signed-off-by: Daniele Palmas <dnlplm@gmail.com>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_mbim.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c
index 7220cd620717..0362acd5cdca 100644
--- a/drivers/net/usb/cdc_mbim.c
+++ b/drivers/net/usb/cdc_mbim.c
@@ -609,7 +609,7 @@ static const struct driver_info cdc_mbim_info_ndp_to_end = {
  */
 static const struct driver_info cdc_mbim_info_avoid_altsetting_toggle = {
 	.description = "CDC MBIM",
-	.flags = FLAG_NO_SETINT | FLAG_MULTI_PACKET | FLAG_WWAN,
+	.flags = FLAG_NO_SETINT | FLAG_MULTI_PACKET | FLAG_WWAN | FLAG_SEND_ZLP,
 	.bind = cdc_mbim_bind,
 	.unbind = cdc_mbim_unbind,
 	.manage_power = cdc_mbim_manage_power,
-- 
2.17.1


From e37c309189c1238c481a03ca4ef56e84303b2306 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Thu, 24 May 2018 18:10:30 -0400
Subject: [PATCH 22/43] packet: fix reserve calculation

[ Upstream commit 9aad13b087ab0a588cd68259de618f100053360e ]

Commit b84bbaf7a6c8 ("packet: in packet_snd start writing at link
layer allocation") ensures that packet_snd always starts writing
the link layer header in reserved headroom allocated for this
purpose.

This is needed because packets may be shorter than hard_header_len,
in which case the space up to hard_header_len may be zeroed. But
that necessary padding is not accounted for in skb->len.

The fix, however, is buggy. It calls skb_push, which grows skb->len
when moving skb->data back. But in this case packet length should not
change.

Instead, call skb_reserve, which moves both skb->data and skb->tail
back, without changing length.

Fixes: b84bbaf7a6c8 ("packet: in packet_snd start writing at link layer allocation")
Reported-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index f2ba3b22ba29..c9432a0ccd56 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2911,7 +2911,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		if (unlikely(offset < 0))
 			goto out_free;
 	} else if (reserve) {
-		skb_push(skb, reserve);
+		skb_reserve(skb, -reserve);
 	}
 
 	/* Returns -EFAULT on error */
-- 
2.17.1


From 126297a7825c8aa54146f4307562184b16fb9041 Mon Sep 17 00:00:00 2001
From: Shahed Shaikh <shahed.shaikh@cavium.com>
Date: Mon, 21 May 2018 12:31:47 -0700
Subject: [PATCH 23/43] qed: Fix mask for physical address in ILT entry

[ Upstream commit fdd13dd350dda1826579eb5c333d76b14513b812 ]

ILT entry requires 12 bit right shifted physical address.
Existing mask for ILT entry of physical address i.e.
ILT_ENTRY_PHY_ADDR_MASK is not sufficient to handle 64bit
address because upper 8 bits of 64 bit address were getting
masked which resulted in completer abort error on
PCIe bus due to invalid address.

Fix that mask to handle 64bit physical address.

Fixes: fe56b9e6a8d9 ("qed: Add module with basic common support")
Signed-off-by: Shahed Shaikh <shahed.shaikh@cavium.com>
Signed-off-by: Ariel Elior <ariel.elior@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_cxt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
index 00f41c145d4d..820b226d6ff8 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
@@ -77,7 +77,7 @@
 #define ILT_CFG_REG(cli, reg)	PSWRQ2_REG_ ## cli ## _ ## reg ## _RT_OFFSET
 
 /* ILT entry structure */
-#define ILT_ENTRY_PHY_ADDR_MASK		0x000FFFFFFFFFFFULL
+#define ILT_ENTRY_PHY_ADDR_MASK		(~0ULL >> 12)
 #define ILT_ENTRY_PHY_ADDR_SHIFT	0
 #define ILT_ENTRY_VALID_MASK		0x1ULL
 #define ILT_ENTRY_VALID_SHIFT		52
-- 
2.17.1


From 9ab6db6f05233aa7fc820f8516465a1f24f9488b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 5 Jun 2018 09:25:19 -0700
Subject: [PATCH 24/43] rtnetlink: validate attributes in do_setlink()

[ Upstream commit 644c7eebbfd59e72982d11ec6cc7d39af12450ae ]

It seems that rtnl_group_changelink() can call do_setlink
while a prior call to validate_linkmsg(dev = NULL, ...) could
not validate IFLA_ADDRESS / IFLA_BROADCAST

Make sure do_setlink() calls validate_linkmsg() instead
of letting its callers having this responsibility.

With help from Dmitry Vyukov, thanks a lot !

BUG: KMSAN: uninit-value in is_valid_ether_addr include/linux/etherdevice.h:199 [inline]
BUG: KMSAN: uninit-value in eth_prepare_mac_addr_change net/ethernet/eth.c:275 [inline]
BUG: KMSAN: uninit-value in eth_mac_addr+0x203/0x2b0 net/ethernet/eth.c:308
CPU: 1 PID: 8695 Comm: syz-executor3 Not tainted 4.17.0-rc5+ #103
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x185/0x1d0 lib/dump_stack.c:113
 kmsan_report+0x149/0x260 mm/kmsan/kmsan.c:1084
 __msan_warning_32+0x6e/0xc0 mm/kmsan/kmsan_instr.c:686
 is_valid_ether_addr include/linux/etherdevice.h:199 [inline]
 eth_prepare_mac_addr_change net/ethernet/eth.c:275 [inline]
 eth_mac_addr+0x203/0x2b0 net/ethernet/eth.c:308
 dev_set_mac_address+0x261/0x530 net/core/dev.c:7157
 do_setlink+0xbc3/0x5fc0 net/core/rtnetlink.c:2317
 rtnl_group_changelink net/core/rtnetlink.c:2824 [inline]
 rtnl_newlink+0x1fe9/0x37a0 net/core/rtnetlink.c:2976
 rtnetlink_rcv_msg+0xa32/0x1560 net/core/rtnetlink.c:4646
 netlink_rcv_skb+0x378/0x600 net/netlink/af_netlink.c:2448
 rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:4664
 netlink_unicast_kernel net/netlink/af_netlink.c:1310 [inline]
 netlink_unicast+0x1678/0x1750 net/netlink/af_netlink.c:1336
 netlink_sendmsg+0x104f/0x1350 net/netlink/af_netlink.c:1901
 sock_sendmsg_nosec net/socket.c:629 [inline]
 sock_sendmsg net/socket.c:639 [inline]
 ___sys_sendmsg+0xec0/0x1310 net/socket.c:2117
 __sys_sendmsg net/socket.c:2155 [inline]
 __do_sys_sendmsg net/socket.c:2164 [inline]
 __se_sys_sendmsg net/socket.c:2162 [inline]
 __x64_sys_sendmsg+0x331/0x460 net/socket.c:2162
 do_syscall_64+0x152/0x230 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x455a09
RSP: 002b:00007fc07480ec68 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 00007fc07480f6d4 RCX: 0000000000455a09
RDX: 0000000000000000 RSI: 00000000200003c0 RDI: 0000000000000014
RBP: 000000000072bea0 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff
R13: 00000000000005d0 R14: 00000000006fdc20 R15: 0000000000000000

Uninit was stored to memory at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:279 [inline]
 kmsan_save_stack mm/kmsan/kmsan.c:294 [inline]
 kmsan_internal_chain_origin+0x12b/0x210 mm/kmsan/kmsan.c:685
 kmsan_memcpy_origins+0x11d/0x170 mm/kmsan/kmsan.c:527
 __msan_memcpy+0x109/0x160 mm/kmsan/kmsan_instr.c:478
 do_setlink+0xb84/0x5fc0 net/core/rtnetlink.c:2315
 rtnl_group_changelink net/core/rtnetlink.c:2824 [inline]
 rtnl_newlink+0x1fe9/0x37a0 net/core/rtnetlink.c:2976
 rtnetlink_rcv_msg+0xa32/0x1560 net/core/rtnetlink.c:4646
 netlink_rcv_skb+0x378/0x600 net/netlink/af_netlink.c:2448
 rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:4664
 netlink_unicast_kernel net/netlink/af_netlink.c:1310 [inline]
 netlink_unicast+0x1678/0x1750 net/netlink/af_netlink.c:1336
 netlink_sendmsg+0x104f/0x1350 net/netlink/af_netlink.c:1901
 sock_sendmsg_nosec net/socket.c:629 [inline]
 sock_sendmsg net/socket.c:639 [inline]
 ___sys_sendmsg+0xec0/0x1310 net/socket.c:2117
 __sys_sendmsg net/socket.c:2155 [inline]
 __do_sys_sendmsg net/socket.c:2164 [inline]
 __se_sys_sendmsg net/socket.c:2162 [inline]
 __x64_sys_sendmsg+0x331/0x460 net/socket.c:2162
 do_syscall_64+0x152/0x230 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:279 [inline]
 kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:189
 kmsan_kmalloc+0x94/0x100 mm/kmsan/kmsan.c:315
 kmsan_slab_alloc+0x10/0x20 mm/kmsan/kmsan.c:322
 slab_post_alloc_hook mm/slab.h:446 [inline]
 slab_alloc_node mm/slub.c:2753 [inline]
 __kmalloc_node_track_caller+0xb32/0x11b0 mm/slub.c:4395
 __kmalloc_reserve net/core/skbuff.c:138 [inline]
 __alloc_skb+0x2cb/0x9e0 net/core/skbuff.c:206
 alloc_skb include/linux/skbuff.h:988 [inline]
 netlink_alloc_large_skb net/netlink/af_netlink.c:1182 [inline]
 netlink_sendmsg+0x76e/0x1350 net/netlink/af_netlink.c:1876
 sock_sendmsg_nosec net/socket.c:629 [inline]
 sock_sendmsg net/socket.c:639 [inline]
 ___sys_sendmsg+0xec0/0x1310 net/socket.c:2117
 __sys_sendmsg net/socket.c:2155 [inline]
 __do_sys_sendmsg net/socket.c:2164 [inline]
 __se_sys_sendmsg net/socket.c:2162 [inline]
 __x64_sys_sendmsg+0x331/0x460 net/socket.c:2162
 do_syscall_64+0x152/0x230 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: e7ed828f10bd ("netlink: support setting devgroup parameters")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index bc290413a49d..824b32936e75 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2245,6 +2245,10 @@ static int do_setlink(const struct sk_buff *skb,
 	const struct net_device_ops *ops = dev->netdev_ops;
 	int err;
 
+	err = validate_linkmsg(dev, tb);
+	if (err < 0)
+		return err;
+
 	if (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD] || tb[IFLA_IF_NETNSID]) {
 		struct net *net = rtnl_link_get_net_capable(skb, dev_net(dev),
 							    tb, CAP_NET_ADMIN);
@@ -2608,10 +2612,6 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 		goto errout;
 	}
 
-	err = validate_linkmsg(dev, tb);
-	if (err < 0)
-		goto errout;
-
 	err = do_setlink(skb, dev, ifm, extack, tb, ifname, 0);
 errout:
 	return err;
-- 
2.17.1


From cf1c6a28c63cfdade085bda33cd2fae15f1de906 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 5 Jun 2018 12:16:58 +0800
Subject: [PATCH 25/43] sctp: not allow transport timeout value less than HZ/5
 for hb_timer

[ Upstream commit 1d88ba1ebb2763aa86172cd7ca05dedbeccc0d35 ]

syzbot reported a rcu_sched self-detected stall on CPU which is caused
by too small value set on rto_min with SCTP_RTOINFO sockopt. With this
value, hb_timer will get stuck there, as in its timer handler it starts
this timer again with this value, then goes to the timer handler again.

This problem is there since very beginning, and thanks to Eric for the
reproducer shared from a syzbot mail.

This patch fixes it by not allowing sctp_transport_timeout to return a
smaller value than HZ/5 for hb_timer, which is based on TCP's min rto.

Note that it doesn't fix this issue by limiting rto_min, as some users
are still using small rto and no proper value was found for it yet.

Reported-by: syzbot+3dcd59a1f907245f891f@syzkaller.appspotmail.com
Suggested-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/transport.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index 47f82bd794d9..03fc2c427aca 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -634,7 +634,7 @@ unsigned long sctp_transport_timeout(struct sctp_transport *trans)
 	    trans->state != SCTP_PF)
 		timeout += trans->hbinterval;
 
-	return timeout;
+	return max_t(unsigned long, timeout, HZ / 5);
 }
 
 /* Reset transport variables to their initial values */
-- 
2.17.1


From 0b71d91ad36888b412b7fd0a2f8684ddaaee2ebd Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Mon, 4 Jun 2018 17:46:01 +0300
Subject: [PATCH 26/43] team: use netdev_features_t instead of u32

[ Upstream commit 25ea66544bfd1d9df1b7e1502f8717e85fa1e6e6 ]

This code was introduced in 2011 around the same time that we made
netdev_features_t a u64 type.  These days a u32 is not big enough to
hold all the potential features.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 3175f7410baf..8f3863cd0094 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1004,7 +1004,8 @@ static void team_port_disable(struct team *team,
 static void __team_compute_features(struct team *team)
 {
 	struct team_port *port;
-	u32 vlan_features = TEAM_VLAN_FEATURES & NETIF_F_ALL_FOR_ALL;
+	netdev_features_t vlan_features = TEAM_VLAN_FEATURES &
+					  NETIF_F_ALL_FOR_ALL;
 	netdev_features_t enc_features  = TEAM_ENC_FEATURES;
 	unsigned short max_hard_header_len = ETH_HLEN;
 	unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE |
-- 
2.17.1


From 4948e7338041986eb337b00204e455748941382d Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Tue, 22 May 2018 19:58:57 +0800
Subject: [PATCH 27/43] vhost: synchronize IOTLB message with dev cleanup

[ Upstream commit 1b15ad683ab42a203f98b67045b40720e99d0e9a ]

DaeRyong Jeong reports a race between vhost_dev_cleanup() and
vhost_process_iotlb_msg():

Thread interleaving:
CPU0 (vhost_process_iotlb_msg)			CPU1 (vhost_dev_cleanup)
(In the case of both VHOST_IOTLB_UPDATE and
VHOST_IOTLB_INVALIDATE)

=====						=====
						vhost_umem_clean(dev->iotlb);
if (!dev->iotlb) {
	        ret = -EFAULT;
		        break;
}
						dev->iotlb = NULL;

The reason is we don't synchronize between them, fixing by protecting
vhost_process_iotlb_msg() with dev mutex.

Reported-by: DaeRyong Jeong <threeearcat@gmail.com>
Fixes: 6b1e6cc7855b0 ("vhost: new device IOTLB API")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/vhost.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index be6a4b6a76c6..68242f50c303 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -981,6 +981,7 @@ static int vhost_process_iotlb_msg(struct vhost_dev *dev,
 {
 	int ret = 0;
 
+	mutex_lock(&dev->mutex);
 	vhost_dev_lock_vqs(dev);
 	switch (msg->type) {
 	case VHOST_IOTLB_UPDATE:
@@ -1016,6 +1017,8 @@ static int vhost_process_iotlb_msg(struct vhost_dev *dev,
 	}
 
 	vhost_dev_unlock_vqs(dev);
+	mutex_unlock(&dev->mutex);
+
 	return ret;
 }
 ssize_t vhost_chr_write_iter(struct vhost_dev *dev,
-- 
2.17.1


From c93597877fdf226e0c2671effca3f267f77fc980 Mon Sep 17 00:00:00 2001
From: Stephen Suryaputra <ssuryaextr@gmail.com>
Date: Fri, 1 Jun 2018 00:05:21 -0400
Subject: [PATCH 28/43] vrf: check the original netdevice for generating
 redirect

[ Upstream commit 2f17becfbea5e9a0529b51da7345783e96e69516 ]

Use the right device to determine if redirect should be sent especially
when using vrf. Same as well as when sending the redirect.

Signed-off-by: Stephen Suryaputra <ssuryaextr@gmail.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_output.c | 3 ++-
 net/ipv6/ndisc.c      | 6 ++++++
 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 072333760a52..f39ea066977d 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -507,7 +507,8 @@ int ip6_forward(struct sk_buff *skb)
 	   send redirects to source routed frames.
 	   We don't send redirects to frames decapsulated from IPsec.
 	 */
-	if (skb->dev == dst->dev && opt->srcrt == 0 && !skb_sec_path(skb)) {
+	if (IP6CB(skb)->iif == dst->dev->ifindex &&
+	    opt->srcrt == 0 && !skb_sec_path(skb)) {
 		struct in6_addr *target = NULL;
 		struct inet_peer *peer;
 		struct rt6_info *rt;
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index ba5e04c6ae17..65956d0f8a1f 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1576,6 +1576,12 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
 	   ops_data_buf[NDISC_OPS_REDIRECT_DATA_SPACE], *ops_data = NULL;
 	bool ret;
 
+	if (netif_is_l3_master(skb->dev)) {
+		dev = __dev_get_by_index(dev_net(skb->dev), IPCB(skb)->iif);
+		if (!dev)
+			return;
+	}
+
 	if (ipv6_get_lladdr(dev, &saddr_buf, IFA_F_TENTATIVE)) {
 		ND_PRINTK(2, warn, "Redirect: no link-local address on %s\n",
 			  dev->name);
-- 
2.17.1


From cd92bfe17ce756cf34e02264d7de29da63dec20b Mon Sep 17 00:00:00 2001
From: Mathieu Xhonneux <m.xhonneux@gmail.com>
Date: Fri, 25 May 2018 13:29:41 +0100
Subject: [PATCH 29/43] ipv6: sr: fix memory OOB access in
 seg6_do_srh_encap/inline

[ Upstream commit bbb40a0b75209734ff9286f3326171638c9f6569 ]

seg6_do_srh_encap and seg6_do_srh_inline can possibly do an
out-of-bounds access when adding the SRH to the packet. This no longer
happen when expanding the skb not only by the size of the SRH (+
outer IPv6 header), but also by skb->mac_len.

[   53.793056] BUG: KASAN: use-after-free in seg6_do_srh_encap+0x284/0x620
[   53.794564] Write of size 14 at addr ffff88011975ecfa by task ping/674

[   53.796665] CPU: 0 PID: 674 Comm: ping Not tainted 4.17.0-rc3-ARCH+ #90
[   53.796670] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996),
BIOS 1.11.0-20171110_100015-anatol 04/01/2014
[   53.796673] Call Trace:
[   53.796679]  <IRQ>
[   53.796689]  dump_stack+0x71/0xab
[   53.796700]  print_address_description+0x6a/0x270
[   53.796707]  kasan_report+0x258/0x380
[   53.796715]  ? seg6_do_srh_encap+0x284/0x620
[   53.796722]  memmove+0x34/0x50
[   53.796730]  seg6_do_srh_encap+0x284/0x620
[   53.796741]  ? seg6_do_srh+0x29b/0x360
[   53.796747]  seg6_do_srh+0x29b/0x360
[   53.796756]  seg6_input+0x2e/0x2e0
[   53.796765]  lwtunnel_input+0x93/0xd0
[   53.796774]  ipv6_rcv+0x690/0x920
[   53.796783]  ? ip6_input+0x170/0x170
[   53.796791]  ? eth_gro_receive+0x2d0/0x2d0
[   53.796800]  ? ip6_input+0x170/0x170
[   53.796809]  __netif_receive_skb_core+0xcc0/0x13f0
[   53.796820]  ? netdev_info+0x110/0x110
[   53.796827]  ? napi_complete_done+0xb6/0x170
[   53.796834]  ? e1000_clean+0x6da/0xf70
[   53.796845]  ? process_backlog+0x129/0x2a0
[   53.796853]  process_backlog+0x129/0x2a0
[   53.796862]  net_rx_action+0x211/0x5c0
[   53.796870]  ? napi_complete_done+0x170/0x170
[   53.796887]  ? run_rebalance_domains+0x11f/0x150
[   53.796891]  __do_softirq+0x10e/0x39e
[   53.796894]  do_softirq_own_stack+0x2a/0x40
[   53.796895]  </IRQ>
[   53.796898]  do_softirq.part.16+0x54/0x60
[   53.796900]  __local_bh_enable_ip+0x5b/0x60
[   53.796903]  ip6_finish_output2+0x416/0x9f0
[   53.796906]  ? ip6_dst_lookup_flow+0x110/0x110
[   53.796909]  ? ip6_sk_dst_lookup_flow+0x390/0x390
[   53.796911]  ? __rcu_read_unlock+0x66/0x80
[   53.796913]  ? ip6_mtu+0x44/0xf0
[   53.796916]  ? ip6_output+0xfc/0x220
[   53.796918]  ip6_output+0xfc/0x220
[   53.796921]  ? ip6_finish_output+0x2b0/0x2b0
[   53.796923]  ? memcpy+0x34/0x50
[   53.796926]  ip6_send_skb+0x43/0xc0
[   53.796929]  rawv6_sendmsg+0x1216/0x1530
[   53.796932]  ? __orc_find+0x6b/0xc0
[   53.796934]  ? rawv6_rcv_skb+0x160/0x160
[   53.796937]  ? __rcu_read_unlock+0x66/0x80
[   53.796939]  ? __rcu_read_unlock+0x66/0x80
[   53.796942]  ? is_bpf_text_address+0x1e/0x30
[   53.796944]  ? kernel_text_address+0xec/0x100
[   53.796946]  ? __kernel_text_address+0xe/0x30
[   53.796948]  ? unwind_get_return_address+0x2f/0x50
[   53.796950]  ? __save_stack_trace+0x92/0x100
[   53.796954]  ? save_stack+0x89/0xb0
[   53.796956]  ? kasan_kmalloc+0xa0/0xd0
[   53.796958]  ? kmem_cache_alloc+0xd2/0x1f0
[   53.796961]  ? prepare_creds+0x23/0x160
[   53.796963]  ? __x64_sys_capset+0x252/0x3e0
[   53.796966]  ? do_syscall_64+0x69/0x160
[   53.796968]  ? entry_SYSCALL_64_after_hwframe+0x44/0xa9
[   53.796971]  ? __alloc_pages_nodemask+0x170/0x380
[   53.796973]  ? __alloc_pages_slowpath+0x12c0/0x12c0
[   53.796977]  ? tty_vhangup+0x20/0x20
[   53.796979]  ? policy_nodemask+0x1a/0x90
[   53.796982]  ? __mod_node_page_state+0x8d/0xa0
[   53.796986]  ? __check_object_size+0xe7/0x240
[   53.796989]  ? __sys_sendto+0x229/0x290
[   53.796991]  ? rawv6_rcv_skb+0x160/0x160
[   53.796993]  __sys_sendto+0x229/0x290
[   53.796996]  ? __ia32_sys_getpeername+0x50/0x50
[   53.796999]  ? commit_creds+0x2de/0x520
[   53.797002]  ? security_capset+0x57/0x70
[   53.797004]  ? __x64_sys_capset+0x29f/0x3e0
[   53.797007]  ? __x64_sys_rt_sigsuspend+0xe0/0xe0
[   53.797011]  ? __do_page_fault+0x664/0x770
[   53.797014]  __x64_sys_sendto+0x74/0x90
[   53.797017]  do_syscall_64+0x69/0x160
[   53.797019]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[   53.797022] RIP: 0033:0x7f43b7a6714a
[   53.797023] RSP: 002b:00007ffd891bd368 EFLAGS: 00000246 ORIG_RAX:
000000000000002c
[   53.797026] RAX: ffffffffffffffda RBX: 00000000006129c0 RCX: 00007f43b7a6714a
[   53.797028] RDX: 0000000000000040 RSI: 00000000006129c0 RDI: 0000000000000004
[   53.797029] RBP: 00007ffd891be640 R08: 0000000000610940 R09: 000000000000001c
[   53.797030] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000040
[   53.797032] R13: 000000000060e6a0 R14: 0000000000008004 R15: 000000000040b661

[   53.797171] Allocated by task 642:
[   53.797460]  kasan_kmalloc+0xa0/0xd0
[   53.797463]  kmem_cache_alloc+0xd2/0x1f0
[   53.797465]  getname_flags+0x40/0x210
[   53.797467]  user_path_at_empty+0x1d/0x40
[   53.797469]  do_faccessat+0x12a/0x320
[   53.797471]  do_syscall_64+0x69/0x160
[   53.797473]  entry_SYSCALL_64_after_hwframe+0x44/0xa9

[   53.797607] Freed by task 642:
[   53.797869]  __kasan_slab_free+0x130/0x180
[   53.797871]  kmem_cache_free+0xa8/0x230
[   53.797872]  filename_lookup+0x15b/0x230
[   53.797874]  do_faccessat+0x12a/0x320
[   53.797876]  do_syscall_64+0x69/0x160
[   53.797878]  entry_SYSCALL_64_after_hwframe+0x44/0xa9

[   53.798014] The buggy address belongs to the object at ffff88011975e600
                which belongs to the cache names_cache of size 4096
[   53.799043] The buggy address is located 1786 bytes inside of
                4096-byte region [ffff88011975e600, ffff88011975f600)
[   53.800013] The buggy address belongs to the page:
[   53.800414] page:ffffea000465d600 count:1 mapcount:0
mapping:0000000000000000 index:0x0 compound_mapcount: 0
[   53.801259] flags: 0x17fff0000008100(slab|head)
[   53.801640] raw: 017fff0000008100 0000000000000000 0000000000000000
0000000100070007
[   53.803147] raw: dead000000000100 dead000000000200 ffff88011b185a40
0000000000000000
[   53.803787] page dumped because: kasan: bad access detected

[   53.804384] Memory state around the buggy address:
[   53.804788]  ffff88011975eb80: fb fb fb fb fb fb fb fb fb fb fb fb
fb fb fb fb
[   53.805384]  ffff88011975ec00: fb fb fb fb fb fb fb fb fb fb fb fb
fb fb fb fb
[   53.805979] >ffff88011975ec80: fb fb fb fb fb fb fb fb fb fb fb fb
fb fb fb fb
[   53.806577]                                                                 ^
[   53.807165]  ffff88011975ed00: fb fb fb fb fb fb fb fb fb fb fb fb
fb fb fb fb
[   53.807762]  ffff88011975ed80: fb fb fb fb fb fb fb fb fb fb fb fb
fb fb fb fb
[   53.808356] ==================================================================
[   53.808949] Disabling lock debugging due to kernel taint

Fixes: 6c8702c60b88 ("ipv6: sr: add support for SRH encapsulation and injection with lwtunnels")
Signed-off-by: David Lebrun <dlebrun@google.com>
Signed-off-by: Mathieu Xhonneux <m.xhonneux@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/seg6_iptunnel.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 5fe139484919..bf4763fd68c2 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -103,7 +103,7 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
 	hdrlen = (osrh->hdrlen + 1) << 3;
 	tot_len = hdrlen + sizeof(*hdr);
 
-	err = skb_cow_head(skb, tot_len);
+	err = skb_cow_head(skb, tot_len + skb->mac_len);
 	if (unlikely(err))
 		return err;
 
@@ -161,7 +161,7 @@ int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
 
 	hdrlen = (osrh->hdrlen + 1) << 3;
 
-	err = skb_cow_head(skb, hdrlen);
+	err = skb_cow_head(skb, hdrlen + skb->mac_len);
 	if (unlikely(err))
 		return err;
 
-- 
2.17.1


From 34bebee804381f722d1de31e637c94019c9d76d5 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 22 May 2018 16:22:26 -0700
Subject: [PATCH 30/43] net: phy: broadcom: Fix auxiliary control register
 reads

[ Upstream commit 733a969a7ed14fc5786bcc59c1bdda83c7ddb46e ]

We are currently doing auxiliary control register reads with the shadow
register value 0b111 (0x7) which incidentally is also the selector value
that should be present in bits [2:0]. Fix this by using the appropriate
selector mask which is defined (MII_BCM54XX_AUXCTL_SHDWSEL_MASK).

This does not have a functional impact yet because we always access the
MII_BCM54XX_AUXCTL_SHDWSEL_MISC (0x7) register in the current code.
This might change at some point though.

Fixes: 5b4e29005123 ("net: phy: broadcom: add bcm54xx_auxctl_read")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/bcm-phy-lib.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/bcm-phy-lib.c b/drivers/net/phy/bcm-phy-lib.c
index 5ad130c3da43..d5e0833d69b9 100644
--- a/drivers/net/phy/bcm-phy-lib.c
+++ b/drivers/net/phy/bcm-phy-lib.c
@@ -56,7 +56,7 @@ int bcm54xx_auxctl_read(struct phy_device *phydev, u16 regnum)
 	/* The register must be written to both the Shadow Register Select and
 	 * the Shadow Read Register Selector
 	 */
-	phy_write(phydev, MII_BCM54XX_AUX_CTL, regnum |
+	phy_write(phydev, MII_BCM54XX_AUX_CTL, MII_BCM54XX_AUXCTL_SHDWSEL_MASK |
 		  regnum << MII_BCM54XX_AUXCTL_SHDWSEL_READ_SHIFT);
 	return phy_read(phydev, MII_BCM54XX_AUX_CTL);
 }
-- 
2.17.1


From 1ef6aa81b2aae26619a17bd8ae738d02979d1071 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Thu, 31 May 2018 15:59:46 -0400
Subject: [PATCH 31/43] net-sysfs: Fix memory leak in XPS configuration

[ Upstream commit 664088f8d68178809b848ca450f2797efb34e8e7 ]

This patch reorders the error cases in showing the XPS configuration so
that we hold off on memory allocation until after we have verified that we
can support XPS on a given ring.

Fixes: 184c449f91fe ("net: Add support for XPS with QoS via traffic classes")
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/net-sysfs.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 60a5ad2c33ee..82690745f94a 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1214,9 +1214,6 @@ static ssize_t xps_cpus_show(struct netdev_queue *queue,
 	cpumask_var_t mask;
 	unsigned long index;
 
-	if (!zalloc_cpumask_var(&mask, GFP_KERNEL))
-		return -ENOMEM;
-
 	index = get_netdev_queue_index(queue);
 
 	if (dev->num_tc) {
@@ -1226,6 +1223,9 @@ static ssize_t xps_cpus_show(struct netdev_queue *queue,
 			return -EINVAL;
 	}
 
+	if (!zalloc_cpumask_var(&mask, GFP_KERNEL))
+		return -ENOMEM;
+
 	rcu_read_lock();
 	dev_maps = rcu_dereference(dev->xps_maps);
 	if (dev_maps) {
-- 
2.17.1


From f1b46d942fa3c90ecc73f58fb3ca85afb5a80790 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Tue, 22 May 2018 11:44:29 +0800
Subject: [PATCH 32/43] virtio-net: correctly transmit XDP buff after
 linearizing

[ Upstream commit 5d458a13dd59d04b4d6658a6d5b94d42732b15ae ]

We should not go for the error path after successfully transmitting a
XDP buffer after linearizing. Since the error path may try to pop and
drop next packet and increase the drop counters. Fixing this by simply
drop the refcnt of original page and go for xmit path.

Fixes: 72979a6c3590 ("virtio_net: xdp, add slowpath case for non contiguous buffers")
Cc: John Fastabend <john.fastabend@gmail.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 16b0c7db431b..8db684c70162 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -775,7 +775,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 			}
 			*xdp_xmit = true;
 			if (unlikely(xdp_page != page))
-				goto err_xdp;
+				put_page(page);
 			rcu_read_unlock();
 			goto xdp_xmit;
 		case XDP_REDIRECT:
-- 
2.17.1


From b2dc992f364f147a7d4daa1e2f1ee320efc78265 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Tue, 22 May 2018 11:44:31 +0800
Subject: [PATCH 33/43] virtio-net: fix leaking page for gso packet during
 mergeable XDP

[ Upstream commit 3d62b2a0db505bbf9ed0755f254e45d775f9807f ]

We need to drop refcnt to xdp_page if we see a gso packet. Otherwise
it will be leaked. Fixing this by moving the check of gso packet above
the linearizing logic. While at it, remove useless comment as well.

Cc: John Fastabend <john.fastabend@gmail.com>
Fixes: 72979a6c3590 ("virtio_net: xdp, add slowpath case for non contiguous buffers")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 8db684c70162..62f2bee34a4b 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -707,6 +707,13 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 		void *data;
 		u32 act;
 
+		/* Transient failure which in theory could occur if
+		 * in-flight packets from before XDP was enabled reach
+		 * the receive path after XDP is loaded.
+		 */
+		if (unlikely(hdr->hdr.gso_type))
+			goto err_xdp;
+
 		/* This happens when rx buffer size is underestimated
 		 * or headroom is not enough because of the buffer
 		 * was refilled before XDP is set. This should only
@@ -727,14 +734,6 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 			xdp_page = page;
 		}
 
-		/* Transient failure which in theory could occur if
-		 * in-flight packets from before XDP was enabled reach
-		 * the receive path after XDP is loaded. In practice I
-		 * was not able to create this condition.
-		 */
-		if (unlikely(hdr->hdr.gso_type))
-			goto err_xdp;
-
 		/* Allow consuming headroom but reserve enough space to push
 		 * the descriptor on if we get an XDP_TX return code.
 		 */
-- 
2.17.1


From 4c6a5a6cdd4a4d88a4c24ec9b9b34103f1620334 Mon Sep 17 00:00:00 2001
From: Jack Morgenstein <jackm@dev.mellanox.co.il>
Date: Wed, 23 May 2018 10:41:59 +0300
Subject: [PATCH 34/43] net/mlx4: Fix irq-unsafe spinlock usage

[ Upstream commit d546b67cda015fb92bfee93d5dc0ceadb91deaee ]

spin_lock/unlock was used instead of spin_un/lock_irq
in a procedure used in process space, on a spinlock
which can be grabbed in an interrupt.

This caused the stack trace below to be displayed (on kernel
4.17.0-rc1 compiled with Lock Debugging enabled):

[  154.661474] WARNING: SOFTIRQ-safe -> SOFTIRQ-unsafe lock order detected
[  154.668909] 4.17.0-rc1-rdma_rc_mlx+ #3 Tainted: G          I
[  154.675856] -----------------------------------------------------
[  154.682706] modprobe/10159 [HC0[0]:SC0[0]:HE0:SE1] is trying to acquire:
[  154.690254] 00000000f3b0e495 (&(&qp_table->lock)->rlock){+.+.}, at: mlx4_qp_remove+0x20/0x50 [mlx4_core]
[  154.700927]
and this task is already holding:
[  154.707461] 0000000094373b5d (&(&cq->lock)->rlock/1){....}, at: destroy_qp_common+0x111/0x560 [mlx4_ib]
[  154.718028] which would create a new lock dependency:
[  154.723705]  (&(&cq->lock)->rlock/1){....} -> (&(&qp_table->lock)->rlock){+.+.}
[  154.731922]
but this new dependency connects a SOFTIRQ-irq-safe lock:
[  154.740798]  (&(&cq->lock)->rlock){..-.}
[  154.740800]
... which became SOFTIRQ-irq-safe at:
[  154.752163]   _raw_spin_lock_irqsave+0x3e/0x50
[  154.757163]   mlx4_ib_poll_cq+0x36/0x900 [mlx4_ib]
[  154.762554]   ipoib_tx_poll+0x4a/0xf0 [ib_ipoib]
...
to a SOFTIRQ-irq-unsafe lock:
[  154.815603]  (&(&qp_table->lock)->rlock){+.+.}
[  154.815604]
... which became SOFTIRQ-irq-unsafe at:
[  154.827718] ...
[  154.827720]   _raw_spin_lock+0x35/0x50
[  154.833912]   mlx4_qp_lookup+0x1e/0x50 [mlx4_core]
[  154.839302]   mlx4_flow_attach+0x3f/0x3d0 [mlx4_core]

Since mlx4_qp_lookup() is called only in process space, we can
simply replace the spin_un/lock calls with spin_un/lock_irq calls.

Fixes: 6dc06c08bef1 ("net/mlx4: Fix the check in attaching steering rules")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/qp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c
index 3aaf4bad6c5a..427e7a31862c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx4/qp.c
@@ -393,11 +393,11 @@ struct mlx4_qp *mlx4_qp_lookup(struct mlx4_dev *dev, u32 qpn)
 	struct mlx4_qp_table *qp_table = &mlx4_priv(dev)->qp_table;
 	struct mlx4_qp *qp;
 
-	spin_lock(&qp_table->lock);
+	spin_lock_irq(&qp_table->lock);
 
 	qp = __mlx4_qp_lookup(dev, qpn);
 
-	spin_unlock(&qp_table->lock);
+	spin_unlock_irq(&qp_table->lock);
 	return qp;
 }
 
-- 
2.17.1


From 2f8f07b3f216d182f8395f8e22262f18abf61c00 Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Tue, 1 May 2018 16:25:07 +0300
Subject: [PATCH 35/43] net/mlx5e: When RXFCS is set, add FCS data into
 checksum calculation

[ Upstream commit 902a545904c71d719ed144234d67df75f31db63b ]

When RXFCS feature is enabled, the HW do not strip the FCS data,
however it is not present in the checksum calculated by the HW.

Fix that by manually calculating the FCS checksum and adding it to the SKB
checksum field.

Add helper function to find the FCS data for all SKB forms (linear,
one fragment or more).

Fixes: 102722fc6832 ("net/mlx5e: Add support for RXFCS feature flag")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en_rx.c   | 42 +++++++++++++++++++
 1 file changed, 42 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index e5c3ab46a24a..f63b317f7b32 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -635,6 +635,45 @@ static inline bool is_last_ethertype_ip(struct sk_buff *skb, int *network_depth)
 	return (ethertype == htons(ETH_P_IP) || ethertype == htons(ETH_P_IPV6));
 }
 
+static __be32 mlx5e_get_fcs(struct sk_buff *skb)
+{
+	int last_frag_sz, bytes_in_prev, nr_frags;
+	u8 *fcs_p1, *fcs_p2;
+	skb_frag_t *last_frag;
+	__be32 fcs_bytes;
+
+	if (!skb_is_nonlinear(skb))
+		return *(__be32 *)(skb->data + skb->len - ETH_FCS_LEN);
+
+	nr_frags = skb_shinfo(skb)->nr_frags;
+	last_frag = &skb_shinfo(skb)->frags[nr_frags - 1];
+	last_frag_sz = skb_frag_size(last_frag);
+
+	/* If all FCS data is in last frag */
+	if (last_frag_sz >= ETH_FCS_LEN)
+		return *(__be32 *)(skb_frag_address(last_frag) +
+				   last_frag_sz - ETH_FCS_LEN);
+
+	fcs_p2 = (u8 *)skb_frag_address(last_frag);
+	bytes_in_prev = ETH_FCS_LEN - last_frag_sz;
+
+	/* Find where the other part of the FCS is - Linear or another frag */
+	if (nr_frags == 1) {
+		fcs_p1 = skb_tail_pointer(skb);
+	} else {
+		skb_frag_t *prev_frag = &skb_shinfo(skb)->frags[nr_frags - 2];
+
+		fcs_p1 = skb_frag_address(prev_frag) +
+			    skb_frag_size(prev_frag);
+	}
+	fcs_p1 -= bytes_in_prev;
+
+	memcpy(&fcs_bytes, fcs_p1, bytes_in_prev);
+	memcpy(((u8 *)&fcs_bytes) + bytes_in_prev, fcs_p2, last_frag_sz);
+
+	return fcs_bytes;
+}
+
 static inline void mlx5e_handle_csum(struct net_device *netdev,
 				     struct mlx5_cqe64 *cqe,
 				     struct mlx5e_rq *rq,
@@ -663,6 +702,9 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 			skb->csum = csum_partial(skb->data + ETH_HLEN,
 						 network_depth - ETH_HLEN,
 						 skb->csum);
+		if (unlikely(netdev->features & NETIF_F_RXFCS))
+			skb->csum = csum_add(skb->csum,
+					     (__force __wsum)mlx5e_get_fcs(skb));
 		rq->stats.csum_complete++;
 		return;
 	}
-- 
2.17.1


From 88b78cefd425abf0eb7324f4cd3142009a9b1346 Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Mon, 28 May 2018 19:37:49 +0900
Subject: [PATCH 36/43] tun: Fix NULL pointer dereference in XDP redirect

[ Upstream commit 6547e387d7f52f2ba681a229de3c13e5b9e01ee1 ]

Calling XDP redirection requires bh disabled. Softirq can call another
XDP function and redirection functions, then the percpu static variable
ri->map can be overwritten to NULL.

This is a generic XDP case called from tun.

[ 3535.736058] BUG: unable to handle kernel NULL pointer dereference at 0000000000000018
[ 3535.743974] PGD 0 P4D 0
[ 3535.746530] Oops: 0000 [#1] SMP PTI
[ 3535.750049] Modules linked in: vhost_net vhost tap tun bridge stp llc ebtable_filter ebtables ip6table_filter ip6_tables iptable_filter sunrpc vfat fat ext4 mbcache jbd2 intel_rapl skx_edac nfit libnvdimm x86_pkg_temp_thermal intel_powerclamp coretemp kvm_intel kvm ipmi_ssif irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel pcbc ses aesni_intel crypto_simd cryptd enclosure hpwdt hpilo glue_helper ipmi_si pcspkr wmi mei_me ioatdma mei ipmi_devintf shpchp dca ipmi_msghandler lpc_ich acpi_power_meter sch_fq_codel ip_tables xfs libcrc32c sd_mod mgag200 i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm drm smartpqi i40e crc32c_intel scsi_transport_sas tg3 i2c_core ptp pps_core
[ 3535.813456] CPU: 5 PID: 1630 Comm: vhost-1614 Not tainted 4.17.0-rc4 #2
[ 3535.820127] Hardware name: HPE ProLiant DL360 Gen10/ProLiant DL360 Gen10, BIOS U32 11/14/2017
[ 3535.828732] RIP: 0010:__xdp_map_lookup_elem+0x5/0x30
[ 3535.833740] RSP: 0018:ffffb4bc47bf7c58 EFLAGS: 00010246
[ 3535.839009] RAX: ffff9fdfcfea1c40 RBX: 0000000000000000 RCX: ffff9fdf27fe3100
[ 3535.846205] RDX: ffff9fdfca769200 RSI: 0000000000000000 RDI: 0000000000000000
[ 3535.853402] RBP: ffffb4bc491d9000 R08: 00000000000045ad R09: 0000000000000ec0
[ 3535.860597] R10: 0000000000000001 R11: ffff9fdf26c3ce4e R12: ffff9fdf9e72c000
[ 3535.867794] R13: 0000000000000000 R14: fffffffffffffff2 R15: ffff9fdfc82cdd00
[ 3535.874990] FS:  0000000000000000(0000) GS:ffff9fdfcfe80000(0000) knlGS:0000000000000000
[ 3535.883152] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 3535.888948] CR2: 0000000000000018 CR3: 0000000bde724004 CR4: 00000000007626e0
[ 3535.896145] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 3535.903342] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ 3535.910538] PKRU: 55555554
[ 3535.913267] Call Trace:
[ 3535.915736]  xdp_do_generic_redirect+0x7a/0x310
[ 3535.920310]  do_xdp_generic.part.117+0x285/0x370
[ 3535.924970]  tun_get_user+0x5b9/0x1260 [tun]
[ 3535.929279]  tun_sendmsg+0x52/0x70 [tun]
[ 3535.933237]  handle_tx+0x2ad/0x5f0 [vhost_net]
[ 3535.937721]  vhost_worker+0xa5/0x100 [vhost]
[ 3535.942030]  kthread+0xf5/0x130
[ 3535.945198]  ? vhost_dev_ioctl+0x3b0/0x3b0 [vhost]
[ 3535.950031]  ? kthread_bind+0x10/0x10
[ 3535.953727]  ret_from_fork+0x35/0x40
[ 3535.957334] Code: 0e 74 15 83 f8 10 75 05 e9 49 aa b3 ff f3 c3 0f 1f 80 00 00 00 00 f3 c3 e9 29 9d b3 ff 66 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 <8b> 47 18 83 f8 0e 74 0d 83 f8 10 75 05 e9 49 a9 b3 ff 31 c0 c3
[ 3535.976387] RIP: __xdp_map_lookup_elem+0x5/0x30 RSP: ffffb4bc47bf7c58
[ 3535.982883] CR2: 0000000000000018
[ 3535.987096] ---[ end trace 383b299dd1430240 ]---
[ 3536.131325] Kernel panic - not syncing: Fatal exception
[ 3536.137484] Kernel Offset: 0x26a00000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff)
[ 3536.281406] ---[ end Kernel panic - not syncing: Fatal exception ]---

And a kernel with generic case fixed still panics in tun driver XDP
redirect, because it disabled only preemption, but not bh.

[ 2055.128746] BUG: unable to handle kernel NULL pointer dereference at 0000000000000018
[ 2055.136662] PGD 0 P4D 0
[ 2055.139219] Oops: 0000 [#1] SMP PTI
[ 2055.142736] Modules linked in: vhost_net vhost tap tun bridge stp llc ebtable_filter ebtables ip6table_filter ip6_tables iptable_filter sunrpc vfat fat ext4 mbcache jbd2 intel_rapl skx_edac nfit libnvdimm x86_pkg_temp_thermal intel_powerclamp coretemp kvm_intel kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel pcbc ses aesni_intel ipmi_ssif crypto_simd enclosure cryptd hpwdt glue_helper ioatdma hpilo wmi dca pcspkr ipmi_si acpi_power_meter ipmi_devintf shpchp mei_me ipmi_msghandler mei lpc_ich sch_fq_codel ip_tables xfs libcrc32c sd_mod mgag200 i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm drm i40e smartpqi tg3 scsi_transport_sas crc32c_intel i2c_core ptp pps_core
[ 2055.206142] CPU: 6 PID: 1693 Comm: vhost-1683 Tainted: G        W         4.17.0-rc5-fix-tun+ #1
[ 2055.215011] Hardware name: HPE ProLiant DL360 Gen10/ProLiant DL360 Gen10, BIOS U32 11/14/2017
[ 2055.223617] RIP: 0010:__xdp_map_lookup_elem+0x5/0x30
[ 2055.228624] RSP: 0018:ffff998b07607cc0 EFLAGS: 00010246
[ 2055.233892] RAX: ffff8dbd8e235700 RBX: ffff8dbd8ff21c40 RCX: 0000000000000004
[ 2055.241089] RDX: ffff998b097a9000 RSI: 0000000000000000 RDI: 0000000000000000
[ 2055.248286] RBP: 0000000000000000 R08: 00000000000065a8 R09: 0000000000005d80
[ 2055.255483] R10: 0000000000000040 R11: ffff8dbcf0100000 R12: ffff998b097a9000
[ 2055.262681] R13: ffff8dbd8c98c000 R14: 0000000000000000 R15: ffff998b07607d78
[ 2055.269879] FS:  0000000000000000(0000) GS:ffff8dbd8ff00000(0000) knlGS:0000000000000000
[ 2055.278039] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 2055.283834] CR2: 0000000000000018 CR3: 0000000c0c8cc005 CR4: 00000000007626e0
[ 2055.291030] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 2055.298227] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ 2055.305424] PKRU: 55555554
[ 2055.308153] Call Trace:
[ 2055.310624]  xdp_do_redirect+0x7b/0x380
[ 2055.314499]  tun_get_user+0x10fe/0x12a0 [tun]
[ 2055.318895]  tun_sendmsg+0x52/0x70 [tun]
[ 2055.322852]  handle_tx+0x2ad/0x5f0 [vhost_net]
[ 2055.327337]  vhost_worker+0xa5/0x100 [vhost]
[ 2055.331646]  kthread+0xf5/0x130
[ 2055.334813]  ? vhost_dev_ioctl+0x3b0/0x3b0 [vhost]
[ 2055.339646]  ? kthread_bind+0x10/0x10
[ 2055.343343]  ret_from_fork+0x35/0x40
[ 2055.346950] Code: 0e 74 15 83 f8 10 75 05 e9 e9 aa b3 ff f3 c3 0f 1f 80 00 00 00 00 f3 c3 e9 c9 9d b3 ff 66 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 <8b> 47 18 83 f8 0e 74 0d 83 f8 10 75 05 e9 e9 a9 b3 ff 31 c0 c3
[ 2055.366004] RIP: __xdp_map_lookup_elem+0x5/0x30 RSP: ffff998b07607cc0
[ 2055.372500] CR2: 0000000000000018
[ 2055.375856] ---[ end trace 2a2dcc5e9e174268 ]---
[ 2055.523626] Kernel panic - not syncing: Fatal exception
[ 2055.529796] Kernel Offset: 0x2e000000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff)
[ 2055.677539] ---[ end Kernel panic - not syncing: Fatal exception ]---

v2:
 - Removed preempt_disable/enable since local_bh_disable will prevent
   preemption as well, feedback from Jason Wang.

Fixes: 761876c857cb ("tap: XDP support")
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index ffae19714ffd..24e645c86ae7 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1632,7 +1632,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 	else
 		*skb_xdp = 0;
 
-	preempt_disable();
+	local_bh_disable();
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(tun->xdp_prog);
 	if (xdp_prog && !*skb_xdp) {
@@ -1657,7 +1657,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 			if (err)
 				goto err_redirect;
 			rcu_read_unlock();
-			preempt_enable();
+			local_bh_enable();
 			return NULL;
 		case XDP_TX:
 			xdp_xmit = true;
@@ -1679,7 +1679,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 	skb = build_skb(buf, buflen);
 	if (!skb) {
 		rcu_read_unlock();
-		preempt_enable();
+		local_bh_enable();
 		return ERR_PTR(-ENOMEM);
 	}
 
@@ -1692,12 +1692,12 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 		skb->dev = tun->dev;
 		generic_xdp_tx(skb, xdp_prog);
 		rcu_read_unlock();
-		preempt_enable();
+		local_bh_enable();
 		return NULL;
 	}
 
 	rcu_read_unlock();
-	preempt_enable();
+	local_bh_enable();
 
 	return skb;
 
@@ -1705,7 +1705,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 	put_page(alloc_frag->page);
 err_xdp:
 	rcu_read_unlock();
-	preempt_enable();
+	local_bh_enable();
 	this_cpu_inc(tun->pcpu_stats->rx_dropped);
 	return NULL;
 }
@@ -1901,16 +1901,19 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 		struct bpf_prog *xdp_prog;
 		int ret;
 
+		local_bh_disable();
 		rcu_read_lock();
 		xdp_prog = rcu_dereference(tun->xdp_prog);
 		if (xdp_prog) {
 			ret = do_xdp_generic(xdp_prog, skb);
 			if (ret != XDP_PASS) {
 				rcu_read_unlock();
+				local_bh_enable();
 				return total_len;
 			}
 		}
 		rcu_read_unlock();
+		local_bh_enable();
 	}
 
 	rcu_read_lock();
-- 
2.17.1


From eaab3a908dbddd4e631f0b9ea13b86211d306cd4 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Tue, 22 May 2018 11:44:30 +0800
Subject: [PATCH 37/43] virtio-net: correctly check num_buf during err path

[ Upstream commit 850e088d5bbb333342fd4def08d0a4035f2b7126 ]

If we successfully linearize the packet, num_buf will be set to zero
which may confuse error handling path which assumes num_buf is at
least 1 and this can lead the code tries to pop the descriptor of next
buffer. Fixing this by checking num_buf against 1 before decreasing.

Fixes: 4941d472bf95 ("virtio-net: do not reset during XDP set")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 62f2bee34a4b..64e7a32098be 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -874,7 +874,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 	rcu_read_unlock();
 err_skb:
 	put_page(page);
-	while (--num_buf) {
+	while (num_buf-- > 1) {
 		buf = virtqueue_get_buf(rq->vq, &len);
 		if (unlikely(!buf)) {
 			pr_debug("%s: rx error: %d buffers missing\n",
-- 
2.17.1


From 541c1e9864894e13c2c4f047a31fbcaf3daf6c18 Mon Sep 17 00:00:00 2001
From: Arun Parameswaran <arun.parameswaran@broadcom.com>
Date: Tue, 5 Jun 2018 13:38:12 -0700
Subject: [PATCH 38/43] net: dsa: b53: Fix for brcm tag issue in Cygnus SoC
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 5040cc990cbac98733df4d58fdeac5bbdab15b49 ]

In the Broadcom Cygnus SoC, the brcm tag needs to be inserted
in between the mac address and the ether type (should use
'DSA_PROTO_TAG_BRCM') for the packets sent to the internal
b53 switch.

Since the Cygnus was added with the BCM58XX device id and the
BCM58XX uses 'DSA_PROTO_TAG_BRCM_PREPEND', the data path is
broken, due to the incorrect brcm tag location.

Add a new b53 device id (BCM583XX) for Cygnus family to fix the
issue. Add the new device id to the BCM58XX family as Cygnus
is similar to the BCM58XX in most other functionalities.

Fixes: 11606039604c ("net: dsa: b53: Support prepended Broadcom tags")

Signed-off-by: Arun Parameswaran <arun.parameswaran@broadcom.com>
Acked-by: Scott Branden <scott.branden@broadcom.com>
Reported-by: Clément Péron <peron.clem@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Tested-by: Clément Péron <peron.clem@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/b53/b53_common.c | 15 ++++++++++++++-
 drivers/net/dsa/b53/b53_priv.h   |  2 ++
 drivers/net/dsa/b53/b53_srab.c   |  4 ++--
 3 files changed, 18 insertions(+), 3 deletions(-)

diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 63e02a54d537..06e8e7a81994 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -684,7 +684,8 @@ static int b53_switch_reset(struct b53_device *dev)
 	 * still use this driver as a library and need to perform the reset
 	 * earlier.
 	 */
-	if (dev->chip_id == BCM58XX_DEVICE_ID) {
+	if (dev->chip_id == BCM58XX_DEVICE_ID ||
+	    dev->chip_id == BCM583XX_DEVICE_ID) {
 		b53_read8(dev, B53_CTRL_PAGE, B53_SOFTRESET, &reg);
 		reg |= SW_RST | EN_SW_RST | EN_CH_RST;
 		b53_write8(dev, B53_CTRL_PAGE, B53_SOFTRESET, reg);
@@ -1867,6 +1868,18 @@ static const struct b53_chip_data b53_switch_chips[] = {
 		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
 		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
 	},
+	{
+		.chip_id = BCM583XX_DEVICE_ID,
+		.dev_name = "BCM583xx/11360",
+		.vlans = 4096,
+		.enabled_ports = 0x103,
+		.arl_entries = 4,
+		.cpu_port = B53_CPU_PORT,
+		.vta_regs = B53_VTA_REGS,
+		.duplex_reg = B53_DUPLEX_STAT_GE,
+		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
+		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+	},
 	{
 		.chip_id = BCM7445_DEVICE_ID,
 		.dev_name = "BCM7445",
diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h
index d954cf36ecd8..f91acda37572 100644
--- a/drivers/net/dsa/b53/b53_priv.h
+++ b/drivers/net/dsa/b53/b53_priv.h
@@ -61,6 +61,7 @@ enum {
 	BCM53018_DEVICE_ID = 0x53018,
 	BCM53019_DEVICE_ID = 0x53019,
 	BCM58XX_DEVICE_ID = 0x5800,
+	BCM583XX_DEVICE_ID = 0x58300,
 	BCM7445_DEVICE_ID = 0x7445,
 	BCM7278_DEVICE_ID = 0x7278,
 };
@@ -180,6 +181,7 @@ static inline int is5301x(struct b53_device *dev)
 static inline int is58xx(struct b53_device *dev)
 {
 	return dev->chip_id == BCM58XX_DEVICE_ID ||
+		dev->chip_id == BCM583XX_DEVICE_ID ||
 		dev->chip_id == BCM7445_DEVICE_ID ||
 		dev->chip_id == BCM7278_DEVICE_ID;
 }
diff --git a/drivers/net/dsa/b53/b53_srab.c b/drivers/net/dsa/b53/b53_srab.c
index c37ffd1b6833..8247481eaa06 100644
--- a/drivers/net/dsa/b53/b53_srab.c
+++ b/drivers/net/dsa/b53/b53_srab.c
@@ -364,7 +364,7 @@ static const struct of_device_id b53_srab_of_match[] = {
 	{ .compatible = "brcm,bcm53018-srab" },
 	{ .compatible = "brcm,bcm53019-srab" },
 	{ .compatible = "brcm,bcm5301x-srab" },
-	{ .compatible = "brcm,bcm11360-srab", .data = (void *)BCM58XX_DEVICE_ID },
+	{ .compatible = "brcm,bcm11360-srab", .data = (void *)BCM583XX_DEVICE_ID },
 	{ .compatible = "brcm,bcm58522-srab", .data = (void *)BCM58XX_DEVICE_ID },
 	{ .compatible = "brcm,bcm58525-srab", .data = (void *)BCM58XX_DEVICE_ID },
 	{ .compatible = "brcm,bcm58535-srab", .data = (void *)BCM58XX_DEVICE_ID },
@@ -372,7 +372,7 @@ static const struct of_device_id b53_srab_of_match[] = {
 	{ .compatible = "brcm,bcm58623-srab", .data = (void *)BCM58XX_DEVICE_ID },
 	{ .compatible = "brcm,bcm58625-srab", .data = (void *)BCM58XX_DEVICE_ID },
 	{ .compatible = "brcm,bcm88312-srab", .data = (void *)BCM58XX_DEVICE_ID },
-	{ .compatible = "brcm,cygnus-srab", .data = (void *)BCM58XX_DEVICE_ID },
+	{ .compatible = "brcm,cygnus-srab", .data = (void *)BCM583XX_DEVICE_ID },
 	{ .compatible = "brcm,nsp-srab", .data = (void *)BCM58XX_DEVICE_ID },
 	{ /* sentinel */ },
 };
-- 
2.17.1


From 9b24e9a5e587b4d094dc7141e20d38fd73345641 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Wed, 23 May 2018 19:24:48 +0300
Subject: [PATCH 39/43] net : sched: cls_api: deal with egdev path only if
 needed

[ Upstream commit f8f4bef322e4600c5856911c7a632c0e3da920d6 ]

When dealing with ingress rule on a netdev, if we did fine through the
conventional path, there's no need to continue into the egdev route,
and we can stop right there.

Not doing so may cause a 2nd rule to be added by the cls api layer
with the ingress being the egdev.

For example, under sriov switchdev scheme, a user rule of VFR A --> VFR B
will end up with two HW rules (1) VF A --> VF B and (2) uplink --> VF B

Fixes: 208c0f4b5237 ('net: sched: use tc_setup_cb_call to call per-block callbacks')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index c2c732aad87c..86d2d5977f56 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1587,7 +1587,7 @@ int tc_setup_cb_call(struct tcf_block *block, struct tcf_exts *exts,
 		return ret;
 	ok_count = ret;
 
-	if (!exts)
+	if (!exts || ok_count)
 		return ok_count;
 	ret = tc_exts_setup_cb_egdev_call(exts, type, type_data, err_stop);
 	if (ret < 0)
-- 
2.17.1


From 7d5392fa14839de938aebffa518191dffe86a392 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Tue, 22 May 2018 11:44:28 +0800
Subject: [PATCH 40/43] virtio-net: correctly redirect linearized packet

[ Upstream commit 6890418bbb780f0ee9cf124055afa79777f1b4f1 ]

After a linearized packet was redirected by XDP, we should not go for
the err path which will try to pop buffers for the next packet and
increase the drop counter. Fixing this by just drop the page refcnt
for the original page.

Fixes: 186b3c998c50 ("virtio-net: support XDP_REDIRECT")
Reported-by: David Ahern <dsahern@gmail.com>
Tested-by: David Ahern <dsahern@gmail.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 64e7a32098be..8911e3466e61 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -786,7 +786,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 			}
 			*xdp_xmit = true;
 			if (unlikely(xdp_page != page))
-				goto err_xdp;
+				put_page(page);
 			rcu_read_unlock();
 			goto xdp_xmit;
 		default:
-- 
2.17.1


From f3e3a090fad3bb933c95f50d06cbf3ee5a159de0 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Thu, 31 May 2018 10:59:32 +0200
Subject: [PATCH 41/43] ip_tunnel: restore binding to ifaces with a large mtu

[ Upstream commit 82612de1c98e610d194e34178bde3cca7dedce41 ]

After commit f6cc9c054e77, the following conf is broken (note that the
default loopback mtu is 65536, ie IP_MAX_MTU + 1):

$ ip tunnel add gre1 mode gre local 10.125.0.1 remote 10.125.0.2 dev lo
add tunnel "gre0" failed: Invalid argument
$ ip l a type dummy
$ ip l s dummy1 up
$ ip l s dummy1 mtu 65535
$ ip tunnel add gre1 mode gre local 10.125.0.1 remote 10.125.0.2 dev dummy1
add tunnel "gre0" failed: Invalid argument

dev_set_mtu() doesn't allow to set a mtu which is too large.
First, let's cap the mtu returned by ip_tunnel_bind_dev(). Second, remove
the magic value 0xFFF8 and use IP_MAX_MTU instead.
0xFFF8 seems to be there for ages, I don't know why this value was used.

With a recent kernel, it's also possible to set a mtu > IP_MAX_MTU:
$ ip l s dummy1 mtu 66000
After that patch, it's also possible to bind an ip tunnel on that kind of
interface.

CC: Petr Machata <petrm@mellanox.com>
CC: Ido Schimmel <idosch@mellanox.com>
Link: https://git.kernel.org/pub/scm/linux/kernel/git/davem/netdev-vger-cvs.git/commit/?id=e5afd356a411a
Fixes: f6cc9c054e77 ("ip_tunnel: Emit events for post-register MTU changes")
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_tunnel.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 57478d68248d..c4e33f4141d8 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -344,7 +344,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
 
 	if (tdev) {
 		hlen = tdev->hard_header_len + tdev->needed_headroom;
-		mtu = tdev->mtu;
+		mtu = min(tdev->mtu, IP_MAX_MTU);
 	}
 
 	dev->needed_headroom = t_hlen + hlen;
@@ -379,7 +379,7 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net,
 	nt = netdev_priv(dev);
 	t_hlen = nt->hlen + sizeof(struct iphdr);
 	dev->min_mtu = ETH_MIN_MTU;
-	dev->max_mtu = 0xFFF8 - dev->hard_header_len - t_hlen;
+	dev->max_mtu = IP_MAX_MTU - dev->hard_header_len - t_hlen;
 	ip_tunnel_add(itn, nt);
 	return nt;
 
@@ -948,7 +948,7 @@ int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	int t_hlen = tunnel->hlen + sizeof(struct iphdr);
-	int max_mtu = 0xFFF8 - dev->hard_header_len - t_hlen;
+	int max_mtu = IP_MAX_MTU - dev->hard_header_len - t_hlen;
 
 	if (new_mtu < ETH_MIN_MTU)
 		return -EINVAL;
@@ -1119,7 +1119,7 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
 
 	mtu = ip_tunnel_bind_dev(dev);
 	if (tb[IFLA_MTU]) {
-		unsigned int max = 0xfff8 - dev->hard_header_len - nt->hlen;
+		unsigned int max = IP_MAX_MTU - dev->hard_header_len - nt->hlen;
 
 		mtu = clamp(dev->mtu, (unsigned int)ETH_MIN_MTU,
 			    (unsigned int)(max - sizeof(struct iphdr)));
-- 
2.17.1


From 34319d8fb61b85ae8cb98b3f863141ea21c7033e Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Fri, 25 May 2018 14:50:37 +0200
Subject: [PATCH 42/43] net: netsec: reduce DMA mask to 40 bits

[ Upstream commit 312564269535892cc082bc80592150cd1f5e8ec3 ]

The netsec network controller IP can drive 64 address bits for DMA, and
the DMA mask is set accordingly in the driver. However, the SynQuacer
SoC, which is the only silicon incorporating this IP at the moment,
integrates this IP in a manner that leaves address bits [63:40]
unconnected.

Up until now, this has not resulted in any problems, given that the DDR
controller doesn't decode those bits to begin with. However, recent
firmware updates for platforms incorporating this SoC allow the IOMMU
to be enabled, which does decode address bits [47:40], and allocates
top down from the IOVA space, producing DMA addresses that have bits
set that have been left unconnected.

Both the DT and ACPI (IORT) descriptions of the platform take this into
account, and only describe a DMA address space of 40 bits (using either
dma-ranges DT properties, or DMA address limits in IORT named component
nodes). However, even though our IOMMU and bus layers may take such
limitations into account by setting a narrower DMA mask when creating
the platform device, the netsec probe() entrypoint follows the common
practice of setting the DMA mask uncondionally, according to the
capabilities of the IP block itself rather than to its integration into
the chip.

It is currently unclear what the correct fix is here. We could hack around
it by only setting the DMA mask if it deviates from its default value of
DMA_BIT_MASK(32). However, this makes it impossible for the bus layer to
use DMA_BIT_MASK(32) as the bus limit, and so it appears that a more
comprehensive approach is required to take DMA limits imposed by the
SoC as a whole into account.

In the mean time, let's limit the DMA mask to 40 bits. Given that there
is currently only one SoC that incorporates this IP, this is a reasonable
approach that can be backported to -stable and buys us some time to come
up with a proper fix going forward.

Fixes: 533dd11a12f6 ("net: socionext: Add Synquacer NetSec driver")
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: Jassi Brar <jaswinder.singh@linaro.org>
Cc: Masahisa Kojima <masahisa.kojima@linaro.org>
Cc: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Acked-by: Jassi Brar <jaswinder.singh@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/socionext/netsec.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index f4c0b02ddad8..59fbf74dcada 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -1674,8 +1674,8 @@ static int netsec_probe(struct platform_device *pdev)
 	if (ret)
 		goto unreg_napi;
 
-	if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)))
-		dev_warn(&pdev->dev, "Failed to enable 64-bit DMA\n");
+	if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(40)))
+		dev_warn(&pdev->dev, "Failed to set DMA mask\n");
 
 	ret = register_netdev(ndev);
 	if (ret) {
-- 
2.17.1


From 222f8015bf588669d78b4d58b66fb9056caca962 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Tue, 29 May 2018 14:18:19 +0800
Subject: [PATCH 43/43] vhost_net: flush batched heads before trying to busy
 polling

[ Upstream commit f5a4941aa6d190e676065e8f4ed35999f52a01c3 ]

After commit e2b3b35eb989 ("vhost_net: batch used ring update in rx"),
we tend to batch updating used heads. But it doesn't flush batched
heads before trying to do busy polling, this will cause vhost to wait
for guest TX which waits for the used RX. Fixing by flush batched
heads before busy loop.

1 byte TCP_RR performance recovers from 13107.83 to 50402.65.

Fixes: e2b3b35eb989 ("vhost_net: batch used ring update in rx")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/net.c | 37 ++++++++++++++++++++++++-------------
 1 file changed, 24 insertions(+), 13 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 12bcfbac2cc9..d3c90ce5d4c4 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -101,7 +101,9 @@ struct vhost_net_virtqueue {
 	/* vhost zerocopy support fields below: */
 	/* last used idx for outstanding DMA zerocopy buffers */
 	int upend_idx;
-	/* first used idx for DMA done zerocopy buffers */
+	/* For TX, first used idx for DMA done zerocopy buffers
+	 * For RX, number of batched heads
+	 */
 	int done_idx;
 	/* an array of userspace buffers info */
 	struct ubuf_info *ubuf_info;
@@ -620,6 +622,18 @@ static int sk_has_rx_data(struct sock *sk)
 	return skb_queue_empty(&sk->sk_receive_queue);
 }
 
+static void vhost_rx_signal_used(struct vhost_net_virtqueue *nvq)
+{
+	struct vhost_virtqueue *vq = &nvq->vq;
+	struct vhost_dev *dev = vq->dev;
+
+	if (!nvq->done_idx)
+		return;
+
+	vhost_add_used_and_signal_n(dev, vq, vq->heads, nvq->done_idx);
+	nvq->done_idx = 0;
+}
+
 static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk)
 {
 	struct vhost_net_virtqueue *rvq = &net->vqs[VHOST_NET_VQ_RX];
@@ -629,6 +643,8 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk)
 	int len = peek_head_len(rvq, sk);
 
 	if (!len && vq->busyloop_timeout) {
+		/* Flush batched heads first */
+		vhost_rx_signal_used(rvq);
 		/* Both tx vq and rx socket were polled here */
 		mutex_lock_nested(&vq->mutex, 1);
 		vhost_disable_notify(&net->dev, vq);
@@ -756,7 +772,7 @@ static void handle_rx(struct vhost_net *net)
 	};
 	size_t total_len = 0;
 	int err, mergeable;
-	s16 headcount, nheads = 0;
+	s16 headcount;
 	size_t vhost_hlen, sock_hlen;
 	size_t vhost_len, sock_len;
 	struct socket *sock;
@@ -784,8 +800,8 @@ static void handle_rx(struct vhost_net *net)
 	while ((sock_len = vhost_net_rx_peek_head_len(net, sock->sk))) {
 		sock_len += sock_hlen;
 		vhost_len = sock_len + vhost_hlen;
-		headcount = get_rx_bufs(vq, vq->heads + nheads, vhost_len,
-					&in, vq_log, &log,
+		headcount = get_rx_bufs(vq, vq->heads + nvq->done_idx,
+					vhost_len, &in, vq_log, &log,
 					likely(mergeable) ? UIO_MAXIOV : 1);
 		/* On error, stop handling until the next kick. */
 		if (unlikely(headcount < 0))
@@ -856,12 +872,9 @@ static void handle_rx(struct vhost_net *net)
 			vhost_discard_vq_desc(vq, headcount);
 			goto out;
 		}
-		nheads += headcount;
-		if (nheads > VHOST_RX_BATCH) {
-			vhost_add_used_and_signal_n(&net->dev, vq, vq->heads,
-						    nheads);
-			nheads = 0;
-		}
+		nvq->done_idx += headcount;
+		if (nvq->done_idx > VHOST_RX_BATCH)
+			vhost_rx_signal_used(nvq);
 		if (unlikely(vq_log))
 			vhost_log_write(vq, vq_log, log, vhost_len);
 		total_len += vhost_len;
@@ -872,9 +885,7 @@ static void handle_rx(struct vhost_net *net)
 	}
 	vhost_net_enable_vq(net, vq);
 out:
-	if (nheads)
-		vhost_add_used_and_signal_n(&net->dev, vq, vq->heads,
-					    nheads);
+	vhost_rx_signal_used(nvq);
 	mutex_unlock(&vq->mutex);
 }
 
-- 
2.17.1


[-- Attachment #3: net_417.mbox --]
[-- Type: Application/Octet-Stream, Size: 44189 bytes --]

From e9bf5f4e7a4f8b50f008acded3becaacb55e4901 Mon Sep 17 00:00:00 2001
From: Julia Lawall <Julia.Lawall@lip6.fr>
Date: Wed, 6 Jun 2018 15:03:22 +0200
Subject: [PATCH 01/13] bnx2x: use the right constant

[ Upstream commit dd612f18a49b63af8b3a5f572d999bdb197385bc ]

Nearby code that also tests port suggests that the P0 constant should be
used when port is zero.

The semantic match that finds this problem is as follows:
(http://coccinelle.lip6.fr/)

// <smpl>
@@
expression e,e1;
@@

* e ? e1 : e1
// </smpl>

Fixes: 6c3218c6f7e5 ("bnx2x: Adjust ETS to 578xx")
Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
index 7dd83d0ef0a0..22243c480a05 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
@@ -588,7 +588,7 @@ static void bnx2x_ets_e3b0_nig_disabled(const struct link_params *params,
 	 * slots for the highest priority.
 	 */
 	REG_WR(bp, (port) ? NIG_REG_P1_TX_ARB_NUM_STRICT_ARB_SLOTS :
-		   NIG_REG_P1_TX_ARB_NUM_STRICT_ARB_SLOTS, 0x100);
+		   NIG_REG_P0_TX_ARB_NUM_STRICT_ARB_SLOTS, 0x100);
 	/* Mapping between the CREDIT_WEIGHT registers and actual client
 	 * numbers
 	 */
-- 
2.17.1


From 5633326b4c2836afdf08f25fd17e0cbab8a7c91e Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 5 Jun 2018 15:01:59 +0200
Subject: [PATCH 02/13] ip6mr: only set ip6mr_table from setsockopt when
 ip6mr_new_table succeeds

[ Upstream commit 848235edb5c93ed086700584c8ff64f6d7fc778d ]

Currently, raw6_sk(sk)->ip6mr_table is set unconditionally during
ip6_mroute_setsockopt(MRT6_TABLE). A subsequent attempt at the same
setsockopt will fail with -ENOENT, since we haven't actually created
that table.

A similar fix for ipv4 was included in commit 5e1859fbcc3c ("ipv4: ipmr:
various fixes and cleanups").

Fixes: d1db275dd3f6 ("ipv6: ip6mr: support multiple tables")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6mr.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 298fd8b6ed17..42eca2689c3b 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1759,7 +1759,8 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
 		ret = 0;
 		if (!ip6mr_new_table(net, v))
 			ret = -ENOMEM;
-		raw6_sk(sk)->ip6mr_table = v;
+		else
+			raw6_sk(sk)->ip6mr_table = v;
 		rtnl_unlock();
 		return ret;
 	}
-- 
2.17.1


From 70ecc248ea5cb86c796f229b48b794f5122b1851 Mon Sep 17 00:00:00 2001
From: Michal Kubecek <mkubecek@suse.cz>
Date: Mon, 4 Jun 2018 11:36:05 +0200
Subject: [PATCH 03/13] ipv6: omit traffic class when calculating flow hash

[ Upstream commit fa1be7e01ea863e911349e30456706749518eeab ]

Some of the code paths calculating flow hash for IPv6 use flowlabel member
of struct flowi6 which, despite its name, encodes both flow label and
traffic class. If traffic class changes within a TCP connection (as e.g.
ssh does), ECMP route can switch between path. It's also inconsistent with
other code paths where ip6_flowlabel() (returning only flow label) is used
to feed the key.

Use only flow label everywhere, including one place where hash key is set
using ip6_flowinfo().

Fixes: 51ebd3181572 ("ipv6: add support of equal cost multipath (ECMP)")
Fixes: f70ea018da06 ("net: Add functions to get skb->hash based on flow structures")
Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h        | 5 +++++
 net/core/flow_dissector.c | 2 +-
 net/ipv6/route.c          | 4 ++--
 3 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 836f31af1369..a406f2e8680a 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -906,6 +906,11 @@ static inline __be32 ip6_make_flowinfo(unsigned int tclass, __be32 flowlabel)
 	return htonl(tclass << IPV6_TCLASS_SHIFT) | flowlabel;
 }
 
+static inline __be32 flowi6_get_flowlabel(const struct flowi6 *fl6)
+{
+	return fl6->flowlabel & IPV6_FLOWLABEL_MASK;
+}
+
 /*
  *	Prototypes exported by ipv6
  */
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index d29f09bc5ff9..0234f8d1f0ac 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -1334,7 +1334,7 @@ __u32 __get_hash_from_flowi6(const struct flowi6 *fl6, struct flow_keys *keys)
 	keys->ports.src = fl6->fl6_sport;
 	keys->ports.dst = fl6->fl6_dport;
 	keys->keyid.keyid = fl6->fl6_gre_key;
-	keys->tags.flow_label = (__force u32)fl6->flowlabel;
+	keys->tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6);
 	keys->basic.ip_proto = fl6->flowi6_proto;
 
 	return flow_hash_from_keys(keys);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index f4d61736c41a..4530a82aaa2e 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1868,7 +1868,7 @@ static void ip6_multipath_l3_keys(const struct sk_buff *skb,
 	} else {
 		keys->addrs.v6addrs.src = key_iph->saddr;
 		keys->addrs.v6addrs.dst = key_iph->daddr;
-		keys->tags.flow_label = ip6_flowinfo(key_iph);
+		keys->tags.flow_label = ip6_flowlabel(key_iph);
 		keys->basic.ip_proto = key_iph->nexthdr;
 	}
 }
@@ -1889,7 +1889,7 @@ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6,
 		} else {
 			hash_keys.addrs.v6addrs.src = fl6->saddr;
 			hash_keys.addrs.v6addrs.dst = fl6->daddr;
-			hash_keys.tags.flow_label = (__force u32)fl6->flowlabel;
+			hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6);
 			hash_keys.basic.ip_proto = fl6->flowi6_proto;
 		}
 		break;
-- 
2.17.1


From 40ee21013bf191fad46cbf388754f7b6be0a56f0 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Mon, 4 Jun 2018 18:52:19 +0200
Subject: [PATCH 04/13] l2tp: fix refcount leakage on PPPoL2TP sockets

[ Upstream commit 3d609342cc04129ff7568e19316ce3d7451a27e8 ]

Commit d02ba2a6110c ("l2tp: fix race in pppol2tp_release with session
object destroy") tried to fix a race condition where a PPPoL2TP socket
would disappear while the L2TP session was still using it. However, it
missed the root issue which is that an L2TP session may accept to be
reconnected if its associated socket has entered the release process.

The tentative fix makes the session hold the socket it is connected to.
That saves the kernel from crashing, but introduces refcount leakage,
preventing the socket from completing the release process. Once stalled,
everything the socket depends on can't be released anymore, including
the L2TP session and the l2tp_ppp module.

The root issue is that, when releasing a connected PPPoL2TP socket, the
session's ->sk pointer (RCU-protected) is reset to NULL and we have to
wait for a grace period before destroying the socket. The socket drops
the session in its ->sk_destruct callback function, so the session
will exist until the last reference on the socket is dropped.
Therefore, there is a time frame where pppol2tp_connect() may accept
reconnecting a session, as it only checks ->sk to figure out if the
session is connected. This time frame is shortened by the fact that
pppol2tp_release() calls l2tp_session_delete(), making the session
unreachable before resetting ->sk. However, pppol2tp_connect() may
grab the session before it gets unhashed by l2tp_session_delete(), but
it may test ->sk after the later got reset. The race is not so hard to
trigger and syzbot found a pretty reliable reproducer:
https://syzkaller.appspot.com/bug?id=418578d2a4389074524e04d641eacb091961b2cf

Before d02ba2a6110c, another race could let pppol2tp_release()
overwrite the ->__sk pointer of an L2TP session, thus tricking
pppol2tp_put_sk() into calling sock_put() on a socket that is different
than the one for which pppol2tp_release() was originally called. To get
there, we had to trigger the race described above, therefore having one
PPPoL2TP socket being released, while the session it is connected to is
reconnecting to a different PPPoL2TP socket. When releasing this new
socket fast enough, pppol2tp_release() overwrites the session's
->__sk pointer with the address of the new socket, before the first
pppol2tp_put_sk() call gets scheduled. Then the pppol2tp_put_sk() call
invoked by the original socket will sock_put() the new socket,
potentially dropping its last reference. When the second
pppol2tp_put_sk() finally runs, its socket has already been freed.

With d02ba2a6110c, the session takes a reference on both sockets.
Furthermore, the session's ->sk pointer is reset in the
pppol2tp_session_close() callback function rather than in
pppol2tp_release(). Therefore, ->__sk can't be overwritten and
pppol2tp_put_sk() is called only once (l2tp_session_delete() will only
run pppol2tp_session_close() once, to protect the session against
concurrent deletion requests). Now pppol2tp_put_sk() will properly
sock_put() the original socket, but the new socket will remain, as
l2tp_session_delete() prevented the release process from completing.
Here, we don't depend on the ->__sk race to trigger the bug. Getting
into the pppol2tp_connect() race is enough to leak the reference, no
matter when new socket is released.

So it all boils down to pppol2tp_connect() failing to realise that the
session has already been connected. This patch drops the unneeded extra
reference counting (mostly reverting d02ba2a6110c) and checks that
neither ->sk nor ->__sk is set before allowing a session to be
connected.

Fixes: d02ba2a6110c ("l2tp: fix race in pppol2tp_release with session object destroy")
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ppp.c | 35 +++++++++++++++++------------------
 1 file changed, 17 insertions(+), 18 deletions(-)

diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 1fd9e145076a..466f17646625 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -428,16 +428,6 @@ static void pppol2tp_put_sk(struct rcu_head *head)
  */
 static void pppol2tp_session_close(struct l2tp_session *session)
 {
-	struct pppol2tp_session *ps;
-
-	ps = l2tp_session_priv(session);
-	mutex_lock(&ps->sk_lock);
-	ps->__sk = rcu_dereference_protected(ps->sk,
-					     lockdep_is_held(&ps->sk_lock));
-	RCU_INIT_POINTER(ps->sk, NULL);
-	if (ps->__sk)
-		call_rcu(&ps->rcu, pppol2tp_put_sk);
-	mutex_unlock(&ps->sk_lock);
 }
 
 /* Really kill the session socket. (Called from sock_put() if
@@ -480,15 +470,24 @@ static int pppol2tp_release(struct socket *sock)
 	sock_orphan(sk);
 	sock->sk = NULL;
 
-	/* If the socket is associated with a session,
-	 * l2tp_session_delete will call pppol2tp_session_close which
-	 * will drop the session's ref on the socket.
-	 */
 	session = pppol2tp_sock_to_session(sk);
 	if (session) {
+		struct pppol2tp_session *ps;
+
 		l2tp_session_delete(session);
-		/* drop the ref obtained by pppol2tp_sock_to_session */
-		sock_put(sk);
+
+		ps = l2tp_session_priv(session);
+		mutex_lock(&ps->sk_lock);
+		ps->__sk = rcu_dereference_protected(ps->sk,
+						     lockdep_is_held(&ps->sk_lock));
+		RCU_INIT_POINTER(ps->sk, NULL);
+		mutex_unlock(&ps->sk_lock);
+		call_rcu(&ps->rcu, pppol2tp_put_sk);
+
+		/* Rely on the sock_put() call at the end of the function for
+		 * dropping the reference held by pppol2tp_sock_to_session().
+		 * The last reference will be dropped by pppol2tp_put_sk().
+		 */
 	}
 
 	release_sock(sk);
@@ -742,7 +741,8 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 		 */
 		mutex_lock(&ps->sk_lock);
 		if (rcu_dereference_protected(ps->sk,
-					      lockdep_is_held(&ps->sk_lock))) {
+					      lockdep_is_held(&ps->sk_lock)) ||
+		    ps->__sk) {
 			mutex_unlock(&ps->sk_lock);
 			error = -EEXIST;
 			goto end;
@@ -803,7 +803,6 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 
 out_no_ppp:
 	/* This is how we get the session context from the socket. */
-	sock_hold(sk);
 	sk->sk_user_data = session;
 	rcu_assign_pointer(ps->sk, sk);
 	mutex_unlock(&ps->sk_lock);
-- 
2.17.1


From 486a187a3eef03793c25670d888ee21502a28de8 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Tue, 5 Jun 2018 09:48:13 -0700
Subject: [PATCH 05/13] netdev-FAQ: clarify DaveM's position for stable
 backports

[ Upstream commit 75d4e704fa8d2cf33ff295e5b441317603d7f9fd ]

Per discussion with David at netconf 2018, let's clarify
DaveM's position of handling stable backports in netdev-FAQ.

This is important for people relying on upstream -stable
releases.

Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/netdev-FAQ.txt | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/Documentation/networking/netdev-FAQ.txt b/Documentation/networking/netdev-FAQ.txt
index 2a3278d5cf35..fa951b820b25 100644
--- a/Documentation/networking/netdev-FAQ.txt
+++ b/Documentation/networking/netdev-FAQ.txt
@@ -179,6 +179,15 @@ A: No.  See above answer.  In short, if you think it really belongs in
    dash marker line as described in Documentation/process/submitting-patches.rst to
    temporarily embed that information into the patch that you send.
 
+Q: Are all networking bug fixes backported to all stable releases?
+
+A: Due to capacity, Dave could only take care of the backports for the last
+   2 stable releases. For earlier stable releases, each stable branch maintainer
+   is supposed to take care of them. If you find any patch is missing from an
+   earlier stable branch, please notify stable@vger.kernel.org with either a
+   commit ID or a formal patch backported, and CC Dave and other relevant
+   networking developers.
+
 Q: Someone said that the comment style and coding convention is different
    for the networking content.  Is this true?
 
-- 
2.17.1


From d4400818dc31f21da21953947dd70aa7fc66fd40 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 5 Jun 2018 06:06:19 -0700
Subject: [PATCH 06/13] net: metrics: add proper netlink validation

[ Upstream commit 5b5e7a0de2bbf2a1afcd9f49e940010e9fb80d53 ]

Before using nla_get_u32(), better make sure the attribute
is of the proper size.

Code recently was changed, but bug has been there from beginning
of git.

BUG: KMSAN: uninit-value in rtnetlink_put_metrics+0x553/0x960 net/core/rtnetlink.c:746
CPU: 1 PID: 14139 Comm: syz-executor6 Not tainted 4.17.0-rc5+ #103
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x185/0x1d0 lib/dump_stack.c:113
 kmsan_report+0x149/0x260 mm/kmsan/kmsan.c:1084
 __msan_warning_32+0x6e/0xc0 mm/kmsan/kmsan_instr.c:686
 rtnetlink_put_metrics+0x553/0x960 net/core/rtnetlink.c:746
 fib_dump_info+0xc42/0x2190 net/ipv4/fib_semantics.c:1361
 rtmsg_fib+0x65f/0x8c0 net/ipv4/fib_semantics.c:419
 fib_table_insert+0x2314/0x2b50 net/ipv4/fib_trie.c:1287
 inet_rtm_newroute+0x210/0x340 net/ipv4/fib_frontend.c:779
 rtnetlink_rcv_msg+0xa32/0x1560 net/core/rtnetlink.c:4646
 netlink_rcv_skb+0x378/0x600 net/netlink/af_netlink.c:2448
 rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:4664
 netlink_unicast_kernel net/netlink/af_netlink.c:1310 [inline]
 netlink_unicast+0x1678/0x1750 net/netlink/af_netlink.c:1336
 netlink_sendmsg+0x104f/0x1350 net/netlink/af_netlink.c:1901
 sock_sendmsg_nosec net/socket.c:629 [inline]
 sock_sendmsg net/socket.c:639 [inline]
 ___sys_sendmsg+0xec0/0x1310 net/socket.c:2117
 __sys_sendmsg net/socket.c:2155 [inline]
 __do_sys_sendmsg net/socket.c:2164 [inline]
 __se_sys_sendmsg net/socket.c:2162 [inline]
 __x64_sys_sendmsg+0x331/0x460 net/socket.c:2162
 do_syscall_64+0x152/0x230 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x455a09
RSP: 002b:00007faae5fd8c68 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 00007faae5fd96d4 RCX: 0000000000455a09
RDX: 0000000000000000 RSI: 0000000020000000 RDI: 0000000000000013
RBP: 000000000072bea0 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff
R13: 00000000000005d0 R14: 00000000006fdc20 R15: 0000000000000000

Uninit was stored to memory at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:279 [inline]
 kmsan_save_stack mm/kmsan/kmsan.c:294 [inline]
 kmsan_internal_chain_origin+0x12b/0x210 mm/kmsan/kmsan.c:685
 __msan_chain_origin+0x69/0xc0 mm/kmsan/kmsan_instr.c:529
 fib_convert_metrics net/ipv4/fib_semantics.c:1056 [inline]
 fib_create_info+0x2d46/0x9dc0 net/ipv4/fib_semantics.c:1150
 fib_table_insert+0x3e4/0x2b50 net/ipv4/fib_trie.c:1146
 inet_rtm_newroute+0x210/0x340 net/ipv4/fib_frontend.c:779
 rtnetlink_rcv_msg+0xa32/0x1560 net/core/rtnetlink.c:4646
 netlink_rcv_skb+0x378/0x600 net/netlink/af_netlink.c:2448
 rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:4664
 netlink_unicast_kernel net/netlink/af_netlink.c:1310 [inline]
 netlink_unicast+0x1678/0x1750 net/netlink/af_netlink.c:1336
 netlink_sendmsg+0x104f/0x1350 net/netlink/af_netlink.c:1901
 sock_sendmsg_nosec net/socket.c:629 [inline]
 sock_sendmsg net/socket.c:639 [inline]
 ___sys_sendmsg+0xec0/0x1310 net/socket.c:2117
 __sys_sendmsg net/socket.c:2155 [inline]
 __do_sys_sendmsg net/socket.c:2164 [inline]
 __se_sys_sendmsg net/socket.c:2162 [inline]
 __x64_sys_sendmsg+0x331/0x460 net/socket.c:2162
 do_syscall_64+0x152/0x230 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:279 [inline]
 kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:189
 kmsan_kmalloc+0x94/0x100 mm/kmsan/kmsan.c:315
 kmsan_slab_alloc+0x10/0x20 mm/kmsan/kmsan.c:322
 slab_post_alloc_hook mm/slab.h:446 [inline]
 slab_alloc_node mm/slub.c:2753 [inline]
 __kmalloc_node_track_caller+0xb32/0x11b0 mm/slub.c:4395
 __kmalloc_reserve net/core/skbuff.c:138 [inline]
 __alloc_skb+0x2cb/0x9e0 net/core/skbuff.c:206
 alloc_skb include/linux/skbuff.h:988 [inline]
 netlink_alloc_large_skb net/netlink/af_netlink.c:1182 [inline]
 netlink_sendmsg+0x76e/0x1350 net/netlink/af_netlink.c:1876
 sock_sendmsg_nosec net/socket.c:629 [inline]
 sock_sendmsg net/socket.c:639 [inline]
 ___sys_sendmsg+0xec0/0x1310 net/socket.c:2117
 __sys_sendmsg net/socket.c:2155 [inline]
 __do_sys_sendmsg net/socket.c:2164 [inline]
 __se_sys_sendmsg net/socket.c:2162 [inline]
 __x64_sys_sendmsg+0x331/0x460 net/socket.c:2162
 do_syscall_64+0x152/0x230 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: a919525ad832 ("net: Move fib_convert_metrics to metrics file")
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_semantics.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index c27122f01b87..cfae17335705 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -717,6 +717,8 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi)
 			nla_strlcpy(tmp, nla, sizeof(tmp));
 			val = tcp_ca_get_key_by_name(fi->fib_net, tmp, &ecn_ca);
 		} else {
+			if (nla_len(nla) != sizeof(u32))
+				return false;
 			val = nla_get_u32(nla);
 		}
 
@@ -1043,6 +1045,8 @@ fib_convert_metrics(struct fib_info *fi, const struct fib_config *cfg)
 			if (val == TCP_CA_UNSPEC)
 				return -EINVAL;
 		} else {
+			if (nla_len(nla) != sizeof(u32))
+				return -EINVAL;
 			val = nla_get_u32(nla);
 		}
 		if (type == RTAX_ADVMSS && val > 65535 - 40)
-- 
2.17.1


From 14768a2bb95221390847c7292f8de20868df4295 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 1 Jun 2018 09:23:02 -0700
Subject: [PATCH 07/13] net/packet: refine check for priv area size

[ Upstream commit eb73190f4fbeedf762394e92d6a4ec9ace684c88 ]

syzbot was able to trick af_packet again [1]

Various commits tried to address the problem in the past,
but failed to take into account V3 header size.

[1]

tpacket_rcv: packet too big, clamped from 72 to 4294967224. macoff=96
BUG: KASAN: use-after-free in prb_run_all_ft_ops net/packet/af_packet.c:1016 [inline]
BUG: KASAN: use-after-free in prb_fill_curr_block.isra.59+0x4e5/0x5c0 net/packet/af_packet.c:1039
Write of size 2 at addr ffff8801cb62000e by task kworker/1:2/2106

CPU: 1 PID: 2106 Comm: kworker/1:2 Not tainted 4.17.0-rc7+ #77
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Workqueue: ipv6_addrconf addrconf_dad_work
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1b9/0x294 lib/dump_stack.c:113
 print_address_description+0x6c/0x20b mm/kasan/report.c:256
 kasan_report_error mm/kasan/report.c:354 [inline]
 kasan_report.cold.7+0x242/0x2fe mm/kasan/report.c:412
 __asan_report_store2_noabort+0x17/0x20 mm/kasan/report.c:436
 prb_run_all_ft_ops net/packet/af_packet.c:1016 [inline]
 prb_fill_curr_block.isra.59+0x4e5/0x5c0 net/packet/af_packet.c:1039
 __packet_lookup_frame_in_block net/packet/af_packet.c:1094 [inline]
 packet_current_rx_frame net/packet/af_packet.c:1117 [inline]
 tpacket_rcv+0x1866/0x3340 net/packet/af_packet.c:2282
 dev_queue_xmit_nit+0x891/0xb90 net/core/dev.c:2018
 xmit_one net/core/dev.c:3049 [inline]
 dev_hard_start_xmit+0x16b/0xc10 net/core/dev.c:3069
 __dev_queue_xmit+0x2724/0x34c0 net/core/dev.c:3584
 dev_queue_xmit+0x17/0x20 net/core/dev.c:3617
 neigh_resolve_output+0x679/0xad0 net/core/neighbour.c:1358
 neigh_output include/net/neighbour.h:482 [inline]
 ip6_finish_output2+0xc9c/0x2810 net/ipv6/ip6_output.c:120
 ip6_finish_output+0x5fe/0xbc0 net/ipv6/ip6_output.c:154
 NF_HOOK_COND include/linux/netfilter.h:277 [inline]
 ip6_output+0x227/0x9b0 net/ipv6/ip6_output.c:171
 dst_output include/net/dst.h:444 [inline]
 NF_HOOK include/linux/netfilter.h:288 [inline]
 ndisc_send_skb+0x100d/0x1570 net/ipv6/ndisc.c:491
 ndisc_send_ns+0x3c1/0x8d0 net/ipv6/ndisc.c:633
 addrconf_dad_work+0xbef/0x1340 net/ipv6/addrconf.c:4033
 process_one_work+0xc1e/0x1b50 kernel/workqueue.c:2145
 worker_thread+0x1cc/0x1440 kernel/workqueue.c:2279
 kthread+0x345/0x410 kernel/kthread.c:240
 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:412

The buggy address belongs to the page:
page:ffffea00072d8800 count:0 mapcount:-127 mapping:0000000000000000 index:0xffff8801cb620e80
flags: 0x2fffc0000000000()
raw: 02fffc0000000000 0000000000000000 ffff8801cb620e80 00000000ffffff80
raw: ffffea00072e3820 ffffea0007132d20 0000000000000002 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff8801cb61ff00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
 ffff8801cb61ff80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
>ffff8801cb620000: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
                      ^
 ffff8801cb620080: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
 ffff8801cb620100: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff

Fixes: 2b6867c2ce76 ("net/packet: fix overflow in check for priv area size")
Fixes: dc808110bb62 ("packet: handle too big packets for PACKET_V3")
Fixes: f6fb8f100b80 ("af-packet: TPACKET_V3 flexible buffer implementation.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index acb7b86574cd..60c2a252bdf5 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -4282,7 +4282,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 			goto out;
 		if (po->tp_version >= TPACKET_V3 &&
 		    req->tp_block_size <=
-			  BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv))
+		    BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv) + sizeof(struct tpacket3_hdr))
 			goto out;
 		if (unlikely(req->tp_frame_size < po->tp_hdrlen +
 					po->tp_reserve))
-- 
2.17.1


From bd9d54e4a2801dd08d5c3c1517415dffcb5f11d5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 5 Jun 2018 09:25:19 -0700
Subject: [PATCH 08/13] rtnetlink: validate attributes in do_setlink()

[ Upstream commit 644c7eebbfd59e72982d11ec6cc7d39af12450ae ]

It seems that rtnl_group_changelink() can call do_setlink
while a prior call to validate_linkmsg(dev = NULL, ...) could
not validate IFLA_ADDRESS / IFLA_BROADCAST

Make sure do_setlink() calls validate_linkmsg() instead
of letting its callers having this responsibility.

With help from Dmitry Vyukov, thanks a lot !

BUG: KMSAN: uninit-value in is_valid_ether_addr include/linux/etherdevice.h:199 [inline]
BUG: KMSAN: uninit-value in eth_prepare_mac_addr_change net/ethernet/eth.c:275 [inline]
BUG: KMSAN: uninit-value in eth_mac_addr+0x203/0x2b0 net/ethernet/eth.c:308
CPU: 1 PID: 8695 Comm: syz-executor3 Not tainted 4.17.0-rc5+ #103
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x185/0x1d0 lib/dump_stack.c:113
 kmsan_report+0x149/0x260 mm/kmsan/kmsan.c:1084
 __msan_warning_32+0x6e/0xc0 mm/kmsan/kmsan_instr.c:686
 is_valid_ether_addr include/linux/etherdevice.h:199 [inline]
 eth_prepare_mac_addr_change net/ethernet/eth.c:275 [inline]
 eth_mac_addr+0x203/0x2b0 net/ethernet/eth.c:308
 dev_set_mac_address+0x261/0x530 net/core/dev.c:7157
 do_setlink+0xbc3/0x5fc0 net/core/rtnetlink.c:2317
 rtnl_group_changelink net/core/rtnetlink.c:2824 [inline]
 rtnl_newlink+0x1fe9/0x37a0 net/core/rtnetlink.c:2976
 rtnetlink_rcv_msg+0xa32/0x1560 net/core/rtnetlink.c:4646
 netlink_rcv_skb+0x378/0x600 net/netlink/af_netlink.c:2448
 rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:4664
 netlink_unicast_kernel net/netlink/af_netlink.c:1310 [inline]
 netlink_unicast+0x1678/0x1750 net/netlink/af_netlink.c:1336
 netlink_sendmsg+0x104f/0x1350 net/netlink/af_netlink.c:1901
 sock_sendmsg_nosec net/socket.c:629 [inline]
 sock_sendmsg net/socket.c:639 [inline]
 ___sys_sendmsg+0xec0/0x1310 net/socket.c:2117
 __sys_sendmsg net/socket.c:2155 [inline]
 __do_sys_sendmsg net/socket.c:2164 [inline]
 __se_sys_sendmsg net/socket.c:2162 [inline]
 __x64_sys_sendmsg+0x331/0x460 net/socket.c:2162
 do_syscall_64+0x152/0x230 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x455a09
RSP: 002b:00007fc07480ec68 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 00007fc07480f6d4 RCX: 0000000000455a09
RDX: 0000000000000000 RSI: 00000000200003c0 RDI: 0000000000000014
RBP: 000000000072bea0 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff
R13: 00000000000005d0 R14: 00000000006fdc20 R15: 0000000000000000

Uninit was stored to memory at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:279 [inline]
 kmsan_save_stack mm/kmsan/kmsan.c:294 [inline]
 kmsan_internal_chain_origin+0x12b/0x210 mm/kmsan/kmsan.c:685
 kmsan_memcpy_origins+0x11d/0x170 mm/kmsan/kmsan.c:527
 __msan_memcpy+0x109/0x160 mm/kmsan/kmsan_instr.c:478
 do_setlink+0xb84/0x5fc0 net/core/rtnetlink.c:2315
 rtnl_group_changelink net/core/rtnetlink.c:2824 [inline]
 rtnl_newlink+0x1fe9/0x37a0 net/core/rtnetlink.c:2976
 rtnetlink_rcv_msg+0xa32/0x1560 net/core/rtnetlink.c:4646
 netlink_rcv_skb+0x378/0x600 net/netlink/af_netlink.c:2448
 rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:4664
 netlink_unicast_kernel net/netlink/af_netlink.c:1310 [inline]
 netlink_unicast+0x1678/0x1750 net/netlink/af_netlink.c:1336
 netlink_sendmsg+0x104f/0x1350 net/netlink/af_netlink.c:1901
 sock_sendmsg_nosec net/socket.c:629 [inline]
 sock_sendmsg net/socket.c:639 [inline]
 ___sys_sendmsg+0xec0/0x1310 net/socket.c:2117
 __sys_sendmsg net/socket.c:2155 [inline]
 __do_sys_sendmsg net/socket.c:2164 [inline]
 __se_sys_sendmsg net/socket.c:2162 [inline]
 __x64_sys_sendmsg+0x331/0x460 net/socket.c:2162
 do_syscall_64+0x152/0x230 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:279 [inline]
 kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:189
 kmsan_kmalloc+0x94/0x100 mm/kmsan/kmsan.c:315
 kmsan_slab_alloc+0x10/0x20 mm/kmsan/kmsan.c:322
 slab_post_alloc_hook mm/slab.h:446 [inline]
 slab_alloc_node mm/slub.c:2753 [inline]
 __kmalloc_node_track_caller+0xb32/0x11b0 mm/slub.c:4395
 __kmalloc_reserve net/core/skbuff.c:138 [inline]
 __alloc_skb+0x2cb/0x9e0 net/core/skbuff.c:206
 alloc_skb include/linux/skbuff.h:988 [inline]
 netlink_alloc_large_skb net/netlink/af_netlink.c:1182 [inline]
 netlink_sendmsg+0x76e/0x1350 net/netlink/af_netlink.c:1876
 sock_sendmsg_nosec net/socket.c:629 [inline]
 sock_sendmsg net/socket.c:639 [inline]
 ___sys_sendmsg+0xec0/0x1310 net/socket.c:2117
 __sys_sendmsg net/socket.c:2155 [inline]
 __do_sys_sendmsg net/socket.c:2164 [inline]
 __se_sys_sendmsg net/socket.c:2162 [inline]
 __x64_sys_sendmsg+0x331/0x460 net/socket.c:2162
 do_syscall_64+0x152/0x230 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: e7ed828f10bd ("netlink: support setting devgroup parameters")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 45936922d7e2..19f6ab5de6e1 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2256,6 +2256,10 @@ static int do_setlink(const struct sk_buff *skb,
 	const struct net_device_ops *ops = dev->netdev_ops;
 	int err;
 
+	err = validate_linkmsg(dev, tb);
+	if (err < 0)
+		return err;
+
 	if (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD] || tb[IFLA_IF_NETNSID]) {
 		struct net *net = rtnl_link_get_net_capable(skb, dev_net(dev),
 							    tb, CAP_NET_ADMIN);
@@ -2619,10 +2623,6 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 		goto errout;
 	}
 
-	err = validate_linkmsg(dev, tb);
-	if (err < 0)
-		goto errout;
-
 	err = do_setlink(skb, dev, ifm, extack, tb, ifname, 0);
 errout:
 	return err;
-- 
2.17.1


From 2f9102ca5323fc9e4bf6422027ee5d7d194f59c7 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 5 Jun 2018 12:16:58 +0800
Subject: [PATCH 09/13] sctp: not allow transport timeout value less than HZ/5
 for hb_timer

[ Upstream commit 1d88ba1ebb2763aa86172cd7ca05dedbeccc0d35 ]

syzbot reported a rcu_sched self-detected stall on CPU which is caused
by too small value set on rto_min with SCTP_RTOINFO sockopt. With this
value, hb_timer will get stuck there, as in its timer handler it starts
this timer again with this value, then goes to the timer handler again.

This problem is there since very beginning, and thanks to Eric for the
reproducer shared from a syzbot mail.

This patch fixes it by not allowing sctp_transport_timeout to return a
smaller value than HZ/5 for hb_timer, which is based on TCP's min rto.

Note that it doesn't fix this issue by limiting rto_min, as some users
are still using small rto and no proper value was found for it yet.

Reported-by: syzbot+3dcd59a1f907245f891f@syzkaller.appspotmail.com
Suggested-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/transport.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index 47f82bd794d9..03fc2c427aca 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -634,7 +634,7 @@ unsigned long sctp_transport_timeout(struct sctp_transport *trans)
 	    trans->state != SCTP_PF)
 		timeout += trans->hbinterval;
 
-	return timeout;
+	return max_t(unsigned long, timeout, HZ / 5);
 }
 
 /* Reset transport variables to their initial values */
-- 
2.17.1


From 00a2d513757409053fbb4aacb007365ec0f0a47d Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Mon, 4 Jun 2018 17:46:01 +0300
Subject: [PATCH 10/13] team: use netdev_features_t instead of u32

[ Upstream commit 25ea66544bfd1d9df1b7e1502f8717e85fa1e6e6 ]

This code was introduced in 2011 around the same time that we made
netdev_features_t a u64 type.  These days a u32 is not big enough to
hold all the potential features.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index ddb6bf85a59c..e141563a4682 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1004,7 +1004,8 @@ static void team_port_disable(struct team *team,
 static void __team_compute_features(struct team *team)
 {
 	struct team_port *port;
-	u32 vlan_features = TEAM_VLAN_FEATURES & NETIF_F_ALL_FOR_ALL;
+	netdev_features_t vlan_features = TEAM_VLAN_FEATURES &
+					  NETIF_F_ALL_FOR_ALL;
 	netdev_features_t enc_features  = TEAM_ENC_FEATURES;
 	unsigned short max_hard_header_len = ETH_HLEN;
 	unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE |
-- 
2.17.1


From 8b36b6e42074bb6be0938e7b987e97f1143dca19 Mon Sep 17 00:00:00 2001
From: Stephen Suryaputra <ssuryaextr@gmail.com>
Date: Fri, 1 Jun 2018 00:05:21 -0400
Subject: [PATCH 11/13] vrf: check the original netdevice for generating
 redirect

[ Upstream commit 2f17becfbea5e9a0529b51da7345783e96e69516 ]

Use the right device to determine if redirect should be sent especially
when using vrf. Same as well as when sending the redirect.

Signed-off-by: Stephen Suryaputra <ssuryaextr@gmail.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_output.c | 3 ++-
 net/ipv6/ndisc.c      | 6 ++++++
 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 7b6d1689087b..af49f6cb5d3e 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -507,7 +507,8 @@ int ip6_forward(struct sk_buff *skb)
 	   send redirects to source routed frames.
 	   We don't send redirects to frames decapsulated from IPsec.
 	 */
-	if (skb->dev == dst->dev && opt->srcrt == 0 && !skb_sec_path(skb)) {
+	if (IP6CB(skb)->iif == dst->dev->ifindex &&
+	    opt->srcrt == 0 && !skb_sec_path(skb)) {
 		struct in6_addr *target = NULL;
 		struct inet_peer *peer;
 		struct rt6_info *rt;
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 9de4dfb126ba..525051a886bc 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1576,6 +1576,12 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
 	   ops_data_buf[NDISC_OPS_REDIRECT_DATA_SPACE], *ops_data = NULL;
 	bool ret;
 
+	if (netif_is_l3_master(skb->dev)) {
+		dev = __dev_get_by_index(dev_net(skb->dev), IPCB(skb)->iif);
+		if (!dev)
+			return;
+	}
+
 	if (ipv6_get_lladdr(dev, &saddr_buf, IFA_F_TENTATIVE)) {
 		ND_PRINTK(2, warn, "Redirect: no link-local address on %s\n",
 			  dev->name);
-- 
2.17.1


From b969815a526c90488d0749c09b81c64193848ee3 Mon Sep 17 00:00:00 2001
From: Arun Parameswaran <arun.parameswaran@broadcom.com>
Date: Tue, 5 Jun 2018 13:38:12 -0700
Subject: [PATCH 12/13] net: dsa: b53: Fix for brcm tag issue in Cygnus SoC
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 5040cc990cbac98733df4d58fdeac5bbdab15b49 ]

In the Broadcom Cygnus SoC, the brcm tag needs to be inserted
in between the mac address and the ether type (should use
'DSA_PROTO_TAG_BRCM') for the packets sent to the internal
b53 switch.

Since the Cygnus was added with the BCM58XX device id and the
BCM58XX uses 'DSA_PROTO_TAG_BRCM_PREPEND', the data path is
broken, due to the incorrect brcm tag location.

Add a new b53 device id (BCM583XX) for Cygnus family to fix the
issue. Add the new device id to the BCM58XX family as Cygnus
is similar to the BCM58XX in most other functionalities.

Fixes: 11606039604c ("net: dsa: b53: Support prepended Broadcom tags")

Signed-off-by: Arun Parameswaran <arun.parameswaran@broadcom.com>
Acked-by: Scott Branden <scott.branden@broadcom.com>
Reported-by: Clément Péron <peron.clem@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Tested-by: Clément Péron <peron.clem@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/b53/b53_common.c | 15 ++++++++++++++-
 drivers/net/dsa/b53/b53_priv.h   |  2 ++
 drivers/net/dsa/b53/b53_srab.c   |  4 ++--
 3 files changed, 18 insertions(+), 3 deletions(-)

diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 3da5fca77cbd..bbc6cc609ec3 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -684,7 +684,8 @@ static int b53_switch_reset(struct b53_device *dev)
 	 * still use this driver as a library and need to perform the reset
 	 * earlier.
 	 */
-	if (dev->chip_id == BCM58XX_DEVICE_ID) {
+	if (dev->chip_id == BCM58XX_DEVICE_ID ||
+	    dev->chip_id == BCM583XX_DEVICE_ID) {
 		b53_read8(dev, B53_CTRL_PAGE, B53_SOFTRESET, &reg);
 		reg |= SW_RST | EN_SW_RST | EN_CH_RST;
 		b53_write8(dev, B53_CTRL_PAGE, B53_SOFTRESET, reg);
@@ -1879,6 +1880,18 @@ static const struct b53_chip_data b53_switch_chips[] = {
 		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
 		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
 	},
+	{
+		.chip_id = BCM583XX_DEVICE_ID,
+		.dev_name = "BCM583xx/11360",
+		.vlans = 4096,
+		.enabled_ports = 0x103,
+		.arl_entries = 4,
+		.cpu_port = B53_CPU_PORT,
+		.vta_regs = B53_VTA_REGS,
+		.duplex_reg = B53_DUPLEX_STAT_GE,
+		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
+		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+	},
 	{
 		.chip_id = BCM7445_DEVICE_ID,
 		.dev_name = "BCM7445",
diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h
index 3b57f47d0e79..b232aaae20aa 100644
--- a/drivers/net/dsa/b53/b53_priv.h
+++ b/drivers/net/dsa/b53/b53_priv.h
@@ -62,6 +62,7 @@ enum {
 	BCM53018_DEVICE_ID = 0x53018,
 	BCM53019_DEVICE_ID = 0x53019,
 	BCM58XX_DEVICE_ID = 0x5800,
+	BCM583XX_DEVICE_ID = 0x58300,
 	BCM7445_DEVICE_ID = 0x7445,
 	BCM7278_DEVICE_ID = 0x7278,
 };
@@ -181,6 +182,7 @@ static inline int is5301x(struct b53_device *dev)
 static inline int is58xx(struct b53_device *dev)
 {
 	return dev->chip_id == BCM58XX_DEVICE_ID ||
+		dev->chip_id == BCM583XX_DEVICE_ID ||
 		dev->chip_id == BCM7445_DEVICE_ID ||
 		dev->chip_id == BCM7278_DEVICE_ID;
 }
diff --git a/drivers/net/dsa/b53/b53_srab.c b/drivers/net/dsa/b53/b53_srab.c
index c37ffd1b6833..8247481eaa06 100644
--- a/drivers/net/dsa/b53/b53_srab.c
+++ b/drivers/net/dsa/b53/b53_srab.c
@@ -364,7 +364,7 @@ static const struct of_device_id b53_srab_of_match[] = {
 	{ .compatible = "brcm,bcm53018-srab" },
 	{ .compatible = "brcm,bcm53019-srab" },
 	{ .compatible = "brcm,bcm5301x-srab" },
-	{ .compatible = "brcm,bcm11360-srab", .data = (void *)BCM58XX_DEVICE_ID },
+	{ .compatible = "brcm,bcm11360-srab", .data = (void *)BCM583XX_DEVICE_ID },
 	{ .compatible = "brcm,bcm58522-srab", .data = (void *)BCM58XX_DEVICE_ID },
 	{ .compatible = "brcm,bcm58525-srab", .data = (void *)BCM58XX_DEVICE_ID },
 	{ .compatible = "brcm,bcm58535-srab", .data = (void *)BCM58XX_DEVICE_ID },
@@ -372,7 +372,7 @@ static const struct of_device_id b53_srab_of_match[] = {
 	{ .compatible = "brcm,bcm58623-srab", .data = (void *)BCM58XX_DEVICE_ID },
 	{ .compatible = "brcm,bcm58625-srab", .data = (void *)BCM58XX_DEVICE_ID },
 	{ .compatible = "brcm,bcm88312-srab", .data = (void *)BCM58XX_DEVICE_ID },
-	{ .compatible = "brcm,cygnus-srab", .data = (void *)BCM58XX_DEVICE_ID },
+	{ .compatible = "brcm,cygnus-srab", .data = (void *)BCM583XX_DEVICE_ID },
 	{ .compatible = "brcm,nsp-srab", .data = (void *)BCM58XX_DEVICE_ID },
 	{ /* sentinel */ },
 };
-- 
2.17.1


From 93de88594306e6944c7c356c891e9206658ec9b0 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 5 Jun 2018 15:02:00 +0200
Subject: [PATCH 13/13] ipmr: fix error path when ipmr_new_table fails

[ Upstream commit e783bb00ad86d9d1f01d9d3a750713070036358e ]

commit 0bbbf0e7d0e7 ("ipmr, ip6mr: Unite creation of new mr_table")
refactored ipmr_new_table, so that it now returns NULL when
mr_table_alloc fails. Unfortunately, all callers of ipmr_new_table
expect an ERR_PTR.

This can result in NULL deref, for example when ipmr_rules_exit calls
ipmr_free_table with NULL net->ipv4.mrt in the
!CONFIG_IP_MROUTE_MULTIPLE_TABLES version.

This patch makes mr_table_alloc return errors, and changes
ip6mr_new_table and its callers to return/expect error pointers as
well. It also removes the version of mr_table_alloc defined under
!CONFIG_IP_MROUTE_COMMON, since it is never used.

Fixes: 0bbbf0e7d0e7 ("ipmr, ip6mr: Unite creation of new mr_table")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/mroute_base.h | 10 ----------
 net/ipv4/ipmr_base.c        |  8 +++++---
 net/ipv6/ip6mr.c            | 18 ++++++++++++------
 3 files changed, 17 insertions(+), 19 deletions(-)

diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h
index d617fe45543e..d633f737b3c6 100644
--- a/include/linux/mroute_base.h
+++ b/include/linux/mroute_base.h
@@ -307,16 +307,6 @@ static inline void vif_device_init(struct vif_device *v,
 {
 }
 
-static inline void *
-mr_table_alloc(struct net *net, u32 id,
-	       struct mr_table_ops *ops,
-	       void (*expire_func)(struct timer_list *t),
-	       void (*table_set)(struct mr_table *mrt,
-				 struct net *net))
-{
-	return NULL;
-}
-
 static inline void *mr_mfc_find_parent(struct mr_table *mrt,
 				       void *hasharg, int parent)
 {
diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c
index 30221701614c..cafb0506c8c9 100644
--- a/net/ipv4/ipmr_base.c
+++ b/net/ipv4/ipmr_base.c
@@ -35,17 +35,19 @@ mr_table_alloc(struct net *net, u32 id,
 				 struct net *net))
 {
 	struct mr_table *mrt;
+	int err;
 
 	mrt = kzalloc(sizeof(*mrt), GFP_KERNEL);
 	if (!mrt)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	mrt->id = id;
 	write_pnet(&mrt->net, net);
 
 	mrt->ops = *ops;
-	if (rhltable_init(&mrt->mfc_hash, mrt->ops.rht_params)) {
+	err = rhltable_init(&mrt->mfc_hash, mrt->ops.rht_params);
+	if (err) {
 		kfree(mrt);
-		return NULL;
+		return ERR_PTR(err);
 	}
 	INIT_LIST_HEAD(&mrt->mfc_cache_list);
 	INIT_LIST_HEAD(&mrt->mfc_unres_queue);
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 42eca2689c3b..37936671dcb3 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -227,8 +227,8 @@ static int __net_init ip6mr_rules_init(struct net *net)
 	INIT_LIST_HEAD(&net->ipv6.mr6_tables);
 
 	mrt = ip6mr_new_table(net, RT6_TABLE_DFLT);
-	if (!mrt) {
-		err = -ENOMEM;
+	if (IS_ERR(mrt)) {
+		err = PTR_ERR(mrt);
 		goto err1;
 	}
 
@@ -301,8 +301,13 @@ static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6,
 
 static int __net_init ip6mr_rules_init(struct net *net)
 {
-	net->ipv6.mrt6 = ip6mr_new_table(net, RT6_TABLE_DFLT);
-	return net->ipv6.mrt6 ? 0 : -ENOMEM;
+	struct mr_table *mrt;
+
+	mrt = ip6mr_new_table(net, RT6_TABLE_DFLT);
+	if (IS_ERR(mrt))
+		return PTR_ERR(mrt);
+	net->ipv6.mrt6 = mrt;
+	return 0;
 }
 
 static void __net_exit ip6mr_rules_exit(struct net *net)
@@ -1757,8 +1762,9 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
 
 		rtnl_lock();
 		ret = 0;
-		if (!ip6mr_new_table(net, v))
-			ret = -ENOMEM;
+		mrt = ip6mr_new_table(net, v);
+		if (IS_ERR(mrt))
+			ret = PTR_ERR(mrt);
 		else
 			raw6_sk(sk)->ip6mr_table = v;
 		rtnl_unlock();
-- 
2.17.1

Re: [PATCHES] Networking

[Greg KH]

On Thu, Jun 07, 2018 at 10:18:39PM -0400, David Miller wrote:
> 
> Please queue up the following netwokring bug fixes for
> v4.16 and v4.17 -stable, respectively.

Thanks so much for these, all now queued up.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 93 bytes --]


Please queue up the following networking bug fixes for 4.16 and
4.17 -stable, respectively.

[-- Attachment #2: net_416.mbox --]
[-- Type: Application/Octet-Stream, Size: 39039 bytes --]

From 0a7a10fd2e60800d8ed79c6dfabf6fba84a4cb80 Mon Sep 17 00:00:00 2001
From: Xiangning Yu <yuxiangning@gmail.com>
Date: Thu, 7 Jun 2018 13:39:59 +0800
Subject: [PATCH 01/12] bonding: re-evaluate force_primary when the primary
 slave name changes

[ Upstream commit eb55bbf865d9979098c6a7a17cbdb41237ece951 ]

There is a timing issue under active-standy mode, when bond_enslave() is
called, bond->params.primary might not be initialized yet.

Any time the primary slave string changes, bond->force_primary should be
set to true to make sure the primary becomes the active slave.

Signed-off-by: Xiangning Yu <yuxiangning@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_options.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 58c705f24f96..b594bae1adbd 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -1142,6 +1142,7 @@ static int bond_option_primary_set(struct bonding *bond,
 				   slave->dev->name);
 			rcu_assign_pointer(bond->primary_slave, slave);
 			strcpy(bond->params.primary, slave->dev->name);
+			bond->force_primary = true;
 			bond_select_active_slave(bond);
 			goto out;
 		}
-- 
2.17.1


From e18b9383b929e8e6900a669704c9dc0a5b57abf6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Fri, 8 Jun 2018 09:15:24 +0200
Subject: [PATCH 02/12] cdc_ncm: avoid padding beyond end of skb
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 49c2c3f246e2fc3009039e31a826333dcd0283cd ]

Commit 4a0e3e989d66 ("cdc_ncm: Add support for moving NDP to end
of NCM frame") added logic to reserve space for the NDP at the
end of the NTB/skb.  This reservation did not take the final
alignment of the NDP into account, causing us to reserve too
little space. Additionally the padding prior to NDP addition did
not ensure there was enough space for the NDP.

The NTB/skb with the NDP appended would then exceed the configured
max size. This caused the final padding of the NTB to use a
negative count, padding to almost INT_MAX, and resulting in:

[60103.825970] BUG: unable to handle kernel paging request at ffff9641f2004000
[60103.825998] IP: __memset+0x24/0x30
[60103.826001] PGD a6a06067 P4D a6a06067 PUD 4f65a063 PMD 72003063 PTE 0
[60103.826013] Oops: 0002 [#1] SMP NOPTI
[60103.826018] Modules linked in: (removed(
[60103.826158] CPU: 0 PID: 5990 Comm: Chrome_DevTools Tainted: G           O 4.14.0-3-amd64 #1 Debian 4.14.17-1
[60103.826162] Hardware name: LENOVO 20081 BIOS 41CN28WW(V2.04) 05/03/2012
[60103.826166] task: ffff964193484fc0 task.stack: ffffb2890137c000
[60103.826171] RIP: 0010:__memset+0x24/0x30
[60103.826174] RSP: 0000:ffff964316c03b68 EFLAGS: 00010216
[60103.826178] RAX: 0000000000000000 RBX: 00000000fffffffd RCX: 000000001ffa5000
[60103.826181] RDX: 0000000000000005 RSI: 0000000000000000 RDI: ffff9641f2003ffc
[60103.826184] RBP: ffff964192f6c800 R08: 00000000304d434e R09: ffff9641f1d2c004
[60103.826187] R10: 0000000000000002 R11: 00000000000005ae R12: ffff9642e6957a80
[60103.826190] R13: ffff964282ff2ee8 R14: 000000000000000d R15: ffff9642e4843900
[60103.826194] FS:  00007f395aaf6700(0000) GS:ffff964316c00000(0000) knlGS:0000000000000000
[60103.826197] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[60103.826200] CR2: ffff9641f2004000 CR3: 0000000013b0c000 CR4: 00000000000006f0
[60103.826204] Call Trace:
[60103.826212]  <IRQ>
[60103.826225]  cdc_ncm_fill_tx_frame+0x5e3/0x740 [cdc_ncm]
[60103.826236]  cdc_ncm_tx_fixup+0x57/0x70 [cdc_ncm]
[60103.826246]  usbnet_start_xmit+0x5d/0x710 [usbnet]
[60103.826254]  ? netif_skb_features+0x119/0x250
[60103.826259]  dev_hard_start_xmit+0xa1/0x200
[60103.826267]  sch_direct_xmit+0xf2/0x1b0
[60103.826273]  __dev_queue_xmit+0x5e3/0x7c0
[60103.826280]  ? ip_finish_output2+0x263/0x3c0
[60103.826284]  ip_finish_output2+0x263/0x3c0
[60103.826289]  ? ip_output+0x6c/0xe0
[60103.826293]  ip_output+0x6c/0xe0
[60103.826298]  ? ip_forward_options+0x1a0/0x1a0
[60103.826303]  tcp_transmit_skb+0x516/0x9b0
[60103.826309]  tcp_write_xmit+0x1aa/0xee0
[60103.826313]  ? sch_direct_xmit+0x71/0x1b0
[60103.826318]  tcp_tasklet_func+0x177/0x180
[60103.826325]  tasklet_action+0x5f/0x110
[60103.826332]  __do_softirq+0xde/0x2b3
[60103.826337]  irq_exit+0xae/0xb0
[60103.826342]  do_IRQ+0x81/0xd0
[60103.826347]  common_interrupt+0x98/0x98
[60103.826351]  </IRQ>
[60103.826355] RIP: 0033:0x7f397bdf2282
[60103.826358] RSP: 002b:00007f395aaf57d8 EFLAGS: 00000206 ORIG_RAX: ffffffffffffff6e
[60103.826362] RAX: 0000000000000000 RBX: 00002f07bc6d0900 RCX: 00007f39752d7fe7
[60103.826365] RDX: 0000000000000022 RSI: 0000000000000147 RDI: 00002f07baea02c0
[60103.826368] RBP: 0000000000000001 R08: 0000000000000000 R09: 0000000000000000
[60103.826371] R10: 00000000ffffffff R11: 0000000000000000 R12: 00002f07baea02c0
[60103.826373] R13: 00002f07bba227a0 R14: 00002f07bc6d090c R15: 0000000000000000
[60103.826377] Code: 90 90 90 90 90 90 90 0f 1f 44 00 00 49 89 f9 48 89 d1 83
e2 07 48 c1 e9 03 40 0f b6 f6 48 b8 01 01 01 01 01 01 01 01 48 0f af c6 <f3> 48
ab 89 d1 f3 aa 4c 89 c8 c3 90 49 89 f9 40 88 f0 48 89 d1
[60103.826442] RIP: __memset+0x24/0x30 RSP: ffff964316c03b68
[60103.826444] CR2: ffff9641f2004000

Commit e1069bbfcf3b ("net: cdc_ncm: Reduce memory use when kernel
memory low") made this bug much more likely to trigger by reducing
the NTB size under memory pressure.

Link: https://bugs.debian.org/893393
Reported-by: Горбешко Богдан <bodqhrohro@gmail.com>
Reported-and-tested-by: Dennis Wassenberg <dennis.wassenberg@secunet.com>
Cc: Enrico Mioso <mrkiko.rs@gmail.com>
Fixes: 4a0e3e989d66 ("cdc_ncm: Add support for moving NDP to end of NCM frame")
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ncm.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 9e1b74590682..f5316ab68a0a 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -1124,7 +1124,7 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign)
 	 * accordingly. Otherwise, we should check here.
 	 */
 	if (ctx->drvflags & CDC_NCM_FLAG_NDP_TO_END)
-		delayed_ndp_size = ctx->max_ndp_size;
+		delayed_ndp_size = ALIGN(ctx->max_ndp_size, ctx->tx_ndp_modulus);
 	else
 		delayed_ndp_size = 0;
 
@@ -1285,7 +1285,7 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign)
 	/* If requested, put NDP at end of frame. */
 	if (ctx->drvflags & CDC_NCM_FLAG_NDP_TO_END) {
 		nth16 = (struct usb_cdc_ncm_nth16 *)skb_out->data;
-		cdc_ncm_align_tail(skb_out, ctx->tx_ndp_modulus, 0, ctx->tx_curr_size);
+		cdc_ncm_align_tail(skb_out, ctx->tx_ndp_modulus, 0, ctx->tx_curr_size - ctx->max_ndp_size);
 		nth16->wNdpIndex = cpu_to_le16(skb_out->len);
 		skb_put_data(skb_out, ctx->delayed_ndp16, ctx->max_ndp_size);
 
-- 
2.17.1


From 85b337df375673304fd302e963cade25d547b42d Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Mon, 11 Jun 2018 02:02:54 +0300
Subject: [PATCH 03/12] ipv6: allow PMTU exceptions to local routes

[ Upstream commit 0975764684487bf3f7a47eef009e750ea41bd514 ]

IPVS setups with local client and remote tunnel server need
to create exception for the local virtual IP. What we do is to
change PMTU from 64KB (on "lo") to 1460 in the common case.

Suggested-by: Martin KaFai Lau <kafai@fb.com>
Fixes: 45e4fd26683c ("ipv6: Only create RTF_CACHE routes after encountering pmtu exception")
Fixes: 7343ff31ebf0 ("ipv6: Don't create clones of host routes.")
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Acked-by: David Ahern <dsahern@gmail.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 8f749742f11f..0cb580cd5f00 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2077,9 +2077,6 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
 	const struct in6_addr *daddr, *saddr;
 	struct rt6_info *rt6 = (struct rt6_info *)dst;
 
-	if (rt6->rt6i_flags & RTF_LOCAL)
-		return;
-
 	if (dst_metric_locked(dst, RTAX_MTU))
 		return;
 
-- 
2.17.1


From e69155c885855b56f7c1a5bcd635005cf82038ff Mon Sep 17 00:00:00 2001
From: Zhouyang Jia <jiazhouyang09@gmail.com>
Date: Mon, 11 Jun 2018 13:26:35 +0800
Subject: [PATCH 04/12] net: dsa: add error handling for pskb_trim_rcsum

[ Upstream commit 349b71d6f427ff8211adf50839dbbff3f27c1805 ]

When pskb_trim_rcsum fails, the lack of error-handling code may
cause unexpected results.

This patch adds error-handling code after calling pskb_trim_rcsum.

Signed-off-by: Zhouyang Jia <jiazhouyang09@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/tag_trailer.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c
index 7d20e1f3de28..56197f0d9608 100644
--- a/net/dsa/tag_trailer.c
+++ b/net/dsa/tag_trailer.c
@@ -75,7 +75,8 @@ static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev,
 	if (!skb->dev)
 		return NULL;
 
-	pskb_trim_rcsum(skb, skb->len - 4);
+	if (pskb_trim_rcsum(skb, skb->len - 4))
+		return NULL;
 
 	return skb;
 }
-- 
2.17.1


From 968d3a62384fa92e1ce53eeb91fb3c3b6b4642c3 Mon Sep 17 00:00:00 2001
From: Alvaro Gamez Machado <alvaro.gamez@hazent.com>
Date: Fri, 8 Jun 2018 12:23:39 +0200
Subject: [PATCH 05/12] net: phy: dp83822: use BMCR_ANENABLE instead of
 BMSR_ANEGCAPABLE for DP83620

[ Upstream commit b718e8c8f4f5920aaddc2e52d5e32f494c91129c ]

DP83620 register set is compatible with the DP83848, but it also supports
100base-FX. When the hardware is configured such as that fiber mode is
enabled, autonegotiation is not possible.

The chip, however, doesn't expose this information via BMSR_ANEGCAPABLE.
Instead, this bit is always set high, even if the particular hardware
configuration makes it so that auto negotiation is not possible [1]. Under
these circumstances, the phy subsystem keeps trying for autonegotiation to
happen, without success.

Hereby, we inspect BMCR_ANENABLE bit after genphy_config_init, which on
reset is set to 0 when auto negotiation is disabled, and so we use this
value instead of BMSR_ANEGCAPABLE.

[1] https://e2e.ti.com/support/interface/ethernet/f/903/p/697165/2571170

Signed-off-by: Alvaro Gamez Machado <alvaro.gamez@hazent.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/dp83848.c | 35 +++++++++++++++++++++++++++++------
 1 file changed, 29 insertions(+), 6 deletions(-)

diff --git a/drivers/net/phy/dp83848.c b/drivers/net/phy/dp83848.c
index cd09c3af2117..6e8e42361fd5 100644
--- a/drivers/net/phy/dp83848.c
+++ b/drivers/net/phy/dp83848.c
@@ -74,6 +74,25 @@ static int dp83848_config_intr(struct phy_device *phydev)
 	return phy_write(phydev, DP83848_MICR, control);
 }
 
+static int dp83848_config_init(struct phy_device *phydev)
+{
+	int err;
+	int val;
+
+	err = genphy_config_init(phydev);
+	if (err < 0)
+		return err;
+
+	/* DP83620 always reports Auto Negotiation Ability on BMSR. Instead,
+	 * we check initial value of BMCR Auto negotiation enable bit
+	 */
+	val = phy_read(phydev, MII_BMCR);
+	if (!(val & BMCR_ANENABLE))
+		phydev->autoneg = AUTONEG_DISABLE;
+
+	return 0;
+}
+
 static struct mdio_device_id __maybe_unused dp83848_tbl[] = {
 	{ TI_DP83848C_PHY_ID, 0xfffffff0 },
 	{ NS_DP83848C_PHY_ID, 0xfffffff0 },
@@ -83,7 +102,7 @@ static struct mdio_device_id __maybe_unused dp83848_tbl[] = {
 };
 MODULE_DEVICE_TABLE(mdio, dp83848_tbl);
 
-#define DP83848_PHY_DRIVER(_id, _name)				\
+#define DP83848_PHY_DRIVER(_id, _name, _config_init)		\
 	{							\
 		.phy_id		= _id,				\
 		.phy_id_mask	= 0xfffffff0,			\
@@ -92,7 +111,7 @@ MODULE_DEVICE_TABLE(mdio, dp83848_tbl);
 		.flags		= PHY_HAS_INTERRUPT,		\
 								\
 		.soft_reset	= genphy_soft_reset,		\
-		.config_init	= genphy_config_init,		\
+		.config_init	= _config_init,			\
 		.suspend	= genphy_suspend,		\
 		.resume		= genphy_resume,		\
 								\
@@ -102,10 +121,14 @@ MODULE_DEVICE_TABLE(mdio, dp83848_tbl);
 	}
 
 static struct phy_driver dp83848_driver[] = {
-	DP83848_PHY_DRIVER(TI_DP83848C_PHY_ID, "TI DP83848C 10/100 Mbps PHY"),
-	DP83848_PHY_DRIVER(NS_DP83848C_PHY_ID, "NS DP83848C 10/100 Mbps PHY"),
-	DP83848_PHY_DRIVER(TI_DP83620_PHY_ID, "TI DP83620 10/100 Mbps PHY"),
-	DP83848_PHY_DRIVER(TLK10X_PHY_ID, "TI TLK10X 10/100 Mbps PHY"),
+	DP83848_PHY_DRIVER(TI_DP83848C_PHY_ID, "TI DP83848C 10/100 Mbps PHY",
+			   genphy_config_init),
+	DP83848_PHY_DRIVER(NS_DP83848C_PHY_ID, "NS DP83848C 10/100 Mbps PHY",
+			   genphy_config_init),
+	DP83848_PHY_DRIVER(TI_DP83620_PHY_ID, "TI DP83620 10/100 Mbps PHY",
+			   dp83848_config_init),
+	DP83848_PHY_DRIVER(TLK10X_PHY_ID, "TI TLK10X 10/100 Mbps PHY",
+			   genphy_config_init),
 };
 module_phy_driver(dp83848_driver);
 
-- 
2.17.1


From 442641276032e48cc4d4080c856f5630d83c82be Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Fri, 8 Jun 2018 05:02:31 +0200
Subject: [PATCH 06/12] net/sched: act_simple: fix parsing of TCA_DEF_DATA

[ Upstream commit 8d499533e0bc02d44283dbdab03142b599b8ba16 ]

use nla_strlcpy() to avoid copying data beyond the length of TCA_DEF_DATA
netlink attribute, in case it is less than SIMP_MAX_DATA and it does not
end with '\0' character.

v2: fix errors in the commit message, thanks Hangbin Liu

Fixes: fa1b1cff3d06 ("net_cls_act: Make act_simple use of netlink policy.")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_simple.c | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index b1f38063ada0..e5685b3debda 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -53,22 +53,22 @@ static void tcf_simp_release(struct tc_action *a)
 	kfree(d->tcfd_defdata);
 }
 
-static int alloc_defdata(struct tcf_defact *d, char *defdata)
+static int alloc_defdata(struct tcf_defact *d, const struct nlattr *defdata)
 {
 	d->tcfd_defdata = kzalloc(SIMP_MAX_DATA, GFP_KERNEL);
 	if (unlikely(!d->tcfd_defdata))
 		return -ENOMEM;
-	strlcpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA);
+	nla_strlcpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA);
 	return 0;
 }
 
-static void reset_policy(struct tcf_defact *d, char *defdata,
+static void reset_policy(struct tcf_defact *d, const struct nlattr *defdata,
 			 struct tc_defact *p)
 {
 	spin_lock_bh(&d->tcf_lock);
 	d->tcf_action = p->action;
 	memset(d->tcfd_defdata, 0, SIMP_MAX_DATA);
-	strlcpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA);
+	nla_strlcpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA);
 	spin_unlock_bh(&d->tcf_lock);
 }
 
@@ -87,7 +87,6 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
 	struct tcf_defact *d;
 	bool exists = false;
 	int ret = 0, err;
-	char *defdata;
 
 	if (nla == NULL)
 		return -EINVAL;
@@ -110,8 +109,6 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
 		return -EINVAL;
 	}
 
-	defdata = nla_data(tb[TCA_DEF_DATA]);
-
 	if (!exists) {
 		ret = tcf_idr_create(tn, parm->index, est, a,
 				     &act_simp_ops, bind, false);
@@ -119,7 +116,7 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
 			return ret;
 
 		d = to_defact(*a);
-		ret = alloc_defdata(d, defdata);
+		ret = alloc_defdata(d, tb[TCA_DEF_DATA]);
 		if (ret < 0) {
 			tcf_idr_release(*a, bind);
 			return ret;
@@ -133,7 +130,7 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
 		if (!ovr)
 			return -EEXIST;
 
-		reset_policy(d, defdata, parm);
+		reset_policy(d, tb[TCA_DEF_DATA], parm);
 	}
 
 	if (ret == ACT_P_CREATED)
-- 
2.17.1


From 0e4f6fddb03e501c8d738b1091af02407f467733 Mon Sep 17 00:00:00 2001
From: Frank van der Linden <fllinden@amazon.com>
Date: Tue, 12 Jun 2018 23:09:37 +0000
Subject: [PATCH 07/12] tcp: verify the checksum of the first data segment in a
 new connection

[ Upstream commit 4fd44a98ffe0d048246efef67ed640fdf2098a62 ]

commit 079096f103fa ("tcp/dccp: install syn_recv requests into ehash
table") introduced an optimization for the handling of child sockets
created for a new TCP connection.

But this optimization passes any data associated with the last ACK of the
connection handshake up the stack without verifying its checksum, because it
calls tcp_child_process(), which in turn calls tcp_rcv_state_process()
directly.  These lower-level processing functions do not do any checksum
verification.

Insert a tcp_checksum_complete call in the TCP_NEW_SYN_RECEIVE path to
fix this.

Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table")
Signed-off-by: Frank van der Linden <fllinden@amazon.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Tested-by: Balbir Singh <bsingharora@gmail.com>
Reviewed-by: Balbir Singh <bsingharora@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c | 4 ++++
 net/ipv6/tcp_ipv6.c | 4 ++++
 2 files changed, 8 insertions(+)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index f8ad397e285e..27e87e96defc 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1680,6 +1680,10 @@ int tcp_v4_rcv(struct sk_buff *skb)
 			reqsk_put(req);
 			goto discard_it;
 		}
+		if (tcp_checksum_complete(skb)) {
+			reqsk_put(req);
+			goto csum_error;
+		}
 		if (unlikely(sk->sk_state != TCP_LISTEN)) {
 			inet_csk_reqsk_queue_drop_and_put(sk, req);
 			goto lookup;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 412139f4eccd..f7a9bd50b0ac 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1459,6 +1459,10 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 			reqsk_put(req);
 			goto discard_it;
 		}
+		if (tcp_checksum_complete(skb)) {
+			reqsk_put(req);
+			goto csum_error;
+		}
 		if (unlikely(sk->sk_state != TCP_LISTEN)) {
 			inet_csk_reqsk_queue_drop_and_put(sk, req);
 			goto lookup;
-- 
2.17.1


From ebec8fcbe481bca38ca05e7d82bc1bf612c0ffb4 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 7 Jun 2018 13:39:49 -0700
Subject: [PATCH 08/12] socket: close race condition between sock_close() and
 sockfs_setattr()

[ Upstream commit 6d8c50dcb029872b298eea68cc6209c866fd3e14 ]

fchownat() doesn't even hold refcnt of fd until it figures out
fd is really needed (otherwise is ignored) and releases it after
it resolves the path. This means sock_close() could race with
sockfs_setattr(), which leads to a NULL pointer dereference
since typically we set sock->sk to NULL in ->release().

As pointed out by Al, this is unique to sockfs. So we can fix this
in socket layer by acquiring inode_lock in sock_close() and
checking against NULL in sockfs_setattr().

sock_release() is called in many places, only the sock_close()
path matters here. And fortunately, this should not affect normal
sock_close() as it is only called when the last fd refcnt is gone.
It only affects sock_close() with a parallel sockfs_setattr() in
progress, which is not common.

Fixes: 86741ec25462 ("net: core: Add a UID field to struct sock.")
Reported-by: shankarapailoor <shankarapailoor@gmail.com>
Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Cc: Lorenzo Colitti <lorenzo@google.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/socket.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/net/socket.c b/net/socket.c
index 08847c3b8c39..26b1fab01daf 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -538,7 +538,10 @@ static int sockfs_setattr(struct dentry *dentry, struct iattr *iattr)
 	if (!err && (iattr->ia_valid & ATTR_UID)) {
 		struct socket *sock = SOCKET_I(d_inode(dentry));
 
-		sock->sk->sk_uid = iattr->ia_uid;
+		if (sock->sk)
+			sock->sk->sk_uid = iattr->ia_uid;
+		else
+			err = -ENOENT;
 	}
 
 	return err;
@@ -587,12 +590,16 @@ EXPORT_SYMBOL(sock_alloc);
  *	an inode not a file.
  */
 
-void sock_release(struct socket *sock)
+static void __sock_release(struct socket *sock, struct inode *inode)
 {
 	if (sock->ops) {
 		struct module *owner = sock->ops->owner;
 
+		if (inode)
+			inode_lock(inode);
 		sock->ops->release(sock);
+		if (inode)
+			inode_unlock(inode);
 		sock->ops = NULL;
 		module_put(owner);
 	}
@@ -606,6 +613,11 @@ void sock_release(struct socket *sock)
 	}
 	sock->file = NULL;
 }
+
+void sock_release(struct socket *sock)
+{
+	__sock_release(sock, NULL);
+}
 EXPORT_SYMBOL(sock_release);
 
 void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags)
@@ -1146,7 +1158,7 @@ static int sock_mmap(struct file *file, struct vm_area_struct *vma)
 
 static int sock_close(struct inode *inode, struct file *filp)
 {
-	sock_release(SOCKET_I(inode));
+	__sock_release(SOCKET_I(inode), inode);
 	return 0;
 }
 
-- 
2.17.1


From c7bfb4bdd75e9ebb0da1e727679563d9e53ddf9b Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 8 Jun 2018 11:35:40 +0200
Subject: [PATCH 09/12] udp: fix rx queue len reported by diag and proc
 interface

[ Upstream commit 6c206b20092a3623184cff9470dba75d21507874 ]

After commit 6b229cf77d68 ("udp: add batching to udp_rmem_release()")
the sk_rmem_alloc field does not measure exactly anymore the
receive queue length, because we batch the rmem release. The issue
is really apparent only after commit 0d4a6608f68c ("udp: do rmem bulk
free even if the rx sk queue is empty"): the user space can easily
check for an empty socket with not-0 queue length reported by the 'ss'
tool or the procfs interface.

We need to use a custom UDP helper to report the correct queue length,
taking into account the forward allocation deficit.

Reported-by: trevor.francis@46labs.com
Fixes: 6b229cf77d68 ("UDP: add batching to udp_rmem_release()")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/transp_v6.h | 11 +++++++++--
 include/net/udp.h       |  5 +++++
 net/ipv4/udp.c          |  2 +-
 net/ipv4/udp_diag.c     |  2 +-
 net/ipv6/datagram.c     |  6 +++---
 net/ipv6/udp.c          |  3 ++-
 6 files changed, 21 insertions(+), 8 deletions(-)

diff --git a/include/net/transp_v6.h b/include/net/transp_v6.h
index c4f5caaf3778..f6a3543e5247 100644
--- a/include/net/transp_v6.h
+++ b/include/net/transp_v6.h
@@ -45,8 +45,15 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk, struct msghdr *msg,
 			  struct flowi6 *fl6, struct ipcm6_cookie *ipc6,
 			  struct sockcm_cookie *sockc);
 
-void ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp,
-			     __u16 srcp, __u16 destp, int bucket);
+void __ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp,
+			       __u16 srcp, __u16 destp, int rqueue, int bucket);
+static inline void
+ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp, __u16 srcp,
+			__u16 destp, int bucket)
+{
+	__ip6_dgram_sock_seq_show(seq, sp, srcp, destp, sk_rmem_alloc_get(sp),
+				  bucket);
+}
 
 #define LOOPBACK4_IPV6 cpu_to_be32(0x7f000006)
 
diff --git a/include/net/udp.h b/include/net/udp.h
index 850a8e581cce..a42523e8e9c9 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -244,6 +244,11 @@ static inline __be16 udp_flow_src_port(struct net *net, struct sk_buff *skb,
 	return htons((((u64) hash * (max - min)) >> 32) + min);
 }
 
+static inline int udp_rqueue_get(struct sock *sk)
+{
+	return sk_rmem_alloc_get(sk) - READ_ONCE(udp_sk(sk)->forward_deficit);
+}
+
 /* net/ipv4/udp.c */
 void udp_destruct_sock(struct sock *sk);
 void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index b6ba51536b37..b20b21577b27 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2710,7 +2710,7 @@ static void udp4_format_sock(struct sock *sp, struct seq_file *f,
 		" %02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %d",
 		bucket, src, srcp, dest, destp, sp->sk_state,
 		sk_wmem_alloc_get(sp),
-		sk_rmem_alloc_get(sp),
+		udp_rqueue_get(sp),
 		0, 0L, 0,
 		from_kuid_munged(seq_user_ns(f), sock_i_uid(sp)),
 		0, sock_i_ino(sp),
diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c
index d0390d844ac8..d9ad986c7b2c 100644
--- a/net/ipv4/udp_diag.c
+++ b/net/ipv4/udp_diag.c
@@ -163,7 +163,7 @@ static int udp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh,
 static void udp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
 		void *info)
 {
-	r->idiag_rqueue = sk_rmem_alloc_get(sk);
+	r->idiag_rqueue = udp_rqueue_get(sk);
 	r->idiag_wqueue = sk_wmem_alloc_get(sk);
 }
 
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index a9f7eca0b6a3..6840abb79a69 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -1025,8 +1025,8 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
 }
 EXPORT_SYMBOL_GPL(ip6_datagram_send_ctl);
 
-void ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp,
-			     __u16 srcp, __u16 destp, int bucket)
+void __ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp,
+			       __u16 srcp, __u16 destp, int rqueue, int bucket)
 {
 	const struct in6_addr *dest, *src;
 
@@ -1042,7 +1042,7 @@ void ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp,
 		   dest->s6_addr32[2], dest->s6_addr32[3], destp,
 		   sp->sk_state,
 		   sk_wmem_alloc_get(sp),
-		   sk_rmem_alloc_get(sp),
+		   rqueue,
 		   0, 0L, 0,
 		   from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)),
 		   0,
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 68d589f8d2b2..908476583b30 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1473,7 +1473,8 @@ int udp6_seq_show(struct seq_file *seq, void *v)
 		struct inet_sock *inet = inet_sk(v);
 		__u16 srcp = ntohs(inet->inet_sport);
 		__u16 destp = ntohs(inet->inet_dport);
-		ip6_dgram_sock_seq_show(seq, v, srcp, destp, bucket);
+		__ip6_dgram_sock_seq_show(seq, v, srcp, destp,
+					  udp_rqueue_get(v), bucket);
 	}
 	return 0;
 }
-- 
2.17.1


From 1e728cc558191c2ef91a61926ba552c8e344538e Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 6 Jun 2018 11:23:01 -0400
Subject: [PATCH 10/12] net: in virtio_net_hdr only add VLAN_HLEN to csum_start
 if payload holds vlan

[ Upstream commit fd3a88625844907151737fc3b4201676effa6d27 ]

Tun, tap, virtio, packet and uml vector all use struct virtio_net_hdr
to communicate packet metadata to userspace.

For skbuffs with vlan, the first two return the packet as it may have
existed on the wire, inserting the VLAN tag in the user buffer.  Then
virtio_net_hdr.csum_start needs to be adjusted by VLAN_HLEN bytes.

Commit f09e2249c4f5 ("macvtap: restore vlan header on user read")
added this feature to macvtap. Commit 3ce9b20f1971 ("macvtap: Fix
csum_start when VLAN tags are present") then fixed up csum_start.

Virtio, packet and uml do not insert the vlan header in the user
buffer.

When introducing virtio_net_hdr_from_skb to deduplicate filling in
the virtio_net_hdr, the variant from macvtap which adds VLAN_HLEN was
applied uniformly, breaking csum offset for packets with vlan on
virtio and packet.

Make insertion of VLAN_HLEN optional. Convert the callers to pass it
when needed.

Fixes: e858fae2b0b8f4 ("virtio_net: use common code for virtio_net_hdr and skb GSO conversion")
Fixes: 1276f24eeef2 ("packet: use common code for virtio_net_hdr and skb GSO conversion")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tap.c          |  5 ++++-
 drivers/net/tun.c          |  3 ++-
 drivers/net/virtio_net.c   |  3 ++-
 include/linux/virtio_net.h | 11 ++++-------
 net/packet/af_packet.c     |  4 ++--
 5 files changed, 14 insertions(+), 12 deletions(-)

diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index 9b6cb780affe..f0f7cd977667 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -774,13 +774,16 @@ static ssize_t tap_put_user(struct tap_queue *q,
 	int total;
 
 	if (q->flags & IFF_VNET_HDR) {
+		int vlan_hlen = skb_vlan_tag_present(skb) ? VLAN_HLEN : 0;
 		struct virtio_net_hdr vnet_hdr;
+
 		vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz);
 		if (iov_iter_count(iter) < vnet_hdr_len)
 			return -EINVAL;
 
 		if (virtio_net_hdr_from_skb(skb, &vnet_hdr,
-					    tap_is_little_endian(q), true))
+					    tap_is_little_endian(q), true,
+					    vlan_hlen))
 			BUG();
 
 		if (copy_to_iter(&vnet_hdr, sizeof(vnet_hdr), iter) !=
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 24e645c86ae7..b3c58890ef33 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -2062,7 +2062,8 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 			return -EINVAL;
 
 		if (virtio_net_hdr_from_skb(skb, &gso,
-					    tun_is_little_endian(tun), true)) {
+					    tun_is_little_endian(tun), true,
+					    vlan_hlen)) {
 			struct skb_shared_info *sinfo = skb_shinfo(skb);
 			pr_err("unexpected GSO type: "
 			       "0x%x, gso_size %d, hdr_len %d\n",
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 8911e3466e61..89bc5cd4d02f 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1358,7 +1358,8 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
 		hdr = skb_vnet_hdr(skb);
 
 	if (virtio_net_hdr_from_skb(skb, &hdr->hdr,
-				    virtio_is_little_endian(vi->vdev), false))
+				    virtio_is_little_endian(vi->vdev), false,
+				    0))
 		BUG();
 
 	if (vi->mergeable_rx_bufs)
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index f144216febc6..9397628a1967 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -58,7 +58,8 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb,
 					  struct virtio_net_hdr *hdr,
 					  bool little_endian,
-					  bool has_data_valid)
+					  bool has_data_valid,
+					  int vlan_hlen)
 {
 	memset(hdr, 0, sizeof(*hdr));   /* no info leak */
 
@@ -83,12 +84,8 @@ static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb,
 
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
-		if (skb_vlan_tag_present(skb))
-			hdr->csum_start = __cpu_to_virtio16(little_endian,
-				skb_checksum_start_offset(skb) + VLAN_HLEN);
-		else
-			hdr->csum_start = __cpu_to_virtio16(little_endian,
-				skb_checksum_start_offset(skb));
+		hdr->csum_start = __cpu_to_virtio16(little_endian,
+			skb_checksum_start_offset(skb) + vlan_hlen);
 		hdr->csum_offset = __cpu_to_virtio16(little_endian,
 				skb->csum_offset);
 	} else if (has_data_valid &&
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index c9432a0ccd56..29102f3639fe 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2037,7 +2037,7 @@ static int packet_rcv_vnet(struct msghdr *msg, const struct sk_buff *skb,
 		return -EINVAL;
 	*len -= sizeof(vnet_hdr);
 
-	if (virtio_net_hdr_from_skb(skb, &vnet_hdr, vio_le(), true))
+	if (virtio_net_hdr_from_skb(skb, &vnet_hdr, vio_le(), true, 0))
 		return -EINVAL;
 
 	return memcpy_to_msg(msg, (void *)&vnet_hdr, sizeof(vnet_hdr));
@@ -2304,7 +2304,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	if (do_vnet) {
 		if (virtio_net_hdr_from_skb(skb, h.raw + macoff -
 					    sizeof(struct virtio_net_hdr),
-					    vio_le(), true)) {
+					    vio_le(), true, 0)) {
 			spin_lock(&sk->sk_receive_queue.lock);
 			goto drop_n_account;
 		}
-- 
2.17.1


From 382e3680de2a0ae3e1c2124af730b368ff0c1e42 Mon Sep 17 00:00:00 2001
From: Dexuan Cui <decui@microsoft.com>
Date: Wed, 6 Jun 2018 21:32:51 +0000
Subject: [PATCH 11/12] hv_netvsc: Fix a network regression after ifdown/ifup

[ Upstream commit 52acf73b6e9a6962045feb2ba5a8921da2201915 ]

Recently people reported the NIC stops working after
"ifdown eth0; ifup eth0". It turns out in this case the TX queues are not
enabled, after the refactoring of the common detach logic: when the NIC
has sub-channels, usually we enable all the TX queues after all
sub-channels are set up: see rndis_set_subchannel() ->
netif_device_attach(), but in the case of "ifdown eth0; ifup eth0" where
the number of channels doesn't change, we also must make sure the TX queues
are enabled. The patch fixes the regression.

Fixes: 7b2ee50c0cd5 ("hv_netvsc: common detach logic")
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/netvsc_drv.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 2a7752c113df..adbfa82b76e9 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -126,8 +126,10 @@ static int netvsc_open(struct net_device *net)
 	}
 
 	rdev = nvdev->extension;
-	if (!rdev->link_state)
+	if (!rdev->link_state) {
 		netif_carrier_on(net);
+		netif_tx_wake_all_queues(net);
+	}
 
 	if (vf_netdev) {
 		/* Setting synthetic device up transparently sets
-- 
2.17.1


From 2f7717e92f413ebc6bc79f3952b3237723c6ad1d Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 15 Jun 2018 03:07:45 +0200
Subject: [PATCH 12/12] tls: fix use-after-free in tls_push_record

[ Upstream commit a447da7d00410278c90d3576782a43f8b675d7be ]

syzkaller managed to trigger a use-after-free in tls like the
following:

  BUG: KASAN: use-after-free in tls_push_record.constprop.15+0x6a2/0x810 [tls]
  Write of size 1 at addr ffff88037aa08000 by task a.out/2317

  CPU: 3 PID: 2317 Comm: a.out Not tainted 4.17.0+ #144
  Hardware name: LENOVO 20FBCTO1WW/20FBCTO1WW, BIOS N1FET47W (1.21 ) 11/28/2016
  Call Trace:
   dump_stack+0x71/0xab
   print_address_description+0x6a/0x280
   kasan_report+0x258/0x380
   ? tls_push_record.constprop.15+0x6a2/0x810 [tls]
   tls_push_record.constprop.15+0x6a2/0x810 [tls]
   tls_sw_push_pending_record+0x2e/0x40 [tls]
   tls_sk_proto_close+0x3fe/0x710 [tls]
   ? tcp_check_oom+0x4c0/0x4c0
   ? tls_write_space+0x260/0x260 [tls]
   ? kmem_cache_free+0x88/0x1f0
   inet_release+0xd6/0x1b0
   __sock_release+0xc0/0x240
   sock_close+0x11/0x20
   __fput+0x22d/0x660
   task_work_run+0x114/0x1a0
   do_exit+0x71a/0x2780
   ? mm_update_next_owner+0x650/0x650
   ? handle_mm_fault+0x2f5/0x5f0
   ? __do_page_fault+0x44f/0xa50
   ? mm_fault_error+0x2d0/0x2d0
   do_group_exit+0xde/0x300
   __x64_sys_exit_group+0x3a/0x50
   do_syscall_64+0x9a/0x300
   ? page_fault+0x8/0x30
   entry_SYSCALL_64_after_hwframe+0x44/0xa9

This happened through fault injection where aead_req allocation in
tls_do_encryption() eventually failed and we returned -ENOMEM from
the function. Turns out that the use-after-free is triggered from
tls_sw_sendmsg() in the second tls_push_record(). The error then
triggers a jump to waiting for memory in sk_stream_wait_memory()
resp. returning immediately in case of MSG_DONTWAIT. What follows is
the trim_both_sgl(sk, orig_size), which drops elements from the sg
list added via tls_sw_sendmsg(). Now the use-after-free gets triggered
when the socket is being closed, where tls_sk_proto_close() callback
is invoked. The tls_complete_pending_work() will figure that there's
a pending closed tls record to be flushed and thus calls into the
tls_push_pending_closed_record() from there. ctx->push_pending_record()
is called from the latter, which is the tls_sw_push_pending_record()
from sw path. This again calls into tls_push_record(). And here the
tls_fill_prepend() will panic since the buffer address has been freed
earlier via trim_both_sgl(). One way to fix it is to move the aead
request allocation out of tls_do_encryption() early into tls_push_record().
This means we don't prep the tls header and advance state to the
TLS_PENDING_CLOSED_RECORD before allocation which could potentially
fail happened. That fixes the issue on my side.

Fixes: 3c4d7559159b ("tls: kernel TLS support")
Reported-by: syzbot+5c74af81c547738e1684@syzkaller.appspotmail.com
Reported-by: syzbot+709f2810a6a05f11d4d3@syzkaller.appspotmail.com
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Dave Watson <davejwatson@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index f26376e954ae..cb0e7d97cdda 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -195,18 +195,12 @@ static void tls_free_both_sg(struct sock *sk)
 }
 
 static int tls_do_encryption(struct tls_context *tls_ctx,
-			     struct tls_sw_context *ctx, size_t data_len,
-			     gfp_t flags)
+			     struct tls_sw_context *ctx,
+			     struct aead_request *aead_req,
+			     size_t data_len)
 {
-	unsigned int req_size = sizeof(struct aead_request) +
-		crypto_aead_reqsize(ctx->aead_send);
-	struct aead_request *aead_req;
 	int rc;
 
-	aead_req = kzalloc(req_size, flags);
-	if (!aead_req)
-		return -ENOMEM;
-
 	ctx->sg_encrypted_data[0].offset += tls_ctx->prepend_size;
 	ctx->sg_encrypted_data[0].length -= tls_ctx->prepend_size;
 
@@ -223,7 +217,6 @@ static int tls_do_encryption(struct tls_context *tls_ctx,
 	ctx->sg_encrypted_data[0].offset -= tls_ctx->prepend_size;
 	ctx->sg_encrypted_data[0].length += tls_ctx->prepend_size;
 
-	kfree(aead_req);
 	return rc;
 }
 
@@ -232,8 +225,14 @@ static int tls_push_record(struct sock *sk, int flags,
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+	struct aead_request *req;
 	int rc;
 
+	req = kzalloc(sizeof(struct aead_request) +
+		      crypto_aead_reqsize(ctx->aead_send), sk->sk_allocation);
+	if (!req)
+		return -ENOMEM;
+
 	sg_mark_end(ctx->sg_plaintext_data + ctx->sg_plaintext_num_elem - 1);
 	sg_mark_end(ctx->sg_encrypted_data + ctx->sg_encrypted_num_elem - 1);
 
@@ -249,15 +248,14 @@ static int tls_push_record(struct sock *sk, int flags,
 	tls_ctx->pending_open_record_frags = 0;
 	set_bit(TLS_PENDING_CLOSED_RECORD, &tls_ctx->flags);
 
-	rc = tls_do_encryption(tls_ctx, ctx, ctx->sg_plaintext_size,
-			       sk->sk_allocation);
+	rc = tls_do_encryption(tls_ctx, ctx, req, ctx->sg_plaintext_size);
 	if (rc < 0) {
 		/* If we are called from write_space and
 		 * we fail, we need to set this SOCK_NOSPACE
 		 * to trigger another write_space in the future.
 		 */
 		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
-		return rc;
+		goto out_req;
 	}
 
 	free_sg(sk, ctx->sg_plaintext_data, &ctx->sg_plaintext_num_elem,
@@ -272,6 +270,8 @@ static int tls_push_record(struct sock *sk, int flags,
 		tls_err_abort(sk);
 
 	tls_advance_record_sn(sk, tls_ctx);
+out_req:
+	kfree(req);
 	return rc;
 }
 
-- 
2.17.1


[-- Attachment #3: net_417.mbox --]
[-- Type: Application/Octet-Stream, Size: 43591 bytes --]

From 30d9b4377e6cc8060133d68c7bceca82d159150d Mon Sep 17 00:00:00 2001
From: Xiangning Yu <yuxiangning@gmail.com>
Date: Thu, 7 Jun 2018 13:39:59 +0800
Subject: [PATCH 01/14] bonding: re-evaluate force_primary when the primary
 slave name changes

[ Upstream commit eb55bbf865d9979098c6a7a17cbdb41237ece951 ]

There is a timing issue under active-standy mode, when bond_enslave() is
called, bond->params.primary might not be initialized yet.

Any time the primary slave string changes, bond->force_primary should be
set to true to make sure the primary becomes the active slave.

Signed-off-by: Xiangning Yu <yuxiangning@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_options.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 58c705f24f96..b594bae1adbd 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -1142,6 +1142,7 @@ static int bond_option_primary_set(struct bonding *bond,
 				   slave->dev->name);
 			rcu_assign_pointer(bond->primary_slave, slave);
 			strcpy(bond->params.primary, slave->dev->name);
+			bond->force_primary = true;
 			bond_select_active_slave(bond);
 			goto out;
 		}
-- 
2.17.1


From f20b4bfe1da84e2c2a9c4514fd5372fab7137f31 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Fri, 8 Jun 2018 09:15:24 +0200
Subject: [PATCH 02/14] cdc_ncm: avoid padding beyond end of skb
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 49c2c3f246e2fc3009039e31a826333dcd0283cd ]

Commit 4a0e3e989d66 ("cdc_ncm: Add support for moving NDP to end
of NCM frame") added logic to reserve space for the NDP at the
end of the NTB/skb.  This reservation did not take the final
alignment of the NDP into account, causing us to reserve too
little space. Additionally the padding prior to NDP addition did
not ensure there was enough space for the NDP.

The NTB/skb with the NDP appended would then exceed the configured
max size. This caused the final padding of the NTB to use a
negative count, padding to almost INT_MAX, and resulting in:

[60103.825970] BUG: unable to handle kernel paging request at ffff9641f2004000
[60103.825998] IP: __memset+0x24/0x30
[60103.826001] PGD a6a06067 P4D a6a06067 PUD 4f65a063 PMD 72003063 PTE 0
[60103.826013] Oops: 0002 [#1] SMP NOPTI
[60103.826018] Modules linked in: (removed(
[60103.826158] CPU: 0 PID: 5990 Comm: Chrome_DevTools Tainted: G           O 4.14.0-3-amd64 #1 Debian 4.14.17-1
[60103.826162] Hardware name: LENOVO 20081 BIOS 41CN28WW(V2.04) 05/03/2012
[60103.826166] task: ffff964193484fc0 task.stack: ffffb2890137c000
[60103.826171] RIP: 0010:__memset+0x24/0x30
[60103.826174] RSP: 0000:ffff964316c03b68 EFLAGS: 00010216
[60103.826178] RAX: 0000000000000000 RBX: 00000000fffffffd RCX: 000000001ffa5000
[60103.826181] RDX: 0000000000000005 RSI: 0000000000000000 RDI: ffff9641f2003ffc
[60103.826184] RBP: ffff964192f6c800 R08: 00000000304d434e R09: ffff9641f1d2c004
[60103.826187] R10: 0000000000000002 R11: 00000000000005ae R12: ffff9642e6957a80
[60103.826190] R13: ffff964282ff2ee8 R14: 000000000000000d R15: ffff9642e4843900
[60103.826194] FS:  00007f395aaf6700(0000) GS:ffff964316c00000(0000) knlGS:0000000000000000
[60103.826197] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[60103.826200] CR2: ffff9641f2004000 CR3: 0000000013b0c000 CR4: 00000000000006f0
[60103.826204] Call Trace:
[60103.826212]  <IRQ>
[60103.826225]  cdc_ncm_fill_tx_frame+0x5e3/0x740 [cdc_ncm]
[60103.826236]  cdc_ncm_tx_fixup+0x57/0x70 [cdc_ncm]
[60103.826246]  usbnet_start_xmit+0x5d/0x710 [usbnet]
[60103.826254]  ? netif_skb_features+0x119/0x250
[60103.826259]  dev_hard_start_xmit+0xa1/0x200
[60103.826267]  sch_direct_xmit+0xf2/0x1b0
[60103.826273]  __dev_queue_xmit+0x5e3/0x7c0
[60103.826280]  ? ip_finish_output2+0x263/0x3c0
[60103.826284]  ip_finish_output2+0x263/0x3c0
[60103.826289]  ? ip_output+0x6c/0xe0
[60103.826293]  ip_output+0x6c/0xe0
[60103.826298]  ? ip_forward_options+0x1a0/0x1a0
[60103.826303]  tcp_transmit_skb+0x516/0x9b0
[60103.826309]  tcp_write_xmit+0x1aa/0xee0
[60103.826313]  ? sch_direct_xmit+0x71/0x1b0
[60103.826318]  tcp_tasklet_func+0x177/0x180
[60103.826325]  tasklet_action+0x5f/0x110
[60103.826332]  __do_softirq+0xde/0x2b3
[60103.826337]  irq_exit+0xae/0xb0
[60103.826342]  do_IRQ+0x81/0xd0
[60103.826347]  common_interrupt+0x98/0x98
[60103.826351]  </IRQ>
[60103.826355] RIP: 0033:0x7f397bdf2282
[60103.826358] RSP: 002b:00007f395aaf57d8 EFLAGS: 00000206 ORIG_RAX: ffffffffffffff6e
[60103.826362] RAX: 0000000000000000 RBX: 00002f07bc6d0900 RCX: 00007f39752d7fe7
[60103.826365] RDX: 0000000000000022 RSI: 0000000000000147 RDI: 00002f07baea02c0
[60103.826368] RBP: 0000000000000001 R08: 0000000000000000 R09: 0000000000000000
[60103.826371] R10: 00000000ffffffff R11: 0000000000000000 R12: 00002f07baea02c0
[60103.826373] R13: 00002f07bba227a0 R14: 00002f07bc6d090c R15: 0000000000000000
[60103.826377] Code: 90 90 90 90 90 90 90 0f 1f 44 00 00 49 89 f9 48 89 d1 83
e2 07 48 c1 e9 03 40 0f b6 f6 48 b8 01 01 01 01 01 01 01 01 48 0f af c6 <f3> 48
ab 89 d1 f3 aa 4c 89 c8 c3 90 49 89 f9 40 88 f0 48 89 d1
[60103.826442] RIP: __memset+0x24/0x30 RSP: ffff964316c03b68
[60103.826444] CR2: ffff9641f2004000

Commit e1069bbfcf3b ("net: cdc_ncm: Reduce memory use when kernel
memory low") made this bug much more likely to trigger by reducing
the NTB size under memory pressure.

Link: https://bugs.debian.org/893393
Reported-by: Горбешко Богдан <bodqhrohro@gmail.com>
Reported-and-tested-by: Dennis Wassenberg <dennis.wassenberg@secunet.com>
Cc: Enrico Mioso <mrkiko.rs@gmail.com>
Fixes: 4a0e3e989d66 ("cdc_ncm: Add support for moving NDP to end of NCM frame")
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ncm.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 90d07ed224d5..b0e8b9613054 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -1124,7 +1124,7 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign)
 	 * accordingly. Otherwise, we should check here.
 	 */
 	if (ctx->drvflags & CDC_NCM_FLAG_NDP_TO_END)
-		delayed_ndp_size = ctx->max_ndp_size;
+		delayed_ndp_size = ALIGN(ctx->max_ndp_size, ctx->tx_ndp_modulus);
 	else
 		delayed_ndp_size = 0;
 
@@ -1285,7 +1285,7 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign)
 	/* If requested, put NDP at end of frame. */
 	if (ctx->drvflags & CDC_NCM_FLAG_NDP_TO_END) {
 		nth16 = (struct usb_cdc_ncm_nth16 *)skb_out->data;
-		cdc_ncm_align_tail(skb_out, ctx->tx_ndp_modulus, 0, ctx->tx_curr_size);
+		cdc_ncm_align_tail(skb_out, ctx->tx_ndp_modulus, 0, ctx->tx_curr_size - ctx->max_ndp_size);
 		nth16->wNdpIndex = cpu_to_le16(skb_out->len);
 		skb_put_data(skb_out, ctx->delayed_ndp16, ctx->max_ndp_size);
 
-- 
2.17.1


From bf686aade48ae9459db733bcfa913c894af550ff Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Mon, 11 Jun 2018 02:02:54 +0300
Subject: [PATCH 03/14] ipv6: allow PMTU exceptions to local routes

[ Upstream commit 0975764684487bf3f7a47eef009e750ea41bd514 ]

IPVS setups with local client and remote tunnel server need
to create exception for the local virtual IP. What we do is to
change PMTU from 64KB (on "lo") to 1460 in the common case.

Suggested-by: Martin KaFai Lau <kafai@fb.com>
Fixes: 45e4fd26683c ("ipv6: Only create RTF_CACHE routes after encountering pmtu exception")
Fixes: 7343ff31ebf0 ("ipv6: Don't create clones of host routes.")
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Acked-by: David Ahern <dsahern@gmail.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 4530a82aaa2e..b94345e657f7 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2149,9 +2149,6 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
 	const struct in6_addr *daddr, *saddr;
 	struct rt6_info *rt6 = (struct rt6_info *)dst;
 
-	if (rt6->rt6i_flags & RTF_LOCAL)
-		return;
-
 	if (dst_metric_locked(dst, RTAX_MTU))
 		return;
 
-- 
2.17.1


From 44ca3627a7d8b22b996a8c5d776603f2e6efcaf8 Mon Sep 17 00:00:00 2001
From: Zhouyang Jia <jiazhouyang09@gmail.com>
Date: Mon, 11 Jun 2018 13:26:35 +0800
Subject: [PATCH 04/14] net: dsa: add error handling for pskb_trim_rcsum

[ Upstream commit 349b71d6f427ff8211adf50839dbbff3f27c1805 ]

When pskb_trim_rcsum fails, the lack of error-handling code may
cause unexpected results.

This patch adds error-handling code after calling pskb_trim_rcsum.

Signed-off-by: Zhouyang Jia <jiazhouyang09@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/tag_trailer.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c
index 7d20e1f3de28..56197f0d9608 100644
--- a/net/dsa/tag_trailer.c
+++ b/net/dsa/tag_trailer.c
@@ -75,7 +75,8 @@ static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev,
 	if (!skb->dev)
 		return NULL;
 
-	pskb_trim_rcsum(skb, skb->len - 4);
+	if (pskb_trim_rcsum(skb, skb->len - 4))
+		return NULL;
 
 	return skb;
 }
-- 
2.17.1


From 03fe4d47d7141cc78225f87548b6c0b0288ea158 Mon Sep 17 00:00:00 2001
From: Alvaro Gamez Machado <alvaro.gamez@hazent.com>
Date: Fri, 8 Jun 2018 12:23:39 +0200
Subject: [PATCH 05/14] net: phy: dp83822: use BMCR_ANENABLE instead of
 BMSR_ANEGCAPABLE for DP83620

[ Upstream commit b718e8c8f4f5920aaddc2e52d5e32f494c91129c ]

DP83620 register set is compatible with the DP83848, but it also supports
100base-FX. When the hardware is configured such as that fiber mode is
enabled, autonegotiation is not possible.

The chip, however, doesn't expose this information via BMSR_ANEGCAPABLE.
Instead, this bit is always set high, even if the particular hardware
configuration makes it so that auto negotiation is not possible [1]. Under
these circumstances, the phy subsystem keeps trying for autonegotiation to
happen, without success.

Hereby, we inspect BMCR_ANENABLE bit after genphy_config_init, which on
reset is set to 0 when auto negotiation is disabled, and so we use this
value instead of BMSR_ANEGCAPABLE.

[1] https://e2e.ti.com/support/interface/ethernet/f/903/p/697165/2571170

Signed-off-by: Alvaro Gamez Machado <alvaro.gamez@hazent.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/dp83848.c | 35 +++++++++++++++++++++++++++++------
 1 file changed, 29 insertions(+), 6 deletions(-)

diff --git a/drivers/net/phy/dp83848.c b/drivers/net/phy/dp83848.c
index cd09c3af2117..6e8e42361fd5 100644
--- a/drivers/net/phy/dp83848.c
+++ b/drivers/net/phy/dp83848.c
@@ -74,6 +74,25 @@ static int dp83848_config_intr(struct phy_device *phydev)
 	return phy_write(phydev, DP83848_MICR, control);
 }
 
+static int dp83848_config_init(struct phy_device *phydev)
+{
+	int err;
+	int val;
+
+	err = genphy_config_init(phydev);
+	if (err < 0)
+		return err;
+
+	/* DP83620 always reports Auto Negotiation Ability on BMSR. Instead,
+	 * we check initial value of BMCR Auto negotiation enable bit
+	 */
+	val = phy_read(phydev, MII_BMCR);
+	if (!(val & BMCR_ANENABLE))
+		phydev->autoneg = AUTONEG_DISABLE;
+
+	return 0;
+}
+
 static struct mdio_device_id __maybe_unused dp83848_tbl[] = {
 	{ TI_DP83848C_PHY_ID, 0xfffffff0 },
 	{ NS_DP83848C_PHY_ID, 0xfffffff0 },
@@ -83,7 +102,7 @@ static struct mdio_device_id __maybe_unused dp83848_tbl[] = {
 };
 MODULE_DEVICE_TABLE(mdio, dp83848_tbl);
 
-#define DP83848_PHY_DRIVER(_id, _name)				\
+#define DP83848_PHY_DRIVER(_id, _name, _config_init)		\
 	{							\
 		.phy_id		= _id,				\
 		.phy_id_mask	= 0xfffffff0,			\
@@ -92,7 +111,7 @@ MODULE_DEVICE_TABLE(mdio, dp83848_tbl);
 		.flags		= PHY_HAS_INTERRUPT,		\
 								\
 		.soft_reset	= genphy_soft_reset,		\
-		.config_init	= genphy_config_init,		\
+		.config_init	= _config_init,			\
 		.suspend	= genphy_suspend,		\
 		.resume		= genphy_resume,		\
 								\
@@ -102,10 +121,14 @@ MODULE_DEVICE_TABLE(mdio, dp83848_tbl);
 	}
 
 static struct phy_driver dp83848_driver[] = {
-	DP83848_PHY_DRIVER(TI_DP83848C_PHY_ID, "TI DP83848C 10/100 Mbps PHY"),
-	DP83848_PHY_DRIVER(NS_DP83848C_PHY_ID, "NS DP83848C 10/100 Mbps PHY"),
-	DP83848_PHY_DRIVER(TI_DP83620_PHY_ID, "TI DP83620 10/100 Mbps PHY"),
-	DP83848_PHY_DRIVER(TLK10X_PHY_ID, "TI TLK10X 10/100 Mbps PHY"),
+	DP83848_PHY_DRIVER(TI_DP83848C_PHY_ID, "TI DP83848C 10/100 Mbps PHY",
+			   genphy_config_init),
+	DP83848_PHY_DRIVER(NS_DP83848C_PHY_ID, "NS DP83848C 10/100 Mbps PHY",
+			   genphy_config_init),
+	DP83848_PHY_DRIVER(TI_DP83620_PHY_ID, "TI DP83620 10/100 Mbps PHY",
+			   dp83848_config_init),
+	DP83848_PHY_DRIVER(TLK10X_PHY_ID, "TI TLK10X 10/100 Mbps PHY",
+			   genphy_config_init),
 };
 module_phy_driver(dp83848_driver);
 
-- 
2.17.1


From 754c57a7dc6700be64a05b62aa5df6fbce0aff15 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Fri, 8 Jun 2018 05:02:31 +0200
Subject: [PATCH 06/14] net/sched: act_simple: fix parsing of TCA_DEF_DATA

[ Upstream commit 8d499533e0bc02d44283dbdab03142b599b8ba16 ]

use nla_strlcpy() to avoid copying data beyond the length of TCA_DEF_DATA
netlink attribute, in case it is less than SIMP_MAX_DATA and it does not
end with '\0' character.

v2: fix errors in the commit message, thanks Hangbin Liu

Fixes: fa1b1cff3d06 ("net_cls_act: Make act_simple use of netlink policy.")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_simple.c | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 9618b4a83cee..98c4afe7c15b 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -53,22 +53,22 @@ static void tcf_simp_release(struct tc_action *a)
 	kfree(d->tcfd_defdata);
 }
 
-static int alloc_defdata(struct tcf_defact *d, char *defdata)
+static int alloc_defdata(struct tcf_defact *d, const struct nlattr *defdata)
 {
 	d->tcfd_defdata = kzalloc(SIMP_MAX_DATA, GFP_KERNEL);
 	if (unlikely(!d->tcfd_defdata))
 		return -ENOMEM;
-	strlcpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA);
+	nla_strlcpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA);
 	return 0;
 }
 
-static void reset_policy(struct tcf_defact *d, char *defdata,
+static void reset_policy(struct tcf_defact *d, const struct nlattr *defdata,
 			 struct tc_defact *p)
 {
 	spin_lock_bh(&d->tcf_lock);
 	d->tcf_action = p->action;
 	memset(d->tcfd_defdata, 0, SIMP_MAX_DATA);
-	strlcpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA);
+	nla_strlcpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA);
 	spin_unlock_bh(&d->tcf_lock);
 }
 
@@ -87,7 +87,6 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
 	struct tcf_defact *d;
 	bool exists = false;
 	int ret = 0, err;
-	char *defdata;
 
 	if (nla == NULL)
 		return -EINVAL;
@@ -110,8 +109,6 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
 		return -EINVAL;
 	}
 
-	defdata = nla_data(tb[TCA_DEF_DATA]);
-
 	if (!exists) {
 		ret = tcf_idr_create(tn, parm->index, est, a,
 				     &act_simp_ops, bind, false);
@@ -119,7 +116,7 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
 			return ret;
 
 		d = to_defact(*a);
-		ret = alloc_defdata(d, defdata);
+		ret = alloc_defdata(d, tb[TCA_DEF_DATA]);
 		if (ret < 0) {
 			tcf_idr_release(*a, bind);
 			return ret;
@@ -133,7 +130,7 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
 		if (!ovr)
 			return -EEXIST;
 
-		reset_policy(d, defdata, parm);
+		reset_policy(d, tb[TCA_DEF_DATA], parm);
 	}
 
 	if (ret == ACT_P_CREATED)
-- 
2.17.1


From ab2f72c18f8d506d9266bc65cfc5f88407a005b6 Mon Sep 17 00:00:00 2001
From: Frank van der Linden <fllinden@amazon.com>
Date: Tue, 12 Jun 2018 23:09:37 +0000
Subject: [PATCH 07/14] tcp: verify the checksum of the first data segment in a
 new connection

[ Upstream commit 4fd44a98ffe0d048246efef67ed640fdf2098a62 ]

commit 079096f103fa ("tcp/dccp: install syn_recv requests into ehash
table") introduced an optimization for the handling of child sockets
created for a new TCP connection.

But this optimization passes any data associated with the last ACK of the
connection handshake up the stack without verifying its checksum, because it
calls tcp_child_process(), which in turn calls tcp_rcv_state_process()
directly.  These lower-level processing functions do not do any checksum
verification.

Insert a tcp_checksum_complete call in the TCP_NEW_SYN_RECEIVE path to
fix this.

Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table")
Signed-off-by: Frank van der Linden <fllinden@amazon.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Tested-by: Balbir Singh <bsingharora@gmail.com>
Reviewed-by: Balbir Singh <bsingharora@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c | 4 ++++
 net/ipv6/tcp_ipv6.c | 4 ++++
 2 files changed, 8 insertions(+)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index f70586b50838..ef8cd0f7db89 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1689,6 +1689,10 @@ int tcp_v4_rcv(struct sk_buff *skb)
 			reqsk_put(req);
 			goto discard_it;
 		}
+		if (tcp_checksum_complete(skb)) {
+			reqsk_put(req);
+			goto csum_error;
+		}
 		if (unlikely(sk->sk_state != TCP_LISTEN)) {
 			inet_csk_reqsk_queue_drop_and_put(sk, req);
 			goto lookup;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 6d664d83cd16..5d4eb9d2c3a7 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1475,6 +1475,10 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 			reqsk_put(req);
 			goto discard_it;
 		}
+		if (tcp_checksum_complete(skb)) {
+			reqsk_put(req);
+			goto csum_error;
+		}
 		if (unlikely(sk->sk_state != TCP_LISTEN)) {
 			inet_csk_reqsk_queue_drop_and_put(sk, req);
 			goto lookup;
-- 
2.17.1


From 4837852b85d7d9752e7ff03af81eb3b34419aeaf Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 15 Jun 2018 03:07:45 +0200
Subject: [PATCH 08/14] tls: fix use-after-free in tls_push_record

[ Upstream commit a447da7d00410278c90d3576782a43f8b675d7be ]

syzkaller managed to trigger a use-after-free in tls like the
following:

  BUG: KASAN: use-after-free in tls_push_record.constprop.15+0x6a2/0x810 [tls]
  Write of size 1 at addr ffff88037aa08000 by task a.out/2317

  CPU: 3 PID: 2317 Comm: a.out Not tainted 4.17.0+ #144
  Hardware name: LENOVO 20FBCTO1WW/20FBCTO1WW, BIOS N1FET47W (1.21 ) 11/28/2016
  Call Trace:
   dump_stack+0x71/0xab
   print_address_description+0x6a/0x280
   kasan_report+0x258/0x380
   ? tls_push_record.constprop.15+0x6a2/0x810 [tls]
   tls_push_record.constprop.15+0x6a2/0x810 [tls]
   tls_sw_push_pending_record+0x2e/0x40 [tls]
   tls_sk_proto_close+0x3fe/0x710 [tls]
   ? tcp_check_oom+0x4c0/0x4c0
   ? tls_write_space+0x260/0x260 [tls]
   ? kmem_cache_free+0x88/0x1f0
   inet_release+0xd6/0x1b0
   __sock_release+0xc0/0x240
   sock_close+0x11/0x20
   __fput+0x22d/0x660
   task_work_run+0x114/0x1a0
   do_exit+0x71a/0x2780
   ? mm_update_next_owner+0x650/0x650
   ? handle_mm_fault+0x2f5/0x5f0
   ? __do_page_fault+0x44f/0xa50
   ? mm_fault_error+0x2d0/0x2d0
   do_group_exit+0xde/0x300
   __x64_sys_exit_group+0x3a/0x50
   do_syscall_64+0x9a/0x300
   ? page_fault+0x8/0x30
   entry_SYSCALL_64_after_hwframe+0x44/0xa9

This happened through fault injection where aead_req allocation in
tls_do_encryption() eventually failed and we returned -ENOMEM from
the function. Turns out that the use-after-free is triggered from
tls_sw_sendmsg() in the second tls_push_record(). The error then
triggers a jump to waiting for memory in sk_stream_wait_memory()
resp. returning immediately in case of MSG_DONTWAIT. What follows is
the trim_both_sgl(sk, orig_size), which drops elements from the sg
list added via tls_sw_sendmsg(). Now the use-after-free gets triggered
when the socket is being closed, where tls_sk_proto_close() callback
is invoked. The tls_complete_pending_work() will figure that there's
a pending closed tls record to be flushed and thus calls into the
tls_push_pending_closed_record() from there. ctx->push_pending_record()
is called from the latter, which is the tls_sw_push_pending_record()
from sw path. This again calls into tls_push_record(). And here the
tls_fill_prepend() will panic since the buffer address has been freed
earlier via trim_both_sgl(). One way to fix it is to move the aead
request allocation out of tls_do_encryption() early into tls_push_record().
This means we don't prep the tls header and advance state to the
TLS_PENDING_CLOSED_RECORD before allocation which could potentially
fail happened. That fixes the issue on my side.

Fixes: 3c4d7559159b ("tls: kernel TLS support")
Reported-by: syzbot+5c74af81c547738e1684@syzkaller.appspotmail.com
Reported-by: syzbot+709f2810a6a05f11d4d3@syzkaller.appspotmail.com
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Dave Watson <davejwatson@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index e1c93ce74e0f..a8001854eb23 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -191,18 +191,12 @@ static void tls_free_both_sg(struct sock *sk)
 }
 
 static int tls_do_encryption(struct tls_context *tls_ctx,
-			     struct tls_sw_context *ctx, size_t data_len,
-			     gfp_t flags)
+			     struct tls_sw_context *ctx,
+			     struct aead_request *aead_req,
+			     size_t data_len)
 {
-	unsigned int req_size = sizeof(struct aead_request) +
-		crypto_aead_reqsize(ctx->aead_send);
-	struct aead_request *aead_req;
 	int rc;
 
-	aead_req = kzalloc(req_size, flags);
-	if (!aead_req)
-		return -ENOMEM;
-
 	ctx->sg_encrypted_data[0].offset += tls_ctx->tx.prepend_size;
 	ctx->sg_encrypted_data[0].length -= tls_ctx->tx.prepend_size;
 
@@ -219,7 +213,6 @@ static int tls_do_encryption(struct tls_context *tls_ctx,
 	ctx->sg_encrypted_data[0].offset -= tls_ctx->tx.prepend_size;
 	ctx->sg_encrypted_data[0].length += tls_ctx->tx.prepend_size;
 
-	kfree(aead_req);
 	return rc;
 }
 
@@ -228,8 +221,14 @@ static int tls_push_record(struct sock *sk, int flags,
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+	struct aead_request *req;
 	int rc;
 
+	req = kzalloc(sizeof(struct aead_request) +
+		      crypto_aead_reqsize(ctx->aead_send), sk->sk_allocation);
+	if (!req)
+		return -ENOMEM;
+
 	sg_mark_end(ctx->sg_plaintext_data + ctx->sg_plaintext_num_elem - 1);
 	sg_mark_end(ctx->sg_encrypted_data + ctx->sg_encrypted_num_elem - 1);
 
@@ -245,15 +244,14 @@ static int tls_push_record(struct sock *sk, int flags,
 	tls_ctx->pending_open_record_frags = 0;
 	set_bit(TLS_PENDING_CLOSED_RECORD, &tls_ctx->flags);
 
-	rc = tls_do_encryption(tls_ctx, ctx, ctx->sg_plaintext_size,
-			       sk->sk_allocation);
+	rc = tls_do_encryption(tls_ctx, ctx, req, ctx->sg_plaintext_size);
 	if (rc < 0) {
 		/* If we are called from write_space and
 		 * we fail, we need to set this SOCK_NOSPACE
 		 * to trigger another write_space in the future.
 		 */
 		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
-		return rc;
+		goto out_req;
 	}
 
 	free_sg(sk, ctx->sg_plaintext_data, &ctx->sg_plaintext_num_elem,
@@ -268,6 +266,8 @@ static int tls_push_record(struct sock *sk, int flags,
 		tls_err_abort(sk, EBADMSG);
 
 	tls_advance_record_sn(sk, &tls_ctx->tx);
+out_req:
+	kfree(req);
 	return rc;
 }
 
-- 
2.17.1


From a480383387e124189f49a1561dcb4e0d7e197d7f Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 15 Jun 2018 03:07:46 +0200
Subject: [PATCH 09/14] tls: fix waitall behavior in tls_sw_recvmsg

[ Upstream commit 06030dbaf3b6c5801dcdb7fe4fbab3b91c8da84a ]

Current behavior in tls_sw_recvmsg() is to wait for incoming tls
messages and copy up to exactly len bytes of data that the user
provided. This is problematic in the sense that i) if no packet
is currently queued in strparser we keep waiting until one has been
processed and pushed into tls receive layer for tls_wait_data() to
wake up and push the decrypted bits to user space. Given after
tls decryption, we're back at streaming data, use sock_rcvlowat()
hint from tcp socket instead. Retain current behavior with MSG_WAITALL
flag and otherwise use the hint target for breaking the loop and
returning to application. This is done if currently no ctx->recv_pkt
is ready, otherwise continue to process it from our strparser
backlog.

Fixes: c46234ebb4d1 ("tls: RX path for ktls")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Dave Watson <davejwatson@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index a8001854eb23..5fe29121b9a8 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -755,7 +755,7 @@ int tls_sw_recvmsg(struct sock *sk,
 	struct sk_buff *skb;
 	ssize_t copied = 0;
 	bool cmsg = false;
-	int err = 0;
+	int target, err = 0;
 	long timeo;
 
 	flags |= nonblock;
@@ -765,6 +765,7 @@ int tls_sw_recvmsg(struct sock *sk,
 
 	lock_sock(sk);
 
+	target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
 	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
 	do {
 		bool zc = false;
@@ -857,6 +858,9 @@ int tls_sw_recvmsg(struct sock *sk,
 					goto recv_end;
 			}
 		}
+		/* If we have a new message from strparser, continue now. */
+		if (copied >= target && !ctx->recv_pkt)
+			break;
 	} while (len);
 
 recv_end:
-- 
2.17.1


From dbf1e450e47a0c7eee8e6c9e9c6f259c80dcf785 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 7 Jun 2018 13:39:49 -0700
Subject: [PATCH 10/14] socket: close race condition between sock_close() and
 sockfs_setattr()

[ Upstream commit 6d8c50dcb029872b298eea68cc6209c866fd3e14 ]

fchownat() doesn't even hold refcnt of fd until it figures out
fd is really needed (otherwise is ignored) and releases it after
it resolves the path. This means sock_close() could race with
sockfs_setattr(), which leads to a NULL pointer dereference
since typically we set sock->sk to NULL in ->release().

As pointed out by Al, this is unique to sockfs. So we can fix this
in socket layer by acquiring inode_lock in sock_close() and
checking against NULL in sockfs_setattr().

sock_release() is called in many places, only the sock_close()
path matters here. And fortunately, this should not affect normal
sock_close() as it is only called when the last fd refcnt is gone.
It only affects sock_close() with a parallel sockfs_setattr() in
progress, which is not common.

Fixes: 86741ec25462 ("net: core: Add a UID field to struct sock.")
Reported-by: shankarapailoor <shankarapailoor@gmail.com>
Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Cc: Lorenzo Colitti <lorenzo@google.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/socket.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/net/socket.c b/net/socket.c
index f10f1d947c78..d1b02f161429 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -537,7 +537,10 @@ static int sockfs_setattr(struct dentry *dentry, struct iattr *iattr)
 	if (!err && (iattr->ia_valid & ATTR_UID)) {
 		struct socket *sock = SOCKET_I(d_inode(dentry));
 
-		sock->sk->sk_uid = iattr->ia_uid;
+		if (sock->sk)
+			sock->sk->sk_uid = iattr->ia_uid;
+		else
+			err = -ENOENT;
 	}
 
 	return err;
@@ -586,12 +589,16 @@ EXPORT_SYMBOL(sock_alloc);
  *	an inode not a file.
  */
 
-void sock_release(struct socket *sock)
+static void __sock_release(struct socket *sock, struct inode *inode)
 {
 	if (sock->ops) {
 		struct module *owner = sock->ops->owner;
 
+		if (inode)
+			inode_lock(inode);
 		sock->ops->release(sock);
+		if (inode)
+			inode_unlock(inode);
 		sock->ops = NULL;
 		module_put(owner);
 	}
@@ -605,6 +612,11 @@ void sock_release(struct socket *sock)
 	}
 	sock->file = NULL;
 }
+
+void sock_release(struct socket *sock)
+{
+	__sock_release(sock, NULL);
+}
 EXPORT_SYMBOL(sock_release);
 
 void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags)
@@ -1146,7 +1158,7 @@ static int sock_mmap(struct file *file, struct vm_area_struct *vma)
 
 static int sock_close(struct inode *inode, struct file *filp)
 {
-	sock_release(SOCKET_I(inode));
+	__sock_release(SOCKET_I(inode), inode);
 	return 0;
 }
 
-- 
2.17.1


From f7d2fb8589aaaeb9deaed614399efea3ce936dbb Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 8 Jun 2018 11:35:40 +0200
Subject: [PATCH 11/14] udp: fix rx queue len reported by diag and proc
 interface

[ Upstream commit 6c206b20092a3623184cff9470dba75d21507874 ]

After commit 6b229cf77d68 ("udp: add batching to udp_rmem_release()")
the sk_rmem_alloc field does not measure exactly anymore the
receive queue length, because we batch the rmem release. The issue
is really apparent only after commit 0d4a6608f68c ("udp: do rmem bulk
free even if the rx sk queue is empty"): the user space can easily
check for an empty socket with not-0 queue length reported by the 'ss'
tool or the procfs interface.

We need to use a custom UDP helper to report the correct queue length,
taking into account the forward allocation deficit.

Reported-by: trevor.francis@46labs.com
Fixes: 6b229cf77d68 ("UDP: add batching to udp_rmem_release()")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/transp_v6.h | 11 +++++++++--
 include/net/udp.h       |  5 +++++
 net/ipv4/udp.c          |  2 +-
 net/ipv4/udp_diag.c     |  2 +-
 net/ipv6/datagram.c     |  6 +++---
 net/ipv6/udp.c          |  3 ++-
 6 files changed, 21 insertions(+), 8 deletions(-)

diff --git a/include/net/transp_v6.h b/include/net/transp_v6.h
index c4f5caaf3778..f6a3543e5247 100644
--- a/include/net/transp_v6.h
+++ b/include/net/transp_v6.h
@@ -45,8 +45,15 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk, struct msghdr *msg,
 			  struct flowi6 *fl6, struct ipcm6_cookie *ipc6,
 			  struct sockcm_cookie *sockc);
 
-void ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp,
-			     __u16 srcp, __u16 destp, int bucket);
+void __ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp,
+			       __u16 srcp, __u16 destp, int rqueue, int bucket);
+static inline void
+ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp, __u16 srcp,
+			__u16 destp, int bucket)
+{
+	__ip6_dgram_sock_seq_show(seq, sp, srcp, destp, sk_rmem_alloc_get(sp),
+				  bucket);
+}
 
 #define LOOPBACK4_IPV6 cpu_to_be32(0x7f000006)
 
diff --git a/include/net/udp.h b/include/net/udp.h
index 0676b272f6ac..1db85dcb06f6 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -244,6 +244,11 @@ static inline __be16 udp_flow_src_port(struct net *net, struct sk_buff *skb,
 	return htons((((u64) hash * (max - min)) >> 32) + min);
 }
 
+static inline int udp_rqueue_get(struct sock *sk)
+{
+	return sk_rmem_alloc_get(sk) - READ_ONCE(udp_sk(sk)->forward_deficit);
+}
+
 /* net/ipv4/udp.c */
 void udp_destruct_sock(struct sock *sk);
 void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index b61a770884fa..5f7bc5c6366a 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2718,7 +2718,7 @@ static void udp4_format_sock(struct sock *sp, struct seq_file *f,
 		" %02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %d",
 		bucket, src, srcp, dest, destp, sp->sk_state,
 		sk_wmem_alloc_get(sp),
-		sk_rmem_alloc_get(sp),
+		udp_rqueue_get(sp),
 		0, 0L, 0,
 		from_kuid_munged(seq_user_ns(f), sock_i_uid(sp)),
 		0, sock_i_ino(sp),
diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c
index d0390d844ac8..d9ad986c7b2c 100644
--- a/net/ipv4/udp_diag.c
+++ b/net/ipv4/udp_diag.c
@@ -163,7 +163,7 @@ static int udp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh,
 static void udp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
 		void *info)
 {
-	r->idiag_rqueue = sk_rmem_alloc_get(sk);
+	r->idiag_rqueue = udp_rqueue_get(sk);
 	r->idiag_wqueue = sk_wmem_alloc_get(sk);
 }
 
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index a02ad100f0d7..2ee08b6a86a4 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -1019,8 +1019,8 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
 }
 EXPORT_SYMBOL_GPL(ip6_datagram_send_ctl);
 
-void ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp,
-			     __u16 srcp, __u16 destp, int bucket)
+void __ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp,
+			       __u16 srcp, __u16 destp, int rqueue, int bucket)
 {
 	const struct in6_addr *dest, *src;
 
@@ -1036,7 +1036,7 @@ void ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp,
 		   dest->s6_addr32[2], dest->s6_addr32[3], destp,
 		   sp->sk_state,
 		   sk_wmem_alloc_get(sp),
-		   sk_rmem_alloc_get(sp),
+		   rqueue,
 		   0, 0L, 0,
 		   from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)),
 		   0,
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index ea0730028e5d..977bd5a07cab 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1475,7 +1475,8 @@ int udp6_seq_show(struct seq_file *seq, void *v)
 		struct inet_sock *inet = inet_sk(v);
 		__u16 srcp = ntohs(inet->inet_sport);
 		__u16 destp = ntohs(inet->inet_dport);
-		ip6_dgram_sock_seq_show(seq, v, srcp, destp, bucket);
+		__ip6_dgram_sock_seq_show(seq, v, srcp, destp,
+					  udp_rqueue_get(v), bucket);
 	}
 	return 0;
 }
-- 
2.17.1


From c63f06afad00631fb7f9069a4d8ec39b6703dd2f Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 6 Jun 2018 11:23:01 -0400
Subject: [PATCH 12/14] net: in virtio_net_hdr only add VLAN_HLEN to csum_start
 if payload holds vlan

[ Upstream commit fd3a88625844907151737fc3b4201676effa6d27 ]

Tun, tap, virtio, packet and uml vector all use struct virtio_net_hdr
to communicate packet metadata to userspace.

For skbuffs with vlan, the first two return the packet as it may have
existed on the wire, inserting the VLAN tag in the user buffer.  Then
virtio_net_hdr.csum_start needs to be adjusted by VLAN_HLEN bytes.

Commit f09e2249c4f5 ("macvtap: restore vlan header on user read")
added this feature to macvtap. Commit 3ce9b20f1971 ("macvtap: Fix
csum_start when VLAN tags are present") then fixed up csum_start.

Virtio, packet and uml do not insert the vlan header in the user
buffer.

When introducing virtio_net_hdr_from_skb to deduplicate filling in
the virtio_net_hdr, the variant from macvtap which adds VLAN_HLEN was
applied uniformly, breaking csum offset for packets with vlan on
virtio and packet.

Make insertion of VLAN_HLEN optional. Convert the callers to pass it
when needed.

Fixes: e858fae2b0b8f4 ("virtio_net: use common code for virtio_net_hdr and skb GSO conversion")
Fixes: 1276f24eeef2 ("packet: use common code for virtio_net_hdr and skb GSO conversion")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/um/drivers/vector_transports.c |  3 ++-
 drivers/net/tap.c                   |  5 ++++-
 drivers/net/tun.c                   |  3 ++-
 drivers/net/virtio_net.c            |  3 ++-
 include/linux/virtio_net.h          | 11 ++++-------
 net/packet/af_packet.c              |  4 ++--
 6 files changed, 16 insertions(+), 13 deletions(-)

diff --git a/arch/um/drivers/vector_transports.c b/arch/um/drivers/vector_transports.c
index 9065047f844b..77e4ebc206ae 100644
--- a/arch/um/drivers/vector_transports.c
+++ b/arch/um/drivers/vector_transports.c
@@ -120,7 +120,8 @@ static int raw_form_header(uint8_t *header,
 		skb,
 		vheader,
 		virtio_legacy_is_little_endian(),
-		false
+		false,
+		0
 	);
 
 	return 0;
diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index 9b6cb780affe..f0f7cd977667 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -774,13 +774,16 @@ static ssize_t tap_put_user(struct tap_queue *q,
 	int total;
 
 	if (q->flags & IFF_VNET_HDR) {
+		int vlan_hlen = skb_vlan_tag_present(skb) ? VLAN_HLEN : 0;
 		struct virtio_net_hdr vnet_hdr;
+
 		vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz);
 		if (iov_iter_count(iter) < vnet_hdr_len)
 			return -EINVAL;
 
 		if (virtio_net_hdr_from_skb(skb, &vnet_hdr,
-					    tap_is_little_endian(q), true))
+					    tap_is_little_endian(q), true,
+					    vlan_hlen))
 			BUG();
 
 		if (copy_to_iter(&vnet_hdr, sizeof(vnet_hdr), iter) !=
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 23e9eb66197f..409eb8b74740 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -2078,7 +2078,8 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 			return -EINVAL;
 
 		if (virtio_net_hdr_from_skb(skb, &gso,
-					    tun_is_little_endian(tun), true)) {
+					    tun_is_little_endian(tun), true,
+					    vlan_hlen)) {
 			struct skb_shared_info *sinfo = skb_shinfo(skb);
 			pr_err("unexpected GSO type: "
 			       "0x%x, gso_size %d, hdr_len %d\n",
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 032e1ac10a30..8c7207535179 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1358,7 +1358,8 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
 		hdr = skb_vnet_hdr(skb);
 
 	if (virtio_net_hdr_from_skb(skb, &hdr->hdr,
-				    virtio_is_little_endian(vi->vdev), false))
+				    virtio_is_little_endian(vi->vdev), false,
+				    0))
 		BUG();
 
 	if (vi->mergeable_rx_bufs)
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index f144216febc6..9397628a1967 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -58,7 +58,8 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb,
 					  struct virtio_net_hdr *hdr,
 					  bool little_endian,
-					  bool has_data_valid)
+					  bool has_data_valid,
+					  int vlan_hlen)
 {
 	memset(hdr, 0, sizeof(*hdr));   /* no info leak */
 
@@ -83,12 +84,8 @@ static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb,
 
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
-		if (skb_vlan_tag_present(skb))
-			hdr->csum_start = __cpu_to_virtio16(little_endian,
-				skb_checksum_start_offset(skb) + VLAN_HLEN);
-		else
-			hdr->csum_start = __cpu_to_virtio16(little_endian,
-				skb_checksum_start_offset(skb));
+		hdr->csum_start = __cpu_to_virtio16(little_endian,
+			skb_checksum_start_offset(skb) + vlan_hlen);
 		hdr->csum_offset = __cpu_to_virtio16(little_endian,
 				skb->csum_offset);
 	} else if (has_data_valid &&
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 60c2a252bdf5..38d132d007ba 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2037,7 +2037,7 @@ static int packet_rcv_vnet(struct msghdr *msg, const struct sk_buff *skb,
 		return -EINVAL;
 	*len -= sizeof(vnet_hdr);
 
-	if (virtio_net_hdr_from_skb(skb, &vnet_hdr, vio_le(), true))
+	if (virtio_net_hdr_from_skb(skb, &vnet_hdr, vio_le(), true, 0))
 		return -EINVAL;
 
 	return memcpy_to_msg(msg, (void *)&vnet_hdr, sizeof(vnet_hdr));
@@ -2304,7 +2304,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	if (do_vnet) {
 		if (virtio_net_hdr_from_skb(skb, h.raw + macoff -
 					    sizeof(struct virtio_net_hdr),
-					    vio_le(), true)) {
+					    vio_le(), true, 0)) {
 			spin_lock(&sk->sk_receive_queue.lock);
 			goto drop_n_account;
 		}
-- 
2.17.1


From 32e7beb3ed9048abce3317b685042a13d58b547d Mon Sep 17 00:00:00 2001
From: Dexuan Cui <decui@microsoft.com>
Date: Wed, 6 Jun 2018 21:32:51 +0000
Subject: [PATCH 13/14] hv_netvsc: Fix a network regression after ifdown/ifup

[ Upstream commit 52acf73b6e9a6962045feb2ba5a8921da2201915 ]

Recently people reported the NIC stops working after
"ifdown eth0; ifup eth0". It turns out in this case the TX queues are not
enabled, after the refactoring of the common detach logic: when the NIC
has sub-channels, usually we enable all the TX queues after all
sub-channels are set up: see rndis_set_subchannel() ->
netif_device_attach(), but in the case of "ifdown eth0; ifup eth0" where
the number of channels doesn't change, we also must make sure the TX queues
are enabled. The patch fixes the regression.

Fixes: 7b2ee50c0cd5 ("hv_netvsc: common detach logic")
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/netvsc_drv.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index da07ccdf84bf..eb8dccd24abf 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -126,8 +126,10 @@ static int netvsc_open(struct net_device *net)
 	}
 
 	rdev = nvdev->extension;
-	if (!rdev->link_state)
+	if (!rdev->link_state) {
 		netif_carrier_on(net);
+		netif_tx_wake_all_queues(net);
+	}
 
 	if (vf_netdev) {
 		/* Setting synthetic device up transparently sets
-- 
2.17.1


From 1b29a5b84f572a0f4f2635877097f6919f95c58d Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Thu, 7 Jun 2018 17:54:37 -0400
Subject: [PATCH 14/14] net: aquantia: fix unsigned numvecs comparison with
 less than zero

[ Upstream commit 58d813afbe89658a5972747460a5fe19dec4dbcb ]

From: Colin Ian King <colin.king@canonical.com>

This was originally mistakenly submitted to net-next. Resubmitting to net.

The comparison of numvecs < 0 is always false because numvecs is a u32
and hence the error return from a failed call to pci_alloc_irq_vectores
is never detected.  Fix this by using the signed int ret to handle the
error return and assign numvecs to err.

Detected by CoverityScan, CID#1468650 ("Unsigned compared against 0")

Fixes: a09bd81b5413 ("net: aquantia: Limit number of vectors to actually allocated irqs")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
index a50e08bb4748..750007513f9d 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
@@ -267,14 +267,13 @@ static int aq_pci_probe(struct pci_dev *pdev,
 	numvecs = min(numvecs, num_online_cpus());
 	/*enable interrupts */
 #if !AQ_CFG_FORCE_LEGACY_INT
-	numvecs = pci_alloc_irq_vectors(self->pdev, 1, numvecs,
-					PCI_IRQ_MSIX | PCI_IRQ_MSI |
-					PCI_IRQ_LEGACY);
+	err = pci_alloc_irq_vectors(self->pdev, 1, numvecs,
+				    PCI_IRQ_MSIX | PCI_IRQ_MSI |
+				    PCI_IRQ_LEGACY);
 
-	if (numvecs < 0) {
-		err = numvecs;
+	if (err < 0)
 		goto err_hwinit;
-	}
+	numvecs = err;
 #endif
 	self->irqvecs = numvecs;
 
-- 
2.17.1

Re: [PATCHES] Networking

[Greg KH]

On Wed, Jun 20, 2018 at 09:37:12PM +0900, David Miller wrote:
> 
> Please queue up the following networking bug fixes for 4.16 and
> 4.17 -stable, respectively.


All now queued up, thanks.

greg k-h

Re: [PATCHES] Networking

[Greg KH]

On Fri, Jun 22, 2018 at 06:10:19AM +0900, Greg KH wrote:
> On Wed, Jun 20, 2018 at 09:37:12PM +0900, David Miller wrote:
> > 
> > Please queue up the following networking bug fixes for 4.16 and
> > 4.17 -stable, respectively.
> 
> 
> All now queued up, thanks.

Also, no need for you to care about 4.16 anymore, unless there is
something very serious, as I should only be doing one more release of
that kernel tree, in a day or so.

thanks,

greg k-h

Re: [PATCHES] Networking

[Greg KH]

On Thu, Jun 07, 2018 at 01:47:34PM +0300, Ido Schimmel wrote:
> On Thu, Jun 07, 2018 at 09:00:12AM +0200, Jiri Slaby wrote:
> > On 09/15/2017, 06:57 AM, David Miller wrote:
> > > Please queue up the following networking bug fixes for v4.9, v4.12, and
> > > v4.13 -stable, respectively.
> > 
> > Hi,
> > 
> > while walking through some fixes, I wonder, whether backports of
> > 25cc72a33835 (mlxsw: spectrum: Forbid linking to devices that have
> >  uppers) to 4.9 and 4.12 are correct.
> 
> [...]
> 
> > 
> > 
> > Did I miss something or is this a mistake?
> 
> Your analysis looks correct to me. How do you want to proceed? Do you
> want me to send you fixed backports for 4.9.y and 4.12.y?

Yes, can you send a fix for this?  4.12.y is end-of-life, so it doesn't
matter, but 4.9.y does.

thanks,

greg k-h

Re: [PATCHES] Networking

[Ido Schimmel]

On Thu, Jul 05, 2018 at 06:15:34PM +0200, Greg KH wrote:
> On Thu, Jun 07, 2018 at 01:47:34PM +0300, Ido Schimmel wrote:
> > On Thu, Jun 07, 2018 at 09:00:12AM +0200, Jiri Slaby wrote:
> > > On 09/15/2017, 06:57 AM, David Miller wrote:
> > > > Please queue up the following networking bug fixes for v4.9, v4.12, and
> > > > v4.13 -stable, respectively.
> > > 
> > > Hi,
> > > 
> > > while walking through some fixes, I wonder, whether backports of
> > > 25cc72a33835 (mlxsw: spectrum: Forbid linking to devices that have
> > >  uppers) to 4.9 and 4.12 are correct.
> > 
> > [...]
> > 
> > > 
> > > 
> > > Did I miss something or is this a mistake?
> > 
> > Your analysis looks correct to me. How do you want to proceed? Do you
> > want me to send you fixed backports for 4.9.y and 4.12.y?
> 
> Yes, can you send a fix for this?  4.12.y is end-of-life, so it doesn't
> matter, but 4.9.y does.

Yes, sure, will do that now. Sorry

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 310 bytes --]


====================
READ ME.  I have this stale email in my outgoing draft folder, and I
have no idea if I actually sent this out successfully or not.

Please double check, thanks!
====================

Please queue up the following networking bug fixes for v4.14 and v4.17
-stable, repectively.

Thank you!

[-- Attachment #2: net_414.mbox --]
[-- Type: Application/Octet-Stream, Size: 98576 bytes --]

From 0fea41484f63ebc46a838e26b3fa5fb3a73dc024 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 29 Jun 2018 17:51:26 +0200
Subject: [PATCH 01/35] alx: take rtnl before calling __alx_open from resume

[ Upstream commit bc800e8b39bad60ccdb83be828da63af71ab87b3 ]

The __alx_open function can be called from ndo_open, which is called
under RTNL, or from alx_resume, which isn't. Since commit d768319cd427,
we're calling the netif_set_real_num_{tx,rx}_queues functions, which
need to be called under RTNL.

This is similar to commit 0c2cc02e571a ("igb: Move the calls to set the
Tx and Rx queues into igb_open").

Fixes: d768319cd427 ("alx: enable multiple tx queues")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/atheros/alx/main.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index 567ee54504bc..5e5022fa1d04 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -1897,13 +1897,19 @@ static int alx_resume(struct device *dev)
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct alx_priv *alx = pci_get_drvdata(pdev);
 	struct alx_hw *hw = &alx->hw;
+	int err;
 
 	alx_reset_phy(hw);
 
 	if (!netif_running(alx->dev))
 		return 0;
 	netif_device_attach(alx->dev);
-	return __alx_open(alx, true);
+
+	rtnl_lock();
+	err = __alx_open(alx, true);
+	rtnl_unlock();
+
+	return err;
 }
 
 static SIMPLE_DEV_PM_OPS(alx_pm_ops, alx_suspend, alx_resume);
-- 
2.17.1


From 146e8f9d7d0dc93cb51a5cf07308b0c938ed33d0 Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw2@infradead.org>
Date: Sat, 16 Jun 2018 11:55:44 +0100
Subject: [PATCH 02/35] atm: Preserve value of skb->truesize when accounting to
 vcc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 9bbe60a67be5a1c6f79b3c9be5003481a50529ff ]

ATM accounts for in-flight TX packets in sk_wmem_alloc of the VCC on
which they are to be sent. But it doesn't take ownership of those
packets from the sock (if any) which originally owned them. They should
remain owned by their actual sender until they've left the box.

There's a hack in pskb_expand_head() to avoid adjusting skb->truesize
for certain skbs, precisely to avoid messing up sk_wmem_alloc
accounting. Ideally that hack would cover the ATM use case too, but it
doesn't — skbs which aren't owned by any sock, for example PPP control
frames, still get their truesize adjusted when the low-level ATM driver
adds headroom.

This has always been an issue, it seems. The truesize of a packet
increases, and sk_wmem_alloc on the VCC goes negative. But this wasn't
for normal traffic, only for control frames. So I think we just got away
with it, and we probably needed to send 2GiB of LCP echo frames before
the misaccounting would ever have caused a problem and caused
atm_may_send() to start refusing packets.

Commit 14afee4b609 ("net: convert sock.sk_wmem_alloc from atomic_t to
refcount_t") did exactly what it was intended to do, and turned this
mostly-theoretical problem into a real one, causing PPPoATM to fail
immediately as sk_wmem_alloc underflows and atm_may_send() *immediately*
starts refusing to allow new packets.

The least intrusive solution to this problem is to stash the value of
skb->truesize that was accounted to the VCC, in a new member of the
ATM_SKB(skb) structure. Then in atm_pop_raw() subtract precisely that
value instead of the then-current value of skb->truesize.

Fixes: 158f323b9868 ("net: adjust skb->truesize in pskb_expand_head()")
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Tested-by: Kevin Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/atmdev.h | 15 +++++++++++++++
 net/atm/br2684.c       |  3 +--
 net/atm/clip.c         |  3 +--
 net/atm/common.c       |  3 +--
 net/atm/lec.c          |  3 +--
 net/atm/mpc.c          |  3 +--
 net/atm/pppoatm.c      |  3 +--
 net/atm/raw.c          |  4 ++--
 8 files changed, 23 insertions(+), 14 deletions(-)

diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h
index 0c27515d2cf6..8124815eb121 100644
--- a/include/linux/atmdev.h
+++ b/include/linux/atmdev.h
@@ -214,6 +214,7 @@ struct atmphy_ops {
 struct atm_skb_data {
 	struct atm_vcc	*vcc;		/* ATM VCC */
 	unsigned long	atm_options;	/* ATM layer options */
+	unsigned int	acct_truesize;  /* truesize accounted to vcc */
 };
 
 #define VCC_HTABLE_SIZE 32
@@ -241,6 +242,20 @@ void vcc_insert_socket(struct sock *sk);
 
 void atm_dev_release_vccs(struct atm_dev *dev);
 
+static inline void atm_account_tx(struct atm_vcc *vcc, struct sk_buff *skb)
+{
+	/*
+	 * Because ATM skbs may not belong to a sock (and we don't
+	 * necessarily want to), skb->truesize may be adjusted,
+	 * escaping the hack in pskb_expand_head() which avoids
+	 * doing so for some cases. So stash the value of truesize
+	 * at the time we accounted it, and atm_pop_raw() can use
+	 * that value later, in case it changes.
+	 */
+	refcount_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc);
+	ATM_SKB(skb)->acct_truesize = skb->truesize;
+	ATM_SKB(skb)->atm_options = vcc->atm_options;
+}
 
 static inline void atm_force_charge(struct atm_vcc *vcc,int truesize)
 {
diff --git a/net/atm/br2684.c b/net/atm/br2684.c
index 4e111196f902..bc21f8e8daf2 100644
--- a/net/atm/br2684.c
+++ b/net/atm/br2684.c
@@ -252,8 +252,7 @@ static int br2684_xmit_vcc(struct sk_buff *skb, struct net_device *dev,
 
 	ATM_SKB(skb)->vcc = atmvcc = brvcc->atmvcc;
 	pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n", skb, atmvcc, atmvcc->dev);
-	refcount_add(skb->truesize, &sk_atm(atmvcc)->sk_wmem_alloc);
-	ATM_SKB(skb)->atm_options = atmvcc->atm_options;
+	atm_account_tx(atmvcc, skb);
 	dev->stats.tx_packets++;
 	dev->stats.tx_bytes += skb->len;
 
diff --git a/net/atm/clip.c b/net/atm/clip.c
index 65f706e4344c..60920a42f640 100644
--- a/net/atm/clip.c
+++ b/net/atm/clip.c
@@ -381,8 +381,7 @@ static netdev_tx_t clip_start_xmit(struct sk_buff *skb,
 		memcpy(here, llc_oui, sizeof(llc_oui));
 		((__be16 *) here)[3] = skb->protocol;
 	}
-	refcount_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc);
-	ATM_SKB(skb)->atm_options = vcc->atm_options;
+	atm_account_tx(vcc, skb);
 	entry->vccs->last_use = jiffies;
 	pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n", skb, vcc, vcc->dev);
 	old = xchg(&entry->vccs->xoff, 1);	/* assume XOFF ... */
diff --git a/net/atm/common.c b/net/atm/common.c
index 8a4f99114cd2..9e812c782a37 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -630,10 +630,9 @@ int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t size)
 		goto out;
 	}
 	pr_debug("%d += %d\n", sk_wmem_alloc_get(sk), skb->truesize);
-	refcount_add(skb->truesize, &sk->sk_wmem_alloc);
+	atm_account_tx(vcc, skb);
 
 	skb->dev = NULL; /* for paths shared with net_device interfaces */
-	ATM_SKB(skb)->atm_options = vcc->atm_options;
 	if (!copy_from_iter_full(skb_put(skb, size), size, &m->msg_iter)) {
 		kfree_skb(skb);
 		error = -EFAULT;
diff --git a/net/atm/lec.c b/net/atm/lec.c
index 5741b6474dd9..9f2365694ad4 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -182,9 +182,8 @@ lec_send(struct atm_vcc *vcc, struct sk_buff *skb)
 	struct net_device *dev = skb->dev;
 
 	ATM_SKB(skb)->vcc = vcc;
-	ATM_SKB(skb)->atm_options = vcc->atm_options;
+	atm_account_tx(vcc, skb);
 
-	refcount_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc);
 	if (vcc->send(vcc, skb) < 0) {
 		dev->stats.tx_dropped++;
 		return;
diff --git a/net/atm/mpc.c b/net/atm/mpc.c
index 5677147209e8..db9a1838687c 100644
--- a/net/atm/mpc.c
+++ b/net/atm/mpc.c
@@ -555,8 +555,7 @@ static int send_via_shortcut(struct sk_buff *skb, struct mpoa_client *mpc)
 					sizeof(struct llc_snap_hdr));
 	}
 
-	refcount_add(skb->truesize, &sk_atm(entry->shortcut)->sk_wmem_alloc);
-	ATM_SKB(skb)->atm_options = entry->shortcut->atm_options;
+	atm_account_tx(entry->shortcut, skb);
 	entry->shortcut->send(entry->shortcut, skb);
 	entry->packets_fwded++;
 	mpc->in_ops->put(entry);
diff --git a/net/atm/pppoatm.c b/net/atm/pppoatm.c
index 21d9d341a619..af8c4b38b746 100644
--- a/net/atm/pppoatm.c
+++ b/net/atm/pppoatm.c
@@ -350,8 +350,7 @@ static int pppoatm_send(struct ppp_channel *chan, struct sk_buff *skb)
 		return 1;
 	}
 
-	refcount_add(skb->truesize, &sk_atm(ATM_SKB(skb)->vcc)->sk_wmem_alloc);
-	ATM_SKB(skb)->atm_options = ATM_SKB(skb)->vcc->atm_options;
+	atm_account_tx(vcc, skb);
 	pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n",
 		 skb, ATM_SKB(skb)->vcc, ATM_SKB(skb)->vcc->dev);
 	ret = ATM_SKB(skb)->vcc->send(ATM_SKB(skb)->vcc, skb)
diff --git a/net/atm/raw.c b/net/atm/raw.c
index ee10e8d46185..b3ba44aab0ee 100644
--- a/net/atm/raw.c
+++ b/net/atm/raw.c
@@ -35,8 +35,8 @@ static void atm_pop_raw(struct atm_vcc *vcc, struct sk_buff *skb)
 	struct sock *sk = sk_atm(vcc);
 
 	pr_debug("(%d) %d -= %d\n",
-		 vcc->vci, sk_wmem_alloc_get(sk), skb->truesize);
-	WARN_ON(refcount_sub_and_test(skb->truesize, &sk->sk_wmem_alloc));
+		 vcc->vci, sk_wmem_alloc_get(sk), ATM_SKB(skb)->acct_truesize);
+	WARN_ON(refcount_sub_and_test(ATM_SKB(skb)->acct_truesize, &sk->sk_wmem_alloc));
 	dev_kfree_skb_any(skb);
 	sk->sk_write_space(sk);
 }
-- 
2.17.1


From 96a2634fa36b379502ac6e47b599123b4268c219 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Fri, 29 Jun 2018 13:28:07 -0500
Subject: [PATCH 03/35] atm: zatm: Fix potential Spectre v1

[ Upstream commit ced9e191501e52b95e1b57b8e0db00943869eed0 ]

pool can be indirectly controlled by user-space, hence leading to
a potential exploitation of the Spectre variant 1 vulnerability.

This issue was detected with the help of Smatch:

drivers/atm/zatm.c:1491 zatm_ioctl() warn: potential spectre issue
'zatm_dev->pool_info' (local cap)

Fix this by sanitizing pool before using it to index
zatm_dev->pool_info

Notice that given that speculation windows are large, the policy is
to kill the speculation on the first load and not worry if it can be
completed with a dependent load/store [1].

[1] https://marc.info/?l=linux-kernel&m=152449131114778&w=2

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/atm/zatm.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/atm/zatm.c b/drivers/atm/zatm.c
index 9c9a22958717..8de54a7a345f 100644
--- a/drivers/atm/zatm.c
+++ b/drivers/atm/zatm.c
@@ -1483,6 +1483,8 @@ static int zatm_ioctl(struct atm_dev *dev,unsigned int cmd,void __user *arg)
 					return -EFAULT;
 				if (pool < 0 || pool > ZATM_LAST_POOL)
 					return -EINVAL;
+				pool = array_index_nospec(pool,
+							  ZATM_LAST_POOL + 1);
 				if (copy_from_user(&info,
 				    &((struct zatm_pool_req __user *) arg)->info,
 				    sizeof(info))) return -EFAULT;
-- 
2.17.1


From 42e29e27bac581a4183d89aa8921f480507ea48d Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <sthemmin@microsoft.com>
Date: Fri, 29 Jun 2018 14:07:16 -0700
Subject: [PATCH 04/35] hv_netvsc: split sub-channel setup into async and sync

[ Upstream commit 3ffe64f1a641b80a82d9ef4efa7a05ce69049871 ]

When doing device hotplug the sub channel must be async to avoid
deadlock issues because device is discovered in softirq context.

When doing changes to MTU and number of channels, the setup
must be synchronous to avoid races such as when MTU and device
settings are done in a single ip command.

Reported-by: Thomas Walker <Thomas.Walker@twosigma.com>
Fixes: 8195b1396ec8 ("hv_netvsc: fix deadlock on hotplug")
Fixes: 732e49850c5e ("netvsc: fix race on sub channel creation")
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/hyperv_net.h   |  2 +-
 drivers/net/hyperv/netvsc.c       | 37 ++++++++++++++++++-
 drivers/net/hyperv/netvsc_drv.c   | 17 ++++++++-
 drivers/net/hyperv/rndis_filter.c | 61 ++++++-------------------------
 4 files changed, 65 insertions(+), 52 deletions(-)

diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 01017dd88802..cb250cacf721 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -207,7 +207,7 @@ int netvsc_recv_callback(struct net_device *net,
 void netvsc_channel_cb(void *context);
 int netvsc_poll(struct napi_struct *napi, int budget);
 
-void rndis_set_subchannel(struct work_struct *w);
+int rndis_set_subchannel(struct net_device *ndev, struct netvsc_device *nvdev);
 int rndis_filter_open(struct netvsc_device *nvdev);
 int rndis_filter_close(struct netvsc_device *nvdev);
 struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 4647ecbe6f36..701be5d81062 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -62,6 +62,41 @@ void netvsc_switch_datapath(struct net_device *ndev, bool vf)
 			       VM_PKT_DATA_INBAND, 0);
 }
 
+/* Worker to setup sub channels on initial setup
+ * Initial hotplug event occurs in softirq context
+ * and can't wait for channels.
+ */
+static void netvsc_subchan_work(struct work_struct *w)
+{
+	struct netvsc_device *nvdev =
+		container_of(w, struct netvsc_device, subchan_work);
+	struct rndis_device *rdev;
+	int i, ret;
+
+	/* Avoid deadlock with device removal already under RTNL */
+	if (!rtnl_trylock()) {
+		schedule_work(w);
+		return;
+	}
+
+	rdev = nvdev->extension;
+	if (rdev) {
+		ret = rndis_set_subchannel(rdev->ndev, nvdev);
+		if (ret == 0) {
+			netif_device_attach(rdev->ndev);
+		} else {
+			/* fallback to only primary channel */
+			for (i = 1; i < nvdev->num_chn; i++)
+				netif_napi_del(&nvdev->chan_table[i].napi);
+
+			nvdev->max_chn = 1;
+			nvdev->num_chn = 1;
+		}
+	}
+
+	rtnl_unlock();
+}
+
 static struct netvsc_device *alloc_net_device(void)
 {
 	struct netvsc_device *net_device;
@@ -78,7 +113,7 @@ static struct netvsc_device *alloc_net_device(void)
 
 	init_completion(&net_device->channel_init_wait);
 	init_waitqueue_head(&net_device->subchan_open);
-	INIT_WORK(&net_device->subchan_work, rndis_set_subchannel);
+	INIT_WORK(&net_device->subchan_work, netvsc_subchan_work);
 
 	return net_device;
 }
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 6890478a0851..aeabeb107fed 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -911,8 +911,20 @@ static int netvsc_attach(struct net_device *ndev,
 	if (IS_ERR(nvdev))
 		return PTR_ERR(nvdev);
 
-	/* Note: enable and attach happen when sub-channels setup */
+	if (nvdev->num_chn > 1) {
+		ret = rndis_set_subchannel(ndev, nvdev);
+
+		/* if unavailable, just proceed with one queue */
+		if (ret) {
+			nvdev->max_chn = 1;
+			nvdev->num_chn = 1;
+		}
+	}
+
+	/* In any case device is now ready */
+	netif_device_attach(ndev);
 
+	/* Note: enable and attach happen when sub-channels setup */
 	netif_carrier_off(ndev);
 
 	if (netif_running(ndev)) {
@@ -2035,6 +2047,9 @@ static int netvsc_probe(struct hv_device *dev,
 
 	memcpy(net->dev_addr, device_info.mac_adr, ETH_ALEN);
 
+	if (nvdev->num_chn > 1)
+		schedule_work(&nvdev->subchan_work);
+
 	/* hw_features computed in rndis_netdev_set_hwcaps() */
 	net->features = net->hw_features |
 		NETIF_F_HIGHDMA | NETIF_F_SG |
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index d1ae184008b4..cb03a6ea076a 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -1055,29 +1055,15 @@ static void netvsc_sc_open(struct vmbus_channel *new_sc)
  * This breaks overlap of processing the host message for the
  * new primary channel with the initialization of sub-channels.
  */
-void rndis_set_subchannel(struct work_struct *w)
+int rndis_set_subchannel(struct net_device *ndev, struct netvsc_device *nvdev)
 {
-	struct netvsc_device *nvdev
-		= container_of(w, struct netvsc_device, subchan_work);
 	struct nvsp_message *init_packet = &nvdev->channel_init_pkt;
-	struct net_device_context *ndev_ctx;
-	struct rndis_device *rdev;
-	struct net_device *ndev;
-	struct hv_device *hv_dev;
+	struct net_device_context *ndev_ctx = netdev_priv(ndev);
+	struct hv_device *hv_dev = ndev_ctx->device_ctx;
+	struct rndis_device *rdev = nvdev->extension;
 	int i, ret;
 
-	if (!rtnl_trylock()) {
-		schedule_work(w);
-		return;
-	}
-
-	rdev = nvdev->extension;
-	if (!rdev)
-		goto unlock;	/* device was removed */
-
-	ndev = rdev->ndev;
-	ndev_ctx = netdev_priv(ndev);
-	hv_dev = ndev_ctx->device_ctx;
+	ASSERT_RTNL();
 
 	memset(init_packet, 0, sizeof(struct nvsp_message));
 	init_packet->hdr.msg_type = NVSP_MSG5_TYPE_SUBCHANNEL;
@@ -1091,13 +1077,13 @@ void rndis_set_subchannel(struct work_struct *w)
 			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
 	if (ret) {
 		netdev_err(ndev, "sub channel allocate send failed: %d\n", ret);
-		goto failed;
+		return ret;
 	}
 
 	wait_for_completion(&nvdev->channel_init_wait);
 	if (init_packet->msg.v5_msg.subchn_comp.status != NVSP_STAT_SUCCESS) {
 		netdev_err(ndev, "sub channel request failed\n");
-		goto failed;
+		return -EIO;
 	}
 
 	nvdev->num_chn = 1 +
@@ -1116,21 +1102,7 @@ void rndis_set_subchannel(struct work_struct *w)
 	for (i = 0; i < VRSS_SEND_TAB_SIZE; i++)
 		ndev_ctx->tx_table[i] = i % nvdev->num_chn;
 
-	netif_device_attach(ndev);
-	rtnl_unlock();
-	return;
-
-failed:
-	/* fallback to only primary channel */
-	for (i = 1; i < nvdev->num_chn; i++)
-		netif_napi_del(&nvdev->chan_table[i].napi);
-
-	nvdev->max_chn = 1;
-	nvdev->num_chn = 1;
-
-	netif_device_attach(ndev);
-unlock:
-	rtnl_unlock();
+	return 0;
 }
 
 static int rndis_netdev_set_hwcaps(struct rndis_device *rndis_device,
@@ -1321,21 +1293,12 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
 		netif_napi_add(net, &net_device->chan_table[i].napi,
 			       netvsc_poll, NAPI_POLL_WEIGHT);
 
-	if (net_device->num_chn > 1)
-		schedule_work(&net_device->subchan_work);
+	return net_device;
 
 out:
-	/* if unavailable, just proceed with one queue */
-	if (ret) {
-		net_device->max_chn = 1;
-		net_device->num_chn = 1;
-	}
-
-	/* No sub channels, device is ready */
-	if (net_device->num_chn == 1)
-		netif_device_attach(net);
-
-	return net_device;
+	/* setting up multiple channels failed */
+	net_device->max_chn = 1;
+	net_device->num_chn = 1;
 
 err_dev_remv:
 	rndis_filter_device_remove(dev, net_device);
-- 
2.17.1


From 3c1e16963d9df665d0682bad14faaa324daedd2c Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Sat, 30 Jun 2018 15:26:56 -0700
Subject: [PATCH 05/35] ipv6: sr: fix passing wrong flags to
 crypto_alloc_shash()

[ Upstream commit fc9c2029e37c3ae9efc28bf47045e0b87e09660c ]

The 'mask' argument to crypto_alloc_shash() uses the CRYPTO_ALG_* flags,
not 'gfp_t'.  So don't pass GFP_KERNEL to it.

Fixes: bf355b8d2c30 ("ipv6: sr: add core files for SR HMAC support")
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/seg6_hmac.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c
index 33fb35cbfac1..558fe8cc6d43 100644
--- a/net/ipv6/seg6_hmac.c
+++ b/net/ipv6/seg6_hmac.c
@@ -373,7 +373,7 @@ static int seg6_hmac_init_algo(void)
 			return -ENOMEM;
 
 		for_each_possible_cpu(cpu) {
-			tfm = crypto_alloc_shash(algo->name, 0, GFP_KERNEL);
+			tfm = crypto_alloc_shash(algo->name, 0, 0);
 			if (IS_ERR(tfm))
 				return PTR_ERR(tfm);
 			p_tfm = per_cpu_ptr(algo->tfms, cpu);
-- 
2.17.1


From 3ae201e78d44a7f0f016a6ff1ea52eafb0ce2ec8 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 21 Jun 2018 12:56:04 +0800
Subject: [PATCH 06/35] ipvlan: fix IFLA_MTU ignored on NEWLINK

[ Upstream commit 30877961b1cdd6fdca783c2e8c4f0f47e95dc58c ]

Commit 296d48568042 ("ipvlan: inherit MTU from master device") adjusted
the mtu from the master device when creating a ipvlan device, but it
would also override the mtu value set in rtnl_create_link. It causes
IFLA_MTU param not to take effect.

So this patch is to not adjust the mtu if IFLA_MTU param is set when
creating a ipvlan device.

Fixes: 296d48568042 ("ipvlan: inherit MTU from master device")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ipvlan/ipvlan_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index c74893c1e620..e7f7a1a002ee 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -546,7 +546,8 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev,
 	ipvlan->dev = dev;
 	ipvlan->port = port;
 	ipvlan->sfeatures = IPVLAN_FEATURES;
-	ipvlan_adjust_mtu(ipvlan, phy_dev);
+	if (!tb[IFLA_MTU])
+		ipvlan_adjust_mtu(ipvlan, phy_dev);
 	INIT_LIST_HEAD(&ipvlan->addrs);
 
 	/* If the port-id base is at the MAX value, then wrap it around and
-- 
2.17.1


From 60fd040861ea3e7ecde97eae3a8f86714dda175b Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Tue, 26 Jun 2018 17:39:48 +0200
Subject: [PATCH 07/35] ixgbe: split XDP_TX tail and XDP_REDIRECT map flushing

[ Upstream commit ad088ec480768850db019a5cc543685e868a513d ]

The driver was combining the XDP_TX tail flush and XDP_REDIRECT
map flushing (xdp_do_flush_map).  This is suboptimal, these two
flush operations should be kept separate.

Fixes: 11393cc9b9be ("xdp: Add batching support to redirect map")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 24 +++++++++++--------
 1 file changed, 14 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 20a8018d41ef..b68d94b49a8a 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -2211,9 +2211,10 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring,
 	return skb;
 }
 
-#define IXGBE_XDP_PASS 0
-#define IXGBE_XDP_CONSUMED 1
-#define IXGBE_XDP_TX 2
+#define IXGBE_XDP_PASS		0
+#define IXGBE_XDP_CONSUMED	BIT(0)
+#define IXGBE_XDP_TX		BIT(1)
+#define IXGBE_XDP_REDIR		BIT(2)
 
 static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter,
 			       struct xdp_buff *xdp);
@@ -2242,7 +2243,7 @@ static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter,
 	case XDP_REDIRECT:
 		err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog);
 		if (!err)
-			result = IXGBE_XDP_TX;
+			result = IXGBE_XDP_REDIR;
 		else
 			result = IXGBE_XDP_CONSUMED;
 		break;
@@ -2302,7 +2303,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 	unsigned int mss = 0;
 #endif /* IXGBE_FCOE */
 	u16 cleaned_count = ixgbe_desc_unused(rx_ring);
-	bool xdp_xmit = false;
+	unsigned int xdp_xmit = 0;
 
 	while (likely(total_rx_packets < budget)) {
 		union ixgbe_adv_rx_desc *rx_desc;
@@ -2342,8 +2343,10 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 		}
 
 		if (IS_ERR(skb)) {
-			if (PTR_ERR(skb) == -IXGBE_XDP_TX) {
-				xdp_xmit = true;
+			unsigned int xdp_res = -PTR_ERR(skb);
+
+			if (xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR)) {
+				xdp_xmit |= xdp_res;
 				ixgbe_rx_buffer_flip(rx_ring, rx_buffer, size);
 			} else {
 				rx_buffer->pagecnt_bias++;
@@ -2415,7 +2418,10 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 		total_rx_packets++;
 	}
 
-	if (xdp_xmit) {
+	if (xdp_xmit & IXGBE_XDP_REDIR)
+		xdp_do_flush_map();
+
+	if (xdp_xmit & IXGBE_XDP_TX) {
 		struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()];
 
 		/* Force memory writes to complete before letting h/w
@@ -2423,8 +2429,6 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 		 */
 		wmb();
 		writel(ring->next_to_use, ring->tail);
-
-		xdp_do_flush_map();
 	}
 
 	u64_stats_update_begin(&rx_ring->syncp);
-- 
2.17.1


From 4a745edc726bff7156f089eaa61e6e98b8fefe44 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 22 Jun 2018 06:44:14 -0700
Subject: [PATCH 08/35] net: dccp: avoid crash in ccid3_hc_rx_send_feedback()

[ Upstream commit 74174fe5634ffbf645a7ca5a261571f700b2f332 ]

On fast hosts or malicious bots, we trigger a DCCP_BUG() which
seems excessive.

syzbot reported :

BUG: delta (-6195) <= 0 at net/dccp/ccids/ccid3.c:628/ccid3_hc_rx_send_feedback()
CPU: 1 PID: 18 Comm: ksoftirqd/1 Not tainted 4.18.0-rc1+ #112
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c9/0x2b4 lib/dump_stack.c:113
 ccid3_hc_rx_send_feedback net/dccp/ccids/ccid3.c:628 [inline]
 ccid3_hc_rx_packet_recv.cold.16+0x38/0x71 net/dccp/ccids/ccid3.c:793
 ccid_hc_rx_packet_recv net/dccp/ccid.h:185 [inline]
 dccp_deliver_input_to_ccids+0xf0/0x280 net/dccp/input.c:180
 dccp_rcv_established+0x87/0xb0 net/dccp/input.c:378
 dccp_v4_do_rcv+0x153/0x180 net/dccp/ipv4.c:654
 sk_backlog_rcv include/net/sock.h:914 [inline]
 __sk_receive_skb+0x3ba/0xd80 net/core/sock.c:517
 dccp_v4_rcv+0x10f9/0x1f58 net/dccp/ipv4.c:875
 ip_local_deliver_finish+0x2eb/0xda0 net/ipv4/ip_input.c:215
 NF_HOOK include/linux/netfilter.h:287 [inline]
 ip_local_deliver+0x1e9/0x750 net/ipv4/ip_input.c:256
 dst_input include/net/dst.h:450 [inline]
 ip_rcv_finish+0x823/0x2220 net/ipv4/ip_input.c:396
 NF_HOOK include/linux/netfilter.h:287 [inline]
 ip_rcv+0xa18/0x1284 net/ipv4/ip_input.c:492
 __netif_receive_skb_core+0x2488/0x3680 net/core/dev.c:4628
 __netif_receive_skb+0x2c/0x1e0 net/core/dev.c:4693
 process_backlog+0x219/0x760 net/core/dev.c:5373
 napi_poll net/core/dev.c:5771 [inline]
 net_rx_action+0x7da/0x1980 net/core/dev.c:5837
 __do_softirq+0x2e8/0xb17 kernel/softirq.c:284
 run_ksoftirqd+0x86/0x100 kernel/softirq.c:645
 smpboot_thread_fn+0x417/0x870 kernel/smpboot.c:164
 kthread+0x345/0x410 kernel/kthread.c:240
 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:412

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Cc: dccp@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ccids/ccid3.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c
index 119c04317d48..b913ee062a81 100644
--- a/net/dccp/ccids/ccid3.c
+++ b/net/dccp/ccids/ccid3.c
@@ -624,9 +624,8 @@ static void ccid3_hc_rx_send_feedback(struct sock *sk,
 	case CCID3_FBACK_PERIODIC:
 		delta = ktime_us_delta(now, hc->rx_tstamp_last_feedback);
 		if (delta <= 0)
-			DCCP_BUG("delta (%ld) <= 0", (long)delta);
-		else
-			hc->rx_x_recv = scaled_div32(hc->rx_bytes_recv, delta);
+			delta = 1;
+		hc->rx_x_recv = scaled_div32(hc->rx_bytes_recv, delta);
 		break;
 	default:
 		return;
-- 
2.17.1


From 7af8e64e6c731023f16edba31c1656069bf64076 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 22 Jun 2018 06:44:15 -0700
Subject: [PATCH 09/35] net: dccp: switch rx_tstamp_last_feedback to monotonic
 clock

[ Upstream commit 0ce4e70ff00662ad7490e545ba0cd8c1fa179fca ]

To compute delays, better not use time of the day which can
be changed by admins or malicious programs.

Also change ccid3_first_li() to use s64 type for delta variable
to avoid potential overflows.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Cc: dccp@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ccids/ccid3.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c
index b913ee062a81..03fcf3ee1534 100644
--- a/net/dccp/ccids/ccid3.c
+++ b/net/dccp/ccids/ccid3.c
@@ -599,7 +599,7 @@ static void ccid3_hc_rx_send_feedback(struct sock *sk,
 {
 	struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk);
 	struct dccp_sock *dp = dccp_sk(sk);
-	ktime_t now = ktime_get_real();
+	ktime_t now = ktime_get();
 	s64 delta = 0;
 
 	switch (fbtype) {
@@ -631,7 +631,7 @@ static void ccid3_hc_rx_send_feedback(struct sock *sk,
 		return;
 	}
 
-	ccid3_pr_debug("Interval %ldusec, X_recv=%u, 1/p=%u\n", (long)delta,
+	ccid3_pr_debug("Interval %lldusec, X_recv=%u, 1/p=%u\n", delta,
 		       hc->rx_x_recv, hc->rx_pinv);
 
 	hc->rx_tstamp_last_feedback = now;
@@ -678,7 +678,8 @@ static int ccid3_hc_rx_insert_options(struct sock *sk, struct sk_buff *skb)
 static u32 ccid3_first_li(struct sock *sk)
 {
 	struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk);
-	u32 x_recv, p, delta;
+	u32 x_recv, p;
+	s64 delta;
 	u64 fval;
 
 	if (hc->rx_rtt == 0) {
@@ -686,7 +687,9 @@ static u32 ccid3_first_li(struct sock *sk)
 		hc->rx_rtt = DCCP_FALLBACK_RTT;
 	}
 
-	delta  = ktime_to_us(net_timedelta(hc->rx_tstamp_last_feedback));
+	delta = ktime_us_delta(ktime_get(), hc->rx_tstamp_last_feedback);
+	if (delta <= 0)
+		delta = 1;
 	x_recv = scaled_div32(hc->rx_bytes_recv, delta);
 	if (x_recv == 0) {		/* would also trigger divide-by-zero */
 		DCCP_WARN("X_recv==0\n");
-- 
2.17.1


From b734a7c5997d06d008cb47f4ffe1bcd808f60720 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Sat, 30 Jun 2018 17:38:55 +0200
Subject: [PATCH 10/35] net: fix use-after-free in GRO with ESP

[ Upstream commit 603d4cf8fe095b1ee78f423d514427be507fb513 ]

Since the addition of GRO for ESP, gro_receive can consume the skb and
return -EINPROGRESS. In that case, the lower layer GRO handler cannot
touch the skb anymore.

Commit 5f114163f2f5 ("net: Add a skb_gro_flush_final helper.") converted
some of the gro_receive handlers that can lead to ESP's gro_receive so
that they wouldn't access the skb when -EINPROGRESS is returned, but
missed other spots, mainly in tunneling protocols.

This patch finishes the conversion to using skb_gro_flush_final(), and
adds a new helper, skb_gro_flush_final_remcsum(), used in VXLAN and
GUE.

Fixes: 5f114163f2f5 ("net: Add a skb_gro_flush_final helper.")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c      |  2 +-
 drivers/net/vxlan.c       |  4 +---
 include/linux/netdevice.h | 20 ++++++++++++++++++++
 net/8021q/vlan.c          |  2 +-
 net/ipv4/fou.c            |  4 +---
 net/ipv4/gre_offload.c    |  2 +-
 net/ipv4/udp_offload.c    |  2 +-
 7 files changed, 26 insertions(+), 10 deletions(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index fbc825ac97ab..cb51448389a1 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -474,7 +474,7 @@ static struct sk_buff **geneve_gro_receive(struct sock *sk,
 out_unlock:
 	rcu_read_unlock();
 out:
-	NAPI_GRO_CB(skb)->flush |= flush;
+	skb_gro_flush_final(skb, pp, flush);
 
 	return pp;
 }
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 3d9c5b35a4a7..bbdb46916dc3 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -623,9 +623,7 @@ static struct sk_buff **vxlan_gro_receive(struct sock *sk,
 	flush = 0;
 
 out:
-	skb_gro_remcsum_cleanup(skb, &grc);
-	skb->remcsum_offload = 0;
-	NAPI_GRO_CB(skb)->flush |= flush;
+	skb_gro_flush_final_remcsum(skb, pp, flush, &grc);
 
 	return pp;
 }
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 46bf7cc7d5d5..2ea7ee1fb495 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2668,11 +2668,31 @@ static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp,
 	if (PTR_ERR(pp) != -EINPROGRESS)
 		NAPI_GRO_CB(skb)->flush |= flush;
 }
+static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb,
+					       struct sk_buff **pp,
+					       int flush,
+					       struct gro_remcsum *grc)
+{
+	if (PTR_ERR(pp) != -EINPROGRESS) {
+		NAPI_GRO_CB(skb)->flush |= flush;
+		skb_gro_remcsum_cleanup(skb, grc);
+		skb->remcsum_offload = 0;
+	}
+}
 #else
 static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, int flush)
 {
 	NAPI_GRO_CB(skb)->flush |= flush;
 }
+static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb,
+					       struct sk_buff **pp,
+					       int flush,
+					       struct gro_remcsum *grc)
+{
+	NAPI_GRO_CB(skb)->flush |= flush;
+	skb_gro_remcsum_cleanup(skb, grc);
+	skb->remcsum_offload = 0;
+}
 #endif
 
 static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev,
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index cf2e70003a53..cf82d970b0e4 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -664,7 +664,7 @@ static struct sk_buff **vlan_gro_receive(struct sk_buff **head,
 out_unlock:
 	rcu_read_unlock();
 out:
-	NAPI_GRO_CB(skb)->flush |= flush;
+	skb_gro_flush_final(skb, pp, flush);
 
 	return pp;
 }
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 1540db65241a..c9ec1603666b 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -448,9 +448,7 @@ static struct sk_buff **gue_gro_receive(struct sock *sk,
 out_unlock:
 	rcu_read_unlock();
 out:
-	NAPI_GRO_CB(skb)->flush |= flush;
-	skb_gro_remcsum_cleanup(skb, &grc);
-	skb->remcsum_offload = 0;
+	skb_gro_flush_final_remcsum(skb, pp, flush, &grc);
 
 	return pp;
 }
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index 1859c473b21a..6a7d980105f6 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -223,7 +223,7 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head,
 out_unlock:
 	rcu_read_unlock();
 out:
-	NAPI_GRO_CB(skb)->flush |= flush;
+	skb_gro_flush_final(skb, pp, flush);
 
 	return pp;
 }
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index ea6e6e7df0ee..cde2719fcb89 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -295,7 +295,7 @@ struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb,
 out_unlock:
 	rcu_read_unlock();
 out:
-	NAPI_GRO_CB(skb)->flush |= flush;
+	skb_gro_flush_final(skb, pp, flush);
 	return pp;
 }
 EXPORT_SYMBOL(udp_gro_receive);
-- 
2.17.1


From e40a0e8c5107c72e131fce1f0669c51629936e4d Mon Sep 17 00:00:00 2001
From: Harini Katakam <harini.katakam@xilinx.com>
Date: Wed, 20 Jun 2018 17:04:20 +0530
Subject: [PATCH 11/35] net: macb: Fix ptp time adjustment for large negative
 delta

[ Upstream commit 64d7839af8c8f67daaf9bf387135052c55d85f90 ]

When delta passed to gem_ptp_adjtime is negative, the sign is
maintained in the ns_to_timespec64 conversion. Hence timespec_add
should be used directly. timespec_sub will just subtract the negative
value thus increasing the time difference.

Signed-off-by: Harini Katakam <harini.katakam@xilinx.com>
Acked-by: Nicolas Ferre <nicolas.ferre@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_ptp.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_ptp.c b/drivers/net/ethernet/cadence/macb_ptp.c
index 2220c771092b..678835136bf8 100755
--- a/drivers/net/ethernet/cadence/macb_ptp.c
+++ b/drivers/net/ethernet/cadence/macb_ptp.c
@@ -170,10 +170,7 @@ static int gem_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 
 	if (delta > TSU_NSEC_MAX_VAL) {
 		gem_tsu_get_time(&bp->ptp_clock_info, &now);
-		if (sign)
-			now = timespec64_sub(now, then);
-		else
-			now = timespec64_add(now, then);
+		now = timespec64_add(now, then);
 
 		gem_tsu_set_time(&bp->ptp_clock_info,
 				 (const struct timespec64 *)&now);
-- 
2.17.1


From e46724db6660cf788322b92e4fe7f81b57faa5d8 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Thu, 31 May 2018 11:32:56 +0300
Subject: [PATCH 12/35] net/mlx5e: Avoid dealing with vport representors if not
 being e-switch manager

[ Upstream commit 733d3e5497070d05971352ca5087bac83c197c3d ]

In smartnic env, the host (PF) driver might not be an e-switch
manager, hence the switchdev mode representors are running on
the embedded cpu (EC) and not at the host.

As such, we should avoid dealing with vport representors if
not being esw manager.

While here, make sure to disallow eswitch switchdev related
setups through devlink if we are not esw managers.

Fixes: cb67b832921c ('net/mlx5e: Introduce SRIOV VF representors')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c    | 12 ++++++------
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c     |  2 +-
 .../ethernet/mellanox/mlx5/core/eswitch_offloads.c   |  4 ++--
 3 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 337ce9423794..bf34264c734b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2626,7 +2626,7 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv)
 	mlx5e_activate_channels(&priv->channels);
 	netif_tx_start_all_queues(priv->netdev);
 
-	if (MLX5_VPORT_MANAGER(priv->mdev))
+	if (MLX5_ESWITCH_MANAGER(priv->mdev))
 		mlx5e_add_sqs_fwd_rules(priv);
 
 	mlx5e_wait_channels_min_rx_wqes(&priv->channels);
@@ -2637,7 +2637,7 @@ void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv)
 {
 	mlx5e_redirect_rqts_to_drop(priv);
 
-	if (MLX5_VPORT_MANAGER(priv->mdev))
+	if (MLX5_ESWITCH_MANAGER(priv->mdev))
 		mlx5e_remove_sqs_fwd_rules(priv);
 
 	/* FIXME: This is a W/A only for tx timeout watch dog false alarm when
@@ -4127,7 +4127,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	mlx5e_set_netdev_dev_addr(netdev);
 
 #if IS_ENABLED(CONFIG_MLX5_ESWITCH)
-	if (MLX5_VPORT_MANAGER(mdev))
+	if (MLX5_ESWITCH_MANAGER(mdev))
 		netdev->switchdev_ops = &mlx5e_switchdev_ops;
 #endif
 
@@ -4273,7 +4273,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 
 	mlx5e_enable_async_events(priv);
 
-	if (MLX5_VPORT_MANAGER(priv->mdev))
+	if (MLX5_ESWITCH_MANAGER(priv->mdev))
 		mlx5e_register_vport_reps(priv);
 
 	if (netdev->reg_state != NETREG_REGISTERED)
@@ -4300,7 +4300,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv)
 
 	queue_work(priv->wq, &priv->set_rx_mode_work);
 
-	if (MLX5_VPORT_MANAGER(priv->mdev))
+	if (MLX5_ESWITCH_MANAGER(priv->mdev))
 		mlx5e_unregister_vport_reps(priv);
 
 	mlx5e_disable_async_events(priv);
@@ -4483,7 +4483,7 @@ static void *mlx5e_add(struct mlx5_core_dev *mdev)
 		return NULL;
 
 #ifdef CONFIG_MLX5_ESWITCH
-	if (MLX5_VPORT_MANAGER(mdev)) {
+	if (MLX5_ESWITCH_MANAGER(mdev)) {
 		rpriv = mlx5e_alloc_nic_rep_priv(mdev);
 		if (!rpriv) {
 			mlx5_core_warn(mdev, "Failed to alloc NIC rep priv data\n");
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 4727e7390834..3f6a7ca1cee8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -710,7 +710,7 @@ bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv)
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	struct mlx5_eswitch_rep *rep;
 
-	if (!MLX5_CAP_GEN(priv->mdev, vport_group_manager))
+	if (!MLX5_ESWITCH_MANAGER(priv->mdev))
 		return false;
 
 	rep = rpriv->rep;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index d9fd8570b07c..c699055c0ffd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -912,8 +912,8 @@ static int mlx5_devlink_eswitch_check(struct devlink *devlink)
 	if (MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH)
 		return -EOPNOTSUPP;
 
-	if (!MLX5_CAP_GEN(dev, vport_group_manager))
-		return -EOPNOTSUPP;
+	if(!MLX5_ESWITCH_MANAGER(dev))
+		return -EPERM;
 
 	if (dev->priv.eswitch->mode == SRIOV_NONE)
 		return -EOPNOTSUPP;
-- 
2.17.1


From 9359fcebe4ae5af746b9ab5d385ac76c0f42c1b6 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Mon, 4 Jun 2018 19:46:53 +0300
Subject: [PATCH 13/35] net/mlx5e: Don't attempt to dereference the ppriv
 struct if not being eswitch manager

[ Upstream commit 8ffd569aaa818f2624ca821d9a246342fa8b8c50 ]

The check for cpu hit statistics was not returning immediate false for
any non vport rep netdev and hence we crashed (say on mlx5 probed VFs) if
user-space tool was calling into any possible netdev in the system.

Fix that by doing a proper check before dereferencing.

Fixes: 1d447a39142e ('net/mlx5e: Extendable vport representor netdev private data')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reported-by: Eli Cohen <eli@melloanox.com>
Reviewed-by: Eli Cohen <eli@melloanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 3f6a7ca1cee8..0e70cd6d8bc8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -724,8 +724,12 @@ bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv)
 static bool mlx5e_is_vf_vport_rep(struct mlx5e_priv *priv)
 {
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
-	struct mlx5_eswitch_rep *rep = rpriv->rep;
+	struct mlx5_eswitch_rep *rep;
 
+	if (!MLX5_CAP_GEN(priv->mdev, eswitch_flow_table))
+		return false;
+
+	rep = rpriv->rep;
 	if (rep && rep->vport != FDB_UPLINK_VPORT)
 		return true;
 
-- 
2.17.1


From c93e083ac9abd019bfc73d0b4e350a259361c9ff Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Thu, 31 May 2018 11:16:18 +0300
Subject: [PATCH 14/35] net/mlx5: E-Switch, Avoid setup attempt if not being
 e-switch manager

[ Upstream commit 0efc8562491b7d36f6bbc4fbc8f3348cb6641e9c ]

In smartnic env, the host (PF) driver might not be an e-switch
manager, hence the FW will err on driver attempts to deal with
setting/unsetting the eswitch and as a result the overall setup
of sriov will fail.

Fix that by avoiding the operation if e-switch management is not
allowed for this driver instance. While here, move to use the
correct name for the esw manager capability name.

Fixes: 81848731ff40 ('net/mlx5: E-Switch, Add SR-IOV (FDB) support')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reported-by: Guy Kushnir <guyk@mellanox.com>
Reviewed-by: Eli Cohen <eli@melloanox.com>
Tested-by: Eli Cohen <eli@melloanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c  | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 2 ++
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 3 ++-
 drivers/net/ethernet/mellanox/mlx5/core/fw.c      | 5 +++--
 drivers/net/ethernet/mellanox/mlx5/core/sriov.c   | 7 ++++++-
 include/linux/mlx5/mlx5_ifc.h                     | 2 +-
 7 files changed, 16 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 0e70cd6d8bc8..281911698f72 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -726,7 +726,7 @@ static bool mlx5e_is_vf_vport_rep(struct mlx5e_priv *priv)
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	struct mlx5_eswitch_rep *rep;
 
-	if (!MLX5_CAP_GEN(priv->mdev, eswitch_flow_table))
+	if (!MLX5_ESWITCH_MANAGER(priv->mdev))
 		return false;
 
 	rep = rpriv->rep;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 82e37250ed01..667415301066 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1535,7 +1535,7 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
 	if (!ESW_ALLOWED(esw))
 		return 0;
 
-	if (!MLX5_CAP_GEN(esw->dev, eswitch_flow_table) ||
+	if (!MLX5_ESWITCH_MANAGER(esw->dev) ||
 	    !MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ft_support)) {
 		esw_warn(esw->dev, "E-Switch FDB is not supported, aborting ...\n");
 		return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 565c8b7a399a..10bf770675f3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -39,6 +39,8 @@
 #include <linux/mlx5/device.h>
 #include "lib/mpfs.h"
 
+#define MLX5_ESWITCH_MANAGER(mdev) MLX5_CAP_GEN(mdev, eswitch_manager)
+
 enum {
 	SRIOV_NONE,
 	SRIOV_LEGACY,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 33e5ff081e36..dd05cf148845 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -36,6 +36,7 @@
 #include "mlx5_core.h"
 #include "fs_core.h"
 #include "fs_cmd.h"
+#include "eswitch.h"
 #include "diag/fs_tracepoint.h"
 
 #define INIT_TREE_NODE_ARRAY_SIZE(...)	(sizeof((struct init_tree_node[]){__VA_ARGS__}) /\
@@ -2211,7 +2212,7 @@ int mlx5_init_fs(struct mlx5_core_dev *dev)
 			goto err;
 	}
 
-	if (MLX5_CAP_GEN(dev, eswitch_flow_table)) {
+	if (MLX5_ESWITCH_MANAGER(dev)) {
 		if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, ft_support)) {
 			err = init_fdb_root_ns(steering);
 			if (err)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index 2c71557d1cee..d69897a1e2ce 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -34,6 +34,7 @@
 #include <linux/mlx5/cmd.h>
 #include <linux/module.h>
 #include "mlx5_core.h"
+#include "eswitch.h"
 #include "../../mlxfw/mlxfw.h"
 
 static int mlx5_cmd_query_adapter(struct mlx5_core_dev *dev, u32 *out,
@@ -152,13 +153,13 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev)
 	}
 
 	if (MLX5_CAP_GEN(dev, vport_group_manager) &&
-	    MLX5_CAP_GEN(dev, eswitch_flow_table)) {
+	    MLX5_ESWITCH_MANAGER(dev)) {
 		err = mlx5_core_get_caps(dev, MLX5_CAP_ESWITCH_FLOW_TABLE);
 		if (err)
 			return err;
 	}
 
-	if (MLX5_CAP_GEN(dev, eswitch_flow_table)) {
+	if (MLX5_ESWITCH_MANAGER(dev)) {
 		err = mlx5_core_get_caps(dev, MLX5_CAP_ESWITCH);
 		if (err)
 			return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
index 2a8b529ce6dd..a0674962f02c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
@@ -88,6 +88,9 @@ static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs)
 		return -EBUSY;
 	}
 
+	if (!MLX5_ESWITCH_MANAGER(dev))
+		goto enable_vfs_hca;
+
 	err = mlx5_eswitch_enable_sriov(dev->priv.eswitch, num_vfs, SRIOV_LEGACY);
 	if (err) {
 		mlx5_core_warn(dev,
@@ -95,6 +98,7 @@ static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs)
 		return err;
 	}
 
+enable_vfs_hca:
 	for (vf = 0; vf < num_vfs; vf++) {
 		err = mlx5_core_enable_hca(dev, vf + 1);
 		if (err) {
@@ -140,7 +144,8 @@ static void mlx5_device_disable_sriov(struct mlx5_core_dev *dev)
 	}
 
 out:
-	mlx5_eswitch_disable_sriov(dev->priv.eswitch);
+	if (MLX5_ESWITCH_MANAGER(dev))
+		mlx5_eswitch_disable_sriov(dev->priv.eswitch);
 
 	if (mlx5_wait_for_vf_pages(dev))
 		mlx5_core_warn(dev, "timeout reclaiming VFs pages\n");
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index f3765155fa4d..1d793d86d55f 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -857,7 +857,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         reserved_at_1a4[0x1];
 	u8         ets[0x1];
 	u8         nic_flow_table[0x1];
-	u8         eswitch_flow_table[0x1];
+	u8         eswitch_manager[0x1];
 	u8	   early_vf_enable[0x1];
 	u8         mcam_reg[0x1];
 	u8         pcam_reg[0x1];
-- 
2.17.1


From ba65b67a8349a27cb50ca881c1fba6b011a9cc89 Mon Sep 17 00:00:00 2001
From: Alex Vesker <valex@mellanox.com>
Date: Tue, 12 Jun 2018 16:14:31 +0300
Subject: [PATCH 15/35] net/mlx5: Fix command interface race in polling mode

[ Upstream commit d412c31dae053bf30a1bc15582a9990df297a660 ]

The command interface can work in two modes: Events and Polling.
In the general case, each time we invoke a command, a work is
queued to handle it.

When working in events, the interrupt handler completes the
command execution. On the other hand, when working in polling
mode, the work itself completes it.

Due to a bug in the work handler, a command could have been
completed by the interrupt handler, while the work handler
hasn't finished yet, causing the it to complete once again
if the command interface mode was changed from Events to
polling after the interrupt handler was called.

mlx5_unload_one()
        mlx5_stop_eqs()
                // Destroy the EQ before cmd EQ
                ...cmd_work_handler()
                        write_doorbell()
                        --> EVENT_TYPE_CMD
                                mlx5_cmd_comp_handler() // First free
                                        free_ent(cmd, ent->idx)
                                        complete(&ent->done)

        <-- mlx5_stop_eqs //cmd was complete
                // move to polling before destroying the last cmd EQ
                mlx5_cmd_use_polling()
                        cmd->mode = POLL;

                --> cmd_work_handler (continues)
                        if (cmd->mode == POLL)
                                mlx5_cmd_comp_handler() // Double free

The solution is to store the cmd->mode before writing the doorbell.

Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters")
Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 3efe45bc2471..c5b649316bc1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -801,6 +801,7 @@ static void cmd_work_handler(struct work_struct *work)
 	unsigned long flags;
 	bool poll_cmd = ent->polling;
 	int alloc_ret;
+	int cmd_mode;
 
 	sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem;
 	down(sem);
@@ -847,6 +848,7 @@ static void cmd_work_handler(struct work_struct *work)
 	set_signature(ent, !cmd->checksum_disabled);
 	dump_command(dev, ent, 1);
 	ent->ts1 = ktime_get_ns();
+	cmd_mode = cmd->mode;
 
 	if (ent->callback)
 		schedule_delayed_work(&ent->cb_timeout_work, cb_timeout);
@@ -871,7 +873,7 @@ static void cmd_work_handler(struct work_struct *work)
 	iowrite32be(1 << ent->idx, &dev->iseg->cmd_dbell);
 	mmiowb();
 	/* if not in polling don't use ent after this point */
-	if (cmd->mode == CMD_MODE_POLLING || poll_cmd) {
+	if (cmd_mode == CMD_MODE_POLLING || poll_cmd) {
 		poll_timeout(ent);
 		/* make sure we read the descriptor after ownership is SW */
 		rmb();
-- 
2.17.1


From 7a9c6789e0f83a19344811d54b7628df0a28f9c2 Mon Sep 17 00:00:00 2001
From: Alex Vesker <valex@mellanox.com>
Date: Fri, 25 May 2018 20:25:59 +0300
Subject: [PATCH 16/35] net/mlx5: Fix incorrect raw command length parsing

[ Upstream commit 603b7bcff824740500ddfa001d7a7168b0b38542 ]

The NULL character was not set correctly for the string containing
the command length, this caused failures reading the output of the
command due to a random length. The fix is to initialize the output
length string.

Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters")
Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index c5b649316bc1..cf94fdf25155 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -1274,7 +1274,7 @@ static ssize_t outlen_write(struct file *filp, const char __user *buf,
 {
 	struct mlx5_core_dev *dev = filp->private_data;
 	struct mlx5_cmd_debug *dbg = &dev->cmd.dbg;
-	char outlen_str[8];
+	char outlen_str[8] = {0};
 	int outlen;
 	void *ptr;
 	int err;
@@ -1289,8 +1289,6 @@ static ssize_t outlen_write(struct file *filp, const char __user *buf,
 	if (copy_from_user(outlen_str, buf, count))
 		return -EFAULT;
 
-	outlen_str[7] = 0;
-
 	err = sscanf(outlen_str, "%d", &outlen);
 	if (err < 0)
 		return err;
-- 
2.17.1


From 60c2cf77220f7921fd6870baa301cd4ea1d9b63a Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.com>
Date: Wed, 13 Jun 2018 10:27:34 +0300
Subject: [PATCH 17/35] net/mlx5: Fix required capability for manipulating MPFS

[ Upstream commit f811980444ec59ad62f9e041adbb576a821132c7 ]

Manipulating of the MPFS requires eswitch manager capabilities.

Fixes: eeb66cdb6826 ('net/mlx5: Separate between E-Switch and MPFS')
Signed-off-by: Eli Cohen <eli@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c
index 7cb67122e8b5..22811ecd8fcd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c
@@ -34,6 +34,7 @@
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/mlx5_ifc.h>
 #include "mlx5_core.h"
+#include "eswitch.h"
 #include "lib/mpfs.h"
 
 /* HW L2 Table (MPFS) management */
@@ -98,7 +99,7 @@ int mlx5_mpfs_init(struct mlx5_core_dev *dev)
 	int l2table_size = 1 << MLX5_CAP_GEN(dev, log_max_l2_table);
 	struct mlx5_mpfs *mpfs;
 
-	if (!MLX5_VPORT_MANAGER(dev))
+	if (!MLX5_ESWITCH_MANAGER(dev))
 		return 0;
 
 	mpfs = kzalloc(sizeof(*mpfs), GFP_KERNEL);
@@ -122,7 +123,7 @@ void mlx5_mpfs_cleanup(struct mlx5_core_dev *dev)
 {
 	struct mlx5_mpfs *mpfs = dev->priv.mpfs;
 
-	if (!MLX5_VPORT_MANAGER(dev))
+	if (!MLX5_ESWITCH_MANAGER(dev))
 		return;
 
 	WARN_ON(!hlist_empty(mpfs->hash));
@@ -137,7 +138,7 @@ int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac)
 	u32 index;
 	int err;
 
-	if (!MLX5_VPORT_MANAGER(dev))
+	if (!MLX5_ESWITCH_MANAGER(dev))
 		return 0;
 
 	mutex_lock(&mpfs->lock);
@@ -179,7 +180,7 @@ int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac)
 	int err = 0;
 	u32 index;
 
-	if (!MLX5_VPORT_MANAGER(dev))
+	if (!MLX5_ESWITCH_MANAGER(dev))
 		return 0;
 
 	mutex_lock(&mpfs->lock);
-- 
2.17.1


From 3435a026ab9f887a02c600df64ff75ec48e3bd98 Mon Sep 17 00:00:00 2001
From: Shay Agroskin <shayag@mellanox.com>
Date: Tue, 22 May 2018 14:14:02 +0300
Subject: [PATCH 18/35] net/mlx5: Fix wrong size allocation for QoS ETC TC
 regitster

[ Upstream commit d14fcb8d877caf1b8d6bd65d444bf62b21f2070c ]

The driver allocates wrong size (due to wrong struct name) when issuing
a query/set request to NIC's register.

Fixes: d8880795dabf ("net/mlx5e: Implement DCBNL IEEE max rate")
Signed-off-by: Shay Agroskin <shayag@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/port.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index e07061f565d6..ccb6287aeeb7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -641,7 +641,7 @@ EXPORT_SYMBOL_GPL(mlx5_query_port_prio_tc);
 static int mlx5_set_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *in,
 				   int inlen)
 {
-	u32 out[MLX5_ST_SZ_DW(qtct_reg)];
+	u32 out[MLX5_ST_SZ_DW(qetc_reg)];
 
 	if (!MLX5_CAP_GEN(mdev, ets))
 		return -EOPNOTSUPP;
@@ -653,7 +653,7 @@ static int mlx5_set_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *in,
 static int mlx5_query_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *out,
 				     int outlen)
 {
-	u32 in[MLX5_ST_SZ_DW(qtct_reg)];
+	u32 in[MLX5_ST_SZ_DW(qetc_reg)];
 
 	if (!MLX5_CAP_GEN(mdev, ets))
 		return -EOPNOTSUPP;
-- 
2.17.1


From d323bb4955f2b392d737ed73ba65074606f1a80b Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Fri, 22 Jun 2018 10:15:39 +0200
Subject: [PATCH 19/35] net: mvneta: fix the Rx desc DMA address in the Rx path

[ Upstream commit 271f7ff5aa5a73488b7a9d8b84b5205fb5b2f7cc ]

When using s/w buffer management, buffers are allocated and DMA mapped.
When doing so on an arm64 platform, an offset correction is applied on
the DMA address, before storing it in an Rx descriptor. The issue is
this DMA address is then used later in the Rx path without removing the
offset correction. Thus the DMA address is wrong, which can led to
various issues.

This patch fixes this by removing the offset correction from the DMA
address retrieved from the Rx descriptor before using it in the Rx path.

Fixes: 8d5047cf9ca2 ("net: mvneta: Convert to be 64 bits compatible")
Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index d28f873169a9..3deaa3413313 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -1959,7 +1959,7 @@ static int mvneta_rx_swbm(struct mvneta_port *pp, int rx_todo,
 		rx_bytes = rx_desc->data_size - (ETH_FCS_LEN + MVNETA_MH_SIZE);
 		index = rx_desc - rxq->descs;
 		data = rxq->buf_virt_addr[index];
-		phys_addr = rx_desc->buf_phys_addr;
+		phys_addr = rx_desc->buf_phys_addr - pp->rx_offset_correction;
 
 		if (!mvneta_rxq_desc_is_first_last(rx_status) ||
 		    (rx_status & MVNETA_RXD_ERR_SUMMARY)) {
-- 
2.17.1


From 47042980c6f2039e9d8769b1de178c4ec5c260dc Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 21 Jun 2018 14:16:02 -0700
Subject: [PATCH 20/35] net/packet: fix use-after-free

[ Upstream commit 945d015ee0c3095d2290e845565a23dedfd8027c ]

We should put copy_skb in receive_queue only after
a successful call to virtio_net_hdr_from_skb().

syzbot report :

BUG: KASAN: use-after-free in __skb_unlink include/linux/skbuff.h:1843 [inline]
BUG: KASAN: use-after-free in __skb_dequeue include/linux/skbuff.h:1863 [inline]
BUG: KASAN: use-after-free in skb_dequeue+0x16a/0x180 net/core/skbuff.c:2815
Read of size 8 at addr ffff8801b044ecc0 by task syz-executor217/4553

CPU: 0 PID: 4553 Comm: syz-executor217 Not tainted 4.18.0-rc1+ #111
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c9/0x2b4 lib/dump_stack.c:113
 print_address_description+0x6c/0x20b mm/kasan/report.c:256
 kasan_report_error mm/kasan/report.c:354 [inline]
 kasan_report.cold.7+0x242/0x2fe mm/kasan/report.c:412
 __asan_report_load8_noabort+0x14/0x20 mm/kasan/report.c:433
 __skb_unlink include/linux/skbuff.h:1843 [inline]
 __skb_dequeue include/linux/skbuff.h:1863 [inline]
 skb_dequeue+0x16a/0x180 net/core/skbuff.c:2815
 skb_queue_purge+0x26/0x40 net/core/skbuff.c:2852
 packet_set_ring+0x675/0x1da0 net/packet/af_packet.c:4331
 packet_release+0x630/0xd90 net/packet/af_packet.c:2991
 __sock_release+0xd7/0x260 net/socket.c:603
 sock_close+0x19/0x20 net/socket.c:1186
 __fput+0x35b/0x8b0 fs/file_table.c:209
 ____fput+0x15/0x20 fs/file_table.c:243
 task_work_run+0x1ec/0x2a0 kernel/task_work.c:113
 exit_task_work include/linux/task_work.h:22 [inline]
 do_exit+0x1b08/0x2750 kernel/exit.c:865
 do_group_exit+0x177/0x440 kernel/exit.c:968
 __do_sys_exit_group kernel/exit.c:979 [inline]
 __se_sys_exit_group kernel/exit.c:977 [inline]
 __x64_sys_exit_group+0x3e/0x50 kernel/exit.c:977
 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x4448e9
Code: Bad RIP value.
RSP: 002b:00007ffd5f777ca8 EFLAGS: 00000202 ORIG_RAX: 00000000000000e7
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00000000004448e9
RDX: 00000000004448e9 RSI: 000000000000fcfb RDI: 0000000000000001
RBP: 00000000006cf018 R08: 00007ffd0000a45b R09: 0000000000000000
R10: 00007ffd5f777e48 R11: 0000000000000202 R12: 00000000004021f0
R13: 0000000000402280 R14: 0000000000000000 R15: 0000000000000000

Allocated by task 4553:
 save_stack+0x43/0xd0 mm/kasan/kasan.c:448
 set_track mm/kasan/kasan.c:460 [inline]
 kasan_kmalloc+0xc4/0xe0 mm/kasan/kasan.c:553
 kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:490
 kmem_cache_alloc+0x12e/0x760 mm/slab.c:3554
 skb_clone+0x1f5/0x500 net/core/skbuff.c:1282
 tpacket_rcv+0x28f7/0x3200 net/packet/af_packet.c:2221
 deliver_skb net/core/dev.c:1925 [inline]
 deliver_ptype_list_skb net/core/dev.c:1940 [inline]
 __netif_receive_skb_core+0x1bfb/0x3680 net/core/dev.c:4611
 __netif_receive_skb+0x2c/0x1e0 net/core/dev.c:4693
 netif_receive_skb_internal+0x12e/0x7d0 net/core/dev.c:4767
 netif_receive_skb+0xbf/0x420 net/core/dev.c:4791
 tun_rx_batched.isra.55+0x4ba/0x8c0 drivers/net/tun.c:1571
 tun_get_user+0x2af1/0x42f0 drivers/net/tun.c:1981
 tun_chr_write_iter+0xb9/0x154 drivers/net/tun.c:2009
 call_write_iter include/linux/fs.h:1795 [inline]
 new_sync_write fs/read_write.c:474 [inline]
 __vfs_write+0x6c6/0x9f0 fs/read_write.c:487
 vfs_write+0x1f8/0x560 fs/read_write.c:549
 ksys_write+0x101/0x260 fs/read_write.c:598
 __do_sys_write fs/read_write.c:610 [inline]
 __se_sys_write fs/read_write.c:607 [inline]
 __x64_sys_write+0x73/0xb0 fs/read_write.c:607
 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Freed by task 4553:
 save_stack+0x43/0xd0 mm/kasan/kasan.c:448
 set_track mm/kasan/kasan.c:460 [inline]
 __kasan_slab_free+0x11a/0x170 mm/kasan/kasan.c:521
 kasan_slab_free+0xe/0x10 mm/kasan/kasan.c:528
 __cache_free mm/slab.c:3498 [inline]
 kmem_cache_free+0x86/0x2d0 mm/slab.c:3756
 kfree_skbmem+0x154/0x230 net/core/skbuff.c:582
 __kfree_skb net/core/skbuff.c:642 [inline]
 kfree_skb+0x1a5/0x580 net/core/skbuff.c:659
 tpacket_rcv+0x189e/0x3200 net/packet/af_packet.c:2385
 deliver_skb net/core/dev.c:1925 [inline]
 deliver_ptype_list_skb net/core/dev.c:1940 [inline]
 __netif_receive_skb_core+0x1bfb/0x3680 net/core/dev.c:4611
 __netif_receive_skb+0x2c/0x1e0 net/core/dev.c:4693
 netif_receive_skb_internal+0x12e/0x7d0 net/core/dev.c:4767
 netif_receive_skb+0xbf/0x420 net/core/dev.c:4791
 tun_rx_batched.isra.55+0x4ba/0x8c0 drivers/net/tun.c:1571
 tun_get_user+0x2af1/0x42f0 drivers/net/tun.c:1981
 tun_chr_write_iter+0xb9/0x154 drivers/net/tun.c:2009
 call_write_iter include/linux/fs.h:1795 [inline]
 new_sync_write fs/read_write.c:474 [inline]
 __vfs_write+0x6c6/0x9f0 fs/read_write.c:487
 vfs_write+0x1f8/0x560 fs/read_write.c:549
 ksys_write+0x101/0x260 fs/read_write.c:598
 __do_sys_write fs/read_write.c:610 [inline]
 __se_sys_write fs/read_write.c:607 [inline]
 __x64_sys_write+0x73/0xb0 fs/read_write.c:607
 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

The buggy address belongs to the object at ffff8801b044ecc0
 which belongs to the cache skbuff_head_cache of size 232
The buggy address is located 0 bytes inside of
 232-byte region [ffff8801b044ecc0, ffff8801b044eda8)
The buggy address belongs to the page:
page:ffffea0006c11380 count:1 mapcount:0 mapping:ffff8801d9be96c0 index:0x0
flags: 0x2fffc0000000100(slab)
raw: 02fffc0000000100 ffffea0006c17988 ffff8801d9bec248 ffff8801d9be96c0
raw: 0000000000000000 ffff8801b044e040 000000010000000c 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff8801b044eb80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
 ffff8801b044ec00: 00 00 00 00 00 00 00 00 00 00 00 00 00 fc fc fc
>ffff8801b044ec80: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb
                                           ^
 ffff8801b044ed00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff8801b044ed80: fb fb fb fb fb fc fc fc fc fc fc fc fc fc fc fc

Fixes: 58d19b19cd99 ("packet: vnet_hdr support for tpacket_rcv")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 16 +++++++---------
 1 file changed, 7 insertions(+), 9 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 4fe2e34522d6..27dafe36f29c 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2303,6 +2303,13 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 		if (po->stats.stats1.tp_drops)
 			status |= TP_STATUS_LOSING;
 	}
+
+	if (do_vnet &&
+	    virtio_net_hdr_from_skb(skb, h.raw + macoff -
+				    sizeof(struct virtio_net_hdr),
+				    vio_le(), true, 0))
+		goto drop_n_account;
+
 	po->stats.stats1.tp_packets++;
 	if (copy_skb) {
 		status |= TP_STATUS_COPY;
@@ -2310,15 +2317,6 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	}
 	spin_unlock(&sk->sk_receive_queue.lock);
 
-	if (do_vnet) {
-		if (virtio_net_hdr_from_skb(skb, h.raw + macoff -
-					    sizeof(struct virtio_net_hdr),
-					    vio_le(), true, 0)) {
-			spin_lock(&sk->sk_receive_queue.lock);
-			goto drop_n_account;
-		}
-	}
-
 	skb_copy_bits(skb, 0, h.raw + macoff, snaplen);
 
 	if (!(ts_status = tpacket_get_timestamp(skb, &ts, po->tp_tstamp)))
-- 
2.17.1


From 8c932714f7153ab562445cd85cec5f1279c203b5 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Date: Fri, 15 Jun 2018 13:27:31 +0300
Subject: [PATCH 21/35] net_sched: blackhole: tell upper qdisc about dropped
 packets

[ Upstream commit 7e85dc8cb35abf16455f1511f0670b57c1a84608 ]

When blackhole is used on top of classful qdisc like hfsc it breaks
qlen and backlog counters because packets are disappear without notice.

In HFSC non-zero qlen while all classes are inactive triggers warning:
WARNING: ... at net/sched/sch_hfsc.c:1393 hfsc_dequeue+0xba4/0xe90 [sch_hfsc]
and schedules watchdog work endlessly.

This patch return __NET_XMIT_BYPASS in addition to NET_XMIT_SUCCESS,
this flag tells upper layer: this packet is gone and isn't queued.

Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_blackhole.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_blackhole.c b/net/sched/sch_blackhole.c
index c98a61e980ba..9c4c2bb547d7 100644
--- a/net/sched/sch_blackhole.c
+++ b/net/sched/sch_blackhole.c
@@ -21,7 +21,7 @@ static int blackhole_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 			     struct sk_buff **to_free)
 {
 	qdisc_drop(skb, sch, to_free);
-	return NET_XMIT_SUCCESS;
+	return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
 }
 
 static struct sk_buff *blackhole_dequeue(struct Qdisc *sch)
-- 
2.17.1


From 51d68893bf15375baf13eba4a0d66a1213c3a8a8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 19 Jun 2018 19:18:50 -0700
Subject: [PATCH 22/35] net: sungem: fix rx checksum support

[ Upstream commit 12b03558cef6d655d0d394f5e98a6fd07c1f6c0f ]

After commit 88078d98d1bb ("net: pskb_trim_rcsum() and CHECKSUM_COMPLETE
are friends"), sungem owners reported the infamous "eth0: hw csum failure"
message.

CHECKSUM_COMPLETE has in fact never worked for this driver, but this
was masked by the fact that upper stacks had to strip the FCS, and
therefore skb->ip_summed was set back to CHECKSUM_NONE before
my recent change.

Driver configures a number of bytes to skip when the chip computes
the checksum, and for some reason only half of the Ethernet header
was skipped.

Then a second problem is that we should strip the FCS by default,
unless the driver is updated to eventually support NETIF_F_RXFCS in
the future.

Finally, a driver should check if NETIF_F_RXCSUM feature is enabled
or not, so that the admin can turn off rx checksum if wanted.

Many thanks to Andreas Schwab and Mathieu Malaterre for their
help in debugging this issue.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Meelis Roos <mroos@linux.ee>
Reported-by: Mathieu Malaterre <malat@debian.org>
Reported-by: Andreas Schwab <schwab@linux-m68k.org>
Tested-by: Andreas Schwab <schwab@linux-m68k.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sun/sungem.c | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c
index fa607d062cb3..15cd086e3f47 100644
--- a/drivers/net/ethernet/sun/sungem.c
+++ b/drivers/net/ethernet/sun/sungem.c
@@ -59,8 +59,7 @@
 #include <linux/sungem_phy.h>
 #include "sungem.h"
 
-/* Stripping FCS is causing problems, disabled for now */
-#undef STRIP_FCS
+#define STRIP_FCS
 
 #define DEFAULT_MSG	(NETIF_MSG_DRV		| \
 			 NETIF_MSG_PROBE	| \
@@ -434,7 +433,7 @@ static int gem_rxmac_reset(struct gem *gp)
 	writel(desc_dma & 0xffffffff, gp->regs + RXDMA_DBLOW);
 	writel(RX_RING_SIZE - 4, gp->regs + RXDMA_KICK);
 	val = (RXDMA_CFG_BASE | (RX_OFFSET << 10) |
-	       ((14 / 2) << 13) | RXDMA_CFG_FTHRESH_128);
+	       (ETH_HLEN << 13) | RXDMA_CFG_FTHRESH_128);
 	writel(val, gp->regs + RXDMA_CFG);
 	if (readl(gp->regs + GREG_BIFCFG) & GREG_BIFCFG_M66EN)
 		writel(((5 & RXDMA_BLANK_IPKTS) |
@@ -759,7 +758,6 @@ static int gem_rx(struct gem *gp, int work_to_do)
 	struct net_device *dev = gp->dev;
 	int entry, drops, work_done = 0;
 	u32 done;
-	__sum16 csum;
 
 	if (netif_msg_rx_status(gp))
 		printk(KERN_DEBUG "%s: rx interrupt, done: %d, rx_new: %d\n",
@@ -854,9 +852,13 @@ static int gem_rx(struct gem *gp, int work_to_do)
 			skb = copy_skb;
 		}
 
-		csum = (__force __sum16)htons((status & RXDCTRL_TCPCSUM) ^ 0xffff);
-		skb->csum = csum_unfold(csum);
-		skb->ip_summed = CHECKSUM_COMPLETE;
+		if (likely(dev->features & NETIF_F_RXCSUM)) {
+			__sum16 csum;
+
+			csum = (__force __sum16)htons((status & RXDCTRL_TCPCSUM) ^ 0xffff);
+			skb->csum = csum_unfold(csum);
+			skb->ip_summed = CHECKSUM_COMPLETE;
+		}
 		skb->protocol = eth_type_trans(skb, gp->dev);
 
 		napi_gro_receive(&gp->napi, skb);
@@ -1760,7 +1762,7 @@ static void gem_init_dma(struct gem *gp)
 	writel(0, gp->regs + TXDMA_KICK);
 
 	val = (RXDMA_CFG_BASE | (RX_OFFSET << 10) |
-	       ((14 / 2) << 13) | RXDMA_CFG_FTHRESH_128);
+	       (ETH_HLEN << 13) | RXDMA_CFG_FTHRESH_128);
 	writel(val, gp->regs + RXDMA_CFG);
 
 	writel(desc_dma >> 32, gp->regs + RXDMA_DBHI);
@@ -2986,8 +2988,8 @@ static int gem_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	pci_set_drvdata(pdev, dev);
 
 	/* We can do scatter/gather and HW checksum */
-	dev->hw_features = NETIF_F_SG | NETIF_F_HW_CSUM;
-	dev->features |= dev->hw_features | NETIF_F_RXCSUM;
+	dev->hw_features = NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_RXCSUM;
+	dev->features = dev->hw_features;
 	if (pci_using_dac)
 		dev->features |= NETIF_F_HIGHDMA;
 
-- 
2.17.1


From b39b6718298983b8e390892bb3919bda8a2b9426 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Mon, 18 Jun 2018 12:30:37 -0700
Subject: [PATCH 23/35] net/tcp: Fix socket lookups with SO_BINDTODEVICE

[ Upstream commit 8c43bd1706885ba1acfa88da02bc60a2ec16f68c ]

Similar to 69678bcd4d2d ("udp: fix SO_BINDTODEVICE"), TCP socket lookups
need to fail if dev_match is not true. Currently, a packet to a given port
can match a socket bound to device when it should not. In the VRF case,
this causes the lookup to hit a VRF socket and not a global socket
resulting in a response trying to go through the VRF when it should not.

Fixes: 3fa6f616a7a4d ("net: ipv4: add second dif to inet socket lookups")
Fixes: 4297a0ef08572 ("net: ipv6: add second dif to inet6 socket lookups")
Reported-by: Lou Berger <lberger@labn.net>
Diagnosed-by: Renato Westphal <renato@opensourcerouting.org>
Tested-by: Renato Westphal <renato@opensourcerouting.org>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/inet_hashtables.c  | 4 ++--
 net/ipv6/inet6_hashtables.c | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index e7d15fb0d94d..24b066c32e06 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -188,9 +188,9 @@ static inline int compute_score(struct sock *sk, struct net *net,
 			bool dev_match = (sk->sk_bound_dev_if == dif ||
 					  sk->sk_bound_dev_if == sdif);
 
-			if (exact_dif && !dev_match)
+			if (!dev_match)
 				return -1;
-			if (sk->sk_bound_dev_if && dev_match)
+			if (sk->sk_bound_dev_if)
 				score += 4;
 		}
 		if (sk->sk_incoming_cpu == raw_smp_processor_id())
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index b01858f5deb1..6dc93ac28261 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -113,9 +113,9 @@ static inline int compute_score(struct sock *sk, struct net *net,
 			bool dev_match = (sk->sk_bound_dev_if == dif ||
 					  sk->sk_bound_dev_if == sdif);
 
-			if (exact_dif && !dev_match)
+			if (!dev_match)
 				return -1;
-			if (sk->sk_bound_dev_if && dev_match)
+			if (sk->sk_bound_dev_if)
 				score++;
 		}
 		if (sk->sk_incoming_cpu == raw_smp_processor_id())
-- 
2.17.1


From 59b9cbf1de17c6304f4a9e4b674a98e223de4be9 Mon Sep 17 00:00:00 2001
From: Sudarsana Reddy Kalluru <sudarsana.kalluru@cavium.com>
Date: Sun, 1 Jul 2018 20:03:08 -0700
Subject: [PATCH 24/35] qede: Adverstise software timestamp caps when PHC is
 not available.

[ Upstream commit 82a4e71b1565dea8387f54503e806cf374e779ec ]

When ptp clock is not available for a PF (e.g., higher PFs in NPAR mode),
get-tsinfo() callback should return the software timestamp capabilities
instead of returning the error.

Fixes: 4c55215c ("qede: Add driver support for PTP")
Signed-off-by: Sudarsana Reddy Kalluru <Sudarsana.Kalluru@cavium.com>
Signed-off-by: Michal Kalderon <Michal.Kalderon@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qede/qede_ptp.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qede/qede_ptp.c b/drivers/net/ethernet/qlogic/qede/qede_ptp.c
index 9b2280badaf7..475f6ae5d4b3 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ptp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ptp.c
@@ -337,8 +337,14 @@ int qede_ptp_get_ts_info(struct qede_dev *edev, struct ethtool_ts_info *info)
 {
 	struct qede_ptp *ptp = edev->ptp;
 
-	if (!ptp)
-		return -EIO;
+	if (!ptp) {
+		info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
+					SOF_TIMESTAMPING_RX_SOFTWARE |
+					SOF_TIMESTAMPING_SOFTWARE;
+		info->phc_index = -1;
+
+		return 0;
+	}
 
 	info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
 				SOF_TIMESTAMPING_RX_SOFTWARE |
-- 
2.17.1


From f39e96abb139cc64498f06faa960c7614ad6857e Mon Sep 17 00:00:00 2001
From: Sudarsana Reddy Kalluru <sudarsana.kalluru@cavium.com>
Date: Sun, 1 Jul 2018 20:03:06 -0700
Subject: [PATCH 25/35] qed: Fix setting of incorrect eswitch mode.

[ Upstream commit 538f8d00ba8bb417c4d9e76c61dee59d812d8287 ]

By default, driver sets the eswitch mode incorrectly as VEB (virtual
Ethernet bridging).
Need to set VEB eswitch mode only when sriov is enabled, and it should be
to set NONE by default. The patch incorporates this change.

Fixes: 0fefbfbaa ("qed*: Management firmware - notifications and defaults")
Signed-off-by: Sudarsana Reddy Kalluru <Sudarsana.Kalluru@cavium.com>
Signed-off-by: Michal Kalderon <Michal.Kalderon@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_dev.c   |  2 +-
 drivers/net/ethernet/qlogic/qed/qed_sriov.c | 19 +++++++++++++++++--
 2 files changed, 18 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index 58a689fb04db..ef2374699726 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -1782,7 +1782,7 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
 			DP_INFO(p_hwfn, "Failed to update driver state\n");
 
 		rc = qed_mcp_ov_update_eswitch(p_hwfn, p_hwfn->p_main_ptt,
-					       QED_OV_ESWITCH_VEB);
+					       QED_OV_ESWITCH_NONE);
 		if (rc)
 			DP_INFO(p_hwfn, "Failed to update eswitch mode\n");
 	}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
index 3f40b1de7957..d08fe350ab6c 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
@@ -4396,6 +4396,8 @@ static void qed_sriov_enable_qid_config(struct qed_hwfn *hwfn,
 static int qed_sriov_enable(struct qed_dev *cdev, int num)
 {
 	struct qed_iov_vf_init_params params;
+	struct qed_hwfn *hwfn;
+	struct qed_ptt *ptt;
 	int i, j, rc;
 
 	if (num >= RESC_NUM(&cdev->hwfns[0], QED_VPORT)) {
@@ -4408,8 +4410,8 @@ static int qed_sriov_enable(struct qed_dev *cdev, int num)
 
 	/* Initialize HW for VF access */
 	for_each_hwfn(cdev, j) {
-		struct qed_hwfn *hwfn = &cdev->hwfns[j];
-		struct qed_ptt *ptt = qed_ptt_acquire(hwfn);
+		hwfn = &cdev->hwfns[j];
+		ptt = qed_ptt_acquire(hwfn);
 
 		/* Make sure not to use more than 16 queues per VF */
 		params.num_queues = min_t(int,
@@ -4445,6 +4447,19 @@ static int qed_sriov_enable(struct qed_dev *cdev, int num)
 		goto err;
 	}
 
+	hwfn = QED_LEADING_HWFN(cdev);
+	ptt = qed_ptt_acquire(hwfn);
+	if (!ptt) {
+		DP_ERR(hwfn, "Failed to acquire ptt\n");
+		rc = -EBUSY;
+		goto err;
+	}
+
+	rc = qed_mcp_ov_update_eswitch(hwfn, ptt, QED_OV_ESWITCH_VEB);
+	if (rc)
+		DP_INFO(cdev, "Failed to update eswitch mode\n");
+	qed_ptt_release(hwfn, ptt);
+
 	return num;
 
 err:
-- 
2.17.1


From 97739fa3fd18d833db1b6724f9c3faa0394ffeb8 Mon Sep 17 00:00:00 2001
From: Sudarsana Reddy Kalluru <sudarsana.kalluru@cavium.com>
Date: Sun, 1 Jul 2018 20:03:07 -0700
Subject: [PATCH 26/35] qed: Fix use of incorrect size in memcpy call.

[ Upstream commit cc9b27cdf7bd3c86df73439758ac1564bc8f5bbe ]

Use the correct size value while copying chassis/port id values.

Fixes: 6ad8c632e ("qed: Add support for query/config dcbx.")
Signed-off-by: Sudarsana Reddy Kalluru <Sudarsana.Kalluru@cavium.com>
Signed-off-by: Michal Kalderon <Michal.Kalderon@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_dcbx.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
index 8f6ccc0c39e5..b306961b02fd 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
@@ -700,9 +700,9 @@ qed_dcbx_get_local_lldp_params(struct qed_hwfn *p_hwfn,
 	p_local = &p_hwfn->p_dcbx_info->lldp_local[LLDP_NEAREST_BRIDGE];
 
 	memcpy(params->lldp_local.local_chassis_id, p_local->local_chassis_id,
-	       ARRAY_SIZE(p_local->local_chassis_id));
+	       sizeof(p_local->local_chassis_id));
 	memcpy(params->lldp_local.local_port_id, p_local->local_port_id,
-	       ARRAY_SIZE(p_local->local_port_id));
+	       sizeof(p_local->local_port_id));
 }
 
 static void
@@ -714,9 +714,9 @@ qed_dcbx_get_remote_lldp_params(struct qed_hwfn *p_hwfn,
 	p_remote = &p_hwfn->p_dcbx_info->lldp_remote[LLDP_NEAREST_BRIDGE];
 
 	memcpy(params->lldp_remote.peer_chassis_id, p_remote->peer_chassis_id,
-	       ARRAY_SIZE(p_remote->peer_chassis_id));
+	       sizeof(p_remote->peer_chassis_id));
 	memcpy(params->lldp_remote.peer_port_id, p_remote->peer_port_id,
-	       ARRAY_SIZE(p_remote->peer_port_id));
+	       sizeof(p_remote->peer_port_id));
 }
 
 static int
-- 
2.17.1


From 6e1d03d1b89cd219293001cffefb0dc24c341e34 Mon Sep 17 00:00:00 2001
From: Sudarsana Reddy Kalluru <sudarsana.kalluru@cavium.com>
Date: Sun, 1 Jul 2018 20:03:05 -0700
Subject: [PATCH 27/35] qed: Limit msix vectors in kdump kernel to the minimum
 required count.

[ Upstream commit bb7858ba1102f82470a917e041fd23e6385c31be ]

Memory size is limited in the kdump kernel environment. Allocation of more
msix-vectors (or queues) consumes few tens of MBs of memory, which might
lead to the kdump kernel failure.
This patch adds changes to limit the number of MSI-X vectors in kdump
kernel to minimum required value (i.e., 2 per engine).

Fixes: fe56b9e6a ("qed: Add module with basic common support")
Signed-off-by: Sudarsana Reddy Kalluru <Sudarsana.Kalluru@cavium.com>
Signed-off-by: Michal Kalderon <Michal.Kalderon@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_main.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index 27832885a87f..2c958921dfb3 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -779,6 +779,14 @@ static int qed_slowpath_setup_int(struct qed_dev *cdev,
 	/* We want a minimum of one slowpath and one fastpath vector per hwfn */
 	cdev->int_params.in.min_msix_cnt = cdev->num_hwfns * 2;
 
+	if (is_kdump_kernel()) {
+		DP_INFO(cdev,
+			"Kdump kernel: Limit the max number of requested MSI-X vectors to %hd\n",
+			cdev->int_params.in.min_msix_cnt);
+		cdev->int_params.in.num_vectors =
+			cdev->int_params.in.min_msix_cnt;
+	}
+
 	rc = qed_set_int_mode(cdev, false);
 	if (rc)  {
 		DP_ERR(cdev, "qed_slowpath_setup_int ERR\n");
-- 
2.17.1


From be42283e71682d708d42dfa6aaaab65b86a99b2f Mon Sep 17 00:00:00 2001
From: Aleksander Morgado <aleksander@aleksander.es>
Date: Sat, 23 Jun 2018 23:22:52 +0200
Subject: [PATCH 28/35] qmi_wwan: add support for the Dell Wireless 5821e
 module
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit e7e197edd09c25774b4f12cab19f9d5462f240f4 ]

This module exposes two USB configurations: a QMI+AT capable setup on
USB config #1 and a MBIM capable setup on USB config #2.

By default the kernel will choose the MBIM capable configuration as
long as the cdc_mbim driver is available. This patch adds support for
the QMI port in the secondary configuration.

Signed-off-by: Aleksander Morgado <aleksander@aleksander.es>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 8e06f308ce44..5e0b343dfbdc 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1244,6 +1244,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x413c, 0x81b3, 8)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */
 	{QMI_FIXED_INTF(0x413c, 0x81b6, 8)},	/* Dell Wireless 5811e */
 	{QMI_FIXED_INTF(0x413c, 0x81b6, 10)},	/* Dell Wireless 5811e */
+	{QMI_FIXED_INTF(0x413c, 0x81d7, 1)},	/* Dell Wireless 5821e */
 	{QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)},	/* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */
 	{QMI_FIXED_INTF(0x03f0, 0x9d1d, 1)},	/* HP lt4120 Snapdragon X5 LTE */
 	{QMI_FIXED_INTF(0x22de, 0x9061, 3)},	/* WeTelecom WPD-600N */
-- 
2.17.1


From 73b42d2dc3b9860d95e014f6698186abf0b77798 Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jslaby@suse.cz>
Date: Mon, 25 Jun 2018 09:26:27 +0200
Subject: [PATCH 29/35] r8152: napi hangup fix after disconnect

[ Upstream commit 0ee1f4734967af8321ecebaf9c74221ace34f2d5 ]

When unplugging an r8152 adapter while the interface is UP, the NIC
becomes unusable.  usb->disconnect (aka rtl8152_disconnect) deletes
napi. Then, rtl8152_disconnect calls unregister_netdev and that invokes
netdev->ndo_stop (aka rtl8152_close). rtl8152_close tries to
napi_disable, but the napi is already deleted by disconnect above. So
the first while loop in napi_disable never finishes. This results in
complete deadlock of the network layer as there is rtnl_mutex held by
unregister_netdev.

So avoid the call to napi_disable in rtl8152_close when the device is
already gone.

The other calls to usb_kill_urb, cancel_delayed_work_sync,
netif_stop_queue etc. seem to be fine. The urb and netdev is not
destroyed yet.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Cc: linux-usb@vger.kernel.org
Cc: netdev@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index aa88b640cb6c..0fa64cc1a011 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -3959,7 +3959,8 @@ static int rtl8152_close(struct net_device *netdev)
 #ifdef CONFIG_PM_SLEEP
 	unregister_pm_notifier(&tp->pm_notifier);
 #endif
-	napi_disable(&tp->napi);
+	if (!test_bit(RTL8152_UNPLUG, &tp->flags))
+		napi_disable(&tp->napi);
 	clear_bit(WORK_ENABLE, &tp->flags);
 	usb_kill_urb(tp->intr_urb);
 	cancel_delayed_work_sync(&tp->schedule);
-- 
2.17.1


From 71458be62ced898cefc3bce094a191adc8e6bad9 Mon Sep 17 00:00:00 2001
From: Bhadram Varka <vbhadram@nvidia.com>
Date: Sun, 17 Jun 2018 20:02:05 +0530
Subject: [PATCH 30/35] stmmac: fix DMA channel hang in half-duplex mode

[ Upstream commit b6cfffa7ad923c73f317ea50fd4ebcb3b4b6669c ]

HW does not support Half-duplex mode in multi-queue
scenario. Fix it by not advertising the Half-Duplex
mode if multi-queue enabled.

Signed-off-by: Bhadram Varka <vbhadram@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 9866d2e34cdd..27f2e650e27b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -914,6 +914,7 @@ static void stmmac_check_pcs_mode(struct stmmac_priv *priv)
 static int stmmac_init_phy(struct net_device *dev)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
+	u32 tx_cnt = priv->plat->tx_queues_to_use;
 	struct phy_device *phydev;
 	char phy_id_fmt[MII_BUS_ID_SIZE + 3];
 	char bus_id[MII_BUS_ID_SIZE];
@@ -954,6 +955,15 @@ static int stmmac_init_phy(struct net_device *dev)
 		phydev->advertising &= ~(SUPPORTED_1000baseT_Half |
 					 SUPPORTED_1000baseT_Full);
 
+	/*
+	 * Half-duplex mode not supported with multiqueue
+	 * half-duplex can only works with single queue
+	 */
+	if (tx_cnt > 1)
+		phydev->supported &= ~(SUPPORTED_1000baseT_Half |
+				       SUPPORTED_100baseT_Half |
+				       SUPPORTED_10baseT_Half);
+
 	/*
 	 * Broken HW is sometimes missing the pull-up resistor on the
 	 * MDIO line, which results in reads to non-existent devices returning
-- 
2.17.1


From 7f13ce944abfb5ea098256c32567bd93aeaaac45 Mon Sep 17 00:00:00 2001
From: Doron Roberts-Kedes <doronrk@fb.com>
Date: Tue, 26 Jun 2018 18:33:33 -0700
Subject: [PATCH 31/35] strparser: Remove early eaten to fix full tcp receive
 buffer stall

[ Upstream commit 977c7114ebda2e746a114840d3a875e0cdb826fb ]

On receving an incomplete message, the existing code stores the
remaining length of the cloned skb in the early_eaten field instead of
incrementing the value returned by __strp_recv. This defers invocation
of sock_rfree for the current skb until the next invocation of
__strp_recv, which returns early_eaten if early_eaten is non-zero.

This behavior causes a stall when the current message occupies the very
tail end of a massive skb, and strp_peek/need_bytes indicates that the
remainder of the current message has yet to arrive on the socket. The
TCP receive buffer is totally full, causing the TCP window to go to
zero, so the remainder of the message will never arrive.

Incrementing the value returned by __strp_recv by the amount otherwise
stored in early_eaten prevents stalls of this nature.

Signed-off-by: Doron Roberts-Kedes <doronrk@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/strparser/strparser.c | 17 +----------------
 1 file changed, 1 insertion(+), 16 deletions(-)

diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index c741365f77da..a68c754e84ea 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -35,7 +35,6 @@ struct _strp_msg {
 	 */
 	struct strp_msg strp;
 	int accum_len;
-	int early_eaten;
 };
 
 static inline struct _strp_msg *_strp_msg(struct sk_buff *skb)
@@ -115,20 +114,6 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb,
 	head = strp->skb_head;
 	if (head) {
 		/* Message already in progress */
-
-		stm = _strp_msg(head);
-		if (unlikely(stm->early_eaten)) {
-			/* Already some number of bytes on the receive sock
-			 * data saved in skb_head, just indicate they
-			 * are consumed.
-			 */
-			eaten = orig_len <= stm->early_eaten ?
-				orig_len : stm->early_eaten;
-			stm->early_eaten -= eaten;
-
-			return eaten;
-		}
-
 		if (unlikely(orig_offset)) {
 			/* Getting data with a non-zero offset when a message is
 			 * in progress is not expected. If it does happen, we
@@ -297,9 +282,9 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb,
 				}
 
 				stm->accum_len += cand_len;
+				eaten += cand_len;
 				strp->need_bytes = stm->strp.full_len -
 						       stm->accum_len;
-				stm->early_eaten = cand_len;
 				STRP_STATS_ADD(strp->stats.bytes, cand_len);
 				desc->count = 0; /* Stop reading socket */
 				break;
-- 
2.17.1


From 4fae140f72abb21ec16822072f128a49de7505fa Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Wed, 27 Jun 2018 16:04:48 -0700
Subject: [PATCH 32/35] tcp: fix Fast Open key endianness

[ Upstream commit c860e997e9170a6d68f9d1e6e2cf61f572191aaf ]

Fast Open key could be stored in different endian based on the CPU.
Previously hosts in different endianness in a server farm using
the same key config (sysctl value) would produce different cookies.
This patch fixes it by always storing it as little endian to keep
same API for LE hosts.

Reported-by: Daniele Iamartino <danielei@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/sysctl_net_ipv4.c | 18 +++++++++++++-----
 1 file changed, 13 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 0989e739d098..5a29dc5083a3 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -258,8 +258,9 @@ static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write,
 {
 	struct ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) };
 	struct tcp_fastopen_context *ctxt;
-	int ret;
 	u32  user_key[4]; /* 16 bytes, matching TCP_FASTOPEN_KEY_LENGTH */
+	__le32 key[4];
+	int ret, i;
 
 	tbl.data = kmalloc(tbl.maxlen, GFP_KERNEL);
 	if (!tbl.data)
@@ -268,11 +269,14 @@ static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write,
 	rcu_read_lock();
 	ctxt = rcu_dereference(tcp_fastopen_ctx);
 	if (ctxt)
-		memcpy(user_key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH);
+		memcpy(key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH);
 	else
-		memset(user_key, 0, sizeof(user_key));
+		memset(key, 0, sizeof(key));
 	rcu_read_unlock();
 
+	for (i = 0; i < ARRAY_SIZE(key); i++)
+		user_key[i] = le32_to_cpu(key[i]);
+
 	snprintf(tbl.data, tbl.maxlen, "%08x-%08x-%08x-%08x",
 		user_key[0], user_key[1], user_key[2], user_key[3]);
 	ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
@@ -288,12 +292,16 @@ static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write,
 		 * first invocation of tcp_fastopen_cookie_gen
 		 */
 		tcp_fastopen_init_key_once(false);
-		tcp_fastopen_reset_cipher(user_key, TCP_FASTOPEN_KEY_LENGTH);
+
+		for (i = 0; i < ARRAY_SIZE(user_key); i++)
+			key[i] = cpu_to_le32(user_key[i]);
+
+		tcp_fastopen_reset_cipher(key, TCP_FASTOPEN_KEY_LENGTH);
 	}
 
 bad_key:
 	pr_debug("proc FO key set 0x%x-%x-%x-%x <- 0x%s: %u\n",
-	       user_key[0], user_key[1], user_key[2], user_key[3],
+		 user_key[0], user_key[1], user_key[2], user_key[3],
 	       (char *)tbl.data, ret);
 	kfree(tbl.data);
 	return ret;
-- 
2.17.1


From 25993e0f666184cbc17e843a65c924388f33270e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@helsinki.fi>
Date: Fri, 29 Jun 2018 13:07:53 +0300
Subject: [PATCH 33/35] tcp: prevent bogus FRTO undos with non-SACK flows
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 1236f22fbae15df3736ab4a984c64c0c6ee6254c ]

If SACK is not enabled and the first cumulative ACK after the RTO
retransmission covers more than the retransmitted skb, a spurious
FRTO undo will trigger (assuming FRTO is enabled for that RTO).
The reason is that any non-retransmitted segment acknowledged will
set FLAG_ORIG_SACK_ACKED in tcp_clean_rtx_queue even if there is
no indication that it would have been delivered for real (the
scoreboard is not kept with TCPCB_SACKED_ACKED bits in the non-SACK
case so the check for that bit won't help like it does with SACK).
Having FLAG_ORIG_SACK_ACKED set results in the spurious FRTO undo
in tcp_process_loss.

We need to use more strict condition for non-SACK case and check
that none of the cumulatively ACKed segments were retransmitted
to prove that progress is due to original transmissions. Only then
keep FLAG_ORIG_SACK_ACKED set, allowing FRTO undo to proceed in
non-SACK case.

(FLAG_ORIG_SACK_ACKED is planned to be renamed to FLAG_ORIG_PROGRESS
to better indicate its purpose but to keep this change minimal, it
will be done in another patch).

Besides burstiness and congestion control violations, this problem
can result in RTO loop: When the loss recovery is prematurely
undoed, only new data will be transmitted (if available) and
the next retransmission can occur only after a new RTO which in case
of multiple losses (that are not for consecutive packets) requires
one RTO per loss to recover.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Tested-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index f0caff3139ed..5711b1b12d28 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3194,6 +3194,15 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 
 		if (tcp_is_reno(tp)) {
 			tcp_remove_reno_sacks(sk, pkts_acked);
+
+			/* If any of the cumulatively ACKed segments was
+			 * retransmitted, non-SACK case cannot confirm that
+			 * progress was due to original transmission due to
+			 * lack of TCPCB_SACKED_ACKED bits even if some of
+			 * the packets may have been never retransmitted.
+			 */
+			if (flag & FLAG_RETRANS_DATA_ACKED)
+				flag &= ~FLAG_ORIG_SACK_ACKED;
 		} else {
 			int delta;
 
-- 
2.17.1


From 44f7623090642a25fabd879dddd2a582fe06c832 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Thu, 21 Jun 2018 13:11:31 +0800
Subject: [PATCH 34/35] vhost_net: validate sock before trying to put its fd

[ Upstream commit b8f1f65882f07913157c44673af7ec0b308d03eb ]

Sock will be NULL if we pass -1 to vhost_net_set_backend(), but when
we meet errors during ubuf allocation, the code does not check for
NULL before calling sockfd_put(), this will lead NULL
dereferencing. Fixing by checking sock pointer before.

Fixes: bab632d69ee4 ("vhost: vhost TX zero-copy support")
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/net.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index b0d606b2d06c..6123b4dd8638 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -1186,7 +1186,8 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
 	if (ubufs)
 		vhost_net_ubuf_put_wait_and_free(ubufs);
 err_ubufs:
-	sockfd_put(sock);
+	if (sock)
+		sockfd_put(sock);
 err_vq:
 	mutex_unlock(&vq->mutex);
 err:
-- 
2.17.1


From 3832dd6d4e3f31b5cc5cb6e90d561d01ef4b01a1 Mon Sep 17 00:00:00 2001
From: Claudio Imbrenda <imbrenda@linux.vnet.ibm.com>
Date: Wed, 20 Jun 2018 15:51:51 +0200
Subject: [PATCH 35/35] VSOCK: fix loopback on big-endian systems

[ Upstream commit e5ab564c9ebee77794842ca7d7476147b83d6a27 ]

The dst_cid and src_cid are 64 bits, therefore 64 bit accessors should be
used, and in fact in virtio_transport_common.c only 64 bit accessors are
used. Using 32 bit accessors for 64 bit values breaks big endian systems.

This patch fixes a wrong use of le32_to_cpu in virtio_transport_send_pkt.

Fixes: b9116823189e85ccf384 ("VSOCK: add loopback to virtio_transport")

Signed-off-by: Claudio Imbrenda <imbrenda@linux.vnet.ibm.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/vmw_vsock/virtio_transport.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 403d86e80162..fdb294441682 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -201,7 +201,7 @@ virtio_transport_send_pkt(struct virtio_vsock_pkt *pkt)
 		return -ENODEV;
 	}
 
-	if (le32_to_cpu(pkt->hdr.dst_cid) == vsock->guest_cid)
+	if (le64_to_cpu(pkt->hdr.dst_cid) == vsock->guest_cid)
 		return virtio_transport_send_pkt_loopback(vsock, pkt);
 
 	if (pkt->reply)
-- 
2.17.1


[-- Attachment #3: net_417.mbox --]
[-- Type: Application/Octet-Stream, Size: 144824 bytes --]

From b059ca46aaaddf01a47eb3a8099df2446be5c49a Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 29 Jun 2018 17:51:26 +0200
Subject: [PATCH 01/53] alx: take rtnl before calling __alx_open from resume

[ Upstream commit bc800e8b39bad60ccdb83be828da63af71ab87b3 ]

The __alx_open function can be called from ndo_open, which is called
under RTNL, or from alx_resume, which isn't. Since commit d768319cd427,
we're calling the netif_set_real_num_{tx,rx}_queues functions, which
need to be called under RTNL.

This is similar to commit 0c2cc02e571a ("igb: Move the calls to set the
Tx and Rx queues into igb_open").

Fixes: d768319cd427 ("alx: enable multiple tx queues")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/atheros/alx/main.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index 567ee54504bc..5e5022fa1d04 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -1897,13 +1897,19 @@ static int alx_resume(struct device *dev)
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct alx_priv *alx = pci_get_drvdata(pdev);
 	struct alx_hw *hw = &alx->hw;
+	int err;
 
 	alx_reset_phy(hw);
 
 	if (!netif_running(alx->dev))
 		return 0;
 	netif_device_attach(alx->dev);
-	return __alx_open(alx, true);
+
+	rtnl_lock();
+	err = __alx_open(alx, true);
+	rtnl_unlock();
+
+	return err;
 }
 
 static SIMPLE_DEV_PM_OPS(alx_pm_ops, alx_suspend, alx_resume);
-- 
2.17.1


From 2bf6e6de2aefc1c3a278a674f93d4bbe887a3943 Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw2@infradead.org>
Date: Sat, 16 Jun 2018 11:55:44 +0100
Subject: [PATCH 02/53] atm: Preserve value of skb->truesize when accounting to
 vcc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 9bbe60a67be5a1c6f79b3c9be5003481a50529ff ]

ATM accounts for in-flight TX packets in sk_wmem_alloc of the VCC on
which they are to be sent. But it doesn't take ownership of those
packets from the sock (if any) which originally owned them. They should
remain owned by their actual sender until they've left the box.

There's a hack in pskb_expand_head() to avoid adjusting skb->truesize
for certain skbs, precisely to avoid messing up sk_wmem_alloc
accounting. Ideally that hack would cover the ATM use case too, but it
doesn't — skbs which aren't owned by any sock, for example PPP control
frames, still get their truesize adjusted when the low-level ATM driver
adds headroom.

This has always been an issue, it seems. The truesize of a packet
increases, and sk_wmem_alloc on the VCC goes negative. But this wasn't
for normal traffic, only for control frames. So I think we just got away
with it, and we probably needed to send 2GiB of LCP echo frames before
the misaccounting would ever have caused a problem and caused
atm_may_send() to start refusing packets.

Commit 14afee4b609 ("net: convert sock.sk_wmem_alloc from atomic_t to
refcount_t") did exactly what it was intended to do, and turned this
mostly-theoretical problem into a real one, causing PPPoATM to fail
immediately as sk_wmem_alloc underflows and atm_may_send() *immediately*
starts refusing to allow new packets.

The least intrusive solution to this problem is to stash the value of
skb->truesize that was accounted to the VCC, in a new member of the
ATM_SKB(skb) structure. Then in atm_pop_raw() subtract precisely that
value instead of the then-current value of skb->truesize.

Fixes: 158f323b9868 ("net: adjust skb->truesize in pskb_expand_head()")
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Tested-by: Kevin Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/atmdev.h | 15 +++++++++++++++
 net/atm/br2684.c       |  3 +--
 net/atm/clip.c         |  3 +--
 net/atm/common.c       |  3 +--
 net/atm/lec.c          |  3 +--
 net/atm/mpc.c          |  3 +--
 net/atm/pppoatm.c      |  3 +--
 net/atm/raw.c          |  4 ++--
 8 files changed, 23 insertions(+), 14 deletions(-)

diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h
index 0c27515d2cf6..8124815eb121 100644
--- a/include/linux/atmdev.h
+++ b/include/linux/atmdev.h
@@ -214,6 +214,7 @@ struct atmphy_ops {
 struct atm_skb_data {
 	struct atm_vcc	*vcc;		/* ATM VCC */
 	unsigned long	atm_options;	/* ATM layer options */
+	unsigned int	acct_truesize;  /* truesize accounted to vcc */
 };
 
 #define VCC_HTABLE_SIZE 32
@@ -241,6 +242,20 @@ void vcc_insert_socket(struct sock *sk);
 
 void atm_dev_release_vccs(struct atm_dev *dev);
 
+static inline void atm_account_tx(struct atm_vcc *vcc, struct sk_buff *skb)
+{
+	/*
+	 * Because ATM skbs may not belong to a sock (and we don't
+	 * necessarily want to), skb->truesize may be adjusted,
+	 * escaping the hack in pskb_expand_head() which avoids
+	 * doing so for some cases. So stash the value of truesize
+	 * at the time we accounted it, and atm_pop_raw() can use
+	 * that value later, in case it changes.
+	 */
+	refcount_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc);
+	ATM_SKB(skb)->acct_truesize = skb->truesize;
+	ATM_SKB(skb)->atm_options = vcc->atm_options;
+}
 
 static inline void atm_force_charge(struct atm_vcc *vcc,int truesize)
 {
diff --git a/net/atm/br2684.c b/net/atm/br2684.c
index fd94bea36ee8..82c8d33bd8ba 100644
--- a/net/atm/br2684.c
+++ b/net/atm/br2684.c
@@ -252,8 +252,7 @@ static int br2684_xmit_vcc(struct sk_buff *skb, struct net_device *dev,
 
 	ATM_SKB(skb)->vcc = atmvcc = brvcc->atmvcc;
 	pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n", skb, atmvcc, atmvcc->dev);
-	refcount_add(skb->truesize, &sk_atm(atmvcc)->sk_wmem_alloc);
-	ATM_SKB(skb)->atm_options = atmvcc->atm_options;
+	atm_account_tx(atmvcc, skb);
 	dev->stats.tx_packets++;
 	dev->stats.tx_bytes += skb->len;
 
diff --git a/net/atm/clip.c b/net/atm/clip.c
index f07dbc632222..0edebf8decc0 100644
--- a/net/atm/clip.c
+++ b/net/atm/clip.c
@@ -381,8 +381,7 @@ static netdev_tx_t clip_start_xmit(struct sk_buff *skb,
 		memcpy(here, llc_oui, sizeof(llc_oui));
 		((__be16 *) here)[3] = skb->protocol;
 	}
-	refcount_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc);
-	ATM_SKB(skb)->atm_options = vcc->atm_options;
+	atm_account_tx(vcc, skb);
 	entry->vccs->last_use = jiffies;
 	pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n", skb, vcc, vcc->dev);
 	old = xchg(&entry->vccs->xoff, 1);	/* assume XOFF ... */
diff --git a/net/atm/common.c b/net/atm/common.c
index fc78a0508ae1..a7a68e509628 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -630,10 +630,9 @@ int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t size)
 		goto out;
 	}
 	pr_debug("%d += %d\n", sk_wmem_alloc_get(sk), skb->truesize);
-	refcount_add(skb->truesize, &sk->sk_wmem_alloc);
+	atm_account_tx(vcc, skb);
 
 	skb->dev = NULL; /* for paths shared with net_device interfaces */
-	ATM_SKB(skb)->atm_options = vcc->atm_options;
 	if (!copy_from_iter_full(skb_put(skb, size), size, &m->msg_iter)) {
 		kfree_skb(skb);
 		error = -EFAULT;
diff --git a/net/atm/lec.c b/net/atm/lec.c
index 3138a869b5c0..19ad2fd04983 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -182,9 +182,8 @@ lec_send(struct atm_vcc *vcc, struct sk_buff *skb)
 	struct net_device *dev = skb->dev;
 
 	ATM_SKB(skb)->vcc = vcc;
-	ATM_SKB(skb)->atm_options = vcc->atm_options;
+	atm_account_tx(vcc, skb);
 
-	refcount_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc);
 	if (vcc->send(vcc, skb) < 0) {
 		dev->stats.tx_dropped++;
 		return;
diff --git a/net/atm/mpc.c b/net/atm/mpc.c
index 31e0dcb970f8..44ddcdd5fd35 100644
--- a/net/atm/mpc.c
+++ b/net/atm/mpc.c
@@ -555,8 +555,7 @@ static int send_via_shortcut(struct sk_buff *skb, struct mpoa_client *mpc)
 					sizeof(struct llc_snap_hdr));
 	}
 
-	refcount_add(skb->truesize, &sk_atm(entry->shortcut)->sk_wmem_alloc);
-	ATM_SKB(skb)->atm_options = entry->shortcut->atm_options;
+	atm_account_tx(entry->shortcut, skb);
 	entry->shortcut->send(entry->shortcut, skb);
 	entry->packets_fwded++;
 	mpc->in_ops->put(entry);
diff --git a/net/atm/pppoatm.c b/net/atm/pppoatm.c
index 21d9d341a619..af8c4b38b746 100644
--- a/net/atm/pppoatm.c
+++ b/net/atm/pppoatm.c
@@ -350,8 +350,7 @@ static int pppoatm_send(struct ppp_channel *chan, struct sk_buff *skb)
 		return 1;
 	}
 
-	refcount_add(skb->truesize, &sk_atm(ATM_SKB(skb)->vcc)->sk_wmem_alloc);
-	ATM_SKB(skb)->atm_options = ATM_SKB(skb)->vcc->atm_options;
+	atm_account_tx(vcc, skb);
 	pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n",
 		 skb, ATM_SKB(skb)->vcc, ATM_SKB(skb)->vcc->dev);
 	ret = ATM_SKB(skb)->vcc->send(ATM_SKB(skb)->vcc, skb)
diff --git a/net/atm/raw.c b/net/atm/raw.c
index ee10e8d46185..b3ba44aab0ee 100644
--- a/net/atm/raw.c
+++ b/net/atm/raw.c
@@ -35,8 +35,8 @@ static void atm_pop_raw(struct atm_vcc *vcc, struct sk_buff *skb)
 	struct sock *sk = sk_atm(vcc);
 
 	pr_debug("(%d) %d -= %d\n",
-		 vcc->vci, sk_wmem_alloc_get(sk), skb->truesize);
-	WARN_ON(refcount_sub_and_test(skb->truesize, &sk->sk_wmem_alloc));
+		 vcc->vci, sk_wmem_alloc_get(sk), ATM_SKB(skb)->acct_truesize);
+	WARN_ON(refcount_sub_and_test(ATM_SKB(skb)->acct_truesize, &sk->sk_wmem_alloc));
 	dev_kfree_skb_any(skb);
 	sk->sk_write_space(sk);
 }
-- 
2.17.1


From d5084f22f5d1f1c313e0cd1bf51a686621f5ee76 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Fri, 29 Jun 2018 13:28:07 -0500
Subject: [PATCH 03/53] atm: zatm: Fix potential Spectre v1

[ Upstream commit ced9e191501e52b95e1b57b8e0db00943869eed0 ]

pool can be indirectly controlled by user-space, hence leading to
a potential exploitation of the Spectre variant 1 vulnerability.

This issue was detected with the help of Smatch:

drivers/atm/zatm.c:1491 zatm_ioctl() warn: potential spectre issue
'zatm_dev->pool_info' (local cap)

Fix this by sanitizing pool before using it to index
zatm_dev->pool_info

Notice that given that speculation windows are large, the policy is
to kill the speculation on the first load and not worry if it can be
completed with a dependent load/store [1].

[1] https://marc.info/?l=linux-kernel&m=152449131114778&w=2

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/atm/zatm.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/atm/zatm.c b/drivers/atm/zatm.c
index a8d2eb0ceb8d..2c288d1f42bb 100644
--- a/drivers/atm/zatm.c
+++ b/drivers/atm/zatm.c
@@ -1483,6 +1483,8 @@ static int zatm_ioctl(struct atm_dev *dev,unsigned int cmd,void __user *arg)
 					return -EFAULT;
 				if (pool < 0 || pool > ZATM_LAST_POOL)
 					return -EINVAL;
+				pool = array_index_nospec(pool,
+							  ZATM_LAST_POOL + 1);
 				if (copy_from_user(&info,
 				    &((struct zatm_pool_req __user *) arg)->info,
 				    sizeof(info))) return -EFAULT;
-- 
2.17.1


From 125bd0dd6af57d6eb230fe9289f94369c39a3093 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <sthemmin@microsoft.com>
Date: Fri, 29 Jun 2018 14:07:16 -0700
Subject: [PATCH 04/53] hv_netvsc: split sub-channel setup into async and sync

[ Upstream commit 3ffe64f1a641b80a82d9ef4efa7a05ce69049871 ]

When doing device hotplug the sub channel must be async to avoid
deadlock issues because device is discovered in softirq context.

When doing changes to MTU and number of channels, the setup
must be synchronous to avoid races such as when MTU and device
settings are done in a single ip command.

Reported-by: Thomas Walker <Thomas.Walker@twosigma.com>
Fixes: 8195b1396ec8 ("hv_netvsc: fix deadlock on hotplug")
Fixes: 732e49850c5e ("netvsc: fix race on sub channel creation")
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/hyperv_net.h   |  2 +-
 drivers/net/hyperv/netvsc.c       | 37 ++++++++++++++++++-
 drivers/net/hyperv/netvsc_drv.c   | 17 ++++++++-
 drivers/net/hyperv/rndis_filter.c | 61 ++++++-------------------------
 4 files changed, 65 insertions(+), 52 deletions(-)

diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 960f06141472..eaeee3201e8f 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -211,7 +211,7 @@ int netvsc_recv_callback(struct net_device *net,
 void netvsc_channel_cb(void *context);
 int netvsc_poll(struct napi_struct *napi, int budget);
 
-void rndis_set_subchannel(struct work_struct *w);
+int rndis_set_subchannel(struct net_device *ndev, struct netvsc_device *nvdev);
 int rndis_filter_open(struct netvsc_device *nvdev);
 int rndis_filter_close(struct netvsc_device *nvdev);
 struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 04f611e6f678..c418113c6b20 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -66,6 +66,41 @@ void netvsc_switch_datapath(struct net_device *ndev, bool vf)
 			       VM_PKT_DATA_INBAND, 0);
 }
 
+/* Worker to setup sub channels on initial setup
+ * Initial hotplug event occurs in softirq context
+ * and can't wait for channels.
+ */
+static void netvsc_subchan_work(struct work_struct *w)
+{
+	struct netvsc_device *nvdev =
+		container_of(w, struct netvsc_device, subchan_work);
+	struct rndis_device *rdev;
+	int i, ret;
+
+	/* Avoid deadlock with device removal already under RTNL */
+	if (!rtnl_trylock()) {
+		schedule_work(w);
+		return;
+	}
+
+	rdev = nvdev->extension;
+	if (rdev) {
+		ret = rndis_set_subchannel(rdev->ndev, nvdev);
+		if (ret == 0) {
+			netif_device_attach(rdev->ndev);
+		} else {
+			/* fallback to only primary channel */
+			for (i = 1; i < nvdev->num_chn; i++)
+				netif_napi_del(&nvdev->chan_table[i].napi);
+
+			nvdev->max_chn = 1;
+			nvdev->num_chn = 1;
+		}
+	}
+
+	rtnl_unlock();
+}
+
 static struct netvsc_device *alloc_net_device(void)
 {
 	struct netvsc_device *net_device;
@@ -82,7 +117,7 @@ static struct netvsc_device *alloc_net_device(void)
 
 	init_completion(&net_device->channel_init_wait);
 	init_waitqueue_head(&net_device->subchan_open);
-	INIT_WORK(&net_device->subchan_work, rndis_set_subchannel);
+	INIT_WORK(&net_device->subchan_work, netvsc_subchan_work);
 
 	return net_device;
 }
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index eb8dccd24abf..82c3c8e200f0 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -905,8 +905,20 @@ static int netvsc_attach(struct net_device *ndev,
 	if (IS_ERR(nvdev))
 		return PTR_ERR(nvdev);
 
-	/* Note: enable and attach happen when sub-channels setup */
+	if (nvdev->num_chn > 1) {
+		ret = rndis_set_subchannel(ndev, nvdev);
+
+		/* if unavailable, just proceed with one queue */
+		if (ret) {
+			nvdev->max_chn = 1;
+			nvdev->num_chn = 1;
+		}
+	}
+
+	/* In any case device is now ready */
+	netif_device_attach(ndev);
 
+	/* Note: enable and attach happen when sub-channels setup */
 	netif_carrier_off(ndev);
 
 	if (netif_running(ndev)) {
@@ -2064,6 +2076,9 @@ static int netvsc_probe(struct hv_device *dev,
 
 	memcpy(net->dev_addr, device_info.mac_adr, ETH_ALEN);
 
+	if (nvdev->num_chn > 1)
+		schedule_work(&nvdev->subchan_work);
+
 	/* hw_features computed in rndis_netdev_set_hwcaps() */
 	net->features = net->hw_features |
 		NETIF_F_HIGHDMA | NETIF_F_SG |
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index e7ca5b5f39ed..f362cda85425 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -1061,29 +1061,15 @@ static void netvsc_sc_open(struct vmbus_channel *new_sc)
  * This breaks overlap of processing the host message for the
  * new primary channel with the initialization of sub-channels.
  */
-void rndis_set_subchannel(struct work_struct *w)
+int rndis_set_subchannel(struct net_device *ndev, struct netvsc_device *nvdev)
 {
-	struct netvsc_device *nvdev
-		= container_of(w, struct netvsc_device, subchan_work);
 	struct nvsp_message *init_packet = &nvdev->channel_init_pkt;
-	struct net_device_context *ndev_ctx;
-	struct rndis_device *rdev;
-	struct net_device *ndev;
-	struct hv_device *hv_dev;
+	struct net_device_context *ndev_ctx = netdev_priv(ndev);
+	struct hv_device *hv_dev = ndev_ctx->device_ctx;
+	struct rndis_device *rdev = nvdev->extension;
 	int i, ret;
 
-	if (!rtnl_trylock()) {
-		schedule_work(w);
-		return;
-	}
-
-	rdev = nvdev->extension;
-	if (!rdev)
-		goto unlock;	/* device was removed */
-
-	ndev = rdev->ndev;
-	ndev_ctx = netdev_priv(ndev);
-	hv_dev = ndev_ctx->device_ctx;
+	ASSERT_RTNL();
 
 	memset(init_packet, 0, sizeof(struct nvsp_message));
 	init_packet->hdr.msg_type = NVSP_MSG5_TYPE_SUBCHANNEL;
@@ -1099,13 +1085,13 @@ void rndis_set_subchannel(struct work_struct *w)
 			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
 	if (ret) {
 		netdev_err(ndev, "sub channel allocate send failed: %d\n", ret);
-		goto failed;
+		return ret;
 	}
 
 	wait_for_completion(&nvdev->channel_init_wait);
 	if (init_packet->msg.v5_msg.subchn_comp.status != NVSP_STAT_SUCCESS) {
 		netdev_err(ndev, "sub channel request failed\n");
-		goto failed;
+		return -EIO;
 	}
 
 	nvdev->num_chn = 1 +
@@ -1124,21 +1110,7 @@ void rndis_set_subchannel(struct work_struct *w)
 	for (i = 0; i < VRSS_SEND_TAB_SIZE; i++)
 		ndev_ctx->tx_table[i] = i % nvdev->num_chn;
 
-	netif_device_attach(ndev);
-	rtnl_unlock();
-	return;
-
-failed:
-	/* fallback to only primary channel */
-	for (i = 1; i < nvdev->num_chn; i++)
-		netif_napi_del(&nvdev->chan_table[i].napi);
-
-	nvdev->max_chn = 1;
-	nvdev->num_chn = 1;
-
-	netif_device_attach(ndev);
-unlock:
-	rtnl_unlock();
+	return 0;
 }
 
 static int rndis_netdev_set_hwcaps(struct rndis_device *rndis_device,
@@ -1329,21 +1301,12 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
 		netif_napi_add(net, &net_device->chan_table[i].napi,
 			       netvsc_poll, NAPI_POLL_WEIGHT);
 
-	if (net_device->num_chn > 1)
-		schedule_work(&net_device->subchan_work);
+	return net_device;
 
 out:
-	/* if unavailable, just proceed with one queue */
-	if (ret) {
-		net_device->max_chn = 1;
-		net_device->num_chn = 1;
-	}
-
-	/* No sub channels, device is ready */
-	if (net_device->num_chn == 1)
-		netif_device_attach(net);
-
-	return net_device;
+	/* setting up multiple channels failed */
+	net_device->max_chn = 1;
+	net_device->num_chn = 1;
 
 err_dev_remv:
 	rndis_filter_device_remove(dev, net_device);
-- 
2.17.1


From 2a14df6c589141e377ea5881b21758378482d9c0 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Sat, 30 Jun 2018 15:26:56 -0700
Subject: [PATCH 05/53] ipv6: sr: fix passing wrong flags to
 crypto_alloc_shash()

[ Upstream commit fc9c2029e37c3ae9efc28bf47045e0b87e09660c ]

The 'mask' argument to crypto_alloc_shash() uses the CRYPTO_ALG_* flags,
not 'gfp_t'.  So don't pass GFP_KERNEL to it.

Fixes: bf355b8d2c30 ("ipv6: sr: add core files for SR HMAC support")
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/seg6_hmac.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c
index 33fb35cbfac1..558fe8cc6d43 100644
--- a/net/ipv6/seg6_hmac.c
+++ b/net/ipv6/seg6_hmac.c
@@ -373,7 +373,7 @@ static int seg6_hmac_init_algo(void)
 			return -ENOMEM;
 
 		for_each_possible_cpu(cpu) {
-			tfm = crypto_alloc_shash(algo->name, 0, GFP_KERNEL);
+			tfm = crypto_alloc_shash(algo->name, 0, 0);
 			if (IS_ERR(tfm))
 				return PTR_ERR(tfm);
 			p_tfm = per_cpu_ptr(algo->tfms, cpu);
-- 
2.17.1


From 2f00e5df69f16200a670ea4874dd2789d8482096 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 21 Jun 2018 12:56:04 +0800
Subject: [PATCH 06/53] ipvlan: fix IFLA_MTU ignored on NEWLINK

[ Upstream commit 30877961b1cdd6fdca783c2e8c4f0f47e95dc58c ]

Commit 296d48568042 ("ipvlan: inherit MTU from master device") adjusted
the mtu from the master device when creating a ipvlan device, but it
would also override the mtu value set in rtnl_create_link. It causes
IFLA_MTU param not to take effect.

So this patch is to not adjust the mtu if IFLA_MTU param is set when
creating a ipvlan device.

Fixes: 296d48568042 ("ipvlan: inherit MTU from master device")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ipvlan/ipvlan_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 4377c26f714d..6641fd5355e0 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -594,7 +594,8 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev,
 	ipvlan->phy_dev = phy_dev;
 	ipvlan->dev = dev;
 	ipvlan->sfeatures = IPVLAN_FEATURES;
-	ipvlan_adjust_mtu(ipvlan, phy_dev);
+	if (!tb[IFLA_MTU])
+		ipvlan_adjust_mtu(ipvlan, phy_dev);
 	INIT_LIST_HEAD(&ipvlan->addrs);
 	spin_lock_init(&ipvlan->addrs_lock);
 
-- 
2.17.1


From 086c6438d08b9a529497afb379456c070eac4991 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Tue, 26 Jun 2018 17:39:48 +0200
Subject: [PATCH 07/53] ixgbe: split XDP_TX tail and XDP_REDIRECT map flushing

[ Upstream commit ad088ec480768850db019a5cc543685e868a513d ]

The driver was combining the XDP_TX tail flush and XDP_REDIRECT
map flushing (xdp_do_flush_map).  This is suboptimal, these two
flush operations should be kept separate.

Fixes: 11393cc9b9be ("xdp: Add batching support to redirect map")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 24 +++++++++++--------
 1 file changed, 14 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 2ecd55856c50..a820a6cd831a 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -2257,9 +2257,10 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring,
 	return skb;
 }
 
-#define IXGBE_XDP_PASS 0
-#define IXGBE_XDP_CONSUMED 1
-#define IXGBE_XDP_TX 2
+#define IXGBE_XDP_PASS		0
+#define IXGBE_XDP_CONSUMED	BIT(0)
+#define IXGBE_XDP_TX		BIT(1)
+#define IXGBE_XDP_REDIR		BIT(2)
 
 static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter,
 			       struct xdp_buff *xdp);
@@ -2288,7 +2289,7 @@ static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter,
 	case XDP_REDIRECT:
 		err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog);
 		if (!err)
-			result = IXGBE_XDP_TX;
+			result = IXGBE_XDP_REDIR;
 		else
 			result = IXGBE_XDP_CONSUMED;
 		break;
@@ -2348,7 +2349,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 	unsigned int mss = 0;
 #endif /* IXGBE_FCOE */
 	u16 cleaned_count = ixgbe_desc_unused(rx_ring);
-	bool xdp_xmit = false;
+	unsigned int xdp_xmit = 0;
 	struct xdp_buff xdp;
 
 	xdp.rxq = &rx_ring->xdp_rxq;
@@ -2391,8 +2392,10 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 		}
 
 		if (IS_ERR(skb)) {
-			if (PTR_ERR(skb) == -IXGBE_XDP_TX) {
-				xdp_xmit = true;
+			unsigned int xdp_res = -PTR_ERR(skb);
+
+			if (xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR)) {
+				xdp_xmit |= xdp_res;
 				ixgbe_rx_buffer_flip(rx_ring, rx_buffer, size);
 			} else {
 				rx_buffer->pagecnt_bias++;
@@ -2464,7 +2467,10 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 		total_rx_packets++;
 	}
 
-	if (xdp_xmit) {
+	if (xdp_xmit & IXGBE_XDP_REDIR)
+		xdp_do_flush_map();
+
+	if (xdp_xmit & IXGBE_XDP_TX) {
 		struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()];
 
 		/* Force memory writes to complete before letting h/w
@@ -2472,8 +2478,6 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 		 */
 		wmb();
 		writel(ring->next_to_use, ring->tail);
-
-		xdp_do_flush_map();
 	}
 
 	u64_stats_update_begin(&rx_ring->syncp);
-- 
2.17.1


From e206421c91e7c1cd2d8e34c688c720eef2a5fa15 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 22 Jun 2018 06:44:14 -0700
Subject: [PATCH 08/53] net: dccp: avoid crash in ccid3_hc_rx_send_feedback()

[ Upstream commit 74174fe5634ffbf645a7ca5a261571f700b2f332 ]

On fast hosts or malicious bots, we trigger a DCCP_BUG() which
seems excessive.

syzbot reported :

BUG: delta (-6195) <= 0 at net/dccp/ccids/ccid3.c:628/ccid3_hc_rx_send_feedback()
CPU: 1 PID: 18 Comm: ksoftirqd/1 Not tainted 4.18.0-rc1+ #112
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c9/0x2b4 lib/dump_stack.c:113
 ccid3_hc_rx_send_feedback net/dccp/ccids/ccid3.c:628 [inline]
 ccid3_hc_rx_packet_recv.cold.16+0x38/0x71 net/dccp/ccids/ccid3.c:793
 ccid_hc_rx_packet_recv net/dccp/ccid.h:185 [inline]
 dccp_deliver_input_to_ccids+0xf0/0x280 net/dccp/input.c:180
 dccp_rcv_established+0x87/0xb0 net/dccp/input.c:378
 dccp_v4_do_rcv+0x153/0x180 net/dccp/ipv4.c:654
 sk_backlog_rcv include/net/sock.h:914 [inline]
 __sk_receive_skb+0x3ba/0xd80 net/core/sock.c:517
 dccp_v4_rcv+0x10f9/0x1f58 net/dccp/ipv4.c:875
 ip_local_deliver_finish+0x2eb/0xda0 net/ipv4/ip_input.c:215
 NF_HOOK include/linux/netfilter.h:287 [inline]
 ip_local_deliver+0x1e9/0x750 net/ipv4/ip_input.c:256
 dst_input include/net/dst.h:450 [inline]
 ip_rcv_finish+0x823/0x2220 net/ipv4/ip_input.c:396
 NF_HOOK include/linux/netfilter.h:287 [inline]
 ip_rcv+0xa18/0x1284 net/ipv4/ip_input.c:492
 __netif_receive_skb_core+0x2488/0x3680 net/core/dev.c:4628
 __netif_receive_skb+0x2c/0x1e0 net/core/dev.c:4693
 process_backlog+0x219/0x760 net/core/dev.c:5373
 napi_poll net/core/dev.c:5771 [inline]
 net_rx_action+0x7da/0x1980 net/core/dev.c:5837
 __do_softirq+0x2e8/0xb17 kernel/softirq.c:284
 run_ksoftirqd+0x86/0x100 kernel/softirq.c:645
 smpboot_thread_fn+0x417/0x870 kernel/smpboot.c:164
 kthread+0x345/0x410 kernel/kthread.c:240
 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:412

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Cc: dccp@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ccids/ccid3.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c
index 8b5ba6dffac7..d57a2be1e2e0 100644
--- a/net/dccp/ccids/ccid3.c
+++ b/net/dccp/ccids/ccid3.c
@@ -625,9 +625,8 @@ static void ccid3_hc_rx_send_feedback(struct sock *sk,
 	case CCID3_FBACK_PERIODIC:
 		delta = ktime_us_delta(now, hc->rx_tstamp_last_feedback);
 		if (delta <= 0)
-			DCCP_BUG("delta (%ld) <= 0", (long)delta);
-		else
-			hc->rx_x_recv = scaled_div32(hc->rx_bytes_recv, delta);
+			delta = 1;
+		hc->rx_x_recv = scaled_div32(hc->rx_bytes_recv, delta);
 		break;
 	default:
 		return;
-- 
2.17.1


From 5fb7532db3a21b7baf90b0be78358dc23f8b0c2f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 22 Jun 2018 06:44:15 -0700
Subject: [PATCH 09/53] net: dccp: switch rx_tstamp_last_feedback to monotonic
 clock

[ Upstream commit 0ce4e70ff00662ad7490e545ba0cd8c1fa179fca ]

To compute delays, better not use time of the day which can
be changed by admins or malicious programs.

Also change ccid3_first_li() to use s64 type for delta variable
to avoid potential overflows.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Cc: dccp@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ccids/ccid3.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c
index d57a2be1e2e0..12877a1514e7 100644
--- a/net/dccp/ccids/ccid3.c
+++ b/net/dccp/ccids/ccid3.c
@@ -600,7 +600,7 @@ static void ccid3_hc_rx_send_feedback(struct sock *sk,
 {
 	struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk);
 	struct dccp_sock *dp = dccp_sk(sk);
-	ktime_t now = ktime_get_real();
+	ktime_t now = ktime_get();
 	s64 delta = 0;
 
 	switch (fbtype) {
@@ -632,7 +632,7 @@ static void ccid3_hc_rx_send_feedback(struct sock *sk,
 		return;
 	}
 
-	ccid3_pr_debug("Interval %ldusec, X_recv=%u, 1/p=%u\n", (long)delta,
+	ccid3_pr_debug("Interval %lldusec, X_recv=%u, 1/p=%u\n", delta,
 		       hc->rx_x_recv, hc->rx_pinv);
 
 	hc->rx_tstamp_last_feedback = now;
@@ -679,7 +679,8 @@ static int ccid3_hc_rx_insert_options(struct sock *sk, struct sk_buff *skb)
 static u32 ccid3_first_li(struct sock *sk)
 {
 	struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk);
-	u32 x_recv, p, delta;
+	u32 x_recv, p;
+	s64 delta;
 	u64 fval;
 
 	if (hc->rx_rtt == 0) {
@@ -687,7 +688,9 @@ static u32 ccid3_first_li(struct sock *sk)
 		hc->rx_rtt = DCCP_FALLBACK_RTT;
 	}
 
-	delta  = ktime_to_us(net_timedelta(hc->rx_tstamp_last_feedback));
+	delta = ktime_us_delta(ktime_get(), hc->rx_tstamp_last_feedback);
+	if (delta <= 0)
+		delta = 1;
 	x_recv = scaled_div32(hc->rx_bytes_recv, delta);
 	if (x_recv == 0) {		/* would also trigger divide-by-zero */
 		DCCP_WARN("X_recv==0\n");
-- 
2.17.1


From 69ae309f4bbdfc17d40cce62381427437b018e93 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Sat, 30 Jun 2018 17:38:55 +0200
Subject: [PATCH 10/53] net: fix use-after-free in GRO with ESP

[ Upstream commit 603d4cf8fe095b1ee78f423d514427be507fb513 ]

Since the addition of GRO for ESP, gro_receive can consume the skb and
return -EINPROGRESS. In that case, the lower layer GRO handler cannot
touch the skb anymore.

Commit 5f114163f2f5 ("net: Add a skb_gro_flush_final helper.") converted
some of the gro_receive handlers that can lead to ESP's gro_receive so
that they wouldn't access the skb when -EINPROGRESS is returned, but
missed other spots, mainly in tunneling protocols.

This patch finishes the conversion to using skb_gro_flush_final(), and
adds a new helper, skb_gro_flush_final_remcsum(), used in VXLAN and
GUE.

Fixes: 5f114163f2f5 ("net: Add a skb_gro_flush_final helper.")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c      |  2 +-
 drivers/net/vxlan.c       |  4 +---
 include/linux/netdevice.h | 20 ++++++++++++++++++++
 net/8021q/vlan.c          |  2 +-
 net/ipv4/fou.c            |  4 +---
 net/ipv4/gre_offload.c    |  2 +-
 net/ipv4/udp_offload.c    |  2 +-
 7 files changed, 26 insertions(+), 10 deletions(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index b919e89a9b93..4b3986dda52e 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -474,7 +474,7 @@ static struct sk_buff **geneve_gro_receive(struct sock *sk,
 out_unlock:
 	rcu_read_unlock();
 out:
-	NAPI_GRO_CB(skb)->flush |= flush;
+	skb_gro_flush_final(skb, pp, flush);
 
 	return pp;
 }
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index fab7a4db249e..4b170599fa5e 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -623,9 +623,7 @@ static struct sk_buff **vxlan_gro_receive(struct sock *sk,
 	flush = 0;
 
 out:
-	skb_gro_remcsum_cleanup(skb, &grc);
-	skb->remcsum_offload = 0;
-	NAPI_GRO_CB(skb)->flush |= flush;
+	skb_gro_flush_final_remcsum(skb, pp, flush, &grc);
 
 	return pp;
 }
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index cf44503ea81a..5ad916d31471 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2735,11 +2735,31 @@ static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp,
 	if (PTR_ERR(pp) != -EINPROGRESS)
 		NAPI_GRO_CB(skb)->flush |= flush;
 }
+static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb,
+					       struct sk_buff **pp,
+					       int flush,
+					       struct gro_remcsum *grc)
+{
+	if (PTR_ERR(pp) != -EINPROGRESS) {
+		NAPI_GRO_CB(skb)->flush |= flush;
+		skb_gro_remcsum_cleanup(skb, grc);
+		skb->remcsum_offload = 0;
+	}
+}
 #else
 static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, int flush)
 {
 	NAPI_GRO_CB(skb)->flush |= flush;
 }
+static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb,
+					       struct sk_buff **pp,
+					       int flush,
+					       struct gro_remcsum *grc)
+{
+	NAPI_GRO_CB(skb)->flush |= flush;
+	skb_gro_remcsum_cleanup(skb, grc);
+	skb->remcsum_offload = 0;
+}
 #endif
 
 static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev,
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 5505ee6ebdbe..d3a5ec02e64c 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -688,7 +688,7 @@ static struct sk_buff **vlan_gro_receive(struct sk_buff **head,
 out_unlock:
 	rcu_read_unlock();
 out:
-	NAPI_GRO_CB(skb)->flush |= flush;
+	skb_gro_flush_final(skb, pp, flush);
 
 	return pp;
 }
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 1540db65241a..c9ec1603666b 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -448,9 +448,7 @@ static struct sk_buff **gue_gro_receive(struct sock *sk,
 out_unlock:
 	rcu_read_unlock();
 out:
-	NAPI_GRO_CB(skb)->flush |= flush;
-	skb_gro_remcsum_cleanup(skb, &grc);
-	skb->remcsum_offload = 0;
+	skb_gro_flush_final_remcsum(skb, pp, flush, &grc);
 
 	return pp;
 }
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index 1859c473b21a..6a7d980105f6 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -223,7 +223,7 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head,
 out_unlock:
 	rcu_read_unlock();
 out:
-	NAPI_GRO_CB(skb)->flush |= flush;
+	skb_gro_flush_final(skb, pp, flush);
 
 	return pp;
 }
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index ea6e6e7df0ee..cde2719fcb89 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -295,7 +295,7 @@ struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb,
 out_unlock:
 	rcu_read_unlock();
 out:
-	NAPI_GRO_CB(skb)->flush |= flush;
+	skb_gro_flush_final(skb, pp, flush);
 	return pp;
 }
 EXPORT_SYMBOL(udp_gro_receive);
-- 
2.17.1


From 56d933f71fef9771f1c444a65ff494087cea6e7a Mon Sep 17 00:00:00 2001
From: Harini Katakam <harini.katakam@xilinx.com>
Date: Wed, 20 Jun 2018 17:04:20 +0530
Subject: [PATCH 11/53] net: macb: Fix ptp time adjustment for large negative
 delta

[ Upstream commit 64d7839af8c8f67daaf9bf387135052c55d85f90 ]

When delta passed to gem_ptp_adjtime is negative, the sign is
maintained in the ns_to_timespec64 conversion. Hence timespec_add
should be used directly. timespec_sub will just subtract the negative
value thus increasing the time difference.

Signed-off-by: Harini Katakam <harini.katakam@xilinx.com>
Acked-by: Nicolas Ferre <nicolas.ferre@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_ptp.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_ptp.c b/drivers/net/ethernet/cadence/macb_ptp.c
index 2220c771092b..678835136bf8 100644
--- a/drivers/net/ethernet/cadence/macb_ptp.c
+++ b/drivers/net/ethernet/cadence/macb_ptp.c
@@ -170,10 +170,7 @@ static int gem_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 
 	if (delta > TSU_NSEC_MAX_VAL) {
 		gem_tsu_get_time(&bp->ptp_clock_info, &now);
-		if (sign)
-			now = timespec64_sub(now, then);
-		else
-			now = timespec64_add(now, then);
+		now = timespec64_add(now, then);
 
 		gem_tsu_set_time(&bp->ptp_clock_info,
 				 (const struct timespec64 *)&now);
-- 
2.17.1


From e427ece1cde42a4fce5f1eeb56a48310fc8e24d3 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Thu, 31 May 2018 11:32:56 +0300
Subject: [PATCH 12/53] net/mlx5e: Avoid dealing with vport representors if not
 being e-switch manager

[ Upstream commit 733d3e5497070d05971352ca5087bac83c197c3d ]

In smartnic env, the host (PF) driver might not be an e-switch
manager, hence the switchdev mode representors are running on
the embedded cpu (EC) and not at the host.

As such, we should avoid dealing with vport representors if
not being esw manager.

While here, make sure to disallow eswitch switchdev related
setups through devlink if we are not esw managers.

Fixes: cb67b832921c ('net/mlx5e: Introduce SRIOV VF representors')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c    | 12 ++++++------
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c     |  2 +-
 .../ethernet/mellanox/mlx5/core/eswitch_offloads.c   |  4 ++--
 3 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index b29c1d93f058..d3a1a2281e77 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2612,7 +2612,7 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv)
 	mlx5e_activate_channels(&priv->channels);
 	netif_tx_start_all_queues(priv->netdev);
 
-	if (MLX5_VPORT_MANAGER(priv->mdev))
+	if (MLX5_ESWITCH_MANAGER(priv->mdev))
 		mlx5e_add_sqs_fwd_rules(priv);
 
 	mlx5e_wait_channels_min_rx_wqes(&priv->channels);
@@ -2623,7 +2623,7 @@ void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv)
 {
 	mlx5e_redirect_rqts_to_drop(priv);
 
-	if (MLX5_VPORT_MANAGER(priv->mdev))
+	if (MLX5_ESWITCH_MANAGER(priv->mdev))
 		mlx5e_remove_sqs_fwd_rules(priv);
 
 	/* FIXME: This is a W/A only for tx timeout watch dog false alarm when
@@ -4315,7 +4315,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	mlx5e_set_netdev_dev_addr(netdev);
 
 #if IS_ENABLED(CONFIG_MLX5_ESWITCH)
-	if (MLX5_VPORT_MANAGER(mdev))
+	if (MLX5_ESWITCH_MANAGER(mdev))
 		netdev->switchdev_ops = &mlx5e_switchdev_ops;
 #endif
 
@@ -4465,7 +4465,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 
 	mlx5e_enable_async_events(priv);
 
-	if (MLX5_VPORT_MANAGER(priv->mdev))
+	if (MLX5_ESWITCH_MANAGER(priv->mdev))
 		mlx5e_register_vport_reps(priv);
 
 	if (netdev->reg_state != NETREG_REGISTERED)
@@ -4500,7 +4500,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv)
 
 	queue_work(priv->wq, &priv->set_rx_mode_work);
 
-	if (MLX5_VPORT_MANAGER(priv->mdev))
+	if (MLX5_ESWITCH_MANAGER(priv->mdev))
 		mlx5e_unregister_vport_reps(priv);
 
 	mlx5e_disable_async_events(priv);
@@ -4684,7 +4684,7 @@ static void *mlx5e_add(struct mlx5_core_dev *mdev)
 		return NULL;
 
 #ifdef CONFIG_MLX5_ESWITCH
-	if (MLX5_VPORT_MANAGER(mdev)) {
+	if (MLX5_ESWITCH_MANAGER(mdev)) {
 		rpriv = mlx5e_alloc_nic_rep_priv(mdev);
 		if (!rpriv) {
 			mlx5_core_warn(mdev, "Failed to alloc NIC rep priv data\n");
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 876c3e4c6193..68399d764484 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -790,7 +790,7 @@ bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv)
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	struct mlx5_eswitch_rep *rep;
 
-	if (!MLX5_CAP_GEN(priv->mdev, vport_group_manager))
+	if (!MLX5_ESWITCH_MANAGER(priv->mdev))
 		return false;
 
 	rep = rpriv->rep;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 35e256eb2f6e..2feb33dcad2f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -983,8 +983,8 @@ static int mlx5_devlink_eswitch_check(struct devlink *devlink)
 	if (MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH)
 		return -EOPNOTSUPP;
 
-	if (!MLX5_CAP_GEN(dev, vport_group_manager))
-		return -EOPNOTSUPP;
+	if(!MLX5_ESWITCH_MANAGER(dev))
+		return -EPERM;
 
 	if (dev->priv.eswitch->mode == SRIOV_NONE)
 		return -EOPNOTSUPP;
-- 
2.17.1


From 7f28c99a0aafa1d217bee996774815b5059558fc Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Mon, 4 Jun 2018 19:46:53 +0300
Subject: [PATCH 13/53] net/mlx5e: Don't attempt to dereference the ppriv
 struct if not being eswitch manager

[ Upstream commit 8ffd569aaa818f2624ca821d9a246342fa8b8c50 ]

The check for cpu hit statistics was not returning immediate false for
any non vport rep netdev and hence we crashed (say on mlx5 probed VFs) if
user-space tool was calling into any possible netdev in the system.

Fix that by doing a proper check before dereferencing.

Fixes: 1d447a39142e ('net/mlx5e: Extendable vport representor netdev private data')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reported-by: Eli Cohen <eli@melloanox.com>
Reviewed-by: Eli Cohen <eli@melloanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 68399d764484..2dc6f030613d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -804,8 +804,12 @@ bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv)
 static bool mlx5e_is_vf_vport_rep(struct mlx5e_priv *priv)
 {
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
-	struct mlx5_eswitch_rep *rep = rpriv->rep;
+	struct mlx5_eswitch_rep *rep;
 
+	if (!MLX5_CAP_GEN(priv->mdev, eswitch_flow_table))
+		return false;
+
+	rep = rpriv->rep;
 	if (rep && rep->vport != FDB_UPLINK_VPORT)
 		return true;
 
-- 
2.17.1


From baa1696a7a8e10d7f87419a3906ac123238d6f34 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Thu, 31 May 2018 11:16:18 +0300
Subject: [PATCH 14/53] net/mlx5: E-Switch, Avoid setup attempt if not being
 e-switch manager

[ Upstream commit 0efc8562491b7d36f6bbc4fbc8f3348cb6641e9c ]

In smartnic env, the host (PF) driver might not be an e-switch
manager, hence the FW will err on driver attempts to deal with
setting/unsetting the eswitch and as a result the overall setup
of sriov will fail.

Fix that by avoiding the operation if e-switch management is not
allowed for this driver instance. While here, move to use the
correct name for the esw manager capability name.

Fixes: 81848731ff40 ('net/mlx5: E-Switch, Add SR-IOV (FDB) support')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reported-by: Guy Kushnir <guyk@mellanox.com>
Reviewed-by: Eli Cohen <eli@melloanox.com>
Tested-by: Eli Cohen <eli@melloanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c  | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 3 ++-
 drivers/net/ethernet/mellanox/mlx5/core/fw.c      | 5 +++--
 drivers/net/ethernet/mellanox/mlx5/core/sriov.c   | 7 ++++++-
 include/linux/mlx5/eswitch.h                      | 2 ++
 include/linux/mlx5/mlx5_ifc.h                     | 2 +-
 7 files changed, 16 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 2dc6f030613d..286565862341 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -806,7 +806,7 @@ static bool mlx5e_is_vf_vport_rep(struct mlx5e_priv *priv)
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	struct mlx5_eswitch_rep *rep;
 
-	if (!MLX5_CAP_GEN(priv->mdev, eswitch_flow_table))
+	if (!MLX5_ESWITCH_MANAGER(priv->mdev))
 		return false;
 
 	rep = rpriv->rep;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 1352d13eedb3..c3a18ddf5dba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1604,7 +1604,7 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
 	if (!ESW_ALLOWED(esw))
 		return 0;
 
-	if (!MLX5_CAP_GEN(esw->dev, eswitch_flow_table) ||
+	if (!MLX5_ESWITCH_MANAGER(esw->dev) ||
 	    !MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ft_support)) {
 		esw_warn(esw->dev, "E-Switch FDB is not supported, aborting ...\n");
 		return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index c39c1692e674..bd0ffc347bd7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -32,6 +32,7 @@
 
 #include <linux/mutex.h>
 #include <linux/mlx5/driver.h>
+#include <linux/mlx5/eswitch.h>
 
 #include "mlx5_core.h"
 #include "fs_core.h"
@@ -2631,7 +2632,7 @@ int mlx5_init_fs(struct mlx5_core_dev *dev)
 			goto err;
 	}
 
-	if (MLX5_CAP_GEN(dev, eswitch_flow_table)) {
+	if (MLX5_ESWITCH_MANAGER(dev)) {
 		if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, ft_support)) {
 			err = init_fdb_root_ns(steering);
 			if (err)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index afd9f4fa22f4..41ad24f0de2c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -32,6 +32,7 @@
 
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/cmd.h>
+#include <linux/mlx5/eswitch.h>
 #include <linux/module.h>
 #include "mlx5_core.h"
 #include "../../mlxfw/mlxfw.h"
@@ -159,13 +160,13 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev)
 	}
 
 	if (MLX5_CAP_GEN(dev, vport_group_manager) &&
-	    MLX5_CAP_GEN(dev, eswitch_flow_table)) {
+	    MLX5_ESWITCH_MANAGER(dev)) {
 		err = mlx5_core_get_caps(dev, MLX5_CAP_ESWITCH_FLOW_TABLE);
 		if (err)
 			return err;
 	}
 
-	if (MLX5_CAP_GEN(dev, eswitch_flow_table)) {
+	if (MLX5_ESWITCH_MANAGER(dev)) {
 		err = mlx5_core_get_caps(dev, MLX5_CAP_ESWITCH);
 		if (err)
 			return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
index 2a8b529ce6dd..a0674962f02c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
@@ -88,6 +88,9 @@ static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs)
 		return -EBUSY;
 	}
 
+	if (!MLX5_ESWITCH_MANAGER(dev))
+		goto enable_vfs_hca;
+
 	err = mlx5_eswitch_enable_sriov(dev->priv.eswitch, num_vfs, SRIOV_LEGACY);
 	if (err) {
 		mlx5_core_warn(dev,
@@ -95,6 +98,7 @@ static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs)
 		return err;
 	}
 
+enable_vfs_hca:
 	for (vf = 0; vf < num_vfs; vf++) {
 		err = mlx5_core_enable_hca(dev, vf + 1);
 		if (err) {
@@ -140,7 +144,8 @@ static void mlx5_device_disable_sriov(struct mlx5_core_dev *dev)
 	}
 
 out:
-	mlx5_eswitch_disable_sriov(dev->priv.eswitch);
+	if (MLX5_ESWITCH_MANAGER(dev))
+		mlx5_eswitch_disable_sriov(dev->priv.eswitch);
 
 	if (mlx5_wait_for_vf_pages(dev))
 		mlx5_core_warn(dev, "timeout reclaiming VFs pages\n");
diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h
index d3c9db492b30..fab5121ffb8f 100644
--- a/include/linux/mlx5/eswitch.h
+++ b/include/linux/mlx5/eswitch.h
@@ -8,6 +8,8 @@
 
 #include <linux/mlx5/driver.h>
 
+#define MLX5_ESWITCH_MANAGER(mdev) MLX5_CAP_GEN(mdev, eswitch_manager)
+
 enum {
 	SRIOV_NONE,
 	SRIOV_LEGACY,
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 1aad455538f4..5b662ea2e32a 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -905,7 +905,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         vnic_env_queue_counters[0x1];
 	u8         ets[0x1];
 	u8         nic_flow_table[0x1];
-	u8         eswitch_flow_table[0x1];
+	u8         eswitch_manager[0x1];
 	u8         device_memory[0x1];
 	u8         mcam_reg[0x1];
 	u8         pcam_reg[0x1];
-- 
2.17.1


From 63149aae8b16a14978f667152f1ff5a7c07c2fd8 Mon Sep 17 00:00:00 2001
From: Alex Vesker <valex@mellanox.com>
Date: Tue, 12 Jun 2018 16:14:31 +0300
Subject: [PATCH 15/53] net/mlx5: Fix command interface race in polling mode

[ Upstream commit d412c31dae053bf30a1bc15582a9990df297a660 ]

The command interface can work in two modes: Events and Polling.
In the general case, each time we invoke a command, a work is
queued to handle it.

When working in events, the interrupt handler completes the
command execution. On the other hand, when working in polling
mode, the work itself completes it.

Due to a bug in the work handler, a command could have been
completed by the interrupt handler, while the work handler
hasn't finished yet, causing the it to complete once again
if the command interface mode was changed from Events to
polling after the interrupt handler was called.

mlx5_unload_one()
        mlx5_stop_eqs()
                // Destroy the EQ before cmd EQ
                ...cmd_work_handler()
                        write_doorbell()
                        --> EVENT_TYPE_CMD
                                mlx5_cmd_comp_handler() // First free
                                        free_ent(cmd, ent->idx)
                                        complete(&ent->done)

        <-- mlx5_stop_eqs //cmd was complete
                // move to polling before destroying the last cmd EQ
                mlx5_cmd_use_polling()
                        cmd->mode = POLL;

                --> cmd_work_handler (continues)
                        if (cmd->mode == POLL)
                                mlx5_cmd_comp_handler() // Double free

The solution is to store the cmd->mode before writing the doorbell.

Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters")
Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 21cd1703a862..fd18beefba08 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -803,6 +803,7 @@ static void cmd_work_handler(struct work_struct *work)
 	unsigned long flags;
 	bool poll_cmd = ent->polling;
 	int alloc_ret;
+	int cmd_mode;
 
 	sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem;
 	down(sem);
@@ -849,6 +850,7 @@ static void cmd_work_handler(struct work_struct *work)
 	set_signature(ent, !cmd->checksum_disabled);
 	dump_command(dev, ent, 1);
 	ent->ts1 = ktime_get_ns();
+	cmd_mode = cmd->mode;
 
 	if (ent->callback)
 		schedule_delayed_work(&ent->cb_timeout_work, cb_timeout);
@@ -873,7 +875,7 @@ static void cmd_work_handler(struct work_struct *work)
 	iowrite32be(1 << ent->idx, &dev->iseg->cmd_dbell);
 	mmiowb();
 	/* if not in polling don't use ent after this point */
-	if (cmd->mode == CMD_MODE_POLLING || poll_cmd) {
+	if (cmd_mode == CMD_MODE_POLLING || poll_cmd) {
 		poll_timeout(ent);
 		/* make sure we read the descriptor after ownership is SW */
 		rmb();
-- 
2.17.1


From 336938c2fb702131cbd0151dc04700ab0c0346e7 Mon Sep 17 00:00:00 2001
From: Alex Vesker <valex@mellanox.com>
Date: Fri, 25 May 2018 20:25:59 +0300
Subject: [PATCH 16/53] net/mlx5: Fix incorrect raw command length parsing

[ Upstream commit 603b7bcff824740500ddfa001d7a7168b0b38542 ]

The NULL character was not set correctly for the string containing
the command length, this caused failures reading the output of the
command due to a random length. The fix is to initialize the output
length string.

Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters")
Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index fd18beefba08..33ab34dc6d96 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -1276,7 +1276,7 @@ static ssize_t outlen_write(struct file *filp, const char __user *buf,
 {
 	struct mlx5_core_dev *dev = filp->private_data;
 	struct mlx5_cmd_debug *dbg = &dev->cmd.dbg;
-	char outlen_str[8];
+	char outlen_str[8] = {0};
 	int outlen;
 	void *ptr;
 	int err;
@@ -1291,8 +1291,6 @@ static ssize_t outlen_write(struct file *filp, const char __user *buf,
 	if (copy_from_user(outlen_str, buf, count))
 		return -EFAULT;
 
-	outlen_str[7] = 0;
-
 	err = sscanf(outlen_str, "%d", &outlen);
 	if (err < 0)
 		return err;
-- 
2.17.1


From 5f5db787e67671cf2f409ebfe177b610b32ec358 Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.com>
Date: Wed, 13 Jun 2018 10:27:34 +0300
Subject: [PATCH 17/53] net/mlx5: Fix required capability for manipulating MPFS

[ Upstream commit f811980444ec59ad62f9e041adbb576a821132c7 ]

Manipulating of the MPFS requires eswitch manager capabilities.

Fixes: eeb66cdb6826 ('net/mlx5: Separate between E-Switch and MPFS')
Signed-off-by: Eli Cohen <eli@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c
index 7cb67122e8b5..98359559c77e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c
@@ -33,6 +33,7 @@
 #include <linux/etherdevice.h>
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/mlx5_ifc.h>
+#include <linux/mlx5/eswitch.h>
 #include "mlx5_core.h"
 #include "lib/mpfs.h"
 
@@ -98,7 +99,7 @@ int mlx5_mpfs_init(struct mlx5_core_dev *dev)
 	int l2table_size = 1 << MLX5_CAP_GEN(dev, log_max_l2_table);
 	struct mlx5_mpfs *mpfs;
 
-	if (!MLX5_VPORT_MANAGER(dev))
+	if (!MLX5_ESWITCH_MANAGER(dev))
 		return 0;
 
 	mpfs = kzalloc(sizeof(*mpfs), GFP_KERNEL);
@@ -122,7 +123,7 @@ void mlx5_mpfs_cleanup(struct mlx5_core_dev *dev)
 {
 	struct mlx5_mpfs *mpfs = dev->priv.mpfs;
 
-	if (!MLX5_VPORT_MANAGER(dev))
+	if (!MLX5_ESWITCH_MANAGER(dev))
 		return;
 
 	WARN_ON(!hlist_empty(mpfs->hash));
@@ -137,7 +138,7 @@ int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac)
 	u32 index;
 	int err;
 
-	if (!MLX5_VPORT_MANAGER(dev))
+	if (!MLX5_ESWITCH_MANAGER(dev))
 		return 0;
 
 	mutex_lock(&mpfs->lock);
@@ -179,7 +180,7 @@ int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac)
 	int err = 0;
 	u32 index;
 
-	if (!MLX5_VPORT_MANAGER(dev))
+	if (!MLX5_ESWITCH_MANAGER(dev))
 		return 0;
 
 	mutex_lock(&mpfs->lock);
-- 
2.17.1


From d1d6f36b826f9f924691e955d6cc549e5ae84468 Mon Sep 17 00:00:00 2001
From: Shay Agroskin <shayag@mellanox.com>
Date: Tue, 22 May 2018 14:14:02 +0300
Subject: [PATCH 18/53] net/mlx5: Fix wrong size allocation for QoS ETC TC
 regitster

[ Upstream commit d14fcb8d877caf1b8d6bd65d444bf62b21f2070c ]

The driver allocates wrong size (due to wrong struct name) when issuing
a query/set request to NIC's register.

Fixes: d8880795dabf ("net/mlx5e: Implement DCBNL IEEE max rate")
Signed-off-by: Shay Agroskin <shayag@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/port.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index fa9d0760dd36..31a9cbd85689 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -701,7 +701,7 @@ EXPORT_SYMBOL_GPL(mlx5_query_port_prio_tc);
 static int mlx5_set_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *in,
 				   int inlen)
 {
-	u32 out[MLX5_ST_SZ_DW(qtct_reg)];
+	u32 out[MLX5_ST_SZ_DW(qetc_reg)];
 
 	if (!MLX5_CAP_GEN(mdev, ets))
 		return -EOPNOTSUPP;
@@ -713,7 +713,7 @@ static int mlx5_set_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *in,
 static int mlx5_query_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *out,
 				     int outlen)
 {
-	u32 in[MLX5_ST_SZ_DW(qtct_reg)];
+	u32 in[MLX5_ST_SZ_DW(qetc_reg)];
 
 	if (!MLX5_CAP_GEN(mdev, ets))
 		return -EOPNOTSUPP;
-- 
2.17.1


From 852473b1fccbd63a7d32bf185495df048118d0b6 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Fri, 22 Jun 2018 10:15:39 +0200
Subject: [PATCH 19/53] net: mvneta: fix the Rx desc DMA address in the Rx path

[ Upstream commit 271f7ff5aa5a73488b7a9d8b84b5205fb5b2f7cc ]

When using s/w buffer management, buffers are allocated and DMA mapped.
When doing so on an arm64 platform, an offset correction is applied on
the DMA address, before storing it in an Rx descriptor. The issue is
this DMA address is then used later in the Rx path without removing the
offset correction. Thus the DMA address is wrong, which can led to
various issues.

This patch fixes this by removing the offset correction from the DMA
address retrieved from the Rx descriptor before using it in the Rx path.

Fixes: 8d5047cf9ca2 ("net: mvneta: Convert to be 64 bits compatible")
Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 17a904cc6a5e..0ad2f3f7da85 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -1932,7 +1932,7 @@ static int mvneta_rx_swbm(struct mvneta_port *pp, int rx_todo,
 		rx_bytes = rx_desc->data_size - (ETH_FCS_LEN + MVNETA_MH_SIZE);
 		index = rx_desc - rxq->descs;
 		data = rxq->buf_virt_addr[index];
-		phys_addr = rx_desc->buf_phys_addr;
+		phys_addr = rx_desc->buf_phys_addr - pp->rx_offset_correction;
 
 		if (!mvneta_rxq_desc_is_first_last(rx_status) ||
 		    (rx_status & MVNETA_RXD_ERR_SUMMARY)) {
-- 
2.17.1


From bd11d1c0af3d46183a2286007c6b26f23b645923 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 21 Jun 2018 14:16:02 -0700
Subject: [PATCH 20/53] net/packet: fix use-after-free

[ Upstream commit 945d015ee0c3095d2290e845565a23dedfd8027c ]

We should put copy_skb in receive_queue only after
a successful call to virtio_net_hdr_from_skb().

syzbot report :

BUG: KASAN: use-after-free in __skb_unlink include/linux/skbuff.h:1843 [inline]
BUG: KASAN: use-after-free in __skb_dequeue include/linux/skbuff.h:1863 [inline]
BUG: KASAN: use-after-free in skb_dequeue+0x16a/0x180 net/core/skbuff.c:2815
Read of size 8 at addr ffff8801b044ecc0 by task syz-executor217/4553

CPU: 0 PID: 4553 Comm: syz-executor217 Not tainted 4.18.0-rc1+ #111
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c9/0x2b4 lib/dump_stack.c:113
 print_address_description+0x6c/0x20b mm/kasan/report.c:256
 kasan_report_error mm/kasan/report.c:354 [inline]
 kasan_report.cold.7+0x242/0x2fe mm/kasan/report.c:412
 __asan_report_load8_noabort+0x14/0x20 mm/kasan/report.c:433
 __skb_unlink include/linux/skbuff.h:1843 [inline]
 __skb_dequeue include/linux/skbuff.h:1863 [inline]
 skb_dequeue+0x16a/0x180 net/core/skbuff.c:2815
 skb_queue_purge+0x26/0x40 net/core/skbuff.c:2852
 packet_set_ring+0x675/0x1da0 net/packet/af_packet.c:4331
 packet_release+0x630/0xd90 net/packet/af_packet.c:2991
 __sock_release+0xd7/0x260 net/socket.c:603
 sock_close+0x19/0x20 net/socket.c:1186
 __fput+0x35b/0x8b0 fs/file_table.c:209
 ____fput+0x15/0x20 fs/file_table.c:243
 task_work_run+0x1ec/0x2a0 kernel/task_work.c:113
 exit_task_work include/linux/task_work.h:22 [inline]
 do_exit+0x1b08/0x2750 kernel/exit.c:865
 do_group_exit+0x177/0x440 kernel/exit.c:968
 __do_sys_exit_group kernel/exit.c:979 [inline]
 __se_sys_exit_group kernel/exit.c:977 [inline]
 __x64_sys_exit_group+0x3e/0x50 kernel/exit.c:977
 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x4448e9
Code: Bad RIP value.
RSP: 002b:00007ffd5f777ca8 EFLAGS: 00000202 ORIG_RAX: 00000000000000e7
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00000000004448e9
RDX: 00000000004448e9 RSI: 000000000000fcfb RDI: 0000000000000001
RBP: 00000000006cf018 R08: 00007ffd0000a45b R09: 0000000000000000
R10: 00007ffd5f777e48 R11: 0000000000000202 R12: 00000000004021f0
R13: 0000000000402280 R14: 0000000000000000 R15: 0000000000000000

Allocated by task 4553:
 save_stack+0x43/0xd0 mm/kasan/kasan.c:448
 set_track mm/kasan/kasan.c:460 [inline]
 kasan_kmalloc+0xc4/0xe0 mm/kasan/kasan.c:553
 kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:490
 kmem_cache_alloc+0x12e/0x760 mm/slab.c:3554
 skb_clone+0x1f5/0x500 net/core/skbuff.c:1282
 tpacket_rcv+0x28f7/0x3200 net/packet/af_packet.c:2221
 deliver_skb net/core/dev.c:1925 [inline]
 deliver_ptype_list_skb net/core/dev.c:1940 [inline]
 __netif_receive_skb_core+0x1bfb/0x3680 net/core/dev.c:4611
 __netif_receive_skb+0x2c/0x1e0 net/core/dev.c:4693
 netif_receive_skb_internal+0x12e/0x7d0 net/core/dev.c:4767
 netif_receive_skb+0xbf/0x420 net/core/dev.c:4791
 tun_rx_batched.isra.55+0x4ba/0x8c0 drivers/net/tun.c:1571
 tun_get_user+0x2af1/0x42f0 drivers/net/tun.c:1981
 tun_chr_write_iter+0xb9/0x154 drivers/net/tun.c:2009
 call_write_iter include/linux/fs.h:1795 [inline]
 new_sync_write fs/read_write.c:474 [inline]
 __vfs_write+0x6c6/0x9f0 fs/read_write.c:487
 vfs_write+0x1f8/0x560 fs/read_write.c:549
 ksys_write+0x101/0x260 fs/read_write.c:598
 __do_sys_write fs/read_write.c:610 [inline]
 __se_sys_write fs/read_write.c:607 [inline]
 __x64_sys_write+0x73/0xb0 fs/read_write.c:607
 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Freed by task 4553:
 save_stack+0x43/0xd0 mm/kasan/kasan.c:448
 set_track mm/kasan/kasan.c:460 [inline]
 __kasan_slab_free+0x11a/0x170 mm/kasan/kasan.c:521
 kasan_slab_free+0xe/0x10 mm/kasan/kasan.c:528
 __cache_free mm/slab.c:3498 [inline]
 kmem_cache_free+0x86/0x2d0 mm/slab.c:3756
 kfree_skbmem+0x154/0x230 net/core/skbuff.c:582
 __kfree_skb net/core/skbuff.c:642 [inline]
 kfree_skb+0x1a5/0x580 net/core/skbuff.c:659
 tpacket_rcv+0x189e/0x3200 net/packet/af_packet.c:2385
 deliver_skb net/core/dev.c:1925 [inline]
 deliver_ptype_list_skb net/core/dev.c:1940 [inline]
 __netif_receive_skb_core+0x1bfb/0x3680 net/core/dev.c:4611
 __netif_receive_skb+0x2c/0x1e0 net/core/dev.c:4693
 netif_receive_skb_internal+0x12e/0x7d0 net/core/dev.c:4767
 netif_receive_skb+0xbf/0x420 net/core/dev.c:4791
 tun_rx_batched.isra.55+0x4ba/0x8c0 drivers/net/tun.c:1571
 tun_get_user+0x2af1/0x42f0 drivers/net/tun.c:1981
 tun_chr_write_iter+0xb9/0x154 drivers/net/tun.c:2009
 call_write_iter include/linux/fs.h:1795 [inline]
 new_sync_write fs/read_write.c:474 [inline]
 __vfs_write+0x6c6/0x9f0 fs/read_write.c:487
 vfs_write+0x1f8/0x560 fs/read_write.c:549
 ksys_write+0x101/0x260 fs/read_write.c:598
 __do_sys_write fs/read_write.c:610 [inline]
 __se_sys_write fs/read_write.c:607 [inline]
 __x64_sys_write+0x73/0xb0 fs/read_write.c:607
 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

The buggy address belongs to the object at ffff8801b044ecc0
 which belongs to the cache skbuff_head_cache of size 232
The buggy address is located 0 bytes inside of
 232-byte region [ffff8801b044ecc0, ffff8801b044eda8)
The buggy address belongs to the page:
page:ffffea0006c11380 count:1 mapcount:0 mapping:ffff8801d9be96c0 index:0x0
flags: 0x2fffc0000000100(slab)
raw: 02fffc0000000100 ffffea0006c17988 ffff8801d9bec248 ffff8801d9be96c0
raw: 0000000000000000 ffff8801b044e040 000000010000000c 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff8801b044eb80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
 ffff8801b044ec00: 00 00 00 00 00 00 00 00 00 00 00 00 00 fc fc fc
>ffff8801b044ec80: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb
                                           ^
 ffff8801b044ed00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff8801b044ed80: fb fb fb fb fb fc fc fc fc fc fc fc fc fc fc fc

Fixes: 58d19b19cd99 ("packet: vnet_hdr support for tpacket_rcv")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 16 +++++++---------
 1 file changed, 7 insertions(+), 9 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 38d132d007ba..cb0f02785749 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2294,6 +2294,13 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 		if (po->stats.stats1.tp_drops)
 			status |= TP_STATUS_LOSING;
 	}
+
+	if (do_vnet &&
+	    virtio_net_hdr_from_skb(skb, h.raw + macoff -
+				    sizeof(struct virtio_net_hdr),
+				    vio_le(), true, 0))
+		goto drop_n_account;
+
 	po->stats.stats1.tp_packets++;
 	if (copy_skb) {
 		status |= TP_STATUS_COPY;
@@ -2301,15 +2308,6 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	}
 	spin_unlock(&sk->sk_receive_queue.lock);
 
-	if (do_vnet) {
-		if (virtio_net_hdr_from_skb(skb, h.raw + macoff -
-					    sizeof(struct virtio_net_hdr),
-					    vio_le(), true, 0)) {
-			spin_lock(&sk->sk_receive_queue.lock);
-			goto drop_n_account;
-		}
-	}
-
 	skb_copy_bits(skb, 0, h.raw + macoff, snaplen);
 
 	if (!(ts_status = tpacket_get_timestamp(skb, &ts, po->tp_tstamp)))
-- 
2.17.1


From c65075fee803c4b284d1a9cb88e9d64a738b1ae9 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Tue, 19 Jun 2018 15:39:46 +0200
Subject: [PATCH 21/53] net/sched: act_ife: fix recursive lock and idr leak

[ Upstream commit 0a889b9404c084c6fd145020c939a8f688b3e058 ]

a recursive lock warning [1] can be observed with the following script,

 # $TC actions add action ife encode allow prio pass index 42
 IFE type 0xED3E
 # $TC actions replace action ife encode allow tcindex pass index 42

in case the kernel was unable to run the last command (e.g. because of
the impossibility to load 'act_meta_skbtcindex'). For a similar reason,
the kernel can leak idr in the error path of tcf_ife_init(), because
tcf_idr_release() is not called after successful idr reservation:

 # $TC actions add action ife encode allow tcindex index 47
 IFE type 0xED3E
 RTNETLINK answers: No such file or directory
 We have an error talking to the kernel
 # $TC actions add action ife encode allow tcindex index 47
 IFE type 0xED3E
 RTNETLINK answers: No space left on device
 We have an error talking to the kernel
 # $TC actions add action ife encode use mark 7 type 0xfefe pass index 47
 IFE type 0xFEFE
 RTNETLINK answers: No space left on device
 We have an error talking to the kernel

Since tcfa_lock is already taken when the action is being edited, a call
to tcf_idr_release() wrongly makes tcf_idr_cleanup() take the same lock
again. On the other hand, tcf_idr_release() needs to be called in the
error path of tcf_ife_init(), to undo the last tcf_idr_create() invocation.
Fix both problems in tcf_ife_init().
Since the cleanup() routine can now be called when ife->params is NULL,
also add a NULL pointer check to avoid calling kfree_rcu(NULL, rcu).

 [1]
 ============================================
 WARNING: possible recursive locking detected
 4.17.0-rc4.kasan+ #417 Tainted: G            E
 --------------------------------------------
 tc/3932 is trying to acquire lock:
 000000005097c9a6 (&(&p->tcfa_lock)->rlock){+...}, at: tcf_ife_cleanup+0x19/0x80 [act_ife]

 but task is already holding lock:
 000000005097c9a6 (&(&p->tcfa_lock)->rlock){+...}, at: tcf_ife_init+0xf6d/0x13c0 [act_ife]

 other info that might help us debug this:
  Possible unsafe locking scenario:

        CPU0
        ----
   lock(&(&p->tcfa_lock)->rlock);
   lock(&(&p->tcfa_lock)->rlock);

  *** DEADLOCK ***

  May be due to missing lock nesting notation

 2 locks held by tc/3932:
  #0: 000000007ca8e990 (rtnl_mutex){+.+.}, at: tcf_ife_init+0xf61/0x13c0 [act_ife]
  #1: 000000005097c9a6 (&(&p->tcfa_lock)->rlock){+...}, at: tcf_ife_init+0xf6d/0x13c0 [act_ife]

 stack backtrace:
 CPU: 3 PID: 3932 Comm: tc Tainted: G            E     4.17.0-rc4.kasan+ #417
 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
 Call Trace:
  dump_stack+0x9a/0xeb
  __lock_acquire+0xf43/0x34a0
  ? debug_check_no_locks_freed+0x2b0/0x2b0
  ? debug_check_no_locks_freed+0x2b0/0x2b0
  ? debug_check_no_locks_freed+0x2b0/0x2b0
  ? __mutex_lock+0x62f/0x1240
  ? kvm_sched_clock_read+0x1a/0x30
  ? sched_clock+0x5/0x10
  ? sched_clock_cpu+0x18/0x170
  ? find_held_lock+0x39/0x1d0
  ? lock_acquire+0x10b/0x330
  lock_acquire+0x10b/0x330
  ? tcf_ife_cleanup+0x19/0x80 [act_ife]
  _raw_spin_lock_bh+0x38/0x70
  ? tcf_ife_cleanup+0x19/0x80 [act_ife]
  tcf_ife_cleanup+0x19/0x80 [act_ife]
  __tcf_idr_release+0xff/0x350
  tcf_ife_init+0xdde/0x13c0 [act_ife]
  ? ife_exit_net+0x290/0x290 [act_ife]
  ? __lock_is_held+0xb4/0x140
  tcf_action_init_1+0x67b/0xad0
  ? tcf_action_dump_old+0xa0/0xa0
  ? sched_clock+0x5/0x10
  ? sched_clock_cpu+0x18/0x170
  ? kvm_sched_clock_read+0x1a/0x30
  ? sched_clock+0x5/0x10
  ? sched_clock_cpu+0x18/0x170
  ? memset+0x1f/0x40
  tcf_action_init+0x30f/0x590
  ? tcf_action_init_1+0xad0/0xad0
  ? memset+0x1f/0x40
  tc_ctl_action+0x48e/0x5e0
  ? mutex_lock_io_nested+0x1160/0x1160
  ? tca_action_gd+0x990/0x990
  ? sched_clock+0x5/0x10
  ? find_held_lock+0x39/0x1d0
  rtnetlink_rcv_msg+0x4da/0x990
  ? validate_linkmsg+0x680/0x680
  ? sched_clock_cpu+0x18/0x170
  ? find_held_lock+0x39/0x1d0
  netlink_rcv_skb+0x127/0x350
  ? validate_linkmsg+0x680/0x680
  ? netlink_ack+0x970/0x970
  ? __kmalloc_node_track_caller+0x304/0x3a0
  netlink_unicast+0x40f/0x5d0
  ? netlink_attachskb+0x580/0x580
  ? _copy_from_iter_full+0x187/0x760
  ? import_iovec+0x90/0x390
  netlink_sendmsg+0x67f/0xb50
  ? netlink_unicast+0x5d0/0x5d0
  ? copy_msghdr_from_user+0x206/0x340
  ? netlink_unicast+0x5d0/0x5d0
  sock_sendmsg+0xb3/0xf0
  ___sys_sendmsg+0x60a/0x8b0
  ? copy_msghdr_from_user+0x340/0x340
  ? lock_downgrade+0x5e0/0x5e0
  ? tty_write_lock+0x18/0x50
  ? kvm_sched_clock_read+0x1a/0x30
  ? sched_clock+0x5/0x10
  ? sched_clock_cpu+0x18/0x170
  ? find_held_lock+0x39/0x1d0
  ? lock_downgrade+0x5e0/0x5e0
  ? lock_acquire+0x10b/0x330
  ? __audit_syscall_entry+0x316/0x690
  ? current_kernel_time64+0x6b/0xd0
  ? __fget_light+0x55/0x1f0
  ? __sys_sendmsg+0xd2/0x170
  __sys_sendmsg+0xd2/0x170
  ? __ia32_sys_shutdown+0x70/0x70
  ? syscall_trace_enter+0x57a/0xd60
  ? rcu_read_lock_sched_held+0xdc/0x110
  ? __bpf_trace_sys_enter+0x10/0x10
  ? do_syscall_64+0x22/0x480
  do_syscall_64+0xa5/0x480
  entry_SYSCALL_64_after_hwframe+0x49/0xbe
 RIP: 0033:0x7fd646988ba0
 RSP: 002b:00007fffc9fab3c8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
 RAX: ffffffffffffffda RBX: 00007fffc9fab4f0 RCX: 00007fd646988ba0
 RDX: 0000000000000000 RSI: 00007fffc9fab440 RDI: 0000000000000003
 RBP: 000000005b28c8b3 R08: 0000000000000002 R09: 0000000000000000
 R10: 00007fffc9faae20 R11: 0000000000000246 R12: 0000000000000000
 R13: 00007fffc9fab504 R14: 0000000000000001 R15: 000000000066c100

Fixes: 4e8c86155010 ("net sched: net sched: ife action fix late binding")
Fixes: ef6980b6becb ("introduce IFE action")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ife.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 8527cfdc446d..078d52212172 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -415,7 +415,8 @@ static void tcf_ife_cleanup(struct tc_action *a)
 	spin_unlock_bh(&ife->tcf_lock);
 
 	p = rcu_dereference_protected(ife->params, 1);
-	kfree_rcu(p, rcu);
+	if (p)
+		kfree_rcu(p, rcu);
 }
 
 /* under ife->tcf_lock for existing action */
@@ -543,10 +544,8 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 				       NULL, NULL);
 		if (err) {
 metadata_parse_err:
-			if (exists)
-				tcf_idr_release(*a, bind);
 			if (ret == ACT_P_CREATED)
-				_tcf_ife_cleanup(*a);
+				tcf_idr_release(*a, bind);
 
 			if (exists)
 				spin_unlock_bh(&ife->tcf_lock);
@@ -567,7 +566,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 		err = use_all_metadata(ife);
 		if (err) {
 			if (ret == ACT_P_CREATED)
-				_tcf_ife_cleanup(*a);
+				tcf_idr_release(*a, bind);
 
 			if (exists)
 				spin_unlock_bh(&ife->tcf_lock);
-- 
2.17.1


From e379a1f2134dc0f777f327db5ff640a28e1eba37 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Tue, 19 Jun 2018 15:45:50 +0200
Subject: [PATCH 22/53] net/sched: act_ife: preserve the action control in case
 of error

[ Upstream commit cbf56c29624fa056a0c1c3d177e67aa51a7fd8d6 ]

in the following script

 # tc actions add action ife encode allow prio pass index 42
 # tc actions replace action ife encode allow tcindex drop index 42

the action control should remain equal to 'pass', if the kernel failed
to replace the TC action. Pospone the assignment of the action control,
to ensure it is not overwritten in the error path of tcf_ife_init().

Fixes: ef6980b6becb ("introduce IFE action")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ife.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 078d52212172..20d7d36b2fc9 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -517,8 +517,6 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 			saddr = nla_data(tb[TCA_IFE_SMAC]);
 	}
 
-	ife->tcf_action = parm->action;
-
 	if (parm->flags & IFE_ENCODE) {
 		if (daddr)
 			ether_addr_copy(p->eth_dst, daddr);
@@ -575,6 +573,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 		}
 	}
 
+	ife->tcf_action = parm->action;
 	if (exists)
 		spin_unlock_bh(&ife->tcf_lock);
 
-- 
2.17.1


From 22cb83c29060813e663b76e557a68ce9c70fc246 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Date: Fri, 15 Jun 2018 13:27:31 +0300
Subject: [PATCH 23/53] net_sched: blackhole: tell upper qdisc about dropped
 packets

[ Upstream commit 7e85dc8cb35abf16455f1511f0670b57c1a84608 ]

When blackhole is used on top of classful qdisc like hfsc it breaks
qlen and backlog counters because packets are disappear without notice.

In HFSC non-zero qlen while all classes are inactive triggers warning:
WARNING: ... at net/sched/sch_hfsc.c:1393 hfsc_dequeue+0xba4/0xe90 [sch_hfsc]
and schedules watchdog work endlessly.

This patch return __NET_XMIT_BYPASS in addition to NET_XMIT_SUCCESS,
this flag tells upper layer: this packet is gone and isn't queued.

Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_blackhole.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_blackhole.c b/net/sched/sch_blackhole.c
index c98a61e980ba..9c4c2bb547d7 100644
--- a/net/sched/sch_blackhole.c
+++ b/net/sched/sch_blackhole.c
@@ -21,7 +21,7 @@ static int blackhole_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 			     struct sk_buff **to_free)
 {
 	qdisc_drop(skb, sch, to_free);
-	return NET_XMIT_SUCCESS;
+	return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
 }
 
 static struct sk_buff *blackhole_dequeue(struct Qdisc *sch)
-- 
2.17.1


From 20f99fdbcf1995c13164f54fb3046691038e3225 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 19 Jun 2018 19:18:50 -0700
Subject: [PATCH 24/53] net: sungem: fix rx checksum support

[ Upstream commit 12b03558cef6d655d0d394f5e98a6fd07c1f6c0f ]

After commit 88078d98d1bb ("net: pskb_trim_rcsum() and CHECKSUM_COMPLETE
are friends"), sungem owners reported the infamous "eth0: hw csum failure"
message.

CHECKSUM_COMPLETE has in fact never worked for this driver, but this
was masked by the fact that upper stacks had to strip the FCS, and
therefore skb->ip_summed was set back to CHECKSUM_NONE before
my recent change.

Driver configures a number of bytes to skip when the chip computes
the checksum, and for some reason only half of the Ethernet header
was skipped.

Then a second problem is that we should strip the FCS by default,
unless the driver is updated to eventually support NETIF_F_RXFCS in
the future.

Finally, a driver should check if NETIF_F_RXCSUM feature is enabled
or not, so that the admin can turn off rx checksum if wanted.

Many thanks to Andreas Schwab and Mathieu Malaterre for their
help in debugging this issue.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Meelis Roos <mroos@linux.ee>
Reported-by: Mathieu Malaterre <malat@debian.org>
Reported-by: Andreas Schwab <schwab@linux-m68k.org>
Tested-by: Andreas Schwab <schwab@linux-m68k.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sun/sungem.c | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c
index 7a16d40a72d1..b9221fc1674d 100644
--- a/drivers/net/ethernet/sun/sungem.c
+++ b/drivers/net/ethernet/sun/sungem.c
@@ -60,8 +60,7 @@
 #include <linux/sungem_phy.h>
 #include "sungem.h"
 
-/* Stripping FCS is causing problems, disabled for now */
-#undef STRIP_FCS
+#define STRIP_FCS
 
 #define DEFAULT_MSG	(NETIF_MSG_DRV		| \
 			 NETIF_MSG_PROBE	| \
@@ -435,7 +434,7 @@ static int gem_rxmac_reset(struct gem *gp)
 	writel(desc_dma & 0xffffffff, gp->regs + RXDMA_DBLOW);
 	writel(RX_RING_SIZE - 4, gp->regs + RXDMA_KICK);
 	val = (RXDMA_CFG_BASE | (RX_OFFSET << 10) |
-	       ((14 / 2) << 13) | RXDMA_CFG_FTHRESH_128);
+	       (ETH_HLEN << 13) | RXDMA_CFG_FTHRESH_128);
 	writel(val, gp->regs + RXDMA_CFG);
 	if (readl(gp->regs + GREG_BIFCFG) & GREG_BIFCFG_M66EN)
 		writel(((5 & RXDMA_BLANK_IPKTS) |
@@ -760,7 +759,6 @@ static int gem_rx(struct gem *gp, int work_to_do)
 	struct net_device *dev = gp->dev;
 	int entry, drops, work_done = 0;
 	u32 done;
-	__sum16 csum;
 
 	if (netif_msg_rx_status(gp))
 		printk(KERN_DEBUG "%s: rx interrupt, done: %d, rx_new: %d\n",
@@ -855,9 +853,13 @@ static int gem_rx(struct gem *gp, int work_to_do)
 			skb = copy_skb;
 		}
 
-		csum = (__force __sum16)htons((status & RXDCTRL_TCPCSUM) ^ 0xffff);
-		skb->csum = csum_unfold(csum);
-		skb->ip_summed = CHECKSUM_COMPLETE;
+		if (likely(dev->features & NETIF_F_RXCSUM)) {
+			__sum16 csum;
+
+			csum = (__force __sum16)htons((status & RXDCTRL_TCPCSUM) ^ 0xffff);
+			skb->csum = csum_unfold(csum);
+			skb->ip_summed = CHECKSUM_COMPLETE;
+		}
 		skb->protocol = eth_type_trans(skb, gp->dev);
 
 		napi_gro_receive(&gp->napi, skb);
@@ -1761,7 +1763,7 @@ static void gem_init_dma(struct gem *gp)
 	writel(0, gp->regs + TXDMA_KICK);
 
 	val = (RXDMA_CFG_BASE | (RX_OFFSET << 10) |
-	       ((14 / 2) << 13) | RXDMA_CFG_FTHRESH_128);
+	       (ETH_HLEN << 13) | RXDMA_CFG_FTHRESH_128);
 	writel(val, gp->regs + RXDMA_CFG);
 
 	writel(desc_dma >> 32, gp->regs + RXDMA_DBHI);
@@ -2985,8 +2987,8 @@ static int gem_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	pci_set_drvdata(pdev, dev);
 
 	/* We can do scatter/gather and HW checksum */
-	dev->hw_features = NETIF_F_SG | NETIF_F_HW_CSUM;
-	dev->features |= dev->hw_features | NETIF_F_RXCSUM;
+	dev->hw_features = NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_RXCSUM;
+	dev->features = dev->hw_features;
 	if (pci_using_dac)
 		dev->features |= NETIF_F_HIGHDMA;
 
-- 
2.17.1


From adf8f75c12b7a2327e268f94ac7cd46613b860db Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Mon, 18 Jun 2018 12:30:37 -0700
Subject: [PATCH 25/53] net/tcp: Fix socket lookups with SO_BINDTODEVICE

[ Upstream commit 8c43bd1706885ba1acfa88da02bc60a2ec16f68c ]

Similar to 69678bcd4d2d ("udp: fix SO_BINDTODEVICE"), TCP socket lookups
need to fail if dev_match is not true. Currently, a packet to a given port
can match a socket bound to device when it should not. In the VRF case,
this causes the lookup to hit a VRF socket and not a global socket
resulting in a response trying to go through the VRF when it should not.

Fixes: 3fa6f616a7a4d ("net: ipv4: add second dif to inet socket lookups")
Fixes: 4297a0ef08572 ("net: ipv6: add second dif to inet6 socket lookups")
Reported-by: Lou Berger <lberger@labn.net>
Diagnosed-by: Renato Westphal <renato@opensourcerouting.org>
Tested-by: Renato Westphal <renato@opensourcerouting.org>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/inet_hashtables.c  | 4 ++--
 net/ipv6/inet6_hashtables.c | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 31ff46daae97..3647167c8fa3 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -243,9 +243,9 @@ static inline int compute_score(struct sock *sk, struct net *net,
 			bool dev_match = (sk->sk_bound_dev_if == dif ||
 					  sk->sk_bound_dev_if == sdif);
 
-			if (exact_dif && !dev_match)
+			if (!dev_match)
 				return -1;
-			if (sk->sk_bound_dev_if && dev_match)
+			if (sk->sk_bound_dev_if)
 				score += 4;
 		}
 		if (sk->sk_incoming_cpu == raw_smp_processor_id())
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 2febe26de6a1..595ad408dba0 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -113,9 +113,9 @@ static inline int compute_score(struct sock *sk, struct net *net,
 			bool dev_match = (sk->sk_bound_dev_if == dif ||
 					  sk->sk_bound_dev_if == sdif);
 
-			if (exact_dif && !dev_match)
+			if (!dev_match)
 				return -1;
-			if (sk->sk_bound_dev_if && dev_match)
+			if (sk->sk_bound_dev_if)
 				score++;
 		}
 		if (sk->sk_incoming_cpu == raw_smp_processor_id())
-- 
2.17.1


From 9d18cc296e09be62eeea9e3a9b2964b1c316df5a Mon Sep 17 00:00:00 2001
From: Sudarsana Reddy Kalluru <sudarsana.kalluru@cavium.com>
Date: Sun, 1 Jul 2018 20:03:08 -0700
Subject: [PATCH 26/53] qede: Adverstise software timestamp caps when PHC is
 not available.

[ Upstream commit 82a4e71b1565dea8387f54503e806cf374e779ec ]

When ptp clock is not available for a PF (e.g., higher PFs in NPAR mode),
get-tsinfo() callback should return the software timestamp capabilities
instead of returning the error.

Fixes: 4c55215c ("qede: Add driver support for PTP")
Signed-off-by: Sudarsana Reddy Kalluru <Sudarsana.Kalluru@cavium.com>
Signed-off-by: Michal Kalderon <Michal.Kalderon@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qede/qede_ptp.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qede/qede_ptp.c b/drivers/net/ethernet/qlogic/qede/qede_ptp.c
index 02adb513f475..013ff567283c 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ptp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ptp.c
@@ -337,8 +337,14 @@ int qede_ptp_get_ts_info(struct qede_dev *edev, struct ethtool_ts_info *info)
 {
 	struct qede_ptp *ptp = edev->ptp;
 
-	if (!ptp)
-		return -EIO;
+	if (!ptp) {
+		info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
+					SOF_TIMESTAMPING_RX_SOFTWARE |
+					SOF_TIMESTAMPING_SOFTWARE;
+		info->phc_index = -1;
+
+		return 0;
+	}
 
 	info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
 				SOF_TIMESTAMPING_RX_SOFTWARE |
-- 
2.17.1


From 5e27a995fb09ca678d922daa955b91b495ab87b8 Mon Sep 17 00:00:00 2001
From: Sudarsana Reddy Kalluru <sudarsana.kalluru@cavium.com>
Date: Sun, 1 Jul 2018 20:03:06 -0700
Subject: [PATCH 27/53] qed: Fix setting of incorrect eswitch mode.

[ Upstream commit 538f8d00ba8bb417c4d9e76c61dee59d812d8287 ]

By default, driver sets the eswitch mode incorrectly as VEB (virtual
Ethernet bridging).
Need to set VEB eswitch mode only when sriov is enabled, and it should be
to set NONE by default. The patch incorporates this change.

Fixes: 0fefbfbaa ("qed*: Management firmware - notifications and defaults")
Signed-off-by: Sudarsana Reddy Kalluru <Sudarsana.Kalluru@cavium.com>
Signed-off-by: Michal Kalderon <Michal.Kalderon@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_dev.c   |  2 +-
 drivers/net/ethernet/qlogic/qed/qed_sriov.c | 19 +++++++++++++++++--
 2 files changed, 18 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index d2ad5e92c74f..5644b24d85b0 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -1789,7 +1789,7 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
 			DP_INFO(p_hwfn, "Failed to update driver state\n");
 
 		rc = qed_mcp_ov_update_eswitch(p_hwfn, p_hwfn->p_main_ptt,
-					       QED_OV_ESWITCH_VEB);
+					       QED_OV_ESWITCH_NONE);
 		if (rc)
 			DP_INFO(p_hwfn, "Failed to update eswitch mode\n");
 	}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
index 5acb91b3564c..419c681ea2be 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
@@ -4400,6 +4400,8 @@ static void qed_sriov_enable_qid_config(struct qed_hwfn *hwfn,
 static int qed_sriov_enable(struct qed_dev *cdev, int num)
 {
 	struct qed_iov_vf_init_params params;
+	struct qed_hwfn *hwfn;
+	struct qed_ptt *ptt;
 	int i, j, rc;
 
 	if (num >= RESC_NUM(&cdev->hwfns[0], QED_VPORT)) {
@@ -4412,8 +4414,8 @@ static int qed_sriov_enable(struct qed_dev *cdev, int num)
 
 	/* Initialize HW for VF access */
 	for_each_hwfn(cdev, j) {
-		struct qed_hwfn *hwfn = &cdev->hwfns[j];
-		struct qed_ptt *ptt = qed_ptt_acquire(hwfn);
+		hwfn = &cdev->hwfns[j];
+		ptt = qed_ptt_acquire(hwfn);
 
 		/* Make sure not to use more than 16 queues per VF */
 		params.num_queues = min_t(int,
@@ -4449,6 +4451,19 @@ static int qed_sriov_enable(struct qed_dev *cdev, int num)
 		goto err;
 	}
 
+	hwfn = QED_LEADING_HWFN(cdev);
+	ptt = qed_ptt_acquire(hwfn);
+	if (!ptt) {
+		DP_ERR(hwfn, "Failed to acquire ptt\n");
+		rc = -EBUSY;
+		goto err;
+	}
+
+	rc = qed_mcp_ov_update_eswitch(hwfn, ptt, QED_OV_ESWITCH_VEB);
+	if (rc)
+		DP_INFO(cdev, "Failed to update eswitch mode\n");
+	qed_ptt_release(hwfn, ptt);
+
 	return num;
 
 err:
-- 
2.17.1


From 2249a22bf3e703cf4750ac9bd2eb1aa3dc635b58 Mon Sep 17 00:00:00 2001
From: Sudarsana Reddy Kalluru <sudarsana.kalluru@cavium.com>
Date: Sun, 1 Jul 2018 20:03:07 -0700
Subject: [PATCH 28/53] qed: Fix use of incorrect size in memcpy call.

[ Upstream commit cc9b27cdf7bd3c86df73439758ac1564bc8f5bbe ]

Use the correct size value while copying chassis/port id values.

Fixes: 6ad8c632e ("qed: Add support for query/config dcbx.")
Signed-off-by: Sudarsana Reddy Kalluru <Sudarsana.Kalluru@cavium.com>
Signed-off-by: Michal Kalderon <Michal.Kalderon@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_dcbx.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
index 449777f21237..e82986df9b8e 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
@@ -700,9 +700,9 @@ qed_dcbx_get_local_lldp_params(struct qed_hwfn *p_hwfn,
 	p_local = &p_hwfn->p_dcbx_info->lldp_local[LLDP_NEAREST_BRIDGE];
 
 	memcpy(params->lldp_local.local_chassis_id, p_local->local_chassis_id,
-	       ARRAY_SIZE(p_local->local_chassis_id));
+	       sizeof(p_local->local_chassis_id));
 	memcpy(params->lldp_local.local_port_id, p_local->local_port_id,
-	       ARRAY_SIZE(p_local->local_port_id));
+	       sizeof(p_local->local_port_id));
 }
 
 static void
@@ -714,9 +714,9 @@ qed_dcbx_get_remote_lldp_params(struct qed_hwfn *p_hwfn,
 	p_remote = &p_hwfn->p_dcbx_info->lldp_remote[LLDP_NEAREST_BRIDGE];
 
 	memcpy(params->lldp_remote.peer_chassis_id, p_remote->peer_chassis_id,
-	       ARRAY_SIZE(p_remote->peer_chassis_id));
+	       sizeof(p_remote->peer_chassis_id));
 	memcpy(params->lldp_remote.peer_port_id, p_remote->peer_port_id,
-	       ARRAY_SIZE(p_remote->peer_port_id));
+	       sizeof(p_remote->peer_port_id));
 }
 
 static int
-- 
2.17.1


From 406d463d0efc5eb6c4bbfaeb50eaf6b9f877e81e Mon Sep 17 00:00:00 2001
From: Sudarsana Reddy Kalluru <sudarsana.kalluru@cavium.com>
Date: Sun, 1 Jul 2018 20:03:05 -0700
Subject: [PATCH 29/53] qed: Limit msix vectors in kdump kernel to the minimum
 required count.

[ Upstream commit bb7858ba1102f82470a917e041fd23e6385c31be ]

Memory size is limited in the kdump kernel environment. Allocation of more
msix-vectors (or queues) consumes few tens of MBs of memory, which might
lead to the kdump kernel failure.
This patch adds changes to limit the number of MSI-X vectors in kdump
kernel to minimum required value (i.e., 2 per engine).

Fixes: fe56b9e6a ("qed: Add module with basic common support")
Signed-off-by: Sudarsana Reddy Kalluru <Sudarsana.Kalluru@cavium.com>
Signed-off-by: Michal Kalderon <Michal.Kalderon@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_main.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index 7870ae2a6f7e..261f21d6b0b0 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -780,6 +780,14 @@ static int qed_slowpath_setup_int(struct qed_dev *cdev,
 	/* We want a minimum of one slowpath and one fastpath vector per hwfn */
 	cdev->int_params.in.min_msix_cnt = cdev->num_hwfns * 2;
 
+	if (is_kdump_kernel()) {
+		DP_INFO(cdev,
+			"Kdump kernel: Limit the max number of requested MSI-X vectors to %hd\n",
+			cdev->int_params.in.min_msix_cnt);
+		cdev->int_params.in.num_vectors =
+			cdev->int_params.in.min_msix_cnt;
+	}
+
 	rc = qed_set_int_mode(cdev, false);
 	if (rc)  {
 		DP_ERR(cdev, "qed_slowpath_setup_int ERR\n");
-- 
2.17.1


From 4cd820aca0b4ca551ce76b1b98ba1bae1adb5109 Mon Sep 17 00:00:00 2001
From: Aleksander Morgado <aleksander@aleksander.es>
Date: Sat, 23 Jun 2018 23:22:52 +0200
Subject: [PATCH 30/53] qmi_wwan: add support for the Dell Wireless 5821e
 module
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit e7e197edd09c25774b4f12cab19f9d5462f240f4 ]

This module exposes two USB configurations: a QMI+AT capable setup on
USB config #1 and a MBIM capable setup on USB config #2.

By default the kernel will choose the MBIM capable configuration as
long as the cdc_mbim driver is available. This patch adds support for
the QMI port in the secondary configuration.

Signed-off-by: Aleksander Morgado <aleksander@aleksander.es>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 094680871687..04c22f508ed9 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1246,6 +1246,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x413c, 0x81b3, 8)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */
 	{QMI_FIXED_INTF(0x413c, 0x81b6, 8)},	/* Dell Wireless 5811e */
 	{QMI_FIXED_INTF(0x413c, 0x81b6, 10)},	/* Dell Wireless 5811e */
+	{QMI_FIXED_INTF(0x413c, 0x81d7, 1)},	/* Dell Wireless 5821e */
 	{QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)},	/* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */
 	{QMI_FIXED_INTF(0x03f0, 0x9d1d, 1)},	/* HP lt4120 Snapdragon X5 LTE */
 	{QMI_FIXED_INTF(0x22de, 0x9061, 3)},	/* WeTelecom WPD-600N */
-- 
2.17.1


From bc62778099ae1e8c04e0b15afa93b653f2aba23d Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jslaby@suse.cz>
Date: Mon, 25 Jun 2018 09:26:27 +0200
Subject: [PATCH 31/53] r8152: napi hangup fix after disconnect

[ Upstream commit 0ee1f4734967af8321ecebaf9c74221ace34f2d5 ]

When unplugging an r8152 adapter while the interface is UP, the NIC
becomes unusable.  usb->disconnect (aka rtl8152_disconnect) deletes
napi. Then, rtl8152_disconnect calls unregister_netdev and that invokes
netdev->ndo_stop (aka rtl8152_close). rtl8152_close tries to
napi_disable, but the napi is already deleted by disconnect above. So
the first while loop in napi_disable never finishes. This results in
complete deadlock of the network layer as there is rtnl_mutex held by
unregister_netdev.

So avoid the call to napi_disable in rtl8152_close when the device is
already gone.

The other calls to usb_kill_urb, cancel_delayed_work_sync,
netif_stop_queue etc. seem to be fine. The urb and netdev is not
destroyed yet.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Cc: linux-usb@vger.kernel.org
Cc: netdev@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 86f7196f9d91..2a58607a6aea 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -3962,7 +3962,8 @@ static int rtl8152_close(struct net_device *netdev)
 #ifdef CONFIG_PM_SLEEP
 	unregister_pm_notifier(&tp->pm_notifier);
 #endif
-	napi_disable(&tp->napi);
+	if (!test_bit(RTL8152_UNPLUG, &tp->flags))
+		napi_disable(&tp->napi);
 	clear_bit(WORK_ENABLE, &tp->flags);
 	usb_kill_urb(tp->intr_urb);
 	cancel_delayed_work_sync(&tp->schedule);
-- 
2.17.1


From 461dc2afa1c4468da253ded4755bb774eb967541 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Fri, 29 Jun 2018 19:45:53 +0200
Subject: [PATCH 32/53] s390/qeth: don't clobber buffer on async TX completion

[ Upstream commit ce28867fd20c23cd769e78b4d619c4755bf71a1c ]

If qeth_qdio_output_handler() detects that a transmit requires async
completion, it replaces the pending buffer's metadata object
(qeth_qdio_out_buffer) so that this queue buffer can be re-used while
the data is pending completion.

Later when the CQ indicates async completion of such a metadata object,
qeth_qdio_cq_handler() tries to free any data associated with this
object (since HW has now completed the transfer). By calling
qeth_clear_output_buffer(), it erronously operates on the queue buffer
that _previously_ belonged to this transfer ... but which has been
potentially re-used several times by now.
This results in double-free's of the buffer's data, and failing
transmits as the buffer descriptor is scrubbed in mid-air.

The correct way of handling this situation is to
1. scrub the queue buffer when it is prepared for re-use, and
2. later obtain the data addresses from the async-completion notifier
   (ie. the AOB), instead of the queue buffer.

All this only affects qeth devices used for af_iucv HiperTransport.

Fixes: 0da9581ddb0f ("qeth: exploit asynchronous delivery of storage blocks")
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core.h      | 11 +++++++++++
 drivers/s390/net/qeth_core_main.c | 22 ++++++++++++++++------
 2 files changed, 27 insertions(+), 6 deletions(-)

diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 78b98b3e7efa..b7f75339683e 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -831,6 +831,17 @@ struct qeth_trap_id {
 /*some helper functions*/
 #define QETH_CARD_IFNAME(card) (((card)->dev)? (card)->dev->name : "")
 
+static inline void qeth_scrub_qdio_buffer(struct qdio_buffer *buf,
+					  unsigned int elements)
+{
+	unsigned int i;
+
+	for (i = 0; i < elements; i++)
+		memset(&buf->element[i], 0, sizeof(struct qdio_buffer_element));
+	buf->element[14].sflags = 0;
+	buf->element[15].sflags = 0;
+}
+
 /**
  * qeth_get_elements_for_range() -	find number of SBALEs to cover range.
  * @start:				Start of the address range.
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index dffd820731f2..955409a7a1c1 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -73,9 +73,6 @@ static void qeth_notify_skbs(struct qeth_qdio_out_q *queue,
 		struct qeth_qdio_out_buffer *buf,
 		enum iucv_tx_notify notification);
 static void qeth_release_skbs(struct qeth_qdio_out_buffer *buf);
-static void qeth_clear_output_buffer(struct qeth_qdio_out_q *queue,
-		struct qeth_qdio_out_buffer *buf,
-		enum qeth_qdio_buffer_states newbufstate);
 static int qeth_init_qdio_out_buf(struct qeth_qdio_out_q *, int);
 
 struct workqueue_struct *qeth_wq;
@@ -488,6 +485,7 @@ static void qeth_qdio_handle_aob(struct qeth_card *card,
 	struct qaob *aob;
 	struct qeth_qdio_out_buffer *buffer;
 	enum iucv_tx_notify notification;
+	unsigned int i;
 
 	aob = (struct qaob *) phys_to_virt(phys_aob_addr);
 	QETH_CARD_TEXT(card, 5, "haob");
@@ -512,10 +510,18 @@ static void qeth_qdio_handle_aob(struct qeth_card *card,
 	qeth_notify_skbs(buffer->q, buffer, notification);
 
 	buffer->aob = NULL;
-	qeth_clear_output_buffer(buffer->q, buffer,
-				 QETH_QDIO_BUF_HANDLED_DELAYED);
+	/* Free dangling allocations. The attached skbs are handled by
+	 * qeth_cleanup_handled_pending().
+	 */
+	for (i = 0;
+	     i < aob->sb_count && i < QETH_MAX_BUFFER_ELEMENTS(card);
+	     i++) {
+		if (aob->sba[i] && buffer->is_header[i])
+			kmem_cache_free(qeth_core_header_cache,
+					(void *) aob->sba[i]);
+	}
+	atomic_set(&buffer->state, QETH_QDIO_BUF_HANDLED_DELAYED);
 
-	/* from here on: do not touch buffer anymore */
 	qdio_release_aob(aob);
 }
 
@@ -3759,6 +3765,10 @@ void qeth_qdio_output_handler(struct ccw_device *ccwdev,
 			QETH_CARD_TEXT(queue->card, 5, "aob");
 			QETH_CARD_TEXT_(queue->card, 5, "%lx",
 					virt_to_phys(buffer->aob));
+
+			/* prepare the queue slot for re-use: */
+			qeth_scrub_qdio_buffer(buffer->buffer,
+					       QETH_MAX_BUFFER_ELEMENTS(card));
 			if (qeth_init_qdio_out_buf(queue, bidx)) {
 				QETH_CARD_TEXT(card, 2, "outofbuf");
 				qeth_schedule_recovery(card);
-- 
2.17.1


From 7bada52759fba8e1547a6b77a90ab920e91a790f Mon Sep 17 00:00:00 2001
From: Bhadram Varka <vbhadram@nvidia.com>
Date: Sun, 17 Jun 2018 20:02:05 +0530
Subject: [PATCH 33/53] stmmac: fix DMA channel hang in half-duplex mode

[ Upstream commit b6cfffa7ad923c73f317ea50fd4ebcb3b4b6669c ]

HW does not support Half-duplex mode in multi-queue
scenario. Fix it by not advertising the Half-Duplex
mode if multi-queue enabled.

Signed-off-by: Bhadram Varka <vbhadram@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index b65e2d144698..1e1cc5256eca 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -927,6 +927,7 @@ static void stmmac_check_pcs_mode(struct stmmac_priv *priv)
 static int stmmac_init_phy(struct net_device *dev)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
+	u32 tx_cnt = priv->plat->tx_queues_to_use;
 	struct phy_device *phydev;
 	char phy_id_fmt[MII_BUS_ID_SIZE + 3];
 	char bus_id[MII_BUS_ID_SIZE];
@@ -967,6 +968,15 @@ static int stmmac_init_phy(struct net_device *dev)
 		phydev->advertising &= ~(SUPPORTED_1000baseT_Half |
 					 SUPPORTED_1000baseT_Full);
 
+	/*
+	 * Half-duplex mode not supported with multiqueue
+	 * half-duplex can only works with single queue
+	 */
+	if (tx_cnt > 1)
+		phydev->supported &= ~(SUPPORTED_1000baseT_Half |
+				       SUPPORTED_100baseT_Half |
+				       SUPPORTED_10baseT_Half);
+
 	/*
 	 * Broken HW is sometimes missing the pull-up resistor on the
 	 * MDIO line, which results in reads to non-existent devices returning
-- 
2.17.1


From c29887d13b1fe1ce44344d3110f723b42f58affa Mon Sep 17 00:00:00 2001
From: Doron Roberts-Kedes <doronrk@fb.com>
Date: Tue, 26 Jun 2018 18:33:33 -0700
Subject: [PATCH 34/53] strparser: Remove early eaten to fix full tcp receive
 buffer stall

[ Upstream commit 977c7114ebda2e746a114840d3a875e0cdb826fb ]

On receving an incomplete message, the existing code stores the
remaining length of the cloned skb in the early_eaten field instead of
incrementing the value returned by __strp_recv. This defers invocation
of sock_rfree for the current skb until the next invocation of
__strp_recv, which returns early_eaten if early_eaten is non-zero.

This behavior causes a stall when the current message occupies the very
tail end of a massive skb, and strp_peek/need_bytes indicates that the
remainder of the current message has yet to arrive on the socket. The
TCP receive buffer is totally full, causing the TCP window to go to
zero, so the remainder of the message will never arrive.

Incrementing the value returned by __strp_recv by the amount otherwise
stored in early_eaten prevents stalls of this nature.

Signed-off-by: Doron Roberts-Kedes <doronrk@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/strparser/strparser.c | 17 +----------------
 1 file changed, 1 insertion(+), 16 deletions(-)

diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index 092bebc70048..7afd66949a91 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -35,7 +35,6 @@ struct _strp_msg {
 	 */
 	struct strp_msg strp;
 	int accum_len;
-	int early_eaten;
 };
 
 static inline struct _strp_msg *_strp_msg(struct sk_buff *skb)
@@ -115,20 +114,6 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb,
 	head = strp->skb_head;
 	if (head) {
 		/* Message already in progress */
-
-		stm = _strp_msg(head);
-		if (unlikely(stm->early_eaten)) {
-			/* Already some number of bytes on the receive sock
-			 * data saved in skb_head, just indicate they
-			 * are consumed.
-			 */
-			eaten = orig_len <= stm->early_eaten ?
-				orig_len : stm->early_eaten;
-			stm->early_eaten -= eaten;
-
-			return eaten;
-		}
-
 		if (unlikely(orig_offset)) {
 			/* Getting data with a non-zero offset when a message is
 			 * in progress is not expected. If it does happen, we
@@ -297,9 +282,9 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb,
 				}
 
 				stm->accum_len += cand_len;
+				eaten += cand_len;
 				strp->need_bytes = stm->strp.full_len -
 						       stm->accum_len;
-				stm->early_eaten = cand_len;
 				STRP_STATS_ADD(strp->stats.bytes, cand_len);
 				desc->count = 0; /* Stop reading socket */
 				break;
-- 
2.17.1


From 4c23fba85ce9396304d01796f4680370fe84adba Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Wed, 27 Jun 2018 16:04:48 -0700
Subject: [PATCH 35/53] tcp: fix Fast Open key endianness

[ Upstream commit c860e997e9170a6d68f9d1e6e2cf61f572191aaf ]

Fast Open key could be stored in different endian based on the CPU.
Previously hosts in different endianness in a server farm using
the same key config (sysctl value) would produce different cookies.
This patch fixes it by always storing it as little endian to keep
same API for LE hosts.

Reported-by: Daniele Iamartino <danielei@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/sysctl_net_ipv4.c | 18 +++++++++++++-----
 1 file changed, 13 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 4b195bac8ac0..2f600f261690 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -263,8 +263,9 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write,
 	    ipv4.sysctl_tcp_fastopen);
 	struct ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) };
 	struct tcp_fastopen_context *ctxt;
-	int ret;
 	u32  user_key[4]; /* 16 bytes, matching TCP_FASTOPEN_KEY_LENGTH */
+	__le32 key[4];
+	int ret, i;
 
 	tbl.data = kmalloc(tbl.maxlen, GFP_KERNEL);
 	if (!tbl.data)
@@ -273,11 +274,14 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write,
 	rcu_read_lock();
 	ctxt = rcu_dereference(net->ipv4.tcp_fastopen_ctx);
 	if (ctxt)
-		memcpy(user_key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH);
+		memcpy(key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH);
 	else
-		memset(user_key, 0, sizeof(user_key));
+		memset(key, 0, sizeof(key));
 	rcu_read_unlock();
 
+	for (i = 0; i < ARRAY_SIZE(key); i++)
+		user_key[i] = le32_to_cpu(key[i]);
+
 	snprintf(tbl.data, tbl.maxlen, "%08x-%08x-%08x-%08x",
 		user_key[0], user_key[1], user_key[2], user_key[3]);
 	ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
@@ -288,13 +292,17 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write,
 			ret = -EINVAL;
 			goto bad_key;
 		}
-		tcp_fastopen_reset_cipher(net, NULL, user_key,
+
+		for (i = 0; i < ARRAY_SIZE(user_key); i++)
+			key[i] = cpu_to_le32(user_key[i]);
+
+		tcp_fastopen_reset_cipher(net, NULL, key,
 					  TCP_FASTOPEN_KEY_LENGTH);
 	}
 
 bad_key:
 	pr_debug("proc FO key set 0x%x-%x-%x-%x <- 0x%s: %u\n",
-	       user_key[0], user_key[1], user_key[2], user_key[3],
+		user_key[0], user_key[1], user_key[2], user_key[3],
 	       (char *)tbl.data, ret);
 	kfree(tbl.data);
 	return ret;
-- 
2.17.1


From 5d934f2418aa32f7241bc15a5394ee5112cf3df9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@helsinki.fi>
Date: Fri, 29 Jun 2018 13:07:53 +0300
Subject: [PATCH 36/53] tcp: prevent bogus FRTO undos with non-SACK flows
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 1236f22fbae15df3736ab4a984c64c0c6ee6254c ]

If SACK is not enabled and the first cumulative ACK after the RTO
retransmission covers more than the retransmitted skb, a spurious
FRTO undo will trigger (assuming FRTO is enabled for that RTO).
The reason is that any non-retransmitted segment acknowledged will
set FLAG_ORIG_SACK_ACKED in tcp_clean_rtx_queue even if there is
no indication that it would have been delivered for real (the
scoreboard is not kept with TCPCB_SACKED_ACKED bits in the non-SACK
case so the check for that bit won't help like it does with SACK).
Having FLAG_ORIG_SACK_ACKED set results in the spurious FRTO undo
in tcp_process_loss.

We need to use more strict condition for non-SACK case and check
that none of the cumulatively ACKed segments were retransmitted
to prove that progress is due to original transmissions. Only then
keep FLAG_ORIG_SACK_ACKED set, allowing FRTO undo to proceed in
non-SACK case.

(FLAG_ORIG_SACK_ACKED is planned to be renamed to FLAG_ORIG_PROGRESS
to better indicate its purpose but to keep this change minimal, it
will be done in another patch).

Besides burstiness and congestion control violations, this problem
can result in RTO loop: When the loss recovery is prematurely
undoed, only new data will be transmitted (if available) and
the next retransmission can occur only after a new RTO which in case
of multiple losses (that are not for consecutive packets) requires
one RTO per loss to recover.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Tested-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e51c644484dc..1f25ebab25d2 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3149,6 +3149,15 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack,
 
 		if (tcp_is_reno(tp)) {
 			tcp_remove_reno_sacks(sk, pkts_acked);
+
+			/* If any of the cumulatively ACKed segments was
+			 * retransmitted, non-SACK case cannot confirm that
+			 * progress was due to original transmission due to
+			 * lack of TCPCB_SACKED_ACKED bits even if some of
+			 * the packets may have been never retransmitted.
+			 */
+			if (flag & FLAG_RETRANS_DATA_ACKED)
+				flag &= ~FLAG_ORIG_SACK_ACKED;
 		} else {
 			int delta;
 
-- 
2.17.1


From 142505db3b8631f8aa70fa9fa8538a68aa27a7ef Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Thu, 21 Jun 2018 13:11:31 +0800
Subject: [PATCH 37/53] vhost_net: validate sock before trying to put its fd

[ Upstream commit b8f1f65882f07913157c44673af7ec0b308d03eb ]

Sock will be NULL if we pass -1 to vhost_net_set_backend(), but when
we meet errors during ubuf allocation, the code does not check for
NULL before calling sockfd_put(), this will lead NULL
dereferencing. Fixing by checking sock pointer before.

Fixes: bab632d69ee4 ("vhost: vhost TX zero-copy support")
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/net.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index eeaf6739215f..dd4eb986f693 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -1219,7 +1219,8 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
 	if (ubufs)
 		vhost_net_ubuf_put_wait_and_free(ubufs);
 err_ubufs:
-	sockfd_put(sock);
+	if (sock)
+		sockfd_put(sock);
 err_vq:
 	mutex_unlock(&vq->mutex);
 err:
-- 
2.17.1


From 5ff3ecfe0def2238f4f93986dae142c5cd2f9613 Mon Sep 17 00:00:00 2001
From: Claudio Imbrenda <imbrenda@linux.vnet.ibm.com>
Date: Wed, 20 Jun 2018 15:51:51 +0200
Subject: [PATCH 38/53] VSOCK: fix loopback on big-endian systems

[ Upstream commit e5ab564c9ebee77794842ca7d7476147b83d6a27 ]

The dst_cid and src_cid are 64 bits, therefore 64 bit accessors should be
used, and in fact in virtio_transport_common.c only 64 bit accessors are
used. Using 32 bit accessors for 64 bit values breaks big endian systems.

This patch fixes a wrong use of le32_to_cpu in virtio_transport_send_pkt.

Fixes: b9116823189e85ccf384 ("VSOCK: add loopback to virtio_transport")

Signed-off-by: Claudio Imbrenda <imbrenda@linux.vnet.ibm.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/vmw_vsock/virtio_transport.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 8e03bd3f3668..5d3cce9e8744 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -201,7 +201,7 @@ virtio_transport_send_pkt(struct virtio_vsock_pkt *pkt)
 		return -ENODEV;
 	}
 
-	if (le32_to_cpu(pkt->hdr.dst_cid) == vsock->guest_cid)
+	if (le64_to_cpu(pkt->hdr.dst_cid) == vsock->guest_cid)
 		return virtio_transport_send_pkt_loopback(vsock, pkt);
 
 	if (pkt->reply)
-- 
2.17.1


From 3ba939b6a0a269e79961c33ddc9a65bda2c89f8d Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Wed, 27 Jun 2018 17:47:37 +0800
Subject: [PATCH 39/53] hinic: reset irq affinity before freeing irq

[ Upstream commit 82be2ab159a3a0ae4024b946a31f12b221f6c8ff ]

Following warning is seen when rmmod hinic. This is because affinity
value is not reset before calling free_irq(). This patch fixes it.

[   55.181232] WARNING: CPU: 38 PID: 19589 at kernel/irq/manage.c:1608
__free_irq+0x2aa/0x2c0

Fixes: 352f58b0d9f2 ("net-next/hinic: Set Rxq irq to specific cpu for NUMA")
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/huawei/hinic/hinic_rx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.c b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
index e2e5cdc7119c..4c0f7eda1166 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_rx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
@@ -439,6 +439,7 @@ static void rx_free_irq(struct hinic_rxq *rxq)
 {
 	struct hinic_rq *rq = rxq->rq;
 
+	irq_set_affinity_hint(rq->irq, NULL);
 	free_irq(rq->irq, rxq);
 	rx_del_napi(rxq);
 }
-- 
2.17.1


From e490cb3d1a532648756dd7e593020dffafc59956 Mon Sep 17 00:00:00 2001
From: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Date: Mon, 25 Jun 2018 20:36:27 -0700
Subject: [PATCH 40/53] nfp: flower: fix mpls ether type detection

[ Upstream commit a64119415ff248efa61301783bc26551df5dabf6 ]

Previously it was not possible to distinguish between mpls ether types and
other ether types. This leads to incorrect classification of offloaded
filters that match on mpls ether type. For example the following two
filters overlap:

 # tc filter add dev eth0 parent ffff: \
    protocol 0x8847 flower \
    action mirred egress redirect dev eth1

 # tc filter add dev eth0 parent ffff: \
    protocol 0x0800 flower \
    action mirred egress redirect dev eth2

The driver now correctly includes the mac_mpls layer where HW stores mpls
fields, when it detects an mpls ether type. It also sets the MPLS_Q bit to
indicate that the filter should match mpls packets.

Fixes: bb055c198d9b ("nfp: add mpls match offloading support")
Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/match.c  | 14 ++++++++++++++
 .../net/ethernet/netronome/nfp/flower/offload.c    |  8 ++++++++
 2 files changed, 22 insertions(+)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c
index 91935405f586..84f7a5dbea9d 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/match.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/match.c
@@ -123,6 +123,20 @@ nfp_flower_compile_mac(struct nfp_flower_mac_mpls *frame,
 			 NFP_FLOWER_MASK_MPLS_Q;
 
 		frame->mpls_lse = cpu_to_be32(t_mpls);
+	} else if (dissector_uses_key(flow->dissector,
+				      FLOW_DISSECTOR_KEY_BASIC)) {
+		/* Check for mpls ether type and set NFP_FLOWER_MASK_MPLS_Q
+		 * bit, which indicates an mpls ether type but without any
+		 * mpls fields.
+		 */
+		struct flow_dissector_key_basic *key_basic;
+
+		key_basic = skb_flow_dissector_target(flow->dissector,
+						      FLOW_DISSECTOR_KEY_BASIC,
+						      flow->key);
+		if (key_basic->n_proto == cpu_to_be16(ETH_P_MPLS_UC) ||
+		    key_basic->n_proto == cpu_to_be16(ETH_P_MPLS_MC))
+			frame->mpls_lse = cpu_to_be32(NFP_FLOWER_MASK_MPLS_Q);
 	}
 }
 
diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index 114d2ab02a38..33c8d67b55a3 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -264,6 +264,14 @@ nfp_flower_calculate_key_layers(struct nfp_app *app,
 		case cpu_to_be16(ETH_P_ARP):
 			return -EOPNOTSUPP;
 
+		case cpu_to_be16(ETH_P_MPLS_UC):
+		case cpu_to_be16(ETH_P_MPLS_MC):
+			if (!(key_layer & NFP_FLOWER_LAYER_MAC)) {
+				key_layer |= NFP_FLOWER_LAYER_MAC;
+				key_size += sizeof(struct nfp_flower_mac_mpls);
+			}
+			break;
+
 		/* Will be included in layer 2. */
 		case cpu_to_be16(ETH_P_8021Q):
 			break;
-- 
2.17.1


From 23aea371208a4e7e5bc2b1281422ffefba9e8059 Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Tue, 26 Jun 2018 10:44:01 +0200
Subject: [PATCH 41/53] net: macb: initialize bp->queues[0].bp for at91rm9200

[ Upstream commit fec9d3b1dc4c481f20f5d2f5aef3ad1cb7504186 ]

The macb driver currently crashes on at91rm9200 with the following trace:

Unable to handle kernel NULL pointer dereference at virtual address 00000014
[...]
[<c031da44>] (macb_rx_desc) from [<c031f2bc>] (at91ether_open+0x2e8/0x3f8)
[<c031f2bc>] (at91ether_open) from [<c041e8d8>] (__dev_open+0x120/0x13c)
[<c041e8d8>] (__dev_open) from [<c041ec08>] (__dev_change_flags+0x17c/0x1a8)
[<c041ec08>] (__dev_change_flags) from [<c041ec4c>] (dev_change_flags+0x18/0x4c)
[<c041ec4c>] (dev_change_flags) from [<c07a5f4c>] (ip_auto_config+0x220/0x10b0)
[<c07a5f4c>] (ip_auto_config) from [<c000a4fc>] (do_one_initcall+0x78/0x18c)
[<c000a4fc>] (do_one_initcall) from [<c0783e50>] (kernel_init_freeable+0x184/0x1c4)
[<c0783e50>] (kernel_init_freeable) from [<c0574d70>] (kernel_init+0x8/0xe8)
[<c0574d70>] (kernel_init) from [<c00090e0>] (ret_from_fork+0x14/0x34)

Solve that by initializing bp->queues[0].bp in at91ether_init (as is done
in macb_init).

Fixes: ae1f2a56d273 ("net: macb: Added support for many RX queues")
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Acked-by: Nicolas Ferre <nicolas.ferre@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index b4c9268100bb..068f991395dc 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -3732,6 +3732,8 @@ static int at91ether_init(struct platform_device *pdev)
 	int err;
 	u32 reg;
 
+	bp->queues[0].bp = bp;
+
 	dev->netdev_ops = &at91ether_netdev_ops;
 	dev->ethtool_ops = &macb_ethtool_ops;
 
-- 
2.17.1


From 982bb50e2ff2507a9ba5bba638f63393dc86b0da Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Fri, 29 Jun 2018 13:42:48 -0700
Subject: [PATCH 42/53] net: use dev_change_tx_queue_len() for SIOCSIFTXQLEN

[ Upstream commit 3f76df198288ceec92fc9eddecad1e73c52769b0 ]

As noticed by Eric, we need to switch to the helper
dev_change_tx_queue_len() for SIOCSIFTXQLEN call path too,
otheriwse still miss dev_qdisc_change_tx_queue_len().

Fixes: 6a643ddb5624 ("net: introduce helper dev_change_tx_queue_len()")
Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev_ioctl.c | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index a04e1e88bf3a..50537ff961a7 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -285,16 +285,9 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
 		if (ifr->ifr_qlen < 0)
 			return -EINVAL;
 		if (dev->tx_queue_len ^ ifr->ifr_qlen) {
-			unsigned int orig_len = dev->tx_queue_len;
-
-			dev->tx_queue_len = ifr->ifr_qlen;
-			err = call_netdevice_notifiers(
-					NETDEV_CHANGE_TX_QUEUE_LEN, dev);
-			err = notifier_to_errno(err);
-			if (err) {
-				dev->tx_queue_len = orig_len;
+			err = dev_change_tx_queue_len(dev, ifr->ifr_qlen);
+			if (err)
 				return err;
-			}
 		}
 		return 0;
 
-- 
2.17.1


From b2c30a5753bf77c8145f9dae94e3cb3819c03531 Mon Sep 17 00:00:00 2001
From: John Hurley <john.hurley@netronome.com>
Date: Mon, 25 Jun 2018 20:36:28 -0700
Subject: [PATCH 43/53] nfp: reject binding to shared blocks

[ Upstream commit 951a8ee6def39e25d0e60b9394e5a249ba8b2390 ]

TC shared blocks allow multiple qdiscs to be grouped together and filters
shared between them. Currently the chains of filters attached to a block
are only flushed when the block is removed. If a qdisc is removed from a
block but the block still exists, flow del messages are not passed to the
callback registered for that qdisc. For the NFP, this presents the
possibility of rules still existing in hw when they should be removed.

Prevent binding to shared blocks until the kernel can send per qdisc del
messages when block unbinds occur.

tcf_block_shared() was not used outside of the core until now, so also
add an empty implementation for builds with CONFIG_NET_CLS=n.

Fixes: 4861738775d7 ("net: sched: introduce shared filter blocks infrastructure")
Signed-off-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/bpf/main.c       | 3 +++
 drivers/net/ethernet/netronome/nfp/flower/offload.c | 3 +++
 include/net/pkt_cls.h                               | 5 +++++
 3 files changed, 11 insertions(+)

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c
index 35fb31f682af..1a781281c57a 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c
@@ -194,6 +194,9 @@ static int nfp_bpf_setup_tc_block(struct net_device *netdev,
 	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
 		return -EOPNOTSUPP;
 
+	if (tcf_block_shared(f->block))
+		return -EOPNOTSUPP;
+
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block,
diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index 33c8d67b55a3..4de30d0f9491 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -601,6 +601,9 @@ static int nfp_flower_setup_tc_block(struct net_device *netdev,
 	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
 		return -EOPNOTSUPP;
 
+	if (tcf_block_shared(f->block))
+		return -EOPNOTSUPP;
+
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block,
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index e828d31be5da..3b4fbf690957 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -111,6 +111,11 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
 {
 }
 
+static inline bool tcf_block_shared(struct tcf_block *block)
+{
+	return false;
+}
+
 static inline struct Qdisc *tcf_block_q(struct tcf_block *block)
 {
 	return NULL;
-- 
2.17.1


From 4e9ace755b43b0e83b036ba2e113fef71574442f Mon Sep 17 00:00:00 2001
From: Ross Lagerwall <ross.lagerwall@citrix.com>
Date: Thu, 21 Jun 2018 14:00:20 +0100
Subject: [PATCH 44/53] xen-netfront: Fix mismatched rtnl_unlock

[ Upstream commit cb257783c2927b73614b20f915a91ff78aa6f3e8 ]

Fixes: f599c64fdf7d ("xen-netfront: Fix race between device setup and open")
Reported-by: Ben Hutchings <ben.hutchings@codethink.co.uk>
Signed-off-by: Ross Lagerwall <ross.lagerwall@citrix.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netfront.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 4dd0668003e7..244095bfd604 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -1810,7 +1810,7 @@ static int talk_to_netback(struct xenbus_device *dev,
 	err = xen_net_read_mac(dev, info->netdev->dev_addr);
 	if (err) {
 		xenbus_dev_fatal(dev, err, "parsing %s/mac", dev->nodename);
-		goto out;
+		goto out_unlocked;
 	}
 
 	rtnl_lock();
@@ -1925,6 +1925,7 @@ static int talk_to_netback(struct xenbus_device *dev,
 	xennet_destroy_queues(info);
  out:
 	rtnl_unlock();
+out_unlocked:
 	device_unregister(&dev->dev);
 	return err;
 }
-- 
2.17.1


From cdb1946f893a0d5bc6c1b412ac27c34626cbfa02 Mon Sep 17 00:00:00 2001
From: Ross Lagerwall <ross.lagerwall@citrix.com>
Date: Thu, 21 Jun 2018 14:00:21 +0100
Subject: [PATCH 45/53] xen-netfront: Update features after registering netdev

[ Upstream commit 45c8184c1bed1ca8a7f02918552063a00b909bf5 ]

Update the features after calling register_netdev() otherwise the
device features are not set up correctly and it not possible to change
the MTU of the device. After this change, the features reported by
ethtool match the device's features before the commit which introduced
the issue and it is possible to change the device's MTU.

Fixes: f599c64fdf7d ("xen-netfront: Fix race between device setup and open")
Reported-by: Liam Shepherd <liam@dancer.es>
Signed-off-by: Ross Lagerwall <ross.lagerwall@citrix.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netfront.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 244095bfd604..1d5082d30187 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -1951,10 +1951,6 @@ static int xennet_connect(struct net_device *dev)
 	/* talk_to_netback() sets the correct number of queues */
 	num_queues = dev->real_num_tx_queues;
 
-	rtnl_lock();
-	netdev_update_features(dev);
-	rtnl_unlock();
-
 	if (dev->reg_state == NETREG_UNINITIALIZED) {
 		err = register_netdev(dev);
 		if (err) {
@@ -1964,6 +1960,10 @@ static int xennet_connect(struct net_device *dev)
 		}
 	}
 
+	rtnl_lock();
+	netdev_update_features(dev);
+	rtnl_unlock();
+
 	/*
 	 * All public and private state should now be sane.  Get
 	 * ready to start sending and receiving packets and give the driver
-- 
2.17.1


From 28967315115375625dc501c737bb674be8b4eaef Mon Sep 17 00:00:00 2001
From: Govindarajulu Varadarajan <gvaradar@cisco.com>
Date: Mon, 18 Jun 2018 10:01:05 -0700
Subject: [PATCH 46/53] enic: do not overwrite error code

[ Upstream commit 56f772279a762984f6e9ebbf24a7c829faba5712 ]

In failure path, we overwrite err to what vnic_rq_disable() returns. In
case it returns 0, enic_open() returns success in case of error.

Reported-by: Ben Hutchings <ben.hutchings@codethink.co.uk>
Fixes: e8588e268509 ("enic: enable rq before updating rq descriptors")
Signed-off-by: Govindarajulu Varadarajan <gvaradar@cisco.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cisco/enic/enic_main.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index 8a8b12b720ef..454e57ef047a 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -1920,7 +1920,7 @@ static int enic_open(struct net_device *netdev)
 {
 	struct enic *enic = netdev_priv(netdev);
 	unsigned int i;
-	int err;
+	int err, ret;
 
 	err = enic_request_intr(enic);
 	if (err) {
@@ -1977,10 +1977,9 @@ static int enic_open(struct net_device *netdev)
 
 err_out_free_rq:
 	for (i = 0; i < enic->rq_count; i++) {
-		err = vnic_rq_disable(&enic->rq[i]);
-		if (err)
-			return err;
-		vnic_rq_clean(&enic->rq[i], enic_free_rq_buf);
+		ret = vnic_rq_disable(&enic->rq[i]);
+		if (!ret)
+			vnic_rq_clean(&enic->rq[i], enic_free_rq_buf);
 	}
 	enic_dev_notify_unset(enic);
 err_out_free_intr:
-- 
2.17.1


From a862cdb21e9571965af59adbd04e85782a4fb060 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Tue, 26 Jun 2018 17:39:53 +0200
Subject: [PATCH 47/53] i40e: split XDP_TX tail and XDP_REDIRECT map flushing
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 2e6893123830d04edc366e0ce59d46e622e140c1 ]

The driver was combining the XDP_TX tail flush and XDP_REDIRECT
map flushing (xdp_do_flush_map).  This is suboptimal, these two
flush operations should be kept separate.

It looks like the mistake was copy-pasted from ixgbe.

Fixes: d9314c474d4f ("i40e: add support for XDP_REDIRECT")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/i40e/i40e_txrx.c | 24 +++++++++++++--------
 1 file changed, 15 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index f174c72480ab..8d3522c94c3f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2199,9 +2199,10 @@ static bool i40e_is_non_eop(struct i40e_ring *rx_ring,
 	return true;
 }
 
-#define I40E_XDP_PASS 0
-#define I40E_XDP_CONSUMED 1
-#define I40E_XDP_TX 2
+#define I40E_XDP_PASS		0
+#define I40E_XDP_CONSUMED	BIT(0)
+#define I40E_XDP_TX		BIT(1)
+#define I40E_XDP_REDIR		BIT(2)
 
 static int i40e_xmit_xdp_ring(struct xdp_buff *xdp,
 			      struct i40e_ring *xdp_ring);
@@ -2235,7 +2236,7 @@ static struct sk_buff *i40e_run_xdp(struct i40e_ring *rx_ring,
 		break;
 	case XDP_REDIRECT:
 		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
-		result = !err ? I40E_XDP_TX : I40E_XDP_CONSUMED;
+		result = !err ? I40E_XDP_REDIR : I40E_XDP_CONSUMED;
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
@@ -2298,7 +2299,8 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
 	struct sk_buff *skb = rx_ring->skb;
 	u16 cleaned_count = I40E_DESC_UNUSED(rx_ring);
-	bool failure = false, xdp_xmit = false;
+	unsigned int xdp_xmit = 0;
+	bool failure = false;
 	struct xdp_buff xdp;
 
 	xdp.rxq = &rx_ring->xdp_rxq;
@@ -2359,8 +2361,10 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		}
 
 		if (IS_ERR(skb)) {
-			if (PTR_ERR(skb) == -I40E_XDP_TX) {
-				xdp_xmit = true;
+			unsigned int xdp_res = -PTR_ERR(skb);
+
+			if (xdp_res & (I40E_XDP_TX | I40E_XDP_REDIR)) {
+				xdp_xmit |= xdp_res;
 				i40e_rx_buffer_flip(rx_ring, rx_buffer, size);
 			} else {
 				rx_buffer->pagecnt_bias++;
@@ -2414,12 +2418,14 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		total_rx_packets++;
 	}
 
-	if (xdp_xmit) {
+	if (xdp_xmit & I40E_XDP_REDIR)
+		xdp_do_flush_map();
+
+	if (xdp_xmit & I40E_XDP_TX) {
 		struct i40e_ring *xdp_ring =
 			rx_ring->vsi->xdp_rings[rx_ring->queue_index];
 
 		i40e_xdp_ring_update_tail(xdp_ring);
-		xdp_do_flush_map();
 	}
 
 	rx_ring->skb = skb;
-- 
2.17.1


From 87e713715361dee9ba4cf78b9648e03868fe0ba2 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Thu, 31 May 2018 11:40:17 +0300
Subject: [PATCH 48/53] IB/mlx5: Avoid dealing with vport representors if not
 being e-switch manager

[ Upstream commit aff2252a2ad3844ca47bf2f18af071101baace40 ]

In smartnic env, the host (PF) driver might not be an e-switch
manager, hence the switchdev mode representors are running on
the embedded cpu (EC) and not at the host.

As such, we should avoid dealing with vport representors if
not being esw manager.

Fixes: b5ca15ad7e61 ('IB/mlx5: Add proper representors support')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/infiniband/hw/mlx5/main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 69716a7ea993..95a516ac6c39 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -5736,7 +5736,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	dev->num_ports = max(MLX5_CAP_GEN(mdev, num_ports),
 			     MLX5_CAP_GEN(mdev, num_vhca_ports));
 
-	if (MLX5_VPORT_MANAGER(mdev) &&
+	if (MLX5_ESWITCH_MANAGER(mdev) &&
 	    mlx5_ib_eswitch_mode(mdev->priv.eswitch) == SRIOV_OFFLOADS) {
 		dev->rep = mlx5_ib_vport_rep(mdev->priv.eswitch, 0);
 
-- 
2.17.1


From 6fe30e2580575423b470b029a0852cd8a2788983 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Fri, 29 Jun 2018 19:45:50 +0200
Subject: [PATCH 49/53] Revert "s390/qeth: use Read device to query hypervisor
 for MAC"

[ Upstream commit 4664610537d398d55be19432f9cd9c29c831e159 ]

This reverts commit b7493e91c11a757cf0f8ab26989642ee4bb2c642.

On its own, querying RDEV for a MAC address works fine. But when upgrading
from a qeth that previously queried DDEV on a z/VM NIC (ie. any kernel with
commit ec61bd2fd2a2), the RDEV query now returns a _different_ MAC address
than the DDEV query.

If the NIC is configured with MACPROTECT, z/VM apparently requires us to
use the MAC that was initially returned (on DDEV) and registered. So after
upgrading to a kernel that uses RDEV, the SETVMAC registration cmd for the
new MAC address fails and we end up with a non-operabel interface.

To avoid regressions on upgrade, switch back to using DDEV for the MAC
address query. The downgrade path (first RDEV, later DDEV) is fine, in this
case both queries return the same MAC address.

Fixes: b7493e91c11a ("s390/qeth: use Read device to query hypervisor for MAC")
Reported-by: Michal Kubecek <mkubecek@suse.com>
Tested-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 955409a7a1c1..b2eebcffd502 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -4845,7 +4845,7 @@ int qeth_vm_request_mac(struct qeth_card *card)
 		goto out;
 	}
 
-	ccw_device_get_id(CARD_RDEV(card), &id);
+	ccw_device_get_id(CARD_DDEV(card), &id);
 	request->resp_buf_len = sizeof(*response);
 	request->resp_version = DIAG26C_VERSION2;
 	request->op_code = DIAG26C_GET_MAC;
-- 
2.17.1


From 992cfa9a9afc3d1ada58bf58f35fb51c64b6b8b4 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Fri, 29 Jun 2018 19:45:52 +0200
Subject: [PATCH 50/53] s390/qeth: avoid using is_multicast_ether_addr_64bits
 on (u8 *)[6]

[ Upstream commit 9d0a58fb9747afd27d490c02a97889a1b59f6be4 ]

*ether_addr*_64bits functions have been introduced to optimize
performance critical paths, which access 6-byte ethernet address as u64
value to get "nice" assembly. A harmless hack works nicely on ethernet
addresses shoved into a structure or a larger buffer, until busted by
Kasan on smth like plain (u8 *)[6].

qeth_l2_set_mac_address calls qeth_l2_remove_mac passing
u8 old_addr[ETH_ALEN] as an argument.

Adding/removing macs for an ethernet adapter is not that performance
critical. Moreover is_multicast_ether_addr_64bits itself on s390 is not
faster than is_multicast_ether_addr:

is_multicast_ether_addr(%r2) -> %r2
llc	%r2,0(%r2)
risbg	%r2,%r2,63,191,0

is_multicast_ether_addr_64bits(%r2) -> %r2
llgc	%r2,0(%r2)
risbg	%r2,%r2,63,191,0

So, let's just use is_multicast_ether_addr instead of
is_multicast_ether_addr_64bits.

Fixes: bcacfcbc82b4 ("s390/qeth: fix MAC address update sequence")
Reviewed-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_l2_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index b8079f2a65b3..eea7001051d1 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -141,7 +141,7 @@ static int qeth_l2_send_setmac(struct qeth_card *card, __u8 *mac)
 
 static int qeth_l2_write_mac(struct qeth_card *card, u8 *mac)
 {
-	enum qeth_ipa_cmds cmd = is_multicast_ether_addr_64bits(mac) ?
+	enum qeth_ipa_cmds cmd = is_multicast_ether_addr(mac) ?
 					IPA_CMD_SETGMAC : IPA_CMD_SETVMAC;
 	int rc;
 
@@ -158,7 +158,7 @@ static int qeth_l2_write_mac(struct qeth_card *card, u8 *mac)
 
 static int qeth_l2_remove_mac(struct qeth_card *card, u8 *mac)
 {
-	enum qeth_ipa_cmds cmd = is_multicast_ether_addr_64bits(mac) ?
+	enum qeth_ipa_cmds cmd = is_multicast_ether_addr(mac) ?
 					IPA_CMD_DELGMAC : IPA_CMD_DELVMAC;
 	int rc;
 
-- 
2.17.1


From b76e0ca4ff23c15357a0bec1f0c4df99a9280c07 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Fri, 29 Jun 2018 19:45:51 +0200
Subject: [PATCH 51/53] s390/qeth: fix race when setting MAC address

[ Upstream commit 4789a21880488048105590049fc41a99f53d565d ]

When qeth_l2_set_mac_address() finds the card in a non-reachable state,
it merely copies the new MAC address into dev->dev_addr so that
__qeth_l2_set_online() can later register it with the HW.

But __qeth_l2_set_online() may very well be running concurrently, so we
can't trust the card state without appropriate locking:
If the online sequence is past the point where it registers
dev->dev_addr (but not yet in SOFTSETUP state), any address change needs
to be properly programmed into the HW. Otherwise the netdevice ends up
with a different MAC address than what's set in the HW, and inbound
traffic is not forwarded as expected.

This is most likely to occur for OSD in LPAR, where
commit 21b1702af12e ("s390/qeth: improve fallback to random MAC address")
now triggers eg. systemd to immediately change the MAC when the netdevice
is registered with a NET_ADDR_RANDOM address.

Fixes: bcacfcbc82b4 ("s390/qeth: fix MAC address update sequence")
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_l2_main.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index eea7001051d1..16dc8b83ca6f 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -523,27 +523,34 @@ static int qeth_l2_set_mac_address(struct net_device *dev, void *p)
 		return -ERESTARTSYS;
 	}
 
+	/* avoid racing against concurrent state change: */
+	if (!mutex_trylock(&card->conf_mutex))
+		return -EAGAIN;
+
 	if (!qeth_card_hw_is_reachable(card)) {
 		ether_addr_copy(dev->dev_addr, addr->sa_data);
-		return 0;
+		goto out_unlock;
 	}
 
 	/* don't register the same address twice */
 	if (ether_addr_equal_64bits(dev->dev_addr, addr->sa_data) &&
 	    (card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED))
-		return 0;
+		goto out_unlock;
 
 	/* add the new address, switch over, drop the old */
 	rc = qeth_l2_send_setmac(card, addr->sa_data);
 	if (rc)
-		return rc;
+		goto out_unlock;
 	ether_addr_copy(old_addr, dev->dev_addr);
 	ether_addr_copy(dev->dev_addr, addr->sa_data);
 
 	if (card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED)
 		qeth_l2_remove_mac(card, old_addr);
 	card->info.mac_bits |= QETH_LAYER2_MAC_REGISTERED;
-	return 0;
+
+out_unlock:
+	mutex_unlock(&card->conf_mutex);
+	return rc;
 }
 
 static void qeth_promisc_to_bridge(struct qeth_card *card)
-- 
2.17.1


From e51d52147db64a8a675a577109a3a42b805490de Mon Sep 17 00:00:00 2001
From: Bert Kenward <bkenward@solarflare.com>
Date: Fri, 29 Jun 2018 16:29:28 +0100
Subject: [PATCH 52/53] sfc: correctly initialise filter rwsem for farch

[ Upstream commit cafb39600e7a73263122a0e2db052d691686378f ]

Fixes: fc7a6c287ff3 ("sfc: use a semaphore to lock farch filters too")
Suggested-by: Joseph Korty <joe.korty@concurrent-rt.com>
Signed-off-by: Bert Kenward <bkenward@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/farch.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c
index c72adf8b52ea..9165e2b0c590 100644
--- a/drivers/net/ethernet/sfc/farch.c
+++ b/drivers/net/ethernet/sfc/farch.c
@@ -2794,6 +2794,7 @@ int efx_farch_filter_table_probe(struct efx_nic *efx)
 	if (!state)
 		return -ENOMEM;
 	efx->filter_state = state;
+	init_rwsem(&state->lock);
 
 	table = &state->table[EFX_FARCH_FILTER_TABLE_RX_IP];
 	table->id = EFX_FARCH_FILTER_TABLE_RX_IP;
-- 
2.17.1


From 82c02b71e5d95630afdb6b4d936bd34fe0f17fd8 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Tue, 26 Jun 2018 17:39:58 +0200
Subject: [PATCH 53/53] virtio_net: split XDP_TX kick and XDP_REDIRECT map
 flushing

[ Upstream commit 2471c75efed32529698c26da499954f0253cb401 ]

The driver was combining XDP_TX virtqueue_kick and XDP_REDIRECT
map flushing (xdp_do_flush_map).  This is suboptimal, these two
flush operations should be kept separate.

The suboptimal behavior was introduced in commit 9267c430c6b6
("virtio-net: add missing virtqueue kick when flushing packets").

Fixes: 9267c430c6b6 ("virtio-net: add missing virtqueue kick when flushing packets")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 30 +++++++++++++++++++-----------
 1 file changed, 19 insertions(+), 11 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 8c7207535179..11a3915e92e9 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -50,6 +50,10 @@ module_param(napi_tx, bool, 0644);
 /* Amount of XDP headroom to prepend to packets for use by xdp_adjust_head */
 #define VIRTIO_XDP_HEADROOM 256
 
+/* Separating two types of XDP xmit */
+#define VIRTIO_XDP_TX		BIT(0)
+#define VIRTIO_XDP_REDIR	BIT(1)
+
 /* RX packet size EWMA. The average packet size is used to determine the packet
  * buffer size when refilling RX rings. As the entire RX ring may be refilled
  * at once, the weight is chosen so that the EWMA will be insensitive to short-
@@ -547,7 +551,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 				     struct receive_queue *rq,
 				     void *buf, void *ctx,
 				     unsigned int len,
-				     bool *xdp_xmit)
+				     unsigned int *xdp_xmit)
 {
 	struct sk_buff *skb;
 	struct bpf_prog *xdp_prog;
@@ -615,14 +619,14 @@ static struct sk_buff *receive_small(struct net_device *dev,
 				trace_xdp_exception(vi->dev, xdp_prog, act);
 				goto err_xdp;
 			}
-			*xdp_xmit = true;
+			*xdp_xmit |= VIRTIO_XDP_TX;
 			rcu_read_unlock();
 			goto xdp_xmit;
 		case XDP_REDIRECT:
 			err = xdp_do_redirect(dev, &xdp, xdp_prog);
 			if (err)
 				goto err_xdp;
-			*xdp_xmit = true;
+			*xdp_xmit |= VIRTIO_XDP_REDIR;
 			rcu_read_unlock();
 			goto xdp_xmit;
 		default:
@@ -684,7 +688,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 					 void *buf,
 					 void *ctx,
 					 unsigned int len,
-					 bool *xdp_xmit)
+					 unsigned int *xdp_xmit)
 {
 	struct virtio_net_hdr_mrg_rxbuf *hdr = buf;
 	u16 num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers);
@@ -772,7 +776,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 					put_page(xdp_page);
 				goto err_xdp;
 			}
-			*xdp_xmit = true;
+			*xdp_xmit |= VIRTIO_XDP_REDIR;
 			if (unlikely(xdp_page != page))
 				put_page(page);
 			rcu_read_unlock();
@@ -784,7 +788,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 					put_page(xdp_page);
 				goto err_xdp;
 			}
-			*xdp_xmit = true;
+			*xdp_xmit |= VIRTIO_XDP_TX;
 			if (unlikely(xdp_page != page))
 				put_page(page);
 			rcu_read_unlock();
@@ -893,7 +897,8 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 }
 
 static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
-		       void *buf, unsigned int len, void **ctx, bool *xdp_xmit)
+		       void *buf, unsigned int len, void **ctx,
+		       unsigned int *xdp_xmit)
 {
 	struct net_device *dev = vi->dev;
 	struct sk_buff *skb;
@@ -1186,7 +1191,8 @@ static void refill_work(struct work_struct *work)
 	}
 }
 
-static int virtnet_receive(struct receive_queue *rq, int budget, bool *xdp_xmit)
+static int virtnet_receive(struct receive_queue *rq, int budget,
+			   unsigned int *xdp_xmit)
 {
 	struct virtnet_info *vi = rq->vq->vdev->priv;
 	unsigned int len, received = 0, bytes = 0;
@@ -1275,7 +1281,7 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
 	struct virtnet_info *vi = rq->vq->vdev->priv;
 	struct send_queue *sq;
 	unsigned int received, qp;
-	bool xdp_xmit = false;
+	unsigned int xdp_xmit = 0;
 
 	virtnet_poll_cleantx(rq);
 
@@ -1285,12 +1291,14 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
 	if (received < budget)
 		virtqueue_napi_complete(napi, rq->vq, received);
 
-	if (xdp_xmit) {
+	if (xdp_xmit & VIRTIO_XDP_REDIR)
+		xdp_do_flush_map();
+
+	if (xdp_xmit & VIRTIO_XDP_TX) {
 		qp = vi->curr_queue_pairs - vi->xdp_queue_pairs +
 		     smp_processor_id();
 		sq = &vi->sq[qp];
 		virtqueue_kick(sq->vq);
-		xdp_do_flush_map();
 	}
 
 	return received;
-- 
2.17.1

Re: [PATCHES] Networking

[Greg KH]

On Thu, Jul 19, 2018 at 08:35:57AM +0900, David Miller wrote:
> 
> ====================
> READ ME.  I have this stale email in my outgoing draft folder, and I
> have no idea if I actually sent this out successfully or not.
> 
> Please double check, thanks!

Nope, I have not seen these patches before at all.  Thanks for them, all
now queued up.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 107 bytes --]


Please queue up the following networking bug fixxes for 4.14.x and
4.17.x -stable, respectively.

Thanks!

[-- Attachment #2: net_414.mbox --]
[-- Type: Application/Octet-Stream, Size: 34759 bytes --]

From 706faa308e3dd22956a9eb52743ef2418bea4cb1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@toke.dk>
Date: Mon, 2 Jul 2018 22:52:20 +0200
Subject: [PATCH 01/18] gen_stats: Fix netlink stats dumping in the presence of
 padding
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit d5a672ac9f48f81b20b1cad1d9ed7bbf4e418d4c ]

The gen_stats facility will add a header for the toplevel nlattr of type
TCA_STATS2 that contains all stats added by qdisc callbacks. A reference
to this header is stored in the gnet_dump struct, and when all the
per-qdisc callbacks have finished adding their stats, the length of the
containing header will be adjusted to the right value.

However, on architectures that need padding (i.e., that don't set
CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS), the padding nlattr is added
before the stats, which means that the stored pointer will point to the
padding, and so when the header is fixed up, the result is just a very
big padding nlattr. Because most qdiscs also supply the legacy TCA_STATS
struct, this problem has been mostly invisible, but we exposed it with
the netlink attribute-based statistics in CAKE.

Fix the issue by fixing up the stored pointer if it points to a padding
nlattr.

Tested-by: Pete Heist <pete@heistp.net>
Tested-by: Kevin Darbyshire-Bryant <kevin@darbyshire-bryant.me.uk>
Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/gen_stats.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c
index 87f28557b329..441c04adedba 100644
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -77,8 +77,20 @@ gnet_stats_start_copy_compat(struct sk_buff *skb, int type, int tc_stats_type,
 		d->lock = lock;
 		spin_lock_bh(lock);
 	}
-	if (d->tail)
-		return gnet_stats_copy(d, type, NULL, 0, padattr);
+	if (d->tail) {
+		int ret = gnet_stats_copy(d, type, NULL, 0, padattr);
+
+		/* The initial attribute added in gnet_stats_copy() may be
+		 * preceded by a padding attribute, in which case d->tail will
+		 * end up pointing at the padding instead of the real attribute.
+		 * Fix this so gnet_stats_finish_copy() adjusts the length of
+		 * the right attribute.
+		 */
+		if (ret == 0 && d->tail->nla_type == padattr)
+			d->tail = (struct nlattr *)((char *)d->tail +
+						    NLA_ALIGN(d->tail->nla_len));
+		return ret;
+	}
 
 	return 0;
 }
-- 
2.17.1


From 00a18fd512080a07f38bacf15f030dd3a96dcf7d Mon Sep 17 00:00:00 2001
From: Tyler Hicks <tyhicks@canonical.com>
Date: Thu, 5 Jul 2018 18:49:23 +0000
Subject: [PATCH 02/18] ipv4: Return EINVAL when ping_group_range sysctl
 doesn't map to user ns

[ Upstream commit 70ba5b6db96ff7324b8cfc87e0d0383cf59c9677 ]

The low and high values of the net.ipv4.ping_group_range sysctl were
being silently forced to the default disabled state when a write to the
sysctl contained GIDs that didn't map to the associated user namespace.
Confusingly, the sysctl's write operation would return success and then
a subsequent read of the sysctl would indicate that the low and high
values are the overflowgid.

This patch changes the behavior by clearly returning an error when the
sysctl write operation receives a GID range that doesn't map to the
associated user namespace. In such a situation, the previous value of
the sysctl is preserved and that range will be returned in a subsequent
read of the sysctl.

Signed-off-by: Tyler Hicks <tyhicks@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/sysctl_net_ipv4.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 5a29dc5083a3..d82e8344fc54 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -186,8 +186,9 @@ static int ipv4_ping_group_range(struct ctl_table *table, int write,
 	if (write && ret == 0) {
 		low = make_kgid(user_ns, urange[0]);
 		high = make_kgid(user_ns, urange[1]);
-		if (!gid_valid(low) || !gid_valid(high) ||
-		    (urange[1] < urange[0]) || gid_lt(high, low)) {
+		if (!gid_valid(low) || !gid_valid(high))
+			return -EINVAL;
+		if (urange[1] < urange[0] || gid_lt(high, low)) {
 			low = make_kgid(&init_user_ns, 1);
 			high = make_kgid(&init_user_ns, 0);
 		}
-- 
2.17.1


From d698506c1de9e390efc5257e1b870123f8eb5563 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Tue, 17 Jul 2018 17:12:39 +0100
Subject: [PATCH 03/18] ipv6: fix useless rol32 call on hash

[ Upstream commit 169dc027fb02492ea37a0575db6a658cf922b854 ]

The rol32 call is currently rotating hash but the rol'd value is
being discarded. I believe the current code is incorrect and hash
should be assigned the rotated value returned from rol32.

Thanks to David Lebrun for spotting this.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index a54b8c58ccb7..e59f385da38e 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -795,7 +795,7 @@ static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb,
 	 * to minimize possbility that any useful information to an
 	 * attacker is leaked. Only lower 20 bits are relevant.
 	 */
-	rol32(hash, 16);
+	hash = rol32(hash, 16);
 
 	flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK;
 
-- 
2.17.1


From 99e09027159ef4fa6974e1d96825342955f88cf1 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 18 Jul 2018 10:48:56 +0200
Subject: [PATCH 04/18] ipv6: ila: select CONFIG_DST_CACHE

[ Upstream commit 83ed7d1fe2d2d4a11b30660dec20168bb473d9c1 ]

My randconfig builds came across an old missing dependency for ILA:

ERROR: "dst_cache_set_ip6" [net/ipv6/ila/ila.ko] undefined!
ERROR: "dst_cache_get" [net/ipv6/ila/ila.ko] undefined!
ERROR: "dst_cache_init" [net/ipv6/ila/ila.ko] undefined!
ERROR: "dst_cache_destroy" [net/ipv6/ila/ila.ko] undefined!

We almost never run into this by accident because randconfig builds
end up selecting DST_CACHE from some other tunnel protocol, and this
one appears to be the only one missing the explicit 'select'.

>From all I can tell, this problem first appeared in linux-4.9
when dst_cache support got added to ILA.

Fixes: 79ff2fc31e0f ("ila: Cache a route to translated address")
Cc: Tom Herbert <tom@herbertland.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index ea71e4b0ab7a..2d36fd097299 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -109,6 +109,7 @@ config IPV6_MIP6
 config IPV6_ILA
 	tristate "IPv6: Identifier Locator Addressing (ILA)"
 	depends on NETFILTER
+	select DST_CACHE
 	select LWTUNNEL
 	---help---
 	  Support for IPv6 Identifier Locator Addressing (ILA).
-- 
2.17.1


From 0bd35521f0182eb834c465b26c7796c0cafaa850 Mon Sep 17 00:00:00 2001
From: Davidlohr Bueso <dave@stgolabs.net>
Date: Mon, 16 Jul 2018 13:26:13 -0700
Subject: [PATCH 05/18] lib/rhashtable: consider param->min_size when setting
 initial table size

[ Upstream commit 107d01f5ba10f4162c38109496607eb197059064 ]

rhashtable_init() currently does not take into account the user-passed
min_size parameter unless param->nelem_hint is set as well. As such,
the default size (number of buckets) will always be HASH_DEFAULT_SIZE
even if the smallest allowed size is larger than that. Remediate this
by unconditionally calling into rounded_hashtable_size() and handling
things accordingly.

Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 lib/rhashtable.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index b734ce731a7a..39215c724fc7 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -878,8 +878,16 @@ EXPORT_SYMBOL_GPL(rhashtable_walk_stop);
 
 static size_t rounded_hashtable_size(const struct rhashtable_params *params)
 {
-	return max(roundup_pow_of_two(params->nelem_hint * 4 / 3),
-		   (unsigned long)params->min_size);
+	size_t retsize;
+
+	if (params->nelem_hint)
+		retsize = max(roundup_pow_of_two(params->nelem_hint * 4 / 3),
+			      (unsigned long)params->min_size);
+	else
+		retsize = max(HASH_DEFAULT_SIZE,
+			      (unsigned long)params->min_size);
+
+	return retsize;
 }
 
 static u32 rhashtable_jhash2(const void *key, u32 length, u32 seed)
@@ -936,8 +944,6 @@ int rhashtable_init(struct rhashtable *ht,
 	struct bucket_table *tbl;
 	size_t size;
 
-	size = HASH_DEFAULT_SIZE;
-
 	if ((!params->key_len && !params->obj_hashfn) ||
 	    (params->obj_hashfn && !params->obj_cmpfn))
 		return -EINVAL;
@@ -964,8 +970,7 @@ int rhashtable_init(struct rhashtable *ht,
 
 	ht->p.min_size = max_t(u16, ht->p.min_size, HASH_MIN_SIZE);
 
-	if (params->nelem_hint)
-		size = rounded_hashtable_size(&ht->p);
+	size = rounded_hashtable_size(&ht->p);
 
 	if (params->locks_mul)
 		ht->p.locks_mul = roundup_pow_of_two(params->locks_mul);
-- 
2.17.1


From 35af592de6645c8332a16858a9e60e36e995a864 Mon Sep 17 00:00:00 2001
From: Lorenzo Colitti <lorenzo@google.com>
Date: Sat, 7 Jul 2018 16:31:40 +0900
Subject: [PATCH 06/18] net: diag: Don't double-free TCP_NEW_SYN_RECV sockets
 in tcp_abort

[ Upstream commit acc2cf4e37174646a24cba42fa53c668b2338d4e ]

When tcp_diag_destroy closes a TCP_NEW_SYN_RECV socket, it first
frees it by calling inet_csk_reqsk_queue_drop_and_and_put in
tcp_abort, and then frees it again by calling sock_gen_put.

Since tcp_abort only has one caller, and all the other codepaths
in tcp_abort don't free the socket, just remove the free in that
function.

Cc: David Ahern <dsa@cumulusnetworks.com>
Tested: passes Android sock_diag_test.py, which exercises this codepath
Fixes: d7226c7a4dd1 ("net: diag: Fix refcnt leak in error path destroying socket")
Signed-off-by: Lorenzo Colitti <lorenzo@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsa@cumulusnetworks.com>
Tested-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e3ece12f0250..e81ff9d545a4 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3415,8 +3415,7 @@ int tcp_abort(struct sock *sk, int err)
 			struct request_sock *req = inet_reqsk(sk);
 
 			local_bh_disable();
-			inet_csk_reqsk_queue_drop_and_put(req->rsk_listener,
-							  req);
+			inet_csk_reqsk_queue_drop(req->rsk_listener, req);
 			local_bh_enable();
 			return 0;
 		}
-- 
2.17.1


From 613133de84dbe1febabbbc93ea0bc5d6e8a22faa Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Wed, 11 Jul 2018 14:39:42 +0200
Subject: [PATCH 07/18] net: Don't copy pfmemalloc flag in __copy_skb_header()

[ Upstream commit 8b7008620b8452728cadead460a36f64ed78c460 ]

The pfmemalloc flag indicates that the skb was allocated from
the PFMEMALLOC reserves, and the flag is currently copied on skb
copy and clone.

However, an skb copied from an skb flagged with pfmemalloc
wasn't necessarily allocated from PFMEMALLOC reserves, and on
the other hand an skb allocated that way might be copied from an
skb that wasn't.

So we should not copy the flag on skb copy, and rather decide
whether to allow an skb to be associated with sockets unrelated
to page reclaim depending only on how it was allocated.

Move the pfmemalloc flag before headers_start[0] using an
existing 1-bit hole, so that __copy_skb_header() doesn't copy
it.

When cloning, we'll now take care of this flag explicitly,
contravening to the warning comment of __skb_clone().

While at it, restore the newline usage introduced by commit
b19372273164 ("net: reorganize sk_buff for faster
__copy_skb_header()") to visually separate bytes used in
bitfields after headers_start[0], that was gone after commit
a9e419dc7be6 ("netfilter: merge ctinfo into nfct pointer storage
area"), and describe the pfmemalloc flag in the kernel-doc
structure comment.

This doesn't change the size of sk_buff or cacheline boundaries,
but consolidates the 15 bits hole before tc_index into a 2 bytes
hole before csum, that could now be filled more easily.

Reported-by: Patrick Talbert <ptalbert@redhat.com>
Fixes: c93bdd0e03e8 ("netvm: allow skb allocation to use PFMEMALLOC reserves")
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 10 +++++-----
 net/core/skbuff.c      |  2 ++
 2 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index be45224b01d7..9cf971c68401 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -624,6 +624,7 @@ typedef unsigned char *sk_buff_data_t;
  *	@hash: the packet hash
  *	@queue_mapping: Queue mapping for multiqueue devices
  *	@xmit_more: More SKBs are pending for this queue
+ *	@pfmemalloc: skbuff was allocated from PFMEMALLOC reserves
  *	@ndisc_nodetype: router type (from link layer)
  *	@ooo_okay: allow the mapping of a socket to a queue to be changed
  *	@l4_hash: indicate hash is a canonical 4-tuple hash over transport
@@ -722,7 +723,7 @@ struct sk_buff {
 				peeked:1,
 				head_frag:1,
 				xmit_more:1,
-				__unused:1; /* one bit hole */
+				pfmemalloc:1;
 
 	/* fields enclosed in headers_start/headers_end are copied
 	 * using a single memcpy() in __copy_skb_header()
@@ -741,31 +742,30 @@ struct sk_buff {
 
 	__u8			__pkt_type_offset[0];
 	__u8			pkt_type:3;
-	__u8			pfmemalloc:1;
 	__u8			ignore_df:1;
-
 	__u8			nf_trace:1;
 	__u8			ip_summed:2;
 	__u8			ooo_okay:1;
+
 	__u8			l4_hash:1;
 	__u8			sw_hash:1;
 	__u8			wifi_acked_valid:1;
 	__u8			wifi_acked:1;
-
 	__u8			no_fcs:1;
 	/* Indicates the inner headers are valid in the skbuff. */
 	__u8			encapsulation:1;
 	__u8			encap_hdr_csum:1;
 	__u8			csum_valid:1;
+
 	__u8			csum_complete_sw:1;
 	__u8			csum_level:2;
 	__u8			csum_not_inet:1;
-
 	__u8			dst_pending_confirm:1;
 #ifdef CONFIG_IPV6_NDISC_NODETYPE
 	__u8			ndisc_nodetype:2;
 #endif
 	__u8			ipvs_property:1;
+
 	__u8			inner_protocol_type:1;
 	__u8			remcsum_offload:1;
 #ifdef CONFIG_NET_SWITCHDEV
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index c132eca9e383..159518a80a46 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -858,6 +858,8 @@ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb)
 	n->cloned = 1;
 	n->nohdr = 0;
 	n->peeked = 0;
+	if (skb->pfmemalloc)
+		n->pfmemalloc = 1;
 	n->destructor = NULL;
 	C(tail);
 	C(end);
-- 
2.17.1


From 1c66468d896fe1a04f6d31a019f43115fad265fa Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Fri, 13 Jul 2018 13:21:07 +0200
Subject: [PATCH 08/18] skbuff: Unconditionally copy pfmemalloc in
 __skb_clone()

[ Upstream commit e78bfb0751d4e312699106ba7efbed2bab1a53ca ]

Commit 8b7008620b84 ("net: Don't copy pfmemalloc flag in
__copy_skb_header()") introduced a different handling for the
pfmemalloc flag in copy and clone paths.

In __skb_clone(), now, the flag is set only if it was set in the
original skb, but not cleared if it wasn't. This is wrong and
might lead to socket buffers being flagged with pfmemalloc even
if the skb data wasn't allocated from pfmemalloc reserves. Copy
the flag instead of ORing it.

Reported-by: Sabrina Dubroca <sd@queasysnail.net>
Fixes: 8b7008620b84 ("net: Don't copy pfmemalloc flag in __copy_skb_header()")
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Tested-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 159518a80a46..23041b5c0b27 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -858,8 +858,7 @@ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb)
 	n->cloned = 1;
 	n->nohdr = 0;
 	n->peeked = 0;
-	if (skb->pfmemalloc)
-		n->pfmemalloc = 1;
+	C(pfmemalloc);
 	n->destructor = NULL;
 	C(tail);
 	C(end);
-- 
2.17.1


From 9984611b58c09f977283241475399db5fdb5fe2b Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Sat, 7 Jul 2018 16:15:26 -0700
Subject: [PATCH 09/18] net/ipv4: Set oif in fib_compute_spec_dst

[ Upstream commit e7372197e15856ec4ee66b668020a662994db103 ]

Xin reported that icmp replies may not use the address on the device the
echo request is received if the destination address is broadcast. Instead
a route lookup is done without considering VRF context. Fix by setting
oif in flow struct to the master device if it is enslaved. That directs
the lookup to the VRF table. If the device is not enslaved, oif is still
0 so no affect.

Fixes: cd2fbe1b6b51 ("net: Use VRF device index for lookups on RX")
Reported-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_frontend.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index df8fd3ce713d..67eebcb113f3 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -290,6 +290,7 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb)
 	if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) {
 		struct flowi4 fl4 = {
 			.flowi4_iif = LOOPBACK_IFINDEX,
+			.flowi4_oif = l3mdev_master_ifindex_rcu(dev),
 			.daddr = ip_hdr(skb)->saddr,
 			.flowi4_tos = RT_TOS(ip_hdr(skb)->tos),
 			.flowi4_scope = scope,
-- 
2.17.1


From 63b33ff8277a2daf13052af5c9ae3aea87b47316 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Tue, 3 Jul 2018 22:34:54 +0200
Subject: [PATCH 10/18] net: phy: fix flag masking in __set_phy_supported

[ Upstream commit df8ed346d4a806a6eef2db5924285e839604b3f9 ]

Currently also the pause flags are removed from phydev->supported because
they're not included in PHY_DEFAULT_FEATURES. I don't think this is
intended, especially when considering that this function can be called
via phy_set_max_speed() anywhere in a driver. Change the masking to mask
out only the values we're going to change. In addition remove the
misleading comment, job of this small function is just to adjust the
supported and advertised speeds.

Fixes: f3a6bd393c2c ("phylib: Add phy_set_max_speed helper")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index a1e7ea4d4b16..a174d05a9752 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1686,11 +1686,8 @@ EXPORT_SYMBOL(genphy_loopback);
 
 static int __set_phy_supported(struct phy_device *phydev, u32 max_speed)
 {
-	/* The default values for phydev->supported are provided by the PHY
-	 * driver "features" member, we want to reset to sane defaults first
-	 * before supporting higher speeds.
-	 */
-	phydev->supported &= PHY_DEFAULT_FEATURES;
+	phydev->supported &= ~(PHY_1000BT_FEATURES | PHY_100BT_FEATURES |
+			       PHY_10BT_FEATURES);
 
 	switch (max_speed) {
 	default:
-- 
2.17.1


From 8ea3b5a3cd1c52591dcbda50c7038c68a5bac631 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 17 Jul 2018 20:17:33 -0500
Subject: [PATCH 11/18] ptp: fix missing break in switch

[ Upstream commit 9ba8376ce1e2cbf4ce44f7e4bee1d0648e10d594 ]

It seems that a *break* is missing in order to avoid falling through
to the default case. Otherwise, checking *chan* makes no sense.

Fixes: 72df7a7244c0 ("ptp: Allow reassigning calibration pin function")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/ptp/ptp_chardev.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c
index 58a97d420572..51364621f77c 100644
--- a/drivers/ptp/ptp_chardev.c
+++ b/drivers/ptp/ptp_chardev.c
@@ -89,6 +89,7 @@ int ptp_set_pinfunc(struct ptp_clock *ptp, unsigned int pin,
 	case PTP_PF_PHYSYNC:
 		if (chan != 0)
 			return -EINVAL;
+		break;
 	default:
 		return -EINVAL;
 	}
-- 
2.17.1


From dd9fe1ab1ce014d86cf7144a9e23e76138983fe8 Mon Sep 17 00:00:00 2001
From: Matevz Vucnik <vucnikm@gmail.com>
Date: Wed, 4 Jul 2018 18:12:48 +0200
Subject: [PATCH 12/18] qmi_wwan: add support for Quectel EG91
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 38cd58ed9c4e389799b507bcffe02a7a7a180b33 ]

This adds the USB id of LTE modem Quectel EG91. It requires the
same quirk as other Quectel modems to make it work.

Signed-off-by: Matevz Vucnik <vucnikm@gmail.com>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 0db500bf86d9..6d3811c869fd 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1252,6 +1252,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1e0e, 0x9001, 5)},	/* SIMCom 7230E */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0125, 4)},	/* Quectel EC25, EC20 R2.0  Mini PCIe */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0121, 4)},	/* Quectel EC21 Mini PCIe */
+	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0191, 4)},	/* Quectel EG91 */
 	{QMI_FIXED_INTF(0x2c7c, 0x0296, 4)},	/* Quectel BG96 */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0306, 4)},	/* Quectel EP06 Mini PCIe */
 
-- 
2.17.1


From ac4bd0b2519413d277db005e233c6b8cb99eea13 Mon Sep 17 00:00:00 2001
From: Sanjeev Bansal <sanjeevb.bansal@broadcom.com>
Date: Mon, 16 Jul 2018 11:13:32 +0530
Subject: [PATCH 13/18] tg3: Add higher cpu clock for 5762.

[ Upstream commit 3a498606bb04af603a46ebde8296040b2de350d1 ]

This patch has fix for TX timeout while running bi-directional
traffic with 100 Mbps using 5762.

Signed-off-by: Sanjeev Bansal <sanjeevb.bansal@broadcom.com>
Signed-off-by: Siva Reddy Kallam <siva.kallam@broadcom.com>
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/tg3.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 9a8ef630466f..1b1d2a67f412 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -9279,6 +9279,15 @@ static int tg3_chip_reset(struct tg3 *tp)
 
 	tg3_restore_clk(tp);
 
+	/* Increase the core clock speed to fix tx timeout issue for 5762
+	 * with 100Mbps link speed.
+	 */
+	if (tg3_asic_rev(tp) == ASIC_REV_5762) {
+		val = tr32(TG3_CPMU_CLCK_ORIDE_ENABLE);
+		tw32(TG3_CPMU_CLCK_ORIDE_ENABLE, val |
+		     TG3_CPMU_MAC_ORIDE_ENABLE);
+	}
+
 	/* Reprobe ASF enable state.  */
 	tg3_flag_clear(tp, ENABLE_ASF);
 	tp->phy_flags &= ~(TG3_PHYFLG_1G_ON_VAUX_OK |
-- 
2.17.1


From f64c567aaff41c0fe40693f682b9616d3b8a71e0 Mon Sep 17 00:00:00 2001
From: Haiyang Zhang <haiyangz@microsoft.com>
Date: Tue, 17 Jul 2018 17:11:13 +0000
Subject: [PATCH 14/18] hv_netvsc: Fix napi reschedule while receive completion
 is busy

[ Upstream commit 6b81b193b83e87da1ea13217d684b54fccf8ee8a ]

If out ring is full temporarily and receive completion cannot go out,
we may still need to reschedule napi if certain conditions are met.
Otherwise the napi poll might be stopped forever, and cause network
disconnect.

Fixes: 7426b1a51803 ("netvsc: optimize receive completions")
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/netvsc.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 701be5d81062..806239b89990 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -1250,6 +1250,7 @@ int netvsc_poll(struct napi_struct *napi, int budget)
 	struct hv_device *device = netvsc_channel_to_device(channel);
 	struct net_device *ndev = hv_get_drvdata(device);
 	int work_done = 0;
+	int ret;
 
 	/* If starting a new interval */
 	if (!nvchan->desc)
@@ -1261,16 +1262,18 @@ int netvsc_poll(struct napi_struct *napi, int budget)
 		nvchan->desc = hv_pkt_iter_next(channel, nvchan->desc);
 	}
 
-	/* If send of pending receive completions suceeded
-	 *   and did not exhaust NAPI budget this time
-	 *   and not doing busy poll
+	/* Send any pending receive completions */
+	ret = send_recv_completions(ndev, net_device, nvchan);
+
+	/* If it did not exhaust NAPI budget this time
+	 *  and not doing busy poll
 	 * then re-enable host interrupts
-	 *     and reschedule if ring is not empty.
+	 *  and reschedule if ring is not empty
+	 *   or sending receive completion failed.
 	 */
-	if (send_recv_completions(ndev, net_device, nvchan) == 0 &&
-	    work_done < budget &&
+	if (work_done < budget &&
 	    napi_complete_done(napi, work_done) &&
-	    hv_end_read(&channel->inbound) &&
+	    (ret || hv_end_read(&channel->inbound)) &&
 	    napi_schedule_prep(napi)) {
 		hv_begin_read(&channel->inbound);
 		__napi_schedule(napi);
-- 
2.17.1


From 7ebc55e74a3f0e787e73e7b24a386c8be7825c83 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Sun, 15 Jul 2018 13:54:39 +0300
Subject: [PATCH 15/18] net/mlx4_en: Don't reuse RX page when XDP is set

[ Upstream commit 432e629e56432064761be63bcd5e263c0920430d ]

When a new rx packet arrives, the rx path will decide whether to reuse
the remainder of the page or not according to one of the below conditions:
1. frag_info->frag_stride == PAGE_SIZE / 2
2. frags->page_offset + frag_info->frag_size > PAGE_SIZE;

The first condition is no met for when XDP is set.
For XDP, page_offset is always set to priv->rx_headroom which is
XDP_PACKET_HEADROOM and frag_info->frag_size is around mtu size + some
padding, still the 2nd release condition will hold since
XDP_PACKET_HEADROOM + 1536 < PAGE_SIZE, as a result the page will not
be released and will be _wrongly_ reused for next free rx descriptor.

In XDP there is an assumption to have a page per packet and reuse can
break such assumption and might cause packet data corruptions.

Fix this by adding an extra condition (!priv->rx_headroom) to the 2nd
case to avoid page reuse when XDP is set, since rx_headroom is set to 0
for non XDP setup and set to XDP_PACKET_HEADROOM for XDP setup.

No additional cache line is required for the new condition.

Fixes: 34db548bfb95 ("mlx4: add page recycling in receive path")
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Suggested-by: Martin KaFai Lau <kafai@fb.com>
CC: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_rx.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index b97a55c827eb..ab2a9dbb46c7 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -472,10 +472,10 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv,
 {
 	const struct mlx4_en_frag_info *frag_info = priv->frag_info;
 	unsigned int truesize = 0;
+	bool release = true;
 	int nr, frag_size;
 	struct page *page;
 	dma_addr_t dma;
-	bool release;
 
 	/* Collect used fragments while replacing them in the HW descriptors */
 	for (nr = 0;; frags++) {
@@ -498,7 +498,11 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv,
 			release = page_count(page) != 1 ||
 				  page_is_pfmemalloc(page) ||
 				  page_to_nid(page) != numa_mem_id();
-		} else {
+		} else if (!priv->rx_headroom) {
+			/* rx_headroom for non XDP setup is always 0.
+			 * When XDP is set, the above condition will
+			 * guarantee page is always released.
+			 */
 			u32 sz_align = ALIGN(frag_size, SMP_CACHE_BYTES);
 
 			frags->page_offset += sz_align;
-- 
2.17.1


From 75841f68a1c18c8908427c1b78e0264bee1bbf03 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 11 Jul 2018 02:47:58 -0700
Subject: [PATCH 16/18] net: systemport: Fix CRC forwarding check for
 SYSTEMPORT Lite

[ Upstream commit 9e3bff923913729d76d87f0015848ee7b8ff7083 ]

SYSTEMPORT Lite reversed the logic compared to SYSTEMPORT, the
GIB_FCS_STRIP bit is set when the Ethernet FCS is stripped, and that bit
is not set by default. Fix the logic such that we properly check whether
that bit is set or not and we don't forward an extra 4 bytes to the
network stack.

Fixes: 44a4524c54af ("net: systemport: Add support for SYSTEMPORT Lite")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bcmsysport.c | 4 ++--
 drivers/net/ethernet/broadcom/bcmsysport.h | 3 ++-
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 1e856e8b9a92..0fff2432ab4c 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -1851,8 +1851,8 @@ static int bcm_sysport_open(struct net_device *dev)
 	if (!priv->is_lite)
 		priv->crc_fwd = !!(umac_readl(priv, UMAC_CMD) & CMD_CRC_FWD);
 	else
-		priv->crc_fwd = !!(gib_readl(priv, GIB_CONTROL) &
-				   GIB_FCS_STRIP);
+		priv->crc_fwd = !((gib_readl(priv, GIB_CONTROL) &
+				  GIB_FCS_STRIP) >> GIB_FCS_STRIP_SHIFT);
 
 	phydev = of_phy_connect(dev, priv->phy_dn, bcm_sysport_adj_link,
 				0, priv->phy_interface);
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h
index a2006f5fc26f..86ae751ccb5c 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.h
+++ b/drivers/net/ethernet/broadcom/bcmsysport.h
@@ -277,7 +277,8 @@ struct bcm_rsb {
 #define  GIB_GTX_CLK_EXT_CLK		(0 << GIB_GTX_CLK_SEL_SHIFT)
 #define  GIB_GTX_CLK_125MHZ		(1 << GIB_GTX_CLK_SEL_SHIFT)
 #define  GIB_GTX_CLK_250MHZ		(2 << GIB_GTX_CLK_SEL_SHIFT)
-#define  GIB_FCS_STRIP			(1 << 6)
+#define  GIB_FCS_STRIP_SHIFT		6
+#define  GIB_FCS_STRIP			(1 << GIB_FCS_STRIP_SHIFT)
 #define  GIB_LCL_LOOP_EN		(1 << 7)
 #define  GIB_LCL_LOOP_TXEN		(1 << 8)
 #define  GIB_RMT_LOOP_EN		(1 << 9)
-- 
2.17.1


From 08b81bc24b49895c5df7012e18f2a8c6ed567d3f Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 13 Jul 2018 17:21:42 +0200
Subject: [PATCH 17/18] ipv6: make DAD fail with enhanced DAD when nonce length
 differs

[ Upstream commit e66515999b627368892ccc9b3a13a506f2ea1357 ]

Commit adc176c54722 ("ipv6 addrconf: Implemented enhanced DAD (RFC7527)")
added enhanced DAD with a nonce length of 6 bytes. However, RFC7527
doesn't specify the length of the nonce, other than being 6 + 8*k bytes,
with integer k >= 0 (RFC3971 5.3.2). The current implementation simply
assumes that the nonce will always be 6 bytes, but others systems are
free to choose different sizes.

If another system sends a nonce of different length but with the same 6
bytes prefix, it shouldn't be considered as the same nonce. Thus, check
that the length of the received nonce is the same as the length we sent.

Ugly scapy test script running on veth0:

def loop():
    pkt=sniff(iface="veth0", filter="icmp6", count=1)
    pkt = pkt[0]
    b = bytearray(pkt[Raw].load)
    b[1] += 1
    b += b'\xde\xad\xbe\xef\xde\xad\xbe\xef'
    pkt[Raw].load = bytes(b)
    pkt[IPv6].plen += 8
    # fixup checksum after modifying the payload
    pkt[IPv6].payload.cksum -= 0x3b44
    if pkt[IPv6].payload.cksum < 0:
        pkt[IPv6].payload.cksum += 0xffff
    sendp(pkt, iface="veth0")

This should result in DAD failure for any address added to veth0's peer,
but is currently ignored.

Fixes: adc176c54722 ("ipv6 addrconf: Implemented enhanced DAD (RFC7527)")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ndisc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index d081db125905..528218460bc5 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -803,7 +803,7 @@ static void ndisc_recv_ns(struct sk_buff *skb)
 			return;
 		}
 	}
-	if (ndopts.nd_opts_nonce)
+	if (ndopts.nd_opts_nonce && ndopts.nd_opts_nonce->nd_opt_len == 1)
 		memcpy(&nonce, (u8 *)(ndopts.nd_opts_nonce + 1), 6);
 
 	inc = ipv6_addr_is_multicast(daddr);
-- 
2.17.1


From 8afee6918d1da02587b18f0e8cf453101dacb11e Mon Sep 17 00:00:00 2001
From: Alexander Couzens <lynxis@fe80.eu>
Date: Tue, 17 Jul 2018 13:17:09 +0200
Subject: [PATCH 18/18] net: usb: asix: replace mii_nway_restart in resume path

[ Upstream commit 5c968f48021a9b3faa61ac2543cfab32461c0e05 ]

mii_nway_restart is not pm aware which results in a rtnl deadlock.
Implement mii_nway_restart manual by setting BMCR_ANRESTART if
BMCR_ANENABLE is set.

To reproduce:
* plug an asix based usb network interface
* wait until the device enters PM (~5 sec)
* `ip link set eth1 up` will never return

Fixes: d9fe64e51114 ("net: asix: Add in_pm parameter")
Signed-off-by: Alexander Couzens <lynxis@fe80.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/asix_devices.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c
index 3d4f7959dabb..b1b3d8f7e67d 100644
--- a/drivers/net/usb/asix_devices.c
+++ b/drivers/net/usb/asix_devices.c
@@ -642,10 +642,12 @@ static void ax88772_restore_phy(struct usbnet *dev)
 				     priv->presvd_phy_advertise);
 
 		/* Restore BMCR */
+		if (priv->presvd_phy_bmcr & BMCR_ANENABLE)
+			priv->presvd_phy_bmcr |= BMCR_ANRESTART;
+
 		asix_mdio_write_nopm(dev->net, dev->mii.phy_id, MII_BMCR,
 				     priv->presvd_phy_bmcr);
 
-		mii_nway_restart(&dev->mii);
 		priv->presvd_phy_advertise = 0;
 		priv->presvd_phy_bmcr = 0;
 	}
-- 
2.17.1


[-- Attachment #3: net_417.mbox --]
[-- Type: Application/Octet-Stream, Size: 63061 bytes --]

From 8c1311644477440e8fdb83746a573d827bfcd547 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@toke.dk>
Date: Mon, 2 Jul 2018 22:52:20 +0200
Subject: [PATCH 01/25] gen_stats: Fix netlink stats dumping in the presence of
 padding
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit d5a672ac9f48f81b20b1cad1d9ed7bbf4e418d4c ]

The gen_stats facility will add a header for the toplevel nlattr of type
TCA_STATS2 that contains all stats added by qdisc callbacks. A reference
to this header is stored in the gnet_dump struct, and when all the
per-qdisc callbacks have finished adding their stats, the length of the
containing header will be adjusted to the right value.

However, on architectures that need padding (i.e., that don't set
CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS), the padding nlattr is added
before the stats, which means that the stored pointer will point to the
padding, and so when the header is fixed up, the result is just a very
big padding nlattr. Because most qdiscs also supply the legacy TCA_STATS
struct, this problem has been mostly invisible, but we exposed it with
the netlink attribute-based statistics in CAKE.

Fix the issue by fixing up the stored pointer if it points to a padding
nlattr.

Tested-by: Pete Heist <pete@heistp.net>
Tested-by: Kevin Darbyshire-Bryant <kevin@darbyshire-bryant.me.uk>
Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/gen_stats.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c
index b2b2323bdc84..188d693cb251 100644
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -77,8 +77,20 @@ gnet_stats_start_copy_compat(struct sk_buff *skb, int type, int tc_stats_type,
 		d->lock = lock;
 		spin_lock_bh(lock);
 	}
-	if (d->tail)
-		return gnet_stats_copy(d, type, NULL, 0, padattr);
+	if (d->tail) {
+		int ret = gnet_stats_copy(d, type, NULL, 0, padattr);
+
+		/* The initial attribute added in gnet_stats_copy() may be
+		 * preceded by a padding attribute, in which case d->tail will
+		 * end up pointing at the padding instead of the real attribute.
+		 * Fix this so gnet_stats_finish_copy() adjusts the length of
+		 * the right attribute.
+		 */
+		if (ret == 0 && d->tail->nla_type == padattr)
+			d->tail = (struct nlattr *)((char *)d->tail +
+						    NLA_ALIGN(d->tail->nla_len));
+		return ret;
+	}
 
 	return 0;
 }
-- 
2.17.1


From a6797d6fdb19f80510756da2526c6cb83f4c6af0 Mon Sep 17 00:00:00 2001
From: Tyler Hicks <tyhicks@canonical.com>
Date: Thu, 5 Jul 2018 18:49:23 +0000
Subject: [PATCH 02/25] ipv4: Return EINVAL when ping_group_range sysctl
 doesn't map to user ns

[ Upstream commit 70ba5b6db96ff7324b8cfc87e0d0383cf59c9677 ]

The low and high values of the net.ipv4.ping_group_range sysctl were
being silently forced to the default disabled state when a write to the
sysctl contained GIDs that didn't map to the associated user namespace.
Confusingly, the sysctl's write operation would return success and then
a subsequent read of the sysctl would indicate that the low and high
values are the overflowgid.

This patch changes the behavior by clearly returning an error when the
sysctl write operation receives a GID range that doesn't map to the
associated user namespace. In such a situation, the previous value of
the sysctl is preserved and that range will be returned in a subsequent
read of the sysctl.

Signed-off-by: Tyler Hicks <tyhicks@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/sysctl_net_ipv4.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 2f600f261690..61e42a3390ba 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -187,8 +187,9 @@ static int ipv4_ping_group_range(struct ctl_table *table, int write,
 	if (write && ret == 0) {
 		low = make_kgid(user_ns, urange[0]);
 		high = make_kgid(user_ns, urange[1]);
-		if (!gid_valid(low) || !gid_valid(high) ||
-		    (urange[1] < urange[0]) || gid_lt(high, low)) {
+		if (!gid_valid(low) || !gid_valid(high))
+			return -EINVAL;
+		if (urange[1] < urange[0] || gid_lt(high, low)) {
 			low = make_kgid(&init_user_ns, 1);
 			high = make_kgid(&init_user_ns, 0);
 		}
-- 
2.17.1


From 107dc56ecdf179b8415bf886ff14828fd7bdae8d Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Tue, 17 Jul 2018 17:12:39 +0100
Subject: [PATCH 03/25] ipv6: fix useless rol32 call on hash

[ Upstream commit 169dc027fb02492ea37a0575db6a658cf922b854 ]

The rol32 call is currently rotating hash but the rol'd value is
being discarded. I believe the current code is incorrect and hash
should be assigned the rotated value returned from rol32.

Thanks to David Lebrun for spotting this.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index a406f2e8680a..aeebbbb9e0bd 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -829,7 +829,7 @@ static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb,
 	 * to minimize possbility that any useful information to an
 	 * attacker is leaked. Only lower 20 bits are relevant.
 	 */
-	rol32(hash, 16);
+	hash = rol32(hash, 16);
 
 	flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK;
 
-- 
2.17.1


From 73fc6d2dded8155bdd59efd30b05c107cfa18bf5 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 18 Jul 2018 10:48:56 +0200
Subject: [PATCH 04/25] ipv6: ila: select CONFIG_DST_CACHE

[ Upstream commit 83ed7d1fe2d2d4a11b30660dec20168bb473d9c1 ]

My randconfig builds came across an old missing dependency for ILA:

ERROR: "dst_cache_set_ip6" [net/ipv6/ila/ila.ko] undefined!
ERROR: "dst_cache_get" [net/ipv6/ila/ila.ko] undefined!
ERROR: "dst_cache_init" [net/ipv6/ila/ila.ko] undefined!
ERROR: "dst_cache_destroy" [net/ipv6/ila/ila.ko] undefined!

We almost never run into this by accident because randconfig builds
end up selecting DST_CACHE from some other tunnel protocol, and this
one appears to be the only one missing the explicit 'select'.

>From all I can tell, this problem first appeared in linux-4.9
when dst_cache support got added to ILA.

Fixes: 79ff2fc31e0f ("ila: Cache a route to translated address")
Cc: Tom Herbert <tom@herbertland.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index 11e4e80cf7e9..0efb914695ac 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -108,6 +108,7 @@ config IPV6_MIP6
 config IPV6_ILA
 	tristate "IPv6: Identifier Locator Addressing (ILA)"
 	depends on NETFILTER
+	select DST_CACHE
 	select LWTUNNEL
 	---help---
 	  Support for IPv6 Identifier Locator Addressing (ILA).
-- 
2.17.1


From b7b3e9e21fb1583ade2aa4df65af2e54f0843698 Mon Sep 17 00:00:00 2001
From: Davidlohr Bueso <dave@stgolabs.net>
Date: Mon, 16 Jul 2018 13:26:13 -0700
Subject: [PATCH 05/25] lib/rhashtable: consider param->min_size when setting
 initial table size

[ Upstream commit 107d01f5ba10f4162c38109496607eb197059064 ]

rhashtable_init() currently does not take into account the user-passed
min_size parameter unless param->nelem_hint is set as well. As such,
the default size (number of buckets) will always be HASH_DEFAULT_SIZE
even if the smallest allowed size is larger than that. Remediate this
by unconditionally calling into rounded_hashtable_size() and handling
things accordingly.

Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 lib/rhashtable.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 2b2b79974b61..11e89c3b76e3 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -923,8 +923,16 @@ EXPORT_SYMBOL_GPL(rhashtable_walk_stop);
 
 static size_t rounded_hashtable_size(const struct rhashtable_params *params)
 {
-	return max(roundup_pow_of_two(params->nelem_hint * 4 / 3),
-		   (unsigned long)params->min_size);
+	size_t retsize;
+
+	if (params->nelem_hint)
+		retsize = max(roundup_pow_of_two(params->nelem_hint * 4 / 3),
+			      (unsigned long)params->min_size);
+	else
+		retsize = max(HASH_DEFAULT_SIZE,
+			      (unsigned long)params->min_size);
+
+	return retsize;
 }
 
 static u32 rhashtable_jhash2(const void *key, u32 length, u32 seed)
@@ -981,8 +989,6 @@ int rhashtable_init(struct rhashtable *ht,
 	struct bucket_table *tbl;
 	size_t size;
 
-	size = HASH_DEFAULT_SIZE;
-
 	if ((!params->key_len && !params->obj_hashfn) ||
 	    (params->obj_hashfn && !params->obj_cmpfn))
 		return -EINVAL;
@@ -1009,8 +1015,7 @@ int rhashtable_init(struct rhashtable *ht,
 
 	ht->p.min_size = max_t(u16, ht->p.min_size, HASH_MIN_SIZE);
 
-	if (params->nelem_hint)
-		size = rounded_hashtable_size(&ht->p);
+	size = rounded_hashtable_size(&ht->p);
 
 	if (params->locks_mul)
 		ht->p.locks_mul = roundup_pow_of_two(params->locks_mul);
-- 
2.17.1


From 8b9f828ada76a338332a7b3ebc692357c3d42b8f Mon Sep 17 00:00:00 2001
From: Lorenzo Colitti <lorenzo@google.com>
Date: Sat, 7 Jul 2018 16:31:40 +0900
Subject: [PATCH 06/25] net: diag: Don't double-free TCP_NEW_SYN_RECV sockets
 in tcp_abort

[ Upstream commit acc2cf4e37174646a24cba42fa53c668b2338d4e ]

When tcp_diag_destroy closes a TCP_NEW_SYN_RECV socket, it first
frees it by calling inet_csk_reqsk_queue_drop_and_and_put in
tcp_abort, and then frees it again by calling sock_gen_put.

Since tcp_abort only has one caller, and all the other codepaths
in tcp_abort don't free the socket, just remove the free in that
function.

Cc: David Ahern <dsa@cumulusnetworks.com>
Tested: passes Android sock_diag_test.py, which exercises this codepath
Fixes: d7226c7a4dd1 ("net: diag: Fix refcnt leak in error path destroying socket")
Signed-off-by: Lorenzo Colitti <lorenzo@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsa@cumulusnetworks.com>
Tested-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index c9d00ef54dec..58e316cf6607 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3524,8 +3524,7 @@ int tcp_abort(struct sock *sk, int err)
 			struct request_sock *req = inet_reqsk(sk);
 
 			local_bh_disable();
-			inet_csk_reqsk_queue_drop_and_put(req->rsk_listener,
-							  req);
+			inet_csk_reqsk_queue_drop(req->rsk_listener, req);
 			local_bh_enable();
 			return 0;
 		}
-- 
2.17.1


From 8ee8b73590e534fb2f16ae4957b07e3fd0e40771 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Wed, 11 Jul 2018 14:39:42 +0200
Subject: [PATCH 07/25] net: Don't copy pfmemalloc flag in __copy_skb_header()

[ Upstream commit 8b7008620b8452728cadead460a36f64ed78c460 ]

The pfmemalloc flag indicates that the skb was allocated from
the PFMEMALLOC reserves, and the flag is currently copied on skb
copy and clone.

However, an skb copied from an skb flagged with pfmemalloc
wasn't necessarily allocated from PFMEMALLOC reserves, and on
the other hand an skb allocated that way might be copied from an
skb that wasn't.

So we should not copy the flag on skb copy, and rather decide
whether to allow an skb to be associated with sockets unrelated
to page reclaim depending only on how it was allocated.

Move the pfmemalloc flag before headers_start[0] using an
existing 1-bit hole, so that __copy_skb_header() doesn't copy
it.

When cloning, we'll now take care of this flag explicitly,
contravening to the warning comment of __skb_clone().

While at it, restore the newline usage introduced by commit
b19372273164 ("net: reorganize sk_buff for faster
__copy_skb_header()") to visually separate bytes used in
bitfields after headers_start[0], that was gone after commit
a9e419dc7be6 ("netfilter: merge ctinfo into nfct pointer storage
area"), and describe the pfmemalloc flag in the kernel-doc
structure comment.

This doesn't change the size of sk_buff or cacheline boundaries,
but consolidates the 15 bits hole before tc_index into a 2 bytes
hole before csum, that could now be filled more easily.

Reported-by: Patrick Talbert <ptalbert@redhat.com>
Fixes: c93bdd0e03e8 ("netvm: allow skb allocation to use PFMEMALLOC reserves")
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 10 +++++-----
 net/core/skbuff.c      |  2 ++
 2 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 9065477ed255..15d8f9c84ca5 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -628,6 +628,7 @@ typedef unsigned char *sk_buff_data_t;
  *	@hash: the packet hash
  *	@queue_mapping: Queue mapping for multiqueue devices
  *	@xmit_more: More SKBs are pending for this queue
+ *	@pfmemalloc: skbuff was allocated from PFMEMALLOC reserves
  *	@ndisc_nodetype: router type (from link layer)
  *	@ooo_okay: allow the mapping of a socket to a queue to be changed
  *	@l4_hash: indicate hash is a canonical 4-tuple hash over transport
@@ -733,7 +734,7 @@ struct sk_buff {
 				peeked:1,
 				head_frag:1,
 				xmit_more:1,
-				__unused:1; /* one bit hole */
+				pfmemalloc:1;
 
 	/* fields enclosed in headers_start/headers_end are copied
 	 * using a single memcpy() in __copy_skb_header()
@@ -752,31 +753,30 @@ struct sk_buff {
 
 	__u8			__pkt_type_offset[0];
 	__u8			pkt_type:3;
-	__u8			pfmemalloc:1;
 	__u8			ignore_df:1;
-
 	__u8			nf_trace:1;
 	__u8			ip_summed:2;
 	__u8			ooo_okay:1;
+
 	__u8			l4_hash:1;
 	__u8			sw_hash:1;
 	__u8			wifi_acked_valid:1;
 	__u8			wifi_acked:1;
-
 	__u8			no_fcs:1;
 	/* Indicates the inner headers are valid in the skbuff. */
 	__u8			encapsulation:1;
 	__u8			encap_hdr_csum:1;
 	__u8			csum_valid:1;
+
 	__u8			csum_complete_sw:1;
 	__u8			csum_level:2;
 	__u8			csum_not_inet:1;
-
 	__u8			dst_pending_confirm:1;
 #ifdef CONFIG_IPV6_NDISC_NODETYPE
 	__u8			ndisc_nodetype:2;
 #endif
 	__u8			ipvs_property:1;
+
 	__u8			inner_protocol_type:1;
 	__u8			remcsum_offload:1;
 #ifdef CONFIG_NET_SWITCHDEV
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 345b51837ca8..b4ac43418e79 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -858,6 +858,8 @@ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb)
 	n->cloned = 1;
 	n->nohdr = 0;
 	n->peeked = 0;
+	if (skb->pfmemalloc)
+		n->pfmemalloc = 1;
 	n->destructor = NULL;
 	C(tail);
 	C(end);
-- 
2.17.1


From 00551db68521078767cc4df2915f67038ac62ecd Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Fri, 13 Jul 2018 13:21:07 +0200
Subject: [PATCH 08/25] skbuff: Unconditionally copy pfmemalloc in
 __skb_clone()

[ Upstream commit e78bfb0751d4e312699106ba7efbed2bab1a53ca ]

Commit 8b7008620b84 ("net: Don't copy pfmemalloc flag in
__copy_skb_header()") introduced a different handling for the
pfmemalloc flag in copy and clone paths.

In __skb_clone(), now, the flag is set only if it was set in the
original skb, but not cleared if it wasn't. This is wrong and
might lead to socket buffers being flagged with pfmemalloc even
if the skb data wasn't allocated from pfmemalloc reserves. Copy
the flag instead of ORing it.

Reported-by: Sabrina Dubroca <sd@queasysnail.net>
Fixes: 8b7008620b84 ("net: Don't copy pfmemalloc flag in __copy_skb_header()")
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Tested-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index b4ac43418e79..a84d69c047ac 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -858,8 +858,7 @@ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb)
 	n->cloned = 1;
 	n->nohdr = 0;
 	n->peeked = 0;
-	if (skb->pfmemalloc)
-		n->pfmemalloc = 1;
+	C(pfmemalloc);
 	n->destructor = NULL;
 	C(tail);
 	C(end);
-- 
2.17.1


From 3e87c54082ac1a5a97be2892ff34412404b78cee Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Sat, 7 Jul 2018 16:15:26 -0700
Subject: [PATCH 09/25] net/ipv4: Set oif in fib_compute_spec_dst

[ Upstream commit e7372197e15856ec4ee66b668020a662994db103 ]

Xin reported that icmp replies may not use the address on the device the
echo request is received if the destination address is broadcast. Instead
a route lookup is done without considering VRF context. Fix by setting
oif in flow struct to the master device if it is enslaved. That directs
the lookup to the VRF table. If the device is not enslaved, oif is still
0 so no affect.

Fixes: cd2fbe1b6b51 ("net: Use VRF device index for lookups on RX")
Reported-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_frontend.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index e66172aaf241..511d6748ea5f 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -300,6 +300,7 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb)
 	if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) {
 		struct flowi4 fl4 = {
 			.flowi4_iif = LOOPBACK_IFINDEX,
+			.flowi4_oif = l3mdev_master_ifindex_rcu(dev),
 			.daddr = ip_hdr(skb)->saddr,
 			.flowi4_tos = RT_TOS(ip_hdr(skb)->tos),
 			.flowi4_scope = scope,
-- 
2.17.1


From ca9f5eafb5b216e21cebb9365285b6f0d631cc84 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Sun, 15 Jul 2018 09:35:19 -0700
Subject: [PATCH 10/25] net/ipv6: Do not allow device only routes via the
 multipath API

[ Upstream commit b5d2d75e079a918be686957b1a8d2f6c5cc95a0a ]

Eric reported that reverting the patch that fixed and simplified IPv6
multipath routes means reverting back to invalid userspace notifications.
eg.,
$ ip -6 route add 2001:db8:1::/64 nexthop dev eth0 nexthop dev eth1

only generates a single notification:
2001:db8:1::/64 dev eth0 metric 1024 pref medium

While working on a fix for this problem I found another case that is just
broken completely - a multipath route with a gateway followed by device
followed by gateway:
    $ ip -6 ro add 2001:db8:103::/64
          nexthop via 2001:db8:1::64
          nexthop dev dummy2
          nexthop via 2001:db8:3::64

In this case the device only route is dropped completely - no notification
to userpsace but no addition to the FIB either:

$ ip -6 ro ls
2001:db8:1::/64 dev dummy1 proto kernel metric 256 pref medium
2001:db8:2::/64 dev dummy2 proto kernel metric 256 pref medium
2001:db8:3::/64 dev dummy3 proto kernel metric 256 pref medium
2001:db8:103::/64 metric 1024
	nexthop via 2001:db8:1::64 dev dummy1 weight 1
	nexthop via 2001:db8:3::64 dev dummy3 weight 1 pref medium
fe80::/64 dev dummy1 proto kernel metric 256 pref medium
fe80::/64 dev dummy2 proto kernel metric 256 pref medium
fe80::/64 dev dummy3 proto kernel metric 256 pref medium

Really, IPv6 multipath is just FUBAR'ed beyond repair when it comes to
device only routes, so do not allow it all.

This change will break any scripts relying on the mpath api for insert,
but I don't see any other way to handle the permutations. Besides, since
the routes are added to the FIB as standalone (non-multipath) routes the
kernel is not doing what the user requested, so it might as well tell the
user that.

Reported-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index b94345e657f7..3ed4de230830 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -4274,6 +4274,13 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 			err_nh = nh;
 			goto add_errout;
 		}
+		if (!rt6_qualify_for_ecmp(rt)) {
+			err = -EINVAL;
+			NL_SET_ERR_MSG(extack,
+				       "Device only routes can not be added for IPv6 using the multipath API.");
+			dst_release_immediate(&rt->dst);
+			goto cleanup;
+		}
 
 		/* Because each route is added like a single route we remove
 		 * these flags after the first nexthop: if there is a collision,
-- 
2.17.1


From 52649dbfa04620e2c818b23d3af644ea7eae9f86 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Tue, 3 Jul 2018 22:34:54 +0200
Subject: [PATCH 11/25] net: phy: fix flag masking in __set_phy_supported

[ Upstream commit df8ed346d4a806a6eef2db5924285e839604b3f9 ]

Currently also the pause flags are removed from phydev->supported because
they're not included in PHY_DEFAULT_FEATURES. I don't think this is
intended, especially when considering that this function can be called
via phy_set_max_speed() anywhere in a driver. Change the masking to mask
out only the values we're going to change. In addition remove the
misleading comment, job of this small function is just to adjust the
supported and advertised speeds.

Fixes: f3a6bd393c2c ("phylib: Add phy_set_max_speed helper")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 9e4ba8e80a18..5aa081fda447 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1720,11 +1720,8 @@ EXPORT_SYMBOL(genphy_loopback);
 
 static int __set_phy_supported(struct phy_device *phydev, u32 max_speed)
 {
-	/* The default values for phydev->supported are provided by the PHY
-	 * driver "features" member, we want to reset to sane defaults first
-	 * before supporting higher speeds.
-	 */
-	phydev->supported &= PHY_DEFAULT_FEATURES;
+	phydev->supported &= ~(PHY_1000BT_FEATURES | PHY_100BT_FEATURES |
+			       PHY_10BT_FEATURES);
 
 	switch (max_speed) {
 	default:
-- 
2.17.1


From 7f6c0b651b8c3e607785797523fb7f828d70f5a0 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 17 Jul 2018 20:17:33 -0500
Subject: [PATCH 12/25] ptp: fix missing break in switch

[ Upstream commit 9ba8376ce1e2cbf4ce44f7e4bee1d0648e10d594 ]

It seems that a *break* is missing in order to avoid falling through
to the default case. Otherwise, checking *chan* makes no sense.

Fixes: 72df7a7244c0 ("ptp: Allow reassigning calibration pin function")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/ptp/ptp_chardev.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c
index 767c485af59b..522719b494f3 100644
--- a/drivers/ptp/ptp_chardev.c
+++ b/drivers/ptp/ptp_chardev.c
@@ -89,6 +89,7 @@ int ptp_set_pinfunc(struct ptp_clock *ptp, unsigned int pin,
 	case PTP_PF_PHYSYNC:
 		if (chan != 0)
 			return -EINVAL;
+		break;
 	default:
 		return -EINVAL;
 	}
-- 
2.17.1


From fd12cb071b02d5d91ee8a2bd3b105fab3e042af4 Mon Sep 17 00:00:00 2001
From: Matevz Vucnik <vucnikm@gmail.com>
Date: Wed, 4 Jul 2018 18:12:48 +0200
Subject: [PATCH 13/25] qmi_wwan: add support for Quectel EG91
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 38cd58ed9c4e389799b507bcffe02a7a7a180b33 ]

This adds the USB id of LTE modem Quectel EG91. It requires the
same quirk as other Quectel modems to make it work.

Signed-off-by: Matevz Vucnik <vucnikm@gmail.com>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 04c22f508ed9..f8f90d77cf0f 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1253,6 +1253,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1e0e, 0x9001, 5)},	/* SIMCom 7230E */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0125, 4)},	/* Quectel EC25, EC20 R2.0  Mini PCIe */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0121, 4)},	/* Quectel EC21 Mini PCIe */
+	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0191, 4)},	/* Quectel EG91 */
 	{QMI_FIXED_INTF(0x2c7c, 0x0296, 4)},	/* Quectel BG96 */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0306, 4)},	/* Quectel EP06 Mini PCIe */
 
-- 
2.17.1


From 54a178ffa7de135718d2a78a522ccc45a7afade5 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Sun, 8 Jul 2018 11:55:51 +0900
Subject: [PATCH 14/25] rhashtable: add restart routine in
 rhashtable_free_and_destroy()

[ Upstream commit 0026129c8629265bfe5079c1e017fa8543796d9f ]

rhashtable_free_and_destroy() cancels re-hash deferred work
then walks and destroys elements. at this moment, some elements can be
still in future_tbl. that elements are not destroyed.

test case:
nft_rhash_destroy() calls rhashtable_free_and_destroy() to destroy
all elements of sets before destroying sets and chains.
But rhashtable_free_and_destroy() doesn't destroy elements of future_tbl.
so that splat occurred.

test script:
   %cat test.nft
   table ip aa {
	   map map1 {
		   type ipv4_addr : verdict;
		   elements = {
			   0 : jump a0,
			   1 : jump a0,
			   2 : jump a0,
			   3 : jump a0,
			   4 : jump a0,
			   5 : jump a0,
			   6 : jump a0,
			   7 : jump a0,
			   8 : jump a0,
			   9 : jump a0,
		}
	   }
	   chain a0 {
	   }
   }
   flush ruleset
   table ip aa {
	   map map1 {
		   type ipv4_addr : verdict;
		   elements = {
			   0 : jump a0,
			   1 : jump a0,
			   2 : jump a0,
			   3 : jump a0,
			   4 : jump a0,
			   5 : jump a0,
			   6 : jump a0,
			   7 : jump a0,
			   8 : jump a0,
			   9 : jump a0,
		   }
	   }
	   chain a0 {
	   }
   }
   flush ruleset

   %while :; do nft -f test.nft; done

Splat looks like:
[  200.795603] kernel BUG at net/netfilter/nf_tables_api.c:1363!
[  200.806944] invalid opcode: 0000 [#1] SMP DEBUG_PAGEALLOC KASAN PTI
[  200.812253] CPU: 1 PID: 1582 Comm: nft Not tainted 4.17.0+ #24
[  200.820297] Hardware name: To be filled by O.E.M. To be filled by O.E.M./Aptio CRB, BIOS 5.6.5 07/08/2015
[  200.830309] RIP: 0010:nf_tables_chain_destroy.isra.34+0x62/0x240 [nf_tables]
[  200.838317] Code: 43 50 85 c0 74 26 48 8b 45 00 48 8b 4d 08 ba 54 05 00 00 48 c7 c6 60 6d 29 c0 48 c7 c7 c0 65 29 c0 4c 8b 40 08 e8 58 e5 fd f8 <0f> 0b 48 89 da 48 b8 00 00 00 00 00 fc ff
[  200.860366] RSP: 0000:ffff880118dbf4d0 EFLAGS: 00010282
[  200.866354] RAX: 0000000000000061 RBX: ffff88010cdeaf08 RCX: 0000000000000000
[  200.874355] RDX: 0000000000000061 RSI: 0000000000000008 RDI: ffffed00231b7e90
[  200.882361] RBP: ffff880118dbf4e8 R08: ffffed002373bcfb R09: ffffed002373bcfa
[  200.890354] R10: 0000000000000000 R11: ffffed002373bcfb R12: dead000000000200
[  200.898356] R13: dead000000000100 R14: ffffffffbb62af38 R15: dffffc0000000000
[  200.906354] FS:  00007fefc31fd700(0000) GS:ffff88011b800000(0000) knlGS:0000000000000000
[  200.915533] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  200.922355] CR2: 0000557f1c8e9128 CR3: 0000000106880000 CR4: 00000000001006e0
[  200.930353] Call Trace:
[  200.932351]  ? nf_tables_commit+0x26f6/0x2c60 [nf_tables]
[  200.939525]  ? nf_tables_setelem_notify.constprop.49+0x1a0/0x1a0 [nf_tables]
[  200.947525]  ? nf_tables_delchain+0x6e0/0x6e0 [nf_tables]
[  200.952383]  ? nft_add_set_elem+0x1700/0x1700 [nf_tables]
[  200.959532]  ? nla_parse+0xab/0x230
[  200.963529]  ? nfnetlink_rcv_batch+0xd06/0x10d0 [nfnetlink]
[  200.968384]  ? nfnetlink_net_init+0x130/0x130 [nfnetlink]
[  200.975525]  ? debug_show_all_locks+0x290/0x290
[  200.980363]  ? debug_show_all_locks+0x290/0x290
[  200.986356]  ? sched_clock_cpu+0x132/0x170
[  200.990352]  ? find_held_lock+0x39/0x1b0
[  200.994355]  ? sched_clock_local+0x10d/0x130
[  200.999531]  ? memset+0x1f/0x40

V2:
 - free all tables requested by Herbert Xu

Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 lib/rhashtable.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 11e89c3b76e3..240a8b864d5b 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -1107,13 +1107,14 @@ void rhashtable_free_and_destroy(struct rhashtable *ht,
 				 void (*free_fn)(void *ptr, void *arg),
 				 void *arg)
 {
-	struct bucket_table *tbl;
+	struct bucket_table *tbl, *next_tbl;
 	unsigned int i;
 
 	cancel_work_sync(&ht->run_work);
 
 	mutex_lock(&ht->mutex);
 	tbl = rht_dereference(ht->tbl, ht);
+restart:
 	if (free_fn) {
 		for (i = 0; i < tbl->size; i++) {
 			struct rhash_head *pos, *next;
@@ -1130,7 +1131,12 @@ void rhashtable_free_and_destroy(struct rhashtable *ht,
 		}
 	}
 
+	next_tbl = rht_dereference(tbl->future_tbl, ht);
 	bucket_table_free(tbl);
+	if (next_tbl) {
+		tbl = next_tbl;
+		goto restart;
+	}
 	mutex_unlock(&ht->mutex);
 }
 EXPORT_SYMBOL_GPL(rhashtable_free_and_destroy);
-- 
2.17.1


From 213e627e5191671488a0a6caefcfcb3c26f30daf Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Tue, 10 Jul 2018 14:22:27 -0700
Subject: [PATCH 15/25] sch_fq_codel: zero q->flows_cnt when fq_codel_init
 fails

[ Upstream commit 83fe6b8709f65bc505b10235bd82ece12c4c5099 ]

When fq_codel_init fails, qdisc_create_dflt will cleanup by using
qdisc_destroy. This function calls the ->reset() op prior to calling the
->destroy() op.

Unfortunately, during the failure flow for sch_fq_codel, the ->flows
parameter is not initialized, so the fq_codel_reset function will null
pointer dereference.

   kernel: BUG: unable to handle kernel NULL pointer dereference at 0000000000000008
   kernel: IP: fq_codel_reset+0x58/0xd0 [sch_fq_codel]
   kernel: PGD 0 P4D 0
   kernel: Oops: 0000 [#1] SMP PTI
   kernel: Modules linked in: i40iw i40e(OE) xt_CHECKSUM iptable_mangle ipt_MASQUERADE nf_nat_masquerade_ipv4 iptable_nat nf_nat_ipv4 nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_conntrack nf_conntrack tun bridge stp llc devlink ebtable_filter ebtables ip6table_filter ip6_tables rpcrdma ib_isert iscsi_target_mod sunrpc ib_iser libiscsi scsi_transport_iscsi ib_srpt target_core_mod ib_srp scsi_transport_srp ib_ipoib rdma_ucm ib_ucm ib_uverbs ib_umad rdma_cm ib_cm iw_cm intel_rapl sb_edac x86_pkg_temp_thermal intel_powerclamp coretemp kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel intel_cstate iTCO_wdt iTCO_vendor_support intel_uncore ib_core intel_rapl_perf mei_me mei joydev i2c_i801 lpc_ich ioatdma shpchp wmi sch_fq_codel xfs libcrc32c mgag200 ixgbe drm_kms_helper isci ttm firewire_ohci
   kernel:  mdio drm igb libsas crc32c_intel firewire_core ptp pps_core scsi_transport_sas crc_itu_t dca i2c_algo_bit ipmi_si ipmi_devintf ipmi_msghandler [last unloaded: i40e]
   kernel: CPU: 10 PID: 4219 Comm: ip Tainted: G           OE    4.16.13custom-fq-codel-test+ #3
   kernel: Hardware name: Intel Corporation S2600CO/S2600CO, BIOS SE5C600.86B.02.05.0004.051120151007 05/11/2015
   kernel: RIP: 0010:fq_codel_reset+0x58/0xd0 [sch_fq_codel]
   kernel: RSP: 0018:ffffbfbf4c1fb620 EFLAGS: 00010246
   kernel: RAX: 0000000000000400 RBX: 0000000000000000 RCX: 00000000000005b9
   kernel: RDX: 0000000000000000 RSI: ffff9d03264a60c0 RDI: ffff9cfd17b31c00
   kernel: RBP: 0000000000000001 R08: 00000000000260c0 R09: ffffffffb679c3e9
   kernel: R10: fffff1dab06a0e80 R11: ffff9cfd163af800 R12: ffff9cfd17b31c00
   kernel: R13: 0000000000000001 R14: ffff9cfd153de600 R15: 0000000000000001
   kernel: FS:  00007fdec2f92800(0000) GS:ffff9d0326480000(0000) knlGS:0000000000000000
   kernel: CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
   kernel: CR2: 0000000000000008 CR3: 0000000c1956a006 CR4: 00000000000606e0
   kernel: Call Trace:
   kernel:  qdisc_destroy+0x56/0x140
   kernel:  qdisc_create_dflt+0x8b/0xb0
   kernel:  mq_init+0xc1/0xf0
   kernel:  qdisc_create_dflt+0x5a/0xb0
   kernel:  dev_activate+0x205/0x230
   kernel:  __dev_open+0xf5/0x160
   kernel:  __dev_change_flags+0x1a3/0x210
   kernel:  dev_change_flags+0x21/0x60
   kernel:  do_setlink+0x660/0xdf0
   kernel:  ? down_trylock+0x25/0x30
   kernel:  ? xfs_buf_trylock+0x1a/0xd0 [xfs]
   kernel:  ? rtnl_newlink+0x816/0x990
   kernel:  ? _xfs_buf_find+0x327/0x580 [xfs]
   kernel:  ? _cond_resched+0x15/0x30
   kernel:  ? kmem_cache_alloc+0x20/0x1b0
   kernel:  ? rtnetlink_rcv_msg+0x200/0x2f0
   kernel:  ? rtnl_calcit.isra.30+0x100/0x100
   kernel:  ? netlink_rcv_skb+0x4c/0x120
   kernel:  ? netlink_unicast+0x19e/0x260
   kernel:  ? netlink_sendmsg+0x1ff/0x3c0
   kernel:  ? sock_sendmsg+0x36/0x40
   kernel:  ? ___sys_sendmsg+0x295/0x2f0
   kernel:  ? ebitmap_cmp+0x6d/0x90
   kernel:  ? dev_get_by_name_rcu+0x73/0x90
   kernel:  ? skb_dequeue+0x52/0x60
   kernel:  ? __inode_wait_for_writeback+0x7f/0xf0
   kernel:  ? bit_waitqueue+0x30/0x30
   kernel:  ? fsnotify_grab_connector+0x3c/0x60
   kernel:  ? __sys_sendmsg+0x51/0x90
   kernel:  ? do_syscall_64+0x74/0x180
   kernel:  ? entry_SYSCALL_64_after_hwframe+0x3d/0xa2
   kernel: Code: 00 00 48 89 87 00 02 00 00 8b 87 a0 01 00 00 85 c0 0f 84 84 00 00 00 31 ed 48 63 dd 83 c5 01 48 c1 e3 06 49 03 9c 24 90 01 00 00 <48> 8b 73 08 48 8b 3b e8 6c 9a 4f f6 48 8d 43 10 48 c7 03 00 00
   kernel: RIP: fq_codel_reset+0x58/0xd0 [sch_fq_codel] RSP: ffffbfbf4c1fb620
   kernel: CR2: 0000000000000008
   kernel: ---[ end trace e81a62bede66274e ]---

This is caused because flows_cnt is non-zero, but flows hasn't been
initialized. fq_codel_init has left the private data in a partially
initialized state.

To fix this, reset flows_cnt to 0 when we fail to initialize.
Additionally, to make the state more consistent, also cleanup the flows
pointer when the allocation of backlogs fails.

This fixes the NULL pointer dereference, since both the for-loop and
memset in fq_codel_reset will be no-ops when flow_cnt is zero.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_fq_codel.c | 25 ++++++++++++++++++-------
 1 file changed, 18 insertions(+), 7 deletions(-)

diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 22fa13cf5d8b..846883907cd4 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -479,23 +479,27 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt,
 	q->cparams.mtu = psched_mtu(qdisc_dev(sch));
 
 	if (opt) {
-		int err = fq_codel_change(sch, opt, extack);
+		err = fq_codel_change(sch, opt, extack);
 		if (err)
-			return err;
+			goto init_failure;
 	}
 
 	err = tcf_block_get(&q->block, &q->filter_list, sch, extack);
 	if (err)
-		return err;
+		goto init_failure;
 
 	if (!q->flows) {
 		q->flows = kvzalloc(q->flows_cnt *
 					   sizeof(struct fq_codel_flow), GFP_KERNEL);
-		if (!q->flows)
-			return -ENOMEM;
+		if (!q->flows) {
+			err = -ENOMEM;
+			goto init_failure;
+		}
 		q->backlogs = kvzalloc(q->flows_cnt * sizeof(u32), GFP_KERNEL);
-		if (!q->backlogs)
-			return -ENOMEM;
+		if (!q->backlogs) {
+			err = -ENOMEM;
+			goto alloc_failure;
+		}
 		for (i = 0; i < q->flows_cnt; i++) {
 			struct fq_codel_flow *flow = q->flows + i;
 
@@ -508,6 +512,13 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt,
 	else
 		sch->flags &= ~TCQ_F_CAN_BYPASS;
 	return 0;
+
+alloc_failure:
+	kvfree(q->flows);
+	q->flows = NULL;
+init_failure:
+	q->flows_cnt = 0;
+	return err;
 }
 
 static int fq_codel_dump(struct Qdisc *sch, struct sk_buff *skb)
-- 
2.17.1


From e4d4218eae38471ccf2d919b7c6190477bc69723 Mon Sep 17 00:00:00 2001
From: Sanjeev Bansal <sanjeevb.bansal@broadcom.com>
Date: Mon, 16 Jul 2018 11:13:32 +0530
Subject: [PATCH 16/25] tg3: Add higher cpu clock for 5762.

[ Upstream commit 3a498606bb04af603a46ebde8296040b2de350d1 ]

This patch has fix for TX timeout while running bi-directional
traffic with 100 Mbps using 5762.

Signed-off-by: Sanjeev Bansal <sanjeevb.bansal@broadcom.com>
Signed-off-by: Siva Reddy Kallam <siva.kallam@broadcom.com>
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/tg3.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 9f59b1270a7c..3e0e7f18ecf9 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -9289,6 +9289,15 @@ static int tg3_chip_reset(struct tg3 *tp)
 
 	tg3_restore_clk(tp);
 
+	/* Increase the core clock speed to fix tx timeout issue for 5762
+	 * with 100Mbps link speed.
+	 */
+	if (tg3_asic_rev(tp) == ASIC_REV_5762) {
+		val = tr32(TG3_CPMU_CLCK_ORIDE_ENABLE);
+		tw32(TG3_CPMU_CLCK_ORIDE_ENABLE, val |
+		     TG3_CPMU_MAC_ORIDE_ENABLE);
+	}
+
 	/* Reprobe ASF enable state.  */
 	tg3_flag_clear(tp, ENABLE_ASF);
 	tp->phy_flags &= ~(TG3_PHYFLG_1G_ON_VAUX_OK |
-- 
2.17.1


From 2169bcc4e91c153b73efb72157d33b87ca3828bd Mon Sep 17 00:00:00 2001
From: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Date: Fri, 13 Jul 2018 14:40:50 +0900
Subject: [PATCH 17/25] net: ip6_gre: get ipv6hdr after skb_cow_head()

[ Upstream commit b7ed879425be371905d856410d19e9a42a62bcf3 ]

A KASAN:use-after-free bug was found related to ip6-erspan
while running selftests/net/ip6_gre_headroom.sh

It happens because of following sequence:
- ipv6hdr pointer is obtained from skb
- skb_cow_head() is called, skb->head memory is reallocated
- old data is accessed using ipv6hdr pointer

skb_cow_head() call was added in e41c7c68ea77 ("ip6erspan: make sure
enough headroom at xmit."), but looking at the history there was a
chance of similar bug because gre_handle_offloads() and pskb_trim()
can also reallocate skb->head memory. Fixes tag points to commit
which introduced possibility of this bug.

This patch moves ipv6hdr pointer assignment after skb_cow_head() call.

Fixes: 5a963eb61b7c ("ip6_gre: Add ERSPAN native tunnel support")
Signed-off-by: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Reviewed-by: Greg Rose <gvrose8192@gmail.com>
Acked-by: William Tu <u9012063@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 458de353f5d9..1a4d6897d17f 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -927,7 +927,6 @@ static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb,
 static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 					 struct net_device *dev)
 {
-	struct ipv6hdr *ipv6h = ipv6_hdr(skb);
 	struct ip6_tnl *t = netdev_priv(dev);
 	struct dst_entry *dst = skb_dst(skb);
 	struct net_device_stats *stats;
@@ -998,6 +997,8 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 			goto tx_err;
 		}
 	} else {
+		struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+
 		switch (skb->protocol) {
 		case htons(ETH_P_IP):
 			memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
-- 
2.17.1


From 969097a95836dc4209d08c92fb1796faa2ea1c8a Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Thu, 26 Apr 2018 16:58:57 -0300
Subject: [PATCH 18/25] sctp: introduce sctp_dst_mtu

[ Upstream commit 6ff0f871c20ec1769a481edca86f23c76b2b06d3 ]

Which makes sure that the MTU respects the minimum value of
SCTP_DEFAULT_MINSEGMENT and that it is correctly aligned.

Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/sctp.h | 9 +++++++--
 net/sctp/associola.c    | 6 ++----
 net/sctp/transport.c    | 6 +++---
 3 files changed, 12 insertions(+), 9 deletions(-)

diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 35498e613ff5..edfa9d0f6005 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -609,10 +609,15 @@ static inline struct dst_entry *sctp_transport_dst_check(struct sctp_transport *
 	return t->dst;
 }
 
+static inline __u32 sctp_dst_mtu(const struct dst_entry *dst)
+{
+	return SCTP_TRUNC4(max_t(__u32, dst_mtu(dst),
+				 SCTP_DEFAULT_MINSEGMENT));
+}
+
 static inline bool sctp_transport_pmtu_check(struct sctp_transport *t)
 {
-	__u32 pmtu = max_t(size_t, SCTP_TRUNC4(dst_mtu(t->dst)),
-			   SCTP_DEFAULT_MINSEGMENT);
+	__u32 pmtu = sctp_dst_mtu(t->dst);
 
 	if (t->pathmtu == pmtu)
 		return true;
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index a47179da24e6..ef8adac1be83 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -1446,11 +1446,9 @@ void sctp_assoc_sync_pmtu(struct sctp_association *asoc)
 		return;
 
 	/* Get the lowest pmtu of all the transports. */
-	list_for_each_entry(t, &asoc->peer.transport_addr_list,
-				transports) {
+	list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) {
 		if (t->pmtu_pending && t->dst) {
-			sctp_transport_update_pmtu(
-					t, SCTP_TRUNC4(dst_mtu(t->dst)));
+			sctp_transport_update_pmtu(t, sctp_dst_mtu(t->dst));
 			t->pmtu_pending = 0;
 		}
 		if (!pmtu || (t->pathmtu < pmtu))
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index 03fc2c427aca..e23071741bbf 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -242,9 +242,9 @@ void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk)
 						&transport->fl, sk);
 	}
 
-	if (transport->dst) {
-		transport->pathmtu = SCTP_TRUNC4(dst_mtu(transport->dst));
-	} else
+	if (transport->dst)
+		transport->pathmtu = sctp_dst_mtu(transport->dst);
+	else
 		transport->pathmtu = SCTP_DEFAULT_MAXSEGMENT;
 }
 
-- 
2.17.1


From edca889c17128568401f164eb5013c3902547d7c Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 3 Jul 2018 16:30:47 +0800
Subject: [PATCH 19/25] sctp: fix the issue that pathmtu may be set lower than
 MINSEGMENT

[ Upstream commit a65925475571953da12a9bc2082aec29d4e2c0e7 ]

After commit b6c5734db070 ("sctp: fix the handling of ICMP Frag Needed
for too small MTUs"), sctp_transport_update_pmtu would refetch pathmtu
from the dst and set it to transport's pathmtu without any check.

The new pathmtu may be lower than MINSEGMENT if the dst is obsolete and
updated by .get_dst() in sctp_transport_update_pmtu. In this case, it
could have a smaller MTU as well, and thus we should validate it
against MINSEGMENT instead.

Syzbot reported a warning in sctp_mtu_payload caused by this.

This patch refetches the pathmtu by calling sctp_dst_mtu where it does
the check against MINSEGMENT.

v1->v2:
  - refetch the pathmtu by calling sctp_dst_mtu instead as Marcelo's
    suggestion.

Fixes: b6c5734db070 ("sctp: fix the handling of ICMP Frag Needed for too small MTUs")
Reported-by: syzbot+f0d9d7cba052f9344b03@syzkaller.appspotmail.com
Suggested-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/transport.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index e23071741bbf..e890ceb55939 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -273,7 +273,7 @@ bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu)
 
 	if (dst) {
 		/* Re-fetch, as under layers may have a higher minimum size */
-		pmtu = SCTP_TRUNC4(dst_mtu(dst));
+		pmtu = sctp_dst_mtu(dst);
 		change = t->pathmtu != pmtu;
 	}
 	t->pathmtu = pmtu;
-- 
2.17.1


From a12fba6a7fb20f8db956fef84957e0a1dacf9279 Mon Sep 17 00:00:00 2001
From: Haiyang Zhang <haiyangz@microsoft.com>
Date: Tue, 17 Jul 2018 17:11:13 +0000
Subject: [PATCH 20/25] hv_netvsc: Fix napi reschedule while receive completion
 is busy

[ Upstream commit 6b81b193b83e87da1ea13217d684b54fccf8ee8a ]

If out ring is full temporarily and receive completion cannot go out,
we may still need to reschedule napi if certain conditions are met.
Otherwise the napi poll might be stopped forever, and cause network
disconnect.

Fixes: 7426b1a51803 ("netvsc: optimize receive completions")
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/netvsc.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index c418113c6b20..c10ca3c20b36 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -1291,6 +1291,7 @@ int netvsc_poll(struct napi_struct *napi, int budget)
 	struct hv_device *device = netvsc_channel_to_device(channel);
 	struct net_device *ndev = hv_get_drvdata(device);
 	int work_done = 0;
+	int ret;
 
 	/* If starting a new interval */
 	if (!nvchan->desc)
@@ -1302,16 +1303,18 @@ int netvsc_poll(struct napi_struct *napi, int budget)
 		nvchan->desc = hv_pkt_iter_next(channel, nvchan->desc);
 	}
 
-	/* If send of pending receive completions suceeded
-	 *   and did not exhaust NAPI budget this time
-	 *   and not doing busy poll
+	/* Send any pending receive completions */
+	ret = send_recv_completions(ndev, net_device, nvchan);
+
+	/* If it did not exhaust NAPI budget this time
+	 *  and not doing busy poll
 	 * then re-enable host interrupts
-	 *     and reschedule if ring is not empty.
+	 *  and reschedule if ring is not empty
+	 *   or sending receive completion failed.
 	 */
-	if (send_recv_completions(ndev, net_device, nvchan) == 0 &&
-	    work_done < budget &&
+	if (work_done < budget &&
 	    napi_complete_done(napi, work_done) &&
-	    hv_end_read(&channel->inbound) &&
+	    (ret || hv_end_read(&channel->inbound)) &&
 	    napi_schedule_prep(napi)) {
 		hv_begin_read(&channel->inbound);
 		__napi_schedule(napi);
-- 
2.17.1


From 88db7806f184cd697bc831b756bf338316b73a0f Mon Sep 17 00:00:00 2001
From: Igor Russkikh <igor.russkikh@aquantia.com>
Date: Thu, 5 Jul 2018 17:01:09 +0300
Subject: [PATCH 21/25] net: aquantia: vlan unicast address list correct
 handling

[ Upstream commit 94b3b542303f3055c326df74ef144a8a790d7d7f ]

Setting up macvlan/macvtap networks over atlantic NIC results
in no traffic over these networks because ndo_set_rx_mode did
not listed UC MACs as registered in unicast filter.

Here we fix that taking into account maximum number of UC
filters supported by hardware. If more than MAX addresses were
registered, we just enable promisc  and/or allmulti to pass
the traffic in.

We also remove MULTICAST_ADDRESS_MAX constant from aq_cfg since
thats not a configurable parameter at all.

Fixes: b21f502 ("net:ethernet:aquantia: Fix for multicast filter handling.")
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/aquantia/atlantic/aq_cfg.h   |  2 -
 .../net/ethernet/aquantia/atlantic/aq_hw.h    |  4 +-
 .../net/ethernet/aquantia/atlantic/aq_main.c  | 11 +----
 .../net/ethernet/aquantia/atlantic/aq_nic.c   | 47 +++++++++++--------
 .../net/ethernet/aquantia/atlantic/aq_nic.h   |  2 +-
 .../aquantia/atlantic/hw_atl/hw_atl_a0.c      |  2 +-
 .../aquantia/atlantic/hw_atl/hw_atl_b0.c      |  4 +-
 7 files changed, 36 insertions(+), 36 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h
index fc7383106946..91eb8910b1c9 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h
@@ -63,8 +63,6 @@
 
 #define AQ_CFG_NAPI_WEIGHT     64U
 
-#define AQ_CFG_MULTICAST_ADDRESS_MAX     32U
-
 /*#define AQ_CFG_MAC_ADDR_PERMANENT {0x30, 0x0E, 0xE3, 0x12, 0x34, 0x56}*/
 
 #define AQ_NIC_FC_OFF    0U
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
index a2d416b24ffc..2c6ebd91a9f2 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
@@ -98,6 +98,8 @@ struct aq_stats_s {
 #define AQ_HW_MEDIA_TYPE_TP    1U
 #define AQ_HW_MEDIA_TYPE_FIBRE 2U
 
+#define AQ_HW_MULTICAST_ADDRESS_MAX     32U
+
 struct aq_hw_s {
 	atomic_t flags;
 	u8 rbl_enabled:1;
@@ -177,7 +179,7 @@ struct aq_hw_ops {
 				    unsigned int packet_filter);
 
 	int (*hw_multicast_list_set)(struct aq_hw_s *self,
-				     u8 ar_mac[AQ_CFG_MULTICAST_ADDRESS_MAX]
+				     u8 ar_mac[AQ_HW_MULTICAST_ADDRESS_MAX]
 				     [ETH_ALEN],
 				     u32 count);
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
index ba5fe8c4125d..e3ae29e523f0 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
@@ -135,17 +135,10 @@ static int aq_ndev_set_mac_address(struct net_device *ndev, void *addr)
 static void aq_ndev_set_multicast_settings(struct net_device *ndev)
 {
 	struct aq_nic_s *aq_nic = netdev_priv(ndev);
-	int err = 0;
 
-	err = aq_nic_set_packet_filter(aq_nic, ndev->flags);
-	if (err < 0)
-		return;
+	aq_nic_set_packet_filter(aq_nic, ndev->flags);
 
-	if (netdev_mc_count(ndev)) {
-		err = aq_nic_set_multicast_list(aq_nic, ndev);
-		if (err < 0)
-			return;
-	}
+	aq_nic_set_multicast_list(aq_nic, ndev);
 }
 
 static const struct net_device_ops aq_ndev_ops = {
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 1a1a6380c128..7a22d0257e04 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -563,34 +563,41 @@ int aq_nic_set_packet_filter(struct aq_nic_s *self, unsigned int flags)
 
 int aq_nic_set_multicast_list(struct aq_nic_s *self, struct net_device *ndev)
 {
+	unsigned int packet_filter = self->packet_filter;
 	struct netdev_hw_addr *ha = NULL;
 	unsigned int i = 0U;
 
-	self->mc_list.count = 0U;
-
-	netdev_for_each_mc_addr(ha, ndev) {
-		ether_addr_copy(self->mc_list.ar[i++], ha->addr);
-		++self->mc_list.count;
+	self->mc_list.count = 0;
+	if (netdev_uc_count(ndev) > AQ_HW_MULTICAST_ADDRESS_MAX) {
+		packet_filter |= IFF_PROMISC;
+	} else {
+		netdev_for_each_uc_addr(ha, ndev) {
+			ether_addr_copy(self->mc_list.ar[i++], ha->addr);
 
-		if (i >= AQ_CFG_MULTICAST_ADDRESS_MAX)
-			break;
+			if (i >= AQ_HW_MULTICAST_ADDRESS_MAX)
+				break;
+		}
 	}
 
-	if (i >= AQ_CFG_MULTICAST_ADDRESS_MAX) {
-		/* Number of filters is too big: atlantic does not support this.
-		 * Force all multi filter to support this.
-		 * With this we disable all UC filters and setup "all pass"
-		 * multicast mask
-		 */
-		self->packet_filter |= IFF_ALLMULTI;
-		self->aq_nic_cfg.mc_list_count = 0;
-		return self->aq_hw_ops->hw_packet_filter_set(self->aq_hw,
-							     self->packet_filter);
+	if (i + netdev_mc_count(ndev) > AQ_HW_MULTICAST_ADDRESS_MAX) {
+		packet_filter |= IFF_ALLMULTI;
 	} else {
-		return self->aq_hw_ops->hw_multicast_list_set(self->aq_hw,
-						    self->mc_list.ar,
-						    self->mc_list.count);
+		netdev_for_each_mc_addr(ha, ndev) {
+			ether_addr_copy(self->mc_list.ar[i++], ha->addr);
+
+			if (i >= AQ_HW_MULTICAST_ADDRESS_MAX)
+				break;
+		}
+	}
+
+	if (i > 0 && i < AQ_HW_MULTICAST_ADDRESS_MAX) {
+		packet_filter |= IFF_MULTICAST;
+		self->mc_list.count = i;
+		self->aq_hw_ops->hw_multicast_list_set(self->aq_hw,
+						       self->mc_list.ar,
+						       self->mc_list.count);
 	}
+	return aq_nic_set_packet_filter(self, packet_filter);
 }
 
 int aq_nic_set_mtu(struct aq_nic_s *self, int new_mtu)
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
index faa533a0ec47..fecfc401f95d 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
@@ -75,7 +75,7 @@ struct aq_nic_s {
 	struct aq_hw_link_status_s link_status;
 	struct {
 		u32 count;
-		u8 ar[AQ_CFG_MULTICAST_ADDRESS_MAX][ETH_ALEN];
+		u8 ar[AQ_HW_MULTICAST_ADDRESS_MAX][ETH_ALEN];
 	} mc_list;
 
 	struct pci_dev *pdev;
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
index 67e2f9fb9402..8cc6abadc03b 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
@@ -765,7 +765,7 @@ static int hw_atl_a0_hw_packet_filter_set(struct aq_hw_s *self,
 
 static int hw_atl_a0_hw_multicast_list_set(struct aq_hw_s *self,
 					   u8 ar_mac
-					   [AQ_CFG_MULTICAST_ADDRESS_MAX]
+					   [AQ_HW_MULTICAST_ADDRESS_MAX]
 					   [ETH_ALEN],
 					   u32 count)
 {
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index 819f6bcf9b4e..956860a69797 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -784,7 +784,7 @@ static int hw_atl_b0_hw_packet_filter_set(struct aq_hw_s *self,
 
 static int hw_atl_b0_hw_multicast_list_set(struct aq_hw_s *self,
 					   u8 ar_mac
-					   [AQ_CFG_MULTICAST_ADDRESS_MAX]
+					   [AQ_HW_MULTICAST_ADDRESS_MAX]
 					   [ETH_ALEN],
 					   u32 count)
 {
@@ -812,7 +812,7 @@ static int hw_atl_b0_hw_multicast_list_set(struct aq_hw_s *self,
 
 		hw_atl_rpfl2_uc_flr_en_set(self,
 					   (self->aq_nic_cfg->is_mc_list_enabled),
-				    HW_ATL_B0_MAC_MIN + i);
+					   HW_ATL_B0_MAC_MIN + i);
 	}
 
 	err = aq_hw_err_from_flags(self);
-- 
2.17.1


From 2fec1a266e183e43caabc900869918df6a2b13bc Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Sun, 15 Jul 2018 13:54:39 +0300
Subject: [PATCH 22/25] net/mlx4_en: Don't reuse RX page when XDP is set

[ Upstream commit 432e629e56432064761be63bcd5e263c0920430d ]

When a new rx packet arrives, the rx path will decide whether to reuse
the remainder of the page or not according to one of the below conditions:
1. frag_info->frag_stride == PAGE_SIZE / 2
2. frags->page_offset + frag_info->frag_size > PAGE_SIZE;

The first condition is no met for when XDP is set.
For XDP, page_offset is always set to priv->rx_headroom which is
XDP_PACKET_HEADROOM and frag_info->frag_size is around mtu size + some
padding, still the 2nd release condition will hold since
XDP_PACKET_HEADROOM + 1536 < PAGE_SIZE, as a result the page will not
be released and will be _wrongly_ reused for next free rx descriptor.

In XDP there is an assumption to have a page per packet and reuse can
break such assumption and might cause packet data corruptions.

Fix this by adding an extra condition (!priv->rx_headroom) to the 2nd
case to avoid page reuse when XDP is set, since rx_headroom is set to 0
for non XDP setup and set to XDP_PACKET_HEADROOM for XDP setup.

No additional cache line is required for the new condition.

Fixes: 34db548bfb95 ("mlx4: add page recycling in receive path")
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Suggested-by: Martin KaFai Lau <kafai@fb.com>
CC: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_rx.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 5c613c6663da..2ca0f1dad54c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -474,10 +474,10 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv,
 {
 	const struct mlx4_en_frag_info *frag_info = priv->frag_info;
 	unsigned int truesize = 0;
+	bool release = true;
 	int nr, frag_size;
 	struct page *page;
 	dma_addr_t dma;
-	bool release;
 
 	/* Collect used fragments while replacing them in the HW descriptors */
 	for (nr = 0;; frags++) {
@@ -500,7 +500,11 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv,
 			release = page_count(page) != 1 ||
 				  page_is_pfmemalloc(page) ||
 				  page_to_nid(page) != numa_mem_id();
-		} else {
+		} else if (!priv->rx_headroom) {
+			/* rx_headroom for non XDP setup is always 0.
+			 * When XDP is set, the above condition will
+			 * guarantee page is always released.
+			 */
 			u32 sz_align = ALIGN(frag_size, SMP_CACHE_BYTES);
 
 			frags->page_offset += sz_align;
-- 
2.17.1


From 7a27cc8981c20e294c8b76455ec0491a960b88c9 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 11 Jul 2018 02:47:58 -0700
Subject: [PATCH 23/25] net: systemport: Fix CRC forwarding check for
 SYSTEMPORT Lite

[ Upstream commit 9e3bff923913729d76d87f0015848ee7b8ff7083 ]

SYSTEMPORT Lite reversed the logic compared to SYSTEMPORT, the
GIB_FCS_STRIP bit is set when the Ethernet FCS is stripped, and that bit
is not set by default. Fix the logic such that we properly check whether
that bit is set or not and we don't forward an extra 4 bytes to the
network stack.

Fixes: 44a4524c54af ("net: systemport: Add support for SYSTEMPORT Lite")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bcmsysport.c | 4 ++--
 drivers/net/ethernet/broadcom/bcmsysport.h | 3 ++-
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index f33b25fbca63..7db072fe5f22 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -1946,8 +1946,8 @@ static int bcm_sysport_open(struct net_device *dev)
 	if (!priv->is_lite)
 		priv->crc_fwd = !!(umac_readl(priv, UMAC_CMD) & CMD_CRC_FWD);
 	else
-		priv->crc_fwd = !!(gib_readl(priv, GIB_CONTROL) &
-				   GIB_FCS_STRIP);
+		priv->crc_fwd = !((gib_readl(priv, GIB_CONTROL) &
+				  GIB_FCS_STRIP) >> GIB_FCS_STRIP_SHIFT);
 
 	phydev = of_phy_connect(dev, priv->phy_dn, bcm_sysport_adj_link,
 				0, priv->phy_interface);
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h
index d6e5d0cbf3a3..cf440b91fd04 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.h
+++ b/drivers/net/ethernet/broadcom/bcmsysport.h
@@ -278,7 +278,8 @@ struct bcm_rsb {
 #define  GIB_GTX_CLK_EXT_CLK		(0 << GIB_GTX_CLK_SEL_SHIFT)
 #define  GIB_GTX_CLK_125MHZ		(1 << GIB_GTX_CLK_SEL_SHIFT)
 #define  GIB_GTX_CLK_250MHZ		(2 << GIB_GTX_CLK_SEL_SHIFT)
-#define  GIB_FCS_STRIP			(1 << 6)
+#define  GIB_FCS_STRIP_SHIFT		6
+#define  GIB_FCS_STRIP			(1 << GIB_FCS_STRIP_SHIFT)
 #define  GIB_LCL_LOOP_EN		(1 << 7)
 #define  GIB_LCL_LOOP_TXEN		(1 << 8)
 #define  GIB_RMT_LOOP_EN		(1 << 9)
-- 
2.17.1


From 66e5830b060f2badd1f43e7dbcd3149fac8586db Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 13 Jul 2018 17:21:42 +0200
Subject: [PATCH 24/25] ipv6: make DAD fail with enhanced DAD when nonce length
 differs

[ Upstream commit e66515999b627368892ccc9b3a13a506f2ea1357 ]

Commit adc176c54722 ("ipv6 addrconf: Implemented enhanced DAD (RFC7527)")
added enhanced DAD with a nonce length of 6 bytes. However, RFC7527
doesn't specify the length of the nonce, other than being 6 + 8*k bytes,
with integer k >= 0 (RFC3971 5.3.2). The current implementation simply
assumes that the nonce will always be 6 bytes, but others systems are
free to choose different sizes.

If another system sends a nonce of different length but with the same 6
bytes prefix, it shouldn't be considered as the same nonce. Thus, check
that the length of the received nonce is the same as the length we sent.

Ugly scapy test script running on veth0:

def loop():
    pkt=sniff(iface="veth0", filter="icmp6", count=1)
    pkt = pkt[0]
    b = bytearray(pkt[Raw].load)
    b[1] += 1
    b += b'\xde\xad\xbe\xef\xde\xad\xbe\xef'
    pkt[Raw].load = bytes(b)
    pkt[IPv6].plen += 8
    # fixup checksum after modifying the payload
    pkt[IPv6].payload.cksum -= 0x3b44
    if pkt[IPv6].payload.cksum < 0:
        pkt[IPv6].payload.cksum += 0xffff
    sendp(pkt, iface="veth0")

This should result in DAD failure for any address added to veth0's peer,
but is currently ignored.

Fixes: adc176c54722 ("ipv6 addrconf: Implemented enhanced DAD (RFC7527)")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ndisc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 525051a886bc..3ff9316616d8 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -811,7 +811,7 @@ static void ndisc_recv_ns(struct sk_buff *skb)
 			return;
 		}
 	}
-	if (ndopts.nd_opts_nonce)
+	if (ndopts.nd_opts_nonce && ndopts.nd_opts_nonce->nd_opt_len == 1)
 		memcpy(&nonce, (u8 *)(ndopts.nd_opts_nonce + 1), 6);
 
 	inc = ipv6_addr_is_multicast(daddr);
-- 
2.17.1


From 1736d112673007003bafc8ba6d9a9fbf37bce404 Mon Sep 17 00:00:00 2001
From: Alexander Couzens <lynxis@fe80.eu>
Date: Tue, 17 Jul 2018 13:17:09 +0200
Subject: [PATCH 25/25] net: usb: asix: replace mii_nway_restart in resume path

[ Upstream commit 5c968f48021a9b3faa61ac2543cfab32461c0e05 ]

mii_nway_restart is not pm aware which results in a rtnl deadlock.
Implement mii_nway_restart manual by setting BMCR_ANRESTART if
BMCR_ANENABLE is set.

To reproduce:
* plug an asix based usb network interface
* wait until the device enters PM (~5 sec)
* `ip link set eth1 up` will never return

Fixes: d9fe64e51114 ("net: asix: Add in_pm parameter")
Signed-off-by: Alexander Couzens <lynxis@fe80.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/asix_devices.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c
index 3d4f7959dabb..b1b3d8f7e67d 100644
--- a/drivers/net/usb/asix_devices.c
+++ b/drivers/net/usb/asix_devices.c
@@ -642,10 +642,12 @@ static void ax88772_restore_phy(struct usbnet *dev)
 				     priv->presvd_phy_advertise);
 
 		/* Restore BMCR */
+		if (priv->presvd_phy_bmcr & BMCR_ANENABLE)
+			priv->presvd_phy_bmcr |= BMCR_ANRESTART;
+
 		asix_mdio_write_nopm(dev->net, dev->mii.phy_id, MII_BMCR,
 				     priv->presvd_phy_bmcr);
 
-		mii_nway_restart(&dev->mii);
 		priv->presvd_phy_advertise = 0;
 		priv->presvd_phy_bmcr = 0;
 	}
-- 
2.17.1

Re: [PATCHES] Networking

[Greg KH]

On Sun, Jul 22, 2018 at 08:51:17PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixxes for 4.14.x and
> 4.17.x -stable, respectively.
> 
> Thanks!

All now applied, thanks.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 168 bytes --]


[ Eric please double check my TCP backports, thank you... ]

Please queue up the following networking fixes for v4.14.x and v4.17.x
-stable, respectively.

Thank you!

[-- Attachment #2: net_414.mbox --]
[-- Type: Application/Octet-Stream, Size: 76177 bytes --]

From 27a5acb110888fac3010af05087764103a0115f9 Mon Sep 17 00:00:00 2001
From: Jarod Wilson <jarod@redhat.com>
Date: Wed, 18 Jul 2018 14:49:36 -0400
Subject: [PATCH 01/25] bonding: set default miimon value for non-arp modes if
 not set

[ Upstream commit c1f897ce186a529a494441642125479d38727a3d ]

For some time now, if you load the bonding driver and configure bond
parameters via sysfs using minimal config options, such as specifying
nothing but the mode, relying on defaults for everything else, modes
that cannot use arp monitoring (802.3ad, balance-tlb, balance-alb) all
wind up with both arp_interval=0 (as it should be) and miimon=0, which
means the miimon monitor thread never actually runs. This is particularly
problematic for 802.3ad.

For example, from an LNST recipe I've set up:

$ modprobe bonding max_bonds=0"
$ echo "+t_bond0" > /sys/class/net/bonding_masters"
$ ip link set t_bond0 down"
$ echo "802.3ad" > /sys/class/net/t_bond0/bonding/mode"
$ ip link set ens1f1 down"
$ echo "+ens1f1" > /sys/class/net/t_bond0/bonding/slaves"
$ ip link set ens1f0 down"
$ echo "+ens1f0" > /sys/class/net/t_bond0/bonding/slaves"
$ ethtool -i t_bond0"
$ ip link set ens1f1 up"
$ ip link set ens1f0 up"
$ ip link set t_bond0 up"
$ ip addr add 192.168.9.1/24 dev t_bond0"
$ ip addr add 2002::1/64 dev t_bond0"

This bond comes up okay, but things look slightly suspect in
/proc/net/bonding/t_bond0 output:

$ grep -i mii /proc/net/bonding/t_bond0
MII Status: up
MII Polling Interval (ms): 0
MII Status: up
MII Status: up

Now, pull a cable on one of the ports in the bond, then reconnect it, and
you'll see:

Slave Interface: ens1f0
MII Status: down
Speed: 1000 Mbps
Duplex: full

I believe this became a major issue as of commit 4d2c0cda0744, which for
802.3ad bonds, sets slave->link = BOND_LINK_DOWN, with a comment about
relying on link monitoring via miimon to set it correctly, but since the
miimon work queue never runs, the link just stays marked down.

If we simply tweak bond_option_mode_set() slightly, we can check for the
non-arp modes having no miimon value set, and insert BOND_DEFAULT_MIIMON,
which gets things back in full working order. This problem exists as far
back as 4.14, and might be worth fixing in all stable trees since, though
the work-around is to simply specify an miimon value yourself.

Reported-by: Bob Ball <ball@umich.edu>
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Acked-by: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_options.c | 23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)

diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 61084ba69a99..3d154eb63dcf 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -743,15 +743,20 @@ const struct bond_option *bond_opt_get(unsigned int option)
 static int bond_option_mode_set(struct bonding *bond,
 				const struct bond_opt_value *newval)
 {
-	if (!bond_mode_uses_arp(newval->value) && bond->params.arp_interval) {
-		netdev_dbg(bond->dev, "%s mode is incompatible with arp monitoring, start mii monitoring\n",
-			   newval->string);
-		/* disable arp monitoring */
-		bond->params.arp_interval = 0;
-		/* set miimon to default value */
-		bond->params.miimon = BOND_DEFAULT_MIIMON;
-		netdev_dbg(bond->dev, "Setting MII monitoring interval to %d\n",
-			   bond->params.miimon);
+	if (!bond_mode_uses_arp(newval->value)) {
+		if (bond->params.arp_interval) {
+			netdev_dbg(bond->dev, "%s mode is incompatible with arp monitoring, start mii monitoring\n",
+				   newval->string);
+			/* disable arp monitoring */
+			bond->params.arp_interval = 0;
+		}
+
+		if (!bond->params.miimon) {
+			/* set miimon to default value */
+			bond->params.miimon = BOND_DEFAULT_MIIMON;
+			netdev_dbg(bond->dev, "Setting MII monitoring interval to %d\n",
+				   bond->params.miimon);
+		}
 	}
 
 	if (newval->value == BOND_MODE_ALB)
-- 
2.17.1


From 8cb06fe728227a8daf71f0f9fc16e7acecd85c0a Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 23 Jul 2018 16:50:48 +0200
Subject: [PATCH 02/25] ip: hash fragments consistently

[ Upstream commit 3dd1c9a1270736029ffca670e9bd0265f4120600 ]

The skb hash for locally generated ip[v6] fragments belonging
to the same datagram can vary in several circumstances:
* for connected UDP[v6] sockets, the first fragment get its hash
  via set_owner_w()/skb_set_hash_from_sk()
* for unconnected IPv6 UDPv6 sockets, the first fragment can get
  its hash via ip6_make_flowlabel()/skb_get_hash_flowi6(), if
  auto_flowlabel is enabled

For the following frags the hash is usually computed via
skb_get_hash().
The above can cause OoO for unconnected IPv6 UDPv6 socket: in that
scenario the egress tx queue can be selected on a per packet basis
via the skb hash.
It may also fool flow-oriented schedulers to place fragments belonging
to the same datagram in different flows.

Fix the issue by copying the skb hash from the head frag into
the others at fragmentation time.

Before this commit:
perf probe -a "dev_queue_xmit skb skb->hash skb->l4_hash:b1@0/8 skb->sw_hash:b1@1/8"
netperf -H $IPV4 -t UDP_STREAM -l 5 -- -m 2000 -n &
perf record -e probe:dev_queue_xmit -e probe:skb_set_owner_w -a sleep 0.1
perf script
probe:dev_queue_xmit: (ffffffff8c6b1b20) hash=3713014309 l4_hash=1 sw_hash=0
probe:dev_queue_xmit: (ffffffff8c6b1b20) hash=0 l4_hash=0 sw_hash=0

After this commit:
probe:dev_queue_xmit: (ffffffff8c6b1b20) hash=2171763177 l4_hash=1 sw_hash=0
probe:dev_queue_xmit: (ffffffff8c6b1b20) hash=2171763177 l4_hash=1 sw_hash=0

Fixes: b73c3d0e4f0e ("net: Save TX flow hash in sock and set in skbuf on xmit")
Fixes: 67800f9b1f4e ("ipv6: Call skb_get_hash_flowi6 to get skb->hash in ip6_make_flowlabel")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_output.c  | 2 ++
 net/ipv6/ip6_output.c | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 63d5d66e040a..e2dd325bed9b 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -523,6 +523,8 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	to->dev = from->dev;
 	to->mark = from->mark;
 
+	skb_copy_hash(to, from);
+
 	/* Copy the flags to each fragment. */
 	IPCB(to)->flags = IPCB(from)->flags;
 
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 32fcce711855..1da021527fcd 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -595,6 +595,8 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	to->dev = from->dev;
 	to->mark = from->mark;
 
+	skb_copy_hash(to, from);
+
 #ifdef CONFIG_NET_SCHED
 	to->tc_index = from->tc_index;
 #endif
-- 
2.17.1


From b9934e72403c450b5d892e2fe0f80492097efa3d Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Mon, 23 Jul 2018 19:36:48 -0400
Subject: [PATCH 03/25] ip: in cmsg IP(V6)_ORIGDSTADDR call pskb_may_pull

[ Upstream commit 2efd4fca703a6707cad16ab486eaab8fc7f0fd49 ]

Syzbot reported a read beyond the end of the skb head when returning
IPV6_ORIGDSTADDR:

  BUG: KMSAN: kernel-infoleak in put_cmsg+0x5ef/0x860 net/core/scm.c:242
  CPU: 0 PID: 4501 Comm: syz-executor128 Not tainted 4.17.0+ #9
  Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
  Google 01/01/2011
  Call Trace:
    __dump_stack lib/dump_stack.c:77 [inline]
    dump_stack+0x185/0x1d0 lib/dump_stack.c:113
    kmsan_report+0x188/0x2a0 mm/kmsan/kmsan.c:1125
    kmsan_internal_check_memory+0x138/0x1f0 mm/kmsan/kmsan.c:1219
    kmsan_copy_to_user+0x7a/0x160 mm/kmsan/kmsan.c:1261
    copy_to_user include/linux/uaccess.h:184 [inline]
    put_cmsg+0x5ef/0x860 net/core/scm.c:242
    ip6_datagram_recv_specific_ctl+0x1cf3/0x1eb0 net/ipv6/datagram.c:719
    ip6_datagram_recv_ctl+0x41c/0x450 net/ipv6/datagram.c:733
    rawv6_recvmsg+0x10fb/0x1460 net/ipv6/raw.c:521
    [..]

This logic and its ipv4 counterpart read the destination port from
the packet at skb_transport_offset(skb) + 4.

With MSG_MORE and a local SOCK_RAW sender, syzbot was able to cook a
packet that stores headers exactly up to skb_transport_offset(skb) in
the head and the remainder in a frag.

Call pskb_may_pull before accessing the pointer to ensure that it lies
in skb head.

Link: http://lkml.kernel.org/r/CAF=yD-LEJwZj5a1-bAAj2Oy_hKmGygV6rsJ_WOrAYnv-fnayiQ@mail.gmail.com
Reported-by: syzbot+9adb4b567003cac781f0@syzkaller.appspotmail.com
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_sockglue.c | 7 +++++--
 net/ipv6/datagram.c    | 7 +++++--
 2 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index d07ba4d5917b..048d5f6dd320 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -148,15 +148,18 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
 {
 	struct sockaddr_in sin;
 	const struct iphdr *iph = ip_hdr(skb);
-	__be16 *ports = (__be16 *)skb_transport_header(skb);
+	__be16 *ports;
+	int end;
 
-	if (skb_transport_offset(skb) + 4 > (int)skb->len)
+	end = skb_transport_offset(skb) + 4;
+	if (end > 0 && !pskb_may_pull(skb, end))
 		return;
 
 	/* All current transport protocols have the port numbers in the
 	 * first four bytes of the transport header and this function is
 	 * written with this assumption in mind.
 	 */
+	ports = (__be16 *)skb_transport_header(skb);
 
 	sin.sin_family = AF_INET;
 	sin.sin_addr.s_addr = iph->daddr;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 453dc3726199..461825e0680f 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -708,13 +708,16 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg,
 	}
 	if (np->rxopt.bits.rxorigdstaddr) {
 		struct sockaddr_in6 sin6;
-		__be16 *ports = (__be16 *) skb_transport_header(skb);
+		__be16 *ports;
+		int end;
 
-		if (skb_transport_offset(skb) + 4 <= (int)skb->len) {
+		end = skb_transport_offset(skb) + 4;
+		if (end <= 0 || pskb_may_pull(skb, end)) {
 			/* All current transport protocols have the port numbers in the
 			 * first four bytes of the transport header and this function is
 			 * written with this assumption in mind.
 			 */
+			ports = (__be16 *)skb_transport_header(skb);
 
 			sin6.sin6_family = AF_INET6;
 			sin6.sin6_addr = ipv6_hdr(skb)->daddr;
-- 
2.17.1


From 25eda3e422b7087567c9f0f1f0b84b846112fdc6 Mon Sep 17 00:00:00 2001
From: Jack Morgenstein <jackm@dev.mellanox.co.il>
Date: Tue, 24 Jul 2018 14:27:55 +0300
Subject: [PATCH 04/25] net/mlx4_core: Save the qpn from the input modifier in
 RST2INIT wrapper

[ Upstream commit 958c696f5a7274d9447a458ad7aa70719b29a50a ]

Function mlx4_RST2INIT_QP_wrapper saved the qp number passed in the qp
context, rather than the one passed in the input modifier.

However, the qp number in the qp context is not defined as a
required parameter by the FW. Therefore, drivers may choose to not
specify the qp number in the qp context for the reset-to-init transition.

Thus, we must save the qp number passed in the command input modifier --
which is always present. (This saved qp number is used as the input
modifier for command 2RST_QP when a slave's qp's are destroyed).

Fixes: c82e9aa0a8bc ("mlx4_core: resource tracking for HCA resources used by guests")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/resource_tracker.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index a069fcc823c3..b26da0952a4d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -2957,7 +2957,7 @@ int mlx4_RST2INIT_QP_wrapper(struct mlx4_dev *dev, int slave,
 	u32 srqn = qp_get_srqn(qpc) & 0xffffff;
 	int use_srq = (qp_get_srqn(qpc) >> 24) & 1;
 	struct res_srq *srq;
-	int local_qpn = be32_to_cpu(qpc->local_qpn) & 0xffffff;
+	int local_qpn = vhcr->in_modifier & 0xffffff;
 
 	err = adjust_qp_sched_queue(dev, slave, qpc, inbox);
 	if (err)
-- 
2.17.1


From 04f2b92cdb200d18f08ba012ea4cdf28c7930418 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 19 Jul 2018 16:04:38 -0700
Subject: [PATCH 05/25] net: skb_segment() should not return NULL

[ Upstream commit ff907a11a0d68a749ce1a321f4505c03bf72190c ]

syzbot caught a NULL deref [1], caused by skb_segment()

skb_segment() has many "goto err;" that assume the @err variable
contains -ENOMEM.

A successful call to __skb_linearize() should not clear @err,
otherwise a subsequent memory allocation error could return NULL.

While we are at it, we might use -EINVAL instead of -ENOMEM when
MAX_SKB_FRAGS limit is reached.

[1]
kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] SMP KASAN
CPU: 0 PID: 13285 Comm: syz-executor3 Not tainted 4.18.0-rc4+ #146
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:tcp_gso_segment+0x3dc/0x1780 net/ipv4/tcp_offload.c:106
Code: f0 ff ff 0f 87 1c fd ff ff e8 00 88 0b fb 48 8b 75 d0 48 b9 00 00 00 00 00 fc ff df 48 8d be 90 00 00 00 48 89 f8 48 c1 e8 03 <0f> b6 14 08 48 8d 86 94 00 00 00 48 89 c6 83 e0 07 48 c1 ee 03 0f
RSP: 0018:ffff88019b7fd060 EFLAGS: 00010206
RAX: 0000000000000012 RBX: 0000000000000020 RCX: dffffc0000000000
RDX: 0000000000040000 RSI: 0000000000000000 RDI: 0000000000000090
RBP: ffff88019b7fd0f0 R08: ffff88019510e0c0 R09: ffffed003b5c46d6
R10: ffffed003b5c46d6 R11: ffff8801dae236b3 R12: 0000000000000001
R13: ffff8801d6c581f4 R14: 0000000000000000 R15: ffff8801d6c58128
FS:  00007fcae64d6700(0000) GS:ffff8801dae00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000004e8664 CR3: 00000001b669b000 CR4: 00000000001406f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 tcp4_gso_segment+0x1c3/0x440 net/ipv4/tcp_offload.c:54
 inet_gso_segment+0x64e/0x12d0 net/ipv4/af_inet.c:1342
 inet_gso_segment+0x64e/0x12d0 net/ipv4/af_inet.c:1342
 skb_mac_gso_segment+0x3b5/0x740 net/core/dev.c:2792
 __skb_gso_segment+0x3c3/0x880 net/core/dev.c:2865
 skb_gso_segment include/linux/netdevice.h:4099 [inline]
 validate_xmit_skb+0x640/0xf30 net/core/dev.c:3104
 __dev_queue_xmit+0xc14/0x3910 net/core/dev.c:3561
 dev_queue_xmit+0x17/0x20 net/core/dev.c:3602
 neigh_hh_output include/net/neighbour.h:473 [inline]
 neigh_output include/net/neighbour.h:481 [inline]
 ip_finish_output2+0x1063/0x1860 net/ipv4/ip_output.c:229
 ip_finish_output+0x841/0xfa0 net/ipv4/ip_output.c:317
 NF_HOOK_COND include/linux/netfilter.h:276 [inline]
 ip_output+0x223/0x880 net/ipv4/ip_output.c:405
 dst_output include/net/dst.h:444 [inline]
 ip_local_out+0xc5/0x1b0 net/ipv4/ip_output.c:124
 iptunnel_xmit+0x567/0x850 net/ipv4/ip_tunnel_core.c:91
 ip_tunnel_xmit+0x1598/0x3af1 net/ipv4/ip_tunnel.c:778
 ipip_tunnel_xmit+0x264/0x2c0 net/ipv4/ipip.c:308
 __netdev_start_xmit include/linux/netdevice.h:4148 [inline]
 netdev_start_xmit include/linux/netdevice.h:4157 [inline]
 xmit_one net/core/dev.c:3034 [inline]
 dev_hard_start_xmit+0x26c/0xc30 net/core/dev.c:3050
 __dev_queue_xmit+0x29ef/0x3910 net/core/dev.c:3569
 dev_queue_xmit+0x17/0x20 net/core/dev.c:3602
 neigh_direct_output+0x15/0x20 net/core/neighbour.c:1403
 neigh_output include/net/neighbour.h:483 [inline]
 ip_finish_output2+0xa67/0x1860 net/ipv4/ip_output.c:229
 ip_finish_output+0x841/0xfa0 net/ipv4/ip_output.c:317
 NF_HOOK_COND include/linux/netfilter.h:276 [inline]
 ip_output+0x223/0x880 net/ipv4/ip_output.c:405
 dst_output include/net/dst.h:444 [inline]
 ip_local_out+0xc5/0x1b0 net/ipv4/ip_output.c:124
 ip_queue_xmit+0x9df/0x1f80 net/ipv4/ip_output.c:504
 tcp_transmit_skb+0x1bf9/0x3f10 net/ipv4/tcp_output.c:1168
 tcp_write_xmit+0x1641/0x5c20 net/ipv4/tcp_output.c:2363
 __tcp_push_pending_frames+0xb2/0x290 net/ipv4/tcp_output.c:2536
 tcp_push+0x638/0x8c0 net/ipv4/tcp.c:735
 tcp_sendmsg_locked+0x2ec5/0x3f00 net/ipv4/tcp.c:1410
 tcp_sendmsg+0x2f/0x50 net/ipv4/tcp.c:1447
 inet_sendmsg+0x1a1/0x690 net/ipv4/af_inet.c:798
 sock_sendmsg_nosec net/socket.c:641 [inline]
 sock_sendmsg+0xd5/0x120 net/socket.c:651
 __sys_sendto+0x3d7/0x670 net/socket.c:1797
 __do_sys_sendto net/socket.c:1809 [inline]
 __se_sys_sendto net/socket.c:1805 [inline]
 __x64_sys_sendto+0xe1/0x1a0 net/socket.c:1805
 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x455ab9
Code: 1d ba fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 eb b9 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007fcae64d5c68 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 00007fcae64d66d4 RCX: 0000000000455ab9
RDX: 0000000000000001 RSI: 0000000020000200 RDI: 0000000000000013
RBP: 000000000072bea0 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000014
R13: 00000000004c1145 R14: 00000000004d1818 R15: 0000000000000006
Modules linked in:
Dumping ftrace buffer:
   (ftrace buffer empty)

Fixes: ddff00d42043 ("net: Move skb_has_shared_frag check out of GRE code and into segmentation")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 23041b5c0b27..2e5eeba97de9 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3675,6 +3675,7 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 				net_warn_ratelimited(
 					"skb_segment: too many frags: %u %u\n",
 					pos, mss);
+				err = -EINVAL;
 				goto err;
 			}
 
@@ -3713,11 +3714,10 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 
 perform_csum_check:
 		if (!csum) {
-			if (skb_has_shared_frag(nskb)) {
-				err = __skb_linearize(nskb);
-				if (err)
-					goto err;
-			}
+			if (skb_has_shared_frag(nskb) &&
+			    __skb_linearize(nskb))
+				goto err;
+
 			if (!nskb->remcsum_offload)
 				nskb->ip_summed = CHECKSUM_NONE;
 			SKB_GSO_CB(nskb)->csum =
-- 
2.17.1


From 32bd9a99f422d6663fef9b773ec9b3fb710ccb02 Mon Sep 17 00:00:00 2001
From: Ariel Levkovich <lariel@mellanox.com>
Date: Mon, 25 Jun 2018 19:12:02 +0300
Subject: [PATCH 06/25] net/mlx5: Adjust clock overflow work period

[ Upstream commit 33180bee86a8940a84950edca46315cd9dd6deb5 ]

When driver converts HW timestamp to wall clock time it subtracts
the last saved cycle counter from the HW timestamp and converts the
difference to nanoseconds.
The conversion is done by multiplying the cycles difference with the
clock multiplier value as a first step and therefore the cycles
difference should be small enough so that the multiplication product
doesn't exceed 64bit.

The overflow handling routine is in charge of updating the last saved
cycle counter in driver and it is called periodically using kernel
delayed workqueue.

The delay period for this work is calculated using the max HW cycle
counter value (a 41 bit mask) as a base which doesn't take the 64bit
limit into account so the delay period may be incorrect and too
long to prevent a large difference between the HW counter and the last
saved counter in SW.

This change adjusts the work period for the HW clock overflow work by
taking the minimum between the previous value and the quotient of max
u64 value and the clock multiplier value.

Fixes: ef9814deafd0 ("net/mlx5e: Add HW timestamping (TS) support")
Signed-off-by: Ariel Levkovich <lariel@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_clock.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
index 84dd63e74041..27040009d87a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
@@ -545,6 +545,7 @@ void mlx5e_pps_event_handler(struct mlx5e_priv *priv,
 void mlx5e_timestamp_init(struct mlx5e_priv *priv)
 {
 	struct mlx5e_tstamp *tstamp = &priv->tstamp;
+	u64 overflow_cycles;
 	u64 ns;
 	u64 frac = 0;
 	u32 dev_freq;
@@ -569,10 +570,17 @@ void mlx5e_timestamp_init(struct mlx5e_priv *priv)
 
 	/* Calculate period in seconds to call the overflow watchdog - to make
 	 * sure counter is checked at least once every wrap around.
+	 * The period is calculated as the minimum between max HW cycles count
+	 * (The clock source mask) and max amount of cycles that can be
+	 * multiplied by clock multiplier where the result doesn't exceed
+	 * 64bits.
 	 */
-	ns = cyclecounter_cyc2ns(&tstamp->cycles, tstamp->cycles.mask,
+	overflow_cycles = div64_u64(~0ULL >> 1, tstamp->cycles.mult);
+	overflow_cycles = min(overflow_cycles, tstamp->cycles.mask >> 1);
+
+	ns = cyclecounter_cyc2ns(&tstamp->cycles, overflow_cycles,
 				 frac, &frac);
-	do_div(ns, NSEC_PER_SEC / 2 / HZ);
+	do_div(ns, NSEC_PER_SEC / HZ);
 	tstamp->overflow_period = ns;
 
 	INIT_WORK(&tstamp->pps_info.out_work, mlx5e_pps_out);
-- 
2.17.1


From c9036ba0243b457dfb73a36b7924f36e43721e9b Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Sun, 8 Jul 2018 14:52:12 +0300
Subject: [PATCH 07/25] net/mlx5e: Don't allow aRFS for encapsulated packets

[ Upstream commit d2e1c57bcf9a07cbb67f30ecf238f298799bce1c ]

Driver is yet to support aRFS for encapsulated packets, return early
error in such case.

Fixes: 18c908e477dc ("net/mlx5e: Add accelerated RFS support")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
index 12d3ced61114..0f0c1d7b80c0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
@@ -711,6 +711,9 @@ int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 	    skb->protocol != htons(ETH_P_IPV6))
 		return -EPROTONOSUPPORT;
 
+	if (skb->encapsulation)
+		return -EPROTONOSUPPORT;
+
 	arfs_t = arfs_get_table(arfs, arfs_get_ip_proto(skb), skb->protocol);
 	if (!arfs_t)
 		return -EPROTONOSUPPORT;
-- 
2.17.1


From ae6041f20e94a63ff2f091825e8b4a5d9f632f7f Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Sun, 8 Jul 2018 13:08:55 +0300
Subject: [PATCH 08/25] net/mlx5e: Fix quota counting in aRFS expire flow

[ Upstream commit 2630bae8018823c3b88788b69fb9f16ea3b4a11e ]

Quota should follow the amount of rules which do expire, and not the
number of rules that were examined, fixed that.

Fixes: 18c908e477dc ("net/mlx5e: Add accelerated RFS support")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
index 0f0c1d7b80c0..e87923e046c9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
@@ -381,14 +381,14 @@ static void arfs_may_expire_flow(struct mlx5e_priv *priv)
 	HLIST_HEAD(del_list);
 	spin_lock_bh(&priv->fs.arfs.arfs_lock);
 	mlx5e_for_each_arfs_rule(arfs_rule, htmp, priv->fs.arfs.arfs_tables, i, j) {
-		if (quota++ > MLX5E_ARFS_EXPIRY_QUOTA)
-			break;
 		if (!work_pending(&arfs_rule->arfs_work) &&
 		    rps_may_expire_flow(priv->netdev,
 					arfs_rule->rxq, arfs_rule->flow_id,
 					arfs_rule->filter_id)) {
 			hlist_del_init(&arfs_rule->hlist);
 			hlist_add_head(&arfs_rule->hlist, &del_list);
+			if (quota++ > MLX5E_ARFS_EXPIRY_QUOTA)
+				break;
 		}
 	}
 	spin_unlock_bh(&priv->fs.arfs.arfs_lock);
-- 
2.17.1


From 2322aae35fca352c84923711d68612440a6ebec7 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Thu, 19 Jul 2018 12:41:18 -0700
Subject: [PATCH 09/25] net/ipv6: Fix linklocal to global address with VRF

[ Upstream commit 24b711edfc34bc45777a3f068812b7d1ed004a5d ]

Example setup:
    host: ip -6 addr add dev eth1 2001:db8:104::4
           where eth1 is enslaved to a VRF

    switch: ip -6 ro add 2001:db8:104::4/128 dev br1
            where br1 only has an LLA

           ping6 2001:db8:104::4
           ssh   2001:db8:104::4

(NOTE: UDP works fine if the PKTINFO has the address set to the global
address and ifindex is set to the index of eth1 with a destination an
LLA).

For ICMP, icmp6_iif needs to be updated to check if skb->dev is an
L3 master. If it is then return the ifindex from rt6i_idev similar
to what is done for loopback.

For TCP, restore the original tcp_v6_iif definition which is needed in
most places and add a new tcp_v6_iif_l3_slave that considers the
l3_slave variability. This latter check is only needed for socket
lookups.

Fixes: 9ff74384600a ("net: vrf: Handle ipv6 multicast and link-local addresses")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h   | 5 +++++
 net/ipv6/icmp.c     | 5 +++--
 net/ipv6/tcp_ipv6.c | 6 ++++--
 3 files changed, 12 insertions(+), 4 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index fb653736f335..3b49f3aafed7 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -857,6 +857,11 @@ struct tcp_skb_cb {
  * as TCP moves IP6CB into a different location in skb->cb[]
  */
 static inline int tcp_v6_iif(const struct sk_buff *skb)
+{
+	return TCP_SKB_CB(skb)->header.h6.iif;
+}
+
+static inline int tcp_v6_iif_l3_slave(const struct sk_buff *skb)
 {
 	bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags);
 
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 5acb54405b10..c5f2b17b7ee1 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -405,9 +405,10 @@ static int icmp6_iif(const struct sk_buff *skb)
 
 	/* for local traffic to local address, skb dev is the loopback
 	 * device. Check if there is a dst attached to the skb and if so
-	 * get the real device index.
+	 * get the real device index. Same is needed for replies to a link
+	 * local address on a device enslaved to an L3 master device
 	 */
-	if (unlikely(iif == LOOPBACK_IFINDEX)) {
+	if (unlikely(iif == LOOPBACK_IFINDEX || netif_is_l3_master(skb->dev))) {
 		const struct rt6_info *rt6 = skb_rt6_info(skb);
 
 		if (rt6)
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 35e8aef9ceed..ba8586aadffa 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -918,7 +918,8 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
 					   &tcp_hashinfo, NULL, 0,
 					   &ipv6h->saddr,
 					   th->source, &ipv6h->daddr,
-					   ntohs(th->source), tcp_v6_iif(skb),
+					   ntohs(th->source),
+					   tcp_v6_iif_l3_slave(skb),
 					   tcp_v6_sdif(skb));
 		if (!sk1)
 			goto out;
@@ -1573,7 +1574,8 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 					    skb, __tcp_hdrlen(th),
 					    &ipv6_hdr(skb)->saddr, th->source,
 					    &ipv6_hdr(skb)->daddr,
-					    ntohs(th->dest), tcp_v6_iif(skb),
+					    ntohs(th->dest),
+					    tcp_v6_iif_l3_slave(skb),
 					    sdif);
 		if (sk2) {
 			struct inet_timewait_sock *tw = inet_twsk(sk);
-- 
2.17.1


From a35eb5072936f83d6564c172d59b928d467aa6b0 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Fri, 20 Jul 2018 14:04:27 +0800
Subject: [PATCH 10/25] multicast: do not restore deleted record source filter
 mode to new one

There are two scenarios that we will restore deleted records. The first is
when device down and up(or unmap/remap). In this scenario the new filter
mode is same with previous one. Because we get it from in_dev->mc_list and
we do not touch it during device down and up.

The other scenario is when a new socket join a group which was just delete
and not finish sending status reports. In this scenario, we should use the
current filter mode instead of restore old one. Here are 4 cases in total.

old_socket        new_socket       before_fix       after_fix
  IN(A)             IN(A)           ALLOW(A)         ALLOW(A)
  IN(A)             EX( )           TO_IN( )         TO_EX( )
  EX( )             IN(A)           TO_EX( )         ALLOW(A)
  EX( )             EX( )           TO_EX( )         TO_EX( )

Fixes: 24803f38a5c0b (igmp: do not remove igmp souce list info when set link down)
Fixes: 1666d49e1d416 (mld: do not remove mld souce list info when set link down)
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/igmp.c  | 3 +--
 net/ipv6/mcast.c | 3 +--
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index fbeb35ad804b..502aae3e3ab8 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -1201,8 +1201,7 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im)
 	if (pmc) {
 		im->interface = pmc->interface;
 		im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
-		im->sfmode = pmc->sfmode;
-		if (pmc->sfmode == MCAST_INCLUDE) {
+		if (im->sfmode == MCAST_INCLUDE) {
 			im->tomb = pmc->tomb;
 			im->sources = pmc->sources;
 			for (psf = im->sources; psf; psf = psf->sf_next)
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 9a38a2c641fa..6fd913d63835 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -771,8 +771,7 @@ static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im)
 	if (pmc) {
 		im->idev = pmc->idev;
 		im->mca_crcount = idev->mc_qrv;
-		im->mca_sfmode = pmc->mca_sfmode;
-		if (pmc->mca_sfmode == MCAST_INCLUDE) {
+		if (im->mca_sfmode == MCAST_INCLUDE) {
 			im->mca_tomb = pmc->mca_tomb;
 			im->mca_sources = pmc->mca_sources;
 			for (psf = im->mca_sources; psf; psf = psf->sf_next)
-- 
2.17.1


From ade80c8ab07f5d3fd146d9f6b5cef88e57ca8f5e Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 19 Jul 2018 08:15:16 +0200
Subject: [PATCH 11/25] net: phy: consider PHY_IGNORE_INTERRUPT in
 phy_start_aneg_priv

[ Upstream commit 215d08a85b9acf5e1fe9dbf50f1774cde333efef ]

The situation described in the comment can occur also with
PHY_IGNORE_INTERRUPT, therefore change the condition to include it.

Fixes: f555f34fdc58 ("net: phy: fix auto-negotiation stall due to unavailable interrupt")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index dba6d17ad885..47d2ef2fb9b3 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -511,7 +511,7 @@ static int phy_start_aneg_priv(struct phy_device *phydev, bool sync)
 	 * negotiation may already be done and aneg interrupt may not be
 	 * generated.
 	 */
-	if (phy_interrupt_is_valid(phydev) && (phydev->state == PHY_AN)) {
+	if (phydev->irq != PHY_POLL && phydev->state == PHY_AN) {
 		err = phy_aneg_done(phydev);
 		if (err > 0) {
 			trigger = true;
-- 
2.17.1


From a60e2b83b88ada9ae8b04499f04cbfc22a10be56 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Mon, 23 Jul 2018 22:37:54 +0200
Subject: [PATCH 12/25] sock: fix sg page frag coalescing in sk_alloc_sg

[ Upstream commit 144fe2bfd236dc814eae587aea7e2af03dbdd755 ]

Current sg coalescing logic in sk_alloc_sg() (latter is used by tls and
sockmap) is not quite correct in that we do fetch the previous sg entry,
however the subsequent check whether the refilled page frag from the
socket is still the same as from the last entry with prior offset and
length matching the start of the current buffer is comparing always the
first sg list entry instead of the prior one.

Fixes: 3c4d7559159b ("tls: kernel TLS support")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Dave Watson <davejwatson@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 8ee4e667a414..fb79caf56d0e 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -135,9 +135,10 @@ static int alloc_sg(struct sock *sk, int len, struct scatterlist *sg,
 		pfrag->offset += use;
 
 		sge = sg + num_elem - 1;
-		if (num_elem > first_coalesce && sg_page(sg) == pfrag->page &&
-		    sg->offset + sg->length == orig_offset) {
-			sg->length += use;
+
+		if (num_elem > first_coalesce && sg_page(sge) == pfrag->page &&
+		    sge->offset + sge->length == orig_offset) {
+			sge->length += use;
 		} else {
 			sge++;
 			sg_unmark_end(sge);
-- 
2.17.1


From 0fa9e5dac236b3b00d5231efe9ec0ce35b7eb184 Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Fri, 20 Jul 2018 13:21:01 -0700
Subject: [PATCH 13/25] rtnetlink: add rtnl_link_state check in
 rtnl_configure_link

[ Upstream commit 5025f7f7d506fba9b39e7fe8ca10f6f34cb9bc2d ]

rtnl_configure_link sets dev->rtnl_link_state to
RTNL_LINK_INITIALIZED and unconditionally calls
__dev_notify_flags to notify user-space of dev flags.

current call sequence for rtnl_configure_link
rtnetlink_newlink
    rtnl_link_ops->newlink
    rtnl_configure_link (unconditionally notifies userspace of
                         default and new dev flags)

If a newlink handler wants to call rtnl_configure_link
early, we will end up with duplicate notifications to
user-space.

This patch fixes rtnl_configure_link to check rtnl_link_state
and call __dev_notify_flags with gchanges = 0 if already
RTNL_LINK_INITIALIZED.

Later in the series, this patch will help the following sequence
where a driver implementing newlink can call rtnl_configure_link
to initialize the link early.

makes the following call sequence work:
rtnetlink_newlink
    rtnl_link_ops->newlink (vxlan) -> rtnl_configure_link (initializes
                                                link and notifies
                                                user-space of default
                                                dev flags)
    rtnl_configure_link (updates dev flags if requested by user ifm
                         and notifies user-space of new dev flags)

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 4cfdad08aca0..efe396cc77b5 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2402,9 +2402,12 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm)
 			return err;
 	}
 
-	dev->rtnl_link_state = RTNL_LINK_INITIALIZED;
-
-	__dev_notify_flags(dev, old_flags, ~0U);
+	if (dev->rtnl_link_state == RTNL_LINK_INITIALIZED) {
+		__dev_notify_flags(dev, old_flags, 0U);
+	} else {
+		dev->rtnl_link_state = RTNL_LINK_INITIALIZED;
+		__dev_notify_flags(dev, old_flags, ~0U);
+	}
 	return 0;
 }
 EXPORT_SYMBOL(rtnl_configure_link);
-- 
2.17.1


From a0612989dfd4fef5c7a7f9b5e38fb66fd92ccfed Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Fri, 20 Jul 2018 13:21:02 -0700
Subject: [PATCH 14/25] vxlan: add new fdb alloc and create helpers

[ Upstream commit 7431016b107c95cb5b2014aa1901fcb115f746bc ]

- Add new vxlan_fdb_alloc helper
- rename existing vxlan_fdb_create into vxlan_fdb_update:
        because it really creates or updates an existing
        fdb entry
- move new fdb creation into a separate vxlan_fdb_create

Main motivation for this change is to introduce the ability
to decouple vxlan fdb creation and notify, used in a later patch.

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 91 ++++++++++++++++++++++++++++++---------------
 1 file changed, 62 insertions(+), 29 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index bbdb46916dc3..d72c24d504d8 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -636,8 +636,61 @@ static int vxlan_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff)
 	return eth_gro_complete(skb, nhoff + sizeof(struct vxlanhdr));
 }
 
-/* Add new entry to forwarding table -- assumes lock held */
+static struct vxlan_fdb *vxlan_fdb_alloc(struct vxlan_dev *vxlan,
+					 const u8 *mac, __u16 state,
+					 __be32 src_vni, __u8 ndm_flags)
+{
+	struct vxlan_fdb *f;
+
+	f = kmalloc(sizeof(*f), GFP_ATOMIC);
+	if (!f)
+		return NULL;
+	f->state = state;
+	f->flags = ndm_flags;
+	f->updated = f->used = jiffies;
+	f->vni = src_vni;
+	INIT_LIST_HEAD(&f->remotes);
+	memcpy(f->eth_addr, mac, ETH_ALEN);
+
+	return f;
+}
+
 static int vxlan_fdb_create(struct vxlan_dev *vxlan,
+			    const u8 *mac, union vxlan_addr *ip,
+			    __u16 state, __be16 port, __be32 src_vni,
+			    __be32 vni, __u32 ifindex, __u8 ndm_flags,
+			    struct vxlan_fdb **fdb)
+{
+	struct vxlan_rdst *rd = NULL;
+	struct vxlan_fdb *f;
+	int rc;
+
+	if (vxlan->cfg.addrmax &&
+	    vxlan->addrcnt >= vxlan->cfg.addrmax)
+		return -ENOSPC;
+
+	netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip);
+	f = vxlan_fdb_alloc(vxlan, mac, state, src_vni, ndm_flags);
+	if (!f)
+		return -ENOMEM;
+
+	rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd);
+	if (rc < 0) {
+		kfree(f);
+		return rc;
+	}
+
+	++vxlan->addrcnt;
+	hlist_add_head_rcu(&f->hlist,
+			   vxlan_fdb_head(vxlan, mac, src_vni));
+
+	*fdb = f;
+
+	return 0;
+}
+
+/* Add new entry to forwarding table -- assumes lock held */
+static int vxlan_fdb_update(struct vxlan_dev *vxlan,
 			    const u8 *mac, union vxlan_addr *ip,
 			    __u16 state, __u16 flags,
 			    __be16 port, __be32 src_vni, __be32 vni,
@@ -687,37 +740,17 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan,
 		if (!(flags & NLM_F_CREATE))
 			return -ENOENT;
 
-		if (vxlan->cfg.addrmax &&
-		    vxlan->addrcnt >= vxlan->cfg.addrmax)
-			return -ENOSPC;
-
 		/* Disallow replace to add a multicast entry */
 		if ((flags & NLM_F_REPLACE) &&
 		    (is_multicast_ether_addr(mac) || is_zero_ether_addr(mac)))
 			return -EOPNOTSUPP;
 
 		netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip);
-		f = kmalloc(sizeof(*f), GFP_ATOMIC);
-		if (!f)
-			return -ENOMEM;
-
-		notify = 1;
-		f->state = state;
-		f->flags = ndm_flags;
-		f->updated = f->used = jiffies;
-		f->vni = src_vni;
-		INIT_LIST_HEAD(&f->remotes);
-		memcpy(f->eth_addr, mac, ETH_ALEN);
-
-		rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd);
-		if (rc < 0) {
-			kfree(f);
+		rc = vxlan_fdb_create(vxlan, mac, ip, state, port, src_vni,
+				      vni, ifindex, ndm_flags, &f);
+		if (rc < 0)
 			return rc;
-		}
-
-		++vxlan->addrcnt;
-		hlist_add_head_rcu(&f->hlist,
-				   vxlan_fdb_head(vxlan, mac, src_vni));
+		notify = 1;
 	}
 
 	if (notify) {
@@ -863,7 +896,7 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 		return -EAFNOSUPPORT;
 
 	spin_lock_bh(&vxlan->hash_lock);
-	err = vxlan_fdb_create(vxlan, addr, &ip, ndm->ndm_state, flags,
+	err = vxlan_fdb_update(vxlan, addr, &ip, ndm->ndm_state, flags,
 			       port, src_vni, vni, ifindex, ndm->ndm_flags);
 	spin_unlock_bh(&vxlan->hash_lock);
 
@@ -1006,7 +1039,7 @@ static bool vxlan_snoop(struct net_device *dev,
 
 		/* close off race between vxlan_flush and incoming packets */
 		if (netif_running(dev))
-			vxlan_fdb_create(vxlan, src_mac, src_ip,
+			vxlan_fdb_update(vxlan, src_mac, src_ip,
 					 NUD_REACHABLE,
 					 NLM_F_EXCL|NLM_F_CREATE,
 					 vxlan->cfg.dst_port,
@@ -3167,7 +3200,7 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev,
 
 	/* create an fdb entry for a valid default destination */
 	if (!vxlan_addr_any(&vxlan->default_dst.remote_ip)) {
-		err = vxlan_fdb_create(vxlan, all_zeros_mac,
+		err = vxlan_fdb_update(vxlan, all_zeros_mac,
 				       &vxlan->default_dst.remote_ip,
 				       NUD_REACHABLE | NUD_PERMANENT,
 				       NLM_F_EXCL | NLM_F_CREATE,
@@ -3441,7 +3474,7 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 					   old_dst.remote_ifindex, 0);
 
 		if (!vxlan_addr_any(&dst->remote_ip)) {
-			err = vxlan_fdb_create(vxlan, all_zeros_mac,
+			err = vxlan_fdb_update(vxlan, all_zeros_mac,
 					       &dst->remote_ip,
 					       NUD_REACHABLE | NUD_PERMANENT,
 					       NLM_F_CREATE | NLM_F_APPEND,
-- 
2.17.1


From c8a664e63b74143420ca547af7aea4d62dcaa5e5 Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Fri, 20 Jul 2018 13:21:03 -0700
Subject: [PATCH 15/25] vxlan: make netlink notify in vxlan_fdb_destroy
 optional

[ Upstream commit f6e053858671bb156b6e44ad66418acc8c7f4e77 ]

Add a new option do_notify to vxlan_fdb_destroy to make
sending netlink notify optional. Used by a later patch.

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index d72c24d504d8..5ee0f6d9f7bc 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -774,13 +774,15 @@ static void vxlan_fdb_free(struct rcu_head *head)
 	kfree(f);
 }
 
-static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f)
+static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f,
+			      bool do_notify)
 {
 	netdev_dbg(vxlan->dev,
 		    "delete %pM\n", f->eth_addr);
 
 	--vxlan->addrcnt;
-	vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_DELNEIGH);
+	if (do_notify)
+		vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_DELNEIGH);
 
 	hlist_del_rcu(&f->hlist);
 	call_rcu(&f->rcu, vxlan_fdb_free);
@@ -930,7 +932,7 @@ static int __vxlan_fdb_delete(struct vxlan_dev *vxlan,
 		goto out;
 	}
 
-	vxlan_fdb_destroy(vxlan, f);
+	vxlan_fdb_destroy(vxlan, f, true);
 
 out:
 	return 0;
@@ -2393,7 +2395,7 @@ static void vxlan_cleanup(unsigned long arg)
 					   "garbage collect %pM\n",
 					   f->eth_addr);
 				f->state = NUD_STALE;
-				vxlan_fdb_destroy(vxlan, f);
+				vxlan_fdb_destroy(vxlan, f, true);
 			} else if (time_before(timeout, next_timer))
 				next_timer = timeout;
 		}
@@ -2444,7 +2446,7 @@ static void vxlan_fdb_delete_default(struct vxlan_dev *vxlan, __be32 vni)
 	spin_lock_bh(&vxlan->hash_lock);
 	f = __vxlan_find_mac(vxlan, all_zeros_mac, vni);
 	if (f)
-		vxlan_fdb_destroy(vxlan, f);
+		vxlan_fdb_destroy(vxlan, f, true);
 	spin_unlock_bh(&vxlan->hash_lock);
 }
 
@@ -2498,7 +2500,7 @@ static void vxlan_flush(struct vxlan_dev *vxlan, bool do_all)
 				continue;
 			/* the all_zeros_mac entry is deleted at vxlan_uninit */
 			if (!is_zero_ether_addr(f->eth_addr))
-				vxlan_fdb_destroy(vxlan, f);
+				vxlan_fdb_destroy(vxlan, f, true);
 		}
 	}
 	spin_unlock_bh(&vxlan->hash_lock);
-- 
2.17.1


From 70c328c414abedb5b096fcce9dcf049eed36f201 Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Fri, 20 Jul 2018 13:21:04 -0700
Subject: [PATCH 16/25] vxlan: fix default fdb entry netlink notify ordering
 during netdev create

[ Upstream commit e99465b952861533d9ba748fdbecc96d9a36da3e ]

Problem:
In vxlan_newlink, a default fdb entry is added before register_netdev.
The default fdb creation function also notifies user-space of the
fdb entry on the vxlan device which user-space does not know about yet.
(RTM_NEWNEIGH goes before RTM_NEWLINK for the same ifindex).

This patch fixes the user-space netlink notification ordering issue
with the following changes:
- decouple fdb notify from fdb create.
- Move fdb notify after register_netdev.
- Call rtnl_configure_link in vxlan newlink handler to notify
userspace about the newlink before fdb notify and
hence avoiding the user-space race.

Fixes: afbd8bae9c79 ("vxlan: add implicit fdb entry for default destination")
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 29 +++++++++++++++++++++--------
 1 file changed, 21 insertions(+), 8 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 5ee0f6d9f7bc..13d39a72fe0d 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -3192,6 +3192,7 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev,
 {
 	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
 	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_fdb *f = NULL;
 	int err;
 
 	err = vxlan_dev_configure(net, dev, conf, false, extack);
@@ -3202,27 +3203,38 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev,
 
 	/* create an fdb entry for a valid default destination */
 	if (!vxlan_addr_any(&vxlan->default_dst.remote_ip)) {
-		err = vxlan_fdb_update(vxlan, all_zeros_mac,
+		err = vxlan_fdb_create(vxlan, all_zeros_mac,
 				       &vxlan->default_dst.remote_ip,
 				       NUD_REACHABLE | NUD_PERMANENT,
-				       NLM_F_EXCL | NLM_F_CREATE,
 				       vxlan->cfg.dst_port,
 				       vxlan->default_dst.remote_vni,
 				       vxlan->default_dst.remote_vni,
 				       vxlan->default_dst.remote_ifindex,
-				       NTF_SELF);
+				       NTF_SELF, &f);
 		if (err)
 			return err;
 	}
 
 	err = register_netdevice(dev);
+	if (err)
+		goto errout;
+
+	err = rtnl_configure_link(dev, NULL);
 	if (err) {
-		vxlan_fdb_delete_default(vxlan, vxlan->default_dst.remote_vni);
-		return err;
+		unregister_netdevice(dev);
+		goto errout;
 	}
 
+	/* notify default fdb entry */
+	if (f)
+		vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH);
+
 	list_add(&vxlan->next, &vn->vxlan_list);
 	return 0;
+errout:
+	if (f)
+		vxlan_fdb_destroy(vxlan, f, false);
+	return err;
 }
 
 static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[],
@@ -3451,6 +3463,7 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 	struct vxlan_rdst *dst = &vxlan->default_dst;
 	struct vxlan_rdst old_dst;
 	struct vxlan_config conf;
+	struct vxlan_fdb *f = NULL;
 	int err;
 
 	err = vxlan_nl2conf(tb, data,
@@ -3476,19 +3489,19 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 					   old_dst.remote_ifindex, 0);
 
 		if (!vxlan_addr_any(&dst->remote_ip)) {
-			err = vxlan_fdb_update(vxlan, all_zeros_mac,
+			err = vxlan_fdb_create(vxlan, all_zeros_mac,
 					       &dst->remote_ip,
 					       NUD_REACHABLE | NUD_PERMANENT,
-					       NLM_F_CREATE | NLM_F_APPEND,
 					       vxlan->cfg.dst_port,
 					       dst->remote_vni,
 					       dst->remote_vni,
 					       dst->remote_ifindex,
-					       NTF_SELF);
+					       NTF_SELF, &f);
 			if (err) {
 				spin_unlock_bh(&vxlan->hash_lock);
 				return err;
 			}
+			vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH);
 		}
 		spin_unlock_bh(&vxlan->hash_lock);
 	}
-- 
2.17.1


From f9410dc0907c06ad9a66a17b9e4c648220d8796e Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Thu, 12 Jul 2018 06:04:52 -0700
Subject: [PATCH 17/25] tcp: fix dctcp delayed ACK schedule

[ Upstream commit b0c05d0e99d98d7f0cd41efc1eeec94efdc3325d ]

Previously, when a data segment was sent an ACK was piggybacked
on the data segment without generating a CA_EVENT_NON_DELAYED_ACK
event to notify congestion control modules. So the DCTCP
ca->delayed_ack_reserved flag could incorrectly stay set when
in fact there were no delayed ACKs being reserved. This could result
in sending a special ECN notification ACK that carries an older
ACK sequence, when in fact there was no need for such an ACK.
DCTCP keeps track of the delayed ACK status with its own separate
state ca->delayed_ack_reserved. Previously it may accidentally cancel
the delayed ACK without updating this field upon sending a special
ACK that carries a older ACK sequence. This inconsistency would
lead to DCTCP receiver never acknowledging the latest data until the
sender times out and retry in some cases.

Packetdrill script (provided by Larry Brakmo)

0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
0.000 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
0.000 setsockopt(3, SOL_TCP, TCP_CONGESTION, "dctcp", 5) = 0
0.000 bind(3, ..., ...) = 0
0.000 listen(3, 1) = 0

0.100 < [ect0] SEW 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
0.100 > SE. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
0.110 < [ect0] . 1:1(0) ack 1 win 257
0.200 accept(3, ..., ...) = 4

0.200 < [ect0] . 1:1001(1000) ack 1 win 257
0.200 > [ect01] . 1:1(0) ack 1001

0.200 write(4, ..., 1) = 1
0.200 > [ect01] P. 1:2(1) ack 1001

0.200 < [ect0] . 1001:2001(1000) ack 2 win 257
0.200 write(4, ..., 1) = 1
0.200 > [ect01] P. 2:3(1) ack 2001

0.200 < [ect0] . 2001:3001(1000) ack 3 win 257
0.200 < [ect0] . 3001:4001(1000) ack 3 win 257
0.200 > [ect01] . 3:3(0) ack 4001

0.210 < [ce] P. 4001:4501(500) ack 3 win 257

+0.001 read(4, ..., 4500) = 4500
+0 write(4, ..., 1) = 1
+0 > [ect01] PE. 3:4(1) ack 4501

+0.010 < [ect0] W. 4501:5501(1000) ack 4 win 257
// Previously the ACK sequence below would be 4501, causing a long RTO
+0.040~+0.045 > [ect01] . 4:4(0) ack 5501   // delayed ack

+0.311 < [ect0] . 5501:6501(1000) ack 4 win 257  // More data
+0 > [ect01] . 4:4(0) ack 6501     // now acks everything

+0.500 < F. 9501:9501(0) ack 4 win 257

Reported-by: Larry Brakmo <brakmo@fb.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Lawrence Brakmo <brakmo@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_dctcp.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 5f5e5936760e..89f88b0d8167 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -134,7 +134,8 @@ static void dctcp_ce_state_0_to_1(struct sock *sk)
 	/* State has changed from CE=0 to CE=1 and delayed
 	 * ACK has not sent yet.
 	 */
-	if (!ca->ce_state && ca->delayed_ack_reserved) {
+	if (!ca->ce_state &&
+	    inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) {
 		u32 tmp_rcv_nxt;
 
 		/* Save current rcv_nxt. */
@@ -164,7 +165,8 @@ static void dctcp_ce_state_1_to_0(struct sock *sk)
 	/* State has changed from CE=1 to CE=0 and delayed
 	 * ACK has not sent yet.
 	 */
-	if (ca->ce_state && ca->delayed_ack_reserved) {
+	if (ca->ce_state &&
+	    inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) {
 		u32 tmp_rcv_nxt;
 
 		/* Save current rcv_nxt. */
-- 
2.17.1


From 173acd4e9f88f8320de743fa0674adc3e13effe9 Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Wed, 18 Jul 2018 13:56:34 -0700
Subject: [PATCH 18/25] tcp: helpers to send special DCTCP ack

[ Upstream commit 2987babb6982306509380fc11b450227a844493b ]

Refactor and create helpers to send the special ACK in DCTCP.

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 22 +++++++++++++++++-----
 1 file changed, 17 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index abae5196cd3a..c8da25f37ae4 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -984,8 +984,8 @@ static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb)
  * We are working here with either a clone of the original
  * SKB, or a fresh unique copy made by the retransmit engine.
  */
-static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
-			    gfp_t gfp_mask)
+static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
+			      int clone_it, gfp_t gfp_mask, u32 rcv_nxt)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	struct inet_sock *inet;
@@ -1057,7 +1057,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	th->source		= inet->inet_sport;
 	th->dest		= inet->inet_dport;
 	th->seq			= htonl(tcb->seq);
-	th->ack_seq		= htonl(tp->rcv_nxt);
+	th->ack_seq		= htonl(rcv_nxt);
 	*(((__be16 *)th) + 6)	= htons(((tcp_header_size >> 2) << 12) |
 					tcb->tcp_flags);
 
@@ -1135,6 +1135,13 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	return err;
 }
 
+static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
+			    gfp_t gfp_mask)
+{
+	return __tcp_transmit_skb(sk, skb, clone_it, gfp_mask,
+				  tcp_sk(sk)->rcv_nxt);
+}
+
 /* This routine just queues the buffer for sending.
  *
  * NOTE: probe0 timer is not checked, do not forget tcp_push_pending_frames,
@@ -3551,7 +3558,7 @@ void tcp_send_delayed_ack(struct sock *sk)
 }
 
 /* This routine sends an ack and also updates the window. */
-void tcp_send_ack(struct sock *sk)
+void __tcp_send_ack(struct sock *sk, u32 rcv_nxt)
 {
 	struct sk_buff *buff;
 
@@ -3586,7 +3593,12 @@ void tcp_send_ack(struct sock *sk)
 	skb_set_tcp_pure_ack(buff);
 
 	/* Send it off, this clears delayed acks for us. */
-	tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0);
+	__tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0, rcv_nxt);
+}
+
+void tcp_send_ack(struct sock *sk)
+{
+	__tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt);
 }
 EXPORT_SYMBOL_GPL(tcp_send_ack);
 
-- 
2.17.1


From 8ec492bb5a90ee0ddc479ba9c4d0599273b24ec6 Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Wed, 18 Jul 2018 13:56:35 -0700
Subject: [PATCH 19/25] tcp: do not cancel delay-AcK on DCTCP special ACK

[ Upstream commit 27cde44a259c380a3c09066fc4b42de7dde9b1ad ]

Currently when a DCTCP receiver delays an ACK and receive a
data packet with a different CE mark from the previous one's, it
sends two immediate ACKs acking previous and latest sequences
respectly (for ECN accounting).

Previously sending the first ACK may mark off the delayed ACK timer
(tcp_event_ack_sent). This may subsequently prevent sending the
second ACK to acknowledge the latest sequence (tcp_ack_snd_check).
The culprit is that tcp_send_ack() assumes it always acknowleges
the latest sequence, which is not true for the first special ACK.

The fix is to not make the assumption in tcp_send_ack and check the
actual ack sequence before cancelling the delayed ACK. Further it's
safer to pass the ack sequence number as a local variable into
tcp_send_ack routine, instead of intercepting tp->rcv_nxt to avoid
future bugs like this.

Reported-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h     |  1 +
 net/ipv4/tcp_dctcp.c  | 34 ++++------------------------------
 net/ipv4/tcp_output.c | 11 ++++++++---
 3 files changed, 13 insertions(+), 33 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 3b49f3aafed7..62af4ae27430 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -560,6 +560,7 @@ void tcp_send_fin(struct sock *sk);
 void tcp_send_active_reset(struct sock *sk, gfp_t priority);
 int tcp_send_synack(struct sock *);
 void tcp_push_one(struct sock *, unsigned int mss_now);
+void __tcp_send_ack(struct sock *sk, u32 rcv_nxt);
 void tcp_send_ack(struct sock *sk);
 void tcp_send_delayed_ack(struct sock *sk);
 void tcp_send_loss_probe(struct sock *sk);
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 89f88b0d8167..39d96d27ff94 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -135,21 +135,8 @@ static void dctcp_ce_state_0_to_1(struct sock *sk)
 	 * ACK has not sent yet.
 	 */
 	if (!ca->ce_state &&
-	    inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) {
-		u32 tmp_rcv_nxt;
-
-		/* Save current rcv_nxt. */
-		tmp_rcv_nxt = tp->rcv_nxt;
-
-		/* Generate previous ack with CE=0. */
-		tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
-		tp->rcv_nxt = ca->prior_rcv_nxt;
-
-		tcp_send_ack(sk);
-
-		/* Recover current rcv_nxt. */
-		tp->rcv_nxt = tmp_rcv_nxt;
-	}
+	    inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
+		__tcp_send_ack(sk, ca->prior_rcv_nxt);
 
 	ca->prior_rcv_nxt = tp->rcv_nxt;
 	ca->ce_state = 1;
@@ -166,21 +153,8 @@ static void dctcp_ce_state_1_to_0(struct sock *sk)
 	 * ACK has not sent yet.
 	 */
 	if (ca->ce_state &&
-	    inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) {
-		u32 tmp_rcv_nxt;
-
-		/* Save current rcv_nxt. */
-		tmp_rcv_nxt = tp->rcv_nxt;
-
-		/* Generate previous ack with CE=1. */
-		tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
-		tp->rcv_nxt = ca->prior_rcv_nxt;
-
-		tcp_send_ack(sk);
-
-		/* Recover current rcv_nxt. */
-		tp->rcv_nxt = tmp_rcv_nxt;
-	}
+	    inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
+		__tcp_send_ack(sk, ca->prior_rcv_nxt);
 
 	ca->prior_rcv_nxt = tp->rcv_nxt;
 	ca->ce_state = 0;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index c8da25f37ae4..3d8f6f342cb1 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -175,8 +175,13 @@ static void tcp_event_data_sent(struct tcp_sock *tp,
 }
 
 /* Account for an ACK we sent. */
-static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts)
+static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts,
+				      u32 rcv_nxt)
 {
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	if (unlikely(rcv_nxt != tp->rcv_nxt))
+		return;  /* Special ACK sent by DCTCP to reflect ECN */
 	tcp_dec_quickack_mode(sk, pkts);
 	inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
 }
@@ -1098,7 +1103,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 	icsk->icsk_af_ops->send_check(sk, skb);
 
 	if (likely(tcb->tcp_flags & TCPHDR_ACK))
-		tcp_event_ack_sent(sk, tcp_skb_pcount(skb));
+		tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt);
 
 	if (skb->len != tcp_header_size) {
 		tcp_event_data_sent(tp, sk);
@@ -3595,12 +3600,12 @@ void __tcp_send_ack(struct sock *sk, u32 rcv_nxt)
 	/* Send it off, this clears delayed acks for us. */
 	__tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0, rcv_nxt);
 }
+EXPORT_SYMBOL_GPL(__tcp_send_ack);
 
 void tcp_send_ack(struct sock *sk)
 {
 	__tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt);
 }
-EXPORT_SYMBOL_GPL(tcp_send_ack);
 
 /* This routine sends a packet with an out of date sequence
  * number. It assumes the other end will try to ack it.
-- 
2.17.1


From 85652b295f7a7c7efd6f622832ae1c9968575a1d Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Wed, 18 Jul 2018 13:56:36 -0700
Subject: [PATCH 20/25] tcp: do not delay ACK in DCTCP upon CE status change

[ Upstream commit a0496ef2c23b3b180902dd185d0d63ccbc624cf8 ]

Per DCTCP RFC8257 (Section 3.2) the ACK reflecting the CE status change
has to be sent immediately so the sender can respond quickly:

""" When receiving packets, the CE codepoint MUST be processed as follows:

   1.  If the CE codepoint is set and DCTCP.CE is false, set DCTCP.CE to
       true and send an immediate ACK.

   2.  If the CE codepoint is not set and DCTCP.CE is true, set DCTCP.CE
       to false and send an immediate ACK.
"""

Previously DCTCP implementation may continue to delay the ACK. This
patch fixes that to implement the RFC by forcing an immediate ACK.

Tested with this packetdrill script provided by Larry Brakmo

0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
0.000 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
0.000 setsockopt(3, SOL_TCP, TCP_CONGESTION, "dctcp", 5) = 0
0.000 bind(3, ..., ...) = 0
0.000 listen(3, 1) = 0

0.100 < [ect0] SEW 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
0.100 > SE. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
0.110 < [ect0] . 1:1(0) ack 1 win 257
0.200 accept(3, ..., ...) = 4
   +0 setsockopt(4, SOL_SOCKET, SO_DEBUG, [1], 4) = 0

0.200 < [ect0] . 1:1001(1000) ack 1 win 257
0.200 > [ect01] . 1:1(0) ack 1001

0.200 write(4, ..., 1) = 1
0.200 > [ect01] P. 1:2(1) ack 1001

0.200 < [ect0] . 1001:2001(1000) ack 2 win 257
+0.005 < [ce] . 2001:3001(1000) ack 2 win 257

+0.000 > [ect01] . 2:2(0) ack 2001
// Previously the ACK below would be delayed by 40ms
+0.000 > [ect01] E. 2:2(0) ack 3001

+0.500 < F. 9501:9501(0) ack 4 win 257

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h    |  1 +
 net/ipv4/tcp_dctcp.c | 30 ++++++++++++++++++------------
 net/ipv4/tcp_input.c |  3 ++-
 3 files changed, 21 insertions(+), 13 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 62af4ae27430..3173dd12b8cc 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -372,6 +372,7 @@ ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos,
 			struct pipe_inode_info *pipe, size_t len,
 			unsigned int flags);
 
+void tcp_enter_quickack_mode(struct sock *sk);
 static inline void tcp_dec_quickack_mode(struct sock *sk,
 					 const unsigned int pkts)
 {
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 39d96d27ff94..c78fb53988a1 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -131,12 +131,15 @@ static void dctcp_ce_state_0_to_1(struct sock *sk)
 	struct dctcp *ca = inet_csk_ca(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	/* State has changed from CE=0 to CE=1 and delayed
-	 * ACK has not sent yet.
-	 */
-	if (!ca->ce_state &&
-	    inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
-		__tcp_send_ack(sk, ca->prior_rcv_nxt);
+	if (!ca->ce_state) {
+		/* State has changed from CE=0 to CE=1, force an immediate
+		 * ACK to reflect the new CE state. If an ACK was delayed,
+		 * send that first to reflect the prior CE state.
+		 */
+		if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
+			__tcp_send_ack(sk, ca->prior_rcv_nxt);
+		tcp_enter_quickack_mode(sk);
+	}
 
 	ca->prior_rcv_nxt = tp->rcv_nxt;
 	ca->ce_state = 1;
@@ -149,12 +152,15 @@ static void dctcp_ce_state_1_to_0(struct sock *sk)
 	struct dctcp *ca = inet_csk_ca(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	/* State has changed from CE=1 to CE=0 and delayed
-	 * ACK has not sent yet.
-	 */
-	if (ca->ce_state &&
-	    inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
-		__tcp_send_ack(sk, ca->prior_rcv_nxt);
+	if (ca->ce_state) {
+		/* State has changed from CE=1 to CE=0, force an immediate
+		 * ACK to reflect the new CE state. If an ACK was delayed,
+		 * send that first to reflect the prior CE state.
+		 */
+		if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
+			__tcp_send_ack(sk, ca->prior_rcv_nxt);
+		tcp_enter_quickack_mode(sk);
+	}
 
 	ca->prior_rcv_nxt = tp->rcv_nxt;
 	ca->ce_state = 0;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 5711b1b12d28..03fd2ff4007b 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -209,13 +209,14 @@ static void tcp_incr_quickack(struct sock *sk)
 		icsk->icsk_ack.quick = min(quickacks, TCP_MAX_QUICKACKS);
 }
 
-static void tcp_enter_quickack_mode(struct sock *sk)
+void tcp_enter_quickack_mode(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	tcp_incr_quickack(sk);
 	icsk->icsk_ack.pingpong = 0;
 	icsk->icsk_ack.ato = TCP_ATO_MIN;
 }
+EXPORT_SYMBOL(tcp_enter_quickack_mode);
 
 /* Send ACKs quickly, if "quick" count is not exhausted
  * and the session is not interactive.
-- 
2.17.1


From d6961539c95534ea866d8de9a2d5b2a91a5de252 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 23 Jul 2018 09:28:17 -0700
Subject: [PATCH 21/25] tcp: free batches of packets in tcp_prune_ofo_queue()

[ Upstream commit 72cd43ba64fc172a443410ce01645895850844c8 ]

Juha-Matti Tilli reported that malicious peers could inject tiny
packets in out_of_order_queue, forcing very expensive calls
to tcp_collapse_ofo_queue() and tcp_prune_ofo_queue() for
every incoming packet. out_of_order_queue rb-tree can contain
thousands of nodes, iterating over all of them is not nice.

Before linux-4.9, we would have pruned all packets in ofo_queue
in one go, every XXXX packets. XXXX depends on sk_rcvbuf and skbs
truesize, but is about 7000 packets with tcp_rmem[2] default of 6 MB.

Since we plan to increase tcp_rmem[2] in the future to cope with
modern BDP, can not revert to the old behavior, without great pain.

Strategy taken in this patch is to purge ~12.5 % of the queue capacity.

Fixes: 36a6503fedda ("tcp: refine tcp_prune_ofo_queue() to not drop all packets")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Juha-Matti Tilli <juha-matti.tilli@iki.fi>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h |  2 ++
 net/ipv4/tcp_input.c   | 15 +++++++++++----
 2 files changed, 13 insertions(+), 4 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 9cf971c68401..6dd77767fd5b 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3167,6 +3167,8 @@ static inline int __skb_grow_rcsum(struct sk_buff *skb, unsigned int len)
 	return __skb_grow(skb, len);
 }
 
+#define rb_to_skb(rb) rb_entry_safe(rb, struct sk_buff, rbnode)
+
 #define skb_queue_walk(queue, skb) \
 		for (skb = (queue)->next;					\
 		     skb != (struct sk_buff *)(queue);				\
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 03fd2ff4007b..1e7175bd3b59 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4924,6 +4924,7 @@ static void tcp_collapse_ofo_queue(struct sock *sk)
  * 2) not add too big latencies if thousands of packets sit there.
  *    (But if application shrinks SO_RCVBUF, we could still end up
  *     freeing whole queue here)
+ * 3) Drop at least 12.5 % of sk_rcvbuf to avoid malicious attacks.
  *
  * Return true if queue has shrunk.
  */
@@ -4931,20 +4932,26 @@ static bool tcp_prune_ofo_queue(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct rb_node *node, *prev;
+	int goal;
 
 	if (RB_EMPTY_ROOT(&tp->out_of_order_queue))
 		return false;
 
 	NET_INC_STATS(sock_net(sk), LINUX_MIB_OFOPRUNED);
+	goal = sk->sk_rcvbuf >> 3;
 	node = &tp->ooo_last_skb->rbnode;
 	do {
 		prev = rb_prev(node);
 		rb_erase(node, &tp->out_of_order_queue);
+		goal -= rb_to_skb(node)->truesize;
 		tcp_drop(sk, rb_entry(node, struct sk_buff, rbnode));
-		sk_mem_reclaim(sk);
-		if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
-		    !tcp_under_memory_pressure(sk))
-			break;
+		if (!prev || goal <= 0) {
+			sk_mem_reclaim(sk);
+			if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
+			    !tcp_under_memory_pressure(sk))
+				break;
+			goal = sk->sk_rcvbuf >> 3;
+		}
 		node = prev;
 	} while (node);
 	tp->ooo_last_skb = rb_entry(prev, struct sk_buff, rbnode);
-- 
2.17.1


From 88451e88aa32d87a5be98046531973a9d3d6845e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 23 Jul 2018 09:28:18 -0700
Subject: [PATCH 22/25] tcp: avoid collapses in tcp_prune_queue() if possible

[ Upstream commit f4a3313d8e2ca9fd8d8f45e40a2903ba782607e7 ]

Right after a TCP flow is created, receiving tiny out of order
packets allways hit the condition :

if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
	tcp_clamp_window(sk);

tcp_clamp_window() increases sk_rcvbuf to match sk_rmem_alloc
(guarded by tcp_rmem[2])

Calling tcp_collapse_ofo_queue() in this case is not useful,
and offers a O(N^2) surface attack to malicious peers.

Better not attempt anything before full queue capacity is reached,
forcing attacker to spend lots of resource and allow us to more
easily detect the abuse.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 1e7175bd3b59..023d2b016f5d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4986,6 +4986,9 @@ static int tcp_prune_queue(struct sock *sk)
 	else if (tcp_under_memory_pressure(sk))
 		tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss);
 
+	if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf)
+		return 0;
+
 	tcp_collapse_ofo_queue(sk);
 	if (!skb_queue_empty(&sk->sk_receive_queue))
 		tcp_collapse(sk, &sk->sk_receive_queue, NULL,
-- 
2.17.1


From a43450a233ff48b58b9d468521bd477b713a6ea8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 23 Jul 2018 09:28:19 -0700
Subject: [PATCH 23/25] tcp: detect malicious patterns in
 tcp_collapse_ofo_queue()

[ Upstream commit 3d4bf93ac12003f9b8e1e2de37fe27983deebdcf ]

In case an attacker feeds tiny packets completely out of order,
tcp_collapse_ofo_queue() might scan the whole rb-tree, performing
expensive copies, but not changing socket memory usage at all.

1) Do not attempt to collapse tiny skbs.
2) Add logic to exit early when too many tiny skbs are detected.

We prefer not doing aggressive collapsing (which copies packets)
for pathological flows, and revert to tcp_prune_ofo_queue() which
will be less expensive.

In the future, we might add the possibility of terminating flows
that are proven to be malicious.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 023d2b016f5d..6f09c45dc20c 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4877,6 +4877,7 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct rb_root *root,
 static void tcp_collapse_ofo_queue(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	u32 range_truesize, sum_tiny = 0;
 	struct sk_buff *skb, *head;
 	struct rb_node *p;
 	u32 start, end;
@@ -4895,6 +4896,7 @@ static void tcp_collapse_ofo_queue(struct sock *sk)
 	}
 	start = TCP_SKB_CB(skb)->seq;
 	end = TCP_SKB_CB(skb)->end_seq;
+	range_truesize = skb->truesize;
 
 	for (head = skb;;) {
 		skb = tcp_skb_next(skb, NULL);
@@ -4905,11 +4907,20 @@ static void tcp_collapse_ofo_queue(struct sock *sk)
 		if (!skb ||
 		    after(TCP_SKB_CB(skb)->seq, end) ||
 		    before(TCP_SKB_CB(skb)->end_seq, start)) {
-			tcp_collapse(sk, NULL, &tp->out_of_order_queue,
-				     head, skb, start, end);
+			/* Do not attempt collapsing tiny skbs */
+			if (range_truesize != head->truesize ||
+			    end - start >= SKB_WITH_OVERHEAD(SK_MEM_QUANTUM)) {
+				tcp_collapse(sk, NULL, &tp->out_of_order_queue,
+					     head, skb, start, end);
+			} else {
+				sum_tiny += range_truesize;
+				if (sum_tiny > sk->sk_rcvbuf >> 3)
+					return;
+			}
 			goto new_range;
 		}
 
+		range_truesize += skb->truesize;
 		if (unlikely(before(TCP_SKB_CB(skb)->seq, start)))
 			start = TCP_SKB_CB(skb)->seq;
 		if (after(TCP_SKB_CB(skb)->end_seq, end))
-- 
2.17.1


From f53ce9fbf1b3dfd9fe3c47e5dd93439ad56186ae Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 23 Jul 2018 09:28:20 -0700
Subject: [PATCH 24/25] tcp: call tcp_drop() from tcp_data_queue_ofo()

[ Upstream commit 8541b21e781a22dce52a74fef0b9bed00404a1cd ]

In order to be able to give better diagnostics and detect
malicious traffic, we need to have better sk->sk_drops tracking.

Fixes: 9f5afeae5152 ("tcp: use an RB tree for ooo receive queue")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 6f09c45dc20c..35b0e38fe31a 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4492,7 +4492,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 				/* All the bits are present. Drop. */
 				NET_INC_STATS(sock_net(sk),
 					      LINUX_MIB_TCPOFOMERGE);
-				__kfree_skb(skb);
+				tcp_drop(sk, skb);
 				skb = NULL;
 				tcp_dsack_set(sk, seq, end_seq);
 				goto add_sack;
@@ -4511,7 +4511,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 						 TCP_SKB_CB(skb1)->end_seq);
 				NET_INC_STATS(sock_net(sk),
 					      LINUX_MIB_TCPOFOMERGE);
-				__kfree_skb(skb1);
+				tcp_drop(sk, skb1);
 				goto merge_right;
 			}
 		} else if (tcp_try_coalesce(sk, OOO_QUEUE, skb1,
-- 
2.17.1


From 7ba6a411d4d9cbe540e90137cfe77e6c89e513bd Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 23 Jul 2018 09:28:21 -0700
Subject: [PATCH 25/25] tcp: add tcp_ooo_try_coalesce() helper

[ Upstream commit 58152ecbbcc6a0ce7fddd5bf5f6ee535834ece0c ]

In case skb in out_or_order_queue is the result of
multiple skbs coalescing, we would like to get a proper gso_segs
counter tracking, so that future tcp_drop() can report an accurate
number.

I chose to not implement this tracking for skbs in receive queue,
since they are not dropped, unless socket is disconnected.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 25 +++++++++++++++++++++----
 1 file changed, 21 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 35b0e38fe31a..b86e7b8beb1d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4332,6 +4332,23 @@ static bool tcp_try_coalesce(struct sock *sk,
 	return true;
 }
 
+static bool tcp_ooo_try_coalesce(struct sock *sk,
+			     struct sk_buff *to,
+			     struct sk_buff *from,
+			     bool *fragstolen)
+{
+	bool res = tcp_try_coalesce(sk, OOO_QUEUE, to, from, fragstolen);
+
+	/* In case tcp_drop() is called later, update to->gso_segs */
+	if (res) {
+		u32 gso_segs = max_t(u16, 1, skb_shinfo(to)->gso_segs) +
+			       max_t(u16, 1, skb_shinfo(from)->gso_segs);
+
+		skb_shinfo(to)->gso_segs = min_t(u32, gso_segs, 0xFFFF);
+	}
+	return res;
+}
+
 static void tcp_drop(struct sock *sk, struct sk_buff *skb)
 {
 	sk_drops_add(sk, skb);
@@ -4463,8 +4480,8 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 	/* In the typical case, we are adding an skb to the end of the list.
 	 * Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup.
 	 */
-	if (tcp_try_coalesce(sk, OOO_QUEUE, tp->ooo_last_skb,
-			     skb, &fragstolen)) {
+	if (tcp_ooo_try_coalesce(sk, tp->ooo_last_skb,
+				 skb, &fragstolen)) {
 coalesce_done:
 		tcp_grow_window(sk, skb);
 		kfree_skb_partial(skb, fragstolen);
@@ -4514,8 +4531,8 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 				tcp_drop(sk, skb1);
 				goto merge_right;
 			}
-		} else if (tcp_try_coalesce(sk, OOO_QUEUE, skb1,
-					    skb, &fragstolen)) {
+		} else if (tcp_ooo_try_coalesce(sk, skb1,
+						skb, &fragstolen)) {
 			goto coalesce_done;
 		}
 		p = &parent->rb_right;
-- 
2.17.1


[-- Attachment #3: net_417.mbox --]
[-- Type: Application/Octet-Stream, Size: 101773 bytes --]

From a85f36391fbfaa26d5a9d1d1156741e95b2293dd Mon Sep 17 00:00:00 2001
From: Jarod Wilson <jarod@redhat.com>
Date: Wed, 18 Jul 2018 14:49:36 -0400
Subject: [PATCH 01/34] bonding: set default miimon value for non-arp modes if
 not set

[ Upstream commit c1f897ce186a529a494441642125479d38727a3d ]

For some time now, if you load the bonding driver and configure bond
parameters via sysfs using minimal config options, such as specifying
nothing but the mode, relying on defaults for everything else, modes
that cannot use arp monitoring (802.3ad, balance-tlb, balance-alb) all
wind up with both arp_interval=0 (as it should be) and miimon=0, which
means the miimon monitor thread never actually runs. This is particularly
problematic for 802.3ad.

For example, from an LNST recipe I've set up:

$ modprobe bonding max_bonds=0"
$ echo "+t_bond0" > /sys/class/net/bonding_masters"
$ ip link set t_bond0 down"
$ echo "802.3ad" > /sys/class/net/t_bond0/bonding/mode"
$ ip link set ens1f1 down"
$ echo "+ens1f1" > /sys/class/net/t_bond0/bonding/slaves"
$ ip link set ens1f0 down"
$ echo "+ens1f0" > /sys/class/net/t_bond0/bonding/slaves"
$ ethtool -i t_bond0"
$ ip link set ens1f1 up"
$ ip link set ens1f0 up"
$ ip link set t_bond0 up"
$ ip addr add 192.168.9.1/24 dev t_bond0"
$ ip addr add 2002::1/64 dev t_bond0"

This bond comes up okay, but things look slightly suspect in
/proc/net/bonding/t_bond0 output:

$ grep -i mii /proc/net/bonding/t_bond0
MII Status: up
MII Polling Interval (ms): 0
MII Status: up
MII Status: up

Now, pull a cable on one of the ports in the bond, then reconnect it, and
you'll see:

Slave Interface: ens1f0
MII Status: down
Speed: 1000 Mbps
Duplex: full

I believe this became a major issue as of commit 4d2c0cda0744, which for
802.3ad bonds, sets slave->link = BOND_LINK_DOWN, with a comment about
relying on link monitoring via miimon to set it correctly, but since the
miimon work queue never runs, the link just stays marked down.

If we simply tweak bond_option_mode_set() slightly, we can check for the
non-arp modes having no miimon value set, and insert BOND_DEFAULT_MIIMON,
which gets things back in full working order. This problem exists as far
back as 4.14, and might be worth fixing in all stable trees since, though
the work-around is to simply specify an miimon value yourself.

Reported-by: Bob Ball <ball@umich.edu>
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Acked-by: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_options.c | 23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)

diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index b594bae1adbd..cdc72b7e3d26 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -743,15 +743,20 @@ const struct bond_option *bond_opt_get(unsigned int option)
 static int bond_option_mode_set(struct bonding *bond,
 				const struct bond_opt_value *newval)
 {
-	if (!bond_mode_uses_arp(newval->value) && bond->params.arp_interval) {
-		netdev_dbg(bond->dev, "%s mode is incompatible with arp monitoring, start mii monitoring\n",
-			   newval->string);
-		/* disable arp monitoring */
-		bond->params.arp_interval = 0;
-		/* set miimon to default value */
-		bond->params.miimon = BOND_DEFAULT_MIIMON;
-		netdev_dbg(bond->dev, "Setting MII monitoring interval to %d\n",
-			   bond->params.miimon);
+	if (!bond_mode_uses_arp(newval->value)) {
+		if (bond->params.arp_interval) {
+			netdev_dbg(bond->dev, "%s mode is incompatible with arp monitoring, start mii monitoring\n",
+				   newval->string);
+			/* disable arp monitoring */
+			bond->params.arp_interval = 0;
+		}
+
+		if (!bond->params.miimon) {
+			/* set miimon to default value */
+			bond->params.miimon = BOND_DEFAULT_MIIMON;
+			netdev_dbg(bond->dev, "Setting MII monitoring interval to %d\n",
+				   bond->params.miimon);
+		}
 	}
 
 	if (newval->value == BOND_MODE_ALB)
-- 
2.17.1


From 67c8042c77fe9750309af9856d029dcf6de11abb Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 23 Jul 2018 16:50:48 +0200
Subject: [PATCH 02/34] ip: hash fragments consistently

[ Upstream commit 3dd1c9a1270736029ffca670e9bd0265f4120600 ]

The skb hash for locally generated ip[v6] fragments belonging
to the same datagram can vary in several circumstances:
* for connected UDP[v6] sockets, the first fragment get its hash
  via set_owner_w()/skb_set_hash_from_sk()
* for unconnected IPv6 UDPv6 sockets, the first fragment can get
  its hash via ip6_make_flowlabel()/skb_get_hash_flowi6(), if
  auto_flowlabel is enabled

For the following frags the hash is usually computed via
skb_get_hash().
The above can cause OoO for unconnected IPv6 UDPv6 socket: in that
scenario the egress tx queue can be selected on a per packet basis
via the skb hash.
It may also fool flow-oriented schedulers to place fragments belonging
to the same datagram in different flows.

Fix the issue by copying the skb hash from the head frag into
the others at fragmentation time.

Before this commit:
perf probe -a "dev_queue_xmit skb skb->hash skb->l4_hash:b1@0/8 skb->sw_hash:b1@1/8"
netperf -H $IPV4 -t UDP_STREAM -l 5 -- -m 2000 -n &
perf record -e probe:dev_queue_xmit -e probe:skb_set_owner_w -a sleep 0.1
perf script
probe:dev_queue_xmit: (ffffffff8c6b1b20) hash=3713014309 l4_hash=1 sw_hash=0
probe:dev_queue_xmit: (ffffffff8c6b1b20) hash=0 l4_hash=0 sw_hash=0

After this commit:
probe:dev_queue_xmit: (ffffffff8c6b1b20) hash=2171763177 l4_hash=1 sw_hash=0
probe:dev_queue_xmit: (ffffffff8c6b1b20) hash=2171763177 l4_hash=1 sw_hash=0

Fixes: b73c3d0e4f0e ("net: Save TX flow hash in sock and set in skbuf on xmit")
Fixes: 67800f9b1f4e ("ipv6: Call skb_get_hash_flowi6 to get skb->hash in ip6_make_flowlabel")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_output.c  | 2 ++
 net/ipv6/ip6_output.c | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index d54abc097800..267b69cfea71 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -523,6 +523,8 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	to->dev = from->dev;
 	to->mark = from->mark;
 
+	skb_copy_hash(to, from);
+
 	/* Copy the flags to each fragment. */
 	IPCB(to)->flags = IPCB(from)->flags;
 
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index af49f6cb5d3e..8f4c596a683d 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -596,6 +596,8 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	to->dev = from->dev;
 	to->mark = from->mark;
 
+	skb_copy_hash(to, from);
+
 #ifdef CONFIG_NET_SCHED
 	to->tc_index = from->tc_index;
 #endif
-- 
2.17.1


From ad43ca0f19aecd67e71cb73e82d2a5d9a67fba87 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Mon, 23 Jul 2018 19:36:48 -0400
Subject: [PATCH 03/34] ip: in cmsg IP(V6)_ORIGDSTADDR call pskb_may_pull

[ Upstream commit 2efd4fca703a6707cad16ab486eaab8fc7f0fd49 ]

Syzbot reported a read beyond the end of the skb head when returning
IPV6_ORIGDSTADDR:

  BUG: KMSAN: kernel-infoleak in put_cmsg+0x5ef/0x860 net/core/scm.c:242
  CPU: 0 PID: 4501 Comm: syz-executor128 Not tainted 4.17.0+ #9
  Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
  Google 01/01/2011
  Call Trace:
    __dump_stack lib/dump_stack.c:77 [inline]
    dump_stack+0x185/0x1d0 lib/dump_stack.c:113
    kmsan_report+0x188/0x2a0 mm/kmsan/kmsan.c:1125
    kmsan_internal_check_memory+0x138/0x1f0 mm/kmsan/kmsan.c:1219
    kmsan_copy_to_user+0x7a/0x160 mm/kmsan/kmsan.c:1261
    copy_to_user include/linux/uaccess.h:184 [inline]
    put_cmsg+0x5ef/0x860 net/core/scm.c:242
    ip6_datagram_recv_specific_ctl+0x1cf3/0x1eb0 net/ipv6/datagram.c:719
    ip6_datagram_recv_ctl+0x41c/0x450 net/ipv6/datagram.c:733
    rawv6_recvmsg+0x10fb/0x1460 net/ipv6/raw.c:521
    [..]

This logic and its ipv4 counterpart read the destination port from
the packet at skb_transport_offset(skb) + 4.

With MSG_MORE and a local SOCK_RAW sender, syzbot was able to cook a
packet that stores headers exactly up to skb_transport_offset(skb) in
the head and the remainder in a frag.

Call pskb_may_pull before accessing the pointer to ensure that it lies
in skb head.

Link: http://lkml.kernel.org/r/CAF=yD-LEJwZj5a1-bAAj2Oy_hKmGygV6rsJ_WOrAYnv-fnayiQ@mail.gmail.com
Reported-by: syzbot+9adb4b567003cac781f0@syzkaller.appspotmail.com
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_sockglue.c | 7 +++++--
 net/ipv6/datagram.c    | 7 +++++--
 2 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 57bbb060faaf..7c14c7818ead 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -148,15 +148,18 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
 {
 	struct sockaddr_in sin;
 	const struct iphdr *iph = ip_hdr(skb);
-	__be16 *ports = (__be16 *)skb_transport_header(skb);
+	__be16 *ports;
+	int end;
 
-	if (skb_transport_offset(skb) + 4 > (int)skb->len)
+	end = skb_transport_offset(skb) + 4;
+	if (end > 0 && !pskb_may_pull(skb, end))
 		return;
 
 	/* All current transport protocols have the port numbers in the
 	 * first four bytes of the transport header and this function is
 	 * written with this assumption in mind.
 	 */
+	ports = (__be16 *)skb_transport_header(skb);
 
 	sin.sin_family = AF_INET;
 	sin.sin_addr.s_addr = iph->daddr;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 2ee08b6a86a4..1a1f876f8e28 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -700,13 +700,16 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg,
 	}
 	if (np->rxopt.bits.rxorigdstaddr) {
 		struct sockaddr_in6 sin6;
-		__be16 *ports = (__be16 *) skb_transport_header(skb);
+		__be16 *ports;
+		int end;
 
-		if (skb_transport_offset(skb) + 4 <= (int)skb->len) {
+		end = skb_transport_offset(skb) + 4;
+		if (end <= 0 || pskb_may_pull(skb, end)) {
 			/* All current transport protocols have the port numbers in the
 			 * first four bytes of the transport header and this function is
 			 * written with this assumption in mind.
 			 */
+			ports = (__be16 *)skb_transport_header(skb);
 
 			sin6.sin6_family = AF_INET6;
 			sin6.sin6_addr = ipv6_hdr(skb)->daddr;
-- 
2.17.1


From 04a6dfdd23bdb5f103702108bd7089d8bb6cefc3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 20 Jul 2018 11:53:15 +0200
Subject: [PATCH 04/34] net: dsa: mv88e6xxx: fix races between lock and irq
 freeing
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 3d82475ad46c0b65f2618b5f2bbb4cadbb5ac5d8 ]

free_irq() waits until all handlers for this IRQ have completed. As the
relevant handler (mv88e6xxx_g1_irq_thread_fn()) takes the chip's reg_lock
it might never return if the thread calling free_irq() holds this lock.

For the same reason kthread_cancel_delayed_work_sync() in the polling case
must not hold this lock.

Also first free the irq (or stop the worker respectively) such that
mv88e6xxx_g1_irq_thread_work() isn't called any more before the irq
mappings are dropped in mv88e6xxx_g1_irq_free_common() to prevent the
worker thread to call handle_nested_irq(0) which results in a NULL-pointer
exception.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 21 +++++++++++++--------
 1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 5b4374f21d76..04371b0bba80 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -341,6 +341,7 @@ static const struct irq_domain_ops mv88e6xxx_g1_irq_domain_ops = {
 	.xlate	= irq_domain_xlate_twocell,
 };
 
+/* To be called with reg_lock held */
 static void mv88e6xxx_g1_irq_free_common(struct mv88e6xxx_chip *chip)
 {
 	int irq, virq;
@@ -360,9 +361,15 @@ static void mv88e6xxx_g1_irq_free_common(struct mv88e6xxx_chip *chip)
 
 static void mv88e6xxx_g1_irq_free(struct mv88e6xxx_chip *chip)
 {
-	mv88e6xxx_g1_irq_free_common(chip);
-
+	/*
+	 * free_irq must be called without reg_lock taken because the irq
+	 * handler takes this lock, too.
+	 */
 	free_irq(chip->irq, chip);
+
+	mutex_lock(&chip->reg_lock);
+	mv88e6xxx_g1_irq_free_common(chip);
+	mutex_unlock(&chip->reg_lock);
 }
 
 static int mv88e6xxx_g1_irq_setup_common(struct mv88e6xxx_chip *chip)
@@ -467,10 +474,12 @@ static int mv88e6xxx_irq_poll_setup(struct mv88e6xxx_chip *chip)
 
 static void mv88e6xxx_irq_poll_free(struct mv88e6xxx_chip *chip)
 {
-	mv88e6xxx_g1_irq_free_common(chip);
-
 	kthread_cancel_delayed_work_sync(&chip->irq_poll_work);
 	kthread_destroy_worker(chip->kworker);
+
+	mutex_lock(&chip->reg_lock);
+	mv88e6xxx_g1_irq_free_common(chip);
+	mutex_unlock(&chip->reg_lock);
 }
 
 int mv88e6xxx_wait(struct mv88e6xxx_chip *chip, int addr, int reg, u16 mask)
@@ -4286,12 +4295,10 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev)
 	if (chip->info->g2_irqs > 0)
 		mv88e6xxx_g2_irq_free(chip);
 out_g1_irq:
-	mutex_lock(&chip->reg_lock);
 	if (chip->irq > 0)
 		mv88e6xxx_g1_irq_free(chip);
 	else
 		mv88e6xxx_irq_poll_free(chip);
-	mutex_unlock(&chip->reg_lock);
 out:
 	return err;
 }
@@ -4316,12 +4323,10 @@ static void mv88e6xxx_remove(struct mdio_device *mdiodev)
 	if (chip->info->g2_irqs > 0)
 		mv88e6xxx_g2_irq_free(chip);
 
-	mutex_lock(&chip->reg_lock);
 	if (chip->irq > 0)
 		mv88e6xxx_g1_irq_free(chip);
 	else
 		mv88e6xxx_irq_poll_free(chip);
-	mutex_unlock(&chip->reg_lock);
 }
 
 static const struct of_device_id mv88e6xxx_of_match[] = {
-- 
2.17.1


From c9bfa296289193e7c8056ce8510cda094b72d811 Mon Sep 17 00:00:00 2001
From: Jack Morgenstein <jackm@dev.mellanox.co.il>
Date: Tue, 24 Jul 2018 14:27:55 +0300
Subject: [PATCH 05/34] net/mlx4_core: Save the qpn from the input modifier in
 RST2INIT wrapper

[ Upstream commit 958c696f5a7274d9447a458ad7aa70719b29a50a ]

Function mlx4_RST2INIT_QP_wrapper saved the qp number passed in the qp
context, rather than the one passed in the input modifier.

However, the qp number in the qp context is not defined as a
required parameter by the FW. Therefore, drivers may choose to not
specify the qp number in the qp context for the reset-to-init transition.

Thus, we must save the qp number passed in the command input modifier --
which is always present. (This saved qp number is used as the input
modifier for command 2RST_QP when a slave's qp's are destroyed).

Fixes: c82e9aa0a8bc ("mlx4_core: resource tracking for HCA resources used by guests")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/resource_tracker.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 29e50f787349..db63f0ec3d01 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -2956,7 +2956,7 @@ int mlx4_RST2INIT_QP_wrapper(struct mlx4_dev *dev, int slave,
 	u32 srqn = qp_get_srqn(qpc) & 0xffffff;
 	int use_srq = (qp_get_srqn(qpc) >> 24) & 1;
 	struct res_srq *srq;
-	int local_qpn = be32_to_cpu(qpc->local_qpn) & 0xffffff;
+	int local_qpn = vhcr->in_modifier & 0xffffff;
 
 	err = adjust_qp_sched_queue(dev, slave, qpc, inbox);
 	if (err)
-- 
2.17.1


From 82c378982c28b84144adafdb9874a80e16b7d1d9 Mon Sep 17 00:00:00 2001
From: Zhao Chen <zhaochen6@huawei.com>
Date: Wed, 18 Jul 2018 00:33:18 -0400
Subject: [PATCH 06/34] net-next/hinic: fix a problem in hinic_xmit_frame()

[ Upstream commit f7482683f1f4925c60941dbbd0813ceaa069d106 ]

The calculation of "wqe_size" is not correct when the tx queue is busy in
hinic_xmit_frame().

When there are no free WQEs, the tx flow will unmap the skb buffer, then
ring the doobell for the pending packets. But the "wqe_size" which used
to calculate the doorbell address is not correct. The wqe size should be
cleared to 0, otherwise, it will cause a doorbell error.

This patch fixes the problem.

Reported-by: Zhou Wang <wangzhou1@hisilicon.com>
Signed-off-by: Zhao Chen <zhaochen6@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/huawei/hinic/hinic_tx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
index 9128858479c4..2353ec829c04 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
@@ -229,6 +229,7 @@ netdev_tx_t hinic_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 		txq->txq_stats.tx_busy++;
 		u64_stats_update_end(&txq->txq_stats.syncp);
 		err = NETDEV_TX_BUSY;
+		wqe_size = 0;
 		goto flush_skbs;
 	}
 
-- 
2.17.1


From 4833a0ed5dd2fdf80f703cd8fa80c74928c0569e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 19 Jul 2018 16:04:38 -0700
Subject: [PATCH 07/34] net: skb_segment() should not return NULL

[ Upstream commit ff907a11a0d68a749ce1a321f4505c03bf72190c ]

syzbot caught a NULL deref [1], caused by skb_segment()

skb_segment() has many "goto err;" that assume the @err variable
contains -ENOMEM.

A successful call to __skb_linearize() should not clear @err,
otherwise a subsequent memory allocation error could return NULL.

While we are at it, we might use -EINVAL instead of -ENOMEM when
MAX_SKB_FRAGS limit is reached.

[1]
kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] SMP KASAN
CPU: 0 PID: 13285 Comm: syz-executor3 Not tainted 4.18.0-rc4+ #146
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:tcp_gso_segment+0x3dc/0x1780 net/ipv4/tcp_offload.c:106
Code: f0 ff ff 0f 87 1c fd ff ff e8 00 88 0b fb 48 8b 75 d0 48 b9 00 00 00 00 00 fc ff df 48 8d be 90 00 00 00 48 89 f8 48 c1 e8 03 <0f> b6 14 08 48 8d 86 94 00 00 00 48 89 c6 83 e0 07 48 c1 ee 03 0f
RSP: 0018:ffff88019b7fd060 EFLAGS: 00010206
RAX: 0000000000000012 RBX: 0000000000000020 RCX: dffffc0000000000
RDX: 0000000000040000 RSI: 0000000000000000 RDI: 0000000000000090
RBP: ffff88019b7fd0f0 R08: ffff88019510e0c0 R09: ffffed003b5c46d6
R10: ffffed003b5c46d6 R11: ffff8801dae236b3 R12: 0000000000000001
R13: ffff8801d6c581f4 R14: 0000000000000000 R15: ffff8801d6c58128
FS:  00007fcae64d6700(0000) GS:ffff8801dae00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000004e8664 CR3: 00000001b669b000 CR4: 00000000001406f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 tcp4_gso_segment+0x1c3/0x440 net/ipv4/tcp_offload.c:54
 inet_gso_segment+0x64e/0x12d0 net/ipv4/af_inet.c:1342
 inet_gso_segment+0x64e/0x12d0 net/ipv4/af_inet.c:1342
 skb_mac_gso_segment+0x3b5/0x740 net/core/dev.c:2792
 __skb_gso_segment+0x3c3/0x880 net/core/dev.c:2865
 skb_gso_segment include/linux/netdevice.h:4099 [inline]
 validate_xmit_skb+0x640/0xf30 net/core/dev.c:3104
 __dev_queue_xmit+0xc14/0x3910 net/core/dev.c:3561
 dev_queue_xmit+0x17/0x20 net/core/dev.c:3602
 neigh_hh_output include/net/neighbour.h:473 [inline]
 neigh_output include/net/neighbour.h:481 [inline]
 ip_finish_output2+0x1063/0x1860 net/ipv4/ip_output.c:229
 ip_finish_output+0x841/0xfa0 net/ipv4/ip_output.c:317
 NF_HOOK_COND include/linux/netfilter.h:276 [inline]
 ip_output+0x223/0x880 net/ipv4/ip_output.c:405
 dst_output include/net/dst.h:444 [inline]
 ip_local_out+0xc5/0x1b0 net/ipv4/ip_output.c:124
 iptunnel_xmit+0x567/0x850 net/ipv4/ip_tunnel_core.c:91
 ip_tunnel_xmit+0x1598/0x3af1 net/ipv4/ip_tunnel.c:778
 ipip_tunnel_xmit+0x264/0x2c0 net/ipv4/ipip.c:308
 __netdev_start_xmit include/linux/netdevice.h:4148 [inline]
 netdev_start_xmit include/linux/netdevice.h:4157 [inline]
 xmit_one net/core/dev.c:3034 [inline]
 dev_hard_start_xmit+0x26c/0xc30 net/core/dev.c:3050
 __dev_queue_xmit+0x29ef/0x3910 net/core/dev.c:3569
 dev_queue_xmit+0x17/0x20 net/core/dev.c:3602
 neigh_direct_output+0x15/0x20 net/core/neighbour.c:1403
 neigh_output include/net/neighbour.h:483 [inline]
 ip_finish_output2+0xa67/0x1860 net/ipv4/ip_output.c:229
 ip_finish_output+0x841/0xfa0 net/ipv4/ip_output.c:317
 NF_HOOK_COND include/linux/netfilter.h:276 [inline]
 ip_output+0x223/0x880 net/ipv4/ip_output.c:405
 dst_output include/net/dst.h:444 [inline]
 ip_local_out+0xc5/0x1b0 net/ipv4/ip_output.c:124
 ip_queue_xmit+0x9df/0x1f80 net/ipv4/ip_output.c:504
 tcp_transmit_skb+0x1bf9/0x3f10 net/ipv4/tcp_output.c:1168
 tcp_write_xmit+0x1641/0x5c20 net/ipv4/tcp_output.c:2363
 __tcp_push_pending_frames+0xb2/0x290 net/ipv4/tcp_output.c:2536
 tcp_push+0x638/0x8c0 net/ipv4/tcp.c:735
 tcp_sendmsg_locked+0x2ec5/0x3f00 net/ipv4/tcp.c:1410
 tcp_sendmsg+0x2f/0x50 net/ipv4/tcp.c:1447
 inet_sendmsg+0x1a1/0x690 net/ipv4/af_inet.c:798
 sock_sendmsg_nosec net/socket.c:641 [inline]
 sock_sendmsg+0xd5/0x120 net/socket.c:651
 __sys_sendto+0x3d7/0x670 net/socket.c:1797
 __do_sys_sendto net/socket.c:1809 [inline]
 __se_sys_sendto net/socket.c:1805 [inline]
 __x64_sys_sendto+0xe1/0x1a0 net/socket.c:1805
 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x455ab9
Code: 1d ba fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 eb b9 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007fcae64d5c68 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 00007fcae64d66d4 RCX: 0000000000455ab9
RDX: 0000000000000001 RSI: 0000000020000200 RDI: 0000000000000013
RBP: 000000000072bea0 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000014
R13: 00000000004c1145 R14: 00000000004d1818 R15: 0000000000000006
Modules linked in:
Dumping ftrace buffer:
   (ftrace buffer empty)

Fixes: ddff00d42043 ("net: Move skb_has_shared_frag check out of GRE code and into segmentation")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index a84d69c047ac..b2d457df7d86 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3705,6 +3705,7 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 				net_warn_ratelimited(
 					"skb_segment: too many frags: %u %u\n",
 					pos, mss);
+				err = -EINVAL;
 				goto err;
 			}
 
@@ -3738,11 +3739,10 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 
 perform_csum_check:
 		if (!csum) {
-			if (skb_has_shared_frag(nskb)) {
-				err = __skb_linearize(nskb);
-				if (err)
-					goto err;
-			}
+			if (skb_has_shared_frag(nskb) &&
+			    __skb_linearize(nskb))
+				goto err;
+
 			if (!nskb->remcsum_offload)
 				nskb->ip_summed = CHECKSUM_NONE;
 			SKB_GSO_CB(nskb)->csum =
-- 
2.17.1


From 6ff40875f131b470d417a12938bc125ee6683787 Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Thu, 12 Jul 2018 06:04:52 -0700
Subject: [PATCH 08/34] tcp: fix dctcp delayed ACK schedule

[ Upstream commit b0c05d0e99d98d7f0cd41efc1eeec94efdc3325d ]

Previously, when a data segment was sent an ACK was piggybacked
on the data segment without generating a CA_EVENT_NON_DELAYED_ACK
event to notify congestion control modules. So the DCTCP
ca->delayed_ack_reserved flag could incorrectly stay set when
in fact there were no delayed ACKs being reserved. This could result
in sending a special ECN notification ACK that carries an older
ACK sequence, when in fact there was no need for such an ACK.
DCTCP keeps track of the delayed ACK status with its own separate
state ca->delayed_ack_reserved. Previously it may accidentally cancel
the delayed ACK without updating this field upon sending a special
ACK that carries a older ACK sequence. This inconsistency would
lead to DCTCP receiver never acknowledging the latest data until the
sender times out and retry in some cases.

Packetdrill script (provided by Larry Brakmo)

0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
0.000 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
0.000 setsockopt(3, SOL_TCP, TCP_CONGESTION, "dctcp", 5) = 0
0.000 bind(3, ..., ...) = 0
0.000 listen(3, 1) = 0

0.100 < [ect0] SEW 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
0.100 > SE. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
0.110 < [ect0] . 1:1(0) ack 1 win 257
0.200 accept(3, ..., ...) = 4

0.200 < [ect0] . 1:1001(1000) ack 1 win 257
0.200 > [ect01] . 1:1(0) ack 1001

0.200 write(4, ..., 1) = 1
0.200 > [ect01] P. 1:2(1) ack 1001

0.200 < [ect0] . 1001:2001(1000) ack 2 win 257
0.200 write(4, ..., 1) = 1
0.200 > [ect01] P. 2:3(1) ack 2001

0.200 < [ect0] . 2001:3001(1000) ack 3 win 257
0.200 < [ect0] . 3001:4001(1000) ack 3 win 257
0.200 > [ect01] . 3:3(0) ack 4001

0.210 < [ce] P. 4001:4501(500) ack 3 win 257

+0.001 read(4, ..., 4500) = 4500
+0 write(4, ..., 1) = 1
+0 > [ect01] PE. 3:4(1) ack 4501

+0.010 < [ect0] W. 4501:5501(1000) ack 4 win 257
// Previously the ACK sequence below would be 4501, causing a long RTO
+0.040~+0.045 > [ect01] . 4:4(0) ack 5501   // delayed ack

+0.311 < [ect0] . 5501:6501(1000) ack 4 win 257  // More data
+0 > [ect01] . 4:4(0) ack 6501     // now acks everything

+0.500 < F. 9501:9501(0) ack 4 win 257

Reported-by: Larry Brakmo <brakmo@fb.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Lawrence Brakmo <brakmo@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_dctcp.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 5f5e5936760e..89f88b0d8167 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -134,7 +134,8 @@ static void dctcp_ce_state_0_to_1(struct sock *sk)
 	/* State has changed from CE=0 to CE=1 and delayed
 	 * ACK has not sent yet.
 	 */
-	if (!ca->ce_state && ca->delayed_ack_reserved) {
+	if (!ca->ce_state &&
+	    inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) {
 		u32 tmp_rcv_nxt;
 
 		/* Save current rcv_nxt. */
@@ -164,7 +165,8 @@ static void dctcp_ce_state_1_to_0(struct sock *sk)
 	/* State has changed from CE=1 to CE=0 and delayed
 	 * ACK has not sent yet.
 	 */
-	if (ca->ce_state && ca->delayed_ack_reserved) {
+	if (ca->ce_state &&
+	    inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) {
 		u32 tmp_rcv_nxt;
 
 		/* Save current rcv_nxt. */
-- 
2.17.1


From 6cf8027f8eec0316ddd9921fa524e23ec1dce360 Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Wed, 18 Jul 2018 13:56:34 -0700
Subject: [PATCH 09/34] tcp: helpers to send special DCTCP ack

[ Upstream commit 2987babb6982306509380fc11b450227a844493b ]

Refactor and create helpers to send the special ACK in DCTCP.

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 22 +++++++++++++++++-----
 1 file changed, 17 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index d07e34f8e309..eafdcd81583f 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1031,8 +1031,8 @@ static void tcp_update_skb_after_send(struct tcp_sock *tp, struct sk_buff *skb)
  * We are working here with either a clone of the original
  * SKB, or a fresh unique copy made by the retransmit engine.
  */
-static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
-			    gfp_t gfp_mask)
+static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
+			      int clone_it, gfp_t gfp_mask, u32 rcv_nxt)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	struct inet_sock *inet;
@@ -1108,7 +1108,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	th->source		= inet->inet_sport;
 	th->dest		= inet->inet_dport;
 	th->seq			= htonl(tcb->seq);
-	th->ack_seq		= htonl(tp->rcv_nxt);
+	th->ack_seq		= htonl(rcv_nxt);
 	*(((__be16 *)th) + 6)	= htons(((tcp_header_size >> 2) << 12) |
 					tcb->tcp_flags);
 
@@ -1186,6 +1186,13 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	return err;
 }
 
+static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
+			    gfp_t gfp_mask)
+{
+	return __tcp_transmit_skb(sk, skb, clone_it, gfp_mask,
+				  tcp_sk(sk)->rcv_nxt);
+}
+
 /* This routine just queues the buffer for sending.
  *
  * NOTE: probe0 timer is not checked, do not forget tcp_push_pending_frames,
@@ -3583,7 +3590,7 @@ void tcp_send_delayed_ack(struct sock *sk)
 }
 
 /* This routine sends an ack and also updates the window. */
-void tcp_send_ack(struct sock *sk)
+void __tcp_send_ack(struct sock *sk, u32 rcv_nxt)
 {
 	struct sk_buff *buff;
 
@@ -3618,7 +3625,12 @@ void tcp_send_ack(struct sock *sk)
 	skb_set_tcp_pure_ack(buff);
 
 	/* Send it off, this clears delayed acks for us. */
-	tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0);
+	__tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0, rcv_nxt);
+}
+
+void tcp_send_ack(struct sock *sk)
+{
+	__tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt);
 }
 EXPORT_SYMBOL_GPL(tcp_send_ack);
 
-- 
2.17.1


From 7a022e9fffab07288486123c2bf85f684e03c10f Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Wed, 18 Jul 2018 13:56:35 -0700
Subject: [PATCH 10/34] tcp: do not cancel delay-AcK on DCTCP special ACK

[ Upstream commit 27cde44a259c380a3c09066fc4b42de7dde9b1ad ]

Currently when a DCTCP receiver delays an ACK and receive a
data packet with a different CE mark from the previous one's, it
sends two immediate ACKs acking previous and latest sequences
respectly (for ECN accounting).

Previously sending the first ACK may mark off the delayed ACK timer
(tcp_event_ack_sent). This may subsequently prevent sending the
second ACK to acknowledge the latest sequence (tcp_ack_snd_check).
The culprit is that tcp_send_ack() assumes it always acknowleges
the latest sequence, which is not true for the first special ACK.

The fix is to not make the assumption in tcp_send_ack and check the
actual ack sequence before cancelling the delayed ACK. Further it's
safer to pass the ack sequence number as a local variable into
tcp_send_ack routine, instead of intercepting tp->rcv_nxt to avoid
future bugs like this.

Reported-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h     |  1 +
 net/ipv4/tcp_dctcp.c  | 34 ++++------------------------------
 net/ipv4/tcp_output.c | 11 ++++++++---
 3 files changed, 13 insertions(+), 33 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 9c9b3768b350..d4ea41d76946 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -535,6 +535,7 @@ void tcp_send_fin(struct sock *sk);
 void tcp_send_active_reset(struct sock *sk, gfp_t priority);
 int tcp_send_synack(struct sock *);
 void tcp_push_one(struct sock *, unsigned int mss_now);
+void __tcp_send_ack(struct sock *sk, u32 rcv_nxt);
 void tcp_send_ack(struct sock *sk);
 void tcp_send_delayed_ack(struct sock *sk);
 void tcp_send_loss_probe(struct sock *sk);
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 89f88b0d8167..39d96d27ff94 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -135,21 +135,8 @@ static void dctcp_ce_state_0_to_1(struct sock *sk)
 	 * ACK has not sent yet.
 	 */
 	if (!ca->ce_state &&
-	    inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) {
-		u32 tmp_rcv_nxt;
-
-		/* Save current rcv_nxt. */
-		tmp_rcv_nxt = tp->rcv_nxt;
-
-		/* Generate previous ack with CE=0. */
-		tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
-		tp->rcv_nxt = ca->prior_rcv_nxt;
-
-		tcp_send_ack(sk);
-
-		/* Recover current rcv_nxt. */
-		tp->rcv_nxt = tmp_rcv_nxt;
-	}
+	    inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
+		__tcp_send_ack(sk, ca->prior_rcv_nxt);
 
 	ca->prior_rcv_nxt = tp->rcv_nxt;
 	ca->ce_state = 1;
@@ -166,21 +153,8 @@ static void dctcp_ce_state_1_to_0(struct sock *sk)
 	 * ACK has not sent yet.
 	 */
 	if (ca->ce_state &&
-	    inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) {
-		u32 tmp_rcv_nxt;
-
-		/* Save current rcv_nxt. */
-		tmp_rcv_nxt = tp->rcv_nxt;
-
-		/* Generate previous ack with CE=1. */
-		tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
-		tp->rcv_nxt = ca->prior_rcv_nxt;
-
-		tcp_send_ack(sk);
-
-		/* Recover current rcv_nxt. */
-		tp->rcv_nxt = tmp_rcv_nxt;
-	}
+	    inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
+		__tcp_send_ack(sk, ca->prior_rcv_nxt);
 
 	ca->prior_rcv_nxt = tp->rcv_nxt;
 	ca->ce_state = 0;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index eafdcd81583f..3049d10a1476 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -160,8 +160,13 @@ static void tcp_event_data_sent(struct tcp_sock *tp,
 }
 
 /* Account for an ACK we sent. */
-static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts)
+static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts,
+				      u32 rcv_nxt)
 {
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	if (unlikely(rcv_nxt != tp->rcv_nxt))
+		return;  /* Special ACK sent by DCTCP to reflect ECN */
 	tcp_dec_quickack_mode(sk, pkts);
 	inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
 }
@@ -1149,7 +1154,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 	icsk->icsk_af_ops->send_check(sk, skb);
 
 	if (likely(tcb->tcp_flags & TCPHDR_ACK))
-		tcp_event_ack_sent(sk, tcp_skb_pcount(skb));
+		tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt);
 
 	if (skb->len != tcp_header_size) {
 		tcp_event_data_sent(tp, sk);
@@ -3627,12 +3632,12 @@ void __tcp_send_ack(struct sock *sk, u32 rcv_nxt)
 	/* Send it off, this clears delayed acks for us. */
 	__tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0, rcv_nxt);
 }
+EXPORT_SYMBOL_GPL(__tcp_send_ack);
 
 void tcp_send_ack(struct sock *sk)
 {
 	__tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt);
 }
-EXPORT_SYMBOL_GPL(tcp_send_ack);
 
 /* This routine sends a packet with an out of date sequence
  * number. It assumes the other end will try to ack it.
-- 
2.17.1


From ad29f96b85a3e45108f1d9cc1f163cb6f5d47c09 Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Wed, 18 Jul 2018 13:56:36 -0700
Subject: [PATCH 11/34] tcp: do not delay ACK in DCTCP upon CE status change

[ Upstream commit a0496ef2c23b3b180902dd185d0d63ccbc624cf8 ]

Per DCTCP RFC8257 (Section 3.2) the ACK reflecting the CE status change
has to be sent immediately so the sender can respond quickly:

""" When receiving packets, the CE codepoint MUST be processed as follows:

   1.  If the CE codepoint is set and DCTCP.CE is false, set DCTCP.CE to
       true and send an immediate ACK.

   2.  If the CE codepoint is not set and DCTCP.CE is true, set DCTCP.CE
       to false and send an immediate ACK.
"""

Previously DCTCP implementation may continue to delay the ACK. This
patch fixes that to implement the RFC by forcing an immediate ACK.

Tested with this packetdrill script provided by Larry Brakmo

0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
0.000 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
0.000 setsockopt(3, SOL_TCP, TCP_CONGESTION, "dctcp", 5) = 0
0.000 bind(3, ..., ...) = 0
0.000 listen(3, 1) = 0

0.100 < [ect0] SEW 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
0.100 > SE. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
0.110 < [ect0] . 1:1(0) ack 1 win 257
0.200 accept(3, ..., ...) = 4
   +0 setsockopt(4, SOL_SOCKET, SO_DEBUG, [1], 4) = 0

0.200 < [ect0] . 1:1001(1000) ack 1 win 257
0.200 > [ect01] . 1:1(0) ack 1001

0.200 write(4, ..., 1) = 1
0.200 > [ect01] P. 1:2(1) ack 1001

0.200 < [ect0] . 1001:2001(1000) ack 2 win 257
+0.005 < [ce] . 2001:3001(1000) ack 2 win 257

+0.000 > [ect01] . 2:2(0) ack 2001
// Previously the ACK below would be delayed by 40ms
+0.000 > [ect01] E. 2:2(0) ack 3001

+0.500 < F. 9501:9501(0) ack 4 win 257

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h    |  1 +
 net/ipv4/tcp_dctcp.c | 30 ++++++++++++++++++------------
 net/ipv4/tcp_input.c |  3 ++-
 3 files changed, 21 insertions(+), 13 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index d4ea41d76946..c1ba68e45f20 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -342,6 +342,7 @@ ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos,
 			struct pipe_inode_info *pipe, size_t len,
 			unsigned int flags);
 
+void tcp_enter_quickack_mode(struct sock *sk);
 static inline void tcp_dec_quickack_mode(struct sock *sk,
 					 const unsigned int pkts)
 {
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 39d96d27ff94..c78fb53988a1 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -131,12 +131,15 @@ static void dctcp_ce_state_0_to_1(struct sock *sk)
 	struct dctcp *ca = inet_csk_ca(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	/* State has changed from CE=0 to CE=1 and delayed
-	 * ACK has not sent yet.
-	 */
-	if (!ca->ce_state &&
-	    inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
-		__tcp_send_ack(sk, ca->prior_rcv_nxt);
+	if (!ca->ce_state) {
+		/* State has changed from CE=0 to CE=1, force an immediate
+		 * ACK to reflect the new CE state. If an ACK was delayed,
+		 * send that first to reflect the prior CE state.
+		 */
+		if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
+			__tcp_send_ack(sk, ca->prior_rcv_nxt);
+		tcp_enter_quickack_mode(sk);
+	}
 
 	ca->prior_rcv_nxt = tp->rcv_nxt;
 	ca->ce_state = 1;
@@ -149,12 +152,15 @@ static void dctcp_ce_state_1_to_0(struct sock *sk)
 	struct dctcp *ca = inet_csk_ca(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	/* State has changed from CE=1 to CE=0 and delayed
-	 * ACK has not sent yet.
-	 */
-	if (ca->ce_state &&
-	    inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
-		__tcp_send_ack(sk, ca->prior_rcv_nxt);
+	if (ca->ce_state) {
+		/* State has changed from CE=1 to CE=0, force an immediate
+		 * ACK to reflect the new CE state. If an ACK was delayed,
+		 * send that first to reflect the prior CE state.
+		 */
+		if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
+			__tcp_send_ack(sk, ca->prior_rcv_nxt);
+		tcp_enter_quickack_mode(sk);
+	}
 
 	ca->prior_rcv_nxt = tp->rcv_nxt;
 	ca->ce_state = 0;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 1f25ebab25d2..ba358b7369c4 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -195,13 +195,14 @@ static void tcp_incr_quickack(struct sock *sk)
 		icsk->icsk_ack.quick = min(quickacks, TCP_MAX_QUICKACKS);
 }
 
-static void tcp_enter_quickack_mode(struct sock *sk)
+void tcp_enter_quickack_mode(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	tcp_incr_quickack(sk);
 	icsk->icsk_ack.pingpong = 0;
 	icsk->icsk_ack.ato = TCP_ATO_MIN;
 }
+EXPORT_SYMBOL(tcp_enter_quickack_mode);
 
 /* Send ACKs quickly, if "quick" count is not exhausted
  * and the session is not interactive.
-- 
2.17.1


From 29f388a0313693ef90e7f8351adeb332201a2cfe Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 9 Jul 2018 16:41:40 -0700
Subject: [PATCH 12/34] net/mlx5: E-Switch, UBSAN fix undefined behavior in
 mlx5_eswitch_mode

[ Upstream commit 443a858158d35916e572b75667ca4924a6af2182 ]

With debug kernel UBSAN detects the following issue, which might happen
when eswitch instance is not created, fix this by testing the eswitch
pointer before returning the eswitch mode, if not set return mode =
SRIOV_NONE.

[   32.528951] UBSAN: Undefined behaviour in drivers/net/ethernet/mellanox/mlx5/core/eswitch.c:2219:12
[   32.528951] member access within null pointer of type 'struct mlx5_eswitch'
[   32.528951] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 4.18.0-rc3-dirty #181
[   32.528951] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.11.0-0-g63451fca13-prebuilt.qemu-project.org 04/01/2014
[   32.528951] Call Trace:
[   32.528951]  dump_stack+0xc7/0x13b
[   32.528951]  ? show_regs_print_info+0x5/0x5
[   32.528951]  ? __pm_runtime_use_autosuspend+0x140/0x140
[   32.528951]  ubsan_epilogue+0x9/0x49
[   32.528951]  ubsan_type_mismatch_common+0x1f9/0x2c0
[   32.528951]  ? ucs2_as_utf8+0x310/0x310
[   32.528951]  ? device_initialize+0x229/0x2e0
[   32.528951]  __ubsan_handle_type_mismatch+0x9f/0xc9
[   32.528951]  ? __ubsan_handle_divrem_overflow+0x19b/0x19b
[   32.578008]  ? ib_device_get_by_index+0xf0/0xf0
[   32.578008]  mlx5_eswitch_mode+0x30/0x40
[   32.578008]  mlx5_ib_add+0x1e0/0x4a0

Fixes: 57cbd893c4c5 ("net/mlx5: E-Switch, Move representors definition to a global scope")
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index c3a18ddf5dba..0a75e9d441e6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -2221,6 +2221,6 @@ int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,
 
 u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw)
 {
-	return esw->mode;
+	return ESW_ALLOWED(esw) ? esw->mode : SRIOV_NONE;
 }
 EXPORT_SYMBOL_GPL(mlx5_eswitch_mode);
-- 
2.17.1


From a8552d760b0e1117f5830d403e423f6470a58c2f Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Tue, 24 Jul 2018 22:21:04 +0200
Subject: [PATCH 13/34] r8169: restore previous behavior to accept BIOS WoL
 settings

[ Upstream commit 18041b523692038d41751fd8046638c356d77a36 ]

Commit 7edf6d314cd0 tried to resolve an inconsistency (BIOS WoL
settings are accepted, but device isn't wakeup-enabled) resulting
from a previous broken-BIOS workaround by making disabled WoL the
default.
This however had some side effects, most likely due to a broken BIOS
some systems don't properly resume from suspend when the MagicPacket
WoL bit isn't set in the chip, see
https://bugzilla.kernel.org/show_bug.cgi?id=200195
Therefore restore the WoL behavior from 4.16.

Reported-by: Albert Astals Cid <aacid@kde.org>
Fixes: 7edf6d314cd0 ("r8169: disable WOL per default")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index c7aac1fc99e8..764b25fa470c 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -8272,8 +8272,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		return rc;
 	}
 
-	/* override BIOS settings, use userspace tools to enable WOL */
-	__rtl8169_set_wol(tp, 0);
+	tp->saved_wolopts = __rtl8169_get_wol(tp);
 
 	if (rtl_tbi_enabled(tp)) {
 		tp->set_speed = rtl8169_set_speed_tbi;
-- 
2.17.1


From 391a12623ed6c69d1f7bba5c9d26aa08b38290d5 Mon Sep 17 00:00:00 2001
From: Doron Roberts-Kedes <doronrk@fb.com>
Date: Wed, 18 Jul 2018 16:22:27 -0700
Subject: [PATCH 14/34] tls: check RCV_SHUTDOWN in tls_wait_data

[ Upstream commit fcf4793e278edede8fcd748198d12128037e526c ]

The current code does not check sk->sk_shutdown & RCV_SHUTDOWN.
tls_sw_recvmsg may return a positive value in the case where bytes have
already been copied when the socket is shutdown. sk->sk_err has been
cleared, causing the tls_wait_data to hang forever on a subsequent
invocation. Checking sk->sk_shutdown & RCV_SHUTDOWN, as in tcp_recvmsg,
fixes this problem.

Fixes: c46234ebb4d1 ("tls: RX path for ktls")
Acked-by: Dave Watson <davejwatson@fb.com>
Signed-off-by: Doron Roberts-Kedes <doronrk@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 9a7f91232de8..60708a4ebed4 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -646,6 +646,9 @@ static struct sk_buff *tls_wait_data(struct sock *sk, int flags,
 			return NULL;
 		}
 
+		if (sk->sk_shutdown & RCV_SHUTDOWN)
+			return NULL;
+
 		if (sock_flag(sk, SOCK_DONE))
 			return NULL;
 
-- 
2.17.1


From bb531d36a7ba70e43a7e278023ab90c5f0d59e27 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Wed, 18 Apr 2018 13:45:11 +0300
Subject: [PATCH 15/34] net/mlx5e: Add ingress/egress indication for offloaded
 TC flows

[ Upstream commit 60bd4af814fec164c42bdd2efd7984b85d6b1e1e ]

When an e-switch TC rule is offloaded through the egdev (egress
device) mechanism, we treat this as egress, all other cases (NIC
and e-switch) are considred ingress.

This is preparation step that will allow us to  identify "wrong"
stat/del offload calls made by the TC core on egdev based flows and
ignore them.

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Paul Blakey <paulb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h  |  3 --
 .../net/ethernet/mellanox/mlx5/core/en_main.c | 15 ++++----
 .../net/ethernet/mellanox/mlx5/core/en_rep.c  | 32 ++++++++++++----
 .../net/ethernet/mellanox/mlx5/core/en_tc.c   | 38 ++++++++++++++-----
 .../net/ethernet/mellanox/mlx5/core/en_tc.h   | 13 +++++--
 5 files changed, 70 insertions(+), 31 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 30cad07be2b5..065ff87f0bef 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -1092,9 +1092,6 @@ int mlx5e_ethtool_get_ts_info(struct mlx5e_priv *priv,
 int mlx5e_ethtool_flash_device(struct mlx5e_priv *priv,
 			       struct ethtool_flash *flash);
 
-int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
-			    void *cb_priv);
-
 /* mlx5e generic netdev management API */
 struct net_device*
 mlx5e_create_netdev(struct mlx5_core_dev *mdev, const struct mlx5e_profile *profile,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index d3a1a2281e77..fdf40812a2a9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3093,22 +3093,23 @@ static int mlx5e_setup_tc_mqprio(struct net_device *netdev,
 
 #ifdef CONFIG_MLX5_ESWITCH
 static int mlx5e_setup_tc_cls_flower(struct mlx5e_priv *priv,
-				     struct tc_cls_flower_offload *cls_flower)
+				     struct tc_cls_flower_offload *cls_flower,
+				     int flags)
 {
 	switch (cls_flower->command) {
 	case TC_CLSFLOWER_REPLACE:
-		return mlx5e_configure_flower(priv, cls_flower);
+		return mlx5e_configure_flower(priv, cls_flower, flags);
 	case TC_CLSFLOWER_DESTROY:
-		return mlx5e_delete_flower(priv, cls_flower);
+		return mlx5e_delete_flower(priv, cls_flower, flags);
 	case TC_CLSFLOWER_STATS:
-		return mlx5e_stats_flower(priv, cls_flower);
+		return mlx5e_stats_flower(priv, cls_flower, flags);
 	default:
 		return -EOPNOTSUPP;
 	}
 }
 
-int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
-			    void *cb_priv)
+static int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
+				   void *cb_priv)
 {
 	struct mlx5e_priv *priv = cb_priv;
 
@@ -3117,7 +3118,7 @@ int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 
 	switch (type) {
 	case TC_SETUP_CLSFLOWER:
-		return mlx5e_setup_tc_cls_flower(priv, type_data);
+		return mlx5e_setup_tc_cls_flower(priv, type_data, MLX5E_TC_INGRESS);
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 286565862341..c88eb80278dd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -723,15 +723,31 @@ static int mlx5e_rep_get_phys_port_name(struct net_device *dev,
 
 static int
 mlx5e_rep_setup_tc_cls_flower(struct mlx5e_priv *priv,
-			      struct tc_cls_flower_offload *cls_flower)
+			      struct tc_cls_flower_offload *cls_flower, int flags)
 {
 	switch (cls_flower->command) {
 	case TC_CLSFLOWER_REPLACE:
-		return mlx5e_configure_flower(priv, cls_flower);
+		return mlx5e_configure_flower(priv, cls_flower, flags);
 	case TC_CLSFLOWER_DESTROY:
-		return mlx5e_delete_flower(priv, cls_flower);
+		return mlx5e_delete_flower(priv, cls_flower, flags);
 	case TC_CLSFLOWER_STATS:
-		return mlx5e_stats_flower(priv, cls_flower);
+		return mlx5e_stats_flower(priv, cls_flower, flags);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int mlx5e_rep_setup_tc_cb_egdev(enum tc_setup_type type, void *type_data,
+				       void *cb_priv)
+{
+	struct mlx5e_priv *priv = cb_priv;
+
+	if (!tc_cls_can_offload_and_chain0(priv->netdev, type_data))
+		return -EOPNOTSUPP;
+
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		return mlx5e_rep_setup_tc_cls_flower(priv, type_data, MLX5E_TC_EGRESS);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -747,7 +763,7 @@ static int mlx5e_rep_setup_tc_cb(enum tc_setup_type type, void *type_data,
 
 	switch (type) {
 	case TC_SETUP_CLSFLOWER:
-		return mlx5e_rep_setup_tc_cls_flower(priv, type_data);
+		return mlx5e_rep_setup_tc_cls_flower(priv, type_data, MLX5E_TC_INGRESS);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -1111,7 +1127,7 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 
 	uplink_rpriv = mlx5_eswitch_get_uplink_priv(dev->priv.eswitch, REP_ETH);
 	upriv = netdev_priv(uplink_rpriv->netdev);
-	err = tc_setup_cb_egdev_register(netdev, mlx5e_setup_tc_block_cb,
+	err = tc_setup_cb_egdev_register(netdev, mlx5e_rep_setup_tc_cb_egdev,
 					 upriv);
 	if (err)
 		goto err_neigh_cleanup;
@@ -1126,7 +1142,7 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 	return 0;
 
 err_egdev_cleanup:
-	tc_setup_cb_egdev_unregister(netdev, mlx5e_setup_tc_block_cb,
+	tc_setup_cb_egdev_unregister(netdev, mlx5e_rep_setup_tc_cb_egdev,
 				     upriv);
 
 err_neigh_cleanup:
@@ -1155,7 +1171,7 @@ mlx5e_vport_rep_unload(struct mlx5_eswitch_rep *rep)
 	uplink_rpriv = mlx5_eswitch_get_uplink_priv(priv->mdev->priv.eswitch,
 						    REP_ETH);
 	upriv = netdev_priv(uplink_rpriv->netdev);
-	tc_setup_cb_egdev_unregister(netdev, mlx5e_setup_tc_block_cb,
+	tc_setup_cb_egdev_unregister(netdev, mlx5e_rep_setup_tc_cb_egdev,
 				     upriv);
 	mlx5e_rep_neigh_cleanup(rpriv);
 	mlx5e_detach_netdev(priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index b94276db3ce9..a1b0abc24ef5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -61,12 +61,16 @@ struct mlx5_nic_flow_attr {
 	struct mlx5_flow_table	*hairpin_ft;
 };
 
+#define MLX5E_TC_FLOW_BASE (MLX5E_TC_LAST_EXPORTED_BIT + 1)
+
 enum {
-	MLX5E_TC_FLOW_ESWITCH	= BIT(0),
-	MLX5E_TC_FLOW_NIC	= BIT(1),
-	MLX5E_TC_FLOW_OFFLOADED	= BIT(2),
-	MLX5E_TC_FLOW_HAIRPIN	= BIT(3),
-	MLX5E_TC_FLOW_HAIRPIN_RSS = BIT(4),
+	MLX5E_TC_FLOW_INGRESS	= MLX5E_TC_INGRESS,
+	MLX5E_TC_FLOW_EGRESS	= MLX5E_TC_EGRESS,
+	MLX5E_TC_FLOW_ESWITCH	= BIT(MLX5E_TC_FLOW_BASE),
+	MLX5E_TC_FLOW_NIC	= BIT(MLX5E_TC_FLOW_BASE + 1),
+	MLX5E_TC_FLOW_OFFLOADED	= BIT(MLX5E_TC_FLOW_BASE + 2),
+	MLX5E_TC_FLOW_HAIRPIN	= BIT(MLX5E_TC_FLOW_BASE + 3),
+	MLX5E_TC_FLOW_HAIRPIN_RSS = BIT(MLX5E_TC_FLOW_BASE + 4),
 };
 
 struct mlx5e_tc_flow {
@@ -2566,8 +2570,20 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 	return err;
 }
 
+static void get_flags(int flags, u8 *flow_flags)
+{
+	u8 __flow_flags = 0;
+
+	if (flags & MLX5E_TC_INGRESS)
+		__flow_flags |= MLX5E_TC_FLOW_INGRESS;
+	if (flags & MLX5E_TC_EGRESS)
+		__flow_flags |= MLX5E_TC_FLOW_EGRESS;
+
+	*flow_flags = __flow_flags;
+}
+
 int mlx5e_configure_flower(struct mlx5e_priv *priv,
-			   struct tc_cls_flower_offload *f)
+			   struct tc_cls_flower_offload *f, int flags)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	struct mlx5e_tc_flow_parse_attr *parse_attr;
@@ -2576,11 +2592,13 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv,
 	int attr_size, err = 0;
 	u8 flow_flags = 0;
 
+	get_flags(flags, &flow_flags);
+
 	if (esw && esw->mode == SRIOV_OFFLOADS) {
-		flow_flags = MLX5E_TC_FLOW_ESWITCH;
+		flow_flags |= MLX5E_TC_FLOW_ESWITCH;
 		attr_size  = sizeof(struct mlx5_esw_flow_attr);
 	} else {
-		flow_flags = MLX5E_TC_FLOW_NIC;
+		flow_flags |= MLX5E_TC_FLOW_NIC;
 		attr_size  = sizeof(struct mlx5_nic_flow_attr);
 	}
 
@@ -2639,7 +2657,7 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv,
 }
 
 int mlx5e_delete_flower(struct mlx5e_priv *priv,
-			struct tc_cls_flower_offload *f)
+			struct tc_cls_flower_offload *f, int flags)
 {
 	struct mlx5e_tc_flow *flow;
 	struct mlx5e_tc_table *tc = &priv->fs.tc;
@@ -2659,7 +2677,7 @@ int mlx5e_delete_flower(struct mlx5e_priv *priv,
 }
 
 int mlx5e_stats_flower(struct mlx5e_priv *priv,
-		       struct tc_cls_flower_offload *f)
+		       struct tc_cls_flower_offload *f, int flags)
 {
 	struct mlx5e_tc_table *tc = &priv->fs.tc;
 	struct mlx5e_tc_flow *flow;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index c14c263a739b..2255345c2e18 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -38,16 +38,23 @@
 #define MLX5E_TC_FLOW_ID_MASK 0x0000ffff
 
 #ifdef CONFIG_MLX5_ESWITCH
+
+enum {
+	MLX5E_TC_INGRESS = BIT(0),
+	MLX5E_TC_EGRESS  = BIT(1),
+	MLX5E_TC_LAST_EXPORTED_BIT = 1,
+};
+
 int mlx5e_tc_init(struct mlx5e_priv *priv);
 void mlx5e_tc_cleanup(struct mlx5e_priv *priv);
 
 int mlx5e_configure_flower(struct mlx5e_priv *priv,
-			   struct tc_cls_flower_offload *f);
+			   struct tc_cls_flower_offload *f, int flags);
 int mlx5e_delete_flower(struct mlx5e_priv *priv,
-			struct tc_cls_flower_offload *f);
+			struct tc_cls_flower_offload *f, int flags);
 
 int mlx5e_stats_flower(struct mlx5e_priv *priv,
-		       struct tc_cls_flower_offload *f);
+		       struct tc_cls_flower_offload *f, int flags);
 
 struct mlx5e_encap_entry;
 void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
-- 
2.17.1


From 62e4551d02214a8319e004796df49ae2137890d8 Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@mellanox.com>
Date: Thu, 12 Jul 2018 18:25:59 +0300
Subject: [PATCH 16/34] net/mlx5e: Only allow offloading decap egress (egdev)
 flows

[ Upstream commit 7e29392eee7a1e3318eeb1099807264a49f60e33 ]

We get egress rules through the egdev mechanism when the ingress device
is not supporting offload, with the expected use-case of tunnel decap
ingress rule set on shared tunnel device.

Make sure to offload egress/egdev rules only if decap action (tunnel key
unset) exists there and err otherwise.

Fixes: 717503b9cf57 ("net: sched: convert cls_flower->egress_dev users to tc_setup_cb_egdev infra")
Signed-off-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index a1b0abc24ef5..a0ba6cfc9092 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1894,6 +1894,10 @@ static bool actions_match_supported(struct mlx5e_priv *priv,
 	else
 		actions = flow->nic_attr->action;
 
+	if (flow->flags & MLX5E_TC_FLOW_EGRESS &&
+	    !(actions & MLX5_FLOW_CONTEXT_ACTION_DECAP))
+		return false;
+
 	if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
 		return modify_header_match_supported(&parse_attr->spec, exts);
 
-- 
2.17.1


From 6ac7a14c3cfc9dce68e4764c6484ffaf62920d33 Mon Sep 17 00:00:00 2001
From: Shay Agroskin <shayag@mellanox.com>
Date: Wed, 27 Jun 2018 15:43:07 +0300
Subject: [PATCH 17/34] net/mlx5e: Refine ets validation function

[ Upstream commit e279d634f3d57452eb106a0c0e99a6add3fba1a6 ]

Removed an error message received when configuring ETS total
bandwidth to be zero.
Our hardware doesn't support such configuration, so we shall
reject it in the driver. Nevertheless, we removed the error message
in order to eliminate error messages caused by old userspace tools
who try to pass such configuration.

Fixes: ff0891915cd7 ("net/mlx5e: Fix ETS BW check")
Signed-off-by: Shay Agroskin <shayag@mellanox.com>
Reviewed-by: Huy Nguyen <huyn@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en_dcbnl.c  | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index c641d5656b2d..0c6015ce85fd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -272,7 +272,8 @@ int mlx5e_dcbnl_ieee_setets_core(struct mlx5e_priv *priv, struct ieee_ets *ets)
 }
 
 static int mlx5e_dbcnl_validate_ets(struct net_device *netdev,
-				    struct ieee_ets *ets)
+				    struct ieee_ets *ets,
+				    bool zero_sum_allowed)
 {
 	bool have_ets_tc = false;
 	int bw_sum = 0;
@@ -297,8 +298,9 @@ static int mlx5e_dbcnl_validate_ets(struct net_device *netdev,
 	}
 
 	if (have_ets_tc && bw_sum != 100) {
-		netdev_err(netdev,
-			   "Failed to validate ETS: BW sum is illegal\n");
+		if (bw_sum || (!bw_sum && !zero_sum_allowed))
+			netdev_err(netdev,
+				   "Failed to validate ETS: BW sum is illegal\n");
 		return -EINVAL;
 	}
 	return 0;
@@ -313,7 +315,7 @@ static int mlx5e_dcbnl_ieee_setets(struct net_device *netdev,
 	if (!MLX5_CAP_GEN(priv->mdev, ets))
 		return -EOPNOTSUPP;
 
-	err = mlx5e_dbcnl_validate_ets(netdev, ets);
+	err = mlx5e_dbcnl_validate_ets(netdev, ets, false);
 	if (err)
 		return err;
 
@@ -613,12 +615,9 @@ static u8 mlx5e_dcbnl_setall(struct net_device *netdev)
 			  ets.prio_tc[i]);
 	}
 
-	err = mlx5e_dbcnl_validate_ets(netdev, &ets);
-	if (err) {
-		netdev_err(netdev,
-			   "%s, Failed to validate ETS: %d\n", __func__, err);
+	err = mlx5e_dbcnl_validate_ets(netdev, &ets, true);
+	if (err)
 		goto out;
-	}
 
 	err = mlx5e_dcbnl_ieee_setets_core(priv, &ets);
 	if (err) {
-- 
2.17.1


From f1ef9c58e6a6a25456cd23acea654b97c8793f40 Mon Sep 17 00:00:00 2001
From: John Hurley <john.hurley@netronome.com>
Date: Fri, 20 Jul 2018 21:07:54 -0700
Subject: [PATCH 18/34] nfp: flower: ensure dead neighbour entries are not
 offloaded

[ Upstream commit b809ec869b2cf2af053ffd99e5a46ab600e94aa2 ]

Previously only the neighbour state was checked to decide if an offloaded
entry should be removed. However, there can be situations when the entry
is dead but still marked as valid. This can lead to dead entries not
being removed from fw tables or even incorrect data being added.

Check the entry dead bit before deciding if it should be added to or
removed from fw neighbour tables.

Fixes: 8e6a9046b66a ("nfp: flower vxlan neighbour offload")
Signed-off-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
index ec524d97869d..5ef61132604e 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
@@ -317,7 +317,7 @@ nfp_tun_write_neigh(struct net_device *netdev, struct nfp_app *app,
 	payload.dst_ipv4 = flow->daddr;
 
 	/* If entry has expired send dst IP with all other fields 0. */
-	if (!(neigh->nud_state & NUD_VALID)) {
+	if (!(neigh->nud_state & NUD_VALID) || neigh->dead) {
 		nfp_tun_del_route_from_cache(app, payload.dst_ipv4);
 		/* Trigger ARP to verify invalid neighbour state. */
 		neigh_event_send(neigh, NULL);
-- 
2.17.1


From e9aa4d483cecdca4342981d7630bae55b587db12 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Mon, 23 Jul 2018 22:37:54 +0200
Subject: [PATCH 19/34] sock: fix sg page frag coalescing in sk_alloc_sg

[ Upstream commit 144fe2bfd236dc814eae587aea7e2af03dbdd755 ]

Current sg coalescing logic in sk_alloc_sg() (latter is used by tls and
sockmap) is not quite correct in that we do fetch the previous sg entry,
however the subsequent check whether the refilled page frag from the
socket is still the same as from the last entry with prior offset and
length matching the start of the current buffer is comparing always the
first sg list entry instead of the prior one.

Fixes: 3c4d7559159b ("tls: kernel TLS support")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Dave Watson <davejwatson@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index 3b6d02854e57..f82843756534 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2270,9 +2270,9 @@ int sk_alloc_sg(struct sock *sk, int len, struct scatterlist *sg,
 		pfrag->offset += use;
 
 		sge = sg + sg_curr - 1;
-		if (sg_curr > first_coalesce && sg_page(sg) == pfrag->page &&
-		    sg->offset + sg->length == orig_offset) {
-			sg->length += use;
+		if (sg_curr > first_coalesce && sg_page(sge) == pfrag->page &&
+		    sge->offset + sge->length == orig_offset) {
+			sge->length += use;
 		} else {
 			sge = sg + sg_curr;
 			sg_unmark_end(sge);
-- 
2.17.1


From 78046ee1039ca15b86948ace0032b9f761b5497d Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 19 Jul 2018 08:15:16 +0200
Subject: [PATCH 20/34] net: phy: consider PHY_IGNORE_INTERRUPT in
 phy_start_aneg_priv

[ Upstream commit 215d08a85b9acf5e1fe9dbf50f1774cde333efef ]

The situation described in the comment can occur also with
PHY_IGNORE_INTERRUPT, therefore change the condition to include it.

Fixes: f555f34fdc58 ("net: phy: fix auto-negotiation stall due to unavailable interrupt")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 05c1e8ef15e6..69a8106b9b98 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -514,7 +514,7 @@ static int phy_start_aneg_priv(struct phy_device *phydev, bool sync)
 	 * negotiation may already be done and aneg interrupt may not be
 	 * generated.
 	 */
-	if (phy_interrupt_is_valid(phydev) && (phydev->state == PHY_AN)) {
+	if (phydev->irq != PHY_POLL && phydev->state == PHY_AN) {
 		err = phy_aneg_done(phydev);
 		if (err > 0) {
 			trigger = true;
-- 
2.17.1


From 5cab175c1f3d7ea259b27b69f3bbd922910e8b33 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Fri, 20 Jul 2018 14:04:27 +0800
Subject: [PATCH 21/34] multicast: do not restore deleted record source filter
 mode to new one

There are two scenarios that we will restore deleted records. The first is
when device down and up(or unmap/remap). In this scenario the new filter
mode is same with previous one. Because we get it from in_dev->mc_list and
we do not touch it during device down and up.

The other scenario is when a new socket join a group which was just delete
and not finish sending status reports. In this scenario, we should use the
current filter mode instead of restore old one. Here are 4 cases in total.

old_socket        new_socket       before_fix       after_fix
  IN(A)             IN(A)           ALLOW(A)         ALLOW(A)
  IN(A)             EX( )           TO_IN( )         TO_EX( )
  EX( )             IN(A)           TO_EX( )         ALLOW(A)
  EX( )             EX( )           TO_EX( )         TO_EX( )

Fixes: 24803f38a5c0b (igmp: do not remove igmp souce list info when set link down)
Fixes: 1666d49e1d416 (mld: do not remove mld souce list info when set link down)
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/igmp.c  | 3 +--
 net/ipv6/mcast.c | 3 +--
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index b26a81a7de42..4af0625344a0 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -1201,8 +1201,7 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im)
 	if (pmc) {
 		im->interface = pmc->interface;
 		im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
-		im->sfmode = pmc->sfmode;
-		if (pmc->sfmode == MCAST_INCLUDE) {
+		if (im->sfmode == MCAST_INCLUDE) {
 			im->tomb = pmc->tomb;
 			im->sources = pmc->sources;
 			for (psf = im->sources; psf; psf = psf->sf_next)
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 793159d77d8a..0604a737eecf 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -771,8 +771,7 @@ static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im)
 	if (pmc) {
 		im->idev = pmc->idev;
 		im->mca_crcount = idev->mc_qrv;
-		im->mca_sfmode = pmc->mca_sfmode;
-		if (pmc->mca_sfmode == MCAST_INCLUDE) {
+		if (im->mca_sfmode == MCAST_INCLUDE) {
 			im->mca_tomb = pmc->mca_tomb;
 			im->mca_sources = pmc->mca_sources;
 			for (psf = im->mca_sources; psf; psf = psf->sf_next)
-- 
2.17.1


From f1678a1f88f0b56fbc6e5f783e246c559a4bb708 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Thu, 19 Jul 2018 12:41:18 -0700
Subject: [PATCH 22/34] net/ipv6: Fix linklocal to global address with VRF

[ Upstream commit 24b711edfc34bc45777a3f068812b7d1ed004a5d ]

Example setup:
    host: ip -6 addr add dev eth1 2001:db8:104::4
           where eth1 is enslaved to a VRF

    switch: ip -6 ro add 2001:db8:104::4/128 dev br1
            where br1 only has an LLA

           ping6 2001:db8:104::4
           ssh   2001:db8:104::4

(NOTE: UDP works fine if the PKTINFO has the address set to the global
address and ifindex is set to the index of eth1 with a destination an
LLA).

For ICMP, icmp6_iif needs to be updated to check if skb->dev is an
L3 master. If it is then return the ifindex from rt6i_idev similar
to what is done for loopback.

For TCP, restore the original tcp_v6_iif definition which is needed in
most places and add a new tcp_v6_iif_l3_slave that considers the
l3_slave variability. This latter check is only needed for socket
lookups.

Fixes: 9ff74384600a ("net: vrf: Handle ipv6 multicast and link-local addresses")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h   | 5 +++++
 net/ipv6/icmp.c     | 5 +++--
 net/ipv6/tcp_ipv6.c | 6 ++++--
 3 files changed, 12 insertions(+), 4 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index c1ba68e45f20..9cf770150539 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -828,6 +828,11 @@ struct tcp_skb_cb {
  * as TCP moves IP6CB into a different location in skb->cb[]
  */
 static inline int tcp_v6_iif(const struct sk_buff *skb)
+{
+	return TCP_SKB_CB(skb)->header.h6.iif;
+}
+
+static inline int tcp_v6_iif_l3_slave(const struct sk_buff *skb)
 {
 	bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags);
 
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index d8c4b6374377..ca893a798d8a 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -402,9 +402,10 @@ static int icmp6_iif(const struct sk_buff *skb)
 
 	/* for local traffic to local address, skb dev is the loopback
 	 * device. Check if there is a dst attached to the skb and if so
-	 * get the real device index.
+	 * get the real device index. Same is needed for replies to a link
+	 * local address on a device enslaved to an L3 master device
 	 */
-	if (unlikely(iif == LOOPBACK_IFINDEX)) {
+	if (unlikely(iif == LOOPBACK_IFINDEX || netif_is_l3_master(skb->dev))) {
 		const struct rt6_info *rt6 = skb_rt6_info(skb);
 
 		if (rt6)
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 5d4eb9d2c3a7..1adf7eb80d03 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -934,7 +934,8 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
 					   &tcp_hashinfo, NULL, 0,
 					   &ipv6h->saddr,
 					   th->source, &ipv6h->daddr,
-					   ntohs(th->source), tcp_v6_iif(skb),
+					   ntohs(th->source),
+					   tcp_v6_iif_l3_slave(skb),
 					   tcp_v6_sdif(skb));
 		if (!sk1)
 			goto out;
@@ -1605,7 +1606,8 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 					    skb, __tcp_hdrlen(th),
 					    &ipv6_hdr(skb)->saddr, th->source,
 					    &ipv6_hdr(skb)->daddr,
-					    ntohs(th->dest), tcp_v6_iif(skb),
+					    ntohs(th->dest),
+					    tcp_v6_iif_l3_slave(skb),
 					    sdif);
 		if (sk2) {
 			struct inet_timewait_sock *tw = inet_twsk(sk);
-- 
2.17.1


From e531bf69cda878333e267eab45da73508e05068d Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Sun, 8 Jul 2018 14:52:12 +0300
Subject: [PATCH 23/34] net/mlx5e: Don't allow aRFS for encapsulated packets

[ Upstream commit d2e1c57bcf9a07cbb67f30ecf238f298799bce1c ]

Driver is yet to support aRFS for encapsulated packets, return early
error in such case.

Fixes: 18c908e477dc ("net/mlx5e: Add accelerated RFS support")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
index 610d485c4b03..53a13a28f824 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
@@ -711,6 +711,9 @@ int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 	    skb->protocol != htons(ETH_P_IPV6))
 		return -EPROTONOSUPPORT;
 
+	if (skb->encapsulation)
+		return -EPROTONOSUPPORT;
+
 	arfs_t = arfs_get_table(arfs, arfs_get_ip_proto(skb), skb->protocol);
 	if (!arfs_t)
 		return -EPROTONOSUPPORT;
-- 
2.17.1


From b70a388c7c15a8524c316fe39b3c39891c1cbdf7 Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Sun, 8 Jul 2018 13:08:55 +0300
Subject: [PATCH 24/34] net/mlx5e: Fix quota counting in aRFS expire flow

[ Upstream commit 2630bae8018823c3b88788b69fb9f16ea3b4a11e ]

Quota should follow the amount of rules which do expire, and not the
number of rules that were examined, fixed that.

Fixes: 18c908e477dc ("net/mlx5e: Add accelerated RFS support")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
index 53a13a28f824..dda281cff880 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
@@ -381,14 +381,14 @@ static void arfs_may_expire_flow(struct mlx5e_priv *priv)
 	HLIST_HEAD(del_list);
 	spin_lock_bh(&priv->fs.arfs.arfs_lock);
 	mlx5e_for_each_arfs_rule(arfs_rule, htmp, priv->fs.arfs.arfs_tables, i, j) {
-		if (quota++ > MLX5E_ARFS_EXPIRY_QUOTA)
-			break;
 		if (!work_pending(&arfs_rule->arfs_work) &&
 		    rps_may_expire_flow(priv->netdev,
 					arfs_rule->rxq, arfs_rule->flow_id,
 					arfs_rule->filter_id)) {
 			hlist_del_init(&arfs_rule->hlist);
 			hlist_add_head(&arfs_rule->hlist, &del_list);
+			if (quota++ > MLX5E_ARFS_EXPIRY_QUOTA)
+				break;
 		}
 	}
 	spin_unlock_bh(&priv->fs.arfs.arfs_lock);
-- 
2.17.1


From 36637c619c6a6b18de14444e9c2723aa910cd024 Mon Sep 17 00:00:00 2001
From: Ariel Levkovich <lariel@mellanox.com>
Date: Mon, 25 Jun 2018 19:12:02 +0300
Subject: [PATCH 25/34] net/mlx5: Adjust clock overflow work period

[ Upstream commit 33180bee86a8940a84950edca46315cd9dd6deb5 ]

When driver converts HW timestamp to wall clock time it subtracts
the last saved cycle counter from the HW timestamp and converts the
difference to nanoseconds.
The conversion is done by multiplying the cycles difference with the
clock multiplier value as a first step and therefore the cycles
difference should be small enough so that the multiplication product
doesn't exceed 64bit.

The overflow handling routine is in charge of updating the last saved
cycle counter in driver and it is called periodically using kernel
delayed workqueue.

The delay period for this work is calculated using the max HW cycle
counter value (a 41 bit mask) as a base which doesn't take the 64bit
limit into account so the delay period may be incorrect and too
long to prevent a large difference between the HW counter and the last
saved counter in SW.

This change adjusts the work period for the HW clock overflow work by
taking the minimum between the previous value and the quotient of max
u64 value and the clock multiplier value.

Fixes: ef9814deafd0 ("net/mlx5e: Add HW timestamping (TS) support")
Signed-off-by: Ariel Levkovich <lariel@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index 857035583ccd..c14e7fc11d8a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -487,6 +487,7 @@ void mlx5_pps_event(struct mlx5_core_dev *mdev,
 void mlx5_init_clock(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_clock *clock = &mdev->clock;
+	u64 overflow_cycles;
 	u64 ns;
 	u64 frac = 0;
 	u32 dev_freq;
@@ -510,10 +511,17 @@ void mlx5_init_clock(struct mlx5_core_dev *mdev)
 
 	/* Calculate period in seconds to call the overflow watchdog - to make
 	 * sure counter is checked at least once every wrap around.
+	 * The period is calculated as the minimum between max HW cycles count
+	 * (The clock source mask) and max amount of cycles that can be
+	 * multiplied by clock multiplier where the result doesn't exceed
+	 * 64bits.
 	 */
-	ns = cyclecounter_cyc2ns(&clock->cycles, clock->cycles.mask,
+	overflow_cycles = div64_u64(~0ULL >> 1, clock->cycles.mult);
+	overflow_cycles = min(overflow_cycles, clock->cycles.mask >> 1);
+
+	ns = cyclecounter_cyc2ns(&clock->cycles, overflow_cycles,
 				 frac, &frac);
-	do_div(ns, NSEC_PER_SEC / 2 / HZ);
+	do_div(ns, NSEC_PER_SEC / HZ);
 	clock->overflow_period = ns;
 
 	mdev->clock_info_page = alloc_page(GFP_KERNEL);
-- 
2.17.1


From abaa668d031277782766da08b08ff4ec9046b475 Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Fri, 20 Jul 2018 13:21:01 -0700
Subject: [PATCH 26/34] rtnetlink: add rtnl_link_state check in
 rtnl_configure_link

[ Upstream commit 5025f7f7d506fba9b39e7fe8ca10f6f34cb9bc2d ]

rtnl_configure_link sets dev->rtnl_link_state to
RTNL_LINK_INITIALIZED and unconditionally calls
__dev_notify_flags to notify user-space of dev flags.

current call sequence for rtnl_configure_link
rtnetlink_newlink
    rtnl_link_ops->newlink
    rtnl_configure_link (unconditionally notifies userspace of
                         default and new dev flags)

If a newlink handler wants to call rtnl_configure_link
early, we will end up with duplicate notifications to
user-space.

This patch fixes rtnl_configure_link to check rtnl_link_state
and call __dev_notify_flags with gchanges = 0 if already
RTNL_LINK_INITIALIZED.

Later in the series, this patch will help the following sequence
where a driver implementing newlink can call rtnl_configure_link
to initialize the link early.

makes the following call sequence work:
rtnetlink_newlink
    rtnl_link_ops->newlink (vxlan) -> rtnl_configure_link (initializes
                                                link and notifies
                                                user-space of default
                                                dev flags)
    rtnl_configure_link (updates dev flags if requested by user ifm
                         and notifies user-space of new dev flags)

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 19f6ab5de6e1..3dab3c7b6831 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2749,9 +2749,12 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm)
 			return err;
 	}
 
-	dev->rtnl_link_state = RTNL_LINK_INITIALIZED;
-
-	__dev_notify_flags(dev, old_flags, ~0U);
+	if (dev->rtnl_link_state == RTNL_LINK_INITIALIZED) {
+		__dev_notify_flags(dev, old_flags, 0U);
+	} else {
+		dev->rtnl_link_state = RTNL_LINK_INITIALIZED;
+		__dev_notify_flags(dev, old_flags, ~0U);
+	}
 	return 0;
 }
 EXPORT_SYMBOL(rtnl_configure_link);
-- 
2.17.1


From b689505e8ce6dcc27ab0ab09f623916a8594d860 Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Fri, 20 Jul 2018 13:21:02 -0700
Subject: [PATCH 27/34] vxlan: add new fdb alloc and create helpers

[ Upstream commit 7431016b107c95cb5b2014aa1901fcb115f746bc ]

- Add new vxlan_fdb_alloc helper
- rename existing vxlan_fdb_create into vxlan_fdb_update:
        because it really creates or updates an existing
        fdb entry
- move new fdb creation into a separate vxlan_fdb_create

Main motivation for this change is to introduce the ability
to decouple vxlan fdb creation and notify, used in a later patch.

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 91 ++++++++++++++++++++++++++++++---------------
 1 file changed, 62 insertions(+), 29 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 4b170599fa5e..5a26b6689990 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -636,8 +636,61 @@ static int vxlan_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff)
 	return eth_gro_complete(skb, nhoff + sizeof(struct vxlanhdr));
 }
 
-/* Add new entry to forwarding table -- assumes lock held */
+static struct vxlan_fdb *vxlan_fdb_alloc(struct vxlan_dev *vxlan,
+					 const u8 *mac, __u16 state,
+					 __be32 src_vni, __u8 ndm_flags)
+{
+	struct vxlan_fdb *f;
+
+	f = kmalloc(sizeof(*f), GFP_ATOMIC);
+	if (!f)
+		return NULL;
+	f->state = state;
+	f->flags = ndm_flags;
+	f->updated = f->used = jiffies;
+	f->vni = src_vni;
+	INIT_LIST_HEAD(&f->remotes);
+	memcpy(f->eth_addr, mac, ETH_ALEN);
+
+	return f;
+}
+
 static int vxlan_fdb_create(struct vxlan_dev *vxlan,
+			    const u8 *mac, union vxlan_addr *ip,
+			    __u16 state, __be16 port, __be32 src_vni,
+			    __be32 vni, __u32 ifindex, __u8 ndm_flags,
+			    struct vxlan_fdb **fdb)
+{
+	struct vxlan_rdst *rd = NULL;
+	struct vxlan_fdb *f;
+	int rc;
+
+	if (vxlan->cfg.addrmax &&
+	    vxlan->addrcnt >= vxlan->cfg.addrmax)
+		return -ENOSPC;
+
+	netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip);
+	f = vxlan_fdb_alloc(vxlan, mac, state, src_vni, ndm_flags);
+	if (!f)
+		return -ENOMEM;
+
+	rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd);
+	if (rc < 0) {
+		kfree(f);
+		return rc;
+	}
+
+	++vxlan->addrcnt;
+	hlist_add_head_rcu(&f->hlist,
+			   vxlan_fdb_head(vxlan, mac, src_vni));
+
+	*fdb = f;
+
+	return 0;
+}
+
+/* Add new entry to forwarding table -- assumes lock held */
+static int vxlan_fdb_update(struct vxlan_dev *vxlan,
 			    const u8 *mac, union vxlan_addr *ip,
 			    __u16 state, __u16 flags,
 			    __be16 port, __be32 src_vni, __be32 vni,
@@ -687,37 +740,17 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan,
 		if (!(flags & NLM_F_CREATE))
 			return -ENOENT;
 
-		if (vxlan->cfg.addrmax &&
-		    vxlan->addrcnt >= vxlan->cfg.addrmax)
-			return -ENOSPC;
-
 		/* Disallow replace to add a multicast entry */
 		if ((flags & NLM_F_REPLACE) &&
 		    (is_multicast_ether_addr(mac) || is_zero_ether_addr(mac)))
 			return -EOPNOTSUPP;
 
 		netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip);
-		f = kmalloc(sizeof(*f), GFP_ATOMIC);
-		if (!f)
-			return -ENOMEM;
-
-		notify = 1;
-		f->state = state;
-		f->flags = ndm_flags;
-		f->updated = f->used = jiffies;
-		f->vni = src_vni;
-		INIT_LIST_HEAD(&f->remotes);
-		memcpy(f->eth_addr, mac, ETH_ALEN);
-
-		rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd);
-		if (rc < 0) {
-			kfree(f);
+		rc = vxlan_fdb_create(vxlan, mac, ip, state, port, src_vni,
+				      vni, ifindex, ndm_flags, &f);
+		if (rc < 0)
 			return rc;
-		}
-
-		++vxlan->addrcnt;
-		hlist_add_head_rcu(&f->hlist,
-				   vxlan_fdb_head(vxlan, mac, src_vni));
+		notify = 1;
 	}
 
 	if (notify) {
@@ -863,7 +896,7 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 		return -EAFNOSUPPORT;
 
 	spin_lock_bh(&vxlan->hash_lock);
-	err = vxlan_fdb_create(vxlan, addr, &ip, ndm->ndm_state, flags,
+	err = vxlan_fdb_update(vxlan, addr, &ip, ndm->ndm_state, flags,
 			       port, src_vni, vni, ifindex, ndm->ndm_flags);
 	spin_unlock_bh(&vxlan->hash_lock);
 
@@ -1006,7 +1039,7 @@ static bool vxlan_snoop(struct net_device *dev,
 
 		/* close off race between vxlan_flush and incoming packets */
 		if (netif_running(dev))
-			vxlan_fdb_create(vxlan, src_mac, src_ip,
+			vxlan_fdb_update(vxlan, src_mac, src_ip,
 					 NUD_REACHABLE,
 					 NLM_F_EXCL|NLM_F_CREATE,
 					 vxlan->cfg.dst_port,
@@ -3165,7 +3198,7 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev,
 
 	/* create an fdb entry for a valid default destination */
 	if (!vxlan_addr_any(&vxlan->default_dst.remote_ip)) {
-		err = vxlan_fdb_create(vxlan, all_zeros_mac,
+		err = vxlan_fdb_update(vxlan, all_zeros_mac,
 				       &vxlan->default_dst.remote_ip,
 				       NUD_REACHABLE | NUD_PERMANENT,
 				       NLM_F_EXCL | NLM_F_CREATE,
@@ -3439,7 +3472,7 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 					   old_dst.remote_ifindex, 0);
 
 		if (!vxlan_addr_any(&dst->remote_ip)) {
-			err = vxlan_fdb_create(vxlan, all_zeros_mac,
+			err = vxlan_fdb_update(vxlan, all_zeros_mac,
 					       &dst->remote_ip,
 					       NUD_REACHABLE | NUD_PERMANENT,
 					       NLM_F_CREATE | NLM_F_APPEND,
-- 
2.17.1


From c3e293c36ade68b44edd9b943e991851677316b9 Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Fri, 20 Jul 2018 13:21:03 -0700
Subject: [PATCH 28/34] vxlan: make netlink notify in vxlan_fdb_destroy
 optional

[ Upstream commit f6e053858671bb156b6e44ad66418acc8c7f4e77 ]

Add a new option do_notify to vxlan_fdb_destroy to make
sending netlink notify optional. Used by a later patch.

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 5a26b6689990..cdc7b01d20ce 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -774,13 +774,15 @@ static void vxlan_fdb_free(struct rcu_head *head)
 	kfree(f);
 }
 
-static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f)
+static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f,
+			      bool do_notify)
 {
 	netdev_dbg(vxlan->dev,
 		    "delete %pM\n", f->eth_addr);
 
 	--vxlan->addrcnt;
-	vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_DELNEIGH);
+	if (do_notify)
+		vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_DELNEIGH);
 
 	hlist_del_rcu(&f->hlist);
 	call_rcu(&f->rcu, vxlan_fdb_free);
@@ -930,7 +932,7 @@ static int __vxlan_fdb_delete(struct vxlan_dev *vxlan,
 		goto out;
 	}
 
-	vxlan_fdb_destroy(vxlan, f);
+	vxlan_fdb_destroy(vxlan, f, true);
 
 out:
 	return 0;
@@ -2393,7 +2395,7 @@ static void vxlan_cleanup(struct timer_list *t)
 					   "garbage collect %pM\n",
 					   f->eth_addr);
 				f->state = NUD_STALE;
-				vxlan_fdb_destroy(vxlan, f);
+				vxlan_fdb_destroy(vxlan, f, true);
 			} else if (time_before(timeout, next_timer))
 				next_timer = timeout;
 		}
@@ -2444,7 +2446,7 @@ static void vxlan_fdb_delete_default(struct vxlan_dev *vxlan, __be32 vni)
 	spin_lock_bh(&vxlan->hash_lock);
 	f = __vxlan_find_mac(vxlan, all_zeros_mac, vni);
 	if (f)
-		vxlan_fdb_destroy(vxlan, f);
+		vxlan_fdb_destroy(vxlan, f, true);
 	spin_unlock_bh(&vxlan->hash_lock);
 }
 
@@ -2498,7 +2500,7 @@ static void vxlan_flush(struct vxlan_dev *vxlan, bool do_all)
 				continue;
 			/* the all_zeros_mac entry is deleted at vxlan_uninit */
 			if (!is_zero_ether_addr(f->eth_addr))
-				vxlan_fdb_destroy(vxlan, f);
+				vxlan_fdb_destroy(vxlan, f, true);
 		}
 	}
 	spin_unlock_bh(&vxlan->hash_lock);
-- 
2.17.1


From 91547874d8e342ad503a3422996b3459d4f57faf Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Fri, 20 Jul 2018 13:21:04 -0700
Subject: [PATCH 29/34] vxlan: fix default fdb entry netlink notify ordering
 during netdev create

[ Upstream commit e99465b952861533d9ba748fdbecc96d9a36da3e ]

Problem:
In vxlan_newlink, a default fdb entry is added before register_netdev.
The default fdb creation function also notifies user-space of the
fdb entry on the vxlan device which user-space does not know about yet.
(RTM_NEWNEIGH goes before RTM_NEWLINK for the same ifindex).

This patch fixes the user-space netlink notification ordering issue
with the following changes:
- decouple fdb notify from fdb create.
- Move fdb notify after register_netdev.
- Call rtnl_configure_link in vxlan newlink handler to notify
userspace about the newlink before fdb notify and
hence avoiding the user-space race.

Fixes: afbd8bae9c79 ("vxlan: add implicit fdb entry for default destination")
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 29 +++++++++++++++++++++--------
 1 file changed, 21 insertions(+), 8 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index cdc7b01d20ce..3b050817bbda 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -3190,6 +3190,7 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev,
 {
 	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
 	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_fdb *f = NULL;
 	int err;
 
 	err = vxlan_dev_configure(net, dev, conf, false, extack);
@@ -3200,27 +3201,38 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev,
 
 	/* create an fdb entry for a valid default destination */
 	if (!vxlan_addr_any(&vxlan->default_dst.remote_ip)) {
-		err = vxlan_fdb_update(vxlan, all_zeros_mac,
+		err = vxlan_fdb_create(vxlan, all_zeros_mac,
 				       &vxlan->default_dst.remote_ip,
 				       NUD_REACHABLE | NUD_PERMANENT,
-				       NLM_F_EXCL | NLM_F_CREATE,
 				       vxlan->cfg.dst_port,
 				       vxlan->default_dst.remote_vni,
 				       vxlan->default_dst.remote_vni,
 				       vxlan->default_dst.remote_ifindex,
-				       NTF_SELF);
+				       NTF_SELF, &f);
 		if (err)
 			return err;
 	}
 
 	err = register_netdevice(dev);
+	if (err)
+		goto errout;
+
+	err = rtnl_configure_link(dev, NULL);
 	if (err) {
-		vxlan_fdb_delete_default(vxlan, vxlan->default_dst.remote_vni);
-		return err;
+		unregister_netdevice(dev);
+		goto errout;
 	}
 
+	/* notify default fdb entry */
+	if (f)
+		vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH);
+
 	list_add(&vxlan->next, &vn->vxlan_list);
 	return 0;
+errout:
+	if (f)
+		vxlan_fdb_destroy(vxlan, f, false);
+	return err;
 }
 
 static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[],
@@ -3449,6 +3461,7 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 	struct vxlan_rdst *dst = &vxlan->default_dst;
 	struct vxlan_rdst old_dst;
 	struct vxlan_config conf;
+	struct vxlan_fdb *f = NULL;
 	int err;
 
 	err = vxlan_nl2conf(tb, data,
@@ -3474,19 +3487,19 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 					   old_dst.remote_ifindex, 0);
 
 		if (!vxlan_addr_any(&dst->remote_ip)) {
-			err = vxlan_fdb_update(vxlan, all_zeros_mac,
+			err = vxlan_fdb_create(vxlan, all_zeros_mac,
 					       &dst->remote_ip,
 					       NUD_REACHABLE | NUD_PERMANENT,
-					       NLM_F_CREATE | NLM_F_APPEND,
 					       vxlan->cfg.dst_port,
 					       dst->remote_vni,
 					       dst->remote_vni,
 					       dst->remote_ifindex,
-					       NTF_SELF);
+					       NTF_SELF, &f);
 			if (err) {
 				spin_unlock_bh(&vxlan->hash_lock);
 				return err;
 			}
+			vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH);
 		}
 		spin_unlock_bh(&vxlan->hash_lock);
 	}
-- 
2.17.1


From 5a9fe479fc7825e26d73c81522cc12789af5d3ed Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 23 Jul 2018 09:28:17 -0700
Subject: [PATCH 30/34] tcp: free batches of packets in tcp_prune_ofo_queue()

[ Upstream commit 72cd43ba64fc172a443410ce01645895850844c8 ]

Juha-Matti Tilli reported that malicious peers could inject tiny
packets in out_of_order_queue, forcing very expensive calls
to tcp_collapse_ofo_queue() and tcp_prune_ofo_queue() for
every incoming packet. out_of_order_queue rb-tree can contain
thousands of nodes, iterating over all of them is not nice.

Before linux-4.9, we would have pruned all packets in ofo_queue
in one go, every XXXX packets. XXXX depends on sk_rcvbuf and skbs
truesize, but is about 7000 packets with tcp_rmem[2] default of 6 MB.

Since we plan to increase tcp_rmem[2] in the future to cope with
modern BDP, can not revert to the old behavior, without great pain.

Strategy taken in this patch is to purge ~12.5 % of the queue capacity.

Fixes: 36a6503fedda ("tcp: refine tcp_prune_ofo_queue() to not drop all packets")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Juha-Matti Tilli <juha-matti.tilli@iki.fi>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index ba358b7369c4..650bd2e6c60f 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4874,6 +4874,7 @@ static void tcp_collapse_ofo_queue(struct sock *sk)
  * 2) not add too big latencies if thousands of packets sit there.
  *    (But if application shrinks SO_RCVBUF, we could still end up
  *     freeing whole queue here)
+ * 3) Drop at least 12.5 % of sk_rcvbuf to avoid malicious attacks.
  *
  * Return true if queue has shrunk.
  */
@@ -4881,20 +4882,26 @@ static bool tcp_prune_ofo_queue(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct rb_node *node, *prev;
+	int goal;
 
 	if (RB_EMPTY_ROOT(&tp->out_of_order_queue))
 		return false;
 
 	NET_INC_STATS(sock_net(sk), LINUX_MIB_OFOPRUNED);
+	goal = sk->sk_rcvbuf >> 3;
 	node = &tp->ooo_last_skb->rbnode;
 	do {
 		prev = rb_prev(node);
 		rb_erase(node, &tp->out_of_order_queue);
+		goal -= rb_to_skb(node)->truesize;
 		tcp_drop(sk, rb_to_skb(node));
-		sk_mem_reclaim(sk);
-		if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
-		    !tcp_under_memory_pressure(sk))
-			break;
+		if (!prev || goal <= 0) {
+			sk_mem_reclaim(sk);
+			if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
+			    !tcp_under_memory_pressure(sk))
+				break;
+			goal = sk->sk_rcvbuf >> 3;
+		}
 		node = prev;
 	} while (node);
 	tp->ooo_last_skb = rb_to_skb(prev);
-- 
2.17.1


From 7cca289619b3f30449ea512d8c2e3c5c6a8a1511 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 23 Jul 2018 09:28:18 -0700
Subject: [PATCH 31/34] tcp: avoid collapses in tcp_prune_queue() if possible

[ Upstream commit f4a3313d8e2ca9fd8d8f45e40a2903ba782607e7 ]

Right after a TCP flow is created, receiving tiny out of order
packets allways hit the condition :

if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
	tcp_clamp_window(sk);

tcp_clamp_window() increases sk_rcvbuf to match sk_rmem_alloc
(guarded by tcp_rmem[2])

Calling tcp_collapse_ofo_queue() in this case is not useful,
and offers a O(N^2) surface attack to malicious peers.

Better not attempt anything before full queue capacity is reached,
forcing attacker to spend lots of resource and allow us to more
easily detect the abuse.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 650bd2e6c60f..719a20daea78 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4936,6 +4936,9 @@ static int tcp_prune_queue(struct sock *sk)
 	else if (tcp_under_memory_pressure(sk))
 		tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss);
 
+	if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf)
+		return 0;
+
 	tcp_collapse_ofo_queue(sk);
 	if (!skb_queue_empty(&sk->sk_receive_queue))
 		tcp_collapse(sk, &sk->sk_receive_queue, NULL,
-- 
2.17.1


From cf60f912586217e5322a47dbded19257c7ef6f54 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 23 Jul 2018 09:28:19 -0700
Subject: [PATCH 32/34] tcp: detect malicious patterns in
 tcp_collapse_ofo_queue()

[ Upstream commit 3d4bf93ac12003f9b8e1e2de37fe27983deebdcf ]

In case an attacker feeds tiny packets completely out of order,
tcp_collapse_ofo_queue() might scan the whole rb-tree, performing
expensive copies, but not changing socket memory usage at all.

1) Do not attempt to collapse tiny skbs.
2) Add logic to exit early when too many tiny skbs are detected.

We prefer not doing aggressive collapsing (which copies packets)
for pathological flows, and revert to tcp_prune_ofo_queue() which
will be less expensive.

In the future, we might add the possibility of terminating flows
that are proven to be malicious.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 719a20daea78..08b39bb92095 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4834,6 +4834,7 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct rb_root *root,
 static void tcp_collapse_ofo_queue(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	u32 range_truesize, sum_tiny = 0;
 	struct sk_buff *skb, *head;
 	u32 start, end;
 
@@ -4845,6 +4846,7 @@ static void tcp_collapse_ofo_queue(struct sock *sk)
 	}
 	start = TCP_SKB_CB(skb)->seq;
 	end = TCP_SKB_CB(skb)->end_seq;
+	range_truesize = skb->truesize;
 
 	for (head = skb;;) {
 		skb = skb_rb_next(skb);
@@ -4855,11 +4857,20 @@ static void tcp_collapse_ofo_queue(struct sock *sk)
 		if (!skb ||
 		    after(TCP_SKB_CB(skb)->seq, end) ||
 		    before(TCP_SKB_CB(skb)->end_seq, start)) {
-			tcp_collapse(sk, NULL, &tp->out_of_order_queue,
-				     head, skb, start, end);
+			/* Do not attempt collapsing tiny skbs */
+			if (range_truesize != head->truesize ||
+			    end - start >= SKB_WITH_OVERHEAD(SK_MEM_QUANTUM)) {
+				tcp_collapse(sk, NULL, &tp->out_of_order_queue,
+					     head, skb, start, end);
+			} else {
+				sum_tiny += range_truesize;
+				if (sum_tiny > sk->sk_rcvbuf >> 3)
+					return;
+			}
 			goto new_range;
 		}
 
+		range_truesize += skb->truesize;
 		if (unlikely(before(TCP_SKB_CB(skb)->seq, start)))
 			start = TCP_SKB_CB(skb)->seq;
 		if (after(TCP_SKB_CB(skb)->end_seq, end))
-- 
2.17.1


From 26157f671286c5087fb429920cd4adc83a80aef2 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 23 Jul 2018 09:28:20 -0700
Subject: [PATCH 33/34] tcp: call tcp_drop() from tcp_data_queue_ofo()

[ Upstream commit 8541b21e781a22dce52a74fef0b9bed00404a1cd ]

In order to be able to give better diagnostics and detect
malicious traffic, we need to have better sk->sk_drops tracking.

Fixes: 9f5afeae5152 ("tcp: use an RB tree for ooo receive queue")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 08b39bb92095..cc9c67df3f74 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4451,7 +4451,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 				/* All the bits are present. Drop. */
 				NET_INC_STATS(sock_net(sk),
 					      LINUX_MIB_TCPOFOMERGE);
-				__kfree_skb(skb);
+				tcp_drop(sk, skb);
 				skb = NULL;
 				tcp_dsack_set(sk, seq, end_seq);
 				goto add_sack;
@@ -4470,7 +4470,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 						 TCP_SKB_CB(skb1)->end_seq);
 				NET_INC_STATS(sock_net(sk),
 					      LINUX_MIB_TCPOFOMERGE);
-				__kfree_skb(skb1);
+				tcp_drop(sk, skb1);
 				goto merge_right;
 			}
 		} else if (tcp_try_coalesce(sk, skb1,
-- 
2.17.1


From b0b587464a20b33a86e4a55883c9818ebe4ab3ab Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 23 Jul 2018 09:28:21 -0700
Subject: [PATCH 34/34] tcp: add tcp_ooo_try_coalesce() helper

[ Upstream commit 58152ecbbcc6a0ce7fddd5bf5f6ee535834ece0c ]

In case skb in out_or_order_queue is the result of
multiple skbs coalescing, we would like to get a proper gso_segs
counter tracking, so that future tcp_drop() can report an accurate
number.

I chose to not implement this tracking for skbs in receive queue,
since they are not dropped, unless socket is disconnected.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 25 +++++++++++++++++++++----
 1 file changed, 21 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index cc9c67df3f74..0f5e9510c3fa 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4299,6 +4299,23 @@ static bool tcp_try_coalesce(struct sock *sk,
 	return true;
 }
 
+static bool tcp_ooo_try_coalesce(struct sock *sk,
+			     struct sk_buff *to,
+			     struct sk_buff *from,
+			     bool *fragstolen)
+{
+	bool res = tcp_try_coalesce(sk, to, from, fragstolen);
+
+	/* In case tcp_drop() is called later, update to->gso_segs */
+	if (res) {
+		u32 gso_segs = max_t(u16, 1, skb_shinfo(to)->gso_segs) +
+			       max_t(u16, 1, skb_shinfo(from)->gso_segs);
+
+		skb_shinfo(to)->gso_segs = min_t(u32, gso_segs, 0xFFFF);
+	}
+	return res;
+}
+
 static void tcp_drop(struct sock *sk, struct sk_buff *skb)
 {
 	sk_drops_add(sk, skb);
@@ -4422,8 +4439,8 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 	/* In the typical case, we are adding an skb to the end of the list.
 	 * Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup.
 	 */
-	if (tcp_try_coalesce(sk, tp->ooo_last_skb,
-			     skb, &fragstolen)) {
+	if (tcp_ooo_try_coalesce(sk, tp->ooo_last_skb,
+				 skb, &fragstolen)) {
 coalesce_done:
 		tcp_grow_window(sk, skb);
 		kfree_skb_partial(skb, fragstolen);
@@ -4473,8 +4490,8 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 				tcp_drop(sk, skb1);
 				goto merge_right;
 			}
-		} else if (tcp_try_coalesce(sk, skb1,
-					    skb, &fragstolen)) {
+		} else if (tcp_ooo_try_coalesce(sk, skb1,
+						skb, &fragstolen)) {
 			goto coalesce_done;
 		}
 		p = &parent->rb_right;
-- 
2.17.1

Re: [PATCHES] Networking

[Eric Dumazet]

Hi David

SGTM for TCP patches.

Thanks !

On Thu, Jul 26, 2018 at 4:51 PM David Miller <davem@davemloft.net> wrote:
>
>
> [ Eric please double check my TCP backports, thank you... ]
>
> Please queue up the following networking fixes for v4.14.x and v4.17.x
> -stable, respectively.
>
> Thank you!

Re: [PATCHES] Networking

[Greg KH]

On Thu, Jul 26, 2018 at 04:50:51PM -0700, David Miller wrote:
> 
> [ Eric please double check my TCP backports, thank you... ]
> 
> Please queue up the following networking fixes for v4.14.x and v4.17.x
> -stable, respectively.

All now queued up, many thanks for these.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 106 bytes --]


Please queue up the following networking bug fixes for 4.14.x and
4.17.x -stable, respectively.

Thanks!

[-- Attachment #2: net_414.mbox --]
[-- Type: Application/Octet-Stream, Size: 31040 bytes --]

From c8b107eb8f9bc48bf54e441c1e4c78437e2bbaa5 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Fri, 27 Jul 2018 18:15:46 +0200
Subject: [PATCH 01/15] ipv4: remove BUG_ON() from fib_compute_spec_dst

[ Upstream commit 9fc12023d6f51551d6ca9ed7e02ecc19d79caf17 ]

Remove BUG_ON() from fib_compute_spec_dst routine and check
in_dev pointer during flowi4 data structure initialization.
fib_compute_spec_dst routine can be run concurrently with device removal
where ip_ptr net_device pointer is set to NULL. This can happen
if userspace enables pkt info on UDP rx socket and the device
is removed while traffic is flowing

Fixes: 35ebf65e851c ("ipv4: Create and use fib_compute_spec_dst() helper")
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_frontend.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 67eebcb113f3..5bbdd05d0cd3 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -282,19 +282,19 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb)
 		return ip_hdr(skb)->daddr;
 
 	in_dev = __in_dev_get_rcu(dev);
-	BUG_ON(!in_dev);
 
 	net = dev_net(dev);
 
 	scope = RT_SCOPE_UNIVERSE;
 	if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) {
+		bool vmark = in_dev && IN_DEV_SRC_VMARK(in_dev);
 		struct flowi4 fl4 = {
 			.flowi4_iif = LOOPBACK_IFINDEX,
 			.flowi4_oif = l3mdev_master_ifindex_rcu(dev),
 			.daddr = ip_hdr(skb)->saddr,
 			.flowi4_tos = RT_TOS(ip_hdr(skb)->tos),
 			.flowi4_scope = scope,
-			.flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0,
+			.flowi4_mark = vmark ? skb->mark : 0,
 		};
 		if (!fib_lookup(net, &fl4, &res, 0))
 			return FIB_RES_PREFSRC(net, res);
-- 
2.17.1


From 04f8a3c32a19ca41d113a8600b878abc66ea4dd4 Mon Sep 17 00:00:00 2001
From: Gal Pressman <pressmangal@gmail.com>
Date: Thu, 26 Jul 2018 23:40:33 +0300
Subject: [PATCH 02/15] net: ena: Fix use of uninitialized DMA address bits
 field

[ Upstream commit 101f0cd4f2216d32f1b8a75a2154cf3997484ee2 ]

UBSAN triggers the following undefined behaviour warnings:
[...]
[   13.236124] UBSAN: Undefined behaviour in drivers/net/ethernet/amazon/ena/ena_eth_com.c:468:22
[   13.240043] shift exponent 64 is too large for 64-bit type 'long long unsigned int'
[...]
[   13.744769] UBSAN: Undefined behaviour in drivers/net/ethernet/amazon/ena/ena_eth_com.c:373:4
[   13.748694] shift exponent 64 is too large for 64-bit type 'long long unsigned int'
[...]

When splitting the address to high and low, GENMASK_ULL is used to generate
a bitmask with dma_addr_bits field from io_sq (in ena_com_prepare_tx and
ena_com_add_single_rx_desc).
The problem is that dma_addr_bits is not initialized with a proper value
(besides being cleared in ena_com_create_io_queue).
Assign dma_addr_bits the correct value that is stored in ena_dev when
initializing the SQ.

Fixes: 1738cd3ed342 ("net: ena: Add a driver for Amazon Elastic Network Adapters (ENA)")
Signed-off-by: Gal Pressman <pressmangal@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_com.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index 52beba8c7a39..e3b7a71fcad9 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -331,6 +331,7 @@ static int ena_com_init_io_sq(struct ena_com_dev *ena_dev,
 
 	memset(&io_sq->desc_addr, 0x0, sizeof(io_sq->desc_addr));
 
+	io_sq->dma_addr_bits = ena_dev->dma_addr_bits;
 	io_sq->desc_entry_size =
 		(io_sq->direction == ENA_COM_IO_QUEUE_DIRECTION_TX) ?
 		sizeof(struct ena_eth_io_tx_desc) :
-- 
2.17.1


From a8239d6a84f0a2c93f5b185ad87e82da901c2dac Mon Sep 17 00:00:00 2001
From: tangpengpeng <tangpengpeng@higon.com>
Date: Thu, 26 Jul 2018 14:45:16 +0800
Subject: [PATCH 03/15] net: fix amd-xgbe flow-control issue

[ Upstream commit 7f3fc7ddf719cd6faaf787722c511f6918ac6aab ]

If we enable or disable xgbe flow-control by ethtool ,
it does't work.Because the parameter is not properly
assigned,so we need to adjust the assignment order
of the parameters.

Fixes: c1ce2f77366b ("amd-xgbe: Fix flow control setting logic")
Signed-off-by: tangpengpeng <tangpengpeng@higon.com>
Acked-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe-mdio.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
index 1b45cd73a258..119777986ea4 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
@@ -1128,14 +1128,14 @@ static void xgbe_phy_adjust_link(struct xgbe_prv_data *pdata)
 
 		if (pdata->tx_pause != pdata->phy.tx_pause) {
 			new_state = 1;
-			pdata->hw_if.config_tx_flow_control(pdata);
 			pdata->tx_pause = pdata->phy.tx_pause;
+			pdata->hw_if.config_tx_flow_control(pdata);
 		}
 
 		if (pdata->rx_pause != pdata->phy.rx_pause) {
 			new_state = 1;
-			pdata->hw_if.config_rx_flow_control(pdata);
 			pdata->rx_pause = pdata->phy.rx_pause;
+			pdata->hw_if.config_rx_flow_control(pdata);
 		}
 
 		/* Speed support */
-- 
2.17.1


From d390255937867ae05f307a590d379ff3c9d187af Mon Sep 17 00:00:00 2001
From: Stefan Wahren <stefan.wahren@i2se.com>
Date: Sat, 28 Jul 2018 09:52:10 +0200
Subject: [PATCH 04/15] net: lan78xx: fix rx handling before first packet is
 send

[ Upstream commit 136f55f660192ce04af091642efc75d85e017364 ]

As long the bh tasklet isn't scheduled once, no packet from the rx path
will be handled. Since the tx path also schedule the same tasklet
this situation only persits until the first packet transmission.
So fix this issue by scheduling the tasklet after link reset.

Link: https://github.com/raspberrypi/linux/issues/2617
Fixes: 55d7de9de6c3 ("Microchip's LAN7800 family USB 2/3 to 10/100/1000 Ethernet")
Suggested-by: Floris Bos <bos@je-eigen-domein.nl>
Signed-off-by: Stefan Wahren <stefan.wahren@i2se.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/lan78xx.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 0aa91ab9a0fb..9e3f632e22f1 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -1216,6 +1216,8 @@ static int lan78xx_link_reset(struct lan78xx_net *dev)
 			mod_timer(&dev->stat_monitor,
 				  jiffies + STAT_UPDATE_TIMER);
 		}
+
+		tasklet_schedule(&dev->bh);
 	}
 
 	return ret;
-- 
2.17.1


From dadfe1bdb3a0555a3f2abc8cf65b7dea8d1672a0 Mon Sep 17 00:00:00 2001
From: Anton Vasilyev <vasilyev@ispras.ru>
Date: Fri, 27 Jul 2018 18:57:47 +0300
Subject: [PATCH 05/15] net: mdio-mux: bcm-iproc: fix wrong getter and setter
 pair

[ Upstream commit b0753408aadf32c7ece9e6b765017881e54af833 ]

mdio_mux_iproc_probe() uses platform_set_drvdata() to store md pointer
in device, whereas mdio_mux_iproc_remove() restores md pointer by
dev_get_platdata(&pdev->dev). This leads to wrong resources release.

The patch replaces getter to platform_get_drvdata.

Fixes: 98bc865a1ec8 ("net: mdio-mux: Add MDIO mux driver for iProc SoCs")
Signed-off-by: Anton Vasilyev <vasilyev@ispras.ru>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mdio-mux-bcm-iproc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/mdio-mux-bcm-iproc.c b/drivers/net/phy/mdio-mux-bcm-iproc.c
index 0831b7142df7..0c5b68e7da51 100644
--- a/drivers/net/phy/mdio-mux-bcm-iproc.c
+++ b/drivers/net/phy/mdio-mux-bcm-iproc.c
@@ -218,7 +218,7 @@ static int mdio_mux_iproc_probe(struct platform_device *pdev)
 
 static int mdio_mux_iproc_remove(struct platform_device *pdev)
 {
-	struct iproc_mdiomux_desc *md = dev_get_platdata(&pdev->dev);
+	struct iproc_mdiomux_desc *md = platform_get_drvdata(pdev);
 
 	mdio_mux_uninit(md->mux_handle);
 	mdiobus_unregister(md->mii_bus);
-- 
2.17.1


From 3f1d80e60ef48ff6d2086e1a4d1efca70c4cf237 Mon Sep 17 00:00:00 2001
From: Eugeniy Paltsev <Eugeniy.Paltsev@synopsys.com>
Date: Thu, 26 Jul 2018 15:05:37 +0300
Subject: [PATCH 06/15] NET: stmmac: align DMA stuff to largest cache line
 length

[ Upstream commit 9939a46d90c6c76f4533d534dbadfa7b39dc6acc ]

As for today STMMAC_ALIGN macro (which is used to align DMA stuff)
relies on L1 line length (L1_CACHE_BYTES).
This isn't correct in case of system with several cache levels
which might have L1 cache line length smaller than L2 line. This
can lead to sharing one cache line between DMA buffer and other
data, so we can lose this data while invalidate DMA buffer before
DMA transaction.

Fix that by using SMP_CACHE_BYTES instead of L1_CACHE_BYTES for
aligning.

Signed-off-by: Eugeniy Paltsev <Eugeniy.Paltsev@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 27f2e650e27b..1a9a382bf1c4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -51,7 +51,7 @@
 #include <linux/of_mdio.h>
 #include "dwmac1000.h"
 
-#define STMMAC_ALIGN(x)	L1_CACHE_ALIGN(x)
+#define	STMMAC_ALIGN(x)		__ALIGN_KERNEL(x, SMP_CACHE_BYTES)
 #define	TSO_MAX_BUFF_SIZE	(SZ_16K - 1)
 
 /* Module parameters */
-- 
2.17.1


From ccadd135107931d378c25b3510ba91caf1943ccc Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Fri, 27 Jul 2018 17:19:12 -0400
Subject: [PATCH 07/15] tcp_bbr: fix bw probing to raise in-flight data for
 very small BDPs

[ Upstream commit 383d470936c05554219094a4d364d964cb324827 ]

For some very small BDPs (with just a few packets) there was a
quantization effect where the target number of packets in flight
during the super-unity-gain (1.25x) phase of gain cycling was
implicitly truncated to a number of packets no larger than the normal
unity-gain (1.0x) phase of gain cycling. This meant that in multi-flow
scenarios some flows could get stuck with a lower bandwidth, because
they did not push enough packets inflight to discover that there was
more bandwidth available. This was really only an issue in multi-flow
LAN scenarios, where RTTs and BDPs are low enough for this to be an
issue.

This fix ensures that gain cycling can raise inflight for small BDPs
by ensuring that in PROBE_BW mode target inflight values with a
super-unity gain are always greater than inflight values with a gain
<= 1. Importantly, this applies whether the inflight value is
calculated for use as a cwnd value, or as a target inflight value for
the end of the super-unity phase in bbr_is_next_cycle_phase() (both
need to be bigger to ensure we can probe with more packets in flight
reliably).

This is a candidate fix for stable releases.

Fixes: 0f8782ea1497 ("tcp_bbr: add BBR congestion control")
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Priyaranjan Jha <priyarjha@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_bbr.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 9a0b952dd09b..06f247ca9197 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -353,6 +353,10 @@ static u32 bbr_target_cwnd(struct sock *sk, u32 bw, int gain)
 	/* Reduce delayed ACKs by rounding up cwnd to the next even number. */
 	cwnd = (cwnd + 1) & ~1U;
 
+	/* Ensure gain cycling gets inflight above BDP even for small BDPs. */
+	if (bbr->mode == BBR_PROBE_BW && gain > BBR_UNIT)
+		cwnd += 2;
+
 	return cwnd;
 }
 
-- 
2.17.1


From 0e76b3de67548c3be0b464d2250a6e107ee2bcb7 Mon Sep 17 00:00:00 2001
From: Xiao Liang <xiliang@redhat.com>
Date: Fri, 27 Jul 2018 17:56:08 +0800
Subject: [PATCH 08/15] xen-netfront: wait xenbus state change when load module
 manually

[ Upstream commit 822fb18a82abaf4ee7058793d95d340f5dab7bfc ]

When loading module manually, after call xenbus_switch_state to initializes
the state of the netfront device, the driver state did not change so fast
that may lead no dev created in latest kernel. This patch adds wait to make
sure xenbus knows the driver is not in closed/unknown state.

Current state:
[vm]# ethtool eth0
Settings for eth0:
	Link detected: yes
[vm]# modprobe -r xen_netfront
[vm]# modprobe  xen_netfront
[vm]# ethtool eth0
Settings for eth0:
Cannot get device settings: No such device
Cannot get wake-on-lan settings: No such device
Cannot get message level: No such device
Cannot get link status: No such device
No data available

With the patch installed.
[vm]# ethtool eth0
Settings for eth0:
	Link detected: yes
[vm]# modprobe -r xen_netfront
[vm]# modprobe xen_netfront
[vm]# ethtool eth0
Settings for eth0:
	Link detected: yes

Signed-off-by: Xiao Liang <xiliang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netfront.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index f07b9c9bb5ba..25a376f550c1 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -87,6 +87,7 @@ struct netfront_cb {
 /* IRQ name is queue name with "-tx" or "-rx" appended */
 #define IRQ_NAME_SIZE (QUEUE_NAME_SIZE + 3)
 
+static DECLARE_WAIT_QUEUE_HEAD(module_load_q);
 static DECLARE_WAIT_QUEUE_HEAD(module_unload_q);
 
 struct netfront_stats {
@@ -1330,6 +1331,11 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev)
 	netif_carrier_off(netdev);
 
 	xenbus_switch_state(dev, XenbusStateInitialising);
+	wait_event(module_load_q,
+			   xenbus_read_driver_state(dev->otherend) !=
+			   XenbusStateClosed &&
+			   xenbus_read_driver_state(dev->otherend) !=
+			   XenbusStateUnknown);
 	return netdev;
 
  exit:
-- 
2.17.1


From c744adc4b6992557260008ea25a77a0a2034d950 Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <dima@arista.com>
Date: Fri, 27 Jul 2018 16:54:44 +0100
Subject: [PATCH 09/15] netlink: Do not subscribe to non-existent groups

[ Upstream commit 7acf9d4237c46894e0fa0492dd96314a41742e84 ]

Make ABI more strict about subscribing to group > ngroups.
Code doesn't check for that and it looks bogus.
(one can subscribe to non-existing group)
Still, it's possible to bind() to all possible groups with (-1)

Cc: "David S. Miller" <davem@davemloft.net>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Cc: netdev@vger.kernel.org
Signed-off-by: Dmitry Safonov <dima@arista.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index b3932846f6c4..143d9001e87d 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -976,6 +976,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 		if (err)
 			return err;
 	}
+	groups &= (1UL << nlk->ngroups) - 1;
 
 	bound = nlk->bound;
 	if (bound) {
-- 
2.17.1


From 472b40ec09bd465ebeb61b172121a8ba2c5e0e31 Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <dima@arista.com>
Date: Mon, 30 Jul 2018 18:32:36 +0100
Subject: [PATCH 10/15] netlink: Don't shift with UB on nlk->ngroups

[ Upstream commit 61f4b23769f0cc72ae62c9a81cf08f0397d40da8 ]

On i386 nlk->ngroups might be 32 or 0. Which leads to UB, resulting in
hang during boot.
Check for 0 ngroups and use (unsigned long long) as a type to shift.

Fixes: 7acf9d4237c4 ("netlink: Do not subscribe to non-existent groups").
Reported-by: kernel test robot <rong.a.chen@intel.com>
Signed-off-by: Dmitry Safonov <dima@arista.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 143d9001e87d..b2fcbf012056 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -976,7 +976,11 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 		if (err)
 			return err;
 	}
-	groups &= (1UL << nlk->ngroups) - 1;
+
+	if (nlk->ngroups == 0)
+		groups = 0;
+	else
+		groups &= (1ULL << nlk->ngroups) - 1;
 
 	bound = nlk->bound;
 	if (bound) {
-- 
2.17.1


From c00562a44a53a7e5d0c86077f00e67bd034fc955 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 17 May 2018 14:47:25 -0700
Subject: [PATCH 11/15] tcp: do not force quickack when receiving out-of-order
 packets

[ Upstream commit a3893637e1eb0ef5eb1bbc52b3a8d2dfa317a35d ]

As explained in commit 9f9843a751d0 ("tcp: properly handle stretch
acks in slow start"), TCP stacks have to consider how many packets
are acknowledged in one single ACK, because of GRO, but also
because of ACK compression or losses.

We plan to add SACK compression in the following patch, we
must therefore not call tcp_enter_quickack_mode()

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index b86e7b8beb1d..e12bf35beb1c 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4721,8 +4721,6 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 	if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt + tcp_receive_window(tp)))
 		goto out_of_window;
 
-	tcp_enter_quickack_mode(sk);
-
 	if (before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
 		/* Partial packet, seq < rcv_next < end_seq */
 		SOCK_DEBUG(sk, "partial packet: rcv_next %X seq %X - %X\n",
-- 
2.17.1


From d569c45577256b08f4e74be6616234af9bff13da Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 21 May 2018 15:08:56 -0700
Subject: [PATCH 12/15] tcp: add max_quickacks param to tcp_incr_quickack and
 tcp_enter_quickack_mode

[ Upstream commit 9a9c9b51e54618861420093ae6e9b50a961914c5 ]

We want to add finer control of the number of ACK packets sent after
ECN events.

This patch is not changing current behavior, it only enables following
change.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h    |  2 +-
 net/ipv4/tcp_dctcp.c |  4 ++--
 net/ipv4/tcp_input.c | 24 +++++++++++++-----------
 3 files changed, 16 insertions(+), 14 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 3173dd12b8cc..686e33ea76e7 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -372,7 +372,7 @@ ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos,
 			struct pipe_inode_info *pipe, size_t len,
 			unsigned int flags);
 
-void tcp_enter_quickack_mode(struct sock *sk);
+void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks);
 static inline void tcp_dec_quickack_mode(struct sock *sk,
 					 const unsigned int pkts)
 {
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index c78fb53988a1..1a9b88c8cf72 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -138,7 +138,7 @@ static void dctcp_ce_state_0_to_1(struct sock *sk)
 		 */
 		if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
 			__tcp_send_ack(sk, ca->prior_rcv_nxt);
-		tcp_enter_quickack_mode(sk);
+		tcp_enter_quickack_mode(sk, 1);
 	}
 
 	ca->prior_rcv_nxt = tp->rcv_nxt;
@@ -159,7 +159,7 @@ static void dctcp_ce_state_1_to_0(struct sock *sk)
 		 */
 		if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
 			__tcp_send_ack(sk, ca->prior_rcv_nxt);
-		tcp_enter_quickack_mode(sk);
+		tcp_enter_quickack_mode(sk, 1);
 	}
 
 	ca->prior_rcv_nxt = tp->rcv_nxt;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e12bf35beb1c..bc9c48d01980 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -198,21 +198,23 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb)
 	}
 }
 
-static void tcp_incr_quickack(struct sock *sk)
+static void tcp_incr_quickack(struct sock *sk, unsigned int max_quickacks)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	unsigned int quickacks = tcp_sk(sk)->rcv_wnd / (2 * icsk->icsk_ack.rcv_mss);
 
 	if (quickacks == 0)
 		quickacks = 2;
+	quickacks = min(quickacks, max_quickacks);
 	if (quickacks > icsk->icsk_ack.quick)
-		icsk->icsk_ack.quick = min(quickacks, TCP_MAX_QUICKACKS);
+		icsk->icsk_ack.quick = quickacks;
 }
 
-void tcp_enter_quickack_mode(struct sock *sk)
+void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
-	tcp_incr_quickack(sk);
+
+	tcp_incr_quickack(sk, max_quickacks);
 	icsk->icsk_ack.pingpong = 0;
 	icsk->icsk_ack.ato = TCP_ATO_MIN;
 }
@@ -257,7 +259,7 @@ static void __tcp_ecn_check_ce(struct tcp_sock *tp, const struct sk_buff *skb)
 		 * it is probably a retransmit.
 		 */
 		if (tp->ecn_flags & TCP_ECN_SEEN)
-			tcp_enter_quickack_mode((struct sock *)tp);
+			tcp_enter_quickack_mode((struct sock *)tp, TCP_MAX_QUICKACKS);
 		break;
 	case INET_ECN_CE:
 		if (tcp_ca_needs_ecn((struct sock *)tp))
@@ -265,7 +267,7 @@ static void __tcp_ecn_check_ce(struct tcp_sock *tp, const struct sk_buff *skb)
 
 		if (!(tp->ecn_flags & TCP_ECN_DEMAND_CWR)) {
 			/* Better not delay acks, sender can have a very low cwnd */
-			tcp_enter_quickack_mode((struct sock *)tp);
+			tcp_enter_quickack_mode((struct sock *)tp, TCP_MAX_QUICKACKS);
 			tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
 		}
 		tp->ecn_flags |= TCP_ECN_SEEN;
@@ -686,7 +688,7 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb)
 		/* The _first_ data packet received, initialize
 		 * delayed ACK engine.
 		 */
-		tcp_incr_quickack(sk);
+		tcp_incr_quickack(sk, TCP_MAX_QUICKACKS);
 		icsk->icsk_ack.ato = TCP_ATO_MIN;
 	} else {
 		int m = now - icsk->icsk_ack.lrcvtime;
@@ -702,7 +704,7 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb)
 			/* Too long gap. Apparently sender failed to
 			 * restart window, so that we send ACKs quickly.
 			 */
-			tcp_incr_quickack(sk);
+			tcp_incr_quickack(sk, TCP_MAX_QUICKACKS);
 			sk_mem_reclaim(sk);
 		}
 	}
@@ -4160,7 +4162,7 @@ static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb)
 	if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq &&
 	    before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST);
-		tcp_enter_quickack_mode(sk);
+		tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS);
 
 		if (tcp_is_sack(tp) && sysctl_tcp_dsack) {
 			u32 end_seq = TCP_SKB_CB(skb)->end_seq;
@@ -4710,7 +4712,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 		tcp_dsack_set(sk, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq);
 
 out_of_window:
-		tcp_enter_quickack_mode(sk);
+		tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS);
 		inet_csk_schedule_ack(sk);
 drop:
 		tcp_drop(sk, skb);
@@ -5791,7 +5793,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 			 * to stand against the temptation 8)     --ANK
 			 */
 			inet_csk_schedule_ack(sk);
-			tcp_enter_quickack_mode(sk);
+			tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS);
 			inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
 						  TCP_DELACK_MAX, TCP_RTO_MAX);
 
-- 
2.17.1


From ddd7b38f5bf9fd1f3010d7041e94e637928549e8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 21 May 2018 15:08:57 -0700
Subject: [PATCH 13/15] tcp: do not aggressively quick ack after ECN events

[ Upstream commit 522040ea5fdd1c33bbf75e1d7c7c0422b96a94ef ]

ECN signals currently forces TCP to enter quickack mode for
up to 16 (TCP_MAX_QUICKACKS) following incoming packets.

We believe this is not needed, and only sending one immediate ack
for the current packet should be enough.

This should reduce the extra load noticed in DCTCP environments,
after congestion events.

This is part 2 of our effort to reduce pure ACK packets.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index bc9c48d01980..a7bb96054852 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -259,7 +259,7 @@ static void __tcp_ecn_check_ce(struct tcp_sock *tp, const struct sk_buff *skb)
 		 * it is probably a retransmit.
 		 */
 		if (tp->ecn_flags & TCP_ECN_SEEN)
-			tcp_enter_quickack_mode((struct sock *)tp, TCP_MAX_QUICKACKS);
+			tcp_enter_quickack_mode((struct sock *)tp, 1);
 		break;
 	case INET_ECN_CE:
 		if (tcp_ca_needs_ecn((struct sock *)tp))
@@ -267,7 +267,7 @@ static void __tcp_ecn_check_ce(struct tcp_sock *tp, const struct sk_buff *skb)
 
 		if (!(tp->ecn_flags & TCP_ECN_DEMAND_CWR)) {
 			/* Better not delay acks, sender can have a very low cwnd */
-			tcp_enter_quickack_mode((struct sock *)tp, TCP_MAX_QUICKACKS);
+			tcp_enter_quickack_mode((struct sock *)tp, 1);
 			tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
 		}
 		tp->ecn_flags |= TCP_ECN_SEEN;
-- 
2.17.1


From 33d41975d7587831e9328339e277d01938250022 Mon Sep 17 00:00:00 2001
From: Yousuk Seung <ysseung@google.com>
Date: Mon, 4 Jun 2018 15:29:51 -0700
Subject: [PATCH 14/15] tcp: refactor tcp_ecn_check_ce to remove sk type cast

[ Upstream commit f4c9f85f3b2cb7669830cd04d0be61192a4d2436 ]

Refactor tcp_ecn_check_ce and __tcp_ecn_check_ce to accept struct sock*
instead of tcp_sock* to clean up type casts. This is a pure refactor
patch.

Signed-off-by: Yousuk Seung <ysseung@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 26 ++++++++++++++------------
 1 file changed, 14 insertions(+), 12 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a7bb96054852..124be1636efe 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -250,8 +250,10 @@ static void tcp_ecn_withdraw_cwr(struct tcp_sock *tp)
 	tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
 }
 
-static void __tcp_ecn_check_ce(struct tcp_sock *tp, const struct sk_buff *skb)
+static void __tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb)
 {
+	struct tcp_sock *tp = tcp_sk(sk);
+
 	switch (TCP_SKB_CB(skb)->ip_dsfield & INET_ECN_MASK) {
 	case INET_ECN_NOT_ECT:
 		/* Funny extension: if ECT is not set on a segment,
@@ -259,31 +261,31 @@ static void __tcp_ecn_check_ce(struct tcp_sock *tp, const struct sk_buff *skb)
 		 * it is probably a retransmit.
 		 */
 		if (tp->ecn_flags & TCP_ECN_SEEN)
-			tcp_enter_quickack_mode((struct sock *)tp, 1);
+			tcp_enter_quickack_mode(sk, 1);
 		break;
 	case INET_ECN_CE:
-		if (tcp_ca_needs_ecn((struct sock *)tp))
-			tcp_ca_event((struct sock *)tp, CA_EVENT_ECN_IS_CE);
+		if (tcp_ca_needs_ecn(sk))
+			tcp_ca_event(sk, CA_EVENT_ECN_IS_CE);
 
 		if (!(tp->ecn_flags & TCP_ECN_DEMAND_CWR)) {
 			/* Better not delay acks, sender can have a very low cwnd */
-			tcp_enter_quickack_mode((struct sock *)tp, 1);
+			tcp_enter_quickack_mode(sk, 1);
 			tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
 		}
 		tp->ecn_flags |= TCP_ECN_SEEN;
 		break;
 	default:
-		if (tcp_ca_needs_ecn((struct sock *)tp))
-			tcp_ca_event((struct sock *)tp, CA_EVENT_ECN_NO_CE);
+		if (tcp_ca_needs_ecn(sk))
+			tcp_ca_event(sk, CA_EVENT_ECN_NO_CE);
 		tp->ecn_flags |= TCP_ECN_SEEN;
 		break;
 	}
 }
 
-static void tcp_ecn_check_ce(struct tcp_sock *tp, const struct sk_buff *skb)
+static void tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb)
 {
-	if (tp->ecn_flags & TCP_ECN_OK)
-		__tcp_ecn_check_ce(tp, skb);
+	if (tcp_sk(sk)->ecn_flags & TCP_ECN_OK)
+		__tcp_ecn_check_ce(sk, skb);
 }
 
 static void tcp_ecn_rcv_synack(struct tcp_sock *tp, const struct tcphdr *th)
@@ -710,7 +712,7 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb)
 	}
 	icsk->icsk_ack.lrcvtime = now;
 
-	tcp_ecn_check_ce(tp, skb);
+	tcp_ecn_check_ce(sk, skb);
 
 	if (skb->len >= 128)
 		tcp_grow_window(sk, skb);
@@ -4443,7 +4445,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 	u32 seq, end_seq;
 	bool fragstolen;
 
-	tcp_ecn_check_ce(tp, skb);
+	tcp_ecn_check_ce(sk, skb);
 
 	if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFODROP);
-- 
2.17.1


From 227b0653da9b78c4c76fe500a679d69609080add Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 27 Jun 2018 08:47:21 -0700
Subject: [PATCH 15/15] tcp: add one more quick ack after after ECN events

[ Upstream commit 15ecbe94a45ef88491ca459b26efdd02f91edb6d ]

Larry Brakmo proposal ( https://patchwork.ozlabs.org/patch/935233/
tcp: force cwnd at least 2 in tcp_cwnd_reduction) made us rethink
about our recent patch removing ~16 quick acks after ECN events.

tcp_enter_quickack_mode(sk, 1) makes sure one immediate ack is sent,
but in the case the sender cwnd was lowered to 1, we do not want
to have a delayed ack for the next packet we will receive.

Fixes: 522040ea5fdd ("tcp: do not aggressively quick ack after ECN events")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Neal Cardwell <ncardwell@google.com>
Cc: Lawrence Brakmo <brakmo@fb.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 124be1636efe..bdabd748f4bc 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -261,7 +261,7 @@ static void __tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb)
 		 * it is probably a retransmit.
 		 */
 		if (tp->ecn_flags & TCP_ECN_SEEN)
-			tcp_enter_quickack_mode(sk, 1);
+			tcp_enter_quickack_mode(sk, 2);
 		break;
 	case INET_ECN_CE:
 		if (tcp_ca_needs_ecn(sk))
@@ -269,7 +269,7 @@ static void __tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb)
 
 		if (!(tp->ecn_flags & TCP_ECN_DEMAND_CWR)) {
 			/* Better not delay acks, sender can have a very low cwnd */
-			tcp_enter_quickack_mode(sk, 1);
+			tcp_enter_quickack_mode(sk, 2);
 			tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
 		}
 		tp->ecn_flags |= TCP_ECN_SEEN;
-- 
2.17.1


[-- Attachment #3: net_417.mbox --]
[-- Type: Application/Octet-Stream, Size: 53786 bytes --]

From a3011cda95eba19d9227585b735f0b6490480fe9 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Fri, 27 Jul 2018 18:15:46 +0200
Subject: [PATCH 01/21] ipv4: remove BUG_ON() from fib_compute_spec_dst

[ Upstream commit 9fc12023d6f51551d6ca9ed7e02ecc19d79caf17 ]

Remove BUG_ON() from fib_compute_spec_dst routine and check
in_dev pointer during flowi4 data structure initialization.
fib_compute_spec_dst routine can be run concurrently with device removal
where ip_ptr net_device pointer is set to NULL. This can happen
if userspace enables pkt info on UDP rx socket and the device
is removed while traffic is flowing

Fixes: 35ebf65e851c ("ipv4: Create and use fib_compute_spec_dst() helper")
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_frontend.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 511d6748ea5f..6901349f07d7 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -292,19 +292,19 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb)
 		return ip_hdr(skb)->daddr;
 
 	in_dev = __in_dev_get_rcu(dev);
-	BUG_ON(!in_dev);
 
 	net = dev_net(dev);
 
 	scope = RT_SCOPE_UNIVERSE;
 	if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) {
+		bool vmark = in_dev && IN_DEV_SRC_VMARK(in_dev);
 		struct flowi4 fl4 = {
 			.flowi4_iif = LOOPBACK_IFINDEX,
 			.flowi4_oif = l3mdev_master_ifindex_rcu(dev),
 			.daddr = ip_hdr(skb)->saddr,
 			.flowi4_tos = RT_TOS(ip_hdr(skb)->tos),
 			.flowi4_scope = scope,
-			.flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0,
+			.flowi4_mark = vmark ? skb->mark : 0,
 		};
 		if (!fib_lookup(net, &fl4, &res, 0))
 			return FIB_RES_PREFSRC(net, res);
-- 
2.17.1


From cba679917eab80739c70a7e41fa68809add69160 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 25 Jul 2018 15:39:27 -0700
Subject: [PATCH 02/21] netdevsim: don't leak devlink resources

[ Upstream commit c259b4fb33ee6e7667bf1d34bf0803b7c5fdbdce ]

Devlink resources registered with devlink_resource_register() have
to be unregistered.

Fixes: 37923ed6b8ce ("netdevsim: Add simple FIB resource controller via devlink")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/netdevsim/devlink.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/netdevsim/devlink.c b/drivers/net/netdevsim/devlink.c
index bef7db5d129a..82f0e2663e1a 100644
--- a/drivers/net/netdevsim/devlink.c
+++ b/drivers/net/netdevsim/devlink.c
@@ -206,6 +206,7 @@ void nsim_devlink_teardown(struct netdevsim *ns)
 		struct net *net = nsim_to_net(ns);
 		bool *reg_devlink = net_generic(net, nsim_devlink_id);
 
+		devlink_resources_unregister(ns->devlink, NULL);
 		devlink_unregister(ns->devlink);
 		devlink_free(ns->devlink);
 		ns->devlink = NULL;
-- 
2.17.1


From 778cd17c5bf2dfcf104a1afccc5986bf25240003 Mon Sep 17 00:00:00 2001
From: Gal Pressman <pressmangal@gmail.com>
Date: Thu, 26 Jul 2018 23:40:33 +0300
Subject: [PATCH 03/21] net: ena: Fix use of uninitialized DMA address bits
 field

[ Upstream commit 101f0cd4f2216d32f1b8a75a2154cf3997484ee2 ]

UBSAN triggers the following undefined behaviour warnings:
[...]
[   13.236124] UBSAN: Undefined behaviour in drivers/net/ethernet/amazon/ena/ena_eth_com.c:468:22
[   13.240043] shift exponent 64 is too large for 64-bit type 'long long unsigned int'
[...]
[   13.744769] UBSAN: Undefined behaviour in drivers/net/ethernet/amazon/ena/ena_eth_com.c:373:4
[   13.748694] shift exponent 64 is too large for 64-bit type 'long long unsigned int'
[...]

When splitting the address to high and low, GENMASK_ULL is used to generate
a bitmask with dma_addr_bits field from io_sq (in ena_com_prepare_tx and
ena_com_add_single_rx_desc).
The problem is that dma_addr_bits is not initialized with a proper value
(besides being cleared in ena_com_create_io_queue).
Assign dma_addr_bits the correct value that is stored in ena_dev when
initializing the SQ.

Fixes: 1738cd3ed342 ("net: ena: Add a driver for Amazon Elastic Network Adapters (ENA)")
Signed-off-by: Gal Pressman <pressmangal@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_com.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index 1b9d3130af4d..17f12c18d225 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -333,6 +333,7 @@ static int ena_com_init_io_sq(struct ena_com_dev *ena_dev,
 
 	memset(&io_sq->desc_addr, 0x0, sizeof(io_sq->desc_addr));
 
+	io_sq->dma_addr_bits = ena_dev->dma_addr_bits;
 	io_sq->desc_entry_size =
 		(io_sq->direction == ENA_COM_IO_QUEUE_DIRECTION_TX) ?
 		sizeof(struct ena_eth_io_tx_desc) :
-- 
2.17.1


From 14a2f45cdcd5c41831d92b56f188c8d3b5adf89a Mon Sep 17 00:00:00 2001
From: tangpengpeng <tangpengpeng@higon.com>
Date: Thu, 26 Jul 2018 14:45:16 +0800
Subject: [PATCH 04/21] net: fix amd-xgbe flow-control issue

[ Upstream commit 7f3fc7ddf719cd6faaf787722c511f6918ac6aab ]

If we enable or disable xgbe flow-control by ethtool ,
it does't work.Because the parameter is not properly
assigned,so we need to adjust the assignment order
of the parameters.

Fixes: c1ce2f77366b ("amd-xgbe: Fix flow control setting logic")
Signed-off-by: tangpengpeng <tangpengpeng@higon.com>
Acked-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe-mdio.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
index 1b45cd73a258..119777986ea4 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
@@ -1128,14 +1128,14 @@ static void xgbe_phy_adjust_link(struct xgbe_prv_data *pdata)
 
 		if (pdata->tx_pause != pdata->phy.tx_pause) {
 			new_state = 1;
-			pdata->hw_if.config_tx_flow_control(pdata);
 			pdata->tx_pause = pdata->phy.tx_pause;
+			pdata->hw_if.config_tx_flow_control(pdata);
 		}
 
 		if (pdata->rx_pause != pdata->phy.rx_pause) {
 			new_state = 1;
-			pdata->hw_if.config_rx_flow_control(pdata);
 			pdata->rx_pause = pdata->phy.rx_pause;
+			pdata->hw_if.config_rx_flow_control(pdata);
 		}
 
 		/* Speed support */
-- 
2.17.1


From 91f1d3d2762ab4b1f1b5a5fcba969891f09d7129 Mon Sep 17 00:00:00 2001
From: Stefan Wahren <stefan.wahren@i2se.com>
Date: Sat, 28 Jul 2018 09:52:10 +0200
Subject: [PATCH 05/21] net: lan78xx: fix rx handling before first packet is
 send

[ Upstream commit 136f55f660192ce04af091642efc75d85e017364 ]

As long the bh tasklet isn't scheduled once, no packet from the rx path
will be handled. Since the tx path also schedule the same tasklet
this situation only persits until the first packet transmission.
So fix this issue by scheduling the tasklet after link reset.

Link: https://github.com/raspberrypi/linux/issues/2617
Fixes: 55d7de9de6c3 ("Microchip's LAN7800 family USB 2/3 to 10/100/1000 Ethernet")
Suggested-by: Floris Bos <bos@je-eigen-domein.nl>
Signed-off-by: Stefan Wahren <stefan.wahren@i2se.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/lan78xx.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 8a76c1e5de8d..838df4c2b17f 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -1216,6 +1216,8 @@ static int lan78xx_link_reset(struct lan78xx_net *dev)
 			mod_timer(&dev->stat_monitor,
 				  jiffies + STAT_UPDATE_TIMER);
 		}
+
+		tasklet_schedule(&dev->bh);
 	}
 
 	return ret;
-- 
2.17.1


From d796b3ed9689a5bab117a1af7d4caad3e72c2fd7 Mon Sep 17 00:00:00 2001
From: Anton Vasilyev <vasilyev@ispras.ru>
Date: Fri, 27 Jul 2018 18:57:47 +0300
Subject: [PATCH 06/21] net: mdio-mux: bcm-iproc: fix wrong getter and setter
 pair

[ Upstream commit b0753408aadf32c7ece9e6b765017881e54af833 ]

mdio_mux_iproc_probe() uses platform_set_drvdata() to store md pointer
in device, whereas mdio_mux_iproc_remove() restores md pointer by
dev_get_platdata(&pdev->dev). This leads to wrong resources release.

The patch replaces getter to platform_get_drvdata.

Fixes: 98bc865a1ec8 ("net: mdio-mux: Add MDIO mux driver for iProc SoCs")
Signed-off-by: Anton Vasilyev <vasilyev@ispras.ru>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mdio-mux-bcm-iproc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/mdio-mux-bcm-iproc.c b/drivers/net/phy/mdio-mux-bcm-iproc.c
index 0831b7142df7..0c5b68e7da51 100644
--- a/drivers/net/phy/mdio-mux-bcm-iproc.c
+++ b/drivers/net/phy/mdio-mux-bcm-iproc.c
@@ -218,7 +218,7 @@ static int mdio_mux_iproc_probe(struct platform_device *pdev)
 
 static int mdio_mux_iproc_remove(struct platform_device *pdev)
 {
-	struct iproc_mdiomux_desc *md = dev_get_platdata(&pdev->dev);
+	struct iproc_mdiomux_desc *md = platform_get_drvdata(pdev);
 
 	mdio_mux_uninit(md->mux_handle);
 	mdiobus_unregister(md->mii_bus);
-- 
2.17.1


From 3207e69e0900d313674b8e59eebee2205d225cb8 Mon Sep 17 00:00:00 2001
From: Eugeniy Paltsev <Eugeniy.Paltsev@synopsys.com>
Date: Thu, 26 Jul 2018 15:05:37 +0300
Subject: [PATCH 07/21] NET: stmmac: align DMA stuff to largest cache line
 length

[ Upstream commit 9939a46d90c6c76f4533d534dbadfa7b39dc6acc ]

As for today STMMAC_ALIGN macro (which is used to align DMA stuff)
relies on L1 line length (L1_CACHE_BYTES).
This isn't correct in case of system with several cache levels
which might have L1 cache line length smaller than L2 line. This
can lead to sharing one cache line between DMA buffer and other
data, so we can lose this data while invalidate DMA buffer before
DMA transaction.

Fix that by using SMP_CACHE_BYTES instead of L1_CACHE_BYTES for
aligning.

Signed-off-by: Eugeniy Paltsev <Eugeniy.Paltsev@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 1e1cc5256eca..57491da89140 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -51,7 +51,7 @@
 #include <linux/of_mdio.h>
 #include "dwmac1000.h"
 
-#define STMMAC_ALIGN(x)	L1_CACHE_ALIGN(x)
+#define	STMMAC_ALIGN(x)		__ALIGN_KERNEL(x, SMP_CACHE_BYTES)
 #define	TSO_MAX_BUFF_SIZE	(SZ_16K - 1)
 
 /* Module parameters */
-- 
2.17.1


From 9aece850cd4795f48f25680b03b62584f42babc6 Mon Sep 17 00:00:00 2001
From: Avinash Repaka <avinash.repaka@oracle.com>
Date: Tue, 24 Jul 2018 20:31:58 -0700
Subject: [PATCH 08/21] RDS: RDMA: Fix the NULL-ptr deref in rds_ib_get_mr

[ Upstream commit 9e630bcb7701f94dbd729fe57d37c089c763ad9f ]

Registration of a memory region(MR) through FRMR/fastreg(unlike FMR)
needs a connection/qp. With a proxy qp, this dependency on connection
will be removed, but that needs more infrastructure patches, which is a
work in progress.

As an intermediate fix, the get_mr returns EOPNOTSUPP when connection
details are not populated. The MR registration through sendmsg() will
continue to work even with fast registration, since connection in this
case is formed upfront.

This patch fixes the following crash:
kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] SMP KASAN
Modules linked in:
CPU: 1 PID: 4244 Comm: syzkaller468044 Not tainted 4.16.0-rc6+ #361
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
RIP: 0010:rds_ib_get_mr+0x5c/0x230 net/rds/ib_rdma.c:544
RSP: 0018:ffff8801b059f890 EFLAGS: 00010202
RAX: dffffc0000000000 RBX: ffff8801b07e1300 RCX: ffffffff8562d96e
RDX: 000000000000000d RSI: 0000000000000001 RDI: 0000000000000068
RBP: ffff8801b059f8b8 R08: ffffed0036274244 R09: ffff8801b13a1200
R10: 0000000000000004 R11: ffffed0036274243 R12: ffff8801b13a1200
R13: 0000000000000001 R14: ffff8801ca09fa9c R15: 0000000000000000
FS:  00007f4d050af700(0000) GS:ffff8801db300000(0000)
knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f4d050aee78 CR3: 00000001b0d9b006 CR4: 00000000001606e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 __rds_rdma_map+0x710/0x1050 net/rds/rdma.c:271
 rds_get_mr_for_dest+0x1d4/0x2c0 net/rds/rdma.c:357
 rds_setsockopt+0x6cc/0x980 net/rds/af_rds.c:347
 SYSC_setsockopt net/socket.c:1849 [inline]
 SyS_setsockopt+0x189/0x360 net/socket.c:1828
 do_syscall_64+0x281/0x940 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x42/0xb7
RIP: 0033:0x4456d9
RSP: 002b:00007f4d050aedb8 EFLAGS: 00000246 ORIG_RAX: 0000000000000036
RAX: ffffffffffffffda RBX: 00000000006dac3c RCX: 00000000004456d9
RDX: 0000000000000007 RSI: 0000000000000114 RDI: 0000000000000004
RBP: 00000000006dac38 R08: 00000000000000a0 R09: 0000000000000000
R10: 0000000020000380 R11: 0000000000000246 R12: 0000000000000000
R13: 00007fffbfb36d6f R14: 00007f4d050af9c0 R15: 0000000000000005
Code: fa 48 c1 ea 03 80 3c 02 00 0f 85 cc 01 00 00 4c 8b bb 80 04 00 00
48
b8 00 00 00 00 00 fc ff df 49 8d 7f 68 48 89 fa 48 c1 ea 03 <80> 3c 02
00 0f
85 9c 01 00 00 4d 8b 7f 68 48 b8 00 00 00 00 00
RIP: rds_ib_get_mr+0x5c/0x230 net/rds/ib_rdma.c:544 RSP:
ffff8801b059f890
---[ end trace 7e1cea13b85473b0 ]---

Reported-by: syzbot+b51c77ef956678a65834@syzkaller.appspotmail.com
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: Avinash Repaka <avinash.repaka@oracle.com>

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/ib_frmr.c |  5 +++++
 net/rds/ib_mr.h   |  3 ++-
 net/rds/ib_rdma.c | 21 +++++++++++++--------
 net/rds/rdma.c    | 13 ++++++++-----
 net/rds/rds.h     |  5 ++++-
 net/rds/send.c    | 12 +++++++-----
 6 files changed, 39 insertions(+), 20 deletions(-)

diff --git a/net/rds/ib_frmr.c b/net/rds/ib_frmr.c
index 48332a6ed738..d152e48ea371 100644
--- a/net/rds/ib_frmr.c
+++ b/net/rds/ib_frmr.c
@@ -344,6 +344,11 @@ struct rds_ib_mr *rds_ib_reg_frmr(struct rds_ib_device *rds_ibdev,
 	struct rds_ib_frmr *frmr;
 	int ret;
 
+	if (!ic) {
+		/* TODO: Add FRWR support for RDS_GET_MR using proxy qp*/
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
 	do {
 		if (ibmr)
 			rds_ib_free_frmr(ibmr, true);
diff --git a/net/rds/ib_mr.h b/net/rds/ib_mr.h
index 0ea4ab017a8c..655f01d427fe 100644
--- a/net/rds/ib_mr.h
+++ b/net/rds/ib_mr.h
@@ -115,7 +115,8 @@ void rds_ib_get_mr_info(struct rds_ib_device *rds_ibdev,
 			struct rds_info_rdma_connection *iinfo);
 void rds_ib_destroy_mr_pool(struct rds_ib_mr_pool *);
 void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents,
-		    struct rds_sock *rs, u32 *key_ret);
+		    struct rds_sock *rs, u32 *key_ret,
+		    struct rds_connection *conn);
 void rds_ib_sync_mr(void *trans_private, int dir);
 void rds_ib_free_mr(void *trans_private, int invalidate);
 void rds_ib_flush_mrs(void);
diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c
index e678699268a2..2e49a40a5e11 100644
--- a/net/rds/ib_rdma.c
+++ b/net/rds/ib_rdma.c
@@ -537,11 +537,12 @@ void rds_ib_flush_mrs(void)
 }
 
 void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents,
-		    struct rds_sock *rs, u32 *key_ret)
+		    struct rds_sock *rs, u32 *key_ret,
+		    struct rds_connection *conn)
 {
 	struct rds_ib_device *rds_ibdev;
 	struct rds_ib_mr *ibmr = NULL;
-	struct rds_ib_connection *ic = rs->rs_conn->c_transport_data;
+	struct rds_ib_connection *ic = NULL;
 	int ret;
 
 	rds_ibdev = rds_ib_get_device(rs->rs_bound_addr);
@@ -550,6 +551,9 @@ void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents,
 		goto out;
 	}
 
+	if (conn)
+		ic = conn->c_transport_data;
+
 	if (!rds_ibdev->mr_8k_pool || !rds_ibdev->mr_1m_pool) {
 		ret = -ENODEV;
 		goto out;
@@ -559,17 +563,18 @@ void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents,
 		ibmr = rds_ib_reg_frmr(rds_ibdev, ic, sg, nents, key_ret);
 	else
 		ibmr = rds_ib_reg_fmr(rds_ibdev, sg, nents, key_ret);
-	if (ibmr)
-		rds_ibdev = NULL;
-
- out:
-	if (!ibmr)
+	if (IS_ERR(ibmr)) {
+		ret = PTR_ERR(ibmr);
 		pr_warn("RDS/IB: rds_ib_get_mr failed (errno=%d)\n", ret);
+	} else {
+		return ibmr;
+	}
 
+ out:
 	if (rds_ibdev)
 		rds_ib_dev_put(rds_ibdev);
 
-	return ibmr;
+	return ERR_PTR(ret);
 }
 
 void rds_ib_destroy_mr_pool(struct rds_ib_mr_pool *pool)
diff --git a/net/rds/rdma.c b/net/rds/rdma.c
index 634cfcb7bba6..80920e47f2c7 100644
--- a/net/rds/rdma.c
+++ b/net/rds/rdma.c
@@ -170,7 +170,8 @@ static int rds_pin_pages(unsigned long user_addr, unsigned int nr_pages,
 }
 
 static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args,
-				u64 *cookie_ret, struct rds_mr **mr_ret)
+			  u64 *cookie_ret, struct rds_mr **mr_ret,
+			  struct rds_conn_path *cp)
 {
 	struct rds_mr *mr = NULL, *found;
 	unsigned int nr_pages;
@@ -269,7 +270,8 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args,
 	 * Note that dma_map() implies that pending writes are
 	 * flushed to RAM, so no dma_sync is needed here. */
 	trans_private = rs->rs_transport->get_mr(sg, nents, rs,
-						 &mr->r_key);
+						 &mr->r_key,
+						 cp ? cp->cp_conn : NULL);
 
 	if (IS_ERR(trans_private)) {
 		for (i = 0 ; i < nents; i++)
@@ -330,7 +332,7 @@ int rds_get_mr(struct rds_sock *rs, char __user *optval, int optlen)
 			   sizeof(struct rds_get_mr_args)))
 		return -EFAULT;
 
-	return __rds_rdma_map(rs, &args, NULL, NULL);
+	return __rds_rdma_map(rs, &args, NULL, NULL, NULL);
 }
 
 int rds_get_mr_for_dest(struct rds_sock *rs, char __user *optval, int optlen)
@@ -354,7 +356,7 @@ int rds_get_mr_for_dest(struct rds_sock *rs, char __user *optval, int optlen)
 	new_args.cookie_addr = args.cookie_addr;
 	new_args.flags = args.flags;
 
-	return __rds_rdma_map(rs, &new_args, NULL, NULL);
+	return __rds_rdma_map(rs, &new_args, NULL, NULL, NULL);
 }
 
 /*
@@ -782,7 +784,8 @@ int rds_cmsg_rdma_map(struct rds_sock *rs, struct rds_message *rm,
 	    rm->m_rdma_cookie != 0)
 		return -EINVAL;
 
-	return __rds_rdma_map(rs, CMSG_DATA(cmsg), &rm->m_rdma_cookie, &rm->rdma.op_rdma_mr);
+	return __rds_rdma_map(rs, CMSG_DATA(cmsg), &rm->m_rdma_cookie,
+			      &rm->rdma.op_rdma_mr, rm->m_conn_path);
 }
 
 /*
diff --git a/net/rds/rds.h b/net/rds/rds.h
index f2272fb8cd45..60b3b787fbdb 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -464,6 +464,8 @@ struct rds_message {
 			struct scatterlist	*op_sg;
 		} data;
 	};
+
+	struct rds_conn_path *m_conn_path;
 };
 
 /*
@@ -544,7 +546,8 @@ struct rds_transport {
 					unsigned int avail);
 	void (*exit)(void);
 	void *(*get_mr)(struct scatterlist *sg, unsigned long nr_sg,
-			struct rds_sock *rs, u32 *key_ret);
+			struct rds_sock *rs, u32 *key_ret,
+			struct rds_connection *conn);
 	void (*sync_mr)(void *trans_private, int direction);
 	void (*free_mr)(void *trans_private, int invalidate);
 	void (*flush_mrs)(void);
diff --git a/net/rds/send.c b/net/rds/send.c
index 94c7f74909be..59f17a2335f4 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -1169,6 +1169,13 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 		rs->rs_conn = conn;
 	}
 
+	if (conn->c_trans->t_mp_capable)
+		cpath = &conn->c_path[rds_send_mprds_hash(rs, conn)];
+	else
+		cpath = &conn->c_path[0];
+
+	rm->m_conn_path = cpath;
+
 	/* Parse any control messages the user may have included. */
 	ret = rds_cmsg_send(rs, rm, msg, &allocated_mr);
 	if (ret) {
@@ -1192,11 +1199,6 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 		goto out;
 	}
 
-	if (conn->c_trans->t_mp_capable)
-		cpath = &conn->c_path[rds_send_mprds_hash(rs, conn)];
-	else
-		cpath = &conn->c_path[0];
-
 	if (rds_destroy_pending(conn)) {
 		ret = -EAGAIN;
 		goto out;
-- 
2.17.1


From a3c32c57efa9fe7dec3ed8418a864c332eb0d2b8 Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Fri, 27 Jul 2018 17:19:12 -0400
Subject: [PATCH 09/21] tcp_bbr: fix bw probing to raise in-flight data for
 very small BDPs

[ Upstream commit 383d470936c05554219094a4d364d964cb324827 ]

For some very small BDPs (with just a few packets) there was a
quantization effect where the target number of packets in flight
during the super-unity-gain (1.25x) phase of gain cycling was
implicitly truncated to a number of packets no larger than the normal
unity-gain (1.0x) phase of gain cycling. This meant that in multi-flow
scenarios some flows could get stuck with a lower bandwidth, because
they did not push enough packets inflight to discover that there was
more bandwidth available. This was really only an issue in multi-flow
LAN scenarios, where RTTs and BDPs are low enough for this to be an
issue.

This fix ensures that gain cycling can raise inflight for small BDPs
by ensuring that in PROBE_BW mode target inflight values with a
super-unity gain are always greater than inflight values with a gain
<= 1. Importantly, this applies whether the inflight value is
calculated for use as a cwnd value, or as a target inflight value for
the end of the super-unity phase in bbr_is_next_cycle_phase() (both
need to be bigger to ensure we can probe with more packets in flight
reliably).

This is a candidate fix for stable releases.

Fixes: 0f8782ea1497 ("tcp_bbr: add BBR congestion control")
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Priyaranjan Jha <priyarjha@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_bbr.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 58e2f479ffb4..4bfff3c87e8e 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -354,6 +354,10 @@ static u32 bbr_target_cwnd(struct sock *sk, u32 bw, int gain)
 	/* Reduce delayed ACKs by rounding up cwnd to the next even number. */
 	cwnd = (cwnd + 1) & ~1U;
 
+	/* Ensure gain cycling gets inflight above BDP even for small BDPs. */
+	if (bbr->mode == BBR_PROBE_BW && gain > BBR_UNIT)
+		cwnd += 2;
+
 	return cwnd;
 }
 
-- 
2.17.1


From ab6454fd3dcea726ba4f2dfab3b0cfd47f0ebfeb Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Mon, 23 Jul 2018 23:36:04 +0900
Subject: [PATCH 10/21] virtio_net: Fix incosistent received bytes counter

[ Upstream commit ecbc42ca5d665e9238a4cdb595024d2e6cf87f2d ]

When received packets are dropped in virtio_net driver, received packets
counter is incremented but bytes counter is not.
As a result, for instance if we drop all packets by XDP, only received
is counted and bytes stays 0, which looks inconsistent.
IMHO received packets/bytes should be counted if packets are produced by
the hypervisor, like what common NICs on physical machines are doing.
So fix the bytes counter.

Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 41 ++++++++++++++++++++++------------------
 1 file changed, 23 insertions(+), 18 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 11a3915e92e9..6bdf01ed07ab 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -551,7 +551,8 @@ static struct sk_buff *receive_small(struct net_device *dev,
 				     struct receive_queue *rq,
 				     void *buf, void *ctx,
 				     unsigned int len,
-				     unsigned int *xdp_xmit)
+				     unsigned int *xdp_xmit,
+				     unsigned int *rbytes)
 {
 	struct sk_buff *skb;
 	struct bpf_prog *xdp_prog;
@@ -567,6 +568,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 	int err;
 
 	len -= vi->hdr_len;
+	*rbytes += len;
 
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(rq->xdp_prog);
@@ -666,11 +668,13 @@ static struct sk_buff *receive_big(struct net_device *dev,
 				   struct virtnet_info *vi,
 				   struct receive_queue *rq,
 				   void *buf,
-				   unsigned int len)
+				   unsigned int len,
+				   unsigned int *rbytes)
 {
 	struct page *page = buf;
 	struct sk_buff *skb = page_to_skb(vi, rq, page, 0, len, PAGE_SIZE);
 
+	*rbytes += len - vi->hdr_len;
 	if (unlikely(!skb))
 		goto err;
 
@@ -688,7 +692,8 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 					 void *buf,
 					 void *ctx,
 					 unsigned int len,
-					 unsigned int *xdp_xmit)
+					 unsigned int *xdp_xmit,
+					 unsigned int *rbytes)
 {
 	struct virtio_net_hdr_mrg_rxbuf *hdr = buf;
 	u16 num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers);
@@ -702,6 +707,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 	int err;
 
 	head_skb = NULL;
+	*rbytes += len - vi->hdr_len;
 
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(rq->xdp_prog);
@@ -831,6 +837,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 			goto err_buf;
 		}
 
+		*rbytes += len;
 		page = virt_to_head_page(buf);
 
 		truesize = mergeable_ctx_to_truesize(ctx);
@@ -886,6 +893,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 			dev->stats.rx_length_errors++;
 			break;
 		}
+		*rbytes += len;
 		page = virt_to_head_page(buf);
 		put_page(page);
 	}
@@ -896,14 +904,13 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 	return NULL;
 }
 
-static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
-		       void *buf, unsigned int len, void **ctx,
-		       unsigned int *xdp_xmit)
+static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
+			void *buf, unsigned int len, void **ctx,
+			unsigned int *xdp_xmit, unsigned int *rbytes)
 {
 	struct net_device *dev = vi->dev;
 	struct sk_buff *skb;
 	struct virtio_net_hdr_mrg_rxbuf *hdr;
-	int ret;
 
 	if (unlikely(len < vi->hdr_len + ETH_HLEN)) {
 		pr_debug("%s: short packet %i\n", dev->name, len);
@@ -915,23 +922,22 @@ static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
 		} else {
 			put_page(virt_to_head_page(buf));
 		}
-		return 0;
+		return;
 	}
 
 	if (vi->mergeable_rx_bufs)
-		skb = receive_mergeable(dev, vi, rq, buf, ctx, len, xdp_xmit);
+		skb = receive_mergeable(dev, vi, rq, buf, ctx, len, xdp_xmit,
+					rbytes);
 	else if (vi->big_packets)
-		skb = receive_big(dev, vi, rq, buf, len);
+		skb = receive_big(dev, vi, rq, buf, len, rbytes);
 	else
-		skb = receive_small(dev, vi, rq, buf, ctx, len, xdp_xmit);
+		skb = receive_small(dev, vi, rq, buf, ctx, len, xdp_xmit, rbytes);
 
 	if (unlikely(!skb))
-		return 0;
+		return;
 
 	hdr = skb_vnet_hdr(skb);
 
-	ret = skb->len;
-
 	if (hdr->hdr.flags & VIRTIO_NET_HDR_F_DATA_VALID)
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
 
@@ -948,12 +954,11 @@ static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
 		 ntohs(skb->protocol), skb->len, skb->pkt_type);
 
 	napi_gro_receive(&rq->napi, skb);
-	return ret;
+	return;
 
 frame_err:
 	dev->stats.rx_frame_errors++;
 	dev_kfree_skb(skb);
-	return 0;
 }
 
 /* Unlike mergeable buffers, all buffers are allocated to the
@@ -1203,13 +1208,13 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
 
 		while (received < budget &&
 		       (buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx))) {
-			bytes += receive_buf(vi, rq, buf, len, ctx, xdp_xmit);
+			receive_buf(vi, rq, buf, len, ctx, xdp_xmit, &bytes);
 			received++;
 		}
 	} else {
 		while (received < budget &&
 		       (buf = virtqueue_get_buf(rq->vq, &len)) != NULL) {
-			bytes += receive_buf(vi, rq, buf, len, NULL, xdp_xmit);
+			receive_buf(vi, rq, buf, len, NULL, xdp_xmit, &bytes);
 			received++;
 		}
 	}
-- 
2.17.1


From d4da627cf2d6d10ab89530fab78ca2dba85fefaa Mon Sep 17 00:00:00 2001
From: Xiao Liang <xiliang@redhat.com>
Date: Fri, 27 Jul 2018 17:56:08 +0800
Subject: [PATCH 11/21] xen-netfront: wait xenbus state change when load module
 manually

[ Upstream commit 822fb18a82abaf4ee7058793d95d340f5dab7bfc ]

When loading module manually, after call xenbus_switch_state to initializes
the state of the netfront device, the driver state did not change so fast
that may lead no dev created in latest kernel. This patch adds wait to make
sure xenbus knows the driver is not in closed/unknown state.

Current state:
[vm]# ethtool eth0
Settings for eth0:
	Link detected: yes
[vm]# modprobe -r xen_netfront
[vm]# modprobe  xen_netfront
[vm]# ethtool eth0
Settings for eth0:
Cannot get device settings: No such device
Cannot get wake-on-lan settings: No such device
Cannot get message level: No such device
Cannot get link status: No such device
No data available

With the patch installed.
[vm]# ethtool eth0
Settings for eth0:
	Link detected: yes
[vm]# modprobe -r xen_netfront
[vm]# modprobe xen_netfront
[vm]# ethtool eth0
Settings for eth0:
	Link detected: yes

Signed-off-by: Xiao Liang <xiliang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netfront.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 1d5082d30187..5fc1540c9c84 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -87,6 +87,7 @@ struct netfront_cb {
 /* IRQ name is queue name with "-tx" or "-rx" appended */
 #define IRQ_NAME_SIZE (QUEUE_NAME_SIZE + 3)
 
+static DECLARE_WAIT_QUEUE_HEAD(module_load_q);
 static DECLARE_WAIT_QUEUE_HEAD(module_unload_q);
 
 struct netfront_stats {
@@ -1330,6 +1331,11 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev)
 	netif_carrier_off(netdev);
 
 	xenbus_switch_state(dev, XenbusStateInitialising);
+	wait_event(module_load_q,
+			   xenbus_read_driver_state(dev->otherend) !=
+			   XenbusStateClosed &&
+			   xenbus_read_driver_state(dev->otherend) !=
+			   XenbusStateUnknown);
 	return netdev;
 
  exit:
-- 
2.17.1


From b772ab4b6d26baee6e3c7d97ef8a8f7e99fdb186 Mon Sep 17 00:00:00 2001
From: Arjun Vynipadath <arjun@chelsio.com>
Date: Wed, 25 Jul 2018 19:39:52 +0530
Subject: [PATCH 12/21] cxgb4: Added missing break in ndo_udp_tunnel_{add/del}

[ Upstream commit 942a656f1f228f06a37adad0e6c347773cfe7bd6 ]

Break statements were missing for Geneve case in
ndo_udp_tunnel_{add/del}, thereby raw mac matchall
entries were not getting added.

Fixes: c746fc0e8b2d("cxgb4: add geneve offload support for T6")
Signed-off-by: Arjun Vynipadath <arjun@chelsio.com>
Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 005283c7cdfe..72c83496e01f 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -3066,6 +3066,7 @@ static void cxgb_del_udp_tunnel(struct net_device *netdev,
 
 		adapter->geneve_port = 0;
 		t4_write_reg(adapter, MPS_RX_GENEVE_TYPE_A, 0);
+		break;
 	default:
 		return;
 	}
@@ -3151,6 +3152,7 @@ static void cxgb_add_udp_tunnel(struct net_device *netdev,
 
 		t4_write_reg(adapter, MPS_RX_GENEVE_TYPE_A,
 			     GENEVE_V(be16_to_cpu(ti->port)) | GENEVE_EN_F);
+		break;
 	default:
 		return;
 	}
-- 
2.17.1


From 92af5be82d85a6ce5f06bdd21ea387e96250e061 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Tue, 24 Jul 2018 14:12:20 +0300
Subject: [PATCH 13/21] net: rollback orig value on failure of
 dev_qdisc_change_tx_queue_len

[ Upstream commit 7effaf06c3cdef6855e127886c7405b9ab62f90d ]

Fix dev_change_tx_queue_len so it rolls back original value
upon a failure in dev_qdisc_change_tx_queue_len.
This is already done for notifirers' failures, share the code.

In case of failure in dev_qdisc_change_tx_queue_len, some tx queues
would still be of the new length, while they should be reverted.
Currently, the revert is not done, and is marked with a TODO label
in dev_qdisc_change_tx_queue_len, and should find some nice solution
to do it.
Yet it is still better to not apply the newly requested value.

Fixes: 48bfd55e7e41 ("net_sched: plug in qdisc ops change_tx_queue_len")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Reported-by: Ran Rozenstein <ranro@mellanox.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 2af787e8b130..1ccc2a2ac2e9 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7113,16 +7113,19 @@ int dev_change_tx_queue_len(struct net_device *dev, unsigned long new_len)
 		dev->tx_queue_len = new_len;
 		res = call_netdevice_notifiers(NETDEV_CHANGE_TX_QUEUE_LEN, dev);
 		res = notifier_to_errno(res);
-		if (res) {
-			netdev_err(dev,
-				   "refused to change device tx_queue_len\n");
-			dev->tx_queue_len = orig_len;
-			return res;
-		}
-		return dev_qdisc_change_tx_queue_len(dev);
+		if (res)
+			goto err_rollback;
+		res = dev_qdisc_change_tx_queue_len(dev);
+		if (res)
+			goto err_rollback;
 	}
 
 	return 0;
+
+err_rollback:
+	netdev_err(dev, "refused to change device tx_queue_len\n");
+	dev->tx_queue_len = orig_len;
+	return res;
 }
 
 /**
-- 
2.17.1


From 498d7c9afefaae48ae1873a03605dd60999b5d31 Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <dima@arista.com>
Date: Fri, 27 Jul 2018 16:54:44 +0100
Subject: [PATCH 14/21] netlink: Do not subscribe to non-existent groups

[ Upstream commit 7acf9d4237c46894e0fa0492dd96314a41742e84 ]

Make ABI more strict about subscribing to group > ngroups.
Code doesn't check for that and it looks bogus.
(one can subscribe to non-existing group)
Still, it's possible to bind() to all possible groups with (-1)

Cc: "David S. Miller" <davem@davemloft.net>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Cc: netdev@vger.kernel.org
Signed-off-by: Dmitry Safonov <dima@arista.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 2e2dd88fc79f..fc5df9598a5a 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1008,6 +1008,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 		if (err)
 			return err;
 	}
+	groups &= (1UL << nlk->ngroups) - 1;
 
 	bound = nlk->bound;
 	if (bound) {
-- 
2.17.1


From fbee661f9993d2732bb29a960ee146dac428dff2 Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <dima@arista.com>
Date: Mon, 30 Jul 2018 18:32:36 +0100
Subject: [PATCH 15/21] netlink: Don't shift with UB on nlk->ngroups

[ Upstream commit 61f4b23769f0cc72ae62c9a81cf08f0397d40da8 ]

On i386 nlk->ngroups might be 32 or 0. Which leads to UB, resulting in
hang during boot.
Check for 0 ngroups and use (unsigned long long) as a type to shift.

Fixes: 7acf9d4237c4 ("netlink: Do not subscribe to non-existent groups").
Reported-by: kernel test robot <rong.a.chen@intel.com>
Signed-off-by: Dmitry Safonov <dima@arista.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index fc5df9598a5a..890f22f90344 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1008,7 +1008,11 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 		if (err)
 			return err;
 	}
-	groups &= (1UL << nlk->ngroups) - 1;
+
+	if (nlk->ngroups == 0)
+		groups = 0;
+	else
+		groups &= (1ULL << nlk->ngroups) - 1;
 
 	bound = nlk->bound;
 	if (bound) {
-- 
2.17.1


From c6282c90ab73b906b8d530f7d8d324cb86823fa4 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 17 May 2018 14:47:25 -0700
Subject: [PATCH 16/21] tcp: do not force quickack when receiving out-of-order
 packets

[ Upstream commit a3893637e1eb0ef5eb1bbc52b3a8d2dfa317a35d ]

As explained in commit 9f9843a751d0 ("tcp: properly handle stretch
acks in slow start"), TCP stacks have to consider how many packets
are acknowledged in one single ACK, because of GRO, but also
because of ACK compression or losses.

We plan to add SACK compression in the following patch, we
must therefore not call tcp_enter_quickack_mode()

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 0f5e9510c3fa..1a68a70ddb0d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4678,8 +4678,6 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 	if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt + tcp_receive_window(tp)))
 		goto out_of_window;
 
-	tcp_enter_quickack_mode(sk);
-
 	if (before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
 		/* Partial packet, seq < rcv_next < end_seq */
 		SOCK_DEBUG(sk, "partial packet: rcv_next %X seq %X - %X\n",
-- 
2.17.1


From 93a399f397b8818df714d69bd3282442ccdbd1d9 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 21 May 2018 15:08:56 -0700
Subject: [PATCH 17/21] tcp: add max_quickacks param to tcp_incr_quickack and
 tcp_enter_quickack_mode

[ Upstream commit 9a9c9b51e54618861420093ae6e9b50a961914c5 ]

We want to add finer control of the number of ACK packets sent after
ECN events.

This patch is not changing current behavior, it only enables following
change.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h    |  2 +-
 net/ipv4/tcp_dctcp.c |  4 ++--
 net/ipv4/tcp_input.c | 24 +++++++++++++-----------
 3 files changed, 16 insertions(+), 14 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 9cf770150539..5ccc4ec646cb 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -342,7 +342,7 @@ ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos,
 			struct pipe_inode_info *pipe, size_t len,
 			unsigned int flags);
 
-void tcp_enter_quickack_mode(struct sock *sk);
+void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks);
 static inline void tcp_dec_quickack_mode(struct sock *sk,
 					 const unsigned int pkts)
 {
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index c78fb53988a1..1a9b88c8cf72 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -138,7 +138,7 @@ static void dctcp_ce_state_0_to_1(struct sock *sk)
 		 */
 		if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
 			__tcp_send_ack(sk, ca->prior_rcv_nxt);
-		tcp_enter_quickack_mode(sk);
+		tcp_enter_quickack_mode(sk, 1);
 	}
 
 	ca->prior_rcv_nxt = tp->rcv_nxt;
@@ -159,7 +159,7 @@ static void dctcp_ce_state_1_to_0(struct sock *sk)
 		 */
 		if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
 			__tcp_send_ack(sk, ca->prior_rcv_nxt);
-		tcp_enter_quickack_mode(sk);
+		tcp_enter_quickack_mode(sk, 1);
 	}
 
 	ca->prior_rcv_nxt = tp->rcv_nxt;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 1a68a70ddb0d..4fa1028b90b5 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -184,21 +184,23 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb)
 	}
 }
 
-static void tcp_incr_quickack(struct sock *sk)
+static void tcp_incr_quickack(struct sock *sk, unsigned int max_quickacks)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	unsigned int quickacks = tcp_sk(sk)->rcv_wnd / (2 * icsk->icsk_ack.rcv_mss);
 
 	if (quickacks == 0)
 		quickacks = 2;
+	quickacks = min(quickacks, max_quickacks);
 	if (quickacks > icsk->icsk_ack.quick)
-		icsk->icsk_ack.quick = min(quickacks, TCP_MAX_QUICKACKS);
+		icsk->icsk_ack.quick = quickacks;
 }
 
-void tcp_enter_quickack_mode(struct sock *sk)
+void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
-	tcp_incr_quickack(sk);
+
+	tcp_incr_quickack(sk, max_quickacks);
 	icsk->icsk_ack.pingpong = 0;
 	icsk->icsk_ack.ato = TCP_ATO_MIN;
 }
@@ -243,7 +245,7 @@ static void __tcp_ecn_check_ce(struct tcp_sock *tp, const struct sk_buff *skb)
 		 * it is probably a retransmit.
 		 */
 		if (tp->ecn_flags & TCP_ECN_SEEN)
-			tcp_enter_quickack_mode((struct sock *)tp);
+			tcp_enter_quickack_mode((struct sock *)tp, TCP_MAX_QUICKACKS);
 		break;
 	case INET_ECN_CE:
 		if (tcp_ca_needs_ecn((struct sock *)tp))
@@ -251,7 +253,7 @@ static void __tcp_ecn_check_ce(struct tcp_sock *tp, const struct sk_buff *skb)
 
 		if (!(tp->ecn_flags & TCP_ECN_DEMAND_CWR)) {
 			/* Better not delay acks, sender can have a very low cwnd */
-			tcp_enter_quickack_mode((struct sock *)tp);
+			tcp_enter_quickack_mode((struct sock *)tp, TCP_MAX_QUICKACKS);
 			tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
 		}
 		tp->ecn_flags |= TCP_ECN_SEEN;
@@ -666,7 +668,7 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb)
 		/* The _first_ data packet received, initialize
 		 * delayed ACK engine.
 		 */
-		tcp_incr_quickack(sk);
+		tcp_incr_quickack(sk, TCP_MAX_QUICKACKS);
 		icsk->icsk_ack.ato = TCP_ATO_MIN;
 	} else {
 		int m = now - icsk->icsk_ack.lrcvtime;
@@ -682,7 +684,7 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb)
 			/* Too long gap. Apparently sender failed to
 			 * restart window, so that we send ACKs quickly.
 			 */
-			tcp_incr_quickack(sk);
+			tcp_incr_quickack(sk, TCP_MAX_QUICKACKS);
 			sk_mem_reclaim(sk);
 		}
 	}
@@ -4136,7 +4138,7 @@ static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb)
 	if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq &&
 	    before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST);
-		tcp_enter_quickack_mode(sk);
+		tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS);
 
 		if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) {
 			u32 end_seq = TCP_SKB_CB(skb)->end_seq;
@@ -4667,7 +4669,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 		tcp_dsack_set(sk, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq);
 
 out_of_window:
-		tcp_enter_quickack_mode(sk);
+		tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS);
 		inet_csk_schedule_ack(sk);
 drop:
 		tcp_drop(sk, skb);
@@ -5744,7 +5746,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 			 * to stand against the temptation 8)     --ANK
 			 */
 			inet_csk_schedule_ack(sk);
-			tcp_enter_quickack_mode(sk);
+			tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS);
 			inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
 						  TCP_DELACK_MAX, TCP_RTO_MAX);
 
-- 
2.17.1


From 9077c70836a242a85051e0fc530b6c856407044b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 21 May 2018 15:08:57 -0700
Subject: [PATCH 18/21] tcp: do not aggressively quick ack after ECN events

[ Upstream commit 522040ea5fdd1c33bbf75e1d7c7c0422b96a94ef ]

ECN signals currently forces TCP to enter quickack mode for
up to 16 (TCP_MAX_QUICKACKS) following incoming packets.

We believe this is not needed, and only sending one immediate ack
for the current packet should be enough.

This should reduce the extra load noticed in DCTCP environments,
after congestion events.

This is part 2 of our effort to reduce pure ACK packets.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 4fa1028b90b5..35e07643f227 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -245,7 +245,7 @@ static void __tcp_ecn_check_ce(struct tcp_sock *tp, const struct sk_buff *skb)
 		 * it is probably a retransmit.
 		 */
 		if (tp->ecn_flags & TCP_ECN_SEEN)
-			tcp_enter_quickack_mode((struct sock *)tp, TCP_MAX_QUICKACKS);
+			tcp_enter_quickack_mode((struct sock *)tp, 1);
 		break;
 	case INET_ECN_CE:
 		if (tcp_ca_needs_ecn((struct sock *)tp))
@@ -253,7 +253,7 @@ static void __tcp_ecn_check_ce(struct tcp_sock *tp, const struct sk_buff *skb)
 
 		if (!(tp->ecn_flags & TCP_ECN_DEMAND_CWR)) {
 			/* Better not delay acks, sender can have a very low cwnd */
-			tcp_enter_quickack_mode((struct sock *)tp, TCP_MAX_QUICKACKS);
+			tcp_enter_quickack_mode((struct sock *)tp, 1);
 			tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
 		}
 		tp->ecn_flags |= TCP_ECN_SEEN;
-- 
2.17.1


From ac29a68f572b5011387bf0c75c0c45acaf7d4009 Mon Sep 17 00:00:00 2001
From: Yousuk Seung <ysseung@google.com>
Date: Mon, 4 Jun 2018 15:29:51 -0700
Subject: [PATCH 19/21] tcp: refactor tcp_ecn_check_ce to remove sk type cast

[ Upstream commit f4c9f85f3b2cb7669830cd04d0be61192a4d2436 ]

Refactor tcp_ecn_check_ce and __tcp_ecn_check_ce to accept struct sock*
instead of tcp_sock* to clean up type casts. This is a pure refactor
patch.

Signed-off-by: Yousuk Seung <ysseung@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 26 ++++++++++++++------------
 1 file changed, 14 insertions(+), 12 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 35e07643f227..48c352f183d5 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -236,8 +236,10 @@ static void tcp_ecn_withdraw_cwr(struct tcp_sock *tp)
 	tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
 }
 
-static void __tcp_ecn_check_ce(struct tcp_sock *tp, const struct sk_buff *skb)
+static void __tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb)
 {
+	struct tcp_sock *tp = tcp_sk(sk);
+
 	switch (TCP_SKB_CB(skb)->ip_dsfield & INET_ECN_MASK) {
 	case INET_ECN_NOT_ECT:
 		/* Funny extension: if ECT is not set on a segment,
@@ -245,31 +247,31 @@ static void __tcp_ecn_check_ce(struct tcp_sock *tp, const struct sk_buff *skb)
 		 * it is probably a retransmit.
 		 */
 		if (tp->ecn_flags & TCP_ECN_SEEN)
-			tcp_enter_quickack_mode((struct sock *)tp, 1);
+			tcp_enter_quickack_mode(sk, 1);
 		break;
 	case INET_ECN_CE:
-		if (tcp_ca_needs_ecn((struct sock *)tp))
-			tcp_ca_event((struct sock *)tp, CA_EVENT_ECN_IS_CE);
+		if (tcp_ca_needs_ecn(sk))
+			tcp_ca_event(sk, CA_EVENT_ECN_IS_CE);
 
 		if (!(tp->ecn_flags & TCP_ECN_DEMAND_CWR)) {
 			/* Better not delay acks, sender can have a very low cwnd */
-			tcp_enter_quickack_mode((struct sock *)tp, 1);
+			tcp_enter_quickack_mode(sk, 1);
 			tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
 		}
 		tp->ecn_flags |= TCP_ECN_SEEN;
 		break;
 	default:
-		if (tcp_ca_needs_ecn((struct sock *)tp))
-			tcp_ca_event((struct sock *)tp, CA_EVENT_ECN_NO_CE);
+		if (tcp_ca_needs_ecn(sk))
+			tcp_ca_event(sk, CA_EVENT_ECN_NO_CE);
 		tp->ecn_flags |= TCP_ECN_SEEN;
 		break;
 	}
 }
 
-static void tcp_ecn_check_ce(struct tcp_sock *tp, const struct sk_buff *skb)
+static void tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb)
 {
-	if (tp->ecn_flags & TCP_ECN_OK)
-		__tcp_ecn_check_ce(tp, skb);
+	if (tcp_sk(sk)->ecn_flags & TCP_ECN_OK)
+		__tcp_ecn_check_ce(sk, skb);
 }
 
 static void tcp_ecn_rcv_synack(struct tcp_sock *tp, const struct tcphdr *th)
@@ -690,7 +692,7 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb)
 	}
 	icsk->icsk_ack.lrcvtime = now;
 
-	tcp_ecn_check_ce(tp, skb);
+	tcp_ecn_check_ce(sk, skb);
 
 	if (skb->len >= 128)
 		tcp_grow_window(sk, skb);
@@ -4406,7 +4408,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 	u32 seq, end_seq;
 	bool fragstolen;
 
-	tcp_ecn_check_ce(tp, skb);
+	tcp_ecn_check_ce(sk, skb);
 
 	if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFODROP);
-- 
2.17.1


From 674194e98fd09e063cbe8d01dd9fc7379abdb51a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 27 Jun 2018 08:47:21 -0700
Subject: [PATCH 20/21] tcp: add one more quick ack after after ECN events

[ Upstream commit 15ecbe94a45ef88491ca459b26efdd02f91edb6d ]

Larry Brakmo proposal ( https://patchwork.ozlabs.org/patch/935233/
tcp: force cwnd at least 2 in tcp_cwnd_reduction) made us rethink
about our recent patch removing ~16 quick acks after ECN events.

tcp_enter_quickack_mode(sk, 1) makes sure one immediate ack is sent,
but in the case the sender cwnd was lowered to 1, we do not want
to have a delayed ack for the next packet we will receive.

Fixes: 522040ea5fdd ("tcp: do not aggressively quick ack after ECN events")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Neal Cardwell <ncardwell@google.com>
Cc: Lawrence Brakmo <brakmo@fb.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 48c352f183d5..a2ddcace1ca3 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -247,7 +247,7 @@ static void __tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb)
 		 * it is probably a retransmit.
 		 */
 		if (tp->ecn_flags & TCP_ECN_SEEN)
-			tcp_enter_quickack_mode(sk, 1);
+			tcp_enter_quickack_mode(sk, 2);
 		break;
 	case INET_ECN_CE:
 		if (tcp_ca_needs_ecn(sk))
@@ -255,7 +255,7 @@ static void __tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb)
 
 		if (!(tp->ecn_flags & TCP_ECN_DEMAND_CWR)) {
 			/* Better not delay acks, sender can have a very low cwnd */
-			tcp_enter_quickack_mode(sk, 1);
+			tcp_enter_quickack_mode(sk, 2);
 			tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
 		}
 		tp->ecn_flags |= TCP_ECN_SEEN;
-- 
2.17.1


From d7d4fef2a8ff3001a0ea686260e066673b03fb95 Mon Sep 17 00:00:00 2001
From: Lawrence Brakmo <brakmo@fb.com>
Date: Mon, 23 Jul 2018 17:49:39 -0700
Subject: [PATCH 21/21] tcp: ack immediately when a cwr packet arrives

[ Upstream commit 9aee40006190a3cda9a4d2dbae71e92617c8c362 ]

We observed high 99 and 99.9% latencies when doing RPCs with DCTCP. The
problem is triggered when the last packet of a request arrives CE
marked. The reply will carry the ECE mark causing TCP to shrink its cwnd
to 1 (because there are no packets in flight). When the 1st packet of
the next request arrives, the ACK was sometimes delayed even though it
is CWR marked, adding up to 40ms to the RPC latency.

This patch insures that CWR marked data packets arriving will be acked
immediately.

Packetdrill script to reproduce the problem:

0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
0.000 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
0.000 setsockopt(3, SOL_TCP, TCP_CONGESTION, "dctcp", 5) = 0
0.000 bind(3, ..., ...) = 0
0.000 listen(3, 1) = 0

0.100 < [ect0] SEW 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
0.100 > SE. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
0.110 < [ect0] . 1:1(0) ack 1 win 257
0.200 accept(3, ..., ...) = 4

0.200 < [ect0] . 1:1001(1000) ack 1 win 257
0.200 > [ect01] . 1:1(0) ack 1001

0.200 write(4, ..., 1) = 1
0.200 > [ect01] P. 1:2(1) ack 1001

0.200 < [ect0] . 1001:2001(1000) ack 2 win 257
0.200 write(4, ..., 1) = 1
0.200 > [ect01] P. 2:3(1) ack 2001

0.200 < [ect0] . 2001:3001(1000) ack 3 win 257
0.200 < [ect0] . 3001:4001(1000) ack 3 win 257
0.200 > [ect01] . 3:3(0) ack 4001

0.210 < [ce] P. 4001:4501(500) ack 3 win 257

+0.001 read(4, ..., 4500) = 4500
+0 write(4, ..., 1) = 1
+0 > [ect01] PE. 3:4(1) ack 4501

+0.010 < [ect0] W. 4501:5501(1000) ack 4 win 257
// Previously the ACK sequence below would be 4501, causing a long RTO
+0.040~+0.045 > [ect01] . 4:4(0) ack 5501   // delayed ack

+0.311 < [ect0] . 5501:6501(1000) ack 4 win 257  // More data
+0 > [ect01] . 4:4(0) ack 6501     // now acks everything

+0.500 < F. 9501:9501(0) ack 4 win 257

Modified based on comments by Neal Cardwell <ncardwell@google.com>

Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a2ddcace1ca3..4f115830f6a8 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -227,8 +227,15 @@ static void tcp_ecn_queue_cwr(struct tcp_sock *tp)
 
 static void tcp_ecn_accept_cwr(struct tcp_sock *tp, const struct sk_buff *skb)
 {
-	if (tcp_hdr(skb)->cwr)
+	if (tcp_hdr(skb)->cwr) {
 		tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
+
+		/* If the sender is telling us it has entered CWR, then its
+		 * cwnd may be very low (even just 1 packet), so we should ACK
+		 * immediately.
+		 */
+		tcp_enter_quickack_mode((struct sock *)tp, 2);
+	}
 }
 
 static void tcp_ecn_withdraw_cwr(struct tcp_sock *tp)
-- 
2.17.1

Re: [PATCHES] Networking

[Greg KH]

On Tue, Jul 31, 2018 at 10:32:19PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for 4.14.x and
> 4.17.x -stable, respectively.

All now applied, thanks.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 111 bytes --]


Please queue up the following networking bug fixes for v4.14.x
and v4.17.x -stable, respectively.

Thank you.

[-- Attachment #2: net_414.mbox --]
[-- Type: Application/Octet-Stream, Size: 19775 bytes --]

From 16e5f023427bcf1ac9e81e067f358104a8206ed2 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 31 Jul 2018 06:30:54 -0700
Subject: [PATCH 1/8] bonding: avoid lockdep confusion in bond_get_stats()

[ Upstream commit 7e2556e40026a1b0c16f37446ab398d5a5a892e4 ]

syzbot found that the following sequence produces a LOCKDEP splat [1]

ip link add bond10 type bond
ip link add bond11 type bond
ip link set bond11 master bond10

To fix this, we can use the already provided nest_level.

This patch also provides correct nesting for dev->addr_list_lock

[1]
WARNING: possible recursive locking detected
4.18.0-rc6+ #167 Not tainted
--------------------------------------------
syz-executor751/4439 is trying to acquire lock:
(____ptrval____) (&(&bond->stats_lock)->rlock){+.+.}, at: spin_lock include/linux/spinlock.h:310 [inline]
(____ptrval____) (&(&bond->stats_lock)->rlock){+.+.}, at: bond_get_stats+0xb4/0x560 drivers/net/bonding/bond_main.c:3426

but task is already holding lock:
(____ptrval____) (&(&bond->stats_lock)->rlock){+.+.}, at: spin_lock include/linux/spinlock.h:310 [inline]
(____ptrval____) (&(&bond->stats_lock)->rlock){+.+.}, at: bond_get_stats+0xb4/0x560 drivers/net/bonding/bond_main.c:3426

other info that might help us debug this:
 Possible unsafe locking scenario:

       CPU0
       ----
  lock(&(&bond->stats_lock)->rlock);
  lock(&(&bond->stats_lock)->rlock);

 *** DEADLOCK ***

 May be due to missing lock nesting notation

3 locks held by syz-executor751/4439:
 #0: (____ptrval____) (rtnl_mutex){+.+.}, at: rtnl_lock+0x17/0x20 net/core/rtnetlink.c:77
 #1: (____ptrval____) (&(&bond->stats_lock)->rlock){+.+.}, at: spin_lock include/linux/spinlock.h:310 [inline]
 #1: (____ptrval____) (&(&bond->stats_lock)->rlock){+.+.}, at: bond_get_stats+0xb4/0x560 drivers/net/bonding/bond_main.c:3426
 #2: (____ptrval____) (rcu_read_lock){....}, at: bond_get_stats+0x0/0x560 include/linux/compiler.h:215

stack backtrace:
CPU: 0 PID: 4439 Comm: syz-executor751 Not tainted 4.18.0-rc6+ #167
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c9/0x2b4 lib/dump_stack.c:113
 print_deadlock_bug kernel/locking/lockdep.c:1765 [inline]
 check_deadlock kernel/locking/lockdep.c:1809 [inline]
 validate_chain kernel/locking/lockdep.c:2405 [inline]
 __lock_acquire.cold.64+0x1fb/0x486 kernel/locking/lockdep.c:3435
 lock_acquire+0x1e4/0x540 kernel/locking/lockdep.c:3924
 __raw_spin_lock include/linux/spinlock_api_smp.h:142 [inline]
 _raw_spin_lock+0x2a/0x40 kernel/locking/spinlock.c:144
 spin_lock include/linux/spinlock.h:310 [inline]
 bond_get_stats+0xb4/0x560 drivers/net/bonding/bond_main.c:3426
 dev_get_stats+0x10f/0x470 net/core/dev.c:8316
 bond_get_stats+0x232/0x560 drivers/net/bonding/bond_main.c:3432
 dev_get_stats+0x10f/0x470 net/core/dev.c:8316
 rtnl_fill_stats+0x4d/0xac0 net/core/rtnetlink.c:1169
 rtnl_fill_ifinfo+0x1aa6/0x3fb0 net/core/rtnetlink.c:1611
 rtmsg_ifinfo_build_skb+0xc8/0x190 net/core/rtnetlink.c:3268
 rtmsg_ifinfo_event.part.30+0x45/0xe0 net/core/rtnetlink.c:3300
 rtmsg_ifinfo_event net/core/rtnetlink.c:3297 [inline]
 rtnetlink_event+0x144/0x170 net/core/rtnetlink.c:4716
 notifier_call_chain+0x180/0x390 kernel/notifier.c:93
 __raw_notifier_call_chain kernel/notifier.c:394 [inline]
 raw_notifier_call_chain+0x2d/0x40 kernel/notifier.c:401
 call_netdevice_notifiers_info+0x3f/0x90 net/core/dev.c:1735
 call_netdevice_notifiers net/core/dev.c:1753 [inline]
 netdev_features_change net/core/dev.c:1321 [inline]
 netdev_change_features+0xb3/0x110 net/core/dev.c:7759
 bond_compute_features.isra.47+0x585/0xa50 drivers/net/bonding/bond_main.c:1120
 bond_enslave+0x1b25/0x5da0 drivers/net/bonding/bond_main.c:1755
 bond_do_ioctl+0x7cb/0xae0 drivers/net/bonding/bond_main.c:3528
 dev_ifsioc+0x43c/0xb30 net/core/dev_ioctl.c:327
 dev_ioctl+0x1b5/0xcc0 net/core/dev_ioctl.c:493
 sock_do_ioctl+0x1d3/0x3e0 net/socket.c:992
 sock_ioctl+0x30d/0x680 net/socket.c:1093
 vfs_ioctl fs/ioctl.c:46 [inline]
 file_ioctl fs/ioctl.c:500 [inline]
 do_vfs_ioctl+0x1de/0x1720 fs/ioctl.c:684
 ksys_ioctl+0xa9/0xd0 fs/ioctl.c:701
 __do_sys_ioctl fs/ioctl.c:708 [inline]
 __se_sys_ioctl fs/ioctl.c:706 [inline]
 __x64_sys_ioctl+0x73/0xb0 fs/ioctl.c:706
 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x440859
Code: e8 2c af 02 00 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 3b 10 fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007ffc51a92878 EFLAGS: 00000213 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 0000000000440859
RDX: 0000000020000040 RSI: 0000000000008990 RDI: 0000000000000003
RBP: 0000000000000000 R08: 00000000004002c8 R09: 00000000004002c8
R10: 00000000022d5880 R11: 0000000000000213 R12: 0000000000007390
R13: 0000000000401db0 R14: 0000000000000000 R15: 0000000000000000

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Cc: Veaceslav Falico <vfalico@gmail.com>
Cc: Andy Gospodarek <andy@greyhouse.net>

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 00245b73c224..15aedb64a02b 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1687,6 +1687,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 		goto err_upper_unlink;
 	}
 
+	bond->nest_level = dev_get_nest_level(bond_dev) + 1;
+
 	/* If the mode uses primary, then the following is handled by
 	 * bond_change_active_slave().
 	 */
@@ -1734,7 +1736,6 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	if (bond_mode_uses_xmit_hash(bond))
 		bond_update_slave_arr(bond, NULL);
 
-	bond->nest_level = dev_get_nest_level(bond_dev);
 
 	netdev_info(bond_dev, "Enslaving %s as %s interface with %s link\n",
 		    slave_dev->name,
@@ -3379,6 +3380,13 @@ static void bond_fold_stats(struct rtnl_link_stats64 *_res,
 	}
 }
 
+static int bond_get_nest_level(struct net_device *bond_dev)
+{
+	struct bonding *bond = netdev_priv(bond_dev);
+
+	return bond->nest_level;
+}
+
 static void bond_get_stats(struct net_device *bond_dev,
 			   struct rtnl_link_stats64 *stats)
 {
@@ -3387,7 +3395,7 @@ static void bond_get_stats(struct net_device *bond_dev,
 	struct list_head *iter;
 	struct slave *slave;
 
-	spin_lock(&bond->stats_lock);
+	spin_lock_nested(&bond->stats_lock, bond_get_nest_level(bond_dev));
 	memcpy(stats, &bond->bond_stats, sizeof(*stats));
 
 	rcu_read_lock();
@@ -4182,6 +4190,7 @@ static const struct net_device_ops bond_netdev_ops = {
 	.ndo_neigh_setup	= bond_neigh_setup,
 	.ndo_vlan_rx_add_vid	= bond_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= bond_vlan_rx_kill_vid,
+	.ndo_get_lock_subclass  = bond_get_nest_level,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_netpoll_setup	= bond_netpoll_setup,
 	.ndo_netpoll_cleanup	= bond_netpoll_cleanup,
@@ -4680,6 +4689,7 @@ static int bond_init(struct net_device *bond_dev)
 	if (!bond->wq)
 		return -ENOMEM;
 
+	bond->nest_level = SINGLE_DEPTH_NESTING;
 	netdev_lockdep_set_classes(bond_dev);
 
 	list_add_tail(&bond->bond_list, &bn->dev_list);
-- 
2.17.1


From 70b85d9c7c3d31632cbdba2ead716db0c8b3579e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 30 Jul 2018 20:09:11 -0700
Subject: [PATCH 2/8] inet: frag: enforce memory limits earlier

[ Upstream commit 56e2c94f055d328f5f6b0a5c1721cca2f2d4e0a1 ]

We currently check current frags memory usage only when
a new frag queue is created. This allows attackers to first
consume the memory budget (default : 4 MB) creating thousands
of frag queues, then sending tiny skbs to exceed high_thresh
limit by 2 to 3 order of magnitude.

Note that before commit 648700f76b03 ("inet: frags: use rhashtables
for reassembly units"), work queue could be starved under DOS,
getting no cpu cycles.
After commit 648700f76b03, only the per frag queue timer can eventually
remove an incomplete frag queue and its skbs.

Fixes: b13d3cbfb8e8 ("inet: frag: move eviction of queues to work queue")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Jann Horn <jannh@google.com>
Cc: Florian Westphal <fw@strlen.de>
Cc: Peter Oskolkov <posk@google.com>
Cc: Paolo Abeni <pabeni@redhat.com>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/inet_fragment.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index e691705f0a85..ba4454ecdf0f 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -356,11 +356,6 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
 {
 	struct inet_frag_queue *q;
 
-	if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh) {
-		inet_frag_schedule_worker(f);
-		return NULL;
-	}
-
 	q = kmem_cache_zalloc(f->frags_cachep, GFP_ATOMIC);
 	if (!q)
 		return NULL;
@@ -397,6 +392,11 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
 	struct inet_frag_queue *q;
 	int depth = 0;
 
+	if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh) {
+		inet_frag_schedule_worker(f);
+		return NULL;
+	}
+
 	if (frag_mem_limit(nf) > nf->low_thresh)
 		inet_frag_schedule_worker(f);
 
-- 
2.17.1


From 23c37a676dd660a02c51f02d682244f12f68abdb Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 30 Jul 2018 21:50:29 -0700
Subject: [PATCH 3/8] ipv4: frags: handle possible skb truesize change

[ Upstream commit 4672694bd4f1aebdab0ad763ae4716e89cb15221 ]

ip_frag_queue() might call pskb_pull() on one skb that
is already in the fragment queue.

We need to take care of possible truesize change, or we
might have an imbalance of the netns frags memory usage.

IPv6 is immune to this bug, because RFC5722, Section 4,
amended by Errata ID 3089 states :

  When reassembling an IPv6 datagram, if
  one or more its constituent fragments is determined to be an
  overlapping fragment, the entire datagram (and any constituent
  fragments) MUST be silently discarded.

Fixes: 158f323b9868 ("net: adjust skb->truesize in pskb_expand_head()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_fragment.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index df8fe0503de0..4cb1befc3949 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -447,11 +447,16 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 		int i = end - FRAG_CB(next)->offset; /* overlap is 'i' bytes */
 
 		if (i < next->len) {
+			int delta = -next->truesize;
+
 			/* Eat head of the next overlapped fragment
 			 * and leave the loop. The next ones cannot overlap.
 			 */
 			if (!pskb_pull(next, i))
 				goto err;
+			delta += next->truesize;
+			if (delta)
+				add_frag_mem_limit(qp->q.net, delta);
 			FRAG_CB(next)->offset += i;
 			qp->q.meat -= i;
 			if (next->ip_summed != CHECKSUM_UNNECESSARY)
-- 
2.17.1


From 57d39d3c866d174e11f85a854e2b0c4c52f89862 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 31 Jul 2018 17:12:52 -0700
Subject: [PATCH 4/8] net: dsa: Do not suspend/resume closed slave_dev

[ Upstream commit a94c689e6c9e72e722f28339e12dff191ee5a265 ]

If a DSA slave network device was previously disabled, there is no need
to suspend or resume it.

Fixes: 2446254915a7 ("net: dsa: allow switch drivers to implement suspend/resume hooks")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/slave.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 865e29e62bad..242e74b9d454 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -1219,6 +1219,9 @@ int dsa_slave_suspend(struct net_device *slave_dev)
 {
 	struct dsa_slave_priv *p = netdev_priv(slave_dev);
 
+	if (!netif_running(slave_dev))
+		return 0;
+
 	netif_device_detach(slave_dev);
 
 	if (p->phy) {
@@ -1236,6 +1239,9 @@ int dsa_slave_resume(struct net_device *slave_dev)
 {
 	struct dsa_slave_priv *p = netdev_priv(slave_dev);
 
+	if (!netif_running(slave_dev))
+		return 0;
+
 	netif_device_attach(slave_dev);
 
 	if (p->phy) {
-- 
2.17.1


From 56f8c3fd9b2feddc5253b0ff7fc23bd410670bad Mon Sep 17 00:00:00 2001
From: Jeremy Cline <jcline@redhat.com>
Date: Tue, 31 Jul 2018 21:13:16 +0000
Subject: [PATCH 5/8] netlink: Fix spectre v1 gadget in netlink_create()

[ Upstream commit bc5b6c0b62b932626a135f516a41838c510c6eba ]

'protocol' is a user-controlled value, so sanitize it after the bounds
check to avoid using it for speculative out-of-bounds access to arrays
indexed by it.

This addresses the following accesses detected with the help of smatch:

* net/netlink/af_netlink.c:654 __netlink_create() warn: potential
  spectre issue 'nlk_cb_mutex_keys' [w]

* net/netlink/af_netlink.c:654 __netlink_create() warn: potential
  spectre issue 'nlk_cb_mutex_key_strings' [w]

* net/netlink/af_netlink.c:685 netlink_create() warn: potential spectre
  issue 'nl_table' [w] (local cap)

Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Jeremy Cline <jcline@redhat.com>
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index b2fcbf012056..68c9d1833b95 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -63,6 +63,7 @@
 #include <linux/hash.h>
 #include <linux/genetlink.h>
 #include <linux/net_namespace.h>
+#include <linux/nospec.h>
 
 #include <net/net_namespace.h>
 #include <net/sock.h>
@@ -647,6 +648,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
 
 	if (protocol < 0 || protocol >= MAX_LINKS)
 		return -EPROTONOSUPPORT;
+	protocol = array_index_nospec(protocol, MAX_LINKS);
 
 	netlink_lock_table();
 #ifdef CONFIG_MODULES
-- 
2.17.1


From 8575211985fe325dac0c1eb35dbc3439270cd4db Mon Sep 17 00:00:00 2001
From: Jose Abreu <Jose.Abreu@synopsys.com>
Date: Tue, 31 Jul 2018 15:08:20 +0100
Subject: [PATCH 6/8] net: stmmac: Fix WoL for PCI-based setups

[ Upstream commit b7d0f08e9129c45ed41bc0cfa8e77067881e45fd ]

WoL won't work in PCI-based setups because we are not saving the PCI EP
state before entering suspend state and not allowing D3 wake.

Fix this by using a wrapper around stmmac_{suspend/resume} which
correctly sets the PCI EP state.

Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/stmicro/stmmac/stmmac_pci.c  | 40 ++++++++++++++++++-
 1 file changed, 38 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
index 8d375e51a526..6a393b16a1fc 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
@@ -257,7 +257,7 @@ static int stmmac_pci_probe(struct pci_dev *pdev,
 		return -ENOMEM;
 
 	/* Enable pci device */
-	ret = pcim_enable_device(pdev);
+	ret = pci_enable_device(pdev);
 	if (ret) {
 		dev_err(&pdev->dev, "%s: ERROR: failed to enable device\n",
 			__func__);
@@ -300,9 +300,45 @@ static int stmmac_pci_probe(struct pci_dev *pdev,
 static void stmmac_pci_remove(struct pci_dev *pdev)
 {
 	stmmac_dvr_remove(&pdev->dev);
+	pci_disable_device(pdev);
 }
 
-static SIMPLE_DEV_PM_OPS(stmmac_pm_ops, stmmac_suspend, stmmac_resume);
+static int stmmac_pci_suspend(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	int ret;
+
+	ret = stmmac_suspend(dev);
+	if (ret)
+		return ret;
+
+	ret = pci_save_state(pdev);
+	if (ret)
+		return ret;
+
+	pci_disable_device(pdev);
+	pci_wake_from_d3(pdev, true);
+	return 0;
+}
+
+static int stmmac_pci_resume(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	int ret;
+
+	pci_restore_state(pdev);
+	pci_set_power_state(pdev, PCI_D0);
+
+	ret = pci_enable_device(pdev);
+	if (ret)
+		return ret;
+
+	pci_set_master(pdev);
+
+	return stmmac_resume(dev);
+}
+
+static SIMPLE_DEV_PM_OPS(stmmac_pm_ops, stmmac_pci_suspend, stmmac_pci_resume);
 
 /* synthetic ID, no official vendor */
 #define PCI_VENDOR_ID_STMMAC 0x700
-- 
2.17.1


From e1953cc5b674cb77b8d89a85729fcaf097cc7850 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 1 Aug 2018 13:27:23 +0100
Subject: [PATCH 7/8] rxrpc: Fix user call ID check in
 rxrpc_service_prealloc_one

[ Upstream commit c01f6c9b3207e52fc9973a066a856ddf7a0538d8 ]

There just check the user call ID isn't already in use, hence should
compare user_call_ID with xcall->user_call_ID, which is current
node's user_call_ID.

Fixes: 540b1c48c37a ("rxrpc: Fix deadlock between call creation and sendmsg/recvmsg")
Suggested-by: David Howells <dhowells@redhat.com>
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/call_accept.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index 3028298ca561..62b1581d44a5 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -115,9 +115,9 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx,
 		while (*pp) {
 			parent = *pp;
 			xcall = rb_entry(parent, struct rxrpc_call, sock_node);
-			if (user_call_ID < call->user_call_ID)
+			if (user_call_ID < xcall->user_call_ID)
 				pp = &(*pp)->rb_left;
-			else if (user_call_ID > call->user_call_ID)
+			else if (user_call_ID > xcall->user_call_ID)
 				pp = &(*pp)->rb_right;
 			else
 				goto id_in_use;
-- 
2.17.1


From 935a319bf546158b4e5ed88246936d19ea65338c Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.com>
Date: Mon, 16 Jul 2018 11:49:27 +0300
Subject: [PATCH 8/8] net/mlx5e: E-Switch, Initialize eswitch only if eswitch
 manager

[ Upstream commit 5f5991f36dce1e69dd8bd7495763eec2e28f08e7 ]

Execute mlx5_eswitch_init() only if we have MLX5_ESWITCH_MANAGER
capabilities.
Do the same for mlx5_eswitch_cleanup().

Fixes: a9f7705ffd66 ("net/mlx5: Unify vport manager capability check")
Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 667415301066..f697084937c3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1616,7 +1616,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 	int vport_num;
 	int err;
 
-	if (!MLX5_VPORT_MANAGER(dev))
+	if (!MLX5_ESWITCH_MANAGER(dev))
 		return 0;
 
 	esw_info(dev,
@@ -1689,7 +1689,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 
 void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw)
 {
-	if (!esw || !MLX5_VPORT_MANAGER(esw->dev))
+	if (!esw || !MLX5_ESWITCH_MANAGER(esw->dev))
 		return;
 
 	esw_info(esw->dev, "cleanup\n");
-- 
2.17.1


[-- Attachment #3: net_417.mbox --]
[-- Type: Application/Octet-Stream, Size: 22966 bytes --]

From fb1d7a174f733f5b6762868236575324cb39b909 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 31 Jul 2018 06:30:54 -0700
Subject: [PATCH 01/10] bonding: avoid lockdep confusion in bond_get_stats()

[ Upstream commit 7e2556e40026a1b0c16f37446ab398d5a5a892e4 ]

syzbot found that the following sequence produces a LOCKDEP splat [1]

ip link add bond10 type bond
ip link add bond11 type bond
ip link set bond11 master bond10

To fix this, we can use the already provided nest_level.

This patch also provides correct nesting for dev->addr_list_lock

[1]
WARNING: possible recursive locking detected
4.18.0-rc6+ #167 Not tainted
--------------------------------------------
syz-executor751/4439 is trying to acquire lock:
(____ptrval____) (&(&bond->stats_lock)->rlock){+.+.}, at: spin_lock include/linux/spinlock.h:310 [inline]
(____ptrval____) (&(&bond->stats_lock)->rlock){+.+.}, at: bond_get_stats+0xb4/0x560 drivers/net/bonding/bond_main.c:3426

but task is already holding lock:
(____ptrval____) (&(&bond->stats_lock)->rlock){+.+.}, at: spin_lock include/linux/spinlock.h:310 [inline]
(____ptrval____) (&(&bond->stats_lock)->rlock){+.+.}, at: bond_get_stats+0xb4/0x560 drivers/net/bonding/bond_main.c:3426

other info that might help us debug this:
 Possible unsafe locking scenario:

       CPU0
       ----
  lock(&(&bond->stats_lock)->rlock);
  lock(&(&bond->stats_lock)->rlock);

 *** DEADLOCK ***

 May be due to missing lock nesting notation

3 locks held by syz-executor751/4439:
 #0: (____ptrval____) (rtnl_mutex){+.+.}, at: rtnl_lock+0x17/0x20 net/core/rtnetlink.c:77
 #1: (____ptrval____) (&(&bond->stats_lock)->rlock){+.+.}, at: spin_lock include/linux/spinlock.h:310 [inline]
 #1: (____ptrval____) (&(&bond->stats_lock)->rlock){+.+.}, at: bond_get_stats+0xb4/0x560 drivers/net/bonding/bond_main.c:3426
 #2: (____ptrval____) (rcu_read_lock){....}, at: bond_get_stats+0x0/0x560 include/linux/compiler.h:215

stack backtrace:
CPU: 0 PID: 4439 Comm: syz-executor751 Not tainted 4.18.0-rc6+ #167
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c9/0x2b4 lib/dump_stack.c:113
 print_deadlock_bug kernel/locking/lockdep.c:1765 [inline]
 check_deadlock kernel/locking/lockdep.c:1809 [inline]
 validate_chain kernel/locking/lockdep.c:2405 [inline]
 __lock_acquire.cold.64+0x1fb/0x486 kernel/locking/lockdep.c:3435
 lock_acquire+0x1e4/0x540 kernel/locking/lockdep.c:3924
 __raw_spin_lock include/linux/spinlock_api_smp.h:142 [inline]
 _raw_spin_lock+0x2a/0x40 kernel/locking/spinlock.c:144
 spin_lock include/linux/spinlock.h:310 [inline]
 bond_get_stats+0xb4/0x560 drivers/net/bonding/bond_main.c:3426
 dev_get_stats+0x10f/0x470 net/core/dev.c:8316
 bond_get_stats+0x232/0x560 drivers/net/bonding/bond_main.c:3432
 dev_get_stats+0x10f/0x470 net/core/dev.c:8316
 rtnl_fill_stats+0x4d/0xac0 net/core/rtnetlink.c:1169
 rtnl_fill_ifinfo+0x1aa6/0x3fb0 net/core/rtnetlink.c:1611
 rtmsg_ifinfo_build_skb+0xc8/0x190 net/core/rtnetlink.c:3268
 rtmsg_ifinfo_event.part.30+0x45/0xe0 net/core/rtnetlink.c:3300
 rtmsg_ifinfo_event net/core/rtnetlink.c:3297 [inline]
 rtnetlink_event+0x144/0x170 net/core/rtnetlink.c:4716
 notifier_call_chain+0x180/0x390 kernel/notifier.c:93
 __raw_notifier_call_chain kernel/notifier.c:394 [inline]
 raw_notifier_call_chain+0x2d/0x40 kernel/notifier.c:401
 call_netdevice_notifiers_info+0x3f/0x90 net/core/dev.c:1735
 call_netdevice_notifiers net/core/dev.c:1753 [inline]
 netdev_features_change net/core/dev.c:1321 [inline]
 netdev_change_features+0xb3/0x110 net/core/dev.c:7759
 bond_compute_features.isra.47+0x585/0xa50 drivers/net/bonding/bond_main.c:1120
 bond_enslave+0x1b25/0x5da0 drivers/net/bonding/bond_main.c:1755
 bond_do_ioctl+0x7cb/0xae0 drivers/net/bonding/bond_main.c:3528
 dev_ifsioc+0x43c/0xb30 net/core/dev_ioctl.c:327
 dev_ioctl+0x1b5/0xcc0 net/core/dev_ioctl.c:493
 sock_do_ioctl+0x1d3/0x3e0 net/socket.c:992
 sock_ioctl+0x30d/0x680 net/socket.c:1093
 vfs_ioctl fs/ioctl.c:46 [inline]
 file_ioctl fs/ioctl.c:500 [inline]
 do_vfs_ioctl+0x1de/0x1720 fs/ioctl.c:684
 ksys_ioctl+0xa9/0xd0 fs/ioctl.c:701
 __do_sys_ioctl fs/ioctl.c:708 [inline]
 __se_sys_ioctl fs/ioctl.c:706 [inline]
 __x64_sys_ioctl+0x73/0xb0 fs/ioctl.c:706
 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x440859
Code: e8 2c af 02 00 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 3b 10 fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007ffc51a92878 EFLAGS: 00000213 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 0000000000440859
RDX: 0000000020000040 RSI: 0000000000008990 RDI: 0000000000000003
RBP: 0000000000000000 R08: 00000000004002c8 R09: 00000000004002c8
R10: 00000000022d5880 R11: 0000000000000213 R12: 0000000000007390
R13: 0000000000401db0 R14: 0000000000000000 R15: 0000000000000000

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Cc: Veaceslav Falico <vfalico@gmail.com>
Cc: Andy Gospodarek <andy@greyhouse.net>

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 1f1e97b26f95..da94bd39aff6 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1691,6 +1691,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 		goto err_upper_unlink;
 	}
 
+	bond->nest_level = dev_get_nest_level(bond_dev) + 1;
+
 	/* If the mode uses primary, then the following is handled by
 	 * bond_change_active_slave().
 	 */
@@ -1738,7 +1740,6 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 	if (bond_mode_uses_xmit_hash(bond))
 		bond_update_slave_arr(bond, NULL);
 
-	bond->nest_level = dev_get_nest_level(bond_dev);
 
 	netdev_info(bond_dev, "Enslaving %s as %s interface with %s link\n",
 		    slave_dev->name,
@@ -3389,6 +3390,13 @@ static void bond_fold_stats(struct rtnl_link_stats64 *_res,
 	}
 }
 
+static int bond_get_nest_level(struct net_device *bond_dev)
+{
+	struct bonding *bond = netdev_priv(bond_dev);
+
+	return bond->nest_level;
+}
+
 static void bond_get_stats(struct net_device *bond_dev,
 			   struct rtnl_link_stats64 *stats)
 {
@@ -3397,7 +3405,7 @@ static void bond_get_stats(struct net_device *bond_dev,
 	struct list_head *iter;
 	struct slave *slave;
 
-	spin_lock(&bond->stats_lock);
+	spin_lock_nested(&bond->stats_lock, bond_get_nest_level(bond_dev));
 	memcpy(stats, &bond->bond_stats, sizeof(*stats));
 
 	rcu_read_lock();
@@ -4192,6 +4200,7 @@ static const struct net_device_ops bond_netdev_ops = {
 	.ndo_neigh_setup	= bond_neigh_setup,
 	.ndo_vlan_rx_add_vid	= bond_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= bond_vlan_rx_kill_vid,
+	.ndo_get_lock_subclass  = bond_get_nest_level,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_netpoll_setup	= bond_netpoll_setup,
 	.ndo_netpoll_cleanup	= bond_netpoll_cleanup,
@@ -4690,6 +4699,7 @@ static int bond_init(struct net_device *bond_dev)
 	if (!bond->wq)
 		return -ENOMEM;
 
+	bond->nest_level = SINGLE_DEPTH_NESTING;
 	netdev_lockdep_set_classes(bond_dev);
 
 	list_add_tail(&bond->bond_list, &bn->dev_list);
-- 
2.17.1


From fc75cdf29e3e18484fa755df7d625d3ceb0794e0 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 30 Jul 2018 20:09:11 -0700
Subject: [PATCH 02/10] inet: frag: enforce memory limits earlier

[ Upstream commit 56e2c94f055d328f5f6b0a5c1721cca2f2d4e0a1 ]

We currently check current frags memory usage only when
a new frag queue is created. This allows attackers to first
consume the memory budget (default : 4 MB) creating thousands
of frag queues, then sending tiny skbs to exceed high_thresh
limit by 2 to 3 order of magnitude.

Note that before commit 648700f76b03 ("inet: frags: use rhashtables
for reassembly units"), work queue could be starved under DOS,
getting no cpu cycles.
After commit 648700f76b03, only the per frag queue timer can eventually
remove an incomplete frag queue and its skbs.

Fixes: b13d3cbfb8e8 ("inet: frag: move eviction of queues to work queue")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Jann Horn <jannh@google.com>
Cc: Florian Westphal <fw@strlen.de>
Cc: Peter Oskolkov <posk@google.com>
Cc: Paolo Abeni <pabeni@redhat.com>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/inet_fragment.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index c9e35b81d093..eeb6646aa892 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -157,9 +157,6 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
 {
 	struct inet_frag_queue *q;
 
-	if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh)
-		return NULL;
-
 	q = kmem_cache_zalloc(f->frags_cachep, GFP_ATOMIC);
 	if (!q)
 		return NULL;
@@ -204,6 +201,9 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key)
 {
 	struct inet_frag_queue *fq;
 
+	if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh)
+		return NULL;
+
 	rcu_read_lock();
 
 	fq = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params);
-- 
2.17.1


From 643c723ad4a12ed388a1ebcf13beb06d2543075c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 30 Jul 2018 21:50:29 -0700
Subject: [PATCH 03/10] ipv4: frags: handle possible skb truesize change

[ Upstream commit 4672694bd4f1aebdab0ad763ae4716e89cb15221 ]

ip_frag_queue() might call pskb_pull() on one skb that
is already in the fragment queue.

We need to take care of possible truesize change, or we
might have an imbalance of the netns frags memory usage.

IPv6 is immune to this bug, because RFC5722, Section 4,
amended by Errata ID 3089 states :

  When reassembling an IPv6 datagram, if
  one or more its constituent fragments is determined to be an
  overlapping fragment, the entire datagram (and any constituent
  fragments) MUST be silently discarded.

Fixes: 158f323b9868 ("net: adjust skb->truesize in pskb_expand_head()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_fragment.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 8e9528ebaa8e..d14d741fb05e 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -383,11 +383,16 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 		int i = end - next->ip_defrag_offset; /* overlap is 'i' bytes */
 
 		if (i < next->len) {
+			int delta = -next->truesize;
+
 			/* Eat head of the next overlapped fragment
 			 * and leave the loop. The next ones cannot overlap.
 			 */
 			if (!pskb_pull(next, i))
 				goto err;
+			delta += next->truesize;
+			if (delta)
+				add_frag_mem_limit(qp->q.net, delta);
 			next->ip_defrag_offset += i;
 			qp->q.meat -= i;
 			if (next->ip_summed != CHECKSUM_UNNECESSARY)
-- 
2.17.1


From 7b867601c708b5bdffccca2d8ed43fa21da02925 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 31 Jul 2018 17:12:52 -0700
Subject: [PATCH 04/10] net: dsa: Do not suspend/resume closed slave_dev

[ Upstream commit a94c689e6c9e72e722f28339e12dff191ee5a265 ]

If a DSA slave network device was previously disabled, there is no need
to suspend or resume it.

Fixes: 2446254915a7 ("net: dsa: allow switch drivers to implement suspend/resume hooks")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/slave.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 18561af7a8f1..01fa96f29734 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -1195,6 +1195,9 @@ int dsa_slave_suspend(struct net_device *slave_dev)
 {
 	struct dsa_slave_priv *p = netdev_priv(slave_dev);
 
+	if (!netif_running(slave_dev))
+		return 0;
+
 	netif_device_detach(slave_dev);
 
 	if (slave_dev->phydev) {
@@ -1210,6 +1213,9 @@ int dsa_slave_suspend(struct net_device *slave_dev)
 
 int dsa_slave_resume(struct net_device *slave_dev)
 {
+	if (!netif_running(slave_dev))
+		return 0;
+
 	netif_device_attach(slave_dev);
 
 	if (slave_dev->phydev) {
-- 
2.17.1


From bf3e63938f7bf2727968ba241a05e9a52f85378d Mon Sep 17 00:00:00 2001
From: Jeremy Cline <jcline@redhat.com>
Date: Tue, 31 Jul 2018 21:13:16 +0000
Subject: [PATCH 05/10] netlink: Fix spectre v1 gadget in netlink_create()

[ Upstream commit bc5b6c0b62b932626a135f516a41838c510c6eba ]

'protocol' is a user-controlled value, so sanitize it after the bounds
check to avoid using it for speculative out-of-bounds access to arrays
indexed by it.

This addresses the following accesses detected with the help of smatch:

* net/netlink/af_netlink.c:654 __netlink_create() warn: potential
  spectre issue 'nlk_cb_mutex_keys' [w]

* net/netlink/af_netlink.c:654 __netlink_create() warn: potential
  spectre issue 'nlk_cb_mutex_key_strings' [w]

* net/netlink/af_netlink.c:685 netlink_create() warn: potential spectre
  issue 'nl_table' [w] (local cap)

Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Jeremy Cline <jcline@redhat.com>
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 890f22f90344..adc434752d67 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -63,6 +63,7 @@
 #include <linux/hash.h>
 #include <linux/genetlink.h>
 #include <linux/net_namespace.h>
+#include <linux/nospec.h>
 
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
@@ -679,6 +680,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
 
 	if (protocol < 0 || protocol >= MAX_LINKS)
 		return -EPROTONOSUPPORT;
+	protocol = array_index_nospec(protocol, MAX_LINKS);
 
 	netlink_lock_table();
 #ifdef CONFIG_MODULES
-- 
2.17.1


From e7ae7c2eba0b38465d494666efb68477dedd1896 Mon Sep 17 00:00:00 2001
From: Jose Abreu <Jose.Abreu@synopsys.com>
Date: Tue, 31 Jul 2018 15:08:20 +0100
Subject: [PATCH 06/10] net: stmmac: Fix WoL for PCI-based setups

[ Upstream commit b7d0f08e9129c45ed41bc0cfa8e77067881e45fd ]

WoL won't work in PCI-based setups because we are not saving the PCI EP
state before entering suspend state and not allowing D3 wake.

Fix this by using a wrapper around stmmac_{suspend/resume} which
correctly sets the PCI EP state.

Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/stmicro/stmmac/stmmac_pci.c  | 40 ++++++++++++++++++-
 1 file changed, 38 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
index 8d375e51a526..6a393b16a1fc 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
@@ -257,7 +257,7 @@ static int stmmac_pci_probe(struct pci_dev *pdev,
 		return -ENOMEM;
 
 	/* Enable pci device */
-	ret = pcim_enable_device(pdev);
+	ret = pci_enable_device(pdev);
 	if (ret) {
 		dev_err(&pdev->dev, "%s: ERROR: failed to enable device\n",
 			__func__);
@@ -300,9 +300,45 @@ static int stmmac_pci_probe(struct pci_dev *pdev,
 static void stmmac_pci_remove(struct pci_dev *pdev)
 {
 	stmmac_dvr_remove(&pdev->dev);
+	pci_disable_device(pdev);
 }
 
-static SIMPLE_DEV_PM_OPS(stmmac_pm_ops, stmmac_suspend, stmmac_resume);
+static int stmmac_pci_suspend(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	int ret;
+
+	ret = stmmac_suspend(dev);
+	if (ret)
+		return ret;
+
+	ret = pci_save_state(pdev);
+	if (ret)
+		return ret;
+
+	pci_disable_device(pdev);
+	pci_wake_from_d3(pdev, true);
+	return 0;
+}
+
+static int stmmac_pci_resume(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	int ret;
+
+	pci_restore_state(pdev);
+	pci_set_power_state(pdev, PCI_D0);
+
+	ret = pci_enable_device(pdev);
+	if (ret)
+		return ret;
+
+	pci_set_master(pdev);
+
+	return stmmac_resume(dev);
+}
+
+static SIMPLE_DEV_PM_OPS(stmmac_pm_ops, stmmac_pci_suspend, stmmac_pci_resume);
 
 /* synthetic ID, no official vendor */
 #define PCI_VENDOR_ID_STMMAC 0x700
-- 
2.17.1


From 505079efa33ec0edc015a15811b258cee37c6620 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 1 Aug 2018 13:27:23 +0100
Subject: [PATCH 07/10] rxrpc: Fix user call ID check in
 rxrpc_service_prealloc_one

[ Upstream commit c01f6c9b3207e52fc9973a066a856ddf7a0538d8 ]

There just check the user call ID isn't already in use, hence should
compare user_call_ID with xcall->user_call_ID, which is current
node's user_call_ID.

Fixes: 540b1c48c37a ("rxrpc: Fix deadlock between call creation and sendmsg/recvmsg")
Suggested-by: David Howells <dhowells@redhat.com>
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/call_accept.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index a9a9be5519b9..9d1e298b784c 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -116,9 +116,9 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx,
 		while (*pp) {
 			parent = *pp;
 			xcall = rb_entry(parent, struct rxrpc_call, sock_node);
-			if (user_call_ID < call->user_call_ID)
+			if (user_call_ID < xcall->user_call_ID)
 				pp = &(*pp)->rb_left;
-			else if (user_call_ID > call->user_call_ID)
+			else if (user_call_ID > xcall->user_call_ID)
 				pp = &(*pp)->rb_right;
 			else
 				goto id_in_use;
-- 
2.17.1


From df93c987aea2e1470e024e10a141bec3c55c84e6 Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.com>
Date: Mon, 16 Jul 2018 11:49:27 +0300
Subject: [PATCH 08/10] net/mlx5e: E-Switch, Initialize eswitch only if eswitch
 manager

[ Upstream commit 5f5991f36dce1e69dd8bd7495763eec2e28f08e7 ]

Execute mlx5_eswitch_init() only if we have MLX5_ESWITCH_MANAGER
capabilities.
Do the same for mlx5_eswitch_cleanup().

Fixes: a9f7705ffd66 ("net/mlx5: Unify vport manager capability check")
Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 0a75e9d441e6..4f52f87cf210 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1698,7 +1698,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 	int vport_num;
 	int err;
 
-	if (!MLX5_VPORT_MANAGER(dev))
+	if (!MLX5_ESWITCH_MANAGER(dev))
 		return 0;
 
 	esw_info(dev,
@@ -1767,7 +1767,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 
 void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw)
 {
-	if (!esw || !MLX5_VPORT_MANAGER(esw->dev))
+	if (!esw || !MLX5_ESWITCH_MANAGER(esw->dev))
 		return;
 
 	esw_info(esw->dev, "cleanup\n");
-- 
2.17.1


From 0b0cc877640a41539f29f51ffda85ab7e02f5e97 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Thu, 19 Jul 2018 16:17:00 +0000
Subject: [PATCH 09/10] net/mlx5e: Set port trust mode to PCP as default

[ Upstream commit 2e8e70d249e8c5c79bf88bbb36bb68154ab15471 ]

The hairpin offload code has dependency on the trust mode being PCP.

Hence we should set PCP as the default for handling cases where we are
disallowed to read the trust mode from the FW, or failed to initialize it.

Fixes: 106be53b6b0a ('net/mlx5e: Set per priority hairpin pairs')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index 0c6015ce85fd..f7c4feefaf2a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -1057,6 +1057,8 @@ static int mlx5e_trust_initialize(struct mlx5e_priv *priv)
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int err;
 
+	priv->dcbx_dp.trust_state = MLX5_QPTS_TRUST_PCP;
+
 	if (!MLX5_DSCP_SUPPORTED(mdev))
 		return 0;
 
-- 
2.17.1


From e0cbfcb62f5ba16d7edcfd4aabf0891bbfebdb48 Mon Sep 17 00:00:00 2001
From: Feras Daoud <ferasda@mellanox.com>
Date: Sun, 15 Jul 2018 13:59:36 +0300
Subject: [PATCH 10/10] net/mlx5e: IPoIB, Set the netdevice sw mtu in ipoib
 enhanced flow

[ Upstream commit 8e1d162d8e81838119de18b4ca1e302ce906f2a6 ]

After introduction of the cited commit, mlx5e_build_nic_params
receives the netdevice mtu in order to set the sw_mtu of mlx5e_params.
For enhanced IPoIB, the netdevice mtu is not set in this stage,
therefore, the initial sw_mtu equals zero. As a result, the hw_mtu
of the receive queue will be calculated incorrectly causing traffic
issues.

To fix this issue, query for port mtu before building the nic params.

Fixes: 472a1e44b349 ("net/mlx5e: Save MTU in channels params")
Signed-off-by: Feras Daoud <ferasda@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index af3bb2f7a504..b7c21eb21a21 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -76,6 +76,7 @@ void mlx5i_init(struct mlx5_core_dev *mdev,
 		void *ppriv)
 {
 	struct mlx5e_priv *priv  = mlx5i_epriv(netdev);
+	u16 max_mtu;
 
 	/* priv init */
 	priv->mdev        = mdev;
@@ -84,6 +85,9 @@ void mlx5i_init(struct mlx5_core_dev *mdev,
 	priv->ppriv       = ppriv;
 	mutex_init(&priv->state_lock);
 
+	mlx5_query_port_max_mtu(mdev, &max_mtu, 1);
+	netdev->mtu = max_mtu;
+
 	mlx5e_build_nic_params(mdev, &priv->channels.params,
 			       profile->max_nch(mdev), netdev->mtu);
 	mlx5i_build_nic_params(mdev, &priv->channels.params);
-- 
2.17.1

Re: [PATCHES] Networking

[Greg KH]

On Fri, Aug 03, 2018 at 10:05:23PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.14.x
> and v4.17.x -stable, respectively.

All now applied, thanks.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 105 bytes --]


Please queue up the following networking bug fixes up for 4.17 and
4.18 -stable, respectively.

Thanks!

[-- Attachment #2: net_417.mbox --]
[-- Type: Application/Octet-Stream, Size: 64756 bytes --]

From b5ff1eeaa00b27ff42713012e42b9fb07bddc11a Mon Sep 17 00:00:00 2001
From: Alexey Kodanev <alexey.kodanev@oracle.com>
Date: Tue, 7 Aug 2018 20:03:57 +0300
Subject: [PATCH 01/17] dccp: fix undefined behavior with 'cwnd' shift in
 ccid2_cwnd_restart()

[ Upstream commit 61ef4b07fcdc30535889990cf4229766502561cf ]

The shift of 'cwnd' with '(now - hc->tx_lsndtime) / hc->tx_rto' value
can lead to undefined behavior [1].

In order to fix this use a gradual shift of the window with a 'while'
loop, similar to what tcp_cwnd_restart() is doing.

When comparing delta and RTO there is a minor difference between TCP
and DCCP, the last one also invokes dccp_cwnd_restart() and reduces
'cwnd' if delta equals RTO. That case is preserved in this change.

[1]:
[40850.963623] UBSAN: Undefined behaviour in net/dccp/ccids/ccid2.c:237:7
[40851.043858] shift exponent 67 is too large for 32-bit type 'unsigned int'
[40851.127163] CPU: 3 PID: 15940 Comm: netstress Tainted: G        W   E     4.18.0-rc7.x86_64 #1
...
[40851.377176] Call Trace:
[40851.408503]  dump_stack+0xf1/0x17b
[40851.451331]  ? show_regs_print_info+0x5/0x5
[40851.503555]  ubsan_epilogue+0x9/0x7c
[40851.548363]  __ubsan_handle_shift_out_of_bounds+0x25b/0x2b4
[40851.617109]  ? __ubsan_handle_load_invalid_value+0x18f/0x18f
[40851.686796]  ? xfrm4_output_finish+0x80/0x80
[40851.739827]  ? lock_downgrade+0x6d0/0x6d0
[40851.789744]  ? xfrm4_prepare_output+0x160/0x160
[40851.845912]  ? ip_queue_xmit+0x810/0x1db0
[40851.895845]  ? ccid2_hc_tx_packet_sent+0xd36/0x10a0 [dccp]
[40851.963530]  ccid2_hc_tx_packet_sent+0xd36/0x10a0 [dccp]
[40852.029063]  dccp_xmit_packet+0x1d3/0x720 [dccp]
[40852.086254]  dccp_write_xmit+0x116/0x1d0 [dccp]
[40852.142412]  dccp_sendmsg+0x428/0xb20 [dccp]
[40852.195454]  ? inet_dccp_listen+0x200/0x200 [dccp]
[40852.254833]  ? sched_clock+0x5/0x10
[40852.298508]  ? sched_clock+0x5/0x10
[40852.342194]  ? inet_create+0xdf0/0xdf0
[40852.388988]  sock_sendmsg+0xd9/0x160
...

Fixes: 113ced1f52e5 ("dccp ccid-2: Perform congestion-window validation")
Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ccids/ccid2.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c
index 385f153fe031..33c5b1c88be2 100644
--- a/net/dccp/ccids/ccid2.c
+++ b/net/dccp/ccids/ccid2.c
@@ -228,14 +228,16 @@ static void ccid2_cwnd_restart(struct sock *sk, const u32 now)
 	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
 	u32 cwnd = hc->tx_cwnd, restart_cwnd,
 	    iwnd = rfc3390_bytes_to_packets(dccp_sk(sk)->dccps_mss_cache);
+	s32 delta = now - hc->tx_lsndtime;
 
 	hc->tx_ssthresh = max(hc->tx_ssthresh, (cwnd >> 1) + (cwnd >> 2));
 
 	/* don't reduce cwnd below the initial window (IW) */
 	restart_cwnd = min(cwnd, iwnd);
-	cwnd >>= (now - hc->tx_lsndtime) / hc->tx_rto;
-	hc->tx_cwnd = max(cwnd, restart_cwnd);
 
+	while ((delta -= hc->tx_rto) >= 0 && cwnd > restart_cwnd)
+		cwnd >>= 1;
+	hc->tx_cwnd = max(cwnd, restart_cwnd);
 	hc->tx_cwnd_stamp = now;
 	hc->tx_cwnd_used  = 0;
 
-- 
2.17.1


From ce6f14608571d12841c8a72332004c8c52cf0823 Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Fri, 10 Aug 2018 11:14:56 -0700
Subject: [PATCH 02/17] l2tp: use sk_dst_check() to avoid race on
 sk->sk_dst_cache

[ Upstream commit 6d37fa49da1e8db8fb1995be22ac837ca41ac8a8 ]

In l2tp code, if it is a L2TP_UDP_ENCAP tunnel, tunnel->sk points to a
UDP socket. User could call sendmsg() on both this tunnel and the UDP
socket itself concurrently. As l2tp_xmit_skb() holds socket lock and call
__sk_dst_check() to refresh sk->sk_dst_cache, while udpv6_sendmsg() is
lockless and call sk_dst_check() to refresh sk->sk_dst_cache, there
could be a race and cause the dst cache to be freed multiple times.
So we fix l2tp side code to always call sk_dst_check() to garantee
xchg() is called when refreshing sk->sk_dst_cache to avoid race
conditions.

Syzkaller reported stack trace:
BUG: KASAN: use-after-free in atomic_read include/asm-generic/atomic-instrumented.h:21 [inline]
BUG: KASAN: use-after-free in atomic_fetch_add_unless include/linux/atomic.h:575 [inline]
BUG: KASAN: use-after-free in atomic_add_unless include/linux/atomic.h:597 [inline]
BUG: KASAN: use-after-free in dst_hold_safe include/net/dst.h:308 [inline]
BUG: KASAN: use-after-free in ip6_hold_safe+0xe6/0x670 net/ipv6/route.c:1029
Read of size 4 at addr ffff8801aea9a880 by task syz-executor129/4829

CPU: 0 PID: 4829 Comm: syz-executor129 Not tainted 4.18.0-rc7-next-20180802+ #30
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c9/0x2b4 lib/dump_stack.c:113
 print_address_description+0x6c/0x20b mm/kasan/report.c:256
 kasan_report_error mm/kasan/report.c:354 [inline]
 kasan_report.cold.7+0x242/0x30d mm/kasan/report.c:412
 check_memory_region_inline mm/kasan/kasan.c:260 [inline]
 check_memory_region+0x13e/0x1b0 mm/kasan/kasan.c:267
 kasan_check_read+0x11/0x20 mm/kasan/kasan.c:272
 atomic_read include/asm-generic/atomic-instrumented.h:21 [inline]
 atomic_fetch_add_unless include/linux/atomic.h:575 [inline]
 atomic_add_unless include/linux/atomic.h:597 [inline]
 dst_hold_safe include/net/dst.h:308 [inline]
 ip6_hold_safe+0xe6/0x670 net/ipv6/route.c:1029
 rt6_get_pcpu_route net/ipv6/route.c:1249 [inline]
 ip6_pol_route+0x354/0xd20 net/ipv6/route.c:1922
 ip6_pol_route_output+0x54/0x70 net/ipv6/route.c:2098
 fib6_rule_lookup+0x283/0x890 net/ipv6/fib6_rules.c:122
 ip6_route_output_flags+0x2c5/0x350 net/ipv6/route.c:2126
 ip6_dst_lookup_tail+0x1278/0x1da0 net/ipv6/ip6_output.c:978
 ip6_dst_lookup_flow+0xc8/0x270 net/ipv6/ip6_output.c:1079
 ip6_sk_dst_lookup_flow+0x5ed/0xc50 net/ipv6/ip6_output.c:1117
 udpv6_sendmsg+0x2163/0x36b0 net/ipv6/udp.c:1354
 inet_sendmsg+0x1a1/0x690 net/ipv4/af_inet.c:798
 sock_sendmsg_nosec net/socket.c:622 [inline]
 sock_sendmsg+0xd5/0x120 net/socket.c:632
 ___sys_sendmsg+0x51d/0x930 net/socket.c:2115
 __sys_sendmmsg+0x240/0x6f0 net/socket.c:2210
 __do_sys_sendmmsg net/socket.c:2239 [inline]
 __se_sys_sendmmsg net/socket.c:2236 [inline]
 __x64_sys_sendmmsg+0x9d/0x100 net/socket.c:2236
 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x446a29
Code: e8 ac b8 02 00 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 eb 08 fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f4de5532db8 EFLAGS: 00000246 ORIG_RAX: 0000000000000133
RAX: ffffffffffffffda RBX: 00000000006dcc38 RCX: 0000000000446a29
RDX: 00000000000000b8 RSI: 0000000020001b00 RDI: 0000000000000003
RBP: 00000000006dcc30 R08: 00007f4de5533700 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00000000006dcc3c
R13: 00007ffe2b830fdf R14: 00007f4de55339c0 R15: 0000000000000001

Fixes: 71b1391a4128 ("l2tp: ensure sk->dst is still valid")
Reported-by: syzbot+05f840f3b04f211bad55@syzkaller.appspotmail.com
Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Cc: Guillaume Nault <g.nault@alphalink.fr>
Cc: David Ahern <dsahern@gmail.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 40261cb68e83..8aaf8157da2b 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1110,7 +1110,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len
 
 	/* Get routing info from the tunnel socket */
 	skb_dst_drop(skb);
-	skb_dst_set(skb, dst_clone(__sk_dst_check(sk, 0)));
+	skb_dst_set(skb, sk_dst_check(sk, 0));
 
 	inet = inet_sk(sk);
 	fl = &inet->cork.fl;
-- 
2.17.1


From 3fe24f570ab709bc0f0c92c7e813632a0a2961c7 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Tue, 7 Aug 2018 12:41:38 -0700
Subject: [PATCH 03/17] llc: use refcount_inc_not_zero() for llc_sap_find()

[ Upstream commit 0dcb82254d65f72333aa50ad626d1e9665ad093b ]

llc_sap_put() decreases the refcnt before deleting sap
from the global list. Therefore, there is a chance
llc_sap_find() could find a sap with zero refcnt
in this global list.

Close this race condition by checking if refcnt is zero
or not in llc_sap_find(), if it is zero then it is being
removed so we can just treat it as gone.

Reported-by: <syzbot+278893f3f7803871f7ce@syzkaller.appspotmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/llc.h  | 5 +++++
 net/llc/llc_core.c | 4 ++--
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/include/net/llc.h b/include/net/llc.h
index dc35f25eb679..890a87318014 100644
--- a/include/net/llc.h
+++ b/include/net/llc.h
@@ -116,6 +116,11 @@ static inline void llc_sap_hold(struct llc_sap *sap)
 	refcount_inc(&sap->refcnt);
 }
 
+static inline bool llc_sap_hold_safe(struct llc_sap *sap)
+{
+	return refcount_inc_not_zero(&sap->refcnt);
+}
+
 void llc_sap_close(struct llc_sap *sap);
 
 static inline void llc_sap_put(struct llc_sap *sap)
diff --git a/net/llc/llc_core.c b/net/llc/llc_core.c
index 89041260784c..260b3dc1b4a2 100644
--- a/net/llc/llc_core.c
+++ b/net/llc/llc_core.c
@@ -73,8 +73,8 @@ struct llc_sap *llc_sap_find(unsigned char sap_value)
 
 	rcu_read_lock_bh();
 	sap = __llc_sap_find(sap_value);
-	if (sap)
-		llc_sap_hold(sap);
+	if (!sap || !llc_sap_hold_safe(sap))
+		sap = NULL;
 	rcu_read_unlock_bh();
 	return sap;
 }
-- 
2.17.1


From 8ace1f8724001acc613a9170e082c6f3f7b62218 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Mon, 13 Aug 2018 18:44:03 +0800
Subject: [PATCH 04/17] net_sched: fix NULL pointer dereference when delete
 tcindex filter

[ Upstream commit 2df8bee5654bb2b7312662ca6810d4dc16b0b67f ]

Li Shuang reported the following crash:

[   71.267724] BUG: unable to handle kernel NULL pointer dereference at 0000000000000004
[   71.276456] PGD 800000085d9bd067 P4D 800000085d9bd067 PUD 859a0b067 PMD 0
[   71.284127] Oops: 0000 [#1] SMP PTI
[   71.288015] CPU: 12 PID: 2386 Comm: tc Not tainted 4.18.0-rc8.latest+ #131
[   71.295686] Hardware name: Dell Inc. PowerEdge R730/0WCJNT, BIOS 2.1.5 04/11/2016
[   71.304037] RIP: 0010:tcindex_delete+0x72/0x280 [cls_tcindex]
[   71.310446] Code: 00 31 f6 48 87 75 20 48 85 f6 74 11 48 8b 47 18 48 8b 40 08 48 8b 40 50 e8 fb a6 f8 fc 48 85 db 0f 84 dc 00 00 00 48 8b 73 18 <8b> 56 04 48 8d 7e 04 85 d2 0f 84 7b 01 00
[   71.331517] RSP: 0018:ffffb45207b3f898 EFLAGS: 00010282
[   71.337345] RAX: ffff8ad3d72d6360 RBX: ffff8acc84393680 RCX: 000000000000002e
[   71.345306] RDX: ffff8ad3d72c8570 RSI: 0000000000000000 RDI: ffff8ad847a45800
[   71.353277] RBP: ffff8acc84393688 R08: ffff8ad3d72c8400 R09: 0000000000000000
[   71.361238] R10: ffff8ad3de786e00 R11: 0000000000000000 R12: ffffb45207b3f8c7
[   71.369199] R13: ffff8ad3d93bd2a0 R14: 000000000000002e R15: ffff8ad3d72c9600
[   71.377161] FS:  00007f9d3ec3e740(0000) GS:ffff8ad3df980000(0000) knlGS:0000000000000000
[   71.386188] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   71.392597] CR2: 0000000000000004 CR3: 0000000852f06003 CR4: 00000000001606e0
[   71.400558] Call Trace:
[   71.403299]  tcindex_destroy_element+0x25/0x40 [cls_tcindex]
[   71.409611]  tcindex_walk+0xbb/0x110 [cls_tcindex]
[   71.414953]  tcindex_destroy+0x44/0x90 [cls_tcindex]
[   71.420492]  ? tcindex_delete+0x280/0x280 [cls_tcindex]
[   71.426323]  tcf_proto_destroy+0x16/0x40
[   71.430696]  tcf_chain_flush+0x51/0x70
[   71.434876]  tcf_block_put_ext.part.30+0x8f/0x1b0
[   71.440122]  tcf_block_put+0x4d/0x70
[   71.444108]  cbq_destroy+0x4d/0xd0 [sch_cbq]
[   71.448869]  qdisc_destroy+0x62/0x130
[   71.452951]  dsmark_destroy+0x2a/0x70 [sch_dsmark]
[   71.458300]  qdisc_destroy+0x62/0x130
[   71.462373]  qdisc_graft+0x3ba/0x470
[   71.466359]  tc_get_qdisc+0x2a6/0x2c0
[   71.470443]  ? cred_has_capability+0x7d/0x130
[   71.475307]  rtnetlink_rcv_msg+0x263/0x2d0
[   71.479875]  ? rtnl_calcit.isra.30+0x110/0x110
[   71.484832]  netlink_rcv_skb+0x4d/0x130
[   71.489109]  netlink_unicast+0x1a3/0x250
[   71.493482]  netlink_sendmsg+0x2ae/0x3a0
[   71.497859]  sock_sendmsg+0x36/0x40
[   71.501748]  ___sys_sendmsg+0x26f/0x2d0
[   71.506029]  ? handle_pte_fault+0x586/0xdf0
[   71.510694]  ? __handle_mm_fault+0x389/0x500
[   71.515457]  ? __sys_sendmsg+0x5e/0xa0
[   71.519636]  __sys_sendmsg+0x5e/0xa0
[   71.523626]  do_syscall_64+0x5b/0x180
[   71.527711]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[   71.533345] RIP: 0033:0x7f9d3e257f10
[   71.537331] Code: c3 48 8b 05 82 6f 2c 00 f7 db 64 89 18 48 83 cb ff eb dd 0f 1f 80 00 00 00 00 83 3d 8d d0 2c 00 00 75 10 b8 2e 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8
[   71.558401] RSP: 002b:00007fff6f893398 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
[   71.566848] RAX: ffffffffffffffda RBX: 000000005b71274d RCX: 00007f9d3e257f10
[   71.574810] RDX: 0000000000000000 RSI: 00007fff6f8933e0 RDI: 0000000000000003
[   71.582770] RBP: 00007fff6f8933e0 R08: 000000000000ffff R09: 0000000000000003
[   71.590729] R10: 00007fff6f892e20 R11: 0000000000000246 R12: 0000000000000000
[   71.598689] R13: 0000000000662ee0 R14: 0000000000000000 R15: 0000000000000000
[   71.606651] Modules linked in: sch_cbq cls_tcindex sch_dsmark xt_CHECKSUM iptable_mangle ipt_MASQUERADE iptable_nat nf_nat_ipv4 nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_conntrack nf_coni
[   71.685425]  libahci i2c_algo_bit i2c_core i40e libata dca mdio megaraid_sas dm_mirror dm_region_hash dm_log dm_mod
[   71.697075] CR2: 0000000000000004
[   71.700792] ---[ end trace f604eb1acacd978b ]---

Reproducer:
tc qdisc add dev lo handle 1:0 root dsmark indices 64 set_tc_index
tc filter add dev lo parent 1:0 protocol ip prio 1 tcindex mask 0xfc shift 2
tc qdisc add dev lo parent 1:0 handle 2:0 cbq bandwidth 10Mbit cell 8 avpkt 1000 mpu 64
tc class add dev lo parent 2:0 classid 2:1 cbq bandwidth 10Mbit rate 1500Kbit avpkt 1000 prio 1 bounded isolated allot 1514 weight 1 maxburst 10
tc filter add dev lo parent 2:0 protocol ip prio 1 handle 0x2e tcindex classid 2:1 pass_on
tc qdisc add dev lo parent 2:1 pfifo limit 5
tc qdisc del dev lo root

This is because in tcindex_set_parms, when there is no old_r, we set new
exts to cr.exts. And we didn't set it to filter when r == &new_filter_result.

Then in tcindex_delete() -> tcf_exts_get_net(), we will get NULL pointer
dereference as we didn't init exts.

Fix it by moving tcf_exts_change() after "if (old_r && old_r != r)" check.
Then we don't need "cr" as there is no errout after that.

Fixes: bf63ac73b3e13 ("net_sched: fix an oops in tcindex filter")
Reported-by: Li Shuang <shuali@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_tcindex.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index b49cc990a000..bff3b612aa70 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -468,11 +468,6 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 		tcf_bind_filter(tp, &cr.res, base);
 	}
 
-	if (old_r)
-		tcf_exts_change(&r->exts, &e);
-	else
-		tcf_exts_change(&cr.exts, &e);
-
 	if (old_r && old_r != r) {
 		err = tcindex_filter_result_init(old_r);
 		if (err < 0) {
@@ -483,6 +478,8 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 
 	oldp = p;
 	r->res = cr.res;
+	tcf_exts_change(&r->exts, &e);
+
 	rcu_assign_pointer(tp->root, cp);
 
 	if (r == &new_filter_result) {
-- 
2.17.1


From fb4be8963b7ec8c26b01ff445d7c7f91b07d313c Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 6 Aug 2018 11:06:02 -0700
Subject: [PATCH 05/17] vsock: split dwork to avoid reinitializations

[ Upstream commit 455f05ecd2b219e9a216050796d30c830d9bc393 ]

syzbot reported that we reinitialize an active delayed
work in vsock_stream_connect():

	ODEBUG: init active (active state 0) object type: timer_list hint:
	delayed_work_timer_fn+0x0/0x90 kernel/workqueue.c:1414
	WARNING: CPU: 1 PID: 11518 at lib/debugobjects.c:329
	debug_print_object+0x16a/0x210 lib/debugobjects.c:326

The pattern is apparently wrong, we should only initialize
the dealyed work once and could repeatly schedule it. So we
have to move out the initializations to allocation side.
And to avoid confusion, we can split the shared dwork
into two, instead of re-using the same one.

Fixes: d021c344051a ("VSOCK: Introduce VM Sockets")
Reported-by: <syzbot+8a9b1bd330476a4f3db6@syzkaller.appspotmail.com>
Cc: Andy king <acking@vmware.com>
Cc: Stefan Hajnoczi <stefanha@redhat.com>
Cc: Jorgen Hansen <jhansen@vmware.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/af_vsock.h         |  4 ++--
 net/vmw_vsock/af_vsock.c       | 15 ++++++++-------
 net/vmw_vsock/vmci_transport.c |  3 +--
 3 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index 9324ac2d9ff2..43913ae79f64 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -64,7 +64,8 @@ struct vsock_sock {
 	struct list_head pending_links;
 	struct list_head accept_queue;
 	bool rejected;
-	struct delayed_work dwork;
+	struct delayed_work connect_work;
+	struct delayed_work pending_work;
 	struct delayed_work close_work;
 	bool close_work_scheduled;
 	u32 peer_shutdown;
@@ -77,7 +78,6 @@ struct vsock_sock {
 
 s64 vsock_stream_has_data(struct vsock_sock *vsk);
 s64 vsock_stream_has_space(struct vsock_sock *vsk);
-void vsock_pending_work(struct work_struct *work);
 struct sock *__vsock_create(struct net *net,
 			    struct socket *sock,
 			    struct sock *parent,
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index c1076c19b858..ab27a2872935 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -451,14 +451,14 @@ static int vsock_send_shutdown(struct sock *sk, int mode)
 	return transport->shutdown(vsock_sk(sk), mode);
 }
 
-void vsock_pending_work(struct work_struct *work)
+static void vsock_pending_work(struct work_struct *work)
 {
 	struct sock *sk;
 	struct sock *listener;
 	struct vsock_sock *vsk;
 	bool cleanup;
 
-	vsk = container_of(work, struct vsock_sock, dwork.work);
+	vsk = container_of(work, struct vsock_sock, pending_work.work);
 	sk = sk_vsock(vsk);
 	listener = vsk->listener;
 	cleanup = true;
@@ -498,7 +498,6 @@ void vsock_pending_work(struct work_struct *work)
 	sock_put(sk);
 	sock_put(listener);
 }
-EXPORT_SYMBOL_GPL(vsock_pending_work);
 
 /**** SOCKET OPERATIONS ****/
 
@@ -597,6 +596,8 @@ static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr)
 	return retval;
 }
 
+static void vsock_connect_timeout(struct work_struct *work);
+
 struct sock *__vsock_create(struct net *net,
 			    struct socket *sock,
 			    struct sock *parent,
@@ -638,6 +639,8 @@ struct sock *__vsock_create(struct net *net,
 	vsk->sent_request = false;
 	vsk->ignore_connecting_rst = false;
 	vsk->peer_shutdown = 0;
+	INIT_DELAYED_WORK(&vsk->connect_work, vsock_connect_timeout);
+	INIT_DELAYED_WORK(&vsk->pending_work, vsock_pending_work);
 
 	psk = parent ? vsock_sk(parent) : NULL;
 	if (parent) {
@@ -1117,7 +1120,7 @@ static void vsock_connect_timeout(struct work_struct *work)
 	struct vsock_sock *vsk;
 	int cancel = 0;
 
-	vsk = container_of(work, struct vsock_sock, dwork.work);
+	vsk = container_of(work, struct vsock_sock, connect_work.work);
 	sk = sk_vsock(vsk);
 
 	lock_sock(sk);
@@ -1221,9 +1224,7 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr,
 			 * timeout fires.
 			 */
 			sock_hold(sk);
-			INIT_DELAYED_WORK(&vsk->dwork,
-					  vsock_connect_timeout);
-			schedule_delayed_work(&vsk->dwork, timeout);
+			schedule_delayed_work(&vsk->connect_work, timeout);
 
 			/* Skip ahead to preserve error code set above. */
 			goto out_wait;
diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index a7a73ffe675b..cb332adb84cd 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -1094,8 +1094,7 @@ static int vmci_transport_recv_listen(struct sock *sk,
 	vpending->listener = sk;
 	sock_hold(sk);
 	sock_hold(pending);
-	INIT_DELAYED_WORK(&vpending->dwork, vsock_pending_work);
-	schedule_delayed_work(&vpending->dwork, HZ);
+	schedule_delayed_work(&vpending->pending_work, HZ);
 
 out:
 	return err;
-- 
2.17.1


From acebc15ddb37d12edd77bb00ee63cb805f7098df Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Thu, 9 Aug 2018 16:42:16 +0200
Subject: [PATCH 06/17] xen/netfront: don't cache skb_shinfo()

[ Upstream commit d472b3a6cf63cd31cae1ed61930f07e6cd6671b5 ]

skb_shinfo() can change when calling __pskb_pull_tail(): Don't cache
its return value.

Cc: stable@vger.kernel.org
Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Wei Liu <wei.liu2@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netfront.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 42e93cb4eca7..ea2da91a96ea 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -894,7 +894,6 @@ static RING_IDX xennet_fill_frags(struct netfront_queue *queue,
 				  struct sk_buff *skb,
 				  struct sk_buff_head *list)
 {
-	struct skb_shared_info *shinfo = skb_shinfo(skb);
 	RING_IDX cons = queue->rx.rsp_cons;
 	struct sk_buff *nskb;
 
@@ -903,15 +902,16 @@ static RING_IDX xennet_fill_frags(struct netfront_queue *queue,
 			RING_GET_RESPONSE(&queue->rx, ++cons);
 		skb_frag_t *nfrag = &skb_shinfo(nskb)->frags[0];
 
-		if (shinfo->nr_frags == MAX_SKB_FRAGS) {
+		if (skb_shinfo(skb)->nr_frags == MAX_SKB_FRAGS) {
 			unsigned int pull_to = NETFRONT_SKB_CB(skb)->pull_to;
 
 			BUG_ON(pull_to <= skb_headlen(skb));
 			__pskb_pull_tail(skb, pull_to - skb_headlen(skb));
 		}
-		BUG_ON(shinfo->nr_frags >= MAX_SKB_FRAGS);
+		BUG_ON(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS);
 
-		skb_add_rx_frag(skb, shinfo->nr_frags, skb_frag_page(nfrag),
+		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
+				skb_frag_page(nfrag),
 				rx->offset, rx->status, PAGE_SIZE);
 
 		skb_shinfo(nskb)->nr_frags = 0;
-- 
2.17.1


From e51c8eeafa21b122c8c9501446dc9c7e6875683c Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Mon, 13 Aug 2018 18:44:04 +0800
Subject: [PATCH 07/17] net_sched: Fix missing res info when create new
 tc_index filter

[ Upstream commit 008369dcc5f7bfba526c98054f8525322acf0ea3 ]

Li Shuang reported the following warn:

[  733.484610] WARNING: CPU: 6 PID: 21123 at net/sched/sch_cbq.c:1418 cbq_destroy_class+0x5d/0x70 [sch_cbq]
[  733.495190] Modules linked in: sch_cbq cls_tcindex sch_dsmark rpcsec_gss_krb5 auth_rpcgss nfsv4 dns_resolver nfs lockd grace fscache xt_CHECKSUM iptable_mangle ipt_MASQUERADE iptable_nat l
[  733.574155]  syscopyarea sysfillrect sysimgblt fb_sys_fops ttm drm igb ixgbe ahci libahci i2c_algo_bit libata i40e i2c_core dca mdio megaraid_sas dm_mirror dm_region_hash dm_log dm_mod
[  733.592500] CPU: 6 PID: 21123 Comm: tc Not tainted 4.18.0-rc8.latest+ #131
[  733.600169] Hardware name: Dell Inc. PowerEdge R730/0WCJNT, BIOS 2.1.5 04/11/2016
[  733.608518] RIP: 0010:cbq_destroy_class+0x5d/0x70 [sch_cbq]
[  733.614734] Code: e7 d9 d2 48 8b 7b 48 e8 61 05 da d2 48 8d bb f8 00 00 00 e8 75 ae d5 d2 48 39 eb 74 0a 48 89 df 5b 5d e9 16 6c 94 d2 5b 5d c3 <0f> 0b eb b6 0f 1f 44 00 00 66 2e 0f 1f 84
[  733.635798] RSP: 0018:ffffbfbb066bb9d8 EFLAGS: 00010202
[  733.641627] RAX: 0000000000000001 RBX: ffff9cdd17392800 RCX: 000000008010000f
[  733.649588] RDX: ffff9cdd1df547e0 RSI: ffff9cdd17392800 RDI: ffff9cdd0f84c800
[  733.657547] RBP: ffff9cdd0f84c800 R08: 0000000000000001 R09: 0000000000000000
[  733.665508] R10: ffff9cdd0f84d000 R11: 0000000000000001 R12: 0000000000000001
[  733.673469] R13: 0000000000000000 R14: 0000000000000001 R15: ffff9cdd17392200
[  733.681430] FS:  00007f911890a740(0000) GS:ffff9cdd1f8c0000(0000) knlGS:0000000000000000
[  733.690456] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  733.696864] CR2: 0000000000b5544c CR3: 0000000859374002 CR4: 00000000001606e0
[  733.704826] Call Trace:
[  733.707554]  cbq_destroy+0xa1/0xd0 [sch_cbq]
[  733.712318]  qdisc_destroy+0x62/0x130
[  733.716401]  dsmark_destroy+0x2a/0x70 [sch_dsmark]
[  733.721745]  qdisc_destroy+0x62/0x130
[  733.725829]  qdisc_graft+0x3ba/0x470
[  733.729817]  tc_get_qdisc+0x2a6/0x2c0
[  733.733901]  ? cred_has_capability+0x7d/0x130
[  733.738761]  rtnetlink_rcv_msg+0x263/0x2d0
[  733.743330]  ? rtnl_calcit.isra.30+0x110/0x110
[  733.748287]  netlink_rcv_skb+0x4d/0x130
[  733.752576]  netlink_unicast+0x1a3/0x250
[  733.756949]  netlink_sendmsg+0x2ae/0x3a0
[  733.761324]  sock_sendmsg+0x36/0x40
[  733.765213]  ___sys_sendmsg+0x26f/0x2d0
[  733.769493]  ? handle_pte_fault+0x586/0xdf0
[  733.774158]  ? __handle_mm_fault+0x389/0x500
[  733.778919]  ? __sys_sendmsg+0x5e/0xa0
[  733.783099]  __sys_sendmsg+0x5e/0xa0
[  733.787087]  do_syscall_64+0x5b/0x180
[  733.791171]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[  733.796805] RIP: 0033:0x7f9117f23f10
[  733.800791] Code: c3 48 8b 05 82 6f 2c 00 f7 db 64 89 18 48 83 cb ff eb dd 0f 1f 80 00 00 00 00 83 3d 8d d0 2c 00 00 75 10 b8 2e 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8
[  733.821873] RSP: 002b:00007ffe96818398 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
[  733.830319] RAX: ffffffffffffffda RBX: 000000005b71244c RCX: 00007f9117f23f10
[  733.838280] RDX: 0000000000000000 RSI: 00007ffe968183e0 RDI: 0000000000000003
[  733.846241] RBP: 00007ffe968183e0 R08: 000000000000ffff R09: 0000000000000003
[  733.854202] R10: 00007ffe96817e20 R11: 0000000000000246 R12: 0000000000000000
[  733.862161] R13: 0000000000662ee0 R14: 0000000000000000 R15: 0000000000000000
[  733.870121] ---[ end trace 28edd4aad712ddca ]---

This is because we didn't update f->result.res when create new filter. Then in
tcindex_delete() -> tcf_unbind_filter(), we will failed to find out the res
and unbind filter, which will trigger the WARN_ON() in cbq_destroy_class().

Fix it by updating f->result.res when create new filter.

Fixes: 6e0565697a106 ("net_sched: fix another crash in cls_tcindex")
Reported-by: Li Shuang <shuali@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_tcindex.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index bff3b612aa70..9cb37c63c3e5 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -486,6 +486,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 		struct tcindex_filter *nfp;
 		struct tcindex_filter __rcu **fp;
 
+		f->result.res = r->res;
 		tcf_exts_change(&f->result.exts, &r->exts);
 
 		fp = cp->h + (handle % cp->hash);
-- 
2.17.1


From 2550ef7be066f5b61e098988a0c5aadbf6065c7c Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Wed, 8 Aug 2018 11:43:04 +0800
Subject: [PATCH 08/17] vhost: reset metadata cache when initializing new IOTLB

[ Upstream commit b13f9c6364373a1b9f71e9846dc4fb199296f926 ]

We need to reset metadata cache during new IOTLB initialization,
otherwise the stale pointers to previous IOTLB may be still accessed
which will lead a use after free.

Reported-by: syzbot+c51e6736a1bf614b3272@syzkaller.appspotmail.com
Fixes: f88949138058 ("vhost: introduce O(1) vq metadata cache")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/vhost.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 9beefa6ed1ce..d1de2cb13fd6 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -1556,9 +1556,12 @@ int vhost_init_device_iotlb(struct vhost_dev *d, bool enabled)
 	d->iotlb = niotlb;
 
 	for (i = 0; i < d->nvqs; ++i) {
-		mutex_lock(&d->vqs[i]->mutex);
-		d->vqs[i]->iotlb = niotlb;
-		mutex_unlock(&d->vqs[i]->mutex);
+		struct vhost_virtqueue *vq = d->vqs[i];
+
+		mutex_lock(&vq->mutex);
+		vq->iotlb = niotlb;
+		__vhost_vq_meta_reset(vq);
+		mutex_unlock(&vq->mutex);
 	}
 
 	vhost_umem_clean(oiotlb);
-- 
2.17.1


From ec5fcc2474f0dacfcfe786e3cfba97858a59bc87 Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Fri, 3 Aug 2018 15:57:41 +0300
Subject: [PATCH 09/17] mlxsw: core_acl_flex_actions: Return error for
 conflicting actions

[ Upstream commit 3757b255bf20ae3c941abae7624ff215bfd9ef05 ]

Spectrum switch ACL action set is built in groups of three actions
which may point to additional actions. A group holds a single record
which can be set as goto record for pointing at a following group
or can be set to mark the termination of the lookup. This is perfectly
adequate for handling a series of actions to be executed on a packet.
While the SW model allows configuration of conflicting actions
where it is clear that some actions will never execute, the mlxsw
driver must block such configurations as it creates a conflict
over the single terminate/goto record value.

For a conflicting actions configuration such as:

 # tc filter add dev swp49 parent ffff: \
   protocol ip pref 10 \
   flower skip_sw dst_ip 192.168.101.1 \
   action goto chain 100 \
   action mirred egress mirror dev swp4

Where it is clear that the last action will never execute, the
mlxsw driver was issuing a warning instead of returning an error.
Therefore replace that warning with an error for this specific
case.

Fixes: 4cda7d8d7098 ("mlxsw: core: Introduce flexible actions support")
Signed-off-by: Nir Dotan <nird@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../mellanox/mlxsw/core_acl_flex_actions.c    | 42 +++++++++----------
 1 file changed, 21 insertions(+), 21 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
index 3c0d882ba183..ce280680258e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
@@ -626,8 +626,8 @@ static char *mlxsw_afa_block_append_action(struct mlxsw_afa_block *block,
 	char *oneact;
 	char *actions;
 
-	if (WARN_ON(block->finished))
-		return NULL;
+	if (block->finished)
+		return ERR_PTR(-EINVAL);
 	if (block->cur_act_index + action_size >
 	    block->afa->max_acts_per_set) {
 		struct mlxsw_afa_set *set;
@@ -637,7 +637,7 @@ static char *mlxsw_afa_block_append_action(struct mlxsw_afa_block *block,
 		 */
 		set = mlxsw_afa_set_create(false);
 		if (!set)
-			return NULL;
+			return ERR_PTR(-ENOBUFS);
 		set->prev = block->cur_set;
 		block->cur_act_index = 0;
 		block->cur_set->next = set;
@@ -724,8 +724,8 @@ int mlxsw_afa_block_append_vlan_modify(struct mlxsw_afa_block *block,
 						  MLXSW_AFA_VLAN_CODE,
 						  MLXSW_AFA_VLAN_SIZE);
 
-	if (!act)
-		return -ENOBUFS;
+	if (IS_ERR(act))
+		return PTR_ERR(act);
 	mlxsw_afa_vlan_pack(act, MLXSW_AFA_VLAN_VLAN_TAG_CMD_NOP,
 			    MLXSW_AFA_VLAN_CMD_SET_OUTER, vid,
 			    MLXSW_AFA_VLAN_CMD_SET_OUTER, pcp,
@@ -806,8 +806,8 @@ int mlxsw_afa_block_append_drop(struct mlxsw_afa_block *block)
 						  MLXSW_AFA_TRAPDISC_CODE,
 						  MLXSW_AFA_TRAPDISC_SIZE);
 
-	if (!act)
-		return -ENOBUFS;
+	if (IS_ERR(act))
+		return PTR_ERR(act);
 	mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_NOP,
 				MLXSW_AFA_TRAPDISC_FORWARD_ACTION_DISCARD, 0);
 	return 0;
@@ -820,8 +820,8 @@ int mlxsw_afa_block_append_trap(struct mlxsw_afa_block *block, u16 trap_id)
 						  MLXSW_AFA_TRAPDISC_CODE,
 						  MLXSW_AFA_TRAPDISC_SIZE);
 
-	if (!act)
-		return -ENOBUFS;
+	if (IS_ERR(act))
+		return PTR_ERR(act);
 	mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_TRAP,
 				MLXSW_AFA_TRAPDISC_FORWARD_ACTION_DISCARD,
 				trap_id);
@@ -836,8 +836,8 @@ int mlxsw_afa_block_append_trap_and_forward(struct mlxsw_afa_block *block,
 						  MLXSW_AFA_TRAPDISC_CODE,
 						  MLXSW_AFA_TRAPDISC_SIZE);
 
-	if (!act)
-		return -ENOBUFS;
+	if (IS_ERR(act))
+		return PTR_ERR(act);
 	mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_TRAP,
 				MLXSW_AFA_TRAPDISC_FORWARD_ACTION_FORWARD,
 				trap_id);
@@ -908,8 +908,8 @@ mlxsw_afa_block_append_allocated_mirror(struct mlxsw_afa_block *block,
 	char *act = mlxsw_afa_block_append_action(block,
 						  MLXSW_AFA_TRAPDISC_CODE,
 						  MLXSW_AFA_TRAPDISC_SIZE);
-	if (!act)
-		return -ENOBUFS;
+	if (IS_ERR(act))
+		return PTR_ERR(act);
 	mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_NOP,
 				MLXSW_AFA_TRAPDISC_FORWARD_ACTION_FORWARD, 0);
 	mlxsw_afa_trapdisc_mirror_pack(act, true, mirror_agent);
@@ -996,8 +996,8 @@ int mlxsw_afa_block_append_fwd(struct mlxsw_afa_block *block,
 
 	act = mlxsw_afa_block_append_action(block, MLXSW_AFA_FORWARD_CODE,
 					    MLXSW_AFA_FORWARD_SIZE);
-	if (!act) {
-		err = -ENOBUFS;
+	if (IS_ERR(act)) {
+		err = PTR_ERR(act);
 		goto err_append_action;
 	}
 	mlxsw_afa_forward_pack(act, MLXSW_AFA_FORWARD_TYPE_PBS,
@@ -1052,8 +1052,8 @@ int mlxsw_afa_block_append_allocated_counter(struct mlxsw_afa_block *block,
 {
 	char *act = mlxsw_afa_block_append_action(block, MLXSW_AFA_POLCNT_CODE,
 						  MLXSW_AFA_POLCNT_SIZE);
-	if (!act)
-		return -ENOBUFS;
+	if (IS_ERR(act))
+		return PTR_ERR(act);
 	mlxsw_afa_polcnt_pack(act, MLXSW_AFA_POLCNT_COUNTER_SET_TYPE_PACKETS_BYTES,
 			      counter_index);
 	return 0;
@@ -1123,8 +1123,8 @@ int mlxsw_afa_block_append_fid_set(struct mlxsw_afa_block *block, u16 fid)
 	char *act = mlxsw_afa_block_append_action(block,
 						  MLXSW_AFA_VIRFWD_CODE,
 						  MLXSW_AFA_VIRFWD_SIZE);
-	if (!act)
-		return -ENOBUFS;
+	if (IS_ERR(act))
+		return PTR_ERR(act);
 	mlxsw_afa_virfwd_pack(act, MLXSW_AFA_VIRFWD_FID_CMD_SET, fid);
 	return 0;
 }
@@ -1193,8 +1193,8 @@ int mlxsw_afa_block_append_mcrouter(struct mlxsw_afa_block *block,
 	char *act = mlxsw_afa_block_append_action(block,
 						  MLXSW_AFA_MCROUTER_CODE,
 						  MLXSW_AFA_MCROUTER_SIZE);
-	if (!act)
-		return -ENOBUFS;
+	if (IS_ERR(act))
+		return PTR_ERR(act);
 	mlxsw_afa_mcrouter_pack(act, MLXSW_AFA_MCROUTER_RPF_ACTION_TRAP,
 				expected_irif, min_mtu, rmid_valid, kvdl_index);
 	return 0;
-- 
2.17.1


From a7957fb3769b222a629bbbef11e7174580025590 Mon Sep 17 00:00:00 2001
From: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Date: Wed, 8 Aug 2018 14:06:32 +0300
Subject: [PATCH 10/17] net: aquantia: Fix IFF_ALLMULTI flag functionality

[ Upstream commit 11ba961c916127651e12af6cad3891f8aeb25aa9 ]

It was noticed that NIC always pass all multicast traffic to the host
regardless of IFF_ALLMULTI flag on the interface.
The rule in MC Filter Table in NIC, that is configured to accept any
multicast packets, is turning on if IFF_MULTICAST flag is set on the
interface. It leads to passing all multicast traffic to the host.
This fix changes the condition to turn on that rule by checking
IFF_ALLMULTI flag as it should.

Fixes: b21f502f84be ("net:ethernet:aquantia: Fix for multicast filter handling.")
Signed-off-by: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index 956860a69797..3bdab972420b 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -762,7 +762,7 @@ static int hw_atl_b0_hw_packet_filter_set(struct aq_hw_s *self,
 
 	hw_atl_rpfl2promiscuous_mode_en_set(self, IS_FILTER_ENABLED(IFF_PROMISC));
 	hw_atl_rpfl2multicast_flr_en_set(self,
-					 IS_FILTER_ENABLED(IFF_MULTICAST), 0);
+					 IS_FILTER_ENABLED(IFF_ALLMULTI), 0);
 
 	hw_atl_rpfl2_accept_all_mc_packets_set(self,
 					       IS_FILTER_ENABLED(IFF_ALLMULTI));
-- 
2.17.1


From 6cc20e0a73623bb346bfe79f49ad3e926edc97c1 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 5 Aug 2018 22:46:07 +0800
Subject: [PATCH 11/17] ip6_tunnel: use the right value for ipv4 min mtu check
 in ip6_tnl_xmit

[ Upstream commit 82a40777de12728dedf4075453b694f0d1baee80 ]

According to RFC791, 68 bytes is the minimum size of IPv4 datagram every
device must be able to forward without further fragmentation while 576
bytes is the minimum size of IPv4 datagram every device has to be able
to receive, so in ip6_tnl_xmit(), 68(IPV4_MIN_MTU) should be the right
value for the ipv4 min mtu check in ip6_tnl_xmit.

While at it, change to use max() instead of if statement.

Fixes: c9fefa08190f ("ip6_tunnel: get the min mtu properly in ip6_tnl_xmit")
Reported-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 00e138a44cbb..1cc9650af9fb 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1133,12 +1133,8 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 		max_headroom += 8;
 		mtu -= 8;
 	}
-	if (skb->protocol == htons(ETH_P_IPV6)) {
-		if (mtu < IPV6_MIN_MTU)
-			mtu = IPV6_MIN_MTU;
-	} else if (mtu < 576) {
-		mtu = 576;
-	}
+	mtu = max(mtu, skb->protocol == htons(ETH_P_IPV6) ?
+		       IPV6_MIN_MTU : IPV4_MIN_MTU);
 
 	skb_dst_update_pmtu(skb, mtu);
 	if (skb->len - t->tun_hlen - eth_hlen > mtu && !skb_is_gso(skb)) {
-- 
2.17.1


From c9bee880a343cee59b8b7eed8aa902a722f80882 Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Fri, 3 Aug 2018 15:57:42 +0300
Subject: [PATCH 12/17] mlxsw: core_acl_flex_actions: Remove redundant resource
 destruction

[ Upstream commit dda0a3a3fb92451d4a922e56365ee1f73c8a9586 ]

Some ACL actions require the allocation of a separate resource
prior to applying the action itself. When facing an error condition
during the setup phase of the action, resource should be destroyed.
For such actions the destruction was done twice which is dangerous
and lead to a potential crash.
The destruction took place first upon error on action setup phase
and then as the rule was destroyed.

The following sequence generated a crash:

 # tc qdisc add dev swp49 ingress
 # tc filter add dev swp49 parent ffff: \
   protocol ip chain 100 pref 10 \
   flower skip_sw dst_ip 192.168.101.1 action drop
 # tc filter add dev swp49 parent ffff: \
   protocol ip pref 10 \
   flower skip_sw dst_ip 192.168.101.1 action goto chain 100 \
   action mirred egress mirror dev swp4

Therefore add mlxsw_afa_resource_del() as a complement of
mlxsw_afa_resource_add() to add symmetry to resource_list membership
handling. Call this from mlxsw_afa_fwd_entry_ref_destroy() to make the
_fwd_entry_ref_create() and _fwd_entry_ref_destroy() pair of calls a
NOP.

Fixes: 140ce421217e ("mlxsw: core: Convert fwd_entry_ref list to be generic per-block resource list")
Signed-off-by: Nir Dotan <nird@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c    | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
index ce280680258e..d664cc0289c2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
@@ -327,12 +327,16 @@ static void mlxsw_afa_resource_add(struct mlxsw_afa_block *block,
 	list_add(&resource->list, &block->resource_list);
 }
 
+static void mlxsw_afa_resource_del(struct mlxsw_afa_resource *resource)
+{
+	list_del(&resource->list);
+}
+
 static void mlxsw_afa_resources_destroy(struct mlxsw_afa_block *block)
 {
 	struct mlxsw_afa_resource *resource, *tmp;
 
 	list_for_each_entry_safe(resource, tmp, &block->resource_list, list) {
-		list_del(&resource->list);
 		resource->destructor(block, resource);
 	}
 }
@@ -530,6 +534,7 @@ static void
 mlxsw_afa_fwd_entry_ref_destroy(struct mlxsw_afa_block *block,
 				struct mlxsw_afa_fwd_entry_ref *fwd_entry_ref)
 {
+	mlxsw_afa_resource_del(&fwd_entry_ref->resource);
 	mlxsw_afa_fwd_entry_put(block->afa, fwd_entry_ref->fwd_entry);
 	kfree(fwd_entry_ref);
 }
-- 
2.17.1


From ddb886388ee7a9b153d0a83b239cd8a1959acf7c Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Fri, 3 Aug 2018 15:57:43 +0300
Subject: [PATCH 13/17] mlxsw: core_acl_flex_actions: Remove redundant counter
 destruction

[ Upstream commit 7cc6169493990dec488eda0a3f6612729ca25e81 ]

Each tc flower rule uses a hidden count action. As counter resource may
not be available due to limited HW resources, update _counter_create()
and _counter_destroy() pair to follow previously introduced symmetric
error condition handling, add a call to mlxsw_afa_resource_del() as part
of the counter resource destruction.

Fixes: c18c1e186ba8 ("mlxsw: core: Make counter index allocated inside the action append")
Signed-off-by: Nir Dotan <nird@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
index d664cc0289c2..a54f23f00a5f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
@@ -584,6 +584,7 @@ static void
 mlxsw_afa_counter_destroy(struct mlxsw_afa_block *block,
 			  struct mlxsw_afa_counter *counter)
 {
+	mlxsw_afa_resource_del(&counter->resource);
 	block->afa->ops->counter_index_put(block->afa->ops_priv,
 					   counter->counter_index);
 	kfree(counter);
-- 
2.17.1


From 209d92bcdd98e603577fceaa580b25f7fe70b8d0 Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Fri, 3 Aug 2018 15:57:44 +0300
Subject: [PATCH 14/17] mlxsw: core_acl_flex_actions: Remove redundant mirror
 resource destruction

[ Upstream commit caebd1b389708bf3d0465be829480fc706a68720 ]

In previous patch mlxsw_afa_resource_del() was added to avoid a duplicate
resource detruction scenario.
For mirror actions, such duplicate destruction leads to a crash as in:

 # tc qdisc add dev swp49 ingress
 # tc filter add dev swp49 parent ffff: \
   protocol ip chain 100 pref 10 \
   flower skip_sw dst_ip 192.168.101.1 action drop
 # tc filter add dev swp49 parent ffff: \
   protocol ip pref 10 \
   flower skip_sw dst_ip 192.168.101.1 action goto chain 100 \
   action mirred egress mirror dev swp4

Therefore add a call to mlxsw_afa_resource_del() in
mlxsw_afa_mirror_destroy() in order to clear that resource
from rule's resources.

Fixes: d0d13c1858a1 ("mlxsw: spectrum_acl: Add support for mirror action")
Signed-off-by: Nir Dotan <nird@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
index a54f23f00a5f..f6f6a568d66a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
@@ -862,6 +862,7 @@ static void
 mlxsw_afa_mirror_destroy(struct mlxsw_afa_block *block,
 			 struct mlxsw_afa_mirror *mirror)
 {
+	mlxsw_afa_resource_del(&mirror->resource);
 	block->afa->ops->mirror_del(block->afa->ops_priv,
 				    mirror->local_in_port,
 				    mirror->span_id,
-- 
2.17.1


From 523bc98656fc65b41b82500de3f1cbc550a61072 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Wed, 8 Aug 2018 15:48:07 -0700
Subject: [PATCH 15/17] net/mlx5e: Properly check if hairpin is possible
 between two functions

[ Upstream commit 816f670623692b5da2787f278cbfdb331ed29b8a ]

The current check relies on function BDF addresses and can get
us wrong e.g when two VFs are assigned into a VM and the PCI
v-address is set by the hypervisor.

Fixes: 5c65c564c962 ('net/mlx5e: Support offloading TC NIC hairpin flows')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reported-by: Alaa Hleihel <alaa@mellanox.com>
Tested-by: Alaa Hleihel <alaa@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index a0ba6cfc9092..290fc6f9afc1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1907,15 +1907,15 @@ static bool actions_match_supported(struct mlx5e_priv *priv,
 static bool same_hw_devs(struct mlx5e_priv *priv, struct mlx5e_priv *peer_priv)
 {
 	struct mlx5_core_dev *fmdev, *pmdev;
-	u16 func_id, peer_id;
+	u64 fsystem_guid, psystem_guid;
 
 	fmdev = priv->mdev;
 	pmdev = peer_priv->mdev;
 
-	func_id = (u16)((fmdev->pdev->bus->number << 8) | PCI_SLOT(fmdev->pdev->devfn));
-	peer_id = (u16)((pmdev->pdev->bus->number << 8) | PCI_SLOT(pmdev->pdev->devfn));
+	mlx5_query_nic_vport_system_image_guid(fmdev, &fsystem_guid);
+	mlx5_query_nic_vport_system_image_guid(pmdev, &psystem_guid);
 
-	return (func_id == peer_id);
+	return (fsystem_guid == psystem_guid);
 }
 
 static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
-- 
2.17.1


From 65a051f033a1ed76da2dd752bb1fe2d298249a6f Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 12 Aug 2018 13:26:26 +0200
Subject: [PATCH 16/17] r8169: don't use MSI-X on RTL8168g

[ Upstream commit 7c53a722459c1d6ffb0f5b2058c06ca8980b8600 ]

There have been two reports that network doesn't come back on resume
from suspend when using MSI-X. Both cases affect the same chip version
(RTL8168g - version 40), on different systems. Falling back to MSI
fixes the issue.
Even though we don't really have a proof yet that the network chip
version is to blame, let's disable MSI-X for this version.

Reported-by: Steve Dodd <steved424@gmail.com>
Reported-by: Lou Reed <gogen@disroot.org>
Tested-by: Steve Dodd <steved424@gmail.com>
Tested-by: Lou Reed <gogen@disroot.org>
Fixes: 6c6aa15fdea5 ("r8169: improve interrupt handling")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 764b25fa470c..d19065857afe 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -8066,6 +8066,11 @@ static int rtl_alloc_irq(struct rtl8169_private *tp)
 		RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~MSIEnable);
 		RTL_W8(tp, Cfg9346, Cfg9346_Lock);
 		flags = PCI_IRQ_LEGACY;
+	} else if (tp->mac_version == RTL_GIGA_MAC_VER_40) {
+		/* This version was reported to have issues with resume
+		 * from suspend when using MSI-X
+		 */
+		flags = PCI_IRQ_LEGACY | PCI_IRQ_MSI;
 	} else {
 		flags = PCI_IRQ_ALL_TYPES;
 	}
-- 
2.17.1


From cf5701147e9336b067943fe3fd87211d6ec4c7b1 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 8 Aug 2018 11:30:02 +0100
Subject: [PATCH 17/17] rxrpc: Fix the keepalive generator [ver #2]

[ Upstream commit 330bdcfadceea5e9a1526d731711e163f9a90975 ]

AF_RXRPC has a keepalive message generator that generates a message for a
peer ~20s after the last transmission to that peer to keep firewall ports
open.  The implementation is incorrect in the following ways:

 (1) It mixes up ktime_t and time64_t types.

 (2) It uses ktime_get_real(), the output of which may jump forward or
     backward due to adjustments to the time of day.

 (3) If the current time jumps forward too much or jumps backwards, the
     generator function will crank the base of the time ring round one slot
     at a time (ie. a 1s period) until it catches up, spewing out VERSION
     packets as it goes.

Fix the problem by:

 (1) Only using time64_t.  There's no need for sub-second resolution.

 (2) Use ktime_get_seconds() rather than ktime_get_real() so that time
     isn't perceived to go backwards.

 (3) Simplifying rxrpc_peer_keepalive_worker() by splitting it into two
     parts:

     (a) The "worker" function that manages the buckets and the timer.

     (b) The "dispatch" function that takes the pending peers and
     	 potentially transmits a keepalive packet before putting them back
     	 in the ring into the slot appropriate to the revised last-Tx time.

 (4) Taking everything that's pending out of the ring and splicing it into
     a temporary collector list for processing.

     In the case that there's been a significant jump forward, the ring
     gets entirely emptied and then the time base can be warped forward
     before the peers are processed.

     The warping can't happen if the ring isn't empty because the slot a
     peer is in is keepalive-time dependent, relative to the base time.

 (5) Limit the number of iterations of the bucket array when scanning it.

 (6) Set the timer to skip any empty slots as there's no point waking up if
     there's nothing to do yet.

This can be triggered by an incoming call from a server after a reboot with
AF_RXRPC and AFS built into the kernel causing a peer record to be set up
before userspace is started.  The system clock is then adjusted by
userspace, thereby potentially causing the keepalive generator to have a
meltdown - which leads to a message like:

	watchdog: BUG: soft lockup - CPU#0 stuck for 23s! [kworker/0:1:23]
	...
	Workqueue: krxrpcd rxrpc_peer_keepalive_worker
	EIP: lock_acquire+0x69/0x80
	...
	Call Trace:
	 ? rxrpc_peer_keepalive_worker+0x5e/0x350
	 ? _raw_spin_lock_bh+0x29/0x60
	 ? rxrpc_peer_keepalive_worker+0x5e/0x350
	 ? rxrpc_peer_keepalive_worker+0x5e/0x350
	 ? __lock_acquire+0x3d3/0x870
	 ? process_one_work+0x110/0x340
	 ? process_one_work+0x166/0x340
	 ? process_one_work+0x110/0x340
	 ? worker_thread+0x39/0x3c0
	 ? kthread+0xdb/0x110
	 ? cancel_delayed_work+0x90/0x90
	 ? kthread_stop+0x70/0x70
	 ? ret_from_fork+0x19/0x24

Fixes: ace45bec6d77 ("rxrpc: Fix firewall route keepalive")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/ar-internal.h |   8 +--
 net/rxrpc/conn_event.c  |   4 +-
 net/rxrpc/net_ns.c      |   6 +-
 net/rxrpc/output.c      |  12 ++--
 net/rxrpc/peer_event.c  | 156 ++++++++++++++++++++++------------------
 net/rxrpc/peer_object.c |   8 +--
 net/rxrpc/rxkad.c       |   4 +-
 7 files changed, 109 insertions(+), 89 deletions(-)

diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 19975d2ca9a2..5da2d3379a57 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -104,9 +104,9 @@ struct rxrpc_net {
 
 #define RXRPC_KEEPALIVE_TIME 20 /* NAT keepalive time in seconds */
 	u8			peer_keepalive_cursor;
-	ktime_t			peer_keepalive_base;
-	struct hlist_head	peer_keepalive[RXRPC_KEEPALIVE_TIME + 1];
-	struct hlist_head	peer_keepalive_new;
+	time64_t		peer_keepalive_base;
+	struct list_head	peer_keepalive[32];
+	struct list_head	peer_keepalive_new;
 	struct timer_list	peer_keepalive_timer;
 	struct work_struct	peer_keepalive_work;
 };
@@ -295,7 +295,7 @@ struct rxrpc_peer {
 	struct hlist_head	error_targets;	/* targets for net error distribution */
 	struct work_struct	error_distributor;
 	struct rb_root		service_conns;	/* Service connections */
-	struct hlist_node	keepalive_link;	/* Link in net->peer_keepalive[] */
+	struct list_head	keepalive_link;	/* Link in net->peer_keepalive[] */
 	time64_t		last_tx_at;	/* Last time packet sent here */
 	seqlock_t		service_conn_lock;
 	spinlock_t		lock;		/* access lock */
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index 8229a52c2acd..3fde001fcc39 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -136,7 +136,7 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
 	}
 
 	ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, ioc, len);
-	conn->params.peer->last_tx_at = ktime_get_real();
+	conn->params.peer->last_tx_at = ktime_get_seconds();
 	if (ret < 0)
 		trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
 				    rxrpc_tx_fail_call_final_resend);
@@ -245,7 +245,7 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn,
 		return -EAGAIN;
 	}
 
-	conn->params.peer->last_tx_at = ktime_get_real();
+	conn->params.peer->last_tx_at = ktime_get_seconds();
 
 	_leave(" = 0");
 	return 0;
diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c
index c7a023fb22d0..48fb8754c387 100644
--- a/net/rxrpc/net_ns.c
+++ b/net/rxrpc/net_ns.c
@@ -85,12 +85,12 @@ static __net_init int rxrpc_init_net(struct net *net)
 	hash_init(rxnet->peer_hash);
 	spin_lock_init(&rxnet->peer_hash_lock);
 	for (i = 0; i < ARRAY_SIZE(rxnet->peer_keepalive); i++)
-		INIT_HLIST_HEAD(&rxnet->peer_keepalive[i]);
-	INIT_HLIST_HEAD(&rxnet->peer_keepalive_new);
+		INIT_LIST_HEAD(&rxnet->peer_keepalive[i]);
+	INIT_LIST_HEAD(&rxnet->peer_keepalive_new);
 	timer_setup(&rxnet->peer_keepalive_timer,
 		    rxrpc_peer_keepalive_timeout, 0);
 	INIT_WORK(&rxnet->peer_keepalive_work, rxrpc_peer_keepalive_worker);
-	rxnet->peer_keepalive_base = ktime_add(ktime_get_real(), NSEC_PER_SEC);
+	rxnet->peer_keepalive_base = ktime_get_seconds();
 
 	ret = -ENOMEM;
 	rxnet->proc_net = proc_net_mkdir(net, "rxrpc", net->proc_net);
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index f03de1c59ba3..4774c8f5634d 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -209,7 +209,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
 	now = ktime_get_real();
 	if (ping)
 		call->ping_time = now;
-	conn->params.peer->last_tx_at = ktime_get_real();
+	conn->params.peer->last_tx_at = ktime_get_seconds();
 	if (ret < 0)
 		trace_rxrpc_tx_fail(call->debug_id, serial, ret,
 				    rxrpc_tx_fail_call_ack);
@@ -296,7 +296,7 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call)
 
 	ret = kernel_sendmsg(conn->params.local->socket,
 			     &msg, iov, 1, sizeof(pkt));
-	conn->params.peer->last_tx_at = ktime_get_real();
+	conn->params.peer->last_tx_at = ktime_get_seconds();
 	if (ret < 0)
 		trace_rxrpc_tx_fail(call->debug_id, serial, ret,
 				    rxrpc_tx_fail_call_abort);
@@ -391,7 +391,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
 	 *     message and update the peer record
 	 */
 	ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len);
-	conn->params.peer->last_tx_at = ktime_get_real();
+	conn->params.peer->last_tx_at = ktime_get_seconds();
 
 	up_read(&conn->params.local->defrag_sem);
 	if (ret < 0)
@@ -457,7 +457,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
 		if (ret == 0) {
 			ret = kernel_sendmsg(conn->params.local->socket, &msg,
 					     iov, 2, len);
-			conn->params.peer->last_tx_at = ktime_get_real();
+			conn->params.peer->last_tx_at = ktime_get_seconds();
 
 			opt = IP_PMTUDISC_DO;
 			kernel_setsockopt(conn->params.local->socket, SOL_IP,
@@ -475,7 +475,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
 		if (ret == 0) {
 			ret = kernel_sendmsg(conn->params.local->socket, &msg,
 					     iov, 2, len);
-			conn->params.peer->last_tx_at = ktime_get_real();
+			conn->params.peer->last_tx_at = ktime_get_seconds();
 
 			opt = IPV6_PMTUDISC_DO;
 			kernel_setsockopt(conn->params.local->socket,
@@ -599,6 +599,6 @@ void rxrpc_send_keepalive(struct rxrpc_peer *peer)
 		trace_rxrpc_tx_fail(peer->debug_id, 0, ret,
 				    rxrpc_tx_fail_version_keepalive);
 
-	peer->last_tx_at = ktime_get_real();
+	peer->last_tx_at = ktime_get_seconds();
 	_leave("");
 }
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index 0ed8b651cec2..4f9da2f51c69 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -350,97 +350,117 @@ void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why,
 }
 
 /*
- * Perform keep-alive pings with VERSION packets to keep any NAT alive.
+ * Perform keep-alive pings.
  */
-void rxrpc_peer_keepalive_worker(struct work_struct *work)
+static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet,
+					  struct list_head *collector,
+					  time64_t base,
+					  u8 cursor)
 {
-	struct rxrpc_net *rxnet =
-		container_of(work, struct rxrpc_net, peer_keepalive_work);
 	struct rxrpc_peer *peer;
-	unsigned long delay;
-	ktime_t base, now = ktime_get_real();
-	s64 diff;
-	u8 cursor, slot;
+	const u8 mask = ARRAY_SIZE(rxnet->peer_keepalive) - 1;
+	time64_t keepalive_at;
+	int slot;
 
-	base = rxnet->peer_keepalive_base;
-	cursor = rxnet->peer_keepalive_cursor;
+	spin_lock_bh(&rxnet->peer_hash_lock);
 
-	_enter("%u,%lld", cursor, ktime_sub(now, base));
+	while (!list_empty(collector)) {
+		peer = list_entry(collector->next,
+				  struct rxrpc_peer, keepalive_link);
 
-next_bucket:
-	diff = ktime_to_ns(ktime_sub(now, base));
-	if (diff < 0)
-		goto resched;
+		list_del_init(&peer->keepalive_link);
+		if (!rxrpc_get_peer_maybe(peer))
+			continue;
 
-	_debug("at %u", cursor);
-	spin_lock_bh(&rxnet->peer_hash_lock);
-next_peer:
-	if (!rxnet->live) {
 		spin_unlock_bh(&rxnet->peer_hash_lock);
-		goto out;
-	}
 
-	/* Everything in the bucket at the cursor is processed this second; the
-	 * bucket at cursor + 1 goes now + 1s and so on...
-	 */
-	if (hlist_empty(&rxnet->peer_keepalive[cursor])) {
-		if (hlist_empty(&rxnet->peer_keepalive_new)) {
-			spin_unlock_bh(&rxnet->peer_hash_lock);
-			goto emptied_bucket;
+		keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME;
+		slot = keepalive_at - base;
+		_debug("%02x peer %u t=%d {%pISp}",
+		       cursor, peer->debug_id, slot, &peer->srx.transport);
+
+		if (keepalive_at <= base ||
+		    keepalive_at > base + RXRPC_KEEPALIVE_TIME) {
+			rxrpc_send_keepalive(peer);
+			slot = RXRPC_KEEPALIVE_TIME;
 		}
 
-		hlist_move_list(&rxnet->peer_keepalive_new,
-				&rxnet->peer_keepalive[cursor]);
+		/* A transmission to this peer occurred since last we examined
+		 * it so put it into the appropriate future bucket.
+		 */
+		slot += cursor;
+		slot &= mask;
+		spin_lock_bh(&rxnet->peer_hash_lock);
+		list_add_tail(&peer->keepalive_link,
+			      &rxnet->peer_keepalive[slot & mask]);
+		rxrpc_put_peer(peer);
 	}
 
-	peer = hlist_entry(rxnet->peer_keepalive[cursor].first,
-			   struct rxrpc_peer, keepalive_link);
-	hlist_del_init(&peer->keepalive_link);
-	if (!rxrpc_get_peer_maybe(peer))
-		goto next_peer;
-
 	spin_unlock_bh(&rxnet->peer_hash_lock);
+}
 
-	_debug("peer %u {%pISp}", peer->debug_id, &peer->srx.transport);
+/*
+ * Perform keep-alive pings with VERSION packets to keep any NAT alive.
+ */
+void rxrpc_peer_keepalive_worker(struct work_struct *work)
+{
+	struct rxrpc_net *rxnet =
+		container_of(work, struct rxrpc_net, peer_keepalive_work);
+	const u8 mask = ARRAY_SIZE(rxnet->peer_keepalive) - 1;
+	time64_t base, now, delay;
+	u8 cursor, stop;
+	LIST_HEAD(collector);
 
-recalc:
-	diff = ktime_divns(ktime_sub(peer->last_tx_at, base), NSEC_PER_SEC);
-	if (diff < -30 || diff > 30)
-		goto send; /* LSW of 64-bit time probably wrapped on 32-bit */
-	diff += RXRPC_KEEPALIVE_TIME - 1;
-	if (diff < 0)
-		goto send;
+	now = ktime_get_seconds();
+	base = rxnet->peer_keepalive_base;
+	cursor = rxnet->peer_keepalive_cursor;
+	_enter("%lld,%u", base - now, cursor);
 
-	slot = (diff > RXRPC_KEEPALIVE_TIME - 1) ? RXRPC_KEEPALIVE_TIME - 1 : diff;
-	if (slot == 0)
-		goto send;
+	if (!rxnet->live)
+		return;
 
-	/* A transmission to this peer occurred since last we examined it so
-	 * put it into the appropriate future bucket.
+	/* Remove to a temporary list all the peers that are currently lodged
+	 * in expired buckets plus all new peers.
+	 *
+	 * Everything in the bucket at the cursor is processed this
+	 * second; the bucket at cursor + 1 goes at now + 1s and so
+	 * on...
 	 */
-	slot = (slot + cursor) % ARRAY_SIZE(rxnet->peer_keepalive);
 	spin_lock_bh(&rxnet->peer_hash_lock);
-	hlist_add_head(&peer->keepalive_link, &rxnet->peer_keepalive[slot]);
-	rxrpc_put_peer(peer);
-	goto next_peer;
-
-send:
-	rxrpc_send_keepalive(peer);
-	now = ktime_get_real();
-	goto recalc;
+	list_splice_init(&rxnet->peer_keepalive_new, &collector);
+
+	stop = cursor + ARRAY_SIZE(rxnet->peer_keepalive);
+	while (base <= now && (s8)(cursor - stop) < 0) {
+		list_splice_tail_init(&rxnet->peer_keepalive[cursor & mask],
+				      &collector);
+		base++;
+		cursor++;
+	}
 
-emptied_bucket:
-	cursor++;
-	if (cursor >= ARRAY_SIZE(rxnet->peer_keepalive))
-		cursor = 0;
-	base = ktime_add_ns(base, NSEC_PER_SEC);
-	goto next_bucket;
+	base = now;
+	spin_unlock_bh(&rxnet->peer_hash_lock);
 
-resched:
 	rxnet->peer_keepalive_base = base;
 	rxnet->peer_keepalive_cursor = cursor;
-	delay = nsecs_to_jiffies(-diff) + 1;
-	timer_reduce(&rxnet->peer_keepalive_timer, jiffies + delay);
-out:
+	rxrpc_peer_keepalive_dispatch(rxnet, &collector, base, cursor);
+	ASSERT(list_empty(&collector));
+
+	/* Schedule the timer for the next occupied timeslot. */
+	cursor = rxnet->peer_keepalive_cursor;
+	stop = cursor + RXRPC_KEEPALIVE_TIME - 1;
+	for (; (s8)(cursor - stop) < 0; cursor++) {
+		if (!list_empty(&rxnet->peer_keepalive[cursor & mask]))
+			break;
+		base++;
+	}
+
+	now = ktime_get_seconds();
+	delay = base - now;
+	if (delay < 1)
+		delay = 1;
+	delay *= HZ;
+	if (rxnet->live)
+		timer_reduce(&rxnet->peer_keepalive_timer, jiffies + delay);
+
 	_leave("");
 }
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index 1b7e8107b3ae..24ec7cdcf332 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -322,7 +322,7 @@ struct rxrpc_peer *rxrpc_lookup_incoming_peer(struct rxrpc_local *local,
 	if (!peer) {
 		peer = prealloc;
 		hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key);
-		hlist_add_head(&peer->keepalive_link, &rxnet->peer_keepalive_new);
+		list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive_new);
 	}
 
 	spin_unlock(&rxnet->peer_hash_lock);
@@ -367,8 +367,8 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local,
 		if (!peer) {
 			hash_add_rcu(rxnet->peer_hash,
 				     &candidate->hash_link, hash_key);
-			hlist_add_head(&candidate->keepalive_link,
-				       &rxnet->peer_keepalive_new);
+			list_add_tail(&candidate->keepalive_link,
+				      &rxnet->peer_keepalive_new);
 		}
 
 		spin_unlock_bh(&rxnet->peer_hash_lock);
@@ -441,7 +441,7 @@ static void __rxrpc_put_peer(struct rxrpc_peer *peer)
 
 	spin_lock_bh(&rxnet->peer_hash_lock);
 	hash_del_rcu(&peer->hash_link);
-	hlist_del_init(&peer->keepalive_link);
+	list_del_init(&peer->keepalive_link);
 	spin_unlock_bh(&rxnet->peer_hash_lock);
 
 	kfree_rcu(peer, rcu);
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index 6c0ae27fff84..94262c3ead88 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -669,7 +669,7 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn)
 		return -EAGAIN;
 	}
 
-	conn->params.peer->last_tx_at = ktime_get_real();
+	conn->params.peer->last_tx_at = ktime_get_seconds();
 	_leave(" = 0");
 	return 0;
 }
@@ -725,7 +725,7 @@ static int rxkad_send_response(struct rxrpc_connection *conn,
 		return -EAGAIN;
 	}
 
-	conn->params.peer->last_tx_at = ktime_get_real();
+	conn->params.peer->last_tx_at = ktime_get_seconds();
 	_leave(" = 0");
 	return 0;
 }
-- 
2.17.1


[-- Attachment #3: net_418.mbox --]
[-- Type: Application/Octet-Stream, Size: 17393 bytes --]

From 6a01bf1b22a197a0275b01ebdda00f6e7283f90d Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Fri, 10 Aug 2018 11:14:56 -0700
Subject: [PATCH 1/4] l2tp: use sk_dst_check() to avoid race on
 sk->sk_dst_cache

[ Upstream commit 6d37fa49da1e8db8fb1995be22ac837ca41ac8a8 ]

In l2tp code, if it is a L2TP_UDP_ENCAP tunnel, tunnel->sk points to a
UDP socket. User could call sendmsg() on both this tunnel and the UDP
socket itself concurrently. As l2tp_xmit_skb() holds socket lock and call
__sk_dst_check() to refresh sk->sk_dst_cache, while udpv6_sendmsg() is
lockless and call sk_dst_check() to refresh sk->sk_dst_cache, there
could be a race and cause the dst cache to be freed multiple times.
So we fix l2tp side code to always call sk_dst_check() to garantee
xchg() is called when refreshing sk->sk_dst_cache to avoid race
conditions.

Syzkaller reported stack trace:
BUG: KASAN: use-after-free in atomic_read include/asm-generic/atomic-instrumented.h:21 [inline]
BUG: KASAN: use-after-free in atomic_fetch_add_unless include/linux/atomic.h:575 [inline]
BUG: KASAN: use-after-free in atomic_add_unless include/linux/atomic.h:597 [inline]
BUG: KASAN: use-after-free in dst_hold_safe include/net/dst.h:308 [inline]
BUG: KASAN: use-after-free in ip6_hold_safe+0xe6/0x670 net/ipv6/route.c:1029
Read of size 4 at addr ffff8801aea9a880 by task syz-executor129/4829

CPU: 0 PID: 4829 Comm: syz-executor129 Not tainted 4.18.0-rc7-next-20180802+ #30
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c9/0x2b4 lib/dump_stack.c:113
 print_address_description+0x6c/0x20b mm/kasan/report.c:256
 kasan_report_error mm/kasan/report.c:354 [inline]
 kasan_report.cold.7+0x242/0x30d mm/kasan/report.c:412
 check_memory_region_inline mm/kasan/kasan.c:260 [inline]
 check_memory_region+0x13e/0x1b0 mm/kasan/kasan.c:267
 kasan_check_read+0x11/0x20 mm/kasan/kasan.c:272
 atomic_read include/asm-generic/atomic-instrumented.h:21 [inline]
 atomic_fetch_add_unless include/linux/atomic.h:575 [inline]
 atomic_add_unless include/linux/atomic.h:597 [inline]
 dst_hold_safe include/net/dst.h:308 [inline]
 ip6_hold_safe+0xe6/0x670 net/ipv6/route.c:1029
 rt6_get_pcpu_route net/ipv6/route.c:1249 [inline]
 ip6_pol_route+0x354/0xd20 net/ipv6/route.c:1922
 ip6_pol_route_output+0x54/0x70 net/ipv6/route.c:2098
 fib6_rule_lookup+0x283/0x890 net/ipv6/fib6_rules.c:122
 ip6_route_output_flags+0x2c5/0x350 net/ipv6/route.c:2126
 ip6_dst_lookup_tail+0x1278/0x1da0 net/ipv6/ip6_output.c:978
 ip6_dst_lookup_flow+0xc8/0x270 net/ipv6/ip6_output.c:1079
 ip6_sk_dst_lookup_flow+0x5ed/0xc50 net/ipv6/ip6_output.c:1117
 udpv6_sendmsg+0x2163/0x36b0 net/ipv6/udp.c:1354
 inet_sendmsg+0x1a1/0x690 net/ipv4/af_inet.c:798
 sock_sendmsg_nosec net/socket.c:622 [inline]
 sock_sendmsg+0xd5/0x120 net/socket.c:632
 ___sys_sendmsg+0x51d/0x930 net/socket.c:2115
 __sys_sendmmsg+0x240/0x6f0 net/socket.c:2210
 __do_sys_sendmmsg net/socket.c:2239 [inline]
 __se_sys_sendmmsg net/socket.c:2236 [inline]
 __x64_sys_sendmmsg+0x9d/0x100 net/socket.c:2236
 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x446a29
Code: e8 ac b8 02 00 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 eb 08 fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f4de5532db8 EFLAGS: 00000246 ORIG_RAX: 0000000000000133
RAX: ffffffffffffffda RBX: 00000000006dcc38 RCX: 0000000000446a29
RDX: 00000000000000b8 RSI: 0000000020001b00 RDI: 0000000000000003
RBP: 00000000006dcc30 R08: 00007f4de5533700 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00000000006dcc3c
R13: 00007ffe2b830fdf R14: 00007f4de55339c0 R15: 0000000000000001

Fixes: 71b1391a4128 ("l2tp: ensure sk->dst is still valid")
Reported-by: syzbot+05f840f3b04f211bad55@syzkaller.appspotmail.com
Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Cc: Guillaume Nault <g.nault@alphalink.fr>
Cc: David Ahern <dsahern@gmail.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 40261cb68e83..8aaf8157da2b 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1110,7 +1110,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len
 
 	/* Get routing info from the tunnel socket */
 	skb_dst_drop(skb);
-	skb_dst_set(skb, dst_clone(__sk_dst_check(sk, 0)));
+	skb_dst_set(skb, sk_dst_check(sk, 0));
 
 	inet = inet_sk(sk);
 	fl = &inet->cork.fl;
-- 
2.17.1


From 6ac5c644d20b9a89bcfcf7a2d51b3613ede2e509 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Mon, 13 Aug 2018 18:44:03 +0800
Subject: [PATCH 2/4] net_sched: fix NULL pointer dereference when delete
 tcindex filter

[ Upstream commit 2df8bee5654bb2b7312662ca6810d4dc16b0b67f ]

Li Shuang reported the following crash:

[   71.267724] BUG: unable to handle kernel NULL pointer dereference at 0000000000000004
[   71.276456] PGD 800000085d9bd067 P4D 800000085d9bd067 PUD 859a0b067 PMD 0
[   71.284127] Oops: 0000 [#1] SMP PTI
[   71.288015] CPU: 12 PID: 2386 Comm: tc Not tainted 4.18.0-rc8.latest+ #131
[   71.295686] Hardware name: Dell Inc. PowerEdge R730/0WCJNT, BIOS 2.1.5 04/11/2016
[   71.304037] RIP: 0010:tcindex_delete+0x72/0x280 [cls_tcindex]
[   71.310446] Code: 00 31 f6 48 87 75 20 48 85 f6 74 11 48 8b 47 18 48 8b 40 08 48 8b 40 50 e8 fb a6 f8 fc 48 85 db 0f 84 dc 00 00 00 48 8b 73 18 <8b> 56 04 48 8d 7e 04 85 d2 0f 84 7b 01 00
[   71.331517] RSP: 0018:ffffb45207b3f898 EFLAGS: 00010282
[   71.337345] RAX: ffff8ad3d72d6360 RBX: ffff8acc84393680 RCX: 000000000000002e
[   71.345306] RDX: ffff8ad3d72c8570 RSI: 0000000000000000 RDI: ffff8ad847a45800
[   71.353277] RBP: ffff8acc84393688 R08: ffff8ad3d72c8400 R09: 0000000000000000
[   71.361238] R10: ffff8ad3de786e00 R11: 0000000000000000 R12: ffffb45207b3f8c7
[   71.369199] R13: ffff8ad3d93bd2a0 R14: 000000000000002e R15: ffff8ad3d72c9600
[   71.377161] FS:  00007f9d3ec3e740(0000) GS:ffff8ad3df980000(0000) knlGS:0000000000000000
[   71.386188] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   71.392597] CR2: 0000000000000004 CR3: 0000000852f06003 CR4: 00000000001606e0
[   71.400558] Call Trace:
[   71.403299]  tcindex_destroy_element+0x25/0x40 [cls_tcindex]
[   71.409611]  tcindex_walk+0xbb/0x110 [cls_tcindex]
[   71.414953]  tcindex_destroy+0x44/0x90 [cls_tcindex]
[   71.420492]  ? tcindex_delete+0x280/0x280 [cls_tcindex]
[   71.426323]  tcf_proto_destroy+0x16/0x40
[   71.430696]  tcf_chain_flush+0x51/0x70
[   71.434876]  tcf_block_put_ext.part.30+0x8f/0x1b0
[   71.440122]  tcf_block_put+0x4d/0x70
[   71.444108]  cbq_destroy+0x4d/0xd0 [sch_cbq]
[   71.448869]  qdisc_destroy+0x62/0x130
[   71.452951]  dsmark_destroy+0x2a/0x70 [sch_dsmark]
[   71.458300]  qdisc_destroy+0x62/0x130
[   71.462373]  qdisc_graft+0x3ba/0x470
[   71.466359]  tc_get_qdisc+0x2a6/0x2c0
[   71.470443]  ? cred_has_capability+0x7d/0x130
[   71.475307]  rtnetlink_rcv_msg+0x263/0x2d0
[   71.479875]  ? rtnl_calcit.isra.30+0x110/0x110
[   71.484832]  netlink_rcv_skb+0x4d/0x130
[   71.489109]  netlink_unicast+0x1a3/0x250
[   71.493482]  netlink_sendmsg+0x2ae/0x3a0
[   71.497859]  sock_sendmsg+0x36/0x40
[   71.501748]  ___sys_sendmsg+0x26f/0x2d0
[   71.506029]  ? handle_pte_fault+0x586/0xdf0
[   71.510694]  ? __handle_mm_fault+0x389/0x500
[   71.515457]  ? __sys_sendmsg+0x5e/0xa0
[   71.519636]  __sys_sendmsg+0x5e/0xa0
[   71.523626]  do_syscall_64+0x5b/0x180
[   71.527711]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[   71.533345] RIP: 0033:0x7f9d3e257f10
[   71.537331] Code: c3 48 8b 05 82 6f 2c 00 f7 db 64 89 18 48 83 cb ff eb dd 0f 1f 80 00 00 00 00 83 3d 8d d0 2c 00 00 75 10 b8 2e 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8
[   71.558401] RSP: 002b:00007fff6f893398 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
[   71.566848] RAX: ffffffffffffffda RBX: 000000005b71274d RCX: 00007f9d3e257f10
[   71.574810] RDX: 0000000000000000 RSI: 00007fff6f8933e0 RDI: 0000000000000003
[   71.582770] RBP: 00007fff6f8933e0 R08: 000000000000ffff R09: 0000000000000003
[   71.590729] R10: 00007fff6f892e20 R11: 0000000000000246 R12: 0000000000000000
[   71.598689] R13: 0000000000662ee0 R14: 0000000000000000 R15: 0000000000000000
[   71.606651] Modules linked in: sch_cbq cls_tcindex sch_dsmark xt_CHECKSUM iptable_mangle ipt_MASQUERADE iptable_nat nf_nat_ipv4 nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_conntrack nf_coni
[   71.685425]  libahci i2c_algo_bit i2c_core i40e libata dca mdio megaraid_sas dm_mirror dm_region_hash dm_log dm_mod
[   71.697075] CR2: 0000000000000004
[   71.700792] ---[ end trace f604eb1acacd978b ]---

Reproducer:
tc qdisc add dev lo handle 1:0 root dsmark indices 64 set_tc_index
tc filter add dev lo parent 1:0 protocol ip prio 1 tcindex mask 0xfc shift 2
tc qdisc add dev lo parent 1:0 handle 2:0 cbq bandwidth 10Mbit cell 8 avpkt 1000 mpu 64
tc class add dev lo parent 2:0 classid 2:1 cbq bandwidth 10Mbit rate 1500Kbit avpkt 1000 prio 1 bounded isolated allot 1514 weight 1 maxburst 10
tc filter add dev lo parent 2:0 protocol ip prio 1 handle 0x2e tcindex classid 2:1 pass_on
tc qdisc add dev lo parent 2:1 pfifo limit 5
tc qdisc del dev lo root

This is because in tcindex_set_parms, when there is no old_r, we set new
exts to cr.exts. And we didn't set it to filter when r == &new_filter_result.

Then in tcindex_delete() -> tcf_exts_get_net(), we will get NULL pointer
dereference as we didn't init exts.

Fix it by moving tcf_exts_change() after "if (old_r && old_r != r)" check.
Then we don't need "cr" as there is no errout after that.

Fixes: bf63ac73b3e13 ("net_sched: fix an oops in tcindex filter")
Reported-by: Li Shuang <shuali@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_tcindex.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 32f4bbd82f35..ddaa4e63ce94 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -447,11 +447,6 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 		tcf_bind_filter(tp, &cr.res, base);
 	}
 
-	if (old_r)
-		tcf_exts_change(&r->exts, &e);
-	else
-		tcf_exts_change(&cr.exts, &e);
-
 	if (old_r && old_r != r) {
 		err = tcindex_filter_result_init(old_r);
 		if (err < 0) {
@@ -462,6 +457,8 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 
 	oldp = p;
 	r->res = cr.res;
+	tcf_exts_change(&r->exts, &e);
+
 	rcu_assign_pointer(tp->root, cp);
 
 	if (r == &new_filter_result) {
-- 
2.17.1


From 6bf7c6db96afb591bc234e487e03f23453de0bd7 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Mon, 13 Aug 2018 18:44:04 +0800
Subject: [PATCH 3/4] net_sched: Fix missing res info when create new tc_index
 filter

[ Upstream commit 008369dcc5f7bfba526c98054f8525322acf0ea3 ]

Li Shuang reported the following warn:

[  733.484610] WARNING: CPU: 6 PID: 21123 at net/sched/sch_cbq.c:1418 cbq_destroy_class+0x5d/0x70 [sch_cbq]
[  733.495190] Modules linked in: sch_cbq cls_tcindex sch_dsmark rpcsec_gss_krb5 auth_rpcgss nfsv4 dns_resolver nfs lockd grace fscache xt_CHECKSUM iptable_mangle ipt_MASQUERADE iptable_nat l
[  733.574155]  syscopyarea sysfillrect sysimgblt fb_sys_fops ttm drm igb ixgbe ahci libahci i2c_algo_bit libata i40e i2c_core dca mdio megaraid_sas dm_mirror dm_region_hash dm_log dm_mod
[  733.592500] CPU: 6 PID: 21123 Comm: tc Not tainted 4.18.0-rc8.latest+ #131
[  733.600169] Hardware name: Dell Inc. PowerEdge R730/0WCJNT, BIOS 2.1.5 04/11/2016
[  733.608518] RIP: 0010:cbq_destroy_class+0x5d/0x70 [sch_cbq]
[  733.614734] Code: e7 d9 d2 48 8b 7b 48 e8 61 05 da d2 48 8d bb f8 00 00 00 e8 75 ae d5 d2 48 39 eb 74 0a 48 89 df 5b 5d e9 16 6c 94 d2 5b 5d c3 <0f> 0b eb b6 0f 1f 44 00 00 66 2e 0f 1f 84
[  733.635798] RSP: 0018:ffffbfbb066bb9d8 EFLAGS: 00010202
[  733.641627] RAX: 0000000000000001 RBX: ffff9cdd17392800 RCX: 000000008010000f
[  733.649588] RDX: ffff9cdd1df547e0 RSI: ffff9cdd17392800 RDI: ffff9cdd0f84c800
[  733.657547] RBP: ffff9cdd0f84c800 R08: 0000000000000001 R09: 0000000000000000
[  733.665508] R10: ffff9cdd0f84d000 R11: 0000000000000001 R12: 0000000000000001
[  733.673469] R13: 0000000000000000 R14: 0000000000000001 R15: ffff9cdd17392200
[  733.681430] FS:  00007f911890a740(0000) GS:ffff9cdd1f8c0000(0000) knlGS:0000000000000000
[  733.690456] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  733.696864] CR2: 0000000000b5544c CR3: 0000000859374002 CR4: 00000000001606e0
[  733.704826] Call Trace:
[  733.707554]  cbq_destroy+0xa1/0xd0 [sch_cbq]
[  733.712318]  qdisc_destroy+0x62/0x130
[  733.716401]  dsmark_destroy+0x2a/0x70 [sch_dsmark]
[  733.721745]  qdisc_destroy+0x62/0x130
[  733.725829]  qdisc_graft+0x3ba/0x470
[  733.729817]  tc_get_qdisc+0x2a6/0x2c0
[  733.733901]  ? cred_has_capability+0x7d/0x130
[  733.738761]  rtnetlink_rcv_msg+0x263/0x2d0
[  733.743330]  ? rtnl_calcit.isra.30+0x110/0x110
[  733.748287]  netlink_rcv_skb+0x4d/0x130
[  733.752576]  netlink_unicast+0x1a3/0x250
[  733.756949]  netlink_sendmsg+0x2ae/0x3a0
[  733.761324]  sock_sendmsg+0x36/0x40
[  733.765213]  ___sys_sendmsg+0x26f/0x2d0
[  733.769493]  ? handle_pte_fault+0x586/0xdf0
[  733.774158]  ? __handle_mm_fault+0x389/0x500
[  733.778919]  ? __sys_sendmsg+0x5e/0xa0
[  733.783099]  __sys_sendmsg+0x5e/0xa0
[  733.787087]  do_syscall_64+0x5b/0x180
[  733.791171]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[  733.796805] RIP: 0033:0x7f9117f23f10
[  733.800791] Code: c3 48 8b 05 82 6f 2c 00 f7 db 64 89 18 48 83 cb ff eb dd 0f 1f 80 00 00 00 00 83 3d 8d d0 2c 00 00 75 10 b8 2e 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8
[  733.821873] RSP: 002b:00007ffe96818398 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
[  733.830319] RAX: ffffffffffffffda RBX: 000000005b71244c RCX: 00007f9117f23f10
[  733.838280] RDX: 0000000000000000 RSI: 00007ffe968183e0 RDI: 0000000000000003
[  733.846241] RBP: 00007ffe968183e0 R08: 000000000000ffff R09: 0000000000000003
[  733.854202] R10: 00007ffe96817e20 R11: 0000000000000246 R12: 0000000000000000
[  733.862161] R13: 0000000000662ee0 R14: 0000000000000000 R15: 0000000000000000
[  733.870121] ---[ end trace 28edd4aad712ddca ]---

This is because we didn't update f->result.res when create new filter. Then in
tcindex_delete() -> tcf_unbind_filter(), we will failed to find out the res
and unbind filter, which will trigger the WARN_ON() in cbq_destroy_class().

Fix it by updating f->result.res when create new filter.

Fixes: 6e0565697a106 ("net_sched: fix another crash in cls_tcindex")
Reported-by: Li Shuang <shuali@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_tcindex.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index ddaa4e63ce94..9ccc93f257db 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -465,6 +465,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 		struct tcindex_filter *nfp;
 		struct tcindex_filter __rcu **fp;
 
+		f->result.res = r->res;
 		tcf_exts_change(&f->result.exts, &r->exts);
 
 		fp = cp->h + (handle % cp->hash);
-- 
2.17.1


From 9b54e96c574444276c2af516ad892066f752f1fc Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 12 Aug 2018 13:26:26 +0200
Subject: [PATCH 4/4] r8169: don't use MSI-X on RTL8168g

[ Upstream commit 7c53a722459c1d6ffb0f5b2058c06ca8980b8600 ]

There have been two reports that network doesn't come back on resume
from suspend when using MSI-X. Both cases affect the same chip version
(RTL8168g - version 40), on different systems. Falling back to MSI
fixes the issue.
Even though we don't really have a proof yet that the network chip
version is to blame, let's disable MSI-X for this version.

Reported-by: Steve Dodd <steved424@gmail.com>
Reported-by: Lou Reed <gogen@disroot.org>
Tested-by: Steve Dodd <steved424@gmail.com>
Tested-by: Lou Reed <gogen@disroot.org>
Fixes: 6c6aa15fdea5 ("r8169: improve interrupt handling")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index eaedc11ed686..a0311fe1a457 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -7544,6 +7544,11 @@ static int rtl_alloc_irq(struct rtl8169_private *tp)
 		RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~MSIEnable);
 		RTL_W8(tp, Cfg9346, Cfg9346_Lock);
 		flags = PCI_IRQ_LEGACY;
+	} else if (tp->mac_version == RTL_GIGA_MAC_VER_40) {
+		/* This version was reported to have issues with resume
+		 * from suspend when using MSI-X
+		 */
+		flags = PCI_IRQ_LEGACY | PCI_IRQ_MSI;
 	} else {
 		flags = PCI_IRQ_ALL_TYPES;
 	}
-- 
2.17.1

Re: [PATCHES] Networking

[Greg KH]

On Fri, Aug 17, 2018 at 12:32:37PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes up for 4.17 and
> 4.18 -stable, respectively.

All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 104 bytes --]


Please queue up the following networking bug fixes for v4.17
and v4.18 -stable, respectively.

Thanks!

[-- Attachment #2: net_417.mbox --]
[-- Type: Application/Octet-Stream, Size: 87521 bytes --]

From 3e372b79659e6ff76c31909aebf7eaa02b8e9c0a Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 3 Sep 2018 11:08:15 -0700
Subject: [PATCH 01/29] act_ife: fix a potential use-after-free

[ Upstream commit 6d784f1625ea68783cc1fb17de8f6cd3e1660c3f ]

Immediately after module_put(), user could delete this
module, so e->ops could be already freed before we call
e->ops->release().

Fix this by moving module_put() after ops->release().

Fixes: ef6980b6becb ("introduce IFE action")
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ife.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 20d7d36b2fc9..201e599baed9 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -393,7 +393,6 @@ static void _tcf_ife_cleanup(struct tc_action *a)
 	struct tcf_meta_info *e, *n;
 
 	list_for_each_entry_safe(e, n, &ife->metalist, metalist) {
-		module_put(e->ops->owner);
 		list_del(&e->metalist);
 		if (e->metaval) {
 			if (e->ops->release)
@@ -401,6 +400,7 @@ static void _tcf_ife_cleanup(struct tc_action *a)
 			else
 				kfree(e->metaval);
 		}
+		module_put(e->ops->owner);
 		kfree(e);
 	}
 }
-- 
2.13.6


From 461a8a2ddd87739f5d203114d679db14594b43ab Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 22 Aug 2018 13:30:45 -0700
Subject: [PATCH 02/29] ipv4: tcp: send zero IPID for RST and ACK sent in
 SYN-RECV and TIME-WAIT state

[ Upstream commit 431280eebed9f5079553daf003011097763e71fd ]

tcp uses per-cpu (and per namespace) sockets (net->ipv4.tcp_sk) internally
to send some control packets.

1) RST packets, through tcp_v4_send_reset()
2) ACK packets in SYN-RECV and TIME-WAIT state, through tcp_v4_send_ack()

These packets assert IP_DF, and also use the hashed IP ident generator
to provide an IPv4 ID number.

Geoff Alexander reported this could be used to build off-path attacks.

These packets should not be fragmented, since their size is smaller than
IPV4_MIN_MTU. Only some tunneled paths could eventually have to fragment,
regardless of inner IPID.

We really can use zero IPID, to address the flaw, and as a bonus,
avoid a couple of atomic operations in ip_idents_reserve()

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Geoff Alexander <alexandg@cs.unm.edu>
Tested-by: Geoff Alexander <alexandg@cs.unm.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index ef8cd0f7db89..7ac7dc54b800 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2498,6 +2498,12 @@ static int __net_init tcp_sk_init(struct net *net)
 		if (res)
 			goto fail;
 		sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);
+
+		/* Please enforce IP_DF and IPID==0 for RST and
+		 * ACK sent in SYN-RECV and TIME-WAIT state.
+		 */
+		inet_sk(sk)->pmtudisc = IP_PMTUDISC_DO;
+
 		*per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk;
 	}
 
-- 
2.13.6


From 6eb091b2a2f4f3a7789b7fe054d80c33cec67e93 Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Tue, 28 Aug 2018 12:33:15 -0700
Subject: [PATCH 03/29] net: bcmgenet: use MAC link status for fixed phy

[ Upstream commit c3c397c1f16c51601a3fac4fe0c63ad8aa85a904 ]

When using the fixed PHY with GENET (e.g. MOCA) the PHY link
status can be determined from the internal link status captured
by the MAC. This allows the PHY state machine to use the correct
link state with the fixed PHY even if MAC link event interrupts
are missed when the net device is opened.

Fixes: 8d88c6ebb34c ("net: bcmgenet: enable MoCA link state change detection")
Signed-off-by: Doug Berger <opendmb@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.h |  3 +++
 drivers/net/ethernet/broadcom/genet/bcmmii.c   | 10 ++++++++--
 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index b773bc07edf7..14b49612aa86 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -186,6 +186,9 @@ struct bcmgenet_mib_counters {
 #define UMAC_MAC1			0x010
 #define UMAC_MAX_FRAME_LEN		0x014
 
+#define UMAC_MODE			0x44
+#define  MODE_LINK_STATUS		(1 << 5)
+
 #define UMAC_EEE_CTRL			0x064
 #define  EN_LPI_RX_PAUSE		(1 << 0)
 #define  EN_LPI_TX_PFC			(1 << 1)
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index 5333274a283c..4241ae928d4a 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -115,8 +115,14 @@ void bcmgenet_mii_setup(struct net_device *dev)
 static int bcmgenet_fixed_phy_link_update(struct net_device *dev,
 					  struct fixed_phy_status *status)
 {
-	if (dev && dev->phydev && status)
-		status->link = dev->phydev->link;
+	struct bcmgenet_priv *priv;
+	u32 reg;
+
+	if (dev && dev->phydev && status) {
+		priv = netdev_priv(dev);
+		reg = bcmgenet_umac_readl(priv, UMAC_MODE);
+		status->link = !!(reg & MODE_LINK_STATUS);
+	}
 
 	return 0;
 }
-- 
2.13.6


From d96d723a141ca8592b3377db1408c51ad2616fc4 Mon Sep 17 00:00:00 2001
From: Anssi Hannula <anssi.hannula@bitwise.fi>
Date: Thu, 23 Aug 2018 10:45:22 +0300
Subject: [PATCH 04/29] net: macb: do not disable MDIO bus at open/close time

[ Upstream commit 0da70f808029476001109b6cb076737bc04cea2e ]

macb_reset_hw() is called from macb_close() and indirectly from
macb_open(). macb_reset_hw() zeroes the NCR register, including the MPE
(Management Port Enable) bit.

This will prevent accessing any other PHYs for other Ethernet MACs on
the MDIO bus, which remains registered at macb_reset_hw() time, until
macb_init_hw() is called from macb_open() which sets the MPE bit again.

I.e. currently the MDIO bus has a short disruption at open time and is
disabled at close time until the interface is opened again.

Fix that by only touching the RE and TE bits when enabling and disabling
RX/TX.

v2: Make macb_init_hw() NCR write a single statement.

Fixes: 6c36a7074436 ("macb: Use generic PHY layer")
Signed-off-by: Anssi Hannula <anssi.hannula@bitwise.fi>
Reviewed-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Tested-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 01032f37a308..6263003aafef 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -1960,14 +1960,17 @@ static void macb_reset_hw(struct macb *bp)
 {
 	struct macb_queue *queue;
 	unsigned int q;
+	u32 ctrl = macb_readl(bp, NCR);
 
 	/* Disable RX and TX (XXX: Should we halt the transmission
 	 * more gracefully?)
 	 */
-	macb_writel(bp, NCR, 0);
+	ctrl &= ~(MACB_BIT(RE) | MACB_BIT(TE));
 
 	/* Clear the stats registers (XXX: Update stats first?) */
-	macb_writel(bp, NCR, MACB_BIT(CLRSTAT));
+	ctrl |= MACB_BIT(CLRSTAT);
+
+	macb_writel(bp, NCR, ctrl);
 
 	/* Clear all status flags */
 	macb_writel(bp, TSR, -1);
@@ -2155,7 +2158,7 @@ static void macb_init_hw(struct macb *bp)
 	}
 
 	/* Enable TX and RX */
-	macb_writel(bp, NCR, MACB_BIT(RE) | MACB_BIT(TE) | MACB_BIT(MPE));
+	macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(RE) | MACB_BIT(TE));
 }
 
 /* The hash address register is 64 bits long and takes up two
-- 
2.13.6


From 884ce8896c4e398f446ebc9f6a8e87c72d2892a7 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Sat, 25 Aug 2018 22:58:01 -0700
Subject: [PATCH 05/29] net: sched: Fix memory exposure from short TCA_U32_SEL

[ Upstream commit 98c8f125fd8a6240ea343c1aa50a1be9047791b8 ]

Via u32_change(), TCA_U32_SEL has an unspecified type in the netlink
policy, so max length isn't enforced, only minimum. This means nkeys
(from userspace) was being trusted without checking the actual size of
nla_len(), which could lead to a memory over-read, and ultimately an
exposure via a call to u32_dump(). Reachability is CAP_NET_ADMIN within
a namespace.

Reported-by: Al Viro <viro@zeniv.linux.org.uk>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_u32.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index bac47b5d18fd..75092a3bec59 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -929,6 +929,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 	struct nlattr *opt = tca[TCA_OPTIONS];
 	struct nlattr *tb[TCA_U32_MAX + 1];
 	u32 htid, flags = 0;
+	size_t sel_size;
 	int err;
 #ifdef CONFIG_CLS_U32_PERF
 	size_t size;
@@ -1091,8 +1092,13 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 	}
 
 	s = nla_data(tb[TCA_U32_SEL]);
+	sel_size = sizeof(*s) + sizeof(*s->keys) * s->nkeys;
+	if (nla_len(tb[TCA_U32_SEL]) < sel_size) {
+		err = -EINVAL;
+		goto erridr;
+	}
 
-	n = kzalloc(sizeof(*n) + s->nkeys*sizeof(struct tc_u32_key), GFP_KERNEL);
+	n = kzalloc(offsetof(typeof(*n), sel) + sel_size, GFP_KERNEL);
 	if (n == NULL) {
 		err = -ENOBUFS;
 		goto erridr;
@@ -1107,7 +1113,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 	}
 #endif
 
-	memcpy(&n->sel, s, sizeof(*s) + s->nkeys*sizeof(struct tc_u32_key));
+	memcpy(&n->sel, s, sel_size);
 	RCU_INIT_POINTER(n->ht_up, ht);
 	n->handle = handle;
 	n->fshift = s->hmask ? ffs(ntohl(s->hmask)) - 1 : 0;
-- 
2.13.6


From 5788f50918b494c706102e55f0bcd834481ce77b Mon Sep 17 00:00:00 2001
From: Manish Chopra <manish.chopra@cavium.com>
Date: Thu, 23 Aug 2018 13:20:52 -0700
Subject: [PATCH 06/29] qlge: Fix netdev features configuration.

[ Upstream commit 6750c87074c5b534d82fdaabb1deb45b8f1f57de ]

qlge_fix_features() is not supposed to modify hardware or
driver state, rather it is supposed to only fix requested
fetures bits. Currently qlge_fix_features() also goes for
interface down and up unnecessarily if there is not even
any change in features set.

This patch changes/fixes following -

1) Move reload of interface or device re-config from
   qlge_fix_features() to qlge_set_features().
2) Reload of interface in qlge_set_features() only if
   relevant feature bit (NETIF_F_HW_VLAN_CTAG_RX) is changed.
3) Get rid of qlge_fix_features() since driver is not really
   required to fix any features bit.

Signed-off-by: Manish <manish.chopra@cavium.com>
Reviewed-by: Benjamin Poirier <bpoirier@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qlge/qlge_main.c | 23 ++++++++---------------
 1 file changed, 8 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
index 8293c2028002..ee996acb39a9 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
@@ -2384,26 +2384,20 @@ static int qlge_update_hw_vlan_features(struct net_device *ndev,
 	return status;
 }
 
-static netdev_features_t qlge_fix_features(struct net_device *ndev,
-	netdev_features_t features)
-{
-	int err;
-
-	/* Update the behavior of vlan accel in the adapter */
-	err = qlge_update_hw_vlan_features(ndev, features);
-	if (err)
-		return err;
-
-	return features;
-}
-
 static int qlge_set_features(struct net_device *ndev,
 	netdev_features_t features)
 {
 	netdev_features_t changed = ndev->features ^ features;
+	int err;
+
+	if (changed & NETIF_F_HW_VLAN_CTAG_RX) {
+		/* Update the behavior of vlan accel in the adapter */
+		err = qlge_update_hw_vlan_features(ndev, features);
+		if (err)
+			return err;
 
-	if (changed & NETIF_F_HW_VLAN_CTAG_RX)
 		qlge_vlan_mode(ndev, features);
+	}
 
 	return 0;
 }
@@ -4718,7 +4712,6 @@ static const struct net_device_ops qlge_netdev_ops = {
 	.ndo_set_mac_address	= qlge_set_mac_address,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_tx_timeout		= qlge_tx_timeout,
-	.ndo_fix_features	= qlge_fix_features,
 	.ndo_set_features	= qlge_set_features,
 	.ndo_vlan_rx_add_vid	= qlge_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= qlge_vlan_rx_kill_vid,
-- 
2.13.6


From 8f24e7d7f5c359fcad49dff02fb2460d3df59380 Mon Sep 17 00:00:00 2001
From: Kai-Heng Feng <kai.heng.feng@canonical.com>
Date: Mon, 20 Aug 2018 12:43:51 +0800
Subject: [PATCH 07/29] r8152: disable RX aggregation on new Dell TB16 dock

[ Upstream commit 176eb614b118c96e7797f5ddefd10708c316f621 ]

There's a new Dell TB16 dock with a different iSerialNumber.

Apply the same fix from commit 0b1655143df0 ("r8152: disable RX
aggregation on Dell TB16 dock") to this model.

BugLink: https://bugs.launchpad.net/bugs/1785780
Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 2a58607a6aea..1b07bb5e110d 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -5214,8 +5214,8 @@ static int rtl8152_probe(struct usb_interface *intf,
 		netdev->hw_features &= ~NETIF_F_RXCSUM;
 	}
 
-	if (le16_to_cpu(udev->descriptor.bcdDevice) == 0x3011 &&
-	    udev->serial && !strcmp(udev->serial, "000001000000")) {
+	if (le16_to_cpu(udev->descriptor.bcdDevice) == 0x3011 && udev->serial &&
+	    (!strcmp(udev->serial, "000001000000") || !strcmp(udev->serial, "000002000000"))) {
 		dev_info(&udev->dev, "Dell TB16 Dock, disable RX aggregation");
 		set_bit(DELL_TB_RX_AGG_BUG, &tp->flags);
 	}
-- 
2.13.6


From d5039121e91fc63052797e68ae93ffdc2a31e8e1 Mon Sep 17 00:00:00 2001
From: Anthony Wong <anthony.wong@ubuntu.com>
Date: Fri, 31 Aug 2018 20:06:42 +0800
Subject: [PATCH 08/29] r8169: add support for NCube 8168 network card

[ Upstream commit 9fd0e09a4e86499639653243edfcb417a05c5c46 ]

This card identifies itself as:
  Ethernet controller [0200]: NCube Device [10ff:8168] (rev 06)
  Subsystem: TP-LINK Technologies Co., Ltd. Device [7470:3468]

Adding a new entry to rtl8169_pci_tbl makes the card work.

Link: http://launchpad.net/bugs/1788730
Signed-off-by: Anthony Wong <anthony.wong@ubuntu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 1 +
 include/linux/pci_ids.h              | 2 ++
 2 files changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 07cc71cc9b76..e50604ebbf57 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -329,6 +329,7 @@ static const struct pci_device_id rtl8169_pci_tbl[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8161), 0, 0, RTL_CFG_1 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8167), 0, 0, RTL_CFG_0 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8168), 0, 0, RTL_CFG_1 },
+	{ PCI_DEVICE(PCI_VENDOR_ID_NCUBE,	0x8168), 0, 0, RTL_CFG_1 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8169), 0, 0, RTL_CFG_0 },
 	{ PCI_VENDOR_ID_DLINK,			0x4300,
 		PCI_VENDOR_ID_DLINK, 0x4b10,		 0, 0, RTL_CFG_1 },
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index cc608fc55334..6efb1422b60e 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -3073,4 +3073,6 @@
 
 #define PCI_VENDOR_ID_OCZ		0x1b85
 
+#define PCI_VENDOR_ID_NCUBE		0x10ff
+
 #endif /* _LINUX_PCI_IDS_H */
-- 
2.13.6


From 0225dfd3aafd1a38c31ee3c004a8548fd5a105e8 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 30 Aug 2018 14:24:29 +0200
Subject: [PATCH 09/29] tcp: do not restart timewait timer on rst reception

[ Upstream commit 63cc357f7bba6729869565a12df08441a5995d9a ]

RFC 1337 says:
 ''Ignore RST segments in TIME-WAIT state.
   If the 2 minute MSL is enforced, this fix avoids all three hazards.''

So with net.ipv4.tcp_rfc1337=1, expected behaviour is to have TIME-WAIT sk
expire rather than removing it instantly when a reset is received.

However, Linux will also re-start the TIME-WAIT timer.

This causes connect to fail when tying to re-use ports or very long
delays (until syn retry interval exceeds MSL).

packetdrill test case:
// Demonstrate bogus rearming of TIME-WAIT timer in rfc1337 mode.
`sysctl net.ipv4.tcp_rfc1337=1`

0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
0.000 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
0.000 bind(3, ..., ...) = 0
0.000 listen(3, 1) = 0

0.100 < S 0:0(0) win 29200 <mss 1460,nop,nop,sackOK,nop,wscale 7>
0.100 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 7>
0.200 < . 1:1(0) ack 1 win 257
0.200 accept(3, ..., ...) = 4

// Receive first segment
0.310 < P. 1:1001(1000) ack 1 win 46

// Send one ACK
0.310 > . 1:1(0) ack 1001

// read 1000 byte
0.310 read(4, ..., 1000) = 1000

// Application writes 100 bytes
0.350 write(4, ..., 100) = 100
0.350 > P. 1:101(100) ack 1001

// ACK
0.500 < . 1001:1001(0) ack 101 win 257

// close the connection
0.600 close(4) = 0
0.600 > F. 101:101(0) ack 1001 win 244

// Our side is in FIN_WAIT_1 & waits for ack to fin
0.7 < . 1001:1001(0) ack 102 win 244

// Our side is in FIN_WAIT_2 with no outstanding data.
0.8 < F. 1001:1001(0) ack 102 win 244
0.8 > . 102:102(0) ack 1002 win 244

// Our side is now in TIME_WAIT state, send ack for fin.
0.9 < F. 1002:1002(0) ack 102 win 244
0.9 > . 102:102(0) ack 1002 win 244

// Peer reopens with in-window SYN:
1.000 < S 1000:1000(0) win 9200 <mss 1460,nop,nop,sackOK,nop,wscale 7>

// Therefore, reply with ACK.
1.000 > . 102:102(0) ack 1002 win 244

// Peer sends RST for this ACK.  Normally this RST results
// in tw socket removal, but rfc1337=1 setting prevents this.
1.100 < R 1002:1002(0) win 244

// second syn. Due to rfc1337=1 expect another pure ACK.
31.0 < S 1000:1000(0) win 9200 <mss 1460,nop,nop,sackOK,nop,wscale 7>
31.0 > . 102:102(0) ack 1002 win 244

// .. and another RST from peer.
31.1 < R 1002:1002(0) win 244
31.2 `echo no timer restart;ss -m -e -a -i -n -t -o state TIME-WAIT`

// third syn after one minute.  Time-Wait socket should have expired by now.
63.0 < S 1000:1000(0) win 9200 <mss 1460,nop,nop,sackOK,nop,wscale 7>

// so we expect a syn-ack & 3whs to proceed from here on.
63.0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 7>

Without this patch, 'ss' shows restarts of tw timer and last packet is
thus just another pure ack, more than one minute later.

This restores the original code from commit 283fd6cf0be690a83
("Merge in ANK networking jumbo patch") in netdev-vger-cvs.git .

For some reason the else branch was removed/lost in 1f28b683339f7
("Merge in TCP/UDP optimizations and [..]") and timer restart became
unconditional.

Reported-by: Michal Tesar <mtesar@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_minisocks.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 57b5468b5139..79e1b77bcd71 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -184,8 +184,9 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 				inet_twsk_deschedule_put(tw);
 				return TCP_TW_SUCCESS;
 			}
+		} else {
+			inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN);
 		}
-		inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN);
 
 		if (tmp_opt.saw_tstamp) {
 			tcptw->tw_ts_recent	  = tmp_opt.rcv_tsval;
-- 
2.13.6


From 798ff8964382a1d08f4e01648367092701a1572f Mon Sep 17 00:00:00 2001
From: Alexey Kodanev <alexey.kodanev@oracle.com>
Date: Thu, 23 Aug 2018 19:49:54 +0300
Subject: [PATCH 10/29] vti6: remove !skb->ignore_df check from vti6_xmit()

[ Upstream commit 9f2895461439fda2801a7906fb4c5fb3dbb37a0a ]

Before the commit d6990976af7c ("vti6: fix PMTU caching and reporting
on xmit") '!skb->ignore_df' check was always true because the function
skb_scrub_packet() was called before it, resetting ignore_df to zero.

In the commit, skb_scrub_packet() was moved below, and now this check
can be false for the packet, e.g. when sending it in the two fragments,
this prevents successful PMTU updates in such case. The next attempts
to send the packet lead to the same tx error. Moreover, vti6 initial
MTU value relies on PMTU adjustments.

This issue can be reproduced with the following LTP test script:
    udp_ipsec_vti.sh -6 -p ah -m tunnel -s 2000

Fixes: ccd740cbc6e0 ("vti6: Add pmtu handling to vti6_xmit.")
Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Acked-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_vti.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index ca957dd93a29..01dea2bfc59f 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -485,7 +485,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 	skb->dev = skb_dst(skb)->dev;
 
 	mtu = dst_mtu(dst);
-	if (!skb->ignore_df && skb->len > mtu) {
+	if (skb->len > mtu) {
 		skb_dst_update_pmtu(skb, mtu);
 
 		if (skb->protocol == htons(ETH_P_IPV6)) {
-- 
2.13.6


From 7a5598c4101e01934416d37b6652980902649c89 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sun, 19 Aug 2018 12:22:12 -0700
Subject: [PATCH 11/29] act_ife: move tcfa_lock down to where necessary

[ Upstream commit 4e407ff5cd67ec76eeeea1deec227b7982dc7f66 ]

The only time we need to take tcfa_lock is when adding
a new metainfo to an existing ife->metalist. We don't need
to take tcfa_lock so early and so broadly in tcf_ife_init().

This means we can always take ife_mod_lock first, avoid the
reverse locking ordering warning as reported by Vlad.

Reported-by: Vlad Buslov <vladbu@mellanox.com>
Tested-by: Vlad Buslov <vladbu@mellanox.com>
Cc: Vlad Buslov <vladbu@mellanox.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ife.c | 36 +++++++++++++-----------------------
 1 file changed, 13 insertions(+), 23 deletions(-)

diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 201e599baed9..fc4b6e18cd2d 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -265,10 +265,8 @@ static const char *ife_meta_id2name(u32 metaid)
 #endif
 
 /* called when adding new meta information
- * under ife->tcf_lock for existing action
 */
-static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid,
-				void *val, int len, bool exists)
+static int load_metaops_and_vet(u32 metaid, void *val, int len)
 {
 	struct tcf_meta_ops *ops = find_ife_oplist(metaid);
 	int ret = 0;
@@ -276,13 +274,9 @@ static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid,
 	if (!ops) {
 		ret = -ENOENT;
 #ifdef CONFIG_MODULES
-		if (exists)
-			spin_unlock_bh(&ife->tcf_lock);
 		rtnl_unlock();
 		request_module("ife-meta-%s", ife_meta_id2name(metaid));
 		rtnl_lock();
-		if (exists)
-			spin_lock_bh(&ife->tcf_lock);
 		ops = find_ife_oplist(metaid);
 #endif
 	}
@@ -299,10 +293,9 @@ static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid,
 }
 
 /* called when adding new meta information
- * under ife->tcf_lock for existing action
 */
 static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval,
-			int len, bool atomic)
+			int len, bool atomic, bool exists)
 {
 	struct tcf_meta_info *mi = NULL;
 	struct tcf_meta_ops *ops = find_ife_oplist(metaid);
@@ -329,12 +322,16 @@ static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval,
 		}
 	}
 
+	if (exists)
+		spin_lock_bh(&ife->tcf_lock);
 	list_add_tail(&mi->metalist, &ife->metalist);
+	if (exists)
+		spin_unlock_bh(&ife->tcf_lock);
 
 	return ret;
 }
 
-static int use_all_metadata(struct tcf_ife_info *ife)
+static int use_all_metadata(struct tcf_ife_info *ife, bool exists)
 {
 	struct tcf_meta_ops *o;
 	int rc = 0;
@@ -342,7 +339,7 @@ static int use_all_metadata(struct tcf_ife_info *ife)
 
 	read_lock(&ife_mod_lock);
 	list_for_each_entry(o, &ifeoplist, list) {
-		rc = add_metainfo(ife, o->metaid, NULL, 0, true);
+		rc = add_metainfo(ife, o->metaid, NULL, 0, true, exists);
 		if (rc == 0)
 			installed += 1;
 	}
@@ -419,7 +416,6 @@ static void tcf_ife_cleanup(struct tc_action *a)
 		kfree_rcu(p, rcu);
 }
 
-/* under ife->tcf_lock for existing action */
 static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb,
 			     bool exists)
 {
@@ -433,11 +429,11 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb,
 			val = nla_data(tb[i]);
 			len = nla_len(tb[i]);
 
-			rc = load_metaops_and_vet(ife, i, val, len, exists);
+			rc = load_metaops_and_vet(i, val, len);
 			if (rc != 0)
 				return rc;
 
-			rc = add_metainfo(ife, i, val, len, exists);
+			rc = add_metainfo(ife, i, val, len, false, exists);
 			if (rc)
 				return rc;
 		}
@@ -531,8 +527,6 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 		p->eth_type = ife_type;
 	}
 
-	if (exists)
-		spin_lock_bh(&ife->tcf_lock);
 
 	if (ret == ACT_P_CREATED)
 		INIT_LIST_HEAD(&ife->metalist);
@@ -544,9 +538,6 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 metadata_parse_err:
 			if (ret == ACT_P_CREATED)
 				tcf_idr_release(*a, bind);
-
-			if (exists)
-				spin_unlock_bh(&ife->tcf_lock);
 			kfree(p);
 			return err;
 		}
@@ -561,18 +552,17 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 		 * as we can. You better have at least one else we are
 		 * going to bail out
 		 */
-		err = use_all_metadata(ife);
+		err = use_all_metadata(ife, exists);
 		if (err) {
 			if (ret == ACT_P_CREATED)
 				tcf_idr_release(*a, bind);
-
-			if (exists)
-				spin_unlock_bh(&ife->tcf_lock);
 			kfree(p);
 			return err;
 		}
 	}
 
+	if (exists)
+		spin_lock_bh(&ife->tcf_lock);
 	ife->tcf_action = parm->action;
 	if (exists)
 		spin_unlock_bh(&ife->tcf_lock);
-- 
2.13.6


From d0820ab05e497303b58b577816ad832eb766e6d4 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sun, 19 Aug 2018 12:22:13 -0700
Subject: [PATCH 12/29] act_ife: fix a potential deadlock

[ Upstream commit 5ffe57da29b3802baeddaa40909682bbb4cb4d48 ]

use_all_metadata() acquires read_lock(&ife_mod_lock), then calls
add_metainfo() which calls find_ife_oplist() which acquires the same
lock again. Deadlock!

Introduce __add_metainfo() which accepts struct tcf_meta_ops *ops
as an additional parameter and let its callers to decide how
to find it. For use_all_metadata(), it already has ops, no
need to find it again, just call __add_metainfo() directly.

And, as ife_mod_lock is only needed for find_ife_oplist(),
this means we can make non-atomic allocation for populate_metalist()
now.

Fixes: 817e9f2c5c26 ("act_ife: acquire ife_mod_lock before reading ifeoplist")
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ife.c | 34 +++++++++++++++++++++-------------
 1 file changed, 21 insertions(+), 13 deletions(-)

diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index fc4b6e18cd2d..43ca04eb6108 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -294,22 +294,16 @@ static int load_metaops_and_vet(u32 metaid, void *val, int len)
 
 /* called when adding new meta information
 */
-static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval,
-			int len, bool atomic, bool exists)
+static int __add_metainfo(const struct tcf_meta_ops *ops,
+			  struct tcf_ife_info *ife, u32 metaid, void *metaval,
+			  int len, bool atomic, bool exists)
 {
 	struct tcf_meta_info *mi = NULL;
-	struct tcf_meta_ops *ops = find_ife_oplist(metaid);
 	int ret = 0;
 
-	if (!ops)
-		return -ENOENT;
-
 	mi = kzalloc(sizeof(*mi), atomic ? GFP_ATOMIC : GFP_KERNEL);
-	if (!mi) {
-		/*put back what find_ife_oplist took */
-		module_put(ops->owner);
+	if (!mi)
 		return -ENOMEM;
-	}
 
 	mi->metaid = metaid;
 	mi->ops = ops;
@@ -317,7 +311,6 @@ static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval,
 		ret = ops->alloc(mi, metaval, atomic ? GFP_ATOMIC : GFP_KERNEL);
 		if (ret != 0) {
 			kfree(mi);
-			module_put(ops->owner);
 			return ret;
 		}
 	}
@@ -331,6 +324,21 @@ static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval,
 	return ret;
 }
 
+static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval,
+			int len, bool exists)
+{
+	const struct tcf_meta_ops *ops = find_ife_oplist(metaid);
+	int ret;
+
+	if (!ops)
+		return -ENOENT;
+	ret = __add_metainfo(ops, ife, metaid, metaval, len, false, exists);
+	if (ret)
+		/*put back what find_ife_oplist took */
+		module_put(ops->owner);
+	return ret;
+}
+
 static int use_all_metadata(struct tcf_ife_info *ife, bool exists)
 {
 	struct tcf_meta_ops *o;
@@ -339,7 +347,7 @@ static int use_all_metadata(struct tcf_ife_info *ife, bool exists)
 
 	read_lock(&ife_mod_lock);
 	list_for_each_entry(o, &ifeoplist, list) {
-		rc = add_metainfo(ife, o->metaid, NULL, 0, true, exists);
+		rc = __add_metainfo(o, ife, o->metaid, NULL, 0, true, exists);
 		if (rc == 0)
 			installed += 1;
 	}
@@ -433,7 +441,7 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb,
 			if (rc != 0)
 				return rc;
 
-			rc = add_metainfo(ife, i, val, len, false, exists);
+			rc = add_metainfo(ife, i, val, len, exists);
 			if (rc)
 				return rc;
 		}
-- 
2.13.6


From ccd552208d2412484268cde35d93db1410bb69f8 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Tue, 4 Sep 2018 00:44:42 +0300
Subject: [PATCH 13/29] net: sched: action_ife: take reference to meta module

[ Upstream commit 84cb8eb26cb9ce3c79928094962a475a9d850a53 ]

Recent refactoring of add_metainfo() caused use_all_metadata() to add
metainfo to ife action metalist without taking reference to module. This
causes warning in module_put called from ife action cleanup function.

Implement add_metainfo_and_get_ops() function that returns with reference
to module taken if metainfo was added successfully, and call it from
use_all_metadata(), instead of calling __add_metainfo() directly.

Example warning:

[  646.344393] WARNING: CPU: 1 PID: 2278 at kernel/module.c:1139 module_put+0x1cb/0x230
[  646.352437] Modules linked in: act_meta_skbtcindex act_meta_mark act_meta_skbprio act_ife ife veth nfsv3 nfs fscache xt_CHECKSUM iptable_mangle ipt_MASQUERADE iptable_nat nf_nat_ipv4 nf_nat xt_conntrack nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 libcrc32c tun ebtable_filter ebtables ip6table_filter ip6_tables bridge stp llc mlx5_ib ib_uverbs ib_core intel_rapl sb_edac x86_pkg_temp_thermal mlx5_core coretemp kvm_intel kvm nfsd igb irqbypass crct10dif_pclmul devlink crc32_pclmul mei_me joydev ses crc32c_intel enclosure auth_rpcgss i2c_algo_bit ioatdma ptp mei pps_core ghash_clmulni_intel iTCO_wdt iTCO_vendor_support pcspkr dca ipmi_ssif lpc_ich target_core_mod i2c_i801 ipmi_si ipmi_devintf pcc_cpufreq wmi ipmi_msghandler nfs_acl lockd acpi_pad acpi_power_meter grace sunrpc mpt3sas raid_class scsi_transport_sas
[  646.425631] CPU: 1 PID: 2278 Comm: tc Not tainted 4.19.0-rc1+ #799
[  646.432187] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017
[  646.440595] RIP: 0010:module_put+0x1cb/0x230
[  646.445238] Code: f3 66 94 02 e8 26 ff fa ff 85 c0 74 11 0f b6 1d 51 30 94 02 80 fb 01 77 60 83 e3 01 74 13 65 ff 0d 3a 83 db 73 e9 2b ff ff ff <0f> 0b e9 00 ff ff ff e8 59 01 fb ff 85 c0 75 e4 48 c7 c2 20 62 6b
[  646.464997] RSP: 0018:ffff880354d37068 EFLAGS: 00010286
[  646.470599] RAX: 0000000000000000 RBX: ffffffffc0a52518 RCX: ffffffff8c2668db
[  646.478118] RDX: 0000000000000003 RSI: dffffc0000000000 RDI: ffffffffc0a52518
[  646.485641] RBP: ffffffffc0a52180 R08: fffffbfff814a4a4 R09: fffffbfff814a4a3
[  646.493164] R10: ffffffffc0a5251b R11: fffffbfff814a4a4 R12: 1ffff1006a9a6e0d
[  646.500687] R13: 00000000ffffffff R14: ffff880362bab890 R15: dead000000000100
[  646.508213] FS:  00007f4164c99800(0000) GS:ffff88036fe40000(0000) knlGS:0000000000000000
[  646.516961] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  646.523080] CR2: 00007f41638b8420 CR3: 0000000351df0004 CR4: 00000000001606e0
[  646.530595] Call Trace:
[  646.533408]  ? find_symbol_in_section+0x260/0x260
[  646.538509]  tcf_ife_cleanup+0x11b/0x200 [act_ife]
[  646.543695]  tcf_action_cleanup+0x29/0xa0
[  646.548078]  __tcf_action_put+0x5a/0xb0
[  646.552289]  ? nla_put+0x65/0xe0
[  646.555889]  __tcf_idr_release+0x48/0x60
[  646.560187]  tcf_generic_walker+0x448/0x6b0
[  646.564764]  ? tcf_action_dump_1+0x450/0x450
[  646.569411]  ? __lock_is_held+0x84/0x110
[  646.573720]  ? tcf_ife_walker+0x10c/0x20f [act_ife]
[  646.578982]  tca_action_gd+0x972/0xc40
[  646.583129]  ? tca_get_fill.constprop.17+0x250/0x250
[  646.588471]  ? mark_lock+0xcf/0x980
[  646.592324]  ? check_chain_key+0x140/0x1f0
[  646.596832]  ? debug_show_all_locks+0x240/0x240
[  646.601839]  ? memset+0x1f/0x40
[  646.605350]  ? nla_parse+0xca/0x1a0
[  646.609217]  tc_ctl_action+0x215/0x230
[  646.613339]  ? tcf_action_add+0x220/0x220
[  646.617748]  rtnetlink_rcv_msg+0x56a/0x6d0
[  646.622227]  ? rtnl_fdb_del+0x3f0/0x3f0
[  646.626466]  netlink_rcv_skb+0x18d/0x200
[  646.630752]  ? rtnl_fdb_del+0x3f0/0x3f0
[  646.634959]  ? netlink_ack+0x500/0x500
[  646.639106]  netlink_unicast+0x2d0/0x370
[  646.643409]  ? netlink_attachskb+0x340/0x340
[  646.648050]  ? _copy_from_iter_full+0xe9/0x3e0
[  646.652870]  ? import_iovec+0x11e/0x1c0
[  646.657083]  netlink_sendmsg+0x3b9/0x6a0
[  646.661388]  ? netlink_unicast+0x370/0x370
[  646.665877]  ? netlink_unicast+0x370/0x370
[  646.670351]  sock_sendmsg+0x6b/0x80
[  646.674212]  ___sys_sendmsg+0x4a1/0x520
[  646.678443]  ? copy_msghdr_from_user+0x210/0x210
[  646.683463]  ? lock_downgrade+0x320/0x320
[  646.687849]  ? debug_show_all_locks+0x240/0x240
[  646.692760]  ? do_raw_spin_unlock+0xa2/0x130
[  646.697418]  ? _raw_spin_unlock+0x24/0x30
[  646.701798]  ? __handle_mm_fault+0x1819/0x1c10
[  646.706619]  ? __pmd_alloc+0x320/0x320
[  646.710738]  ? debug_show_all_locks+0x240/0x240
[  646.715649]  ? restore_nameidata+0x7b/0xa0
[  646.720117]  ? check_chain_key+0x140/0x1f0
[  646.724590]  ? check_chain_key+0x140/0x1f0
[  646.729070]  ? __fget_light+0xbc/0xd0
[  646.733121]  ? __sys_sendmsg+0xd7/0x150
[  646.737329]  __sys_sendmsg+0xd7/0x150
[  646.741359]  ? __ia32_sys_shutdown+0x30/0x30
[  646.746003]  ? up_read+0x53/0x90
[  646.749601]  ? __do_page_fault+0x484/0x780
[  646.754105]  ? do_syscall_64+0x1e/0x2c0
[  646.758320]  do_syscall_64+0x72/0x2c0
[  646.762353]  entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  646.767776] RIP: 0033:0x7f4163872150
[  646.771713] Code: 8b 15 3c 7d 2b 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb cd 66 0f 1f 44 00 00 83 3d b9 d5 2b 00 00 75 10 b8 2e 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be cd 00 00 48 89 04 24
[  646.791474] RSP: 002b:00007ffdef7d6b58 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
[  646.799721] RAX: ffffffffffffffda RBX: 0000000000000024 RCX: 00007f4163872150
[  646.807240] RDX: 0000000000000000 RSI: 00007ffdef7d6bd0 RDI: 0000000000000003
[  646.814760] RBP: 000000005b8b9482 R08: 0000000000000001 R09: 0000000000000000
[  646.822286] R10: 00000000000005e7 R11: 0000000000000246 R12: 00007ffdef7dad20
[  646.829807] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000679bc0
[  646.837360] irq event stamp: 6083
[  646.841043] hardirqs last  enabled at (6081): [<ffffffff8c220a7d>] __call_rcu+0x17d/0x500
[  646.849882] hardirqs last disabled at (6083): [<ffffffff8c004f06>] trace_hardirqs_off_thunk+0x1a/0x1c
[  646.859775] softirqs last  enabled at (5968): [<ffffffff8d4004a1>] __do_softirq+0x4a1/0x6ee
[  646.868784] softirqs last disabled at (6082): [<ffffffffc0a78759>] tcf_ife_cleanup+0x39/0x200 [act_ife]
[  646.878845] ---[ end trace b1b8c12ffe51e657 ]---

Fixes: 5ffe57da29b3 ("act_ife: fix a potential deadlock")
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ife.c | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 43ca04eb6108..005cb21348c9 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -324,6 +324,20 @@ static int __add_metainfo(const struct tcf_meta_ops *ops,
 	return ret;
 }
 
+static int add_metainfo_and_get_ops(const struct tcf_meta_ops *ops,
+				    struct tcf_ife_info *ife, u32 metaid,
+				    bool exists)
+{
+	int ret;
+
+	if (!try_module_get(ops->owner))
+		return -ENOENT;
+	ret = __add_metainfo(ops, ife, metaid, NULL, 0, true, exists);
+	if (ret)
+		module_put(ops->owner);
+	return ret;
+}
+
 static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval,
 			int len, bool exists)
 {
@@ -347,7 +361,7 @@ static int use_all_metadata(struct tcf_ife_info *ife, bool exists)
 
 	read_lock(&ife_mod_lock);
 	list_for_each_entry(o, &ifeoplist, list) {
-		rc = __add_metainfo(o, ife, o->metaid, NULL, 0, true, exists);
+		rc = add_metainfo_and_get_ops(o, ife, o->metaid, exists);
 		if (rc == 0)
 			installed += 1;
 	}
-- 
2.13.6


From 59d01dfae69374deb58e476fad95e5853ed83edc Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Mon, 3 Sep 2018 04:23:18 -0400
Subject: [PATCH 14/29] bnxt_en: Clean up unused functions.

[ Upstream commit ad95c27bdb930105f3eea02621bda157caf2862d ]

Remove unused bnxt_subtract_ulp_resources().  Change
bnxt_get_max_func_irqs() to static since it is only locally used.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c     |  2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt.h     |  1 -
 drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c | 15 ---------------
 drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h |  1 -
 4 files changed, 1 insertion(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index cb026e500127..e94dead76af3 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -5908,7 +5908,7 @@ void bnxt_set_max_func_cp_rings(struct bnxt *bp, unsigned int max)
 	bp->hw_resc.max_cp_rings = max;
 }
 
-unsigned int bnxt_get_max_func_irqs(struct bnxt *bp)
+static unsigned int bnxt_get_max_func_irqs(struct bnxt *bp)
 {
 	struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 79bce5dcf7fe..c19a0123dcf7 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1454,7 +1454,6 @@ unsigned int bnxt_get_max_func_stat_ctxs(struct bnxt *bp);
 void bnxt_set_max_func_stat_ctxs(struct bnxt *bp, unsigned int max);
 unsigned int bnxt_get_max_func_cp_rings(struct bnxt *bp);
 void bnxt_set_max_func_cp_rings(struct bnxt *bp, unsigned int max);
-unsigned int bnxt_get_max_func_irqs(struct bnxt *bp);
 int bnxt_get_avail_msix(struct bnxt *bp, int num);
 int bnxt_reserve_rings(struct bnxt *bp);
 void bnxt_tx_disable(struct bnxt *bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index 840f6e505f73..ba8f8e6af363 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -220,21 +220,6 @@ int bnxt_get_ulp_msix_base(struct bnxt *bp)
 	return 0;
 }
 
-void bnxt_subtract_ulp_resources(struct bnxt *bp, int ulp_id)
-{
-	ASSERT_RTNL();
-	if (bnxt_ulp_registered(bp->edev, ulp_id)) {
-		struct bnxt_en_dev *edev = bp->edev;
-		unsigned int msix_req, max;
-
-		msix_req = edev->ulp_tbl[ulp_id].msix_requested;
-		max = bnxt_get_max_func_cp_rings(bp);
-		bnxt_set_max_func_cp_rings(bp, max - msix_req);
-		max = bnxt_get_max_func_stat_ctxs(bp);
-		bnxt_set_max_func_stat_ctxs(bp, max - 1);
-	}
-}
-
 static int bnxt_send_msg(struct bnxt_en_dev *edev, int ulp_id,
 			 struct bnxt_fw_msg *fw_msg)
 {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
index df48ac71729f..d9bea37cd211 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
@@ -90,7 +90,6 @@ static inline bool bnxt_ulp_registered(struct bnxt_en_dev *edev, int ulp_id)
 
 int bnxt_get_ulp_msix_num(struct bnxt *bp);
 int bnxt_get_ulp_msix_base(struct bnxt *bp);
-void bnxt_subtract_ulp_resources(struct bnxt *bp, int ulp_id);
 void bnxt_ulp_stop(struct bnxt *bp);
 void bnxt_ulp_start(struct bnxt *bp);
 void bnxt_ulp_sriov_cfg(struct bnxt *bp, int num_vfs);
-- 
2.13.6


From 723d0bb874e2ba98b648587dcd07f011466ac661 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Mon, 3 Sep 2018 04:23:19 -0400
Subject: [PATCH 15/29] bnxt_en: Do not adjust max_cp_rings by the ones used by
 RDMA.

[ Upstream commit 00fe9c326d2027f2437dea38ef0e82f9d02d94c0 ]

Currently, the driver adjusts the bp->hw_resc.max_cp_rings by the number
of MSIX vectors used by RDMA.  There is one code path in open that needs
to check the true max_cp_rings including any used by RDMA.  This code
is now checking for the reduced max_cp_rings which will fail when the
number of cp rings is very small.

To fix this in a clean way, we don't adjust max_cp_rings anymore.
Instead, we add a helper bnxt_get_max_func_cp_rings_for_en() to get the
reduced max_cp_rings when appropriate.

Fixes: ec86f14ea506 ("bnxt_en: Add ULP calls to stop and restart IRQs.")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c       | 7 ++++---
 drivers/net/ethernet/broadcom/bnxt/bnxt.h       | 2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c | 7 ++++---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c   | 5 -----
 4 files changed, 9 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index e94dead76af3..cfba20d72935 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -5903,9 +5903,9 @@ unsigned int bnxt_get_max_func_cp_rings(struct bnxt *bp)
 	return bp->hw_resc.max_cp_rings;
 }
 
-void bnxt_set_max_func_cp_rings(struct bnxt *bp, unsigned int max)
+unsigned int bnxt_get_max_func_cp_rings_for_en(struct bnxt *bp)
 {
-	bp->hw_resc.max_cp_rings = max;
+	return bp->hw_resc.max_cp_rings - bnxt_get_ulp_msix_num(bp);
 }
 
 static unsigned int bnxt_get_max_func_irqs(struct bnxt *bp)
@@ -8452,7 +8452,8 @@ static void _bnxt_get_max_rings(struct bnxt *bp, int *max_rx, int *max_tx,
 
 	*max_tx = hw_resc->max_tx_rings;
 	*max_rx = hw_resc->max_rx_rings;
-	*max_cp = min_t(int, hw_resc->max_irqs, hw_resc->max_cp_rings);
+	*max_cp = min_t(int, bnxt_get_max_func_cp_rings_for_en(bp),
+			hw_resc->max_irqs);
 	*max_cp = min_t(int, *max_cp, hw_resc->max_stat_ctxs);
 	max_ring_grps = hw_resc->max_hw_ring_grps;
 	if (BNXT_CHIP_TYPE_NITRO_A0(bp) && BNXT_PF(bp)) {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index c19a0123dcf7..dad418ff0ca4 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1453,7 +1453,7 @@ int bnxt_hwrm_set_coal(struct bnxt *);
 unsigned int bnxt_get_max_func_stat_ctxs(struct bnxt *bp);
 void bnxt_set_max_func_stat_ctxs(struct bnxt *bp, unsigned int max);
 unsigned int bnxt_get_max_func_cp_rings(struct bnxt *bp);
-void bnxt_set_max_func_cp_rings(struct bnxt *bp, unsigned int max);
+unsigned int bnxt_get_max_func_cp_rings_for_en(struct bnxt *bp);
 int bnxt_get_avail_msix(struct bnxt *bp, int num);
 int bnxt_reserve_rings(struct bnxt *bp);
 void bnxt_tx_disable(struct bnxt *bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index e1f025b2a6bc..31346b7c04a8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -451,7 +451,7 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs)
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_VF_RESOURCE_CFG, -1, -1);
 
-	vf_cp_rings = hw_resc->max_cp_rings - bp->cp_nr_rings;
+	vf_cp_rings = bnxt_get_max_func_cp_rings_for_en(bp) - bp->cp_nr_rings;
 	vf_stat_ctx = hw_resc->max_stat_ctxs - bp->num_stat_ctxs;
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		vf_rx_rings = hw_resc->max_rx_rings - bp->rx_nr_rings * 2;
@@ -544,7 +544,8 @@ static int bnxt_hwrm_func_cfg(struct bnxt *bp, int num_vfs)
 	max_stat_ctxs = hw_resc->max_stat_ctxs;
 
 	/* Remaining rings are distributed equally amongs VF's for now */
-	vf_cp_rings = (hw_resc->max_cp_rings - bp->cp_nr_rings) / num_vfs;
+	vf_cp_rings = (bnxt_get_max_func_cp_rings_for_en(bp) -
+		       bp->cp_nr_rings) / num_vfs;
 	vf_stat_ctx = (max_stat_ctxs - bp->num_stat_ctxs) / num_vfs;
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		vf_rx_rings = (hw_resc->max_rx_rings - bp->rx_nr_rings * 2) /
@@ -638,7 +639,7 @@ static int bnxt_sriov_enable(struct bnxt *bp, int *num_vfs)
 	 */
 	vfs_supported = *num_vfs;
 
-	avail_cp = hw_resc->max_cp_rings - bp->cp_nr_rings;
+	avail_cp = bnxt_get_max_func_cp_rings_for_en(bp) - bp->cp_nr_rings;
 	avail_stat = hw_resc->max_stat_ctxs - bp->num_stat_ctxs;
 	avail_cp = min_t(int, avail_cp, avail_stat);
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index ba8f8e6af363..4209cfd73971 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -169,7 +169,6 @@ static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, int ulp_id,
 		edev->ulp_tbl[ulp_id].msix_requested = avail_msix;
 	}
 	bnxt_fill_msix_vecs(bp, ent);
-	bnxt_set_max_func_cp_rings(bp, max_cp_rings - avail_msix);
 	edev->flags |= BNXT_EN_FLAG_MSIX_REQUESTED;
 	return avail_msix;
 }
@@ -178,7 +177,6 @@ static int bnxt_free_msix_vecs(struct bnxt_en_dev *edev, int ulp_id)
 {
 	struct net_device *dev = edev->net;
 	struct bnxt *bp = netdev_priv(dev);
-	int max_cp_rings, msix_requested;
 
 	ASSERT_RTNL();
 	if (ulp_id != BNXT_ROCE_ULP)
@@ -187,9 +185,6 @@ static int bnxt_free_msix_vecs(struct bnxt_en_dev *edev, int ulp_id)
 	if (!(edev->flags & BNXT_EN_FLAG_MSIX_REQUESTED))
 		return 0;
 
-	max_cp_rings = bnxt_get_max_func_cp_rings(bp);
-	msix_requested = edev->ulp_tbl[ulp_id].msix_requested;
-	bnxt_set_max_func_cp_rings(bp, max_cp_rings + msix_requested);
 	edev->ulp_tbl[ulp_id].msix_requested = 0;
 	edev->flags &= ~BNXT_EN_FLAG_MSIX_REQUESTED;
 	if (netif_running(dev)) {
-- 
2.13.6


From e4b528654979d1ec791fb4495c1cffbda1976f27 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Mon, 27 Aug 2018 22:56:22 +0200
Subject: [PATCH 16/29] net/sched: act_pedit: fix dump of extended layered op

[ Upstream commit 85eb9af182243ce9a8b72410d5321c440ac5f8d7 ]

in the (rare) case of failure in nla_nest_start(), missing NULL checks in
tcf_pedit_key_ex_dump() can make the following command

 # tc action add action pedit ex munge ip ttl set 64

dereference a NULL pointer:

 BUG: unable to handle kernel NULL pointer dereference at 0000000000000000
 PGD 800000007d1cd067 P4D 800000007d1cd067 PUD 7acd3067 PMD 0
 Oops: 0002 [#1] SMP PTI
 CPU: 0 PID: 3336 Comm: tc Tainted: G            E     4.18.0.pedit+ #425
 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
 RIP: 0010:tcf_pedit_dump+0x19d/0x358 [act_pedit]
 Code: be 02 00 00 00 48 89 df 66 89 44 24 20 e8 9b b1 fd e0 85 c0 75 46 8b 83 c8 00 00 00 49 83 c5 08 48 03 83 d0 00 00 00 4d 39 f5 <66> 89 04 25 00 00 00 00 0f 84 81 01 00 00 41 8b 45 00 48 8d 4c 24
 RSP: 0018:ffffb5d4004478a8 EFLAGS: 00010246
 RAX: ffff8880fcda2070 RBX: ffff8880fadd2900 RCX: 0000000000000000
 RDX: 0000000000000002 RSI: ffffb5d4004478ca RDI: ffff8880fcda206e
 RBP: ffff8880fb9cb900 R08: 0000000000000008 R09: ffff8880fcda206e
 R10: ffff8880fadd2900 R11: 0000000000000000 R12: ffff8880fd26cf40
 R13: ffff8880fc957430 R14: ffff8880fc957430 R15: ffff8880fb9cb988
 FS:  00007f75a537a740(0000) GS:ffff8880fda00000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000000000 CR3: 000000007a2fa005 CR4: 00000000001606f0
 Call Trace:
  ? __nla_reserve+0x38/0x50
  tcf_action_dump_1+0xd2/0x130
  tcf_action_dump+0x6a/0xf0
  tca_get_fill.constprop.31+0xa3/0x120
  tcf_action_add+0xd1/0x170
  tc_ctl_action+0x137/0x150
  rtnetlink_rcv_msg+0x263/0x2d0
  ? _cond_resched+0x15/0x40
  ? rtnl_calcit.isra.30+0x110/0x110
  netlink_rcv_skb+0x4d/0x130
  netlink_unicast+0x1a3/0x250
  netlink_sendmsg+0x2ae/0x3a0
  sock_sendmsg+0x36/0x40
  ___sys_sendmsg+0x26f/0x2d0
  ? do_wp_page+0x8e/0x5f0
  ? handle_pte_fault+0x6c3/0xf50
  ? __handle_mm_fault+0x38e/0x520
  ? __sys_sendmsg+0x5e/0xa0
  __sys_sendmsg+0x5e/0xa0
  do_syscall_64+0x5b/0x180
  entry_SYSCALL_64_after_hwframe+0x44/0xa9
 RIP: 0033:0x7f75a4583ba0
 Code: c3 48 8b 05 f2 62 2c 00 f7 db 64 89 18 48 83 cb ff eb dd 0f 1f 80 00 00 00 00 83 3d fd c3 2c 00 00 75 10 b8 2e 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 ae cc 00 00 48 89 04 24
 RSP: 002b:00007fff60ee7418 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
 RAX: ffffffffffffffda RBX: 00007fff60ee7540 RCX: 00007f75a4583ba0
 RDX: 0000000000000000 RSI: 00007fff60ee7490 RDI: 0000000000000003
 RBP: 000000005b842d3e R08: 0000000000000002 R09: 0000000000000000
 R10: 00007fff60ee6ea0 R11: 0000000000000246 R12: 0000000000000000
 R13: 00007fff60ee7554 R14: 0000000000000001 R15: 000000000066c100
 Modules linked in: act_pedit(E) ip6table_filter ip6_tables iptable_filter binfmt_misc crct10dif_pclmul ext4 crc32_pclmul mbcache ghash_clmulni_intel jbd2 pcbc snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hda_core snd_hwdep snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd snd_timer cryptd glue_helper snd joydev pcspkr soundcore virtio_balloon i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c ata_generic pata_acpi virtio_net net_failover virtio_blk virtio_console failover qxl crc32c_intel drm_kms_helper syscopyarea serio_raw sysfillrect sysimgblt fb_sys_fops ttm drm ata_piix virtio_pci libata virtio_ring i2c_core virtio floppy dm_mirror dm_region_hash dm_log dm_mod [last unloaded: act_pedit]
 CR2: 0000000000000000

Like it's done for other TC actions, give up dumping pedit rules and return
an error if nla_nest_start() returns NULL.

Fixes: 71d0ed7079df ("net/act_pedit: Support using offset relative to the conventional network headers")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_pedit.c | 18 +++++++++++++-----
 1 file changed, 13 insertions(+), 5 deletions(-)

diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 8a925c72db5f..bad475c87688 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -109,16 +109,18 @@ static int tcf_pedit_key_ex_dump(struct sk_buff *skb,
 {
 	struct nlattr *keys_start = nla_nest_start(skb, TCA_PEDIT_KEYS_EX);
 
+	if (!keys_start)
+		goto nla_failure;
 	for (; n > 0; n--) {
 		struct nlattr *key_start;
 
 		key_start = nla_nest_start(skb, TCA_PEDIT_KEY_EX);
+		if (!key_start)
+			goto nla_failure;
 
 		if (nla_put_u16(skb, TCA_PEDIT_KEY_EX_HTYPE, keys_ex->htype) ||
-		    nla_put_u16(skb, TCA_PEDIT_KEY_EX_CMD, keys_ex->cmd)) {
-			nlmsg_trim(skb, keys_start);
-			return -EINVAL;
-		}
+		    nla_put_u16(skb, TCA_PEDIT_KEY_EX_CMD, keys_ex->cmd))
+			goto nla_failure;
 
 		nla_nest_end(skb, key_start);
 
@@ -128,6 +130,9 @@ static int tcf_pedit_key_ex_dump(struct sk_buff *skb,
 	nla_nest_end(skb, keys_start);
 
 	return 0;
+nla_failure:
+	nla_nest_cancel(skb, keys_start);
+	return -EINVAL;
 }
 
 static int tcf_pedit_init(struct net *net, struct nlattr *nla,
@@ -395,7 +400,10 @@ static int tcf_pedit_dump(struct sk_buff *skb, struct tc_action *a,
 	opt->bindcnt = p->tcf_bindcnt - bind;
 
 	if (p->tcfp_keys_ex) {
-		tcf_pedit_key_ex_dump(skb, p->tcfp_keys_ex, p->tcfp_nkeys);
+		if (tcf_pedit_key_ex_dump(skb,
+					  p->tcfp_keys_ex,
+					  p->tcfp_nkeys))
+			goto nla_put_failure;
 
 		if (nla_put(skb, TCA_PEDIT_PARMS_EX, s, opt))
 			goto nla_put_failure;
-- 
2.13.6


From 524ce3d8ece2a4e713faee0f50460cfe5311e460 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 23 Aug 2018 16:19:44 -0700
Subject: [PATCH 17/29] tipc: fix a missing rhashtable_walk_exit()

[ Upstream commit bd583fe30427500a2d0abe25724025b1cb5e2636 ]

rhashtable_walk_exit() must be paired with rhashtable_walk_enter().

Fixes: 40f9f4397060 ("tipc: Fix tipc_sk_reinit race conditions")
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/socket.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 6be21575503a..dacd356186f8 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2675,6 +2675,8 @@ void tipc_sk_reinit(struct net *net)
 
 		rhashtable_walk_stop(&iter);
 	} while (tsk == ERR_PTR(-EAGAIN));
+
+	rhashtable_walk_exit(&iter);
 }
 
 static struct tipc_sock *tipc_sk_lookup(struct net *net, u32 portid)
-- 
2.13.6


From 5e43e70c878a30ad99b86782d58a4b610e284e6f Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 29 Aug 2018 12:46:08 -0700
Subject: [PATCH 18/29] nfp: wait for posted reconfigs when disabling the
 device

[ Upstream commit 9ad716b95fd6c6be46a4f2d5936e514b5bcd744d ]

To avoid leaking a running timer we need to wait for the
posted reconfigs after netdev is unregistered.  In common
case the process of deinitializing the device will perform
synchronous reconfigs which wait for posted requests, but
especially with VXLAN ports being actively added and removed
there can be a race condition leaving a timer running after
adapter structure is freed leading to a crash.

Add an explicit flush after deregistering and for a good
measure a warning to check if timer is running just before
structures are freed.

Fixes: 3d780b926a12 ("nfp: add async reconfiguration mechanism")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/netronome/nfp/nfp_net_common.c    | 48 +++++++++++++++-------
 1 file changed, 33 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 1eb6549f2a54..47b77fee8419 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -227,29 +227,16 @@ static void nfp_net_reconfig_post(struct nfp_net *nn, u32 update)
 	spin_unlock_bh(&nn->reconfig_lock);
 }
 
-/**
- * nfp_net_reconfig() - Reconfigure the firmware
- * @nn:      NFP Net device to reconfigure
- * @update:  The value for the update field in the BAR config
- *
- * Write the update word to the BAR and ping the reconfig queue.  The
- * poll until the firmware has acknowledged the update by zeroing the
- * update word.
- *
- * Return: Negative errno on error, 0 on success
- */
-int nfp_net_reconfig(struct nfp_net *nn, u32 update)
+static void nfp_net_reconfig_sync_enter(struct nfp_net *nn)
 {
 	bool cancelled_timer = false;
 	u32 pre_posted_requests;
-	int ret;
 
 	spin_lock_bh(&nn->reconfig_lock);
 
 	nn->reconfig_sync_present = true;
 
 	if (nn->reconfig_timer_active) {
-		del_timer(&nn->reconfig_timer);
 		nn->reconfig_timer_active = false;
 		cancelled_timer = true;
 	}
@@ -258,14 +245,43 @@ int nfp_net_reconfig(struct nfp_net *nn, u32 update)
 
 	spin_unlock_bh(&nn->reconfig_lock);
 
-	if (cancelled_timer)
+	if (cancelled_timer) {
+		del_timer_sync(&nn->reconfig_timer);
 		nfp_net_reconfig_wait(nn, nn->reconfig_timer.expires);
+	}
 
 	/* Run the posted reconfigs which were issued before we started */
 	if (pre_posted_requests) {
 		nfp_net_reconfig_start(nn, pre_posted_requests);
 		nfp_net_reconfig_wait(nn, jiffies + HZ * NFP_NET_POLL_TIMEOUT);
 	}
+}
+
+static void nfp_net_reconfig_wait_posted(struct nfp_net *nn)
+{
+	nfp_net_reconfig_sync_enter(nn);
+
+	spin_lock_bh(&nn->reconfig_lock);
+	nn->reconfig_sync_present = false;
+	spin_unlock_bh(&nn->reconfig_lock);
+}
+
+/**
+ * nfp_net_reconfig() - Reconfigure the firmware
+ * @nn:      NFP Net device to reconfigure
+ * @update:  The value for the update field in the BAR config
+ *
+ * Write the update word to the BAR and ping the reconfig queue.  The
+ * poll until the firmware has acknowledged the update by zeroing the
+ * update word.
+ *
+ * Return: Negative errno on error, 0 on success
+ */
+int nfp_net_reconfig(struct nfp_net *nn, u32 update)
+{
+	int ret;
+
+	nfp_net_reconfig_sync_enter(nn);
 
 	nfp_net_reconfig_start(nn, update);
 	ret = nfp_net_reconfig_wait(nn, jiffies + HZ * NFP_NET_POLL_TIMEOUT);
@@ -3590,6 +3606,7 @@ struct nfp_net *nfp_net_alloc(struct pci_dev *pdev, bool needs_netdev,
  */
 void nfp_net_free(struct nfp_net *nn)
 {
+	WARN_ON(timer_pending(&nn->reconfig_timer) || nn->reconfig_posted);
 	if (nn->dp.netdev)
 		free_netdev(nn->dp.netdev);
 	else
@@ -3874,4 +3891,5 @@ void nfp_net_clean(struct nfp_net *nn)
 		return;
 
 	unregister_netdev(nn->dp.netdev);
+	nfp_net_reconfig_wait_posted(nn);
 }
-- 
2.13.6


From df473229beaeaf3d35937adfb3a156b7697bbc89 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 27 Aug 2018 18:38:31 +0800
Subject: [PATCH 19/29] sctp: hold transport before accessing its asoc in
 sctp_transport_get_next

[ Upstream commit bab1be79a5169ac748d8292b20c86d874022d7ba ]

As Marcelo noticed, in sctp_transport_get_next, it is iterating over
transports but then also accessing the association directly, without
checking any refcnts before that, which can cause an use-after-free
Read.

So fix it by holding transport before accessing the association. With
that, sctp_transport_hold calls can be removed in the later places.

Fixes: 626d16f50f39 ("sctp: export some apis or variables for sctp_diag and reuse some for proc")
Reported-by: syzbot+fe62a0c9aa6a85c6de16@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/proc.c   |  4 ----
 net/sctp/socket.c | 22 +++++++++++++++-------
 2 files changed, 15 insertions(+), 11 deletions(-)

diff --git a/net/sctp/proc.c b/net/sctp/proc.c
index 1d9ccc6dab2b..65c9189f8f6b 100644
--- a/net/sctp/proc.c
+++ b/net/sctp/proc.c
@@ -292,8 +292,6 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v)
 	}
 
 	transport = (struct sctp_transport *)v;
-	if (!sctp_transport_hold(transport))
-		return 0;
 	assoc = transport->asoc;
 	epb = &assoc->base;
 	sk = epb->sk;
@@ -364,8 +362,6 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v)
 	}
 
 	transport = (struct sctp_transport *)v;
-	if (!sctp_transport_hold(transport))
-		return 0;
 	assoc = transport->asoc;
 
 	list_for_each_entry_rcu(tsp, &assoc->peer.transport_addr_list,
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index ae7e7c606f72..d42f2242f1b1 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4886,9 +4886,14 @@ struct sctp_transport *sctp_transport_get_next(struct net *net,
 			break;
 		}
 
+		if (!sctp_transport_hold(t))
+			continue;
+
 		if (net_eq(sock_net(t->asoc->base.sk), net) &&
 		    t->asoc->peer.primary_path == t)
 			break;
+
+		sctp_transport_put(t);
 	}
 
 	return t;
@@ -4898,13 +4903,18 @@ struct sctp_transport *sctp_transport_get_idx(struct net *net,
 					      struct rhashtable_iter *iter,
 					      int pos)
 {
-	void *obj = SEQ_START_TOKEN;
+	struct sctp_transport *t;
 
-	while (pos && (obj = sctp_transport_get_next(net, iter)) &&
-	       !IS_ERR(obj))
-		pos--;
+	if (!pos)
+		return SEQ_START_TOKEN;
 
-	return obj;
+	while ((t = sctp_transport_get_next(net, iter)) && !IS_ERR(t)) {
+		if (!--pos)
+			break;
+		sctp_transport_put(t);
+	}
+
+	return t;
 }
 
 int sctp_for_each_endpoint(int (*cb)(struct sctp_endpoint *, void *),
@@ -4963,8 +4973,6 @@ int sctp_for_each_transport(int (*cb)(struct sctp_transport *, void *),
 
 	tsp = sctp_transport_get_idx(net, &hti, *pos + 1);
 	for (; !IS_ERR_OR_NULL(tsp); tsp = sctp_transport_get_next(net, &hti)) {
-		if (!sctp_transport_hold(tsp))
-			continue;
 		ret = cb(tsp, p);
 		if (ret)
 			break;
-- 
2.13.6


From c13e4dc4b8882c7f294d25bdf04dc3f7f72e44eb Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Fri, 24 Aug 2018 15:41:35 +0300
Subject: [PATCH 20/29] mlxsw: spectrum_switchdev: Do not leak RIFs when
 removing bridge

[ Upstream commit 602b74eda81311dbdb5dbab08c30f789f648ebdc ]

When a bridge device is removed, the VLANs are flushed from each
configured port. This causes the ports to decrement the reference count
on the associated FIDs (filtering identifier). If the reference count of
a FID is 1 and it has a RIF (router interface), then this RIF is
destroyed.

However, if no port is member in the VLAN for which a RIF exists, then
the RIF will continue to exist after the removal of the bridge. To
reproduce:

# ip link add name br0 type bridge vlan_filtering 1
# ip link set dev swp1 master br0
# ip link add link br0 name br0.10 type vlan id 10
# ip address add 192.0.2.0/24 dev br0.10
# ip link del dev br0

The RIF associated with br0.10 continues to exist.

Fix this by iterating over all the bridge device uppers when it is
destroyed and take care of destroying their RIFs.

Fixes: 99f44bb3527b ("mlxsw: spectrum: Enable L3 interfaces on top of bridge devices")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h       |  2 ++
 .../net/ethernet/mellanox/mlxsw/spectrum_router.c    | 11 +++++++++++
 .../net/ethernet/mellanox/mlxsw/spectrum_switchdev.c | 20 ++++++++++++++++++++
 3 files changed, 33 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 804d4d2c8031..6828895ec01f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -432,6 +432,8 @@ mlxsw_sp_netdevice_ipip_ul_event(struct mlxsw_sp *mlxsw_sp,
 void
 mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan);
 void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif);
+void mlxsw_sp_rif_destroy_by_dev(struct mlxsw_sp *mlxsw_sp,
+				 struct net_device *dev);
 
 /* spectrum_kvdl.c */
 int mlxsw_sp_kvdl_init(struct mlxsw_sp *mlxsw_sp);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 692855183187..40fa7508e26e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -6219,6 +6219,17 @@ void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif)
 	mlxsw_sp_vr_put(mlxsw_sp, vr);
 }
 
+void mlxsw_sp_rif_destroy_by_dev(struct mlxsw_sp *mlxsw_sp,
+				 struct net_device *dev)
+{
+	struct mlxsw_sp_rif *rif;
+
+	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
+	if (!rif)
+		return;
+	mlxsw_sp_rif_destroy(rif);
+}
+
 static void
 mlxsw_sp_rif_subport_params_init(struct mlxsw_sp_rif_params *params,
 				 struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 0ae2da9d08c7..2000be1598c4 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -158,6 +158,24 @@ bool mlxsw_sp_bridge_device_is_offloaded(const struct mlxsw_sp *mlxsw_sp,
 	return !!mlxsw_sp_bridge_device_find(mlxsw_sp->bridge, br_dev);
 }
 
+static int mlxsw_sp_bridge_device_upper_rif_destroy(struct net_device *dev,
+						    void *data)
+{
+	struct mlxsw_sp *mlxsw_sp = data;
+
+	mlxsw_sp_rif_destroy_by_dev(mlxsw_sp, dev);
+	return 0;
+}
+
+static void mlxsw_sp_bridge_device_rifs_destroy(struct mlxsw_sp *mlxsw_sp,
+						struct net_device *dev)
+{
+	mlxsw_sp_rif_destroy_by_dev(mlxsw_sp, dev);
+	netdev_walk_all_upper_dev_rcu(dev,
+				      mlxsw_sp_bridge_device_upper_rif_destroy,
+				      mlxsw_sp);
+}
+
 static struct mlxsw_sp_bridge_device *
 mlxsw_sp_bridge_device_create(struct mlxsw_sp_bridge *bridge,
 			      struct net_device *br_dev)
@@ -196,6 +214,8 @@ static void
 mlxsw_sp_bridge_device_destroy(struct mlxsw_sp_bridge *bridge,
 			       struct mlxsw_sp_bridge_device *bridge_device)
 {
+	mlxsw_sp_bridge_device_rifs_destroy(bridge->mlxsw_sp,
+					    bridge_device->dev);
 	list_del(&bridge_device->list);
 	if (bridge_device->vlan_enabled)
 		bridge->vlan_enabled_exists = false;
-- 
2.13.6


From 055e43a4f4702ef323b1e51054d1d2771becbb77 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Fri, 24 Aug 2018 16:53:13 +0800
Subject: [PATCH 21/29] vhost: correctly check the iova range when waking
 virtqueue

[ Upstream commit 2d66f997f0545c8f7fc5cf0b49af1decb35170e7 ]

We don't wakeup the virtqueue if the first byte of pending iova range
is the last byte of the range we just got updated. This will lead a
virtqueue to wait for IOTLB updating forever. Fixing by correct the
check and wake up the virtqueue in this case.

Fixes: 6b1e6cc7855b ("vhost: new device IOTLB API")
Reported-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Tested-by: Peter Xu <peterx@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/vhost.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index d1de2cb13fd6..9eb7b75da958 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -948,7 +948,7 @@ static void vhost_iotlb_notify_vq(struct vhost_dev *d,
 	list_for_each_entry_safe(node, n, &d->pending_list, node) {
 		struct vhost_iotlb_msg *vq_msg = &node->msg.iotlb;
 		if (msg->iova <= vq_msg->iova &&
-		    msg->iova + msg->size - 1 > vq_msg->iova &&
+		    msg->iova + msg->size - 1 >= vq_msg->iova &&
 		    vq_msg->type == VHOST_IOTLB_MISS) {
 			vhost_poll_queue(&node->vq->poll);
 			list_del(&node->node);
-- 
2.13.6


From 9ea99b9e5907e5b71bc9bcb3d527cc2d7ff47bbe Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Tue, 21 Aug 2018 10:40:38 -0700
Subject: [PATCH 22/29] hv_netvsc: ignore devices that are not PCI

[ Upstream commit b93c1b5ac8643cc08bb74fa8ae21d6c63dfcb23d ]

Registering another device with same MAC address (such as TAP, VPN or
DPDK KNI) will confuse the VF autobinding logic.  Restrict the search
to only run if the device is known to be a PCI attached VF.

Fixes: e8ff40d4bff1 ("hv_netvsc: improve VF device matching")
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/netvsc_drv.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index adc176943d94..eed55922f553 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -29,6 +29,7 @@
 #include <linux/netdevice.h>
 #include <linux/inetdevice.h>
 #include <linux/etherdevice.h>
+#include <linux/pci.h>
 #include <linux/skbuff.h>
 #include <linux/if_vlan.h>
 #include <linux/in.h>
@@ -1925,11 +1926,15 @@ static int netvsc_register_vf(struct net_device *vf_netdev)
 {
 	struct net_device *ndev;
 	struct net_device_context *net_device_ctx;
+	struct device *pdev = vf_netdev->dev.parent;
 	struct netvsc_device *netvsc_dev;
 
 	if (vf_netdev->addr_len != ETH_ALEN)
 		return NOTIFY_DONE;
 
+	if (!pdev || !dev_is_pci(pdev) || dev_is_pf(pdev))
+		return NOTIFY_DONE;
+
 	/*
 	 * We will use the MAC address to locate the synthetic interface to
 	 * associate with the VF interface. If we don't find a matching
-- 
2.13.6


From fa1e458e9163c1cb9218ee83c592e9e174e3c6ca Mon Sep 17 00:00:00 2001
From: Dexuan Cui <decui@microsoft.com>
Date: Thu, 30 Aug 2018 05:42:13 +0000
Subject: [PATCH 23/29] hv_netvsc: Fix a deadlock by getting rtnl lock earlier
 in netvsc_probe()

[ Upstream commit e04e7a7bbd4bbabef4e1a58367e5fc9b2edc3b10 ]

This patch fixes the race between netvsc_probe() and
rndis_set_subchannel(), which can cause a deadlock.

These are the related 3 paths which show the deadlock:

path #1:
    Workqueue: hv_vmbus_con vmbus_onmessage_work [hv_vmbus]
    Call Trace:
     schedule
     schedule_preempt_disabled
     __mutex_lock
     __device_attach
     bus_probe_device
     device_add
     vmbus_device_register
     vmbus_onoffer
     vmbus_onmessage_work
     process_one_work
     worker_thread
     kthread
     ret_from_fork

path #2:
    schedule
     schedule_preempt_disabled
     __mutex_lock
     netvsc_probe
     vmbus_probe
     really_probe
     __driver_attach
     bus_for_each_dev
     driver_attach_async
     async_run_entry_fn
     process_one_work
     worker_thread
     kthread
     ret_from_fork

path #3:
    Workqueue: events netvsc_subchan_work [hv_netvsc]
    Call Trace:
     schedule
     rndis_set_subchannel
     netvsc_subchan_work
     process_one_work
     worker_thread
     kthread
     ret_from_fork

Before path #1 finishes, path #2 can start to run, because just before
the "bus_probe_device(dev);" in device_add() in path #1, there is a line
"object_uevent(&dev->kobj, KOBJ_ADD);", so systemd-udevd can
immediately try to load hv_netvsc and hence path #2 can start to run.

Next, path #2 offloads the subchannal's initialization to a workqueue,
i.e. path #3, so we can end up in a deadlock situation like this:

Path #2 gets the device lock, and is trying to get the rtnl lock;
Path #3 gets the rtnl lock and is waiting for all the subchannel messages
to be processed;
Path #1 is trying to get the device lock, but since #2 is not releasing
the device lock, path #1 has to sleep; since the VMBus messages are
processed one by one, this means the sub-channel messages can't be
procedded, so #3 has to sleep with the rtnl lock held, and finally #2
has to sleep... Now all the 3 paths are sleeping and we hit the deadlock.

With the patch, we can make sure #2 gets both the device lock and the
rtnl lock together, gets its job done, and releases the locks, so #1
and #3 will not be blocked for ever.

Fixes: 8195b1396ec8 ("hv_netvsc: fix deadlock on hotplug")
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/netvsc_drv.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index eed55922f553..e2668dc6b065 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -2073,6 +2073,16 @@ static int netvsc_probe(struct hv_device *dev,
 
 	memcpy(net->dev_addr, device_info.mac_adr, ETH_ALEN);
 
+	/* We must get rtnl lock before scheduling nvdev->subchan_work,
+	 * otherwise netvsc_subchan_work() can get rtnl lock first and wait
+	 * all subchannels to show up, but that may not happen because
+	 * netvsc_probe() can't get rtnl lock and as a result vmbus_onoffer()
+	 * -> ... -> device_add() -> ... -> __device_attach() can't get
+	 * the device lock, so all the subchannels can't be processed --
+	 * finally netvsc_subchan_work() hangs for ever.
+	 */
+	rtnl_lock();
+
 	if (nvdev->num_chn > 1)
 		schedule_work(&nvdev->subchan_work);
 
@@ -2091,7 +2101,6 @@ static int netvsc_probe(struct hv_device *dev,
 	else
 		net->max_mtu = ETH_DATA_LEN;
 
-	rtnl_lock();
 	ret = register_netdevice(net);
 	if (ret != 0) {
 		pr_err("Unable to register netdev.\n");
-- 
2.13.6


From 2c19535b652718f03f4b34421b2e4d841c175e34 Mon Sep 17 00:00:00 2001
From: Haiqing Bai <Haiqing.Bai@windriver.com>
Date: Mon, 27 Aug 2018 09:32:26 +0800
Subject: [PATCH 24/29] tipc: fix the big/little endian issue in tipc_dest

[ Upstream commit 30935198b7d0be12b1c45c328b66a7fdefb16256 ]

In function tipc_dest_push, the 32bit variables 'node' and 'port'
are stored separately in uppper and lower part of 64bit 'value'.
Then this value is assigned to dst->value which is a union like:
union
{
  struct {
    u32 port;
    u32 node;
  };
  u64 value;
}
This works on little-endian machines like x86 but fails on big-endian
machines.

The fix remove the 'value' stack parameter and even the 'value'
member of the union in tipc_dest, assign the 'node' and 'port' member
directly with the input parameter to avoid the endian issue.

Fixes: a80ae5306a73 ("tipc: improve destination linked list")
Signed-off-by: Zhenbo Gao <zhenbo.gao@windriver.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Haiqing Bai <Haiqing.Bai@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/name_table.c | 10 ++++------
 net/tipc/name_table.h |  9 ++-------
 2 files changed, 6 insertions(+), 13 deletions(-)

diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index dd1c4fa2eb78..ff3f2d827f32 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -977,20 +977,17 @@ int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb)
 
 struct tipc_dest *tipc_dest_find(struct list_head *l, u32 node, u32 port)
 {
-	u64 value = (u64)node << 32 | port;
 	struct tipc_dest *dst;
 
 	list_for_each_entry(dst, l, list) {
-		if (dst->value != value)
-			continue;
-		return dst;
+		if (dst->node == node && dst->port == port)
+			return dst;
 	}
 	return NULL;
 }
 
 bool tipc_dest_push(struct list_head *l, u32 node, u32 port)
 {
-	u64 value = (u64)node << 32 | port;
 	struct tipc_dest *dst;
 
 	if (tipc_dest_find(l, node, port))
@@ -999,7 +996,8 @@ bool tipc_dest_push(struct list_head *l, u32 node, u32 port)
 	dst = kmalloc(sizeof(*dst), GFP_ATOMIC);
 	if (unlikely(!dst))
 		return false;
-	dst->value = value;
+	dst->node = node;
+	dst->port = port;
 	list_add(&dst->list, l);
 	return true;
 }
diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h
index 0febba41da86..892bd750b85f 100644
--- a/net/tipc/name_table.h
+++ b/net/tipc/name_table.h
@@ -133,13 +133,8 @@ void tipc_nametbl_stop(struct net *net);
 
 struct tipc_dest {
 	struct list_head list;
-	union {
-		struct {
-			u32 port;
-			u32 node;
-		};
-		u64 value;
-	};
+	u32 port;
+	u32 node;
 };
 
 struct tipc_dest *tipc_dest_find(struct list_head *l, u32 node, u32 port);
-- 
2.13.6


From 4fbf71c3ccafa5896dcbf810692f276bdd4e3269 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 27 Aug 2018 18:40:18 +0800
Subject: [PATCH 25/29] sctp: remove useless start_fail from sctp_ht_iter in
 proc

[ Upstream commit 834539e69a5fe2aab33cc777ccfd4a4fcc5b9770 ]

After changing rhashtable_walk_start to return void, start_fail would
never be set other value than 0, and the checking for start_fail is
pointless, so remove it.

Fixes: 97a6ec4ac021 ("rhashtable: Change rhashtable_walk_start to return void")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/proc.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/net/sctp/proc.c b/net/sctp/proc.c
index 65c9189f8f6b..1e8e5b473b06 100644
--- a/net/sctp/proc.c
+++ b/net/sctp/proc.c
@@ -243,7 +243,6 @@ static const struct file_operations sctp_eps_seq_fops = {
 struct sctp_ht_iter {
 	struct seq_net_private p;
 	struct rhashtable_iter hti;
-	int start_fail;
 };
 
 static void *sctp_transport_seq_start(struct seq_file *seq, loff_t *pos)
@@ -252,7 +251,6 @@ static void *sctp_transport_seq_start(struct seq_file *seq, loff_t *pos)
 
 	sctp_transport_walk_start(&iter->hti);
 
-	iter->start_fail = 0;
 	return sctp_transport_get_idx(seq_file_net(seq), &iter->hti, *pos);
 }
 
@@ -260,8 +258,6 @@ static void sctp_transport_seq_stop(struct seq_file *seq, void *v)
 {
 	struct sctp_ht_iter *iter = seq->private;
 
-	if (iter->start_fail)
-		return;
 	sctp_transport_walk_stop(&iter->hti);
 }
 
-- 
2.13.6


From 12818c885b475d6facded1e2beef60e56ea671f7 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 27 Aug 2018 18:41:32 +0800
Subject: [PATCH 26/29] erspan: set erspan_ver to 1 by default when adding an
 erspan dev

[ Upstream commit 84581bdae9587023cea1d139523f0ef0f28bd88d ]

After erspan_ver is introudced, if erspan_ver is not set in iproute, its
value will be left 0 by default. Since Commit 02f99df1875c ("erspan: fix
invalid erspan version."), it has broken the traffic due to the version
check in erspan_xmit if users are not aware of 'erspan_ver' param, like
using an old version of iproute.

To fix this compatibility problem, it sets erspan_ver to 1 by default
when adding an erspan dev in erspan_setup. Note that we can't do it in
ipgre_netlink_parms, as this function is also used by ipgre_changelink.

Fixes: 02f99df1875c ("erspan: fix invalid erspan version.")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_gre.c  | 3 +++
 net/ipv6/ip6_gre.c | 1 +
 2 files changed, 4 insertions(+)

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index f200b304f76c..c2c1f5766d68 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1499,11 +1499,14 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev)
 
 static void erspan_setup(struct net_device *dev)
 {
+	struct ip_tunnel *t = netdev_priv(dev);
+
 	ether_setup(dev);
 	dev->netdev_ops = &erspan_netdev_ops;
 	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 	ip_tunnel_setup(dev, erspan_net_id);
+	t->erspan_ver = 1;
 }
 
 static const struct nla_policy ipgre_policy[IFLA_GRE_MAX + 1] = {
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 1a4d6897d17f..320164c91deb 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1755,6 +1755,7 @@ static void ip6gre_netlink_parms(struct nlattr *data[],
 	if (data[IFLA_GRE_COLLECT_METADATA])
 		parms->collect_md = true;
 
+	parms->erspan_ver = 1;
 	if (data[IFLA_GRE_ERSPAN_VER])
 		parms->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]);
 
-- 
2.13.6


From c03b895021c17cb51c3a12eac5c05d0f584c1e94 Mon Sep 17 00:00:00 2001
From: Ahmad Fatoum <a.fatoum@pengutronix.de>
Date: Tue, 21 Aug 2018 17:35:48 +0200
Subject: [PATCH 27/29] net: macb: Fix regression breaking non-MDIO fixed-link
 PHYs

[ Upstream commit ab5f11055fdf8dfc3ddbd89e8e3cc550de41d1d3 ]

commit 739de9a1563a ("net: macb: Reorganize macb_mii bringup") broke
initializing macb on the EVB-KSZ9477 eval board.
There, of_mdiobus_register was called even for the fixed-link representing
the RGMII-link to the switch with the result that the driver attempts to
enumerate PHYs on a non-existent MDIO bus:

	libphy: MACB_mii_bus: probed
	mdio_bus f0028000.ethernet-ffffffff: fixed-link has invalid PHY address
	mdio_bus f0028000.ethernet-ffffffff: scan phy fixed-link at address 0
        [snip]
	mdio_bus f0028000.ethernet-ffffffff: scan phy fixed-link at address 31

The "MDIO" bus registration succeeds regardless, having claimed the reset GPIO,
and calling of_phy_register_fixed_link later on fails because it tries
to claim the same GPIO:

	macb f0028000.ethernet: broken fixed-link specification

Fix this by registering the fixed-link before calling mdiobus_register.

Fixes: 739de9a1563a ("net: macb: Reorganize macb_mii bringup")
Signed-off-by: Ahmad Fatoum <a.fatoum@pengutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 6263003aafef..90ee2061daa8 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -481,11 +481,6 @@ static int macb_mii_probe(struct net_device *dev)
 
 	if (np) {
 		if (of_phy_is_fixed_link(np)) {
-			if (of_phy_register_fixed_link(np) < 0) {
-				dev_err(&bp->pdev->dev,
-					"broken fixed-link specification\n");
-				return -ENODEV;
-			}
 			bp->phy_node = of_node_get(np);
 		} else {
 			bp->phy_node = of_parse_phandle(np, "phy-handle", 0);
@@ -568,7 +563,7 @@ static int macb_mii_init(struct macb *bp)
 {
 	struct macb_platform_data *pdata;
 	struct device_node *np;
-	int err;
+	int err = -ENXIO;
 
 	/* Enable management port */
 	macb_writel(bp, NCR, MACB_BIT(MPE));
@@ -592,17 +587,23 @@ static int macb_mii_init(struct macb *bp)
 
 	np = bp->pdev->dev.of_node;
 
-	if (np) {
-		err = of_mdiobus_register(bp->mii_bus, np);
+	if (np && of_phy_is_fixed_link(np)) {
+		if (of_phy_register_fixed_link(np) < 0) {
+			dev_err(&bp->pdev->dev,
+				"broken fixed-link specification %pOF\n", np);
+			goto err_out_free_mdiobus;
+		}
+
+		err = mdiobus_register(bp->mii_bus);
 	} else {
 		if (pdata)
 			bp->mii_bus->phy_mask = pdata->phy_mask;
 
-		err = mdiobus_register(bp->mii_bus);
+		err = of_mdiobus_register(bp->mii_bus, np);
 	}
 
 	if (err)
-		goto err_out_free_mdiobus;
+		goto err_out_free_fixed_link;
 
 	err = macb_mii_probe(bp->dev);
 	if (err)
@@ -612,6 +613,7 @@ static int macb_mii_init(struct macb *bp)
 
 err_out_unregister_bus:
 	mdiobus_unregister(bp->mii_bus);
+err_out_free_fixed_link:
 	if (np && of_phy_is_fixed_link(np))
 		of_phy_deregister_fixed_link(np);
 err_out_free_mdiobus:
-- 
2.13.6


From 2d844949f60a3ca59e9c2be872cc940f07bb4864 Mon Sep 17 00:00:00 2001
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Sun, 19 Aug 2018 15:05:05 +0800
Subject: [PATCH 28/29] ip6_vti: fix creating fallback tunnel device for vti6

[ Upstream commit e2948e5af8eeb6c945000772b7613b0323a0a203 ]

When set fb_tunnels_only_for_init_net to 1, don't create fallback tunnel
device for vti6 when a new namespace is created.

Tested:
[root@builder2 ~]# modprobe ip6_tunnel
[root@builder2 ~]# modprobe ip6_vti
[root@builder2 ~]# echo 1 > /proc/sys/net/core/fb_tunnels_only_for_init_net
[root@builder2 ~]# unshare -n
[root@builder2 ~]# ip link
1: lo: <LOOPBACK> mtu 65536 qdisc noop state DOWN mode DEFAULT group
default qlen 1000
    link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00

Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_vti.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 01dea2bfc59f..04200cebddd5 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -1113,6 +1113,8 @@ static int __net_init vti6_init_net(struct net *net)
 	ip6n->tnls[0] = ip6n->tnls_wc;
 	ip6n->tnls[1] = ip6n->tnls_r_l;
 
+	if (!net_has_fallback_tunnels(net))
+		return 0;
 	err = -ENOMEM;
 	ip6n->fb_tnl_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6_vti0",
 					NET_NAME_UNKNOWN, vti6_dev_setup);
-- 
2.13.6


From 6fecadc8b6e1e79c46951956f02bf351fdbd146f Mon Sep 17 00:00:00 2001
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Mon, 20 Aug 2018 10:51:05 +0800
Subject: [PATCH 29/29] ip6_vti: fix a null pointer deference when destroy vti6
 tunnel

[ Upstream commit 9c86336c15db1c48cbaddff56caf2be0a930e991 ]

If load ip6_vti module and create a network namespace when set
fb_tunnels_only_for_init_net to 1, then exit the namespace will
cause following crash:

[ 6601.677036] BUG: unable to handle kernel NULL pointer dereference at 0000000000000008
[ 6601.679057] PGD 8000000425eca067 P4D 8000000425eca067 PUD 424292067 PMD 0
[ 6601.680483] Oops: 0000 [#1] SMP PTI
[ 6601.681223] CPU: 7 PID: 93 Comm: kworker/u16:1 Kdump: loaded Tainted: G            E     4.18.0+ #3
[ 6601.683153] Hardware name: Fedora Project OpenStack Nova, BIOS seabios-1.7.5-11.el7 04/01/2014
[ 6601.684919] Workqueue: netns cleanup_net
[ 6601.685742] RIP: 0010:vti6_exit_batch_net+0x87/0xd0 [ip6_vti]
[ 6601.686932] Code: 7b 08 48 89 e6 e8 b9 ea d3 dd 48 8b 1b 48 85 db 75 ec 48 83 c5 08 48 81 fd 00 01 00 00 75 d5 49 8b 84 24 08 01 00 00 48 89 e6 <48> 8b 78 08 e8 90 ea d3 dd 49 8b 45 28 49 39 c6 4c 8d 68 d8 75 a1
[ 6601.690735] RSP: 0018:ffffa897c2737de0 EFLAGS: 00010246
[ 6601.691846] RAX: 0000000000000000 RBX: 0000000000000000 RCX: dead000000000200
[ 6601.693324] RDX: 0000000000000015 RSI: ffffa897c2737de0 RDI: ffffffff9f2ea9e0
[ 6601.694824] RBP: 0000000000000100 R08: 0000000000000000 R09: 0000000000000000
[ 6601.696314] R10: 0000000000000001 R11: 0000000000000000 R12: ffff8dc323c07e00
[ 6601.697812] R13: ffff8dc324a63100 R14: ffffa897c2737e30 R15: ffffa897c2737e30
[ 6601.699345] FS:  0000000000000000(0000) GS:ffff8dc33fdc0000(0000) knlGS:0000000000000000
[ 6601.701068] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 6601.702282] CR2: 0000000000000008 CR3: 0000000424966002 CR4: 00000000001606e0
[ 6601.703791] Call Trace:
[ 6601.704329]  cleanup_net+0x1b4/0x2c0
[ 6601.705268]  process_one_work+0x16c/0x370
[ 6601.706145]  worker_thread+0x49/0x3e0
[ 6601.706942]  kthread+0xf8/0x130
[ 6601.707626]  ? rescuer_thread+0x340/0x340
[ 6601.708476]  ? kthread_bind+0x10/0x10
[ 6601.709266]  ret_from_fork+0x35/0x40

Reproduce:
modprobe ip6_vti
echo 1 > /proc/sys/net/core/fb_tunnels_only_for_init_net
unshare -n
exit

This because ip6n->tnls_wc[0] point to fallback device in default, but
in non-default namespace, ip6n->tnls_wc[0] will be NULL, so add the NULL
check comparatively.

Fixes: e2948e5af8ee ("ip6_vti: fix creating fallback tunnel device for vti6")
Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_vti.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 04200cebddd5..727a8448cfef 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -1101,7 +1101,8 @@ static void __net_exit vti6_destroy_tunnels(struct vti6_net *ip6n,
 	}
 
 	t = rtnl_dereference(ip6n->tnls_wc[0]);
-	unregister_netdevice_queue(t->dev, list);
+	if (t)
+		unregister_netdevice_queue(t->dev, list);
 }
 
 static int __net_init vti6_init_net(struct net *net)
-- 
2.13.6


[-- Attachment #3: net_418.mbox --]
[-- Type: Application/Octet-Stream, Size: 101970 bytes --]

From 92ed83f821f39009b23e3652f6646990a24dff88 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 3 Sep 2018 11:08:15 -0700
Subject: [PATCH 01/36] act_ife: fix a potential use-after-free

[ Upstream commit 6d784f1625ea68783cc1fb17de8f6cd3e1660c3f ]

Immediately after module_put(), user could delete this
module, so e->ops could be already freed before we call
e->ops->release().

Fix this by moving module_put() after ops->release().

Fixes: ef6980b6becb ("introduce IFE action")
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ife.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 20d7d36b2fc9..201e599baed9 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -393,7 +393,6 @@ static void _tcf_ife_cleanup(struct tc_action *a)
 	struct tcf_meta_info *e, *n;
 
 	list_for_each_entry_safe(e, n, &ife->metalist, metalist) {
-		module_put(e->ops->owner);
 		list_del(&e->metalist);
 		if (e->metaval) {
 			if (e->ops->release)
@@ -401,6 +400,7 @@ static void _tcf_ife_cleanup(struct tc_action *a)
 			else
 				kfree(e->metaval);
 		}
+		module_put(e->ops->owner);
 		kfree(e);
 	}
 }
-- 
2.13.6


From 08a956a3d03de39c9fdbf5fcd5f74eede2a104b8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 22 Aug 2018 13:30:45 -0700
Subject: [PATCH 02/36] ipv4: tcp: send zero IPID for RST and ACK sent in
 SYN-RECV and TIME-WAIT state

[ Upstream commit 431280eebed9f5079553daf003011097763e71fd ]

tcp uses per-cpu (and per namespace) sockets (net->ipv4.tcp_sk) internally
to send some control packets.

1) RST packets, through tcp_v4_send_reset()
2) ACK packets in SYN-RECV and TIME-WAIT state, through tcp_v4_send_ack()

These packets assert IP_DF, and also use the hashed IP ident generator
to provide an IPv4 ID number.

Geoff Alexander reported this could be used to build off-path attacks.

These packets should not be fragmented, since their size is smaller than
IPV4_MIN_MTU. Only some tunneled paths could eventually have to fragment,
regardless of inner IPID.

We really can use zero IPID, to address the flaw, and as a bonus,
avoid a couple of atomic operations in ip_idents_reserve()

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Geoff Alexander <alexandg@cs.unm.edu>
Tested-by: Geoff Alexander <alexandg@cs.unm.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 3b2711e33e4c..488b201851d7 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2516,6 +2516,12 @@ static int __net_init tcp_sk_init(struct net *net)
 		if (res)
 			goto fail;
 		sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);
+
+		/* Please enforce IP_DF and IPID==0 for RST and
+		 * ACK sent in SYN-RECV and TIME-WAIT state.
+		 */
+		inet_sk(sk)->pmtudisc = IP_PMTUDISC_DO;
+
 		*per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk;
 	}
 
-- 
2.13.6


From 3b98a7274042596bcedbd3e6694746cd21dc6b96 Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Tue, 28 Aug 2018 12:33:15 -0700
Subject: [PATCH 03/36] net: bcmgenet: use MAC link status for fixed phy

[ Upstream commit c3c397c1f16c51601a3fac4fe0c63ad8aa85a904 ]

When using the fixed PHY with GENET (e.g. MOCA) the PHY link
status can be determined from the internal link status captured
by the MAC. This allows the PHY state machine to use the correct
link state with the fixed PHY even if MAC link event interrupts
are missed when the net device is opened.

Fixes: 8d88c6ebb34c ("net: bcmgenet: enable MoCA link state change detection")
Signed-off-by: Doug Berger <opendmb@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.h |  3 +++
 drivers/net/ethernet/broadcom/genet/bcmmii.c   | 10 ++++++++--
 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index b773bc07edf7..14b49612aa86 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -186,6 +186,9 @@ struct bcmgenet_mib_counters {
 #define UMAC_MAC1			0x010
 #define UMAC_MAX_FRAME_LEN		0x014
 
+#define UMAC_MODE			0x44
+#define  MODE_LINK_STATUS		(1 << 5)
+
 #define UMAC_EEE_CTRL			0x064
 #define  EN_LPI_RX_PAUSE		(1 << 0)
 #define  EN_LPI_TX_PFC			(1 << 1)
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index 5333274a283c..4241ae928d4a 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -115,8 +115,14 @@ void bcmgenet_mii_setup(struct net_device *dev)
 static int bcmgenet_fixed_phy_link_update(struct net_device *dev,
 					  struct fixed_phy_status *status)
 {
-	if (dev && dev->phydev && status)
-		status->link = dev->phydev->link;
+	struct bcmgenet_priv *priv;
+	u32 reg;
+
+	if (dev && dev->phydev && status) {
+		priv = netdev_priv(dev);
+		reg = bcmgenet_umac_readl(priv, UMAC_MODE);
+		status->link = !!(reg & MODE_LINK_STATUS);
+	}
 
 	return 0;
 }
-- 
2.13.6


From 734123d37ebcdc765cc0e7deef94ff02ca887480 Mon Sep 17 00:00:00 2001
From: Anssi Hannula <anssi.hannula@bitwise.fi>
Date: Thu, 23 Aug 2018 10:45:22 +0300
Subject: [PATCH 04/36] net: macb: do not disable MDIO bus at open/close time

[ Upstream commit 0da70f808029476001109b6cb076737bc04cea2e ]

macb_reset_hw() is called from macb_close() and indirectly from
macb_open(). macb_reset_hw() zeroes the NCR register, including the MPE
(Management Port Enable) bit.

This will prevent accessing any other PHYs for other Ethernet MACs on
the MDIO bus, which remains registered at macb_reset_hw() time, until
macb_init_hw() is called from macb_open() which sets the MPE bit again.

I.e. currently the MDIO bus has a short disruption at open time and is
disabled at close time until the interface is opened again.

Fix that by only touching the RE and TE bits when enabling and disabling
RX/TX.

v2: Make macb_init_hw() NCR write a single statement.

Fixes: 6c36a7074436 ("macb: Use generic PHY layer")
Signed-off-by: Anssi Hannula <anssi.hannula@bitwise.fi>
Reviewed-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Tested-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index a6c911bb5ce2..e4b4a6a879be 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -1957,14 +1957,17 @@ static void macb_reset_hw(struct macb *bp)
 {
 	struct macb_queue *queue;
 	unsigned int q;
+	u32 ctrl = macb_readl(bp, NCR);
 
 	/* Disable RX and TX (XXX: Should we halt the transmission
 	 * more gracefully?)
 	 */
-	macb_writel(bp, NCR, 0);
+	ctrl &= ~(MACB_BIT(RE) | MACB_BIT(TE));
 
 	/* Clear the stats registers (XXX: Update stats first?) */
-	macb_writel(bp, NCR, MACB_BIT(CLRSTAT));
+	ctrl |= MACB_BIT(CLRSTAT);
+
+	macb_writel(bp, NCR, ctrl);
 
 	/* Clear all status flags */
 	macb_writel(bp, TSR, -1);
@@ -2152,7 +2155,7 @@ static void macb_init_hw(struct macb *bp)
 	}
 
 	/* Enable TX and RX */
-	macb_writel(bp, NCR, MACB_BIT(RE) | MACB_BIT(TE) | MACB_BIT(MPE));
+	macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(RE) | MACB_BIT(TE));
 }
 
 /* The hash address register is 64 bits long and takes up two
-- 
2.13.6


From 32678e9ad94534f2a280bb427cb4451a2025d324 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Sat, 25 Aug 2018 22:58:01 -0700
Subject: [PATCH 05/36] net: sched: Fix memory exposure from short TCA_U32_SEL

[ Upstream commit 98c8f125fd8a6240ea343c1aa50a1be9047791b8 ]

Via u32_change(), TCA_U32_SEL has an unspecified type in the netlink
policy, so max length isn't enforced, only minimum. This means nkeys
(from userspace) was being trusted without checking the actual size of
nla_len(), which could lead to a memory over-read, and ultimately an
exposure via a call to u32_dump(). Reachability is CAP_NET_ADMIN within
a namespace.

Reported-by: Al Viro <viro@zeniv.linux.org.uk>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_u32.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index fb861f90fde6..260749956ef3 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -912,6 +912,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 	struct nlattr *opt = tca[TCA_OPTIONS];
 	struct nlattr *tb[TCA_U32_MAX + 1];
 	u32 htid, flags = 0;
+	size_t sel_size;
 	int err;
 #ifdef CONFIG_CLS_U32_PERF
 	size_t size;
@@ -1074,8 +1075,13 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 	}
 
 	s = nla_data(tb[TCA_U32_SEL]);
+	sel_size = struct_size(s, keys, s->nkeys);
+	if (nla_len(tb[TCA_U32_SEL]) < sel_size) {
+		err = -EINVAL;
+		goto erridr;
+	}
 
-	n = kzalloc(sizeof(*n) + s->nkeys*sizeof(struct tc_u32_key), GFP_KERNEL);
+	n = kzalloc(offsetof(typeof(*n), sel) + sel_size, GFP_KERNEL);
 	if (n == NULL) {
 		err = -ENOBUFS;
 		goto erridr;
@@ -1090,7 +1096,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 	}
 #endif
 
-	memcpy(&n->sel, s, sizeof(*s) + s->nkeys*sizeof(struct tc_u32_key));
+	memcpy(&n->sel, s, sel_size);
 	RCU_INIT_POINTER(n->ht_up, ht);
 	n->handle = handle;
 	n->fshift = s->hmask ? ffs(ntohl(s->hmask)) - 1 : 0;
-- 
2.13.6


From 206cf053debd00c5e6407cc1b11537ac67834646 Mon Sep 17 00:00:00 2001
From: Manish Chopra <manish.chopra@cavium.com>
Date: Thu, 23 Aug 2018 13:20:52 -0700
Subject: [PATCH 06/36] qlge: Fix netdev features configuration.

[ Upstream commit 6750c87074c5b534d82fdaabb1deb45b8f1f57de ]

qlge_fix_features() is not supposed to modify hardware or
driver state, rather it is supposed to only fix requested
fetures bits. Currently qlge_fix_features() also goes for
interface down and up unnecessarily if there is not even
any change in features set.

This patch changes/fixes following -

1) Move reload of interface or device re-config from
   qlge_fix_features() to qlge_set_features().
2) Reload of interface in qlge_set_features() only if
   relevant feature bit (NETIF_F_HW_VLAN_CTAG_RX) is changed.
3) Get rid of qlge_fix_features() since driver is not really
   required to fix any features bit.

Signed-off-by: Manish <manish.chopra@cavium.com>
Reviewed-by: Benjamin Poirier <bpoirier@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qlge/qlge_main.c | 23 ++++++++---------------
 1 file changed, 8 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
index 353f1c129af1..059ba9429e51 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
@@ -2384,26 +2384,20 @@ static int qlge_update_hw_vlan_features(struct net_device *ndev,
 	return status;
 }
 
-static netdev_features_t qlge_fix_features(struct net_device *ndev,
-	netdev_features_t features)
-{
-	int err;
-
-	/* Update the behavior of vlan accel in the adapter */
-	err = qlge_update_hw_vlan_features(ndev, features);
-	if (err)
-		return err;
-
-	return features;
-}
-
 static int qlge_set_features(struct net_device *ndev,
 	netdev_features_t features)
 {
 	netdev_features_t changed = ndev->features ^ features;
+	int err;
+
+	if (changed & NETIF_F_HW_VLAN_CTAG_RX) {
+		/* Update the behavior of vlan accel in the adapter */
+		err = qlge_update_hw_vlan_features(ndev, features);
+		if (err)
+			return err;
 
-	if (changed & NETIF_F_HW_VLAN_CTAG_RX)
 		qlge_vlan_mode(ndev, features);
+	}
 
 	return 0;
 }
@@ -4719,7 +4713,6 @@ static const struct net_device_ops qlge_netdev_ops = {
 	.ndo_set_mac_address	= qlge_set_mac_address,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_tx_timeout		= qlge_tx_timeout,
-	.ndo_fix_features	= qlge_fix_features,
 	.ndo_set_features	= qlge_set_features,
 	.ndo_vlan_rx_add_vid	= qlge_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= qlge_vlan_rx_kill_vid,
-- 
2.13.6


From 068be63f6aa21a26412b02a5f56a8e1afa3330e9 Mon Sep 17 00:00:00 2001
From: Kai-Heng Feng <kai.heng.feng@canonical.com>
Date: Mon, 20 Aug 2018 12:43:51 +0800
Subject: [PATCH 07/36] r8152: disable RX aggregation on new Dell TB16 dock

[ Upstream commit 176eb614b118c96e7797f5ddefd10708c316f621 ]

There's a new Dell TB16 dock with a different iSerialNumber.

Apply the same fix from commit 0b1655143df0 ("r8152: disable RX
aggregation on Dell TB16 dock") to this model.

BugLink: https://bugs.launchpad.net/bugs/1785780
Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 2a58607a6aea..1b07bb5e110d 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -5214,8 +5214,8 @@ static int rtl8152_probe(struct usb_interface *intf,
 		netdev->hw_features &= ~NETIF_F_RXCSUM;
 	}
 
-	if (le16_to_cpu(udev->descriptor.bcdDevice) == 0x3011 &&
-	    udev->serial && !strcmp(udev->serial, "000001000000")) {
+	if (le16_to_cpu(udev->descriptor.bcdDevice) == 0x3011 && udev->serial &&
+	    (!strcmp(udev->serial, "000001000000") || !strcmp(udev->serial, "000002000000"))) {
 		dev_info(&udev->dev, "Dell TB16 Dock, disable RX aggregation");
 		set_bit(DELL_TB_RX_AGG_BUG, &tp->flags);
 	}
-- 
2.13.6


From 1e4149f6c9870eb10d7ec26d0fe2a306edf6ce16 Mon Sep 17 00:00:00 2001
From: Anthony Wong <anthony.wong@ubuntu.com>
Date: Fri, 31 Aug 2018 20:06:42 +0800
Subject: [PATCH 08/36] r8169: add support for NCube 8168 network card

[ Upstream commit 9fd0e09a4e86499639653243edfcb417a05c5c46 ]

This card identifies itself as:
  Ethernet controller [0200]: NCube Device [10ff:8168] (rev 06)
  Subsystem: TP-LINK Technologies Co., Ltd. Device [7470:3468]

Adding a new entry to rtl8169_pci_tbl makes the card work.

Link: http://launchpad.net/bugs/1788730
Signed-off-by: Anthony Wong <anthony.wong@ubuntu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 1 +
 include/linux/pci_ids.h              | 2 ++
 2 files changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 9ceb34bac3a9..65e4e392774a 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -303,6 +303,7 @@ static const struct pci_device_id rtl8169_pci_tbl[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8161), 0, 0, RTL_CFG_1 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8167), 0, 0, RTL_CFG_0 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8168), 0, 0, RTL_CFG_1 },
+	{ PCI_DEVICE(PCI_VENDOR_ID_NCUBE,	0x8168), 0, 0, RTL_CFG_1 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8169), 0, 0, RTL_CFG_0 },
 	{ PCI_VENDOR_ID_DLINK,			0x4300,
 		PCI_VENDOR_ID_DLINK, 0x4b10,		 0, 0, RTL_CFG_1 },
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 29502238e510..bf85e152af05 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -3082,4 +3082,6 @@
 
 #define PCI_VENDOR_ID_OCZ		0x1b85
 
+#define PCI_VENDOR_ID_NCUBE		0x10ff
+
 #endif /* _LINUX_PCI_IDS_H */
-- 
2.13.6


From 484f12aa0a02f0bd81153d738cf2de8bcfb5628a Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 30 Aug 2018 14:24:29 +0200
Subject: [PATCH 09/36] tcp: do not restart timewait timer on rst reception

[ Upstream commit 63cc357f7bba6729869565a12df08441a5995d9a ]

RFC 1337 says:
 ''Ignore RST segments in TIME-WAIT state.
   If the 2 minute MSL is enforced, this fix avoids all three hazards.''

So with net.ipv4.tcp_rfc1337=1, expected behaviour is to have TIME-WAIT sk
expire rather than removing it instantly when a reset is received.

However, Linux will also re-start the TIME-WAIT timer.

This causes connect to fail when tying to re-use ports or very long
delays (until syn retry interval exceeds MSL).

packetdrill test case:
// Demonstrate bogus rearming of TIME-WAIT timer in rfc1337 mode.
`sysctl net.ipv4.tcp_rfc1337=1`

0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
0.000 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
0.000 bind(3, ..., ...) = 0
0.000 listen(3, 1) = 0

0.100 < S 0:0(0) win 29200 <mss 1460,nop,nop,sackOK,nop,wscale 7>
0.100 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 7>
0.200 < . 1:1(0) ack 1 win 257
0.200 accept(3, ..., ...) = 4

// Receive first segment
0.310 < P. 1:1001(1000) ack 1 win 46

// Send one ACK
0.310 > . 1:1(0) ack 1001

// read 1000 byte
0.310 read(4, ..., 1000) = 1000

// Application writes 100 bytes
0.350 write(4, ..., 100) = 100
0.350 > P. 1:101(100) ack 1001

// ACK
0.500 < . 1001:1001(0) ack 101 win 257

// close the connection
0.600 close(4) = 0
0.600 > F. 101:101(0) ack 1001 win 244

// Our side is in FIN_WAIT_1 & waits for ack to fin
0.7 < . 1001:1001(0) ack 102 win 244

// Our side is in FIN_WAIT_2 with no outstanding data.
0.8 < F. 1001:1001(0) ack 102 win 244
0.8 > . 102:102(0) ack 1002 win 244

// Our side is now in TIME_WAIT state, send ack for fin.
0.9 < F. 1002:1002(0) ack 102 win 244
0.9 > . 102:102(0) ack 1002 win 244

// Peer reopens with in-window SYN:
1.000 < S 1000:1000(0) win 9200 <mss 1460,nop,nop,sackOK,nop,wscale 7>

// Therefore, reply with ACK.
1.000 > . 102:102(0) ack 1002 win 244

// Peer sends RST for this ACK.  Normally this RST results
// in tw socket removal, but rfc1337=1 setting prevents this.
1.100 < R 1002:1002(0) win 244

// second syn. Due to rfc1337=1 expect another pure ACK.
31.0 < S 1000:1000(0) win 9200 <mss 1460,nop,nop,sackOK,nop,wscale 7>
31.0 > . 102:102(0) ack 1002 win 244

// .. and another RST from peer.
31.1 < R 1002:1002(0) win 244
31.2 `echo no timer restart;ss -m -e -a -i -n -t -o state TIME-WAIT`

// third syn after one minute.  Time-Wait socket should have expired by now.
63.0 < S 1000:1000(0) win 9200 <mss 1460,nop,nop,sackOK,nop,wscale 7>

// so we expect a syn-ack & 3whs to proceed from here on.
63.0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 7>

Without this patch, 'ss' shows restarts of tw timer and last packet is
thus just another pure ack, more than one minute later.

This restores the original code from commit 283fd6cf0be690a83
("Merge in ANK networking jumbo patch") in netdev-vger-cvs.git .

For some reason the else branch was removed/lost in 1f28b683339f7
("Merge in TCP/UDP optimizations and [..]") and timer restart became
unconditional.

Reported-by: Michal Tesar <mtesar@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_minisocks.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 1dda1341a223..b690132f5da2 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -184,8 +184,9 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 				inet_twsk_deschedule_put(tw);
 				return TCP_TW_SUCCESS;
 			}
+		} else {
+			inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN);
 		}
-		inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN);
 
 		if (tmp_opt.saw_tstamp) {
 			tcptw->tw_ts_recent	  = tmp_opt.rcv_tsval;
-- 
2.13.6


From a39ba4ddfbf947aa717ec3e496ca53128763ee9c Mon Sep 17 00:00:00 2001
From: Alexey Kodanev <alexey.kodanev@oracle.com>
Date: Thu, 23 Aug 2018 19:49:54 +0300
Subject: [PATCH 10/36] vti6: remove !skb->ignore_df check from vti6_xmit()

[ Upstream commit 9f2895461439fda2801a7906fb4c5fb3dbb37a0a ]

Before the commit d6990976af7c ("vti6: fix PMTU caching and reporting
on xmit") '!skb->ignore_df' check was always true because the function
skb_scrub_packet() was called before it, resetting ignore_df to zero.

In the commit, skb_scrub_packet() was moved below, and now this check
can be false for the packet, e.g. when sending it in the two fragments,
this prevents successful PMTU updates in such case. The next attempts
to send the packet lead to the same tx error. Moreover, vti6 initial
MTU value relies on PMTU adjustments.

This issue can be reproduced with the following LTP test script:
    udp_ipsec_vti.sh -6 -p ah -m tunnel -s 2000

Fixes: ccd740cbc6e0 ("vti6: Add pmtu handling to vti6_xmit.")
Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Acked-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_vti.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index c72ae3a4fe09..fbd3752ea587 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -481,7 +481,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 	}
 
 	mtu = dst_mtu(dst);
-	if (!skb->ignore_df && skb->len > mtu) {
+	if (skb->len > mtu) {
 		skb_dst_update_pmtu(skb, mtu);
 
 		if (skb->protocol == htons(ETH_P_IPV6)) {
-- 
2.13.6


From c6af9ef5d8c8077f6535f3b313f23d250bd438a9 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sun, 19 Aug 2018 12:22:12 -0700
Subject: [PATCH 11/36] act_ife: move tcfa_lock down to where necessary

[ Upstream commit 4e407ff5cd67ec76eeeea1deec227b7982dc7f66 ]

The only time we need to take tcfa_lock is when adding
a new metainfo to an existing ife->metalist. We don't need
to take tcfa_lock so early and so broadly in tcf_ife_init().

This means we can always take ife_mod_lock first, avoid the
reverse locking ordering warning as reported by Vlad.

Reported-by: Vlad Buslov <vladbu@mellanox.com>
Tested-by: Vlad Buslov <vladbu@mellanox.com>
Cc: Vlad Buslov <vladbu@mellanox.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ife.c | 36 +++++++++++++-----------------------
 1 file changed, 13 insertions(+), 23 deletions(-)

diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 201e599baed9..fc4b6e18cd2d 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -265,10 +265,8 @@ static const char *ife_meta_id2name(u32 metaid)
 #endif
 
 /* called when adding new meta information
- * under ife->tcf_lock for existing action
 */
-static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid,
-				void *val, int len, bool exists)
+static int load_metaops_and_vet(u32 metaid, void *val, int len)
 {
 	struct tcf_meta_ops *ops = find_ife_oplist(metaid);
 	int ret = 0;
@@ -276,13 +274,9 @@ static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid,
 	if (!ops) {
 		ret = -ENOENT;
 #ifdef CONFIG_MODULES
-		if (exists)
-			spin_unlock_bh(&ife->tcf_lock);
 		rtnl_unlock();
 		request_module("ife-meta-%s", ife_meta_id2name(metaid));
 		rtnl_lock();
-		if (exists)
-			spin_lock_bh(&ife->tcf_lock);
 		ops = find_ife_oplist(metaid);
 #endif
 	}
@@ -299,10 +293,9 @@ static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid,
 }
 
 /* called when adding new meta information
- * under ife->tcf_lock for existing action
 */
 static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval,
-			int len, bool atomic)
+			int len, bool atomic, bool exists)
 {
 	struct tcf_meta_info *mi = NULL;
 	struct tcf_meta_ops *ops = find_ife_oplist(metaid);
@@ -329,12 +322,16 @@ static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval,
 		}
 	}
 
+	if (exists)
+		spin_lock_bh(&ife->tcf_lock);
 	list_add_tail(&mi->metalist, &ife->metalist);
+	if (exists)
+		spin_unlock_bh(&ife->tcf_lock);
 
 	return ret;
 }
 
-static int use_all_metadata(struct tcf_ife_info *ife)
+static int use_all_metadata(struct tcf_ife_info *ife, bool exists)
 {
 	struct tcf_meta_ops *o;
 	int rc = 0;
@@ -342,7 +339,7 @@ static int use_all_metadata(struct tcf_ife_info *ife)
 
 	read_lock(&ife_mod_lock);
 	list_for_each_entry(o, &ifeoplist, list) {
-		rc = add_metainfo(ife, o->metaid, NULL, 0, true);
+		rc = add_metainfo(ife, o->metaid, NULL, 0, true, exists);
 		if (rc == 0)
 			installed += 1;
 	}
@@ -419,7 +416,6 @@ static void tcf_ife_cleanup(struct tc_action *a)
 		kfree_rcu(p, rcu);
 }
 
-/* under ife->tcf_lock for existing action */
 static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb,
 			     bool exists)
 {
@@ -433,11 +429,11 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb,
 			val = nla_data(tb[i]);
 			len = nla_len(tb[i]);
 
-			rc = load_metaops_and_vet(ife, i, val, len, exists);
+			rc = load_metaops_and_vet(i, val, len);
 			if (rc != 0)
 				return rc;
 
-			rc = add_metainfo(ife, i, val, len, exists);
+			rc = add_metainfo(ife, i, val, len, false, exists);
 			if (rc)
 				return rc;
 		}
@@ -531,8 +527,6 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 		p->eth_type = ife_type;
 	}
 
-	if (exists)
-		spin_lock_bh(&ife->tcf_lock);
 
 	if (ret == ACT_P_CREATED)
 		INIT_LIST_HEAD(&ife->metalist);
@@ -544,9 +538,6 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 metadata_parse_err:
 			if (ret == ACT_P_CREATED)
 				tcf_idr_release(*a, bind);
-
-			if (exists)
-				spin_unlock_bh(&ife->tcf_lock);
 			kfree(p);
 			return err;
 		}
@@ -561,18 +552,17 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 		 * as we can. You better have at least one else we are
 		 * going to bail out
 		 */
-		err = use_all_metadata(ife);
+		err = use_all_metadata(ife, exists);
 		if (err) {
 			if (ret == ACT_P_CREATED)
 				tcf_idr_release(*a, bind);
-
-			if (exists)
-				spin_unlock_bh(&ife->tcf_lock);
 			kfree(p);
 			return err;
 		}
 	}
 
+	if (exists)
+		spin_lock_bh(&ife->tcf_lock);
 	ife->tcf_action = parm->action;
 	if (exists)
 		spin_unlock_bh(&ife->tcf_lock);
-- 
2.13.6


From daf217717b9bea2c2fec85475e545e49d063a23f Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sun, 19 Aug 2018 12:22:13 -0700
Subject: [PATCH 12/36] act_ife: fix a potential deadlock

[ Upstream commit 5ffe57da29b3802baeddaa40909682bbb4cb4d48 ]

use_all_metadata() acquires read_lock(&ife_mod_lock), then calls
add_metainfo() which calls find_ife_oplist() which acquires the same
lock again. Deadlock!

Introduce __add_metainfo() which accepts struct tcf_meta_ops *ops
as an additional parameter and let its callers to decide how
to find it. For use_all_metadata(), it already has ops, no
need to find it again, just call __add_metainfo() directly.

And, as ife_mod_lock is only needed for find_ife_oplist(),
this means we can make non-atomic allocation for populate_metalist()
now.

Fixes: 817e9f2c5c26 ("act_ife: acquire ife_mod_lock before reading ifeoplist")
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ife.c | 34 +++++++++++++++++++++-------------
 1 file changed, 21 insertions(+), 13 deletions(-)

diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index fc4b6e18cd2d..43ca04eb6108 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -294,22 +294,16 @@ static int load_metaops_and_vet(u32 metaid, void *val, int len)
 
 /* called when adding new meta information
 */
-static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval,
-			int len, bool atomic, bool exists)
+static int __add_metainfo(const struct tcf_meta_ops *ops,
+			  struct tcf_ife_info *ife, u32 metaid, void *metaval,
+			  int len, bool atomic, bool exists)
 {
 	struct tcf_meta_info *mi = NULL;
-	struct tcf_meta_ops *ops = find_ife_oplist(metaid);
 	int ret = 0;
 
-	if (!ops)
-		return -ENOENT;
-
 	mi = kzalloc(sizeof(*mi), atomic ? GFP_ATOMIC : GFP_KERNEL);
-	if (!mi) {
-		/*put back what find_ife_oplist took */
-		module_put(ops->owner);
+	if (!mi)
 		return -ENOMEM;
-	}
 
 	mi->metaid = metaid;
 	mi->ops = ops;
@@ -317,7 +311,6 @@ static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval,
 		ret = ops->alloc(mi, metaval, atomic ? GFP_ATOMIC : GFP_KERNEL);
 		if (ret != 0) {
 			kfree(mi);
-			module_put(ops->owner);
 			return ret;
 		}
 	}
@@ -331,6 +324,21 @@ static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval,
 	return ret;
 }
 
+static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval,
+			int len, bool exists)
+{
+	const struct tcf_meta_ops *ops = find_ife_oplist(metaid);
+	int ret;
+
+	if (!ops)
+		return -ENOENT;
+	ret = __add_metainfo(ops, ife, metaid, metaval, len, false, exists);
+	if (ret)
+		/*put back what find_ife_oplist took */
+		module_put(ops->owner);
+	return ret;
+}
+
 static int use_all_metadata(struct tcf_ife_info *ife, bool exists)
 {
 	struct tcf_meta_ops *o;
@@ -339,7 +347,7 @@ static int use_all_metadata(struct tcf_ife_info *ife, bool exists)
 
 	read_lock(&ife_mod_lock);
 	list_for_each_entry(o, &ifeoplist, list) {
-		rc = add_metainfo(ife, o->metaid, NULL, 0, true, exists);
+		rc = __add_metainfo(o, ife, o->metaid, NULL, 0, true, exists);
 		if (rc == 0)
 			installed += 1;
 	}
@@ -433,7 +441,7 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb,
 			if (rc != 0)
 				return rc;
 
-			rc = add_metainfo(ife, i, val, len, false, exists);
+			rc = add_metainfo(ife, i, val, len, exists);
 			if (rc)
 				return rc;
 		}
-- 
2.13.6


From 33f9ddfa34ccf71e876779c9f5caf100436336fa Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Tue, 4 Sep 2018 00:44:42 +0300
Subject: [PATCH 13/36] net: sched: action_ife: take reference to meta module

[ Upstream commit 84cb8eb26cb9ce3c79928094962a475a9d850a53 ]

Recent refactoring of add_metainfo() caused use_all_metadata() to add
metainfo to ife action metalist without taking reference to module. This
causes warning in module_put called from ife action cleanup function.

Implement add_metainfo_and_get_ops() function that returns with reference
to module taken if metainfo was added successfully, and call it from
use_all_metadata(), instead of calling __add_metainfo() directly.

Example warning:

[  646.344393] WARNING: CPU: 1 PID: 2278 at kernel/module.c:1139 module_put+0x1cb/0x230
[  646.352437] Modules linked in: act_meta_skbtcindex act_meta_mark act_meta_skbprio act_ife ife veth nfsv3 nfs fscache xt_CHECKSUM iptable_mangle ipt_MASQUERADE iptable_nat nf_nat_ipv4 nf_nat xt_conntrack nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 libcrc32c tun ebtable_filter ebtables ip6table_filter ip6_tables bridge stp llc mlx5_ib ib_uverbs ib_core intel_rapl sb_edac x86_pkg_temp_thermal mlx5_core coretemp kvm_intel kvm nfsd igb irqbypass crct10dif_pclmul devlink crc32_pclmul mei_me joydev ses crc32c_intel enclosure auth_rpcgss i2c_algo_bit ioatdma ptp mei pps_core ghash_clmulni_intel iTCO_wdt iTCO_vendor_support pcspkr dca ipmi_ssif lpc_ich target_core_mod i2c_i801 ipmi_si ipmi_devintf pcc_cpufreq wmi ipmi_msghandler nfs_acl lockd acpi_pad acpi_power_meter grace sunrpc mpt3sas raid_class scsi_transport_sas
[  646.425631] CPU: 1 PID: 2278 Comm: tc Not tainted 4.19.0-rc1+ #799
[  646.432187] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017
[  646.440595] RIP: 0010:module_put+0x1cb/0x230
[  646.445238] Code: f3 66 94 02 e8 26 ff fa ff 85 c0 74 11 0f b6 1d 51 30 94 02 80 fb 01 77 60 83 e3 01 74 13 65 ff 0d 3a 83 db 73 e9 2b ff ff ff <0f> 0b e9 00 ff ff ff e8 59 01 fb ff 85 c0 75 e4 48 c7 c2 20 62 6b
[  646.464997] RSP: 0018:ffff880354d37068 EFLAGS: 00010286
[  646.470599] RAX: 0000000000000000 RBX: ffffffffc0a52518 RCX: ffffffff8c2668db
[  646.478118] RDX: 0000000000000003 RSI: dffffc0000000000 RDI: ffffffffc0a52518
[  646.485641] RBP: ffffffffc0a52180 R08: fffffbfff814a4a4 R09: fffffbfff814a4a3
[  646.493164] R10: ffffffffc0a5251b R11: fffffbfff814a4a4 R12: 1ffff1006a9a6e0d
[  646.500687] R13: 00000000ffffffff R14: ffff880362bab890 R15: dead000000000100
[  646.508213] FS:  00007f4164c99800(0000) GS:ffff88036fe40000(0000) knlGS:0000000000000000
[  646.516961] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  646.523080] CR2: 00007f41638b8420 CR3: 0000000351df0004 CR4: 00000000001606e0
[  646.530595] Call Trace:
[  646.533408]  ? find_symbol_in_section+0x260/0x260
[  646.538509]  tcf_ife_cleanup+0x11b/0x200 [act_ife]
[  646.543695]  tcf_action_cleanup+0x29/0xa0
[  646.548078]  __tcf_action_put+0x5a/0xb0
[  646.552289]  ? nla_put+0x65/0xe0
[  646.555889]  __tcf_idr_release+0x48/0x60
[  646.560187]  tcf_generic_walker+0x448/0x6b0
[  646.564764]  ? tcf_action_dump_1+0x450/0x450
[  646.569411]  ? __lock_is_held+0x84/0x110
[  646.573720]  ? tcf_ife_walker+0x10c/0x20f [act_ife]
[  646.578982]  tca_action_gd+0x972/0xc40
[  646.583129]  ? tca_get_fill.constprop.17+0x250/0x250
[  646.588471]  ? mark_lock+0xcf/0x980
[  646.592324]  ? check_chain_key+0x140/0x1f0
[  646.596832]  ? debug_show_all_locks+0x240/0x240
[  646.601839]  ? memset+0x1f/0x40
[  646.605350]  ? nla_parse+0xca/0x1a0
[  646.609217]  tc_ctl_action+0x215/0x230
[  646.613339]  ? tcf_action_add+0x220/0x220
[  646.617748]  rtnetlink_rcv_msg+0x56a/0x6d0
[  646.622227]  ? rtnl_fdb_del+0x3f0/0x3f0
[  646.626466]  netlink_rcv_skb+0x18d/0x200
[  646.630752]  ? rtnl_fdb_del+0x3f0/0x3f0
[  646.634959]  ? netlink_ack+0x500/0x500
[  646.639106]  netlink_unicast+0x2d0/0x370
[  646.643409]  ? netlink_attachskb+0x340/0x340
[  646.648050]  ? _copy_from_iter_full+0xe9/0x3e0
[  646.652870]  ? import_iovec+0x11e/0x1c0
[  646.657083]  netlink_sendmsg+0x3b9/0x6a0
[  646.661388]  ? netlink_unicast+0x370/0x370
[  646.665877]  ? netlink_unicast+0x370/0x370
[  646.670351]  sock_sendmsg+0x6b/0x80
[  646.674212]  ___sys_sendmsg+0x4a1/0x520
[  646.678443]  ? copy_msghdr_from_user+0x210/0x210
[  646.683463]  ? lock_downgrade+0x320/0x320
[  646.687849]  ? debug_show_all_locks+0x240/0x240
[  646.692760]  ? do_raw_spin_unlock+0xa2/0x130
[  646.697418]  ? _raw_spin_unlock+0x24/0x30
[  646.701798]  ? __handle_mm_fault+0x1819/0x1c10
[  646.706619]  ? __pmd_alloc+0x320/0x320
[  646.710738]  ? debug_show_all_locks+0x240/0x240
[  646.715649]  ? restore_nameidata+0x7b/0xa0
[  646.720117]  ? check_chain_key+0x140/0x1f0
[  646.724590]  ? check_chain_key+0x140/0x1f0
[  646.729070]  ? __fget_light+0xbc/0xd0
[  646.733121]  ? __sys_sendmsg+0xd7/0x150
[  646.737329]  __sys_sendmsg+0xd7/0x150
[  646.741359]  ? __ia32_sys_shutdown+0x30/0x30
[  646.746003]  ? up_read+0x53/0x90
[  646.749601]  ? __do_page_fault+0x484/0x780
[  646.754105]  ? do_syscall_64+0x1e/0x2c0
[  646.758320]  do_syscall_64+0x72/0x2c0
[  646.762353]  entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  646.767776] RIP: 0033:0x7f4163872150
[  646.771713] Code: 8b 15 3c 7d 2b 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb cd 66 0f 1f 44 00 00 83 3d b9 d5 2b 00 00 75 10 b8 2e 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be cd 00 00 48 89 04 24
[  646.791474] RSP: 002b:00007ffdef7d6b58 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
[  646.799721] RAX: ffffffffffffffda RBX: 0000000000000024 RCX: 00007f4163872150
[  646.807240] RDX: 0000000000000000 RSI: 00007ffdef7d6bd0 RDI: 0000000000000003
[  646.814760] RBP: 000000005b8b9482 R08: 0000000000000001 R09: 0000000000000000
[  646.822286] R10: 00000000000005e7 R11: 0000000000000246 R12: 00007ffdef7dad20
[  646.829807] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000679bc0
[  646.837360] irq event stamp: 6083
[  646.841043] hardirqs last  enabled at (6081): [<ffffffff8c220a7d>] __call_rcu+0x17d/0x500
[  646.849882] hardirqs last disabled at (6083): [<ffffffff8c004f06>] trace_hardirqs_off_thunk+0x1a/0x1c
[  646.859775] softirqs last  enabled at (5968): [<ffffffff8d4004a1>] __do_softirq+0x4a1/0x6ee
[  646.868784] softirqs last disabled at (6082): [<ffffffffc0a78759>] tcf_ife_cleanup+0x39/0x200 [act_ife]
[  646.878845] ---[ end trace b1b8c12ffe51e657 ]---

Fixes: 5ffe57da29b3 ("act_ife: fix a potential deadlock")
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ife.c | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 43ca04eb6108..005cb21348c9 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -324,6 +324,20 @@ static int __add_metainfo(const struct tcf_meta_ops *ops,
 	return ret;
 }
 
+static int add_metainfo_and_get_ops(const struct tcf_meta_ops *ops,
+				    struct tcf_ife_info *ife, u32 metaid,
+				    bool exists)
+{
+	int ret;
+
+	if (!try_module_get(ops->owner))
+		return -ENOENT;
+	ret = __add_metainfo(ops, ife, metaid, NULL, 0, true, exists);
+	if (ret)
+		module_put(ops->owner);
+	return ret;
+}
+
 static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval,
 			int len, bool exists)
 {
@@ -347,7 +361,7 @@ static int use_all_metadata(struct tcf_ife_info *ife, bool exists)
 
 	read_lock(&ife_mod_lock);
 	list_for_each_entry(o, &ifeoplist, list) {
-		rc = __add_metainfo(o, ife, o->metaid, NULL, 0, true, exists);
+		rc = add_metainfo_and_get_ops(o, ife, o->metaid, exists);
 		if (rc == 0)
 			installed += 1;
 	}
-- 
2.13.6


From 5416a98c35d2b3bc2da2accec2b3217c39b32a15 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Mon, 3 Sep 2018 04:23:18 -0400
Subject: [PATCH 14/36] bnxt_en: Clean up unused functions.

[ Upstream commit ad95c27bdb930105f3eea02621bda157caf2862d ]

Remove unused bnxt_subtract_ulp_resources().  Change
bnxt_get_max_func_irqs() to static since it is only locally used.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c     |  2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt.h     |  1 -
 drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c | 15 ---------------
 drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h |  1 -
 4 files changed, 1 insertion(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 4394c1162be4..7fa1dcbd638f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -5912,7 +5912,7 @@ void bnxt_set_max_func_cp_rings(struct bnxt *bp, unsigned int max)
 	bp->hw_resc.max_cp_rings = max;
 }
 
-unsigned int bnxt_get_max_func_irqs(struct bnxt *bp)
+static unsigned int bnxt_get_max_func_irqs(struct bnxt *bp)
 {
 	struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 91575ef97c8c..ca9bb24bc265 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1469,7 +1469,6 @@ unsigned int bnxt_get_max_func_stat_ctxs(struct bnxt *bp);
 void bnxt_set_max_func_stat_ctxs(struct bnxt *bp, unsigned int max);
 unsigned int bnxt_get_max_func_cp_rings(struct bnxt *bp);
 void bnxt_set_max_func_cp_rings(struct bnxt *bp, unsigned int max);
-unsigned int bnxt_get_max_func_irqs(struct bnxt *bp);
 int bnxt_get_avail_msix(struct bnxt *bp, int num);
 int bnxt_reserve_rings(struct bnxt *bp);
 void bnxt_tx_disable(struct bnxt *bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index 840f6e505f73..ba8f8e6af363 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -220,21 +220,6 @@ int bnxt_get_ulp_msix_base(struct bnxt *bp)
 	return 0;
 }
 
-void bnxt_subtract_ulp_resources(struct bnxt *bp, int ulp_id)
-{
-	ASSERT_RTNL();
-	if (bnxt_ulp_registered(bp->edev, ulp_id)) {
-		struct bnxt_en_dev *edev = bp->edev;
-		unsigned int msix_req, max;
-
-		msix_req = edev->ulp_tbl[ulp_id].msix_requested;
-		max = bnxt_get_max_func_cp_rings(bp);
-		bnxt_set_max_func_cp_rings(bp, max - msix_req);
-		max = bnxt_get_max_func_stat_ctxs(bp);
-		bnxt_set_max_func_stat_ctxs(bp, max - 1);
-	}
-}
-
 static int bnxt_send_msg(struct bnxt_en_dev *edev, int ulp_id,
 			 struct bnxt_fw_msg *fw_msg)
 {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
index df48ac71729f..d9bea37cd211 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
@@ -90,7 +90,6 @@ static inline bool bnxt_ulp_registered(struct bnxt_en_dev *edev, int ulp_id)
 
 int bnxt_get_ulp_msix_num(struct bnxt *bp);
 int bnxt_get_ulp_msix_base(struct bnxt *bp);
-void bnxt_subtract_ulp_resources(struct bnxt *bp, int ulp_id);
 void bnxt_ulp_stop(struct bnxt *bp);
 void bnxt_ulp_start(struct bnxt *bp);
 void bnxt_ulp_sriov_cfg(struct bnxt *bp, int num_vfs);
-- 
2.13.6


From d26e94b45b2446e27f5692a7c11fb20e86dd8eb9 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Mon, 3 Sep 2018 04:23:19 -0400
Subject: [PATCH 15/36] bnxt_en: Do not adjust max_cp_rings by the ones used by
 RDMA.

[ Upstream commit 00fe9c326d2027f2437dea38ef0e82f9d02d94c0 ]

Currently, the driver adjusts the bp->hw_resc.max_cp_rings by the number
of MSIX vectors used by RDMA.  There is one code path in open that needs
to check the true max_cp_rings including any used by RDMA.  This code
is now checking for the reduced max_cp_rings which will fail when the
number of cp rings is very small.

To fix this in a clean way, we don't adjust max_cp_rings anymore.
Instead, we add a helper bnxt_get_max_func_cp_rings_for_en() to get the
reduced max_cp_rings when appropriate.

Fixes: ec86f14ea506 ("bnxt_en: Add ULP calls to stop and restart IRQs.")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c       | 7 ++++---
 drivers/net/ethernet/broadcom/bnxt/bnxt.h       | 2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c | 7 ++++---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c   | 5 -----
 4 files changed, 9 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 7fa1dcbd638f..4fdf3d33aa59 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -5907,9 +5907,9 @@ unsigned int bnxt_get_max_func_cp_rings(struct bnxt *bp)
 	return bp->hw_resc.max_cp_rings;
 }
 
-void bnxt_set_max_func_cp_rings(struct bnxt *bp, unsigned int max)
+unsigned int bnxt_get_max_func_cp_rings_for_en(struct bnxt *bp)
 {
-	bp->hw_resc.max_cp_rings = max;
+	return bp->hw_resc.max_cp_rings - bnxt_get_ulp_msix_num(bp);
 }
 
 static unsigned int bnxt_get_max_func_irqs(struct bnxt *bp)
@@ -8492,7 +8492,8 @@ static void _bnxt_get_max_rings(struct bnxt *bp, int *max_rx, int *max_tx,
 
 	*max_tx = hw_resc->max_tx_rings;
 	*max_rx = hw_resc->max_rx_rings;
-	*max_cp = min_t(int, hw_resc->max_irqs, hw_resc->max_cp_rings);
+	*max_cp = min_t(int, bnxt_get_max_func_cp_rings_for_en(bp),
+			hw_resc->max_irqs);
 	*max_cp = min_t(int, *max_cp, hw_resc->max_stat_ctxs);
 	max_ring_grps = hw_resc->max_hw_ring_grps;
 	if (BNXT_CHIP_TYPE_NITRO_A0(bp) && BNXT_PF(bp)) {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index ca9bb24bc265..ea1246a94b38 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1468,7 +1468,7 @@ int bnxt_hwrm_set_coal(struct bnxt *);
 unsigned int bnxt_get_max_func_stat_ctxs(struct bnxt *bp);
 void bnxt_set_max_func_stat_ctxs(struct bnxt *bp, unsigned int max);
 unsigned int bnxt_get_max_func_cp_rings(struct bnxt *bp);
-void bnxt_set_max_func_cp_rings(struct bnxt *bp, unsigned int max);
+unsigned int bnxt_get_max_func_cp_rings_for_en(struct bnxt *bp);
 int bnxt_get_avail_msix(struct bnxt *bp, int num);
 int bnxt_reserve_rings(struct bnxt *bp);
 void bnxt_tx_disable(struct bnxt *bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index a64910892c25..2c77004a022b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -451,7 +451,7 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs)
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_VF_RESOURCE_CFG, -1, -1);
 
-	vf_cp_rings = hw_resc->max_cp_rings - bp->cp_nr_rings;
+	vf_cp_rings = bnxt_get_max_func_cp_rings_for_en(bp) - bp->cp_nr_rings;
 	vf_stat_ctx = hw_resc->max_stat_ctxs - bp->num_stat_ctxs;
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		vf_rx_rings = hw_resc->max_rx_rings - bp->rx_nr_rings * 2;
@@ -544,7 +544,8 @@ static int bnxt_hwrm_func_cfg(struct bnxt *bp, int num_vfs)
 	max_stat_ctxs = hw_resc->max_stat_ctxs;
 
 	/* Remaining rings are distributed equally amongs VF's for now */
-	vf_cp_rings = (hw_resc->max_cp_rings - bp->cp_nr_rings) / num_vfs;
+	vf_cp_rings = (bnxt_get_max_func_cp_rings_for_en(bp) -
+		       bp->cp_nr_rings) / num_vfs;
 	vf_stat_ctx = (max_stat_ctxs - bp->num_stat_ctxs) / num_vfs;
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		vf_rx_rings = (hw_resc->max_rx_rings - bp->rx_nr_rings * 2) /
@@ -638,7 +639,7 @@ static int bnxt_sriov_enable(struct bnxt *bp, int *num_vfs)
 	 */
 	vfs_supported = *num_vfs;
 
-	avail_cp = hw_resc->max_cp_rings - bp->cp_nr_rings;
+	avail_cp = bnxt_get_max_func_cp_rings_for_en(bp) - bp->cp_nr_rings;
 	avail_stat = hw_resc->max_stat_ctxs - bp->num_stat_ctxs;
 	avail_cp = min_t(int, avail_cp, avail_stat);
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index ba8f8e6af363..4209cfd73971 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -169,7 +169,6 @@ static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, int ulp_id,
 		edev->ulp_tbl[ulp_id].msix_requested = avail_msix;
 	}
 	bnxt_fill_msix_vecs(bp, ent);
-	bnxt_set_max_func_cp_rings(bp, max_cp_rings - avail_msix);
 	edev->flags |= BNXT_EN_FLAG_MSIX_REQUESTED;
 	return avail_msix;
 }
@@ -178,7 +177,6 @@ static int bnxt_free_msix_vecs(struct bnxt_en_dev *edev, int ulp_id)
 {
 	struct net_device *dev = edev->net;
 	struct bnxt *bp = netdev_priv(dev);
-	int max_cp_rings, msix_requested;
 
 	ASSERT_RTNL();
 	if (ulp_id != BNXT_ROCE_ULP)
@@ -187,9 +185,6 @@ static int bnxt_free_msix_vecs(struct bnxt_en_dev *edev, int ulp_id)
 	if (!(edev->flags & BNXT_EN_FLAG_MSIX_REQUESTED))
 		return 0;
 
-	max_cp_rings = bnxt_get_max_func_cp_rings(bp);
-	msix_requested = edev->ulp_tbl[ulp_id].msix_requested;
-	bnxt_set_max_func_cp_rings(bp, max_cp_rings + msix_requested);
 	edev->ulp_tbl[ulp_id].msix_requested = 0;
 	edev->flags &= ~BNXT_EN_FLAG_MSIX_REQUESTED;
 	if (netif_running(dev)) {
-- 
2.13.6


From 79e863e81184cb7c3b839558d5c580efc2449534 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Mon, 27 Aug 2018 22:56:22 +0200
Subject: [PATCH 16/36] net/sched: act_pedit: fix dump of extended layered op

[ Upstream commit 85eb9af182243ce9a8b72410d5321c440ac5f8d7 ]

in the (rare) case of failure in nla_nest_start(), missing NULL checks in
tcf_pedit_key_ex_dump() can make the following command

 # tc action add action pedit ex munge ip ttl set 64

dereference a NULL pointer:

 BUG: unable to handle kernel NULL pointer dereference at 0000000000000000
 PGD 800000007d1cd067 P4D 800000007d1cd067 PUD 7acd3067 PMD 0
 Oops: 0002 [#1] SMP PTI
 CPU: 0 PID: 3336 Comm: tc Tainted: G            E     4.18.0.pedit+ #425
 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
 RIP: 0010:tcf_pedit_dump+0x19d/0x358 [act_pedit]
 Code: be 02 00 00 00 48 89 df 66 89 44 24 20 e8 9b b1 fd e0 85 c0 75 46 8b 83 c8 00 00 00 49 83 c5 08 48 03 83 d0 00 00 00 4d 39 f5 <66> 89 04 25 00 00 00 00 0f 84 81 01 00 00 41 8b 45 00 48 8d 4c 24
 RSP: 0018:ffffb5d4004478a8 EFLAGS: 00010246
 RAX: ffff8880fcda2070 RBX: ffff8880fadd2900 RCX: 0000000000000000
 RDX: 0000000000000002 RSI: ffffb5d4004478ca RDI: ffff8880fcda206e
 RBP: ffff8880fb9cb900 R08: 0000000000000008 R09: ffff8880fcda206e
 R10: ffff8880fadd2900 R11: 0000000000000000 R12: ffff8880fd26cf40
 R13: ffff8880fc957430 R14: ffff8880fc957430 R15: ffff8880fb9cb988
 FS:  00007f75a537a740(0000) GS:ffff8880fda00000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000000000 CR3: 000000007a2fa005 CR4: 00000000001606f0
 Call Trace:
  ? __nla_reserve+0x38/0x50
  tcf_action_dump_1+0xd2/0x130
  tcf_action_dump+0x6a/0xf0
  tca_get_fill.constprop.31+0xa3/0x120
  tcf_action_add+0xd1/0x170
  tc_ctl_action+0x137/0x150
  rtnetlink_rcv_msg+0x263/0x2d0
  ? _cond_resched+0x15/0x40
  ? rtnl_calcit.isra.30+0x110/0x110
  netlink_rcv_skb+0x4d/0x130
  netlink_unicast+0x1a3/0x250
  netlink_sendmsg+0x2ae/0x3a0
  sock_sendmsg+0x36/0x40
  ___sys_sendmsg+0x26f/0x2d0
  ? do_wp_page+0x8e/0x5f0
  ? handle_pte_fault+0x6c3/0xf50
  ? __handle_mm_fault+0x38e/0x520
  ? __sys_sendmsg+0x5e/0xa0
  __sys_sendmsg+0x5e/0xa0
  do_syscall_64+0x5b/0x180
  entry_SYSCALL_64_after_hwframe+0x44/0xa9
 RIP: 0033:0x7f75a4583ba0
 Code: c3 48 8b 05 f2 62 2c 00 f7 db 64 89 18 48 83 cb ff eb dd 0f 1f 80 00 00 00 00 83 3d fd c3 2c 00 00 75 10 b8 2e 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 ae cc 00 00 48 89 04 24
 RSP: 002b:00007fff60ee7418 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
 RAX: ffffffffffffffda RBX: 00007fff60ee7540 RCX: 00007f75a4583ba0
 RDX: 0000000000000000 RSI: 00007fff60ee7490 RDI: 0000000000000003
 RBP: 000000005b842d3e R08: 0000000000000002 R09: 0000000000000000
 R10: 00007fff60ee6ea0 R11: 0000000000000246 R12: 0000000000000000
 R13: 00007fff60ee7554 R14: 0000000000000001 R15: 000000000066c100
 Modules linked in: act_pedit(E) ip6table_filter ip6_tables iptable_filter binfmt_misc crct10dif_pclmul ext4 crc32_pclmul mbcache ghash_clmulni_intel jbd2 pcbc snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hda_core snd_hwdep snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd snd_timer cryptd glue_helper snd joydev pcspkr soundcore virtio_balloon i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c ata_generic pata_acpi virtio_net net_failover virtio_blk virtio_console failover qxl crc32c_intel drm_kms_helper syscopyarea serio_raw sysfillrect sysimgblt fb_sys_fops ttm drm ata_piix virtio_pci libata virtio_ring i2c_core virtio floppy dm_mirror dm_region_hash dm_log dm_mod [last unloaded: act_pedit]
 CR2: 0000000000000000

Like it's done for other TC actions, give up dumping pedit rules and return
an error if nla_nest_start() returns NULL.

Fixes: 71d0ed7079df ("net/act_pedit: Support using offset relative to the conventional network headers")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_pedit.c | 18 +++++++++++++-----
 1 file changed, 13 insertions(+), 5 deletions(-)

diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 8a925c72db5f..bad475c87688 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -109,16 +109,18 @@ static int tcf_pedit_key_ex_dump(struct sk_buff *skb,
 {
 	struct nlattr *keys_start = nla_nest_start(skb, TCA_PEDIT_KEYS_EX);
 
+	if (!keys_start)
+		goto nla_failure;
 	for (; n > 0; n--) {
 		struct nlattr *key_start;
 
 		key_start = nla_nest_start(skb, TCA_PEDIT_KEY_EX);
+		if (!key_start)
+			goto nla_failure;
 
 		if (nla_put_u16(skb, TCA_PEDIT_KEY_EX_HTYPE, keys_ex->htype) ||
-		    nla_put_u16(skb, TCA_PEDIT_KEY_EX_CMD, keys_ex->cmd)) {
-			nlmsg_trim(skb, keys_start);
-			return -EINVAL;
-		}
+		    nla_put_u16(skb, TCA_PEDIT_KEY_EX_CMD, keys_ex->cmd))
+			goto nla_failure;
 
 		nla_nest_end(skb, key_start);
 
@@ -128,6 +130,9 @@ static int tcf_pedit_key_ex_dump(struct sk_buff *skb,
 	nla_nest_end(skb, keys_start);
 
 	return 0;
+nla_failure:
+	nla_nest_cancel(skb, keys_start);
+	return -EINVAL;
 }
 
 static int tcf_pedit_init(struct net *net, struct nlattr *nla,
@@ -395,7 +400,10 @@ static int tcf_pedit_dump(struct sk_buff *skb, struct tc_action *a,
 	opt->bindcnt = p->tcf_bindcnt - bind;
 
 	if (p->tcfp_keys_ex) {
-		tcf_pedit_key_ex_dump(skb, p->tcfp_keys_ex, p->tcfp_nkeys);
+		if (tcf_pedit_key_ex_dump(skb,
+					  p->tcfp_keys_ex,
+					  p->tcfp_nkeys))
+			goto nla_put_failure;
 
 		if (nla_put(skb, TCA_PEDIT_PARMS_EX, s, opt))
 			goto nla_put_failure;
-- 
2.13.6


From 155284910b6c51953ce4cfaa7de535c0dbbb76d9 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 23 Aug 2018 16:19:44 -0700
Subject: [PATCH 17/36] tipc: fix a missing rhashtable_walk_exit()

[ Upstream commit bd583fe30427500a2d0abe25724025b1cb5e2636 ]

rhashtable_walk_exit() must be paired with rhashtable_walk_enter().

Fixes: 40f9f4397060 ("tipc: Fix tipc_sk_reinit race conditions")
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/socket.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 930852c54d7a..0a5fa347135e 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2675,6 +2675,8 @@ void tipc_sk_reinit(struct net *net)
 
 		rhashtable_walk_stop(&iter);
 	} while (tsk == ERR_PTR(-EAGAIN));
+
+	rhashtable_walk_exit(&iter);
 }
 
 static struct tipc_sock *tipc_sk_lookup(struct net *net, u32 portid)
-- 
2.13.6


From 26f8da87359ec62afb146b4defb44b5015b73ecd Mon Sep 17 00:00:00 2001
From: Dexuan Cui <decui@microsoft.com>
Date: Thu, 30 Aug 2018 05:42:13 +0000
Subject: [PATCH 18/36] hv_netvsc: Fix a deadlock by getting rtnl lock earlier
 in netvsc_probe()

[ Upstream commit e04e7a7bbd4bbabef4e1a58367e5fc9b2edc3b10 ]

This patch fixes the race between netvsc_probe() and
rndis_set_subchannel(), which can cause a deadlock.

These are the related 3 paths which show the deadlock:

path #1:
    Workqueue: hv_vmbus_con vmbus_onmessage_work [hv_vmbus]
    Call Trace:
     schedule
     schedule_preempt_disabled
     __mutex_lock
     __device_attach
     bus_probe_device
     device_add
     vmbus_device_register
     vmbus_onoffer
     vmbus_onmessage_work
     process_one_work
     worker_thread
     kthread
     ret_from_fork

path #2:
    schedule
     schedule_preempt_disabled
     __mutex_lock
     netvsc_probe
     vmbus_probe
     really_probe
     __driver_attach
     bus_for_each_dev
     driver_attach_async
     async_run_entry_fn
     process_one_work
     worker_thread
     kthread
     ret_from_fork

path #3:
    Workqueue: events netvsc_subchan_work [hv_netvsc]
    Call Trace:
     schedule
     rndis_set_subchannel
     netvsc_subchan_work
     process_one_work
     worker_thread
     kthread
     ret_from_fork

Before path #1 finishes, path #2 can start to run, because just before
the "bus_probe_device(dev);" in device_add() in path #1, there is a line
"object_uevent(&dev->kobj, KOBJ_ADD);", so systemd-udevd can
immediately try to load hv_netvsc and hence path #2 can start to run.

Next, path #2 offloads the subchannal's initialization to a workqueue,
i.e. path #3, so we can end up in a deadlock situation like this:

Path #2 gets the device lock, and is trying to get the rtnl lock;
Path #3 gets the rtnl lock and is waiting for all the subchannel messages
to be processed;
Path #1 is trying to get the device lock, but since #2 is not releasing
the device lock, path #1 has to sleep; since the VMBus messages are
processed one by one, this means the sub-channel messages can't be
procedded, so #3 has to sleep with the rtnl lock held, and finally #2
has to sleep... Now all the 3 paths are sleeping and we hit the deadlock.

With the patch, we can make sure #2 gets both the device lock and the
rtnl lock together, gets its job done, and releases the locks, so #1
and #3 will not be blocked for ever.

Fixes: 8195b1396ec8 ("hv_netvsc: fix deadlock on hotplug")
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/netvsc_drv.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index dd1d6e115145..df6fab625923 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -2101,6 +2101,16 @@ static int netvsc_probe(struct hv_device *dev,
 
 	memcpy(net->dev_addr, device_info.mac_adr, ETH_ALEN);
 
+	/* We must get rtnl lock before scheduling nvdev->subchan_work,
+	 * otherwise netvsc_subchan_work() can get rtnl lock first and wait
+	 * all subchannels to show up, but that may not happen because
+	 * netvsc_probe() can't get rtnl lock and as a result vmbus_onoffer()
+	 * -> ... -> device_add() -> ... -> __device_attach() can't get
+	 * the device lock, so all the subchannels can't be processed --
+	 * finally netvsc_subchan_work() hangs for ever.
+	 */
+	rtnl_lock();
+
 	if (nvdev->num_chn > 1)
 		schedule_work(&nvdev->subchan_work);
 
@@ -2119,7 +2129,6 @@ static int netvsc_probe(struct hv_device *dev,
 	else
 		net->max_mtu = ETH_DATA_LEN;
 
-	rtnl_lock();
 	ret = register_netdevice(net);
 	if (ret != 0) {
 		pr_err("Unable to register netdev.\n");
-- 
2.13.6


From d54a9949f098afe87bc13601711954356b82aaa9 Mon Sep 17 00:00:00 2001
From: Haiqing Bai <Haiqing.Bai@windriver.com>
Date: Mon, 27 Aug 2018 09:32:26 +0800
Subject: [PATCH 19/36] tipc: fix the big/little endian issue in tipc_dest

[ Upstream commit 30935198b7d0be12b1c45c328b66a7fdefb16256 ]

In function tipc_dest_push, the 32bit variables 'node' and 'port'
are stored separately in uppper and lower part of 64bit 'value'.
Then this value is assigned to dst->value which is a union like:
union
{
  struct {
    u32 port;
    u32 node;
  };
  u64 value;
}
This works on little-endian machines like x86 but fails on big-endian
machines.

The fix remove the 'value' stack parameter and even the 'value'
member of the union in tipc_dest, assign the 'node' and 'port' member
directly with the input parameter to avoid the endian issue.

Fixes: a80ae5306a73 ("tipc: improve destination linked list")
Signed-off-by: Zhenbo Gao <zhenbo.gao@windriver.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Haiqing Bai <Haiqing.Bai@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/name_table.c | 10 ++++------
 net/tipc/name_table.h |  9 ++-------
 2 files changed, 6 insertions(+), 13 deletions(-)

diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index bebe88cae07b..ff968c7afef6 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -980,20 +980,17 @@ int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb)
 
 struct tipc_dest *tipc_dest_find(struct list_head *l, u32 node, u32 port)
 {
-	u64 value = (u64)node << 32 | port;
 	struct tipc_dest *dst;
 
 	list_for_each_entry(dst, l, list) {
-		if (dst->value != value)
-			continue;
-		return dst;
+		if (dst->node == node && dst->port == port)
+			return dst;
 	}
 	return NULL;
 }
 
 bool tipc_dest_push(struct list_head *l, u32 node, u32 port)
 {
-	u64 value = (u64)node << 32 | port;
 	struct tipc_dest *dst;
 
 	if (tipc_dest_find(l, node, port))
@@ -1002,7 +999,8 @@ bool tipc_dest_push(struct list_head *l, u32 node, u32 port)
 	dst = kmalloc(sizeof(*dst), GFP_ATOMIC);
 	if (unlikely(!dst))
 		return false;
-	dst->value = value;
+	dst->node = node;
+	dst->port = port;
 	list_add(&dst->list, l);
 	return true;
 }
diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h
index 0febba41da86..892bd750b85f 100644
--- a/net/tipc/name_table.h
+++ b/net/tipc/name_table.h
@@ -133,13 +133,8 @@ void tipc_nametbl_stop(struct net *net);
 
 struct tipc_dest {
 	struct list_head list;
-	union {
-		struct {
-			u32 port;
-			u32 node;
-		};
-		u64 value;
-	};
+	u32 port;
+	u32 node;
 };
 
 struct tipc_dest *tipc_dest_find(struct list_head *l, u32 node, u32 port);
-- 
2.13.6


From 78a3f867b4029ac37391a4e575ea8bd46388ceb8 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 27 Aug 2018 18:40:18 +0800
Subject: [PATCH 20/36] sctp: remove useless start_fail from sctp_ht_iter in
 proc

[ Upstream commit 834539e69a5fe2aab33cc777ccfd4a4fcc5b9770 ]

After changing rhashtable_walk_start to return void, start_fail would
never be set other value than 0, and the checking for start_fail is
pointless, so remove it.

Fixes: 97a6ec4ac021 ("rhashtable: Change rhashtable_walk_start to return void")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/proc.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/net/sctp/proc.c b/net/sctp/proc.c
index ef5c9a82d4e8..14ab9358d660 100644
--- a/net/sctp/proc.c
+++ b/net/sctp/proc.c
@@ -215,7 +215,6 @@ static const struct seq_operations sctp_eps_ops = {
 struct sctp_ht_iter {
 	struct seq_net_private p;
 	struct rhashtable_iter hti;
-	int start_fail;
 };
 
 static void *sctp_transport_seq_start(struct seq_file *seq, loff_t *pos)
@@ -224,7 +223,6 @@ static void *sctp_transport_seq_start(struct seq_file *seq, loff_t *pos)
 
 	sctp_transport_walk_start(&iter->hti);
 
-	iter->start_fail = 0;
 	return sctp_transport_get_idx(seq_file_net(seq), &iter->hti, *pos);
 }
 
@@ -232,8 +230,6 @@ static void sctp_transport_seq_stop(struct seq_file *seq, void *v)
 {
 	struct sctp_ht_iter *iter = seq->private;
 
-	if (iter->start_fail)
-		return;
 	sctp_transport_walk_stop(&iter->hti);
 }
 
-- 
2.13.6


From 7a26a07bf1ade2dd3b597fcdb0231adee79c3da1 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 27 Aug 2018 18:41:32 +0800
Subject: [PATCH 21/36] erspan: set erspan_ver to 1 by default when adding an
 erspan dev

[ Upstream commit 84581bdae9587023cea1d139523f0ef0f28bd88d ]

After erspan_ver is introudced, if erspan_ver is not set in iproute, its
value will be left 0 by default. Since Commit 02f99df1875c ("erspan: fix
invalid erspan version."), it has broken the traffic due to the version
check in erspan_xmit if users are not aware of 'erspan_ver' param, like
using an old version of iproute.

To fix this compatibility problem, it sets erspan_ver to 1 by default
when adding an erspan dev in erspan_setup. Note that we can't do it in
ipgre_netlink_parms, as this function is also used by ipgre_changelink.

Fixes: 02f99df1875c ("erspan: fix invalid erspan version.")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_gre.c  | 3 +++
 net/ipv6/ip6_gre.c | 1 +
 2 files changed, 4 insertions(+)

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 2d8efeecf619..055f4bbba86b 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1511,11 +1511,14 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev)
 
 static void erspan_setup(struct net_device *dev)
 {
+	struct ip_tunnel *t = netdev_priv(dev);
+
 	ether_setup(dev);
 	dev->netdev_ops = &erspan_netdev_ops;
 	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 	ip_tunnel_setup(dev, erspan_net_id);
+	t->erspan_ver = 1;
 }
 
 static const struct nla_policy ipgre_policy[IFLA_GRE_MAX + 1] = {
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index cd2cfb04e5d8..7ec997fcbc43 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1776,6 +1776,7 @@ static void ip6gre_netlink_parms(struct nlattr *data[],
 	if (data[IFLA_GRE_COLLECT_METADATA])
 		parms->collect_md = true;
 
+	parms->erspan_ver = 1;
 	if (data[IFLA_GRE_ERSPAN_VER])
 		parms->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]);
 
-- 
2.13.6


From 9a3d2524d0a194e6883148af032a2ab488b867aa Mon Sep 17 00:00:00 2001
From: Ahmad Fatoum <a.fatoum@pengutronix.de>
Date: Tue, 21 Aug 2018 17:35:48 +0200
Subject: [PATCH 22/36] net: macb: Fix regression breaking non-MDIO fixed-link
 PHYs

[ Upstream commit ab5f11055fdf8dfc3ddbd89e8e3cc550de41d1d3 ]

commit 739de9a1563a ("net: macb: Reorganize macb_mii bringup") broke
initializing macb on the EVB-KSZ9477 eval board.
There, of_mdiobus_register was called even for the fixed-link representing
the RGMII-link to the switch with the result that the driver attempts to
enumerate PHYs on a non-existent MDIO bus:

	libphy: MACB_mii_bus: probed
	mdio_bus f0028000.ethernet-ffffffff: fixed-link has invalid PHY address
	mdio_bus f0028000.ethernet-ffffffff: scan phy fixed-link at address 0
        [snip]
	mdio_bus f0028000.ethernet-ffffffff: scan phy fixed-link at address 31

The "MDIO" bus registration succeeds regardless, having claimed the reset GPIO,
and calling of_phy_register_fixed_link later on fails because it tries
to claim the same GPIO:

	macb f0028000.ethernet: broken fixed-link specification

Fix this by registering the fixed-link before calling mdiobus_register.

Fixes: 739de9a1563a ("net: macb: Reorganize macb_mii bringup")
Signed-off-by: Ahmad Fatoum <a.fatoum@pengutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 27 +++++++++++++++++----------
 1 file changed, 17 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index e4b4a6a879be..515d96e32143 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -481,11 +481,6 @@ static int macb_mii_probe(struct net_device *dev)
 
 	if (np) {
 		if (of_phy_is_fixed_link(np)) {
-			if (of_phy_register_fixed_link(np) < 0) {
-				dev_err(&bp->pdev->dev,
-					"broken fixed-link specification\n");
-				return -ENODEV;
-			}
 			bp->phy_node = of_node_get(np);
 		} else {
 			bp->phy_node = of_parse_phandle(np, "phy-handle", 0);
@@ -568,7 +563,7 @@ static int macb_mii_init(struct macb *bp)
 {
 	struct macb_platform_data *pdata;
 	struct device_node *np;
-	int err;
+	int err = -ENXIO;
 
 	/* Enable management port */
 	macb_writel(bp, NCR, MACB_BIT(MPE));
@@ -591,12 +586,23 @@ static int macb_mii_init(struct macb *bp)
 	dev_set_drvdata(&bp->dev->dev, bp->mii_bus);
 
 	np = bp->pdev->dev.of_node;
-	if (pdata)
-		bp->mii_bus->phy_mask = pdata->phy_mask;
+	if (np && of_phy_is_fixed_link(np)) {
+		if (of_phy_register_fixed_link(np) < 0) {
+			dev_err(&bp->pdev->dev,
+				"broken fixed-link specification %pOF\n", np);
+			goto err_out_free_mdiobus;
+		}
+
+		err = mdiobus_register(bp->mii_bus);
+	} else {
+		if (pdata)
+			bp->mii_bus->phy_mask = pdata->phy_mask;
+
+		err = of_mdiobus_register(bp->mii_bus, np);
+	}
 
-	err = of_mdiobus_register(bp->mii_bus, np);
 	if (err)
-		goto err_out_free_mdiobus;
+		goto err_out_free_fixed_link;
 
 	err = macb_mii_probe(bp->dev);
 	if (err)
@@ -606,6 +612,7 @@ static int macb_mii_init(struct macb *bp)
 
 err_out_unregister_bus:
 	mdiobus_unregister(bp->mii_bus);
+err_out_free_fixed_link:
 	if (np && of_phy_is_fixed_link(np))
 		of_phy_deregister_fixed_link(np);
 err_out_free_mdiobus:
-- 
2.13.6


From 032a9ebfc36f8cd035f1e1620000e474f2470da0 Mon Sep 17 00:00:00 2001
From: Alexey Kodanev <alexey.kodanev@oracle.com>
Date: Thu, 30 Aug 2018 19:11:24 +0300
Subject: [PATCH 23/36] ipv6: don't get lwtstate twice in ip6_rt_copy_init()

[ Upstream commit 93bbadd6e0a2a58e49d265b9b1aa58e621b60a26 ]

Commit 80f1a0f4e0cd ("net/ipv6: Put lwtstate when destroying fib6_info")
partially fixed the kmemleak [1], lwtstate can be copied from fib6_info,
with ip6_rt_copy_init(), and it should be done only once there.

rt->dst.lwtstate is set by ip6_rt_init_dst(), at the start of the function
ip6_rt_copy_init(), so there is no need to get it again at the end.

With this patch, lwtstate also isn't copied from RTF_REJECT routes.

[1]:
unreferenced object 0xffff880b6aaa14e0 (size 64):
  comm "ip", pid 10577, jiffies 4295149341 (age 1273.903s)
  hex dump (first 32 bytes):
    01 00 04 00 04 00 00 00 10 00 00 00 00 00 00 00  ................
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<0000000018664623>] lwtunnel_build_state+0x1bc/0x420
    [<00000000b73aa29a>] ip6_route_info_create+0x9f7/0x1fd0
    [<00000000ee2c5d1f>] ip6_route_add+0x14/0x70
    [<000000008537b55c>] inet6_rtm_newroute+0xd9/0xe0
    [<000000002acc50f5>] rtnetlink_rcv_msg+0x66f/0x8e0
    [<000000008d9cd381>] netlink_rcv_skb+0x268/0x3b0
    [<000000004c893c76>] netlink_unicast+0x417/0x5a0
    [<00000000f2ab1afb>] netlink_sendmsg+0x70b/0xc30
    [<00000000890ff0aa>] sock_sendmsg+0xb1/0xf0
    [<00000000a2e7b66f>] ___sys_sendmsg+0x659/0x950
    [<000000001e7426c8>] __sys_sendmsg+0xde/0x170
    [<00000000fe411443>] do_syscall_64+0x9f/0x4a0
    [<000000001be7b28b>] entry_SYSCALL_64_after_hwframe+0x49/0xbe
    [<000000006d21f353>] 0xffffffffffffffff

Fixes: 6edb3c96a5f0 ("net/ipv6: Defer initialization of dst to data path")
Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 7208c16302f6..10da55961f14 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -996,7 +996,6 @@ static void ip6_rt_copy_init(struct rt6_info *rt, struct fib6_info *ort)
 	rt->rt6i_src = ort->fib6_src;
 #endif
 	rt->rt6i_prefsrc = ort->fib6_prefsrc;
-	rt->dst.lwtstate = lwtstate_get(ort->fib6_nh.nh_lwtstate);
 }
 
 static struct fib6_node* fib6_backtrack(struct fib6_node *fn,
-- 
2.13.6


From f77ae6e4f7641f304bbe9d7fa7a04126f4f0223c Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Thu, 23 Aug 2018 11:31:37 +0800
Subject: [PATCH 24/36] net/ipv6: init ip6 anycast rt->dst.input as ip6_input

[ Upstream commit d23c4b6336ef30898dcdff351f21e633e7a64930 ]

Commit 6edb3c96a5f02 ("net/ipv6: Defer initialization of dst to data path")
forgot to handle anycast route and init anycast rt->dst.input to ip6_forward.
Fix it by setting anycast rt->dst.input back to ip6_input.

Fixes: 6edb3c96a5f02 ("net/ipv6: Defer initialization of dst to data path")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 10da55961f14..18e00ce1719a 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -956,7 +956,7 @@ static void ip6_rt_init_dst(struct rt6_info *rt, struct fib6_info *ort)
 	rt->dst.error = 0;
 	rt->dst.output = ip6_output;
 
-	if (ort->fib6_type == RTN_LOCAL) {
+	if (ort->fib6_type == RTN_LOCAL || ort->fib6_type == RTN_ANYCAST) {
 		rt->dst.input = ip6_input;
 	} else if (ipv6_addr_type(&ort->fib6_dst.addr) & IPV6_ADDR_MULTICAST) {
 		rt->dst.input = ip6_mc_input;
-- 
2.13.6


From 7f6a93daf9a4bbf0f6022f39a9623daa65e1108f Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Thu, 30 Aug 2018 14:15:43 -0700
Subject: [PATCH 25/36] net/ipv6: Only update MTU metric if it set

[ Upstream commit 15a81b418e22a9aa4a0504471fdcb0f4ebf69b96 ]

Jan reported a regression after an update to 4.18.5. In this case ipv6
default route is setup by systemd-networkd based on data from an RA. The
RA contains an MTU of 1492 which is used when the route is first inserted
but then systemd-networkd pushes down updates to the default route
without the mtu set.

Prior to the change to fib6_info, metrics such as MTU were held in the
dst_entry and rt6i_pmtu in rt6_info contained an update to the mtu if
any. ip6_mtu would look at rt6i_pmtu first and use it if set. If not,
the value from the metrics is used if it is set and finally falling
back to the idev value.

After the fib6_info change metrics are contained in the fib6_info struct
and there is no equivalent to rt6i_pmtu. To maintain consistency with
the old behavior the new code should only reset the MTU in the metrics
if the route update has it set.

Fixes: d4ead6b34b67 ("net/ipv6: move metrics from dst to rt6_info")
Reported-by: Jan Janssen <medhefgo@web.de>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_fib.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index d212738e9d10..f43d278e0040 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -987,7 +987,10 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
 					fib6_clean_expires(iter);
 				else
 					fib6_set_expires(iter, rt->expires);
-				fib6_metric_set(iter, RTAX_MTU, rt->fib6_pmtu);
+
+				if (rt->fib6_pmtu)
+					fib6_metric_set(iter, RTAX_MTU,
+							rt->fib6_pmtu);
 				return -EEXIST;
 			}
 			/* If we have the same destination and the same metric,
-- 
2.13.6


From 25f9c7b1a8662edccf2f9be3aeb66da440805a59 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Mon, 20 Aug 2018 13:02:41 -0700
Subject: [PATCH 26/36] net/ipv6: Put lwtstate when destroying fib6_info

[ Upstream commit 80f1a0f4e0cd4bfc8a74fc1c39843a6e7b206b95 ]

Prior to the introduction of fib6_info lwtstate was managed by the dst
code. With fib6_info releasing lwtstate needs to be done when the struct
is freed.

Fixes: 93531c674315 ("net/ipv6: separate handling of FIB entries from dst based routes")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_fib.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index f43d278e0040..5516f55e214b 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -198,6 +198,8 @@ void fib6_info_destroy_rcu(struct rcu_head *head)
 		}
 	}
 
+	lwtstate_put(f6i->fib6_nh.nh_lwtstate);
+
 	if (f6i->fib6_nh.nh_dev)
 		dev_put(f6i->fib6_nh.nh_dev);
 
-- 
2.13.6


From 764dda168da8d293dbb4edc2e76112f893a6f91a Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Mon, 3 Sep 2018 18:06:24 +0300
Subject: [PATCH 27/36] net/mlx5: Fix SQ offset in QPs with small RQ

[ Upstream commit 639505d4397b8c654a8e2616f9cb70ece40c83f9 ]

Correct the formula for calculating the RQ page remainder,
which should be in byte granularity.  The result will be
non-zero only for RQs smaller than PAGE_SIZE, as an RQ size
is a power of 2.

Divide this by the SQ stride (MLX5_SEND_WQE_BB) to get the
SQ offset in strides granularity.

Fixes: d7037ad73daa ("net/mlx5: Fix QP fragmented buffer allocation")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/wq.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c
index 86478a6b99c5..c8c315eb5128 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c
@@ -139,14 +139,15 @@ int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		      struct mlx5_wq_ctrl *wq_ctrl)
 {
 	u32 sq_strides_offset;
+	u32 rq_pg_remainder;
 	int err;
 
 	mlx5_fill_fbc(MLX5_GET(qpc, qpc, log_rq_stride) + 4,
 		      MLX5_GET(qpc, qpc, log_rq_size),
 		      &wq->rq.fbc);
 
-	sq_strides_offset =
-		((wq->rq.fbc.frag_sz_m1 + 1) % PAGE_SIZE) / MLX5_SEND_WQE_BB;
+	rq_pg_remainder   = mlx5_wq_cyc_get_byte_size(&wq->rq) % PAGE_SIZE;
+	sq_strides_offset = rq_pg_remainder / MLX5_SEND_WQE_BB;
 
 	mlx5_fill_fbc_offset(ilog2(MLX5_SEND_WQE_BB),
 			     MLX5_GET(qpc, qpc, log_sq_size),
-- 
2.13.6


From a0047ebb43d597d1889ccfae1d6ff6d45572e073 Mon Sep 17 00:00:00 2001
From: Azat Khuzhin <a3at.mail@gmail.com>
Date: Sun, 26 Aug 2018 17:03:09 +0300
Subject: [PATCH 28/36] r8169: set RxConfig after tx/rx is enabled for
 RTL8169sb/8110sb devices

[ Upstream commit 05212ba8132b42047ab5d63d759c6f9c28e7eab5 ]

I have two Ethernet adapters:
  r8169 0000:03:01.0 eth0: RTL8169sb/8110sb, 00:14:d1:14:2d:49, XID 10000000, IRQ 18
  r8169 0000:01:00.0 eth0: RTL8168e/8111e, 64:66:b3:11:14:5d, XID 2c200000, IRQ 30
And after upgrading from linux 4.15 [1] to linux 4.18+ [2] RTL8169sb failed to
receive any packets. tcpdump shows a lot of checksum mismatch.

  [1]: a0f79386a4968b4925da6db2d1daffd0605a4402
  [2]: 0519359784328bfa92bf0931bf0cff3b58c16932 (4.19 merge window opened)

I started bisecting and the found that [3] breaks it. According to [4]:
  "For 8110S, 8110SB, and 8110SC series, the initial value of RxConfig
  needs to be set after the tx/rx is enabled."
So I moved rtl_init_rxcfg() after enabling tx/rs and now my adapter works
(RTL8168e works too).

  [3]: 3559d81e76bfe3803e89f2e04cf6ef7ab4f3aace
  [4]: e542a2269f232d61270ceddd42b73a4348dee2bb ("r8169: adjust the RxConfig
settings.")

Also drop "rx" from rtl_set_rx_tx_config_registers(), since it does nothing
with it already.

Fixes: 3559d81e76bfe3803e89f2e04cf6ef7ab4f3aace ("r8169: simplify
rtl_hw_start_8169")

Cc: Heiner Kallweit <hkallweit1@gmail.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Cc: Realtek linux nic maintainers <nic_swsd@realtek.com>
Signed-off-by: Azat Khuzhin <a3at.mail@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 65e4e392774a..e5eb361b973c 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -5039,7 +5039,7 @@ static void rtl8169_hw_reset(struct rtl8169_private *tp)
 	rtl_hw_reset(tp);
 }
 
-static void rtl_set_rx_tx_config_registers(struct rtl8169_private *tp)
+static void rtl_set_tx_config_registers(struct rtl8169_private *tp)
 {
 	/* Set DMA burst size and Interframe Gap Time */
 	RTL_W32(tp, TxConfig, (TX_DMA_BURST << TxDMAShift) |
@@ -5150,12 +5150,14 @@ static void rtl_hw_start(struct  rtl8169_private *tp)
 
 	rtl_set_rx_max_size(tp);
 	rtl_set_rx_tx_desc_registers(tp);
-	rtl_set_rx_tx_config_registers(tp);
+	rtl_set_tx_config_registers(tp);
 	RTL_W8(tp, Cfg9346, Cfg9346_Lock);
 
 	/* Initially a 10 us delay. Turned it into a PCI commit. - FR */
 	RTL_R8(tp, IntrMask);
 	RTL_W8(tp, ChipCmd, CmdTxEnb | CmdRxEnb);
+	rtl_init_rxcfg(tp);
+
 	rtl_set_rx_mode(tp->dev);
 	/* no early-rx interrupts */
 	RTL_W16(tp, MultiIntr, RTL_R16(tp, MultiIntr) & 0xf000);
-- 
2.13.6


From fbd7c287a16f1d5fc58d7da5f4fe0912854f90b1 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Fri, 24 Aug 2018 11:04:40 +0200
Subject: [PATCH 29/36] Revert "net: stmmac: Do not keep rearming the coalesce
 timer in stmmac_xmit"

[ Upstream commit e5133f2f1261f8ab412e7fc5e3694c9f84328f89 ]

This reverts commit 4ae0169fd1b3c792b66be58995b7e6b629919ecf.

This change in the handling of the coalesce timer is causing regression on
(at least) amlogic platforms.

Network will break down very quickly (a few seconds) after starting
a download. This can easily be reproduced using iperf3 for example.

The problem has been reported on the S805, S905, S912 and A113 SoCs
(Realtek and Micrel PHYs) and it is likely impacting all Amlogics
platforms using Gbit ethernet

No problem was seen with the platform using 10/100 only PHYs (GXL internal)

Reverting change brings things back to normal and allows to use network
again until we better understand the problem with the coalesce timer.

Cc: Jose Abreu <joabreu@synopsys.com>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Vitor Soares <soares@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Cc: Corentin Labbe <clabbe@baylibre.com>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac.h      | 1 -
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 5 +----
 2 files changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index 76649adf8fb0..c0a855b7ab3b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -112,7 +112,6 @@ struct stmmac_priv {
 	u32 tx_count_frames;
 	u32 tx_coal_frames;
 	u32 tx_coal_timer;
-	bool tx_timer_armed;
 
 	int tx_coalesce;
 	int hwts_tx_en;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index ef6a8d39db2f..c579d98b9666 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3126,16 +3126,13 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 	 * element in case of no SG.
 	 */
 	priv->tx_count_frames += nfrags + 1;
-	if (likely(priv->tx_coal_frames > priv->tx_count_frames) &&
-	    !priv->tx_timer_armed) {
+	if (likely(priv->tx_coal_frames > priv->tx_count_frames)) {
 		mod_timer(&priv->txtimer,
 			  STMMAC_COAL_TIMER(priv->tx_coal_timer));
-		priv->tx_timer_armed = true;
 	} else {
 		priv->tx_count_frames = 0;
 		stmmac_set_tx_ic(priv, desc);
 		priv->xstats.tx_set_ic_bit++;
-		priv->tx_timer_armed = false;
 	}
 
 	skb_tx_timestamp(skb);
-- 
2.13.6


From 83e14dc50857d8541afe5780e285733044f68618 Mon Sep 17 00:00:00 2001
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Sun, 19 Aug 2018 15:05:05 +0800
Subject: [PATCH 30/36] ip6_vti: fix creating fallback tunnel device for vti6

[ Upstream commit e2948e5af8eeb6c945000772b7613b0323a0a203 ]

When set fb_tunnels_only_for_init_net to 1, don't create fallback tunnel
device for vti6 when a new namespace is created.

Tested:
[root@builder2 ~]# modprobe ip6_tunnel
[root@builder2 ~]# modprobe ip6_vti
[root@builder2 ~]# echo 1 > /proc/sys/net/core/fb_tunnels_only_for_init_net
[root@builder2 ~]# unshare -n
[root@builder2 ~]# ip link
1: lo: <LOOPBACK> mtu 65536 qdisc noop state DOWN mode DEFAULT group
default qlen 1000
    link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00

Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_vti.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index fbd3752ea587..71b2fccd1484 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -1114,6 +1114,8 @@ static int __net_init vti6_init_net(struct net *net)
 	ip6n->tnls[0] = ip6n->tnls_wc;
 	ip6n->tnls[1] = ip6n->tnls_r_l;
 
+	if (!net_has_fallback_tunnels(net))
+		return 0;
 	err = -ENOMEM;
 	ip6n->fb_tnl_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6_vti0",
 					NET_NAME_UNKNOWN, vti6_dev_setup);
-- 
2.13.6


From 2d0685ed0487e68e113be7323dfd49642b710b9e Mon Sep 17 00:00:00 2001
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Mon, 20 Aug 2018 10:51:05 +0800
Subject: [PATCH 31/36] ip6_vti: fix a null pointer deference when destroy vti6
 tunnel

[ Upstream commit 9c86336c15db1c48cbaddff56caf2be0a930e991 ]

If load ip6_vti module and create a network namespace when set
fb_tunnels_only_for_init_net to 1, then exit the namespace will
cause following crash:

[ 6601.677036] BUG: unable to handle kernel NULL pointer dereference at 0000000000000008
[ 6601.679057] PGD 8000000425eca067 P4D 8000000425eca067 PUD 424292067 PMD 0
[ 6601.680483] Oops: 0000 [#1] SMP PTI
[ 6601.681223] CPU: 7 PID: 93 Comm: kworker/u16:1 Kdump: loaded Tainted: G            E     4.18.0+ #3
[ 6601.683153] Hardware name: Fedora Project OpenStack Nova, BIOS seabios-1.7.5-11.el7 04/01/2014
[ 6601.684919] Workqueue: netns cleanup_net
[ 6601.685742] RIP: 0010:vti6_exit_batch_net+0x87/0xd0 [ip6_vti]
[ 6601.686932] Code: 7b 08 48 89 e6 e8 b9 ea d3 dd 48 8b 1b 48 85 db 75 ec 48 83 c5 08 48 81 fd 00 01 00 00 75 d5 49 8b 84 24 08 01 00 00 48 89 e6 <48> 8b 78 08 e8 90 ea d3 dd 49 8b 45 28 49 39 c6 4c 8d 68 d8 75 a1
[ 6601.690735] RSP: 0018:ffffa897c2737de0 EFLAGS: 00010246
[ 6601.691846] RAX: 0000000000000000 RBX: 0000000000000000 RCX: dead000000000200
[ 6601.693324] RDX: 0000000000000015 RSI: ffffa897c2737de0 RDI: ffffffff9f2ea9e0
[ 6601.694824] RBP: 0000000000000100 R08: 0000000000000000 R09: 0000000000000000
[ 6601.696314] R10: 0000000000000001 R11: 0000000000000000 R12: ffff8dc323c07e00
[ 6601.697812] R13: ffff8dc324a63100 R14: ffffa897c2737e30 R15: ffffa897c2737e30
[ 6601.699345] FS:  0000000000000000(0000) GS:ffff8dc33fdc0000(0000) knlGS:0000000000000000
[ 6601.701068] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 6601.702282] CR2: 0000000000000008 CR3: 0000000424966002 CR4: 00000000001606e0
[ 6601.703791] Call Trace:
[ 6601.704329]  cleanup_net+0x1b4/0x2c0
[ 6601.705268]  process_one_work+0x16c/0x370
[ 6601.706145]  worker_thread+0x49/0x3e0
[ 6601.706942]  kthread+0xf8/0x130
[ 6601.707626]  ? rescuer_thread+0x340/0x340
[ 6601.708476]  ? kthread_bind+0x10/0x10
[ 6601.709266]  ret_from_fork+0x35/0x40

Reproduce:
modprobe ip6_vti
echo 1 > /proc/sys/net/core/fb_tunnels_only_for_init_net
unshare -n
exit

This because ip6n->tnls_wc[0] point to fallback device in default, but
in non-default namespace, ip6n->tnls_wc[0] will be NULL, so add the NULL
check comparatively.

Fixes: e2948e5af8ee ("ip6_vti: fix creating fallback tunnel device for vti6")
Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_vti.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 71b2fccd1484..c31a7c4a9249 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -1102,7 +1102,8 @@ static void __net_exit vti6_destroy_tunnels(struct vti6_net *ip6n,
 	}
 
 	t = rtnl_dereference(ip6n->tnls_wc[0]);
-	unregister_netdevice_queue(t->dev, list);
+	if (t)
+		unregister_netdevice_queue(t->dev, list);
 }
 
 static int __net_init vti6_init_net(struct net *net)
-- 
2.13.6


From 2e56aad40aebf62812c40e1d77463204514873f2 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 29 Aug 2018 12:46:08 -0700
Subject: [PATCH 32/36] nfp: wait for posted reconfigs when disabling the
 device

[ Upstream commit 9ad716b95fd6c6be46a4f2d5936e514b5bcd744d ]

To avoid leaking a running timer we need to wait for the
posted reconfigs after netdev is unregistered.  In common
case the process of deinitializing the device will perform
synchronous reconfigs which wait for posted requests, but
especially with VXLAN ports being actively added and removed
there can be a race condition leaving a timer running after
adapter structure is freed leading to a crash.

Add an explicit flush after deregistering and for a good
measure a warning to check if timer is running just before
structures are freed.

Fixes: 3d780b926a12 ("nfp: add async reconfiguration mechanism")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/netronome/nfp/nfp_net_common.c    | 48 +++++++++++++++-------
 1 file changed, 33 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index d4c27f849f9b..c2a9e64bc57b 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -227,29 +227,16 @@ static void nfp_net_reconfig_post(struct nfp_net *nn, u32 update)
 	spin_unlock_bh(&nn->reconfig_lock);
 }
 
-/**
- * nfp_net_reconfig() - Reconfigure the firmware
- * @nn:      NFP Net device to reconfigure
- * @update:  The value for the update field in the BAR config
- *
- * Write the update word to the BAR and ping the reconfig queue.  The
- * poll until the firmware has acknowledged the update by zeroing the
- * update word.
- *
- * Return: Negative errno on error, 0 on success
- */
-int nfp_net_reconfig(struct nfp_net *nn, u32 update)
+static void nfp_net_reconfig_sync_enter(struct nfp_net *nn)
 {
 	bool cancelled_timer = false;
 	u32 pre_posted_requests;
-	int ret;
 
 	spin_lock_bh(&nn->reconfig_lock);
 
 	nn->reconfig_sync_present = true;
 
 	if (nn->reconfig_timer_active) {
-		del_timer(&nn->reconfig_timer);
 		nn->reconfig_timer_active = false;
 		cancelled_timer = true;
 	}
@@ -258,14 +245,43 @@ int nfp_net_reconfig(struct nfp_net *nn, u32 update)
 
 	spin_unlock_bh(&nn->reconfig_lock);
 
-	if (cancelled_timer)
+	if (cancelled_timer) {
+		del_timer_sync(&nn->reconfig_timer);
 		nfp_net_reconfig_wait(nn, nn->reconfig_timer.expires);
+	}
 
 	/* Run the posted reconfigs which were issued before we started */
 	if (pre_posted_requests) {
 		nfp_net_reconfig_start(nn, pre_posted_requests);
 		nfp_net_reconfig_wait(nn, jiffies + HZ * NFP_NET_POLL_TIMEOUT);
 	}
+}
+
+static void nfp_net_reconfig_wait_posted(struct nfp_net *nn)
+{
+	nfp_net_reconfig_sync_enter(nn);
+
+	spin_lock_bh(&nn->reconfig_lock);
+	nn->reconfig_sync_present = false;
+	spin_unlock_bh(&nn->reconfig_lock);
+}
+
+/**
+ * nfp_net_reconfig() - Reconfigure the firmware
+ * @nn:      NFP Net device to reconfigure
+ * @update:  The value for the update field in the BAR config
+ *
+ * Write the update word to the BAR and ping the reconfig queue.  The
+ * poll until the firmware has acknowledged the update by zeroing the
+ * update word.
+ *
+ * Return: Negative errno on error, 0 on success
+ */
+int nfp_net_reconfig(struct nfp_net *nn, u32 update)
+{
+	int ret;
+
+	nfp_net_reconfig_sync_enter(nn);
 
 	nfp_net_reconfig_start(nn, update);
 	ret = nfp_net_reconfig_wait(nn, jiffies + HZ * NFP_NET_POLL_TIMEOUT);
@@ -3609,6 +3625,7 @@ struct nfp_net *nfp_net_alloc(struct pci_dev *pdev, bool needs_netdev,
  */
 void nfp_net_free(struct nfp_net *nn)
 {
+	WARN_ON(timer_pending(&nn->reconfig_timer) || nn->reconfig_posted);
 	if (nn->dp.netdev)
 		free_netdev(nn->dp.netdev);
 	else
@@ -3893,4 +3910,5 @@ void nfp_net_clean(struct nfp_net *nn)
 		return;
 
 	unregister_netdev(nn->dp.netdev);
+	nfp_net_reconfig_wait_posted(nn);
 }
-- 
2.13.6


From 26da23eb05124158f63e3900b077cc60ca4dd2a1 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 27 Aug 2018 18:38:31 +0800
Subject: [PATCH 33/36] sctp: hold transport before accessing its asoc in
 sctp_transport_get_next

[ Upstream commit bab1be79a5169ac748d8292b20c86d874022d7ba ]

As Marcelo noticed, in sctp_transport_get_next, it is iterating over
transports but then also accessing the association directly, without
checking any refcnts before that, which can cause an use-after-free
Read.

So fix it by holding transport before accessing the association. With
that, sctp_transport_hold calls can be removed in the later places.

Fixes: 626d16f50f39 ("sctp: export some apis or variables for sctp_diag and reuse some for proc")
Reported-by: syzbot+fe62a0c9aa6a85c6de16@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/proc.c   |  4 ----
 net/sctp/socket.c | 22 +++++++++++++++-------
 2 files changed, 15 insertions(+), 11 deletions(-)

diff --git a/net/sctp/proc.c b/net/sctp/proc.c
index 14ab9358d660..a644292f9faf 100644
--- a/net/sctp/proc.c
+++ b/net/sctp/proc.c
@@ -260,8 +260,6 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v)
 	}
 
 	transport = (struct sctp_transport *)v;
-	if (!sctp_transport_hold(transport))
-		return 0;
 	assoc = transport->asoc;
 	epb = &assoc->base;
 	sk = epb->sk;
@@ -318,8 +316,6 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v)
 	}
 
 	transport = (struct sctp_transport *)v;
-	if (!sctp_transport_hold(transport))
-		return 0;
 	assoc = transport->asoc;
 
 	list_for_each_entry_rcu(tsp, &assoc->peer.transport_addr_list,
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index ce620e878538..50ee07cd20c4 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4881,9 +4881,14 @@ struct sctp_transport *sctp_transport_get_next(struct net *net,
 			break;
 		}
 
+		if (!sctp_transport_hold(t))
+			continue;
+
 		if (net_eq(sock_net(t->asoc->base.sk), net) &&
 		    t->asoc->peer.primary_path == t)
 			break;
+
+		sctp_transport_put(t);
 	}
 
 	return t;
@@ -4893,13 +4898,18 @@ struct sctp_transport *sctp_transport_get_idx(struct net *net,
 					      struct rhashtable_iter *iter,
 					      int pos)
 {
-	void *obj = SEQ_START_TOKEN;
+	struct sctp_transport *t;
 
-	while (pos && (obj = sctp_transport_get_next(net, iter)) &&
-	       !IS_ERR(obj))
-		pos--;
+	if (!pos)
+		return SEQ_START_TOKEN;
 
-	return obj;
+	while ((t = sctp_transport_get_next(net, iter)) && !IS_ERR(t)) {
+		if (!--pos)
+			break;
+		sctp_transport_put(t);
+	}
+
+	return t;
 }
 
 int sctp_for_each_endpoint(int (*cb)(struct sctp_endpoint *, void *),
@@ -4958,8 +4968,6 @@ int sctp_for_each_transport(int (*cb)(struct sctp_transport *, void *),
 
 	tsp = sctp_transport_get_idx(net, &hti, *pos + 1);
 	for (; !IS_ERR_OR_NULL(tsp); tsp = sctp_transport_get_next(net, &hti)) {
-		if (!sctp_transport_hold(tsp))
-			continue;
 		ret = cb(tsp, p);
 		if (ret)
 			break;
-- 
2.13.6


From bb3292ac3899372afcc4a1204b8eb844aa867828 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Fri, 24 Aug 2018 15:41:35 +0300
Subject: [PATCH 34/36] mlxsw: spectrum_switchdev: Do not leak RIFs when
 removing bridge

[ Upstream commit 602b74eda81311dbdb5dbab08c30f789f648ebdc ]

When a bridge device is removed, the VLANs are flushed from each
configured port. This causes the ports to decrement the reference count
on the associated FIDs (filtering identifier). If the reference count of
a FID is 1 and it has a RIF (router interface), then this RIF is
destroyed.

However, if no port is member in the VLAN for which a RIF exists, then
the RIF will continue to exist after the removal of the bridge. To
reproduce:

# ip link add name br0 type bridge vlan_filtering 1
# ip link set dev swp1 master br0
# ip link add link br0 name br0.10 type vlan id 10
# ip address add 192.0.2.0/24 dev br0.10
# ip link del dev br0

The RIF associated with br0.10 continues to exist.

Fix this by iterating over all the bridge device uppers when it is
destroyed and take care of destroying their RIFs.

Fixes: 99f44bb3527b ("mlxsw: spectrum: Enable L3 interfaces on top of bridge devices")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h       |  2 ++
 .../net/ethernet/mellanox/mlxsw/spectrum_router.c    | 11 +++++++++++
 .../net/ethernet/mellanox/mlxsw/spectrum_switchdev.c | 20 ++++++++++++++++++++
 3 files changed, 33 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 4a519d8edec8..3500c79e29cd 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -433,6 +433,8 @@ mlxsw_sp_netdevice_ipip_ul_event(struct mlxsw_sp *mlxsw_sp,
 void
 mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan);
 void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif);
+void mlxsw_sp_rif_destroy_by_dev(struct mlxsw_sp *mlxsw_sp,
+				 struct net_device *dev);
 
 /* spectrum_kvdl.c */
 int mlxsw_sp_kvdl_init(struct mlxsw_sp *mlxsw_sp);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 77b2adb29341..cb43d17097fa 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -6228,6 +6228,17 @@ void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif)
 	mlxsw_sp_vr_put(mlxsw_sp, vr);
 }
 
+void mlxsw_sp_rif_destroy_by_dev(struct mlxsw_sp *mlxsw_sp,
+				 struct net_device *dev)
+{
+	struct mlxsw_sp_rif *rif;
+
+	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
+	if (!rif)
+		return;
+	mlxsw_sp_rif_destroy(rif);
+}
+
 static void
 mlxsw_sp_rif_subport_params_init(struct mlxsw_sp_rif_params *params,
 				 struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index eea5666a86b2..6cb43dda8232 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -160,6 +160,24 @@ bool mlxsw_sp_bridge_device_is_offloaded(const struct mlxsw_sp *mlxsw_sp,
 	return !!mlxsw_sp_bridge_device_find(mlxsw_sp->bridge, br_dev);
 }
 
+static int mlxsw_sp_bridge_device_upper_rif_destroy(struct net_device *dev,
+						    void *data)
+{
+	struct mlxsw_sp *mlxsw_sp = data;
+
+	mlxsw_sp_rif_destroy_by_dev(mlxsw_sp, dev);
+	return 0;
+}
+
+static void mlxsw_sp_bridge_device_rifs_destroy(struct mlxsw_sp *mlxsw_sp,
+						struct net_device *dev)
+{
+	mlxsw_sp_rif_destroy_by_dev(mlxsw_sp, dev);
+	netdev_walk_all_upper_dev_rcu(dev,
+				      mlxsw_sp_bridge_device_upper_rif_destroy,
+				      mlxsw_sp);
+}
+
 static struct mlxsw_sp_bridge_device *
 mlxsw_sp_bridge_device_create(struct mlxsw_sp_bridge *bridge,
 			      struct net_device *br_dev)
@@ -198,6 +216,8 @@ static void
 mlxsw_sp_bridge_device_destroy(struct mlxsw_sp_bridge *bridge,
 			       struct mlxsw_sp_bridge_device *bridge_device)
 {
+	mlxsw_sp_bridge_device_rifs_destroy(bridge->mlxsw_sp,
+					    bridge_device->dev);
 	list_del(&bridge_device->list);
 	if (bridge_device->vlan_enabled)
 		bridge->vlan_enabled_exists = false;
-- 
2.13.6


From 2d221e450593855fad74f338e6abd598bfe2bdb0 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Fri, 24 Aug 2018 16:53:13 +0800
Subject: [PATCH 35/36] vhost: correctly check the iova range when waking
 virtqueue

[ Upstream commit 2d66f997f0545c8f7fc5cf0b49af1decb35170e7 ]

We don't wakeup the virtqueue if the first byte of pending iova range
is the last byte of the range we just got updated. This will lead a
virtqueue to wait for IOTLB updating forever. Fixing by correct the
check and wake up the virtqueue in this case.

Fixes: 6b1e6cc7855b ("vhost: new device IOTLB API")
Reported-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Tested-by: Peter Xu <peterx@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/vhost.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index ed3114556fda..560ed8711706 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -951,7 +951,7 @@ static void vhost_iotlb_notify_vq(struct vhost_dev *d,
 	list_for_each_entry_safe(node, n, &d->pending_list, node) {
 		struct vhost_iotlb_msg *vq_msg = &node->msg.iotlb;
 		if (msg->iova <= vq_msg->iova &&
-		    msg->iova + msg->size - 1 > vq_msg->iova &&
+		    msg->iova + msg->size - 1 >= vq_msg->iova &&
 		    vq_msg->type == VHOST_IOTLB_MISS) {
 			vhost_poll_queue(&node->vq->poll);
 			list_del(&node->node);
-- 
2.13.6


From f882a01c36eaae930564c43a7228bf261ab2b7d7 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Tue, 21 Aug 2018 10:40:38 -0700
Subject: [PATCH 36/36] hv_netvsc: ignore devices that are not PCI

[ Upstream commit b93c1b5ac8643cc08bb74fa8ae21d6c63dfcb23d ]

Registering another device with same MAC address (such as TAP, VPN or
DPDK KNI) will confuse the VF autobinding logic.  Restrict the search
to only run if the device is known to be a PCI attached VF.

Fixes: e8ff40d4bff1 ("hv_netvsc: improve VF device matching")
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/netvsc_drv.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index df6fab625923..6d74cde68163 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -29,6 +29,7 @@
 #include <linux/netdevice.h>
 #include <linux/inetdevice.h>
 #include <linux/etherdevice.h>
+#include <linux/pci.h>
 #include <linux/skbuff.h>
 #include <linux/if_vlan.h>
 #include <linux/in.h>
@@ -1939,12 +1940,16 @@ static int netvsc_register_vf(struct net_device *vf_netdev)
 {
 	struct net_device *ndev;
 	struct net_device_context *net_device_ctx;
+	struct device *pdev = vf_netdev->dev.parent;
 	struct netvsc_device *netvsc_dev;
 	int ret;
 
 	if (vf_netdev->addr_len != ETH_ALEN)
 		return NOTIFY_DONE;
 
+	if (!pdev || !dev_is_pci(pdev) || dev_is_pf(pdev))
+		return NOTIFY_DONE;
+
 	/*
 	 * We will use the MAC address to locate the synthetic interface to
 	 * associate with the VF interface. If we don't find a matching
-- 
2.13.6

Re: [PATCHES] Networking

[Greg KH]

On Mon, Sep 10, 2018 at 11:15:08PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.17
> and v4.18 -stable, respectively.

Thanks for these, I've queued up the 4.18 patches now.

Unfortunatly 4.17 is end-of-life, but I will use that mbox as a basis
for what should be looked at for 4.14.  No need to do anything for 4.17
anymore if you don't want to.

thanks again,

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 111 bytes --]


Please queue up the following networking bug fixes for v4.14.x and
v4.18.x -stable, respectively.

Thank you!

[-- Attachment #2: net_414.mbox --]
[-- Type: Application/Octet-Stream, Size: 29504 bytes --]

From b83a5c914943feaab0e66177bd2fc8844400e431 Mon Sep 17 00:00:00 2001
From: Petr Oros <poros@redhat.com>
Date: Wed, 5 Sep 2018 14:37:45 +0200
Subject: [PATCH 01/11] be2net: Fix memory leak in be_cmd_get_profile_config()

[ Upstream commit 9d7f19dc4673fbafebfcbf30eb90e09fa7d1c037 ]

DMA allocated memory is lost in be_cmd_get_profile_config() when we
call it with non-NULL port_res parameter.

Signed-off-by: Petr Oros <poros@redhat.com>
Reviewed-by: Ivan Vecera <ivecera@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/emulex/benet/be_cmds.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index 02dd5246dfae..1589a568bfe0 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -4500,7 +4500,7 @@ int be_cmd_get_profile_config(struct be_adapter *adapter,
 				port_res->max_vfs += le16_to_cpu(pcie->num_vfs);
 			}
 		}
-		return status;
+		goto err;
 	}
 
 	pcie = be_get_pcie_desc(resp->func_param, desc_count,
-- 
2.17.1


From f7961a265c066ee3dc0c21be1879eaa374a4932b Mon Sep 17 00:00:00 2001
From: Jack Morgenstein <jackm@dev.mellanox.co.il>
Date: Sun, 5 Aug 2018 09:19:33 +0300
Subject: [PATCH 02/11] net/mlx5: Fix use-after-free in self-healing flow

[ Upstream commit 76d5581c870454be5f1f1a106c57985902e7ea20 ]

When the mlx5 health mechanism detects a problem while the driver
is in the middle of init_one or remove_one, the driver needs to prevent
the health mechanism from scheduling future work; if future work
is scheduled, there is a problem with use-after-free: the system WQ
tries to run the work item (which has been freed) at the scheduled
future time.

Prevent this by disabling work item scheduling in the health mechanism
when the driver is in the middle of init_one() or remove_one().

Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Reviewed-by: Feras Daoud <ferasda@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/health.c | 10 +++++++++-
 drivers/net/ethernet/mellanox/mlx5/core/main.c   |  6 +++---
 include/linux/mlx5/driver.h                      |  2 +-
 3 files changed, 13 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index db86e1506c8b..61f284966a8c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -333,9 +333,17 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev)
 	add_timer(&health->timer);
 }
 
-void mlx5_stop_health_poll(struct mlx5_core_dev *dev)
+void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health)
 {
 	struct mlx5_core_health *health = &dev->priv.health;
+	unsigned long flags;
+
+	if (disable_health) {
+		spin_lock_irqsave(&health->wq_lock, flags);
+		set_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags);
+		set_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags);
+		spin_unlock_irqrestore(&health->wq_lock, flags);
+	}
 
 	del_timer_sync(&health->timer);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 4ddd632d10f9..68e48b188458 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1227,7 +1227,7 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 		mlx5_cleanup_once(dev);
 
 err_stop_poll:
-	mlx5_stop_health_poll(dev);
+	mlx5_stop_health_poll(dev, boot);
 	if (mlx5_cmd_teardown_hca(dev)) {
 		dev_err(&dev->pdev->dev, "tear_down_hca failed, skip cleanup\n");
 		goto out_err;
@@ -1286,7 +1286,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 	mlx5_free_irq_vectors(dev);
 	if (cleanup)
 		mlx5_cleanup_once(dev);
-	mlx5_stop_health_poll(dev);
+	mlx5_stop_health_poll(dev, cleanup);
 	err = mlx5_cmd_teardown_hca(dev);
 	if (err) {
 		dev_err(&dev->pdev->dev, "tear_down_hca failed, skip cleanup\n");
@@ -1548,7 +1548,7 @@ static int mlx5_try_fast_unload(struct mlx5_core_dev *dev)
 	 * with the HCA, so the health polll is no longer needed.
 	 */
 	mlx5_drain_health_wq(dev);
-	mlx5_stop_health_poll(dev);
+	mlx5_stop_health_poll(dev, false);
 
 	ret = mlx5_cmd_force_teardown_hca(dev);
 	if (ret) {
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index f2f9e957bf1b..c4d19e77fea8 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -950,7 +950,7 @@ int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn);
 void mlx5_health_cleanup(struct mlx5_core_dev *dev);
 int mlx5_health_init(struct mlx5_core_dev *dev);
 void mlx5_start_health_poll(struct mlx5_core_dev *dev);
-void mlx5_stop_health_poll(struct mlx5_core_dev *dev);
+void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health);
 void mlx5_drain_health_wq(struct mlx5_core_dev *dev);
 void mlx5_trigger_health_work(struct mlx5_core_dev *dev);
 void mlx5_drain_health_recovery(struct mlx5_core_dev *dev);
-- 
2.17.1


From 6c176932f64cf0ec60749e382a7124576f40233f Mon Sep 17 00:00:00 2001
From: Stefan Wahren <stefan.wahren@i2se.com>
Date: Wed, 5 Sep 2018 15:23:18 +0200
Subject: [PATCH 03/11] net: qca_spi: Fix race condition in spi transfers

[ Upstream commit e65a9e480e91ddf9e15155454d370cead64689c8 ]

With performance optimization the spi transfer and messages of basic
register operations like qcaspi_read_register moved into the private
driver structure. But they weren't protected against mutual access
(e.g. between driver kthread and ethtool). So dumping the QCA7000
registers via ethtool during network traffic could make spi_sync
hang forever, because the completion in spi_message is overwritten.

So revert the optimization completely.

Fixes: 291ab06ecf676 ("net: qualcomm: new Ethernet over SPI driver for QCA700")
Signed-off-by: Stefan Wahren <stefan.wahren@i2se.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qualcomm/qca_7k.c  |  76 ++++++++--------
 drivers/net/ethernet/qualcomm/qca_spi.c | 110 ++++++++++++------------
 drivers/net/ethernet/qualcomm/qca_spi.h |   5 --
 3 files changed, 93 insertions(+), 98 deletions(-)

diff --git a/drivers/net/ethernet/qualcomm/qca_7k.c b/drivers/net/ethernet/qualcomm/qca_7k.c
index ffe7a16bdfc8..6c8543fb90c0 100644
--- a/drivers/net/ethernet/qualcomm/qca_7k.c
+++ b/drivers/net/ethernet/qualcomm/qca_7k.c
@@ -45,34 +45,33 @@ qcaspi_read_register(struct qcaspi *qca, u16 reg, u16 *result)
 {
 	__be16 rx_data;
 	__be16 tx_data;
-	struct spi_transfer *transfer;
-	struct spi_message *msg;
+	struct spi_transfer transfer[2];
+	struct spi_message msg;
 	int ret;
 
+	memset(transfer, 0, sizeof(transfer));
+
+	spi_message_init(&msg);
+
 	tx_data = cpu_to_be16(QCA7K_SPI_READ | QCA7K_SPI_INTERNAL | reg);
+	*result = 0;
+
+	transfer[0].tx_buf = &tx_data;
+	transfer[0].len = QCASPI_CMD_LEN;
+	transfer[1].rx_buf = &rx_data;
+	transfer[1].len = QCASPI_CMD_LEN;
+
+	spi_message_add_tail(&transfer[0], &msg);
 
 	if (qca->legacy_mode) {
-		msg = &qca->spi_msg1;
-		transfer = &qca->spi_xfer1;
-		transfer->tx_buf = &tx_data;
-		transfer->rx_buf = NULL;
-		transfer->len = QCASPI_CMD_LEN;
-		spi_sync(qca->spi_dev, msg);
-	} else {
-		msg = &qca->spi_msg2;
-		transfer = &qca->spi_xfer2[0];
-		transfer->tx_buf = &tx_data;
-		transfer->rx_buf = NULL;
-		transfer->len = QCASPI_CMD_LEN;
-		transfer = &qca->spi_xfer2[1];
+		spi_sync(qca->spi_dev, &msg);
+		spi_message_init(&msg);
 	}
-	transfer->tx_buf = NULL;
-	transfer->rx_buf = &rx_data;
-	transfer->len = QCASPI_CMD_LEN;
-	ret = spi_sync(qca->spi_dev, msg);
+	spi_message_add_tail(&transfer[1], &msg);
+	ret = spi_sync(qca->spi_dev, &msg);
 
 	if (!ret)
-		ret = msg->status;
+		ret = msg.status;
 
 	if (ret)
 		qcaspi_spi_error(qca);
@@ -86,35 +85,32 @@ int
 qcaspi_write_register(struct qcaspi *qca, u16 reg, u16 value)
 {
 	__be16 tx_data[2];
-	struct spi_transfer *transfer;
-	struct spi_message *msg;
+	struct spi_transfer transfer[2];
+	struct spi_message msg;
 	int ret;
 
+	memset(&transfer, 0, sizeof(transfer));
+
+	spi_message_init(&msg);
+
 	tx_data[0] = cpu_to_be16(QCA7K_SPI_WRITE | QCA7K_SPI_INTERNAL | reg);
 	tx_data[1] = cpu_to_be16(value);
 
+	transfer[0].tx_buf = &tx_data[0];
+	transfer[0].len = QCASPI_CMD_LEN;
+	transfer[1].tx_buf = &tx_data[1];
+	transfer[1].len = QCASPI_CMD_LEN;
+
+	spi_message_add_tail(&transfer[0], &msg);
 	if (qca->legacy_mode) {
-		msg = &qca->spi_msg1;
-		transfer = &qca->spi_xfer1;
-		transfer->tx_buf = &tx_data[0];
-		transfer->rx_buf = NULL;
-		transfer->len = QCASPI_CMD_LEN;
-		spi_sync(qca->spi_dev, msg);
-	} else {
-		msg = &qca->spi_msg2;
-		transfer = &qca->spi_xfer2[0];
-		transfer->tx_buf = &tx_data[0];
-		transfer->rx_buf = NULL;
-		transfer->len = QCASPI_CMD_LEN;
-		transfer = &qca->spi_xfer2[1];
+		spi_sync(qca->spi_dev, &msg);
+		spi_message_init(&msg);
 	}
-	transfer->tx_buf = &tx_data[1];
-	transfer->rx_buf = NULL;
-	transfer->len = QCASPI_CMD_LEN;
-	ret = spi_sync(qca->spi_dev, msg);
+	spi_message_add_tail(&transfer[1], &msg);
+	ret = spi_sync(qca->spi_dev, &msg);
 
 	if (!ret)
-		ret = msg->status;
+		ret = msg.status;
 
 	if (ret)
 		qcaspi_spi_error(qca);
diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c
index b1f5f0b8e546..275fc6f154a7 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.c
+++ b/drivers/net/ethernet/qualcomm/qca_spi.c
@@ -99,22 +99,24 @@ static u32
 qcaspi_write_burst(struct qcaspi *qca, u8 *src, u32 len)
 {
 	__be16 cmd;
-	struct spi_message *msg = &qca->spi_msg2;
-	struct spi_transfer *transfer = &qca->spi_xfer2[0];
+	struct spi_message msg;
+	struct spi_transfer transfer[2];
 	int ret;
 
+	memset(&transfer, 0, sizeof(transfer));
+	spi_message_init(&msg);
+
 	cmd = cpu_to_be16(QCA7K_SPI_WRITE | QCA7K_SPI_EXTERNAL);
-	transfer->tx_buf = &cmd;
-	transfer->rx_buf = NULL;
-	transfer->len = QCASPI_CMD_LEN;
-	transfer = &qca->spi_xfer2[1];
-	transfer->tx_buf = src;
-	transfer->rx_buf = NULL;
-	transfer->len = len;
+	transfer[0].tx_buf = &cmd;
+	transfer[0].len = QCASPI_CMD_LEN;
+	transfer[1].tx_buf = src;
+	transfer[1].len = len;
 
-	ret = spi_sync(qca->spi_dev, msg);
+	spi_message_add_tail(&transfer[0], &msg);
+	spi_message_add_tail(&transfer[1], &msg);
+	ret = spi_sync(qca->spi_dev, &msg);
 
-	if (ret || (msg->actual_length != QCASPI_CMD_LEN + len)) {
+	if (ret || (msg.actual_length != QCASPI_CMD_LEN + len)) {
 		qcaspi_spi_error(qca);
 		return 0;
 	}
@@ -125,17 +127,20 @@ qcaspi_write_burst(struct qcaspi *qca, u8 *src, u32 len)
 static u32
 qcaspi_write_legacy(struct qcaspi *qca, u8 *src, u32 len)
 {
-	struct spi_message *msg = &qca->spi_msg1;
-	struct spi_transfer *transfer = &qca->spi_xfer1;
+	struct spi_message msg;
+	struct spi_transfer transfer;
 	int ret;
 
-	transfer->tx_buf = src;
-	transfer->rx_buf = NULL;
-	transfer->len = len;
+	memset(&transfer, 0, sizeof(transfer));
+	spi_message_init(&msg);
+
+	transfer.tx_buf = src;
+	transfer.len = len;
 
-	ret = spi_sync(qca->spi_dev, msg);
+	spi_message_add_tail(&transfer, &msg);
+	ret = spi_sync(qca->spi_dev, &msg);
 
-	if (ret || (msg->actual_length != len)) {
+	if (ret || (msg.actual_length != len)) {
 		qcaspi_spi_error(qca);
 		return 0;
 	}
@@ -146,23 +151,25 @@ qcaspi_write_legacy(struct qcaspi *qca, u8 *src, u32 len)
 static u32
 qcaspi_read_burst(struct qcaspi *qca, u8 *dst, u32 len)
 {
-	struct spi_message *msg = &qca->spi_msg2;
+	struct spi_message msg;
 	__be16 cmd;
-	struct spi_transfer *transfer = &qca->spi_xfer2[0];
+	struct spi_transfer transfer[2];
 	int ret;
 
+	memset(&transfer, 0, sizeof(transfer));
+	spi_message_init(&msg);
+
 	cmd = cpu_to_be16(QCA7K_SPI_READ | QCA7K_SPI_EXTERNAL);
-	transfer->tx_buf = &cmd;
-	transfer->rx_buf = NULL;
-	transfer->len = QCASPI_CMD_LEN;
-	transfer = &qca->spi_xfer2[1];
-	transfer->tx_buf = NULL;
-	transfer->rx_buf = dst;
-	transfer->len = len;
+	transfer[0].tx_buf = &cmd;
+	transfer[0].len = QCASPI_CMD_LEN;
+	transfer[1].rx_buf = dst;
+	transfer[1].len = len;
 
-	ret = spi_sync(qca->spi_dev, msg);
+	spi_message_add_tail(&transfer[0], &msg);
+	spi_message_add_tail(&transfer[1], &msg);
+	ret = spi_sync(qca->spi_dev, &msg);
 
-	if (ret || (msg->actual_length != QCASPI_CMD_LEN + len)) {
+	if (ret || (msg.actual_length != QCASPI_CMD_LEN + len)) {
 		qcaspi_spi_error(qca);
 		return 0;
 	}
@@ -173,17 +180,20 @@ qcaspi_read_burst(struct qcaspi *qca, u8 *dst, u32 len)
 static u32
 qcaspi_read_legacy(struct qcaspi *qca, u8 *dst, u32 len)
 {
-	struct spi_message *msg = &qca->spi_msg1;
-	struct spi_transfer *transfer = &qca->spi_xfer1;
+	struct spi_message msg;
+	struct spi_transfer transfer;
 	int ret;
 
-	transfer->tx_buf = NULL;
-	transfer->rx_buf = dst;
-	transfer->len = len;
+	memset(&transfer, 0, sizeof(transfer));
+	spi_message_init(&msg);
 
-	ret = spi_sync(qca->spi_dev, msg);
+	transfer.rx_buf = dst;
+	transfer.len = len;
 
-	if (ret || (msg->actual_length != len)) {
+	spi_message_add_tail(&transfer, &msg);
+	ret = spi_sync(qca->spi_dev, &msg);
+
+	if (ret || (msg.actual_length != len)) {
 		qcaspi_spi_error(qca);
 		return 0;
 	}
@@ -195,19 +205,23 @@ static int
 qcaspi_tx_cmd(struct qcaspi *qca, u16 cmd)
 {
 	__be16 tx_data;
-	struct spi_message *msg = &qca->spi_msg1;
-	struct spi_transfer *transfer = &qca->spi_xfer1;
+	struct spi_message msg;
+	struct spi_transfer transfer;
 	int ret;
 
+	memset(&transfer, 0, sizeof(transfer));
+
+	spi_message_init(&msg);
+
 	tx_data = cpu_to_be16(cmd);
-	transfer->len = sizeof(tx_data);
-	transfer->tx_buf = &tx_data;
-	transfer->rx_buf = NULL;
+	transfer.len = sizeof(cmd);
+	transfer.tx_buf = &tx_data;
+	spi_message_add_tail(&transfer, &msg);
 
-	ret = spi_sync(qca->spi_dev, msg);
+	ret = spi_sync(qca->spi_dev, &msg);
 
 	if (!ret)
-		ret = msg->status;
+		ret = msg.status;
 
 	if (ret)
 		qcaspi_spi_error(qca);
@@ -836,16 +850,6 @@ qcaspi_netdev_setup(struct net_device *dev)
 	qca = netdev_priv(dev);
 	memset(qca, 0, sizeof(struct qcaspi));
 
-	memset(&qca->spi_xfer1, 0, sizeof(struct spi_transfer));
-	memset(&qca->spi_xfer2, 0, sizeof(struct spi_transfer) * 2);
-
-	spi_message_init(&qca->spi_msg1);
-	spi_message_add_tail(&qca->spi_xfer1, &qca->spi_msg1);
-
-	spi_message_init(&qca->spi_msg2);
-	spi_message_add_tail(&qca->spi_xfer2[0], &qca->spi_msg2);
-	spi_message_add_tail(&qca->spi_xfer2[1], &qca->spi_msg2);
-
 	memset(&qca->txr, 0, sizeof(qca->txr));
 	qca->txr.count = TX_RING_MAX_LEN;
 }
diff --git a/drivers/net/ethernet/qualcomm/qca_spi.h b/drivers/net/ethernet/qualcomm/qca_spi.h
index fc4beb1b32d1..fc0e98726b36 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.h
+++ b/drivers/net/ethernet/qualcomm/qca_spi.h
@@ -83,11 +83,6 @@ struct qcaspi {
 	struct tx_ring txr;
 	struct qcaspi_stats stats;
 
-	struct spi_message spi_msg1;
-	struct spi_message spi_msg2;
-	struct spi_transfer spi_xfer1;
-	struct spi_transfer spi_xfer2[2];
-
 	u8 *rx_buffer;
 	u32 buffer_size;
 	u8 sync;
-- 
2.17.1


From e854e171ed7c65c0cc76ea2710a840a838f449a8 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 10 Sep 2018 18:27:26 -0700
Subject: [PATCH 04/11] rds: fix two RCU related problems

[ Upstream commit cc4dfb7f70a344f24c1c71e298deea0771dadcb2 ]

When a rds sock is bound, it is inserted into the bind_hash_table
which is protected by RCU. But when releasing rds sock, after it
is removed from this hash table, it is freed immediately without
respecting RCU grace period. This could cause some use-after-free
as reported by syzbot.

Mark the rds sock with SOCK_RCU_FREE before inserting it into the
bind_hash_table, so that it would be always freed after a RCU grace
period.

The other problem is in rds_find_bound(), the rds sock could be
freed in between rhashtable_lookup_fast() and rds_sock_addref(),
so we need to extend RCU read lock protection in rds_find_bound()
to close this race condition.

Reported-and-tested-by: syzbot+8967084bcac563795dc6@syzkaller.appspotmail.com
Reported-by: syzbot+93a5839deb355537440f@syzkaller.appspotmail.com
Cc: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Cc: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Cc: rds-devel@oss.oracle.com
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oarcle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/bind.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/rds/bind.c b/net/rds/bind.c
index 5aa3a64aa4f0..48257d3a4201 100644
--- a/net/rds/bind.c
+++ b/net/rds/bind.c
@@ -60,11 +60,13 @@ struct rds_sock *rds_find_bound(__be32 addr, __be16 port)
 	u64 key = ((u64)addr << 32) | port;
 	struct rds_sock *rs;
 
-	rs = rhashtable_lookup_fast(&bind_hash_table, &key, ht_parms);
+	rcu_read_lock();
+	rs = rhashtable_lookup(&bind_hash_table, &key, ht_parms);
 	if (rs && !sock_flag(rds_rs_to_sk(rs), SOCK_DEAD))
 		rds_sock_addref(rs);
 	else
 		rs = NULL;
+	rcu_read_unlock();
 
 	rdsdebug("returning rs %p for %pI4:%u\n", rs, &addr,
 		ntohs(port));
@@ -157,6 +159,7 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		goto out;
 	}
 
+	sock_set_flag(sk, SOCK_RCU_FREE);
 	ret = rds_add_bound(rs, sin->sin_addr.s_addr, &sin->sin_port);
 	if (ret)
 		goto out;
-- 
2.17.1


From 7fa2b13064677670bfe8864ea0cef0e45986a25a Mon Sep 17 00:00:00 2001
From: Huy Nguyen <huyn@mellanox.com>
Date: Wed, 15 Aug 2018 11:08:48 -0500
Subject: [PATCH 05/11] net/mlx5: Check for error in mlx5_attach_interface

[ Upstream commit 47bc94b82291e007da61ee1b3d18c77871f3e158 ]

Currently, mlx5_attach_interface does not check for error
after calling intf->attach or intf->add. When these two calls
fails, the client is not initialized and will cause issues such as
kernel panic on invalid address in the teardown path (mlx5_detach_interface)

Fixes: 737a234bb638 ("net/mlx5: Introduce attach/detach to interface API")
Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/dev.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
index 17b723218b0c..9f9c9ff10735 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -132,11 +132,11 @@ void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv)
 	delayed_event_start(priv);
 
 	dev_ctx->context = intf->add(dev);
-	set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state);
-	if (intf->attach)
-		set_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state);
-
 	if (dev_ctx->context) {
+		set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state);
+		if (intf->attach)
+			set_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state);
+
 		spin_lock_irq(&priv->ctx_lock);
 		list_add_tail(&dev_ctx->list, &priv->ctx_list);
 
@@ -211,12 +211,17 @@ static void mlx5_attach_interface(struct mlx5_interface *intf, struct mlx5_priv
 	if (intf->attach) {
 		if (test_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state))
 			goto out;
-		intf->attach(dev, dev_ctx->context);
+		if (intf->attach(dev, dev_ctx->context))
+			goto out;
+
 		set_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state);
 	} else {
 		if (test_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state))
 			goto out;
 		dev_ctx->context = intf->add(dev);
+		if (!dev_ctx->context)
+			goto out;
+
 		set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state);
 	}
 
-- 
2.17.1


From 217d2fc32b4850df3194f99b3e044c030bce4bec Mon Sep 17 00:00:00 2001
From: Jack Morgenstein <jackm@dev.mellanox.co.il>
Date: Tue, 7 Aug 2018 09:59:03 +0300
Subject: [PATCH 06/11] net/mlx5: Fix debugfs cleanup in the device init/remove
 flow

[ Upstream commit 5df816e7f43f1297c40021ef17ec6e722b45c82f ]

When initializing the device (procedure init_one), the driver
calls mlx5_pci_init to perform pci initialization. As part of this
initialization, mlx5_pci_init creates a debugfs directory.
If this creation fails, init_one aborts, returning failure to
the caller (which is the probe method caller).

The main reason for such a failure to occur is if the debugfs
directory already exists. This can happen if the last time
mlx5_pci_close was called, debugfs_remove (silently) failed due
to the debugfs directory not being empty.

Guarantee that such a debugfs_remove failure will not occur by
instead calling debugfs_remove_recursive in procedure mlx5_pci_close.

Fixes: 59211bd3b632 ("net/mlx5: Split the load/unload flow into hardware and software flows")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 68e48b188458..e99f1382a4f0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -857,8 +857,10 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
 	priv->numa_node = dev_to_node(&dev->pdev->dev);
 
 	priv->dbg_root = debugfs_create_dir(dev_name(&pdev->dev), mlx5_debugfs_root);
-	if (!priv->dbg_root)
+	if (!priv->dbg_root) {
+		dev_err(&pdev->dev, "Cannot create debugfs dir, aborting\n");
 		return -ENOMEM;
+	}
 
 	err = mlx5_pci_enable_device(dev);
 	if (err) {
@@ -907,7 +909,7 @@ static void mlx5_pci_close(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
 	pci_clear_master(dev->pdev);
 	release_bar(dev->pdev);
 	mlx5_pci_disable_device(dev);
-	debugfs_remove(priv->dbg_root);
+	debugfs_remove_recursive(priv->dbg_root);
 }
 
 static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
-- 
2.17.1


From d5f2a1bd1c9af52585a4c232073edce64ad1ec1b Mon Sep 17 00:00:00 2001
From: Raed Salem <raeds@mellanox.com>
Date: Tue, 21 Aug 2018 15:22:42 +0300
Subject: [PATCH 07/11] net/mlx5: E-Switch, Fix memory leak when creating
 switchdev mode FDB tables

[ Upstream commit c88a026e01219488e745f4f0267fd76c2bb68421 ]

The memory allocated for the slow path table flow group input structure
was not freed upon successful return, fix that.

Fixes: 1967ce6ea5c8 ("net/mlx5: E-Switch, Refactor fast path FDB table creation in switchdev mode")
Signed-off-by: Raed Salem <raeds@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index c699055c0ffd..4b52b722135d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -557,6 +557,7 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
 	if (err)
 		goto miss_rule_err;
 
+	kvfree(flow_group_in);
 	return 0;
 
 miss_rule_err:
-- 
2.17.1


From aea26bd3dfb53a04c55470d255183f6c330f4d5c Mon Sep 17 00:00:00 2001
From: Vakul Garg <vakul.garg@nxp.com>
Date: Thu, 6 Sep 2018 21:41:40 +0530
Subject: [PATCH 08/11] net/tls: Set count of SG entries if sk_alloc_sg returns
 -ENOSPC

[ Upstream commit 52ea992cfac357b73180d5c051dca43bc8d20c2a ]

tls_sw_sendmsg() allocates plaintext and encrypted SG entries using
function sk_alloc_sg(). In case the number of SG entries hit
MAX_SKB_FRAGS, sk_alloc_sg() returns -ENOSPC and sets the variable for
current SG index to '0'. This leads to calling of function
tls_push_record() with 'sg_encrypted_num_elem = 0' and later causes
kernel crash. To fix this, set the number of SG elements to the number
of elements in plaintext/encrypted SG arrays in case sk_alloc_sg()
returns -ENOSPC.

Fixes: 3c4d7559159b ("tls: kernel TLS support")
Signed-off-by: Vakul Garg <vakul.garg@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index fb79caf56d0e..b81aa6d7dc45 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -170,6 +170,9 @@ static int alloc_encrypted_sg(struct sock *sk, int len)
 	rc = alloc_sg(sk, len, ctx->sg_encrypted_data,
 		      &ctx->sg_encrypted_num_elem, &ctx->sg_encrypted_size, 0);
 
+	if (rc == -ENOSPC)
+		ctx->sg_encrypted_num_elem = ARRAY_SIZE(ctx->sg_encrypted_data);
+
 	return rc;
 }
 
@@ -183,6 +186,9 @@ static int alloc_plaintext_sg(struct sock *sk, int len)
 		      &ctx->sg_plaintext_num_elem, &ctx->sg_plaintext_size,
 		      tls_ctx->pending_open_record_frags);
 
+	if (rc == -ENOSPC)
+		ctx->sg_plaintext_num_elem = ARRAY_SIZE(ctx->sg_plaintext_data);
+
 	return rc;
 }
 
-- 
2.17.1


From 7878a32000c9a82b048b22afe9c95f8f334b364e Mon Sep 17 00:00:00 2001
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Mon, 10 Sep 2018 22:19:48 +0800
Subject: [PATCH 09/11] erspan: fix error handling for erspan tunnel

[ Upstream commit 51dc63e3911fbb1f0a7a32da2fe56253e2040ea4 ]

When processing icmp unreachable message for erspan tunnel, tunnel id
should be erspan_net_id instead of ipgre_net_id.

Fixes: 84e54fe0a5ea ("gre: introduce native tunnel support for ERSPAN")
Cc: William Tu <u9012063@gmail.com>
Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Acked-by: William Tu <u9012063@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_gre.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 2459e9cc22a6..fcb807d4f766 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -177,6 +177,9 @@ static void ipgre_err(struct sk_buff *skb, u32 info,
 
 	if (tpi->proto == htons(ETH_P_TEB))
 		itn = net_generic(net, gre_tap_net_id);
+	else if (tpi->proto == htons(ETH_P_ERSPAN) ||
+		 tpi->proto == htons(ETH_P_ERSPAN2))
+		itn = net_generic(net, erspan_net_id);
 	else
 		itn = net_generic(net, ipgre_net_id);
 
-- 
2.17.1


From 8452a58164604733aa6492dd1a52ea806094ef6f Mon Sep 17 00:00:00 2001
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Mon, 10 Sep 2018 22:19:47 +0800
Subject: [PATCH 10/11] erspan: return PACKET_REJECT when the appropriate
 tunnel is not found

[ Upstream commit 5a64506b5c2c3cdb29d817723205330378075448 ]

If erspan tunnel hasn't been established, we'd better send icmp port
unreachable message after receive erspan packets.

Fixes: 84e54fe0a5ea ("gre: introduce native tunnel support for ERSPAN")
Cc: William Tu <u9012063@gmail.com>
Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Acked-by: William Tu <u9012063@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_gre.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index fcb807d4f766..83be56f2ac71 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -323,6 +323,8 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 		ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error);
 		return PACKET_RCVD;
 	}
+	return PACKET_REJECT;
+
 drop:
 	kfree_skb(skb);
 	return PACKET_RCVD;
-- 
2.17.1


From 7fab3d545ab1cebe72309968620559bf54113740 Mon Sep 17 00:00:00 2001
From: Vincent Whitchurch <vincent.whitchurch@axis.com>
Date: Thu, 6 Sep 2018 15:54:59 +0200
Subject: [PATCH 11/11] tcp: really ignore MSG_ZEROCOPY if no SO_ZEROCOPY

[ Upstream commit 5cf4a8532c992bb22a9ecd5f6d93f873f4eaccc2 ]

According to the documentation in msg_zerocopy.rst, the SO_ZEROCOPY
flag was introduced because send(2) ignores unknown message flags and
any legacy application which was accidentally passing the equivalent of
MSG_ZEROCOPY earlier should not see any new behaviour.

Before commit f214f915e7db ("tcp: enable MSG_ZEROCOPY"), a send(2) call
which passed the equivalent of MSG_ZEROCOPY without setting SO_ZEROCOPY
would succeed.  However, after that commit, it fails with -ENOBUFS.  So
it appears that the SO_ZEROCOPY flag fails to fulfill its intended
purpose.  Fix it.

Fixes: f214f915e7db ("tcp: enable MSG_ZEROCOPY")
Signed-off-by: Vincent Whitchurch <vincent.whitchurch@axis.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 3 ---
 net/ipv4/tcp.c    | 2 +-
 2 files changed, 1 insertion(+), 4 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 2e5eeba97de9..80dd2aa6b3ad 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -937,9 +937,6 @@ struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size)
 
 	WARN_ON_ONCE(!in_task());
 
-	if (!sock_flag(sk, SOCK_ZEROCOPY))
-		return NULL;
-
 	skb = sock_omalloc(sk, 0, GFP_KERNEL);
 	if (!skb)
 		return NULL;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 7462ec7587ce..f9c985460faa 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1177,7 +1177,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 
 	flags = msg->msg_flags;
 
-	if (flags & MSG_ZEROCOPY && size) {
+	if (flags & MSG_ZEROCOPY && size && sock_flag(sk, SOCK_ZEROCOPY)) {
 		if (sk->sk_state != TCP_ESTABLISHED) {
 			err = -EINVAL;
 			goto out_err;
-- 
2.17.1


[-- Attachment #3: net_418.mbox --]
[-- Type: Application/Octet-Stream, Size: 39626 bytes --]

From d2e50b16b5607d93411819c037caea622e4d01cb Mon Sep 17 00:00:00 2001
From: Petr Oros <poros@redhat.com>
Date: Wed, 5 Sep 2018 14:37:45 +0200
Subject: [PATCH 01/15] be2net: Fix memory leak in be_cmd_get_profile_config()

[ Upstream commit 9d7f19dc4673fbafebfcbf30eb90e09fa7d1c037 ]

DMA allocated memory is lost in be_cmd_get_profile_config() when we
call it with non-NULL port_res parameter.

Signed-off-by: Petr Oros <poros@redhat.com>
Reviewed-by: Ivan Vecera <ivecera@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/emulex/benet/be_cmds.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index ff92ab1daeb8..1e9d882c04ef 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -4500,7 +4500,7 @@ int be_cmd_get_profile_config(struct be_adapter *adapter,
 				port_res->max_vfs += le16_to_cpu(pcie->num_vfs);
 			}
 		}
-		return status;
+		goto err;
 	}
 
 	pcie = be_get_pcie_desc(resp->func_param, desc_count,
-- 
2.17.1


From 57420e314f935377b3e9a40872edf912aea9dc24 Mon Sep 17 00:00:00 2001
From: Jack Morgenstein <jackm@dev.mellanox.co.il>
Date: Sun, 5 Aug 2018 09:19:33 +0300
Subject: [PATCH 02/15] net/mlx5: Fix use-after-free in self-healing flow

[ Upstream commit 76d5581c870454be5f1f1a106c57985902e7ea20 ]

When the mlx5 health mechanism detects a problem while the driver
is in the middle of init_one or remove_one, the driver needs to prevent
the health mechanism from scheduling future work; if future work
is scheduled, there is a problem with use-after-free: the system WQ
tries to run the work item (which has been freed) at the scheduled
future time.

Prevent this by disabling work item scheduling in the health mechanism
when the driver is in the middle of init_one() or remove_one().

Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Reviewed-by: Feras Daoud <ferasda@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/health.c | 10 +++++++++-
 drivers/net/ethernet/mellanox/mlx5/core/main.c   |  6 +++---
 include/linux/mlx5/driver.h                      |  2 +-
 3 files changed, 13 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index d39b0b7011b2..9f39aeca863f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -331,9 +331,17 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev)
 	add_timer(&health->timer);
 }
 
-void mlx5_stop_health_poll(struct mlx5_core_dev *dev)
+void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health)
 {
 	struct mlx5_core_health *health = &dev->priv.health;
+	unsigned long flags;
+
+	if (disable_health) {
+		spin_lock_irqsave(&health->wq_lock, flags);
+		set_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags);
+		set_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags);
+		spin_unlock_irqrestore(&health->wq_lock, flags);
+	}
 
 	del_timer_sync(&health->timer);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 615005e63819..260efa07ee9d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1266,7 +1266,7 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 		mlx5_cleanup_once(dev);
 
 err_stop_poll:
-	mlx5_stop_health_poll(dev);
+	mlx5_stop_health_poll(dev, boot);
 	if (mlx5_cmd_teardown_hca(dev)) {
 		dev_err(&dev->pdev->dev, "tear_down_hca failed, skip cleanup\n");
 		goto out_err;
@@ -1325,7 +1325,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 	mlx5_free_irq_vectors(dev);
 	if (cleanup)
 		mlx5_cleanup_once(dev);
-	mlx5_stop_health_poll(dev);
+	mlx5_stop_health_poll(dev, cleanup);
 	err = mlx5_cmd_teardown_hca(dev);
 	if (err) {
 		dev_err(&dev->pdev->dev, "tear_down_hca failed, skip cleanup\n");
@@ -1587,7 +1587,7 @@ static int mlx5_try_fast_unload(struct mlx5_core_dev *dev)
 	 * with the HCA, so the health polll is no longer needed.
 	 */
 	mlx5_drain_health_wq(dev);
-	mlx5_stop_health_poll(dev);
+	mlx5_stop_health_poll(dev, false);
 
 	ret = mlx5_cmd_force_teardown_hca(dev);
 	if (ret) {
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 83957920653a..01a1a8baeb9d 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1042,7 +1042,7 @@ int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn);
 void mlx5_health_cleanup(struct mlx5_core_dev *dev);
 int mlx5_health_init(struct mlx5_core_dev *dev);
 void mlx5_start_health_poll(struct mlx5_core_dev *dev);
-void mlx5_stop_health_poll(struct mlx5_core_dev *dev);
+void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health);
 void mlx5_drain_health_wq(struct mlx5_core_dev *dev);
 void mlx5_trigger_health_work(struct mlx5_core_dev *dev);
 void mlx5_drain_health_recovery(struct mlx5_core_dev *dev);
-- 
2.17.1


From 7f57f359f4b154656a8a1e6912f9901bd1d7d4d8 Mon Sep 17 00:00:00 2001
From: Stefan Wahren <stefan.wahren@i2se.com>
Date: Wed, 5 Sep 2018 15:23:18 +0200
Subject: [PATCH 03/15] net: qca_spi: Fix race condition in spi transfers

[ Upstream commit e65a9e480e91ddf9e15155454d370cead64689c8 ]

With performance optimization the spi transfer and messages of basic
register operations like qcaspi_read_register moved into the private
driver structure. But they weren't protected against mutual access
(e.g. between driver kthread and ethtool). So dumping the QCA7000
registers via ethtool during network traffic could make spi_sync
hang forever, because the completion in spi_message is overwritten.

So revert the optimization completely.

Fixes: 291ab06ecf676 ("net: qualcomm: new Ethernet over SPI driver for QCA700")
Signed-off-by: Stefan Wahren <stefan.wahren@i2se.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qualcomm/qca_7k.c  |  76 ++++++++--------
 drivers/net/ethernet/qualcomm/qca_spi.c | 110 ++++++++++++------------
 drivers/net/ethernet/qualcomm/qca_spi.h |   5 --
 3 files changed, 93 insertions(+), 98 deletions(-)

diff --git a/drivers/net/ethernet/qualcomm/qca_7k.c b/drivers/net/ethernet/qualcomm/qca_7k.c
index ffe7a16bdfc8..6c8543fb90c0 100644
--- a/drivers/net/ethernet/qualcomm/qca_7k.c
+++ b/drivers/net/ethernet/qualcomm/qca_7k.c
@@ -45,34 +45,33 @@ qcaspi_read_register(struct qcaspi *qca, u16 reg, u16 *result)
 {
 	__be16 rx_data;
 	__be16 tx_data;
-	struct spi_transfer *transfer;
-	struct spi_message *msg;
+	struct spi_transfer transfer[2];
+	struct spi_message msg;
 	int ret;
 
+	memset(transfer, 0, sizeof(transfer));
+
+	spi_message_init(&msg);
+
 	tx_data = cpu_to_be16(QCA7K_SPI_READ | QCA7K_SPI_INTERNAL | reg);
+	*result = 0;
+
+	transfer[0].tx_buf = &tx_data;
+	transfer[0].len = QCASPI_CMD_LEN;
+	transfer[1].rx_buf = &rx_data;
+	transfer[1].len = QCASPI_CMD_LEN;
+
+	spi_message_add_tail(&transfer[0], &msg);
 
 	if (qca->legacy_mode) {
-		msg = &qca->spi_msg1;
-		transfer = &qca->spi_xfer1;
-		transfer->tx_buf = &tx_data;
-		transfer->rx_buf = NULL;
-		transfer->len = QCASPI_CMD_LEN;
-		spi_sync(qca->spi_dev, msg);
-	} else {
-		msg = &qca->spi_msg2;
-		transfer = &qca->spi_xfer2[0];
-		transfer->tx_buf = &tx_data;
-		transfer->rx_buf = NULL;
-		transfer->len = QCASPI_CMD_LEN;
-		transfer = &qca->spi_xfer2[1];
+		spi_sync(qca->spi_dev, &msg);
+		spi_message_init(&msg);
 	}
-	transfer->tx_buf = NULL;
-	transfer->rx_buf = &rx_data;
-	transfer->len = QCASPI_CMD_LEN;
-	ret = spi_sync(qca->spi_dev, msg);
+	spi_message_add_tail(&transfer[1], &msg);
+	ret = spi_sync(qca->spi_dev, &msg);
 
 	if (!ret)
-		ret = msg->status;
+		ret = msg.status;
 
 	if (ret)
 		qcaspi_spi_error(qca);
@@ -86,35 +85,32 @@ int
 qcaspi_write_register(struct qcaspi *qca, u16 reg, u16 value)
 {
 	__be16 tx_data[2];
-	struct spi_transfer *transfer;
-	struct spi_message *msg;
+	struct spi_transfer transfer[2];
+	struct spi_message msg;
 	int ret;
 
+	memset(&transfer, 0, sizeof(transfer));
+
+	spi_message_init(&msg);
+
 	tx_data[0] = cpu_to_be16(QCA7K_SPI_WRITE | QCA7K_SPI_INTERNAL | reg);
 	tx_data[1] = cpu_to_be16(value);
 
+	transfer[0].tx_buf = &tx_data[0];
+	transfer[0].len = QCASPI_CMD_LEN;
+	transfer[1].tx_buf = &tx_data[1];
+	transfer[1].len = QCASPI_CMD_LEN;
+
+	spi_message_add_tail(&transfer[0], &msg);
 	if (qca->legacy_mode) {
-		msg = &qca->spi_msg1;
-		transfer = &qca->spi_xfer1;
-		transfer->tx_buf = &tx_data[0];
-		transfer->rx_buf = NULL;
-		transfer->len = QCASPI_CMD_LEN;
-		spi_sync(qca->spi_dev, msg);
-	} else {
-		msg = &qca->spi_msg2;
-		transfer = &qca->spi_xfer2[0];
-		transfer->tx_buf = &tx_data[0];
-		transfer->rx_buf = NULL;
-		transfer->len = QCASPI_CMD_LEN;
-		transfer = &qca->spi_xfer2[1];
+		spi_sync(qca->spi_dev, &msg);
+		spi_message_init(&msg);
 	}
-	transfer->tx_buf = &tx_data[1];
-	transfer->rx_buf = NULL;
-	transfer->len = QCASPI_CMD_LEN;
-	ret = spi_sync(qca->spi_dev, msg);
+	spi_message_add_tail(&transfer[1], &msg);
+	ret = spi_sync(qca->spi_dev, &msg);
 
 	if (!ret)
-		ret = msg->status;
+		ret = msg.status;
 
 	if (ret)
 		qcaspi_spi_error(qca);
diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c
index 206f0266463e..66b775d462fd 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.c
+++ b/drivers/net/ethernet/qualcomm/qca_spi.c
@@ -99,22 +99,24 @@ static u32
 qcaspi_write_burst(struct qcaspi *qca, u8 *src, u32 len)
 {
 	__be16 cmd;
-	struct spi_message *msg = &qca->spi_msg2;
-	struct spi_transfer *transfer = &qca->spi_xfer2[0];
+	struct spi_message msg;
+	struct spi_transfer transfer[2];
 	int ret;
 
+	memset(&transfer, 0, sizeof(transfer));
+	spi_message_init(&msg);
+
 	cmd = cpu_to_be16(QCA7K_SPI_WRITE | QCA7K_SPI_EXTERNAL);
-	transfer->tx_buf = &cmd;
-	transfer->rx_buf = NULL;
-	transfer->len = QCASPI_CMD_LEN;
-	transfer = &qca->spi_xfer2[1];
-	transfer->tx_buf = src;
-	transfer->rx_buf = NULL;
-	transfer->len = len;
+	transfer[0].tx_buf = &cmd;
+	transfer[0].len = QCASPI_CMD_LEN;
+	transfer[1].tx_buf = src;
+	transfer[1].len = len;
 
-	ret = spi_sync(qca->spi_dev, msg);
+	spi_message_add_tail(&transfer[0], &msg);
+	spi_message_add_tail(&transfer[1], &msg);
+	ret = spi_sync(qca->spi_dev, &msg);
 
-	if (ret || (msg->actual_length != QCASPI_CMD_LEN + len)) {
+	if (ret || (msg.actual_length != QCASPI_CMD_LEN + len)) {
 		qcaspi_spi_error(qca);
 		return 0;
 	}
@@ -125,17 +127,20 @@ qcaspi_write_burst(struct qcaspi *qca, u8 *src, u32 len)
 static u32
 qcaspi_write_legacy(struct qcaspi *qca, u8 *src, u32 len)
 {
-	struct spi_message *msg = &qca->spi_msg1;
-	struct spi_transfer *transfer = &qca->spi_xfer1;
+	struct spi_message msg;
+	struct spi_transfer transfer;
 	int ret;
 
-	transfer->tx_buf = src;
-	transfer->rx_buf = NULL;
-	transfer->len = len;
+	memset(&transfer, 0, sizeof(transfer));
+	spi_message_init(&msg);
+
+	transfer.tx_buf = src;
+	transfer.len = len;
 
-	ret = spi_sync(qca->spi_dev, msg);
+	spi_message_add_tail(&transfer, &msg);
+	ret = spi_sync(qca->spi_dev, &msg);
 
-	if (ret || (msg->actual_length != len)) {
+	if (ret || (msg.actual_length != len)) {
 		qcaspi_spi_error(qca);
 		return 0;
 	}
@@ -146,23 +151,25 @@ qcaspi_write_legacy(struct qcaspi *qca, u8 *src, u32 len)
 static u32
 qcaspi_read_burst(struct qcaspi *qca, u8 *dst, u32 len)
 {
-	struct spi_message *msg = &qca->spi_msg2;
+	struct spi_message msg;
 	__be16 cmd;
-	struct spi_transfer *transfer = &qca->spi_xfer2[0];
+	struct spi_transfer transfer[2];
 	int ret;
 
+	memset(&transfer, 0, sizeof(transfer));
+	spi_message_init(&msg);
+
 	cmd = cpu_to_be16(QCA7K_SPI_READ | QCA7K_SPI_EXTERNAL);
-	transfer->tx_buf = &cmd;
-	transfer->rx_buf = NULL;
-	transfer->len = QCASPI_CMD_LEN;
-	transfer = &qca->spi_xfer2[1];
-	transfer->tx_buf = NULL;
-	transfer->rx_buf = dst;
-	transfer->len = len;
+	transfer[0].tx_buf = &cmd;
+	transfer[0].len = QCASPI_CMD_LEN;
+	transfer[1].rx_buf = dst;
+	transfer[1].len = len;
 
-	ret = spi_sync(qca->spi_dev, msg);
+	spi_message_add_tail(&transfer[0], &msg);
+	spi_message_add_tail(&transfer[1], &msg);
+	ret = spi_sync(qca->spi_dev, &msg);
 
-	if (ret || (msg->actual_length != QCASPI_CMD_LEN + len)) {
+	if (ret || (msg.actual_length != QCASPI_CMD_LEN + len)) {
 		qcaspi_spi_error(qca);
 		return 0;
 	}
@@ -173,17 +180,20 @@ qcaspi_read_burst(struct qcaspi *qca, u8 *dst, u32 len)
 static u32
 qcaspi_read_legacy(struct qcaspi *qca, u8 *dst, u32 len)
 {
-	struct spi_message *msg = &qca->spi_msg1;
-	struct spi_transfer *transfer = &qca->spi_xfer1;
+	struct spi_message msg;
+	struct spi_transfer transfer;
 	int ret;
 
-	transfer->tx_buf = NULL;
-	transfer->rx_buf = dst;
-	transfer->len = len;
+	memset(&transfer, 0, sizeof(transfer));
+	spi_message_init(&msg);
 
-	ret = spi_sync(qca->spi_dev, msg);
+	transfer.rx_buf = dst;
+	transfer.len = len;
 
-	if (ret || (msg->actual_length != len)) {
+	spi_message_add_tail(&transfer, &msg);
+	ret = spi_sync(qca->spi_dev, &msg);
+
+	if (ret || (msg.actual_length != len)) {
 		qcaspi_spi_error(qca);
 		return 0;
 	}
@@ -195,19 +205,23 @@ static int
 qcaspi_tx_cmd(struct qcaspi *qca, u16 cmd)
 {
 	__be16 tx_data;
-	struct spi_message *msg = &qca->spi_msg1;
-	struct spi_transfer *transfer = &qca->spi_xfer1;
+	struct spi_message msg;
+	struct spi_transfer transfer;
 	int ret;
 
+	memset(&transfer, 0, sizeof(transfer));
+
+	spi_message_init(&msg);
+
 	tx_data = cpu_to_be16(cmd);
-	transfer->len = sizeof(tx_data);
-	transfer->tx_buf = &tx_data;
-	transfer->rx_buf = NULL;
+	transfer.len = sizeof(cmd);
+	transfer.tx_buf = &tx_data;
+	spi_message_add_tail(&transfer, &msg);
 
-	ret = spi_sync(qca->spi_dev, msg);
+	ret = spi_sync(qca->spi_dev, &msg);
 
 	if (!ret)
-		ret = msg->status;
+		ret = msg.status;
 
 	if (ret)
 		qcaspi_spi_error(qca);
@@ -835,16 +849,6 @@ qcaspi_netdev_setup(struct net_device *dev)
 	qca = netdev_priv(dev);
 	memset(qca, 0, sizeof(struct qcaspi));
 
-	memset(&qca->spi_xfer1, 0, sizeof(struct spi_transfer));
-	memset(&qca->spi_xfer2, 0, sizeof(struct spi_transfer) * 2);
-
-	spi_message_init(&qca->spi_msg1);
-	spi_message_add_tail(&qca->spi_xfer1, &qca->spi_msg1);
-
-	spi_message_init(&qca->spi_msg2);
-	spi_message_add_tail(&qca->spi_xfer2[0], &qca->spi_msg2);
-	spi_message_add_tail(&qca->spi_xfer2[1], &qca->spi_msg2);
-
 	memset(&qca->txr, 0, sizeof(qca->txr));
 	qca->txr.count = TX_RING_MAX_LEN;
 }
diff --git a/drivers/net/ethernet/qualcomm/qca_spi.h b/drivers/net/ethernet/qualcomm/qca_spi.h
index fc4beb1b32d1..fc0e98726b36 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.h
+++ b/drivers/net/ethernet/qualcomm/qca_spi.h
@@ -83,11 +83,6 @@ struct qcaspi {
 	struct tx_ring txr;
 	struct qcaspi_stats stats;
 
-	struct spi_message spi_msg1;
-	struct spi_message spi_msg2;
-	struct spi_transfer spi_xfer1;
-	struct spi_transfer spi_xfer2[2];
-
 	u8 *rx_buffer;
 	u32 buffer_size;
 	u8 sync;
-- 
2.17.1


From b5fbf4841a1a2aa0c42fcb51d35bce7d43906062 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 10 Sep 2018 18:27:26 -0700
Subject: [PATCH 04/15] rds: fix two RCU related problems

[ Upstream commit cc4dfb7f70a344f24c1c71e298deea0771dadcb2 ]

When a rds sock is bound, it is inserted into the bind_hash_table
which is protected by RCU. But when releasing rds sock, after it
is removed from this hash table, it is freed immediately without
respecting RCU grace period. This could cause some use-after-free
as reported by syzbot.

Mark the rds sock with SOCK_RCU_FREE before inserting it into the
bind_hash_table, so that it would be always freed after a RCU grace
period.

The other problem is in rds_find_bound(), the rds sock could be
freed in between rhashtable_lookup_fast() and rds_sock_addref(),
so we need to extend RCU read lock protection in rds_find_bound()
to close this race condition.

Reported-and-tested-by: syzbot+8967084bcac563795dc6@syzkaller.appspotmail.com
Reported-by: syzbot+93a5839deb355537440f@syzkaller.appspotmail.com
Cc: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Cc: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Cc: rds-devel@oss.oracle.com
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oarcle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/bind.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/rds/bind.c b/net/rds/bind.c
index 5aa3a64aa4f0..48257d3a4201 100644
--- a/net/rds/bind.c
+++ b/net/rds/bind.c
@@ -60,11 +60,13 @@ struct rds_sock *rds_find_bound(__be32 addr, __be16 port)
 	u64 key = ((u64)addr << 32) | port;
 	struct rds_sock *rs;
 
-	rs = rhashtable_lookup_fast(&bind_hash_table, &key, ht_parms);
+	rcu_read_lock();
+	rs = rhashtable_lookup(&bind_hash_table, &key, ht_parms);
 	if (rs && !sock_flag(rds_rs_to_sk(rs), SOCK_DEAD))
 		rds_sock_addref(rs);
 	else
 		rs = NULL;
+	rcu_read_unlock();
 
 	rdsdebug("returning rs %p for %pI4:%u\n", rs, &addr,
 		ntohs(port));
@@ -157,6 +159,7 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		goto out;
 	}
 
+	sock_set_flag(sk, SOCK_RCU_FREE);
 	ret = rds_add_bound(rs, sin->sin_addr.s_addr, &sin->sin_port);
 	if (ret)
 		goto out;
-- 
2.17.1


From 255e08c960a6d63cc43a613720737511d0795c31 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 3 Sep 2018 19:12:41 -0700
Subject: [PATCH 05/15] tipc: orphan sock in tipc_release()

[ Upstream commit 0a3b8b2b215f9e84b82ae97df71292ccfd92b1e7 ]

Before we unlock the sock in tipc_release(), we have to
detach sk->sk_socket from sk, otherwise a parallel
tipc_sk_fill_sock_diag() could stil read it after we
free this socket.

Fixes: c30b70deb5f4 ("tipc: implement socket diagnostics for AF_TIPC")
Reported-and-tested-by: syzbot+48804b87c16588ad491d@syzkaller.appspotmail.com
Cc: Jon Maloy <jon.maloy@ericsson.com>
Cc: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/socket.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 0a5fa347135e..ac8ca238c541 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -578,6 +578,7 @@ static int tipc_release(struct socket *sock)
 	sk_stop_timer(sk, &sk->sk_timer);
 	tipc_sk_remove(tsk);
 
+	sock_orphan(sk);
 	/* Reject any messages that accumulated in backlog queue */
 	release_sock(sk);
 	tipc_dest_list_purge(&tsk->cong_links);
-- 
2.17.1


From a09cf81dc7b7bd56e16bab7c8a52b44dacdc26ee Mon Sep 17 00:00:00 2001
From: Raed Salem <raeds@mellanox.com>
Date: Tue, 21 Aug 2018 15:22:42 +0300
Subject: [PATCH 06/15] net/mlx5: E-Switch, Fix memory leak when creating
 switchdev mode FDB tables

[ Upstream commit c88a026e01219488e745f4f0267fd76c2bb68421 ]

The memory allocated for the slow path table flow group input structure
was not freed upon successful return, fix that.

Fixes: 1967ce6ea5c8 ("net/mlx5: E-Switch, Refactor fast path FDB table creation in switchdev mode")
Signed-off-by: Raed Salem <raeds@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 91f1209886ff..4c53957c918c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -658,6 +658,7 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
 	if (err)
 		goto miss_rule_err;
 
+	kvfree(flow_group_in);
 	return 0;
 
 miss_rule_err:
-- 
2.17.1


From 673a9bf52bb9bea871db4f3de799b708ac9b4533 Mon Sep 17 00:00:00 2001
From: Vakul Garg <vakul.garg@nxp.com>
Date: Thu, 6 Sep 2018 21:41:40 +0530
Subject: [PATCH 07/15] net/tls: Set count of SG entries if sk_alloc_sg returns
 -ENOSPC

[ Upstream commit 52ea992cfac357b73180d5c051dca43bc8d20c2a ]

tls_sw_sendmsg() allocates plaintext and encrypted SG entries using
function sk_alloc_sg(). In case the number of SG entries hit
MAX_SKB_FRAGS, sk_alloc_sg() returns -ENOSPC and sets the variable for
current SG index to '0'. This leads to calling of function
tls_push_record() with 'sg_encrypted_num_elem = 0' and later causes
kernel crash. To fix this, set the number of SG elements to the number
of elements in plaintext/encrypted SG arrays in case sk_alloc_sg()
returns -ENOSPC.

Fixes: 3c4d7559159b ("tls: kernel TLS support")
Signed-off-by: Vakul Garg <vakul.garg@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 1f3d9789af30..db0712b8ddf1 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -149,6 +149,9 @@ static int alloc_encrypted_sg(struct sock *sk, int len)
 			 &ctx->sg_encrypted_num_elem,
 			 &ctx->sg_encrypted_size, 0);
 
+	if (rc == -ENOSPC)
+		ctx->sg_encrypted_num_elem = ARRAY_SIZE(ctx->sg_encrypted_data);
+
 	return rc;
 }
 
@@ -162,6 +165,9 @@ static int alloc_plaintext_sg(struct sock *sk, int len)
 			 &ctx->sg_plaintext_num_elem, &ctx->sg_plaintext_size,
 			 tls_ctx->pending_open_record_frags);
 
+	if (rc == -ENOSPC)
+		ctx->sg_plaintext_num_elem = ARRAY_SIZE(ctx->sg_plaintext_data);
+
 	return rc;
 }
 
-- 
2.17.1


From f82454a80739a930a98891fd5c239501040eb03c Mon Sep 17 00:00:00 2001
From: Huy Nguyen <huyn@mellanox.com>
Date: Wed, 15 Aug 2018 11:08:48 -0500
Subject: [PATCH 08/15] net/mlx5: Check for error in mlx5_attach_interface

[ Upstream commit 47bc94b82291e007da61ee1b3d18c77871f3e158 ]

Currently, mlx5_attach_interface does not check for error
after calling intf->attach or intf->add. When these two calls
fails, the client is not initialized and will cause issues such as
kernel panic on invalid address in the teardown path (mlx5_detach_interface)

Fixes: 737a234bb638 ("net/mlx5: Introduce attach/detach to interface API")
Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/dev.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
index b994b80d5714..922811fb66e7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -132,11 +132,11 @@ void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv)
 	delayed_event_start(priv);
 
 	dev_ctx->context = intf->add(dev);
-	set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state);
-	if (intf->attach)
-		set_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state);
-
 	if (dev_ctx->context) {
+		set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state);
+		if (intf->attach)
+			set_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state);
+
 		spin_lock_irq(&priv->ctx_lock);
 		list_add_tail(&dev_ctx->list, &priv->ctx_list);
 
@@ -211,12 +211,17 @@ static void mlx5_attach_interface(struct mlx5_interface *intf, struct mlx5_priv
 	if (intf->attach) {
 		if (test_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state))
 			goto out;
-		intf->attach(dev, dev_ctx->context);
+		if (intf->attach(dev, dev_ctx->context))
+			goto out;
+
 		set_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state);
 	} else {
 		if (test_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state))
 			goto out;
 		dev_ctx->context = intf->add(dev);
+		if (!dev_ctx->context)
+			goto out;
+
 		set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state);
 	}
 
-- 
2.17.1


From fd5c3326b19feb95d3c8e29820f9019981675842 Mon Sep 17 00:00:00 2001
From: Jack Morgenstein <jackm@dev.mellanox.co.il>
Date: Tue, 7 Aug 2018 09:59:03 +0300
Subject: [PATCH 09/15] net/mlx5: Fix debugfs cleanup in the device init/remove
 flow

[ Upstream commit 5df816e7f43f1297c40021ef17ec6e722b45c82f ]

When initializing the device (procedure init_one), the driver
calls mlx5_pci_init to perform pci initialization. As part of this
initialization, mlx5_pci_init creates a debugfs directory.
If this creation fails, init_one aborts, returning failure to
the caller (which is the probe method caller).

The main reason for such a failure to occur is if the debugfs
directory already exists. This can happen if the last time
mlx5_pci_close was called, debugfs_remove (silently) failed due
to the debugfs directory not being empty.

Guarantee that such a debugfs_remove failure will not occur by
instead calling debugfs_remove_recursive in procedure mlx5_pci_close.

Fixes: 59211bd3b632 ("net/mlx5: Split the load/unload flow into hardware and software flows")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 260efa07ee9d..76e6ca87db11 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -874,8 +874,10 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
 	priv->numa_node = dev_to_node(&dev->pdev->dev);
 
 	priv->dbg_root = debugfs_create_dir(dev_name(&pdev->dev), mlx5_debugfs_root);
-	if (!priv->dbg_root)
+	if (!priv->dbg_root) {
+		dev_err(&pdev->dev, "Cannot create debugfs dir, aborting\n");
 		return -ENOMEM;
+	}
 
 	err = mlx5_pci_enable_device(dev);
 	if (err) {
@@ -924,7 +926,7 @@ static void mlx5_pci_close(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
 	pci_clear_master(dev->pdev);
 	release_bar(dev->pdev);
 	mlx5_pci_disable_device(dev);
-	debugfs_remove(priv->dbg_root);
+	debugfs_remove_recursive(priv->dbg_root);
 }
 
 static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
-- 
2.17.1


From 4dbd17fc7eb0cc83cde90ab21a6d9124abdd6ccd Mon Sep 17 00:00:00 2001
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Mon, 10 Sep 2018 22:19:48 +0800
Subject: [PATCH 10/15] erspan: fix error handling for erspan tunnel

[ Upstream commit 51dc63e3911fbb1f0a7a32da2fe56253e2040ea4 ]

When processing icmp unreachable message for erspan tunnel, tunnel id
should be erspan_net_id instead of ipgre_net_id.

Fixes: 84e54fe0a5ea ("gre: introduce native tunnel support for ERSPAN")
Cc: William Tu <u9012063@gmail.com>
Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Acked-by: William Tu <u9012063@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_gre.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 055f4bbba86b..6909d4d74072 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -178,6 +178,9 @@ static void ipgre_err(struct sk_buff *skb, u32 info,
 
 	if (tpi->proto == htons(ETH_P_TEB))
 		itn = net_generic(net, gre_tap_net_id);
+	else if (tpi->proto == htons(ETH_P_ERSPAN) ||
+		 tpi->proto == htons(ETH_P_ERSPAN2))
+		itn = net_generic(net, erspan_net_id);
 	else
 		itn = net_generic(net, ipgre_net_id);
 
-- 
2.17.1


From ff6daf395dd0defbb2deed2b5a013f665563b3d0 Mon Sep 17 00:00:00 2001
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Mon, 10 Sep 2018 22:19:47 +0800
Subject: [PATCH 11/15] erspan: return PACKET_REJECT when the appropriate
 tunnel is not found

[ Upstream commit 5a64506b5c2c3cdb29d817723205330378075448 ]

If erspan tunnel hasn't been established, we'd better send icmp port
unreachable message after receive erspan packets.

Fixes: 84e54fe0a5ea ("gre: introduce native tunnel support for ERSPAN")
Cc: William Tu <u9012063@gmail.com>
Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Acked-by: William Tu <u9012063@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_gre.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 6909d4d74072..41883c34a385 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -331,6 +331,8 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 		ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error);
 		return PACKET_RCVD;
 	}
+	return PACKET_REJECT;
+
 drop:
 	kfree_skb(skb);
 	return PACKET_RCVD;
-- 
2.17.1


From 5ea8607cd5ec2934fdb1929b9064fa5d337aa53f Mon Sep 17 00:00:00 2001
From: Vincent Whitchurch <vincent.whitchurch@axis.com>
Date: Thu, 6 Sep 2018 15:54:59 +0200
Subject: [PATCH 12/15] tcp: really ignore MSG_ZEROCOPY if no SO_ZEROCOPY

[ Upstream commit 5cf4a8532c992bb22a9ecd5f6d93f873f4eaccc2 ]

According to the documentation in msg_zerocopy.rst, the SO_ZEROCOPY
flag was introduced because send(2) ignores unknown message flags and
any legacy application which was accidentally passing the equivalent of
MSG_ZEROCOPY earlier should not see any new behaviour.

Before commit f214f915e7db ("tcp: enable MSG_ZEROCOPY"), a send(2) call
which passed the equivalent of MSG_ZEROCOPY without setting SO_ZEROCOPY
would succeed.  However, after that commit, it fails with -ENOBUFS.  So
it appears that the SO_ZEROCOPY flag fails to fulfill its intended
purpose.  Fix it.

Fixes: f214f915e7db ("tcp: enable MSG_ZEROCOPY")
Signed-off-by: Vincent Whitchurch <vincent.whitchurch@axis.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 3 ---
 net/ipv4/tcp.c    | 2 +-
 2 files changed, 1 insertion(+), 4 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index fb35b62af272..3680912f056a 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -939,9 +939,6 @@ struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size)
 
 	WARN_ON_ONCE(!in_task());
 
-	if (!sock_flag(sk, SOCK_ZEROCOPY))
-		return NULL;
-
 	skb = sock_omalloc(sk, 0, GFP_KERNEL);
 	if (!skb)
 		return NULL;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 4491faf83f4f..086201d96d54 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1186,7 +1186,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 
 	flags = msg->msg_flags;
 
-	if (flags & MSG_ZEROCOPY && size) {
+	if (flags & MSG_ZEROCOPY && size && sock_flag(sk, SOCK_ZEROCOPY)) {
 		if (sk->sk_state != TCP_ESTABLISHED) {
 			err = -EINVAL;
 			goto out_err;
-- 
2.17.1


From 7e84169ef3daec389d09b5839bc1c6748d359e07 Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@mellanox.com>
Date: Sun, 19 Aug 2018 08:56:09 +0300
Subject: [PATCH 13/15] net/mlx5: Fix not releasing read lock when adding flow
 rules

[ Upstream commit 071304772fc747d5df13c51f1cf48a4b922a5e0d ]

If building match list fg fails and we never jumped to
search_again_locked label then the function returned without
unlocking the read lock.

Fixes: bd71b08ec2ee ("net/mlx5: Support multiple updates of steering rules in parallel")
Signed-off-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 6ddb2565884d..8df9132896d6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -1797,6 +1797,8 @@ _mlx5_add_flow_rules(struct mlx5_flow_table *ft,
 	if (err) {
 		if (take_write)
 			up_write_ref_node(&ft->node);
+		else
+			up_read_ref_node(&ft->node);
 		return ERR_PTR(err);
 	}
 
-- 
2.17.1


From a2b4ed7646fa1a8a6cc6aa84d9bea60ecde220b8 Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@mellanox.com>
Date: Mon, 20 Aug 2018 11:43:03 +0300
Subject: [PATCH 14/15] net/mlx5: Fix possible deadlock from lockdep when
 adding fte to fg

[ Upstream commit ad9421e36a77056a4f095d49b9605e80b4d216ed ]

This is a false positive report due to incorrect nested lock
annotations as we lock multiple fgs with the same subclass.
Instead of locking all fgs only lock the one being used as was
done before.

Fixes: bd71b08ec2ee ("net/mlx5: Support multiple updates of steering rules in parallel")
Signed-off-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/fs_core.c | 74 +++++++++----------
 1 file changed, 37 insertions(+), 37 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 8df9132896d6..0031c510ab68 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -1649,6 +1649,33 @@ static u64 matched_fgs_get_version(struct list_head *match_head)
 	return version;
 }
 
+static struct fs_fte *
+lookup_fte_locked(struct mlx5_flow_group *g,
+		  u32 *match_value,
+		  bool take_write)
+{
+	struct fs_fte *fte_tmp;
+
+	if (take_write)
+		nested_down_write_ref_node(&g->node, FS_LOCK_PARENT);
+	else
+		nested_down_read_ref_node(&g->node, FS_LOCK_PARENT);
+	fte_tmp = rhashtable_lookup_fast(&g->ftes_hash, match_value,
+					 rhash_fte);
+	if (!fte_tmp || !tree_get_node(&fte_tmp->node)) {
+		fte_tmp = NULL;
+		goto out;
+	}
+
+	nested_down_write_ref_node(&fte_tmp->node, FS_LOCK_CHILD);
+out:
+	if (take_write)
+		up_write_ref_node(&g->node);
+	else
+		up_read_ref_node(&g->node);
+	return fte_tmp;
+}
+
 static struct mlx5_flow_handle *
 try_add_to_existing_fg(struct mlx5_flow_table *ft,
 		       struct list_head *match_head,
@@ -1671,10 +1698,6 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft,
 	if (IS_ERR(fte))
 		return  ERR_PTR(-ENOMEM);
 
-	list_for_each_entry(iter, match_head, list) {
-		nested_down_read_ref_node(&iter->g->node, FS_LOCK_PARENT);
-	}
-
 search_again_locked:
 	version = matched_fgs_get_version(match_head);
 	/* Try to find a fg that already contains a matching fte */
@@ -1682,20 +1705,9 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft,
 		struct fs_fte *fte_tmp;
 
 		g = iter->g;
-		fte_tmp = rhashtable_lookup_fast(&g->ftes_hash, spec->match_value,
-						 rhash_fte);
-		if (!fte_tmp || !tree_get_node(&fte_tmp->node))
+		fte_tmp = lookup_fte_locked(g, spec->match_value, take_write);
+		if (!fte_tmp)
 			continue;
-
-		nested_down_write_ref_node(&fte_tmp->node, FS_LOCK_CHILD);
-		if (!take_write) {
-			list_for_each_entry(iter, match_head, list)
-				up_read_ref_node(&iter->g->node);
-		} else {
-			list_for_each_entry(iter, match_head, list)
-				up_write_ref_node(&iter->g->node);
-		}
-
 		rule = add_rule_fg(g, spec->match_value,
 				   flow_act, dest, dest_num, fte_tmp);
 		up_write_ref_node(&fte_tmp->node);
@@ -1704,19 +1716,6 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft,
 		return rule;
 	}
 
-	/* No group with matching fte found. Try to add a new fte to any
-	 * matching fg.
-	 */
-
-	if (!take_write) {
-		list_for_each_entry(iter, match_head, list)
-			up_read_ref_node(&iter->g->node);
-		list_for_each_entry(iter, match_head, list)
-			nested_down_write_ref_node(&iter->g->node,
-						   FS_LOCK_PARENT);
-		take_write = true;
-	}
-
 	/* Check the ft version, for case that new flow group
 	 * was added while the fgs weren't locked
 	 */
@@ -1728,27 +1727,30 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft,
 	/* Check the fgs version, for case the new FTE with the
 	 * same values was added while the fgs weren't locked
 	 */
-	if (version != matched_fgs_get_version(match_head))
+	if (version != matched_fgs_get_version(match_head)) {
+		take_write = true;
 		goto search_again_locked;
+	}
 
 	list_for_each_entry(iter, match_head, list) {
 		g = iter->g;
 
 		if (!g->node.active)
 			continue;
+
+		nested_down_write_ref_node(&g->node, FS_LOCK_PARENT);
+
 		err = insert_fte(g, fte);
 		if (err) {
+			up_write_ref_node(&g->node);
 			if (err == -ENOSPC)
 				continue;
-			list_for_each_entry(iter, match_head, list)
-				up_write_ref_node(&iter->g->node);
 			kmem_cache_free(steering->ftes_cache, fte);
 			return ERR_PTR(err);
 		}
 
 		nested_down_write_ref_node(&fte->node, FS_LOCK_CHILD);
-		list_for_each_entry(iter, match_head, list)
-			up_write_ref_node(&iter->g->node);
+		up_write_ref_node(&g->node);
 		rule = add_rule_fg(g, spec->match_value,
 				   flow_act, dest, dest_num, fte);
 		up_write_ref_node(&fte->node);
@@ -1757,8 +1759,6 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft,
 	}
 	rule = ERR_PTR(-ENOENT);
 out:
-	list_for_each_entry(iter, match_head, list)
-		up_write_ref_node(&iter->g->node);
 	kmem_cache_free(steering->ftes_cache, fte);
 	return rule;
 }
-- 
2.17.1


From ca3027c34cc0eecb39b20f593d0f3f33cec00b43 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Tue, 21 Aug 2018 16:04:41 +0300
Subject: [PATCH 15/15] net/mlx5: Use u16 for Work Queue buffer fragment size

[ Upstream commit 8d71e818506718e8d7032ce824b5c74a17d4f7a5 ]

Minimal stride size is 16.
Hence, the number of strides in a fragment (of PAGE_SIZE)
is <= PAGE_SIZE / 16 <= 4K.

u16 is sufficient to represent this.

Fixes: 388ca8be0037 ("IB/mlx5: Implement fragmented completion queue (CQ)")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/wq.c | 4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/wq.h | 2 +-
 include/linux/mlx5/driver.h                  | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c
index c8c315eb5128..d838af9539b1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c
@@ -39,9 +39,9 @@ u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq)
 	return (u32)wq->fbc.sz_m1 + 1;
 }
 
-u32 mlx5_wq_cyc_get_frag_size(struct mlx5_wq_cyc *wq)
+u16 mlx5_wq_cyc_get_frag_size(struct mlx5_wq_cyc *wq)
 {
-	return (u32)wq->fbc.frag_sz_m1 + 1;
+	return wq->fbc.frag_sz_m1 + 1;
 }
 
 u32 mlx5_cqwq_get_size(struct mlx5_cqwq *wq)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h
index 0b47126815b6..16476cc1a602 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/wq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h
@@ -80,7 +80,7 @@ int mlx5_wq_cyc_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		       void *wqc, struct mlx5_wq_cyc *wq,
 		       struct mlx5_wq_ctrl *wq_ctrl);
 u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq);
-u32 mlx5_wq_cyc_get_frag_size(struct mlx5_wq_cyc *wq);
+u16 mlx5_wq_cyc_get_frag_size(struct mlx5_wq_cyc *wq);
 
 int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		      void *qpc, struct mlx5_wq_qp *wq,
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 01a1a8baeb9d..64f450593b54 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -357,7 +357,7 @@ struct mlx5_frag_buf {
 struct mlx5_frag_buf_ctrl {
 	struct mlx5_frag_buf	frag_buf;
 	u32			sz_m1;
-	u32			frag_sz_m1;
+	u16			frag_sz_m1;
 	u32			strides_offset;
 	u8			log_sz;
 	u8			log_stride;
-- 
2.17.1

Re: [PATCHES] Networking

[Greg KH]

On Tue, Sep 18, 2018 at 09:14:58AM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.14.x and
> v4.18.x -stable, respectively.

Thanks for these, all now queued up.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 111 bytes --]


Please queue up the following networking bug fixes for v4.14.x and
v4.18.x -stable, respectively.

Thank you!

[-- Attachment #2: net_414.mbox --]
[-- Type: Application/Octet-Stream, Size: 33655 bytes --]

From 28bc53e94dd4af7ec59c0ead5769fe0e1b88e46b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@toke.dk>
Date: Thu, 13 Sep 2018 16:43:07 +0200
Subject: [PATCH 01/13] gso_segment: Reset skb->mac_len after modifying network
 header
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit c56cae23c6b167acc68043c683c4573b80cbcc2c ]

When splitting a GSO segment that consists of encapsulated packets, the
skb->mac_len of the segments can end up being set wrong, causing packet
drops in particular when using act_mirred and ifb interfaces in
combination with a qdisc that splits GSO packets.

This happens because at the time skb_segment() is called, network_header
will point to the inner header, throwing off the calculation in
skb_reset_mac_len(). The network_header is subsequently adjust by the
outer IP gso_segment handlers, but they don't set the mac_len.

Fix this by adding skb_reset_mac_len() calls to both the IPv4 and IPv6
gso_segment handlers, after they modify the network_header.

Many thanks to Eric Dumazet for his help in identifying the cause of
the bug.

Acked-by: Dave Taht <dave.taht@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/af_inet.c     | 1 +
 net/ipv6/ip6_offload.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index b9d9a2b8792c..f31c09873d0f 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1307,6 +1307,7 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 		if (encap)
 			skb_reset_inner_headers(skb);
 		skb->network_header = (u8 *)iph - skb->head;
+		skb_reset_mac_len(skb);
 	} while ((skb = skb->next));
 
 out:
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 4a87f9428ca5..e3698b6d8231 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -113,6 +113,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 			payload_len = skb->len - nhoff - sizeof(*ipv6h);
 		ipv6h->payload_len = htons(payload_len);
 		skb->network_header = (u8 *)ipv6h - skb->head;
+		skb_reset_mac_len(skb);
 
 		if (udpfrag) {
 			int err = ip6_find_1stfragopt(skb, &prevhdr);
-- 
2.13.6


From 67a7d1d6ca7894b852138553ba8f8e46b0ca7abf Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 14 Sep 2018 12:02:31 -0700
Subject: [PATCH 02/13] ipv6: fix possible use-after-free in ip6_xmit()

[ Upstream commit bbd6528d28c1b8e80832b3b018ec402b6f5c3215 ]

In the unlikely case ip6_xmit() has to call skb_realloc_headroom(),
we need to call skb_set_owner_w() before consuming original skb,
otherwise we risk a use-after-free.

Bring IPv6 in line with what we do in IPv4 to fix this.

Fixes: 1da177e4c3f41 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_output.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 1da021527fcd..9ab1e0fcbc13 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -219,12 +219,10 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 				kfree_skb(skb);
 				return -ENOBUFS;
 			}
+			if (skb->sk)
+				skb_set_owner_w(skb2, skb->sk);
 			consume_skb(skb);
 			skb = skb2;
-			/* skb_set_owner_w() changes sk->sk_wmem_alloc atomically,
-			 * it is safe to call in our context (socket lock not held)
-			 */
-			skb_set_owner_w(skb, (struct sock *)sk);
 		}
 		if (opt->opt_flen)
 			ipv6_push_frag_opts(skb, opt, &proto);
-- 
2.13.6


From eed3a34e0c1428f7fc60bc26d34504562460a08b Mon Sep 17 00:00:00 2001
From: Willy Tarreau <w@1wt.eu>
Date: Wed, 12 Sep 2018 07:36:35 +0200
Subject: [PATCH 03/13] net/appletalk: fix minor pointer leak to userspace in
 SIOCFINDIPDDPRT

[ Upstream commit 9824dfae5741275473a23a7ed5756c7b6efacc9d ]

Fields ->dev and ->next of struct ipddp_route may be copied to
userspace on the SIOCFINDIPDDPRT ioctl. This is only accessible
to CAP_NET_ADMIN though. Let's manually copy the relevant fields
instead of using memcpy().

BugLink: http://blog.infosectcbr.com.au/2018/09/linux-kernel-infoleaks.html
Cc: Jann Horn <jannh@google.com>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/appletalk/ipddp.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/appletalk/ipddp.c b/drivers/net/appletalk/ipddp.c
index 9375cef22420..3d27616d9c85 100644
--- a/drivers/net/appletalk/ipddp.c
+++ b/drivers/net/appletalk/ipddp.c
@@ -283,8 +283,12 @@ static int ipddp_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
                 case SIOCFINDIPDDPRT:
 			spin_lock_bh(&ipddp_route_lock);
 			rp = __ipddp_find_route(&rcp);
-			if (rp)
-				memcpy(&rcp2, rp, sizeof(rcp2));
+			if (rp) {
+				memset(&rcp2, 0, sizeof(rcp2));
+				rcp2.ip    = rp->ip;
+				rcp2.at    = rp->at;
+				rcp2.flags = rp->flags;
+			}
 			spin_unlock_bh(&ipddp_route_lock);
 
 			if (rp) {
-- 
2.13.6


From a9548c1f4229eef04597a44e82635d566b35f548 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Fri, 14 Sep 2018 17:39:53 +0100
Subject: [PATCH 04/13] net: hp100: fix always-true check for link up state

[ Upstream commit a7f38002fb69b44f8fc622ecb838665d0b8666af ]

The operation ~(p100_inb(VG_LAN_CFG_1) & HP100_LINK_UP) returns a value
that is always non-zero and hence the wait for the link to drop always
terminates prematurely.  Fix this by using a logical not operator instead
of a bitwise complement.  This issue has been in the driver since
pre-2.6.12-rc2.

Detected by CoverityScan, CID#114157 ("Logical vs. bitwise operator")

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hp/hp100.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hp/hp100.c b/drivers/net/ethernet/hp/hp100.c
index c8c7ad2eff77..9b5a68b65432 100644
--- a/drivers/net/ethernet/hp/hp100.c
+++ b/drivers/net/ethernet/hp/hp100.c
@@ -2634,7 +2634,7 @@ static int hp100_login_to_vg_hub(struct net_device *dev, u_short force_relogin)
 		/* Wait for link to drop */
 		time = jiffies + (HZ / 10);
 		do {
-			if (~(hp100_inb(VG_LAN_CFG_1) & HP100_LINK_UP_ST))
+			if (!(hp100_inb(VG_LAN_CFG_1) & HP100_LINK_UP_ST))
 				break;
 			if (!in_interrupt())
 				schedule_timeout_interruptible(1);
-- 
2.13.6


From 6ec55ded6156c7d111cc97d6983a8086fba69078 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Fri, 14 Sep 2018 16:28:05 +0200
Subject: [PATCH 05/13] pppoe: fix reception of frames with no mac header

[ Upstream commit 8540827ebac6b654ab2f69c8fbce9e4fbd6304a0 ]

pppoe_rcv() needs to look back at the Ethernet header in order to
lookup the PPPoE session. Therefore we need to ensure that the mac
header is big enough to contain an Ethernet header. Otherwise
eth_hdr(skb)->h_source might access invalid data.

==================================================================
BUG: KMSAN: uninit-value in __get_item drivers/net/ppp/pppoe.c:172 [inline]
BUG: KMSAN: uninit-value in get_item drivers/net/ppp/pppoe.c:236 [inline]
BUG: KMSAN: uninit-value in pppoe_rcv+0xcef/0x10e0 drivers/net/ppp/pppoe.c:450
CPU: 0 PID: 4543 Comm: syz-executor355 Not tainted 4.16.0+ #87
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google
01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x185/0x1d0 lib/dump_stack.c:53
 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067
 __msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:683
 __get_item drivers/net/ppp/pppoe.c:172 [inline]
 get_item drivers/net/ppp/pppoe.c:236 [inline]
 pppoe_rcv+0xcef/0x10e0 drivers/net/ppp/pppoe.c:450
 __netif_receive_skb_core+0x47df/0x4a90 net/core/dev.c:4562
 __netif_receive_skb net/core/dev.c:4627 [inline]
 netif_receive_skb_internal+0x49d/0x630 net/core/dev.c:4701
 netif_receive_skb+0x230/0x240 net/core/dev.c:4725
 tun_rx_batched drivers/net/tun.c:1555 [inline]
 tun_get_user+0x740f/0x7c60 drivers/net/tun.c:1962
 tun_chr_write_iter+0x1d4/0x330 drivers/net/tun.c:1990
 call_write_iter include/linux/fs.h:1782 [inline]
 new_sync_write fs/read_write.c:469 [inline]
 __vfs_write+0x7fb/0x9f0 fs/read_write.c:482
 vfs_write+0x463/0x8d0 fs/read_write.c:544
 SYSC_write+0x172/0x360 fs/read_write.c:589
 SyS_write+0x55/0x80 fs/read_write.c:581
 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x3d/0xa2
RIP: 0033:0x4447c9
RSP: 002b:00007fff64c8fc28 EFLAGS: 00000297 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00000000004447c9
RDX: 000000000000fd87 RSI: 0000000020000600 RDI: 0000000000000004
RBP: 00000000006cf018 R08: 00007fff64c8fda8 R09: 00007fff00006bda
R10: 0000000000005fe7 R11: 0000000000000297 R12: 00000000004020d0
R13: 0000000000402160 R14: 0000000000000000 R15: 0000000000000000

Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:278 [inline]
 kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:188
 kmsan_kmalloc+0x94/0x100 mm/kmsan/kmsan.c:314
 kmsan_slab_alloc+0x11/0x20 mm/kmsan/kmsan.c:321
 slab_post_alloc_hook mm/slab.h:445 [inline]
 slab_alloc_node mm/slub.c:2737 [inline]
 __kmalloc_node_track_caller+0xaed/0x11c0 mm/slub.c:4369
 __kmalloc_reserve net/core/skbuff.c:138 [inline]
 __alloc_skb+0x2cf/0x9f0 net/core/skbuff.c:206
 alloc_skb include/linux/skbuff.h:984 [inline]
 alloc_skb_with_frags+0x1d4/0xb20 net/core/skbuff.c:5234
 sock_alloc_send_pskb+0xb56/0x1190 net/core/sock.c:2085
 tun_alloc_skb drivers/net/tun.c:1532 [inline]
 tun_get_user+0x2242/0x7c60 drivers/net/tun.c:1829
 tun_chr_write_iter+0x1d4/0x330 drivers/net/tun.c:1990
 call_write_iter include/linux/fs.h:1782 [inline]
 new_sync_write fs/read_write.c:469 [inline]
 __vfs_write+0x7fb/0x9f0 fs/read_write.c:482
 vfs_write+0x463/0x8d0 fs/read_write.c:544
 SYSC_write+0x172/0x360 fs/read_write.c:589
 SyS_write+0x55/0x80 fs/read_write.c:581
 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x3d/0xa2
==================================================================

Fixes: 224cf5ad14c0 ("ppp: Move the PPP drivers")
Reported-by: syzbot+f5f6080811c849739212@syzkaller.appspotmail.com
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pppoe.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 71e2aef6b7a1..951892da3352 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -429,6 +429,9 @@ static int pppoe_rcv(struct sk_buff *skb, struct net_device *dev,
 	if (!skb)
 		goto out;
 
+	if (skb_mac_header_len(skb) < ETH_HLEN)
+		goto drop;
+
 	if (!pskb_may_pull(skb, sizeof(struct pppoe_hdr)))
 		goto drop;
 
-- 
2.13.6


From d35b7270efdad9ae335f4aa287a81f3639c5c0c5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Mon, 17 Sep 2018 22:00:24 +0200
Subject: [PATCH 06/13] qmi_wwan: set DTR for modems in forced USB2 mode
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 922005c7f50e7f4b2a6dbc182e9c575b4f92396b ]

Recent firmware revisions have added the ability to force
these modems to USB2 mode, hiding their SuperSpeed
capabilities from the host.  The driver has been using the
SuperSpeed capability, as shown by the bcdUSB field of the
device descriptor, to detect the need to enable the DTR
quirk.  This method fails when the modems are forced to
USB2 mode by the modem firmware.

Fix by unconditionally enabling the DTR quirk for the
affected device IDs.

Reported-by: Fred Veldini <fred.veldini@gmail.com>
Reported-by: Deshu Wen <dwen@sierrawireless.com>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Reported-by: Fred Veldini <fred.veldini@gmail.com>
Reported-by: Deshu Wen <dwen@sierrawireless.com>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 31684f3382f6..c5d4b35bb72a 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1205,13 +1205,13 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1199, 0x9061, 8)},	/* Sierra Wireless Modem */
 	{QMI_FIXED_INTF(0x1199, 0x9063, 8)},	/* Sierra Wireless EM7305 */
 	{QMI_FIXED_INTF(0x1199, 0x9063, 10)},	/* Sierra Wireless EM7305 */
-	{QMI_FIXED_INTF(0x1199, 0x9071, 8)},	/* Sierra Wireless MC74xx */
-	{QMI_FIXED_INTF(0x1199, 0x9071, 10)},	/* Sierra Wireless MC74xx */
-	{QMI_FIXED_INTF(0x1199, 0x9079, 8)},	/* Sierra Wireless EM74xx */
-	{QMI_FIXED_INTF(0x1199, 0x9079, 10)},	/* Sierra Wireless EM74xx */
-	{QMI_FIXED_INTF(0x1199, 0x907b, 8)},	/* Sierra Wireless EM74xx */
-	{QMI_FIXED_INTF(0x1199, 0x907b, 10)},	/* Sierra Wireless EM74xx */
-	{QMI_FIXED_INTF(0x1199, 0x9091, 8)},	/* Sierra Wireless EM7565 */
+	{QMI_QUIRK_SET_DTR(0x1199, 0x9071, 8)},	/* Sierra Wireless MC74xx */
+	{QMI_QUIRK_SET_DTR(0x1199, 0x9071, 10)},/* Sierra Wireless MC74xx */
+	{QMI_QUIRK_SET_DTR(0x1199, 0x9079, 8)},	/* Sierra Wireless EM74xx */
+	{QMI_QUIRK_SET_DTR(0x1199, 0x9079, 10)},/* Sierra Wireless EM74xx */
+	{QMI_QUIRK_SET_DTR(0x1199, 0x907b, 8)},	/* Sierra Wireless EM74xx */
+	{QMI_QUIRK_SET_DTR(0x1199, 0x907b, 10)},/* Sierra Wireless EM74xx */
+	{QMI_QUIRK_SET_DTR(0x1199, 0x9091, 8)},	/* Sierra Wireless EM7565 */
 	{QMI_FIXED_INTF(0x1bbb, 0x011e, 4)},	/* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */
 	{QMI_FIXED_INTF(0x1bbb, 0x0203, 2)},	/* Alcatel L800MA */
 	{QMI_FIXED_INTF(0x2357, 0x0201, 4)},	/* TP-LINK HSUPA Modem MA180 */
-- 
2.13.6


From 8101ff08d562c1750ec2e9fb58529f1dc726dbaf Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 13 Sep 2018 16:27:20 +0200
Subject: [PATCH 07/13] udp4: fix IP_CMSG_CHECKSUM for connected sockets

[ Upstream commit 2b5a921740a55c00223a797d075b9c77c42cb171 ]

commit 2abb7cdc0dc8 ("udp: Add support for doing checksum
unnecessary conversion") left out the early demux path for
connected sockets. As a result IP_CMSG_CHECKSUM gives wrong
values for such socket when GRO is not enabled/available.

This change addresses the issue by moving the csum conversion to a
common helper and using such helper in both the default and the
early demux rx path.

Fixes: 2abb7cdc0dc8 ("udp: Add support for doing checksum unnecessary conversion")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 49 ++++++++++++++++++++++++++-----------------------
 1 file changed, 26 insertions(+), 23 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 5752bf7593dc..3de413867991 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2049,6 +2049,28 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh,
 							 inet_compute_pseudo);
 }
 
+/* wrapper for udp_queue_rcv_skb tacking care of csum conversion and
+ * return code conversion for ip layer consumption
+ */
+static int udp_unicast_rcv_skb(struct sock *sk, struct sk_buff *skb,
+			       struct udphdr *uh)
+{
+	int ret;
+
+	if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk))
+		skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
+					 inet_compute_pseudo);
+
+	ret = udp_queue_rcv_skb(sk, skb);
+
+	/* a return value > 0 means to resubmit the input, but
+	 * it wants the return to be -protocol, or 0
+	 */
+	if (ret > 0)
+		return -ret;
+	return 0;
+}
+
 /*
  *	All we need to do is get the socket, and then do a checksum.
  */
@@ -2095,14 +2117,9 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 		if (unlikely(sk->sk_rx_dst != dst))
 			udp_sk_rx_dst_set(sk, dst);
 
-		ret = udp_queue_rcv_skb(sk, skb);
+		ret = udp_unicast_rcv_skb(sk, skb, uh);
 		sock_put(sk);
-		/* a return value > 0 means to resubmit the input, but
-		 * it wants the return to be -protocol, or 0
-		 */
-		if (ret > 0)
-			return -ret;
-		return 0;
+		return ret;
 	}
 
 	if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST))
@@ -2110,22 +2127,8 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 						saddr, daddr, udptable, proto);
 
 	sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
-	if (sk) {
-		int ret;
-
-		if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk))
-			skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
-						 inet_compute_pseudo);
-
-		ret = udp_queue_rcv_skb(sk, skb);
-
-		/* a return value > 0 means to resubmit the input, but
-		 * it wants the return to be -protocol, or 0
-		 */
-		if (ret > 0)
-			return -ret;
-		return 0;
-	}
+	if (sk)
+		return udp_unicast_rcv_skb(sk, skb, uh);
 
 	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
 		goto drop;
-- 
2.13.6


From 2e91137c10b2ebb4b5977ac88c4b2657a83356bc Mon Sep 17 00:00:00 2001
From: Vasily Khoruzhick <vasilykh@arista.com>
Date: Thu, 13 Sep 2018 11:12:03 -0700
Subject: [PATCH 08/13] neighbour: confirm neigh entries when ARP packet is
 received

[ Upstream commit f0e0d04413fcce9bc76388839099aee93cd0d33b ]

Update 'confirmed' timestamp when ARP packet is received. It shouldn't
affect locktime logic and anyway entry can be confirmed by any higher-layer
protocol. Thus it makes sense to confirm it when ARP packet is received.

Fixes: 77d7123342dc ("neighbour: update neigh timestamps iff update is effective")
Signed-off-by: Vasily Khoruzhick <vasilykh@arista.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 514d697d4691..dcb89cbc2730 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1174,6 +1174,12 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
 		lladdr = neigh->ha;
 	}
 
+	/* Update confirmed timestamp for neighbour entry after we
+	 * received ARP packet even if it doesn't change IP to MAC binding.
+	 */
+	if (new & NUD_CONNECTED)
+		neigh->confirmed = jiffies;
+
 	/* If entry was valid and address is not changed,
 	   do not change entry state, if new one is STALE.
 	 */
@@ -1195,15 +1201,12 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
 		}
 	}
 
-	/* Update timestamps only once we know we will make a change to the
+	/* Update timestamp only once we know we will make a change to the
 	 * neighbour entry. Otherwise we risk to move the locktime window with
 	 * noop updates and ignore relevant ARP updates.
 	 */
-	if (new != old || lladdr != neigh->ha) {
-		if (new & NUD_CONNECTED)
-			neigh->confirmed = jiffies;
+	if (new != old || lladdr != neigh->ha)
 		neigh->updated = jiffies;
-	}
 
 	if (new != old) {
 		neigh_del_timer(neigh);
-- 
2.13.6


From 6311b98a12e8758bbfcebecbb5990053b18d226f Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 13 Sep 2018 16:27:21 +0200
Subject: [PATCH 09/13] udp6: add missing checks on edumux packet processing

[ Upstream commit eb63f2964dbe36f26deac77d3016791675821ded ]

Currently the UDPv6 early demux rx code path lacks some mandatory
checks, already implemented into the normal RX code path - namely
the checksum conversion and no_check6_rx check.

Similar to the previous commit, we move the common processing to
an UDPv6 specific helper and call it from both edemux code path
and normal code path. In respect to the UDPv4, we need to add an
explicit check for non zero csum according to no_check6_rx value.

Reported-by: Jianlin Shi <jishi@redhat.com>
Suggested-by: Xin Long <lucien.xin@gmail.com>
Fixes: c9f2c1ae123a ("udp6: fix socket leak on early demux")
Fixes: 2abb7cdc0dc8 ("udp: Add support for doing checksum unnecessary conversion")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/udp.c | 65 +++++++++++++++++++++++++++++++++-------------------------
 1 file changed, 37 insertions(+), 28 deletions(-)

diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 330d5ea8451b..5cee941ab0a9 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -780,6 +780,28 @@ static void udp6_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
 	}
 }
 
+/* wrapper for udp_queue_rcv_skb tacking care of csum conversion and
+ * return code conversion for ip layer consumption
+ */
+static int udp6_unicast_rcv_skb(struct sock *sk, struct sk_buff *skb,
+				struct udphdr *uh)
+{
+	int ret;
+
+	if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk))
+		skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
+					 ip6_compute_pseudo);
+
+	ret = udpv6_queue_rcv_skb(sk, skb);
+
+	/* a return value > 0 means to resubmit the input, but
+	 * it wants the return to be -protocol, or 0
+	 */
+	if (ret > 0)
+		return -ret;
+	return 0;
+}
+
 int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 		   int proto)
 {
@@ -831,13 +853,14 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 		if (unlikely(sk->sk_rx_dst != dst))
 			udp6_sk_rx_dst_set(sk, dst);
 
-		ret = udpv6_queue_rcv_skb(sk, skb);
-		sock_put(sk);
+		if (!uh->check && !udp_sk(sk)->no_check6_rx) {
+			sock_put(sk);
+			goto report_csum_error;
+		}
 
-		/* a return value > 0 means to resubmit the input */
-		if (ret > 0)
-			return ret;
-		return 0;
+		ret = udp6_unicast_rcv_skb(sk, skb, uh);
+		sock_put(sk);
+		return ret;
 	}
 
 	/*
@@ -850,30 +873,13 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	/* Unicast */
 	sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
 	if (sk) {
-		int ret;
-
-		if (!uh->check && !udp_sk(sk)->no_check6_rx) {
-			udp6_csum_zero_error(skb);
-			goto csum_error;
-		}
-
-		if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk))
-			skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
-						 ip6_compute_pseudo);
-
-		ret = udpv6_queue_rcv_skb(sk, skb);
-
-		/* a return value > 0 means to resubmit the input */
-		if (ret > 0)
-			return ret;
-
-		return 0;
+		if (!uh->check && !udp_sk(sk)->no_check6_rx)
+			goto report_csum_error;
+		return udp6_unicast_rcv_skb(sk, skb, uh);
 	}
 
-	if (!uh->check) {
-		udp6_csum_zero_error(skb);
-		goto csum_error;
-	}
+	if (!uh->check)
+		goto report_csum_error;
 
 	if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
 		goto discard;
@@ -894,6 +900,9 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 			    ulen, skb->len,
 			    daddr, ntohs(uh->dest));
 	goto discard;
+
+report_csum_error:
+	udp6_csum_zero_error(skb);
 csum_error:
 	__UDP6_INC_STATS(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE);
 discard:
-- 
2.13.6


From edc1a57539efc0a4a93be77c5548cecfa90b1d44 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Fri, 14 Sep 2018 12:03:18 +0200
Subject: [PATCH 10/13] net/sched: act_sample: fix NULL dereference in the data
 path

[ Upstream commit 34043d250f51368f214aed7f54c2dc29c819a8c7 ]

Matteo reported the following splat, testing the datapath of TC 'sample':

 BUG: KASAN: null-ptr-deref in tcf_sample_act+0xc4/0x310
 Read of size 8 at addr 0000000000000000 by task nc/433

 CPU: 0 PID: 433 Comm: nc Not tainted 4.19.0-rc3-kvm #17
 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS ?-20180531_142017-buildhw-08.phx2.fedoraproject.org-1.fc28 04/01/2014
 Call Trace:
  kasan_report.cold.6+0x6c/0x2fa
  tcf_sample_act+0xc4/0x310
  ? dev_hard_start_xmit+0x117/0x180
  tcf_action_exec+0xa3/0x160
  tcf_classify+0xdd/0x1d0
  htb_enqueue+0x18e/0x6b0
  ? deref_stack_reg+0x7a/0xb0
  ? htb_delete+0x4b0/0x4b0
  ? unwind_next_frame+0x819/0x8f0
  ? entry_SYSCALL_64_after_hwframe+0x44/0xa9
  __dev_queue_xmit+0x722/0xca0
  ? unwind_get_return_address_ptr+0x50/0x50
  ? netdev_pick_tx+0xe0/0xe0
  ? save_stack+0x8c/0xb0
  ? kasan_kmalloc+0xbe/0xd0
  ? __kmalloc_track_caller+0xe4/0x1c0
  ? __kmalloc_reserve.isra.45+0x24/0x70
  ? __alloc_skb+0xdd/0x2e0
  ? sk_stream_alloc_skb+0x91/0x3b0
  ? tcp_sendmsg_locked+0x71b/0x15a0
  ? tcp_sendmsg+0x22/0x40
  ? __sys_sendto+0x1b0/0x250
  ? __x64_sys_sendto+0x6f/0x80
  ? do_syscall_64+0x5d/0x150
  ? entry_SYSCALL_64_after_hwframe+0x44/0xa9
  ? __sys_sendto+0x1b0/0x250
  ? __x64_sys_sendto+0x6f/0x80
  ? do_syscall_64+0x5d/0x150
  ? entry_SYSCALL_64_after_hwframe+0x44/0xa9
  ip_finish_output2+0x495/0x590
  ? ip_copy_metadata+0x2e0/0x2e0
  ? skb_gso_validate_network_len+0x6f/0x110
  ? ip_finish_output+0x174/0x280
  __tcp_transmit_skb+0xb17/0x12b0
  ? __tcp_select_window+0x380/0x380
  tcp_write_xmit+0x913/0x1de0
  ? __sk_mem_schedule+0x50/0x80
  tcp_sendmsg_locked+0x49d/0x15a0
  ? tcp_rcv_established+0x8da/0xa30
  ? tcp_set_state+0x220/0x220
  ? clear_user+0x1f/0x50
  ? iov_iter_zero+0x1ae/0x590
  ? __fget_light+0xa0/0xe0
  tcp_sendmsg+0x22/0x40
  __sys_sendto+0x1b0/0x250
  ? __ia32_sys_getpeername+0x40/0x40
  ? _copy_to_user+0x58/0x70
  ? poll_select_copy_remaining+0x176/0x200
  ? __pollwait+0x1c0/0x1c0
  ? ktime_get_ts64+0x11f/0x140
  ? kern_select+0x108/0x150
  ? core_sys_select+0x360/0x360
  ? vfs_read+0x127/0x150
  ? kernel_write+0x90/0x90
  __x64_sys_sendto+0x6f/0x80
  do_syscall_64+0x5d/0x150
  entry_SYSCALL_64_after_hwframe+0x44/0xa9
 RIP: 0033:0x7fefef2b129d
 Code: ff ff ff ff eb b6 0f 1f 80 00 00 00 00 48 8d 05 51 37 0c 00 41 89 ca 8b 00 85 c0 75 20 45 31 c9 45 31 c0 b8 2c 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 6b f3 c3 66 0f 1f 84 00 00 00 00 00 41 56 41
 RSP: 002b:00007fff2f5350c8 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
 RAX: ffffffffffffffda RBX: 000056118d60c120 RCX: 00007fefef2b129d
 RDX: 0000000000002000 RSI: 000056118d629320 RDI: 0000000000000003
 RBP: 000056118d530370 R08: 0000000000000000 R09: 0000000000000000
 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000002000
 R13: 000056118d5c2a10 R14: 000056118d5c2a10 R15: 000056118d5303b8

tcf_sample_act() tried to update its per-cpu stats, but tcf_sample_init()
forgot to allocate them, because tcf_idr_create() was called with a wrong
value of 'cpustats'. Setting it to true proved to fix the reported crash.

Reported-by: Matteo Croce <mcroce@redhat.com>
Fixes: 65a206c01e8e ("net/sched: Change act_api and act_xxx modules to use IDR")
Fixes: 5c5670fae430 ("net/sched: Introduce sample tc action")
Tested-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_sample.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 53752b9327d0..a859b55d7899 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -64,7 +64,7 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, parm->index, est, a,
-				     &act_sample_ops, bind, false);
+				     &act_sample_ops, bind, true);
 		if (ret)
 			return ret;
 		ret = ACT_P_CREATED;
-- 
2.13.6


From 52232d0c09ab758ea47a38985b480b4e99bf8a89 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Wed, 12 Sep 2018 17:44:41 +0200
Subject: [PATCH 11/13] tls: don't copy the key out of
 tls12_crypto_info_aes_gcm_128

[ Upstream commit 7cba09c6d5bc73ebbd25a353742d9ddb7a713b95 ]

There's no need to copy the key to an on-stack buffer before calling
crypto_aead_setkey().

Fixes: 3c4d7559159b ("tls: kernel TLS support")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index fb79caf56d0e..3157a52b4867 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -655,7 +655,6 @@ static void tls_sw_free_resources(struct sock *sk)
 
 int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx)
 {
-	char keyval[TLS_CIPHER_AES_GCM_128_KEY_SIZE];
 	struct tls_crypto_info *crypto_info;
 	struct tls12_crypto_info_aes_gcm_128 *gcm_128_info;
 	struct tls_sw_context *sw_ctx;
@@ -747,9 +746,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx)
 
 	ctx->push_pending_record = tls_sw_push_pending_record;
 
-	memcpy(keyval, gcm_128_info->key, TLS_CIPHER_AES_GCM_128_KEY_SIZE);
-
-	rc = crypto_aead_setkey(sw_ctx->aead_send, keyval,
+	rc = crypto_aead_setkey(sw_ctx->aead_send, gcm_128_info->key,
 				TLS_CIPHER_AES_GCM_128_KEY_SIZE);
 	if (rc)
 		goto free_aead;
-- 
2.13.6


From 412304331ddf0e836a5278192f8dbb3a7da65628 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Wed, 12 Sep 2018 17:44:42 +0200
Subject: [PATCH 12/13] tls: zero the crypto information from tls_context
 before freeing

[ Upstream commit 86029d10af18381814881d6cce2dd6872163b59f ]

This contains key material in crypto_send_aes_gcm_128 and
crypto_recv_aes_gcm_128.

Introduce union tls_crypto_context, and replace the two identical
unions directly embedded in struct tls_context with it. We can then
use this union to clean up the memory in the new tls_ctx_free()
function.

Fixes: 3c4d7559159b ("tls: kernel TLS support")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h  | 14 ++++++++------
 net/tls/tls_main.c | 15 ++++++++++++---
 net/tls/tls_sw.c   |  2 +-
 3 files changed, 21 insertions(+), 10 deletions(-)

diff --git a/include/net/tls.h b/include/net/tls.h
index 48940a883d9a..86ed3dd80fe7 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -79,11 +79,13 @@ enum {
 	TLS_PENDING_CLOSED_RECORD
 };
 
+union tls_crypto_context {
+	struct tls_crypto_info info;
+	struct tls12_crypto_info_aes_gcm_128 aes_gcm_128;
+};
+
 struct tls_context {
-	union {
-		struct tls_crypto_info crypto_send;
-		struct tls12_crypto_info_aes_gcm_128 crypto_send_aes_gcm_128;
-	};
+	union tls_crypto_context crypto_send;
 
 	void *priv_ctx;
 
@@ -208,8 +210,8 @@ static inline void tls_fill_prepend(struct tls_context *ctx,
 	 * size KTLS_DTLS_HEADER_SIZE + KTLS_DTLS_NONCE_EXPLICIT_SIZE
 	 */
 	buf[0] = record_type;
-	buf[1] = TLS_VERSION_MINOR(ctx->crypto_send.version);
-	buf[2] = TLS_VERSION_MAJOR(ctx->crypto_send.version);
+	buf[1] = TLS_VERSION_MINOR(ctx->crypto_send.info.version);
+	buf[2] = TLS_VERSION_MAJOR(ctx->crypto_send.info.version);
 	/* we can use IV for nonce explicit according to spec */
 	buf[3] = pkt_len >> 8;
 	buf[4] = pkt_len & 0xFF;
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 055b9992d8c7..a66c6a30669c 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -218,6 +218,15 @@ static void tls_write_space(struct sock *sk)
 	ctx->sk_write_space(sk);
 }
 
+static void tls_ctx_free(struct tls_context *ctx)
+{
+	if (!ctx)
+		return;
+
+	memzero_explicit(&ctx->crypto_send, sizeof(ctx->crypto_send));
+	kfree(ctx);
+}
+
 static void tls_sk_proto_close(struct sock *sk, long timeout)
 {
 	struct tls_context *ctx = tls_get_ctx(sk);
@@ -246,7 +255,7 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
 	kfree(ctx->iv);
 
 	sk_proto_close = ctx->sk_proto_close;
-	kfree(ctx);
+	tls_ctx_free(ctx);
 
 	release_sock(sk);
 	sk_proto_close(sk, timeout);
@@ -274,7 +283,7 @@ static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval,
 	}
 
 	/* get user crypto info */
-	crypto_info = &ctx->crypto_send;
+	crypto_info = &ctx->crypto_send.info;
 
 	if (!TLS_CRYPTO_INFO_READY(crypto_info)) {
 		rc = -EBUSY;
@@ -371,7 +380,7 @@ static int do_tls_setsockopt_tx(struct sock *sk, char __user *optval,
 	}
 
 	/* get user crypto info */
-	crypto_info = &ctx->crypto_send;
+	crypto_info = &ctx->crypto_send.info;
 
 	/* Currently we don't support set crypto info more than one time */
 	if (TLS_CRYPTO_INFO_READY(crypto_info)) {
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 3157a52b4867..b7abbef52c90 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -681,7 +681,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx)
 	ctx->priv_ctx = (struct tls_offload_context *)sw_ctx;
 	ctx->free_resources = tls_sw_free_resources;
 
-	crypto_info = &ctx->crypto_send;
+	crypto_info = &ctx->crypto_send.info;
 	switch (crypto_info->cipher_type) {
 	case TLS_CIPHER_AES_GCM_128: {
 		nonce_size = TLS_CIPHER_AES_GCM_128_IV_SIZE;
-- 
2.13.6


From 2cbe03852102db350a4c6c436b231765d7cf6f91 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Wed, 12 Sep 2018 17:44:43 +0200
Subject: [PATCH 13/13] tls: clear key material from kernel memory when
 do_tls_setsockopt_conf fails

[ Upstream commit c844eb46b7d43c2cf760169df5ae1d5b033af338 ]

Fixes: 3c4d7559159b ("tls: kernel TLS support")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index a66c6a30669c..efa2cdba99d3 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -425,7 +425,7 @@ static int do_tls_setsockopt_tx(struct sock *sk, char __user *optval,
 	goto out;
 
 err_crypto_info:
-	memset(crypto_info, 0, sizeof(*crypto_info));
+	memzero_explicit(crypto_info, sizeof(union tls_crypto_context));
 out:
 	return rc;
 }
-- 
2.13.6


[-- Attachment #3: net_418.mbox --]
[-- Type: Application/Octet-Stream, Size: 66853 bytes --]

From adc36c085954e35dae71e53bcfe1a9d949de962f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@toke.dk>
Date: Thu, 13 Sep 2018 16:43:07 +0200
Subject: [PATCH 01/22] gso_segment: Reset skb->mac_len after modifying network
 header
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit c56cae23c6b167acc68043c683c4573b80cbcc2c ]

When splitting a GSO segment that consists of encapsulated packets, the
skb->mac_len of the segments can end up being set wrong, causing packet
drops in particular when using act_mirred and ifb interfaces in
combination with a qdisc that splits GSO packets.

This happens because at the time skb_segment() is called, network_header
will point to the inner header, throwing off the calculation in
skb_reset_mac_len(). The network_header is subsequently adjust by the
outer IP gso_segment handlers, but they don't set the mac_len.

Fix this by adding skb_reset_mac_len() calls to both the IPv4 and IPv6
gso_segment handlers, after they modify the network_header.

Many thanks to Eric Dumazet for his help in identifying the cause of
the bug.

Acked-by: Dave Taht <dave.taht@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/af_inet.c     | 1 +
 net/ipv6/ip6_offload.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index b403499fdabe..0c43b050dac7 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1377,6 +1377,7 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 		if (encap)
 			skb_reset_inner_headers(skb);
 		skb->network_header = (u8 *)iph - skb->head;
+		skb_reset_mac_len(skb);
 	} while ((skb = skb->next));
 
 out:
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 5b3f2f89ef41..c6b75e96868c 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -115,6 +115,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 			payload_len = skb->len - nhoff - sizeof(*ipv6h);
 		ipv6h->payload_len = htons(payload_len);
 		skb->network_header = (u8 *)ipv6h - skb->head;
+		skb_reset_mac_len(skb);
 
 		if (udpfrag) {
 			int err = ip6_find_1stfragopt(skb, &prevhdr);
-- 
2.13.6


From 8c3065467e3e83bfa5681d1498cbd26c38fbf39a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 14 Sep 2018 12:02:31 -0700
Subject: [PATCH 02/22] ipv6: fix possible use-after-free in ip6_xmit()

[ Upstream commit bbd6528d28c1b8e80832b3b018ec402b6f5c3215 ]

In the unlikely case ip6_xmit() has to call skb_realloc_headroom(),
we need to call skb_set_owner_w() before consuming original skb,
otherwise we risk a use-after-free.

Bring IPv6 in line with what we do in IPv4 to fix this.

Fixes: 1da177e4c3f41 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_output.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 3168847c30d1..4f607aace43c 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -219,12 +219,10 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 				kfree_skb(skb);
 				return -ENOBUFS;
 			}
+			if (skb->sk)
+				skb_set_owner_w(skb2, skb->sk);
 			consume_skb(skb);
 			skb = skb2;
-			/* skb_set_owner_w() changes sk->sk_wmem_alloc atomically,
-			 * it is safe to call in our context (socket lock not held)
-			 */
-			skb_set_owner_w(skb, (struct sock *)sk);
 		}
 		if (opt->opt_flen)
 			ipv6_push_frag_opts(skb, opt, &proto);
-- 
2.13.6


From f9a2ee9e2fcf43a059c6598bd09e4ec4fa5d2d7b Mon Sep 17 00:00:00 2001
From: Willy Tarreau <w@1wt.eu>
Date: Wed, 12 Sep 2018 07:36:35 +0200
Subject: [PATCH 03/22] net/appletalk: fix minor pointer leak to userspace in
 SIOCFINDIPDDPRT

[ Upstream commit 9824dfae5741275473a23a7ed5756c7b6efacc9d ]

Fields ->dev and ->next of struct ipddp_route may be copied to
userspace on the SIOCFINDIPDDPRT ioctl. This is only accessible
to CAP_NET_ADMIN though. Let's manually copy the relevant fields
instead of using memcpy().

BugLink: http://blog.infosectcbr.com.au/2018/09/linux-kernel-infoleaks.html
Cc: Jann Horn <jannh@google.com>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/appletalk/ipddp.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/appletalk/ipddp.c b/drivers/net/appletalk/ipddp.c
index 9375cef22420..3d27616d9c85 100644
--- a/drivers/net/appletalk/ipddp.c
+++ b/drivers/net/appletalk/ipddp.c
@@ -283,8 +283,12 @@ static int ipddp_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
                 case SIOCFINDIPDDPRT:
 			spin_lock_bh(&ipddp_route_lock);
 			rp = __ipddp_find_route(&rcp);
-			if (rp)
-				memcpy(&rcp2, rp, sizeof(rcp2));
+			if (rp) {
+				memset(&rcp2, 0, sizeof(rcp2));
+				rcp2.ip    = rp->ip;
+				rcp2.at    = rp->at;
+				rcp2.flags = rp->flags;
+			}
 			spin_unlock_bh(&ipddp_route_lock);
 
 			if (rp) {
-- 
2.13.6


From 84db30b4f157420f537216c4ccd3afcdffca7a2e Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Fri, 14 Sep 2018 17:39:53 +0100
Subject: [PATCH 04/22] net: hp100: fix always-true check for link up state

[ Upstream commit a7f38002fb69b44f8fc622ecb838665d0b8666af ]

The operation ~(p100_inb(VG_LAN_CFG_1) & HP100_LINK_UP) returns a value
that is always non-zero and hence the wait for the link to drop always
terminates prematurely.  Fix this by using a logical not operator instead
of a bitwise complement.  This issue has been in the driver since
pre-2.6.12-rc2.

Detected by CoverityScan, CID#114157 ("Logical vs. bitwise operator")

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hp/hp100.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hp/hp100.c b/drivers/net/ethernet/hp/hp100.c
index c8c7ad2eff77..9b5a68b65432 100644
--- a/drivers/net/ethernet/hp/hp100.c
+++ b/drivers/net/ethernet/hp/hp100.c
@@ -2634,7 +2634,7 @@ static int hp100_login_to_vg_hub(struct net_device *dev, u_short force_relogin)
 		/* Wait for link to drop */
 		time = jiffies + (HZ / 10);
 		do {
-			if (~(hp100_inb(VG_LAN_CFG_1) & HP100_LINK_UP_ST))
+			if (!(hp100_inb(VG_LAN_CFG_1) & HP100_LINK_UP_ST))
 				break;
 			if (!in_interrupt())
 				schedule_timeout_interruptible(1);
-- 
2.13.6


From ff6cda4991ffe45970786e0eb90b88ffa3bcd394 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Fri, 14 Sep 2018 16:28:05 +0200
Subject: [PATCH 05/22] pppoe: fix reception of frames with no mac header

[ Upstream commit 8540827ebac6b654ab2f69c8fbce9e4fbd6304a0 ]

pppoe_rcv() needs to look back at the Ethernet header in order to
lookup the PPPoE session. Therefore we need to ensure that the mac
header is big enough to contain an Ethernet header. Otherwise
eth_hdr(skb)->h_source might access invalid data.

==================================================================
BUG: KMSAN: uninit-value in __get_item drivers/net/ppp/pppoe.c:172 [inline]
BUG: KMSAN: uninit-value in get_item drivers/net/ppp/pppoe.c:236 [inline]
BUG: KMSAN: uninit-value in pppoe_rcv+0xcef/0x10e0 drivers/net/ppp/pppoe.c:450
CPU: 0 PID: 4543 Comm: syz-executor355 Not tainted 4.16.0+ #87
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google
01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x185/0x1d0 lib/dump_stack.c:53
 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067
 __msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:683
 __get_item drivers/net/ppp/pppoe.c:172 [inline]
 get_item drivers/net/ppp/pppoe.c:236 [inline]
 pppoe_rcv+0xcef/0x10e0 drivers/net/ppp/pppoe.c:450
 __netif_receive_skb_core+0x47df/0x4a90 net/core/dev.c:4562
 __netif_receive_skb net/core/dev.c:4627 [inline]
 netif_receive_skb_internal+0x49d/0x630 net/core/dev.c:4701
 netif_receive_skb+0x230/0x240 net/core/dev.c:4725
 tun_rx_batched drivers/net/tun.c:1555 [inline]
 tun_get_user+0x740f/0x7c60 drivers/net/tun.c:1962
 tun_chr_write_iter+0x1d4/0x330 drivers/net/tun.c:1990
 call_write_iter include/linux/fs.h:1782 [inline]
 new_sync_write fs/read_write.c:469 [inline]
 __vfs_write+0x7fb/0x9f0 fs/read_write.c:482
 vfs_write+0x463/0x8d0 fs/read_write.c:544
 SYSC_write+0x172/0x360 fs/read_write.c:589
 SyS_write+0x55/0x80 fs/read_write.c:581
 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x3d/0xa2
RIP: 0033:0x4447c9
RSP: 002b:00007fff64c8fc28 EFLAGS: 00000297 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00000000004447c9
RDX: 000000000000fd87 RSI: 0000000020000600 RDI: 0000000000000004
RBP: 00000000006cf018 R08: 00007fff64c8fda8 R09: 00007fff00006bda
R10: 0000000000005fe7 R11: 0000000000000297 R12: 00000000004020d0
R13: 0000000000402160 R14: 0000000000000000 R15: 0000000000000000

Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:278 [inline]
 kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:188
 kmsan_kmalloc+0x94/0x100 mm/kmsan/kmsan.c:314
 kmsan_slab_alloc+0x11/0x20 mm/kmsan/kmsan.c:321
 slab_post_alloc_hook mm/slab.h:445 [inline]
 slab_alloc_node mm/slub.c:2737 [inline]
 __kmalloc_node_track_caller+0xaed/0x11c0 mm/slub.c:4369
 __kmalloc_reserve net/core/skbuff.c:138 [inline]
 __alloc_skb+0x2cf/0x9f0 net/core/skbuff.c:206
 alloc_skb include/linux/skbuff.h:984 [inline]
 alloc_skb_with_frags+0x1d4/0xb20 net/core/skbuff.c:5234
 sock_alloc_send_pskb+0xb56/0x1190 net/core/sock.c:2085
 tun_alloc_skb drivers/net/tun.c:1532 [inline]
 tun_get_user+0x2242/0x7c60 drivers/net/tun.c:1829
 tun_chr_write_iter+0x1d4/0x330 drivers/net/tun.c:1990
 call_write_iter include/linux/fs.h:1782 [inline]
 new_sync_write fs/read_write.c:469 [inline]
 __vfs_write+0x7fb/0x9f0 fs/read_write.c:482
 vfs_write+0x463/0x8d0 fs/read_write.c:544
 SYSC_write+0x172/0x360 fs/read_write.c:589
 SyS_write+0x55/0x80 fs/read_write.c:581
 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x3d/0xa2
==================================================================

Fixes: 224cf5ad14c0 ("ppp: Move the PPP drivers")
Reported-by: syzbot+f5f6080811c849739212@syzkaller.appspotmail.com
Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pppoe.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index ce61231e96ea..62dc564b251d 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -429,6 +429,9 @@ static int pppoe_rcv(struct sk_buff *skb, struct net_device *dev,
 	if (!skb)
 		goto out;
 
+	if (skb_mac_header_len(skb) < ETH_HLEN)
+		goto drop;
+
 	if (!pskb_may_pull(skb, sizeof(struct pppoe_hdr)))
 		goto drop;
 
-- 
2.13.6


From 84eb65b6f83882fcfcc1ecaaf21702f18c0e0247 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Mon, 17 Sep 2018 22:00:24 +0200
Subject: [PATCH 06/22] qmi_wwan: set DTR for modems in forced USB2 mode
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 922005c7f50e7f4b2a6dbc182e9c575b4f92396b ]

Recent firmware revisions have added the ability to force
these modems to USB2 mode, hiding their SuperSpeed
capabilities from the host.  The driver has been using the
SuperSpeed capability, as shown by the bcdUSB field of the
device descriptor, to detect the need to enable the DTR
quirk.  This method fails when the modems are forced to
USB2 mode by the modem firmware.

Fix by unconditionally enabling the DTR quirk for the
affected device IDs.

Reported-by: Fred Veldini <fred.veldini@gmail.com>
Reported-by: Deshu Wen <dwen@sierrawireless.com>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Reported-by: Fred Veldini <fred.veldini@gmail.com>
Reported-by: Deshu Wen <dwen@sierrawireless.com>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index cb0cc30c3d6a..1e95d37c6e27 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1206,13 +1206,13 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1199, 0x9061, 8)},	/* Sierra Wireless Modem */
 	{QMI_FIXED_INTF(0x1199, 0x9063, 8)},	/* Sierra Wireless EM7305 */
 	{QMI_FIXED_INTF(0x1199, 0x9063, 10)},	/* Sierra Wireless EM7305 */
-	{QMI_FIXED_INTF(0x1199, 0x9071, 8)},	/* Sierra Wireless MC74xx */
-	{QMI_FIXED_INTF(0x1199, 0x9071, 10)},	/* Sierra Wireless MC74xx */
-	{QMI_FIXED_INTF(0x1199, 0x9079, 8)},	/* Sierra Wireless EM74xx */
-	{QMI_FIXED_INTF(0x1199, 0x9079, 10)},	/* Sierra Wireless EM74xx */
-	{QMI_FIXED_INTF(0x1199, 0x907b, 8)},	/* Sierra Wireless EM74xx */
-	{QMI_FIXED_INTF(0x1199, 0x907b, 10)},	/* Sierra Wireless EM74xx */
-	{QMI_FIXED_INTF(0x1199, 0x9091, 8)},	/* Sierra Wireless EM7565 */
+	{QMI_QUIRK_SET_DTR(0x1199, 0x9071, 8)},	/* Sierra Wireless MC74xx */
+	{QMI_QUIRK_SET_DTR(0x1199, 0x9071, 10)},/* Sierra Wireless MC74xx */
+	{QMI_QUIRK_SET_DTR(0x1199, 0x9079, 8)},	/* Sierra Wireless EM74xx */
+	{QMI_QUIRK_SET_DTR(0x1199, 0x9079, 10)},/* Sierra Wireless EM74xx */
+	{QMI_QUIRK_SET_DTR(0x1199, 0x907b, 8)},	/* Sierra Wireless EM74xx */
+	{QMI_QUIRK_SET_DTR(0x1199, 0x907b, 10)},/* Sierra Wireless EM74xx */
+	{QMI_QUIRK_SET_DTR(0x1199, 0x9091, 8)},	/* Sierra Wireless EM7565 */
 	{QMI_FIXED_INTF(0x1bbb, 0x011e, 4)},	/* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */
 	{QMI_FIXED_INTF(0x1bbb, 0x0203, 2)},	/* Alcatel L800MA */
 	{QMI_FIXED_INTF(0x2357, 0x0201, 4)},	/* TP-LINK HSUPA Modem MA180 */
-- 
2.13.6


From b5c63777af83a0a8da722400f2c84d207edccfba Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 13 Sep 2018 16:27:20 +0200
Subject: [PATCH 07/22] udp4: fix IP_CMSG_CHECKSUM for connected sockets

[ Upstream commit 2b5a921740a55c00223a797d075b9c77c42cb171 ]

commit 2abb7cdc0dc8 ("udp: Add support for doing checksum
unnecessary conversion") left out the early demux path for
connected sockets. As a result IP_CMSG_CHECKSUM gives wrong
values for such socket when GRO is not enabled/available.

This change addresses the issue by moving the csum conversion to a
common helper and using such helper in both the default and the
early demux rx path.

Fixes: 2abb7cdc0dc8 ("udp: Add support for doing checksum unnecessary conversion")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 49 ++++++++++++++++++++++++++-----------------------
 1 file changed, 26 insertions(+), 23 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 24e116ddae79..fed65bc9df86 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2128,6 +2128,28 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh,
 							 inet_compute_pseudo);
 }
 
+/* wrapper for udp_queue_rcv_skb tacking care of csum conversion and
+ * return code conversion for ip layer consumption
+ */
+static int udp_unicast_rcv_skb(struct sock *sk, struct sk_buff *skb,
+			       struct udphdr *uh)
+{
+	int ret;
+
+	if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk))
+		skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
+					 inet_compute_pseudo);
+
+	ret = udp_queue_rcv_skb(sk, skb);
+
+	/* a return value > 0 means to resubmit the input, but
+	 * it wants the return to be -protocol, or 0
+	 */
+	if (ret > 0)
+		return -ret;
+	return 0;
+}
+
 /*
  *	All we need to do is get the socket, and then do a checksum.
  */
@@ -2174,14 +2196,9 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 		if (unlikely(sk->sk_rx_dst != dst))
 			udp_sk_rx_dst_set(sk, dst);
 
-		ret = udp_queue_rcv_skb(sk, skb);
+		ret = udp_unicast_rcv_skb(sk, skb, uh);
 		sock_put(sk);
-		/* a return value > 0 means to resubmit the input, but
-		 * it wants the return to be -protocol, or 0
-		 */
-		if (ret > 0)
-			return -ret;
-		return 0;
+		return ret;
 	}
 
 	if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST))
@@ -2189,22 +2206,8 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 						saddr, daddr, udptable, proto);
 
 	sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
-	if (sk) {
-		int ret;
-
-		if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk))
-			skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
-						 inet_compute_pseudo);
-
-		ret = udp_queue_rcv_skb(sk, skb);
-
-		/* a return value > 0 means to resubmit the input, but
-		 * it wants the return to be -protocol, or 0
-		 */
-		if (ret > 0)
-			return -ret;
-		return 0;
-	}
+	if (sk)
+		return udp_unicast_rcv_skb(sk, skb, uh);
 
 	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
 		goto drop;
-- 
2.13.6


From 760568ff611db6c594c3ed1db69a05e2c913f95e Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Wed, 12 Sep 2018 17:44:41 +0200
Subject: [PATCH 08/22] tls: don't copy the key out of
 tls12_crypto_info_aes_gcm_128

[ Upstream commit 7cba09c6d5bc73ebbd25a353742d9ddb7a713b95 ]

There's no need to copy the key to an on-stack buffer before calling
crypto_aead_setkey().

Fixes: 3c4d7559159b ("tls: kernel TLS support")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 1f3d9789af30..131b6d282a1d 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1056,7 +1056,6 @@ void tls_sw_free_resources_rx(struct sock *sk)
 
 int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 {
-	char keyval[TLS_CIPHER_AES_GCM_128_KEY_SIZE];
 	struct tls_crypto_info *crypto_info;
 	struct tls12_crypto_info_aes_gcm_128 *gcm_128_info;
 	struct tls_sw_context_tx *sw_ctx_tx = NULL;
@@ -1176,9 +1175,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 
 	ctx->push_pending_record = tls_sw_push_pending_record;
 
-	memcpy(keyval, gcm_128_info->key, TLS_CIPHER_AES_GCM_128_KEY_SIZE);
-
-	rc = crypto_aead_setkey(*aead, keyval,
+	rc = crypto_aead_setkey(*aead, gcm_128_info->key,
 				TLS_CIPHER_AES_GCM_128_KEY_SIZE);
 	if (rc)
 		goto free_aead;
-- 
2.13.6


From 1a999be6ded7d5361186f56fdfea9ed1f2e4028b Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Wed, 12 Sep 2018 17:44:42 +0200
Subject: [PATCH 09/22] tls: zero the crypto information from tls_context
 before freeing

[ Upstream commit 86029d10af18381814881d6cce2dd6872163b59f ]

This contains key material in crypto_send_aes_gcm_128 and
crypto_recv_aes_gcm_128.

Introduce union tls_crypto_context, and replace the two identical
unions directly embedded in struct tls_context with it. We can then
use this union to clean up the memory in the new tls_ctx_free()
function.

Fixes: 3c4d7559159b ("tls: kernel TLS support")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h             | 19 +++++++++----------
 net/tls/tls_device.c          |  4 ++--
 net/tls/tls_device_fallback.c |  2 +-
 net/tls/tls_main.c            | 20 +++++++++++++++-----
 net/tls/tls_sw.c              |  8 ++++----
 5 files changed, 31 insertions(+), 22 deletions(-)

diff --git a/include/net/tls.h b/include/net/tls.h
index 70c273777fe9..32b71e5b1290 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -165,15 +165,14 @@ struct cipher_context {
 	char *rec_seq;
 };
 
+union tls_crypto_context {
+	struct tls_crypto_info info;
+	struct tls12_crypto_info_aes_gcm_128 aes_gcm_128;
+};
+
 struct tls_context {
-	union {
-		struct tls_crypto_info crypto_send;
-		struct tls12_crypto_info_aes_gcm_128 crypto_send_aes_gcm_128;
-	};
-	union {
-		struct tls_crypto_info crypto_recv;
-		struct tls12_crypto_info_aes_gcm_128 crypto_recv_aes_gcm_128;
-	};
+	union tls_crypto_context crypto_send;
+	union tls_crypto_context crypto_recv;
 
 	struct list_head list;
 	struct net_device *netdev;
@@ -337,8 +336,8 @@ static inline void tls_fill_prepend(struct tls_context *ctx,
 	 * size KTLS_DTLS_HEADER_SIZE + KTLS_DTLS_NONCE_EXPLICIT_SIZE
 	 */
 	buf[0] = record_type;
-	buf[1] = TLS_VERSION_MINOR(ctx->crypto_send.version);
-	buf[2] = TLS_VERSION_MAJOR(ctx->crypto_send.version);
+	buf[1] = TLS_VERSION_MINOR(ctx->crypto_send.info.version);
+	buf[2] = TLS_VERSION_MAJOR(ctx->crypto_send.info.version);
 	/* we can use IV for nonce explicit according to spec */
 	buf[3] = pkt_len >> 8;
 	buf[4] = pkt_len & 0xFF;
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index a7a8f8e20ff3..9bd0286d5407 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -552,7 +552,7 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx)
 		goto free_marker_record;
 	}
 
-	crypto_info = &ctx->crypto_send;
+	crypto_info = &ctx->crypto_send.info;
 	switch (crypto_info->cipher_type) {
 	case TLS_CIPHER_AES_GCM_128:
 		nonce_size = TLS_CIPHER_AES_GCM_128_IV_SIZE;
@@ -650,7 +650,7 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx)
 
 	ctx->priv_ctx_tx = offload_ctx;
 	rc = netdev->tlsdev_ops->tls_dev_add(netdev, sk, TLS_OFFLOAD_CTX_DIR_TX,
-					     &ctx->crypto_send,
+					     &ctx->crypto_send.info,
 					     tcp_sk(sk)->write_seq);
 	if (rc)
 		goto release_netdev;
diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c
index 748914abdb60..72143679d3d6 100644
--- a/net/tls/tls_device_fallback.c
+++ b/net/tls/tls_device_fallback.c
@@ -320,7 +320,7 @@ static struct sk_buff *tls_enc_skb(struct tls_context *tls_ctx,
 		goto free_req;
 
 	iv = buf;
-	memcpy(iv, tls_ctx->crypto_send_aes_gcm_128.salt,
+	memcpy(iv, tls_ctx->crypto_send.aes_gcm_128.salt,
 	       TLS_CIPHER_AES_GCM_128_SALT_SIZE);
 	aad = buf + TLS_CIPHER_AES_GCM_128_SALT_SIZE +
 	      TLS_CIPHER_AES_GCM_128_IV_SIZE;
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 45188d920013..4e28210e0343 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -245,6 +245,16 @@ static void tls_write_space(struct sock *sk)
 	ctx->sk_write_space(sk);
 }
 
+static void tls_ctx_free(struct tls_context *ctx)
+{
+	if (!ctx)
+		return;
+
+	memzero_explicit(&ctx->crypto_send, sizeof(ctx->crypto_send));
+	memzero_explicit(&ctx->crypto_recv, sizeof(ctx->crypto_recv));
+	kfree(ctx);
+}
+
 static void tls_sk_proto_close(struct sock *sk, long timeout)
 {
 	struct tls_context *ctx = tls_get_ctx(sk);
@@ -295,7 +305,7 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
 #else
 	{
 #endif
-		kfree(ctx);
+		tls_ctx_free(ctx);
 		ctx = NULL;
 	}
 
@@ -306,7 +316,7 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
 	 * for sk->sk_prot->unhash [tls_hw_unhash]
 	 */
 	if (free_ctx)
-		kfree(ctx);
+		tls_ctx_free(ctx);
 }
 
 static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval,
@@ -331,7 +341,7 @@ static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval,
 	}
 
 	/* get user crypto info */
-	crypto_info = &ctx->crypto_send;
+	crypto_info = &ctx->crypto_send.info;
 
 	if (!TLS_CRYPTO_INFO_READY(crypto_info)) {
 		rc = -EBUSY;
@@ -418,9 +428,9 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval,
 	}
 
 	if (tx)
-		crypto_info = &ctx->crypto_send;
+		crypto_info = &ctx->crypto_send.info;
 	else
-		crypto_info = &ctx->crypto_recv;
+		crypto_info = &ctx->crypto_recv.info;
 
 	/* Currently we don't support set crypto info more than one time */
 	if (TLS_CRYPTO_INFO_READY(crypto_info)) {
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 131b6d282a1d..26b95eb52feb 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -981,8 +981,8 @@ static int tls_read_size(struct strparser *strp, struct sk_buff *skb)
 		goto read_failure;
 	}
 
-	if (header[1] != TLS_VERSION_MINOR(tls_ctx->crypto_recv.version) ||
-	    header[2] != TLS_VERSION_MAJOR(tls_ctx->crypto_recv.version)) {
+	if (header[1] != TLS_VERSION_MINOR(tls_ctx->crypto_recv.info.version) ||
+	    header[2] != TLS_VERSION_MAJOR(tls_ctx->crypto_recv.info.version)) {
 		ret = -EINVAL;
 		goto read_failure;
 	}
@@ -1091,11 +1091,11 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 	}
 
 	if (tx) {
-		crypto_info = &ctx->crypto_send;
+		crypto_info = &ctx->crypto_send.info;
 		cctx = &ctx->tx;
 		aead = &sw_ctx_tx->aead_send;
 	} else {
-		crypto_info = &ctx->crypto_recv;
+		crypto_info = &ctx->crypto_recv.info;
 		cctx = &ctx->rx;
 		aead = &sw_ctx_rx->aead_recv;
 	}
-- 
2.13.6


From 706ecaafe76d3a1d0c448a6521d58e7579a9d156 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Wed, 12 Sep 2018 17:44:43 +0200
Subject: [PATCH 10/22] tls: clear key material from kernel memory when
 do_tls_setsockopt_conf fails

[ Upstream commit c844eb46b7d43c2cf760169df5ae1d5b033af338 ]

Fixes: 3c4d7559159b ("tls: kernel TLS support")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 4e28210e0343..2ccf194c3ebb 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -502,7 +502,7 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval,
 	goto out;
 
 err_crypto_info:
-	memset(crypto_info, 0, sizeof(*crypto_info));
+	memzero_explicit(crypto_info, sizeof(union tls_crypto_context));
 out:
 	return rc;
 }
-- 
2.13.6


From 002fc177e1d2eef217849a14f5e24efc15ce4e5c Mon Sep 17 00:00:00 2001
From: Vasily Khoruzhick <vasilykh@arista.com>
Date: Thu, 13 Sep 2018 11:12:03 -0700
Subject: [PATCH 11/22] neighbour: confirm neigh entries when ARP packet is
 received

[ Upstream commit f0e0d04413fcce9bc76388839099aee93cd0d33b ]

Update 'confirmed' timestamp when ARP packet is received. It shouldn't
affect locktime logic and anyway entry can be confirmed by any higher-layer
protocol. Thus it makes sense to confirm it when ARP packet is received.

Fixes: 77d7123342dc ("neighbour: update neigh timestamps iff update is effective")
Signed-off-by: Vasily Khoruzhick <vasilykh@arista.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 8e3fda9e725c..cb01d509d511 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1179,6 +1179,12 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
 		lladdr = neigh->ha;
 	}
 
+	/* Update confirmed timestamp for neighbour entry after we
+	 * received ARP packet even if it doesn't change IP to MAC binding.
+	 */
+	if (new & NUD_CONNECTED)
+		neigh->confirmed = jiffies;
+
 	/* If entry was valid and address is not changed,
 	   do not change entry state, if new one is STALE.
 	 */
@@ -1200,15 +1206,12 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
 		}
 	}
 
-	/* Update timestamps only once we know we will make a change to the
+	/* Update timestamp only once we know we will make a change to the
 	 * neighbour entry. Otherwise we risk to move the locktime window with
 	 * noop updates and ignore relevant ARP updates.
 	 */
-	if (new != old || lladdr != neigh->ha) {
-		if (new & NUD_CONNECTED)
-			neigh->confirmed = jiffies;
+	if (new != old || lladdr != neigh->ha)
 		neigh->updated = jiffies;
-	}
 
 	if (new != old) {
 		neigh_del_timer(neigh);
-- 
2.13.6


From a91abad065cc9be6274ca005a8612f7d21209e98 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 13 Sep 2018 16:27:21 +0200
Subject: [PATCH 12/22] udp6: add missing checks on edumux packet processing

[ Upstream commit eb63f2964dbe36f26deac77d3016791675821ded ]

Currently the UDPv6 early demux rx code path lacks some mandatory
checks, already implemented into the normal RX code path - namely
the checksum conversion and no_check6_rx check.

Similar to the previous commit, we move the common processing to
an UDPv6 specific helper and call it from both edemux code path
and normal code path. In respect to the UDPv4, we need to add an
explicit check for non zero csum according to no_check6_rx value.

Reported-by: Jianlin Shi <jishi@redhat.com>
Suggested-by: Xin Long <lucien.xin@gmail.com>
Fixes: c9f2c1ae123a ("udp6: fix socket leak on early demux")
Fixes: 2abb7cdc0dc8 ("udp: Add support for doing checksum unnecessary conversion")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/udp.c | 65 +++++++++++++++++++++++++++++++++-------------------------
 1 file changed, 37 insertions(+), 28 deletions(-)

diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index e6645cae403e..39d0cab919bb 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -748,6 +748,28 @@ static void udp6_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
 	}
 }
 
+/* wrapper for udp_queue_rcv_skb tacking care of csum conversion and
+ * return code conversion for ip layer consumption
+ */
+static int udp6_unicast_rcv_skb(struct sock *sk, struct sk_buff *skb,
+				struct udphdr *uh)
+{
+	int ret;
+
+	if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk))
+		skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
+					 ip6_compute_pseudo);
+
+	ret = udpv6_queue_rcv_skb(sk, skb);
+
+	/* a return value > 0 means to resubmit the input, but
+	 * it wants the return to be -protocol, or 0
+	 */
+	if (ret > 0)
+		return -ret;
+	return 0;
+}
+
 int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 		   int proto)
 {
@@ -799,13 +821,14 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 		if (unlikely(sk->sk_rx_dst != dst))
 			udp6_sk_rx_dst_set(sk, dst);
 
-		ret = udpv6_queue_rcv_skb(sk, skb);
-		sock_put(sk);
+		if (!uh->check && !udp_sk(sk)->no_check6_rx) {
+			sock_put(sk);
+			goto report_csum_error;
+		}
 
-		/* a return value > 0 means to resubmit the input */
-		if (ret > 0)
-			return ret;
-		return 0;
+		ret = udp6_unicast_rcv_skb(sk, skb, uh);
+		sock_put(sk);
+		return ret;
 	}
 
 	/*
@@ -818,30 +841,13 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	/* Unicast */
 	sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
 	if (sk) {
-		int ret;
-
-		if (!uh->check && !udp_sk(sk)->no_check6_rx) {
-			udp6_csum_zero_error(skb);
-			goto csum_error;
-		}
-
-		if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk))
-			skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
-						 ip6_compute_pseudo);
-
-		ret = udpv6_queue_rcv_skb(sk, skb);
-
-		/* a return value > 0 means to resubmit the input */
-		if (ret > 0)
-			return ret;
-
-		return 0;
+		if (!uh->check && !udp_sk(sk)->no_check6_rx)
+			goto report_csum_error;
+		return udp6_unicast_rcv_skb(sk, skb, uh);
 	}
 
-	if (!uh->check) {
-		udp6_csum_zero_error(skb);
-		goto csum_error;
-	}
+	if (!uh->check)
+		goto report_csum_error;
 
 	if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
 		goto discard;
@@ -862,6 +868,9 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 			    ulen, skb->len,
 			    daddr, ntohs(uh->dest));
 	goto discard;
+
+report_csum_error:
+	udp6_csum_zero_error(skb);
 csum_error:
 	__UDP6_INC_STATS(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE);
 discard:
-- 
2.13.6


From a49c7e9b87454c75c32eaa53d735d9c368460b07 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Fri, 14 Sep 2018 12:03:18 +0200
Subject: [PATCH 13/22] net/sched: act_sample: fix NULL dereference in the data
 path

[ Upstream commit 34043d250f51368f214aed7f54c2dc29c819a8c7 ]

Matteo reported the following splat, testing the datapath of TC 'sample':

 BUG: KASAN: null-ptr-deref in tcf_sample_act+0xc4/0x310
 Read of size 8 at addr 0000000000000000 by task nc/433

 CPU: 0 PID: 433 Comm: nc Not tainted 4.19.0-rc3-kvm #17
 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS ?-20180531_142017-buildhw-08.phx2.fedoraproject.org-1.fc28 04/01/2014
 Call Trace:
  kasan_report.cold.6+0x6c/0x2fa
  tcf_sample_act+0xc4/0x310
  ? dev_hard_start_xmit+0x117/0x180
  tcf_action_exec+0xa3/0x160
  tcf_classify+0xdd/0x1d0
  htb_enqueue+0x18e/0x6b0
  ? deref_stack_reg+0x7a/0xb0
  ? htb_delete+0x4b0/0x4b0
  ? unwind_next_frame+0x819/0x8f0
  ? entry_SYSCALL_64_after_hwframe+0x44/0xa9
  __dev_queue_xmit+0x722/0xca0
  ? unwind_get_return_address_ptr+0x50/0x50
  ? netdev_pick_tx+0xe0/0xe0
  ? save_stack+0x8c/0xb0
  ? kasan_kmalloc+0xbe/0xd0
  ? __kmalloc_track_caller+0xe4/0x1c0
  ? __kmalloc_reserve.isra.45+0x24/0x70
  ? __alloc_skb+0xdd/0x2e0
  ? sk_stream_alloc_skb+0x91/0x3b0
  ? tcp_sendmsg_locked+0x71b/0x15a0
  ? tcp_sendmsg+0x22/0x40
  ? __sys_sendto+0x1b0/0x250
  ? __x64_sys_sendto+0x6f/0x80
  ? do_syscall_64+0x5d/0x150
  ? entry_SYSCALL_64_after_hwframe+0x44/0xa9
  ? __sys_sendto+0x1b0/0x250
  ? __x64_sys_sendto+0x6f/0x80
  ? do_syscall_64+0x5d/0x150
  ? entry_SYSCALL_64_after_hwframe+0x44/0xa9
  ip_finish_output2+0x495/0x590
  ? ip_copy_metadata+0x2e0/0x2e0
  ? skb_gso_validate_network_len+0x6f/0x110
  ? ip_finish_output+0x174/0x280
  __tcp_transmit_skb+0xb17/0x12b0
  ? __tcp_select_window+0x380/0x380
  tcp_write_xmit+0x913/0x1de0
  ? __sk_mem_schedule+0x50/0x80
  tcp_sendmsg_locked+0x49d/0x15a0
  ? tcp_rcv_established+0x8da/0xa30
  ? tcp_set_state+0x220/0x220
  ? clear_user+0x1f/0x50
  ? iov_iter_zero+0x1ae/0x590
  ? __fget_light+0xa0/0xe0
  tcp_sendmsg+0x22/0x40
  __sys_sendto+0x1b0/0x250
  ? __ia32_sys_getpeername+0x40/0x40
  ? _copy_to_user+0x58/0x70
  ? poll_select_copy_remaining+0x176/0x200
  ? __pollwait+0x1c0/0x1c0
  ? ktime_get_ts64+0x11f/0x140
  ? kern_select+0x108/0x150
  ? core_sys_select+0x360/0x360
  ? vfs_read+0x127/0x150
  ? kernel_write+0x90/0x90
  __x64_sys_sendto+0x6f/0x80
  do_syscall_64+0x5d/0x150
  entry_SYSCALL_64_after_hwframe+0x44/0xa9
 RIP: 0033:0x7fefef2b129d
 Code: ff ff ff ff eb b6 0f 1f 80 00 00 00 00 48 8d 05 51 37 0c 00 41 89 ca 8b 00 85 c0 75 20 45 31 c9 45 31 c0 b8 2c 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 6b f3 c3 66 0f 1f 84 00 00 00 00 00 41 56 41
 RSP: 002b:00007fff2f5350c8 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
 RAX: ffffffffffffffda RBX: 000056118d60c120 RCX: 00007fefef2b129d
 RDX: 0000000000002000 RSI: 000056118d629320 RDI: 0000000000000003
 RBP: 000056118d530370 R08: 0000000000000000 R09: 0000000000000000
 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000002000
 R13: 000056118d5c2a10 R14: 000056118d5c2a10 R15: 000056118d5303b8

tcf_sample_act() tried to update its per-cpu stats, but tcf_sample_init()
forgot to allocate them, because tcf_idr_create() was called with a wrong
value of 'cpustats'. Setting it to true proved to fix the reported crash.

Reported-by: Matteo Croce <mcroce@redhat.com>
Fixes: 65a206c01e8e ("net/sched: Change act_api and act_xxx modules to use IDR")
Fixes: 5c5670fae430 ("net/sched: Introduce sample tc action")
Tested-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_sample.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 5db358497c9e..e0e334a3a6e1 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -64,7 +64,7 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, parm->index, est, a,
-				     &act_sample_ops, bind, false);
+				     &act_sample_ops, bind, true);
 		if (ret)
 			return ret;
 		ret = ACT_P_CREATED;
-- 
2.13.6


From ced79c9e7c00fbaf19849696ff55c4f33cb38627 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Thu, 13 Sep 2018 08:03:43 -0700
Subject: [PATCH 14/22] hv_netvsc: fix schedule in RCU context

[ Upstream commit 018349d70f28a78d5343b3660cb66e1667005f8a ]

When netvsc device is removed it can call reschedule in RCU context.
This happens because canceling the subchannel setup work could (in theory)
cause a reschedule when manipulating the timer.

To reproduce, run with lockdep enabled kernel and unbind
a network device from hv_netvsc (via sysfs).

[  160.682011] WARNING: suspicious RCU usage
[  160.707466] 4.19.0-rc3-uio+ #2 Not tainted
[  160.709937] -----------------------------
[  160.712352] ./include/linux/rcupdate.h:302 Illegal context switch in RCU read-side critical section!
[  160.723691]
[  160.723691] other info that might help us debug this:
[  160.723691]
[  160.730955]
[  160.730955] rcu_scheduler_active = 2, debug_locks = 1
[  160.762813] 5 locks held by rebind-eth.sh/1812:
[  160.766851]  #0: 000000008befa37a (sb_writers#6){.+.+}, at: vfs_write+0x184/0x1b0
[  160.773416]  #1: 00000000b097f236 (&of->mutex){+.+.}, at: kernfs_fop_write+0xe2/0x1a0
[  160.783766]  #2: 0000000041ee6889 (kn->count#3){++++}, at: kernfs_fop_write+0xeb/0x1a0
[  160.787465]  #3: 0000000056d92a74 (&dev->mutex){....}, at: device_release_driver_internal+0x39/0x250
[  160.816987]  #4: 0000000030f6031e (rcu_read_lock){....}, at: netvsc_remove+0x1e/0x250 [hv_netvsc]
[  160.828629]
[  160.828629] stack backtrace:
[  160.831966] CPU: 1 PID: 1812 Comm: rebind-eth.sh Not tainted 4.19.0-rc3-uio+ #2
[  160.832952] Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS Hyper-V UEFI Release v1.0 11/26/2012
[  160.832952] Call Trace:
[  160.832952]  dump_stack+0x85/0xcb
[  160.832952]  ___might_sleep+0x1a3/0x240
[  160.832952]  __flush_work+0x57/0x2e0
[  160.832952]  ? __mutex_lock+0x83/0x990
[  160.832952]  ? __kernfs_remove+0x24f/0x2e0
[  160.832952]  ? __kernfs_remove+0x1b2/0x2e0
[  160.832952]  ? mark_held_locks+0x50/0x80
[  160.832952]  ? get_work_pool+0x90/0x90
[  160.832952]  __cancel_work_timer+0x13c/0x1e0
[  160.832952]  ? netvsc_remove+0x1e/0x250 [hv_netvsc]
[  160.832952]  ? __lock_is_held+0x55/0x90
[  160.832952]  netvsc_remove+0x9a/0x250 [hv_netvsc]
[  160.832952]  vmbus_remove+0x26/0x30
[  160.832952]  device_release_driver_internal+0x18a/0x250
[  160.832952]  unbind_store+0xb4/0x180
[  160.832952]  kernfs_fop_write+0x113/0x1a0
[  160.832952]  __vfs_write+0x36/0x1a0
[  160.832952]  ? rcu_read_lock_sched_held+0x6b/0x80
[  160.832952]  ? rcu_sync_lockdep_assert+0x2e/0x60
[  160.832952]  ? __sb_start_write+0x141/0x1a0
[  160.832952]  ? vfs_write+0x184/0x1b0
[  160.832952]  vfs_write+0xbe/0x1b0
[  160.832952]  ksys_write+0x55/0xc0
[  160.832952]  do_syscall_64+0x60/0x1b0
[  160.832952]  entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  160.832952] RIP: 0033:0x7fe48f4c8154

Resolve this by getting RTNL earlier. This is safe because the subchannel
work queue does trylock on RTNL and will detect the race.

Fixes: 7b2ee50c0cd5 ("hv_netvsc: common detach logic")
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/netvsc_drv.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 6d74cde68163..c0fc30a1f600 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -2172,17 +2172,15 @@ static int netvsc_remove(struct hv_device *dev)
 
 	cancel_delayed_work_sync(&ndev_ctx->dwork);
 
-	rcu_read_lock();
-	nvdev = rcu_dereference(ndev_ctx->nvdev);
-
-	if  (nvdev)
+	rtnl_lock();
+	nvdev = rtnl_dereference(ndev_ctx->nvdev);
+	if (nvdev)
 		cancel_work_sync(&nvdev->subchan_work);
 
 	/*
 	 * Call to the vsc driver to let it know that the device is being
 	 * removed. Also blocks mtu and channel changes.
 	 */
-	rtnl_lock();
 	vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev);
 	if (vf_netdev)
 		netvsc_unregister_vf(vf_netdev);
@@ -2194,7 +2192,6 @@ static int netvsc_remove(struct hv_device *dev)
 	list_del(&ndev_ctx->list);
 
 	rtnl_unlock();
-	rcu_read_unlock();
 
 	hv_set_drvdata(dev, NULL);
 
-- 
2.13.6


From e273e9cf9bac9b9bd6f92d49d3f83f74cf3698eb Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Fri, 14 Sep 2018 23:46:12 +0200
Subject: [PATCH 15/22] net: dsa: mv88e6xxx: Fix ATU Miss Violation

[ Upstream commit ddca24dfcf1bec608668dd44c45d49397b70f520 ]

Fix a cut/paste error and a typo which results in ATU miss violations
not being reported.

Fixes: 0977644c5005 ("net: dsa: mv88e6xxx: Decode ATU problem interrupt")
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/global1.h     | 2 +-
 drivers/net/dsa/mv88e6xxx/global1_atu.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/global1.h b/drivers/net/dsa/mv88e6xxx/global1.h
index 7c791c1da4b9..bef01331266f 100644
--- a/drivers/net/dsa/mv88e6xxx/global1.h
+++ b/drivers/net/dsa/mv88e6xxx/global1.h
@@ -128,7 +128,7 @@
 #define MV88E6XXX_G1_ATU_OP_GET_CLR_VIOLATION		0x7000
 #define MV88E6XXX_G1_ATU_OP_AGE_OUT_VIOLATION		BIT(7)
 #define MV88E6XXX_G1_ATU_OP_MEMBER_VIOLATION		BIT(6)
-#define MV88E6XXX_G1_ATU_OP_MISS_VIOLTATION		BIT(5)
+#define MV88E6XXX_G1_ATU_OP_MISS_VIOLATION		BIT(5)
 #define MV88E6XXX_G1_ATU_OP_FULL_VIOLATION		BIT(4)
 
 /* Offset 0x0C: ATU Data Register */
diff --git a/drivers/net/dsa/mv88e6xxx/global1_atu.c b/drivers/net/dsa/mv88e6xxx/global1_atu.c
index 307410898fc9..5200e4bdce93 100644
--- a/drivers/net/dsa/mv88e6xxx/global1_atu.c
+++ b/drivers/net/dsa/mv88e6xxx/global1_atu.c
@@ -349,7 +349,7 @@ static irqreturn_t mv88e6xxx_g1_atu_prob_irq_thread_fn(int irq, void *dev_id)
 		chip->ports[entry.portvec].atu_member_violation++;
 	}
 
-	if (val & MV88E6XXX_G1_ATU_OP_MEMBER_VIOLATION) {
+	if (val & MV88E6XXX_G1_ATU_OP_MISS_VIOLATION) {
 		dev_err_ratelimited(chip->dev,
 				    "ATU miss violation for %pM portvec %x\n",
 				    entry.mac, entry.portvec);
-- 
2.13.6


From 9f771e857db72a5513cd97233e300be1f4135a22 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 13 Sep 2018 14:40:55 +0200
Subject: [PATCH 16/22] socket: fix struct ifreq size in compat ioctl

[ Upstream commit 1cebf8f143c21eb422cd0f4e27ab2ae366eb4d04 ]

As reported by Reobert O'Callahan, since Viro's commit to kill
dev_ifsioc() we attempt to copy too much data in compat mode,
which may lead to EFAULT when the 32-bit version of struct ifreq
sits at/near the end of a page boundary, and the next page isn't
mapped.

Fix this by passing the approprate compat/non-compat size to copy
and using that, as before the dev_ifsioc() removal. This works
because only the embedded "struct ifmap" has different size, and
this is only used in SIOCGIFMAP/SIOCSIFMAP which has a different
handler. All other parts of the union are naturally compatible.

This fixes https://bugzilla.kernel.org/show_bug.cgi?id=199469.

Fixes: bf4405737f9f ("kill dev_ifsioc()")
Reported-by: Robert O'Callahan <robert@ocallahan.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/socket.c | 22 ++++++++++++++--------
 1 file changed, 14 insertions(+), 8 deletions(-)

diff --git a/net/socket.c b/net/socket.c
index 4ac3b834cce9..d4187ac17d55 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -962,7 +962,8 @@ void dlci_ioctl_set(int (*hook) (unsigned int, void __user *))
 EXPORT_SYMBOL(dlci_ioctl_set);
 
 static long sock_do_ioctl(struct net *net, struct socket *sock,
-				 unsigned int cmd, unsigned long arg)
+			  unsigned int cmd, unsigned long arg,
+			  unsigned int ifreq_size)
 {
 	int err;
 	void __user *argp = (void __user *)arg;
@@ -988,11 +989,11 @@ static long sock_do_ioctl(struct net *net, struct socket *sock,
 	} else {
 		struct ifreq ifr;
 		bool need_copyout;
-		if (copy_from_user(&ifr, argp, sizeof(struct ifreq)))
+		if (copy_from_user(&ifr, argp, ifreq_size))
 			return -EFAULT;
 		err = dev_ioctl(net, cmd, &ifr, &need_copyout);
 		if (!err && need_copyout)
-			if (copy_to_user(argp, &ifr, sizeof(struct ifreq)))
+			if (copy_to_user(argp, &ifr, ifreq_size))
 				return -EFAULT;
 	}
 	return err;
@@ -1091,7 +1092,8 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 			err = open_related_ns(&net->ns, get_net_ns);
 			break;
 		default:
-			err = sock_do_ioctl(net, sock, cmd, arg);
+			err = sock_do_ioctl(net, sock, cmd, arg,
+					    sizeof(struct ifreq));
 			break;
 		}
 	return err;
@@ -2762,7 +2764,8 @@ static int do_siocgstamp(struct net *net, struct socket *sock,
 	int err;
 
 	set_fs(KERNEL_DS);
-	err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv);
+	err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv,
+			    sizeof(struct compat_ifreq));
 	set_fs(old_fs);
 	if (!err)
 		err = compat_put_timeval(&ktv, up);
@@ -2778,7 +2781,8 @@ static int do_siocgstampns(struct net *net, struct socket *sock,
 	int err;
 
 	set_fs(KERNEL_DS);
-	err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts);
+	err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts,
+			    sizeof(struct compat_ifreq));
 	set_fs(old_fs);
 	if (!err)
 		err = compat_put_timespec(&kts, up);
@@ -3084,7 +3088,8 @@ static int routing_ioctl(struct net *net, struct socket *sock,
 	}
 
 	set_fs(KERNEL_DS);
-	ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r);
+	ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r,
+			    sizeof(struct compat_ifreq));
 	set_fs(old_fs);
 
 out:
@@ -3197,7 +3202,8 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
 	case SIOCBONDSETHWADDR:
 	case SIOCBONDCHANGEACTIVE:
 	case SIOCGIFNAME:
-		return sock_do_ioctl(net, sock, cmd, arg);
+		return sock_do_ioctl(net, sock, cmd, arg,
+				     sizeof(struct compat_ifreq));
 	}
 
 	return -ENOIOCTLCMD;
-- 
2.13.6


From 73017263c72d7b8dec0b7adc0b992a84702db445 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 14 Sep 2018 23:00:55 +0200
Subject: [PATCH 17/22] tls: fix currently broken MSG_PEEK behavior

[ Upstream commit 50c6b58a814d86a93c0f6964570f839632854044 ]

In kTLS MSG_PEEK behavior is currently failing, strace example:

  [pid  2430] socket(AF_INET, SOCK_STREAM, IPPROTO_IP) = 3
  [pid  2430] socket(AF_INET, SOCK_STREAM, IPPROTO_IP) = 4
  [pid  2430] bind(4, {sa_family=AF_INET, sin_port=htons(0), sin_addr=inet_addr("0.0.0.0")}, 16) = 0
  [pid  2430] listen(4, 10)               = 0
  [pid  2430] getsockname(4, {sa_family=AF_INET, sin_port=htons(38855), sin_addr=inet_addr("0.0.0.0")}, [16]) = 0
  [pid  2430] connect(3, {sa_family=AF_INET, sin_port=htons(38855), sin_addr=inet_addr("0.0.0.0")}, 16) = 0
  [pid  2430] setsockopt(3, SOL_TCP, 0x1f /* TCP_??? */, [7564404], 4) = 0
  [pid  2430] setsockopt(3, 0x11a /* SOL_?? */, 1, "\3\0033\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0"..., 40) = 0
  [pid  2430] accept(4, {sa_family=AF_INET, sin_port=htons(49636), sin_addr=inet_addr("127.0.0.1")}, [16]) = 5
  [pid  2430] setsockopt(5, SOL_TCP, 0x1f /* TCP_??? */, [7564404], 4) = 0
  [pid  2430] setsockopt(5, 0x11a /* SOL_?? */, 2, "\3\0033\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0"..., 40) = 0
  [pid  2430] close(4)                    = 0
  [pid  2430] sendto(3, "test_read_peek", 14, 0, NULL, 0) = 14
  [pid  2430] sendto(3, "_mult_recs\0", 11, 0, NULL, 0) = 11
  [pid  2430] recvfrom(5, "test_read_peektest_read_peektest"..., 64, MSG_PEEK, NULL, NULL) = 64

As can be seen from strace, there are two TLS records sent,
i) 'test_read_peek' and ii) '_mult_recs\0' where we end up
peeking 'test_read_peektest_read_peektest'. This is clearly
wrong, and what happens is that given peek cannot call into
tls_sw_advance_skb() to unpause strparser and proceed with
the next skb, we end up looping over the current one, copying
the 'test_read_peek' over and over into the user provided
buffer.

Here, we can only peek into the currently held skb (current,
full TLS record) as otherwise we would end up having to hold
all the original skb(s) (depending on the peek depth) in a
separate queue when unpausing strparser to process next
records, minimally intrusive is to return only up to the
current record's size (which likely was what c46234ebb4d1
("tls: RX path for ktls") originally intended as well). Thus,
after patch we properly peek the first record:

  [pid  2046] wait4(2075,  <unfinished ...>
  [pid  2075] socket(AF_INET, SOCK_STREAM, IPPROTO_IP) = 3
  [pid  2075] socket(AF_INET, SOCK_STREAM, IPPROTO_IP) = 4
  [pid  2075] bind(4, {sa_family=AF_INET, sin_port=htons(0), sin_addr=inet_addr("0.0.0.0")}, 16) = 0
  [pid  2075] listen(4, 10)               = 0
  [pid  2075] getsockname(4, {sa_family=AF_INET, sin_port=htons(55115), sin_addr=inet_addr("0.0.0.0")}, [16]) = 0
  [pid  2075] connect(3, {sa_family=AF_INET, sin_port=htons(55115), sin_addr=inet_addr("0.0.0.0")}, 16) = 0
  [pid  2075] setsockopt(3, SOL_TCP, 0x1f /* TCP_??? */, [7564404], 4) = 0
  [pid  2075] setsockopt(3, 0x11a /* SOL_?? */, 1, "\3\0033\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0"..., 40) = 0
  [pid  2075] accept(4, {sa_family=AF_INET, sin_port=htons(45732), sin_addr=inet_addr("127.0.0.1")}, [16]) = 5
  [pid  2075] setsockopt(5, SOL_TCP, 0x1f /* TCP_??? */, [7564404], 4) = 0
  [pid  2075] setsockopt(5, 0x11a /* SOL_?? */, 2, "\3\0033\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0"..., 40) = 0
  [pid  2075] close(4)                    = 0
  [pid  2075] sendto(3, "test_read_peek", 14, 0, NULL, 0) = 14
  [pid  2075] sendto(3, "_mult_recs\0", 11, 0, NULL, 0) = 11
  [pid  2075] recvfrom(5, "test_read_peek", 64, MSG_PEEK, NULL, NULL) = 14

Fixes: c46234ebb4d1 ("tls: RX path for ktls")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 26b95eb52feb..17486c6495aa 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -864,7 +864,15 @@ int tls_sw_recvmsg(struct sock *sk,
 				if (control != TLS_RECORD_TYPE_DATA)
 					goto recv_end;
 			}
+		} else {
+			/* MSG_PEEK right now cannot look beyond current skb
+			 * from strparser, meaning we cannot advance skb here
+			 * and thus unpause strparser since we'd loose original
+			 * one.
+			 */
+			break;
 		}
+
 		/* If we have a new message from strparser, continue now. */
 		if (copied >= target && !ctx->recv_pkt)
 			break;
-- 
2.13.6


From f53dfd3dc09dfea787c5315708e81278de944901 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Fri, 14 Sep 2018 15:41:29 -0400
Subject: [PATCH 18/22] bnxt_en: Fix VF mac address regression.

[ Upstream commit 28ea334bd1657f3c43485b4a8592672fc6835fac ]

The recent commit to always forward the VF MAC address to the PF for
approval may not work if the PF driver or the firmware is older.  This
will cause the VF driver to fail during probe:

  bnxt_en 0000:00:03.0 (unnamed net_device) (uninitialized): hwrm req_type 0xf seq id 0x5 error 0xffff
  bnxt_en 0000:00:03.0 (unnamed net_device) (uninitialized): VF MAC address 00:00:17:02:05:d0 not approved by the PF
  bnxt_en 0000:00:03.0: Unable to initialize mac address.
  bnxt_en: probe of 0000:00:03.0 failed with error -99

We fix it by treating the error as fatal only if the VF MAC address is
locally generated by the VF.

Fixes: 707e7e966026 ("bnxt_en: Always forward VF MAC address to the PF.")
Reported-by: Seth Forshee <seth.forshee@canonical.com>
Reported-by: Siwei Liu <loseweigh@gmail.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c       | 9 +++++++--
 drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c | 9 +++++----
 drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h | 2 +-
 3 files changed, 13 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 4fdf3d33aa59..80b05597c5fe 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -7888,7 +7888,7 @@ static int bnxt_change_mac_addr(struct net_device *dev, void *p)
 	if (ether_addr_equal(addr->sa_data, dev->dev_addr))
 		return 0;
 
-	rc = bnxt_approve_mac(bp, addr->sa_data);
+	rc = bnxt_approve_mac(bp, addr->sa_data, true);
 	if (rc)
 		return rc;
 
@@ -8683,14 +8683,19 @@ static int bnxt_init_mac_addr(struct bnxt *bp)
 	} else {
 #ifdef CONFIG_BNXT_SRIOV
 		struct bnxt_vf_info *vf = &bp->vf;
+		bool strict_approval = true;
 
 		if (is_valid_ether_addr(vf->mac_addr)) {
 			/* overwrite netdev dev_addr with admin VF MAC */
 			memcpy(bp->dev->dev_addr, vf->mac_addr, ETH_ALEN);
+			/* Older PF driver or firmware may not approve this
+			 * correctly.
+			 */
+			strict_approval = false;
 		} else {
 			eth_hw_addr_random(bp->dev);
 		}
-		rc = bnxt_approve_mac(bp, bp->dev->dev_addr);
+		rc = bnxt_approve_mac(bp, bp->dev->dev_addr, strict_approval);
 #endif
 	}
 	return rc;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index 2c77004a022b..24d16d3d33a1 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -1095,7 +1095,7 @@ void bnxt_update_vf_mac(struct bnxt *bp)
 	mutex_unlock(&bp->hwrm_cmd_lock);
 }
 
-int bnxt_approve_mac(struct bnxt *bp, u8 *mac)
+int bnxt_approve_mac(struct bnxt *bp, u8 *mac, bool strict)
 {
 	struct hwrm_func_vf_cfg_input req = {0};
 	int rc = 0;
@@ -1113,12 +1113,13 @@ int bnxt_approve_mac(struct bnxt *bp, u8 *mac)
 	memcpy(req.dflt_mac_addr, mac, ETH_ALEN);
 	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 mac_done:
-	if (rc) {
+	if (rc && strict) {
 		rc = -EADDRNOTAVAIL;
 		netdev_warn(bp->dev, "VF MAC address %pM not approved by the PF\n",
 			    mac);
+		return rc;
 	}
-	return rc;
+	return 0;
 }
 #else
 
@@ -1135,7 +1136,7 @@ void bnxt_update_vf_mac(struct bnxt *bp)
 {
 }
 
-int bnxt_approve_mac(struct bnxt *bp, u8 *mac)
+int bnxt_approve_mac(struct bnxt *bp, u8 *mac, bool strict)
 {
 	return 0;
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h
index e9b20cd19881..2eed9eda1195 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h
@@ -39,5 +39,5 @@ int bnxt_sriov_configure(struct pci_dev *pdev, int num_vfs);
 void bnxt_sriov_disable(struct bnxt *);
 void bnxt_hwrm_exec_fwd_req(struct bnxt *);
 void bnxt_update_vf_mac(struct bnxt *);
-int bnxt_approve_mac(struct bnxt *, u8 *);
+int bnxt_approve_mac(struct bnxt *, u8 *, bool);
 #endif
-- 
2.13.6


From fd8ddf8a6b40e7a6119444d3d7b725d665f319d1 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 11 Sep 2018 14:33:58 +0800
Subject: [PATCH 19/22] ipv6: use rt6_info members when dst is set in
 rt6_fill_node

[ Upstream commit 22d0bd82cc7cec7d9ed4bd5913f3ab65643364be ]

In inet6_rtm_getroute, since Commit 93531c674315 ("net/ipv6: separate
handling of FIB entries from dst based routes"), it has used rt->from
to dump route info instead of rt.

However for some route like cache, some of its information like flags
or gateway is not the same as that of the 'from' one. It caused 'ip
route get' to dump the wrong route information.

In Jianlin's testing, the output information even lost the expiration
time for a pmtu route cache due to the wrong fib6_flags.

So change to use rt6_info members for dst addr, src addr, flags and
gateway when it tries to dump a route entry without fibmatch set.

v1->v2:
  - not use rt6i_prefsrc.
  - also fix the gw dump issue.

Fixes: 93531c674315 ("net/ipv6: separate handling of FIB entries from dst based routes")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 42 ++++++++++++++++++++++++++++++------------
 1 file changed, 30 insertions(+), 12 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 18e00ce1719a..3eed045c65a5 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -4670,20 +4670,31 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 			 int iif, int type, u32 portid, u32 seq,
 			 unsigned int flags)
 {
-	struct rtmsg *rtm;
+	struct rt6_info *rt6 = (struct rt6_info *)dst;
+	struct rt6key *rt6_dst, *rt6_src;
+	u32 *pmetrics, table, rt6_flags;
 	struct nlmsghdr *nlh;
+	struct rtmsg *rtm;
 	long expires = 0;
-	u32 *pmetrics;
-	u32 table;
 
 	nlh = nlmsg_put(skb, portid, seq, type, sizeof(*rtm), flags);
 	if (!nlh)
 		return -EMSGSIZE;
 
+	if (rt6) {
+		rt6_dst = &rt6->rt6i_dst;
+		rt6_src = &rt6->rt6i_src;
+		rt6_flags = rt6->rt6i_flags;
+	} else {
+		rt6_dst = &rt->fib6_dst;
+		rt6_src = &rt->fib6_src;
+		rt6_flags = rt->fib6_flags;
+	}
+
 	rtm = nlmsg_data(nlh);
 	rtm->rtm_family = AF_INET6;
-	rtm->rtm_dst_len = rt->fib6_dst.plen;
-	rtm->rtm_src_len = rt->fib6_src.plen;
+	rtm->rtm_dst_len = rt6_dst->plen;
+	rtm->rtm_src_len = rt6_src->plen;
 	rtm->rtm_tos = 0;
 	if (rt->fib6_table)
 		table = rt->fib6_table->tb6_id;
@@ -4698,7 +4709,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 	rtm->rtm_scope = RT_SCOPE_UNIVERSE;
 	rtm->rtm_protocol = rt->fib6_protocol;
 
-	if (rt->fib6_flags & RTF_CACHE)
+	if (rt6_flags & RTF_CACHE)
 		rtm->rtm_flags |= RTM_F_CLONED;
 
 	if (dest) {
@@ -4706,7 +4717,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 			goto nla_put_failure;
 		rtm->rtm_dst_len = 128;
 	} else if (rtm->rtm_dst_len)
-		if (nla_put_in6_addr(skb, RTA_DST, &rt->fib6_dst.addr))
+		if (nla_put_in6_addr(skb, RTA_DST, &rt6_dst->addr))
 			goto nla_put_failure;
 #ifdef CONFIG_IPV6_SUBTREES
 	if (src) {
@@ -4714,12 +4725,12 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 			goto nla_put_failure;
 		rtm->rtm_src_len = 128;
 	} else if (rtm->rtm_src_len &&
-		   nla_put_in6_addr(skb, RTA_SRC, &rt->fib6_src.addr))
+		   nla_put_in6_addr(skb, RTA_SRC, &rt6_src->addr))
 		goto nla_put_failure;
 #endif
 	if (iif) {
 #ifdef CONFIG_IPV6_MROUTE
-		if (ipv6_addr_is_multicast(&rt->fib6_dst.addr)) {
+		if (ipv6_addr_is_multicast(&rt6_dst->addr)) {
 			int err = ip6mr_get_route(net, skb, rtm, portid);
 
 			if (err == 0)
@@ -4754,7 +4765,14 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 	/* For multipath routes, walk the siblings list and add
 	 * each as a nexthop within RTA_MULTIPATH.
 	 */
-	if (rt->fib6_nsiblings) {
+	if (rt6) {
+		if (rt6_flags & RTF_GATEWAY &&
+		    nla_put_in6_addr(skb, RTA_GATEWAY, &rt6->rt6i_gateway))
+			goto nla_put_failure;
+
+		if (dst->dev && nla_put_u32(skb, RTA_OIF, dst->dev->ifindex))
+			goto nla_put_failure;
+	} else if (rt->fib6_nsiblings) {
 		struct fib6_info *sibling, *next_sibling;
 		struct nlattr *mp;
 
@@ -4777,7 +4795,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 			goto nla_put_failure;
 	}
 
-	if (rt->fib6_flags & RTF_EXPIRES) {
+	if (rt6_flags & RTF_EXPIRES) {
 		expires = dst ? dst->expires : rt->expires;
 		expires -= jiffies;
 	}
@@ -4785,7 +4803,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 	if (rtnl_put_cacheinfo(skb, dst, 0, expires, dst ? dst->error : 0) < 0)
 		goto nla_put_failure;
 
-	if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt->fib6_flags)))
+	if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt6_flags)))
 		goto nla_put_failure;
 
 
-- 
2.13.6


From de4e0c56686b4a0b1263c704937a1ba9ceab362e Mon Sep 17 00:00:00 2001
From: Peter Oskolkov <posk@google.com>
Date: Mon, 17 Sep 2018 10:20:53 -0700
Subject: [PATCH 20/22] net/ipv6: do not copy dst flags on rt init

[ Upstream commit 30bfd93062814d6767e452a8f5ddcd97f7e38c7e ]

DST_NOCOUNT in dst_entry::flags tracks whether the entry counts
toward route cache size (net->ipv6.sysctl.ip6_rt_max_size).

If the flag is NOT set, dst_ops::pcpuc_entries counter is incremented
in dist_init() and decremented in dst_destroy().

This flag is tied to allocation/deallocation of dst_entry and
should not be copied from another dst/route. Otherwise it can happen
that dst_ops::pcpuc_entries counter grows until no new routes can
be allocated because the counter reached ip6_rt_max_size due to
DST_NOCOUNT not set and thus no counter decrements on gc-ed routes.

Fixes: 3b6761d18bc1 ("net/ipv6: Move dst flags to booleans in fib entries")
Cc: David Ahern <dsahern@gmail.com>
Acked-by: Wei Wang <weiwan@google.com>
Signed-off-by: Peter Oskolkov <posk@google.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 3eed045c65a5..480a79f47c52 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -946,8 +946,6 @@ static void ip6_rt_init_dst_reject(struct rt6_info *rt, struct fib6_info *ort)
 
 static void ip6_rt_init_dst(struct rt6_info *rt, struct fib6_info *ort)
 {
-	rt->dst.flags |= fib6_info_dst_flags(ort);
-
 	if (ort->fib6_flags & RTF_REJECT) {
 		ip6_rt_init_dst_reject(rt, ort);
 		return;
-- 
2.13.6


From 5f03741aceb425ccd0fb2a570c68d2aaa7a673cf Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Fri, 14 Sep 2018 16:56:35 +0200
Subject: [PATCH 21/22] net: mvpp2: let phylink manage the carrier state

[ Upstream commit 41948ccb4a856dddacfbd4d789d4fa8663fe41bb ]

Net drivers using phylink shouldn't mess with the link carrier
themselves and should let phylink manage it. The mvpp2 driver wasn't
following this best practice as the mac_config() function made calls to
change the link carrier state. This led to wrongly reported carrier link
state which then triggered other issues. This patch fixes this
behaviour.

But the PPv2 driver relied on this misbehaviour in two cases: for fixed
links and when not using phylink (ACPI mode). The later was fixed by
adding an explicit call to link_up(), which when the ACPI mode will use
phylink should be removed.

The fixed link case was relying on the mac_config() function to set the
link up, as we found an issue in phylink_start() which assumes the
carrier is off. If not, the link_up() function is never called. To fix
this, a call to netif_carrier_off() is added just before phylink_start()
so that we do not introduce a regression in the driver.

Fixes: 4bb043262878 ("net: mvpp2: phylink support")
Reported-by: Russell King <linux@armlinux.org.uk>
Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 21 ++++++---------------
 1 file changed, 6 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 0319ed9ef8b8..323d3f9a1b55 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -61,6 +61,8 @@ static struct {
  */
 static void mvpp2_mac_config(struct net_device *dev, unsigned int mode,
 			     const struct phylink_link_state *state);
+static void mvpp2_mac_link_up(struct net_device *dev, unsigned int mode,
+			      phy_interface_t interface, struct phy_device *phy);
 
 /* Queue modes */
 #define MVPP2_QDIST_SINGLE_MODE	0
@@ -3142,6 +3144,7 @@ static void mvpp2_start_dev(struct mvpp2_port *port)
 		mvpp22_mode_reconfigure(port);
 
 	if (port->phylink) {
+		netif_carrier_off(port->dev);
 		phylink_start(port->phylink);
 	} else {
 		/* Phylink isn't used as of now for ACPI, so the MAC has to be
@@ -3150,9 +3153,10 @@ static void mvpp2_start_dev(struct mvpp2_port *port)
 		 */
 		struct phylink_link_state state = {
 			.interface = port->phy_interface,
-			.link = 1,
 		};
 		mvpp2_mac_config(port->dev, MLO_AN_INBAND, &state);
+		mvpp2_mac_link_up(port->dev, MLO_AN_INBAND, port->phy_interface,
+				  NULL);
 	}
 
 	netif_tx_start_all_queues(port->dev);
@@ -4389,10 +4393,6 @@ static void mvpp2_mac_config(struct net_device *dev, unsigned int mode,
 		return;
 	}
 
-	netif_tx_stop_all_queues(port->dev);
-	if (!port->has_phy)
-		netif_carrier_off(port->dev);
-
 	/* Make sure the port is disabled when reconfiguring the mode */
 	mvpp2_port_disable(port);
 
@@ -4417,16 +4417,7 @@ static void mvpp2_mac_config(struct net_device *dev, unsigned int mode,
 	if (port->priv->hw_version == MVPP21 && port->flags & MVPP2_F_LOOPBACK)
 		mvpp2_port_loopback_set(port, state);
 
-	/* If the port already was up, make sure it's still in the same state */
-	if (state->link || !port->has_phy) {
-		mvpp2_port_enable(port);
-
-		mvpp2_egress_enable(port);
-		mvpp2_ingress_enable(port);
-		if (!port->has_phy)
-			netif_carrier_on(dev);
-		netif_tx_wake_all_queues(dev);
-	}
+	mvpp2_port_enable(port);
 }
 
 static void mvpp2_mac_link_up(struct net_device *dev, unsigned int mode,
-- 
2.13.6


From 950b9fda2218b69cba259ef61afe1f03445767b3 Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Wed, 12 Sep 2018 13:21:48 -0700
Subject: [PATCH 22/22] net: rtnl_configure_link: fix dev flags changes arg to
 __dev_notify_flags

[ Upstream commit 56a49d7048703f5ffdb84d3a0ee034108fba6850 ]

This fix addresses https://bugzilla.kernel.org/show_bug.cgi?id=201071

Commit 5025f7f7d506 wrongly relied on __dev_change_flags to notify users of
dev flag changes in the case when dev->rtnl_link_state = RTNL_LINK_INITIALIZED.
Fix it by indicating flag changes explicitly to __dev_notify_flags.

Fixes: 5025f7f7d506 ("rtnetlink: add rtnl_link_state check in rtnl_configure_link")
Reported-By: Liam mcbirnie <liam.mcbirnie@boeing.com>
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index e3f743c141b3..bafaa033826f 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2760,7 +2760,7 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm)
 	}
 
 	if (dev->rtnl_link_state == RTNL_LINK_INITIALIZED) {
-		__dev_notify_flags(dev, old_flags, 0U);
+		__dev_notify_flags(dev, old_flags, (old_flags ^ dev->flags));
 	} else {
 		dev->rtnl_link_state = RTNL_LINK_INITIALIZED;
 		__dev_notify_flags(dev, old_flags, ~0U);
-- 
2.13.6

Re: [PATCHES] Networking

[Greg KH]

On Mon, Sep 24, 2018 at 09:46:40AM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.14.x and
> v4.18.x -stable, respectively.

All now queued up, thanks.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 95 bytes --]


Please queue up the following networking bug fixes for v4.18 and
v4.19 -stable, respectively.

[-- Attachment #2: net_418.mbox --]
[-- Type: Application/Octet-Stream, Size: 104994 bytes --]

From a7e68213176fc86f4a9f9b3e11adff29ea323256 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Fri, 26 Oct 2018 10:28:43 +0800
Subject: [PATCH 01/39] bridge: do not add port to router list when receives
 query with source 0.0.0.0

[ Upstream commit 5a2de63fd1a59c30c02526d427bc014b98adf508 ]

Based on RFC 4541, 2.1.1.  IGMP Forwarding Rules

  The switch supporting IGMP snooping must maintain a list of
  multicast routers and the ports on which they are attached.  This
  list can be constructed in any combination of the following ways:

  a) This list should be built by the snooping switch sending
     Multicast Router Solicitation messages as described in IGMP
     Multicast Router Discovery [MRDISC].  It may also snoop
     Multicast Router Advertisement messages sent by and to other
     nodes.

  b) The arrival port for IGMP Queries (sent by multicast routers)
     where the source address is not 0.0.0.0.

We should not add the port to router list when receives query with source
0.0.0.0.

Reported-by: Ying Xu <yinxu@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Acked-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 920665dd92db..b4e5c515a6da 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1420,7 +1420,15 @@ static void br_multicast_query_received(struct net_bridge *br,
 		return;
 
 	br_multicast_update_query_timer(br, query, max_delay);
-	br_multicast_mark_router(br, port);
+
+	/* Based on RFC4541, section 2.1.1 IGMP Forwarding Rules,
+	 * the arrival port for IGMP Queries where the source address
+	 * is 0.0.0.0 should not be added to router port list.
+	 */
+	if ((saddr->proto == htons(ETH_P_IP) && saddr->u.ip4) ||
+	    (saddr->proto == htons(ETH_P_IPV6) &&
+	     !ipv6_addr_any(&saddr->u.ip6)))
+		br_multicast_mark_router(br, port);
 }
 
 static int br_ip4_multicast_query(struct net_bridge *br,
-- 
2.19.1


From 705d08bfc77445d63fba8d0317796086a3457668 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 12 Oct 2018 18:58:53 -0700
Subject: [PATCH 02/39] ipv6: mcast: fix a use-after-free in inet6_mc_check

[ Upstream commit dc012f3628eaecfb5ba68404a5c30ef501daf63d ]

syzbot found a use-after-free in inet6_mc_check [1]

The problem here is that inet6_mc_check() uses rcu
and read_lock(&iml->sflock)

So the fact that ip6_mc_leave_src() is called under RTNL
and the socket lock does not help us, we need to acquire
iml->sflock in write mode.

In the future, we should convert all this stuff to RCU.

[1]
BUG: KASAN: use-after-free in ipv6_addr_equal include/net/ipv6.h:521 [inline]
BUG: KASAN: use-after-free in inet6_mc_check+0xae7/0xb40 net/ipv6/mcast.c:649
Read of size 8 at addr ffff8801ce7f2510 by task syz-executor0/22432

CPU: 1 PID: 22432 Comm: syz-executor0 Not tainted 4.19.0-rc7+ #280
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c4/0x2b4 lib/dump_stack.c:113
 print_address_description.cold.8+0x9/0x1ff mm/kasan/report.c:256
 kasan_report_error mm/kasan/report.c:354 [inline]
 kasan_report.cold.9+0x242/0x309 mm/kasan/report.c:412
 __asan_report_load8_noabort+0x14/0x20 mm/kasan/report.c:433
 ipv6_addr_equal include/net/ipv6.h:521 [inline]
 inet6_mc_check+0xae7/0xb40 net/ipv6/mcast.c:649
 __raw_v6_lookup+0x320/0x3f0 net/ipv6/raw.c:98
 ipv6_raw_deliver net/ipv6/raw.c:183 [inline]
 raw6_local_deliver+0x3d3/0xcb0 net/ipv6/raw.c:240
 ip6_input_finish+0x467/0x1aa0 net/ipv6/ip6_input.c:345
 NF_HOOK include/linux/netfilter.h:289 [inline]
 ip6_input+0xe9/0x600 net/ipv6/ip6_input.c:426
 ip6_mc_input+0x48a/0xd20 net/ipv6/ip6_input.c:503
 dst_input include/net/dst.h:450 [inline]
 ip6_rcv_finish+0x17a/0x330 net/ipv6/ip6_input.c:76
 NF_HOOK include/linux/netfilter.h:289 [inline]
 ipv6_rcv+0x120/0x640 net/ipv6/ip6_input.c:271
 __netif_receive_skb_one_core+0x14d/0x200 net/core/dev.c:4913
 __netif_receive_skb+0x2c/0x1e0 net/core/dev.c:5023
 netif_receive_skb_internal+0x12c/0x620 net/core/dev.c:5126
 napi_frags_finish net/core/dev.c:5664 [inline]
 napi_gro_frags+0x75a/0xc90 net/core/dev.c:5737
 tun_get_user+0x3189/0x4250 drivers/net/tun.c:1923
 tun_chr_write_iter+0xb9/0x154 drivers/net/tun.c:1968
 call_write_iter include/linux/fs.h:1808 [inline]
 do_iter_readv_writev+0x8b0/0xa80 fs/read_write.c:680
 do_iter_write+0x185/0x5f0 fs/read_write.c:959
 vfs_writev+0x1f1/0x360 fs/read_write.c:1004
 do_writev+0x11a/0x310 fs/read_write.c:1039
 __do_sys_writev fs/read_write.c:1112 [inline]
 __se_sys_writev fs/read_write.c:1109 [inline]
 __x64_sys_writev+0x75/0xb0 fs/read_write.c:1109
 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x457421
Code: 75 14 b8 14 00 00 00 0f 05 48 3d 01 f0 ff ff 0f 83 34 b5 fb ff c3 48 83 ec 08 e8 1a 2d 00 00 48 89 04 24 b8 14 00 00 00 0f 05 <48> 8b 3c 24 48 89 c2 e8 63 2d 00 00 48 89 d0 48 83 c4 08 48 3d 01
RSP: 002b:00007f2d30ecaba0 EFLAGS: 00000293 ORIG_RAX: 0000000000000014
RAX: ffffffffffffffda RBX: 000000000000003e RCX: 0000000000457421
RDX: 0000000000000001 RSI: 00007f2d30ecabf0 RDI: 00000000000000f0
RBP: 0000000020000500 R08: 00000000000000f0 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000293 R12: 00007f2d30ecb6d4
R13: 00000000004c4890 R14: 00000000004d7b90 R15: 00000000ffffffff

Allocated by task 22437:
 save_stack+0x43/0xd0 mm/kasan/kasan.c:448
 set_track mm/kasan/kasan.c:460 [inline]
 kasan_kmalloc+0xc7/0xe0 mm/kasan/kasan.c:553
 __do_kmalloc mm/slab.c:3718 [inline]
 __kmalloc+0x14e/0x760 mm/slab.c:3727
 kmalloc include/linux/slab.h:518 [inline]
 sock_kmalloc+0x15a/0x1f0 net/core/sock.c:1983
 ip6_mc_source+0x14dd/0x1960 net/ipv6/mcast.c:427
 do_ipv6_setsockopt.isra.9+0x3afb/0x45d0 net/ipv6/ipv6_sockglue.c:743
 ipv6_setsockopt+0xbd/0x170 net/ipv6/ipv6_sockglue.c:933
 rawv6_setsockopt+0x59/0x140 net/ipv6/raw.c:1069
 sock_common_setsockopt+0x9a/0xe0 net/core/sock.c:3038
 __sys_setsockopt+0x1ba/0x3c0 net/socket.c:1902
 __do_sys_setsockopt net/socket.c:1913 [inline]
 __se_sys_setsockopt net/socket.c:1910 [inline]
 __x64_sys_setsockopt+0xbe/0x150 net/socket.c:1910
 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Freed by task 22430:
 save_stack+0x43/0xd0 mm/kasan/kasan.c:448
 set_track mm/kasan/kasan.c:460 [inline]
 __kasan_slab_free+0x102/0x150 mm/kasan/kasan.c:521
 kasan_slab_free+0xe/0x10 mm/kasan/kasan.c:528
 __cache_free mm/slab.c:3498 [inline]
 kfree+0xcf/0x230 mm/slab.c:3813
 __sock_kfree_s net/core/sock.c:2004 [inline]
 sock_kfree_s+0x29/0x60 net/core/sock.c:2010
 ip6_mc_leave_src+0x11a/0x1d0 net/ipv6/mcast.c:2448
 __ipv6_sock_mc_close+0x20b/0x4e0 net/ipv6/mcast.c:310
 ipv6_sock_mc_close+0x158/0x1d0 net/ipv6/mcast.c:328
 inet6_release+0x40/0x70 net/ipv6/af_inet6.c:452
 __sock_release+0xd7/0x250 net/socket.c:579
 sock_close+0x19/0x20 net/socket.c:1141
 __fput+0x385/0xa30 fs/file_table.c:278
 ____fput+0x15/0x20 fs/file_table.c:309
 task_work_run+0x1e8/0x2a0 kernel/task_work.c:113
 tracehook_notify_resume include/linux/tracehook.h:193 [inline]
 exit_to_usermode_loop+0x318/0x380 arch/x86/entry/common.c:166
 prepare_exit_to_usermode arch/x86/entry/common.c:197 [inline]
 syscall_return_slowpath arch/x86/entry/common.c:268 [inline]
 do_syscall_64+0x6be/0x820 arch/x86/entry/common.c:293
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

The buggy address belongs to the object at ffff8801ce7f2500
 which belongs to the cache kmalloc-192 of size 192
The buggy address is located 16 bytes inside of
 192-byte region [ffff8801ce7f2500, ffff8801ce7f25c0)
The buggy address belongs to the page:
page:ffffea000739fc80 count:1 mapcount:0 mapping:ffff8801da800040 index:0x0
flags: 0x2fffc0000000100(slab)
raw: 02fffc0000000100 ffffea0006f6e548 ffffea000737b948 ffff8801da800040
raw: 0000000000000000 ffff8801ce7f2000 0000000100000010 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff8801ce7f2400: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff8801ce7f2480: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
>ffff8801ce7f2500: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                         ^
 ffff8801ce7f2580: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
 ffff8801ce7f2600: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/mcast.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index f60f310785fd..131440ea6b51 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -2436,17 +2436,17 @@ static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml,
 {
 	int err;
 
-	/* callers have the socket lock and rtnl lock
-	 * so no other readers or writers of iml or its sflist
-	 */
+	write_lock_bh(&iml->sflock);
 	if (!iml->sflist) {
 		/* any-source empty exclude case */
-		return ip6_mc_del_src(idev, &iml->addr, iml->sfmode, 0, NULL, 0);
+		err = ip6_mc_del_src(idev, &iml->addr, iml->sfmode, 0, NULL, 0);
+	} else {
+		err = ip6_mc_del_src(idev, &iml->addr, iml->sfmode,
+				iml->sflist->sl_count, iml->sflist->sl_addr, 0);
+		sock_kfree_s(sk, iml->sflist, IP6_SFLSIZE(iml->sflist->sl_max));
+		iml->sflist = NULL;
 	}
-	err = ip6_mc_del_src(idev, &iml->addr, iml->sfmode,
-		iml->sflist->sl_count, iml->sflist->sl_addr, 0);
-	sock_kfree_s(sk, iml->sflist, IP6_SFLSIZE(iml->sflist->sl_max));
-	iml->sflist = NULL;
+	write_unlock_bh(&iml->sflock);
 	return err;
 }
 
-- 
2.19.1


From e75f6ec70dff81308d61ce8ff280623160ebc90d Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Wed, 24 Oct 2018 14:37:21 +0200
Subject: [PATCH 03/39] ipv6/ndisc: Preserve IPv6 control buffer if protocol
 error handlers are called

[ Upstream commit ee1abcf689353f36d9322231b4320926096bdee0 ]

Commit a61bbcf28a8c ("[NET]: Store skb->timestamp as offset to a base
timestamp") introduces a neighbour control buffer and zeroes it out in
ndisc_rcv(), as ndisc_recv_ns() uses it.

Commit f2776ff04722 ("[IPV6]: Fix address/interface handling in UDP and
DCCP, according to the scoping architecture.") introduces the usage of the
IPv6 control buffer in protocol error handlers (e.g. inet6_iif() in
present-day __udp6_lib_err()).

Now, with commit b94f1c0904da ("ipv6: Use icmpv6_notify() to propagate
redirect, instead of rt6_redirect()."), we call protocol error handlers
from ndisc_redirect_rcv(), after the control buffer is already stolen and
some parts are already zeroed out. This implies that inet6_iif() on this
path will always return zero.

This gives unexpected results on UDP socket lookup in __udp6_lib_err(), as
we might actually need to match sockets for a given interface.

Instead of always claiming the control buffer in ndisc_rcv(), do that only
when needed.

Fixes: b94f1c0904da ("ipv6: Use icmpv6_notify() to propagate redirect, instead of rt6_redirect().")
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ndisc.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 0ec273997d1d..673a4a932f2a 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1732,10 +1732,9 @@ int ndisc_rcv(struct sk_buff *skb)
 		return 0;
 	}
 
-	memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb));
-
 	switch (msg->icmph.icmp6_type) {
 	case NDISC_NEIGHBOUR_SOLICITATION:
+		memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb));
 		ndisc_recv_ns(skb);
 		break;
 
-- 
2.19.1


From ec74077b90717d69a2284cc67e142150a452fa46 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 12 Oct 2018 16:22:47 +0200
Subject: [PATCH 04/39] ipv6: rate-limit probes for neighbourless routes

[ Upstream commit f547fac624be53ad8b07e9ebca7654a7827ba61b ]

When commit 270972554c91 ("[IPV6]: ROUTE: Add Router Reachability
Probing (RFC4191).") introduced router probing, the rt6_probe() function
required that a neighbour entry existed. This neighbour entry is used to
record the timestamp of the last probe via the ->updated field.

Later, commit 2152caea7196 ("ipv6: Do not depend on rt->n in rt6_probe().")
removed the requirement for a neighbour entry. Neighbourless routes skip
the interval check and are not rate-limited.

This patch adds rate-limiting for neighbourless routes, by recording the
timestamp of the last probe in the fib6_info itself.

Fixes: 2152caea7196 ("ipv6: Do not depend on rt->n in rt6_probe().")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h |  4 ++++
 net/ipv6/route.c      | 12 ++++++------
 2 files changed, 10 insertions(+), 6 deletions(-)

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 3d4930528db0..2d31e22babd8 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -159,6 +159,10 @@ struct fib6_info {
 	struct rt6_info * __percpu	*rt6i_pcpu;
 	struct rt6_exception_bucket __rcu *rt6i_exception_bucket;
 
+#ifdef CONFIG_IPV6_ROUTER_PREF
+	unsigned long			last_probe;
+#endif
+
 	u32				fib6_metric;
 	u8				fib6_protocol;
 	u8				fib6_type;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index ed526e257da6..d9e8960e58d3 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -517,10 +517,11 @@ static void rt6_probe_deferred(struct work_struct *w)
 
 static void rt6_probe(struct fib6_info *rt)
 {
-	struct __rt6_probe_work *work;
+	struct __rt6_probe_work *work = NULL;
 	const struct in6_addr *nh_gw;
 	struct neighbour *neigh;
 	struct net_device *dev;
+	struct inet6_dev *idev;
 
 	/*
 	 * Okay, this does not seem to be appropriate
@@ -536,15 +537,12 @@ static void rt6_probe(struct fib6_info *rt)
 	nh_gw = &rt->fib6_nh.nh_gw;
 	dev = rt->fib6_nh.nh_dev;
 	rcu_read_lock_bh();
+	idev = __in6_dev_get(dev);
 	neigh = __ipv6_neigh_lookup_noref(dev, nh_gw);
 	if (neigh) {
-		struct inet6_dev *idev;
-
 		if (neigh->nud_state & NUD_VALID)
 			goto out;
 
-		idev = __in6_dev_get(dev);
-		work = NULL;
 		write_lock(&neigh->lock);
 		if (!(neigh->nud_state & NUD_VALID) &&
 		    time_after(jiffies,
@@ -554,11 +552,13 @@ static void rt6_probe(struct fib6_info *rt)
 				__neigh_set_probe_once(neigh);
 		}
 		write_unlock(&neigh->lock);
-	} else {
+	} else if (time_after(jiffies, rt->last_probe +
+				       idev->cnf.rtr_probe_interval)) {
 		work = kmalloc(sizeof(*work), GFP_ATOMIC);
 	}
 
 	if (work) {
+		rt->last_probe = jiffies;
 		INIT_WORK(&work->work, rt6_probe_deferred);
 		work->target = *nh_gw;
 		dev_hold(dev);
-- 
2.19.1


From f926a82066939253b47a97fde3f9702a621e3c59 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 11 Oct 2018 11:15:13 -0700
Subject: [PATCH 05/39] llc: set SOCK_RCU_FREE in llc_sap_add_socket()

[ Upstream commit 5a8e7aea953bdb6d4da13aff6f1e7f9c62023499 ]

WHen an llc sock is added into the sk_laddr_hash of an llc_sap,
it is not marked with SOCK_RCU_FREE.

This causes that the sock could be freed while it is still being
read by __llc_lookup_established() with RCU read lock. sock is
refcounted, but with RCU read lock, nothing prevents the readers
getting a zero refcnt.

Fix it by setting SOCK_RCU_FREE in llc_sap_add_socket().

Reported-by: syzbot+11e05f04c15e03be5254@syzkaller.appspotmail.com
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/llc/llc_conn.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c
index c0ac522b48a1..4ff89cb7c86f 100644
--- a/net/llc/llc_conn.c
+++ b/net/llc/llc_conn.c
@@ -734,6 +734,7 @@ void llc_sap_add_socket(struct llc_sap *sap, struct sock *sk)
 	llc_sk(sk)->sap = sap;
 
 	spin_lock_bh(&sap->sk_lock);
+	sock_set_flag(sk, SOCK_RCU_FREE);
 	sap->sk_count++;
 	sk_nulls_add_node_rcu(sk, laddr_hb);
 	hlist_add_head(&llc->dev_hash_node, dev_hb);
-- 
2.19.1


From 3d5fdd2c948c47b60effabb98bbb1aada43fc1da Mon Sep 17 00:00:00 2001
From: Fugang Duan <fugang.duan@nxp.com>
Date: Mon, 15 Oct 2018 05:19:00 +0000
Subject: [PATCH 06/39] net: fec: don't dump RX FIFO register when not
 available

[ Upstream commit ec20a63aa8b8ec3223fb25cdb2a49f9f9dfda88c ]

Commit db65f35f50e0 ("net: fec: add support of ethtool get_regs") introduce
ethool "--register-dump" interface to dump all FEC registers.

But not all silicon implementations of the Freescale FEC hardware module
have the FRBR (FIFO Receive Bound Register) and FRSR (FIFO Receive Start
Register) register, so we should not be trying to dump them on those that
don't.

To fix it we create a quirk flag, FEC_QUIRK_HAS_RFREG, and check it before
dump those RX FIFO registers.

Signed-off-by: Fugang Duan <fugang.duan@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec.h      |  4 ++++
 drivers/net/ethernet/freescale/fec_main.c | 16 ++++++++++++----
 2 files changed, 16 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index 4778b663653e..bf80855dd0dd 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -452,6 +452,10 @@ struct bufdesc_ex {
  * initialisation.
  */
 #define FEC_QUIRK_MIB_CLEAR		(1 << 15)
+/* Only i.MX25/i.MX27/i.MX28 controller supports FRBR,FRSR registers,
+ * those FIFO receive registers are resolved in other platforms.
+ */
+#define FEC_QUIRK_HAS_FRREG		(1 << 16)
 
 struct bufdesc_prop {
 	int qid;
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index c729665107f5..ae274b30c618 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -90,14 +90,16 @@ static struct platform_device_id fec_devtype[] = {
 		.driver_data = 0,
 	}, {
 		.name = "imx25-fec",
-		.driver_data = FEC_QUIRK_USE_GASKET | FEC_QUIRK_MIB_CLEAR,
+		.driver_data = FEC_QUIRK_USE_GASKET | FEC_QUIRK_MIB_CLEAR |
+			       FEC_QUIRK_HAS_FRREG,
 	}, {
 		.name = "imx27-fec",
-		.driver_data = FEC_QUIRK_MIB_CLEAR,
+		.driver_data = FEC_QUIRK_MIB_CLEAR | FEC_QUIRK_HAS_FRREG,
 	}, {
 		.name = "imx28-fec",
 		.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_SWAP_FRAME |
-				FEC_QUIRK_SINGLE_MDIO | FEC_QUIRK_HAS_RACC,
+				FEC_QUIRK_SINGLE_MDIO | FEC_QUIRK_HAS_RACC |
+				FEC_QUIRK_HAS_FRREG,
 	}, {
 		.name = "imx6q-fec",
 		.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT |
@@ -2163,7 +2165,13 @@ static void fec_enet_get_regs(struct net_device *ndev,
 	memset(buf, 0, regs->len);
 
 	for (i = 0; i < ARRAY_SIZE(fec_enet_register_offset); i++) {
-		off = fec_enet_register_offset[i] / 4;
+		off = fec_enet_register_offset[i];
+
+		if ((off == FEC_R_BOUND || off == FEC_R_FSTART) &&
+		    !(fep->quirks & FEC_QUIRK_HAS_FRREG))
+			continue;
+
+		off >>= 2;
 		buf[off] = readl(&theregs[off]);
 	}
 }
-- 
2.19.1


From a048efc4e63e0721c815689c2218ea175dff119a Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Fri, 19 Oct 2018 10:00:19 -0700
Subject: [PATCH 07/39] net/ipv6: Fix index counter for unicast addresses in
 in6_dump_addrs

[ Upstream commit 4ba4c566ba8448a05e6257e0b98a21f1a0d55315 ]

The loop wants to skip previously dumped addresses, so loops until
current index >= saved index. If the message fills it wants to save
the index for the next address to dump - ie., the one that did not
fit in the current message.

Currently, it is incrementing the index counter before comparing to the
saved index, and then the saved index is off by 1 - it assumes the
current address is going to fit in the message.

Change the index handling to increment only after a succesful dump.

Fixes: 502a2ffd7376a ("ipv6: convert idev_list to list macros")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 3484c7020fd9..ac3de1aa1cd3 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -4930,8 +4930,8 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb,
 
 		/* unicast address incl. temp addr */
 		list_for_each_entry(ifa, &idev->addr_list, if_list) {
-			if (++ip_idx < s_ip_idx)
-				continue;
+			if (ip_idx < s_ip_idx)
+				goto next;
 			err = inet6_fill_ifaddr(skb, ifa,
 						NETLINK_CB(cb->skb).portid,
 						cb->nlh->nlmsg_seq,
@@ -4940,6 +4940,8 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb,
 			if (err < 0)
 				break;
 			nl_dump_check_consistent(cb, nlmsg_hdr(skb));
+next:
+			ip_idx++;
 		}
 		break;
 	}
-- 
2.19.1


From c693d60d31b1bb8c2899f637af789af14d274383 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 30 Oct 2018 00:57:25 -0700
Subject: [PATCH 08/39] net/mlx5e: fix csum adjustments caused by RXFCS
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit d48051c5b8376038c2b287c3b1bd55b8d391d567 ]

As shown by Dmitris, we need to use csum_block_add() instead of csum_add()
when adding the FCS contribution to skb csum.

Before 4.18 (more exactly commit 88078d98d1bb "net: pskb_trim_rcsum()
and CHECKSUM_COMPLETE are friends"), the whole skb csum was thrown away,
so RXFCS changes were ignored.

Then before commit d55bef5059dd ("net: fix pskb_trim_rcsum_slow() with
odd trim offset") both mlx5 and pskb_trim_rcsum_slow() bugs were canceling
each other.

Now we fixed pskb_trim_rcsum_slow() we need to fix mlx5.

Note that this patch also rewrites mlx5e_get_fcs() to :

- Use skb_header_pointer() instead of reinventing it.
- Use __get_unaligned_cpu32() to avoid possible non aligned accesses
  as Dmitris pointed out.

Fixes: 902a545904c7 ("net/mlx5e: When RXFCS is set, add FCS data into checksum calculation")
Reported-by: Paweł Staszewski <pstaszewski@itcare.pl>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Eran Ben Elisha <eranbe@mellanox.com>
Cc: Saeed Mahameed <saeedm@mellanox.com>
Cc: Dimitris Michailidis <dmichail@google.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Paweł Staszewski <pstaszewski@itcare.pl>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Tested-By: Maria Pasechnik <mariap@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlx5/core/en_rx.c   | 45 ++++---------------
 1 file changed, 9 insertions(+), 36 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index d3a1dd20e41d..696edeff255b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -693,43 +693,15 @@ static inline bool is_last_ethertype_ip(struct sk_buff *skb, int *network_depth)
 	return (ethertype == htons(ETH_P_IP) || ethertype == htons(ETH_P_IPV6));
 }
 
-static __be32 mlx5e_get_fcs(struct sk_buff *skb)
+static u32 mlx5e_get_fcs(const struct sk_buff *skb)
 {
-	int last_frag_sz, bytes_in_prev, nr_frags;
-	u8 *fcs_p1, *fcs_p2;
-	skb_frag_t *last_frag;
-	__be32 fcs_bytes;
+	const void *fcs_bytes;
+	u32 _fcs_bytes;
 
-	if (!skb_is_nonlinear(skb))
-		return *(__be32 *)(skb->data + skb->len - ETH_FCS_LEN);
+	fcs_bytes = skb_header_pointer(skb, skb->len - ETH_FCS_LEN,
+				       ETH_FCS_LEN, &_fcs_bytes);
 
-	nr_frags = skb_shinfo(skb)->nr_frags;
-	last_frag = &skb_shinfo(skb)->frags[nr_frags - 1];
-	last_frag_sz = skb_frag_size(last_frag);
-
-	/* If all FCS data is in last frag */
-	if (last_frag_sz >= ETH_FCS_LEN)
-		return *(__be32 *)(skb_frag_address(last_frag) +
-				   last_frag_sz - ETH_FCS_LEN);
-
-	fcs_p2 = (u8 *)skb_frag_address(last_frag);
-	bytes_in_prev = ETH_FCS_LEN - last_frag_sz;
-
-	/* Find where the other part of the FCS is - Linear or another frag */
-	if (nr_frags == 1) {
-		fcs_p1 = skb_tail_pointer(skb);
-	} else {
-		skb_frag_t *prev_frag = &skb_shinfo(skb)->frags[nr_frags - 2];
-
-		fcs_p1 = skb_frag_address(prev_frag) +
-			    skb_frag_size(prev_frag);
-	}
-	fcs_p1 -= bytes_in_prev;
-
-	memcpy(&fcs_bytes, fcs_p1, bytes_in_prev);
-	memcpy(((u8 *)&fcs_bytes) + bytes_in_prev, fcs_p2, last_frag_sz);
-
-	return fcs_bytes;
+	return __get_unaligned_cpu32(fcs_bytes);
 }
 
 static inline void mlx5e_handle_csum(struct net_device *netdev,
@@ -762,8 +734,9 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 						 network_depth - ETH_HLEN,
 						 skb->csum);
 		if (unlikely(netdev->features & NETIF_F_RXFCS))
-			skb->csum = csum_add(skb->csum,
-					     (__force __wsum)mlx5e_get_fcs(skb));
+			skb->csum = csum_block_add(skb->csum,
+						   (__force __wsum)mlx5e_get_fcs(skb),
+						   skb->len - ETH_FCS_LEN);
 		stats->csum_complete++;
 		return;
 	}
-- 
2.19.1


From d5c84230418d8f4fe3e45bd53b42b10a97855c84 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 26 Oct 2018 15:51:06 -0700
Subject: [PATCH 09/39] net: sched: gred: pass the right attribute to
 gred_change_table_def()

[ Upstream commit 38b4f18d56372e1e21771ab7b0357b853330186c ]

gred_change_table_def() takes a pointer to TCA_GRED_DPS attribute,
and expects it will be able to interpret its contents as
struct tc_gred_sopt.  Pass the correct gred attribute, instead of
TCA_OPTIONS.

This bug meant the table definition could never be changed after
Qdisc was initialized (unless whatever TCA_OPTIONS contained both
passed netlink validation and was a valid struct tc_gred_sopt...).

Old behaviour:
$ ip link add type dummy
$ tc qdisc replace dev dummy0 parent root handle 7: \
     gred setup vqs 4 default 0
$ tc qdisc replace dev dummy0 parent root handle 7: \
     gred setup vqs 4 default 0
RTNETLINK answers: Invalid argument

Now:
$ ip link add type dummy
$ tc qdisc replace dev dummy0 parent root handle 7: \
     gred setup vqs 4 default 0
$ tc qdisc replace dev dummy0 parent root handle 7: \
     gred setup vqs 4 default 0
$ tc qdisc replace dev dummy0 parent root handle 7: \
     gred setup vqs 4 default 0

Fixes: f62d6b936df5 ("[PKT_SCHED]: GRED: Use central VQ change procedure")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_gred.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index cbe4831f46f4..4a042abf844c 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -413,7 +413,7 @@ static int gred_change(struct Qdisc *sch, struct nlattr *opt,
 	if (tb[TCA_GRED_PARMS] == NULL && tb[TCA_GRED_STAB] == NULL) {
 		if (tb[TCA_GRED_LIMIT] != NULL)
 			sch->limit = nla_get_u32(tb[TCA_GRED_LIMIT]);
-		return gred_change_table_def(sch, opt);
+		return gred_change_table_def(sch, tb[TCA_GRED_DPS]);
 	}
 
 	if (tb[TCA_GRED_PARMS] == NULL ||
-- 
2.19.1


From 24ca2a943b9684a6c54344782e1bee3c77dff5c0 Mon Sep 17 00:00:00 2001
From: Wenwen Wang <wang6495@umn.edu>
Date: Thu, 18 Oct 2018 09:36:46 -0500
Subject: [PATCH 10/39] net: socket: fix a missing-check bug

[ Upstream commit b6168562c8ce2bd5a30e213021650422e08764dc ]

In ethtool_ioctl(), the ioctl command 'ethcmd' is checked through a switch
statement to see whether it is necessary to pre-process the ethtool
structure, because, as mentioned in the comment, the structure
ethtool_rxnfc is defined with padding. If yes, a user-space buffer 'rxnfc'
is allocated through compat_alloc_user_space(). One thing to note here is
that, if 'ethcmd' is ETHTOOL_GRXCLSRLALL, the size of the buffer 'rxnfc' is
partially determined by 'rule_cnt', which is actually acquired from the
user-space buffer 'compat_rxnfc', i.e., 'compat_rxnfc->rule_cnt', through
get_user(). After 'rxnfc' is allocated, the data in the original user-space
buffer 'compat_rxnfc' is then copied to 'rxnfc' through copy_in_user(),
including the 'rule_cnt' field. However, after this copy, no check is
re-enforced on 'rxnfc->rule_cnt'. So it is possible that a malicious user
race to change the value in the 'compat_rxnfc->rule_cnt' between these two
copies. Through this way, the attacker can bypass the previous check on
'rule_cnt' and inject malicious data. This can cause undefined behavior of
the kernel and introduce potential security risk.

This patch avoids the above issue via copying the value acquired by
get_user() to 'rxnfc->rule_cn', if 'ethcmd' is ETHTOOL_GRXCLSRLALL.

Signed-off-by: Wenwen Wang <wang6495@umn.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/socket.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/net/socket.c b/net/socket.c
index d4187ac17d55..fcb18a7ed14b 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2887,9 +2887,14 @@ static int ethtool_ioctl(struct net *net, struct compat_ifreq __user *ifr32)
 		    copy_in_user(&rxnfc->fs.ring_cookie,
 				 &compat_rxnfc->fs.ring_cookie,
 				 (void __user *)(&rxnfc->fs.location + 1) -
-				 (void __user *)&rxnfc->fs.ring_cookie) ||
-		    copy_in_user(&rxnfc->rule_cnt, &compat_rxnfc->rule_cnt,
-				 sizeof(rxnfc->rule_cnt)))
+				 (void __user *)&rxnfc->fs.ring_cookie))
+			return -EFAULT;
+		if (ethcmd == ETHTOOL_GRXCLSRLALL) {
+			if (put_user(rule_cnt, &rxnfc->rule_cnt))
+				return -EFAULT;
+		} else if (copy_in_user(&rxnfc->rule_cnt,
+					&compat_rxnfc->rule_cnt,
+					sizeof(rxnfc->rule_cnt)))
 			return -EFAULT;
 	}
 
-- 
2.19.1


From de0c48dc9f498811478fcb4e473098665cbf90e0 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <niklas.cassel@linaro.org>
Date: Wed, 31 Oct 2018 16:08:10 +0100
Subject: [PATCH 11/39] net: stmmac: Fix stmmac_mdio_reset() when building
 stmmac as modules

[ Upstream commit 30549aab146ccb1275230c3b4b4bc6b4181fd54e ]

When building stmmac, it is only possible to select CONFIG_DWMAC_GENERIC,
or any of the glue drivers, when CONFIG_STMMAC_PLATFORM is set.
The only exception is CONFIG_STMMAC_PCI.

When calling of_mdiobus_register(), it will call our ->reset()
callback, which is set to stmmac_mdio_reset().

Most of the code in stmmac_mdio_reset() is protected by a
"#if defined(CONFIG_STMMAC_PLATFORM)", which will evaluate
to false when CONFIG_STMMAC_PLATFORM=m.

Because of this, the phy reset gpio will only be pulled when
stmmac is built as built-in, but not when built as modules.

Fix this by using "#if IS_ENABLED()" instead of "#if defined()".

Signed-off-by: Niklas Cassel <niklas.cassel@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index 5df1a608e566..541602d70c24 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -133,7 +133,7 @@ static int stmmac_mdio_write(struct mii_bus *bus, int phyaddr, int phyreg,
  */
 int stmmac_mdio_reset(struct mii_bus *bus)
 {
-#if defined(CONFIG_STMMAC_PLATFORM)
+#if IS_ENABLED(CONFIG_STMMAC_PLATFORM)
 	struct net_device *ndev = bus->priv;
 	struct stmmac_priv *priv = netdev_priv(ndev);
 	unsigned int mii_address = priv->hw->mii.addr;
-- 
2.19.1


From 4a6201dee9cc7b4933b793aaf8bbdea63de14fb8 Mon Sep 17 00:00:00 2001
From: Sean Tranchetti <stranche@codeaurora.org>
Date: Tue, 23 Oct 2018 16:04:31 -0600
Subject: [PATCH 12/39] net: udp: fix handling of CHECKSUM_COMPLETE packets

[ Upstream commit db4f1be3ca9b0ef7330763d07bf4ace83ad6f913 ]

Current handling of CHECKSUM_COMPLETE packets by the UDP stack is
incorrect for any packet that has an incorrect checksum value.

udp4/6_csum_init() will both make a call to
__skb_checksum_validate_complete() to initialize/validate the csum
field when receiving a CHECKSUM_COMPLETE packet. When this packet
fails validation, skb->csum will be overwritten with the pseudoheader
checksum so the packet can be fully validated by software, but the
skb->ip_summed value will be left as CHECKSUM_COMPLETE so that way
the stack can later warn the user about their hardware spewing bad
checksums. Unfortunately, leaving the SKB in this state can cause
problems later on in the checksum calculation.

Since the the packet is still marked as CHECKSUM_COMPLETE,
udp_csum_pull_header() will SUBTRACT the checksum of the UDP header
from skb->csum instead of adding it, leaving us with a garbage value
in that field. Once we try to copy the packet to userspace in the
udp4/6_recvmsg(), we'll make a call to skb_copy_and_csum_datagram_msg()
to checksum the packet data and add it in the garbage skb->csum value
to perform our final validation check.

Since the value we're validating is not the proper checksum, it's possible
that the folded value could come out to 0, causing us not to drop the
packet. Instead, we believe that the packet was checksummed incorrectly
by hardware since skb->ip_summed is still CHECKSUM_COMPLETE, and we attempt
to warn the user with netdev_rx_csum_fault(skb->dev);

Unfortunately, since this is the UDP path, skb->dev has been overwritten
by skb->dev_scratch and is no longer a valid pointer, so we end up
reading invalid memory.

This patch addresses this problem in two ways:
	1) Do not use the dev pointer when calling netdev_rx_csum_fault()
	   from skb_copy_and_csum_datagram_msg(). Since this gets called
	   from the UDP path where skb->dev has been overwritten, we have
	   no way of knowing if the pointer is still valid. Also for the
	   sake of consistency with the other uses of
	   netdev_rx_csum_fault(), don't attempt to call it if the
	   packet was checksummed by software.

	2) Add better CHECKSUM_COMPLETE handling to udp4/6_csum_init().
	   If we receive a packet that's CHECKSUM_COMPLETE that fails
	   verification (i.e. skb->csum_valid == 0), check who performed
	   the calculation. It's possible that the checksum was done in
	   software by the network stack earlier (such as Netfilter's
	   CONNTRACK module), and if that says the checksum is bad,
	   we can drop the packet immediately instead of waiting until
	   we try and copy it to userspace. Otherwise, we need to
	   mark the SKB as CHECKSUM_NONE, since the skb->csum field
	   no longer contains the full packet checksum after the
	   call to __skb_checksum_validate_complete().

Fixes: e6afc8ace6dd ("udp: remove headers from UDP packets before queueing")
Fixes: c84d949057ca ("udp: copy skb->truesize in the first cache line")
Cc: Sam Kumar <samanthakumar@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Sean Tranchetti <stranche@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/datagram.c     |  5 +++--
 net/ipv4/udp.c          | 20 ++++++++++++++++++--
 net/ipv6/ip6_checksum.c | 20 ++++++++++++++++++--
 3 files changed, 39 insertions(+), 6 deletions(-)

diff --git a/net/core/datagram.c b/net/core/datagram.c
index 9938952c5c78..16f0eb0970c4 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -808,8 +808,9 @@ int skb_copy_and_csum_datagram_msg(struct sk_buff *skb,
 			return -EINVAL;
 		}
 
-		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE))
-			netdev_rx_csum_fault(skb->dev);
+		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
+		    !skb->csum_complete_sw)
+			netdev_rx_csum_fault(NULL);
 	}
 	return 0;
 fault:
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index a12df801de94..2fe7e2713350 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2124,8 +2124,24 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh,
 	/* Note, we are only interested in != 0 or == 0, thus the
 	 * force to int.
 	 */
-	return (__force int)skb_checksum_init_zero_check(skb, proto, uh->check,
-							 inet_compute_pseudo);
+	err = (__force int)skb_checksum_init_zero_check(skb, proto, uh->check,
+							inet_compute_pseudo);
+	if (err)
+		return err;
+
+	if (skb->ip_summed == CHECKSUM_COMPLETE && !skb->csum_valid) {
+		/* If SW calculated the value, we know it's bad */
+		if (skb->csum_complete_sw)
+			return 1;
+
+		/* HW says the value is bad. Let's validate that.
+		 * skb->csum is no longer the full packet checksum,
+		 * so don't treat it as such.
+		 */
+		skb_checksum_complete_unset(skb);
+	}
+
+	return 0;
 }
 
 /* wrapper for udp_queue_rcv_skb tacking care of csum conversion and
diff --git a/net/ipv6/ip6_checksum.c b/net/ipv6/ip6_checksum.c
index 547515e8450a..377717045f8f 100644
--- a/net/ipv6/ip6_checksum.c
+++ b/net/ipv6/ip6_checksum.c
@@ -88,8 +88,24 @@ int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto)
 	 * Note, we are only interested in != 0 or == 0, thus the
 	 * force to int.
 	 */
-	return (__force int)skb_checksum_init_zero_check(skb, proto, uh->check,
-							 ip6_compute_pseudo);
+	err = (__force int)skb_checksum_init_zero_check(skb, proto, uh->check,
+							ip6_compute_pseudo);
+	if (err)
+		return err;
+
+	if (skb->ip_summed == CHECKSUM_COMPLETE && !skb->csum_valid) {
+		/* If SW calculated the value, we know it's bad */
+		if (skb->csum_complete_sw)
+			return 1;
+
+		/* HW says the value is bad. Let's validate that.
+		 * skb->csum is no longer the full packet checksum,
+		 * so don't treat is as such.
+		 */
+		skb_checksum_complete_unset(skb);
+	}
+
+	return 0;
 }
 EXPORT_SYMBOL(udp6_csum_init);
 
-- 
2.19.1


From a5e8f69c87b3889b501c11d6eded6fd53a6f7a3c Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 18 Oct 2018 19:56:01 +0200
Subject: [PATCH 13/39] r8169: fix NAPI handling under high load

[ Upstream commit 6b839b6cf9eada30b086effb51e5d6076bafc761 ]

rtl_rx() and rtl_tx() are called only if the respective bits are set
in the interrupt status register. Under high load NAPI may not be
able to process all data (work_done == budget) and it will schedule
subsequent calls to the poll callback.
rtl_ack_events() however resets the bits in the interrupt status
register, therefore subsequent calls to rtl8169_poll() won't call
rtl_rx() and rtl_tx() - chip interrupts are still disabled.

Fix this by calling rtl_rx() and rtl_tx() independent of the bits
set in the interrupt status register. Both functions will detect
if there's nothing to do for them.

Fixes: da78dbff2e05 ("r8169: remove work from irq handler.")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 627c5cd8f786..f18087102d40 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -7044,17 +7044,15 @@ static int rtl8169_poll(struct napi_struct *napi, int budget)
 	struct rtl8169_private *tp = container_of(napi, struct rtl8169_private, napi);
 	struct net_device *dev = tp->dev;
 	u16 enable_mask = RTL_EVENT_NAPI | tp->event_slow;
-	int work_done= 0;
+	int work_done;
 	u16 status;
 
 	status = rtl_get_events(tp);
 	rtl_ack_events(tp, status & ~tp->event_slow);
 
-	if (status & RTL_EVENT_NAPI_RX)
-		work_done = rtl_rx(dev, tp, (u32) budget);
+	work_done = rtl_rx(dev, tp, (u32) budget);
 
-	if (status & RTL_EVENT_NAPI_TX)
-		rtl_tx(dev, tp);
+	rtl_tx(dev, tp);
 
 	if (status & tp->event_slow) {
 		enable_mask &= ~tp->event_slow;
-- 
2.19.1


From cb5c1ff95932d8c64b6f896e25f3bbcd5702c6c3 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Mon, 29 Oct 2018 20:36:43 +0000
Subject: [PATCH 14/39] rtnetlink: Disallow FDB configuration for non-Ethernet
 device

[ Upstream commit da71577545a52be3e0e9225a946e5fd79cfab015 ]

When an FDB entry is configured, the address is validated to have the
length of an Ethernet address, but the device for which the address is
configured can be of any type.

The above can result in the use of uninitialized memory when the address
is later compared against existing addresses since 'dev->addr_len' is
used and it may be greater than ETH_ALEN, as with ip6tnl devices.

Fix this by making sure that FDB entries are only configured for
Ethernet devices.

BUG: KMSAN: uninit-value in memcmp+0x11d/0x180 lib/string.c:863
CPU: 1 PID: 4318 Comm: syz-executor998 Not tainted 4.19.0-rc3+ #49
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
Call Trace:
  __dump_stack lib/dump_stack.c:77 [inline]
  dump_stack+0x14b/0x190 lib/dump_stack.c:113
  kmsan_report+0x183/0x2b0 mm/kmsan/kmsan.c:956
  __msan_warning+0x70/0xc0 mm/kmsan/kmsan_instr.c:645
  memcmp+0x11d/0x180 lib/string.c:863
  dev_uc_add_excl+0x165/0x7b0 net/core/dev_addr_lists.c:464
  ndo_dflt_fdb_add net/core/rtnetlink.c:3463 [inline]
  rtnl_fdb_add+0x1081/0x1270 net/core/rtnetlink.c:3558
  rtnetlink_rcv_msg+0xa0b/0x1530 net/core/rtnetlink.c:4715
  netlink_rcv_skb+0x36e/0x5f0 net/netlink/af_netlink.c:2454
  rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:4733
  netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline]
  netlink_unicast+0x1638/0x1720 net/netlink/af_netlink.c:1343
  netlink_sendmsg+0x1205/0x1290 net/netlink/af_netlink.c:1908
  sock_sendmsg_nosec net/socket.c:621 [inline]
  sock_sendmsg net/socket.c:631 [inline]
  ___sys_sendmsg+0xe70/0x1290 net/socket.c:2114
  __sys_sendmsg net/socket.c:2152 [inline]
  __do_sys_sendmsg net/socket.c:2161 [inline]
  __se_sys_sendmsg+0x2a3/0x3d0 net/socket.c:2159
  __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2159
  do_syscall_64+0xb8/0x100 arch/x86/entry/common.c:291
  entry_SYSCALL_64_after_hwframe+0x63/0xe7
RIP: 0033:0x440ee9
Code: e8 cc ab 02 00 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7
48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff
ff 0f 83 bb 0a fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007fff6a93b518 EFLAGS: 00000213 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 0000000000440ee9
RDX: 0000000000000000 RSI: 0000000020000240 RDI: 0000000000000003
RBP: 0000000000000000 R08: 00000000004002c8 R09: 00000000004002c8
R10: 00000000004002c8 R11: 0000000000000213 R12: 000000000000b4b0
R13: 0000000000401ec0 R14: 0000000000000000 R15: 0000000000000000

Uninit was created at:
  kmsan_save_stack_with_flags mm/kmsan/kmsan.c:256 [inline]
  kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:181
  kmsan_kmalloc+0x98/0x100 mm/kmsan/kmsan_hooks.c:91
  kmsan_slab_alloc+0x10/0x20 mm/kmsan/kmsan_hooks.c:100
  slab_post_alloc_hook mm/slab.h:446 [inline]
  slab_alloc_node mm/slub.c:2718 [inline]
  __kmalloc_node_track_caller+0x9e7/0x1160 mm/slub.c:4351
  __kmalloc_reserve net/core/skbuff.c:138 [inline]
  __alloc_skb+0x2f5/0x9e0 net/core/skbuff.c:206
  alloc_skb include/linux/skbuff.h:996 [inline]
  netlink_alloc_large_skb net/netlink/af_netlink.c:1189 [inline]
  netlink_sendmsg+0xb49/0x1290 net/netlink/af_netlink.c:1883
  sock_sendmsg_nosec net/socket.c:621 [inline]
  sock_sendmsg net/socket.c:631 [inline]
  ___sys_sendmsg+0xe70/0x1290 net/socket.c:2114
  __sys_sendmsg net/socket.c:2152 [inline]
  __do_sys_sendmsg net/socket.c:2161 [inline]
  __se_sys_sendmsg+0x2a3/0x3d0 net/socket.c:2159
  __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2159
  do_syscall_64+0xb8/0x100 arch/x86/entry/common.c:291
  entry_SYSCALL_64_after_hwframe+0x63/0xe7

v2:
* Make error message more specific (David)

Fixes: 090096bf3db1 ("net: generic fdb support for drivers without ndo_fdb_<op>")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-and-tested-by: syzbot+3a288d5f5530b901310e@syzkaller.appspotmail.com
Reported-and-tested-by: syzbot+d53ab4e92a1db04110ff@syzkaller.appspotmail.com
Cc: Vlad Yasevich <vyasevich@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 18de39dbdc30..4b25fd14bc5a 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3480,6 +3480,11 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 		return -EINVAL;
 	}
 
+	if (dev->type != ARPHRD_ETHER) {
+		NL_SET_ERR_MSG(extack, "FDB delete only supported for Ethernet devices");
+		return -EINVAL;
+	}
+
 	addr = nla_data(tb[NDA_LLADDR]);
 
 	err = fdb_vid_parse(tb[NDA_VLAN], &vid, extack);
@@ -3584,6 +3589,11 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
 		return -EINVAL;
 	}
 
+	if (dev->type != ARPHRD_ETHER) {
+		NL_SET_ERR_MSG(extack, "FDB add only supported for Ethernet devices");
+		return -EINVAL;
+	}
+
 	addr = nla_data(tb[NDA_LLADDR]);
 
 	err = fdb_vid_parse(tb[NDA_VLAN], &vid, extack);
-- 
2.19.1


From c4db0a4c8e067d2d2295d06bcf4b3ed6bf6d6ecf Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Tue, 16 Oct 2018 15:18:17 -0300
Subject: [PATCH 15/39] sctp: fix race on sctp_id2asoc

[ Upstream commit b336decab22158937975293aea79396525f92bb3 ]

syzbot reported an use-after-free involving sctp_id2asoc.  Dmitry Vyukov
helped to root cause it and it is because of reading the asoc after it
was freed:

        CPU 1                       CPU 2
(working on socket 1)            (working on socket 2)
	                         sctp_association_destroy
sctp_id2asoc
   spin lock
     grab the asoc from idr
   spin unlock
                                   spin lock
				     remove asoc from idr
				   spin unlock
				   free(asoc)
   if asoc->base.sk != sk ... [*]

This can only be hit if trying to fetch asocs from different sockets. As
we have a single IDR for all asocs, in all SCTP sockets, their id is
unique on the system. An application can try to send stuff on an id
that matches on another socket, and the if in [*] will protect from such
usage. But it didn't consider that as that asoc may belong to another
socket, it may be freed in parallel (read: under another socket lock).

We fix it by moving the checks in [*] into the protected region. This
fixes it because the asoc cannot be freed while the lock is held.

Reported-by: syzbot+c7dd55d7aec49d48e49a@syzkaller.appspotmail.com
Acked-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 50ee07cd20c4..b0f50a8e8fc6 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -270,11 +270,10 @@ struct sctp_association *sctp_id2assoc(struct sock *sk, sctp_assoc_t id)
 
 	spin_lock_bh(&sctp_assocs_id_lock);
 	asoc = (struct sctp_association *)idr_find(&sctp_assocs_id, (int)id);
+	if (asoc && (asoc->base.sk != sk || asoc->base.dead))
+		asoc = NULL;
 	spin_unlock_bh(&sctp_assocs_id_lock);
 
-	if (!asoc || (asoc->base.sk != sk) || asoc->base.dead)
-		return NULL;
-
 	return asoc;
 }
 
-- 
2.19.1


From 4899ef12e20315dbfb38cc22046b41efefbfc9f0 Mon Sep 17 00:00:00 2001
From: Tung Nguyen <tung.q.nguyen@dektech.com.au>
Date: Fri, 12 Oct 2018 22:46:55 +0200
Subject: [PATCH 16/39] tipc: fix unsafe rcu locking when accessing publication
 list

[ Upstream commit d3092b2efca1cd1d492d0b08499a2066c5ca8cec ]

The binding table's 'cluster_scope' list is rcu protected to handle
races between threads changing the list and those traversing the list at
the same moment. We have now found that the function named_distribute()
uses the regular list_for_each() macro to traverse the said list.
Likewise, the function tipc_named_withdraw() is removing items from the
same list using the regular list_del() call. When these two functions
execute in parallel we see occasional crashes.

This commit fixes this by adding the missing _rcu() suffixes.

Signed-off-by: Tung Nguyen <tung.q.nguyen@dektech.com.au>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/name_distr.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c
index 51b4b96f89db..3cfeb9df64b0 100644
--- a/net/tipc/name_distr.c
+++ b/net/tipc/name_distr.c
@@ -115,7 +115,7 @@ struct sk_buff *tipc_named_withdraw(struct net *net, struct publication *publ)
 	struct sk_buff *buf;
 	struct distr_item *item;
 
-	list_del(&publ->binding_node);
+	list_del_rcu(&publ->binding_node);
 
 	if (publ->scope == TIPC_NODE_SCOPE)
 		return NULL;
@@ -147,7 +147,7 @@ static void named_distribute(struct net *net, struct sk_buff_head *list,
 			ITEM_SIZE) * ITEM_SIZE;
 	u32 msg_rem = msg_dsz;
 
-	list_for_each_entry(publ, pls, binding_node) {
+	list_for_each_entry_rcu(publ, pls, binding_node) {
 		/* Prepare next buffer: */
 		if (!skb) {
 			skb = named_prepare_buf(net, PUBLICATION, msg_rem,
-- 
2.19.1


From cb0a156dcd14e31a5be7174aacc92207e23ed94c Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 17 Oct 2018 11:44:04 +0200
Subject: [PATCH 17/39] udp6: fix encap return code for resubmitting

[ Upstream commit 84dad55951b0d009372ec21760b650634246e144 ]

The commit eb63f2964dbe ("udp6: add missing checks on edumux packet
processing") used the same return code convention of the ipv4 counterpart,
but ipv6 uses the opposite one: positive values means resubmit.

This change addresses the issue, using positive return value for
resubmitting. Also update the related comment, which was broken, too.

Fixes: eb63f2964dbe ("udp6: add missing checks on edumux packet processing")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/udp.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 39d0cab919bb..4f2c7a196365 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -762,11 +762,9 @@ static int udp6_unicast_rcv_skb(struct sock *sk, struct sk_buff *skb,
 
 	ret = udpv6_queue_rcv_skb(sk, skb);
 
-	/* a return value > 0 means to resubmit the input, but
-	 * it wants the return to be -protocol, or 0
-	 */
+	/* a return value > 0 means to resubmit the input */
 	if (ret > 0)
-		return -ret;
+		return ret;
 	return 0;
 }
 
-- 
2.19.1


From b4f12930c45611eeedbe2951b090ecfdcf1d99df Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Tue, 30 Oct 2018 14:10:49 +0800
Subject: [PATCH 18/39] vhost: Fix Spectre V1 vulnerability

[ Upstream commit ff002269a4ee9c769dbf9365acef633ebcbd6cbe ]

The idx in vhost_vring_ioctl() was controlled by userspace, hence a
potential exploitation of the Spectre variant 1 vulnerability.

Fixing this by sanitizing idx before using it to index d->vqs.

Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/vhost.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 560ed8711706..c4424cbd9943 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -30,6 +30,7 @@
 #include <linux/sched/mm.h>
 #include <linux/sched/signal.h>
 #include <linux/interval_tree_generic.h>
+#include <linux/nospec.h>
 
 #include "vhost.h"
 
@@ -1362,6 +1363,7 @@ long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *arg
 	if (idx >= d->nvqs)
 		return -ENOBUFS;
 
+	idx = array_index_nospec(idx, d->nvqs);
 	vq = d->vqs[idx];
 
 	mutex_lock(&vq->mutex);
-- 
2.19.1


From 563dd93163a6fca31f1e72b15343c3f7d8a8cb9a Mon Sep 17 00:00:00 2001
From: Ake Koomsin <ake@igel.co.jp>
Date: Wed, 17 Oct 2018 19:44:12 +0900
Subject: [PATCH 19/39] virtio_net: avoid using netif_tx_disable() for
 serializing tx routine

[ Upstream commit 05c998b738fdd3e5d6a257bcacc8f34b6284d795 ]

Commit 713a98d90c5e ("virtio-net: serialize tx routine during reset")
introduces netif_tx_disable() after netif_device_detach() in order to
avoid use-after-free of tx queues. However, there are two issues.

1) Its operation is redundant with netif_device_detach() in case the
   interface is running.
2) In case of the interface is not running before suspending and
   resuming, the tx does not get resumed by netif_device_attach().
   This results in losing network connectivity.

It is better to use netif_tx_lock_bh()/netif_tx_unlock_bh() instead for
serializing tx routine during reset. This also preserves the symmetry
of netif_device_detach() and netif_device_attach().

Fixes commit 713a98d90c5e ("virtio-net: serialize tx routine during reset")
Signed-off-by: Ake Koomsin <ake@igel.co.jp>
Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 2b6ec927809e..500e2d8f10bc 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2162,8 +2162,9 @@ static void virtnet_freeze_down(struct virtio_device *vdev)
 	/* Make sure no work handler is accessing the device */
 	flush_work(&vi->config_work);
 
+	netif_tx_lock_bh(vi->dev);
 	netif_device_detach(vi->dev);
-	netif_tx_disable(vi->dev);
+	netif_tx_unlock_bh(vi->dev);
 	cancel_delayed_work_sync(&vi->refill);
 
 	if (netif_running(vi->dev)) {
@@ -2199,7 +2200,9 @@ static int virtnet_restore_up(struct virtio_device *vdev)
 		}
 	}
 
+	netif_tx_lock_bh(vi->dev);
 	netif_device_attach(vi->dev);
+	netif_tx_unlock_bh(vi->dev);
 	return err;
 }
 
-- 
2.19.1


From d365aa0e50cc4b2673b623ae75c322229132e96d Mon Sep 17 00:00:00 2001
From: Wenwen Wang <wang6495@umn.edu>
Date: Mon, 8 Oct 2018 10:49:35 -0500
Subject: [PATCH 20/39] ethtool: fix a privilege escalation bug

[ Upstream commit 58f5bbe331c566f49c9559568f982202a278aa78 ]

In dev_ethtool(), the eth command 'ethcmd' is firstly copied from the
use-space buffer 'useraddr' and checked to see whether it is
ETHTOOL_PERQUEUE. If yes, the sub-command 'sub_cmd' is further copied from
the user space. Otherwise, 'sub_cmd' is the same as 'ethcmd'. Next,
according to 'sub_cmd', a permission check is enforced through the function
ns_capable(). For example, the permission check is required if 'sub_cmd' is
ETHTOOL_SCOALESCE, but it is not necessary if 'sub_cmd' is
ETHTOOL_GCOALESCE, as suggested in the comment "Allow some commands to be
done by anyone". The following execution invokes different handlers
according to 'ethcmd'. Specifically, if 'ethcmd' is ETHTOOL_PERQUEUE,
ethtool_set_per_queue() is called. In ethtool_set_per_queue(), the kernel
object 'per_queue_opt' is copied again from the user-space buffer
'useraddr' and 'per_queue_opt.sub_command' is used to determine which
operation should be performed. Given that the buffer 'useraddr' is in the
user space, a malicious user can race to change the sub-command between the
two copies. In particular, the attacker can supply ETHTOOL_PERQUEUE and
ETHTOOL_GCOALESCE to bypass the permission check in dev_ethtool(). Then
before ethtool_set_per_queue() is called, the attacker changes
ETHTOOL_GCOALESCE to ETHTOOL_SCOALESCE. In this way, the attacker can
bypass the permission check and execute ETHTOOL_SCOALESCE.

This patch enforces a check in ethtool_set_per_queue() after the second
copy from 'useraddr'. If the sub-command is different from the one obtained
in the first copy in dev_ethtool(), an error code EINVAL will be returned.

Fixes: f38d138a7da6 ("net/ethtool: support set coalesce per queue")
Signed-off-by: Wenwen Wang <wang6495@umn.edu>
Reviewed-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/ethtool.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 6c04f1bf377d..548d0e615bc7 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -2461,13 +2461,17 @@ static int ethtool_set_per_queue_coalesce(struct net_device *dev,
 	return ret;
 }
 
-static int ethtool_set_per_queue(struct net_device *dev, void __user *useraddr)
+static int ethtool_set_per_queue(struct net_device *dev,
+				 void __user *useraddr, u32 sub_cmd)
 {
 	struct ethtool_per_queue_op per_queue_opt;
 
 	if (copy_from_user(&per_queue_opt, useraddr, sizeof(per_queue_opt)))
 		return -EFAULT;
 
+	if (per_queue_opt.sub_command != sub_cmd)
+		return -EINVAL;
+
 	switch (per_queue_opt.sub_command) {
 	case ETHTOOL_GCOALESCE:
 		return ethtool_get_per_queue_coalesce(dev, useraddr, &per_queue_opt);
@@ -2838,7 +2842,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
 		rc = ethtool_get_phy_stats(dev, useraddr);
 		break;
 	case ETHTOOL_PERQUEUE:
-		rc = ethtool_set_per_queue(dev, useraddr);
+		rc = ethtool_set_per_queue(dev, useraddr, sub_cmd);
 		break;
 	case ETHTOOL_GLINKSETTINGS:
 		rc = ethtool_get_link_ksettings(dev, useraddr);
-- 
2.19.1


From 020d22a098404a43c7d3726465276c0ee97c003b Mon Sep 17 00:00:00 2001
From: Tobias Jungel <tobias.jungel@gmail.com>
Date: Sun, 28 Oct 2018 12:54:10 +0100
Subject: [PATCH 21/39] bonding: fix length of actor system

[ Upstream commit 414dd6fb9a1a1b59983aea7bf0f79f0085ecc5b8 ]

The attribute IFLA_BOND_AD_ACTOR_SYSTEM is sent to user space having the
length of sizeof(bond->params.ad_actor_system) which is 8 byte. This
patch aligns the length to ETH_ALEN to have the same MAC address exposed
as using sysfs.

Fixes: f87fda00b6ed2 ("bonding: prevent out of bound accesses")
Signed-off-by: Tobias Jungel <tobias.jungel@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_netlink.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index 9697977b80f0..6b9ad8673218 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -638,8 +638,7 @@ static int bond_fill_info(struct sk_buff *skb,
 				goto nla_put_failure;
 
 			if (nla_put(skb, IFLA_BOND_AD_ACTOR_SYSTEM,
-				    sizeof(bond->params.ad_actor_system),
-				    &bond->params.ad_actor_system))
+				    ETH_ALEN, &bond->params.ad_actor_system))
 				goto nla_put_failure;
 		}
 		if (!bond_3ad_get_active_agg_info(bond, &info)) {
-- 
2.19.1


From 71af4bebcba1029f782f9f8b061c296127a25b0d Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Thu, 18 Oct 2018 21:25:07 +0200
Subject: [PATCH 22/39] ip6_tunnel: Fix encapsulation layout

[ Upstream commit d4d576f5ab7edcb757bb33e6a5600666a0b1232d ]

Commit 058214a4d1df ("ip6_tun: Add infrastructure for doing
encapsulation") added the ip6_tnl_encap() call in ip6_tnl_xmit(), before
the call to ipv6_push_frag_opts() to append the IPv6 Tunnel Encapsulation
Limit option (option 4, RFC 2473, par. 5.1) to the outer IPv6 header.

As long as the option didn't actually end up in generated packets, this
wasn't an issue. Then commit 89a23c8b528b ("ip6_tunnel: Fix missing tunnel
encapsulation limit option") fixed sending of this option, and the
resulting layout, e.g. for FoU, is:

.-------------------.------------.----------.-------------------.----- - -
| Outer IPv6 Header | UDP header | Option 4 | Inner IPv6 Header | Payload
'-------------------'------------'----------'-------------------'----- - -

Needless to say, FoU and GUE (at least) won't work over IPv6. The option
is appended by default, and I couldn't find a way to disable it with the
current iproute2.

Turn this into a more reasonable:

.-------------------.----------.------------.-------------------.----- - -
| Outer IPv6 Header | Option 4 | UDP header | Inner IPv6 Header | Payload
'-------------------'----------'------------'-------------------'----- - -

With this, and with 84dad55951b0 ("udp6: fix encap return code for
resubmitting"), FoU and GUE work again over IPv6.

Fixes: 058214a4d1df ("ip6_tun: Add infrastructure for doing encapsulation")
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index f5b5b0574a2d..009b508127e6 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1184,10 +1184,6 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 	}
 	skb_dst_set(skb, dst);
 
-	if (encap_limit >= 0) {
-		init_tel_txopt(&opt, encap_limit);
-		ipv6_push_frag_opts(skb, &opt.ops, &proto);
-	}
 	hop_limit = hop_limit ? : ip6_dst_hoplimit(dst);
 
 	/* Calculate max headroom for all the headers and adjust
@@ -1202,6 +1198,11 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 	if (err)
 		return err;
 
+	if (encap_limit >= 0) {
+		init_tel_txopt(&opt, encap_limit);
+		ipv6_push_frag_opts(skb, &opt.ops, &proto);
+	}
+
 	skb_push(skb, sizeof(struct ipv6hdr));
 	skb_reset_network_header(skb);
 	ipv6h = ipv6_hdr(skb);
-- 
2.19.1


From 0cb7e2e139d70ea50791ac967e11499c66031ad2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jaime=20Caama=C3=B1o=20Ruiz?= <jcaamano@suse.com>
Date: Wed, 31 Oct 2018 18:52:03 +0100
Subject: [PATCH 23/39] openvswitch: Fix push/pop ethernet validation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 46ebe2834ba5b541f28ee72e556a3fed42c47570 ]

When there are both pop and push ethernet header actions among the
actions to be applied to a packet, an unexpected EINVAL (Invalid
argument) error is obtained. This is due to mac_proto not being reset
correctly when those actions are validated.

Reported-at:
https://mail.openvswitch.org/pipermail/ovs-discuss/2018-October/047554.html
Fixes: 91820da6ae85 ("openvswitch: add Ethernet push and pop actions")
Signed-off-by: Jaime Caamaño Ruiz <jcaamano@suse.com>
Tested-by: Greg Rose <gvrose8192@gmail.com>
Reviewed-by: Greg Rose <gvrose8192@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/flow_netlink.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 492ab0c36f7c..8b1ba43b1ece 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -2990,7 +2990,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 			 * is already present */
 			if (mac_proto != MAC_PROTO_NONE)
 				return -EINVAL;
-			mac_proto = MAC_PROTO_NONE;
+			mac_proto = MAC_PROTO_ETHERNET;
 			break;
 
 		case OVS_ACTION_ATTR_POP_ETH:
@@ -2998,7 +2998,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 				return -EINVAL;
 			if (vlan_tci & htons(VLAN_TAG_PRESENT))
 				return -EINVAL;
-			mac_proto = MAC_PROTO_ETHERNET;
+			mac_proto = MAC_PROTO_NONE;
 			break;
 
 		case OVS_ACTION_ATTR_PUSH_NSH:
-- 
2.19.1


From 8b0986a46a91256d4ff2ba838c6c5fb65d0726f0 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Wed, 17 Oct 2018 22:34:34 +0300
Subject: [PATCH 24/39] net: ipmr: fix unresolved entry dumps

[ Upstream commit eddf016b910486d2123675a6b5fd7d64f77cdca8 ]

If the skb space ends in an unresolved entry while dumping we'll miss
some unresolved entries. The reason is due to zeroing the entry counter
between dumping resolved and unresolved mfc entries. We should just
keep counting until the whole table is dumped and zero when we move to
the next as we have a separate table counter.

Reported-by: Colin Ian King <colin.king@canonical.com>
Fixes: 8fb472c09b9d ("ipmr: improve hash scalability")
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ipmr_base.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c
index cafb0506c8c9..33be09791c74 100644
--- a/net/ipv4/ipmr_base.c
+++ b/net/ipv4/ipmr_base.c
@@ -295,8 +295,6 @@ int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb,
 next_entry:
 			e++;
 		}
-		e = 0;
-		s_e = 0;
 
 		spin_lock_bh(lock);
 		list_for_each_entry(mfc, &mrt->mfc_unres_queue, list) {
-- 
2.19.1


From aaae1e4ff5edb2f41bd06fd41042bf7533ba6e9c Mon Sep 17 00:00:00 2001
From: Huy Nguyen <huyn@mellanox.com>
Date: Tue, 11 Sep 2018 14:58:22 -0500
Subject: [PATCH 25/39] net/mlx5: Take only bit 24-26 of wqe.pftype_wq for page
 fault type

[ Upstream commit a48bc513159d4767f9988f0d857b2b0c38a4d614 ]

The HW spec defines only bits 24-26 of pftype_wq as the page fault type,
use the required mask to ensure that.

Fixes: d9aaed838765 ("{net,IB}/mlx5: Refactor page fault handling")
Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 406c23862f5f..01ccc8201052 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -269,7 +269,7 @@ static void eq_pf_process(struct mlx5_eq *eq)
 		case MLX5_PFAULT_SUBTYPE_WQE:
 			/* WQE based event */
 			pfault->type =
-				be32_to_cpu(pf_eqe->wqe.pftype_wq) >> 24;
+				(be32_to_cpu(pf_eqe->wqe.pftype_wq) >> 24) & 0x7;
 			pfault->token =
 				be32_to_cpu(pf_eqe->wqe.token);
 			pfault->wqe.wq_num =
-- 
2.19.1


From 82acfc6b5fa2ed6eecd5848afac52acf81d0d04b Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 11 Oct 2018 15:06:33 -0700
Subject: [PATCH 26/39] net: bcmgenet: Poll internal PHY for GENETv5

[ Upstream commit 64bd9c8135751b561f27edaaffe93d07093f81af ]

On GENETv5, there is a hardware issue which prevents the GENET hardware
from generating a link UP interrupt when the link is operating at
10Mbits/sec. Since we do not have any way to configure the link
detection logic, fallback to polling in that case.

Fixes: 421380856d9c ("net: bcmgenet: add support for the GENETv5 hardware")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmmii.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index 4241ae928d4a..34af5f1569c8 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -321,9 +321,12 @@ int bcmgenet_mii_probe(struct net_device *dev)
 	phydev->advertising = phydev->supported;
 
 	/* The internal PHY has its link interrupts routed to the
-	 * Ethernet MAC ISRs
+	 * Ethernet MAC ISRs. On GENETv5 there is a hardware issue
+	 * that prevents the signaling of link UP interrupts when
+	 * the link operates at 10Mbps, so fallback to polling for
+	 * those versions of GENET.
 	 */
-	if (priv->internal_phy)
+	if (priv->internal_phy && !GENET_IS_V5(priv))
 		dev->phydev->irq = PHY_IGNORE_INTERRUPT;
 
 	return 0;
-- 
2.19.1


From ff05ed2b774d10b0da1cb51661d9634f895142c1 Mon Sep 17 00:00:00 2001
From: Phil Sutter <phil@nwl.cc>
Date: Thu, 18 Oct 2018 10:34:26 +0200
Subject: [PATCH 27/39] net: sched: Fix for duplicate class dump

[ Upstream commit 3c53ed8fef6881a864f0ee8240ed2793ef73ad0d ]

When dumping classes by parent, kernel would return classes twice:

| # tc qdisc add dev lo root prio
| # tc class show dev lo
| class prio 8001:1 parent 8001:
| class prio 8001:2 parent 8001:
| class prio 8001:3 parent 8001:
| # tc class show dev lo parent 8001:
| class prio 8001:1 parent 8001:
| class prio 8001:2 parent 8001:
| class prio 8001:3 parent 8001:
| class prio 8001:1 parent 8001:
| class prio 8001:2 parent 8001:
| class prio 8001:3 parent 8001:

This comes from qdisc_match_from_root() potentially returning the root
qdisc itself if its handle matched. Though in that case, root's classes
were already dumped a few lines above.

Fixes: cb395b2010879 ("net: sched: optimize class dumps")
Signed-off-by: Phil Sutter <phil@nwl.cc>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_api.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 99cc25aae503..57f71765febe 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -2052,7 +2052,8 @@ static int tc_dump_tclass_root(struct Qdisc *root, struct sk_buff *skb,
 
 	if (tcm->tcm_parent) {
 		q = qdisc_match_from_root(root, TC_H_MAJ(tcm->tcm_parent));
-		if (q && tc_dump_tclass_qdisc(q, skb, tcm, cb, t_p, s_t) < 0)
+		if (q && q != root &&
+		    tc_dump_tclass_qdisc(q, skb, tcm, cb, t_p, s_t) < 0)
 			return -1;
 		return 0;
 	}
-- 
2.19.1


From 404db6a2400b17d5e850f8867dfba19998b59242 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Wed, 10 Oct 2018 22:00:58 +0200
Subject: [PATCH 28/39] net/sched: cls_api: add missing validation of netlink
 attributes

[ Upstream commit e331473fee3d500bb0d2582a1fe598df3326d8cd ]

Similarly to what has been done in 8b4c3cdd9dd8 ("net: sched: Add policy
validation for tc attributes"), fix classifier code to add validation of
TCA_CHAIN and TCA_KIND netlink attributes.

tested with:
 # ./tdc.py -c filter

v2: Let sch_api and cls_api share nla_policy they have in common, thanks
    to David Ahern.
v3: Avoid EXPORT_SYMBOL(), as validation of those attributes is not done
    by TC modules, thanks to Cong Wang.
    While at it, restore the 'Delete / get qdisc' comment to its orginal
    position, just above tc_get_qdisc() function prototype.

Fixes: 5bc1701881e39 ("net: sched: introduce multichain support for filters")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index f74513a7c7a8..c855fd045a3c 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -31,6 +31,8 @@
 #include <net/pkt_sched.h>
 #include <net/pkt_cls.h>
 
+extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1];
+
 /* The list of all installed classifier types */
 static LIST_HEAD(tcf_proto_base);
 
@@ -1083,7 +1085,7 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
 replay:
 	tp_created = 0;
 
-	err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL, extack);
+	err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, rtm_tca_policy, extack);
 	if (err < 0)
 		return err;
 
@@ -1226,7 +1228,7 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
 	if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
-	err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL, extack);
+	err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, rtm_tca_policy, extack);
 	if (err < 0)
 		return err;
 
@@ -1334,7 +1336,7 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
 	void *fh = NULL;
 	int err;
 
-	err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL, extack);
+	err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, rtm_tca_policy, extack);
 	if (err < 0)
 		return err;
 
@@ -1488,7 +1490,8 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
 	if (nlmsg_len(cb->nlh) < sizeof(*tcm))
 		return skb->len;
 
-	err = nlmsg_parse(cb->nlh, sizeof(*tcm), tca, TCA_MAX, NULL, NULL);
+	err = nlmsg_parse(cb->nlh, sizeof(*tcm), tca, TCA_MAX, rtm_tca_policy,
+			  NULL);
 	if (err)
 		return err;
 
-- 
2.19.1


From a3d3992945f52ee00236c53ea1285148d394e707 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 24 Oct 2018 13:58:39 -0700
Subject: [PATCH 29/39] net/ipv6: Allow onlink routes to have a device mismatch
 if it is the default route

[ Upstream commit 4ed591c8ab44e711e56b8e021ffaf4f407c045f5 ]

The intent of ip6_route_check_nh_onlink is to make sure the gateway
given for an onlink route is not actually on a connected route for
a different interface (e.g., 2001:db8:1::/64 is on dev eth1 and then
an onlink route has a via 2001:db8:1::1 dev eth2). If the gateway
lookup hits the default route then it most likely will be a different
interface than the onlink route which is ok.

Update ip6_route_check_nh_onlink to disregard the device mismatch
if the gateway lookup hits the default route. Turns out the existing
onlink tests are passing because there is no default route or it is
an unreachable default, so update the onlink tests to have a default
route other than unreachable.

Fixes: fc1e64e1092f6 ("net/ipv6: Add support for onlink flag")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c                                |  2 ++
 tools/testing/selftests/net/fib-onlink-tests.sh | 14 +++++++-------
 2 files changed, 9 insertions(+), 7 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index d9e8960e58d3..a243d5249b51 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2792,6 +2792,8 @@ static int ip6_route_check_nh_onlink(struct net *net,
 	grt = ip6_nh_lookup_table(net, cfg, gw_addr, tbid, 0);
 	if (grt) {
 		if (!grt->dst.error &&
+		    /* ignore match if it is the default route */
+		    grt->from && !ipv6_addr_any(&grt->from->fib6_dst.addr) &&
 		    (grt->rt6i_flags & flags || dev != grt->dst.dev)) {
 			NL_SET_ERR_MSG(extack,
 				       "Nexthop has invalid gateway or device mismatch");
diff --git a/tools/testing/selftests/net/fib-onlink-tests.sh b/tools/testing/selftests/net/fib-onlink-tests.sh
index 3991ad1a368d..864f865eee55 100755
--- a/tools/testing/selftests/net/fib-onlink-tests.sh
+++ b/tools/testing/selftests/net/fib-onlink-tests.sh
@@ -167,8 +167,8 @@ setup()
 	# add vrf table
 	ip li add ${VRF} type vrf table ${VRF_TABLE}
 	ip li set ${VRF} up
-	ip ro add table ${VRF_TABLE} unreachable default
-	ip -6 ro add table ${VRF_TABLE} unreachable default
+	ip ro add table ${VRF_TABLE} unreachable default metric 8192
+	ip -6 ro add table ${VRF_TABLE} unreachable default metric 8192
 
 	# create test interfaces
 	ip li add ${NETIFS[p1]} type veth peer name ${NETIFS[p2]}
@@ -185,20 +185,20 @@ setup()
 	for n in 1 3 5 7; do
 		ip li set ${NETIFS[p${n}]} up
 		ip addr add ${V4ADDRS[p${n}]}/24 dev ${NETIFS[p${n}]}
-		ip addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]}
+		ip addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} nodad
 	done
 
 	# move peer interfaces to namespace and add addresses
 	for n in 2 4 6 8; do
 		ip li set ${NETIFS[p${n}]} netns ${PEER_NS} up
 		ip -netns ${PEER_NS} addr add ${V4ADDRS[p${n}]}/24 dev ${NETIFS[p${n}]}
-		ip -netns ${PEER_NS} addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]}
+		ip -netns ${PEER_NS} addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} nodad
 	done
 
-	set +e
+	ip -6 ro add default via ${V6ADDRS[p3]/::[0-9]/::64}
+	ip -6 ro add table ${VRF_TABLE} default via ${V6ADDRS[p7]/::[0-9]/::64}
 
-	# let DAD complete - assume default of 1 probe
-	sleep 1
+	set +e
 }
 
 cleanup()
-- 
2.19.1


From 49a116c57e58a409c0f69e7a8dce4b201b9baab9 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 17 Oct 2018 21:11:27 +0800
Subject: [PATCH 30/39] sctp: fix the data size calculation in sctp_data_size

[ Upstream commit 5660b9d9d6a29c2c3cc12f62ae44bfb56b0a15a9 ]

sctp data size should be calculated by subtracting data chunk header's
length from chunk_hdr->length, not just data header.

Fixes: 668c9beb9020 ("sctp: implement assign_number for sctp_stream_interleave")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/sm.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h
index 5ef1bad81ef5..9e3d32746430 100644
--- a/include/net/sctp/sm.h
+++ b/include/net/sctp/sm.h
@@ -347,7 +347,7 @@ static inline __u16 sctp_data_size(struct sctp_chunk *chunk)
 	__u16 size;
 
 	size = ntohs(chunk->chunk_hdr->length);
-	size -= sctp_datahdr_len(&chunk->asoc->stream);
+	size -= sctp_datachk_len(&chunk->asoc->stream);
 
 	return size;
 }
-- 
2.19.1


From 9b44187e227a60c94b35177ab3dec48fcc9b2d40 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 17 Oct 2018 03:06:12 +0800
Subject: [PATCH 31/39] sctp: not free the new asoc when sctp_wait_for_connect
 returns err

[ Upstream commit c863850ce22e1b0bb365d49cadf51f4765153ae4 ]

When sctp_wait_for_connect is called to wait for connect ready
for sp->strm_interleave in sctp_sendmsg_to_asoc, a panic could
be triggered if cpu is scheduled out and the new asoc is freed
elsewhere, as it will return err and later the asoc gets freed
again in sctp_sendmsg.

[  285.840764] list_del corruption, ffff9f0f7b284078->next is LIST_POISON1 (dead000000000100)
[  285.843590] WARNING: CPU: 1 PID: 8861 at lib/list_debug.c:47 __list_del_entry_valid+0x50/0xa0
[  285.846193] Kernel panic - not syncing: panic_on_warn set ...
[  285.846193]
[  285.848206] CPU: 1 PID: 8861 Comm: sctp_ndata Kdump: loaded Not tainted 4.19.0-rc7.label #584
[  285.850559] Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
[  285.852164] Call Trace:
...
[  285.872210]  ? __list_del_entry_valid+0x50/0xa0
[  285.872894]  sctp_association_free+0x42/0x2d0 [sctp]
[  285.873612]  sctp_sendmsg+0x5a4/0x6b0 [sctp]
[  285.874236]  sock_sendmsg+0x30/0x40
[  285.874741]  ___sys_sendmsg+0x27a/0x290
[  285.875304]  ? __switch_to_asm+0x34/0x70
[  285.875872]  ? __switch_to_asm+0x40/0x70
[  285.876438]  ? ptep_set_access_flags+0x2a/0x30
[  285.877083]  ? do_wp_page+0x151/0x540
[  285.877614]  __sys_sendmsg+0x58/0xa0
[  285.878138]  do_syscall_64+0x55/0x180
[  285.878669]  entry_SYSCALL_64_after_hwframe+0x44/0xa9

This is a similar issue with the one fixed in Commit ca3af4dd28cf
("sctp: do not free asoc when it is already dead in sctp_sendmsg").
But this one can't be fixed by returning -ESRCH for the dead asoc
in sctp_wait_for_connect, as it will break sctp_connect's return
value to users.

This patch is to simply set err to -ESRCH before it returns to
sctp_sendmsg when any err is returned by sctp_wait_for_connect
for sp->strm_interleave, so that no asoc would be freed due to
this.

When users see this error, they will know the packet hasn't been
sent. And it also makes sense to not free asoc because waiting
connect fails, like the second call for sctp_wait_for_connect in
sctp_sendmsg_to_asoc.

Fixes: 668c9beb9020 ("sctp: implement assign_number for sctp_stream_interleave")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index b0f50a8e8fc6..9d903b870790 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1939,8 +1939,10 @@ static int sctp_sendmsg_to_asoc(struct sctp_association *asoc,
 		if (sp->strm_interleave) {
 			timeo = sock_sndtimeo(sk, 0);
 			err = sctp_wait_for_connect(asoc, &timeo);
-			if (err)
+			if (err) {
+				err = -ESRCH;
 				goto err;
+			}
 		} else {
 			wait_connect = true;
 		}
-- 
2.19.1


From 54db0d70f9399872892b3867a31f907287ece972 Mon Sep 17 00:00:00 2001
From: Talat Batheesh <talatb@mellanox.com>
Date: Thu, 30 Aug 2018 16:31:52 +0300
Subject: [PATCH 32/39] net/mlx5: Fix memory leak when setting fpga ipsec caps

[ Upstream commit fd7e848077c1a466b9187537adce16658f7cb94b ]

Allocated memory for context should be freed once
finished working with it.

Fixes: d6c4f0298cec ("net/mlx5: Refactor accel IPSec code")
Signed-off-by: Talat Batheesh <talatb@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
index 5645a4facad2..b8ee9101c506 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
@@ -245,7 +245,7 @@ static void *mlx5_fpga_ipsec_cmd_exec(struct mlx5_core_dev *mdev,
 		return ERR_PTR(res);
 	}
 
-	/* Context will be freed by wait func after completion */
+	/* Context should be freed by the caller after completion. */
 	return context;
 }
 
@@ -418,10 +418,8 @@ static int mlx5_fpga_ipsec_set_caps(struct mlx5_core_dev *mdev, u32 flags)
 	cmd.cmd = htonl(MLX5_FPGA_IPSEC_CMD_OP_SET_CAP);
 	cmd.flags = htonl(flags);
 	context = mlx5_fpga_ipsec_cmd_exec(mdev, &cmd, sizeof(cmd));
-	if (IS_ERR(context)) {
-		err = PTR_ERR(context);
-		goto out;
-	}
+	if (IS_ERR(context))
+		return PTR_ERR(context);
 
 	err = mlx5_fpga_ipsec_cmd_wait(context);
 	if (err)
@@ -435,6 +433,7 @@ static int mlx5_fpga_ipsec_set_caps(struct mlx5_core_dev *mdev, u32 flags)
 	}
 
 out:
+	kfree(context);
 	return err;
 }
 
-- 
2.19.1


From 90b568480c169bc8dfc85e95962d382961cd196d Mon Sep 17 00:00:00 2001
From: Karsten Graul <kgraul@linux.ibm.com>
Date: Thu, 25 Oct 2018 13:25:28 +0200
Subject: [PATCH 33/39] net/smc: fix smc_buf_unuse to use the lgr pointer

[ Upstream commit fb692ec4117f6fd25044cfb5720d6b79d400dc65 ]

The pointer to the link group is unset in the smc connection structure
right before the call to smc_buf_unuse. Provide the lgr pointer to
smc_buf_unuse explicitly.
And move the call to smc_lgr_schedule_free_work to the end of
smc_conn_free.

Fixes: a6920d1d130c ("net/smc: handle unregistered buffers")
Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/smc_core.c | 23 +++++++++++------------
 1 file changed, 11 insertions(+), 12 deletions(-)

diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index add82b0266f3..3be95f77ec7f 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -114,22 +114,17 @@ static void __smc_lgr_unregister_conn(struct smc_connection *conn)
 	sock_put(&smc->sk); /* sock_hold in smc_lgr_register_conn() */
 }
 
-/* Unregister connection and trigger lgr freeing if applicable
+/* Unregister connection from lgr
  */
 static void smc_lgr_unregister_conn(struct smc_connection *conn)
 {
 	struct smc_link_group *lgr = conn->lgr;
-	int reduced = 0;
 
 	write_lock_bh(&lgr->conns_lock);
 	if (conn->alert_token_local) {
-		reduced = 1;
 		__smc_lgr_unregister_conn(conn);
 	}
 	write_unlock_bh(&lgr->conns_lock);
-	if (!reduced || lgr->conns_num)
-		return;
-	smc_lgr_schedule_free_work(lgr);
 }
 
 static void smc_lgr_free_work(struct work_struct *work)
@@ -238,7 +233,8 @@ static int smc_lgr_create(struct smc_sock *smc,
 	return rc;
 }
 
-static void smc_buf_unuse(struct smc_connection *conn)
+static void smc_buf_unuse(struct smc_connection *conn,
+			  struct smc_link_group *lgr)
 {
 	if (conn->sndbuf_desc)
 		conn->sndbuf_desc->used = 0;
@@ -248,8 +244,6 @@ static void smc_buf_unuse(struct smc_connection *conn)
 			conn->rmb_desc->used = 0;
 		} else {
 			/* buf registration failed, reuse not possible */
-			struct smc_link_group *lgr = conn->lgr;
-
 			write_lock_bh(&lgr->rmbs_lock);
 			list_del(&conn->rmb_desc->list);
 			write_unlock_bh(&lgr->rmbs_lock);
@@ -262,11 +256,16 @@ static void smc_buf_unuse(struct smc_connection *conn)
 /* remove a finished connection from its link group */
 void smc_conn_free(struct smc_connection *conn)
 {
-	if (!conn->lgr)
+	struct smc_link_group *lgr = conn->lgr;
+
+	if (!lgr)
 		return;
 	smc_cdc_tx_dismiss_slots(conn);
-	smc_lgr_unregister_conn(conn);
-	smc_buf_unuse(conn);
+	smc_lgr_unregister_conn(conn);		/* unsets conn->lgr */
+	smc_buf_unuse(conn, lgr);		/* allow buffer reuse */
+
+	if (!lgr->conns_num)
+		smc_lgr_schedule_free_work(lgr);
 }
 
 static void smc_link_clear(struct smc_link *lnk)
-- 
2.19.1


From 0cfdf66f29ade9ec238f5bb029fb63cc85acbec4 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 29 Oct 2018 14:26:14 +0000
Subject: [PATCH 34/39] mlxsw: spectrum_switchdev: Don't ignore deletions of
 learned MACs

[ Upstream commit ad0b9d94182be8356978d220c82f9837cffeb7a9 ]

Demands to remove FDB entries should be honored even if the FDB entry in
question was originally learned, and not added by the user. Therefore
ignore the added_by_user datum for SWITCHDEV_FDB_DEL_TO_DEVICE.

Fixes: 816a3bed9549 ("switchdev: Add fdb.added_by_user to switchdev notifications")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Suggested-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 6cb43dda8232..9883e48d8a21 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -2307,8 +2307,6 @@ static void mlxsw_sp_switchdev_event_work(struct work_struct *work)
 		break;
 	case SWITCHDEV_FDB_DEL_TO_DEVICE:
 		fdb_info = &switchdev_work->fdb_info;
-		if (!fdb_info->added_by_user)
-			break;
 		mlxsw_sp_port_fdb_set(mlxsw_sp_port, fdb_info, false);
 		break;
 	case SWITCHDEV_FDB_ADD_TO_BRIDGE: /* fall through */
-- 
2.19.1


From 84ca2d2ec7caaf149b8289d8f5a4c75c8be1c609 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Wed, 17 Oct 2018 00:35:10 +0900
Subject: [PATCH 35/39] net: bpfilter: use get_pid_task instead of pid_task

[ Upstream commit 84258438e8ce12d6888b68a1238bba9cb25307e2 ]

pid_task() dereferences rcu protected tasks array.
But there is no rcu_read_lock() in shutdown_umh() routine so that
rcu_read_lock() is needed.
get_pid_task() is wrapper function of pid_task. it holds rcu_read_lock()
then calls pid_task(). if task isn't NULL, it increases reference count
of task.

test commands:
   %modprobe bpfilter
   %modprobe -rv bpfilter

splat looks like:
[15102.030932] =============================
[15102.030957] WARNING: suspicious RCU usage
[15102.030985] 4.19.0-rc7+ #21 Not tainted
[15102.031010] -----------------------------
[15102.031038] kernel/pid.c:330 suspicious rcu_dereference_check() usage!
[15102.031063]
	       other info that might help us debug this:

[15102.031332]
	       rcu_scheduler_active = 2, debug_locks = 1
[15102.031363] 1 lock held by modprobe/1570:
[15102.031389]  #0: 00000000580ef2b0 (bpfilter_lock){+.+.}, at: stop_umh+0x13/0x52 [bpfilter]
[15102.031552]
               stack backtrace:
[15102.031583] CPU: 1 PID: 1570 Comm: modprobe Not tainted 4.19.0-rc7+ #21
[15102.031607] Hardware name: To be filled by O.E.M. To be filled by O.E.M./Aptio CRB, BIOS 5.6.5 07/08/2015
[15102.031628] Call Trace:
[15102.031676]  dump_stack+0xc9/0x16b
[15102.031723]  ? show_regs_print_info+0x5/0x5
[15102.031801]  ? lockdep_rcu_suspicious+0x117/0x160
[15102.031855]  pid_task+0x134/0x160
[15102.031900]  ? find_vpid+0xf0/0xf0
[15102.032017]  shutdown_umh.constprop.1+0x1e/0x53 [bpfilter]
[15102.032055]  stop_umh+0x46/0x52 [bpfilter]
[15102.032092]  __x64_sys_delete_module+0x47e/0x570
[ ... ]

Fixes: d2ba09c17a06 ("net: add skeleton of bpfilter kernel module")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bpfilter/bpfilter_kern.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/bpfilter/bpfilter_kern.c b/net/bpfilter/bpfilter_kern.c
index f0fc182d3db7..d5dd6b8b4248 100644
--- a/net/bpfilter/bpfilter_kern.c
+++ b/net/bpfilter/bpfilter_kern.c
@@ -23,9 +23,11 @@ static void shutdown_umh(struct umh_info *info)
 
 	if (!info->pid)
 		return;
-	tsk = pid_task(find_vpid(info->pid), PIDTYPE_PID);
-	if (tsk)
+	tsk = get_pid_task(find_vpid(info->pid), PIDTYPE_PID);
+	if (tsk) {
 		force_sig(SIGKILL, tsk);
+		put_task_struct(tsk);
+	}
 	fput(info->pipe_to_umh);
 	fput(info->pipe_from_umh);
 	info->pid = 0;
-- 
2.19.1


From e2f3a6113c99e572a6d2f154416ccd5233992900 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 1 Nov 2018 12:02:37 -0700
Subject: [PATCH 36/39] net: drop skb on failure in ip_check_defrag()

[ Upstream commit 7de414a9dd91426318df7b63da024b2b07e53df5 ]

Most callers of pskb_trim_rcsum() simply drop the skb when
it fails, however, ip_check_defrag() still continues to pass
the skb up to stack. This is suspicious.

In ip_check_defrag(), after we learn the skb is an IP fragment,
passing the skb to callers makes no sense, because callers expect
fragments are defrag'ed on success. So, dropping the skb when we
can't defrag it is reasonable.

Note, prior to commit 88078d98d1bb, this is not a big problem as
checksum will be fixed up anyway. After it, the checksum is not
correct on failure.

Found this during code review.

Fixes: 88078d98d1bb ("net: pskb_trim_rcsum() and CHECKSUM_COMPLETE are friends")
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_fragment.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index d14d741fb05e..9d3bdce1ad8a 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -657,10 +657,14 @@ struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user)
 	if (ip_is_fragment(&iph)) {
 		skb = skb_share_check(skb, GFP_ATOMIC);
 		if (skb) {
-			if (!pskb_may_pull(skb, netoff + iph.ihl * 4))
-				return skb;
-			if (pskb_trim_rcsum(skb, netoff + len))
-				return skb;
+			if (!pskb_may_pull(skb, netoff + iph.ihl * 4)) {
+				kfree_skb(skb);
+				return NULL;
+			}
+			if (pskb_trim_rcsum(skb, netoff + len)) {
+				kfree_skb(skb);
+				return NULL;
+			}
 			memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
 			if (ip_defrag(net, skb, user))
 				return NULL;
-- 
2.19.1


From c8a90d202c7a95b2b623e83fa5c2889d19b287eb Mon Sep 17 00:00:00 2001
From: Dimitris Michailidis <dmichail@google.com>
Date: Fri, 19 Oct 2018 17:07:13 -0700
Subject: [PATCH 37/39] net: fix pskb_trim_rcsum_slow() with odd trim offset

[ Upstream commit d55bef5059dd057bd077155375c581b49d25be7e ]

We've been getting checksum errors involving small UDP packets, usually
59B packets with 1 extra non-zero padding byte. netdev_rx_csum_fault()
has been complaining that HW is providing bad checksums. Turns out the
problem is in pskb_trim_rcsum_slow(), introduced in commit 88078d98d1bb
("net: pskb_trim_rcsum() and CHECKSUM_COMPLETE are friends").

The source of the problem is that when the bytes we are trimming start
at an odd address, as in the case of the 1 padding byte above,
skb_checksum() returns a byte-swapped value. We cannot just combine this
with skb->csum using csum_sub(). We need to use csum_block_sub() here
that takes into account the parity of the start address and handles the
swapping.

Matches existing code in __skb_postpull_rcsum() and esp_remove_trailer().

Fixes: 88078d98d1bb ("net: pskb_trim_rcsum() and CHECKSUM_COMPLETE are friends")
Signed-off-by: Dimitris Michailidis <dmichail@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 3680912f056a..c45916b91a9c 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1845,8 +1845,9 @@ int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len)
 	if (skb->ip_summed == CHECKSUM_COMPLETE) {
 		int delta = skb->len - len;
 
-		skb->csum = csum_sub(skb->csum,
-				     skb_checksum(skb, len, delta, 0));
+		skb->csum = csum_block_sub(skb->csum,
+					   skb_checksum(skb, len, delta, 0),
+					   len);
 	}
 	return __pskb_trim(skb, len);
 }
-- 
2.19.1


From 760439b5ea803ed4f2f86376d946efb8a3e5a23b Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Tue, 21 Aug 2018 14:41:41 +0300
Subject: [PATCH 38/39] net/mlx5: WQ, fixes for fragmented WQ buffers API

[ Upstream commit 37fdffb217a45609edccbb8b407d031143f551c0 ]

mlx5e netdevice used to calculate fragment edges by a call to
mlx5_wq_cyc_get_frag_size(). This calculation did not give the correct
indication for queues smaller than a PAGE_SIZE, (broken by default on
PowerPC, where PAGE_SIZE == 64KB).  Here it is replaced by the correct new
calls/API.

Since (TX/RX) Work Queues buffers are fragmented, here we introduce
changes to the API in core driver, so that it gets a stride index and
returns the index of last stride on same fragment, and an additional
wrapping function that returns the number of physically contiguous
strides that can be written contiguously to the work queue.

This obsoletes the following API functions, and their buggy
usage in EN driver:
* mlx5_wq_cyc_get_frag_size()
* mlx5_wq_cyc_ctr2fragix()

The new API improves modularity and hides the details of such
calculation for mlx5e netdevice and mlx5_ib rdma drivers.

New calculation is also more efficient, and improves performance
as follows:

Packet rate test: pktgen, UDP / IPv4, 64byte, single ring, 8K ring size.

Before: 16,477,619 pps
After:  17,085,793 pps

3.7% improvement

Fixes: 3a2f70331226 ("net/mlx5: Use order-0 allocations for all WQ types")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en_rx.c   | 12 +++++-----
 .../net/ethernet/mellanox/mlx5/core/en_tx.c   | 22 +++++++++----------
 .../ethernet/mellanox/mlx5/core/ipoib/ipoib.h |  5 ++---
 drivers/net/ethernet/mellanox/mlx5/core/wq.c  |  5 -----
 drivers/net/ethernet/mellanox/mlx5/core/wq.h  | 11 +++++-----
 include/linux/mlx5/driver.h                   |  8 +++++++
 6 files changed, 31 insertions(+), 32 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 696edeff255b..fb6c72cf70a0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -429,10 +429,9 @@ static inline u16 mlx5e_icosq_wrap_cnt(struct mlx5e_icosq *sq)
 
 static inline void mlx5e_fill_icosq_frag_edge(struct mlx5e_icosq *sq,
 					      struct mlx5_wq_cyc *wq,
-					      u16 pi, u16 frag_pi)
+					      u16 pi, u16 nnops)
 {
 	struct mlx5e_sq_wqe_info *edge_wi, *wi = &sq->db.ico_wqe[pi];
-	u8 nnops = mlx5_wq_cyc_get_frag_size(wq) - frag_pi;
 
 	edge_wi = wi + nnops;
 
@@ -451,15 +450,14 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 	struct mlx5_wq_cyc *wq = &sq->wq;
 	struct mlx5e_umr_wqe *umr_wqe;
 	u16 xlt_offset = ix << (MLX5E_LOG_ALIGNED_MPWQE_PPW - 1);
-	u16 pi, frag_pi;
+	u16 pi, contig_wqebbs_room;
 	int err;
 	int i;
 
 	pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
-	frag_pi = mlx5_wq_cyc_ctr2fragix(wq, sq->pc);
-
-	if (unlikely(frag_pi + MLX5E_UMR_WQEBBS > mlx5_wq_cyc_get_frag_size(wq))) {
-		mlx5e_fill_icosq_frag_edge(sq, wq, pi, frag_pi);
+	contig_wqebbs_room = mlx5_wq_cyc_get_contig_wqebbs(wq, pi);
+	if (unlikely(contig_wqebbs_room < MLX5E_UMR_WQEBBS)) {
+		mlx5e_fill_icosq_frag_edge(sq, wq, pi, contig_wqebbs_room);
 		pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index f29deb44bf3b..1e774d979c85 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -287,10 +287,9 @@ mlx5e_txwqe_build_dsegs(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 
 static inline void mlx5e_fill_sq_frag_edge(struct mlx5e_txqsq *sq,
 					   struct mlx5_wq_cyc *wq,
-					   u16 pi, u16 frag_pi)
+					   u16 pi, u16 nnops)
 {
 	struct mlx5e_tx_wqe_info *edge_wi, *wi = &sq->db.wqe_info[pi];
-	u8 nnops = mlx5_wq_cyc_get_frag_size(wq) - frag_pi;
 
 	edge_wi = wi + nnops;
 
@@ -345,8 +344,8 @@ netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	struct mlx5e_tx_wqe_info *wi;
 
 	struct mlx5e_sq_stats *stats = sq->stats;
+	u16 headlen, ihs, contig_wqebbs_room;
 	u16 ds_cnt, ds_cnt_inl = 0;
-	u16 headlen, ihs, frag_pi;
 	u8 num_wqebbs, opcode;
 	u32 num_bytes;
 	int num_dma;
@@ -383,9 +382,9 @@ netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	}
 
 	num_wqebbs = DIV_ROUND_UP(ds_cnt, MLX5_SEND_WQEBB_NUM_DS);
-	frag_pi = mlx5_wq_cyc_ctr2fragix(wq, sq->pc);
-	if (unlikely(frag_pi + num_wqebbs > mlx5_wq_cyc_get_frag_size(wq))) {
-		mlx5e_fill_sq_frag_edge(sq, wq, pi, frag_pi);
+	contig_wqebbs_room = mlx5_wq_cyc_get_contig_wqebbs(wq, pi);
+	if (unlikely(contig_wqebbs_room < num_wqebbs)) {
+		mlx5e_fill_sq_frag_edge(sq, wq, pi, contig_wqebbs_room);
 		mlx5e_sq_fetch_wqe(sq, &wqe, &pi);
 	}
 
@@ -629,7 +628,7 @@ netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	struct mlx5e_tx_wqe_info *wi;
 
 	struct mlx5e_sq_stats *stats = sq->stats;
-	u16 headlen, ihs, pi, frag_pi;
+	u16 headlen, ihs, pi, contig_wqebbs_room;
 	u16 ds_cnt, ds_cnt_inl = 0;
 	u8 num_wqebbs, opcode;
 	u32 num_bytes;
@@ -665,13 +664,14 @@ netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	}
 
 	num_wqebbs = DIV_ROUND_UP(ds_cnt, MLX5_SEND_WQEBB_NUM_DS);
-	frag_pi = mlx5_wq_cyc_ctr2fragix(wq, sq->pc);
-	if (unlikely(frag_pi + num_wqebbs > mlx5_wq_cyc_get_frag_size(wq))) {
+	pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+	contig_wqebbs_room = mlx5_wq_cyc_get_contig_wqebbs(wq, pi);
+	if (unlikely(contig_wqebbs_room < num_wqebbs)) {
+		mlx5e_fill_sq_frag_edge(sq, wq, pi, contig_wqebbs_room);
 		pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
-		mlx5e_fill_sq_frag_edge(sq, wq, pi, frag_pi);
 	}
 
-	mlx5i_sq_fetch_wqe(sq, &wqe, &pi);
+	mlx5i_sq_fetch_wqe(sq, &wqe, pi);
 
 	/* fill wqe */
 	wi       = &sq->db.wqe_info[pi];
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
index 08eac92fc26c..0982c579ec74 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
@@ -109,12 +109,11 @@ struct mlx5i_tx_wqe {
 
 static inline void mlx5i_sq_fetch_wqe(struct mlx5e_txqsq *sq,
 				      struct mlx5i_tx_wqe **wqe,
-				      u16 *pi)
+				      u16 pi)
 {
 	struct mlx5_wq_cyc *wq = &sq->wq;
 
-	*pi  = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
-	*wqe = mlx5_wq_cyc_get_wqe(wq, *pi);
+	*wqe = mlx5_wq_cyc_get_wqe(wq, pi);
 	memset(*wqe, 0, sizeof(**wqe));
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c
index d838af9539b1..9046475c531c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c
@@ -39,11 +39,6 @@ u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq)
 	return (u32)wq->fbc.sz_m1 + 1;
 }
 
-u16 mlx5_wq_cyc_get_frag_size(struct mlx5_wq_cyc *wq)
-{
-	return wq->fbc.frag_sz_m1 + 1;
-}
-
 u32 mlx5_cqwq_get_size(struct mlx5_cqwq *wq)
 {
 	return wq->fbc.sz_m1 + 1;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h
index 16476cc1a602..311256554520 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/wq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h
@@ -80,7 +80,6 @@ int mlx5_wq_cyc_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		       void *wqc, struct mlx5_wq_cyc *wq,
 		       struct mlx5_wq_ctrl *wq_ctrl);
 u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq);
-u16 mlx5_wq_cyc_get_frag_size(struct mlx5_wq_cyc *wq);
 
 int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		      void *qpc, struct mlx5_wq_qp *wq,
@@ -140,11 +139,6 @@ static inline u16 mlx5_wq_cyc_ctr2ix(struct mlx5_wq_cyc *wq, u16 ctr)
 	return ctr & wq->fbc.sz_m1;
 }
 
-static inline u16 mlx5_wq_cyc_ctr2fragix(struct mlx5_wq_cyc *wq, u16 ctr)
-{
-	return ctr & wq->fbc.frag_sz_m1;
-}
-
 static inline u16 mlx5_wq_cyc_get_head(struct mlx5_wq_cyc *wq)
 {
 	return mlx5_wq_cyc_ctr2ix(wq, wq->wqe_ctr);
@@ -160,6 +154,11 @@ static inline void *mlx5_wq_cyc_get_wqe(struct mlx5_wq_cyc *wq, u16 ix)
 	return mlx5_frag_buf_get_wqe(&wq->fbc, ix);
 }
 
+static inline u16 mlx5_wq_cyc_get_contig_wqebbs(struct mlx5_wq_cyc *wq, u16 ix)
+{
+	return mlx5_frag_buf_get_idx_last_contig_stride(&wq->fbc, ix) - ix + 1;
+}
+
 static inline int mlx5_wq_cyc_cc_bigger(u16 cc1, u16 cc2)
 {
 	int equal   = (cc1 == cc2);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 64f450593b54..b49bfc8e68b0 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1022,6 +1022,14 @@ static inline void *mlx5_frag_buf_get_wqe(struct mlx5_frag_buf_ctrl *fbc,
 		((fbc->frag_sz_m1 & ix) << fbc->log_stride);
 }
 
+static inline u32
+mlx5_frag_buf_get_idx_last_contig_stride(struct mlx5_frag_buf_ctrl *fbc, u32 ix)
+{
+	u32 last_frag_stride_idx = (ix + fbc->strides_offset) | fbc->frag_sz_m1;
+
+	return min_t(u32, last_frag_stride_idx - fbc->strides_offset, fbc->sz_m1);
+}
+
 int mlx5_cmd_init(struct mlx5_core_dev *dev);
 void mlx5_cmd_cleanup(struct mlx5_core_dev *dev);
 void mlx5_cmd_use_events(struct mlx5_core_dev *dev);
-- 
2.19.1


From c1facf5d072ef0ca6923cf465bd196521592b463 Mon Sep 17 00:00:00 2001
From: Shalom Toledo <shalomt@mellanox.com>
Date: Mon, 29 Oct 2018 14:26:16 +0000
Subject: [PATCH 39/39] mlxsw: core: Fix devlink unregister flow

[ Upstream commit a22712a962912faf257e857ab6857f56a93cfb34 ]

After a failed reload, the driver is still registered to devlink, its
devlink instance is still allocated and the 'reload_fail' flag is set.
Then, in the next reload try, the driver's allocated devlink instance will
be freed without unregistering from devlink and its components (e.g,
resources). This scenario can cause a use-after-free if the user tries to
execute command via devlink user-space tool.

Fix by not freeing the devlink instance during reload (failed or not).

Fixes: 24cc68ad6c46 ("mlxsw: core: Add support for reload")
Signed-off-by: Shalom Toledo <shalomt@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/core.c | 24 +++++++++++++++-------
 1 file changed, 17 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index f9c724752a32..13636a537f37 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -985,8 +985,8 @@ static int mlxsw_devlink_core_bus_device_reload(struct devlink *devlink,
 					     mlxsw_core->bus,
 					     mlxsw_core->bus_priv, true,
 					     devlink);
-	if (err)
-		mlxsw_core->reload_fail = true;
+	mlxsw_core->reload_fail = !!err;
+
 	return err;
 }
 
@@ -1126,8 +1126,15 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core,
 	const char *device_kind = mlxsw_core->bus_info->device_kind;
 	struct devlink *devlink = priv_to_devlink(mlxsw_core);
 
-	if (mlxsw_core->reload_fail)
-		goto reload_fail;
+	if (mlxsw_core->reload_fail) {
+		if (!reload)
+			/* Only the parts that were not de-initialized in the
+			 * failed reload attempt need to be de-initialized.
+			 */
+			goto reload_fail_deinit;
+		else
+			return;
+	}
 
 	if (mlxsw_core->driver->fini)
 		mlxsw_core->driver->fini(mlxsw_core);
@@ -1140,9 +1147,12 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core,
 	if (!reload)
 		devlink_resources_unregister(devlink, NULL);
 	mlxsw_core->bus->fini(mlxsw_core->bus_priv);
-	if (reload)
-		return;
-reload_fail:
+
+	return;
+
+reload_fail_deinit:
+	devlink_unregister(devlink);
+	devlink_resources_unregister(devlink, NULL);
 	devlink_free(devlink);
 	mlxsw_core_driver_put(device_kind);
 }
-- 
2.19.1


[-- Attachment #3: net_419.mbox --]
[-- Type: Application/Octet-Stream, Size: 55918 bytes --]

From b5a2374820d7774adb5da4c5e1b15015e354878f Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Fri, 26 Oct 2018 10:28:43 +0800
Subject: [PATCH 01/20] bridge: do not add port to router list when receives
 query with source 0.0.0.0

[ Upstream commit 5a2de63fd1a59c30c02526d427bc014b98adf508 ]

Based on RFC 4541, 2.1.1.  IGMP Forwarding Rules

  The switch supporting IGMP snooping must maintain a list of
  multicast routers and the ports on which they are attached.  This
  list can be constructed in any combination of the following ways:

  a) This list should be built by the snooping switch sending
     Multicast Router Solicitation messages as described in IGMP
     Multicast Router Discovery [MRDISC].  It may also snoop
     Multicast Router Advertisement messages sent by and to other
     nodes.

  b) The arrival port for IGMP Queries (sent by multicast routers)
     where the source address is not 0.0.0.0.

We should not add the port to router list when receives query with source
0.0.0.0.

Reported-by: Ying Xu <yinxu@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Acked-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 20ed7adcf1cc..ef0efb3e6b91 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1420,7 +1420,15 @@ static void br_multicast_query_received(struct net_bridge *br,
 		return;
 
 	br_multicast_update_query_timer(br, query, max_delay);
-	br_multicast_mark_router(br, port);
+
+	/* Based on RFC4541, section 2.1.1 IGMP Forwarding Rules,
+	 * the arrival port for IGMP Queries where the source address
+	 * is 0.0.0.0 should not be added to router port list.
+	 */
+	if ((saddr->proto == htons(ETH_P_IP) && saddr->u.ip4) ||
+	    (saddr->proto == htons(ETH_P_IPV6) &&
+	     !ipv6_addr_any(&saddr->u.ip6)))
+		br_multicast_mark_router(br, port);
 }
 
 static void br_ip4_multicast_query(struct net_bridge *br,
-- 
2.19.1


From fcc8ff3dea7c90a80b649bfee6e36baa38d68789 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Wed, 24 Oct 2018 14:37:21 +0200
Subject: [PATCH 02/20] ipv6/ndisc: Preserve IPv6 control buffer if protocol
 error handlers are called

[ Upstream commit ee1abcf689353f36d9322231b4320926096bdee0 ]

Commit a61bbcf28a8c ("[NET]: Store skb->timestamp as offset to a base
timestamp") introduces a neighbour control buffer and zeroes it out in
ndisc_rcv(), as ndisc_recv_ns() uses it.

Commit f2776ff04722 ("[IPV6]: Fix address/interface handling in UDP and
DCCP, according to the scoping architecture.") introduces the usage of the
IPv6 control buffer in protocol error handlers (e.g. inet6_iif() in
present-day __udp6_lib_err()).

Now, with commit b94f1c0904da ("ipv6: Use icmpv6_notify() to propagate
redirect, instead of rt6_redirect()."), we call protocol error handlers
from ndisc_redirect_rcv(), after the control buffer is already stolen and
some parts are already zeroed out. This implies that inet6_iif() on this
path will always return zero.

This gives unexpected results on UDP socket lookup in __udp6_lib_err(), as
we might actually need to match sockets for a given interface.

Instead of always claiming the control buffer in ndisc_rcv(), do that only
when needed.

Fixes: b94f1c0904da ("ipv6: Use icmpv6_notify() to propagate redirect, instead of rt6_redirect().")
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ndisc.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 0ec273997d1d..673a4a932f2a 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1732,10 +1732,9 @@ int ndisc_rcv(struct sk_buff *skb)
 		return 0;
 	}
 
-	memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb));
-
 	switch (msg->icmph.icmp6_type) {
 	case NDISC_NEIGHBOUR_SOLICITATION:
+		memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb));
 		ndisc_recv_ns(skb);
 		break;
 
-- 
2.19.1


From 5ebe64483ef52f8b7a79bfc27eb4d1a69501996c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 30 Oct 2018 00:57:25 -0700
Subject: [PATCH 03/20] net/mlx5e: fix csum adjustments caused by RXFCS
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit d48051c5b8376038c2b287c3b1bd55b8d391d567 ]

As shown by Dmitris, we need to use csum_block_add() instead of csum_add()
when adding the FCS contribution to skb csum.

Before 4.18 (more exactly commit 88078d98d1bb "net: pskb_trim_rcsum()
and CHECKSUM_COMPLETE are friends"), the whole skb csum was thrown away,
so RXFCS changes were ignored.

Then before commit d55bef5059dd ("net: fix pskb_trim_rcsum_slow() with
odd trim offset") both mlx5 and pskb_trim_rcsum_slow() bugs were canceling
each other.

Now we fixed pskb_trim_rcsum_slow() we need to fix mlx5.

Note that this patch also rewrites mlx5e_get_fcs() to :

- Use skb_header_pointer() instead of reinventing it.
- Use __get_unaligned_cpu32() to avoid possible non aligned accesses
  as Dmitris pointed out.

Fixes: 902a545904c7 ("net/mlx5e: When RXFCS is set, add FCS data into checksum calculation")
Reported-by: Paweł Staszewski <pstaszewski@itcare.pl>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Eran Ben Elisha <eranbe@mellanox.com>
Cc: Saeed Mahameed <saeedm@mellanox.com>
Cc: Dimitris Michailidis <dmichail@google.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Paweł Staszewski <pstaszewski@itcare.pl>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Tested-By: Maria Pasechnik <mariap@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlx5/core/en_rx.c   | 45 ++++---------------
 1 file changed, 9 insertions(+), 36 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 00172dee5339..a144146b769c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -696,43 +696,15 @@ static inline bool is_last_ethertype_ip(struct sk_buff *skb, int *network_depth)
 	return (ethertype == htons(ETH_P_IP) || ethertype == htons(ETH_P_IPV6));
 }
 
-static __be32 mlx5e_get_fcs(struct sk_buff *skb)
+static u32 mlx5e_get_fcs(const struct sk_buff *skb)
 {
-	int last_frag_sz, bytes_in_prev, nr_frags;
-	u8 *fcs_p1, *fcs_p2;
-	skb_frag_t *last_frag;
-	__be32 fcs_bytes;
+	const void *fcs_bytes;
+	u32 _fcs_bytes;
 
-	if (!skb_is_nonlinear(skb))
-		return *(__be32 *)(skb->data + skb->len - ETH_FCS_LEN);
+	fcs_bytes = skb_header_pointer(skb, skb->len - ETH_FCS_LEN,
+				       ETH_FCS_LEN, &_fcs_bytes);
 
-	nr_frags = skb_shinfo(skb)->nr_frags;
-	last_frag = &skb_shinfo(skb)->frags[nr_frags - 1];
-	last_frag_sz = skb_frag_size(last_frag);
-
-	/* If all FCS data is in last frag */
-	if (last_frag_sz >= ETH_FCS_LEN)
-		return *(__be32 *)(skb_frag_address(last_frag) +
-				   last_frag_sz - ETH_FCS_LEN);
-
-	fcs_p2 = (u8 *)skb_frag_address(last_frag);
-	bytes_in_prev = ETH_FCS_LEN - last_frag_sz;
-
-	/* Find where the other part of the FCS is - Linear or another frag */
-	if (nr_frags == 1) {
-		fcs_p1 = skb_tail_pointer(skb);
-	} else {
-		skb_frag_t *prev_frag = &skb_shinfo(skb)->frags[nr_frags - 2];
-
-		fcs_p1 = skb_frag_address(prev_frag) +
-			    skb_frag_size(prev_frag);
-	}
-	fcs_p1 -= bytes_in_prev;
-
-	memcpy(&fcs_bytes, fcs_p1, bytes_in_prev);
-	memcpy(((u8 *)&fcs_bytes) + bytes_in_prev, fcs_p2, last_frag_sz);
-
-	return fcs_bytes;
+	return __get_unaligned_cpu32(fcs_bytes);
 }
 
 static inline void mlx5e_handle_csum(struct net_device *netdev,
@@ -765,8 +737,9 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 						 network_depth - ETH_HLEN,
 						 skb->csum);
 		if (unlikely(netdev->features & NETIF_F_RXFCS))
-			skb->csum = csum_add(skb->csum,
-					     (__force __wsum)mlx5e_get_fcs(skb));
+			skb->csum = csum_block_add(skb->csum,
+						   (__force __wsum)mlx5e_get_fcs(skb),
+						   skb->len - ETH_FCS_LEN);
 		stats->csum_complete++;
 		return;
 	}
-- 
2.19.1


From 1a90cb96ad36fc875c516c51ffa0982d5461c538 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 26 Oct 2018 15:51:06 -0700
Subject: [PATCH 04/20] net: sched: gred: pass the right attribute to
 gred_change_table_def()

[ Upstream commit 38b4f18d56372e1e21771ab7b0357b853330186c ]

gred_change_table_def() takes a pointer to TCA_GRED_DPS attribute,
and expects it will be able to interpret its contents as
struct tc_gred_sopt.  Pass the correct gred attribute, instead of
TCA_OPTIONS.

This bug meant the table definition could never be changed after
Qdisc was initialized (unless whatever TCA_OPTIONS contained both
passed netlink validation and was a valid struct tc_gred_sopt...).

Old behaviour:
$ ip link add type dummy
$ tc qdisc replace dev dummy0 parent root handle 7: \
     gred setup vqs 4 default 0
$ tc qdisc replace dev dummy0 parent root handle 7: \
     gred setup vqs 4 default 0
RTNETLINK answers: Invalid argument

Now:
$ ip link add type dummy
$ tc qdisc replace dev dummy0 parent root handle 7: \
     gred setup vqs 4 default 0
$ tc qdisc replace dev dummy0 parent root handle 7: \
     gred setup vqs 4 default 0
$ tc qdisc replace dev dummy0 parent root handle 7: \
     gred setup vqs 4 default 0

Fixes: f62d6b936df5 ("[PKT_SCHED]: GRED: Use central VQ change procedure")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_gred.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index cbe4831f46f4..4a042abf844c 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -413,7 +413,7 @@ static int gred_change(struct Qdisc *sch, struct nlattr *opt,
 	if (tb[TCA_GRED_PARMS] == NULL && tb[TCA_GRED_STAB] == NULL) {
 		if (tb[TCA_GRED_LIMIT] != NULL)
 			sch->limit = nla_get_u32(tb[TCA_GRED_LIMIT]);
-		return gred_change_table_def(sch, opt);
+		return gred_change_table_def(sch, tb[TCA_GRED_DPS]);
 	}
 
 	if (tb[TCA_GRED_PARMS] == NULL ||
-- 
2.19.1


From 1ce15da8e3541bb4e26471d42f690c3cd22919dc Mon Sep 17 00:00:00 2001
From: Niklas Cassel <niklas.cassel@linaro.org>
Date: Wed, 31 Oct 2018 16:08:10 +0100
Subject: [PATCH 05/20] net: stmmac: Fix stmmac_mdio_reset() when building
 stmmac as modules

[ Upstream commit 30549aab146ccb1275230c3b4b4bc6b4181fd54e ]

When building stmmac, it is only possible to select CONFIG_DWMAC_GENERIC,
or any of the glue drivers, when CONFIG_STMMAC_PLATFORM is set.
The only exception is CONFIG_STMMAC_PCI.

When calling of_mdiobus_register(), it will call our ->reset()
callback, which is set to stmmac_mdio_reset().

Most of the code in stmmac_mdio_reset() is protected by a
"#if defined(CONFIG_STMMAC_PLATFORM)", which will evaluate
to false when CONFIG_STMMAC_PLATFORM=m.

Because of this, the phy reset gpio will only be pulled when
stmmac is built as built-in, but not when built as modules.

Fix this by using "#if IS_ENABLED()" instead of "#if defined()".

Signed-off-by: Niklas Cassel <niklas.cassel@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index b72ef171477e..bdd351597b55 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -243,7 +243,7 @@ static int stmmac_mdio_write(struct mii_bus *bus, int phyaddr, int phyreg,
  */
 int stmmac_mdio_reset(struct mii_bus *bus)
 {
-#if defined(CONFIG_STMMAC_PLATFORM)
+#if IS_ENABLED(CONFIG_STMMAC_PLATFORM)
 	struct net_device *ndev = bus->priv;
 	struct stmmac_priv *priv = netdev_priv(ndev);
 	unsigned int mii_address = priv->hw->mii.addr;
-- 
2.19.1


From 88a9beeb539b24bbbdd90288a1abeeb06f241a2d Mon Sep 17 00:00:00 2001
From: Sean Tranchetti <stranche@codeaurora.org>
Date: Tue, 23 Oct 2018 16:04:31 -0600
Subject: [PATCH 06/20] net: udp: fix handling of CHECKSUM_COMPLETE packets

[ Upstream commit db4f1be3ca9b0ef7330763d07bf4ace83ad6f913 ]

Current handling of CHECKSUM_COMPLETE packets by the UDP stack is
incorrect for any packet that has an incorrect checksum value.

udp4/6_csum_init() will both make a call to
__skb_checksum_validate_complete() to initialize/validate the csum
field when receiving a CHECKSUM_COMPLETE packet. When this packet
fails validation, skb->csum will be overwritten with the pseudoheader
checksum so the packet can be fully validated by software, but the
skb->ip_summed value will be left as CHECKSUM_COMPLETE so that way
the stack can later warn the user about their hardware spewing bad
checksums. Unfortunately, leaving the SKB in this state can cause
problems later on in the checksum calculation.

Since the the packet is still marked as CHECKSUM_COMPLETE,
udp_csum_pull_header() will SUBTRACT the checksum of the UDP header
from skb->csum instead of adding it, leaving us with a garbage value
in that field. Once we try to copy the packet to userspace in the
udp4/6_recvmsg(), we'll make a call to skb_copy_and_csum_datagram_msg()
to checksum the packet data and add it in the garbage skb->csum value
to perform our final validation check.

Since the value we're validating is not the proper checksum, it's possible
that the folded value could come out to 0, causing us not to drop the
packet. Instead, we believe that the packet was checksummed incorrectly
by hardware since skb->ip_summed is still CHECKSUM_COMPLETE, and we attempt
to warn the user with netdev_rx_csum_fault(skb->dev);

Unfortunately, since this is the UDP path, skb->dev has been overwritten
by skb->dev_scratch and is no longer a valid pointer, so we end up
reading invalid memory.

This patch addresses this problem in two ways:
	1) Do not use the dev pointer when calling netdev_rx_csum_fault()
	   from skb_copy_and_csum_datagram_msg(). Since this gets called
	   from the UDP path where skb->dev has been overwritten, we have
	   no way of knowing if the pointer is still valid. Also for the
	   sake of consistency with the other uses of
	   netdev_rx_csum_fault(), don't attempt to call it if the
	   packet was checksummed by software.

	2) Add better CHECKSUM_COMPLETE handling to udp4/6_csum_init().
	   If we receive a packet that's CHECKSUM_COMPLETE that fails
	   verification (i.e. skb->csum_valid == 0), check who performed
	   the calculation. It's possible that the checksum was done in
	   software by the network stack earlier (such as Netfilter's
	   CONNTRACK module), and if that says the checksum is bad,
	   we can drop the packet immediately instead of waiting until
	   we try and copy it to userspace. Otherwise, we need to
	   mark the SKB as CHECKSUM_NONE, since the skb->csum field
	   no longer contains the full packet checksum after the
	   call to __skb_checksum_validate_complete().

Fixes: e6afc8ace6dd ("udp: remove headers from UDP packets before queueing")
Fixes: c84d949057ca ("udp: copy skb->truesize in the first cache line")
Cc: Sam Kumar <samanthakumar@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Sean Tranchetti <stranche@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/datagram.c     |  5 +++--
 net/ipv4/udp.c          | 20 ++++++++++++++++++--
 net/ipv6/ip6_checksum.c | 20 ++++++++++++++++++--
 3 files changed, 39 insertions(+), 6 deletions(-)

diff --git a/net/core/datagram.c b/net/core/datagram.c
index 9aac0d63d53e..df16493232aa 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -808,8 +808,9 @@ int skb_copy_and_csum_datagram_msg(struct sk_buff *skb,
 			return -EINVAL;
 		}
 
-		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE))
-			netdev_rx_csum_fault(skb->dev);
+		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
+		    !skb->csum_complete_sw)
+			netdev_rx_csum_fault(NULL);
 	}
 	return 0;
 fault:
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index c32a4c16b7ff..f8183fdce5b2 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2120,8 +2120,24 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh,
 	/* Note, we are only interested in != 0 or == 0, thus the
 	 * force to int.
 	 */
-	return (__force int)skb_checksum_init_zero_check(skb, proto, uh->check,
-							 inet_compute_pseudo);
+	err = (__force int)skb_checksum_init_zero_check(skb, proto, uh->check,
+							inet_compute_pseudo);
+	if (err)
+		return err;
+
+	if (skb->ip_summed == CHECKSUM_COMPLETE && !skb->csum_valid) {
+		/* If SW calculated the value, we know it's bad */
+		if (skb->csum_complete_sw)
+			return 1;
+
+		/* HW says the value is bad. Let's validate that.
+		 * skb->csum is no longer the full packet checksum,
+		 * so don't treat it as such.
+		 */
+		skb_checksum_complete_unset(skb);
+	}
+
+	return 0;
 }
 
 /* wrapper for udp_queue_rcv_skb tacking care of csum conversion and
diff --git a/net/ipv6/ip6_checksum.c b/net/ipv6/ip6_checksum.c
index 547515e8450a..377717045f8f 100644
--- a/net/ipv6/ip6_checksum.c
+++ b/net/ipv6/ip6_checksum.c
@@ -88,8 +88,24 @@ int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto)
 	 * Note, we are only interested in != 0 or == 0, thus the
 	 * force to int.
 	 */
-	return (__force int)skb_checksum_init_zero_check(skb, proto, uh->check,
-							 ip6_compute_pseudo);
+	err = (__force int)skb_checksum_init_zero_check(skb, proto, uh->check,
+							ip6_compute_pseudo);
+	if (err)
+		return err;
+
+	if (skb->ip_summed == CHECKSUM_COMPLETE && !skb->csum_valid) {
+		/* If SW calculated the value, we know it's bad */
+		if (skb->csum_complete_sw)
+			return 1;
+
+		/* HW says the value is bad. Let's validate that.
+		 * skb->csum is no longer the full packet checksum,
+		 * so don't treat is as such.
+		 */
+		skb_checksum_complete_unset(skb);
+	}
+
+	return 0;
 }
 EXPORT_SYMBOL(udp6_csum_init);
 
-- 
2.19.1


From 7a6c99faeabde3daea4d6252493503da298c0217 Mon Sep 17 00:00:00 2001
From: Karsten Graul <kgraul@linux.ibm.com>
Date: Tue, 23 Oct 2018 13:40:39 +0200
Subject: [PATCH 07/20] Revert "net: simplify sock_poll_wait"

[ Upstream commit 89ab066d4229acd32e323f1569833302544a4186 ]

This reverts commit dd979b4df817e9976f18fb6f9d134d6bc4a3c317.

This broke tcp_poll for SMC fallback: An AF_SMC socket establishes an
internal TCP socket for the initial handshake with the remote peer.
Whenever the SMC connection can not be established this TCP socket is
used as a fallback. All socket operations on the SMC socket are then
forwarded to the TCP socket. In case of poll, the file->private_data
pointer references the SMC socket because the TCP socket has no file
assigned. This causes tcp_poll to wait on the wrong socket.

Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 crypto/af_alg.c        |  2 +-
 include/net/sock.h     | 12 +++++++++---
 net/atm/common.c       |  2 +-
 net/caif/caif_socket.c |  2 +-
 net/core/datagram.c    |  2 +-
 net/dccp/proto.c       |  2 +-
 net/ipv4/tcp.c         |  2 +-
 net/iucv/af_iucv.c     |  2 +-
 net/nfc/llcp_sock.c    |  2 +-
 net/rxrpc/af_rxrpc.c   |  2 +-
 net/smc/af_smc.c       |  2 +-
 net/tipc/socket.c      |  2 +-
 net/unix/af_unix.c     |  4 ++--
 13 files changed, 22 insertions(+), 16 deletions(-)

diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index b053179e0bc5..17eb09d222ff 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -1071,7 +1071,7 @@ __poll_t af_alg_poll(struct file *file, struct socket *sock,
 	struct af_alg_ctx *ctx = ask->private;
 	__poll_t mask;
 
-	sock_poll_wait(file, wait);
+	sock_poll_wait(file, sock, wait);
 	mask = 0;
 
 	if (!ctx->more || ctx->used)
diff --git a/include/net/sock.h b/include/net/sock.h
index 433f45fc2d68..c64a1cff9eb3 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2057,14 +2057,20 @@ static inline bool skwq_has_sleeper(struct socket_wq *wq)
 /**
  * sock_poll_wait - place memory barrier behind the poll_wait call.
  * @filp:           file
+ * @sock:           socket to wait on
  * @p:              poll_table
  *
  * See the comments in the wq_has_sleeper function.
+ *
+ * Do not derive sock from filp->private_data here. An SMC socket establishes
+ * an internal TCP socket that is used in the fallback case. All socket
+ * operations on the SMC socket are then forwarded to the TCP socket. In case of
+ * poll, the filp->private_data pointer references the SMC socket because the
+ * TCP socket has no file assigned.
  */
-static inline void sock_poll_wait(struct file *filp, poll_table *p)
+static inline void sock_poll_wait(struct file *filp, struct socket *sock,
+				  poll_table *p)
 {
-	struct socket *sock = filp->private_data;
-
 	if (!poll_does_not_wait(p)) {
 		poll_wait(filp, &sock->wq->wait, p);
 		/* We need to be sure we are in sync with the
diff --git a/net/atm/common.c b/net/atm/common.c
index 9f8cb0d2e71e..a38c174fc766 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -653,7 +653,7 @@ __poll_t vcc_poll(struct file *file, struct socket *sock, poll_table *wait)
 	struct atm_vcc *vcc;
 	__poll_t mask;
 
-	sock_poll_wait(file, wait);
+	sock_poll_wait(file, sock, wait);
 	mask = 0;
 
 	vcc = ATM_SD(sock);
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index d18965f3291f..416717c57cd1 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -941,7 +941,7 @@ static __poll_t caif_poll(struct file *file,
 	__poll_t mask;
 	struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);
 
-	sock_poll_wait(file, wait);
+	sock_poll_wait(file, sock, wait);
 	mask = 0;
 
 	/* exceptional events? */
diff --git a/net/core/datagram.c b/net/core/datagram.c
index df16493232aa..57f3a6fcfc1e 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -838,7 +838,7 @@ __poll_t datagram_poll(struct file *file, struct socket *sock,
 	struct sock *sk = sock->sk;
 	__poll_t mask;
 
-	sock_poll_wait(file, wait);
+	sock_poll_wait(file, sock, wait);
 	mask = 0;
 
 	/* exceptional events? */
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 875858c8b059..43733accf58e 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -325,7 +325,7 @@ __poll_t dccp_poll(struct file *file, struct socket *sock,
 	__poll_t mask;
 	struct sock *sk = sock->sk;
 
-	sock_poll_wait(file, wait);
+	sock_poll_wait(file, sock, wait);
 	if (sk->sk_state == DCCP_LISTEN)
 		return inet_csk_listen_poll(sk);
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 10c6246396cc..bbd07736fb0f 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -507,7 +507,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	const struct tcp_sock *tp = tcp_sk(sk);
 	int state;
 
-	sock_poll_wait(file, wait);
+	sock_poll_wait(file, sock, wait);
 
 	state = inet_sk_state_load(sk);
 	if (state == TCP_LISTEN)
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index e2f16a0173a9..f024914da1b2 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1505,7 +1505,7 @@ __poll_t iucv_sock_poll(struct file *file, struct socket *sock,
 	struct sock *sk = sock->sk;
 	__poll_t mask = 0;
 
-	sock_poll_wait(file, wait);
+	sock_poll_wait(file, sock, wait);
 
 	if (sk->sk_state == IUCV_LISTEN)
 		return iucv_accept_poll(sk);
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index dd4adf8b1167..ae296273ce3d 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -556,7 +556,7 @@ static __poll_t llcp_sock_poll(struct file *file, struct socket *sock,
 
 	pr_debug("%p\n", sk);
 
-	sock_poll_wait(file, wait);
+	sock_poll_wait(file, sock, wait);
 
 	if (sk->sk_state == LLCP_LISTEN)
 		return llcp_accept_poll(sk);
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index ac44d8afffb1..3c39b8805d01 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -741,7 +741,7 @@ static __poll_t rxrpc_poll(struct file *file, struct socket *sock,
 	struct rxrpc_sock *rx = rxrpc_sk(sk);
 	__poll_t mask;
 
-	sock_poll_wait(file, wait);
+	sock_poll_wait(file, sock, wait);
 	mask = 0;
 
 	/* the socket is readable if there are any messages waiting on the Rx
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 015231789ed2..80e2119f1c70 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1543,7 +1543,7 @@ static __poll_t smc_poll(struct file *file, struct socket *sock,
 			mask |= EPOLLERR;
 	} else {
 		if (sk->sk_state != SMC_CLOSED)
-			sock_poll_wait(file, wait);
+			sock_poll_wait(file, sock, wait);
 		if (sk->sk_err)
 			mask |= EPOLLERR;
 		if ((sk->sk_shutdown == SHUTDOWN_MASK) ||
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 49810fdff4c5..0bf8ad486c5e 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -715,7 +715,7 @@ static __poll_t tipc_poll(struct file *file, struct socket *sock,
 	struct tipc_sock *tsk = tipc_sk(sk);
 	__poll_t revents = 0;
 
-	sock_poll_wait(file, wait);
+	sock_poll_wait(file, sock, wait);
 
 	if (sk->sk_shutdown & RCV_SHUTDOWN)
 		revents |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index d1edfa3cad61..c754f3a90a2e 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2640,7 +2640,7 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa
 	struct sock *sk = sock->sk;
 	__poll_t mask;
 
-	sock_poll_wait(file, wait);
+	sock_poll_wait(file, sock, wait);
 	mask = 0;
 
 	/* exceptional events? */
@@ -2677,7 +2677,7 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock,
 	unsigned int writable;
 	__poll_t mask;
 
-	sock_poll_wait(file, wait);
+	sock_poll_wait(file, sock, wait);
 	mask = 0;
 
 	/* exceptional events? */
-- 
2.19.1


From b43216537c8bdacf4f2dfa6e083c88221632be8a Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Mon, 29 Oct 2018 20:36:43 +0000
Subject: [PATCH 08/20] rtnetlink: Disallow FDB configuration for non-Ethernet
 device

[ Upstream commit da71577545a52be3e0e9225a946e5fd79cfab015 ]

When an FDB entry is configured, the address is validated to have the
length of an Ethernet address, but the device for which the address is
configured can be of any type.

The above can result in the use of uninitialized memory when the address
is later compared against existing addresses since 'dev->addr_len' is
used and it may be greater than ETH_ALEN, as with ip6tnl devices.

Fix this by making sure that FDB entries are only configured for
Ethernet devices.

BUG: KMSAN: uninit-value in memcmp+0x11d/0x180 lib/string.c:863
CPU: 1 PID: 4318 Comm: syz-executor998 Not tainted 4.19.0-rc3+ #49
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
Call Trace:
  __dump_stack lib/dump_stack.c:77 [inline]
  dump_stack+0x14b/0x190 lib/dump_stack.c:113
  kmsan_report+0x183/0x2b0 mm/kmsan/kmsan.c:956
  __msan_warning+0x70/0xc0 mm/kmsan/kmsan_instr.c:645
  memcmp+0x11d/0x180 lib/string.c:863
  dev_uc_add_excl+0x165/0x7b0 net/core/dev_addr_lists.c:464
  ndo_dflt_fdb_add net/core/rtnetlink.c:3463 [inline]
  rtnl_fdb_add+0x1081/0x1270 net/core/rtnetlink.c:3558
  rtnetlink_rcv_msg+0xa0b/0x1530 net/core/rtnetlink.c:4715
  netlink_rcv_skb+0x36e/0x5f0 net/netlink/af_netlink.c:2454
  rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:4733
  netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline]
  netlink_unicast+0x1638/0x1720 net/netlink/af_netlink.c:1343
  netlink_sendmsg+0x1205/0x1290 net/netlink/af_netlink.c:1908
  sock_sendmsg_nosec net/socket.c:621 [inline]
  sock_sendmsg net/socket.c:631 [inline]
  ___sys_sendmsg+0xe70/0x1290 net/socket.c:2114
  __sys_sendmsg net/socket.c:2152 [inline]
  __do_sys_sendmsg net/socket.c:2161 [inline]
  __se_sys_sendmsg+0x2a3/0x3d0 net/socket.c:2159
  __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2159
  do_syscall_64+0xb8/0x100 arch/x86/entry/common.c:291
  entry_SYSCALL_64_after_hwframe+0x63/0xe7
RIP: 0033:0x440ee9
Code: e8 cc ab 02 00 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7
48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff
ff 0f 83 bb 0a fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007fff6a93b518 EFLAGS: 00000213 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 0000000000440ee9
RDX: 0000000000000000 RSI: 0000000020000240 RDI: 0000000000000003
RBP: 0000000000000000 R08: 00000000004002c8 R09: 00000000004002c8
R10: 00000000004002c8 R11: 0000000000000213 R12: 000000000000b4b0
R13: 0000000000401ec0 R14: 0000000000000000 R15: 0000000000000000

Uninit was created at:
  kmsan_save_stack_with_flags mm/kmsan/kmsan.c:256 [inline]
  kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:181
  kmsan_kmalloc+0x98/0x100 mm/kmsan/kmsan_hooks.c:91
  kmsan_slab_alloc+0x10/0x20 mm/kmsan/kmsan_hooks.c:100
  slab_post_alloc_hook mm/slab.h:446 [inline]
  slab_alloc_node mm/slub.c:2718 [inline]
  __kmalloc_node_track_caller+0x9e7/0x1160 mm/slub.c:4351
  __kmalloc_reserve net/core/skbuff.c:138 [inline]
  __alloc_skb+0x2f5/0x9e0 net/core/skbuff.c:206
  alloc_skb include/linux/skbuff.h:996 [inline]
  netlink_alloc_large_skb net/netlink/af_netlink.c:1189 [inline]
  netlink_sendmsg+0xb49/0x1290 net/netlink/af_netlink.c:1883
  sock_sendmsg_nosec net/socket.c:621 [inline]
  sock_sendmsg net/socket.c:631 [inline]
  ___sys_sendmsg+0xe70/0x1290 net/socket.c:2114
  __sys_sendmsg net/socket.c:2152 [inline]
  __do_sys_sendmsg net/socket.c:2161 [inline]
  __se_sys_sendmsg+0x2a3/0x3d0 net/socket.c:2159
  __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2159
  do_syscall_64+0xb8/0x100 arch/x86/entry/common.c:291
  entry_SYSCALL_64_after_hwframe+0x63/0xe7

v2:
* Make error message more specific (David)

Fixes: 090096bf3db1 ("net: generic fdb support for drivers without ndo_fdb_<op>")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-and-tested-by: syzbot+3a288d5f5530b901310e@syzkaller.appspotmail.com
Reported-and-tested-by: syzbot+d53ab4e92a1db04110ff@syzkaller.appspotmail.com
Cc: Vlad Yasevich <vyasevich@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 37c7936124e6..6e5d61a20a70 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3530,6 +3530,11 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 		return -EINVAL;
 	}
 
+	if (dev->type != ARPHRD_ETHER) {
+		NL_SET_ERR_MSG(extack, "FDB delete only supported for Ethernet devices");
+		return -EINVAL;
+	}
+
 	addr = nla_data(tb[NDA_LLADDR]);
 
 	err = fdb_vid_parse(tb[NDA_VLAN], &vid, extack);
@@ -3634,6 +3639,11 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
 		return -EINVAL;
 	}
 
+	if (dev->type != ARPHRD_ETHER) {
+		NL_SET_ERR_MSG(extack, "FDB add only supported for Ethernet devices");
+		return -EINVAL;
+	}
+
 	addr = nla_data(tb[NDA_LLADDR]);
 
 	err = fdb_vid_parse(tb[NDA_VLAN], &vid, extack);
-- 
2.19.1


From 8518a74a10c224658979c9e0f33eeca029676bf6 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Tue, 30 Oct 2018 14:10:49 +0800
Subject: [PATCH 09/20] vhost: Fix Spectre V1 vulnerability

[ Upstream commit ff002269a4ee9c769dbf9365acef633ebcbd6cbe ]

The idx in vhost_vring_ioctl() was controlled by userspace, hence a
potential exploitation of the Spectre variant 1 vulnerability.

Fixing this by sanitizing idx before using it to index d->vqs.

Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/vhost.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index b13c6b4b2c66..eb95daa3e5a5 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -30,6 +30,7 @@
 #include <linux/sched/mm.h>
 #include <linux/sched/signal.h>
 #include <linux/interval_tree_generic.h>
+#include <linux/nospec.h>
 
 #include "vhost.h"
 
@@ -1397,6 +1398,7 @@ long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *arg
 	if (idx >= d->nvqs)
 		return -ENOBUFS;
 
+	idx = array_index_nospec(idx, d->nvqs);
 	vq = d->vqs[idx];
 
 	mutex_lock(&vq->mutex);
-- 
2.19.1


From 6d0e541fdee18397d33c5354521ea571493bf9a8 Mon Sep 17 00:00:00 2001
From: Tobias Jungel <tobias.jungel@gmail.com>
Date: Sun, 28 Oct 2018 12:54:10 +0100
Subject: [PATCH 10/20] bonding: fix length of actor system

[ Upstream commit 414dd6fb9a1a1b59983aea7bf0f79f0085ecc5b8 ]

The attribute IFLA_BOND_AD_ACTOR_SYSTEM is sent to user space having the
length of sizeof(bond->params.ad_actor_system) which is 8 byte. This
patch aligns the length to ETH_ALEN to have the same MAC address exposed
as using sysfs.

Fixes: f87fda00b6ed2 ("bonding: prevent out of bound accesses")
Signed-off-by: Tobias Jungel <tobias.jungel@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_netlink.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index 9697977b80f0..6b9ad8673218 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -638,8 +638,7 @@ static int bond_fill_info(struct sk_buff *skb,
 				goto nla_put_failure;
 
 			if (nla_put(skb, IFLA_BOND_AD_ACTOR_SYSTEM,
-				    sizeof(bond->params.ad_actor_system),
-				    &bond->params.ad_actor_system))
+				    ETH_ALEN, &bond->params.ad_actor_system))
 				goto nla_put_failure;
 		}
 		if (!bond_3ad_get_active_agg_info(bond, &info)) {
-- 
2.19.1


From bbf4abcd1123d88d71a2ad778703678fda834f7c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jaime=20Caama=C3=B1o=20Ruiz?= <jcaamano@suse.com>
Date: Wed, 31 Oct 2018 18:52:03 +0100
Subject: [PATCH 11/20] openvswitch: Fix push/pop ethernet validation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 46ebe2834ba5b541f28ee72e556a3fed42c47570 ]

When there are both pop and push ethernet header actions among the
actions to be applied to a packet, an unexpected EINVAL (Invalid
argument) error is obtained. This is due to mac_proto not being reset
correctly when those actions are validated.

Reported-at:
https://mail.openvswitch.org/pipermail/ovs-discuss/2018-October/047554.html
Fixes: 91820da6ae85 ("openvswitch: add Ethernet push and pop actions")
Signed-off-by: Jaime Caamaño Ruiz <jcaamano@suse.com>
Tested-by: Greg Rose <gvrose8192@gmail.com>
Reviewed-by: Greg Rose <gvrose8192@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/flow_netlink.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index a70097ecf33c..865ecef68196 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -3030,7 +3030,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 			 * is already present */
 			if (mac_proto != MAC_PROTO_NONE)
 				return -EINVAL;
-			mac_proto = MAC_PROTO_NONE;
+			mac_proto = MAC_PROTO_ETHERNET;
 			break;
 
 		case OVS_ACTION_ATTR_POP_ETH:
@@ -3038,7 +3038,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 				return -EINVAL;
 			if (vlan_tci & htons(VLAN_TAG_PRESENT))
 				return -EINVAL;
-			mac_proto = MAC_PROTO_ETHERNET;
+			mac_proto = MAC_PROTO_NONE;
 			break;
 
 		case OVS_ACTION_ATTR_PUSH_NSH:
-- 
2.19.1


From f8c5cb4077b2e3a09dbf9437941aff01ba9146cb Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 24 Oct 2018 13:58:39 -0700
Subject: [PATCH 12/20] net/ipv6: Allow onlink routes to have a device mismatch
 if it is the default route

[ Upstream commit 4ed591c8ab44e711e56b8e021ffaf4f407c045f5 ]

The intent of ip6_route_check_nh_onlink is to make sure the gateway
given for an onlink route is not actually on a connected route for
a different interface (e.g., 2001:db8:1::/64 is on dev eth1 and then
an onlink route has a via 2001:db8:1::1 dev eth2). If the gateway
lookup hits the default route then it most likely will be a different
interface than the onlink route which is ok.

Update ip6_route_check_nh_onlink to disregard the device mismatch
if the gateway lookup hits the default route. Turns out the existing
onlink tests are passing because there is no default route or it is
an unreachable default, so update the onlink tests to have a default
route other than unreachable.

Fixes: fc1e64e1092f6 ("net/ipv6: Add support for onlink flag")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c                                |  2 ++
 tools/testing/selftests/net/fib-onlink-tests.sh | 14 +++++++-------
 2 files changed, 9 insertions(+), 7 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index abcb5ae77319..1cf00d857fc1 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2799,6 +2799,8 @@ static int ip6_route_check_nh_onlink(struct net *net,
 	grt = ip6_nh_lookup_table(net, cfg, gw_addr, tbid, 0);
 	if (grt) {
 		if (!grt->dst.error &&
+		    /* ignore match if it is the default route */
+		    grt->from && !ipv6_addr_any(&grt->from->fib6_dst.addr) &&
 		    (grt->rt6i_flags & flags || dev != grt->dst.dev)) {
 			NL_SET_ERR_MSG(extack,
 				       "Nexthop has invalid gateway or device mismatch");
diff --git a/tools/testing/selftests/net/fib-onlink-tests.sh b/tools/testing/selftests/net/fib-onlink-tests.sh
index 3991ad1a368d..864f865eee55 100755
--- a/tools/testing/selftests/net/fib-onlink-tests.sh
+++ b/tools/testing/selftests/net/fib-onlink-tests.sh
@@ -167,8 +167,8 @@ setup()
 	# add vrf table
 	ip li add ${VRF} type vrf table ${VRF_TABLE}
 	ip li set ${VRF} up
-	ip ro add table ${VRF_TABLE} unreachable default
-	ip -6 ro add table ${VRF_TABLE} unreachable default
+	ip ro add table ${VRF_TABLE} unreachable default metric 8192
+	ip -6 ro add table ${VRF_TABLE} unreachable default metric 8192
 
 	# create test interfaces
 	ip li add ${NETIFS[p1]} type veth peer name ${NETIFS[p2]}
@@ -185,20 +185,20 @@ setup()
 	for n in 1 3 5 7; do
 		ip li set ${NETIFS[p${n}]} up
 		ip addr add ${V4ADDRS[p${n}]}/24 dev ${NETIFS[p${n}]}
-		ip addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]}
+		ip addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} nodad
 	done
 
 	# move peer interfaces to namespace and add addresses
 	for n in 2 4 6 8; do
 		ip li set ${NETIFS[p${n}]} netns ${PEER_NS} up
 		ip -netns ${PEER_NS} addr add ${V4ADDRS[p${n}]}/24 dev ${NETIFS[p${n}]}
-		ip -netns ${PEER_NS} addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]}
+		ip -netns ${PEER_NS} addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} nodad
 	done
 
-	set +e
+	ip -6 ro add default via ${V6ADDRS[p3]/::[0-9]/::64}
+	ip -6 ro add table ${VRF_TABLE} default via ${V6ADDRS[p7]/::[0-9]/::64}
 
-	# let DAD complete - assume default of 1 probe
-	sleep 1
+	set +e
 }
 
 cleanup()
-- 
2.19.1


From f5cb02690aaedf340abf24b65617f8d294a2b55c Mon Sep 17 00:00:00 2001
From: Karsten Graul <kgraul@linux.ibm.com>
Date: Thu, 25 Oct 2018 13:25:28 +0200
Subject: [PATCH 13/20] net/smc: fix smc_buf_unuse to use the lgr pointer

[ Upstream commit fb692ec4117f6fd25044cfb5720d6b79d400dc65 ]

The pointer to the link group is unset in the smc connection structure
right before the call to smc_buf_unuse. Provide the lgr pointer to
smc_buf_unuse explicitly.
And move the call to smc_lgr_schedule_free_work to the end of
smc_conn_free.

Fixes: a6920d1d130c ("net/smc: handle unregistered buffers")
Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/smc_core.c | 25 ++++++++++++-------------
 1 file changed, 12 insertions(+), 13 deletions(-)

diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index e871368500e3..18daebcef181 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -122,22 +122,17 @@ static void __smc_lgr_unregister_conn(struct smc_connection *conn)
 	sock_put(&smc->sk); /* sock_hold in smc_lgr_register_conn() */
 }
 
-/* Unregister connection and trigger lgr freeing if applicable
+/* Unregister connection from lgr
  */
 static void smc_lgr_unregister_conn(struct smc_connection *conn)
 {
 	struct smc_link_group *lgr = conn->lgr;
-	int reduced = 0;
 
 	write_lock_bh(&lgr->conns_lock);
 	if (conn->alert_token_local) {
-		reduced = 1;
 		__smc_lgr_unregister_conn(conn);
 	}
 	write_unlock_bh(&lgr->conns_lock);
-	if (!reduced || lgr->conns_num)
-		return;
-	smc_lgr_schedule_free_work(lgr);
 }
 
 /* Send delete link, either as client to request the initiation
@@ -291,7 +286,8 @@ static int smc_lgr_create(struct smc_sock *smc, bool is_smcd,
 	return rc;
 }
 
-static void smc_buf_unuse(struct smc_connection *conn)
+static void smc_buf_unuse(struct smc_connection *conn,
+			  struct smc_link_group *lgr)
 {
 	if (conn->sndbuf_desc)
 		conn->sndbuf_desc->used = 0;
@@ -301,8 +297,6 @@ static void smc_buf_unuse(struct smc_connection *conn)
 			conn->rmb_desc->used = 0;
 		} else {
 			/* buf registration failed, reuse not possible */
-			struct smc_link_group *lgr = conn->lgr;
-
 			write_lock_bh(&lgr->rmbs_lock);
 			list_del(&conn->rmb_desc->list);
 			write_unlock_bh(&lgr->rmbs_lock);
@@ -315,16 +309,21 @@ static void smc_buf_unuse(struct smc_connection *conn)
 /* remove a finished connection from its link group */
 void smc_conn_free(struct smc_connection *conn)
 {
-	if (!conn->lgr)
+	struct smc_link_group *lgr = conn->lgr;
+
+	if (!lgr)
 		return;
-	if (conn->lgr->is_smcd) {
+	if (lgr->is_smcd) {
 		smc_ism_unset_conn(conn);
 		tasklet_kill(&conn->rx_tsklet);
 	} else {
 		smc_cdc_tx_dismiss_slots(conn);
 	}
-	smc_lgr_unregister_conn(conn);
-	smc_buf_unuse(conn);
+	smc_lgr_unregister_conn(conn);		/* unsets conn->lgr */
+	smc_buf_unuse(conn, lgr);		/* allow buffer reuse */
+
+	if (!lgr->conns_num)
+		smc_lgr_schedule_free_work(lgr);
 }
 
 static void smc_link_clear(struct smc_link *lnk)
-- 
2.19.1


From 16f9d14de91617475424607b0374349d74d75294 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 29 Oct 2018 14:26:14 +0000
Subject: [PATCH 14/20] mlxsw: spectrum_switchdev: Don't ignore deletions of
 learned MACs

[ Upstream commit ad0b9d94182be8356978d220c82f9837cffeb7a9 ]

Demands to remove FDB entries should be honored even if the FDB entry in
question was originally learned, and not added by the user. Therefore
ignore the added_by_user datum for SWITCHDEV_FDB_DEL_TO_DEVICE.

Fixes: 816a3bed9549 ("switchdev: Add fdb.added_by_user to switchdev notifications")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Suggested-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index db715da7bab7..7715f1ed2bcb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -2317,8 +2317,6 @@ static void mlxsw_sp_switchdev_event_work(struct work_struct *work)
 		break;
 	case SWITCHDEV_FDB_DEL_TO_DEVICE:
 		fdb_info = &switchdev_work->fdb_info;
-		if (!fdb_info->added_by_user)
-			break;
 		mlxsw_sp_port_fdb_set(mlxsw_sp_port, fdb_info, false);
 		break;
 	case SWITCHDEV_FDB_ADD_TO_BRIDGE: /* fall through */
-- 
2.19.1


From 137b472abe4ba999b5dbe554ff5762c4d3a3a1ac Mon Sep 17 00:00:00 2001
From: Shalom Toledo <shalomt@mellanox.com>
Date: Mon, 29 Oct 2018 14:26:16 +0000
Subject: [PATCH 15/20] mlxsw: core: Fix devlink unregister flow

[ Upstream commit a22712a962912faf257e857ab6857f56a93cfb34 ]

After a failed reload, the driver is still registered to devlink, its
devlink instance is still allocated and the 'reload_fail' flag is set.
Then, in the next reload try, the driver's allocated devlink instance will
be freed without unregistering from devlink and its components (e.g,
resources). This scenario can cause a use-after-free if the user tries to
execute command via devlink user-space tool.

Fix by not freeing the devlink instance during reload (failed or not).

Fixes: 24cc68ad6c46 ("mlxsw: core: Add support for reload")
Signed-off-by: Shalom Toledo <shalomt@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/core.c | 24 +++++++++++++++-------
 1 file changed, 17 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index 937d0ace699a..30f751e69698 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -943,8 +943,8 @@ static int mlxsw_devlink_core_bus_device_reload(struct devlink *devlink,
 					     mlxsw_core->bus,
 					     mlxsw_core->bus_priv, true,
 					     devlink);
-	if (err)
-		mlxsw_core->reload_fail = true;
+	mlxsw_core->reload_fail = !!err;
+
 	return err;
 }
 
@@ -1083,8 +1083,15 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core,
 {
 	struct devlink *devlink = priv_to_devlink(mlxsw_core);
 
-	if (mlxsw_core->reload_fail)
-		goto reload_fail;
+	if (mlxsw_core->reload_fail) {
+		if (!reload)
+			/* Only the parts that were not de-initialized in the
+			 * failed reload attempt need to be de-initialized.
+			 */
+			goto reload_fail_deinit;
+		else
+			return;
+	}
 
 	if (mlxsw_core->driver->fini)
 		mlxsw_core->driver->fini(mlxsw_core);
@@ -1098,9 +1105,12 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core,
 	if (!reload)
 		devlink_resources_unregister(devlink, NULL);
 	mlxsw_core->bus->fini(mlxsw_core->bus_priv);
-	if (reload)
-		return;
-reload_fail:
+
+	return;
+
+reload_fail_deinit:
+	devlink_unregister(devlink);
+	devlink_resources_unregister(devlink, NULL);
 	devlink_free(devlink);
 }
 EXPORT_SYMBOL(mlxsw_core_bus_device_unregister);
-- 
2.19.1


From 01a72874de5a982a7003c87eb72c378c627272d2 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 1 Nov 2018 12:02:37 -0700
Subject: [PATCH 16/20] net: drop skb on failure in ip_check_defrag()

[ Upstream commit 7de414a9dd91426318df7b63da024b2b07e53df5 ]

Most callers of pskb_trim_rcsum() simply drop the skb when
it fails, however, ip_check_defrag() still continues to pass
the skb up to stack. This is suspicious.

In ip_check_defrag(), after we learn the skb is an IP fragment,
passing the skb to callers makes no sense, because callers expect
fragments are defrag'ed on success. So, dropping the skb when we
can't defrag it is reasonable.

Note, prior to commit 88078d98d1bb, this is not a big problem as
checksum will be fixed up anyway. After it, the checksum is not
correct on failure.

Found this during code review.

Fixes: 88078d98d1bb ("net: pskb_trim_rcsum() and CHECKSUM_COMPLETE are friends")
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_fragment.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index e7227128df2c..cb8fa5d7afe1 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -720,10 +720,14 @@ struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user)
 	if (ip_is_fragment(&iph)) {
 		skb = skb_share_check(skb, GFP_ATOMIC);
 		if (skb) {
-			if (!pskb_may_pull(skb, netoff + iph.ihl * 4))
-				return skb;
-			if (pskb_trim_rcsum(skb, netoff + len))
-				return skb;
+			if (!pskb_may_pull(skb, netoff + iph.ihl * 4)) {
+				kfree_skb(skb);
+				return NULL;
+			}
+			if (pskb_trim_rcsum(skb, netoff + len)) {
+				kfree_skb(skb);
+				return NULL;
+			}
 			memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
 			if (ip_defrag(net, skb, user))
 				return NULL;
-- 
2.19.1


From 99559717ab8792464664957ba117c8dbf7744e8a Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sun, 28 Oct 2018 10:35:12 -0700
Subject: [PATCH 17/20] net: Properly unlink GRO packets on overflow.

[ Upstream commti ece23711dd956cd5053c9cb03e9fe0668f9c8894 ]

Just like with normal GRO processing, we have to initialize
skb->next to NULL when we unlink overflow packets from the
GRO hash lists.

Fixes: d4546c2509b1 ("net: Convert GRO SKB handling to list_head.")
Reported-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/core/dev.c b/net/core/dev.c
index 93243479085f..e16ba3625400 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5431,6 +5431,7 @@ static void gro_flush_oldest(struct list_head *head)
 	 * SKB to the chain.
 	 */
 	list_del(&oldest->list);
+	oldest->next = NULL;
 	napi_gro_complete(oldest);
 }
 
-- 
2.19.1


From 8a3ac388ee24af880204acc081db916b20587712 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 25 Oct 2018 18:40:19 +0200
Subject: [PATCH 18/20] r8169: fix broken Wake-on-LAN from S5 (poweroff)

[ Upstream commit 649f0837a8cc2b39329f2de00fa0d04b029291c5 ]

It was reported that WoL from S5 is broken (WoL from S3 works) and the
analysis showed that during system shutdown the network interface was
brought down already when the actual kernel shutdown started.
Therefore netif_running() returned false and as a consequence the PHY
was suspended. Obviously WoL wasn't working then.
To fix this the original patch needs to be effectively reverted.
A side effect is that when normally bringing down the interface and
WoL is enabled the PHY will remain powered on (like it was before the
original patch).

Fixes: fe87bef01f9b ("r8169: don't check WoL when powering down PHY and interface is down")
Reported-by: Neil MacLeod <neil@nmacleod.com>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 2c350099b83c..4930e0375c1d 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -4175,10 +4175,15 @@ static void rtl_wol_suspend_quirk(struct rtl8169_private *tp)
 
 static bool rtl_wol_pll_power_down(struct rtl8169_private *tp)
 {
-	if (!netif_running(tp->dev) || !__rtl8169_get_wol(tp))
+	struct phy_device *phydev;
+
+	if (!__rtl8169_get_wol(tp))
 		return false;
 
-	phy_speed_down(tp->dev->phydev, false);
+	/* phydev may not be attached to netdevice */
+	phydev = mdiobus_get_phy(tp->mii_bus, 0);
+
+	phy_speed_down(phydev, false);
 	rtl_wol_suspend_quirk(tp);
 
 	return true;
-- 
2.19.1


From d37c63c236c23127e1aa3a2a76fcfc32a92b25dc Mon Sep 17 00:00:00 2001
From: Ivan Vecera <ivecera@redhat.com>
Date: Tue, 23 Oct 2018 16:40:26 +0200
Subject: [PATCH 19/20] Revert "be2net: remove desc field from be_eq_obj"

[ Upstream commit 5ef79151c2fbc401cf38325e9a32e77b9fc593ae ]

The mentioned commit needs to be reverted because we cannot pass
string allocated on stack to request_irq(). This function stores
uses this pointer for later use (e.g. /proc/interrupts) so we need
to keep this string persistently.

Fixes: d6d9704af8f4 ("be2net: remove desc field from be_eq_obj")
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/emulex/benet/be.h      | 1 +
 drivers/net/ethernet/emulex/benet/be_main.c | 6 ++----
 2 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index 58bcee8f0a58..ce041c90adb0 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -185,6 +185,7 @@ static inline void queue_tail_inc(struct be_queue_info *q)
 
 struct be_eq_obj {
 	struct be_queue_info q;
+	char desc[32];
 
 	struct be_adapter *adapter;
 	struct napi_struct napi;
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 534787291b44..bff74752cef1 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -3488,11 +3488,9 @@ static int be_msix_register(struct be_adapter *adapter)
 	int status, i, vec;
 
 	for_all_evt_queues(adapter, eqo, i) {
-		char irq_name[IFNAMSIZ+4];
-
-		snprintf(irq_name, sizeof(irq_name), "%s-q%d", netdev->name, i);
+		sprintf(eqo->desc, "%s-q%d", netdev->name, i);
 		vec = be_msix_vec_get(adapter, eqo);
-		status = request_irq(vec, be_msix, 0, irq_name, eqo);
+		status = request_irq(vec, be_msix, 0, eqo->desc, eqo);
 		if (status)
 			goto err_msix;
 
-- 
2.19.1


From 8290ec285303f86df16140cb3ccdfe23fc309740 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 29 Oct 2018 23:13:11 +0800
Subject: [PATCH 20/20] sctp: check policy more carefully when getting pr
 status

[ Upstream commit 713358369382cebf92f6e98ce2005f94e7344931 ]

When getting pr_assocstatus and pr_streamstatus by sctp_getsockopt,
it doesn't correctly process the case when policy is set with
SCTP_PR_SCTP_ALL | SCTP_PR_SCTP_MASK. It even causes a
slab-out-of-bounds in sctp_getsockopt_pr_streamstatus().

This patch fixes it by return -EINVAL for this case.

Fixes: 0ac1077e3a54 ("sctp: get pr_assoc and pr_stream all status with SCTP_PR_SCTP_ALL")
Reported-by: syzbot+5da0d0a72a9e7d791748@syzkaller.appspotmail.com
Suggested-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index c1c1bda334a4..c1693e28aed4 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -7101,14 +7101,15 @@ static int sctp_getsockopt_pr_assocstatus(struct sock *sk, int len,
 	}
 
 	policy = params.sprstat_policy;
-	if (!policy || (policy & ~(SCTP_PR_SCTP_MASK | SCTP_PR_SCTP_ALL)))
+	if (!policy || (policy & ~(SCTP_PR_SCTP_MASK | SCTP_PR_SCTP_ALL)) ||
+	    ((policy & SCTP_PR_SCTP_ALL) && (policy & SCTP_PR_SCTP_MASK)))
 		goto out;
 
 	asoc = sctp_id2assoc(sk, params.sprstat_assoc_id);
 	if (!asoc)
 		goto out;
 
-	if (policy & SCTP_PR_SCTP_ALL) {
+	if (policy == SCTP_PR_SCTP_ALL) {
 		params.sprstat_abandoned_unsent = 0;
 		params.sprstat_abandoned_sent = 0;
 		for (policy = 0; policy <= SCTP_PR_INDEX(MAX); policy++) {
@@ -7160,7 +7161,8 @@ static int sctp_getsockopt_pr_streamstatus(struct sock *sk, int len,
 	}
 
 	policy = params.sprstat_policy;
-	if (!policy || (policy & ~(SCTP_PR_SCTP_MASK | SCTP_PR_SCTP_ALL)))
+	if (!policy || (policy & ~(SCTP_PR_SCTP_MASK | SCTP_PR_SCTP_ALL)) ||
+	    ((policy & SCTP_PR_SCTP_ALL) && (policy & SCTP_PR_SCTP_MASK)))
 		goto out;
 
 	asoc = sctp_id2assoc(sk, params.sprstat_assoc_id);
-- 
2.19.1

Re: [PATCHES] Networking

[Greg KH]

On Thu, Nov 01, 2018 at 08:55:15PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.18 and
> v4.19 -stable, respectively.


Now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 104 bytes --]


Please queue up the following networking bug fixes for v4.18 and
v4.19 -stable, respectively.

Thanks!

[-- Attachment #2: net_418.mbox --]
[-- Type: Application/Octet-Stream, Size: 84873 bytes --]

From 0cda4d19d5f70eecaa0815f52c46e5a69591e42b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=EB=B0=B0=EC=84=9D=EC=A7=84?= <soukjin.bae@samsung.com>
Date: Fri, 9 Nov 2018 16:53:06 -0800
Subject: [PATCH 01/36] flow_dissector: do not dissect l4 ports for fragments
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 62230715fd2453b3ba948c9d83cfb3ada9169169 ]

Only first fragment has the sport/dport information,
not the following ones.

If we want consistent hash for all fragments, we need to
ignore ports even for first fragment.

This bug is visible for IPv6 traffic, if incoming fragments
do not have a flow label, since skb_get_hash() will give
different results for first fragment and following ones.

It is also visible if any routing rule wants dissection
and sport or dport.

See commit 5e5d6fed3741 ("ipv6: route: dissect flow
in input path if fib rules need it") for details.

[edumazet] rewrote the changelog completely.

Fixes: 06635a35d13d ("flow_dissect: use programable dissector in skb_flow_dissect and friends")
Signed-off-by: 배석진 <soukjin.bae@samsung.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/flow_dissector.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 53f96e4f7bf5..d48016da1b72 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -993,8 +993,8 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
 		break;
 	}
 
-	if (dissector_uses_key(flow_dissector,
-			       FLOW_DISSECTOR_KEY_PORTS)) {
+	if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS) &&
+	    !(key_control->flags & FLOW_DIS_IS_FRAGMENT)) {
 		key_ports = skb_flow_dissector_target(flow_dissector,
 						      FLOW_DISSECTOR_KEY_PORTS,
 						      target_container);
-- 
2.19.1


From 1c262b93d2e2ebec04a7f0d10a12b13d8713125e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Micha=C5=82=20Miros=C5=82aw?= <mirq-linux@rere.qmqm.pl>
Date: Wed, 7 Nov 2018 17:50:52 +0100
Subject: [PATCH 02/36] ibmvnic: fix accelerated VLAN handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit e84b47941e15e6666afb8ee8b21d1c3fc1a013af ]

Don't request tag insertion when it isn't present in outgoing skb.

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ibm/ibmvnic.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index d834308adf95..b6754cc925dc 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -1563,7 +1563,7 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 	tx_crq.v1.sge_len = cpu_to_be32(skb->len);
 	tx_crq.v1.ioba = cpu_to_be64(data_dma_addr);
 
-	if (adapter->vlan_header_insertion) {
+	if (adapter->vlan_header_insertion && skb_vlan_tag_present(skb)) {
 		tx_crq.v1.flags2 |= IBMVNIC_TX_VLAN_INSERT;
 		tx_crq.v1.vlan_id = cpu_to_be16(skb->vlan_tci);
 	}
-- 
2.19.1


From 7f5b8ff0b1144ebe1e7af2b6d743d7c2f5b99f05 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 16 Nov 2018 16:58:19 +0100
Subject: [PATCH 03/36] ip_tunnel: don't force DF when MTU is locked

[ Upstream commit 16f7eb2b77b55da816c4e207f3f9440a8cafc00a ]

The various types of tunnels running over IPv4 can ask to set the DF
bit to do PMTU discovery. However, PMTU discovery is subject to the
threshold set by the net.ipv4.route.min_pmtu sysctl, and is also
disabled on routes with "mtu lock". In those cases, we shouldn't set
the DF bit.

This patch makes setting the DF bit conditional on the route's MTU
locking state.

This issue seems to be older than git history.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_tunnel_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index dde671e97829..c248e0dccbe1 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -80,7 +80,7 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
 
 	iph->version	=	4;
 	iph->ihl	=	sizeof(struct iphdr) >> 2;
-	iph->frag_off	=	df;
+	iph->frag_off	=	ip_mtu_locked(&rt->dst) ? 0 : df;
 	iph->protocol	=	proto;
 	iph->tos	=	tos;
 	iph->daddr	=	dst;
-- 
2.19.1


From 9c378b6c512a29cb331c16120263821b47f761b4 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 14 Nov 2018 00:48:28 +0800
Subject: [PATCH 04/36] ipv6: fix a dst leak when removing its exception

[ Upstream commit 761f60261b4401aa368d71d431b4c218af0efcee ]

These is no need to hold dst before calling rt6_remove_exception_rt().
The call to dst_hold_safe() in ip6_link_failure() was for ip6_del_rt(),
which has been removed in Commit 93531c674315 ("net/ipv6: separate
handling of FIB entries from dst based routes"). Otherwise, it will
cause a dst leak.

This patch is to simply remove the dst_hold_safe() call before calling
rt6_remove_exception_rt() and also do the same in ip6_del_cached_rt().
It's safe, because the removal of the exception that holds its dst's
refcnt is protected by rt6_exception_lock.

Fixes: 93531c674315 ("net/ipv6: separate handling of FIB entries from dst based routes")
Fixes: 23fb93a4d3f1 ("net/ipv6: Cleanup exception and cache route handling")
Reported-by: Li Shuang <shuali@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index a243d5249b51..6045c7af02b6 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2256,8 +2256,7 @@ static void ip6_link_failure(struct sk_buff *skb)
 	if (rt) {
 		rcu_read_lock();
 		if (rt->rt6i_flags & RTF_CACHE) {
-			if (dst_hold_safe(&rt->dst))
-				rt6_remove_exception_rt(rt);
+			rt6_remove_exception_rt(rt);
 		} else {
 			struct fib6_info *from;
 			struct fib6_node *fn;
@@ -3259,8 +3258,8 @@ static int ip6_del_cached_rt(struct rt6_info *rt, struct fib6_config *cfg)
 	if (cfg->fc_flags & RTF_GATEWAY &&
 	    !ipv6_addr_equal(&cfg->fc_gateway, &rt->rt6i_gateway))
 		goto out;
-	if (dst_hold_safe(&rt->dst))
-		rc = rt6_remove_exception_rt(rt);
+
+	rc = rt6_remove_exception_rt(rt);
 out:
 	return rc;
 }
-- 
2.19.1


From b87a04b2290251d5aecc7b4a2141a14e1fae67ce Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Sun, 18 Nov 2018 10:45:30 -0800
Subject: [PATCH 05/36] ipv6: Fix PMTU updates for UDP/raw sockets in presence
 of VRF

[ Upstream commit 7ddacfa564870cdd97275fd87decb6174abc6380 ]

Preethi reported that PMTU discovery for UDP/raw applications is not
working in the presence of VRF when the socket is not bound to a device.
The problem is that ip6_sk_update_pmtu does not consider the L3 domain
of the skb device if the socket is not bound. Update the function to
set oif to the L3 master device if relevant.

Fixes: ca254490c8df ("net: Add VRF support to IPv6 stack")
Reported-by: Preethi Ramachandra <preethir@juniper.net>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 6045c7af02b6..b2edcf724cb8 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2384,10 +2384,13 @@ EXPORT_SYMBOL_GPL(ip6_update_pmtu);
 
 void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu)
 {
+	int oif = sk->sk_bound_dev_if;
 	struct dst_entry *dst;
 
-	ip6_update_pmtu(skb, sock_net(sk), mtu,
-			sk->sk_bound_dev_if, sk->sk_mark, sk->sk_uid);
+	if (!oif && skb->dev)
+		oif = l3mdev_master_ifindex(skb->dev);
+
+	ip6_update_pmtu(skb, sock_net(sk), mtu, oif, sk->sk_mark, sk->sk_uid);
 
 	dst = __sk_dst_get(sk);
 	if (!dst || !dst->obsolete ||
-- 
2.19.1


From 853bed216a2d4a781c7e3a8e320409ef6572b803 Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Thu, 1 Nov 2018 15:55:37 -0700
Subject: [PATCH 06/36] net: bcmgenet: protect stop from timeout

A timing hazard exists when the network interface is stopped that
allows a watchdog timeout to be processed by a separate core in
parallel. This creates the potential for the timeout handler to
wake the queues while the driver is shutting down, or access
registers after their clocks have been removed.

The more common case is that the watchdog timeout will produce a
warning message which doesn't lead to a crash. The chances of this
are greatly increased by the fact that bcmgenet_netif_stop stops
the transmit queues which can easily precipitate a watchdog time-
out because of stale trans_start data in the queues.

This commit corrects the behavior by ensuring that the watchdog
timeout is disabled before enterring bcmgenet_netif_stop. There
are currently only two users of the bcmgenet_netif_stop function:
close and suspend.

The close case already handles the issue by exiting the RUNNING
state before invoking the driver close service.

The suspend case now performs the netif_device_detach to exit the
PRESENT state before the call to bcmgenet_netif_stop rather than
after it.

These behaviors prevent any future scheduling of the driver timeout
service during the window. The netif_tx_stop_all_queues function
in bcmgenet_netif_stop is replaced with netif_tx_disable to ensure
synchronization with any transmit or timeout threads that may
already be executing on other cores.

For symmetry, the netif_device_attach call upon resume is moved to
after the call to bcmgenet_netif_start. Since it wakes the transmit
queues it is not necessary to invoke netif_tx_start_all_queues from
bcmgenet_netif_start so it is moved into the driver open service.

[ Upstream commit 09e805d2570a3a94f13dd9c9ad2bcab23da76e09 ]

Fixes: 1c1008c793fa ("net: bcmgenet: add main driver file")
Signed-off-by: Doug Berger <opendmb@gmail.com>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 20c1681bb1af..2d6f090bf644 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -2855,7 +2855,6 @@ static void bcmgenet_netif_start(struct net_device *dev)
 
 	umac_enable_set(priv, CMD_TX_EN | CMD_RX_EN, true);
 
-	netif_tx_start_all_queues(dev);
 	bcmgenet_enable_tx_napi(priv);
 
 	/* Monitor link interrupts now */
@@ -2937,6 +2936,8 @@ static int bcmgenet_open(struct net_device *dev)
 
 	bcmgenet_netif_start(dev);
 
+	netif_tx_start_all_queues(dev);
+
 	return 0;
 
 err_irq1:
@@ -2958,7 +2959,7 @@ static void bcmgenet_netif_stop(struct net_device *dev)
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 
 	bcmgenet_disable_tx_napi(priv);
-	netif_tx_stop_all_queues(dev);
+	netif_tx_disable(dev);
 
 	/* Disable MAC receive */
 	umac_enable_set(priv, CMD_RX_EN, false);
@@ -3620,13 +3621,13 @@ static int bcmgenet_suspend(struct device *d)
 	if (!netif_running(dev))
 		return 0;
 
+	netif_device_detach(dev);
+
 	bcmgenet_netif_stop(dev);
 
 	if (!device_may_wakeup(d))
 		phy_suspend(dev->phydev);
 
-	netif_device_detach(dev);
-
 	/* Prepare the device for Wake-on-LAN and switch to the slow clock */
 	if (device_may_wakeup(d) && priv->wolopts) {
 		ret = bcmgenet_power_down(priv, GENET_POWER_WOL_MAGIC);
@@ -3700,8 +3701,6 @@ static int bcmgenet_resume(struct device *d)
 	/* Always enable ring 16 - descriptor ring */
 	bcmgenet_enable_dma(priv, dma_ctrl);
 
-	netif_device_attach(dev);
-
 	if (!device_may_wakeup(d))
 		phy_resume(dev->phydev);
 
@@ -3710,6 +3709,8 @@ static int bcmgenet_resume(struct device *d)
 
 	bcmgenet_netif_start(dev);
 
+	netif_device_attach(dev);
+
 	return 0;
 
 out_clk_disable:
-- 
2.19.1


From a5fc9ca6224d3ca98301da4f58343eeee921d72e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 17 Nov 2018 21:57:02 -0800
Subject: [PATCH 07/36] net-gro: reset skb->pkt_type in napi_reuse_skb()

[ Upstream commit 33d9a2c72f086cbf1087b2fd2d1a15aa9df14a7f ]

eth_type_trans() assumes initial value for skb->pkt_type
is PACKET_HOST.

This is indeed the value right after a fresh skb allocation.

However, it is possible that GRO merged a packet with a different
value (like PACKET_OTHERHOST in case macvlan is used), so
we need to make sure napi->skb will have pkt_type set back to
PACKET_HOST.

Otherwise, valid packets might be dropped by the stack because
their pkt_type is not PACKET_HOST.

napi_reuse_skb() was added in commit 96e93eab2033 ("gro: Add
internal interfaces for VLAN"), but this bug always has
been there.

Fixes: 96e93eab2033 ("gro: Add internal interfaces for VLAN")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/core/dev.c b/net/core/dev.c
index bf669e77f9f3..6ace8d201ab9 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5195,6 +5195,10 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
 	skb->vlan_tci = 0;
 	skb->dev = napi->dev;
 	skb->skb_iif = 0;
+
+	/* eth_type_trans() assumes pkt_type is PACKET_HOST */
+	skb->pkt_type = PACKET_HOST;
+
 	skb->encapsulation = 0;
 	skb_shinfo(skb)->gso_type = 0;
 	skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));
-- 
2.19.1


From 020ff54b4a78aa7a6497e35a5ed4c4ae00c15766 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 18 Nov 2018 15:21:53 +0800
Subject: [PATCH 08/36] sctp: not allow to set asoc prsctp_enable by sockopt

[ Upstream commit cc3ccf26f0649089b3a34a2781977755ea36e72c ]

As rfc7496#section4.5 says about SCTP_PR_SUPPORTED:

   This socket option allows the enabling or disabling of the
   negotiation of PR-SCTP support for future associations.  For existing
   associations, it allows one to query whether or not PR-SCTP support
   was negotiated on a particular association.

It means only sctp sock's prsctp_enable can be set.

Note that for the limitation of SCTP_{CURRENT|ALL}_ASSOC, we will
add it when introducing SCTP_{FUTURE|CURRENT|ALL}_ASSOC for linux
sctp in another patchset.

v1->v2:
  - drop the params.assoc_id check as Neil suggested.

Fixes: 28aa4c26fce2 ("sctp: add SCTP_PR_SUPPORTED on sctp sockopt")
Reported-by: Ying Xu <yinxu@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 26 +++++---------------------
 1 file changed, 5 insertions(+), 21 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 9d903b870790..18f09e431391 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -3855,32 +3855,16 @@ static int sctp_setsockopt_pr_supported(struct sock *sk,
 					unsigned int optlen)
 {
 	struct sctp_assoc_value params;
-	struct sctp_association *asoc;
-	int retval = -EINVAL;
 
 	if (optlen != sizeof(params))
-		goto out;
-
-	if (copy_from_user(&params, optval, optlen)) {
-		retval = -EFAULT;
-		goto out;
-	}
-
-	asoc = sctp_id2assoc(sk, params.assoc_id);
-	if (asoc) {
-		asoc->prsctp_enable = !!params.assoc_value;
-	} else if (!params.assoc_id) {
-		struct sctp_sock *sp = sctp_sk(sk);
+		return -EINVAL;
 
-		sp->ep->prsctp_enable = !!params.assoc_value;
-	} else {
-		goto out;
-	}
+	if (copy_from_user(&params, optval, optlen))
+		return -EFAULT;
 
-	retval = 0;
+	sctp_sk(sk)->ep->prsctp_enable = !!params.assoc_value;
 
-out:
-	return retval;
+	return 0;
 }
 
 static int sctp_setsockopt_default_prinfo(struct sock *sk,
-- 
2.19.1


From 699b1909a1b1ee5e54c1dfda490e1cb19c7a3b72 Mon Sep 17 00:00:00 2001
From: Stephen Mallon <stephen.mallon@sydney.edu.au>
Date: Tue, 20 Nov 2018 19:15:02 +1100
Subject: [PATCH 09/36] tcp: Fix SOF_TIMESTAMPING_RX_HARDWARE to use the latest
 timestamp during TCP coalescing

[ Upstream commit cadf9df27e7cf40e390e060a1c71bb86ecde798b ]

During tcp coalescing ensure that the skb hardware timestamp refers to the
highest sequence number data.
Previously only the software timestamp was updated during coalescing.

Signed-off-by: Stephen Mallon <stephen.mallon@sydney.edu.au>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 8b7294688633..fea8745699c3 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4360,6 +4360,7 @@ static bool tcp_try_coalesce(struct sock *sk,
 	if (TCP_SKB_CB(from)->has_rxtstamp) {
 		TCP_SKB_CB(to)->has_rxtstamp = true;
 		to->tstamp = from->tstamp;
+		skb_hwtstamps(to)->hwtstamp = skb_hwtstamps(from)->hwtstamp;
 	}
 
 	return true;
-- 
2.19.1


From 3e5dec1c27c2a365c9bdf1410ca3432094415871 Mon Sep 17 00:00:00 2001
From: Siva Reddy Kallam <siva.kallam@broadcom.com>
Date: Tue, 20 Nov 2018 10:04:04 +0530
Subject: [PATCH 10/36] tg3: Add PHY reset for 5717/5719/5720 in change ring
 and flow control paths

[ Upstream commit 59663e42199c93d1d7314d1446f6782fc4b1eb81 ]

This patch has the fix to avoid PHY lockup with 5717/5719/5720 in change
ring and flow control paths. This patch solves the RX hang while doing
continuous ring or flow control parameters with heavy traffic from peer.

Signed-off-by: Siva Reddy Kallam <siva.kallam@broadcom.com>
Acked-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/tg3.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index aa1374d0af93..c03296c204c2 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -12411,6 +12411,7 @@ static int tg3_set_ringparam(struct net_device *dev, struct ethtool_ringparam *e
 {
 	struct tg3 *tp = netdev_priv(dev);
 	int i, irq_sync = 0, err = 0;
+	bool reset_phy = false;
 
 	if ((ering->rx_pending > tp->rx_std_ring_mask) ||
 	    (ering->rx_jumbo_pending > tp->rx_jmb_ring_mask) ||
@@ -12442,7 +12443,13 @@ static int tg3_set_ringparam(struct net_device *dev, struct ethtool_ringparam *e
 
 	if (netif_running(dev)) {
 		tg3_halt(tp, RESET_KIND_SHUTDOWN, 1);
-		err = tg3_restart_hw(tp, false);
+		/* Reset PHY to avoid PHY lock up */
+		if (tg3_asic_rev(tp) == ASIC_REV_5717 ||
+		    tg3_asic_rev(tp) == ASIC_REV_5719 ||
+		    tg3_asic_rev(tp) == ASIC_REV_5720)
+			reset_phy = true;
+
+		err = tg3_restart_hw(tp, reset_phy);
 		if (!err)
 			tg3_netif_start(tp);
 	}
@@ -12476,6 +12483,7 @@ static int tg3_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam
 {
 	struct tg3 *tp = netdev_priv(dev);
 	int err = 0;
+	bool reset_phy = false;
 
 	if (tp->link_config.autoneg == AUTONEG_ENABLE)
 		tg3_warn_mgmt_link_flap(tp);
@@ -12566,7 +12574,13 @@ static int tg3_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam
 
 		if (netif_running(dev)) {
 			tg3_halt(tp, RESET_KIND_SHUTDOWN, 1);
-			err = tg3_restart_hw(tp, false);
+			/* Reset PHY to avoid PHY lock up */
+			if (tg3_asic_rev(tp) == ASIC_REV_5717 ||
+			    tg3_asic_rev(tp) == ASIC_REV_5719 ||
+			    tg3_asic_rev(tp) == ASIC_REV_5720)
+				reset_phy = true;
+
+			err = tg3_restart_hw(tp, reset_phy);
 			if (!err)
 				tg3_netif_start(tp);
 		}
-- 
2.19.1


From c1ba06da59ab1ea67c265886e4b0a2bfc0712d0d Mon Sep 17 00:00:00 2001
From: Jon Maloy <donmalo99@gmail.com>
Date: Sat, 17 Nov 2018 12:17:06 -0500
Subject: [PATCH 11/36] tipc: don't assume linear buffer when reading ancillary
 data

[ Upstream commit 1c1274a56999fbdf9cf84e332b28448bb2d55221 ]

The code for reading ancillary data from a received buffer is assuming
the buffer is linear. To make this assumption true we have to linearize
the buffer before message data is read.

Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/socket.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index cdaf3534e373..c7e4aff8935f 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1541,16 +1541,17 @@ static void tipc_sk_set_orig_addr(struct msghdr *m, struct sk_buff *skb)
 /**
  * tipc_sk_anc_data_recv - optionally capture ancillary data for received message
  * @m: descriptor for message info
- * @msg: received message header
+ * @skb: received message buffer
  * @tsk: TIPC port associated with message
  *
  * Note: Ancillary data is not captured if not requested by receiver.
  *
  * Returns 0 if successful, otherwise errno
  */
-static int tipc_sk_anc_data_recv(struct msghdr *m, struct tipc_msg *msg,
+static int tipc_sk_anc_data_recv(struct msghdr *m, struct sk_buff *skb,
 				 struct tipc_sock *tsk)
 {
+	struct tipc_msg *msg;
 	u32 anc_data[3];
 	u32 err;
 	u32 dest_type;
@@ -1559,6 +1560,7 @@ static int tipc_sk_anc_data_recv(struct msghdr *m, struct tipc_msg *msg,
 
 	if (likely(m->msg_controllen == 0))
 		return 0;
+	msg = buf_msg(skb);
 
 	/* Optionally capture errored message object(s) */
 	err = msg ? msg_errcode(msg) : 0;
@@ -1569,6 +1571,9 @@ static int tipc_sk_anc_data_recv(struct msghdr *m, struct tipc_msg *msg,
 		if (res)
 			return res;
 		if (anc_data[1]) {
+			if (skb_linearize(skb))
+				return -ENOMEM;
+			msg = buf_msg(skb);
 			res = put_cmsg(m, SOL_TIPC, TIPC_RETDATA, anc_data[1],
 				       msg_data(msg));
 			if (res)
@@ -1730,9 +1735,10 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m,
 
 	/* Collect msg meta data, including error code and rejected data */
 	tipc_sk_set_orig_addr(m, skb);
-	rc = tipc_sk_anc_data_recv(m, hdr, tsk);
+	rc = tipc_sk_anc_data_recv(m, skb, tsk);
 	if (unlikely(rc))
 		goto exit;
+	hdr = buf_msg(skb);
 
 	/* Capture data if non-error msg, otherwise just set return value */
 	if (likely(!err)) {
@@ -1842,9 +1848,10 @@ static int tipc_recvstream(struct socket *sock, struct msghdr *m,
 		/* Collect msg meta data, incl. error code and rejected data */
 		if (!copied) {
 			tipc_sk_set_orig_addr(m, skb);
-			rc = tipc_sk_anc_data_recv(m, hdr, tsk);
+			rc = tipc_sk_anc_data_recv(m, skb, tsk);
 			if (rc)
 				break;
+			hdr = buf_msg(skb);
 		}
 
 		/* Copy data if msg ok, otherwise return error/partial data */
-- 
2.19.1


From a10d2105b346c8d3a775a510688f9f5c7404a609 Mon Sep 17 00:00:00 2001
From: Jon Maloy <donmalo99@gmail.com>
Date: Fri, 16 Nov 2018 16:55:04 -0500
Subject: [PATCH 12/36] tipc: fix lockdep warning when reinitilaizing sockets

[ Upstream commit adba75be0d23cca92a028749d92c60c8909bbdb3 ]

We get the following warning:

[   47.926140] 32-bit node address hash set to 2010a0a
[   47.927202]
[   47.927433] ================================
[   47.928050] WARNING: inconsistent lock state
[   47.928661] 4.19.0+ #37 Tainted: G            E
[   47.929346] --------------------------------
[   47.929954] inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage.
[   47.930116] swapper/3/0 [HC0[0]:SC1[3]:HE1:SE0] takes:
[   47.930116] 00000000af8bc31e (&(&ht->lock)->rlock){+.?.}, at: rhashtable_walk_enter+0x36/0xb0
[   47.930116] {SOFTIRQ-ON-W} state was registered at:
[   47.930116]   _raw_spin_lock+0x29/0x60
[   47.930116]   rht_deferred_worker+0x556/0x810
[   47.930116]   process_one_work+0x1f5/0x540
[   47.930116]   worker_thread+0x64/0x3e0
[   47.930116]   kthread+0x112/0x150
[   47.930116]   ret_from_fork+0x3a/0x50
[   47.930116] irq event stamp: 14044
[   47.930116] hardirqs last  enabled at (14044): [<ffffffff9a07fbba>] __local_bh_enable_ip+0x7a/0xf0
[   47.938117] hardirqs last disabled at (14043): [<ffffffff9a07fb81>] __local_bh_enable_ip+0x41/0xf0
[   47.938117] softirqs last  enabled at (14028): [<ffffffff9a0803ee>] irq_enter+0x5e/0x60
[   47.938117] softirqs last disabled at (14029): [<ffffffff9a0804a5>] irq_exit+0xb5/0xc0
[   47.938117]
[   47.938117] other info that might help us debug this:
[   47.938117]  Possible unsafe locking scenario:
[   47.938117]
[   47.938117]        CPU0
[   47.938117]        ----
[   47.938117]   lock(&(&ht->lock)->rlock);
[   47.938117]   <Interrupt>
[   47.938117]     lock(&(&ht->lock)->rlock);
[   47.938117]
[   47.938117]  *** DEADLOCK ***
[   47.938117]
[   47.938117] 2 locks held by swapper/3/0:
[   47.938117]  #0: 0000000062c64f90 ((&d->timer)){+.-.}, at: call_timer_fn+0x5/0x280
[   47.938117]  #1: 00000000ee39619c (&(&d->lock)->rlock){+.-.}, at: tipc_disc_timeout+0xc8/0x540 [tipc]
[   47.938117]
[   47.938117] stack backtrace:
[   47.938117] CPU: 3 PID: 0 Comm: swapper/3 Tainted: G            E     4.19.0+ #37
[   47.938117] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
[   47.938117] Call Trace:
[   47.938117]  <IRQ>
[   47.938117]  dump_stack+0x5e/0x8b
[   47.938117]  print_usage_bug+0x1ed/0x1ff
[   47.938117]  mark_lock+0x5b5/0x630
[   47.938117]  __lock_acquire+0x4c0/0x18f0
[   47.938117]  ? lock_acquire+0xa6/0x180
[   47.938117]  lock_acquire+0xa6/0x180
[   47.938117]  ? rhashtable_walk_enter+0x36/0xb0
[   47.938117]  _raw_spin_lock+0x29/0x60
[   47.938117]  ? rhashtable_walk_enter+0x36/0xb0
[   47.938117]  rhashtable_walk_enter+0x36/0xb0
[   47.938117]  tipc_sk_reinit+0xb0/0x410 [tipc]
[   47.938117]  ? mark_held_locks+0x6f/0x90
[   47.938117]  ? __local_bh_enable_ip+0x7a/0xf0
[   47.938117]  ? lockdep_hardirqs_on+0x20/0x1a0
[   47.938117]  tipc_net_finalize+0xbf/0x180 [tipc]
[   47.938117]  tipc_disc_timeout+0x509/0x540 [tipc]
[   47.938117]  ? call_timer_fn+0x5/0x280
[   47.938117]  ? tipc_disc_msg_xmit.isra.19+0xa0/0xa0 [tipc]
[   47.938117]  ? tipc_disc_msg_xmit.isra.19+0xa0/0xa0 [tipc]
[   47.938117]  call_timer_fn+0xa1/0x280
[   47.938117]  ? tipc_disc_msg_xmit.isra.19+0xa0/0xa0 [tipc]
[   47.938117]  run_timer_softirq+0x1f2/0x4d0
[   47.938117]  __do_softirq+0xfc/0x413
[   47.938117]  irq_exit+0xb5/0xc0
[   47.938117]  smp_apic_timer_interrupt+0xac/0x210
[   47.938117]  apic_timer_interrupt+0xf/0x20
[   47.938117]  </IRQ>
[   47.938117] RIP: 0010:default_idle+0x1c/0x140
[   47.938117] Code: 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1f 44 00 00 41 54 55 53 65 8b 2d d8 2b 74 65 0f 1f 44 00 00 e8 c6 2c 8b ff fb f4 <65> 8b 2d c5 2b 74 65 0f 1f 44 00 00 5b 5d 41 5c c3 65 8b 05 b4 2b
[   47.938117] RSP: 0018:ffffaf6ac0207ec8 EFLAGS: 00000206 ORIG_RAX: ffffffffffffff13
[   47.938117] RAX: ffff8f5b3735e200 RBX: 0000000000000003 RCX: 0000000000000001
[   47.938117] RDX: 0000000000000001 RSI: 0000000000000001 RDI: ffff8f5b3735e200
[   47.938117] RBP: 0000000000000003 R08: 0000000000000001 R09: 0000000000000000
[   47.938117] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
[   47.938117] R13: 0000000000000000 R14: ffff8f5b3735e200 R15: ffff8f5b3735e200
[   47.938117]  ? default_idle+0x1a/0x140
[   47.938117]  do_idle+0x1bc/0x280
[   47.938117]  cpu_startup_entry+0x19/0x20
[   47.938117]  start_secondary+0x187/0x1c0
[   47.938117]  secondary_startup_64+0xa4/0xb0

The reason seems to be that tipc_net_finalize()->tipc_sk_reinit() is
calling the function rhashtable_walk_enter() within a timer interrupt.
We fix this by executing tipc_net_finalize() in work queue context.

Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/discover.c | 19 ++++++++++---------
 net/tipc/net.c      | 45 +++++++++++++++++++++++++++++++++++++--------
 net/tipc/net.h      |  2 +-
 3 files changed, 48 insertions(+), 18 deletions(-)

diff --git a/net/tipc/discover.c b/net/tipc/discover.c
index 2830709957bd..c138d68e8a69 100644
--- a/net/tipc/discover.c
+++ b/net/tipc/discover.c
@@ -166,7 +166,8 @@ static bool tipc_disc_addr_trial_msg(struct tipc_discoverer *d,
 
 	/* Apply trial address if we just left trial period */
 	if (!trial && !self) {
-		tipc_net_finalize(net, tn->trial_addr);
+		tipc_sched_net_finalize(net, tn->trial_addr);
+		msg_set_prevnode(buf_msg(d->skb), tn->trial_addr);
 		msg_set_type(buf_msg(d->skb), DSC_REQ_MSG);
 	}
 
@@ -300,14 +301,12 @@ static void tipc_disc_timeout(struct timer_list *t)
 		goto exit;
 	}
 
-	/* Trial period over ? */
-	if (!time_before(jiffies, tn->addr_trial_end)) {
-		/* Did we just leave it ? */
-		if (!tipc_own_addr(net))
-			tipc_net_finalize(net, tn->trial_addr);
-
-		msg_set_type(buf_msg(d->skb), DSC_REQ_MSG);
-		msg_set_prevnode(buf_msg(d->skb), tipc_own_addr(net));
+	/* Did we just leave trial period ? */
+	if (!time_before(jiffies, tn->addr_trial_end) && !tipc_own_addr(net)) {
+		mod_timer(&d->timer, jiffies + TIPC_DISC_INIT);
+		spin_unlock_bh(&d->lock);
+		tipc_sched_net_finalize(net, tn->trial_addr);
+		return;
 	}
 
 	/* Adjust timeout interval according to discovery phase */
@@ -319,6 +318,8 @@ static void tipc_disc_timeout(struct timer_list *t)
 			d->timer_intv = TIPC_DISC_SLOW;
 		else if (!d->num_nodes && d->timer_intv > TIPC_DISC_FAST)
 			d->timer_intv = TIPC_DISC_FAST;
+		msg_set_type(buf_msg(d->skb), DSC_REQ_MSG);
+		msg_set_prevnode(buf_msg(d->skb), tn->trial_addr);
 	}
 
 	mod_timer(&d->timer, jiffies + d->timer_intv);
diff --git a/net/tipc/net.c b/net/tipc/net.c
index 62199cf5a56c..f076edb74338 100644
--- a/net/tipc/net.c
+++ b/net/tipc/net.c
@@ -104,6 +104,14 @@
  *     - A local spin_lock protecting the queue of subscriber events.
 */
 
+struct tipc_net_work {
+	struct work_struct work;
+	struct net *net;
+	u32 addr;
+};
+
+static void tipc_net_finalize(struct net *net, u32 addr);
+
 int tipc_net_init(struct net *net, u8 *node_id, u32 addr)
 {
 	if (tipc_own_id(net)) {
@@ -119,17 +127,38 @@ int tipc_net_init(struct net *net, u8 *node_id, u32 addr)
 	return 0;
 }
 
-void tipc_net_finalize(struct net *net, u32 addr)
+static void tipc_net_finalize(struct net *net, u32 addr)
 {
 	struct tipc_net *tn = tipc_net(net);
 
-	if (!cmpxchg(&tn->node_addr, 0, addr)) {
-		tipc_set_node_addr(net, addr);
-		tipc_named_reinit(net);
-		tipc_sk_reinit(net);
-		tipc_nametbl_publish(net, TIPC_CFG_SRV, addr, addr,
-				     TIPC_CLUSTER_SCOPE, 0, addr);
-	}
+	if (cmpxchg(&tn->node_addr, 0, addr))
+		return;
+	tipc_set_node_addr(net, addr);
+	tipc_named_reinit(net);
+	tipc_sk_reinit(net);
+	tipc_nametbl_publish(net, TIPC_CFG_SRV, addr, addr,
+			     TIPC_CLUSTER_SCOPE, 0, addr);
+}
+
+static void tipc_net_finalize_work(struct work_struct *work)
+{
+	struct tipc_net_work *fwork;
+
+	fwork = container_of(work, struct tipc_net_work, work);
+	tipc_net_finalize(fwork->net, fwork->addr);
+	kfree(fwork);
+}
+
+void tipc_sched_net_finalize(struct net *net, u32 addr)
+{
+	struct tipc_net_work *fwork = kzalloc(sizeof(*fwork), GFP_ATOMIC);
+
+	if (!fwork)
+		return;
+	INIT_WORK(&fwork->work, tipc_net_finalize_work);
+	fwork->net = net;
+	fwork->addr = addr;
+	schedule_work(&fwork->work);
 }
 
 void tipc_net_stop(struct net *net)
diff --git a/net/tipc/net.h b/net/tipc/net.h
index 09ad02b50bb1..b7f2e364eb99 100644
--- a/net/tipc/net.h
+++ b/net/tipc/net.h
@@ -42,7 +42,7 @@
 extern const struct nla_policy tipc_nl_net_policy[];
 
 int tipc_net_init(struct net *net, u8 *node_id, u32 addr);
-void tipc_net_finalize(struct net *net, u32 addr);
+void tipc_sched_net_finalize(struct net *net, u32 addr);
 void tipc_net_stop(struct net *net);
 int tipc_nl_net_dump(struct sk_buff *skb, struct netlink_callback *cb);
 int tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info);
-- 
2.19.1


From cce8394da8ab0deaaa32722636d8a9c2ee58f40d Mon Sep 17 00:00:00 2001
From: Matthew Cover <werekraken@gmail.com>
Date: Sun, 18 Nov 2018 00:46:00 -0700
Subject: [PATCH 13/36] tuntap: fix multiqueue rx

[ Upstream commit 8ebebcba559a1bfbaec7bbda64feb9870b9c58da ]

When writing packets to a descriptor associated with a combined queue, the
packets should end up on that queue.

Before this change all packets written to any descriptor associated with a
tap interface end up on rx-0, even when the descriptor is associated with a
different queue.

The rx traffic can be generated by either of the following.
  1. a simple tap program which spins up multiple queues and writes packets
     to each of the file descriptors
  2. tx from a qemu vm with a tap multiqueue netdev

The queue for rx traffic can be observed by either of the following (done
on the hypervisor in the qemu case).
  1. a simple netmap program which opens and reads from per-queue
     descriptors
  2. configuring RPS and doing per-cpu captures with rxtxcpu

Alternatively, if you printk() the return value of skb_get_rx_queue() just
before each instance of netif_receive_skb() in tun.c, you will get 65535
for every skb.

Calling skb_record_rx_queue() to set the rx queue to the queue_index fixes
the association between descriptor and rx queue.

Signed-off-by: Matthew Cover <matthew.cover@stackpath.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 546081993ecf..b69975c6d309 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1567,6 +1567,7 @@ static void tun_rx_batched(struct tun_struct *tun, struct tun_file *tfile,
 
 	if (!rx_batched || (!more && skb_queue_empty(queue))) {
 		local_bh_disable();
+		skb_record_rx_queue(skb, tfile->queue_index);
 		netif_receive_skb(skb);
 		local_bh_enable();
 		return;
@@ -1586,8 +1587,11 @@ static void tun_rx_batched(struct tun_struct *tun, struct tun_file *tfile,
 		struct sk_buff *nskb;
 
 		local_bh_disable();
-		while ((nskb = __skb_dequeue(&process_queue)))
+		while ((nskb = __skb_dequeue(&process_queue))) {
+			skb_record_rx_queue(nskb, tfile->queue_index);
 			netif_receive_skb(nskb);
+		}
+		skb_record_rx_queue(skb, tfile->queue_index);
 		netif_receive_skb(skb);
 		local_bh_enable();
 	}
-- 
2.19.1


From 4f1482860353b87a6f68260128663ba154246b6c Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 1 Nov 2018 15:55:38 -0700
Subject: [PATCH 14/36] net: systemport: Protect stop from timeout

[ Upstream commit 7cb6a2a2c72c1ed8f42fb01f1a661281b568dead ]

A timing hazard exists when the network interface is stopped that
allows a watchdog timeout to be processed by a separate core in
parallel. This creates the potential for the timeout handler to
wake the queues while the driver is shutting down, or access
registers after their clocks have been removed.

The more common case is that the watchdog timeout will produce a
warning message which doesn't lead to a crash. The chances of this
are greatly increased by the fact that bcm_sysport_netif_stop stops
the transmit queues which can easily precipitate a watchdog time-
out because of stale trans_start data in the queues.

This commit corrects the behavior by ensuring that the watchdog
timeout is disabled before enterring bcm_sysport_netif_stop. There
are currently only two users of the bcm_sysport_netif_stop function:
close and suspend.

The close case already handles the issue by exiting the RUNNING
state before invoking the driver close service.

The suspend case now performs the netif_device_detach to exit the
PRESENT state before the call to bcm_sysport_netif_stop rather than
after it.

These behaviors prevent any future scheduling of the driver timeout
service during the window. The netif_tx_stop_all_queues function
in bcm_sysport_netif_stop is replaced with netif_tx_disable to ensure
synchronization with any transmit or timeout threads that may
already be executing on other cores.

For symmetry, the netif_device_attach call upon resume is moved to
after the call to bcm_sysport_netif_start. Since it wakes the transmit
queues it is not necessary to invoke netif_tx_start_all_queues from
bcm_sysport_netif_start so it is moved into the driver open service.

Fixes: 40755a0fce17 ("net: systemport: add suspend and resume support")
Fixes: 80105befdb4b ("net: systemport: add Broadcom SYSTEMPORT Ethernet MAC driver")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bcmsysport.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 7a03ee45840e..8ff7ea0a2395 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -1869,9 +1869,6 @@ static void bcm_sysport_netif_start(struct net_device *dev)
 		intrl2_1_mask_clear(priv, 0xffffffff);
 	else
 		intrl2_0_mask_clear(priv, INTRL2_0_TDMA_MBDONE_MASK);
-
-	/* Last call before we start the real business */
-	netif_tx_start_all_queues(dev);
 }
 
 static void rbuf_init(struct bcm_sysport_priv *priv)
@@ -2017,6 +2014,8 @@ static int bcm_sysport_open(struct net_device *dev)
 
 	bcm_sysport_netif_start(dev);
 
+	netif_tx_start_all_queues(dev);
+
 	return 0;
 
 out_clear_rx_int:
@@ -2040,7 +2039,7 @@ static void bcm_sysport_netif_stop(struct net_device *dev)
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
 
 	/* stop all software from updating hardware */
-	netif_tx_stop_all_queues(dev);
+	netif_tx_disable(dev);
 	napi_disable(&priv->napi);
 	cancel_work_sync(&priv->dim.dim.work);
 	phy_stop(dev->phydev);
@@ -2478,12 +2477,12 @@ static int bcm_sysport_suspend(struct device *d)
 	if (!netif_running(dev))
 		return 0;
 
+	netif_device_detach(dev);
+
 	bcm_sysport_netif_stop(dev);
 
 	phy_suspend(dev->phydev);
 
-	netif_device_detach(dev);
-
 	/* Disable UniMAC RX */
 	umac_enable_set(priv, CMD_RX_EN, 0);
 
@@ -2567,8 +2566,6 @@ static int bcm_sysport_resume(struct device *d)
 		goto out_free_rx_ring;
 	}
 
-	netif_device_attach(dev);
-
 	/* RX pipe enable */
 	topctrl_writel(priv, 0, RX_FLUSH_CNTL);
 
@@ -2613,6 +2610,8 @@ static int bcm_sysport_resume(struct device *d)
 
 	bcm_sysport_netif_start(dev);
 
+	netif_device_attach(dev);
+
 	return 0;
 
 out_free_rx_ring:
-- 
2.19.1


From 3d1a993e27692843682a3ce99d9deacc016826ea Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 18 Nov 2018 16:14:47 +0800
Subject: [PATCH 15/36] Revert "sctp: remove sctp_transport_pmtu_check"

[ Upstream commit 69fec325a64383667b8a35df5d48d6ce52fb2782 ]

This reverts commit 22d7be267eaa8114dcc28d66c1c347f667d7878a.

The dst's mtu in transport can be updated by a non sctp place like
in xfrm where the MTU information didn't get synced between asoc,
transport and dst, so it is still needed to do the pmtu check
in sctp_packet_config.

Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/sctp.h | 12 ++++++++++++
 net/sctp/output.c       |  3 +++
 2 files changed, 15 insertions(+)

diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 8c2caa370e0f..ab9242e51d9e 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -608,4 +608,16 @@ static inline __u32 sctp_dst_mtu(const struct dst_entry *dst)
 				 SCTP_DEFAULT_MINSEGMENT));
 }
 
+static inline bool sctp_transport_pmtu_check(struct sctp_transport *t)
+{
+	__u32 pmtu = sctp_dst_mtu(t->dst);
+
+	if (t->pathmtu == pmtu)
+		return true;
+
+	t->pathmtu = pmtu;
+
+	return false;
+}
+
 #endif /* __net_sctp_h__ */
diff --git a/net/sctp/output.c b/net/sctp/output.c
index 7f849b01ec8e..2b258e57384f 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -118,6 +118,9 @@ void sctp_packet_config(struct sctp_packet *packet, __u32 vtag,
 		sctp_transport_route(tp, NULL, sp);
 		if (asoc->param_flags & SPP_PMTUD_ENABLE)
 			sctp_assoc_sync_pmtu(asoc);
+	} else if (!sctp_transport_pmtu_check(tp)) {
+		if (asoc->param_flags & SPP_PMTUD_ENABLE)
+			sctp_assoc_sync_pmtu(asoc);
 	}
 
 	/* If there a is a prepend chunk stick it on the list before
-- 
2.19.1


From b83fbe7ca7dec923ac6603f73b881dd0621f41fb Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Sun, 28 Oct 2018 12:27:29 +0200
Subject: [PATCH 16/36] net/mlx5e: Always use the match level enum when parsing
 TC rule match

[ Upstream commit 83621b7df6a646e550fd3d36db2e301cf9a5096b ]

We get the match level (none, l2, l3, l4) while going over the match
dissectors of an offloaded tc rule. When doing this, the match level
enum and the not min inline enum values should be used, fix that.

This worked accidentally b/c both enums have the same numerical values.

Fixes: d708f902989b ('net/mlx5e: Get the required HW match level while parsing TC flow matches')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 701af5ffcbc9..679675a9645d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1385,10 +1385,10 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 
 			/* the HW doesn't need L3 inline to match on frag=no */
 			if (!(key->flags & FLOW_DIS_IS_FRAGMENT))
-				*match_level = MLX5_INLINE_MODE_L2;
+				*match_level = MLX5_MATCH_L2;
 	/* ***  L2 attributes parsing up to here *** */
 			else
-				*match_level = MLX5_INLINE_MODE_IP;
+				*match_level = MLX5_MATCH_L3;
 		}
 	}
 
-- 
2.19.1


From 8f3790f44f7f62deea025811223cd14a6542f9ec Mon Sep 17 00:00:00 2001
From: Valentine Fatiev <valentinef@mellanox.com>
Date: Wed, 17 Oct 2018 11:45:07 +0300
Subject: [PATCH 17/36] net/mlx5e: Fix selftest for small MTUs

[ Upstream commit 228c4cd04dfd0667eda182c91504b83c17d97584 ]

Loopback test had fixed packet size, which can be bigger than configured
MTU. Shorten the loopback packet size to be bigger than minimal MTU
allowed by the device. Text field removed from struct 'mlx5ehdr'
as redundant to allow send small packets as minimal allowed MTU.

Fixes: d605d66 ("net/mlx5e: Add support for ethtool self diagnostics test")
Signed-off-by: Valentine Fatiev <valentinef@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../ethernet/mellanox/mlx5/core/en_selftest.c | 26 +++++++------------
 1 file changed, 10 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
index 4d316cc9b008..5d827fced7c2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
@@ -98,18 +98,17 @@ static int mlx5e_test_link_speed(struct mlx5e_priv *priv)
 	return 1;
 }
 
-#ifdef CONFIG_INET
-/* loopback test */
-#define MLX5E_TEST_PKT_SIZE (MLX5E_RX_MAX_HEAD - NET_IP_ALIGN)
-static const char mlx5e_test_text[ETH_GSTRING_LEN] = "MLX5E SELF TEST";
-#define MLX5E_TEST_MAGIC 0x5AEED15C001ULL
-
 struct mlx5ehdr {
 	__be32 version;
 	__be64 magic;
-	char   text[ETH_GSTRING_LEN];
 };
 
+#ifdef CONFIG_INET
+/* loopback test */
+#define MLX5E_TEST_PKT_SIZE (sizeof(struct ethhdr) + sizeof(struct iphdr) +\
+			     sizeof(struct udphdr) + sizeof(struct mlx5ehdr))
+#define MLX5E_TEST_MAGIC 0x5AEED15C001ULL
+
 static struct sk_buff *mlx5e_test_get_udp_skb(struct mlx5e_priv *priv)
 {
 	struct sk_buff *skb = NULL;
@@ -117,10 +116,7 @@ static struct sk_buff *mlx5e_test_get_udp_skb(struct mlx5e_priv *priv)
 	struct ethhdr *ethh;
 	struct udphdr *udph;
 	struct iphdr *iph;
-	int datalen, iplen;
-
-	datalen = MLX5E_TEST_PKT_SIZE -
-		  (sizeof(*ethh) + sizeof(*iph) + sizeof(*udph));
+	int    iplen;
 
 	skb = netdev_alloc_skb(priv->netdev, MLX5E_TEST_PKT_SIZE);
 	if (!skb) {
@@ -149,7 +145,7 @@ static struct sk_buff *mlx5e_test_get_udp_skb(struct mlx5e_priv *priv)
 	/* Fill UDP header */
 	udph->source = htons(9);
 	udph->dest = htons(9); /* Discard Protocol */
-	udph->len = htons(datalen + sizeof(struct udphdr));
+	udph->len = htons(sizeof(struct mlx5ehdr) + sizeof(struct udphdr));
 	udph->check = 0;
 
 	/* Fill IP header */
@@ -157,7 +153,8 @@ static struct sk_buff *mlx5e_test_get_udp_skb(struct mlx5e_priv *priv)
 	iph->ttl = 32;
 	iph->version = 4;
 	iph->protocol = IPPROTO_UDP;
-	iplen = sizeof(struct iphdr) + sizeof(struct udphdr) + datalen;
+	iplen = sizeof(struct iphdr) + sizeof(struct udphdr) +
+		sizeof(struct mlx5ehdr);
 	iph->tot_len = htons(iplen);
 	iph->frag_off = 0;
 	iph->saddr = 0;
@@ -170,9 +167,6 @@ static struct sk_buff *mlx5e_test_get_udp_skb(struct mlx5e_priv *priv)
 	mlxh = skb_put(skb, sizeof(*mlxh));
 	mlxh->version = 0;
 	mlxh->magic = cpu_to_be64(MLX5E_TEST_MAGIC);
-	strlcpy(mlxh->text, mlx5e_test_text, sizeof(mlxh->text));
-	datalen -= sizeof(*mlxh);
-	skb_put_zero(skb, datalen);
 
 	skb->csum = 0;
 	skb->ip_summed = CHECKSUM_PARTIAL;
-- 
2.19.1


From 7716d0887fc4780b42acfe28928518c7891f908c Mon Sep 17 00:00:00 2001
From: Shay Agroskin <shayag@mellanox.com>
Date: Sun, 28 Oct 2018 09:06:11 +0200
Subject: [PATCH 18/36] net/mlx5e: Removed unnecessary warnings in FEC caps
 query

[ Upstream commit 64e283348458e2fd2fe41b60dfb6c30e88ee695f ]

Querying interface FEC caps with 'ethtool [int]' after link reset
throws warning regading link speed.
This warning is not needed as there is already an indication in
user space that the link is not up.

Fixes: 0696d60853d5 ("net/mlx5e: Receive buffer configuration")
Signed-off-by: Shay Agroskin <shayag@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/port.c        | 4 +---
 drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c | 4 +++-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
index 24e3b564964f..12e1682f940b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
@@ -88,10 +88,8 @@ int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
 
 	eth_proto_oper = MLX5_GET(ptys_reg, out, eth_proto_oper);
 	*speed = mlx5e_port_ptys2speed(eth_proto_oper);
-	if (!(*speed)) {
-		mlx5_core_warn(mdev, "cannot get port speed\n");
+	if (!(*speed))
 		err = -EINVAL;
-	}
 
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
index c047da8752da..eac245a93f91 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
@@ -130,8 +130,10 @@ static u32 calculate_xoff(struct mlx5e_priv *priv, unsigned int mtu)
 	int err;
 
 	err = mlx5e_port_linkspeed(priv->mdev, &speed);
-	if (err)
+	if (err) {
+		mlx5_core_warn(priv->mdev, "cannot get port speed\n");
 		return 0;
+	}
 
 	xoff = (301 + 216 * priv->dcbx.cable_len / 100) * speed / 1000 + 272 * mtu / 100;
 
-- 
2.19.1


From d44247a61ec2f0e9c3890d2283d38ba9b4c566cd Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 8 Nov 2018 17:34:27 -0800
Subject: [PATCH 19/36] inet: frags: better deal with smp races
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 0d5b9311baf27bb545f187f12ecfd558220c607d ]

Multiple cpus might attempt to insert a new fragment in rhashtable,
if for example RPS is buggy, as reported by 배석진 in
https://patchwork.ozlabs.org/patch/994601/

We use rhashtable_lookup_get_insert_key() instead of
rhashtable_insert_fast() to let cpus losing the race
free their own inet_frag_queue and use the one that
was inserted by another cpu.

Fixes: 648700f76b03 ("inet: frags: use rhashtables for reassembly units")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: 배석진 <soukjin.bae@samsung.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/inet_fragment.c | 29 +++++++++++++++--------------
 1 file changed, 15 insertions(+), 14 deletions(-)

diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 0d70608cc2e1..732b04f20c14 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -173,21 +173,22 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
 }
 
 static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf,
-						void *arg)
+						void *arg,
+						struct inet_frag_queue **prev)
 {
 	struct inet_frags *f = nf->f;
 	struct inet_frag_queue *q;
-	int err;
 
 	q = inet_frag_alloc(nf, f, arg);
-	if (!q)
+	if (!q) {
+		*prev = ERR_PTR(-ENOMEM);
 		return NULL;
-
+	}
 	mod_timer(&q->timer, jiffies + nf->timeout);
 
-	err = rhashtable_insert_fast(&nf->rhashtable, &q->node,
-				     f->rhash_params);
-	if (err < 0) {
+	*prev = rhashtable_lookup_get_insert_key(&nf->rhashtable, &q->key,
+						 &q->node, f->rhash_params);
+	if (*prev) {
 		q->flags |= INET_FRAG_COMPLETE;
 		inet_frag_kill(q);
 		inet_frag_destroy(q);
@@ -199,22 +200,22 @@ static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf,
 /* TODO : call from rcu_read_lock() and no longer use refcount_inc_not_zero() */
 struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key)
 {
-	struct inet_frag_queue *fq;
+	struct inet_frag_queue *fq = NULL, *prev;
 
 	if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh)
 		return NULL;
 
 	rcu_read_lock();
 
-	fq = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params);
-	if (fq) {
+	prev = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params);
+	if (!prev)
+		fq = inet_frag_create(nf, key, &prev);
+	if (prev && !IS_ERR(prev)) {
+		fq = prev;
 		if (!refcount_inc_not_zero(&fq->refcnt))
 			fq = NULL;
-		rcu_read_unlock();
-		return fq;
 	}
 	rcu_read_unlock();
-
-	return inet_frag_create(nf, key);
+	return fq;
 }
 EXPORT_SYMBOL(inet_frag_find);
-- 
2.19.1


From 2dbfb27c7bd6ea2bd0a32794031a0bfa2b4722b4 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 13 Nov 2018 01:08:25 +0800
Subject: [PATCH 20/36] l2tp: fix a sock refcnt leak in l2tp_tunnel_register

[ Upstream commit f8504f4ca0a0e9f84546ef86e00b24d2ea9a0bd2 ]

This issue happens when trying to add an existent tunnel. It
doesn't call sock_put() before returning -EEXIST to release
the sock refcnt that was held by calling sock_hold() before
the existence check.

This patch is to fix it by holding the sock after doing the
existence check.

Fixes: f6cd651b056f ("l2tp: fix race in duplicate tunnel detection")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Reviewed-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 8aaf8157da2b..4bb802f2fccd 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1503,12 +1503,7 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
 			goto err_sock;
 	}
 
-	sk = sock->sk;
-
-	sock_hold(sk);
-	tunnel->sock = sk;
 	tunnel->l2tp_net = net;
-
 	pn = l2tp_pernet(net);
 
 	spin_lock_bh(&pn->l2tp_tunnel_list_lock);
@@ -1523,6 +1518,10 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
 	list_add_rcu(&tunnel->list, &pn->l2tp_tunnel_list);
 	spin_unlock_bh(&pn->l2tp_tunnel_list_lock);
 
+	sk = sock->sk;
+	sock_hold(sk);
+	tunnel->sock = sk;
+
 	if (tunnel->encap == L2TP_ENCAPTYPE_UDP) {
 		struct udp_tunnel_sock_cfg udp_cfg = {
 			.sk_user_data = tunnel,
-- 
2.19.1


From 4ac31c50332a3269d738db15c020291518bd5bd5 Mon Sep 17 00:00:00 2001
From: Raed Salem <raeds@mellanox.com>
Date: Thu, 18 Oct 2018 08:55:21 +0300
Subject: [PATCH 21/36] net/mlx5: IPSec, Fix the SA context hash key

[ Upstream commit f2b18732ee9863ac036759baf616ffa03c252ed5 ]

The commit "net/mlx5: Refactor accel IPSec code" introduced a
bug where asynchronous short time change in hash key value
by create/release SA context might happen during an asynchronous
hash resize operation this could cause a subsequent remove SA
context operation to fail as the key value used during resize is
not the same key value used when remove SA context operation is
invoked.

This commit fixes the bug by defining the SA context hash key
such that it includes only fields that never change during the
lifetime of the SA context object.

Fixes: d6c4f0298cec ("net/mlx5: Refactor accel IPSec code")
Signed-off-by: Raed Salem <raeds@mellanox.com>
Reviewed-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
index b8ee9101c506..b5a8769a5bfd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
@@ -83,8 +83,14 @@ struct mlx5_fpga_ipsec_rule {
 };
 
 static const struct rhashtable_params rhash_sa = {
-	.key_len = FIELD_SIZEOF(struct mlx5_fpga_ipsec_sa_ctx, hw_sa),
-	.key_offset = offsetof(struct mlx5_fpga_ipsec_sa_ctx, hw_sa),
+	/* Keep out "cmd" field from the key as it's
+	 * value is not constant during the lifetime
+	 * of the key object.
+	 */
+	.key_len = FIELD_SIZEOF(struct mlx5_fpga_ipsec_sa_ctx, hw_sa) -
+		   FIELD_SIZEOF(struct mlx5_ifc_fpga_ipsec_sa_v1, cmd),
+	.key_offset = offsetof(struct mlx5_fpga_ipsec_sa_ctx, hw_sa) +
+		      FIELD_SIZEOF(struct mlx5_ifc_fpga_ipsec_sa_v1, cmd),
 	.head_offset = offsetof(struct mlx5_fpga_ipsec_sa_ctx, hash),
 	.automatic_shrinking = true,
 	.min_size = 1,
-- 
2.19.1


From 8b6fa3faa60ec7eb86dd7ba3c12fbbc6bf2506de Mon Sep 17 00:00:00 2001
From: Denis Drozdov <denisd@mellanox.com>
Date: Thu, 27 Sep 2018 14:17:54 +0300
Subject: [PATCH 22/36] net/mlx5e: IPoIB, Reset QP after channels are closed

[ Upstream commit acf3766b36d8e59ecbc307894c6d05703ee48014 ]

The mlx5e channels should be closed before mlx5i_uninit_underlay_qp
puts the QP into RST (reset) state during mlx5i_close. Currently QP
state incorrectly set to RST before channels got deactivated and closed,
since mlx5_post_send request expects QP in RTS (Ready To Send) state.

The fix is to keep QP in RTS state until mlx5e channels get closed
and to reset QP afterwards.

Also this fix is simply correct in order to keep the open/close flow
symmetric, i.e mlx5i_init_underlay_qp() is called first thing at open,
the correct thing to do is to call mlx5i_uninit_underlay_qp() last thing
at close, which is exactly what this patch is doing.

Fixes: dae37456c8ac ("net/mlx5: Support for attaching multiple underlay QPs to root flow table")
Signed-off-by: Denis Drozdov <denisd@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index b7c21eb21a21..4097b9eff179 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -502,9 +502,9 @@ static int mlx5i_close(struct net_device *netdev)
 
 	netif_carrier_off(epriv->netdev);
 	mlx5_fs_remove_rx_underlay_qpn(mdev, ipriv->qp.qpn);
-	mlx5i_uninit_underlay_qp(epriv);
 	mlx5e_deactivate_priv_channels(epriv);
 	mlx5e_close_channels(&epriv->channels);
+	mlx5i_uninit_underlay_qp(epriv);
 unlock:
 	mutex_unlock(&epriv->state_lock);
 	return 0;
-- 
2.19.1


From 3048a5286f1e8e8ea1c50c88e565f218018ab0ae Mon Sep 17 00:00:00 2001
From: Jarod Wilson <jarod@redhat.com>
Date: Sun, 4 Nov 2018 14:59:46 -0500
Subject: [PATCH 23/36] bonding/802.3ad: fix link_failure_count tracking

[ Upstream commit ea53abfab960909d622ca37bcfb8e1c5378d21cc ]

Commit 4d2c0cda07448ea6980f00102dc3964eb25e241c set slave->link to
BOND_LINK_DOWN for 802.3ad bonds whenever invalid speed/duplex values
were read, to fix a problem with slaves getting into weird states, but
in the process, broke tracking of link failures, as going straight to
BOND_LINK_DOWN when a link is indeed down (cable pulled, switch rebooted)
means we broke out of bond_miimon_inspect()'s BOND_LINK_DOWN case because
!link_state was already true, we never incremented commit, and never got
a chance to call bond_miimon_commit(), where slave->link_failure_count
would be incremented. I believe the simple fix here is to mark the slave
as BOND_LINK_FAIL, and let bond_miimon_inspect() transition the link from
_FAIL to either _UP or _DOWN, and in the latter case, we now get proper
incrementing of link_failure_count again.

Fixes: 4d2c0cda0744 ("bonding: speed/duplex update at NETDEV_UP event")
CC: Mahesh Bandewar <maheshb@google.com>
CC: David S. Miller <davem@davemloft.net>
CC: netdev@vger.kernel.org
CC: stable@vger.kernel.org
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 2b01180be834..29661d45c6d0 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3118,13 +3118,13 @@ static int bond_slave_netdev_event(unsigned long event,
 	case NETDEV_CHANGE:
 		/* For 802.3ad mode only:
 		 * Getting invalid Speed/Duplex values here will put slave
-		 * in weird state. So mark it as link-down for the time
+		 * in weird state. So mark it as link-fail for the time
 		 * being and let link-monitoring (miimon) set it right when
 		 * correct speeds/duplex are available.
 		 */
 		if (bond_update_speed_duplex(slave) &&
 		    BOND_MODE(bond) == BOND_MODE_8023AD)
-			slave->link = BOND_LINK_DOWN;
+			slave->link = BOND_LINK_FAIL;
 
 		if (BOND_MODE(bond) == BOND_MODE_8023AD)
 			bond_3ad_adapter_speed_duplex_changed(slave);
-- 
2.19.1


From b44d81fe154828cb43a0fc9d34d21d139620855b Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sun, 11 Nov 2018 00:41:10 +0100
Subject: [PATCH 24/36] net: dsa: mv88e6xxx: Fix clearing of stats counters

[ Upstream commit a9049ff9214da68df1179a7d5e36b43479abc9b8 ]

The mv88e6161 would sometime fail to probe with a timeout waiting for
the switch to complete an operation. This operation is supposed to
clear the statistics counters. However, due to a read/modify/write,
without the needed mask, the operation actually carried out was more
random, with invalid parameters, resulting in the switch not
responding. We need to preserve the histogram mode bits, so apply a
mask to keep them.

Reported-by: Chris Healy <Chris.Healy@zii.aero>
Fixes: 40cff8fca9e3 ("net: dsa: mv88e6xxx: Fix stats histogram mode")
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/global1.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/dsa/mv88e6xxx/global1.c b/drivers/net/dsa/mv88e6xxx/global1.c
index d721ccf7d8be..38e399e0f30e 100644
--- a/drivers/net/dsa/mv88e6xxx/global1.c
+++ b/drivers/net/dsa/mv88e6xxx/global1.c
@@ -567,6 +567,8 @@ int mv88e6xxx_g1_stats_clear(struct mv88e6xxx_chip *chip)
 	if (err)
 		return err;
 
+	/* Keep the histogram mode bits */
+	val &= MV88E6XXX_G1_STATS_OP_HIST_RX_TX;
 	val |= MV88E6XXX_G1_STATS_OP_BUSY | MV88E6XXX_G1_STATS_OP_FLUSH_ALL;
 
 	err = mv88e6xxx_g1_write(chip, MV88E6XXX_G1_STATS_OP, val);
-- 
2.19.1


From 724ae3bb8ac20caa9e5c471272db438da3bc77e0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Holger=20Hoffst=C3=A4tte?= <holger@applied-asynchrony.com>
Date: Sun, 4 Nov 2018 19:02:42 +0100
Subject: [PATCH 25/36] net: phy: realtek: fix RTL8201F sysfs name
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 0432e833191ad4d17b7fc2364941f91dad51db1a ]

Since 4.19 the following error in sysfs has appeared when using the
r8169 NIC driver:

$cd /sys/module/realtek/drivers
$ls -l
ls: cannot access 'mdio_bus:RTL8201F 10/100Mbps Ethernet': No such file or directory
[..garbled dir entries follow..]

Apparently the forward slash in "10/100Mbps Ethernet" is interpreted
as directory separator that leads nowhere, and was introduced in commit
513588dd44b ("net: phy: realtek: add RTL8201F phy-id and functions").

Fix this by removing the offending slash in the driver name.

Other drivers in net/phy seem to have the same problem, but I cannot
test/verify them.

Fixes: 513588dd44b ("net: phy: realtek: add RTL8201F phy-id and functions")
Signed-off-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/realtek.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c
index 082fb40c656d..c278a870484c 100644
--- a/drivers/net/phy/realtek.c
+++ b/drivers/net/phy/realtek.c
@@ -168,7 +168,7 @@ static struct phy_driver realtek_drvs[] = {
 		.flags          = PHY_HAS_INTERRUPT,
 	}, {
 		.phy_id		= 0x001cc816,
-		.name		= "RTL8201F 10/100Mbps Ethernet",
+		.name		= "RTL8201F Fast Ethernet",
 		.phy_id_mask	= 0x001fffff,
 		.features	= PHY_BASIC_FEATURES,
 		.flags		= PHY_HAS_INTERRUPT,
-- 
2.19.1


From ae53572f5e5f7caf6bc4d07831fbd07b09b79853 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sat, 3 Nov 2018 14:01:31 +0800
Subject: [PATCH 26/36] sctp: define SCTP_SS_DEFAULT for Stream schedulers

[ Upstream commit 12480e3b16982c4026de10dd8155823219cd6391 ]

According to rfc8260#section-4.3.2, SCTP_SS_DEFAULT is required to
defined as SCTP_SS_FCFS or SCTP_SS_RR.

SCTP_SS_FCFS is used for SCTP_SS_DEFAULT's value in this patch.

Fixes: 5bbbbe32a431 ("sctp: introduce stream scheduler foundations")
Reported-by: Jianwen Ji <jiji@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/sctp.h | 1 +
 net/sctp/outqueue.c       | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h
index b64d583bf053..12160bf4d4ce 100644
--- a/include/uapi/linux/sctp.h
+++ b/include/uapi/linux/sctp.h
@@ -1145,6 +1145,7 @@ struct sctp_add_streams {
 /* SCTP Stream schedulers */
 enum sctp_sched_type {
 	SCTP_SS_FCFS,
+	SCTP_SS_DEFAULT = SCTP_SS_FCFS,
 	SCTP_SS_PRIO,
 	SCTP_SS_RR,
 	SCTP_SS_MAX = SCTP_SS_RR
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index d68aa33485a9..2a933418043e 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -212,7 +212,7 @@ void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q)
 	INIT_LIST_HEAD(&q->retransmit);
 	INIT_LIST_HEAD(&q->sacked);
 	INIT_LIST_HEAD(&q->abandoned);
-	sctp_sched_set_sched(asoc, SCTP_SS_FCFS);
+	sctp_sched_set_sched(asoc, SCTP_SS_DEFAULT);
 }
 
 /* Free the outqueue structure and any related pending chunks.
-- 
2.19.1


From 54a4f1c3ccc4cfc94e5f341b0d32449644586459 Mon Sep 17 00:00:00 2001
From: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Date: Fri, 9 Nov 2018 18:56:27 -0700
Subject: [PATCH 27/36] net: qualcomm: rmnet: Fix incorrect assignment of
 real_dev

[ Upstream commit d02854dc1999ed3e7fd79ec700c64ac23ac0c458 ]

A null dereference was observed when a sysctl was being set
from userspace and rmnet was stuck trying to complete some actions
in the NETDEV_REGISTER callback. This is because the real_dev is set
only after the device registration handler completes.

sysctl call stack -

<6> Unable to handle kernel NULL pointer dereference at
    virtual address 00000108
<2> pc : rmnet_vnd_get_iflink+0x1c/0x28
<2> lr : dev_get_iflink+0x2c/0x40
<2>  rmnet_vnd_get_iflink+0x1c/0x28
<2>  inet6_fill_ifinfo+0x15c/0x234
<2>  inet6_ifinfo_notify+0x68/0xd4
<2>  ndisc_ifinfo_sysctl_change+0x1b8/0x234
<2>  proc_sys_call_handler+0xac/0x100
<2>  proc_sys_write+0x3c/0x4c
<2>  __vfs_write+0x54/0x14c
<2>  vfs_write+0xcc/0x188
<2>  SyS_write+0x60/0xc0
<2>  el0_svc_naked+0x34/0x38

device register call stack -

<2>  notifier_call_chain+0x84/0xbc
<2>  raw_notifier_call_chain+0x38/0x48
<2>  call_netdevice_notifiers_info+0x40/0x70
<2>  call_netdevice_notifiers+0x38/0x60
<2>  register_netdevice+0x29c/0x3d8
<2>  rmnet_vnd_newlink+0x68/0xe8
<2>  rmnet_newlink+0xa0/0x160
<2>  rtnl_newlink+0x57c/0x6c8
<2>  rtnetlink_rcv_msg+0x1dc/0x328
<2>  netlink_rcv_skb+0xac/0x118
<2>  rtnetlink_rcv+0x24/0x30
<2>  netlink_unicast+0x158/0x1f0
<2>  netlink_sendmsg+0x32c/0x338
<2>  sock_sendmsg+0x44/0x60
<2>  SyS_sendto+0x150/0x1ac
<2>  el0_svc_naked+0x34/0x38

Fixes: b752eff5be24 ("net: qualcomm: rmnet: Implement ndo_get_iflink")
Signed-off-by: Sean Tranchetti <stranche@codeaurora.org>
Signed-off-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
index b9a7548ec6a0..2efdf7d2dec8 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
@@ -234,7 +234,7 @@ int rmnet_vnd_newlink(u8 id, struct net_device *rmnet_dev,
 		      struct net_device *real_dev,
 		      struct rmnet_endpoint *ep)
 {
-	struct rmnet_priv *priv;
+	struct rmnet_priv *priv = netdev_priv(rmnet_dev);
 	int rc;
 
 	if (ep->egress_dev)
@@ -247,6 +247,8 @@ int rmnet_vnd_newlink(u8 id, struct net_device *rmnet_dev,
 	rmnet_dev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
 	rmnet_dev->hw_features |= NETIF_F_SG;
 
+	priv->real_dev = real_dev;
+
 	rc = register_netdevice(rmnet_dev);
 	if (!rc) {
 		ep->egress_dev = rmnet_dev;
@@ -255,9 +257,7 @@ int rmnet_vnd_newlink(u8 id, struct net_device *rmnet_dev,
 
 		rmnet_dev->rtnl_link_ops = &rmnet_link_ops;
 
-		priv = netdev_priv(rmnet_dev);
 		priv->mux_id = id;
-		priv->real_dev = real_dev;
 
 		netdev_dbg(rmnet_dev, "rmnet dev created\n");
 	}
-- 
2.19.1


From 0fa553a084b5256c780d70d1ade8ac00a382343b Mon Sep 17 00:00:00 2001
From: Tristram Ha <Tristram.Ha@microchip.com>
Date: Fri, 2 Nov 2018 19:23:41 -0700
Subject: [PATCH 28/36] net: dsa: microchip: initialize mutex before use

[ Upstream commit 284fb78ed7572117846f8e1d1d8e3dbfd16880c2 ]

Initialize mutex before use.  Avoid kernel complaint when
CONFIG_DEBUG_LOCK_ALLOC is enabled.

Fixes: b987e98e50ab90e5 ("dsa: add DSA switch driver for Microchip KSZ9477")
Signed-off-by: Tristram Ha <Tristram.Ha@microchip.com>
Reviewed-by: Pavel Machek <pavel@ucw.cz>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/microchip/ksz_common.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index 7210c49b7922..c3103bdb6cf6 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -1108,11 +1108,6 @@ static int ksz_switch_init(struct ksz_device *dev)
 {
 	int i;
 
-	mutex_init(&dev->reg_mutex);
-	mutex_init(&dev->stats_mutex);
-	mutex_init(&dev->alu_mutex);
-	mutex_init(&dev->vlan_mutex);
-
 	dev->ds->ops = &ksz_switch_ops;
 
 	for (i = 0; i < ARRAY_SIZE(ksz_switch_chips); i++) {
@@ -1197,6 +1192,11 @@ int ksz_switch_register(struct ksz_device *dev)
 	if (dev->pdata)
 		dev->chip_id = dev->pdata->chip_id;
 
+	mutex_init(&dev->reg_mutex);
+	mutex_init(&dev->stats_mutex);
+	mutex_init(&dev->alu_mutex);
+	mutex_init(&dev->vlan_mutex);
+
 	if (ksz_switch_detect(dev))
 		return -EINVAL;
 
-- 
2.19.1


From 48c9a716577c0d1a17372ff75bd4a89e5b8565fd Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sat, 3 Nov 2018 13:59:45 +0800
Subject: [PATCH 29/36] sctp: fix strchange_flags name for Stream Change Event

[ Upstream commit fd82d61ba142f0b83463e47064bf5460aac57b6e ]

As defined in rfc6525#section-6.1.3, SCTP_STREAM_CHANGE_DENIED
and SCTP_STREAM_CHANGE_FAILED should be used instead of
SCTP_ASSOC_CHANGE_DENIED and SCTP_ASSOC_CHANGE_FAILED.

To keep the compatibility, fix it by adding two macros.

Fixes: b444153fb5a6 ("sctp: add support for generating add stream change event notification")
Reported-by: Jianwen Ji <jiji@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/sctp.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h
index 12160bf4d4ce..8d851c3aebc2 100644
--- a/include/uapi/linux/sctp.h
+++ b/include/uapi/linux/sctp.h
@@ -566,6 +566,8 @@ struct sctp_assoc_reset_event {
 
 #define SCTP_ASSOC_CHANGE_DENIED	0x0004
 #define SCTP_ASSOC_CHANGE_FAILED	0x0008
+#define SCTP_STREAM_CHANGE_DENIED	SCTP_ASSOC_CHANGE_DENIED
+#define SCTP_STREAM_CHANGE_FAILED	SCTP_ASSOC_CHANGE_FAILED
 struct sctp_stream_change_event {
 	__u16 strchange_type;
 	__u16 strchange_flags;
-- 
2.19.1


From db5a65e57541b93904cf9b56b2c8ae57354d187c Mon Sep 17 00:00:00 2001
From: Martin Schiller <ms@dev.tdt.de>
Date: Fri, 16 Nov 2018 08:38:36 +0100
Subject: [PATCH 30/36] net: phy: mdio-gpio: Fix working over slow can_sleep
 GPIOs

[ Upstream commit df5a8ec64eed7fe45b556cfff503acd6429ab817 ]

Up until commit 7e5fbd1e0700 ("net: mdio-gpio: Convert to use gpiod
functions where possible"), the _cansleep variants of the gpio_ API was
used. After that commit and the change to gpiod_ API, the _cansleep()
was dropped. This then results in WARN_ON() when used with GPIO
devices which do sleep. Add back the _cansleep() to avoid this.

Fixes: 7e5fbd1e0700 ("net: mdio-gpio: Convert to use gpiod functions where possible")
Signed-off-by: Martin Schiller <ms@dev.tdt.de>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mdio-gpio.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/phy/mdio-gpio.c b/drivers/net/phy/mdio-gpio.c
index 33265747bf39..0fbcedcdf6e2 100644
--- a/drivers/net/phy/mdio-gpio.c
+++ b/drivers/net/phy/mdio-gpio.c
@@ -63,7 +63,7 @@ static void mdio_dir(struct mdiobb_ctrl *ctrl, int dir)
 		 * assume the pin serves as pull-up. If direction is
 		 * output, the default value is high.
 		 */
-		gpiod_set_value(bitbang->mdo, 1);
+		gpiod_set_value_cansleep(bitbang->mdo, 1);
 		return;
 	}
 
@@ -78,7 +78,7 @@ static int mdio_get(struct mdiobb_ctrl *ctrl)
 	struct mdio_gpio_info *bitbang =
 		container_of(ctrl, struct mdio_gpio_info, ctrl);
 
-	return gpiod_get_value(bitbang->mdio);
+	return gpiod_get_value_cansleep(bitbang->mdio);
 }
 
 static void mdio_set(struct mdiobb_ctrl *ctrl, int what)
@@ -87,9 +87,9 @@ static void mdio_set(struct mdiobb_ctrl *ctrl, int what)
 		container_of(ctrl, struct mdio_gpio_info, ctrl);
 
 	if (bitbang->mdo)
-		gpiod_set_value(bitbang->mdo, what);
+		gpiod_set_value_cansleep(bitbang->mdo, what);
 	else
-		gpiod_set_value(bitbang->mdio, what);
+		gpiod_set_value_cansleep(bitbang->mdio, what);
 }
 
 static void mdc_set(struct mdiobb_ctrl *ctrl, int what)
@@ -97,7 +97,7 @@ static void mdc_set(struct mdiobb_ctrl *ctrl, int what)
 	struct mdio_gpio_info *bitbang =
 		container_of(ctrl, struct mdio_gpio_info, ctrl);
 
-	gpiod_set_value(bitbang->mdc, what);
+	gpiod_set_value_cansleep(bitbang->mdc, what);
 }
 
 static const struct mdiobb_ops mdio_gpio_ops = {
-- 
2.19.1


From 1625043498748a294b4fc43bde34434837ea85c3 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 18 Nov 2018 21:59:49 +0800
Subject: [PATCH 32/36] sctp: not increase stream's incnt before sending
 addstrm_in request

[ Upstream commit e1e46479847e66f78f79d8c24d5169a5954b3fc2 ]

Different from processing the addstrm_out request, The receiver handles
an addstrm_in request by sending back an addstrm_out request to the
sender who will increase its stream's in and incnt later.

Now stream->incnt has been increased since it sent out the addstrm_in
request in sctp_send_add_streams(), with the wrong stream->incnt will
even cause crash when copying stream info from the old stream's in to
the new one's in sctp_process_strreset_addstrm_out().

This patch is to fix it by simply removing the stream->incnt change
from sctp_send_add_streams().

Fixes: 242bd2d519d7 ("sctp: implement sender-side procedures for Add Incoming/Outgoing Streams Request Parameter")
Reported-by: Jianwen Ji <jiji@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/stream.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index f1f1d1b232ba..ff233f6bd465 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -491,7 +491,6 @@ int sctp_send_add_streams(struct sctp_association *asoc,
 		goto out;
 	}
 
-	stream->incnt = incnt;
 	stream->outcnt = outcnt;
 
 	asoc->strreset_outstanding = !!out + !!in;
-- 
2.19.1


From 0f788815c3d8785c271bc8edb2344f589721dd7d Mon Sep 17 00:00:00 2001
From: Shalom Toledo <shalomt@mellanox.com>
Date: Fri, 2 Nov 2018 19:49:15 +0000
Subject: [PATCH 33/36] mlxsw: spectrum: Fix IP2ME CPU policer configuration

[ Upstream commit 96801552f846460fe9ac10f1b189602992f004e1 ]

The CPU policer used to police packets being trapped via a local route
(IP2ME) was incorrectly configured to police based on bytes per second
instead of packets per second.

Change the policer to police based on packets per second and avoid
packet loss under certain circumstances.

Fixes: 9148e7cf73ce ("mlxsw: spectrum: Add policers for trap groups")
Signed-off-by: Shalom Toledo <shalomt@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 968b88af2ef5..9171d21576ad 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -3429,7 +3429,6 @@ static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core)
 			burst_size = 7;
 			break;
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IP2ME:
-			is_bytes = true;
 			rate = 4 * 1024;
 			burst_size = 4;
 			break;
-- 
2.19.1


From bdff57ceec65219957a3ea29d579cb803c5ba431 Mon Sep 17 00:00:00 2001
From: Stefan Wahren <stefan.wahren@i2se.com>
Date: Thu, 8 Nov 2018 20:38:26 +0100
Subject: [PATCH 34/36] net: smsc95xx: Fix MTU range

[ Upstream commit 85b18b0237ce9986a81a1b9534b5e2ee116f5504 ]

The commit f77f0aee4da4 ("net: use core MTU range checking in USB NIC
drivers") introduce a common MTU handling for usbnet. But it's missing
the necessary changes for smsc95xx. So set the MTU range accordingly.

This patch has been tested on a Raspberry Pi 3.

Fixes: f77f0aee4da4 ("net: use core MTU range checking in USB NIC drivers")
Signed-off-by: Stefan Wahren <stefan.wahren@i2se.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/smsc95xx.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index 262e7a3c23cb..5974478b5be4 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -1321,6 +1321,8 @@ static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf)
 	dev->net->ethtool_ops = &smsc95xx_ethtool_ops;
 	dev->net->flags |= IFF_MULTICAST;
 	dev->net->hard_header_len += SMSC95XX_TX_OVERHEAD_CSUM;
+	dev->net->min_mtu = ETH_MIN_MTU;
+	dev->net->max_mtu = ETH_DATA_LEN;
 	dev->hard_mtu = dev->net->mtu + dev->net->hard_header_len;
 
 	pdata->dev = dev;
-- 
2.19.1


From 87e4811b94e9df4cd31c78841c58c4e3e855b457 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 1 Nov 2018 13:39:53 +0000
Subject: [PATCH 35/36] rxrpc: Fix lockup due to no error backoff after ack
 transmit error

[ Upstream commit c7e86acfcee30794dc99a0759924bf7b9d43f1ca ]

If the network becomes (partially) unavailable, say by disabling IPv6, the
background ACK transmission routine can get itself into a tizzy by
proposing immediate ACK retransmission.  Since we're in the call event
processor, that happens immediately without returning to the workqueue
manager.

The condition should clear after a while when either the network comes back
or the call times out.

Fix this by:

 (1) When re-proposing an ACK on failed Tx, don't schedule it immediately.
     This will allow a certain amount of time to elapse before we try
     again.

 (2) Enforce a return to the workqueue manager after a certain number of
     iterations of the call processing loop.

 (3) Add a backoff delay that increases the delay on deferred ACKs by a
     jiffy per failed transmission to a limit of HZ.  The backoff delay is
     cleared on a successful return from kernel_sendmsg().

 (4) Cancel calls immediately if the opening sendmsg fails.  The layer
     above can arrange retransmission or rotate to another server.

Fixes: 248f219cb8bc ("rxrpc: Rewrite the data and ack handling code")
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/ar-internal.h |  1 +
 net/rxrpc/call_event.c  | 18 ++++++++++++++----
 net/rxrpc/output.c      | 35 ++++++++++++++++++++++++++++++++---
 3 files changed, 47 insertions(+), 7 deletions(-)

diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 330372c04940..5f6c461ee6aa 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -613,6 +613,7 @@ struct rxrpc_call {
 						 * not hard-ACK'd packet follows this.
 						 */
 	rxrpc_seq_t		tx_top;		/* Highest Tx slot allocated. */
+	u16			tx_backoff;	/* Delay to insert due to Tx failure */
 
 	/* TCP-style slow-start congestion control [RFC5681].  Since the SMSS
 	 * is fixed, we keep these numbers in terms of segments (ie. DATA
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index 20210418904b..3cdca085ddb4 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -123,6 +123,7 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason,
 		else
 			ack_at = expiry;
 
+		ack_at += READ_ONCE(call->tx_backoff);
 		ack_at += now;
 		if (time_before(ack_at, call->ack_at)) {
 			WRITE_ONCE(call->ack_at, ack_at);
@@ -313,6 +314,7 @@ void rxrpc_process_call(struct work_struct *work)
 		container_of(work, struct rxrpc_call, processor);
 	rxrpc_serial_t *send_ack;
 	unsigned long now, next, t;
+	unsigned int iterations = 0;
 
 	rxrpc_see_call(call);
 
@@ -321,6 +323,11 @@ void rxrpc_process_call(struct work_struct *work)
 	       call->debug_id, rxrpc_call_states[call->state], call->events);
 
 recheck_state:
+	/* Limit the number of times we do this before returning to the manager */
+	iterations++;
+	if (iterations > 5)
+		goto requeue;
+
 	if (test_and_clear_bit(RXRPC_CALL_EV_ABORT, &call->events)) {
 		rxrpc_send_abort_packet(call);
 		goto recheck_state;
@@ -449,13 +456,16 @@ void rxrpc_process_call(struct work_struct *work)
 	rxrpc_reduce_call_timer(call, next, now, rxrpc_timer_restart);
 
 	/* other events may have been raised since we started checking */
-	if (call->events && call->state < RXRPC_CALL_COMPLETE) {
-		__rxrpc_queue_call(call);
-		goto out;
-	}
+	if (call->events && call->state < RXRPC_CALL_COMPLETE)
+		goto requeue;
 
 out_put:
 	rxrpc_put_call(call, rxrpc_call_put);
 out:
 	_leave("");
+	return;
+
+requeue:
+	__rxrpc_queue_call(call);
+	goto out;
 }
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index 6ac21bb2071d..9813a3fe402b 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -34,6 +34,21 @@ struct rxrpc_abort_buffer {
 
 static const char rxrpc_keepalive_string[] = "";
 
+/*
+ * Increase Tx backoff on transmission failure and clear it on success.
+ */
+static void rxrpc_tx_backoff(struct rxrpc_call *call, int ret)
+{
+	if (ret < 0) {
+		u16 tx_backoff = READ_ONCE(call->tx_backoff);
+
+		if (tx_backoff < HZ)
+			WRITE_ONCE(call->tx_backoff, tx_backoff + 1);
+	} else {
+		WRITE_ONCE(call->tx_backoff, 0);
+	}
+}
+
 /*
  * Arrange for a keepalive ping a certain time after we last transmitted.  This
  * lets the far side know we're still interested in this call and helps keep
@@ -207,6 +222,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
 	if (ret < 0)
 		trace_rxrpc_tx_fail(call->debug_id, serial, ret,
 				    rxrpc_tx_fail_call_ack);
+	rxrpc_tx_backoff(call, ret);
 
 	if (call->state < RXRPC_CALL_COMPLETE) {
 		if (ret < 0) {
@@ -215,7 +231,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
 			rxrpc_propose_ACK(call, pkt->ack.reason,
 					  ntohs(pkt->ack.maxSkew),
 					  ntohl(pkt->ack.serial),
-					  true, true,
+					  false, true,
 					  rxrpc_propose_ack_retry_tx);
 		} else {
 			spin_lock_bh(&call->lock);
@@ -295,6 +311,8 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call)
 		trace_rxrpc_tx_fail(call->debug_id, serial, ret,
 				    rxrpc_tx_fail_call_abort);
 
+	rxrpc_tx_backoff(call, ret);
+
 
 	rxrpc_put_connection(conn);
 	return ret;
@@ -402,6 +420,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
 	if (ret < 0)
 		trace_rxrpc_tx_fail(call->debug_id, serial, ret,
 				    rxrpc_tx_fail_call_data_nofrag);
+	rxrpc_tx_backoff(call, ret);
 	if (ret == -EMSGSIZE)
 		goto send_fragmentable;
 
@@ -436,9 +455,18 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
 			rxrpc_reduce_call_timer(call, expect_rx_by, nowj,
 						rxrpc_timer_set_for_normal);
 		}
-	}
 
-	rxrpc_set_keepalive(call);
+		rxrpc_set_keepalive(call);
+	} else {
+		/* Cancel the call if the initial transmission fails,
+		 * particularly if that's due to network routing issues that
+		 * aren't going away anytime soon.  The layer above can arrange
+		 * the retransmission.
+		 */
+		if (!test_and_set_bit(RXRPC_CALL_BEGAN_RX_TIMER, &call->flags))
+			rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR,
+						  RX_USER_ABORT, ret);
+	}
 
 	_leave(" = %d [%u]", ret, call->peer->maxdata);
 	return ret;
@@ -494,6 +522,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
 	if (ret < 0)
 		trace_rxrpc_tx_fail(call->debug_id, serial, ret,
 				    rxrpc_tx_fail_call_data_frag);
+	rxrpc_tx_backoff(call, ret);
 
 	up_write(&conn->params.local->defrag_sem);
 	goto done;
-- 
2.19.1


From bb7f1e60ef32708cbad595e36194b9eb658bb344 Mon Sep 17 00:00:00 2001
From: Frieder Schrempf <frieder.schrempf@kontron.de>
Date: Wed, 31 Oct 2018 22:52:19 +0100
Subject: [PATCH 36/36] usbnet: smsc95xx: disable carrier check while
 suspending

[ Upstream commit 7b900ead6cc66b2ee873cb042dfba169aa68b56c ]

We need to make sure, that the carrier check polling is disabled
while suspending. Otherwise we can end up with usbnet_read_cmd()
being issued when only usbnet_read_cmd_nopm() is allowed. If this
happens, read operations lock up.

Fixes: d69d169493 ("usbnet: smsc95xx: fix link detection for disabled autonegotiation")
Signed-off-by: Frieder Schrempf <frieder.schrempf@kontron.de>
Reviewed-by: Raghuram Chary J <RaghuramChary.Jallipalli@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/smsc95xx.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index 5974478b5be4..f2d01cb6f958 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -1600,6 +1600,8 @@ static int smsc95xx_suspend(struct usb_interface *intf, pm_message_t message)
 		return ret;
 	}
 
+	cancel_delayed_work_sync(&pdata->carrier_check);
+
 	if (pdata->suspend_flags) {
 		netdev_warn(dev->net, "error during last resume\n");
 		pdata->suspend_flags = 0;
@@ -1842,6 +1844,11 @@ static int smsc95xx_suspend(struct usb_interface *intf, pm_message_t message)
 	 */
 	if (ret && PMSG_IS_AUTO(message))
 		usbnet_resume(intf);
+
+	if (ret)
+		schedule_delayed_work(&pdata->carrier_check,
+				      CARRIER_CHECK_DELAY);
+
 	return ret;
 }
 
-- 
2.19.1


[-- Attachment #3: net_419.mbox --]
[-- Type: Application/Octet-Stream, Size: 110004 bytes --]

From 0633713f2b415fef04afaa50c598f0159f3ba6b7 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=EB=B0=B0=EC=84=9D=EC=A7=84?= <soukjin.bae@samsung.com>
Date: Fri, 9 Nov 2018 16:53:06 -0800
Subject: [PATCH 01/43] flow_dissector: do not dissect l4 ports for fragments
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 62230715fd2453b3ba948c9d83cfb3ada9169169 ]

Only first fragment has the sport/dport information,
not the following ones.

If we want consistent hash for all fragments, we need to
ignore ports even for first fragment.

This bug is visible for IPv6 traffic, if incoming fragments
do not have a flow label, since skb_get_hash() will give
different results for first fragment and following ones.

It is also visible if any routing rule wants dissection
and sport or dport.

See commit 5e5d6fed3741 ("ipv6: route: dissect flow
in input path if fib rules need it") for details.

[edumazet] rewrote the changelog completely.

Fixes: 06635a35d13d ("flow_dissect: use programable dissector in skb_flow_dissect and friends")
Signed-off-by: 배석진 <soukjin.bae@samsung.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/flow_dissector.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index ce9eeeb7c024..415b95f76b66 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -1026,8 +1026,8 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
 		break;
 	}
 
-	if (dissector_uses_key(flow_dissector,
-			       FLOW_DISSECTOR_KEY_PORTS)) {
+	if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS) &&
+	    !(key_control->flags & FLOW_DIS_IS_FRAGMENT)) {
 		key_ports = skb_flow_dissector_target(flow_dissector,
 						      FLOW_DISSECTOR_KEY_PORTS,
 						      target_container);
-- 
2.19.1


From 1df7c13ddc25979c723ffaf28196fb9ea8a315c8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Micha=C5=82=20Miros=C5=82aw?= <mirq-linux@rere.qmqm.pl>
Date: Wed, 7 Nov 2018 17:50:52 +0100
Subject: [PATCH 02/43] ibmvnic: fix accelerated VLAN handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit e84b47941e15e6666afb8ee8b21d1c3fc1a013af ]

Don't request tag insertion when it isn't present in outgoing skb.

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ibm/ibmvnic.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 699ef942b615..7661064c815b 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -1545,7 +1545,7 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 	tx_crq.v1.sge_len = cpu_to_be32(skb->len);
 	tx_crq.v1.ioba = cpu_to_be64(data_dma_addr);
 
-	if (adapter->vlan_header_insertion) {
+	if (adapter->vlan_header_insertion && skb_vlan_tag_present(skb)) {
 		tx_crq.v1.flags2 |= IBMVNIC_TX_VLAN_INSERT;
 		tx_crq.v1.vlan_id = cpu_to_be16(skb->vlan_tci);
 	}
-- 
2.19.1


From f8c54c2ffb815663328a35a69f48e5b5596ab5de Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 16 Nov 2018 16:58:19 +0100
Subject: [PATCH 03/43] ip_tunnel: don't force DF when MTU is locked

[ Upstream commit 16f7eb2b77b55da816c4e207f3f9440a8cafc00a ]

The various types of tunnels running over IPv4 can ask to set the DF
bit to do PMTU discovery. However, PMTU discovery is subject to the
threshold set by the net.ipv4.route.min_pmtu sysctl, and is also
disabled on routes with "mtu lock". In those cases, we shouldn't set
the DF bit.

This patch makes setting the DF bit conditional on the route's MTU
locking state.

This issue seems to be older than git history.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_tunnel_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index dde671e97829..c248e0dccbe1 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -80,7 +80,7 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
 
 	iph->version	=	4;
 	iph->ihl	=	sizeof(struct iphdr) >> 2;
-	iph->frag_off	=	df;
+	iph->frag_off	=	ip_mtu_locked(&rt->dst) ? 0 : df;
 	iph->protocol	=	proto;
 	iph->tos	=	tos;
 	iph->daddr	=	dst;
-- 
2.19.1


From 534b4536a46da7019bbd43077ac194d3832acd4e Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 14 Nov 2018 00:48:28 +0800
Subject: [PATCH 04/43] ipv6: fix a dst leak when removing its exception

[ Upstream commit 761f60261b4401aa368d71d431b4c218af0efcee ]

These is no need to hold dst before calling rt6_remove_exception_rt().
The call to dst_hold_safe() in ip6_link_failure() was for ip6_del_rt(),
which has been removed in Commit 93531c674315 ("net/ipv6: separate
handling of FIB entries from dst based routes"). Otherwise, it will
cause a dst leak.

This patch is to simply remove the dst_hold_safe() call before calling
rt6_remove_exception_rt() and also do the same in ip6_del_cached_rt().
It's safe, because the removal of the exception that holds its dst's
refcnt is protected by rt6_exception_lock.

Fixes: 93531c674315 ("net/ipv6: separate handling of FIB entries from dst based routes")
Fixes: 23fb93a4d3f1 ("net/ipv6: Cleanup exception and cache route handling")
Reported-by: Li Shuang <shuali@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 1cf00d857fc1..ed72ae3c54e7 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2263,8 +2263,7 @@ static void ip6_link_failure(struct sk_buff *skb)
 	if (rt) {
 		rcu_read_lock();
 		if (rt->rt6i_flags & RTF_CACHE) {
-			if (dst_hold_safe(&rt->dst))
-				rt6_remove_exception_rt(rt);
+			rt6_remove_exception_rt(rt);
 		} else {
 			struct fib6_info *from;
 			struct fib6_node *fn;
@@ -3266,8 +3265,8 @@ static int ip6_del_cached_rt(struct rt6_info *rt, struct fib6_config *cfg)
 	if (cfg->fc_flags & RTF_GATEWAY &&
 	    !ipv6_addr_equal(&cfg->fc_gateway, &rt->rt6i_gateway))
 		goto out;
-	if (dst_hold_safe(&rt->dst))
-		rc = rt6_remove_exception_rt(rt);
+
+	rc = rt6_remove_exception_rt(rt);
 out:
 	return rc;
 }
-- 
2.19.1


From fd1909221b6206a1758222e8b0ab646f95d4449a Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Sun, 18 Nov 2018 10:45:30 -0800
Subject: [PATCH 05/43] ipv6: Fix PMTU updates for UDP/raw sockets in presence
 of VRF

[ Upstream commit 7ddacfa564870cdd97275fd87decb6174abc6380 ]

Preethi reported that PMTU discovery for UDP/raw applications is not
working in the presence of VRF when the socket is not bound to a device.
The problem is that ip6_sk_update_pmtu does not consider the L3 domain
of the skb device if the socket is not bound. Update the function to
set oif to the L3 master device if relevant.

Fixes: ca254490c8df ("net: Add VRF support to IPv6 stack")
Reported-by: Preethi Ramachandra <preethir@juniper.net>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index ed72ae3c54e7..a33681dc4796 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2391,10 +2391,13 @@ EXPORT_SYMBOL_GPL(ip6_update_pmtu);
 
 void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu)
 {
+	int oif = sk->sk_bound_dev_if;
 	struct dst_entry *dst;
 
-	ip6_update_pmtu(skb, sock_net(sk), mtu,
-			sk->sk_bound_dev_if, sk->sk_mark, sk->sk_uid);
+	if (!oif && skb->dev)
+		oif = l3mdev_master_ifindex(skb->dev);
+
+	ip6_update_pmtu(skb, sock_net(sk), mtu, oif, sk->sk_mark, sk->sk_uid);
 
 	dst = __sk_dst_get(sk);
 	if (!dst || !dst->obsolete ||
-- 
2.19.1


From e5940904bf139f8ed90cbd344ca4a1ba687ebe10 Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Thu, 1 Nov 2018 15:55:37 -0700
Subject: [PATCH 06/43] net: bcmgenet: protect stop from timeout

A timing hazard exists when the network interface is stopped that
allows a watchdog timeout to be processed by a separate core in
parallel. This creates the potential for the timeout handler to
wake the queues while the driver is shutting down, or access
registers after their clocks have been removed.

The more common case is that the watchdog timeout will produce a
warning message which doesn't lead to a crash. The chances of this
are greatly increased by the fact that bcmgenet_netif_stop stops
the transmit queues which can easily precipitate a watchdog time-
out because of stale trans_start data in the queues.

This commit corrects the behavior by ensuring that the watchdog
timeout is disabled before enterring bcmgenet_netif_stop. There
are currently only two users of the bcmgenet_netif_stop function:
close and suspend.

The close case already handles the issue by exiting the RUNNING
state before invoking the driver close service.

The suspend case now performs the netif_device_detach to exit the
PRESENT state before the call to bcmgenet_netif_stop rather than
after it.

These behaviors prevent any future scheduling of the driver timeout
service during the window. The netif_tx_stop_all_queues function
in bcmgenet_netif_stop is replaced with netif_tx_disable to ensure
synchronization with any transmit or timeout threads that may
already be executing on other cores.

For symmetry, the netif_device_attach call upon resume is moved to
after the call to bcmgenet_netif_start. Since it wakes the transmit
queues it is not necessary to invoke netif_tx_start_all_queues from
bcmgenet_netif_start so it is moved into the driver open service.

[ Upstream commit 09e805d2570a3a94f13dd9c9ad2bcab23da76e09 ]

Fixes: 1c1008c793fa ("net: bcmgenet: add main driver file")
Signed-off-by: Doug Berger <opendmb@gmail.com>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 20c1681bb1af..2d6f090bf644 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -2855,7 +2855,6 @@ static void bcmgenet_netif_start(struct net_device *dev)
 
 	umac_enable_set(priv, CMD_TX_EN | CMD_RX_EN, true);
 
-	netif_tx_start_all_queues(dev);
 	bcmgenet_enable_tx_napi(priv);
 
 	/* Monitor link interrupts now */
@@ -2937,6 +2936,8 @@ static int bcmgenet_open(struct net_device *dev)
 
 	bcmgenet_netif_start(dev);
 
+	netif_tx_start_all_queues(dev);
+
 	return 0;
 
 err_irq1:
@@ -2958,7 +2959,7 @@ static void bcmgenet_netif_stop(struct net_device *dev)
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 
 	bcmgenet_disable_tx_napi(priv);
-	netif_tx_stop_all_queues(dev);
+	netif_tx_disable(dev);
 
 	/* Disable MAC receive */
 	umac_enable_set(priv, CMD_RX_EN, false);
@@ -3620,13 +3621,13 @@ static int bcmgenet_suspend(struct device *d)
 	if (!netif_running(dev))
 		return 0;
 
+	netif_device_detach(dev);
+
 	bcmgenet_netif_stop(dev);
 
 	if (!device_may_wakeup(d))
 		phy_suspend(dev->phydev);
 
-	netif_device_detach(dev);
-
 	/* Prepare the device for Wake-on-LAN and switch to the slow clock */
 	if (device_may_wakeup(d) && priv->wolopts) {
 		ret = bcmgenet_power_down(priv, GENET_POWER_WOL_MAGIC);
@@ -3700,8 +3701,6 @@ static int bcmgenet_resume(struct device *d)
 	/* Always enable ring 16 - descriptor ring */
 	bcmgenet_enable_dma(priv, dma_ctrl);
 
-	netif_device_attach(dev);
-
 	if (!device_may_wakeup(d))
 		phy_resume(dev->phydev);
 
@@ -3710,6 +3709,8 @@ static int bcmgenet_resume(struct device *d)
 
 	bcmgenet_netif_start(dev);
 
+	netif_device_attach(dev);
+
 	return 0;
 
 out_clk_disable:
-- 
2.19.1


From 4cc9e577003ee025f2b236531f3d03b22e14c230 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 17 Nov 2018 21:57:02 -0800
Subject: [PATCH 07/43] net-gro: reset skb->pkt_type in napi_reuse_skb()

[ Upstream commit 33d9a2c72f086cbf1087b2fd2d1a15aa9df14a7f ]

eth_type_trans() assumes initial value for skb->pkt_type
is PACKET_HOST.

This is indeed the value right after a fresh skb allocation.

However, it is possible that GRO merged a packet with a different
value (like PACKET_OTHERHOST in case macvlan is used), so
we need to make sure napi->skb will have pkt_type set back to
PACKET_HOST.

Otherwise, valid packets might be dropped by the stack because
their pkt_type is not PACKET_HOST.

napi_reuse_skb() was added in commit 96e93eab2033 ("gro: Add
internal interfaces for VLAN"), but this bug always has
been there.

Fixes: 96e93eab2033 ("gro: Add internal interfaces for VLAN")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/core/dev.c b/net/core/dev.c
index e16ba3625400..097c02101450 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5630,6 +5630,10 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
 	skb->vlan_tci = 0;
 	skb->dev = napi->dev;
 	skb->skb_iif = 0;
+
+	/* eth_type_trans() assumes pkt_type is PACKET_HOST */
+	skb->pkt_type = PACKET_HOST;
+
 	skb->encapsulation = 0;
 	skb_shinfo(skb)->gso_type = 0;
 	skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));
-- 
2.19.1


From 0c0dfa95b65f215afa73c23c8aa3d3799fb0b16e Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 18 Nov 2018 15:21:53 +0800
Subject: [PATCH 08/43] sctp: not allow to set asoc prsctp_enable by sockopt

[ Upstream commit cc3ccf26f0649089b3a34a2781977755ea36e72c ]

As rfc7496#section4.5 says about SCTP_PR_SUPPORTED:

   This socket option allows the enabling or disabling of the
   negotiation of PR-SCTP support for future associations.  For existing
   associations, it allows one to query whether or not PR-SCTP support
   was negotiated on a particular association.

It means only sctp sock's prsctp_enable can be set.

Note that for the limitation of SCTP_{CURRENT|ALL}_ASSOC, we will
add it when introducing SCTP_{FUTURE|CURRENT|ALL}_ASSOC for linux
sctp in another patchset.

v1->v2:
  - drop the params.assoc_id check as Neil suggested.

Fixes: 28aa4c26fce2 ("sctp: add SCTP_PR_SUPPORTED on sctp sockopt")
Reported-by: Ying Xu <yinxu@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 26 +++++---------------------
 1 file changed, 5 insertions(+), 21 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index c1693e28aed4..876393cf5ed6 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -3958,32 +3958,16 @@ static int sctp_setsockopt_pr_supported(struct sock *sk,
 					unsigned int optlen)
 {
 	struct sctp_assoc_value params;
-	struct sctp_association *asoc;
-	int retval = -EINVAL;
 
 	if (optlen != sizeof(params))
-		goto out;
-
-	if (copy_from_user(&params, optval, optlen)) {
-		retval = -EFAULT;
-		goto out;
-	}
-
-	asoc = sctp_id2assoc(sk, params.assoc_id);
-	if (asoc) {
-		asoc->prsctp_enable = !!params.assoc_value;
-	} else if (!params.assoc_id) {
-		struct sctp_sock *sp = sctp_sk(sk);
+		return -EINVAL;
 
-		sp->ep->prsctp_enable = !!params.assoc_value;
-	} else {
-		goto out;
-	}
+	if (copy_from_user(&params, optval, optlen))
+		return -EFAULT;
 
-	retval = 0;
+	sctp_sk(sk)->ep->prsctp_enable = !!params.assoc_value;
 
-out:
-	return retval;
+	return 0;
 }
 
 static int sctp_setsockopt_default_prinfo(struct sock *sk,
-- 
2.19.1


From d4f4a9ba2ee6445ac43efa0c000c645a0544fa42 Mon Sep 17 00:00:00 2001
From: Stephen Mallon <stephen.mallon@sydney.edu.au>
Date: Tue, 20 Nov 2018 19:15:02 +1100
Subject: [PATCH 09/43] tcp: Fix SOF_TIMESTAMPING_RX_HARDWARE to use the latest
 timestamp during TCP coalescing

[ Upstream commit cadf9df27e7cf40e390e060a1c71bb86ecde798b ]

During tcp coalescing ensure that the skb hardware timestamp refers to the
highest sequence number data.
Previously only the software timestamp was updated during coalescing.

Signed-off-by: Stephen Mallon <stephen.mallon@sydney.edu.au>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 47e08c1b5bc3..72898cbef43d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4371,6 +4371,7 @@ static bool tcp_try_coalesce(struct sock *sk,
 	if (TCP_SKB_CB(from)->has_rxtstamp) {
 		TCP_SKB_CB(to)->has_rxtstamp = true;
 		to->tstamp = from->tstamp;
+		skb_hwtstamps(to)->hwtstamp = skb_hwtstamps(from)->hwtstamp;
 	}
 
 	return true;
-- 
2.19.1


From 4dd647977d5ce17951bd5bb7192a5213668d639a Mon Sep 17 00:00:00 2001
From: Siva Reddy Kallam <siva.kallam@broadcom.com>
Date: Tue, 20 Nov 2018 10:04:04 +0530
Subject: [PATCH 10/43] tg3: Add PHY reset for 5717/5719/5720 in change ring
 and flow control paths

[ Upstream commit 59663e42199c93d1d7314d1446f6782fc4b1eb81 ]

This patch has the fix to avoid PHY lockup with 5717/5719/5720 in change
ring and flow control paths. This patch solves the RX hang while doing
continuous ring or flow control parameters with heavy traffic from peer.

Signed-off-by: Siva Reddy Kallam <siva.kallam@broadcom.com>
Acked-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/tg3.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index e6f28c7942ab..a12962702611 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -12426,6 +12426,7 @@ static int tg3_set_ringparam(struct net_device *dev, struct ethtool_ringparam *e
 {
 	struct tg3 *tp = netdev_priv(dev);
 	int i, irq_sync = 0, err = 0;
+	bool reset_phy = false;
 
 	if ((ering->rx_pending > tp->rx_std_ring_mask) ||
 	    (ering->rx_jumbo_pending > tp->rx_jmb_ring_mask) ||
@@ -12457,7 +12458,13 @@ static int tg3_set_ringparam(struct net_device *dev, struct ethtool_ringparam *e
 
 	if (netif_running(dev)) {
 		tg3_halt(tp, RESET_KIND_SHUTDOWN, 1);
-		err = tg3_restart_hw(tp, false);
+		/* Reset PHY to avoid PHY lock up */
+		if (tg3_asic_rev(tp) == ASIC_REV_5717 ||
+		    tg3_asic_rev(tp) == ASIC_REV_5719 ||
+		    tg3_asic_rev(tp) == ASIC_REV_5720)
+			reset_phy = true;
+
+		err = tg3_restart_hw(tp, reset_phy);
 		if (!err)
 			tg3_netif_start(tp);
 	}
@@ -12491,6 +12498,7 @@ static int tg3_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam
 {
 	struct tg3 *tp = netdev_priv(dev);
 	int err = 0;
+	bool reset_phy = false;
 
 	if (tp->link_config.autoneg == AUTONEG_ENABLE)
 		tg3_warn_mgmt_link_flap(tp);
@@ -12581,7 +12589,13 @@ static int tg3_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam
 
 		if (netif_running(dev)) {
 			tg3_halt(tp, RESET_KIND_SHUTDOWN, 1);
-			err = tg3_restart_hw(tp, false);
+			/* Reset PHY to avoid PHY lock up */
+			if (tg3_asic_rev(tp) == ASIC_REV_5717 ||
+			    tg3_asic_rev(tp) == ASIC_REV_5719 ||
+			    tg3_asic_rev(tp) == ASIC_REV_5720)
+				reset_phy = true;
+
+			err = tg3_restart_hw(tp, reset_phy);
 			if (!err)
 				tg3_netif_start(tp);
 		}
-- 
2.19.1


From 36b32c550777158f289cfa2625ba116ce8625c84 Mon Sep 17 00:00:00 2001
From: Jon Maloy <donmalo99@gmail.com>
Date: Sat, 17 Nov 2018 12:17:06 -0500
Subject: [PATCH 11/43] tipc: don't assume linear buffer when reading ancillary
 data

[ Upstream commit 1c1274a56999fbdf9cf84e332b28448bb2d55221 ]

The code for reading ancillary data from a received buffer is assuming
the buffer is linear. To make this assumption true we have to linearize
the buffer before message data is read.

Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/socket.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 0bf8ad486c5e..366ce0bf2658 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1548,16 +1548,17 @@ static void tipc_sk_set_orig_addr(struct msghdr *m, struct sk_buff *skb)
 /**
  * tipc_sk_anc_data_recv - optionally capture ancillary data for received message
  * @m: descriptor for message info
- * @msg: received message header
+ * @skb: received message buffer
  * @tsk: TIPC port associated with message
  *
  * Note: Ancillary data is not captured if not requested by receiver.
  *
  * Returns 0 if successful, otherwise errno
  */
-static int tipc_sk_anc_data_recv(struct msghdr *m, struct tipc_msg *msg,
+static int tipc_sk_anc_data_recv(struct msghdr *m, struct sk_buff *skb,
 				 struct tipc_sock *tsk)
 {
+	struct tipc_msg *msg;
 	u32 anc_data[3];
 	u32 err;
 	u32 dest_type;
@@ -1566,6 +1567,7 @@ static int tipc_sk_anc_data_recv(struct msghdr *m, struct tipc_msg *msg,
 
 	if (likely(m->msg_controllen == 0))
 		return 0;
+	msg = buf_msg(skb);
 
 	/* Optionally capture errored message object(s) */
 	err = msg ? msg_errcode(msg) : 0;
@@ -1576,6 +1578,9 @@ static int tipc_sk_anc_data_recv(struct msghdr *m, struct tipc_msg *msg,
 		if (res)
 			return res;
 		if (anc_data[1]) {
+			if (skb_linearize(skb))
+				return -ENOMEM;
+			msg = buf_msg(skb);
 			res = put_cmsg(m, SOL_TIPC, TIPC_RETDATA, anc_data[1],
 				       msg_data(msg));
 			if (res)
@@ -1737,9 +1742,10 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m,
 
 	/* Collect msg meta data, including error code and rejected data */
 	tipc_sk_set_orig_addr(m, skb);
-	rc = tipc_sk_anc_data_recv(m, hdr, tsk);
+	rc = tipc_sk_anc_data_recv(m, skb, tsk);
 	if (unlikely(rc))
 		goto exit;
+	hdr = buf_msg(skb);
 
 	/* Capture data if non-error msg, otherwise just set return value */
 	if (likely(!err)) {
@@ -1849,9 +1855,10 @@ static int tipc_recvstream(struct socket *sock, struct msghdr *m,
 		/* Collect msg meta data, incl. error code and rejected data */
 		if (!copied) {
 			tipc_sk_set_orig_addr(m, skb);
-			rc = tipc_sk_anc_data_recv(m, hdr, tsk);
+			rc = tipc_sk_anc_data_recv(m, skb, tsk);
 			if (rc)
 				break;
+			hdr = buf_msg(skb);
 		}
 
 		/* Copy data if msg ok, otherwise return error/partial data */
-- 
2.19.1


From 25faed9dfa4334dccac5df1d6edace464aba562d Mon Sep 17 00:00:00 2001
From: Jon Maloy <donmalo99@gmail.com>
Date: Fri, 16 Nov 2018 16:55:04 -0500
Subject: [PATCH 12/43] tipc: fix lockdep warning when reinitilaizing sockets

[ Upstream commit adba75be0d23cca92a028749d92c60c8909bbdb3 ]

We get the following warning:

[   47.926140] 32-bit node address hash set to 2010a0a
[   47.927202]
[   47.927433] ================================
[   47.928050] WARNING: inconsistent lock state
[   47.928661] 4.19.0+ #37 Tainted: G            E
[   47.929346] --------------------------------
[   47.929954] inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage.
[   47.930116] swapper/3/0 [HC0[0]:SC1[3]:HE1:SE0] takes:
[   47.930116] 00000000af8bc31e (&(&ht->lock)->rlock){+.?.}, at: rhashtable_walk_enter+0x36/0xb0
[   47.930116] {SOFTIRQ-ON-W} state was registered at:
[   47.930116]   _raw_spin_lock+0x29/0x60
[   47.930116]   rht_deferred_worker+0x556/0x810
[   47.930116]   process_one_work+0x1f5/0x540
[   47.930116]   worker_thread+0x64/0x3e0
[   47.930116]   kthread+0x112/0x150
[   47.930116]   ret_from_fork+0x3a/0x50
[   47.930116] irq event stamp: 14044
[   47.930116] hardirqs last  enabled at (14044): [<ffffffff9a07fbba>] __local_bh_enable_ip+0x7a/0xf0
[   47.938117] hardirqs last disabled at (14043): [<ffffffff9a07fb81>] __local_bh_enable_ip+0x41/0xf0
[   47.938117] softirqs last  enabled at (14028): [<ffffffff9a0803ee>] irq_enter+0x5e/0x60
[   47.938117] softirqs last disabled at (14029): [<ffffffff9a0804a5>] irq_exit+0xb5/0xc0
[   47.938117]
[   47.938117] other info that might help us debug this:
[   47.938117]  Possible unsafe locking scenario:
[   47.938117]
[   47.938117]        CPU0
[   47.938117]        ----
[   47.938117]   lock(&(&ht->lock)->rlock);
[   47.938117]   <Interrupt>
[   47.938117]     lock(&(&ht->lock)->rlock);
[   47.938117]
[   47.938117]  *** DEADLOCK ***
[   47.938117]
[   47.938117] 2 locks held by swapper/3/0:
[   47.938117]  #0: 0000000062c64f90 ((&d->timer)){+.-.}, at: call_timer_fn+0x5/0x280
[   47.938117]  #1: 00000000ee39619c (&(&d->lock)->rlock){+.-.}, at: tipc_disc_timeout+0xc8/0x540 [tipc]
[   47.938117]
[   47.938117] stack backtrace:
[   47.938117] CPU: 3 PID: 0 Comm: swapper/3 Tainted: G            E     4.19.0+ #37
[   47.938117] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
[   47.938117] Call Trace:
[   47.938117]  <IRQ>
[   47.938117]  dump_stack+0x5e/0x8b
[   47.938117]  print_usage_bug+0x1ed/0x1ff
[   47.938117]  mark_lock+0x5b5/0x630
[   47.938117]  __lock_acquire+0x4c0/0x18f0
[   47.938117]  ? lock_acquire+0xa6/0x180
[   47.938117]  lock_acquire+0xa6/0x180
[   47.938117]  ? rhashtable_walk_enter+0x36/0xb0
[   47.938117]  _raw_spin_lock+0x29/0x60
[   47.938117]  ? rhashtable_walk_enter+0x36/0xb0
[   47.938117]  rhashtable_walk_enter+0x36/0xb0
[   47.938117]  tipc_sk_reinit+0xb0/0x410 [tipc]
[   47.938117]  ? mark_held_locks+0x6f/0x90
[   47.938117]  ? __local_bh_enable_ip+0x7a/0xf0
[   47.938117]  ? lockdep_hardirqs_on+0x20/0x1a0
[   47.938117]  tipc_net_finalize+0xbf/0x180 [tipc]
[   47.938117]  tipc_disc_timeout+0x509/0x540 [tipc]
[   47.938117]  ? call_timer_fn+0x5/0x280
[   47.938117]  ? tipc_disc_msg_xmit.isra.19+0xa0/0xa0 [tipc]
[   47.938117]  ? tipc_disc_msg_xmit.isra.19+0xa0/0xa0 [tipc]
[   47.938117]  call_timer_fn+0xa1/0x280
[   47.938117]  ? tipc_disc_msg_xmit.isra.19+0xa0/0xa0 [tipc]
[   47.938117]  run_timer_softirq+0x1f2/0x4d0
[   47.938117]  __do_softirq+0xfc/0x413
[   47.938117]  irq_exit+0xb5/0xc0
[   47.938117]  smp_apic_timer_interrupt+0xac/0x210
[   47.938117]  apic_timer_interrupt+0xf/0x20
[   47.938117]  </IRQ>
[   47.938117] RIP: 0010:default_idle+0x1c/0x140
[   47.938117] Code: 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1f 44 00 00 41 54 55 53 65 8b 2d d8 2b 74 65 0f 1f 44 00 00 e8 c6 2c 8b ff fb f4 <65> 8b 2d c5 2b 74 65 0f 1f 44 00 00 5b 5d 41 5c c3 65 8b 05 b4 2b
[   47.938117] RSP: 0018:ffffaf6ac0207ec8 EFLAGS: 00000206 ORIG_RAX: ffffffffffffff13
[   47.938117] RAX: ffff8f5b3735e200 RBX: 0000000000000003 RCX: 0000000000000001
[   47.938117] RDX: 0000000000000001 RSI: 0000000000000001 RDI: ffff8f5b3735e200
[   47.938117] RBP: 0000000000000003 R08: 0000000000000001 R09: 0000000000000000
[   47.938117] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
[   47.938117] R13: 0000000000000000 R14: ffff8f5b3735e200 R15: ffff8f5b3735e200
[   47.938117]  ? default_idle+0x1a/0x140
[   47.938117]  do_idle+0x1bc/0x280
[   47.938117]  cpu_startup_entry+0x19/0x20
[   47.938117]  start_secondary+0x187/0x1c0
[   47.938117]  secondary_startup_64+0xa4/0xb0

The reason seems to be that tipc_net_finalize()->tipc_sk_reinit() is
calling the function rhashtable_walk_enter() within a timer interrupt.
We fix this by executing tipc_net_finalize() in work queue context.

Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/discover.c | 19 ++++++++++---------
 net/tipc/net.c      | 45 +++++++++++++++++++++++++++++++++++++--------
 net/tipc/net.h      |  2 +-
 3 files changed, 48 insertions(+), 18 deletions(-)

diff --git a/net/tipc/discover.c b/net/tipc/discover.c
index 2830709957bd..c138d68e8a69 100644
--- a/net/tipc/discover.c
+++ b/net/tipc/discover.c
@@ -166,7 +166,8 @@ static bool tipc_disc_addr_trial_msg(struct tipc_discoverer *d,
 
 	/* Apply trial address if we just left trial period */
 	if (!trial && !self) {
-		tipc_net_finalize(net, tn->trial_addr);
+		tipc_sched_net_finalize(net, tn->trial_addr);
+		msg_set_prevnode(buf_msg(d->skb), tn->trial_addr);
 		msg_set_type(buf_msg(d->skb), DSC_REQ_MSG);
 	}
 
@@ -300,14 +301,12 @@ static void tipc_disc_timeout(struct timer_list *t)
 		goto exit;
 	}
 
-	/* Trial period over ? */
-	if (!time_before(jiffies, tn->addr_trial_end)) {
-		/* Did we just leave it ? */
-		if (!tipc_own_addr(net))
-			tipc_net_finalize(net, tn->trial_addr);
-
-		msg_set_type(buf_msg(d->skb), DSC_REQ_MSG);
-		msg_set_prevnode(buf_msg(d->skb), tipc_own_addr(net));
+	/* Did we just leave trial period ? */
+	if (!time_before(jiffies, tn->addr_trial_end) && !tipc_own_addr(net)) {
+		mod_timer(&d->timer, jiffies + TIPC_DISC_INIT);
+		spin_unlock_bh(&d->lock);
+		tipc_sched_net_finalize(net, tn->trial_addr);
+		return;
 	}
 
 	/* Adjust timeout interval according to discovery phase */
@@ -319,6 +318,8 @@ static void tipc_disc_timeout(struct timer_list *t)
 			d->timer_intv = TIPC_DISC_SLOW;
 		else if (!d->num_nodes && d->timer_intv > TIPC_DISC_FAST)
 			d->timer_intv = TIPC_DISC_FAST;
+		msg_set_type(buf_msg(d->skb), DSC_REQ_MSG);
+		msg_set_prevnode(buf_msg(d->skb), tn->trial_addr);
 	}
 
 	mod_timer(&d->timer, jiffies + d->timer_intv);
diff --git a/net/tipc/net.c b/net/tipc/net.c
index 62199cf5a56c..f076edb74338 100644
--- a/net/tipc/net.c
+++ b/net/tipc/net.c
@@ -104,6 +104,14 @@
  *     - A local spin_lock protecting the queue of subscriber events.
 */
 
+struct tipc_net_work {
+	struct work_struct work;
+	struct net *net;
+	u32 addr;
+};
+
+static void tipc_net_finalize(struct net *net, u32 addr);
+
 int tipc_net_init(struct net *net, u8 *node_id, u32 addr)
 {
 	if (tipc_own_id(net)) {
@@ -119,17 +127,38 @@ int tipc_net_init(struct net *net, u8 *node_id, u32 addr)
 	return 0;
 }
 
-void tipc_net_finalize(struct net *net, u32 addr)
+static void tipc_net_finalize(struct net *net, u32 addr)
 {
 	struct tipc_net *tn = tipc_net(net);
 
-	if (!cmpxchg(&tn->node_addr, 0, addr)) {
-		tipc_set_node_addr(net, addr);
-		tipc_named_reinit(net);
-		tipc_sk_reinit(net);
-		tipc_nametbl_publish(net, TIPC_CFG_SRV, addr, addr,
-				     TIPC_CLUSTER_SCOPE, 0, addr);
-	}
+	if (cmpxchg(&tn->node_addr, 0, addr))
+		return;
+	tipc_set_node_addr(net, addr);
+	tipc_named_reinit(net);
+	tipc_sk_reinit(net);
+	tipc_nametbl_publish(net, TIPC_CFG_SRV, addr, addr,
+			     TIPC_CLUSTER_SCOPE, 0, addr);
+}
+
+static void tipc_net_finalize_work(struct work_struct *work)
+{
+	struct tipc_net_work *fwork;
+
+	fwork = container_of(work, struct tipc_net_work, work);
+	tipc_net_finalize(fwork->net, fwork->addr);
+	kfree(fwork);
+}
+
+void tipc_sched_net_finalize(struct net *net, u32 addr)
+{
+	struct tipc_net_work *fwork = kzalloc(sizeof(*fwork), GFP_ATOMIC);
+
+	if (!fwork)
+		return;
+	INIT_WORK(&fwork->work, tipc_net_finalize_work);
+	fwork->net = net;
+	fwork->addr = addr;
+	schedule_work(&fwork->work);
 }
 
 void tipc_net_stop(struct net *net)
diff --git a/net/tipc/net.h b/net/tipc/net.h
index 09ad02b50bb1..b7f2e364eb99 100644
--- a/net/tipc/net.h
+++ b/net/tipc/net.h
@@ -42,7 +42,7 @@
 extern const struct nla_policy tipc_nl_net_policy[];
 
 int tipc_net_init(struct net *net, u8 *node_id, u32 addr);
-void tipc_net_finalize(struct net *net, u32 addr);
+void tipc_sched_net_finalize(struct net *net, u32 addr);
 void tipc_net_stop(struct net *net);
 int tipc_nl_net_dump(struct sk_buff *skb, struct netlink_callback *cb);
 int tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info);
-- 
2.19.1


From 4a45693068a6de191aea5db738c8a13dd2c99573 Mon Sep 17 00:00:00 2001
From: Matthew Cover <werekraken@gmail.com>
Date: Sun, 18 Nov 2018 00:46:00 -0700
Subject: [PATCH 13/43] tuntap: fix multiqueue rx

[ Upstream commit 8ebebcba559a1bfbaec7bbda64feb9870b9c58da ]

When writing packets to a descriptor associated with a combined queue, the
packets should end up on that queue.

Before this change all packets written to any descriptor associated with a
tap interface end up on rx-0, even when the descriptor is associated with a
different queue.

The rx traffic can be generated by either of the following.
  1. a simple tap program which spins up multiple queues and writes packets
     to each of the file descriptors
  2. tx from a qemu vm with a tap multiqueue netdev

The queue for rx traffic can be observed by either of the following (done
on the hypervisor in the qemu case).
  1. a simple netmap program which opens and reads from per-queue
     descriptors
  2. configuring RPS and doing per-cpu captures with rxtxcpu

Alternatively, if you printk() the return value of skb_get_rx_queue() just
before each instance of netif_receive_skb() in tun.c, you will get 65535
for every skb.

Calling skb_record_rx_queue() to set the rx queue to the queue_index fixes
the association between descriptor and rx queue.

Signed-off-by: Matthew Cover <matthew.cover@stackpath.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index c52207beef88..573620771154 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1527,6 +1527,7 @@ static void tun_rx_batched(struct tun_struct *tun, struct tun_file *tfile,
 
 	if (!rx_batched || (!more && skb_queue_empty(queue))) {
 		local_bh_disable();
+		skb_record_rx_queue(skb, tfile->queue_index);
 		netif_receive_skb(skb);
 		local_bh_enable();
 		return;
@@ -1546,8 +1547,11 @@ static void tun_rx_batched(struct tun_struct *tun, struct tun_file *tfile,
 		struct sk_buff *nskb;
 
 		local_bh_disable();
-		while ((nskb = __skb_dequeue(&process_queue)))
+		while ((nskb = __skb_dequeue(&process_queue))) {
+			skb_record_rx_queue(nskb, tfile->queue_index);
 			netif_receive_skb(nskb);
+		}
+		skb_record_rx_queue(skb, tfile->queue_index);
 		netif_receive_skb(skb);
 		local_bh_enable();
 	}
-- 
2.19.1


From 0d39d9e3dce2452f39064b72ad560e373d70e7a9 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 1 Nov 2018 15:55:38 -0700
Subject: [PATCH 14/43] net: systemport: Protect stop from timeout

[ Upstream commit 7cb6a2a2c72c1ed8f42fb01f1a661281b568dead ]

A timing hazard exists when the network interface is stopped that
allows a watchdog timeout to be processed by a separate core in
parallel. This creates the potential for the timeout handler to
wake the queues while the driver is shutting down, or access
registers after their clocks have been removed.

The more common case is that the watchdog timeout will produce a
warning message which doesn't lead to a crash. The chances of this
are greatly increased by the fact that bcm_sysport_netif_stop stops
the transmit queues which can easily precipitate a watchdog time-
out because of stale trans_start data in the queues.

This commit corrects the behavior by ensuring that the watchdog
timeout is disabled before enterring bcm_sysport_netif_stop. There
are currently only two users of the bcm_sysport_netif_stop function:
close and suspend.

The close case already handles the issue by exiting the RUNNING
state before invoking the driver close service.

The suspend case now performs the netif_device_detach to exit the
PRESENT state before the call to bcm_sysport_netif_stop rather than
after it.

These behaviors prevent any future scheduling of the driver timeout
service during the window. The netif_tx_stop_all_queues function
in bcm_sysport_netif_stop is replaced with netif_tx_disable to ensure
synchronization with any transmit or timeout threads that may
already be executing on other cores.

For symmetry, the netif_device_attach call upon resume is moved to
after the call to bcm_sysport_netif_start. Since it wakes the transmit
queues it is not necessary to invoke netif_tx_start_all_queues from
bcm_sysport_netif_start so it is moved into the driver open service.

Fixes: 40755a0fce17 ("net: systemport: add suspend and resume support")
Fixes: 80105befdb4b ("net: systemport: add Broadcom SYSTEMPORT Ethernet MAC driver")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bcmsysport.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index c57238fce863..7b6859e4924e 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -1897,9 +1897,6 @@ static void bcm_sysport_netif_start(struct net_device *dev)
 		intrl2_1_mask_clear(priv, 0xffffffff);
 	else
 		intrl2_0_mask_clear(priv, INTRL2_0_TDMA_MBDONE_MASK);
-
-	/* Last call before we start the real business */
-	netif_tx_start_all_queues(dev);
 }
 
 static void rbuf_init(struct bcm_sysport_priv *priv)
@@ -2045,6 +2042,8 @@ static int bcm_sysport_open(struct net_device *dev)
 
 	bcm_sysport_netif_start(dev);
 
+	netif_tx_start_all_queues(dev);
+
 	return 0;
 
 out_clear_rx_int:
@@ -2068,7 +2067,7 @@ static void bcm_sysport_netif_stop(struct net_device *dev)
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
 
 	/* stop all software from updating hardware */
-	netif_tx_stop_all_queues(dev);
+	netif_tx_disable(dev);
 	napi_disable(&priv->napi);
 	cancel_work_sync(&priv->dim.dim.work);
 	phy_stop(dev->phydev);
@@ -2654,12 +2653,12 @@ static int __maybe_unused bcm_sysport_suspend(struct device *d)
 	if (!netif_running(dev))
 		return 0;
 
+	netif_device_detach(dev);
+
 	bcm_sysport_netif_stop(dev);
 
 	phy_suspend(dev->phydev);
 
-	netif_device_detach(dev);
-
 	/* Disable UniMAC RX */
 	umac_enable_set(priv, CMD_RX_EN, 0);
 
@@ -2743,8 +2742,6 @@ static int __maybe_unused bcm_sysport_resume(struct device *d)
 		goto out_free_rx_ring;
 	}
 
-	netif_device_attach(dev);
-
 	/* RX pipe enable */
 	topctrl_writel(priv, 0, RX_FLUSH_CNTL);
 
@@ -2789,6 +2786,8 @@ static int __maybe_unused bcm_sysport_resume(struct device *d)
 
 	bcm_sysport_netif_start(dev);
 
+	netif_device_attach(dev);
+
 	return 0;
 
 out_free_rx_ring:
-- 
2.19.1


From d40e3da347bbb3fee2d546b572e5619b2bafa677 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Wed, 14 Nov 2018 12:17:25 +0100
Subject: [PATCH 15/43] net/sched: act_pedit: fix memory leak when IDR
 allocation fails

[ Upstream commit 19ab69107d3ecfb7cd3e38ad262a881be40c01a3 ]

tcf_idr_check_alloc() can return a negative value, on allocation failures
(-ENOMEM) or IDR exhaustion (-ENOSPC): don't leak keys_ex in these cases.

Fixes: 0190c1d452a9 ("net: sched: atomically check-allocate action")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_pedit.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index ad99a99f11f6..ca535a8585bc 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -201,7 +201,8 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 			goto out_release;
 		}
 	} else {
-		return err;
+		ret = err;
+		goto out_free;
 	}
 
 	p = to_pedit(*a);
-- 
2.19.1


From ea4d443600fb834e225b1d00e4e8819a04b5d77b Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 9 Nov 2018 21:06:26 -0800
Subject: [PATCH 16/43] net: sched: cls_flower: validate nested enc_opts_policy
 to avoid warning
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 63c82997f5c0f3e1b914af43d82f712a86bc5f3a ]

TCA_FLOWER_KEY_ENC_OPTS and TCA_FLOWER_KEY_ENC_OPTS_MASK can only
currently contain further nested attributes, which are parsed by
hand, so the policy is never actually used resulting in a W=1
build warning:

net/sched/cls_flower.c:492:1: warning: ‘enc_opts_policy’ defined but not used [-Wunused-const-variable=]
 enc_opts_policy[TCA_FLOWER_KEY_ENC_OPTS_MAX + 1] = {

Add the validation anyway to avoid potential bugs when other
attributes are added and to make the attribute structure slightly
more clear.  Validation will also set extact to point to bad
attribute on error.

Fixes: 0a6e77784f49 ("net/sched: allow flower to match tunnel options")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Simon Horman <simon.horman@netronome.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_flower.c | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 6fd9bdd93796..7fade7107f95 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -709,11 +709,23 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key,
 			  struct netlink_ext_ack *extack)
 {
 	const struct nlattr *nla_enc_key, *nla_opt_key, *nla_opt_msk = NULL;
-	int option_len, key_depth, msk_depth = 0;
+	int err, option_len, key_depth, msk_depth = 0;
+
+	err = nla_validate_nested(tb[TCA_FLOWER_KEY_ENC_OPTS],
+				  TCA_FLOWER_KEY_ENC_OPTS_MAX,
+				  enc_opts_policy, extack);
+	if (err)
+		return err;
 
 	nla_enc_key = nla_data(tb[TCA_FLOWER_KEY_ENC_OPTS]);
 
 	if (tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]) {
+		err = nla_validate_nested(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK],
+					  TCA_FLOWER_KEY_ENC_OPTS_MAX,
+					  enc_opts_policy, extack);
+		if (err)
+			return err;
+
 		nla_opt_msk = nla_data(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]);
 		msk_depth = nla_len(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]);
 	}
-- 
2.19.1


From bf43765184d7713e71eb9c57d6817608bf9041ae Mon Sep 17 00:00:00 2001
From: Jon Maloy <donmalo99@gmail.com>
Date: Sat, 10 Nov 2018 17:30:24 -0500
Subject: [PATCH 17/43] tipc: fix link re-establish failure

[ Upstream commit 7ab412d33b4c7ff3e0148d3db25dd861edd1283d ]

When a link failure is detected locally, the link is reset, the flag
link->in_session is set to false, and a RESET_MSG with the 'stopping'
bit set is sent to the peer.

The purpose of this bit is to inform the peer that this endpoint just
is going down, and that the peer should handle the reception of this
particular RESET message as a local failure. This forces the peer to
accept another RESET or ACTIVATE message from this endpoint before it
can re-establish the link. This again is necessary to ensure that
link session numbers are properly exchanged before the link comes up
again.

If a failure is detected locally at the same time at the peer endpoint
this will do the same, which is also a correct behavior.

However, when receiving such messages, the endpoints will not
distinguish between 'stopping' RESETs and ordinary ones when it comes
to updating session numbers. Both endpoints will copy the received
session number and set their 'in_session' flags to true at the
reception, while they are still expecting another RESET from the
peer before they can go ahead and re-establish. This is contradictory,
since, after applying the validation check referred to below, the
'in_session' flag will cause rejection of all such messages, and the
link will never come up again.

We now fix this by not only handling received RESET/STOPPING messages
as a local failure, but also by omitting to set a new session number
and the 'in_session' flag in such cases.

Fixes: 7ea817f4e832 ("tipc: check session number before accepting link protocol messages")
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/link.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/net/tipc/link.c b/net/tipc/link.c
index 201c3b5bc96b..836727e363c4 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -1594,14 +1594,17 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
 		if (in_range(peers_prio, l->priority + 1, TIPC_MAX_LINK_PRI))
 			l->priority = peers_prio;
 
-		/* ACTIVATE_MSG serves as PEER_RESET if link is already down */
-		if (msg_peer_stopping(hdr))
+		/* If peer is going down we want full re-establish cycle */
+		if (msg_peer_stopping(hdr)) {
 			rc = tipc_link_fsm_evt(l, LINK_FAILURE_EVT);
-		else if ((mtyp == RESET_MSG) || !link_is_up(l))
+			break;
+		}
+		/* ACTIVATE_MSG serves as PEER_RESET if link is already down */
+		if (mtyp == RESET_MSG || !link_is_up(l))
 			rc = tipc_link_fsm_evt(l, LINK_PEER_RESET_EVT);
 
 		/* ACTIVATE_MSG takes up link if it was already locally reset */
-		if ((mtyp == ACTIVATE_MSG) && (l->state == LINK_ESTABLISHING))
+		if (mtyp == ACTIVATE_MSG && l->state == LINK_ESTABLISHING)
 			rc = TIPC_LINK_UP_EVT;
 
 		l->peer_session = msg_session(hdr);
-- 
2.19.1


From a69d0f3ce3ba98b09633aabce68c337f0ebe5780 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Thu, 25 Oct 2018 15:41:58 +0000
Subject: [PATCH 18/43] net/mlx5e: Don't match on vlan non-existence if
 ethertype is wildcarded

[ Upstream commit d3a80bb5a3eac311ddf28387402593977574460d ]

For the "all" ethertype we should not care whether the packet has
vlans. Besides being wrong, the way we did it caused FW error
for rules such as:

tc filter add dev eth0 protocol all parent ffff: \
	prio 1 flower skip_sw action drop

b/c the matching meta-data (outer headers bit in struct mlx5_flow_spec)
wasn't set. Fix that by matching on vlan non-existence only if we were
also told to match on the ethertype.

Fixes: cee26487620b ('net/mlx5e: Set vlan masks for all offloaded TC rules')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reported-by: Slava Ovsiienko <viacheslavo@mellanox.com>
Reviewed-by: Jianbo Liu <jianbol@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en_tc.c   | 63 ++++++++++---------
 1 file changed, 32 insertions(+), 31 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 85796727093e..e3eecbb11a14 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1310,31 +1310,21 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 					 inner_headers);
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
-		struct flow_dissector_key_eth_addrs *key =
+	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_dissector_key_basic *key =
 			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ETH_ADDRS,
+						  FLOW_DISSECTOR_KEY_BASIC,
 						  f->key);
-		struct flow_dissector_key_eth_addrs *mask =
+		struct flow_dissector_key_basic *mask =
 			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ETH_ADDRS,
+						  FLOW_DISSECTOR_KEY_BASIC,
 						  f->mask);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ethertype,
+			 ntohs(mask->n_proto));
+		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype,
+			 ntohs(key->n_proto));
 
-		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
-					     dmac_47_16),
-				mask->dst);
-		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
-					     dmac_47_16),
-				key->dst);
-
-		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
-					     smac_47_16),
-				mask->src);
-		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
-					     smac_47_16),
-				key->src);
-
-		if (!is_zero_ether_addr(mask->src) || !is_zero_ether_addr(mask->dst))
+		if (mask->n_proto)
 			*match_level = MLX5_MATCH_L2;
 	}
 
@@ -1368,9 +1358,10 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 
 			*match_level = MLX5_MATCH_L2;
 		}
-	} else {
+	} else if (*match_level != MLX5_MATCH_NONE) {
 		MLX5_SET(fte_match_set_lyr_2_4, headers_c, svlan_tag, 1);
 		MLX5_SET(fte_match_set_lyr_2_4, headers_c, cvlan_tag, 1);
+		*match_level = MLX5_MATCH_L2;
 	}
 
 	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CVLAN)) {
@@ -1408,21 +1399,31 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 		}
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
-		struct flow_dissector_key_basic *key =
+	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+		struct flow_dissector_key_eth_addrs *key =
 			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
+						  FLOW_DISSECTOR_KEY_ETH_ADDRS,
 						  f->key);
-		struct flow_dissector_key_basic *mask =
+		struct flow_dissector_key_eth_addrs *mask =
 			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
+						  FLOW_DISSECTOR_KEY_ETH_ADDRS,
 						  f->mask);
-		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ethertype,
-			 ntohs(mask->n_proto));
-		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype,
-			 ntohs(key->n_proto));
 
-		if (mask->n_proto)
+		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
+					     dmac_47_16),
+				mask->dst);
+		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
+					     dmac_47_16),
+				key->dst);
+
+		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
+					     smac_47_16),
+				mask->src);
+		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
+					     smac_47_16),
+				key->src);
+
+		if (!is_zero_ether_addr(mask->src) || !is_zero_ether_addr(mask->dst))
 			*match_level = MLX5_MATCH_L2;
 	}
 
-- 
2.19.1


From 9de2a214483ed1750af8a587b0a4073f1f8beac9 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Thu, 18 Oct 2018 12:31:27 +0200
Subject: [PATCH 19/43] net/mlx5e: Claim TC hw offloads support only under a
 proper build config

[ Upstream commit 077ecd785d90c6cbba08d719faa4be8561aa0a1e ]

Currently, we are only supporting tc hw offloads when the eswitch
support is compiled in, but we are not gating the adevertizment
of the NETIF_F_HW_TC feature on this config being set.

Fix it, and while doing that, also avoid dealing with the feature
on ethtool when the config is not set.

Fixes: e8f887ac6a45 ('net/mlx5e: Introduce tc offload support')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index f291d1bf1558..e56f0f17e5fb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3566,6 +3566,7 @@ static int set_feature_cvlan_filter(struct net_device *netdev, bool enable)
 	return 0;
 }
 
+#ifdef CONFIG_MLX5_ESWITCH
 static int set_feature_tc_num_filters(struct net_device *netdev, bool enable)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -3578,6 +3579,7 @@ static int set_feature_tc_num_filters(struct net_device *netdev, bool enable)
 
 	return 0;
 }
+#endif
 
 static int set_feature_rx_all(struct net_device *netdev, bool enable)
 {
@@ -3676,7 +3678,9 @@ static int mlx5e_set_features(struct net_device *netdev,
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_LRO, set_feature_lro);
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_HW_VLAN_CTAG_FILTER,
 				    set_feature_cvlan_filter);
+#ifdef CONFIG_MLX5_ESWITCH
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_HW_TC, set_feature_tc_num_filters);
+#endif
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_RXALL, set_feature_rx_all);
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_RXFCS, set_feature_rx_fcs);
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_HW_VLAN_CTAG_RX, set_feature_rx_vlan);
@@ -4685,7 +4689,9 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	    FT_CAP(modify_root) &&
 	    FT_CAP(identified_miss_table_mode) &&
 	    FT_CAP(flow_table_modify)) {
+#ifdef CONFIG_MLX5_ESWITCH
 		netdev->hw_features      |= NETIF_F_HW_TC;
+#endif
 #ifdef CONFIG_MLX5_EN_ARFS
 		netdev->hw_features	 |= NETIF_F_NTUPLE;
 #endif
-- 
2.19.1


From 9e0d68fb490114606e682ad087036ea4f621f239 Mon Sep 17 00:00:00 2001
From: Yuval Avnery <yuvalav@mellanox.com>
Date: Tue, 16 Oct 2018 15:20:20 -0500
Subject: [PATCH 20/43] net/mlx5e: Adjust to max number of channles when
 re-attaching

[ Upstream commit a1f240f1801721f76bee734c50df2d9529da86e0 ]

When core driver enters deattach/attach flow after pci reset,
Number of logical CPUs may have changed.
As a result we need to update the cpu affiliated resource tables.
	1. indirect rqt list
	2. eq table

Reproduction (PowerPC):
	echo 1000 > /sys/kernel/debug/powerpc/eeh_max_freezes
	ppc64_cpu --smt=on
	# Restart driver
	modprobe -r ... ; modprobe ...
	# Link up
	ifconfig ...
	# Only physical CPUs
	ppc64_cpu --smt=off
	# Inject PCI errors so PCI will reset - calling the pci error handler
	echo 0x8000000000000000 > /sys/kernel/debug/powerpc/<PCI BUS>/err_injct_inboundA

Call trace when trying to add non-existing rqs to an indirect rqt:
	mlx5e_redirect_rqt+0x84/0x260 [mlx5_core] (unreliable)
	mlx5e_redirect_rqts+0x188/0x190 [mlx5_core]
	mlx5e_activate_priv_channels+0x488/0x570 [mlx5_core]
	mlx5e_open_locked+0xbc/0x140 [mlx5_core]
	mlx5e_open+0x50/0x130 [mlx5_core]
	mlx5e_nic_enable+0x174/0x1b0 [mlx5_core]
	mlx5e_attach_netdev+0x154/0x290 [mlx5_core]
	mlx5e_attach+0x88/0xd0 [mlx5_core]
	mlx5_attach_device+0x168/0x1e0 [mlx5_core]
	mlx5_load_one+0x1140/0x1210 [mlx5_core]
	mlx5_pci_resume+0x6c/0xf0 [mlx5_core]

Create cq will fail when trying to use non-existing EQ.

Fixes: 89d44f0a6c73 ("net/mlx5_core: Add pci error handlers to mlx5_core driver")
Signed-off-by: Yuval Avnery <yuvalav@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en_main.c | 27 +++++++++++++++----
 1 file changed, 22 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index e56f0f17e5fb..6e8eead8fde5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1610,13 +1610,15 @@ static int mlx5e_alloc_cq_common(struct mlx5_core_dev *mdev,
 	int err;
 	u32 i;
 
+	err = mlx5_vector2eqn(mdev, param->eq_ix, &eqn_not_used, &irqn);
+	if (err)
+		return err;
+
 	err = mlx5_cqwq_create(mdev, &param->wq, param->cqc, &cq->wq,
 			       &cq->wq_ctrl);
 	if (err)
 		return err;
 
-	mlx5_vector2eqn(mdev, param->eq_ix, &eqn_not_used, &irqn);
-
 	mcq->cqe_sz     = 64;
 	mcq->set_ci_db  = cq->wq_ctrl.db.db;
 	mcq->arm_db     = cq->wq_ctrl.db.db + 1;
@@ -1674,6 +1676,10 @@ static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
 	int eqn;
 	int err;
 
+	err = mlx5_vector2eqn(mdev, param->eq_ix, &eqn, &irqn_not_used);
+	if (err)
+		return err;
+
 	inlen = MLX5_ST_SZ_BYTES(create_cq_in) +
 		sizeof(u64) * cq->wq_ctrl.buf.npages;
 	in = kvzalloc(inlen, GFP_KERNEL);
@@ -1687,8 +1693,6 @@ static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
 	mlx5_fill_page_frag_array(&cq->wq_ctrl.buf,
 				  (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas));
 
-	mlx5_vector2eqn(mdev, param->eq_ix, &eqn, &irqn_not_used);
-
 	MLX5_SET(cqc,   cqc, cq_period_mode, param->cq_period_mode);
 	MLX5_SET(cqc,   cqc, c_eqn,         eqn);
 	MLX5_SET(cqc,   cqc, uar_page,      mdev->priv.uar->index);
@@ -1908,6 +1912,10 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	int err;
 	int eqn;
 
+	err = mlx5_vector2eqn(priv->mdev, ix, &eqn, &irq);
+	if (err)
+		return err;
+
 	c = kvzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
 	if (!c)
 		return -ENOMEM;
@@ -1924,7 +1932,6 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	c->xdp      = !!params->xdp_prog;
 	c->stats    = &priv->channel_stats[ix].ch;
 
-	mlx5_vector2eqn(priv->mdev, ix, &eqn, &irq);
 	c->irq_desc = irq_to_desc(irq);
 
 	netif_napi_add(netdev, &c->napi, mlx5e_napi_poll, 64);
@@ -4964,11 +4971,21 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	const struct mlx5e_profile *profile;
+	int max_nch;
 	int err;
 
 	profile = priv->profile;
 	clear_bit(MLX5E_STATE_DESTROYING, &priv->state);
 
+	/* max number of channels may have changed */
+	max_nch = mlx5e_get_max_num_channels(priv->mdev);
+	if (priv->channels.params.num_channels > max_nch) {
+		mlx5_core_warn(priv->mdev, "MLX5E: Reducing number of channels to %d\n", max_nch);
+		priv->channels.params.num_channels = max_nch;
+		mlx5e_build_default_indir_rqt(priv->channels.params.indirection_rqt,
+					      MLX5E_INDIR_RQT_SIZE, max_nch);
+	}
+
 	err = profile->init_tx(priv);
 	if (err)
 		goto out;
-- 
2.19.1


From e4c3c65cc7ced7612a38f551edbc628dec20b7dc Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Thu, 11 Oct 2018 07:31:10 +0300
Subject: [PATCH 21/43] net/mlx5e: RX, verify received packet size in Linear
 Striding RQ

[ Upstream commit 0073c8f72736b423aade8a817587a5f3e4df4ad8 ]

In case of striding RQ, we use  MPWRQ (Multi Packet WQE RQ), which means
that WQE (RX descriptor) can be used for many packets and so the WQE is
much bigger than MTU.  In virtualization setups where the port mtu can
be larger than the vf mtu, if received packet is bigger than MTU, it
won't be dropped by HW on too small receive WQE. If we use linear SKB in
striding RQ, since each stride has room for mtu size payload and skb
info, an oversized packet can lead to crash for crossing allocated page
boundary upon the call to build_skb. So driver needs to check packet
size and drop it.

Introduce new SW rx counter, rx_oversize_pkts_sw_drop, which counts the
number of packets dropped by the driver for being too large.

As a new field is added to the RQ struct, re-open the channels whenever
this field is being used in datapath (i.e., in the case of linear
Striding RQ).

Fixes: 619a8f2a42f1 ("net/mlx5e: Use linear SKB in Striding RQ")
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h       | 1 +
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  | 4 +++-
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c    | 6 ++++++
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.c | 3 +++
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.h | 2 ++
 5 files changed, 15 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 0f189f873859..16ceeb1b2c9d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -566,6 +566,7 @@ struct mlx5e_rq {
 
 	unsigned long          state;
 	int                    ix;
+	unsigned int           hw_mtu;
 
 	struct net_dim         dim; /* Dynamic Interrupt Moderation */
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 6e8eead8fde5..faa84b45e20a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -492,6 +492,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	rq->channel = c;
 	rq->ix      = c->ix;
 	rq->mdev    = mdev;
+	rq->hw_mtu  = MLX5E_SW2HW_MTU(params, params->sw_mtu);
 	rq->stats   = &c->priv->channel_stats[c->ix].rq;
 
 	rq->xdp_prog = params->xdp_prog ? bpf_prog_inc(params->xdp_prog) : NULL;
@@ -3758,10 +3759,11 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu,
 	}
 
 	if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
+		bool is_linear = mlx5e_rx_mpwqe_is_linear_skb(priv->mdev, &new_channels.params);
 		u8 ppw_old = mlx5e_mpwqe_log_pkts_per_wqe(params);
 		u8 ppw_new = mlx5e_mpwqe_log_pkts_per_wqe(&new_channels.params);
 
-		reset = reset && (ppw_old != ppw_new);
+		reset = reset && (is_linear || (ppw_old != ppw_new));
 	}
 
 	if (!reset) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index a144146b769c..d543a5cff049 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1064,6 +1064,12 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 	u32 frag_size;
 	bool consumed;
 
+	/* Check packet size. Note LRO doesn't use linear SKB */
+	if (unlikely(cqe_bcnt > rq->hw_mtu)) {
+		rq->stats->oversize_pkts_sw_drop++;
+		return NULL;
+	}
+
 	va             = page_address(di->page) + head_offset;
 	data           = va + rx_headroom;
 	frag_size      = MLX5_SKB_FRAG_SZ(rx_headroom + cqe_bcnt32);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 6839481f7697..d57d51c4e658 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -82,6 +82,7 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_wqe_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler_cqes) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler_strides) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_oversize_pkts_sw_drop) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_buff_alloc_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_blks) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_pkts) },
@@ -158,6 +159,7 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 		s->rx_wqe_err   += rq_stats->wqe_err;
 		s->rx_mpwqe_filler_cqes    += rq_stats->mpwqe_filler_cqes;
 		s->rx_mpwqe_filler_strides += rq_stats->mpwqe_filler_strides;
+		s->rx_oversize_pkts_sw_drop += rq_stats->oversize_pkts_sw_drop;
 		s->rx_buff_alloc_err += rq_stats->buff_alloc_err;
 		s->rx_cqe_compress_blks += rq_stats->cqe_compress_blks;
 		s->rx_cqe_compress_pkts += rq_stats->cqe_compress_pkts;
@@ -1148,6 +1150,7 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, wqe_err) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler_cqes) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler_strides) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, oversize_pkts_sw_drop) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, buff_alloc_err) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_blks) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_pkts) },
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index a4c035aedd46..c1064af9d54c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -95,6 +95,7 @@ struct mlx5e_sw_stats {
 	u64 rx_wqe_err;
 	u64 rx_mpwqe_filler_cqes;
 	u64 rx_mpwqe_filler_strides;
+	u64 rx_oversize_pkts_sw_drop;
 	u64 rx_buff_alloc_err;
 	u64 rx_cqe_compress_blks;
 	u64 rx_cqe_compress_pkts;
@@ -190,6 +191,7 @@ struct mlx5e_rq_stats {
 	u64 wqe_err;
 	u64 mpwqe_filler_cqes;
 	u64 mpwqe_filler_strides;
+	u64 oversize_pkts_sw_drop;
 	u64 buff_alloc_err;
 	u64 cqe_compress_blks;
 	u64 cqe_compress_pkts;
-- 
2.19.1


From c77997a017fc1c4bd3807dbde7262edf188b4698 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 18 Nov 2018 16:14:47 +0800
Subject: [PATCH 22/43] Revert "sctp: remove sctp_transport_pmtu_check"

[ Upstream commit 69fec325a64383667b8a35df5d48d6ce52fb2782 ]

This reverts commit 22d7be267eaa8114dcc28d66c1c347f667d7878a.

The dst's mtu in transport can be updated by a non sctp place like
in xfrm where the MTU information didn't get synced between asoc,
transport and dst, so it is still needed to do the pmtu check
in sctp_packet_config.

Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/sctp.h | 12 ++++++++++++
 net/sctp/output.c       |  3 +++
 2 files changed, 15 insertions(+)

diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 8c2caa370e0f..ab9242e51d9e 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -608,4 +608,16 @@ static inline __u32 sctp_dst_mtu(const struct dst_entry *dst)
 				 SCTP_DEFAULT_MINSEGMENT));
 }
 
+static inline bool sctp_transport_pmtu_check(struct sctp_transport *t)
+{
+	__u32 pmtu = sctp_dst_mtu(t->dst);
+
+	if (t->pathmtu == pmtu)
+		return true;
+
+	t->pathmtu = pmtu;
+
+	return false;
+}
+
 #endif /* __net_sctp_h__ */
diff --git a/net/sctp/output.c b/net/sctp/output.c
index 67939ad99c01..08601223b0bf 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -118,6 +118,9 @@ void sctp_packet_config(struct sctp_packet *packet, __u32 vtag,
 		sctp_transport_route(tp, NULL, sp);
 		if (asoc->param_flags & SPP_PMTUD_ENABLE)
 			sctp_assoc_sync_pmtu(asoc);
+	} else if (!sctp_transport_pmtu_check(tp)) {
+		if (asoc->param_flags & SPP_PMTUD_ENABLE)
+			sctp_assoc_sync_pmtu(asoc);
 	}
 
 	if (asoc->pmtu_pending) {
-- 
2.19.1


From 21e4eedf92c1dcdf53496ec865d70559dcf1c1b4 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Sun, 28 Oct 2018 12:27:29 +0200
Subject: [PATCH 23/43] net/mlx5e: Always use the match level enum when parsing
 TC rule match

[ Upstream commit 83621b7df6a646e550fd3d36db2e301cf9a5096b ]

We get the match level (none, l2, l3, l4) while going over the match
dissectors of an offloaded tc rule. When doing this, the match level
enum and the not min inline enum values should be used, fix that.

This worked accidentally b/c both enums have the same numerical values.

Fixes: d708f902989b ('net/mlx5e: Get the required HW match level while parsing TC flow matches')
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index e3eecbb11a14..3092c59c0dc7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1450,10 +1450,10 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 
 			/* the HW doesn't need L3 inline to match on frag=no */
 			if (!(key->flags & FLOW_DIS_IS_FRAGMENT))
-				*match_level = MLX5_INLINE_MODE_L2;
+				*match_level = MLX5_MATCH_L2;
 	/* ***  L2 attributes parsing up to here *** */
 			else
-				*match_level = MLX5_INLINE_MODE_IP;
+				*match_level = MLX5_MATCH_L3;
 		}
 	}
 
-- 
2.19.1


From 3e72cb947708bbd7c608a32d1bcd92d7c2c53b24 Mon Sep 17 00:00:00 2001
From: Valentine Fatiev <valentinef@mellanox.com>
Date: Wed, 17 Oct 2018 11:45:07 +0300
Subject: [PATCH 24/43] net/mlx5e: Fix selftest for small MTUs

[ Upstream commit 228c4cd04dfd0667eda182c91504b83c17d97584 ]

Loopback test had fixed packet size, which can be bigger than configured
MTU. Shorten the loopback packet size to be bigger than minimal MTU
allowed by the device. Text field removed from struct 'mlx5ehdr'
as redundant to allow send small packets as minimal allowed MTU.

Fixes: d605d66 ("net/mlx5e: Add support for ethtool self diagnostics test")
Signed-off-by: Valentine Fatiev <valentinef@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../ethernet/mellanox/mlx5/core/en_selftest.c | 26 +++++++------------
 1 file changed, 10 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
index 35ded91203f5..4382ef85488c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
@@ -98,18 +98,17 @@ static int mlx5e_test_link_speed(struct mlx5e_priv *priv)
 	return 1;
 }
 
-#ifdef CONFIG_INET
-/* loopback test */
-#define MLX5E_TEST_PKT_SIZE (MLX5E_RX_MAX_HEAD - NET_IP_ALIGN)
-static const char mlx5e_test_text[ETH_GSTRING_LEN] = "MLX5E SELF TEST";
-#define MLX5E_TEST_MAGIC 0x5AEED15C001ULL
-
 struct mlx5ehdr {
 	__be32 version;
 	__be64 magic;
-	char   text[ETH_GSTRING_LEN];
 };
 
+#ifdef CONFIG_INET
+/* loopback test */
+#define MLX5E_TEST_PKT_SIZE (sizeof(struct ethhdr) + sizeof(struct iphdr) +\
+			     sizeof(struct udphdr) + sizeof(struct mlx5ehdr))
+#define MLX5E_TEST_MAGIC 0x5AEED15C001ULL
+
 static struct sk_buff *mlx5e_test_get_udp_skb(struct mlx5e_priv *priv)
 {
 	struct sk_buff *skb = NULL;
@@ -117,10 +116,7 @@ static struct sk_buff *mlx5e_test_get_udp_skb(struct mlx5e_priv *priv)
 	struct ethhdr *ethh;
 	struct udphdr *udph;
 	struct iphdr *iph;
-	int datalen, iplen;
-
-	datalen = MLX5E_TEST_PKT_SIZE -
-		  (sizeof(*ethh) + sizeof(*iph) + sizeof(*udph));
+	int    iplen;
 
 	skb = netdev_alloc_skb(priv->netdev, MLX5E_TEST_PKT_SIZE);
 	if (!skb) {
@@ -149,7 +145,7 @@ static struct sk_buff *mlx5e_test_get_udp_skb(struct mlx5e_priv *priv)
 	/* Fill UDP header */
 	udph->source = htons(9);
 	udph->dest = htons(9); /* Discard Protocol */
-	udph->len = htons(datalen + sizeof(struct udphdr));
+	udph->len = htons(sizeof(struct mlx5ehdr) + sizeof(struct udphdr));
 	udph->check = 0;
 
 	/* Fill IP header */
@@ -157,7 +153,8 @@ static struct sk_buff *mlx5e_test_get_udp_skb(struct mlx5e_priv *priv)
 	iph->ttl = 32;
 	iph->version = 4;
 	iph->protocol = IPPROTO_UDP;
-	iplen = sizeof(struct iphdr) + sizeof(struct udphdr) + datalen;
+	iplen = sizeof(struct iphdr) + sizeof(struct udphdr) +
+		sizeof(struct mlx5ehdr);
 	iph->tot_len = htons(iplen);
 	iph->frag_off = 0;
 	iph->saddr = 0;
@@ -170,9 +167,6 @@ static struct sk_buff *mlx5e_test_get_udp_skb(struct mlx5e_priv *priv)
 	mlxh = skb_put(skb, sizeof(*mlxh));
 	mlxh->version = 0;
 	mlxh->magic = cpu_to_be64(MLX5E_TEST_MAGIC);
-	strlcpy(mlxh->text, mlx5e_test_text, sizeof(mlxh->text));
-	datalen -= sizeof(*mlxh);
-	skb_put_zero(skb, datalen);
 
 	skb->csum = 0;
 	skb->ip_summed = CHECKSUM_PARTIAL;
-- 
2.19.1


From e88c43c67f9b3c1d9f41a17893168d8ff91c3867 Mon Sep 17 00:00:00 2001
From: Shay Agroskin <shayag@mellanox.com>
Date: Sun, 28 Oct 2018 09:06:11 +0200
Subject: [PATCH 25/43] net/mlx5e: Removed unnecessary warnings in FEC caps
 query

[ Upstream commit 64e283348458e2fd2fe41b60dfb6c30e88ee695f ]

Querying interface FEC caps with 'ethtool [int]' after link reset
throws warning regading link speed.
This warning is not needed as there is already an indication in
user space that the link is not up.

Fixes: 0696d60853d5 ("net/mlx5e: Receive buffer configuration")
Signed-off-by: Shay Agroskin <shayag@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/port.c        | 4 +---
 drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c | 4 +++-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
index 24e3b564964f..12e1682f940b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
@@ -88,10 +88,8 @@ int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
 
 	eth_proto_oper = MLX5_GET(ptys_reg, out, eth_proto_oper);
 	*speed = mlx5e_port_ptys2speed(eth_proto_oper);
-	if (!(*speed)) {
-		mlx5_core_warn(mdev, "cannot get port speed\n");
+	if (!(*speed))
 		err = -EINVAL;
-	}
 
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
index c047da8752da..eac245a93f91 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
@@ -130,8 +130,10 @@ static u32 calculate_xoff(struct mlx5e_priv *priv, unsigned int mtu)
 	int err;
 
 	err = mlx5e_port_linkspeed(priv->mdev, &speed);
-	if (err)
+	if (err) {
+		mlx5_core_warn(priv->mdev, "cannot get port speed\n");
 		return 0;
+	}
 
 	xoff = (301 + 216 * priv->dcbx.cable_len / 100) * speed / 1000 + 272 * mtu / 100;
 
-- 
2.19.1


From 090db42bf1b29753f08d977d415f5cf87c067c64 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 8 Nov 2018 17:34:27 -0800
Subject: [PATCH 26/43] inet: frags: better deal with smp races
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 0d5b9311baf27bb545f187f12ecfd558220c607d ]

Multiple cpus might attempt to insert a new fragment in rhashtable,
if for example RPS is buggy, as reported by 배석진 in
https://patchwork.ozlabs.org/patch/994601/

We use rhashtable_lookup_get_insert_key() instead of
rhashtable_insert_fast() to let cpus losing the race
free their own inet_frag_queue and use the one that
was inserted by another cpu.

Fixes: 648700f76b03 ("inet: frags: use rhashtables for reassembly units")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: 배석진 <soukjin.bae@samsung.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/inet_fragment.c | 29 +++++++++++++++--------------
 1 file changed, 15 insertions(+), 14 deletions(-)

diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index bcb11f3a27c0..760a9e52e02b 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -178,21 +178,22 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
 }
 
 static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf,
-						void *arg)
+						void *arg,
+						struct inet_frag_queue **prev)
 {
 	struct inet_frags *f = nf->f;
 	struct inet_frag_queue *q;
-	int err;
 
 	q = inet_frag_alloc(nf, f, arg);
-	if (!q)
+	if (!q) {
+		*prev = ERR_PTR(-ENOMEM);
 		return NULL;
-
+	}
 	mod_timer(&q->timer, jiffies + nf->timeout);
 
-	err = rhashtable_insert_fast(&nf->rhashtable, &q->node,
-				     f->rhash_params);
-	if (err < 0) {
+	*prev = rhashtable_lookup_get_insert_key(&nf->rhashtable, &q->key,
+						 &q->node, f->rhash_params);
+	if (*prev) {
 		q->flags |= INET_FRAG_COMPLETE;
 		inet_frag_kill(q);
 		inet_frag_destroy(q);
@@ -204,22 +205,22 @@ static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf,
 /* TODO : call from rcu_read_lock() and no longer use refcount_inc_not_zero() */
 struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key)
 {
-	struct inet_frag_queue *fq;
+	struct inet_frag_queue *fq = NULL, *prev;
 
 	if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh)
 		return NULL;
 
 	rcu_read_lock();
 
-	fq = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params);
-	if (fq) {
+	prev = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params);
+	if (!prev)
+		fq = inet_frag_create(nf, key, &prev);
+	if (prev && !IS_ERR(prev)) {
+		fq = prev;
 		if (!refcount_inc_not_zero(&fq->refcnt))
 			fq = NULL;
-		rcu_read_unlock();
-		return fq;
 	}
 	rcu_read_unlock();
-
-	return inet_frag_create(nf, key);
+	return fq;
 }
 EXPORT_SYMBOL(inet_frag_find);
-- 
2.19.1


From ba1a62abc68b3488752d27ed1c2fbaeb50c6398d Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 13 Nov 2018 01:08:25 +0800
Subject: [PATCH 27/43] l2tp: fix a sock refcnt leak in l2tp_tunnel_register

[ Upstream commit f8504f4ca0a0e9f84546ef86e00b24d2ea9a0bd2 ]

This issue happens when trying to add an existent tunnel. It
doesn't call sock_put() before returning -EEXIST to release
the sock refcnt that was held by calling sock_hold() before
the existence check.

This patch is to fix it by holding the sock after doing the
existence check.

Fixes: f6cd651b056f ("l2tp: fix race in duplicate tunnel detection")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Reviewed-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 82cdf9020b53..26f1d435696a 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1490,12 +1490,7 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
 			goto err_sock;
 	}
 
-	sk = sock->sk;
-
-	sock_hold(sk);
-	tunnel->sock = sk;
 	tunnel->l2tp_net = net;
-
 	pn = l2tp_pernet(net);
 
 	spin_lock_bh(&pn->l2tp_tunnel_list_lock);
@@ -1510,6 +1505,10 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
 	list_add_rcu(&tunnel->list, &pn->l2tp_tunnel_list);
 	spin_unlock_bh(&pn->l2tp_tunnel_list_lock);
 
+	sk = sock->sk;
+	sock_hold(sk);
+	tunnel->sock = sk;
+
 	if (tunnel->encap == L2TP_ENCAPTYPE_UDP) {
 		struct udp_tunnel_sock_cfg udp_cfg = {
 			.sk_user_data = tunnel,
-- 
2.19.1


From 269c470dc7c1b287704e087834b77ea2afffa9c5 Mon Sep 17 00:00:00 2001
From: Raed Salem <raeds@mellanox.com>
Date: Thu, 18 Oct 2018 08:55:21 +0300
Subject: [PATCH 28/43] net/mlx5: IPSec, Fix the SA context hash key

[ Upstream commit f2b18732ee9863ac036759baf616ffa03c252ed5 ]

The commit "net/mlx5: Refactor accel IPSec code" introduced a
bug where asynchronous short time change in hash key value
by create/release SA context might happen during an asynchronous
hash resize operation this could cause a subsequent remove SA
context operation to fail as the key value used during resize is
not the same key value used when remove SA context operation is
invoked.

This commit fixes the bug by defining the SA context hash key
such that it includes only fields that never change during the
lifetime of the SA context object.

Fixes: d6c4f0298cec ("net/mlx5: Refactor accel IPSec code")
Signed-off-by: Raed Salem <raeds@mellanox.com>
Reviewed-by: Aviad Yehezkel <aviadye@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
index b8ee9101c506..b5a8769a5bfd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
@@ -83,8 +83,14 @@ struct mlx5_fpga_ipsec_rule {
 };
 
 static const struct rhashtable_params rhash_sa = {
-	.key_len = FIELD_SIZEOF(struct mlx5_fpga_ipsec_sa_ctx, hw_sa),
-	.key_offset = offsetof(struct mlx5_fpga_ipsec_sa_ctx, hw_sa),
+	/* Keep out "cmd" field from the key as it's
+	 * value is not constant during the lifetime
+	 * of the key object.
+	 */
+	.key_len = FIELD_SIZEOF(struct mlx5_fpga_ipsec_sa_ctx, hw_sa) -
+		   FIELD_SIZEOF(struct mlx5_ifc_fpga_ipsec_sa_v1, cmd),
+	.key_offset = offsetof(struct mlx5_fpga_ipsec_sa_ctx, hw_sa) +
+		      FIELD_SIZEOF(struct mlx5_ifc_fpga_ipsec_sa_v1, cmd),
 	.head_offset = offsetof(struct mlx5_fpga_ipsec_sa_ctx, hash),
 	.automatic_shrinking = true,
 	.min_size = 1,
-- 
2.19.1


From e6734bcaa21fea211849f414199f6712e583ead8 Mon Sep 17 00:00:00 2001
From: Denis Drozdov <denisd@mellanox.com>
Date: Thu, 27 Sep 2018 14:17:54 +0300
Subject: [PATCH 29/43] net/mlx5e: IPoIB, Reset QP after channels are closed

[ Upstream commit acf3766b36d8e59ecbc307894c6d05703ee48014 ]

The mlx5e channels should be closed before mlx5i_uninit_underlay_qp
puts the QP into RST (reset) state during mlx5i_close. Currently QP
state incorrectly set to RST before channels got deactivated and closed,
since mlx5_post_send request expects QP in RTS (Ready To Send) state.

The fix is to keep QP in RTS state until mlx5e channels get closed
and to reset QP afterwards.

Also this fix is simply correct in order to keep the open/close flow
symmetric, i.e mlx5i_init_underlay_qp() is called first thing at open,
the correct thing to do is to call mlx5i_uninit_underlay_qp() last thing
at close, which is exactly what this patch is doing.

Fixes: dae37456c8ac ("net/mlx5: Support for attaching multiple underlay QPs to root flow table")
Signed-off-by: Denis Drozdov <denisd@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index e3797a44e074..5b7fe8264144 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -502,9 +502,9 @@ static int mlx5i_close(struct net_device *netdev)
 
 	netif_carrier_off(epriv->netdev);
 	mlx5_fs_remove_rx_underlay_qpn(mdev, ipriv->qp.qpn);
-	mlx5i_uninit_underlay_qp(epriv);
 	mlx5e_deactivate_priv_channels(epriv);
 	mlx5e_close_channels(&epriv->channels);
+	mlx5i_uninit_underlay_qp(epriv);
 unlock:
 	mutex_unlock(&epriv->state_lock);
 	return 0;
-- 
2.19.1


From bff4ac3c65e8f8315fc9338f688e92401f9ae912 Mon Sep 17 00:00:00 2001
From: Jarod Wilson <jarod@redhat.com>
Date: Sun, 4 Nov 2018 14:59:46 -0500
Subject: [PATCH 30/43] bonding/802.3ad: fix link_failure_count tracking

[ Upstream commit ea53abfab960909d622ca37bcfb8e1c5378d21cc ]

Commit 4d2c0cda07448ea6980f00102dc3964eb25e241c set slave->link to
BOND_LINK_DOWN for 802.3ad bonds whenever invalid speed/duplex values
were read, to fix a problem with slaves getting into weird states, but
in the process, broke tracking of link failures, as going straight to
BOND_LINK_DOWN when a link is indeed down (cable pulled, switch rebooted)
means we broke out of bond_miimon_inspect()'s BOND_LINK_DOWN case because
!link_state was already true, we never incremented commit, and never got
a chance to call bond_miimon_commit(), where slave->link_failure_count
would be incremented. I believe the simple fix here is to mark the slave
as BOND_LINK_FAIL, and let bond_miimon_inspect() transition the link from
_FAIL to either _UP or _DOWN, and in the latter case, we now get proper
incrementing of link_failure_count again.

Fixes: 4d2c0cda0744 ("bonding: speed/duplex update at NETDEV_UP event")
CC: Mahesh Bandewar <maheshb@google.com>
CC: David S. Miller <davem@davemloft.net>
CC: netdev@vger.kernel.org
CC: stable@vger.kernel.org
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index ee28ec9e0aba..3c597569cfae 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3111,13 +3111,13 @@ static int bond_slave_netdev_event(unsigned long event,
 	case NETDEV_CHANGE:
 		/* For 802.3ad mode only:
 		 * Getting invalid Speed/Duplex values here will put slave
-		 * in weird state. So mark it as link-down for the time
+		 * in weird state. So mark it as link-fail for the time
 		 * being and let link-monitoring (miimon) set it right when
 		 * correct speeds/duplex are available.
 		 */
 		if (bond_update_speed_duplex(slave) &&
 		    BOND_MODE(bond) == BOND_MODE_8023AD)
-			slave->link = BOND_LINK_DOWN;
+			slave->link = BOND_LINK_FAIL;
 
 		if (BOND_MODE(bond) == BOND_MODE_8023AD)
 			bond_3ad_adapter_speed_duplex_changed(slave);
-- 
2.19.1


From 068463e90864132f253922230e07330a1af901f0 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sun, 11 Nov 2018 00:41:10 +0100
Subject: [PATCH 31/43] net: dsa: mv88e6xxx: Fix clearing of stats counters

[ Upstream commit a9049ff9214da68df1179a7d5e36b43479abc9b8 ]

The mv88e6161 would sometime fail to probe with a timeout waiting for
the switch to complete an operation. This operation is supposed to
clear the statistics counters. However, due to a read/modify/write,
without the needed mask, the operation actually carried out was more
random, with invalid parameters, resulting in the switch not
responding. We need to preserve the histogram mode bits, so apply a
mask to keep them.

Reported-by: Chris Healy <Chris.Healy@zii.aero>
Fixes: 40cff8fca9e3 ("net: dsa: mv88e6xxx: Fix stats histogram mode")
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/global1.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/dsa/mv88e6xxx/global1.c b/drivers/net/dsa/mv88e6xxx/global1.c
index d721ccf7d8be..38e399e0f30e 100644
--- a/drivers/net/dsa/mv88e6xxx/global1.c
+++ b/drivers/net/dsa/mv88e6xxx/global1.c
@@ -567,6 +567,8 @@ int mv88e6xxx_g1_stats_clear(struct mv88e6xxx_chip *chip)
 	if (err)
 		return err;
 
+	/* Keep the histogram mode bits */
+	val &= MV88E6XXX_G1_STATS_OP_HIST_RX_TX;
 	val |= MV88E6XXX_G1_STATS_OP_BUSY | MV88E6XXX_G1_STATS_OP_FLUSH_ALL;
 
 	err = mv88e6xxx_g1_write(chip, MV88E6XXX_G1_STATS_OP, val);
-- 
2.19.1


From 18a6c82795613d18cfbecacd2566a040f9554803 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Holger=20Hoffst=C3=A4tte?= <holger@applied-asynchrony.com>
Date: Sun, 4 Nov 2018 19:02:42 +0100
Subject: [PATCH 32/43] net: phy: realtek: fix RTL8201F sysfs name
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 0432e833191ad4d17b7fc2364941f91dad51db1a ]

Since 4.19 the following error in sysfs has appeared when using the
r8169 NIC driver:

$cd /sys/module/realtek/drivers
$ls -l
ls: cannot access 'mdio_bus:RTL8201F 10/100Mbps Ethernet': No such file or directory
[..garbled dir entries follow..]

Apparently the forward slash in "10/100Mbps Ethernet" is interpreted
as directory separator that leads nowhere, and was introduced in commit
513588dd44b ("net: phy: realtek: add RTL8201F phy-id and functions").

Fix this by removing the offending slash in the driver name.

Other drivers in net/phy seem to have the same problem, but I cannot
test/verify them.

Fixes: 513588dd44b ("net: phy: realtek: add RTL8201F phy-id and functions")
Signed-off-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/realtek.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c
index 7fc8508b5231..271e8adc39f1 100644
--- a/drivers/net/phy/realtek.c
+++ b/drivers/net/phy/realtek.c
@@ -220,7 +220,7 @@ static struct phy_driver realtek_drvs[] = {
 		.flags          = PHY_HAS_INTERRUPT,
 	}, {
 		.phy_id		= 0x001cc816,
-		.name		= "RTL8201F 10/100Mbps Ethernet",
+		.name		= "RTL8201F Fast Ethernet",
 		.phy_id_mask	= 0x001fffff,
 		.features	= PHY_BASIC_FEATURES,
 		.flags		= PHY_HAS_INTERRUPT,
-- 
2.19.1


From c9611174f3214179d23fdf950da24f7f8b1def0c Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sat, 3 Nov 2018 14:01:31 +0800
Subject: [PATCH 33/43] sctp: define SCTP_SS_DEFAULT for Stream schedulers

[ Upstream commit 12480e3b16982c4026de10dd8155823219cd6391 ]

According to rfc8260#section-4.3.2, SCTP_SS_DEFAULT is required to
defined as SCTP_SS_FCFS or SCTP_SS_RR.

SCTP_SS_FCFS is used for SCTP_SS_DEFAULT's value in this patch.

Fixes: 5bbbbe32a431 ("sctp: introduce stream scheduler foundations")
Reported-by: Jianwen Ji <jiji@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/sctp.h | 1 +
 net/sctp/outqueue.c       | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h
index 34dd3d497f2c..9c2780a65fb4 100644
--- a/include/uapi/linux/sctp.h
+++ b/include/uapi/linux/sctp.h
@@ -1151,6 +1151,7 @@ struct sctp_add_streams {
 /* SCTP Stream schedulers */
 enum sctp_sched_type {
 	SCTP_SS_FCFS,
+	SCTP_SS_DEFAULT = SCTP_SS_FCFS,
 	SCTP_SS_PRIO,
 	SCTP_SS_RR,
 	SCTP_SS_MAX = SCTP_SS_RR
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index 42191ed9902b..7bb8e5603298 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -212,7 +212,7 @@ void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q)
 	INIT_LIST_HEAD(&q->retransmit);
 	INIT_LIST_HEAD(&q->sacked);
 	INIT_LIST_HEAD(&q->abandoned);
-	sctp_sched_set_sched(asoc, SCTP_SS_FCFS);
+	sctp_sched_set_sched(asoc, SCTP_SS_DEFAULT);
 }
 
 /* Free the outqueue structure and any related pending chunks.
-- 
2.19.1


From 06e0991f496519d27890b82e0e3905d8295e9939 Mon Sep 17 00:00:00 2001
From: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Date: Fri, 9 Nov 2018 18:56:27 -0700
Subject: [PATCH 34/43] net: qualcomm: rmnet: Fix incorrect assignment of
 real_dev

[ Upstream commit d02854dc1999ed3e7fd79ec700c64ac23ac0c458 ]

A null dereference was observed when a sysctl was being set
from userspace and rmnet was stuck trying to complete some actions
in the NETDEV_REGISTER callback. This is because the real_dev is set
only after the device registration handler completes.

sysctl call stack -

<6> Unable to handle kernel NULL pointer dereference at
    virtual address 00000108
<2> pc : rmnet_vnd_get_iflink+0x1c/0x28
<2> lr : dev_get_iflink+0x2c/0x40
<2>  rmnet_vnd_get_iflink+0x1c/0x28
<2>  inet6_fill_ifinfo+0x15c/0x234
<2>  inet6_ifinfo_notify+0x68/0xd4
<2>  ndisc_ifinfo_sysctl_change+0x1b8/0x234
<2>  proc_sys_call_handler+0xac/0x100
<2>  proc_sys_write+0x3c/0x4c
<2>  __vfs_write+0x54/0x14c
<2>  vfs_write+0xcc/0x188
<2>  SyS_write+0x60/0xc0
<2>  el0_svc_naked+0x34/0x38

device register call stack -

<2>  notifier_call_chain+0x84/0xbc
<2>  raw_notifier_call_chain+0x38/0x48
<2>  call_netdevice_notifiers_info+0x40/0x70
<2>  call_netdevice_notifiers+0x38/0x60
<2>  register_netdevice+0x29c/0x3d8
<2>  rmnet_vnd_newlink+0x68/0xe8
<2>  rmnet_newlink+0xa0/0x160
<2>  rtnl_newlink+0x57c/0x6c8
<2>  rtnetlink_rcv_msg+0x1dc/0x328
<2>  netlink_rcv_skb+0xac/0x118
<2>  rtnetlink_rcv+0x24/0x30
<2>  netlink_unicast+0x158/0x1f0
<2>  netlink_sendmsg+0x32c/0x338
<2>  sock_sendmsg+0x44/0x60
<2>  SyS_sendto+0x150/0x1ac
<2>  el0_svc_naked+0x34/0x38

Fixes: b752eff5be24 ("net: qualcomm: rmnet: Implement ndo_get_iflink")
Signed-off-by: Sean Tranchetti <stranche@codeaurora.org>
Signed-off-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
index 0afc3d335d56..d11c16aeb19a 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
@@ -234,7 +234,7 @@ int rmnet_vnd_newlink(u8 id, struct net_device *rmnet_dev,
 		      struct net_device *real_dev,
 		      struct rmnet_endpoint *ep)
 {
-	struct rmnet_priv *priv;
+	struct rmnet_priv *priv = netdev_priv(rmnet_dev);
 	int rc;
 
 	if (ep->egress_dev)
@@ -247,6 +247,8 @@ int rmnet_vnd_newlink(u8 id, struct net_device *rmnet_dev,
 	rmnet_dev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
 	rmnet_dev->hw_features |= NETIF_F_SG;
 
+	priv->real_dev = real_dev;
+
 	rc = register_netdevice(rmnet_dev);
 	if (!rc) {
 		ep->egress_dev = rmnet_dev;
@@ -255,9 +257,7 @@ int rmnet_vnd_newlink(u8 id, struct net_device *rmnet_dev,
 
 		rmnet_dev->rtnl_link_ops = &rmnet_link_ops;
 
-		priv = netdev_priv(rmnet_dev);
 		priv->mux_id = id;
-		priv->real_dev = real_dev;
 
 		netdev_dbg(rmnet_dev, "rmnet dev created\n");
 	}
-- 
2.19.1


From dac0fbc40327c67833fdb167a25a0537b7062ef5 Mon Sep 17 00:00:00 2001
From: Tristram Ha <Tristram.Ha@microchip.com>
Date: Fri, 2 Nov 2018 19:23:41 -0700
Subject: [PATCH 35/43] net: dsa: microchip: initialize mutex before use

[ Upstream commit 284fb78ed7572117846f8e1d1d8e3dbfd16880c2 ]

Initialize mutex before use.  Avoid kernel complaint when
CONFIG_DEBUG_LOCK_ALLOC is enabled.

Fixes: b987e98e50ab90e5 ("dsa: add DSA switch driver for Microchip KSZ9477")
Signed-off-by: Tristram Ha <Tristram.Ha@microchip.com>
Reviewed-by: Pavel Machek <pavel@ucw.cz>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/microchip/ksz_common.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index 54e0ca6ed730..86b6464b4525 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -1117,11 +1117,6 @@ static int ksz_switch_init(struct ksz_device *dev)
 {
 	int i;
 
-	mutex_init(&dev->reg_mutex);
-	mutex_init(&dev->stats_mutex);
-	mutex_init(&dev->alu_mutex);
-	mutex_init(&dev->vlan_mutex);
-
 	dev->ds->ops = &ksz_switch_ops;
 
 	for (i = 0; i < ARRAY_SIZE(ksz_switch_chips); i++) {
@@ -1206,6 +1201,11 @@ int ksz_switch_register(struct ksz_device *dev)
 	if (dev->pdata)
 		dev->chip_id = dev->pdata->chip_id;
 
+	mutex_init(&dev->reg_mutex);
+	mutex_init(&dev->stats_mutex);
+	mutex_init(&dev->alu_mutex);
+	mutex_init(&dev->vlan_mutex);
+
 	if (ksz_switch_detect(dev))
 		return -EINVAL;
 
-- 
2.19.1


From 881cfb76e0f544df1615242bcb84a4b9f7651d29 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sat, 3 Nov 2018 13:59:45 +0800
Subject: [PATCH 36/43] sctp: fix strchange_flags name for Stream Change Event

[ Upstream commit fd82d61ba142f0b83463e47064bf5460aac57b6e ]

As defined in rfc6525#section-6.1.3, SCTP_STREAM_CHANGE_DENIED
and SCTP_STREAM_CHANGE_FAILED should be used instead of
SCTP_ASSOC_CHANGE_DENIED and SCTP_ASSOC_CHANGE_FAILED.

To keep the compatibility, fix it by adding two macros.

Fixes: b444153fb5a6 ("sctp: add support for generating add stream change event notification")
Reported-by: Jianwen Ji <jiji@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/sctp.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h
index 9c2780a65fb4..c81feb373d3e 100644
--- a/include/uapi/linux/sctp.h
+++ b/include/uapi/linux/sctp.h
@@ -568,6 +568,8 @@ struct sctp_assoc_reset_event {
 
 #define SCTP_ASSOC_CHANGE_DENIED	0x0004
 #define SCTP_ASSOC_CHANGE_FAILED	0x0008
+#define SCTP_STREAM_CHANGE_DENIED	SCTP_ASSOC_CHANGE_DENIED
+#define SCTP_STREAM_CHANGE_FAILED	SCTP_ASSOC_CHANGE_FAILED
 struct sctp_stream_change_event {
 	__u16 strchange_type;
 	__u16 strchange_flags;
-- 
2.19.1


From 3ce32a0e7146f1f4827963f63387490664007cd9 Mon Sep 17 00:00:00 2001
From: Martin Schiller <ms@dev.tdt.de>
Date: Fri, 16 Nov 2018 08:38:36 +0100
Subject: [PATCH 37/43] net: phy: mdio-gpio: Fix working over slow can_sleep
 GPIOs

[ Upstream commit df5a8ec64eed7fe45b556cfff503acd6429ab817 ]

Up until commit 7e5fbd1e0700 ("net: mdio-gpio: Convert to use gpiod
functions where possible"), the _cansleep variants of the gpio_ API was
used. After that commit and the change to gpiod_ API, the _cansleep()
was dropped. This then results in WARN_ON() when used with GPIO
devices which do sleep. Add back the _cansleep() to avoid this.

Fixes: 7e5fbd1e0700 ("net: mdio-gpio: Convert to use gpiod functions where possible")
Signed-off-by: Martin Schiller <ms@dev.tdt.de>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mdio-gpio.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/phy/mdio-gpio.c b/drivers/net/phy/mdio-gpio.c
index 33265747bf39..0fbcedcdf6e2 100644
--- a/drivers/net/phy/mdio-gpio.c
+++ b/drivers/net/phy/mdio-gpio.c
@@ -63,7 +63,7 @@ static void mdio_dir(struct mdiobb_ctrl *ctrl, int dir)
 		 * assume the pin serves as pull-up. If direction is
 		 * output, the default value is high.
 		 */
-		gpiod_set_value(bitbang->mdo, 1);
+		gpiod_set_value_cansleep(bitbang->mdo, 1);
 		return;
 	}
 
@@ -78,7 +78,7 @@ static int mdio_get(struct mdiobb_ctrl *ctrl)
 	struct mdio_gpio_info *bitbang =
 		container_of(ctrl, struct mdio_gpio_info, ctrl);
 
-	return gpiod_get_value(bitbang->mdio);
+	return gpiod_get_value_cansleep(bitbang->mdio);
 }
 
 static void mdio_set(struct mdiobb_ctrl *ctrl, int what)
@@ -87,9 +87,9 @@ static void mdio_set(struct mdiobb_ctrl *ctrl, int what)
 		container_of(ctrl, struct mdio_gpio_info, ctrl);
 
 	if (bitbang->mdo)
-		gpiod_set_value(bitbang->mdo, what);
+		gpiod_set_value_cansleep(bitbang->mdo, what);
 	else
-		gpiod_set_value(bitbang->mdio, what);
+		gpiod_set_value_cansleep(bitbang->mdio, what);
 }
 
 static void mdc_set(struct mdiobb_ctrl *ctrl, int what)
@@ -97,7 +97,7 @@ static void mdc_set(struct mdiobb_ctrl *ctrl, int what)
 	struct mdio_gpio_info *bitbang =
 		container_of(ctrl, struct mdio_gpio_info, ctrl);
 
-	gpiod_set_value(bitbang->mdc, what);
+	gpiod_set_value_cansleep(bitbang->mdc, what);
 }
 
 static const struct mdiobb_ops mdio_gpio_ops = {
-- 
2.19.1


From 1192a754e847ece9fc481349e3aafa65e400cb52 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 18 Nov 2018 21:59:49 +0800
Subject: [PATCH 39/43] sctp: not increase stream's incnt before sending
 addstrm_in request

[ Upstream commit e1e46479847e66f78f79d8c24d5169a5954b3fc2 ]

Different from processing the addstrm_out request, The receiver handles
an addstrm_in request by sending back an addstrm_out request to the
sender who will increase its stream's in and incnt later.

Now stream->incnt has been increased since it sent out the addstrm_in
request in sctp_send_add_streams(), with the wrong stream->incnt will
even cause crash when copying stream info from the old stream's in to
the new one's in sctp_process_strreset_addstrm_out().

This patch is to fix it by simply removing the stream->incnt change
from sctp_send_add_streams().

Fixes: 242bd2d519d7 ("sctp: implement sender-side procedures for Add Incoming/Outgoing Streams Request Parameter")
Reported-by: Jianwen Ji <jiji@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/stream.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index ffb940d3b57c..3892e7630f3a 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -535,7 +535,6 @@ int sctp_send_add_streams(struct sctp_association *asoc,
 		goto out;
 	}
 
-	stream->incnt = incnt;
 	stream->outcnt = outcnt;
 
 	asoc->strreset_outstanding = !!out + !!in;
-- 
2.19.1


From e89a1060b7932c2acd2d1ba03f31f93179b6fe5c Mon Sep 17 00:00:00 2001
From: Shalom Toledo <shalomt@mellanox.com>
Date: Fri, 2 Nov 2018 19:49:15 +0000
Subject: [PATCH 40/43] mlxsw: spectrum: Fix IP2ME CPU policer configuration

[ Upstream commit 96801552f846460fe9ac10f1b189602992f004e1 ]

The CPU policer used to police packets being trapped via a local route
(IP2ME) was incorrectly configured to police based on bytes per second
instead of packets per second.

Change the policer to police based on packets per second and avoid
packet loss under certain circumstances.

Fixes: 9148e7cf73ce ("mlxsw: spectrum: Add policers for trap groups")
Signed-off-by: Shalom Toledo <shalomt@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 30bb2c533cec..ada644d90029 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -3519,7 +3519,6 @@ static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core)
 			burst_size = 7;
 			break;
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IP2ME:
-			is_bytes = true;
 			rate = 4 * 1024;
 			burst_size = 4;
 			break;
-- 
2.19.1


From a172b7f1b341916022c4f2631b9259ddd8b5ef16 Mon Sep 17 00:00:00 2001
From: Stefan Wahren <stefan.wahren@i2se.com>
Date: Thu, 8 Nov 2018 20:38:26 +0100
Subject: [PATCH 41/43] net: smsc95xx: Fix MTU range

[ Upstream commit 85b18b0237ce9986a81a1b9534b5e2ee116f5504 ]

The commit f77f0aee4da4 ("net: use core MTU range checking in USB NIC
drivers") introduce a common MTU handling for usbnet. But it's missing
the necessary changes for smsc95xx. So set the MTU range accordingly.

This patch has been tested on a Raspberry Pi 3.

Fixes: f77f0aee4da4 ("net: use core MTU range checking in USB NIC drivers")
Signed-off-by: Stefan Wahren <stefan.wahren@i2se.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/smsc95xx.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index 262e7a3c23cb..5974478b5be4 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -1321,6 +1321,8 @@ static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf)
 	dev->net->ethtool_ops = &smsc95xx_ethtool_ops;
 	dev->net->flags |= IFF_MULTICAST;
 	dev->net->hard_header_len += SMSC95XX_TX_OVERHEAD_CSUM;
+	dev->net->min_mtu = ETH_MIN_MTU;
+	dev->net->max_mtu = ETH_DATA_LEN;
 	dev->hard_mtu = dev->net->mtu + dev->net->hard_header_len;
 
 	pdata->dev = dev;
-- 
2.19.1


From fa1408118b54c14cda20024cec9c2e577c4322c2 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 1 Nov 2018 13:39:53 +0000
Subject: [PATCH 42/43] rxrpc: Fix lockup due to no error backoff after ack
 transmit error

[ Upstream commit c7e86acfcee30794dc99a0759924bf7b9d43f1ca ]

If the network becomes (partially) unavailable, say by disabling IPv6, the
background ACK transmission routine can get itself into a tizzy by
proposing immediate ACK retransmission.  Since we're in the call event
processor, that happens immediately without returning to the workqueue
manager.

The condition should clear after a while when either the network comes back
or the call times out.

Fix this by:

 (1) When re-proposing an ACK on failed Tx, don't schedule it immediately.
     This will allow a certain amount of time to elapse before we try
     again.

 (2) Enforce a return to the workqueue manager after a certain number of
     iterations of the call processing loop.

 (3) Add a backoff delay that increases the delay on deferred ACKs by a
     jiffy per failed transmission to a limit of HZ.  The backoff delay is
     cleared on a successful return from kernel_sendmsg().

 (4) Cancel calls immediately if the opening sendmsg fails.  The layer
     above can arrange retransmission or rotate to another server.

Fixes: 248f219cb8bc ("rxrpc: Rewrite the data and ack handling code")
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/ar-internal.h |  1 +
 net/rxrpc/call_event.c  | 18 ++++++++++++++----
 net/rxrpc/output.c      | 35 +++++++++++++++++++++++++++++++----
 3 files changed, 46 insertions(+), 8 deletions(-)

diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index a6e6cae82c30..03e0fc8c183f 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -611,6 +611,7 @@ struct rxrpc_call {
 						 * not hard-ACK'd packet follows this.
 						 */
 	rxrpc_seq_t		tx_top;		/* Highest Tx slot allocated. */
+	u16			tx_backoff;	/* Delay to insert due to Tx failure */
 
 	/* TCP-style slow-start congestion control [RFC5681].  Since the SMSS
 	 * is fixed, we keep these numbers in terms of segments (ie. DATA
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index 8e7434e92097..468efc3660c0 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -123,6 +123,7 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason,
 		else
 			ack_at = expiry;
 
+		ack_at += READ_ONCE(call->tx_backoff);
 		ack_at += now;
 		if (time_before(ack_at, call->ack_at)) {
 			WRITE_ONCE(call->ack_at, ack_at);
@@ -311,6 +312,7 @@ void rxrpc_process_call(struct work_struct *work)
 		container_of(work, struct rxrpc_call, processor);
 	rxrpc_serial_t *send_ack;
 	unsigned long now, next, t;
+	unsigned int iterations = 0;
 
 	rxrpc_see_call(call);
 
@@ -319,6 +321,11 @@ void rxrpc_process_call(struct work_struct *work)
 	       call->debug_id, rxrpc_call_states[call->state], call->events);
 
 recheck_state:
+	/* Limit the number of times we do this before returning to the manager */
+	iterations++;
+	if (iterations > 5)
+		goto requeue;
+
 	if (test_and_clear_bit(RXRPC_CALL_EV_ABORT, &call->events)) {
 		rxrpc_send_abort_packet(call);
 		goto recheck_state;
@@ -447,13 +454,16 @@ void rxrpc_process_call(struct work_struct *work)
 	rxrpc_reduce_call_timer(call, next, now, rxrpc_timer_restart);
 
 	/* other events may have been raised since we started checking */
-	if (call->events && call->state < RXRPC_CALL_COMPLETE) {
-		__rxrpc_queue_call(call);
-		goto out;
-	}
+	if (call->events && call->state < RXRPC_CALL_COMPLETE)
+		goto requeue;
 
 out_put:
 	rxrpc_put_call(call, rxrpc_call_put);
 out:
 	_leave("");
+	return;
+
+requeue:
+	__rxrpc_queue_call(call);
+	goto out;
 }
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index a141ee3ab812..345dc1c5fe72 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -34,6 +34,21 @@ struct rxrpc_abort_buffer {
 
 static const char rxrpc_keepalive_string[] = "";
 
+/*
+ * Increase Tx backoff on transmission failure and clear it on success.
+ */
+static void rxrpc_tx_backoff(struct rxrpc_call *call, int ret)
+{
+	if (ret < 0) {
+		u16 tx_backoff = READ_ONCE(call->tx_backoff);
+
+		if (tx_backoff < HZ)
+			WRITE_ONCE(call->tx_backoff, tx_backoff + 1);
+	} else {
+		WRITE_ONCE(call->tx_backoff, 0);
+	}
+}
+
 /*
  * Arrange for a keepalive ping a certain time after we last transmitted.  This
  * lets the far side know we're still interested in this call and helps keep
@@ -210,6 +225,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
 	else
 		trace_rxrpc_tx_packet(call->debug_id, &pkt->whdr,
 				      rxrpc_tx_point_call_ack);
+	rxrpc_tx_backoff(call, ret);
 
 	if (call->state < RXRPC_CALL_COMPLETE) {
 		if (ret < 0) {
@@ -218,7 +234,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
 			rxrpc_propose_ACK(call, pkt->ack.reason,
 					  ntohs(pkt->ack.maxSkew),
 					  ntohl(pkt->ack.serial),
-					  true, true,
+					  false, true,
 					  rxrpc_propose_ack_retry_tx);
 		} else {
 			spin_lock_bh(&call->lock);
@@ -300,7 +316,7 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call)
 	else
 		trace_rxrpc_tx_packet(call->debug_id, &pkt.whdr,
 				      rxrpc_tx_point_call_abort);
-
+	rxrpc_tx_backoff(call, ret);
 
 	rxrpc_put_connection(conn);
 	return ret;
@@ -411,6 +427,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
 	else
 		trace_rxrpc_tx_packet(call->debug_id, &whdr,
 				      rxrpc_tx_point_call_data_nofrag);
+	rxrpc_tx_backoff(call, ret);
 	if (ret == -EMSGSIZE)
 		goto send_fragmentable;
 
@@ -445,9 +462,18 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
 			rxrpc_reduce_call_timer(call, expect_rx_by, nowj,
 						rxrpc_timer_set_for_normal);
 		}
-	}
 
-	rxrpc_set_keepalive(call);
+		rxrpc_set_keepalive(call);
+	} else {
+		/* Cancel the call if the initial transmission fails,
+		 * particularly if that's due to network routing issues that
+		 * aren't going away anytime soon.  The layer above can arrange
+		 * the retransmission.
+		 */
+		if (!test_and_set_bit(RXRPC_CALL_BEGAN_RX_TIMER, &call->flags))
+			rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR,
+						  RX_USER_ABORT, ret);
+	}
 
 	_leave(" = %d [%u]", ret, call->peer->maxdata);
 	return ret;
@@ -506,6 +532,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
 	else
 		trace_rxrpc_tx_packet(call->debug_id, &whdr,
 				      rxrpc_tx_point_call_data_frag);
+	rxrpc_tx_backoff(call, ret);
 
 	up_write(&conn->params.local->defrag_sem);
 	goto done;
-- 
2.19.1


From 6550de32d2062cd6cdc6be49c8c8220564120a38 Mon Sep 17 00:00:00 2001
From: Frieder Schrempf <frieder.schrempf@kontron.de>
Date: Wed, 31 Oct 2018 22:52:19 +0100
Subject: [PATCH 43/43] usbnet: smsc95xx: disable carrier check while
 suspending

[ Upstream commit 7b900ead6cc66b2ee873cb042dfba169aa68b56c ]

We need to make sure, that the carrier check polling is disabled
while suspending. Otherwise we can end up with usbnet_read_cmd()
being issued when only usbnet_read_cmd_nopm() is allowed. If this
happens, read operations lock up.

Fixes: d69d169493 ("usbnet: smsc95xx: fix link detection for disabled autonegotiation")
Signed-off-by: Frieder Schrempf <frieder.schrempf@kontron.de>
Reviewed-by: Raghuram Chary J <RaghuramChary.Jallipalli@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/smsc95xx.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index 5974478b5be4..f2d01cb6f958 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -1600,6 +1600,8 @@ static int smsc95xx_suspend(struct usb_interface *intf, pm_message_t message)
 		return ret;
 	}
 
+	cancel_delayed_work_sync(&pdata->carrier_check);
+
 	if (pdata->suspend_flags) {
 		netdev_warn(dev->net, "error during last resume\n");
 		pdata->suspend_flags = 0;
@@ -1842,6 +1844,11 @@ static int smsc95xx_suspend(struct usb_interface *intf, pm_message_t message)
 	 */
 	if (ret && PMSG_IS_AUTO(message))
 		usbnet_resume(intf);
+
+	if (ret)
+		schedule_delayed_work(&pdata->carrier_check,
+				      CARRIER_CHECK_DELAY);
+
 	return ret;
 }
 
-- 
2.19.1

Re: [PATCHES] Networking

[Greg KH]

On Tue, Nov 20, 2018 at 07:49:49PM -0800, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.18 and
> v4.19 -stable, respectively.

Thanks for the patches, now queued up.

Note, 4.18 is now end-of-life, so no need to be making patches for that
anymore.

thanks,

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 104 bytes --]


Please queue up the following networking bug fixes for v4.14 and
v4.19 -stable, respectively.

Thanks!

[-- Attachment #2: net_414.mbox --]
[-- Type: Application/Octet-Stream, Size: 30794 bytes --]

From 55c91df0b4ded43daeb6650df6607320579dbea6 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Tue, 20 Nov 2018 11:39:56 +0000
Subject: [PATCH 1/9] net: skb_scrub_packet(): Scrub offload_fwd_mark

[ Upstream commit b5dd186d10ba59e6b5ba60e42b3b083df56df6f3 ]

When a packet is trapped and the corresponding SKB marked as
already-forwarded, it retains this marking even after it is forwarded
across veth links into another bridge. There, since it ingresses the
bridge over veth, which doesn't have offload_fwd_mark, it triggers a
warning in nbp_switchdev_frame_mark().

Then nbp_switchdev_allowed_egress() decides not to allow egress from
this bridge through another veth, because the SKB is already marked, and
the mark (of 0) of course matches. Thus the packet is incorrectly
blocked.

Solve by resetting offload_fwd_mark() in skb_scrub_packet(). That
function is called from tunnels and also from veth, and thus catches the
cases where traffic is forwarded between bridges and transformed in a
way that invalidates the marking.

Fixes: 6bc506b4fb06 ("bridge: switchdev: Add forward mark support for stacked devices")
Fixes: abf4bb6b63d0 ("skbuff: Add the offload_mr_fwd_mark field")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Suggested-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index c19a118f9f82..4067fa3fcbb2 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4882,6 +4882,10 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet)
 	nf_reset(skb);
 	nf_reset_trace(skb);
 
+#ifdef CONFIG_NET_SWITCHDEV
+	skb->offload_fwd_mark = 0;
+#endif
+
 	if (!xnet)
 		return;
 
-- 
2.19.2


From 5b84bfd7e2ae01892282b42edeaf3bf42d16a833 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Wed, 21 Nov 2018 16:32:10 +0100
Subject: [PATCH 2/9] net: thunderx: set xdp_prog to NULL if bpf_prog_add fails

[ Upstream commit 6d0f60b0f8588fd4380ea5df9601e12fddd55ce2 ]

Set xdp_prog pointer to NULL if bpf_prog_add fails since that routine
reports the error code instead of NULL in case of failure and xdp_prog
pointer value is used in the driver to verify if XDP is currently
enabled.
Moreover report the error code to userspace if nicvf_xdp_setup fails

Fixes: 05c773f52b96 ("net: thunderx: Add basic XDP support")
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/thunder/nicvf_main.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 2237ef8e4344..f13256af8031 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -1691,6 +1691,7 @@ static int nicvf_xdp_setup(struct nicvf *nic, struct bpf_prog *prog)
 	bool if_up = netif_running(nic->netdev);
 	struct bpf_prog *old_prog;
 	bool bpf_attached = false;
+	int ret = 0;
 
 	/* For now just support only the usual MTU sized frames */
 	if (prog && (dev->mtu > 1500)) {
@@ -1724,8 +1725,12 @@ static int nicvf_xdp_setup(struct nicvf *nic, struct bpf_prog *prog)
 	if (nic->xdp_prog) {
 		/* Attach BPF program */
 		nic->xdp_prog = bpf_prog_add(nic->xdp_prog, nic->rx_queues - 1);
-		if (!IS_ERR(nic->xdp_prog))
+		if (!IS_ERR(nic->xdp_prog)) {
 			bpf_attached = true;
+		} else {
+			ret = PTR_ERR(nic->xdp_prog);
+			nic->xdp_prog = NULL;
+		}
 	}
 
 	/* Calculate Tx queues needed for XDP and network stack */
@@ -1737,7 +1742,7 @@ static int nicvf_xdp_setup(struct nicvf *nic, struct bpf_prog *prog)
 		netif_trans_update(nic->netdev);
 	}
 
-	return 0;
+	return ret;
 }
 
 static int nicvf_xdp(struct net_device *netdev, struct netdev_xdp *xdp)
-- 
2.19.2


From e008e72cb45fcd4494afa2e03a3b182165104975 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Thu, 22 Nov 2018 14:36:30 +0800
Subject: [PATCH 3/9] virtio-net: disable guest csum during XDP set

[ Upstream commit e59ff2c49ae16e1d179de679aca81405829aee6c ]

We don't disable VIRTIO_NET_F_GUEST_CSUM if XDP was set. This means we
can receive partial csumed packets with metadata kept in the
vnet_hdr. This may have several side effects:

- It could be overridden by header adjustment, thus is might be not
  correct after XDP processing.
- There's no way to pass such metadata information through
  XDP_REDIRECT to another driver.
- XDP does not support checksum offload right now.

So simply disable guest csum if possible in this the case of XDP.

Fixes: 3f93522ffab2d ("virtio-net: switch off offloads on demand if possible on XDP set")
Reported-by: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Pavel Popa <pashinho1990@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index f528e9ac3413..2ffa7b290591 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -61,7 +61,8 @@ static const unsigned long guest_offloads[] = {
 	VIRTIO_NET_F_GUEST_TSO4,
 	VIRTIO_NET_F_GUEST_TSO6,
 	VIRTIO_NET_F_GUEST_ECN,
-	VIRTIO_NET_F_GUEST_UFO
+	VIRTIO_NET_F_GUEST_UFO,
+	VIRTIO_NET_F_GUEST_CSUM
 };
 
 struct virtnet_stats {
@@ -1939,9 +1940,6 @@ static int virtnet_clear_guest_offloads(struct virtnet_info *vi)
 	if (!vi->guest_offloads)
 		return 0;
 
-	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_CSUM))
-		offloads = 1ULL << VIRTIO_NET_F_GUEST_CSUM;
-
 	return virtnet_set_guest_offloads(vi, offloads);
 }
 
@@ -1951,8 +1949,6 @@ static int virtnet_restore_guest_offloads(struct virtnet_info *vi)
 
 	if (!vi->guest_offloads)
 		return 0;
-	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_CSUM))
-		offloads |= 1ULL << VIRTIO_NET_F_GUEST_CSUM;
 
 	return virtnet_set_guest_offloads(vi, offloads);
 }
-- 
2.19.2


From 337ce61bdf5a2193d6d7089b8ec12735b3d17e28 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Thu, 22 Nov 2018 14:36:31 +0800
Subject: [PATCH 4/9] virtio-net: fail XDP set if guest csum is negotiated

[ Upstream commit 18ba58e1c234ea1a2d9835ac8c1735d965ce4640 ]

We don't support partial csumed packet since its metadata will be lost
or incorrect during XDP processing. So fail the XDP set if guest_csum
feature is negotiated.

Fixes: f600b6905015 ("virtio_net: Add XDP support")
Reported-by: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Pavel Popa <pashinho1990@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 2ffa7b290591..0e8e3be50332 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1966,8 +1966,9 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 	    && (virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO4) ||
 	        virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO6) ||
 	        virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_ECN) ||
-		virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_UFO))) {
-		NL_SET_ERR_MSG_MOD(extack, "Can't set XDP while host is implementing LRO, disable LRO first");
+		virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_UFO) ||
+		virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_CSUM))) {
+		NL_SET_ERR_MSG_MOD(extack, "Can't set XDP while host is implementing LRO/CSUM, disable LRO/CSUM first");
 		return -EOPNOTSUPP;
 	}
 
-- 
2.19.2


From 1c63769083c7b823ba7931ace035f17fac186cc2 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Fri, 23 Nov 2018 18:28:01 +0100
Subject: [PATCH 5/9] net: thunderx: set tso_hdrs pointer to NULL in
 nicvf_free_snd_queue

[ Upstream commit ef2a7cf1d8831535b8991459567b385661eb4a36 ]

Reset snd_queue tso_hdrs pointer to NULL in nicvf_free_snd_queue routine
since it is used to check if tso dma descriptor queue has been previously
allocated. The issue can be triggered with the following reproducer:

$ip link set dev enP2p1s0v0 xdpdrv obj xdp_dummy.o
$ip link set dev enP2p1s0v0 xdpdrv off

[  341.467649] WARNING: CPU: 74 PID: 2158 at mm/vmalloc.c:1511 __vunmap+0x98/0xe0
[  341.515010] Hardware name: GIGABYTE H270-T70/MT70-HD0, BIOS T49 02/02/2018
[  341.521874] pstate: 60400005 (nZCv daif +PAN -UAO)
[  341.526654] pc : __vunmap+0x98/0xe0
[  341.530132] lr : __vunmap+0x98/0xe0
[  341.533609] sp : ffff00001c5db860
[  341.536913] x29: ffff00001c5db860 x28: 0000000000020000
[  341.542214] x27: ffff810feb5090b0 x26: ffff000017e57000
[  341.547515] x25: 0000000000000000 x24: 00000000fbd00000
[  341.552816] x23: 0000000000000000 x22: ffff810feb5090b0
[  341.558117] x21: 0000000000000000 x20: 0000000000000000
[  341.563418] x19: ffff000017e57000 x18: 0000000000000000
[  341.568719] x17: 0000000000000000 x16: 0000000000000000
[  341.574020] x15: 0000000000000010 x14: ffffffffffffffff
[  341.579321] x13: ffff00008985eb27 x12: ffff00000985eb2f
[  341.584622] x11: ffff0000096b3000 x10: ffff00001c5db510
[  341.589923] x9 : 00000000ffffffd0 x8 : ffff0000086868e8
[  341.595224] x7 : 3430303030303030 x6 : 00000000000006ef
[  341.600525] x5 : 00000000003fffff x4 : 0000000000000000
[  341.605825] x3 : 0000000000000000 x2 : ffffffffffffffff
[  341.611126] x1 : ffff0000096b3728 x0 : 0000000000000038
[  341.616428] Call trace:
[  341.618866]  __vunmap+0x98/0xe0
[  341.621997]  vunmap+0x3c/0x50
[  341.624961]  arch_dma_free+0x68/0xa0
[  341.628534]  dma_direct_free+0x50/0x80
[  341.632285]  nicvf_free_resources+0x160/0x2d8 [nicvf]
[  341.637327]  nicvf_config_data_transfer+0x174/0x5e8 [nicvf]
[  341.642890]  nicvf_stop+0x298/0x340 [nicvf]
[  341.647066]  __dev_close_many+0x9c/0x108
[  341.650977]  dev_close_many+0xa4/0x158
[  341.654720]  rollback_registered_many+0x140/0x530
[  341.659414]  rollback_registered+0x54/0x80
[  341.663499]  unregister_netdevice_queue+0x9c/0xe8
[  341.668192]  unregister_netdev+0x28/0x38
[  341.672106]  nicvf_remove+0xa4/0xa8 [nicvf]
[  341.676280]  nicvf_shutdown+0x20/0x30 [nicvf]
[  341.680630]  pci_device_shutdown+0x44/0x88
[  341.684720]  device_shutdown+0x144/0x250
[  341.688640]  kernel_restart_prepare+0x44/0x50
[  341.692986]  kernel_restart+0x20/0x68
[  341.696638]  __se_sys_reboot+0x210/0x238
[  341.700550]  __arm64_sys_reboot+0x24/0x30
[  341.704555]  el0_svc_handler+0x94/0x110
[  341.708382]  el0_svc+0x8/0xc
[  341.711252] ---[ end trace 3f4019c8439959c9 ]---
[  341.715874] page:ffff7e0003ef4000 count:0 mapcount:0 mapping:0000000000000000 index:0x4
[  341.723872] flags: 0x1fffe000000000()
[  341.727527] raw: 001fffe000000000 ffff7e0003f1a008 ffff7e0003ef4048 0000000000000000
[  341.735263] raw: 0000000000000004 0000000000000000 00000000ffffffff 0000000000000000
[  341.742994] page dumped because: VM_BUG_ON_PAGE(page_ref_count(page) == 0)

where xdp_dummy.c is a simple bpf program that forwards the incoming
frames to the network stack (available here:
https://github.com/altoor/xdp_walkthrough_examples/blob/master/sample_1/xdp_dummy.c)

Fixes: 05c773f52b96 ("net: thunderx: Add basic XDP support")
Fixes: 4863dea3fab0 ("net: Adding support for Cavium ThunderX network controller")
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/thunder/nicvf_queues.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index a3d12dbde95b..09494e1c77c5 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -585,10 +585,12 @@ static void nicvf_free_snd_queue(struct nicvf *nic, struct snd_queue *sq)
 	if (!sq->dmem.base)
 		return;
 
-	if (sq->tso_hdrs)
+	if (sq->tso_hdrs) {
 		dma_free_coherent(&nic->pdev->dev,
 				  sq->dmem.q_len * TSO_HEADER_SIZE,
 				  sq->tso_hdrs, sq->tso_hdrs_phys);
+		sq->tso_hdrs = NULL;
+	}
 
 	/* Free pending skbs in the queue */
 	smp_rmb();
-- 
2.19.2


From ef0a9acdf05ac456a147bc098900726ed983c2ff Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Tue, 20 Nov 2018 13:00:18 -0500
Subject: [PATCH 6/9] packet: copy user buffers before orphan or clone

[ Upstream commit 5cd8d46ea1562be80063f53c7c6a5f40224de623 ]

tpacket_snd sends packets with user pages linked into skb frags. It
notifies that pages can be reused when the skb is released by setting
skb->destructor to tpacket_destruct_skb.

This can cause data corruption if the skb is orphaned (e.g., on
transmit through veth) or cloned (e.g., on mirror to another psock).

Create a kernel-private copy of data in these cases, same as tun/tap
zerocopy transmission. Reuse that infrastructure: mark the skb as
SKBTX_ZEROCOPY_FRAG, which will trigger copy in skb_orphan_frags(_rx).

Unlike other zerocopy packets, do not set shinfo destructor_arg to
struct ubuf_info. tpacket_destruct_skb already uses that ptr to notify
when the original skb is released and a timestamp is recorded. Do not
change this timestamp behavior. The ubuf_info->callback is not needed
anyway, as no zerocopy notification is expected.

Mark destructor_arg as not-a-uarg by setting the lower bit to 1. The
resulting value is not a valid ubuf_info pointer, nor a valid
tpacket_snd frame address. Add skb_zcopy_.._nouarg helpers for this.

The fix relies on features introduced in commit 52267790ef52 ("sock:
add MSG_ZEROCOPY"), so can be backported as is only to 4.14.

Tested with from `./in_netns.sh ./txring_overwrite` from
http://github.com/wdebruij/kerneltools/tests

Fixes: 69e3c75f4d54 ("net: TX_RING and packet mmap")
Reported-by: Anand H. Krishnan <anandhkrishnan@gmail.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 18 +++++++++++++++++-
 net/packet/af_packet.c |  4 ++--
 2 files changed, 19 insertions(+), 3 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index f64e88444082..f6250555ce7d 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1288,6 +1288,22 @@ static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg)
 	}
 }
 
+static inline void skb_zcopy_set_nouarg(struct sk_buff *skb, void *val)
+{
+	skb_shinfo(skb)->destructor_arg = (void *)((uintptr_t) val | 0x1UL);
+	skb_shinfo(skb)->tx_flags |= SKBTX_ZEROCOPY_FRAG;
+}
+
+static inline bool skb_zcopy_is_nouarg(struct sk_buff *skb)
+{
+	return (uintptr_t) skb_shinfo(skb)->destructor_arg & 0x1UL;
+}
+
+static inline void *skb_zcopy_get_nouarg(struct sk_buff *skb)
+{
+	return (void *)((uintptr_t) skb_shinfo(skb)->destructor_arg & ~0x1UL);
+}
+
 /* Release a reference on a zerocopy structure */
 static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy)
 {
@@ -1297,7 +1313,7 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy)
 		if (uarg->callback == sock_zerocopy_callback) {
 			uarg->zerocopy = uarg->zerocopy && zerocopy;
 			sock_zerocopy_put(uarg);
-		} else {
+		} else if (!skb_zcopy_is_nouarg(skb)) {
 			uarg->callback(uarg, zerocopy);
 		}
 
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 8d1a7c900393..88d5b2645bb0 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2433,7 +2433,7 @@ static void tpacket_destruct_skb(struct sk_buff *skb)
 		void *ph;
 		__u32 ts;
 
-		ph = skb_shinfo(skb)->destructor_arg;
+		ph = skb_zcopy_get_nouarg(skb);
 		packet_dec_pending(&po->tx_ring);
 
 		ts = __packet_set_timestamp(po, ph, skb);
@@ -2499,7 +2499,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 	skb->priority = po->sk.sk_priority;
 	skb->mark = po->sk.sk_mark;
 	sock_tx_timestamp(&po->sk, sockc->tsflags, &skb_shinfo(skb)->tx_flags);
-	skb_shinfo(skb)->destructor_arg = ph.raw;
+	skb_zcopy_set_nouarg(skb, ph.raw);
 
 	skb_reserve(skb, hlen);
 	skb_reset_network_header(skb);
-- 
2.19.2


From 5dab5883b4c880007b3b69865692beed48f3581d Mon Sep 17 00:00:00 2001
From: Pan Bian <bianpan2016@163.com>
Date: Wed, 28 Nov 2018 14:53:19 +0800
Subject: [PATCH 7/9] rapidio/rionet: do not free skb before reading its length

[ Upstream commit cfc435198f53a6fa1f656d98466b24967ff457d0 ]

skb is freed via dev_kfree_skb_any, however, skb->len is read then. This
may result in a use-after-free bug.

Fixes: e6161d64263 ("rapidio/rionet: rework driver initialization and removal")
Signed-off-by: Pan Bian <bianpan2016@163.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/rionet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/rionet.c b/drivers/net/rionet.c
index e9f101c9bae2..bfbb39f93554 100644
--- a/drivers/net/rionet.c
+++ b/drivers/net/rionet.c
@@ -216,9 +216,9 @@ static int rionet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 			 * it just report sending a packet to the target
 			 * (without actual packet transfer).
 			 */
-			dev_kfree_skb_any(skb);
 			ndev->stats.tx_packets++;
 			ndev->stats.tx_bytes += skb->len;
+			dev_kfree_skb_any(skb);
 		}
 	}
 
-- 
2.19.2


From d02b518e347d570ee2d0cdc19d47ea3eb7eba10a Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Wed, 28 Nov 2018 16:20:50 +0100
Subject: [PATCH 8/9] s390/qeth: fix length check in SNMP processing

[ Upstream commit 9a764c1e59684c0358e16ccaafd870629f2cfe67 ]

The response for a SNMP request can consist of multiple parts, which
the cmd callback stages into a kernel buffer until all parts have been
received. If the callback detects that the staging buffer provides
insufficient space, it bails out with error.
This processing is buggy for the first part of the response - while it
initially checks for a length of 'data_len', it later copies an
additional amount of 'offsetof(struct qeth_snmp_cmd, data)' bytes.

Fix the calculation of 'data_len' for the first part of the response.
This also nicely cleans up the memcpy code.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Reviewed-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 27 ++++++++++++---------------
 1 file changed, 12 insertions(+), 15 deletions(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 169dd7127f9e..69ef5f4060ed 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -4545,8 +4545,8 @@ static int qeth_snmp_command_cb(struct qeth_card *card,
 {
 	struct qeth_ipa_cmd *cmd;
 	struct qeth_arp_query_info *qinfo;
-	struct qeth_snmp_cmd *snmp;
 	unsigned char *data;
+	void *snmp_data;
 	__u16 data_len;
 
 	QETH_CARD_TEXT(card, 3, "snpcmdcb");
@@ -4554,7 +4554,6 @@ static int qeth_snmp_command_cb(struct qeth_card *card,
 	cmd = (struct qeth_ipa_cmd *) sdata;
 	data = (unsigned char *)((char *)cmd - reply->offset);
 	qinfo = (struct qeth_arp_query_info *) reply->param;
-	snmp = &cmd->data.setadapterparms.data.snmp;
 
 	if (cmd->hdr.return_code) {
 		QETH_CARD_TEXT_(card, 4, "scer1%x", cmd->hdr.return_code);
@@ -4567,10 +4566,15 @@ static int qeth_snmp_command_cb(struct qeth_card *card,
 		return 0;
 	}
 	data_len = *((__u16 *)QETH_IPA_PDU_LEN_PDU1(data));
-	if (cmd->data.setadapterparms.hdr.seq_no == 1)
-		data_len -= (__u16)((char *)&snmp->data - (char *)cmd);
-	else
-		data_len -= (__u16)((char *)&snmp->request - (char *)cmd);
+	if (cmd->data.setadapterparms.hdr.seq_no == 1) {
+		snmp_data = &cmd->data.setadapterparms.data.snmp;
+		data_len -= offsetof(struct qeth_ipa_cmd,
+				     data.setadapterparms.data.snmp);
+	} else {
+		snmp_data = &cmd->data.setadapterparms.data.snmp.request;
+		data_len -= offsetof(struct qeth_ipa_cmd,
+				     data.setadapterparms.data.snmp.request);
+	}
 
 	/* check if there is enough room in userspace */
 	if ((qinfo->udata_len - qinfo->udata_offset) < data_len) {
@@ -4583,16 +4587,9 @@ static int qeth_snmp_command_cb(struct qeth_card *card,
 	QETH_CARD_TEXT_(card, 4, "sseqn%i",
 		cmd->data.setadapterparms.hdr.seq_no);
 	/*copy entries to user buffer*/
-	if (cmd->data.setadapterparms.hdr.seq_no == 1) {
-		memcpy(qinfo->udata + qinfo->udata_offset,
-		       (char *)snmp,
-		       data_len + offsetof(struct qeth_snmp_cmd, data));
-		qinfo->udata_offset += offsetof(struct qeth_snmp_cmd, data);
-	} else {
-		memcpy(qinfo->udata + qinfo->udata_offset,
-		       (char *)&snmp->request, data_len);
-	}
+	memcpy(qinfo->udata + qinfo->udata_offset, snmp_data, data_len);
 	qinfo->udata_offset += data_len;
+
 	/* check if all replies received ... */
 		QETH_CARD_TEXT_(card, 4, "srtot%i",
 			       cmd->data.setadapterparms.hdr.used_total);
-- 
2.19.2


From 3a96e30b60064946ea6261de83bbe74844e949ae Mon Sep 17 00:00:00 2001
From: Bernd Eckstein <3erndeckstein@gmail.com>
Date: Fri, 23 Nov 2018 13:51:26 +0100
Subject: [PATCH 9/9] usbnet: ipheth: fix potential recvmsg bug and recvmsg bug
 2

[ Upstream commit 45611c61dd503454b2edae00aabe1e429ec49ebe ]

The bug is not easily reproducable, as it may occur very infrequently
(we had machines with 20minutes heavy downloading before it occurred)
However, on a virual machine (VMWare on Windows 10 host) it occurred
pretty frequently (1-2 seconds after a speedtest was started)

dev->tx_skb mab be freed via dev_kfree_skb_irq on a callback
before it is set.

This causes the following problems:
- double free of the skb or potential memory leak
- in dmesg: 'recvmsg bug' and 'recvmsg bug 2' and eventually
  general protection fault

Example dmesg output:
[  134.841986] ------------[ cut here ]------------
[  134.841987] recvmsg bug: copied 9C24A555 seq 9C24B557 rcvnxt 9C25A6B3 fl 0
[  134.841993] WARNING: CPU: 7 PID: 2629 at /build/linux-hwe-On9fm7/linux-hwe-4.15.0/net/ipv4/tcp.c:1865 tcp_recvmsg+0x44d/0xab0
[  134.841994] Modules linked in: ipheth(OE) kvm_intel kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel pcbc aesni_intel aes_x86_64 crypto_simd glue_helper cryptd vmw_balloon intel_rapl_perf joydev input_leds serio_raw vmw_vsock_vmci_transport vsock shpchp i2c_piix4 mac_hid binfmt_misc vmw_vmci parport_pc ppdev lp parport autofs4 vmw_pvscsi vmxnet3 hid_generic usbhid hid vmwgfx ttm drm_kms_helper syscopyarea sysfillrect mptspi mptscsih sysimgblt ahci psmouse fb_sys_fops pata_acpi mptbase libahci e1000 drm scsi_transport_spi
[  134.842046] CPU: 7 PID: 2629 Comm: python Tainted: G        W  OE    4.15.0-34-generic #37~16.04.1-Ubuntu
[  134.842046] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 05/19/2017
[  134.842048] RIP: 0010:tcp_recvmsg+0x44d/0xab0
[  134.842048] RSP: 0018:ffffa6630422bcc8 EFLAGS: 00010286
[  134.842049] RAX: 0000000000000000 RBX: ffff997616f4f200 RCX: 0000000000000006
[  134.842049] RDX: 0000000000000007 RSI: 0000000000000082 RDI: ffff9976257d6490
[  134.842050] RBP: ffffa6630422bd98 R08: 0000000000000001 R09: 000000000004bba4
[  134.842050] R10: 0000000001e00c6f R11: 000000000004bba4 R12: ffff99760dee3000
[  134.842051] R13: 0000000000000000 R14: ffff99760dee3514 R15: 0000000000000000
[  134.842051] FS:  00007fe332347700(0000) GS:ffff9976257c0000(0000) knlGS:0000000000000000
[  134.842052] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  134.842053] CR2: 0000000001e41000 CR3: 000000020e9b4006 CR4: 00000000003606e0
[  134.842055] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  134.842055] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[  134.842057] Call Trace:
[  134.842060]  ? aa_sk_perm+0x53/0x1a0
[  134.842064]  inet_recvmsg+0x51/0xc0
[  134.842066]  sock_recvmsg+0x43/0x50
[  134.842070]  SYSC_recvfrom+0xe4/0x160
[  134.842072]  ? __schedule+0x3de/0x8b0
[  134.842075]  ? ktime_get_ts64+0x4c/0xf0
[  134.842079]  SyS_recvfrom+0xe/0x10
[  134.842082]  do_syscall_64+0x73/0x130
[  134.842086]  entry_SYSCALL_64_after_hwframe+0x3d/0xa2
[  134.842086] RIP: 0033:0x7fe331f5a81d
[  134.842088] RSP: 002b:00007ffe8da98398 EFLAGS: 00000246 ORIG_RAX: 000000000000002d
[  134.842090] RAX: ffffffffffffffda RBX: ffffffffffffffff RCX: 00007fe331f5a81d
[  134.842094] RDX: 00000000000003fb RSI: 0000000001e00874 RDI: 0000000000000003
[  134.842095] RBP: 00007fe32f642c70 R08: 0000000000000000 R09: 0000000000000000
[  134.842097] R10: 0000000000000000 R11: 0000000000000246 R12: 00007fe332347698
[  134.842099] R13: 0000000001b7e0a0 R14: 0000000001e00874 R15: 0000000000000000
[  134.842103] Code: 24 fd ff ff e9 cc fe ff ff 48 89 d8 41 8b 8c 24 10 05 00 00 44 8b 45 80 48 c7 c7 08 bd 59 8b 48 89 85 68 ff ff ff e8 b3 c4 7d ff <0f> 0b 48 8b 85 68 ff ff ff e9 e9 fe ff ff 41 8b 8c 24 10 05 00
[  134.842126] ---[ end trace b7138fc08c83147f ]---
[  134.842144] general protection fault: 0000 [#1] SMP PTI
[  134.842145] Modules linked in: ipheth(OE) kvm_intel kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel pcbc aesni_intel aes_x86_64 crypto_simd glue_helper cryptd vmw_balloon intel_rapl_perf joydev input_leds serio_raw vmw_vsock_vmci_transport vsock shpchp i2c_piix4 mac_hid binfmt_misc vmw_vmci parport_pc ppdev lp parport autofs4 vmw_pvscsi vmxnet3 hid_generic usbhid hid vmwgfx ttm drm_kms_helper syscopyarea sysfillrect mptspi mptscsih sysimgblt ahci psmouse fb_sys_fops pata_acpi mptbase libahci e1000 drm scsi_transport_spi
[  134.842161] CPU: 7 PID: 2629 Comm: python Tainted: G        W  OE    4.15.0-34-generic #37~16.04.1-Ubuntu
[  134.842162] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 05/19/2017
[  134.842164] RIP: 0010:tcp_close+0x2c6/0x440
[  134.842165] RSP: 0018:ffffa6630422bde8 EFLAGS: 00010202
[  134.842167] RAX: 0000000000000000 RBX: ffff99760dee3000 RCX: 0000000180400034
[  134.842168] RDX: 5c4afd407207a6c4 RSI: ffffe868495bd300 RDI: ffff997616f4f200
[  134.842169] RBP: ffffa6630422be08 R08: 0000000016f4d401 R09: 0000000180400034
[  134.842169] R10: ffffa6630422bd98 R11: 0000000000000000 R12: 000000000000600c
[  134.842170] R13: 0000000000000000 R14: ffff99760dee30c8 R15: ffff9975bd44fe00
[  134.842171] FS:  00007fe332347700(0000) GS:ffff9976257c0000(0000) knlGS:0000000000000000
[  134.842173] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  134.842174] CR2: 0000000001e41000 CR3: 000000020e9b4006 CR4: 00000000003606e0
[  134.842177] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  134.842178] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[  134.842179] Call Trace:
[  134.842181]  inet_release+0x42/0x70
[  134.842183]  __sock_release+0x42/0xb0
[  134.842184]  sock_close+0x15/0x20
[  134.842187]  __fput+0xea/0x220
[  134.842189]  ____fput+0xe/0x10
[  134.842191]  task_work_run+0x8a/0xb0
[  134.842193]  exit_to_usermode_loop+0xc4/0xd0
[  134.842195]  do_syscall_64+0xf4/0x130
[  134.842197]  entry_SYSCALL_64_after_hwframe+0x3d/0xa2
[  134.842197] RIP: 0033:0x7fe331f5a560
[  134.842198] RSP: 002b:00007ffe8da982e8 EFLAGS: 00000246 ORIG_RAX: 0000000000000003
[  134.842200] RAX: 0000000000000000 RBX: 00007fe32f642c70 RCX: 00007fe331f5a560
[  134.842201] RDX: 00000000008f5320 RSI: 0000000001cd4b50 RDI: 0000000000000003
[  134.842202] RBP: 00007fe32f6500f8 R08: 000000000000003c R09: 00000000009343c0
[  134.842203] R10: 0000000000000000 R11: 0000000000000246 R12: 00007fe32f6500d0
[  134.842204] R13: 00000000008f5320 R14: 00000000008f5320 R15: 0000000001cd4770
[  134.842205] Code: c8 00 00 00 45 31 e4 49 39 fe 75 4d eb 50 83 ab d8 00 00 00 01 48 8b 17 48 8b 47 08 48 c7 07 00 00 00 00 48 c7 47 08 00 00 00 00 <48> 89 42 08 48 89 10 0f b6 57 34 8b 47 2c 2b 47 28 83 e2 01 80
[  134.842226] RIP: tcp_close+0x2c6/0x440 RSP: ffffa6630422bde8
[  134.842227] ---[ end trace b7138fc08c831480 ]---

The proposed patch eliminates a potential racing condition.
Before, usb_submit_urb was called and _after_ that, the skb was attached
(dev->tx_skb). So, on a callback it was possible, however unlikely that the
skb was freed before it was set. That way (because dev->tx_skb was not set
to NULL after it was freed), it could happen that a skb from a earlier
transmission was freed a second time (and the skb we should have freed did
not get freed at all)

Now we free the skb directly in ipheth_tx(). It is not passed to the
callback anymore, eliminating the posibility of a double free of the same
skb. Depending on the retval of usb_submit_urb() we use dev_kfree_skb_any()
respectively dev_consume_skb_any() to free the skb.

Signed-off-by: Oliver Zweigle <Oliver.Zweigle@faro.com>
Signed-off-by: Bernd Eckstein <3ernd.Eckstein@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/ipheth.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c
index d49c7103085e..aabbcfb6e6da 100644
--- a/drivers/net/usb/ipheth.c
+++ b/drivers/net/usb/ipheth.c
@@ -140,7 +140,6 @@ struct ipheth_device {
 	struct usb_device *udev;
 	struct usb_interface *intf;
 	struct net_device *net;
-	struct sk_buff *tx_skb;
 	struct urb *tx_urb;
 	struct urb *rx_urb;
 	unsigned char *tx_buf;
@@ -229,6 +228,7 @@ static void ipheth_rcvbulk_callback(struct urb *urb)
 	case -ENOENT:
 	case -ECONNRESET:
 	case -ESHUTDOWN:
+	case -EPROTO:
 		return;
 	case 0:
 		break;
@@ -280,7 +280,6 @@ static void ipheth_sndbulk_callback(struct urb *urb)
 		dev_err(&dev->intf->dev, "%s: urb status: %d\n",
 		__func__, status);
 
-	dev_kfree_skb_irq(dev->tx_skb);
 	netif_wake_queue(dev->net);
 }
 
@@ -410,7 +409,7 @@ static int ipheth_tx(struct sk_buff *skb, struct net_device *net)
 	if (skb->len > IPHETH_BUF_SIZE) {
 		WARN(1, "%s: skb too large: %d bytes\n", __func__, skb->len);
 		dev->net->stats.tx_dropped++;
-		dev_kfree_skb_irq(skb);
+		dev_kfree_skb_any(skb);
 		return NETDEV_TX_OK;
 	}
 
@@ -430,12 +429,11 @@ static int ipheth_tx(struct sk_buff *skb, struct net_device *net)
 		dev_err(&dev->intf->dev, "%s: usb_submit_urb: %d\n",
 			__func__, retval);
 		dev->net->stats.tx_errors++;
-		dev_kfree_skb_irq(skb);
+		dev_kfree_skb_any(skb);
 	} else {
-		dev->tx_skb = skb;
-
 		dev->net->stats.tx_packets++;
 		dev->net->stats.tx_bytes += skb->len;
+		dev_consume_skb_any(skb);
 		netif_stop_queue(net);
 	}
 
-- 
2.19.2


[-- Attachment #3: net_419.mbox --]
[-- Type: Application/Octet-Stream, Size: 52873 bytes --]

From 80486792b649703cb9393391a810c7f5336b7df5 Mon Sep 17 00:00:00 2001
From: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Date: Mon, 26 Nov 2018 12:27:10 -0500
Subject: [PATCH 01/17] lan743x: Enable driver to work with LAN7431

[ Upstream commit 4df5ce9bc03e47d05f400e64aa32a82ec4cef419 ]

This driver was designed to work with both LAN7430 and LAN7431.
The only difference between the two is the LAN7431 has support
for external phy.

This change adds LAN7431 to the list of recognized devices
supported by this driver.

Updates for v2:
    changed 'fixes' tag to match defined format

fixes: 23f0703c125b ("lan743x: Add main source files for new lan743x driver")
Signed-off-by: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/lan743x_main.c | 1 +
 drivers/net/ethernet/microchip/lan743x_main.h | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index 001b5f714c1b..a151544a7fa9 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -3020,6 +3020,7 @@ static const struct dev_pm_ops lan743x_pm_ops = {
 
 static const struct pci_device_id lan743x_pcidev_tbl[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_SMSC, PCI_DEVICE_ID_SMSC_LAN7430) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_SMSC, PCI_DEVICE_ID_SMSC_LAN7431) },
 	{ 0, }
 };
 
diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h
index 0e82b6368798..2d6eea18973e 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.h
+++ b/drivers/net/ethernet/microchip/lan743x_main.h
@@ -548,6 +548,7 @@ struct lan743x_adapter;
 /* SMSC acquired EFAR late 1990's, MCHP acquired SMSC 2012 */
 #define PCI_VENDOR_ID_SMSC		PCI_VENDOR_ID_EFAR
 #define PCI_DEVICE_ID_SMSC_LAN7430	(0x7430)
+#define PCI_DEVICE_ID_SMSC_LAN7431	(0x7431)
 
 #define PCI_CONFIG_LENGTH		(0x1000)
 
-- 
2.19.2


From 970de6e11c03f3d40c81979fdc2a71a7253606f2 Mon Sep 17 00:00:00 2001
From: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Date: Mon, 26 Nov 2018 12:04:57 -0500
Subject: [PATCH 02/17] lan743x: fix return value for lan743x_tx_napi_poll

[ Upstream commit cc5922054131f9abefdc0622ae64fc55e6b2671d ]

The lan743x driver, when under heavy traffic load, has been noticed
to sometimes hang, or cause a kernel panic.

Debugging reveals that the TX napi poll routine was returning
the wrong value, 'weight'. Most other drivers return 0.
And call napi_complete, instead of napi_complete_done.

Additionally when creating the tx napi poll routine.
Changed netif_napi_add, to netif_tx_napi_add.

Updates for v3:
    changed 'fixes' tag to match defined format

Updates for v2:
use napi_complete, instead of napi_complete_done in
    lan743x_tx_napi_poll
use netif_tx_napi_add, instead of netif_napi_add for
    registration of tx napi poll routine

fixes: 23f0703c125b ("lan743x: Add main source files for new lan743x driver")
Signed-off-by: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/lan743x_main.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index a151544a7fa9..aaedf1072460 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -1675,7 +1675,7 @@ static int lan743x_tx_napi_poll(struct napi_struct *napi, int weight)
 		netif_wake_queue(adapter->netdev);
 	}
 
-	if (!napi_complete_done(napi, weight))
+	if (!napi_complete(napi))
 		goto done;
 
 	/* enable isr */
@@ -1684,7 +1684,7 @@ static int lan743x_tx_napi_poll(struct napi_struct *napi, int weight)
 	lan743x_csr_read(adapter, INT_STS);
 
 done:
-	return weight;
+	return 0;
 }
 
 static void lan743x_tx_ring_cleanup(struct lan743x_tx *tx)
@@ -1873,9 +1873,9 @@ static int lan743x_tx_open(struct lan743x_tx *tx)
 	tx->vector_flags = lan743x_intr_get_vector_flags(adapter,
 							 INT_BIT_DMA_TX_
 							 (tx->channel_number));
-	netif_napi_add(adapter->netdev,
-		       &tx->napi, lan743x_tx_napi_poll,
-		       tx->ring_size - 1);
+	netif_tx_napi_add(adapter->netdev,
+			  &tx->napi, lan743x_tx_napi_poll,
+			  tx->ring_size - 1);
 	napi_enable(&tx->napi);
 
 	data = 0;
-- 
2.19.2


From d8dd11e75279faa447f6e19832cd7c055f05fb4d Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 21 Nov 2018 18:21:35 +0100
Subject: [PATCH 03/17] net: don't keep lonely packets forever in the gro hash

[ Upstream commit 605108acfe6233b72e2f803aa1cb59a2af3001ca ]

Eric noted that with UDP GRO and NAPI timeout, we could keep a single
UDP packet inside the GRO hash forever, if the related NAPI instance
calls napi_gro_complete() at an higher frequency than the NAPI timeout.
Willem noted that even TCP packets could be trapped there, till the
next retransmission.
This patch tries to address the issue, flushing the old packets -
those with a NAPI_GRO_CB age before the current jiffy - before scheduling
the NAPI timeout. The rationale is that such a timeout should be
well below a jiffy and we are not flushing packets eligible for sane GRO.

v1  -> v2:
 - clarified the commit message and comment

RFC -> v1:
 - added 'Fixes tags', cleaned-up the wording.

Reported-by: Eric Dumazet <eric.dumazet@gmail.com>
Fixes: 3b47d30396ba ("net: gro: add a per device gro flush timer")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 097c02101450..22af88c47756 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5945,11 +5945,14 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 		if (work_done)
 			timeout = n->dev->gro_flush_timeout;
 
+		/* When the NAPI instance uses a timeout and keeps postponing
+		 * it, we need to bound somehow the time packets are kept in
+		 * the GRO layer
+		 */
+		napi_gro_flush(n, !!timeout);
 		if (timeout)
 			hrtimer_start(&n->timer, ns_to_ktime(timeout),
 				      HRTIMER_MODE_REL_PINNED);
-		else
-			napi_gro_flush(n, false);
 	}
 	if (unlikely(!list_empty(&n->poll_list))) {
 		/* If n->poll_list is not empty, we need to mask irqs */
-- 
2.19.2


From ca37d17fb750be3629a9c4d476b247b0d2e9bc86 Mon Sep 17 00:00:00 2001
From: Andreas Fiedler <andreas.fiedler@gmx.net>
Date: Sat, 24 Nov 2018 00:16:34 +0100
Subject: [PATCH 04/17] net: gemini: Fix copy/paste error

[ Upstream commit 07093b76476903f820d83d56c3040e656fb4d9e3 ]

The TX stats should be started with the tx_stats_syncp,
there seems to be a copy/paste error in the driver.

Signed-off-by: Andreas Fiedler <andreas.fiedler@gmx.net>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cortina/gemini.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index 1c9ad3630c77..dfd1ad0b1cb9 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -661,7 +661,7 @@ static void gmac_clean_txq(struct net_device *netdev, struct gmac_txq *txq,
 
 			u64_stats_update_begin(&port->tx_stats_syncp);
 			port->tx_frag_stats[nfrags]++;
-			u64_stats_update_end(&port->ir_stats_syncp);
+			u64_stats_update_end(&port->tx_stats_syncp);
 		}
 	}
 
-- 
2.19.2


From 6b930ae8be2c89688b79966b9bb0644022404437 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Fri, 23 Nov 2018 18:28:01 +0100
Subject: [PATCH 05/17] net: thunderx: set tso_hdrs pointer to NULL in
 nicvf_free_snd_queue

[ Upstream commit ef2a7cf1d8831535b8991459567b385661eb4a36 ]

Reset snd_queue tso_hdrs pointer to NULL in nicvf_free_snd_queue routine
since it is used to check if tso dma descriptor queue has been previously
allocated. The issue can be triggered with the following reproducer:

$ip link set dev enP2p1s0v0 xdpdrv obj xdp_dummy.o
$ip link set dev enP2p1s0v0 xdpdrv off

[  341.467649] WARNING: CPU: 74 PID: 2158 at mm/vmalloc.c:1511 __vunmap+0x98/0xe0
[  341.515010] Hardware name: GIGABYTE H270-T70/MT70-HD0, BIOS T49 02/02/2018
[  341.521874] pstate: 60400005 (nZCv daif +PAN -UAO)
[  341.526654] pc : __vunmap+0x98/0xe0
[  341.530132] lr : __vunmap+0x98/0xe0
[  341.533609] sp : ffff00001c5db860
[  341.536913] x29: ffff00001c5db860 x28: 0000000000020000
[  341.542214] x27: ffff810feb5090b0 x26: ffff000017e57000
[  341.547515] x25: 0000000000000000 x24: 00000000fbd00000
[  341.552816] x23: 0000000000000000 x22: ffff810feb5090b0
[  341.558117] x21: 0000000000000000 x20: 0000000000000000
[  341.563418] x19: ffff000017e57000 x18: 0000000000000000
[  341.568719] x17: 0000000000000000 x16: 0000000000000000
[  341.574020] x15: 0000000000000010 x14: ffffffffffffffff
[  341.579321] x13: ffff00008985eb27 x12: ffff00000985eb2f
[  341.584622] x11: ffff0000096b3000 x10: ffff00001c5db510
[  341.589923] x9 : 00000000ffffffd0 x8 : ffff0000086868e8
[  341.595224] x7 : 3430303030303030 x6 : 00000000000006ef
[  341.600525] x5 : 00000000003fffff x4 : 0000000000000000
[  341.605825] x3 : 0000000000000000 x2 : ffffffffffffffff
[  341.611126] x1 : ffff0000096b3728 x0 : 0000000000000038
[  341.616428] Call trace:
[  341.618866]  __vunmap+0x98/0xe0
[  341.621997]  vunmap+0x3c/0x50
[  341.624961]  arch_dma_free+0x68/0xa0
[  341.628534]  dma_direct_free+0x50/0x80
[  341.632285]  nicvf_free_resources+0x160/0x2d8 [nicvf]
[  341.637327]  nicvf_config_data_transfer+0x174/0x5e8 [nicvf]
[  341.642890]  nicvf_stop+0x298/0x340 [nicvf]
[  341.647066]  __dev_close_many+0x9c/0x108
[  341.650977]  dev_close_many+0xa4/0x158
[  341.654720]  rollback_registered_many+0x140/0x530
[  341.659414]  rollback_registered+0x54/0x80
[  341.663499]  unregister_netdevice_queue+0x9c/0xe8
[  341.668192]  unregister_netdev+0x28/0x38
[  341.672106]  nicvf_remove+0xa4/0xa8 [nicvf]
[  341.676280]  nicvf_shutdown+0x20/0x30 [nicvf]
[  341.680630]  pci_device_shutdown+0x44/0x88
[  341.684720]  device_shutdown+0x144/0x250
[  341.688640]  kernel_restart_prepare+0x44/0x50
[  341.692986]  kernel_restart+0x20/0x68
[  341.696638]  __se_sys_reboot+0x210/0x238
[  341.700550]  __arm64_sys_reboot+0x24/0x30
[  341.704555]  el0_svc_handler+0x94/0x110
[  341.708382]  el0_svc+0x8/0xc
[  341.711252] ---[ end trace 3f4019c8439959c9 ]---
[  341.715874] page:ffff7e0003ef4000 count:0 mapcount:0 mapping:0000000000000000 index:0x4
[  341.723872] flags: 0x1fffe000000000()
[  341.727527] raw: 001fffe000000000 ffff7e0003f1a008 ffff7e0003ef4048 0000000000000000
[  341.735263] raw: 0000000000000004 0000000000000000 00000000ffffffff 0000000000000000
[  341.742994] page dumped because: VM_BUG_ON_PAGE(page_ref_count(page) == 0)

where xdp_dummy.c is a simple bpf program that forwards the incoming
frames to the network stack (available here:
https://github.com/altoor/xdp_walkthrough_examples/blob/master/sample_1/xdp_dummy.c)

Fixes: 05c773f52b96 ("net: thunderx: Add basic XDP support")
Fixes: 4863dea3fab0 ("net: Adding support for Cavium ThunderX network controller")
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/thunder/nicvf_queues.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index 187a249ff2d1..fcaf18fa3904 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -585,10 +585,12 @@ static void nicvf_free_snd_queue(struct nicvf *nic, struct snd_queue *sq)
 	if (!sq->dmem.base)
 		return;
 
-	if (sq->tso_hdrs)
+	if (sq->tso_hdrs) {
 		dma_free_coherent(&nic->pdev->dev,
 				  sq->dmem.q_len * TSO_HEADER_SIZE,
 				  sq->tso_hdrs, sq->tso_hdrs_phys);
+		sq->tso_hdrs = NULL;
+	}
 
 	/* Free pending skbs in the queue */
 	smp_rmb();
-- 
2.19.2


From 4d1cd7d09927e33e7a679232914d90def17bf039 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Tue, 20 Nov 2018 13:00:18 -0500
Subject: [PATCH 06/17] packet: copy user buffers before orphan or clone

[ Upstream commit 5cd8d46ea1562be80063f53c7c6a5f40224de623 ]

tpacket_snd sends packets with user pages linked into skb frags. It
notifies that pages can be reused when the skb is released by setting
skb->destructor to tpacket_destruct_skb.

This can cause data corruption if the skb is orphaned (e.g., on
transmit through veth) or cloned (e.g., on mirror to another psock).

Create a kernel-private copy of data in these cases, same as tun/tap
zerocopy transmission. Reuse that infrastructure: mark the skb as
SKBTX_ZEROCOPY_FRAG, which will trigger copy in skb_orphan_frags(_rx).

Unlike other zerocopy packets, do not set shinfo destructor_arg to
struct ubuf_info. tpacket_destruct_skb already uses that ptr to notify
when the original skb is released and a timestamp is recorded. Do not
change this timestamp behavior. The ubuf_info->callback is not needed
anyway, as no zerocopy notification is expected.

Mark destructor_arg as not-a-uarg by setting the lower bit to 1. The
resulting value is not a valid ubuf_info pointer, nor a valid
tpacket_snd frame address. Add skb_zcopy_.._nouarg helpers for this.

The fix relies on features introduced in commit 52267790ef52 ("sock:
add MSG_ZEROCOPY"), so can be backported as is only to 4.14.

Tested with from `./in_netns.sh ./txring_overwrite` from
http://github.com/wdebruij/kerneltools/tests

Fixes: 69e3c75f4d54 ("net: TX_RING and packet mmap")
Reported-by: Anand H. Krishnan <anandhkrishnan@gmail.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 18 +++++++++++++++++-
 net/packet/af_packet.c |  4 ++--
 2 files changed, 19 insertions(+), 3 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 17a13e4785fc..e6ef9cc05e60 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1311,6 +1311,22 @@ static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg)
 	}
 }
 
+static inline void skb_zcopy_set_nouarg(struct sk_buff *skb, void *val)
+{
+	skb_shinfo(skb)->destructor_arg = (void *)((uintptr_t) val | 0x1UL);
+	skb_shinfo(skb)->tx_flags |= SKBTX_ZEROCOPY_FRAG;
+}
+
+static inline bool skb_zcopy_is_nouarg(struct sk_buff *skb)
+{
+	return (uintptr_t) skb_shinfo(skb)->destructor_arg & 0x1UL;
+}
+
+static inline void *skb_zcopy_get_nouarg(struct sk_buff *skb)
+{
+	return (void *)((uintptr_t) skb_shinfo(skb)->destructor_arg & ~0x1UL);
+}
+
 /* Release a reference on a zerocopy structure */
 static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy)
 {
@@ -1320,7 +1336,7 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy)
 		if (uarg->callback == sock_zerocopy_callback) {
 			uarg->zerocopy = uarg->zerocopy && zerocopy;
 			sock_zerocopy_put(uarg);
-		} else {
+		} else if (!skb_zcopy_is_nouarg(skb)) {
 			uarg->callback(uarg, zerocopy);
 		}
 
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index d6e94dc7e290..6477b131e809 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2394,7 +2394,7 @@ static void tpacket_destruct_skb(struct sk_buff *skb)
 		void *ph;
 		__u32 ts;
 
-		ph = skb_shinfo(skb)->destructor_arg;
+		ph = skb_zcopy_get_nouarg(skb);
 		packet_dec_pending(&po->tx_ring);
 
 		ts = __packet_set_timestamp(po, ph, skb);
@@ -2461,7 +2461,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 	skb->mark = po->sk.sk_mark;
 	skb->tstamp = sockc->transmit_time;
 	sock_tx_timestamp(&po->sk, sockc->tsflags, &skb_shinfo(skb)->tx_flags);
-	skb_shinfo(skb)->destructor_arg = ph.raw;
+	skb_zcopy_set_nouarg(skb, ph.raw);
 
 	skb_reserve(skb, hlen);
 	skb_reset_network_header(skb);
-- 
2.19.2


From 924fb1cff3ddefb7fb18ff661c41b50dd11fed1d Mon Sep 17 00:00:00 2001
From: Pan Bian <bianpan2016@163.com>
Date: Wed, 28 Nov 2018 14:53:19 +0800
Subject: [PATCH 07/17] rapidio/rionet: do not free skb before reading its
 length

[ Upstream commit cfc435198f53a6fa1f656d98466b24967ff457d0 ]

skb is freed via dev_kfree_skb_any, however, skb->len is read then. This
may result in a use-after-free bug.

Fixes: e6161d64263 ("rapidio/rionet: rework driver initialization and removal")
Signed-off-by: Pan Bian <bianpan2016@163.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/rionet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/rionet.c b/drivers/net/rionet.c
index e9f101c9bae2..bfbb39f93554 100644
--- a/drivers/net/rionet.c
+++ b/drivers/net/rionet.c
@@ -216,9 +216,9 @@ static int rionet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 			 * it just report sending a packet to the target
 			 * (without actual packet transfer).
 			 */
-			dev_kfree_skb_any(skb);
 			ndev->stats.tx_packets++;
 			ndev->stats.tx_bytes += skb->len;
+			dev_kfree_skb_any(skb);
 		}
 	}
 
-- 
2.19.2


From 7c46bd9718ec6ad9ed9652724f1de8ed88d59ade Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Wed, 28 Nov 2018 16:20:50 +0100
Subject: [PATCH 08/17] s390/qeth: fix length check in SNMP processing

[ Upstream commit 9a764c1e59684c0358e16ccaafd870629f2cfe67 ]

The response for a SNMP request can consist of multiple parts, which
the cmd callback stages into a kernel buffer until all parts have been
received. If the callback detects that the staging buffer provides
insufficient space, it bails out with error.
This processing is buggy for the first part of the response - while it
initially checks for a length of 'data_len', it later copies an
additional amount of 'offsetof(struct qeth_snmp_cmd, data)' bytes.

Fix the calculation of 'data_len' for the first part of the response.
This also nicely cleans up the memcpy code.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Reviewed-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 27 ++++++++++++---------------
 1 file changed, 12 insertions(+), 15 deletions(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index ffce6f39828a..b03515d43745 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -4524,8 +4524,8 @@ static int qeth_snmp_command_cb(struct qeth_card *card,
 {
 	struct qeth_ipa_cmd *cmd;
 	struct qeth_arp_query_info *qinfo;
-	struct qeth_snmp_cmd *snmp;
 	unsigned char *data;
+	void *snmp_data;
 	__u16 data_len;
 
 	QETH_CARD_TEXT(card, 3, "snpcmdcb");
@@ -4533,7 +4533,6 @@ static int qeth_snmp_command_cb(struct qeth_card *card,
 	cmd = (struct qeth_ipa_cmd *) sdata;
 	data = (unsigned char *)((char *)cmd - reply->offset);
 	qinfo = (struct qeth_arp_query_info *) reply->param;
-	snmp = &cmd->data.setadapterparms.data.snmp;
 
 	if (cmd->hdr.return_code) {
 		QETH_CARD_TEXT_(card, 4, "scer1%x", cmd->hdr.return_code);
@@ -4546,10 +4545,15 @@ static int qeth_snmp_command_cb(struct qeth_card *card,
 		return 0;
 	}
 	data_len = *((__u16 *)QETH_IPA_PDU_LEN_PDU1(data));
-	if (cmd->data.setadapterparms.hdr.seq_no == 1)
-		data_len -= (__u16)((char *)&snmp->data - (char *)cmd);
-	else
-		data_len -= (__u16)((char *)&snmp->request - (char *)cmd);
+	if (cmd->data.setadapterparms.hdr.seq_no == 1) {
+		snmp_data = &cmd->data.setadapterparms.data.snmp;
+		data_len -= offsetof(struct qeth_ipa_cmd,
+				     data.setadapterparms.data.snmp);
+	} else {
+		snmp_data = &cmd->data.setadapterparms.data.snmp.request;
+		data_len -= offsetof(struct qeth_ipa_cmd,
+				     data.setadapterparms.data.snmp.request);
+	}
 
 	/* check if there is enough room in userspace */
 	if ((qinfo->udata_len - qinfo->udata_offset) < data_len) {
@@ -4562,16 +4566,9 @@ static int qeth_snmp_command_cb(struct qeth_card *card,
 	QETH_CARD_TEXT_(card, 4, "sseqn%i",
 		cmd->data.setadapterparms.hdr.seq_no);
 	/*copy entries to user buffer*/
-	if (cmd->data.setadapterparms.hdr.seq_no == 1) {
-		memcpy(qinfo->udata + qinfo->udata_offset,
-		       (char *)snmp,
-		       data_len + offsetof(struct qeth_snmp_cmd, data));
-		qinfo->udata_offset += offsetof(struct qeth_snmp_cmd, data);
-	} else {
-		memcpy(qinfo->udata + qinfo->udata_offset,
-		       (char *)&snmp->request, data_len);
-	}
+	memcpy(qinfo->udata + qinfo->udata_offset, snmp_data, data_len);
 	qinfo->udata_offset += data_len;
+
 	/* check if all replies received ... */
 		QETH_CARD_TEXT_(card, 4, "srtot%i",
 			       cmd->data.setadapterparms.hdr.used_total);
-- 
2.19.2


From 26deb5ba84d891fbd746b11ef8f48b76cc23b9e5 Mon Sep 17 00:00:00 2001
From: Bernd Eckstein <3erndeckstein@gmail.com>
Date: Fri, 23 Nov 2018 13:51:26 +0100
Subject: [PATCH 09/17] usbnet: ipheth: fix potential recvmsg bug and recvmsg
 bug 2

[ Upstream commit 45611c61dd503454b2edae00aabe1e429ec49ebe ]

The bug is not easily reproducable, as it may occur very infrequently
(we had machines with 20minutes heavy downloading before it occurred)
However, on a virual machine (VMWare on Windows 10 host) it occurred
pretty frequently (1-2 seconds after a speedtest was started)

dev->tx_skb mab be freed via dev_kfree_skb_irq on a callback
before it is set.

This causes the following problems:
- double free of the skb or potential memory leak
- in dmesg: 'recvmsg bug' and 'recvmsg bug 2' and eventually
  general protection fault

Example dmesg output:
[  134.841986] ------------[ cut here ]------------
[  134.841987] recvmsg bug: copied 9C24A555 seq 9C24B557 rcvnxt 9C25A6B3 fl 0
[  134.841993] WARNING: CPU: 7 PID: 2629 at /build/linux-hwe-On9fm7/linux-hwe-4.15.0/net/ipv4/tcp.c:1865 tcp_recvmsg+0x44d/0xab0
[  134.841994] Modules linked in: ipheth(OE) kvm_intel kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel pcbc aesni_intel aes_x86_64 crypto_simd glue_helper cryptd vmw_balloon intel_rapl_perf joydev input_leds serio_raw vmw_vsock_vmci_transport vsock shpchp i2c_piix4 mac_hid binfmt_misc vmw_vmci parport_pc ppdev lp parport autofs4 vmw_pvscsi vmxnet3 hid_generic usbhid hid vmwgfx ttm drm_kms_helper syscopyarea sysfillrect mptspi mptscsih sysimgblt ahci psmouse fb_sys_fops pata_acpi mptbase libahci e1000 drm scsi_transport_spi
[  134.842046] CPU: 7 PID: 2629 Comm: python Tainted: G        W  OE    4.15.0-34-generic #37~16.04.1-Ubuntu
[  134.842046] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 05/19/2017
[  134.842048] RIP: 0010:tcp_recvmsg+0x44d/0xab0
[  134.842048] RSP: 0018:ffffa6630422bcc8 EFLAGS: 00010286
[  134.842049] RAX: 0000000000000000 RBX: ffff997616f4f200 RCX: 0000000000000006
[  134.842049] RDX: 0000000000000007 RSI: 0000000000000082 RDI: ffff9976257d6490
[  134.842050] RBP: ffffa6630422bd98 R08: 0000000000000001 R09: 000000000004bba4
[  134.842050] R10: 0000000001e00c6f R11: 000000000004bba4 R12: ffff99760dee3000
[  134.842051] R13: 0000000000000000 R14: ffff99760dee3514 R15: 0000000000000000
[  134.842051] FS:  00007fe332347700(0000) GS:ffff9976257c0000(0000) knlGS:0000000000000000
[  134.842052] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  134.842053] CR2: 0000000001e41000 CR3: 000000020e9b4006 CR4: 00000000003606e0
[  134.842055] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  134.842055] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[  134.842057] Call Trace:
[  134.842060]  ? aa_sk_perm+0x53/0x1a0
[  134.842064]  inet_recvmsg+0x51/0xc0
[  134.842066]  sock_recvmsg+0x43/0x50
[  134.842070]  SYSC_recvfrom+0xe4/0x160
[  134.842072]  ? __schedule+0x3de/0x8b0
[  134.842075]  ? ktime_get_ts64+0x4c/0xf0
[  134.842079]  SyS_recvfrom+0xe/0x10
[  134.842082]  do_syscall_64+0x73/0x130
[  134.842086]  entry_SYSCALL_64_after_hwframe+0x3d/0xa2
[  134.842086] RIP: 0033:0x7fe331f5a81d
[  134.842088] RSP: 002b:00007ffe8da98398 EFLAGS: 00000246 ORIG_RAX: 000000000000002d
[  134.842090] RAX: ffffffffffffffda RBX: ffffffffffffffff RCX: 00007fe331f5a81d
[  134.842094] RDX: 00000000000003fb RSI: 0000000001e00874 RDI: 0000000000000003
[  134.842095] RBP: 00007fe32f642c70 R08: 0000000000000000 R09: 0000000000000000
[  134.842097] R10: 0000000000000000 R11: 0000000000000246 R12: 00007fe332347698
[  134.842099] R13: 0000000001b7e0a0 R14: 0000000001e00874 R15: 0000000000000000
[  134.842103] Code: 24 fd ff ff e9 cc fe ff ff 48 89 d8 41 8b 8c 24 10 05 00 00 44 8b 45 80 48 c7 c7 08 bd 59 8b 48 89 85 68 ff ff ff e8 b3 c4 7d ff <0f> 0b 48 8b 85 68 ff ff ff e9 e9 fe ff ff 41 8b 8c 24 10 05 00
[  134.842126] ---[ end trace b7138fc08c83147f ]---
[  134.842144] general protection fault: 0000 [#1] SMP PTI
[  134.842145] Modules linked in: ipheth(OE) kvm_intel kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel pcbc aesni_intel aes_x86_64 crypto_simd glue_helper cryptd vmw_balloon intel_rapl_perf joydev input_leds serio_raw vmw_vsock_vmci_transport vsock shpchp i2c_piix4 mac_hid binfmt_misc vmw_vmci parport_pc ppdev lp parport autofs4 vmw_pvscsi vmxnet3 hid_generic usbhid hid vmwgfx ttm drm_kms_helper syscopyarea sysfillrect mptspi mptscsih sysimgblt ahci psmouse fb_sys_fops pata_acpi mptbase libahci e1000 drm scsi_transport_spi
[  134.842161] CPU: 7 PID: 2629 Comm: python Tainted: G        W  OE    4.15.0-34-generic #37~16.04.1-Ubuntu
[  134.842162] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 05/19/2017
[  134.842164] RIP: 0010:tcp_close+0x2c6/0x440
[  134.842165] RSP: 0018:ffffa6630422bde8 EFLAGS: 00010202
[  134.842167] RAX: 0000000000000000 RBX: ffff99760dee3000 RCX: 0000000180400034
[  134.842168] RDX: 5c4afd407207a6c4 RSI: ffffe868495bd300 RDI: ffff997616f4f200
[  134.842169] RBP: ffffa6630422be08 R08: 0000000016f4d401 R09: 0000000180400034
[  134.842169] R10: ffffa6630422bd98 R11: 0000000000000000 R12: 000000000000600c
[  134.842170] R13: 0000000000000000 R14: ffff99760dee30c8 R15: ffff9975bd44fe00
[  134.842171] FS:  00007fe332347700(0000) GS:ffff9976257c0000(0000) knlGS:0000000000000000
[  134.842173] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  134.842174] CR2: 0000000001e41000 CR3: 000000020e9b4006 CR4: 00000000003606e0
[  134.842177] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  134.842178] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[  134.842179] Call Trace:
[  134.842181]  inet_release+0x42/0x70
[  134.842183]  __sock_release+0x42/0xb0
[  134.842184]  sock_close+0x15/0x20
[  134.842187]  __fput+0xea/0x220
[  134.842189]  ____fput+0xe/0x10
[  134.842191]  task_work_run+0x8a/0xb0
[  134.842193]  exit_to_usermode_loop+0xc4/0xd0
[  134.842195]  do_syscall_64+0xf4/0x130
[  134.842197]  entry_SYSCALL_64_after_hwframe+0x3d/0xa2
[  134.842197] RIP: 0033:0x7fe331f5a560
[  134.842198] RSP: 002b:00007ffe8da982e8 EFLAGS: 00000246 ORIG_RAX: 0000000000000003
[  134.842200] RAX: 0000000000000000 RBX: 00007fe32f642c70 RCX: 00007fe331f5a560
[  134.842201] RDX: 00000000008f5320 RSI: 0000000001cd4b50 RDI: 0000000000000003
[  134.842202] RBP: 00007fe32f6500f8 R08: 000000000000003c R09: 00000000009343c0
[  134.842203] R10: 0000000000000000 R11: 0000000000000246 R12: 00007fe32f6500d0
[  134.842204] R13: 00000000008f5320 R14: 00000000008f5320 R15: 0000000001cd4770
[  134.842205] Code: c8 00 00 00 45 31 e4 49 39 fe 75 4d eb 50 83 ab d8 00 00 00 01 48 8b 17 48 8b 47 08 48 c7 07 00 00 00 00 48 c7 47 08 00 00 00 00 <48> 89 42 08 48 89 10 0f b6 57 34 8b 47 2c 2b 47 28 83 e2 01 80
[  134.842226] RIP: tcp_close+0x2c6/0x440 RSP: ffffa6630422bde8
[  134.842227] ---[ end trace b7138fc08c831480 ]---

The proposed patch eliminates a potential racing condition.
Before, usb_submit_urb was called and _after_ that, the skb was attached
(dev->tx_skb). So, on a callback it was possible, however unlikely that the
skb was freed before it was set. That way (because dev->tx_skb was not set
to NULL after it was freed), it could happen that a skb from a earlier
transmission was freed a second time (and the skb we should have freed did
not get freed at all)

Now we free the skb directly in ipheth_tx(). It is not passed to the
callback anymore, eliminating the posibility of a double free of the same
skb. Depending on the retval of usb_submit_urb() we use dev_kfree_skb_any()
respectively dev_consume_skb_any() to free the skb.

Signed-off-by: Oliver Zweigle <Oliver.Zweigle@faro.com>
Signed-off-by: Bernd Eckstein <3ernd.Eckstein@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/ipheth.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c
index 7275761a1177..3d8a70d3ea9b 100644
--- a/drivers/net/usb/ipheth.c
+++ b/drivers/net/usb/ipheth.c
@@ -140,7 +140,6 @@ struct ipheth_device {
 	struct usb_device *udev;
 	struct usb_interface *intf;
 	struct net_device *net;
-	struct sk_buff *tx_skb;
 	struct urb *tx_urb;
 	struct urb *rx_urb;
 	unsigned char *tx_buf;
@@ -230,6 +229,7 @@ static void ipheth_rcvbulk_callback(struct urb *urb)
 	case -ENOENT:
 	case -ECONNRESET:
 	case -ESHUTDOWN:
+	case -EPROTO:
 		return;
 	case 0:
 		break;
@@ -281,7 +281,6 @@ static void ipheth_sndbulk_callback(struct urb *urb)
 		dev_err(&dev->intf->dev, "%s: urb status: %d\n",
 		__func__, status);
 
-	dev_kfree_skb_irq(dev->tx_skb);
 	if (status == 0)
 		netif_wake_queue(dev->net);
 	else
@@ -423,7 +422,7 @@ static int ipheth_tx(struct sk_buff *skb, struct net_device *net)
 	if (skb->len > IPHETH_BUF_SIZE) {
 		WARN(1, "%s: skb too large: %d bytes\n", __func__, skb->len);
 		dev->net->stats.tx_dropped++;
-		dev_kfree_skb_irq(skb);
+		dev_kfree_skb_any(skb);
 		return NETDEV_TX_OK;
 	}
 
@@ -443,12 +442,11 @@ static int ipheth_tx(struct sk_buff *skb, struct net_device *net)
 		dev_err(&dev->intf->dev, "%s: usb_submit_urb: %d\n",
 			__func__, retval);
 		dev->net->stats.tx_errors++;
-		dev_kfree_skb_irq(skb);
+		dev_kfree_skb_any(skb);
 	} else {
-		dev->tx_skb = skb;
-
 		dev->net->stats.tx_packets++;
 		dev->net->stats.tx_bytes += skb->len;
+		dev_consume_skb_any(skb);
 		netif_stop_queue(net);
 	}
 
-- 
2.19.2


From ddf98f644602d1aa66b97b8bda83d4b15939f524 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Wed, 21 Nov 2018 16:32:10 +0100
Subject: [PATCH 10/17] net: thunderx: set xdp_prog to NULL if bpf_prog_add
 fails

[ Upstream commit 6d0f60b0f8588fd4380ea5df9601e12fddd55ce2 ]

Set xdp_prog pointer to NULL if bpf_prog_add fails since that routine
reports the error code instead of NULL in case of failure and xdp_prog
pointer value is used in the driver to verify if XDP is currently
enabled.
Moreover report the error code to userspace if nicvf_xdp_setup fails

Fixes: 05c773f52b96 ("net: thunderx: Add basic XDP support")
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/thunder/nicvf_main.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 768f584f8392..88f8a8fa93cd 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -1784,6 +1784,7 @@ static int nicvf_xdp_setup(struct nicvf *nic, struct bpf_prog *prog)
 	bool if_up = netif_running(nic->netdev);
 	struct bpf_prog *old_prog;
 	bool bpf_attached = false;
+	int ret = 0;
 
 	/* For now just support only the usual MTU sized frames */
 	if (prog && (dev->mtu > 1500)) {
@@ -1817,8 +1818,12 @@ static int nicvf_xdp_setup(struct nicvf *nic, struct bpf_prog *prog)
 	if (nic->xdp_prog) {
 		/* Attach BPF program */
 		nic->xdp_prog = bpf_prog_add(nic->xdp_prog, nic->rx_queues - 1);
-		if (!IS_ERR(nic->xdp_prog))
+		if (!IS_ERR(nic->xdp_prog)) {
 			bpf_attached = true;
+		} else {
+			ret = PTR_ERR(nic->xdp_prog);
+			nic->xdp_prog = NULL;
+		}
 	}
 
 	/* Calculate Tx queues needed for XDP and network stack */
@@ -1830,7 +1835,7 @@ static int nicvf_xdp_setup(struct nicvf *nic, struct bpf_prog *prog)
 		netif_trans_update(nic->netdev);
 	}
 
-	return 0;
+	return ret;
 }
 
 static int nicvf_xdp(struct net_device *netdev, struct netdev_bpf *xdp)
-- 
2.19.2


From e4979f6e9b917df284e8f387cdfc087350257ba4 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Tue, 20 Nov 2018 11:39:56 +0000
Subject: [PATCH 11/17] net: skb_scrub_packet(): Scrub offload_fwd_mark

[ Upstream commit b5dd186d10ba59e6b5ba60e42b3b083df56df6f3 ]

When a packet is trapped and the corresponding SKB marked as
already-forwarded, it retains this marking even after it is forwarded
across veth links into another bridge. There, since it ingresses the
bridge over veth, which doesn't have offload_fwd_mark, it triggers a
warning in nbp_switchdev_frame_mark().

Then nbp_switchdev_allowed_egress() decides not to allow egress from
this bridge through another veth, because the SKB is already marked, and
the mark (of 0) of course matches. Thus the packet is incorrectly
blocked.

Solve by resetting offload_fwd_mark() in skb_scrub_packet(). That
function is called from tunnels and also from veth, and thus catches the
cases where traffic is forwarded between bridges and transformed in a
way that invalidates the marking.

Fixes: 6bc506b4fb06 ("bridge: switchdev: Add forward mark support for stacked devices")
Fixes: abf4bb6b63d0 ("skbuff: Add the offload_mr_fwd_mark field")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Suggested-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index f817f336595d..abbbd7fd17fe 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4912,6 +4912,11 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet)
 	nf_reset(skb);
 	nf_reset_trace(skb);
 
+#ifdef CONFIG_NET_SWITCHDEV
+	skb->offload_fwd_mark = 0;
+	skb->offload_mr_fwd_mark = 0;
+#endif
+
 	if (!xnet)
 		return;
 
-- 
2.19.2


From e7fa4426cfce2d3f4fbbf7a637a51fc166d82777 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Thu, 22 Nov 2018 14:36:30 +0800
Subject: [PATCH 12/17] virtio-net: disable guest csum during XDP set

[ Upstream commit e59ff2c49ae16e1d179de679aca81405829aee6c ]

We don't disable VIRTIO_NET_F_GUEST_CSUM if XDP was set. This means we
can receive partial csumed packets with metadata kept in the
vnet_hdr. This may have several side effects:

- It could be overridden by header adjustment, thus is might be not
  correct after XDP processing.
- There's no way to pass such metadata information through
  XDP_REDIRECT to another driver.
- XDP does not support checksum offload right now.

So simply disable guest csum if possible in this the case of XDP.

Fixes: 3f93522ffab2d ("virtio-net: switch off offloads on demand if possible on XDP set")
Reported-by: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Pavel Popa <pashinho1990@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index ddfa3f24204c..9cc51517e16f 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -70,7 +70,8 @@ static const unsigned long guest_offloads[] = {
 	VIRTIO_NET_F_GUEST_TSO4,
 	VIRTIO_NET_F_GUEST_TSO6,
 	VIRTIO_NET_F_GUEST_ECN,
-	VIRTIO_NET_F_GUEST_UFO
+	VIRTIO_NET_F_GUEST_UFO,
+	VIRTIO_NET_F_GUEST_CSUM
 };
 
 struct virtnet_stat_desc {
@@ -2285,9 +2286,6 @@ static int virtnet_clear_guest_offloads(struct virtnet_info *vi)
 	if (!vi->guest_offloads)
 		return 0;
 
-	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_CSUM))
-		offloads = 1ULL << VIRTIO_NET_F_GUEST_CSUM;
-
 	return virtnet_set_guest_offloads(vi, offloads);
 }
 
@@ -2297,8 +2295,6 @@ static int virtnet_restore_guest_offloads(struct virtnet_info *vi)
 
 	if (!vi->guest_offloads)
 		return 0;
-	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_CSUM))
-		offloads |= 1ULL << VIRTIO_NET_F_GUEST_CSUM;
 
 	return virtnet_set_guest_offloads(vi, offloads);
 }
-- 
2.19.2


From ce1a7c36e3e14f7316469ce4fcf960d2b1804e66 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Thu, 22 Nov 2018 14:36:31 +0800
Subject: [PATCH 13/17] virtio-net: fail XDP set if guest csum is negotiated

[ Upstream commit 18ba58e1c234ea1a2d9835ac8c1735d965ce4640 ]

We don't support partial csumed packet since its metadata will be lost
or incorrect during XDP processing. So fail the XDP set if guest_csum
feature is negotiated.

Fixes: f600b6905015 ("virtio_net: Add XDP support")
Reported-by: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Pavel Popa <pashinho1990@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 9cc51517e16f..c2ca6cd3fbe0 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2312,8 +2312,9 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 	    && (virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO4) ||
 	        virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO6) ||
 	        virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_ECN) ||
-		virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_UFO))) {
-		NL_SET_ERR_MSG_MOD(extack, "Can't set XDP while host is implementing LRO, disable LRO first");
+		virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_UFO) ||
+		virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_CSUM))) {
+		NL_SET_ERR_MSG_MOD(extack, "Can't set XDP while host is implementing LRO/CSUM, disable LRO/CSUM first");
 		return -EOPNOTSUPP;
 	}
 
-- 
2.19.2


From b5715921e60c02b104f6156cfa415ae77b568419 Mon Sep 17 00:00:00 2001
From: Tal Gilboa <talgi@mellanox.com>
Date: Wed, 21 Nov 2018 16:28:23 +0200
Subject: [PATCH 14/17] net/dim: Update DIM start sample after each DIM
 iteration

[ Upstream commit 0211dda68a4f6531923a2f72d8e8959207f59fba ]

On every iteration of net_dim, the algorithm may choose to
check for the system state by comparing current data sample
with previous data sample. After each of these comparison,
regardless of the action taken, the sample used as baseline
is needed to be updated.

This patch fixes a bug that causes DIM to take wrong decisions,
due to never updating the baseline sample for comparison between
iterations. This way, DIM always compares current sample with
zeros.

Although this is a functional fix, it also improves and stabilizes
performance as the algorithm works properly now.

Performance:
Tested single UDP TX stream with pktgen:
samples/pktgen/pktgen_sample03_burst_single_flow.sh -i p4p2 -d 1.1.1.1
-m 24:8a:07:88:26:8b -f 3 -b 128

ConnectX-5 100GbE packet rate improved from 15-19Mpps to 19-20Mpps.
Also, toggling between profiles is less frequent with the fix.

Fixes: 8115b750dbcb ("net/dim: use struct net_dim_sample as arg to net_dim")
Signed-off-by: Tal Gilboa <talgi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/net_dim.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/include/linux/net_dim.h b/include/linux/net_dim.h
index c79e859408e6..fd458389f7d1 100644
--- a/include/linux/net_dim.h
+++ b/include/linux/net_dim.h
@@ -406,6 +406,8 @@ static inline void net_dim(struct net_dim *dim,
 		}
 		/* fall through */
 	case NET_DIM_START_MEASURE:
+		net_dim_sample(end_sample.event_ctr, end_sample.pkt_ctr, end_sample.byte_ctr,
+			       &dim->start_sample);
 		dim->state = NET_DIM_MEASURE_IN_PROGRESS;
 		break;
 	case NET_DIM_APPLY_NEW_PROFILE:
-- 
2.19.2


From 742ef972d9a480c717b3892946d1a68ece51fd24 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 20 Nov 2018 05:53:59 -0800
Subject: [PATCH 15/17] tcp: defer SACK compression after DupThresh

[ Upstream commit 86de5921a3d5dd246df661e09bdd0a6131b39ae3 ]

Jean-Louis reported a TCP regression and bisected to recent SACK
compression.

After a loss episode (receiver not able to keep up and dropping
packets because its backlog is full), linux TCP stack is sending
a single SACK (DUPACK).

Sender waits a full RTO timer before recovering losses.

While RFC 6675 says in section 5, "Algorithm Details",

   (2) If DupAcks < DupThresh but IsLost (HighACK + 1) returns true --
       indicating at least three segments have arrived above the current
       cumulative acknowledgment point, which is taken to indicate loss
       -- go to step (4).
...
   (4) Invoke fast retransmit and enter loss recovery as follows:

there are old TCP stacks not implementing this strategy, and
still counting the dupacks before starting fast retransmit.

While these stacks probably perform poorly when receivers implement
LRO/GRO, we should be a little more gentle to them.

This patch makes sure we do not enable SACK compression unless
3 dupacks have been sent since last rcv_nxt update.

Ideally we should even rearm the timer to send one or two
more DUPACK if no more packets are coming, but that will
be work aiming for linux-4.21.

Many thanks to Jean-Louis for bisecting the issue, providing
packet captures and testing this patch.

Fixes: 5d9f4262b7ea ("tcp: add SACK compression")
Reported-by: Jean-Louis Dupond <jean-louis@dupond.be>
Tested-by: Jean-Louis Dupond <jean-louis@dupond.be>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h   |  1 +
 net/ipv4/tcp_input.c  | 14 ++++++++++++--
 net/ipv4/tcp_output.c |  6 +++---
 net/ipv4/tcp_timer.c  |  2 +-
 4 files changed, 17 insertions(+), 6 deletions(-)

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 263e37271afd..d2c8f280e48f 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -196,6 +196,7 @@ struct tcp_sock {
 	u32	rcv_tstamp;	/* timestamp of last received ACK (for keepalives) */
 	u32	lsndtime;	/* timestamp of last sent data packet (for restart window) */
 	u32	last_oow_ack_time;  /* timestamp of last out-of-window ACK */
+	u32	compressed_ack_rcv_nxt;
 
 	u32	tsoffset;	/* timestamp offset */
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 72898cbef43d..664fa7d8f7d9 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4276,7 +4276,7 @@ static void tcp_sack_new_ofo_skb(struct sock *sk, u32 seq, u32 end_seq)
 	 * If the sack array is full, forget about the last one.
 	 */
 	if (this_sack >= TCP_NUM_SACKS) {
-		if (tp->compressed_ack)
+		if (tp->compressed_ack > TCP_FASTRETRANS_THRESH)
 			tcp_send_ack(sk);
 		this_sack--;
 		tp->rx_opt.num_sacks--;
@@ -5196,7 +5196,17 @@ static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible)
 	if (!tcp_is_sack(tp) ||
 	    tp->compressed_ack >= sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr)
 		goto send_now;
-	tp->compressed_ack++;
+
+	if (tp->compressed_ack_rcv_nxt != tp->rcv_nxt) {
+		tp->compressed_ack_rcv_nxt = tp->rcv_nxt;
+		if (tp->compressed_ack > TCP_FASTRETRANS_THRESH)
+			NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPACKCOMPRESSED,
+				      tp->compressed_ack - TCP_FASTRETRANS_THRESH);
+		tp->compressed_ack = 0;
+	}
+
+	if (++tp->compressed_ack <= TCP_FASTRETRANS_THRESH)
+		goto send_now;
 
 	if (hrtimer_is_queued(&tp->compressed_ack_timer))
 		return;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 597dbd749f05..68f65ddf9e3c 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -165,10 +165,10 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts,
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	if (unlikely(tp->compressed_ack)) {
+	if (unlikely(tp->compressed_ack > TCP_FASTRETRANS_THRESH)) {
 		NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPACKCOMPRESSED,
-			      tp->compressed_ack);
-		tp->compressed_ack = 0;
+			      tp->compressed_ack - TCP_FASTRETRANS_THRESH);
+		tp->compressed_ack = TCP_FASTRETRANS_THRESH;
 		if (hrtimer_try_to_cancel(&tp->compressed_ack_timer) == 1)
 			__sock_put(sk);
 	}
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 7fdf222a0bdf..57eae8d70ba1 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -740,7 +740,7 @@ static enum hrtimer_restart tcp_compressed_ack_kick(struct hrtimer *timer)
 
 	bh_lock_sock(sk);
 	if (!sock_owned_by_user(sk)) {
-		if (tp->compressed_ack)
+		if (tp->compressed_ack > TCP_FASTRETRANS_THRESH)
 			tcp_send_ack(sk);
 	} else {
 		if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED,
-- 
2.19.2


From 3bcdc396a4e95f7561ce7d633d8134907585c33b Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 23 Nov 2018 19:41:29 +0100
Subject: [PATCH 16/17] net: phy: add workaround for issue where PHY driver
 doesn't bind to the device

[ Upstream commit c85ddecae6e5e82ca3ae6f20c63f1d865e2ff5ea ]

After switching the r8169 driver to use phylib some user reported that
their network is broken. This was caused by the genphy PHY driver being
used instead of the dedicated PHY driver for the RTL8211B. Users
reported that loading the Realtek PHY driver module upfront fixes the
issue. See also this mail thread:
https://marc.info/?t=154279781800003&r=1&w=2
The issue is quite weird and the root cause seems to be somewhere in
the base driver core. The patch works around the issue and may be
removed once the actual issue is fixed.

The Fixes tag refers to the first reported occurrence of the issue.
The issue itself may have been existing much longer and it may affect
users of other network chips as well. Users typically will recognize
this issue only if their PHY stops working when being used with the
genphy driver.

Fixes: f1e911d5d0df ("r8169: add basic phylib support")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 19ab8a7d1e48..733e35b7c4bb 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1930,6 +1930,14 @@ int phy_driver_register(struct phy_driver *new_driver, struct module *owner)
 	new_driver->mdiodrv.driver.remove = phy_remove;
 	new_driver->mdiodrv.driver.owner = owner;
 
+	/* The following works around an issue where the PHY driver doesn't bind
+	 * to the device, resulting in the genphy driver being used instead of
+	 * the dedicated driver. The root cause of the issue isn't known yet
+	 * and seems to be in the base driver core. Once this is fixed we may
+	 * remove this workaround.
+	 */
+	new_driver->mdiodrv.driver.probe_type = PROBE_FORCE_SYNCHRONOUS;
+
 	retval = driver_register(&new_driver->mdiodrv.driver);
 	if (retval) {
 		pr_err("%s: Error %d in registering driver\n",
-- 
2.19.2


From a4ba3d377bdb36c9a1923ca7074b91713ea3a187 Mon Sep 17 00:00:00 2001
From: Jon Maloy <donmalo99@gmail.com>
Date: Mon, 26 Nov 2018 12:26:14 -0500
Subject: [PATCH 17/17] tipc: fix lockdep warning during node delete

[ Upstream commit ec835f891232d7763dea9da0358f31e24ca6dfb7 ]

We see the following lockdep warning:

[ 2284.078521] ======================================================
[ 2284.078604] WARNING: possible circular locking dependency detected
[ 2284.078604] 4.19.0+ #42 Tainted: G            E
[ 2284.078604] ------------------------------------------------------
[ 2284.078604] rmmod/254 is trying to acquire lock:
[ 2284.078604] 00000000acd94e28 ((&n->timer)#2){+.-.}, at: del_timer_sync+0x5/0xa0
[ 2284.078604]
[ 2284.078604] but task is already holding lock:
[ 2284.078604] 00000000f997afc0 (&(&tn->node_list_lock)->rlock){+.-.}, at: tipc_node_stop+0xac/0x190 [tipc]
[ 2284.078604]
[ 2284.078604] which lock already depends on the new lock.
[ 2284.078604]
[ 2284.078604]
[ 2284.078604] the existing dependency chain (in reverse order) is:
[ 2284.078604]
[ 2284.078604] -> #1 (&(&tn->node_list_lock)->rlock){+.-.}:
[ 2284.078604]        tipc_node_timeout+0x20a/0x330 [tipc]
[ 2284.078604]        call_timer_fn+0xa1/0x280
[ 2284.078604]        run_timer_softirq+0x1f2/0x4d0
[ 2284.078604]        __do_softirq+0xfc/0x413
[ 2284.078604]        irq_exit+0xb5/0xc0
[ 2284.078604]        smp_apic_timer_interrupt+0xac/0x210
[ 2284.078604]        apic_timer_interrupt+0xf/0x20
[ 2284.078604]        default_idle+0x1c/0x140
[ 2284.078604]        do_idle+0x1bc/0x280
[ 2284.078604]        cpu_startup_entry+0x19/0x20
[ 2284.078604]        start_secondary+0x187/0x1c0
[ 2284.078604]        secondary_startup_64+0xa4/0xb0
[ 2284.078604]
[ 2284.078604] -> #0 ((&n->timer)#2){+.-.}:
[ 2284.078604]        del_timer_sync+0x34/0xa0
[ 2284.078604]        tipc_node_delete+0x1a/0x40 [tipc]
[ 2284.078604]        tipc_node_stop+0xcb/0x190 [tipc]
[ 2284.078604]        tipc_net_stop+0x154/0x170 [tipc]
[ 2284.078604]        tipc_exit_net+0x16/0x30 [tipc]
[ 2284.078604]        ops_exit_list.isra.8+0x36/0x70
[ 2284.078604]        unregister_pernet_operations+0x87/0xd0
[ 2284.078604]        unregister_pernet_subsys+0x1d/0x30
[ 2284.078604]        tipc_exit+0x11/0x6f2 [tipc]
[ 2284.078604]        __x64_sys_delete_module+0x1df/0x240
[ 2284.078604]        do_syscall_64+0x66/0x460
[ 2284.078604]        entry_SYSCALL_64_after_hwframe+0x49/0xbe
[ 2284.078604]
[ 2284.078604] other info that might help us debug this:
[ 2284.078604]
[ 2284.078604]  Possible unsafe locking scenario:
[ 2284.078604]
[ 2284.078604]        CPU0                    CPU1
[ 2284.078604]        ----                    ----
[ 2284.078604]   lock(&(&tn->node_list_lock)->rlock);
[ 2284.078604]                                lock((&n->timer)#2);
[ 2284.078604]                                lock(&(&tn->node_list_lock)->rlock);
[ 2284.078604]   lock((&n->timer)#2);
[ 2284.078604]
[ 2284.078604]  *** DEADLOCK ***
[ 2284.078604]
[ 2284.078604] 3 locks held by rmmod/254:
[ 2284.078604]  #0: 000000003368be9b (pernet_ops_rwsem){+.+.}, at: unregister_pernet_subsys+0x15/0x30
[ 2284.078604]  #1: 0000000046ed9c86 (rtnl_mutex){+.+.}, at: tipc_net_stop+0x144/0x170 [tipc]
[ 2284.078604]  #2: 00000000f997afc0 (&(&tn->node_list_lock)->rlock){+.-.}, at: tipc_node_stop+0xac/0x19
[...}

The reason is that the node timer handler sometimes needs to delete a
node which has been disconnected for too long. To do this, it grabs
the lock 'node_list_lock', which may at the same time be held by the
generic node cleanup function, tipc_node_stop(), during module removal.
Since the latter is calling del_timer_sync() inside the same lock, we
have a potential deadlock.

We fix this letting the timer cleanup function use spin_trylock()
instead of just spin_lock(), and when it fails to grab the lock it
just returns so that the timer handler can terminate its execution.
This is safe to do, since tipc_node_stop() anyway is about to
delete both the timer and the node instance.

Fixes: 6a939f365bdb ("tipc: Auto removal of peer down node instance")
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/node.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/tipc/node.c b/net/tipc/node.c
index 2afc4f8c37a7..488019766433 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -584,12 +584,15 @@ static void  tipc_node_clear_links(struct tipc_node *node)
 /* tipc_node_cleanup - delete nodes that does not
  * have active links for NODE_CLEANUP_AFTER time
  */
-static int tipc_node_cleanup(struct tipc_node *peer)
+static bool tipc_node_cleanup(struct tipc_node *peer)
 {
 	struct tipc_net *tn = tipc_net(peer->net);
 	bool deleted = false;
 
-	spin_lock_bh(&tn->node_list_lock);
+	/* If lock held by tipc_node_stop() the node will be deleted anyway */
+	if (!spin_trylock_bh(&tn->node_list_lock))
+		return false;
+
 	tipc_node_write_lock(peer);
 
 	if (!node_is_up(peer) && time_after(jiffies, peer->delete_at)) {
-- 
2.19.2

Re: [PATCHES] Networking

[Greg KH]

On Sun, Dec 02, 2018 at 11:01:21PM -0800, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.14 and
> v4.19 -stable, respectively.

All queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 107 bytes --]


Please queue up the following networking bug fixes for v4.14 and
v4.19 -stable, respectively.

Thank you.

[-- Attachment #2: net_414.mbox --]
[-- Type: Application/Octet-Stream, Size: 47310 bytes --]

From 5a944d6abe4d441f5b9512409e2b3e782f83bce3 Mon Sep 17 00:00:00 2001
From: Jiri Wiesner <jwiesner@suse.com>
Date: Wed, 5 Dec 2018 16:55:29 +0100
Subject: [PATCH 01/15] ipv4: ipv6: netfilter: Adjust the frag mem limit when
 truesize changes

[ Upstream commit ebaf39e6032faf77218220707fc3fa22487784e0 ]

The *_frag_reasm() functions are susceptible to miscalculating the byte
count of packet fragments in case the truesize of a head buffer changes.
The truesize member may be changed by the call to skb_unclone(), leaving
the fragment memory limit counter unbalanced even if all fragments are
processed. This miscalculation goes unnoticed as long as the network
namespace which holds the counter is not destroyed.

Should an attempt be made to destroy a network namespace that holds an
unbalanced fragment memory limit counter the cleanup of the namespace
never finishes. The thread handling the cleanup gets stuck in
inet_frags_exit_net() waiting for the percpu counter to reach zero. The
thread is usually in running state with a stacktrace similar to:

 PID: 1073   TASK: ffff880626711440  CPU: 1   COMMAND: "kworker/u48:4"
  #5 [ffff880621563d48] _raw_spin_lock at ffffffff815f5480
  #6 [ffff880621563d48] inet_evict_bucket at ffffffff8158020b
  #7 [ffff880621563d80] inet_frags_exit_net at ffffffff8158051c
  #8 [ffff880621563db0] ops_exit_list at ffffffff814f5856
  #9 [ffff880621563dd8] cleanup_net at ffffffff814f67c0
 #10 [ffff880621563e38] process_one_work at ffffffff81096f14

It is not possible to create new network namespaces, and processes
that call unshare() end up being stuck in uninterruptible sleep state
waiting to acquire the net_mutex.

The bug was observed in the IPv6 netfilter code by Per Sundstrom.
I thank him for his analysis of the problem. The parts of this patch
that apply to IPv4 and IPv6 fragment reassembly are preemptive measures.

Signed-off-by: Jiri Wiesner <jwiesner@suse.com>
Reported-by: Per Sundstrom <per.sundstrom@redqube.se>
Acked-by: Peter Oskolkov <posk@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_fragment.c                  | 7 +++++++
 net/ipv6/netfilter/nf_conntrack_reasm.c | 8 +++++++-
 net/ipv6/reassembly.c                   | 8 +++++++-
 3 files changed, 21 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index cb8fa5d7afe1..f686d7761acb 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -513,6 +513,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
 	struct rb_node *rbn;
 	int len;
 	int ihlen;
+	int delta;
 	int err;
 	u8 ecn;
 
@@ -554,10 +555,16 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
 	if (len > 65535)
 		goto out_oversize;
 
+	delta = - head->truesize;
+
 	/* Head of list must not be cloned. */
 	if (skb_unclone(head, GFP_ATOMIC))
 		goto out_nomem;
 
+	delta += head->truesize;
+	if (delta)
+		add_frag_mem_limit(qp->q.net, delta);
+
 	/* If the first fragment is fragmented itself, we split
 	 * it to two chunks: the first with data and paged part
 	 * and the second, holding only fragments. */
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 611d406c4656..237fb04c6716 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -349,7 +349,7 @@ static bool
 nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev,  struct net_device *dev)
 {
 	struct sk_buff *fp, *head = fq->q.fragments;
-	int    payload_len;
+	int    payload_len, delta;
 	u8 ecn;
 
 	inet_frag_kill(&fq->q);
@@ -371,10 +371,16 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev,  struct net_devic
 		return false;
 	}
 
+	delta = - head->truesize;
+
 	/* Head of list must not be cloned. */
 	if (skb_unclone(head, GFP_ATOMIC))
 		return false;
 
+	delta += head->truesize;
+	if (delta)
+		add_frag_mem_limit(fq->q.net, delta);
+
 	/* If the first fragment is fragmented itself, we split
 	 * it to two chunks: the first with data and paged part
 	 * and the second, holding only fragments. */
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index ede0061b6f5d..2a8c680b67cd 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -348,7 +348,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
 {
 	struct net *net = container_of(fq->q.net, struct net, ipv6.frags);
 	struct sk_buff *fp, *head = fq->q.fragments;
-	int    payload_len;
+	int    payload_len, delta;
 	unsigned int nhoff;
 	int sum_truesize;
 	u8 ecn;
@@ -389,10 +389,16 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
 	if (payload_len > IPV6_MAXPLEN)
 		goto out_oversize;
 
+	delta = - head->truesize;
+
 	/* Head of list must not be cloned. */
 	if (skb_unclone(head, GFP_ATOMIC))
 		goto out_oom;
 
+	delta += head->truesize;
+	if (delta)
+		add_frag_mem_limit(fq->q.net, delta);
+
 	/* If the first fragment is fragmented itself, we split
 	 * it to two chunks: the first with data and paged part
 	 * and the second, holding only fragments. */
-- 
2.19.2


From 93bf15ae5a3297b3c2b62c5f23e3014ffc385fd3 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Thu, 6 Dec 2018 19:30:36 +0100
Subject: [PATCH 02/15] ipv6: Check available headroom in ip6_xmit() even
 without options

[ Upstream commit 66033f47ca60294a95fc85ec3a3cc909dab7b765 ]

Even if we send an IPv6 packet without options, MAX_HEADER might not be
enough to account for the additional headroom required by alignment of
hardware headers.

On a configuration without HYPERV_NET, WLAN, AX25, and with IPV6_TUNNEL,
sending short SCTP packets over IPv4 over L2TP over IPv6, we start with
100 bytes of allocated headroom in sctp_packet_transmit(), end up with 54
bytes after l2tp_xmit_skb(), and 14 bytes in ip6_finish_output2().

Those would be enough to append our 14 bytes header, but we're going to
align that to 16 bytes, and write 2 bytes out of the allocated slab in
neigh_hh_output().

KASan says:

[  264.967848] ==================================================================
[  264.967861] BUG: KASAN: slab-out-of-bounds in ip6_finish_output2+0x1aec/0x1c70
[  264.967866] Write of size 16 at addr 000000006af1c7fe by task netperf/6201
[  264.967870]
[  264.967876] CPU: 0 PID: 6201 Comm: netperf Not tainted 4.20.0-rc4+ #1
[  264.967881] Hardware name: IBM 2827 H43 400 (z/VM 6.4.0)
[  264.967887] Call Trace:
[  264.967896] ([<00000000001347d6>] show_stack+0x56/0xa0)
[  264.967903]  [<00000000017e379c>] dump_stack+0x23c/0x290
[  264.967912]  [<00000000007bc594>] print_address_description+0xf4/0x290
[  264.967919]  [<00000000007bc8fc>] kasan_report+0x13c/0x240
[  264.967927]  [<000000000162f5e4>] ip6_finish_output2+0x1aec/0x1c70
[  264.967935]  [<000000000163f890>] ip6_finish_output+0x430/0x7f0
[  264.967943]  [<000000000163fe44>] ip6_output+0x1f4/0x580
[  264.967953]  [<000000000163882a>] ip6_xmit+0xfea/0x1ce8
[  264.967963]  [<00000000017396e2>] inet6_csk_xmit+0x282/0x3f8
[  264.968033]  [<000003ff805fb0ba>] l2tp_xmit_skb+0xe02/0x13e0 [l2tp_core]
[  264.968037]  [<000003ff80631192>] l2tp_eth_dev_xmit+0xda/0x150 [l2tp_eth]
[  264.968041]  [<0000000001220020>] dev_hard_start_xmit+0x268/0x928
[  264.968069]  [<0000000001330e8e>] sch_direct_xmit+0x7ae/0x1350
[  264.968071]  [<000000000122359c>] __dev_queue_xmit+0x2b7c/0x3478
[  264.968075]  [<00000000013d2862>] ip_finish_output2+0xce2/0x11a0
[  264.968078]  [<00000000013d9b14>] ip_finish_output+0x56c/0x8c8
[  264.968081]  [<00000000013ddd1e>] ip_output+0x226/0x4c0
[  264.968083]  [<00000000013dbd6c>] __ip_queue_xmit+0x894/0x1938
[  264.968100]  [<000003ff80bc3a5c>] sctp_packet_transmit+0x29d4/0x3648 [sctp]
[  264.968116]  [<000003ff80b7bf68>] sctp_outq_flush_ctrl.constprop.5+0x8d0/0xe50 [sctp]
[  264.968131]  [<000003ff80b7c716>] sctp_outq_flush+0x22e/0x7d8 [sctp]
[  264.968146]  [<000003ff80b35c68>] sctp_cmd_interpreter.isra.16+0x530/0x6800 [sctp]
[  264.968161]  [<000003ff80b3410a>] sctp_do_sm+0x222/0x648 [sctp]
[  264.968177]  [<000003ff80bbddac>] sctp_primitive_ASSOCIATE+0xbc/0xf8 [sctp]
[  264.968192]  [<000003ff80b93328>] __sctp_connect+0x830/0xc20 [sctp]
[  264.968208]  [<000003ff80bb11ce>] sctp_inet_connect+0x2e6/0x378 [sctp]
[  264.968212]  [<0000000001197942>] __sys_connect+0x21a/0x450
[  264.968215]  [<000000000119aff8>] sys_socketcall+0x3d0/0xb08
[  264.968218]  [<000000000184ea7a>] system_call+0x2a2/0x2c0

[...]

Just like ip_finish_output2() does for IPv4, check that we have enough
headroom in ip6_xmit(), and reallocate it if we don't.

This issue is older than git history.

Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_output.c | 42 +++++++++++++++++++++---------------------
 1 file changed, 21 insertions(+), 21 deletions(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 9ab1e0fcbc13..7ca8264cbdf9 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -195,37 +195,37 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 	const struct ipv6_pinfo *np = inet6_sk(sk);
 	struct in6_addr *first_hop = &fl6->daddr;
 	struct dst_entry *dst = skb_dst(skb);
+	unsigned int head_room;
 	struct ipv6hdr *hdr;
 	u8  proto = fl6->flowi6_proto;
 	int seg_len = skb->len;
 	int hlimit = -1;
 	u32 mtu;
 
-	if (opt) {
-		unsigned int head_room;
+	head_room = sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dst->dev);
+	if (opt)
+		head_room += opt->opt_nflen + opt->opt_flen;
 
-		/* First: exthdrs may take lots of space (~8K for now)
-		   MAX_HEADER is not enough.
-		 */
-		head_room = opt->opt_nflen + opt->opt_flen;
-		seg_len += head_room;
-		head_room += sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dst->dev);
-
-		if (skb_headroom(skb) < head_room) {
-			struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room);
-			if (!skb2) {
-				IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
-					      IPSTATS_MIB_OUTDISCARDS);
-				kfree_skb(skb);
-				return -ENOBUFS;
-			}
-			if (skb->sk)
-				skb_set_owner_w(skb2, skb->sk);
-			consume_skb(skb);
-			skb = skb2;
+	if (unlikely(skb_headroom(skb) < head_room)) {
+		struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room);
+		if (!skb2) {
+			IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
+				      IPSTATS_MIB_OUTDISCARDS);
+			kfree_skb(skb);
+			return -ENOBUFS;
 		}
+		if (skb->sk)
+			skb_set_owner_w(skb2, skb->sk);
+		consume_skb(skb);
+		skb = skb2;
+	}
+
+	if (opt) {
+		seg_len += opt->opt_nflen + opt->opt_flen;
+
 		if (opt->opt_flen)
 			ipv6_push_frag_opts(skb, opt, &proto);
+
 		if (opt->opt_nflen)
 			ipv6_push_nfrag_opts(skb, opt, &proto, &first_hop,
 					     &fl6->saddr);
-- 
2.19.2


From d58bc88e5f59474fc237449cac5c87c883b79d99 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Thu, 6 Dec 2018 19:30:37 +0100
Subject: [PATCH 03/15] neighbour: Avoid writing before skb->head in
 neigh_hh_output()

[ Upstream commit e6ac64d4c4d095085d7dd71cbd05704ac99829b2 ]

While skb_push() makes the kernel panic if the skb headroom is less than
the unaligned hardware header size, it will proceed normally in case we
copy more than that because of alignment, and we'll silently corrupt
adjacent slabs.

In the case fixed by the previous patch,
"ipv6: Check available headroom in ip6_xmit() even without options", we
end up in neigh_hh_output() with 14 bytes headroom, 14 bytes hardware
header and write 16 bytes, starting 2 bytes before the allocated buffer.

Always check we're not writing before skb->head and, if the headroom is
not enough, warn and drop the packet.

v2:
 - instead of panicking with BUG_ON(), WARN_ON_ONCE() and drop the packet
   (Eric Dumazet)
 - if we avoid the panic, though, we need to explicitly check the headroom
   before the memcpy(), otherwise we'll have corrupted slabs on a running
   kernel, after we warn
 - use __skb_push() instead of skb_push(), as the headroom check is
   already implemented here explicitly (Eric Dumazet)

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/neighbour.h | 28 +++++++++++++++++++++++-----
 1 file changed, 23 insertions(+), 5 deletions(-)

diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index a964366a7ef5..393099b1901a 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -452,6 +452,7 @@ static inline int neigh_hh_bridge(struct hh_cache *hh, struct sk_buff *skb)
 
 static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb)
 {
+	unsigned int hh_alen = 0;
 	unsigned int seq;
 	unsigned int hh_len;
 
@@ -459,16 +460,33 @@ static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb
 		seq = read_seqbegin(&hh->hh_lock);
 		hh_len = hh->hh_len;
 		if (likely(hh_len <= HH_DATA_MOD)) {
-			/* this is inlined by gcc */
-			memcpy(skb->data - HH_DATA_MOD, hh->hh_data, HH_DATA_MOD);
+			hh_alen = HH_DATA_MOD;
+
+			/* skb_push() would proceed silently if we have room for
+			 * the unaligned size but not for the aligned size:
+			 * check headroom explicitly.
+			 */
+			if (likely(skb_headroom(skb) >= HH_DATA_MOD)) {
+				/* this is inlined by gcc */
+				memcpy(skb->data - HH_DATA_MOD, hh->hh_data,
+				       HH_DATA_MOD);
+			}
 		} else {
-			unsigned int hh_alen = HH_DATA_ALIGN(hh_len);
+			hh_alen = HH_DATA_ALIGN(hh_len);
 
-			memcpy(skb->data - hh_alen, hh->hh_data, hh_alen);
+			if (likely(skb_headroom(skb) >= hh_alen)) {
+				memcpy(skb->data - hh_alen, hh->hh_data,
+				       hh_alen);
+			}
 		}
 	} while (read_seqretry(&hh->hh_lock, seq));
 
-	skb_push(skb, hh_len);
+	if (WARN_ON_ONCE(skb_headroom(skb) < hh_alen)) {
+		kfree_skb(skb);
+		return NET_XMIT_DROP;
+	}
+
+	__skb_push(skb, hh_len);
 	return dev_queue_xmit(skb);
 }
 
-- 
2.19.2


From 05a8294d472ea300340d5ded428f8686dd243d24 Mon Sep 17 00:00:00 2001
From: Shmulik Ladkani <shmulik@metanetworks.com>
Date: Fri, 7 Dec 2018 09:50:17 +0200
Subject: [PATCH 04/15] ipv6: sr: properly initialize flowi6 prior passing to
 ip6_route_output

[ Upstream commit 1b4e5ad5d6b9f15cd0b5121f86d4719165958417 ]

In 'seg6_output', stack variable 'struct flowi6 fl6' was missing
initialization.

Fixes: 6c8702c60b88 ("ipv6: sr: add support for SRH encapsulation and injection with lwtunnels")
Signed-off-by: Shmulik Ladkani <shmulik.ladkani@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/seg6_iptunnel.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index bf4763fd68c2..cf9342bfe95a 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -327,6 +327,7 @@ static int seg6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 		struct ipv6hdr *hdr = ipv6_hdr(skb);
 		struct flowi6 fl6;
 
+		memset(&fl6, 0, sizeof(fl6));
 		fl6.daddr = hdr->daddr;
 		fl6.saddr = hdr->saddr;
 		fl6.flowlabel = ip6_flowinfo(hdr);
-- 
2.19.2


From 1fb2cb5ef9c2cbaa760da58199d009cd771e9b7a Mon Sep 17 00:00:00 2001
From: Su Yanjun <suyj.fnst@cn.fujitsu.com>
Date: Mon, 3 Dec 2018 15:33:07 +0800
Subject: [PATCH 05/15] net: 8139cp: fix a BUG triggered by changing mtu with
 network traffic

[ Upstream commit a5d4a89245ead1f37ed135213653c5beebea4237 ]

When changing mtu many times with traffic, a bug is triggered:

[ 1035.684037] kernel BUG at lib/dynamic_queue_limits.c:26!
[ 1035.684042] invalid opcode: 0000 [#1] SMP
[ 1035.684049] Modules linked in: loop binfmt_misc 8139cp(OE) macsec
tcp_diag udp_diag inet_diag unix_diag af_packet_diag netlink_diag tcp_lp
fuse uinput xt_CHECKSUM iptable_mangle ipt_MASQUERADE
nf_nat_masquerade_ipv4 iptable_nat nf_nat_ipv4 nf_nat nf_conntrack_ipv4
nf_defrag_ipv4 xt_conntrack nf_conntrack ipt_REJECT nf_reject_ipv4 tun
bridge stp llc ebtable_filter ebtables ip6table_filter devlink
ip6_tables iptable_filter sunrpc snd_hda_codec_generic snd_hda_intel
snd_hda_codec snd_hda_core snd_hwdep ppdev snd_seq iosf_mbi crc32_pclmul
parport_pc snd_seq_device ghash_clmulni_intel parport snd_pcm
aesni_intel joydev lrw snd_timer virtio_balloon sg gf128mul glue_helper
ablk_helper cryptd snd soundcore i2c_piix4 pcspkr ip_tables xfs
libcrc32c sr_mod sd_mod cdrom crc_t10dif crct10dif_generic ata_generic
[ 1035.684102]  pata_acpi virtio_console qxl drm_kms_helper syscopyarea
sysfillrect sysimgblt floppy fb_sys_fops crct10dif_pclmul
crct10dif_common ttm crc32c_intel serio_raw ata_piix drm libata 8139too
virtio_pci drm_panel_orientation_quirks virtio_ring virtio mii dm_mirror
dm_region_hash dm_log dm_mod [last unloaded: 8139cp]
[ 1035.684132] CPU: 9 PID: 25140 Comm: if-mtu-change Kdump: loaded
Tainted: G           OE  ------------ T 3.10.0-957.el7.x86_64 #1
[ 1035.684134] Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
[ 1035.684136] task: ffff8f59b1f5a080 ti: ffff8f5a2e32c000 task.ti:
ffff8f5a2e32c000
[ 1035.684149] RIP: 0010:[<ffffffffba3a40d0>]  [<ffffffffba3a40d0>]
dql_completed+0x180/0x190
[ 1035.684162] RSP: 0000:ffff8f5a75483e50  EFLAGS: 00010093
[ 1035.684162] RAX: 00000000000000c2 RBX: ffff8f5a6f91c000 RCX:
0000000000000000
[ 1035.684162] RDX: 0000000000000000 RSI: 0000000000000184 RDI:
ffff8f599fea3ec0
[ 1035.684162] RBP: ffff8f5a75483ea8 R08: 00000000000000c2 R09:
0000000000000000
[ 1035.684162] R10: 00000000000616ef R11: ffff8f5a75483b56 R12:
ffff8f599fea3e00
[ 1035.684162] R13: 0000000000000001 R14: 0000000000000000 R15:
0000000000000184
[ 1035.684162] FS:  00007fa8434de740(0000) GS:ffff8f5a75480000(0000)
knlGS:0000000000000000
[ 1035.684162] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 1035.684162] CR2: 00000000004305d0 CR3: 000000024eb66000 CR4:
00000000001406e0
[ 1035.684162] Call Trace:
[ 1035.684162]  <IRQ>
[ 1035.684162]  [<ffffffffc08cbaf8>] ? cp_interrupt+0x478/0x580 [8139cp]
[ 1035.684162]  [<ffffffffba14a294>]
__handle_irq_event_percpu+0x44/0x1c0
[ 1035.684162]  [<ffffffffba14a442>] handle_irq_event_percpu+0x32/0x80
[ 1035.684162]  [<ffffffffba14a4cc>] handle_irq_event+0x3c/0x60
[ 1035.684162]  [<ffffffffba14db29>] handle_fasteoi_irq+0x59/0x110
[ 1035.684162]  [<ffffffffba02e554>] handle_irq+0xe4/0x1a0
[ 1035.684162]  [<ffffffffba7795dd>] do_IRQ+0x4d/0xf0
[ 1035.684162]  [<ffffffffba76b362>] common_interrupt+0x162/0x162
[ 1035.684162]  <EOI>
[ 1035.684162]  [<ffffffffba0c2ae4>] ? __wake_up_bit+0x24/0x70
[ 1035.684162]  [<ffffffffba1e46f5>] ? do_set_pte+0xd5/0x120
[ 1035.684162]  [<ffffffffba1b64fb>] unlock_page+0x2b/0x30
[ 1035.684162]  [<ffffffffba1e4879>] do_read_fault.isra.61+0x139/0x1b0
[ 1035.684162]  [<ffffffffba1e9134>] handle_pte_fault+0x2f4/0xd10
[ 1035.684162]  [<ffffffffba1ebc6d>] handle_mm_fault+0x39d/0x9b0
[ 1035.684162]  [<ffffffffba76f5e3>] __do_page_fault+0x203/0x500
[ 1035.684162]  [<ffffffffba76f9c6>] trace_do_page_fault+0x56/0x150
[ 1035.684162]  [<ffffffffba76ef42>] do_async_page_fault+0x22/0xf0
[ 1035.684162]  [<ffffffffba76b788>] async_page_fault+0x28/0x30
[ 1035.684162] Code: 54 c7 47 54 ff ff ff ff 44 0f 49 ce 48 8b 35 48 2f
9c 00 48 89 77 58 e9 fe fe ff ff 0f 1f 80 00 00 00 00 41 89 d1 e9 ef fe
ff ff <0f> 0b 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 55 8d 42 ff 48
[ 1035.684162] RIP  [<ffffffffba3a40d0>] dql_completed+0x180/0x190
[ 1035.684162]  RSP <ffff8f5a75483e50>

It's not the same as in 7fe0ee09 patch described.
As 8139cp uses shared irq mode, other device irq will trigger
cp_interrupt to execute.

cp_change_mtu
 -> cp_close
 -> cp_open

In cp_close routine  just before free_irq(), some interrupt may occur.
In my environment, cp_interrupt exectutes and IntrStatus is 0x4,
exactly TxOk. That will cause cp_tx to wake device queue.

As device queue is started, cp_start_xmit and cp_open will run at same
time which will cause kernel BUG.

For example:
[#] for tx descriptor

At start:

[#][#][#]
num_queued=3

After cp_init_hw->cp_start_hw->netdev_reset_queue:

[#][#][#]
num_queued=0

When 8139cp starts to work then cp_tx will check
num_queued mismatchs the complete_bytes.

The patch will check IntrMask before check IntrStatus in cp_interrupt.
When 8139cp interrupt is disabled, just return.

Signed-off-by: Su Yanjun <suyj.fnst@cn.fujitsu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/8139cp.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c
index e7ab23e87de2..d1e88712a275 100644
--- a/drivers/net/ethernet/realtek/8139cp.c
+++ b/drivers/net/ethernet/realtek/8139cp.c
@@ -571,6 +571,7 @@ static irqreturn_t cp_interrupt (int irq, void *dev_instance)
 	struct cp_private *cp;
 	int handled = 0;
 	u16 status;
+	u16 mask;
 
 	if (unlikely(dev == NULL))
 		return IRQ_NONE;
@@ -578,6 +579,10 @@ static irqreturn_t cp_interrupt (int irq, void *dev_instance)
 
 	spin_lock(&cp->lock);
 
+	mask = cpr16(IntrMask);
+	if (!mask)
+		goto out_unlock;
+
 	status = cpr16(IntrStatus);
 	if (!status || (status == 0xFFFF))
 		goto out_unlock;
-- 
2.19.2


From 26a0e744ed1a30f545a96218f1ad8d5c5fa7d9ca Mon Sep 17 00:00:00 2001
From: Tarick Bedeir <tarick@google.com>
Date: Fri, 7 Dec 2018 00:30:26 -0800
Subject: [PATCH 06/15] net/mlx4_core: Correctly set PFC param if global pause
 is turned off.

[ Upstream commit bd5122cd1e0644d8bd8dd84517c932773e999766 ]

rx_ppp and tx_ppp can be set between 0 and 255, so don't clamp to 1.

Fixes: 6e8814ceb7e8 ("net/mlx4_en: Fix mixed PFC and Global pause user control requests")
Signed-off-by: Tarick Bedeir <tarick@google.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 5fe56dc4cfae..5363cee88a0a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1070,8 +1070,8 @@ static int mlx4_en_set_pauseparam(struct net_device *dev,
 
 	tx_pause = !!(pause->tx_pause);
 	rx_pause = !!(pause->rx_pause);
-	rx_ppp = priv->prof->rx_ppp && !(tx_pause || rx_pause);
-	tx_ppp = priv->prof->tx_ppp && !(tx_pause || rx_pause);
+	rx_ppp = (tx_pause || rx_pause) ? 0 : priv->prof->rx_ppp;
+	tx_ppp = (tx_pause || rx_pause) ? 0 : priv->prof->tx_ppp;
 
 	err = mlx4_SET_PORT_general(mdev->dev, priv->port,
 				    priv->rx_skb_size + ETH_FCS_LEN,
-- 
2.19.2


From 749e1bcb3214d84e449e69feb38f8947f497b925 Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Sun, 2 Dec 2018 14:34:36 +0200
Subject: [PATCH 07/15] net/mlx4_en: Change min MTU size to ETH_MIN_MTU

[ Upstream commit 24be19e47779d604d1492c114459dca9a92acf78 ]

NIC driver minimal MTU size shall be set to ETH_MIN_MTU, as defined in
the RFC791 and in the network stack. Remove old mlx4_en only define for
it, which was set to wrong value.

Fixes: b80f71f5816f ("ethernet/mellanox: use core min/max MTU checking")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 4 ++--
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h   | 1 -
 2 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index faa4bd21f148..0fb85d71c11b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -3505,8 +3505,8 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 		dev->gso_partial_features = NETIF_F_GSO_UDP_TUNNEL_CSUM;
 	}
 
-	/* MTU range: 46 - hw-specific max */
-	dev->min_mtu = MLX4_EN_MIN_MTU;
+	/* MTU range: 68 - hw-specific max */
+	dev->min_mtu = ETH_MIN_MTU;
 	dev->max_mtu = priv->max_mtu;
 
 	mdev->pndev[port] = dev;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 09f4764a3f39..bdd87438a354 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -157,7 +157,6 @@
 #define HEADER_COPY_SIZE       (128 - NET_IP_ALIGN)
 #define MLX4_LOOPBACK_TEST_PAYLOAD (HEADER_COPY_SIZE - ETH_HLEN)
 
-#define MLX4_EN_MIN_MTU		46
 /* VLAN_HLEN is added twice,to support skb vlan tagged with multiple
  * headers. (For example: ETH_P_8021Q and ETH_P_8021AD).
  */
-- 
2.19.2


From 9e6a7684eb554972be58c250e5c1635f43124e78 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 3 Dec 2018 08:19:33 +0100
Subject: [PATCH 08/15] net: phy: don't allow __set_phy_supported to add
 unsupported modes

[ Upstream commit d2a36971ef595069b7a600d1144c2e0881a930a1 ]

Currently __set_phy_supported allows to add modes w/o checking whether
the PHY supports them. This is wrong, it should never add modes but
only remove modes we don't want to support.

The commit marked as fixed didn't do anything wrong, it just copied
existing functionality to the helper which is being fixed now.

Fixes: f3a6bd393c2c ("phylib: Add phy_set_max_speed helper")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 19 ++++++++-----------
 1 file changed, 8 insertions(+), 11 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index fe76e2c4022a..5b56a86e88ff 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1703,20 +1703,17 @@ EXPORT_SYMBOL(genphy_loopback);
 
 static int __set_phy_supported(struct phy_device *phydev, u32 max_speed)
 {
-	phydev->supported &= ~(PHY_1000BT_FEATURES | PHY_100BT_FEATURES |
-			       PHY_10BT_FEATURES);
-
 	switch (max_speed) {
-	default:
-		return -ENOTSUPP;
-	case SPEED_1000:
-		phydev->supported |= PHY_1000BT_FEATURES;
+	case SPEED_10:
+		phydev->supported &= ~PHY_100BT_FEATURES;
 		/* fall through */
 	case SPEED_100:
-		phydev->supported |= PHY_100BT_FEATURES;
-		/* fall through */
-	case SPEED_10:
-		phydev->supported |= PHY_10BT_FEATURES;
+		phydev->supported &= ~PHY_1000BT_FEATURES;
+		break;
+	case SPEED_1000:
+		break;
+	default:
+		return -ENOTSUPP;
 	}
 
 	return 0;
-- 
2.19.2


From 292562da0eca5d53dc46ef56bc9dcff8d60ec648 Mon Sep 17 00:00:00 2001
From: Christoph Paasch <cpaasch@apple.com>
Date: Thu, 29 Nov 2018 16:01:04 -0800
Subject: [PATCH 09/15] net: Prevent invalid access to skb->prev in
 __qdisc_drop_all

[ Upstream commit 9410d386d0a829ace9558336263086c2fbbe8aed ]

__qdisc_drop_all() accesses skb->prev to get to the tail of the
segment-list.

With commit 68d2f84a1368 ("net: gro: properly remove skb from list")
the skb-list handling has been changed to set skb->next to NULL and set
the list-poison on skb->prev.

With that change, __qdisc_drop_all() will panic when it tries to
dereference skb->prev.

Since commit 992cba7e276d ("net: Add and use skb_list_del_init().")
__list_del_entry is used, leaving skb->prev unchanged (thus,
pointing to the list-head if it's the first skb of the list).
This will make __qdisc_drop_all modify the next-pointer of the list-head
and result in a panic later on:

[   34.501053] general protection fault: 0000 [#1] SMP KASAN PTI
[   34.501968] CPU: 2 PID: 0 Comm: swapper/2 Not tainted 4.20.0-rc2.mptcp #108
[   34.502887] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 0.5.1 01/01/2011
[   34.504074] RIP: 0010:dev_gro_receive+0x343/0x1f90
[   34.504751] Code: e0 48 c1 e8 03 42 80 3c 30 00 0f 85 4a 1c 00 00 4d 8b 24 24 4c 39 65 d0 0f 84 0a 04 00 00 49 8d 7c 24 38 48 89 f8 48 c1 e8 03 <42> 0f b6 04 30 84 c0 74 08 3c 04
[   34.507060] RSP: 0018:ffff8883af507930 EFLAGS: 00010202
[   34.507761] RAX: 0000000000000007 RBX: ffff8883970b2c80 RCX: 1ffff11072e165a6
[   34.508640] RDX: 1ffff11075867008 RSI: ffff8883ac338040 RDI: 0000000000000038
[   34.509493] RBP: ffff8883af5079d0 R08: ffff8883970b2d40 R09: 0000000000000062
[   34.510346] R10: 0000000000000034 R11: 0000000000000000 R12: 0000000000000000
[   34.511215] R13: 0000000000000000 R14: dffffc0000000000 R15: ffff8883ac338008
[   34.512082] FS:  0000000000000000(0000) GS:ffff8883af500000(0000) knlGS:0000000000000000
[   34.513036] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   34.513741] CR2: 000055ccc3e9d020 CR3: 00000003abf32000 CR4: 00000000000006e0
[   34.514593] Call Trace:
[   34.514893]  <IRQ>
[   34.515157]  napi_gro_receive+0x93/0x150
[   34.515632]  receive_buf+0x893/0x3700
[   34.516094]  ? __netif_receive_skb+0x1f/0x1a0
[   34.516629]  ? virtnet_probe+0x1b40/0x1b40
[   34.517153]  ? __stable_node_chain+0x4d0/0x850
[   34.517684]  ? kfree+0x9a/0x180
[   34.518067]  ? __kasan_slab_free+0x171/0x190
[   34.518582]  ? detach_buf+0x1df/0x650
[   34.519061]  ? lapic_next_event+0x5a/0x90
[   34.519539]  ? virtqueue_get_buf_ctx+0x280/0x7f0
[   34.520093]  virtnet_poll+0x2df/0xd60
[   34.520533]  ? receive_buf+0x3700/0x3700
[   34.521027]  ? qdisc_watchdog_schedule_ns+0xd5/0x140
[   34.521631]  ? htb_dequeue+0x1817/0x25f0
[   34.522107]  ? sch_direct_xmit+0x142/0xf30
[   34.522595]  ? virtqueue_napi_schedule+0x26/0x30
[   34.523155]  net_rx_action+0x2f6/0xc50
[   34.523601]  ? napi_complete_done+0x2f0/0x2f0
[   34.524126]  ? kasan_check_read+0x11/0x20
[   34.524608]  ? _raw_spin_lock+0x7d/0xd0
[   34.525070]  ? _raw_spin_lock_bh+0xd0/0xd0
[   34.525563]  ? kvm_guest_apic_eoi_write+0x6b/0x80
[   34.526130]  ? apic_ack_irq+0x9e/0xe0
[   34.526567]  __do_softirq+0x188/0x4b5
[   34.527015]  irq_exit+0x151/0x180
[   34.527417]  do_IRQ+0xdb/0x150
[   34.527783]  common_interrupt+0xf/0xf
[   34.528223]  </IRQ>

This patch makes sure that skb->prev is set to NULL when entering
netem_enqueue.

Cc: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Cc: Tyler Hicks <tyhicks@canonical.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Fixes: 68d2f84a1368 ("net: gro: properly remove skb from list")
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Christoph Paasch <cpaasch@apple.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_netem.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 3d325b840802..3f4f0b946798 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -436,6 +436,9 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	int count = 1;
 	int rc = NET_XMIT_SUCCESS;
 
+	/* Do not fool qdisc_drop_all() */
+	skb->prev = NULL;
+
 	/* Random duplication */
 	if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor))
 		++count;
-- 
2.19.2


From 3300ad4b80823f509547e25a81c416063bcf13f3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 4 Dec 2018 09:40:35 -0800
Subject: [PATCH 10/15] rtnetlink: ndo_dflt_fdb_dump() only work for
 ARPHRD_ETHER devices

[ Upstream commit 688838934c231bb08f46db687e57f6d8bf82709c ]

kmsan was able to trigger a kernel-infoleak using a gre device [1]

nlmsg_populate_fdb_fill() has a hard coded assumption
that dev->addr_len is ETH_ALEN, as normally guaranteed
for ARPHRD_ETHER devices.

A similar issue was fixed recently in commit da71577545a5
("rtnetlink: Disallow FDB configuration for non-Ethernet device")

[1]
BUG: KMSAN: kernel-infoleak in copyout lib/iov_iter.c:143 [inline]
BUG: KMSAN: kernel-infoleak in _copy_to_iter+0x4c0/0x2700 lib/iov_iter.c:576
CPU: 0 PID: 6697 Comm: syz-executor310 Not tainted 4.20.0-rc3+ #95
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x32d/0x480 lib/dump_stack.c:113
 kmsan_report+0x12c/0x290 mm/kmsan/kmsan.c:683
 kmsan_internal_check_memory+0x32a/0xa50 mm/kmsan/kmsan.c:743
 kmsan_copy_to_user+0x78/0xd0 mm/kmsan/kmsan_hooks.c:634
 copyout lib/iov_iter.c:143 [inline]
 _copy_to_iter+0x4c0/0x2700 lib/iov_iter.c:576
 copy_to_iter include/linux/uio.h:143 [inline]
 skb_copy_datagram_iter+0x4e2/0x1070 net/core/datagram.c:431
 skb_copy_datagram_msg include/linux/skbuff.h:3316 [inline]
 netlink_recvmsg+0x6f9/0x19d0 net/netlink/af_netlink.c:1975
 sock_recvmsg_nosec net/socket.c:794 [inline]
 sock_recvmsg+0x1d1/0x230 net/socket.c:801
 ___sys_recvmsg+0x444/0xae0 net/socket.c:2278
 __sys_recvmsg net/socket.c:2327 [inline]
 __do_sys_recvmsg net/socket.c:2337 [inline]
 __se_sys_recvmsg+0x2fa/0x450 net/socket.c:2334
 __x64_sys_recvmsg+0x4a/0x70 net/socket.c:2334
 do_syscall_64+0xcf/0x110 arch/x86/entry/common.c:291
 entry_SYSCALL_64_after_hwframe+0x63/0xe7
RIP: 0033:0x441119
Code: 18 89 d0 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 db 0a fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007fffc7f008a8 EFLAGS: 00000207 ORIG_RAX: 000000000000002f
RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 0000000000441119
RDX: 0000000000000040 RSI: 00000000200005c0 RDI: 0000000000000003
RBP: 00000000006cc018 R08: 0000000000000100 R09: 0000000000000100
R10: 0000000000000100 R11: 0000000000000207 R12: 0000000000402080
R13: 0000000000402110 R14: 0000000000000000 R15: 0000000000000000

Uninit was stored to memory at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:246 [inline]
 kmsan_save_stack mm/kmsan/kmsan.c:261 [inline]
 kmsan_internal_chain_origin+0x13d/0x240 mm/kmsan/kmsan.c:469
 kmsan_memcpy_memmove_metadata+0x1a9/0xf70 mm/kmsan/kmsan.c:344
 kmsan_memcpy_metadata+0xb/0x10 mm/kmsan/kmsan.c:362
 __msan_memcpy+0x61/0x70 mm/kmsan/kmsan_instr.c:162
 __nla_put lib/nlattr.c:744 [inline]
 nla_put+0x20a/0x2d0 lib/nlattr.c:802
 nlmsg_populate_fdb_fill+0x444/0x810 net/core/rtnetlink.c:3466
 nlmsg_populate_fdb net/core/rtnetlink.c:3775 [inline]
 ndo_dflt_fdb_dump+0x73a/0x960 net/core/rtnetlink.c:3807
 rtnl_fdb_dump+0x1318/0x1cb0 net/core/rtnetlink.c:3979
 netlink_dump+0xc79/0x1c90 net/netlink/af_netlink.c:2244
 __netlink_dump_start+0x10c4/0x11d0 net/netlink/af_netlink.c:2352
 netlink_dump_start include/linux/netlink.h:216 [inline]
 rtnetlink_rcv_msg+0x141b/0x1540 net/core/rtnetlink.c:4910
 netlink_rcv_skb+0x394/0x640 net/netlink/af_netlink.c:2477
 rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:4965
 netlink_unicast_kernel net/netlink/af_netlink.c:1310 [inline]
 netlink_unicast+0x1699/0x1740 net/netlink/af_netlink.c:1336
 netlink_sendmsg+0x13c7/0x1440 net/netlink/af_netlink.c:1917
 sock_sendmsg_nosec net/socket.c:621 [inline]
 sock_sendmsg net/socket.c:631 [inline]
 ___sys_sendmsg+0xe3b/0x1240 net/socket.c:2116
 __sys_sendmsg net/socket.c:2154 [inline]
 __do_sys_sendmsg net/socket.c:2163 [inline]
 __se_sys_sendmsg+0x305/0x460 net/socket.c:2161
 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2161
 do_syscall_64+0xcf/0x110 arch/x86/entry/common.c:291
 entry_SYSCALL_64_after_hwframe+0x63/0xe7

Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:246 [inline]
 kmsan_internal_poison_shadow+0x6d/0x130 mm/kmsan/kmsan.c:170
 kmsan_kmalloc+0xa1/0x100 mm/kmsan/kmsan_hooks.c:186
 __kmalloc+0x14c/0x4d0 mm/slub.c:3825
 kmalloc include/linux/slab.h:551 [inline]
 __hw_addr_create_ex net/core/dev_addr_lists.c:34 [inline]
 __hw_addr_add_ex net/core/dev_addr_lists.c:80 [inline]
 __dev_mc_add+0x357/0x8a0 net/core/dev_addr_lists.c:670
 dev_mc_add+0x6d/0x80 net/core/dev_addr_lists.c:687
 ip_mc_filter_add net/ipv4/igmp.c:1128 [inline]
 igmp_group_added+0x4d4/0xb80 net/ipv4/igmp.c:1311
 __ip_mc_inc_group+0xea9/0xf70 net/ipv4/igmp.c:1444
 ip_mc_inc_group net/ipv4/igmp.c:1453 [inline]
 ip_mc_up+0x1c3/0x400 net/ipv4/igmp.c:1775
 inetdev_event+0x1d03/0x1d80 net/ipv4/devinet.c:1522
 notifier_call_chain kernel/notifier.c:93 [inline]
 __raw_notifier_call_chain kernel/notifier.c:394 [inline]
 raw_notifier_call_chain+0x13d/0x240 kernel/notifier.c:401
 __dev_notify_flags+0x3da/0x860 net/core/dev.c:1733
 dev_change_flags+0x1ac/0x230 net/core/dev.c:7569
 do_setlink+0x165f/0x5ea0 net/core/rtnetlink.c:2492
 rtnl_newlink+0x2ad7/0x35a0 net/core/rtnetlink.c:3111
 rtnetlink_rcv_msg+0x1148/0x1540 net/core/rtnetlink.c:4947
 netlink_rcv_skb+0x394/0x640 net/netlink/af_netlink.c:2477
 rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:4965
 netlink_unicast_kernel net/netlink/af_netlink.c:1310 [inline]
 netlink_unicast+0x1699/0x1740 net/netlink/af_netlink.c:1336
 netlink_sendmsg+0x13c7/0x1440 net/netlink/af_netlink.c:1917
 sock_sendmsg_nosec net/socket.c:621 [inline]
 sock_sendmsg net/socket.c:631 [inline]
 ___sys_sendmsg+0xe3b/0x1240 net/socket.c:2116
 __sys_sendmsg net/socket.c:2154 [inline]
 __do_sys_sendmsg net/socket.c:2163 [inline]
 __se_sys_sendmsg+0x305/0x460 net/socket.c:2161
 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2161
 do_syscall_64+0xcf/0x110 arch/x86/entry/common.c:291
 entry_SYSCALL_64_after_hwframe+0x63/0xe7

Bytes 36-37 of 105 are uninitialized
Memory access of size 105 starts at ffff88819686c000
Data copied to user address 0000000020000380

Fixes: d83b06036048 ("net: add fdb generic dump routine")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: Ido Schimmel <idosch@mellanox.com>
Cc: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index c392a77ff788..925af6b43017 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3280,6 +3280,9 @@ int ndo_dflt_fdb_dump(struct sk_buff *skb,
 {
 	int err;
 
+	if (dev->type != ARPHRD_ETHER)
+		return -EINVAL;
+
 	netif_addr_lock_bh(dev);
 	err = nlmsg_populate_fdb(skb, cb, dev, idx, &dev->uc);
 	if (err)
-- 
2.19.2


From 1b7b7e73bd7b587575e337d8bfe3f396fda2b582 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sat, 1 Dec 2018 01:36:59 +0800
Subject: [PATCH 11/15] sctp: kfree_rcu asoc

[ Upstream commit fb6df5a6234c38a9c551559506a49a677ac6f07a ]

In sctp_hash_transport/sctp_epaddr_lookup_transport, it dereferences
a transport's asoc under rcu_read_lock while asoc is freed not after
a grace period, which leads to a use-after-free panic.

This patch fixes it by calling kfree_rcu to make asoc be freed after
a grace period.

Note that only the asoc's memory is delayed to free in the patch, it
won't cause sk to linger longer.

Thanks Neil and Marcelo to make this clear.

Fixes: 7fda702f9315 ("sctp: use new rhlist interface on sctp transport rhashtable")
Fixes: cd2b70875058 ("sctp: check duplicate node before inserting a new transport")
Reported-by: syzbot+0b05d8aa7cb185107483@syzkaller.appspotmail.com
Reported-by: syzbot+aad231d51b1923158444@syzkaller.appspotmail.com
Suggested-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/structs.h | 2 ++
 net/sctp/associola.c       | 2 +-
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 8e1e1dc490fd..94c775773f58 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1902,6 +1902,8 @@ struct sctp_association {
 
 	__u64 abandoned_unsent[SCTP_PR_INDEX(MAX) + 1];
 	__u64 abandoned_sent[SCTP_PR_INDEX(MAX) + 1];
+
+	struct rcu_head rcu;
 };
 
 
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 4982b31fec8e..23fec3817e0c 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -432,7 +432,7 @@ static void sctp_association_destroy(struct sctp_association *asoc)
 
 	WARN_ON(atomic_read(&asoc->rmem_alloc));
 
-	kfree(asoc);
+	kfree_rcu(asoc, rcu);
 	SCTP_DBG_OBJCNT_DEC(assoc);
 }
 
-- 
2.19.2


From d329c3f06742fac7fd3207680ea686d9cf3903c6 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 5 Dec 2018 14:24:31 -0800
Subject: [PATCH 12/15] tcp: Do not underestimate rwnd_limited

[ Upstream commit 41727549de3e7281feb174d568c6e46823db8684 ]

If available rwnd is too small, tcp_tso_should_defer()
can decide it is worth waiting before splitting a TSO packet.

This really means we are rwnd limited.

Fixes: 5615f88614a4 ("tcp: instrument how long TCP is limited by receive window")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index b2ead31afcba..12cd64382768 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2328,8 +2328,11 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 		} else {
 			if (!push_one &&
 			    tcp_tso_should_defer(sk, skb, &is_cwnd_limited,
-						 max_segs))
+						 max_segs)) {
+				if (!is_cwnd_limited)
+					is_rwnd_limited = true;
 				break;
+			}
 		}
 
 		limit = mss_now;
-- 
2.19.2


From 642e93836ba285fd58684e18d4d7be96253c2b50 Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Wed, 5 Dec 2018 14:38:38 -0800
Subject: [PATCH 13/15] tcp: fix NULL ref in tail loss probe

[ Upstream commit b2b7af861122a0c0f6260155c29a1b2e594cd5b5 ]

TCP loss probe timer may fire when the retranmission queue is empty but
has a non-zero tp->packets_out counter. tcp_send_loss_probe will call
tcp_rearm_rto which triggers NULL pointer reference by fetching the
retranmission queue head in its sub-routines.

Add a more detailed warning to help catch the root cause of the inflight
accounting inconsistency.

Reported-by: Rafael Tinoco <rafael.tinoco@linaro.org>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 12cd64382768..1b31b0a1c7fa 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2476,14 +2476,18 @@ void tcp_send_loss_probe(struct sock *sk)
 		skb = tcp_write_queue_tail(sk);
 	}
 
+	if (unlikely(!skb)) {
+		WARN_ONCE(tp->packets_out,
+			  "invalid inflight: %u state %u cwnd %u mss %d\n",
+			  tp->packets_out, sk->sk_state, tp->snd_cwnd, mss);
+		inet_csk(sk)->icsk_pending = 0;
+		return;
+	}
+
 	/* At most one outstanding TLP retransmission. */
 	if (tp->tlp_high_seq)
 		goto rearm_timer;
 
-	/* Retransmit last segment. */
-	if (WARN_ON(!skb))
-		goto rearm_timer;
-
 	if (skb_still_in_host_queue(sk, skb))
 		goto rearm_timer;
 
-- 
2.19.2


From 359cdb037ec048444bb674082b65e24bf2eaeac3 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Thu, 29 Nov 2018 14:45:39 +0100
Subject: [PATCH 14/15] tun: forbid iface creation with rtnl ops

[ Upstream commit 35b827b6d06199841a83839e8bb69c0cd13a28be ]

It's not supported right now (the goal of the initial patch was to support
'ip link del' only).

Before the patch:
$ ip link add foo type tun
[  239.632660] BUG: unable to handle kernel NULL pointer dereference at 0000000000000000
[snip]
[  239.636410] RIP: 0010:register_netdevice+0x8e/0x3a0

This panic occurs because dev->netdev_ops is not set by tun_setup(). But to
have something usable, it will require more than just setting
netdev_ops.

Fixes: f019a7a594d9 ("tun: Implement ip link del tunXXX")
CC: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 0a008d136aae..2956bb6cda72 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1818,9 +1818,9 @@ static void tun_setup(struct net_device *dev)
 static int tun_validate(struct nlattr *tb[], struct nlattr *data[],
 			struct netlink_ext_ack *extack)
 {
-	if (!data)
-		return 0;
-	return -EINVAL;
+	NL_SET_ERR_MSG(extack,
+		       "tun/tap creation via rtnetlink is not supported.");
+	return -EOPNOTSUPP;
 }
 
 static struct rtnl_link_ops tun_link_ops __read_mostly = {
-- 
2.19.2


From fabb6e10e474bb336abe4200aaa4f4ba87f62a97 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Thu, 29 Nov 2018 13:53:16 +0800
Subject: [PATCH 15/15] virtio-net: keep vnet header zeroed after processing
 XDP

[ Upstream commit 436c9453a1ac0944b82870ef2e0d9be956b396d9 ]

We copy vnet header unconditionally in page_to_skb() this is wrong
since XDP may modify the packet data. So let's keep a zeroed vnet
header for not confusing the conversion between vnet header and skb
metadata.

In the future, we should able to detect whether or not the packet was
modified and keep using the vnet header when packet was not touched.

Fixes: f600b6905015 ("virtio_net: Add XDP support")
Reported-by: Pavel Popa <pashinho1990@gmail.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 0e8e3be50332..215696f21d67 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -309,7 +309,8 @@ static unsigned int mergeable_ctx_to_truesize(void *mrg_ctx)
 static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 				   struct receive_queue *rq,
 				   struct page *page, unsigned int offset,
-				   unsigned int len, unsigned int truesize)
+				   unsigned int len, unsigned int truesize,
+				   bool hdr_valid)
 {
 	struct sk_buff *skb;
 	struct virtio_net_hdr_mrg_rxbuf *hdr;
@@ -331,7 +332,8 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 	else
 		hdr_padded_len = sizeof(struct padded_vnet_hdr);
 
-	memcpy(hdr, p, hdr_len);
+	if (hdr_valid)
+		memcpy(hdr, p, hdr_len);
 
 	len -= hdr_len;
 	offset += hdr_padded_len;
@@ -594,7 +596,8 @@ static struct sk_buff *receive_big(struct net_device *dev,
 				   unsigned int len)
 {
 	struct page *page = buf;
-	struct sk_buff *skb = page_to_skb(vi, rq, page, 0, len, PAGE_SIZE);
+	struct sk_buff *skb = page_to_skb(vi, rq, page, 0, len,
+					  PAGE_SIZE, true);
 
 	if (unlikely(!skb))
 		goto err;
@@ -678,7 +681,8 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 				rcu_read_unlock();
 				put_page(page);
 				head_skb = page_to_skb(vi, rq, xdp_page,
-						       offset, len, PAGE_SIZE);
+						       offset, len,
+						       PAGE_SIZE, false);
 				ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len);
 				return head_skb;
 			}
@@ -712,7 +716,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 		goto err_skb;
 	}
 
-	head_skb = page_to_skb(vi, rq, page, offset, len, truesize);
+	head_skb = page_to_skb(vi, rq, page, offset, len, truesize, !xdp_prog);
 	curr_skb = head_skb;
 
 	if (unlikely(!curr_skb))
-- 
2.19.2


[-- Attachment #3: net_419.mbox --]
[-- Type: Application/Octet-Stream, Size: 66948 bytes --]

From 3366fc54a3a973008c45dab01c239d940ca22a29 Mon Sep 17 00:00:00 2001
From: Jiri Wiesner <jwiesner@suse.com>
Date: Wed, 5 Dec 2018 16:55:29 +0100
Subject: [PATCH 01/21] ipv4: ipv6: netfilter: Adjust the frag mem limit when
 truesize changes

[ Upstream commit ebaf39e6032faf77218220707fc3fa22487784e0 ]

The *_frag_reasm() functions are susceptible to miscalculating the byte
count of packet fragments in case the truesize of a head buffer changes.
The truesize member may be changed by the call to skb_unclone(), leaving
the fragment memory limit counter unbalanced even if all fragments are
processed. This miscalculation goes unnoticed as long as the network
namespace which holds the counter is not destroyed.

Should an attempt be made to destroy a network namespace that holds an
unbalanced fragment memory limit counter the cleanup of the namespace
never finishes. The thread handling the cleanup gets stuck in
inet_frags_exit_net() waiting for the percpu counter to reach zero. The
thread is usually in running state with a stacktrace similar to:

 PID: 1073   TASK: ffff880626711440  CPU: 1   COMMAND: "kworker/u48:4"
  #5 [ffff880621563d48] _raw_spin_lock at ffffffff815f5480
  #6 [ffff880621563d48] inet_evict_bucket at ffffffff8158020b
  #7 [ffff880621563d80] inet_frags_exit_net at ffffffff8158051c
  #8 [ffff880621563db0] ops_exit_list at ffffffff814f5856
  #9 [ffff880621563dd8] cleanup_net at ffffffff814f67c0
 #10 [ffff880621563e38] process_one_work at ffffffff81096f14

It is not possible to create new network namespaces, and processes
that call unshare() end up being stuck in uninterruptible sleep state
waiting to acquire the net_mutex.

The bug was observed in the IPv6 netfilter code by Per Sundstrom.
I thank him for his analysis of the problem. The parts of this patch
that apply to IPv4 and IPv6 fragment reassembly are preemptive measures.

Signed-off-by: Jiri Wiesner <jwiesner@suse.com>
Reported-by: Per Sundstrom <per.sundstrom@redqube.se>
Acked-by: Peter Oskolkov <posk@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_fragment.c                  | 7 +++++++
 net/ipv6/netfilter/nf_conntrack_reasm.c | 8 +++++++-
 net/ipv6/reassembly.c                   | 8 +++++++-
 3 files changed, 21 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index cb8fa5d7afe1..f686d7761acb 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -513,6 +513,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
 	struct rb_node *rbn;
 	int len;
 	int ihlen;
+	int delta;
 	int err;
 	u8 ecn;
 
@@ -554,10 +555,16 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
 	if (len > 65535)
 		goto out_oversize;
 
+	delta = - head->truesize;
+
 	/* Head of list must not be cloned. */
 	if (skb_unclone(head, GFP_ATOMIC))
 		goto out_nomem;
 
+	delta += head->truesize;
+	if (delta)
+		add_frag_mem_limit(qp->q.net, delta);
+
 	/* If the first fragment is fragmented itself, we split
 	 * it to two chunks: the first with data and paged part
 	 * and the second, holding only fragments. */
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index f76bd4d15704..043ed8eb0ab9 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -341,7 +341,7 @@ static bool
 nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev,  struct net_device *dev)
 {
 	struct sk_buff *fp, *head = fq->q.fragments;
-	int    payload_len;
+	int    payload_len, delta;
 	u8 ecn;
 
 	inet_frag_kill(&fq->q);
@@ -363,10 +363,16 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev,  struct net_devic
 		return false;
 	}
 
+	delta = - head->truesize;
+
 	/* Head of list must not be cloned. */
 	if (skb_unclone(head, GFP_ATOMIC))
 		return false;
 
+	delta += head->truesize;
+	if (delta)
+		add_frag_mem_limit(fq->q.net, delta);
+
 	/* If the first fragment is fragmented itself, we split
 	 * it to two chunks: the first with data and paged part
 	 * and the second, holding only fragments. */
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 5c5b4f79296e..d3fd2d7e5aa4 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -281,7 +281,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
 {
 	struct net *net = container_of(fq->q.net, struct net, ipv6.frags);
 	struct sk_buff *fp, *head = fq->q.fragments;
-	int    payload_len;
+	int    payload_len, delta;
 	unsigned int nhoff;
 	int sum_truesize;
 	u8 ecn;
@@ -322,10 +322,16 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
 	if (payload_len > IPV6_MAXPLEN)
 		goto out_oversize;
 
+	delta = - head->truesize;
+
 	/* Head of list must not be cloned. */
 	if (skb_unclone(head, GFP_ATOMIC))
 		goto out_oom;
 
+	delta += head->truesize;
+	if (delta)
+		add_frag_mem_limit(fq->q.net, delta);
+
 	/* If the first fragment is fragmented itself, we split
 	 * it to two chunks: the first with data and paged part
 	 * and the second, holding only fragments. */
-- 
2.19.2


From 7eb1f9fd388b4d053907f9d722c4096b036a3b0b Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Thu, 6 Dec 2018 19:30:36 +0100
Subject: [PATCH 02/21] ipv6: Check available headroom in ip6_xmit() even
 without options

[ Upstream commit 66033f47ca60294a95fc85ec3a3cc909dab7b765 ]

Even if we send an IPv6 packet without options, MAX_HEADER might not be
enough to account for the additional headroom required by alignment of
hardware headers.

On a configuration without HYPERV_NET, WLAN, AX25, and with IPV6_TUNNEL,
sending short SCTP packets over IPv4 over L2TP over IPv6, we start with
100 bytes of allocated headroom in sctp_packet_transmit(), end up with 54
bytes after l2tp_xmit_skb(), and 14 bytes in ip6_finish_output2().

Those would be enough to append our 14 bytes header, but we're going to
align that to 16 bytes, and write 2 bytes out of the allocated slab in
neigh_hh_output().

KASan says:

[  264.967848] ==================================================================
[  264.967861] BUG: KASAN: slab-out-of-bounds in ip6_finish_output2+0x1aec/0x1c70
[  264.967866] Write of size 16 at addr 000000006af1c7fe by task netperf/6201
[  264.967870]
[  264.967876] CPU: 0 PID: 6201 Comm: netperf Not tainted 4.20.0-rc4+ #1
[  264.967881] Hardware name: IBM 2827 H43 400 (z/VM 6.4.0)
[  264.967887] Call Trace:
[  264.967896] ([<00000000001347d6>] show_stack+0x56/0xa0)
[  264.967903]  [<00000000017e379c>] dump_stack+0x23c/0x290
[  264.967912]  [<00000000007bc594>] print_address_description+0xf4/0x290
[  264.967919]  [<00000000007bc8fc>] kasan_report+0x13c/0x240
[  264.967927]  [<000000000162f5e4>] ip6_finish_output2+0x1aec/0x1c70
[  264.967935]  [<000000000163f890>] ip6_finish_output+0x430/0x7f0
[  264.967943]  [<000000000163fe44>] ip6_output+0x1f4/0x580
[  264.967953]  [<000000000163882a>] ip6_xmit+0xfea/0x1ce8
[  264.967963]  [<00000000017396e2>] inet6_csk_xmit+0x282/0x3f8
[  264.968033]  [<000003ff805fb0ba>] l2tp_xmit_skb+0xe02/0x13e0 [l2tp_core]
[  264.968037]  [<000003ff80631192>] l2tp_eth_dev_xmit+0xda/0x150 [l2tp_eth]
[  264.968041]  [<0000000001220020>] dev_hard_start_xmit+0x268/0x928
[  264.968069]  [<0000000001330e8e>] sch_direct_xmit+0x7ae/0x1350
[  264.968071]  [<000000000122359c>] __dev_queue_xmit+0x2b7c/0x3478
[  264.968075]  [<00000000013d2862>] ip_finish_output2+0xce2/0x11a0
[  264.968078]  [<00000000013d9b14>] ip_finish_output+0x56c/0x8c8
[  264.968081]  [<00000000013ddd1e>] ip_output+0x226/0x4c0
[  264.968083]  [<00000000013dbd6c>] __ip_queue_xmit+0x894/0x1938
[  264.968100]  [<000003ff80bc3a5c>] sctp_packet_transmit+0x29d4/0x3648 [sctp]
[  264.968116]  [<000003ff80b7bf68>] sctp_outq_flush_ctrl.constprop.5+0x8d0/0xe50 [sctp]
[  264.968131]  [<000003ff80b7c716>] sctp_outq_flush+0x22e/0x7d8 [sctp]
[  264.968146]  [<000003ff80b35c68>] sctp_cmd_interpreter.isra.16+0x530/0x6800 [sctp]
[  264.968161]  [<000003ff80b3410a>] sctp_do_sm+0x222/0x648 [sctp]
[  264.968177]  [<000003ff80bbddac>] sctp_primitive_ASSOCIATE+0xbc/0xf8 [sctp]
[  264.968192]  [<000003ff80b93328>] __sctp_connect+0x830/0xc20 [sctp]
[  264.968208]  [<000003ff80bb11ce>] sctp_inet_connect+0x2e6/0x378 [sctp]
[  264.968212]  [<0000000001197942>] __sys_connect+0x21a/0x450
[  264.968215]  [<000000000119aff8>] sys_socketcall+0x3d0/0xb08
[  264.968218]  [<000000000184ea7a>] system_call+0x2a2/0x2c0

[...]

Just like ip_finish_output2() does for IPv4, check that we have enough
headroom in ip6_xmit(), and reallocate it if we don't.

This issue is older than git history.

Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_output.c | 42 +++++++++++++++++++++---------------------
 1 file changed, 21 insertions(+), 21 deletions(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index f9f8f554d141..2694def1e72c 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -195,37 +195,37 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 	const struct ipv6_pinfo *np = inet6_sk(sk);
 	struct in6_addr *first_hop = &fl6->daddr;
 	struct dst_entry *dst = skb_dst(skb);
+	unsigned int head_room;
 	struct ipv6hdr *hdr;
 	u8  proto = fl6->flowi6_proto;
 	int seg_len = skb->len;
 	int hlimit = -1;
 	u32 mtu;
 
-	if (opt) {
-		unsigned int head_room;
+	head_room = sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dst->dev);
+	if (opt)
+		head_room += opt->opt_nflen + opt->opt_flen;
 
-		/* First: exthdrs may take lots of space (~8K for now)
-		   MAX_HEADER is not enough.
-		 */
-		head_room = opt->opt_nflen + opt->opt_flen;
-		seg_len += head_room;
-		head_room += sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dst->dev);
-
-		if (skb_headroom(skb) < head_room) {
-			struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room);
-			if (!skb2) {
-				IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
-					      IPSTATS_MIB_OUTDISCARDS);
-				kfree_skb(skb);
-				return -ENOBUFS;
-			}
-			if (skb->sk)
-				skb_set_owner_w(skb2, skb->sk);
-			consume_skb(skb);
-			skb = skb2;
+	if (unlikely(skb_headroom(skb) < head_room)) {
+		struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room);
+		if (!skb2) {
+			IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
+				      IPSTATS_MIB_OUTDISCARDS);
+			kfree_skb(skb);
+			return -ENOBUFS;
 		}
+		if (skb->sk)
+			skb_set_owner_w(skb2, skb->sk);
+		consume_skb(skb);
+		skb = skb2;
+	}
+
+	if (opt) {
+		seg_len += opt->opt_nflen + opt->opt_flen;
+
 		if (opt->opt_flen)
 			ipv6_push_frag_opts(skb, opt, &proto);
+
 		if (opt->opt_nflen)
 			ipv6_push_nfrag_opts(skb, opt, &proto, &first_hop,
 					     &fl6->saddr);
-- 
2.19.2


From 22e9e0b9d8ea2dcc86ea826131a6b4ed29f484dc Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Thu, 6 Dec 2018 19:30:37 +0100
Subject: [PATCH 03/21] neighbour: Avoid writing before skb->head in
 neigh_hh_output()

[ Upstream commit e6ac64d4c4d095085d7dd71cbd05704ac99829b2 ]

While skb_push() makes the kernel panic if the skb headroom is less than
the unaligned hardware header size, it will proceed normally in case we
copy more than that because of alignment, and we'll silently corrupt
adjacent slabs.

In the case fixed by the previous patch,
"ipv6: Check available headroom in ip6_xmit() even without options", we
end up in neigh_hh_output() with 14 bytes headroom, 14 bytes hardware
header and write 16 bytes, starting 2 bytes before the allocated buffer.

Always check we're not writing before skb->head and, if the headroom is
not enough, warn and drop the packet.

v2:
 - instead of panicking with BUG_ON(), WARN_ON_ONCE() and drop the packet
   (Eric Dumazet)
 - if we avoid the panic, though, we need to explicitly check the headroom
   before the memcpy(), otherwise we'll have corrupted slabs on a running
   kernel, after we warn
 - use __skb_push() instead of skb_push(), as the headroom check is
   already implemented here explicitly (Eric Dumazet)

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/neighbour.h | 28 +++++++++++++++++++++++-----
 1 file changed, 23 insertions(+), 5 deletions(-)

diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 6c1eecd56a4d..beeeed126872 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -453,6 +453,7 @@ static inline int neigh_hh_bridge(struct hh_cache *hh, struct sk_buff *skb)
 
 static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb)
 {
+	unsigned int hh_alen = 0;
 	unsigned int seq;
 	unsigned int hh_len;
 
@@ -460,16 +461,33 @@ static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb
 		seq = read_seqbegin(&hh->hh_lock);
 		hh_len = hh->hh_len;
 		if (likely(hh_len <= HH_DATA_MOD)) {
-			/* this is inlined by gcc */
-			memcpy(skb->data - HH_DATA_MOD, hh->hh_data, HH_DATA_MOD);
+			hh_alen = HH_DATA_MOD;
+
+			/* skb_push() would proceed silently if we have room for
+			 * the unaligned size but not for the aligned size:
+			 * check headroom explicitly.
+			 */
+			if (likely(skb_headroom(skb) >= HH_DATA_MOD)) {
+				/* this is inlined by gcc */
+				memcpy(skb->data - HH_DATA_MOD, hh->hh_data,
+				       HH_DATA_MOD);
+			}
 		} else {
-			unsigned int hh_alen = HH_DATA_ALIGN(hh_len);
+			hh_alen = HH_DATA_ALIGN(hh_len);
 
-			memcpy(skb->data - hh_alen, hh->hh_data, hh_alen);
+			if (likely(skb_headroom(skb) >= hh_alen)) {
+				memcpy(skb->data - hh_alen, hh->hh_data,
+				       hh_alen);
+			}
 		}
 	} while (read_seqretry(&hh->hh_lock, seq));
 
-	skb_push(skb, hh_len);
+	if (WARN_ON_ONCE(skb_headroom(skb) < hh_alen)) {
+		kfree_skb(skb);
+		return NET_XMIT_DROP;
+	}
+
+	__skb_push(skb, hh_len);
 	return dev_queue_xmit(skb);
 }
 
-- 
2.19.2


From 3615146b8c21b87e40001de883ece2fbd0ee37b6 Mon Sep 17 00:00:00 2001
From: Shmulik Ladkani <shmulik@metanetworks.com>
Date: Fri, 7 Dec 2018 09:50:17 +0200
Subject: [PATCH 04/21] ipv6: sr: properly initialize flowi6 prior passing to
 ip6_route_output

[ Upstream commit 1b4e5ad5d6b9f15cd0b5121f86d4719165958417 ]

In 'seg6_output', stack variable 'struct flowi6 fl6' was missing
initialization.

Fixes: 6c8702c60b88 ("ipv6: sr: add support for SRH encapsulation and injection with lwtunnels")
Signed-off-by: Shmulik Ladkani <shmulik.ladkani@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/seg6_iptunnel.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index a8854dd3e9c5..8181ee7e1e27 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -347,6 +347,7 @@ static int seg6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 		struct ipv6hdr *hdr = ipv6_hdr(skb);
 		struct flowi6 fl6;
 
+		memset(&fl6, 0, sizeof(fl6));
 		fl6.daddr = hdr->daddr;
 		fl6.saddr = hdr->saddr;
 		fl6.flowlabel = ip6_flowinfo(hdr);
-- 
2.19.2


From a305fcfa544bc91aa6eac23a1c79824d2b794cc7 Mon Sep 17 00:00:00 2001
From: Su Yanjun <suyj.fnst@cn.fujitsu.com>
Date: Mon, 3 Dec 2018 15:33:07 +0800
Subject: [PATCH 05/21] net: 8139cp: fix a BUG triggered by changing mtu with
 network traffic

[ Upstream commit a5d4a89245ead1f37ed135213653c5beebea4237 ]

When changing mtu many times with traffic, a bug is triggered:

[ 1035.684037] kernel BUG at lib/dynamic_queue_limits.c:26!
[ 1035.684042] invalid opcode: 0000 [#1] SMP
[ 1035.684049] Modules linked in: loop binfmt_misc 8139cp(OE) macsec
tcp_diag udp_diag inet_diag unix_diag af_packet_diag netlink_diag tcp_lp
fuse uinput xt_CHECKSUM iptable_mangle ipt_MASQUERADE
nf_nat_masquerade_ipv4 iptable_nat nf_nat_ipv4 nf_nat nf_conntrack_ipv4
nf_defrag_ipv4 xt_conntrack nf_conntrack ipt_REJECT nf_reject_ipv4 tun
bridge stp llc ebtable_filter ebtables ip6table_filter devlink
ip6_tables iptable_filter sunrpc snd_hda_codec_generic snd_hda_intel
snd_hda_codec snd_hda_core snd_hwdep ppdev snd_seq iosf_mbi crc32_pclmul
parport_pc snd_seq_device ghash_clmulni_intel parport snd_pcm
aesni_intel joydev lrw snd_timer virtio_balloon sg gf128mul glue_helper
ablk_helper cryptd snd soundcore i2c_piix4 pcspkr ip_tables xfs
libcrc32c sr_mod sd_mod cdrom crc_t10dif crct10dif_generic ata_generic
[ 1035.684102]  pata_acpi virtio_console qxl drm_kms_helper syscopyarea
sysfillrect sysimgblt floppy fb_sys_fops crct10dif_pclmul
crct10dif_common ttm crc32c_intel serio_raw ata_piix drm libata 8139too
virtio_pci drm_panel_orientation_quirks virtio_ring virtio mii dm_mirror
dm_region_hash dm_log dm_mod [last unloaded: 8139cp]
[ 1035.684132] CPU: 9 PID: 25140 Comm: if-mtu-change Kdump: loaded
Tainted: G           OE  ------------ T 3.10.0-957.el7.x86_64 #1
[ 1035.684134] Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
[ 1035.684136] task: ffff8f59b1f5a080 ti: ffff8f5a2e32c000 task.ti:
ffff8f5a2e32c000
[ 1035.684149] RIP: 0010:[<ffffffffba3a40d0>]  [<ffffffffba3a40d0>]
dql_completed+0x180/0x190
[ 1035.684162] RSP: 0000:ffff8f5a75483e50  EFLAGS: 00010093
[ 1035.684162] RAX: 00000000000000c2 RBX: ffff8f5a6f91c000 RCX:
0000000000000000
[ 1035.684162] RDX: 0000000000000000 RSI: 0000000000000184 RDI:
ffff8f599fea3ec0
[ 1035.684162] RBP: ffff8f5a75483ea8 R08: 00000000000000c2 R09:
0000000000000000
[ 1035.684162] R10: 00000000000616ef R11: ffff8f5a75483b56 R12:
ffff8f599fea3e00
[ 1035.684162] R13: 0000000000000001 R14: 0000000000000000 R15:
0000000000000184
[ 1035.684162] FS:  00007fa8434de740(0000) GS:ffff8f5a75480000(0000)
knlGS:0000000000000000
[ 1035.684162] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 1035.684162] CR2: 00000000004305d0 CR3: 000000024eb66000 CR4:
00000000001406e0
[ 1035.684162] Call Trace:
[ 1035.684162]  <IRQ>
[ 1035.684162]  [<ffffffffc08cbaf8>] ? cp_interrupt+0x478/0x580 [8139cp]
[ 1035.684162]  [<ffffffffba14a294>]
__handle_irq_event_percpu+0x44/0x1c0
[ 1035.684162]  [<ffffffffba14a442>] handle_irq_event_percpu+0x32/0x80
[ 1035.684162]  [<ffffffffba14a4cc>] handle_irq_event+0x3c/0x60
[ 1035.684162]  [<ffffffffba14db29>] handle_fasteoi_irq+0x59/0x110
[ 1035.684162]  [<ffffffffba02e554>] handle_irq+0xe4/0x1a0
[ 1035.684162]  [<ffffffffba7795dd>] do_IRQ+0x4d/0xf0
[ 1035.684162]  [<ffffffffba76b362>] common_interrupt+0x162/0x162
[ 1035.684162]  <EOI>
[ 1035.684162]  [<ffffffffba0c2ae4>] ? __wake_up_bit+0x24/0x70
[ 1035.684162]  [<ffffffffba1e46f5>] ? do_set_pte+0xd5/0x120
[ 1035.684162]  [<ffffffffba1b64fb>] unlock_page+0x2b/0x30
[ 1035.684162]  [<ffffffffba1e4879>] do_read_fault.isra.61+0x139/0x1b0
[ 1035.684162]  [<ffffffffba1e9134>] handle_pte_fault+0x2f4/0xd10
[ 1035.684162]  [<ffffffffba1ebc6d>] handle_mm_fault+0x39d/0x9b0
[ 1035.684162]  [<ffffffffba76f5e3>] __do_page_fault+0x203/0x500
[ 1035.684162]  [<ffffffffba76f9c6>] trace_do_page_fault+0x56/0x150
[ 1035.684162]  [<ffffffffba76ef42>] do_async_page_fault+0x22/0xf0
[ 1035.684162]  [<ffffffffba76b788>] async_page_fault+0x28/0x30
[ 1035.684162] Code: 54 c7 47 54 ff ff ff ff 44 0f 49 ce 48 8b 35 48 2f
9c 00 48 89 77 58 e9 fe fe ff ff 0f 1f 80 00 00 00 00 41 89 d1 e9 ef fe
ff ff <0f> 0b 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 55 8d 42 ff 48
[ 1035.684162] RIP  [<ffffffffba3a40d0>] dql_completed+0x180/0x190
[ 1035.684162]  RSP <ffff8f5a75483e50>

It's not the same as in 7fe0ee09 patch described.
As 8139cp uses shared irq mode, other device irq will trigger
cp_interrupt to execute.

cp_change_mtu
 -> cp_close
 -> cp_open

In cp_close routine  just before free_irq(), some interrupt may occur.
In my environment, cp_interrupt exectutes and IntrStatus is 0x4,
exactly TxOk. That will cause cp_tx to wake device queue.

As device queue is started, cp_start_xmit and cp_open will run at same
time which will cause kernel BUG.

For example:
[#] for tx descriptor

At start:

[#][#][#]
num_queued=3

After cp_init_hw->cp_start_hw->netdev_reset_queue:

[#][#][#]
num_queued=0

When 8139cp starts to work then cp_tx will check
num_queued mismatchs the complete_bytes.

The patch will check IntrMask before check IntrStatus in cp_interrupt.
When 8139cp interrupt is disabled, just return.

Signed-off-by: Su Yanjun <suyj.fnst@cn.fujitsu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/8139cp.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c
index 81045dfa1cd8..44f6e4873aad 100644
--- a/drivers/net/ethernet/realtek/8139cp.c
+++ b/drivers/net/ethernet/realtek/8139cp.c
@@ -571,6 +571,7 @@ static irqreturn_t cp_interrupt (int irq, void *dev_instance)
 	struct cp_private *cp;
 	int handled = 0;
 	u16 status;
+	u16 mask;
 
 	if (unlikely(dev == NULL))
 		return IRQ_NONE;
@@ -578,6 +579,10 @@ static irqreturn_t cp_interrupt (int irq, void *dev_instance)
 
 	spin_lock(&cp->lock);
 
+	mask = cpr16(IntrMask);
+	if (!mask)
+		goto out_unlock;
+
 	status = cpr16(IntrStatus);
 	if (!status || (status == 0xFFFF))
 		goto out_unlock;
-- 
2.19.2


From c03dca62d2bbb6240b8cc9a58be36d0daf2bf58b Mon Sep 17 00:00:00 2001
From: Tarick Bedeir <tarick@google.com>
Date: Fri, 7 Dec 2018 00:30:26 -0800
Subject: [PATCH 06/21] net/mlx4_core: Correctly set PFC param if global pause
 is turned off.

[ Upstream commit bd5122cd1e0644d8bd8dd84517c932773e999766 ]

rx_ppp and tx_ppp can be set between 0 and 255, so don't clamp to 1.

Fixes: 6e8814ceb7e8 ("net/mlx4_en: Fix mixed PFC and Global pause user control requests")
Signed-off-by: Tarick Bedeir <tarick@google.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index f11b45001cad..d290f0787dfb 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1084,8 +1084,8 @@ static int mlx4_en_set_pauseparam(struct net_device *dev,
 
 	tx_pause = !!(pause->tx_pause);
 	rx_pause = !!(pause->rx_pause);
-	rx_ppp = priv->prof->rx_ppp && !(tx_pause || rx_pause);
-	tx_ppp = priv->prof->tx_ppp && !(tx_pause || rx_pause);
+	rx_ppp = (tx_pause || rx_pause) ? 0 : priv->prof->rx_ppp;
+	tx_ppp = (tx_pause || rx_pause) ? 0 : priv->prof->tx_ppp;
 
 	err = mlx4_SET_PORT_general(mdev->dev, priv->port,
 				    priv->rx_skb_size + ETH_FCS_LEN,
-- 
2.19.2


From 586fb6b10268648ed6c180063f602895bbc2968e Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Sun, 2 Dec 2018 14:34:36 +0200
Subject: [PATCH 07/21] net/mlx4_en: Change min MTU size to ETH_MIN_MTU

[ Upstream commit 24be19e47779d604d1492c114459dca9a92acf78 ]

NIC driver minimal MTU size shall be set to ETH_MIN_MTU, as defined in
the RFC791 and in the network stack. Remove old mlx4_en only define for
it, which was set to wrong value.

Fixes: b80f71f5816f ("ethernet/mellanox: use core min/max MTU checking")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 4 ++--
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h   | 1 -
 2 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index fe49384eba48..0d7fd3f043cf 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -3494,8 +3494,8 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 		dev->gso_partial_features = NETIF_F_GSO_UDP_TUNNEL_CSUM;
 	}
 
-	/* MTU range: 46 - hw-specific max */
-	dev->min_mtu = MLX4_EN_MIN_MTU;
+	/* MTU range: 68 - hw-specific max */
+	dev->min_mtu = ETH_MIN_MTU;
 	dev->max_mtu = priv->max_mtu;
 
 	mdev->pndev[port] = dev;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index c3228b89df46..240f9c9ca943 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -161,7 +161,6 @@
 #define MLX4_SELFTEST_LB_MIN_MTU (MLX4_LOOPBACK_TEST_PAYLOAD + NET_IP_ALIGN + \
 				  ETH_HLEN + PREAMBLE_LEN)
 
-#define MLX4_EN_MIN_MTU		46
 /* VLAN_HLEN is added twice,to support skb vlan tagged with multiple
  * headers. (For example: ETH_P_8021Q and ETH_P_8021AD).
  */
-- 
2.19.2


From 99477c58d703f374689ea2d47ba4c764e3940c00 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 3 Dec 2018 08:19:33 +0100
Subject: [PATCH 08/21] net: phy: don't allow __set_phy_supported to add
 unsupported modes

[ Upstream commit d2a36971ef595069b7a600d1144c2e0881a930a1 ]

Currently __set_phy_supported allows to add modes w/o checking whether
the PHY supports them. This is wrong, it should never add modes but
only remove modes we don't want to support.

The commit marked as fixed didn't do anything wrong, it just copied
existing functionality to the helper which is being fixed now.

Fixes: f3a6bd393c2c ("phylib: Add phy_set_max_speed helper")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 19 ++++++++-----------
 1 file changed, 8 insertions(+), 11 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 733e35b7c4bb..20d1be2b070b 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1738,20 +1738,17 @@ EXPORT_SYMBOL(genphy_loopback);
 
 static int __set_phy_supported(struct phy_device *phydev, u32 max_speed)
 {
-	phydev->supported &= ~(PHY_1000BT_FEATURES | PHY_100BT_FEATURES |
-			       PHY_10BT_FEATURES);
-
 	switch (max_speed) {
-	default:
-		return -ENOTSUPP;
-	case SPEED_1000:
-		phydev->supported |= PHY_1000BT_FEATURES;
+	case SPEED_10:
+		phydev->supported &= ~PHY_100BT_FEATURES;
 		/* fall through */
 	case SPEED_100:
-		phydev->supported |= PHY_100BT_FEATURES;
-		/* fall through */
-	case SPEED_10:
-		phydev->supported |= PHY_10BT_FEATURES;
+		phydev->supported &= ~PHY_1000BT_FEATURES;
+		break;
+	case SPEED_1000:
+		break;
+	default:
+		return -ENOTSUPP;
 	}
 
 	return 0;
-- 
2.19.2


From 8066a71262386df02e422af3d661090f146804a5 Mon Sep 17 00:00:00 2001
From: Christoph Paasch <cpaasch@apple.com>
Date: Thu, 29 Nov 2018 16:01:04 -0800
Subject: [PATCH 09/21] net: Prevent invalid access to skb->prev in
 __qdisc_drop_all

[ Upstream commit 9410d386d0a829ace9558336263086c2fbbe8aed ]

__qdisc_drop_all() accesses skb->prev to get to the tail of the
segment-list.

With commit 68d2f84a1368 ("net: gro: properly remove skb from list")
the skb-list handling has been changed to set skb->next to NULL and set
the list-poison on skb->prev.

With that change, __qdisc_drop_all() will panic when it tries to
dereference skb->prev.

Since commit 992cba7e276d ("net: Add and use skb_list_del_init().")
__list_del_entry is used, leaving skb->prev unchanged (thus,
pointing to the list-head if it's the first skb of the list).
This will make __qdisc_drop_all modify the next-pointer of the list-head
and result in a panic later on:

[   34.501053] general protection fault: 0000 [#1] SMP KASAN PTI
[   34.501968] CPU: 2 PID: 0 Comm: swapper/2 Not tainted 4.20.0-rc2.mptcp #108
[   34.502887] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 0.5.1 01/01/2011
[   34.504074] RIP: 0010:dev_gro_receive+0x343/0x1f90
[   34.504751] Code: e0 48 c1 e8 03 42 80 3c 30 00 0f 85 4a 1c 00 00 4d 8b 24 24 4c 39 65 d0 0f 84 0a 04 00 00 49 8d 7c 24 38 48 89 f8 48 c1 e8 03 <42> 0f b6 04 30 84 c0 74 08 3c 04
[   34.507060] RSP: 0018:ffff8883af507930 EFLAGS: 00010202
[   34.507761] RAX: 0000000000000007 RBX: ffff8883970b2c80 RCX: 1ffff11072e165a6
[   34.508640] RDX: 1ffff11075867008 RSI: ffff8883ac338040 RDI: 0000000000000038
[   34.509493] RBP: ffff8883af5079d0 R08: ffff8883970b2d40 R09: 0000000000000062
[   34.510346] R10: 0000000000000034 R11: 0000000000000000 R12: 0000000000000000
[   34.511215] R13: 0000000000000000 R14: dffffc0000000000 R15: ffff8883ac338008
[   34.512082] FS:  0000000000000000(0000) GS:ffff8883af500000(0000) knlGS:0000000000000000
[   34.513036] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   34.513741] CR2: 000055ccc3e9d020 CR3: 00000003abf32000 CR4: 00000000000006e0
[   34.514593] Call Trace:
[   34.514893]  <IRQ>
[   34.515157]  napi_gro_receive+0x93/0x150
[   34.515632]  receive_buf+0x893/0x3700
[   34.516094]  ? __netif_receive_skb+0x1f/0x1a0
[   34.516629]  ? virtnet_probe+0x1b40/0x1b40
[   34.517153]  ? __stable_node_chain+0x4d0/0x850
[   34.517684]  ? kfree+0x9a/0x180
[   34.518067]  ? __kasan_slab_free+0x171/0x190
[   34.518582]  ? detach_buf+0x1df/0x650
[   34.519061]  ? lapic_next_event+0x5a/0x90
[   34.519539]  ? virtqueue_get_buf_ctx+0x280/0x7f0
[   34.520093]  virtnet_poll+0x2df/0xd60
[   34.520533]  ? receive_buf+0x3700/0x3700
[   34.521027]  ? qdisc_watchdog_schedule_ns+0xd5/0x140
[   34.521631]  ? htb_dequeue+0x1817/0x25f0
[   34.522107]  ? sch_direct_xmit+0x142/0xf30
[   34.522595]  ? virtqueue_napi_schedule+0x26/0x30
[   34.523155]  net_rx_action+0x2f6/0xc50
[   34.523601]  ? napi_complete_done+0x2f0/0x2f0
[   34.524126]  ? kasan_check_read+0x11/0x20
[   34.524608]  ? _raw_spin_lock+0x7d/0xd0
[   34.525070]  ? _raw_spin_lock_bh+0xd0/0xd0
[   34.525563]  ? kvm_guest_apic_eoi_write+0x6b/0x80
[   34.526130]  ? apic_ack_irq+0x9e/0xe0
[   34.526567]  __do_softirq+0x188/0x4b5
[   34.527015]  irq_exit+0x151/0x180
[   34.527417]  do_IRQ+0xdb/0x150
[   34.527783]  common_interrupt+0xf/0xf
[   34.528223]  </IRQ>

This patch makes sure that skb->prev is set to NULL when entering
netem_enqueue.

Cc: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Cc: Tyler Hicks <tyhicks@canonical.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Fixes: 68d2f84a1368 ("net: gro: properly remove skb from list")
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Christoph Paasch <cpaasch@apple.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_netem.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index ad18a2052416..74c0f656f28c 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -441,6 +441,9 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	int count = 1;
 	int rc = NET_XMIT_SUCCESS;
 
+	/* Do not fool qdisc_drop_all() */
+	skb->prev = NULL;
+
 	/* Random duplication */
 	if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor))
 		++count;
-- 
2.19.2


From 1c3237461b925cca8cd48d71429ce08bd1ae8152 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Tue, 4 Dec 2018 17:37:57 +0000
Subject: [PATCH 10/21] net: use skb_list_del_init() to remove from RX sublists

[ Upstream commit 22f6bbb7bcfcef0b373b0502a7ff390275c575dd ]

list_del() leaves the skb->next pointer poisoned, which can then lead to
 a crash in e.g. OVS forwarding.  For example, setting up an OVS VXLAN
 forwarding bridge on sfc as per:

========
$ ovs-vsctl show
5dfd9c47-f04b-4aaa-aa96-4fbb0a522a30
    Bridge "br0"
        Port "br0"
            Interface "br0"
                type: internal
        Port "enp6s0f0"
            Interface "enp6s0f0"
        Port "vxlan0"
            Interface "vxlan0"
                type: vxlan
                options: {key="1", local_ip="10.0.0.5", remote_ip="10.0.0.4"}
    ovs_version: "2.5.0"
========
(where 10.0.0.5 is an address on enp6s0f1)
and sending traffic across it will lead to the following panic:
========
general protection fault: 0000 [#1] SMP PTI
CPU: 5 PID: 0 Comm: swapper/5 Not tainted 4.20.0-rc3-ehc+ #701
Hardware name: Dell Inc. PowerEdge R710/0M233H, BIOS 6.4.0 07/23/2013
RIP: 0010:dev_hard_start_xmit+0x38/0x200
Code: 53 48 89 fb 48 83 ec 20 48 85 ff 48 89 54 24 08 48 89 4c 24 18 0f 84 ab 01 00 00 48 8d 86 90 00 00 00 48 89 f5 48 89 44 24 10 <4c> 8b 33 48 c7 03 00 00 00 00 48 8b 05 c7 d1 b3 00 4d 85 f6 0f 95
RSP: 0018:ffff888627b437e0 EFLAGS: 00010202
RAX: 0000000000000000 RBX: dead000000000100 RCX: ffff88862279c000
RDX: ffff888614a342c0 RSI: 0000000000000000 RDI: 0000000000000000
RBP: ffff888618a88000 R08: 0000000000000001 R09: 00000000000003e8
R10: 0000000000000000 R11: ffff888614a34140 R12: 0000000000000000
R13: 0000000000000062 R14: dead000000000100 R15: ffff888616430000
FS:  0000000000000000(0000) GS:ffff888627b40000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f6d2bc6d000 CR3: 000000000200a000 CR4: 00000000000006e0
Call Trace:
 <IRQ>
 __dev_queue_xmit+0x623/0x870
 ? masked_flow_lookup+0xf7/0x220 [openvswitch]
 ? ep_poll_callback+0x101/0x310
 do_execute_actions+0xaba/0xaf0 [openvswitch]
 ? __wake_up_common+0x8a/0x150
 ? __wake_up_common_lock+0x87/0xc0
 ? queue_userspace_packet+0x31c/0x5b0 [openvswitch]
 ovs_execute_actions+0x47/0x120 [openvswitch]
 ovs_dp_process_packet+0x7d/0x110 [openvswitch]
 ovs_vport_receive+0x6e/0xd0 [openvswitch]
 ? dst_alloc+0x64/0x90
 ? rt_dst_alloc+0x50/0xd0
 ? ip_route_input_slow+0x19a/0x9a0
 ? __udp_enqueue_schedule_skb+0x198/0x1b0
 ? __udp4_lib_rcv+0x856/0xa30
 ? __udp4_lib_rcv+0x856/0xa30
 ? cpumask_next_and+0x19/0x20
 ? find_busiest_group+0x12d/0xcd0
 netdev_frame_hook+0xce/0x150 [openvswitch]
 __netif_receive_skb_core+0x205/0xae0
 __netif_receive_skb_list_core+0x11e/0x220
 netif_receive_skb_list+0x203/0x460
 ? __efx_rx_packet+0x335/0x5e0 [sfc]
 efx_poll+0x182/0x320 [sfc]
 net_rx_action+0x294/0x3c0
 __do_softirq+0xca/0x297
 irq_exit+0xa6/0xb0
 do_IRQ+0x54/0xd0
 common_interrupt+0xf/0xf
 </IRQ>
========
So, in all listified-receive handling, instead pull skbs off the lists with
 skb_list_del_init().

Fixes: 9af86f933894 ("net: core: fix use-after-free in __netif_receive_skb_list_core")
Fixes: 7da517a3bc52 ("net: core: Another step of skb receive list processing")
Fixes: a4ca8b7df73c ("net: ipv4: fix drop handling in ip_list_rcv() and ip_list_rcv_finish()")
Fixes: d8269e2cbf90 ("net: ipv6: listify ipv6_rcv() and ip6_rcv_finish()")
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 11 +++++++++++
 net/core/dev.c         |  8 ++++----
 net/ipv4/ip_input.c    |  4 ++--
 net/ipv6/ip6_input.c   |  4 ++--
 4 files changed, 19 insertions(+), 8 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index e6ef9cc05e60..60a2e7646985 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1355,6 +1355,17 @@ static inline void skb_zcopy_abort(struct sk_buff *skb)
 	}
 }
 
+static inline void skb_mark_not_on_list(struct sk_buff *skb)
+{
+	skb->next = NULL;
+}
+
+static inline void skb_list_del_init(struct sk_buff *skb)
+{
+	__list_del_entry(&skb->list);
+	skb_mark_not_on_list(skb);
+}
+
 /**
  *	skb_queue_empty - check if a queue is empty
  *	@list: queue head
diff --git a/net/core/dev.c b/net/core/dev.c
index 22af88c47756..1ec7f34f4c17 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4981,7 +4981,7 @@ static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemallo
 		struct net_device *orig_dev = skb->dev;
 		struct packet_type *pt_prev = NULL;
 
-		list_del(&skb->list);
+		skb_list_del_init(skb);
 		__netif_receive_skb_core(skb, pfmemalloc, &pt_prev);
 		if (!pt_prev)
 			continue;
@@ -5137,7 +5137,7 @@ static void netif_receive_skb_list_internal(struct list_head *head)
 	INIT_LIST_HEAD(&sublist);
 	list_for_each_entry_safe(skb, next, head, list) {
 		net_timestamp_check(netdev_tstamp_prequeue, skb);
-		list_del(&skb->list);
+		skb_list_del_init(skb);
 		if (!skb_defer_rx_timestamp(skb))
 			list_add_tail(&skb->list, &sublist);
 	}
@@ -5148,7 +5148,7 @@ static void netif_receive_skb_list_internal(struct list_head *head)
 		rcu_read_lock();
 		list_for_each_entry_safe(skb, next, head, list) {
 			xdp_prog = rcu_dereference(skb->dev->xdp_prog);
-			list_del(&skb->list);
+			skb_list_del_init(skb);
 			if (do_xdp_generic(xdp_prog, skb) == XDP_PASS)
 				list_add_tail(&skb->list, &sublist);
 		}
@@ -5167,7 +5167,7 @@ static void netif_receive_skb_list_internal(struct list_head *head)
 
 			if (cpu >= 0) {
 				/* Will be handled, remove from list */
-				list_del(&skb->list);
+				skb_list_del_init(skb);
 				enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
 			}
 		}
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 3196cf58f418..27c863f6dd83 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -551,7 +551,7 @@ static void ip_list_rcv_finish(struct net *net, struct sock *sk,
 	list_for_each_entry_safe(skb, next, head, list) {
 		struct dst_entry *dst;
 
-		list_del(&skb->list);
+		skb_list_del_init(skb);
 		/* if ingress device is enslaved to an L3 master device pass the
 		 * skb to its handler for processing
 		 */
@@ -598,7 +598,7 @@ void ip_list_rcv(struct list_head *head, struct packet_type *pt,
 		struct net_device *dev = skb->dev;
 		struct net *net = dev_net(dev);
 
-		list_del(&skb->list);
+		skb_list_del_init(skb);
 		skb = ip_rcv_core(skb, net);
 		if (skb == NULL)
 			continue;
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 6242682be876..6b74523fc1c4 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -95,7 +95,7 @@ static void ip6_list_rcv_finish(struct net *net, struct sock *sk,
 	list_for_each_entry_safe(skb, next, head, list) {
 		struct dst_entry *dst;
 
-		list_del(&skb->list);
+		skb_list_del_init(skb);
 		/* if ingress device is enslaved to an L3 master device pass the
 		 * skb to its handler for processing
 		 */
@@ -295,7 +295,7 @@ void ipv6_list_rcv(struct list_head *head, struct packet_type *pt,
 		struct net_device *dev = skb->dev;
 		struct net *net = dev_net(dev);
 
-		list_del(&skb->list);
+		skb_list_del_init(skb);
 		skb = ip6_rcv_core(skb, dev, net);
 		if (skb == NULL)
 			continue;
-- 
2.19.2


From fce60e25f1267b59a126ce10cb84face3f6a72af Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Fri, 7 Dec 2018 15:05:04 +1100
Subject: [PATCH 11/21] Revert "net/ibm/emac: wrong bit is used for STA
 control"

[ Upstream commit 5b3279e2cba2238b37f6c18adfdea8bddb32715a ]

This reverts commit 624ca9c33c8a853a4a589836e310d776620f4ab9.

This commit is completely bogus. The STACR register has two formats, old
and new, depending on the version of the IP block used. There's a pair of
device-tree properties that can be used to specify the format used:

	has-inverted-stacr-oc
	has-new-stacr-staopc

What this commit did was to change the bit definition used with the old
parts to match the new parts. This of course breaks the driver on all
the old ones.

Instead, the author should have set the appropriate properties in the
device-tree for the variant used on his board.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ibm/emac/emac.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ibm/emac/emac.h b/drivers/net/ethernet/ibm/emac/emac.h
index e2f80cca9bed..0d2de6f67676 100644
--- a/drivers/net/ethernet/ibm/emac/emac.h
+++ b/drivers/net/ethernet/ibm/emac/emac.h
@@ -231,7 +231,7 @@ struct emac_regs {
 #define EMAC_STACR_PHYE			0x00004000
 #define EMAC_STACR_STAC_MASK		0x00003000
 #define EMAC_STACR_STAC_READ		0x00001000
-#define EMAC_STACR_STAC_WRITE		0x00000800
+#define EMAC_STACR_STAC_WRITE		0x00002000
 #define EMAC_STACR_OPBC_MASK		0x00000C00
 #define EMAC_STACR_OPBC_50		0x00000000
 #define EMAC_STACR_OPBC_66		0x00000400
-- 
2.19.2


From 1c388a544c59a533e266949f3b888535f9658d23 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 4 Dec 2018 09:40:35 -0800
Subject: [PATCH 12/21] rtnetlink: ndo_dflt_fdb_dump() only work for
 ARPHRD_ETHER devices

[ Upstream commit 688838934c231bb08f46db687e57f6d8bf82709c ]

kmsan was able to trigger a kernel-infoleak using a gre device [1]

nlmsg_populate_fdb_fill() has a hard coded assumption
that dev->addr_len is ETH_ALEN, as normally guaranteed
for ARPHRD_ETHER devices.

A similar issue was fixed recently in commit da71577545a5
("rtnetlink: Disallow FDB configuration for non-Ethernet device")

[1]
BUG: KMSAN: kernel-infoleak in copyout lib/iov_iter.c:143 [inline]
BUG: KMSAN: kernel-infoleak in _copy_to_iter+0x4c0/0x2700 lib/iov_iter.c:576
CPU: 0 PID: 6697 Comm: syz-executor310 Not tainted 4.20.0-rc3+ #95
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x32d/0x480 lib/dump_stack.c:113
 kmsan_report+0x12c/0x290 mm/kmsan/kmsan.c:683
 kmsan_internal_check_memory+0x32a/0xa50 mm/kmsan/kmsan.c:743
 kmsan_copy_to_user+0x78/0xd0 mm/kmsan/kmsan_hooks.c:634
 copyout lib/iov_iter.c:143 [inline]
 _copy_to_iter+0x4c0/0x2700 lib/iov_iter.c:576
 copy_to_iter include/linux/uio.h:143 [inline]
 skb_copy_datagram_iter+0x4e2/0x1070 net/core/datagram.c:431
 skb_copy_datagram_msg include/linux/skbuff.h:3316 [inline]
 netlink_recvmsg+0x6f9/0x19d0 net/netlink/af_netlink.c:1975
 sock_recvmsg_nosec net/socket.c:794 [inline]
 sock_recvmsg+0x1d1/0x230 net/socket.c:801
 ___sys_recvmsg+0x444/0xae0 net/socket.c:2278
 __sys_recvmsg net/socket.c:2327 [inline]
 __do_sys_recvmsg net/socket.c:2337 [inline]
 __se_sys_recvmsg+0x2fa/0x450 net/socket.c:2334
 __x64_sys_recvmsg+0x4a/0x70 net/socket.c:2334
 do_syscall_64+0xcf/0x110 arch/x86/entry/common.c:291
 entry_SYSCALL_64_after_hwframe+0x63/0xe7
RIP: 0033:0x441119
Code: 18 89 d0 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 db 0a fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007fffc7f008a8 EFLAGS: 00000207 ORIG_RAX: 000000000000002f
RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 0000000000441119
RDX: 0000000000000040 RSI: 00000000200005c0 RDI: 0000000000000003
RBP: 00000000006cc018 R08: 0000000000000100 R09: 0000000000000100
R10: 0000000000000100 R11: 0000000000000207 R12: 0000000000402080
R13: 0000000000402110 R14: 0000000000000000 R15: 0000000000000000

Uninit was stored to memory at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:246 [inline]
 kmsan_save_stack mm/kmsan/kmsan.c:261 [inline]
 kmsan_internal_chain_origin+0x13d/0x240 mm/kmsan/kmsan.c:469
 kmsan_memcpy_memmove_metadata+0x1a9/0xf70 mm/kmsan/kmsan.c:344
 kmsan_memcpy_metadata+0xb/0x10 mm/kmsan/kmsan.c:362
 __msan_memcpy+0x61/0x70 mm/kmsan/kmsan_instr.c:162
 __nla_put lib/nlattr.c:744 [inline]
 nla_put+0x20a/0x2d0 lib/nlattr.c:802
 nlmsg_populate_fdb_fill+0x444/0x810 net/core/rtnetlink.c:3466
 nlmsg_populate_fdb net/core/rtnetlink.c:3775 [inline]
 ndo_dflt_fdb_dump+0x73a/0x960 net/core/rtnetlink.c:3807
 rtnl_fdb_dump+0x1318/0x1cb0 net/core/rtnetlink.c:3979
 netlink_dump+0xc79/0x1c90 net/netlink/af_netlink.c:2244
 __netlink_dump_start+0x10c4/0x11d0 net/netlink/af_netlink.c:2352
 netlink_dump_start include/linux/netlink.h:216 [inline]
 rtnetlink_rcv_msg+0x141b/0x1540 net/core/rtnetlink.c:4910
 netlink_rcv_skb+0x394/0x640 net/netlink/af_netlink.c:2477
 rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:4965
 netlink_unicast_kernel net/netlink/af_netlink.c:1310 [inline]
 netlink_unicast+0x1699/0x1740 net/netlink/af_netlink.c:1336
 netlink_sendmsg+0x13c7/0x1440 net/netlink/af_netlink.c:1917
 sock_sendmsg_nosec net/socket.c:621 [inline]
 sock_sendmsg net/socket.c:631 [inline]
 ___sys_sendmsg+0xe3b/0x1240 net/socket.c:2116
 __sys_sendmsg net/socket.c:2154 [inline]
 __do_sys_sendmsg net/socket.c:2163 [inline]
 __se_sys_sendmsg+0x305/0x460 net/socket.c:2161
 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2161
 do_syscall_64+0xcf/0x110 arch/x86/entry/common.c:291
 entry_SYSCALL_64_after_hwframe+0x63/0xe7

Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:246 [inline]
 kmsan_internal_poison_shadow+0x6d/0x130 mm/kmsan/kmsan.c:170
 kmsan_kmalloc+0xa1/0x100 mm/kmsan/kmsan_hooks.c:186
 __kmalloc+0x14c/0x4d0 mm/slub.c:3825
 kmalloc include/linux/slab.h:551 [inline]
 __hw_addr_create_ex net/core/dev_addr_lists.c:34 [inline]
 __hw_addr_add_ex net/core/dev_addr_lists.c:80 [inline]
 __dev_mc_add+0x357/0x8a0 net/core/dev_addr_lists.c:670
 dev_mc_add+0x6d/0x80 net/core/dev_addr_lists.c:687
 ip_mc_filter_add net/ipv4/igmp.c:1128 [inline]
 igmp_group_added+0x4d4/0xb80 net/ipv4/igmp.c:1311
 __ip_mc_inc_group+0xea9/0xf70 net/ipv4/igmp.c:1444
 ip_mc_inc_group net/ipv4/igmp.c:1453 [inline]
 ip_mc_up+0x1c3/0x400 net/ipv4/igmp.c:1775
 inetdev_event+0x1d03/0x1d80 net/ipv4/devinet.c:1522
 notifier_call_chain kernel/notifier.c:93 [inline]
 __raw_notifier_call_chain kernel/notifier.c:394 [inline]
 raw_notifier_call_chain+0x13d/0x240 kernel/notifier.c:401
 __dev_notify_flags+0x3da/0x860 net/core/dev.c:1733
 dev_change_flags+0x1ac/0x230 net/core/dev.c:7569
 do_setlink+0x165f/0x5ea0 net/core/rtnetlink.c:2492
 rtnl_newlink+0x2ad7/0x35a0 net/core/rtnetlink.c:3111
 rtnetlink_rcv_msg+0x1148/0x1540 net/core/rtnetlink.c:4947
 netlink_rcv_skb+0x394/0x640 net/netlink/af_netlink.c:2477
 rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:4965
 netlink_unicast_kernel net/netlink/af_netlink.c:1310 [inline]
 netlink_unicast+0x1699/0x1740 net/netlink/af_netlink.c:1336
 netlink_sendmsg+0x13c7/0x1440 net/netlink/af_netlink.c:1917
 sock_sendmsg_nosec net/socket.c:621 [inline]
 sock_sendmsg net/socket.c:631 [inline]
 ___sys_sendmsg+0xe3b/0x1240 net/socket.c:2116
 __sys_sendmsg net/socket.c:2154 [inline]
 __do_sys_sendmsg net/socket.c:2163 [inline]
 __se_sys_sendmsg+0x305/0x460 net/socket.c:2161
 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2161
 do_syscall_64+0xcf/0x110 arch/x86/entry/common.c:291
 entry_SYSCALL_64_after_hwframe+0x63/0xe7

Bytes 36-37 of 105 are uninitialized
Memory access of size 105 starts at ffff88819686c000
Data copied to user address 0000000020000380

Fixes: d83b06036048 ("net: add fdb generic dump routine")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: Ido Schimmel <idosch@mellanox.com>
Cc: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 6e5d61a20a70..ebde98b565e9 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3730,6 +3730,9 @@ int ndo_dflt_fdb_dump(struct sk_buff *skb,
 {
 	int err;
 
+	if (dev->type != ARPHRD_ETHER)
+		return -EINVAL;
+
 	netif_addr_lock_bh(dev);
 	err = nlmsg_populate_fdb(skb, cb, dev, idx, &dev->uc);
 	if (err)
-- 
2.19.2


From 2562a2d846b711bf8c805168fd6c3552b5721ab2 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sat, 1 Dec 2018 01:36:59 +0800
Subject: [PATCH 13/21] sctp: kfree_rcu asoc

[ Upstream commit fb6df5a6234c38a9c551559506a49a677ac6f07a ]

In sctp_hash_transport/sctp_epaddr_lookup_transport, it dereferences
a transport's asoc under rcu_read_lock while asoc is freed not after
a grace period, which leads to a use-after-free panic.

This patch fixes it by calling kfree_rcu to make asoc be freed after
a grace period.

Note that only the asoc's memory is delayed to free in the patch, it
won't cause sk to linger longer.

Thanks Neil and Marcelo to make this clear.

Fixes: 7fda702f9315 ("sctp: use new rhlist interface on sctp transport rhashtable")
Fixes: cd2b70875058 ("sctp: check duplicate node before inserting a new transport")
Reported-by: syzbot+0b05d8aa7cb185107483@syzkaller.appspotmail.com
Reported-by: syzbot+aad231d51b1923158444@syzkaller.appspotmail.com
Suggested-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/structs.h | 2 ++
 net/sctp/associola.c       | 2 +-
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index a11f93790476..feada358d872 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -2075,6 +2075,8 @@ struct sctp_association {
 
 	__u64 abandoned_unsent[SCTP_PR_INDEX(MAX) + 1];
 	__u64 abandoned_sent[SCTP_PR_INDEX(MAX) + 1];
+
+	struct rcu_head rcu;
 };
 
 
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 6a28b96e779e..3702f48a931d 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -434,7 +434,7 @@ static void sctp_association_destroy(struct sctp_association *asoc)
 
 	WARN_ON(atomic_read(&asoc->rmem_alloc));
 
-	kfree(asoc);
+	kfree_rcu(asoc, rcu);
 	SCTP_DBG_OBJCNT_DEC(assoc);
 }
 
-- 
2.19.2


From b2afe9d24db40723805c51e3ec91af74fed7da4f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 5 Dec 2018 14:24:31 -0800
Subject: [PATCH 14/21] tcp: Do not underestimate rwnd_limited

[ Upstream commit 41727549de3e7281feb174d568c6e46823db8684 ]

If available rwnd is too small, tcp_tso_should_defer()
can decide it is worth waiting before splitting a TSO packet.

This really means we are rwnd limited.

Fixes: 5615f88614a4 ("tcp: instrument how long TCP is limited by receive window")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 68f65ddf9e3c..97e8aea4ac71 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2338,8 +2338,11 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 		} else {
 			if (!push_one &&
 			    tcp_tso_should_defer(sk, skb, &is_cwnd_limited,
-						 max_segs))
+						 max_segs)) {
+				if (!is_cwnd_limited)
+					is_rwnd_limited = true;
 				break;
+			}
 		}
 
 		limit = mss_now;
-- 
2.19.2


From b80aec18514b323028e1ee9009f863c2803dd6ef Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Wed, 5 Dec 2018 14:38:38 -0800
Subject: [PATCH 15/21] tcp: fix NULL ref in tail loss probe

[ Upstream commit b2b7af861122a0c0f6260155c29a1b2e594cd5b5 ]

TCP loss probe timer may fire when the retranmission queue is empty but
has a non-zero tp->packets_out counter. tcp_send_loss_probe will call
tcp_rearm_rto which triggers NULL pointer reference by fetching the
retranmission queue head in its sub-routines.

Add a more detailed warning to help catch the root cause of the inflight
accounting inconsistency.

Reported-by: Rafael Tinoco <rafael.tinoco@linaro.org>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 97e8aea4ac71..65632f827eea 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2479,15 +2479,18 @@ void tcp_send_loss_probe(struct sock *sk)
 		goto rearm_timer;
 	}
 	skb = skb_rb_last(&sk->tcp_rtx_queue);
+	if (unlikely(!skb)) {
+		WARN_ONCE(tp->packets_out,
+			  "invalid inflight: %u state %u cwnd %u mss %d\n",
+			  tp->packets_out, sk->sk_state, tp->snd_cwnd, mss);
+		inet_csk(sk)->icsk_pending = 0;
+		return;
+	}
 
 	/* At most one outstanding TLP retransmission. */
 	if (tp->tlp_high_seq)
 		goto rearm_timer;
 
-	/* Retransmit last segment. */
-	if (WARN_ON(!skb))
-		goto rearm_timer;
-
 	if (skb_still_in_host_queue(sk, skb))
 		goto rearm_timer;
 
-- 
2.19.2


From 3f6ab1d3d8e5ac80023de18d0d9fc3f6ce2af077 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Thu, 29 Nov 2018 14:45:39 +0100
Subject: [PATCH 16/21] tun: forbid iface creation with rtnl ops

[ Upstream commit 35b827b6d06199841a83839e8bb69c0cd13a28be ]

It's not supported right now (the goal of the initial patch was to support
'ip link del' only).

Before the patch:
$ ip link add foo type tun
[  239.632660] BUG: unable to handle kernel NULL pointer dereference at 0000000000000000
[snip]
[  239.636410] RIP: 0010:register_netdevice+0x8e/0x3a0

This panic occurs because dev->netdev_ops is not set by tun_setup(). But to
have something usable, it will require more than just setting
netdev_ops.

Fixes: f019a7a594d9 ("tun: Implement ip link del tunXXX")
CC: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 573620771154..8c1abcba4cbd 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -2268,9 +2268,9 @@ static void tun_setup(struct net_device *dev)
 static int tun_validate(struct nlattr *tb[], struct nlattr *data[],
 			struct netlink_ext_ack *extack)
 {
-	if (!data)
-		return 0;
-	return -EINVAL;
+	NL_SET_ERR_MSG(extack,
+		       "tun/tap creation via rtnetlink is not supported.");
+	return -EOPNOTSUPP;
 }
 
 static size_t tun_get_size(const struct net_device *dev)
-- 
2.19.2


From 4c9f3fa8946f61efd91ad24f87a25569122bbc56 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Thu, 29 Nov 2018 13:53:16 +0800
Subject: [PATCH 17/21] virtio-net: keep vnet header zeroed after processing
 XDP

[ Upstream commit 436c9453a1ac0944b82870ef2e0d9be956b396d9 ]

We copy vnet header unconditionally in page_to_skb() this is wrong
since XDP may modify the packet data. So let's keep a zeroed vnet
header for not confusing the conversion between vnet header and skb
metadata.

In the future, we should able to detect whether or not the packet was
modified and keep using the vnet header when packet was not touched.

Fixes: f600b6905015 ("virtio_net: Add XDP support")
Reported-by: Pavel Popa <pashinho1990@gmail.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index c2ca6cd3fbe0..ad14fbfa1864 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -365,7 +365,8 @@ static unsigned int mergeable_ctx_to_truesize(void *mrg_ctx)
 static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 				   struct receive_queue *rq,
 				   struct page *page, unsigned int offset,
-				   unsigned int len, unsigned int truesize)
+				   unsigned int len, unsigned int truesize,
+				   bool hdr_valid)
 {
 	struct sk_buff *skb;
 	struct virtio_net_hdr_mrg_rxbuf *hdr;
@@ -387,7 +388,8 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 	else
 		hdr_padded_len = sizeof(struct padded_vnet_hdr);
 
-	memcpy(hdr, p, hdr_len);
+	if (hdr_valid)
+		memcpy(hdr, p, hdr_len);
 
 	len -= hdr_len;
 	offset += hdr_padded_len;
@@ -739,7 +741,8 @@ static struct sk_buff *receive_big(struct net_device *dev,
 				   struct virtnet_rq_stats *stats)
 {
 	struct page *page = buf;
-	struct sk_buff *skb = page_to_skb(vi, rq, page, 0, len, PAGE_SIZE);
+	struct sk_buff *skb = page_to_skb(vi, rq, page, 0, len,
+					  PAGE_SIZE, true);
 
 	stats->bytes += len - vi->hdr_len;
 	if (unlikely(!skb))
@@ -842,7 +845,8 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 				rcu_read_unlock();
 				put_page(page);
 				head_skb = page_to_skb(vi, rq, xdp_page,
-						       offset, len, PAGE_SIZE);
+						       offset, len,
+						       PAGE_SIZE, false);
 				return head_skb;
 			}
 			break;
@@ -898,7 +902,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 		goto err_skb;
 	}
 
-	head_skb = page_to_skb(vi, rq, page, offset, len, truesize);
+	head_skb = page_to_skb(vi, rq, page, offset, len, truesize, !xdp_prog);
 	curr_skb = head_skb;
 
 	if (unlikely(!curr_skb))
-- 
2.19.2


From f139caabe729ef15eb65c5abb5f974aecd5fa8e6 Mon Sep 17 00:00:00 2001
From: Baruch Siach <baruch@tkos.co.il>
Date: Thu, 29 Nov 2018 12:40:11 +0200
Subject: [PATCH 18/21] net: phy: sfp: correct store of detected link modes

[ Upstream commit d7f7e0018b96fd1a30a968faa9464eb57372c1ec ]

The link modes that sfp_parse_support() detects are stored in the
'modes' bitmap. There is no reason to make an exception for 1000Base-PX
or 1000Base-BX10.

Fixes: 03145864bd0f ("sfp: support 1G BiDi (eg, FiberStore SFP-GE-BX) modules")
Signed-off-by: Baruch Siach <baruch@tkos.co.il>
Acked-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/sfp-bus.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c
index 83060fb349f4..ad9db652874d 100644
--- a/drivers/net/phy/sfp-bus.c
+++ b/drivers/net/phy/sfp-bus.c
@@ -162,7 +162,7 @@ void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id,
 	/* 1000Base-PX or 1000Base-BX10 */
 	if ((id->base.e_base_px || id->base.e_base_bx10) &&
 	    br_min <= 1300 && br_max >= 1200)
-		phylink_set(support, 1000baseX_Full);
+		phylink_set(modes, 1000baseX_Full);
 
 	/* For active or passive cables, select the link modes
 	 * based on the bit rates and the cable compliance bytes.
-- 
2.19.2


From f999691d5d3052788856d5c1801c6c1b0d3cbf21 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 27 Nov 2018 19:11:50 +0800
Subject: [PATCH 19/21] sctp: update frag_point when stream_interleave is set

[ Upstream commit 4135cce7fd0a0d755665c02728578c7c5afe4726 ]

sctp_assoc_update_frag_point() should be called whenever asoc->pathmtu
changes, but we missed one place in sctp_association_init(). It would
cause frag_point is zero when sending data.

As says in Jakub's reproducer, if sp->pathmtu is set by socketopt, the
new asoc->pathmtu inherits it in sctp_association_init(). Later when
transports are added and their pmtu >= asoc->pathmtu, it will never
call sctp_assoc_update_frag_point() to set frag_point.

This patch is to fix it by updating frag_point after asoc->pathmtu is
set as sp->pathmtu in sctp_association_init(). Note that it moved them
after sctp_stream_init(), as stream->si needs to be set first.

Frag_point's calculation is also related with datachunk's type, so it
needs to update frag_point when stream->si may be changed in
sctp_process_init().

v1->v2:
  - call sctp_assoc_update_frag_point() separately in sctp_process_init
    and sctp_association_init, per Marcelo's suggestion.

Fixes: 2f5e3c9df693 ("sctp: introduce sctp_assoc_update_frag_point")
Reported-by: Jakub Audykowicz <jakub.audykowicz@gmail.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/associola.c     | 7 ++++---
 net/sctp/sm_make_chunk.c | 3 +++
 2 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 3702f48a931d..914750b819b2 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -118,9 +118,6 @@ static struct sctp_association *sctp_association_init(
 	asoc->flowlabel = sp->flowlabel;
 	asoc->dscp = sp->dscp;
 
-	/* Initialize default path MTU. */
-	asoc->pathmtu = sp->pathmtu;
-
 	/* Set association default SACK delay */
 	asoc->sackdelay = msecs_to_jiffies(sp->sackdelay);
 	asoc->sackfreq = sp->sackfreq;
@@ -252,6 +249,10 @@ static struct sctp_association *sctp_association_init(
 			     0, gfp))
 		goto fail_init;
 
+	/* Initialize default path MTU. */
+	asoc->pathmtu = sp->pathmtu;
+	sctp_assoc_update_frag_point(asoc);
+
 	/* Assume that peer would support both address types unless we are
 	 * told otherwise.
 	 */
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 4a4fd1971255..f4ac6c592e13 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -2462,6 +2462,9 @@ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk,
 			     asoc->c.sinit_max_instreams, gfp))
 		goto clean_up;
 
+	/* Update frag_point when stream_interleave may get changed. */
+	sctp_assoc_update_frag_point(asoc);
+
 	if (!asoc->temp && sctp_assoc_set_id(asoc, gfp))
 		goto clean_up;
 
-- 
2.19.2


From b6fd7e47c0af12d5257b75e62c17d0d294f975f7 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Thu, 29 Nov 2018 14:14:48 +0100
Subject: [PATCH 20/21] net: restore call to netdev_queue_numa_node_write when
 resetting XPS

[ Upstream commit f28c020fb488e1a8b87469812017044bef88aa2b ]

Before commit 80d19669ecd3 ("net: Refactor XPS for CPUs and Rx queues"),
netif_reset_xps_queues() did netdev_queue_numa_node_write() for all the
queues being reset. Now, this is only done when the "active" variable in
clean_xps_maps() is false, ie when on all the CPUs, there's no active
XPS mapping left.

Fixes: 80d19669ecd3 ("net: Refactor XPS for CPUs and Rx queues")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 1ec7f34f4c17..4275b46d2b3f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2173,17 +2173,19 @@ static void clean_xps_maps(struct net_device *dev, const unsigned long *mask,
 		active |= remove_xps_queue_cpu(dev, dev_maps, j, offset,
 					       count);
 	if (!active) {
-		if (is_rxqs_map) {
+		if (is_rxqs_map)
 			RCU_INIT_POINTER(dev->xps_rxqs_map, NULL);
-		} else {
+		else
 			RCU_INIT_POINTER(dev->xps_cpus_map, NULL);
+		kfree_rcu(dev_maps, rcu);
+	}
 
-			for (i = offset + (count - 1); count--; i--)
-				netdev_queue_numa_node_write(
-					netdev_get_tx_queue(dev, i),
-							NUMA_NO_NODE);
+	if (!is_rxqs_map) {
+		for (i = offset + (count - 1); count--; i--) {
+			netdev_queue_numa_node_write(
+				netdev_get_tx_queue(dev, i),
+				NUMA_NO_NODE);
 		}
-		kfree_rcu(dev_maps, rcu);
 	}
 }
 
-- 
2.19.2


From 02d7e0c71b245b981407fd93a2defef4bea869fa Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Thu, 29 Nov 2018 14:14:49 +0100
Subject: [PATCH 21/21] net: fix XPS static_key accounting

[ Upstream commit 867d0ad476db89a1e8af3f297af402399a54eea5 ]

Commit 04157469b7b8 ("net: Use static_key for XPS maps") introduced a
static key for XPS, but the increments/decrements don't match.

First, the static key's counter is incremented once for each queue, but
only decremented once for a whole batch of queues, leading to large
unbalances.

Second, the xps_rxqs_needed key is decremented whenever we reset a batch
of queues, whether they had any rxqs mapping or not, so that if we setup
cpu-XPS on em1 and RXQS-XPS on em2, resetting the queues on em1 would
decrement the xps_rxqs_needed key.

This reworks the accounting scheme so that the xps_needed key is
incremented only once for each type of XPS for all the queues on a
device, and the xps_rxqs_needed key is incremented only once for all
queues. This is sufficient to let us retrieve queues via
get_xps_queue().

This patch introduces a new reset_xps_maps(), which reinitializes and
frees the appropriate map (xps_rxqs_map or xps_cpus_map), and drops a
reference to the needed keys:
 - both xps_needed and xps_rxqs_needed, in case of rxqs maps,
 - only xps_needed, in case of CPU maps.

Now, we also need to call reset_xps_maps() at the end of
__netif_set_xps_queue() when there's no active map left, for example
when writing '00000000,00000000' to all queues' xps_rxqs setting.

Fixes: 04157469b7b8 ("net: Use static_key for XPS maps")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 45 ++++++++++++++++++++++++---------------------
 1 file changed, 24 insertions(+), 21 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 4275b46d2b3f..1f1aae27d41f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2161,6 +2161,20 @@ static bool remove_xps_queue_cpu(struct net_device *dev,
 	return active;
 }
 
+static void reset_xps_maps(struct net_device *dev,
+			   struct xps_dev_maps *dev_maps,
+			   bool is_rxqs_map)
+{
+	if (is_rxqs_map) {
+		static_key_slow_dec_cpuslocked(&xps_rxqs_needed);
+		RCU_INIT_POINTER(dev->xps_rxqs_map, NULL);
+	} else {
+		RCU_INIT_POINTER(dev->xps_cpus_map, NULL);
+	}
+	static_key_slow_dec_cpuslocked(&xps_needed);
+	kfree_rcu(dev_maps, rcu);
+}
+
 static void clean_xps_maps(struct net_device *dev, const unsigned long *mask,
 			   struct xps_dev_maps *dev_maps, unsigned int nr_ids,
 			   u16 offset, u16 count, bool is_rxqs_map)
@@ -2172,13 +2186,8 @@ static void clean_xps_maps(struct net_device *dev, const unsigned long *mask,
 	     j < nr_ids;)
 		active |= remove_xps_queue_cpu(dev, dev_maps, j, offset,
 					       count);
-	if (!active) {
-		if (is_rxqs_map)
-			RCU_INIT_POINTER(dev->xps_rxqs_map, NULL);
-		else
-			RCU_INIT_POINTER(dev->xps_cpus_map, NULL);
-		kfree_rcu(dev_maps, rcu);
-	}
+	if (!active)
+		reset_xps_maps(dev, dev_maps, is_rxqs_map);
 
 	if (!is_rxqs_map) {
 		for (i = offset + (count - 1); count--; i--) {
@@ -2222,10 +2231,6 @@ static void netif_reset_xps_queues(struct net_device *dev, u16 offset,
 		       false);
 
 out_no_maps:
-	if (static_key_enabled(&xps_rxqs_needed))
-		static_key_slow_dec_cpuslocked(&xps_rxqs_needed);
-
-	static_key_slow_dec_cpuslocked(&xps_needed);
 	mutex_unlock(&xps_map_mutex);
 	cpus_read_unlock();
 }
@@ -2343,9 +2348,12 @@ int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask,
 	if (!new_dev_maps)
 		goto out_no_new_maps;
 
-	static_key_slow_inc_cpuslocked(&xps_needed);
-	if (is_rxqs_map)
-		static_key_slow_inc_cpuslocked(&xps_rxqs_needed);
+	if (!dev_maps) {
+		/* Increment static keys at most once per type */
+		static_key_slow_inc_cpuslocked(&xps_needed);
+		if (is_rxqs_map)
+			static_key_slow_inc_cpuslocked(&xps_rxqs_needed);
+	}
 
 	for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids),
 	     j < nr_ids;) {
@@ -2443,13 +2451,8 @@ int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask,
 	}
 
 	/* free map if not active */
-	if (!active) {
-		if (is_rxqs_map)
-			RCU_INIT_POINTER(dev->xps_rxqs_map, NULL);
-		else
-			RCU_INIT_POINTER(dev->xps_cpus_map, NULL);
-		kfree_rcu(dev_maps, rcu);
-	}
+	if (!active)
+		reset_xps_maps(dev, dev_maps, is_rxqs_map);
 
 out_no_maps:
 	mutex_unlock(&xps_map_mutex);
-- 
2.19.2

Re: [PATCHES] Networking

[Greg KH]

On Tue, Dec 11, 2018 at 10:31:38PM -0800, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.14 and
> v4.19 -stable, respectively.

All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 104 bytes --]


Please queue up the following networking bug fixes for v4.19 and v4.20
-stable, respectively.

Thanks!

[-- Attachment #2: net_419.mbox --]
[-- Type: Application/Octet-Stream, Size: 145563 bytes --]

From e67008e80d8938c3d1d8cd889b1b4fc605fe808d Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sat, 29 Dec 2018 13:56:36 -0800
Subject: [PATCH 01/58] ax25: fix a use-after-free in ax25_fillin_cb()

[ Upstream commit c433570458e49bccea5c551df628d058b3526289 ]

There are multiple issues here:

1. After freeing dev->ax25_ptr, we need to set it to NULL otherwise
   we may use a dangling pointer.

2. There is a race between ax25_setsockopt() and device notifier as
   reported by syzbot. Close it by holding RTNL lock.

3. We need to test if dev->ax25_ptr is NULL before using it.

Reported-and-tested-by: syzbot+ae6bb869cbed29b29040@syzkaller.appspotmail.com
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ax25/af_ax25.c  | 11 +++++++++--
 net/ax25/ax25_dev.c |  2 ++
 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index c603d33d5410..5d01edf8d819 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -653,15 +653,22 @@ static int ax25_setsockopt(struct socket *sock, int level, int optname,
 			break;
 		}
 
-		dev = dev_get_by_name(&init_net, devname);
+		rtnl_lock();
+		dev = __dev_get_by_name(&init_net, devname);
 		if (!dev) {
+			rtnl_unlock();
 			res = -ENODEV;
 			break;
 		}
 
 		ax25->ax25_dev = ax25_dev_ax25dev(dev);
+		if (!ax25->ax25_dev) {
+			rtnl_unlock();
+			res = -ENODEV;
+			break;
+		}
 		ax25_fillin_cb(ax25, ax25->ax25_dev);
-		dev_put(dev);
+		rtnl_unlock();
 		break;
 
 	default:
diff --git a/net/ax25/ax25_dev.c b/net/ax25/ax25_dev.c
index 9a3a301e1e2f..d92195cd7834 100644
--- a/net/ax25/ax25_dev.c
+++ b/net/ax25/ax25_dev.c
@@ -116,6 +116,7 @@ void ax25_dev_device_down(struct net_device *dev)
 	if ((s = ax25_dev_list) == ax25_dev) {
 		ax25_dev_list = s->next;
 		spin_unlock_bh(&ax25_dev_lock);
+		dev->ax25_ptr = NULL;
 		dev_put(dev);
 		kfree(ax25_dev);
 		return;
@@ -125,6 +126,7 @@ void ax25_dev_device_down(struct net_device *dev)
 		if (s->next == ax25_dev) {
 			s->next = ax25_dev->next;
 			spin_unlock_bh(&ax25_dev_lock);
+			dev->ax25_ptr = NULL;
 			dev_put(dev);
 			kfree(ax25_dev);
 			return;
-- 
2.20.1


From bc22f27ee79708db4ac8c763dfb565baec85265b Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Wed, 19 Dec 2018 23:23:00 +0100
Subject: [PATCH 02/58] gro_cell: add napi_disable in gro_cells_destroy

[ Upstream commit 8e1da73acded4751a93d4166458a7e640f37d26c ]

Add napi_disable routine in gro_cells_destroy since starting from
commit c42858eaf492 ("gro_cells: remove spinlock protecting receive
queues") gro_cell_poll and gro_cells_destroy can run concurrently on
napi_skbs list producing a kernel Oops if the tunnel interface is
removed while gro_cell_poll is running. The following Oops has been
triggered removing a vxlan device while the interface is receiving
traffic

[ 5628.948853] BUG: unable to handle kernel NULL pointer dereference at 0000000000000008
[ 5628.949981] PGD 0 P4D 0
[ 5628.950308] Oops: 0002 [#1] SMP PTI
[ 5628.950748] CPU: 0 PID: 9 Comm: ksoftirqd/0 Not tainted 4.20.0-rc6+ #41
[ 5628.952940] RIP: 0010:gro_cell_poll+0x49/0x80
[ 5628.955615] RSP: 0018:ffffc9000004fdd8 EFLAGS: 00010202
[ 5628.956250] RAX: 0000000000000000 RBX: ffffe8ffffc08150 RCX: 0000000000000000
[ 5628.957102] RDX: 0000000000000000 RSI: ffff88802356bf00 RDI: ffffe8ffffc08150
[ 5628.957940] RBP: 0000000000000026 R08: 0000000000000000 R09: 0000000000000000
[ 5628.958803] R10: 0000000000000001 R11: 0000000000000000 R12: 0000000000000040
[ 5628.959661] R13: ffffe8ffffc08100 R14: 0000000000000000 R15: 0000000000000040
[ 5628.960682] FS:  0000000000000000(0000) GS:ffff88803ea00000(0000) knlGS:0000000000000000
[ 5628.961616] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 5628.962359] CR2: 0000000000000008 CR3: 000000000221c000 CR4: 00000000000006b0
[ 5628.963188] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 5628.964034] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ 5628.964871] Call Trace:
[ 5628.965179]  net_rx_action+0xf0/0x380
[ 5628.965637]  __do_softirq+0xc7/0x431
[ 5628.966510]  run_ksoftirqd+0x24/0x30
[ 5628.966957]  smpboot_thread_fn+0xc5/0x160
[ 5628.967436]  kthread+0x113/0x130
[ 5628.968283]  ret_from_fork+0x3a/0x50
[ 5628.968721] Modules linked in:
[ 5628.969099] CR2: 0000000000000008
[ 5628.969510] ---[ end trace 9d9dedc7181661fe ]---
[ 5628.970073] RIP: 0010:gro_cell_poll+0x49/0x80
[ 5628.972965] RSP: 0018:ffffc9000004fdd8 EFLAGS: 00010202
[ 5628.973611] RAX: 0000000000000000 RBX: ffffe8ffffc08150 RCX: 0000000000000000
[ 5628.974504] RDX: 0000000000000000 RSI: ffff88802356bf00 RDI: ffffe8ffffc08150
[ 5628.975462] RBP: 0000000000000026 R08: 0000000000000000 R09: 0000000000000000
[ 5628.976413] R10: 0000000000000001 R11: 0000000000000000 R12: 0000000000000040
[ 5628.977375] R13: ffffe8ffffc08100 R14: 0000000000000000 R15: 0000000000000040
[ 5628.978296] FS:  0000000000000000(0000) GS:ffff88803ea00000(0000) knlGS:0000000000000000
[ 5628.979327] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 5628.980044] CR2: 0000000000000008 CR3: 000000000221c000 CR4: 00000000000006b0
[ 5628.980929] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 5628.981736] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ 5628.982409] Kernel panic - not syncing: Fatal exception in interrupt
[ 5628.983307] Kernel Offset: disabled

Fixes: c42858eaf492 ("gro_cells: remove spinlock protecting receive queues")
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/gro_cells.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c
index 4b54e5f107c6..acf45ddbe924 100644
--- a/net/core/gro_cells.c
+++ b/net/core/gro_cells.c
@@ -84,6 +84,7 @@ void gro_cells_destroy(struct gro_cells *gcells)
 	for_each_possible_cpu(i) {
 		struct gro_cell *cell = per_cpu_ptr(gcells->cells, i);
 
+		napi_disable(&cell->napi);
 		netif_napi_del(&cell->napi);
 		__skb_queue_purge(&cell->napi_skbs);
 	}
-- 
2.20.1


From c6dcae19ff0d5e7447a136b4dd6983c1e5aebce2 Mon Sep 17 00:00:00 2001
From: Tyrel Datwyler <tyreld@linux.vnet.ibm.com>
Date: Mon, 31 Dec 2018 15:43:01 -0600
Subject: [PATCH 03/58] ibmveth: fix DMA unmap error in ibmveth_xmit_start
 error path

[ Upstream commit 756af9c642329d54f048bac2a62f829b391f6944 ]

Commit 33a48ab105a7 ("ibmveth: Fix DMA unmap error") fixed an issue in the
normal code path of ibmveth_xmit_start() that was originally introduced by
Commit 6e8ab30ec677 ("ibmveth: Add scatter-gather support"). This original
fix missed the error path where dma_unmap_page is wrongly called on the
header portion in descs[0] which was mapped with dma_map_single. As a
result a failure to DMA map any of the frags results in a dmesg warning
when CONFIG_DMA_API_DEBUG is enabled.

------------[ cut here ]------------
DMA-API: ibmveth 30000002: device driver frees DMA memory with wrong function
  [device address=0x000000000a430000] [size=172 bytes] [mapped as page] [unmapped as single]
WARNING: CPU: 1 PID: 8426 at kernel/dma/debug.c:1085 check_unmap+0x4fc/0xe10
...
<snip>
...
DMA-API: Mapped at:
ibmveth_start_xmit+0x30c/0xb60
dev_hard_start_xmit+0x100/0x450
sch_direct_xmit+0x224/0x490
__qdisc_run+0x20c/0x980
__dev_queue_xmit+0x1bc/0xf20

This fixes the API misuse by unampping descs[0] with dma_unmap_single.

Fixes: 6e8ab30ec677 ("ibmveth: Add scatter-gather support")
Signed-off-by: Tyrel Datwyler <tyreld@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ibm/ibmveth.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index 525d8b89187b..91f48c078073 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -1172,11 +1172,15 @@ static netdev_tx_t ibmveth_start_xmit(struct sk_buff *skb,
 
 map_failed_frags:
 	last = i+1;
-	for (i = 0; i < last; i++)
+	for (i = 1; i < last; i++)
 		dma_unmap_page(&adapter->vdev->dev, descs[i].fields.address,
 			       descs[i].fields.flags_len & IBMVETH_BUF_LEN_MASK,
 			       DMA_TO_DEVICE);
 
+	dma_unmap_single(&adapter->vdev->dev,
+			 descs[0].fields.address,
+			 descs[0].fields.flags_len & IBMVETH_BUF_LEN_MASK,
+			 DMA_TO_DEVICE);
 map_failed:
 	if (!firmware_has_feature(FW_FEATURE_CMO))
 		netdev_err(netdev, "tx: unable to map xmit buffer\n");
-- 
2.20.1


From 64748b1135b53857492d1760d54f3de5a5d38bd8 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Sun, 23 Dec 2018 12:52:18 -0500
Subject: [PATCH 04/58] ieee802154: lowpan_header_create check must check daddr

[ Upstream commit 40c3ff6d5e0809505a067dd423c110c5658c478c ]

Packet sockets may call dev_header_parse with NULL daddr. Make
lowpan_header_ops.create fail.

Fixes: 87a93e4eceb4 ("ieee802154: change needed headroom/tailroom")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Alexander Aring <aring@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ieee802154/6lowpan/tx.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ieee802154/6lowpan/tx.c b/net/ieee802154/6lowpan/tx.c
index ca53efa17be1..8bec827081cd 100644
--- a/net/ieee802154/6lowpan/tx.c
+++ b/net/ieee802154/6lowpan/tx.c
@@ -48,6 +48,9 @@ int lowpan_header_create(struct sk_buff *skb, struct net_device *ldev,
 	const struct ipv6hdr *hdr = ipv6_hdr(skb);
 	struct neighbour *n;
 
+	if (!daddr)
+		return -EINVAL;
+
 	/* TODO:
 	 * if this package isn't ipv6 one, where should it be routed?
 	 */
-- 
2.20.1


From aede2ff941172bea176cde6b699944828241c375 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 11 Dec 2018 14:10:08 -0600
Subject: [PATCH 05/58] ip6mr: Fix potential Spectre v1 vulnerability

[ Upstream commit 69d2c86766da2ded2b70281f1bf242cb0d58a778 ]

vr.mifi is indirectly controlled by user-space, hence leading to
a potential exploitation of the Spectre variant 1 vulnerability.

This issue was detected with the help of Smatch:

net/ipv6/ip6mr.c:1845 ip6mr_ioctl() warn: potential spectre issue 'mrt->vif_table' [r] (local cap)
net/ipv6/ip6mr.c:1919 ip6mr_compat_ioctl() warn: potential spectre issue 'mrt->vif_table' [r] (local cap)

Fix this by sanitizing vr.mifi before using it to index mrt->vif_table'

Notice that given that speculation windows are large, the policy is
to kill the speculation on the first load and not worry if it can be
completed with a dependent load/store [1].

[1] https://marc.info/?l=linux-kernel&m=152449131114778&w=2

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6mr.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index d0b7e0249c13..fb70bbd9e6d1 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -52,6 +52,8 @@
 #include <net/ip6_checksum.h>
 #include <linux/netconf.h>
 
+#include <linux/nospec.h>
+
 struct ip6mr_rule {
 	struct fib_rule		common;
 };
@@ -1831,6 +1833,7 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg)
 			return -EFAULT;
 		if (vr.mifi >= mrt->maxvif)
 			return -EINVAL;
+		vr.mifi = array_index_nospec(vr.mifi, mrt->maxvif);
 		read_lock(&mrt_lock);
 		vif = &mrt->vif_table[vr.mifi];
 		if (VIF_EXISTS(mrt, vr.mifi)) {
@@ -1905,6 +1908,7 @@ int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg)
 			return -EFAULT;
 		if (vr.mifi >= mrt->maxvif)
 			return -EINVAL;
+		vr.mifi = array_index_nospec(vr.mifi, mrt->maxvif);
 		read_lock(&mrt_lock);
 		vif = &mrt->vif_table[vr.mifi];
 		if (VIF_EXISTS(mrt, vr.mifi)) {
-- 
2.20.1


From 94e2d01d68c326be2b1428018c2af61d9f756bd1 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 10 Dec 2018 12:41:24 -0600
Subject: [PATCH 06/58] ipv4: Fix potential Spectre v1 vulnerability

[ Upstream commit 5648451e30a0d13d11796574919a359025d52cce ]

vr.vifi is indirectly controlled by user-space, hence leading to
a potential exploitation of the Spectre variant 1 vulnerability.

This issue was detected with the help of Smatch:

net/ipv4/ipmr.c:1616 ipmr_ioctl() warn: potential spectre issue 'mrt->vif_table' [r] (local cap)
net/ipv4/ipmr.c:1690 ipmr_compat_ioctl() warn: potential spectre issue 'mrt->vif_table' [r] (local cap)

Fix this by sanitizing vr.vifi before using it to index mrt->vif_table'

Notice that given that speculation windows are large, the policy is
to kill the speculation on the first load and not worry if it can be
completed with a dependent load/store [1].

[1] https://marc.info/?l=linux-kernel&m=152449131114778&w=2

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ipmr.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 5660adcf7a04..f6275aa19b6a 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -69,6 +69,8 @@
 #include <net/nexthop.h>
 #include <net/switchdev.h>
 
+#include <linux/nospec.h>
+
 struct ipmr_rule {
 	struct fib_rule		common;
 };
@@ -1612,6 +1614,7 @@ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg)
 			return -EFAULT;
 		if (vr.vifi >= mrt->maxvif)
 			return -EINVAL;
+		vr.vifi = array_index_nospec(vr.vifi, mrt->maxvif);
 		read_lock(&mrt_lock);
 		vif = &mrt->vif_table[vr.vifi];
 		if (VIF_EXISTS(mrt, vr.vifi)) {
@@ -1686,6 +1689,7 @@ int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg)
 			return -EFAULT;
 		if (vr.vifi >= mrt->maxvif)
 			return -EINVAL;
+		vr.vifi = array_index_nospec(vr.vifi, mrt->maxvif);
 		read_lock(&mrt_lock);
 		vif = &mrt->vif_table[vr.vifi];
 		if (VIF_EXISTS(mrt, vr.vifi)) {
-- 
2.20.1


From a7ce8a842a87b95583562842fea35120197c113f Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Tue, 18 Dec 2018 21:17:44 -0800
Subject: [PATCH 07/58] ipv6: explicitly initialize udp6_addr in
 udp_sock_create6()

[ Upstream commit fb24274546310872eeeaf3d1d53799d8414aa0f2 ]

syzbot reported the use of uninitialized udp6_addr::sin6_scope_id.
We can just set ::sin6_scope_id to zero, as tunnels are unlikely
to use an IPv6 address that needs a scope id and there is no
interface to bind in this context.

For net-next, it looks different as we have cfg->bind_ifindex there
so we can probably call ipv6_iface_scope_id().

Same for ::sin6_flowinfo, tunnels don't use it.

Fixes: 8024e02879dd ("udp: Add udp_sock_create for UDP tunnels to open listener socket")
Reported-by: syzbot+c56449ed3652e6720f30@syzkaller.appspotmail.com
Cc: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_udp_tunnel.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c
index b283f293ee4a..caad40d6e74d 100644
--- a/net/ipv6/ip6_udp_tunnel.c
+++ b/net/ipv6/ip6_udp_tunnel.c
@@ -15,7 +15,7 @@
 int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg,
 		     struct socket **sockp)
 {
-	struct sockaddr_in6 udp6_addr;
+	struct sockaddr_in6 udp6_addr = {};
 	int err;
 	struct socket *sock = NULL;
 
@@ -42,6 +42,7 @@ int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg,
 		goto error;
 
 	if (cfg->peer_udp_port) {
+		memset(&udp6_addr, 0, sizeof(udp6_addr));
 		udp6_addr.sin6_family = AF_INET6;
 		memcpy(&udp6_addr.sin6_addr, &cfg->peer_ip6,
 		       sizeof(udp6_addr.sin6_addr));
-- 
2.20.1


From d0f521467fa93f84b00cf4273f38394348937c17 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 21 Dec 2018 07:47:51 -0800
Subject: [PATCH 08/58] ipv6: tunnels: fix two use-after-free

[ Upstream commit cbb49697d5512ce9e61b45ce75d3ee43d7ea5524 ]

xfrm6_policy_check() might have re-allocated skb->head, we need
to reload ipv6 header pointer.

sysbot reported :

BUG: KASAN: use-after-free in __ipv6_addr_type+0x302/0x32f net/ipv6/addrconf_core.c:40
Read of size 4 at addr ffff888191b8cb70 by task syz-executor2/1304

CPU: 0 PID: 1304 Comm: syz-executor2 Not tainted 4.20.0-rc7+ #356
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x244/0x39d lib/dump_stack.c:113
 print_address_description.cold.7+0x9/0x1ff mm/kasan/report.c:256
 kasan_report_error mm/kasan/report.c:354 [inline]
 kasan_report.cold.8+0x242/0x309 mm/kasan/report.c:412
 __asan_report_load4_noabort+0x14/0x20 mm/kasan/report.c:432
 __ipv6_addr_type+0x302/0x32f net/ipv6/addrconf_core.c:40
 ipv6_addr_type include/net/ipv6.h:403 [inline]
 ip6_tnl_get_cap+0x27/0x190 net/ipv6/ip6_tunnel.c:727
 ip6_tnl_rcv_ctl+0xdb/0x2a0 net/ipv6/ip6_tunnel.c:757
 vti6_rcv+0x336/0x8f3 net/ipv6/ip6_vti.c:321
 xfrm6_ipcomp_rcv+0x1a5/0x3a0 net/ipv6/xfrm6_protocol.c:132
 ip6_protocol_deliver_rcu+0x372/0x1940 net/ipv6/ip6_input.c:394
 ip6_input_finish+0x84/0x170 net/ipv6/ip6_input.c:434
 NF_HOOK include/linux/netfilter.h:289 [inline]
 ip6_input+0xe9/0x600 net/ipv6/ip6_input.c:443
IPVS: ftp: loaded support on port[0] = 21
 ip6_mc_input+0x514/0x11c0 net/ipv6/ip6_input.c:537
 dst_input include/net/dst.h:450 [inline]
 ip6_rcv_finish+0x17a/0x330 net/ipv6/ip6_input.c:76
 NF_HOOK include/linux/netfilter.h:289 [inline]
 ipv6_rcv+0x115/0x640 net/ipv6/ip6_input.c:272
 __netif_receive_skb_one_core+0x14d/0x200 net/core/dev.c:4973
 __netif_receive_skb+0x2c/0x1e0 net/core/dev.c:5083
 process_backlog+0x24e/0x7a0 net/core/dev.c:5923
 napi_poll net/core/dev.c:6346 [inline]
 net_rx_action+0x7fa/0x19b0 net/core/dev.c:6412
 __do_softirq+0x308/0xb7e kernel/softirq.c:292
 do_softirq_own_stack+0x2a/0x40 arch/x86/entry/entry_64.S:1027
 </IRQ>
 do_softirq.part.14+0x126/0x160 kernel/softirq.c:337
 do_softirq+0x19/0x20 kernel/softirq.c:340
 netif_rx_ni+0x521/0x860 net/core/dev.c:4569
 dev_loopback_xmit+0x287/0x8c0 net/core/dev.c:3576
 NF_HOOK include/linux/netfilter.h:289 [inline]
 ip6_finish_output2+0x193a/0x2930 net/ipv6/ip6_output.c:84
 ip6_fragment+0x2b06/0x3850 net/ipv6/ip6_output.c:727
 ip6_finish_output+0x6b7/0xc50 net/ipv6/ip6_output.c:152
 NF_HOOK_COND include/linux/netfilter.h:278 [inline]
 ip6_output+0x232/0x9d0 net/ipv6/ip6_output.c:171
 dst_output include/net/dst.h:444 [inline]
 ip6_local_out+0xc5/0x1b0 net/ipv6/output_core.c:176
 ip6_send_skb+0xbc/0x340 net/ipv6/ip6_output.c:1727
 ip6_push_pending_frames+0xc5/0xf0 net/ipv6/ip6_output.c:1747
 rawv6_push_pending_frames net/ipv6/raw.c:615 [inline]
 rawv6_sendmsg+0x3a3e/0x4b40 net/ipv6/raw.c:945
kobject: 'queues' (0000000089e6eea2): kobject_add_internal: parent: 'tunl0', set: '<NULL>'
kobject: 'queues' (0000000089e6eea2): kobject_uevent_env
 inet_sendmsg+0x1a1/0x690 net/ipv4/af_inet.c:798
kobject: 'queues' (0000000089e6eea2): kobject_uevent_env: filter function caused the event to drop!
 sock_sendmsg_nosec net/socket.c:621 [inline]
 sock_sendmsg+0xd5/0x120 net/socket.c:631
 sock_write_iter+0x35e/0x5c0 net/socket.c:900
 call_write_iter include/linux/fs.h:1857 [inline]
 new_sync_write fs/read_write.c:474 [inline]
 __vfs_write+0x6b8/0x9f0 fs/read_write.c:487
kobject: 'rx-0' (00000000e2d902d9): kobject_add_internal: parent: 'queues', set: 'queues'
kobject: 'rx-0' (00000000e2d902d9): kobject_uevent_env
 vfs_write+0x1fc/0x560 fs/read_write.c:549
 ksys_write+0x101/0x260 fs/read_write.c:598
kobject: 'rx-0' (00000000e2d902d9): fill_kobj_path: path = '/devices/virtual/net/tunl0/queues/rx-0'
 __do_sys_write fs/read_write.c:610 [inline]
 __se_sys_write fs/read_write.c:607 [inline]
 __x64_sys_write+0x73/0xb0 fs/read_write.c:607
 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290
kobject: 'tx-0' (00000000443b70ac): kobject_add_internal: parent: 'queues', set: 'queues'
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x457669
Code: fd b3 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 cb b3 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f9bd200bc78 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000457669
RDX: 000000000000058f RSI: 00000000200033c0 RDI: 0000000000000003
kobject: 'tx-0' (00000000443b70ac): kobject_uevent_env
RBP: 000000000072bf00 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00007f9bd200c6d4
R13: 00000000004c2dcc R14: 00000000004da398 R15: 00000000ffffffff

Allocated by task 1304:
 save_stack+0x43/0xd0 mm/kasan/kasan.c:448
 set_track mm/kasan/kasan.c:460 [inline]
 kasan_kmalloc+0xc7/0xe0 mm/kasan/kasan.c:553
 __do_kmalloc_node mm/slab.c:3684 [inline]
 __kmalloc_node_track_caller+0x50/0x70 mm/slab.c:3698
 __kmalloc_reserve.isra.41+0x41/0xe0 net/core/skbuff.c:140
 __alloc_skb+0x155/0x760 net/core/skbuff.c:208
kobject: 'tx-0' (00000000443b70ac): fill_kobj_path: path = '/devices/virtual/net/tunl0/queues/tx-0'
 alloc_skb include/linux/skbuff.h:1011 [inline]
 __ip6_append_data.isra.49+0x2f1a/0x3f50 net/ipv6/ip6_output.c:1450
 ip6_append_data+0x1bc/0x2d0 net/ipv6/ip6_output.c:1619
 rawv6_sendmsg+0x15ab/0x4b40 net/ipv6/raw.c:938
 inet_sendmsg+0x1a1/0x690 net/ipv4/af_inet.c:798
 sock_sendmsg_nosec net/socket.c:621 [inline]
 sock_sendmsg+0xd5/0x120 net/socket.c:631
 ___sys_sendmsg+0x7fd/0x930 net/socket.c:2116
 __sys_sendmsg+0x11d/0x280 net/socket.c:2154
 __do_sys_sendmsg net/socket.c:2163 [inline]
 __se_sys_sendmsg net/socket.c:2161 [inline]
 __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2161
 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
kobject: 'gre0' (00000000cb1b2d7b): kobject_add_internal: parent: 'net', set: 'devices'

Freed by task 1304:
 save_stack+0x43/0xd0 mm/kasan/kasan.c:448
 set_track mm/kasan/kasan.c:460 [inline]
 __kasan_slab_free+0x102/0x150 mm/kasan/kasan.c:521
 kasan_slab_free+0xe/0x10 mm/kasan/kasan.c:528
 __cache_free mm/slab.c:3498 [inline]
 kfree+0xcf/0x230 mm/slab.c:3817
 skb_free_head+0x93/0xb0 net/core/skbuff.c:553
 pskb_expand_head+0x3b2/0x10d0 net/core/skbuff.c:1498
 __pskb_pull_tail+0x156/0x18a0 net/core/skbuff.c:1896
 pskb_may_pull include/linux/skbuff.h:2188 [inline]
 _decode_session6+0xd11/0x14d0 net/ipv6/xfrm6_policy.c:150
 __xfrm_decode_session+0x71/0x140 net/xfrm/xfrm_policy.c:3272
kobject: 'gre0' (00000000cb1b2d7b): kobject_uevent_env
 __xfrm_policy_check+0x380/0x2c40 net/xfrm/xfrm_policy.c:3322
 __xfrm_policy_check2 include/net/xfrm.h:1170 [inline]
 xfrm_policy_check include/net/xfrm.h:1175 [inline]
 xfrm6_policy_check include/net/xfrm.h:1185 [inline]
 vti6_rcv+0x4bd/0x8f3 net/ipv6/ip6_vti.c:316
 xfrm6_ipcomp_rcv+0x1a5/0x3a0 net/ipv6/xfrm6_protocol.c:132
 ip6_protocol_deliver_rcu+0x372/0x1940 net/ipv6/ip6_input.c:394
 ip6_input_finish+0x84/0x170 net/ipv6/ip6_input.c:434
 NF_HOOK include/linux/netfilter.h:289 [inline]
 ip6_input+0xe9/0x600 net/ipv6/ip6_input.c:443
 ip6_mc_input+0x514/0x11c0 net/ipv6/ip6_input.c:537
 dst_input include/net/dst.h:450 [inline]
 ip6_rcv_finish+0x17a/0x330 net/ipv6/ip6_input.c:76
 NF_HOOK include/linux/netfilter.h:289 [inline]
 ipv6_rcv+0x115/0x640 net/ipv6/ip6_input.c:272
 __netif_receive_skb_one_core+0x14d/0x200 net/core/dev.c:4973
 __netif_receive_skb+0x2c/0x1e0 net/core/dev.c:5083
 process_backlog+0x24e/0x7a0 net/core/dev.c:5923
kobject: 'gre0' (00000000cb1b2d7b): fill_kobj_path: path = '/devices/virtual/net/gre0'
 napi_poll net/core/dev.c:6346 [inline]
 net_rx_action+0x7fa/0x19b0 net/core/dev.c:6412
 __do_softirq+0x308/0xb7e kernel/softirq.c:292

The buggy address belongs to the object at ffff888191b8cac0
 which belongs to the cache kmalloc-512 of size 512
The buggy address is located 176 bytes inside of
 512-byte region [ffff888191b8cac0, ffff888191b8ccc0)
The buggy address belongs to the page:
page:ffffea000646e300 count:1 mapcount:0 mapping:ffff8881da800940 index:0x0
flags: 0x2fffc0000000200(slab)
raw: 02fffc0000000200 ffffea0006eaaa48 ffffea00065356c8 ffff8881da800940
raw: 0000000000000000 ffff888191b8c0c0 0000000100000006 0000000000000000
page dumped because: kasan: bad access detected
kobject: 'queues' (000000005fd6226e): kobject_add_internal: parent: 'gre0', set: '<NULL>'

Memory state around the buggy address:
 ffff888191b8ca00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 ffff888191b8ca80: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb
>ffff888191b8cb00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                                                             ^
 ffff888191b8cb80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff888191b8cc00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb

Fixes: 0d3c703a9d17 ("ipv6: Cleanup IPv6 tunnel receive path")
Fixes: ed1efb2aefbb ("ipv6: Add support for IPsec virtual tunnel interfaces")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 1 +
 net/ipv6/ip6_vti.c    | 1 +
 2 files changed, 2 insertions(+)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index a9d06d4dd057..99179b9c8384 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -901,6 +901,7 @@ static int ipxip6_rcv(struct sk_buff *skb, u8 ipproto,
 			goto drop;
 		if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
 			goto drop;
+		ipv6h = ipv6_hdr(skb);
 		if (!ip6_tnl_rcv_ctl(t, &ipv6h->daddr, &ipv6h->saddr))
 			goto drop;
 		if (iptunnel_pull_header(skb, 0, tpi->proto, false))
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index eeaf7455d51e..706fe42e4928 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -318,6 +318,7 @@ static int vti6_rcv(struct sk_buff *skb)
 			return 0;
 		}
 
+		ipv6h = ipv6_hdr(skb);
 		if (!ip6_tnl_rcv_ctl(t, &ipv6h->daddr, &ipv6h->saddr)) {
 			t->dev->stats.rx_dropped++;
 			rcu_read_unlock();
-- 
2.20.1


From c8b9a5ddbf4178caae680a199f43fb50f7141d99 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Sun, 30 Dec 2018 17:24:36 -0500
Subject: [PATCH 09/58] ip: validate header length on virtual device xmit

[ Upstream commit cb9f1b783850b14cbd7f87d061d784a666dfba1f ]

KMSAN detected read beyond end of buffer in vti and sit devices when
passing truncated packets with PF_PACKET. The issue affects additional
ip tunnel devices.

Extend commit 76c0ddd8c3a6 ("ip6_tunnel: be careful when accessing the
inner header") and commit ccfec9e5cb2d ("ip_tunnel: be careful when
accessing the inner header").

Move the check to a separate helper and call at the start of each
ndo_start_xmit function in net/ipv4 and net/ipv6.

Minor changes:
- convert dev_kfree_skb to kfree_skb on error path,
  as dev_kfree_skb calls consume_skb which is not for error paths.
- use pskb_network_may_pull even though that is pedantic here,
  as the same as pskb_may_pull for devices without llheaders.
- do not cache ipv6 hdrs if used only once
  (unsafe across pskb_may_pull, was more relevant to earlier patch)

Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_tunnels.h | 20 ++++++++++++++++++++
 net/ipv4/ip_gre.c        |  9 +++++++++
 net/ipv4/ip_tunnel.c     |  9 ---------
 net/ipv4/ip_vti.c        | 12 +++++++++---
 net/ipv6/ip6_gre.c       | 10 +++++++---
 net/ipv6/ip6_tunnel.c    | 10 +++-------
 net/ipv6/ip6_vti.c       |  8 ++++----
 net/ipv6/ip6mr.c         | 17 +++++++++++------
 net/ipv6/sit.c           |  3 +++
 9 files changed, 66 insertions(+), 32 deletions(-)

diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index b0d022ff6ea1..e11423530d64 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -326,6 +326,26 @@ int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *op,
 int ip_tunnel_encap_setup(struct ip_tunnel *t,
 			  struct ip_tunnel_encap *ipencap);
 
+static inline bool pskb_inet_may_pull(struct sk_buff *skb)
+{
+	int nhlen;
+
+	switch (skb->protocol) {
+#if IS_ENABLED(CONFIG_IPV6)
+	case htons(ETH_P_IPV6):
+		nhlen = sizeof(struct ipv6hdr);
+		break;
+#endif
+	case htons(ETH_P_IP):
+		nhlen = sizeof(struct iphdr);
+		break;
+	default:
+		nhlen = 0;
+	}
+
+	return pskb_network_may_pull(skb, nhlen);
+}
+
 static inline int ip_encap_hlen(struct ip_tunnel_encap *e)
 {
 	const struct ip_tunnel_encap_ops *ops;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 8cce0e9ea08c..5ef5df3a06f1 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -677,6 +677,9 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb,
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	const struct iphdr *tnl_params;
 
+	if (!pskb_inet_may_pull(skb))
+		goto free_skb;
+
 	if (tunnel->collect_md) {
 		gre_fb_xmit(skb, dev, skb->protocol);
 		return NETDEV_TX_OK;
@@ -720,6 +723,9 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb,
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	bool truncate = false;
 
+	if (!pskb_inet_may_pull(skb))
+		goto free_skb;
+
 	if (tunnel->collect_md) {
 		erspan_fb_xmit(skb, dev, skb->protocol);
 		return NETDEV_TX_OK;
@@ -763,6 +769,9 @@ static netdev_tx_t gre_tap_xmit(struct sk_buff *skb,
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 
+	if (!pskb_inet_may_pull(skb))
+		goto free_skb;
+
 	if (tunnel->collect_md) {
 		gre_fb_xmit(skb, dev, htons(ETH_P_TEB));
 		return NETDEV_TX_OK;
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 284a22154b4e..c4f5602308ed 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -627,7 +627,6 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		    const struct iphdr *tnl_params, u8 protocol)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
-	unsigned int inner_nhdr_len = 0;
 	const struct iphdr *inner_iph;
 	struct flowi4 fl4;
 	u8     tos, ttl;
@@ -637,14 +636,6 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	__be32 dst;
 	bool connected;
 
-	/* ensure we can access the inner net header, for several users below */
-	if (skb->protocol == htons(ETH_P_IP))
-		inner_nhdr_len = sizeof(struct iphdr);
-	else if (skb->protocol == htons(ETH_P_IPV6))
-		inner_nhdr_len = sizeof(struct ipv6hdr);
-	if (unlikely(!pskb_may_pull(skb, inner_nhdr_len)))
-		goto tx_error;
-
 	inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
 	connected = (tunnel->parms.iph.daddr != 0);
 
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index f38cb21d773d..7f56944b020f 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -241,6 +241,9 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	struct flowi fl;
 
+	if (!pskb_inet_may_pull(skb))
+		goto tx_err;
+
 	memset(&fl, 0, sizeof(fl));
 
 	switch (skb->protocol) {
@@ -253,15 +256,18 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 		memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
 		break;
 	default:
-		dev->stats.tx_errors++;
-		dev_kfree_skb(skb);
-		return NETDEV_TX_OK;
+		goto tx_err;
 	}
 
 	/* override mark with tunnel output key */
 	fl.flowi_mark = be32_to_cpu(tunnel->parms.o_key);
 
 	return vti_xmit(skb, dev, &fl);
+
+tx_err:
+	dev->stats.tx_errors++;
+	kfree_skb(skb);
+	return NETDEV_TX_OK;
 }
 
 static int vti4_err(struct sk_buff *skb, u32 info)
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index e493b041d4ac..c270726b01b0 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -897,6 +897,9 @@ static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb,
 	struct net_device_stats *stats = &t->dev->stats;
 	int ret;
 
+	if (!pskb_inet_may_pull(skb))
+		goto tx_err;
+
 	if (!ip6_tnl_xmit_ctl(t, &t->parms.laddr, &t->parms.raddr))
 		goto tx_err;
 
@@ -939,6 +942,9 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 	int nhoff;
 	int thoff;
 
+	if (!pskb_inet_may_pull(skb))
+		goto tx_err;
+
 	if (!ip6_tnl_xmit_ctl(t, &t->parms.laddr, &t->parms.raddr))
 		goto tx_err;
 
@@ -1011,8 +1017,6 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 			goto tx_err;
 		}
 	} else {
-		struct ipv6hdr *ipv6h = ipv6_hdr(skb);
-
 		switch (skb->protocol) {
 		case htons(ETH_P_IP):
 			memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
@@ -1020,7 +1024,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 						 &dsfield, &encap_limit);
 			break;
 		case htons(ETH_P_IPV6):
-			if (ipv6_addr_equal(&t->parms.raddr, &ipv6h->saddr))
+			if (ipv6_addr_equal(&t->parms.raddr, &ipv6_hdr(skb)->saddr))
 				goto tx_err;
 			if (prepare_ip6gre_xmit_ipv6(skb, dev, &fl6,
 						     &dsfield, &encap_limit))
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 99179b9c8384..0c6403cf8b52 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1243,10 +1243,6 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	u8 tproto;
 	int err;
 
-	/* ensure we can access the full inner ip header */
-	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
-		return -1;
-
 	iph = ip_hdr(skb);
 	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
 
@@ -1321,9 +1317,6 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	u8 tproto;
 	int err;
 
-	if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
-		return -1;
-
 	ipv6h = ipv6_hdr(skb);
 	tproto = READ_ONCE(t->parms.proto);
 	if ((tproto != IPPROTO_IPV6 && tproto != 0) ||
@@ -1405,6 +1398,9 @@ ip6_tnl_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct net_device_stats *stats = &t->dev->stats;
 	int ret;
 
+	if (!pskb_inet_may_pull(skb))
+		goto tx_err;
+
 	switch (skb->protocol) {
 	case htons(ETH_P_IP):
 		ret = ip4ip6_tnl_xmit(skb, dev);
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 706fe42e4928..8b6eefff2f7e 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -522,18 +522,18 @@ vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ip6_tnl *t = netdev_priv(dev);
 	struct net_device_stats *stats = &t->dev->stats;
-	struct ipv6hdr *ipv6h;
 	struct flowi fl;
 	int ret;
 
+	if (!pskb_inet_may_pull(skb))
+		goto tx_err;
+
 	memset(&fl, 0, sizeof(fl));
 
 	switch (skb->protocol) {
 	case htons(ETH_P_IPV6):
-		ipv6h = ipv6_hdr(skb);
-
 		if ((t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) ||
-		    vti6_addr_conflict(t, ipv6h))
+		    vti6_addr_conflict(t, ipv6_hdr(skb)))
 			goto tx_err;
 
 		xfrm_decode_session(skb, &fl, AF_INET6);
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index fb70bbd9e6d1..331e6b6dd252 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -51,6 +51,7 @@
 #include <linux/export.h>
 #include <net/ip6_checksum.h>
 #include <linux/netconf.h>
+#include <net/ip_tunnels.h>
 
 #include <linux/nospec.h>
 
@@ -593,13 +594,12 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb,
 		.flowi6_iif	= skb->skb_iif ? : LOOPBACK_IFINDEX,
 		.flowi6_mark	= skb->mark,
 	};
-	int err;
 
-	err = ip6mr_fib_lookup(net, &fl6, &mrt);
-	if (err < 0) {
-		kfree_skb(skb);
-		return err;
-	}
+	if (!pskb_inet_may_pull(skb))
+		goto tx_err;
+
+	if (ip6mr_fib_lookup(net, &fl6, &mrt) < 0)
+		goto tx_err;
 
 	read_lock(&mrt_lock);
 	dev->stats.tx_bytes += skb->len;
@@ -608,6 +608,11 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb,
 	read_unlock(&mrt_lock);
 	kfree_skb(skb);
 	return NETDEV_TX_OK;
+
+tx_err:
+	dev->stats.tx_errors++;
+	kfree_skb(skb);
+	return NETDEV_TX_OK;
 }
 
 static int reg_vif_get_iflink(const struct net_device *dev)
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index e9400ffa7875..eb162bd0e041 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1021,6 +1021,9 @@ static netdev_tx_t sit_tunnel_xmit__(struct sk_buff *skb,
 static netdev_tx_t sit_tunnel_xmit(struct sk_buff *skb,
 				   struct net_device *dev)
 {
+	if (!pskb_inet_may_pull(skb))
+		goto tx_err;
+
 	switch (skb->protocol) {
 	case htons(ETH_P_IP):
 		sit_tunnel_xmit__(skb, dev, IPPROTO_IPIP);
-- 
2.20.1


From e16c0206835df8f8a4b20217bdae4e4110ae77d7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 2 Jan 2019 09:20:27 -0800
Subject: [PATCH 10/58] isdn: fix kernel-infoleak in capi_unlocked_ioctl

[ Upstream commit d63967e475ae10f286dbd35e189cb241e0b1f284 ]

Since capi_ioctl() copies 64 bytes after calling
capi20_get_manufacturer() we need to ensure to not leak
information to user.

BUG: KMSAN: kernel-infoleak in _copy_to_user+0x16b/0x1f0 lib/usercopy.c:32
CPU: 0 PID: 11245 Comm: syz-executor633 Not tainted 4.20.0-rc7+ #2
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x173/0x1d0 lib/dump_stack.c:113
 kmsan_report+0x12e/0x2a0 mm/kmsan/kmsan.c:613
 kmsan_internal_check_memory+0x9d4/0xb00 mm/kmsan/kmsan.c:704
 kmsan_copy_to_user+0xab/0xc0 mm/kmsan/kmsan_hooks.c:601
 _copy_to_user+0x16b/0x1f0 lib/usercopy.c:32
 capi_ioctl include/linux/uaccess.h:177 [inline]
 capi_unlocked_ioctl+0x1a0b/0x1bf0 drivers/isdn/capi/capi.c:939
 do_vfs_ioctl+0xebd/0x2bf0 fs/ioctl.c:46
 ksys_ioctl fs/ioctl.c:713 [inline]
 __do_sys_ioctl fs/ioctl.c:720 [inline]
 __se_sys_ioctl+0x1da/0x270 fs/ioctl.c:718
 __x64_sys_ioctl+0x4a/0x70 fs/ioctl.c:718
 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291
 entry_SYSCALL_64_after_hwframe+0x63/0xe7
RIP: 0033:0x440019
Code: 18 89 d0 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 fb 13 fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007ffdd4659fb8 EFLAGS: 00000213 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 0000000000440019
RDX: 0000000020000080 RSI: 00000000c0044306 RDI: 0000000000000003
RBP: 00000000006ca018 R08: 0000000000000000 R09: 00000000004002c8
R10: 0000000000000000 R11: 0000000000000213 R12: 00000000004018a0
R13: 0000000000401930 R14: 0000000000000000 R15: 0000000000000000

Local variable description: ----data.i@capi_unlocked_ioctl
Variable was created at:
 capi_ioctl drivers/isdn/capi/capi.c:747 [inline]
 capi_unlocked_ioctl+0x82/0x1bf0 drivers/isdn/capi/capi.c:939
 do_vfs_ioctl+0xebd/0x2bf0 fs/ioctl.c:46

Bytes 12-63 of 64 are uninitialized
Memory access of size 64 starts at ffff88807ac5fce8
Data copied to user address 0000000020000080

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Karsten Keil <isdn@linux-pingi.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/capi/kcapi.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/isdn/capi/kcapi.c b/drivers/isdn/capi/kcapi.c
index 0ff517d3c98f..a4ceb61c5b60 100644
--- a/drivers/isdn/capi/kcapi.c
+++ b/drivers/isdn/capi/kcapi.c
@@ -852,7 +852,7 @@ u16 capi20_get_manufacturer(u32 contr, u8 *buf)
 	u16 ret;
 
 	if (contr == 0) {
-		strlcpy(buf, capi_manufakturer, CAPI_MANUFACTURER_LEN);
+		strncpy(buf, capi_manufakturer, CAPI_MANUFACTURER_LEN);
 		return CAPI_NOERROR;
 	}
 
@@ -860,7 +860,7 @@ u16 capi20_get_manufacturer(u32 contr, u8 *buf)
 
 	ctr = get_capi_ctr_by_nr(contr);
 	if (ctr && ctr->state == CAPI_CTR_RUNNING) {
-		strlcpy(buf, ctr->manu, CAPI_MANUFACTURER_LEN);
+		strncpy(buf, ctr->manu, CAPI_MANUFACTURER_LEN);
 		ret = CAPI_NOERROR;
 	} else
 		ret = CAPI_REGNOTINSTALLED;
-- 
2.20.1


From a6004ea72528bcf83d5a73e9a0fe3f266ad12657 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 14 Dec 2018 06:46:49 -0800
Subject: [PATCH 11/58] net: clear skb->tstamp in forwarding paths

[ Upstream commit 8203e2d844d34af247a151d8ebd68553a6e91785 ]

Sergey reported that forwarding was no longer working
if fq packet scheduler was used.

This is caused by the recent switch to EDT model, since incoming
packets might have been timestamped by __net_timestamp()

__net_timestamp() uses ktime_get_real(), while fq expects packets
using CLOCK_MONOTONIC base.

The fix is to clear skb->tstamp in forwarding paths.

Fixes: 80b14dee2bea ("net: Add a new socket option for a future transmit time.")
Fixes: fb420d5d91c1 ("tcp/fq: move back to CLOCK_MONOTONIC")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Sergey Matyukevich <geomatsi@gmail.com>
Tested-by: Sergey Matyukevich <geomatsi@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_forward.c | 1 +
 net/ipv6/ip6_output.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 32662e9e5d21..d5984d31ab93 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -72,6 +72,7 @@ static int ip_forward_finish(struct net *net, struct sock *sk, struct sk_buff *s
 	if (unlikely(opt->optlen))
 		ip_forward_options(skb);
 
+	skb->tstamp = 0;
 	return dst_output(net, sk, skb);
 }
 
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 2694def1e72c..0bb87f3a10c7 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -378,6 +378,7 @@ static inline int ip6_forward_finish(struct net *net, struct sock *sk,
 	__IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS);
 	__IP6_ADD_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTOCTETS, skb->len);
 
+	skb->tstamp = 0;
 	return dst_output(net, sk, skb);
 }
 
-- 
2.20.1


From c370ed8ec356718836baffb34e1bb4a1d76f51f9 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Fri, 21 Dec 2018 14:49:01 -0600
Subject: [PATCH 12/58] net: core: Fix Spectre v1 vulnerability

[ Upstream commit 50d5258634aee2e62832aa086d2fb0de00e72b91 ]

flen is indirectly controlled by user-space, hence leading to
a potential exploitation of the Spectre variant 1 vulnerability.

This issue was detected with the help of Smatch:

net/core/filter.c:1101 bpf_check_classic() warn: potential spectre issue 'filter' [w]

Fix this by sanitizing flen before using it to index filter at line 1101:

	switch (filter[flen - 1].code) {

and through pc at line 1040:

	const struct sock_filter *ftest = &filter[pc];

Notice that given that speculation windows are large, the policy is
to kill the speculation on the first load and not worry if it can be
completed with a dependent load/store [1].

[1] https://marc.info/?l=linux-kernel&m=152449131114778&w=2

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/filter.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/core/filter.c b/net/core/filter.c
index 5e00f2b85a56..cde9fa11c5dd 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -68,6 +68,7 @@
 #include <linux/seg6_local.h>
 #include <net/seg6.h>
 #include <net/seg6_local.h>
+#include <linux/nospec.h>
 
 /**
  *	sk_filter_trim_cap - run a packet through a socket filter
@@ -1033,6 +1034,7 @@ static int bpf_check_classic(const struct sock_filter *filter,
 	bool anc_found;
 	int pc;
 
+	flen = array_index_nospec(flen, BPF_MAXINSNS + 1);
 	/* Check the filter code now */
 	for (pc = 0; pc < flen; pc++) {
 		const struct sock_filter *ftest = &filter[pc];
-- 
2.20.1


From f29fda9a7aafac0524c92d85ac7471f84264df65 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 2 Jan 2019 04:24:20 -0800
Subject: [PATCH 13/58] net/hamradio/6pack: use mod_timer() to rearm timers

[ Upstream commit 202700e30740c6568b5a6943662f3829566dd533 ]

Using del_timer() + add_timer() is generally unsafe on SMP,
as noticed by syzbot. Use mod_timer() instead.

kernel BUG at kernel/time/timer.c:1136!
invalid opcode: 0000 [#1] PREEMPT SMP KASAN
CPU: 1 PID: 1026 Comm: kworker/u4:4 Not tainted 4.20.0+ #2
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Workqueue: events_unbound flush_to_ldisc
RIP: 0010:add_timer kernel/time/timer.c:1136 [inline]
RIP: 0010:add_timer+0xa81/0x1470 kernel/time/timer.c:1134
Code: 4d 89 7d 40 48 c7 85 70 fe ff ff 00 00 00 00 c7 85 7c fe ff ff ff ff ff ff 48 89 85 90 fe ff ff e9 e6 f7 ff ff e8 cf 42 12 00 <0f> 0b e8 c8 42 12 00 0f 0b e8 c1 42 12 00 4c 89 bd 60 fe ff ff e9
RSP: 0018:ffff8880a7fdf5a8 EFLAGS: 00010293
RAX: ffff8880a7846340 RBX: dffffc0000000000 RCX: 0000000000000000
RDX: 0000000000000000 RSI: ffffffff816f3ee1 RDI: ffff88808a514ff8
RBP: ffff8880a7fdf760 R08: 0000000000000007 R09: ffff8880a7846c58
R10: ffff8880a7846340 R11: 0000000000000000 R12: ffff88808a514ff8
R13: ffff88808a514ff8 R14: ffff88808a514dc0 R15: 0000000000000030
FS:  0000000000000000(0000) GS:ffff8880ae700000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000000000061c500 CR3: 00000000994d9000 CR4: 00000000001406e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 decode_prio_command drivers/net/hamradio/6pack.c:903 [inline]
 sixpack_decode drivers/net/hamradio/6pack.c:971 [inline]
 sixpack_receive_buf drivers/net/hamradio/6pack.c:457 [inline]
 sixpack_receive_buf+0xf9c/0x1470 drivers/net/hamradio/6pack.c:434
 tty_ldisc_receive_buf+0x164/0x1c0 drivers/tty/tty_buffer.c:465
 tty_port_default_receive_buf+0x114/0x190 drivers/tty/tty_port.c:38
 receive_buf drivers/tty/tty_buffer.c:481 [inline]
 flush_to_ldisc+0x3b2/0x590 drivers/tty/tty_buffer.c:533
 process_one_work+0xd0c/0x1ce0 kernel/workqueue.c:2153
 worker_thread+0x143/0x14a0 kernel/workqueue.c:2296
 kthread+0x357/0x430 kernel/kthread.c:246
 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:352

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Andreas Koensgen <ajk@comnets.uni-bremen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hamradio/6pack.c | 16 ++++------------
 1 file changed, 4 insertions(+), 12 deletions(-)

diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c
index d79a69dd2146..54e63ec04907 100644
--- a/drivers/net/hamradio/6pack.c
+++ b/drivers/net/hamradio/6pack.c
@@ -524,10 +524,7 @@ static void resync_tnc(struct timer_list *t)
 
 
 	/* Start resync timer again -- the TNC might be still absent */
-
-	del_timer(&sp->resync_t);
-	sp->resync_t.expires	= jiffies + SIXP_RESYNC_TIMEOUT;
-	add_timer(&sp->resync_t);
+	mod_timer(&sp->resync_t, jiffies + SIXP_RESYNC_TIMEOUT);
 }
 
 static inline int tnc_init(struct sixpack *sp)
@@ -538,9 +535,7 @@ static inline int tnc_init(struct sixpack *sp)
 
 	sp->tty->ops->write(sp->tty, &inbyte, 1);
 
-	del_timer(&sp->resync_t);
-	sp->resync_t.expires = jiffies + SIXP_RESYNC_TIMEOUT;
-	add_timer(&sp->resync_t);
+	mod_timer(&sp->resync_t, jiffies + SIXP_RESYNC_TIMEOUT);
 
 	return 0;
 }
@@ -918,11 +913,8 @@ static void decode_prio_command(struct sixpack *sp, unsigned char cmd)
         /* if the state byte has been received, the TNC is present,
            so the resync timer can be reset. */
 
-	if (sp->tnc_state == TNC_IN_SYNC) {
-		del_timer(&sp->resync_t);
-		sp->resync_t.expires	= jiffies + SIXP_INIT_RESYNC_TIMEOUT;
-		add_timer(&sp->resync_t);
-	}
+	if (sp->tnc_state == TNC_IN_SYNC)
+		mod_timer(&sp->resync_t, jiffies + SIXP_INIT_RESYNC_TIMEOUT);
 
 	sp->status1 = cmd & SIXP_PRIO_DATA_MASK;
 }
-- 
2.20.1


From e4ea2248ba606baf54498f5f777c39b229fce0da Mon Sep 17 00:00:00 2001
From: Michal Kubecek <mkubecek@suse.cz>
Date: Thu, 13 Dec 2018 17:23:32 +0100
Subject: [PATCH 14/58] net: ipv4: do not handle duplicate fragments as
 overlapping

[ Upstream commit ade446403bfb79d3528d56071a84b15351a139ad ]

Since commit 7969e5c40dfd ("ip: discard IPv4 datagrams with overlapping
segments.") IPv4 reassembly code drops the whole queue whenever an
overlapping fragment is received. However, the test is written in a way
which detects duplicate fragments as overlapping so that in environments
with many duplicate packets, fragmented packets may be undeliverable.

Add an extra test and for (potentially) duplicate fragment, only drop the
new fragment rather than the whole queue. Only starting offset and length
are checked, not the contents of the fragments as that would be too
expensive. For similar reason, linear list ("run") of a rbtree node is not
iterated, we only check if the new fragment is a subset of the interval
covered by existing consecutive fragments.

v2: instead of an exact check iterating through linear list of an rbtree
node, only check if the new fragment is subset of the "run" (suggested
by Eric Dumazet)

Fixes: 7969e5c40dfd ("ip: discard IPv4 datagrams with overlapping segments.")
Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_fragment.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index f686d7761acb..f8bbd693c19c 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -347,10 +347,10 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 	struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
 	struct rb_node **rbn, *parent;
 	struct sk_buff *skb1, *prev_tail;
+	int ihl, end, skb1_run_end;
 	struct net_device *dev;
 	unsigned int fragsize;
 	int flags, offset;
-	int ihl, end;
 	int err = -ENOENT;
 	u8 ecn;
 
@@ -420,7 +420,9 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 	 *   overlapping fragment, the entire datagram (and any constituent
 	 *   fragments) MUST be silently discarded.
 	 *
-	 * We do the same here for IPv4 (and increment an snmp counter).
+	 * We do the same here for IPv4 (and increment an snmp counter) but
+	 * we do not want to drop the whole queue in response to a duplicate
+	 * fragment.
 	 */
 
 	/* Find out where to put this fragment.  */
@@ -444,13 +446,17 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 		do {
 			parent = *rbn;
 			skb1 = rb_to_skb(parent);
+			skb1_run_end = skb1->ip_defrag_offset +
+				       FRAG_CB(skb1)->frag_run_len;
 			if (end <= skb1->ip_defrag_offset)
 				rbn = &parent->rb_left;
-			else if (offset >= skb1->ip_defrag_offset +
-						FRAG_CB(skb1)->frag_run_len)
+			else if (offset >= skb1_run_end)
 				rbn = &parent->rb_right;
-			else /* Found an overlap with skb1. */
-				goto discard_qp;
+			else if (offset >= skb1->ip_defrag_offset &&
+				 end <= skb1_run_end)
+				goto err; /* No new data, potential duplicate */
+			else
+				goto discard_qp; /* Found an overlap */
 		} while (*rbn);
 		/* Here we have parent properly set, and rbn pointing to
 		 * one of its NULL left/right children. Insert skb.
-- 
2.20.1


From a2bbf9a7e09c5cded117635f4c59189b3cdfff96 Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@microchip.com>
Date: Mon, 17 Dec 2018 10:02:42 +0000
Subject: [PATCH 15/58] net: macb: restart tx after tx used bit read

[ Upstream commit 4298388574dae6168fa8940b3edc7ba965e8a7ab ]

On some platforms (currently detected only on SAMA5D4) TX might stuck
even the pachets are still present in DMA memories and TX start was
issued for them. This happens due to race condition between MACB driver
updating next TX buffer descriptor to be used and IP reading the same
descriptor. In such a case, the "TX USED BIT READ" interrupt is asserted.
GEM/MACB user guide specifies that if a "TX USED BIT READ" interrupt
is asserted TX must be restarted. Restart TX if used bit is read and
packets are present in software TX queue. Packets are removed from software
TX queue if TX was successful for them (see macb_tx_interrupt()).

Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Acked-by: Nicolas Ferre <nicolas.ferre@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 21 ++++++++++++++++++++-
 1 file changed, 20 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 58b9744c4058..240fd36b5074 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -61,7 +61,8 @@
 #define MACB_TX_ERR_FLAGS	(MACB_BIT(ISR_TUND)			\
 					| MACB_BIT(ISR_RLE)		\
 					| MACB_BIT(TXERR))
-#define MACB_TX_INT_FLAGS	(MACB_TX_ERR_FLAGS | MACB_BIT(TCOMP))
+#define MACB_TX_INT_FLAGS	(MACB_TX_ERR_FLAGS | MACB_BIT(TCOMP)	\
+					| MACB_BIT(TXUBR))
 
 /* Max length of transmit frame must be a multiple of 8 bytes */
 #define MACB_TX_LEN_ALIGN	8
@@ -1313,6 +1314,21 @@ static void macb_hresp_error_task(unsigned long data)
 	netif_tx_start_all_queues(dev);
 }
 
+static void macb_tx_restart(struct macb_queue *queue)
+{
+	unsigned int head = queue->tx_head;
+	unsigned int tail = queue->tx_tail;
+	struct macb *bp = queue->bp;
+
+	if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE)
+		queue_writel(queue, ISR, MACB_BIT(TXUBR));
+
+	if (head == tail)
+		return;
+
+	macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(TSTART));
+}
+
 static irqreturn_t macb_interrupt(int irq, void *dev_id)
 {
 	struct macb_queue *queue = dev_id;
@@ -1370,6 +1386,9 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id)
 		if (status & MACB_BIT(TCOMP))
 			macb_tx_interrupt(queue);
 
+		if (status & MACB_BIT(TXUBR))
+			macb_tx_restart(queue);
+
 		/* Link change detection isn't possible with RMII, so we'll
 		 * add that if/when we get our hands on a full-blown MII PHY.
 		 */
-- 
2.20.1


From e54c78096cdda272d4978c10bc690bf75b9aaeb2 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Tue, 11 Dec 2018 17:32:28 +0100
Subject: [PATCH 16/58] net: mvpp2: 10G modes aren't supported on all ports

[ Upstream commit 006791772084383de779ef29f2e06f3a6e111e7d ]

The mvpp2_phylink_validate() function sets all modes that are
supported by a given PPv2 port. A recent change made all ports to
advertise they support 10G modes in certain cases. This is not true,
as only the port #0 can do so. This patch fixes it.

Fixes: 01b3fd5ac97c ("net: mvpp2: fix detection of 10G SFP modules")
Cc: Baruch Siach <baruch@tkos.co.il>
Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 6320e080b831..d5bc90476b4f 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -4292,12 +4292,14 @@ static void mvpp2_phylink_validate(struct net_device *dev,
 	case PHY_INTERFACE_MODE_10GKR:
 	case PHY_INTERFACE_MODE_XAUI:
 	case PHY_INTERFACE_MODE_NA:
-		phylink_set(mask, 10000baseCR_Full);
-		phylink_set(mask, 10000baseSR_Full);
-		phylink_set(mask, 10000baseLR_Full);
-		phylink_set(mask, 10000baseLRM_Full);
-		phylink_set(mask, 10000baseER_Full);
-		phylink_set(mask, 10000baseKR_Full);
+		if (port->gop_id == 0) {
+			phylink_set(mask, 10000baseCR_Full);
+			phylink_set(mask, 10000baseSR_Full);
+			phylink_set(mask, 10000baseLR_Full);
+			phylink_set(mask, 10000baseLRM_Full);
+			phylink_set(mask, 10000baseER_Full);
+			phylink_set(mask, 10000baseKR_Full);
+		}
 		/* Fall-through */
 	case PHY_INTERFACE_MODE_RGMII:
 	case PHY_INTERFACE_MODE_RGMII_ID:
-- 
2.20.1


From 9963ae59f68b1c2ca3f83761eac920ca071fb2a3 Mon Sep 17 00:00:00 2001
From: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Date: Tue, 18 Dec 2018 16:57:04 +0900
Subject: [PATCH 17/58] net: phy: Fix the issue that netif always links up
 after resuming

[ Upstream commit 8742beb50f2db903d3b6d69ddd81d67ce9914453 ]

Even though the link is down before entering hibernation,
there is an issue that the network interface always links up after resuming
from hibernation.

If the link is still down before enabling the network interface,
and after resuming from hibernation, the phydev->state is forcibly set
to PHY_UP in mdio_bus_phy_restore(), and the link becomes up.

In suspend sequence, only if the PHY is attached, mdio_bus_phy_suspend()
calls phy_stop_machine(), and mdio_bus_phy_resume() calls
phy_start_machine().
In resume sequence, it's enough to do the same as mdio_bus_phy_resume()
because the state has been preserved.

This patch fixes the issue by calling phy_start_machine() in
mdio_bus_phy_restore() in the same way as mdio_bus_phy_resume().

Fixes: bc87922ff59d ("phy: Move PHY PM operations into phy_device")
Suggested-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 20d1be2b070b..2c32c795f5dd 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -164,11 +164,8 @@ static int mdio_bus_phy_restore(struct device *dev)
 	if (ret < 0)
 		return ret;
 
-	/* The PHY needs to renegotiate. */
-	phydev->link = 0;
-	phydev->state = PHY_UP;
-
-	phy_start_machine(phydev);
+	if (phydev->attached_dev && phydev->adjust_link)
+		phy_start_machine(phydev);
 
 	return 0;
 }
-- 
2.20.1


From 2a5ca5a158a4c1d0c7253df654a7b2c29ef27b4e Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sat, 29 Dec 2018 13:56:38 -0800
Subject: [PATCH 18/58] netrom: fix locking in nr_find_socket()

[ Upstream commit 7314f5480f3e37e570104dc5e0f28823ef849e72 ]

nr_find_socket(), nr_find_peer() and nr_find_listener() lock the
sock after finding it in the global list. However, the call path
requires BH disabled for the sock lock consistently.

Actually the locking is unnecessary at this point, we can just hold
the sock refcnt to make sure it is not gone after we unlock the global
list, and lock it later only when needed.

Reported-and-tested-by: syzbot+f621cda8b7e598908efa@syzkaller.appspotmail.com
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netrom/af_netrom.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 03f37c4e64fe..1d3144d19903 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -153,7 +153,7 @@ static struct sock *nr_find_listener(ax25_address *addr)
 	sk_for_each(s, &nr_list)
 		if (!ax25cmp(&nr_sk(s)->source_addr, addr) &&
 		    s->sk_state == TCP_LISTEN) {
-			bh_lock_sock(s);
+			sock_hold(s);
 			goto found;
 		}
 	s = NULL;
@@ -174,7 +174,7 @@ static struct sock *nr_find_socket(unsigned char index, unsigned char id)
 		struct nr_sock *nr = nr_sk(s);
 
 		if (nr->my_index == index && nr->my_id == id) {
-			bh_lock_sock(s);
+			sock_hold(s);
 			goto found;
 		}
 	}
@@ -198,7 +198,7 @@ static struct sock *nr_find_peer(unsigned char index, unsigned char id,
 
 		if (nr->your_index == index && nr->your_id == id &&
 		    !ax25cmp(&nr->dest_addr, dest)) {
-			bh_lock_sock(s);
+			sock_hold(s);
 			goto found;
 		}
 	}
@@ -224,7 +224,7 @@ static unsigned short nr_find_next_circuit(void)
 		if (i != 0 && j != 0) {
 			if ((sk=nr_find_socket(i, j)) == NULL)
 				break;
-			bh_unlock_sock(sk);
+			sock_put(sk);
 		}
 
 		id++;
@@ -920,6 +920,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	if (sk != NULL) {
+		bh_lock_sock(sk);
 		skb_reset_transport_header(skb);
 
 		if (frametype == NR_CONNACK && skb->len == 22)
@@ -929,6 +930,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev)
 
 		ret = nr_process_rx_frame(sk, skb);
 		bh_unlock_sock(sk);
+		sock_put(sk);
 		return ret;
 	}
 
@@ -960,10 +962,12 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev)
 	    (make = nr_make_new(sk)) == NULL) {
 		nr_transmit_refusal(skb, 0);
 		if (sk)
-			bh_unlock_sock(sk);
+			sock_put(sk);
 		return 0;
 	}
 
+	bh_lock_sock(sk);
+
 	window = skb->data[20];
 
 	skb->sk             = make;
@@ -1016,6 +1020,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev)
 		sk->sk_data_ready(sk);
 
 	bh_unlock_sock(sk);
+	sock_put(sk);
 
 	nr_insert_socket(make);
 
-- 
2.20.1


From d7331b0fca8b7f85dfc32c7d0c2267ac691f2376 Mon Sep 17 00:00:00 2001
From: Myungho Jung <mhjungk@gmail.com>
Date: Tue, 18 Dec 2018 09:02:25 -0800
Subject: [PATCH 19/58] net/smc: fix TCP fallback socket release

[ Upstream commit 78abe3d0dfad196959b1246003366e2610775ea6 ]

clcsock can be released while kernel_accept() references it in TCP
listen worker. Also, clcsock needs to wake up before released if TCP
fallback is used and the clcsock is blocked by accept. Add a lock to
safely release clcsock and call kernel_sock_shutdown() to wake up
clcsock from accept in smc_release().

Reported-by: syzbot+0bf2e01269f1274b4b03@syzkaller.appspotmail.com
Reported-by: syzbot+e3132895630f957306bc@syzkaller.appspotmail.com
Signed-off-by: Myungho Jung <mhjungk@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/af_smc.c | 14 ++++++++++++--
 net/smc/smc.h    |  4 ++++
 2 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 80e2119f1c70..2b8f95290627 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -145,8 +145,14 @@ static int smc_release(struct socket *sock)
 		sk->sk_shutdown |= SHUTDOWN_MASK;
 	}
 	if (smc->clcsock) {
+		if (smc->use_fallback && sk->sk_state == SMC_LISTEN) {
+			/* wake up clcsock accept */
+			rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR);
+		}
+		mutex_lock(&smc->clcsock_release_lock);
 		sock_release(smc->clcsock);
 		smc->clcsock = NULL;
+		mutex_unlock(&smc->clcsock_release_lock);
 	}
 	if (smc->use_fallback) {
 		if (sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_INIT)
@@ -203,6 +209,7 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock,
 	spin_lock_init(&smc->conn.send_lock);
 	sk->sk_prot->hash(sk);
 	sk_refcnt_debug_inc(sk);
+	mutex_init(&smc->clcsock_release_lock);
 
 	return sk;
 }
@@ -818,7 +825,7 @@ static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc)
 	struct socket *new_clcsock = NULL;
 	struct sock *lsk = &lsmc->sk;
 	struct sock *new_sk;
-	int rc;
+	int rc = -EINVAL;
 
 	release_sock(lsk);
 	new_sk = smc_sock_alloc(sock_net(lsk), NULL, lsk->sk_protocol);
@@ -831,7 +838,10 @@ static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc)
 	}
 	*new_smc = smc_sk(new_sk);
 
-	rc = kernel_accept(lsmc->clcsock, &new_clcsock, 0);
+	mutex_lock(&lsmc->clcsock_release_lock);
+	if (lsmc->clcsock)
+		rc = kernel_accept(lsmc->clcsock, &new_clcsock, 0);
+	mutex_unlock(&lsmc->clcsock_release_lock);
 	lock_sock(lsk);
 	if  (rc < 0)
 		lsk->sk_err = -rc;
diff --git a/net/smc/smc.h b/net/smc/smc.h
index 08786ace6010..5721416d0605 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -219,6 +219,10 @@ struct smc_sock {				/* smc sock container */
 						 * started, waiting for unsent
 						 * data to be sent
 						 */
+	struct mutex            clcsock_release_lock;
+						/* protects clcsock of a listen
+						 * socket
+						 * */
 };
 
 static inline struct smc_sock *smc_sk(const struct sock *sk)
-- 
2.20.1


From f6d9af0ace44b48944f473e9e5bc1f5cffaeabc5 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Mon, 17 Dec 2018 11:06:06 +0300
Subject: [PATCH 20/58] net: stmmac: Fix an error code in probe()

[ Upstream commit b26322d2ac6c1c1087af73856531bb836f6963ca ]

The function should return an error if create_singlethread_workqueue()
fails.

Fixes: 34877a15f787 ("net: stmmac: Rework and fix TX Timeout code")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 99ea5c4ce29c..2103b865726a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -4247,6 +4247,7 @@ int stmmac_dvr_probe(struct device *device,
 	priv->wq = create_singlethread_workqueue("stmmac_wq");
 	if (!priv->wq) {
 		dev_err(priv->device, "failed to create workqueue\n");
+		ret = -ENOMEM;
 		goto error_wq;
 	}
 
-- 
2.20.1


From 062cc6fd28a82c8defa2d2ccf9ca0fff579feb14 Mon Sep 17 00:00:00 2001
From: Ganesh Goudar <ganeshgr@chelsio.com>
Date: Wed, 19 Dec 2018 17:18:22 +0530
Subject: [PATCH 21/58] net/tls: allocate tls context using GFP_ATOMIC

[ Upstream commit c6ec179a0082e2e76e3a72050c2b99d3d0f3da3f ]

create_ctx can be called from atomic context, hence use
GFP_ATOMIC instead of GFP_KERNEL.

[  395.962599] BUG: sleeping function called from invalid context at mm/slab.h:421
[  395.979896] in_atomic(): 1, irqs_disabled(): 0, pid: 16254, name: openssl
[  395.996564] 2 locks held by openssl/16254:
[  396.010492]  #0: 00000000347acb52 (sk_lock-AF_INET){+.+.}, at: do_tcp_setsockopt.isra.44+0x13b/0x9a0
[  396.029838]  #1: 000000006c9552b5 (device_spinlock){+...}, at: tls_init+0x1d/0x280
[  396.047675] CPU: 5 PID: 16254 Comm: openssl Tainted: G           O      4.20.0-rc6+ #25
[  396.066019] Hardware name: Supermicro X10SRA-F/X10SRA-F, BIOS 2.0c 09/25/2017
[  396.083537] Call Trace:
[  396.096265]  dump_stack+0x5e/0x8b
[  396.109876]  ___might_sleep+0x216/0x250
[  396.123940]  kmem_cache_alloc_trace+0x1b0/0x240
[  396.138800]  create_ctx+0x1f/0x60
[  396.152504]  tls_init+0xbd/0x280
[  396.166135]  tcp_set_ulp+0x191/0x2d0
[  396.180035]  ? tcp_set_ulp+0x2c/0x2d0
[  396.193960]  do_tcp_setsockopt.isra.44+0x148/0x9a0
[  396.209013]  __sys_setsockopt+0x7c/0xe0
[  396.223054]  __x64_sys_setsockopt+0x20/0x30
[  396.237378]  do_syscall_64+0x4a/0x180
[  396.251200]  entry_SYSCALL_64_after_hwframe+0x49/0xbe

Fixes: df9d4a178022 ("net/tls: sleeping function from invalid context")
Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 523622dc74f8..7fab2891ce7f 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -550,7 +550,7 @@ static struct tls_context *create_ctx(struct sock *sk)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tls_context *ctx;
 
-	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	ctx = kzalloc(sizeof(*ctx), GFP_ATOMIC);
 	if (!ctx)
 		return NULL;
 
-- 
2.20.1


From 2de1d8614e1ea20f00f62f9ae723dfda2882312e Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sat, 29 Dec 2018 13:56:37 -0800
Subject: [PATCH 22/58] net/wan: fix a double free in x25_asy_open_tty()

[ Upstream commit d5c7c745f254c6cb98b3b3f15fe789b8bd770c72 ]

When x25_asy_open() fails, it already cleans up by itself,
so its caller doesn't need to free the memory again.

It seems we still have to call x25_asy_free() to clear the SLF_INUSE
bit, so just set these pointers to NULL after kfree().

Reported-and-tested-by: syzbot+5e5e969e525129229052@syzkaller.appspotmail.com
Fixes: 3b780bed3138 ("x25_asy: Free x25_asy on x25_asy_open() failure.")
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wan/x25_asy.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wan/x25_asy.c b/drivers/net/wan/x25_asy.c
index 74c06a5f586f..4f25c2d8fff0 100644
--- a/drivers/net/wan/x25_asy.c
+++ b/drivers/net/wan/x25_asy.c
@@ -486,8 +486,10 @@ static int x25_asy_open(struct net_device *dev)
 
 	/* Cleanup */
 	kfree(sl->xbuff);
+	sl->xbuff = NULL;
 noxbuff:
 	kfree(sl->rbuff);
+	sl->rbuff = NULL;
 norbuff:
 	return -ENOMEM;
 }
-- 
2.20.1


From fa3b048ee895452883b8d9abc8c007de753363eb Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 21 Dec 2018 12:06:59 -0500
Subject: [PATCH 23/58] packet: validate address length

[ Upstream commit 99137b7888f4058087895d035d81c6b2d31015c5 ]

Packet sockets with SOCK_DGRAM may pass an address for use in
dev_hard_header. Ensure that it is of sufficient length.

Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 6477b131e809..425169cc5b26 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2627,6 +2627,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 		proto	= saddr->sll_protocol;
 		addr	= saddr->sll_addr;
 		dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex);
+		if (addr && dev && saddr->sll_halen < dev->addr_len)
+			goto out;
 	}
 
 	err = -ENXIO;
@@ -2825,6 +2827,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		proto	= saddr->sll_protocol;
 		addr	= saddr->sll_addr;
 		dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex);
+		if (addr && dev && saddr->sll_halen < dev->addr_len)
+			goto out;
 	}
 
 	err = -ENXIO;
-- 
2.20.1


From ac6fc399533d8ef02d8c8ef73aba1bd9a17d83dc Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Sat, 22 Dec 2018 16:53:45 -0500
Subject: [PATCH 24/58] packet: validate address length if non-zero

[ Upstream commit 6b8d95f1795c42161dc0984b6863e95d6acf24ed ]

Validate packet socket address length if a length is given. Zero
length is equivalent to not setting an address.

Fixes: 99137b7888f4 ("packet: validate address length")
Reported-by: Ido Schimmel <idosch@idosch.org>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 425169cc5b26..0541cfc93440 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2625,7 +2625,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 						sll_addr)))
 			goto out;
 		proto	= saddr->sll_protocol;
-		addr	= saddr->sll_addr;
+		addr	= saddr->sll_halen ? saddr->sll_addr : NULL;
 		dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex);
 		if (addr && dev && saddr->sll_halen < dev->addr_len)
 			goto out;
@@ -2825,7 +2825,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		if (msg->msg_namelen < (saddr->sll_halen + offsetof(struct sockaddr_ll, sll_addr)))
 			goto out;
 		proto	= saddr->sll_protocol;
-		addr	= saddr->sll_addr;
+		addr	= saddr->sll_halen ? saddr->sll_addr : NULL;
 		dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex);
 		if (addr && dev && saddr->sll_halen < dev->addr_len)
 			goto out;
-- 
2.20.1


From 29570b2c01b196ba7f8a107b478247214b66d031 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Fri, 21 Dec 2018 15:41:17 -0600
Subject: [PATCH 25/58] phonet: af_phonet: Fix Spectre v1 vulnerability

[ Upstream commit d686026b1e6ed4ea27d630d8f54f9a694db088b2 ]

protocol is indirectly controlled by user-space, hence leading to
a potential exploitation of the Spectre variant 1 vulnerability.

This issue was detected with the help of Smatch:

net/phonet/af_phonet.c:48 phonet_proto_get() warn: potential spectre issue 'proto_tab' [w] (local cap)

Fix this by sanitizing protocol before using it to index proto_tab.

Notice that given that speculation windows are large, the policy is
to kill the speculation on the first load and not worry if it can be
completed with a dependent load/store [1].

[1] https://marc.info/?l=linux-kernel&m=152449131114778&w=2

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/phonet/af_phonet.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c
index 3b0ef691f5b1..d4b2abd78858 100644
--- a/net/phonet/af_phonet.c
+++ b/net/phonet/af_phonet.c
@@ -34,6 +34,8 @@
 #include <net/phonet/phonet.h>
 #include <net/phonet/pn_dev.h>
 
+#include <linux/nospec.h>
+
 /* Transport protocol registration */
 static const struct phonet_protocol *proto_tab[PHONET_NPROTO] __read_mostly;
 
@@ -43,6 +45,7 @@ static const struct phonet_protocol *phonet_proto_get(unsigned int protocol)
 
 	if (protocol >= PHONET_NPROTO)
 		return NULL;
+	protocol = array_index_nospec(protocol, PHONET_NPROTO);
 
 	rcu_read_lock();
 	pp = rcu_dereference(proto_tab[protocol]);
-- 
2.20.1


From b4d1a3b994c0e90e76f6087e3bcb8f19d893ef80 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sun, 30 Dec 2018 12:43:42 -0800
Subject: [PATCH 26/58] ptr_ring: wrap back ->producer in
 __ptr_ring_swap_queue()

[ Upstream commit aff6db454599d62191aabc208930e891748e4322 ]

__ptr_ring_swap_queue() tries to move pointers from the old
ring to the new one, but it forgets to check if ->producer
is beyond the new size at the end of the operation. This leads
to an out-of-bound access in __ptr_ring_produce() as reported
by syzbot.

Reported-by: syzbot+8993c0fa96d57c399735@syzkaller.appspotmail.com
Fixes: 5d49de532002 ("ptr_ring: resize support")
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: Jason Wang <jasowang@redhat.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ptr_ring.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h
index 6894976b54e3..186cd8e970c7 100644
--- a/include/linux/ptr_ring.h
+++ b/include/linux/ptr_ring.h
@@ -573,6 +573,8 @@ static inline void **__ptr_ring_swap_queue(struct ptr_ring *r, void **queue,
 		else if (destroy)
 			destroy(ptr);
 
+	if (producer >= size)
+		producer = 0;
 	__ptr_ring_set_size(r, size);
 	r->producer = producer;
 	r->consumer_head = 0;
-- 
2.20.1


From 0c46c38a287162d994fb1b6876b49edc6ae6c961 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?J=C3=B6rgen=20Storvist?= <jorgen.storvist@gmail.com>
Date: Wed, 12 Dec 2018 22:45:34 +0100
Subject: [PATCH 27/58] qmi_wwan: Added support for Fibocom NL668 series
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 110a1cc28bc383adb4885eff27e18c61ddebffb4 ]

Added support for Fibocom NL668 series QMI interface.
Using QMI_QUIRK_SET_DTR required for Qualcomm MDM9x07 chipsets.

Signed-off-by: Jörgen Storvist <jorgen.storvist@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 72a55b6b4211..dada68f279bc 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1117,6 +1117,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1435, 0xd181, 4)},	/* Wistron NeWeb D18Q1 */
 	{QMI_FIXED_INTF(0x1435, 0xd181, 5)},	/* Wistron NeWeb D18Q1 */
 	{QMI_FIXED_INTF(0x1435, 0xd191, 4)},	/* Wistron NeWeb D19Q1 */
+	{QMI_QUIRK_SET_DTR(0x1508, 0x1001, 4)},	/* Fibocom NL668 series */
 	{QMI_FIXED_INTF(0x16d8, 0x6003, 0)},	/* CMOTech 6003 */
 	{QMI_FIXED_INTF(0x16d8, 0x6007, 0)},	/* CMOTech CHE-628S */
 	{QMI_FIXED_INTF(0x16d8, 0x6008, 0)},	/* CMOTech CMU-301 */
-- 
2.20.1


From 8f4d8623c1bbf700280138dd53960220a27f84e9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?J=C3=B6rgen=20Storvist?= <jorgen.storvist@gmail.com>
Date: Thu, 13 Dec 2018 17:00:35 +0100
Subject: [PATCH 28/58] qmi_wwan: Added support for Telit LN940 series
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 1986af16e8ed355822600c24b3d2f0be46b573df ]

Added support for the Telit LN940 series cellular modules QMI interface.
QMI_QUIRK_SET_DTR quirk requied for Qualcomm MDM9x40 chipset.

Signed-off-by: Jörgen Storvist <jorgen.storvist@gmail.com>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index dada68f279bc..c8872dd5ff5e 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1230,6 +1230,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1bc7, 0x1101, 3)},	/* Telit ME910 dual modem */
 	{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)},	/* Telit LE920 */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1201, 2)},	/* Telit LE920, LE920A4 */
+	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1900, 1)},	/* Telit LN940 series */
 	{QMI_FIXED_INTF(0x1c9e, 0x9801, 3)},	/* Telewell TW-3G HSPA+ */
 	{QMI_FIXED_INTF(0x1c9e, 0x9803, 4)},	/* Telewell TW-3G HSPA+ */
 	{QMI_FIXED_INTF(0x1c9e, 0x9b01, 3)},	/* XS Stick W100-2 from 4G Systems */
-- 
2.20.1


From 423936f93a8cf24119221490f6d873765a4a7144 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?J=C3=B6rgen=20Storvist?= <jorgen.storvist@gmail.com>
Date: Fri, 21 Dec 2018 15:38:52 +0100
Subject: [PATCH 29/58] qmi_wwan: Add support for Fibocom NL678 series
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 7c3db4105ce8d69bcb5c04bfa9acd1e9119af8d5 ]

Added support for Fibocom NL678 series cellular module QMI interface.
Using QMI_QUIRK_SET_DTR required for Qualcomm MDM9x40 series chipsets.

Signed-off-by: Jörgen Storvist <jorgen.storvist@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index c8872dd5ff5e..f5bac5075386 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1265,6 +1265,7 @@ static const struct usb_device_id products[] = {
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0121, 4)},	/* Quectel EC21 Mini PCIe */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0191, 4)},	/* Quectel EG91 */
 	{QMI_FIXED_INTF(0x2c7c, 0x0296, 4)},	/* Quectel BG96 */
+	{QMI_QUIRK_SET_DTR(0x2cb7, 0x0104, 4)},	/* Fibocom NL678 series */
 
 	/* 4. Gobi 1000 devices */
 	{QMI_GOBI1K_DEVICE(0x05c6, 0x9212)},	/* Acer Gobi Modem Device */
-- 
2.20.1


From 4f440a762789ed449705e29307fd4a655991c11a Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 10 Dec 2018 18:00:52 +0800
Subject: [PATCH 30/58] sctp: initialize sin6_flowinfo for ipv6 addrs in
 sctp_inet6addr_event

[ Upstream commit 4a2eb0c37b4759416996fbb4c45b932500cf06d3 ]

syzbot reported a kernel-infoleak, which is caused by an uninitialized
field(sin6_flowinfo) of addr->a.v6 in sctp_inet6addr_event().
The call trace is as below:

  BUG: KMSAN: kernel-infoleak in _copy_to_user+0x19a/0x230 lib/usercopy.c:33
  CPU: 1 PID: 8164 Comm: syz-executor2 Not tainted 4.20.0-rc3+ #95
  Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
  Google 01/01/2011
  Call Trace:
    __dump_stack lib/dump_stack.c:77 [inline]
    dump_stack+0x32d/0x480 lib/dump_stack.c:113
    kmsan_report+0x12c/0x290 mm/kmsan/kmsan.c:683
    kmsan_internal_check_memory+0x32a/0xa50 mm/kmsan/kmsan.c:743
    kmsan_copy_to_user+0x78/0xd0 mm/kmsan/kmsan_hooks.c:634
    _copy_to_user+0x19a/0x230 lib/usercopy.c:33
    copy_to_user include/linux/uaccess.h:183 [inline]
    sctp_getsockopt_local_addrs net/sctp/socket.c:5998 [inline]
    sctp_getsockopt+0x15248/0x186f0 net/sctp/socket.c:7477
    sock_common_getsockopt+0x13f/0x180 net/core/sock.c:2937
    __sys_getsockopt+0x489/0x550 net/socket.c:1939
    __do_sys_getsockopt net/socket.c:1950 [inline]
    __se_sys_getsockopt+0xe1/0x100 net/socket.c:1947
    __x64_sys_getsockopt+0x62/0x80 net/socket.c:1947
    do_syscall_64+0xcf/0x110 arch/x86/entry/common.c:291
    entry_SYSCALL_64_after_hwframe+0x63/0xe7

sin6_flowinfo is not really used by SCTP, so it will be fixed by simply
setting it to 0.

The issue exists since very beginning.
Thanks Alexander for the reproducer provided.

Reported-by: syzbot+ad5d327e6936a2e284be@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ipv6.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index fc6c5e4bffa5..7f0539db5604 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -101,6 +101,7 @@ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev,
 		if (addr) {
 			addr->a.v6.sin6_family = AF_INET6;
 			addr->a.v6.sin6_port = 0;
+			addr->a.v6.sin6_flowinfo = 0;
 			addr->a.v6.sin6_addr = ifa->addr;
 			addr->a.v6.sin6_scope_id = ifa->idev->dev->ifindex;
 			addr->valid = 1;
-- 
2.20.1


From c12859dd1d7a541903ae96041f5ade2820fbd40c Mon Sep 17 00:00:00 2001
From: Deepa Dinamani <deepa.kernel@gmail.com>
Date: Thu, 27 Dec 2018 18:55:09 -0800
Subject: [PATCH 31/58] sock: Make sock->sk_stamp thread-safe

[ Upstream commit 3a0ed3e9619738067214871e9cb826fa23b2ddb9 ]

Al Viro mentioned (Message-ID
<20170626041334.GZ10672@ZenIV.linux.org.uk>)
that there is probably a race condition
lurking in accesses of sk_stamp on 32-bit machines.

sock->sk_stamp is of type ktime_t which is always an s64.
On a 32 bit architecture, we might run into situations of
unsafe access as the access to the field becomes non atomic.

Use seqlocks for synchronization.
This allows us to avoid using spinlocks for readers as
readers do not need mutual exclusion.

Another approach to solve this is to require sk_lock for all
modifications of the timestamps. The current approach allows
for timestamps to have their own lock: sk_stamp_lock.
This allows for the patch to not compete with already
existing critical sections, and side effects are limited
to the paths in the patch.

The addition of the new field maintains the data locality
optimizations from
commit 9115e8cd2a0c ("net: reorganize struct sock for better data
locality")

Note that all the instances of the sk_stamp accesses
are either through the ioctl or the syscall recvmsg.

Signed-off-by: Deepa Dinamani <deepa.kernel@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h   | 38 +++++++++++++++++++++++++++++++++++---
 net/compat.c         | 15 +++++++++------
 net/core/sock.c      | 15 ++++++++++-----
 net/sunrpc/svcsock.c |  2 +-
 4 files changed, 55 insertions(+), 15 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index f18dbd6da906..6cb5a545df7d 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -298,6 +298,7 @@ struct sock_common {
   *	@sk_filter: socket filtering instructions
   *	@sk_timer: sock cleanup timer
   *	@sk_stamp: time stamp of last packet received
+  *	@sk_stamp_seq: lock for accessing sk_stamp on 32 bit architectures only
   *	@sk_tsflags: SO_TIMESTAMPING socket options
   *	@sk_tskey: counter to disambiguate concurrent tstamp requests
   *	@sk_zckey: counter to order MSG_ZEROCOPY notifications
@@ -474,6 +475,9 @@ struct sock {
 	const struct cred	*sk_peer_cred;
 	long			sk_rcvtimeo;
 	ktime_t			sk_stamp;
+#if BITS_PER_LONG==32
+	seqlock_t		sk_stamp_seq;
+#endif
 	u16			sk_tsflags;
 	u8			sk_shutdown;
 	u32			sk_tskey;
@@ -2290,6 +2294,34 @@ static inline void sk_drops_add(struct sock *sk, const struct sk_buff *skb)
 	atomic_add(segs, &sk->sk_drops);
 }
 
+static inline ktime_t sock_read_timestamp(struct sock *sk)
+{
+#if BITS_PER_LONG==32
+	unsigned int seq;
+	ktime_t kt;
+
+	do {
+		seq = read_seqbegin(&sk->sk_stamp_seq);
+		kt = sk->sk_stamp;
+	} while (read_seqretry(&sk->sk_stamp_seq, seq));
+
+	return kt;
+#else
+	return sk->sk_stamp;
+#endif
+}
+
+static inline void sock_write_timestamp(struct sock *sk, ktime_t kt)
+{
+#if BITS_PER_LONG==32
+	write_seqlock(&sk->sk_stamp_seq);
+	sk->sk_stamp = kt;
+	write_sequnlock(&sk->sk_stamp_seq);
+#else
+	sk->sk_stamp = kt;
+#endif
+}
+
 void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
 			   struct sk_buff *skb);
 void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk,
@@ -2314,7 +2346,7 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
 	     (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE)))
 		__sock_recv_timestamp(msg, sk, skb);
 	else
-		sk->sk_stamp = kt;
+		sock_write_timestamp(sk, kt);
 
 	if (sock_flag(sk, SOCK_WIFI_STATUS) && skb->wifi_acked_valid)
 		__sock_recv_wifi_status(msg, sk, skb);
@@ -2335,9 +2367,9 @@ static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
 	if (sk->sk_flags & FLAGS_TS_OR_DROPS || sk->sk_tsflags & TSFLAGS_ANY)
 		__sock_recv_ts_and_drops(msg, sk, skb);
 	else if (unlikely(sock_flag(sk, SOCK_TIMESTAMP)))
-		sk->sk_stamp = skb->tstamp;
+		sock_write_timestamp(sk, skb->tstamp);
 	else if (unlikely(sk->sk_stamp == SK_DEFAULT_STAMP))
-		sk->sk_stamp = 0;
+		sock_write_timestamp(sk, 0);
 }
 
 void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags);
diff --git a/net/compat.c b/net/compat.c
index 3b2105f6549d..3c4b0283b29a 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -467,12 +467,14 @@ int compat_sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp)
 	ctv = (struct compat_timeval __user *) userstamp;
 	err = -ENOENT;
 	sock_enable_timestamp(sk, SOCK_TIMESTAMP);
-	tv = ktime_to_timeval(sk->sk_stamp);
+	tv = ktime_to_timeval(sock_read_timestamp(sk));
+
 	if (tv.tv_sec == -1)
 		return err;
 	if (tv.tv_sec == 0) {
-		sk->sk_stamp = ktime_get_real();
-		tv = ktime_to_timeval(sk->sk_stamp);
+		ktime_t kt = ktime_get_real();
+		sock_write_timestamp(sk, kt);
+		tv = ktime_to_timeval(kt);
 	}
 	err = 0;
 	if (put_user(tv.tv_sec, &ctv->tv_sec) ||
@@ -494,12 +496,13 @@ int compat_sock_get_timestampns(struct sock *sk, struct timespec __user *usersta
 	ctv = (struct compat_timespec __user *) userstamp;
 	err = -ENOENT;
 	sock_enable_timestamp(sk, SOCK_TIMESTAMP);
-	ts = ktime_to_timespec(sk->sk_stamp);
+	ts = ktime_to_timespec(sock_read_timestamp(sk));
 	if (ts.tv_sec == -1)
 		return err;
 	if (ts.tv_sec == 0) {
-		sk->sk_stamp = ktime_get_real();
-		ts = ktime_to_timespec(sk->sk_stamp);
+		ktime_t kt = ktime_get_real();
+		sock_write_timestamp(sk, kt);
+		ts = ktime_to_timespec(kt);
 	}
 	err = 0;
 	if (put_user(ts.tv_sec, &ctv->tv_sec) ||
diff --git a/net/core/sock.c b/net/core/sock.c
index 748765e35423..5a8a3b76832f 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2803,6 +2803,9 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 	sk->sk_sndtimeo		=	MAX_SCHEDULE_TIMEOUT;
 
 	sk->sk_stamp = SK_DEFAULT_STAMP;
+#if BITS_PER_LONG==32
+	seqlock_init(&sk->sk_stamp_seq);
+#endif
 	atomic_set(&sk->sk_zckey, 0);
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
@@ -2902,12 +2905,13 @@ int sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp)
 	struct timeval tv;
 
 	sock_enable_timestamp(sk, SOCK_TIMESTAMP);
-	tv = ktime_to_timeval(sk->sk_stamp);
+	tv = ktime_to_timeval(sock_read_timestamp(sk));
 	if (tv.tv_sec == -1)
 		return -ENOENT;
 	if (tv.tv_sec == 0) {
-		sk->sk_stamp = ktime_get_real();
-		tv = ktime_to_timeval(sk->sk_stamp);
+		ktime_t kt = ktime_get_real();
+		sock_write_timestamp(sk, kt);
+		tv = ktime_to_timeval(kt);
 	}
 	return copy_to_user(userstamp, &tv, sizeof(tv)) ? -EFAULT : 0;
 }
@@ -2918,11 +2922,12 @@ int sock_get_timestampns(struct sock *sk, struct timespec __user *userstamp)
 	struct timespec ts;
 
 	sock_enable_timestamp(sk, SOCK_TIMESTAMP);
-	ts = ktime_to_timespec(sk->sk_stamp);
+	ts = ktime_to_timespec(sock_read_timestamp(sk));
 	if (ts.tv_sec == -1)
 		return -ENOENT;
 	if (ts.tv_sec == 0) {
-		sk->sk_stamp = ktime_get_real();
+		ktime_t kt = ktime_get_real();
+		sock_write_timestamp(sk, kt);
 		ts = ktime_to_timespec(sk->sk_stamp);
 	}
 	return copy_to_user(userstamp, &ts, sizeof(ts)) ? -EFAULT : 0;
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 5445145e639c..fc1c0d9ef57d 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -574,7 +574,7 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp)
 		/* Don't enable netstamp, sunrpc doesn't
 		   need that much accuracy */
 	}
-	svsk->sk_sk->sk_stamp = skb->tstamp;
+	sock_write_timestamp(svsk->sk_sk, skb->tstamp);
 	set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); /* there may be more data... */
 
 	len  = skb->len;
-- 
2.20.1


From 75ba460c19060aa39147b8e1eaec603308308194 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 20 Dec 2018 15:28:56 -0800
Subject: [PATCH 32/58] tcp: fix a race in inet_diag_dump_icsk()

[ Upstream commit f0c928d878e7d01b613c9ae5c971a6b1e473a938 ]

Alexei reported use after frees in inet_diag_dump_icsk() [1]

Because we use refcount_set() when various sockets are setup and
inserted into ehash, we also need to make sure inet_diag_dump_icsk()
wont race with the refcount_set() operations.

Jonathan Lemon sent a patch changing net_twsk_hashdance() but
other spots would need risky changes.

Instead, fix inet_diag_dump_icsk() as this bug came with
linux-4.10 only.

[1] Quoting Alexei :

First something iterating over sockets finds already freed tw socket:

refcount_t: increment on 0; use-after-free.
WARNING: CPU: 2 PID: 2738 at lib/refcount.c:153 refcount_inc+0x26/0x30
RIP: 0010:refcount_inc+0x26/0x30
RSP: 0018:ffffc90004c8fbc0 EFLAGS: 00010282
RAX: 000000000000002b RBX: 0000000000000000 RCX: 0000000000000000
RDX: ffff88085ee9d680 RSI: ffff88085ee954c8 RDI: ffff88085ee954c8
RBP: ffff88010ecbd2c0 R08: 0000000000000000 R09: 000000000000174c
R10: ffffffff81e7c5a0 R11: 0000000000000000 R12: 0000000000000000
R13: ffff8806ba9bf210 R14: ffffffff82304600 R15: ffff88010ecbd328
FS:  00007f81f5a7d700(0000) GS:ffff88085ee80000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f81e2a95000 CR3: 000000069b2eb006 CR4: 00000000003606e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 inet_diag_dump_icsk+0x2b3/0x4e0 [inet_diag]  // sock_hold(sk); in net/ipv4/inet_diag.c:1002
 ? kmalloc_large_node+0x37/0x70
 ? __kmalloc_node_track_caller+0x1cb/0x260
 ? __alloc_skb+0x72/0x1b0
 ? __kmalloc_reserve.isra.40+0x2e/0x80
 __inet_diag_dump+0x3b/0x80 [inet_diag]
 netlink_dump+0x116/0x2a0
 netlink_recvmsg+0x205/0x3c0
 sock_read_iter+0x89/0xd0
 __vfs_read+0xf7/0x140
 vfs_read+0x8a/0x140
 SyS_read+0x3f/0xa0
 do_syscall_64+0x5a/0x100

then a minute later twsk timer fires and hits two bad refcnts
for this freed socket:

refcount_t: decrement hit 0; leaking memory.
WARNING: CPU: 31 PID: 0 at lib/refcount.c:228 refcount_dec+0x2e/0x40
Modules linked in:
RIP: 0010:refcount_dec+0x2e/0x40
RSP: 0018:ffff88085f5c3ea8 EFLAGS: 00010296
RAX: 000000000000002c RBX: ffff88010ecbd2c0 RCX: 000000000000083f
RDX: 0000000000000000 RSI: 00000000000000f6 RDI: 000000000000003f
RBP: ffffc90003c77280 R08: 0000000000000000 R09: 00000000000017d3
R10: ffffffff81e7c5a0 R11: 0000000000000000 R12: ffffffff82ad2d80
R13: ffffffff8182de00 R14: ffff88085f5c3ef8 R15: 0000000000000000
FS:  0000000000000000(0000) GS:ffff88085f5c0000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007fbe42685250 CR3: 0000000002209001 CR4: 00000000003606e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 <IRQ>
 inet_twsk_kill+0x9d/0xc0  // inet_twsk_bind_unhash(tw, hashinfo);
 call_timer_fn+0x29/0x110
 run_timer_softirq+0x36b/0x3a0

refcount_t: underflow; use-after-free.
WARNING: CPU: 31 PID: 0 at lib/refcount.c:187 refcount_sub_and_test+0x46/0x50
RIP: 0010:refcount_sub_and_test+0x46/0x50
RSP: 0018:ffff88085f5c3eb8 EFLAGS: 00010296
RAX: 0000000000000026 RBX: ffff88010ecbd2c0 RCX: 000000000000083f
RDX: 0000000000000000 RSI: 00000000000000f6 RDI: 000000000000003f
RBP: ffff88010ecbd358 R08: 0000000000000000 R09: 000000000000185b
R10: ffffffff81e7c5a0 R11: 0000000000000000 R12: ffff88010ecbd358
R13: ffffffff8182de00 R14: ffff88085f5c3ef8 R15: 0000000000000000
FS:  0000000000000000(0000) GS:ffff88085f5c0000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007fbe42685250 CR3: 0000000002209001 CR4: 00000000003606e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 <IRQ>
 inet_twsk_put+0x12/0x20  // inet_twsk_put(tw);
 call_timer_fn+0x29/0x110
 run_timer_softirq+0x36b/0x3a0

Fixes: 67db3e4bfbc9 ("tcp: no longer hold ehash lock while calling tcp_get_info()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Alexei Starovoitov <ast@kernel.org>
Cc: Jonathan Lemon <jonathan.lemon@gmail.com>
Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/inet_diag.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 4e5bc4b2f14e..1a4e9ff02762 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -998,7 +998,9 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb,
 			if (!inet_diag_bc_sk(bc, sk))
 				goto next_normal;
 
-			sock_hold(sk);
+			if (!refcount_inc_not_zero(&sk->sk_refcnt))
+				goto next_normal;
+
 			num_arr[accum] = num;
 			sk_arr[accum] = sk;
 			if (++accum == SKARR_SZ)
-- 
2.20.1


From cae883af6e5af0a74f498e0b7a381790335dbdf9 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Tue, 11 Dec 2018 21:43:51 -0800
Subject: [PATCH 33/58] tipc: check tsk->group in tipc_wait_for_cond()

[ Upstream commit 143ece654f9f5b37bedea252a990be37e48ae3a5 ]

tipc_wait_for_cond() drops socket lock before going to sleep,
but tsk->group could be freed right after that release_sock().
So we have to re-check and reload tsk->group after it wakes up.

After this patch, tipc_wait_for_cond() returns -ERESTARTSYS when
tsk->group is NULL, instead of continuing with the assumption of
a non-NULL tsk->group.

(It looks like 'dsts' should be re-checked and reloaded too, but
it is a different bug.)

Similar for tipc_send_group_unicast() and tipc_send_group_anycast().

Reported-by: syzbot+10a9db47c3a0e13eb31c@syzkaller.appspotmail.com
Fixes: b7d42635517f ("tipc: introduce flow control for group broadcast messages")
Fixes: ee106d7f942d ("tipc: introduce group anycast messaging")
Fixes: 27bd9ec027f3 ("tipc: introduce group unicast messaging")
Cc: Ying Xue <ying.xue@windriver.com>
Cc: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/socket.c | 25 ++++++++++++++-----------
 1 file changed, 14 insertions(+), 11 deletions(-)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 366ce0bf2658..9f3acd570a12 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -878,7 +878,6 @@ static int tipc_send_group_unicast(struct socket *sock, struct msghdr *m,
 	DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
 	int blks = tsk_blocks(GROUP_H_SIZE + dlen);
 	struct tipc_sock *tsk = tipc_sk(sk);
-	struct tipc_group *grp = tsk->group;
 	struct net *net = sock_net(sk);
 	struct tipc_member *mb = NULL;
 	u32 node, port;
@@ -892,7 +891,9 @@ static int tipc_send_group_unicast(struct socket *sock, struct msghdr *m,
 	/* Block or return if destination link or member is congested */
 	rc = tipc_wait_for_cond(sock, &timeout,
 				!tipc_dest_find(&tsk->cong_links, node, 0) &&
-				!tipc_group_cong(grp, node, port, blks, &mb));
+				tsk->group &&
+				!tipc_group_cong(tsk->group, node, port, blks,
+						 &mb));
 	if (unlikely(rc))
 		return rc;
 
@@ -922,7 +923,6 @@ static int tipc_send_group_anycast(struct socket *sock, struct msghdr *m,
 	struct tipc_sock *tsk = tipc_sk(sk);
 	struct list_head *cong_links = &tsk->cong_links;
 	int blks = tsk_blocks(GROUP_H_SIZE + dlen);
-	struct tipc_group *grp = tsk->group;
 	struct tipc_msg *hdr = &tsk->phdr;
 	struct tipc_member *first = NULL;
 	struct tipc_member *mbr = NULL;
@@ -939,9 +939,10 @@ static int tipc_send_group_anycast(struct socket *sock, struct msghdr *m,
 	type = msg_nametype(hdr);
 	inst = dest->addr.name.name.instance;
 	scope = msg_lookup_scope(hdr);
-	exclude = tipc_group_exclude(grp);
 
 	while (++lookups < 4) {
+		exclude = tipc_group_exclude(tsk->group);
+
 		first = NULL;
 
 		/* Look for a non-congested destination member, if any */
@@ -950,7 +951,8 @@ static int tipc_send_group_anycast(struct socket *sock, struct msghdr *m,
 						 &dstcnt, exclude, false))
 				return -EHOSTUNREACH;
 			tipc_dest_pop(&dsts, &node, &port);
-			cong = tipc_group_cong(grp, node, port, blks, &mbr);
+			cong = tipc_group_cong(tsk->group, node, port, blks,
+					       &mbr);
 			if (!cong)
 				break;
 			if (mbr == first)
@@ -969,7 +971,8 @@ static int tipc_send_group_anycast(struct socket *sock, struct msghdr *m,
 		/* Block or return if destination link or member is congested */
 		rc = tipc_wait_for_cond(sock, &timeout,
 					!tipc_dest_find(cong_links, node, 0) &&
-					!tipc_group_cong(grp, node, port,
+					tsk->group &&
+					!tipc_group_cong(tsk->group, node, port,
 							 blks, &mbr));
 		if (unlikely(rc))
 			return rc;
@@ -1004,8 +1007,7 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m,
 	struct sock *sk = sock->sk;
 	struct net *net = sock_net(sk);
 	struct tipc_sock *tsk = tipc_sk(sk);
-	struct tipc_group *grp = tsk->group;
-	struct tipc_nlist *dsts = tipc_group_dests(grp);
+	struct tipc_nlist *dsts = tipc_group_dests(tsk->group);
 	struct tipc_mc_method *method = &tsk->mc_method;
 	bool ack = method->mandatory && method->rcast;
 	int blks = tsk_blocks(MCAST_H_SIZE + dlen);
@@ -1018,8 +1020,9 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m,
 		return -EHOSTUNREACH;
 
 	/* Block or return if any destination link or member is congested */
-	rc = tipc_wait_for_cond(sock, &timeout,	!tsk->cong_link_cnt &&
-				!tipc_group_bc_cong(grp, blks));
+	rc = tipc_wait_for_cond(sock, &timeout,
+				!tsk->cong_link_cnt && tsk->group &&
+				!tipc_group_bc_cong(tsk->group, blks));
 	if (unlikely(rc))
 		return rc;
 
@@ -1034,7 +1037,7 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m,
 	msg_set_hdr_sz(hdr, GROUP_H_SIZE);
 	msg_set_destport(hdr, 0);
 	msg_set_destnode(hdr, 0);
-	msg_set_grp_bc_seqno(hdr, tipc_group_bc_snd_nxt(grp));
+	msg_set_grp_bc_seqno(hdr, tipc_group_bc_snd_nxt(tsk->group));
 
 	/* Avoid getting stuck with repeated forced replicasts */
 	msg_set_grp_bc_ack_req(hdr, ack);
-- 
2.20.1


From 33b9b9107edfd12f16e0769ca64f520e808fffce Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 10 Dec 2018 15:23:30 -0800
Subject: [PATCH 34/58] tipc: compare remote and local protocols in
 tipc_udp_enable()

[ Upstream commit fb83ed496b9a654f60cd1d58a0e1e79ec5694808 ]

When TIPC_NLA_UDP_REMOTE is an IPv6 mcast address but
TIPC_NLA_UDP_LOCAL is an IPv4 address, a NULL-ptr deref is triggered
as the UDP tunnel sock is initialized to IPv4 or IPv6 sock merely
based on the protocol in local address.

We should just error out when the remote address and local address
have different protocols.

Reported-by: syzbot+eb4da3a20fad2e52555d@syzkaller.appspotmail.com
Cc: Ying Xue <ying.xue@windriver.com>
Cc: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/udp_media.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index 9783101bc4a9..e685af4f5483 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -680,6 +680,11 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b,
 	if (err)
 		goto err;
 
+	if (remote.proto != local.proto) {
+		err = -EINVAL;
+		goto err;
+	}
+
 	/* Autoconfigure own node identity if needed */
 	if (!tipc_own_id(net)) {
 		memcpy(node_id, local.ipv6.in6_u.u6_addr8, 16);
-- 
2.20.1


From a911a6fc7311f2b9d9e63827a98d53dae91768dc Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sun, 23 Dec 2018 21:45:56 -0800
Subject: [PATCH 35/58] tipc: fix a double free in tipc_enable_bearer()

[ Upstream commit dc4501ff287547dea7ca10f1c580c741291a8760 ]

bearer_disable() already calls kfree_rcu() to free struct tipc_bearer,
we don't need to call kfree() again.

Fixes: cb30a63384bc ("tipc: refactor function tipc_enable_bearer()")
Reported-by: syzbot+b981acf1fb240c0c128b@syzkaller.appspotmail.com
Cc: Ying Xue <ying.xue@windriver.com>
Cc: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/bearer.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index 645c16052052..2649a0a0d45e 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -317,7 +317,6 @@ static int tipc_enable_bearer(struct net *net, const char *name,
 	res = tipc_disc_create(net, b, &b->bcast_addr, &skb);
 	if (res) {
 		bearer_disable(net, b);
-		kfree(b);
 		errstr = "failed to create discoverer";
 		goto rejected;
 	}
-- 
2.20.1


From 2156f760a12b4cdabfafc0d6f76b2c045e1899ff Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 10 Dec 2018 12:45:45 -0800
Subject: [PATCH 36/58] tipc: fix a double kfree_skb()

[ Upstream commit acb4a33e9856d5fa3384b87d3d8369229be06d31 ]

tipc_udp_xmit() drops the packet on error, there is no
need to drop it again.

Fixes: ef20cd4dd163 ("tipc: introduce UDP replicast")
Reported-and-tested-by: syzbot+eae585ba2cc2752d3704@syzkaller.appspotmail.com
Cc: Ying Xue <ying.xue@windriver.com>
Cc: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/udp_media.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index e685af4f5483..da2d311476ab 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -245,10 +245,8 @@ static int tipc_udp_send_msg(struct net *net, struct sk_buff *skb,
 		}
 
 		err = tipc_udp_xmit(net, _skb, ub, src, &rcast->addr);
-		if (err) {
-			kfree_skb(_skb);
+		if (err)
 			goto out;
-		}
 	}
 	err = 0;
 out:
-- 
2.20.1


From af37c4dd02b09e191d867068f6ec29afd194f2b5 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 10 Dec 2018 11:49:55 -0800
Subject: [PATCH 37/58] tipc: use lock_sock() in tipc_sk_reinit()

[ Upstream commit 15ef70e286176165d28b0b8a969b422561a68dfc ]

lock_sock() must be used in process context to be race-free with
other lock_sock() callers, for example, tipc_release(). Otherwise
using the spinlock directly can't serialize a parallel tipc_release().

As it is blocking, we have to hold the sock refcnt before
rhashtable_walk_stop() and release it after rhashtable_walk_start().

Fixes: 07f6c4bc048a ("tipc: convert tipc reference table to use generic rhashtable")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Ying Xue <ying.xue@windriver.com>
Cc: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/socket.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 9f3acd570a12..ece09dfeac52 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2686,11 +2686,15 @@ void tipc_sk_reinit(struct net *net)
 		rhashtable_walk_start(&iter);
 
 		while ((tsk = rhashtable_walk_next(&iter)) && !IS_ERR(tsk)) {
-			spin_lock_bh(&tsk->sk.sk_lock.slock);
+			sock_hold(&tsk->sk);
+			rhashtable_walk_stop(&iter);
+			lock_sock(&tsk->sk);
 			msg = &tsk->phdr;
 			msg_set_prevnode(msg, tipc_own_addr(net));
 			msg_set_orignode(msg, tipc_own_addr(net));
-			spin_unlock_bh(&tsk->sk.sk_lock.slock);
+			release_sock(&tsk->sk);
+			rhashtable_walk_start(&iter);
+			sock_put(&tsk->sk);
 		}
 
 		rhashtable_walk_stop(&iter);
-- 
2.20.1


From 8dd00f70aec0413f70f22e1a9cdc7138c763a461 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Thu, 13 Dec 2018 10:53:37 +0800
Subject: [PATCH 38/58] vhost: make sure used idx is seen before log in
 vhost_add_used_n()

[ Upstream commit 841df922417eb82c835e93d4b93eb6a68c99d599 ]

We miss a write barrier that guarantees used idx is updated and seen
before log. This will let userspace sync and copy used ring before
used idx is update. Fix this by adding a barrier before log_write().

Fixes: 8dd014adfea6f ("vhost-net: mergeable buffers support")
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/vhost.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index eb95daa3e5a5..55e5aa662ad5 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -2233,6 +2233,8 @@ int vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads,
 		return -EFAULT;
 	}
 	if (unlikely(vq->log_used)) {
+		/* Make sure used idx is seen before log. */
+		smp_wmb();
 		/* Log used index update. */
 		log_write(vq->log_base,
 			  vq->log_addr + offsetof(struct vring_used, idx),
-- 
2.20.1


From 1b8b8341bc2daf3fcc36ad8ead37bfb8625670e1 Mon Sep 17 00:00:00 2001
From: Jorgen Hansen <jhansen@vmware.com>
Date: Tue, 18 Dec 2018 00:34:06 -0800
Subject: [PATCH 39/58] VSOCK: Send reset control packet when socket is
 partially bound

[ Upstream commit a915b982d8f5e4295f64b8dd37ce753874867e88 ]

If a server side socket is bound to an address, but not in the listening
state yet, incoming connection requests should receive a reset control
packet in response. However, the function used to send the reset
silently drops the reset packet if the sending socket isn't bound
to a remote address (as is the case for a bound socket not yet in
the listening state). This change fixes this by using the src
of the incoming packet as destination for the reset packet in
this case.

Fixes: d021c344051a ("VSOCK: Introduce VM Sockets")
Reviewed-by: Adit Ranadive <aditr@vmware.com>
Reviewed-by: Vishnu Dasa <vdasa@vmware.com>
Signed-off-by: Jorgen Hansen <jhansen@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/vmw_vsock/vmci_transport.c | 67 +++++++++++++++++++++++++---------
 1 file changed, 50 insertions(+), 17 deletions(-)

diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index cb332adb84cd..c361ce782412 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -263,6 +263,31 @@ vmci_transport_send_control_pkt_bh(struct sockaddr_vm *src,
 						 false);
 }
 
+static int
+vmci_transport_alloc_send_control_pkt(struct sockaddr_vm *src,
+				      struct sockaddr_vm *dst,
+				      enum vmci_transport_packet_type type,
+				      u64 size,
+				      u64 mode,
+				      struct vmci_transport_waiting_info *wait,
+				      u16 proto,
+				      struct vmci_handle handle)
+{
+	struct vmci_transport_packet *pkt;
+	int err;
+
+	pkt = kmalloc(sizeof(*pkt), GFP_KERNEL);
+	if (!pkt)
+		return -ENOMEM;
+
+	err = __vmci_transport_send_control_pkt(pkt, src, dst, type, size,
+						mode, wait, proto, handle,
+						true);
+	kfree(pkt);
+
+	return err;
+}
+
 static int
 vmci_transport_send_control_pkt(struct sock *sk,
 				enum vmci_transport_packet_type type,
@@ -272,9 +297,7 @@ vmci_transport_send_control_pkt(struct sock *sk,
 				u16 proto,
 				struct vmci_handle handle)
 {
-	struct vmci_transport_packet *pkt;
 	struct vsock_sock *vsk;
-	int err;
 
 	vsk = vsock_sk(sk);
 
@@ -284,17 +307,10 @@ vmci_transport_send_control_pkt(struct sock *sk,
 	if (!vsock_addr_bound(&vsk->remote_addr))
 		return -EINVAL;
 
-	pkt = kmalloc(sizeof(*pkt), GFP_KERNEL);
-	if (!pkt)
-		return -ENOMEM;
-
-	err = __vmci_transport_send_control_pkt(pkt, &vsk->local_addr,
-						&vsk->remote_addr, type, size,
-						mode, wait, proto, handle,
-						true);
-	kfree(pkt);
-
-	return err;
+	return vmci_transport_alloc_send_control_pkt(&vsk->local_addr,
+						     &vsk->remote_addr,
+						     type, size, mode,
+						     wait, proto, handle);
 }
 
 static int vmci_transport_send_reset_bh(struct sockaddr_vm *dst,
@@ -312,12 +328,29 @@ static int vmci_transport_send_reset_bh(struct sockaddr_vm *dst,
 static int vmci_transport_send_reset(struct sock *sk,
 				     struct vmci_transport_packet *pkt)
 {
+	struct sockaddr_vm *dst_ptr;
+	struct sockaddr_vm dst;
+	struct vsock_sock *vsk;
+
 	if (pkt->type == VMCI_TRANSPORT_PACKET_TYPE_RST)
 		return 0;
-	return vmci_transport_send_control_pkt(sk,
-					VMCI_TRANSPORT_PACKET_TYPE_RST,
-					0, 0, NULL, VSOCK_PROTO_INVALID,
-					VMCI_INVALID_HANDLE);
+
+	vsk = vsock_sk(sk);
+
+	if (!vsock_addr_bound(&vsk->local_addr))
+		return -EINVAL;
+
+	if (vsock_addr_bound(&vsk->remote_addr)) {
+		dst_ptr = &vsk->remote_addr;
+	} else {
+		vsock_addr_init(&dst, pkt->dg.src.context,
+				pkt->src_port);
+		dst_ptr = &dst;
+	}
+	return vmci_transport_alloc_send_control_pkt(&vsk->local_addr, dst_ptr,
+					     VMCI_TRANSPORT_PACKET_TYPE_RST,
+					     0, 0, NULL, VSOCK_PROTO_INVALID,
+					     VMCI_INVALID_HANDLE);
 }
 
 static int vmci_transport_send_negotiate(struct sock *sk, size_t size)
-- 
2.20.1


From cc983a1b00bc196bc571350c00006e555b3c1abc Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Tue, 18 Dec 2018 16:06:19 +0100
Subject: [PATCH 40/58] xen/netfront: tolerate frags with no data

[ Upstream commit d81c5054a5d1d4999c7cdead7636b6cd4af83d36 ]

At least old Xen net backends seem to send frags with no real data
sometimes. In case such a fragment happens to occur with the frag limit
already reached the frontend will BUG currently even if this situation
is easily recoverable.

Modify the BUG_ON() condition accordingly.

Tested-by: Dietmar Hahn <dietmar.hahn@ts.fujitsu.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netfront.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index f17f602e6171..5b97cc946d70 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -905,7 +905,7 @@ static RING_IDX xennet_fill_frags(struct netfront_queue *queue,
 		if (skb_shinfo(skb)->nr_frags == MAX_SKB_FRAGS) {
 			unsigned int pull_to = NETFRONT_SKB_CB(skb)->pull_to;
 
-			BUG_ON(pull_to <= skb_headlen(skb));
+			BUG_ON(pull_to < skb_headlen(skb));
 			__pskb_pull_tail(skb, pull_to - skb_headlen(skb));
 		}
 		if (unlikely(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS)) {
-- 
2.20.1


From 661e55267df44c5539cea355c41410770f607310 Mon Sep 17 00:00:00 2001
From: Yuval Avnery <yuvalav@mellanox.com>
Date: Thu, 13 Dec 2018 02:26:46 +0200
Subject: [PATCH 41/58] net/mlx5: Typo fix in del_sw_hw_rule

[ Upstream commit f0337889147c956721696553ffcc97212b0948fe ]

Expression terminated with "," instead of ";", resulted in
set_fte getting bad value for modify_enable_mask field.

Fixes: bd5251dbf156 ("net/mlx5_core: Introduce flow steering destination of type counter")
Signed-off-by: Yuval Avnery <yuvalav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 37d114c668b7..d181645fd968 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -432,7 +432,7 @@ static void del_sw_hw_rule(struct fs_node *node)
 
 	if ((fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) &&
 	    --fte->dests_size) {
-		modify_mask = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_DESTINATION_LIST),
+		modify_mask = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_DESTINATION_LIST);
 		update_fte = true;
 	}
 out:
-- 
2.20.1


From 5d1a6461e47275bb74091159df8a0e1172f4924f Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sun, 16 Dec 2018 23:25:12 -0800
Subject: [PATCH 42/58] tipc: check group dests after tipc_wait_for_cond()

[ Upstream commit 3c6306d44082ef007a258ae1b86ea58e6974ee3f ]

Similar to commit 143ece654f9f ("tipc: check tsk->group in tipc_wait_for_cond()")
we have to reload grp->dests too after we re-take the sock lock.
This means we need to move the dsts check after tipc_wait_for_cond()
too.

Fixes: 75da2163dbb6 ("tipc: introduce communication groups")
Reported-and-tested-by: syzbot+99f20222fc5018d2b97a@syzkaller.appspotmail.com
Cc: Ying Xue <ying.xue@windriver.com>
Cc: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/socket.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index ece09dfeac52..e1bdaf056c8f 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1007,7 +1007,7 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m,
 	struct sock *sk = sock->sk;
 	struct net *net = sock_net(sk);
 	struct tipc_sock *tsk = tipc_sk(sk);
-	struct tipc_nlist *dsts = tipc_group_dests(tsk->group);
+	struct tipc_nlist *dsts;
 	struct tipc_mc_method *method = &tsk->mc_method;
 	bool ack = method->mandatory && method->rcast;
 	int blks = tsk_blocks(MCAST_H_SIZE + dlen);
@@ -1016,9 +1016,6 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m,
 	struct sk_buff_head pkts;
 	int rc = -EHOSTUNREACH;
 
-	if (!dsts->local && !dsts->remote)
-		return -EHOSTUNREACH;
-
 	/* Block or return if any destination link or member is congested */
 	rc = tipc_wait_for_cond(sock, &timeout,
 				!tsk->cong_link_cnt && tsk->group &&
@@ -1026,6 +1023,10 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m,
 	if (unlikely(rc))
 		return rc;
 
+	dsts = tipc_group_dests(tsk->group);
+	if (!dsts->local && !dsts->remote)
+		return -EHOSTUNREACH;
+
 	/* Complete message header */
 	if (dest) {
 		msg_set_type(hdr, TIPC_GRP_MCAST_MSG);
-- 
2.20.1


From f8b8dfe26e0f20ae16dfbf0728916d715a9b43d1 Mon Sep 17 00:00:00 2001
From: Alaa Hleihel <alaa@mellanox.com>
Date: Sun, 25 Nov 2018 11:46:09 +0200
Subject: [PATCH 43/58] net/mlx5e: Remove the false indication of software
 timestamping support

[ Upstream commit 4765420439e758bfa4808392d18b0a4cb6f06065 ]

mlx5 driver falsely advertises support of software timestamping.
Fix it by removing the false indication.

Fixes: ef9814deafd0 ("net/mlx5e: Add HW timestamping (TS) support")
Signed-off-by: Alaa Hleihel <alaa@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 98dd3e0ada72..5e5423076b03 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1101,11 +1101,6 @@ int mlx5e_ethtool_get_ts_info(struct mlx5e_priv *priv,
 			      struct ethtool_ts_info *info)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
-	int ret;
-
-	ret = ethtool_op_get_ts_info(priv->netdev, info);
-	if (ret)
-		return ret;
 
 	info->phc_index = mlx5_clock_get_ptp_index(mdev);
 
@@ -1113,9 +1108,9 @@ int mlx5e_ethtool_get_ts_info(struct mlx5e_priv *priv,
 	    info->phc_index == -1)
 		return 0;
 
-	info->so_timestamping |= SOF_TIMESTAMPING_TX_HARDWARE |
-				 SOF_TIMESTAMPING_RX_HARDWARE |
-				 SOF_TIMESTAMPING_RAW_HARDWARE;
+	info->so_timestamping = SOF_TIMESTAMPING_TX_HARDWARE |
+				SOF_TIMESTAMPING_RX_HARDWARE |
+				SOF_TIMESTAMPING_RAW_HARDWARE;
 
 	info->tx_types = BIT(HWTSTAMP_TX_OFF) |
 			 BIT(HWTSTAMP_TX_ON);
-- 
2.20.1


From ae7476f75c080d9006528faf1d7ea292f6e4661a Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Thu, 20 Dec 2018 21:20:10 +0800
Subject: [PATCH 44/58] ipv6: frags: Fix bogus skb->sk in reassembled packets

[ Upstream commit d15f5ac8deea936d3adf629421a66a88b42b8a2f ]

It was reported that IPsec would crash when it encounters an IPv6
reassembled packet because skb->sk is non-zero and not a valid
pointer.

This is because skb->sk is now a union with ip_defrag_offset.

This patch fixes this by resetting skb->sk when exiting from
the reassembly code.

Reported-by: Xiumei Mu <xmu@redhat.com>
Fixes: 219badfaade9 ("ipv6: frags: get rid of ip6frag_skb_cb/...")
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/reassembly.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index d3fd2d7e5aa4..7c943392c128 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -384,6 +384,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
 		if (skb_try_coalesce(head, fp, &headstolen, &delta)) {
 			kfree_skb_partial(fp, headstolen);
 		} else {
+			fp->sk = NULL;
 			if (!skb_shinfo(head)->frag_list)
 				skb_shinfo(head)->frag_list = fp;
 			head->data_len += fp->len;
-- 
2.20.1


From 42634b6b33dccdeb8f874d294a30ed7b6843376b Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Fri, 28 Dec 2018 23:28:21 +0100
Subject: [PATCH 45/58] net/ipv6: Fix a test against 'ipv6_find_idev()' return
 value

[ Upstream commit 178fe94405bffbd1acd83b6ff3b40211185ae9c9 ]

'ipv6_find_idev()' returns NULL on error, not an error pointer.
Update the test accordingly and return -ENOBUFS, as already done in
'addrconf_add_dev()', if NULL is returned.

Fixes: ("ipv6: allow userspace to add IFA_F_OPTIMISTIC addresses")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 4e81ff2f4588..3dfc50cd86d6 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -4711,8 +4711,8 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
 			 IFA_F_MCAUTOJOIN | IFA_F_OPTIMISTIC;
 
 	idev = ipv6_find_idev(dev);
-	if (IS_ERR(idev))
-		return PTR_ERR(idev);
+	if (!idev)
+		return -ENOBUFS;
 
 	if (!ipv6_allow_optimistic_dad(net, idev))
 		cfg.ifa_flags &= ~IFA_F_OPTIMISTIC;
-- 
2.20.1


From 1808111c71bed57dcca472777b0fcb7da7b4b9e3 Mon Sep 17 00:00:00 2001
From: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Date: Mon, 10 Dec 2018 15:03:43 -0800
Subject: [PATCH 46/58] nfp: flower: ensure TCP flags can be placed in IPv6
 frame

[ Upstream commit 290974d434783624c13a9530a23c45f9c5ffe018 ]

Previously we did not ensure tcp flags have a place to be stored
when using IPv6. We correct this by including IPv6 key layer when
we match tcp flags and the IPv6 key layer has not been included
already.

Fixes: 07e1671cfca5 ("nfp: flower: refactor shared ip header in match offload")
Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/netronome/nfp/flower/offload.c   | 28 +++++++++++++++----
 1 file changed, 22 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index bd19624f10cf..90148dbb261b 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -375,13 +375,29 @@ nfp_flower_calculate_key_layers(struct nfp_app *app,
 		    !(tcp_flags & (TCPHDR_FIN | TCPHDR_SYN | TCPHDR_RST)))
 			return -EOPNOTSUPP;
 
-		/* We need to store TCP flags in the IPv4 key space, thus
-		 * we need to ensure we include a IPv4 key layer if we have
-		 * not done so already.
+		/* We need to store TCP flags in the either the IPv4 or IPv6 key
+		 * space, thus we need to ensure we include a IPv4/IPv6 key
+		 * layer if we have not done so already.
 		 */
-		if (!(key_layer & NFP_FLOWER_LAYER_IPV4)) {
-			key_layer |= NFP_FLOWER_LAYER_IPV4;
-			key_size += sizeof(struct nfp_flower_ipv4);
+		if (!key_basic)
+			return -EOPNOTSUPP;
+
+		if (!(key_layer & NFP_FLOWER_LAYER_IPV4) &&
+		    !(key_layer & NFP_FLOWER_LAYER_IPV6)) {
+			switch (key_basic->n_proto) {
+			case cpu_to_be16(ETH_P_IP):
+				key_layer |= NFP_FLOWER_LAYER_IPV4;
+				key_size += sizeof(struct nfp_flower_ipv4);
+				break;
+
+			case cpu_to_be16(ETH_P_IPV6):
+				key_layer |= NFP_FLOWER_LAYER_IPV6;
+				key_size += sizeof(struct nfp_flower_ipv6);
+				break;
+
+			default:
+				return -EOPNOTSUPP;
+			}
 		}
 	}
 
-- 
2.20.1


From 9accda8ff27ea102e9dcf505d6bce14e34541fa6 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Wed, 2 Jan 2019 13:29:27 +0100
Subject: [PATCH 47/58] ipv6: route: Fix return value of ip6_neigh_lookup() on
 neigh_create() error

[ Upstream commit 7adf3246092f5e87ed0fa610e8088fae416c581f ]

In ip6_neigh_lookup(), we must not return errors coming from
neigh_create(): if creation of a neighbour entry fails, the lookup should
return NULL, in the same way as it's done in __neigh_lookup().

Otherwise, callers legitimately checking for a non-NULL return value of
the lookup function might dereference an invalid pointer.

For instance, on neighbour table overflow, ndisc_router_discovery()
crashes ndisc_update() by passing ERR_PTR(-ENOBUFS) as 'neigh' argument.

Reported-by: Jianlin Shi <jishi@redhat.com>
Fixes: f8a1b43b709d ("net/ipv6: Create a neigh_lookup for FIB entries")
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index a33681dc4796..08c4516ae4a4 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -210,7 +210,9 @@ struct neighbour *ip6_neigh_lookup(const struct in6_addr *gw,
 	n = __ipv6_neigh_lookup(dev, daddr);
 	if (n)
 		return n;
-	return neigh_create(&nd_tbl, daddr, dev);
+
+	n = neigh_create(&nd_tbl, daddr, dev);
+	return IS_ERR(n) ? NULL : n;
 }
 
 static struct neighbour *ip6_dst_neigh_lookup(const struct dst_entry *dst,
-- 
2.20.1


From 4aa6a772add21c1b282bee1c3e444895bbb9a153 Mon Sep 17 00:00:00 2001
From: "Allan W. Nielsen" <allan.nielsen@microchip.com>
Date: Thu, 20 Dec 2018 09:37:17 +0100
Subject: [PATCH 48/58] mscc: Configured MAC entries should be locked.

[ Upstream commit 8fd1a4affbdafda592f80cd01bf7a382a5ff2fe8 ]

The MAC table in Ocelot supports auto aging (normal) and static entries.
MAC entries that is manually configured should be static and not subject
to aging.

Fixes: a556c76adc05 ("net: mscc: Add initial Ocelot switch support")
Signed-off-by: Allan Nielsen <allan.nielsen@microchip.com>
Reviewed-by: Steen Hegelund <steen.hegelund@microchip.com>
Signed-off-by: Steen Hegelund <steen.hegelund@microchip.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index ed4e298cd823..0bdd3c400c92 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -733,7 +733,7 @@ static int ocelot_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 	}
 
 	return ocelot_mact_learn(ocelot, port->chip_port, addr, vid,
-				 ENTRYTYPE_NORMAL);
+				 ENTRYTYPE_LOCKED);
 }
 
 static int ocelot_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
-- 
2.20.1


From ce16bf5e3b4a9f27246bdb699a59ad4fffd50613 Mon Sep 17 00:00:00 2001
From: Tal Gilboa <talgi@mellanox.com>
Date: Thu, 22 Nov 2018 14:20:45 +0200
Subject: [PATCH 49/58] net/mlx5e: Cancel DIM work on close SQ

[ Upstream commit fa2bf86bab4bbc61e5678a42a14e40075093a98f ]

TXQ SQ closure is followed by closing the corresponding CQ. A pending
DIM work would try to modify the now non-existing CQ.
This would trigger an error:
[85535.835926] mlx5_core 0000:af:00.0: mlx5_cmd_check:769:(pid 124399):
MODIFY_CQ(0x403) op_mod(0x0) failed, status bad resource state(0x9), syndrome (0x1d7771)

Fix by making sure to cancel any pending DIM work before destroying the SQ.

Fixes: cbce4f444798 ("net/mlx5e: Enable adaptive-TX moderation")
Signed-off-by: Tal Gilboa <talgi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index faa84b45e20a..fddb6001e3a7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1383,6 +1383,7 @@ static void mlx5e_close_txqsq(struct mlx5e_txqsq *sq)
 	struct mlx5_core_dev *mdev = c->mdev;
 	struct mlx5_rate_limit rl = {0};
 
+	cancel_work_sync(&sq->dim.work);
 	mlx5e_destroy_sq(mdev, sq->sqn);
 	if (sq->rate_limit) {
 		rl.rate = sq->rate_limit;
-- 
2.20.1


From e1151c0e4634ac064c02eece9029a3738c1517c5 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Fri, 2 Nov 2018 06:10:49 +0200
Subject: [PATCH 50/58] net/mlx5e: RX, Verify MPWQE stride size is in range

[ Upstream commit e1c15b62b7015119d3e5915cd2ae3b89d59c2576 ]

Add check of MPWQE stride size is within range supported by HW. In case
calculated MPWQE stride size exceed range, linear SKB can't be used and
we should use non linear MPWQE instead.

Fixes: 619a8f2a42f1 ("net/mlx5e: Use linear SKB in Striding RQ")
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index fddb6001e3a7..7365899c3ac9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -128,6 +128,8 @@ static bool mlx5e_rx_is_linear_skb(struct mlx5_core_dev *mdev,
 	return !params->lro_en && frag_sz <= PAGE_SIZE;
 }
 
+#define MLX5_MAX_MPWQE_LOG_WQE_STRIDE_SZ ((BIT(__mlx5_bit_sz(wq, log_wqe_stride_size)) - 1) + \
+					  MLX5_MPWQE_LOG_STRIDE_SZ_BASE)
 static bool mlx5e_rx_mpwqe_is_linear_skb(struct mlx5_core_dev *mdev,
 					 struct mlx5e_params *params)
 {
@@ -138,6 +140,9 @@ static bool mlx5e_rx_mpwqe_is_linear_skb(struct mlx5_core_dev *mdev,
 	if (!mlx5e_rx_is_linear_skb(mdev, params))
 		return false;
 
+	if (order_base_2(frag_sz) > MLX5_MAX_MPWQE_LOG_WQE_STRIDE_SZ)
+		return false;
+
 	if (MLX5_CAP_GEN(mdev, ext_stride_num_range))
 		return true;
 
-- 
2.20.1


From 19d0eb2c95613a871e83642ee566abf473b6341a Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Wed, 19 Dec 2018 18:00:12 +0100
Subject: [PATCH 51/58] net: mvpp2: fix the phylink mode validation

[ Upstream commit 1b451fb2051b464b9758c09a3492104403252e2b ]

The mvpp2_phylink_validate() sets all modes that are supported by a
given PPv2 port. An mistake made the 10000baseT_Full mode being
advertised in some cases when a port wasn't configured to perform at
10G. This patch fixes this.

Fixes: d97c9f4ab000 ("net: mvpp2: 1000baseX support")
Reported-by: Russell King <linux@armlinux.org.uk>
Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index d5bc90476b4f..f8e4808a8317 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -4293,6 +4293,7 @@ static void mvpp2_phylink_validate(struct net_device *dev,
 	case PHY_INTERFACE_MODE_XAUI:
 	case PHY_INTERFACE_MODE_NA:
 		if (port->gop_id == 0) {
+			phylink_set(mask, 10000baseT_Full);
 			phylink_set(mask, 10000baseCR_Full);
 			phylink_set(mask, 10000baseSR_Full);
 			phylink_set(mask, 10000baseLR_Full);
@@ -4310,7 +4311,6 @@ static void mvpp2_phylink_validate(struct net_device *dev,
 		phylink_set(mask, 10baseT_Full);
 		phylink_set(mask, 100baseT_Half);
 		phylink_set(mask, 100baseT_Full);
-		phylink_set(mask, 10000baseT_Full);
 		/* Fall-through */
 	case PHY_INTERFACE_MODE_1000BASEX:
 	case PHY_INTERFACE_MODE_2500BASEX:
-- 
2.20.1


From 386bb44877355be7ef26f59e421a14e1e0ce3754 Mon Sep 17 00:00:00 2001
From: Sudarsana Reddy Kalluru <sudarsana.kalluru@cavium.com>
Date: Sun, 9 Dec 2018 23:27:01 -0800
Subject: [PATCH 52/58] qed: Fix command number mismatch between driver and the
 mfw

[ Upstream commit c3db8d531045774aeee6e0f731ab15b0c450de45 ]

The value for OEM_CFG_UPDATE command differs between driver and the
Management firmware (mfw). Fix this gap with adding a reserved field.

Fixes: cac6f691546b ("qed: Add support for Unified Fabric Port.")
Signed-off-by: Sudarsana Reddy Kalluru <Sudarsana.Kalluru@cavium.com>
Signed-off-by: Ariel Elior <ariel.elior@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_hsi.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
index a71382687ef2..bed8f48e029a 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
@@ -12669,8 +12669,9 @@ enum MFW_DRV_MSG_TYPE {
 	MFW_DRV_MSG_BW_UPDATE10,
 	MFW_DRV_MSG_TRANSCEIVER_STATE_CHANGE,
 	MFW_DRV_MSG_BW_UPDATE11,
-	MFW_DRV_MSG_OEM_CFG_UPDATE,
+	MFW_DRV_MSG_RESERVED,
 	MFW_DRV_MSG_GET_TLV_REQ,
+	MFW_DRV_MSG_OEM_CFG_UPDATE,
 	MFW_DRV_MSG_MAX
 };
 
-- 
2.20.1


From e42b2f72a2af221013d437ddddf2b63a65681eac Mon Sep 17 00:00:00 2001
From: Shalom Toledo <shalomt@mellanox.com>
Date: Tue, 18 Dec 2018 15:59:20 +0000
Subject: [PATCH 53/58] mlxsw: core: Increase timeout during firmware flash
 process

[ Upstream commit cf0b70e71b32137ccf9c1f3dd9fb30cbf89b4322 ]

During the firmware flash process, some of the EMADs get timed out, which
causes the driver to send them again with a limit of 5 retries. There are
some situations in which 5 retries is not enough and the EMAD access fails.
If the failed EMAD was related to the flashing process, the driver fails
the flashing.

The reason for these timeouts during firmware flashing is cache misses in
the CPU running the firmware. In case the CPU needs to fetch instructions
from the flash when a firmware is flashed, it needs to wait for the
flashing to complete. Since flashing takes time, it is possible for pending
EMADs to timeout.

Fix by increasing EMADs' timeout while flashing firmware.

Fixes: ce6ef68f433f ("mlxsw: spectrum: Implement the ethtool flash_device callback")
Signed-off-by: Shalom Toledo <shalomt@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/core.c    | 19 ++++++++++++++++++-
 drivers/net/ethernet/mellanox/mlxsw/core.h    |  3 +++
 .../net/ethernet/mellanox/mlxsw/spectrum.c    |  7 ++++++-
 3 files changed, 27 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index 30f751e69698..f7154f358f27 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -81,6 +81,7 @@ struct mlxsw_core {
 	struct mlxsw_core_port *ports;
 	unsigned int max_ports;
 	bool reload_fail;
+	bool fw_flash_in_progress;
 	unsigned long driver_priv[0];
 	/* driver_priv has to be always the last item */
 };
@@ -428,12 +429,16 @@ struct mlxsw_reg_trans {
 	struct rcu_head rcu;
 };
 
-#define MLXSW_EMAD_TIMEOUT_MS 200
+#define MLXSW_EMAD_TIMEOUT_DURING_FW_FLASH_MS	3000
+#define MLXSW_EMAD_TIMEOUT_MS			200
 
 static void mlxsw_emad_trans_timeout_schedule(struct mlxsw_reg_trans *trans)
 {
 	unsigned long timeout = msecs_to_jiffies(MLXSW_EMAD_TIMEOUT_MS);
 
+	if (trans->core->fw_flash_in_progress)
+		timeout = msecs_to_jiffies(MLXSW_EMAD_TIMEOUT_DURING_FW_FLASH_MS);
+
 	queue_delayed_work(trans->core->emad_wq, &trans->timeout_dw, timeout);
 }
 
@@ -1854,6 +1859,18 @@ int mlxsw_core_kvd_sizes_get(struct mlxsw_core *mlxsw_core,
 }
 EXPORT_SYMBOL(mlxsw_core_kvd_sizes_get);
 
+void mlxsw_core_fw_flash_start(struct mlxsw_core *mlxsw_core)
+{
+	mlxsw_core->fw_flash_in_progress = true;
+}
+EXPORT_SYMBOL(mlxsw_core_fw_flash_start);
+
+void mlxsw_core_fw_flash_end(struct mlxsw_core *mlxsw_core)
+{
+	mlxsw_core->fw_flash_in_progress = false;
+}
+EXPORT_SYMBOL(mlxsw_core_fw_flash_end);
+
 static int __init mlxsw_core_module_init(void)
 {
 	int err;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h
index c35be477856f..c4e4971764e5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.h
@@ -292,6 +292,9 @@ int mlxsw_core_kvd_sizes_get(struct mlxsw_core *mlxsw_core,
 			     u64 *p_single_size, u64 *p_double_size,
 			     u64 *p_linear_size);
 
+void mlxsw_core_fw_flash_start(struct mlxsw_core *mlxsw_core);
+void mlxsw_core_fw_flash_end(struct mlxsw_core *mlxsw_core);
+
 bool mlxsw_core_res_valid(struct mlxsw_core *mlxsw_core,
 			  enum mlxsw_res_id res_id);
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index ada644d90029..3d1159f8a53f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -308,8 +308,13 @@ static int mlxsw_sp_firmware_flash(struct mlxsw_sp *mlxsw_sp,
 		},
 		.mlxsw_sp = mlxsw_sp
 	};
+	int err;
+
+	mlxsw_core_fw_flash_start(mlxsw_sp->core);
+	err = mlxfw_firmware_flash(&mlxsw_sp_mlxfw_dev.mlxfw_dev, firmware);
+	mlxsw_core_fw_flash_end(mlxsw_sp->core);
 
-	return mlxfw_firmware_flash(&mlxsw_sp_mlxfw_dev.mlxfw_dev, firmware);
+	return err;
 }
 
 static int mlxsw_sp_fw_rev_validate(struct mlxsw_sp *mlxsw_sp)
-- 
2.20.1


From d159f82b3de5a2acab65570f090d23c0d3273b46 Mon Sep 17 00:00:00 2001
From: Mikhael Goikhman <migo@mellanox.com>
Date: Mon, 19 Nov 2018 19:11:12 +0200
Subject: [PATCH 54/58] net/mlx5e: Remove unused UDP GSO remaining counter

[ Upstream commit d13b224f431579fe2d712871d4265d7a22ca6c9c ]

Remove tx_udp_seg_rem counter from ethtool output, as it is no longer
being updated in the driver's data flow.

Fixes: 3f44899ef2ce ("net/mlx5e: Use PARTIAL_GSO for UDP segmentation")
Signed-off-by: Mikhael Goikhman <migo@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.c | 2 --
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.h | 2 --
 2 files changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index d57d51c4e658..7047cc293545 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -73,7 +73,6 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_recover) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_cqes) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_wake) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_udp_seg_rem) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_cqe_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_xmit) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_full) },
@@ -194,7 +193,6 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 			s->tx_nop               += sq_stats->nop;
 			s->tx_queue_stopped	+= sq_stats->stopped;
 			s->tx_queue_wake	+= sq_stats->wake;
-			s->tx_udp_seg_rem	+= sq_stats->udp_seg_rem;
 			s->tx_queue_dropped	+= sq_stats->dropped;
 			s->tx_cqe_err		+= sq_stats->cqe_err;
 			s->tx_recover		+= sq_stats->recover;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index c1064af9d54c..0ad7a165443a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -86,7 +86,6 @@ struct mlx5e_sw_stats {
 	u64 tx_recover;
 	u64 tx_cqes;
 	u64 tx_queue_wake;
-	u64 tx_udp_seg_rem;
 	u64 tx_cqe_err;
 	u64 tx_xdp_xmit;
 	u64 tx_xdp_full;
@@ -217,7 +216,6 @@ struct mlx5e_sq_stats {
 	u64 csum_partial_inner;
 	u64 added_vlan_packets;
 	u64 nop;
-	u64 udp_seg_rem;
 #ifdef CONFIG_MLX5_EN_TLS
 	u64 tls_ooo;
 	u64 tls_resync_bytes;
-- 
2.20.1


From fb929ff317626b5a0bc6b76ccc2d0ebe17b432fe Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Sun, 2 Dec 2018 15:45:53 +0200
Subject: [PATCH 55/58] net/mlx5e: RX, Fix wrong early return in receive queue
 poll

[ Upstream commit bfc698254ba97b3e3e4ebbfae0ffa1f7e2fa0717 ]

When the completion queue of the RQ is empty, do not immediately return.
If left-over decompressed CQEs (from the previous cycle) were processed,
need to go to the finalization part of the poll function.

Bug exists only when CQE compression is turned ON.

This solves the following issue:
mlx5_core 0000:82:00.1: mlx5_eq_int:544:(pid 0): CQ error on CQN 0xc08, syndrome 0x1
mlx5_core 0000:82:00.1 p4p2: mlx5e_cq_error_event: cqn=0x000c08 event=0x04

Fixes: 4b7dfc992514 ("net/mlx5e: Early-return on empty completion queues")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index d543a5cff049..8262f093fec4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1150,7 +1150,7 @@ void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 {
 	struct mlx5e_rq *rq = container_of(cq, struct mlx5e_rq, cq);
-	struct mlx5e_xdpsq *xdpsq;
+	struct mlx5e_xdpsq *xdpsq = &rq->xdpsq;
 	struct mlx5_cqe64 *cqe;
 	int work_done = 0;
 
@@ -1161,10 +1161,11 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 		work_done += mlx5e_decompress_cqes_cont(rq, cq, 0, budget);
 
 	cqe = mlx5_cqwq_get_cqe(&cq->wq);
-	if (!cqe)
+	if (!cqe) {
+		if (unlikely(work_done))
+			goto out;
 		return 0;
-
-	xdpsq = &rq->xdpsq;
+	}
 
 	do {
 		if (mlx5_get_cqe_format(cqe) == MLX5_COMPRESSED) {
@@ -1179,6 +1180,7 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 		rq->handle_rx_cqe(rq, cqe);
 	} while ((++work_done < budget) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
 
+out:
 	if (xdpsq->doorbell) {
 		mlx5e_xmit_xdp_doorbell(xdpsq);
 		xdpsq->doorbell = false;
-- 
2.20.1


From 00cee4493b4f585f203806df743ae8279e0d4e83 Mon Sep 17 00:00:00 2001
From: Marcin Wojtas <mw@semihalf.com>
Date: Tue, 11 Dec 2018 13:56:49 +0100
Subject: [PATCH 56/58] net: mvneta: fix operation for 64K PAGE_SIZE

[ Upstream commit e735fd55b94bb48363737db3b1d57627c1a16b47 ]

Recent changes in the mvneta driver reworked allocation
and handling of the ingress buffers to use entire pages.
Apart from that in SW BM scenario the HW must be informed
via PRXDQS about the biggest possible incoming buffer
that can be propagated by RX descriptors.

The BufferSize field was filled according to the MTU-dependent
pkt_size value. Later change to PAGE_SIZE broke RX operation
when usin 64K pages, as the field is simply too small.

This patch conditionally limits the value passed to the BufferSize
of the PRXDQS register, depending on the PAGE_SIZE used.
On the occasion remove now unused frag_size field of the mvneta_port
structure.

Fixes: 562e2f467e71 ("net: mvneta: Improve the buffer allocation method for SWBM")
Signed-off-by: Marcin Wojtas <mw@semihalf.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index b4ed7d394d07..a78a39244b79 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -406,7 +406,6 @@ struct mvneta_port {
 	struct mvneta_pcpu_stats __percpu	*stats;
 
 	int pkt_size;
-	unsigned int frag_size;
 	void __iomem *base;
 	struct mvneta_rx_queue *rxqs;
 	struct mvneta_tx_queue *txqs;
@@ -2905,7 +2904,9 @@ static void mvneta_rxq_hw_init(struct mvneta_port *pp,
 	if (!pp->bm_priv) {
 		/* Set Offset */
 		mvneta_rxq_offset_set(pp, rxq, 0);
-		mvneta_rxq_buf_size_set(pp, rxq, pp->frag_size);
+		mvneta_rxq_buf_size_set(pp, rxq, PAGE_SIZE < SZ_64K ?
+					PAGE_SIZE :
+					MVNETA_RX_BUF_SIZE(pp->pkt_size));
 		mvneta_rxq_bm_disable(pp, rxq);
 		mvneta_rxq_fill(pp, rxq, rxq->size);
 	} else {
@@ -3749,7 +3750,6 @@ static int mvneta_open(struct net_device *dev)
 	int ret;
 
 	pp->pkt_size = MVNETA_RX_PKT_SIZE(pp->dev->mtu);
-	pp->frag_size = PAGE_SIZE;
 
 	ret = mvneta_setup_rxqs(pp);
 	if (ret)
-- 
2.20.1


From 32af3d88e35436bdb611fa073196e6633396f493 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Mon, 17 Dec 2018 11:26:38 +0100
Subject: [PATCH 57/58] net: Use __kernel_clockid_t in uapi net_stamp.h
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit e2c4cf7f98a519eb4d95532bfa06bcaf3562fed5 ]

Herton reports the following error when building a userspace program that
includes net_stamp.h:

 In file included from foo.c:2:
 /usr/include/linux/net_tstamp.h:158:2: error: unknown type name
 ‘clockid_t’
   clockid_t clockid; /* reference clockid */
   ^~~~~~~~~

Fix it by using __kernel_clockid_t in place of clockid_t.

Fixes: 80b14dee2bea ("net: Add a new socket option for a future transmit time.")
Cc: Timothy Redaelli <tredaelli@redhat.com>
Reported-by: Herton R. Krzesinski <herton@redhat.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Tested-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/net_tstamp.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h
index 97ff3c17ec4d..e5b39721c6e4 100644
--- a/include/uapi/linux/net_tstamp.h
+++ b/include/uapi/linux/net_tstamp.h
@@ -155,8 +155,8 @@ enum txtime_flags {
 };
 
 struct sock_txtime {
-	clockid_t	clockid;	/* reference clockid */
-	__u32		flags;		/* as defined by enum txtime_flags */
+	__kernel_clockid_t	clockid;/* reference clockid */
+	__u32			flags;	/* as defined by enum txtime_flags */
 };
 
 #endif /* _NET_TIMESTAMPING_H */
-- 
2.20.1


From 20a552cbe7fb0df93e8170e710b8de8d07d1d0d3 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 30 Dec 2018 13:16:12 +0100
Subject: [PATCH 58/58] r8169: fix WoL device wakeup enable

[ Upstream commit 3bd8264511035dc97c902f03fa9f1d07f95f8f62 ]

In rtl8169_runtime_resume() we configure WoL but don't set the device
to wakeup-enabled. This prevents PME generation once the cable is
re-plugged. Fix this by moving the call to device_set_wakeup_enable()
to __rtl8169_set_wol().

Fixes: 433f9d0ddcc6 ("r8169: improve saved_wolopts handling")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 4930e0375c1d..9fc8a2bc0ff1 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -1528,6 +1528,8 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts)
 	}
 
 	RTL_W8(tp, Cfg9346, Cfg9346_Lock);
+
+	device_set_wakeup_enable(tp_to_dev(tp), wolopts);
 }
 
 static int rtl8169_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
@@ -1549,8 +1551,6 @@ static int rtl8169_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 
 	rtl_unlock_work(tp);
 
-	device_set_wakeup_enable(d, tp->saved_wolopts);
-
 	pm_runtime_put_noidle(d);
 
 	return 0;
-- 
2.20.1


[-- Attachment #3: net_420.mbox --]
[-- Type: Application/Octet-Stream, Size: 48817 bytes --]

From ebd4235693497b8effd3e14ee2da6ecbf152d48d Mon Sep 17 00:00:00 2001
From: Ivan Mironov <mironov.ivan@gmail.com>
Date: Mon, 24 Dec 2018 20:13:05 +0500
Subject: [PATCH 01/16] bnx2x: Fix NULL pointer dereference in
 bnx2x_del_all_vlans() on some hw

[ Upstream commit 38355a5f9a22bfa5bd5b1bb79805aca39fa53729 ]

This happened when I tried to boot normal Fedora 29 system with latest
available kernel (from fedora rawhide, plus some unrelated custom
patches):

	BUG: unable to handle kernel NULL pointer dereference at 0000000000000000
	PGD 0 P4D 0
	Oops: 0010 [#1] SMP PTI
	CPU: 6 PID: 1422 Comm: libvirtd Tainted: G          I       4.20.0-0.rc7.git3.hpsa2.1.fc29.x86_64 #1
	Hardware name: HP ProLiant BL460c G6, BIOS I24 05/21/2018
	RIP: 0010:          (null)
	Code: Bad RIP value.
	RSP: 0018:ffffa47ccdc9fbe0 EFLAGS: 00010246
	RAX: 0000000000000000 RBX: 00000000000003e8 RCX: ffffa47ccdc9fbf8
	RDX: ffffa47ccdc9fc00 RSI: ffff97d9ee7b01f8 RDI: ffff97d9f0150b80
	RBP: ffff97d9f0150b80 R08: 0000000000000000 R09: 0000000000000000
	R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000003
	R13: ffff97d9ef1e53e8 R14: 0000000000000009 R15: ffff97d9f0ac6730
	FS:  00007f4d224ef700(0000) GS:ffff97d9fa200000(0000) knlGS:0000000000000000
	CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
	CR2: ffffffffffffffd6 CR3: 00000011ece52006 CR4: 00000000000206e0
	Call Trace:
	 ? bnx2x_chip_cleanup+0x195/0x610 [bnx2x]
	 ? bnx2x_nic_unload+0x1e2/0x8f0 [bnx2x]
	 ? bnx2x_reload_if_running+0x24/0x40 [bnx2x]
	 ? bnx2x_set_features+0x79/0xa0 [bnx2x]
	 ? __netdev_update_features+0x244/0x9e0
	 ? netlink_broadcast_filtered+0x136/0x4b0
	 ? netdev_update_features+0x22/0x60
	 ? dev_disable_lro+0x1c/0xe0
	 ? devinet_sysctl_forward+0x1c6/0x211
	 ? proc_sys_call_handler+0xab/0x100
	 ? __vfs_write+0x36/0x1a0
	 ? rcu_read_lock_sched_held+0x79/0x80
	 ? rcu_sync_lockdep_assert+0x2e/0x60
	 ? __sb_start_write+0x14c/0x1b0
	 ? vfs_write+0x159/0x1c0
	 ? vfs_write+0xba/0x1c0
	 ? ksys_write+0x52/0xc0
	 ? do_syscall_64+0x60/0x1f0
	 ? entry_SYSCALL_64_after_hwframe+0x49/0xbe

After some investigation I figured out that recently added cleanup code
tries to call VLAN filtering de-initialization function which exist only
for newer hardware. Corresponding function pointer is not
set (== 0) for older hardware, namely these chips:

	#define CHIP_NUM_57710			0x164e
	#define CHIP_NUM_57711			0x164f
	#define CHIP_NUM_57711E			0x1650

And I have one of those in my test system:

	Broadcom Inc. and subsidiaries NetXtreme II BCM57711E 10-Gigabit PCIe [14e4:1650]

Function bnx2x_init_vlan_mac_fp_objs() from
drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h decides whether to
initialize relevant pointers in bnx2x_sp_objs.vlan_obj or not.

This regression was introduced after v4.20-rc7, and still exists in v4.20
release.

Fixes: 04f05230c5c13 ("bnx2x: Remove configured vlans as part of unload sequence.")
Signed-off-by: Ivan Mironov <mironov.ivan@gmail.com>
Signed-off-by: Ivan Mironov <mironov.ivan@gmail.com>
Acked-by: Sudarsana Kalluru <Sudarsana.Kalluru@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index b164f705709d..3b5b47e98c73 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -9360,10 +9360,16 @@ void bnx2x_chip_cleanup(struct bnx2x *bp, int unload_mode, bool keep_link)
 		BNX2X_ERR("Failed to schedule DEL commands for UC MACs list: %d\n",
 			  rc);
 
-	/* Remove all currently configured VLANs */
-	rc = bnx2x_del_all_vlans(bp);
-	if (rc < 0)
-		BNX2X_ERR("Failed to delete all VLANs\n");
+	/* The whole *vlan_obj structure may be not initialized if VLAN
+	 * filtering offload is not supported by hardware. Currently this is
+	 * true for all hardware covered by CHIP_IS_E1x().
+	 */
+	if (!CHIP_IS_E1x(bp)) {
+		/* Remove all currently configured VLANs */
+		rc = bnx2x_del_all_vlans(bp);
+		if (rc < 0)
+			BNX2X_ERR("Failed to delete all VLANs\n");
+	}
 
 	/* Disable LLH */
 	if (!CHIP_IS_E1(bp))
-- 
2.20.1


From 49e014901d25610c95ae2eff65a6f456f1cc9c20 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Sun, 30 Dec 2018 17:21:05 -0500
Subject: [PATCH 02/16] tap: call skb_probe_transport_header after setting
 skb->dev

[ Upstream commit 8c76e77f9069f10505c08e02646c3ee11ad79038 ]

The BPF flow dissector expects either skb->sk or skb->dev set on
all skbs. Delay flow dissection until after skb->dev is set.

This requires calling from within an rcu read-side critical section.
That is fine, see also the call from tun_xdp_one.

Fixes: d0e13a1488ad ("flow_dissector: lookup netns by skb->sk if skb->dev is NULL")
Reported-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tap.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index f03004f37eca..276f800ed57f 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -1177,8 +1177,6 @@ static int tap_get_user_xdp(struct tap_queue *q, struct xdp_buff *xdp)
 			goto err_kfree;
 	}
 
-	skb_probe_transport_header(skb, ETH_HLEN);
-
 	/* Move network header to the right position for VLAN tagged packets */
 	if ((skb->protocol == htons(ETH_P_8021Q) ||
 	     skb->protocol == htons(ETH_P_8021AD)) &&
@@ -1189,6 +1187,7 @@ static int tap_get_user_xdp(struct tap_queue *q, struct xdp_buff *xdp)
 	tap = rcu_dereference(q->tap);
 	if (tap) {
 		skb->dev = tap->dev;
+		skb_probe_transport_header(skb, ETH_HLEN);
 		dev_queue_xmit(skb);
 	} else {
 		kfree_skb(skb);
-- 
2.20.1


From e7d8b24f1abc359f8fa3fd4796f52a2bb8a08fae Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sat, 29 Dec 2018 13:56:36 -0800
Subject: [PATCH 03/16] ax25: fix a use-after-free in ax25_fillin_cb()

[ Upstream commit c433570458e49bccea5c551df628d058b3526289 ]

There are multiple issues here:

1. After freeing dev->ax25_ptr, we need to set it to NULL otherwise
   we may use a dangling pointer.

2. There is a race between ax25_setsockopt() and device notifier as
   reported by syzbot. Close it by holding RTNL lock.

3. We need to test if dev->ax25_ptr is NULL before using it.

Reported-and-tested-by: syzbot+ae6bb869cbed29b29040@syzkaller.appspotmail.com
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ax25/af_ax25.c  | 11 +++++++++--
 net/ax25/ax25_dev.c |  2 ++
 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index c603d33d5410..5d01edf8d819 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -653,15 +653,22 @@ static int ax25_setsockopt(struct socket *sock, int level, int optname,
 			break;
 		}
 
-		dev = dev_get_by_name(&init_net, devname);
+		rtnl_lock();
+		dev = __dev_get_by_name(&init_net, devname);
 		if (!dev) {
+			rtnl_unlock();
 			res = -ENODEV;
 			break;
 		}
 
 		ax25->ax25_dev = ax25_dev_ax25dev(dev);
+		if (!ax25->ax25_dev) {
+			rtnl_unlock();
+			res = -ENODEV;
+			break;
+		}
 		ax25_fillin_cb(ax25, ax25->ax25_dev);
-		dev_put(dev);
+		rtnl_unlock();
 		break;
 
 	default:
diff --git a/net/ax25/ax25_dev.c b/net/ax25/ax25_dev.c
index 9a3a301e1e2f..d92195cd7834 100644
--- a/net/ax25/ax25_dev.c
+++ b/net/ax25/ax25_dev.c
@@ -116,6 +116,7 @@ void ax25_dev_device_down(struct net_device *dev)
 	if ((s = ax25_dev_list) == ax25_dev) {
 		ax25_dev_list = s->next;
 		spin_unlock_bh(&ax25_dev_lock);
+		dev->ax25_ptr = NULL;
 		dev_put(dev);
 		kfree(ax25_dev);
 		return;
@@ -125,6 +126,7 @@ void ax25_dev_device_down(struct net_device *dev)
 		if (s->next == ax25_dev) {
 			s->next = ax25_dev->next;
 			spin_unlock_bh(&ax25_dev_lock);
+			dev->ax25_ptr = NULL;
 			dev_put(dev);
 			kfree(ax25_dev);
 			return;
-- 
2.20.1


From e01fef5292ad79268b7517d83bf06ecdc0b734e2 Mon Sep 17 00:00:00 2001
From: Tyrel Datwyler <tyreld@linux.vnet.ibm.com>
Date: Mon, 31 Dec 2018 15:43:01 -0600
Subject: [PATCH 04/16] ibmveth: fix DMA unmap error in ibmveth_xmit_start
 error path

[ Upstream commit 756af9c642329d54f048bac2a62f829b391f6944 ]

Commit 33a48ab105a7 ("ibmveth: Fix DMA unmap error") fixed an issue in the
normal code path of ibmveth_xmit_start() that was originally introduced by
Commit 6e8ab30ec677 ("ibmveth: Add scatter-gather support"). This original
fix missed the error path where dma_unmap_page is wrongly called on the
header portion in descs[0] which was mapped with dma_map_single. As a
result a failure to DMA map any of the frags results in a dmesg warning
when CONFIG_DMA_API_DEBUG is enabled.

------------[ cut here ]------------
DMA-API: ibmveth 30000002: device driver frees DMA memory with wrong function
  [device address=0x000000000a430000] [size=172 bytes] [mapped as page] [unmapped as single]
WARNING: CPU: 1 PID: 8426 at kernel/dma/debug.c:1085 check_unmap+0x4fc/0xe10
...
<snip>
...
DMA-API: Mapped at:
ibmveth_start_xmit+0x30c/0xb60
dev_hard_start_xmit+0x100/0x450
sch_direct_xmit+0x224/0x490
__qdisc_run+0x20c/0x980
__dev_queue_xmit+0x1bc/0xf20

This fixes the API misuse by unampping descs[0] with dma_unmap_single.

Fixes: 6e8ab30ec677 ("ibmveth: Add scatter-gather support")
Signed-off-by: Tyrel Datwyler <tyreld@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ibm/ibmveth.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index a4681780a55d..098d8764c0ea 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -1171,11 +1171,15 @@ static netdev_tx_t ibmveth_start_xmit(struct sk_buff *skb,
 
 map_failed_frags:
 	last = i+1;
-	for (i = 0; i < last; i++)
+	for (i = 1; i < last; i++)
 		dma_unmap_page(&adapter->vdev->dev, descs[i].fields.address,
 			       descs[i].fields.flags_len & IBMVETH_BUF_LEN_MASK,
 			       DMA_TO_DEVICE);
 
+	dma_unmap_single(&adapter->vdev->dev,
+			 descs[0].fields.address,
+			 descs[0].fields.flags_len & IBMVETH_BUF_LEN_MASK,
+			 DMA_TO_DEVICE);
 map_failed:
 	if (!firmware_has_feature(FW_FEATURE_CMO))
 		netdev_err(netdev, "tx: unable to map xmit buffer\n");
-- 
2.20.1


From d0e9a7ef4aa9b248c928919dbeb8789b948addc8 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Sun, 23 Dec 2018 12:52:18 -0500
Subject: [PATCH 05/16] ieee802154: lowpan_header_create check must check daddr

[ Upstream commit 40c3ff6d5e0809505a067dd423c110c5658c478c ]

Packet sockets may call dev_header_parse with NULL daddr. Make
lowpan_header_ops.create fail.

Fixes: 87a93e4eceb4 ("ieee802154: change needed headroom/tailroom")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Alexander Aring <aring@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ieee802154/6lowpan/tx.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ieee802154/6lowpan/tx.c b/net/ieee802154/6lowpan/tx.c
index ca53efa17be1..8bec827081cd 100644
--- a/net/ieee802154/6lowpan/tx.c
+++ b/net/ieee802154/6lowpan/tx.c
@@ -48,6 +48,9 @@ int lowpan_header_create(struct sk_buff *skb, struct net_device *ldev,
 	const struct ipv6hdr *hdr = ipv6_hdr(skb);
 	struct neighbour *n;
 
+	if (!daddr)
+		return -EINVAL;
+
 	/* TODO:
 	 * if this package isn't ipv6 one, where should it be routed?
 	 */
-- 
2.20.1


From 0df8f6c2d60437dc70128361729a6a80e3324b3f Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Sun, 30 Dec 2018 17:24:36 -0500
Subject: [PATCH 06/16] ip: validate header length on virtual device xmit

[ Upstream commit cb9f1b783850b14cbd7f87d061d784a666dfba1f ]

KMSAN detected read beyond end of buffer in vti and sit devices when
passing truncated packets with PF_PACKET. The issue affects additional
ip tunnel devices.

Extend commit 76c0ddd8c3a6 ("ip6_tunnel: be careful when accessing the
inner header") and commit ccfec9e5cb2d ("ip_tunnel: be careful when
accessing the inner header").

Move the check to a separate helper and call at the start of each
ndo_start_xmit function in net/ipv4 and net/ipv6.

Minor changes:
- convert dev_kfree_skb to kfree_skb on error path,
  as dev_kfree_skb calls consume_skb which is not for error paths.
- use pskb_network_may_pull even though that is pedantic here,
  as the same as pskb_may_pull for devices without llheaders.
- do not cache ipv6 hdrs if used only once
  (unsafe across pskb_may_pull, was more relevant to earlier patch)

Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_tunnels.h | 20 ++++++++++++++++++++
 net/ipv4/ip_gre.c        |  9 +++++++++
 net/ipv4/ip_tunnel.c     |  9 ---------
 net/ipv4/ip_vti.c        | 12 +++++++++---
 net/ipv6/ip6_gre.c       | 10 +++++++---
 net/ipv6/ip6_tunnel.c    | 10 +++-------
 net/ipv6/ip6_vti.c       |  8 ++++----
 net/ipv6/ip6mr.c         | 17 +++++++++++------
 net/ipv6/sit.c           |  3 +++
 9 files changed, 66 insertions(+), 32 deletions(-)

diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 5ce926701bd0..5f67efbb77e8 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -307,6 +307,26 @@ int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *op,
 int ip_tunnel_encap_setup(struct ip_tunnel *t,
 			  struct ip_tunnel_encap *ipencap);
 
+static inline bool pskb_inet_may_pull(struct sk_buff *skb)
+{
+	int nhlen;
+
+	switch (skb->protocol) {
+#if IS_ENABLED(CONFIG_IPV6)
+	case htons(ETH_P_IPV6):
+		nhlen = sizeof(struct ipv6hdr);
+		break;
+#endif
+	case htons(ETH_P_IP):
+		nhlen = sizeof(struct iphdr);
+		break;
+	default:
+		nhlen = 0;
+	}
+
+	return pskb_network_may_pull(skb, nhlen);
+}
+
 static inline int ip_encap_hlen(struct ip_tunnel_encap *e)
 {
 	const struct ip_tunnel_encap_ops *ops;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 38befe829caf..0fe9419bd12b 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -674,6 +674,9 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb,
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	const struct iphdr *tnl_params;
 
+	if (!pskb_inet_may_pull(skb))
+		goto free_skb;
+
 	if (tunnel->collect_md) {
 		gre_fb_xmit(skb, dev, skb->protocol);
 		return NETDEV_TX_OK;
@@ -717,6 +720,9 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb,
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	bool truncate = false;
 
+	if (!pskb_inet_may_pull(skb))
+		goto free_skb;
+
 	if (tunnel->collect_md) {
 		erspan_fb_xmit(skb, dev, skb->protocol);
 		return NETDEV_TX_OK;
@@ -760,6 +766,9 @@ static netdev_tx_t gre_tap_xmit(struct sk_buff *skb,
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 
+	if (!pskb_inet_may_pull(skb))
+		goto free_skb;
+
 	if (tunnel->collect_md) {
 		gre_fb_xmit(skb, dev, htons(ETH_P_TEB));
 		return NETDEV_TX_OK;
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 284a22154b4e..c4f5602308ed 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -627,7 +627,6 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		    const struct iphdr *tnl_params, u8 protocol)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
-	unsigned int inner_nhdr_len = 0;
 	const struct iphdr *inner_iph;
 	struct flowi4 fl4;
 	u8     tos, ttl;
@@ -637,14 +636,6 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	__be32 dst;
 	bool connected;
 
-	/* ensure we can access the inner net header, for several users below */
-	if (skb->protocol == htons(ETH_P_IP))
-		inner_nhdr_len = sizeof(struct iphdr);
-	else if (skb->protocol == htons(ETH_P_IPV6))
-		inner_nhdr_len = sizeof(struct ipv6hdr);
-	if (unlikely(!pskb_may_pull(skb, inner_nhdr_len)))
-		goto tx_error;
-
 	inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
 	connected = (tunnel->parms.iph.daddr != 0);
 
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index de31b302d69c..d7b43e700023 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -241,6 +241,9 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	struct flowi fl;
 
+	if (!pskb_inet_may_pull(skb))
+		goto tx_err;
+
 	memset(&fl, 0, sizeof(fl));
 
 	switch (skb->protocol) {
@@ -253,15 +256,18 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 		memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
 		break;
 	default:
-		dev->stats.tx_errors++;
-		dev_kfree_skb(skb);
-		return NETDEV_TX_OK;
+		goto tx_err;
 	}
 
 	/* override mark with tunnel output key */
 	fl.flowi_mark = be32_to_cpu(tunnel->parms.o_key);
 
 	return vti_xmit(skb, dev, &fl);
+
+tx_err:
+	dev->stats.tx_errors++;
+	kfree_skb(skb);
+	return NETDEV_TX_OK;
 }
 
 static int vti4_err(struct sk_buff *skb, u32 info)
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 515adbdba1d2..0f7d434c1eed 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -879,6 +879,9 @@ static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb,
 	struct net_device_stats *stats = &t->dev->stats;
 	int ret;
 
+	if (!pskb_inet_may_pull(skb))
+		goto tx_err;
+
 	if (!ip6_tnl_xmit_ctl(t, &t->parms.laddr, &t->parms.raddr))
 		goto tx_err;
 
@@ -921,6 +924,9 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 	int nhoff;
 	int thoff;
 
+	if (!pskb_inet_may_pull(skb))
+		goto tx_err;
+
 	if (!ip6_tnl_xmit_ctl(t, &t->parms.laddr, &t->parms.raddr))
 		goto tx_err;
 
@@ -993,8 +999,6 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 			goto tx_err;
 		}
 	} else {
-		struct ipv6hdr *ipv6h = ipv6_hdr(skb);
-
 		switch (skb->protocol) {
 		case htons(ETH_P_IP):
 			memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
@@ -1002,7 +1006,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 						 &dsfield, &encap_limit);
 			break;
 		case htons(ETH_P_IPV6):
-			if (ipv6_addr_equal(&t->parms.raddr, &ipv6h->saddr))
+			if (ipv6_addr_equal(&t->parms.raddr, &ipv6_hdr(skb)->saddr))
 				goto tx_err;
 			if (prepare_ip6gre_xmit_ipv6(skb, dev, &fl6,
 						     &dsfield, &encap_limit))
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 99179b9c8384..0c6403cf8b52 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1243,10 +1243,6 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	u8 tproto;
 	int err;
 
-	/* ensure we can access the full inner ip header */
-	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
-		return -1;
-
 	iph = ip_hdr(skb);
 	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
 
@@ -1321,9 +1317,6 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	u8 tproto;
 	int err;
 
-	if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
-		return -1;
-
 	ipv6h = ipv6_hdr(skb);
 	tproto = READ_ONCE(t->parms.proto);
 	if ((tproto != IPPROTO_IPV6 && tproto != 0) ||
@@ -1405,6 +1398,9 @@ ip6_tnl_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct net_device_stats *stats = &t->dev->stats;
 	int ret;
 
+	if (!pskb_inet_may_pull(skb))
+		goto tx_err;
+
 	switch (skb->protocol) {
 	case htons(ETH_P_IP):
 		ret = ip4ip6_tnl_xmit(skb, dev);
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 706fe42e4928..8b6eefff2f7e 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -522,18 +522,18 @@ vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ip6_tnl *t = netdev_priv(dev);
 	struct net_device_stats *stats = &t->dev->stats;
-	struct ipv6hdr *ipv6h;
 	struct flowi fl;
 	int ret;
 
+	if (!pskb_inet_may_pull(skb))
+		goto tx_err;
+
 	memset(&fl, 0, sizeof(fl));
 
 	switch (skb->protocol) {
 	case htons(ETH_P_IPV6):
-		ipv6h = ipv6_hdr(skb);
-
 		if ((t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) ||
-		    vti6_addr_conflict(t, ipv6h))
+		    vti6_addr_conflict(t, ipv6_hdr(skb)))
 			goto tx_err;
 
 		xfrm_decode_session(skb, &fl, AF_INET6);
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 377a2ee5d9ad..eb3220812b56 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -51,6 +51,7 @@
 #include <linux/export.h>
 #include <net/ip6_checksum.h>
 #include <linux/netconf.h>
+#include <net/ip_tunnels.h>
 
 #include <linux/nospec.h>
 
@@ -599,13 +600,12 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb,
 		.flowi6_iif	= skb->skb_iif ? : LOOPBACK_IFINDEX,
 		.flowi6_mark	= skb->mark,
 	};
-	int err;
 
-	err = ip6mr_fib_lookup(net, &fl6, &mrt);
-	if (err < 0) {
-		kfree_skb(skb);
-		return err;
-	}
+	if (!pskb_inet_may_pull(skb))
+		goto tx_err;
+
+	if (ip6mr_fib_lookup(net, &fl6, &mrt) < 0)
+		goto tx_err;
 
 	read_lock(&mrt_lock);
 	dev->stats.tx_bytes += skb->len;
@@ -614,6 +614,11 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb,
 	read_unlock(&mrt_lock);
 	kfree_skb(skb);
 	return NETDEV_TX_OK;
+
+tx_err:
+	dev->stats.tx_errors++;
+	kfree_skb(skb);
+	return NETDEV_TX_OK;
 }
 
 static int reg_vif_get_iflink(const struct net_device *dev)
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 51c9f75f34b9..1e03305c0549 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1021,6 +1021,9 @@ static netdev_tx_t sit_tunnel_xmit__(struct sk_buff *skb,
 static netdev_tx_t sit_tunnel_xmit(struct sk_buff *skb,
 				   struct net_device *dev)
 {
+	if (!pskb_inet_may_pull(skb))
+		goto tx_err;
+
 	switch (skb->protocol) {
 	case htons(ETH_P_IP):
 		sit_tunnel_xmit__(skb, dev, IPPROTO_IPIP);
-- 
2.20.1


From d4c007691613fa12ab209ca1d925f6bc4a0d0f93 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Fri, 21 Dec 2018 14:49:01 -0600
Subject: [PATCH 07/16] net: core: Fix Spectre v1 vulnerability

[ Upstream commit 50d5258634aee2e62832aa086d2fb0de00e72b91 ]

flen is indirectly controlled by user-space, hence leading to
a potential exploitation of the Spectre variant 1 vulnerability.

This issue was detected with the help of Smatch:

net/core/filter.c:1101 bpf_check_classic() warn: potential spectre issue 'filter' [w]

Fix this by sanitizing flen before using it to index filter at line 1101:

	switch (filter[flen - 1].code) {

and through pc at line 1040:

	const struct sock_filter *ftest = &filter[pc];

Notice that given that speculation windows are large, the policy is
to kill the speculation on the first load and not worry if it can be
completed with a dependent load/store [1].

[1] https://marc.info/?l=linux-kernel&m=152449131114778&w=2

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/filter.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/core/filter.c b/net/core/filter.c
index 8d2c629501e2..0c74c2f9776a 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -73,6 +73,7 @@
 #include <linux/seg6_local.h>
 #include <net/seg6.h>
 #include <net/seg6_local.h>
+#include <linux/nospec.h>
 
 /**
  *	sk_filter_trim_cap - run a packet through a socket filter
@@ -1038,6 +1039,7 @@ static int bpf_check_classic(const struct sock_filter *filter,
 	bool anc_found;
 	int pc;
 
+	flen = array_index_nospec(flen, BPF_MAXINSNS + 1);
 	/* Check the filter code now */
 	for (pc = 0; pc < flen; pc++) {
 		const struct sock_filter *ftest = &filter[pc];
-- 
2.20.1


From 01a2e772add929f3eb34f8a9f33c22131a6afec6 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 2 Jan 2019 04:24:20 -0800
Subject: [PATCH 08/16] net/hamradio/6pack: use mod_timer() to rearm timers

[ Upstream commit 202700e30740c6568b5a6943662f3829566dd533 ]

Using del_timer() + add_timer() is generally unsafe on SMP,
as noticed by syzbot. Use mod_timer() instead.

kernel BUG at kernel/time/timer.c:1136!
invalid opcode: 0000 [#1] PREEMPT SMP KASAN
CPU: 1 PID: 1026 Comm: kworker/u4:4 Not tainted 4.20.0+ #2
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Workqueue: events_unbound flush_to_ldisc
RIP: 0010:add_timer kernel/time/timer.c:1136 [inline]
RIP: 0010:add_timer+0xa81/0x1470 kernel/time/timer.c:1134
Code: 4d 89 7d 40 48 c7 85 70 fe ff ff 00 00 00 00 c7 85 7c fe ff ff ff ff ff ff 48 89 85 90 fe ff ff e9 e6 f7 ff ff e8 cf 42 12 00 <0f> 0b e8 c8 42 12 00 0f 0b e8 c1 42 12 00 4c 89 bd 60 fe ff ff e9
RSP: 0018:ffff8880a7fdf5a8 EFLAGS: 00010293
RAX: ffff8880a7846340 RBX: dffffc0000000000 RCX: 0000000000000000
RDX: 0000000000000000 RSI: ffffffff816f3ee1 RDI: ffff88808a514ff8
RBP: ffff8880a7fdf760 R08: 0000000000000007 R09: ffff8880a7846c58
R10: ffff8880a7846340 R11: 0000000000000000 R12: ffff88808a514ff8
R13: ffff88808a514ff8 R14: ffff88808a514dc0 R15: 0000000000000030
FS:  0000000000000000(0000) GS:ffff8880ae700000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000000000061c500 CR3: 00000000994d9000 CR4: 00000000001406e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 decode_prio_command drivers/net/hamradio/6pack.c:903 [inline]
 sixpack_decode drivers/net/hamradio/6pack.c:971 [inline]
 sixpack_receive_buf drivers/net/hamradio/6pack.c:457 [inline]
 sixpack_receive_buf+0xf9c/0x1470 drivers/net/hamradio/6pack.c:434
 tty_ldisc_receive_buf+0x164/0x1c0 drivers/tty/tty_buffer.c:465
 tty_port_default_receive_buf+0x114/0x190 drivers/tty/tty_port.c:38
 receive_buf drivers/tty/tty_buffer.c:481 [inline]
 flush_to_ldisc+0x3b2/0x590 drivers/tty/tty_buffer.c:533
 process_one_work+0xd0c/0x1ce0 kernel/workqueue.c:2153
 worker_thread+0x143/0x14a0 kernel/workqueue.c:2296
 kthread+0x357/0x430 kernel/kthread.c:246
 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:352

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Andreas Koensgen <ajk@comnets.uni-bremen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hamradio/6pack.c | 16 ++++------------
 1 file changed, 4 insertions(+), 12 deletions(-)

diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c
index 17e6dcd2eb42..c99dd3f1e6a8 100644
--- a/drivers/net/hamradio/6pack.c
+++ b/drivers/net/hamradio/6pack.c
@@ -523,10 +523,7 @@ static void resync_tnc(struct timer_list *t)
 
 
 	/* Start resync timer again -- the TNC might be still absent */
-
-	del_timer(&sp->resync_t);
-	sp->resync_t.expires	= jiffies + SIXP_RESYNC_TIMEOUT;
-	add_timer(&sp->resync_t);
+	mod_timer(&sp->resync_t, jiffies + SIXP_RESYNC_TIMEOUT);
 }
 
 static inline int tnc_init(struct sixpack *sp)
@@ -537,9 +534,7 @@ static inline int tnc_init(struct sixpack *sp)
 
 	sp->tty->ops->write(sp->tty, &inbyte, 1);
 
-	del_timer(&sp->resync_t);
-	sp->resync_t.expires = jiffies + SIXP_RESYNC_TIMEOUT;
-	add_timer(&sp->resync_t);
+	mod_timer(&sp->resync_t, jiffies + SIXP_RESYNC_TIMEOUT);
 
 	return 0;
 }
@@ -897,11 +892,8 @@ static void decode_prio_command(struct sixpack *sp, unsigned char cmd)
         /* if the state byte has been received, the TNC is present,
            so the resync timer can be reset. */
 
-	if (sp->tnc_state == TNC_IN_SYNC) {
-		del_timer(&sp->resync_t);
-		sp->resync_t.expires	= jiffies + SIXP_INIT_RESYNC_TIMEOUT;
-		add_timer(&sp->resync_t);
-	}
+	if (sp->tnc_state == TNC_IN_SYNC)
+		mod_timer(&sp->resync_t, jiffies + SIXP_INIT_RESYNC_TIMEOUT);
 
 	sp->status1 = cmd & SIXP_PRIO_DATA_MASK;
 }
-- 
2.20.1


From 30240379cf1b9554a8037fd6a4f88ffa735ec8d1 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 2 Jan 2019 09:20:27 -0800
Subject: [PATCH 09/16] isdn: fix kernel-infoleak in capi_unlocked_ioctl

[ Upstream commit d63967e475ae10f286dbd35e189cb241e0b1f284 ]

Since capi_ioctl() copies 64 bytes after calling
capi20_get_manufacturer() we need to ensure to not leak
information to user.

BUG: KMSAN: kernel-infoleak in _copy_to_user+0x16b/0x1f0 lib/usercopy.c:32
CPU: 0 PID: 11245 Comm: syz-executor633 Not tainted 4.20.0-rc7+ #2
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x173/0x1d0 lib/dump_stack.c:113
 kmsan_report+0x12e/0x2a0 mm/kmsan/kmsan.c:613
 kmsan_internal_check_memory+0x9d4/0xb00 mm/kmsan/kmsan.c:704
 kmsan_copy_to_user+0xab/0xc0 mm/kmsan/kmsan_hooks.c:601
 _copy_to_user+0x16b/0x1f0 lib/usercopy.c:32
 capi_ioctl include/linux/uaccess.h:177 [inline]
 capi_unlocked_ioctl+0x1a0b/0x1bf0 drivers/isdn/capi/capi.c:939
 do_vfs_ioctl+0xebd/0x2bf0 fs/ioctl.c:46
 ksys_ioctl fs/ioctl.c:713 [inline]
 __do_sys_ioctl fs/ioctl.c:720 [inline]
 __se_sys_ioctl+0x1da/0x270 fs/ioctl.c:718
 __x64_sys_ioctl+0x4a/0x70 fs/ioctl.c:718
 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291
 entry_SYSCALL_64_after_hwframe+0x63/0xe7
RIP: 0033:0x440019
Code: 18 89 d0 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 fb 13 fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007ffdd4659fb8 EFLAGS: 00000213 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 0000000000440019
RDX: 0000000020000080 RSI: 00000000c0044306 RDI: 0000000000000003
RBP: 00000000006ca018 R08: 0000000000000000 R09: 00000000004002c8
R10: 0000000000000000 R11: 0000000000000213 R12: 00000000004018a0
R13: 0000000000401930 R14: 0000000000000000 R15: 0000000000000000

Local variable description: ----data.i@capi_unlocked_ioctl
Variable was created at:
 capi_ioctl drivers/isdn/capi/capi.c:747 [inline]
 capi_unlocked_ioctl+0x82/0x1bf0 drivers/isdn/capi/capi.c:939
 do_vfs_ioctl+0xebd/0x2bf0 fs/ioctl.c:46

Bytes 12-63 of 64 are uninitialized
Memory access of size 64 starts at ffff88807ac5fce8
Data copied to user address 0000000020000080

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Karsten Keil <isdn@linux-pingi.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/capi/kcapi.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/isdn/capi/kcapi.c b/drivers/isdn/capi/kcapi.c
index 0ff517d3c98f..a4ceb61c5b60 100644
--- a/drivers/isdn/capi/kcapi.c
+++ b/drivers/isdn/capi/kcapi.c
@@ -852,7 +852,7 @@ u16 capi20_get_manufacturer(u32 contr, u8 *buf)
 	u16 ret;
 
 	if (contr == 0) {
-		strlcpy(buf, capi_manufakturer, CAPI_MANUFACTURER_LEN);
+		strncpy(buf, capi_manufakturer, CAPI_MANUFACTURER_LEN);
 		return CAPI_NOERROR;
 	}
 
@@ -860,7 +860,7 @@ u16 capi20_get_manufacturer(u32 contr, u8 *buf)
 
 	ctr = get_capi_ctr_by_nr(contr);
 	if (ctr && ctr->state == CAPI_CTR_RUNNING) {
-		strlcpy(buf, ctr->manu, CAPI_MANUFACTURER_LEN);
+		strncpy(buf, ctr->manu, CAPI_MANUFACTURER_LEN);
 		ret = CAPI_NOERROR;
 	} else
 		ret = CAPI_REGNOTINSTALLED;
-- 
2.20.1


From 830747f1d45e6be87c24f0f6384d21ee2996b3dc Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sat, 29 Dec 2018 13:56:38 -0800
Subject: [PATCH 10/16] netrom: fix locking in nr_find_socket()

[ Upstream commit 7314f5480f3e37e570104dc5e0f28823ef849e72 ]

nr_find_socket(), nr_find_peer() and nr_find_listener() lock the
sock after finding it in the global list. However, the call path
requires BH disabled for the sock lock consistently.

Actually the locking is unnecessary at this point, we can just hold
the sock refcnt to make sure it is not gone after we unlock the global
list, and lock it later only when needed.

Reported-and-tested-by: syzbot+f621cda8b7e598908efa@syzkaller.appspotmail.com
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netrom/af_netrom.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 03f37c4e64fe..1d3144d19903 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -153,7 +153,7 @@ static struct sock *nr_find_listener(ax25_address *addr)
 	sk_for_each(s, &nr_list)
 		if (!ax25cmp(&nr_sk(s)->source_addr, addr) &&
 		    s->sk_state == TCP_LISTEN) {
-			bh_lock_sock(s);
+			sock_hold(s);
 			goto found;
 		}
 	s = NULL;
@@ -174,7 +174,7 @@ static struct sock *nr_find_socket(unsigned char index, unsigned char id)
 		struct nr_sock *nr = nr_sk(s);
 
 		if (nr->my_index == index && nr->my_id == id) {
-			bh_lock_sock(s);
+			sock_hold(s);
 			goto found;
 		}
 	}
@@ -198,7 +198,7 @@ static struct sock *nr_find_peer(unsigned char index, unsigned char id,
 
 		if (nr->your_index == index && nr->your_id == id &&
 		    !ax25cmp(&nr->dest_addr, dest)) {
-			bh_lock_sock(s);
+			sock_hold(s);
 			goto found;
 		}
 	}
@@ -224,7 +224,7 @@ static unsigned short nr_find_next_circuit(void)
 		if (i != 0 && j != 0) {
 			if ((sk=nr_find_socket(i, j)) == NULL)
 				break;
-			bh_unlock_sock(sk);
+			sock_put(sk);
 		}
 
 		id++;
@@ -920,6 +920,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	if (sk != NULL) {
+		bh_lock_sock(sk);
 		skb_reset_transport_header(skb);
 
 		if (frametype == NR_CONNACK && skb->len == 22)
@@ -929,6 +930,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev)
 
 		ret = nr_process_rx_frame(sk, skb);
 		bh_unlock_sock(sk);
+		sock_put(sk);
 		return ret;
 	}
 
@@ -960,10 +962,12 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev)
 	    (make = nr_make_new(sk)) == NULL) {
 		nr_transmit_refusal(skb, 0);
 		if (sk)
-			bh_unlock_sock(sk);
+			sock_put(sk);
 		return 0;
 	}
 
+	bh_lock_sock(sk);
+
 	window = skb->data[20];
 
 	skb->sk             = make;
@@ -1016,6 +1020,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev)
 		sk->sk_data_ready(sk);
 
 	bh_unlock_sock(sk);
+	sock_put(sk);
 
 	nr_insert_socket(make);
 
-- 
2.20.1


From baf7ea2774557cb67905b67d0ec366ed8c1597e8 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sat, 29 Dec 2018 13:56:37 -0800
Subject: [PATCH 11/16] net/wan: fix a double free in x25_asy_open_tty()

[ Upstream commit d5c7c745f254c6cb98b3b3f15fe789b8bd770c72 ]

When x25_asy_open() fails, it already cleans up by itself,
so its caller doesn't need to free the memory again.

It seems we still have to call x25_asy_free() to clear the SLF_INUSE
bit, so just set these pointers to NULL after kfree().

Reported-and-tested-by: syzbot+5e5e969e525129229052@syzkaller.appspotmail.com
Fixes: 3b780bed3138 ("x25_asy: Free x25_asy on x25_asy_open() failure.")
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wan/x25_asy.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wan/x25_asy.c b/drivers/net/wan/x25_asy.c
index 1098263ab862..46c3d983b7b7 100644
--- a/drivers/net/wan/x25_asy.c
+++ b/drivers/net/wan/x25_asy.c
@@ -485,8 +485,10 @@ static int x25_asy_open(struct net_device *dev)
 
 	/* Cleanup */
 	kfree(sl->xbuff);
+	sl->xbuff = NULL;
 noxbuff:
 	kfree(sl->rbuff);
+	sl->rbuff = NULL;
 norbuff:
 	return -ENOMEM;
 }
-- 
2.20.1


From ddf4169126933b0a0d80e55b87515e661962ab04 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Sat, 22 Dec 2018 16:53:45 -0500
Subject: [PATCH 12/16] packet: validate address length if non-zero

[ Upstream commit 6b8d95f1795c42161dc0984b6863e95d6acf24ed ]

Validate packet socket address length if a length is given. Zero
length is equivalent to not setting an address.

Fixes: 99137b7888f4 ("packet: validate address length")
Reported-by: Ido Schimmel <idosch@idosch.org>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 5dda263b4a0a..eedacdebcd4c 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2625,7 +2625,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 						sll_addr)))
 			goto out;
 		proto	= saddr->sll_protocol;
-		addr	= saddr->sll_addr;
+		addr	= saddr->sll_halen ? saddr->sll_addr : NULL;
 		dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex);
 		if (addr && dev && saddr->sll_halen < dev->addr_len)
 			goto out;
@@ -2825,7 +2825,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		if (msg->msg_namelen < (saddr->sll_halen + offsetof(struct sockaddr_ll, sll_addr)))
 			goto out;
 		proto	= saddr->sll_protocol;
-		addr	= saddr->sll_addr;
+		addr	= saddr->sll_halen ? saddr->sll_addr : NULL;
 		dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex);
 		if (addr && dev && saddr->sll_halen < dev->addr_len)
 			goto out;
-- 
2.20.1


From 6a61a40ec3a09663efe075c5c4d98cd8de92315d Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Fri, 21 Dec 2018 15:41:17 -0600
Subject: [PATCH 13/16] phonet: af_phonet: Fix Spectre v1 vulnerability

[ Upstream commit d686026b1e6ed4ea27d630d8f54f9a694db088b2 ]

protocol is indirectly controlled by user-space, hence leading to
a potential exploitation of the Spectre variant 1 vulnerability.

This issue was detected with the help of Smatch:

net/phonet/af_phonet.c:48 phonet_proto_get() warn: potential spectre issue 'proto_tab' [w] (local cap)

Fix this by sanitizing protocol before using it to index proto_tab.

Notice that given that speculation windows are large, the policy is
to kill the speculation on the first load and not worry if it can be
completed with a dependent load/store [1].

[1] https://marc.info/?l=linux-kernel&m=152449131114778&w=2

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/phonet/af_phonet.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c
index 3b0ef691f5b1..d4b2abd78858 100644
--- a/net/phonet/af_phonet.c
+++ b/net/phonet/af_phonet.c
@@ -34,6 +34,8 @@
 #include <net/phonet/phonet.h>
 #include <net/phonet/pn_dev.h>
 
+#include <linux/nospec.h>
+
 /* Transport protocol registration */
 static const struct phonet_protocol *proto_tab[PHONET_NPROTO] __read_mostly;
 
@@ -43,6 +45,7 @@ static const struct phonet_protocol *phonet_proto_get(unsigned int protocol)
 
 	if (protocol >= PHONET_NPROTO)
 		return NULL;
+	protocol = array_index_nospec(protocol, PHONET_NPROTO);
 
 	rcu_read_lock();
 	pp = rcu_dereference(proto_tab[protocol]);
-- 
2.20.1


From a251095a789ed572064c0af43d77a3a0c5f88831 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sun, 30 Dec 2018 12:43:42 -0800
Subject: [PATCH 14/16] ptr_ring: wrap back ->producer in
 __ptr_ring_swap_queue()

[ Upstream commit aff6db454599d62191aabc208930e891748e4322 ]

__ptr_ring_swap_queue() tries to move pointers from the old
ring to the new one, but it forgets to check if ->producer
is beyond the new size at the end of the operation. This leads
to an out-of-bound access in __ptr_ring_produce() as reported
by syzbot.

Reported-by: syzbot+8993c0fa96d57c399735@syzkaller.appspotmail.com
Fixes: 5d49de532002 ("ptr_ring: resize support")
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: Jason Wang <jasowang@redhat.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ptr_ring.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h
index 6894976b54e3..186cd8e970c7 100644
--- a/include/linux/ptr_ring.h
+++ b/include/linux/ptr_ring.h
@@ -573,6 +573,8 @@ static inline void **__ptr_ring_swap_queue(struct ptr_ring *r, void **queue,
 		else if (destroy)
 			destroy(ptr);
 
+	if (producer >= size)
+		producer = 0;
 	__ptr_ring_set_size(r, size);
 	r->producer = producer;
 	r->consumer_head = 0;
-- 
2.20.1


From 92013061638c90b7365694948e48c2976091d0e3 Mon Sep 17 00:00:00 2001
From: Deepa Dinamani <deepa.kernel@gmail.com>
Date: Thu, 27 Dec 2018 18:55:09 -0800
Subject: [PATCH 15/16] sock: Make sock->sk_stamp thread-safe

[ Upstream commit 3a0ed3e9619738067214871e9cb826fa23b2ddb9 ]

Al Viro mentioned (Message-ID
<20170626041334.GZ10672@ZenIV.linux.org.uk>)
that there is probably a race condition
lurking in accesses of sk_stamp on 32-bit machines.

sock->sk_stamp is of type ktime_t which is always an s64.
On a 32 bit architecture, we might run into situations of
unsafe access as the access to the field becomes non atomic.

Use seqlocks for synchronization.
This allows us to avoid using spinlocks for readers as
readers do not need mutual exclusion.

Another approach to solve this is to require sk_lock for all
modifications of the timestamps. The current approach allows
for timestamps to have their own lock: sk_stamp_lock.
This allows for the patch to not compete with already
existing critical sections, and side effects are limited
to the paths in the patch.

The addition of the new field maintains the data locality
optimizations from
commit 9115e8cd2a0c ("net: reorganize struct sock for better data
locality")

Note that all the instances of the sk_stamp accesses
are either through the ioctl or the syscall recvmsg.

Signed-off-by: Deepa Dinamani <deepa.kernel@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h   | 38 +++++++++++++++++++++++++++++++++++---
 net/compat.c         | 15 +++++++++------
 net/core/sock.c      | 15 ++++++++++-----
 net/sunrpc/svcsock.c |  2 +-
 4 files changed, 55 insertions(+), 15 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index 0e3a09380655..13f11e905a00 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -298,6 +298,7 @@ struct sock_common {
   *	@sk_filter: socket filtering instructions
   *	@sk_timer: sock cleanup timer
   *	@sk_stamp: time stamp of last packet received
+  *	@sk_stamp_seq: lock for accessing sk_stamp on 32 bit architectures only
   *	@sk_tsflags: SO_TIMESTAMPING socket options
   *	@sk_tskey: counter to disambiguate concurrent tstamp requests
   *	@sk_zckey: counter to order MSG_ZEROCOPY notifications
@@ -474,6 +475,9 @@ struct sock {
 	const struct cred	*sk_peer_cred;
 	long			sk_rcvtimeo;
 	ktime_t			sk_stamp;
+#if BITS_PER_LONG==32
+	seqlock_t		sk_stamp_seq;
+#endif
 	u16			sk_tsflags;
 	u8			sk_shutdown;
 	u32			sk_tskey;
@@ -2287,6 +2291,34 @@ static inline void sk_drops_add(struct sock *sk, const struct sk_buff *skb)
 	atomic_add(segs, &sk->sk_drops);
 }
 
+static inline ktime_t sock_read_timestamp(struct sock *sk)
+{
+#if BITS_PER_LONG==32
+	unsigned int seq;
+	ktime_t kt;
+
+	do {
+		seq = read_seqbegin(&sk->sk_stamp_seq);
+		kt = sk->sk_stamp;
+	} while (read_seqretry(&sk->sk_stamp_seq, seq));
+
+	return kt;
+#else
+	return sk->sk_stamp;
+#endif
+}
+
+static inline void sock_write_timestamp(struct sock *sk, ktime_t kt)
+{
+#if BITS_PER_LONG==32
+	write_seqlock(&sk->sk_stamp_seq);
+	sk->sk_stamp = kt;
+	write_sequnlock(&sk->sk_stamp_seq);
+#else
+	sk->sk_stamp = kt;
+#endif
+}
+
 void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
 			   struct sk_buff *skb);
 void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk,
@@ -2311,7 +2343,7 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
 	     (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE)))
 		__sock_recv_timestamp(msg, sk, skb);
 	else
-		sk->sk_stamp = kt;
+		sock_write_timestamp(sk, kt);
 
 	if (sock_flag(sk, SOCK_WIFI_STATUS) && skb->wifi_acked_valid)
 		__sock_recv_wifi_status(msg, sk, skb);
@@ -2332,9 +2364,9 @@ static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
 	if (sk->sk_flags & FLAGS_TS_OR_DROPS || sk->sk_tsflags & TSFLAGS_ANY)
 		__sock_recv_ts_and_drops(msg, sk, skb);
 	else if (unlikely(sock_flag(sk, SOCK_TIMESTAMP)))
-		sk->sk_stamp = skb->tstamp;
+		sock_write_timestamp(sk, skb->tstamp);
 	else if (unlikely(sk->sk_stamp == SK_DEFAULT_STAMP))
-		sk->sk_stamp = 0;
+		sock_write_timestamp(sk, 0);
 }
 
 void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags);
diff --git a/net/compat.c b/net/compat.c
index 47a614b370cd..d1f3a8a0b3ef 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -467,12 +467,14 @@ int compat_sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp)
 	ctv = (struct compat_timeval __user *) userstamp;
 	err = -ENOENT;
 	sock_enable_timestamp(sk, SOCK_TIMESTAMP);
-	tv = ktime_to_timeval(sk->sk_stamp);
+	tv = ktime_to_timeval(sock_read_timestamp(sk));
+
 	if (tv.tv_sec == -1)
 		return err;
 	if (tv.tv_sec == 0) {
-		sk->sk_stamp = ktime_get_real();
-		tv = ktime_to_timeval(sk->sk_stamp);
+		ktime_t kt = ktime_get_real();
+		sock_write_timestamp(sk, kt);
+		tv = ktime_to_timeval(kt);
 	}
 	err = 0;
 	if (put_user(tv.tv_sec, &ctv->tv_sec) ||
@@ -494,12 +496,13 @@ int compat_sock_get_timestampns(struct sock *sk, struct timespec __user *usersta
 	ctv = (struct compat_timespec __user *) userstamp;
 	err = -ENOENT;
 	sock_enable_timestamp(sk, SOCK_TIMESTAMP);
-	ts = ktime_to_timespec(sk->sk_stamp);
+	ts = ktime_to_timespec(sock_read_timestamp(sk));
 	if (ts.tv_sec == -1)
 		return err;
 	if (ts.tv_sec == 0) {
-		sk->sk_stamp = ktime_get_real();
-		ts = ktime_to_timespec(sk->sk_stamp);
+		ktime_t kt = ktime_get_real();
+		sock_write_timestamp(sk, kt);
+		ts = ktime_to_timespec(kt);
 	}
 	err = 0;
 	if (put_user(ts.tv_sec, &ctv->tv_sec) ||
diff --git a/net/core/sock.c b/net/core/sock.c
index 080a880a1761..98659fb6e9fb 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2743,6 +2743,9 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 	sk->sk_sndtimeo		=	MAX_SCHEDULE_TIMEOUT;
 
 	sk->sk_stamp = SK_DEFAULT_STAMP;
+#if BITS_PER_LONG==32
+	seqlock_init(&sk->sk_stamp_seq);
+#endif
 	atomic_set(&sk->sk_zckey, 0);
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
@@ -2842,12 +2845,13 @@ int sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp)
 	struct timeval tv;
 
 	sock_enable_timestamp(sk, SOCK_TIMESTAMP);
-	tv = ktime_to_timeval(sk->sk_stamp);
+	tv = ktime_to_timeval(sock_read_timestamp(sk));
 	if (tv.tv_sec == -1)
 		return -ENOENT;
 	if (tv.tv_sec == 0) {
-		sk->sk_stamp = ktime_get_real();
-		tv = ktime_to_timeval(sk->sk_stamp);
+		ktime_t kt = ktime_get_real();
+		sock_write_timestamp(sk, kt);
+		tv = ktime_to_timeval(kt);
 	}
 	return copy_to_user(userstamp, &tv, sizeof(tv)) ? -EFAULT : 0;
 }
@@ -2858,11 +2862,12 @@ int sock_get_timestampns(struct sock *sk, struct timespec __user *userstamp)
 	struct timespec ts;
 
 	sock_enable_timestamp(sk, SOCK_TIMESTAMP);
-	ts = ktime_to_timespec(sk->sk_stamp);
+	ts = ktime_to_timespec(sock_read_timestamp(sk));
 	if (ts.tv_sec == -1)
 		return -ENOENT;
 	if (ts.tv_sec == 0) {
-		sk->sk_stamp = ktime_get_real();
+		ktime_t kt = ktime_get_real();
+		sock_write_timestamp(sk, kt);
 		ts = ktime_to_timespec(sk->sk_stamp);
 	}
 	return copy_to_user(userstamp, &ts, sizeof(ts)) ? -EFAULT : 0;
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 986f3ed7d1a2..b7e67310ec37 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -549,7 +549,7 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp)
 		/* Don't enable netstamp, sunrpc doesn't
 		   need that much accuracy */
 	}
-	svsk->sk_sk->sk_stamp = skb->tstamp;
+	sock_write_timestamp(svsk->sk_sk, skb->tstamp);
 	set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); /* there may be more data... */
 
 	len  = skb->len;
-- 
2.20.1


From ba9057b43ad459560070e322aceec370a169280a Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sun, 23 Dec 2018 21:45:56 -0800
Subject: [PATCH 16/16] tipc: fix a double free in tipc_enable_bearer()

[ Upstream commit dc4501ff287547dea7ca10f1c580c741291a8760 ]

bearer_disable() already calls kfree_rcu() to free struct tipc_bearer,
we don't need to call kfree() again.

Fixes: cb30a63384bc ("tipc: refactor function tipc_enable_bearer()")
Reported-by: syzbot+b981acf1fb240c0c128b@syzkaller.appspotmail.com
Cc: Ying Xue <ying.xue@windriver.com>
Cc: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/bearer.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index e65c3a8551e4..040153ffc357 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -317,7 +317,6 @@ static int tipc_enable_bearer(struct net *net, const char *name,
 	res = tipc_disc_create(net, b, &b->bcast_addr, &skb);
 	if (res) {
 		bearer_disable(net, b);
-		kfree(b);
 		errstr = "failed to create discoverer";
 		goto rejected;
 	}
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Fri, Jan 04, 2019 at 10:17:20AM -0800, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.19 and v4.20
> -stable, respectively.

All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 107 bytes --]


Please queue up the following networking bug fixes for v4.19
and v4.20 -stable, respectively.

Thank you.

[-- Attachment #2: net_419.mbox --]
[-- Type: Application/Octet-Stream, Size: 26049 bytes --]

From 709874234baee5a88ff0a06207ca07990063887e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 8 Jan 2019 04:06:14 -0800
Subject: [PATCH 01/11] ipv6: fix kernel-infoleak in ipv6_local_error()

[ Upstream commit 7d033c9f6a7fd3821af75620a0257db87c2b552a ]

This patch makes sure the flow label in the IPv6 header
forged in ipv6_local_error() is initialized.

BUG: KMSAN: kernel-infoleak in _copy_to_user+0x16b/0x1f0 lib/usercopy.c:32
CPU: 1 PID: 24675 Comm: syz-executor1 Not tainted 4.20.0-rc7+ #4
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x173/0x1d0 lib/dump_stack.c:113
 kmsan_report+0x12e/0x2a0 mm/kmsan/kmsan.c:613
 kmsan_internal_check_memory+0x455/0xb00 mm/kmsan/kmsan.c:675
 kmsan_copy_to_user+0xab/0xc0 mm/kmsan/kmsan_hooks.c:601
 _copy_to_user+0x16b/0x1f0 lib/usercopy.c:32
 copy_to_user include/linux/uaccess.h:177 [inline]
 move_addr_to_user+0x2e9/0x4f0 net/socket.c:227
 ___sys_recvmsg+0x5d7/0x1140 net/socket.c:2284
 __sys_recvmsg net/socket.c:2327 [inline]
 __do_sys_recvmsg net/socket.c:2337 [inline]
 __se_sys_recvmsg+0x2fa/0x450 net/socket.c:2334
 __x64_sys_recvmsg+0x4a/0x70 net/socket.c:2334
 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291
 entry_SYSCALL_64_after_hwframe+0x63/0xe7
RIP: 0033:0x457ec9
Code: 6d b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 3b b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f8750c06c78 EFLAGS: 00000246 ORIG_RAX: 000000000000002f
RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000457ec9
RDX: 0000000000002000 RSI: 0000000020000400 RDI: 0000000000000005
RBP: 000000000073bf00 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00007f8750c076d4
R13: 00000000004c4a60 R14: 00000000004d8140 R15: 00000000ffffffff

Uninit was stored to memory at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:204 [inline]
 kmsan_save_stack mm/kmsan/kmsan.c:219 [inline]
 kmsan_internal_chain_origin+0x134/0x230 mm/kmsan/kmsan.c:439
 __msan_chain_origin+0x70/0xe0 mm/kmsan/kmsan_instr.c:200
 ipv6_recv_error+0x1e3f/0x1eb0 net/ipv6/datagram.c:475
 udpv6_recvmsg+0x398/0x2ab0 net/ipv6/udp.c:335
 inet_recvmsg+0x4fb/0x600 net/ipv4/af_inet.c:830
 sock_recvmsg_nosec net/socket.c:794 [inline]
 sock_recvmsg+0x1d1/0x230 net/socket.c:801
 ___sys_recvmsg+0x4d5/0x1140 net/socket.c:2278
 __sys_recvmsg net/socket.c:2327 [inline]
 __do_sys_recvmsg net/socket.c:2337 [inline]
 __se_sys_recvmsg+0x2fa/0x450 net/socket.c:2334
 __x64_sys_recvmsg+0x4a/0x70 net/socket.c:2334
 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291
 entry_SYSCALL_64_after_hwframe+0x63/0xe7

Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:204 [inline]
 kmsan_internal_poison_shadow+0x92/0x150 mm/kmsan/kmsan.c:158
 kmsan_kmalloc+0xa6/0x130 mm/kmsan/kmsan_hooks.c:176
 kmsan_slab_alloc+0xe/0x10 mm/kmsan/kmsan_hooks.c:185
 slab_post_alloc_hook mm/slab.h:446 [inline]
 slab_alloc_node mm/slub.c:2759 [inline]
 __kmalloc_node_track_caller+0xe18/0x1030 mm/slub.c:4383
 __kmalloc_reserve net/core/skbuff.c:137 [inline]
 __alloc_skb+0x309/0xa20 net/core/skbuff.c:205
 alloc_skb include/linux/skbuff.h:998 [inline]
 ipv6_local_error+0x1a7/0x9e0 net/ipv6/datagram.c:334
 __ip6_append_data+0x129f/0x4fd0 net/ipv6/ip6_output.c:1311
 ip6_make_skb+0x6cc/0xcf0 net/ipv6/ip6_output.c:1775
 udpv6_sendmsg+0x3f8e/0x45d0 net/ipv6/udp.c:1384
 inet_sendmsg+0x54a/0x720 net/ipv4/af_inet.c:798
 sock_sendmsg_nosec net/socket.c:621 [inline]
 sock_sendmsg net/socket.c:631 [inline]
 __sys_sendto+0x8c4/0xac0 net/socket.c:1788
 __do_sys_sendto net/socket.c:1800 [inline]
 __se_sys_sendto+0x107/0x130 net/socket.c:1796
 __x64_sys_sendto+0x6e/0x90 net/socket.c:1796
 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291
 entry_SYSCALL_64_after_hwframe+0x63/0xe7

Bytes 4-7 of 28 are uninitialized
Memory access of size 28 starts at ffff8881937bfce0
Data copied to user address 0000000020000000

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/datagram.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 1ede7a16a0be..7b090578f044 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -341,6 +341,7 @@ void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info)
 	skb_reset_network_header(skb);
 	iph = ipv6_hdr(skb);
 	iph->daddr = fl6->daddr;
+	ip6_flow_hdr(iph, 0, 0);
 
 	serr = SKB_EXT_ERR(skb);
 	serr->ee.ee_errno = err;
-- 
2.20.1


From 69dd68d262e4193f2bf936c83a8ece6a32862062 Mon Sep 17 00:00:00 2001
From: JianJhen Chen <kchen@synology.com>
Date: Sun, 6 Jan 2019 11:28:13 +0800
Subject: [PATCH 02/11] net: bridge: fix a bug on using a neighbour cache entry
 without checking its state

[ Upstream commit 4c84edc11b76590859b1e45dd676074c59602dc4 ]

When handling DNAT'ed packets on a bridge device, the neighbour cache entry
from lookup was used without checking its state. It means that a cache entry
in the NUD_STALE state will be used directly instead of entering the NUD_DELAY
state to confirm the reachability of the neighbor.

This problem becomes worse after commit 2724680bceee ("neigh: Keep neighbour
cache entries if number of them is small enough."), since all neighbour cache
entries in the NUD_STALE state will be kept in the neighbour table as long as
the number of cache entries does not exceed the value specified in gc_thresh1.

This commit validates the state of a neighbour cache entry before using
the entry.

Signed-off-by: JianJhen Chen <kchen@synology.com>
Reviewed-by: JinLin Chen <jlchen@synology.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_netfilter_hooks.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 37278dc280eb..e07a7e62c705 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -278,7 +278,7 @@ int br_nf_pre_routing_finish_bridge(struct net *net, struct sock *sk, struct sk_
 		struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 		int ret;
 
-		if (neigh->hh.hh_len) {
+		if ((neigh->nud_state & NUD_CONNECTED) && neigh->hh.hh_len) {
 			neigh_hh_bridge(&neigh->hh, skb);
 			skb->dev = nf_bridge->physindev;
 			ret = br_handle_frame_finish(net, sk, skb);
-- 
2.20.1


From f45f49f6b883fd8c2c9e05bc7ea5186c5010b01f Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@mellanox.com>
Date: Tue, 8 Jan 2019 23:27:06 +0000
Subject: [PATCH 03/11] packet: Do not leak dev refcounts on error exit

[ Upstream commit d972f3dce8d161e2142da0ab1ef25df00e2f21a9 ]

'dev' is non NULL when the addr_len check triggers so it must goto a label
that does the dev_put otherwise dev will have a leaked refcount.

This bug causes the ib_ipoib module to become unloadable when using
systemd-network as it triggers this check on InfiniBand links.

Fixes: 99137b7888f4 ("packet: validate address length")
Reported-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 0541cfc93440..b6ea0fadb34f 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2628,7 +2628,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 		addr	= saddr->sll_halen ? saddr->sll_addr : NULL;
 		dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex);
 		if (addr && dev && saddr->sll_halen < dev->addr_len)
-			goto out;
+			goto out_put;
 	}
 
 	err = -ENXIO;
@@ -2828,7 +2828,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		addr	= saddr->sll_halen ? saddr->sll_addr : NULL;
 		dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex);
 		if (addr && dev && saddr->sll_halen < dev->addr_len)
-			goto out;
+			goto out_unlock;
 	}
 
 	err = -ENXIO;
-- 
2.20.1


From 62601d794d6f1d52c32b4ea8d5550c7e2752fd8c Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Tue, 8 Jan 2019 18:14:28 -0800
Subject: [PATCH 04/11] tcp: change txhash on SYN-data timeout

[ Upstream commit c5715b8fabfca0ef85903f8bad2189940ed41cc8 ]

Previously upon SYN timeouts the sender recomputes the txhash to
try a different path. However this does not apply on the initial
timeout of SYN-data (active Fast Open). Therefore an active IPv6
Fast Open connection may incur one second RTO penalty to take on
a new path after the second SYN retransmission uses a new flow label.

This patch removes this undesirable behavior so Fast Open changes
the flow label just like the regular connections. This also helps
avoid falsely disabling Fast Open on the sender which triggers
after two consecutive SYN timeouts on Fast Open.

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_timer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 57eae8d70ba1..b1b5a648def6 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -224,7 +224,7 @@ static int tcp_write_timeout(struct sock *sk)
 	if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
 		if (icsk->icsk_retransmits) {
 			dst_negative_advice(sk);
-		} else if (!tp->syn_data && !tp->syn_fastopen) {
+		} else {
 			sk_rethink_txhash(sk);
 		}
 		retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries;
-- 
2.20.1


From acaa2c44887765a25f000a615c62ddee854ec94d Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Mon, 7 Jan 2019 13:38:38 -0800
Subject: [PATCH 05/11] tun: publish tfile after it's fully initialized

[ Upstream commit 0b7959b6257322f7693b08a459c505d4938646f2 ]

BUG: unable to handle kernel NULL pointer dereference at 00000000000000d1
Call Trace:
 ? napi_gro_frags+0xa7/0x2c0
 tun_get_user+0xb50/0xf20
 tun_chr_write_iter+0x53/0x70
 new_sync_write+0xff/0x160
 vfs_write+0x191/0x1e0
 __x64_sys_write+0x5e/0xd0
 do_syscall_64+0x47/0xf0
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

I think there is a subtle race between sending a packet via tap and
attaching it:

CPU0:                    CPU1:
tun_chr_ioctl(TUNSETIFF)
  tun_set_iff
    tun_attach
      rcu_assign_pointer(tfile->tun, tun);
                         tun_fops->write_iter()
                           tun_chr_write_iter
                             tun_napi_alloc_frags
                               napi_get_frags
                                 napi->skb = napi_alloc_skb
      tun_napi_init
        netif_napi_add
          napi->skb = NULL
                              napi->skb is NULL here
                              napi_gro_frags
                                napi_frags_skb
				  skb = napi->skb
				  skb_reset_mac_header(skb)
				  panic()

Move rcu_assign_pointer(tfile->tun) and rcu_assign_pointer(tun->tfiles) to
be the last thing we do in tun_attach(); this should guarantee that when we
call tun_get() we always get an initialized object.

v2 changes:
* remove extra napi_mutex locks/unlocks for napi operations

Reported-by: syzbot <syzkaller@googlegroups.com>
Fixes: 90e33d459407 ("tun: enable napi_gro_frags() for TUN/TAP driver")

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 8c1abcba4cbd..33978b0cdac8 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -859,10 +859,6 @@ static int tun_attach(struct tun_struct *tun, struct file *file,
 		err = 0;
 	}
 
-	rcu_assign_pointer(tfile->tun, tun);
-	rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile);
-	tun->numqueues++;
-
 	if (tfile->detached) {
 		tun_enable_queue(tfile);
 	} else {
@@ -876,6 +872,13 @@ static int tun_attach(struct tun_struct *tun, struct file *file,
 	 * refcnt.
 	 */
 
+	/* Publish tfile->tun and tun->tfiles only after we've fully
+	 * initialized tfile; otherwise we risk using half-initialized
+	 * object.
+	 */
+	rcu_assign_pointer(tfile->tun, tun);
+	rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile);
+	tun->numqueues++;
 out:
 	return err;
 }
-- 
2.20.1


From 288e0ca9aa2954e5f5a46abbd4e6c2de6505b761 Mon Sep 17 00:00:00 2001
From: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Date: Mon, 7 Jan 2019 14:00:09 -0500
Subject: [PATCH 06/11] lan743x: Remove phy_read from link status change
 function

[ Upstream commit a0071840d2040ea1b27e5a008182b09b88defc15 ]

It has been noticed that some phys do not have the registers
required by the previous implementation.

To fix this, instead of using phy_read, the required information
is extracted from the phy_device structure.

fixes: 23f0703c125b ("lan743x: Add main source files for new lan743x driver")
Signed-off-by: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/lan743x_main.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index 1393252c6e3c..42f5bfa33694 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -962,13 +962,10 @@ static void lan743x_phy_link_status_change(struct net_device *netdev)
 
 		memset(&ksettings, 0, sizeof(ksettings));
 		phy_ethtool_get_link_ksettings(netdev, &ksettings);
-		local_advertisement = phy_read(phydev, MII_ADVERTISE);
-		if (local_advertisement < 0)
-			return;
-
-		remote_advertisement = phy_read(phydev, MII_LPA);
-		if (remote_advertisement < 0)
-			return;
+		local_advertisement =
+			ethtool_adv_to_mii_adv_t(phydev->advertising);
+		remote_advertisement =
+			ethtool_adv_to_mii_adv_t(phydev->lp_advertising);
 
 		lan743x_phy_update_flowcontrol(adapter,
 					       ksettings.base.duplex,
-- 
2.20.1


From 624828d1b80abb7bc831618e06c4169b1be9e9ff Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sat, 5 Jan 2019 23:45:26 -0800
Subject: [PATCH 07/11] smc: move unhash as early as possible in smc_release()

[ Upstream commit 26d92e951fe0a44ee4aec157cabb65a818cc8151 ]

In smc_release() we release smc->clcsock before unhash the smc
sock, but a parallel smc_diag_dump() may be still reading
smc->clcsock, therefore this could cause a use-after-free as
reported by syzbot.

Reported-and-tested-by: syzbot+fbd1e5476e4c94c7b34e@syzkaller.appspotmail.com
Fixes: 51f1de79ad8e ("net/smc: replace sock_put worker by socket refcounting")
Cc: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Reported-by: syzbot+0bf2e01269f1274b4b03@syzkaller.appspotmail.com
Reported-by: syzbot+e3132895630f957306bc@syzkaller.appspotmail.com
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/af_smc.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 2b8f95290627..e6e506b2db99 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -144,6 +144,9 @@ static int smc_release(struct socket *sock)
 		sock_set_flag(sk, SOCK_DEAD);
 		sk->sk_shutdown |= SHUTDOWN_MASK;
 	}
+
+	sk->sk_prot->unhash(sk);
+
 	if (smc->clcsock) {
 		if (smc->use_fallback && sk->sk_state == SMC_LISTEN) {
 			/* wake up clcsock accept */
@@ -168,7 +171,6 @@ static int smc_release(struct socket *sock)
 		smc_conn_free(&smc->conn);
 	release_sock(sk);
 
-	sk->sk_prot->unhash(sk);
 	sock_put(sk); /* final sock_put */
 out:
 	return rc;
-- 
2.20.1


From a106fedbec1c18d75a760dec41494e974d7273ed Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 6 Jan 2019 20:44:00 +0100
Subject: [PATCH 08/11] r8169: don't try to read counters if chip is in a PCI
 power-save state

[ Upstream commit 10262b0b53666cbc506989b17a3ead1e9c3b43b4 ]

Avoid log spam caused by trying to read counters from the chip whilst
it is in a PCI power-save state.

Reference: https://bugzilla.kernel.org/show_bug.cgi?id=107421

Fixes: 1ef7286e7f36 ("r8169: Dereference MMIO address immediately before use")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 9fc8a2bc0ff1..b4bca27b460f 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -1730,11 +1730,13 @@ static bool rtl8169_reset_counters(struct rtl8169_private *tp)
 
 static bool rtl8169_update_counters(struct rtl8169_private *tp)
 {
+	u8 val = RTL_R8(tp, ChipCmd);
+
 	/*
 	 * Some chips are unable to dump tally counters when the receiver
-	 * is disabled.
+	 * is disabled. If 0xff chip may be in a PCI power-save state.
 	 */
-	if ((RTL_R8(tp, ChipCmd) & CmdRxEnb) == 0)
+	if (!(val & CmdRxEnb) || val == 0xff)
 		return true;
 
 	return rtl8169_do_counters(tp, CounterDump);
-- 
2.20.1


From f2276111694100725647177dd97c446fc1db3911 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Tue, 8 Jan 2019 12:32:42 -0500
Subject: [PATCH 09/11] bonding: update nest level on unlink

[ Upstream commit 001e465f09a18857443489a57e74314a3368c805 ]

A network device stack with multiple layers of bonding devices can
trigger a false positive lockdep warning. Adding lockdep nest levels
fixes this. Update the level on both enslave and unlink, to avoid the
following series of events ..

    ip netns add test
    ip netns exec test bash
    ip link set dev lo addr 00:11:22:33:44:55
    ip link set dev lo down

    ip link add dev bond1 type bond
    ip link add dev bond2 type bond

    ip link set dev lo master bond1
    ip link set dev bond1 master bond2

    ip link set dev bond1 nomaster
    ip link set dev bond2 master bond1

.. from still generating a splat:

    [  193.652127] ======================================================
    [  193.658231] WARNING: possible circular locking dependency detected
    [  193.664350] 4.20.0 #8 Not tainted
    [  193.668310] ------------------------------------------------------
    [  193.674417] ip/15577 is trying to acquire lock:
    [  193.678897] 00000000a40e3b69 (&(&bond->stats_lock)->rlock#3/3){+.+.}, at: bond_get_stats+0x58/0x290
    [  193.687851]
    	       but task is already holding lock:
    [  193.693625] 00000000807b9d9f (&(&bond->stats_lock)->rlock#2/2){+.+.}, at: bond_get_stats+0x58/0x290

    [..]

    [  193.851092]        lock_acquire+0xa7/0x190
    [  193.855138]        _raw_spin_lock_nested+0x2d/0x40
    [  193.859878]        bond_get_stats+0x58/0x290
    [  193.864093]        dev_get_stats+0x5a/0xc0
    [  193.868140]        bond_get_stats+0x105/0x290
    [  193.872444]        dev_get_stats+0x5a/0xc0
    [  193.876493]        rtnl_fill_stats+0x40/0x130
    [  193.880797]        rtnl_fill_ifinfo+0x6c5/0xdc0
    [  193.885271]        rtmsg_ifinfo_build_skb+0x86/0xe0
    [  193.890091]        rtnetlink_event+0x5b/0xa0
    [  193.894320]        raw_notifier_call_chain+0x43/0x60
    [  193.899225]        netdev_change_features+0x50/0xa0
    [  193.904044]        bond_compute_features.isra.46+0x1ab/0x270
    [  193.909640]        bond_enslave+0x141d/0x15b0
    [  193.913946]        do_set_master+0x89/0xa0
    [  193.918016]        do_setlink+0x37c/0xda0
    [  193.921980]        __rtnl_newlink+0x499/0x890
    [  193.926281]        rtnl_newlink+0x48/0x70
    [  193.930238]        rtnetlink_rcv_msg+0x171/0x4b0
    [  193.934801]        netlink_rcv_skb+0xd1/0x110
    [  193.939103]        rtnetlink_rcv+0x15/0x20
    [  193.943151]        netlink_unicast+0x3b5/0x520
    [  193.947544]        netlink_sendmsg+0x2fd/0x3f0
    [  193.951942]        sock_sendmsg+0x38/0x50
    [  193.955899]        ___sys_sendmsg+0x2ba/0x2d0
    [  193.960205]        __x64_sys_sendmsg+0xad/0x100
    [  193.964687]        do_syscall_64+0x5a/0x460
    [  193.968823]        entry_SYSCALL_64_after_hwframe+0x49/0xbe

Fixes: 7e2556e40026 ("bonding: avoid lockdep confusion in bond_get_stats()")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 3c597569cfae..a6fcc5c96070 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1947,6 +1947,9 @@ static int __bond_release_one(struct net_device *bond_dev,
 	if (!bond_has_slaves(bond)) {
 		bond_set_carrier(bond);
 		eth_hw_addr_random(bond_dev);
+		bond->nest_level = SINGLE_DEPTH_NESTING;
+	} else {
+		bond->nest_level = dev_get_nest_level(bond_dev) + 1;
 	}
 
 	unblock_netpoll_tx();
-- 
2.20.1


From 484e28235ff3e2b9e3320c19fe83b2a67827c044 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Mon, 7 Jan 2019 16:47:33 -0500
Subject: [PATCH 10/11] ip: on queued skb use skb_header_pointer instead of
 pskb_may_pull

[ Upstream commit 4a06fa67c4da20148803525151845276cdb995c1 ]

Commit 2efd4fca703a ("ip: in cmsg IP(V6)_ORIGDSTADDR call
pskb_may_pull") avoided a read beyond the end of the skb linear
segment by calling pskb_may_pull.

That function can trigger a BUG_ON in pskb_expand_head if the skb is
shared, which it is when when peeking. It can also return ENOMEM.

Avoid both by switching to safer skb_header_pointer.

Fixes: 2efd4fca703a ("ip: in cmsg IP(V6)_ORIGDSTADDR call pskb_may_pull")
Reported-by: syzbot <syzkaller@googlegroups.com>
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_sockglue.c | 12 +++++-------
 net/ipv6/datagram.c    | 10 ++++------
 2 files changed, 9 insertions(+), 13 deletions(-)

diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 26c36cccabdc..b7a26120d552 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -148,19 +148,17 @@ static void ip_cmsg_recv_security(struct msghdr *msg, struct sk_buff *skb)
 
 static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
 {
+	__be16 _ports[2], *ports;
 	struct sockaddr_in sin;
-	__be16 *ports;
-	int end;
-
-	end = skb_transport_offset(skb) + 4;
-	if (end > 0 && !pskb_may_pull(skb, end))
-		return;
 
 	/* All current transport protocols have the port numbers in the
 	 * first four bytes of the transport header and this function is
 	 * written with this assumption in mind.
 	 */
-	ports = (__be16 *)skb_transport_header(skb);
+	ports = skb_header_pointer(skb, skb_transport_offset(skb),
+				   sizeof(_ports), &_ports);
+	if (!ports)
+		return;
 
 	sin.sin_family = AF_INET;
 	sin.sin_addr.s_addr = ip_hdr(skb)->daddr;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 7b090578f044..cb24850d2c7f 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -701,17 +701,15 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg,
 	}
 	if (np->rxopt.bits.rxorigdstaddr) {
 		struct sockaddr_in6 sin6;
-		__be16 *ports;
-		int end;
+		__be16 _ports[2], *ports;
 
-		end = skb_transport_offset(skb) + 4;
-		if (end <= 0 || pskb_may_pull(skb, end)) {
+		ports = skb_header_pointer(skb, skb_transport_offset(skb),
+					   sizeof(_ports), &_ports);
+		if (ports) {
 			/* All current transport protocols have the port numbers in the
 			 * first four bytes of the transport header and this function is
 			 * written with this assumption in mind.
 			 */
-			ports = (__be16 *)skb_transport_header(skb);
-
 			sin6.sin6_family = AF_INET6;
 			sin6.sin6_addr = ipv6_hdr(skb)->daddr;
 			sin6.sin6_port = ports[1];
-- 
2.20.1


From d14ff6d0958612e816046b524c6021f20dd74238 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 7 Jan 2019 21:49:09 +0100
Subject: [PATCH 11/11] r8169: load Realtek PHY driver module before r8169

[ Upstream commit 11287b693d03830010356339e4ceddf47dee34fa ]

This soft dependency works around an issue where sometimes the genphy
driver is used instead of the dedicated PHY driver. The root cause of
the issue isn't clear yet. People reported the unloading/re-loading
module r8169 helps, and also configuring this soft dependency in
the modprobe config files. Important just seems to be that the
realtek module is loaded before r8169.

Once this has been applied preliminary fix 38af4b903210 ("net: phy:
add workaround for issue where PHY driver doesn't bind to the device")
will be removed.

Fixes: f1e911d5d0df ("r8169: add basic phylib support")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index b4bca27b460f..07f3080eca18 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -717,6 +717,7 @@ module_param(use_dac, int, 0);
 MODULE_PARM_DESC(use_dac, "Enable PCI DAC. Unsafe on 32 bit PCI slot.");
 module_param_named(debug, debug.msg_enable, int, 0);
 MODULE_PARM_DESC(debug, "Debug verbosity level (0=none, ..., 16=all)");
+MODULE_SOFTDEP("pre: realtek");
 MODULE_LICENSE("GPL");
 MODULE_FIRMWARE(FIRMWARE_8168D_1);
 MODULE_FIRMWARE(FIRMWARE_8168D_2);
-- 
2.20.1


[-- Attachment #3: net_420.mbox --]
[-- Type: Application/Octet-Stream, Size: 35487 bytes --]

From 8a9fd1b9aa87aa2356a0e7ba3b838475b9d66a94 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 8 Jan 2019 04:06:14 -0800
Subject: [PATCH 01/15] ipv6: fix kernel-infoleak in ipv6_local_error()

[ Upstream commit 7d033c9f6a7fd3821af75620a0257db87c2b552a ]

This patch makes sure the flow label in the IPv6 header
forged in ipv6_local_error() is initialized.

BUG: KMSAN: kernel-infoleak in _copy_to_user+0x16b/0x1f0 lib/usercopy.c:32
CPU: 1 PID: 24675 Comm: syz-executor1 Not tainted 4.20.0-rc7+ #4
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x173/0x1d0 lib/dump_stack.c:113
 kmsan_report+0x12e/0x2a0 mm/kmsan/kmsan.c:613
 kmsan_internal_check_memory+0x455/0xb00 mm/kmsan/kmsan.c:675
 kmsan_copy_to_user+0xab/0xc0 mm/kmsan/kmsan_hooks.c:601
 _copy_to_user+0x16b/0x1f0 lib/usercopy.c:32
 copy_to_user include/linux/uaccess.h:177 [inline]
 move_addr_to_user+0x2e9/0x4f0 net/socket.c:227
 ___sys_recvmsg+0x5d7/0x1140 net/socket.c:2284
 __sys_recvmsg net/socket.c:2327 [inline]
 __do_sys_recvmsg net/socket.c:2337 [inline]
 __se_sys_recvmsg+0x2fa/0x450 net/socket.c:2334
 __x64_sys_recvmsg+0x4a/0x70 net/socket.c:2334
 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291
 entry_SYSCALL_64_after_hwframe+0x63/0xe7
RIP: 0033:0x457ec9
Code: 6d b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 3b b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f8750c06c78 EFLAGS: 00000246 ORIG_RAX: 000000000000002f
RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000457ec9
RDX: 0000000000002000 RSI: 0000000020000400 RDI: 0000000000000005
RBP: 000000000073bf00 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00007f8750c076d4
R13: 00000000004c4a60 R14: 00000000004d8140 R15: 00000000ffffffff

Uninit was stored to memory at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:204 [inline]
 kmsan_save_stack mm/kmsan/kmsan.c:219 [inline]
 kmsan_internal_chain_origin+0x134/0x230 mm/kmsan/kmsan.c:439
 __msan_chain_origin+0x70/0xe0 mm/kmsan/kmsan_instr.c:200
 ipv6_recv_error+0x1e3f/0x1eb0 net/ipv6/datagram.c:475
 udpv6_recvmsg+0x398/0x2ab0 net/ipv6/udp.c:335
 inet_recvmsg+0x4fb/0x600 net/ipv4/af_inet.c:830
 sock_recvmsg_nosec net/socket.c:794 [inline]
 sock_recvmsg+0x1d1/0x230 net/socket.c:801
 ___sys_recvmsg+0x4d5/0x1140 net/socket.c:2278
 __sys_recvmsg net/socket.c:2327 [inline]
 __do_sys_recvmsg net/socket.c:2337 [inline]
 __se_sys_recvmsg+0x2fa/0x450 net/socket.c:2334
 __x64_sys_recvmsg+0x4a/0x70 net/socket.c:2334
 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291
 entry_SYSCALL_64_after_hwframe+0x63/0xe7

Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:204 [inline]
 kmsan_internal_poison_shadow+0x92/0x150 mm/kmsan/kmsan.c:158
 kmsan_kmalloc+0xa6/0x130 mm/kmsan/kmsan_hooks.c:176
 kmsan_slab_alloc+0xe/0x10 mm/kmsan/kmsan_hooks.c:185
 slab_post_alloc_hook mm/slab.h:446 [inline]
 slab_alloc_node mm/slub.c:2759 [inline]
 __kmalloc_node_track_caller+0xe18/0x1030 mm/slub.c:4383
 __kmalloc_reserve net/core/skbuff.c:137 [inline]
 __alloc_skb+0x309/0xa20 net/core/skbuff.c:205
 alloc_skb include/linux/skbuff.h:998 [inline]
 ipv6_local_error+0x1a7/0x9e0 net/ipv6/datagram.c:334
 __ip6_append_data+0x129f/0x4fd0 net/ipv6/ip6_output.c:1311
 ip6_make_skb+0x6cc/0xcf0 net/ipv6/ip6_output.c:1775
 udpv6_sendmsg+0x3f8e/0x45d0 net/ipv6/udp.c:1384
 inet_sendmsg+0x54a/0x720 net/ipv4/af_inet.c:798
 sock_sendmsg_nosec net/socket.c:621 [inline]
 sock_sendmsg net/socket.c:631 [inline]
 __sys_sendto+0x8c4/0xac0 net/socket.c:1788
 __do_sys_sendto net/socket.c:1800 [inline]
 __se_sys_sendto+0x107/0x130 net/socket.c:1796
 __x64_sys_sendto+0x6e/0x90 net/socket.c:1796
 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291
 entry_SYSCALL_64_after_hwframe+0x63/0xe7

Bytes 4-7 of 28 are uninitialized
Memory access of size 28 starts at ffff8881937bfce0
Data copied to user address 0000000020000000

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/datagram.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 1ede7a16a0be..7b090578f044 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -341,6 +341,7 @@ void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info)
 	skb_reset_network_header(skb);
 	iph = ipv6_hdr(skb);
 	iph->daddr = fl6->daddr;
+	ip6_flow_hdr(iph, 0, 0);
 
 	serr = SKB_EXT_ERR(skb);
 	serr->ee.ee_errno = err;
-- 
2.20.1


From c0b771f180da9ca829b5e427bfdbe2039f9aca63 Mon Sep 17 00:00:00 2001
From: JianJhen Chen <kchen@synology.com>
Date: Sun, 6 Jan 2019 11:28:13 +0800
Subject: [PATCH 02/15] net: bridge: fix a bug on using a neighbour cache entry
 without checking its state

[ Upstream commit 4c84edc11b76590859b1e45dd676074c59602dc4 ]

When handling DNAT'ed packets on a bridge device, the neighbour cache entry
from lookup was used without checking its state. It means that a cache entry
in the NUD_STALE state will be used directly instead of entering the NUD_DELAY
state to confirm the reachability of the neighbor.

This problem becomes worse after commit 2724680bceee ("neigh: Keep neighbour
cache entries if number of them is small enough."), since all neighbour cache
entries in the NUD_STALE state will be kept in the neighbour table as long as
the number of cache entries does not exceed the value specified in gc_thresh1.

This commit validates the state of a neighbour cache entry before using
the entry.

Signed-off-by: JianJhen Chen <kchen@synology.com>
Reviewed-by: JinLin Chen <jlchen@synology.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_netfilter_hooks.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index b1b5e8516724..ed683e5b73ba 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -278,7 +278,7 @@ int br_nf_pre_routing_finish_bridge(struct net *net, struct sock *sk, struct sk_
 		struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 		int ret;
 
-		if (neigh->hh.hh_len) {
+		if ((neigh->nud_state & NUD_CONNECTED) && neigh->hh.hh_len) {
 			neigh_hh_bridge(&neigh->hh, skb);
 			skb->dev = nf_bridge->physindev;
 			ret = br_handle_frame_finish(net, sk, skb);
-- 
2.20.1


From 38c7eba161ae1410ccf8e1bbe18622aee5489d4a Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@mellanox.com>
Date: Tue, 8 Jan 2019 23:27:06 +0000
Subject: [PATCH 03/15] packet: Do not leak dev refcounts on error exit

[ Upstream commit d972f3dce8d161e2142da0ab1ef25df00e2f21a9 ]

'dev' is non NULL when the addr_len check triggers so it must goto a label
that does the dev_put otherwise dev will have a leaked refcount.

This bug causes the ib_ipoib module to become unloadable when using
systemd-network as it triggers this check on InfiniBand links.

Fixes: 99137b7888f4 ("packet: validate address length")
Reported-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index eedacdebcd4c..d0945253f43b 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2628,7 +2628,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 		addr	= saddr->sll_halen ? saddr->sll_addr : NULL;
 		dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex);
 		if (addr && dev && saddr->sll_halen < dev->addr_len)
-			goto out;
+			goto out_put;
 	}
 
 	err = -ENXIO;
@@ -2828,7 +2828,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		addr	= saddr->sll_halen ? saddr->sll_addr : NULL;
 		dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex);
 		if (addr && dev && saddr->sll_halen < dev->addr_len)
-			goto out;
+			goto out_unlock;
 	}
 
 	err = -ENXIO;
-- 
2.20.1


From 6d5b75a45ca0234493804bcf14168bea74aa52e0 Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Tue, 8 Jan 2019 18:14:28 -0800
Subject: [PATCH 04/15] tcp: change txhash on SYN-data timeout

[ Upstream commit c5715b8fabfca0ef85903f8bad2189940ed41cc8 ]

Previously upon SYN timeouts the sender recomputes the txhash to
try a different path. However this does not apply on the initial
timeout of SYN-data (active Fast Open). Therefore an active IPv6
Fast Open connection may incur one second RTO penalty to take on
a new path after the second SYN retransmission uses a new flow label.

This patch removes this undesirable behavior so Fast Open changes
the flow label just like the regular connections. This also helps
avoid falsely disabling Fast Open on the sender which triggers
after two consecutive SYN timeouts on Fast Open.

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_timer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index f87dbc78b6bc..71a29e9c0620 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -226,7 +226,7 @@ static int tcp_write_timeout(struct sock *sk)
 	if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
 		if (icsk->icsk_retransmits) {
 			dst_negative_advice(sk);
-		} else if (!tp->syn_data && !tp->syn_fastopen) {
+		} else {
 			sk_rethink_txhash(sk);
 		}
 		retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries;
-- 
2.20.1


From 8c9f42c21149f1565b380c67a41556f6286ddb12 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Mon, 7 Jan 2019 13:38:38 -0800
Subject: [PATCH 05/15] tun: publish tfile after it's fully initialized

[ Upstream commit 0b7959b6257322f7693b08a459c505d4938646f2 ]

BUG: unable to handle kernel NULL pointer dereference at 00000000000000d1
Call Trace:
 ? napi_gro_frags+0xa7/0x2c0
 tun_get_user+0xb50/0xf20
 tun_chr_write_iter+0x53/0x70
 new_sync_write+0xff/0x160
 vfs_write+0x191/0x1e0
 __x64_sys_write+0x5e/0xd0
 do_syscall_64+0x47/0xf0
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

I think there is a subtle race between sending a packet via tap and
attaching it:

CPU0:                    CPU1:
tun_chr_ioctl(TUNSETIFF)
  tun_set_iff
    tun_attach
      rcu_assign_pointer(tfile->tun, tun);
                         tun_fops->write_iter()
                           tun_chr_write_iter
                             tun_napi_alloc_frags
                               napi_get_frags
                                 napi->skb = napi_alloc_skb
      tun_napi_init
        netif_napi_add
          napi->skb = NULL
                              napi->skb is NULL here
                              napi_gro_frags
                                napi_frags_skb
				  skb = napi->skb
				  skb_reset_mac_header(skb)
				  panic()

Move rcu_assign_pointer(tfile->tun) and rcu_assign_pointer(tun->tfiles) to
be the last thing we do in tun_attach(); this should guarantee that when we
call tun_get() we always get an initialized object.

v2 changes:
* remove extra napi_mutex locks/unlocks for napi operations

Reported-by: syzbot <syzkaller@googlegroups.com>
Fixes: 90e33d459407 ("tun: enable napi_gro_frags() for TUN/TAP driver")

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 005020042be9..6658658246d2 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -852,10 +852,6 @@ static int tun_attach(struct tun_struct *tun, struct file *file,
 		err = 0;
 	}
 
-	rcu_assign_pointer(tfile->tun, tun);
-	rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile);
-	tun->numqueues++;
-
 	if (tfile->detached) {
 		tun_enable_queue(tfile);
 	} else {
@@ -872,6 +868,13 @@ static int tun_attach(struct tun_struct *tun, struct file *file,
 	 * refcnt.
 	 */
 
+	/* Publish tfile->tun and tun->tfiles only after we've fully
+	 * initialized tfile; otherwise we risk using half-initialized
+	 * object.
+	 */
+	rcu_assign_pointer(tfile->tun, tun);
+	rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile);
+	tun->numqueues++;
 out:
 	return err;
 }
-- 
2.20.1


From 6b92a391478908b470a8f7ac0706c09d14f3008a Mon Sep 17 00:00:00 2001
From: Camelia Groza <camelia.groza@nxp.com>
Date: Thu, 17 Jan 2019 14:33:33 +0200
Subject: [PATCH 06/15] net: phy: add missing phy driver features

[ Upstream commit 40f89ebfbd73fc9439ae8d4950f60226ad176690 ]

The phy drivers for CS4340 and TN2020 are missing their
features attributes. Add them.

Fixes: 719655a14971 ("net: phy: Replace phy driver features u32 with link_mode bitmap")
Reported-by: Scott Wood <oss@buserror.net>
Signed-off-by: Camelia Groza <camelia.groza@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/cortina.c    | 1 +
 drivers/net/phy/teranetics.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/net/phy/cortina.c b/drivers/net/phy/cortina.c
index 8022cd317f62..1a4d04afb7f0 100644
--- a/drivers/net/phy/cortina.c
+++ b/drivers/net/phy/cortina.c
@@ -88,6 +88,7 @@ static struct phy_driver cortina_driver[] = {
 	.phy_id		= PHY_ID_CS4340,
 	.phy_id_mask	= 0xffffffff,
 	.name		= "Cortina CS4340",
+	.features       = PHY_10GBIT_FEATURES,
 	.config_init	= gen10g_config_init,
 	.config_aneg	= gen10g_config_aneg,
 	.read_status	= cortina_read_status,
diff --git a/drivers/net/phy/teranetics.c b/drivers/net/phy/teranetics.c
index 22f3bdd8206c..91247182bc52 100644
--- a/drivers/net/phy/teranetics.c
+++ b/drivers/net/phy/teranetics.c
@@ -80,6 +80,7 @@ static struct phy_driver teranetics_driver[] = {
 	.phy_id		= PHY_ID_TN2020,
 	.phy_id_mask	= 0xffffffff,
 	.name		= "Teranetics TN2020",
+	.features       = PHY_10GBIT_FEATURES,
 	.soft_reset	= gen10g_no_soft_reset,
 	.aneg_done	= teranetics_aneg_done,
 	.config_init    = gen10g_config_init,
-- 
2.20.1


From c7742059ffc70730a5ab8b28f789f2ed5ea55ae5 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Tue, 15 Jan 2019 16:55:30 +0100
Subject: [PATCH 07/15] net: phy: Add missing features to PHY drivers

[ Upstream commit 9e857a40dc4eba15a739b4194d7db873d82c28a0 ]

The bcm87xx and micrel driver has PHYs which are missing the .features
value. Add them. The bcm87xx is a 10G FEC only PHY. Add the needed
features definition of this PHY.

Fixes: 719655a14971 ("net: phy: Replace phy driver features u32 with link_mode bitmap")
Reported-by: Scott Wood <oss@buserror.net>
Reported-by: Camelia Groza <camelia.groza@nxp.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/bcm87xx.c    |  2 ++
 drivers/net/phy/micrel.c     |  1 +
 drivers/net/phy/phy_device.c | 12 ++++++++++++
 include/linux/phy.h          |  2 ++
 4 files changed, 17 insertions(+)

diff --git a/drivers/net/phy/bcm87xx.c b/drivers/net/phy/bcm87xx.c
index f7ebdcff53e4..4d66e4bb904a 100644
--- a/drivers/net/phy/bcm87xx.c
+++ b/drivers/net/phy/bcm87xx.c
@@ -193,6 +193,7 @@ static struct phy_driver bcm87xx_driver[] = {
 	.phy_id		= PHY_ID_BCM8706,
 	.phy_id_mask	= 0xffffffff,
 	.name		= "Broadcom BCM8706",
+	.features	= PHY_10GBIT_FEC_FEATURES,
 	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= bcm87xx_config_init,
 	.config_aneg	= bcm87xx_config_aneg,
@@ -205,6 +206,7 @@ static struct phy_driver bcm87xx_driver[] = {
 	.phy_id		= PHY_ID_BCM8727,
 	.phy_id_mask	= 0xffffffff,
 	.name		= "Broadcom BCM8727",
+	.features	= PHY_10GBIT_FEC_FEATURES,
 	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= bcm87xx_config_init,
 	.config_aneg	= bcm87xx_config_aneg,
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 9265dea79412..51611c7a23d1 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -1105,6 +1105,7 @@ static struct phy_driver ksphy_driver[] = {
 	.phy_id		= PHY_ID_KSZ8873MLL,
 	.phy_id_mask	= MICREL_PHY_ID_MASK,
 	.name		= "Micrel KSZ8873MLL Switch",
+	.features	= PHY_BASIC_FEATURES,
 	.config_init	= kszphy_config_init,
 	.config_aneg	= ksz8873mll_config_aneg,
 	.read_status	= ksz8873mll_read_status,
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 26c41ede54a4..fd051ae787cb 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -61,6 +61,9 @@ EXPORT_SYMBOL_GPL(phy_gbit_all_ports_features);
 __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_features) __ro_after_init;
 EXPORT_SYMBOL_GPL(phy_10gbit_features);
 
+__ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_fec_features) __ro_after_init;
+EXPORT_SYMBOL_GPL(phy_10gbit_fec_features);
+
 static const int phy_basic_ports_array[] = {
 	ETHTOOL_LINK_MODE_Autoneg_BIT,
 	ETHTOOL_LINK_MODE_TP_BIT,
@@ -102,6 +105,11 @@ static const int phy_10gbit_features_array[] = {
 	ETHTOOL_LINK_MODE_10000baseT_Full_BIT,
 };
 
+const int phy_10gbit_fec_features_array[1] = {
+	ETHTOOL_LINK_MODE_10000baseR_FEC_BIT,
+};
+EXPORT_SYMBOL_GPL(phy_10gbit_fec_features_array);
+
 __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_init;
 EXPORT_SYMBOL_GPL(phy_10gbit_full_features);
 
@@ -184,6 +192,10 @@ static void features_init(void)
 	linkmode_set_bit_array(phy_10gbit_full_features_array,
 			       ARRAY_SIZE(phy_10gbit_full_features_array),
 			       phy_10gbit_full_features);
+	/* 10G FEC only */
+	linkmode_set_bit_array(phy_10gbit_fec_features_array,
+			       ARRAY_SIZE(phy_10gbit_fec_features_array),
+			       phy_10gbit_fec_features);
 }
 
 void phy_device_free(struct phy_device *phydev)
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 3ea87f774a76..306630d13523 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -48,6 +48,7 @@ extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_features) __ro_after_init;
 extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_fibre_features) __ro_after_init;
 extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_all_ports_features) __ro_after_init;
 extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_features) __ro_after_init;
+extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_fec_features) __ro_after_init;
 extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_init;
 
 #define PHY_BASIC_FEATURES ((unsigned long *)&phy_basic_features)
@@ -56,6 +57,7 @@ extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_ini
 #define PHY_GBIT_FIBRE_FEATURES ((unsigned long *)&phy_gbit_fibre_features)
 #define PHY_GBIT_ALL_PORTS_FEATURES ((unsigned long *)&phy_gbit_all_ports_features)
 #define PHY_10GBIT_FEATURES ((unsigned long *)&phy_10gbit_features)
+#define PHY_10GBIT_FEC_FEATURES ((unsigned long *)&phy_10gbit_fec_features)
 #define PHY_10GBIT_FULL_FEATURES ((unsigned long *)&phy_10gbit_full_features)
 
 /*
-- 
2.20.1


From 5b7ebd439a507ea891253d80253b745c459082cb Mon Sep 17 00:00:00 2001
From: Timotej Lazar <timotej.lazar@araneo.si>
Date: Sun, 13 Jan 2019 01:22:55 +0100
Subject: [PATCH 08/15] net: phy: meson-gxl: Use the genphy_soft_reset callback

[ Upstream commit f2f98c1d7fa81e25a5cf910edc9db4d3c6f36c1b ]

Since the referenced commit, Ethernet fails to come up at boot on the
board meson-gxl-s905x-libretech-cc. Fix this by re-enabling the
genphy_soft_reset callback for the Amlogic Meson GXL PHY driver.

Fixes: 6e2d85ec0559 ("net: phy: Stop with excessive soft reset")
Signed-off-by: Timotej Lazar <timotej.lazar@araneo.si>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/meson-gxl.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/phy/meson-gxl.c b/drivers/net/phy/meson-gxl.c
index ddc2c5ea3787..6ace118502b9 100644
--- a/drivers/net/phy/meson-gxl.c
+++ b/drivers/net/phy/meson-gxl.c
@@ -233,6 +233,7 @@ static struct phy_driver meson_gxl_phy[] = {
 		.name		= "Meson GXL Internal PHY",
 		.features	= PHY_BASIC_FEATURES,
 		.flags		= PHY_IS_INTERNAL | PHY_HAS_INTERRUPT,
+		.soft_reset     = genphy_soft_reset,
 		.config_init	= meson_gxl_config_init,
 		.aneg_done      = genphy_aneg_done,
 		.read_status	= meson_gxl_read_status,
-- 
2.20.1


From 64c4cc4dfa161c7102f315e297cb23dc3a89d72b Mon Sep 17 00:00:00 2001
From: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Date: Mon, 7 Jan 2019 14:00:09 -0500
Subject: [PATCH 09/15] lan743x: Remove phy_read from link status change
 function

[ Upstream commit a0071840d2040ea1b27e5a008182b09b88defc15 ]

It has been noticed that some phys do not have the registers
required by the previous implementation.

To fix this, instead of using phy_read, the required information
is extracted from the phy_device structure.

fixes: 23f0703c125b ("lan743x: Add main source files for new lan743x driver")
Signed-off-by: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/lan743x_main.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index 20c9377e99cb..1ce8b729929f 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -962,13 +962,10 @@ static void lan743x_phy_link_status_change(struct net_device *netdev)
 
 		memset(&ksettings, 0, sizeof(ksettings));
 		phy_ethtool_get_link_ksettings(netdev, &ksettings);
-		local_advertisement = phy_read(phydev, MII_ADVERTISE);
-		if (local_advertisement < 0)
-			return;
-
-		remote_advertisement = phy_read(phydev, MII_LPA);
-		if (remote_advertisement < 0)
-			return;
+		local_advertisement =
+			ethtool_adv_to_mii_adv_t(phydev->advertising);
+		remote_advertisement =
+			ethtool_adv_to_mii_adv_t(phydev->lp_advertising);
 
 		lan743x_phy_update_flowcontrol(adapter,
 					       ksettings.base.duplex,
-- 
2.20.1


From b490ae47c45c1025efedcaf6d81a76b8dab3e495 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Thu, 10 Jan 2019 21:24:13 +0100
Subject: [PATCH 10/15] IN_BADCLASS: fix macro to actually work

[ Upstream commit f275ee0fa3a06eb87edc229749cf1eb18f0663fa ]

Commit 65cab850f0ee ("net: Allow class-e address assignment via ifconfig
ioctl") modified the IN_BADCLASS macro a bit, but unfortunatly one too
many '(' characters were added to the line, making any code that used
it, not build properly.

Also, the macro now compares an unsigned with a signed value, which
isn't ok, so fix that up by making both types match properly.

Reported-by: Christopher Ferris <cferris@google.com>
Fixes: 65cab850f0ee ("net: Allow class-e address assignment via ifconfig ioctl")
Cc: Dave Taht <dave.taht@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/in.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h
index f6052e70bf40..a55cb8b10165 100644
--- a/include/uapi/linux/in.h
+++ b/include/uapi/linux/in.h
@@ -268,7 +268,7 @@ struct sockaddr_in {
 #define	IN_MULTICAST(a)		IN_CLASSD(a)
 #define	IN_MULTICAST_NET	0xe0000000
 
-#define	IN_BADCLASS(a)		((((long int) (a) ) == 0xffffffff)
+#define	IN_BADCLASS(a)		(((long int) (a) ) == (long int)0xffffffff)
 #define	IN_EXPERIMENTAL(a)	IN_BADCLASS((a))
 
 #define	IN_CLASSE(a)		((((long int) (a)) & 0xf0000000) == 0xf0000000)
-- 
2.20.1


From 572f3842051fcb952b6ec48fbb46689e34d342e1 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 7 Jan 2019 21:49:09 +0100
Subject: [PATCH 11/15] r8169: load Realtek PHY driver module before r8169

[ Upstream commit 11287b693d03830010356339e4ceddf47dee34fa ]

This soft dependency works around an issue where sometimes the genphy
driver is used instead of the dedicated PHY driver. The root cause of
the issue isn't clear yet. People reported the unloading/re-loading
module r8169 helps, and also configuring this soft dependency in
the modprobe config files. Important just seems to be that the
realtek module is loaded before r8169.

Once this has been applied preliminary fix 38af4b903210 ("net: phy:
add workaround for issue where PHY driver doesn't bind to the device")
will be removed.

Fixes: f1e911d5d0df ("r8169: add basic phylib support")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 209566f8097b..44ecab6339ab 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -714,6 +714,7 @@ module_param(use_dac, int, 0);
 MODULE_PARM_DESC(use_dac, "Enable PCI DAC. Unsafe on 32 bit PCI slot.");
 module_param_named(debug, debug.msg_enable, int, 0);
 MODULE_PARM_DESC(debug, "Debug verbosity level (0=none, ..., 16=all)");
+MODULE_SOFTDEP("pre: realtek");
 MODULE_LICENSE("GPL");
 MODULE_FIRMWARE(FIRMWARE_8168D_1);
 MODULE_FIRMWARE(FIRMWARE_8168D_2);
-- 
2.20.1


From a59db92c91aa4f7497e5884365ad76863a42eec7 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Tue, 8 Jan 2019 12:32:42 -0500
Subject: [PATCH 12/15] bonding: update nest level on unlink

[ Upstream commit 001e465f09a18857443489a57e74314a3368c805 ]

A network device stack with multiple layers of bonding devices can
trigger a false positive lockdep warning. Adding lockdep nest levels
fixes this. Update the level on both enslave and unlink, to avoid the
following series of events ..

    ip netns add test
    ip netns exec test bash
    ip link set dev lo addr 00:11:22:33:44:55
    ip link set dev lo down

    ip link add dev bond1 type bond
    ip link add dev bond2 type bond

    ip link set dev lo master bond1
    ip link set dev bond1 master bond2

    ip link set dev bond1 nomaster
    ip link set dev bond2 master bond1

.. from still generating a splat:

    [  193.652127] ======================================================
    [  193.658231] WARNING: possible circular locking dependency detected
    [  193.664350] 4.20.0 #8 Not tainted
    [  193.668310] ------------------------------------------------------
    [  193.674417] ip/15577 is trying to acquire lock:
    [  193.678897] 00000000a40e3b69 (&(&bond->stats_lock)->rlock#3/3){+.+.}, at: bond_get_stats+0x58/0x290
    [  193.687851]
    	       but task is already holding lock:
    [  193.693625] 00000000807b9d9f (&(&bond->stats_lock)->rlock#2/2){+.+.}, at: bond_get_stats+0x58/0x290

    [..]

    [  193.851092]        lock_acquire+0xa7/0x190
    [  193.855138]        _raw_spin_lock_nested+0x2d/0x40
    [  193.859878]        bond_get_stats+0x58/0x290
    [  193.864093]        dev_get_stats+0x5a/0xc0
    [  193.868140]        bond_get_stats+0x105/0x290
    [  193.872444]        dev_get_stats+0x5a/0xc0
    [  193.876493]        rtnl_fill_stats+0x40/0x130
    [  193.880797]        rtnl_fill_ifinfo+0x6c5/0xdc0
    [  193.885271]        rtmsg_ifinfo_build_skb+0x86/0xe0
    [  193.890091]        rtnetlink_event+0x5b/0xa0
    [  193.894320]        raw_notifier_call_chain+0x43/0x60
    [  193.899225]        netdev_change_features+0x50/0xa0
    [  193.904044]        bond_compute_features.isra.46+0x1ab/0x270
    [  193.909640]        bond_enslave+0x141d/0x15b0
    [  193.913946]        do_set_master+0x89/0xa0
    [  193.918016]        do_setlink+0x37c/0xda0
    [  193.921980]        __rtnl_newlink+0x499/0x890
    [  193.926281]        rtnl_newlink+0x48/0x70
    [  193.930238]        rtnetlink_rcv_msg+0x171/0x4b0
    [  193.934801]        netlink_rcv_skb+0xd1/0x110
    [  193.939103]        rtnetlink_rcv+0x15/0x20
    [  193.943151]        netlink_unicast+0x3b5/0x520
    [  193.947544]        netlink_sendmsg+0x2fd/0x3f0
    [  193.951942]        sock_sendmsg+0x38/0x50
    [  193.955899]        ___sys_sendmsg+0x2ba/0x2d0
    [  193.960205]        __x64_sys_sendmsg+0xad/0x100
    [  193.964687]        do_syscall_64+0x5a/0x460
    [  193.968823]        entry_SYSCALL_64_after_hwframe+0x49/0xbe

Fixes: 7e2556e40026 ("bonding: avoid lockdep confusion in bond_get_stats()")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 333387f1f1fe..62659abf73cd 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1948,6 +1948,9 @@ static int __bond_release_one(struct net_device *bond_dev,
 	if (!bond_has_slaves(bond)) {
 		bond_set_carrier(bond);
 		eth_hw_addr_random(bond_dev);
+		bond->nest_level = SINGLE_DEPTH_NESTING;
+	} else {
+		bond->nest_level = dev_get_nest_level(bond_dev) + 1;
 	}
 
 	unblock_netpoll_tx();
-- 
2.20.1


From 417adeeaecdbb1acf949a6bda4c9bdb162441f72 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Mon, 7 Jan 2019 16:47:33 -0500
Subject: [PATCH 13/15] ip: on queued skb use skb_header_pointer instead of
 pskb_may_pull

[ Upstream commit 4a06fa67c4da20148803525151845276cdb995c1 ]

Commit 2efd4fca703a ("ip: in cmsg IP(V6)_ORIGDSTADDR call
pskb_may_pull") avoided a read beyond the end of the skb linear
segment by calling pskb_may_pull.

That function can trigger a BUG_ON in pskb_expand_head if the skb is
shared, which it is when when peeking. It can also return ENOMEM.

Avoid both by switching to safer skb_header_pointer.

Fixes: 2efd4fca703a ("ip: in cmsg IP(V6)_ORIGDSTADDR call pskb_may_pull")
Reported-by: syzbot <syzkaller@googlegroups.com>
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_sockglue.c | 12 +++++-------
 net/ipv6/datagram.c    | 10 ++++------
 2 files changed, 9 insertions(+), 13 deletions(-)

diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index fffcc130900e..82f341e84fae 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -148,19 +148,17 @@ static void ip_cmsg_recv_security(struct msghdr *msg, struct sk_buff *skb)
 
 static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
 {
+	__be16 _ports[2], *ports;
 	struct sockaddr_in sin;
-	__be16 *ports;
-	int end;
-
-	end = skb_transport_offset(skb) + 4;
-	if (end > 0 && !pskb_may_pull(skb, end))
-		return;
 
 	/* All current transport protocols have the port numbers in the
 	 * first four bytes of the transport header and this function is
 	 * written with this assumption in mind.
 	 */
-	ports = (__be16 *)skb_transport_header(skb);
+	ports = skb_header_pointer(skb, skb_transport_offset(skb),
+				   sizeof(_ports), &_ports);
+	if (!ports)
+		return;
 
 	sin.sin_family = AF_INET;
 	sin.sin_addr.s_addr = ip_hdr(skb)->daddr;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 7b090578f044..cb24850d2c7f 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -701,17 +701,15 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg,
 	}
 	if (np->rxopt.bits.rxorigdstaddr) {
 		struct sockaddr_in6 sin6;
-		__be16 *ports;
-		int end;
+		__be16 _ports[2], *ports;
 
-		end = skb_transport_offset(skb) + 4;
-		if (end <= 0 || pskb_may_pull(skb, end)) {
+		ports = skb_header_pointer(skb, skb_transport_offset(skb),
+					   sizeof(_ports), &_ports);
+		if (ports) {
 			/* All current transport protocols have the port numbers in the
 			 * first four bytes of the transport header and this function is
 			 * written with this assumption in mind.
 			 */
-			ports = (__be16 *)skb_transport_header(skb);
-
 			sin6.sin6_family = AF_INET6;
 			sin6.sin6_addr = ipv6_hdr(skb)->daddr;
 			sin6.sin6_port = ports[1];
-- 
2.20.1


From 051257acef596ff10a1009ee3d156dea0a76072c Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 6 Jan 2019 20:44:00 +0100
Subject: [PATCH 14/15] r8169: don't try to read counters if chip is in a PCI
 power-save state

[ Upstream commit 10262b0b53666cbc506989b17a3ead1e9c3b43b4 ]

Avoid log spam caused by trying to read counters from the chip whilst
it is in a PCI power-save state.

Reference: https://bugzilla.kernel.org/show_bug.cgi?id=107421

Fixes: 1ef7286e7f36 ("r8169: Dereference MMIO address immediately before use")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 44ecab6339ab..78ea9639b622 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -1729,11 +1729,13 @@ static bool rtl8169_reset_counters(struct rtl8169_private *tp)
 
 static bool rtl8169_update_counters(struct rtl8169_private *tp)
 {
+	u8 val = RTL_R8(tp, ChipCmd);
+
 	/*
 	 * Some chips are unable to dump tally counters when the receiver
-	 * is disabled.
+	 * is disabled. If 0xff chip may be in a PCI power-save state.
 	 */
-	if ((RTL_R8(tp, ChipCmd) & CmdRxEnb) == 0)
+	if (!(val & CmdRxEnb) || val == 0xff)
 		return true;
 
 	return rtl8169_do_counters(tp, CounterDump);
-- 
2.20.1


From 73ea006fc9084865f0bc18ef129efa122b82fc4b Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sat, 5 Jan 2019 23:45:26 -0800
Subject: [PATCH 15/15] smc: move unhash as early as possible in smc_release()

[ Upstream commit 26d92e951fe0a44ee4aec157cabb65a818cc8151 ]

In smc_release() we release smc->clcsock before unhash the smc
sock, but a parallel smc_diag_dump() may be still reading
smc->clcsock, therefore this could cause a use-after-free as
reported by syzbot.

Reported-and-tested-by: syzbot+fbd1e5476e4c94c7b34e@syzkaller.appspotmail.com
Fixes: 51f1de79ad8e ("net/smc: replace sock_put worker by socket refcounting")
Cc: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Reported-by: syzbot+0bf2e01269f1274b4b03@syzkaller.appspotmail.com
Reported-by: syzbot+e3132895630f957306bc@syzkaller.appspotmail.com
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/af_smc.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 82cb0e5634bc..5d2214183601 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -146,6 +146,9 @@ static int smc_release(struct socket *sock)
 		sock_set_flag(sk, SOCK_DEAD);
 		sk->sk_shutdown |= SHUTDOWN_MASK;
 	}
+
+	sk->sk_prot->unhash(sk);
+
 	if (smc->clcsock) {
 		if (smc->use_fallback && sk->sk_state == SMC_LISTEN) {
 			/* wake up clcsock accept */
@@ -170,7 +173,6 @@ static int smc_release(struct socket *sock)
 		smc_conn_free(&smc->conn);
 	release_sock(sk);
 
-	sk->sk_prot->unhash(sk);
 	sock_put(sk); /* final sock_put */
 out:
 	return rc;
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Sun, Jan 20, 2019 at 11:12:06AM -0800, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.19
> and v4.20 -stable, respectively.
> 
> Thank you.


All now queued up, thanks.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 118 bytes --]


Another day, another batch of networking fixes.

Please queue up for v4.19 and v4.20 -stable, respectively.

Thanks!

[-- Attachment #2: net_419.mbox --]
[-- Type: Application/Octet-Stream, Size: 23451 bytes --]

From b4facfaa08ea832515a15d174893fd6f821e7e36 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Fri, 4 Jan 2019 16:58:15 -0800
Subject: [PATCH 01/10] ipv6: Consider sk_bound_dev_if when binding a socket to
 a v4 mapped address

[ Upstream commit ec90ad334986fa5856d11dd272f7f22fa86c55c4 ]

Similar to c5ee066333eb ("ipv6: Consider sk_bound_dev_if when binding a
socket to an address"), binding a socket to v4 mapped addresses needs to
consider if the socket is bound to a device.

This problem also exists from the beginning of git history.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/af_inet6.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 9a4261e50272..895847e57a8e 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -309,6 +309,7 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
 
 	/* Check if the address belongs to the host. */
 	if (addr_type == IPV6_ADDR_MAPPED) {
+		struct net_device *dev = NULL;
 		int chk_addr_ret;
 
 		/* Binding to v4-mapped address on a v6-only socket
@@ -319,9 +320,17 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
 			goto out;
 		}
 
+		if (sk->sk_bound_dev_if) {
+			dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if);
+			if (!dev) {
+				err = -ENODEV;
+				goto out;
+			}
+		}
+
 		/* Reproduce AF_INET checks to make the bindings consistent */
 		v4addr = addr->sin6_addr.s6_addr32[3];
-		chk_addr_ret = inet_addr_type(net, v4addr);
+		chk_addr_ret = inet_addr_type_dev_table(net, dev, v4addr);
 		if (!inet_can_nonlocal_bind(net, inet) &&
 		    v4addr != htonl(INADDR_ANY) &&
 		    chk_addr_ret != RTN_LOCAL &&
-- 
2.20.1


From 99c3f7c82a8c37c97398982440f89803d21082c7 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Tue, 8 Jan 2019 16:48:05 +0000
Subject: [PATCH 02/10] mlxsw: spectrum: Disable lag port TX before removing it

[ Upstream commit 8adbe212a159d9c78a90fca1d854f6e63452426b ]

Make sure that lag port TX is disabled before mlxsw_sp_port_lag_leave()
is called and prevent from possible EMAD error.

Fixes: 0d65fc13042f ("mlxsw: spectrum: Implement LAG port join/leave")
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 3d1159f8a53f..de821a9fdfaf 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4635,12 +4635,15 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev,
 							   lower_dev,
 							   upper_dev);
 		} else if (netif_is_lag_master(upper_dev)) {
-			if (info->linking)
+			if (info->linking) {
 				err = mlxsw_sp_port_lag_join(mlxsw_sp_port,
 							     upper_dev);
-			else
+			} else {
+				mlxsw_sp_port_lag_tx_en_set(mlxsw_sp_port,
+							    false);
 				mlxsw_sp_port_lag_leave(mlxsw_sp_port,
 							upper_dev);
+			}
 		} else if (netif_is_ovs_master(upper_dev)) {
 			if (info->linking)
 				err = mlxsw_sp_port_ovs_join(mlxsw_sp_port);
-- 
2.20.1


From db96f6ddf573802f7f42d8396201fb9a128d8ca8 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Tue, 8 Jan 2019 16:48:13 +0000
Subject: [PATCH 03/10] mlxsw: spectrum_switchdev: Set PVID correctly during
 VLAN deletion

[ Upstream commit 674bed5df4cab8f96d04f7b99608883a48f9226b ]

When a VLAN is deleted from a bridge port we should not change the PVID
unless the deleted VLAN is the PVID.

Fixes: fe9ccc785de5 ("mlxsw: spectrum_switchdev: Don't batch VLAN operations")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 4eb64cb0d9a1..0d9ea37c5d21 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -1761,7 +1761,7 @@ static void
 mlxsw_sp_bridge_port_vlan_del(struct mlxsw_sp_port *mlxsw_sp_port,
 			      struct mlxsw_sp_bridge_port *bridge_port, u16 vid)
 {
-	u16 pvid = mlxsw_sp_port->pvid == vid ? 0 : vid;
+	u16 pvid = mlxsw_sp_port->pvid == vid ? 0 : mlxsw_sp_port->pvid;
 	struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan;
 
 	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid);
-- 
2.20.1


From 95c0e532a5712cf97b0e4f2873d5d8e4c7aa9789 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Wed, 9 Jan 2019 00:24:03 +0100
Subject: [PATCH 04/10] net: dsa: mv88x6xxx: mv88e6390 errata

[ Upstream commit ea89098ef9a574bceca00d3b5df14aaf0b3f9ccf ]

The 6390 copper ports have an errata which require poking magic values
into undocumented magic registers and then performing a software
reset.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 113 +++++++++++++++++++++++++++++++
 drivers/net/dsa/mv88e6xxx/chip.h |   5 ++
 drivers/net/dsa/mv88e6xxx/port.h |  10 +++
 3 files changed, 128 insertions(+)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 8da3d39e3218..258918d8a416 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -2391,6 +2391,107 @@ static int mv88e6xxx_stats_setup(struct mv88e6xxx_chip *chip)
 	return mv88e6xxx_g1_stats_clear(chip);
 }
 
+/* The mv88e6390 has some hidden registers used for debug and
+ * development. The errata also makes use of them.
+ */
+static int mv88e6390_hidden_write(struct mv88e6xxx_chip *chip, int port,
+				  int reg, u16 val)
+{
+	u16 ctrl;
+	int err;
+
+	err = mv88e6xxx_port_write(chip, PORT_RESERVED_1A_DATA_PORT,
+				   PORT_RESERVED_1A, val);
+	if (err)
+		return err;
+
+	ctrl = PORT_RESERVED_1A_BUSY | PORT_RESERVED_1A_WRITE |
+	       PORT_RESERVED_1A_BLOCK | port << PORT_RESERVED_1A_PORT_SHIFT |
+	       reg;
+
+	return mv88e6xxx_port_write(chip, PORT_RESERVED_1A_CTRL_PORT,
+				    PORT_RESERVED_1A, ctrl);
+}
+
+static int mv88e6390_hidden_wait(struct mv88e6xxx_chip *chip)
+{
+	return mv88e6xxx_wait(chip, PORT_RESERVED_1A_CTRL_PORT,
+			      PORT_RESERVED_1A, PORT_RESERVED_1A_BUSY);
+}
+
+
+static int mv88e6390_hidden_read(struct mv88e6xxx_chip *chip, int port,
+				  int reg, u16 *val)
+{
+	u16 ctrl;
+	int err;
+
+	ctrl = PORT_RESERVED_1A_BUSY | PORT_RESERVED_1A_READ |
+	       PORT_RESERVED_1A_BLOCK | port << PORT_RESERVED_1A_PORT_SHIFT |
+	       reg;
+
+	err = mv88e6xxx_port_write(chip, PORT_RESERVED_1A_CTRL_PORT,
+				   PORT_RESERVED_1A, ctrl);
+	if (err)
+		return err;
+
+	err = mv88e6390_hidden_wait(chip);
+	if (err)
+		return err;
+
+	return 	mv88e6xxx_port_read(chip, PORT_RESERVED_1A_DATA_PORT,
+				    PORT_RESERVED_1A, val);
+}
+
+/* Check if the errata has already been applied. */
+static bool mv88e6390_setup_errata_applied(struct mv88e6xxx_chip *chip)
+{
+	int port;
+	int err;
+	u16 val;
+
+	for (port = 0; port < mv88e6xxx_num_ports(chip); port++) {
+		err = mv88e6390_hidden_read(chip, port, 0, &val);
+		if (err) {
+			dev_err(chip->dev,
+				"Error reading hidden register: %d\n", err);
+			return false;
+		}
+		if (val != 0x01c0)
+			return false;
+	}
+
+	return true;
+}
+
+/* The 6390 copper ports have an errata which require poking magic
+ * values into undocumented hidden registers and then performing a
+ * software reset.
+ */
+static int mv88e6390_setup_errata(struct mv88e6xxx_chip *chip)
+{
+	int port;
+	int err;
+
+	if (mv88e6390_setup_errata_applied(chip))
+		return 0;
+
+	/* Set the ports into blocking mode */
+	for (port = 0; port < mv88e6xxx_num_ports(chip); port++) {
+		err = mv88e6xxx_port_set_state(chip, port, BR_STATE_DISABLED);
+		if (err)
+			return err;
+	}
+
+	for (port = 0; port < mv88e6xxx_num_ports(chip); port++) {
+		err = mv88e6390_hidden_write(chip, port, 0, 0x01c0);
+		if (err)
+			return err;
+	}
+
+	return mv88e6xxx_software_reset(chip);
+}
+
 static int mv88e6xxx_setup(struct dsa_switch *ds)
 {
 	struct mv88e6xxx_chip *chip = ds->priv;
@@ -2403,6 +2504,12 @@ static int mv88e6xxx_setup(struct dsa_switch *ds)
 
 	mutex_lock(&chip->reg_lock);
 
+	if (chip->info->ops->setup_errata) {
+		err = chip->info->ops->setup_errata(chip);
+		if (err)
+			goto unlock;
+	}
+
 	/* Cache the cmode of each port. */
 	for (i = 0; i < mv88e6xxx_num_ports(chip); i++) {
 		if (chip->info->ops->port_get_cmode) {
@@ -3201,6 +3308,7 @@ static const struct mv88e6xxx_ops mv88e6185_ops = {
 
 static const struct mv88e6xxx_ops mv88e6190_ops = {
 	/* MV88E6XXX_FAMILY_6390 */
+	.setup_errata = mv88e6390_setup_errata,
 	.irl_init_all = mv88e6390_g2_irl_init_all,
 	.get_eeprom = mv88e6xxx_g2_get_eeprom8,
 	.set_eeprom = mv88e6xxx_g2_set_eeprom8,
@@ -3243,6 +3351,7 @@ static const struct mv88e6xxx_ops mv88e6190_ops = {
 
 static const struct mv88e6xxx_ops mv88e6190x_ops = {
 	/* MV88E6XXX_FAMILY_6390 */
+	.setup_errata = mv88e6390_setup_errata,
 	.irl_init_all = mv88e6390_g2_irl_init_all,
 	.get_eeprom = mv88e6xxx_g2_get_eeprom8,
 	.set_eeprom = mv88e6xxx_g2_set_eeprom8,
@@ -3285,6 +3394,7 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = {
 
 static const struct mv88e6xxx_ops mv88e6191_ops = {
 	/* MV88E6XXX_FAMILY_6390 */
+	.setup_errata = mv88e6390_setup_errata,
 	.irl_init_all = mv88e6390_g2_irl_init_all,
 	.get_eeprom = mv88e6xxx_g2_get_eeprom8,
 	.set_eeprom = mv88e6xxx_g2_set_eeprom8,
@@ -3374,6 +3484,7 @@ static const struct mv88e6xxx_ops mv88e6240_ops = {
 
 static const struct mv88e6xxx_ops mv88e6290_ops = {
 	/* MV88E6XXX_FAMILY_6390 */
+	.setup_errata = mv88e6390_setup_errata,
 	.irl_init_all = mv88e6390_g2_irl_init_all,
 	.get_eeprom = mv88e6xxx_g2_get_eeprom8,
 	.set_eeprom = mv88e6xxx_g2_set_eeprom8,
@@ -3675,6 +3786,7 @@ static const struct mv88e6xxx_ops mv88e6352_ops = {
 
 static const struct mv88e6xxx_ops mv88e6390_ops = {
 	/* MV88E6XXX_FAMILY_6390 */
+	.setup_errata = mv88e6390_setup_errata,
 	.irl_init_all = mv88e6390_g2_irl_init_all,
 	.get_eeprom = mv88e6xxx_g2_get_eeprom8,
 	.set_eeprom = mv88e6xxx_g2_set_eeprom8,
@@ -3722,6 +3834,7 @@ static const struct mv88e6xxx_ops mv88e6390_ops = {
 
 static const struct mv88e6xxx_ops mv88e6390x_ops = {
 	/* MV88E6XXX_FAMILY_6390 */
+	.setup_errata = mv88e6390_setup_errata,
 	.irl_init_all = mv88e6390_g2_irl_init_all,
 	.get_eeprom = mv88e6xxx_g2_get_eeprom8,
 	.set_eeprom = mv88e6xxx_g2_set_eeprom8,
diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h
index f9ecb7872d32..546651d8c3e1 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.h
+++ b/drivers/net/dsa/mv88e6xxx/chip.h
@@ -300,6 +300,11 @@ struct mv88e6xxx_mdio_bus {
 };
 
 struct mv88e6xxx_ops {
+	/* Switch Setup Errata, called early in the switch setup to
+	 * allow any errata actions to be performed
+	 */
+	int (*setup_errata)(struct mv88e6xxx_chip *chip);
+
 	int (*ieee_pri_map)(struct mv88e6xxx_chip *chip);
 	int (*ip_pri_map)(struct mv88e6xxx_chip *chip);
 
diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h
index f32f56af8e35..b31910023bb6 100644
--- a/drivers/net/dsa/mv88e6xxx/port.h
+++ b/drivers/net/dsa/mv88e6xxx/port.h
@@ -251,6 +251,16 @@
 /* Offset 0x19: Port IEEE Priority Remapping Registers (4-7) */
 #define MV88E6095_PORT_IEEE_PRIO_REMAP_4567	0x19
 
+/* Offset 0x1a: Magic undocumented errata register */
+#define PORT_RESERVED_1A			0x1a
+#define PORT_RESERVED_1A_BUSY			BIT(15)
+#define PORT_RESERVED_1A_WRITE			BIT(14)
+#define PORT_RESERVED_1A_READ			0
+#define PORT_RESERVED_1A_PORT_SHIFT		5
+#define PORT_RESERVED_1A_BLOCK			(0xf << 10)
+#define PORT_RESERVED_1A_CTRL_PORT		4
+#define PORT_RESERVED_1A_DATA_PORT		5
+
 int mv88e6xxx_port_read(struct mv88e6xxx_chip *chip, int port, int reg,
 			u16 *val);
 int mv88e6xxx_port_write(struct mv88e6xxx_chip *chip, int port, int reg,
-- 
2.20.1


From e9d202139775c7aadddb8fde6f6d03dac9b3e080 Mon Sep 17 00:00:00 2001
From: David Rientjes <rientjes@google.com>
Date: Wed, 2 Jan 2019 13:01:43 -0800
Subject: [PATCH 05/10] net, skbuff: do not prefer skb allocation fails early

[ Upstream commit f8c468e8537925e0c4607263f498a1b7c0c8982e ]

Commit dcda9b04713c ("mm, tree wide: replace __GFP_REPEAT by
__GFP_RETRY_MAYFAIL with more useful semantic") replaced __GFP_REPEAT in
alloc_skb_with_frags() with __GFP_RETRY_MAYFAIL when the allocation may
directly reclaim.

The previous behavior would require reclaim up to 1 << order pages for
skb aligned header_len of order > PAGE_ALLOC_COSTLY_ORDER before failing,
otherwise the allocations in alloc_skb() would loop in the page allocator
looking for memory.  __GFP_RETRY_MAYFAIL makes both allocations failable
under memory pressure, including for the HEAD allocation.

This can cause, among many other things, write() to fail with ENOTCONN
during RPC when under memory pressure.

These allocations should succeed as they did previous to dcda9b04713c
even if it requires calling the oom killer and additional looping in the
page allocator to find memory.  There is no way to specify the previous
behavior of __GFP_REPEAT, but it's unlikely to be necessary since the
previous behavior only guaranteed that 1 << order pages would be reclaimed
before failing for order > PAGE_ALLOC_COSTLY_ORDER.  That reclaim is not
guaranteed to be contiguous memory, so repeating for such large orders is
usually not beneficial.

Removing the setting of __GFP_RETRY_MAYFAIL to restore the previous
behavior, specifically not allowing alloc_skb() to fail for small orders
and oom kill if necessary rather than allowing RPCs to fail.

Fixes: dcda9b04713c ("mm, tree wide: replace __GFP_REPEAT by __GFP_RETRY_MAYFAIL with more useful semantic")
Signed-off-by: David Rientjes <rientjes@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index abbbd7fd17fe..589ec5b9ec5f 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5258,7 +5258,6 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len,
 	unsigned long chunk;
 	struct sk_buff *skb;
 	struct page *page;
-	gfp_t gfp_head;
 	int i;
 
 	*errcode = -EMSGSIZE;
@@ -5268,12 +5267,8 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len,
 	if (npages > MAX_SKB_FRAGS)
 		return NULL;
 
-	gfp_head = gfp_mask;
-	if (gfp_head & __GFP_DIRECT_RECLAIM)
-		gfp_head |= __GFP_RETRY_MAYFAIL;
-
 	*errcode = -ENOBUFS;
-	skb = alloc_skb(header_len, gfp_head);
+	skb = alloc_skb(header_len, gfp_mask);
 	if (!skb)
 		return NULL;
 
-- 
2.20.1


From 1b55ef63bc3af16b0f9e6244f54dedd63c318c27 Mon Sep 17 00:00:00 2001
From: Daniele Palmas <dnlplm@gmail.com>
Date: Fri, 4 Jan 2019 13:26:10 +0100
Subject: [PATCH 06/10] qmi_wwan: add MTU default to qmap network interface
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit f87118d5760f00af7228033fbe783c7f380d2866 ]

This patch adds MTU default value to qmap network interface in
order to avoid "RTNETLINK answers: No buffer space available"
error when setting an ipv6 address.

Signed-off-by: Daniele Palmas <dnlplm@gmail.com>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 774e1ff01c9a..735ad838e2ba 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -123,6 +123,7 @@ static void qmimux_setup(struct net_device *dev)
 	dev->addr_len        = 0;
 	dev->flags           = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST;
 	dev->netdev_ops      = &qmimux_netdev_ops;
+	dev->mtu             = 1500;
 	dev->needs_free_netdev = true;
 }
 
-- 
2.20.1


From a8eb4eb3763b9bd7bf800cd935acd67f476daefb Mon Sep 17 00:00:00 2001
From: Kai-Heng Feng <kai.heng.feng@canonical.com>
Date: Wed, 2 Jan 2019 14:45:07 +0800
Subject: [PATCH 07/10] r8169: Add support for new Realtek Ethernet

[ Upstream commit 36352991835ce99e46b4441dd0eb6980f9a83e8f ]

There are two new Realtek Ethernet devices which are re-branded r8168h.
Add the IDs to to support them.

Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Reviewed-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 9fc8a2bc0ff1..91d6dae73675 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -214,6 +214,8 @@ enum cfg_version {
 };
 
 static const struct pci_device_id rtl8169_pci_tbl[] = {
+	{ PCI_VDEVICE(REALTEK,	0x2502), RTL_CFG_1 },
+	{ PCI_VDEVICE(REALTEK,	0x2600), RTL_CFG_1 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8129), 0, 0, RTL_CFG_0 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8136), 0, 0, RTL_CFG_2 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8161), 0, 0, RTL_CFG_1 },
-- 
2.20.1


From 043f7f321d7894c177332c6e591b90dc2b3ce8a2 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Sat, 5 Jan 2019 07:35:04 -0800
Subject: [PATCH 08/10] ipv6: Take rcu_read_lock in __inet6_bind for mapped
 addresses

[ Upstream commit d4a7e9bb74b5aaf07b89f6531c080b1130bdf019 ]

I realized the last patch calls dev_get_by_index_rcu in a branch not
holding the rcu lock. Add the calls to rcu_read_lock and rcu_read_unlock.

Fixes: ec90ad334986 ("ipv6: Consider sk_bound_dev_if when binding a socket to a v4 mapped address")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/af_inet6.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 895847e57a8e..506b2ae07bb3 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -320,17 +320,20 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
 			goto out;
 		}
 
+		rcu_read_lock();
 		if (sk->sk_bound_dev_if) {
 			dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if);
 			if (!dev) {
 				err = -ENODEV;
-				goto out;
+				goto out_unlock;
 			}
 		}
 
 		/* Reproduce AF_INET checks to make the bindings consistent */
 		v4addr = addr->sin6_addr.s6_addr32[3];
 		chk_addr_ret = inet_addr_type_dev_table(net, dev, v4addr);
+		rcu_read_unlock();
+
 		if (!inet_can_nonlocal_bind(net, inet) &&
 		    v4addr != htonl(INADDR_ANY) &&
 		    chk_addr_ret != RTN_LOCAL &&
-- 
2.20.1


From 26e550e4cdd83fc369193f4cdf255b798d2ebb88 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 4 Jan 2019 11:00:00 -0800
Subject: [PATCH 09/10] ipv6: make icmp6_send() robust against null skb->dev

[ Upstream commit 8d933670452107e41165bea70a30dffbd281bef1 ]

syzbot was able to crash one host with the following stack trace :

kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] PREEMPT SMP KASAN
CPU: 0 PID: 8625 Comm: syz-executor4 Not tainted 4.20.0+ #8
RIP: 0010:dev_net include/linux/netdevice.h:2169 [inline]
RIP: 0010:icmp6_send+0x116/0x2d30 net/ipv6/icmp.c:426
 icmpv6_send
 smack_socket_sock_rcv_skb
 security_sock_rcv_skb
 sk_filter_trim_cap
 __sk_receive_skb
 dccp_v6_do_rcv
 release_sock

This is because a RX packet found socket owned by user and
was stored into socket backlog. Before leaving RCU protected section,
skb->dev was cleared in __sk_receive_skb(). When socket backlog
was finally handled at release_sock() time, skb was fed to
smack_socket_sock_rcv_skb() then icmp6_send()

We could fix the bug in smack_socket_sock_rcv_skb(), or simply
make icmp6_send() more robust against such possibility.

In the future we might provide to icmp6_send() the net pointer
instead of infering it.

Fixes: d66a8acbda92 ("Smack: Inform peer that IPv6 traffic has been blocked")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Piotr Sawicki <p.sawicki2@partner.samsung.com>
Cc: Casey Schaufler <casey@schaufler-ca.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: Casey Schaufler <casey@schaufler-ca.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/icmp.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index c9c53ade55c3..6d14cbe443f8 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -421,10 +421,10 @@ static int icmp6_iif(const struct sk_buff *skb)
 static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 		       const struct in6_addr *force_saddr)
 {
-	struct net *net = dev_net(skb->dev);
 	struct inet6_dev *idev = NULL;
 	struct ipv6hdr *hdr = ipv6_hdr(skb);
 	struct sock *sk;
+	struct net *net;
 	struct ipv6_pinfo *np;
 	const struct in6_addr *saddr = NULL;
 	struct dst_entry *dst;
@@ -435,12 +435,16 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 	int iif = 0;
 	int addr_type = 0;
 	int len;
-	u32 mark = IP6_REPLY_MARK(net, skb->mark);
+	u32 mark;
 
 	if ((u8 *)hdr < skb->head ||
 	    (skb_network_header(skb) + sizeof(*hdr)) > skb_tail_pointer(skb))
 		return;
 
+	if (!skb->dev)
+		return;
+	net = dev_net(skb->dev);
+	mark = IP6_REPLY_MARK(net, skb->mark);
 	/*
 	 *	Make sure we respect the rules
 	 *	i.e. RFC 1885 2.4(e)
-- 
2.20.1


From 95409338d63f2e526daf7115bbb0b5a640f9d742 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 8 Jan 2019 18:45:05 +0100
Subject: [PATCH 10/10] net: clear skb->tstamp in bridge forwarding path

[ Upstream commit 41d1c8839e5f8cb781cc635f12791decee8271b7 ]

Matteo reported forwarding issues inside the linux bridge,
if the enslaved interfaces use the fq qdisc.

Similar to commit 8203e2d844d3 ("net: clear skb->tstamp in
forwarding paths"), we need to clear the tstamp field in
the bridge forwarding path.

Fixes: 80b14dee2bea ("net: Add a new socket option for a future transmit time.")
Fixes: fb420d5d91c1 ("tcp/fq: move back to CLOCK_MONOTONIC")
Reported-and-tested-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Acked-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_forward.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 5372e2042adf..2cb8da465b98 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -65,6 +65,7 @@ EXPORT_SYMBOL_GPL(br_dev_queue_push_xmit);
 
 int br_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
+	skb->tstamp = 0;
 	return NF_HOOK(NFPROTO_BRIDGE, NF_BR_POST_ROUTING,
 		       net, sk, skb, NULL, skb->dev,
 		       br_dev_queue_push_xmit);
-- 
2.20.1


[-- Attachment #3: net_420.mbox --]
[-- Type: Application/Octet-Stream, Size: 30570 bytes --]

From 90919cb5ae40306c71ecdb9005b62fdc33f0d36f Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Fri, 4 Jan 2019 16:58:15 -0800
Subject: [PATCH 01/14] ipv6: Consider sk_bound_dev_if when binding a socket to
 a v4 mapped address

[ Upstream commit ec90ad334986fa5856d11dd272f7f22fa86c55c4 ]

Similar to c5ee066333eb ("ipv6: Consider sk_bound_dev_if when binding a
socket to an address"), binding a socket to v4 mapped addresses needs to
consider if the socket is bound to a device.

This problem also exists from the beginning of git history.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/af_inet6.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index f0cd291034f0..63d154578955 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -310,6 +310,7 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
 
 	/* Check if the address belongs to the host. */
 	if (addr_type == IPV6_ADDR_MAPPED) {
+		struct net_device *dev = NULL;
 		int chk_addr_ret;
 
 		/* Binding to v4-mapped address on a v6-only socket
@@ -320,9 +321,17 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
 			goto out;
 		}
 
+		if (sk->sk_bound_dev_if) {
+			dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if);
+			if (!dev) {
+				err = -ENODEV;
+				goto out;
+			}
+		}
+
 		/* Reproduce AF_INET checks to make the bindings consistent */
 		v4addr = addr->sin6_addr.s6_addr32[3];
-		chk_addr_ret = inet_addr_type(net, v4addr);
+		chk_addr_ret = inet_addr_type_dev_table(net, dev, v4addr);
 		if (!inet_can_nonlocal_bind(net, inet) &&
 		    v4addr != htonl(INADDR_ANY) &&
 		    chk_addr_ret != RTN_LOCAL &&
-- 
2.20.1


From 0f6babea7085b103847f1b476f7f745da11b6e50 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Tue, 8 Jan 2019 16:48:05 +0000
Subject: [PATCH 02/14] mlxsw: spectrum: Disable lag port TX before removing it

[ Upstream commit 8adbe212a159d9c78a90fca1d854f6e63452426b ]

Make sure that lag port TX is disabled before mlxsw_sp_port_lag_leave()
is called and prevent from possible EMAD error.

Fixes: 0d65fc13042f ("mlxsw: spectrum: Implement LAG port join/leave")
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index f84b9c02fcc5..124aee09e953 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4738,12 +4738,15 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev,
 							   lower_dev,
 							   upper_dev);
 		} else if (netif_is_lag_master(upper_dev)) {
-			if (info->linking)
+			if (info->linking) {
 				err = mlxsw_sp_port_lag_join(mlxsw_sp_port,
 							     upper_dev);
-			else
+			} else {
+				mlxsw_sp_port_lag_tx_en_set(mlxsw_sp_port,
+							    false);
 				mlxsw_sp_port_lag_leave(mlxsw_sp_port,
 							upper_dev);
+			}
 		} else if (netif_is_ovs_master(upper_dev)) {
 			if (info->linking)
 				err = mlxsw_sp_port_ovs_join(mlxsw_sp_port);
-- 
2.20.1


From d97b30b4f0c35aea6f34bc2bd94a502a8e1ddf97 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Tue, 8 Jan 2019 16:48:13 +0000
Subject: [PATCH 03/14] mlxsw: spectrum_switchdev: Set PVID correctly during
 VLAN deletion

[ Upstream commit 674bed5df4cab8f96d04f7b99608883a48f9226b ]

When a VLAN is deleted from a bridge port we should not change the PVID
unless the deleted VLAN is the PVID.

Fixes: fe9ccc785de5 ("mlxsw: spectrum_switchdev: Don't batch VLAN operations")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 50080c60a279..69f556ddb934 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -1816,7 +1816,7 @@ static void
 mlxsw_sp_bridge_port_vlan_del(struct mlxsw_sp_port *mlxsw_sp_port,
 			      struct mlxsw_sp_bridge_port *bridge_port, u16 vid)
 {
-	u16 pvid = mlxsw_sp_port->pvid == vid ? 0 : vid;
+	u16 pvid = mlxsw_sp_port->pvid == vid ? 0 : mlxsw_sp_port->pvid;
 	struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan;
 
 	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid);
-- 
2.20.1


From 7f6a15c9cc669bdd6891ba8fe4e153e0f2d1f538 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Wed, 9 Jan 2019 00:24:03 +0100
Subject: [PATCH 04/14] net: dsa: mv88x6xxx: mv88e6390 errata

[ Upstream commit ea89098ef9a574bceca00d3b5df14aaf0b3f9ccf ]

The 6390 copper ports have an errata which require poking magic values
into undocumented magic registers and then performing a software
reset.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 113 +++++++++++++++++++++++++++++++
 drivers/net/dsa/mv88e6xxx/chip.h |   5 ++
 drivers/net/dsa/mv88e6xxx/port.h |  10 +++
 3 files changed, 128 insertions(+)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 24fb6a685039..b2a0e59b6252 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -2403,6 +2403,107 @@ static int mv88e6xxx_stats_setup(struct mv88e6xxx_chip *chip)
 	return mv88e6xxx_g1_stats_clear(chip);
 }
 
+/* The mv88e6390 has some hidden registers used for debug and
+ * development. The errata also makes use of them.
+ */
+static int mv88e6390_hidden_write(struct mv88e6xxx_chip *chip, int port,
+				  int reg, u16 val)
+{
+	u16 ctrl;
+	int err;
+
+	err = mv88e6xxx_port_write(chip, PORT_RESERVED_1A_DATA_PORT,
+				   PORT_RESERVED_1A, val);
+	if (err)
+		return err;
+
+	ctrl = PORT_RESERVED_1A_BUSY | PORT_RESERVED_1A_WRITE |
+	       PORT_RESERVED_1A_BLOCK | port << PORT_RESERVED_1A_PORT_SHIFT |
+	       reg;
+
+	return mv88e6xxx_port_write(chip, PORT_RESERVED_1A_CTRL_PORT,
+				    PORT_RESERVED_1A, ctrl);
+}
+
+static int mv88e6390_hidden_wait(struct mv88e6xxx_chip *chip)
+{
+	return mv88e6xxx_wait(chip, PORT_RESERVED_1A_CTRL_PORT,
+			      PORT_RESERVED_1A, PORT_RESERVED_1A_BUSY);
+}
+
+
+static int mv88e6390_hidden_read(struct mv88e6xxx_chip *chip, int port,
+				  int reg, u16 *val)
+{
+	u16 ctrl;
+	int err;
+
+	ctrl = PORT_RESERVED_1A_BUSY | PORT_RESERVED_1A_READ |
+	       PORT_RESERVED_1A_BLOCK | port << PORT_RESERVED_1A_PORT_SHIFT |
+	       reg;
+
+	err = mv88e6xxx_port_write(chip, PORT_RESERVED_1A_CTRL_PORT,
+				   PORT_RESERVED_1A, ctrl);
+	if (err)
+		return err;
+
+	err = mv88e6390_hidden_wait(chip);
+	if (err)
+		return err;
+
+	return 	mv88e6xxx_port_read(chip, PORT_RESERVED_1A_DATA_PORT,
+				    PORT_RESERVED_1A, val);
+}
+
+/* Check if the errata has already been applied. */
+static bool mv88e6390_setup_errata_applied(struct mv88e6xxx_chip *chip)
+{
+	int port;
+	int err;
+	u16 val;
+
+	for (port = 0; port < mv88e6xxx_num_ports(chip); port++) {
+		err = mv88e6390_hidden_read(chip, port, 0, &val);
+		if (err) {
+			dev_err(chip->dev,
+				"Error reading hidden register: %d\n", err);
+			return false;
+		}
+		if (val != 0x01c0)
+			return false;
+	}
+
+	return true;
+}
+
+/* The 6390 copper ports have an errata which require poking magic
+ * values into undocumented hidden registers and then performing a
+ * software reset.
+ */
+static int mv88e6390_setup_errata(struct mv88e6xxx_chip *chip)
+{
+	int port;
+	int err;
+
+	if (mv88e6390_setup_errata_applied(chip))
+		return 0;
+
+	/* Set the ports into blocking mode */
+	for (port = 0; port < mv88e6xxx_num_ports(chip); port++) {
+		err = mv88e6xxx_port_set_state(chip, port, BR_STATE_DISABLED);
+		if (err)
+			return err;
+	}
+
+	for (port = 0; port < mv88e6xxx_num_ports(chip); port++) {
+		err = mv88e6390_hidden_write(chip, port, 0, 0x01c0);
+		if (err)
+			return err;
+	}
+
+	return mv88e6xxx_software_reset(chip);
+}
+
 static int mv88e6xxx_setup(struct dsa_switch *ds)
 {
 	struct mv88e6xxx_chip *chip = ds->priv;
@@ -2415,6 +2516,12 @@ static int mv88e6xxx_setup(struct dsa_switch *ds)
 
 	mutex_lock(&chip->reg_lock);
 
+	if (chip->info->ops->setup_errata) {
+		err = chip->info->ops->setup_errata(chip);
+		if (err)
+			goto unlock;
+	}
+
 	/* Cache the cmode of each port. */
 	for (i = 0; i < mv88e6xxx_num_ports(chip); i++) {
 		if (chip->info->ops->port_get_cmode) {
@@ -3215,6 +3322,7 @@ static const struct mv88e6xxx_ops mv88e6185_ops = {
 
 static const struct mv88e6xxx_ops mv88e6190_ops = {
 	/* MV88E6XXX_FAMILY_6390 */
+	.setup_errata = mv88e6390_setup_errata,
 	.irl_init_all = mv88e6390_g2_irl_init_all,
 	.get_eeprom = mv88e6xxx_g2_get_eeprom8,
 	.set_eeprom = mv88e6xxx_g2_set_eeprom8,
@@ -3257,6 +3365,7 @@ static const struct mv88e6xxx_ops mv88e6190_ops = {
 
 static const struct mv88e6xxx_ops mv88e6190x_ops = {
 	/* MV88E6XXX_FAMILY_6390 */
+	.setup_errata = mv88e6390_setup_errata,
 	.irl_init_all = mv88e6390_g2_irl_init_all,
 	.get_eeprom = mv88e6xxx_g2_get_eeprom8,
 	.set_eeprom = mv88e6xxx_g2_set_eeprom8,
@@ -3299,6 +3408,7 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = {
 
 static const struct mv88e6xxx_ops mv88e6191_ops = {
 	/* MV88E6XXX_FAMILY_6390 */
+	.setup_errata = mv88e6390_setup_errata,
 	.irl_init_all = mv88e6390_g2_irl_init_all,
 	.get_eeprom = mv88e6xxx_g2_get_eeprom8,
 	.set_eeprom = mv88e6xxx_g2_set_eeprom8,
@@ -3390,6 +3500,7 @@ static const struct mv88e6xxx_ops mv88e6240_ops = {
 
 static const struct mv88e6xxx_ops mv88e6290_ops = {
 	/* MV88E6XXX_FAMILY_6390 */
+	.setup_errata = mv88e6390_setup_errata,
 	.irl_init_all = mv88e6390_g2_irl_init_all,
 	.get_eeprom = mv88e6xxx_g2_get_eeprom8,
 	.set_eeprom = mv88e6xxx_g2_set_eeprom8,
@@ -3693,6 +3804,7 @@ static const struct mv88e6xxx_ops mv88e6352_ops = {
 
 static const struct mv88e6xxx_ops mv88e6390_ops = {
 	/* MV88E6XXX_FAMILY_6390 */
+	.setup_errata = mv88e6390_setup_errata,
 	.irl_init_all = mv88e6390_g2_irl_init_all,
 	.get_eeprom = mv88e6xxx_g2_get_eeprom8,
 	.set_eeprom = mv88e6xxx_g2_set_eeprom8,
@@ -3740,6 +3852,7 @@ static const struct mv88e6xxx_ops mv88e6390_ops = {
 
 static const struct mv88e6xxx_ops mv88e6390x_ops = {
 	/* MV88E6XXX_FAMILY_6390 */
+	.setup_errata = mv88e6390_setup_errata,
 	.irl_init_all = mv88e6390_g2_irl_init_all,
 	.get_eeprom = mv88e6xxx_g2_get_eeprom8,
 	.set_eeprom = mv88e6xxx_g2_set_eeprom8,
diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h
index f9ecb7872d32..546651d8c3e1 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.h
+++ b/drivers/net/dsa/mv88e6xxx/chip.h
@@ -300,6 +300,11 @@ struct mv88e6xxx_mdio_bus {
 };
 
 struct mv88e6xxx_ops {
+	/* Switch Setup Errata, called early in the switch setup to
+	 * allow any errata actions to be performed
+	 */
+	int (*setup_errata)(struct mv88e6xxx_chip *chip);
+
 	int (*ieee_pri_map)(struct mv88e6xxx_chip *chip);
 	int (*ip_pri_map)(struct mv88e6xxx_chip *chip);
 
diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h
index 36904c9bf955..091aa0057f1f 100644
--- a/drivers/net/dsa/mv88e6xxx/port.h
+++ b/drivers/net/dsa/mv88e6xxx/port.h
@@ -251,6 +251,16 @@
 /* Offset 0x19: Port IEEE Priority Remapping Registers (4-7) */
 #define MV88E6095_PORT_IEEE_PRIO_REMAP_4567	0x19
 
+/* Offset 0x1a: Magic undocumented errata register */
+#define PORT_RESERVED_1A			0x1a
+#define PORT_RESERVED_1A_BUSY			BIT(15)
+#define PORT_RESERVED_1A_WRITE			BIT(14)
+#define PORT_RESERVED_1A_READ			0
+#define PORT_RESERVED_1A_PORT_SHIFT		5
+#define PORT_RESERVED_1A_BLOCK			(0xf << 10)
+#define PORT_RESERVED_1A_CTRL_PORT		4
+#define PORT_RESERVED_1A_DATA_PORT		5
+
 int mv88e6xxx_port_read(struct mv88e6xxx_chip *chip, int port, int reg,
 			u16 *val);
 int mv88e6xxx_port_write(struct mv88e6xxx_chip *chip, int port, int reg,
-- 
2.20.1


From fa6d0875491dbf65ed30346f52138f4ad2b125f2 Mon Sep 17 00:00:00 2001
From: David Rientjes <rientjes@google.com>
Date: Wed, 2 Jan 2019 13:01:43 -0800
Subject: [PATCH 05/14] net, skbuff: do not prefer skb allocation fails early

[ Upstream commit f8c468e8537925e0c4607263f498a1b7c0c8982e ]

Commit dcda9b04713c ("mm, tree wide: replace __GFP_REPEAT by
__GFP_RETRY_MAYFAIL with more useful semantic") replaced __GFP_REPEAT in
alloc_skb_with_frags() with __GFP_RETRY_MAYFAIL when the allocation may
directly reclaim.

The previous behavior would require reclaim up to 1 << order pages for
skb aligned header_len of order > PAGE_ALLOC_COSTLY_ORDER before failing,
otherwise the allocations in alloc_skb() would loop in the page allocator
looking for memory.  __GFP_RETRY_MAYFAIL makes both allocations failable
under memory pressure, including for the HEAD allocation.

This can cause, among many other things, write() to fail with ENOTCONN
during RPC when under memory pressure.

These allocations should succeed as they did previous to dcda9b04713c
even if it requires calling the oom killer and additional looping in the
page allocator to find memory.  There is no way to specify the previous
behavior of __GFP_REPEAT, but it's unlikely to be necessary since the
previous behavior only guaranteed that 1 << order pages would be reclaimed
before failing for order > PAGE_ALLOC_COSTLY_ORDER.  That reclaim is not
guaranteed to be contiguous memory, so repeating for such large orders is
usually not beneficial.

Removing the setting of __GFP_RETRY_MAYFAIL to restore the previous
behavior, specifically not allowing alloc_skb() to fail for small orders
and oom kill if necessary rather than allowing RPCs to fail.

Fixes: dcda9b04713c ("mm, tree wide: replace __GFP_REPEAT by __GFP_RETRY_MAYFAIL with more useful semantic")
Signed-off-by: David Rientjes <rientjes@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index a8217e221e19..eebc3106d30e 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5202,7 +5202,6 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len,
 	unsigned long chunk;
 	struct sk_buff *skb;
 	struct page *page;
-	gfp_t gfp_head;
 	int i;
 
 	*errcode = -EMSGSIZE;
@@ -5212,12 +5211,8 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len,
 	if (npages > MAX_SKB_FRAGS)
 		return NULL;
 
-	gfp_head = gfp_mask;
-	if (gfp_head & __GFP_DIRECT_RECLAIM)
-		gfp_head |= __GFP_RETRY_MAYFAIL;
-
 	*errcode = -ENOBUFS;
-	skb = alloc_skb(header_len, gfp_head);
+	skb = alloc_skb(header_len, gfp_mask);
 	if (!skb)
 		return NULL;
 
-- 
2.20.1


From d755af4943d0f20fc95a2287222af660afddf142 Mon Sep 17 00:00:00 2001
From: Daniele Palmas <dnlplm@gmail.com>
Date: Fri, 4 Jan 2019 13:26:10 +0100
Subject: [PATCH 06/14] qmi_wwan: add MTU default to qmap network interface
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit f87118d5760f00af7228033fbe783c7f380d2866 ]

This patch adds MTU default value to qmap network interface in
order to avoid "RTNETLINK answers: No buffer space available"
error when setting an ipv6 address.

Signed-off-by: Daniele Palmas <dnlplm@gmail.com>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 774e1ff01c9a..735ad838e2ba 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -123,6 +123,7 @@ static void qmimux_setup(struct net_device *dev)
 	dev->addr_len        = 0;
 	dev->flags           = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST;
 	dev->netdev_ops      = &qmimux_netdev_ops;
+	dev->mtu             = 1500;
 	dev->needs_free_netdev = true;
 }
 
-- 
2.20.1


From d94f650878040b82ebbee8b7bc85164055b72209 Mon Sep 17 00:00:00 2001
From: Kai-Heng Feng <kai.heng.feng@canonical.com>
Date: Wed, 2 Jan 2019 14:45:07 +0800
Subject: [PATCH 07/14] r8169: Add support for new Realtek Ethernet

[ Upstream commit 36352991835ce99e46b4441dd0eb6980f9a83e8f ]

There are two new Realtek Ethernet devices which are re-branded r8168h.
Add the IDs to to support them.

Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Reviewed-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 209566f8097b..e30b8cdfe986 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -212,6 +212,8 @@ enum cfg_version {
 };
 
 static const struct pci_device_id rtl8169_pci_tbl[] = {
+	{ PCI_VDEVICE(REALTEK,	0x2502), RTL_CFG_1 },
+	{ PCI_VDEVICE(REALTEK,	0x2600), RTL_CFG_1 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8129), 0, 0, RTL_CFG_0 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8136), 0, 0, RTL_CFG_2 },
 	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8161), 0, 0, RTL_CFG_1 },
-- 
2.20.1


From d9a8ad2bff4bcbfbea47fb9b39ceb862394fc536 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Sat, 5 Jan 2019 07:35:04 -0800
Subject: [PATCH 08/14] ipv6: Take rcu_read_lock in __inet6_bind for mapped
 addresses

[ Upstream commit d4a7e9bb74b5aaf07b89f6531c080b1130bdf019 ]

I realized the last patch calls dev_get_by_index_rcu in a branch not
holding the rcu lock. Add the calls to rcu_read_lock and rcu_read_unlock.

Fixes: ec90ad334986 ("ipv6: Consider sk_bound_dev_if when binding a socket to a v4 mapped address")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/af_inet6.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 63d154578955..4dc935838184 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -321,17 +321,20 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
 			goto out;
 		}
 
+		rcu_read_lock();
 		if (sk->sk_bound_dev_if) {
 			dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if);
 			if (!dev) {
 				err = -ENODEV;
-				goto out;
+				goto out_unlock;
 			}
 		}
 
 		/* Reproduce AF_INET checks to make the bindings consistent */
 		v4addr = addr->sin6_addr.s6_addr32[3];
 		chk_addr_ret = inet_addr_type_dev_table(net, dev, v4addr);
+		rcu_read_unlock();
+
 		if (!inet_can_nonlocal_bind(net, inet) &&
 		    v4addr != htonl(INADDR_ANY) &&
 		    chk_addr_ret != RTN_LOCAL &&
-- 
2.20.1


From ca52d17da9b797164719a68df68f67e8d5ef2f39 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 2 Jan 2019 18:26:13 -0800
Subject: [PATCH 09/14] ipv6: Fix dump of specific table with strict checking

[ Upstream commit 73155879b3c1ac3ace35208a54a3a160ec520bef ]

Dump of a specific table with strict checking enabled is looping. The
problem is that the end of the table dump is not marked in the cb. When
dumping a specific table, cb args 0 and 1 are not used (they are the hash
index and entry with an hash table index when dumping all tables). Re-use
args[0] to hold a 'done' flag for the specific table dump.

Fixes: 13e38901d46ca ("net/ipv6: Plumb support for filtering route dumps")
Reported-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_fib.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index ae3786132c23..6613d8dbb0e5 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -627,7 +627,11 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 			return -ENOENT;
 		}
 
-		res = fib6_dump_table(tb, skb, cb);
+		if (!cb->args[0]) {
+			res = fib6_dump_table(tb, skb, cb);
+			if (!res)
+				cb->args[0] = 1;
+		}
 		goto out;
 	}
 
-- 
2.20.1


From 75afea3ae3d8ec5b7c6026f44cd76897d1e5969f Mon Sep 17 00:00:00 2001
From: Arthur Gautier <baloo@gandi.net>
Date: Mon, 31 Dec 2018 02:10:58 +0000
Subject: [PATCH 10/14] netlink: fixup regression in RTM_GETADDR

[ Upstream commit 7c1e8a3817c55d73b27cc29b84075999c8894179 ]

This commit fixes a regression in AF_INET/RTM_GETADDR and
AF_INET6/RTM_GETADDR.

Before this commit, the kernel would stop dumping addresses once the first
skb was full and end the stream with NLMSG_DONE(-EMSGSIZE). The error
shouldn't be sent back to netlink_dump so the callback is kept alive. The
userspace is expected to call back with a new empty skb.

Changes from V1:
 - The error is not handled in netlink_dump anymore but rather in
   inet_dump_ifaddr and inet6_dump_addr directly as suggested by
   David Ahern.

Fixes: d7e38611b81e ("net/ipv4: Put target net when address dump fails due to bad attributes")
Fixes: 242afaa6968c ("net/ipv6: Put target net when address dump fails due to bad attributes")

Cc: David Ahern <dsahern@gmail.com>
Cc: "David S . Miller" <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Arthur Gautier <baloo@gandi.net>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/devinet.c  | 2 +-
 net/ipv6/addrconf.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 608a6f4223fb..fecd0e7672b5 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1826,7 +1826,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
 	if (fillargs.netnsid >= 0)
 		put_net(tgt_net);
 
-	return err < 0 ? err : skb->len;
+	return skb->len ? : err;
 }
 
 static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh,
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 045597b9a7c0..e3cb53b0ef67 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5154,7 +5154,7 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb,
 	if (fillargs.netnsid >= 0)
 		put_net(tgt_net);
 
-	return err < 0 ? err : skb->len;
+	return skb->len ? : err;
 }
 
 static int inet6_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
-- 
2.20.1


From 2b97954dbe60d038bf10b3f7996cf71f072f2890 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sat, 29 Dec 2018 17:42:22 +0100
Subject: [PATCH 11/14] octeontx2-af: Fix a resource leak in an error handling
 path in 'cgx_probe()'

[ Upstream commit 1492623e837fe7ca6296f7f5411328307e242771 ]

If an error occurs after the call to 'pci_alloc_irq_vectors()', we must
call 'pci_free_irq_vectors()' in order to avoid a	resource leak.

The same sequence is already in place in the corresponding 'cgx_remove()'
function.

Fixes: 1463f382f58d ("octeontx2-af: Add support for CGX link management")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/cgx.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
index 12db256c8c9f..ee67d1c4281d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
@@ -668,7 +668,7 @@ static int cgx_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (!cgx->reg_base) {
 		dev_err(dev, "CGX: Cannot map CSR memory space, aborting\n");
 		err = -ENOMEM;
-		goto err_release_regions;
+		goto err_free_irq_vectors;
 	}
 
 	nvec = CGX_NVEC;
@@ -693,6 +693,8 @@ static int cgx_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 err_release_lmac:
 	cgx_lmac_exit(cgx);
 	list_del(&cgx->cgx_list);
+err_free_irq_vectors:
+	pci_free_irq_vectors(pdev);
 err_release_regions:
 	pci_release_regions(pdev);
 err_disable_device:
-- 
2.20.1


From d1587921531fdfc82f223ca9ff63a27c87e734de Mon Sep 17 00:00:00 2001
From: Yi-Hung Wei <yihung.wei@gmail.com>
Date: Thu, 3 Jan 2019 09:51:57 -0800
Subject: [PATCH 12/14] openvswitch: Fix IPv6 later frags parsing

[ Upstream commit 41e4e2cd75346667b0c531c07dab05cce5b06d15 ]

The previous commit fa642f08839b
("openvswitch: Derive IP protocol number for IPv6 later frags")
introduces IP protocol number parsing for IPv6 later frags that can mess
up the network header length calculation logic, i.e. nh_len < 0.
However, the network header length calculation is mainly for deriving
the transport layer header in the key extraction process which the later
fragment does not apply.

Therefore, this commit skips the network header length calculation to
fix the issue.

Reported-by: Chris Mi <chrism@mellanox.com>
Reported-by: Greg Rose <gvrose8192@gmail.com>
Fixes: fa642f08839b ("openvswitch: Derive IP protocol number for IPv6 later frags")
Signed-off-by: Yi-Hung Wei <yihung.wei@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/flow.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 35966da84769..f920a347ee1c 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -276,10 +276,12 @@ static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key)
 
 	nexthdr = ipv6_find_hdr(skb, &payload_ofs, -1, &frag_off, &flags);
 	if (flags & IP6_FH_F_FRAG) {
-		if (frag_off)
+		if (frag_off) {
 			key->ip.frag = OVS_FRAG_TYPE_LATER;
-		else
-			key->ip.frag = OVS_FRAG_TYPE_FIRST;
+			key->ip.proto = nexthdr;
+			return 0;
+		}
+		key->ip.frag = OVS_FRAG_TYPE_FIRST;
 	} else {
 		key->ip.frag = OVS_FRAG_TYPE_NONE;
 	}
-- 
2.20.1


From a7f1587d9662bc4a2290561356eeee891b99f30c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 4 Jan 2019 11:00:00 -0800
Subject: [PATCH 13/14] ipv6: make icmp6_send() robust against null skb->dev

[ Upstream commit 8d933670452107e41165bea70a30dffbd281bef1 ]

syzbot was able to crash one host with the following stack trace :

kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] PREEMPT SMP KASAN
CPU: 0 PID: 8625 Comm: syz-executor4 Not tainted 4.20.0+ #8
RIP: 0010:dev_net include/linux/netdevice.h:2169 [inline]
RIP: 0010:icmp6_send+0x116/0x2d30 net/ipv6/icmp.c:426
 icmpv6_send
 smack_socket_sock_rcv_skb
 security_sock_rcv_skb
 sk_filter_trim_cap
 __sk_receive_skb
 dccp_v6_do_rcv
 release_sock

This is because a RX packet found socket owned by user and
was stored into socket backlog. Before leaving RCU protected section,
skb->dev was cleared in __sk_receive_skb(). When socket backlog
was finally handled at release_sock() time, skb was fed to
smack_socket_sock_rcv_skb() then icmp6_send()

We could fix the bug in smack_socket_sock_rcv_skb(), or simply
make icmp6_send() more robust against such possibility.

In the future we might provide to icmp6_send() the net pointer
instead of infering it.

Fixes: d66a8acbda92 ("Smack: Inform peer that IPv6 traffic has been blocked")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Piotr Sawicki <p.sawicki2@partner.samsung.com>
Cc: Casey Schaufler <casey@schaufler-ca.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: Casey Schaufler <casey@schaufler-ca.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/icmp.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index c9c53ade55c3..6d14cbe443f8 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -421,10 +421,10 @@ static int icmp6_iif(const struct sk_buff *skb)
 static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 		       const struct in6_addr *force_saddr)
 {
-	struct net *net = dev_net(skb->dev);
 	struct inet6_dev *idev = NULL;
 	struct ipv6hdr *hdr = ipv6_hdr(skb);
 	struct sock *sk;
+	struct net *net;
 	struct ipv6_pinfo *np;
 	const struct in6_addr *saddr = NULL;
 	struct dst_entry *dst;
@@ -435,12 +435,16 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 	int iif = 0;
 	int addr_type = 0;
 	int len;
-	u32 mark = IP6_REPLY_MARK(net, skb->mark);
+	u32 mark;
 
 	if ((u8 *)hdr < skb->head ||
 	    (skb_network_header(skb) + sizeof(*hdr)) > skb_tail_pointer(skb))
 		return;
 
+	if (!skb->dev)
+		return;
+	net = dev_net(skb->dev);
+	mark = IP6_REPLY_MARK(net, skb->mark);
 	/*
 	 *	Make sure we respect the rules
 	 *	i.e. RFC 1885 2.4(e)
-- 
2.20.1


From 164c9d7b534c5a0c41f0d26f11a70a7fdaf41acc Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 8 Jan 2019 18:45:05 +0100
Subject: [PATCH 14/14] net: clear skb->tstamp in bridge forwarding path

[ Upstream commit 41d1c8839e5f8cb781cc635f12791decee8271b7 ]

Matteo reported forwarding issues inside the linux bridge,
if the enslaved interfaces use the fq qdisc.

Similar to commit 8203e2d844d3 ("net: clear skb->tstamp in
forwarding paths"), we need to clear the tstamp field in
the bridge forwarding path.

Fixes: 80b14dee2bea ("net: Add a new socket option for a future transmit time.")
Fixes: fb420d5d91c1 ("tcp/fq: move back to CLOCK_MONOTONIC")
Reported-and-tested-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Acked-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_forward.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 5372e2042adf..2cb8da465b98 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -65,6 +65,7 @@ EXPORT_SYMBOL_GPL(br_dev_queue_push_xmit);
 
 int br_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
+	skb->tstamp = 0;
 	return NF_HOOK(NFPROTO_BRIDGE, NF_BR_POST_ROUTING,
 		       net, sk, skb, NULL, skb->dev,
 		       br_dev_queue_push_xmit);
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Mon, Jan 21, 2019 at 03:28:01PM -0800, David Miller wrote:
> 
> Another day, another batch of networking fixes.
> 
> Please queue up for v4.19 and v4.20 -stable, respectively.

Thanks for these, I'll queue them up in a few days.

greg k-h

Re: [PATCHES] Networking

[Greg KH]

On Mon, Jan 21, 2019 at 03:28:01PM -0800, David Miller wrote:
> 
> Another day, another batch of networking fixes.
> 
> Please queue up for v4.19 and v4.20 -stable, respectively.

All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 91 bytes --]


Please queue up the following bug fixes for 4.19 and 4.20 -stable,
respectively.

Thanks!

[-- Attachment #2: net_419.mbox --]
[-- Type: Application/Octet-Stream, Size: 63006 bytes --]

From 5f3d2ba4fa5f70d5441f26b807c45f6336c8e50a Mon Sep 17 00:00:00 2001
From: "Lendacky, Thomas" <Thomas.Lendacky@amd.com>
Date: Thu, 17 Jan 2019 14:20:14 +0000
Subject: [PATCH 01/21] amd-xgbe: Fix mdio access for non-zero ports and clause
 45 PHYs

[ Upstream commit 5ab3121beeb76aa6090195b67d237115860dd9ec ]

The XGBE hardware has support for performing MDIO operations using an
MDIO command request. The driver mistakenly uses the mdio port address
as the MDIO command request device address instead of the MDIO command
request port address. Additionally, the driver does not properly check
for and create a clause 45 MDIO command.

Check the supplied MDIO register to determine if the request is a clause
45 operation (MII_ADDR_C45). For a clause 45 operation, extract the device
address and register number from the supplied MDIO register and use them
to set the MDIO command request device address and register number fields.
For a clause 22 operation, the MDIO request device address is set to zero
and the MDIO command request register number is set to the supplied MDIO
register. In either case, the supplied MDIO port address is used as the
MDIO command request port address.

Fixes: 732f2ab7afb9 ("amd-xgbe: Add support for MDIO attached PHYs")
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Tested-by: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe-common.h |  2 --
 drivers/net/ethernet/amd/xgbe/xgbe-dev.c    | 22 +++++++++++++++------
 2 files changed, 16 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
index d272dc6984ac..b40d4377cc71 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
@@ -431,8 +431,6 @@
 #define MAC_MDIOSCAR_PA_WIDTH		5
 #define MAC_MDIOSCAR_RA_INDEX		0
 #define MAC_MDIOSCAR_RA_WIDTH		16
-#define MAC_MDIOSCAR_REG_INDEX		0
-#define MAC_MDIOSCAR_REG_WIDTH		21
 #define MAC_MDIOSCCDR_BUSY_INDEX	22
 #define MAC_MDIOSCCDR_BUSY_WIDTH	1
 #define MAC_MDIOSCCDR_CMD_INDEX		16
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
index 1e929a1e4ca7..4666084eda16 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
@@ -1284,6 +1284,20 @@ static void xgbe_write_mmd_regs(struct xgbe_prv_data *pdata, int prtad,
 	}
 }
 
+static unsigned int xgbe_create_mdio_sca(int port, int reg)
+{
+	unsigned int mdio_sca, da;
+
+	da = (reg & MII_ADDR_C45) ? reg >> 16 : 0;
+
+	mdio_sca = 0;
+	XGMAC_SET_BITS(mdio_sca, MAC_MDIOSCAR, RA, reg);
+	XGMAC_SET_BITS(mdio_sca, MAC_MDIOSCAR, PA, port);
+	XGMAC_SET_BITS(mdio_sca, MAC_MDIOSCAR, DA, da);
+
+	return mdio_sca;
+}
+
 static int xgbe_write_ext_mii_regs(struct xgbe_prv_data *pdata, int addr,
 				   int reg, u16 val)
 {
@@ -1291,9 +1305,7 @@ static int xgbe_write_ext_mii_regs(struct xgbe_prv_data *pdata, int addr,
 
 	reinit_completion(&pdata->mdio_complete);
 
-	mdio_sca = 0;
-	XGMAC_SET_BITS(mdio_sca, MAC_MDIOSCAR, REG, reg);
-	XGMAC_SET_BITS(mdio_sca, MAC_MDIOSCAR, DA, addr);
+	mdio_sca = xgbe_create_mdio_sca(addr, reg);
 	XGMAC_IOWRITE(pdata, MAC_MDIOSCAR, mdio_sca);
 
 	mdio_sccd = 0;
@@ -1317,9 +1329,7 @@ static int xgbe_read_ext_mii_regs(struct xgbe_prv_data *pdata, int addr,
 
 	reinit_completion(&pdata->mdio_complete);
 
-	mdio_sca = 0;
-	XGMAC_SET_BITS(mdio_sca, MAC_MDIOSCAR, REG, reg);
-	XGMAC_SET_BITS(mdio_sca, MAC_MDIOSCAR, DA, addr);
+	mdio_sca = xgbe_create_mdio_sca(addr, reg);
 	XGMAC_IOWRITE(pdata, MAC_MDIOSCAR, mdio_sca);
 
 	mdio_sccd = 0;
-- 
2.20.1


From 708662f90570ae3129434f1acce1e4a5e02bc761 Mon Sep 17 00:00:00 2001
From: Yunjian Wang <wangyunjian@huawei.com>
Date: Thu, 17 Jan 2019 09:46:41 +0800
Subject: [PATCH 02/21] net: bridge: Fix ethernet header pointer before check
 skb forwardable

[ Upstream commit 28c1382fa28f2e2d9d0d6f25ae879b5af2ecbd03 ]

The skb header should be set to ethernet header before using
is_skb_forwardable. Because the ethernet header length has been
considered in is_skb_forwardable(including dev->hard_header_len
length).

To reproduce the issue:
1, add 2 ports on linux bridge br using following commands:
$ brctl addbr br
$ brctl addif br eth0
$ brctl addif br eth1
2, the MTU of eth0 and eth1 is 1500
3, send a packet(Data 1480, UDP 8, IP 20, Ethernet 14, VLAN 4)
from eth0 to eth1

So the expect result is packet larger than 1500 cannot pass through
eth0 and eth1. But currently, the packet passes through success, it
means eth1's MTU limit doesn't take effect.

Fixes: f6367b4660dd ("bridge: use is_skb_forwardable in forward path")
Cc: bridge@lists.linux-foundation.org
Cc: Nkolay Aleksandrov <nikolay@cumulusnetworks.com>
Cc: Roopa Prabhu <roopa@cumulusnetworks.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_forward.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 5372e2042adf..d0f26696f2fd 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -36,10 +36,10 @@ static inline int should_deliver(const struct net_bridge_port *p,
 
 int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
+	skb_push(skb, ETH_HLEN);
 	if (!is_skb_forwardable(skb->dev, skb))
 		goto drop;
 
-	skb_push(skb, ETH_HLEN);
 	br_drop_fake_rtable(skb);
 
 	if (skb->ip_summed == CHECKSUM_PARTIAL &&
@@ -97,12 +97,11 @@ static void __br_forward(const struct net_bridge_port *to,
 		net = dev_net(indev);
 	} else {
 		if (unlikely(netpoll_tx_running(to->br->dev))) {
-			if (!is_skb_forwardable(skb->dev, skb)) {
+			skb_push(skb, ETH_HLEN);
+			if (!is_skb_forwardable(skb->dev, skb))
 				kfree_skb(skb);
-			} else {
-				skb_push(skb, ETH_HLEN);
+			else
 				br_netpoll_send_skb(to, skb);
-			}
 			return;
 		}
 		br_hook = NF_BR_LOCAL_OUT;
-- 
2.20.1


From 048f73e23e981cd328d126e5a50a40fb32b88204 Mon Sep 17 00:00:00 2001
From: Ross Lagerwall <ross.lagerwall@citrix.com>
Date: Thu, 17 Jan 2019 15:34:38 +0000
Subject: [PATCH 03/21] net: Fix usage of pskb_trim_rcsum

[ Upstream commit 6c57f0458022298e4da1729c67bd33ce41c14e7a ]

In certain cases, pskb_trim_rcsum() may change skb pointers.
Reinitialize header pointers afterwards to avoid potential
use-after-frees. Add a note in the documentation of
pskb_trim_rcsum(). Found by KASAN.

Signed-off-by: Ross Lagerwall <ross.lagerwall@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pppoe.c                  | 1 +
 include/linux/skbuff.h                   | 1 +
 net/bridge/br_netfilter_ipv6.c           | 1 +
 net/bridge/netfilter/nft_reject_bridge.c | 1 +
 net/ipv4/ip_input.c                      | 1 +
 5 files changed, 5 insertions(+)

diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 62dc564b251d..f22639f0116a 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -445,6 +445,7 @@ static int pppoe_rcv(struct sk_buff *skb, struct net_device *dev,
 	if (pskb_trim_rcsum(skb, len))
 		goto drop;
 
+	ph = pppoe_hdr(skb);
 	pn = pppoe_pernet(dev_net(dev));
 
 	/* Note that get_item does a sock_hold(), so sk_pppox(po)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 60a2e7646985..5d69e208e8d9 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3178,6 +3178,7 @@ int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len);
  *
  *	This is exactly the same as pskb_trim except that it ensures the
  *	checksum of received packets are still valid after the operation.
+ *	It can change skb pointers.
  */
 
 static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len)
diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c
index 96c072e71ea2..5811208863b7 100644
--- a/net/bridge/br_netfilter_ipv6.c
+++ b/net/bridge/br_netfilter_ipv6.c
@@ -131,6 +131,7 @@ int br_validate_ipv6(struct net *net, struct sk_buff *skb)
 					IPSTATS_MIB_INDISCARDS);
 			goto drop;
 		}
+		hdr = ipv6_hdr(skb);
 	}
 	if (hdr->nexthdr == NEXTHDR_HOP && br_nf_check_hbh_len(skb))
 		goto drop;
diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c
index 08cbed7d940e..419e8edf23ba 100644
--- a/net/bridge/netfilter/nft_reject_bridge.c
+++ b/net/bridge/netfilter/nft_reject_bridge.c
@@ -229,6 +229,7 @@ static bool reject6_br_csum_ok(struct sk_buff *skb, int hook)
 	    pskb_trim_rcsum(skb, ntohs(ip6h->payload_len) + sizeof(*ip6h)))
 		return false;
 
+	ip6h = ipv6_hdr(skb);
 	thoff = ipv6_skip_exthdr(skb, ((u8*)(ip6h+1) - skb->data), &proto, &fo);
 	if (thoff < 0 || thoff >= skb->len || (fo & htons(~0x7)) != 0)
 		return false;
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 27c863f6dd83..6f977b0fef54 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -489,6 +489,7 @@ static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net)
 		goto drop;
 	}
 
+	iph = ip_hdr(skb);
 	skb->transport_header = skb->network_header + iph->ihl*4;
 
 	/* Remove any debris in the socket control block */
-- 
2.20.1


From 85c3fbf64160bbe4525dc231a02c53a6f113da4d Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Thu, 10 Jan 2019 22:48:36 +0100
Subject: [PATCH 04/21] net: phy: marvell: Errata for mv88e6390 internal PHYs

[ Upstream commit 8cbcdc1a51999ca81db2956608b917aacd28d837 ]

The VOD can be out of spec, unless some magic value is poked into an
undocumented register in an undocumented page.

Fixes: e4cf8a38fc0d ("net: phy: Marvell: Add mv88e6390 internal PHY")
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/marvell.c | 35 ++++++++++++++++++++++++++++++++++-
 1 file changed, 34 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index f7c69ca34056..b3aa0027c0ff 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -1063,6 +1063,39 @@ static int m88e1145_config_init(struct phy_device *phydev)
 	return 0;
 }
 
+/* The VOD can be out of specification on link up. Poke an
+ * undocumented register, in an undocumented page, with a magic value
+ * to fix this.
+ */
+static int m88e6390_errata(struct phy_device *phydev)
+{
+	int err;
+
+	err = phy_write(phydev, MII_BMCR,
+			BMCR_ANENABLE | BMCR_SPEED1000 | BMCR_FULLDPLX);
+	if (err)
+		return err;
+
+	usleep_range(300, 400);
+
+	err = phy_write_paged(phydev, 0xf8, 0x08, 0x36);
+	if (err)
+		return err;
+
+	return genphy_soft_reset(phydev);
+}
+
+static int m88e6390_config_aneg(struct phy_device *phydev)
+{
+	int err;
+
+	err = m88e6390_errata(phydev);
+	if (err)
+		return err;
+
+	return m88e1510_config_aneg(phydev);
+}
+
 /**
  * fiber_lpa_to_ethtool_lpa_t
  * @lpa: value of the MII_LPA register for fiber link
@@ -2313,7 +2346,7 @@ static struct phy_driver marvell_drivers[] = {
 		.flags = PHY_HAS_INTERRUPT,
 		.probe = m88e6390_probe,
 		.config_init = &marvell_config_init,
-		.config_aneg = &m88e1510_config_aneg,
+		.config_aneg = &m88e6390_config_aneg,
 		.read_status = &marvell_read_status,
 		.ack_interrupt = &marvell_ack_interrupt,
 		.config_intr = &marvell_config_intr,
-- 
2.20.1


From 0dd1b92d37d9b853e7717ff3ea7a52eecf9510cb Mon Sep 17 00:00:00 2001
From: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
Date: Wed, 16 Jan 2019 10:53:58 +0100
Subject: [PATCH 05/21] net: phy: mdio_bus: add missing device_del() in
 mdiobus_register() error handling

[ Upstream commit e40e2a2e78664fa90ea4b9bdf4a84efce2fea9d9 ]

The current code in __mdiobus_register() doesn't properly handle
failures returned by the devm_gpiod_get_optional() call: it returns
immediately, without unregistering the device that was added by the
call to device_register() earlier in the function.

This leaves a stale device, which then causes a NULL pointer
dereference in the code that handles deferred probing:

[    1.489982] Unable to handle kernel NULL pointer dereference at virtual address 00000074
[    1.498110] pgd = (ptrval)
[    1.500838] [00000074] *pgd=00000000
[    1.504432] Internal error: Oops: 17 [#1] SMP ARM
[    1.509133] Modules linked in:
[    1.512192] CPU: 1 PID: 51 Comm: kworker/1:3 Not tainted 4.20.0-00039-g3b73a4cc8b3e-dirty #99
[    1.520708] Hardware name: Xilinx Zynq Platform
[    1.525261] Workqueue: events deferred_probe_work_func
[    1.530403] PC is at klist_next+0x10/0xfc
[    1.534403] LR is at device_for_each_child+0x40/0x94
[    1.539361] pc : [<c0683fbc>]    lr : [<c0455d90>]    psr: 200e0013
[    1.545628] sp : ceeefe68  ip : 00000001  fp : ffffe000
[    1.550863] r10: 00000000  r9 : c0c66790  r8 : 00000000
[    1.556079] r7 : c0457d44  r6 : 00000000  r5 : ceeefe8c  r4 : cfa2ec78
[    1.562604] r3 : 00000064  r2 : c0457d44  r1 : ceeefe8c  r0 : 00000064
[    1.569129] Flags: nzCv  IRQs on  FIQs on  Mode SVC_32  ISA ARM  Segment none
[    1.576263] Control: 18c5387d  Table: 0ed7804a  DAC: 00000051
[    1.582013] Process kworker/1:3 (pid: 51, stack limit = 0x(ptrval))
[    1.588280] Stack: (0xceeefe68 to 0xceef0000)
[    1.592630] fe60:                   cfa2ec78 c0c03c08 00000000 c0457d44 00000000 c0c66790
[    1.600814] fe80: 00000000 c0455d90 ceeefeac 00000064 00000000 0d7a542e cee9d494 cfa2ec78
[    1.608998] fea0: cfa2ec78 00000000 c0457d44 c0457d7c cee9d494 c0c03c08 00000000 c0455dac
[    1.617182] fec0: cf98ba44 cf926a00 cee9d494 0d7a542e 00000000 cf935a10 cf935a10 cf935a10
[    1.625366] fee0: c0c4e9b8 c0457d7c c0c4e80c 00000001 cf935a10 c0457df4 cf935a10 c0c4e99c
[    1.633550] ff00: c0c4e99c c045a27c c0c4e9c4 ced63f80 cfde8a80 cfdebc00 00000000 c013893c
[    1.641734] ff20: cfde8a80 cfde8a80 c07bd354 ced63f80 ced63f94 cfde8a80 00000008 c0c02d00
[    1.649936] ff40: cfde8a98 cfde8a80 ffffe000 c0139a30 ffffe000 c0c6624a c07bd354 00000000
[    1.658120] ff60: ffffe000 cee9e780 ceebfe00 00000000 ceeee000 ced63f80 c0139788 cf8cdea4
[    1.666304] ff80: cee9e79c c013e598 00000001 ceebfe00 c013e44c 00000000 00000000 00000000
[    1.674488] ffa0: 00000000 00000000 00000000 c01010e8 00000000 00000000 00000000 00000000
[    1.682671] ffc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
[    1.690855] ffe0: 00000000 00000000 00000000 00000000 00000013 00000000 00000000 00000000
[    1.699058] [<c0683fbc>] (klist_next) from [<c0455d90>] (device_for_each_child+0x40/0x94)
[    1.707241] [<c0455d90>] (device_for_each_child) from [<c0457d7c>] (device_reorder_to_tail+0x38/0x88)
[    1.716476] [<c0457d7c>] (device_reorder_to_tail) from [<c0455dac>] (device_for_each_child+0x5c/0x94)
[    1.725692] [<c0455dac>] (device_for_each_child) from [<c0457d7c>] (device_reorder_to_tail+0x38/0x88)
[    1.734927] [<c0457d7c>] (device_reorder_to_tail) from [<c0457df4>] (device_pm_move_to_tail+0x28/0x40)
[    1.744235] [<c0457df4>] (device_pm_move_to_tail) from [<c045a27c>] (deferred_probe_work_func+0x58/0x8c)
[    1.753746] [<c045a27c>] (deferred_probe_work_func) from [<c013893c>] (process_one_work+0x210/0x4fc)
[    1.762888] [<c013893c>] (process_one_work) from [<c0139a30>] (worker_thread+0x2a8/0x5c0)
[    1.771072] [<c0139a30>] (worker_thread) from [<c013e598>] (kthread+0x14c/0x154)
[    1.778482] [<c013e598>] (kthread) from [<c01010e8>] (ret_from_fork+0x14/0x2c)
[    1.785689] Exception stack(0xceeeffb0 to 0xceeefff8)
[    1.790739] ffa0:                                     00000000 00000000 00000000 00000000
[    1.798923] ffc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
[    1.807107] ffe0: 00000000 00000000 00000000 00000000 00000013 00000000
[    1.813724] Code: e92d47f0 e1a05000 e8900048 e1a00003 (e5937010)
[    1.819844] ---[ end trace 3c2c0c8b65399ec9 ]---

The actual error that we had from devm_gpiod_get_optional() was
-EPROBE_DEFER, due to the GPIO being provided by a driver that is
probed later than the Ethernet controller driver.

To fix this, we simply add the missing device_del() invocation in the
error path.

Fixes: 69226896ad636 ("mdio_bus: Issue GPIO RESET to PHYs")
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mdio_bus.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index 98f4b1f706df..15c5586d74ff 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -391,6 +391,7 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner)
 	if (IS_ERR(gpiod)) {
 		dev_err(&bus->dev, "mii_bus %s couldn't get reset GPIO\n",
 			bus->id);
+		device_del(&bus->dev);
 		return PTR_ERR(gpiod);
 	} else	if (gpiod) {
 		bus->reset_gpiod = gpiod;
-- 
2.20.1


From f38523690803d2f7e84dcb43d6e0736b87e5ef19 Mon Sep 17 00:00:00 2001
From: Camelia Groza <camelia.groza@nxp.com>
Date: Thu, 17 Jan 2019 14:22:36 +0200
Subject: [PATCH 06/21] net: phy: phy driver features are mandatory

[ Upstream commit 3e64cf7a435ed0500e3adaa8aada2272d3ae8abc ]

Since phy driver features became a link_mode bitmap, phy drivers that
don't have a list of features configured will cause the kernel to crash
when probed.

Prevent the phy driver from registering if the features field is missing.

Fixes: 719655a14971 ("net: phy: Replace phy driver features u32 with link_mode bitmap")
Reported-by: Scott Wood <oss@buserror.net>
Signed-off-by: Camelia Groza <camelia.groza@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 5 +++++
 include/linux/phy.h          | 4 ++--
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 2c32c795f5dd..8fd3df886a31 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1917,6 +1917,11 @@ int phy_driver_register(struct phy_driver *new_driver, struct module *owner)
 {
 	int retval;
 
+	if (WARN_ON(!new_driver->features)) {
+		pr_err("%s: Driver features are missing\n", new_driver->name);
+		return -EINVAL;
+	}
+
 	new_driver->mdiodrv.flags |= MDIO_DEVICE_IS_PHY;
 	new_driver->mdiodrv.driver.name = new_driver->name;
 	new_driver->mdiodrv.driver.bus = &mdio_bus_type;
diff --git a/include/linux/phy.h b/include/linux/phy.h
index cd6f637cbbfb..dca0a04b6e1e 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -491,8 +491,8 @@ struct phy_device {
  *   only works for PHYs with IDs which match this field
  * name: The friendly name of this PHY type
  * phy_id_mask: Defines the important bits of the phy_id
- * features: A list of features (speed, duplex, etc) supported
- *   by this PHY
+ * features: A mandatory list of features (speed, duplex, etc)
+ *   supported by this PHY
  * flags: A bitfield defining certain other features this PHY
  *   supports (like interrupts)
  *
-- 
2.20.1


From f9baf091f80c22a4998d51be713afe500e7a4cb4 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Thu, 10 Jan 2019 20:21:02 +0100
Subject: [PATCH 07/21] net/sched: act_tunnel_key: fix memory leak in case of
 action replace

[ Upstream commit 9174c3df1cd181c14913138d50ccbe539bb08335 ]

running the following TDC test cases:

 7afc - Replace tunnel_key set action with all parameters
 364d - Replace tunnel_key set action with all parameters and cookie

it's possible to trigger kmemleak warnings like:

  unreferenced object 0xffff94797127ab40 (size 192):
  comm "tc", pid 3248, jiffies 4300565293 (age 1006.862s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 c0 93 f9 8a ff ff ff ff  ................
    41 84 ee 89 ff ff ff ff 00 00 00 00 00 00 00 00  A...............
  backtrace:
    [<000000001e85b61c>] tunnel_key_init+0x31d/0x820 [act_tunnel_key]
    [<000000007f3f6ee7>] tcf_action_init_1+0x384/0x4c0
    [<00000000e89e3ded>] tcf_action_init+0x12b/0x1a0
    [<00000000c1c8c0f8>] tcf_action_add+0x73/0x170
    [<0000000095a9fc28>] tc_ctl_action+0x122/0x160
    [<000000004bebeac5>] rtnetlink_rcv_msg+0x263/0x2d0
    [<000000009fd862dd>] netlink_rcv_skb+0x4a/0x110
    [<00000000b55199e7>] netlink_unicast+0x1a0/0x250
    [<000000004996cd21>] netlink_sendmsg+0x2c1/0x3c0
    [<000000004d6a94b4>] sock_sendmsg+0x36/0x40
    [<000000005d9f0208>] ___sys_sendmsg+0x280/0x2f0
    [<00000000dec19023>] __sys_sendmsg+0x5e/0xa0
    [<000000004b82ac81>] do_syscall_64+0x5b/0x180
    [<00000000a0f1209a>] entry_SYSCALL_64_after_hwframe+0x44/0xa9
    [<000000002926b2ab>] 0xffffffffffffffff

when the tunnel_key action is replaced, the kernel forgets to release the
dst metadata: ensure they are released by tunnel_key_init(), the same way
it's done in tunnel_key_release().

Fixes: d0f6dd8a914f4 ("net/sched: Introduce act_tunnel_key")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_tunnel_key.c | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 681f6f04e7da..0f6601fdf889 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -197,6 +197,15 @@ static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = {
 	[TCA_TUNNEL_KEY_ENC_TTL]      = { .type = NLA_U8 },
 };
 
+static void tunnel_key_release_params(struct tcf_tunnel_key_params *p)
+{
+	if (!p)
+		return;
+	if (p->tcft_action == TCA_TUNNEL_KEY_ACT_SET)
+		dst_release(&p->tcft_enc_metadata->dst);
+	kfree_rcu(p, rcu);
+}
+
 static int tunnel_key_init(struct net *net, struct nlattr *nla,
 			   struct nlattr *est, struct tc_action **a,
 			   int ovr, int bind, bool rtnl_held,
@@ -360,8 +369,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 	rcu_swap_protected(t->params, params_new,
 			   lockdep_is_held(&t->tcf_lock));
 	spin_unlock_bh(&t->tcf_lock);
-	if (params_new)
-		kfree_rcu(params_new, rcu);
+	tunnel_key_release_params(params_new);
 
 	if (ret == ACT_P_CREATED)
 		tcf_idr_insert(tn, *a);
@@ -385,12 +393,7 @@ static void tunnel_key_release(struct tc_action *a)
 	struct tcf_tunnel_key_params *params;
 
 	params = rcu_dereference_protected(t->params, 1);
-	if (params) {
-		if (params->tcft_action == TCA_TUNNEL_KEY_ACT_SET)
-			dst_release(&params->tcft_enc_metadata->dst);
-
-		kfree_rcu(params, rcu);
-	}
+	tunnel_key_release_params(params);
 }
 
 static int tunnel_key_geneve_opts_dump(struct sk_buff *skb,
-- 
2.20.1


From c88e39555a3234801de597fb6b48b2c49b7bf3f9 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Fri, 11 Jan 2019 18:55:42 -0800
Subject: [PATCH 08/21] net_sched: refetch skb protocol for each filter

[ Upstream commit cd0c4e70fc0ccfa705cdf55efb27519ce9337a26 ]

Martin reported a set of filters don't work after changing
from reclassify to continue. Looking into the code, it
looks like skb protocol is not always fetched for each
iteration of the filters. But, as demonstrated by Martin,
TC actions could modify skb->protocol, for example act_vlan,
this means we have to refetch skb protocol in each iteration,
rather than using the one we fetch in the beginning of the loop.

This bug is _not_ introduced by commit 3b3ae880266d
("net: sched: consolidate tc_classify{,_compat}"), technically,
if act_vlan is the only action that modifies skb protocol, then
it is commit c7e2b9689ef8 ("sched: introduce vlan action") which
introduced this bug.

Reported-by: Martin Olsson <martin.olsson+netdev@sentorsecurity.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 70f144ac5e1d..2167c6ca55e3 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -960,7 +960,6 @@ static int tcf_block_cb_call(struct tcf_block *block, enum tc_setup_type type,
 int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 		 struct tcf_result *res, bool compat_mode)
 {
-	__be16 protocol = tc_skb_protocol(skb);
 #ifdef CONFIG_NET_CLS_ACT
 	const int max_reclassify_loop = 4;
 	const struct tcf_proto *orig_tp = tp;
@@ -970,6 +969,7 @@ int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 reclassify:
 #endif
 	for (; tp; tp = rcu_dereference_bh(tp->next)) {
+		__be16 protocol = tc_skb_protocol(skb);
 		int err;
 
 		if (tp->protocol != protocol &&
@@ -1002,7 +1002,6 @@ int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 	}
 
 	tp = first_tp;
-	protocol = tc_skb_protocol(skb);
 	goto reclassify;
 #endif
 }
-- 
2.20.1


From 31ba83a883d01c5b6bc1f6fe7df3179a1269d8c7 Mon Sep 17 00:00:00 2001
From: Ross Lagerwall <ross.lagerwall@citrix.com>
Date: Mon, 14 Jan 2019 09:16:56 +0000
Subject: [PATCH 09/21] openvswitch: Avoid OOB read when parsing flow nlattrs

[ Upstream commit 04a4af334b971814eedf4e4a413343ad3287d9a9 ]

For nested and variable attributes, the expected length of an attribute
is not known and marked by a negative number.  This results in an OOB
read when the expected length is later used to check if the attribute is
all zeros. Fix this by using the actual length of the attribute rather
than the expected length.

Signed-off-by: Ross Lagerwall <ross.lagerwall@citrix.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/flow_netlink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 865ecef68196..c7b6010b2c09 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -500,7 +500,7 @@ static int __parse_flow_nlattrs(const struct nlattr *attr,
 			return -EINVAL;
 		}
 
-		if (!nz || !is_all_zero(nla_data(nla), expected_len)) {
+		if (!nz || !is_all_zero(nla_data(nla), nla_len(nla))) {
 			attrs |= 1 << type;
 			a[type] = nla;
 		}
-- 
2.20.1


From ed720245f9b1bbc47ddc631efeb7291e6f89c632 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Wed, 16 Jan 2019 16:54:42 +0800
Subject: [PATCH 10/21] vhost: log dirty page correctly

[ Upstream commit cc5e710759470bc7f3c61d11fd54586f15fdbdf4 ]

Vhost dirty page logging API is designed to sync through GPA. But we
try to log GIOVA when device IOTLB is enabled. This is wrong and may
lead to missing data after migration.

To solve this issue, when logging with device IOTLB enabled, we will:

1) reuse the device IOTLB translation result of GIOVA->HVA mapping to
   get HVA, for writable descriptor, get HVA through iovec. For used
   ring update, translate its GIOVA to HVA
2) traverse the GPA->HVA mapping to get the possible GPA and log
   through GPA. Pay attention this reverse mapping is not guaranteed
   to be unique, so we should log each possible GPA in this case.

This fix the failure of scp to guest during migration. In -next, we
will probably support passing GIOVA->GPA instead of GIOVA->HVA.

Fixes: 6b1e6cc7855b ("vhost: new device IOTLB API")
Reported-by: Jintack Lim <jintack@cs.columbia.edu>
Cc: Jintack Lim <jintack@cs.columbia.edu>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/net.c   |  3 +-
 drivers/vhost/vhost.c | 97 ++++++++++++++++++++++++++++++++++++-------
 drivers/vhost/vhost.h |  3 +-
 3 files changed, 87 insertions(+), 16 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 4e656f89cb22..a86aa65ad66d 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -1024,7 +1024,8 @@ static void handle_rx(struct vhost_net *net)
 		if (nvq->done_idx > VHOST_NET_BATCH)
 			vhost_net_signal_used(nvq);
 		if (unlikely(vq_log))
-			vhost_log_write(vq, vq_log, log, vhost_len);
+			vhost_log_write(vq, vq_log, log, vhost_len,
+					vq->iov, in);
 		total_len += vhost_len;
 		if (unlikely(vhost_exceeds_weight(++recv_pkts, total_len))) {
 			vhost_poll_queue(&vq->poll);
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 55e5aa662ad5..c66fc8308b5e 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -1733,13 +1733,87 @@ static int log_write(void __user *log_base,
 	return r;
 }
 
+static int log_write_hva(struct vhost_virtqueue *vq, u64 hva, u64 len)
+{
+	struct vhost_umem *umem = vq->umem;
+	struct vhost_umem_node *u;
+	u64 start, end, l, min;
+	int r;
+	bool hit = false;
+
+	while (len) {
+		min = len;
+		/* More than one GPAs can be mapped into a single HVA. So
+		 * iterate all possible umems here to be safe.
+		 */
+		list_for_each_entry(u, &umem->umem_list, link) {
+			if (u->userspace_addr > hva - 1 + len ||
+			    u->userspace_addr - 1 + u->size < hva)
+				continue;
+			start = max(u->userspace_addr, hva);
+			end = min(u->userspace_addr - 1 + u->size,
+				  hva - 1 + len);
+			l = end - start + 1;
+			r = log_write(vq->log_base,
+				      u->start + start - u->userspace_addr,
+				      l);
+			if (r < 0)
+				return r;
+			hit = true;
+			min = min(l, min);
+		}
+
+		if (!hit)
+			return -EFAULT;
+
+		len -= min;
+		hva += min;
+	}
+
+	return 0;
+}
+
+static int log_used(struct vhost_virtqueue *vq, u64 used_offset, u64 len)
+{
+	struct iovec iov[64];
+	int i, ret;
+
+	if (!vq->iotlb)
+		return log_write(vq->log_base, vq->log_addr + used_offset, len);
+
+	ret = translate_desc(vq, (uintptr_t)vq->used + used_offset,
+			     len, iov, 64, VHOST_ACCESS_WO);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < ret; i++) {
+		ret = log_write_hva(vq,	(uintptr_t)iov[i].iov_base,
+				    iov[i].iov_len);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
-		    unsigned int log_num, u64 len)
+		    unsigned int log_num, u64 len, struct iovec *iov, int count)
 {
 	int i, r;
 
 	/* Make sure data written is seen before log. */
 	smp_wmb();
+
+	if (vq->iotlb) {
+		for (i = 0; i < count; i++) {
+			r = log_write_hva(vq, (uintptr_t)iov[i].iov_base,
+					  iov[i].iov_len);
+			if (r < 0)
+				return r;
+		}
+		return 0;
+	}
+
 	for (i = 0; i < log_num; ++i) {
 		u64 l = min(log[i].len, len);
 		r = log_write(vq->log_base, log[i].addr, l);
@@ -1769,9 +1843,8 @@ static int vhost_update_used_flags(struct vhost_virtqueue *vq)
 		smp_wmb();
 		/* Log used flag write. */
 		used = &vq->used->flags;
-		log_write(vq->log_base, vq->log_addr +
-			  (used - (void __user *)vq->used),
-			  sizeof vq->used->flags);
+		log_used(vq, (used - (void __user *)vq->used),
+			 sizeof vq->used->flags);
 		if (vq->log_ctx)
 			eventfd_signal(vq->log_ctx, 1);
 	}
@@ -1789,9 +1862,8 @@ static int vhost_update_avail_event(struct vhost_virtqueue *vq, u16 avail_event)
 		smp_wmb();
 		/* Log avail event write */
 		used = vhost_avail_event(vq);
-		log_write(vq->log_base, vq->log_addr +
-			  (used - (void __user *)vq->used),
-			  sizeof *vhost_avail_event(vq));
+		log_used(vq, (used - (void __user *)vq->used),
+			 sizeof *vhost_avail_event(vq));
 		if (vq->log_ctx)
 			eventfd_signal(vq->log_ctx, 1);
 	}
@@ -2191,10 +2263,8 @@ static int __vhost_add_used_n(struct vhost_virtqueue *vq,
 		/* Make sure data is seen before log. */
 		smp_wmb();
 		/* Log used ring entry write. */
-		log_write(vq->log_base,
-			  vq->log_addr +
-			   ((void __user *)used - (void __user *)vq->used),
-			  count * sizeof *used);
+		log_used(vq, ((void __user *)used - (void __user *)vq->used),
+			 count * sizeof *used);
 	}
 	old = vq->last_used_idx;
 	new = (vq->last_used_idx += count);
@@ -2236,9 +2306,8 @@ int vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads,
 		/* Make sure used idx is seen before log. */
 		smp_wmb();
 		/* Log used index update. */
-		log_write(vq->log_base,
-			  vq->log_addr + offsetof(struct vring_used, idx),
-			  sizeof vq->used->idx);
+		log_used(vq, offsetof(struct vring_used, idx),
+			 sizeof vq->used->idx);
 		if (vq->log_ctx)
 			eventfd_signal(vq->log_ctx, 1);
 	}
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index 466ef7542291..1b675dad5e05 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -205,7 +205,8 @@ bool vhost_vq_avail_empty(struct vhost_dev *, struct vhost_virtqueue *);
 bool vhost_enable_notify(struct vhost_dev *, struct vhost_virtqueue *);
 
 int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
-		    unsigned int log_num, u64 len);
+		    unsigned int log_num, u64 len,
+		    struct iovec *iov, int count);
 int vq_iotlb_prefetch(struct vhost_virtqueue *vq);
 
 struct vhost_msg_node *vhost_new_msg(struct vhost_virtqueue *vq, int type);
-- 
2.20.1


From 2b0b8b77871a2e21a799e27f84bfe37e2637b130 Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Fri, 18 Jan 2019 15:57:56 +0000
Subject: [PATCH 11/21] mlxsw: pci: Increase PCI SW reset timeout

[ Upstream commit d2f372ba0914e5722ac28e15f2ed2db61bcf0e44 ]

Spectrum-2 PHY layer introduces a calibration period which is a part of the
Spectrum-2 firmware boot process. Hence increase the SW timeout waiting for
the firmware to come out of boot. This does not increase system boot time
in cases where the firmware PHY calibration process is done quickly.

Fixes: c3ab435466d5 ("mlxsw: spectrum: Extend to support Spectrum-2 ASIC")
Signed-off-by: Nir Dotan <nird@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/pci_hw.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
index 83f452b7ccbb..092bd6b3a210 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
@@ -27,7 +27,7 @@
 
 #define MLXSW_PCI_SW_RESET			0xF0010
 #define MLXSW_PCI_SW_RESET_RST_BIT		BIT(0)
-#define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS	5000
+#define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS	13000
 #define MLXSW_PCI_SW_RESET_WAIT_MSECS		100
 #define MLXSW_PCI_FW_READY			0xA1844
 #define MLXSW_PCI_FW_READY_MASK			0xFFFF
-- 
2.20.1


From dec375175a0541d9cf66a9a1f23a7c57a686eb99 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 9 Jan 2019 09:57:39 +0000
Subject: [PATCH 12/21] net: ipv4: Fix memory leak in network namespace
 dismantle

[ Upstream commit f97f4dd8b3bb9d0993d2491e0f22024c68109184 ]

IPv4 routing tables are flushed in two cases:

1. In response to events in the netdev and inetaddr notification chains
2. When a network namespace is being dismantled

In both cases only routes associated with a dead nexthop group are
flushed. However, a nexthop group will only be marked as dead in case it
is populated with actual nexthops using a nexthop device. This is not
the case when the route in question is an error route (e.g.,
'blackhole', 'unreachable').

Therefore, when a network namespace is being dismantled such routes are
not flushed and leaked [1].

To reproduce:
# ip netns add blue
# ip -n blue route add unreachable 192.0.2.0/24
# ip netns del blue

Fix this by not skipping error routes that are not marked with
RTNH_F_DEAD when flushing the routing tables.

To prevent the flushing of such routes in case #1, add a parameter to
fib_table_flush() that indicates if the table is flushed as part of
namespace dismantle or not.

Note that this problem does not exist in IPv6 since error routes are
associated with the loopback device.

[1]
unreferenced object 0xffff888066650338 (size 56):
  comm "ip", pid 1206, jiffies 4294786063 (age 26.235s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 b0 1c 62 61 80 88 ff ff  ..........ba....
    e8 8b a1 64 80 88 ff ff 00 07 00 08 fe 00 00 00  ...d............
  backtrace:
    [<00000000856ed27d>] inet_rtm_newroute+0x129/0x220
    [<00000000fcdfc00a>] rtnetlink_rcv_msg+0x397/0xa20
    [<00000000cb85801a>] netlink_rcv_skb+0x132/0x380
    [<00000000ebc991d2>] netlink_unicast+0x4c0/0x690
    [<0000000014f62875>] netlink_sendmsg+0x929/0xe10
    [<00000000bac9d967>] sock_sendmsg+0xc8/0x110
    [<00000000223e6485>] ___sys_sendmsg+0x77a/0x8f0
    [<000000002e94f880>] __sys_sendmsg+0xf7/0x250
    [<00000000ccb1fa72>] do_syscall_64+0x14d/0x610
    [<00000000ffbe3dae>] entry_SYSCALL_64_after_hwframe+0x49/0xbe
    [<000000003a8b605b>] 0xffffffffffffffff
unreferenced object 0xffff888061621c88 (size 48):
  comm "ip", pid 1206, jiffies 4294786063 (age 26.235s)
  hex dump (first 32 bytes):
    6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b  kkkkkkkkkkkkkkkk
    6b 6b 6b 6b 6b 6b 6b 6b d8 8e 26 5f 80 88 ff ff  kkkkkkkk..&_....
  backtrace:
    [<00000000733609e3>] fib_table_insert+0x978/0x1500
    [<00000000856ed27d>] inet_rtm_newroute+0x129/0x220
    [<00000000fcdfc00a>] rtnetlink_rcv_msg+0x397/0xa20
    [<00000000cb85801a>] netlink_rcv_skb+0x132/0x380
    [<00000000ebc991d2>] netlink_unicast+0x4c0/0x690
    [<0000000014f62875>] netlink_sendmsg+0x929/0xe10
    [<00000000bac9d967>] sock_sendmsg+0xc8/0x110
    [<00000000223e6485>] ___sys_sendmsg+0x77a/0x8f0
    [<000000002e94f880>] __sys_sendmsg+0xf7/0x250
    [<00000000ccb1fa72>] do_syscall_64+0x14d/0x610
    [<00000000ffbe3dae>] entry_SYSCALL_64_after_hwframe+0x49/0xbe
    [<000000003a8b605b>] 0xffffffffffffffff

Fixes: 8cced9eff1d4 ("[NETNS]: Enable routing configuration in non-initial namespace.")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_fib.h    |  2 +-
 net/ipv4/fib_frontend.c |  4 ++--
 net/ipv4/fib_trie.c     | 15 ++++++++++++---
 3 files changed, 15 insertions(+), 6 deletions(-)

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index c9b7b136939d..95eed32d8c6b 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -230,7 +230,7 @@ int fib_table_delete(struct net *, struct fib_table *, struct fib_config *,
 		     struct netlink_ext_ack *extack);
 int fib_table_dump(struct fib_table *table, struct sk_buff *skb,
 		   struct netlink_callback *cb);
-int fib_table_flush(struct net *net, struct fib_table *table);
+int fib_table_flush(struct net *net, struct fib_table *table, bool flush_all);
 struct fib_table *fib_trie_unmerge(struct fib_table *main_tb);
 void fib_table_flush_external(struct fib_table *table);
 void fib_free_table(struct fib_table *tb);
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 0113993e9b2c..958e185a8e8d 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -203,7 +203,7 @@ static void fib_flush(struct net *net)
 		struct fib_table *tb;
 
 		hlist_for_each_entry_safe(tb, tmp, head, tb_hlist)
-			flushed += fib_table_flush(net, tb);
+			flushed += fib_table_flush(net, tb, false);
 	}
 
 	if (flushed)
@@ -1357,7 +1357,7 @@ static void ip_fib_net_exit(struct net *net)
 
 		hlist_for_each_entry_safe(tb, tmp, head, tb_hlist) {
 			hlist_del(&tb->tb_hlist);
-			fib_table_flush(net, tb);
+			fib_table_flush(net, tb, true);
 			fib_free_table(tb);
 		}
 	}
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 5bc0c89e81e4..3955a6d7ea66 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1856,7 +1856,7 @@ void fib_table_flush_external(struct fib_table *tb)
 }
 
 /* Caller must hold RTNL. */
-int fib_table_flush(struct net *net, struct fib_table *tb)
+int fib_table_flush(struct net *net, struct fib_table *tb, bool flush_all)
 {
 	struct trie *t = (struct trie *)tb->tb_data;
 	struct key_vector *pn = t->kv;
@@ -1904,8 +1904,17 @@ int fib_table_flush(struct net *net, struct fib_table *tb)
 		hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) {
 			struct fib_info *fi = fa->fa_info;
 
-			if (!fi || !(fi->fib_flags & RTNH_F_DEAD) ||
-			    tb->tb_id != fa->tb_id) {
+			if (!fi || tb->tb_id != fa->tb_id ||
+			    (!(fi->fib_flags & RTNH_F_DEAD) &&
+			     !fib_props[fa->fa_type].error)) {
+				slen = fa->fa_slen;
+				continue;
+			}
+
+			/* Do not flush error routes if network namespace is
+			 * not being dismantled
+			 */
+			if (!flush_all && fib_props[fa->fa_type].error) {
 				slen = fa->fa_slen;
 				continue;
 			}
-- 
2.20.1


From 80775ffc5e8ddc1c0c04a25214b02b6b2de96ff5 Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Fri, 18 Jan 2019 15:57:59 +0000
Subject: [PATCH 13/21] mlxsw: spectrum_fid: Update dummy FID index

[ Upstream commit a11dcd6497915ba79d95ef4fe2541aaac27f6201 ]

When using a tc flower action of egress mirred redirect, the driver adds
an implicit FID setting action. This implicit action sets a dummy FID to
the packet and is used as part of a design for trapping unmatched flows
in OVS.  While this implicit FID setting action is supposed to be a NOP
when a redirect action is added, in Spectrum-2 the FID record is
consulted as the dummy FID index is an 802.1D FID index and the packet
is dropped instead of being redirected.

Set the dummy FID index value to be within 802.1Q range. This satisfies
both Spectrum-1 which ignores the FID and Spectrum-2 which identifies it
as an 802.1Q FID and will then follow the redirect action.

Fixes: c3ab435466d5 ("mlxsw: spectrum: Extend to support Spectrum-2 ASIC")
Signed-off-by: Nir Dotan <nird@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
index 715d24ff937e..562c4429eec7 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
@@ -696,8 +696,8 @@ static const struct mlxsw_sp_fid_ops mlxsw_sp_fid_dummy_ops = {
 static const struct mlxsw_sp_fid_family mlxsw_sp_fid_dummy_family = {
 	.type			= MLXSW_SP_FID_TYPE_DUMMY,
 	.fid_size		= sizeof(struct mlxsw_sp_fid),
-	.start_index		= MLXSW_SP_RFID_BASE - 1,
-	.end_index		= MLXSW_SP_RFID_BASE - 1,
+	.start_index		= VLAN_N_VID - 1,
+	.end_index		= VLAN_N_VID - 1,
 	.ops			= &mlxsw_sp_fid_dummy_ops,
 };
 
-- 
2.20.1


From e89f64950af71f793208d5eefa23487f8051f1e4 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Fri, 18 Jan 2019 15:57:55 +0000
Subject: [PATCH 14/21] mlxsw: pci: Ring CQ's doorbell before RDQ's

When a packet should be trapped to the CPU the device consumes a WQE
(work queue element) from an RDQ (receive descriptor queue) and copies
the packet to the address specified in the WQE. The device then tries to
post a CQE (completion queue element) that contains various metadata
(e.g., ingress port) about the packet to a CQ (completion queue).

In case the device managed to consume a WQE, but did not manage to post
the corresponding CQE, it will get stuck. This unlikely situation can be
triggered due to the scheme the driver is currently using to process
CQEs.

The driver will consume up to 512 CQEs at a time and after processing
each corresponding WQE it will ring the RDQ's doorbell, letting the
device know that a new WQE was posted for it to consume. Only after
processing all the CQEs (up to 512), the driver will ring the CQ's
doorbell, letting the device know that new ones can be posted.

Fix this by having the driver ring the CQ's doorbell for every processed
CQE, but before ringing the RDQ's doorbell. This guarantees that
whenever we post a new WQE, there is a corresponding CQE available. Copy
the currently processed CQE to prevent the device from overwriting it
with a new CQE after ringing the doorbell.

Note that the driver still arms the CQ only after processing all the
pending CQEs, so that interrupts for this CQ will only be delivered
after the driver finished its processing.

Before commit 8404f6f2e8ed ("mlxsw: pci: Allow to use CQEs of version 1
and version 2") the issue was virtually impossible to trigger since the
number of CQEs was twice the number of WQEs and the number of CQEs
processed at a time was equal to the number of available WQEs.

Fixes: 8404f6f2e8ed ("mlxsw: pci: Allow to use CQEs of version 1 and version 2")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Semion Lisyansky <semionl@mellanox.com>
Tested-by: Semion Lisyansky <semionl@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/pci.c    | 12 +++++++-----
 drivers/net/ethernet/mellanox/mlxsw/pci_hw.h |  1 +
 2 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index 5890fdfd62c3..c7901a3f2a79 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -604,29 +604,31 @@ static void mlxsw_pci_cq_tasklet(unsigned long data)
 		u16 wqe_counter = mlxsw_pci_cqe_wqe_counter_get(cqe);
 		u8 sendq = mlxsw_pci_cqe_sr_get(q->u.cq.v, cqe);
 		u8 dqn = mlxsw_pci_cqe_dqn_get(q->u.cq.v, cqe);
+		char ncqe[MLXSW_PCI_CQE_SIZE_MAX];
+
+		memcpy(ncqe, cqe, q->elem_size);
+		mlxsw_pci_queue_doorbell_consumer_ring(mlxsw_pci, q);
 
 		if (sendq) {
 			struct mlxsw_pci_queue *sdq;
 
 			sdq = mlxsw_pci_sdq_get(mlxsw_pci, dqn);
 			mlxsw_pci_cqe_sdq_handle(mlxsw_pci, sdq,
-						 wqe_counter, cqe);
+						 wqe_counter, ncqe);
 			q->u.cq.comp_sdq_count++;
 		} else {
 			struct mlxsw_pci_queue *rdq;
 
 			rdq = mlxsw_pci_rdq_get(mlxsw_pci, dqn);
 			mlxsw_pci_cqe_rdq_handle(mlxsw_pci, rdq,
-						 wqe_counter, q->u.cq.v, cqe);
+						 wqe_counter, q->u.cq.v, ncqe);
 			q->u.cq.comp_rdq_count++;
 		}
 		if (++items == credits)
 			break;
 	}
-	if (items) {
-		mlxsw_pci_queue_doorbell_consumer_ring(mlxsw_pci, q);
+	if (items)
 		mlxsw_pci_queue_doorbell_arm_consumer_ring(mlxsw_pci, q);
-	}
 }
 
 static u16 mlxsw_pci_cq_elem_count(const struct mlxsw_pci_queue *q)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
index 092bd6b3a210..72cdaa01d56d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
@@ -53,6 +53,7 @@
 #define MLXSW_PCI_WQE_SIZE	32 /* 32 bytes per element */
 #define MLXSW_PCI_CQE01_SIZE	16 /* 16 bytes per element */
 #define MLXSW_PCI_CQE2_SIZE	32 /* 32 bytes per element */
+#define MLXSW_PCI_CQE_SIZE_MAX	MLXSW_PCI_CQE2_SIZE
 #define MLXSW_PCI_EQE_SIZE	16 /* 16 bytes per element */
 #define MLXSW_PCI_WQE_COUNT	(MLXSW_PCI_AQ_SIZE / MLXSW_PCI_WQE_SIZE)
 #define MLXSW_PCI_CQE01_COUNT	(MLXSW_PCI_AQ_SIZE / MLXSW_PCI_CQE01_SIZE)
-- 
2.20.1


From 6f9ce73c103f1e646c32819692a7815fa0606229 Mon Sep 17 00:00:00 2001
From: Ivan Vecera <ivecera@redhat.com>
Date: Wed, 16 Jan 2019 16:53:52 +0100
Subject: [PATCH 15/21] net/sched: cls_flower: allocate mask dynamically in
 fl_change()

[ Upstream commit 2cddd20147826aef283115abb00012d4dafe3cdb ]

Recent changes (especially 05cd271fd61a ("cls_flower: Support multiple
masks per priority")) in the fl_flow_mask structure grow it and its
current size e.g. on x86_64 with defconfig is 760 bytes and more than
1024 bytes with some debug options enabled. Prior the mentioned commit
its size was 176 bytes (using defconfig on x86_64).
With regard to this fact it's reasonable to allocate this structure
dynamically in fl_change() to reduce its stack size.

v2:
- use kzalloc() instead of kcalloc()

Fixes: 05cd271fd61a ("cls_flower: Support multiple masks per priority")
Cc: Jiri Pirko <jiri@resnulli.us>
Cc: Paul Blakey <paulb@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_flower.c | 19 ++++++++++++++-----
 1 file changed, 14 insertions(+), 5 deletions(-)

diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 7fade7107f95..84893bc67531 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -1176,17 +1176,23 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
 	struct cls_fl_head *head = rtnl_dereference(tp->root);
 	struct cls_fl_filter *fold = *arg;
 	struct cls_fl_filter *fnew;
+	struct fl_flow_mask *mask;
 	struct nlattr **tb;
-	struct fl_flow_mask mask = {};
 	int err;
 
 	if (!tca[TCA_OPTIONS])
 		return -EINVAL;
 
-	tb = kcalloc(TCA_FLOWER_MAX + 1, sizeof(struct nlattr *), GFP_KERNEL);
-	if (!tb)
+	mask = kzalloc(sizeof(struct fl_flow_mask), GFP_KERNEL);
+	if (!mask)
 		return -ENOBUFS;
 
+	tb = kcalloc(TCA_FLOWER_MAX + 1, sizeof(struct nlattr *), GFP_KERNEL);
+	if (!tb) {
+		err = -ENOBUFS;
+		goto errout_mask_alloc;
+	}
+
 	err = nla_parse_nested(tb, TCA_FLOWER_MAX, tca[TCA_OPTIONS],
 			       fl_policy, NULL);
 	if (err < 0)
@@ -1229,12 +1235,12 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
 		}
 	}
 
-	err = fl_set_parms(net, tp, fnew, &mask, base, tb, tca[TCA_RATE], ovr,
+	err = fl_set_parms(net, tp, fnew, mask, base, tb, tca[TCA_RATE], ovr,
 			   tp->chain->tmplt_priv, extack);
 	if (err)
 		goto errout_idr;
 
-	err = fl_check_assign_mask(head, fnew, fold, &mask);
+	err = fl_check_assign_mask(head, fnew, fold, mask);
 	if (err)
 		goto errout_idr;
 
@@ -1281,6 +1287,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
 	}
 
 	kfree(tb);
+	kfree(mask);
 	return 0;
 
 errout_mask:
@@ -1294,6 +1301,8 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
 	kfree(fnew);
 errout_tb:
 	kfree(tb);
+errout_mask_alloc:
+	kfree(mask);
 	return err;
 }
 
-- 
2.20.1


From 88631b55758cf3dd2563ea98cac718f11dcc9d10 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Tue, 15 Jan 2019 11:40:02 -0500
Subject: [PATCH 16/21] udp: with udp_segment release on error path

[ Upstream commit 0f149c9fec3cd720628ecde83bfc6f64c1e7dcb6 ]

Failure __ip_append_data triggers udp_flush_pending_frames, but these
tests happen later. The skb must be freed directly.

Fixes: bec1f6f697362 ("udp: generate gso with UDP_SEGMENT")
Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 16 ++++++++++++----
 net/ipv6/udp.c | 16 ++++++++++++----
 2 files changed, 24 insertions(+), 8 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index f8183fdce5b2..e45a5e19e509 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -785,15 +785,23 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4,
 		const int hlen = skb_network_header_len(skb) +
 				 sizeof(struct udphdr);
 
-		if (hlen + cork->gso_size > cork->fragsize)
+		if (hlen + cork->gso_size > cork->fragsize) {
+			kfree_skb(skb);
 			return -EINVAL;
-		if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS)
+		}
+		if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS) {
+			kfree_skb(skb);
 			return -EINVAL;
-		if (sk->sk_no_check_tx)
+		}
+		if (sk->sk_no_check_tx) {
+			kfree_skb(skb);
 			return -EINVAL;
+		}
 		if (skb->ip_summed != CHECKSUM_PARTIAL || is_udplite ||
-		    dst_xfrm(skb_dst(skb)))
+		    dst_xfrm(skb_dst(skb))) {
+			kfree_skb(skb);
 			return -EIO;
+		}
 
 		skb_shinfo(skb)->gso_size = cork->gso_size;
 		skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index b36694b6716e..76ba2f34ef6b 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1056,15 +1056,23 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6,
 		const int hlen = skb_network_header_len(skb) +
 				 sizeof(struct udphdr);
 
-		if (hlen + cork->gso_size > cork->fragsize)
+		if (hlen + cork->gso_size > cork->fragsize) {
+			kfree_skb(skb);
 			return -EINVAL;
-		if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS)
+		}
+		if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS) {
+			kfree_skb(skb);
 			return -EINVAL;
-		if (udp_sk(sk)->no_check6_tx)
+		}
+		if (udp_sk(sk)->no_check6_tx) {
+			kfree_skb(skb);
 			return -EINVAL;
+		}
 		if (skb->ip_summed != CHECKSUM_PARTIAL || is_udplite ||
-		    dst_xfrm(skb_dst(skb)))
+		    dst_xfrm(skb_dst(skb))) {
+			kfree_skb(skb);
 			return -EIO;
+		}
 
 		skb_shinfo(skb)->gso_size = cork->gso_size;
 		skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
-- 
2.20.1


From daec1b35526738341f95a311ec9782e45bd93978 Mon Sep 17 00:00:00 2001
From: Olivier Matz <olivier.matz@6wind.com>
Date: Wed, 9 Jan 2019 10:57:21 +0100
Subject: [PATCH 17/21] ip6_gre: fix tunnel list corruption for x-netns

[ Upstream commit ab5098fa25b91cb6fe0a0676f17abb64f2bbf024 ]

In changelink ops, the ip6gre_net pointer is retrieved from
dev_net(dev), which is wrong in case of x-netns. Thus, the tunnel is not
unlinked from its current list and is relinked into another net
namespace. This corrupts the tunnel lists and can later trigger a kernel
oops.

Fix this by retrieving the netns from device private area.

Fixes: c8632fc30bb0 ("net: ip6_gre: Split up ip6gre_changelink()")
Cc: Petr Machata <petrm@mellanox.com>
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index c270726b01b0..c0aad1f9ab15 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -2047,9 +2047,9 @@ static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[],
 			     struct nlattr *data[],
 			     struct netlink_ext_ack *extack)
 {
-	struct ip6gre_net *ign = net_generic(dev_net(dev), ip6gre_net_id);
+	struct ip6_tnl *t = netdev_priv(dev);
+	struct ip6gre_net *ign = net_generic(t->net, ip6gre_net_id);
 	struct __ip6_tnl_parm p;
-	struct ip6_tnl *t;
 
 	t = ip6gre_changelink_common(dev, tb, data, &p, extack);
 	if (IS_ERR(t))
-- 
2.20.1


From d9d8e1b415124c4d54bffde45413c454dab06aab Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 14 Jan 2019 18:10:06 +0800
Subject: [PATCH 18/21] erspan: build the header with the right proto according
 to erspan_ver

[ Upstream commit 20704bd1633dd5afb29a321d3a615c9c8e9c9d05 ]

As said in draft-foschiano-erspan-03#section4:

   Different frame variants known as "ERSPAN Types" can be
   distinguished based on the GRE "Protocol Type" field value: Type I
   and II's value is 0x88BE while Type III's is 0x22EB [ETYPES].

So set it properly in erspan_xmit() according to erspan_ver. While at
it, also remove the unused parameter 'proto' in erspan_fb_xmit().

Fixes: 94d7d8f29287 ("ip6_gre: add erspan v2 support")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_gre.c  | 23 ++++++++++++++---------
 net/ipv6/ip6_gre.c |  6 ++++--
 2 files changed, 18 insertions(+), 11 deletions(-)

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 5ef5df3a06f1..0bfad3e72509 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -570,8 +570,7 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev,
 	dev->stats.tx_dropped++;
 }
 
-static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev,
-			   __be16 proto)
+static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	struct ip_tunnel_info *tun_info;
@@ -579,10 +578,10 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev,
 	struct erspan_metadata *md;
 	struct rtable *rt = NULL;
 	bool truncate = false;
+	__be16 df, proto;
 	struct flowi4 fl;
 	int tunnel_hlen;
 	int version;
-	__be16 df;
 	int nhoff;
 	int thoff;
 
@@ -627,18 +626,20 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev,
 	if (version == 1) {
 		erspan_build_header(skb, ntohl(tunnel_id_to_key32(key->tun_id)),
 				    ntohl(md->u.index), truncate, true);
+		proto = htons(ETH_P_ERSPAN);
 	} else if (version == 2) {
 		erspan_build_header_v2(skb,
 				       ntohl(tunnel_id_to_key32(key->tun_id)),
 				       md->u.md2.dir,
 				       get_hwid(&md->u.md2),
 				       truncate, true);
+		proto = htons(ETH_P_ERSPAN2);
 	} else {
 		goto err_free_rt;
 	}
 
 	gre_build_header(skb, 8, TUNNEL_SEQ,
-			 htons(ETH_P_ERSPAN), 0, htonl(tunnel->o_seqno++));
+			 proto, 0, htonl(tunnel->o_seqno++));
 
 	df = key->tun_flags & TUNNEL_DONT_FRAGMENT ?  htons(IP_DF) : 0;
 
@@ -722,12 +723,13 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb,
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	bool truncate = false;
+	__be16 proto;
 
 	if (!pskb_inet_may_pull(skb))
 		goto free_skb;
 
 	if (tunnel->collect_md) {
-		erspan_fb_xmit(skb, dev, skb->protocol);
+		erspan_fb_xmit(skb, dev);
 		return NETDEV_TX_OK;
 	}
 
@@ -743,19 +745,22 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb,
 	}
 
 	/* Push ERSPAN header */
-	if (tunnel->erspan_ver == 1)
+	if (tunnel->erspan_ver == 1) {
 		erspan_build_header(skb, ntohl(tunnel->parms.o_key),
 				    tunnel->index,
 				    truncate, true);
-	else if (tunnel->erspan_ver == 2)
+		proto = htons(ETH_P_ERSPAN);
+	} else if (tunnel->erspan_ver == 2) {
 		erspan_build_header_v2(skb, ntohl(tunnel->parms.o_key),
 				       tunnel->dir, tunnel->hwid,
 				       truncate, true);
-	else
+		proto = htons(ETH_P_ERSPAN2);
+	} else {
 		goto free_skb;
+	}
 
 	tunnel->parms.o_flags &= ~TUNNEL_KEY;
-	__gre_xmit(skb, dev, &tunnel->parms.iph, htons(ETH_P_ERSPAN));
+	__gre_xmit(skb, dev, &tunnel->parms.iph, proto);
 	return NETDEV_TX_OK;
 
 free_skb:
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index c0aad1f9ab15..2805d78c9658 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -938,6 +938,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 	__u8 dsfield = false;
 	struct flowi6 fl6;
 	int err = -EINVAL;
+	__be16 proto;
 	__u32 mtu;
 	int nhoff;
 	int thoff;
@@ -1051,8 +1052,9 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 	}
 
 	/* Push GRE header. */
-	gre_build_header(skb, 8, TUNNEL_SEQ,
-			 htons(ETH_P_ERSPAN), 0, htonl(t->o_seqno++));
+	proto = (t->parms.erspan_ver == 1) ? htons(ETH_P_ERSPAN)
+					   : htons(ETH_P_ERSPAN2);
+	gre_build_header(skb, 8, TUNNEL_SEQ, proto, 0, htonl(t->o_seqno++));
 
 	/* TooBig packet may have updated dst->dev's mtu */
 	if (!t->parms.collect_md && dst && dst_mtu(dst) > dst->dev->mtu)
-- 
2.20.1


From fa8a4ab6975d2694dfad841a7bd76b6701ec2ab9 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Fri, 11 Jan 2019 00:15:21 +0100
Subject: [PATCH 19/21] net: phy: marvell: Fix deadlock from wrong locking
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit e0a7328fad9979104f73e19bedca821ef3262ae1 ]

m88e1318_set_wol() takes the lock as part of phy_select_page(). Don't
take the lock again with phy_read(), use the unlocked __phy_read().

Fixes: 424ca4c55121 ("net: phy: marvell: fix paged access races")
Reported-by: Åke Rehnman <ake.rehnman@gmail.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/marvell.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index b3aa0027c0ff..d71be15c8c69 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -1451,7 +1451,7 @@ static int m88e1318_set_wol(struct phy_device *phydev,
 		 * before enabling it if !phy_interrupt_is_valid()
 		 */
 		if (!phy_interrupt_is_valid(phydev))
-			phy_read(phydev, MII_M1011_IEVENT);
+			__phy_read(phydev, MII_M1011_IEVENT);
 
 		/* Enable the WOL interrupt */
 		err = __phy_modify(phydev, MII_88E1318S_PHY_CSIER, 0,
-- 
2.20.1


From 6ce0e3aee55bb93bac1c591ab331d0068110d2b2 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Thu, 10 Jan 2019 11:17:42 +0800
Subject: [PATCH 20/21] ip6_gre: update version related info when changing link

[ Upstream commit 80b3671e9377916bf2b02e56113fa7377ce5705a ]

We forgot to update ip6erspan version related info when changing link,
which will cause setting new hwid failed.

Reported-by: Jianlin Shi <jishi@redhat.com>
Fixes: 94d7d8f292870 ("ip6_gre: add erspan v2 support")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 2805d78c9658..345e6839f031 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1187,6 +1187,10 @@ static void ip6gre_tnl_copy_tnl_parm(struct ip6_tnl *t,
 	t->parms.i_flags = p->i_flags;
 	t->parms.o_flags = p->o_flags;
 	t->parms.fwmark = p->fwmark;
+	t->parms.erspan_ver = p->erspan_ver;
+	t->parms.index = p->index;
+	t->parms.dir = p->dir;
+	t->parms.hwid = p->hwid;
 	dst_cache_reset(&t->dst_cache);
 }
 
-- 
2.20.1


From d0c1f830666a9acb08b1436c8d0d635dcf56bcd2 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Thu, 10 Jan 2019 14:40:33 -0500
Subject: [PATCH 21/21] tcp: allow MSG_ZEROCOPY transmission also in CLOSE_WAIT
 state

[ Upstream commit 13d7f46386e060df31b727c9975e38306fa51e7a ]

TCP transmission with MSG_ZEROCOPY fails if the peer closes its end of
the connection and so transitions this socket to CLOSE_WAIT state.

Transmission in close wait state is acceptable. Other similar tests in
the stack (e.g., in FastOpen) accept both states. Relax this test, too.

Link: https://www.mail-archive.com/netdev@vger.kernel.org/msg276886.html
Link: https://www.mail-archive.com/netdev@vger.kernel.org/msg227390.html
Fixes: f214f915e7db ("tcp: enable MSG_ZEROCOPY")
Reported-by: Marek Majkowski <marek@cloudflare.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
CC: Yuchung Cheng <ycheng@google.com>
CC: Neal Cardwell <ncardwell@google.com>
CC: Soheil Hassas Yeganeh <soheil@google.com>
CC: Alexey Kodanev <alexey.kodanev@oracle.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index a32a0f4cc138..87fe44197aa1 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1186,7 +1186,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 	flags = msg->msg_flags;
 
 	if (flags & MSG_ZEROCOPY && size && sock_flag(sk, SOCK_ZEROCOPY)) {
-		if (sk->sk_state != TCP_ESTABLISHED) {
+		if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) {
 			err = -EINVAL;
 			goto out_err;
 		}
-- 
2.20.1


[-- Attachment #3: net_420.mbox --]
[-- Type: Application/Octet-Stream, Size: 63042 bytes --]

From b07016adb9b1950ac14aed4812b411fbf22e2157 Mon Sep 17 00:00:00 2001
From: "Lendacky, Thomas" <Thomas.Lendacky@amd.com>
Date: Thu, 17 Jan 2019 14:20:14 +0000
Subject: [PATCH 01/21] amd-xgbe: Fix mdio access for non-zero ports and clause
 45 PHYs

[ Upstream commit 5ab3121beeb76aa6090195b67d237115860dd9ec ]

The XGBE hardware has support for performing MDIO operations using an
MDIO command request. The driver mistakenly uses the mdio port address
as the MDIO command request device address instead of the MDIO command
request port address. Additionally, the driver does not properly check
for and create a clause 45 MDIO command.

Check the supplied MDIO register to determine if the request is a clause
45 operation (MII_ADDR_C45). For a clause 45 operation, extract the device
address and register number from the supplied MDIO register and use them
to set the MDIO command request device address and register number fields.
For a clause 22 operation, the MDIO request device address is set to zero
and the MDIO command request register number is set to the supplied MDIO
register. In either case, the supplied MDIO port address is used as the
MDIO command request port address.

Fixes: 732f2ab7afb9 ("amd-xgbe: Add support for MDIO attached PHYs")
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Tested-by: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe-common.h |  2 --
 drivers/net/ethernet/amd/xgbe/xgbe-dev.c    | 22 +++++++++++++++------
 2 files changed, 16 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
index d272dc6984ac..b40d4377cc71 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
@@ -431,8 +431,6 @@
 #define MAC_MDIOSCAR_PA_WIDTH		5
 #define MAC_MDIOSCAR_RA_INDEX		0
 #define MAC_MDIOSCAR_RA_WIDTH		16
-#define MAC_MDIOSCAR_REG_INDEX		0
-#define MAC_MDIOSCAR_REG_WIDTH		21
 #define MAC_MDIOSCCDR_BUSY_INDEX	22
 #define MAC_MDIOSCCDR_BUSY_WIDTH	1
 #define MAC_MDIOSCCDR_CMD_INDEX		16
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
index 1e929a1e4ca7..4666084eda16 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
@@ -1284,6 +1284,20 @@ static void xgbe_write_mmd_regs(struct xgbe_prv_data *pdata, int prtad,
 	}
 }
 
+static unsigned int xgbe_create_mdio_sca(int port, int reg)
+{
+	unsigned int mdio_sca, da;
+
+	da = (reg & MII_ADDR_C45) ? reg >> 16 : 0;
+
+	mdio_sca = 0;
+	XGMAC_SET_BITS(mdio_sca, MAC_MDIOSCAR, RA, reg);
+	XGMAC_SET_BITS(mdio_sca, MAC_MDIOSCAR, PA, port);
+	XGMAC_SET_BITS(mdio_sca, MAC_MDIOSCAR, DA, da);
+
+	return mdio_sca;
+}
+
 static int xgbe_write_ext_mii_regs(struct xgbe_prv_data *pdata, int addr,
 				   int reg, u16 val)
 {
@@ -1291,9 +1305,7 @@ static int xgbe_write_ext_mii_regs(struct xgbe_prv_data *pdata, int addr,
 
 	reinit_completion(&pdata->mdio_complete);
 
-	mdio_sca = 0;
-	XGMAC_SET_BITS(mdio_sca, MAC_MDIOSCAR, REG, reg);
-	XGMAC_SET_BITS(mdio_sca, MAC_MDIOSCAR, DA, addr);
+	mdio_sca = xgbe_create_mdio_sca(addr, reg);
 	XGMAC_IOWRITE(pdata, MAC_MDIOSCAR, mdio_sca);
 
 	mdio_sccd = 0;
@@ -1317,9 +1329,7 @@ static int xgbe_read_ext_mii_regs(struct xgbe_prv_data *pdata, int addr,
 
 	reinit_completion(&pdata->mdio_complete);
 
-	mdio_sca = 0;
-	XGMAC_SET_BITS(mdio_sca, MAC_MDIOSCAR, REG, reg);
-	XGMAC_SET_BITS(mdio_sca, MAC_MDIOSCAR, DA, addr);
+	mdio_sca = xgbe_create_mdio_sca(addr, reg);
 	XGMAC_IOWRITE(pdata, MAC_MDIOSCAR, mdio_sca);
 
 	mdio_sccd = 0;
-- 
2.20.1


From e8df53a7f719200ae1ff27ac7cdabf869ae99a93 Mon Sep 17 00:00:00 2001
From: Yunjian Wang <wangyunjian@huawei.com>
Date: Thu, 17 Jan 2019 09:46:41 +0800
Subject: [PATCH 02/21] net: bridge: Fix ethernet header pointer before check
 skb forwardable

[ Upstream commit 28c1382fa28f2e2d9d0d6f25ae879b5af2ecbd03 ]

The skb header should be set to ethernet header before using
is_skb_forwardable. Because the ethernet header length has been
considered in is_skb_forwardable(including dev->hard_header_len
length).

To reproduce the issue:
1, add 2 ports on linux bridge br using following commands:
$ brctl addbr br
$ brctl addif br eth0
$ brctl addif br eth1
2, the MTU of eth0 and eth1 is 1500
3, send a packet(Data 1480, UDP 8, IP 20, Ethernet 14, VLAN 4)
from eth0 to eth1

So the expect result is packet larger than 1500 cannot pass through
eth0 and eth1. But currently, the packet passes through success, it
means eth1's MTU limit doesn't take effect.

Fixes: f6367b4660dd ("bridge: use is_skb_forwardable in forward path")
Cc: bridge@lists.linux-foundation.org
Cc: Nkolay Aleksandrov <nikolay@cumulusnetworks.com>
Cc: Roopa Prabhu <roopa@cumulusnetworks.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_forward.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 5372e2042adf..d0f26696f2fd 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -36,10 +36,10 @@ static inline int should_deliver(const struct net_bridge_port *p,
 
 int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
+	skb_push(skb, ETH_HLEN);
 	if (!is_skb_forwardable(skb->dev, skb))
 		goto drop;
 
-	skb_push(skb, ETH_HLEN);
 	br_drop_fake_rtable(skb);
 
 	if (skb->ip_summed == CHECKSUM_PARTIAL &&
@@ -97,12 +97,11 @@ static void __br_forward(const struct net_bridge_port *to,
 		net = dev_net(indev);
 	} else {
 		if (unlikely(netpoll_tx_running(to->br->dev))) {
-			if (!is_skb_forwardable(skb->dev, skb)) {
+			skb_push(skb, ETH_HLEN);
+			if (!is_skb_forwardable(skb->dev, skb))
 				kfree_skb(skb);
-			} else {
-				skb_push(skb, ETH_HLEN);
+			else
 				br_netpoll_send_skb(to, skb);
-			}
 			return;
 		}
 		br_hook = NF_BR_LOCAL_OUT;
-- 
2.20.1


From d8f8633a927d69787cb7b8aa854ee445f2d7641d Mon Sep 17 00:00:00 2001
From: Ross Lagerwall <ross.lagerwall@citrix.com>
Date: Thu, 17 Jan 2019 15:34:38 +0000
Subject: [PATCH 03/21] net: Fix usage of pskb_trim_rcsum

[ Upstream commit 6c57f0458022298e4da1729c67bd33ce41c14e7a ]

In certain cases, pskb_trim_rcsum() may change skb pointers.
Reinitialize header pointers afterwards to avoid potential
use-after-frees. Add a note in the documentation of
pskb_trim_rcsum(). Found by KASAN.

Signed-off-by: Ross Lagerwall <ross.lagerwall@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pppoe.c                  | 1 +
 include/linux/skbuff.h                   | 1 +
 net/bridge/br_netfilter_ipv6.c           | 1 +
 net/bridge/netfilter/nft_reject_bridge.c | 1 +
 net/ipv4/ip_input.c                      | 1 +
 5 files changed, 5 insertions(+)

diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 62dc564b251d..f22639f0116a 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -445,6 +445,7 @@ static int pppoe_rcv(struct sk_buff *skb, struct net_device *dev,
 	if (pskb_trim_rcsum(skb, len))
 		goto drop;
 
+	ph = pppoe_hdr(skb);
 	pn = pppoe_pernet(dev_net(dev));
 
 	/* Note that get_item does a sock_hold(), so sk_pppox(po)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 0d1b2c3f127b..a6d820ad17f0 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3204,6 +3204,7 @@ int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len);
  *
  *	This is exactly the same as pskb_trim except that it ensures the
  *	checksum of received packets are still valid after the operation.
+ *	It can change skb pointers.
  */
 
 static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len)
diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c
index 96c072e71ea2..5811208863b7 100644
--- a/net/bridge/br_netfilter_ipv6.c
+++ b/net/bridge/br_netfilter_ipv6.c
@@ -131,6 +131,7 @@ int br_validate_ipv6(struct net *net, struct sk_buff *skb)
 					IPSTATS_MIB_INDISCARDS);
 			goto drop;
 		}
+		hdr = ipv6_hdr(skb);
 	}
 	if (hdr->nexthdr == NEXTHDR_HOP && br_nf_check_hbh_len(skb))
 		goto drop;
diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c
index 08cbed7d940e..419e8edf23ba 100644
--- a/net/bridge/netfilter/nft_reject_bridge.c
+++ b/net/bridge/netfilter/nft_reject_bridge.c
@@ -229,6 +229,7 @@ static bool reject6_br_csum_ok(struct sk_buff *skb, int hook)
 	    pskb_trim_rcsum(skb, ntohs(ip6h->payload_len) + sizeof(*ip6h)))
 		return false;
 
+	ip6h = ipv6_hdr(skb);
 	thoff = ipv6_skip_exthdr(skb, ((u8*)(ip6h+1) - skb->data), &proto, &fo);
 	if (thoff < 0 || thoff >= skb->len || (fo & htons(~0x7)) != 0)
 		return false;
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index e609b08c9df4..3163428219cd 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -489,6 +489,7 @@ static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net)
 		goto drop;
 	}
 
+	iph = ip_hdr(skb);
 	skb->transport_header = skb->network_header + iph->ihl*4;
 
 	/* Remove any debris in the socket control block */
-- 
2.20.1


From 3b98675d83b75623abb2c94dca4aa90f7e7b80c5 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Thu, 10 Jan 2019 22:48:36 +0100
Subject: [PATCH 04/21] net: phy: marvell: Errata for mv88e6390 internal PHYs

[ Upstream commit 8cbcdc1a51999ca81db2956608b917aacd28d837 ]

The VOD can be out of spec, unless some magic value is poked into an
undocumented register in an undocumented page.

Fixes: e4cf8a38fc0d ("net: phy: Marvell: Add mv88e6390 internal PHY")
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/marvell.c | 35 ++++++++++++++++++++++++++++++++++-
 1 file changed, 34 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index cbec296107bd..426097e7a275 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -1042,6 +1042,39 @@ static int m88e1145_config_init(struct phy_device *phydev)
 	return 0;
 }
 
+/* The VOD can be out of specification on link up. Poke an
+ * undocumented register, in an undocumented page, with a magic value
+ * to fix this.
+ */
+static int m88e6390_errata(struct phy_device *phydev)
+{
+	int err;
+
+	err = phy_write(phydev, MII_BMCR,
+			BMCR_ANENABLE | BMCR_SPEED1000 | BMCR_FULLDPLX);
+	if (err)
+		return err;
+
+	usleep_range(300, 400);
+
+	err = phy_write_paged(phydev, 0xf8, 0x08, 0x36);
+	if (err)
+		return err;
+
+	return genphy_soft_reset(phydev);
+}
+
+static int m88e6390_config_aneg(struct phy_device *phydev)
+{
+	int err;
+
+	err = m88e6390_errata(phydev);
+	if (err)
+		return err;
+
+	return m88e1510_config_aneg(phydev);
+}
+
 /**
  * fiber_lpa_to_ethtool_lpa_t
  * @lpa: value of the MII_LPA register for fiber link
@@ -2292,7 +2325,7 @@ static struct phy_driver marvell_drivers[] = {
 		.flags = PHY_HAS_INTERRUPT,
 		.probe = m88e6390_probe,
 		.config_init = &marvell_config_init,
-		.config_aneg = &m88e1510_config_aneg,
+		.config_aneg = &m88e6390_config_aneg,
 		.read_status = &marvell_read_status,
 		.ack_interrupt = &marvell_ack_interrupt,
 		.config_intr = &marvell_config_intr,
-- 
2.20.1


From ae96196b45db60c426d739526b79d95497542824 Mon Sep 17 00:00:00 2001
From: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
Date: Wed, 16 Jan 2019 10:53:58 +0100
Subject: [PATCH 05/21] net: phy: mdio_bus: add missing device_del() in
 mdiobus_register() error handling

[ Upstream commit e40e2a2e78664fa90ea4b9bdf4a84efce2fea9d9 ]

The current code in __mdiobus_register() doesn't properly handle
failures returned by the devm_gpiod_get_optional() call: it returns
immediately, without unregistering the device that was added by the
call to device_register() earlier in the function.

This leaves a stale device, which then causes a NULL pointer
dereference in the code that handles deferred probing:

[    1.489982] Unable to handle kernel NULL pointer dereference at virtual address 00000074
[    1.498110] pgd = (ptrval)
[    1.500838] [00000074] *pgd=00000000
[    1.504432] Internal error: Oops: 17 [#1] SMP ARM
[    1.509133] Modules linked in:
[    1.512192] CPU: 1 PID: 51 Comm: kworker/1:3 Not tainted 4.20.0-00039-g3b73a4cc8b3e-dirty #99
[    1.520708] Hardware name: Xilinx Zynq Platform
[    1.525261] Workqueue: events deferred_probe_work_func
[    1.530403] PC is at klist_next+0x10/0xfc
[    1.534403] LR is at device_for_each_child+0x40/0x94
[    1.539361] pc : [<c0683fbc>]    lr : [<c0455d90>]    psr: 200e0013
[    1.545628] sp : ceeefe68  ip : 00000001  fp : ffffe000
[    1.550863] r10: 00000000  r9 : c0c66790  r8 : 00000000
[    1.556079] r7 : c0457d44  r6 : 00000000  r5 : ceeefe8c  r4 : cfa2ec78
[    1.562604] r3 : 00000064  r2 : c0457d44  r1 : ceeefe8c  r0 : 00000064
[    1.569129] Flags: nzCv  IRQs on  FIQs on  Mode SVC_32  ISA ARM  Segment none
[    1.576263] Control: 18c5387d  Table: 0ed7804a  DAC: 00000051
[    1.582013] Process kworker/1:3 (pid: 51, stack limit = 0x(ptrval))
[    1.588280] Stack: (0xceeefe68 to 0xceef0000)
[    1.592630] fe60:                   cfa2ec78 c0c03c08 00000000 c0457d44 00000000 c0c66790
[    1.600814] fe80: 00000000 c0455d90 ceeefeac 00000064 00000000 0d7a542e cee9d494 cfa2ec78
[    1.608998] fea0: cfa2ec78 00000000 c0457d44 c0457d7c cee9d494 c0c03c08 00000000 c0455dac
[    1.617182] fec0: cf98ba44 cf926a00 cee9d494 0d7a542e 00000000 cf935a10 cf935a10 cf935a10
[    1.625366] fee0: c0c4e9b8 c0457d7c c0c4e80c 00000001 cf935a10 c0457df4 cf935a10 c0c4e99c
[    1.633550] ff00: c0c4e99c c045a27c c0c4e9c4 ced63f80 cfde8a80 cfdebc00 00000000 c013893c
[    1.641734] ff20: cfde8a80 cfde8a80 c07bd354 ced63f80 ced63f94 cfde8a80 00000008 c0c02d00
[    1.649936] ff40: cfde8a98 cfde8a80 ffffe000 c0139a30 ffffe000 c0c6624a c07bd354 00000000
[    1.658120] ff60: ffffe000 cee9e780 ceebfe00 00000000 ceeee000 ced63f80 c0139788 cf8cdea4
[    1.666304] ff80: cee9e79c c013e598 00000001 ceebfe00 c013e44c 00000000 00000000 00000000
[    1.674488] ffa0: 00000000 00000000 00000000 c01010e8 00000000 00000000 00000000 00000000
[    1.682671] ffc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
[    1.690855] ffe0: 00000000 00000000 00000000 00000000 00000013 00000000 00000000 00000000
[    1.699058] [<c0683fbc>] (klist_next) from [<c0455d90>] (device_for_each_child+0x40/0x94)
[    1.707241] [<c0455d90>] (device_for_each_child) from [<c0457d7c>] (device_reorder_to_tail+0x38/0x88)
[    1.716476] [<c0457d7c>] (device_reorder_to_tail) from [<c0455dac>] (device_for_each_child+0x5c/0x94)
[    1.725692] [<c0455dac>] (device_for_each_child) from [<c0457d7c>] (device_reorder_to_tail+0x38/0x88)
[    1.734927] [<c0457d7c>] (device_reorder_to_tail) from [<c0457df4>] (device_pm_move_to_tail+0x28/0x40)
[    1.744235] [<c0457df4>] (device_pm_move_to_tail) from [<c045a27c>] (deferred_probe_work_func+0x58/0x8c)
[    1.753746] [<c045a27c>] (deferred_probe_work_func) from [<c013893c>] (process_one_work+0x210/0x4fc)
[    1.762888] [<c013893c>] (process_one_work) from [<c0139a30>] (worker_thread+0x2a8/0x5c0)
[    1.771072] [<c0139a30>] (worker_thread) from [<c013e598>] (kthread+0x14c/0x154)
[    1.778482] [<c013e598>] (kthread) from [<c01010e8>] (ret_from_fork+0x14/0x2c)
[    1.785689] Exception stack(0xceeeffb0 to 0xceeefff8)
[    1.790739] ffa0:                                     00000000 00000000 00000000 00000000
[    1.798923] ffc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
[    1.807107] ffe0: 00000000 00000000 00000000 00000000 00000013 00000000
[    1.813724] Code: e92d47f0 e1a05000 e8900048 e1a00003 (e5937010)
[    1.819844] ---[ end trace 3c2c0c8b65399ec9 ]---

The actual error that we had from devm_gpiod_get_optional() was
-EPROBE_DEFER, due to the GPIO being provided by a driver that is
probed later than the Ethernet controller driver.

To fix this, we simply add the missing device_del() invocation in the
error path.

Fixes: 69226896ad636 ("mdio_bus: Issue GPIO RESET to PHYs")
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mdio_bus.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index 2e59a8419b17..66b9cfe692fc 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -390,6 +390,7 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner)
 	if (IS_ERR(gpiod)) {
 		dev_err(&bus->dev, "mii_bus %s couldn't get reset GPIO\n",
 			bus->id);
+		device_del(&bus->dev);
 		return PTR_ERR(gpiod);
 	} else	if (gpiod) {
 		bus->reset_gpiod = gpiod;
-- 
2.20.1


From 7e0104d160d451648a40d3768568897c40b3fb41 Mon Sep 17 00:00:00 2001
From: Camelia Groza <camelia.groza@nxp.com>
Date: Thu, 17 Jan 2019 14:22:36 +0200
Subject: [PATCH 06/21] net: phy: phy driver features are mandatory

[ Upstream commit 3e64cf7a435ed0500e3adaa8aada2272d3ae8abc ]

Since phy driver features became a link_mode bitmap, phy drivers that
don't have a list of features configured will cause the kernel to crash
when probed.

Prevent the phy driver from registering if the features field is missing.

Fixes: 719655a14971 ("net: phy: Replace phy driver features u32 with link_mode bitmap")
Reported-by: Scott Wood <oss@buserror.net>
Signed-off-by: Camelia Groza <camelia.groza@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 5 +++++
 include/linux/phy.h          | 4 ++--
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index fd051ae787cb..5dd661fb662f 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -2196,6 +2196,11 @@ int phy_driver_register(struct phy_driver *new_driver, struct module *owner)
 {
 	int retval;
 
+	if (WARN_ON(!new_driver->features)) {
+		pr_err("%s: Driver features are missing\n", new_driver->name);
+		return -EINVAL;
+	}
+
 	new_driver->mdiodrv.flags |= MDIO_DEVICE_IS_PHY;
 	new_driver->mdiodrv.driver.name = new_driver->name;
 	new_driver->mdiodrv.driver.bus = &mdio_bus_type;
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 306630d13523..f5d4235e3844 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -502,8 +502,8 @@ struct phy_device {
  *   only works for PHYs with IDs which match this field
  * name: The friendly name of this PHY type
  * phy_id_mask: Defines the important bits of the phy_id
- * features: A list of features (speed, duplex, etc) supported
- *   by this PHY
+ * features: A mandatory list of features (speed, duplex, etc)
+ *   supported by this PHY
  * flags: A bitfield defining certain other features this PHY
  *   supports (like interrupts)
  *
-- 
2.20.1


From 66de5d40c158713be27ae3d3a006b063724ffef7 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Thu, 10 Jan 2019 20:21:02 +0100
Subject: [PATCH 07/21] net/sched: act_tunnel_key: fix memory leak in case of
 action replace

[ Upstream commit 9174c3df1cd181c14913138d50ccbe539bb08335 ]

running the following TDC test cases:

 7afc - Replace tunnel_key set action with all parameters
 364d - Replace tunnel_key set action with all parameters and cookie

it's possible to trigger kmemleak warnings like:

  unreferenced object 0xffff94797127ab40 (size 192):
  comm "tc", pid 3248, jiffies 4300565293 (age 1006.862s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 c0 93 f9 8a ff ff ff ff  ................
    41 84 ee 89 ff ff ff ff 00 00 00 00 00 00 00 00  A...............
  backtrace:
    [<000000001e85b61c>] tunnel_key_init+0x31d/0x820 [act_tunnel_key]
    [<000000007f3f6ee7>] tcf_action_init_1+0x384/0x4c0
    [<00000000e89e3ded>] tcf_action_init+0x12b/0x1a0
    [<00000000c1c8c0f8>] tcf_action_add+0x73/0x170
    [<0000000095a9fc28>] tc_ctl_action+0x122/0x160
    [<000000004bebeac5>] rtnetlink_rcv_msg+0x263/0x2d0
    [<000000009fd862dd>] netlink_rcv_skb+0x4a/0x110
    [<00000000b55199e7>] netlink_unicast+0x1a0/0x250
    [<000000004996cd21>] netlink_sendmsg+0x2c1/0x3c0
    [<000000004d6a94b4>] sock_sendmsg+0x36/0x40
    [<000000005d9f0208>] ___sys_sendmsg+0x280/0x2f0
    [<00000000dec19023>] __sys_sendmsg+0x5e/0xa0
    [<000000004b82ac81>] do_syscall_64+0x5b/0x180
    [<00000000a0f1209a>] entry_SYSCALL_64_after_hwframe+0x44/0xa9
    [<000000002926b2ab>] 0xffffffffffffffff

when the tunnel_key action is replaced, the kernel forgets to release the
dst metadata: ensure they are released by tunnel_key_init(), the same way
it's done in tunnel_key_release().

Fixes: d0f6dd8a914f4 ("net/sched: Introduce act_tunnel_key")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_tunnel_key.c | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 4cca8f274662..904730b8ce8f 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -197,6 +197,15 @@ static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = {
 	[TCA_TUNNEL_KEY_ENC_TTL]      = { .type = NLA_U8 },
 };
 
+static void tunnel_key_release_params(struct tcf_tunnel_key_params *p)
+{
+	if (!p)
+		return;
+	if (p->tcft_action == TCA_TUNNEL_KEY_ACT_SET)
+		dst_release(&p->tcft_enc_metadata->dst);
+	kfree_rcu(p, rcu);
+}
+
 static int tunnel_key_init(struct net *net, struct nlattr *nla,
 			   struct nlattr *est, struct tc_action **a,
 			   int ovr, int bind, bool rtnl_held,
@@ -360,8 +369,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 	rcu_swap_protected(t->params, params_new,
 			   lockdep_is_held(&t->tcf_lock));
 	spin_unlock_bh(&t->tcf_lock);
-	if (params_new)
-		kfree_rcu(params_new, rcu);
+	tunnel_key_release_params(params_new);
 
 	if (ret == ACT_P_CREATED)
 		tcf_idr_insert(tn, *a);
@@ -385,12 +393,7 @@ static void tunnel_key_release(struct tc_action *a)
 	struct tcf_tunnel_key_params *params;
 
 	params = rcu_dereference_protected(t->params, 1);
-	if (params) {
-		if (params->tcft_action == TCA_TUNNEL_KEY_ACT_SET)
-			dst_release(&params->tcft_enc_metadata->dst);
-
-		kfree_rcu(params, rcu);
-	}
+	tunnel_key_release_params(params);
 }
 
 static int tunnel_key_geneve_opts_dump(struct sk_buff *skb,
-- 
2.20.1


From 83b2390b0fe1bff488ad583006eaf304853bb709 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Fri, 11 Jan 2019 18:55:42 -0800
Subject: [PATCH 08/21] net_sched: refetch skb protocol for each filter

[ Upstream commit cd0c4e70fc0ccfa705cdf55efb27519ce9337a26 ]

Martin reported a set of filters don't work after changing
from reclassify to continue. Looking into the code, it
looks like skb protocol is not always fetched for each
iteration of the filters. But, as demonstrated by Martin,
TC actions could modify skb->protocol, for example act_vlan,
this means we have to refetch skb protocol in each iteration,
rather than using the one we fetch in the beginning of the loop.

This bug is _not_ introduced by commit 3b3ae880266d
("net: sched: consolidate tc_classify{,_compat}"), technically,
if act_vlan is the only action that modifies skb protocol, then
it is commit c7e2b9689ef8 ("sched: introduce vlan action") which
introduced this bug.

Reported-by: Martin Olsson <martin.olsson+netdev@sentorsecurity.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index f427a1e00e7e..1c4436523aa5 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1053,7 +1053,6 @@ static int tcf_block_cb_call(struct tcf_block *block, enum tc_setup_type type,
 int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 		 struct tcf_result *res, bool compat_mode)
 {
-	__be16 protocol = tc_skb_protocol(skb);
 #ifdef CONFIG_NET_CLS_ACT
 	const int max_reclassify_loop = 4;
 	const struct tcf_proto *orig_tp = tp;
@@ -1063,6 +1062,7 @@ int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 reclassify:
 #endif
 	for (; tp; tp = rcu_dereference_bh(tp->next)) {
+		__be16 protocol = tc_skb_protocol(skb);
 		int err;
 
 		if (tp->protocol != protocol &&
@@ -1095,7 +1095,6 @@ int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 	}
 
 	tp = first_tp;
-	protocol = tc_skb_protocol(skb);
 	goto reclassify;
 #endif
 }
-- 
2.20.1


From 1c33a37d1bc0d3da8e2dc2c23b884696e7c823c7 Mon Sep 17 00:00:00 2001
From: Ross Lagerwall <ross.lagerwall@citrix.com>
Date: Mon, 14 Jan 2019 09:16:56 +0000
Subject: [PATCH 09/21] openvswitch: Avoid OOB read when parsing flow nlattrs

[ Upstream commit 04a4af334b971814eedf4e4a413343ad3287d9a9 ]

For nested and variable attributes, the expected length of an attribute
is not known and marked by a negative number.  This results in an OOB
read when the expected length is later used to check if the attribute is
all zeros. Fix this by using the actual length of the attribute rather
than the expected length.

Signed-off-by: Ross Lagerwall <ross.lagerwall@citrix.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/flow_netlink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 865ecef68196..c7b6010b2c09 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -500,7 +500,7 @@ static int __parse_flow_nlattrs(const struct nlattr *attr,
 			return -EINVAL;
 		}
 
-		if (!nz || !is_all_zero(nla_data(nla), expected_len)) {
+		if (!nz || !is_all_zero(nla_data(nla), nla_len(nla))) {
 			attrs |= 1 << type;
 			a[type] = nla;
 		}
-- 
2.20.1


From 028ec894a086b9ef6eaf49e24711b64be10aa768 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Wed, 16 Jan 2019 16:54:42 +0800
Subject: [PATCH 10/21] vhost: log dirty page correctly

[ Upstream commit cc5e710759470bc7f3c61d11fd54586f15fdbdf4 ]

Vhost dirty page logging API is designed to sync through GPA. But we
try to log GIOVA when device IOTLB is enabled. This is wrong and may
lead to missing data after migration.

To solve this issue, when logging with device IOTLB enabled, we will:

1) reuse the device IOTLB translation result of GIOVA->HVA mapping to
   get HVA, for writable descriptor, get HVA through iovec. For used
   ring update, translate its GIOVA to HVA
2) traverse the GPA->HVA mapping to get the possible GPA and log
   through GPA. Pay attention this reverse mapping is not guaranteed
   to be unique, so we should log each possible GPA in this case.

This fix the failure of scp to guest during migration. In -next, we
will probably support passing GIOVA->GPA instead of GIOVA->HVA.

Fixes: 6b1e6cc7855b ("vhost: new device IOTLB API")
Reported-by: Jintack Lim <jintack@cs.columbia.edu>
Cc: Jintack Lim <jintack@cs.columbia.edu>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/net.c   |  3 +-
 drivers/vhost/vhost.c | 97 ++++++++++++++++++++++++++++++++++++-------
 drivers/vhost/vhost.h |  3 +-
 3 files changed, 87 insertions(+), 16 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index ad7a6f475a44..784df2b49628 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -1192,7 +1192,8 @@ static void handle_rx(struct vhost_net *net)
 		if (nvq->done_idx > VHOST_NET_BATCH)
 			vhost_net_signal_used(nvq);
 		if (unlikely(vq_log))
-			vhost_log_write(vq, vq_log, log, vhost_len);
+			vhost_log_write(vq, vq_log, log, vhost_len,
+					vq->iov, in);
 		total_len += vhost_len;
 		if (unlikely(vhost_exceeds_weight(++recv_pkts, total_len))) {
 			vhost_poll_queue(&vq->poll);
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 55e5aa662ad5..c66fc8308b5e 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -1733,13 +1733,87 @@ static int log_write(void __user *log_base,
 	return r;
 }
 
+static int log_write_hva(struct vhost_virtqueue *vq, u64 hva, u64 len)
+{
+	struct vhost_umem *umem = vq->umem;
+	struct vhost_umem_node *u;
+	u64 start, end, l, min;
+	int r;
+	bool hit = false;
+
+	while (len) {
+		min = len;
+		/* More than one GPAs can be mapped into a single HVA. So
+		 * iterate all possible umems here to be safe.
+		 */
+		list_for_each_entry(u, &umem->umem_list, link) {
+			if (u->userspace_addr > hva - 1 + len ||
+			    u->userspace_addr - 1 + u->size < hva)
+				continue;
+			start = max(u->userspace_addr, hva);
+			end = min(u->userspace_addr - 1 + u->size,
+				  hva - 1 + len);
+			l = end - start + 1;
+			r = log_write(vq->log_base,
+				      u->start + start - u->userspace_addr,
+				      l);
+			if (r < 0)
+				return r;
+			hit = true;
+			min = min(l, min);
+		}
+
+		if (!hit)
+			return -EFAULT;
+
+		len -= min;
+		hva += min;
+	}
+
+	return 0;
+}
+
+static int log_used(struct vhost_virtqueue *vq, u64 used_offset, u64 len)
+{
+	struct iovec iov[64];
+	int i, ret;
+
+	if (!vq->iotlb)
+		return log_write(vq->log_base, vq->log_addr + used_offset, len);
+
+	ret = translate_desc(vq, (uintptr_t)vq->used + used_offset,
+			     len, iov, 64, VHOST_ACCESS_WO);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < ret; i++) {
+		ret = log_write_hva(vq,	(uintptr_t)iov[i].iov_base,
+				    iov[i].iov_len);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
-		    unsigned int log_num, u64 len)
+		    unsigned int log_num, u64 len, struct iovec *iov, int count)
 {
 	int i, r;
 
 	/* Make sure data written is seen before log. */
 	smp_wmb();
+
+	if (vq->iotlb) {
+		for (i = 0; i < count; i++) {
+			r = log_write_hva(vq, (uintptr_t)iov[i].iov_base,
+					  iov[i].iov_len);
+			if (r < 0)
+				return r;
+		}
+		return 0;
+	}
+
 	for (i = 0; i < log_num; ++i) {
 		u64 l = min(log[i].len, len);
 		r = log_write(vq->log_base, log[i].addr, l);
@@ -1769,9 +1843,8 @@ static int vhost_update_used_flags(struct vhost_virtqueue *vq)
 		smp_wmb();
 		/* Log used flag write. */
 		used = &vq->used->flags;
-		log_write(vq->log_base, vq->log_addr +
-			  (used - (void __user *)vq->used),
-			  sizeof vq->used->flags);
+		log_used(vq, (used - (void __user *)vq->used),
+			 sizeof vq->used->flags);
 		if (vq->log_ctx)
 			eventfd_signal(vq->log_ctx, 1);
 	}
@@ -1789,9 +1862,8 @@ static int vhost_update_avail_event(struct vhost_virtqueue *vq, u16 avail_event)
 		smp_wmb();
 		/* Log avail event write */
 		used = vhost_avail_event(vq);
-		log_write(vq->log_base, vq->log_addr +
-			  (used - (void __user *)vq->used),
-			  sizeof *vhost_avail_event(vq));
+		log_used(vq, (used - (void __user *)vq->used),
+			 sizeof *vhost_avail_event(vq));
 		if (vq->log_ctx)
 			eventfd_signal(vq->log_ctx, 1);
 	}
@@ -2191,10 +2263,8 @@ static int __vhost_add_used_n(struct vhost_virtqueue *vq,
 		/* Make sure data is seen before log. */
 		smp_wmb();
 		/* Log used ring entry write. */
-		log_write(vq->log_base,
-			  vq->log_addr +
-			   ((void __user *)used - (void __user *)vq->used),
-			  count * sizeof *used);
+		log_used(vq, ((void __user *)used - (void __user *)vq->used),
+			 count * sizeof *used);
 	}
 	old = vq->last_used_idx;
 	new = (vq->last_used_idx += count);
@@ -2236,9 +2306,8 @@ int vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads,
 		/* Make sure used idx is seen before log. */
 		smp_wmb();
 		/* Log used index update. */
-		log_write(vq->log_base,
-			  vq->log_addr + offsetof(struct vring_used, idx),
-			  sizeof vq->used->idx);
+		log_used(vq, offsetof(struct vring_used, idx),
+			 sizeof vq->used->idx);
 		if (vq->log_ctx)
 			eventfd_signal(vq->log_ctx, 1);
 	}
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index 466ef7542291..1b675dad5e05 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -205,7 +205,8 @@ bool vhost_vq_avail_empty(struct vhost_dev *, struct vhost_virtqueue *);
 bool vhost_enable_notify(struct vhost_dev *, struct vhost_virtqueue *);
 
 int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
-		    unsigned int log_num, u64 len);
+		    unsigned int log_num, u64 len,
+		    struct iovec *iov, int count);
 int vq_iotlb_prefetch(struct vhost_virtqueue *vq);
 
 struct vhost_msg_node *vhost_new_msg(struct vhost_virtqueue *vq, int type);
-- 
2.20.1


From f07710527168781ace733dbaa840c57eee7bc819 Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Fri, 18 Jan 2019 15:57:56 +0000
Subject: [PATCH 11/21] mlxsw: pci: Increase PCI SW reset timeout

[ Upstream commit d2f372ba0914e5722ac28e15f2ed2db61bcf0e44 ]

Spectrum-2 PHY layer introduces a calibration period which is a part of the
Spectrum-2 firmware boot process. Hence increase the SW timeout waiting for
the firmware to come out of boot. This does not increase system boot time
in cases where the firmware PHY calibration process is done quickly.

Fixes: c3ab435466d5 ("mlxsw: spectrum: Extend to support Spectrum-2 ASIC")
Signed-off-by: Nir Dotan <nird@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/pci_hw.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
index bb99f6d41fe0..9c601c17f7ae 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
@@ -27,7 +27,7 @@
 
 #define MLXSW_PCI_SW_RESET			0xF0010
 #define MLXSW_PCI_SW_RESET_RST_BIT		BIT(0)
-#define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS	5000
+#define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS	13000
 #define MLXSW_PCI_SW_RESET_WAIT_MSECS		100
 #define MLXSW_PCI_FW_READY			0xA1844
 #define MLXSW_PCI_FW_READY_MASK			0xFFFF
-- 
2.20.1


From ec8c94512d5d4ceb465b7879f84efb581db2034c Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 9 Jan 2019 09:57:39 +0000
Subject: [PATCH 12/21] net: ipv4: Fix memory leak in network namespace
 dismantle

[ Upstream commit f97f4dd8b3bb9d0993d2491e0f22024c68109184 ]

IPv4 routing tables are flushed in two cases:

1. In response to events in the netdev and inetaddr notification chains
2. When a network namespace is being dismantled

In both cases only routes associated with a dead nexthop group are
flushed. However, a nexthop group will only be marked as dead in case it
is populated with actual nexthops using a nexthop device. This is not
the case when the route in question is an error route (e.g.,
'blackhole', 'unreachable').

Therefore, when a network namespace is being dismantled such routes are
not flushed and leaked [1].

To reproduce:
# ip netns add blue
# ip -n blue route add unreachable 192.0.2.0/24
# ip netns del blue

Fix this by not skipping error routes that are not marked with
RTNH_F_DEAD when flushing the routing tables.

To prevent the flushing of such routes in case #1, add a parameter to
fib_table_flush() that indicates if the table is flushed as part of
namespace dismantle or not.

Note that this problem does not exist in IPv6 since error routes are
associated with the loopback device.

[1]
unreferenced object 0xffff888066650338 (size 56):
  comm "ip", pid 1206, jiffies 4294786063 (age 26.235s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 b0 1c 62 61 80 88 ff ff  ..........ba....
    e8 8b a1 64 80 88 ff ff 00 07 00 08 fe 00 00 00  ...d............
  backtrace:
    [<00000000856ed27d>] inet_rtm_newroute+0x129/0x220
    [<00000000fcdfc00a>] rtnetlink_rcv_msg+0x397/0xa20
    [<00000000cb85801a>] netlink_rcv_skb+0x132/0x380
    [<00000000ebc991d2>] netlink_unicast+0x4c0/0x690
    [<0000000014f62875>] netlink_sendmsg+0x929/0xe10
    [<00000000bac9d967>] sock_sendmsg+0xc8/0x110
    [<00000000223e6485>] ___sys_sendmsg+0x77a/0x8f0
    [<000000002e94f880>] __sys_sendmsg+0xf7/0x250
    [<00000000ccb1fa72>] do_syscall_64+0x14d/0x610
    [<00000000ffbe3dae>] entry_SYSCALL_64_after_hwframe+0x49/0xbe
    [<000000003a8b605b>] 0xffffffffffffffff
unreferenced object 0xffff888061621c88 (size 48):
  comm "ip", pid 1206, jiffies 4294786063 (age 26.235s)
  hex dump (first 32 bytes):
    6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b  kkkkkkkkkkkkkkkk
    6b 6b 6b 6b 6b 6b 6b 6b d8 8e 26 5f 80 88 ff ff  kkkkkkkk..&_....
  backtrace:
    [<00000000733609e3>] fib_table_insert+0x978/0x1500
    [<00000000856ed27d>] inet_rtm_newroute+0x129/0x220
    [<00000000fcdfc00a>] rtnetlink_rcv_msg+0x397/0xa20
    [<00000000cb85801a>] netlink_rcv_skb+0x132/0x380
    [<00000000ebc991d2>] netlink_unicast+0x4c0/0x690
    [<0000000014f62875>] netlink_sendmsg+0x929/0xe10
    [<00000000bac9d967>] sock_sendmsg+0xc8/0x110
    [<00000000223e6485>] ___sys_sendmsg+0x77a/0x8f0
    [<000000002e94f880>] __sys_sendmsg+0xf7/0x250
    [<00000000ccb1fa72>] do_syscall_64+0x14d/0x610
    [<00000000ffbe3dae>] entry_SYSCALL_64_after_hwframe+0x49/0xbe
    [<000000003a8b605b>] 0xffffffffffffffff

Fixes: 8cced9eff1d4 ("[NETNS]: Enable routing configuration in non-initial namespace.")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_fib.h    |  2 +-
 net/ipv4/fib_frontend.c |  4 ++--
 net/ipv4/fib_trie.c     | 15 ++++++++++++---
 3 files changed, 15 insertions(+), 6 deletions(-)

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index c5969762a8f4..9c8214d2116d 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -241,7 +241,7 @@ int fib_table_delete(struct net *, struct fib_table *, struct fib_config *,
 		     struct netlink_ext_ack *extack);
 int fib_table_dump(struct fib_table *table, struct sk_buff *skb,
 		   struct netlink_callback *cb, struct fib_dump_filter *filter);
-int fib_table_flush(struct net *net, struct fib_table *table);
+int fib_table_flush(struct net *net, struct fib_table *table, bool flush_all);
 struct fib_table *fib_trie_unmerge(struct fib_table *main_tb);
 void fib_table_flush_external(struct fib_table *table);
 void fib_free_table(struct fib_table *tb);
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 6df95be96311..fe4f6a624238 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -203,7 +203,7 @@ static void fib_flush(struct net *net)
 		struct fib_table *tb;
 
 		hlist_for_each_entry_safe(tb, tmp, head, tb_hlist)
-			flushed += fib_table_flush(net, tb);
+			flushed += fib_table_flush(net, tb, false);
 	}
 
 	if (flushed)
@@ -1463,7 +1463,7 @@ static void ip_fib_net_exit(struct net *net)
 
 		hlist_for_each_entry_safe(tb, tmp, head, tb_hlist) {
 			hlist_del(&tb->tb_hlist);
-			fib_table_flush(net, tb);
+			fib_table_flush(net, tb, true);
 			fib_free_table(tb);
 		}
 	}
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 237c9f72b265..a573e37e0615 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1856,7 +1856,7 @@ void fib_table_flush_external(struct fib_table *tb)
 }
 
 /* Caller must hold RTNL. */
-int fib_table_flush(struct net *net, struct fib_table *tb)
+int fib_table_flush(struct net *net, struct fib_table *tb, bool flush_all)
 {
 	struct trie *t = (struct trie *)tb->tb_data;
 	struct key_vector *pn = t->kv;
@@ -1904,8 +1904,17 @@ int fib_table_flush(struct net *net, struct fib_table *tb)
 		hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) {
 			struct fib_info *fi = fa->fa_info;
 
-			if (!fi || !(fi->fib_flags & RTNH_F_DEAD) ||
-			    tb->tb_id != fa->tb_id) {
+			if (!fi || tb->tb_id != fa->tb_id ||
+			    (!(fi->fib_flags & RTNH_F_DEAD) &&
+			     !fib_props[fa->fa_type].error)) {
+				slen = fa->fa_slen;
+				continue;
+			}
+
+			/* Do not flush error routes if network namespace is
+			 * not being dismantled
+			 */
+			if (!flush_all && fib_props[fa->fa_type].error) {
 				slen = fa->fa_slen;
 				continue;
 			}
-- 
2.20.1


From 3c66c621cf55c9a3f1046a9f9f5c857abe40f7ae Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Fri, 18 Jan 2019 15:57:59 +0000
Subject: [PATCH 13/21] mlxsw: spectrum_fid: Update dummy FID index

[ Upstream commit a11dcd6497915ba79d95ef4fe2541aaac27f6201 ]

When using a tc flower action of egress mirred redirect, the driver adds
an implicit FID setting action. This implicit action sets a dummy FID to
the packet and is used as part of a design for trapping unmatched flows
in OVS.  While this implicit FID setting action is supposed to be a NOP
when a redirect action is added, in Spectrum-2 the FID record is
consulted as the dummy FID index is an 802.1D FID index and the packet
is dropped instead of being redirected.

Set the dummy FID index value to be within 802.1Q range. This satisfies
both Spectrum-1 which ignores the FID and Spectrum-2 which identifies it
as an 802.1Q FID and will then follow the redirect action.

Fixes: c3ab435466d5 ("mlxsw: spectrum: Extend to support Spectrum-2 ASIC")
Signed-off-by: Nir Dotan <nird@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
index a3db033d7399..b490589ef25c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
@@ -882,8 +882,8 @@ static const struct mlxsw_sp_fid_ops mlxsw_sp_fid_dummy_ops = {
 static const struct mlxsw_sp_fid_family mlxsw_sp_fid_dummy_family = {
 	.type			= MLXSW_SP_FID_TYPE_DUMMY,
 	.fid_size		= sizeof(struct mlxsw_sp_fid),
-	.start_index		= MLXSW_SP_RFID_BASE - 1,
-	.end_index		= MLXSW_SP_RFID_BASE - 1,
+	.start_index		= VLAN_N_VID - 1,
+	.end_index		= VLAN_N_VID - 1,
 	.ops			= &mlxsw_sp_fid_dummy_ops,
 };
 
-- 
2.20.1


From 86d7ce570993718aa6ad40efb8b60b605189023c Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Fri, 18 Jan 2019 15:57:55 +0000
Subject: [PATCH 14/21] mlxsw: pci: Ring CQ's doorbell before RDQ's

When a packet should be trapped to the CPU the device consumes a WQE
(work queue element) from an RDQ (receive descriptor queue) and copies
the packet to the address specified in the WQE. The device then tries to
post a CQE (completion queue element) that contains various metadata
(e.g., ingress port) about the packet to a CQ (completion queue).

In case the device managed to consume a WQE, but did not manage to post
the corresponding CQE, it will get stuck. This unlikely situation can be
triggered due to the scheme the driver is currently using to process
CQEs.

The driver will consume up to 512 CQEs at a time and after processing
each corresponding WQE it will ring the RDQ's doorbell, letting the
device know that a new WQE was posted for it to consume. Only after
processing all the CQEs (up to 512), the driver will ring the CQ's
doorbell, letting the device know that new ones can be posted.

Fix this by having the driver ring the CQ's doorbell for every processed
CQE, but before ringing the RDQ's doorbell. This guarantees that
whenever we post a new WQE, there is a corresponding CQE available. Copy
the currently processed CQE to prevent the device from overwriting it
with a new CQE after ringing the doorbell.

Note that the driver still arms the CQ only after processing all the
pending CQEs, so that interrupts for this CQ will only be delivered
after the driver finished its processing.

Before commit 8404f6f2e8ed ("mlxsw: pci: Allow to use CQEs of version 1
and version 2") the issue was virtually impossible to trigger since the
number of CQEs was twice the number of WQEs and the number of CQEs
processed at a time was equal to the number of available WQEs.

Fixes: 8404f6f2e8ed ("mlxsw: pci: Allow to use CQEs of version 1 and version 2")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Semion Lisyansky <semionl@mellanox.com>
Tested-by: Semion Lisyansky <semionl@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/pci.c    | 12 +++++++-----
 drivers/net/ethernet/mellanox/mlxsw/pci_hw.h |  1 +
 2 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index 5890fdfd62c3..c7901a3f2a79 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -604,29 +604,31 @@ static void mlxsw_pci_cq_tasklet(unsigned long data)
 		u16 wqe_counter = mlxsw_pci_cqe_wqe_counter_get(cqe);
 		u8 sendq = mlxsw_pci_cqe_sr_get(q->u.cq.v, cqe);
 		u8 dqn = mlxsw_pci_cqe_dqn_get(q->u.cq.v, cqe);
+		char ncqe[MLXSW_PCI_CQE_SIZE_MAX];
+
+		memcpy(ncqe, cqe, q->elem_size);
+		mlxsw_pci_queue_doorbell_consumer_ring(mlxsw_pci, q);
 
 		if (sendq) {
 			struct mlxsw_pci_queue *sdq;
 
 			sdq = mlxsw_pci_sdq_get(mlxsw_pci, dqn);
 			mlxsw_pci_cqe_sdq_handle(mlxsw_pci, sdq,
-						 wqe_counter, cqe);
+						 wqe_counter, ncqe);
 			q->u.cq.comp_sdq_count++;
 		} else {
 			struct mlxsw_pci_queue *rdq;
 
 			rdq = mlxsw_pci_rdq_get(mlxsw_pci, dqn);
 			mlxsw_pci_cqe_rdq_handle(mlxsw_pci, rdq,
-						 wqe_counter, q->u.cq.v, cqe);
+						 wqe_counter, q->u.cq.v, ncqe);
 			q->u.cq.comp_rdq_count++;
 		}
 		if (++items == credits)
 			break;
 	}
-	if (items) {
-		mlxsw_pci_queue_doorbell_consumer_ring(mlxsw_pci, q);
+	if (items)
 		mlxsw_pci_queue_doorbell_arm_consumer_ring(mlxsw_pci, q);
-	}
 }
 
 static u16 mlxsw_pci_cq_elem_count(const struct mlxsw_pci_queue *q)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
index 9c601c17f7ae..ffee38e36ce8 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
@@ -53,6 +53,7 @@
 #define MLXSW_PCI_WQE_SIZE	32 /* 32 bytes per element */
 #define MLXSW_PCI_CQE01_SIZE	16 /* 16 bytes per element */
 #define MLXSW_PCI_CQE2_SIZE	32 /* 32 bytes per element */
+#define MLXSW_PCI_CQE_SIZE_MAX	MLXSW_PCI_CQE2_SIZE
 #define MLXSW_PCI_EQE_SIZE	16 /* 16 bytes per element */
 #define MLXSW_PCI_WQE_COUNT	(MLXSW_PCI_AQ_SIZE / MLXSW_PCI_WQE_SIZE)
 #define MLXSW_PCI_CQE01_COUNT	(MLXSW_PCI_AQ_SIZE / MLXSW_PCI_CQE01_SIZE)
-- 
2.20.1


From 50a8a9c622d0f6ad61e46be620b142d5751f0d86 Mon Sep 17 00:00:00 2001
From: Ivan Vecera <ivecera@redhat.com>
Date: Wed, 16 Jan 2019 16:53:52 +0100
Subject: [PATCH 15/21] net/sched: cls_flower: allocate mask dynamically in
 fl_change()

[ Upstream commit 2cddd20147826aef283115abb00012d4dafe3cdb ]

Recent changes (especially 05cd271fd61a ("cls_flower: Support multiple
masks per priority")) in the fl_flow_mask structure grow it and its
current size e.g. on x86_64 with defconfig is 760 bytes and more than
1024 bytes with some debug options enabled. Prior the mentioned commit
its size was 176 bytes (using defconfig on x86_64).
With regard to this fact it's reasonable to allocate this structure
dynamically in fl_change() to reduce its stack size.

v2:
- use kzalloc() instead of kcalloc()

Fixes: 05cd271fd61a ("cls_flower: Support multiple masks per priority")
Cc: Jiri Pirko <jiri@resnulli.us>
Cc: Paul Blakey <paulb@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_flower.c | 19 ++++++++++++++-----
 1 file changed, 14 insertions(+), 5 deletions(-)

diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 208d940464d7..45bc2b72dc1c 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -1176,17 +1176,23 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
 	struct cls_fl_head *head = rtnl_dereference(tp->root);
 	struct cls_fl_filter *fold = *arg;
 	struct cls_fl_filter *fnew;
+	struct fl_flow_mask *mask;
 	struct nlattr **tb;
-	struct fl_flow_mask mask = {};
 	int err;
 
 	if (!tca[TCA_OPTIONS])
 		return -EINVAL;
 
-	tb = kcalloc(TCA_FLOWER_MAX + 1, sizeof(struct nlattr *), GFP_KERNEL);
-	if (!tb)
+	mask = kzalloc(sizeof(struct fl_flow_mask), GFP_KERNEL);
+	if (!mask)
 		return -ENOBUFS;
 
+	tb = kcalloc(TCA_FLOWER_MAX + 1, sizeof(struct nlattr *), GFP_KERNEL);
+	if (!tb) {
+		err = -ENOBUFS;
+		goto errout_mask_alloc;
+	}
+
 	err = nla_parse_nested(tb, TCA_FLOWER_MAX, tca[TCA_OPTIONS],
 			       fl_policy, NULL);
 	if (err < 0)
@@ -1229,12 +1235,12 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
 		}
 	}
 
-	err = fl_set_parms(net, tp, fnew, &mask, base, tb, tca[TCA_RATE], ovr,
+	err = fl_set_parms(net, tp, fnew, mask, base, tb, tca[TCA_RATE], ovr,
 			   tp->chain->tmplt_priv, extack);
 	if (err)
 		goto errout_idr;
 
-	err = fl_check_assign_mask(head, fnew, fold, &mask);
+	err = fl_check_assign_mask(head, fnew, fold, mask);
 	if (err)
 		goto errout_idr;
 
@@ -1278,6 +1284,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
 	}
 
 	kfree(tb);
+	kfree(mask);
 	return 0;
 
 errout_mask:
@@ -1291,6 +1298,8 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
 	kfree(fnew);
 errout_tb:
 	kfree(tb);
+errout_mask_alloc:
+	kfree(mask);
 	return err;
 }
 
-- 
2.20.1


From 4f29d3186b8e5f471ece8ac036d6696859d523b5 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Tue, 15 Jan 2019 11:40:02 -0500
Subject: [PATCH 16/21] udp: with udp_segment release on error path

[ Upstream commit 0f149c9fec3cd720628ecde83bfc6f64c1e7dcb6 ]

Failure __ip_append_data triggers udp_flush_pending_frames, but these
tests happen later. The skb must be freed directly.

Fixes: bec1f6f697362 ("udp: generate gso with UDP_SEGMENT")
Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 16 ++++++++++++----
 net/ipv6/udp.c | 16 ++++++++++++----
 2 files changed, 24 insertions(+), 8 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 1976fddb9e00..ce125f4dc810 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -785,15 +785,23 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4,
 		const int hlen = skb_network_header_len(skb) +
 				 sizeof(struct udphdr);
 
-		if (hlen + cork->gso_size > cork->fragsize)
+		if (hlen + cork->gso_size > cork->fragsize) {
+			kfree_skb(skb);
 			return -EINVAL;
-		if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS)
+		}
+		if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS) {
+			kfree_skb(skb);
 			return -EINVAL;
-		if (sk->sk_no_check_tx)
+		}
+		if (sk->sk_no_check_tx) {
+			kfree_skb(skb);
 			return -EINVAL;
+		}
 		if (skb->ip_summed != CHECKSUM_PARTIAL || is_udplite ||
-		    dst_xfrm(skb_dst(skb)))
+		    dst_xfrm(skb_dst(skb))) {
+			kfree_skb(skb);
 			return -EIO;
+		}
 
 		skb_shinfo(skb)->gso_size = cork->gso_size;
 		skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index d2d97d07ef27..d01ec252cb81 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1056,15 +1056,23 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6,
 		const int hlen = skb_network_header_len(skb) +
 				 sizeof(struct udphdr);
 
-		if (hlen + cork->gso_size > cork->fragsize)
+		if (hlen + cork->gso_size > cork->fragsize) {
+			kfree_skb(skb);
 			return -EINVAL;
-		if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS)
+		}
+		if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS) {
+			kfree_skb(skb);
 			return -EINVAL;
-		if (udp_sk(sk)->no_check6_tx)
+		}
+		if (udp_sk(sk)->no_check6_tx) {
+			kfree_skb(skb);
 			return -EINVAL;
+		}
 		if (skb->ip_summed != CHECKSUM_PARTIAL || is_udplite ||
-		    dst_xfrm(skb_dst(skb)))
+		    dst_xfrm(skb_dst(skb))) {
+			kfree_skb(skb);
 			return -EIO;
+		}
 
 		skb_shinfo(skb)->gso_size = cork->gso_size;
 		skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
-- 
2.20.1


From f5c31d1a3eb1c588989d9e325134bc2329704cb3 Mon Sep 17 00:00:00 2001
From: Olivier Matz <olivier.matz@6wind.com>
Date: Wed, 9 Jan 2019 10:57:21 +0100
Subject: [PATCH 17/21] ip6_gre: fix tunnel list corruption for x-netns

[ Upstream commit ab5098fa25b91cb6fe0a0676f17abb64f2bbf024 ]

In changelink ops, the ip6gre_net pointer is retrieved from
dev_net(dev), which is wrong in case of x-netns. Thus, the tunnel is not
unlinked from its current list and is relinked into another net
namespace. This corrupts the tunnel lists and can later trigger a kernel
oops.

Fix this by retrieving the netns from device private area.

Fixes: c8632fc30bb0 ("net: ip6_gre: Split up ip6gre_changelink()")
Cc: Petr Machata <petrm@mellanox.com>
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 0f7d434c1eed..6ac260adfc9c 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -2029,9 +2029,9 @@ static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[],
 			     struct nlattr *data[],
 			     struct netlink_ext_ack *extack)
 {
-	struct ip6gre_net *ign = net_generic(dev_net(dev), ip6gre_net_id);
+	struct ip6_tnl *t = netdev_priv(dev);
+	struct ip6gre_net *ign = net_generic(t->net, ip6gre_net_id);
 	struct __ip6_tnl_parm p;
-	struct ip6_tnl *t;
 
 	t = ip6gre_changelink_common(dev, tb, data, &p, extack);
 	if (IS_ERR(t))
-- 
2.20.1


From 2b11f01c7e42f1faa798e2c141b891b2253f56b4 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 14 Jan 2019 18:10:06 +0800
Subject: [PATCH 18/21] erspan: build the header with the right proto according
 to erspan_ver

[ Upstream commit 20704bd1633dd5afb29a321d3a615c9c8e9c9d05 ]

As said in draft-foschiano-erspan-03#section4:

   Different frame variants known as "ERSPAN Types" can be
   distinguished based on the GRE "Protocol Type" field value: Type I
   and II's value is 0x88BE while Type III's is 0x22EB [ETYPES].

So set it properly in erspan_xmit() according to erspan_ver. While at
it, also remove the unused parameter 'proto' in erspan_fb_xmit().

Fixes: 94d7d8f29287 ("ip6_gre: add erspan v2 support")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_gre.c  | 23 ++++++++++++++---------
 net/ipv6/ip6_gre.c |  6 ++++--
 2 files changed, 18 insertions(+), 11 deletions(-)

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 0fe9419bd12b..3407a82d4549 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -567,8 +567,7 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev,
 	dev->stats.tx_dropped++;
 }
 
-static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev,
-			   __be16 proto)
+static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	struct ip_tunnel_info *tun_info;
@@ -576,10 +575,10 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev,
 	struct erspan_metadata *md;
 	struct rtable *rt = NULL;
 	bool truncate = false;
+	__be16 df, proto;
 	struct flowi4 fl;
 	int tunnel_hlen;
 	int version;
-	__be16 df;
 	int nhoff;
 	int thoff;
 
@@ -624,18 +623,20 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev,
 	if (version == 1) {
 		erspan_build_header(skb, ntohl(tunnel_id_to_key32(key->tun_id)),
 				    ntohl(md->u.index), truncate, true);
+		proto = htons(ETH_P_ERSPAN);
 	} else if (version == 2) {
 		erspan_build_header_v2(skb,
 				       ntohl(tunnel_id_to_key32(key->tun_id)),
 				       md->u.md2.dir,
 				       get_hwid(&md->u.md2),
 				       truncate, true);
+		proto = htons(ETH_P_ERSPAN2);
 	} else {
 		goto err_free_rt;
 	}
 
 	gre_build_header(skb, 8, TUNNEL_SEQ,
-			 htons(ETH_P_ERSPAN), 0, htonl(tunnel->o_seqno++));
+			 proto, 0, htonl(tunnel->o_seqno++));
 
 	df = key->tun_flags & TUNNEL_DONT_FRAGMENT ?  htons(IP_DF) : 0;
 
@@ -719,12 +720,13 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb,
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	bool truncate = false;
+	__be16 proto;
 
 	if (!pskb_inet_may_pull(skb))
 		goto free_skb;
 
 	if (tunnel->collect_md) {
-		erspan_fb_xmit(skb, dev, skb->protocol);
+		erspan_fb_xmit(skb, dev);
 		return NETDEV_TX_OK;
 	}
 
@@ -740,19 +742,22 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb,
 	}
 
 	/* Push ERSPAN header */
-	if (tunnel->erspan_ver == 1)
+	if (tunnel->erspan_ver == 1) {
 		erspan_build_header(skb, ntohl(tunnel->parms.o_key),
 				    tunnel->index,
 				    truncate, true);
-	else if (tunnel->erspan_ver == 2)
+		proto = htons(ETH_P_ERSPAN);
+	} else if (tunnel->erspan_ver == 2) {
 		erspan_build_header_v2(skb, ntohl(tunnel->parms.o_key),
 				       tunnel->dir, tunnel->hwid,
 				       truncate, true);
-	else
+		proto = htons(ETH_P_ERSPAN2);
+	} else {
 		goto free_skb;
+	}
 
 	tunnel->parms.o_flags &= ~TUNNEL_KEY;
-	__gre_xmit(skb, dev, &tunnel->parms.iph, htons(ETH_P_ERSPAN));
+	__gre_xmit(skb, dev, &tunnel->parms.iph, proto);
 	return NETDEV_TX_OK;
 
 free_skb:
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 6ac260adfc9c..a38e23a8a280 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -920,6 +920,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 	__u8 dsfield = false;
 	struct flowi6 fl6;
 	int err = -EINVAL;
+	__be16 proto;
 	__u32 mtu;
 	int nhoff;
 	int thoff;
@@ -1033,8 +1034,9 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 	}
 
 	/* Push GRE header. */
-	gre_build_header(skb, 8, TUNNEL_SEQ,
-			 htons(ETH_P_ERSPAN), 0, htonl(t->o_seqno++));
+	proto = (t->parms.erspan_ver == 1) ? htons(ETH_P_ERSPAN)
+					   : htons(ETH_P_ERSPAN2);
+	gre_build_header(skb, 8, TUNNEL_SEQ, proto, 0, htonl(t->o_seqno++));
 
 	/* TooBig packet may have updated dst->dev's mtu */
 	if (!t->parms.collect_md && dst && dst_mtu(dst) > dst->dev->mtu)
-- 
2.20.1


From f6b9479dcc52149102a3d13d172087c83db50358 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Fri, 11 Jan 2019 00:15:21 +0100
Subject: [PATCH 19/21] net: phy: marvell: Fix deadlock from wrong locking
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit e0a7328fad9979104f73e19bedca821ef3262ae1 ]

m88e1318_set_wol() takes the lock as part of phy_select_page(). Don't
take the lock again with phy_read(), use the unlocked __phy_read().

Fixes: 424ca4c55121 ("net: phy: marvell: fix paged access races")
Reported-by: Åke Rehnman <ake.rehnman@gmail.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/marvell.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index 426097e7a275..f46da6262abe 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -1430,7 +1430,7 @@ static int m88e1318_set_wol(struct phy_device *phydev,
 		 * before enabling it if !phy_interrupt_is_valid()
 		 */
 		if (!phy_interrupt_is_valid(phydev))
-			phy_read(phydev, MII_M1011_IEVENT);
+			__phy_read(phydev, MII_M1011_IEVENT);
 
 		/* Enable the WOL interrupt */
 		err = __phy_modify(phydev, MII_88E1318S_PHY_CSIER, 0,
-- 
2.20.1


From 57bb70ab8ce2648ec571a0513d5e88d833328ee3 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Thu, 10 Jan 2019 11:17:42 +0800
Subject: [PATCH 20/21] ip6_gre: update version related info when changing link

[ Upstream commit 80b3671e9377916bf2b02e56113fa7377ce5705a ]

We forgot to update ip6erspan version related info when changing link,
which will cause setting new hwid failed.

Reported-by: Jianlin Shi <jishi@redhat.com>
Fixes: 94d7d8f292870 ("ip6_gre: add erspan v2 support")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index a38e23a8a280..b529a79ac222 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1169,6 +1169,10 @@ static void ip6gre_tnl_copy_tnl_parm(struct ip6_tnl *t,
 	t->parms.i_flags = p->i_flags;
 	t->parms.o_flags = p->o_flags;
 	t->parms.fwmark = p->fwmark;
+	t->parms.erspan_ver = p->erspan_ver;
+	t->parms.index = p->index;
+	t->parms.dir = p->dir;
+	t->parms.hwid = p->hwid;
 	dst_cache_reset(&t->dst_cache);
 }
 
-- 
2.20.1


From 52c540dcfa6bbecff8e665df9e1453d2038e93c4 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Thu, 10 Jan 2019 14:40:33 -0500
Subject: [PATCH 21/21] tcp: allow MSG_ZEROCOPY transmission also in CLOSE_WAIT
 state

[ Upstream commit 13d7f46386e060df31b727c9975e38306fa51e7a ]

TCP transmission with MSG_ZEROCOPY fails if the peer closes its end of
the connection and so transitions this socket to CLOSE_WAIT state.

Transmission in close wait state is acceptable. Other similar tests in
the stack (e.g., in FastOpen) accept both states. Relax this test, too.

Link: https://www.mail-archive.com/netdev@vger.kernel.org/msg276886.html
Link: https://www.mail-archive.com/netdev@vger.kernel.org/msg227390.html
Fixes: f214f915e7db ("tcp: enable MSG_ZEROCOPY")
Reported-by: Marek Majkowski <marek@cloudflare.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
CC: Yuchung Cheng <ycheng@google.com>
CC: Neal Cardwell <ncardwell@google.com>
CC: Soheil Hassas Yeganeh <soheil@google.com>
CC: Alexey Kodanev <alexey.kodanev@oracle.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 9e6bc4d6daa7..40cbe5609663 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1186,7 +1186,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 	flags = msg->msg_flags;
 
 	if (flags & MSG_ZEROCOPY && size && sock_flag(sk, SOCK_ZEROCOPY)) {
-		if (sk->sk_state != TCP_ESTABLISHED) {
+		if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) {
 			err = -EINVAL;
 			goto out_err;
 		}
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Fri, Jan 25, 2019 at 04:18:32PM -0800, David Miller wrote:
> 
> Please queue up the following bug fixes for 4.19 and 4.20 -stable,
> respectively.
> 
> Thanks!



All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 104 bytes --]


Please queue up the following networking bug fixes for v4.19 and v4.20
-stable, respectively.

Thanks!

[-- Attachment #2: net_419.mbox --]
[-- Type: Application/Octet-Stream, Size: 90181 bytes --]

From 449c71b179fd2526eca080d84d3577d7c7399843 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 2 Jan 2019 18:57:09 -0800
Subject: [PATCH 01/30] ipv6: Consider sk_bound_dev_if when binding a socket to
 an address

[ Upstream commit c5ee066333ebc322a24a00a743ed941a0c68617e ]

IPv6 does not consider if the socket is bound to a device when binding
to an address. The result is that a socket can be bound to eth0 and then
bound to the address of eth1. If the device is a VRF, the result is that
a socket can only be bound to an address in the default VRF.

Resolve by considering the device if sk_bound_dev_if is set.

This problem exists from the beginning of git history.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/af_inet6.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 506b2ae07bb3..79fcd9550fd2 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -361,6 +361,9 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
 					err = -EINVAL;
 					goto out_unlock;
 				}
+			}
+
+			if (sk->sk_bound_dev_if) {
 				dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if);
 				if (!dev) {
 					err = -ENODEV;
-- 
2.20.1


From 8f6413294097ee61acf52a23f95e315ccb31469b Mon Sep 17 00:00:00 2001
From: Yohei Kanemaru <yohei.kanemaru@gmail.com>
Date: Tue, 29 Jan 2019 15:52:34 +0900
Subject: [PATCH 02/30] ipv6: sr: clear IP6CB(skb) on SRH ip4ip6 encapsulation

[ Upstream commit ef489749aae508e6f17886775c075f12ff919fb1 ]

skb->cb may contain data from previous layers (in an observed case
IPv4 with L3 Master Device). In the observed scenario, the data in
IPCB(skb)->frags was misinterpreted as IP6CB(skb)->frag_max_size,
eventually caused an unexpected IPv6 fragmentation in ip6_fragment()
through ip6_finish_output().

This patch clears IP6CB(skb), which potentially contains garbage data,
on the SRH ip4ip6 encapsulation.

Fixes: 32d99d0b6702 ("ipv6: sr: add support for ip4ip6 encapsulation")
Signed-off-by: Yohei Kanemaru <yohei.kanemaru@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/seg6_iptunnel.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 8181ee7e1e27..ee5403cbe655 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -146,6 +146,8 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
 	} else {
 		ip6_flow_hdr(hdr, 0, flowlabel);
 		hdr->hop_limit = ip6_dst_hoplimit(skb_dst(skb));
+
+		memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
 	}
 
 	hdr->nexthdr = NEXTHDR_ROUTING;
-- 
2.20.1


From ec121177dda5a801a25a724054ff64c36bec1c6a Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 30 Jan 2019 12:49:48 +0100
Subject: [PATCH 03/30] ipvlan, l3mdev: fix broken l3s mode wrt local routes

[ Upstream commit d5256083f62e2720f75bb3c5a928a0afe47d6bc3 ]

While implementing ipvlan l3 and l3s mode for kubernetes CNI plugin,
I ran into the issue that while l3 mode is working fine, l3s mode
does not have any connectivity to kube-apiserver and hence all pods
end up in Error state as well. The ipvlan master device sits on
top of a bond device and hostns traffic to kube-apiserver (also running
in hostns) is DNATed from 10.152.183.1:443 to 139.178.29.207:37573
where the latter is the address of the bond0. While in l3 mode, a
curl to https://10.152.183.1:443 or to https://139.178.29.207:37573
works fine from hostns, neither of them do in case of l3s. In the
latter only a curl to https://127.0.0.1:37573 appeared to work where
for local addresses of bond0 I saw kernel suddenly starting to emit
ARP requests to query HW address of bond0 which remained unanswered
and neighbor entries in INCOMPLETE state. These ARP requests only
happen while in l3s.

Debugging this further, I found the issue is that l3s mode is piggy-
backing on l3 master device, and in this case local routes are using
l3mdev_master_dev_rcu(dev) instead of net->loopback_dev as per commit
f5a0aab84b74 ("net: ipv4: dst for local input routes should use l3mdev
if relevant") and 5f02ce24c269 ("net: l3mdev: Allow the l3mdev to be
a loopback"). I found that reverting them back into using the
net->loopback_dev fixed ipvlan l3s connectivity and got everything
working for the CNI.

Now judging from 4fbae7d83c98 ("ipvlan: Introduce l3s mode") and the
l3mdev paper in [0] the only sole reason why ipvlan l3s is relying
on l3 master device is to get the l3mdev_ip_rcv() receive hook for
setting the dst entry of the input route without adding its own
ipvlan specific hacks into the receive path, however, any l3 domain
semantics beyond just that are breaking l3s operation. Note that
ipvlan also has the ability to dynamically switch its internal
operation from l3 to l3s for all ports via ipvlan_set_port_mode()
at runtime. In any case, l3 vs l3s soley distinguishes itself by
'de-confusing' netfilter through switching skb->dev to ipvlan slave
device late in NF_INET_LOCAL_IN before handing the skb to L4.

Minimal fix taken here is to add a IFF_L3MDEV_RX_HANDLER flag which,
if set from ipvlan setup, gets us only the wanted l3mdev_l3_rcv() hook
without any additional l3mdev semantics on top. This should also have
minimal impact since dev->priv_flags is already hot in cache. With
this set, l3s mode is working fine and I also get things like
masquerading pod traffic on the ipvlan master properly working.

  [0] https://netdevconf.org/1.2/papers/ahern-what-is-l3mdev-paper.pdf

Fixes: f5a0aab84b74 ("net: ipv4: dst for local input routes should use l3mdev if relevant")
Fixes: 5f02ce24c269 ("net: l3mdev: Allow the l3mdev to be a loopback")
Fixes: 4fbae7d83c98 ("ipvlan: Introduce l3s mode")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Mahesh Bandewar <maheshb@google.com>
Cc: David Ahern <dsa@cumulusnetworks.com>
Cc: Florian Westphal <fw@strlen.de>
Cc: Martynas Pumputis <m@lambda.lt>
Acked-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ipvlan/ipvlan_main.c | 6 +++---
 include/linux/netdevice.h        | 8 ++++++++
 include/net/l3mdev.h             | 3 ++-
 3 files changed, 13 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 4a949569ec4c..5fb541897863 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -97,12 +97,12 @@ static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval)
 			err = ipvlan_register_nf_hook(read_pnet(&port->pnet));
 			if (!err) {
 				mdev->l3mdev_ops = &ipvl_l3mdev_ops;
-				mdev->priv_flags |= IFF_L3MDEV_MASTER;
+				mdev->priv_flags |= IFF_L3MDEV_RX_HANDLER;
 			} else
 				goto fail;
 		} else if (port->mode == IPVLAN_MODE_L3S) {
 			/* Old mode was L3S */
-			mdev->priv_flags &= ~IFF_L3MDEV_MASTER;
+			mdev->priv_flags &= ~IFF_L3MDEV_RX_HANDLER;
 			ipvlan_unregister_nf_hook(read_pnet(&port->pnet));
 			mdev->l3mdev_ops = NULL;
 		}
@@ -162,7 +162,7 @@ static void ipvlan_port_destroy(struct net_device *dev)
 	struct sk_buff *skb;
 
 	if (port->mode == IPVLAN_MODE_L3S) {
-		dev->priv_flags &= ~IFF_L3MDEV_MASTER;
+		dev->priv_flags &= ~IFF_L3MDEV_RX_HANDLER;
 		ipvlan_unregister_nf_hook(dev_net(dev));
 		dev->l3mdev_ops = NULL;
 	}
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d837dad24b4c..21fef8c5eca7 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1455,6 +1455,7 @@ struct net_device_ops {
  * @IFF_NO_RX_HANDLER: device doesn't support the rx_handler hook
  * @IFF_FAILOVER: device is a failover master device
  * @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device
+ * @IFF_L3MDEV_RX_HANDLER: only invoke the rx handler of L3 master device
  */
 enum netdev_priv_flags {
 	IFF_802_1Q_VLAN			= 1<<0,
@@ -1486,6 +1487,7 @@ enum netdev_priv_flags {
 	IFF_NO_RX_HANDLER		= 1<<26,
 	IFF_FAILOVER			= 1<<27,
 	IFF_FAILOVER_SLAVE		= 1<<28,
+	IFF_L3MDEV_RX_HANDLER		= 1<<29,
 };
 
 #define IFF_802_1Q_VLAN			IFF_802_1Q_VLAN
@@ -1516,6 +1518,7 @@ enum netdev_priv_flags {
 #define IFF_NO_RX_HANDLER		IFF_NO_RX_HANDLER
 #define IFF_FAILOVER			IFF_FAILOVER
 #define IFF_FAILOVER_SLAVE		IFF_FAILOVER_SLAVE
+#define IFF_L3MDEV_RX_HANDLER		IFF_L3MDEV_RX_HANDLER
 
 /**
  *	struct net_device - The DEVICE structure.
@@ -4464,6 +4467,11 @@ static inline bool netif_supports_nofcs(struct net_device *dev)
 	return dev->priv_flags & IFF_SUPP_NOFCS;
 }
 
+static inline bool netif_has_l3_rx_handler(const struct net_device *dev)
+{
+	return dev->priv_flags & IFF_L3MDEV_RX_HANDLER;
+}
+
 static inline bool netif_is_l3_master(const struct net_device *dev)
 {
 	return dev->priv_flags & IFF_L3MDEV_MASTER;
diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h
index 3832099289c5..128487658ff7 100644
--- a/include/net/l3mdev.h
+++ b/include/net/l3mdev.h
@@ -142,7 +142,8 @@ struct sk_buff *l3mdev_l3_rcv(struct sk_buff *skb, u16 proto)
 
 	if (netif_is_l3_slave(skb->dev))
 		master = netdev_master_upper_dev_get_rcu(skb->dev);
-	else if (netif_is_l3_master(skb->dev))
+	else if (netif_is_l3_master(skb->dev) ||
+		 netif_has_l3_rx_handler(skb->dev))
 		master = skb->dev;
 
 	if (master && master->l3mdev_ops->l3mdev_l3_rcv)
-- 
2.20.1


From 8bf79fb7c8b8bb366cac08a838aa6904d256e08e Mon Sep 17 00:00:00 2001
From: Jacob Wen <jian.w.wen@oracle.com>
Date: Thu, 31 Jan 2019 15:18:56 +0800
Subject: [PATCH 04/30] l2tp: copy 4 more bytes to linear part if necessary

[ Upstream commit 91c524708de6207f59dd3512518d8a1c7b434ee3 ]

The size of L2TPv2 header with all optional fields is 14 bytes.
l2tp_udp_recv_core only moves 10 bytes to the linear part of a
skb. This may lead to l2tp_recv_common read data outside of a skb.

This patch make sure that there is at least 14 bytes in the linear
part of a skb to meet the maximum need of l2tp_udp_recv_core and
l2tp_recv_common. The minimum size of both PPP HDLC-like frame and
Ethernet frame is larger than 14 bytes, so we are safe to do so.

Also remove L2TP_HDR_SIZE_NOSEQ, it is unused now.

Fixes: fd558d186df2 ("l2tp: Split pppol2tp patch into separate l2tp and ppp parts")
Suggested-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: Jacob Wen <jian.w.wen@oracle.com>
Acked-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 26f1d435696a..9accaec15c32 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -83,8 +83,7 @@
 #define L2TP_SLFLAG_S	   0x40000000
 #define L2TP_SL_SEQ_MASK   0x00ffffff
 
-#define L2TP_HDR_SIZE_SEQ		10
-#define L2TP_HDR_SIZE_NOSEQ		6
+#define L2TP_HDR_SIZE_MAX		14
 
 /* Default trace flags */
 #define L2TP_DEFAULT_DEBUG_FLAGS	0
@@ -808,7 +807,7 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb)
 	__skb_pull(skb, sizeof(struct udphdr));
 
 	/* Short packet? */
-	if (!pskb_may_pull(skb, L2TP_HDR_SIZE_SEQ)) {
+	if (!pskb_may_pull(skb, L2TP_HDR_SIZE_MAX)) {
 		l2tp_info(tunnel, L2TP_MSG_DATA,
 			  "%s: recv short packet (len=%d)\n",
 			  tunnel->name, skb->len);
-- 
2.20.1


From 7aa2991f74567ce22dea33db37557475f2705e8e Mon Sep 17 00:00:00 2001
From: Jacob Wen <jian.w.wen@oracle.com>
Date: Wed, 30 Jan 2019 14:55:14 +0800
Subject: [PATCH 05/30] l2tp: fix reading optional fields of L2TPv3

[ Upstream commit 4522a70db7aa5e77526a4079628578599821b193 ]

Use pskb_may_pull() to make sure the optional fields are in skb linear
parts, so we can safely read them later.

It's easy to reproduce the issue with a net driver that supports paged
skb data. Just create a L2TPv3 over IP tunnel and then generates some
network traffic.
Once reproduced, rx err in /sys/kernel/debug/l2tp/tunnels will increase.

Changes in v4:
1. s/l2tp_v3_pull_opt/l2tp_v3_ensure_opt_in_linear/
2. s/tunnel->version != L2TP_HDR_VER_2/tunnel->version == L2TP_HDR_VER_3/
3. Add 'Fixes' in commit messages.

Changes in v3:
1. To keep consistency, move the code out of l2tp_recv_common.
2. Use "net" instead of "net-next", since this is a bug fix.

Changes in v2:
1. Only fix L2TPv3 to make code simple.
   To fix both L2TPv3 and L2TPv2, we'd better refactor l2tp_recv_common.
   It's complicated to do so.
2. Reloading pointers after pskb_may_pull

Fixes: f7faffa3ff8e ("l2tp: Add L2TPv3 protocol support")
Fixes: 0d76751fad77 ("l2tp: Add L2TPv3 IP encapsulation (no UDP) support")
Fixes: a32e0eec7042 ("l2tp: introduce L2TPv3 IP encapsulation support for IPv6")
Signed-off-by: Jacob Wen <jian.w.wen@oracle.com>
Acked-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c |  4 ++++
 net/l2tp/l2tp_core.h | 20 ++++++++++++++++++++
 net/l2tp/l2tp_ip.c   |  3 +++
 net/l2tp/l2tp_ip6.c  |  3 +++
 4 files changed, 30 insertions(+)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 9accaec15c32..fed6becc5daf 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -883,6 +883,10 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb)
 		goto error;
 	}
 
+	if (tunnel->version == L2TP_HDR_VER_3 &&
+	    l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr))
+		goto error;
+
 	l2tp_recv_common(session, skb, ptr, optr, hdrflags, length);
 	l2tp_session_dec_refcount(session);
 
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 9c9afe94d389..b2ce90260c35 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -301,6 +301,26 @@ static inline bool l2tp_tunnel_uses_xfrm(const struct l2tp_tunnel *tunnel)
 }
 #endif
 
+static inline int l2tp_v3_ensure_opt_in_linear(struct l2tp_session *session, struct sk_buff *skb,
+					       unsigned char **ptr, unsigned char **optr)
+{
+	int opt_len = session->peer_cookie_len + l2tp_get_l2specific_len(session);
+
+	if (opt_len > 0) {
+		int off = *ptr - *optr;
+
+		if (!pskb_may_pull(skb, off + opt_len))
+			return -1;
+
+		if (skb->data != *optr) {
+			*optr = skb->data;
+			*ptr = skb->data + off;
+		}
+	}
+
+	return 0;
+}
+
 #define l2tp_printk(ptr, type, func, fmt, ...)				\
 do {									\
 	if (((ptr)->debug) & (type))					\
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 35f6f86d4dcc..d4c60523c549 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -165,6 +165,9 @@ static int l2tp_ip_recv(struct sk_buff *skb)
 		print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length);
 	}
 
+	if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr))
+		goto discard_sess;
+
 	l2tp_recv_common(session, skb, ptr, optr, 0, skb->len);
 	l2tp_session_dec_refcount(session);
 
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 237f1a4a0b0c..0ae6899edac0 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -178,6 +178,9 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
 		print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length);
 	}
 
+	if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr))
+		goto discard_sess;
+
 	l2tp_recv_common(session, skb, ptr, optr, 0, skb->len);
 	l2tp_session_dec_refcount(session);
 
-- 
2.20.1


From 3aa2eb4b309c5e212bfa3a5a8ca4ac369b6de0c1 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Mon, 28 Jan 2019 22:23:48 +0100
Subject: [PATCH 06/30] net: ip_gre: always reports o_key to userspace

[ Upstream commit feaf5c796b3f0240f10d0d6d0b686715fd58a05b ]

Erspan protocol (version 1 and 2) relies on o_key to configure
session id header field. However TUNNEL_KEY bit is cleared in
erspan_xmit since ERSPAN protocol does not set the key field
of the external GRE header and so the configured o_key is not reported
to userspace. The issue can be triggered with the following reproducer:

$ip link add erspan1 type erspan local 192.168.0.1 remote 192.168.0.2 \
    key 1 seq erspan_ver 1
$ip link set erspan1 up
$ip -d link sh erspan1

erspan1@NONE: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1450 qdisc pfifo_fast state UNKNOWN mode DEFAULT
  link/ether 52:aa:99:95:9a:b5 brd ff:ff:ff:ff:ff:ff promiscuity 0 minmtu 68 maxmtu 1500
  erspan remote 192.168.0.2 local 192.168.0.1 ttl inherit ikey 0.0.0.1 iseq oseq erspan_index 0

Fix the issue adding TUNNEL_KEY bit to the o_flags parameter in
ipgre_fill_info

Fixes: 84e54fe0a5ea ("gre: introduce native tunnel support for ERSPAN")
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_gre.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 0bfad3e72509..c097be590976 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1471,12 +1471,17 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev)
 {
 	struct ip_tunnel *t = netdev_priv(dev);
 	struct ip_tunnel_parm *p = &t->parms;
+	__be16 o_flags = p->o_flags;
+
+	if ((t->erspan_ver == 1 || t->erspan_ver == 2) &&
+	    !t->collect_md)
+		o_flags |= TUNNEL_KEY;
 
 	if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) ||
 	    nla_put_be16(skb, IFLA_GRE_IFLAGS,
 			 gre_tnl_flags_to_gre_flags(p->i_flags)) ||
 	    nla_put_be16(skb, IFLA_GRE_OFLAGS,
-			 gre_tnl_flags_to_gre_flags(p->o_flags)) ||
+			 gre_tnl_flags_to_gre_flags(o_flags)) ||
 	    nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) ||
 	    nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) ||
 	    nla_put_in_addr(skb, IFLA_GRE_LOCAL, p->iph.saddr) ||
-- 
2.20.1


From b1e8bfffc4f357092f7de9beb1ae410d704754f4 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Fri, 18 Jan 2019 12:05:39 +0100
Subject: [PATCH 07/30] net: ip_gre: use erspan key field for tunnel lookup

[ Upstream commit cb73ee40b1b381eaf3749e6dbeed567bb38e5258 ]

Use ERSPAN key header field as tunnel key in gre_parse_header routine
since ERSPAN protocol sets the key field of the external GRE header to
0 resulting in a tunnel lookup fail in ip6gre_err.
In addition remove key field parsing and pskb_may_pull check in
erspan_rcv and ip6erspan_rcv

Fixes: 5a963eb61b7c ("ip6_gre: Add ERSPAN native tunnel support")
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/gre_demux.c | 17 +++++++++++++++++
 net/ipv4/ip_gre.c    |  9 ---------
 net/ipv6/ip6_gre.c   |  4 ----
 3 files changed, 17 insertions(+), 13 deletions(-)

diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c
index b798862b6be5..f21ea6125fc2 100644
--- a/net/ipv4/gre_demux.c
+++ b/net/ipv4/gre_demux.c
@@ -25,6 +25,7 @@
 #include <linux/spinlock.h>
 #include <net/protocol.h>
 #include <net/gre.h>
+#include <net/erspan.h>
 
 #include <net/icmp.h>
 #include <net/route.h>
@@ -118,6 +119,22 @@ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 			hdr_len += 4;
 	}
 	tpi->hdr_len = hdr_len;
+
+	/* ERSPAN ver 1 and 2 protocol sets GRE key field
+	 * to 0 and sets the configured key in the
+	 * inner erspan header field
+	 */
+	if (greh->protocol == htons(ETH_P_ERSPAN) ||
+	    greh->protocol == htons(ETH_P_ERSPAN2)) {
+		struct erspan_base_hdr *ershdr;
+
+		if (!pskb_may_pull(skb, nhs + hdr_len + sizeof(*ershdr)))
+			return -EINVAL;
+
+		ershdr = (struct erspan_base_hdr *)options;
+		tpi->key = cpu_to_be32(get_session_id(ershdr));
+	}
+
 	return hdr_len;
 }
 EXPORT_SYMBOL(gre_parse_header);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index c097be590976..f199945f6e4a 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -269,20 +269,11 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 	int len;
 
 	itn = net_generic(net, erspan_net_id);
-	len = gre_hdr_len + sizeof(*ershdr);
-
-	/* Check based hdr len */
-	if (unlikely(!pskb_may_pull(skb, len)))
-		return PACKET_REJECT;
 
 	iph = ip_hdr(skb);
 	ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len);
 	ver = ershdr->ver;
 
-	/* The original GRE header does not have key field,
-	 * Use ERSPAN 10-bit session ID as key.
-	 */
-	tpi->key = cpu_to_be32(get_session_id(ershdr));
 	tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex,
 				  tpi->flags | TUNNEL_KEY,
 				  iph->saddr, iph->daddr, tpi->key);
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 345e6839f031..580907eb42cd 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -550,13 +550,9 @@ static int ip6erspan_rcv(struct sk_buff *skb, int gre_hdr_len,
 	struct ip6_tnl *tunnel;
 	u8 ver;
 
-	if (unlikely(!pskb_may_pull(skb, sizeof(*ershdr))))
-		return PACKET_REJECT;
-
 	ipv6h = ipv6_hdr(skb);
 	ershdr = (struct erspan_base_hdr *)skb->data;
 	ver = ershdr->ver;
-	tpi->key = cpu_to_be32(get_session_id(ershdr));
 
 	tunnel = ip6gre_tunnel_lookup(skb->dev,
 				      &ipv6h->saddr, &ipv6h->daddr, tpi->key,
-- 
2.20.1


From 4ea1f3c642532475b2c26d95fd6a69b0b9b73ab0 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Tue, 22 Jan 2019 15:19:44 +0200
Subject: [PATCH 08/30] net/mlx4_core: Add masking for a few queries on HCA
 caps

[ Upstream commit a40ded6043658444ee4dd6ee374119e4e98b33fc ]

Driver reads the query HCA capabilities without the corresponding masks.
Without the correct masks, the base addresses of the queues are
unaligned.  In addition some reserved bits were wrongly read.  Using the
correct masks, ensures alignment of the base addresses and allows future
firmware versions safe use of the reserved bits.

Fixes: ab9c17a009ee ("mlx4_core: Modify driver initialization flow to accommodate SRIOV for Ethernet")
Fixes: 0ff1fb654bec ("{NET, IB}/mlx4: Add device managed flow steering firmware API")
Signed-off-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/fw.c | 75 +++++++++++++++----------
 1 file changed, 46 insertions(+), 29 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index babcfd9c0571..75213046563c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -2064,9 +2064,11 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev,
 {
 	struct mlx4_cmd_mailbox *mailbox;
 	__be32 *outbox;
+	u64 qword_field;
 	u32 dword_field;
-	int err;
+	u16 word_field;
 	u8 byte_field;
+	int err;
 	static const u8 a0_dmfs_query_hw_steering[] =  {
 		[0] = MLX4_STEERING_DMFS_A0_DEFAULT,
 		[1] = MLX4_STEERING_DMFS_A0_DYNAMIC,
@@ -2094,19 +2096,32 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev,
 
 	/* QPC/EEC/CQC/EQC/RDMARC attributes */
 
-	MLX4_GET(param->qpc_base,      outbox, INIT_HCA_QPC_BASE_OFFSET);
-	MLX4_GET(param->log_num_qps,   outbox, INIT_HCA_LOG_QP_OFFSET);
-	MLX4_GET(param->srqc_base,     outbox, INIT_HCA_SRQC_BASE_OFFSET);
-	MLX4_GET(param->log_num_srqs,  outbox, INIT_HCA_LOG_SRQ_OFFSET);
-	MLX4_GET(param->cqc_base,      outbox, INIT_HCA_CQC_BASE_OFFSET);
-	MLX4_GET(param->log_num_cqs,   outbox, INIT_HCA_LOG_CQ_OFFSET);
-	MLX4_GET(param->altc_base,     outbox, INIT_HCA_ALTC_BASE_OFFSET);
-	MLX4_GET(param->auxc_base,     outbox, INIT_HCA_AUXC_BASE_OFFSET);
-	MLX4_GET(param->eqc_base,      outbox, INIT_HCA_EQC_BASE_OFFSET);
-	MLX4_GET(param->log_num_eqs,   outbox, INIT_HCA_LOG_EQ_OFFSET);
-	MLX4_GET(param->num_sys_eqs,   outbox, INIT_HCA_NUM_SYS_EQS_OFFSET);
-	MLX4_GET(param->rdmarc_base,   outbox, INIT_HCA_RDMARC_BASE_OFFSET);
-	MLX4_GET(param->log_rd_per_qp, outbox, INIT_HCA_LOG_RD_OFFSET);
+	MLX4_GET(qword_field, outbox, INIT_HCA_QPC_BASE_OFFSET);
+	param->qpc_base = qword_field & ~((u64)0x1f);
+	MLX4_GET(byte_field, outbox, INIT_HCA_LOG_QP_OFFSET);
+	param->log_num_qps = byte_field & 0x1f;
+	MLX4_GET(qword_field, outbox, INIT_HCA_SRQC_BASE_OFFSET);
+	param->srqc_base = qword_field & ~((u64)0x1f);
+	MLX4_GET(byte_field, outbox, INIT_HCA_LOG_SRQ_OFFSET);
+	param->log_num_srqs = byte_field & 0x1f;
+	MLX4_GET(qword_field, outbox, INIT_HCA_CQC_BASE_OFFSET);
+	param->cqc_base = qword_field & ~((u64)0x1f);
+	MLX4_GET(byte_field, outbox, INIT_HCA_LOG_CQ_OFFSET);
+	param->log_num_cqs = byte_field & 0x1f;
+	MLX4_GET(qword_field, outbox, INIT_HCA_ALTC_BASE_OFFSET);
+	param->altc_base = qword_field;
+	MLX4_GET(qword_field, outbox, INIT_HCA_AUXC_BASE_OFFSET);
+	param->auxc_base = qword_field;
+	MLX4_GET(qword_field, outbox, INIT_HCA_EQC_BASE_OFFSET);
+	param->eqc_base = qword_field & ~((u64)0x1f);
+	MLX4_GET(byte_field, outbox, INIT_HCA_LOG_EQ_OFFSET);
+	param->log_num_eqs = byte_field & 0x1f;
+	MLX4_GET(word_field, outbox, INIT_HCA_NUM_SYS_EQS_OFFSET);
+	param->num_sys_eqs = word_field & 0xfff;
+	MLX4_GET(qword_field, outbox, INIT_HCA_RDMARC_BASE_OFFSET);
+	param->rdmarc_base = qword_field & ~((u64)0x1f);
+	MLX4_GET(byte_field, outbox, INIT_HCA_LOG_RD_OFFSET);
+	param->log_rd_per_qp = byte_field & 0x7;
 
 	MLX4_GET(dword_field, outbox, INIT_HCA_FLAGS_OFFSET);
 	if (dword_field & (1 << INIT_HCA_DEVICE_MANAGED_FLOW_STEERING_EN)) {
@@ -2125,22 +2140,21 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev,
 	/* steering attributes */
 	if (param->steering_mode == MLX4_STEERING_MODE_DEVICE_MANAGED) {
 		MLX4_GET(param->mc_base, outbox, INIT_HCA_FS_BASE_OFFSET);
-		MLX4_GET(param->log_mc_entry_sz, outbox,
-			 INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET);
-		MLX4_GET(param->log_mc_table_sz, outbox,
-			 INIT_HCA_FS_LOG_TABLE_SZ_OFFSET);
-		MLX4_GET(byte_field, outbox,
-			 INIT_HCA_FS_A0_OFFSET);
+		MLX4_GET(byte_field, outbox, INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET);
+		param->log_mc_entry_sz = byte_field & 0x1f;
+		MLX4_GET(byte_field, outbox, INIT_HCA_FS_LOG_TABLE_SZ_OFFSET);
+		param->log_mc_table_sz = byte_field & 0x1f;
+		MLX4_GET(byte_field, outbox, INIT_HCA_FS_A0_OFFSET);
 		param->dmfs_high_steer_mode =
 			a0_dmfs_query_hw_steering[(byte_field >> 6) & 3];
 	} else {
 		MLX4_GET(param->mc_base, outbox, INIT_HCA_MC_BASE_OFFSET);
-		MLX4_GET(param->log_mc_entry_sz, outbox,
-			 INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET);
-		MLX4_GET(param->log_mc_hash_sz,  outbox,
-			 INIT_HCA_LOG_MC_HASH_SZ_OFFSET);
-		MLX4_GET(param->log_mc_table_sz, outbox,
-			 INIT_HCA_LOG_MC_TABLE_SZ_OFFSET);
+		MLX4_GET(byte_field, outbox, INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET);
+		param->log_mc_entry_sz = byte_field & 0x1f;
+		MLX4_GET(byte_field,  outbox, INIT_HCA_LOG_MC_HASH_SZ_OFFSET);
+		param->log_mc_hash_sz = byte_field & 0x1f;
+		MLX4_GET(byte_field, outbox, INIT_HCA_LOG_MC_TABLE_SZ_OFFSET);
+		param->log_mc_table_sz = byte_field & 0x1f;
 	}
 
 	/* CX3 is capable of extending CQEs/EQEs from 32 to 64 bytes */
@@ -2164,15 +2178,18 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev,
 	/* TPT attributes */
 
 	MLX4_GET(param->dmpt_base,  outbox, INIT_HCA_DMPT_BASE_OFFSET);
-	MLX4_GET(param->mw_enabled, outbox, INIT_HCA_TPT_MW_OFFSET);
-	MLX4_GET(param->log_mpt_sz, outbox, INIT_HCA_LOG_MPT_SZ_OFFSET);
+	MLX4_GET(byte_field, outbox, INIT_HCA_TPT_MW_OFFSET);
+	param->mw_enabled = byte_field >> 7;
+	MLX4_GET(byte_field, outbox, INIT_HCA_LOG_MPT_SZ_OFFSET);
+	param->log_mpt_sz = byte_field & 0x3f;
 	MLX4_GET(param->mtt_base,   outbox, INIT_HCA_MTT_BASE_OFFSET);
 	MLX4_GET(param->cmpt_base,  outbox, INIT_HCA_CMPT_BASE_OFFSET);
 
 	/* UAR attributes */
 
 	MLX4_GET(param->uar_page_sz, outbox, INIT_HCA_UAR_PAGE_SZ_OFFSET);
-	MLX4_GET(param->log_uar_sz, outbox, INIT_HCA_LOG_UAR_SZ_OFFSET);
+	MLX4_GET(byte_field, outbox, INIT_HCA_LOG_UAR_SZ_OFFSET);
+	param->log_uar_sz = byte_field & 0xf;
 
 	/* phv_check enable */
 	MLX4_GET(byte_field, outbox, INIT_HCA_CACHELINE_SZ_OFFSET);
-- 
2.20.1


From 8956d22e52eed35272efb26371909126a9aa2ee4 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 24 Jan 2019 14:18:18 -0800
Subject: [PATCH 09/30] netrom: switch to sock timer API

[ Upstream commit 63346650c1a94a92be61a57416ac88c0a47c4327 ]

sk_reset_timer() and sk_stop_timer() properly handle
sock refcnt for timer function. Switching to them
could fix a refcounting bug reported by syzbot.

Reported-and-tested-by: syzbot+defa700d16f1bd1b9a05@syzkaller.appspotmail.com
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-hams@vger.kernel.org
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netrom/nr_timer.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/net/netrom/nr_timer.c b/net/netrom/nr_timer.c
index cbd51ed5a2d7..908e53ab47a4 100644
--- a/net/netrom/nr_timer.c
+++ b/net/netrom/nr_timer.c
@@ -52,21 +52,21 @@ void nr_start_t1timer(struct sock *sk)
 {
 	struct nr_sock *nr = nr_sk(sk);
 
-	mod_timer(&nr->t1timer, jiffies + nr->t1);
+	sk_reset_timer(sk, &nr->t1timer, jiffies + nr->t1);
 }
 
 void nr_start_t2timer(struct sock *sk)
 {
 	struct nr_sock *nr = nr_sk(sk);
 
-	mod_timer(&nr->t2timer, jiffies + nr->t2);
+	sk_reset_timer(sk, &nr->t2timer, jiffies + nr->t2);
 }
 
 void nr_start_t4timer(struct sock *sk)
 {
 	struct nr_sock *nr = nr_sk(sk);
 
-	mod_timer(&nr->t4timer, jiffies + nr->t4);
+	sk_reset_timer(sk, &nr->t4timer, jiffies + nr->t4);
 }
 
 void nr_start_idletimer(struct sock *sk)
@@ -74,37 +74,37 @@ void nr_start_idletimer(struct sock *sk)
 	struct nr_sock *nr = nr_sk(sk);
 
 	if (nr->idle > 0)
-		mod_timer(&nr->idletimer, jiffies + nr->idle);
+		sk_reset_timer(sk, &nr->idletimer, jiffies + nr->idle);
 }
 
 void nr_start_heartbeat(struct sock *sk)
 {
-	mod_timer(&sk->sk_timer, jiffies + 5 * HZ);
+	sk_reset_timer(sk, &sk->sk_timer, jiffies + 5 * HZ);
 }
 
 void nr_stop_t1timer(struct sock *sk)
 {
-	del_timer(&nr_sk(sk)->t1timer);
+	sk_stop_timer(sk, &nr_sk(sk)->t1timer);
 }
 
 void nr_stop_t2timer(struct sock *sk)
 {
-	del_timer(&nr_sk(sk)->t2timer);
+	sk_stop_timer(sk, &nr_sk(sk)->t2timer);
 }
 
 void nr_stop_t4timer(struct sock *sk)
 {
-	del_timer(&nr_sk(sk)->t4timer);
+	sk_stop_timer(sk, &nr_sk(sk)->t4timer);
 }
 
 void nr_stop_idletimer(struct sock *sk)
 {
-	del_timer(&nr_sk(sk)->idletimer);
+	sk_stop_timer(sk, &nr_sk(sk)->idletimer);
 }
 
 void nr_stop_heartbeat(struct sock *sk)
 {
-	del_timer(&sk->sk_timer);
+	sk_stop_timer(sk, &sk->sk_timer);
 }
 
 int nr_t1timer_running(struct sock *sk)
-- 
2.20.1


From 4f42db01f8c86f34b21599de26ed6c255c1eb774 Mon Sep 17 00:00:00 2001
From: Bernard Pidoux <f6bvp@free.fr>
Date: Fri, 25 Jan 2019 11:46:40 +0100
Subject: [PATCH 10/30] net/rose: fix NULL ax25_cb kernel panic

[ Upstream commit b0cf029234f9b18e10703ba5147f0389c382bccc ]

When an internally generated frame is handled by rose_xmit(),
rose_route_frame() is called:

        if (!rose_route_frame(skb, NULL)) {
                dev_kfree_skb(skb);
                stats->tx_errors++;
                return NETDEV_TX_OK;
        }

We have the same code sequence in Net/Rom where an internally generated
frame is handled by nr_xmit() calling nr_route_frame(skb, NULL).
However, in this function NULL argument is tested while it is not in
rose_route_frame().
Then kernel panic occurs later on when calling ax25cmp() with a NULL
ax25_cb argument as reported many times and recently with syzbot.

We need to test if ax25 is NULL before using it.

Testing:
Built kernel with CONFIG_ROSE=y.

Signed-off-by: Bernard Pidoux <f6bvp@free.fr>
Acked-by: Dmitry Vyukov <dvyukov@google.com>
Reported-by: syzbot+1a2c456a1ea08fa5b5f7@syzkaller.appspotmail.com
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Bernard Pidoux <f6bvp@free.fr>
Cc: linux-hams@vger.kernel.org
Cc: netdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rose/rose_route.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c
index 77e9f85a2c92..f2ff21d7df08 100644
--- a/net/rose/rose_route.c
+++ b/net/rose/rose_route.c
@@ -850,6 +850,7 @@ void rose_link_device_down(struct net_device *dev)
 
 /*
  *	Route a frame to an appropriate AX.25 connection.
+ *	A NULL ax25_cb indicates an internally generated frame.
  */
 int rose_route_frame(struct sk_buff *skb, ax25_cb *ax25)
 {
@@ -867,6 +868,10 @@ int rose_route_frame(struct sk_buff *skb, ax25_cb *ax25)
 
 	if (skb->len < ROSE_MIN_LEN)
 		return res;
+
+	if (!ax25)
+		return rose_loopback_queue(skb, NULL);
+
 	frametype = skb->data[2];
 	lci = ((skb->data[0] << 8) & 0xF00) + ((skb->data[1] << 0) & 0x0FF);
 	if (frametype == ROSE_CALL_REQUEST &&
-- 
2.20.1


From a07db8cb107cbe8dc3369e6c60e616b58d07e306 Mon Sep 17 00:00:00 2001
From: Josh Elsasser <jelsasser@appneta.com>
Date: Sat, 26 Jan 2019 14:38:33 -0800
Subject: [PATCH 11/30] net: set default network namespace in
 init_dummy_netdev()

[ Upstream commit 35edfdc77f683c8fd27d7732af06cf6489af60a5 ]

Assign a default net namespace to netdevs created by init_dummy_netdev().
Fixes a NULL pointer dereference caused by busy-polling a socket bound to
an iwlwifi wireless device, which bumps the per-net BUSYPOLLRXPACKETS stat
if napi_poll() received packets:

  BUG: unable to handle kernel NULL pointer dereference at 0000000000000190
  IP: napi_busy_loop+0xd6/0x200
  Call Trace:
    sock_poll+0x5e/0x80
    do_sys_poll+0x324/0x5a0
    SyS_poll+0x6c/0xf0
    do_syscall_64+0x6b/0x1f0
    entry_SYSCALL_64_after_hwframe+0x3d/0xa2

Fixes: 7db6b048da3b ("net: Commonize busy polling code to focus on napi_id instead of socket")
Signed-off-by: Josh Elsasser <jelsasser@appneta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/core/dev.c b/net/core/dev.c
index 1f1aae27d41f..af097ca9cb4f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8599,6 +8599,9 @@ int init_dummy_netdev(struct net_device *dev)
 	set_bit(__LINK_STATE_PRESENT, &dev->state);
 	set_bit(__LINK_STATE_START, &dev->state);
 
+	/* napi_busy_loop stats accounting wants this */
+	dev_net_set(dev, &init_net);
+
 	/* Note : We dont allocate pcpu_refcnt for dummy devices,
 	 * because users of this 'device' dont need to change
 	 * its refcount.
-- 
2.20.1


From d7327515f2c5e97aaa29bdbf954c0d184555f1a0 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms+renesas@verge.net.au>
Date: Wed, 23 Jan 2019 12:14:52 +0100
Subject: [PATCH 12/30] ravb: expand rx descriptor data to accommodate hw
 checksum

[ Upstream commit 12da64300fbc76b875900445f4146c3dc617d43e ]

EtherAVB may provide a checksum of packet data appended to packet data. In
order to allow this checksum to be received by the host descriptor data
needs to be enlarged by 2 bytes to accommodate the checksum.

In the case of MTU-sized packets without a VLAN tag the
checksum were already accommodated by virtue of the space reserved for the
VLAN tag. However, a packet of MTU-size with a  VLAN tag consumed all
packet data space provided by a descriptor leaving no space for the
trailing checksum.

This was not detected by the driver which incorrectly used the last two
bytes of packet data as the checksum and truncate the packet by two bytes.
This resulted all such packets being dropped.

A work around is to disable RX checksum offload
 # ethtool -K eth0 rx off

This patch resolves this problem by increasing the size available for
packet data in RX descriptors by two bytes.

Tested on R-Car E3 (r8a77990) ES1.0 based Ebisu-4D board

v2
* Use sizeof(__sum16) directly rather than adding a driver-local
  #define for the size of the checksum provided by the hw (2 bytes).

Fixes: 4d86d3818627 ("ravb: RX checksum offload")
Signed-off-by: Simon Horman <horms+renesas@verge.net.au>
Reviewed-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/ravb_main.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index d6f753925352..8441c86d9f3b 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -344,7 +344,7 @@ static int ravb_ring_init(struct net_device *ndev, int q)
 	int i;
 
 	priv->rx_buf_sz = (ndev->mtu <= 1492 ? PKT_BUF_SZ : ndev->mtu) +
-		ETH_HLEN + VLAN_HLEN;
+		ETH_HLEN + VLAN_HLEN + sizeof(__sum16);
 
 	/* Allocate RX and TX skb rings */
 	priv->rx_skb[q] = kcalloc(priv->num_rx_ring[q],
@@ -525,13 +525,15 @@ static void ravb_rx_csum(struct sk_buff *skb)
 {
 	u8 *hw_csum;
 
-	/* The hardware checksum is 2 bytes appended to packet data */
-	if (unlikely(skb->len < 2))
+	/* The hardware checksum is contained in sizeof(__sum16) (2) bytes
+	 * appended to packet data
+	 */
+	if (unlikely(skb->len < sizeof(__sum16)))
 		return;
-	hw_csum = skb_tail_pointer(skb) - 2;
+	hw_csum = skb_tail_pointer(skb) - sizeof(__sum16);
 	skb->csum = csum_unfold((__force __sum16)get_unaligned_le16(hw_csum));
 	skb->ip_summed = CHECKSUM_COMPLETE;
-	skb_trim(skb, skb->len - 2);
+	skb_trim(skb, skb->len - sizeof(__sum16));
 }
 
 /* Packet receive function for Ethernet AVB */
-- 
2.20.1


From d97793427b92a7e68a725ac76be130052f9fd554 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 22 Jan 2019 02:39:34 +0800
Subject: [PATCH 13/30] sctp: improve the events for sctp stream reset

[ Upstream commit 2e6dc4d95110becfe0ff4c3d4749c33ea166e9e7 ]

This patch is to improve sctp stream reset events in 4 places:

  1. In sctp_process_strreset_outreq(), the flag should always be set with
     SCTP_STREAM_RESET_INCOMING_SSN instead of OUTGOING, as receiver's in
     stream is reset here.
  2. In sctp_process_strreset_outreq(), move up SCTP_STRRESET_ERR_WRONG_SSN
     check, as the reset has to succeed after reconf_timer stops for the
     in stream reset request retransmission.
  3. In sctp_process_strreset_inreq(), no event should be sent, as no in
     or out stream is reset here.
  4. In sctp_process_strreset_resp(), SCTP_STREAM_RESET_INCOMING_SSN or
     OUTGOING event should always be sent for stream reset requests, no
     matter it fails or succeeds to process the request.

Fixes: 810544764536 ("sctp: implement receiver-side procedures for the Outgoing SSN Reset Request Parameter")
Fixes: 16e1a91965b0 ("sctp: implement receiver-side procedures for the Incoming SSN Reset Request Parameter")
Fixes: 11ae76e67a17 ("sctp: implement receiver-side procedures for the Reconf Response Parameter")
Reported-by: Ying Xu <yinxu@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/stream.c | 39 +++++++++++++++++----------------------
 1 file changed, 17 insertions(+), 22 deletions(-)

diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index 3892e7630f3a..6c188b06e5e1 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -585,9 +585,9 @@ struct sctp_chunk *sctp_process_strreset_outreq(
 	struct sctp_strreset_outreq *outreq = param.v;
 	struct sctp_stream *stream = &asoc->stream;
 	__u32 result = SCTP_STRRESET_DENIED;
-	__u16 i, nums, flags = 0;
 	__be16 *str_p = NULL;
 	__u32 request_seq;
+	__u16 i, nums;
 
 	request_seq = ntohl(outreq->request_seq);
 
@@ -615,6 +615,15 @@ struct sctp_chunk *sctp_process_strreset_outreq(
 	if (!(asoc->strreset_enable & SCTP_ENABLE_RESET_STREAM_REQ))
 		goto out;
 
+	nums = (ntohs(param.p->length) - sizeof(*outreq)) / sizeof(__u16);
+	str_p = outreq->list_of_streams;
+	for (i = 0; i < nums; i++) {
+		if (ntohs(str_p[i]) >= stream->incnt) {
+			result = SCTP_STRRESET_ERR_WRONG_SSN;
+			goto out;
+		}
+	}
+
 	if (asoc->strreset_chunk) {
 		if (!sctp_chunk_lookup_strreset_param(
 				asoc, outreq->response_seq,
@@ -637,32 +646,19 @@ struct sctp_chunk *sctp_process_strreset_outreq(
 			sctp_chunk_put(asoc->strreset_chunk);
 			asoc->strreset_chunk = NULL;
 		}
-
-		flags = SCTP_STREAM_RESET_INCOMING_SSN;
 	}
 
-	nums = (ntohs(param.p->length) - sizeof(*outreq)) / sizeof(__u16);
-	if (nums) {
-		str_p = outreq->list_of_streams;
-		for (i = 0; i < nums; i++) {
-			if (ntohs(str_p[i]) >= stream->incnt) {
-				result = SCTP_STRRESET_ERR_WRONG_SSN;
-				goto out;
-			}
-		}
-
+	if (nums)
 		for (i = 0; i < nums; i++)
 			SCTP_SI(stream, ntohs(str_p[i]))->mid = 0;
-	} else {
+	else
 		for (i = 0; i < stream->incnt; i++)
 			SCTP_SI(stream, i)->mid = 0;
-	}
 
 	result = SCTP_STRRESET_PERFORMED;
 
 	*evp = sctp_ulpevent_make_stream_reset_event(asoc,
-		flags | SCTP_STREAM_RESET_OUTGOING_SSN, nums, str_p,
-		GFP_ATOMIC);
+		SCTP_STREAM_RESET_INCOMING_SSN, nums, str_p, GFP_ATOMIC);
 
 out:
 	sctp_update_strreset_result(asoc, result);
@@ -738,9 +734,6 @@ struct sctp_chunk *sctp_process_strreset_inreq(
 
 	result = SCTP_STRRESET_PERFORMED;
 
-	*evp = sctp_ulpevent_make_stream_reset_event(asoc,
-		SCTP_STREAM_RESET_INCOMING_SSN, nums, str_p, GFP_ATOMIC);
-
 out:
 	sctp_update_strreset_result(asoc, result);
 err:
@@ -1036,10 +1029,10 @@ struct sctp_chunk *sctp_process_strreset_resp(
 					sout->mid_uo = 0;
 				}
 			}
-
-			flags = SCTP_STREAM_RESET_OUTGOING_SSN;
 		}
 
+		flags |= SCTP_STREAM_RESET_OUTGOING_SSN;
+
 		for (i = 0; i < stream->outcnt; i++)
 			SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN;
 
@@ -1058,6 +1051,8 @@ struct sctp_chunk *sctp_process_strreset_resp(
 		nums = (ntohs(inreq->param_hdr.length) - sizeof(*inreq)) /
 		       sizeof(__u16);
 
+		flags |= SCTP_STREAM_RESET_INCOMING_SSN;
+
 		*evp = sctp_ulpevent_make_stream_reset_event(asoc, flags,
 			nums, str_p, GFP_ATOMIC);
 	} else if (req->type == SCTP_PARAM_RESET_TSN_REQUEST) {
-- 
2.20.1


From aa0259e002c4089041476445bd3a540b4605c5c4 Mon Sep 17 00:00:00 2001
From: George Amanakis <gamanakis@gmail.com>
Date: Tue, 29 Jan 2019 22:50:13 -0500
Subject: [PATCH 14/30] tun: move the call to tun_set_real_num_queues

[ Upstream commit 3a03cb8456cc1d61c467a5375e0a10e5207b948c ]

Call tun_set_real_num_queues() after the increment of tun->numqueues
since the former depends on it. Otherwise, the number of queues is not
correctly accounted for, which results to warnings similar to:
"vnet0 selects TX queue 11, but real number of TX queues is 11".

Fixes: 0b7959b62573 ("tun: publish tfile after it's fully initialized")
Reported-and-tested-by: George Amanakis <gamanakis@gmail.com>
Signed-off-by: George Amanakis <gamanakis@gmail.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 33978b0cdac8..65844f28db30 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -866,8 +866,6 @@ static int tun_attach(struct tun_struct *tun, struct file *file,
 		tun_napi_init(tun, tfile, napi, napi_frags);
 	}
 
-	tun_set_real_num_queues(tun);
-
 	/* device is allowed to go away first, so no need to hold extra
 	 * refcnt.
 	 */
@@ -879,6 +877,7 @@ static int tun_attach(struct tun_struct *tun, struct file *file,
 	rcu_assign_pointer(tfile->tun, tun);
 	rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile);
 	tun->numqueues++;
+	tun_set_real_num_queues(tun);
 out:
 	return err;
 }
-- 
2.20.1


From 3f34751396cd6922cfeca44bb074e9ede7b1d382 Mon Sep 17 00:00:00 2001
From: Mathias Thore <mathias.thore@infinera.com>
Date: Mon, 28 Jan 2019 10:07:47 +0100
Subject: [PATCH 15/30] ucc_geth: Reset BQL queue when stopping device

[ Upstream commit e15aa3b2b1388c399c1a2ce08550d2cc4f7e3e14 ]

After a timeout event caused by for example a broadcast storm, when
the MAC and PHY are reset, the BQL TX queue needs to be reset as
well. Otherwise, the device will exhibit severe performance issues
even after the storm has ended.

Co-authored-by: David Gounaris <david.gounaris@infinera.com>
Signed-off-by: Mathias Thore <mathias.thore@infinera.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/ucc_geth.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c
index 22a817da861e..1e2b53a934fb 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -1888,6 +1888,8 @@ static void ucc_geth_free_tx(struct ucc_geth_private *ugeth)
 	u16 i, j;
 	u8 __iomem *bd;
 
+	netdev_reset_queue(ugeth->ndev);
+
 	ug_info = ugeth->ug_info;
 	uf_info = &ug_info->uf_info;
 
-- 
2.20.1


From 789e1b5baaa9f97cf6b0cbbf71979fd7cf63938d Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Mon, 28 Jan 2019 15:05:05 +0800
Subject: [PATCH 16/30] vhost: fix OOB in get_rx_bufs()

[ Upstream commit b46a0bf78ad7b150ef5910da83859f7f5a514ffd ]

After batched used ring updating was introduced in commit e2b3b35eb989
("vhost_net: batch used ring update in rx"). We tend to batch heads in
vq->heads for more than one packet. But the quota passed to
get_rx_bufs() was not correctly limited, which can result a OOB write
in vq->heads.

        headcount = get_rx_bufs(vq, vq->heads + nvq->done_idx,
                    vhost_len, &in, vq_log, &log,
                    likely(mergeable) ? UIO_MAXIOV : 1);

UIO_MAXIOV was still used which is wrong since we could have batched
used in vq->heads, this will cause OOB if the next buffer needs more
than 960 (1024 (UIO_MAXIOV) - 64 (VHOST_NET_BATCH)) heads after we've
batched 64 (VHOST_NET_BATCH) heads:
Acked-by: Stefan Hajnoczi <stefanha@redhat.com>

=============================================================================
BUG kmalloc-8k (Tainted: G    B            ): Redzone overwritten
-----------------------------------------------------------------------------

INFO: 0x00000000fd93b7a2-0x00000000f0713384. First byte 0xa9 instead of 0xcc
INFO: Allocated in alloc_pd+0x22/0x60 age=3933677 cpu=2 pid=2674
    kmem_cache_alloc_trace+0xbb/0x140
    alloc_pd+0x22/0x60
    gen8_ppgtt_create+0x11d/0x5f0
    i915_ppgtt_create+0x16/0x80
    i915_gem_create_context+0x248/0x390
    i915_gem_context_create_ioctl+0x4b/0xe0
    drm_ioctl_kernel+0xa5/0xf0
    drm_ioctl+0x2ed/0x3a0
    do_vfs_ioctl+0x9f/0x620
    ksys_ioctl+0x6b/0x80
    __x64_sys_ioctl+0x11/0x20
    do_syscall_64+0x43/0xf0
    entry_SYSCALL_64_after_hwframe+0x44/0xa9
INFO: Slab 0x00000000d13e87af objects=3 used=3 fp=0x          (null) flags=0x200000000010201
INFO: Object 0x0000000003278802 @offset=17064 fp=0x00000000e2e6652b

Fixing this by allocating UIO_MAXIOV + VHOST_NET_BATCH iovs for
vhost-net. This is done through set the limitation through
vhost_dev_init(), then set_owner can allocate the number of iov in a
per device manner.

This fixes CVE-2018-16880.

Fixes: e2b3b35eb989 ("vhost_net: batch used ring update in rx")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/net.c   | 3 ++-
 drivers/vhost/scsi.c  | 2 +-
 drivers/vhost/vhost.c | 7 ++++---
 drivers/vhost/vhost.h | 4 +++-
 drivers/vhost/vsock.c | 2 +-
 5 files changed, 11 insertions(+), 7 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index a86aa65ad66d..39155d7cc894 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -1114,7 +1114,8 @@ static int vhost_net_open(struct inode *inode, struct file *f)
 		n->vqs[i].rx_ring = NULL;
 		vhost_net_buf_init(&n->vqs[i].rxq);
 	}
-	vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX);
+	vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX,
+		       UIO_MAXIOV + VHOST_NET_BATCH);
 
 	vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, EPOLLOUT, dev);
 	vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, EPOLLIN, dev);
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index e7e3ae13516d..0cfa925be4ec 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -1398,7 +1398,7 @@ static int vhost_scsi_open(struct inode *inode, struct file *f)
 		vqs[i] = &vs->vqs[i].vq;
 		vs->vqs[i].vq.handle_kick = vhost_scsi_handle_kick;
 	}
-	vhost_dev_init(&vs->dev, vqs, VHOST_SCSI_MAX_VQ);
+	vhost_dev_init(&vs->dev, vqs, VHOST_SCSI_MAX_VQ, UIO_MAXIOV);
 
 	vhost_scsi_init_inflight(vs, NULL);
 
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index c66fc8308b5e..cf82e7266397 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -390,9 +390,9 @@ static long vhost_dev_alloc_iovecs(struct vhost_dev *dev)
 		vq->indirect = kmalloc_array(UIO_MAXIOV,
 					     sizeof(*vq->indirect),
 					     GFP_KERNEL);
-		vq->log = kmalloc_array(UIO_MAXIOV, sizeof(*vq->log),
+		vq->log = kmalloc_array(dev->iov_limit, sizeof(*vq->log),
 					GFP_KERNEL);
-		vq->heads = kmalloc_array(UIO_MAXIOV, sizeof(*vq->heads),
+		vq->heads = kmalloc_array(dev->iov_limit, sizeof(*vq->heads),
 					  GFP_KERNEL);
 		if (!vq->indirect || !vq->log || !vq->heads)
 			goto err_nomem;
@@ -414,7 +414,7 @@ static void vhost_dev_free_iovecs(struct vhost_dev *dev)
 }
 
 void vhost_dev_init(struct vhost_dev *dev,
-		    struct vhost_virtqueue **vqs, int nvqs)
+		    struct vhost_virtqueue **vqs, int nvqs, int iov_limit)
 {
 	struct vhost_virtqueue *vq;
 	int i;
@@ -427,6 +427,7 @@ void vhost_dev_init(struct vhost_dev *dev,
 	dev->iotlb = NULL;
 	dev->mm = NULL;
 	dev->worker = NULL;
+	dev->iov_limit = iov_limit;
 	init_llist_head(&dev->work_list);
 	init_waitqueue_head(&dev->wait);
 	INIT_LIST_HEAD(&dev->read_list);
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index 1b675dad5e05..9490e7ddb340 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -170,9 +170,11 @@ struct vhost_dev {
 	struct list_head read_list;
 	struct list_head pending_list;
 	wait_queue_head_t wait;
+	int iov_limit;
 };
 
-void vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue **vqs, int nvqs);
+void vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue **vqs,
+		    int nvqs, int iov_limit);
 long vhost_dev_set_owner(struct vhost_dev *dev);
 bool vhost_dev_has_owner(struct vhost_dev *dev);
 long vhost_dev_check_owner(struct vhost_dev *);
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 98ed5be132c6..fa93f6711d8d 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -531,7 +531,7 @@ static int vhost_vsock_dev_open(struct inode *inode, struct file *file)
 	vsock->vqs[VSOCK_VQ_TX].handle_kick = vhost_vsock_handle_tx_kick;
 	vsock->vqs[VSOCK_VQ_RX].handle_kick = vhost_vsock_handle_rx_kick;
 
-	vhost_dev_init(&vsock->dev, vqs, ARRAY_SIZE(vsock->vqs));
+	vhost_dev_init(&vsock->dev, vqs, ARRAY_SIZE(vsock->vqs), UIO_MAXIOV);
 
 	file->private_data = vsock;
 	spin_lock_init(&vsock->send_pkt_list_lock);
-- 
2.20.1


From 2bc3c5028dba1a9f6e869737bd533bbd791dedce Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Mon, 28 Jan 2019 22:23:49 +0100
Subject: [PATCH 17/30] net: ip6_gre: always reports o_key to userspace

[ Upstream commit c706863bc8902d0c2d1a5a27ac8e1ead5d06b79d ]

As Erspan_v4, Erspan_v6 protocol relies on o_key to configure
session id header field. However TUNNEL_KEY bit is cleared in
ip6erspan_tunnel_xmit since ERSPAN protocol does not set the key field
of the external GRE header and so the configured o_key is not reported
to userspace. The issue can be triggered with the following reproducer:

$ip link add ip6erspan1 type ip6erspan local 2000::1 remote 2000::2 \
    key 1 seq erspan_ver 1
$ip link set ip6erspan1 up
ip -d link sh ip6erspan1

ip6erspan1@NONE: <BROADCAST,MULTICAST> mtu 1422 qdisc noop state DOWN mode DEFAULT
    link/ether ba:ff:09:24:c3:0e brd ff:ff:ff:ff:ff:ff promiscuity 0 minmtu 68 maxmtu 1500
    ip6erspan remote 2000::2 local 2000::1 encaplimit 4 flowlabel 0x00000 ikey 0.0.0.1 iseq oseq

Fix the issue adding TUNNEL_KEY bit to the o_flags parameter in
ip6gre_fill_info

Fixes: 5a963eb61b7c ("ip6_gre: Add ERSPAN native tunnel support")
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 580907eb42cd..be04877b3827 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -2120,12 +2120,17 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev)
 {
 	struct ip6_tnl *t = netdev_priv(dev);
 	struct __ip6_tnl_parm *p = &t->parms;
+	__be16 o_flags = p->o_flags;
+
+	if ((p->erspan_ver == 1 || p->erspan_ver == 2) &&
+	    !p->collect_md)
+		o_flags |= TUNNEL_KEY;
 
 	if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) ||
 	    nla_put_be16(skb, IFLA_GRE_IFLAGS,
 			 gre_tnl_flags_to_gre_flags(p->i_flags)) ||
 	    nla_put_be16(skb, IFLA_GRE_OFLAGS,
-			 gre_tnl_flags_to_gre_flags(p->o_flags)) ||
+			 gre_tnl_flags_to_gre_flags(o_flags)) ||
 	    nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) ||
 	    nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) ||
 	    nla_put_in6_addr(skb, IFLA_GRE_LOCAL, &p->laddr) ||
-- 
2.20.1


From 3135047719359753bdf0f20f1d5ba68d88496961 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 22 Jan 2019 02:40:12 +0800
Subject: [PATCH 18/30] sctp: improve the events for sctp stream adding

[ Upstream commit 8220c870cb0f4eaa4e335c9645dbd9a1c461c1dd ]

This patch is to improve sctp stream adding events in 2 places:

  1. In sctp_process_strreset_addstrm_out(), move up SCTP_MAX_STREAM
     and in stream allocation failure checks, as the adding has to
     succeed after reconf_timer stops for the in stream adding
     request retransmission.

  3. In sctp_process_strreset_addstrm_in(), no event should be sent,
     as no in or out stream is added here.

Fixes: 50a41591f110 ("sctp: implement receiver-side procedures for the Add Outgoing Streams Request Parameter")
Fixes: c5c4ebb3ab87 ("sctp: implement receiver-side procedures for the Add Incoming Streams Request Parameter")
Reported-by: Ying Xu <yinxu@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/stream.c | 19 ++++++++-----------
 1 file changed, 8 insertions(+), 11 deletions(-)

diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index 6c188b06e5e1..80e0ae5534ec 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -866,6 +866,14 @@ struct sctp_chunk *sctp_process_strreset_addstrm_out(
 	if (!(asoc->strreset_enable & SCTP_ENABLE_CHANGE_ASSOC_REQ))
 		goto out;
 
+	in = ntohs(addstrm->number_of_streams);
+	incnt = stream->incnt + in;
+	if (!in || incnt > SCTP_MAX_STREAM)
+		goto out;
+
+	if (sctp_stream_alloc_in(stream, incnt, GFP_ATOMIC))
+		goto out;
+
 	if (asoc->strreset_chunk) {
 		if (!sctp_chunk_lookup_strreset_param(
 			asoc, 0, SCTP_PARAM_RESET_ADD_IN_STREAMS)) {
@@ -889,14 +897,6 @@ struct sctp_chunk *sctp_process_strreset_addstrm_out(
 		}
 	}
 
-	in = ntohs(addstrm->number_of_streams);
-	incnt = stream->incnt + in;
-	if (!in || incnt > SCTP_MAX_STREAM)
-		goto out;
-
-	if (sctp_stream_alloc_in(stream, incnt, GFP_ATOMIC))
-		goto out;
-
 	stream->incnt = incnt;
 
 	result = SCTP_STRRESET_PERFORMED;
@@ -966,9 +966,6 @@ struct sctp_chunk *sctp_process_strreset_addstrm_in(
 
 	result = SCTP_STRRESET_PERFORMED;
 
-	*evp = sctp_ulpevent_make_stream_change_event(asoc,
-		0, 0, ntohs(addstrm->number_of_streams), GFP_ATOMIC);
-
 out:
 	sctp_update_strreset_result(asoc, result);
 err:
-- 
2.20.1


From 014cdc58eb940890d0a1412359f5d7b726654260 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Mon, 24 Dec 2018 09:48:42 +0200
Subject: [PATCH 19/30] net/mlx5e: Allow MAC invalidation while spoofchk is ON

[ Upstream commit 9d2cbdc5d334967c35b5f58c7bf3208e17325647 ]

Prior to this patch the driver prohibited spoof checking on invalid MAC.
Now the user can set this configuration if it wishes to.

This is required since libvirt might invalidate the VF Mac by setting it
to zero, while spoofcheck is ON.

Fixes: 1ab2068a4c66 ("net/mlx5: Implement vports admin state backup/restore")
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/eswitch.c  | 18 ++++++------------
 1 file changed, 6 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index ea7dedc2d5ad..98befd12486f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1133,13 +1133,6 @@ static int esw_vport_ingress_config(struct mlx5_eswitch *esw,
 	int err = 0;
 	u8 *smac_v;
 
-	if (vport->info.spoofchk && !is_valid_ether_addr(vport->info.mac)) {
-		mlx5_core_warn(esw->dev,
-			       "vport[%d] configure ingress rules failed, illegal mac with spoofchk\n",
-			       vport->vport);
-		return -EPERM;
-	}
-
 	esw_vport_cleanup_ingress_rules(esw, vport);
 
 	if (!vport->info.vlan && !vport->info.qos && !vport->info.spoofchk) {
@@ -1812,13 +1805,10 @@ int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
 	mutex_lock(&esw->state_lock);
 	evport = &esw->vports[vport];
 
-	if (evport->info.spoofchk && !is_valid_ether_addr(mac)) {
+	if (evport->info.spoofchk && !is_valid_ether_addr(mac))
 		mlx5_core_warn(esw->dev,
-			       "MAC invalidation is not allowed when spoofchk is on, vport(%d)\n",
+			       "Set invalid MAC while spoofchk is on, vport(%d)\n",
 			       vport);
-		err = -EPERM;
-		goto unlock;
-	}
 
 	err = mlx5_modify_nic_vport_mac_address(esw->dev, vport, mac);
 	if (err) {
@@ -1964,6 +1954,10 @@ int mlx5_eswitch_set_vport_spoofchk(struct mlx5_eswitch *esw,
 	evport = &esw->vports[vport];
 	pschk = evport->info.spoofchk;
 	evport->info.spoofchk = spoofchk;
+	if (pschk && !is_valid_ether_addr(evport->info.mac))
+		mlx5_core_warn(esw->dev,
+			       "Spoofchk in set while MAC is invalid, vport(%d)\n",
+			       evport->vport);
 	if (evport->enabled && esw->mode == SRIOV_LEGACY)
 		err = esw_vport_ingress_config(esw, evport);
 	if (err)
-- 
2.20.1


From 0e6b87180055939f9e3dd2dca2eff3b6b08d823a Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Sun, 27 Jan 2019 09:26:22 +0200
Subject: [PATCH 20/30] ip6mr: Fix notifiers call on mroute_clean_tables()

[ Upstream commit 146820cc240f4389cf33481c058d9493aef95e25 ]

When the MC route socket is closed, mroute_clean_tables() is called to
cleanup existing routes. Mistakenly notifiers call was put on the cleanup
of the unresolved MC route entries cache.
In a case where the MC socket closes before an unresolved route expires,
the notifier call leads to a crash, caused by the driver trying to
increment a non initialized refcount_t object [1] and then when handling
is done, to decrement it [2]. This was detected by a test recently added in
commit 6d4efada3b82 ("selftests: forwarding: Add multicast routing test").

Fix that by putting notifiers call on the resolved entries traversal,
instead of on the unresolved entries traversal.

[1]

[  245.748967] refcount_t: increment on 0; use-after-free.
[  245.754829] WARNING: CPU: 3 PID: 3223 at lib/refcount.c:153 refcount_inc_checked+0x2b/0x30
...
[  245.802357] Hardware name: Mellanox Technologies Ltd. MSN2740/SA001237, BIOS 5.6.5 06/07/2016
[  245.811873] RIP: 0010:refcount_inc_checked+0x2b/0x30
...
[  245.907487] Call Trace:
[  245.910231]  mlxsw_sp_router_fib_event.cold.181+0x42/0x47 [mlxsw_spectrum]
[  245.917913]  notifier_call_chain+0x45/0x7
[  245.922484]  atomic_notifier_call_chain+0x15/0x20
[  245.927729]  call_fib_notifiers+0x15/0x30
[  245.932205]  mroute_clean_tables+0x372/0x3f
[  245.936971]  ip6mr_sk_done+0xb1/0xc0
[  245.940960]  ip6_mroute_setsockopt+0x1da/0x5f0
...

[2]

[  246.128487] refcount_t: underflow; use-after-free.
[  246.133859] WARNING: CPU: 0 PID: 7 at lib/refcount.c:187 refcount_sub_and_test_checked+0x4c/0x60
[  246.183521] Hardware name: Mellanox Technologies Ltd. MSN2740/SA001237, BIOS 5.6.5 06/07/2016
...
[  246.193062] Workqueue: mlxsw_core_ordered mlxsw_sp_router_fibmr_event_work [mlxsw_spectrum]
[  246.202394] RIP: 0010:refcount_sub_and_test_checked+0x4c/0x60
...
[  246.298889] Call Trace:
[  246.301617]  refcount_dec_and_test_checked+0x11/0x20
[  246.307170]  mlxsw_sp_router_fibmr_event_work.cold.196+0x47/0x78 [mlxsw_spectrum]
[  246.315531]  process_one_work+0x1fa/0x3f0
[  246.320005]  worker_thread+0x2f/0x3e0
[  246.324083]  kthread+0x118/0x130
[  246.327683]  ? wq_update_unbound_numa+0x1b0/0x1b0
[  246.332926]  ? kthread_park+0x80/0x80
[  246.337013]  ret_from_fork+0x1f/0x30

Fixes: 088aa3eec2ce ("ip6mr: Support fib notifications")
Signed-off-by: Nir Dotan <nird@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6mr.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 331e6b6dd252..10aafea3af0f 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1506,6 +1506,9 @@ static void mroute_clean_tables(struct mr_table *mrt, bool all)
 			continue;
 		rhltable_remove(&mrt->mfc_hash, &c->mnode, ip6mr_rht_params);
 		list_del_rcu(&c->list);
+		call_ip6mr_mfc_entry_notifiers(read_pnet(&mrt->net),
+					       FIB_EVENT_ENTRY_DEL,
+					       (struct mfc6_cache *)c, mrt->id);
 		mr6_netlink_event(mrt, (struct mfc6_cache *)c, RTM_DELROUTE);
 		mr_cache_put(c);
 	}
@@ -1514,10 +1517,6 @@ static void mroute_clean_tables(struct mr_table *mrt, bool all)
 		spin_lock_bh(&mfc_unres_lock);
 		list_for_each_entry_safe(c, tmp, &mrt->mfc_unres_queue, list) {
 			list_del(&c->list);
-			call_ip6mr_mfc_entry_notifiers(read_pnet(&mrt->net),
-						       FIB_EVENT_ENTRY_DEL,
-						       (struct mfc6_cache *)c,
-						       mrt->id);
 			mr6_netlink_event(mrt, (struct mfc6_cache *)c,
 					  RTM_DELROUTE);
 			ip6mr_destroy_unres(mrt, (struct mfc6_cache *)c);
-- 
2.20.1


From e30254711c259410382ef3f76fa46d578e997732 Mon Sep 17 00:00:00 2001
From: Bodong Wang <bodong@mellanox.com>
Date: Sun, 13 Jan 2019 22:47:26 -0600
Subject: [PATCH 21/30] Revert "net/mlx5e: E-Switch, Initialize eswitch only if
 eswitch manager"

[ Upstream commit 4e046de0f50e04acd48eb373d6a9061ddf014e0c ]

This reverts commit 5f5991f36dce1e69dd8bd7495763eec2e28f08e7.

With the original commit, eswitch instance will not be initialized for
a function which is vport group manager but not eswitch manager such as
host PF on SmartNIC (BlueField) card. This will result in a kernel crash
when such a vport group manager is trying to access vports in its group.
E.g, PF vport manager (not eswitch manager) tries to configure the MAC
of its VF vport, a kernel trace will happen similar as bellow:

 BUG: unable to handle kernel NULL pointer dereference at 0000000000000000
 ...
 RIP: 0010:mlx5_eswitch_get_vport_config+0xc/0x180 [mlx5_core]
 ...

Fixes: 5f5991f36dce ("net/mlx5e: E-Switch, Initialize eswitch only if eswitch manager")
Signed-off-by: Bodong Wang <bodong@mellanox.com>
Reported-by: Yuval Avnery <yuvalav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 98befd12486f..d6706475a3ba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1689,7 +1689,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 	int vport_num;
 	int err;
 
-	if (!MLX5_ESWITCH_MANAGER(dev))
+	if (!MLX5_VPORT_MANAGER(dev))
 		return 0;
 
 	esw_info(dev,
@@ -1758,7 +1758,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 
 void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw)
 {
-	if (!esw || !MLX5_ESWITCH_MANAGER(esw->dev))
+	if (!esw || !MLX5_VPORT_MANAGER(esw->dev))
 		return;
 
 	esw_info(esw->dev, "cleanup\n");
-- 
2.20.1


From bda244638c4f452193ac2d765d25d4e53f82c774 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 22 Jan 2019 02:42:09 +0800
Subject: [PATCH 22/30] sctp: set chunk transport correctly when it's a new
 asoc

[ Upstream commit 4ff40b86262b73553ee47cc3784ce8ba0f220bd8 ]

In the paths:

  sctp_sf_do_unexpected_init() ->
    sctp_make_init_ack()
  sctp_sf_do_dupcook_a/b()() ->
    sctp_sf_do_5_1D_ce()

The new chunk 'retval' transport is set from the incoming chunk 'chunk'
transport. However, 'retval' transport belong to the new asoc, which
is a different one from 'chunk' transport's asoc.

It will cause that the 'retval' chunk gets set with a wrong transport.
Later when sending it and because of Commit b9fd683982c9 ("sctp: add
sctp_packet_singleton"), sctp_packet_singleton() will set some fields,
like vtag to 'retval' chunk from that wrong transport's asoc.

This patch is to fix it by setting 'retval' transport correctly which
belongs to the right asoc in sctp_make_init_ack() and
sctp_sf_do_5_1D_ce().

Fixes: b9fd683982c9 ("sctp: add sctp_packet_singleton")
Reported-by: Ying Xu <yinxu@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sm_make_chunk.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index f4ac6c592e13..d05c57664e36 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -495,7 +495,10 @@ struct sctp_chunk *sctp_make_init_ack(const struct sctp_association *asoc,
 	 *
 	 * [INIT ACK back to where the INIT came from.]
 	 */
-	retval->transport = chunk->transport;
+	if (chunk->transport)
+		retval->transport =
+			sctp_assoc_lookup_paddr(asoc,
+						&chunk->transport->ipaddr);
 
 	retval->subh.init_hdr =
 		sctp_addto_chunk(retval, sizeof(initack), &initack);
@@ -642,8 +645,10 @@ struct sctp_chunk *sctp_make_cookie_ack(const struct sctp_association *asoc,
 	 *
 	 * [COOKIE ACK back to where the COOKIE ECHO came from.]
 	 */
-	if (retval && chunk)
-		retval->transport = chunk->transport;
+	if (retval && chunk && chunk->transport)
+		retval->transport =
+			sctp_assoc_lookup_paddr(asoc,
+						&chunk->transport->ipaddr);
 
 	return retval;
 }
-- 
2.20.1


From f8d6ab2851d4217b82cddda2837ce472f6cb9078 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 22 Jan 2019 02:42:41 +0800
Subject: [PATCH 23/30] sctp: set flow sport from saddr only when it's 0

[ Upstream commit ecf938fe7d0088077ee1280419a2b3c5429b47c8 ]

Now sctp_transport_pmtu() passes transport->saddr into .get_dst() to set
flow sport from 'saddr'. However, transport->saddr is set only when
transport->dst exists in sctp_transport_route().

If sctp_transport_pmtu() is called without transport->saddr set, like
when transport->dst doesn't exists, the flow sport will be set to 0
from transport->saddr, which will cause a wrong route to be got.

Commit 6e91b578bf3f ("sctp: re-use sctp_transport_pmtu in
sctp_transport_route") made the issue be triggered more easily
since sctp_transport_pmtu() would be called in sctp_transport_route()
after that.

In gerneral, fl4->fl4_sport should always be set to
htons(asoc->base.bind_addr.port), unless transport->asoc doesn't exist
in sctp_v4/6_get_dst(), which is the case:

  sctp_ootb_pkt_new() ->
    sctp_transport_route()

For that, we can simply handle it by setting flow sport from saddr only
when it's 0 in sctp_v4/6_get_dst().

Fixes: 6e91b578bf3f ("sctp: re-use sctp_transport_pmtu in sctp_transport_route")
Reported-by: Ying Xu <yinxu@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ipv6.c     | 3 ++-
 net/sctp/protocol.c | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 0bae07e9c9e7..4fede55b9010 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -277,7 +277,8 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 
 	if (saddr) {
 		fl6->saddr = saddr->v6.sin6_addr;
-		fl6->fl6_sport = saddr->v6.sin6_port;
+		if (!fl6->fl6_sport)
+			fl6->fl6_sport = saddr->v6.sin6_port;
 
 		pr_debug("src=%pI6 - ", &fl6->saddr);
 	}
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index d4352111e69d..1c9f079e8a50 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -440,7 +440,8 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 	}
 	if (saddr) {
 		fl4->saddr = saddr->v4.sin_addr.s_addr;
-		fl4->fl4_sport = saddr->v4.sin_port;
+		if (!fl4->fl4_sport)
+			fl4->fl4_sport = saddr->v4.sin_port;
 	}
 
 	pr_debug("%s: dst:%pI4, src:%pI4 - ", __func__, &fl4->daddr,
-- 
2.20.1


From b8859b9e38a5fbc6657ca8ad89756fe53990b730 Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Tue, 29 Jan 2019 09:45:53 +0900
Subject: [PATCH 24/30] virtio_net: Don't enable NAPI when interface is down

[ Upstream commit 8be4d9a492f88b96d4d3a06c6cbedbc40ca14c83 ]

Commit 4e09ff536284 ("virtio-net: disable NAPI only when enabled during
XDP set") tried to fix inappropriate NAPI enabling/disabling when
!netif_running(), but was not complete.

On error path virtio_net could enable NAPI even when !netif_running().
This can cause enabling NAPI twice on virtnet_open(), which would
trigger BUG_ON() in napi_enable().

Fixes: 4941d472bf95b ("virtio-net: do not reset during XDP set")
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index ad14fbfa1864..8de7b6fbb5c3 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2380,8 +2380,10 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 	return 0;
 
 err:
-	for (i = 0; i < vi->max_queue_pairs; i++)
-		virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
+	if (netif_running(dev)) {
+		for (i = 0; i < vi->max_queue_pairs; i++)
+			virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
+	}
 	if (prog)
 		bpf_prog_sub(prog, vi->max_queue_pairs - 1);
 	return err;
-- 
2.20.1


From 959817c7181d72b18bf93c7cffb0851e775245f6 Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Tue, 29 Jan 2019 09:45:54 +0900
Subject: [PATCH 25/30] virtio_net: Don't call free_old_xmit_skbs for
 xdp_frames

[ Upstream commit 534da5e856334fb54cb0272a9fb3afec28ea3aed ]

When napi_tx is enabled, virtnet_poll_cleantx() called
free_old_xmit_skbs() even for xdp send queue.
This is bogus since the queue has xdp_frames, not sk_buffs, thus mangled
device tx bytes counters because skb->len is meaningless value, and even
triggered oops due to general protection fault on freeing them.

Since xdp send queues do not aquire locks, old xdp_frames should be
freed only in virtnet_xdp_xmit(), so just skip free_old_xmit_skbs() for
xdp send queues.

Similarly virtnet_poll_tx() called free_old_xmit_skbs(). This NAPI
handler is called even without calling start_xmit() because cb for tx is
by default enabled. Once the handler is called, it enabled the cb again,
and then the handler would be called again. We don't need this handler
for XDP, so don't enable cb as well as not calling free_old_xmit_skbs().

Also, we need to disable tx NAPI when disabling XDP, so
virtnet_poll_tx() can safely access curr_queue_pairs and
xdp_queue_pairs, which are not atomically updated while disabling XDP.

Fixes: b92f1e6751a6 ("virtio-net: transmit napi")
Fixes: 7b0411ef4aa6 ("virtio-net: clean tx descriptors from rx napi")
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 49 +++++++++++++++++++++++++++-------------
 1 file changed, 33 insertions(+), 16 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 8de7b6fbb5c3..406171194121 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1357,6 +1357,16 @@ static void free_old_xmit_skbs(struct send_queue *sq)
 	u64_stats_update_end(&sq->stats.syncp);
 }
 
+static bool is_xdp_raw_buffer_queue(struct virtnet_info *vi, int q)
+{
+	if (q < (vi->curr_queue_pairs - vi->xdp_queue_pairs))
+		return false;
+	else if (q < vi->curr_queue_pairs)
+		return true;
+	else
+		return false;
+}
+
 static void virtnet_poll_cleantx(struct receive_queue *rq)
 {
 	struct virtnet_info *vi = rq->vq->vdev->priv;
@@ -1364,7 +1374,7 @@ static void virtnet_poll_cleantx(struct receive_queue *rq)
 	struct send_queue *sq = &vi->sq[index];
 	struct netdev_queue *txq = netdev_get_tx_queue(vi->dev, index);
 
-	if (!sq->napi.weight)
+	if (!sq->napi.weight || is_xdp_raw_buffer_queue(vi, index))
 		return;
 
 	if (__netif_tx_trylock(txq)) {
@@ -1441,8 +1451,16 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget)
 {
 	struct send_queue *sq = container_of(napi, struct send_queue, napi);
 	struct virtnet_info *vi = sq->vq->vdev->priv;
-	struct netdev_queue *txq = netdev_get_tx_queue(vi->dev, vq2txq(sq->vq));
+	unsigned int index = vq2txq(sq->vq);
+	struct netdev_queue *txq;
 
+	if (unlikely(is_xdp_raw_buffer_queue(vi, index))) {
+		/* We don't need to enable cb for XDP */
+		napi_complete_done(napi, 0);
+		return 0;
+	}
+
+	txq = netdev_get_tx_queue(vi->dev, index);
 	__netif_tx_lock(txq, raw_smp_processor_id());
 	free_old_xmit_skbs(sq);
 	__netif_tx_unlock(txq);
@@ -2352,9 +2370,12 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 	}
 
 	/* Make sure NAPI is not using any XDP TX queues for RX. */
-	if (netif_running(dev))
-		for (i = 0; i < vi->max_queue_pairs; i++)
+	if (netif_running(dev)) {
+		for (i = 0; i < vi->max_queue_pairs; i++) {
 			napi_disable(&vi->rq[i].napi);
+			virtnet_napi_tx_disable(&vi->sq[i].napi);
+		}
+	}
 
 	netif_set_real_num_rx_queues(dev, curr_qp + xdp_qp);
 	err = _virtnet_set_queues(vi, curr_qp + xdp_qp);
@@ -2373,16 +2394,22 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 		}
 		if (old_prog)
 			bpf_prog_put(old_prog);
-		if (netif_running(dev))
+		if (netif_running(dev)) {
 			virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
+			virtnet_napi_tx_enable(vi, vi->sq[i].vq,
+					       &vi->sq[i].napi);
+		}
 	}
 
 	return 0;
 
 err:
 	if (netif_running(dev)) {
-		for (i = 0; i < vi->max_queue_pairs; i++)
+		for (i = 0; i < vi->max_queue_pairs; i++) {
 			virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
+			virtnet_napi_tx_enable(vi, vi->sq[i].vq,
+					       &vi->sq[i].napi);
+		}
 	}
 	if (prog)
 		bpf_prog_sub(prog, vi->max_queue_pairs - 1);
@@ -2539,16 +2566,6 @@ static void free_receive_page_frags(struct virtnet_info *vi)
 			put_page(vi->rq[i].alloc_frag.page);
 }
 
-static bool is_xdp_raw_buffer_queue(struct virtnet_info *vi, int q)
-{
-	if (q < (vi->curr_queue_pairs - vi->xdp_queue_pairs))
-		return false;
-	else if (q < vi->curr_queue_pairs)
-		return true;
-	else
-		return false;
-}
-
 static void free_unused_bufs(struct virtnet_info *vi)
 {
 	void *buf;
-- 
2.20.1


From 0fda4162e59fbda52cfea72d1e294f27a41bed83 Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Tue, 29 Jan 2019 09:45:55 +0900
Subject: [PATCH 26/30] virtio_net: Fix not restoring real_num_rx_queues

[ Upstream commit 188313c137c4f76afd0862f50dbc185b198b9e2a ]

When _virtnet_set_queues() failed we did not restore real_num_rx_queues.
Fix this by placing the change of real_num_rx_queues after
_virtnet_set_queues().
This order is also in line with virtnet_set_channels().

Fixes: 4941d472bf95 ("virtio-net: do not reset during XDP set")
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 406171194121..6bea1fe5a2a7 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2377,10 +2377,10 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 		}
 	}
 
-	netif_set_real_num_rx_queues(dev, curr_qp + xdp_qp);
 	err = _virtnet_set_queues(vi, curr_qp + xdp_qp);
 	if (err)
 		goto err;
+	netif_set_real_num_rx_queues(dev, curr_qp + xdp_qp);
 	vi->xdp_queue_pairs = xdp_qp;
 
 	for (i = 0; i < vi->max_queue_pairs; i++) {
-- 
2.20.1


From 12be463ef13a30db141fed23b4c4be39af63716d Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Tue, 29 Jan 2019 09:45:56 +0900
Subject: [PATCH 27/30] virtio_net: Fix out of bounds access of sq

[ Upstream commit 1667c08a9d31c7cdf09f4890816bfbf20b685495 ]

When XDP is disabled, curr_queue_pairs + smp_processor_id() can be
larger than max_queue_pairs.
There is no guarantee that we have enough XDP send queues dedicated for
each cpu when XDP is disabled, so do not count drops on sq in that case.

Fixes: 5b8f3c8d30a6 ("virtio_net: Add XDP related stats")
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 17 +++++++----------
 1 file changed, 7 insertions(+), 10 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 6bea1fe5a2a7..94a6f729236b 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -490,20 +490,17 @@ static int virtnet_xdp_xmit(struct net_device *dev,
 	int ret, err;
 	int i;
 
-	sq = virtnet_xdp_sq(vi);
-
-	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) {
-		ret = -EINVAL;
-		drops = n;
-		goto out;
-	}
-
 	/* Only allow ndo_xdp_xmit if XDP is loaded on dev, as this
 	 * indicate XDP resources have been successfully allocated.
 	 */
 	xdp_prog = rcu_dereference(rq->xdp_prog);
-	if (!xdp_prog) {
-		ret = -ENXIO;
+	if (!xdp_prog)
+		return -ENXIO;
+
+	sq = virtnet_xdp_sq(vi);
+
+	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) {
+		ret = -EINVAL;
 		drops = n;
 		goto out;
 	}
-- 
2.20.1


From 7e3124ffc8925ca3ffc8b4f5a2600294b90773e5 Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Tue, 29 Jan 2019 09:45:57 +0900
Subject: [PATCH 28/30] virtio_net: Don't process redirected XDP frames when
 XDP is disabled

[ Upstream commit 03aa6d34868c07b2b1b8b2db080602d7ec528173 ]

Commit 8dcc5b0ab0ec ("virtio_net: fix ndo_xdp_xmit crash towards dev not
ready for XDP") tried to avoid access to unexpected sq while XDP is
disabled, but was not complete.

There was a small window which causes out of bounds sq access in
virtnet_xdp_xmit() while disabling XDP.

An example case of
 - curr_queue_pairs = 6 (2 for SKB and 4 for XDP)
 - online_cpu_num = xdp_queue_paris = 4
when XDP is enabled:

CPU 0                         CPU 1
(Disabling XDP)               (Processing redirected XDP frames)

                              virtnet_xdp_xmit()
virtnet_xdp_set()
 _virtnet_set_queues()
  set curr_queue_pairs (2)
                               check if rq->xdp_prog is not NULL
                               virtnet_xdp_sq(vi)
                                qp = curr_queue_pairs -
                                     xdp_queue_pairs +
                                     smp_processor_id()
                                   = 2 - 4 + 1 = -1
                                sq = &vi->sq[qp] // out of bounds access
  set xdp_queue_pairs (0)
  rq->xdp_prog = NULL

Basically we should not change curr_queue_pairs and xdp_queue_pairs
while someone can read the values. Thus, when disabling XDP, assign NULL
to rq->xdp_prog first, and wait for RCU grace period, then change
xxx_queue_pairs.
Note that we need to keep the current order when enabling XDP though.

- v2: Make rcu_assign_pointer/synchronize_net conditional instead of
      _virtnet_set_queues.

Fixes: 186b3c998c50 ("virtio-net: support XDP_REDIRECT")
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 33 ++++++++++++++++++++++++++-------
 1 file changed, 26 insertions(+), 7 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 94a6f729236b..188041447d19 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2360,6 +2360,10 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 		return -ENOMEM;
 	}
 
+	old_prog = rtnl_dereference(vi->rq[0].xdp_prog);
+	if (!prog && !old_prog)
+		return 0;
+
 	if (prog) {
 		prog = bpf_prog_add(prog, vi->max_queue_pairs - 1);
 		if (IS_ERR(prog))
@@ -2374,21 +2378,30 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 		}
 	}
 
+	if (!prog) {
+		for (i = 0; i < vi->max_queue_pairs; i++) {
+			rcu_assign_pointer(vi->rq[i].xdp_prog, prog);
+			if (i == 0)
+				virtnet_restore_guest_offloads(vi);
+		}
+		synchronize_net();
+	}
+
 	err = _virtnet_set_queues(vi, curr_qp + xdp_qp);
 	if (err)
 		goto err;
 	netif_set_real_num_rx_queues(dev, curr_qp + xdp_qp);
 	vi->xdp_queue_pairs = xdp_qp;
 
-	for (i = 0; i < vi->max_queue_pairs; i++) {
-		old_prog = rtnl_dereference(vi->rq[i].xdp_prog);
-		rcu_assign_pointer(vi->rq[i].xdp_prog, prog);
-		if (i == 0) {
-			if (!old_prog)
+	if (prog) {
+		for (i = 0; i < vi->max_queue_pairs; i++) {
+			rcu_assign_pointer(vi->rq[i].xdp_prog, prog);
+			if (i == 0 && !old_prog)
 				virtnet_clear_guest_offloads(vi);
-			if (!prog)
-				virtnet_restore_guest_offloads(vi);
 		}
+	}
+
+	for (i = 0; i < vi->max_queue_pairs; i++) {
 		if (old_prog)
 			bpf_prog_put(old_prog);
 		if (netif_running(dev)) {
@@ -2401,6 +2414,12 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 	return 0;
 
 err:
+	if (!prog) {
+		virtnet_clear_guest_offloads(vi);
+		for (i = 0; i < vi->max_queue_pairs; i++)
+			rcu_assign_pointer(vi->rq[i].xdp_prog, old_prog);
+	}
+
 	if (netif_running(dev)) {
 		for (i = 0; i < vi->max_queue_pairs; i++) {
 			virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
-- 
2.20.1


From 32d036b8a68e41cc01ec14893ab2e8dfe1e5a3d8 Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Tue, 29 Jan 2019 09:45:58 +0900
Subject: [PATCH 29/30] virtio_net: Use xdp_return_frame to free xdp_frames on
 destroying vqs

[ Upstream commit 07b344f494ddda9f061b396407c96df8c46c82b5 ]

put_page() can work as a fallback for freeing xdp_frames, but the
appropriate way is to use xdp_return_frame().

Fixes: cac320c850ef ("virtio_net: convert to use generic xdp_frame and xdp_return_frame API")
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 188041447d19..7f97b24baaee 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2593,7 +2593,7 @@ static void free_unused_bufs(struct virtnet_info *vi)
 			if (!is_xdp_raw_buffer_queue(vi, i))
 				dev_kfree_skb(buf);
 			else
-				put_page(virt_to_head_page(buf));
+				xdp_return_frame(buf);
 		}
 	}
 
-- 
2.20.1


From a4fe4502ad00d9306f979023d22d8fda9b1a071d Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Tue, 29 Jan 2019 09:45:59 +0900
Subject: [PATCH 30/30] virtio_net: Differentiate sk_buff and xdp_frame on
 freeing

[ Upstream commit 5050471d35d1316ba32dfcbb409978337eb9e75e

  I had to fold commit df133f3f9625 ("virtio_net: bulk free tx skbs")
  into this to make it work.  ]

We do not reset or free up unused buffers when enabling/disabling XDP,
so it can happen that xdp_frames are freed after disabling XDP or
sk_buffs are freed after enabling XDP on xdp tx queues.
Thus we need to handle both forms (xdp_frames and sk_buffs) regardless
of XDP setting.
One way to trigger this problem is to disable XDP when napi_tx is
enabled. In that case, virtnet_xdp_set() calls virtnet_napi_enable()
which kicks NAPI. The NAPI handler will call virtnet_poll_cleantx()
which invokes free_old_xmit_skbs() for queues which have been used by
XDP.

Note that even with this change we need to keep skipping
free_old_xmit_skbs() from NAPI handlers when XDP is enabled, because XDP
tx queues do not aquire queue locks.

- v2: Use napi_consume_skb() instead of dev_consume_skb_any()

Fixes: 4941d472bf95 ("virtio-net: do not reset during XDP set")
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 64 +++++++++++++++++++++++++++++-----------
 1 file changed, 47 insertions(+), 17 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 7f97b24baaee..42feaa4d2916 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -57,6 +57,8 @@ module_param(napi_tx, bool, 0644);
 #define VIRTIO_XDP_TX		BIT(0)
 #define VIRTIO_XDP_REDIR	BIT(1)
 
+#define VIRTIO_XDP_FLAG	BIT(0)
+
 /* RX packet size EWMA. The average packet size is used to determine the packet
  * buffer size when refilling RX rings. As the entire RX ring may be refilled
  * at once, the weight is chosen so that the EWMA will be insensitive to short-
@@ -251,6 +253,21 @@ struct padded_vnet_hdr {
 	char padding[4];
 };
 
+static bool is_xdp_frame(void *ptr)
+{
+	return (unsigned long)ptr & VIRTIO_XDP_FLAG;
+}
+
+static void *xdp_to_ptr(struct xdp_frame *ptr)
+{
+	return (void *)((unsigned long)ptr | VIRTIO_XDP_FLAG);
+}
+
+static struct xdp_frame *ptr_to_xdp(void *ptr)
+{
+	return (struct xdp_frame *)((unsigned long)ptr & ~VIRTIO_XDP_FLAG);
+}
+
 /* Converting between virtqueue no. and kernel tx/rx queue no.
  * 0:rx0 1:tx0 2:rx1 3:tx1 ... 2N:rxN 2N+1:txN 2N+2:cvq
  */
@@ -461,7 +478,8 @@ static int __virtnet_xdp_xmit_one(struct virtnet_info *vi,
 
 	sg_init_one(sq->sg, xdpf->data, xdpf->len);
 
-	err = virtqueue_add_outbuf(sq->vq, sq->sg, 1, xdpf, GFP_ATOMIC);
+	err = virtqueue_add_outbuf(sq->vq, sq->sg, 1, xdp_to_ptr(xdpf),
+				   GFP_ATOMIC);
 	if (unlikely(err))
 		return -ENOSPC; /* Caller handle free/refcnt */
 
@@ -481,13 +499,13 @@ static int virtnet_xdp_xmit(struct net_device *dev,
 {
 	struct virtnet_info *vi = netdev_priv(dev);
 	struct receive_queue *rq = vi->rq;
-	struct xdp_frame *xdpf_sent;
 	struct bpf_prog *xdp_prog;
 	struct send_queue *sq;
 	unsigned int len;
 	int drops = 0;
 	int kicks = 0;
 	int ret, err;
+	void *ptr;
 	int i;
 
 	/* Only allow ndo_xdp_xmit if XDP is loaded on dev, as this
@@ -506,8 +524,12 @@ static int virtnet_xdp_xmit(struct net_device *dev,
 	}
 
 	/* Free up any pending old buffers before queueing new ones. */
-	while ((xdpf_sent = virtqueue_get_buf(sq->vq, &len)) != NULL)
-		xdp_return_frame(xdpf_sent);
+	while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) {
+		if (likely(is_xdp_frame(ptr)))
+			xdp_return_frame(ptr_to_xdp(ptr));
+		else
+			napi_consume_skb(ptr, false);
+	}
 
 	for (i = 0; i < n; i++) {
 		struct xdp_frame *xdpf = frames[i];
@@ -1326,20 +1348,28 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
 	return stats.packets;
 }
 
-static void free_old_xmit_skbs(struct send_queue *sq)
+static void free_old_xmit_skbs(struct send_queue *sq, bool in_napi)
 {
-	struct sk_buff *skb;
 	unsigned int len;
 	unsigned int packets = 0;
 	unsigned int bytes = 0;
+	void *ptr;
 
-	while ((skb = virtqueue_get_buf(sq->vq, &len)) != NULL) {
-		pr_debug("Sent skb %p\n", skb);
+	while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) {
+		if (likely(!is_xdp_frame(ptr))) {
+			struct sk_buff *skb = ptr;
 
-		bytes += skb->len;
-		packets++;
+			pr_debug("Sent skb %p\n", skb);
 
-		dev_consume_skb_any(skb);
+			bytes += skb->len;
+			napi_consume_skb(skb, in_napi);
+		} else {
+			struct xdp_frame *frame = ptr_to_xdp(ptr);
+
+			bytes += frame->len;
+			xdp_return_frame(frame);
+		}
+		packets++;
 	}
 
 	/* Avoid overhead when no packets have been processed
@@ -1375,7 +1405,7 @@ static void virtnet_poll_cleantx(struct receive_queue *rq)
 		return;
 
 	if (__netif_tx_trylock(txq)) {
-		free_old_xmit_skbs(sq);
+		free_old_xmit_skbs(sq, true);
 		__netif_tx_unlock(txq);
 	}
 
@@ -1459,7 +1489,7 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget)
 
 	txq = netdev_get_tx_queue(vi->dev, index);
 	__netif_tx_lock(txq, raw_smp_processor_id());
-	free_old_xmit_skbs(sq);
+	free_old_xmit_skbs(sq, true);
 	__netif_tx_unlock(txq);
 
 	virtqueue_napi_complete(napi, sq->vq, 0);
@@ -1528,7 +1558,7 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 	bool use_napi = sq->napi.weight;
 
 	/* Free up any pending old buffers before queueing new ones. */
-	free_old_xmit_skbs(sq);
+	free_old_xmit_skbs(sq, false);
 
 	if (use_napi && kick)
 		virtqueue_enable_cb_delayed(sq->vq);
@@ -1571,7 +1601,7 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 		if (!use_napi &&
 		    unlikely(!virtqueue_enable_cb_delayed(sq->vq))) {
 			/* More just got used, free them then recheck. */
-			free_old_xmit_skbs(sq);
+			free_old_xmit_skbs(sq, false);
 			if (sq->vq->num_free >= 2+MAX_SKB_FRAGS) {
 				netif_start_subqueue(dev, qnum);
 				virtqueue_disable_cb(sq->vq);
@@ -2590,10 +2620,10 @@ static void free_unused_bufs(struct virtnet_info *vi)
 	for (i = 0; i < vi->max_queue_pairs; i++) {
 		struct virtqueue *vq = vi->sq[i].vq;
 		while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) {
-			if (!is_xdp_raw_buffer_queue(vi, i))
+			if (!is_xdp_frame(buf))
 				dev_kfree_skb(buf);
 			else
-				xdp_return_frame(buf);
+				xdp_return_frame(ptr_to_xdp(buf));
 		}
 	}
 
-- 
2.20.1


[-- Attachment #3: net_420.mbox --]
[-- Type: Application/Octet-Stream, Size: 95130 bytes --]

From b0f23bf25f916cd935e493e73f2c61776aac7d79 Mon Sep 17 00:00:00 2001
From: Yohei Kanemaru <yohei.kanemaru@gmail.com>
Date: Tue, 29 Jan 2019 15:52:34 +0900
Subject: [PATCH 01/33] ipv6: sr: clear IP6CB(skb) on SRH ip4ip6 encapsulation

[ Upstream commit ef489749aae508e6f17886775c075f12ff919fb1 ]

skb->cb may contain data from previous layers (in an observed case
IPv4 with L3 Master Device). In the observed scenario, the data in
IPCB(skb)->frags was misinterpreted as IP6CB(skb)->frag_max_size,
eventually caused an unexpected IPv6 fragmentation in ip6_fragment()
through ip6_finish_output().

This patch clears IP6CB(skb), which potentially contains garbage data,
on the SRH ip4ip6 encapsulation.

Fixes: 32d99d0b6702 ("ipv6: sr: add support for ip4ip6 encapsulation")
Signed-off-by: Yohei Kanemaru <yohei.kanemaru@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/seg6_iptunnel.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 8181ee7e1e27..ee5403cbe655 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -146,6 +146,8 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
 	} else {
 		ip6_flow_hdr(hdr, 0, flowlabel);
 		hdr->hop_limit = ip6_dst_hoplimit(skb_dst(skb));
+
+		memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
 	}
 
 	hdr->nexthdr = NEXTHDR_ROUTING;
-- 
2.20.1


From 9f9ce7b32b8669b44e443be46ea4bc721cacc125 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 30 Jan 2019 12:49:48 +0100
Subject: [PATCH 02/33] ipvlan, l3mdev: fix broken l3s mode wrt local routes

[ Upstream commit d5256083f62e2720f75bb3c5a928a0afe47d6bc3 ]

While implementing ipvlan l3 and l3s mode for kubernetes CNI plugin,
I ran into the issue that while l3 mode is working fine, l3s mode
does not have any connectivity to kube-apiserver and hence all pods
end up in Error state as well. The ipvlan master device sits on
top of a bond device and hostns traffic to kube-apiserver (also running
in hostns) is DNATed from 10.152.183.1:443 to 139.178.29.207:37573
where the latter is the address of the bond0. While in l3 mode, a
curl to https://10.152.183.1:443 or to https://139.178.29.207:37573
works fine from hostns, neither of them do in case of l3s. In the
latter only a curl to https://127.0.0.1:37573 appeared to work where
for local addresses of bond0 I saw kernel suddenly starting to emit
ARP requests to query HW address of bond0 which remained unanswered
and neighbor entries in INCOMPLETE state. These ARP requests only
happen while in l3s.

Debugging this further, I found the issue is that l3s mode is piggy-
backing on l3 master device, and in this case local routes are using
l3mdev_master_dev_rcu(dev) instead of net->loopback_dev as per commit
f5a0aab84b74 ("net: ipv4: dst for local input routes should use l3mdev
if relevant") and 5f02ce24c269 ("net: l3mdev: Allow the l3mdev to be
a loopback"). I found that reverting them back into using the
net->loopback_dev fixed ipvlan l3s connectivity and got everything
working for the CNI.

Now judging from 4fbae7d83c98 ("ipvlan: Introduce l3s mode") and the
l3mdev paper in [0] the only sole reason why ipvlan l3s is relying
on l3 master device is to get the l3mdev_ip_rcv() receive hook for
setting the dst entry of the input route without adding its own
ipvlan specific hacks into the receive path, however, any l3 domain
semantics beyond just that are breaking l3s operation. Note that
ipvlan also has the ability to dynamically switch its internal
operation from l3 to l3s for all ports via ipvlan_set_port_mode()
at runtime. In any case, l3 vs l3s soley distinguishes itself by
'de-confusing' netfilter through switching skb->dev to ipvlan slave
device late in NF_INET_LOCAL_IN before handing the skb to L4.

Minimal fix taken here is to add a IFF_L3MDEV_RX_HANDLER flag which,
if set from ipvlan setup, gets us only the wanted l3mdev_l3_rcv() hook
without any additional l3mdev semantics on top. This should also have
minimal impact since dev->priv_flags is already hot in cache. With
this set, l3s mode is working fine and I also get things like
masquerading pod traffic on the ipvlan master properly working.

  [0] https://netdevconf.org/1.2/papers/ahern-what-is-l3mdev-paper.pdf

Fixes: f5a0aab84b74 ("net: ipv4: dst for local input routes should use l3mdev if relevant")
Fixes: 5f02ce24c269 ("net: l3mdev: Allow the l3mdev to be a loopback")
Fixes: 4fbae7d83c98 ("ipvlan: Introduce l3s mode")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Mahesh Bandewar <maheshb@google.com>
Cc: David Ahern <dsa@cumulusnetworks.com>
Cc: Florian Westphal <fw@strlen.de>
Cc: Martynas Pumputis <m@lambda.lt>
Acked-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ipvlan/ipvlan_main.c | 6 +++---
 include/linux/netdevice.h        | 8 ++++++++
 include/net/l3mdev.h             | 3 ++-
 3 files changed, 13 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 4a949569ec4c..5fb541897863 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -97,12 +97,12 @@ static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval)
 			err = ipvlan_register_nf_hook(read_pnet(&port->pnet));
 			if (!err) {
 				mdev->l3mdev_ops = &ipvl_l3mdev_ops;
-				mdev->priv_flags |= IFF_L3MDEV_MASTER;
+				mdev->priv_flags |= IFF_L3MDEV_RX_HANDLER;
 			} else
 				goto fail;
 		} else if (port->mode == IPVLAN_MODE_L3S) {
 			/* Old mode was L3S */
-			mdev->priv_flags &= ~IFF_L3MDEV_MASTER;
+			mdev->priv_flags &= ~IFF_L3MDEV_RX_HANDLER;
 			ipvlan_unregister_nf_hook(read_pnet(&port->pnet));
 			mdev->l3mdev_ops = NULL;
 		}
@@ -162,7 +162,7 @@ static void ipvlan_port_destroy(struct net_device *dev)
 	struct sk_buff *skb;
 
 	if (port->mode == IPVLAN_MODE_L3S) {
-		dev->priv_flags &= ~IFF_L3MDEV_MASTER;
+		dev->priv_flags &= ~IFF_L3MDEV_RX_HANDLER;
 		ipvlan_unregister_nf_hook(dev_net(dev));
 		dev->l3mdev_ops = NULL;
 	}
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 857f8abf7b91..d5e38eddfb49 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1487,6 +1487,7 @@ struct net_device_ops {
  * @IFF_NO_RX_HANDLER: device doesn't support the rx_handler hook
  * @IFF_FAILOVER: device is a failover master device
  * @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device
+ * @IFF_L3MDEV_RX_HANDLER: only invoke the rx handler of L3 master device
  */
 enum netdev_priv_flags {
 	IFF_802_1Q_VLAN			= 1<<0,
@@ -1518,6 +1519,7 @@ enum netdev_priv_flags {
 	IFF_NO_RX_HANDLER		= 1<<26,
 	IFF_FAILOVER			= 1<<27,
 	IFF_FAILOVER_SLAVE		= 1<<28,
+	IFF_L3MDEV_RX_HANDLER		= 1<<29,
 };
 
 #define IFF_802_1Q_VLAN			IFF_802_1Q_VLAN
@@ -1548,6 +1550,7 @@ enum netdev_priv_flags {
 #define IFF_NO_RX_HANDLER		IFF_NO_RX_HANDLER
 #define IFF_FAILOVER			IFF_FAILOVER
 #define IFF_FAILOVER_SLAVE		IFF_FAILOVER_SLAVE
+#define IFF_L3MDEV_RX_HANDLER		IFF_L3MDEV_RX_HANDLER
 
 /**
  *	struct net_device - The DEVICE structure.
@@ -4523,6 +4526,11 @@ static inline bool netif_supports_nofcs(struct net_device *dev)
 	return dev->priv_flags & IFF_SUPP_NOFCS;
 }
 
+static inline bool netif_has_l3_rx_handler(const struct net_device *dev)
+{
+	return dev->priv_flags & IFF_L3MDEV_RX_HANDLER;
+}
+
 static inline bool netif_is_l3_master(const struct net_device *dev)
 {
 	return dev->priv_flags & IFF_L3MDEV_MASTER;
diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h
index 3832099289c5..128487658ff7 100644
--- a/include/net/l3mdev.h
+++ b/include/net/l3mdev.h
@@ -142,7 +142,8 @@ struct sk_buff *l3mdev_l3_rcv(struct sk_buff *skb, u16 proto)
 
 	if (netif_is_l3_slave(skb->dev))
 		master = netdev_master_upper_dev_get_rcu(skb->dev);
-	else if (netif_is_l3_master(skb->dev))
+	else if (netif_is_l3_master(skb->dev) ||
+		 netif_has_l3_rx_handler(skb->dev))
 		master = skb->dev;
 
 	if (master && master->l3mdev_ops->l3mdev_l3_rcv)
-- 
2.20.1


From f3cea03ee60a0ffb297cb5303ac9ef6ef6765e30 Mon Sep 17 00:00:00 2001
From: Jacob Wen <jian.w.wen@oracle.com>
Date: Thu, 31 Jan 2019 15:18:56 +0800
Subject: [PATCH 03/33] l2tp: copy 4 more bytes to linear part if necessary

[ Upstream commit 91c524708de6207f59dd3512518d8a1c7b434ee3 ]

The size of L2TPv2 header with all optional fields is 14 bytes.
l2tp_udp_recv_core only moves 10 bytes to the linear part of a
skb. This may lead to l2tp_recv_common read data outside of a skb.

This patch make sure that there is at least 14 bytes in the linear
part of a skb to meet the maximum need of l2tp_udp_recv_core and
l2tp_recv_common. The minimum size of both PPP HDLC-like frame and
Ethernet frame is larger than 14 bytes, so we are safe to do so.

Also remove L2TP_HDR_SIZE_NOSEQ, it is unused now.

Fixes: fd558d186df2 ("l2tp: Split pppol2tp patch into separate l2tp and ppp parts")
Suggested-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: Jacob Wen <jian.w.wen@oracle.com>
Acked-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 26f1d435696a..9accaec15c32 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -83,8 +83,7 @@
 #define L2TP_SLFLAG_S	   0x40000000
 #define L2TP_SL_SEQ_MASK   0x00ffffff
 
-#define L2TP_HDR_SIZE_SEQ		10
-#define L2TP_HDR_SIZE_NOSEQ		6
+#define L2TP_HDR_SIZE_MAX		14
 
 /* Default trace flags */
 #define L2TP_DEFAULT_DEBUG_FLAGS	0
@@ -808,7 +807,7 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb)
 	__skb_pull(skb, sizeof(struct udphdr));
 
 	/* Short packet? */
-	if (!pskb_may_pull(skb, L2TP_HDR_SIZE_SEQ)) {
+	if (!pskb_may_pull(skb, L2TP_HDR_SIZE_MAX)) {
 		l2tp_info(tunnel, L2TP_MSG_DATA,
 			  "%s: recv short packet (len=%d)\n",
 			  tunnel->name, skb->len);
-- 
2.20.1


From 75902800586cae4cff85de57ea19f0e325f3c5c1 Mon Sep 17 00:00:00 2001
From: Jacob Wen <jian.w.wen@oracle.com>
Date: Wed, 30 Jan 2019 14:55:14 +0800
Subject: [PATCH 04/33] l2tp: fix reading optional fields of L2TPv3

[ Upstream commit 4522a70db7aa5e77526a4079628578599821b193 ]

Use pskb_may_pull() to make sure the optional fields are in skb linear
parts, so we can safely read them later.

It's easy to reproduce the issue with a net driver that supports paged
skb data. Just create a L2TPv3 over IP tunnel and then generates some
network traffic.
Once reproduced, rx err in /sys/kernel/debug/l2tp/tunnels will increase.

Changes in v4:
1. s/l2tp_v3_pull_opt/l2tp_v3_ensure_opt_in_linear/
2. s/tunnel->version != L2TP_HDR_VER_2/tunnel->version == L2TP_HDR_VER_3/
3. Add 'Fixes' in commit messages.

Changes in v3:
1. To keep consistency, move the code out of l2tp_recv_common.
2. Use "net" instead of "net-next", since this is a bug fix.

Changes in v2:
1. Only fix L2TPv3 to make code simple.
   To fix both L2TPv3 and L2TPv2, we'd better refactor l2tp_recv_common.
   It's complicated to do so.
2. Reloading pointers after pskb_may_pull

Fixes: f7faffa3ff8e ("l2tp: Add L2TPv3 protocol support")
Fixes: 0d76751fad77 ("l2tp: Add L2TPv3 IP encapsulation (no UDP) support")
Fixes: a32e0eec7042 ("l2tp: introduce L2TPv3 IP encapsulation support for IPv6")
Signed-off-by: Jacob Wen <jian.w.wen@oracle.com>
Acked-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c |  4 ++++
 net/l2tp/l2tp_core.h | 20 ++++++++++++++++++++
 net/l2tp/l2tp_ip.c   |  3 +++
 net/l2tp/l2tp_ip6.c  |  3 +++
 4 files changed, 30 insertions(+)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 9accaec15c32..fed6becc5daf 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -883,6 +883,10 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb)
 		goto error;
 	}
 
+	if (tunnel->version == L2TP_HDR_VER_3 &&
+	    l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr))
+		goto error;
+
 	l2tp_recv_common(session, skb, ptr, optr, hdrflags, length);
 	l2tp_session_dec_refcount(session);
 
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 9c9afe94d389..b2ce90260c35 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -301,6 +301,26 @@ static inline bool l2tp_tunnel_uses_xfrm(const struct l2tp_tunnel *tunnel)
 }
 #endif
 
+static inline int l2tp_v3_ensure_opt_in_linear(struct l2tp_session *session, struct sk_buff *skb,
+					       unsigned char **ptr, unsigned char **optr)
+{
+	int opt_len = session->peer_cookie_len + l2tp_get_l2specific_len(session);
+
+	if (opt_len > 0) {
+		int off = *ptr - *optr;
+
+		if (!pskb_may_pull(skb, off + opt_len))
+			return -1;
+
+		if (skb->data != *optr) {
+			*optr = skb->data;
+			*ptr = skb->data + off;
+		}
+	}
+
+	return 0;
+}
+
 #define l2tp_printk(ptr, type, func, fmt, ...)				\
 do {									\
 	if (((ptr)->debug) & (type))					\
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 35f6f86d4dcc..d4c60523c549 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -165,6 +165,9 @@ static int l2tp_ip_recv(struct sk_buff *skb)
 		print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length);
 	}
 
+	if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr))
+		goto discard_sess;
+
 	l2tp_recv_common(session, skb, ptr, optr, 0, skb->len);
 	l2tp_session_dec_refcount(session);
 
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 237f1a4a0b0c..0ae6899edac0 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -178,6 +178,9 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
 		print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length);
 	}
 
+	if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr))
+		goto discard_sess;
+
 	l2tp_recv_common(session, skb, ptr, optr, 0, skb->len);
 	l2tp_session_dec_refcount(session);
 
-- 
2.20.1


From 9c419bb0d45e5fe8ce8f5a9557857b29795def0e Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Mon, 28 Jan 2019 22:23:48 +0100
Subject: [PATCH 05/33] net: ip_gre: always reports o_key to userspace

[ Upstream commit feaf5c796b3f0240f10d0d6d0b686715fd58a05b ]

Erspan protocol (version 1 and 2) relies on o_key to configure
session id header field. However TUNNEL_KEY bit is cleared in
erspan_xmit since ERSPAN protocol does not set the key field
of the external GRE header and so the configured o_key is not reported
to userspace. The issue can be triggered with the following reproducer:

$ip link add erspan1 type erspan local 192.168.0.1 remote 192.168.0.2 \
    key 1 seq erspan_ver 1
$ip link set erspan1 up
$ip -d link sh erspan1

erspan1@NONE: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1450 qdisc pfifo_fast state UNKNOWN mode DEFAULT
  link/ether 52:aa:99:95:9a:b5 brd ff:ff:ff:ff:ff:ff promiscuity 0 minmtu 68 maxmtu 1500
  erspan remote 192.168.0.2 local 192.168.0.1 ttl inherit ikey 0.0.0.1 iseq oseq erspan_index 0

Fix the issue adding TUNNEL_KEY bit to the o_flags parameter in
ipgre_fill_info

Fixes: 84e54fe0a5ea ("gre: introduce native tunnel support for ERSPAN")
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_gre.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 3407a82d4549..92830710331e 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1468,12 +1468,17 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev)
 {
 	struct ip_tunnel *t = netdev_priv(dev);
 	struct ip_tunnel_parm *p = &t->parms;
+	__be16 o_flags = p->o_flags;
+
+	if ((t->erspan_ver == 1 || t->erspan_ver == 2) &&
+	    !t->collect_md)
+		o_flags |= TUNNEL_KEY;
 
 	if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) ||
 	    nla_put_be16(skb, IFLA_GRE_IFLAGS,
 			 gre_tnl_flags_to_gre_flags(p->i_flags)) ||
 	    nla_put_be16(skb, IFLA_GRE_OFLAGS,
-			 gre_tnl_flags_to_gre_flags(p->o_flags)) ||
+			 gre_tnl_flags_to_gre_flags(o_flags)) ||
 	    nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) ||
 	    nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) ||
 	    nla_put_in_addr(skb, IFLA_GRE_LOCAL, p->iph.saddr) ||
-- 
2.20.1


From 14ddc75bddd94ef075265d27e854fc212c15b448 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Fri, 18 Jan 2019 12:05:39 +0100
Subject: [PATCH 06/33] net: ip_gre: use erspan key field for tunnel lookup

[ Upstream commit cb73ee40b1b381eaf3749e6dbeed567bb38e5258 ]

Use ERSPAN key header field as tunnel key in gre_parse_header routine
since ERSPAN protocol sets the key field of the external GRE header to
0 resulting in a tunnel lookup fail in ip6gre_err.
In addition remove key field parsing and pskb_may_pull check in
erspan_rcv and ip6erspan_rcv

Fixes: 5a963eb61b7c ("ip6_gre: Add ERSPAN native tunnel support")
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/gre_demux.c | 17 +++++++++++++++++
 net/ipv4/ip_gre.c    |  9 ---------
 net/ipv6/ip6_gre.c   |  4 ----
 3 files changed, 17 insertions(+), 13 deletions(-)

diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c
index 7efe740c06eb..511b32ea2533 100644
--- a/net/ipv4/gre_demux.c
+++ b/net/ipv4/gre_demux.c
@@ -25,6 +25,7 @@
 #include <linux/spinlock.h>
 #include <net/protocol.h>
 #include <net/gre.h>
+#include <net/erspan.h>
 
 #include <net/icmp.h>
 #include <net/route.h>
@@ -119,6 +120,22 @@ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 			hdr_len += 4;
 	}
 	tpi->hdr_len = hdr_len;
+
+	/* ERSPAN ver 1 and 2 protocol sets GRE key field
+	 * to 0 and sets the configured key in the
+	 * inner erspan header field
+	 */
+	if (greh->protocol == htons(ETH_P_ERSPAN) ||
+	    greh->protocol == htons(ETH_P_ERSPAN2)) {
+		struct erspan_base_hdr *ershdr;
+
+		if (!pskb_may_pull(skb, nhs + hdr_len + sizeof(*ershdr)))
+			return -EINVAL;
+
+		ershdr = (struct erspan_base_hdr *)options;
+		tpi->key = cpu_to_be32(get_session_id(ershdr));
+	}
+
 	return hdr_len;
 }
 EXPORT_SYMBOL(gre_parse_header);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 92830710331e..b5488c5197bc 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -266,20 +266,11 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 	int len;
 
 	itn = net_generic(net, erspan_net_id);
-	len = gre_hdr_len + sizeof(*ershdr);
-
-	/* Check based hdr len */
-	if (unlikely(!pskb_may_pull(skb, len)))
-		return PACKET_REJECT;
 
 	iph = ip_hdr(skb);
 	ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len);
 	ver = ershdr->ver;
 
-	/* The original GRE header does not have key field,
-	 * Use ERSPAN 10-bit session ID as key.
-	 */
-	tpi->key = cpu_to_be32(get_session_id(ershdr));
 	tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex,
 				  tpi->flags | TUNNEL_KEY,
 				  iph->saddr, iph->daddr, tpi->key);
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index b529a79ac222..ad2d2d269ce4 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -532,13 +532,9 @@ static int ip6erspan_rcv(struct sk_buff *skb, int gre_hdr_len,
 	struct ip6_tnl *tunnel;
 	u8 ver;
 
-	if (unlikely(!pskb_may_pull(skb, sizeof(*ershdr))))
-		return PACKET_REJECT;
-
 	ipv6h = ipv6_hdr(skb);
 	ershdr = (struct erspan_base_hdr *)skb->data;
 	ver = ershdr->ver;
-	tpi->key = cpu_to_be32(get_session_id(ershdr));
 
 	tunnel = ip6gre_tunnel_lookup(skb->dev,
 				      &ipv6h->saddr, &ipv6h->daddr, tpi->key,
-- 
2.20.1


From 5c9d7c5a6845f330164bb4582ce1e57a646ae276 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 22 Jan 2019 14:47:19 -0800
Subject: [PATCH 07/33] net/ipv6: don't return positive numbers when nothing
 was dumped

[ Upstream commit 1518039f6b5ac794313c24c76f85cead0cd60f6c ]

in6_dump_addrs() returns a positive 1 if there was nothing to dump.
This return value can not be passed as return from inet6_dump_addr()
as is, because it will confuse rtnetlink, resulting in NLMSG_DONE
never getting set:

$ ip addr list dev lo
EOF on netlink
Dump terminated

v2: flip condition to avoid a new goto (DaveA)

Fixes: 7c1e8a3817c5 ("netlink: fixup regression in RTM_GETADDR")
Reported-by: Brendan Galloway <brendan.galloway@netronome.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Tested-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index e3cb53b0ef67..d2b597674d60 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5120,6 +5120,8 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb,
 			if (idev) {
 				err = in6_dump_addrs(idev, skb, cb, s_ip_idx,
 						     &fillargs);
+				if (err > 0)
+					err = 0;
 			}
 			goto put_tgt_net;
 		}
-- 
2.20.1


From efb06ef48ca811c65319794097bd145ae8e01fbb Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Tue, 22 Jan 2019 15:19:44 +0200
Subject: [PATCH 08/33] net/mlx4_core: Add masking for a few queries on HCA
 caps

[ Upstream commit a40ded6043658444ee4dd6ee374119e4e98b33fc ]

Driver reads the query HCA capabilities without the corresponding masks.
Without the correct masks, the base addresses of the queues are
unaligned.  In addition some reserved bits were wrongly read.  Using the
correct masks, ensures alignment of the base addresses and allows future
firmware versions safe use of the reserved bits.

Fixes: ab9c17a009ee ("mlx4_core: Modify driver initialization flow to accommodate SRIOV for Ethernet")
Fixes: 0ff1fb654bec ("{NET, IB}/mlx4: Add device managed flow steering firmware API")
Signed-off-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/fw.c | 75 +++++++++++++++----------
 1 file changed, 46 insertions(+), 29 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index babcfd9c0571..75213046563c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -2064,9 +2064,11 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev,
 {
 	struct mlx4_cmd_mailbox *mailbox;
 	__be32 *outbox;
+	u64 qword_field;
 	u32 dword_field;
-	int err;
+	u16 word_field;
 	u8 byte_field;
+	int err;
 	static const u8 a0_dmfs_query_hw_steering[] =  {
 		[0] = MLX4_STEERING_DMFS_A0_DEFAULT,
 		[1] = MLX4_STEERING_DMFS_A0_DYNAMIC,
@@ -2094,19 +2096,32 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev,
 
 	/* QPC/EEC/CQC/EQC/RDMARC attributes */
 
-	MLX4_GET(param->qpc_base,      outbox, INIT_HCA_QPC_BASE_OFFSET);
-	MLX4_GET(param->log_num_qps,   outbox, INIT_HCA_LOG_QP_OFFSET);
-	MLX4_GET(param->srqc_base,     outbox, INIT_HCA_SRQC_BASE_OFFSET);
-	MLX4_GET(param->log_num_srqs,  outbox, INIT_HCA_LOG_SRQ_OFFSET);
-	MLX4_GET(param->cqc_base,      outbox, INIT_HCA_CQC_BASE_OFFSET);
-	MLX4_GET(param->log_num_cqs,   outbox, INIT_HCA_LOG_CQ_OFFSET);
-	MLX4_GET(param->altc_base,     outbox, INIT_HCA_ALTC_BASE_OFFSET);
-	MLX4_GET(param->auxc_base,     outbox, INIT_HCA_AUXC_BASE_OFFSET);
-	MLX4_GET(param->eqc_base,      outbox, INIT_HCA_EQC_BASE_OFFSET);
-	MLX4_GET(param->log_num_eqs,   outbox, INIT_HCA_LOG_EQ_OFFSET);
-	MLX4_GET(param->num_sys_eqs,   outbox, INIT_HCA_NUM_SYS_EQS_OFFSET);
-	MLX4_GET(param->rdmarc_base,   outbox, INIT_HCA_RDMARC_BASE_OFFSET);
-	MLX4_GET(param->log_rd_per_qp, outbox, INIT_HCA_LOG_RD_OFFSET);
+	MLX4_GET(qword_field, outbox, INIT_HCA_QPC_BASE_OFFSET);
+	param->qpc_base = qword_field & ~((u64)0x1f);
+	MLX4_GET(byte_field, outbox, INIT_HCA_LOG_QP_OFFSET);
+	param->log_num_qps = byte_field & 0x1f;
+	MLX4_GET(qword_field, outbox, INIT_HCA_SRQC_BASE_OFFSET);
+	param->srqc_base = qword_field & ~((u64)0x1f);
+	MLX4_GET(byte_field, outbox, INIT_HCA_LOG_SRQ_OFFSET);
+	param->log_num_srqs = byte_field & 0x1f;
+	MLX4_GET(qword_field, outbox, INIT_HCA_CQC_BASE_OFFSET);
+	param->cqc_base = qword_field & ~((u64)0x1f);
+	MLX4_GET(byte_field, outbox, INIT_HCA_LOG_CQ_OFFSET);
+	param->log_num_cqs = byte_field & 0x1f;
+	MLX4_GET(qword_field, outbox, INIT_HCA_ALTC_BASE_OFFSET);
+	param->altc_base = qword_field;
+	MLX4_GET(qword_field, outbox, INIT_HCA_AUXC_BASE_OFFSET);
+	param->auxc_base = qword_field;
+	MLX4_GET(qword_field, outbox, INIT_HCA_EQC_BASE_OFFSET);
+	param->eqc_base = qword_field & ~((u64)0x1f);
+	MLX4_GET(byte_field, outbox, INIT_HCA_LOG_EQ_OFFSET);
+	param->log_num_eqs = byte_field & 0x1f;
+	MLX4_GET(word_field, outbox, INIT_HCA_NUM_SYS_EQS_OFFSET);
+	param->num_sys_eqs = word_field & 0xfff;
+	MLX4_GET(qword_field, outbox, INIT_HCA_RDMARC_BASE_OFFSET);
+	param->rdmarc_base = qword_field & ~((u64)0x1f);
+	MLX4_GET(byte_field, outbox, INIT_HCA_LOG_RD_OFFSET);
+	param->log_rd_per_qp = byte_field & 0x7;
 
 	MLX4_GET(dword_field, outbox, INIT_HCA_FLAGS_OFFSET);
 	if (dword_field & (1 << INIT_HCA_DEVICE_MANAGED_FLOW_STEERING_EN)) {
@@ -2125,22 +2140,21 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev,
 	/* steering attributes */
 	if (param->steering_mode == MLX4_STEERING_MODE_DEVICE_MANAGED) {
 		MLX4_GET(param->mc_base, outbox, INIT_HCA_FS_BASE_OFFSET);
-		MLX4_GET(param->log_mc_entry_sz, outbox,
-			 INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET);
-		MLX4_GET(param->log_mc_table_sz, outbox,
-			 INIT_HCA_FS_LOG_TABLE_SZ_OFFSET);
-		MLX4_GET(byte_field, outbox,
-			 INIT_HCA_FS_A0_OFFSET);
+		MLX4_GET(byte_field, outbox, INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET);
+		param->log_mc_entry_sz = byte_field & 0x1f;
+		MLX4_GET(byte_field, outbox, INIT_HCA_FS_LOG_TABLE_SZ_OFFSET);
+		param->log_mc_table_sz = byte_field & 0x1f;
+		MLX4_GET(byte_field, outbox, INIT_HCA_FS_A0_OFFSET);
 		param->dmfs_high_steer_mode =
 			a0_dmfs_query_hw_steering[(byte_field >> 6) & 3];
 	} else {
 		MLX4_GET(param->mc_base, outbox, INIT_HCA_MC_BASE_OFFSET);
-		MLX4_GET(param->log_mc_entry_sz, outbox,
-			 INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET);
-		MLX4_GET(param->log_mc_hash_sz,  outbox,
-			 INIT_HCA_LOG_MC_HASH_SZ_OFFSET);
-		MLX4_GET(param->log_mc_table_sz, outbox,
-			 INIT_HCA_LOG_MC_TABLE_SZ_OFFSET);
+		MLX4_GET(byte_field, outbox, INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET);
+		param->log_mc_entry_sz = byte_field & 0x1f;
+		MLX4_GET(byte_field,  outbox, INIT_HCA_LOG_MC_HASH_SZ_OFFSET);
+		param->log_mc_hash_sz = byte_field & 0x1f;
+		MLX4_GET(byte_field, outbox, INIT_HCA_LOG_MC_TABLE_SZ_OFFSET);
+		param->log_mc_table_sz = byte_field & 0x1f;
 	}
 
 	/* CX3 is capable of extending CQEs/EQEs from 32 to 64 bytes */
@@ -2164,15 +2178,18 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev,
 	/* TPT attributes */
 
 	MLX4_GET(param->dmpt_base,  outbox, INIT_HCA_DMPT_BASE_OFFSET);
-	MLX4_GET(param->mw_enabled, outbox, INIT_HCA_TPT_MW_OFFSET);
-	MLX4_GET(param->log_mpt_sz, outbox, INIT_HCA_LOG_MPT_SZ_OFFSET);
+	MLX4_GET(byte_field, outbox, INIT_HCA_TPT_MW_OFFSET);
+	param->mw_enabled = byte_field >> 7;
+	MLX4_GET(byte_field, outbox, INIT_HCA_LOG_MPT_SZ_OFFSET);
+	param->log_mpt_sz = byte_field & 0x3f;
 	MLX4_GET(param->mtt_base,   outbox, INIT_HCA_MTT_BASE_OFFSET);
 	MLX4_GET(param->cmpt_base,  outbox, INIT_HCA_CMPT_BASE_OFFSET);
 
 	/* UAR attributes */
 
 	MLX4_GET(param->uar_page_sz, outbox, INIT_HCA_UAR_PAGE_SZ_OFFSET);
-	MLX4_GET(param->log_uar_sz, outbox, INIT_HCA_LOG_UAR_SZ_OFFSET);
+	MLX4_GET(byte_field, outbox, INIT_HCA_LOG_UAR_SZ_OFFSET);
+	param->log_uar_sz = byte_field & 0xf;
 
 	/* phv_check enable */
 	MLX4_GET(byte_field, outbox, INIT_HCA_CACHELINE_SZ_OFFSET);
-- 
2.20.1


From 329795c1cdb363c01217668ccd538434667294ec Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 24 Jan 2019 14:18:18 -0800
Subject: [PATCH 09/33] netrom: switch to sock timer API

[ Upstream commit 63346650c1a94a92be61a57416ac88c0a47c4327 ]

sk_reset_timer() and sk_stop_timer() properly handle
sock refcnt for timer function. Switching to them
could fix a refcounting bug reported by syzbot.

Reported-and-tested-by: syzbot+defa700d16f1bd1b9a05@syzkaller.appspotmail.com
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-hams@vger.kernel.org
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netrom/nr_timer.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/net/netrom/nr_timer.c b/net/netrom/nr_timer.c
index cbd51ed5a2d7..908e53ab47a4 100644
--- a/net/netrom/nr_timer.c
+++ b/net/netrom/nr_timer.c
@@ -52,21 +52,21 @@ void nr_start_t1timer(struct sock *sk)
 {
 	struct nr_sock *nr = nr_sk(sk);
 
-	mod_timer(&nr->t1timer, jiffies + nr->t1);
+	sk_reset_timer(sk, &nr->t1timer, jiffies + nr->t1);
 }
 
 void nr_start_t2timer(struct sock *sk)
 {
 	struct nr_sock *nr = nr_sk(sk);
 
-	mod_timer(&nr->t2timer, jiffies + nr->t2);
+	sk_reset_timer(sk, &nr->t2timer, jiffies + nr->t2);
 }
 
 void nr_start_t4timer(struct sock *sk)
 {
 	struct nr_sock *nr = nr_sk(sk);
 
-	mod_timer(&nr->t4timer, jiffies + nr->t4);
+	sk_reset_timer(sk, &nr->t4timer, jiffies + nr->t4);
 }
 
 void nr_start_idletimer(struct sock *sk)
@@ -74,37 +74,37 @@ void nr_start_idletimer(struct sock *sk)
 	struct nr_sock *nr = nr_sk(sk);
 
 	if (nr->idle > 0)
-		mod_timer(&nr->idletimer, jiffies + nr->idle);
+		sk_reset_timer(sk, &nr->idletimer, jiffies + nr->idle);
 }
 
 void nr_start_heartbeat(struct sock *sk)
 {
-	mod_timer(&sk->sk_timer, jiffies + 5 * HZ);
+	sk_reset_timer(sk, &sk->sk_timer, jiffies + 5 * HZ);
 }
 
 void nr_stop_t1timer(struct sock *sk)
 {
-	del_timer(&nr_sk(sk)->t1timer);
+	sk_stop_timer(sk, &nr_sk(sk)->t1timer);
 }
 
 void nr_stop_t2timer(struct sock *sk)
 {
-	del_timer(&nr_sk(sk)->t2timer);
+	sk_stop_timer(sk, &nr_sk(sk)->t2timer);
 }
 
 void nr_stop_t4timer(struct sock *sk)
 {
-	del_timer(&nr_sk(sk)->t4timer);
+	sk_stop_timer(sk, &nr_sk(sk)->t4timer);
 }
 
 void nr_stop_idletimer(struct sock *sk)
 {
-	del_timer(&nr_sk(sk)->idletimer);
+	sk_stop_timer(sk, &nr_sk(sk)->idletimer);
 }
 
 void nr_stop_heartbeat(struct sock *sk)
 {
-	del_timer(&sk->sk_timer);
+	sk_stop_timer(sk, &sk->sk_timer);
 }
 
 int nr_t1timer_running(struct sock *sk)
-- 
2.20.1


From c91337599de3f1bda0d43d9ca290bd6494a9c693 Mon Sep 17 00:00:00 2001
From: Bernard Pidoux <f6bvp@free.fr>
Date: Fri, 25 Jan 2019 11:46:40 +0100
Subject: [PATCH 10/33] net/rose: fix NULL ax25_cb kernel panic

[ Upstream commit b0cf029234f9b18e10703ba5147f0389c382bccc ]

When an internally generated frame is handled by rose_xmit(),
rose_route_frame() is called:

        if (!rose_route_frame(skb, NULL)) {
                dev_kfree_skb(skb);
                stats->tx_errors++;
                return NETDEV_TX_OK;
        }

We have the same code sequence in Net/Rom where an internally generated
frame is handled by nr_xmit() calling nr_route_frame(skb, NULL).
However, in this function NULL argument is tested while it is not in
rose_route_frame().
Then kernel panic occurs later on when calling ax25cmp() with a NULL
ax25_cb argument as reported many times and recently with syzbot.

We need to test if ax25 is NULL before using it.

Testing:
Built kernel with CONFIG_ROSE=y.

Signed-off-by: Bernard Pidoux <f6bvp@free.fr>
Acked-by: Dmitry Vyukov <dvyukov@google.com>
Reported-by: syzbot+1a2c456a1ea08fa5b5f7@syzkaller.appspotmail.com
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Bernard Pidoux <f6bvp@free.fr>
Cc: linux-hams@vger.kernel.org
Cc: netdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rose/rose_route.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c
index 77e9f85a2c92..f2ff21d7df08 100644
--- a/net/rose/rose_route.c
+++ b/net/rose/rose_route.c
@@ -850,6 +850,7 @@ void rose_link_device_down(struct net_device *dev)
 
 /*
  *	Route a frame to an appropriate AX.25 connection.
+ *	A NULL ax25_cb indicates an internally generated frame.
  */
 int rose_route_frame(struct sk_buff *skb, ax25_cb *ax25)
 {
@@ -867,6 +868,10 @@ int rose_route_frame(struct sk_buff *skb, ax25_cb *ax25)
 
 	if (skb->len < ROSE_MIN_LEN)
 		return res;
+
+	if (!ax25)
+		return rose_loopback_queue(skb, NULL);
+
 	frametype = skb->data[2];
 	lci = ((skb->data[0] << 8) & 0xF00) + ((skb->data[1] << 0) & 0x0FF);
 	if (frametype == ROSE_CALL_REQUEST &&
-- 
2.20.1


From 4fa0e8b89c469dbb548c606c99cd5ec8121ea215 Mon Sep 17 00:00:00 2001
From: Josh Elsasser <jelsasser@appneta.com>
Date: Sat, 26 Jan 2019 14:38:33 -0800
Subject: [PATCH 11/33] net: set default network namespace in
 init_dummy_netdev()

[ Upstream commit 35edfdc77f683c8fd27d7732af06cf6489af60a5 ]

Assign a default net namespace to netdevs created by init_dummy_netdev().
Fixes a NULL pointer dereference caused by busy-polling a socket bound to
an iwlwifi wireless device, which bumps the per-net BUSYPOLLRXPACKETS stat
if napi_poll() received packets:

  BUG: unable to handle kernel NULL pointer dereference at 0000000000000190
  IP: napi_busy_loop+0xd6/0x200
  Call Trace:
    sock_poll+0x5e/0x80
    do_sys_poll+0x324/0x5a0
    SyS_poll+0x6c/0xf0
    do_syscall_64+0x6b/0x1f0
    entry_SYSCALL_64_after_hwframe+0x3d/0xa2

Fixes: 7db6b048da3b ("net: Commonize busy polling code to focus on napi_id instead of socket")
Signed-off-by: Josh Elsasser <jelsasser@appneta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/core/dev.c b/net/core/dev.c
index 722d50dbf8a4..43f8a4fd4968 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8624,6 +8624,9 @@ int init_dummy_netdev(struct net_device *dev)
 	set_bit(__LINK_STATE_PRESENT, &dev->state);
 	set_bit(__LINK_STATE_START, &dev->state);
 
+	/* napi_busy_loop stats accounting wants this */
+	dev_net_set(dev, &init_net);
+
 	/* Note : We dont allocate pcpu_refcnt for dummy devices,
 	 * because users of this 'device' dont need to change
 	 * its refcount.
-- 
2.20.1


From c92ba56caf8c1cb1f748cd8a58c7414f792fbcbe Mon Sep 17 00:00:00 2001
From: Simon Horman <horms+renesas@verge.net.au>
Date: Wed, 23 Jan 2019 12:14:52 +0100
Subject: [PATCH 12/33] ravb: expand rx descriptor data to accommodate hw
 checksum

[ Upstream commit 12da64300fbc76b875900445f4146c3dc617d43e ]

EtherAVB may provide a checksum of packet data appended to packet data. In
order to allow this checksum to be received by the host descriptor data
needs to be enlarged by 2 bytes to accommodate the checksum.

In the case of MTU-sized packets without a VLAN tag the
checksum were already accommodated by virtue of the space reserved for the
VLAN tag. However, a packet of MTU-size with a  VLAN tag consumed all
packet data space provided by a descriptor leaving no space for the
trailing checksum.

This was not detected by the driver which incorrectly used the last two
bytes of packet data as the checksum and truncate the packet by two bytes.
This resulted all such packets being dropped.

A work around is to disable RX checksum offload
 # ethtool -K eth0 rx off

This patch resolves this problem by increasing the size available for
packet data in RX descriptors by two bytes.

Tested on R-Car E3 (r8a77990) ES1.0 based Ebisu-4D board

v2
* Use sizeof(__sum16) directly rather than adding a driver-local
  #define for the size of the checksum provided by the hw (2 bytes).

Fixes: 4d86d3818627 ("ravb: RX checksum offload")
Signed-off-by: Simon Horman <horms+renesas@verge.net.au>
Reviewed-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/ravb_main.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index defed0d0c51d..e7f8ab6e4391 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -350,7 +350,7 @@ static int ravb_ring_init(struct net_device *ndev, int q)
 	int i;
 
 	priv->rx_buf_sz = (ndev->mtu <= 1492 ? PKT_BUF_SZ : ndev->mtu) +
-		ETH_HLEN + VLAN_HLEN;
+		ETH_HLEN + VLAN_HLEN + sizeof(__sum16);
 
 	/* Allocate RX and TX skb rings */
 	priv->rx_skb[q] = kcalloc(priv->num_rx_ring[q],
@@ -533,13 +533,15 @@ static void ravb_rx_csum(struct sk_buff *skb)
 {
 	u8 *hw_csum;
 
-	/* The hardware checksum is 2 bytes appended to packet data */
-	if (unlikely(skb->len < 2))
+	/* The hardware checksum is contained in sizeof(__sum16) (2) bytes
+	 * appended to packet data
+	 */
+	if (unlikely(skb->len < sizeof(__sum16)))
 		return;
-	hw_csum = skb_tail_pointer(skb) - 2;
+	hw_csum = skb_tail_pointer(skb) - sizeof(__sum16);
 	skb->csum = csum_unfold((__force __sum16)get_unaligned_le16(hw_csum));
 	skb->ip_summed = CHECKSUM_COMPLETE;
-	skb_trim(skb, skb->len - 2);
+	skb_trim(skb, skb->len - sizeof(__sum16));
 }
 
 /* Packet receive function for Ethernet AVB */
-- 
2.20.1


From 3c5cbfa155855f25d7cf002e7cc46015f09f012d Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 22 Jan 2019 02:39:34 +0800
Subject: [PATCH 13/33] sctp: improve the events for sctp stream reset

[ Upstream commit 2e6dc4d95110becfe0ff4c3d4749c33ea166e9e7 ]

This patch is to improve sctp stream reset events in 4 places:

  1. In sctp_process_strreset_outreq(), the flag should always be set with
     SCTP_STREAM_RESET_INCOMING_SSN instead of OUTGOING, as receiver's in
     stream is reset here.
  2. In sctp_process_strreset_outreq(), move up SCTP_STRRESET_ERR_WRONG_SSN
     check, as the reset has to succeed after reconf_timer stops for the
     in stream reset request retransmission.
  3. In sctp_process_strreset_inreq(), no event should be sent, as no in
     or out stream is reset here.
  4. In sctp_process_strreset_resp(), SCTP_STREAM_RESET_INCOMING_SSN or
     OUTGOING event should always be sent for stream reset requests, no
     matter it fails or succeeds to process the request.

Fixes: 810544764536 ("sctp: implement receiver-side procedures for the Outgoing SSN Reset Request Parameter")
Fixes: 16e1a91965b0 ("sctp: implement receiver-side procedures for the Incoming SSN Reset Request Parameter")
Fixes: 11ae76e67a17 ("sctp: implement receiver-side procedures for the Reconf Response Parameter")
Reported-by: Ying Xu <yinxu@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/stream.c | 39 +++++++++++++++++----------------------
 1 file changed, 17 insertions(+), 22 deletions(-)

diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index 3892e7630f3a..6c188b06e5e1 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -585,9 +585,9 @@ struct sctp_chunk *sctp_process_strreset_outreq(
 	struct sctp_strreset_outreq *outreq = param.v;
 	struct sctp_stream *stream = &asoc->stream;
 	__u32 result = SCTP_STRRESET_DENIED;
-	__u16 i, nums, flags = 0;
 	__be16 *str_p = NULL;
 	__u32 request_seq;
+	__u16 i, nums;
 
 	request_seq = ntohl(outreq->request_seq);
 
@@ -615,6 +615,15 @@ struct sctp_chunk *sctp_process_strreset_outreq(
 	if (!(asoc->strreset_enable & SCTP_ENABLE_RESET_STREAM_REQ))
 		goto out;
 
+	nums = (ntohs(param.p->length) - sizeof(*outreq)) / sizeof(__u16);
+	str_p = outreq->list_of_streams;
+	for (i = 0; i < nums; i++) {
+		if (ntohs(str_p[i]) >= stream->incnt) {
+			result = SCTP_STRRESET_ERR_WRONG_SSN;
+			goto out;
+		}
+	}
+
 	if (asoc->strreset_chunk) {
 		if (!sctp_chunk_lookup_strreset_param(
 				asoc, outreq->response_seq,
@@ -637,32 +646,19 @@ struct sctp_chunk *sctp_process_strreset_outreq(
 			sctp_chunk_put(asoc->strreset_chunk);
 			asoc->strreset_chunk = NULL;
 		}
-
-		flags = SCTP_STREAM_RESET_INCOMING_SSN;
 	}
 
-	nums = (ntohs(param.p->length) - sizeof(*outreq)) / sizeof(__u16);
-	if (nums) {
-		str_p = outreq->list_of_streams;
-		for (i = 0; i < nums; i++) {
-			if (ntohs(str_p[i]) >= stream->incnt) {
-				result = SCTP_STRRESET_ERR_WRONG_SSN;
-				goto out;
-			}
-		}
-
+	if (nums)
 		for (i = 0; i < nums; i++)
 			SCTP_SI(stream, ntohs(str_p[i]))->mid = 0;
-	} else {
+	else
 		for (i = 0; i < stream->incnt; i++)
 			SCTP_SI(stream, i)->mid = 0;
-	}
 
 	result = SCTP_STRRESET_PERFORMED;
 
 	*evp = sctp_ulpevent_make_stream_reset_event(asoc,
-		flags | SCTP_STREAM_RESET_OUTGOING_SSN, nums, str_p,
-		GFP_ATOMIC);
+		SCTP_STREAM_RESET_INCOMING_SSN, nums, str_p, GFP_ATOMIC);
 
 out:
 	sctp_update_strreset_result(asoc, result);
@@ -738,9 +734,6 @@ struct sctp_chunk *sctp_process_strreset_inreq(
 
 	result = SCTP_STRRESET_PERFORMED;
 
-	*evp = sctp_ulpevent_make_stream_reset_event(asoc,
-		SCTP_STREAM_RESET_INCOMING_SSN, nums, str_p, GFP_ATOMIC);
-
 out:
 	sctp_update_strreset_result(asoc, result);
 err:
@@ -1036,10 +1029,10 @@ struct sctp_chunk *sctp_process_strreset_resp(
 					sout->mid_uo = 0;
 				}
 			}
-
-			flags = SCTP_STREAM_RESET_OUTGOING_SSN;
 		}
 
+		flags |= SCTP_STREAM_RESET_OUTGOING_SSN;
+
 		for (i = 0; i < stream->outcnt; i++)
 			SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN;
 
@@ -1058,6 +1051,8 @@ struct sctp_chunk *sctp_process_strreset_resp(
 		nums = (ntohs(inreq->param_hdr.length) - sizeof(*inreq)) /
 		       sizeof(__u16);
 
+		flags |= SCTP_STREAM_RESET_INCOMING_SSN;
+
 		*evp = sctp_ulpevent_make_stream_reset_event(asoc, flags,
 			nums, str_p, GFP_ATOMIC);
 	} else if (req->type == SCTP_PARAM_RESET_TSN_REQUEST) {
-- 
2.20.1


From 0c35f9575ccada25fb186ee4aa266a805036aa4f Mon Sep 17 00:00:00 2001
From: George Amanakis <gamanakis@gmail.com>
Date: Tue, 29 Jan 2019 22:50:13 -0500
Subject: [PATCH 14/33] tun: move the call to tun_set_real_num_queues

[ Upstream commit 3a03cb8456cc1d61c467a5375e0a10e5207b948c ]

Call tun_set_real_num_queues() after the increment of tun->numqueues
since the former depends on it. Otherwise, the number of queues is not
correctly accounted for, which results to warnings similar to:
"vnet0 selects TX queue 11, but real number of TX queues is 11".

Fixes: 0b7959b62573 ("tun: publish tfile after it's fully initialized")
Reported-and-tested-by: George Amanakis <gamanakis@gmail.com>
Signed-off-by: George Amanakis <gamanakis@gmail.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 6658658246d2..1e6f0da1fa8e 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -862,8 +862,6 @@ static int tun_attach(struct tun_struct *tun, struct file *file,
 	if (rtnl_dereference(tun->xdp_prog))
 		sock_set_flag(&tfile->sk, SOCK_XDP);
 
-	tun_set_real_num_queues(tun);
-
 	/* device is allowed to go away first, so no need to hold extra
 	 * refcnt.
 	 */
@@ -875,6 +873,7 @@ static int tun_attach(struct tun_struct *tun, struct file *file,
 	rcu_assign_pointer(tfile->tun, tun);
 	rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile);
 	tun->numqueues++;
+	tun_set_real_num_queues(tun);
 out:
 	return err;
 }
-- 
2.20.1


From 7a9413d54f0b5c1546475f9c441327b19ce01ec4 Mon Sep 17 00:00:00 2001
From: Mathias Thore <mathias.thore@infinera.com>
Date: Mon, 28 Jan 2019 10:07:47 +0100
Subject: [PATCH 15/33] ucc_geth: Reset BQL queue when stopping device

[ Upstream commit e15aa3b2b1388c399c1a2ce08550d2cc4f7e3e14 ]

After a timeout event caused by for example a broadcast storm, when
the MAC and PHY are reset, the BQL TX queue needs to be reset as
well. Otherwise, the device will exhibit severe performance issues
even after the storm has ended.

Co-authored-by: David Gounaris <david.gounaris@infinera.com>
Signed-off-by: Mathias Thore <mathias.thore@infinera.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/ucc_geth.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c
index 32e02700feaa..91d7965b3dab 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -1883,6 +1883,8 @@ static void ucc_geth_free_tx(struct ucc_geth_private *ugeth)
 	u16 i, j;
 	u8 __iomem *bd;
 
+	netdev_reset_queue(ugeth->ndev);
+
 	ug_info = ugeth->ug_info;
 	uf_info = &ug_info->uf_info;
 
-- 
2.20.1


From 8d81c2d53fbc5396bb5f77edcd3cee5751671457 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Mon, 28 Jan 2019 15:05:05 +0800
Subject: [PATCH 16/33] vhost: fix OOB in get_rx_bufs()

[ Upstream commit b46a0bf78ad7b150ef5910da83859f7f5a514ffd ]

After batched used ring updating was introduced in commit e2b3b35eb989
("vhost_net: batch used ring update in rx"). We tend to batch heads in
vq->heads for more than one packet. But the quota passed to
get_rx_bufs() was not correctly limited, which can result a OOB write
in vq->heads.

        headcount = get_rx_bufs(vq, vq->heads + nvq->done_idx,
                    vhost_len, &in, vq_log, &log,
                    likely(mergeable) ? UIO_MAXIOV : 1);

UIO_MAXIOV was still used which is wrong since we could have batched
used in vq->heads, this will cause OOB if the next buffer needs more
than 960 (1024 (UIO_MAXIOV) - 64 (VHOST_NET_BATCH)) heads after we've
batched 64 (VHOST_NET_BATCH) heads:
Acked-by: Stefan Hajnoczi <stefanha@redhat.com>

=============================================================================
BUG kmalloc-8k (Tainted: G    B            ): Redzone overwritten
-----------------------------------------------------------------------------

INFO: 0x00000000fd93b7a2-0x00000000f0713384. First byte 0xa9 instead of 0xcc
INFO: Allocated in alloc_pd+0x22/0x60 age=3933677 cpu=2 pid=2674
    kmem_cache_alloc_trace+0xbb/0x140
    alloc_pd+0x22/0x60
    gen8_ppgtt_create+0x11d/0x5f0
    i915_ppgtt_create+0x16/0x80
    i915_gem_create_context+0x248/0x390
    i915_gem_context_create_ioctl+0x4b/0xe0
    drm_ioctl_kernel+0xa5/0xf0
    drm_ioctl+0x2ed/0x3a0
    do_vfs_ioctl+0x9f/0x620
    ksys_ioctl+0x6b/0x80
    __x64_sys_ioctl+0x11/0x20
    do_syscall_64+0x43/0xf0
    entry_SYSCALL_64_after_hwframe+0x44/0xa9
INFO: Slab 0x00000000d13e87af objects=3 used=3 fp=0x          (null) flags=0x200000000010201
INFO: Object 0x0000000003278802 @offset=17064 fp=0x00000000e2e6652b

Fixing this by allocating UIO_MAXIOV + VHOST_NET_BATCH iovs for
vhost-net. This is done through set the limitation through
vhost_dev_init(), then set_owner can allocate the number of iov in a
per device manner.

This fixes CVE-2018-16880.

Fixes: e2b3b35eb989 ("vhost_net: batch used ring update in rx")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/net.c   | 3 ++-
 drivers/vhost/scsi.c  | 2 +-
 drivers/vhost/vhost.c | 7 ++++---
 drivers/vhost/vhost.h | 4 +++-
 drivers/vhost/vsock.c | 2 +-
 5 files changed, 11 insertions(+), 7 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 784df2b49628..4954718b2754 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -1293,7 +1293,8 @@ static int vhost_net_open(struct inode *inode, struct file *f)
 		n->vqs[i].rx_ring = NULL;
 		vhost_net_buf_init(&n->vqs[i].rxq);
 	}
-	vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX);
+	vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX,
+		       UIO_MAXIOV + VHOST_NET_BATCH);
 
 	vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, EPOLLOUT, dev);
 	vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, EPOLLIN, dev);
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 50dffe83714c..73a4adeab096 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -1628,7 +1628,7 @@ static int vhost_scsi_open(struct inode *inode, struct file *f)
 		vqs[i] = &vs->vqs[i].vq;
 		vs->vqs[i].vq.handle_kick = vhost_scsi_handle_kick;
 	}
-	vhost_dev_init(&vs->dev, vqs, VHOST_SCSI_MAX_VQ);
+	vhost_dev_init(&vs->dev, vqs, VHOST_SCSI_MAX_VQ, UIO_MAXIOV);
 
 	vhost_scsi_init_inflight(vs, NULL);
 
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index c66fc8308b5e..cf82e7266397 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -390,9 +390,9 @@ static long vhost_dev_alloc_iovecs(struct vhost_dev *dev)
 		vq->indirect = kmalloc_array(UIO_MAXIOV,
 					     sizeof(*vq->indirect),
 					     GFP_KERNEL);
-		vq->log = kmalloc_array(UIO_MAXIOV, sizeof(*vq->log),
+		vq->log = kmalloc_array(dev->iov_limit, sizeof(*vq->log),
 					GFP_KERNEL);
-		vq->heads = kmalloc_array(UIO_MAXIOV, sizeof(*vq->heads),
+		vq->heads = kmalloc_array(dev->iov_limit, sizeof(*vq->heads),
 					  GFP_KERNEL);
 		if (!vq->indirect || !vq->log || !vq->heads)
 			goto err_nomem;
@@ -414,7 +414,7 @@ static void vhost_dev_free_iovecs(struct vhost_dev *dev)
 }
 
 void vhost_dev_init(struct vhost_dev *dev,
-		    struct vhost_virtqueue **vqs, int nvqs)
+		    struct vhost_virtqueue **vqs, int nvqs, int iov_limit)
 {
 	struct vhost_virtqueue *vq;
 	int i;
@@ -427,6 +427,7 @@ void vhost_dev_init(struct vhost_dev *dev,
 	dev->iotlb = NULL;
 	dev->mm = NULL;
 	dev->worker = NULL;
+	dev->iov_limit = iov_limit;
 	init_llist_head(&dev->work_list);
 	init_waitqueue_head(&dev->wait);
 	INIT_LIST_HEAD(&dev->read_list);
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index 1b675dad5e05..9490e7ddb340 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -170,9 +170,11 @@ struct vhost_dev {
 	struct list_head read_list;
 	struct list_head pending_list;
 	wait_queue_head_t wait;
+	int iov_limit;
 };
 
-void vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue **vqs, int nvqs);
+void vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue **vqs,
+		    int nvqs, int iov_limit);
 long vhost_dev_set_owner(struct vhost_dev *dev);
 bool vhost_dev_has_owner(struct vhost_dev *dev);
 long vhost_dev_check_owner(struct vhost_dev *);
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 98ed5be132c6..fa93f6711d8d 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -531,7 +531,7 @@ static int vhost_vsock_dev_open(struct inode *inode, struct file *file)
 	vsock->vqs[VSOCK_VQ_TX].handle_kick = vhost_vsock_handle_tx_kick;
 	vsock->vqs[VSOCK_VQ_RX].handle_kick = vhost_vsock_handle_rx_kick;
 
-	vhost_dev_init(&vsock->dev, vqs, ARRAY_SIZE(vsock->vqs));
+	vhost_dev_init(&vsock->dev, vqs, ARRAY_SIZE(vsock->vqs), UIO_MAXIOV);
 
 	file->private_data = vsock;
 	spin_lock_init(&vsock->send_pkt_list_lock);
-- 
2.20.1


From 3512fe35b4ee0db32341879be3f4905be781bfe2 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Mon, 28 Jan 2019 22:23:49 +0100
Subject: [PATCH 17/33] net: ip6_gre: always reports o_key to userspace

[ Upstream commit c706863bc8902d0c2d1a5a27ac8e1ead5d06b79d ]

As Erspan_v4, Erspan_v6 protocol relies on o_key to configure
session id header field. However TUNNEL_KEY bit is cleared in
ip6erspan_tunnel_xmit since ERSPAN protocol does not set the key field
of the external GRE header and so the configured o_key is not reported
to userspace. The issue can be triggered with the following reproducer:

$ip link add ip6erspan1 type ip6erspan local 2000::1 remote 2000::2 \
    key 1 seq erspan_ver 1
$ip link set ip6erspan1 up
ip -d link sh ip6erspan1

ip6erspan1@NONE: <BROADCAST,MULTICAST> mtu 1422 qdisc noop state DOWN mode DEFAULT
    link/ether ba:ff:09:24:c3:0e brd ff:ff:ff:ff:ff:ff promiscuity 0 minmtu 68 maxmtu 1500
    ip6erspan remote 2000::2 local 2000::1 encaplimit 4 flowlabel 0x00000 ikey 0.0.0.1 iseq oseq

Fix the issue adding TUNNEL_KEY bit to the o_flags parameter in
ip6gre_fill_info

Fixes: 5a963eb61b7c ("ip6_gre: Add ERSPAN native tunnel support")
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index ad2d2d269ce4..94903061f324 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -2102,12 +2102,17 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev)
 {
 	struct ip6_tnl *t = netdev_priv(dev);
 	struct __ip6_tnl_parm *p = &t->parms;
+	__be16 o_flags = p->o_flags;
+
+	if ((p->erspan_ver == 1 || p->erspan_ver == 2) &&
+	    !p->collect_md)
+		o_flags |= TUNNEL_KEY;
 
 	if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) ||
 	    nla_put_be16(skb, IFLA_GRE_IFLAGS,
 			 gre_tnl_flags_to_gre_flags(p->i_flags)) ||
 	    nla_put_be16(skb, IFLA_GRE_OFLAGS,
-			 gre_tnl_flags_to_gre_flags(p->o_flags)) ||
+			 gre_tnl_flags_to_gre_flags(o_flags)) ||
 	    nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) ||
 	    nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) ||
 	    nla_put_in6_addr(skb, IFLA_GRE_LOCAL, &p->laddr) ||
-- 
2.20.1


From 7d3dfbd2c9ff028f0c67ce1e122fec150193aec8 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 22 Jan 2019 02:40:12 +0800
Subject: [PATCH 18/33] sctp: improve the events for sctp stream adding

[ Upstream commit 8220c870cb0f4eaa4e335c9645dbd9a1c461c1dd ]

This patch is to improve sctp stream adding events in 2 places:

  1. In sctp_process_strreset_addstrm_out(), move up SCTP_MAX_STREAM
     and in stream allocation failure checks, as the adding has to
     succeed after reconf_timer stops for the in stream adding
     request retransmission.

  3. In sctp_process_strreset_addstrm_in(), no event should be sent,
     as no in or out stream is added here.

Fixes: 50a41591f110 ("sctp: implement receiver-side procedures for the Add Outgoing Streams Request Parameter")
Fixes: c5c4ebb3ab87 ("sctp: implement receiver-side procedures for the Add Incoming Streams Request Parameter")
Reported-by: Ying Xu <yinxu@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/stream.c | 19 ++++++++-----------
 1 file changed, 8 insertions(+), 11 deletions(-)

diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index 6c188b06e5e1..80e0ae5534ec 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -866,6 +866,14 @@ struct sctp_chunk *sctp_process_strreset_addstrm_out(
 	if (!(asoc->strreset_enable & SCTP_ENABLE_CHANGE_ASSOC_REQ))
 		goto out;
 
+	in = ntohs(addstrm->number_of_streams);
+	incnt = stream->incnt + in;
+	if (!in || incnt > SCTP_MAX_STREAM)
+		goto out;
+
+	if (sctp_stream_alloc_in(stream, incnt, GFP_ATOMIC))
+		goto out;
+
 	if (asoc->strreset_chunk) {
 		if (!sctp_chunk_lookup_strreset_param(
 			asoc, 0, SCTP_PARAM_RESET_ADD_IN_STREAMS)) {
@@ -889,14 +897,6 @@ struct sctp_chunk *sctp_process_strreset_addstrm_out(
 		}
 	}
 
-	in = ntohs(addstrm->number_of_streams);
-	incnt = stream->incnt + in;
-	if (!in || incnt > SCTP_MAX_STREAM)
-		goto out;
-
-	if (sctp_stream_alloc_in(stream, incnt, GFP_ATOMIC))
-		goto out;
-
 	stream->incnt = incnt;
 
 	result = SCTP_STRRESET_PERFORMED;
@@ -966,9 +966,6 @@ struct sctp_chunk *sctp_process_strreset_addstrm_in(
 
 	result = SCTP_STRRESET_PERFORMED;
 
-	*evp = sctp_ulpevent_make_stream_change_event(asoc,
-		0, 0, ntohs(addstrm->number_of_streams), GFP_ATOMIC);
-
 out:
 	sctp_update_strreset_result(asoc, result);
 err:
-- 
2.20.1


From 0fd2052ce24b68e8e06cbd0306abd8b237990b3a Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Mon, 24 Dec 2018 09:48:42 +0200
Subject: [PATCH 19/33] net/mlx5e: Allow MAC invalidation while spoofchk is ON

[ Upstream commit 9d2cbdc5d334967c35b5f58c7bf3208e17325647 ]

Prior to this patch the driver prohibited spoof checking on invalid MAC.
Now the user can set this configuration if it wishes to.

This is required since libvirt might invalidate the VF Mac by setting it
to zero, while spoofcheck is ON.

Fixes: 1ab2068a4c66 ("net/mlx5: Implement vports admin state backup/restore")
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/eswitch.c  | 18 ++++++------------
 1 file changed, 6 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index d004957328f9..599e2930620b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1133,13 +1133,6 @@ static int esw_vport_ingress_config(struct mlx5_eswitch *esw,
 	int err = 0;
 	u8 *smac_v;
 
-	if (vport->info.spoofchk && !is_valid_ether_addr(vport->info.mac)) {
-		mlx5_core_warn(esw->dev,
-			       "vport[%d] configure ingress rules failed, illegal mac with spoofchk\n",
-			       vport->vport);
-		return -EPERM;
-	}
-
 	esw_vport_cleanup_ingress_rules(esw, vport);
 
 	if (!vport->info.vlan && !vport->info.qos && !vport->info.spoofchk) {
@@ -1812,13 +1805,10 @@ int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
 	mutex_lock(&esw->state_lock);
 	evport = &esw->vports[vport];
 
-	if (evport->info.spoofchk && !is_valid_ether_addr(mac)) {
+	if (evport->info.spoofchk && !is_valid_ether_addr(mac))
 		mlx5_core_warn(esw->dev,
-			       "MAC invalidation is not allowed when spoofchk is on, vport(%d)\n",
+			       "Set invalid MAC while spoofchk is on, vport(%d)\n",
 			       vport);
-		err = -EPERM;
-		goto unlock;
-	}
 
 	err = mlx5_modify_nic_vport_mac_address(esw->dev, vport, mac);
 	if (err) {
@@ -1964,6 +1954,10 @@ int mlx5_eswitch_set_vport_spoofchk(struct mlx5_eswitch *esw,
 	evport = &esw->vports[vport];
 	pschk = evport->info.spoofchk;
 	evport->info.spoofchk = spoofchk;
+	if (pschk && !is_valid_ether_addr(evport->info.mac))
+		mlx5_core_warn(esw->dev,
+			       "Spoofchk in set while MAC is invalid, vport(%d)\n",
+			       evport->vport);
 	if (evport->enabled && esw->mode == SRIOV_LEGACY)
 		err = esw_vport_ingress_config(esw, evport);
 	if (err)
-- 
2.20.1


From 48ce718466fb8beb5c9277ee84239beb9fd625c3 Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Sun, 27 Jan 2019 09:26:22 +0200
Subject: [PATCH 20/33] ip6mr: Fix notifiers call on mroute_clean_tables()

[ Upstream commit 146820cc240f4389cf33481c058d9493aef95e25 ]

When the MC route socket is closed, mroute_clean_tables() is called to
cleanup existing routes. Mistakenly notifiers call was put on the cleanup
of the unresolved MC route entries cache.
In a case where the MC socket closes before an unresolved route expires,
the notifier call leads to a crash, caused by the driver trying to
increment a non initialized refcount_t object [1] and then when handling
is done, to decrement it [2]. This was detected by a test recently added in
commit 6d4efada3b82 ("selftests: forwarding: Add multicast routing test").

Fix that by putting notifiers call on the resolved entries traversal,
instead of on the unresolved entries traversal.

[1]

[  245.748967] refcount_t: increment on 0; use-after-free.
[  245.754829] WARNING: CPU: 3 PID: 3223 at lib/refcount.c:153 refcount_inc_checked+0x2b/0x30
...
[  245.802357] Hardware name: Mellanox Technologies Ltd. MSN2740/SA001237, BIOS 5.6.5 06/07/2016
[  245.811873] RIP: 0010:refcount_inc_checked+0x2b/0x30
...
[  245.907487] Call Trace:
[  245.910231]  mlxsw_sp_router_fib_event.cold.181+0x42/0x47 [mlxsw_spectrum]
[  245.917913]  notifier_call_chain+0x45/0x7
[  245.922484]  atomic_notifier_call_chain+0x15/0x20
[  245.927729]  call_fib_notifiers+0x15/0x30
[  245.932205]  mroute_clean_tables+0x372/0x3f
[  245.936971]  ip6mr_sk_done+0xb1/0xc0
[  245.940960]  ip6_mroute_setsockopt+0x1da/0x5f0
...

[2]

[  246.128487] refcount_t: underflow; use-after-free.
[  246.133859] WARNING: CPU: 0 PID: 7 at lib/refcount.c:187 refcount_sub_and_test_checked+0x4c/0x60
[  246.183521] Hardware name: Mellanox Technologies Ltd. MSN2740/SA001237, BIOS 5.6.5 06/07/2016
...
[  246.193062] Workqueue: mlxsw_core_ordered mlxsw_sp_router_fibmr_event_work [mlxsw_spectrum]
[  246.202394] RIP: 0010:refcount_sub_and_test_checked+0x4c/0x60
...
[  246.298889] Call Trace:
[  246.301617]  refcount_dec_and_test_checked+0x11/0x20
[  246.307170]  mlxsw_sp_router_fibmr_event_work.cold.196+0x47/0x78 [mlxsw_spectrum]
[  246.315531]  process_one_work+0x1fa/0x3f0
[  246.320005]  worker_thread+0x2f/0x3e0
[  246.324083]  kthread+0x118/0x130
[  246.327683]  ? wq_update_unbound_numa+0x1b0/0x1b0
[  246.332926]  ? kthread_park+0x80/0x80
[  246.337013]  ret_from_fork+0x1f/0x30

Fixes: 088aa3eec2ce ("ip6mr: Support fib notifications")
Signed-off-by: Nir Dotan <nird@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6mr.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index eb3220812b56..edda3f9daab9 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1516,6 +1516,9 @@ static void mroute_clean_tables(struct mr_table *mrt, bool all)
 			continue;
 		rhltable_remove(&mrt->mfc_hash, &c->mnode, ip6mr_rht_params);
 		list_del_rcu(&c->list);
+		call_ip6mr_mfc_entry_notifiers(read_pnet(&mrt->net),
+					       FIB_EVENT_ENTRY_DEL,
+					       (struct mfc6_cache *)c, mrt->id);
 		mr6_netlink_event(mrt, (struct mfc6_cache *)c, RTM_DELROUTE);
 		mr_cache_put(c);
 	}
@@ -1524,10 +1527,6 @@ static void mroute_clean_tables(struct mr_table *mrt, bool all)
 		spin_lock_bh(&mfc_unres_lock);
 		list_for_each_entry_safe(c, tmp, &mrt->mfc_unres_queue, list) {
 			list_del(&c->list);
-			call_ip6mr_mfc_entry_notifiers(read_pnet(&mrt->net),
-						       FIB_EVENT_ENTRY_DEL,
-						       (struct mfc6_cache *)c,
-						       mrt->id);
 			mr6_netlink_event(mrt, (struct mfc6_cache *)c,
 					  RTM_DELROUTE);
 			ip6mr_destroy_unres(mrt, (struct mfc6_cache *)c);
-- 
2.20.1


From 384de804303da51da23d29cf7fdbda968791b84d Mon Sep 17 00:00:00 2001
From: Bodong Wang <bodong@mellanox.com>
Date: Sun, 13 Jan 2019 22:47:26 -0600
Subject: [PATCH 21/33] Revert "net/mlx5e: E-Switch, Initialize eswitch only if
 eswitch manager"

[ Upstream commit 4e046de0f50e04acd48eb373d6a9061ddf014e0c ]

This reverts commit 5f5991f36dce1e69dd8bd7495763eec2e28f08e7.

With the original commit, eswitch instance will not be initialized for
a function which is vport group manager but not eswitch manager such as
host PF on SmartNIC (BlueField) card. This will result in a kernel crash
when such a vport group manager is trying to access vports in its group.
E.g, PF vport manager (not eswitch manager) tries to configure the MAC
of its VF vport, a kernel trace will happen similar as bellow:

 BUG: unable to handle kernel NULL pointer dereference at 0000000000000000
 ...
 RIP: 0010:mlx5_eswitch_get_vport_config+0xc/0x180 [mlx5_core]
 ...

Fixes: 5f5991f36dce ("net/mlx5e: E-Switch, Initialize eswitch only if eswitch manager")
Signed-off-by: Bodong Wang <bodong@mellanox.com>
Reported-by: Yuval Avnery <yuvalav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 599e2930620b..3908ed554474 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1689,7 +1689,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 	int vport_num;
 	int err;
 
-	if (!MLX5_ESWITCH_MANAGER(dev))
+	if (!MLX5_VPORT_MANAGER(dev))
 		return 0;
 
 	esw_info(dev,
@@ -1758,7 +1758,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 
 void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw)
 {
-	if (!esw || !MLX5_ESWITCH_MANAGER(esw->dev))
+	if (!esw || !MLX5_VPORT_MANAGER(esw->dev))
 		return;
 
 	esw_info(esw->dev, "cleanup\n");
-- 
2.20.1


From 3c60546a4f39da005a73e77caf293232aa1fff38 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 22 Jan 2019 02:42:09 +0800
Subject: [PATCH 22/33] sctp: set chunk transport correctly when it's a new
 asoc

[ Upstream commit 4ff40b86262b73553ee47cc3784ce8ba0f220bd8 ]

In the paths:

  sctp_sf_do_unexpected_init() ->
    sctp_make_init_ack()
  sctp_sf_do_dupcook_a/b()() ->
    sctp_sf_do_5_1D_ce()

The new chunk 'retval' transport is set from the incoming chunk 'chunk'
transport. However, 'retval' transport belong to the new asoc, which
is a different one from 'chunk' transport's asoc.

It will cause that the 'retval' chunk gets set with a wrong transport.
Later when sending it and because of Commit b9fd683982c9 ("sctp: add
sctp_packet_singleton"), sctp_packet_singleton() will set some fields,
like vtag to 'retval' chunk from that wrong transport's asoc.

This patch is to fix it by setting 'retval' transport correctly which
belongs to the right asoc in sctp_make_init_ack() and
sctp_sf_do_5_1D_ce().

Fixes: b9fd683982c9 ("sctp: add sctp_packet_singleton")
Reported-by: Ying Xu <yinxu@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sm_make_chunk.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index f4ac6c592e13..d05c57664e36 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -495,7 +495,10 @@ struct sctp_chunk *sctp_make_init_ack(const struct sctp_association *asoc,
 	 *
 	 * [INIT ACK back to where the INIT came from.]
 	 */
-	retval->transport = chunk->transport;
+	if (chunk->transport)
+		retval->transport =
+			sctp_assoc_lookup_paddr(asoc,
+						&chunk->transport->ipaddr);
 
 	retval->subh.init_hdr =
 		sctp_addto_chunk(retval, sizeof(initack), &initack);
@@ -642,8 +645,10 @@ struct sctp_chunk *sctp_make_cookie_ack(const struct sctp_association *asoc,
 	 *
 	 * [COOKIE ACK back to where the COOKIE ECHO came from.]
 	 */
-	if (retval && chunk)
-		retval->transport = chunk->transport;
+	if (retval && chunk && chunk->transport)
+		retval->transport =
+			sctp_assoc_lookup_paddr(asoc,
+						&chunk->transport->ipaddr);
 
 	return retval;
 }
-- 
2.20.1


From 76d9058b49d5b1d49cd477770989ab680aaa51c6 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 22 Jan 2019 02:42:41 +0800
Subject: [PATCH 23/33] sctp: set flow sport from saddr only when it's 0

[ Upstream commit ecf938fe7d0088077ee1280419a2b3c5429b47c8 ]

Now sctp_transport_pmtu() passes transport->saddr into .get_dst() to set
flow sport from 'saddr'. However, transport->saddr is set only when
transport->dst exists in sctp_transport_route().

If sctp_transport_pmtu() is called without transport->saddr set, like
when transport->dst doesn't exists, the flow sport will be set to 0
from transport->saddr, which will cause a wrong route to be got.

Commit 6e91b578bf3f ("sctp: re-use sctp_transport_pmtu in
sctp_transport_route") made the issue be triggered more easily
since sctp_transport_pmtu() would be called in sctp_transport_route()
after that.

In gerneral, fl4->fl4_sport should always be set to
htons(asoc->base.bind_addr.port), unless transport->asoc doesn't exist
in sctp_v4/6_get_dst(), which is the case:

  sctp_ootb_pkt_new() ->
    sctp_transport_route()

For that, we can simply handle it by setting flow sport from saddr only
when it's 0 in sctp_v4/6_get_dst().

Fixes: 6e91b578bf3f ("sctp: re-use sctp_transport_pmtu in sctp_transport_route")
Reported-by: Ying Xu <yinxu@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ipv6.c     | 3 ++-
 net/sctp/protocol.c | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 0bae07e9c9e7..4fede55b9010 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -277,7 +277,8 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 
 	if (saddr) {
 		fl6->saddr = saddr->v6.sin6_addr;
-		fl6->fl6_sport = saddr->v6.sin6_port;
+		if (!fl6->fl6_sport)
+			fl6->fl6_sport = saddr->v6.sin6_port;
 
 		pr_debug("src=%pI6 - ", &fl6->saddr);
 	}
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 85af878f5668..8410ccc57c40 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -440,7 +440,8 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 	}
 	if (saddr) {
 		fl4->saddr = saddr->v4.sin_addr.s_addr;
-		fl4->fl4_sport = saddr->v4.sin_port;
+		if (!fl4->fl4_sport)
+			fl4->fl4_sport = saddr->v4.sin_port;
 	}
 
 	pr_debug("%s: dst:%pI4, src:%pI4 - ", __func__, &fl4->daddr,
-- 
2.20.1


From e4a772c647589365ad5476fa89388d6480d97f89 Mon Sep 17 00:00:00 2001
From: Dave Watson <davejwatson@fb.com>
Date: Sun, 27 Jan 2019 00:59:03 +0000
Subject: [PATCH 24/33] net: tls: Fix deadlock in free_resources tx

[ Upstream commit 1023121375c6b0b3dc00334983c762ba2b76cb19 ]

If there are outstanding async tx requests (when crypto returns EINPROGRESS),
there is a potential deadlock: the tx work acquires the lock, while we
cancel_delayed_work_sync() while holding the lock.  Drop the lock while waiting
for the work to complete.

Fixes: a42055e8d2c30 ("Add support for async encryption of records...")
Signed-off-by: Dave Watson <davejwatson@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 29b27858fff1..4be2320ec7ce 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1768,7 +1768,9 @@ void tls_sw_free_resources_tx(struct sock *sk)
 	if (atomic_read(&ctx->encrypt_pending))
 		crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
 
+	release_sock(sk);
 	cancel_delayed_work_sync(&ctx->tx_work.work);
+	lock_sock(sk);
 
 	/* Tx whatever records we can transmit and abandon the rest */
 	tls_tx_records(sk, -1);
-- 
2.20.1


From fb4f41892be41ee90c0f4b5ef78483d3f144be1b Mon Sep 17 00:00:00 2001
From: Dave Watson <davejwatson@fb.com>
Date: Sun, 27 Jan 2019 00:57:38 +0000
Subject: [PATCH 25/33] net: tls: Save iv in tls_rec for async crypto requests

[ Upstream commit 32eb67b93c9e3cd62cb423e30b090cdd4aa8d275 ]

aead_request_set_crypt takes an iv pointer, and we change the iv
soon after setting it.  Some async crypto algorithms don't save the iv,
so we need to save it in the tls_rec for async requests.

Found by hardcoding x64 aesni to use async crypto manager (to test the async
codepath), however I don't think this combination can happen in the wild.
Presumably other hardware offloads will need this fix, but there have been
no user reports.

Fixes: a42055e8d2c30 ("Add support for async encryption of records...")
Signed-off-by: Dave Watson <davejwatson@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h | 2 ++
 net/tls/tls_sw.c  | 4 +++-
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/include/net/tls.h b/include/net/tls.h
index 3cbcd12303fd..9f167e77d8ca 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -120,6 +120,8 @@ struct tls_rec {
 	struct scatterlist sg_aead_out[2];
 
 	char aad_space[TLS_AAD_SPACE_SIZE];
+	u8 iv_data[TLS_CIPHER_AES_GCM_128_IV_SIZE +
+		   TLS_CIPHER_AES_GCM_128_SALT_SIZE];
 	struct aead_request aead_req;
 	u8 aead_req_ctx[];
 };
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 4be2320ec7ce..419314ba94ec 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -439,6 +439,8 @@ static int tls_do_encryption(struct sock *sk,
 	struct scatterlist *sge = sk_msg_elem(msg_en, start);
 	int rc;
 
+	memcpy(rec->iv_data, tls_ctx->tx.iv, sizeof(rec->iv_data));
+
 	sge->offset += tls_ctx->tx.prepend_size;
 	sge->length -= tls_ctx->tx.prepend_size;
 
@@ -448,7 +450,7 @@ static int tls_do_encryption(struct sock *sk,
 	aead_request_set_ad(aead_req, TLS_AAD_SPACE_SIZE);
 	aead_request_set_crypt(aead_req, rec->sg_aead_in,
 			       rec->sg_aead_out,
-			       data_len, tls_ctx->tx.iv);
+			       data_len, rec->iv_data);
 
 	aead_request_set_callback(aead_req, CRYPTO_TFM_REQ_MAY_BACKLOG,
 				  tls_encrypt_done, sk);
-- 
2.20.1


From 6df4571bd3b14076f63d4a2b7d62b87d84bca51b Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Tue, 29 Jan 2019 09:45:53 +0900
Subject: [PATCH 26/33] virtio_net: Don't enable NAPI when interface is down

[ Upstream commit 8be4d9a492f88b96d4d3a06c6cbedbc40ca14c83 ]

Commit 4e09ff536284 ("virtio-net: disable NAPI only when enabled during
XDP set") tried to fix inappropriate NAPI enabling/disabling when
!netif_running(), but was not complete.

On error path virtio_net could enable NAPI even when !netif_running().
This can cause enabling NAPI twice on virtnet_open(), which would
trigger BUG_ON() in napi_enable().

Fixes: 4941d472bf95b ("virtio-net: do not reset during XDP set")
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index ea672145f6a6..5e7052749b8d 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2429,8 +2429,10 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 	return 0;
 
 err:
-	for (i = 0; i < vi->max_queue_pairs; i++)
-		virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
+	if (netif_running(dev)) {
+		for (i = 0; i < vi->max_queue_pairs; i++)
+			virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
+	}
 	if (prog)
 		bpf_prog_sub(prog, vi->max_queue_pairs - 1);
 	return err;
-- 
2.20.1


From 7fe919f4d984818733946bdf2fec7bd75bbc52c9 Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Tue, 29 Jan 2019 09:45:54 +0900
Subject: [PATCH 27/33] virtio_net: Don't call free_old_xmit_skbs for
 xdp_frames

[ Upstream commit 534da5e856334fb54cb0272a9fb3afec28ea3aed ]

When napi_tx is enabled, virtnet_poll_cleantx() called
free_old_xmit_skbs() even for xdp send queue.
This is bogus since the queue has xdp_frames, not sk_buffs, thus mangled
device tx bytes counters because skb->len is meaningless value, and even
triggered oops due to general protection fault on freeing them.

Since xdp send queues do not aquire locks, old xdp_frames should be
freed only in virtnet_xdp_xmit(), so just skip free_old_xmit_skbs() for
xdp send queues.

Similarly virtnet_poll_tx() called free_old_xmit_skbs(). This NAPI
handler is called even without calling start_xmit() because cb for tx is
by default enabled. Once the handler is called, it enabled the cb again,
and then the handler would be called again. We don't need this handler
for XDP, so don't enable cb as well as not calling free_old_xmit_skbs().

Also, we need to disable tx NAPI when disabling XDP, so
virtnet_poll_tx() can safely access curr_queue_pairs and
xdp_queue_pairs, which are not atomically updated while disabling XDP.

Fixes: b92f1e6751a6 ("virtio-net: transmit napi")
Fixes: 7b0411ef4aa6 ("virtio-net: clean tx descriptors from rx napi")
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 49 +++++++++++++++++++++++++++-------------
 1 file changed, 33 insertions(+), 16 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 5e7052749b8d..e9763b313274 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1357,6 +1357,16 @@ static void free_old_xmit_skbs(struct send_queue *sq)
 	u64_stats_update_end(&sq->stats.syncp);
 }
 
+static bool is_xdp_raw_buffer_queue(struct virtnet_info *vi, int q)
+{
+	if (q < (vi->curr_queue_pairs - vi->xdp_queue_pairs))
+		return false;
+	else if (q < vi->curr_queue_pairs)
+		return true;
+	else
+		return false;
+}
+
 static void virtnet_poll_cleantx(struct receive_queue *rq)
 {
 	struct virtnet_info *vi = rq->vq->vdev->priv;
@@ -1364,7 +1374,7 @@ static void virtnet_poll_cleantx(struct receive_queue *rq)
 	struct send_queue *sq = &vi->sq[index];
 	struct netdev_queue *txq = netdev_get_tx_queue(vi->dev, index);
 
-	if (!sq->napi.weight)
+	if (!sq->napi.weight || is_xdp_raw_buffer_queue(vi, index))
 		return;
 
 	if (__netif_tx_trylock(txq)) {
@@ -1441,8 +1451,16 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget)
 {
 	struct send_queue *sq = container_of(napi, struct send_queue, napi);
 	struct virtnet_info *vi = sq->vq->vdev->priv;
-	struct netdev_queue *txq = netdev_get_tx_queue(vi->dev, vq2txq(sq->vq));
+	unsigned int index = vq2txq(sq->vq);
+	struct netdev_queue *txq;
 
+	if (unlikely(is_xdp_raw_buffer_queue(vi, index))) {
+		/* We don't need to enable cb for XDP */
+		napi_complete_done(napi, 0);
+		return 0;
+	}
+
+	txq = netdev_get_tx_queue(vi->dev, index);
 	__netif_tx_lock(txq, raw_smp_processor_id());
 	free_old_xmit_skbs(sq);
 	__netif_tx_unlock(txq);
@@ -2401,9 +2419,12 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 	}
 
 	/* Make sure NAPI is not using any XDP TX queues for RX. */
-	if (netif_running(dev))
-		for (i = 0; i < vi->max_queue_pairs; i++)
+	if (netif_running(dev)) {
+		for (i = 0; i < vi->max_queue_pairs; i++) {
 			napi_disable(&vi->rq[i].napi);
+			virtnet_napi_tx_disable(&vi->sq[i].napi);
+		}
+	}
 
 	netif_set_real_num_rx_queues(dev, curr_qp + xdp_qp);
 	err = _virtnet_set_queues(vi, curr_qp + xdp_qp);
@@ -2422,16 +2443,22 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 		}
 		if (old_prog)
 			bpf_prog_put(old_prog);
-		if (netif_running(dev))
+		if (netif_running(dev)) {
 			virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
+			virtnet_napi_tx_enable(vi, vi->sq[i].vq,
+					       &vi->sq[i].napi);
+		}
 	}
 
 	return 0;
 
 err:
 	if (netif_running(dev)) {
-		for (i = 0; i < vi->max_queue_pairs; i++)
+		for (i = 0; i < vi->max_queue_pairs; i++) {
 			virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
+			virtnet_napi_tx_enable(vi, vi->sq[i].vq,
+					       &vi->sq[i].napi);
+		}
 	}
 	if (prog)
 		bpf_prog_sub(prog, vi->max_queue_pairs - 1);
@@ -2588,16 +2615,6 @@ static void free_receive_page_frags(struct virtnet_info *vi)
 			put_page(vi->rq[i].alloc_frag.page);
 }
 
-static bool is_xdp_raw_buffer_queue(struct virtnet_info *vi, int q)
-{
-	if (q < (vi->curr_queue_pairs - vi->xdp_queue_pairs))
-		return false;
-	else if (q < vi->curr_queue_pairs)
-		return true;
-	else
-		return false;
-}
-
 static void free_unused_bufs(struct virtnet_info *vi)
 {
 	void *buf;
-- 
2.20.1


From 2c4792d75bb316ddb39dc64fecbe2e9affb7cb53 Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Tue, 29 Jan 2019 09:45:55 +0900
Subject: [PATCH 28/33] virtio_net: Fix not restoring real_num_rx_queues

[ Upstream commit 188313c137c4f76afd0862f50dbc185b198b9e2a ]

When _virtnet_set_queues() failed we did not restore real_num_rx_queues.
Fix this by placing the change of real_num_rx_queues after
_virtnet_set_queues().
This order is also in line with virtnet_set_channels().

Fixes: 4941d472bf95 ("virtio-net: do not reset during XDP set")
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index e9763b313274..145645dccf3e 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2426,10 +2426,10 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 		}
 	}
 
-	netif_set_real_num_rx_queues(dev, curr_qp + xdp_qp);
 	err = _virtnet_set_queues(vi, curr_qp + xdp_qp);
 	if (err)
 		goto err;
+	netif_set_real_num_rx_queues(dev, curr_qp + xdp_qp);
 	vi->xdp_queue_pairs = xdp_qp;
 
 	for (i = 0; i < vi->max_queue_pairs; i++) {
-- 
2.20.1


From 7b61ca54e56894ee4e07c16494523dad6a5566f3 Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Tue, 29 Jan 2019 09:45:56 +0900
Subject: [PATCH 29/33] virtio_net: Fix out of bounds access of sq

[ Upstream commit 1667c08a9d31c7cdf09f4890816bfbf20b685495 ]

When XDP is disabled, curr_queue_pairs + smp_processor_id() can be
larger than max_queue_pairs.
There is no guarantee that we have enough XDP send queues dedicated for
each cpu when XDP is disabled, so do not count drops on sq in that case.

Fixes: 5b8f3c8d30a6 ("virtio_net: Add XDP related stats")
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 17 +++++++----------
 1 file changed, 7 insertions(+), 10 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 145645dccf3e..c0ab2d4789b9 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -490,20 +490,17 @@ static int virtnet_xdp_xmit(struct net_device *dev,
 	int ret, err;
 	int i;
 
-	sq = virtnet_xdp_sq(vi);
-
-	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) {
-		ret = -EINVAL;
-		drops = n;
-		goto out;
-	}
-
 	/* Only allow ndo_xdp_xmit if XDP is loaded on dev, as this
 	 * indicate XDP resources have been successfully allocated.
 	 */
 	xdp_prog = rcu_dereference(rq->xdp_prog);
-	if (!xdp_prog) {
-		ret = -ENXIO;
+	if (!xdp_prog)
+		return -ENXIO;
+
+	sq = virtnet_xdp_sq(vi);
+
+	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) {
+		ret = -EINVAL;
 		drops = n;
 		goto out;
 	}
-- 
2.20.1


From f02431e0de9f64b1f03764267c1d9fc44e6dcbf1 Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Tue, 29 Jan 2019 09:45:57 +0900
Subject: [PATCH 30/33] virtio_net: Don't process redirected XDP frames when
 XDP is disabled

[ Upstream commit 03aa6d34868c07b2b1b8b2db080602d7ec528173 ]

Commit 8dcc5b0ab0ec ("virtio_net: fix ndo_xdp_xmit crash towards dev not
ready for XDP") tried to avoid access to unexpected sq while XDP is
disabled, but was not complete.

There was a small window which causes out of bounds sq access in
virtnet_xdp_xmit() while disabling XDP.

An example case of
 - curr_queue_pairs = 6 (2 for SKB and 4 for XDP)
 - online_cpu_num = xdp_queue_paris = 4
when XDP is enabled:

CPU 0                         CPU 1
(Disabling XDP)               (Processing redirected XDP frames)

                              virtnet_xdp_xmit()
virtnet_xdp_set()
 _virtnet_set_queues()
  set curr_queue_pairs (2)
                               check if rq->xdp_prog is not NULL
                               virtnet_xdp_sq(vi)
                                qp = curr_queue_pairs -
                                     xdp_queue_pairs +
                                     smp_processor_id()
                                   = 2 - 4 + 1 = -1
                                sq = &vi->sq[qp] // out of bounds access
  set xdp_queue_pairs (0)
  rq->xdp_prog = NULL

Basically we should not change curr_queue_pairs and xdp_queue_pairs
while someone can read the values. Thus, when disabling XDP, assign NULL
to rq->xdp_prog first, and wait for RCU grace period, then change
xxx_queue_pairs.
Note that we need to keep the current order when enabling XDP though.

- v2: Make rcu_assign_pointer/synchronize_net conditional instead of
      _virtnet_set_queues.

Fixes: 186b3c998c50 ("virtio-net: support XDP_REDIRECT")
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 33 ++++++++++++++++++++++++++-------
 1 file changed, 26 insertions(+), 7 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index c0ab2d4789b9..f530932b938f 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2409,6 +2409,10 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 		return -ENOMEM;
 	}
 
+	old_prog = rtnl_dereference(vi->rq[0].xdp_prog);
+	if (!prog && !old_prog)
+		return 0;
+
 	if (prog) {
 		prog = bpf_prog_add(prog, vi->max_queue_pairs - 1);
 		if (IS_ERR(prog))
@@ -2423,21 +2427,30 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 		}
 	}
 
+	if (!prog) {
+		for (i = 0; i < vi->max_queue_pairs; i++) {
+			rcu_assign_pointer(vi->rq[i].xdp_prog, prog);
+			if (i == 0)
+				virtnet_restore_guest_offloads(vi);
+		}
+		synchronize_net();
+	}
+
 	err = _virtnet_set_queues(vi, curr_qp + xdp_qp);
 	if (err)
 		goto err;
 	netif_set_real_num_rx_queues(dev, curr_qp + xdp_qp);
 	vi->xdp_queue_pairs = xdp_qp;
 
-	for (i = 0; i < vi->max_queue_pairs; i++) {
-		old_prog = rtnl_dereference(vi->rq[i].xdp_prog);
-		rcu_assign_pointer(vi->rq[i].xdp_prog, prog);
-		if (i == 0) {
-			if (!old_prog)
+	if (prog) {
+		for (i = 0; i < vi->max_queue_pairs; i++) {
+			rcu_assign_pointer(vi->rq[i].xdp_prog, prog);
+			if (i == 0 && !old_prog)
 				virtnet_clear_guest_offloads(vi);
-			if (!prog)
-				virtnet_restore_guest_offloads(vi);
 		}
+	}
+
+	for (i = 0; i < vi->max_queue_pairs; i++) {
 		if (old_prog)
 			bpf_prog_put(old_prog);
 		if (netif_running(dev)) {
@@ -2450,6 +2463,12 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 	return 0;
 
 err:
+	if (!prog) {
+		virtnet_clear_guest_offloads(vi);
+		for (i = 0; i < vi->max_queue_pairs; i++)
+			rcu_assign_pointer(vi->rq[i].xdp_prog, old_prog);
+	}
+
 	if (netif_running(dev)) {
 		for (i = 0; i < vi->max_queue_pairs; i++) {
 			virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
-- 
2.20.1


From 7e20d37566edc74e88a48558cc7c4fdbfbdbe78b Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Tue, 29 Jan 2019 09:45:58 +0900
Subject: [PATCH 31/33] virtio_net: Use xdp_return_frame to free xdp_frames on
 destroying vqs

[ Upstream commit 07b344f494ddda9f061b396407c96df8c46c82b5 ]

put_page() can work as a fallback for freeing xdp_frames, but the
appropriate way is to use xdp_return_frame().

Fixes: cac320c850ef ("virtio_net: convert to use generic xdp_frame and xdp_return_frame API")
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index f530932b938f..20e350583337 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2642,7 +2642,7 @@ static void free_unused_bufs(struct virtnet_info *vi)
 			if (!is_xdp_raw_buffer_queue(vi, i))
 				dev_kfree_skb(buf);
 			else
-				put_page(virt_to_head_page(buf));
+				xdp_return_frame(buf);
 		}
 	}
 
-- 
2.20.1


From ce193f7aefcd308486bfa4e5d341a808fc2ee258 Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Tue, 29 Jan 2019 09:45:59 +0900
Subject: [PATCH 32/33] virtio_net: Differentiate sk_buff and xdp_frame on
 freeing

[ Upstream commit 5050471d35d1316ba32dfcbb409978337eb9e75e

  I had to fold commit df133f3f9625 ("virtio_net: bulk free tx skbs")
  into this to make it work.  ]

We do not reset or free up unused buffers when enabling/disabling XDP,
so it can happen that xdp_frames are freed after disabling XDP or
sk_buffs are freed after enabling XDP on xdp tx queues.
Thus we need to handle both forms (xdp_frames and sk_buffs) regardless
of XDP setting.
One way to trigger this problem is to disable XDP when napi_tx is
enabled. In that case, virtnet_xdp_set() calls virtnet_napi_enable()
which kicks NAPI. The NAPI handler will call virtnet_poll_cleantx()
which invokes free_old_xmit_skbs() for queues which have been used by
XDP.

Note that even with this change we need to keep skipping
free_old_xmit_skbs() from NAPI handlers when XDP is enabled, because XDP
tx queues do not aquire queue locks.

- v2: Use napi_consume_skb() instead of dev_consume_skb_any()

Fixes: 4941d472bf95 ("virtio-net: do not reset during XDP set")
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 64 +++++++++++++++++++++++++++++-----------
 1 file changed, 47 insertions(+), 17 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 20e350583337..da500c77c5b9 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -57,6 +57,8 @@ module_param(napi_tx, bool, 0644);
 #define VIRTIO_XDP_TX		BIT(0)
 #define VIRTIO_XDP_REDIR	BIT(1)
 
+#define VIRTIO_XDP_FLAG	BIT(0)
+
 /* RX packet size EWMA. The average packet size is used to determine the packet
  * buffer size when refilling RX rings. As the entire RX ring may be refilled
  * at once, the weight is chosen so that the EWMA will be insensitive to short-
@@ -251,6 +253,21 @@ struct padded_vnet_hdr {
 	char padding[4];
 };
 
+static bool is_xdp_frame(void *ptr)
+{
+	return (unsigned long)ptr & VIRTIO_XDP_FLAG;
+}
+
+static void *xdp_to_ptr(struct xdp_frame *ptr)
+{
+	return (void *)((unsigned long)ptr | VIRTIO_XDP_FLAG);
+}
+
+static struct xdp_frame *ptr_to_xdp(void *ptr)
+{
+	return (struct xdp_frame *)((unsigned long)ptr & ~VIRTIO_XDP_FLAG);
+}
+
 /* Converting between virtqueue no. and kernel tx/rx queue no.
  * 0:rx0 1:tx0 2:rx1 3:tx1 ... 2N:rxN 2N+1:txN 2N+2:cvq
  */
@@ -461,7 +478,8 @@ static int __virtnet_xdp_xmit_one(struct virtnet_info *vi,
 
 	sg_init_one(sq->sg, xdpf->data, xdpf->len);
 
-	err = virtqueue_add_outbuf(sq->vq, sq->sg, 1, xdpf, GFP_ATOMIC);
+	err = virtqueue_add_outbuf(sq->vq, sq->sg, 1, xdp_to_ptr(xdpf),
+				   GFP_ATOMIC);
 	if (unlikely(err))
 		return -ENOSPC; /* Caller handle free/refcnt */
 
@@ -481,13 +499,13 @@ static int virtnet_xdp_xmit(struct net_device *dev,
 {
 	struct virtnet_info *vi = netdev_priv(dev);
 	struct receive_queue *rq = vi->rq;
-	struct xdp_frame *xdpf_sent;
 	struct bpf_prog *xdp_prog;
 	struct send_queue *sq;
 	unsigned int len;
 	int drops = 0;
 	int kicks = 0;
 	int ret, err;
+	void *ptr;
 	int i;
 
 	/* Only allow ndo_xdp_xmit if XDP is loaded on dev, as this
@@ -506,8 +524,12 @@ static int virtnet_xdp_xmit(struct net_device *dev,
 	}
 
 	/* Free up any pending old buffers before queueing new ones. */
-	while ((xdpf_sent = virtqueue_get_buf(sq->vq, &len)) != NULL)
-		xdp_return_frame(xdpf_sent);
+	while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) {
+		if (likely(is_xdp_frame(ptr)))
+			xdp_return_frame(ptr_to_xdp(ptr));
+		else
+			napi_consume_skb(ptr, false);
+	}
 
 	for (i = 0; i < n; i++) {
 		struct xdp_frame *xdpf = frames[i];
@@ -1326,20 +1348,28 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
 	return stats.packets;
 }
 
-static void free_old_xmit_skbs(struct send_queue *sq)
+static void free_old_xmit_skbs(struct send_queue *sq, bool in_napi)
 {
-	struct sk_buff *skb;
 	unsigned int len;
 	unsigned int packets = 0;
 	unsigned int bytes = 0;
+	void *ptr;
 
-	while ((skb = virtqueue_get_buf(sq->vq, &len)) != NULL) {
-		pr_debug("Sent skb %p\n", skb);
+	while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) {
+		if (likely(!is_xdp_frame(ptr))) {
+			struct sk_buff *skb = ptr;
 
-		bytes += skb->len;
-		packets++;
+			pr_debug("Sent skb %p\n", skb);
 
-		dev_consume_skb_any(skb);
+			bytes += skb->len;
+			napi_consume_skb(skb, in_napi);
+		} else {
+			struct xdp_frame *frame = ptr_to_xdp(ptr);
+
+			bytes += frame->len;
+			xdp_return_frame(frame);
+		}
+		packets++;
 	}
 
 	/* Avoid overhead when no packets have been processed
@@ -1375,7 +1405,7 @@ static void virtnet_poll_cleantx(struct receive_queue *rq)
 		return;
 
 	if (__netif_tx_trylock(txq)) {
-		free_old_xmit_skbs(sq);
+		free_old_xmit_skbs(sq, true);
 		__netif_tx_unlock(txq);
 	}
 
@@ -1459,7 +1489,7 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget)
 
 	txq = netdev_get_tx_queue(vi->dev, index);
 	__netif_tx_lock(txq, raw_smp_processor_id());
-	free_old_xmit_skbs(sq);
+	free_old_xmit_skbs(sq, true);
 	__netif_tx_unlock(txq);
 
 	virtqueue_napi_complete(napi, sq->vq, 0);
@@ -1528,7 +1558,7 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 	bool use_napi = sq->napi.weight;
 
 	/* Free up any pending old buffers before queueing new ones. */
-	free_old_xmit_skbs(sq);
+	free_old_xmit_skbs(sq, false);
 
 	if (use_napi && kick)
 		virtqueue_enable_cb_delayed(sq->vq);
@@ -1571,7 +1601,7 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 		if (!use_napi &&
 		    unlikely(!virtqueue_enable_cb_delayed(sq->vq))) {
 			/* More just got used, free them then recheck. */
-			free_old_xmit_skbs(sq);
+			free_old_xmit_skbs(sq, false);
 			if (sq->vq->num_free >= 2+MAX_SKB_FRAGS) {
 				netif_start_subqueue(dev, qnum);
 				virtqueue_disable_cb(sq->vq);
@@ -2639,10 +2669,10 @@ static void free_unused_bufs(struct virtnet_info *vi)
 	for (i = 0; i < vi->max_queue_pairs; i++) {
 		struct virtqueue *vq = vi->sq[i].vq;
 		while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) {
-			if (!is_xdp_raw_buffer_queue(vi, i))
+			if (!is_xdp_frame(buf))
 				dev_kfree_skb(buf);
 			else
-				xdp_return_frame(buf);
+				xdp_return_frame(ptr_to_xdp(buf));
 		}
 	}
 
-- 
2.20.1


From d9ea10a7281b91ddcb6b43e19eb179cf1f393f7c Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 2 Jan 2019 18:57:09 -0800
Subject: [PATCH 33/33] ipv6: Consider sk_bound_dev_if when binding a socket to
 an address

[ Upstream commit c5ee066333ebc322a24a00a743ed941a0c68617e ]

IPv6 does not consider if the socket is bound to a device when binding
to an address. The result is that a socket can be bound to eth0 and then
bound to the address of eth1. If the device is a VRF, the result is that
a socket can only be bound to an address in the default VRF.

Resolve by considering the device if sk_bound_dev_if is set.

This problem exists from the beginning of git history.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/af_inet6.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 4dc935838184..d99753b5e39b 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -362,6 +362,9 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
 					err = -EINVAL;
 					goto out_unlock;
 				}
+			}
+
+			if (sk->sk_bound_dev_if) {
 				dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if);
 				if (!dev) {
 					err = -ENODEV;
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Fri, Feb 01, 2019 at 01:45:13PM -0800, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.19 and v4.20
> -stable, respectively.

All now applied, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 104 bytes --]


Please queue up the following networking bug fixes for v4.19 and
v4.20 -stable, respectively.

Thanks!

[-- Attachment #2: net_419.mbox --]
[-- Type: Application/Octet-Stream, Size: 51076 bytes --]

From 32267776d12324030b773939a3cd449afea9e6a8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 30 Jan 2019 11:39:41 -0800
Subject: [PATCH 01/18] dccp: fool proof ccid_hc_[rt]x_parse_options()

[ Upstream commit 9b1f19d810e92d6cdc68455fbc22d9f961a58ce1 ]

Similarly to commit 276bdb82dedb ("dccp: check ccid before dereferencing")
it is wise to test for a NULL ccid.

kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] PREEMPT SMP KASAN
CPU: 1 PID: 16 Comm: ksoftirqd/1 Not tainted 5.0.0-rc3+ #37
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:ccid_hc_tx_parse_options net/dccp/ccid.h:205 [inline]
RIP: 0010:dccp_parse_options+0x8d9/0x12b0 net/dccp/options.c:233
Code: c5 0f b6 75 b3 80 38 00 0f 85 d6 08 00 00 48 b9 00 00 00 00 00 fc ff df 48 8b 45 b8 4c 8b b8 f8 07 00 00 4c 89 f8 48 c1 e8 03 <80> 3c 08 00 0f 85 95 08 00 00 48 b8 00 00 00 00 00 fc ff df 4d 8b
kobject: 'loop5' (0000000080f78fc1): kobject_uevent_env
RSP: 0018:ffff8880a94df0b8 EFLAGS: 00010246
RAX: 0000000000000000 RBX: ffff8880858ac723 RCX: dffffc0000000000
RDX: 0000000000000100 RSI: 0000000000000007 RDI: 0000000000000001
RBP: ffff8880a94df140 R08: 0000000000000001 R09: ffff888061b83a80
R10: ffffed100c370752 R11: ffff888061b83a97 R12: 0000000000000026
R13: 0000000000000001 R14: 0000000000000000 R15: 0000000000000000
FS:  0000000000000000(0000) GS:ffff8880ae700000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f0defa33518 CR3: 000000008db5e000 CR4: 00000000001406e0
kobject: 'loop5' (0000000080f78fc1): fill_kobj_path: path = '/devices/virtual/block/loop5'
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 dccp_rcv_state_process+0x2b6/0x1af6 net/dccp/input.c:654
 dccp_v4_do_rcv+0x100/0x190 net/dccp/ipv4.c:688
 sk_backlog_rcv include/net/sock.h:936 [inline]
 __sk_receive_skb+0x3a9/0xea0 net/core/sock.c:473
 dccp_v4_rcv+0x10cb/0x1f80 net/dccp/ipv4.c:880
 ip_protocol_deliver_rcu+0xb6/0xa20 net/ipv4/ip_input.c:208
 ip_local_deliver_finish+0x23b/0x390 net/ipv4/ip_input.c:234
 NF_HOOK include/linux/netfilter.h:289 [inline]
 NF_HOOK include/linux/netfilter.h:283 [inline]
 ip_local_deliver+0x1f0/0x740 net/ipv4/ip_input.c:255
 dst_input include/net/dst.h:450 [inline]
 ip_rcv_finish+0x1f4/0x2f0 net/ipv4/ip_input.c:414
 NF_HOOK include/linux/netfilter.h:289 [inline]
 NF_HOOK include/linux/netfilter.h:283 [inline]
 ip_rcv+0xed/0x620 net/ipv4/ip_input.c:524
 __netif_receive_skb_one_core+0x160/0x210 net/core/dev.c:4973
 __netif_receive_skb+0x2c/0x1c0 net/core/dev.c:5083
 process_backlog+0x206/0x750 net/core/dev.c:5923
 napi_poll net/core/dev.c:6346 [inline]
 net_rx_action+0x76d/0x1930 net/core/dev.c:6412
 __do_softirq+0x30b/0xb11 kernel/softirq.c:292
 run_ksoftirqd kernel/softirq.c:654 [inline]
 run_ksoftirqd+0x8e/0x110 kernel/softirq.c:646
 smpboot_thread_fn+0x6ab/0xa10 kernel/smpboot.c:164
 kthread+0x357/0x430 kernel/kthread.c:246
 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:352
Modules linked in:
---[ end trace 58a0ba03bea2c376 ]---
RIP: 0010:ccid_hc_tx_parse_options net/dccp/ccid.h:205 [inline]
RIP: 0010:dccp_parse_options+0x8d9/0x12b0 net/dccp/options.c:233
Code: c5 0f b6 75 b3 80 38 00 0f 85 d6 08 00 00 48 b9 00 00 00 00 00 fc ff df 48 8b 45 b8 4c 8b b8 f8 07 00 00 4c 89 f8 48 c1 e8 03 <80> 3c 08 00 0f 85 95 08 00 00 48 b8 00 00 00 00 00 fc ff df 4d 8b
RSP: 0018:ffff8880a94df0b8 EFLAGS: 00010246
RAX: 0000000000000000 RBX: ffff8880858ac723 RCX: dffffc0000000000
RDX: 0000000000000100 RSI: 0000000000000007 RDI: 0000000000000001
RBP: ffff8880a94df140 R08: 0000000000000001 R09: ffff888061b83a80
R10: ffffed100c370752 R11: ffff888061b83a97 R12: 0000000000000026
R13: 0000000000000001 R14: 0000000000000000 R15: 0000000000000000
FS:  0000000000000000(0000) GS:ffff8880ae700000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f0defa33518 CR3: 0000000009871000 CR4: 00000000001406e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ccid.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/dccp/ccid.h b/net/dccp/ccid.h
index 6eb837a47b5c..baaaeb2b2c42 100644
--- a/net/dccp/ccid.h
+++ b/net/dccp/ccid.h
@@ -202,7 +202,7 @@ static inline void ccid_hc_tx_packet_recv(struct ccid *ccid, struct sock *sk,
 static inline int ccid_hc_tx_parse_options(struct ccid *ccid, struct sock *sk,
 					   u8 pkt, u8 opt, u8 *val, u8 len)
 {
-	if (ccid->ccid_ops->ccid_hc_tx_parse_options == NULL)
+	if (!ccid || !ccid->ccid_ops->ccid_hc_tx_parse_options)
 		return 0;
 	return ccid->ccid_ops->ccid_hc_tx_parse_options(sk, pkt, opt, val, len);
 }
@@ -214,7 +214,7 @@ static inline int ccid_hc_tx_parse_options(struct ccid *ccid, struct sock *sk,
 static inline int ccid_hc_rx_parse_options(struct ccid *ccid, struct sock *sk,
 					   u8 pkt, u8 opt, u8 *val, u8 len)
 {
-	if (ccid->ccid_ops->ccid_hc_rx_parse_options == NULL)
+	if (!ccid || !ccid->ccid_ops->ccid_hc_rx_parse_options)
 		return 0;
 	return ccid->ccid_ops->ccid_hc_rx_parse_options(sk, pkt, opt, val, len);
 }
-- 
2.20.1


From 46013f82e1fbe819deba7a0f0f8f9d6d0e9a746b Mon Sep 17 00:00:00 2001
From: Govindarajulu Varadarajan <gvaradar@cisco.com>
Date: Wed, 30 Jan 2019 06:59:00 -0800
Subject: [PATCH 02/18] enic: fix checksum validation for IPv6

[ Upstream commit 7596175e99b3d4bce28022193efd954c201a782a ]

In case of IPv6 pkts, ipv4_csum_ok is 0. Because of this, driver does
not set skb->ip_summed. So IPv6 rx checksum is not offloaded.

Signed-off-by: Govindarajulu Varadarajan <gvaradar@cisco.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cisco/enic/enic_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index 60641e202534..9a7f70db20c7 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -1434,7 +1434,8 @@ static void enic_rq_indicate_buf(struct vnic_rq *rq,
 		 * csum is correct or is zero.
 		 */
 		if ((netdev->features & NETIF_F_RXCSUM) && !csum_not_calc &&
-		    tcp_udp_csum_ok && ipv4_csum_ok && outer_csum_ok) {
+		    tcp_udp_csum_ok && outer_csum_ok &&
+		    (ipv4_csum_ok || ipv6)) {
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
 			skb->csum_level = encap;
 		}
-- 
2.20.1


From d1cb8014c8384142497ecefdfefef473bc169ea3 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Wed, 30 Jan 2019 10:42:30 -0800
Subject: [PATCH 03/18] lib/test_rhashtable: Make test_insert_dup() allocate
 its hash table dynamically

[ Upstream commit fc42a689c4c097859e5bd37b5ea11b60dc426df6 ]

The test_insert_dup() function from lib/test_rhashtable.c passes a
pointer to a stack object to rhltable_init(). Allocate the hash table
dynamically to avoid that the following is reported with object
debugging enabled:

ODEBUG: object (ptrval) is on stack (ptrval), but NOT annotated.
WARNING: CPU: 0 PID: 1 at lib/debugobjects.c:368 __debug_object_init+0x312/0x480
Modules linked in:
EIP: __debug_object_init+0x312/0x480
Call Trace:
 ? debug_object_init+0x1a/0x20
 ? __init_work+0x16/0x30
 ? rhashtable_init+0x1e1/0x460
 ? sched_clock_cpu+0x57/0xe0
 ? rhltable_init+0xb/0x20
 ? test_insert_dup+0x32/0x20f
 ? trace_hardirqs_on+0x38/0xf0
 ? ida_dump+0x10/0x10
 ? jhash+0x130/0x130
 ? my_hashfn+0x30/0x30
 ? test_rht_init+0x6aa/0xab4
 ? ida_dump+0x10/0x10
 ? test_rhltable+0xc5c/0xc5c
 ? do_one_initcall+0x67/0x28e
 ? trace_hardirqs_off+0x22/0xe0
 ? restore_all_kernel+0xf/0x70
 ? trace_hardirqs_on_thunk+0xc/0x10
 ? restore_all_kernel+0xf/0x70
 ? kernel_init_freeable+0x142/0x213
 ? rest_init+0x230/0x230
 ? kernel_init+0x10/0x110
 ? schedule_tail_wrapper+0x9/0xc
 ? ret_from_fork+0x19/0x24

Cc: Thomas Graf <tgraf@suug.ch>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: netdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 lib/test_rhashtable.c | 23 +++++++++++++++--------
 1 file changed, 15 insertions(+), 8 deletions(-)

diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c
index 82ac39ce5310..aecc0996628f 100644
--- a/lib/test_rhashtable.c
+++ b/lib/test_rhashtable.c
@@ -541,38 +541,45 @@ static unsigned int __init print_ht(struct rhltable *rhlt)
 static int __init test_insert_dup(struct test_obj_rhl *rhl_test_objects,
 				  int cnt, bool slow)
 {
-	struct rhltable rhlt;
+	struct rhltable *rhlt;
 	unsigned int i, ret;
 	const char *key;
 	int err = 0;
 
-	err = rhltable_init(&rhlt, &test_rht_params_dup);
-	if (WARN_ON(err))
+	rhlt = kmalloc(sizeof(*rhlt), GFP_KERNEL);
+	if (WARN_ON(!rhlt))
+		return -EINVAL;
+
+	err = rhltable_init(rhlt, &test_rht_params_dup);
+	if (WARN_ON(err)) {
+		kfree(rhlt);
 		return err;
+	}
 
 	for (i = 0; i < cnt; i++) {
 		rhl_test_objects[i].value.tid = i;
-		key = rht_obj(&rhlt.ht, &rhl_test_objects[i].list_node.rhead);
+		key = rht_obj(&rhlt->ht, &rhl_test_objects[i].list_node.rhead);
 		key += test_rht_params_dup.key_offset;
 
 		if (slow) {
-			err = PTR_ERR(rhashtable_insert_slow(&rhlt.ht, key,
+			err = PTR_ERR(rhashtable_insert_slow(&rhlt->ht, key,
 							     &rhl_test_objects[i].list_node.rhead));
 			if (err == -EAGAIN)
 				err = 0;
 		} else
-			err = rhltable_insert(&rhlt,
+			err = rhltable_insert(rhlt,
 					      &rhl_test_objects[i].list_node,
 					      test_rht_params_dup);
 		if (WARN(err, "error %d on element %d/%d (%s)\n", err, i, cnt, slow? "slow" : "fast"))
 			goto skip_print;
 	}
 
-	ret = print_ht(&rhlt);
+	ret = print_ht(rhlt);
 	WARN(ret != cnt, "missing rhltable elements (%d != %d, %s)\n", ret, cnt, slow? "slow" : "fast");
 
 skip_print:
-	rhltable_destroy(&rhlt);
+	rhltable_destroy(rhlt);
+	kfree(rhlt);
 
 	return 0;
 }
-- 
2.20.1


From e5aca5077ab75a52f160a7988adaaacef283e8eb Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Mon, 4 Feb 2019 11:20:29 +0100
Subject: [PATCH 04/18] net: dp83640: expire old TX-skb

[ Upstream commit 53bc8d2af08654659abfadfd3e98eb9922ff787c ]

During sendmsg() a cloned skb is saved via dp83640_txtstamp() in
->tx_queue. After the NIC sends this packet, the PHY will reply with a
timestamp for that TX packet. If the cable is pulled at the right time I
don't see that packet. It might gets flushed as part of queue shutdown
on NIC's side.
Once the link is up again then after the next sendmsg() we enqueue
another skb in dp83640_txtstamp() and have two on the list. Then the PHY
will send a reply and decode_txts() attaches it to the first skb on the
list.
No crash occurs since refcounting works but we are one packet behind.
linuxptp/ptp4l usually closes the socket and opens a new one (in such a
timeout case) so those "stale" replies never get there. However it does
not resume normal operation anymore.

Purge old skbs in decode_txts().

Fixes: cb646e2b02b2 ("ptp: Added a clock driver for the National Semiconductor PHYTER.")
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Kurt Kanzenbach <kurt@linutronix.de>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/dp83640.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index 29aa8d772b0c..59b3f1fbabd4 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -896,14 +896,14 @@ static void decode_txts(struct dp83640_private *dp83640,
 			struct phy_txts *phy_txts)
 {
 	struct skb_shared_hwtstamps shhwtstamps;
+	struct dp83640_skb_info *skb_info;
 	struct sk_buff *skb;
-	u64 ns;
 	u8 overflow;
+	u64 ns;
 
 	/* We must already have the skb that triggered this. */
-
+again:
 	skb = skb_dequeue(&dp83640->tx_queue);
-
 	if (!skb) {
 		pr_debug("have timestamp but tx_queue empty\n");
 		return;
@@ -918,6 +918,11 @@ static void decode_txts(struct dp83640_private *dp83640,
 		}
 		return;
 	}
+	skb_info = (struct dp83640_skb_info *)skb->cb;
+	if (time_after(jiffies, skb_info->tmo)) {
+		kfree_skb(skb);
+		goto again;
+	}
 
 	ns = phy2txts(phy_txts);
 	memset(&shhwtstamps, 0, sizeof(shhwtstamps));
@@ -1470,6 +1475,7 @@ static bool dp83640_rxtstamp(struct phy_device *phydev,
 static void dp83640_txtstamp(struct phy_device *phydev,
 			     struct sk_buff *skb, int type)
 {
+	struct dp83640_skb_info *skb_info = (struct dp83640_skb_info *)skb->cb;
 	struct dp83640_private *dp83640 = phydev->priv;
 
 	switch (dp83640->hwts_tx_en) {
@@ -1482,6 +1488,7 @@ static void dp83640_txtstamp(struct phy_device *phydev,
 		/* fall through */
 	case HWTSTAMP_TX_ON:
 		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+		skb_info->tmo = jiffies + SKB_TIMESTAMP_TIMEOUT;
 		skb_queue_tail(&dp83640->tx_queue, skb);
 		break;
 
-- 
2.20.1


From 7d822f3b32a17bd0b04681ef82ab0ed2f8f64b7b Mon Sep 17 00:00:00 2001
From: Marc Zyngier <marc.zyngier@arm.com>
Date: Sat, 2 Feb 2019 17:53:29 +0000
Subject: [PATCH 05/18] net: dsa: Fix lockdep false positive splat

[ Upstream commit c8101f7729daee251f4f6505f9d135ec08e1342f ]

Creating a macvtap on a DSA-backed interface results in the following
splat when lockdep is enabled:

[   19.638080] IPv6: ADDRCONF(NETDEV_CHANGE): lan0: link becomes ready
[   23.041198] device lan0 entered promiscuous mode
[   23.043445] device eth0 entered promiscuous mode
[   23.049255]
[   23.049557] ============================================
[   23.055021] WARNING: possible recursive locking detected
[   23.060490] 5.0.0-rc3-00013-g56c857a1b8d3 #118 Not tainted
[   23.066132] --------------------------------------------
[   23.071598] ip/2861 is trying to acquire lock:
[   23.076171] 00000000f61990cb (_xmit_ETHER){+...}, at: dev_set_rx_mode+0x1c/0x38
[   23.083693]
[   23.083693] but task is already holding lock:
[   23.089696] 00000000ecf0c3b4 (_xmit_ETHER){+...}, at: dev_uc_add+0x24/0x70
[   23.096774]
[   23.096774] other info that might help us debug this:
[   23.103494]  Possible unsafe locking scenario:
[   23.103494]
[   23.109584]        CPU0
[   23.112093]        ----
[   23.114601]   lock(_xmit_ETHER);
[   23.117917]   lock(_xmit_ETHER);
[   23.121233]
[   23.121233]  *** DEADLOCK ***
[   23.121233]
[   23.127325]  May be due to missing lock nesting notation
[   23.127325]
[   23.134315] 2 locks held by ip/2861:
[   23.137987]  #0: 000000003b766c72 (rtnl_mutex){+.+.}, at: rtnetlink_rcv_msg+0x338/0x4e0
[   23.146231]  #1: 00000000ecf0c3b4 (_xmit_ETHER){+...}, at: dev_uc_add+0x24/0x70
[   23.153757]
[   23.153757] stack backtrace:
[   23.158243] CPU: 0 PID: 2861 Comm: ip Not tainted 5.0.0-rc3-00013-g56c857a1b8d3 #118
[   23.166212] Hardware name: Globalscale Marvell ESPRESSOBin Board (DT)
[   23.172843] Call trace:
[   23.175358]  dump_backtrace+0x0/0x188
[   23.179116]  show_stack+0x14/0x20
[   23.182524]  dump_stack+0xb4/0xec
[   23.185928]  __lock_acquire+0x123c/0x1860
[   23.190048]  lock_acquire+0xc8/0x248
[   23.193724]  _raw_spin_lock_bh+0x40/0x58
[   23.197755]  dev_set_rx_mode+0x1c/0x38
[   23.201607]  dev_set_promiscuity+0x3c/0x50
[   23.205820]  dsa_slave_change_rx_flags+0x5c/0x70
[   23.210567]  __dev_set_promiscuity+0x148/0x1e0
[   23.215136]  __dev_set_rx_mode+0x74/0x98
[   23.219167]  dev_uc_add+0x54/0x70
[   23.222575]  macvlan_open+0x170/0x1d0
[   23.226336]  __dev_open+0xe0/0x160
[   23.229830]  __dev_change_flags+0x16c/0x1b8
[   23.234132]  dev_change_flags+0x20/0x60
[   23.238074]  do_setlink+0x2d0/0xc50
[   23.241658]  __rtnl_newlink+0x5f8/0x6e8
[   23.245601]  rtnl_newlink+0x50/0x78
[   23.249184]  rtnetlink_rcv_msg+0x360/0x4e0
[   23.253397]  netlink_rcv_skb+0xe8/0x130
[   23.257338]  rtnetlink_rcv+0x14/0x20
[   23.261012]  netlink_unicast+0x190/0x210
[   23.265043]  netlink_sendmsg+0x288/0x350
[   23.269075]  sock_sendmsg+0x18/0x30
[   23.272659]  ___sys_sendmsg+0x29c/0x2c8
[   23.276602]  __sys_sendmsg+0x60/0xb8
[   23.280276]  __arm64_sys_sendmsg+0x1c/0x28
[   23.284488]  el0_svc_common+0xd8/0x138
[   23.288340]  el0_svc_handler+0x24/0x80
[   23.292192]  el0_svc+0x8/0xc

This looks fairly harmless (no actual deadlock occurs), and is
fixed in a similar way to c6894dec8ea9 ("bridge: fix lockdep
addr_list_lock false positive splat") by putting the addr_list_lock
in its own lockdep class.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/master.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/dsa/master.c b/net/dsa/master.c
index c90ee3227dea..aae478d61101 100644
--- a/net/dsa/master.c
+++ b/net/dsa/master.c
@@ -158,6 +158,8 @@ static void dsa_master_ethtool_teardown(struct net_device *dev)
 	cpu_dp->orig_ethtool_ops = NULL;
 }
 
+static struct lock_class_key dsa_master_addr_list_lock_key;
+
 int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
 {
 	/* If we use a tagging format that doesn't have an ethertype
@@ -167,6 +169,8 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
 	wmb();
 
 	dev->dsa_ptr = cpu_dp;
+	lockdep_set_class(&dev->addr_list_lock,
+			  &dsa_master_addr_list_lock_key);
 
 	return dsa_master_ethtool_setup(dev);
 }
-- 
2.20.1


From befa357ba1406873964af5549ea3dcbf21645a93 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 6 Feb 2019 18:35:15 +0300
Subject: [PATCH 06/18] net: dsa: Fix NULL checking in dsa_slave_set_eee()

[ Upstream commit 00670cb8a73b10b10d3c40f045c15411715e4465 ]

This function can't succeed if dp->pl is NULL.  It will Oops inside the
call to return phylink_ethtool_get_eee(dp->pl, e);

Fixes: 1be52e97ed3e ("dsa: slave: eee: Allow ports to use phylink")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Vivien Didelot <vivien.didelot@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/slave.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 1c45c1d6d241..ae4de876197d 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -639,7 +639,7 @@ static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e)
 	int ret;
 
 	/* Port's PHY and MAC both need to be EEE capable */
-	if (!dev->phydev && !dp->pl)
+	if (!dev->phydev || !dp->pl)
 		return -ENODEV;
 
 	if (!ds->ops->set_mac_eee)
@@ -659,7 +659,7 @@ static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e)
 	int ret;
 
 	/* Port's PHY and MAC both need to be EEE capable */
-	if (!dev->phydev && !dp->pl)
+	if (!dev->phydev || !dp->pl)
 		return -ENODEV;
 
 	if (!ds->ops->get_mac_eee)
-- 
2.20.1


From 5d9e49742d1b7b3b358cbbb72c697c15a1f5b052 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Wed, 6 Feb 2019 00:02:58 +0100
Subject: [PATCH 07/18] net: dsa: mv88e6xxx: Fix counting of ATU violations

[ Upstream commit 75c05a74e745ae7d663b04d75777af80ada2233c ]

The ATU port vector contains a bit per port of the switch. The code
wrongly used it as a port number, and incremented a port counter. This
resulted in the wrong interfaces counter being incremented, and
potentially going off the end of the array of ports.

Fix this by using the source port ID for the violation, which really
is a port number.

Reported-by: Chris Healy <Chris.Healy@zii.aero>
Tested-by: Chris Healy <Chris.Healy@zii.aero>
Fixes: 65f60e4582bd ("net: dsa: mv88e6xxx: Keep ATU/VTU violation statistics")
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/global1_atu.c | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/global1_atu.c b/drivers/net/dsa/mv88e6xxx/global1_atu.c
index 5200e4bdce93..ea243840ee0f 100644
--- a/drivers/net/dsa/mv88e6xxx/global1_atu.c
+++ b/drivers/net/dsa/mv88e6xxx/global1_atu.c
@@ -314,6 +314,7 @@ static irqreturn_t mv88e6xxx_g1_atu_prob_irq_thread_fn(int irq, void *dev_id)
 {
 	struct mv88e6xxx_chip *chip = dev_id;
 	struct mv88e6xxx_atu_entry entry;
+	int spid;
 	int err;
 	u16 val;
 
@@ -336,6 +337,8 @@ static irqreturn_t mv88e6xxx_g1_atu_prob_irq_thread_fn(int irq, void *dev_id)
 	if (err)
 		goto out;
 
+	spid = entry.state;
+
 	if (val & MV88E6XXX_G1_ATU_OP_AGE_OUT_VIOLATION) {
 		dev_err_ratelimited(chip->dev,
 				    "ATU age out violation for %pM\n",
@@ -344,23 +347,23 @@ static irqreturn_t mv88e6xxx_g1_atu_prob_irq_thread_fn(int irq, void *dev_id)
 
 	if (val & MV88E6XXX_G1_ATU_OP_MEMBER_VIOLATION) {
 		dev_err_ratelimited(chip->dev,
-				    "ATU member violation for %pM portvec %x\n",
-				    entry.mac, entry.portvec);
-		chip->ports[entry.portvec].atu_member_violation++;
+				    "ATU member violation for %pM portvec %x spid %d\n",
+				    entry.mac, entry.portvec, spid);
+		chip->ports[spid].atu_member_violation++;
 	}
 
 	if (val & MV88E6XXX_G1_ATU_OP_MISS_VIOLATION) {
 		dev_err_ratelimited(chip->dev,
-				    "ATU miss violation for %pM portvec %x\n",
-				    entry.mac, entry.portvec);
-		chip->ports[entry.portvec].atu_miss_violation++;
+				    "ATU miss violation for %pM portvec %x spid %d\n",
+				    entry.mac, entry.portvec, spid);
+		chip->ports[spid].atu_miss_violation++;
 	}
 
 	if (val & MV88E6XXX_G1_ATU_OP_FULL_VIOLATION) {
 		dev_err_ratelimited(chip->dev,
-				    "ATU full violation for %pM portvec %x\n",
-				    entry.mac, entry.portvec);
-		chip->ports[entry.portvec].atu_full_violation++;
+				    "ATU full violation for %pM portvec %x spid %d\n",
+				    entry.mac, entry.portvec, spid);
+		chip->ports[spid].atu_full_violation++;
 	}
 	mutex_unlock(&chip->reg_lock);
 
-- 
2.20.1


From 9cb8baa8e0c7798b168d256f1056dd5578f2bb68 Mon Sep 17 00:00:00 2001
From: Rundong Ge <rdong.ge@gmail.com>
Date: Sat, 2 Feb 2019 14:29:35 +0000
Subject: [PATCH 08/18] net: dsa: slave: Don't propagate flag changes on down
 slave interfaces

[ Upstream commit 17ab4f61b8cd6f9c38e9d0b935d86d73b5d0d2b5 ]

The unbalance of master's promiscuity or allmulti will happen after ifdown
and ifup a slave interface which is in a bridge.

When we ifdown a slave interface , both the 'dsa_slave_close' and
'dsa_slave_change_rx_flags' will clear the master's flags. The flags
of master will be decrease twice.
In the other hand, if we ifup the slave interface again, since the
slave's flags were cleared the 'dsa_slave_open' won't set the master's
flag, only 'dsa_slave_change_rx_flags' that triggered by 'br_add_if'
will set the master's flags. The flags of master is increase once.

Only propagating flag changes when a slave interface is up makes
sure this does not happen. The 'vlan_dev_change_rx_flags' had the
same problem and was fixed, and changes here follows that fix.

Fixes: 91da11f870f0 ("net: Distributed Switch Architecture protocol support")
Signed-off-by: Rundong Ge <rdong.ge@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/slave.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index ae4de876197d..b39720d0995d 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -140,11 +140,14 @@ static int dsa_slave_close(struct net_device *dev)
 static void dsa_slave_change_rx_flags(struct net_device *dev, int change)
 {
 	struct net_device *master = dsa_slave_to_master(dev);
-
-	if (change & IFF_ALLMULTI)
-		dev_set_allmulti(master, dev->flags & IFF_ALLMULTI ? 1 : -1);
-	if (change & IFF_PROMISC)
-		dev_set_promiscuity(master, dev->flags & IFF_PROMISC ? 1 : -1);
+	if (dev->flags & IFF_UP) {
+		if (change & IFF_ALLMULTI)
+			dev_set_allmulti(master,
+					 dev->flags & IFF_ALLMULTI ? 1 : -1);
+		if (change & IFF_PROMISC)
+			dev_set_promiscuity(master,
+					    dev->flags & IFF_PROMISC ? 1 : -1);
+	}
 }
 
 static void dsa_slave_set_rx_mode(struct net_device *dev)
-- 
2.20.1


From 5f64544730daeabb4b5683ca388bc4ec8df70f94 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 3 Dec 2018 22:14:04 -0800
Subject: [PATCH 09/18] net/mlx5e: Force CHECKSUM_UNNECESSARY for short
 ethernet frames

[ Upstream commit e8c8b53ccaff568fef4c13a6ccaf08bf241aa01a ]

When an ethernet frame is padded to meet the minimum ethernet frame
size, the padding octets are not covered by the hardware checksum.
Fortunately the padding octets are usually zero's, which don't affect
checksum. However, we have a switch which pads non-zero octets, this
causes kernel hardware checksum fault repeatedly.

Prior to:
commit '88078d98d1bb ("net: pskb_trim_rcsum() and CHECKSUM_COMPLETE ...")'
skb checksum was forced to be CHECKSUM_NONE when padding is detected.
After it, we need to keep skb->csum updated, like what we do for RXFCS.
However, fixing up CHECKSUM_COMPLETE requires to verify and parse IP
headers, it is not worthy the effort as the packets are so small that
CHECKSUM_COMPLETE can't save anything.

Fixes: 88078d98d1bb ("net: pskb_trim_rcsum() and CHECKSUM_COMPLETE are friends"),
Cc: Eric Dumazet <edumazet@google.com>
Cc: Tariq Toukan <tariqt@mellanox.com>
Cc: Nikola Ciprich <nikola.ciprich@linuxbox.cz>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 8262f093fec4..d3f794d4fb96 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -707,6 +707,8 @@ static u32 mlx5e_get_fcs(const struct sk_buff *skb)
 	return __get_unaligned_cpu32(fcs_bytes);
 }
 
+#define short_frame(size) ((size) <= ETH_ZLEN + ETH_FCS_LEN)
+
 static inline void mlx5e_handle_csum(struct net_device *netdev,
 				     struct mlx5_cqe64 *cqe,
 				     struct mlx5e_rq *rq,
@@ -725,6 +727,17 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 		return;
 	}
 
+	/* CQE csum doesn't cover padding octets in short ethernet
+	 * frames. And the pad field is appended prior to calculating
+	 * and appending the FCS field.
+	 *
+	 * Detecting these padded frames requires to verify and parse
+	 * IP headers, so we simply force all those small frames to be
+	 * CHECKSUM_UNNECESSARY even if they are not padded.
+	 */
+	if (short_frame(skb->len))
+		goto csum_unnecessary;
+
 	if (likely(is_last_ethertype_ip(skb, &network_depth))) {
 		skb->ip_summed = CHECKSUM_COMPLETE;
 		skb->csum = csum_unfold((__force __sum16)cqe->check_sum);
@@ -744,6 +757,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 		return;
 	}
 
+csum_unnecessary:
 	if (likely((cqe->hds_ip_ext & CQE_L3_OK) &&
 		   (cqe->hds_ip_ext & CQE_L4_OK))) {
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
-- 
2.20.1


From b97255cac8efdf182431e86845752c7f3eab8fc3 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 1 Feb 2019 13:23:38 -0800
Subject: [PATCH 10/18] net: systemport: Fix WoL with password after deep sleep

[ Upstream commit 8dfb8d2cceb76b74ad5b58cc65c75994329b4d5e ]

Broadcom STB chips support a deep sleep mode where all register
contents are lost. Because we were stashing the MagicPacket password
into some of these registers a suspend into that deep sleep then a
resumption would not lead to being able to wake-up from MagicPacket with
password again.

Fix this by keeping a software copy of the password and program it
during suspend.

Fixes: 83e82f4c706b ("net: systemport: add Wake-on-LAN support")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bcmsysport.c | 25 +++++++++-------------
 drivers/net/ethernet/broadcom/bcmsysport.h |  2 ++
 2 files changed, 12 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 7b6859e4924e..fc16b2b0d0e9 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -519,7 +519,6 @@ static void bcm_sysport_get_wol(struct net_device *dev,
 				struct ethtool_wolinfo *wol)
 {
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
-	u32 reg;
 
 	wol->supported = WAKE_MAGIC | WAKE_MAGICSECURE | WAKE_FILTER;
 	wol->wolopts = priv->wolopts;
@@ -527,11 +526,7 @@ static void bcm_sysport_get_wol(struct net_device *dev,
 	if (!(priv->wolopts & WAKE_MAGICSECURE))
 		return;
 
-	/* Return the programmed SecureOn password */
-	reg = umac_readl(priv, UMAC_PSW_MS);
-	put_unaligned_be16(reg, &wol->sopass[0]);
-	reg = umac_readl(priv, UMAC_PSW_LS);
-	put_unaligned_be32(reg, &wol->sopass[2]);
+	memcpy(wol->sopass, priv->sopass, sizeof(priv->sopass));
 }
 
 static int bcm_sysport_set_wol(struct net_device *dev,
@@ -547,13 +542,8 @@ static int bcm_sysport_set_wol(struct net_device *dev,
 	if (wol->wolopts & ~supported)
 		return -EINVAL;
 
-	/* Program the SecureOn password */
-	if (wol->wolopts & WAKE_MAGICSECURE) {
-		umac_writel(priv, get_unaligned_be16(&wol->sopass[0]),
-			    UMAC_PSW_MS);
-		umac_writel(priv, get_unaligned_be32(&wol->sopass[2]),
-			    UMAC_PSW_LS);
-	}
+	if (wol->wolopts & WAKE_MAGICSECURE)
+		memcpy(priv->sopass, wol->sopass, sizeof(priv->sopass));
 
 	/* Flag the device and relevant IRQ as wakeup capable */
 	if (wol->wolopts) {
@@ -2588,13 +2578,18 @@ static int bcm_sysport_suspend_to_wol(struct bcm_sysport_priv *priv)
 	unsigned int index, i = 0;
 	u32 reg;
 
-	/* Password has already been programmed */
 	reg = umac_readl(priv, UMAC_MPD_CTRL);
 	if (priv->wolopts & (WAKE_MAGIC | WAKE_MAGICSECURE))
 		reg |= MPD_EN;
 	reg &= ~PSW_EN;
-	if (priv->wolopts & WAKE_MAGICSECURE)
+	if (priv->wolopts & WAKE_MAGICSECURE) {
+		/* Program the SecureOn password */
+		umac_writel(priv, get_unaligned_be16(&priv->sopass[0]),
+			    UMAC_PSW_MS);
+		umac_writel(priv, get_unaligned_be32(&priv->sopass[2]),
+			    UMAC_PSW_LS);
 		reg |= PSW_EN;
+	}
 	umac_writel(priv, reg, UMAC_MPD_CTRL);
 
 	if (priv->wolopts & WAKE_FILTER) {
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h
index 046c6c1d97fd..36e0adf5c9b8 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.h
+++ b/drivers/net/ethernet/broadcom/bcmsysport.h
@@ -12,6 +12,7 @@
 #define __BCM_SYSPORT_H
 
 #include <linux/bitmap.h>
+#include <linux/ethtool.h>
 #include <linux/if_vlan.h>
 #include <linux/net_dim.h>
 
@@ -776,6 +777,7 @@ struct bcm_sysport_priv {
 	unsigned int		crc_fwd:1;
 	u16			rev;
 	u32			wolopts;
+	u8			sopass[SOPASS_MAX];
 	unsigned int		wol_irq_disabled:1;
 
 	/* MIB related fields */
-- 
2.20.1


From 29039d3fcf901f12ffa1ace6f94c0b354fa5f374 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 31 Jan 2019 08:47:10 -0800
Subject: [PATCH 11/18] rds: fix refcount bug in rds_sock_addref

[ Upstream commit 6fa19f5637a6c22bc0999596bcc83bdcac8a4fa6 ]

syzbot was able to catch a bug in rds [1]

The issue here is that the socket might be found in a hash table
but that its refcount has already be set to 0 by another cpu.

We need to use refcount_inc_not_zero() to be safe here.

[1]

refcount_t: increment on 0; use-after-free.
WARNING: CPU: 1 PID: 23129 at lib/refcount.c:153 refcount_inc_checked lib/refcount.c:153 [inline]
WARNING: CPU: 1 PID: 23129 at lib/refcount.c:153 refcount_inc_checked+0x61/0x70 lib/refcount.c:151
Kernel panic - not syncing: panic_on_warn set ...
CPU: 1 PID: 23129 Comm: syz-executor3 Not tainted 5.0.0-rc4+ #53
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1db/0x2d0 lib/dump_stack.c:113
 panic+0x2cb/0x65c kernel/panic.c:214
 __warn.cold+0x20/0x48 kernel/panic.c:571
 report_bug+0x263/0x2b0 lib/bug.c:186
 fixup_bug arch/x86/kernel/traps.c:178 [inline]
 fixup_bug arch/x86/kernel/traps.c:173 [inline]
 do_error_trap+0x11b/0x200 arch/x86/kernel/traps.c:271
 do_invalid_op+0x37/0x50 arch/x86/kernel/traps.c:290
 invalid_op+0x14/0x20 arch/x86/entry/entry_64.S:973
RIP: 0010:refcount_inc_checked lib/refcount.c:153 [inline]
RIP: 0010:refcount_inc_checked+0x61/0x70 lib/refcount.c:151
Code: 1d 51 63 c8 06 31 ff 89 de e8 eb 1b f2 fd 84 db 75 dd e8 a2 1a f2 fd 48 c7 c7 60 9f 81 88 c6 05 31 63 c8 06 01 e8 af 65 bb fd <0f> 0b eb c1 90 66 2e 0f 1f 84 00 00 00 00 00 55 48 89 e5 41 54 49
RSP: 0018:ffff8880a0cbf1e8 EFLAGS: 00010282
RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffffc90006113000
RDX: 000000000001047d RSI: ffffffff81685776 RDI: 0000000000000005
RBP: ffff8880a0cbf1f8 R08: ffff888097c9e100 R09: ffffed1015ce5021
R10: ffffed1015ce5020 R11: ffff8880ae728107 R12: ffff8880723c20c0
R13: ffff8880723c24b0 R14: dffffc0000000000 R15: ffffed1014197e64
 sock_hold include/net/sock.h:647 [inline]
 rds_sock_addref+0x19/0x20 net/rds/af_rds.c:675
 rds_find_bound+0x97c/0x1080 net/rds/bind.c:82
 rds_recv_incoming+0x3be/0x1430 net/rds/recv.c:362
 rds_loop_xmit+0xf3/0x2a0 net/rds/loop.c:96
 rds_send_xmit+0x1355/0x2a10 net/rds/send.c:355
 rds_sendmsg+0x323c/0x44e0 net/rds/send.c:1368
 sock_sendmsg_nosec net/socket.c:621 [inline]
 sock_sendmsg+0xdd/0x130 net/socket.c:631
 __sys_sendto+0x387/0x5f0 net/socket.c:1788
 __do_sys_sendto net/socket.c:1800 [inline]
 __se_sys_sendto net/socket.c:1796 [inline]
 __x64_sys_sendto+0xe1/0x1a0 net/socket.c:1796
 do_syscall_64+0x1a3/0x800 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x458089
Code: 6d b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 3b b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007fc266df8c78 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 0000000000000006 RCX: 0000000000458089
RDX: 0000000000000000 RSI: 00000000204b3fff RDI: 0000000000000005
RBP: 000000000073bf00 R08: 00000000202b4000 R09: 0000000000000010
R10: 0000000000000000 R11: 0000000000000246 R12: 00007fc266df96d4
R13: 00000000004c56e4 R14: 00000000004d94a8 R15: 00000000ffffffff

Fixes: cc4dfb7f70a3 ("rds: fix two RCU related problems")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Cc: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Cc: rds-devel@oss.oracle.com
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/bind.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/rds/bind.c b/net/rds/bind.c
index 762d2c6788a3..17c9d9f0c848 100644
--- a/net/rds/bind.c
+++ b/net/rds/bind.c
@@ -78,10 +78,10 @@ struct rds_sock *rds_find_bound(const struct in6_addr *addr, __be16 port,
 	__rds_create_bind_key(key, addr, port, scope_id);
 	rcu_read_lock();
 	rs = rhashtable_lookup(&bind_hash_table, key, ht_parms);
-	if (rs && !sock_flag(rds_rs_to_sk(rs), SOCK_DEAD))
-		rds_sock_addref(rs);
-	else
+	if (rs && (sock_flag(rds_rs_to_sk(rs), SOCK_DEAD) ||
+		   !refcount_inc_not_zero(&rds_rs_to_sk(rs)->sk_refcnt)))
 		rs = NULL;
+
 	rcu_read_unlock();
 
 	rdsdebug("returning rs %p for %pI6c:%u\n", rs, addr,
-- 
2.20.1


From c8ecf527491ab9ac0e01ca341df61fcdc1b3d385 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Thu, 31 Jan 2019 16:59:46 +0000
Subject: [PATCH 12/18] Revert "net: phy: marvell: avoid pause mode on
 SGMII-to-Copper for 88e151x"

[ Upstream commit c14f07c6211cc01d52ed92cce1fade5071b8d197 ]

This reverts commit 6623c0fba10ef45b64ca213ad5dec926f37fa9a0.

The original diagnosis was incorrect: it appears that the NIC had
PHY polling mode enabled, which meant that it overwrote the PHYs
advertisement register during negotiation.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Tested-by: Yonglong Liu <liuyonglong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/marvell.c | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index d71be15c8c69..73813c7afa49 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -868,8 +868,6 @@ static int m88e1510_config_init(struct phy_device *phydev)
 
 	/* SGMII-to-Copper mode initialization */
 	if (phydev->interface == PHY_INTERFACE_MODE_SGMII) {
-		u32 pause;
-
 		/* Select page 18 */
 		err = marvell_set_page(phydev, 18);
 		if (err < 0)
@@ -892,16 +890,6 @@ static int m88e1510_config_init(struct phy_device *phydev)
 		err = marvell_set_page(phydev, MII_MARVELL_COPPER_PAGE);
 		if (err < 0)
 			return err;
-
-		/* There appears to be a bug in the 88e1512 when used in
-		 * SGMII to copper mode, where the AN advertisement register
-		 * clears the pause bits each time a negotiation occurs.
-		 * This means we can never be truely sure what was advertised,
-		 * so disable Pause support.
-		 */
-		pause = SUPPORTED_Pause | SUPPORTED_Asym_Pause;
-		phydev->supported &= ~pause;
-		phydev->advertising &= ~pause;
 	}
 
 	return m88e1318_config_init(phydev);
-- 
2.20.1


From 360d725e1feb11fd2205bc7014f03065b09bf8fd Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 4 Feb 2019 08:36:06 -0800
Subject: [PATCH 13/18] rxrpc: bad unlock balance in rxrpc_recvmsg

[ Upstream commit 6dce3c20ac429e7a651d728e375853370c796e8d ]

When either "goto wait_interrupted;" or "goto wait_error;"
paths are taken, socket lock has already been released.

This patch fixes following syzbot splat :

WARNING: bad unlock balance detected!
5.0.0-rc4+ #59 Not tainted
-------------------------------------
syz-executor223/8256 is trying to release lock (sk_lock-AF_RXRPC) at:
[<ffffffff86651353>] rxrpc_recvmsg+0x6d3/0x3099 net/rxrpc/recvmsg.c:598
but there are no more locks to release!

other info that might help us debug this:
1 lock held by syz-executor223/8256:
 #0: 00000000fa9ed0f4 (slock-AF_RXRPC){+...}, at: spin_lock_bh include/linux/spinlock.h:334 [inline]
 #0: 00000000fa9ed0f4 (slock-AF_RXRPC){+...}, at: release_sock+0x20/0x1c0 net/core/sock.c:2798

stack backtrace:
CPU: 1 PID: 8256 Comm: syz-executor223 Not tainted 5.0.0-rc4+ #59
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 print_unlock_imbalance_bug kernel/locking/lockdep.c:3391 [inline]
 print_unlock_imbalance_bug.cold+0x114/0x123 kernel/locking/lockdep.c:3368
 __lock_release kernel/locking/lockdep.c:3601 [inline]
 lock_release+0x67e/0xa00 kernel/locking/lockdep.c:3860
 sock_release_ownership include/net/sock.h:1471 [inline]
 release_sock+0x183/0x1c0 net/core/sock.c:2808
 rxrpc_recvmsg+0x6d3/0x3099 net/rxrpc/recvmsg.c:598
 sock_recvmsg_nosec net/socket.c:794 [inline]
 sock_recvmsg net/socket.c:801 [inline]
 sock_recvmsg+0xd0/0x110 net/socket.c:797
 __sys_recvfrom+0x1ff/0x350 net/socket.c:1845
 __do_sys_recvfrom net/socket.c:1863 [inline]
 __se_sys_recvfrom net/socket.c:1859 [inline]
 __x64_sys_recvfrom+0xe1/0x1a0 net/socket.c:1859
 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x446379
Code: e8 2c b3 02 00 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 2b 09 fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007fe5da89fd98 EFLAGS: 00000246 ORIG_RAX: 000000000000002d
RAX: ffffffffffffffda RBX: 00000000006dbc28 RCX: 0000000000446379
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000003
RBP: 00000000006dbc20 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00000000006dbc2c
R13: 0000000000000000 R14: 0000000000000000 R15: 20c49ba5e353f7cf

Fixes: 248f219cb8bc ("rxrpc: Rewrite the data and ack handling code")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: David Howells <dhowells@redhat.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/recvmsg.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index 816b19a78809..0374b0623c8b 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -596,6 +596,7 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	}
 error_no_call:
 	release_sock(&rx->sk);
+error_trace:
 	trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, 0, 0, 0, ret);
 	return ret;
 
@@ -604,7 +605,7 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 wait_error:
 	finish_wait(sk_sleep(&rx->sk), &wait);
 	call = NULL;
-	goto error_no_call;
+	goto error_trace;
 }
 
 /**
-- 
2.20.1


From d0b9ad1245c089731738425319db909bba34eeeb Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 4 Feb 2019 03:27:58 +0800
Subject: [PATCH 14/18] sctp: check and update stream->out_curr when allocating
 stream_out

[ Upstream commit cfe4bd7a257f6d6f81d3458d8c9d9ec4957539e6 ]

Now when using stream reconfig to add out streams, stream->out
will get re-allocated, and all old streams' information will
be copied to the new ones and the old ones will be freed.

So without stream->out_curr updated, next time when trying to
send from stream->out_curr stream, a panic would be caused.

This patch is to check and update stream->out_curr when
allocating stream_out.

v1->v2:
  - define fa_index() to get elem index from stream->out_curr.
v2->v3:
  - repost with no change.

Fixes: 5bbbbe32a431 ("sctp: introduce stream scheduler foundations")
Reported-by: Ying Xu <yinxu@redhat.com>
Reported-by: syzbot+e33a3a138267ca119c7d@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/stream.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index 80e0ae5534ec..f24633114dfd 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -84,6 +84,19 @@ static void fa_zero(struct flex_array *fa, size_t index, size_t count)
 	}
 }
 
+static size_t fa_index(struct flex_array *fa, void *elem, size_t count)
+{
+	size_t index = 0;
+
+	while (count--) {
+		if (elem == flex_array_get(fa, index))
+			break;
+		index++;
+	}
+
+	return index;
+}
+
 /* Migrates chunks from stream queues to new stream queues if needed,
  * but not across associations. Also, removes those chunks to streams
  * higher than the new max.
@@ -147,6 +160,13 @@ static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt,
 
 	if (stream->out) {
 		fa_copy(out, stream->out, 0, min(outcnt, stream->outcnt));
+		if (stream->out_curr) {
+			size_t index = fa_index(stream->out, stream->out_curr,
+						stream->outcnt);
+
+			BUG_ON(index == stream->outcnt);
+			stream->out_curr = flex_array_get(out, index);
+		}
 		fa_free(stream->out);
 	}
 
-- 
2.20.1


From 56f0f3d3edecb67082355309a3f0bda807c99181 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Fri, 1 Feb 2019 15:15:22 +0100
Subject: [PATCH 15/18] sctp: walk the list of asoc safely

[ Upstream commit ba59fb0273076637f0add4311faa990a5eec27c0 ]

In sctp_sendmesg(), when walking the list of endpoint associations, the
association can be dropped from the list, making the list corrupt.
Properly handle this by using list_for_each_entry_safe()

Fixes: 4910280503f3 ("sctp: add support for snd flag SCTP_SENDALL process in sendmsg")
Reported-by: Secunia Research <vuln@secunia.com>
Tested-by: Secunia Research <vuln@secunia.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 876393cf5ed6..e5e70cff5bb3 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -2045,7 +2045,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len)
 	struct sctp_endpoint *ep = sctp_sk(sk)->ep;
 	struct sctp_transport *transport = NULL;
 	struct sctp_sndrcvinfo _sinfo, *sinfo;
-	struct sctp_association *asoc;
+	struct sctp_association *asoc, *tmp;
 	struct sctp_cmsgs cmsgs;
 	union sctp_addr *daddr;
 	bool new = false;
@@ -2071,7 +2071,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len)
 
 	/* SCTP_SENDALL process */
 	if ((sflags & SCTP_SENDALL) && sctp_style(sk, UDP)) {
-		list_for_each_entry(asoc, &ep->asocs, asocs) {
+		list_for_each_entry_safe(asoc, tmp, &ep->asocs, asocs) {
 			err = sctp_sendmsg_check_sflags(asoc, sflags, msg,
 							msg_len);
 			if (err == 0)
-- 
2.20.1


From a9b8e679dbd90bc58eb647c7842b6f03dd407cb5 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Fri, 1 Feb 2019 11:28:16 +0300
Subject: [PATCH 16/18] skge: potential memory corruption in skge_get_regs()

[ Upstream commit 294c149a209c6196c2de85f512b52ef50f519949 ]

The "p" buffer is 0x4000 bytes long.  B3_RI_WTO_R1 is 0x190.  The value
of "regs->len" is in the 1-0x4000 range.  The bug here is that
"regs->len - B3_RI_WTO_R1" can be a negative value which would lead to
memory corruption and an abrupt crash.

Fixes: c3f8be961808 ("[PATCH] skge: expand ethtool debug register dump")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/skge.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c
index 9c08c3650c02..15dea48e0195 100644
--- a/drivers/net/ethernet/marvell/skge.c
+++ b/drivers/net/ethernet/marvell/skge.c
@@ -152,8 +152,10 @@ static void skge_get_regs(struct net_device *dev, struct ethtool_regs *regs,
 	memset(p, 0, regs->len);
 	memcpy_fromio(p, io, B3_RAM_ADDR);
 
-	memcpy_fromio(p + B3_RI_WTO_R1, io + B3_RI_WTO_R1,
-		      regs->len - B3_RI_WTO_R1);
+	if (regs->len > B3_RI_WTO_R1) {
+		memcpy_fromio(p + B3_RI_WTO_R1, io + B3_RI_WTO_R1,
+			      regs->len - B3_RI_WTO_R1);
+	}
 }
 
 /* Wake on Lan only supported on Yukon chips with rev 1 or above */
-- 
2.20.1


From e38ac4913815092b7486cb50c852f9724eefcbd0 Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Thu, 31 Jan 2019 20:40:30 +0900
Subject: [PATCH 17/18] virtio_net: Account for tx bytes and packets on sending
 xdp_frames

[ Upstream commit 546f28974d771b124fb0bf7b551b343888cf0419 ]

Previously virtnet_xdp_xmit() did not account for device tx counters,
which caused confusions.
To be consistent with SKBs, account them on freeing xdp_frames.

Reported-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 42feaa4d2916..c88ee376a2eb 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -502,6 +502,8 @@ static int virtnet_xdp_xmit(struct net_device *dev,
 	struct bpf_prog *xdp_prog;
 	struct send_queue *sq;
 	unsigned int len;
+	int packets = 0;
+	int bytes = 0;
 	int drops = 0;
 	int kicks = 0;
 	int ret, err;
@@ -525,10 +527,18 @@ static int virtnet_xdp_xmit(struct net_device *dev,
 
 	/* Free up any pending old buffers before queueing new ones. */
 	while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) {
-		if (likely(is_xdp_frame(ptr)))
-			xdp_return_frame(ptr_to_xdp(ptr));
-		else
-			napi_consume_skb(ptr, false);
+		if (likely(is_xdp_frame(ptr))) {
+			struct xdp_frame *frame = ptr_to_xdp(ptr);
+
+			bytes += frame->len;
+			xdp_return_frame(frame);
+		} else {
+			struct sk_buff *skb = ptr;
+
+			bytes += skb->len;
+			napi_consume_skb(skb, false);
+		}
+		packets++;
 	}
 
 	for (i = 0; i < n; i++) {
@@ -548,6 +558,8 @@ static int virtnet_xdp_xmit(struct net_device *dev,
 	}
 out:
 	u64_stats_update_begin(&sq->stats.syncp);
+	sq->stats.bytes += bytes;
+	sq->stats.packets += packets;
 	sq->stats.xdp_tx += n;
 	sq->stats.xdp_tx_drops += drops;
 	sq->stats.kicks += kicks;
-- 
2.20.1


From 35df2c742cbcc7786a607a62f0c8befdda0f1894 Mon Sep 17 00:00:00 2001
From: Raed Salem <raeds@mellanox.com>
Date: Mon, 17 Dec 2018 11:40:06 +0200
Subject: [PATCH 18/18] net/mlx5e: FPGA, fix Innova IPsec TX offload data path
 performance

[ Upstream commit 82eaa1fa0448da1852d7b80832e67e80a08dcc27 ]

At Innova IPsec TX offload data path a special software parser metadata
is used to pass some packet attributes to the hardware, this metadata
is passed using the Ethernet control segment of a WQE (a HW descriptor)
header.

The cited commit might nullify this header, hence the metadata is lost,
this caused a significant performance drop during hw offloading
operation.

Fix by restoring the metadata at the Ethernet control segment in case
it was nullified.

Fixes: 37fdffb217a4 ("net/mlx5: WQ, fixes for fragmented WQ buffers API")
Signed-off-by: Raed Salem <raeds@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 6dacaeba2fbf..0b03d65474e9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -387,8 +387,14 @@ netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	num_wqebbs = DIV_ROUND_UP(ds_cnt, MLX5_SEND_WQEBB_NUM_DS);
 	contig_wqebbs_room = mlx5_wq_cyc_get_contig_wqebbs(wq, pi);
 	if (unlikely(contig_wqebbs_room < num_wqebbs)) {
+#ifdef CONFIG_MLX5_EN_IPSEC
+		struct mlx5_wqe_eth_seg cur_eth = wqe->eth;
+#endif
 		mlx5e_fill_sq_frag_edge(sq, wq, pi, contig_wqebbs_room);
 		mlx5e_sq_fetch_wqe(sq, &wqe, &pi);
+#ifdef CONFIG_MLX5_EN_IPSEC
+		wqe->eth = cur_eth;
+#endif
 	}
 
 	/* fill wqe */
-- 
2.20.1


[-- Attachment #3: net_420.mbox --]
[-- Type: Application/Octet-Stream, Size: 56396 bytes --]

From c2b8b09835894e31f0a20aa132e7fa6a93b27b24 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 30 Jan 2019 11:39:41 -0800
Subject: [PATCH 01/21] dccp: fool proof ccid_hc_[rt]x_parse_options()

[ Upstream commit 9b1f19d810e92d6cdc68455fbc22d9f961a58ce1 ]

Similarly to commit 276bdb82dedb ("dccp: check ccid before dereferencing")
it is wise to test for a NULL ccid.

kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] PREEMPT SMP KASAN
CPU: 1 PID: 16 Comm: ksoftirqd/1 Not tainted 5.0.0-rc3+ #37
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:ccid_hc_tx_parse_options net/dccp/ccid.h:205 [inline]
RIP: 0010:dccp_parse_options+0x8d9/0x12b0 net/dccp/options.c:233
Code: c5 0f b6 75 b3 80 38 00 0f 85 d6 08 00 00 48 b9 00 00 00 00 00 fc ff df 48 8b 45 b8 4c 8b b8 f8 07 00 00 4c 89 f8 48 c1 e8 03 <80> 3c 08 00 0f 85 95 08 00 00 48 b8 00 00 00 00 00 fc ff df 4d 8b
kobject: 'loop5' (0000000080f78fc1): kobject_uevent_env
RSP: 0018:ffff8880a94df0b8 EFLAGS: 00010246
RAX: 0000000000000000 RBX: ffff8880858ac723 RCX: dffffc0000000000
RDX: 0000000000000100 RSI: 0000000000000007 RDI: 0000000000000001
RBP: ffff8880a94df140 R08: 0000000000000001 R09: ffff888061b83a80
R10: ffffed100c370752 R11: ffff888061b83a97 R12: 0000000000000026
R13: 0000000000000001 R14: 0000000000000000 R15: 0000000000000000
FS:  0000000000000000(0000) GS:ffff8880ae700000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f0defa33518 CR3: 000000008db5e000 CR4: 00000000001406e0
kobject: 'loop5' (0000000080f78fc1): fill_kobj_path: path = '/devices/virtual/block/loop5'
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 dccp_rcv_state_process+0x2b6/0x1af6 net/dccp/input.c:654
 dccp_v4_do_rcv+0x100/0x190 net/dccp/ipv4.c:688
 sk_backlog_rcv include/net/sock.h:936 [inline]
 __sk_receive_skb+0x3a9/0xea0 net/core/sock.c:473
 dccp_v4_rcv+0x10cb/0x1f80 net/dccp/ipv4.c:880
 ip_protocol_deliver_rcu+0xb6/0xa20 net/ipv4/ip_input.c:208
 ip_local_deliver_finish+0x23b/0x390 net/ipv4/ip_input.c:234
 NF_HOOK include/linux/netfilter.h:289 [inline]
 NF_HOOK include/linux/netfilter.h:283 [inline]
 ip_local_deliver+0x1f0/0x740 net/ipv4/ip_input.c:255
 dst_input include/net/dst.h:450 [inline]
 ip_rcv_finish+0x1f4/0x2f0 net/ipv4/ip_input.c:414
 NF_HOOK include/linux/netfilter.h:289 [inline]
 NF_HOOK include/linux/netfilter.h:283 [inline]
 ip_rcv+0xed/0x620 net/ipv4/ip_input.c:524
 __netif_receive_skb_one_core+0x160/0x210 net/core/dev.c:4973
 __netif_receive_skb+0x2c/0x1c0 net/core/dev.c:5083
 process_backlog+0x206/0x750 net/core/dev.c:5923
 napi_poll net/core/dev.c:6346 [inline]
 net_rx_action+0x76d/0x1930 net/core/dev.c:6412
 __do_softirq+0x30b/0xb11 kernel/softirq.c:292
 run_ksoftirqd kernel/softirq.c:654 [inline]
 run_ksoftirqd+0x8e/0x110 kernel/softirq.c:646
 smpboot_thread_fn+0x6ab/0xa10 kernel/smpboot.c:164
 kthread+0x357/0x430 kernel/kthread.c:246
 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:352
Modules linked in:
---[ end trace 58a0ba03bea2c376 ]---
RIP: 0010:ccid_hc_tx_parse_options net/dccp/ccid.h:205 [inline]
RIP: 0010:dccp_parse_options+0x8d9/0x12b0 net/dccp/options.c:233
Code: c5 0f b6 75 b3 80 38 00 0f 85 d6 08 00 00 48 b9 00 00 00 00 00 fc ff df 48 8b 45 b8 4c 8b b8 f8 07 00 00 4c 89 f8 48 c1 e8 03 <80> 3c 08 00 0f 85 95 08 00 00 48 b8 00 00 00 00 00 fc ff df 4d 8b
RSP: 0018:ffff8880a94df0b8 EFLAGS: 00010246
RAX: 0000000000000000 RBX: ffff8880858ac723 RCX: dffffc0000000000
RDX: 0000000000000100 RSI: 0000000000000007 RDI: 0000000000000001
RBP: ffff8880a94df140 R08: 0000000000000001 R09: ffff888061b83a80
R10: ffffed100c370752 R11: ffff888061b83a97 R12: 0000000000000026
R13: 0000000000000001 R14: 0000000000000000 R15: 0000000000000000
FS:  0000000000000000(0000) GS:ffff8880ae700000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f0defa33518 CR3: 0000000009871000 CR4: 00000000001406e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ccid.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/dccp/ccid.h b/net/dccp/ccid.h
index 6eb837a47b5c..baaaeb2b2c42 100644
--- a/net/dccp/ccid.h
+++ b/net/dccp/ccid.h
@@ -202,7 +202,7 @@ static inline void ccid_hc_tx_packet_recv(struct ccid *ccid, struct sock *sk,
 static inline int ccid_hc_tx_parse_options(struct ccid *ccid, struct sock *sk,
 					   u8 pkt, u8 opt, u8 *val, u8 len)
 {
-	if (ccid->ccid_ops->ccid_hc_tx_parse_options == NULL)
+	if (!ccid || !ccid->ccid_ops->ccid_hc_tx_parse_options)
 		return 0;
 	return ccid->ccid_ops->ccid_hc_tx_parse_options(sk, pkt, opt, val, len);
 }
@@ -214,7 +214,7 @@ static inline int ccid_hc_tx_parse_options(struct ccid *ccid, struct sock *sk,
 static inline int ccid_hc_rx_parse_options(struct ccid *ccid, struct sock *sk,
 					   u8 pkt, u8 opt, u8 *val, u8 len)
 {
-	if (ccid->ccid_ops->ccid_hc_rx_parse_options == NULL)
+	if (!ccid || !ccid->ccid_ops->ccid_hc_rx_parse_options)
 		return 0;
 	return ccid->ccid_ops->ccid_hc_rx_parse_options(sk, pkt, opt, val, len);
 }
-- 
2.20.1


From 373f804a2a128a5bc1182a32543c60bb354eac90 Mon Sep 17 00:00:00 2001
From: Govindarajulu Varadarajan <gvaradar@cisco.com>
Date: Wed, 30 Jan 2019 06:59:00 -0800
Subject: [PATCH 02/21] enic: fix checksum validation for IPv6

[ Upstream commit 7596175e99b3d4bce28022193efd954c201a782a ]

In case of IPv6 pkts, ipv4_csum_ok is 0. Because of this, driver does
not set skb->ip_summed. So IPv6 rx checksum is not offloaded.

Signed-off-by: Govindarajulu Varadarajan <gvaradar@cisco.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cisco/enic/enic_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index 60641e202534..9a7f70db20c7 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -1434,7 +1434,8 @@ static void enic_rq_indicate_buf(struct vnic_rq *rq,
 		 * csum is correct or is zero.
 		 */
 		if ((netdev->features & NETIF_F_RXCSUM) && !csum_not_calc &&
-		    tcp_udp_csum_ok && ipv4_csum_ok && outer_csum_ok) {
+		    tcp_udp_csum_ok && outer_csum_ok &&
+		    (ipv4_csum_ok || ipv6)) {
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
 			skb->csum_level = encap;
 		}
-- 
2.20.1


From fd012d1805950de8247b25c8484b170f90bf8872 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Wed, 30 Jan 2019 10:42:30 -0800
Subject: [PATCH 03/21] lib/test_rhashtable: Make test_insert_dup() allocate
 its hash table dynamically

[ Upstream commit fc42a689c4c097859e5bd37b5ea11b60dc426df6 ]

The test_insert_dup() function from lib/test_rhashtable.c passes a
pointer to a stack object to rhltable_init(). Allocate the hash table
dynamically to avoid that the following is reported with object
debugging enabled:

ODEBUG: object (ptrval) is on stack (ptrval), but NOT annotated.
WARNING: CPU: 0 PID: 1 at lib/debugobjects.c:368 __debug_object_init+0x312/0x480
Modules linked in:
EIP: __debug_object_init+0x312/0x480
Call Trace:
 ? debug_object_init+0x1a/0x20
 ? __init_work+0x16/0x30
 ? rhashtable_init+0x1e1/0x460
 ? sched_clock_cpu+0x57/0xe0
 ? rhltable_init+0xb/0x20
 ? test_insert_dup+0x32/0x20f
 ? trace_hardirqs_on+0x38/0xf0
 ? ida_dump+0x10/0x10
 ? jhash+0x130/0x130
 ? my_hashfn+0x30/0x30
 ? test_rht_init+0x6aa/0xab4
 ? ida_dump+0x10/0x10
 ? test_rhltable+0xc5c/0xc5c
 ? do_one_initcall+0x67/0x28e
 ? trace_hardirqs_off+0x22/0xe0
 ? restore_all_kernel+0xf/0x70
 ? trace_hardirqs_on_thunk+0xc/0x10
 ? restore_all_kernel+0xf/0x70
 ? kernel_init_freeable+0x142/0x213
 ? rest_init+0x230/0x230
 ? kernel_init+0x10/0x110
 ? schedule_tail_wrapper+0x9/0xc
 ? ret_from_fork+0x19/0x24

Cc: Thomas Graf <tgraf@suug.ch>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: netdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 lib/test_rhashtable.c | 23 +++++++++++++++--------
 1 file changed, 15 insertions(+), 8 deletions(-)

diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c
index 82ac39ce5310..aecc0996628f 100644
--- a/lib/test_rhashtable.c
+++ b/lib/test_rhashtable.c
@@ -541,38 +541,45 @@ static unsigned int __init print_ht(struct rhltable *rhlt)
 static int __init test_insert_dup(struct test_obj_rhl *rhl_test_objects,
 				  int cnt, bool slow)
 {
-	struct rhltable rhlt;
+	struct rhltable *rhlt;
 	unsigned int i, ret;
 	const char *key;
 	int err = 0;
 
-	err = rhltable_init(&rhlt, &test_rht_params_dup);
-	if (WARN_ON(err))
+	rhlt = kmalloc(sizeof(*rhlt), GFP_KERNEL);
+	if (WARN_ON(!rhlt))
+		return -EINVAL;
+
+	err = rhltable_init(rhlt, &test_rht_params_dup);
+	if (WARN_ON(err)) {
+		kfree(rhlt);
 		return err;
+	}
 
 	for (i = 0; i < cnt; i++) {
 		rhl_test_objects[i].value.tid = i;
-		key = rht_obj(&rhlt.ht, &rhl_test_objects[i].list_node.rhead);
+		key = rht_obj(&rhlt->ht, &rhl_test_objects[i].list_node.rhead);
 		key += test_rht_params_dup.key_offset;
 
 		if (slow) {
-			err = PTR_ERR(rhashtable_insert_slow(&rhlt.ht, key,
+			err = PTR_ERR(rhashtable_insert_slow(&rhlt->ht, key,
 							     &rhl_test_objects[i].list_node.rhead));
 			if (err == -EAGAIN)
 				err = 0;
 		} else
-			err = rhltable_insert(&rhlt,
+			err = rhltable_insert(rhlt,
 					      &rhl_test_objects[i].list_node,
 					      test_rht_params_dup);
 		if (WARN(err, "error %d on element %d/%d (%s)\n", err, i, cnt, slow? "slow" : "fast"))
 			goto skip_print;
 	}
 
-	ret = print_ht(&rhlt);
+	ret = print_ht(rhlt);
 	WARN(ret != cnt, "missing rhltable elements (%d != %d, %s)\n", ret, cnt, slow? "slow" : "fast");
 
 skip_print:
-	rhltable_destroy(&rhlt);
+	rhltable_destroy(rhlt);
+	kfree(rhlt);
 
 	return 0;
 }
-- 
2.20.1


From 35ded25f3576ebe515a4a0a2772539e7037e2b99 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Mon, 4 Feb 2019 11:20:29 +0100
Subject: [PATCH 04/21] net: dp83640: expire old TX-skb

[ Upstream commit 53bc8d2af08654659abfadfd3e98eb9922ff787c ]

During sendmsg() a cloned skb is saved via dp83640_txtstamp() in
->tx_queue. After the NIC sends this packet, the PHY will reply with a
timestamp for that TX packet. If the cable is pulled at the right time I
don't see that packet. It might gets flushed as part of queue shutdown
on NIC's side.
Once the link is up again then after the next sendmsg() we enqueue
another skb in dp83640_txtstamp() and have two on the list. Then the PHY
will send a reply and decode_txts() attaches it to the first skb on the
list.
No crash occurs since refcounting works but we are one packet behind.
linuxptp/ptp4l usually closes the socket and opens a new one (in such a
timeout case) so those "stale" replies never get there. However it does
not resume normal operation anymore.

Purge old skbs in decode_txts().

Fixes: cb646e2b02b2 ("ptp: Added a clock driver for the National Semiconductor PHYTER.")
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Kurt Kanzenbach <kurt@linutronix.de>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/dp83640.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index edd4d44a386d..d3b36936f81e 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -898,14 +898,14 @@ static void decode_txts(struct dp83640_private *dp83640,
 			struct phy_txts *phy_txts)
 {
 	struct skb_shared_hwtstamps shhwtstamps;
+	struct dp83640_skb_info *skb_info;
 	struct sk_buff *skb;
-	u64 ns;
 	u8 overflow;
+	u64 ns;
 
 	/* We must already have the skb that triggered this. */
-
+again:
 	skb = skb_dequeue(&dp83640->tx_queue);
-
 	if (!skb) {
 		pr_debug("have timestamp but tx_queue empty\n");
 		return;
@@ -920,6 +920,11 @@ static void decode_txts(struct dp83640_private *dp83640,
 		}
 		return;
 	}
+	skb_info = (struct dp83640_skb_info *)skb->cb;
+	if (time_after(jiffies, skb_info->tmo)) {
+		kfree_skb(skb);
+		goto again;
+	}
 
 	ns = phy2txts(phy_txts);
 	memset(&shhwtstamps, 0, sizeof(shhwtstamps));
@@ -1472,6 +1477,7 @@ static bool dp83640_rxtstamp(struct phy_device *phydev,
 static void dp83640_txtstamp(struct phy_device *phydev,
 			     struct sk_buff *skb, int type)
 {
+	struct dp83640_skb_info *skb_info = (struct dp83640_skb_info *)skb->cb;
 	struct dp83640_private *dp83640 = phydev->priv;
 
 	switch (dp83640->hwts_tx_en) {
@@ -1484,6 +1490,7 @@ static void dp83640_txtstamp(struct phy_device *phydev,
 		/* fall through */
 	case HWTSTAMP_TX_ON:
 		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+		skb_info->tmo = jiffies + SKB_TIMESTAMP_TIMEOUT;
 		skb_queue_tail(&dp83640->tx_queue, skb);
 		break;
 
-- 
2.20.1


From afa54ee7730e97fc202d23273830891d50da45cd Mon Sep 17 00:00:00 2001
From: Marc Zyngier <marc.zyngier@arm.com>
Date: Sat, 2 Feb 2019 17:53:29 +0000
Subject: [PATCH 05/21] net: dsa: Fix lockdep false positive splat

[ Upstream commit c8101f7729daee251f4f6505f9d135ec08e1342f ]

Creating a macvtap on a DSA-backed interface results in the following
splat when lockdep is enabled:

[   19.638080] IPv6: ADDRCONF(NETDEV_CHANGE): lan0: link becomes ready
[   23.041198] device lan0 entered promiscuous mode
[   23.043445] device eth0 entered promiscuous mode
[   23.049255]
[   23.049557] ============================================
[   23.055021] WARNING: possible recursive locking detected
[   23.060490] 5.0.0-rc3-00013-g56c857a1b8d3 #118 Not tainted
[   23.066132] --------------------------------------------
[   23.071598] ip/2861 is trying to acquire lock:
[   23.076171] 00000000f61990cb (_xmit_ETHER){+...}, at: dev_set_rx_mode+0x1c/0x38
[   23.083693]
[   23.083693] but task is already holding lock:
[   23.089696] 00000000ecf0c3b4 (_xmit_ETHER){+...}, at: dev_uc_add+0x24/0x70
[   23.096774]
[   23.096774] other info that might help us debug this:
[   23.103494]  Possible unsafe locking scenario:
[   23.103494]
[   23.109584]        CPU0
[   23.112093]        ----
[   23.114601]   lock(_xmit_ETHER);
[   23.117917]   lock(_xmit_ETHER);
[   23.121233]
[   23.121233]  *** DEADLOCK ***
[   23.121233]
[   23.127325]  May be due to missing lock nesting notation
[   23.127325]
[   23.134315] 2 locks held by ip/2861:
[   23.137987]  #0: 000000003b766c72 (rtnl_mutex){+.+.}, at: rtnetlink_rcv_msg+0x338/0x4e0
[   23.146231]  #1: 00000000ecf0c3b4 (_xmit_ETHER){+...}, at: dev_uc_add+0x24/0x70
[   23.153757]
[   23.153757] stack backtrace:
[   23.158243] CPU: 0 PID: 2861 Comm: ip Not tainted 5.0.0-rc3-00013-g56c857a1b8d3 #118
[   23.166212] Hardware name: Globalscale Marvell ESPRESSOBin Board (DT)
[   23.172843] Call trace:
[   23.175358]  dump_backtrace+0x0/0x188
[   23.179116]  show_stack+0x14/0x20
[   23.182524]  dump_stack+0xb4/0xec
[   23.185928]  __lock_acquire+0x123c/0x1860
[   23.190048]  lock_acquire+0xc8/0x248
[   23.193724]  _raw_spin_lock_bh+0x40/0x58
[   23.197755]  dev_set_rx_mode+0x1c/0x38
[   23.201607]  dev_set_promiscuity+0x3c/0x50
[   23.205820]  dsa_slave_change_rx_flags+0x5c/0x70
[   23.210567]  __dev_set_promiscuity+0x148/0x1e0
[   23.215136]  __dev_set_rx_mode+0x74/0x98
[   23.219167]  dev_uc_add+0x54/0x70
[   23.222575]  macvlan_open+0x170/0x1d0
[   23.226336]  __dev_open+0xe0/0x160
[   23.229830]  __dev_change_flags+0x16c/0x1b8
[   23.234132]  dev_change_flags+0x20/0x60
[   23.238074]  do_setlink+0x2d0/0xc50
[   23.241658]  __rtnl_newlink+0x5f8/0x6e8
[   23.245601]  rtnl_newlink+0x50/0x78
[   23.249184]  rtnetlink_rcv_msg+0x360/0x4e0
[   23.253397]  netlink_rcv_skb+0xe8/0x130
[   23.257338]  rtnetlink_rcv+0x14/0x20
[   23.261012]  netlink_unicast+0x190/0x210
[   23.265043]  netlink_sendmsg+0x288/0x350
[   23.269075]  sock_sendmsg+0x18/0x30
[   23.272659]  ___sys_sendmsg+0x29c/0x2c8
[   23.276602]  __sys_sendmsg+0x60/0xb8
[   23.280276]  __arm64_sys_sendmsg+0x1c/0x28
[   23.284488]  el0_svc_common+0xd8/0x138
[   23.288340]  el0_svc_handler+0x24/0x80
[   23.292192]  el0_svc+0x8/0xc

This looks fairly harmless (no actual deadlock occurs), and is
fixed in a similar way to c6894dec8ea9 ("bridge: fix lockdep
addr_list_lock false positive splat") by putting the addr_list_lock
in its own lockdep class.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/master.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/dsa/master.c b/net/dsa/master.c
index 5e8c9bef78bd..dbfdda5fe8ed 100644
--- a/net/dsa/master.c
+++ b/net/dsa/master.c
@@ -179,6 +179,8 @@ static const struct attribute_group dsa_group = {
 	.attrs	= dsa_slave_attrs,
 };
 
+static struct lock_class_key dsa_master_addr_list_lock_key;
+
 int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
 {
 	int ret;
@@ -190,6 +192,8 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
 	wmb();
 
 	dev->dsa_ptr = cpu_dp;
+	lockdep_set_class(&dev->addr_list_lock,
+			  &dsa_master_addr_list_lock_key);
 
 	ret = dsa_master_ethtool_setup(dev);
 	if (ret)
-- 
2.20.1


From 5265cb9a72fdfc29fc8b258d01bd0dce45654221 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 6 Feb 2019 18:35:15 +0300
Subject: [PATCH 06/21] net: dsa: Fix NULL checking in dsa_slave_set_eee()

[ Upstream commit 00670cb8a73b10b10d3c40f045c15411715e4465 ]

This function can't succeed if dp->pl is NULL.  It will Oops inside the
call to return phylink_ethtool_get_eee(dp->pl, e);

Fixes: 1be52e97ed3e ("dsa: slave: eee: Allow ports to use phylink")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Vivien Didelot <vivien.didelot@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/slave.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index aec78f5aca72..713af3640dd0 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -639,7 +639,7 @@ static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e)
 	int ret;
 
 	/* Port's PHY and MAC both need to be EEE capable */
-	if (!dev->phydev && !dp->pl)
+	if (!dev->phydev || !dp->pl)
 		return -ENODEV;
 
 	if (!ds->ops->set_mac_eee)
@@ -659,7 +659,7 @@ static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e)
 	int ret;
 
 	/* Port's PHY and MAC both need to be EEE capable */
-	if (!dev->phydev && !dp->pl)
+	if (!dev->phydev || !dp->pl)
 		return -ENODEV;
 
 	if (!ds->ops->get_mac_eee)
-- 
2.20.1


From ea13f6ac2c2c5cb067cce68d3f41b46febcf92b3 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Wed, 6 Feb 2019 00:02:58 +0100
Subject: [PATCH 07/21] net: dsa: mv88e6xxx: Fix counting of ATU violations

[ Upstream commit 75c05a74e745ae7d663b04d75777af80ada2233c ]

The ATU port vector contains a bit per port of the switch. The code
wrongly used it as a port number, and incremented a port counter. This
resulted in the wrong interfaces counter being incremented, and
potentially going off the end of the array of ports.

Fix this by using the source port ID for the violation, which really
is a port number.

Reported-by: Chris Healy <Chris.Healy@zii.aero>
Tested-by: Chris Healy <Chris.Healy@zii.aero>
Fixes: 65f60e4582bd ("net: dsa: mv88e6xxx: Keep ATU/VTU violation statistics")
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/global1_atu.c | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/global1_atu.c b/drivers/net/dsa/mv88e6xxx/global1_atu.c
index 5200e4bdce93..ea243840ee0f 100644
--- a/drivers/net/dsa/mv88e6xxx/global1_atu.c
+++ b/drivers/net/dsa/mv88e6xxx/global1_atu.c
@@ -314,6 +314,7 @@ static irqreturn_t mv88e6xxx_g1_atu_prob_irq_thread_fn(int irq, void *dev_id)
 {
 	struct mv88e6xxx_chip *chip = dev_id;
 	struct mv88e6xxx_atu_entry entry;
+	int spid;
 	int err;
 	u16 val;
 
@@ -336,6 +337,8 @@ static irqreturn_t mv88e6xxx_g1_atu_prob_irq_thread_fn(int irq, void *dev_id)
 	if (err)
 		goto out;
 
+	spid = entry.state;
+
 	if (val & MV88E6XXX_G1_ATU_OP_AGE_OUT_VIOLATION) {
 		dev_err_ratelimited(chip->dev,
 				    "ATU age out violation for %pM\n",
@@ -344,23 +347,23 @@ static irqreturn_t mv88e6xxx_g1_atu_prob_irq_thread_fn(int irq, void *dev_id)
 
 	if (val & MV88E6XXX_G1_ATU_OP_MEMBER_VIOLATION) {
 		dev_err_ratelimited(chip->dev,
-				    "ATU member violation for %pM portvec %x\n",
-				    entry.mac, entry.portvec);
-		chip->ports[entry.portvec].atu_member_violation++;
+				    "ATU member violation for %pM portvec %x spid %d\n",
+				    entry.mac, entry.portvec, spid);
+		chip->ports[spid].atu_member_violation++;
 	}
 
 	if (val & MV88E6XXX_G1_ATU_OP_MISS_VIOLATION) {
 		dev_err_ratelimited(chip->dev,
-				    "ATU miss violation for %pM portvec %x\n",
-				    entry.mac, entry.portvec);
-		chip->ports[entry.portvec].atu_miss_violation++;
+				    "ATU miss violation for %pM portvec %x spid %d\n",
+				    entry.mac, entry.portvec, spid);
+		chip->ports[spid].atu_miss_violation++;
 	}
 
 	if (val & MV88E6XXX_G1_ATU_OP_FULL_VIOLATION) {
 		dev_err_ratelimited(chip->dev,
-				    "ATU full violation for %pM portvec %x\n",
-				    entry.mac, entry.portvec);
-		chip->ports[entry.portvec].atu_full_violation++;
+				    "ATU full violation for %pM portvec %x spid %d\n",
+				    entry.mac, entry.portvec, spid);
+		chip->ports[spid].atu_full_violation++;
 	}
 	mutex_unlock(&chip->reg_lock);
 
-- 
2.20.1


From 24ea93827e5895e573d9f10e7d4325f0049a9f99 Mon Sep 17 00:00:00 2001
From: Rundong Ge <rdong.ge@gmail.com>
Date: Sat, 2 Feb 2019 14:29:35 +0000
Subject: [PATCH 08/21] net: dsa: slave: Don't propagate flag changes on down
 slave interfaces

[ Upstream commit 17ab4f61b8cd6f9c38e9d0b935d86d73b5d0d2b5 ]

The unbalance of master's promiscuity or allmulti will happen after ifdown
and ifup a slave interface which is in a bridge.

When we ifdown a slave interface , both the 'dsa_slave_close' and
'dsa_slave_change_rx_flags' will clear the master's flags. The flags
of master will be decrease twice.
In the other hand, if we ifup the slave interface again, since the
slave's flags were cleared the 'dsa_slave_open' won't set the master's
flag, only 'dsa_slave_change_rx_flags' that triggered by 'br_add_if'
will set the master's flags. The flags of master is increase once.

Only propagating flag changes when a slave interface is up makes
sure this does not happen. The 'vlan_dev_change_rx_flags' had the
same problem and was fixed, and changes here follows that fix.

Fixes: 91da11f870f0 ("net: Distributed Switch Architecture protocol support")
Signed-off-by: Rundong Ge <rdong.ge@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/slave.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 713af3640dd0..a3ddc225f103 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -140,11 +140,14 @@ static int dsa_slave_close(struct net_device *dev)
 static void dsa_slave_change_rx_flags(struct net_device *dev, int change)
 {
 	struct net_device *master = dsa_slave_to_master(dev);
-
-	if (change & IFF_ALLMULTI)
-		dev_set_allmulti(master, dev->flags & IFF_ALLMULTI ? 1 : -1);
-	if (change & IFF_PROMISC)
-		dev_set_promiscuity(master, dev->flags & IFF_PROMISC ? 1 : -1);
+	if (dev->flags & IFF_UP) {
+		if (change & IFF_ALLMULTI)
+			dev_set_allmulti(master,
+					 dev->flags & IFF_ALLMULTI ? 1 : -1);
+		if (change & IFF_PROMISC)
+			dev_set_promiscuity(master,
+					    dev->flags & IFF_PROMISC ? 1 : -1);
+	}
 }
 
 static void dsa_slave_set_rx_mode(struct net_device *dev)
-- 
2.20.1


From b483e4bfef27848ac1bd249d11c9334abe39d579 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 1 Feb 2019 13:23:38 -0800
Subject: [PATCH 09/21] net: systemport: Fix WoL with password after deep sleep

[ Upstream commit 8dfb8d2cceb76b74ad5b58cc65c75994329b4d5e ]

Broadcom STB chips support a deep sleep mode where all register
contents are lost. Because we were stashing the MagicPacket password
into some of these registers a suspend into that deep sleep then a
resumption would not lead to being able to wake-up from MagicPacket with
password again.

Fix this by keeping a software copy of the password and program it
during suspend.

Fixes: 83e82f4c706b ("net: systemport: add Wake-on-LAN support")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bcmsysport.c | 25 +++++++++-------------
 drivers/net/ethernet/broadcom/bcmsysport.h |  2 ++
 2 files changed, 12 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 0e2d99c737e3..baa109040b40 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -520,7 +520,6 @@ static void bcm_sysport_get_wol(struct net_device *dev,
 				struct ethtool_wolinfo *wol)
 {
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
-	u32 reg;
 
 	wol->supported = WAKE_MAGIC | WAKE_MAGICSECURE | WAKE_FILTER;
 	wol->wolopts = priv->wolopts;
@@ -528,11 +527,7 @@ static void bcm_sysport_get_wol(struct net_device *dev,
 	if (!(priv->wolopts & WAKE_MAGICSECURE))
 		return;
 
-	/* Return the programmed SecureOn password */
-	reg = umac_readl(priv, UMAC_PSW_MS);
-	put_unaligned_be16(reg, &wol->sopass[0]);
-	reg = umac_readl(priv, UMAC_PSW_LS);
-	put_unaligned_be32(reg, &wol->sopass[2]);
+	memcpy(wol->sopass, priv->sopass, sizeof(priv->sopass));
 }
 
 static int bcm_sysport_set_wol(struct net_device *dev,
@@ -548,13 +543,8 @@ static int bcm_sysport_set_wol(struct net_device *dev,
 	if (wol->wolopts & ~supported)
 		return -EINVAL;
 
-	/* Program the SecureOn password */
-	if (wol->wolopts & WAKE_MAGICSECURE) {
-		umac_writel(priv, get_unaligned_be16(&wol->sopass[0]),
-			    UMAC_PSW_MS);
-		umac_writel(priv, get_unaligned_be32(&wol->sopass[2]),
-			    UMAC_PSW_LS);
-	}
+	if (wol->wolopts & WAKE_MAGICSECURE)
+		memcpy(priv->sopass, wol->sopass, sizeof(priv->sopass));
 
 	/* Flag the device and relevant IRQ as wakeup capable */
 	if (wol->wolopts) {
@@ -2592,13 +2582,18 @@ static int bcm_sysport_suspend_to_wol(struct bcm_sysport_priv *priv)
 	unsigned int index, i = 0;
 	u32 reg;
 
-	/* Password has already been programmed */
 	reg = umac_readl(priv, UMAC_MPD_CTRL);
 	if (priv->wolopts & (WAKE_MAGIC | WAKE_MAGICSECURE))
 		reg |= MPD_EN;
 	reg &= ~PSW_EN;
-	if (priv->wolopts & WAKE_MAGICSECURE)
+	if (priv->wolopts & WAKE_MAGICSECURE) {
+		/* Program the SecureOn password */
+		umac_writel(priv, get_unaligned_be16(&priv->sopass[0]),
+			    UMAC_PSW_MS);
+		umac_writel(priv, get_unaligned_be32(&priv->sopass[2]),
+			    UMAC_PSW_LS);
 		reg |= PSW_EN;
+	}
 	umac_writel(priv, reg, UMAC_MPD_CTRL);
 
 	if (priv->wolopts & WAKE_FILTER) {
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h
index a7a230884a87..930ab8de3f45 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.h
+++ b/drivers/net/ethernet/broadcom/bcmsysport.h
@@ -12,6 +12,7 @@
 #define __BCM_SYSPORT_H
 
 #include <linux/bitmap.h>
+#include <linux/ethtool.h>
 #include <linux/if_vlan.h>
 #include <linux/net_dim.h>
 
@@ -778,6 +779,7 @@ struct bcm_sysport_priv {
 	unsigned int		crc_fwd:1;
 	u16			rev;
 	u32			wolopts;
+	u8			sopass[SOPASS_MAX];
 	unsigned int		wol_irq_disabled:1;
 
 	/* MIB related fields */
-- 
2.20.1


From 0c7906122ffc65b0e5015b3fd630ed2992c09a43 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 31 Jan 2019 08:47:10 -0800
Subject: [PATCH 10/21] rds: fix refcount bug in rds_sock_addref

[ Upstream commit 6fa19f5637a6c22bc0999596bcc83bdcac8a4fa6 ]

syzbot was able to catch a bug in rds [1]

The issue here is that the socket might be found in a hash table
but that its refcount has already be set to 0 by another cpu.

We need to use refcount_inc_not_zero() to be safe here.

[1]

refcount_t: increment on 0; use-after-free.
WARNING: CPU: 1 PID: 23129 at lib/refcount.c:153 refcount_inc_checked lib/refcount.c:153 [inline]
WARNING: CPU: 1 PID: 23129 at lib/refcount.c:153 refcount_inc_checked+0x61/0x70 lib/refcount.c:151
Kernel panic - not syncing: panic_on_warn set ...
CPU: 1 PID: 23129 Comm: syz-executor3 Not tainted 5.0.0-rc4+ #53
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1db/0x2d0 lib/dump_stack.c:113
 panic+0x2cb/0x65c kernel/panic.c:214
 __warn.cold+0x20/0x48 kernel/panic.c:571
 report_bug+0x263/0x2b0 lib/bug.c:186
 fixup_bug arch/x86/kernel/traps.c:178 [inline]
 fixup_bug arch/x86/kernel/traps.c:173 [inline]
 do_error_trap+0x11b/0x200 arch/x86/kernel/traps.c:271
 do_invalid_op+0x37/0x50 arch/x86/kernel/traps.c:290
 invalid_op+0x14/0x20 arch/x86/entry/entry_64.S:973
RIP: 0010:refcount_inc_checked lib/refcount.c:153 [inline]
RIP: 0010:refcount_inc_checked+0x61/0x70 lib/refcount.c:151
Code: 1d 51 63 c8 06 31 ff 89 de e8 eb 1b f2 fd 84 db 75 dd e8 a2 1a f2 fd 48 c7 c7 60 9f 81 88 c6 05 31 63 c8 06 01 e8 af 65 bb fd <0f> 0b eb c1 90 66 2e 0f 1f 84 00 00 00 00 00 55 48 89 e5 41 54 49
RSP: 0018:ffff8880a0cbf1e8 EFLAGS: 00010282
RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffffc90006113000
RDX: 000000000001047d RSI: ffffffff81685776 RDI: 0000000000000005
RBP: ffff8880a0cbf1f8 R08: ffff888097c9e100 R09: ffffed1015ce5021
R10: ffffed1015ce5020 R11: ffff8880ae728107 R12: ffff8880723c20c0
R13: ffff8880723c24b0 R14: dffffc0000000000 R15: ffffed1014197e64
 sock_hold include/net/sock.h:647 [inline]
 rds_sock_addref+0x19/0x20 net/rds/af_rds.c:675
 rds_find_bound+0x97c/0x1080 net/rds/bind.c:82
 rds_recv_incoming+0x3be/0x1430 net/rds/recv.c:362
 rds_loop_xmit+0xf3/0x2a0 net/rds/loop.c:96
 rds_send_xmit+0x1355/0x2a10 net/rds/send.c:355
 rds_sendmsg+0x323c/0x44e0 net/rds/send.c:1368
 sock_sendmsg_nosec net/socket.c:621 [inline]
 sock_sendmsg+0xdd/0x130 net/socket.c:631
 __sys_sendto+0x387/0x5f0 net/socket.c:1788
 __do_sys_sendto net/socket.c:1800 [inline]
 __se_sys_sendto net/socket.c:1796 [inline]
 __x64_sys_sendto+0xe1/0x1a0 net/socket.c:1796
 do_syscall_64+0x1a3/0x800 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x458089
Code: 6d b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 3b b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007fc266df8c78 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 0000000000000006 RCX: 0000000000458089
RDX: 0000000000000000 RSI: 00000000204b3fff RDI: 0000000000000005
RBP: 000000000073bf00 R08: 00000000202b4000 R09: 0000000000000010
R10: 0000000000000000 R11: 0000000000000246 R12: 00007fc266df96d4
R13: 00000000004c56e4 R14: 00000000004d94a8 R15: 00000000ffffffff

Fixes: cc4dfb7f70a3 ("rds: fix two RCU related problems")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Cc: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Cc: rds-devel@oss.oracle.com
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/bind.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/rds/bind.c b/net/rds/bind.c
index 762d2c6788a3..17c9d9f0c848 100644
--- a/net/rds/bind.c
+++ b/net/rds/bind.c
@@ -78,10 +78,10 @@ struct rds_sock *rds_find_bound(const struct in6_addr *addr, __be16 port,
 	__rds_create_bind_key(key, addr, port, scope_id);
 	rcu_read_lock();
 	rs = rhashtable_lookup(&bind_hash_table, key, ht_parms);
-	if (rs && !sock_flag(rds_rs_to_sk(rs), SOCK_DEAD))
-		rds_sock_addref(rs);
-	else
+	if (rs && (sock_flag(rds_rs_to_sk(rs), SOCK_DEAD) ||
+		   !refcount_inc_not_zero(&rds_rs_to_sk(rs)->sk_refcnt)))
 		rs = NULL;
+
 	rcu_read_unlock();
 
 	rdsdebug("returning rs %p for %pI6c:%u\n", rs, addr,
-- 
2.20.1


From 4d3c03bcc5ba04d2c06f0cf2b71f67af05f54c06 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Thu, 31 Jan 2019 16:59:46 +0000
Subject: [PATCH 11/21] Revert "net: phy: marvell: avoid pause mode on
 SGMII-to-Copper for 88e151x"

[ Upstream commit c14f07c6211cc01d52ed92cce1fade5071b8d197 ]

This reverts commit 6623c0fba10ef45b64ca213ad5dec926f37fa9a0.

The original diagnosis was incorrect: it appears that the NIC had
PHY polling mode enabled, which meant that it overwrote the PHYs
advertisement register during negotiation.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Tested-by: Yonglong Liu <liuyonglong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/marvell.c | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index f46da6262abe..f5290adb49f0 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -847,8 +847,6 @@ static int m88e1510_config_init(struct phy_device *phydev)
 
 	/* SGMII-to-Copper mode initialization */
 	if (phydev->interface == PHY_INTERFACE_MODE_SGMII) {
-		u32 pause;
-
 		/* Select page 18 */
 		err = marvell_set_page(phydev, 18);
 		if (err < 0)
@@ -871,16 +869,6 @@ static int m88e1510_config_init(struct phy_device *phydev)
 		err = marvell_set_page(phydev, MII_MARVELL_COPPER_PAGE);
 		if (err < 0)
 			return err;
-
-		/* There appears to be a bug in the 88e1512 when used in
-		 * SGMII to copper mode, where the AN advertisement register
-		 * clears the pause bits each time a negotiation occurs.
-		 * This means we can never be truely sure what was advertised,
-		 * so disable Pause support.
-		 */
-		pause = SUPPORTED_Pause | SUPPORTED_Asym_Pause;
-		phydev->supported &= ~pause;
-		phydev->advertising &= ~pause;
 	}
 
 	return m88e1318_config_init(phydev);
-- 
2.20.1


From d7f9e904fcd92de7b91986d9af440b199d483445 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 4 Feb 2019 08:36:06 -0800
Subject: [PATCH 12/21] rxrpc: bad unlock balance in rxrpc_recvmsg

[ Upstream commit 6dce3c20ac429e7a651d728e375853370c796e8d ]

When either "goto wait_interrupted;" or "goto wait_error;"
paths are taken, socket lock has already been released.

This patch fixes following syzbot splat :

WARNING: bad unlock balance detected!
5.0.0-rc4+ #59 Not tainted
-------------------------------------
syz-executor223/8256 is trying to release lock (sk_lock-AF_RXRPC) at:
[<ffffffff86651353>] rxrpc_recvmsg+0x6d3/0x3099 net/rxrpc/recvmsg.c:598
but there are no more locks to release!

other info that might help us debug this:
1 lock held by syz-executor223/8256:
 #0: 00000000fa9ed0f4 (slock-AF_RXRPC){+...}, at: spin_lock_bh include/linux/spinlock.h:334 [inline]
 #0: 00000000fa9ed0f4 (slock-AF_RXRPC){+...}, at: release_sock+0x20/0x1c0 net/core/sock.c:2798

stack backtrace:
CPU: 1 PID: 8256 Comm: syz-executor223 Not tainted 5.0.0-rc4+ #59
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 print_unlock_imbalance_bug kernel/locking/lockdep.c:3391 [inline]
 print_unlock_imbalance_bug.cold+0x114/0x123 kernel/locking/lockdep.c:3368
 __lock_release kernel/locking/lockdep.c:3601 [inline]
 lock_release+0x67e/0xa00 kernel/locking/lockdep.c:3860
 sock_release_ownership include/net/sock.h:1471 [inline]
 release_sock+0x183/0x1c0 net/core/sock.c:2808
 rxrpc_recvmsg+0x6d3/0x3099 net/rxrpc/recvmsg.c:598
 sock_recvmsg_nosec net/socket.c:794 [inline]
 sock_recvmsg net/socket.c:801 [inline]
 sock_recvmsg+0xd0/0x110 net/socket.c:797
 __sys_recvfrom+0x1ff/0x350 net/socket.c:1845
 __do_sys_recvfrom net/socket.c:1863 [inline]
 __se_sys_recvfrom net/socket.c:1859 [inline]
 __x64_sys_recvfrom+0xe1/0x1a0 net/socket.c:1859
 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x446379
Code: e8 2c b3 02 00 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 2b 09 fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007fe5da89fd98 EFLAGS: 00000246 ORIG_RAX: 000000000000002d
RAX: ffffffffffffffda RBX: 00000000006dbc28 RCX: 0000000000446379
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000003
RBP: 00000000006dbc20 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00000000006dbc2c
R13: 0000000000000000 R14: 0000000000000000 R15: 20c49ba5e353f7cf

Fixes: 248f219cb8bc ("rxrpc: Rewrite the data and ack handling code")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: David Howells <dhowells@redhat.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/recvmsg.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index eaf19ebaa964..3f7bb11f3290 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -596,6 +596,7 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	}
 error_no_call:
 	release_sock(&rx->sk);
+error_trace:
 	trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, 0, 0, 0, ret);
 	return ret;
 
@@ -604,7 +605,7 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 wait_error:
 	finish_wait(sk_sleep(&rx->sk), &wait);
 	call = NULL;
-	goto error_no_call;
+	goto error_trace;
 }
 
 /**
-- 
2.20.1


From 874b564aa88f9611f0366ef3b58bcc0567d95215 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 4 Feb 2019 03:27:58 +0800
Subject: [PATCH 13/21] sctp: check and update stream->out_curr when allocating
 stream_out

[ Upstream commit cfe4bd7a257f6d6f81d3458d8c9d9ec4957539e6 ]

Now when using stream reconfig to add out streams, stream->out
will get re-allocated, and all old streams' information will
be copied to the new ones and the old ones will be freed.

So without stream->out_curr updated, next time when trying to
send from stream->out_curr stream, a panic would be caused.

This patch is to check and update stream->out_curr when
allocating stream_out.

v1->v2:
  - define fa_index() to get elem index from stream->out_curr.
v2->v3:
  - repost with no change.

Fixes: 5bbbbe32a431 ("sctp: introduce stream scheduler foundations")
Reported-by: Ying Xu <yinxu@redhat.com>
Reported-by: syzbot+e33a3a138267ca119c7d@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/stream.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index 80e0ae5534ec..f24633114dfd 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -84,6 +84,19 @@ static void fa_zero(struct flex_array *fa, size_t index, size_t count)
 	}
 }
 
+static size_t fa_index(struct flex_array *fa, void *elem, size_t count)
+{
+	size_t index = 0;
+
+	while (count--) {
+		if (elem == flex_array_get(fa, index))
+			break;
+		index++;
+	}
+
+	return index;
+}
+
 /* Migrates chunks from stream queues to new stream queues if needed,
  * but not across associations. Also, removes those chunks to streams
  * higher than the new max.
@@ -147,6 +160,13 @@ static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt,
 
 	if (stream->out) {
 		fa_copy(out, stream->out, 0, min(outcnt, stream->outcnt));
+		if (stream->out_curr) {
+			size_t index = fa_index(stream->out, stream->out_curr,
+						stream->outcnt);
+
+			BUG_ON(index == stream->outcnt);
+			stream->out_curr = flex_array_get(out, index);
+		}
 		fa_free(stream->out);
 	}
 
-- 
2.20.1


From 52b873c98fcc72cc33fc7422d7a59b7faa8a2fa1 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Fri, 1 Feb 2019 15:15:22 +0100
Subject: [PATCH 14/21] sctp: walk the list of asoc safely

[ Upstream commit ba59fb0273076637f0add4311faa990a5eec27c0 ]

In sctp_sendmesg(), when walking the list of endpoint associations, the
association can be dropped from the list, making the list corrupt.
Properly handle this by using list_for_each_entry_safe()

Fixes: 4910280503f3 ("sctp: add support for snd flag SCTP_SENDALL process in sendmsg")
Reported-by: Secunia Research <vuln@secunia.com>
Tested-by: Secunia Research <vuln@secunia.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index b8cebd5a87e5..b7a534f6d7c2 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -2027,7 +2027,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len)
 	struct sctp_endpoint *ep = sctp_sk(sk)->ep;
 	struct sctp_transport *transport = NULL;
 	struct sctp_sndrcvinfo _sinfo, *sinfo;
-	struct sctp_association *asoc;
+	struct sctp_association *asoc, *tmp;
 	struct sctp_cmsgs cmsgs;
 	union sctp_addr *daddr;
 	bool new = false;
@@ -2053,7 +2053,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len)
 
 	/* SCTP_SENDALL process */
 	if ((sflags & SCTP_SENDALL) && sctp_style(sk, UDP)) {
-		list_for_each_entry(asoc, &ep->asocs, asocs) {
+		list_for_each_entry_safe(asoc, tmp, &ep->asocs, asocs) {
 			err = sctp_sendmsg_check_sflags(asoc, sflags, msg,
 							msg_len);
 			if (err == 0)
-- 
2.20.1


From 2cfeb9577e588c6521eb54090fa90b6d027c93bd Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Fri, 1 Feb 2019 11:28:16 +0300
Subject: [PATCH 15/21] skge: potential memory corruption in skge_get_regs()

[ Upstream commit 294c149a209c6196c2de85f512b52ef50f519949 ]

The "p" buffer is 0x4000 bytes long.  B3_RI_WTO_R1 is 0x190.  The value
of "regs->len" is in the 1-0x4000 range.  The bug here is that
"regs->len - B3_RI_WTO_R1" can be a negative value which would lead to
memory corruption and an abrupt crash.

Fixes: c3f8be961808 ("[PATCH] skge: expand ethtool debug register dump")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/skge.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c
index 9c08c3650c02..15dea48e0195 100644
--- a/drivers/net/ethernet/marvell/skge.c
+++ b/drivers/net/ethernet/marvell/skge.c
@@ -152,8 +152,10 @@ static void skge_get_regs(struct net_device *dev, struct ethtool_regs *regs,
 	memset(p, 0, regs->len);
 	memcpy_fromio(p, io, B3_RAM_ADDR);
 
-	memcpy_fromio(p + B3_RI_WTO_R1, io + B3_RI_WTO_R1,
-		      regs->len - B3_RI_WTO_R1);
+	if (regs->len > B3_RI_WTO_R1) {
+		memcpy_fromio(p + B3_RI_WTO_R1, io + B3_RI_WTO_R1,
+			      regs->len - B3_RI_WTO_R1);
+	}
 }
 
 /* Wake on Lan only supported on Yukon chips with rev 1 or above */
-- 
2.20.1


From ae94213c39efa6849eb2c7ccc793bc54081e9876 Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Thu, 31 Jan 2019 20:40:30 +0900
Subject: [PATCH 16/21] virtio_net: Account for tx bytes and packets on sending
 xdp_frames

[ Upstream commit 546f28974d771b124fb0bf7b551b343888cf0419 ]

Previously virtnet_xdp_xmit() did not account for device tx counters,
which caused confusions.
To be consistent with SKBs, account them on freeing xdp_frames.

Reported-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index da500c77c5b9..f6a69b56f3e3 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -502,6 +502,8 @@ static int virtnet_xdp_xmit(struct net_device *dev,
 	struct bpf_prog *xdp_prog;
 	struct send_queue *sq;
 	unsigned int len;
+	int packets = 0;
+	int bytes = 0;
 	int drops = 0;
 	int kicks = 0;
 	int ret, err;
@@ -525,10 +527,18 @@ static int virtnet_xdp_xmit(struct net_device *dev,
 
 	/* Free up any pending old buffers before queueing new ones. */
 	while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) {
-		if (likely(is_xdp_frame(ptr)))
-			xdp_return_frame(ptr_to_xdp(ptr));
-		else
-			napi_consume_skb(ptr, false);
+		if (likely(is_xdp_frame(ptr))) {
+			struct xdp_frame *frame = ptr_to_xdp(ptr);
+
+			bytes += frame->len;
+			xdp_return_frame(frame);
+		} else {
+			struct sk_buff *skb = ptr;
+
+			bytes += skb->len;
+			napi_consume_skb(skb, false);
+		}
+		packets++;
 	}
 
 	for (i = 0; i < n; i++) {
@@ -548,6 +558,8 @@ static int virtnet_xdp_xmit(struct net_device *dev,
 	}
 out:
 	u64_stats_update_begin(&sq->stats.syncp);
+	sq->stats.bytes += bytes;
+	sq->stats.packets += packets;
 	sq->stats.xdp_tx += n;
 	sq->stats.xdp_tx_drops += drops;
 	sq->stats.kicks += kicks;
-- 
2.20.1


From a19db132b99afd89eb5b87f89a51892f3362f5ac Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Thu, 31 Jan 2019 14:31:48 -0500
Subject: [PATCH 17/21] bnxt_en: Disable interrupts when allocating CP rings or
 NQs.

[ Upstream commit 5e66e35aab335b83d9ffb220d8a3a13986a7a60e ]

When calling firmware to allocate a CP ring or NQ, an interrupt associated
with that ring may be generated immediately before the doorbell is even
setup after the firmware call returns.  When servicing the interrupt, the
driver may crash when trying to access the doorbell.

Fix it by disabling interrupt on that vector until the doorbell is
set up.

Fixes: 697197e5a173 ("bnxt_en: Re-structure doorbells.")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 5d21c14853ac..a979898efe33 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -4903,12 +4903,18 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp)
 		struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
 		struct bnxt_ring_struct *ring = &cpr->cp_ring_struct;
 		u32 map_idx = ring->map_idx;
+		unsigned int vector;
 
+		vector = bp->irq_tbl[map_idx].vector;
+		disable_irq_nosync(vector);
 		rc = hwrm_ring_alloc_send_msg(bp, ring, type, map_idx);
-		if (rc)
+		if (rc) {
+			enable_irq(vector);
 			goto err_out;
+		}
 		bnxt_set_db(bp, &cpr->cp_db, type, map_idx, ring->fw_ring_id);
 		bnxt_db_nq(bp, &cpr->cp_db, cpr->cp_raw_cons);
+		enable_irq(vector);
 		bp->grp_info[i].cp_fw_ring_id = ring->fw_ring_id;
 
 		if (!i) {
-- 
2.20.1


From e8241b2716fbae77df3dc8d897ea9f098c133960 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 4 Feb 2019 14:50:38 +0000
Subject: [PATCH 18/21] net: cls_flower: Remove filter from mask before freeing
 it

[ Upstream commit c1f7e02979edd7a3a3e69fe04be60b1d650dc8a7 ]

In fl_change(), when adding a new rule (i.e. fold == NULL), a driver may
reject the new rule, for example due to resource exhaustion. By that
point, the new rule was already assigned a mask, and it was added to
that mask's hash table. The clean-up path that's invoked as a result of
the rejection however neglects to undo the hash table addition, and
proceeds to free the new rule, thus leaving a dangling pointer in the
hash table.

Fix by removing fnew from the mask's hash table before it is freed.

Fixes: 35cc3cefc4de ("net/sched: cls_flower: Reject duplicated rules also under skip_sw")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_flower.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 45bc2b72dc1c..2f64e3538127 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -1257,7 +1257,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
 	if (!tc_skip_hw(fnew->flags)) {
 		err = fl_hw_replace_filter(tp, fnew, extack);
 		if (err)
-			goto errout_mask;
+			goto errout_mask_ht;
 	}
 
 	if (!tc_in_hw(fnew->flags))
@@ -1287,6 +1287,10 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
 	kfree(mask);
 	return 0;
 
+errout_mask_ht:
+	rhashtable_remove_fast(&fnew->mask->ht, &fnew->ht_node,
+			       fnew->mask->filter_ht_params);
+
 errout_mask:
 	fl_mask_put(head, fnew->mask, false);
 
-- 
2.20.1


From 3583672f3c635c9befb70182143a3d5f1dd909e7 Mon Sep 17 00:00:00 2001
From: Arun Parameswaran <arun.parameswaran@broadcom.com>
Date: Thu, 7 Feb 2019 16:01:18 -0800
Subject: [PATCH 19/21] net: dsa: b53: Fix for failure when irq is not defined
 in dt

[ Upstream commit 39841cc1cbb69344539c98a1fa9d858ed124c7ba ]

Fixes the issues with non BCM58XX chips in the b53 driver
failing, when the irq is not specified in the device tree.

Removed the check for BCM58XX in b53_srab_prepare_irq(),
so the 'port->irq' will be set to '-EXIO' if the irq is not
specified in the device tree.

Fixes: 16994374a6fc ("net: dsa: b53: Make SRAB driver manage port interrupts")
Fixes: b2ddc48a81b5 ("net: dsa: b53: Do not fail when IRQ are not initialized")
Signed-off-by: Arun Parameswaran <arun.parameswaran@broadcom.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/b53/b53_srab.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/dsa/b53/b53_srab.c b/drivers/net/dsa/b53/b53_srab.c
index 90f514252987..d9c56a779c08 100644
--- a/drivers/net/dsa/b53/b53_srab.c
+++ b/drivers/net/dsa/b53/b53_srab.c
@@ -511,9 +511,6 @@ static void b53_srab_prepare_irq(struct platform_device *pdev)
 	/* Clear all pending interrupts */
 	writel(0xffffffff, priv->regs + B53_SRAB_INTR);
 
-	if (dev->pdata && dev->pdata->chip_id != BCM58XX_DEVICE_ID)
-		return;
-
 	for (i = 0; i < B53_N_PORTS; i++) {
 		port = &priv->port_intrs[i];
 
-- 
2.20.1


From a8a6184716e28746e4fe472523522255a6d25efc Mon Sep 17 00:00:00 2001
From: Guy Shattah <sguy@mellanox.com>
Date: Mon, 28 Jan 2019 13:58:07 +0000
Subject: [PATCH 20/21] net/mlx5e: Use the inner headers to determine tc/pedit
 offload limitation on decap flows

[ Upstream commit 1651925d403e077e3fc86f961905e27c6810e132 ]

In packets that need to be decaped the internal headers
have to be checked, not the external ones.

Fixes: bdd66ac0aeed ("net/mlx5e: Disallow TC offloading of unsupported match/action combinations")
Signed-off-by: Guy Shattah <sguy@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 9dabe9d4b279..4e0151918db1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2133,6 +2133,7 @@ static bool csum_offload_supported(struct mlx5e_priv *priv,
 
 static bool modify_header_match_supported(struct mlx5_flow_spec *spec,
 					  struct tcf_exts *exts,
+					  u32 match_actions,
 					  struct netlink_ext_ack *extack)
 {
 	const struct tc_action *a;
@@ -2143,7 +2144,11 @@ static bool modify_header_match_supported(struct mlx5_flow_spec *spec,
 	u16 ethertype;
 	int nkeys, i;
 
-	headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, outer_headers);
+	if (match_actions & MLX5_FLOW_CONTEXT_ACTION_DECAP)
+		headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, inner_headers);
+	else
+		headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, outer_headers);
+
 	ethertype = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ethertype);
 
 	/* for non-IP we only re-write MACs, so we're okay */
@@ -2200,7 +2205,7 @@ static bool actions_match_supported(struct mlx5e_priv *priv,
 
 	if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
 		return modify_header_match_supported(&parse_attr->spec, exts,
-						     extack);
+						     actions, extack);
 
 	return true;
 }
-- 
2.20.1


From a5454f85390e2b0db9d81dfa8b774f1221ae1091 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 3 Dec 2018 22:14:04 -0800
Subject: [PATCH 21/21] net/mlx5e: Force CHECKSUM_UNNECESSARY for short
 ethernet frames

[ Upstream commit e8c8b53ccaff568fef4c13a6ccaf08bf241aa01a ]

When an ethernet frame is padded to meet the minimum ethernet frame
size, the padding octets are not covered by the hardware checksum.
Fortunately the padding octets are usually zero's, which don't affect
checksum. However, we have a switch which pads non-zero octets, this
causes kernel hardware checksum fault repeatedly.

Prior to:
commit '88078d98d1bb ("net: pskb_trim_rcsum() and CHECKSUM_COMPLETE ...")'
skb checksum was forced to be CHECKSUM_NONE when padding is detected.
After it, we need to keep skb->csum updated, like what we do for RXFCS.
However, fixing up CHECKSUM_COMPLETE requires to verify and parse IP
headers, it is not worthy the effort as the packets are so small that
CHECKSUM_COMPLETE can't save anything.

Fixes: 88078d98d1bb ("net: pskb_trim_rcsum() and CHECKSUM_COMPLETE are friends"),
Cc: Eric Dumazet <edumazet@google.com>
Cc: Tariq Toukan <tariqt@mellanox.com>
Cc: Nikola Ciprich <nikola.ciprich@linuxbox.cz>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 0b5ef6d4e815..7185f0dd58eb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -732,6 +732,8 @@ static u8 get_ip_proto(struct sk_buff *skb, int network_depth, __be16 proto)
 					    ((struct ipv6hdr *)ip_p)->nexthdr;
 }
 
+#define short_frame(size) ((size) <= ETH_ZLEN + ETH_FCS_LEN)
+
 static inline void mlx5e_handle_csum(struct net_device *netdev,
 				     struct mlx5_cqe64 *cqe,
 				     struct mlx5e_rq *rq,
@@ -754,6 +756,17 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 	if (unlikely(test_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &rq->state)))
 		goto csum_unnecessary;
 
+	/* CQE csum doesn't cover padding octets in short ethernet
+	 * frames. And the pad field is appended prior to calculating
+	 * and appending the FCS field.
+	 *
+	 * Detecting these padded frames requires to verify and parse
+	 * IP headers, so we simply force all those small frames to be
+	 * CHECKSUM_UNNECESSARY even if they are not padded.
+	 */
+	if (short_frame(skb->len))
+		goto csum_unnecessary;
+
 	if (likely(is_last_ethertype_ip(skb, &network_depth, &proto))) {
 		if (unlikely(get_ip_proto(skb, network_depth, proto) == IPPROTO_SCTP))
 			goto csum_unnecessary;
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Sat, Feb 09, 2019 at 03:21:32PM -0800, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.19 and
> v4.20 -stable, respectively.

Thanks for these, all now queued up.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 107 bytes --]


Please queue up the following networking bug fixes for v4.19 and v4.20
-stable, respectively.

Thank you.

[-- Attachment #2: net_419.mbox --]
[-- Type: Application/Octet-Stream, Size: 45340 bytes --]

From 588dee24dc1382c7031f4e77ce7bddb7cf005a4b Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Thu, 17 Jan 2019 11:27:22 +0100
Subject: [PATCH 01/20] af_packet: fix raw sockets over 6in4 tunnel

[ Upstream commit 88a8121dc1d3d0dbddd411b79ed236b6b6ea415c ]

Since commit cb9f1b783850, scapy (which uses an AF_PACKET socket in
SOCK_RAW mode) is unable to send a basic icmp packet over a sit tunnel:

Here is a example of the setup:
$ ip link set ntfp2 up
$ ip addr add 10.125.0.1/24 dev ntfp2
$ ip tunnel add tun1 mode sit ttl 64 local 10.125.0.1 remote 10.125.0.2 dev ntfp2
$ ip addr add fd00:cafe:cafe::1/128 dev tun1
$ ip link set dev tun1 up
$ ip route add fd00:200::/64 dev tun1
$ scapy
>>> p = []
>>> p += IPv6(src='fd00:100::1', dst='fd00:200::1')/ICMPv6EchoRequest()
>>> send(p, count=1, inter=0.1)
>>> quit()
$ ip -s link ls dev tun1 | grep -A1 "TX.*errors"
    TX: bytes  packets  errors  dropped carrier collsns
    0          0        1       0       0       0

The problem is that the network offset is set to the hard_header_len of the
output device (tun1, ie 14 + 20) and in our case, because the packet is
small (48 bytes) the pskb_inet_may_pull() fails (it tries to pull 40 bytes
(ipv6 header) starting from the network offset).

This problem is more generally related to device with variable hard header
length. To avoid a too intrusive patch in the current release, a (ugly)
workaround is proposed in this patch. It has to be cleaned up in net-next.

Link: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=993675a3100b1
Link: http://patchwork.ozlabs.org/patch/1024489/
Fixes: cb9f1b783850 ("ip: validate header length on virtual device xmit")
CC: Willem de Bruijn <willemb@google.com>
CC: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index b6ea0fadb34f..c76c21604ffd 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2887,7 +2887,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 			goto out_free;
 	} else if (reserve) {
 		skb_reserve(skb, -reserve);
-		if (len < reserve)
+		if (len < reserve + sizeof(struct ipv6hdr) &&
+		    dev->min_header_len != dev->hard_header_len)
 			skb_reset_network_header(skb);
 	}
 
-- 
2.20.1


From 496f9aa06c11464c0142b82f3c38168f7092ae6f Mon Sep 17 00:00:00 2001
From: John David Anglin <dave.anglin@bell.net>
Date: Mon, 11 Feb 2019 13:40:21 -0500
Subject: [PATCH 02/20] dsa: mv88e6xxx: Ensure all pending interrupts are
 handled prior to exit

[ Upstream commit 7c0db24cc431e2196d98a5d5ddaa9088e2fcbfe5 ]

The GPIO interrupt controller on the espressobin board only supports edge interrupts.
If one enables the use of hardware interrupts in the device tree for the 88E6341, it is
possible to miss an edge.  When this happens, the INTn pin on the Marvell switch is
stuck low and no further interrupts occur.

I found after adding debug statements to mv88e6xxx_g1_irq_thread_work() that there is
a race in handling device interrupts (e.g. PHY link interrupts).  Some interrupts are
directly cleared by reading the Global 1 status register.  However, the device interrupt
flag, for example, is not cleared until all the unmasked SERDES and PHY ports are serviced.
This is done by reading the relevant SERDES and PHY status register.

The code only services interrupts whose status bit is set at the time of reading its status
register.  If an interrupt event occurs after its status is read and before all interrupts
are serviced, then this event will not be serviced and the INTn output pin will remain low.

This is not a problem with polling or level interrupts since the handler will be called
again to process the event.  However, it's a big problem when using level interrupts.

The fix presented here is to add a loop around the code servicing switch interrupts.  If
any pending interrupts remain after the current set has been handled, we loop and process
the new set.  If there are no pending interrupts after servicing, we are sure that INTn has
gone high and we will get an edge when a new event occurs.

Tested on espressobin board.

Fixes: dc30c35be720 ("net: dsa: mv88e6xxx: Implement interrupt support.")
Signed-off-by:  John David Anglin <dave.anglin@bell.net>
Tested-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 28 ++++++++++++++++++++++------
 1 file changed, 22 insertions(+), 6 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 258918d8a416..9f697a5b8e3d 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -261,6 +261,7 @@ static irqreturn_t mv88e6xxx_g1_irq_thread_work(struct mv88e6xxx_chip *chip)
 	unsigned int sub_irq;
 	unsigned int n;
 	u16 reg;
+	u16 ctl1;
 	int err;
 
 	mutex_lock(&chip->reg_lock);
@@ -270,13 +271,28 @@ static irqreturn_t mv88e6xxx_g1_irq_thread_work(struct mv88e6xxx_chip *chip)
 	if (err)
 		goto out;
 
-	for (n = 0; n < chip->g1_irq.nirqs; ++n) {
-		if (reg & (1 << n)) {
-			sub_irq = irq_find_mapping(chip->g1_irq.domain, n);
-			handle_nested_irq(sub_irq);
-			++nhandled;
+	do {
+		for (n = 0; n < chip->g1_irq.nirqs; ++n) {
+			if (reg & (1 << n)) {
+				sub_irq = irq_find_mapping(chip->g1_irq.domain,
+							   n);
+				handle_nested_irq(sub_irq);
+				++nhandled;
+			}
 		}
-	}
+
+		mutex_lock(&chip->reg_lock);
+		err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_CTL1, &ctl1);
+		if (err)
+			goto unlock;
+		err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_STS, &reg);
+unlock:
+		mutex_unlock(&chip->reg_lock);
+		if (err)
+			goto out;
+		ctl1 &= GENMASK(chip->g1_irq.nirqs, 0);
+	} while (reg & ctl1);
+
 out:
 	return (nhandled > 0 ? IRQ_HANDLED : IRQ_NONE);
 }
-- 
2.20.1


From b440532e5e5cb85526050c513c3bc947a29b81d7 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Sun, 17 Feb 2019 07:18:41 +0000
Subject: [PATCH 03/20] mlxsw: __mlxsw_sp_port_headroom_set(): Fix a use of
 local variable

[ Upstream commit 289460404f6947ef1c38e67d680be9a84161250b ]

The function-local variable "delay" enters the loop interpreted as delay
in bits. However, inside the loop it gets overwritten by the result of
mlxsw_sp_pg_buf_delay_get(), and thus leaves the loop as quantity in
cells. Thus on second and further loop iterations, the headroom for a
given priority is configured with a wrong size.

Fix by introducing a loop-local variable, delay_cells. Rename thres to
thres_cells for consistency.

Fixes: f417f04da589 ("mlxsw: spectrum: Refactor port buffer configuration")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index d64cd8d44d83..a12b5710891e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -841,8 +841,9 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu,
 	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
 		bool configure = false;
 		bool pfc = false;
+		u16 thres_cells;
+		u16 delay_cells;
 		bool lossy;
-		u16 thres;
 
 		for (j = 0; j < IEEE_8021QAZ_MAX_TCS; j++) {
 			if (prio_tc[j] == i) {
@@ -856,10 +857,11 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu,
 			continue;
 
 		lossy = !(pfc || pause_en);
-		thres = mlxsw_sp_pg_buf_threshold_get(mlxsw_sp, mtu);
-		delay = mlxsw_sp_pg_buf_delay_get(mlxsw_sp, mtu, delay, pfc,
-						  pause_en);
-		mlxsw_sp_pg_buf_pack(pbmc_pl, i, thres + delay, thres, lossy);
+		thres_cells = mlxsw_sp_pg_buf_threshold_get(mlxsw_sp, mtu);
+		delay_cells = mlxsw_sp_pg_buf_delay_get(mlxsw_sp, mtu, delay,
+							pfc, pause_en);
+		mlxsw_sp_pg_buf_pack(pbmc_pl, i, thres_cells + delay_cells,
+				     thres_cells, lossy);
 	}
 
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pbmc), pbmc_pl);
-- 
2.20.1


From 47015fd76e701c3e19f021f4734221498b40b4a6 Mon Sep 17 00:00:00 2001
From: Mao Wenan <maowenan@huawei.com>
Date: Mon, 18 Feb 2019 10:44:44 +0800
Subject: [PATCH 04/20] net: crypto set sk to NULL when af_alg_release.

[ Upstream commit 9060cb719e61b685ec0102574e10337fa5f445ea ]

KASAN has found use-after-free in sockfs_setattr.
The existed commit 6d8c50dcb029 ("socket: close race condition between sock_close()
and sockfs_setattr()") is to fix this simillar issue, but it seems to ignore
that crypto module forgets to set the sk to NULL after af_alg_release.

KASAN report details as below:
BUG: KASAN: use-after-free in sockfs_setattr+0x120/0x150
Write of size 4 at addr ffff88837b956128 by task syz-executor0/4186

CPU: 2 PID: 4186 Comm: syz-executor0 Not tainted xxx + #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS
1.10.2-1ubuntu1 04/01/2014
Call Trace:
 dump_stack+0xca/0x13e
 print_address_description+0x79/0x330
 ? vprintk_func+0x5e/0xf0
 kasan_report+0x18a/0x2e0
 ? sockfs_setattr+0x120/0x150
 sockfs_setattr+0x120/0x150
 ? sock_register+0x2d0/0x2d0
 notify_change+0x90c/0xd40
 ? chown_common+0x2ef/0x510
 chown_common+0x2ef/0x510
 ? chmod_common+0x3b0/0x3b0
 ? __lock_is_held+0xbc/0x160
 ? __sb_start_write+0x13d/0x2b0
 ? __mnt_want_write+0x19a/0x250
 do_fchownat+0x15c/0x190
 ? __ia32_sys_chmod+0x80/0x80
 ? trace_hardirqs_on_thunk+0x1a/0x1c
 __x64_sys_fchownat+0xbf/0x160
 ? lockdep_hardirqs_on+0x39a/0x5e0
 do_syscall_64+0xc8/0x580
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x462589
Code: f7 d8 64 89 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 48 89 f8 48 89
f7 48 89 d6 48 89
ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3
48 c7 c1 bc ff ff
ff f7 d8 64 89 01 48
RSP: 002b:00007fb4b2c83c58 EFLAGS: 00000246 ORIG_RAX: 0000000000000104
RAX: ffffffffffffffda RBX: 000000000072bfa0 RCX: 0000000000462589
RDX: 0000000000000000 RSI: 00000000200000c0 RDI: 0000000000000007
RBP: 0000000000000005 R08: 0000000000001000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00007fb4b2c846bc
R13: 00000000004bc733 R14: 00000000006f5138 R15: 00000000ffffffff

Allocated by task 4185:
 kasan_kmalloc+0xa0/0xd0
 __kmalloc+0x14a/0x350
 sk_prot_alloc+0xf6/0x290
 sk_alloc+0x3d/0xc00
 af_alg_accept+0x9e/0x670
 hash_accept+0x4a3/0x650
 __sys_accept4+0x306/0x5c0
 __x64_sys_accept4+0x98/0x100
 do_syscall_64+0xc8/0x580
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Freed by task 4184:
 __kasan_slab_free+0x12e/0x180
 kfree+0xeb/0x2f0
 __sk_destruct+0x4e6/0x6a0
 sk_destruct+0x48/0x70
 __sk_free+0xa9/0x270
 sk_free+0x2a/0x30
 af_alg_release+0x5c/0x70
 __sock_release+0xd3/0x280
 sock_close+0x1a/0x20
 __fput+0x27f/0x7f0
 task_work_run+0x136/0x1b0
 exit_to_usermode_loop+0x1a7/0x1d0
 do_syscall_64+0x461/0x580
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Syzkaller reproducer:
r0 = perf_event_open(&(0x7f0000000000)={0x0, 0x70, 0x0, 0x0, 0x0, 0x0,
0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, @perf_config_ext}, 0x0, 0x0,
0xffffffffffffffff, 0x0)
r1 = socket$alg(0x26, 0x5, 0x0)
getrusage(0x0, 0x0)
bind(r1, &(0x7f00000001c0)=@alg={0x26, 'hash\x00', 0x0, 0x0,
'sha256-ssse3\x00'}, 0x80)
r2 = accept(r1, 0x0, 0x0)
r3 = accept4$unix(r2, 0x0, 0x0, 0x0)
r4 = dup3(r3, r0, 0x0)
fchownat(r4, &(0x7f00000000c0)='\x00', 0x0, 0x0, 0x1000)

Fixes: 6d8c50dcb029 ("socket: close race condition between sock_close() and sockfs_setattr()")
Signed-off-by: Mao Wenan <maowenan@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 crypto/af_alg.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index 17eb09d222ff..ec78a04eb136 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -122,8 +122,10 @@ static void alg_do_release(const struct af_alg_type *type, void *private)
 
 int af_alg_release(struct socket *sock)
 {
-	if (sock->sk)
+	if (sock->sk) {
 		sock_put(sock->sk);
+		sock->sk = NULL;
+	}
 	return 0;
 }
 EXPORT_SYMBOL_GPL(af_alg_release);
-- 
2.20.1


From 4632cbad781bae26d3b9fc6ce190f57475b6036a Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens <hauke.mehrtens@intel.com>
Date: Fri, 15 Feb 2019 17:58:54 +0100
Subject: [PATCH 05/20] net: Fix for_each_netdev_feature on Big endian

[ Upstream commit 3b89ea9c5902acccdbbdec307c85edd1bf52515e ]

The features attribute is of type u64 and stored in the native endianes on
the system. The for_each_set_bit() macro takes a pointer to a 32 bit array
and goes over the bits in this area. On little Endian systems this also
works with an u64 as the most significant bit is on the highest address,
but on big endian the words are swapped. When we expect bit 15 here we get
bit 47 (15 + 32).

This patch converts it more or less to its own for_each_set_bit()
implementation which works on 64 bit integers directly. This is then
completely in host endianness and should work like expected.

Fixes: fd867d51f ("net/core: generic support for disabling netdev features down stack")
Signed-off-by: Hauke Mehrtens <hauke.mehrtens@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdev_features.h | 23 +++++++++++++++++++++--
 net/core/dev.c                  |  4 ++--
 2 files changed, 23 insertions(+), 4 deletions(-)

diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index 2b2a6dce1630..fce28562bed2 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -11,6 +11,7 @@
 #define _LINUX_NETDEV_FEATURES_H
 
 #include <linux/types.h>
+#include <asm/byteorder.h>
 
 typedef u64 netdev_features_t;
 
@@ -154,8 +155,26 @@ enum {
 #define NETIF_F_HW_TLS_TX	__NETIF_F(HW_TLS_TX)
 #define NETIF_F_HW_TLS_RX	__NETIF_F(HW_TLS_RX)
 
-#define for_each_netdev_feature(mask_addr, bit)	\
-	for_each_set_bit(bit, (unsigned long *)mask_addr, NETDEV_FEATURE_COUNT)
+/* Finds the next feature with the highest number of the range of start till 0.
+ */
+static inline int find_next_netdev_feature(u64 feature, unsigned long start)
+{
+	/* like BITMAP_LAST_WORD_MASK() for u64
+	 * this sets the most significant 64 - start to 0.
+	 */
+	feature &= ~0ULL >> (-start & ((sizeof(feature) * 8) - 1));
+
+	return fls64(feature) - 1;
+}
+
+/* This goes for the MSB to the LSB through the set feature bits,
+ * mask_addr should be a u64 and bit an int
+ */
+#define for_each_netdev_feature(mask_addr, bit)				\
+	for ((bit) = find_next_netdev_feature((mask_addr),		\
+					      NETDEV_FEATURE_COUNT);	\
+	     (bit) >= 0;						\
+	     (bit) = find_next_netdev_feature((mask_addr), (bit) - 1))
 
 /* Features valid for ethtool to change */
 /* = all defined minus driver/device-class-related */
diff --git a/net/core/dev.c b/net/core/dev.c
index af097ca9cb4f..5c8c0a572ee9 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8039,7 +8039,7 @@ static netdev_features_t netdev_sync_upper_features(struct net_device *lower,
 	netdev_features_t feature;
 	int feature_bit;
 
-	for_each_netdev_feature(&upper_disables, feature_bit) {
+	for_each_netdev_feature(upper_disables, feature_bit) {
 		feature = __NETIF_F_BIT(feature_bit);
 		if (!(upper->wanted_features & feature)
 		    && (features & feature)) {
@@ -8059,7 +8059,7 @@ static void netdev_sync_lower_features(struct net_device *upper,
 	netdev_features_t feature;
 	int feature_bit;
 
-	for_each_netdev_feature(&upper_disables, feature_bit) {
+	for_each_netdev_feature(upper_disables, feature_bit) {
 		feature = __NETIF_F_BIT(feature_bit);
 		if (!(features & feature) && (lower->features & feature)) {
 			netdev_dbg(upper, "Disabling feature %pNF on lower dev %s.\n",
-- 
2.20.1


From 70eaa93bce0dbd87601ee34a7dbc0f507cb67967 Mon Sep 17 00:00:00 2001
From: Zhiqiang Liu <liuzhiqiang26@huawei.com>
Date: Mon, 11 Feb 2019 10:57:46 +0800
Subject: [PATCH 06/20] net: fix IPv6 prefix route residue

[ Upstream commit e75913c93f7cd5f338ab373c34c93a655bd309cb ]

Follow those steps:
 # ip addr add 2001:123::1/32 dev eth0
 # ip addr add 2001:123:456::2/64 dev eth0
 # ip addr del 2001:123::1/32 dev eth0
 # ip addr del 2001:123:456::2/64 dev eth0
and then prefix route of 2001:123::1/32 will still exist.

This is because ipv6_prefix_equal in check_cleanup_prefix_route
func does not check whether two IPv6 addresses have the same
prefix length. If the prefix of one address starts with another
shorter address prefix, even though their prefix lengths are
different, the return value of ipv6_prefix_equal is true.

Here I add a check of whether two addresses have the same prefix
to decide whether their prefixes are equal.

Fixes: 5b84efecb7d9 ("ipv6 addrconf: don't cleanup prefix route for IFA_F_NOPREFIXROUTE")
Signed-off-by: Zhiqiang Liu <liuzhiqiang26@huawei.com>
Reported-by: Wenhao Zhang <zhangwenhao8@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 3dfc50cd86d6..c57efd5c5b38 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1148,7 +1148,8 @@ check_cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long *expires)
 	list_for_each_entry(ifa, &idev->addr_list, if_list) {
 		if (ifa == ifp)
 			continue;
-		if (!ipv6_prefix_equal(&ifa->addr, &ifp->addr,
+		if (ifa->prefix_len != ifp->prefix_len ||
+		    !ipv6_prefix_equal(&ifa->addr, &ifp->addr,
 				       ifp->prefix_len))
 			continue;
 		if (ifa->flags & (IFA_F_PERMANENT | IFA_F_NOPREFIXROUTE))
-- 
2.20.1


From 26fe8ee79ba81174ba2efde2000c6a1d08f2be01 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Fri, 15 Feb 2019 15:10:32 +0100
Subject: [PATCH 07/20] net: ip6_gre: initialize erspan_ver just for erspan
 tunnels

[ Upstream commit 4974d5f678abb34401558559d47e2ea3d1c15cba ]

After commit c706863bc890 ("net: ip6_gre: always reports o_key to
userspace"), ip6gre and ip6gretap tunnels started reporting TUNNEL_KEY
output flag even if it is not configured.
ip6gre_fill_info checks erspan_ver value to add TUNNEL_KEY for
erspan tunnels, however in commit 84581bdae9587 ("erspan: set
erspan_ver to 1 by default when adding an erspan dev")
erspan_ver is initialized to 1 even for ip6gre or ip6gretap
Fix the issue moving erspan_ver initialization in a dedicated routine

Fixes: c706863bc890 ("net: ip6_gre: always reports o_key to userspace")
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Reviewed-by: Greg Rose <gvrose8192@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 34 ++++++++++++++++++++--------------
 1 file changed, 20 insertions(+), 14 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index be04877b3827..faed98dab913 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1735,6 +1735,24 @@ static int ip6erspan_tap_validate(struct nlattr *tb[], struct nlattr *data[],
 	return 0;
 }
 
+static void ip6erspan_set_version(struct nlattr *data[],
+				  struct __ip6_tnl_parm *parms)
+{
+	parms->erspan_ver = 1;
+	if (data[IFLA_GRE_ERSPAN_VER])
+		parms->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]);
+
+	if (parms->erspan_ver == 1) {
+		if (data[IFLA_GRE_ERSPAN_INDEX])
+			parms->index = nla_get_u32(data[IFLA_GRE_ERSPAN_INDEX]);
+	} else if (parms->erspan_ver == 2) {
+		if (data[IFLA_GRE_ERSPAN_DIR])
+			parms->dir = nla_get_u8(data[IFLA_GRE_ERSPAN_DIR]);
+		if (data[IFLA_GRE_ERSPAN_HWID])
+			parms->hwid = nla_get_u16(data[IFLA_GRE_ERSPAN_HWID]);
+	}
+}
+
 static void ip6gre_netlink_parms(struct nlattr *data[],
 				struct __ip6_tnl_parm *parms)
 {
@@ -1783,20 +1801,6 @@ static void ip6gre_netlink_parms(struct nlattr *data[],
 
 	if (data[IFLA_GRE_COLLECT_METADATA])
 		parms->collect_md = true;
-
-	parms->erspan_ver = 1;
-	if (data[IFLA_GRE_ERSPAN_VER])
-		parms->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]);
-
-	if (parms->erspan_ver == 1) {
-		if (data[IFLA_GRE_ERSPAN_INDEX])
-			parms->index = nla_get_u32(data[IFLA_GRE_ERSPAN_INDEX]);
-	} else if (parms->erspan_ver == 2) {
-		if (data[IFLA_GRE_ERSPAN_DIR])
-			parms->dir = nla_get_u8(data[IFLA_GRE_ERSPAN_DIR]);
-		if (data[IFLA_GRE_ERSPAN_HWID])
-			parms->hwid = nla_get_u16(data[IFLA_GRE_ERSPAN_HWID]);
-	}
 }
 
 static int ip6gre_tap_init(struct net_device *dev)
@@ -2225,6 +2229,7 @@ static int ip6erspan_newlink(struct net *src_net, struct net_device *dev,
 	int err;
 
 	ip6gre_netlink_parms(data, &nt->parms);
+	ip6erspan_set_version(data, &nt->parms);
 	ign = net_generic(net, ip6gre_net_id);
 
 	if (nt->parms.collect_md) {
@@ -2270,6 +2275,7 @@ static int ip6erspan_changelink(struct net_device *dev, struct nlattr *tb[],
 	if (IS_ERR(t))
 		return PTR_ERR(t);
 
+	ip6erspan_set_version(data, &p);
 	ip6gre_tunnel_unlink_md(ign, t);
 	ip6gre_tunnel_unlink(ign, t);
 	ip6erspan_tnl_change(t, &p, !tb[IFLA_MTU]);
-- 
2.20.1


From cb1edba348cbcb10135076be79f25f0411ec1096 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Wed, 6 Feb 2019 19:18:04 +0100
Subject: [PATCH 08/20] net: ipv4: use a dedicated counter for icmp_v4 redirect
 packets

[ Upstream commit c09551c6ff7fe16a79a42133bcecba5fc2fc3291 ]

According to the algorithm described in the comment block at the
beginning of ip_rt_send_redirect, the host should try to send
'ip_rt_redirect_number' ICMP redirect packets with an exponential
backoff and then stop sending them at all assuming that the destination
ignores redirects.
If the device has previously sent some ICMP error packets that are
rate-limited (e.g TTL expired) and continues to receive traffic,
the redirect packets will never be transmitted. This happens since
peer->rate_tokens will be typically greater than 'ip_rt_redirect_number'
and so it will never be reset even if the redirect silence timeout
(ip_rt_redirect_silence) has elapsed without receiving any packet
requiring redirects.

Fix it by using a dedicated counter for the number of ICMP redirect
packets that has been sent by the host

I have not been able to identify a given commit that introduced the
issue since ip_rt_send_redirect implements the same rate-limiting
algorithm from commit 1da177e4c3f4 ("Linux-2.6.12-rc2")

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inetpeer.h | 1 +
 net/ipv4/inetpeer.c    | 1 +
 net/ipv4/route.c       | 7 +++++--
 3 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index 00b5e7825508..74ff688568a0 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -39,6 +39,7 @@ struct inet_peer {
 
 	u32			metrics[RTAX_MAX];
 	u32			rate_tokens;	/* rate limiting for ICMP */
+	u32			n_redirects;
 	unsigned long		rate_last;
 	/*
 	 * Once inet_peer is queued for deletion (refcnt == 0), following field
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index d757b9642d0d..be778599bfed 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -216,6 +216,7 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base,
 			atomic_set(&p->rid, 0);
 			p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW;
 			p->rate_tokens = 0;
+			p->n_redirects = 0;
 			/* 60*HZ is arbitrary, but chosen enough high so that the first
 			 * calculation of tokens is at its maximum.
 			 */
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 8501554e96a4..436b46c0e687 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -887,13 +887,15 @@ void ip_rt_send_redirect(struct sk_buff *skb)
 	/* No redirected packets during ip_rt_redirect_silence;
 	 * reset the algorithm.
 	 */
-	if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence))
+	if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence)) {
 		peer->rate_tokens = 0;
+		peer->n_redirects = 0;
+	}
 
 	/* Too many ignored redirects; do not send anything
 	 * set dst.rate_last to the last seen redirected packet.
 	 */
-	if (peer->rate_tokens >= ip_rt_redirect_number) {
+	if (peer->n_redirects >= ip_rt_redirect_number) {
 		peer->rate_last = jiffies;
 		goto out_put_peer;
 	}
@@ -910,6 +912,7 @@ void ip_rt_send_redirect(struct sk_buff *skb)
 		icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw);
 		peer->rate_last = jiffies;
 		++peer->rate_tokens;
+		++peer->n_redirects;
 #ifdef CONFIG_IP_ROUTE_VERBOSE
 		if (log_martians &&
 		    peer->rate_tokens == ip_rt_redirect_number)
-- 
2.20.1


From 37ba832b65c5e28c94072fc65ef361508d39cb8c Mon Sep 17 00:00:00 2001
From: Paul Kocialkowski <paul.kocialkowski@bootlin.com>
Date: Fri, 15 Feb 2019 17:17:08 +0100
Subject: [PATCH 09/20] net: phy: xgmiitorgmii: Support generic PHY status read

[ Upstream commit 197f9ab7f08ce4b9ece662f747c3991b2f0fbb57 ]

Some PHY drivers like the generic one do not provide a read_status
callback on their own but rely on genphy_read_status being called
directly.

With the current code, this results in a NULL function pointer call.
Call genphy_read_status instead when there is no specific callback.

Fixes: f411a6160bd4 ("net: phy: Add gmiitorgmii converter support")
Signed-off-by: Paul Kocialkowski <paul.kocialkowski@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/xilinx_gmii2rgmii.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/xilinx_gmii2rgmii.c b/drivers/net/phy/xilinx_gmii2rgmii.c
index 74a8782313cf..bd6084e315de 100644
--- a/drivers/net/phy/xilinx_gmii2rgmii.c
+++ b/drivers/net/phy/xilinx_gmii2rgmii.c
@@ -44,7 +44,10 @@ static int xgmiitorgmii_read_status(struct phy_device *phydev)
 	u16 val = 0;
 	int err;
 
-	err = priv->phy_drv->read_status(phydev);
+	if (priv->phy_drv->read_status)
+		err = priv->phy_drv->read_status(phydev);
+	else
+		err = genphy_read_status(phydev);
 	if (err < 0)
 		return err;
 
-- 
2.20.1


From 717ac8bc0db725a48ae0d23de67cfc7260447c46 Mon Sep 17 00:00:00 2001
From: Jose Abreu <jose.abreu@synopsys.com>
Date: Mon, 18 Feb 2019 14:35:03 +0100
Subject: [PATCH 10/20] net: stmmac: Fix a race in EEE enable callback

[ Upstream commit 8a7493e58ad688eb23b81e45461c5d314f4402f1 ]

We are saving the status of EEE even before we try to enable it. This
leads to a race with XMIT function that tries to arm EEE timer before we
set it up.

Fix this by only saving the EEE parameters after all operations are
performed with success.

Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Fixes: d765955d2ae0 ("stmmac: add the Energy Efficient Ethernet support")
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/stmicro/stmmac/stmmac_ethtool.c  | 22 ++++++++++---------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index 5710864fa809..9caf79ba5ef1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -692,25 +692,27 @@ static int stmmac_ethtool_op_set_eee(struct net_device *dev,
 				     struct ethtool_eee *edata)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
+	int ret;
 
-	priv->eee_enabled = edata->eee_enabled;
-
-	if (!priv->eee_enabled)
+	if (!edata->eee_enabled) {
 		stmmac_disable_eee_mode(priv);
-	else {
+	} else {
 		/* We are asking for enabling the EEE but it is safe
 		 * to verify all by invoking the eee_init function.
 		 * In case of failure it will return an error.
 		 */
-		priv->eee_enabled = stmmac_eee_init(priv);
-		if (!priv->eee_enabled)
+		edata->eee_enabled = stmmac_eee_init(priv);
+		if (!edata->eee_enabled)
 			return -EOPNOTSUPP;
-
-		/* Do not change tx_lpi_timer in case of failure */
-		priv->tx_lpi_timer = edata->tx_lpi_timer;
 	}
 
-	return phy_ethtool_set_eee(dev->phydev, edata);
+	ret = phy_ethtool_set_eee(dev->phydev, edata);
+	if (ret)
+		return ret;
+
+	priv->eee_enabled = edata->eee_enabled;
+	priv->tx_lpi_timer = edata->tx_lpi_timer;
+	return 0;
 }
 
 static u32 stmmac_usec2riwt(u32 usec, struct stmmac_priv *priv)
-- 
2.20.1


From 259ad9a8c3816ccfc1aaf30f4eb319d45c6ad83c Mon Sep 17 00:00:00 2001
From: Alexandre Torgue <alexandre.torgue@st.com>
Date: Fri, 15 Feb 2019 10:49:09 +0100
Subject: [PATCH 11/20] net: stmmac: handle endianness in dwmac4_get_timestamp

[ Upstream commit 224babd62d6f19581757a6d8bae3bf9501fc10de ]

GMAC IP is little-endian and used on several kind of CPU (big or little
endian). Main callbacks functions of the stmmac drivers take care about
it. It was not the case for dwmac4_get_timestamp function.

Fixes: ba1ffd74df74 ("stmmac: fix PTP support for GMAC4")
Signed-off-by: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
index 20299f6f65fc..736e29635b77 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
@@ -241,15 +241,18 @@ static inline void dwmac4_get_timestamp(void *desc, u32 ats, u64 *ts)
 static int dwmac4_rx_check_timestamp(void *desc)
 {
 	struct dma_desc *p = (struct dma_desc *)desc;
+	unsigned int rdes0 = le32_to_cpu(p->des0);
+	unsigned int rdes1 = le32_to_cpu(p->des1);
+	unsigned int rdes3 = le32_to_cpu(p->des3);
 	u32 own, ctxt;
 	int ret = 1;
 
-	own = p->des3 & RDES3_OWN;
-	ctxt = ((p->des3 & RDES3_CONTEXT_DESCRIPTOR)
+	own = rdes3 & RDES3_OWN;
+	ctxt = ((rdes3 & RDES3_CONTEXT_DESCRIPTOR)
 		>> RDES3_CONTEXT_DESCRIPTOR_SHIFT);
 
 	if (likely(!own && ctxt)) {
-		if ((p->des0 == 0xffffffff) && (p->des1 == 0xffffffff))
+		if ((rdes0 == 0xffffffff) && (rdes1 == 0xffffffff))
 			/* Corrupted value */
 			ret = -EINVAL;
 		else
-- 
2.20.1


From e7bdcc8966bce665066cc6297a4f2317f8e91bb2 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 15 Feb 2019 12:15:47 -0500
Subject: [PATCH 12/20] net: validate untrusted gso packets without csum
 offload

[ Upstream commit d5be7f632bad0f489879eed0ff4b99bd7fe0b74c ]

Syzkaller again found a path to a kernel crash through bad gso input.
By building an excessively large packet to cause an skb field to wrap.

If VIRTIO_NET_HDR_F_NEEDS_CSUM was set this would have been dropped in
skb_partial_csum_set.

GSO packets that do not set checksum offload are suspicious and rare.
Most callers of virtio_net_hdr_to_skb already pass them to
skb_probe_transport_header.

Move that test forward, change it to detect parse failure and drop
packets on failure as those cleary are not one of the legitimate
VIRTIO_NET_HDR_GSO types.

Fixes: bfd5f4a3d605 ("packet: Add GSO/csum offload support.")
Fixes: f43798c27684 ("tun: Allow GSO using virtio_net_hdr")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h     | 2 +-
 include/linux/virtio_net.h | 9 +++++++++
 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 5d69e208e8d9..a404d475acee 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2392,7 +2392,7 @@ static inline void skb_probe_transport_header(struct sk_buff *skb,
 
 	if (skb_flow_dissect_flow_keys_basic(skb, &keys, NULL, 0, 0, 0, 0))
 		skb_set_transport_header(skb, keys.control.thoff);
-	else
+	else if (offset_hint >= 0)
 		skb_set_transport_header(skb, offset_hint);
 }
 
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index cb462f9ab7dd..71f2394abbf7 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -57,6 +57,15 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 
 		if (!skb_partial_csum_set(skb, start, off))
 			return -EINVAL;
+	} else {
+		/* gso packets without NEEDS_CSUM do not set transport_offset.
+		 * probe and drop if does not match one of the above types.
+		 */
+		if (gso_type) {
+			skb_probe_transport_header(skb, -1);
+			if (!skb_transport_header_was_set(skb))
+				return -EINVAL;
+		}
 	}
 
 	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
-- 
2.20.1


From 0da7c13d44bf3002a126ce145aa1e0ffca83db4a Mon Sep 17 00:00:00 2001
From: Kai-Heng Feng <kai.heng.feng@canonical.com>
Date: Tue, 19 Feb 2019 23:45:29 +0800
Subject: [PATCH 13/20] sky2: Increase D3 delay again

[ Upstream commit 1765f5dcd00963e33f1b8a4e0f34061fbc0e2f7f ]

Another platform requires even longer delay to make the device work
correctly after S3.

So increase the delay to 300ms.

BugLink: https://bugs.launchpad.net/bugs/1798921

Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/sky2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index 697d9b374f5e..ae2f35039343 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -5087,7 +5087,7 @@ static int sky2_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	INIT_WORK(&hw->restart_work, sky2_restart);
 
 	pci_set_drvdata(pdev, hw);
-	pdev->d3_delay = 200;
+	pdev->d3_delay = 300;
 
 	return 0;
 
-- 
2.20.1


From 7f415d1df986666c37cf37bba5fe6e342fa3fed8 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Tue, 19 Feb 2019 14:53:44 +0800
Subject: [PATCH 14/20] vhost: correctly check the return value of
 translate_desc() in log_used()

[ Upstream commit 816db7663565cd23f74ed3d5c9240522e3fb0dda ]

When fail, translate_desc() returns negative value, otherwise the
number of iovs. So we should fail when the return value is negative
instead of a blindly check against zero.

Detected by CoverityScan, CID# 1442593:  Control flow issues  (DEADCODE)

Fixes: cc5e71075947 ("vhost: log dirty page correctly")
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Reported-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/vhost.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index cf82e7266397..5eaeca805c95 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -1784,7 +1784,7 @@ static int log_used(struct vhost_virtqueue *vq, u64 used_offset, u64 len)
 
 	ret = translate_desc(vq, (uintptr_t)vq->used + used_offset,
 			     len, iov, 64, VHOST_ACCESS_WO);
-	if (ret)
+	if (ret < 0)
 		return ret;
 
 	for (i = 0; i < ret; i++) {
-- 
2.20.1


From dd2c254a5c2512d4511b6b3735c042571fbc0a10 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 7 Feb 2019 14:13:18 +0100
Subject: [PATCH 15/20] vsock: cope with memory allocation failure at socket
 creation time

[ Upstream commit 225d9464268599a5b4d094d02ec17808e44c7553 ]

In the unlikely event that the kmalloc call in vmci_transport_socket_init()
fails, we end-up calling vmci_transport_destruct() with a NULL vmci_trans()
and oopsing.

This change addresses the above explicitly checking for zero vmci_trans()
at destruction time.

Reported-by: Xiumei Mu <xmu@redhat.com>
Fixes: d021c344051a ("VSOCK: Introduce VM Sockets")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Reviewed-by: Jorgen Hansen <jhansen@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/vmw_vsock/vmci_transport.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index c361ce782412..c3d5ab01fba7 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -1651,6 +1651,10 @@ static void vmci_transport_cleanup(struct work_struct *work)
 
 static void vmci_transport_destruct(struct vsock_sock *vsk)
 {
+	/* transport can be NULL if we hit a failure at init() time */
+	if (!vmci_trans(vsk))
+		return;
+
 	/* Ensure that the detach callback doesn't use the sk/vsk
 	 * we are about to destruct.
 	 */
-- 
2.20.1


From c37188dc3ad05481816b62e5ea25409b1027feb3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 7 Feb 2019 12:27:38 -0800
Subject: [PATCH 16/20] vxlan: test dev->flags & IFF_UP before calling
 netif_rx()

[ Upstream commit 4179cb5a4c924cd233eaadd081882425bc98f44e ]

netif_rx() must be called under a strict contract.

At device dismantle phase, core networking clears IFF_UP
and flush_all_backlogs() is called after rcu grace period
to make sure no incoming packet might be in a cpu backlog
and still referencing the device.

Most drivers call netif_rx() from their interrupt handler,
and since the interrupts are disabled at device dismantle,
netif_rx() does not have to check dev->flags & IFF_UP

Virtual drivers do not have this guarantee, and must
therefore make the check themselves.

Otherwise we risk use-after-free and/or crashes.

Note this patch also fixes a small issue that came
with commit ce6502a8f957 ("vxlan: fix a use after free
in vxlan_encap_bypass"), since the dev->stats.rx_dropped
change was done on the wrong device.

Fixes: d342894c5d2f ("vxlan: virtual extensible lan")
Fixes: ce6502a8f957 ("vxlan: fix a use after free in vxlan_encap_bypass")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Petr Machata <petrm@mellanox.com>
Cc: Ido Schimmel <idosch@mellanox.com>
Cc: Roopa Prabhu <roopa@cumulusnetworks.com>
Cc: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 27bd586b94b0..9fc9aed6ca9a 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2003,7 +2003,7 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan,
 	struct pcpu_sw_netstats *tx_stats, *rx_stats;
 	union vxlan_addr loopback;
 	union vxlan_addr *remote_ip = &dst_vxlan->default_dst.remote_ip;
-	struct net_device *dev = skb->dev;
+	struct net_device *dev;
 	int len = skb->len;
 
 	tx_stats = this_cpu_ptr(src_vxlan->dev->tstats);
@@ -2023,9 +2023,15 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan,
 #endif
 	}
 
+	rcu_read_lock();
+	dev = skb->dev;
+	if (unlikely(!(dev->flags & IFF_UP))) {
+		kfree_skb(skb);
+		goto drop;
+	}
+
 	if (dst_vxlan->cfg.flags & VXLAN_F_LEARN)
-		vxlan_snoop(skb->dev, &loopback, eth_hdr(skb)->h_source, 0,
-			    vni);
+		vxlan_snoop(dev, &loopback, eth_hdr(skb)->h_source, 0, vni);
 
 	u64_stats_update_begin(&tx_stats->syncp);
 	tx_stats->tx_packets++;
@@ -2038,8 +2044,10 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan,
 		rx_stats->rx_bytes += len;
 		u64_stats_update_end(&rx_stats->syncp);
 	} else {
+drop:
 		dev->stats.rx_dropped++;
 	}
+	rcu_read_unlock();
 }
 
 static int encap_bypass_if_local(struct sk_buff *skb, struct net_device *dev,
-- 
2.20.1


From a5a17840b785877f76d09f241a881c48824fb077 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sat, 16 Feb 2019 13:44:39 -0800
Subject: [PATCH 17/20] net: Add header for usage of fls64()

[ Upstream commit 8681ef1f3d295bd3600315325f3b3396d76d02f6 ]

Fixes: 3b89ea9c5902 ("net: Fix for_each_netdev_feature on Big endian")
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdev_features.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index fce28562bed2..4c76fe2c8488 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -11,6 +11,7 @@
 #define _LINUX_NETDEV_FEATURES_H
 
 #include <linux/types.h>
+#include <linux/bitops.h>
 #include <asm/byteorder.h>
 
 typedef u64 netdev_features_t;
-- 
2.20.1


From 3320183bf83a3c05b7ee88fc9d055c11e4d4389b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 15 Feb 2019 13:36:20 -0800
Subject: [PATCH 18/20] tcp: clear icsk_backoff in tcp_write_queue_purge()

[ Upstream commit 04c03114be82194d4a4858d41dba8e286ad1787c ]

soukjin bae reported a crash in tcp_v4_err() handling
ICMP_DEST_UNREACH after tcp_write_queue_head(sk)
returned a NULL pointer.

Current logic should have prevented this :

  if (seq != tp->snd_una  || !icsk->icsk_retransmits ||
      !icsk->icsk_backoff || fastopen)
      break;

Problem is the write queue might have been purged
and icsk_backoff has not been cleared.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: soukjin bae <soukjin.bae@samsung.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 87fe44197aa1..432dc9af1172 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2519,6 +2519,7 @@ void tcp_write_queue_purge(struct sock *sk)
 	sk_mem_reclaim(sk);
 	tcp_clear_all_retrans_hints(tcp_sk(sk));
 	tcp_sk(sk)->packets_out = 0;
+	inet_csk(sk)->icsk_backoff = 0;
 }
 
 int tcp_disconnect(struct sock *sk, int flags)
@@ -2567,7 +2568,6 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tp->write_seq += tp->max_window + 2;
 	if (tp->write_seq == 0)
 		tp->write_seq = 1;
-	icsk->icsk_backoff = 0;
 	tp->snd_cwnd = 2;
 	icsk->icsk_probes_out = 0;
 	tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
-- 
2.20.1


From 5e4722fba79a6b307cb516f911f11b7cdc758e24 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 15 Feb 2019 13:36:21 -0800
Subject: [PATCH 19/20] tcp: tcp_v4_err() should be more careful

[ Upstream commit 2c4cc9712364c051b1de2d175d5fbea6be948ebf ]

ICMP handlers are not very often stressed, we should
make them more resilient to bugs that might surface in
the future.

If there is no packet in retransmit queue, we should
avoid a NULL deref.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: soukjin bae <soukjin.bae@samsung.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index cd426313a298..4370ef1d547e 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -535,6 +535,10 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 		if (sock_owned_by_user(sk))
 			break;
 
+		skb = tcp_rtx_queue_head(sk);
+		if (WARN_ON_ONCE(!skb))
+			break;
+
 		icsk->icsk_backoff--;
 		icsk->icsk_rto = tp->srtt_us ? __tcp_set_rto(tp) :
 					       TCP_TIMEOUT_INIT;
-- 
2.20.1


From a4773963a493d8801a4e50ff700a9aebdc0d5272 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Date: Fri, 15 Feb 2019 14:44:18 -0800
Subject: [PATCH 20/20] net: Do not allocate page fragments that are not skb
 aligned

[ Upstream commit 3bed3cc4156eedf652b4df72bdb35d4f1a2a739d ]

This patch addresses the fact that there are drivers, specifically tun,
that will call into the network page fragment allocators with buffer sizes
that are not cache aligned. Doing this could result in data alignment
and DMA performance issues as these fragment pools are also shared with the
skb allocator and any other devices that will use napi_alloc_frags or
netdev_alloc_frags.

Fixes: ffde7328a36d ("net: Split netdev_alloc_frag into __alloc_page_frag and add __napi_alloc_frag")
Reported-by: Jann Horn <jannh@google.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 589ec5b9ec5f..8656b1e20d35 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -353,6 +353,8 @@ static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
  */
 void *netdev_alloc_frag(unsigned int fragsz)
 {
+	fragsz = SKB_DATA_ALIGN(fragsz);
+
 	return __netdev_alloc_frag(fragsz, GFP_ATOMIC);
 }
 EXPORT_SYMBOL(netdev_alloc_frag);
@@ -366,6 +368,8 @@ static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
 
 void *napi_alloc_frag(unsigned int fragsz)
 {
+	fragsz = SKB_DATA_ALIGN(fragsz);
+
 	return __napi_alloc_frag(fragsz, GFP_ATOMIC);
 }
 EXPORT_SYMBOL(napi_alloc_frag);
-- 
2.20.1


[-- Attachment #3: net_420.mbox --]
[-- Type: Application/Octet-Stream, Size: 46729 bytes --]

From 7795d92e247e9c9f56cf47530c5e2e3635c17fb5 Mon Sep 17 00:00:00 2001
From: John David Anglin <dave.anglin@bell.net>
Date: Mon, 11 Feb 2019 13:40:21 -0500
Subject: [PATCH 01/21] dsa: mv88e6xxx: Ensure all pending interrupts are
 handled prior to exit

[ Upstream commit 7c0db24cc431e2196d98a5d5ddaa9088e2fcbfe5 ]

The GPIO interrupt controller on the espressobin board only supports edge interrupts.
If one enables the use of hardware interrupts in the device tree for the 88E6341, it is
possible to miss an edge.  When this happens, the INTn pin on the Marvell switch is
stuck low and no further interrupts occur.

I found after adding debug statements to mv88e6xxx_g1_irq_thread_work() that there is
a race in handling device interrupts (e.g. PHY link interrupts).  Some interrupts are
directly cleared by reading the Global 1 status register.  However, the device interrupt
flag, for example, is not cleared until all the unmasked SERDES and PHY ports are serviced.
This is done by reading the relevant SERDES and PHY status register.

The code only services interrupts whose status bit is set at the time of reading its status
register.  If an interrupt event occurs after its status is read and before all interrupts
are serviced, then this event will not be serviced and the INTn output pin will remain low.

This is not a problem with polling or level interrupts since the handler will be called
again to process the event.  However, it's a big problem when using level interrupts.

The fix presented here is to add a loop around the code servicing switch interrupts.  If
any pending interrupts remain after the current set has been handled, we loop and process
the new set.  If there are no pending interrupts after servicing, we are sure that INTn has
gone high and we will get an edge when a new event occurs.

Tested on espressobin board.

Fixes: dc30c35be720 ("net: dsa: mv88e6xxx: Implement interrupt support.")
Signed-off-by:  John David Anglin <dave.anglin@bell.net>
Tested-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 28 ++++++++++++++++++++++------
 1 file changed, 22 insertions(+), 6 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index b2a0e59b6252..b0113f6fdbb4 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -261,6 +261,7 @@ static irqreturn_t mv88e6xxx_g1_irq_thread_work(struct mv88e6xxx_chip *chip)
 	unsigned int sub_irq;
 	unsigned int n;
 	u16 reg;
+	u16 ctl1;
 	int err;
 
 	mutex_lock(&chip->reg_lock);
@@ -270,13 +271,28 @@ static irqreturn_t mv88e6xxx_g1_irq_thread_work(struct mv88e6xxx_chip *chip)
 	if (err)
 		goto out;
 
-	for (n = 0; n < chip->g1_irq.nirqs; ++n) {
-		if (reg & (1 << n)) {
-			sub_irq = irq_find_mapping(chip->g1_irq.domain, n);
-			handle_nested_irq(sub_irq);
-			++nhandled;
+	do {
+		for (n = 0; n < chip->g1_irq.nirqs; ++n) {
+			if (reg & (1 << n)) {
+				sub_irq = irq_find_mapping(chip->g1_irq.domain,
+							   n);
+				handle_nested_irq(sub_irq);
+				++nhandled;
+			}
 		}
-	}
+
+		mutex_lock(&chip->reg_lock);
+		err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_CTL1, &ctl1);
+		if (err)
+			goto unlock;
+		err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_STS, &reg);
+unlock:
+		mutex_unlock(&chip->reg_lock);
+		if (err)
+			goto out;
+		ctl1 &= GENMASK(chip->g1_irq.nirqs, 0);
+	} while (reg & ctl1);
+
 out:
 	return (nhandled > 0 ? IRQ_HANDLED : IRQ_NONE);
 }
-- 
2.20.1


From 02ea0f8f4d10b9424a85f50f6bbbc45721c83685 Mon Sep 17 00:00:00 2001
From: Zhiqiang Liu <liuzhiqiang26@huawei.com>
Date: Mon, 11 Feb 2019 10:57:46 +0800
Subject: [PATCH 02/21] net: fix IPv6 prefix route residue

[ Upstream commit e75913c93f7cd5f338ab373c34c93a655bd309cb ]

Follow those steps:
 # ip addr add 2001:123::1/32 dev eth0
 # ip addr add 2001:123:456::2/64 dev eth0
 # ip addr del 2001:123::1/32 dev eth0
 # ip addr del 2001:123:456::2/64 dev eth0
and then prefix route of 2001:123::1/32 will still exist.

This is because ipv6_prefix_equal in check_cleanup_prefix_route
func does not check whether two IPv6 addresses have the same
prefix length. If the prefix of one address starts with another
shorter address prefix, even though their prefix lengths are
different, the return value of ipv6_prefix_equal is true.

Here I add a check of whether two addresses have the same prefix
to decide whether their prefixes are equal.

Fixes: 5b84efecb7d9 ("ipv6 addrconf: don't cleanup prefix route for IFA_F_NOPREFIXROUTE")
Signed-off-by: Zhiqiang Liu <liuzhiqiang26@huawei.com>
Reported-by: Wenhao Zhang <zhangwenhao8@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index d2b597674d60..9fa51ab01ac4 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1165,7 +1165,8 @@ check_cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long *expires)
 	list_for_each_entry(ifa, &idev->addr_list, if_list) {
 		if (ifa == ifp)
 			continue;
-		if (!ipv6_prefix_equal(&ifa->addr, &ifp->addr,
+		if (ifa->prefix_len != ifp->prefix_len ||
+		    !ipv6_prefix_equal(&ifa->addr, &ifp->addr,
 				       ifp->prefix_len))
 			continue;
 		if (ifa->flags & (IFA_F_PERMANENT | IFA_F_NOPREFIXROUTE))
-- 
2.20.1


From 2faaacdeefd29ecff1193da31c336af4d301996d Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Wed, 6 Feb 2019 19:18:04 +0100
Subject: [PATCH 03/21] net: ipv4: use a dedicated counter for icmp_v4 redirect
 packets

[ Upstream commit c09551c6ff7fe16a79a42133bcecba5fc2fc3291 ]

According to the algorithm described in the comment block at the
beginning of ip_rt_send_redirect, the host should try to send
'ip_rt_redirect_number' ICMP redirect packets with an exponential
backoff and then stop sending them at all assuming that the destination
ignores redirects.
If the device has previously sent some ICMP error packets that are
rate-limited (e.g TTL expired) and continues to receive traffic,
the redirect packets will never be transmitted. This happens since
peer->rate_tokens will be typically greater than 'ip_rt_redirect_number'
and so it will never be reset even if the redirect silence timeout
(ip_rt_redirect_silence) has elapsed without receiving any packet
requiring redirects.

Fix it by using a dedicated counter for the number of ICMP redirect
packets that has been sent by the host

I have not been able to identify a given commit that introduced the
issue since ip_rt_send_redirect implements the same rate-limiting
algorithm from commit 1da177e4c3f4 ("Linux-2.6.12-rc2")

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inetpeer.h | 1 +
 net/ipv4/inetpeer.c    | 1 +
 net/ipv4/route.c       | 7 +++++--
 3 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index 00b5e7825508..74ff688568a0 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -39,6 +39,7 @@ struct inet_peer {
 
 	u32			metrics[RTAX_MAX];
 	u32			rate_tokens;	/* rate limiting for ICMP */
+	u32			n_redirects;
 	unsigned long		rate_last;
 	/*
 	 * Once inet_peer is queued for deletion (refcnt == 0), following field
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index d757b9642d0d..be778599bfed 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -216,6 +216,7 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base,
 			atomic_set(&p->rid, 0);
 			p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW;
 			p->rate_tokens = 0;
+			p->n_redirects = 0;
 			/* 60*HZ is arbitrary, but chosen enough high so that the first
 			 * calculation of tokens is at its maximum.
 			 */
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index c0a9d26c06ce..d1ddf1d03721 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -887,13 +887,15 @@ void ip_rt_send_redirect(struct sk_buff *skb)
 	/* No redirected packets during ip_rt_redirect_silence;
 	 * reset the algorithm.
 	 */
-	if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence))
+	if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence)) {
 		peer->rate_tokens = 0;
+		peer->n_redirects = 0;
+	}
 
 	/* Too many ignored redirects; do not send anything
 	 * set dst.rate_last to the last seen redirected packet.
 	 */
-	if (peer->rate_tokens >= ip_rt_redirect_number) {
+	if (peer->n_redirects >= ip_rt_redirect_number) {
 		peer->rate_last = jiffies;
 		goto out_put_peer;
 	}
@@ -910,6 +912,7 @@ void ip_rt_send_redirect(struct sk_buff *skb)
 		icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw);
 		peer->rate_last = jiffies;
 		++peer->rate_tokens;
+		++peer->n_redirects;
 #ifdef CONFIG_IP_ROUTE_VERBOSE
 		if (log_martians &&
 		    peer->rate_tokens == ip_rt_redirect_number)
-- 
2.20.1


From 1377d9927d91a1b301efdd96d86564fe8d557acb Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 7 Feb 2019 14:13:18 +0100
Subject: [PATCH 04/21] vsock: cope with memory allocation failure at socket
 creation time

[ Upstream commit 225d9464268599a5b4d094d02ec17808e44c7553 ]

In the unlikely event that the kmalloc call in vmci_transport_socket_init()
fails, we end-up calling vmci_transport_destruct() with a NULL vmci_trans()
and oopsing.

This change addresses the above explicitly checking for zero vmci_trans()
at destruction time.

Reported-by: Xiumei Mu <xmu@redhat.com>
Fixes: d021c344051a ("VSOCK: Introduce VM Sockets")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Reviewed-by: Jorgen Hansen <jhansen@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/vmw_vsock/vmci_transport.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index c361ce782412..c3d5ab01fba7 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -1651,6 +1651,10 @@ static void vmci_transport_cleanup(struct work_struct *work)
 
 static void vmci_transport_destruct(struct vsock_sock *vsk)
 {
+	/* transport can be NULL if we hit a failure at init() time */
+	if (!vmci_trans(vsk))
+		return;
+
 	/* Ensure that the detach callback doesn't use the sk/vsk
 	 * we are about to destruct.
 	 */
-- 
2.20.1


From 413e1973431edec4f977452d9917af91a6c8c3a4 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 7 Feb 2019 12:27:38 -0800
Subject: [PATCH 05/21] vxlan: test dev->flags & IFF_UP before calling
 netif_rx()

[ Upstream commit 4179cb5a4c924cd233eaadd081882425bc98f44e ]

netif_rx() must be called under a strict contract.

At device dismantle phase, core networking clears IFF_UP
and flush_all_backlogs() is called after rcu grace period
to make sure no incoming packet might be in a cpu backlog
and still referencing the device.

Most drivers call netif_rx() from their interrupt handler,
and since the interrupts are disabled at device dismantle,
netif_rx() does not have to check dev->flags & IFF_UP

Virtual drivers do not have this guarantee, and must
therefore make the check themselves.

Otherwise we risk use-after-free and/or crashes.

Note this patch also fixes a small issue that came
with commit ce6502a8f957 ("vxlan: fix a use after free
in vxlan_encap_bypass"), since the dev->stats.rx_dropped
change was done on the wrong device.

Fixes: d342894c5d2f ("vxlan: virtual extensible lan")
Fixes: ce6502a8f957 ("vxlan: fix a use after free in vxlan_encap_bypass")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Petr Machata <petrm@mellanox.com>
Cc: Ido Schimmel <idosch@mellanox.com>
Cc: Roopa Prabhu <roopa@cumulusnetworks.com>
Cc: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 0565f8880199..8f022964b2d1 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2072,7 +2072,7 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan,
 	struct pcpu_sw_netstats *tx_stats, *rx_stats;
 	union vxlan_addr loopback;
 	union vxlan_addr *remote_ip = &dst_vxlan->default_dst.remote_ip;
-	struct net_device *dev = skb->dev;
+	struct net_device *dev;
 	int len = skb->len;
 
 	tx_stats = this_cpu_ptr(src_vxlan->dev->tstats);
@@ -2092,9 +2092,15 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan,
 #endif
 	}
 
+	rcu_read_lock();
+	dev = skb->dev;
+	if (unlikely(!(dev->flags & IFF_UP))) {
+		kfree_skb(skb);
+		goto drop;
+	}
+
 	if (dst_vxlan->cfg.flags & VXLAN_F_LEARN)
-		vxlan_snoop(skb->dev, &loopback, eth_hdr(skb)->h_source, 0,
-			    vni);
+		vxlan_snoop(dev, &loopback, eth_hdr(skb)->h_source, 0, vni);
 
 	u64_stats_update_begin(&tx_stats->syncp);
 	tx_stats->tx_packets++;
@@ -2107,8 +2113,10 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan,
 		rx_stats->rx_bytes += len;
 		u64_stats_update_end(&rx_stats->syncp);
 	} else {
+drop:
 		dev->stats.rx_dropped++;
 	}
+	rcu_read_unlock();
 }
 
 static int encap_bypass_if_local(struct sk_buff *skb, struct net_device *dev,
-- 
2.20.1


From be0641bf4313f5f4fa14966f690d3b9ca64ea428 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Sun, 17 Feb 2019 07:18:41 +0000
Subject: [PATCH 06/21] mlxsw: __mlxsw_sp_port_headroom_set(): Fix a use of
 local variable

[ Upstream commit 289460404f6947ef1c38e67d680be9a84161250b ]

The function-local variable "delay" enters the loop interpreted as delay
in bits. However, inside the loop it gets overwritten by the result of
mlxsw_sp_pg_buf_delay_get(), and thus leaves the loop as quantity in
cells. Thus on second and further loop iterations, the headroom for a
given priority is configured with a wrong size.

Fix by introducing a loop-local variable, delay_cells. Rename thres to
thres_cells for consistency.

Fixes: f417f04da589 ("mlxsw: spectrum: Refactor port buffer configuration")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 8f1180fff955..280173b48962 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -845,8 +845,9 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu,
 	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
 		bool configure = false;
 		bool pfc = false;
+		u16 thres_cells;
+		u16 delay_cells;
 		bool lossy;
-		u16 thres;
 
 		for (j = 0; j < IEEE_8021QAZ_MAX_TCS; j++) {
 			if (prio_tc[j] == i) {
@@ -860,10 +861,11 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu,
 			continue;
 
 		lossy = !(pfc || pause_en);
-		thres = mlxsw_sp_pg_buf_threshold_get(mlxsw_sp, mtu);
-		delay = mlxsw_sp_pg_buf_delay_get(mlxsw_sp, mtu, delay, pfc,
-						  pause_en);
-		mlxsw_sp_pg_buf_pack(pbmc_pl, i, thres + delay, thres, lossy);
+		thres_cells = mlxsw_sp_pg_buf_threshold_get(mlxsw_sp, mtu);
+		delay_cells = mlxsw_sp_pg_buf_delay_get(mlxsw_sp, mtu, delay,
+							pfc, pause_en);
+		mlxsw_sp_pg_buf_pack(pbmc_pl, i, thres_cells + delay_cells,
+				     thres_cells, lossy);
 	}
 
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pbmc), pbmc_pl);
-- 
2.20.1


From c77a43659f8d933fca352fe3070324a4f326e411 Mon Sep 17 00:00:00 2001
From: Mao Wenan <maowenan@huawei.com>
Date: Mon, 18 Feb 2019 10:44:44 +0800
Subject: [PATCH 07/21] net: crypto set sk to NULL when af_alg_release.

[ Upstream commit 9060cb719e61b685ec0102574e10337fa5f445ea ]

KASAN has found use-after-free in sockfs_setattr.
The existed commit 6d8c50dcb029 ("socket: close race condition between sock_close()
and sockfs_setattr()") is to fix this simillar issue, but it seems to ignore
that crypto module forgets to set the sk to NULL after af_alg_release.

KASAN report details as below:
BUG: KASAN: use-after-free in sockfs_setattr+0x120/0x150
Write of size 4 at addr ffff88837b956128 by task syz-executor0/4186

CPU: 2 PID: 4186 Comm: syz-executor0 Not tainted xxx + #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS
1.10.2-1ubuntu1 04/01/2014
Call Trace:
 dump_stack+0xca/0x13e
 print_address_description+0x79/0x330
 ? vprintk_func+0x5e/0xf0
 kasan_report+0x18a/0x2e0
 ? sockfs_setattr+0x120/0x150
 sockfs_setattr+0x120/0x150
 ? sock_register+0x2d0/0x2d0
 notify_change+0x90c/0xd40
 ? chown_common+0x2ef/0x510
 chown_common+0x2ef/0x510
 ? chmod_common+0x3b0/0x3b0
 ? __lock_is_held+0xbc/0x160
 ? __sb_start_write+0x13d/0x2b0
 ? __mnt_want_write+0x19a/0x250
 do_fchownat+0x15c/0x190
 ? __ia32_sys_chmod+0x80/0x80
 ? trace_hardirqs_on_thunk+0x1a/0x1c
 __x64_sys_fchownat+0xbf/0x160
 ? lockdep_hardirqs_on+0x39a/0x5e0
 do_syscall_64+0xc8/0x580
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x462589
Code: f7 d8 64 89 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 48 89 f8 48 89
f7 48 89 d6 48 89
ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3
48 c7 c1 bc ff ff
ff f7 d8 64 89 01 48
RSP: 002b:00007fb4b2c83c58 EFLAGS: 00000246 ORIG_RAX: 0000000000000104
RAX: ffffffffffffffda RBX: 000000000072bfa0 RCX: 0000000000462589
RDX: 0000000000000000 RSI: 00000000200000c0 RDI: 0000000000000007
RBP: 0000000000000005 R08: 0000000000001000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00007fb4b2c846bc
R13: 00000000004bc733 R14: 00000000006f5138 R15: 00000000ffffffff

Allocated by task 4185:
 kasan_kmalloc+0xa0/0xd0
 __kmalloc+0x14a/0x350
 sk_prot_alloc+0xf6/0x290
 sk_alloc+0x3d/0xc00
 af_alg_accept+0x9e/0x670
 hash_accept+0x4a3/0x650
 __sys_accept4+0x306/0x5c0
 __x64_sys_accept4+0x98/0x100
 do_syscall_64+0xc8/0x580
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Freed by task 4184:
 __kasan_slab_free+0x12e/0x180
 kfree+0xeb/0x2f0
 __sk_destruct+0x4e6/0x6a0
 sk_destruct+0x48/0x70
 __sk_free+0xa9/0x270
 sk_free+0x2a/0x30
 af_alg_release+0x5c/0x70
 __sock_release+0xd3/0x280
 sock_close+0x1a/0x20
 __fput+0x27f/0x7f0
 task_work_run+0x136/0x1b0
 exit_to_usermode_loop+0x1a7/0x1d0
 do_syscall_64+0x461/0x580
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Syzkaller reproducer:
r0 = perf_event_open(&(0x7f0000000000)={0x0, 0x70, 0x0, 0x0, 0x0, 0x0,
0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, @perf_config_ext}, 0x0, 0x0,
0xffffffffffffffff, 0x0)
r1 = socket$alg(0x26, 0x5, 0x0)
getrusage(0x0, 0x0)
bind(r1, &(0x7f00000001c0)=@alg={0x26, 'hash\x00', 0x0, 0x0,
'sha256-ssse3\x00'}, 0x80)
r2 = accept(r1, 0x0, 0x0)
r3 = accept4$unix(r2, 0x0, 0x0, 0x0)
r4 = dup3(r3, r0, 0x0)
fchownat(r4, &(0x7f00000000c0)='\x00', 0x0, 0x0, 0x1000)

Fixes: 6d8c50dcb029 ("socket: close race condition between sock_close() and sockfs_setattr()")
Signed-off-by: Mao Wenan <maowenan@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 crypto/af_alg.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index 17eb09d222ff..ec78a04eb136 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -122,8 +122,10 @@ static void alg_do_release(const struct af_alg_type *type, void *private)
 
 int af_alg_release(struct socket *sock)
 {
-	if (sock->sk)
+	if (sock->sk) {
 		sock_put(sock->sk);
+		sock->sk = NULL;
+	}
 	return 0;
 }
 EXPORT_SYMBOL_GPL(af_alg_release);
-- 
2.20.1


From 404b35b24bbe89530e0aed72a0c6c8a487867ea5 Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens <hauke.mehrtens@intel.com>
Date: Fri, 15 Feb 2019 17:58:54 +0100
Subject: [PATCH 08/21] net: Fix for_each_netdev_feature on Big endian

[ Upstream commit 3b89ea9c5902acccdbbdec307c85edd1bf52515e ]

The features attribute is of type u64 and stored in the native endianes on
the system. The for_each_set_bit() macro takes a pointer to a 32 bit array
and goes over the bits in this area. On little Endian systems this also
works with an u64 as the most significant bit is on the highest address,
but on big endian the words are swapped. When we expect bit 15 here we get
bit 47 (15 + 32).

This patch converts it more or less to its own for_each_set_bit()
implementation which works on 64 bit integers directly. This is then
completely in host endianness and should work like expected.

Fixes: fd867d51f ("net/core: generic support for disabling netdev features down stack")
Signed-off-by: Hauke Mehrtens <hauke.mehrtens@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdev_features.h | 23 +++++++++++++++++++++--
 net/core/dev.c                  |  4 ++--
 2 files changed, 23 insertions(+), 4 deletions(-)

diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index 2b2a6dce1630..fce28562bed2 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -11,6 +11,7 @@
 #define _LINUX_NETDEV_FEATURES_H
 
 #include <linux/types.h>
+#include <asm/byteorder.h>
 
 typedef u64 netdev_features_t;
 
@@ -154,8 +155,26 @@ enum {
 #define NETIF_F_HW_TLS_TX	__NETIF_F(HW_TLS_TX)
 #define NETIF_F_HW_TLS_RX	__NETIF_F(HW_TLS_RX)
 
-#define for_each_netdev_feature(mask_addr, bit)	\
-	for_each_set_bit(bit, (unsigned long *)mask_addr, NETDEV_FEATURE_COUNT)
+/* Finds the next feature with the highest number of the range of start till 0.
+ */
+static inline int find_next_netdev_feature(u64 feature, unsigned long start)
+{
+	/* like BITMAP_LAST_WORD_MASK() for u64
+	 * this sets the most significant 64 - start to 0.
+	 */
+	feature &= ~0ULL >> (-start & ((sizeof(feature) * 8) - 1));
+
+	return fls64(feature) - 1;
+}
+
+/* This goes for the MSB to the LSB through the set feature bits,
+ * mask_addr should be a u64 and bit an int
+ */
+#define for_each_netdev_feature(mask_addr, bit)				\
+	for ((bit) = find_next_netdev_feature((mask_addr),		\
+					      NETDEV_FEATURE_COUNT);	\
+	     (bit) >= 0;						\
+	     (bit) = find_next_netdev_feature((mask_addr), (bit) - 1))
 
 /* Features valid for ethtool to change */
 /* = all defined minus driver/device-class-related */
diff --git a/net/core/dev.c b/net/core/dev.c
index 43f8a4fd4968..de0690e5b3df 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8064,7 +8064,7 @@ static netdev_features_t netdev_sync_upper_features(struct net_device *lower,
 	netdev_features_t feature;
 	int feature_bit;
 
-	for_each_netdev_feature(&upper_disables, feature_bit) {
+	for_each_netdev_feature(upper_disables, feature_bit) {
 		feature = __NETIF_F_BIT(feature_bit);
 		if (!(upper->wanted_features & feature)
 		    && (features & feature)) {
@@ -8084,7 +8084,7 @@ static void netdev_sync_lower_features(struct net_device *upper,
 	netdev_features_t feature;
 	int feature_bit;
 
-	for_each_netdev_feature(&upper_disables, feature_bit) {
+	for_each_netdev_feature(upper_disables, feature_bit) {
 		feature = __NETIF_F_BIT(feature_bit);
 		if (!(features & feature) && (lower->features & feature)) {
 			netdev_dbg(upper, "Disabling feature %pNF on lower dev %s.\n",
-- 
2.20.1


From 330efe0f4bb4de873757dd97afd5dd7572cd4a7f Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Fri, 15 Feb 2019 15:10:32 +0100
Subject: [PATCH 09/21] net: ip6_gre: initialize erspan_ver just for erspan
 tunnels

[ Upstream commit 4974d5f678abb34401558559d47e2ea3d1c15cba ]

After commit c706863bc890 ("net: ip6_gre: always reports o_key to
userspace"), ip6gre and ip6gretap tunnels started reporting TUNNEL_KEY
output flag even if it is not configured.
ip6gre_fill_info checks erspan_ver value to add TUNNEL_KEY for
erspan tunnels, however in commit 84581bdae9587 ("erspan: set
erspan_ver to 1 by default when adding an erspan dev")
erspan_ver is initialized to 1 even for ip6gre or ip6gretap
Fix the issue moving erspan_ver initialization in a dedicated routine

Fixes: c706863bc890 ("net: ip6_gre: always reports o_key to userspace")
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Reviewed-by: Greg Rose <gvrose8192@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 34 ++++++++++++++++++++--------------
 1 file changed, 20 insertions(+), 14 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 94903061f324..e83c41c53f4a 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1717,6 +1717,24 @@ static int ip6erspan_tap_validate(struct nlattr *tb[], struct nlattr *data[],
 	return 0;
 }
 
+static void ip6erspan_set_version(struct nlattr *data[],
+				  struct __ip6_tnl_parm *parms)
+{
+	parms->erspan_ver = 1;
+	if (data[IFLA_GRE_ERSPAN_VER])
+		parms->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]);
+
+	if (parms->erspan_ver == 1) {
+		if (data[IFLA_GRE_ERSPAN_INDEX])
+			parms->index = nla_get_u32(data[IFLA_GRE_ERSPAN_INDEX]);
+	} else if (parms->erspan_ver == 2) {
+		if (data[IFLA_GRE_ERSPAN_DIR])
+			parms->dir = nla_get_u8(data[IFLA_GRE_ERSPAN_DIR]);
+		if (data[IFLA_GRE_ERSPAN_HWID])
+			parms->hwid = nla_get_u16(data[IFLA_GRE_ERSPAN_HWID]);
+	}
+}
+
 static void ip6gre_netlink_parms(struct nlattr *data[],
 				struct __ip6_tnl_parm *parms)
 {
@@ -1765,20 +1783,6 @@ static void ip6gre_netlink_parms(struct nlattr *data[],
 
 	if (data[IFLA_GRE_COLLECT_METADATA])
 		parms->collect_md = true;
-
-	parms->erspan_ver = 1;
-	if (data[IFLA_GRE_ERSPAN_VER])
-		parms->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]);
-
-	if (parms->erspan_ver == 1) {
-		if (data[IFLA_GRE_ERSPAN_INDEX])
-			parms->index = nla_get_u32(data[IFLA_GRE_ERSPAN_INDEX]);
-	} else if (parms->erspan_ver == 2) {
-		if (data[IFLA_GRE_ERSPAN_DIR])
-			parms->dir = nla_get_u8(data[IFLA_GRE_ERSPAN_DIR]);
-		if (data[IFLA_GRE_ERSPAN_HWID])
-			parms->hwid = nla_get_u16(data[IFLA_GRE_ERSPAN_HWID]);
-	}
 }
 
 static int ip6gre_tap_init(struct net_device *dev)
@@ -2207,6 +2211,7 @@ static int ip6erspan_newlink(struct net *src_net, struct net_device *dev,
 	int err;
 
 	ip6gre_netlink_parms(data, &nt->parms);
+	ip6erspan_set_version(data, &nt->parms);
 	ign = net_generic(net, ip6gre_net_id);
 
 	if (nt->parms.collect_md) {
@@ -2252,6 +2257,7 @@ static int ip6erspan_changelink(struct net_device *dev, struct nlattr *tb[],
 	if (IS_ERR(t))
 		return PTR_ERR(t);
 
+	ip6erspan_set_version(data, &p);
 	ip6gre_tunnel_unlink_md(ign, t);
 	ip6gre_tunnel_unlink(ign, t);
 	ip6erspan_tnl_change(t, &p, !tb[IFLA_MTU]);
-- 
2.20.1


From 79107336a87ddf53882e96774b638768d726543c Mon Sep 17 00:00:00 2001
From: Paul Kocialkowski <paul.kocialkowski@bootlin.com>
Date: Fri, 15 Feb 2019 17:17:08 +0100
Subject: [PATCH 10/21] net: phy: xgmiitorgmii: Support generic PHY status read

[ Upstream commit 197f9ab7f08ce4b9ece662f747c3991b2f0fbb57 ]

Some PHY drivers like the generic one do not provide a read_status
callback on their own but rely on genphy_read_status being called
directly.

With the current code, this results in a NULL function pointer call.
Call genphy_read_status instead when there is no specific callback.

Fixes: f411a6160bd4 ("net: phy: Add gmiitorgmii converter support")
Signed-off-by: Paul Kocialkowski <paul.kocialkowski@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/xilinx_gmii2rgmii.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/xilinx_gmii2rgmii.c b/drivers/net/phy/xilinx_gmii2rgmii.c
index 74a8782313cf..bd6084e315de 100644
--- a/drivers/net/phy/xilinx_gmii2rgmii.c
+++ b/drivers/net/phy/xilinx_gmii2rgmii.c
@@ -44,7 +44,10 @@ static int xgmiitorgmii_read_status(struct phy_device *phydev)
 	u16 val = 0;
 	int err;
 
-	err = priv->phy_drv->read_status(phydev);
+	if (priv->phy_drv->read_status)
+		err = priv->phy_drv->read_status(phydev);
+	else
+		err = genphy_read_status(phydev);
 	if (err < 0)
 		return err;
 
-- 
2.20.1


From ac640f557bddd6fa2876f72a6bf2e443d50a8bed Mon Sep 17 00:00:00 2001
From: Jose Abreu <jose.abreu@synopsys.com>
Date: Mon, 18 Feb 2019 14:35:03 +0100
Subject: [PATCH 11/21] net: stmmac: Fix a race in EEE enable callback

[ Upstream commit 8a7493e58ad688eb23b81e45461c5d314f4402f1 ]

We are saving the status of EEE even before we try to enable it. This
leads to a race with XMIT function that tries to arm EEE timer before we
set it up.

Fix this by only saving the EEE parameters after all operations are
performed with success.

Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Fixes: d765955d2ae0 ("stmmac: add the Energy Efficient Ethernet support")
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/stmicro/stmmac/stmmac_ethtool.c  | 22 ++++++++++---------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index 5710864fa809..9caf79ba5ef1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -692,25 +692,27 @@ static int stmmac_ethtool_op_set_eee(struct net_device *dev,
 				     struct ethtool_eee *edata)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
+	int ret;
 
-	priv->eee_enabled = edata->eee_enabled;
-
-	if (!priv->eee_enabled)
+	if (!edata->eee_enabled) {
 		stmmac_disable_eee_mode(priv);
-	else {
+	} else {
 		/* We are asking for enabling the EEE but it is safe
 		 * to verify all by invoking the eee_init function.
 		 * In case of failure it will return an error.
 		 */
-		priv->eee_enabled = stmmac_eee_init(priv);
-		if (!priv->eee_enabled)
+		edata->eee_enabled = stmmac_eee_init(priv);
+		if (!edata->eee_enabled)
 			return -EOPNOTSUPP;
-
-		/* Do not change tx_lpi_timer in case of failure */
-		priv->tx_lpi_timer = edata->tx_lpi_timer;
 	}
 
-	return phy_ethtool_set_eee(dev->phydev, edata);
+	ret = phy_ethtool_set_eee(dev->phydev, edata);
+	if (ret)
+		return ret;
+
+	priv->eee_enabled = edata->eee_enabled;
+	priv->tx_lpi_timer = edata->tx_lpi_timer;
+	return 0;
 }
 
 static u32 stmmac_usec2riwt(u32 usec, struct stmmac_priv *priv)
-- 
2.20.1


From e9c4f323601a484df838385e4ed3b4eeecec22ed Mon Sep 17 00:00:00 2001
From: Alexandre Torgue <alexandre.torgue@st.com>
Date: Fri, 15 Feb 2019 10:49:09 +0100
Subject: [PATCH 12/21] net: stmmac: handle endianness in dwmac4_get_timestamp

[ Upstream commit 224babd62d6f19581757a6d8bae3bf9501fc10de ]

GMAC IP is little-endian and used on several kind of CPU (big or little
endian). Main callbacks functions of the stmmac drivers take care about
it. It was not the case for dwmac4_get_timestamp function.

Fixes: ba1ffd74df74 ("stmmac: fix PTP support for GMAC4")
Signed-off-by: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
index 20299f6f65fc..736e29635b77 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
@@ -241,15 +241,18 @@ static inline void dwmac4_get_timestamp(void *desc, u32 ats, u64 *ts)
 static int dwmac4_rx_check_timestamp(void *desc)
 {
 	struct dma_desc *p = (struct dma_desc *)desc;
+	unsigned int rdes0 = le32_to_cpu(p->des0);
+	unsigned int rdes1 = le32_to_cpu(p->des1);
+	unsigned int rdes3 = le32_to_cpu(p->des3);
 	u32 own, ctxt;
 	int ret = 1;
 
-	own = p->des3 & RDES3_OWN;
-	ctxt = ((p->des3 & RDES3_CONTEXT_DESCRIPTOR)
+	own = rdes3 & RDES3_OWN;
+	ctxt = ((rdes3 & RDES3_CONTEXT_DESCRIPTOR)
 		>> RDES3_CONTEXT_DESCRIPTOR_SHIFT);
 
 	if (likely(!own && ctxt)) {
-		if ((p->des0 == 0xffffffff) && (p->des1 == 0xffffffff))
+		if ((rdes0 == 0xffffffff) && (rdes1 == 0xffffffff))
 			/* Corrupted value */
 			ret = -EINVAL;
 		else
-- 
2.20.1


From aa2ba2d4f7bad075e2c16800d1e808c5e3dc4477 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 15 Feb 2019 12:15:47 -0500
Subject: [PATCH 13/21] net: validate untrusted gso packets without csum
 offload

[ Upstream commit d5be7f632bad0f489879eed0ff4b99bd7fe0b74c ]

Syzkaller again found a path to a kernel crash through bad gso input.
By building an excessively large packet to cause an skb field to wrap.

If VIRTIO_NET_HDR_F_NEEDS_CSUM was set this would have been dropped in
skb_partial_csum_set.

GSO packets that do not set checksum offload are suspicious and rare.
Most callers of virtio_net_hdr_to_skb already pass them to
skb_probe_transport_header.

Move that test forward, change it to detect parse failure and drop
packets on failure as those cleary are not one of the legitimate
VIRTIO_NET_HDR_GSO types.

Fixes: bfd5f4a3d605 ("packet: Add GSO/csum offload support.")
Fixes: f43798c27684 ("tun: Allow GSO using virtio_net_hdr")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h     | 2 +-
 include/linux/virtio_net.h | 9 +++++++++
 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index a6d820ad17f0..8e63c166765e 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2418,7 +2418,7 @@ static inline void skb_probe_transport_header(struct sk_buff *skb,
 
 	if (skb_flow_dissect_flow_keys_basic(skb, &keys, NULL, 0, 0, 0, 0))
 		skb_set_transport_header(skb, keys.control.thoff);
-	else
+	else if (offset_hint >= 0)
 		skb_set_transport_header(skb, offset_hint);
 }
 
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index cb462f9ab7dd..71f2394abbf7 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -57,6 +57,15 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 
 		if (!skb_partial_csum_set(skb, start, off))
 			return -EINVAL;
+	} else {
+		/* gso packets without NEEDS_CSUM do not set transport_offset.
+		 * probe and drop if does not match one of the above types.
+		 */
+		if (gso_type) {
+			skb_probe_transport_header(skb, -1);
+			if (!skb_transport_header_was_set(skb))
+				return -EINVAL;
+		}
 	}
 
 	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
-- 
2.20.1


From 23010860897a6362d0c5893d881667b8fccd79af Mon Sep 17 00:00:00 2001
From: Kai-Heng Feng <kai.heng.feng@canonical.com>
Date: Tue, 19 Feb 2019 23:45:29 +0800
Subject: [PATCH 14/21] sky2: Increase D3 delay again

[ Upstream commit 1765f5dcd00963e33f1b8a4e0f34061fbc0e2f7f ]

Another platform requires even longer delay to make the device work
correctly after S3.

So increase the delay to 300ms.

BugLink: https://bugs.launchpad.net/bugs/1798921

Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/sky2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index 697d9b374f5e..ae2f35039343 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -5087,7 +5087,7 @@ static int sky2_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	INIT_WORK(&hw->restart_work, sky2_restart);
 
 	pci_set_drvdata(pdev, hw);
-	pdev->d3_delay = 200;
+	pdev->d3_delay = 300;
 
 	return 0;
 
-- 
2.20.1


From 5d51a33532faee2def499ff2c4519cfb6e2617e1 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Tue, 19 Feb 2019 14:53:44 +0800
Subject: [PATCH 15/21] vhost: correctly check the return value of
 translate_desc() in log_used()

[ Upstream commit 816db7663565cd23f74ed3d5c9240522e3fb0dda ]

When fail, translate_desc() returns negative value, otherwise the
number of iovs. So we should fail when the return value is negative
instead of a blindly check against zero.

Detected by CoverityScan, CID# 1442593:  Control flow issues  (DEADCODE)

Fixes: cc5e71075947 ("vhost: log dirty page correctly")
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Reported-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/vhost.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index cf82e7266397..5eaeca805c95 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -1784,7 +1784,7 @@ static int log_used(struct vhost_virtqueue *vq, u64 used_offset, u64 len)
 
 	ret = translate_desc(vq, (uintptr_t)vq->used + used_offset,
 			     len, iov, 64, VHOST_ACCESS_WO);
-	if (ret)
+	if (ret < 0)
 		return ret;
 
 	for (i = 0; i < ret; i++) {
-- 
2.20.1


From e24520fbe95beccd4e78e0bc2c78cfd44926a2ae Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sat, 16 Feb 2019 13:44:39 -0800
Subject: [PATCH 16/21] net: Add header for usage of fls64()

[ Upstream commit 8681ef1f3d295bd3600315325f3b3396d76d02f6 ]

Fixes: 3b89ea9c5902 ("net: Fix for_each_netdev_feature on Big endian")
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdev_features.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index fce28562bed2..4c76fe2c8488 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -11,6 +11,7 @@
 #define _LINUX_NETDEV_FEATURES_H
 
 #include <linux/types.h>
+#include <linux/bitops.h>
 #include <asm/byteorder.h>
 
 typedef u64 netdev_features_t;
-- 
2.20.1


From 1cdc45b7403a486f3cdb34fe17dca6b9892dd44f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 15 Feb 2019 13:36:20 -0800
Subject: [PATCH 17/21] tcp: clear icsk_backoff in tcp_write_queue_purge()

[ Upstream commit 04c03114be82194d4a4858d41dba8e286ad1787c ]

soukjin bae reported a crash in tcp_v4_err() handling
ICMP_DEST_UNREACH after tcp_write_queue_head(sk)
returned a NULL pointer.

Current logic should have prevented this :

  if (seq != tp->snd_una  || !icsk->icsk_retransmits ||
      !icsk->icsk_backoff || fastopen)
      break;

Problem is the write queue might have been purged
and icsk_backoff has not been cleared.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: soukjin bae <soukjin.bae@samsung.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 40cbe5609663..b102973102b9 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2532,6 +2532,7 @@ void tcp_write_queue_purge(struct sock *sk)
 	sk_mem_reclaim(sk);
 	tcp_clear_all_retrans_hints(tcp_sk(sk));
 	tcp_sk(sk)->packets_out = 0;
+	inet_csk(sk)->icsk_backoff = 0;
 }
 
 int tcp_disconnect(struct sock *sk, int flags)
@@ -2580,7 +2581,6 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tp->write_seq += tp->max_window + 2;
 	if (tp->write_seq == 0)
 		tp->write_seq = 1;
-	icsk->icsk_backoff = 0;
 	tp->snd_cwnd = 2;
 	icsk->icsk_probes_out = 0;
 	tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
-- 
2.20.1


From 2c2603b6f54484f1a60f66cfaa1639a2c8dbc8f4 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 15 Feb 2019 13:36:21 -0800
Subject: [PATCH 18/21] tcp: tcp_v4_err() should be more careful

[ Upstream commit 2c4cc9712364c051b1de2d175d5fbea6be948ebf ]

ICMP handlers are not very often stressed, we should
make them more resilient to bugs that might surface in
the future.

If there is no packet in retransmit queue, we should
avoid a NULL deref.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: soukjin bae <soukjin.bae@samsung.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index de47038afdf0..daedd75bb745 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -535,6 +535,10 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 		if (sock_owned_by_user(sk))
 			break;
 
+		skb = tcp_rtx_queue_head(sk);
+		if (WARN_ON_ONCE(!skb))
+			break;
+
 		icsk->icsk_backoff--;
 		icsk->icsk_rto = tp->srtt_us ? __tcp_set_rto(tp) :
 					       TCP_TIMEOUT_INIT;
-- 
2.20.1


From ea3b4d8e9b8530782a02e2a34f5b19c3201cc3d3 Mon Sep 17 00:00:00 2001
From: Murali Karicheri <m-karicheri2@ti.com>
Date: Mon, 18 Feb 2019 15:10:51 -0500
Subject: [PATCH 19/21] net: netcp: Fix ethss driver probe issue

[ Upstream commit 1f43f400a2cbb02f3d34de8fe30075c070254816 ]

Recent commit below has introduced a bug in netcp driver that causes
the ethss driver probe failure and thus break the networking function
on K2 SoCs such as K2HK, K2L, K2E etc. This patch fixes the issue to
restore networking on the above SoCs.

Fixes: 21c328dcecfc ("net: ethernet: Convert to using %pOFn instead of device_node.name")
Signed-off-by: Murali Karicheri <m-karicheri2@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/netcp_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c
index 1f612268c998..d847f672a705 100644
--- a/drivers/net/ethernet/ti/netcp_core.c
+++ b/drivers/net/ethernet/ti/netcp_core.c
@@ -259,7 +259,7 @@ static int netcp_module_probe(struct netcp_device *netcp_device,
 		const char *name;
 		char node_name[32];
 
-		if (of_property_read_string(node, "label", &name) < 0) {
+		if (of_property_read_string(child, "label", &name) < 0) {
 			snprintf(node_name, sizeof(node_name), "%pOFn", child);
 			name = node_name;
 		}
-- 
2.20.1


From 8a20e0f6d311094d82772737599dbdddbb2b68a7 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Date: Fri, 15 Feb 2019 14:44:18 -0800
Subject: [PATCH 20/21] net: Do not allocate page fragments that are not skb
 aligned

[ Upstream commit 3bed3cc4156eedf652b4df72bdb35d4f1a2a739d ]

This patch addresses the fact that there are drivers, specifically tun,
that will call into the network page fragment allocators with buffer sizes
that are not cache aligned. Doing this could result in data alignment
and DMA performance issues as these fragment pools are also shared with the
skb allocator and any other devices that will use napi_alloc_frags or
netdev_alloc_frags.

Fixes: ffde7328a36d ("net: Split netdev_alloc_frag into __alloc_page_frag and add __napi_alloc_frag")
Reported-by: Jann Horn <jannh@google.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index eebc3106d30e..fc3d652a2de0 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -353,6 +353,8 @@ static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
  */
 void *netdev_alloc_frag(unsigned int fragsz)
 {
+	fragsz = SKB_DATA_ALIGN(fragsz);
+
 	return __netdev_alloc_frag(fragsz, GFP_ATOMIC);
 }
 EXPORT_SYMBOL(netdev_alloc_frag);
@@ -366,6 +368,8 @@ static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
 
 void *napi_alloc_frag(unsigned int fragsz)
 {
+	fragsz = SKB_DATA_ALIGN(fragsz);
+
 	return __napi_alloc_frag(fragsz, GFP_ATOMIC);
 }
 EXPORT_SYMBOL(napi_alloc_frag);
-- 
2.20.1


From 90a0993c3fd2cce1f7053d8aab95c774a424698d Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Thu, 17 Jan 2019 11:27:22 +0100
Subject: [PATCH 21/21] af_packet: fix raw sockets over 6in4 tunnel

[ Upstream commit 88a8121dc1d3d0dbddd411b79ed236b6b6ea415c ]

Since commit cb9f1b783850, scapy (which uses an AF_PACKET socket in
SOCK_RAW mode) is unable to send a basic icmp packet over a sit tunnel:

Here is a example of the setup:
$ ip link set ntfp2 up
$ ip addr add 10.125.0.1/24 dev ntfp2
$ ip tunnel add tun1 mode sit ttl 64 local 10.125.0.1 remote 10.125.0.2 dev ntfp2
$ ip addr add fd00:cafe:cafe::1/128 dev tun1
$ ip link set dev tun1 up
$ ip route add fd00:200::/64 dev tun1
$ scapy
>>> p = []
>>> p += IPv6(src='fd00:100::1', dst='fd00:200::1')/ICMPv6EchoRequest()
>>> send(p, count=1, inter=0.1)
>>> quit()
$ ip -s link ls dev tun1 | grep -A1 "TX.*errors"
    TX: bytes  packets  errors  dropped carrier collsns
    0          0        1       0       0       0

The problem is that the network offset is set to the hard_header_len of the
output device (tun1, ie 14 + 20) and in our case, because the packet is
small (48 bytes) the pskb_inet_may_pull() fails (it tries to pull 40 bytes
(ipv6 header) starting from the network offset).

This problem is more generally related to device with variable hard header
length. To avoid a too intrusive patch in the current release, a (ugly)
workaround is proposed in this patch. It has to be cleaned up in net-next.

Link: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=993675a3100b1
Link: http://patchwork.ozlabs.org/patch/1024489/
Fixes: cb9f1b783850 ("ip: validate header length on virtual device xmit")
CC: Willem de Bruijn <willemb@google.com>
CC: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index d0945253f43b..3b1a78906bc0 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2887,7 +2887,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 			goto out_free;
 	} else if (reserve) {
 		skb_reserve(skb, -reserve);
-		if (len < reserve)
+		if (len < reserve + sizeof(struct ipv6hdr) &&
+		    dev->min_header_len != dev->hard_header_len)
 			skb_reset_network_header(skb);
 	}
 
-- 
2.20.1

Re: [PATCHES] Networking

[Sasha Levin]

On Wed, Feb 20, 2019 at 12:42:52PM -0800, David Miller wrote:
>
>Please queue up the following networking bug fixes for v4.19 and v4.20
>-stable, respectively.
>
>Thank you.

Now queued, thank you.

--
Thanks,
Sasha

Re: [PATCHES] Networking

[Greg KH]

On Wed, Feb 20, 2019 at 12:42:52PM -0800, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.19 and v4.20
> -stable, respectively.

Thanks for these, Sasha queued them up and I'll go through them for
older kernels as well.

Note, commit 2c4cc9712364 ("tcp: tcp_v4_err() should be more careful")
was backported a bit oddly, the later lines were not removed, so I fixed
that up by hand now.

thanks,

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 97 bytes --]


Please queue up the following networking bug fixes to v4.19 and v4.20
respectively.

Thank you!

[-- Attachment #2: net_419.mbox --]
[-- Type: Application/Octet-Stream, Size: 62891 bytes --]

From 1a62ffd1d0d09c0049cc7f9e178c11eb64ececcd Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 11 Feb 2019 14:41:22 -0800
Subject: [PATCH 01/21] batman-adv: fix uninit-value in batadv_interface_tx()

[ Upstream commit 4ffcbfac60642f63ae3d80891f573ba7e94a265c ]

KMSAN reported batadv_interface_tx() was possibly using a
garbage value [1]

batadv_get_vid() does have a pskb_may_pull() call
but batadv_interface_tx() does not actually make sure
this did not fail.

[1]
BUG: KMSAN: uninit-value in batadv_interface_tx+0x908/0x1e40 net/batman-adv/soft-interface.c:231
CPU: 0 PID: 10006 Comm: syz-executor469 Not tainted 4.20.0-rc7+ #5
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x173/0x1d0 lib/dump_stack.c:113
 kmsan_report+0x12e/0x2a0 mm/kmsan/kmsan.c:613
 __msan_warning+0x82/0xf0 mm/kmsan/kmsan_instr.c:313
 batadv_interface_tx+0x908/0x1e40 net/batman-adv/soft-interface.c:231
 __netdev_start_xmit include/linux/netdevice.h:4356 [inline]
 netdev_start_xmit include/linux/netdevice.h:4365 [inline]
 xmit_one net/core/dev.c:3257 [inline]
 dev_hard_start_xmit+0x607/0xc40 net/core/dev.c:3273
 __dev_queue_xmit+0x2e42/0x3bc0 net/core/dev.c:3843
 dev_queue_xmit+0x4b/0x60 net/core/dev.c:3876
 packet_snd net/packet/af_packet.c:2928 [inline]
 packet_sendmsg+0x8306/0x8f30 net/packet/af_packet.c:2953
 sock_sendmsg_nosec net/socket.c:621 [inline]
 sock_sendmsg net/socket.c:631 [inline]
 __sys_sendto+0x8c4/0xac0 net/socket.c:1788
 __do_sys_sendto net/socket.c:1800 [inline]
 __se_sys_sendto+0x107/0x130 net/socket.c:1796
 __x64_sys_sendto+0x6e/0x90 net/socket.c:1796
 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291
 entry_SYSCALL_64_after_hwframe+0x63/0xe7
RIP: 0033:0x441889
Code: 18 89 d0 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 bb 10 fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007ffdda6fd468 EFLAGS: 00000216 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 0000000000000002 RCX: 0000000000441889
RDX: 000000000000000e RSI: 00000000200000c0 RDI: 0000000000000003
RBP: 0000000000000003 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000216 R12: 00007ffdda6fd4c0
R13: 00007ffdda6fd4b0 R14: 0000000000000000 R15: 0000000000000000

Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:204 [inline]
 kmsan_internal_poison_shadow+0x92/0x150 mm/kmsan/kmsan.c:158
 kmsan_kmalloc+0xa6/0x130 mm/kmsan/kmsan_hooks.c:176
 kmsan_slab_alloc+0xe/0x10 mm/kmsan/kmsan_hooks.c:185
 slab_post_alloc_hook mm/slab.h:446 [inline]
 slab_alloc_node mm/slub.c:2759 [inline]
 __kmalloc_node_track_caller+0xe18/0x1030 mm/slub.c:4383
 __kmalloc_reserve net/core/skbuff.c:137 [inline]
 __alloc_skb+0x309/0xa20 net/core/skbuff.c:205
 alloc_skb include/linux/skbuff.h:998 [inline]
 alloc_skb_with_frags+0x1c7/0xac0 net/core/skbuff.c:5220
 sock_alloc_send_pskb+0xafd/0x10e0 net/core/sock.c:2083
 packet_alloc_skb net/packet/af_packet.c:2781 [inline]
 packet_snd net/packet/af_packet.c:2872 [inline]
 packet_sendmsg+0x661a/0x8f30 net/packet/af_packet.c:2953
 sock_sendmsg_nosec net/socket.c:621 [inline]
 sock_sendmsg net/socket.c:631 [inline]
 __sys_sendto+0x8c4/0xac0 net/socket.c:1788
 __do_sys_sendto net/socket.c:1800 [inline]
 __se_sys_sendto+0x107/0x130 net/socket.c:1796
 __x64_sys_sendto+0x6e/0x90 net/socket.c:1796
 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291
 entry_SYSCALL_64_after_hwframe+0x63/0xe7

Fixes: c6c8fea29769 ("net: Add batman-adv meshing protocol")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc:	Marek Lindner <mareklindner@neomailbox.ch>
Cc:	Simon Wunderlich <sw@simonwunderlich.de>
Cc:	Antonio Quartulli <a@unstable.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/batman-adv/soft-interface.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 3899fa6e201d..a2976adeeedc 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -227,6 +227,8 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb,
 
 	switch (ntohs(ethhdr->h_proto)) {
 	case ETH_P_8021Q:
+		if (!pskb_may_pull(skb, sizeof(*vhdr)))
+			goto dropped;
 		vhdr = vlan_eth_hdr(skb);
 
 		/* drop batman-in-batman packets to prevent loops */
-- 
2.20.1


From 596370bfdd8ad412bba1c5dd1390662983d9f3d4 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Date: Sat, 9 Feb 2019 13:35:52 +0300
Subject: [PATCH 02/21] inet_diag: fix reporting cgroup classid and fallback to
 priority

[ Upstream commit 1ec17dbd90f8b638f41ee650558609c1af63dfa0 ]

Field idiag_ext in struct inet_diag_req_v2 used as bitmap of requested
extensions has only 8 bits. Thus extensions starting from DCTCPINFO
cannot be requested directly. Some of them included into response
unconditionally or hook into some of lower 8 bits.

Extension INET_DIAG_CLASS_ID has not way to request from the beginning.

This patch bundle it with INET_DIAG_TCLASS (ipv6 tos), fixes space
reservation, and documents behavior for other extensions.

Also this patch adds fallback to reporting socket priority. This filed
is more widely used for traffic classification because ipv4 sockets
automatically maps TOS to priority and default qdisc pfifo_fast knows
about that. But priority could be changed via setsockopt SO_PRIORITY so
INET_DIAG_TOS isn't enough for predicting class.

Also cgroup2 obsoletes net_cls classid (it always zero), but we cannot
reuse this field for reporting cgroup2 id because it is 64-bit (ino+gen).

So, after this patch INET_DIAG_CLASS_ID will report socket priority
for most common setup when net_cls isn't set and/or cgroup2 in use.

Fixes: 0888e372c37f ("net: inet: diag: expose sockets cgroup classid")
Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/inet_diag.h | 16 +++++++++++-----
 net/ipv4/inet_diag.c           | 10 +++++++++-
 net/sctp/diag.c                |  1 +
 3 files changed, 21 insertions(+), 6 deletions(-)

diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h
index 14565d703291..e8baca85bac6 100644
--- a/include/uapi/linux/inet_diag.h
+++ b/include/uapi/linux/inet_diag.h
@@ -137,15 +137,21 @@ enum {
 	INET_DIAG_TCLASS,
 	INET_DIAG_SKMEMINFO,
 	INET_DIAG_SHUTDOWN,
-	INET_DIAG_DCTCPINFO,
-	INET_DIAG_PROTOCOL,  /* response attribute only */
+
+	/*
+	 * Next extenstions cannot be requested in struct inet_diag_req_v2:
+	 * its field idiag_ext has only 8 bits.
+	 */
+
+	INET_DIAG_DCTCPINFO,	/* request as INET_DIAG_VEGASINFO */
+	INET_DIAG_PROTOCOL,	/* response attribute only */
 	INET_DIAG_SKV6ONLY,
 	INET_DIAG_LOCALS,
 	INET_DIAG_PEERS,
 	INET_DIAG_PAD,
-	INET_DIAG_MARK,
-	INET_DIAG_BBRINFO,
-	INET_DIAG_CLASS_ID,
+	INET_DIAG_MARK,		/* only with CAP_NET_ADMIN */
+	INET_DIAG_BBRINFO,	/* request as INET_DIAG_VEGASINFO */
+	INET_DIAG_CLASS_ID,	/* request as INET_DIAG_TCLASS */
 	INET_DIAG_MD5SIG,
 	__INET_DIAG_MAX,
 };
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 1a4e9ff02762..5731670c560b 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -108,6 +108,7 @@ static size_t inet_sk_attr_size(struct sock *sk,
 		+ nla_total_size(1) /* INET_DIAG_TOS */
 		+ nla_total_size(1) /* INET_DIAG_TCLASS */
 		+ nla_total_size(4) /* INET_DIAG_MARK */
+		+ nla_total_size(4) /* INET_DIAG_CLASS_ID */
 		+ nla_total_size(sizeof(struct inet_diag_meminfo))
 		+ nla_total_size(sizeof(struct inet_diag_msg))
 		+ nla_total_size(SK_MEMINFO_VARS * sizeof(u32))
@@ -287,12 +288,19 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 			goto errout;
 	}
 
-	if (ext & (1 << (INET_DIAG_CLASS_ID - 1))) {
+	if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) ||
+	    ext & (1 << (INET_DIAG_TCLASS - 1))) {
 		u32 classid = 0;
 
 #ifdef CONFIG_SOCK_CGROUP_DATA
 		classid = sock_cgroup_classid(&sk->sk_cgrp_data);
 #endif
+		/* Fallback to socket priority if class id isn't set.
+		 * Classful qdiscs use it as direct reference to class.
+		 * For cgroup2 classid is always zero.
+		 */
+		if (!classid)
+			classid = sk->sk_priority;
 
 		if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid))
 			goto errout;
diff --git a/net/sctp/diag.c b/net/sctp/diag.c
index 078f01a8d582..435847d98b51 100644
--- a/net/sctp/diag.c
+++ b/net/sctp/diag.c
@@ -256,6 +256,7 @@ static size_t inet_assoc_attr_size(struct sctp_association *asoc)
 		+ nla_total_size(1) /* INET_DIAG_TOS */
 		+ nla_total_size(1) /* INET_DIAG_TCLASS */
 		+ nla_total_size(4) /* INET_DIAG_MARK */
+		+ nla_total_size(4) /* INET_DIAG_CLASS_ID */
 		+ nla_total_size(addrlen * asoc->peer.transport_count)
 		+ nla_total_size(addrlen * addrcnt)
 		+ nla_total_size(sizeof(struct inet_diag_meminfo))
-- 
2.20.1


From d2f2307b9c727f9bc0da03214fdbc491df8398c9 Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Mon, 11 Feb 2019 19:32:20 +0800
Subject: [PATCH 03/21] ipv6: propagate genlmsg_reply return code

[ Upstream commit d1f20798a119be71746949ba9b2e2ff330fdc038 ]

genlmsg_reply can fail, so propagate its return code

Fixes: 915d7e5e593 ("ipv6: sr: add code base for control plane support of SR-IPv6")
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/seg6.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c
index 8d0ba757a46c..9b2f272ca164 100644
--- a/net/ipv6/seg6.c
+++ b/net/ipv6/seg6.c
@@ -221,9 +221,7 @@ static int seg6_genl_get_tunsrc(struct sk_buff *skb, struct genl_info *info)
 	rcu_read_unlock();
 
 	genlmsg_end(msg, hdr);
-	genlmsg_reply(msg, info);
-
-	return 0;
+	return genlmsg_reply(msg, info);
 
 nla_put_failure:
 	rcu_read_unlock();
-- 
2.20.1


From 86c331dd92395c184632b8540f4bee88c186d993 Mon Sep 17 00:00:00 2001
From: Arthur Kiyanovski <akiyano@amazon.com>
Date: Mon, 11 Feb 2019 19:17:43 +0200
Subject: [PATCH 04/21] net: ena: fix race between link up and device
 initalization

[ Upstream commit e1f1bd9bfbedcfce428ee7e1b82a6ec12d4c3863 ]

Fix race condition between ena_update_on_link_change() and
ena_restore_device().

This race can occur if link notification arrives while the driver
is performing a reset sequence. In this case link can be set up,
enabling the device, before it is fully restored. If packets are
sent at this time, the driver might access uninitialized data
structures, causing kernel crash.

Move the clearing of ENA_FLAG_ONGOING_RESET and netif_carrier_on()
after ena_up() to ensure the device is ready when link is set up.

Fixes: d18e4f683445 ("net: ena: fix race condition between device reset and link up setup")
Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 4b73131a0f20..1b5f591cf0a2 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -2595,11 +2595,6 @@ static int ena_restore_device(struct ena_adapter *adapter)
 		goto err_device_destroy;
 	}
 
-	clear_bit(ENA_FLAG_ONGOING_RESET, &adapter->flags);
-	/* Make sure we don't have a race with AENQ Links state handler */
-	if (test_bit(ENA_FLAG_LINK_UP, &adapter->flags))
-		netif_carrier_on(adapter->netdev);
-
 	rc = ena_enable_msix_and_set_admin_interrupts(adapter,
 						      adapter->num_queues);
 	if (rc) {
@@ -2616,6 +2611,11 @@ static int ena_restore_device(struct ena_adapter *adapter)
 	}
 
 	set_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags);
+
+	clear_bit(ENA_FLAG_ONGOING_RESET, &adapter->flags);
+	if (test_bit(ENA_FLAG_LINK_UP, &adapter->flags))
+		netif_carrier_on(adapter->netdev);
+
 	mod_timer(&adapter->timer_service, round_jiffies(jiffies + HZ));
 	dev_err(&pdev->dev, "Device reset completed successfully\n");
 
-- 
2.20.1


From d1817d6084aaace8e6b1fca17d7a1a25ad7969f2 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 11 Feb 2019 18:04:17 +0200
Subject: [PATCH 05/21] net/mlx4_en: Force CHECKSUM_NONE for short ethernet
 frames

[ Upstream commit 29dded89e80e3fff61efb34f07a8a3fba3ea146d ]

When an ethernet frame is padded to meet the minimum ethernet frame
size, the padding octets are not covered by the hardware checksum.
Fortunately the padding octets are usually zero's, which don't affect
checksum. However, it is not guaranteed. For example, switches might
choose to make other use of these octets.
This repeatedly causes kernel hardware checksum fault.

Prior to the cited commit below, skb checksum was forced to be
CHECKSUM_NONE when padding is detected. After it, we need to keep
skb->csum updated. However, fixing up CHECKSUM_COMPLETE requires to
verify and parse IP headers, it does not worth the effort as the packets
are so small that CHECKSUM_COMPLETE has no significant advantage.

Future work: when reporting checksum complete is not an option for
IP non-TCP/UDP packets, we can actually fallback to report checksum
unnecessary, by looking at cqe IPOK bit.

Fixes: 88078d98d1bb ("net: pskb_trim_rcsum() and CHECKSUM_COMPLETE are friends")
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_rx.c | 22 ++++++++++++++++++++--
 1 file changed, 20 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index a1aeeb8094c3..f5cd9539980f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -620,6 +620,8 @@ static int get_fixed_ipv6_csum(__wsum hw_checksum, struct sk_buff *skb,
 }
 #endif
 
+#define short_frame(size) ((size) <= ETH_ZLEN + ETH_FCS_LEN)
+
 /* We reach this function only after checking that any of
  * the (IPv4 | IPv6) bits are set in cqe->status.
  */
@@ -627,9 +629,20 @@ static int check_csum(struct mlx4_cqe *cqe, struct sk_buff *skb, void *va,
 		      netdev_features_t dev_features)
 {
 	__wsum hw_checksum = 0;
+	void *hdr;
+
+	/* CQE csum doesn't cover padding octets in short ethernet
+	 * frames. And the pad field is appended prior to calculating
+	 * and appending the FCS field.
+	 *
+	 * Detecting these padded frames requires to verify and parse
+	 * IP headers, so we simply force all those small frames to skip
+	 * checksum complete.
+	 */
+	if (short_frame(skb->len))
+		return -EINVAL;
 
-	void *hdr = (u8 *)va + sizeof(struct ethhdr);
-
+	hdr = (u8 *)va + sizeof(struct ethhdr);
 	hw_checksum = csum_unfold((__force __sum16)cqe->checksum);
 
 	if (cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_CVLAN_PRESENT_MASK) &&
@@ -822,6 +835,11 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 		skb_record_rx_queue(skb, cq_ring);
 
 		if (likely(dev->features & NETIF_F_RXCSUM)) {
+			/* TODO: For IP non TCP/UDP packets when csum complete is
+			 * not an option (not supported or any other reason) we can
+			 * actually check cqe IPOK status bit and report
+			 * CHECKSUM_UNNECESSARY rather than CHECKSUM_NONE
+			 */
 			if ((cqe->status & cpu_to_be16(MLX4_CQE_STATUS_TCP |
 						       MLX4_CQE_STATUS_UDP)) &&
 			    (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPOK)) &&
-- 
2.20.1


From 142d1208a1e9f694e336834d061c9dae47a12fff Mon Sep 17 00:00:00 2001
From: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Date: Mon, 28 Jan 2019 15:28:06 -0800
Subject: [PATCH 06/21] net/mlx5e: Don't overwrite pedit action when multiple
 pedit used

[ Upstream commit 218d05ce326f9e1b40a56085431fa1068b43d5d9 ]

In some case, we may use multiple pedit actions to modify packets.
The command shown as below: the last pedit action is effective.

$ tc filter add dev netdev_rep parent ffff: protocol ip prio 1    \
	flower skip_sw ip_proto icmp dst_ip 3.3.3.3        \
	action pedit ex munge ip dst set 192.168.1.100 pipe    \
	action pedit ex munge eth src set 00:00:00:00:00:01 pipe    \
	action pedit ex munge eth dst set 00:00:00:00:00:02 pipe    \
	action csum ip pipe    \
	action tunnel_key set src_ip 1.1.1.100 dst_ip 1.1.1.200 dst_port 4789 id 100 \
	action mirred egress redirect dev vxlan0

To fix it, we add max_mod_hdr_actions to mlx5e_tc_flow_parse_attr struction,
max_mod_hdr_actions will store the max pedit action number we support and
num_mod_hdr_actions indicates how many pedit action we used, and store all
pedit action to mod_hdr_actions.

Fixes: d79b6df6b10a ("net/mlx5e: Add parsing of TC pedit actions to HW format")
Cc: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlx5/core/en_tc.c   | 25 +++++++++++--------
 1 file changed, 15 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 3092c59c0dc7..9f7f8425f676 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -96,6 +96,7 @@ struct mlx5e_tc_flow_parse_attr {
 	struct ip_tunnel_info tun_info;
 	struct mlx5_flow_spec spec;
 	int num_mod_hdr_actions;
+	int max_mod_hdr_actions;
 	void *mod_hdr_actions;
 	int mirred_ifindex;
 };
@@ -1742,9 +1743,9 @@ static struct mlx5_fields fields[] = {
 	OFFLOAD(UDP_DPORT, 2, udp.dest,   0),
 };
 
-/* On input attr->num_mod_hdr_actions tells how many HW actions can be parsed at
- * max from the SW pedit action. On success, it says how many HW actions were
- * actually parsed.
+/* On input attr->max_mod_hdr_actions tells how many HW actions can be parsed at
+ * max from the SW pedit action. On success, attr->num_mod_hdr_actions
+ * says how many HW actions were actually parsed.
  */
 static int offload_pedit_fields(struct pedit_headers *masks,
 				struct pedit_headers *vals,
@@ -1767,9 +1768,11 @@ static int offload_pedit_fields(struct pedit_headers *masks,
 	add_vals = &vals[TCA_PEDIT_KEY_EX_CMD_ADD];
 
 	action_size = MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto);
-	action = parse_attr->mod_hdr_actions;
-	max_actions = parse_attr->num_mod_hdr_actions;
-	nactions = 0;
+	action = parse_attr->mod_hdr_actions +
+		 parse_attr->num_mod_hdr_actions * action_size;
+
+	max_actions = parse_attr->max_mod_hdr_actions;
+	nactions = parse_attr->num_mod_hdr_actions;
 
 	for (i = 0; i < ARRAY_SIZE(fields); i++) {
 		f = &fields[i];
@@ -1874,7 +1877,7 @@ static int alloc_mod_hdr_actions(struct mlx5e_priv *priv,
 	if (!parse_attr->mod_hdr_actions)
 		return -ENOMEM;
 
-	parse_attr->num_mod_hdr_actions = max_actions;
+	parse_attr->max_mod_hdr_actions = max_actions;
 	return 0;
 }
 
@@ -1918,9 +1921,11 @@ static int parse_tc_pedit_action(struct mlx5e_priv *priv,
 			goto out_err;
 	}
 
-	err = alloc_mod_hdr_actions(priv, a, namespace, parse_attr);
-	if (err)
-		goto out_err;
+	if (!parse_attr->mod_hdr_actions) {
+		err = alloc_mod_hdr_actions(priv, a, namespace, parse_attr);
+		if (err)
+			goto out_err;
+	}
 
 	err = offload_pedit_fields(masks, vals, parse_attr);
 	if (err < 0)
-- 
2.20.1


From a9f4b827143415da272371d9f0d3235e55419d9c Mon Sep 17 00:00:00 2001
From: Kal Conley <kal.conley@dectris.com>
Date: Sun, 10 Feb 2019 09:57:11 +0100
Subject: [PATCH 07/21] net/packet: fix 4gb buffer limit due to overflow check

[ Upstream commit fc62814d690cf62189854464f4bd07457d5e9e50 ]

When calculating rb->frames_per_block * req->tp_block_nr the result
can overflow. Check it for overflow without limiting the total buffer
size to UINT_MAX.

This change fixes support for packet ring buffers >= UINT_MAX.

Fixes: 8f8d28e4d6d8 ("net/packet: fix overflow in check for tp_frame_nr")
Signed-off-by: Kal Conley <kal.conley@dectris.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index c76c21604ffd..fd16fb836df2 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -4275,7 +4275,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 		rb->frames_per_block = req->tp_block_size / req->tp_frame_size;
 		if (unlikely(rb->frames_per_block == 0))
 			goto out;
-		if (unlikely(req->tp_block_size > UINT_MAX / req->tp_block_nr))
+		if (unlikely(rb->frames_per_block > UINT_MAX / req->tp_block_nr))
 			goto out;
 		if (unlikely((rb->frames_per_block * req->tp_block_nr) !=
 					req->tp_frame_nr))
-- 
2.20.1


From 559e2a5f41db11e545f4389899385746b7752998 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Wed, 6 Feb 2019 10:52:30 +0000
Subject: [PATCH 08/21] net: sfp: do not probe SFP module before we're attached

[ Upstream commit b5bfc21af5cb3d53f9cee0ef82eaa43762a90f81 ]

When we probe a SFP module, we expect to be able to call the upstream
device's module_insert() function so that the upstream link can be
configured.  However, when the upstream device is delayed, we currently
may end up probing the module before the upstream device is available,
and lose the module_insert() call.

Avoid this by holding off probing the module until the SFP bus is
properly connected to both the SFP socket driver and the upstream
driver.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/sfp-bus.c |  2 ++
 drivers/net/phy/sfp.c     | 30 +++++++++++++++++++++---------
 drivers/net/phy/sfp.h     |  2 ++
 3 files changed, 25 insertions(+), 9 deletions(-)

diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c
index ad9db652874d..fef701bfad62 100644
--- a/drivers/net/phy/sfp-bus.c
+++ b/drivers/net/phy/sfp-bus.c
@@ -347,6 +347,7 @@ static int sfp_register_bus(struct sfp_bus *bus)
 				return ret;
 		}
 	}
+	bus->socket_ops->attach(bus->sfp);
 	if (bus->started)
 		bus->socket_ops->start(bus->sfp);
 	bus->netdev->sfp_bus = bus;
@@ -362,6 +363,7 @@ static void sfp_unregister_bus(struct sfp_bus *bus)
 	if (bus->registered) {
 		if (bus->started)
 			bus->socket_ops->stop(bus->sfp);
+		bus->socket_ops->detach(bus->sfp);
 		if (bus->phydev && ops && ops->disconnect_phy)
 			ops->disconnect_phy(bus->upstream);
 	}
diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index fd8bb998ae52..68c8fbf099f8 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -184,6 +184,7 @@ struct sfp {
 
 	struct gpio_desc *gpio[GPIO_MAX];
 
+	bool attached;
 	unsigned int state;
 	struct delayed_work poll;
 	struct delayed_work timeout;
@@ -1475,7 +1476,7 @@ static void sfp_sm_event(struct sfp *sfp, unsigned int event)
 	 */
 	switch (sfp->sm_mod_state) {
 	default:
-		if (event == SFP_E_INSERT) {
+		if (event == SFP_E_INSERT && sfp->attached) {
 			sfp_module_tx_disable(sfp);
 			sfp_sm_ins_next(sfp, SFP_MOD_PROBE, T_PROBE_INIT);
 		}
@@ -1607,6 +1608,19 @@ static void sfp_sm_event(struct sfp *sfp, unsigned int event)
 	mutex_unlock(&sfp->sm_mutex);
 }
 
+static void sfp_attach(struct sfp *sfp)
+{
+	sfp->attached = true;
+	if (sfp->state & SFP_F_PRESENT)
+		sfp_sm_event(sfp, SFP_E_INSERT);
+}
+
+static void sfp_detach(struct sfp *sfp)
+{
+	sfp->attached = false;
+	sfp_sm_event(sfp, SFP_E_REMOVE);
+}
+
 static void sfp_start(struct sfp *sfp)
 {
 	sfp_sm_event(sfp, SFP_E_DEV_UP);
@@ -1667,6 +1681,8 @@ static int sfp_module_eeprom(struct sfp *sfp, struct ethtool_eeprom *ee,
 }
 
 static const struct sfp_socket_ops sfp_module_ops = {
+	.attach = sfp_attach,
+	.detach = sfp_detach,
 	.start = sfp_start,
 	.stop = sfp_stop,
 	.module_info = sfp_module_info,
@@ -1834,10 +1850,6 @@ static int sfp_probe(struct platform_device *pdev)
 	dev_info(sfp->dev, "Host maximum power %u.%uW\n",
 		 sfp->max_power_mW / 1000, (sfp->max_power_mW / 100) % 10);
 
-	sfp->sfp_bus = sfp_register_socket(sfp->dev, sfp, &sfp_module_ops);
-	if (!sfp->sfp_bus)
-		return -ENOMEM;
-
 	/* Get the initial state, and always signal TX disable,
 	 * since the network interface will not be up.
 	 */
@@ -1848,10 +1860,6 @@ static int sfp_probe(struct platform_device *pdev)
 		sfp->state |= SFP_F_RATE_SELECT;
 	sfp_set_state(sfp, sfp->state);
 	sfp_module_tx_disable(sfp);
-	rtnl_lock();
-	if (sfp->state & SFP_F_PRESENT)
-		sfp_sm_event(sfp, SFP_E_INSERT);
-	rtnl_unlock();
 
 	for (i = 0; i < GPIO_MAX; i++) {
 		if (gpio_flags[i] != GPIOD_IN || !sfp->gpio[i])
@@ -1884,6 +1892,10 @@ static int sfp_probe(struct platform_device *pdev)
 		dev_warn(sfp->dev,
 			 "No tx_disable pin: SFP modules will always be emitting.\n");
 
+	sfp->sfp_bus = sfp_register_socket(sfp->dev, sfp, &sfp_module_ops);
+	if (!sfp->sfp_bus)
+		return -ENOMEM;
+
 	return 0;
 }
 
diff --git a/drivers/net/phy/sfp.h b/drivers/net/phy/sfp.h
index 31b0acf337e2..64f54b0bbd8c 100644
--- a/drivers/net/phy/sfp.h
+++ b/drivers/net/phy/sfp.h
@@ -7,6 +7,8 @@
 struct sfp;
 
 struct sfp_socket_ops {
+	void (*attach)(struct sfp *sfp);
+	void (*detach)(struct sfp *sfp);
 	void (*start)(struct sfp *sfp);
 	void (*stop)(struct sfp *sfp);
 	int (*module_info)(struct sfp *sfp, struct ethtool_modinfo *modinfo);
-- 
2.20.1


From 570d5d4f3248b3dc67fc6b80afbee4bdb04e70cf Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 12 Feb 2019 18:47:30 +0800
Subject: [PATCH 09/21] sctp: call gso_reset_checksum when computing checksum
 in sctp_gso_segment

[ Upstream commit fc228abc2347e106a44c0e9b29ab70b712c4ca51 ]

Jianlin reported a panic when running sctp gso over gre over vlan device:

  [   84.772930] RIP: 0010:do_csum+0x6d/0x170
  [   84.790605] Call Trace:
  [   84.791054]  csum_partial+0xd/0x20
  [   84.791657]  gre_gso_segment+0x2c3/0x390
  [   84.792364]  inet_gso_segment+0x161/0x3e0
  [   84.793071]  skb_mac_gso_segment+0xb8/0x120
  [   84.793846]  __skb_gso_segment+0x7e/0x180
  [   84.794581]  validate_xmit_skb+0x141/0x2e0
  [   84.795297]  __dev_queue_xmit+0x258/0x8f0
  [   84.795949]  ? eth_header+0x26/0xc0
  [   84.796581]  ip_finish_output2+0x196/0x430
  [   84.797295]  ? skb_gso_validate_network_len+0x11/0x80
  [   84.798183]  ? ip_finish_output+0x169/0x270
  [   84.798875]  ip_output+0x6c/0xe0
  [   84.799413]  ? ip_append_data.part.50+0xc0/0xc0
  [   84.800145]  iptunnel_xmit+0x144/0x1c0
  [   84.800814]  ip_tunnel_xmit+0x62d/0x930 [ip_tunnel]
  [   84.801699]  gre_tap_xmit+0xac/0xf0 [ip_gre]
  [   84.802395]  dev_hard_start_xmit+0xa5/0x210
  [   84.803086]  sch_direct_xmit+0x14f/0x340
  [   84.803733]  __dev_queue_xmit+0x799/0x8f0
  [   84.804472]  ip_finish_output2+0x2e0/0x430
  [   84.805255]  ? skb_gso_validate_network_len+0x11/0x80
  [   84.806154]  ip_output+0x6c/0xe0
  [   84.806721]  ? ip_append_data.part.50+0xc0/0xc0
  [   84.807516]  sctp_packet_transmit+0x716/0xa10 [sctp]
  [   84.808337]  sctp_outq_flush+0xd7/0x880 [sctp]

It was caused by SKB_GSO_CB(skb)->csum_start not set in sctp_gso_segment.
sctp_gso_segment() calls skb_segment() with 'feature | NETIF_F_HW_CSUM',
which causes SKB_GSO_CB(skb)->csum_start not to be set in skb_segment().

For TCP/UDP, when feature supports HW_CSUM, CHECKSUM_PARTIAL will be set
and gso_reset_checksum will be called to set SKB_GSO_CB(skb)->csum_start.

So SCTP should do the same as TCP/UDP, to call gso_reset_checksum() when
computing checksum in sctp_gso_segment.

Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/offload.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sctp/offload.c b/net/sctp/offload.c
index 123e9f2dc226..edfcf16e704c 100644
--- a/net/sctp/offload.c
+++ b/net/sctp/offload.c
@@ -36,6 +36,7 @@ static __le32 sctp_gso_make_checksum(struct sk_buff *skb)
 {
 	skb->ip_summed = CHECKSUM_NONE;
 	skb->csum_not_inet = 0;
+	gso_reset_checksum(skb, ~0);
 	return sctp_compute_cksum(skb, skb_transport_offset(skb));
 }
 
-- 
2.20.1


From cf3f5bec3637e2116c746b92e98851d7c465e6a0 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 12 Feb 2019 18:51:01 +0800
Subject: [PATCH 10/21] sctp: set stream ext to NULL after freeing it in
 sctp_stream_outq_migrate

[ Upstream commit af98c5a78517c04adb5fd68bb64b1ad6fe3d473f ]

In sctp_stream_init(), after sctp_stream_outq_migrate() freed the
surplus streams' ext, but sctp_stream_alloc_out() returns -ENOMEM,
stream->outcnt will not be set to 'outcnt'.

With the bigger value on stream->outcnt, when closing the assoc and
freeing its streams, the ext of those surplus streams will be freed
again since those stream exts were not set to NULL after freeing in
sctp_stream_outq_migrate(). Then the invalid-free issue reported by
syzbot would be triggered.

We fix it by simply setting them to NULL after freeing.

Fixes: 5bbbbe32a431 ("sctp: introduce stream scheduler foundations")
Reported-by: syzbot+58e480e7b28f2d890bfd@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/stream.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index f24633114dfd..2936ed17bf9e 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -144,8 +144,10 @@ static void sctp_stream_outq_migrate(struct sctp_stream *stream,
 		}
 	}
 
-	for (i = outcnt; i < stream->outcnt; i++)
+	for (i = outcnt; i < stream->outcnt; i++) {
 		kfree(SCTP_SO(stream, i)->ext);
+		SCTP_SO(stream, i)->ext = NULL;
+	}
 }
 
 static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt,
-- 
2.20.1


From ab92844d6dc4b89b9825b9391473e2b12aade1bf Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 11 Feb 2019 21:59:51 -0800
Subject: [PATCH 11/21] team: avoid complex list operations in
 team_nl_cmd_options_set()

[ Upstream commit 2fdeee2549231b1f989f011bb18191f5660d3745 ]

The current opt_inst_list operations inside team_nl_cmd_options_set()
is too complex to track:

    LIST_HEAD(opt_inst_list);
    nla_for_each_nested(...) {
        list_for_each_entry(opt_inst, &team->option_inst_list, list) {
            if (__team_option_inst_tmp_find(&opt_inst_list, opt_inst))
                continue;
            list_add(&opt_inst->tmp_list, &opt_inst_list);
        }
    }
    team_nl_send_event_options_get(team, &opt_inst_list);

as while we retrieve 'opt_inst' from team->option_inst_list, it could
be added to the local 'opt_inst_list' for multiple times. The
__team_option_inst_tmp_find() doesn't work, as the setter
team_mode_option_set() still calls team->ops.exit() which uses
->tmp_list too in __team_options_change_check().

Simplify the list operations by moving the 'opt_inst_list' and
team_nl_send_event_options_get() into the nla_for_each_nested() loop so
that it can be guranteed that we won't insert a same list entry for
multiple times. Therefore, __team_option_inst_tmp_find() can be removed
too.

Fixes: 4fb0534fb7bb ("team: avoid adding twice the same option to the event list")
Fixes: 2fcdb2c9e659 ("team: allow to send multiple set events in one message")
Reported-by: syzbot+4d4af685432dc0e56c91@syzkaller.appspotmail.com
Reported-by: syzbot+68ee510075cf64260cc4@syzkaller.appspotmail.com
Cc: Jiri Pirko <jiri@resnulli.us>
Cc: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 27 +++++----------------------
 1 file changed, 5 insertions(+), 22 deletions(-)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 4b6572f0188a..723814d84b7d 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -256,17 +256,6 @@ static void __team_option_inst_mark_removed_port(struct team *team,
 	}
 }
 
-static bool __team_option_inst_tmp_find(const struct list_head *opts,
-					const struct team_option_inst *needle)
-{
-	struct team_option_inst *opt_inst;
-
-	list_for_each_entry(opt_inst, opts, tmp_list)
-		if (opt_inst == needle)
-			return true;
-	return false;
-}
-
 static int __team_options_register(struct team *team,
 				   const struct team_option *option,
 				   size_t option_count)
@@ -2463,7 +2452,6 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info)
 	int err = 0;
 	int i;
 	struct nlattr *nl_option;
-	LIST_HEAD(opt_inst_list);
 
 	rtnl_lock();
 
@@ -2483,6 +2471,7 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info)
 		struct nlattr *opt_attrs[TEAM_ATTR_OPTION_MAX + 1];
 		struct nlattr *attr;
 		struct nlattr *attr_data;
+		LIST_HEAD(opt_inst_list);
 		enum team_option_type opt_type;
 		int opt_port_ifindex = 0; /* != 0 for per-port options */
 		u32 opt_array_index = 0;
@@ -2587,23 +2576,17 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info)
 			if (err)
 				goto team_put;
 			opt_inst->changed = true;
-
-			/* dumb/evil user-space can send us duplicate opt,
-			 * keep only the last one
-			 */
-			if (__team_option_inst_tmp_find(&opt_inst_list,
-							opt_inst))
-				continue;
-
 			list_add(&opt_inst->tmp_list, &opt_inst_list);
 		}
 		if (!opt_found) {
 			err = -ENOENT;
 			goto team_put;
 		}
-	}
 
-	err = team_nl_send_event_options_get(team, &opt_inst_list);
+		err = team_nl_send_event_options_get(team, &opt_inst_list);
+		if (err)
+			break;
+	}
 
 team_put:
 	team_nl_team_put(team);
-- 
2.20.1


From 4710f459d7bf6ae45fd2fb53fed3acdaf9c471e8 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 25 Jan 2019 22:43:17 +0100
Subject: [PATCH 12/21] Revert "socket: fix struct ifreq size in compat ioctl"

[ Upstream commit 63ff03ab786ab1bc6cca01d48eacd22c95b9b3eb ]

This reverts commit 1cebf8f143c2 ("socket: fix struct ifreq
size in compat ioctl"), it's a bugfix for another commit that
I'll revert next.

This is not a 'perfect' revert, I'm keeping some coding style
intact rather than revert to the state with indentation errors.

Cc: stable@vger.kernel.org
Fixes: 1cebf8f143c2 ("socket: fix struct ifreq size in compat ioctl")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/socket.c | 22 ++++++++--------------
 1 file changed, 8 insertions(+), 14 deletions(-)

diff --git a/net/socket.c b/net/socket.c
index 390a8ecef4bf..85a83553f8fa 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -941,8 +941,7 @@ void dlci_ioctl_set(int (*hook) (unsigned int, void __user *))
 EXPORT_SYMBOL(dlci_ioctl_set);
 
 static long sock_do_ioctl(struct net *net, struct socket *sock,
-			  unsigned int cmd, unsigned long arg,
-			  unsigned int ifreq_size)
+			  unsigned int cmd, unsigned long arg)
 {
 	int err;
 	void __user *argp = (void __user *)arg;
@@ -968,11 +967,11 @@ static long sock_do_ioctl(struct net *net, struct socket *sock,
 	} else {
 		struct ifreq ifr;
 		bool need_copyout;
-		if (copy_from_user(&ifr, argp, ifreq_size))
+		if (copy_from_user(&ifr, argp, sizeof(struct ifreq)))
 			return -EFAULT;
 		err = dev_ioctl(net, cmd, &ifr, &need_copyout);
 		if (!err && need_copyout)
-			if (copy_to_user(argp, &ifr, ifreq_size))
+			if (copy_to_user(argp, &ifr, sizeof(struct ifreq)))
 				return -EFAULT;
 	}
 	return err;
@@ -1071,8 +1070,7 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 			err = open_related_ns(&net->ns, get_net_ns);
 			break;
 		default:
-			err = sock_do_ioctl(net, sock, cmd, arg,
-					    sizeof(struct ifreq));
+			err = sock_do_ioctl(net, sock, cmd, arg);
 			break;
 		}
 	return err;
@@ -2752,8 +2750,7 @@ static int do_siocgstamp(struct net *net, struct socket *sock,
 	int err;
 
 	set_fs(KERNEL_DS);
-	err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv,
-			    sizeof(struct compat_ifreq));
+	err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv);
 	set_fs(old_fs);
 	if (!err)
 		err = compat_put_timeval(&ktv, up);
@@ -2769,8 +2766,7 @@ static int do_siocgstampns(struct net *net, struct socket *sock,
 	int err;
 
 	set_fs(KERNEL_DS);
-	err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts,
-			    sizeof(struct compat_ifreq));
+	err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts);
 	set_fs(old_fs);
 	if (!err)
 		err = compat_put_timespec(&kts, up);
@@ -3081,8 +3077,7 @@ static int routing_ioctl(struct net *net, struct socket *sock,
 	}
 
 	set_fs(KERNEL_DS);
-	ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r,
-			    sizeof(struct compat_ifreq));
+	ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r);
 	set_fs(old_fs);
 
 out:
@@ -3195,8 +3190,7 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
 	case SIOCBONDSETHWADDR:
 	case SIOCBONDCHANGEACTIVE:
 	case SIOCGIFNAME:
-		return sock_do_ioctl(net, sock, cmd, arg,
-				     sizeof(struct compat_ifreq));
+		return sock_do_ioctl(net, sock, cmd, arg);
 	}
 
 	return -ENOIOCTLCMD;
-- 
2.20.1


From 0f237e26f7b81612da1ae09b3d1b7061aae686e7 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 25 Jan 2019 22:43:18 +0100
Subject: [PATCH 13/21] Revert "kill dev_ifsioc()"

[ Upstream commit 37ac39bdddc528c998a9f36db36937de923fdf2a ]

This reverts commit bf4405737f9f ("kill dev_ifsioc()").

This wasn't really unused as implied by the original commit,
it still handles the copy to/from user differently, and the
commit thus caused issues such as
  https://bugzilla.kernel.org/show_bug.cgi?id=199469
and
  https://bugzilla.kernel.org/show_bug.cgi?id=202273

However, deviating from a strict revert, rename dev_ifsioc()
to compat_ifreq_ioctl() to be clearer as to its purpose and
add a comment.

Cc: stable@vger.kernel.org
Fixes: bf4405737f9f ("kill dev_ifsioc()")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/socket.c | 49 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 49 insertions(+)

diff --git a/net/socket.c b/net/socket.c
index 85a83553f8fa..e74ede56e903 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2962,6 +2962,53 @@ static int compat_ifr_data_ioctl(struct net *net, unsigned int cmd,
 	return dev_ioctl(net, cmd, &ifreq, NULL);
 }
 
+static int compat_ifreq_ioctl(struct net *net, struct socket *sock,
+			      unsigned int cmd,
+			      struct compat_ifreq __user *uifr32)
+{
+	struct ifreq __user *uifr;
+	int err;
+
+	/* Handle the fact that while struct ifreq has the same *layout* on
+	 * 32/64 for everything but ifreq::ifru_ifmap and ifreq::ifru_data,
+	 * which are handled elsewhere, it still has different *size* due to
+	 * ifreq::ifru_ifmap (which is 16 bytes on 32 bit, 24 bytes on 64-bit,
+	 * resulting in struct ifreq being 32 and 40 bytes respectively).
+	 * As a result, if the struct happens to be at the end of a page and
+	 * the next page isn't readable/writable, we get a fault. To prevent
+	 * that, copy back and forth to the full size.
+	 */
+
+	uifr = compat_alloc_user_space(sizeof(*uifr));
+	if (copy_in_user(uifr, uifr32, sizeof(*uifr32)))
+		return -EFAULT;
+
+	err = sock_do_ioctl(net, sock, cmd, (unsigned long)uifr);
+
+	if (!err) {
+		switch (cmd) {
+		case SIOCGIFFLAGS:
+		case SIOCGIFMETRIC:
+		case SIOCGIFMTU:
+		case SIOCGIFMEM:
+		case SIOCGIFHWADDR:
+		case SIOCGIFINDEX:
+		case SIOCGIFADDR:
+		case SIOCGIFBRDADDR:
+		case SIOCGIFDSTADDR:
+		case SIOCGIFNETMASK:
+		case SIOCGIFPFLAGS:
+		case SIOCGIFTXQLEN:
+		case SIOCGMIIPHY:
+		case SIOCGMIIREG:
+			if (copy_in_user(uifr32, uifr, sizeof(*uifr32)))
+				err = -EFAULT;
+			break;
+		}
+	}
+	return err;
+}
+
 static int compat_sioc_ifmap(struct net *net, unsigned int cmd,
 			struct compat_ifreq __user *uifr32)
 {
@@ -3181,6 +3228,8 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
 	case SIOCGMIIPHY:
 	case SIOCGMIIREG:
 	case SIOCSMIIREG:
+		return compat_ifreq_ioctl(net, sock, cmd, argp);
+
 	case SIOCSARP:
 	case SIOCGARP:
 	case SIOCDARP:
-- 
2.20.1


From 425356ecadf932539ad22a813c7321de9a262656 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 25 Jan 2019 22:43:19 +0100
Subject: [PATCH 14/21] net: socket: fix SIOCGIFNAME in compat

[ Upstream commit c6c9fee35dc27362b7bac34b2fc9f5b8ace2e22c ]

As reported by Robert O'Callahan in
https://bugzilla.kernel.org/show_bug.cgi?id=202273
reverting the previous changes in this area broke
the SIOCGIFNAME ioctl in compat again (I'd previously
fixed it after his previous report of breakage in
https://bugzilla.kernel.org/show_bug.cgi?id=199469).

This is obviously because I fixed SIOCGIFNAME more or
less by accident.

Fix it explicitly now by making it pass through the
restored compat translation code.

Cc: stable@vger.kernel.org
Fixes: 4cf808e7ac32 ("kill dev_ifname32()")
Reported-by: Robert O'Callahan <robert@ocallahan.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/socket.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/socket.c b/net/socket.c
index e74ede56e903..3b954cafd6a9 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -3001,6 +3001,7 @@ static int compat_ifreq_ioctl(struct net *net, struct socket *sock,
 		case SIOCGIFTXQLEN:
 		case SIOCGMIIPHY:
 		case SIOCGMIIREG:
+		case SIOCGIFNAME:
 			if (copy_in_user(uifr32, uifr, sizeof(*uifr32)))
 				err = -EFAULT;
 			break;
@@ -3224,6 +3225,7 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
 	case SIOCSIFTXQLEN:
 	case SIOCBRADDIF:
 	case SIOCBRDELIF:
+	case SIOCGIFNAME:
 	case SIOCSIFNAME:
 	case SIOCGMIIPHY:
 	case SIOCGMIIREG:
@@ -3238,7 +3240,6 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
 	case SIOCBONDRELEASE:
 	case SIOCBONDSETHWADDR:
 	case SIOCBONDCHANGEACTIVE:
-	case SIOCGIFNAME:
 		return sock_do_ioctl(net, sock, cmd, arg);
 	}
 
-- 
2.20.1


From aa3279ea4923d68a11378a87a95ea2b4f82178a2 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 25 Jan 2019 22:43:20 +0100
Subject: [PATCH 15/21] net: socket: make bond ioctls go through
 compat_ifreq_ioctl()

[ Upstream commit 98406133dd9cb9f195676eab540c270dceca879a ]

Same story as before, these use struct ifreq and thus need
to be read with the shorter version to not cause faults.

Cc: stable@vger.kernel.org
Fixes: f92d4fc95341 ("kill bond_ioctl()")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/socket.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/socket.c b/net/socket.c
index 3b954cafd6a9..5c820212ba81 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -3230,16 +3230,16 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
 	case SIOCGMIIPHY:
 	case SIOCGMIIREG:
 	case SIOCSMIIREG:
+	case SIOCBONDENSLAVE:
+	case SIOCBONDRELEASE:
+	case SIOCBONDSETHWADDR:
+	case SIOCBONDCHANGEACTIVE:
 		return compat_ifreq_ioctl(net, sock, cmd, argp);
 
 	case SIOCSARP:
 	case SIOCGARP:
 	case SIOCDARP:
 	case SIOCATMARK:
-	case SIOCBONDENSLAVE:
-	case SIOCBONDRELEASE:
-	case SIOCBONDSETHWADDR:
-	case SIOCBONDCHANGEACTIVE:
 		return sock_do_ioctl(net, sock, cmd, arg);
 	}
 
-- 
2.20.1


From e0379ae1854595fd2ac079e0d27d2a4a9e21e152 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Thu, 7 Feb 2019 18:36:10 +0800
Subject: [PATCH 16/21] geneve: should not call rt6_lookup() when ipv6 was
 disabled

[ Upstream commit c0a47e44c0980b3b23ee31fa7936d70ea5dce491 ]

When we add a new GENEVE device with IPv6 remote, checking only for
IS_ENABLED(CONFIG_IPV6) is not enough as we may disable IPv6 in the
kernel command line (ipv6.disable=1), and calling rt6_lookup() would
cause a NULL pointer dereference.

v2:
- don't mix declarations and code (reported by Stefano Brivio, Eric Dumazet)
- there's no need to use in6_dev_get() as we only need to check that
  idev exists (reported by David Ahern). This is under RTNL, so we can
  simply use __in6_dev_get() instead (Stefano, Eric).

Reported-by: Jianlin Shi <jishi@redhat.com>
Fixes: c40e89fd358e9 ("geneve: configure MTU based on a lower device")
Cc: Alexey Kodanev <alexey.kodanev@oracle.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 493cd382b8aa..01711e6e9a39 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1406,9 +1406,13 @@ static void geneve_link_config(struct net_device *dev,
 	}
 #if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6: {
-		struct rt6_info *rt = rt6_lookup(geneve->net,
-						 &info->key.u.ipv6.dst, NULL, 0,
-						 NULL, 0);
+		struct rt6_info *rt;
+
+		if (!__in6_dev_get(dev))
+			break;
+
+		rt = rt6_lookup(geneve->net, &info->key.u.ipv6.dst, NULL, 0,
+				NULL, 0);
 
 		if (rt && rt->dst.dev)
 			ldev_mtu = rt->dst.dev->mtu - GENEVE_IPV6_HLEN;
-- 
2.20.1


From c849486045981bfe469fb70de326b2b7ec6f89cb Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Thu, 7 Feb 2019 18:36:11 +0800
Subject: [PATCH 17/21] sit: check if IPv6 enabled before calling
 ip6_err_gen_icmpv6_unreach()

[ Upstream commit 173656accaf583698bac3f9e269884ba60d51ef4 ]

If we disabled IPv6 from the kernel command line (ipv6.disable=1), we should
not call ip6_err_gen_icmpv6_unreach(). This:

  ip link add sit1 type sit local 192.0.2.1 remote 192.0.2.2 ttl 1
  ip link set sit1 up
  ip addr add 198.51.100.1/24 dev sit1
  ping 198.51.100.2

if IPv6 is disabled at boot time, will crash the kernel.

v2: there's no need to use in6_dev_get(), use __in6_dev_get() instead,
    as we only need to check that idev exists and we are under
    rcu_read_lock() (from netif_receive_skb_internal()).

Reported-by: Jianlin Shi <jishi@redhat.com>
Fixes: ca15a078bd90 ("sit: generate icmpv6 error when receiving icmpv4 error")
Cc: Oussama Ghorbel <ghorbel@pivasoftware.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index eb162bd0e041..da6d5a3f5399 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -546,7 +546,8 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
 	}
 
 	err = 0;
-	if (!ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4, type, data_len))
+	if (__in6_dev_get(skb->dev) &&
+	    !ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4, type, data_len))
 		goto out;
 
 	if (t->parms.iph.daddr == 0)
-- 
2.20.1


From 296e61d24182b833cf82126d433ec73504126682 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 11 Feb 2019 13:06:14 -0800
Subject: [PATCH 18/21] net_sched: fix a race condition in tcindex_destroy()

[ Upstream commit 8015d93ebd27484418d4952284fd02172fa4b0b2 ]

tcindex_destroy() invokes tcindex_destroy_element() via
a walker to delete each filter result in its perfect hash
table, and tcindex_destroy_element() calls tcindex_delete()
which schedules tcf RCU works to do the final deletion work.
Unfortunately this races with the RCU callback
__tcindex_destroy(), which could lead to use-after-free as
reported by Adrian.

Fix this by migrating this RCU callback to tcf RCU work too,
as that workqueue is ordered, we will not have use-after-free.

Note, we don't need to hold netns refcnt because we don't call
tcf_exts_destroy() here.

Fixes: 27ce4f05e2ab ("net_sched: use tcf_queue_work() in tcindex filter")
Reported-by: Adrian <bugs@abtelecom.ro>
Cc: Ben Hutchings <ben@decadent.org.uk>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_tcindex.c | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 9ccc93f257db..79b52a637dda 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -48,7 +48,7 @@ struct tcindex_data {
 	u32 hash;		/* hash table size; 0 if undefined */
 	u32 alloc_hash;		/* allocated size */
 	u32 fall_through;	/* 0: only classify if explicit match */
-	struct rcu_head rcu;
+	struct rcu_work rwork;
 };
 
 static inline int tcindex_filter_is_set(struct tcindex_filter_result *r)
@@ -229,9 +229,11 @@ static int tcindex_destroy_element(struct tcf_proto *tp,
 	return tcindex_delete(tp, arg, &last, NULL);
 }
 
-static void __tcindex_destroy(struct rcu_head *head)
+static void tcindex_destroy_work(struct work_struct *work)
 {
-	struct tcindex_data *p = container_of(head, struct tcindex_data, rcu);
+	struct tcindex_data *p = container_of(to_rcu_work(work),
+					      struct tcindex_data,
+					      rwork);
 
 	kfree(p->perfect);
 	kfree(p->h);
@@ -258,9 +260,11 @@ static int tcindex_filter_result_init(struct tcindex_filter_result *r)
 	return tcf_exts_init(&r->exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
 }
 
-static void __tcindex_partial_destroy(struct rcu_head *head)
+static void tcindex_partial_destroy_work(struct work_struct *work)
 {
-	struct tcindex_data *p = container_of(head, struct tcindex_data, rcu);
+	struct tcindex_data *p = container_of(to_rcu_work(work),
+					      struct tcindex_data,
+					      rwork);
 
 	kfree(p->perfect);
 	kfree(p);
@@ -478,7 +482,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	}
 
 	if (oldp)
-		call_rcu(&oldp->rcu, __tcindex_partial_destroy);
+		tcf_queue_work(&oldp->rwork, tcindex_partial_destroy_work);
 	return 0;
 
 errout_alloc:
@@ -570,7 +574,7 @@ static void tcindex_destroy(struct tcf_proto *tp,
 	walker.fn = tcindex_destroy_element;
 	tcindex_walk(tp, &walker);
 
-	call_rcu(&p->rcu, __tcindex_destroy);
+	tcf_queue_work(&p->rwork, tcindex_destroy_work);
 }
 
 
-- 
2.20.1


From d9c31db3bc3663a865d9222e67ff1121464447f2 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 11 Feb 2019 13:06:15 -0800
Subject: [PATCH 19/21] net_sched: fix a memory leak in cls_tcindex

[ Upstream commit 033b228e7f26b29ae37f8bfa1bc6b209a5365e9f ]

When tcindex_destroy() destroys all the filter results in
the perfect hash table, it invokes the walker to delete
each of them. However, results with class==0 are skipped
in either tcindex_walk() or tcindex_delete(), which causes
a memory leak reported by kmemleak.

This patch fixes it by skipping the walker and directly
deleting these filter results so we don't miss any filter
result.

As a result of this change, we have to initialize exts->net
properly in tcindex_alloc_perfect_hash(). For net-next, we
need to consider whether we should initialize ->net in
tcf_exts_init() instead, before that just directly test
CONFIG_NET_CLS_ACT=y.

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_tcindex.c | 46 +++++++++++++++++++++++++++--------------
 1 file changed, 30 insertions(+), 16 deletions(-)

diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 79b52a637dda..70ea5b1a7889 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -221,14 +221,6 @@ static int tcindex_delete(struct tcf_proto *tp, void *arg, bool *last,
 	return 0;
 }
 
-static int tcindex_destroy_element(struct tcf_proto *tp,
-				   void *arg, struct tcf_walker *walker)
-{
-	bool last;
-
-	return tcindex_delete(tp, arg, &last, NULL);
-}
-
 static void tcindex_destroy_work(struct work_struct *work)
 {
 	struct tcindex_data *p = container_of(to_rcu_work(work),
@@ -279,7 +271,7 @@ static void tcindex_free_perfect_hash(struct tcindex_data *cp)
 	kfree(cp->perfect);
 }
 
-static int tcindex_alloc_perfect_hash(struct tcindex_data *cp)
+static int tcindex_alloc_perfect_hash(struct net *net, struct tcindex_data *cp)
 {
 	int i, err = 0;
 
@@ -293,6 +285,9 @@ static int tcindex_alloc_perfect_hash(struct tcindex_data *cp)
 				    TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
 		if (err < 0)
 			goto errout;
+#ifdef CONFIG_NET_CLS_ACT
+		cp->perfect[i].exts.net = net;
+#endif
 	}
 
 	return 0;
@@ -341,7 +336,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	if (p->perfect) {
 		int i;
 
-		if (tcindex_alloc_perfect_hash(cp) < 0)
+		if (tcindex_alloc_perfect_hash(net, cp) < 0)
 			goto errout;
 		for (i = 0; i < cp->hash; i++)
 			cp->perfect[i].res = p->perfect[i].res;
@@ -410,7 +405,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	err = -ENOMEM;
 	if (!cp->perfect && !cp->h) {
 		if (valid_perfect_hash(cp)) {
-			if (tcindex_alloc_perfect_hash(cp) < 0)
+			if (tcindex_alloc_perfect_hash(net, cp) < 0)
 				goto errout_alloc;
 			balloc = 1;
 		} else {
@@ -566,13 +561,32 @@ static void tcindex_destroy(struct tcf_proto *tp,
 			    struct netlink_ext_ack *extack)
 {
 	struct tcindex_data *p = rtnl_dereference(tp->root);
-	struct tcf_walker walker;
+	int i;
 
 	pr_debug("tcindex_destroy(tp %p),p %p\n", tp, p);
-	walker.count = 0;
-	walker.skip = 0;
-	walker.fn = tcindex_destroy_element;
-	tcindex_walk(tp, &walker);
+
+	if (p->perfect) {
+		for (i = 0; i < p->hash; i++) {
+			struct tcindex_filter_result *r = p->perfect + i;
+
+			tcf_unbind_filter(tp, &r->res);
+			if (tcf_exts_get_net(&r->exts))
+				tcf_queue_work(&r->rwork,
+					       tcindex_destroy_rexts_work);
+			else
+				__tcindex_destroy_rexts(r);
+		}
+	}
+
+	for (i = 0; p->h && i < p->hash; i++) {
+		struct tcindex_filter *f, *next;
+		bool last;
+
+		for (f = rtnl_dereference(p->h[i]); f; f = next) {
+			next = rtnl_dereference(f->next);
+			tcindex_delete(tp, &f->result, &last, NULL);
+		}
+	}
 
 	tcf_queue_work(&p->rwork, tcindex_destroy_work);
 }
-- 
2.20.1


From 5f68ce827c827cd0d0156687ec9e02d6db81da4f Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 11 Feb 2019 13:06:16 -0800
Subject: [PATCH 20/21] net_sched: fix two more memory leaks in cls_tcindex

[ Upstream commit 1db817e75f5b9387b8db11e37d5f0624eb9223e0 ]

struct tcindex_filter_result contains two parts:
struct tcf_exts and struct tcf_result.

For the local variable 'cr', its exts part is never used but
initialized without being released properly on success path. So
just completely remove the exts part to fix this leak.

For the local variable 'new_filter_result', it is never properly
released if not used by 'r' on success path.

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_tcindex.c | 16 +++++++---------
 1 file changed, 7 insertions(+), 9 deletions(-)

diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 70ea5b1a7889..38bb882bb958 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -304,9 +304,9 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 		  struct nlattr *est, bool ovr, struct netlink_ext_ack *extack)
 {
 	struct tcindex_filter_result new_filter_result, *old_r = r;
-	struct tcindex_filter_result cr;
 	struct tcindex_data *cp = NULL, *oldp;
 	struct tcindex_filter *f = NULL; /* make gcc behave */
+	struct tcf_result cr = {};
 	int err, balloc = 0;
 	struct tcf_exts e;
 
@@ -345,13 +345,10 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	cp->h = p->h;
 
 	err = tcindex_filter_result_init(&new_filter_result);
-	if (err < 0)
-		goto errout1;
-	err = tcindex_filter_result_init(&cr);
 	if (err < 0)
 		goto errout1;
 	if (old_r)
-		cr.res = r->res;
+		cr = r->res;
 
 	if (tb[TCA_TCINDEX_HASH])
 		cp->hash = nla_get_u32(tb[TCA_TCINDEX_HASH]);
@@ -442,8 +439,8 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	}
 
 	if (tb[TCA_TCINDEX_CLASSID]) {
-		cr.res.classid = nla_get_u32(tb[TCA_TCINDEX_CLASSID]);
-		tcf_bind_filter(tp, &cr.res, base);
+		cr.classid = nla_get_u32(tb[TCA_TCINDEX_CLASSID]);
+		tcf_bind_filter(tp, &cr, base);
 	}
 
 	if (old_r && old_r != r) {
@@ -455,7 +452,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	}
 
 	oldp = p;
-	r->res = cr.res;
+	r->res = cr;
 	tcf_exts_change(&r->exts, &e);
 
 	rcu_assign_pointer(tp->root, cp);
@@ -474,6 +471,8 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 				; /* nothing */
 
 		rcu_assign_pointer(*fp, f);
+	} else {
+		tcf_exts_destroy(&new_filter_result.exts);
 	}
 
 	if (oldp)
@@ -486,7 +485,6 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	else if (balloc == 2)
 		kfree(cp->h);
 errout1:
-	tcf_exts_destroy(&cr.exts);
 	tcf_exts_destroy(&new_filter_result.exts);
 errout:
 	kfree(cp);
-- 
2.20.1


From 95109783c9e10011cb5dab12ce4b1ec020417317 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 11 Feb 2019 16:27:02 -0800
Subject: [PATCH 21/21] net/mlx5e: XDP, fix redirect resources availability
 check
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 407e17b1a69a51ba9a512a04342da56c1f931df4 ]

Currently mlx5 driver creates xdp redirect hw queues unconditionally on
netdevice open, This is great until someone starts redirecting XDP traffic
via ndo_xdp_xmit on mlx5 device and changes the device configuration at
the same time, this might cause crashes, since the other device's napi
is not aware of the mlx5 state change (resources un-availability).

To fix this we must synchronize with other devices napi's on the system.
Added a new flag under mlx5e_priv to determine XDP TX resources are
available, set/clear it up when necessary and use synchronize_rcu()
when the flag is turned off, so other napi's are in-sync with it, before
we actually cleanup the hw resources.

The flag is tested prior to committing to transmit on mlx5e_xdp_xmit, and
it is sufficient to determine if it safe to transmit or not. The other
two internal flags (MLX5E_STATE_OPENED and MLX5E_SQ_STATE_ENABLED) become
unnecessary. Thus, they are removed from data path.

Fixes: 58b99ee3e3eb ("net/mlx5e: Add support for XDP_REDIRECT in device-out side")
Reported-by: Toke Høiland-Jørgensen <toke@redhat.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h    |  1 +
 .../net/ethernet/mellanox/mlx5/core/en/xdp.c    |  6 ++----
 .../net/ethernet/mellanox/mlx5/core/en/xdp.h    | 17 +++++++++++++++++
 .../net/ethernet/mellanox/mlx5/core/en_main.c   |  2 ++
 4 files changed, 22 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 16ceeb1b2c9d..da52e60d4437 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -633,6 +633,7 @@ enum {
 	MLX5E_STATE_ASYNC_EVENTS_ENABLED,
 	MLX5E_STATE_OPENED,
 	MLX5E_STATE_DESTROYING,
+	MLX5E_STATE_XDP_TX_ENABLED,
 };
 
 struct mlx5e_rqt {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index ad6d471d00dd..4a33c9a7cac7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -262,7 +262,8 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 	int sq_num;
 	int i;
 
-	if (unlikely(!test_bit(MLX5E_STATE_OPENED, &priv->state)))
+	/* this flag is sufficient, no need to test internal sq state */
+	if (unlikely(!mlx5e_xdp_tx_is_enabled(priv)))
 		return -ENETDOWN;
 
 	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
@@ -275,9 +276,6 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 
 	sq = &priv->channels.c[sq_num]->xdpsq;
 
-	if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
-		return -ENETDOWN;
-
 	for (i = 0; i < n; i++) {
 		struct xdp_frame *xdpf = frames[i];
 		struct mlx5e_xdp_info xdpi;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index 6dfab045925f..4d096623178b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -49,6 +49,23 @@ bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi);
 int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 		   u32 flags);
 
+static inline void mlx5e_xdp_tx_enable(struct mlx5e_priv *priv)
+{
+	set_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state);
+}
+
+static inline void mlx5e_xdp_tx_disable(struct mlx5e_priv *priv)
+{
+	clear_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state);
+	/* let other device's napi(s) see our new state */
+	synchronize_rcu();
+}
+
+static inline bool mlx5e_xdp_tx_is_enabled(struct mlx5e_priv *priv)
+{
+	return test_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state);
+}
+
 static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq)
 {
 	struct mlx5_wq_cyc *wq = &sq->wq;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 944f21f99d43..637d59c01fe5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2890,6 +2890,7 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv)
 
 	mlx5e_build_tx2sq_maps(priv);
 	mlx5e_activate_channels(&priv->channels);
+	mlx5e_xdp_tx_enable(priv);
 	netif_tx_start_all_queues(priv->netdev);
 
 	if (MLX5_ESWITCH_MANAGER(priv->mdev))
@@ -2911,6 +2912,7 @@ void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv)
 	 */
 	netif_tx_stop_all_queues(priv->netdev);
 	netif_tx_disable(priv->netdev);
+	mlx5e_xdp_tx_disable(priv);
 	mlx5e_deactivate_channels(&priv->channels);
 }
 
-- 
2.20.1


[-- Attachment #3: net_420.mbox --]
[-- Type: Application/Octet-Stream, Size: 66644 bytes --]

From 64bfb5716f7704cb8cef973e5a7413dcbfc7ac18 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 11 Feb 2019 14:41:22 -0800
Subject: [PATCH 01/23] batman-adv: fix uninit-value in batadv_interface_tx()

[ Upstream commit 4ffcbfac60642f63ae3d80891f573ba7e94a265c ]

KMSAN reported batadv_interface_tx() was possibly using a
garbage value [1]

batadv_get_vid() does have a pskb_may_pull() call
but batadv_interface_tx() does not actually make sure
this did not fail.

[1]
BUG: KMSAN: uninit-value in batadv_interface_tx+0x908/0x1e40 net/batman-adv/soft-interface.c:231
CPU: 0 PID: 10006 Comm: syz-executor469 Not tainted 4.20.0-rc7+ #5
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x173/0x1d0 lib/dump_stack.c:113
 kmsan_report+0x12e/0x2a0 mm/kmsan/kmsan.c:613
 __msan_warning+0x82/0xf0 mm/kmsan/kmsan_instr.c:313
 batadv_interface_tx+0x908/0x1e40 net/batman-adv/soft-interface.c:231
 __netdev_start_xmit include/linux/netdevice.h:4356 [inline]
 netdev_start_xmit include/linux/netdevice.h:4365 [inline]
 xmit_one net/core/dev.c:3257 [inline]
 dev_hard_start_xmit+0x607/0xc40 net/core/dev.c:3273
 __dev_queue_xmit+0x2e42/0x3bc0 net/core/dev.c:3843
 dev_queue_xmit+0x4b/0x60 net/core/dev.c:3876
 packet_snd net/packet/af_packet.c:2928 [inline]
 packet_sendmsg+0x8306/0x8f30 net/packet/af_packet.c:2953
 sock_sendmsg_nosec net/socket.c:621 [inline]
 sock_sendmsg net/socket.c:631 [inline]
 __sys_sendto+0x8c4/0xac0 net/socket.c:1788
 __do_sys_sendto net/socket.c:1800 [inline]
 __se_sys_sendto+0x107/0x130 net/socket.c:1796
 __x64_sys_sendto+0x6e/0x90 net/socket.c:1796
 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291
 entry_SYSCALL_64_after_hwframe+0x63/0xe7
RIP: 0033:0x441889
Code: 18 89 d0 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 bb 10 fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007ffdda6fd468 EFLAGS: 00000216 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 0000000000000002 RCX: 0000000000441889
RDX: 000000000000000e RSI: 00000000200000c0 RDI: 0000000000000003
RBP: 0000000000000003 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000216 R12: 00007ffdda6fd4c0
R13: 00007ffdda6fd4b0 R14: 0000000000000000 R15: 0000000000000000

Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:204 [inline]
 kmsan_internal_poison_shadow+0x92/0x150 mm/kmsan/kmsan.c:158
 kmsan_kmalloc+0xa6/0x130 mm/kmsan/kmsan_hooks.c:176
 kmsan_slab_alloc+0xe/0x10 mm/kmsan/kmsan_hooks.c:185
 slab_post_alloc_hook mm/slab.h:446 [inline]
 slab_alloc_node mm/slub.c:2759 [inline]
 __kmalloc_node_track_caller+0xe18/0x1030 mm/slub.c:4383
 __kmalloc_reserve net/core/skbuff.c:137 [inline]
 __alloc_skb+0x309/0xa20 net/core/skbuff.c:205
 alloc_skb include/linux/skbuff.h:998 [inline]
 alloc_skb_with_frags+0x1c7/0xac0 net/core/skbuff.c:5220
 sock_alloc_send_pskb+0xafd/0x10e0 net/core/sock.c:2083
 packet_alloc_skb net/packet/af_packet.c:2781 [inline]
 packet_snd net/packet/af_packet.c:2872 [inline]
 packet_sendmsg+0x661a/0x8f30 net/packet/af_packet.c:2953
 sock_sendmsg_nosec net/socket.c:621 [inline]
 sock_sendmsg net/socket.c:631 [inline]
 __sys_sendto+0x8c4/0xac0 net/socket.c:1788
 __do_sys_sendto net/socket.c:1800 [inline]
 __se_sys_sendto+0x107/0x130 net/socket.c:1796
 __x64_sys_sendto+0x6e/0x90 net/socket.c:1796
 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291
 entry_SYSCALL_64_after_hwframe+0x63/0xe7

Fixes: c6c8fea29769 ("net: Add batman-adv meshing protocol")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc:	Marek Lindner <mareklindner@neomailbox.ch>
Cc:	Simon Wunderlich <sw@simonwunderlich.de>
Cc:	Antonio Quartulli <a@unstable.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/batman-adv/soft-interface.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index b85ca809e509..ffc83bebfe40 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -227,6 +227,8 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb,
 
 	switch (ntohs(ethhdr->h_proto)) {
 	case ETH_P_8021Q:
+		if (!pskb_may_pull(skb, sizeof(*vhdr)))
+			goto dropped;
 		vhdr = vlan_eth_hdr(skb);
 
 		/* drop batman-in-batman packets to prevent loops */
-- 
2.20.1


From 42685ecde52ed2d742f9ac9632ca7da53c332f10 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Date: Sat, 9 Feb 2019 13:35:52 +0300
Subject: [PATCH 02/23] inet_diag: fix reporting cgroup classid and fallback to
 priority

[ Upstream commit 1ec17dbd90f8b638f41ee650558609c1af63dfa0 ]

Field idiag_ext in struct inet_diag_req_v2 used as bitmap of requested
extensions has only 8 bits. Thus extensions starting from DCTCPINFO
cannot be requested directly. Some of them included into response
unconditionally or hook into some of lower 8 bits.

Extension INET_DIAG_CLASS_ID has not way to request from the beginning.

This patch bundle it with INET_DIAG_TCLASS (ipv6 tos), fixes space
reservation, and documents behavior for other extensions.

Also this patch adds fallback to reporting socket priority. This filed
is more widely used for traffic classification because ipv4 sockets
automatically maps TOS to priority and default qdisc pfifo_fast knows
about that. But priority could be changed via setsockopt SO_PRIORITY so
INET_DIAG_TOS isn't enough for predicting class.

Also cgroup2 obsoletes net_cls classid (it always zero), but we cannot
reuse this field for reporting cgroup2 id because it is 64-bit (ino+gen).

So, after this patch INET_DIAG_CLASS_ID will report socket priority
for most common setup when net_cls isn't set and/or cgroup2 in use.

Fixes: 0888e372c37f ("net: inet: diag: expose sockets cgroup classid")
Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/inet_diag.h | 16 +++++++++++-----
 net/ipv4/inet_diag.c           | 10 +++++++++-
 net/sctp/diag.c                |  1 +
 3 files changed, 21 insertions(+), 6 deletions(-)

diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h
index 14565d703291..e8baca85bac6 100644
--- a/include/uapi/linux/inet_diag.h
+++ b/include/uapi/linux/inet_diag.h
@@ -137,15 +137,21 @@ enum {
 	INET_DIAG_TCLASS,
 	INET_DIAG_SKMEMINFO,
 	INET_DIAG_SHUTDOWN,
-	INET_DIAG_DCTCPINFO,
-	INET_DIAG_PROTOCOL,  /* response attribute only */
+
+	/*
+	 * Next extenstions cannot be requested in struct inet_diag_req_v2:
+	 * its field idiag_ext has only 8 bits.
+	 */
+
+	INET_DIAG_DCTCPINFO,	/* request as INET_DIAG_VEGASINFO */
+	INET_DIAG_PROTOCOL,	/* response attribute only */
 	INET_DIAG_SKV6ONLY,
 	INET_DIAG_LOCALS,
 	INET_DIAG_PEERS,
 	INET_DIAG_PAD,
-	INET_DIAG_MARK,
-	INET_DIAG_BBRINFO,
-	INET_DIAG_CLASS_ID,
+	INET_DIAG_MARK,		/* only with CAP_NET_ADMIN */
+	INET_DIAG_BBRINFO,	/* request as INET_DIAG_VEGASINFO */
+	INET_DIAG_CLASS_ID,	/* request as INET_DIAG_TCLASS */
 	INET_DIAG_MD5SIG,
 	__INET_DIAG_MAX,
 };
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 1a4e9ff02762..5731670c560b 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -108,6 +108,7 @@ static size_t inet_sk_attr_size(struct sock *sk,
 		+ nla_total_size(1) /* INET_DIAG_TOS */
 		+ nla_total_size(1) /* INET_DIAG_TCLASS */
 		+ nla_total_size(4) /* INET_DIAG_MARK */
+		+ nla_total_size(4) /* INET_DIAG_CLASS_ID */
 		+ nla_total_size(sizeof(struct inet_diag_meminfo))
 		+ nla_total_size(sizeof(struct inet_diag_msg))
 		+ nla_total_size(SK_MEMINFO_VARS * sizeof(u32))
@@ -287,12 +288,19 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 			goto errout;
 	}
 
-	if (ext & (1 << (INET_DIAG_CLASS_ID - 1))) {
+	if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) ||
+	    ext & (1 << (INET_DIAG_TCLASS - 1))) {
 		u32 classid = 0;
 
 #ifdef CONFIG_SOCK_CGROUP_DATA
 		classid = sock_cgroup_classid(&sk->sk_cgrp_data);
 #endif
+		/* Fallback to socket priority if class id isn't set.
+		 * Classful qdiscs use it as direct reference to class.
+		 * For cgroup2 classid is always zero.
+		 */
+		if (!classid)
+			classid = sk->sk_priority;
 
 		if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid))
 			goto errout;
diff --git a/net/sctp/diag.c b/net/sctp/diag.c
index 078f01a8d582..435847d98b51 100644
--- a/net/sctp/diag.c
+++ b/net/sctp/diag.c
@@ -256,6 +256,7 @@ static size_t inet_assoc_attr_size(struct sctp_association *asoc)
 		+ nla_total_size(1) /* INET_DIAG_TOS */
 		+ nla_total_size(1) /* INET_DIAG_TCLASS */
 		+ nla_total_size(4) /* INET_DIAG_MARK */
+		+ nla_total_size(4) /* INET_DIAG_CLASS_ID */
 		+ nla_total_size(addrlen * asoc->peer.transport_count)
 		+ nla_total_size(addrlen * addrcnt)
 		+ nla_total_size(sizeof(struct inet_diag_meminfo))
-- 
2.20.1


From b2743bf9e8aee9c019b656d4a3e2e7bdd0f0ce73 Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Mon, 11 Feb 2019 19:32:20 +0800
Subject: [PATCH 03/23] ipv6: propagate genlmsg_reply return code

[ Upstream commit d1f20798a119be71746949ba9b2e2ff330fdc038 ]

genlmsg_reply can fail, so propagate its return code

Fixes: 915d7e5e593 ("ipv6: sr: add code base for control plane support of SR-IPv6")
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/seg6.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c
index 8d0ba757a46c..9b2f272ca164 100644
--- a/net/ipv6/seg6.c
+++ b/net/ipv6/seg6.c
@@ -221,9 +221,7 @@ static int seg6_genl_get_tunsrc(struct sk_buff *skb, struct genl_info *info)
 	rcu_read_unlock();
 
 	genlmsg_end(msg, hdr);
-	genlmsg_reply(msg, info);
-
-	return 0;
+	return genlmsg_reply(msg, info);
 
 nla_put_failure:
 	rcu_read_unlock();
-- 
2.20.1


From b59cf5f630e5fe13baeee2a1f12e48de00f2c1ed Mon Sep 17 00:00:00 2001
From: Arthur Kiyanovski <akiyano@amazon.com>
Date: Mon, 11 Feb 2019 19:17:43 +0200
Subject: [PATCH 04/23] net: ena: fix race between link up and device
 initalization

[ Upstream commit e1f1bd9bfbedcfce428ee7e1b82a6ec12d4c3863 ]

Fix race condition between ena_update_on_link_change() and
ena_restore_device().

This race can occur if link notification arrives while the driver
is performing a reset sequence. In this case link can be set up,
enabling the device, before it is fully restored. If packets are
sent at this time, the driver might access uninitialized data
structures, causing kernel crash.

Move the clearing of ENA_FLAG_ONGOING_RESET and netif_carrier_on()
after ena_up() to ensure the device is ready when link is set up.

Fixes: d18e4f683445 ("net: ena: fix race condition between device reset and link up setup")
Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index a70bb1bb90e7..a6eacf2099c3 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -2663,11 +2663,6 @@ static int ena_restore_device(struct ena_adapter *adapter)
 		goto err_device_destroy;
 	}
 
-	clear_bit(ENA_FLAG_ONGOING_RESET, &adapter->flags);
-	/* Make sure we don't have a race with AENQ Links state handler */
-	if (test_bit(ENA_FLAG_LINK_UP, &adapter->flags))
-		netif_carrier_on(adapter->netdev);
-
 	rc = ena_enable_msix_and_set_admin_interrupts(adapter,
 						      adapter->num_queues);
 	if (rc) {
@@ -2684,6 +2679,11 @@ static int ena_restore_device(struct ena_adapter *adapter)
 	}
 
 	set_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags);
+
+	clear_bit(ENA_FLAG_ONGOING_RESET, &adapter->flags);
+	if (test_bit(ENA_FLAG_LINK_UP, &adapter->flags))
+		netif_carrier_on(adapter->netdev);
+
 	mod_timer(&adapter->timer_service, round_jiffies(jiffies + HZ));
 	dev_err(&pdev->dev,
 		"Device reset completed successfully, Driver info: %s\n",
-- 
2.20.1


From c940cc2b20cea5b6fcd9be842faa14b79a5981c6 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 11 Feb 2019 18:04:17 +0200
Subject: [PATCH 05/23] net/mlx4_en: Force CHECKSUM_NONE for short ethernet
 frames

[ Upstream commit 29dded89e80e3fff61efb34f07a8a3fba3ea146d ]

When an ethernet frame is padded to meet the minimum ethernet frame
size, the padding octets are not covered by the hardware checksum.
Fortunately the padding octets are usually zero's, which don't affect
checksum. However, it is not guaranteed. For example, switches might
choose to make other use of these octets.
This repeatedly causes kernel hardware checksum fault.

Prior to the cited commit below, skb checksum was forced to be
CHECKSUM_NONE when padding is detected. After it, we need to keep
skb->csum updated. However, fixing up CHECKSUM_COMPLETE requires to
verify and parse IP headers, it does not worth the effort as the packets
are so small that CHECKSUM_COMPLETE has no significant advantage.

Future work: when reporting checksum complete is not an option for
IP non-TCP/UDP packets, we can actually fallback to report checksum
unnecessary, by looking at cqe IPOK bit.

Fixes: 88078d98d1bb ("net: pskb_trim_rcsum() and CHECKSUM_COMPLETE are friends")
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_rx.c | 22 ++++++++++++++++++++--
 1 file changed, 20 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index db00bf1c23f5..d47d4f86ac11 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -620,6 +620,8 @@ static int get_fixed_ipv6_csum(__wsum hw_checksum, struct sk_buff *skb,
 }
 #endif
 
+#define short_frame(size) ((size) <= ETH_ZLEN + ETH_FCS_LEN)
+
 /* We reach this function only after checking that any of
  * the (IPv4 | IPv6) bits are set in cqe->status.
  */
@@ -627,9 +629,20 @@ static int check_csum(struct mlx4_cqe *cqe, struct sk_buff *skb, void *va,
 		      netdev_features_t dev_features)
 {
 	__wsum hw_checksum = 0;
+	void *hdr;
+
+	/* CQE csum doesn't cover padding octets in short ethernet
+	 * frames. And the pad field is appended prior to calculating
+	 * and appending the FCS field.
+	 *
+	 * Detecting these padded frames requires to verify and parse
+	 * IP headers, so we simply force all those small frames to skip
+	 * checksum complete.
+	 */
+	if (short_frame(skb->len))
+		return -EINVAL;
 
-	void *hdr = (u8 *)va + sizeof(struct ethhdr);
-
+	hdr = (u8 *)va + sizeof(struct ethhdr);
 	hw_checksum = csum_unfold((__force __sum16)cqe->checksum);
 
 	if (cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_CVLAN_PRESENT_MASK) &&
@@ -822,6 +835,11 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 		skb_record_rx_queue(skb, cq_ring);
 
 		if (likely(dev->features & NETIF_F_RXCSUM)) {
+			/* TODO: For IP non TCP/UDP packets when csum complete is
+			 * not an option (not supported or any other reason) we can
+			 * actually check cqe IPOK status bit and report
+			 * CHECKSUM_UNNECESSARY rather than CHECKSUM_NONE
+			 */
 			if ((cqe->status & cpu_to_be16(MLX4_CQE_STATUS_TCP |
 						       MLX4_CQE_STATUS_UDP)) &&
 			    (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPOK)) &&
-- 
2.20.1


From d8f38971f41292dc2a203973721f192a2879346b Mon Sep 17 00:00:00 2001
From: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Date: Mon, 28 Jan 2019 15:28:06 -0800
Subject: [PATCH 06/23] net/mlx5e: Don't overwrite pedit action when multiple
 pedit used

[ Upstream commit 218d05ce326f9e1b40a56085431fa1068b43d5d9 ]

In some case, we may use multiple pedit actions to modify packets.
The command shown as below: the last pedit action is effective.

$ tc filter add dev netdev_rep parent ffff: protocol ip prio 1    \
	flower skip_sw ip_proto icmp dst_ip 3.3.3.3        \
	action pedit ex munge ip dst set 192.168.1.100 pipe    \
	action pedit ex munge eth src set 00:00:00:00:00:01 pipe    \
	action pedit ex munge eth dst set 00:00:00:00:00:02 pipe    \
	action csum ip pipe    \
	action tunnel_key set src_ip 1.1.1.100 dst_ip 1.1.1.200 dst_port 4789 id 100 \
	action mirred egress redirect dev vxlan0

To fix it, we add max_mod_hdr_actions to mlx5e_tc_flow_parse_attr struction,
max_mod_hdr_actions will store the max pedit action number we support and
num_mod_hdr_actions indicates how many pedit action we used, and store all
pedit action to mod_hdr_actions.

Fixes: d79b6df6b10a ("net/mlx5e: Add parsing of TC pedit actions to HW format")
Cc: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlx5/core/en_tc.c   | 25 +++++++++++--------
 1 file changed, 15 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 4e0151918db1..3fba80a8b436 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -98,6 +98,7 @@ struct mlx5e_tc_flow_parse_attr {
 	struct ip_tunnel_info tun_info;
 	struct mlx5_flow_spec spec;
 	int num_mod_hdr_actions;
+	int max_mod_hdr_actions;
 	void *mod_hdr_actions;
 	int mirred_ifindex;
 };
@@ -1888,9 +1889,9 @@ static struct mlx5_fields fields[] = {
 	OFFLOAD(UDP_DPORT, 2, udp.dest,   0),
 };
 
-/* On input attr->num_mod_hdr_actions tells how many HW actions can be parsed at
- * max from the SW pedit action. On success, it says how many HW actions were
- * actually parsed.
+/* On input attr->max_mod_hdr_actions tells how many HW actions can be parsed at
+ * max from the SW pedit action. On success, attr->num_mod_hdr_actions
+ * says how many HW actions were actually parsed.
  */
 static int offload_pedit_fields(struct pedit_headers *masks,
 				struct pedit_headers *vals,
@@ -1914,9 +1915,11 @@ static int offload_pedit_fields(struct pedit_headers *masks,
 	add_vals = &vals[TCA_PEDIT_KEY_EX_CMD_ADD];
 
 	action_size = MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto);
-	action = parse_attr->mod_hdr_actions;
-	max_actions = parse_attr->num_mod_hdr_actions;
-	nactions = 0;
+	action = parse_attr->mod_hdr_actions +
+		 parse_attr->num_mod_hdr_actions * action_size;
+
+	max_actions = parse_attr->max_mod_hdr_actions;
+	nactions = parse_attr->num_mod_hdr_actions;
 
 	for (i = 0; i < ARRAY_SIZE(fields); i++) {
 		f = &fields[i];
@@ -2027,7 +2030,7 @@ static int alloc_mod_hdr_actions(struct mlx5e_priv *priv,
 	if (!parse_attr->mod_hdr_actions)
 		return -ENOMEM;
 
-	parse_attr->num_mod_hdr_actions = max_actions;
+	parse_attr->max_mod_hdr_actions = max_actions;
 	return 0;
 }
 
@@ -2073,9 +2076,11 @@ static int parse_tc_pedit_action(struct mlx5e_priv *priv,
 			goto out_err;
 	}
 
-	err = alloc_mod_hdr_actions(priv, a, namespace, parse_attr);
-	if (err)
-		goto out_err;
+	if (!parse_attr->mod_hdr_actions) {
+		err = alloc_mod_hdr_actions(priv, a, namespace, parse_attr);
+		if (err)
+			goto out_err;
+	}
 
 	err = offload_pedit_fields(masks, vals, parse_attr, extack);
 	if (err < 0)
-- 
2.20.1


From 37dca766858209c88b8f53a4e245d92f65544a4c Mon Sep 17 00:00:00 2001
From: Kal Conley <kal.conley@dectris.com>
Date: Sun, 10 Feb 2019 09:57:11 +0100
Subject: [PATCH 07/23] net/packet: fix 4gb buffer limit due to overflow check

[ Upstream commit fc62814d690cf62189854464f4bd07457d5e9e50 ]

When calculating rb->frames_per_block * req->tp_block_nr the result
can overflow. Check it for overflow without limiting the total buffer
size to UINT_MAX.

This change fixes support for packet ring buffers >= UINT_MAX.

Fixes: 8f8d28e4d6d8 ("net/packet: fix overflow in check for tp_frame_nr")
Signed-off-by: Kal Conley <kal.conley@dectris.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 3b1a78906bc0..1cd1d83a4be0 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -4292,7 +4292,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 		rb->frames_per_block = req->tp_block_size / req->tp_frame_size;
 		if (unlikely(rb->frames_per_block == 0))
 			goto out;
-		if (unlikely(req->tp_block_size > UINT_MAX / req->tp_block_nr))
+		if (unlikely(rb->frames_per_block > UINT_MAX / req->tp_block_nr))
 			goto out;
 		if (unlikely((rb->frames_per_block * req->tp_block_nr) !=
 					req->tp_frame_nr))
-- 
2.20.1


From 9f4333b23eb16bc5d27bd939802b7eb48cdf3886 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Wed, 6 Feb 2019 10:52:30 +0000
Subject: [PATCH 08/23] net: sfp: do not probe SFP module before we're attached

[ Upstream commit b5bfc21af5cb3d53f9cee0ef82eaa43762a90f81 ]

When we probe a SFP module, we expect to be able to call the upstream
device's module_insert() function so that the upstream link can be
configured.  However, when the upstream device is delayed, we currently
may end up probing the module before the upstream device is available,
and lose the module_insert() call.

Avoid this by holding off probing the module until the SFP bus is
properly connected to both the SFP socket driver and the upstream
driver.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/sfp-bus.c |  2 ++
 drivers/net/phy/sfp.c     | 30 +++++++++++++++++++++---------
 drivers/net/phy/sfp.h     |  2 ++
 3 files changed, 25 insertions(+), 9 deletions(-)

diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c
index ad9db652874d..fef701bfad62 100644
--- a/drivers/net/phy/sfp-bus.c
+++ b/drivers/net/phy/sfp-bus.c
@@ -347,6 +347,7 @@ static int sfp_register_bus(struct sfp_bus *bus)
 				return ret;
 		}
 	}
+	bus->socket_ops->attach(bus->sfp);
 	if (bus->started)
 		bus->socket_ops->start(bus->sfp);
 	bus->netdev->sfp_bus = bus;
@@ -362,6 +363,7 @@ static void sfp_unregister_bus(struct sfp_bus *bus)
 	if (bus->registered) {
 		if (bus->started)
 			bus->socket_ops->stop(bus->sfp);
+		bus->socket_ops->detach(bus->sfp);
 		if (bus->phydev && ops && ops->disconnect_phy)
 			ops->disconnect_phy(bus->upstream);
 	}
diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index fd8bb998ae52..68c8fbf099f8 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -184,6 +184,7 @@ struct sfp {
 
 	struct gpio_desc *gpio[GPIO_MAX];
 
+	bool attached;
 	unsigned int state;
 	struct delayed_work poll;
 	struct delayed_work timeout;
@@ -1475,7 +1476,7 @@ static void sfp_sm_event(struct sfp *sfp, unsigned int event)
 	 */
 	switch (sfp->sm_mod_state) {
 	default:
-		if (event == SFP_E_INSERT) {
+		if (event == SFP_E_INSERT && sfp->attached) {
 			sfp_module_tx_disable(sfp);
 			sfp_sm_ins_next(sfp, SFP_MOD_PROBE, T_PROBE_INIT);
 		}
@@ -1607,6 +1608,19 @@ static void sfp_sm_event(struct sfp *sfp, unsigned int event)
 	mutex_unlock(&sfp->sm_mutex);
 }
 
+static void sfp_attach(struct sfp *sfp)
+{
+	sfp->attached = true;
+	if (sfp->state & SFP_F_PRESENT)
+		sfp_sm_event(sfp, SFP_E_INSERT);
+}
+
+static void sfp_detach(struct sfp *sfp)
+{
+	sfp->attached = false;
+	sfp_sm_event(sfp, SFP_E_REMOVE);
+}
+
 static void sfp_start(struct sfp *sfp)
 {
 	sfp_sm_event(sfp, SFP_E_DEV_UP);
@@ -1667,6 +1681,8 @@ static int sfp_module_eeprom(struct sfp *sfp, struct ethtool_eeprom *ee,
 }
 
 static const struct sfp_socket_ops sfp_module_ops = {
+	.attach = sfp_attach,
+	.detach = sfp_detach,
 	.start = sfp_start,
 	.stop = sfp_stop,
 	.module_info = sfp_module_info,
@@ -1834,10 +1850,6 @@ static int sfp_probe(struct platform_device *pdev)
 	dev_info(sfp->dev, "Host maximum power %u.%uW\n",
 		 sfp->max_power_mW / 1000, (sfp->max_power_mW / 100) % 10);
 
-	sfp->sfp_bus = sfp_register_socket(sfp->dev, sfp, &sfp_module_ops);
-	if (!sfp->sfp_bus)
-		return -ENOMEM;
-
 	/* Get the initial state, and always signal TX disable,
 	 * since the network interface will not be up.
 	 */
@@ -1848,10 +1860,6 @@ static int sfp_probe(struct platform_device *pdev)
 		sfp->state |= SFP_F_RATE_SELECT;
 	sfp_set_state(sfp, sfp->state);
 	sfp_module_tx_disable(sfp);
-	rtnl_lock();
-	if (sfp->state & SFP_F_PRESENT)
-		sfp_sm_event(sfp, SFP_E_INSERT);
-	rtnl_unlock();
 
 	for (i = 0; i < GPIO_MAX; i++) {
 		if (gpio_flags[i] != GPIOD_IN || !sfp->gpio[i])
@@ -1884,6 +1892,10 @@ static int sfp_probe(struct platform_device *pdev)
 		dev_warn(sfp->dev,
 			 "No tx_disable pin: SFP modules will always be emitting.\n");
 
+	sfp->sfp_bus = sfp_register_socket(sfp->dev, sfp, &sfp_module_ops);
+	if (!sfp->sfp_bus)
+		return -ENOMEM;
+
 	return 0;
 }
 
diff --git a/drivers/net/phy/sfp.h b/drivers/net/phy/sfp.h
index 31b0acf337e2..64f54b0bbd8c 100644
--- a/drivers/net/phy/sfp.h
+++ b/drivers/net/phy/sfp.h
@@ -7,6 +7,8 @@
 struct sfp;
 
 struct sfp_socket_ops {
+	void (*attach)(struct sfp *sfp);
+	void (*detach)(struct sfp *sfp);
 	void (*start)(struct sfp *sfp);
 	void (*stop)(struct sfp *sfp);
 	int (*module_info)(struct sfp *sfp, struct ethtool_modinfo *modinfo);
-- 
2.20.1


From 9519d893bf5eb317f8709763eae4fe536a6b40c8 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 12 Feb 2019 18:47:30 +0800
Subject: [PATCH 09/23] sctp: call gso_reset_checksum when computing checksum
 in sctp_gso_segment

[ Upstream commit fc228abc2347e106a44c0e9b29ab70b712c4ca51 ]

Jianlin reported a panic when running sctp gso over gre over vlan device:

  [   84.772930] RIP: 0010:do_csum+0x6d/0x170
  [   84.790605] Call Trace:
  [   84.791054]  csum_partial+0xd/0x20
  [   84.791657]  gre_gso_segment+0x2c3/0x390
  [   84.792364]  inet_gso_segment+0x161/0x3e0
  [   84.793071]  skb_mac_gso_segment+0xb8/0x120
  [   84.793846]  __skb_gso_segment+0x7e/0x180
  [   84.794581]  validate_xmit_skb+0x141/0x2e0
  [   84.795297]  __dev_queue_xmit+0x258/0x8f0
  [   84.795949]  ? eth_header+0x26/0xc0
  [   84.796581]  ip_finish_output2+0x196/0x430
  [   84.797295]  ? skb_gso_validate_network_len+0x11/0x80
  [   84.798183]  ? ip_finish_output+0x169/0x270
  [   84.798875]  ip_output+0x6c/0xe0
  [   84.799413]  ? ip_append_data.part.50+0xc0/0xc0
  [   84.800145]  iptunnel_xmit+0x144/0x1c0
  [   84.800814]  ip_tunnel_xmit+0x62d/0x930 [ip_tunnel]
  [   84.801699]  gre_tap_xmit+0xac/0xf0 [ip_gre]
  [   84.802395]  dev_hard_start_xmit+0xa5/0x210
  [   84.803086]  sch_direct_xmit+0x14f/0x340
  [   84.803733]  __dev_queue_xmit+0x799/0x8f0
  [   84.804472]  ip_finish_output2+0x2e0/0x430
  [   84.805255]  ? skb_gso_validate_network_len+0x11/0x80
  [   84.806154]  ip_output+0x6c/0xe0
  [   84.806721]  ? ip_append_data.part.50+0xc0/0xc0
  [   84.807516]  sctp_packet_transmit+0x716/0xa10 [sctp]
  [   84.808337]  sctp_outq_flush+0xd7/0x880 [sctp]

It was caused by SKB_GSO_CB(skb)->csum_start not set in sctp_gso_segment.
sctp_gso_segment() calls skb_segment() with 'feature | NETIF_F_HW_CSUM',
which causes SKB_GSO_CB(skb)->csum_start not to be set in skb_segment().

For TCP/UDP, when feature supports HW_CSUM, CHECKSUM_PARTIAL will be set
and gso_reset_checksum will be called to set SKB_GSO_CB(skb)->csum_start.

So SCTP should do the same as TCP/UDP, to call gso_reset_checksum() when
computing checksum in sctp_gso_segment.

Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/offload.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sctp/offload.c b/net/sctp/offload.c
index 123e9f2dc226..edfcf16e704c 100644
--- a/net/sctp/offload.c
+++ b/net/sctp/offload.c
@@ -36,6 +36,7 @@ static __le32 sctp_gso_make_checksum(struct sk_buff *skb)
 {
 	skb->ip_summed = CHECKSUM_NONE;
 	skb->csum_not_inet = 0;
+	gso_reset_checksum(skb, ~0);
 	return sctp_compute_cksum(skb, skb_transport_offset(skb));
 }
 
-- 
2.20.1


From 4b5b6ab2365d62fa8560dad01881c71e2e6feff6 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 12 Feb 2019 18:51:01 +0800
Subject: [PATCH 10/23] sctp: set stream ext to NULL after freeing it in
 sctp_stream_outq_migrate

[ Upstream commit af98c5a78517c04adb5fd68bb64b1ad6fe3d473f ]

In sctp_stream_init(), after sctp_stream_outq_migrate() freed the
surplus streams' ext, but sctp_stream_alloc_out() returns -ENOMEM,
stream->outcnt will not be set to 'outcnt'.

With the bigger value on stream->outcnt, when closing the assoc and
freeing its streams, the ext of those surplus streams will be freed
again since those stream exts were not set to NULL after freeing in
sctp_stream_outq_migrate(). Then the invalid-free issue reported by
syzbot would be triggered.

We fix it by simply setting them to NULL after freeing.

Fixes: 5bbbbe32a431 ("sctp: introduce stream scheduler foundations")
Reported-by: syzbot+58e480e7b28f2d890bfd@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/stream.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index f24633114dfd..2936ed17bf9e 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -144,8 +144,10 @@ static void sctp_stream_outq_migrate(struct sctp_stream *stream,
 		}
 	}
 
-	for (i = outcnt; i < stream->outcnt; i++)
+	for (i = outcnt; i < stream->outcnt; i++) {
 		kfree(SCTP_SO(stream, i)->ext);
+		SCTP_SO(stream, i)->ext = NULL;
+	}
 }
 
 static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt,
-- 
2.20.1


From e0197d8afb306e980bfd21a230270fb13730fb91 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 11 Feb 2019 21:59:51 -0800
Subject: [PATCH 11/23] team: avoid complex list operations in
 team_nl_cmd_options_set()

[ Upstream commit 2fdeee2549231b1f989f011bb18191f5660d3745 ]

The current opt_inst_list operations inside team_nl_cmd_options_set()
is too complex to track:

    LIST_HEAD(opt_inst_list);
    nla_for_each_nested(...) {
        list_for_each_entry(opt_inst, &team->option_inst_list, list) {
            if (__team_option_inst_tmp_find(&opt_inst_list, opt_inst))
                continue;
            list_add(&opt_inst->tmp_list, &opt_inst_list);
        }
    }
    team_nl_send_event_options_get(team, &opt_inst_list);

as while we retrieve 'opt_inst' from team->option_inst_list, it could
be added to the local 'opt_inst_list' for multiple times. The
__team_option_inst_tmp_find() doesn't work, as the setter
team_mode_option_set() still calls team->ops.exit() which uses
->tmp_list too in __team_options_change_check().

Simplify the list operations by moving the 'opt_inst_list' and
team_nl_send_event_options_get() into the nla_for_each_nested() loop so
that it can be guranteed that we won't insert a same list entry for
multiple times. Therefore, __team_option_inst_tmp_find() can be removed
too.

Fixes: 4fb0534fb7bb ("team: avoid adding twice the same option to the event list")
Fixes: 2fcdb2c9e659 ("team: allow to send multiple set events in one message")
Reported-by: syzbot+4d4af685432dc0e56c91@syzkaller.appspotmail.com
Reported-by: syzbot+68ee510075cf64260cc4@syzkaller.appspotmail.com
Cc: Jiri Pirko <jiri@resnulli.us>
Cc: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 27 +++++----------------------
 1 file changed, 5 insertions(+), 22 deletions(-)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 364f514d56d8..86db1205a396 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -256,17 +256,6 @@ static void __team_option_inst_mark_removed_port(struct team *team,
 	}
 }
 
-static bool __team_option_inst_tmp_find(const struct list_head *opts,
-					const struct team_option_inst *needle)
-{
-	struct team_option_inst *opt_inst;
-
-	list_for_each_entry(opt_inst, opts, tmp_list)
-		if (opt_inst == needle)
-			return true;
-	return false;
-}
-
 static int __team_options_register(struct team *team,
 				   const struct team_option *option,
 				   size_t option_count)
@@ -2460,7 +2449,6 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info)
 	int err = 0;
 	int i;
 	struct nlattr *nl_option;
-	LIST_HEAD(opt_inst_list);
 
 	rtnl_lock();
 
@@ -2480,6 +2468,7 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info)
 		struct nlattr *opt_attrs[TEAM_ATTR_OPTION_MAX + 1];
 		struct nlattr *attr;
 		struct nlattr *attr_data;
+		LIST_HEAD(opt_inst_list);
 		enum team_option_type opt_type;
 		int opt_port_ifindex = 0; /* != 0 for per-port options */
 		u32 opt_array_index = 0;
@@ -2584,23 +2573,17 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info)
 			if (err)
 				goto team_put;
 			opt_inst->changed = true;
-
-			/* dumb/evil user-space can send us duplicate opt,
-			 * keep only the last one
-			 */
-			if (__team_option_inst_tmp_find(&opt_inst_list,
-							opt_inst))
-				continue;
-
 			list_add(&opt_inst->tmp_list, &opt_inst_list);
 		}
 		if (!opt_found) {
 			err = -ENOENT;
 			goto team_put;
 		}
-	}
 
-	err = team_nl_send_event_options_get(team, &opt_inst_list);
+		err = team_nl_send_event_options_get(team, &opt_inst_list);
+		if (err)
+			break;
+	}
 
 team_put:
 	team_nl_team_put(team);
-- 
2.20.1


From c27cb7f672fd7747989eafa711885cbb610672ca Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Mon, 18 Feb 2019 14:30:11 -0800
Subject: [PATCH 12/23] net: dsa: Fix NPD checking for br_vlan_enabled()

[ Upstream not applicable ]

It is possible for the DSA slave network device not to be part of a
bridge, yet have an upper device like a VLAN device be part of a bridge.
When that VLAN device is enslaved, since it does not define any
switchdev_ops, we will recurse down to the lower/physical port device,
call switchdev_port_obj_add() with a VLAN, and here we will check
br_vlan_enabled() on a NULL dp->bridge_dev, thus causing a NULL pointer
de-reference.

This is no longer a problem upstream after commit d17d9f5e5143
("switchdev: Replace port obj add/del SDO with a notification").

Fixes: 2ea7a679ca2a ("net: dsa: Don't add vlans when vlan filtering is disabled")
Reported-by: Frank Wunderlich <frank-w@public-files.de>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
 net/dsa/port.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/dsa/port.c b/net/dsa/port.c
index ed0595459df1..792a13068c50 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -255,7 +255,7 @@ int dsa_port_vlan_add(struct dsa_port *dp,
 	if (netif_is_bridge_master(vlan->obj.orig_dev))
 		return -EOPNOTSUPP;
 
-	if (br_vlan_enabled(dp->bridge_dev))
+	if (dp->bridge_dev && br_vlan_enabled(dp->bridge_dev))
 		return dsa_port_notify(dp, DSA_NOTIFIER_VLAN_ADD, &info);
 
 	return 0;
@@ -273,7 +273,7 @@ int dsa_port_vlan_del(struct dsa_port *dp,
 	if (netif_is_bridge_master(vlan->obj.orig_dev))
 		return -EOPNOTSUPP;
 
-	if (br_vlan_enabled(dp->bridge_dev))
+	if (dp->bridge_dev && br_vlan_enabled(dp->bridge_dev))
 		return dsa_port_notify(dp, DSA_NOTIFIER_VLAN_DEL, &info);
 
 	return 0;
-- 
2.20.1


From c1d212cfb24da09f6511e2bd8294c9bfc5c00e28 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 25 Jan 2019 22:43:17 +0100
Subject: [PATCH 13/23] Revert "socket: fix struct ifreq size in compat ioctl"

[ Upstream commit 63ff03ab786ab1bc6cca01d48eacd22c95b9b3eb ]

This reverts commit 1cebf8f143c2 ("socket: fix struct ifreq
size in compat ioctl"), it's a bugfix for another commit that
I'll revert next.

This is not a 'perfect' revert, I'm keeping some coding style
intact rather than revert to the state with indentation errors.

Cc: stable@vger.kernel.org
Fixes: 1cebf8f143c2 ("socket: fix struct ifreq size in compat ioctl")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/socket.c | 22 ++++++++--------------
 1 file changed, 8 insertions(+), 14 deletions(-)

diff --git a/net/socket.c b/net/socket.c
index 334fcc617ef2..1a3ba4234662 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -941,8 +941,7 @@ void dlci_ioctl_set(int (*hook) (unsigned int, void __user *))
 EXPORT_SYMBOL(dlci_ioctl_set);
 
 static long sock_do_ioctl(struct net *net, struct socket *sock,
-			  unsigned int cmd, unsigned long arg,
-			  unsigned int ifreq_size)
+			  unsigned int cmd, unsigned long arg)
 {
 	int err;
 	void __user *argp = (void __user *)arg;
@@ -968,11 +967,11 @@ static long sock_do_ioctl(struct net *net, struct socket *sock,
 	} else {
 		struct ifreq ifr;
 		bool need_copyout;
-		if (copy_from_user(&ifr, argp, ifreq_size))
+		if (copy_from_user(&ifr, argp, sizeof(struct ifreq)))
 			return -EFAULT;
 		err = dev_ioctl(net, cmd, &ifr, &need_copyout);
 		if (!err && need_copyout)
-			if (copy_to_user(argp, &ifr, ifreq_size))
+			if (copy_to_user(argp, &ifr, sizeof(struct ifreq)))
 				return -EFAULT;
 	}
 	return err;
@@ -1071,8 +1070,7 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 			err = open_related_ns(&net->ns, get_net_ns);
 			break;
 		default:
-			err = sock_do_ioctl(net, sock, cmd, arg,
-					    sizeof(struct ifreq));
+			err = sock_do_ioctl(net, sock, cmd, arg);
 			break;
 		}
 	return err;
@@ -2750,8 +2748,7 @@ static int do_siocgstamp(struct net *net, struct socket *sock,
 	int err;
 
 	set_fs(KERNEL_DS);
-	err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv,
-			    sizeof(struct compat_ifreq));
+	err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv);
 	set_fs(old_fs);
 	if (!err)
 		err = compat_put_timeval(&ktv, up);
@@ -2767,8 +2764,7 @@ static int do_siocgstampns(struct net *net, struct socket *sock,
 	int err;
 
 	set_fs(KERNEL_DS);
-	err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts,
-			    sizeof(struct compat_ifreq));
+	err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts);
 	set_fs(old_fs);
 	if (!err)
 		err = compat_put_timespec(&kts, up);
@@ -3079,8 +3075,7 @@ static int routing_ioctl(struct net *net, struct socket *sock,
 	}
 
 	set_fs(KERNEL_DS);
-	ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r,
-			    sizeof(struct compat_ifreq));
+	ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r);
 	set_fs(old_fs);
 
 out:
@@ -3193,8 +3188,7 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
 	case SIOCBONDSETHWADDR:
 	case SIOCBONDCHANGEACTIVE:
 	case SIOCGIFNAME:
-		return sock_do_ioctl(net, sock, cmd, arg,
-				     sizeof(struct compat_ifreq));
+		return sock_do_ioctl(net, sock, cmd, arg);
 	}
 
 	return -ENOIOCTLCMD;
-- 
2.20.1


From 6dbce414fdc55dd5eb21ad044cfd0f2d29c0a60c Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 25 Jan 2019 22:43:18 +0100
Subject: [PATCH 14/23] Revert "kill dev_ifsioc()"

[ Upstream commit 37ac39bdddc528c998a9f36db36937de923fdf2a ]

This reverts commit bf4405737f9f ("kill dev_ifsioc()").

This wasn't really unused as implied by the original commit,
it still handles the copy to/from user differently, and the
commit thus caused issues such as
  https://bugzilla.kernel.org/show_bug.cgi?id=199469
and
  https://bugzilla.kernel.org/show_bug.cgi?id=202273

However, deviating from a strict revert, rename dev_ifsioc()
to compat_ifreq_ioctl() to be clearer as to its purpose and
add a comment.

Cc: stable@vger.kernel.org
Fixes: bf4405737f9f ("kill dev_ifsioc()")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/socket.c | 49 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 49 insertions(+)

diff --git a/net/socket.c b/net/socket.c
index 1a3ba4234662..8e29af6d6768 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2960,6 +2960,53 @@ static int compat_ifr_data_ioctl(struct net *net, unsigned int cmd,
 	return dev_ioctl(net, cmd, &ifreq, NULL);
 }
 
+static int compat_ifreq_ioctl(struct net *net, struct socket *sock,
+			      unsigned int cmd,
+			      struct compat_ifreq __user *uifr32)
+{
+	struct ifreq __user *uifr;
+	int err;
+
+	/* Handle the fact that while struct ifreq has the same *layout* on
+	 * 32/64 for everything but ifreq::ifru_ifmap and ifreq::ifru_data,
+	 * which are handled elsewhere, it still has different *size* due to
+	 * ifreq::ifru_ifmap (which is 16 bytes on 32 bit, 24 bytes on 64-bit,
+	 * resulting in struct ifreq being 32 and 40 bytes respectively).
+	 * As a result, if the struct happens to be at the end of a page and
+	 * the next page isn't readable/writable, we get a fault. To prevent
+	 * that, copy back and forth to the full size.
+	 */
+
+	uifr = compat_alloc_user_space(sizeof(*uifr));
+	if (copy_in_user(uifr, uifr32, sizeof(*uifr32)))
+		return -EFAULT;
+
+	err = sock_do_ioctl(net, sock, cmd, (unsigned long)uifr);
+
+	if (!err) {
+		switch (cmd) {
+		case SIOCGIFFLAGS:
+		case SIOCGIFMETRIC:
+		case SIOCGIFMTU:
+		case SIOCGIFMEM:
+		case SIOCGIFHWADDR:
+		case SIOCGIFINDEX:
+		case SIOCGIFADDR:
+		case SIOCGIFBRDADDR:
+		case SIOCGIFDSTADDR:
+		case SIOCGIFNETMASK:
+		case SIOCGIFPFLAGS:
+		case SIOCGIFTXQLEN:
+		case SIOCGMIIPHY:
+		case SIOCGMIIREG:
+			if (copy_in_user(uifr32, uifr, sizeof(*uifr32)))
+				err = -EFAULT;
+			break;
+		}
+	}
+	return err;
+}
+
 static int compat_sioc_ifmap(struct net *net, unsigned int cmd,
 			struct compat_ifreq __user *uifr32)
 {
@@ -3179,6 +3226,8 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
 	case SIOCGMIIPHY:
 	case SIOCGMIIREG:
 	case SIOCSMIIREG:
+		return compat_ifreq_ioctl(net, sock, cmd, argp);
+
 	case SIOCSARP:
 	case SIOCGARP:
 	case SIOCDARP:
-- 
2.20.1


From 6c7be0324fe3f399213264e7e15d139ff50c7972 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 25 Jan 2019 22:43:19 +0100
Subject: [PATCH 15/23] net: socket: fix SIOCGIFNAME in compat

[ Upstream commit c6c9fee35dc27362b7bac34b2fc9f5b8ace2e22c ]

As reported by Robert O'Callahan in
https://bugzilla.kernel.org/show_bug.cgi?id=202273
reverting the previous changes in this area broke
the SIOCGIFNAME ioctl in compat again (I'd previously
fixed it after his previous report of breakage in
https://bugzilla.kernel.org/show_bug.cgi?id=199469).

This is obviously because I fixed SIOCGIFNAME more or
less by accident.

Fix it explicitly now by making it pass through the
restored compat translation code.

Cc: stable@vger.kernel.org
Fixes: 4cf808e7ac32 ("kill dev_ifname32()")
Reported-by: Robert O'Callahan <robert@ocallahan.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/socket.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/socket.c b/net/socket.c
index 8e29af6d6768..2d06384a2a7f 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2999,6 +2999,7 @@ static int compat_ifreq_ioctl(struct net *net, struct socket *sock,
 		case SIOCGIFTXQLEN:
 		case SIOCGMIIPHY:
 		case SIOCGMIIREG:
+		case SIOCGIFNAME:
 			if (copy_in_user(uifr32, uifr, sizeof(*uifr32)))
 				err = -EFAULT;
 			break;
@@ -3222,6 +3223,7 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
 	case SIOCSIFTXQLEN:
 	case SIOCBRADDIF:
 	case SIOCBRDELIF:
+	case SIOCGIFNAME:
 	case SIOCSIFNAME:
 	case SIOCGMIIPHY:
 	case SIOCGMIIREG:
@@ -3236,7 +3238,6 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
 	case SIOCBONDRELEASE:
 	case SIOCBONDSETHWADDR:
 	case SIOCBONDCHANGEACTIVE:
-	case SIOCGIFNAME:
 		return sock_do_ioctl(net, sock, cmd, arg);
 	}
 
-- 
2.20.1


From d7e625084b86eec4198bf43d6f7d691dee386031 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 25 Jan 2019 22:43:20 +0100
Subject: [PATCH 16/23] net: socket: make bond ioctls go through
 compat_ifreq_ioctl()

[ Upstream commit 98406133dd9cb9f195676eab540c270dceca879a ]

Same story as before, these use struct ifreq and thus need
to be read with the shorter version to not cause faults.

Cc: stable@vger.kernel.org
Fixes: f92d4fc95341 ("kill bond_ioctl()")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/socket.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/socket.c b/net/socket.c
index 2d06384a2a7f..93a45f15ee40 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -3228,16 +3228,16 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
 	case SIOCGMIIPHY:
 	case SIOCGMIIREG:
 	case SIOCSMIIREG:
+	case SIOCBONDENSLAVE:
+	case SIOCBONDRELEASE:
+	case SIOCBONDSETHWADDR:
+	case SIOCBONDCHANGEACTIVE:
 		return compat_ifreq_ioctl(net, sock, cmd, argp);
 
 	case SIOCSARP:
 	case SIOCGARP:
 	case SIOCDARP:
 	case SIOCATMARK:
-	case SIOCBONDENSLAVE:
-	case SIOCBONDRELEASE:
-	case SIOCBONDSETHWADDR:
-	case SIOCBONDCHANGEACTIVE:
 		return sock_do_ioctl(net, sock, cmd, arg);
 	}
 
-- 
2.20.1


From d7e55852846a4da219df26d04e3d8b678b392178 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Thu, 7 Feb 2019 18:36:10 +0800
Subject: [PATCH 17/23] geneve: should not call rt6_lookup() when ipv6 was
 disabled

[ Upstream commit c0a47e44c0980b3b23ee31fa7936d70ea5dce491 ]

When we add a new GENEVE device with IPv6 remote, checking only for
IS_ENABLED(CONFIG_IPV6) is not enough as we may disable IPv6 in the
kernel command line (ipv6.disable=1), and calling rt6_lookup() would
cause a NULL pointer dereference.

v2:
- don't mix declarations and code (reported by Stefano Brivio, Eric Dumazet)
- there's no need to use in6_dev_get() as we only need to check that
  idev exists (reported by David Ahern). This is under RTNL, so we can
  simply use __in6_dev_get() instead (Stefano, Eric).

Reported-by: Jianlin Shi <jishi@redhat.com>
Fixes: c40e89fd358e9 ("geneve: configure MTU based on a lower device")
Cc: Alexey Kodanev <alexey.kodanev@oracle.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index a0cd1c41cf5f..2e6e11d8cf5c 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1426,9 +1426,13 @@ static void geneve_link_config(struct net_device *dev,
 	}
 #if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6: {
-		struct rt6_info *rt = rt6_lookup(geneve->net,
-						 &info->key.u.ipv6.dst, NULL, 0,
-						 NULL, 0);
+		struct rt6_info *rt;
+
+		if (!__in6_dev_get(dev))
+			break;
+
+		rt = rt6_lookup(geneve->net, &info->key.u.ipv6.dst, NULL, 0,
+				NULL, 0);
 
 		if (rt && rt->dst.dev)
 			ldev_mtu = rt->dst.dev->mtu - GENEVE_IPV6_HLEN;
-- 
2.20.1


From 17e6535c29e491b691746205d937a50fbbab080e Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Thu, 7 Feb 2019 18:36:11 +0800
Subject: [PATCH 18/23] sit: check if IPv6 enabled before calling
 ip6_err_gen_icmpv6_unreach()

[ Upstream commit 173656accaf583698bac3f9e269884ba60d51ef4 ]

If we disabled IPv6 from the kernel command line (ipv6.disable=1), we should
not call ip6_err_gen_icmpv6_unreach(). This:

  ip link add sit1 type sit local 192.0.2.1 remote 192.0.2.2 ttl 1
  ip link set sit1 up
  ip addr add 198.51.100.1/24 dev sit1
  ping 198.51.100.2

if IPv6 is disabled at boot time, will crash the kernel.

v2: there's no need to use in6_dev_get(), use __in6_dev_get() instead,
    as we only need to check that idev exists and we are under
    rcu_read_lock() (from netif_receive_skb_internal()).

Reported-by: Jianlin Shi <jishi@redhat.com>
Fixes: ca15a078bd90 ("sit: generate icmpv6 error when receiving icmpv4 error")
Cc: Oussama Ghorbel <ghorbel@pivasoftware.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 1e03305c0549..e8a1dabef803 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -546,7 +546,8 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
 	}
 
 	err = 0;
-	if (!ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4, type, data_len))
+	if (__in6_dev_get(skb->dev) &&
+	    !ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4, type, data_len))
 		goto out;
 
 	if (t->parms.iph.daddr == 0)
-- 
2.20.1


From 332c308ad83269cbf15bc8f66f8077916ceadcc3 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 11 Feb 2019 13:06:14 -0800
Subject: [PATCH 19/23] net_sched: fix a race condition in tcindex_destroy()

[ Upstream commit 8015d93ebd27484418d4952284fd02172fa4b0b2 ]

tcindex_destroy() invokes tcindex_destroy_element() via
a walker to delete each filter result in its perfect hash
table, and tcindex_destroy_element() calls tcindex_delete()
which schedules tcf RCU works to do the final deletion work.
Unfortunately this races with the RCU callback
__tcindex_destroy(), which could lead to use-after-free as
reported by Adrian.

Fix this by migrating this RCU callback to tcf RCU work too,
as that workqueue is ordered, we will not have use-after-free.

Note, we don't need to hold netns refcnt because we don't call
tcf_exts_destroy() here.

Fixes: 27ce4f05e2ab ("net_sched: use tcf_queue_work() in tcindex filter")
Reported-by: Adrian <bugs@abtelecom.ro>
Cc: Ben Hutchings <ben@decadent.org.uk>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_tcindex.c | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 9ccc93f257db..79b52a637dda 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -48,7 +48,7 @@ struct tcindex_data {
 	u32 hash;		/* hash table size; 0 if undefined */
 	u32 alloc_hash;		/* allocated size */
 	u32 fall_through;	/* 0: only classify if explicit match */
-	struct rcu_head rcu;
+	struct rcu_work rwork;
 };
 
 static inline int tcindex_filter_is_set(struct tcindex_filter_result *r)
@@ -229,9 +229,11 @@ static int tcindex_destroy_element(struct tcf_proto *tp,
 	return tcindex_delete(tp, arg, &last, NULL);
 }
 
-static void __tcindex_destroy(struct rcu_head *head)
+static void tcindex_destroy_work(struct work_struct *work)
 {
-	struct tcindex_data *p = container_of(head, struct tcindex_data, rcu);
+	struct tcindex_data *p = container_of(to_rcu_work(work),
+					      struct tcindex_data,
+					      rwork);
 
 	kfree(p->perfect);
 	kfree(p->h);
@@ -258,9 +260,11 @@ static int tcindex_filter_result_init(struct tcindex_filter_result *r)
 	return tcf_exts_init(&r->exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
 }
 
-static void __tcindex_partial_destroy(struct rcu_head *head)
+static void tcindex_partial_destroy_work(struct work_struct *work)
 {
-	struct tcindex_data *p = container_of(head, struct tcindex_data, rcu);
+	struct tcindex_data *p = container_of(to_rcu_work(work),
+					      struct tcindex_data,
+					      rwork);
 
 	kfree(p->perfect);
 	kfree(p);
@@ -478,7 +482,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	}
 
 	if (oldp)
-		call_rcu(&oldp->rcu, __tcindex_partial_destroy);
+		tcf_queue_work(&oldp->rwork, tcindex_partial_destroy_work);
 	return 0;
 
 errout_alloc:
@@ -570,7 +574,7 @@ static void tcindex_destroy(struct tcf_proto *tp,
 	walker.fn = tcindex_destroy_element;
 	tcindex_walk(tp, &walker);
 
-	call_rcu(&p->rcu, __tcindex_destroy);
+	tcf_queue_work(&p->rwork, tcindex_destroy_work);
 }
 
 
-- 
2.20.1


From 77bb78167a38a8ff37dbe03aed3e8bca08d8d34b Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 11 Feb 2019 13:06:15 -0800
Subject: [PATCH 20/23] net_sched: fix a memory leak in cls_tcindex

[ Upstream commit 033b228e7f26b29ae37f8bfa1bc6b209a5365e9f ]

When tcindex_destroy() destroys all the filter results in
the perfect hash table, it invokes the walker to delete
each of them. However, results with class==0 are skipped
in either tcindex_walk() or tcindex_delete(), which causes
a memory leak reported by kmemleak.

This patch fixes it by skipping the walker and directly
deleting these filter results so we don't miss any filter
result.

As a result of this change, we have to initialize exts->net
properly in tcindex_alloc_perfect_hash(). For net-next, we
need to consider whether we should initialize ->net in
tcf_exts_init() instead, before that just directly test
CONFIG_NET_CLS_ACT=y.

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_tcindex.c | 46 +++++++++++++++++++++++++++--------------
 1 file changed, 30 insertions(+), 16 deletions(-)

diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 79b52a637dda..70ea5b1a7889 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -221,14 +221,6 @@ static int tcindex_delete(struct tcf_proto *tp, void *arg, bool *last,
 	return 0;
 }
 
-static int tcindex_destroy_element(struct tcf_proto *tp,
-				   void *arg, struct tcf_walker *walker)
-{
-	bool last;
-
-	return tcindex_delete(tp, arg, &last, NULL);
-}
-
 static void tcindex_destroy_work(struct work_struct *work)
 {
 	struct tcindex_data *p = container_of(to_rcu_work(work),
@@ -279,7 +271,7 @@ static void tcindex_free_perfect_hash(struct tcindex_data *cp)
 	kfree(cp->perfect);
 }
 
-static int tcindex_alloc_perfect_hash(struct tcindex_data *cp)
+static int tcindex_alloc_perfect_hash(struct net *net, struct tcindex_data *cp)
 {
 	int i, err = 0;
 
@@ -293,6 +285,9 @@ static int tcindex_alloc_perfect_hash(struct tcindex_data *cp)
 				    TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
 		if (err < 0)
 			goto errout;
+#ifdef CONFIG_NET_CLS_ACT
+		cp->perfect[i].exts.net = net;
+#endif
 	}
 
 	return 0;
@@ -341,7 +336,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	if (p->perfect) {
 		int i;
 
-		if (tcindex_alloc_perfect_hash(cp) < 0)
+		if (tcindex_alloc_perfect_hash(net, cp) < 0)
 			goto errout;
 		for (i = 0; i < cp->hash; i++)
 			cp->perfect[i].res = p->perfect[i].res;
@@ -410,7 +405,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	err = -ENOMEM;
 	if (!cp->perfect && !cp->h) {
 		if (valid_perfect_hash(cp)) {
-			if (tcindex_alloc_perfect_hash(cp) < 0)
+			if (tcindex_alloc_perfect_hash(net, cp) < 0)
 				goto errout_alloc;
 			balloc = 1;
 		} else {
@@ -566,13 +561,32 @@ static void tcindex_destroy(struct tcf_proto *tp,
 			    struct netlink_ext_ack *extack)
 {
 	struct tcindex_data *p = rtnl_dereference(tp->root);
-	struct tcf_walker walker;
+	int i;
 
 	pr_debug("tcindex_destroy(tp %p),p %p\n", tp, p);
-	walker.count = 0;
-	walker.skip = 0;
-	walker.fn = tcindex_destroy_element;
-	tcindex_walk(tp, &walker);
+
+	if (p->perfect) {
+		for (i = 0; i < p->hash; i++) {
+			struct tcindex_filter_result *r = p->perfect + i;
+
+			tcf_unbind_filter(tp, &r->res);
+			if (tcf_exts_get_net(&r->exts))
+				tcf_queue_work(&r->rwork,
+					       tcindex_destroy_rexts_work);
+			else
+				__tcindex_destroy_rexts(r);
+		}
+	}
+
+	for (i = 0; p->h && i < p->hash; i++) {
+		struct tcindex_filter *f, *next;
+		bool last;
+
+		for (f = rtnl_dereference(p->h[i]); f; f = next) {
+			next = rtnl_dereference(f->next);
+			tcindex_delete(tp, &f->result, &last, NULL);
+		}
+	}
 
 	tcf_queue_work(&p->rwork, tcindex_destroy_work);
 }
-- 
2.20.1


From e120e4aae9438b244a609207b385fa6fa1f7840d Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 11 Feb 2019 13:06:16 -0800
Subject: [PATCH 21/23] net_sched: fix two more memory leaks in cls_tcindex

[ Upstream commit 1db817e75f5b9387b8db11e37d5f0624eb9223e0 ]

struct tcindex_filter_result contains two parts:
struct tcf_exts and struct tcf_result.

For the local variable 'cr', its exts part is never used but
initialized without being released properly on success path. So
just completely remove the exts part to fix this leak.

For the local variable 'new_filter_result', it is never properly
released if not used by 'r' on success path.

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_tcindex.c | 16 +++++++---------
 1 file changed, 7 insertions(+), 9 deletions(-)

diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 70ea5b1a7889..38bb882bb958 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -304,9 +304,9 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 		  struct nlattr *est, bool ovr, struct netlink_ext_ack *extack)
 {
 	struct tcindex_filter_result new_filter_result, *old_r = r;
-	struct tcindex_filter_result cr;
 	struct tcindex_data *cp = NULL, *oldp;
 	struct tcindex_filter *f = NULL; /* make gcc behave */
+	struct tcf_result cr = {};
 	int err, balloc = 0;
 	struct tcf_exts e;
 
@@ -345,13 +345,10 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	cp->h = p->h;
 
 	err = tcindex_filter_result_init(&new_filter_result);
-	if (err < 0)
-		goto errout1;
-	err = tcindex_filter_result_init(&cr);
 	if (err < 0)
 		goto errout1;
 	if (old_r)
-		cr.res = r->res;
+		cr = r->res;
 
 	if (tb[TCA_TCINDEX_HASH])
 		cp->hash = nla_get_u32(tb[TCA_TCINDEX_HASH]);
@@ -442,8 +439,8 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	}
 
 	if (tb[TCA_TCINDEX_CLASSID]) {
-		cr.res.classid = nla_get_u32(tb[TCA_TCINDEX_CLASSID]);
-		tcf_bind_filter(tp, &cr.res, base);
+		cr.classid = nla_get_u32(tb[TCA_TCINDEX_CLASSID]);
+		tcf_bind_filter(tp, &cr, base);
 	}
 
 	if (old_r && old_r != r) {
@@ -455,7 +452,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	}
 
 	oldp = p;
-	r->res = cr.res;
+	r->res = cr;
 	tcf_exts_change(&r->exts, &e);
 
 	rcu_assign_pointer(tp->root, cp);
@@ -474,6 +471,8 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 				; /* nothing */
 
 		rcu_assign_pointer(*fp, f);
+	} else {
+		tcf_exts_destroy(&new_filter_result.exts);
 	}
 
 	if (oldp)
@@ -486,7 +485,6 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	else if (balloc == 2)
 		kfree(cp->h);
 errout1:
-	tcf_exts_destroy(&cr.exts);
 	tcf_exts_destroy(&new_filter_result.exts);
 errout:
 	kfree(cp);
-- 
2.20.1


From 8d53d8189d366a01a08b36e7a8af466724f248b2 Mon Sep 17 00:00:00 2001
From: Raed Salem <raeds@mellanox.com>
Date: Mon, 17 Dec 2018 11:40:06 +0200
Subject: [PATCH 22/23] net/mlx5e: FPGA, fix Innova IPsec TX offload data path
 performance

[ Upstream commit 82eaa1fa0448da1852d7b80832e67e80a08dcc27 ]

At Innova IPsec TX offload data path a special software parser metadata
is used to pass some packet attributes to the hardware, this metadata
is passed using the Ethernet control segment of a WQE (a HW descriptor)
header.

The cited commit might nullify this header, hence the metadata is lost,
this caused a significant performance drop during hw offloading
operation.

Fix by restoring the metadata at the Ethernet control segment in case
it was nullified.

Fixes: 37fdffb217a4 ("net/mlx5: WQ, fixes for fragmented WQ buffers API")
Signed-off-by: Raed Salem <raeds@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 6dacaeba2fbf..0b03d65474e9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -387,8 +387,14 @@ netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	num_wqebbs = DIV_ROUND_UP(ds_cnt, MLX5_SEND_WQEBB_NUM_DS);
 	contig_wqebbs_room = mlx5_wq_cyc_get_contig_wqebbs(wq, pi);
 	if (unlikely(contig_wqebbs_room < num_wqebbs)) {
+#ifdef CONFIG_MLX5_EN_IPSEC
+		struct mlx5_wqe_eth_seg cur_eth = wqe->eth;
+#endif
 		mlx5e_fill_sq_frag_edge(sq, wq, pi, contig_wqebbs_room);
 		mlx5e_sq_fetch_wqe(sq, &wqe, &pi);
+#ifdef CONFIG_MLX5_EN_IPSEC
+		wqe->eth = cur_eth;
+#endif
 	}
 
 	/* fill wqe */
-- 
2.20.1


From 8c9d1670f2f1862b475f965f331ac3a31972b011 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 11 Feb 2019 16:27:02 -0800
Subject: [PATCH 23/23] net/mlx5e: XDP, fix redirect resources availability
 check
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 407e17b1a69a51ba9a512a04342da56c1f931df4 ]

Currently mlx5 driver creates xdp redirect hw queues unconditionally on
netdevice open, This is great until someone starts redirecting XDP traffic
via ndo_xdp_xmit on mlx5 device and changes the device configuration at
the same time, this might cause crashes, since the other device's napi
is not aware of the mlx5 state change (resources un-availability).

To fix this we must synchronize with other devices napi's on the system.
Added a new flag under mlx5e_priv to determine XDP TX resources are
available, set/clear it up when necessary and use synchronize_rcu()
when the flag is turned off, so other napi's are in-sync with it, before
we actually cleanup the hw resources.

The flag is tested prior to committing to transmit on mlx5e_xdp_xmit, and
it is sufficient to determine if it safe to transmit or not. The other
two internal flags (MLX5E_STATE_OPENED and MLX5E_SQ_STATE_ENABLED) become
unnecessary. Thus, they are removed from data path.

Fixes: 58b99ee3e3eb ("net/mlx5e: Add support for XDP_REDIRECT in device-out side")
Reported-by: Toke Høiland-Jørgensen <toke@redhat.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h    |  1 +
 .../net/ethernet/mellanox/mlx5/core/en/xdp.c    |  6 ++----
 .../net/ethernet/mellanox/mlx5/core/en/xdp.h    | 17 +++++++++++++++++
 .../net/ethernet/mellanox/mlx5/core/en_main.c   |  2 ++
 4 files changed, 22 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 118324802926..7c72b3b5eedf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -636,6 +636,7 @@ enum {
 	MLX5E_STATE_ASYNC_EVENTS_ENABLED,
 	MLX5E_STATE_OPENED,
 	MLX5E_STATE_DESTROYING,
+	MLX5E_STATE_XDP_TX_ENABLED,
 };
 
 struct mlx5e_rqt {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index ad6d471d00dd..4a33c9a7cac7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -262,7 +262,8 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 	int sq_num;
 	int i;
 
-	if (unlikely(!test_bit(MLX5E_STATE_OPENED, &priv->state)))
+	/* this flag is sufficient, no need to test internal sq state */
+	if (unlikely(!mlx5e_xdp_tx_is_enabled(priv)))
 		return -ENETDOWN;
 
 	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
@@ -275,9 +276,6 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 
 	sq = &priv->channels.c[sq_num]->xdpsq;
 
-	if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
-		return -ENETDOWN;
-
 	for (i = 0; i < n; i++) {
 		struct xdp_frame *xdpf = frames[i];
 		struct mlx5e_xdp_info xdpi;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index 6dfab045925f..4d096623178b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -49,6 +49,23 @@ bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi);
 int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 		   u32 flags);
 
+static inline void mlx5e_xdp_tx_enable(struct mlx5e_priv *priv)
+{
+	set_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state);
+}
+
+static inline void mlx5e_xdp_tx_disable(struct mlx5e_priv *priv)
+{
+	clear_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state);
+	/* let other device's napi(s) see our new state */
+	synchronize_rcu();
+}
+
+static inline bool mlx5e_xdp_tx_is_enabled(struct mlx5e_priv *priv)
+{
+	return test_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state);
+}
+
 static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq)
 {
 	struct mlx5_wq_cyc *wq = &sq->wq;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 9577d0657839..1d66a4e22d64 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2903,6 +2903,7 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv)
 
 	mlx5e_build_tx2sq_maps(priv);
 	mlx5e_activate_channels(&priv->channels);
+	mlx5e_xdp_tx_enable(priv);
 	netif_tx_start_all_queues(priv->netdev);
 
 	if (MLX5_ESWITCH_MANAGER(priv->mdev))
@@ -2924,6 +2925,7 @@ void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv)
 	 */
 	netif_tx_stop_all_queues(priv->netdev);
 	netif_tx_disable(priv->netdev);
+	mlx5e_xdp_tx_disable(priv);
 	mlx5e_deactivate_channels(&priv->channels);
 }
 
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Sat, Feb 23, 2019 at 09:18:00PM -0800, David Miller wrote:
> 
> Please queue up the following networking bug fixes to v4.19 and v4.20
> respectively.

Now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 106 bytes --]


Please queue up the following networking bug fixes for v4.20 and v5.0
-stable, respectively.

Thank you.

[-- Attachment #2: net_420.mbox --]
[-- Type: Application/Octet-Stream, Size: 104377 bytes --]

From 943916287b4e8bdb9f371c9a305e3a96353254cd Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Sun, 3 Mar 2019 07:34:57 +0000
Subject: [PATCH 01/42] ip6mr: Do not call __IP6_INC_STATS() from preemptible
 context

[ Upstream commit 87c11f1ddbbad38ad8bad47af133a8208985fbdf ]

Similar to commit 44f49dd8b5a6 ("ipmr: fix possible race resulting from
improper usage of IP_INC_STATS_BH() in preemptible context."), we cannot
assume preemption is disabled when incrementing the counter and
accessing a per-CPU variable.

Preemption can be enabled when we add a route in process context that
corresponds to packets stored in the unresolved queue, which are then
forwarded using this route [1].

Fix this by using IP6_INC_STATS() which takes care of disabling
preemption on architectures where it is needed.

[1]
[  157.451447] BUG: using __this_cpu_add() in preemptible [00000000] code: smcrouted/2314
[  157.460409] caller is ip6mr_forward2+0x73e/0x10e0
[  157.460434] CPU: 3 PID: 2314 Comm: smcrouted Not tainted 5.0.0-rc7-custom-03635-g22f2712113f1 #1336
[  157.460449] Hardware name: Mellanox Technologies Ltd. MSN2100-CB2FO/SA001017, BIOS 5.6.5 06/07/2016
[  157.460461] Call Trace:
[  157.460486]  dump_stack+0xf9/0x1be
[  157.460553]  check_preemption_disabled+0x1d6/0x200
[  157.460576]  ip6mr_forward2+0x73e/0x10e0
[  157.460705]  ip6_mr_forward+0x9a0/0x1510
[  157.460771]  ip6mr_mfc_add+0x16b3/0x1e00
[  157.461155]  ip6_mroute_setsockopt+0x3cb/0x13c0
[  157.461384]  do_ipv6_setsockopt.isra.8+0x348/0x4060
[  157.462013]  ipv6_setsockopt+0x90/0x110
[  157.462036]  rawv6_setsockopt+0x4a/0x120
[  157.462058]  __sys_setsockopt+0x16b/0x340
[  157.462198]  __x64_sys_setsockopt+0xbf/0x160
[  157.462220]  do_syscall_64+0x14d/0x610
[  157.462349]  entry_SYSCALL_64_after_hwframe+0x49/0xbe

Fixes: 0912ea38de61 ("[IPV6] MROUTE: Add stats in multicast routing module method ip6_mr_forward().")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Amit Cohen <amitc@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6mr.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index edda3f9daab9..9ed08ac6066c 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1964,10 +1964,10 @@ int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg)
 
 static inline int ip6mr_forward2_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
-	__IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
-			IPSTATS_MIB_OUTFORWDATAGRAMS);
-	__IP6_ADD_STATS(net, ip6_dst_idev(skb_dst(skb)),
-			IPSTATS_MIB_OUTOCTETS, skb->len);
+	IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
+		      IPSTATS_MIB_OUTFORWDATAGRAMS);
+	IP6_ADD_STATS(net, ip6_dst_idev(skb_dst(skb)),
+		      IPSTATS_MIB_OUTOCTETS, skb->len);
 	return dst_output(net, sk, skb);
 }
 
-- 
2.20.1


From dbe9d6fb76a297afa4f89c58d9fe26293d02194e Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 4 Mar 2019 19:39:03 +0100
Subject: [PATCH 02/42] net: dsa: mv88e6xxx: add call to
 mv88e6xxx_ports_cmode_init to probe for new DSA framework

[ Upstream commit 3acca1dd17060332cfab15693733cdaf9fba1c90 ]

In the original patch I missed to add mv88e6xxx_ports_cmode_init()
to the second probe function, the one for the new DSA framework.

Fixes: ed8fe20205ac ("net: dsa: mv88e6xxx: prevent interrupt storm caused by mv88e6390x_port_set_cmode")
Reported-by: Shaokun Zhang <zhangshaokun@hisilicon.com>
Suggested-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index b0113f6fdbb4..487f1dcd006d 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -4821,6 +4821,7 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev)
 	if (err)
 		goto out;
 
+	mv88e6xxx_ports_cmode_init(chip);
 	mv88e6xxx_phy_init(chip);
 
 	if (chip->info->ops->get_eeprom) {
-- 
2.20.1


From 141e34db09e6b655c8e0295e51cb9bfc8f7cdfe2 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 1 Mar 2019 19:53:57 +0100
Subject: [PATCH 03/42] net: dsa: mv88e6xxx: handle unknown duplex modes
 gracefully in mv88e6xxx_port_set_duplex

[ Upstream commit c6195a8bdfc62a7cecf7df685e64847a4b700275 ]

When testing another issue I faced the problem that
mv88e6xxx_port_setup_mac() failed due to DUPLEX_UNKNOWN being passed
as argument to mv88e6xxx_port_set_duplex(). We should handle this case
gracefully and return -EOPNOTSUPP, like e.g. mv88e6xxx_port_set_speed()
is doing it.

Fixes: 7f1ae07b51e8 ("net: dsa: mv88e6xxx: add port duplex setter")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/port.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c
index cd7db60a508b..ece89756a070 100644
--- a/drivers/net/dsa/mv88e6xxx/port.c
+++ b/drivers/net/dsa/mv88e6xxx/port.c
@@ -190,7 +190,7 @@ int mv88e6xxx_port_set_duplex(struct mv88e6xxx_chip *chip, int port, int dup)
 		/* normal duplex detection */
 		break;
 	default:
-		return -EINVAL;
+		return -EOPNOTSUPP;
 	}
 
 	err = mv88e6xxx_port_write(chip, port, MV88E6XXX_PORT_MAC_CTL, reg);
-- 
2.20.1


From 68cd7fcc2c735de27ad2e2a808f34be383e722d6 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 2 Mar 2019 10:06:05 +0100
Subject: [PATCH 04/42] net: dsa: mv8e6xxx: fix number of internal PHYs for
 88E6x90 family

[ Upstream commit 95150f29ae480276e76368cdf8a9524b5a96c0ca ]

Ports 9 and 10 don't have internal PHY's but are (dependent on the
version) SERDES/SGMII/XAUI/RXAUI ports.

v2:
- fix it for all 88E6x90 family members

Fixes: bc3931557d1d ("net: dsa: mv88e6xxx: Add number of internal PHYs")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 487f1dcd006d..b74cd49d0fb0 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -4206,7 +4206,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6190",
 		.num_databases = 4096,
 		.num_ports = 11,	/* 10 + Z80 */
-		.num_internal_phys = 11,
+		.num_internal_phys = 9,
 		.num_gpio = 16,
 		.max_vid = 8191,
 		.port_base_addr = 0x0,
@@ -4229,7 +4229,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6190X",
 		.num_databases = 4096,
 		.num_ports = 11,	/* 10 + Z80 */
-		.num_internal_phys = 11,
+		.num_internal_phys = 9,
 		.num_gpio = 16,
 		.max_vid = 8191,
 		.port_base_addr = 0x0,
@@ -4252,7 +4252,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6191",
 		.num_databases = 4096,
 		.num_ports = 11,	/* 10 + Z80 */
-		.num_internal_phys = 11,
+		.num_internal_phys = 9,
 		.max_vid = 8191,
 		.port_base_addr = 0x0,
 		.phy_base_addr = 0x0,
@@ -4299,7 +4299,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6290",
 		.num_databases = 4096,
 		.num_ports = 11,	/* 10 + Z80 */
-		.num_internal_phys = 11,
+		.num_internal_phys = 9,
 		.num_gpio = 16,
 		.max_vid = 8191,
 		.port_base_addr = 0x0,
@@ -4461,7 +4461,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6390",
 		.num_databases = 4096,
 		.num_ports = 11,	/* 10 + Z80 */
-		.num_internal_phys = 11,
+		.num_internal_phys = 9,
 		.num_gpio = 16,
 		.max_vid = 8191,
 		.port_base_addr = 0x0,
@@ -4484,7 +4484,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6390X",
 		.num_databases = 4096,
 		.num_ports = 11,	/* 10 + Z80 */
-		.num_internal_phys = 11,
+		.num_internal_phys = 9,
 		.num_gpio = 16,
 		.max_vid = 8191,
 		.port_base_addr = 0x0,
-- 
2.20.1


From b44b0e1709a41e524ccfe529b53dccd260758b0d Mon Sep 17 00:00:00 2001
From: Kavya Sree Kotagiri <kavyasree.kotagiri@microchip.com>
Date: Thu, 28 Feb 2019 07:32:22 +0000
Subject: [PATCH 05/42] net: mscc: Enable all ports in QSGMII

[ Upstream commit 084e5bb16bd7dc2b551bbd9fb358bf73e03ee8d8 ]

When Ocelot phy-mode is QSGMII, all 4 ports involved in
QSGMII shall be kept out of reset and
Tx lanes shall be enabled to pass the data.

Fixes: a556c76adc05 ("net: mscc: Add initial Ocelot switch support")
Signed-off-by: Kavya Sree Kotagiri <kavyasree.kotagiri@microchip.com>
Signed-off-by: Steen Hegelund <Steen.Hegelund@microchip.com>
Co-developed-by: Steen Hegelund <Steen.Hegelund@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot_board.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c
index 4c23d18bbf44..14b83bbf828d 100644
--- a/drivers/net/ethernet/mscc/ocelot_board.c
+++ b/drivers/net/ethernet/mscc/ocelot_board.c
@@ -266,6 +266,7 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
 		struct phy *serdes;
 		void __iomem *regs;
 		char res_name[8];
+		int phy_mode;
 		u32 port;
 
 		if (of_property_read_u32(portnp, "reg", &port))
@@ -291,11 +292,11 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
 		if (err)
 			return err;
 
-		err = of_get_phy_mode(portnp);
-		if (err < 0)
+		phy_mode = of_get_phy_mode(portnp);
+		if (phy_mode < 0)
 			ocelot->ports[port]->phy_mode = PHY_INTERFACE_MODE_NA;
 		else
-			ocelot->ports[port]->phy_mode = err;
+			ocelot->ports[port]->phy_mode = phy_mode;
 
 		switch (ocelot->ports[port]->phy_mode) {
 		case PHY_INTERFACE_MODE_NA:
@@ -303,6 +304,13 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
 		case PHY_INTERFACE_MODE_SGMII:
 			break;
 		case PHY_INTERFACE_MODE_QSGMII:
+			/* Ensure clock signals and speed is set on all
+			 * QSGMII links
+			 */
+			ocelot_port_writel(ocelot->ports[port],
+					   DEV_CLOCK_CFG_LINK_SPEED
+					   (OCELOT_SPEED_1000),
+					   DEV_CLOCK_CFG);
 			break;
 		default:
 			dev_err(ocelot->dev,
-- 
2.20.1


From c131bb0321994f76afe2c2ca6a7b9cc257b7e662 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 28 Feb 2019 12:55:43 -0800
Subject: [PATCH 06/42] net: sched: put back q.qlen into a single location

[ Upstream commit 46b1c18f9deb326a7e18348e668e4c7ab7c7458b ]

In the series fc8b81a5981f ("Merge branch 'lockless-qdisc-series'")
John made the assumption that the data path had no need to read
the qdisc qlen (number of packets in the qdisc).

It is true when pfifo_fast is used as the root qdisc, or as direct MQ/MQPRIO
children.

But pfifo_fast can be used as leaf in class full qdiscs, and existing
logic needs to access the child qlen in an efficient way.

HTB breaks badly, since it uses cl->leaf.q->q.qlen in :
  htb_activate() -> WARN_ON()
  htb_dequeue_tree() to decide if a class can be htb_deactivated
  when it has no more packets.

HFSC, DRR, CBQ, QFQ have similar issues, and some calls to
qdisc_tree_reduce_backlog() also read q.qlen directly.

Using qdisc_qlen_sum() (which iterates over all possible cpus)
in the data path is a non starter.

It seems we have to put back qlen in a central location,
at least for stable kernels.

For all qdisc but pfifo_fast, qlen is guarded by the qdisc lock,
so the existing q.qlen{++|--} are correct.

For 'lockless' qdisc (pfifo_fast so far), we need to use atomic_{inc|dec}()
because the spinlock might be not held (for example from
pfifo_fast_enqueue() and pfifo_fast_dequeue())

This patch adds atomic_qlen (in the same location than qlen)
and renames the following helpers, since we want to express
they can be used without qdisc lock, and that qlen is no longer percpu.

- qdisc_qstats_cpu_qlen_dec -> qdisc_qstats_atomic_qlen_dec()
- qdisc_qstats_cpu_qlen_inc -> qdisc_qstats_atomic_qlen_inc()

Later (net-next) we might revert this patch by tracking all these
qlen uses and replace them by a more efficient method (not having
to access a precise qlen, but an empty/non_empty status that might
be less expensive to maintain/track).

Another possibility is to have a legacy pfifo_fast version that would
be used when used a a child qdisc, since the parent qdisc needs
a spinlock anyway. But then, future lockless qdiscs would also
have the same problem.

Fixes: 7e66016f2c65 ("net: sched: helpers to sum qlen and qlen for per cpu logic")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h | 31 +++++++++++++------------------
 net/core/gen_stats.c      |  2 --
 net/sched/sch_generic.c   | 13 ++++++-------
 3 files changed, 19 insertions(+), 27 deletions(-)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 4d736427a4cb..13327bd43231 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -48,7 +48,10 @@ struct qdisc_size_table {
 struct qdisc_skb_head {
 	struct sk_buff	*head;
 	struct sk_buff	*tail;
-	__u32		qlen;
+	union {
+		u32		qlen;
+		atomic_t	atomic_qlen;
+	};
 	spinlock_t	lock;
 };
 
@@ -405,27 +408,19 @@ static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz)
 	BUILD_BUG_ON(sizeof(qcb->data) < sz);
 }
 
-static inline int qdisc_qlen_cpu(const struct Qdisc *q)
-{
-	return this_cpu_ptr(q->cpu_qstats)->qlen;
-}
-
 static inline int qdisc_qlen(const struct Qdisc *q)
 {
 	return q->q.qlen;
 }
 
-static inline int qdisc_qlen_sum(const struct Qdisc *q)
+static inline u32 qdisc_qlen_sum(const struct Qdisc *q)
 {
-	__u32 qlen = q->qstats.qlen;
-	int i;
+	u32 qlen = q->qstats.qlen;
 
-	if (q->flags & TCQ_F_NOLOCK) {
-		for_each_possible_cpu(i)
-			qlen += per_cpu_ptr(q->cpu_qstats, i)->qlen;
-	} else {
+	if (q->flags & TCQ_F_NOLOCK)
+		qlen += atomic_read(&q->q.atomic_qlen);
+	else
 		qlen += q->q.qlen;
-	}
 
 	return qlen;
 }
@@ -798,14 +793,14 @@ static inline void qdisc_qstats_cpu_backlog_inc(struct Qdisc *sch,
 	this_cpu_add(sch->cpu_qstats->backlog, qdisc_pkt_len(skb));
 }
 
-static inline void qdisc_qstats_cpu_qlen_inc(struct Qdisc *sch)
+static inline void qdisc_qstats_atomic_qlen_inc(struct Qdisc *sch)
 {
-	this_cpu_inc(sch->cpu_qstats->qlen);
+	atomic_inc(&sch->q.atomic_qlen);
 }
 
-static inline void qdisc_qstats_cpu_qlen_dec(struct Qdisc *sch)
+static inline void qdisc_qstats_atomic_qlen_dec(struct Qdisc *sch)
 {
-	this_cpu_dec(sch->cpu_qstats->qlen);
+	atomic_dec(&sch->q.atomic_qlen);
 }
 
 static inline void qdisc_qstats_cpu_requeues_inc(struct Qdisc *sch)
diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c
index 9bf1b9ad1780..ac679f74ba47 100644
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -291,7 +291,6 @@ __gnet_stats_copy_queue_cpu(struct gnet_stats_queue *qstats,
 	for_each_possible_cpu(i) {
 		const struct gnet_stats_queue *qcpu = per_cpu_ptr(q, i);
 
-		qstats->qlen = 0;
 		qstats->backlog += qcpu->backlog;
 		qstats->drops += qcpu->drops;
 		qstats->requeues += qcpu->requeues;
@@ -307,7 +306,6 @@ void __gnet_stats_copy_queue(struct gnet_stats_queue *qstats,
 	if (cpu) {
 		__gnet_stats_copy_queue_cpu(qstats, cpu);
 	} else {
-		qstats->qlen = q->qlen;
 		qstats->backlog = q->backlog;
 		qstats->drops = q->drops;
 		qstats->requeues = q->requeues;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index de1663f7d3ad..52f429b1cdd5 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -68,7 +68,7 @@ static inline struct sk_buff *__skb_dequeue_bad_txq(struct Qdisc *q)
 			skb = __skb_dequeue(&q->skb_bad_txq);
 			if (qdisc_is_percpu_stats(q)) {
 				qdisc_qstats_cpu_backlog_dec(q, skb);
-				qdisc_qstats_cpu_qlen_dec(q);
+				qdisc_qstats_atomic_qlen_dec(q);
 			} else {
 				qdisc_qstats_backlog_dec(q, skb);
 				q->q.qlen--;
@@ -108,7 +108,7 @@ static inline void qdisc_enqueue_skb_bad_txq(struct Qdisc *q,
 
 	if (qdisc_is_percpu_stats(q)) {
 		qdisc_qstats_cpu_backlog_inc(q, skb);
-		qdisc_qstats_cpu_qlen_inc(q);
+		qdisc_qstats_atomic_qlen_inc(q);
 	} else {
 		qdisc_qstats_backlog_inc(q, skb);
 		q->q.qlen++;
@@ -147,7 +147,7 @@ static inline int dev_requeue_skb_locked(struct sk_buff *skb, struct Qdisc *q)
 
 		qdisc_qstats_cpu_requeues_inc(q);
 		qdisc_qstats_cpu_backlog_inc(q, skb);
-		qdisc_qstats_cpu_qlen_inc(q);
+		qdisc_qstats_atomic_qlen_inc(q);
 
 		skb = next;
 	}
@@ -252,7 +252,7 @@ static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate,
 			skb = __skb_dequeue(&q->gso_skb);
 			if (qdisc_is_percpu_stats(q)) {
 				qdisc_qstats_cpu_backlog_dec(q, skb);
-				qdisc_qstats_cpu_qlen_dec(q);
+				qdisc_qstats_atomic_qlen_dec(q);
 			} else {
 				qdisc_qstats_backlog_dec(q, skb);
 				q->q.qlen--;
@@ -645,7 +645,7 @@ static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc,
 	if (unlikely(err))
 		return qdisc_drop_cpu(skb, qdisc, to_free);
 
-	qdisc_qstats_cpu_qlen_inc(qdisc);
+	qdisc_qstats_atomic_qlen_inc(qdisc);
 	/* Note: skb can not be used after skb_array_produce(),
 	 * so we better not use qdisc_qstats_cpu_backlog_inc()
 	 */
@@ -670,7 +670,7 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc)
 	if (likely(skb)) {
 		qdisc_qstats_cpu_backlog_dec(qdisc, skb);
 		qdisc_bstats_cpu_update(qdisc, skb);
-		qdisc_qstats_cpu_qlen_dec(qdisc);
+		qdisc_qstats_atomic_qlen_dec(qdisc);
 	}
 
 	return skb;
@@ -714,7 +714,6 @@ static void pfifo_fast_reset(struct Qdisc *qdisc)
 		struct gnet_stats_queue *q = per_cpu_ptr(qdisc->cpu_qstats, i);
 
 		q->backlog = 0;
-		q->qlen = 0;
 	}
 }
 
-- 
2.20.1


From 06f00a302b2c4c51c300cd5761ee16cf466edcd3 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Sat, 2 Mar 2019 10:34:55 +0800
Subject: [PATCH 07/42] net-sysfs: Fix mem leak in netdev_register_kobject

[ Upstream commit 895a5e96dbd6386c8e78e5b78e067dcc67b7f0ab ]

syzkaller report this:
BUG: memory leak
unreferenced object 0xffff88837a71a500 (size 256):
  comm "syz-executor.2", pid 9770, jiffies 4297825125 (age 17.843s)
  hex dump (first 32 bytes):
    00 00 00 00 ad 4e ad de ff ff ff ff 00 00 00 00  .....N..........
    ff ff ff ff ff ff ff ff 20 c0 ef 86 ff ff ff ff  ........ .......
  backtrace:
    [<00000000db12624b>] netdev_register_kobject+0x124/0x2e0 net/core/net-sysfs.c:1751
    [<00000000dc49a994>] register_netdevice+0xcc1/0x1270 net/core/dev.c:8516
    [<00000000e5f3fea0>] tun_set_iff drivers/net/tun.c:2649 [inline]
    [<00000000e5f3fea0>] __tun_chr_ioctl+0x2218/0x3d20 drivers/net/tun.c:2883
    [<000000001b8ac127>] vfs_ioctl fs/ioctl.c:46 [inline]
    [<000000001b8ac127>] do_vfs_ioctl+0x1a5/0x10e0 fs/ioctl.c:690
    [<0000000079b269f8>] ksys_ioctl+0x89/0xa0 fs/ioctl.c:705
    [<00000000de649beb>] __do_sys_ioctl fs/ioctl.c:712 [inline]
    [<00000000de649beb>] __se_sys_ioctl fs/ioctl.c:710 [inline]
    [<00000000de649beb>] __x64_sys_ioctl+0x74/0xb0 fs/ioctl.c:710
    [<000000007ebded1e>] do_syscall_64+0xc8/0x580 arch/x86/entry/common.c:290
    [<00000000db315d36>] entry_SYSCALL_64_after_hwframe+0x49/0xbe
    [<00000000115be9bb>] 0xffffffffffffffff

It should call kset_unregister to free 'dev->queues_kset'
in error path of register_queue_kobjects, otherwise will cause a mem leak.

Reported-by: Hulk Robot <hulkci@huawei.com>
Fixes: 1d24eb4815d1 ("xps: Transmit Packet Steering")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/net-sysfs.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index bd67c4d0fcfd..2aabb7eb0854 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1547,6 +1547,9 @@ static int register_queue_kobjects(struct net_device *dev)
 error:
 	netdev_queue_update_kobjects(dev, txq, 0);
 	net_rx_queue_update_kobjects(dev, rxq, 0);
+#ifdef CONFIG_SYSFS
+	kset_unregister(dev->queues_kset);
+#endif
 	return error;
 }
 
-- 
2.20.1


From 8b576ba026fb45a8af4562485d50a22f34887046 Mon Sep 17 00:00:00 2001
From: Kristian Evensen <kristian.evensen@gmail.com>
Date: Sat, 2 Mar 2019 13:32:26 +0100
Subject: [PATCH 08/42] qmi_wwan: Add support for Quectel EG12/EM12
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 822e44b45eb991c63487c5e2ce7d636411870a8d ]

Quectel EG12 (module)/EM12 (M.2 card) is a Cat. 12 LTE modem. The modem
behaves in the same way as the EP06, so the "set DTR"-quirk must be
applied and the diagnostic-interface check performed. Since the
diagnostic-check now applies to more modems, I have renamed the function
from quectel_ep06_diag_detected() to quectel_diag_detected().

Signed-off-by: Kristian Evensen <kristian.evensen@gmail.com>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 26 ++++++++++++++++++--------
 1 file changed, 18 insertions(+), 8 deletions(-)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 735ad838e2ba..6e381354f658 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -976,6 +976,13 @@ static const struct usb_device_id products[] = {
 					      0xff),
 		.driver_info	    = (unsigned long)&qmi_wwan_info_quirk_dtr,
 	},
+	{	/* Quectel EG12/EM12 */
+		USB_DEVICE_AND_INTERFACE_INFO(0x2c7c, 0x0512,
+					      USB_CLASS_VENDOR_SPEC,
+					      USB_SUBCLASS_VENDOR_SPEC,
+					      0xff),
+		.driver_info	    = (unsigned long)&qmi_wwan_info_quirk_dtr,
+	},
 
 	/* 3. Combined interface devices matching on interface number */
 	{QMI_FIXED_INTF(0x0408, 0xea42, 4)},	/* Yota / Megafon M100-1 */
@@ -1343,17 +1350,20 @@ static bool quectel_ec20_detected(struct usb_interface *intf)
 	return false;
 }
 
-static bool quectel_ep06_diag_detected(struct usb_interface *intf)
+static bool quectel_diag_detected(struct usb_interface *intf)
 {
 	struct usb_device *dev = interface_to_usbdev(intf);
 	struct usb_interface_descriptor intf_desc = intf->cur_altsetting->desc;
+	u16 id_vendor = le16_to_cpu(dev->descriptor.idVendor);
+	u16 id_product = le16_to_cpu(dev->descriptor.idProduct);
 
-	if (le16_to_cpu(dev->descriptor.idVendor) == 0x2c7c &&
-	    le16_to_cpu(dev->descriptor.idProduct) == 0x0306 &&
-	    intf_desc.bNumEndpoints == 2)
-		return true;
+	if (id_vendor != 0x2c7c || intf_desc.bNumEndpoints != 2)
+		return false;
 
-	return false;
+	if (id_product == 0x0306 || id_product == 0x0512)
+		return true;
+	else
+		return false;
 }
 
 static int qmi_wwan_probe(struct usb_interface *intf,
@@ -1390,13 +1400,13 @@ static int qmi_wwan_probe(struct usb_interface *intf,
 		return -ENODEV;
 	}
 
-	/* Quectel EP06/EM06/EG06 supports dynamic interface configuration, so
+	/* Several Quectel modems supports dynamic interface configuration, so
 	 * we need to match on class/subclass/protocol. These values are
 	 * identical for the diagnostic- and QMI-interface, but bNumEndpoints is
 	 * different. Ignore the current interface if the number of endpoints
 	 * the number for the diag interface (two).
 	 */
-	if (quectel_ep06_diag_detected(intf))
+	if (quectel_diag_detected(intf))
 		return -ENODEV;
 
 	return usbnet_probe(intf, id);
-- 
2.20.1


From 915f9491a45e167194940bf56962976b0cf8f74a Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 3 Mar 2019 16:50:26 +0800
Subject: [PATCH 09/42] sctp: call iov_iter_revert() after sending ABORT

[ Upstream commit 901efe12318b1ea8d3e2c88a7b75ed6e6d5d7245 ]

The user msg is also copied to the abort packet when doing SCTP_ABORT in
sctp_sendmsg_check_sflags(). When SCTP_SENDALL is set, iov_iter_revert()
should have been called for sending abort on the next asoc with copying
this msg. Otherwise, memcpy_from_msg() in sctp_make_abort_user() will
fail and return error.

Fixes: 4910280503f3 ("sctp: add support for snd flag SCTP_SENDALL process in sendmsg")
Reported-by: Ying Xu <yinxu@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index b7a534f6d7c2..1b5728e9c497 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1866,6 +1866,7 @@ static int sctp_sendmsg_check_sflags(struct sctp_association *asoc,
 
 		pr_debug("%s: aborting association:%p\n", __func__, asoc);
 		sctp_primitive_ABORT(net, asoc, chunk);
+		iov_iter_revert(&msg->msg_iter, msg_len);
 
 		return 0;
 	}
-- 
2.20.1


From a17ec2cb65b5b5ce7f1ee6aac55de8f634d8041d Mon Sep 17 00:00:00 2001
From: Kai-Heng Feng <kai.heng.feng@canonical.com>
Date: Mon, 4 Mar 2019 15:00:03 +0800
Subject: [PATCH 10/42] sky2: Disable MSI on Dell Inspiron 1545 and Gateway
 P-79

[ Upstream commit b33b7cd6fd86478dd2890a9abeb6f036aa01fdf7 ]

Some sky2 chips fire IRQ after S3, before the driver is fully resumed:
[ 686.804877] do_IRQ: 1.37 No irq handler for vector

This is likely a platform bug that device isn't fully quiesced during
S3. Use MSI-X, maskable MSI or INTx can prevent this issue from
happening.

Since MSI-X and maskable MSI are not supported by this device, fallback
to use INTx on affected platforms.

BugLink: https://bugs.launchpad.net/bugs/1807259
BugLink: https://bugs.launchpad.net/bugs/1809843
Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/sky2.c | 24 +++++++++++++++++++++++-
 1 file changed, 23 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index ae2f35039343..1485f66cf7b0 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -46,6 +46,7 @@
 #include <linux/mii.h>
 #include <linux/of_device.h>
 #include <linux/of_net.h>
+#include <linux/dmi.h>
 
 #include <asm/irq.h>
 
@@ -93,7 +94,7 @@ static int copybreak __read_mostly = 128;
 module_param(copybreak, int, 0);
 MODULE_PARM_DESC(copybreak, "Receive copy threshold");
 
-static int disable_msi = 0;
+static int disable_msi = -1;
 module_param(disable_msi, int, 0);
 MODULE_PARM_DESC(disable_msi, "Disable Message Signaled Interrupt (MSI)");
 
@@ -4931,6 +4932,24 @@ static const char *sky2_name(u8 chipid, char *buf, int sz)
 	return buf;
 }
 
+static const struct dmi_system_id msi_blacklist[] = {
+	{
+		.ident = "Dell Inspiron 1545",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 1545"),
+		},
+	},
+	{
+		.ident = "Gateway P-79",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Gateway"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "P-79"),
+		},
+	},
+	{}
+};
+
 static int sky2_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	struct net_device *dev, *dev1;
@@ -5042,6 +5061,9 @@ static int sky2_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_out_free_pci;
 	}
 
+	if (disable_msi == -1)
+		disable_msi = !!dmi_check_system(msi_blacklist);
+
 	if (!disable_msi && pci_enable_msi(pdev) == 0) {
 		err = sky2_test_msi(hw);
 		if (err) {
-- 
2.20.1


From abfba30b385f5725592b4ba13f2cee9cfb28d5b9 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Sun, 3 Mar 2019 07:35:51 +0000
Subject: [PATCH 11/42] team: Free BPF filter when unregistering netdev

[ Upstream commit 692c31bd4054212312396b1d303bffab2c5b93a7 ]

When team is used in loadbalance mode a BPF filter can be used to
provide a hash which will determine the Tx port.

When the netdev is later unregistered the filter is not freed which
results in memory leaks [1].

Fix by freeing the program and the corresponding filter when
unregistering the netdev.

[1]
unreferenced object 0xffff8881dbc47cc8 (size 16):
  comm "teamd", pid 3068, jiffies 4294997779 (age 438.247s)
  hex dump (first 16 bytes):
    a3 00 6b 6b 6b 6b 6b 6b 88 a5 82 e1 81 88 ff ff  ..kkkkkk........
  backtrace:
    [<000000008a3b47e3>] team_nl_cmd_options_set+0x88f/0x11b0
    [<00000000c4f4f27e>] genl_family_rcv_msg+0x78f/0x1080
    [<00000000610ef838>] genl_rcv_msg+0xca/0x170
    [<00000000a281df93>] netlink_rcv_skb+0x132/0x380
    [<000000004d9448a2>] genl_rcv+0x29/0x40
    [<000000000321b2f4>] netlink_unicast+0x4c0/0x690
    [<000000008c25dffb>] netlink_sendmsg+0x929/0xe10
    [<00000000068298c5>] sock_sendmsg+0xc8/0x110
    [<0000000082a61ff0>] ___sys_sendmsg+0x77a/0x8f0
    [<00000000663ae29d>] __sys_sendmsg+0xf7/0x250
    [<0000000027c5f11a>] do_syscall_64+0x14d/0x610
    [<000000006cfbc8d3>] entry_SYSCALL_64_after_hwframe+0x49/0xbe
    [<00000000e23197e2>] 0xffffffffffffffff
unreferenced object 0xffff8881e182a588 (size 2048):
  comm "teamd", pid 3068, jiffies 4294997780 (age 438.247s)
  hex dump (first 32 bytes):
    20 00 00 00 02 00 00 00 30 00 00 00 28 f0 ff ff   .......0...(...
    07 00 00 00 00 00 00 00 28 00 00 00 00 00 00 00  ........(.......
  backtrace:
    [<000000002daf01fb>] lb_bpf_func_set+0x45c/0x6d0
    [<000000008a3b47e3>] team_nl_cmd_options_set+0x88f/0x11b0
    [<00000000c4f4f27e>] genl_family_rcv_msg+0x78f/0x1080
    [<00000000610ef838>] genl_rcv_msg+0xca/0x170
    [<00000000a281df93>] netlink_rcv_skb+0x132/0x380
    [<000000004d9448a2>] genl_rcv+0x29/0x40
    [<000000000321b2f4>] netlink_unicast+0x4c0/0x690
    [<000000008c25dffb>] netlink_sendmsg+0x929/0xe10
    [<00000000068298c5>] sock_sendmsg+0xc8/0x110
    [<0000000082a61ff0>] ___sys_sendmsg+0x77a/0x8f0
    [<00000000663ae29d>] __sys_sendmsg+0xf7/0x250
    [<0000000027c5f11a>] do_syscall_64+0x14d/0x610
    [<000000006cfbc8d3>] entry_SYSCALL_64_after_hwframe+0x49/0xbe
    [<00000000e23197e2>] 0xffffffffffffffff

Fixes: 01d7f30a9f96 ("team: add loadbalance mode")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Amit Cohen <amitc@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team_mode_loadbalance.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/net/team/team_mode_loadbalance.c b/drivers/net/team/team_mode_loadbalance.c
index a5ef97010eb3..5541e1c19936 100644
--- a/drivers/net/team/team_mode_loadbalance.c
+++ b/drivers/net/team/team_mode_loadbalance.c
@@ -325,6 +325,20 @@ static int lb_bpf_func_set(struct team *team, struct team_gsetter_ctx *ctx)
 	return 0;
 }
 
+static void lb_bpf_func_free(struct team *team)
+{
+	struct lb_priv *lb_priv = get_lb_priv(team);
+	struct bpf_prog *fp;
+
+	if (!lb_priv->ex->orig_fprog)
+		return;
+
+	__fprog_destroy(lb_priv->ex->orig_fprog);
+	fp = rcu_dereference_protected(lb_priv->fp,
+				       lockdep_is_held(&team->lock));
+	bpf_prog_destroy(fp);
+}
+
 static int lb_tx_method_get(struct team *team, struct team_gsetter_ctx *ctx)
 {
 	struct lb_priv *lb_priv = get_lb_priv(team);
@@ -639,6 +653,7 @@ static void lb_exit(struct team *team)
 
 	team_options_unregister(team, lb_options,
 				ARRAY_SIZE(lb_options));
+	lb_bpf_func_free(team);
 	cancel_delayed_work_sync(&lb_priv->ex->stats.refresh_dw);
 	free_percpu(lb_priv->pcpu_stats);
 	kfree(lb_priv->ex);
-- 
2.20.1


From 5922879e616997d918e23d0fcf7275c446461d3c Mon Sep 17 00:00:00 2001
From: Erik Hugne <erik.hugne@gmail.com>
Date: Mon, 4 Mar 2019 23:26:10 +0100
Subject: [PATCH 12/42] tipc: fix RDM/DGRAM connect() regression

[ Upstream commit 0e63208915a8d7590d0a6218dadb2a6a00ac705a ]

Fix regression bug introduced in
commit 365ad353c256 ("tipc: reduce risk of user starvation during link
congestion")

Only signal -EDESTADDRREQ for RDM/DGRAM if we don't have a cached
sockaddr.

Fixes: 365ad353c256 ("tipc: reduce risk of user starvation during link congestion")
Signed-off-by: Erik Hugne <erik.hugne@gmail.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/socket.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 8f34db2a9785..615de0910a07 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1320,7 +1320,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
 
 	if (unlikely(!dest)) {
 		dest = &tsk->peer;
-		if (!syn || dest->family != AF_TIPC)
+		if (!syn && dest->family != AF_TIPC)
 			return -EDESTADDRREQ;
 	}
 
-- 
2.20.1


From 95ef65503c47ddb211cf327118d98948485f3c6b Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Wed, 27 Feb 2019 03:58:53 -0500
Subject: [PATCH 13/42] bnxt_en: Drop oversize TX packets to prevent errors.

[ Upstream commit 2b3c6885386020b1b9d92d45e8349637e27d1f66 ]

There have been reports of oversize UDP packets being sent to the
driver to be transmitted, causing error conditions.  The issue is
likely caused by the dst of the SKB switching between 'lo' with
64K MTU and the hardware device with a smaller MTU.  Patches are
being proposed by Mahesh Bandewar <maheshb@google.com> to fix the
issue.

In the meantime, add a quick length check in the driver to prevent
the error.  The driver uses the TX packet size as index to look up an
array to setup the TX BD.  The array is large enough to support all MTU
sizes supported by the driver.  The oversize TX packet causes the
driver to index beyond the array and put garbage values into the
TX BD.  Add a simple check to prevent this.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 090207817ad8..29b068b81e2a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -497,6 +497,12 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	length >>= 9;
+	if (unlikely(length >= ARRAY_SIZE(bnxt_lhint_arr))) {
+		dev_warn_ratelimited(&pdev->dev, "Dropped oversize %d bytes TX packet.\n",
+				     skb->len);
+		i = 0;
+		goto tx_dma_error;
+	}
 	flags |= bnxt_lhint_arr[length];
 	txbd->tx_bd_len_flags_type = cpu_to_le32(flags);
 
-- 
2.20.1


From 2961c09e464f461c2cb5af18aeb95396e1427ef0 Mon Sep 17 00:00:00 2001
From: Jiri Benc <jbenc@redhat.com>
Date: Thu, 28 Feb 2019 14:56:04 +0100
Subject: [PATCH 14/42] geneve: correctly handle ipv6.disable module parameter

[ Upstream commit cf1c9ccba7308e48a68fa77f476287d9d614e4c7 ]

When IPv6 is compiled but disabled at runtime, geneve_sock_add returns
-EAFNOSUPPORT. For metadata based tunnels, this causes failure of the whole
operation of bringing up the tunnel.

Ignore failure of IPv6 socket creation for metadata based tunnels caused by
IPv6 not being available.

This is the same fix as what commit d074bf960044 ("vxlan: correctly handle
ipv6.disable module parameter") is doing for vxlan.

Note there's also commit c0a47e44c098 ("geneve: should not call rt6_lookup()
when ipv6 was disabled") which fixes a similar issue but for regular
tunnels, while this patch is needed for metadata based tunnels.

Signed-off-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 2e6e11d8cf5c..d6ad8331ca4f 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -637,15 +637,20 @@ static int geneve_sock_add(struct geneve_dev *geneve, bool ipv6)
 static int geneve_open(struct net_device *dev)
 {
 	struct geneve_dev *geneve = netdev_priv(dev);
-	bool ipv6 = !!(geneve->info.mode & IP_TUNNEL_INFO_IPV6);
 	bool metadata = geneve->collect_md;
+	bool ipv4, ipv6;
 	int ret = 0;
 
+	ipv6 = geneve->info.mode & IP_TUNNEL_INFO_IPV6 || metadata;
+	ipv4 = !ipv6 || metadata;
 #if IS_ENABLED(CONFIG_IPV6)
-	if (ipv6 || metadata)
+	if (ipv6) {
 		ret = geneve_sock_add(geneve, true);
+		if (ret < 0 && ret != -EAFNOSUPPORT)
+			ipv4 = false;
+	}
 #endif
-	if (!ret && (!ipv6 || metadata))
+	if (ipv4)
 		ret = geneve_sock_add(geneve, false);
 	if (ret < 0)
 		geneve_sock_release(geneve);
-- 
2.20.1


From 904e6b38f88346ac1a5110890b7a6c0c2e70dc5a Mon Sep 17 00:00:00 2001
From: Haiyang Zhang <haiyangz@microsoft.com>
Date: Fri, 22 Feb 2019 18:25:03 +0000
Subject: [PATCH 15/42] hv_netvsc: Fix IP header checksum for coalesced packets

[ Upstream commit bf48648d650db1146b75b9bd358502431e86cf4f ]

Incoming packets may have IP header checksum verified by the host.
They may not have IP header checksum computed after coalescing.
This patch re-compute the checksum when necessary, otherwise the
packets may be dropped, because Linux network stack always checks it.

Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/netvsc_drv.c | 22 +++++++++++++++++++---
 1 file changed, 19 insertions(+), 3 deletions(-)

diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 80d9297ad9d9..136533e2e487 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -744,6 +744,14 @@ void netvsc_linkstatus_callback(struct net_device *net,
 	schedule_delayed_work(&ndev_ctx->dwork, 0);
 }
 
+static void netvsc_comp_ipcsum(struct sk_buff *skb)
+{
+	struct iphdr *iph = (struct iphdr *)skb->data;
+
+	iph->check = 0;
+	iph->check = ip_fast_csum(iph, iph->ihl);
+}
+
 static struct sk_buff *netvsc_alloc_recv_skb(struct net_device *net,
 					     struct netvsc_channel *nvchan)
 {
@@ -770,9 +778,17 @@ static struct sk_buff *netvsc_alloc_recv_skb(struct net_device *net,
 	/* skb is already created with CHECKSUM_NONE */
 	skb_checksum_none_assert(skb);
 
-	/*
-	 * In Linux, the IP checksum is always checked.
-	 * Do L4 checksum offload if enabled and present.
+	/* Incoming packets may have IP header checksum verified by the host.
+	 * They may not have IP header checksum computed after coalescing.
+	 * We compute it here if the flags are set, because on Linux, the IP
+	 * checksum is always checked.
+	 */
+	if (csum_info && csum_info->receive.ip_checksum_value_invalid &&
+	    csum_info->receive.ip_checksum_succeeded &&
+	    skb->protocol == htons(ETH_P_IP))
+		netvsc_comp_ipcsum(skb);
+
+	/* Do L4 checksum offload if enabled and present.
 	 */
 	if (csum_info && (net->features & NETIF_F_RXCSUM)) {
 		if (csum_info->receive.tcp_checksum_succeeded ||
-- 
2.20.1


From c6f81c577c609cf7dd6833e16076f8ecbd17855d Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Wed, 27 Feb 2019 16:15:29 +0800
Subject: [PATCH 16/42] ipv4: Add ICMPv6 support when parse route ipproto

[ Upstream commit 5e1a99eae84999a2536f50a0beaf5d5262337f40 ]

For ip rules, we need to use 'ipproto ipv6-icmp' to match ICMPv6 headers.
But for ip -6 route, currently we only support tcp, udp and icmp.

Add ICMPv6 support so we can match ipv6-icmp rules for route lookup.

v2: As David Ahern and Sabrina Dubroca suggested, Add an argument to
rtm_getroute_parse_ip_proto() to handle ICMP/ICMPv6 with different family.

Reported-by: Jianlin Shi <jishi@redhat.com>
Fixes: eacb9384a3fe ("ipv6: support sport, dport and ip_proto in RTM_GETROUTE")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h   |  2 +-
 net/ipv4/netlink.c | 17 +++++++++++++----
 net/ipv4/route.c   |  2 +-
 net/ipv6/route.c   |  3 ++-
 4 files changed, 17 insertions(+), 7 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index 72593e171d14..30c657b128ce 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -714,7 +714,7 @@ extern int sysctl_icmp_msgs_burst;
 int ip_misc_proc_init(void);
 #endif
 
-int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto,
+int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto, u8 family,
 				struct netlink_ext_ack *extack);
 
 #endif	/* _IP_H */
diff --git a/net/ipv4/netlink.c b/net/ipv4/netlink.c
index f86bb4f06609..d8e3a1fb8e82 100644
--- a/net/ipv4/netlink.c
+++ b/net/ipv4/netlink.c
@@ -3,9 +3,10 @@
 #include <linux/types.h>
 #include <net/net_namespace.h>
 #include <net/netlink.h>
+#include <linux/in6.h>
 #include <net/ip.h>
 
-int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto,
+int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto, u8 family,
 				struct netlink_ext_ack *extack)
 {
 	*ip_proto = nla_get_u8(attr);
@@ -13,11 +14,19 @@ int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto,
 	switch (*ip_proto) {
 	case IPPROTO_TCP:
 	case IPPROTO_UDP:
+		return 0;
 	case IPPROTO_ICMP:
+		if (family != AF_INET)
+			break;
+		return 0;
+#if IS_ENABLED(CONFIG_IPV6)
+	case IPPROTO_ICMPV6:
+		if (family != AF_INET6)
+			break;
 		return 0;
-	default:
-		NL_SET_ERR_MSG(extack, "Unsupported ip proto");
-		return -EOPNOTSUPP;
+#endif
 	}
+	NL_SET_ERR_MSG(extack, "Unsupported ip proto");
+	return -EOPNOTSUPP;
 }
 EXPORT_SYMBOL_GPL(rtm_getroute_parse_ip_proto);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d1ddf1d03721..efe45200db4f 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2803,7 +2803,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 
 	if (tb[RTA_IP_PROTO]) {
 		err = rtm_getroute_parse_ip_proto(tb[RTA_IP_PROTO],
-						  &ip_proto, extack);
+						  &ip_proto, AF_INET, extack);
 		if (err)
 			return err;
 	}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 059f0531f7c1..a68d447b6e2c 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -4880,7 +4880,8 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 
 	if (tb[RTA_IP_PROTO]) {
 		err = rtm_getroute_parse_ip_proto(tb[RTA_IP_PROTO],
-						  &fl6.flowi6_proto, extack);
+						  &fl6.flowi6_proto, AF_INET6,
+						  extack);
 		if (err)
 			goto errout;
 	}
-- 
2.20.1


From 0565588709cdc74d47a3fcdd1d5593babefb93aa Mon Sep 17 00:00:00 2001
From: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Date: Tue, 26 Feb 2019 14:06:26 -0500
Subject: [PATCH 17/42] lan743x: Fix TX Stall Issue

[ Upstream commit 90490ef7269906423a1c1b917fc24be8b1602658 ]

It has been observed that tx queue stalls while downloading
from certain web sites (example www.speedtest.net)

The cause has been tracked down to a corner case where
dma descriptors where not setup properly. And there for a tx
completion interrupt was not signaled.

This fix corrects the problem by properly marking the end of
a multi descriptor transmission.

Fixes: 23f0703c125b ("lan743x: Add main source files for new lan743x driver")
Signed-off-by: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/lan743x_main.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index 1ce8b729929f..671ea75d0a4a 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -1400,7 +1400,8 @@ static int lan743x_tx_frame_start(struct lan743x_tx *tx,
 }
 
 static void lan743x_tx_frame_add_lso(struct lan743x_tx *tx,
-				     unsigned int frame_length)
+				     unsigned int frame_length,
+				     int nr_frags)
 {
 	/* called only from within lan743x_tx_xmit_frame.
 	 * assuming tx->ring_lock has already been acquired.
@@ -1410,6 +1411,10 @@ static void lan743x_tx_frame_add_lso(struct lan743x_tx *tx,
 
 	/* wrap up previous descriptor */
 	tx->frame_data0 |= TX_DESC_DATA0_EXT_;
+	if (nr_frags <= 0) {
+		tx->frame_data0 |= TX_DESC_DATA0_LS_;
+		tx->frame_data0 |= TX_DESC_DATA0_IOC_;
+	}
 	tx_descriptor = &tx->ring_cpu_ptr[tx->frame_tail];
 	tx_descriptor->data0 = tx->frame_data0;
 
@@ -1514,8 +1519,11 @@ static void lan743x_tx_frame_end(struct lan743x_tx *tx,
 	u32 tx_tail_flags = 0;
 
 	/* wrap up previous descriptor */
-	tx->frame_data0 |= TX_DESC_DATA0_LS_;
-	tx->frame_data0 |= TX_DESC_DATA0_IOC_;
+	if ((tx->frame_data0 & TX_DESC_DATA0_DTYPE_MASK_) ==
+	    TX_DESC_DATA0_DTYPE_DATA_) {
+		tx->frame_data0 |= TX_DESC_DATA0_LS_;
+		tx->frame_data0 |= TX_DESC_DATA0_IOC_;
+	}
 
 	tx_descriptor = &tx->ring_cpu_ptr[tx->frame_tail];
 	buffer_info = &tx->buffer_info[tx->frame_tail];
@@ -1600,7 +1608,7 @@ static netdev_tx_t lan743x_tx_xmit_frame(struct lan743x_tx *tx,
 	}
 
 	if (gso)
-		lan743x_tx_frame_add_lso(tx, frame_length);
+		lan743x_tx_frame_add_lso(tx, frame_length, nr_frags);
 
 	if (nr_frags <= 0)
 		goto finish;
-- 
2.20.1


From be96c91a0e2145a96eac27c911428ab60fb5c993 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Fri, 1 Mar 2019 23:43:39 +0100
Subject: [PATCH 18/42] net: dsa: mv88e6xxx: Fix statistics on mv88e6161

[ Upstream commit a6da21bb0eae459a375d5bd48baed821d14301d0 ]

Despite what the datesheet says, the silicon implements the older way
of snapshoting the statistics. Change the op.

Reported-by: Chris.Healy@zii.aero
Tested-by: Chris.Healy@zii.aero
Fixes: 0ac64c394900 ("net: dsa: mv88e6xxx: mv88e6161 uses mv88e6320 stats snapshot")
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index b74cd49d0fb0..94222b435378 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -3082,7 +3082,7 @@ static const struct mv88e6xxx_ops mv88e6161_ops = {
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.port_link_state = mv88e6352_port_link_state,
 	.port_get_cmode = mv88e6185_port_get_cmode,
-	.stats_snapshot = mv88e6320_g1_stats_snapshot,
+	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
 	.stats_get_strings = mv88e6095_stats_get_strings,
-- 
2.20.1


From 77b1ebda1a4edb824759bb21693c4c86199f3b62 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Thu, 28 Feb 2019 18:14:03 +0100
Subject: [PATCH 19/42] net: dsa: mv88e6xxx: Fix u64 statistics

[ Upstream commit 6e46e2d821bb22b285ae8187959096b65d063b0d ]

The switch maintains u64 counters for the number of octets sent and
received. These are kept as two u32's which need to be combined.  Fix
the combing, which wrongly worked on u16's.

Fixes: 80c4627b2719 ("dsa: mv88x6xxx: Refactor getting a single statistic")
Reported-by: Chris Healy <Chris.Healy@zii.aero>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 94222b435378..0166f740e625 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -896,7 +896,7 @@ static uint64_t _mv88e6xxx_get_ethtool_stat(struct mv88e6xxx_chip *chip,
 	default:
 		return U64_MAX;
 	}
-	value = (((u64)high) << 16) | low;
+	value = (((u64)high) << 32) | low;
 	return value;
 }
 
-- 
2.20.1


From 27850164b27d044d82eae978d4888781317e508e Mon Sep 17 00:00:00 2001
From: Paul Moore <paul@paul-moore.com>
Date: Mon, 25 Feb 2019 19:06:06 -0500
Subject: [PATCH 20/42] netlabel: fix out-of-bounds memory accesses

[ Upstream commit 5578de4834fe0f2a34fedc7374be691443396d1f ]

There are two array out-of-bounds memory accesses, one in
cipso_v4_map_lvl_valid(), the other in netlbl_bitmap_walk().  Both
errors are embarassingly simple, and the fixes are straightforward.

As a FYI for anyone backporting this patch to kernels prior to v4.8,
you'll want to apply the netlbl_bitmap_walk() patch to
cipso_v4_bitmap_walk() as netlbl_bitmap_walk() doesn't exist before
Linux v4.8.

Reported-by: Jann Horn <jannh@google.com>
Fixes: 446fda4f2682 ("[NetLabel]: CIPSOv4 engine")
Fixes: 3faa8f982f95 ("netlabel: Move bitmap manipulation functions to the NetLabel core.")
Signed-off-by: Paul Moore <paul@paul-moore.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/cipso_ipv4.c        | 3 ++-
 net/netlabel/netlabel_kapi.c | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 777fa3b7fb13..f4b83de2263e 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -667,7 +667,8 @@ static int cipso_v4_map_lvl_valid(const struct cipso_v4_doi *doi_def, u8 level)
 	case CIPSO_V4_MAP_PASS:
 		return 0;
 	case CIPSO_V4_MAP_TRANS:
-		if (doi_def->map.std->lvl.cipso[level] < CIPSO_V4_INV_LVL)
+		if ((level < doi_def->map.std->lvl.cipso_size) &&
+		    (doi_def->map.std->lvl.cipso[level] < CIPSO_V4_INV_LVL))
 			return 0;
 		break;
 	}
diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c
index ea7c67050792..ee3e5b6471a6 100644
--- a/net/netlabel/netlabel_kapi.c
+++ b/net/netlabel/netlabel_kapi.c
@@ -903,7 +903,8 @@ int netlbl_bitmap_walk(const unsigned char *bitmap, u32 bitmap_len,
 		    (state == 0 && (byte & bitmask) == 0))
 			return bit_spot;
 
-		bit_spot++;
+		if (++bit_spot >= bitmap_len)
+			return -1;
 		bitmask >>= 1;
 		if (bitmask == 0) {
 			byte = bitmap[++byte_offset];
-- 
2.20.1


From 0d06b7140eb457cb6061920980735f63ab66834b Mon Sep 17 00:00:00 2001
From: Sheng Lan <lansheng@huawei.com>
Date: Thu, 28 Feb 2019 18:47:58 +0800
Subject: [PATCH 21/42] net: netem: fix skb length BUG_ON in __skb_to_sgvec

[ Upstream commit 5845f706388a4cde0f6b80f9e5d33527e942b7d9 ]

It can be reproduced by following steps:
1. virtio_net NIC is configured with gso/tso on
2. configure nginx as http server with an index file bigger than 1M bytes
3. use tc netem to produce duplicate packets and delay:
   tc qdisc add dev eth0 root netem delay 100ms 10ms 30% duplicate 90%
4. continually curl the nginx http server to get index file on client
5. BUG_ON is seen quickly

[10258690.371129] kernel BUG at net/core/skbuff.c:4028!
[10258690.371748] invalid opcode: 0000 [#1] SMP PTI
[10258690.372094] CPU: 5 PID: 0 Comm: swapper/5 Tainted: G        W         5.0.0-rc6 #2
[10258690.372094] RSP: 0018:ffffa05797b43da0 EFLAGS: 00010202
[10258690.372094] RBP: 00000000000005ea R08: 0000000000000000 R09: 00000000000005ea
[10258690.372094] R10: ffffa0579334d800 R11: 00000000000002c0 R12: 0000000000000002
[10258690.372094] R13: 0000000000000000 R14: ffffa05793122900 R15: ffffa0578f7cb028
[10258690.372094] FS:  0000000000000000(0000) GS:ffffa05797b40000(0000) knlGS:0000000000000000
[10258690.372094] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[10258690.372094] CR2: 00007f1a6dc00868 CR3: 000000001000e000 CR4: 00000000000006e0
[10258690.372094] Call Trace:
[10258690.372094]  <IRQ>
[10258690.372094]  skb_to_sgvec+0x11/0x40
[10258690.372094]  start_xmit+0x38c/0x520 [virtio_net]
[10258690.372094]  dev_hard_start_xmit+0x9b/0x200
[10258690.372094]  sch_direct_xmit+0xff/0x260
[10258690.372094]  __qdisc_run+0x15e/0x4e0
[10258690.372094]  net_tx_action+0x137/0x210
[10258690.372094]  __do_softirq+0xd6/0x2a9
[10258690.372094]  irq_exit+0xde/0xf0
[10258690.372094]  smp_apic_timer_interrupt+0x74/0x140
[10258690.372094]  apic_timer_interrupt+0xf/0x20
[10258690.372094]  </IRQ>

In __skb_to_sgvec(), the skb->len is not equal to the sum of the skb's
linear data size and nonlinear data size, thus BUG_ON triggered.
Because the skb is cloned and a part of nonlinear data is split off.

Duplicate packet is cloned in netem_enqueue() and may be delayed
some time in qdisc. When qdisc len reached the limit and returns
NET_XMIT_DROP, the skb will be retransmit later in write queue.
the skb will be fragmented by tso_fragment(), the limit size
that depends on cwnd and mss decrease, the skb's nonlinear
data will be split off. The length of the skb cloned by netem
will not be updated. When we use virtio_net NIC and invoke skb_to_sgvec(),
the BUG_ON trigger.

To fix it, netem returns NET_XMIT_SUCCESS to upper stack
when it clones a duplicate packet.

Fixes: 35d889d1 ("sch_netem: fix skb leak in netem_enqueue()")
Signed-off-by: Sheng Lan <lansheng@huawei.com>
Reported-by: Qin Ji <jiqin.ji@huawei.com>
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_netem.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 22cd46a60057..ffb9e21ffc5c 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -430,6 +430,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	int nb = 0;
 	int count = 1;
 	int rc = NET_XMIT_SUCCESS;
+	int rc_drop = NET_XMIT_DROP;
 
 	/* Do not fool qdisc_drop_all() */
 	skb->prev = NULL;
@@ -469,6 +470,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		q->duplicate = 0;
 		rootq->enqueue(skb2, rootq, to_free);
 		q->duplicate = dupsave;
+		rc_drop = NET_XMIT_SUCCESS;
 	}
 
 	/*
@@ -481,7 +483,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		if (skb_is_gso(skb)) {
 			segs = netem_segment(skb, sch, to_free);
 			if (!segs)
-				return NET_XMIT_DROP;
+				return rc_drop;
 		} else {
 			segs = skb;
 		}
@@ -504,8 +506,10 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 			1<<(prandom_u32() % 8);
 	}
 
-	if (unlikely(sch->q.qlen >= sch->limit))
-		return qdisc_drop_all(skb, sch, to_free);
+	if (unlikely(sch->q.qlen >= sch->limit)) {
+		qdisc_drop_all(skb, sch, to_free);
+		return rc_drop;
+	}
 
 	qdisc_qstats_backlog_inc(sch, skb);
 
-- 
2.20.1


From f846ca79db60344af2337d05538dd25d201534cf Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Fri, 22 Feb 2019 15:37:58 +0800
Subject: [PATCH 22/42] net: nfc: Fix NULL dereference on nfc_llcp_build_tlv
 fails

[ Upstream commit 58bdd544e2933a21a51eecf17c3f5f94038261b5 ]

KASAN report this:

BUG: KASAN: null-ptr-deref in nfc_llcp_build_gb+0x37f/0x540 [nfc]
Read of size 3 at addr 0000000000000000 by task syz-executor.0/5401

CPU: 0 PID: 5401 Comm: syz-executor.0 Not tainted 5.0.0-rc7+ #45
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0xfa/0x1ce lib/dump_stack.c:113
 kasan_report+0x171/0x18d mm/kasan/report.c:321
 memcpy+0x1f/0x50 mm/kasan/common.c:130
 nfc_llcp_build_gb+0x37f/0x540 [nfc]
 nfc_llcp_register_device+0x6eb/0xb50 [nfc]
 nfc_register_device+0x50/0x1d0 [nfc]
 nfcsim_device_new+0x394/0x67d [nfcsim]
 ? 0xffffffffc1080000
 nfcsim_init+0x6b/0x1000 [nfcsim]
 do_one_initcall+0xfa/0x5ca init/main.c:887
 do_init_module+0x204/0x5f6 kernel/module.c:3460
 load_module+0x66b2/0x8570 kernel/module.c:3808
 __do_sys_finit_module+0x238/0x2a0 kernel/module.c:3902
 do_syscall_64+0x147/0x600 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x462e99
Code: f7 d8 64 89 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007f9cb79dcc58 EFLAGS: 00000246 ORIG_RAX: 0000000000000139
RAX: ffffffffffffffda RBX: 000000000073bf00 RCX: 0000000000462e99
RDX: 0000000000000000 RSI: 0000000020000280 RDI: 0000000000000003
RBP: 00007f9cb79dcc70 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00007f9cb79dd6bc
R13: 00000000004bcefb R14: 00000000006f7030 R15: 0000000000000004

nfc_llcp_build_tlv will return NULL on fails, caller should check it,
otherwise will trigger a NULL dereference.

Reported-by: Hulk Robot <hulkci@huawei.com>
Fixes: eda21f16a5ed ("NFC: Set MIU and RW values from CONNECT and CC LLCP frames")
Fixes: d646960f7986 ("NFC: Initial LLCP support")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/nfc/llcp_commands.c | 20 ++++++++++++++++++++
 net/nfc/llcp_core.c     | 24 ++++++++++++++++++++----
 2 files changed, 40 insertions(+), 4 deletions(-)

diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c
index 6a196e438b6c..d1fc019e932e 100644
--- a/net/nfc/llcp_commands.c
+++ b/net/nfc/llcp_commands.c
@@ -419,6 +419,10 @@ int nfc_llcp_send_connect(struct nfc_llcp_sock *sock)
 						      sock->service_name,
 						      sock->service_name_len,
 						      &service_name_tlv_length);
+		if (!service_name_tlv) {
+			err = -ENOMEM;
+			goto error_tlv;
+		}
 		size += service_name_tlv_length;
 	}
 
@@ -429,9 +433,17 @@ int nfc_llcp_send_connect(struct nfc_llcp_sock *sock)
 
 	miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&miux, 0,
 				      &miux_tlv_length);
+	if (!miux_tlv) {
+		err = -ENOMEM;
+		goto error_tlv;
+	}
 	size += miux_tlv_length;
 
 	rw_tlv = nfc_llcp_build_tlv(LLCP_TLV_RW, &rw, 0, &rw_tlv_length);
+	if (!rw_tlv) {
+		err = -ENOMEM;
+		goto error_tlv;
+	}
 	size += rw_tlv_length;
 
 	pr_debug("SKB size %d SN length %zu\n", size, sock->service_name_len);
@@ -484,9 +496,17 @@ int nfc_llcp_send_cc(struct nfc_llcp_sock *sock)
 
 	miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&miux, 0,
 				      &miux_tlv_length);
+	if (!miux_tlv) {
+		err = -ENOMEM;
+		goto error_tlv;
+	}
 	size += miux_tlv_length;
 
 	rw_tlv = nfc_llcp_build_tlv(LLCP_TLV_RW, &rw, 0, &rw_tlv_length);
+	if (!rw_tlv) {
+		err = -ENOMEM;
+		goto error_tlv;
+	}
 	size += rw_tlv_length;
 
 	skb = llcp_allocate_pdu(sock, LLCP_PDU_CC, size);
diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c
index ef4026a23e80..4fa015208aab 100644
--- a/net/nfc/llcp_core.c
+++ b/net/nfc/llcp_core.c
@@ -532,10 +532,10 @@ static u8 nfc_llcp_reserve_sdp_ssap(struct nfc_llcp_local *local)
 
 static int nfc_llcp_build_gb(struct nfc_llcp_local *local)
 {
-	u8 *gb_cur, *version_tlv, version, version_length;
-	u8 *lto_tlv, lto_length;
-	u8 *wks_tlv, wks_length;
-	u8 *miux_tlv, miux_length;
+	u8 *gb_cur, version, version_length;
+	u8 lto_length, wks_length, miux_length;
+	u8 *version_tlv = NULL, *lto_tlv = NULL,
+	   *wks_tlv = NULL, *miux_tlv = NULL;
 	__be16 wks = cpu_to_be16(local->local_wks);
 	u8 gb_len = 0;
 	int ret = 0;
@@ -543,17 +543,33 @@ static int nfc_llcp_build_gb(struct nfc_llcp_local *local)
 	version = LLCP_VERSION_11;
 	version_tlv = nfc_llcp_build_tlv(LLCP_TLV_VERSION, &version,
 					 1, &version_length);
+	if (!version_tlv) {
+		ret = -ENOMEM;
+		goto out;
+	}
 	gb_len += version_length;
 
 	lto_tlv = nfc_llcp_build_tlv(LLCP_TLV_LTO, &local->lto, 1, &lto_length);
+	if (!lto_tlv) {
+		ret = -ENOMEM;
+		goto out;
+	}
 	gb_len += lto_length;
 
 	pr_debug("Local wks 0x%lx\n", local->local_wks);
 	wks_tlv = nfc_llcp_build_tlv(LLCP_TLV_WKS, (u8 *)&wks, 2, &wks_length);
+	if (!wks_tlv) {
+		ret = -ENOMEM;
+		goto out;
+	}
 	gb_len += wks_length;
 
 	miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&local->miux, 0,
 				      &miux_length);
+	if (!miux_tlv) {
+		ret = -ENOMEM;
+		goto out;
+	}
 	gb_len += miux_length;
 
 	gb_len += ARRAY_SIZE(llcp_magic);
-- 
2.20.1


From a28c9372e22f07979afa30cd4a23fa1eb7c7c04b Mon Sep 17 00:00:00 2001
From: Rajasingh Thavamani <T.Rajasingh@landisgyr.com>
Date: Wed, 27 Feb 2019 17:43:19 +0530
Subject: [PATCH 23/42] net: phy: Micrel KSZ8061: link failure after cable
 connect

[ Upstream commit 232ba3a51cc224b339c7114888ed7f0d4d95695e ]

With Micrel KSZ8061 PHY, the link may occasionally not come up after
Ethernet cable connect. The vendor's (Microchip, former Micrel) errata
sheet 80000688A.pdf descripes the problem and possible workarounds in
detail, see below.
The batch implements workaround 1, which permanently fixes the issue.

DESCRIPTION
Link-up may not occur properly when the Ethernet cable is initially
connected. This issue occurs more commonly when the cable is connected
slowly, but it may occur any time a cable is connected. This issue occurs
in the auto-negotiation circuit, and will not occur if auto-negotiation
is disabled (which requires that the two link partners be set to the
same speed and duplex).

END USER IMPLICATIONS
When this issue occurs, link is not established. Subsequent cable
plug/unplaug cycle will not correct the issue.

WORk AROUND
There are four approaches to work around this issue:
1. This issue can be prevented by setting bit 15 in MMD device address 1,
   register 2, prior to connecting the cable or prior to setting the
   Restart Auto-negotiation bit in register 0h. The MMD registers are
   accessed via the indirect access registers Dh and Eh, or via the Micrel
   EthUtil utility as shown here:
   . if using the EthUtil utility (usually with a Micrel KSZ8061
     Evaluation Board), type the following commands:
     > address 1
     > mmd 1
     > iw 2 b61a
   . Alternatively, write the following registers to write to the
     indirect MMD register:
     Write register Dh, data 0001h
     Write register Eh, data 0002h
     Write register Dh, data 4001h
     Write register Eh, data B61Ah
2. The issue can be avoided by disabling auto-negotiation in the KSZ8061,
   either by the strapping option, or by clearing bit 12 in register 0h.
   Care must be taken to ensure that the KSZ8061 and the link partner
   will link with the same speed and duplex. Note that the KSZ8061
   defaults to full-duplex when auto-negotiation is off, but other
   devices may default to half-duplex in the event of failed
   auto-negotiation.
3. The issue can be avoided by connecting the cable prior to powering-up
   or resetting the KSZ8061, and leaving it plugged in thereafter.
4. If the above measures are not taken and the problem occurs, link can
   be recovered by setting the Restart Auto-Negotiation bit in
   register 0h, or by resetting or power cycling the device. Reset may
   be either hardware reset or software reset (register 0h, bit 15).

PLAN
This errata will not be corrected in the future revision.

Fixes: 7ab59dc15e2f ("drivers/net/phy/micrel_phy: Add support for new PHYs")
Signed-off-by: Alexander Onnasch <alexander.onnasch@landisgyr.com>
Signed-off-by: Rajasingh Thavamani <T.Rajasingh@landisgyr.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/micrel.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 22dfbd4c6aaf..20152eb008d5 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -339,6 +339,17 @@ static int ksz8041_config_aneg(struct phy_device *phydev)
 	return genphy_config_aneg(phydev);
 }
 
+static int ksz8061_config_init(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = phy_write_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_DEVID1, 0xB61A);
+	if (ret)
+		return ret;
+
+	return kszphy_config_init(phydev);
+}
+
 static int ksz9021_load_values_from_of(struct phy_device *phydev,
 				       const struct device_node *of_node,
 				       u16 reg,
@@ -920,7 +931,7 @@ static struct phy_driver ksphy_driver[] = {
 	.features	= PHY_BASIC_FEATURES,
 	.flags		= PHY_HAS_INTERRUPT,
 	.driver_data	= &ks8737_type,
-	.config_init	= kszphy_config_init,
+	.config_init	= ksz8061_config_init,
 	.ack_interrupt	= kszphy_ack_interrupt,
 	.config_intr	= kszphy_config_intr,
 	.suspend	= genphy_suspend,
-- 
2.20.1


From 82c5353dedea8fcc1bd315e582185c7ceea9e648 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Tue, 26 Feb 2019 19:29:22 +0100
Subject: [PATCH 24/42] net: phy: phylink: fix uninitialized variable in
 phylink_get_mac_state

[ Upstream commit d25ed413d5e51644e18f66e34eec049f17a7abcb ]

When debugging an issue I found implausible values in state->pause.
Reason in that state->pause isn't initialized and later only single
bits are changed. Also the struct itself isn't initialized in
phylink_resolve(). So better initialize state->pause and other
not yet initialized fields.

v2:
- use right function name in subject
v3:
- initialize additional fields

Fixes: 9525ae83959b ("phylink: add phylink infrastructure")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phylink.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index b60c82065fd1..93365a5c2557 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -321,6 +321,10 @@ static int phylink_get_mac_state(struct phylink *pl, struct phylink_link_state *
 	linkmode_zero(state->lp_advertising);
 	state->interface = pl->link_config.interface;
 	state->an_enabled = pl->link_config.an_enabled;
+	state->speed = SPEED_UNKNOWN;
+	state->duplex = DUPLEX_UNKNOWN;
+	state->pause = MLO_PAUSE_NONE;
+	state->an_complete = 0;
 	state->link = 1;
 
 	return pl->ops->mac_link_state(ndev, state);
-- 
2.20.1


From d4a9b2410732a99e93ae33770d0cd4630d0fdd6a Mon Sep 17 00:00:00 2001
From: Mao Wenan <maowenan@huawei.com>
Date: Fri, 1 Mar 2019 23:06:40 +0800
Subject: [PATCH 25/42] net: sit: fix memory leak in sit_init_net()

[ Upstream commit 07f12b26e21ab359261bf75cfcb424fdc7daeb6d ]

If register_netdev() is failed to register sitn->fb_tunnel_dev,
it will go to err_reg_dev and forget to free netdev(sitn->fb_tunnel_dev).

BUG: memory leak
unreferenced object 0xffff888378daad00 (size 512):
  comm "syz-executor.1", pid 4006, jiffies 4295121142 (age 16.115s)
  hex dump (first 32 bytes):
    00 e6 ed c0 83 88 ff ff 00 00 00 00 00 00 00 00  ................
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
backtrace:
    [<00000000d6dcb63e>] kvmalloc include/linux/mm.h:577 [inline]
    [<00000000d6dcb63e>] kvzalloc include/linux/mm.h:585 [inline]
    [<00000000d6dcb63e>] netif_alloc_netdev_queues net/core/dev.c:8380 [inline]
    [<00000000d6dcb63e>] alloc_netdev_mqs+0x600/0xcc0 net/core/dev.c:8970
    [<00000000867e172f>] sit_init_net+0x295/0xa40 net/ipv6/sit.c:1848
    [<00000000871019fa>] ops_init+0xad/0x3e0 net/core/net_namespace.c:129
    [<00000000319507f6>] setup_net+0x2ba/0x690 net/core/net_namespace.c:314
    [<0000000087db4f96>] copy_net_ns+0x1dc/0x330 net/core/net_namespace.c:437
    [<0000000057efc651>] create_new_namespaces+0x382/0x730 kernel/nsproxy.c:107
    [<00000000676f83de>] copy_namespaces+0x2ed/0x3d0 kernel/nsproxy.c:165
    [<0000000030b74bac>] copy_process.part.27+0x231e/0x6db0 kernel/fork.c:1919
    [<00000000fff78746>] copy_process kernel/fork.c:1713 [inline]
    [<00000000fff78746>] _do_fork+0x1bc/0xe90 kernel/fork.c:2224
    [<000000001c2e0d1c>] do_syscall_64+0xc8/0x580 arch/x86/entry/common.c:290
    [<00000000ec48bd44>] entry_SYSCALL_64_after_hwframe+0x49/0xbe
    [<0000000039acff8a>] 0xffffffffffffffff

Signed-off-by: Mao Wenan <maowenan@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index e8a1dabef803..09e440e8dfae 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1873,6 +1873,7 @@ static int __net_init sit_init_net(struct net *net)
 
 err_reg_dev:
 	ipip6_dev_free(sitn->fb_tunnel_dev);
+	free_netdev(sitn->fb_tunnel_dev);
 err_alloc_dev:
 	return err;
 }
-- 
2.20.1


From 7b5c652de5bed080522be107544d113b909a9374 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Thu, 21 Feb 2019 14:13:56 -0800
Subject: [PATCH 26/42] net: socket: set sock->sk to NULL after calling
 proto_ops::release()

[ Upstream commit ff7b11aa481f682e0e9711abfeb7d03f5cd612bf ]

Commit 9060cb719e61 ("net: crypto set sk to NULL when af_alg_release.")
fixed a use-after-free in sockfs_setattr() when an AF_ALG socket is
closed concurrently with fchownat().  However, it ignored that many
other proto_ops::release() methods don't set sock->sk to NULL and
therefore allow the same use-after-free:

    - base_sock_release
    - bnep_sock_release
    - cmtp_sock_release
    - data_sock_release
    - dn_release
    - hci_sock_release
    - hidp_sock_release
    - iucv_sock_release
    - l2cap_sock_release
    - llcp_sock_release
    - llc_ui_release
    - rawsock_release
    - rfcomm_sock_release
    - sco_sock_release
    - svc_release
    - vcc_release
    - x25_release

Rather than fixing all these and relying on every socket type to get
this right forever, just make __sock_release() set sock->sk to NULL
itself after calling proto_ops::release().

Reproducer that produces the KASAN splat when any of these socket types
are configured into the kernel:

    #include <pthread.h>
    #include <stdlib.h>
    #include <sys/socket.h>
    #include <unistd.h>

    pthread_t t;
    volatile int fd;

    void *close_thread(void *arg)
    {
        for (;;) {
            usleep(rand() % 100);
            close(fd);
        }
    }

    int main()
    {
        pthread_create(&t, NULL, close_thread, NULL);
        for (;;) {
            fd = socket(rand() % 50, rand() % 11, 0);
            fchownat(fd, "", 1000, 1000, 0x1000);
            close(fd);
        }
    }

Fixes: 86741ec25462 ("net: core: Add a UID field to struct sock.")
Signed-off-by: Eric Biggers <ebiggers@google.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/socket.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/socket.c b/net/socket.c
index 93a45f15ee40..d4ac431b78b2 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -577,6 +577,7 @@ static void __sock_release(struct socket *sock, struct inode *inode)
 		if (inode)
 			inode_lock(inode);
 		sock->ops->release(sock);
+		sock->sk = NULL;
 		if (inode)
 			inode_unlock(inode);
 		sock->ops = NULL;
-- 
2.20.1


From 549c817dc32388c33d5b6e51af4b94a77fdb376d Mon Sep 17 00:00:00 2001
From: Tung Nguyen <tung.q.nguyen@dektech.com.au>
Date: Mon, 25 Feb 2019 10:57:20 +0700
Subject: [PATCH 27/42] tipc: fix race condition causing hung sendto

[ Upstream commit bfd07f3dd4f111b884d7922b37eb239280f83d8c ]

When sending multicast messages via blocking socket,
if sending link is congested (tsk->cong_link_cnt is set to 1),
the sending thread will be put into sleeping state. However,
tipc_sk_filter_rcv() is called under socket spin lock but
tipc_wait_for_cond() is not. So, there is no guarantee that
the setting of tsk->cong_link_cnt to 0 in tipc_sk_proto_rcv() in
CPU-1 will be perceived by CPU-0. If that is the case, the sending
thread in CPU-0 after being waken up, will continue to see
tsk->cong_link_cnt as 1 and put the sending thread into sleeping
state again. The sending thread will sleep forever.

CPU-0                                | CPU-1
tipc_wait_for_cond()                 |
{                                    |
 // condition_ = !tsk->cong_link_cnt |
 while ((rc_ = !(condition_))) {     |
  ...                                |
  release_sock(sk_);                 |
  wait_woken();                      |
                                     | if (!sock_owned_by_user(sk))
                                     |  tipc_sk_filter_rcv()
                                     |  {
                                     |   ...
                                     |   tipc_sk_proto_rcv()
                                     |   {
                                     |    ...
                                     |    tsk->cong_link_cnt--;
                                     |    ...
                                     |    sk->sk_write_space(sk);
                                     |    ...
                                     |   }
                                     |   ...
                                     |  }
  sched_annotate_sleep();            |
  lock_sock(sk_);                    |
  remove_wait_queue();               |
 }                                   |
}                                    |

This commit fixes it by adding memory barrier to tipc_sk_proto_rcv()
and tipc_wait_for_cond().

Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Tung Nguyen <tung.q.nguyen@dektech.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/socket.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 615de0910a07..f08d8e4923f2 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -376,11 +376,13 @@ static int tipc_sk_sock_err(struct socket *sock, long *timeout)
 
 #define tipc_wait_for_cond(sock_, timeo_, condition_)			       \
 ({                                                                             \
+	DEFINE_WAIT_FUNC(wait_, woken_wake_function);                          \
 	struct sock *sk_;						       \
 	int rc_;							       \
 									       \
 	while ((rc_ = !(condition_))) {					       \
-		DEFINE_WAIT_FUNC(wait_, woken_wake_function);	               \
+		/* coupled with smp_wmb() in tipc_sk_proto_rcv() */            \
+		smp_rmb();                                                     \
 		sk_ = (sock_)->sk;					       \
 		rc_ = tipc_sk_sock_err((sock_), timeo_);		       \
 		if (rc_)						       \
@@ -1968,6 +1970,8 @@ static void tipc_sk_proto_rcv(struct sock *sk,
 		return;
 	case SOCK_WAKEUP:
 		tipc_dest_del(&tsk->cong_links, msg_orignode(hdr), 0);
+		/* coupled with smp_rmb() in tipc_wait_for_cond() */
+		smp_wmb();
 		tsk->cong_link_cnt--;
 		wakeup = true;
 		break;
-- 
2.20.1


From 01904978bc20c6471ce56b783d83b068b9cfd8ae Mon Sep 17 00:00:00 2001
From: Timur Celik <mail@timurcelik.de>
Date: Sat, 23 Feb 2019 12:53:13 +0100
Subject: [PATCH 28/42] tun: fix blocking read

[ Upstream commit 71828b2240692cec0e68b8d867bc00e1745e7fae ]

This patch moves setting of the current state into the loop. Otherwise
the task may end up in a busy wait loop if none of the break conditions
are met.

Signed-off-by: Timur Celik <mail@timurcelik.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 1e6f0da1fa8e..05728e583d90 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -2147,9 +2147,9 @@ static void *tun_ring_recv(struct tun_file *tfile, int noblock, int *err)
 	}
 
 	add_wait_queue(&tfile->wq.wait, &wait);
-	current->state = TASK_INTERRUPTIBLE;
 
 	while (1) {
+		set_current_state(TASK_INTERRUPTIBLE);
 		ptr = ptr_ring_consume(&tfile->tx_ring);
 		if (ptr)
 			break;
@@ -2165,7 +2165,7 @@ static void *tun_ring_recv(struct tun_file *tfile, int noblock, int *err)
 		schedule();
 	}
 
-	current->state = TASK_RUNNING;
+	set_current_state(TASK_RUNNING);
 	remove_wait_queue(&tfile->wq.wait, &wait);
 
 out:
-- 
2.20.1


From 92dd5c559cdf51d56d23bed8ea137c74863b4ab7 Mon Sep 17 00:00:00 2001
From: Igor Druzhinin <igor.druzhinin@citrix.com>
Date: Thu, 28 Feb 2019 14:11:26 +0000
Subject: [PATCH 29/42] xen-netback: don't populate the hash cache on XenBus
 disconnect

[ Upstream commit a2288d4e355992d369c50c45d017a85f6061ff71 ]

Occasionally, during the disconnection procedure on XenBus which
includes hash cache deinitialization there might be some packets
still in-flight on other processors. Handling of these packets includes
hashing and hash cache population that finally results in hash cache
data structure corruption.

In order to avoid this we prevent hashing of those packets if there
are no queues initialized. In that case RCU protection of queues guards
the hash cache as well.

Signed-off-by: Igor Druzhinin <igor.druzhinin@citrix.com>
Reviewed-by: Paul Durrant <paul.durrant@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netback/hash.c      | 2 ++
 drivers/net/xen-netback/interface.c | 7 +++++++
 2 files changed, 9 insertions(+)

diff --git a/drivers/net/xen-netback/hash.c b/drivers/net/xen-netback/hash.c
index 0ccb021f1e78..10d580c3dea3 100644
--- a/drivers/net/xen-netback/hash.c
+++ b/drivers/net/xen-netback/hash.c
@@ -454,6 +454,8 @@ void xenvif_init_hash(struct xenvif *vif)
 	if (xenvif_hash_cache_size == 0)
 		return;
 
+	BUG_ON(vif->hash.cache.count);
+
 	spin_lock_init(&vif->hash.cache.lock);
 	INIT_LIST_HEAD(&vif->hash.cache.list);
 }
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index 182d6770f102..6da12518e693 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -153,6 +153,13 @@ static u16 xenvif_select_queue(struct net_device *dev, struct sk_buff *skb,
 {
 	struct xenvif *vif = netdev_priv(dev);
 	unsigned int size = vif->hash.size;
+	unsigned int num_queues;
+
+	/* If queues are not set up internally - always return 0
+	 * as the packet going to be dropped anyway */
+	num_queues = READ_ONCE(vif->num_queues);
+	if (num_queues < 1)
+		return 0;
 
 	if (vif->hash.alg == XEN_NETIF_CTRL_HASH_ALGORITHM_NONE)
 		return fallback(dev, skb, NULL) % dev->real_num_tx_queues;
-- 
2.20.1


From 59e044e9c9e5ddfce7c5047971f61095b212acf5 Mon Sep 17 00:00:00 2001
From: Igor Druzhinin <igor.druzhinin@citrix.com>
Date: Thu, 28 Feb 2019 12:48:03 +0000
Subject: [PATCH 30/42] xen-netback: fix occasional leak of grant ref mappings
 under memory pressure

[ Upstream commit 99e87f56b48f490fb16b6e0f74691c1e664dea95 ]

Zero-copy callback flag is not yet set on frag list skb at the moment
xenvif_handle_frag_list() returns -ENOMEM. This eventually results in
leaking grant ref mappings since xenvif_zerocopy_callback() is never
called for these fragments. Those eventually build up and cause Xen
to kill Dom0 as the slots get reused for new mappings:

"d0v0 Attempt to implicitly unmap a granted PTE c010000329fce005"

That behavior is observed under certain workloads where sudden spikes
of page cache writes coexist with active atomic skb allocations from
network traffic. Additionally, rework the logic to deal with frag_list
deallocation in a single place.

Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Signed-off-by: Igor Druzhinin <igor.druzhinin@citrix.com>
Acked-by: Wei Liu <wei.liu2@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netback/netback.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 80aae3a32c2a..f09948b009dd 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -1072,11 +1072,6 @@ static int xenvif_handle_frag_list(struct xenvif_queue *queue, struct sk_buff *s
 		skb_frag_size_set(&frags[i], len);
 	}
 
-	/* Copied all the bits from the frag list -- free it. */
-	skb_frag_list_init(skb);
-	xenvif_skb_zerocopy_prepare(queue, nskb);
-	kfree_skb(nskb);
-
 	/* Release all the original (foreign) frags. */
 	for (f = 0; f < skb_shinfo(skb)->nr_frags; f++)
 		skb_frag_unref(skb, f);
@@ -1145,6 +1140,8 @@ static int xenvif_tx_submit(struct xenvif_queue *queue)
 		xenvif_fill_frags(queue, skb);
 
 		if (unlikely(skb_has_frag_list(skb))) {
+			struct sk_buff *nskb = skb_shinfo(skb)->frag_list;
+			xenvif_skb_zerocopy_prepare(queue, nskb);
 			if (xenvif_handle_frag_list(queue, skb)) {
 				if (net_ratelimit())
 					netdev_err(queue->vif->dev,
@@ -1153,6 +1150,9 @@ static int xenvif_tx_submit(struct xenvif_queue *queue)
 				kfree_skb(skb);
 				continue;
 			}
+			/* Copied all the bits from the frag list -- free it. */
+			skb_frag_list_init(skb);
+			kfree_skb(nskb);
 		}
 
 		skb->dev      = queue->vif->dev;
-- 
2.20.1


From 9f34dbd388049372b4145666e66b9a0cafdf66b1 Mon Sep 17 00:00:00 2001
From: Timur Celik <mail@timurcelik.de>
Date: Mon, 25 Feb 2019 21:13:13 +0100
Subject: [PATCH 31/42] tun: remove unnecessary memory barrier

[ Upstream commit ecef67cb10db7b83b3b71c61dbb29aa070ab0112 ]

Replace set_current_state with __set_current_state since no memory
barrier is needed at this point.

Signed-off-by: Timur Celik <mail@timurcelik.de>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 05728e583d90..efc08dad3a1b 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -2165,7 +2165,7 @@ static void *tun_ring_recv(struct tun_file *tfile, int noblock, int *err)
 		schedule();
 	}
 
-	set_current_state(TASK_RUNNING);
+	__set_current_state(TASK_RUNNING);
 	remove_wait_queue(&tfile->wq.wait, &wait);
 
 out:
-- 
2.20.1


From 231346d9bfbe1912ab0c4aecc3b738d4a2496678 Mon Sep 17 00:00:00 2001
From: Nazarov Sergey <s-nazarov@yandex.ru>
Date: Mon, 25 Feb 2019 19:24:15 +0300
Subject: [PATCH 32/42] net: Add __icmp_send helper.

[ Upstream commit 9ef6b42ad6fd7929dd1b6092cb02014e382c6a91 ]

Add __icmp_send function having ip_options struct parameter

Signed-off-by: Sergey Nazarov <s-nazarov@yandex.ru>
Reviewed-by: Paul Moore <paul@paul-moore.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/icmp.h | 9 ++++++++-
 net/ipv4/icmp.c    | 7 ++++---
 2 files changed, 12 insertions(+), 4 deletions(-)

diff --git a/include/net/icmp.h b/include/net/icmp.h
index 3ef2743a8eec..8665bf24e3b7 100644
--- a/include/net/icmp.h
+++ b/include/net/icmp.h
@@ -22,6 +22,7 @@
 
 #include <net/inet_sock.h>
 #include <net/snmp.h>
+#include <net/ip.h>
 
 struct icmp_err {
   int		errno;
@@ -39,7 +40,13 @@ struct net_proto_family;
 struct sk_buff;
 struct net;
 
-void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info);
+void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
+		 const struct ip_options *opt);
+static inline void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
+{
+	__icmp_send(skb_in, type, code, info, &IPCB(skb_in)->opt);
+}
+
 int icmp_rcv(struct sk_buff *skb);
 void icmp_err(struct sk_buff *skb, u32 info);
 int icmp_init(void);
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index d832beed6e3a..c897fec9f903 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -570,7 +570,8 @@ static struct rtable *icmp_route_lookup(struct net *net,
  *			MUST reply to only the first fragment.
  */
 
-void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
+void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
+		 const struct ip_options *opt)
 {
 	struct iphdr *iph;
 	int room;
@@ -691,7 +692,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 					  iph->tos;
 	mark = IP4_REPLY_MARK(net, skb_in->mark);
 
-	if (ip_options_echo(net, &icmp_param.replyopts.opt.opt, skb_in))
+	if (__ip_options_echo(net, &icmp_param.replyopts.opt.opt, skb_in, opt))
 		goto out_unlock;
 
 
@@ -742,7 +743,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 	local_bh_enable();
 out:;
 }
-EXPORT_SYMBOL(icmp_send);
+EXPORT_SYMBOL(__icmp_send);
 
 
 static void icmp_socket_deliver(struct sk_buff *skb, u32 info)
-- 
2.20.1


From 994093f8a89f4de4c3019388a927e7b36c56606f Mon Sep 17 00:00:00 2001
From: Nazarov Sergey <s-nazarov@yandex.ru>
Date: Mon, 25 Feb 2019 19:27:15 +0300
Subject: [PATCH 33/42] net: avoid use IPCB in cipso_v4_error

[ Upstream commit 3da1ed7ac398f34fff1694017a07054d69c5f5c5 ]

Extract IP options in cipso_v4_error and use __icmp_send.

Signed-off-by: Sergey Nazarov <s-nazarov@yandex.ru>
Acked-by: Paul Moore <paul@paul-moore.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h      |  2 ++
 net/ipv4/cipso_ipv4.c | 17 +++++++++++++++--
 net/ipv4/ip_options.c | 22 +++++++++++++++++-----
 3 files changed, 34 insertions(+), 7 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index 30c657b128ce..b2b7cdb3f6fd 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -665,6 +665,8 @@ static inline int ip_options_echo(struct net *net, struct ip_options *dopt,
 }
 
 void ip_options_fragment(struct sk_buff *skb);
+int __ip_options_compile(struct net *net, struct ip_options *opt,
+			 struct sk_buff *skb, __be32 *info);
 int ip_options_compile(struct net *net, struct ip_options *opt,
 		       struct sk_buff *skb);
 int ip_options_get(struct net *net, struct ip_options_rcu **optp,
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index f4b83de2263e..f0165c5f376b 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -1736,13 +1736,26 @@ int cipso_v4_validate(const struct sk_buff *skb, unsigned char **option)
  */
 void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway)
 {
+	unsigned char optbuf[sizeof(struct ip_options) + 40];
+	struct ip_options *opt = (struct ip_options *)optbuf;
+
 	if (ip_hdr(skb)->protocol == IPPROTO_ICMP || error != -EACCES)
 		return;
 
+	/*
+	 * We might be called above the IP layer,
+	 * so we can not use icmp_send and IPCB here.
+	 */
+
+	memset(opt, 0, sizeof(struct ip_options));
+	opt->optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr);
+	if (__ip_options_compile(dev_net(skb->dev), opt, skb, NULL))
+		return;
+
 	if (gateway)
-		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_NET_ANO, 0);
+		__icmp_send(skb, ICMP_DEST_UNREACH, ICMP_NET_ANO, 0, opt);
 	else
-		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_ANO, 0);
+		__icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_ANO, 0, opt);
 }
 
 /**
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index ed194d46c00e..32a35043c9f5 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -251,8 +251,9 @@ static void spec_dst_fill(__be32 *spec_dst, struct sk_buff *skb)
  * If opt == NULL, then skb->data should point to IP header.
  */
 
-int ip_options_compile(struct net *net,
-		       struct ip_options *opt, struct sk_buff *skb)
+int __ip_options_compile(struct net *net,
+			 struct ip_options *opt, struct sk_buff *skb,
+			 __be32 *info)
 {
 	__be32 spec_dst = htonl(INADDR_ANY);
 	unsigned char *pp_ptr = NULL;
@@ -468,11 +469,22 @@ int ip_options_compile(struct net *net,
 		return 0;
 
 error:
-	if (skb) {
-		icmp_send(skb, ICMP_PARAMETERPROB, 0, htonl((pp_ptr-iph)<<24));
-	}
+	if (info)
+		*info = htonl((pp_ptr-iph)<<24);
 	return -EINVAL;
 }
+
+int ip_options_compile(struct net *net,
+		       struct ip_options *opt, struct sk_buff *skb)
+{
+	int ret;
+	__be32 info;
+
+	ret = __ip_options_compile(net, opt, skb, &info);
+	if (ret != 0 && skb)
+		icmp_send(skb, ICMP_PARAMETERPROB, 0, info);
+	return ret;
+}
 EXPORT_SYMBOL(ip_options_compile);
 
 /*
-- 
2.20.1


From 89fd06e47d0a70fe34c0190b64cc4b9c2597798a Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 26 Feb 2019 09:00:02 -0800
Subject: [PATCH 34/42] ipv4: Return error for RTA_VIA attribute

[ Upstream commit b6e9e5df4ecf100f6a10ab2ade8e46d47a4b9779 ]

IPv4 currently does not support nexthops outside of the AF_INET family.
Specifically, it does not handle RTA_VIA attribute. If it is passed
in a route add request, the actual route added only uses the device
which is clearly not what the user intended:

  $ ip ro add 172.16.1.0/24 via inet6 2001:db8:1::1 dev eth0
  $ ip ro ls
  ...
  172.16.1.0/24 dev eth0

Catch this and fail the route add:
  $ ip ro add 172.16.1.0/24 via inet6 2001:db8:1::1 dev eth0
  Error: IPv4 does not support RTA_VIA attribute.

Fixes: 03c0566542f4c ("mpls: Netlink commands to add, remove, and dump routes")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_frontend.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index fe4f6a624238..ed14ec245584 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -710,6 +710,10 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
 		case RTA_GATEWAY:
 			cfg->fc_gw = nla_get_be32(attr);
 			break;
+		case RTA_VIA:
+			NL_SET_ERR_MSG(extack, "IPv4 does not support RTA_VIA attribute");
+			err = -EINVAL;
+			goto errout;
 		case RTA_PRIORITY:
 			cfg->fc_priority = nla_get_u32(attr);
 			break;
-- 
2.20.1


From 770604b31e7fae8d18a30602d72c5964cd198c05 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 26 Feb 2019 09:00:03 -0800
Subject: [PATCH 35/42] ipv6: Return error for RTA_VIA attribute

[ Upstream commit e3818541b49fb88650ba339d33cc53e4095da5b3 ]

IPv6 currently does not support nexthops outside of the AF_INET6 family.
Specifically, it does not handle RTA_VIA attribute. If it is passed
in a route add request, the actual route added only uses the device
which is clearly not what the user intended:

  $ ip -6 ro add 2001:db8:2::/64 via inet 172.16.1.1 dev eth0
  $ ip ro ls
  ...
  2001:db8:2::/64 dev eth0 metric 1024 pref medium

Catch this and fail the route add:
  $ ip -6 ro add 2001:db8:2::/64 via inet 172.16.1.1 dev eth0
  Error: IPv6 does not support RTA_VIA attribute.

Fixes: 03c0566542f4c ("mpls: Netlink commands to add, remove, and dump routes")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index a68d447b6e2c..c87ce5732338 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -4163,6 +4163,10 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 		cfg->fc_gateway = nla_get_in6_addr(tb[RTA_GATEWAY]);
 		cfg->fc_flags |= RTF_GATEWAY;
 	}
+	if (tb[RTA_VIA]) {
+		NL_SET_ERR_MSG(extack, "IPv6 does not support RTA_VIA attribute");
+		goto errout;
+	}
 
 	if (tb[RTA_DST]) {
 		int plen = (rtm->rtm_dst_len + 7) >> 3;
-- 
2.20.1


From d58d434052e25c3212745fab2cf70f0e6e89ca8b Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 26 Feb 2019 09:00:04 -0800
Subject: [PATCH 36/42] mpls: Return error for RTA_GATEWAY attribute

[ Upstream commit be48220edd48ca0d569782992840488a52373a24 ]

MPLS does not support nexthops with an MPLS address family.
Specifically, it does not handle RTA_GATEWAY attribute. Make it
clear by returning an error.

Fixes: 03c0566542f4c ("mpls: Netlink commands to add, remove, and dump routes")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mpls/af_mpls.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 7d55d4c04088..fa763e2e50ec 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -1838,6 +1838,9 @@ static int rtm_to_route_config(struct sk_buff *skb,
 				goto errout;
 			break;
 		}
+		case RTA_GATEWAY:
+			NL_SET_ERR_MSG(extack, "MPLS does not support RTA_GATEWAY attribute");
+			goto errout;
 		case RTA_VIA:
 		{
 			if (nla_get_via(nla, &cfg->rc_via_alen,
-- 
2.20.1


From 14593a2861600e6763f2a09c485e87fe17f2be4e Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Mon, 25 Feb 2019 13:55:48 -0800
Subject: [PATCH 37/42] ipv4: Pass original device to ip_rcv_finish_core

[ Upstream commit a1fd1ad2552fad9e649eeb85fd79301e2880a886 ]

ip_route_input_rcu expects the original ingress device (e.g., for
proper multicast handling). The skb->dev can be changed by l3mdev_ip_rcv,
so dev needs to be saved prior to calling it. This was the behavior prior
to the listify changes.

Fixes: 5fa12739a53d0 ("net: ipv4: listify ip_rcv_finish")
Cc: Edward Cree <ecree@solarflare.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_input.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 3163428219cd..a433b74a4f76 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -308,11 +308,10 @@ static inline bool ip_rcv_options(struct sk_buff *skb)
 }
 
 static int ip_rcv_finish_core(struct net *net, struct sock *sk,
-			      struct sk_buff *skb)
+			      struct sk_buff *skb, struct net_device *dev)
 {
 	const struct iphdr *iph = ip_hdr(skb);
 	int (*edemux)(struct sk_buff *skb);
-	struct net_device *dev = skb->dev;
 	struct rtable *rt;
 	int err;
 
@@ -401,6 +400,7 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk,
 
 static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
+	struct net_device *dev = skb->dev;
 	int ret;
 
 	/* if ingress device is enslaved to an L3 master device pass the
@@ -410,7 +410,7 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 	if (!skb)
 		return NET_RX_SUCCESS;
 
-	ret = ip_rcv_finish_core(net, sk, skb);
+	ret = ip_rcv_finish_core(net, sk, skb, dev);
 	if (ret != NET_RX_DROP)
 		ret = dst_input(skb);
 	return ret;
@@ -546,6 +546,7 @@ static void ip_list_rcv_finish(struct net *net, struct sock *sk,
 
 	INIT_LIST_HEAD(&sublist);
 	list_for_each_entry_safe(skb, next, head, list) {
+		struct net_device *dev = skb->dev;
 		struct dst_entry *dst;
 
 		skb_list_del_init(skb);
@@ -555,7 +556,7 @@ static void ip_list_rcv_finish(struct net *net, struct sock *sk,
 		skb = l3mdev_ip_rcv(skb);
 		if (!skb)
 			continue;
-		if (ip_rcv_finish_core(net, sk, skb) == NET_RX_DROP)
+		if (ip_rcv_finish_core(net, sk, skb, dev) == NET_RX_DROP)
 			continue;
 
 		dst = skb_dst(skb);
-- 
2.20.1


From 810d80ba6962d5edbe3afe4c60bdef8e4fc54165 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 28 Feb 2019 22:14:33 +0100
Subject: [PATCH 38/42] net: dsa: mv88e6xxx: power serdes on/off for 10G
 interfaces on 6390X

[ Upstream commit d235c48b40d399328585a68f3f9bf7cc3062d586 ]

Upon setting the cmode on 6390 and 6390X, the associated serdes
interfaces must be powered off/on.

Both 6390X and 6390 share code to do so, but it currently uses the 6390
specific helper mv88e6390_serdes_power() to disable and enable the
serdes interface.

This call will fail silently on 6390X when trying so set a 10G interface
such as XAUI or RXAUI, since mv88e6390_serdes_power() internally grabs
the lane number based on modes supported by the 6390, and returns 0 when
getting -ENODEV as a lane number.

Using mv88e6390x_serdes_power() should be safe here, since we explicitly
rule-out all ports but the 9 and 10, and because modes supported by 6390
ports 9 and 10 are a subset of those supported on 6390X.

This was tested on 6390X using RXAUI mode.

Fixes: 364e9d7776a3 ("net: dsa: mv88e6xxx: Power on/off SERDES on cmode change")
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/port.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c
index ece89756a070..71e604e9531a 100644
--- a/drivers/net/dsa/mv88e6xxx/port.c
+++ b/drivers/net/dsa/mv88e6xxx/port.c
@@ -405,7 +405,7 @@ int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 			return err;
 	}
 
-	err = mv88e6390_serdes_power(chip, port, false);
+	err = mv88e6390x_serdes_power(chip, port, false);
 	if (err)
 		return err;
 
@@ -421,7 +421,7 @@ int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 		if (err)
 			return err;
 
-		err = mv88e6390_serdes_power(chip, port, true);
+		err = mv88e6390x_serdes_power(chip, port, true);
 		if (err)
 			return err;
 
-- 
2.20.1


From 3f9fbb3ce763a07f84cd4b6642367dd7011e0280 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 28 Feb 2019 07:39:15 +0100
Subject: [PATCH 39/42] net: dsa: mv88e6xxx: prevent interrupt storm caused by
 mv88e6390x_port_set_cmode

[ Upstream commit ed8fe20205ac054bf585156709de3913d1890f30 ]

When debugging another issue I faced an interrupt storm in this
driver (88E6390, port 9 in SGMII mode), consisting of alternating
link-up / link-down interrupts. Analysis showed that the driver
wanted to set a cmode that was set already. But so far
mv88e6390x_port_set_cmode() doesn't check this and powers down
SERDES, what causes the link to break, and eventually results in
the described interrupt storm.

Fix this by checking whether the cmode actually changes. We want
that the very first call to mv88e6390x_port_set_cmode() always
configures the registers, therefore initialize port.cmode with
a value that is different from any supported cmode value.
We have to take care that we only init the ports cmode once
chip->info->num_ports is set.

v2:
- add small helper and init the number of actual ports only

Fixes: 364e9d7776a3 ("net: dsa: mv88e6xxx: Power on/off SERDES on cmode change")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 10 ++++++++++
 drivers/net/dsa/mv88e6xxx/port.c |  4 ++++
 drivers/net/dsa/mv88e6xxx/port.h |  1 +
 3 files changed, 15 insertions(+)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 0166f740e625..9021f01651d6 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -4579,6 +4579,14 @@ static int mv88e6xxx_smi_init(struct mv88e6xxx_chip *chip,
 	return 0;
 }
 
+static void mv88e6xxx_ports_cmode_init(struct mv88e6xxx_chip *chip)
+{
+	int i;
+
+	for (i = 0; i < mv88e6xxx_num_ports(chip); i++)
+		chip->ports[i].cmode = MV88E6XXX_PORT_STS_CMODE_INVALID;
+}
+
 static enum dsa_tag_protocol mv88e6xxx_get_tag_protocol(struct dsa_switch *ds,
 							int port)
 {
@@ -4615,6 +4623,8 @@ static const char *mv88e6xxx_drv_probe(struct device *dsa_dev,
 	if (err)
 		goto free;
 
+	mv88e6xxx_ports_cmode_init(chip);
+
 	mutex_lock(&chip->reg_lock);
 	err = mv88e6xxx_switch_reset(chip);
 	mutex_unlock(&chip->reg_lock);
diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c
index 71e604e9531a..abe86d7781d8 100644
--- a/drivers/net/dsa/mv88e6xxx/port.c
+++ b/drivers/net/dsa/mv88e6xxx/port.c
@@ -395,6 +395,10 @@ int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 		cmode = 0;
 	}
 
+	/* cmode doesn't change, nothing to do for us */
+	if (cmode == chip->ports[port].cmode)
+		return 0;
+
 	lane = mv88e6390x_serdes_get_lane(chip, port);
 	if (lane < 0)
 		return lane;
diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h
index 091aa0057f1f..cbb64a7683e2 100644
--- a/drivers/net/dsa/mv88e6xxx/port.h
+++ b/drivers/net/dsa/mv88e6xxx/port.h
@@ -52,6 +52,7 @@
 #define MV88E6185_PORT_STS_CMODE_1000BASE_X	0x0005
 #define MV88E6185_PORT_STS_CMODE_PHY		0x0006
 #define MV88E6185_PORT_STS_CMODE_DISABLED	0x0007
+#define MV88E6XXX_PORT_STS_CMODE_INVALID	0xff
 
 /* Offset 0x01: MAC (or PCS or Physical) Control Register */
 #define MV88E6XXX_PORT_MAC_CTL				0x01
-- 
2.20.1


From 30e8fe8200291a6e1aa331870e8e86d76dbbba10 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Fri, 22 Feb 2019 12:33:25 +0100
Subject: [PATCH 40/42] net/sched: act_ipt: fix refcount leak when replace
 fails

[ Upstream commit 8f67c90ee9148eab3d2b4393c3cf76489b27f87c ]

After commit 4e8ddd7f1758 ("net: sched: don't release reference on action
overwrite"), the error path of all actions was converted to drop refcount
also when the action was being overwritten. But we forgot act_ipt_init(),
in case allocation of 'tname' was not successful:

 # tc action add action xt -j LOG --log-prefix hello index 100
 tablename: mangle hook: NF_IP_POST_ROUTING
         target:  LOG level warning prefix "hello" index 100
 # tc action show action xt
 total acts 1

         action order 0: tablename: mangle  hook: NF_IP_POST_ROUTING
         target  LOG level warning prefix "hello"
         index 100 ref 1 bind 0
 # tc action replace action xt -j LOG --log-prefix world index 100
 tablename: mangle hook: NF_IP_POST_ROUTING
         target:  LOG level warning prefix "world" index 100
 RTNETLINK answers: Cannot allocate memory
 We have an error talking to the kernel
 # tc action show action xt
 total acts 1

         action order 0: tablename: mangle  hook: NF_IP_POST_ROUTING
         target  LOG level warning prefix "hello"
         index 100 ref 2 bind 0

Ensure we call tcf_idr_release(), in case 'tname' allocation failed, also
when the action is being replaced.

Fixes: 4e8ddd7f1758 ("net: sched: don't release reference on action overwrite")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ipt.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 8af6c11d2482..faa1addf89b3 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -199,8 +199,7 @@ static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla,
 err2:
 	kfree(tname);
 err1:
-	if (ret == ACT_P_CREATED)
-		tcf_idr_release(*a, bind);
+	tcf_idr_release(*a, bind);
 	return err;
 }
 
-- 
2.20.1


From d490eebca82047d87056f141fdf485dc6385ae13 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Fri, 22 Feb 2019 12:33:26 +0100
Subject: [PATCH 41/42] net/sched: act_skbedit: fix refcount leak when replace
 fails

[ Upstream commit 6191da98062d25276a3b88fb2a94dcbcfb3ea65d ]

when act_skbedit was converted to use RCU in the data plane, we added an
error path, but we forgot to drop the action refcount in case of failure
during a 'replace' operation:

 # tc actions add action skbedit ptype otherhost pass index 100
 # tc action show action skbedit
 total acts 1

         action order 0: skbedit  ptype otherhost pass
          index 100 ref 1 bind 0
 # tc actions replace action skbedit ptype otherhost drop index 100
 RTNETLINK answers: Cannot allocate memory
 We have an error talking to the kernel
 # tc action show action skbedit
 total acts 1

         action order 0: skbedit  ptype otherhost pass
          index 100 ref 2 bind 0

Ensure we call tcf_idr_release(), in case 'params_new' allocation failed,
also when the action is being replaced.

Fixes: c749cdda9089 ("net/sched: act_skbedit: don't use spinlock in the data path")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_skbedit.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 64dba3708fce..cfceed28c333 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -189,8 +189,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 
 	params_new = kzalloc(sizeof(*params_new), GFP_KERNEL);
 	if (unlikely(!params_new)) {
-		if (ret == ACT_P_CREATED)
-			tcf_idr_release(*a, bind);
+		tcf_idr_release(*a, bind);
 		return -ENOMEM;
 	}
 
-- 
2.20.1


From 259171b7fa5982c2bdfdbd26b2c68c779b54ff2e Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Mon, 25 Feb 2019 17:28:27 +0200
Subject: [PATCH 42/42] net: sched: act_tunnel_key: fix NULL pointer
 dereference during init

[ Upstream commit a3df633a3c92bb96b06552c3f828d7c267774379 ]

Metadata pointer is only initialized for action TCA_TUNNEL_KEY_ACT_SET, but
it is unconditionally dereferenced in tunnel_key_init() error handler.
Verify that metadata pointer is not NULL before dereferencing it in
tunnel_key_init error handling code.

Fixes: ee28bb56ac5b ("net/sched: fix memory leak in act_tunnel_key_init()")
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Reviewed-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_tunnel_key.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 904730b8ce8f..6f16202d4b4f 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -377,7 +377,8 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 	return ret;
 
 release_tun_meta:
-	dst_release(&metadata->dst);
+	if (metadata)
+		dst_release(&metadata->dst);
 
 err_out:
 	if (exists)
-- 
2.20.1


[-- Attachment #3: net_50.mbox --]
[-- Type: Application/Octet-Stream, Size: 32841 bytes --]

From 9a6ab180b3027870b40ef89c77c4cc824fa7c6dd Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Sun, 3 Mar 2019 07:34:57 +0000
Subject: [PATCH 01/12] ip6mr: Do not call __IP6_INC_STATS() from preemptible
 context

[ Upstream commit 87c11f1ddbbad38ad8bad47af133a8208985fbdf ]

Similar to commit 44f49dd8b5a6 ("ipmr: fix possible race resulting from
improper usage of IP_INC_STATS_BH() in preemptible context."), we cannot
assume preemption is disabled when incrementing the counter and
accessing a per-CPU variable.

Preemption can be enabled when we add a route in process context that
corresponds to packets stored in the unresolved queue, which are then
forwarded using this route [1].

Fix this by using IP6_INC_STATS() which takes care of disabling
preemption on architectures where it is needed.

[1]
[  157.451447] BUG: using __this_cpu_add() in preemptible [00000000] code: smcrouted/2314
[  157.460409] caller is ip6mr_forward2+0x73e/0x10e0
[  157.460434] CPU: 3 PID: 2314 Comm: smcrouted Not tainted 5.0.0-rc7-custom-03635-g22f2712113f1 #1336
[  157.460449] Hardware name: Mellanox Technologies Ltd. MSN2100-CB2FO/SA001017, BIOS 5.6.5 06/07/2016
[  157.460461] Call Trace:
[  157.460486]  dump_stack+0xf9/0x1be
[  157.460553]  check_preemption_disabled+0x1d6/0x200
[  157.460576]  ip6mr_forward2+0x73e/0x10e0
[  157.460705]  ip6_mr_forward+0x9a0/0x1510
[  157.460771]  ip6mr_mfc_add+0x16b3/0x1e00
[  157.461155]  ip6_mroute_setsockopt+0x3cb/0x13c0
[  157.461384]  do_ipv6_setsockopt.isra.8+0x348/0x4060
[  157.462013]  ipv6_setsockopt+0x90/0x110
[  157.462036]  rawv6_setsockopt+0x4a/0x120
[  157.462058]  __sys_setsockopt+0x16b/0x340
[  157.462198]  __x64_sys_setsockopt+0xbf/0x160
[  157.462220]  do_syscall_64+0x14d/0x610
[  157.462349]  entry_SYSCALL_64_after_hwframe+0x49/0xbe

Fixes: 0912ea38de61 ("[IPV6] MROUTE: Add stats in multicast routing module method ip6_mr_forward().")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Amit Cohen <amitc@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6mr.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index cc01aa3f2b5e..af91a1a402f1 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1964,10 +1964,10 @@ int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg)
 
 static inline int ip6mr_forward2_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
-	__IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
-			IPSTATS_MIB_OUTFORWDATAGRAMS);
-	__IP6_ADD_STATS(net, ip6_dst_idev(skb_dst(skb)),
-			IPSTATS_MIB_OUTOCTETS, skb->len);
+	IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
+		      IPSTATS_MIB_OUTFORWDATAGRAMS);
+	IP6_ADD_STATS(net, ip6_dst_idev(skb_dst(skb)),
+		      IPSTATS_MIB_OUTOCTETS, skb->len);
 	return dst_output(net, sk, skb);
 }
 
-- 
2.20.1


From 56dd9c8ef6d794b213d277c1aae0c0087ef0adad Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 4 Mar 2019 19:39:03 +0100
Subject: [PATCH 02/12] net: dsa: mv88e6xxx: add call to
 mv88e6xxx_ports_cmode_init to probe for new DSA framework

[ Upstream commit 3acca1dd17060332cfab15693733cdaf9fba1c90 ]

In the original patch I missed to add mv88e6xxx_ports_cmode_init()
to the second probe function, the one for the new DSA framework.

Fixes: ed8fe20205ac ("net: dsa: mv88e6xxx: prevent interrupt storm caused by mv88e6390x_port_set_cmode")
Reported-by: Shaokun Zhang <zhangshaokun@hisilicon.com>
Suggested-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 7e3c00bd9532..e01d7ea62a77 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -4847,6 +4847,7 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev)
 	if (err)
 		goto out;
 
+	mv88e6xxx_ports_cmode_init(chip);
 	mv88e6xxx_phy_init(chip);
 
 	if (chip->info->ops->get_eeprom) {
-- 
2.20.1


From d831cce08ea10e6890413fab97a7f79d5af6ce82 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 1 Mar 2019 19:53:57 +0100
Subject: [PATCH 03/12] net: dsa: mv88e6xxx: handle unknown duplex modes
 gracefully in mv88e6xxx_port_set_duplex

[ Upstream commit c6195a8bdfc62a7cecf7df685e64847a4b700275 ]

When testing another issue I faced the problem that
mv88e6xxx_port_setup_mac() failed due to DUPLEX_UNKNOWN being passed
as argument to mv88e6xxx_port_set_duplex(). We should handle this case
gracefully and return -EOPNOTSUPP, like e.g. mv88e6xxx_port_set_speed()
is doing it.

Fixes: 7f1ae07b51e8 ("net: dsa: mv88e6xxx: add port duplex setter")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/port.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c
index 79ab51e69aee..184c2b1b3115 100644
--- a/drivers/net/dsa/mv88e6xxx/port.c
+++ b/drivers/net/dsa/mv88e6xxx/port.c
@@ -190,7 +190,7 @@ int mv88e6xxx_port_set_duplex(struct mv88e6xxx_chip *chip, int port, int dup)
 		/* normal duplex detection */
 		break;
 	default:
-		return -EINVAL;
+		return -EOPNOTSUPP;
 	}
 
 	err = mv88e6xxx_port_write(chip, port, MV88E6XXX_PORT_MAC_CTL, reg);
-- 
2.20.1


From ebd323084fd6c68c34b939963bb32a2a5433d6c2 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 2 Mar 2019 10:06:05 +0100
Subject: [PATCH 04/12] net: dsa: mv8e6xxx: fix number of internal PHYs for
 88E6x90 family

[ Upstream commit 95150f29ae480276e76368cdf8a9524b5a96c0ca ]

Ports 9 and 10 don't have internal PHY's but are (dependent on the
version) SERDES/SGMII/XAUI/RXAUI ports.

v2:
- fix it for all 88E6x90 family members

Fixes: bc3931557d1d ("net: dsa: mv88e6xxx: Add number of internal PHYs")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index e01d7ea62a77..76cc163b3cf1 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -4222,7 +4222,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6190",
 		.num_databases = 4096,
 		.num_ports = 11,	/* 10 + Z80 */
-		.num_internal_phys = 11,
+		.num_internal_phys = 9,
 		.num_gpio = 16,
 		.max_vid = 8191,
 		.port_base_addr = 0x0,
@@ -4245,7 +4245,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6190X",
 		.num_databases = 4096,
 		.num_ports = 11,	/* 10 + Z80 */
-		.num_internal_phys = 11,
+		.num_internal_phys = 9,
 		.num_gpio = 16,
 		.max_vid = 8191,
 		.port_base_addr = 0x0,
@@ -4268,7 +4268,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6191",
 		.num_databases = 4096,
 		.num_ports = 11,	/* 10 + Z80 */
-		.num_internal_phys = 11,
+		.num_internal_phys = 9,
 		.max_vid = 8191,
 		.port_base_addr = 0x0,
 		.phy_base_addr = 0x0,
@@ -4315,7 +4315,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6290",
 		.num_databases = 4096,
 		.num_ports = 11,	/* 10 + Z80 */
-		.num_internal_phys = 11,
+		.num_internal_phys = 9,
 		.num_gpio = 16,
 		.max_vid = 8191,
 		.port_base_addr = 0x0,
@@ -4477,7 +4477,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6390",
 		.num_databases = 4096,
 		.num_ports = 11,	/* 10 + Z80 */
-		.num_internal_phys = 11,
+		.num_internal_phys = 9,
 		.num_gpio = 16,
 		.max_vid = 8191,
 		.port_base_addr = 0x0,
@@ -4500,7 +4500,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.name = "Marvell 88E6390X",
 		.num_databases = 4096,
 		.num_ports = 11,	/* 10 + Z80 */
-		.num_internal_phys = 11,
+		.num_internal_phys = 9,
 		.num_gpio = 16,
 		.max_vid = 8191,
 		.port_base_addr = 0x0,
-- 
2.20.1


From c4b1694b1e7ce7f6ccbb3e8ddcee54538d033582 Mon Sep 17 00:00:00 2001
From: Kavya Sree Kotagiri <kavyasree.kotagiri@microchip.com>
Date: Thu, 28 Feb 2019 07:32:22 +0000
Subject: [PATCH 05/12] net: mscc: Enable all ports in QSGMII

[ Upstream commit 084e5bb16bd7dc2b551bbd9fb358bf73e03ee8d8 ]

When Ocelot phy-mode is QSGMII, all 4 ports involved in
QSGMII shall be kept out of reset and
Tx lanes shall be enabled to pass the data.

Fixes: a556c76adc05 ("net: mscc: Add initial Ocelot switch support")
Signed-off-by: Kavya Sree Kotagiri <kavyasree.kotagiri@microchip.com>
Signed-off-by: Steen Hegelund <Steen.Hegelund@microchip.com>
Co-developed-by: Steen Hegelund <Steen.Hegelund@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot_board.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c
index ca3ea2fbfcd0..80d87798c62b 100644
--- a/drivers/net/ethernet/mscc/ocelot_board.c
+++ b/drivers/net/ethernet/mscc/ocelot_board.c
@@ -267,6 +267,7 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
 		struct phy *serdes;
 		void __iomem *regs;
 		char res_name[8];
+		int phy_mode;
 		u32 port;
 
 		if (of_property_read_u32(portnp, "reg", &port))
@@ -292,11 +293,11 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
 		if (err)
 			return err;
 
-		err = of_get_phy_mode(portnp);
-		if (err < 0)
+		phy_mode = of_get_phy_mode(portnp);
+		if (phy_mode < 0)
 			ocelot->ports[port]->phy_mode = PHY_INTERFACE_MODE_NA;
 		else
-			ocelot->ports[port]->phy_mode = err;
+			ocelot->ports[port]->phy_mode = phy_mode;
 
 		switch (ocelot->ports[port]->phy_mode) {
 		case PHY_INTERFACE_MODE_NA:
@@ -304,6 +305,13 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
 		case PHY_INTERFACE_MODE_SGMII:
 			break;
 		case PHY_INTERFACE_MODE_QSGMII:
+			/* Ensure clock signals and speed is set on all
+			 * QSGMII links
+			 */
+			ocelot_port_writel(ocelot->ports[port],
+					   DEV_CLOCK_CFG_LINK_SPEED
+					   (OCELOT_SPEED_1000),
+					   DEV_CLOCK_CFG);
 			break;
 		default:
 			dev_err(ocelot->dev,
-- 
2.20.1


From 823553922b0c1c6bfb20bd1e87f83e3f0d5940bf Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 28 Feb 2019 12:55:43 -0800
Subject: [PATCH 06/12] net: sched: put back q.qlen into a single location

[ Upstream commit 46b1c18f9deb326a7e18348e668e4c7ab7c7458b ]

In the series fc8b81a5981f ("Merge branch 'lockless-qdisc-series'")
John made the assumption that the data path had no need to read
the qdisc qlen (number of packets in the qdisc).

It is true when pfifo_fast is used as the root qdisc, or as direct MQ/MQPRIO
children.

But pfifo_fast can be used as leaf in class full qdiscs, and existing
logic needs to access the child qlen in an efficient way.

HTB breaks badly, since it uses cl->leaf.q->q.qlen in :
  htb_activate() -> WARN_ON()
  htb_dequeue_tree() to decide if a class can be htb_deactivated
  when it has no more packets.

HFSC, DRR, CBQ, QFQ have similar issues, and some calls to
qdisc_tree_reduce_backlog() also read q.qlen directly.

Using qdisc_qlen_sum() (which iterates over all possible cpus)
in the data path is a non starter.

It seems we have to put back qlen in a central location,
at least for stable kernels.

For all qdisc but pfifo_fast, qlen is guarded by the qdisc lock,
so the existing q.qlen{++|--} are correct.

For 'lockless' qdisc (pfifo_fast so far), we need to use atomic_{inc|dec}()
because the spinlock might be not held (for example from
pfifo_fast_enqueue() and pfifo_fast_dequeue())

This patch adds atomic_qlen (in the same location than qlen)
and renames the following helpers, since we want to express
they can be used without qdisc lock, and that qlen is no longer percpu.

- qdisc_qstats_cpu_qlen_dec -> qdisc_qstats_atomic_qlen_dec()
- qdisc_qstats_cpu_qlen_inc -> qdisc_qstats_atomic_qlen_inc()

Later (net-next) we might revert this patch by tracking all these
qlen uses and replace them by a more efficient method (not having
to access a precise qlen, but an empty/non_empty status that might
be less expensive to maintain/track).

Another possibility is to have a legacy pfifo_fast version that would
be used when used a a child qdisc, since the parent qdisc needs
a spinlock anyway. But then, future lockless qdiscs would also
have the same problem.

Fixes: 7e66016f2c65 ("net: sched: helpers to sum qlen and qlen for per cpu logic")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h | 31 +++++++++++++------------------
 net/core/gen_stats.c      |  2 --
 net/sched/sch_generic.c   | 13 ++++++-------
 3 files changed, 19 insertions(+), 27 deletions(-)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 9481f2c142e2..e7eb4aa6ccc9 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -51,7 +51,10 @@ struct qdisc_size_table {
 struct qdisc_skb_head {
 	struct sk_buff	*head;
 	struct sk_buff	*tail;
-	__u32		qlen;
+	union {
+		u32		qlen;
+		atomic_t	atomic_qlen;
+	};
 	spinlock_t	lock;
 };
 
@@ -408,27 +411,19 @@ static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz)
 	BUILD_BUG_ON(sizeof(qcb->data) < sz);
 }
 
-static inline int qdisc_qlen_cpu(const struct Qdisc *q)
-{
-	return this_cpu_ptr(q->cpu_qstats)->qlen;
-}
-
 static inline int qdisc_qlen(const struct Qdisc *q)
 {
 	return q->q.qlen;
 }
 
-static inline int qdisc_qlen_sum(const struct Qdisc *q)
+static inline u32 qdisc_qlen_sum(const struct Qdisc *q)
 {
-	__u32 qlen = q->qstats.qlen;
-	int i;
+	u32 qlen = q->qstats.qlen;
 
-	if (q->flags & TCQ_F_NOLOCK) {
-		for_each_possible_cpu(i)
-			qlen += per_cpu_ptr(q->cpu_qstats, i)->qlen;
-	} else {
+	if (q->flags & TCQ_F_NOLOCK)
+		qlen += atomic_read(&q->q.atomic_qlen);
+	else
 		qlen += q->q.qlen;
-	}
 
 	return qlen;
 }
@@ -825,14 +820,14 @@ static inline void qdisc_qstats_cpu_backlog_inc(struct Qdisc *sch,
 	this_cpu_add(sch->cpu_qstats->backlog, qdisc_pkt_len(skb));
 }
 
-static inline void qdisc_qstats_cpu_qlen_inc(struct Qdisc *sch)
+static inline void qdisc_qstats_atomic_qlen_inc(struct Qdisc *sch)
 {
-	this_cpu_inc(sch->cpu_qstats->qlen);
+	atomic_inc(&sch->q.atomic_qlen);
 }
 
-static inline void qdisc_qstats_cpu_qlen_dec(struct Qdisc *sch)
+static inline void qdisc_qstats_atomic_qlen_dec(struct Qdisc *sch)
 {
-	this_cpu_dec(sch->cpu_qstats->qlen);
+	atomic_dec(&sch->q.atomic_qlen);
 }
 
 static inline void qdisc_qstats_cpu_requeues_inc(struct Qdisc *sch)
diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c
index 9bf1b9ad1780..ac679f74ba47 100644
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -291,7 +291,6 @@ __gnet_stats_copy_queue_cpu(struct gnet_stats_queue *qstats,
 	for_each_possible_cpu(i) {
 		const struct gnet_stats_queue *qcpu = per_cpu_ptr(q, i);
 
-		qstats->qlen = 0;
 		qstats->backlog += qcpu->backlog;
 		qstats->drops += qcpu->drops;
 		qstats->requeues += qcpu->requeues;
@@ -307,7 +306,6 @@ void __gnet_stats_copy_queue(struct gnet_stats_queue *qstats,
 	if (cpu) {
 		__gnet_stats_copy_queue_cpu(qstats, cpu);
 	} else {
-		qstats->qlen = q->qlen;
 		qstats->backlog = q->backlog;
 		qstats->drops = q->drops;
 		qstats->requeues = q->requeues;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 968a85fe4d4a..de31f2f3b973 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -68,7 +68,7 @@ static inline struct sk_buff *__skb_dequeue_bad_txq(struct Qdisc *q)
 			skb = __skb_dequeue(&q->skb_bad_txq);
 			if (qdisc_is_percpu_stats(q)) {
 				qdisc_qstats_cpu_backlog_dec(q, skb);
-				qdisc_qstats_cpu_qlen_dec(q);
+				qdisc_qstats_atomic_qlen_dec(q);
 			} else {
 				qdisc_qstats_backlog_dec(q, skb);
 				q->q.qlen--;
@@ -108,7 +108,7 @@ static inline void qdisc_enqueue_skb_bad_txq(struct Qdisc *q,
 
 	if (qdisc_is_percpu_stats(q)) {
 		qdisc_qstats_cpu_backlog_inc(q, skb);
-		qdisc_qstats_cpu_qlen_inc(q);
+		qdisc_qstats_atomic_qlen_inc(q);
 	} else {
 		qdisc_qstats_backlog_inc(q, skb);
 		q->q.qlen++;
@@ -147,7 +147,7 @@ static inline int dev_requeue_skb_locked(struct sk_buff *skb, struct Qdisc *q)
 
 		qdisc_qstats_cpu_requeues_inc(q);
 		qdisc_qstats_cpu_backlog_inc(q, skb);
-		qdisc_qstats_cpu_qlen_inc(q);
+		qdisc_qstats_atomic_qlen_inc(q);
 
 		skb = next;
 	}
@@ -252,7 +252,7 @@ static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate,
 			skb = __skb_dequeue(&q->gso_skb);
 			if (qdisc_is_percpu_stats(q)) {
 				qdisc_qstats_cpu_backlog_dec(q, skb);
-				qdisc_qstats_cpu_qlen_dec(q);
+				qdisc_qstats_atomic_qlen_dec(q);
 			} else {
 				qdisc_qstats_backlog_dec(q, skb);
 				q->q.qlen--;
@@ -645,7 +645,7 @@ static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc,
 	if (unlikely(err))
 		return qdisc_drop_cpu(skb, qdisc, to_free);
 
-	qdisc_qstats_cpu_qlen_inc(qdisc);
+	qdisc_qstats_atomic_qlen_inc(qdisc);
 	/* Note: skb can not be used after skb_array_produce(),
 	 * so we better not use qdisc_qstats_cpu_backlog_inc()
 	 */
@@ -670,7 +670,7 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc)
 	if (likely(skb)) {
 		qdisc_qstats_cpu_backlog_dec(qdisc, skb);
 		qdisc_bstats_cpu_update(qdisc, skb);
-		qdisc_qstats_cpu_qlen_dec(qdisc);
+		qdisc_qstats_atomic_qlen_dec(qdisc);
 	}
 
 	return skb;
@@ -714,7 +714,6 @@ static void pfifo_fast_reset(struct Qdisc *qdisc)
 		struct gnet_stats_queue *q = per_cpu_ptr(qdisc->cpu_qstats, i);
 
 		q->backlog = 0;
-		q->qlen = 0;
 	}
 }
 
-- 
2.20.1


From 42032f7a90e112e5f6d11955d8ba7de45748908d Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Sat, 2 Mar 2019 10:34:55 +0800
Subject: [PATCH 07/12] net-sysfs: Fix mem leak in netdev_register_kobject

[ Upstream commit 895a5e96dbd6386c8e78e5b78e067dcc67b7f0ab ]

syzkaller report this:
BUG: memory leak
unreferenced object 0xffff88837a71a500 (size 256):
  comm "syz-executor.2", pid 9770, jiffies 4297825125 (age 17.843s)
  hex dump (first 32 bytes):
    00 00 00 00 ad 4e ad de ff ff ff ff 00 00 00 00  .....N..........
    ff ff ff ff ff ff ff ff 20 c0 ef 86 ff ff ff ff  ........ .......
  backtrace:
    [<00000000db12624b>] netdev_register_kobject+0x124/0x2e0 net/core/net-sysfs.c:1751
    [<00000000dc49a994>] register_netdevice+0xcc1/0x1270 net/core/dev.c:8516
    [<00000000e5f3fea0>] tun_set_iff drivers/net/tun.c:2649 [inline]
    [<00000000e5f3fea0>] __tun_chr_ioctl+0x2218/0x3d20 drivers/net/tun.c:2883
    [<000000001b8ac127>] vfs_ioctl fs/ioctl.c:46 [inline]
    [<000000001b8ac127>] do_vfs_ioctl+0x1a5/0x10e0 fs/ioctl.c:690
    [<0000000079b269f8>] ksys_ioctl+0x89/0xa0 fs/ioctl.c:705
    [<00000000de649beb>] __do_sys_ioctl fs/ioctl.c:712 [inline]
    [<00000000de649beb>] __se_sys_ioctl fs/ioctl.c:710 [inline]
    [<00000000de649beb>] __x64_sys_ioctl+0x74/0xb0 fs/ioctl.c:710
    [<000000007ebded1e>] do_syscall_64+0xc8/0x580 arch/x86/entry/common.c:290
    [<00000000db315d36>] entry_SYSCALL_64_after_hwframe+0x49/0xbe
    [<00000000115be9bb>] 0xffffffffffffffff

It should call kset_unregister to free 'dev->queues_kset'
in error path of register_queue_kobjects, otherwise will cause a mem leak.

Reported-by: Hulk Robot <hulkci@huawei.com>
Fixes: 1d24eb4815d1 ("xps: Transmit Packet Steering")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/net-sysfs.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index ff9fd2bb4ce4..73ad7607dcd1 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1547,6 +1547,9 @@ static int register_queue_kobjects(struct net_device *dev)
 error:
 	netdev_queue_update_kobjects(dev, txq, 0);
 	net_rx_queue_update_kobjects(dev, rxq, 0);
+#ifdef CONFIG_SYSFS
+	kset_unregister(dev->queues_kset);
+#endif
 	return error;
 }
 
-- 
2.20.1


From 28dcb341ea96a1b0a77fb6475b7aa3261efe7e45 Mon Sep 17 00:00:00 2001
From: Kristian Evensen <kristian.evensen@gmail.com>
Date: Sat, 2 Mar 2019 13:32:26 +0100
Subject: [PATCH 08/12] qmi_wwan: Add support for Quectel EG12/EM12
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 822e44b45eb991c63487c5e2ce7d636411870a8d ]

Quectel EG12 (module)/EM12 (M.2 card) is a Cat. 12 LTE modem. The modem
behaves in the same way as the EP06, so the "set DTR"-quirk must be
applied and the diagnostic-interface check performed. Since the
diagnostic-check now applies to more modems, I have renamed the function
from quectel_ep06_diag_detected() to quectel_diag_detected().

Signed-off-by: Kristian Evensen <kristian.evensen@gmail.com>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 26 ++++++++++++++++++--------
 1 file changed, 18 insertions(+), 8 deletions(-)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 18af2f8eee96..74bebbdb4b15 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -976,6 +976,13 @@ static const struct usb_device_id products[] = {
 					      0xff),
 		.driver_info	    = (unsigned long)&qmi_wwan_info_quirk_dtr,
 	},
+	{	/* Quectel EG12/EM12 */
+		USB_DEVICE_AND_INTERFACE_INFO(0x2c7c, 0x0512,
+					      USB_CLASS_VENDOR_SPEC,
+					      USB_SUBCLASS_VENDOR_SPEC,
+					      0xff),
+		.driver_info	    = (unsigned long)&qmi_wwan_info_quirk_dtr,
+	},
 
 	/* 3. Combined interface devices matching on interface number */
 	{QMI_FIXED_INTF(0x0408, 0xea42, 4)},	/* Yota / Megafon M100-1 */
@@ -1343,17 +1350,20 @@ static bool quectel_ec20_detected(struct usb_interface *intf)
 	return false;
 }
 
-static bool quectel_ep06_diag_detected(struct usb_interface *intf)
+static bool quectel_diag_detected(struct usb_interface *intf)
 {
 	struct usb_device *dev = interface_to_usbdev(intf);
 	struct usb_interface_descriptor intf_desc = intf->cur_altsetting->desc;
+	u16 id_vendor = le16_to_cpu(dev->descriptor.idVendor);
+	u16 id_product = le16_to_cpu(dev->descriptor.idProduct);
 
-	if (le16_to_cpu(dev->descriptor.idVendor) == 0x2c7c &&
-	    le16_to_cpu(dev->descriptor.idProduct) == 0x0306 &&
-	    intf_desc.bNumEndpoints == 2)
-		return true;
+	if (id_vendor != 0x2c7c || intf_desc.bNumEndpoints != 2)
+		return false;
 
-	return false;
+	if (id_product == 0x0306 || id_product == 0x0512)
+		return true;
+	else
+		return false;
 }
 
 static int qmi_wwan_probe(struct usb_interface *intf,
@@ -1390,13 +1400,13 @@ static int qmi_wwan_probe(struct usb_interface *intf,
 		return -ENODEV;
 	}
 
-	/* Quectel EP06/EM06/EG06 supports dynamic interface configuration, so
+	/* Several Quectel modems supports dynamic interface configuration, so
 	 * we need to match on class/subclass/protocol. These values are
 	 * identical for the diagnostic- and QMI-interface, but bNumEndpoints is
 	 * different. Ignore the current interface if the number of endpoints
 	 * the number for the diag interface (two).
 	 */
-	if (quectel_ep06_diag_detected(intf))
+	if (quectel_diag_detected(intf))
 		return -ENODEV;
 
 	return usbnet_probe(intf, id);
-- 
2.20.1


From d336371b3522d799751d397ca5232632d6ead0ef Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 3 Mar 2019 16:50:26 +0800
Subject: [PATCH 09/12] sctp: call iov_iter_revert() after sending ABORT

[ Upstream commit 901efe12318b1ea8d3e2c88a7b75ed6e6d5d7245 ]

The user msg is also copied to the abort packet when doing SCTP_ABORT in
sctp_sendmsg_check_sflags(). When SCTP_SENDALL is set, iov_iter_revert()
should have been called for sending abort on the next asoc with copying
this msg. Otherwise, memcpy_from_msg() in sctp_make_abort_user() will
fail and return error.

Fixes: 4910280503f3 ("sctp: add support for snd flag SCTP_SENDALL process in sendmsg")
Reported-by: Ying Xu <yinxu@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 65d6d04546ae..a2771b3b3c14 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1866,6 +1866,7 @@ static int sctp_sendmsg_check_sflags(struct sctp_association *asoc,
 
 		pr_debug("%s: aborting association:%p\n", __func__, asoc);
 		sctp_primitive_ABORT(net, asoc, chunk);
+		iov_iter_revert(&msg->msg_iter, msg_len);
 
 		return 0;
 	}
-- 
2.20.1


From 14ca207203b168abd6f51e7324d2863191cb0d0a Mon Sep 17 00:00:00 2001
From: Kai-Heng Feng <kai.heng.feng@canonical.com>
Date: Mon, 4 Mar 2019 15:00:03 +0800
Subject: [PATCH 10/12] sky2: Disable MSI on Dell Inspiron 1545 and Gateway
 P-79

[ Upstream commit b33b7cd6fd86478dd2890a9abeb6f036aa01fdf7 ]

Some sky2 chips fire IRQ after S3, before the driver is fully resumed:
[ 686.804877] do_IRQ: 1.37 No irq handler for vector

This is likely a platform bug that device isn't fully quiesced during
S3. Use MSI-X, maskable MSI or INTx can prevent this issue from
happening.

Since MSI-X and maskable MSI are not supported by this device, fallback
to use INTx on affected platforms.

BugLink: https://bugs.launchpad.net/bugs/1807259
BugLink: https://bugs.launchpad.net/bugs/1809843
Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/sky2.c | 24 +++++++++++++++++++++++-
 1 file changed, 23 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index 57727fe1501e..8b3495ee2b6e 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -46,6 +46,7 @@
 #include <linux/mii.h>
 #include <linux/of_device.h>
 #include <linux/of_net.h>
+#include <linux/dmi.h>
 
 #include <asm/irq.h>
 
@@ -93,7 +94,7 @@ static int copybreak __read_mostly = 128;
 module_param(copybreak, int, 0);
 MODULE_PARM_DESC(copybreak, "Receive copy threshold");
 
-static int disable_msi = 0;
+static int disable_msi = -1;
 module_param(disable_msi, int, 0);
 MODULE_PARM_DESC(disable_msi, "Disable Message Signaled Interrupt (MSI)");
 
@@ -4917,6 +4918,24 @@ static const char *sky2_name(u8 chipid, char *buf, int sz)
 	return buf;
 }
 
+static const struct dmi_system_id msi_blacklist[] = {
+	{
+		.ident = "Dell Inspiron 1545",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 1545"),
+		},
+	},
+	{
+		.ident = "Gateway P-79",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Gateway"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "P-79"),
+		},
+	},
+	{}
+};
+
 static int sky2_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	struct net_device *dev, *dev1;
@@ -5028,6 +5047,9 @@ static int sky2_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_out_free_pci;
 	}
 
+	if (disable_msi == -1)
+		disable_msi = !!dmi_check_system(msi_blacklist);
+
 	if (!disable_msi && pci_enable_msi(pdev) == 0) {
 		err = sky2_test_msi(hw);
 		if (err) {
-- 
2.20.1


From 4e3c088094e0151183f76a87fe72154422196787 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Sun, 3 Mar 2019 07:35:51 +0000
Subject: [PATCH 11/12] team: Free BPF filter when unregistering netdev

[ Upstream commit 692c31bd4054212312396b1d303bffab2c5b93a7 ]

When team is used in loadbalance mode a BPF filter can be used to
provide a hash which will determine the Tx port.

When the netdev is later unregistered the filter is not freed which
results in memory leaks [1].

Fix by freeing the program and the corresponding filter when
unregistering the netdev.

[1]
unreferenced object 0xffff8881dbc47cc8 (size 16):
  comm "teamd", pid 3068, jiffies 4294997779 (age 438.247s)
  hex dump (first 16 bytes):
    a3 00 6b 6b 6b 6b 6b 6b 88 a5 82 e1 81 88 ff ff  ..kkkkkk........
  backtrace:
    [<000000008a3b47e3>] team_nl_cmd_options_set+0x88f/0x11b0
    [<00000000c4f4f27e>] genl_family_rcv_msg+0x78f/0x1080
    [<00000000610ef838>] genl_rcv_msg+0xca/0x170
    [<00000000a281df93>] netlink_rcv_skb+0x132/0x380
    [<000000004d9448a2>] genl_rcv+0x29/0x40
    [<000000000321b2f4>] netlink_unicast+0x4c0/0x690
    [<000000008c25dffb>] netlink_sendmsg+0x929/0xe10
    [<00000000068298c5>] sock_sendmsg+0xc8/0x110
    [<0000000082a61ff0>] ___sys_sendmsg+0x77a/0x8f0
    [<00000000663ae29d>] __sys_sendmsg+0xf7/0x250
    [<0000000027c5f11a>] do_syscall_64+0x14d/0x610
    [<000000006cfbc8d3>] entry_SYSCALL_64_after_hwframe+0x49/0xbe
    [<00000000e23197e2>] 0xffffffffffffffff
unreferenced object 0xffff8881e182a588 (size 2048):
  comm "teamd", pid 3068, jiffies 4294997780 (age 438.247s)
  hex dump (first 32 bytes):
    20 00 00 00 02 00 00 00 30 00 00 00 28 f0 ff ff   .......0...(...
    07 00 00 00 00 00 00 00 28 00 00 00 00 00 00 00  ........(.......
  backtrace:
    [<000000002daf01fb>] lb_bpf_func_set+0x45c/0x6d0
    [<000000008a3b47e3>] team_nl_cmd_options_set+0x88f/0x11b0
    [<00000000c4f4f27e>] genl_family_rcv_msg+0x78f/0x1080
    [<00000000610ef838>] genl_rcv_msg+0xca/0x170
    [<00000000a281df93>] netlink_rcv_skb+0x132/0x380
    [<000000004d9448a2>] genl_rcv+0x29/0x40
    [<000000000321b2f4>] netlink_unicast+0x4c0/0x690
    [<000000008c25dffb>] netlink_sendmsg+0x929/0xe10
    [<00000000068298c5>] sock_sendmsg+0xc8/0x110
    [<0000000082a61ff0>] ___sys_sendmsg+0x77a/0x8f0
    [<00000000663ae29d>] __sys_sendmsg+0xf7/0x250
    [<0000000027c5f11a>] do_syscall_64+0x14d/0x610
    [<000000006cfbc8d3>] entry_SYSCALL_64_after_hwframe+0x49/0xbe
    [<00000000e23197e2>] 0xffffffffffffffff

Fixes: 01d7f30a9f96 ("team: add loadbalance mode")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Amit Cohen <amitc@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team_mode_loadbalance.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/net/team/team_mode_loadbalance.c b/drivers/net/team/team_mode_loadbalance.c
index a5ef97010eb3..5541e1c19936 100644
--- a/drivers/net/team/team_mode_loadbalance.c
+++ b/drivers/net/team/team_mode_loadbalance.c
@@ -325,6 +325,20 @@ static int lb_bpf_func_set(struct team *team, struct team_gsetter_ctx *ctx)
 	return 0;
 }
 
+static void lb_bpf_func_free(struct team *team)
+{
+	struct lb_priv *lb_priv = get_lb_priv(team);
+	struct bpf_prog *fp;
+
+	if (!lb_priv->ex->orig_fprog)
+		return;
+
+	__fprog_destroy(lb_priv->ex->orig_fprog);
+	fp = rcu_dereference_protected(lb_priv->fp,
+				       lockdep_is_held(&team->lock));
+	bpf_prog_destroy(fp);
+}
+
 static int lb_tx_method_get(struct team *team, struct team_gsetter_ctx *ctx)
 {
 	struct lb_priv *lb_priv = get_lb_priv(team);
@@ -639,6 +653,7 @@ static void lb_exit(struct team *team)
 
 	team_options_unregister(team, lb_options,
 				ARRAY_SIZE(lb_options));
+	lb_bpf_func_free(team);
 	cancel_delayed_work_sync(&lb_priv->ex->stats.refresh_dw);
 	free_percpu(lb_priv->pcpu_stats);
 	kfree(lb_priv->ex);
-- 
2.20.1


From 35eafc42b81bc876ac19551da5e86e58aee4ea63 Mon Sep 17 00:00:00 2001
From: Erik Hugne <erik.hugne@gmail.com>
Date: Mon, 4 Mar 2019 23:26:10 +0100
Subject: [PATCH 12/12] tipc: fix RDM/DGRAM connect() regression

[ Upstream commit 0e63208915a8d7590d0a6218dadb2a6a00ac705a ]

Fix regression bug introduced in
commit 365ad353c256 ("tipc: reduce risk of user starvation during link
congestion")

Only signal -EDESTADDRREQ for RDM/DGRAM if we don't have a cached
sockaddr.

Fixes: 365ad353c256 ("tipc: reduce risk of user starvation during link congestion")
Signed-off-by: Erik Hugne <erik.hugne@gmail.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/socket.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 70343ac448b1..139694f2c576 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1333,7 +1333,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
 
 	if (unlikely(!dest)) {
 		dest = &tsk->peer;
-		if (!syn || dest->family != AF_TIPC)
+		if (!syn && dest->family != AF_TIPC)
 			return -EDESTADDRREQ;
 	}
 
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Thu, Mar 07, 2019 at 02:47:03PM -0800, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.20 and v5.0
> -stable, respectively.

Thanks for these, they are all now queued up.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 95 bytes --]


Please queue up the following bug fixes for v4.20 and v5.0 -stable,
respectively.

Thank you!

[-- Attachment #2: net_420.mbox --]
[-- Type: Application/Octet-Stream, Size: 133006 bytes --]

From 0c4560d1de4a1d3818b1211a173726d63d93ced3 Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Wed, 6 Mar 2019 14:46:27 +0800
Subject: [PATCH 01/38] connector: fix unsafe usage of ->real_parent

[ Upstream commit 6d2b0f02f5a07a4bf02e4cbc90d7eaa85cac2986 ]

proc_exit_connector() uses ->real_parent lockless. This is not
safe that its parent can go away at any moment, so use RCU to
protect it, and ensure that this task is not released.

[  747.624551] ==================================================================
[  747.632946] BUG: KASAN: use-after-free in proc_exit_connector+0x1f7/0x310
[  747.640686] Read of size 4 at addr ffff88a0276988e0 by task sshd/2882
[  747.648032]
[  747.649804] CPU: 11 PID: 2882 Comm: sshd Tainted: G            E     4.19.26-rc2 #11
[  747.658629] Hardware name: IBM x3550M4 -[7914OFV]-/00AM544, BIOS -[D7E142BUS-1.71]- 07/31/2014
[  747.668419] Call Trace:
[  747.671269]  dump_stack+0xf0/0x19b
[  747.675186]  ? show_regs_print_info+0x5/0x5
[  747.679988]  ? kmsg_dump_rewind_nolock+0x59/0x59
[  747.685302]  print_address_description+0x6a/0x270
[  747.691162]  kasan_report+0x258/0x380
[  747.695835]  ? proc_exit_connector+0x1f7/0x310
[  747.701402]  proc_exit_connector+0x1f7/0x310
[  747.706767]  ? proc_coredump_connector+0x2d0/0x2d0
[  747.712715]  ? _raw_write_unlock_irq+0x29/0x50
[  747.718270]  ? _raw_write_unlock_irq+0x29/0x50
[  747.723820]  ? ___preempt_schedule+0x16/0x18
[  747.729193]  ? ___preempt_schedule+0x16/0x18
[  747.734574]  do_exit+0xa11/0x14f0
[  747.738880]  ? mm_update_next_owner+0x590/0x590
[  747.744525]  ? debug_show_all_locks+0x3c0/0x3c0
[  747.761448]  ? ktime_get_coarse_real_ts64+0xeb/0x1c0
[  747.767589]  ? lockdep_hardirqs_on+0x1a6/0x290
[  747.773154]  ? check_chain_key+0x139/0x1f0
[  747.778345]  ? check_flags.part.35+0x240/0x240
[  747.783908]  ? __lock_acquire+0x2300/0x2300
[  747.789171]  ? _raw_spin_unlock_irqrestore+0x59/0x70
[  747.795316]  ? _raw_spin_unlock_irqrestore+0x59/0x70
[  747.801457]  ? do_raw_spin_unlock+0x10f/0x1e0
[  747.806914]  ? do_raw_spin_trylock+0x120/0x120
[  747.812481]  ? preempt_count_sub+0x14/0xc0
[  747.817645]  ? _raw_spin_unlock+0x2e/0x50
[  747.822708]  ? __handle_mm_fault+0x12db/0x1fa0
[  747.828367]  ? __pmd_alloc+0x2d0/0x2d0
[  747.833143]  ? check_noncircular+0x50/0x50
[  747.838309]  ? match_held_lock+0x7f/0x340
[  747.843380]  ? check_noncircular+0x50/0x50
[  747.848561]  ? handle_mm_fault+0x21a/0x5f0
[  747.853730]  ? check_flags.part.35+0x240/0x240
[  747.859290]  ? check_chain_key+0x139/0x1f0
[  747.864474]  ? __do_page_fault+0x40f/0x760
[  747.869655]  ? __audit_syscall_entry+0x4b/0x1f0
[  747.875319]  ? syscall_trace_enter+0x1d5/0x7b0
[  747.880877]  ? trace_raw_output_preemptirq_template+0x90/0x90
[  747.887895]  ? trace_raw_output_sys_exit+0x80/0x80
[  747.893860]  ? up_read+0x3b/0x90
[  747.898142]  ? stop_critical_timings+0x260/0x260
[  747.903909]  do_group_exit+0xe0/0x1c0
[  747.908591]  ? __x64_sys_exit+0x30/0x30
[  747.913460]  ? trace_raw_output_preemptirq_template+0x90/0x90
[  747.920485]  ? tracer_hardirqs_on+0x270/0x270
[  747.925956]  __x64_sys_exit_group+0x28/0x30
[  747.931214]  do_syscall_64+0x117/0x400
[  747.935988]  ? syscall_return_slowpath+0x2f0/0x2f0
[  747.941931]  ? trace_hardirqs_off_thunk+0x1a/0x1c
[  747.947788]  ? trace_hardirqs_on_caller+0x1d0/0x1d0
[  747.953838]  ? lockdep_sys_exit+0x16/0x8e
[  747.958915]  ? trace_hardirqs_off_thunk+0x1a/0x1c
[  747.964784]  entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  747.971021] RIP: 0033:0x7f572f154c68
[  747.975606] Code: Bad RIP value.
[  747.979791] RSP: 002b:00007ffed2dfaa58 EFLAGS: 00000246 ORIG_RAX: 00000000000000e7
[  747.989324] RAX: ffffffffffffffda RBX: 00007f572f431840 RCX: 00007f572f154c68
[  747.997910] RDX: 0000000000000001 RSI: 000000000000003c RDI: 0000000000000001
[  748.006495] RBP: 0000000000000001 R08: 00000000000000e7 R09: fffffffffffffee0
[  748.015079] R10: 00007f572f4387e8 R11: 0000000000000246 R12: 00007f572f431840
[  748.023664] R13: 000055a7f90f2c50 R14: 000055a7f96e2310 R15: 000055a7f96e2310
[  748.032287]
[  748.034509] Allocated by task 2300:
[  748.038982]  kasan_kmalloc+0xa0/0xd0
[  748.043562]  kmem_cache_alloc_node+0xf5/0x2e0
[  748.049018]  copy_process+0x1781/0x4790
[  748.053884]  _do_fork+0x166/0x9a0
[  748.058163]  do_syscall_64+0x117/0x400
[  748.062943]  entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  748.069180]
[  748.071405] Freed by task 15395:
[  748.075591]  __kasan_slab_free+0x130/0x180
[  748.080752]  kmem_cache_free+0xc2/0x310
[  748.085619]  free_task+0xea/0x130
[  748.089901]  __put_task_struct+0x177/0x230
[  748.095063]  finish_task_switch+0x51b/0x5d0
[  748.100315]  __schedule+0x506/0xfa0
[  748.104791]  schedule+0xca/0x260
[  748.108978]  futex_wait_queue_me+0x27e/0x420
[  748.114333]  futex_wait+0x251/0x550
[  748.118814]  do_futex+0x75b/0xf80
[  748.123097]  __x64_sys_futex+0x231/0x2a0
[  748.128065]  do_syscall_64+0x117/0x400
[  748.132835]  entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  748.139066]
[  748.141289] The buggy address belongs to the object at ffff88a027698000
[  748.141289]  which belongs to the cache task_struct of size 12160
[  748.156589] The buggy address is located 2272 bytes inside of
[  748.156589]  12160-byte region [ffff88a027698000, ffff88a02769af80)
[  748.171114] The buggy address belongs to the page:
[  748.177055] page:ffffea00809da600 count:1 mapcount:0 mapping:ffff888107d01e00 index:0x0 compound_mapcount: 0
[  748.189136] flags: 0x57ffffc0008100(slab|head)
[  748.194688] raw: 0057ffffc0008100 ffffea00809a3200 0000000300000003 ffff888107d01e00
[  748.204424] raw: 0000000000000000 0000000000020002 00000001ffffffff 0000000000000000
[  748.214146] page dumped because: kasan: bad access detected
[  748.220976]
[  748.223197] Memory state around the buggy address:
[  748.229128]  ffff88a027698780: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  748.238271]  ffff88a027698800: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  748.247414] >ffff88a027698880: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  748.256564]                                                        ^
[  748.264267]  ffff88a027698900: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  748.273493]  ffff88a027698980: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  748.282630] ==================================================================

Fixes: b086ff87251b4a4 ("connector: add parent pid and tgid to coredump and exit events")
Signed-off-by: Zhang Yu <zhangyu31@baidu.com>
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Acked-by: Evgeniy Polyakov <zbr@ioremap.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/connector/cn_proc.c | 22 ++++++++++++++++++----
 1 file changed, 18 insertions(+), 4 deletions(-)

diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c
index ed5e42461094..ad48fd52cb53 100644
--- a/drivers/connector/cn_proc.c
+++ b/drivers/connector/cn_proc.c
@@ -250,6 +250,7 @@ void proc_coredump_connector(struct task_struct *task)
 {
 	struct cn_msg *msg;
 	struct proc_event *ev;
+	struct task_struct *parent;
 	__u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
 
 	if (atomic_read(&proc_event_num_listeners) < 1)
@@ -262,8 +263,14 @@ void proc_coredump_connector(struct task_struct *task)
 	ev->what = PROC_EVENT_COREDUMP;
 	ev->event_data.coredump.process_pid = task->pid;
 	ev->event_data.coredump.process_tgid = task->tgid;
-	ev->event_data.coredump.parent_pid = task->real_parent->pid;
-	ev->event_data.coredump.parent_tgid = task->real_parent->tgid;
+
+	rcu_read_lock();
+	if (pid_alive(task)) {
+		parent = rcu_dereference(task->real_parent);
+		ev->event_data.coredump.parent_pid = parent->pid;
+		ev->event_data.coredump.parent_tgid = parent->tgid;
+	}
+	rcu_read_unlock();
 
 	memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
 	msg->ack = 0; /* not used */
@@ -276,6 +283,7 @@ void proc_exit_connector(struct task_struct *task)
 {
 	struct cn_msg *msg;
 	struct proc_event *ev;
+	struct task_struct *parent;
 	__u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
 
 	if (atomic_read(&proc_event_num_listeners) < 1)
@@ -290,8 +298,14 @@ void proc_exit_connector(struct task_struct *task)
 	ev->event_data.exit.process_tgid = task->tgid;
 	ev->event_data.exit.exit_code = task->exit_code;
 	ev->event_data.exit.exit_signal = task->exit_signal;
-	ev->event_data.exit.parent_pid = task->real_parent->pid;
-	ev->event_data.exit.parent_tgid = task->real_parent->tgid;
+
+	rcu_read_lock();
+	if (pid_alive(task)) {
+		parent = rcu_dereference(task->real_parent);
+		ev->event_data.exit.parent_pid = parent->pid;
+		ev->event_data.exit.parent_tgid = parent->tgid;
+	}
+	rcu_read_unlock();
 
 	memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
 	msg->ack = 0; /* not used */
-- 
2.20.1


From d174c206b6a873a680d721a0fc83b2a56602f589 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 10 Mar 2019 10:39:37 -0700
Subject: [PATCH 02/38] gro_cells: make sure device is up in
 gro_cells_receive()

[ Upstream commit 2a5ff07a0eb945f291e361aa6f6becca8340ba46 ]

We keep receiving syzbot reports [1] that show that tunnels do not play
the rcu/IFF_UP rules properly.

At device dismantle phase, gro_cells_destroy() will be called
only after a full rcu grace period is observed after IFF_UP
has been cleared.

This means that IFF_UP needs to be tested before queueing packets
into netif_rx() or gro_cells.

This patch implements the test in gro_cells_receive() because
too many callers do not seem to bother enough.

[1]
BUG: unable to handle kernel paging request at fffff4ca0b9ffffe
PGD 0 P4D 0
Oops: 0000 [#1] PREEMPT SMP KASAN
CPU: 0 PID: 21 Comm: kworker/u4:1 Not tainted 5.0.0+ #97
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Workqueue: netns cleanup_net
RIP: 0010:__skb_unlink include/linux/skbuff.h:1929 [inline]
RIP: 0010:__skb_dequeue include/linux/skbuff.h:1945 [inline]
RIP: 0010:__skb_queue_purge include/linux/skbuff.h:2656 [inline]
RIP: 0010:gro_cells_destroy net/core/gro_cells.c:89 [inline]
RIP: 0010:gro_cells_destroy+0x19d/0x360 net/core/gro_cells.c:78
Code: 03 42 80 3c 20 00 0f 85 53 01 00 00 48 8d 7a 08 49 8b 47 08 49 c7 07 00 00 00 00 48 89 f9 49 c7 47 08 00 00 00 00 48 c1 e9 03 <42> 80 3c 21 00 0f 85 10 01 00 00 48 89 c1 48 89 42 08 48 c1 e9 03
RSP: 0018:ffff8880aa3f79a8 EFLAGS: 00010a02
RAX: 00ffffffffffffe8 RBX: ffffe8ffffc64b70 RCX: 1ffff8ca0b9ffffe
RDX: ffffc6505cffffe8 RSI: ffffffff858410ca RDI: ffffc6505cfffff0
RBP: ffff8880aa3f7a08 R08: ffff8880aa3e8580 R09: fffffbfff1263645
R10: fffffbfff1263644 R11: ffffffff8931b223 R12: dffffc0000000000
R13: 0000000000000000 R14: ffffe8ffffc64b80 R15: ffffe8ffffc64b75
kobject: 'loop2' (000000004bd7d84a): kobject_uevent_env
FS:  0000000000000000(0000) GS:ffff8880ae800000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: fffff4ca0b9ffffe CR3: 0000000094941000 CR4: 00000000001406f0
Call Trace:
kobject: 'loop2' (000000004bd7d84a): fill_kobj_path: path = '/devices/virtual/block/loop2'
 ip_tunnel_dev_free+0x19/0x60 net/ipv4/ip_tunnel.c:1010
 netdev_run_todo+0x51c/0x7d0 net/core/dev.c:8970
 rtnl_unlock+0xe/0x10 net/core/rtnetlink.c:116
 ip_tunnel_delete_nets+0x423/0x5f0 net/ipv4/ip_tunnel.c:1124
 vti_exit_batch_net+0x23/0x30 net/ipv4/ip_vti.c:495
 ops_exit_list.isra.0+0x105/0x160 net/core/net_namespace.c:156
 cleanup_net+0x3fb/0x960 net/core/net_namespace.c:551
 process_one_work+0x98e/0x1790 kernel/workqueue.c:2173
 worker_thread+0x98/0xe40 kernel/workqueue.c:2319
 kthread+0x357/0x430 kernel/kthread.c:246
 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:352
Modules linked in:
CR2: fffff4ca0b9ffffe
   [ end trace 513fc9c1338d1cb3 ]
RIP: 0010:__skb_unlink include/linux/skbuff.h:1929 [inline]
RIP: 0010:__skb_dequeue include/linux/skbuff.h:1945 [inline]
RIP: 0010:__skb_queue_purge include/linux/skbuff.h:2656 [inline]
RIP: 0010:gro_cells_destroy net/core/gro_cells.c:89 [inline]
RIP: 0010:gro_cells_destroy+0x19d/0x360 net/core/gro_cells.c:78
Code: 03 42 80 3c 20 00 0f 85 53 01 00 00 48 8d 7a 08 49 8b 47 08 49 c7 07 00 00 00 00 48 89 f9 49 c7 47 08 00 00 00 00 48 c1 e9 03 <42> 80 3c 21 00 0f 85 10 01 00 00 48 89 c1 48 89 42 08 48 c1 e9 03
RSP: 0018:ffff8880aa3f79a8 EFLAGS: 00010a02
RAX: 00ffffffffffffe8 RBX: ffffe8ffffc64b70 RCX: 1ffff8ca0b9ffffe
RDX: ffffc6505cffffe8 RSI: ffffffff858410ca RDI: ffffc6505cfffff0
RBP: ffff8880aa3f7a08 R08: ffff8880aa3e8580 R09: fffffbfff1263645
R10: fffffbfff1263644 R11: ffffffff8931b223 R12: dffffc0000000000
kobject: 'loop3' (00000000e4ee57a6): kobject_uevent_env
R13: 0000000000000000 R14: ffffe8ffffc64b80 R15: ffffe8ffffc64b75
FS:  0000000000000000(0000) GS:ffff8880ae800000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: fffff4ca0b9ffffe CR3: 0000000094941000 CR4: 00000000001406f0

Fixes: c9e6bc644e55 ("net: add gro_cells infrastructure")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/gro_cells.c | 22 ++++++++++++++++++----
 1 file changed, 18 insertions(+), 4 deletions(-)

diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c
index acf45ddbe924..e095fb871d91 100644
--- a/net/core/gro_cells.c
+++ b/net/core/gro_cells.c
@@ -13,22 +13,36 @@ int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb)
 {
 	struct net_device *dev = skb->dev;
 	struct gro_cell *cell;
+	int res;
 
-	if (!gcells->cells || skb_cloned(skb) || netif_elide_gro(dev))
-		return netif_rx(skb);
+	rcu_read_lock();
+	if (unlikely(!(dev->flags & IFF_UP)))
+		goto drop;
+
+	if (!gcells->cells || skb_cloned(skb) || netif_elide_gro(dev)) {
+		res = netif_rx(skb);
+		goto unlock;
+	}
 
 	cell = this_cpu_ptr(gcells->cells);
 
 	if (skb_queue_len(&cell->napi_skbs) > netdev_max_backlog) {
+drop:
 		atomic_long_inc(&dev->rx_dropped);
 		kfree_skb(skb);
-		return NET_RX_DROP;
+		res = NET_RX_DROP;
+		goto unlock;
 	}
 
 	__skb_queue_tail(&cell->napi_skbs, skb);
 	if (skb_queue_len(&cell->napi_skbs) == 1)
 		napi_schedule(&cell->napi);
-	return NET_RX_SUCCESS;
+
+	res = NET_RX_SUCCESS;
+
+unlock:
+	rcu_read_unlock();
+	return res;
 }
 EXPORT_SYMBOL(gro_cells_receive);
 
-- 
2.20.1


From 4c56fdb1451055fbaecdec728643ede8fe38b815 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 6 Mar 2019 10:42:53 +0100
Subject: [PATCH 03/38] ipv4/route: fail early when inet dev is missing

[ Upstream commit 22c74764aa2943ecdf9f07c900d8a9c8ba6c9265 ]

If a non local multicast packet reaches ip_route_input_rcu() while
the ingress device IPv4 private data (in_dev) is NULL, we end up
doing a NULL pointer dereference in IN_DEV_MFORWARD().

Since the later call to ip_route_input_mc() is going to fail if
!in_dev, we can fail early in such scenario and avoid the dangerous
code path.

v1 -> v2:
 - clarified the commit message, no code changes

Reported-by: Tianhao Zhao <tizhao@redhat.com>
Fixes: e58e41596811 ("net: Enable support for VRF with ipv4 multicast")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index efe45200db4f..a56c73ee965b 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2144,12 +2144,13 @@ int ip_route_input_rcu(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 		int our = 0;
 		int err = -EINVAL;
 
-		if (in_dev)
-			our = ip_check_mc_rcu(in_dev, daddr, saddr,
-					      ip_hdr(skb)->protocol);
+		if (!in_dev)
+			return err;
+		our = ip_check_mc_rcu(in_dev, daddr, saddr,
+				      ip_hdr(skb)->protocol);
 
 		/* check l3 master if no match yet */
-		if ((!in_dev || !our) && netif_is_l3_slave(dev)) {
+		if (!our && netif_is_l3_slave(dev)) {
 			struct in_device *l3_in_dev;
 
 			l3_in_dev = __in_dev_get_rcu(skb->dev);
-- 
2.20.1


From f8aa47da38f1511f0c6fb4fd17cd2008d820da2a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 12 Mar 2019 06:50:11 -0700
Subject: [PATCH 04/38] l2tp: fix infoleak in l2tp_ip6_recvmsg()

[ Upstream commit 163d1c3d6f17556ed3c340d3789ea93be95d6c28 ]

Back in 2013 Hannes took care of most of such leaks in commit
bceaa90240b6 ("inet: prevent leakage of uninitialized memory to user in recv syscalls")

But the bug in l2tp_ip6_recvmsg() has not been fixed.

syzbot report :

BUG: KMSAN: kernel-infoleak in _copy_to_user+0x16b/0x1f0 lib/usercopy.c:32
CPU: 1 PID: 10996 Comm: syz-executor362 Not tainted 5.0.0+ #11
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x173/0x1d0 lib/dump_stack.c:113
 kmsan_report+0x12e/0x2a0 mm/kmsan/kmsan.c:600
 kmsan_internal_check_memory+0x9f4/0xb10 mm/kmsan/kmsan.c:694
 kmsan_copy_to_user+0xab/0xc0 mm/kmsan/kmsan_hooks.c:601
 _copy_to_user+0x16b/0x1f0 lib/usercopy.c:32
 copy_to_user include/linux/uaccess.h:174 [inline]
 move_addr_to_user+0x311/0x570 net/socket.c:227
 ___sys_recvmsg+0xb65/0x1310 net/socket.c:2283
 do_recvmmsg+0x646/0x10c0 net/socket.c:2390
 __sys_recvmmsg net/socket.c:2469 [inline]
 __do_sys_recvmmsg net/socket.c:2492 [inline]
 __se_sys_recvmmsg+0x1d1/0x350 net/socket.c:2485
 __x64_sys_recvmmsg+0x62/0x80 net/socket.c:2485
 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291
 entry_SYSCALL_64_after_hwframe+0x63/0xe7
RIP: 0033:0x445819
Code: e8 6c b6 02 00 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 2b 12 fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f64453eddb8 EFLAGS: 00000246 ORIG_RAX: 000000000000012b
RAX: ffffffffffffffda RBX: 00000000006dac28 RCX: 0000000000445819
RDX: 0000000000000005 RSI: 0000000020002f80 RDI: 0000000000000003
RBP: 00000000006dac20 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00000000006dac2c
R13: 00007ffeba8f87af R14: 00007f64453ee9c0 R15: 20c49ba5e353f7cf

Local variable description: ----addr@___sys_recvmsg
Variable was created at:
 ___sys_recvmsg+0xf6/0x1310 net/socket.c:2244
 do_recvmmsg+0x646/0x10c0 net/socket.c:2390

Bytes 0-31 of 32 are uninitialized
Memory access of size 32 starts at ffff8880ae62fbb0
Data copied to user address 0000000020000000

Fixes: a32e0eec7042 ("l2tp: introduce L2TPv3 IP encapsulation support for IPv6")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ip6.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 0ae6899edac0..37a69df17cab 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -674,9 +674,6 @@ static int l2tp_ip6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	if (flags & MSG_OOB)
 		goto out;
 
-	if (addr_len)
-		*addr_len = sizeof(*lsa);
-
 	if (flags & MSG_ERRQUEUE)
 		return ipv6_recv_error(sk, msg, len, addr_len);
 
@@ -706,6 +703,7 @@ static int l2tp_ip6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		lsa->l2tp_conn_id = 0;
 		if (ipv6_addr_type(&lsa->l2tp_addr) & IPV6_ADDR_LINKLOCAL)
 			lsa->l2tp_scope_id = inet6_iif(skb);
+		*addr_len = sizeof(*lsa);
 	}
 
 	if (np->rxopt.all)
-- 
2.20.1


From 97129facd4d9158ca976146774badab42080f421 Mon Sep 17 00:00:00 2001
From: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Date: Mon, 11 Mar 2019 13:39:39 -0400
Subject: [PATCH 05/38] lan743x: Fix RX Kernel Panic

[ Upstream commit dd9d9f5907bb475f8b1796c47d4ecc7fb9b72136 ]

It has been noticed that running the speed test at
www.speedtest.net occasionally causes a kernel panic.

Investigation revealed that under this test RX buffer allocation
sometimes fails and returns NULL. But the lan743x driver did
not handle this case.

This patch fixes this issue by attempting to allocate a buffer
before sending the new rx packet to the OS. If the allocation
fails then the new rx packet is dropped and the existing buffer
is reused in the DMA ring.

Updates for v2:
    Additional 2 locations where allocation was not checked,
        has been changed to reuse existing buffer.

Fixes: 23f0703c125b ("lan743x: Add main source files for new lan743x driver")
Signed-off-by: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/lan743x_main.c | 46 +++++++++++++------
 1 file changed, 32 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index 671ea75d0a4a..9c7a6799ac00 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -1902,7 +1902,17 @@ static int lan743x_rx_next_index(struct lan743x_rx *rx, int index)
 	return ((++index) % rx->ring_size);
 }
 
-static int lan743x_rx_allocate_ring_element(struct lan743x_rx *rx, int index)
+static struct sk_buff *lan743x_rx_allocate_skb(struct lan743x_rx *rx)
+{
+	int length = 0;
+
+	length = (LAN743X_MAX_FRAME_SIZE + ETH_HLEN + 4 + RX_HEAD_PADDING);
+	return __netdev_alloc_skb(rx->adapter->netdev,
+				  length, GFP_ATOMIC | GFP_DMA);
+}
+
+static int lan743x_rx_init_ring_element(struct lan743x_rx *rx, int index,
+					struct sk_buff *skb)
 {
 	struct lan743x_rx_buffer_info *buffer_info;
 	struct lan743x_rx_descriptor *descriptor;
@@ -1911,9 +1921,7 @@ static int lan743x_rx_allocate_ring_element(struct lan743x_rx *rx, int index)
 	length = (LAN743X_MAX_FRAME_SIZE + ETH_HLEN + 4 + RX_HEAD_PADDING);
 	descriptor = &rx->ring_cpu_ptr[index];
 	buffer_info = &rx->buffer_info[index];
-	buffer_info->skb = __netdev_alloc_skb(rx->adapter->netdev,
-					      length,
-					      GFP_ATOMIC | GFP_DMA);
+	buffer_info->skb = skb;
 	if (!(buffer_info->skb))
 		return -ENOMEM;
 	buffer_info->dma_ptr = dma_map_single(&rx->adapter->pdev->dev,
@@ -2060,8 +2068,19 @@ static int lan743x_rx_process_packet(struct lan743x_rx *rx)
 		/* packet is available */
 		if (first_index == last_index) {
 			/* single buffer packet */
+			struct sk_buff *new_skb = NULL;
 			int packet_length;
 
+			new_skb = lan743x_rx_allocate_skb(rx);
+			if (!new_skb) {
+				/* failed to allocate next skb.
+				 * Memory is very low.
+				 * Drop this packet and reuse buffer.
+				 */
+				lan743x_rx_reuse_ring_element(rx, first_index);
+				goto process_extension;
+			}
+
 			buffer_info = &rx->buffer_info[first_index];
 			skb = buffer_info->skb;
 			descriptor = &rx->ring_cpu_ptr[first_index];
@@ -2081,7 +2100,7 @@ static int lan743x_rx_process_packet(struct lan743x_rx *rx)
 			skb_put(skb, packet_length - 4);
 			skb->protocol = eth_type_trans(skb,
 						       rx->adapter->netdev);
-			lan743x_rx_allocate_ring_element(rx, first_index);
+			lan743x_rx_init_ring_element(rx, first_index, new_skb);
 		} else {
 			int index = first_index;
 
@@ -2094,26 +2113,23 @@ static int lan743x_rx_process_packet(struct lan743x_rx *rx)
 			if (first_index <= last_index) {
 				while ((index >= first_index) &&
 				       (index <= last_index)) {
-					lan743x_rx_release_ring_element(rx,
-									index);
-					lan743x_rx_allocate_ring_element(rx,
-									 index);
+					lan743x_rx_reuse_ring_element(rx,
+								      index);
 					index = lan743x_rx_next_index(rx,
 								      index);
 				}
 			} else {
 				while ((index >= first_index) ||
 				       (index <= last_index)) {
-					lan743x_rx_release_ring_element(rx,
-									index);
-					lan743x_rx_allocate_ring_element(rx,
-									 index);
+					lan743x_rx_reuse_ring_element(rx,
+								      index);
 					index = lan743x_rx_next_index(rx,
 								      index);
 				}
 			}
 		}
 
+process_extension:
 		if (extension_index >= 0) {
 			descriptor = &rx->ring_cpu_ptr[extension_index];
 			buffer_info = &rx->buffer_info[extension_index];
@@ -2290,7 +2306,9 @@ static int lan743x_rx_ring_init(struct lan743x_rx *rx)
 
 	rx->last_head = 0;
 	for (index = 0; index < rx->ring_size; index++) {
-		ret = lan743x_rx_allocate_ring_element(rx, index);
+		struct sk_buff *new_skb = lan743x_rx_allocate_skb(rx);
+
+		ret = lan743x_rx_init_ring_element(rx, index, new_skb);
 		if (ret)
 			goto cleanup;
 	}
-- 
2.20.1


From 3c328cdd0077c566c716586a4c8d9893ca034521 Mon Sep 17 00:00:00 2001
From: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Date: Wed, 13 Mar 2019 15:55:48 -0400
Subject: [PATCH 06/38] lan743x: Fix TX Stall Issue

[ Upstream commit deb6bfabdbb634e91f36a4e9cb00a7137d72d886 ]

It has been observed that tx queue may stall while downloading
from certain web sites (example www.speedtest.net)

The cause has been tracked down to a corner case where
the tx interrupt vector was disabled automatically, but
was not re enabled later.

The lan743x has two mechanisms to enable/disable individual
interrupts. Interrupts can be enabled/disabled by individual
source, and they can also be enabled/disabled by individual
vector which has been mapped to the source. Both must be
enabled for interrupts to work properly.

The TX code path, primarily uses the interrupt enable/disable of
the TX source bit, while leaving the vector enabled all the time.

However, while investigating this issue it was noticed that
the driver requested the use of the vector auto clear feature.

The test above revealed a case where the vector enable was
cleared unintentionally.

This patch fixes the issue by deleting the lines that request
the vector auto clear feature to be used.

Fixes: 23f0703c125b ("lan743x: Add main source files for new lan743x driver")
Signed-off-by: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/lan743x_main.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index 9c7a6799ac00..9bbe41abe854 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -585,8 +585,7 @@ static int lan743x_intr_open(struct lan743x_adapter *adapter)
 
 		if (adapter->csr.flags &
 		   LAN743X_CSR_FLAG_SUPPORTS_INTR_AUTO_SET_CLR) {
-			flags = LAN743X_VECTOR_FLAG_VECTOR_ENABLE_AUTO_CLEAR |
-				LAN743X_VECTOR_FLAG_VECTOR_ENABLE_AUTO_SET |
+			flags = LAN743X_VECTOR_FLAG_VECTOR_ENABLE_AUTO_SET |
 				LAN743X_VECTOR_FLAG_SOURCE_ENABLE_AUTO_SET |
 				LAN743X_VECTOR_FLAG_SOURCE_ENABLE_AUTO_CLEAR |
 				LAN743X_VECTOR_FLAG_SOURCE_STATUS_AUTO_CLEAR;
@@ -599,12 +598,6 @@ static int lan743x_intr_open(struct lan743x_adapter *adapter)
 			/* map TX interrupt to vector */
 			int_vec_map1 |= INT_VEC_MAP1_TX_VEC_(index, vector);
 			lan743x_csr_write(adapter, INT_VEC_MAP1, int_vec_map1);
-			if (flags &
-			    LAN743X_VECTOR_FLAG_VECTOR_ENABLE_AUTO_CLEAR) {
-				int_vec_en_auto_clr |= INT_VEC_EN_(vector);
-				lan743x_csr_write(adapter, INT_VEC_EN_AUTO_CLR,
-						  int_vec_en_auto_clr);
-			}
 
 			/* Remove TX interrupt from shared mask */
 			intr->vector_list[0].int_mask &= ~int_bit;
-- 
2.20.1


From 15320c2334ccc898df9f0d826664175dfeade34c Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Wed, 6 Mar 2019 11:26:37 +0800
Subject: [PATCH 07/38] net: hns3: add dma_rmb() for rx description

[ Upstream commit d394d33bee22421b39a0bcdc51ca6d68ba308625 ]

HW can not guarantee complete write desc->rx.size, even though
HNS3_RXD_VLD_B has been set. Driver needs to add dma_rmb()
instruction to make sure desc->rx.size is always valid.

Fixes: e55970950556 ("net: hns3: Add handling of GRO Pkts not fully RX'ed in NAPI poll")
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index d424d5bc0507..b396e934e83f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -2373,6 +2373,9 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
 	length = le16_to_cpu(desc->rx.size);
 	bd_base_info = le32_to_cpu(desc->rx.bd_base_info);
 
+	/* make sure HW write desc complete */
+	dma_rmb();
+
 	/* Check valid BD */
 	if (unlikely(!hnae3_get_bit(bd_base_info, HNS3_RXD_VLD_B)))
 		return -EFAULT;
-- 
2.20.1


From 7626f84d865a7da33b091511871605dd6cb2d356 Mon Sep 17 00:00:00 2001
From: Mao Wenan <maowenan@huawei.com>
Date: Wed, 6 Mar 2019 22:45:01 +0800
Subject: [PATCH 08/38] net: hsr: fix memory leak in hsr_dev_finalize()

[ Upstream commit 3dc6da493a29dbeda9f13b637bd9c02c414b2261 ]

If hsr_add_port(hsr, hsr_dev, HSR_PT_MASTER) failed to
add port, it directly returns res and forgets to free the node
that allocated in hsr_create_self_node(), and forgets to delete
the node->mac_list linked in hsr->self_node_db.

BUG: memory leak
unreferenced object 0xffff8881cfa0c780 (size 64):
  comm "syz-executor.0", pid 2077, jiffies 4294717969 (age 2415.377s)
  hex dump (first 32 bytes):
    e0 c7 a0 cf 81 88 ff ff 00 02 00 00 00 00 ad de  ................
    00 e6 49 cd 81 88 ff ff c0 9b 87 d0 81 88 ff ff  ..I.............
  backtrace:
    [<00000000e2ff5070>] hsr_dev_finalize+0x736/0x960 [hsr]
    [<000000003ed2e597>] hsr_newlink+0x2b2/0x3e0 [hsr]
    [<000000003fa8c6b6>] __rtnl_newlink+0xf1f/0x1600 net/core/rtnetlink.c:3182
    [<000000001247a7ad>] rtnl_newlink+0x66/0x90 net/core/rtnetlink.c:3240
    [<00000000e7d1b61d>] rtnetlink_rcv_msg+0x54e/0xb90 net/core/rtnetlink.c:5130
    [<000000005556bd3a>] netlink_rcv_skb+0x129/0x340 net/netlink/af_netlink.c:2477
    [<00000000741d5ee6>] netlink_unicast_kernel net/netlink/af_netlink.c:1310 [inline]
    [<00000000741d5ee6>] netlink_unicast+0x49a/0x650 net/netlink/af_netlink.c:1336
    [<000000009d56f9b7>] netlink_sendmsg+0x88b/0xdf0 net/netlink/af_netlink.c:1917
    [<0000000046b35c59>] sock_sendmsg_nosec net/socket.c:621 [inline]
    [<0000000046b35c59>] sock_sendmsg+0xc3/0x100 net/socket.c:631
    [<00000000d208adc9>] __sys_sendto+0x33e/0x560 net/socket.c:1786
    [<00000000b582837a>] __do_sys_sendto net/socket.c:1798 [inline]
    [<00000000b582837a>] __se_sys_sendto net/socket.c:1794 [inline]
    [<00000000b582837a>] __x64_sys_sendto+0xdd/0x1b0 net/socket.c:1794
    [<00000000c866801d>] do_syscall_64+0x147/0x600 arch/x86/entry/common.c:290
    [<00000000fea382d9>] entry_SYSCALL_64_after_hwframe+0x49/0xbe
    [<00000000e01dacb3>] 0xffffffffffffffff

Fixes: c5a759117210 ("net/hsr: Use list_head (and rcu) instead of array for slave devices.")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Mao Wenan <maowenan@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/hsr/hsr_device.c   |  4 +++-
 net/hsr/hsr_framereg.c | 12 ++++++++++++
 net/hsr/hsr_framereg.h |  1 +
 3 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index b8cd43c9ed5b..c4676bacb8db 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -486,7 +486,7 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2],
 
 	res = hsr_add_port(hsr, hsr_dev, HSR_PT_MASTER);
 	if (res)
-		return res;
+		goto err_add_port;
 
 	res = register_netdevice(hsr_dev);
 	if (res)
@@ -506,6 +506,8 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2],
 fail:
 	hsr_for_each_port(hsr, port)
 		hsr_del_port(port);
+err_add_port:
+	hsr_del_node(&hsr->self_node_db);
 
 	return res;
 }
diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c
index 286ceb41ac0c..9af16cb68f76 100644
--- a/net/hsr/hsr_framereg.c
+++ b/net/hsr/hsr_framereg.c
@@ -124,6 +124,18 @@ int hsr_create_self_node(struct list_head *self_node_db,
 	return 0;
 }
 
+void hsr_del_node(struct list_head *self_node_db)
+{
+	struct hsr_node *node;
+
+	rcu_read_lock();
+	node = list_first_or_null_rcu(self_node_db, struct hsr_node, mac_list);
+	rcu_read_unlock();
+	if (node) {
+		list_del_rcu(&node->mac_list);
+		kfree(node);
+	}
+}
 
 /* Allocate an hsr_node and add it to node_db. 'addr' is the node's AddressA;
  * seq_out is used to initialize filtering of outgoing duplicate frames
diff --git a/net/hsr/hsr_framereg.h b/net/hsr/hsr_framereg.h
index 370b45998121..531fd3dfcac1 100644
--- a/net/hsr/hsr_framereg.h
+++ b/net/hsr/hsr_framereg.h
@@ -16,6 +16,7 @@
 
 struct hsr_node;
 
+void hsr_del_node(struct list_head *self_node_db);
 struct hsr_node *hsr_add_node(struct list_head *node_db, unsigned char addr[],
 			      u16 seq_out);
 struct hsr_node *hsr_get_node(struct hsr_port *port, struct sk_buff *skb,
-- 
2.20.1


From 95bd9b8d603d27b21b7b47433430cecf7e982ee0 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 7 Mar 2019 09:36:33 -0800
Subject: [PATCH 09/38] net/hsr: fix possible crash in add_timer()

[ Upstream commit 1e027960edfaa6a43f9ca31081729b716598112b ]

syzbot found another add_timer() issue, this time in net/hsr [1]

Let's use mod_timer() which is safe.

[1]
kernel BUG at kernel/time/timer.c:1136!
invalid opcode: 0000 [#1] PREEMPT SMP KASAN
CPU: 0 PID: 15909 Comm: syz-executor.3 Not tainted 5.0.0+ #97
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
kobject: 'loop2' (00000000f5629718): kobject_uevent_env
RIP: 0010:add_timer kernel/time/timer.c:1136 [inline]
RIP: 0010:add_timer+0x654/0xbe0 kernel/time/timer.c:1134
Code: 0f 94 c5 31 ff 44 89 ee e8 09 61 0f 00 45 84 ed 0f 84 77 fd ff ff e8 bb 5f 0f 00 e8 07 10 a0 ff e9 68 fd ff ff e8 ac 5f 0f 00 <0f> 0b e8 a5 5f 0f 00 0f 0b e8 9e 5f 0f 00 4c 89 b5 58 ff ff ff e9
RSP: 0018:ffff8880656eeca0 EFLAGS: 00010246
kobject: 'loop2' (00000000f5629718): fill_kobj_path: path = '/devices/virtual/block/loop2'
RAX: 0000000000040000 RBX: 1ffff1100caddd9a RCX: ffffc9000c436000
RDX: 0000000000040000 RSI: ffffffff816056c4 RDI: ffff88806a2f6cc8
RBP: ffff8880656eed58 R08: ffff888067f4a300 R09: ffff888067f4abc8
R10: 0000000000000000 R11: 0000000000000000 R12: ffff88806a2f6cc0
R13: dffffc0000000000 R14: 0000000000000001 R15: ffff8880656eed30
FS:  00007fc2019bf700(0000) GS:ffff8880ae800000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000738000 CR3: 0000000067e8e000 CR4: 00000000001406f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 hsr_check_announce net/hsr/hsr_device.c:99 [inline]
 hsr_check_carrier_and_operstate+0x567/0x6f0 net/hsr/hsr_device.c:120
 hsr_netdev_notify+0x297/0xa00 net/hsr/hsr_main.c:51
 notifier_call_chain+0xc7/0x240 kernel/notifier.c:93
 __raw_notifier_call_chain kernel/notifier.c:394 [inline]
 raw_notifier_call_chain+0x2e/0x40 kernel/notifier.c:401
 call_netdevice_notifiers_info+0x3f/0x90 net/core/dev.c:1739
 call_netdevice_notifiers_extack net/core/dev.c:1751 [inline]
 call_netdevice_notifiers net/core/dev.c:1765 [inline]
 dev_open net/core/dev.c:1436 [inline]
 dev_open+0x143/0x160 net/core/dev.c:1424
 team_port_add drivers/net/team/team.c:1203 [inline]
 team_add_slave+0xa07/0x15d0 drivers/net/team/team.c:1933
 do_set_master net/core/rtnetlink.c:2358 [inline]
 do_set_master+0x1d4/0x230 net/core/rtnetlink.c:2332
 do_setlink+0x966/0x3510 net/core/rtnetlink.c:2493
 rtnl_setlink+0x271/0x3b0 net/core/rtnetlink.c:2747
 rtnetlink_rcv_msg+0x465/0xb00 net/core/rtnetlink.c:5192
 netlink_rcv_skb+0x17a/0x460 net/netlink/af_netlink.c:2485
 rtnetlink_rcv+0x1d/0x30 net/core/rtnetlink.c:5210
 netlink_unicast_kernel net/netlink/af_netlink.c:1310 [inline]
 netlink_unicast+0x536/0x720 net/netlink/af_netlink.c:1336
 netlink_sendmsg+0x8ae/0xd70 net/netlink/af_netlink.c:1925
 sock_sendmsg_nosec net/socket.c:622 [inline]
 sock_sendmsg+0xdd/0x130 net/socket.c:632
 sock_write_iter+0x27c/0x3e0 net/socket.c:923
 call_write_iter include/linux/fs.h:1869 [inline]
 do_iter_readv_writev+0x5e0/0x8e0 fs/read_write.c:680
 do_iter_write fs/read_write.c:956 [inline]
 do_iter_write+0x184/0x610 fs/read_write.c:937
 vfs_writev+0x1b3/0x2f0 fs/read_write.c:1001
 do_writev+0xf6/0x290 fs/read_write.c:1036
 __do_sys_writev fs/read_write.c:1109 [inline]
 __se_sys_writev fs/read_write.c:1106 [inline]
 __x64_sys_writev+0x75/0xb0 fs/read_write.c:1106
 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x457f29
Code: ad b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007fc2019bec78 EFLAGS: 00000246 ORIG_RAX: 0000000000000014
RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000457f29
RDX: 0000000000000001 RSI: 00000000200000c0 RDI: 0000000000000003
RBP: 000000000073bf00 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00007fc2019bf6d4
R13: 00000000004c4a60 R14: 00000000004dd218 R15: 00000000ffffffff

Fixes: f421436a591d ("net/hsr: Add support for the High-availability Seamless Redundancy protocol (HSRv0)")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Arvid Brodin <arvid.brodin@alten.se>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/hsr/hsr_device.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index c4676bacb8db..a97bf326b231 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -94,9 +94,8 @@ static void hsr_check_announce(struct net_device *hsr_dev,
 			&& (old_operstate != IF_OPER_UP)) {
 		/* Went up */
 		hsr->announce_count = 0;
-		hsr->announce_timer.expires = jiffies +
-				msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL);
-		add_timer(&hsr->announce_timer);
+		mod_timer(&hsr->announce_timer,
+			  jiffies + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL));
 	}
 
 	if ((hsr_dev->operstate != IF_OPER_UP) && (old_operstate == IF_OPER_UP))
@@ -332,6 +331,7 @@ static void hsr_announce(struct timer_list *t)
 {
 	struct hsr_priv *hsr;
 	struct hsr_port *master;
+	unsigned long interval;
 
 	hsr = from_timer(hsr, t, announce_timer);
 
@@ -343,18 +343,16 @@ static void hsr_announce(struct timer_list *t)
 				hsr->protVersion);
 		hsr->announce_count++;
 
-		hsr->announce_timer.expires = jiffies +
-				msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL);
+		interval = msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL);
 	} else {
 		send_hsr_supervision_frame(master, HSR_TLV_LIFE_CHECK,
 				hsr->protVersion);
 
-		hsr->announce_timer.expires = jiffies +
-				msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL);
+		interval = msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL);
 	}
 
 	if (is_admin_up(master->dev))
-		add_timer(&hsr->announce_timer);
+		mod_timer(&hsr->announce_timer, jiffies + interval);
 
 	rcu_read_unlock();
 }
-- 
2.20.1


From d853bcb0d48be9a166d87a7bde160e2e040ef8d8 Mon Sep 17 00:00:00 2001
From: Miaohe Lin <linmiaohe@huawei.com>
Date: Mon, 11 Mar 2019 16:29:32 +0800
Subject: [PATCH 10/38] net: sit: fix UBSAN Undefined behaviour in check_6rd

[ Upstream commit a843dc4ebaecd15fca1f4d35a97210f72ea1473b ]

In func check_6rd,tunnel->ip6rd.relay_prefixlen may equal to
32,so UBSAN complain about it.

UBSAN: Undefined behaviour in net/ipv6/sit.c:781:47
shift exponent 32 is too large for 32-bit type 'unsigned int'
CPU: 6 PID: 20036 Comm: syz-executor.0 Not tainted 4.19.27 #2
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1
04/01/2014
Call Trace:
__dump_stack lib/dump_stack.c:77 [inline]
dump_stack+0xca/0x13e lib/dump_stack.c:113
ubsan_epilogue+0xe/0x81 lib/ubsan.c:159
__ubsan_handle_shift_out_of_bounds+0x293/0x2e8 lib/ubsan.c:425
check_6rd.constprop.9+0x433/0x4e0 net/ipv6/sit.c:781
try_6rd net/ipv6/sit.c:806 [inline]
ipip6_tunnel_xmit net/ipv6/sit.c:866 [inline]
sit_tunnel_xmit+0x141c/0x2720 net/ipv6/sit.c:1033
__netdev_start_xmit include/linux/netdevice.h:4300 [inline]
netdev_start_xmit include/linux/netdevice.h:4309 [inline]
xmit_one net/core/dev.c:3243 [inline]
dev_hard_start_xmit+0x17c/0x780 net/core/dev.c:3259
__dev_queue_xmit+0x1656/0x2500 net/core/dev.c:3829
neigh_output include/net/neighbour.h:501 [inline]
ip6_finish_output2+0xa36/0x2290 net/ipv6/ip6_output.c:120
ip6_finish_output+0x3e7/0xa20 net/ipv6/ip6_output.c:154
NF_HOOK_COND include/linux/netfilter.h:278 [inline]
ip6_output+0x1e2/0x720 net/ipv6/ip6_output.c:171
dst_output include/net/dst.h:444 [inline]
ip6_local_out+0x99/0x170 net/ipv6/output_core.c:176
ip6_send_skb+0x9d/0x2f0 net/ipv6/ip6_output.c:1697
ip6_push_pending_frames+0xc0/0x100 net/ipv6/ip6_output.c:1717
rawv6_push_pending_frames net/ipv6/raw.c:616 [inline]
rawv6_sendmsg+0x2435/0x3530 net/ipv6/raw.c:946
inet_sendmsg+0xf8/0x5c0 net/ipv4/af_inet.c:798
sock_sendmsg_nosec net/socket.c:621 [inline]
sock_sendmsg+0xc8/0x110 net/socket.c:631
___sys_sendmsg+0x6cf/0x890 net/socket.c:2114
__sys_sendmsg+0xf0/0x1b0 net/socket.c:2152
do_syscall_64+0xc8/0x580 arch/x86/entry/common.c:290
entry_SYSCALL_64_after_hwframe+0x49/0xbe

Signed-off-by: linmiaohe <linmiaohe@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 09e440e8dfae..07e21a82ce4c 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -778,8 +778,9 @@ static bool check_6rd(struct ip_tunnel *tunnel, const struct in6_addr *v6dst,
 		pbw0 = tunnel->ip6rd.prefixlen >> 5;
 		pbi0 = tunnel->ip6rd.prefixlen & 0x1f;
 
-		d = (ntohl(v6dst->s6_addr32[pbw0]) << pbi0) >>
-		    tunnel->ip6rd.relay_prefixlen;
+		d = tunnel->ip6rd.relay_prefixlen < 32 ?
+			(ntohl(v6dst->s6_addr32[pbw0]) << pbi0) >>
+		    tunnel->ip6rd.relay_prefixlen : 0;
 
 		pbi1 = pbi0 - tunnel->ip6rd.relay_prefixlen;
 		if (pbi1 > 0)
-- 
2.20.1


From 9e578e183a351555ee8b395b14a1eb8787e98563 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 10 Mar 2019 09:07:14 -0700
Subject: [PATCH 11/38] net/x25: fix use-after-free in x25_device_event()

[ Upstream commit 95d6ebd53c79522bf9502dbc7e89e0d63f94dae4 ]

In case of failure x25_connect() does a x25_neigh_put(x25->neighbour)
but forgets to clear x25->neighbour pointer, thus triggering use-after-free.

Since the socket is visible in x25_list, we need to hold x25_list_lock
to protect the operation.

syzbot report :

BUG: KASAN: use-after-free in x25_kill_by_device net/x25/af_x25.c:217 [inline]
BUG: KASAN: use-after-free in x25_device_event+0x296/0x2b0 net/x25/af_x25.c:252
Read of size 8 at addr ffff8880a030edd0 by task syz-executor003/7854

CPU: 0 PID: 7854 Comm: syz-executor003 Not tainted 5.0.0+ #97
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 print_address_description.cold+0x7c/0x20d mm/kasan/report.c:187
 kasan_report.cold+0x1b/0x40 mm/kasan/report.c:317
 __asan_report_load8_noabort+0x14/0x20 mm/kasan/generic_report.c:135
 x25_kill_by_device net/x25/af_x25.c:217 [inline]
 x25_device_event+0x296/0x2b0 net/x25/af_x25.c:252
 notifier_call_chain+0xc7/0x240 kernel/notifier.c:93
 __raw_notifier_call_chain kernel/notifier.c:394 [inline]
 raw_notifier_call_chain+0x2e/0x40 kernel/notifier.c:401
 call_netdevice_notifiers_info+0x3f/0x90 net/core/dev.c:1739
 call_netdevice_notifiers_extack net/core/dev.c:1751 [inline]
 call_netdevice_notifiers net/core/dev.c:1765 [inline]
 __dev_notify_flags+0x1e9/0x2c0 net/core/dev.c:7607
 dev_change_flags+0x10d/0x170 net/core/dev.c:7643
 dev_ifsioc+0x2b0/0x940 net/core/dev_ioctl.c:237
 dev_ioctl+0x1b8/0xc70 net/core/dev_ioctl.c:488
 sock_do_ioctl+0x1bd/0x300 net/socket.c:995
 sock_ioctl+0x32b/0x610 net/socket.c:1096
 vfs_ioctl fs/ioctl.c:46 [inline]
 file_ioctl fs/ioctl.c:509 [inline]
 do_vfs_ioctl+0xd6e/0x1390 fs/ioctl.c:696
 ksys_ioctl+0xab/0xd0 fs/ioctl.c:713
 __do_sys_ioctl fs/ioctl.c:720 [inline]
 __se_sys_ioctl fs/ioctl.c:718 [inline]
 __x64_sys_ioctl+0x73/0xb0 fs/ioctl.c:718
 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x4467c9
Code: e8 0c e8 ff ff 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 5b 07 fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007fdbea222d98 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 00000000006dbc58 RCX: 00000000004467c9
RDX: 0000000020000340 RSI: 0000000000008914 RDI: 0000000000000003
RBP: 00000000006dbc50 R08: 00007fdbea223700 R09: 0000000000000000
R10: 00007fdbea223700 R11: 0000000000000246 R12: 00000000006dbc5c
R13: 6000030030626669 R14: 0000000000000000 R15: 0000000030626669

Allocated by task 7843:
 save_stack+0x45/0xd0 mm/kasan/common.c:73
 set_track mm/kasan/common.c:85 [inline]
 __kasan_kmalloc mm/kasan/common.c:495 [inline]
 __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:468
 kasan_kmalloc+0x9/0x10 mm/kasan/common.c:509
 kmem_cache_alloc_trace+0x151/0x760 mm/slab.c:3615
 kmalloc include/linux/slab.h:545 [inline]
 x25_link_device_up+0x46/0x3f0 net/x25/x25_link.c:249
 x25_device_event+0x116/0x2b0 net/x25/af_x25.c:242
 notifier_call_chain+0xc7/0x240 kernel/notifier.c:93
 __raw_notifier_call_chain kernel/notifier.c:394 [inline]
 raw_notifier_call_chain+0x2e/0x40 kernel/notifier.c:401
 call_netdevice_notifiers_info+0x3f/0x90 net/core/dev.c:1739
 call_netdevice_notifiers_extack net/core/dev.c:1751 [inline]
 call_netdevice_notifiers net/core/dev.c:1765 [inline]
 __dev_notify_flags+0x121/0x2c0 net/core/dev.c:7605
 dev_change_flags+0x10d/0x170 net/core/dev.c:7643
 dev_ifsioc+0x2b0/0x940 net/core/dev_ioctl.c:237
 dev_ioctl+0x1b8/0xc70 net/core/dev_ioctl.c:488
 sock_do_ioctl+0x1bd/0x300 net/socket.c:995
 sock_ioctl+0x32b/0x610 net/socket.c:1096
 vfs_ioctl fs/ioctl.c:46 [inline]
 file_ioctl fs/ioctl.c:509 [inline]
 do_vfs_ioctl+0xd6e/0x1390 fs/ioctl.c:696
 ksys_ioctl+0xab/0xd0 fs/ioctl.c:713
 __do_sys_ioctl fs/ioctl.c:720 [inline]
 __se_sys_ioctl fs/ioctl.c:718 [inline]
 __x64_sys_ioctl+0x73/0xb0 fs/ioctl.c:718
 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Freed by task 7865:
 save_stack+0x45/0xd0 mm/kasan/common.c:73
 set_track mm/kasan/common.c:85 [inline]
 __kasan_slab_free+0x102/0x150 mm/kasan/common.c:457
 kasan_slab_free+0xe/0x10 mm/kasan/common.c:465
 __cache_free mm/slab.c:3494 [inline]
 kfree+0xcf/0x230 mm/slab.c:3811
 x25_neigh_put include/net/x25.h:253 [inline]
 x25_connect+0x8d8/0xde0 net/x25/af_x25.c:824
 __sys_connect+0x266/0x330 net/socket.c:1685
 __do_sys_connect net/socket.c:1696 [inline]
 __se_sys_connect net/socket.c:1693 [inline]
 __x64_sys_connect+0x73/0xb0 net/socket.c:1693
 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

The buggy address belongs to the object at ffff8880a030edc0
 which belongs to the cache kmalloc-256 of size 256
The buggy address is located 16 bytes inside of
 256-byte region [ffff8880a030edc0, ffff8880a030eec0)
The buggy address belongs to the page:
page:ffffea000280c380 count:1 mapcount:0 mapping:ffff88812c3f07c0 index:0x0
flags: 0x1fffc0000000200(slab)
raw: 01fffc0000000200 ffffea0002806788 ffffea00027f0188 ffff88812c3f07c0
raw: 0000000000000000 ffff8880a030e000 000000010000000c 0000000000000000
page dumped because: kasan: bad access detected

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot+04babcefcd396fabec37@syzkaller.appspotmail.com
Cc: andrew hendry <andrew.hendry@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/x25/af_x25.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index ec3a828672ef..7c17cc7e19bf 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -817,8 +817,12 @@ static int x25_connect(struct socket *sock, struct sockaddr *uaddr,
 	sock->state = SS_CONNECTED;
 	rc = 0;
 out_put_neigh:
-	if (rc)
+	if (rc) {
+		read_lock_bh(&x25_list_lock);
 		x25_neigh_put(x25->neighbour);
+		x25->neighbour = NULL;
+		read_unlock_bh(&x25_list_lock);
+	}
 out_put_route:
 	x25_route_put(rt);
 out:
-- 
2.20.1


From 273cb0f9af9fc61cb9366a78247ed5511b2746ca Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 11 Mar 2019 13:48:44 -0700
Subject: [PATCH 12/38] net/x25: reset state in x25_connect()

[ Upstream commit ee74d0bd4325efb41e38affe5955f920ed973f23 ]

In case x25_connect() fails and frees the socket neighbour,
we also need to undo the change done to x25->state.

Before my last bug fix, we had use-after-free so this
patch fixes a latent bug.

syzbot report :

kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] PREEMPT SMP KASAN
CPU: 1 PID: 16137 Comm: syz-executor.1 Not tainted 5.0.0+ #117
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:x25_write_internal+0x1e8/0xdf0 net/x25/x25_subr.c:173
Code: 00 40 88 b5 e0 fe ff ff 0f 85 01 0b 00 00 48 8b 8b 80 04 00 00 48 ba 00 00 00 00 00 fc ff df 48 8d 79 1c 48 89 fe 48 c1 ee 03 <0f> b6 34 16 48 89 fa 83 e2 07 83 c2 03 40 38 f2 7c 09 40 84 f6 0f
RSP: 0018:ffff888076717a08 EFLAGS: 00010207
RAX: ffff88805f2f2292 RBX: ffff8880a0ae6000 RCX: 0000000000000000
kobject: 'loop5' (0000000018d0d0ee): kobject_uevent_env
RDX: dffffc0000000000 RSI: 0000000000000003 RDI: 000000000000001c
RBP: ffff888076717b40 R08: ffff8880950e0580 R09: ffffed100be5e46d
R10: ffffed100be5e46c R11: ffff88805f2f2363 R12: ffff888065579840
kobject: 'loop5' (0000000018d0d0ee): fill_kobj_path: path = '/devices/virtual/block/loop5'
R13: 1ffff1100ece2f47 R14: 0000000000000013 R15: 0000000000000013
FS:  00007fb88cf43700(0000) GS:ffff8880ae900000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f9a42a41028 CR3: 0000000087a67000 CR4: 00000000001406e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 x25_release+0xd0/0x340 net/x25/af_x25.c:658
 __sock_release+0xd3/0x2b0 net/socket.c:579
 sock_close+0x1b/0x30 net/socket.c:1162
 __fput+0x2df/0x8d0 fs/file_table.c:278
 ____fput+0x16/0x20 fs/file_table.c:309
 task_work_run+0x14a/0x1c0 kernel/task_work.c:113
 get_signal+0x1961/0x1d50 kernel/signal.c:2388
 do_signal+0x87/0x1940 arch/x86/kernel/signal.c:816
 exit_to_usermode_loop+0x244/0x2c0 arch/x86/entry/common.c:162
 prepare_exit_to_usermode arch/x86/entry/common.c:197 [inline]
 syscall_return_slowpath arch/x86/entry/common.c:268 [inline]
 do_syscall_64+0x52d/0x610 arch/x86/entry/common.c:293
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x457f29
Code: ad b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007fb88cf42c78 EFLAGS: 00000246 ORIG_RAX: 000000000000002a
RAX: fffffffffffffe00 RBX: 0000000000000003 RCX: 0000000000457f29
RDX: 0000000000000012 RSI: 0000000020000080 RDI: 0000000000000004
RBP: 000000000073bf00 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00007fb88cf436d4
R13: 00000000004be462 R14: 00000000004cec98 R15: 00000000ffffffff
Modules linked in:

Fixes: 95d6ebd53c79 ("net/x25: fix use-after-free in x25_device_event()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: andrew hendry <andrew.hendry@gmail.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/x25/af_x25.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 7c17cc7e19bf..5f7a9fab8bad 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -822,6 +822,7 @@ static int x25_connect(struct socket *sock, struct sockaddr *uaddr,
 		x25_neigh_put(x25->neighbour);
 		x25->neighbour = NULL;
 		read_unlock_bh(&x25_list_lock);
+		x25->state = X25_STATE_0;
 	}
 out_put_route:
 	x25_route_put(rt);
-- 
2.20.1


From c9d46e49866c82d6b9d2af0378233154f20faf7a Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 13 Mar 2019 17:00:48 +0800
Subject: [PATCH 13/38] pptp: dst_release sk_dst_cache in pptp_sock_destruct

[ Upstream commit 9417d81f4f8adfe20a12dd1fadf73a618cbd945d ]

sk_setup_caps() is called to set sk->sk_dst_cache in pptp_connect,
so we have to dst_release(sk->sk_dst_cache) in pptp_sock_destruct,
otherwise, the dst refcnt will leak.

It can be reproduced by this syz log:

  r1 = socket$pptp(0x18, 0x1, 0x2)
  bind$pptp(r1, &(0x7f0000000100)={0x18, 0x2, {0x0, @local}}, 0x1e)
  connect$pptp(r1, &(0x7f0000000000)={0x18, 0x2, {0x3, @remote}}, 0x1e)

Consecutive dmesg warnings will occur:

  unregister_netdevice: waiting for lo to become free. Usage count = 1

v1->v2:
  - use rcu_dereference_protected() instead of rcu_dereference_check(),
    as suggested by Eric.

Fixes: 00959ade36ac ("PPTP: PPP over IPv4 (Point-to-Point Tunneling Protocol)")
Reported-by: Xiumei Mu <xmu@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pptp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index 67ffe74747a1..7321a4eca235 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -537,6 +537,7 @@ static void pptp_sock_destruct(struct sock *sk)
 		pppox_unbind_sock(sk);
 	}
 	skb_queue_purge(&sk->sk_receive_queue);
+	dst_release(rcu_dereference_protected(sk->sk_dst_cache, 1));
 }
 
 static int pptp_create(struct net *net, struct socket *sock, int kern)
-- 
2.20.1


From f215d86df871e942b26ff1145f73e562acf5a507 Mon Sep 17 00:00:00 2001
From: Masaru Nagai <masaru.nagai.vx@renesas.com>
Date: Thu, 7 Mar 2019 11:24:47 +0100
Subject: [PATCH 14/38] ravb: Decrease TxFIFO depth of Q3 and Q2 to one

[ Upstream commit ae9819e339b451da7a86ab6fe38ecfcb6814e78a ]

Hardware has the CBS (Credit Based Shaper) which affects only Q3
and Q2. When updating the CBS settings, even if the driver does so
after waiting for Tx DMA finished, there is a possibility that frame
data still remains in TxFIFO.

To avoid this, decrease TxFIFO depth of Q3 and Q2 to one.

This patch has been exercised this using netperf TCP_MAERTS, TCP_STREAM
and UDP_STREAM tests run on an Ebisu board. No performance change was
detected, outside of noise in the tests, both in terms of throughput and
CPU utilisation.

Fixes: c156633f1353 ("Renesas Ethernet AVB driver proper")
Signed-off-by: Masaru Nagai <masaru.nagai.vx@renesas.com>
Signed-off-by: Kazuya Mizuguchi <kazuya.mizuguchi.ks@renesas.com>
[simon: updated changelog]
Signed-off-by: Simon Horman <horms+renesas@verge.net.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/ravb_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index e7f8ab6e4391..b03f7e257dde 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -467,7 +467,7 @@ static int ravb_dmac_init(struct net_device *ndev)
 		   RCR_EFFS | RCR_ENCF | RCR_ETS0 | RCR_ESF | 0x18000000, RCR);
 
 	/* Set FIFO size */
-	ravb_write(ndev, TGC_TQP_AVBMODE1 | 0x00222200, TGC);
+	ravb_write(ndev, TGC_TQP_AVBMODE1 | 0x00112200, TGC);
 
 	/* Timestamp enable */
 	ravb_write(ndev, TCCR_TFEN, TCCR);
-- 
2.20.1


From 973626777a7f622304ba08e41dd92ef43d4c3e61 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Fri, 8 Mar 2019 14:50:54 +0800
Subject: [PATCH 15/38] route: set the deleted fnhe fnhe_daddr to 0 in
 ip_del_fnhe to fix a race

[ Upstream commit ee60ad219f5c7c4fb2f047f88037770063ef785f ]

The race occurs in __mkroute_output() when 2 threads lookup a dst:

  CPU A                 CPU B
  find_exception()
                        find_exception() [fnhe expires]
                        ip_del_fnhe() [fnhe is deleted]
  rt_bind_exception()

In rt_bind_exception() it will bind a deleted fnhe with the new dst, and
this dst will get no chance to be freed. It causes a dev defcnt leak and
consecutive dmesg warnings:

  unregister_netdevice: waiting for ethX to become free. Usage count = 1

Especially thanks Jon to identify the issue.

This patch fixes it by setting fnhe_daddr to 0 in ip_del_fnhe() to stop
binding the deleted fnhe with a new dst when checking fnhe's fnhe_daddr
and daddr in rt_bind_exception().

It works as both ip_del_fnhe() and rt_bind_exception() are protected by
fnhe_lock and the fhne is freed by kfree_rcu().

Fixes: deed49df7390 ("route: check and remove route cache when we get route")
Signed-off-by: Jon Maxwell <jmaxwell37@gmail.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index a56c73ee965b..932fff245253 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1303,6 +1303,10 @@ static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
 		if (fnhe->fnhe_daddr == daddr) {
 			rcu_assign_pointer(*fnhe_p, rcu_dereference_protected(
 				fnhe->fnhe_next, lockdep_is_held(&fnhe_lock)));
+			/* set fnhe_daddr to 0 to ensure it won't bind with
+			 * new dsts in rt_bind_exception().
+			 */
+			fnhe->fnhe_daddr = 0;
 			fnhe_flush_routes(fnhe);
 			kfree_rcu(fnhe, rcu);
 			break;
-- 
2.20.1


From cec1d5006dc02effd22b7912b4753acbb105d338 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Sat, 9 Mar 2019 00:29:58 +0000
Subject: [PATCH 16/38] rxrpc: Fix client call queueing, waiting for channel

[ Upstream commit 69ffaebb90369ce08657b5aea4896777b9d6e8fc ]

rxrpc_get_client_conn() adds a new call to the front of the waiting_calls
queue if the connection it's going to use already exists.  This is bad as
it allows calls to get starved out.

Fix this by adding to the tail instead.

Also change the other enqueue point in the same function to put it on the
front (ie. when we have a new connection).  This makes the point that in
the case of a new connection the new call goes at the front (though it
doesn't actually matter since the queue should be unoccupied).

Fixes: 45025bceef17 ("rxrpc: Improve management and caching of client connection objects")
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Marc Dionne <marc.dionne@auristor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/conn_client.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index 521189f4b666..6e419b15a9f8 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -353,7 +353,7 @@ static int rxrpc_get_client_conn(struct rxrpc_sock *rx,
 	 * normally have to take channel_lock but we do this before anyone else
 	 * can see the connection.
 	 */
-	list_add_tail(&call->chan_wait_link, &candidate->waiting_calls);
+	list_add(&call->chan_wait_link, &candidate->waiting_calls);
 
 	if (cp->exclusive) {
 		call->conn = candidate;
@@ -432,7 +432,7 @@ static int rxrpc_get_client_conn(struct rxrpc_sock *rx,
 	call->conn = conn;
 	call->security_ix = conn->security_ix;
 	call->service_id = conn->service_id;
-	list_add(&call->chan_wait_link, &conn->waiting_calls);
+	list_add_tail(&call->chan_wait_link, &conn->waiting_calls);
 	spin_unlock(&conn->channel_lock);
 	_leave(" = 0 [extant %d]", conn->debug_id);
 	return 0;
-- 
2.20.1


From 1e251615b5849011a5dca205cd9fbfef2c3dd4b2 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Fri, 8 Mar 2019 15:49:16 +0800
Subject: [PATCH 17/38] sctp: remove sched init from sctp_stream_init

[ Upstream commit 2e990dfd13974d9eae493006f42ffb48707970ef ]

syzbot reported a NULL-ptr deref caused by that sched->init() in
sctp_stream_init() set stream->rr_next = NULL.

  kasan: GPF could be caused by NULL-ptr deref or user memory access
  RIP: 0010:sctp_sched_rr_dequeue+0xd3/0x170 net/sctp/stream_sched_rr.c:141
  Call Trace:
    sctp_outq_dequeue_data net/sctp/outqueue.c:90 [inline]
    sctp_outq_flush_data net/sctp/outqueue.c:1079 [inline]
    sctp_outq_flush+0xba2/0x2790 net/sctp/outqueue.c:1205

All sched info is saved in sout->ext now, in sctp_stream_init()
sctp_stream_alloc_out() will not change it, there's no need to
call sched->init() again, since sctp_outq_init() has already
done it.

Fixes: 5bbbbe32a431 ("sctp: introduce stream scheduler foundations")
Reported-by: syzbot+4c9934f20522c0efd657@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/stream.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index 2936ed17bf9e..3b47457862cc 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -230,8 +230,6 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt,
 	for (i = 0; i < stream->outcnt; i++)
 		SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN;
 
-	sched->init(stream);
-
 in:
 	sctp_stream_interleave_init(stream);
 	if (!incnt)
-- 
2.20.1


From b354d53101baaf0f296f874d3e9eb8a64277820a Mon Sep 17 00:00:00 2001
From: Soheil Hassas Yeganeh <soheil@google.com>
Date: Wed, 6 Mar 2019 13:01:36 -0500
Subject: [PATCH 18/38] tcp: do not report TCP_CM_INQ of 0 for closed
 connections

[ Upstream commit 6466e715651f9f358e60c5ea4880e4731325827f ]

Returning 0 as inq to userspace indicates there is no more data to
read, and the application needs to wait for EPOLLIN. For a connection
that has received FIN from the remote peer, however, the application
must continue reading until getting EOF (return value of 0
from tcp_recvmsg) or an error, if edge-triggered epoll (EPOLLET) is
being used. Otherwise, the application will never receive a new
EPOLLIN, since there is no epoll edge after the FIN.

Return 1 when there is no data left on the queue but the
connection has received FIN, so that the applications continue
reading.

Fixes: b75eba76d3d72 (tcp: send in-queue bytes in cmsg upon read)
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index b102973102b9..8672b13cd72a 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1914,6 +1914,11 @@ static int tcp_inq_hint(struct sock *sk)
 		inq = tp->rcv_nxt - tp->copied_seq;
 		release_sock(sk);
 	}
+	/* After receiving a FIN, tell the user-space to continue reading
+	 * by returning a non-zero inq.
+	 */
+	if (inq == 0 && sock_flag(sk, SOCK_DONE))
+		inq = 1;
 	return inq;
 }
 
-- 
2.20.1


From 2a608541bc705ca7d505d4676cc6e4a6e1f9f759 Mon Sep 17 00:00:00 2001
From: Christoph Paasch <cpaasch@apple.com>
Date: Mon, 11 Mar 2019 11:41:05 -0700
Subject: [PATCH 19/38] tcp: Don't access TCP_SKB_CB before initializing it

[ Upstream commit f2feaefdabb0a6253aa020f65e7388f07a9ed47c ]

Since commit eeea10b83a13 ("tcp: add
tcp_v4_fill_cb()/tcp_v4_restore_cb()"), tcp_vX_fill_cb is only called
after tcp_filter(). That means, TCP_SKB_CB(skb)->end_seq still points to
the IP-part of the cb.

We thus should not mock with it, as this can trigger bugs (thanks
syzkaller):
[   12.349396] ==================================================================
[   12.350188] BUG: KASAN: slab-out-of-bounds in ip6_datagram_recv_specific_ctl+0x19b3/0x1a20
[   12.351035] Read of size 1 at addr ffff88006adbc208 by task test_ip6_datagr/1799

Setting end_seq is actually no more necessary in tcp_filter as it gets
initialized later on in tcp_vX_fill_cb.

Cc: Eric Dumazet <edumazet@google.com>
Fixes: eeea10b83a13 ("tcp: add tcp_v4_fill_cb()/tcp_v4_restore_cb()")
Signed-off-by: Christoph Paasch <cpaasch@apple.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index b654f21064bb..1344caccbbde 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1646,15 +1646,8 @@ EXPORT_SYMBOL(tcp_add_backlog);
 int tcp_filter(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcphdr *th = (struct tcphdr *)skb->data;
-	unsigned int eaten = skb->len;
-	int err;
 
-	err = sk_filter_trim_cap(sk, skb, th->doff * 4);
-	if (!err) {
-		eaten -= skb->len;
-		TCP_SKB_CB(skb)->end_seq -= eaten;
-	}
-	return err;
+	return sk_filter_trim_cap(sk, skb, th->doff * 4);
 }
 EXPORT_SYMBOL(tcp_filter);
 
-- 
2.20.1


From 34ca34d6dff636d3dc14c8f56e1b6714a352dfeb Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Fri, 8 Mar 2019 22:09:47 +0100
Subject: [PATCH 20/38] tcp: handle inet_csk_reqsk_queue_add() failures

[  Upstream commit 9d3e1368bb45893a75a5dfb7cd21fdebfa6b47af ]

Commit 7716682cc58e ("tcp/dccp: fix another race at listener
dismantle") let inet_csk_reqsk_queue_add() fail, and adjusted
{tcp,dccp}_check_req() accordingly. However, TFO and syncookies
weren't modified, thus leaking allocated resources on error.

Contrary to tcp_check_req(), in both syncookies and TFO cases,
we need to drop the request socket. Also, since the child socket is
created with inet_csk_clone_lock(), we have to unlock it and drop an
extra reference (->sk_refcount is initially set to 2 and
inet_csk_reqsk_queue_add() drops only one ref).

For TFO, we also need to revert the work done by tcp_try_fastopen()
(with reqsk_fastopen_remove()).

Fixes: 7716682cc58e ("tcp/dccp: fix another race at listener dismantle")
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/syncookies.c | 7 ++++++-
 net/ipv4/tcp_input.c  | 8 +++++++-
 2 files changed, 13 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 606f868d9f3f..e531344611a0 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -216,7 +216,12 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb,
 		refcount_set(&req->rsk_refcnt, 1);
 		tcp_sk(child)->tsoffset = tsoff;
 		sock_rps_save_rxhash(child, skb);
-		inet_csk_reqsk_queue_add(sk, req, child);
+		if (!inet_csk_reqsk_queue_add(sk, req, child)) {
+			bh_unlock_sock(child);
+			sock_put(child);
+			child = NULL;
+			reqsk_put(req);
+		}
 	} else {
 		reqsk_free(req);
 	}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a9d9555a973f..1ceb41cf785f 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6511,7 +6511,13 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 		af_ops->send_synack(fastopen_sk, dst, &fl, req,
 				    &foc, TCP_SYNACK_FASTOPEN);
 		/* Add the child socket directly into the accept queue */
-		inet_csk_reqsk_queue_add(sk, req, fastopen_sk);
+		if (!inet_csk_reqsk_queue_add(sk, req, fastopen_sk)) {
+			reqsk_fastopen_remove(fastopen_sk, req, false);
+			bh_unlock_sock(fastopen_sk);
+			sock_put(fastopen_sk);
+			reqsk_put(req);
+			goto drop;
+		}
 		sk->sk_data_ready(sk);
 		bh_unlock_sock(fastopen_sk);
 		sock_put(fastopen_sk);
-- 
2.20.1


From 68dcc2831850e3e1c494ab59532dc5e770a80e20 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Fri, 8 Mar 2019 16:40:57 +0100
Subject: [PATCH 21/38] vxlan: Fix GRO cells race condition between receive and
 link delete

[ Upstream commit ad6c9986bcb627c7c22b8f9e9a934becc27df87c ]

If we receive a packet while deleting a VXLAN device, there's a chance
vxlan_rcv() is called at the same time as vxlan_dellink(). This is fine,
except that vxlan_dellink() should never ever touch stuff that's still in
use, such as the GRO cells list.

Otherwise, vxlan_rcv() crashes while queueing packets via
gro_cells_receive().

Move the gro_cells_destroy() to vxlan_uninit(), which runs after the RCU
grace period is elapsed and nothing needs the gro_cells anymore.

This is now done in the same way as commit 8e816df87997 ("geneve: Use GRO
cells infrastructure.") originally implemented for GENEVE.

Reported-by: Jianlin Shi <jishi@redhat.com>
Fixes: 58ce31cca1ff ("vxlan: GRO support at tunnel layer")
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 8f022964b2d1..0f4882cb6835 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2529,6 +2529,8 @@ static void vxlan_uninit(struct net_device *dev)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 
+	gro_cells_destroy(&vxlan->gro_cells);
+
 	vxlan_fdb_delete_default(vxlan, vxlan->cfg.vni);
 
 	free_percpu(dev->tstats);
@@ -3601,7 +3603,6 @@ static void vxlan_dellink(struct net_device *dev, struct list_head *head)
 
 	vxlan_flush(vxlan, true);
 
-	gro_cells_destroy(&vxlan->gro_cells);
 	list_del(&vxlan->next);
 	unregister_netdevice_queue(dev, head);
 }
-- 
2.20.1


From e0d0fb50a05e015483555669de05d89fb52cea4a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 10 Mar 2019 10:36:40 -0700
Subject: [PATCH 22/38] vxlan: test dev->flags & IFF_UP before calling
 gro_cells_receive()

[ Upstream commit 59cbf56fcd98ba2a715b6e97c4e43f773f956393 ]

Same reasons than the ones explained in commit 4179cb5a4c92
("vxlan: test dev->flags & IFF_UP before calling netif_rx()")

netif_rx() or gro_cells_receive() must be called under a strict contract.

At device dismantle phase, core networking clears IFF_UP
and flush_all_backlogs() is called after rcu grace period
to make sure no incoming packet might be in a cpu backlog
and still referencing the device.

A similar protocol is used for gro_cells infrastructure, as
gro_cells_destroy() will be called only after a full rcu
grace period is observed after IFF_UP has been cleared.

Most drivers call netif_rx() from their interrupt handler,
and since the interrupts are disabled at device dismantle,
netif_rx() does not have to check dev->flags & IFF_UP

Virtual drivers do not have this guarantee, and must
therefore make the check themselves.

Otherwise we risk use-after-free and/or crashes.

Fixes: d342894c5d2f ("vxlan: virtual extensible lan")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 0f4882cb6835..7530aa83cfad 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1538,6 +1538,14 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb)
 		goto drop;
 	}
 
+	rcu_read_lock();
+
+	if (unlikely(!(vxlan->dev->flags & IFF_UP))) {
+		rcu_read_unlock();
+		atomic_long_inc(&vxlan->dev->rx_dropped);
+		goto drop;
+	}
+
 	stats = this_cpu_ptr(vxlan->dev->tstats);
 	u64_stats_update_begin(&stats->syncp);
 	stats->rx_packets++;
@@ -1545,6 +1553,9 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb)
 	u64_stats_update_end(&stats->syncp);
 
 	gro_cells_receive(&vxlan->gro_cells, skb);
+
+	rcu_read_unlock();
+
 	return 0;
 
 drop:
-- 
2.20.1


From ea5031bf251c47ef0ed6f53b0148768d03af053b Mon Sep 17 00:00:00 2001
From: Jack Morgenstein <jackm@dev.mellanox.co.il>
Date: Tue, 12 Mar 2019 17:05:47 +0200
Subject: [PATCH 23/38] net/mlx4_core: Fix reset flow when in command polling
 mode

[ Upstream commit e15ce4b8d11227007577e6dc1364d288b8874fbe ]

As part of unloading a device, the driver switches from
FW command event mode to FW command polling mode.

Part of switching over to polling mode is freeing the command context array
memory (unfortunately, currently, without NULLing the command context array
pointer).

The reset flow calls "complete" to complete all outstanding fw commands
(if we are in event mode). The check for event vs. polling mode here
is to test if the command context array pointer is NULL.

If the reset flow is activated after the switch to polling mode, it will
attempt (incorrectly) to complete all the commands in the context array --
because the pointer was not NULLed when the driver switched over to polling
mode.

As a result, we have a use-after-free situation, which results in a
kernel crash.

For example:
BUG: unable to handle kernel NULL pointer dereference at           (null)
IP: [<ffffffff876c4a8e>] __wake_up_common+0x2e/0x90
PGD 0
Oops: 0000 [#1] SMP
Modules linked in: netconsole nfsv3 nfs_acl nfs lockd grace ...
CPU: 2 PID: 940 Comm: kworker/2:3 Kdump: loaded Not tainted 3.10.0-862.el7.x86_64 #1
Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS 090006  04/28/2016
Workqueue: events hv_eject_device_work [pci_hyperv]
task: ffff8d1734ca0fd0 ti: ffff8d17354bc000 task.ti: ffff8d17354bc000
RIP: 0010:[<ffffffff876c4a8e>]  [<ffffffff876c4a8e>] __wake_up_common+0x2e/0x90
RSP: 0018:ffff8d17354bfa38  EFLAGS: 00010082
RAX: 0000000000000000 RBX: ffff8d17362d42c8 RCX: 0000000000000000
RDX: 0000000000000001 RSI: 0000000000000003 RDI: ffff8d17362d42c8
RBP: ffff8d17354bfa70 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000298 R11: ffff8d173610e000 R12: ffff8d17362d42d0
R13: 0000000000000246 R14: 0000000000000000 R15: 0000000000000003
FS:  0000000000000000(0000) GS:ffff8d1802680000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000000 CR3: 00000000f16d8000 CR4: 00000000001406e0
Call Trace:
 [<ffffffff876c7adc>] complete+0x3c/0x50
 [<ffffffffc04242f0>] mlx4_cmd_wake_completions+0x70/0x90 [mlx4_core]
 [<ffffffffc041e7b1>] mlx4_enter_error_state+0xe1/0x380 [mlx4_core]
 [<ffffffffc041fa4b>] mlx4_comm_cmd+0x29b/0x360 [mlx4_core]
 [<ffffffffc041ff51>] __mlx4_cmd+0x441/0x920 [mlx4_core]
 [<ffffffff877f62b1>] ? __slab_free+0x81/0x2f0
 [<ffffffff87951384>] ? __radix_tree_lookup+0x84/0xf0
 [<ffffffffc043a8eb>] mlx4_free_mtt_range+0x5b/0xb0 [mlx4_core]
 [<ffffffffc043a957>] mlx4_mtt_cleanup+0x17/0x20 [mlx4_core]
 [<ffffffffc04272c7>] mlx4_free_eq+0xa7/0x1c0 [mlx4_core]
 [<ffffffffc042803e>] mlx4_cleanup_eq_table+0xde/0x130 [mlx4_core]
 [<ffffffffc0433e08>] mlx4_unload_one+0x118/0x300 [mlx4_core]
 [<ffffffffc0434191>] mlx4_remove_one+0x91/0x1f0 [mlx4_core]

The fix is to set the command context array pointer to NULL after freeing
the array.

Fixes: f5aef5aa3506 ("net/mlx4_core: Activate reset flow upon fatal command cases")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/cmd.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index e65bc3c95630..24143ee05427 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -2689,6 +2689,7 @@ void mlx4_cmd_use_polling(struct mlx4_dev *dev)
 		down(&priv->cmd.event_sem);
 
 	kfree(priv->cmd.context);
+	priv->cmd.context = NULL;
 
 	up(&priv->cmd.poll_sem);
 	up_write(&priv->cmd.switch_sem);
-- 
2.20.1


From 6fed864f7da838d82c2a620909577444dade2c1f Mon Sep 17 00:00:00 2001
From: Jack Morgenstein <jackm@dev.mellanox.co.il>
Date: Tue, 12 Mar 2019 17:05:48 +0200
Subject: [PATCH 24/38] net/mlx4_core: Fix locking in SRIOV mode when switching
 between events and polling

[ Upstream commit c07d27927f2f2e96fcd27bb9fb330c9ea65612d0 ]

In procedures mlx4_cmd_use_events() and mlx4_cmd_use_polling(), we need to
guarantee that there are no FW commands in progress on the comm channel
(for VFs) or wrapped FW commands (on the PF) when SRIOV is active.

We do this by also taking the slave_cmd_mutex when SRIOV is active.

This is especially important when switching from event to polling, since we
free the command-context array during the switch.  If there are FW commands
in progress (e.g., waiting for a completion event), the completion event
handler will access freed memory.

Since the decision to use comm_wait or comm_poll is taken before grabbing
the event_sem/poll_sem in mlx4_comm_cmd_wait/poll, we must take the
slave_cmd_mutex as well (to guarantee that the decision to use events or
polling and the call to the appropriate cmd function are atomic).

Fixes: a7e1f04905e5 ("net/mlx4_core: Fix deadlock when switching between polling and event fw commands")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/cmd.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 24143ee05427..857588e2488d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -2645,6 +2645,8 @@ int mlx4_cmd_use_events(struct mlx4_dev *dev)
 	if (!priv->cmd.context)
 		return -ENOMEM;
 
+	if (mlx4_is_mfunc(dev))
+		mutex_lock(&priv->cmd.slave_cmd_mutex);
 	down_write(&priv->cmd.switch_sem);
 	for (i = 0; i < priv->cmd.max_cmds; ++i) {
 		priv->cmd.context[i].token = i;
@@ -2670,6 +2672,8 @@ int mlx4_cmd_use_events(struct mlx4_dev *dev)
 	down(&priv->cmd.poll_sem);
 	priv->cmd.use_events = 1;
 	up_write(&priv->cmd.switch_sem);
+	if (mlx4_is_mfunc(dev))
+		mutex_unlock(&priv->cmd.slave_cmd_mutex);
 
 	return err;
 }
@@ -2682,6 +2686,8 @@ void mlx4_cmd_use_polling(struct mlx4_dev *dev)
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	int i;
 
+	if (mlx4_is_mfunc(dev))
+		mutex_lock(&priv->cmd.slave_cmd_mutex);
 	down_write(&priv->cmd.switch_sem);
 	priv->cmd.use_events = 0;
 
@@ -2693,6 +2699,8 @@ void mlx4_cmd_use_polling(struct mlx4_dev *dev)
 
 	up(&priv->cmd.poll_sem);
 	up_write(&priv->cmd.switch_sem);
+	if (mlx4_is_mfunc(dev))
+		mutex_unlock(&priv->cmd.slave_cmd_mutex);
 }
 
 struct mlx4_cmd_mailbox *mlx4_alloc_cmd_mailbox(struct mlx4_dev *dev)
-- 
2.20.1


From dae6a2e7554bf7c4ab20b6df2038217e7507e1eb Mon Sep 17 00:00:00 2001
From: Jack Morgenstein <jackm@dev.mellanox.co.il>
Date: Tue, 12 Mar 2019 17:05:49 +0200
Subject: [PATCH 25/38] net/mlx4_core: Fix qp mtt size calculation

[ Upstream commit 8511a653e9250ef36b95803c375a7be0e2edb628 ]

Calculation of qp mtt size (in function mlx4_RST2INIT_wrapper)
ultimately depends on function roundup_pow_of_two.

If the amount of memory required by the QP is less than one page,
roundup_pow_of_two is called with argument zero.  In this case, the
roundup_pow_of_two result is undefined.

Calling roundup_pow_of_two with a zero argument resulted in the
following stack trace:

UBSAN: Undefined behaviour in ./include/linux/log2.h:61:13
shift exponent 64 is too large for 64-bit type 'long unsigned int'
CPU: 4 PID: 26939 Comm: rping Tainted: G OE 4.19.0-rc1
Hardware name: Supermicro X9DR3-F/X9DR3-F, BIOS 3.2a 07/09/2015
Call Trace:
dump_stack+0x9a/0xeb
ubsan_epilogue+0x9/0x7c
__ubsan_handle_shift_out_of_bounds+0x254/0x29d
? __ubsan_handle_load_invalid_value+0x180/0x180
? debug_show_all_locks+0x310/0x310
? sched_clock+0x5/0x10
? sched_clock+0x5/0x10
? sched_clock_cpu+0x18/0x260
? find_held_lock+0x35/0x1e0
? mlx4_RST2INIT_QP_wrapper+0xfb1/0x1440 [mlx4_core]
mlx4_RST2INIT_QP_wrapper+0xfb1/0x1440 [mlx4_core]

Fix this by explicitly testing for zero, and returning one if the
argument is zero (assuming that the next higher power of 2 in this case
should be one).

Fixes: c82e9aa0a8bc ("mlx4_core: resource tracking for HCA resources used by guests")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/resource_tracker.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 31bd56727022..676428a57662 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -2719,13 +2719,13 @@ static int qp_get_mtt_size(struct mlx4_qp_context *qpc)
 	int total_pages;
 	int total_mem;
 	int page_offset = (be32_to_cpu(qpc->params2) >> 6) & 0x3f;
+	int tot;
 
 	sq_size = 1 << (log_sq_size + log_sq_sride + 4);
 	rq_size = (srq|rss|xrc) ? 0 : (1 << (log_rq_size + log_rq_stride + 4));
 	total_mem = sq_size + rq_size;
-	total_pages =
-		roundup_pow_of_two((total_mem + (page_offset << 6)) >>
-				   page_shift);
+	tot = (total_mem + (page_offset << 6)) >> page_shift;
+	total_pages = !tot ? 1 : roundup_pow_of_two(tot);
 
 	return total_pages;
 }
-- 
2.20.1


From 6dfd4a4b05b4ee6af507955fb66a72d21d074d00 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Wed, 6 Mar 2019 16:22:12 +0200
Subject: [PATCH 26/38] net: sched: flower: insert new filter to idr after
 setting its mask

[ Upstream commit ecb3dea400d3beaf611ce76ac7a51d4230492cf2 ]

When adding new filter to flower classifier, fl_change() inserts it to
handle_idr before initializing filter extensions and assigning it a mask.
Normally this ordering doesn't matter because all flower classifier ops
callbacks assume rtnl lock protection. However, when filter has an action
that doesn't have its kernel module loaded, rtnl lock is released before
call to request_module(). During this time the filter can be accessed bu
concurrent task before its initialization is completed, which can lead to a
crash.

Example case of NULL pointer dereference in concurrent dump:

Task 1                           Task 2

tc_new_tfilter()
 fl_change()
  idr_alloc_u32(fnew)
  fl_set_parms()
   tcf_exts_validate()
    tcf_action_init()
     tcf_action_init_1()
      rtnl_unlock()
      request_module()
      ...                        rtnl_lock()
      				 tc_dump_tfilter()
      				  tcf_chain_dump()
				   fl_walk()
				    idr_get_next_ul()
				    tcf_node_dump()
				     tcf_fill_node()
				      fl_dump()
				       mask = &f->mask->key; <- NULL ptr
      rtnl_lock()

Extension initialization and mask assignment don't depend on fnew->handle
that is allocated by idr_alloc_u32(). Move idr allocation code after action
creation and mask assignment in fl_change() to prevent concurrent access
to not fully initialized filter when rtnl lock is released to load action
module.

Fixes: 01683a146999 ("net: sched: refactor flower walk to iterate over idr")
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_flower.c | 43 +++++++++++++++++++++---------------------
 1 file changed, 22 insertions(+), 21 deletions(-)

diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 2f64e3538127..2d81cd999d92 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -1213,46 +1213,46 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
 	if (err < 0)
 		goto errout;
 
-	if (!handle) {
-		handle = 1;
-		err = idr_alloc_u32(&head->handle_idr, fnew, &handle,
-				    INT_MAX, GFP_KERNEL);
-	} else if (!fold) {
-		/* user specifies a handle and it doesn't exist */
-		err = idr_alloc_u32(&head->handle_idr, fnew, &handle,
-				    handle, GFP_KERNEL);
-	}
-	if (err)
-		goto errout;
-	fnew->handle = handle;
-
 	if (tb[TCA_FLOWER_FLAGS]) {
 		fnew->flags = nla_get_u32(tb[TCA_FLOWER_FLAGS]);
 
 		if (!tc_flags_valid(fnew->flags)) {
 			err = -EINVAL;
-			goto errout_idr;
+			goto errout;
 		}
 	}
 
 	err = fl_set_parms(net, tp, fnew, mask, base, tb, tca[TCA_RATE], ovr,
 			   tp->chain->tmplt_priv, extack);
 	if (err)
-		goto errout_idr;
+		goto errout;
 
 	err = fl_check_assign_mask(head, fnew, fold, mask);
 	if (err)
-		goto errout_idr;
+		goto errout;
+
+	if (!handle) {
+		handle = 1;
+		err = idr_alloc_u32(&head->handle_idr, fnew, &handle,
+				    INT_MAX, GFP_KERNEL);
+	} else if (!fold) {
+		/* user specifies a handle and it doesn't exist */
+		err = idr_alloc_u32(&head->handle_idr, fnew, &handle,
+				    handle, GFP_KERNEL);
+	}
+	if (err)
+		goto errout_mask;
+	fnew->handle = handle;
 
 	if (!fold && fl_lookup(fnew->mask, &fnew->mkey)) {
 		err = -EEXIST;
-		goto errout_mask;
+		goto errout_idr;
 	}
 
 	err = rhashtable_insert_fast(&fnew->mask->ht, &fnew->ht_node,
 				     fnew->mask->filter_ht_params);
 	if (err)
-		goto errout_mask;
+		goto errout_idr;
 
 	if (!tc_skip_hw(fnew->flags)) {
 		err = fl_hw_replace_filter(tp, fnew, extack);
@@ -1291,12 +1291,13 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
 	rhashtable_remove_fast(&fnew->mask->ht, &fnew->ht_node,
 			       fnew->mask->filter_ht_params);
 
-errout_mask:
-	fl_mask_put(head, fnew->mask, false);
-
 errout_idr:
 	if (!fold)
 		idr_remove(&head->handle_idr, fnew->handle);
+
+errout_mask:
+	fl_mask_put(head, fnew->mask, false);
+
 errout:
 	tcf_exts_destroy(&fnew->exts);
 	kfree(fnew);
-- 
2.20.1


From 23d4efbf46daea0c011ae1b79328e79e27bf3334 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 23 Feb 2019 15:51:51 -0800
Subject: [PATCH 27/38] tcp: repaired skbs must init their tso_segs

[ Upstream commit bf50b606cfd85ac8d3d0adb711f3e22204059848 ]

syzbot reported a WARN_ON(!tcp_skb_pcount(skb))
in tcp_send_loss_probe() [1]

This was caused by TCP_REPAIR sent skbs that inadvertenly
were missing a call to tcp_init_tso_segs()

[1]
WARNING: CPU: 1 PID: 0 at net/ipv4/tcp_output.c:2534 tcp_send_loss_probe+0x771/0x8a0 net/ipv4/tcp_output.c:2534
Kernel panic - not syncing: panic_on_warn set ...
CPU: 1 PID: 0 Comm: swapper/1 Not tainted 5.0.0-rc7+ #77
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 panic+0x2cb/0x65c kernel/panic.c:214
 __warn.cold+0x20/0x45 kernel/panic.c:571
 report_bug+0x263/0x2b0 lib/bug.c:186
 fixup_bug arch/x86/kernel/traps.c:178 [inline]
 fixup_bug arch/x86/kernel/traps.c:173 [inline]
 do_error_trap+0x11b/0x200 arch/x86/kernel/traps.c:271
 do_invalid_op+0x37/0x50 arch/x86/kernel/traps.c:290
 invalid_op+0x14/0x20 arch/x86/entry/entry_64.S:973
RIP: 0010:tcp_send_loss_probe+0x771/0x8a0 net/ipv4/tcp_output.c:2534
Code: 88 fc ff ff 4c 89 ef e8 ed 75 c8 fb e9 c8 fc ff ff e8 43 76 c8 fb e9 63 fd ff ff e8 d9 75 c8 fb e9 94 f9 ff ff e8 bf 03 91 fb <0f> 0b e9 7d fa ff ff e8 b3 03 91 fb 0f b6 1d 37 43 7a 03 31 ff 89
RSP: 0018:ffff8880ae907c60 EFLAGS: 00010206
RAX: ffff8880a989c340 RBX: 0000000000000000 RCX: ffffffff85dedbdb
RDX: 0000000000000100 RSI: ffffffff85dee0b1 RDI: 0000000000000005
RBP: ffff8880ae907c90 R08: ffff8880a989c340 R09: ffffed10147d1ae1
R10: ffffed10147d1ae0 R11: ffff8880a3e8d703 R12: ffff888091b90040
R13: ffff8880a3e8d540 R14: 0000000000008000 R15: ffff888091b90860
 tcp_write_timer_handler+0x5c0/0x8a0 net/ipv4/tcp_timer.c:583
 tcp_write_timer+0x10e/0x1d0 net/ipv4/tcp_timer.c:607
 call_timer_fn+0x190/0x720 kernel/time/timer.c:1325
 expire_timers kernel/time/timer.c:1362 [inline]
 __run_timers kernel/time/timer.c:1681 [inline]
 __run_timers kernel/time/timer.c:1649 [inline]
 run_timer_softirq+0x652/0x1700 kernel/time/timer.c:1694
 __do_softirq+0x266/0x95a kernel/softirq.c:292
 invoke_softirq kernel/softirq.c:373 [inline]
 irq_exit+0x180/0x1d0 kernel/softirq.c:413
 exiting_irq arch/x86/include/asm/apic.h:536 [inline]
 smp_apic_timer_interrupt+0x14a/0x570 arch/x86/kernel/apic/apic.c:1062
 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:807
 </IRQ>
RIP: 0010:native_safe_halt+0x2/0x10 arch/x86/include/asm/irqflags.h:58
Code: ff ff ff 48 89 c7 48 89 45 d8 e8 59 0c a1 fa 48 8b 45 d8 e9 ce fe ff ff 48 89 df e8 48 0c a1 fa eb 82 90 90 90 90 90 90 fb f4 <c3> 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 f4 c3 90 90 90 90 90 90
RSP: 0018:ffff8880a98afd78 EFLAGS: 00000286 ORIG_RAX: ffffffffffffff13
RAX: 1ffffffff1125061 RBX: ffff8880a989c340 RCX: 0000000000000000
RDX: dffffc0000000000 RSI: 0000000000000001 RDI: ffff8880a989cbbc
RBP: ffff8880a98afda8 R08: ffff8880a989c340 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000001
R13: ffffffff889282f8 R14: 0000000000000001 R15: 0000000000000000
 arch_cpu_idle+0x10/0x20 arch/x86/kernel/process.c:555
 default_idle_call+0x36/0x90 kernel/sched/idle.c:93
 cpuidle_idle_call kernel/sched/idle.c:153 [inline]
 do_idle+0x386/0x570 kernel/sched/idle.c:262
 cpu_startup_entry+0x1b/0x20 kernel/sched/idle.c:353
 start_secondary+0x404/0x5c0 arch/x86/kernel/smpboot.c:271
 secondary_startup_64+0xa4/0xb0 arch/x86/kernel/head_64.S:243
Kernel Offset: disabled
Rebooting in 86400 seconds..

Fixes: 79861919b889 ("tcp: fix TCP_REPAIR xmit queue setup")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Andrey Vagin <avagin@openvz.org>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index d1676d8a6ed7..490f8b82bfa8 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2341,6 +2341,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 			/* "skb_mstamp_ns" is used as a start point for the retransmit timer */
 			skb->skb_mstamp_ns = tp->tcp_wstamp_ns = tp->tcp_clock_cache;
 			list_move_tail(&skb->tcp_tsorted_anchor, &tp->tsorted_sent_queue);
+			tcp_init_tso_segs(skb, mss_now);
 			goto repair; /* Skip network transmission */
 		}
 
-- 
2.20.1


From efe5019dc7be52f0aacdfe917240f44a5d4a91ec Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 23 Feb 2019 13:24:59 -0800
Subject: [PATCH 28/38] net/x25: fix a race in x25_bind()

[ Upstream commit 797a22bd5298c2674d927893f46cadf619dad11d ]

syzbot was able to trigger another soft lockup [1]

I first thought it was the O(N^2) issue I mentioned in my
prior fix (f657d22ee1f "net/x25: do not hold the cpu
too long in x25_new_lci()"), but I eventually found
that x25_bind() was not checking SOCK_ZAPPED state under
socket lock protection.

This means that multiple threads can end up calling
x25_insert_socket() for the same socket, and corrupt x25_list

[1]
watchdog: BUG: soft lockup - CPU#0 stuck for 123s! [syz-executor.2:10492]
Modules linked in:
irq event stamp: 27515
hardirqs last  enabled at (27514): [<ffffffff81006673>] trace_hardirqs_on_thunk+0x1a/0x1c
hardirqs last disabled at (27515): [<ffffffff8100668f>] trace_hardirqs_off_thunk+0x1a/0x1c
softirqs last  enabled at (32): [<ffffffff8632ee73>] x25_get_neigh+0xa3/0xd0 net/x25/x25_link.c:336
softirqs last disabled at (34): [<ffffffff86324bc3>] x25_find_socket+0x23/0x140 net/x25/af_x25.c:341
CPU: 0 PID: 10492 Comm: syz-executor.2 Not tainted 5.0.0-rc7+ #88
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:__sanitizer_cov_trace_pc+0x4/0x50 kernel/kcov.c:97
Code: f4 ff ff ff e8 11 9f ea ff 48 c7 05 12 fb e5 08 00 00 00 00 e9 c8 e9 ff ff 90 90 90 90 90 90 90 90 90 90 90 90 90 55 48 89 e5 <48> 8b 75 08 65 48 8b 04 25 40 ee 01 00 65 8b 15 38 0c 92 7e 81 e2
RSP: 0018:ffff88806e94fc48 EFLAGS: 00000286 ORIG_RAX: ffffffffffffff13
RAX: 1ffff1100d84dac5 RBX: 0000000000000001 RCX: ffffc90006197000
RDX: 0000000000040000 RSI: ffffffff86324bf3 RDI: ffff88806c26d628
RBP: ffff88806e94fc48 R08: ffff88806c1c6500 R09: fffffbfff1282561
R10: fffffbfff1282560 R11: ffffffff89412b03 R12: ffff88806c26d628
R13: ffff888090455200 R14: dffffc0000000000 R15: 0000000000000000
FS:  00007f3a107e4700(0000) GS:ffff8880ae800000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f3a107e3db8 CR3: 00000000a5544000 CR4: 00000000001406f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 __x25_find_socket net/x25/af_x25.c:327 [inline]
 x25_find_socket+0x7d/0x140 net/x25/af_x25.c:342
 x25_new_lci net/x25/af_x25.c:355 [inline]
 x25_connect+0x380/0xde0 net/x25/af_x25.c:784
 __sys_connect+0x266/0x330 net/socket.c:1662
 __do_sys_connect net/socket.c:1673 [inline]
 __se_sys_connect net/socket.c:1670 [inline]
 __x64_sys_connect+0x73/0xb0 net/socket.c:1670
 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x457e29
Code: ad b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f3a107e3c78 EFLAGS: 00000246 ORIG_RAX: 000000000000002a
RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000457e29
RDX: 0000000000000012 RSI: 0000000020000200 RDI: 0000000000000005
RBP: 000000000073c040 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00007f3a107e46d4
R13: 00000000004be362 R14: 00000000004ceb98 R15: 00000000ffffffff
Sending NMI from CPU 0 to CPUs 1:
NMI backtrace for cpu 1
CPU: 1 PID: 10493 Comm: syz-executor.3 Not tainted 5.0.0-rc7+ #88
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:__read_once_size include/linux/compiler.h:193 [inline]
RIP: 0010:queued_write_lock_slowpath+0x143/0x290 kernel/locking/qrwlock.c:86
Code: 4c 8d 2c 01 41 83 c7 03 41 0f b6 45 00 41 38 c7 7c 08 84 c0 0f 85 0c 01 00 00 8b 03 3d 00 01 00 00 74 1a f3 90 41 0f b6 55 00 <41> 38 d7 7c eb 84 d2 74 e7 48 89 df e8 cc aa 4e 00 eb dd be 04 00
RSP: 0018:ffff888085c47bd8 EFLAGS: 00000206
RAX: 0000000000000300 RBX: ffffffff89412b00 RCX: 1ffffffff1282560
RDX: 0000000000000000 RSI: 0000000000000004 RDI: ffffffff89412b00
RBP: ffff888085c47c70 R08: 1ffffffff1282560 R09: fffffbfff1282561
R10: fffffbfff1282560 R11: ffffffff89412b03 R12: 00000000000000ff
R13: fffffbfff1282560 R14: 1ffff11010b88f7d R15: 0000000000000003
FS:  00007fdd04086700(0000) GS:ffff8880ae900000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007fdd04064db8 CR3: 0000000090be0000 CR4: 00000000001406e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 queued_write_lock include/asm-generic/qrwlock.h:104 [inline]
 do_raw_write_lock+0x1d6/0x290 kernel/locking/spinlock_debug.c:203
 __raw_write_lock_bh include/linux/rwlock_api_smp.h:204 [inline]
 _raw_write_lock_bh+0x3b/0x50 kernel/locking/spinlock.c:312
 x25_insert_socket+0x21/0xe0 net/x25/af_x25.c:267
 x25_bind+0x273/0x340 net/x25/af_x25.c:703
 __sys_bind+0x23f/0x290 net/socket.c:1481
 __do_sys_bind net/socket.c:1492 [inline]
 __se_sys_bind net/socket.c:1490 [inline]
 __x64_sys_bind+0x73/0xb0 net/socket.c:1490
 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x457e29

Fixes: 90c27297a9bf ("X.25 remove bkl in bind")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: andrew hendry <andrew.hendry@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/x25/af_x25.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 5f7a9fab8bad..20a511398389 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -679,8 +679,7 @@ static int x25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	struct sockaddr_x25 *addr = (struct sockaddr_x25 *)uaddr;
 	int len, i, rc = 0;
 
-	if (!sock_flag(sk, SOCK_ZAPPED) ||
-	    addr_len != sizeof(struct sockaddr_x25) ||
+	if (addr_len != sizeof(struct sockaddr_x25) ||
 	    addr->sx25_family != AF_X25) {
 		rc = -EINVAL;
 		goto out;
@@ -699,9 +698,13 @@ static int x25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	}
 
 	lock_sock(sk);
-	x25_sk(sk)->source_addr = addr->sx25_addr;
-	x25_insert_socket(sk);
-	sock_reset_flag(sk, SOCK_ZAPPED);
+	if (sock_flag(sk, SOCK_ZAPPED)) {
+		x25_sk(sk)->source_addr = addr->sx25_addr;
+		x25_insert_socket(sk);
+		sock_reset_flag(sk, SOCK_ZAPPED);
+	} else {
+		rc = -EINVAL;
+	}
 	release_sock(sk);
 	SOCK_DEBUG(sk, "x25_bind: socket is bound\n");
 out:
-- 
2.20.1


From beab63aab91e49f391c5617de6122af4809e6aa8 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Thu, 21 Feb 2019 22:42:01 +0800
Subject: [PATCH 29/38] mdio_bus: Fix use-after-free on device_register fails

[ Upstream commit 6ff7b060535e87c2ae14dd8548512abfdda528fb ]

KASAN has found use-after-free in fixed_mdio_bus_init,
commit 0c692d07842a ("drivers/net/phy/mdio_bus.c: call
put_device on device_register() failure") call put_device()
while device_register() fails,give up the last reference
to the device and allow mdiobus_release to be executed
,kfreeing the bus. However in most drives, mdiobus_free
be called to free the bus while mdiobus_register fails.
use-after-free occurs when access bus again, this patch
revert it to let mdiobus_free free the bus.

KASAN report details as below:

BUG: KASAN: use-after-free in mdiobus_free+0x85/0x90 drivers/net/phy/mdio_bus.c:482
Read of size 4 at addr ffff8881dc824d78 by task syz-executor.0/3524

CPU: 1 PID: 3524 Comm: syz-executor.0 Not tainted 5.0.0-rc7+ #45
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0xfa/0x1ce lib/dump_stack.c:113
 print_address_description+0x65/0x270 mm/kasan/report.c:187
 kasan_report+0x149/0x18d mm/kasan/report.c:317
 mdiobus_free+0x85/0x90 drivers/net/phy/mdio_bus.c:482
 fixed_mdio_bus_init+0x283/0x1000 [fixed_phy]
 ? 0xffffffffc0e40000
 ? 0xffffffffc0e40000
 ? 0xffffffffc0e40000
 do_one_initcall+0xfa/0x5ca init/main.c:887
 do_init_module+0x204/0x5f6 kernel/module.c:3460
 load_module+0x66b2/0x8570 kernel/module.c:3808
 __do_sys_finit_module+0x238/0x2a0 kernel/module.c:3902
 do_syscall_64+0x147/0x600 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x462e99
Code: f7 d8 64 89 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007f6215c19c58 EFLAGS: 00000246 ORIG_RAX: 0000000000000139
RAX: ffffffffffffffda RBX: 000000000073bf00 RCX: 0000000000462e99
RDX: 0000000000000000 RSI: 0000000020000080 RDI: 0000000000000003
RBP: 00007f6215c19c70 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00007f6215c1a6bc
R13: 00000000004bcefb R14: 00000000006f7030 R15: 0000000000000004

Allocated by task 3524:
 set_track mm/kasan/common.c:85 [inline]
 __kasan_kmalloc.constprop.3+0xa0/0xd0 mm/kasan/common.c:496
 kmalloc include/linux/slab.h:545 [inline]
 kzalloc include/linux/slab.h:740 [inline]
 mdiobus_alloc_size+0x54/0x1b0 drivers/net/phy/mdio_bus.c:143
 fixed_mdio_bus_init+0x163/0x1000 [fixed_phy]
 do_one_initcall+0xfa/0x5ca init/main.c:887
 do_init_module+0x204/0x5f6 kernel/module.c:3460
 load_module+0x66b2/0x8570 kernel/module.c:3808
 __do_sys_finit_module+0x238/0x2a0 kernel/module.c:3902
 do_syscall_64+0x147/0x600 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Freed by task 3524:
 set_track mm/kasan/common.c:85 [inline]
 __kasan_slab_free+0x130/0x180 mm/kasan/common.c:458
 slab_free_hook mm/slub.c:1409 [inline]
 slab_free_freelist_hook mm/slub.c:1436 [inline]
 slab_free mm/slub.c:2986 [inline]
 kfree+0xe1/0x270 mm/slub.c:3938
 device_release+0x78/0x200 drivers/base/core.c:919
 kobject_cleanup lib/kobject.c:662 [inline]
 kobject_release lib/kobject.c:691 [inline]
 kref_put include/linux/kref.h:67 [inline]
 kobject_put+0x146/0x240 lib/kobject.c:708
 put_device+0x1c/0x30 drivers/base/core.c:2060
 __mdiobus_register+0x483/0x560 drivers/net/phy/mdio_bus.c:382
 fixed_mdio_bus_init+0x26b/0x1000 [fixed_phy]
 do_one_initcall+0xfa/0x5ca init/main.c:887
 do_init_module+0x204/0x5f6 kernel/module.c:3460
 load_module+0x66b2/0x8570 kernel/module.c:3808
 __do_sys_finit_module+0x238/0x2a0 kernel/module.c:3902
 do_syscall_64+0x147/0x600 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

The buggy address belongs to the object at ffff8881dc824c80
 which belongs to the cache kmalloc-2k of size 2048
The buggy address is located 248 bytes inside of
 2048-byte region [ffff8881dc824c80, ffff8881dc825480)
The buggy address belongs to the page:
page:ffffea0007720800 count:1 mapcount:0 mapping:ffff8881f6c02800 index:0x0 compound_mapcount: 0
flags: 0x2fffc0000010200(slab|head)
raw: 02fffc0000010200 0000000000000000 0000000500000001 ffff8881f6c02800
raw: 0000000000000000 00000000800f000f 00000001ffffffff 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff8881dc824c00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 ffff8881dc824c80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff8881dc824d00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                                                                ^
 ffff8881dc824d80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff8881dc824e00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb

Fixes: 0c692d07842a ("drivers/net/phy/mdio_bus.c: call put_device on device_register() failure")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mdio_bus.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index 66b9cfe692fc..7368616286ae 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -379,7 +379,6 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner)
 	err = device_register(&bus->dev);
 	if (err) {
 		pr_err("mii_bus %s failed to register\n", bus->id);
-		put_device(&bus->dev);
 		return -EINVAL;
 	}
 
-- 
2.20.1


From 189648a7be3aa6533e43dac9c43f20793a7cf5a1 Mon Sep 17 00:00:00 2001
From: Kalash Nainwal <kalash@arista.com>
Date: Wed, 20 Feb 2019 16:23:04 -0800
Subject: [PATCH 30/38] net: Set rtm_table to RT_TABLE_COMPAT for ipv6 for
 tables > 255

[ Upstream commit 97f0082a0592212fc15d4680f5a4d80f79a1687c ]

Set rtm_table to RT_TABLE_COMPAT for ipv6 for tables > 255 to
keep legacy software happy. This is similar to what was done for
ipv4 in commit 709772e6e065 ("net: Fix routing tables with
id > 255 for legacy software").

Signed-off-by: Kalash Nainwal <kalash@arista.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index c87ce5732338..a4ec629e1562 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -4660,7 +4660,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 		table = rt->fib6_table->tb6_id;
 	else
 		table = RT6_TABLE_UNSPEC;
-	rtm->rtm_table = table;
+	rtm->rtm_table = table < 256 ? table : RT_TABLE_COMPAT;
 	if (nla_put_u32(skb, RTA_TABLE, table))
 		goto nla_put_failure;
 
-- 
2.20.1


From 9351cf7187636b61575f38ce99d1cd2688e07aea Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 20 Feb 2019 18:18:12 +0100
Subject: [PATCH 31/38] ipv6: route: purge exception on removal

[ Upstream commit f5b51fe804ec2a6edce0f8f6b11ea57283f5857b ]

When a netdevice is unregistered, we flush the relevant exception
via rt6_sync_down_dev() -> fib6_ifdown() -> fib6_del() -> fib6_del_route().

Finally, we end-up calling rt6_remove_exception(), where we release
the relevant dst, while we keep the references to the related fib6_info and
dev. Such references should be released later when the dst will be
destroyed.

There are a number of caches that can keep the exception around for an
unlimited amount of time - namely dst_cache, possibly even socket cache.
As a result device registration may hang, as demonstrated by this script:

ip netns add cl
ip netns add rt
ip netns add srv
ip netns exec rt sysctl -w net.ipv6.conf.all.forwarding=1

ip link add name cl_veth type veth peer name cl_rt_veth
ip link set dev cl_veth netns cl
ip -n cl link set dev cl_veth up
ip -n cl addr add dev cl_veth 2001::2/64
ip -n cl route add default via 2001::1

ip -n cl link add tunv6 type ip6tnl mode ip6ip6 local 2001::2 remote 2002::1 hoplimit 64 dev cl_veth
ip -n cl link set tunv6 up
ip -n cl addr add 2013::2/64 dev tunv6

ip link set dev cl_rt_veth netns rt
ip -n rt link set dev cl_rt_veth up
ip -n rt addr add dev cl_rt_veth 2001::1/64

ip link add name rt_srv_veth type veth peer name srv_veth
ip link set dev srv_veth netns srv
ip -n srv link set dev srv_veth up
ip -n srv addr add dev srv_veth 2002::1/64
ip -n srv route add default via 2002::2

ip -n srv link add tunv6 type ip6tnl mode ip6ip6 local 2002::1 remote 2001::2 hoplimit 64 dev srv_veth
ip -n srv link set tunv6 up
ip -n srv addr add 2013::1/64 dev tunv6

ip link set dev rt_srv_veth netns rt
ip -n rt link set dev rt_srv_veth up
ip -n rt addr add dev rt_srv_veth 2002::2/64

ip netns exec srv netserver & sleep 0.1
ip netns exec cl ping6 -c 4 2013::1
ip netns exec cl netperf -H 2013::1 -t TCP_STREAM -l 3 & sleep 1
ip -n rt link set dev rt_srv_veth mtu 1400
wait %2

ip -n cl link del cl_veth

This commit addresses the issue purging all the references held by the
exception at time, as we currently do for e.g. ipv6 pcpu dst entries.

v1 -> v2:
 - re-order the code to avoid accessing dst and net after dst_dev_put()

Fixes: 93531c674315 ("net/ipv6: separate handling of FIB entries from dst based routes")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index a4ec629e1562..e8eb4de0b792 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1272,18 +1272,29 @@ static DEFINE_SPINLOCK(rt6_exception_lock);
 static void rt6_remove_exception(struct rt6_exception_bucket *bucket,
 				 struct rt6_exception *rt6_ex)
 {
+	struct fib6_info *from;
 	struct net *net;
 
 	if (!bucket || !rt6_ex)
 		return;
 
 	net = dev_net(rt6_ex->rt6i->dst.dev);
+	net->ipv6.rt6_stats->fib_rt_cache--;
+
+	/* purge completely the exception to allow releasing the held resources:
+	 * some [sk] cache may keep the dst around for unlimited time
+	 */
+	from = rcu_dereference_protected(rt6_ex->rt6i->from,
+					 lockdep_is_held(&rt6_exception_lock));
+	rcu_assign_pointer(rt6_ex->rt6i->from, NULL);
+	fib6_info_release(from);
+	dst_dev_put(&rt6_ex->rt6i->dst);
+
 	hlist_del_rcu(&rt6_ex->hlist);
 	dst_release(&rt6_ex->rt6i->dst);
 	kfree_rcu(rt6_ex, rcu);
 	WARN_ON_ONCE(!bucket->depth);
 	bucket->depth--;
-	net->ipv6.rt6_stats->fib_rt_cache--;
 }
 
 /* Remove oldest rt6_ex in bucket and free the memory
-- 
2.20.1


From 105d91b9da4d194b8ae7181555cdfa15acaf8777 Mon Sep 17 00:00:00 2001
From: George Wilkie <gwilkie@vyatta.att-mail.com>
Date: Wed, 20 Feb 2019 08:19:11 +0000
Subject: [PATCH 32/38] team: use operstate consistently for linkup

[ Upstream commit 8c7a77267eec81dd81af8412f29e50c0b1082548 ]

When a port is added to a team, its initial state is derived
from netif_carrier_ok rather than netif_oper_up.
If it is carrier up but operationally down at the time of being
added, the port state.linkup will be set prematurely.
port state.linkup should be set consistently using
netif_oper_up rather than netif_carrier_ok.

Fixes: f1d22a1e0595 ("team: account for oper state")
Signed-off-by: George Wilkie <gwilkie@vyatta.att-mail.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 86db1205a396..00632a45928f 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1256,7 +1256,7 @@ static int team_port_add(struct team *team, struct net_device *port_dev,
 	list_add_tail_rcu(&port->list, &team->port_list);
 	team_port_enable(team, port);
 	__team_compute_features(team);
-	__team_port_change_port_added(port, !!netif_carrier_ok(port_dev));
+	__team_port_change_port_added(port, !!netif_oper_up(port_dev));
 	__team_options_change_check(team);
 
 	netdev_info(dev, "Port device %s added\n", portname);
@@ -2915,7 +2915,7 @@ static int team_device_event(struct notifier_block *unused,
 
 	switch (event) {
 	case NETDEV_UP:
-		if (netif_carrier_ok(dev))
+		if (netif_oper_up(dev))
 			team_port_change_check(port, true);
 		break;
 	case NETDEV_DOWN:
-- 
2.20.1


From 40dcf8b16cdd518e6a4fdd620368367e7da0502d Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 20 Feb 2019 00:15:30 +0100
Subject: [PATCH 33/38] ipvlan: disallow userns cap_net_admin to change global
 mode/flags

[ Upstream commit 7cc9f7003a969d359f608ebb701d42cafe75b84a ]

When running Docker with userns isolation e.g. --userns-remap="default"
and spawning up some containers with CAP_NET_ADMIN under this realm, I
noticed that link changes on ipvlan slave device inside that container
can affect all devices from this ipvlan group which are in other net
namespaces where the container should have no permission to make changes
to, such as the init netns, for example.

This effectively allows to undo ipvlan private mode and switch globally to
bridge mode where slaves can communicate directly without going through
hostns, or it allows to switch between global operation mode (l2/l3/l3s)
for everyone bound to the given ipvlan master device. libnetwork plugin
here is creating an ipvlan master and ipvlan slave in hostns and a slave
each that is moved into the container's netns upon creation event.

* In hostns:

  # ip -d a
  [...]
  8: cilium_host@bond0: <BROADCAST,MULTICAST,NOARP,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN group default qlen 1000
     link/ether 0c:c4:7a:e1:3d:cc brd ff:ff:ff:ff:ff:ff promiscuity 0 minmtu 68 maxmtu 65535
     ipvlan  mode l3 bridge numtxqueues 1 numrxqueues 1 gso_max_size 65536 gso_max_segs 65535
     inet 10.41.0.1/32 scope link cilium_host
       valid_lft forever preferred_lft forever
  [...]

* Spawn container & change ipvlan mode setting inside of it:

  # docker run -dt --cap-add=NET_ADMIN --network cilium-net --name client -l app=test cilium/netperf
  9fff485d69dcb5ce37c9e33ca20a11ccafc236d690105aadbfb77e4f4170879c

  # docker exec -ti client ip -d a
  [...]
  10: cilium0@if4: <BROADCAST,MULTICAST,NOARP,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN group default qlen 1000
      link/ether 0c:c4:7a:e1:3d:cc brd ff:ff:ff:ff:ff:ff promiscuity 0 minmtu 68 maxmtu 65535
      ipvlan  mode l3 bridge numtxqueues 1 numrxqueues 1 gso_max_size 65536 gso_max_segs 65535
      inet 10.41.197.43/32 brd 10.41.197.43 scope global cilium0
         valid_lft forever preferred_lft forever

  # docker exec -ti client ip link change link cilium0 name cilium0 type ipvlan mode l2

  # docker exec -ti client ip -d a
  [...]
  10: cilium0@if4: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN group default qlen 1000
      link/ether 0c:c4:7a:e1:3d:cc brd ff:ff:ff:ff:ff:ff promiscuity 0 minmtu 68 maxmtu 65535
      ipvlan  mode l2 bridge numtxqueues 1 numrxqueues 1 gso_max_size 65536 gso_max_segs 65535
      inet 10.41.197.43/32 brd 10.41.197.43 scope global cilium0
         valid_lft forever preferred_lft forever

* In hostns (mode switched to l2):

  # ip -d a
  [...]
  8: cilium_host@bond0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN group default qlen 1000
      link/ether 0c:c4:7a:e1:3d:cc brd ff:ff:ff:ff:ff:ff promiscuity 0 minmtu 68 maxmtu 65535
      ipvlan  mode l2 bridge numtxqueues 1 numrxqueues 1 gso_max_size 65536 gso_max_segs 65535
      inet 10.41.0.1/32 scope link cilium_host
         valid_lft forever preferred_lft forever
  [...]

Same l3 -> l2 switch would also happen by creating another slave inside
the container's network namespace when specifying the existing cilium0
link to derive the actual (bond0) master:

  # docker exec -ti client ip link add link cilium0 name cilium1 type ipvlan mode l2

  # docker exec -ti client ip -d a
  [...]
  2: cilium1@if4: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN group default qlen 1000
      link/ether 0c:c4:7a:e1:3d:cc brd ff:ff:ff:ff:ff:ff promiscuity 0 minmtu 68 maxmtu 65535
      ipvlan  mode l2 bridge numtxqueues 1 numrxqueues 1 gso_max_size 65536 gso_max_segs 65535
  10: cilium0@if4: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN group default qlen 1000
      link/ether 0c:c4:7a:e1:3d:cc brd ff:ff:ff:ff:ff:ff promiscuity 0 minmtu 68 maxmtu 65535
      ipvlan  mode l2 bridge numtxqueues 1 numrxqueues 1 gso_max_size 65536 gso_max_segs 65535
      inet 10.41.197.43/32 brd 10.41.197.43 scope global cilium0
         valid_lft forever preferred_lft forever

* In hostns:

  # ip -d a
  [...]
  8: cilium_host@bond0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN group default qlen 1000
      link/ether 0c:c4:7a:e1:3d:cc brd ff:ff:ff:ff:ff:ff promiscuity 0 minmtu 68 maxmtu 65535
      ipvlan  mode l2 bridge numtxqueues 1 numrxqueues 1 gso_max_size 65536 gso_max_segs 65535
      inet 10.41.0.1/32 scope link cilium_host
         valid_lft forever preferred_lft forever
  [...]

One way to mitigate it is to check CAP_NET_ADMIN permissions of
the ipvlan master device's ns, and only then allow to change
mode or flags for all devices bound to it. Above two cases are
then disallowed after the patch.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ipvlan/ipvlan_main.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 5fb541897863..68b8007da82b 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -494,6 +494,8 @@ static int ipvlan_nl_changelink(struct net_device *dev,
 
 	if (!data)
 		return 0;
+	if (!ns_capable(dev_net(ipvlan->phy_dev)->user_ns, CAP_NET_ADMIN))
+		return -EPERM;
 
 	if (data[IFLA_IPVLAN_MODE]) {
 		u16 nmode = nla_get_u16(data[IFLA_IPVLAN_MODE]);
@@ -596,6 +598,8 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev,
 		struct ipvl_dev *tmp = netdev_priv(phy_dev);
 
 		phy_dev = tmp->phy_dev;
+		if (!ns_capable(dev_net(phy_dev)->user_ns, CAP_NET_ADMIN))
+			return -EPERM;
 	} else if (!netif_is_ipvlan_port(phy_dev)) {
 		/* Exit early if the underlying link is invalid or busy */
 		if (phy_dev->type != ARPHRD_ETHER ||
-- 
2.20.1


From eab5530b018005a7681b930c684271cba0aee9a1 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 21 Feb 2019 11:19:41 +0100
Subject: [PATCH 34/38] ipv6: route: enforce RCU protection in
 rt6_update_exception_stamp_rt()

[ Upstream commit 193f3685d0546b0cea20c99894aadb70098e47bf ]

We must access rt6_info->from under RCU read lock: move the
dereference under such lock, with proper annotation.

v1 -> v2:
 - avoid using multiple, racy, fetch operations for rt->from

Fixes: a68886a69180 ("net/ipv6: Make from in rt6_info rcu protected")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index e8eb4de0b792..7e21797d7ae8 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1608,15 +1608,15 @@ static int rt6_remove_exception_rt(struct rt6_info *rt)
 static void rt6_update_exception_stamp_rt(struct rt6_info *rt)
 {
 	struct rt6_exception_bucket *bucket;
-	struct fib6_info *from = rt->from;
 	struct in6_addr *src_key = NULL;
 	struct rt6_exception *rt6_ex;
-
-	if (!from ||
-	    !(rt->rt6i_flags & RTF_CACHE))
-		return;
+	struct fib6_info *from;
 
 	rcu_read_lock();
+	from = rcu_dereference(rt->from);
+	if (!from || !(rt->rt6i_flags & RTF_CACHE))
+		goto unlock;
+
 	bucket = rcu_dereference(from->rt6i_exception_bucket);
 
 #ifdef CONFIG_IPV6_SUBTREES
@@ -1635,6 +1635,7 @@ static void rt6_update_exception_stamp_rt(struct rt6_info *rt)
 	if (rt6_ex)
 		rt6_ex->stamp = jiffies;
 
+unlock:
 	rcu_read_unlock();
 }
 
-- 
2.20.1


From e97df155863e58277edc839ce5b15858b0a26a5b Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 21 Feb 2019 11:19:42 +0100
Subject: [PATCH 35/38] ipv6: route: enforce RCU protection in
 ip6_route_check_nh_onlink()

[ Upstream commit bf1dc8bad1d42287164d216d8efb51c5cd381b18 ]

We need a RCU critical section around rt6_info->from deference, and
proper annotation.

Fixes: 4ed591c8ab44 ("net/ipv6: Allow onlink routes to have a device mismatch if it is the default route")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 7e21797d7ae8..603488cf132d 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2752,20 +2752,24 @@ static int ip6_route_check_nh_onlink(struct net *net,
 	u32 tbid = l3mdev_fib_table(dev) ? : RT_TABLE_MAIN;
 	const struct in6_addr *gw_addr = &cfg->fc_gateway;
 	u32 flags = RTF_LOCAL | RTF_ANYCAST | RTF_REJECT;
+	struct fib6_info *from;
 	struct rt6_info *grt;
 	int err;
 
 	err = 0;
 	grt = ip6_nh_lookup_table(net, cfg, gw_addr, tbid, 0);
 	if (grt) {
+		rcu_read_lock();
+		from = rcu_dereference(grt->from);
 		if (!grt->dst.error &&
 		    /* ignore match if it is the default route */
-		    grt->from && !ipv6_addr_any(&grt->from->fib6_dst.addr) &&
+		    from && !ipv6_addr_any(&from->fib6_dst.addr) &&
 		    (grt->rt6i_flags & flags || dev != grt->dst.dev)) {
 			NL_SET_ERR_MSG(extack,
 				       "Nexthop has invalid gateway or device mismatch");
 			err = -EINVAL;
 		}
+		rcu_read_unlock();
 
 		ip6_rt_put(grt);
 	}
-- 
2.20.1


From 88c0eeafbae029eeb602caf3395f30f690dcef93 Mon Sep 17 00:00:00 2001
From: Michal Soltys <soltys@ziu.info>
Date: Mon, 18 Feb 2019 17:55:28 +0100
Subject: [PATCH 36/38] bonding: fix PACKET_ORIGDEV regression
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 3c963a3306eada999be5ebf4f293dfa3d3945487 ]

This patch fixes a subtle PACKET_ORIGDEV regression which was a side
effect of fixes introduced by:

6a9e461f6fe4 bonding: pass link-local packets to bonding master also.

... to:

b89f04c61efe bonding: deliver link-local packets with skb->dev set to link that packets arrived on

While 6a9e461f6fe4 restored pre-b89f04c61efe presence of link-local
packets on bonding masters (which is required e.g. by linux bridges
participating in spanning tree or needed for lab-like setups created
with group_fwd_mask) it also caused the originating device
information to be lost due to cloning.

Maciej Żenczykowski proposed another solution that doesn't require
packet cloning and retains original device information - instead of
returning RX_HANDLER_PASS for all link-local packets it's now limited
only to packets from inactive slaves.

At the same time, packets passed to bonding masters retain correct
information about the originating device and PACKET_ORIGDEV can be used
to determine it.

This elegantly solves all issues so far:

- link-local packets that were removed from bonding masters
- LLDP daemons being forced to explicitly bind to slave interfaces
- PACKET_ORIGDEV having no effect on bond interfaces

Fixes: 6a9e461f6fe4 (bonding: pass link-local packets to bonding master also.)
Reported-by: Vincent Bernat <vincent@bernat.ch>
Signed-off-by: Michal Soltys <soltys@ziu.info>
Signed-off-by: Maciej Żenczykowski <maze@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 35 +++++++++++++--------------------
 1 file changed, 14 insertions(+), 21 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 62659abf73cd..f6100918328f 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1172,29 +1172,22 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb)
 		}
 	}
 
-	/* Link-local multicast packets should be passed to the
-	 * stack on the link they arrive as well as pass them to the
-	 * bond-master device. These packets are mostly usable when
-	 * stack receives it with the link on which they arrive
-	 * (e.g. LLDP) they also must be available on master. Some of
-	 * the use cases include (but are not limited to): LLDP agents
-	 * that must be able to operate both on enslaved interfaces as
-	 * well as on bonds themselves; linux bridges that must be able
-	 * to process/pass BPDUs from attached bonds when any kind of
-	 * STP version is enabled on the network.
+	/*
+	 * For packets determined by bond_should_deliver_exact_match() call to
+	 * be suppressed we want to make an exception for link-local packets.
+	 * This is necessary for e.g. LLDP daemons to be able to monitor
+	 * inactive slave links without being forced to bind to them
+	 * explicitly.
+	 *
+	 * At the same time, packets that are passed to the bonding master
+	 * (including link-local ones) can have their originating interface
+	 * determined via PACKET_ORIGDEV socket option.
 	 */
-	if (is_link_local_ether_addr(eth_hdr(skb)->h_dest)) {
-		struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
-
-		if (nskb) {
-			nskb->dev = bond->dev;
-			nskb->queue_mapping = 0;
-			netif_rx(nskb);
-		}
-		return RX_HANDLER_PASS;
-	}
-	if (bond_should_deliver_exact_match(skb, slave, bond))
+	if (bond_should_deliver_exact_match(skb, slave, bond)) {
+		if (is_link_local_ether_addr(eth_hdr(skb)->h_dest))
+			return RX_HANDLER_PASS;
 		return RX_HANDLER_EXACT;
+	}
 
 	skb->dev = bond->dev;
 
-- 
2.20.1


From 91096594da9f8de448425dde03c513b6ff729aed Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.ibm.com>
Date: Thu, 21 Feb 2019 12:56:54 +0100
Subject: [PATCH 37/38] net/smc: fix smc_poll in SMC_INIT state

[ Upstream commit d7cf4a3bf3a83c977a29055e1c4ffada7697b31f ]

smc_poll() returns with mask bit EPOLLPRI if the connection urg_state
is SMC_URG_VALID. Since SMC_URG_VALID is zero, smc_poll signals
EPOLLPRI errorneously if called in state SMC_INIT before the connection
is created, for instance in a non-blocking connect scenario.

This patch switches to non-zero values for the urg states.

Reviewed-by: Karsten Graul <kgraul@linux.ibm.com>
Fixes: de8474eb9d50 ("net/smc: urgent data support")
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/smc.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/smc/smc.h b/net/smc/smc.h
index 5721416d0605..adbdf195eb08 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -113,9 +113,9 @@ struct smc_host_cdc_msg {		/* Connection Data Control message */
 } __aligned(8);
 
 enum smc_urg_state {
-	SMC_URG_VALID,			/* data present */
-	SMC_URG_NOTYET,			/* data pending */
-	SMC_URG_READ			/* data was already read */
+	SMC_URG_VALID	= 1,			/* data present */
+	SMC_URG_NOTYET	= 2,			/* data pending */
+	SMC_URG_READ	= 3,			/* data was already read */
 };
 
 struct smc_connection {
-- 
2.20.1


From aaca1f337fe8bd60bc074841e57a739595572247 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 15 Feb 2019 20:09:35 +0000
Subject: [PATCH 38/38] missing barriers in some of unix_sock ->addr and ->path
 accesses

[ Upstream commit ae3b564179bfd06f32d051b9e5d72ce4b2a07c37 ]

Several u->addr and u->path users are not holding any locks in
common with unix_bind().  unix_state_lock() is useless for those
purposes.

u->addr is assign-once and *(u->addr) is fully set up by the time
we set u->addr (all under unix_table_lock).  u->path is also
set in the same critical area, also before setting u->addr, and
any unix_sock with ->path filled will have non-NULL ->addr.

So setting ->addr with smp_store_release() is all we need for those
"lockless" users - just have them fetch ->addr with smp_load_acquire()
and don't even bother looking at ->path if they see NULL ->addr.

Users of ->addr and ->path fall into several classes now:
    1) ones that do smp_load_acquire(u->addr) and access *(u->addr)
and u->path only if smp_load_acquire() has returned non-NULL.
    2) places holding unix_table_lock.  These are guaranteed that
*(u->addr) is seen fully initialized.  If unix_sock is in one of the
"bound" chains, so's ->path.
    3) unix_sock_destructor() using ->addr is safe.  All places
that set u->addr are guaranteed to have seen all stores *(u->addr)
while holding a reference to u and unix_sock_destructor() is called
when (atomic) refcount hits zero.
    4) unix_release_sock() using ->path is safe.  unix_bind()
is serialized wrt unix_release() (normally - by struct file
refcount), and for the instances that had ->path set by unix_bind()
unix_release_sock() comes from unix_release(), so they are fine.
Instances that had it set in unix_stream_connect() either end up
attached to a socket (in unix_accept()), in which case the call
chain to unix_release_sock() and serialization are the same as in
the previous case, or they never get accept'ed and unix_release_sock()
is called when the listener is shut down and its queue gets purged.
In that case the listener's queue lock provides the barriers needed -
unix_stream_connect() shoves our unix_sock into listener's queue
under that lock right after having set ->path and eventual
unix_release_sock() caller picks them from that queue under the
same lock right before calling unix_release_sock().
    5) unix_find_other() use of ->path is pointless, but safe -
it happens with successful lookup by (abstract) name, so ->path.dentry
is guaranteed to be NULL there.

earlier-variant-reviewed-by: "Paul E. McKenney" <paulmck@linux.ibm.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c   | 57 +++++++++++++++++++++++++-------------------
 net/unix/diag.c      |  3 ++-
 security/lsm_audit.c | 10 ++++----
 3 files changed, 41 insertions(+), 29 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 74d1eed7cbd4..a95d479caeea 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -890,7 +890,7 @@ static int unix_autobind(struct socket *sock)
 	addr->hash ^= sk->sk_type;
 
 	__unix_remove_socket(sk);
-	u->addr = addr;
+	smp_store_release(&u->addr, addr);
 	__unix_insert_socket(&unix_socket_table[addr->hash], sk);
 	spin_unlock(&unix_table_lock);
 	err = 0;
@@ -1060,7 +1060,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 
 	err = 0;
 	__unix_remove_socket(sk);
-	u->addr = addr;
+	smp_store_release(&u->addr, addr);
 	__unix_insert_socket(list, sk);
 
 out_unlock:
@@ -1331,15 +1331,29 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 	RCU_INIT_POINTER(newsk->sk_wq, &newu->peer_wq);
 	otheru = unix_sk(other);
 
-	/* copy address information from listening to new sock*/
-	if (otheru->addr) {
-		refcount_inc(&otheru->addr->refcnt);
-		newu->addr = otheru->addr;
-	}
+	/* copy address information from listening to new sock
+	 *
+	 * The contents of *(otheru->addr) and otheru->path
+	 * are seen fully set up here, since we have found
+	 * otheru in hash under unix_table_lock.  Insertion
+	 * into the hash chain we'd found it in had been done
+	 * in an earlier critical area protected by unix_table_lock,
+	 * the same one where we'd set *(otheru->addr) contents,
+	 * as well as otheru->path and otheru->addr itself.
+	 *
+	 * Using smp_store_release() here to set newu->addr
+	 * is enough to make those stores, as well as stores
+	 * to newu->path visible to anyone who gets newu->addr
+	 * by smp_load_acquire().  IOW, the same warranties
+	 * as for unix_sock instances bound in unix_bind() or
+	 * in unix_autobind().
+	 */
 	if (otheru->path.dentry) {
 		path_get(&otheru->path);
 		newu->path = otheru->path;
 	}
+	refcount_inc(&otheru->addr->refcnt);
+	smp_store_release(&newu->addr, otheru->addr);
 
 	/* Set credentials */
 	copy_peercred(sk, other);
@@ -1453,7 +1467,7 @@ static int unix_accept(struct socket *sock, struct socket *newsock, int flags,
 static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int peer)
 {
 	struct sock *sk = sock->sk;
-	struct unix_sock *u;
+	struct unix_address *addr;
 	DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, uaddr);
 	int err = 0;
 
@@ -1468,19 +1482,15 @@ static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int peer)
 		sock_hold(sk);
 	}
 
-	u = unix_sk(sk);
-	unix_state_lock(sk);
-	if (!u->addr) {
+	addr = smp_load_acquire(&unix_sk(sk)->addr);
+	if (!addr) {
 		sunaddr->sun_family = AF_UNIX;
 		sunaddr->sun_path[0] = 0;
 		err = sizeof(short);
 	} else {
-		struct unix_address *addr = u->addr;
-
 		err = addr->len;
 		memcpy(sunaddr, addr->name, addr->len);
 	}
-	unix_state_unlock(sk);
 	sock_put(sk);
 out:
 	return err;
@@ -2073,11 +2083,11 @@ static int unix_seqpacket_recvmsg(struct socket *sock, struct msghdr *msg,
 
 static void unix_copy_addr(struct msghdr *msg, struct sock *sk)
 {
-	struct unix_sock *u = unix_sk(sk);
+	struct unix_address *addr = smp_load_acquire(&unix_sk(sk)->addr);
 
-	if (u->addr) {
-		msg->msg_namelen = u->addr->len;
-		memcpy(msg->msg_name, u->addr->name, u->addr->len);
+	if (addr) {
+		msg->msg_namelen = addr->len;
+		memcpy(msg->msg_name, addr->name, addr->len);
 	}
 }
 
@@ -2581,15 +2591,14 @@ static int unix_open_file(struct sock *sk)
 	if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
-	unix_state_lock(sk);
+	if (!smp_load_acquire(&unix_sk(sk)->addr))
+		return -ENOENT;
+
 	path = unix_sk(sk)->path;
-	if (!path.dentry) {
-		unix_state_unlock(sk);
+	if (!path.dentry)
 		return -ENOENT;
-	}
 
 	path_get(&path);
-	unix_state_unlock(sk);
 
 	fd = get_unused_fd_flags(O_CLOEXEC);
 	if (fd < 0)
@@ -2830,7 +2839,7 @@ static int unix_seq_show(struct seq_file *seq, void *v)
 			(s->sk_state == TCP_ESTABLISHED ? SS_CONNECTING : SS_DISCONNECTING),
 			sock_i_ino(s));
 
-		if (u->addr) {
+		if (u->addr) {	// under unix_table_lock here
 			int i, len;
 			seq_putc(seq, ' ');
 
diff --git a/net/unix/diag.c b/net/unix/diag.c
index 384c84e83462..3183d9b8ab33 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -10,7 +10,8 @@
 
 static int sk_diag_dump_name(struct sock *sk, struct sk_buff *nlskb)
 {
-	struct unix_address *addr = unix_sk(sk)->addr;
+	/* might or might not have unix_table_lock */
+	struct unix_address *addr = smp_load_acquire(&unix_sk(sk)->addr);
 
 	if (!addr)
 		return 0;
diff --git a/security/lsm_audit.c b/security/lsm_audit.c
index f84001019356..33028c098ef3 100644
--- a/security/lsm_audit.c
+++ b/security/lsm_audit.c
@@ -321,6 +321,7 @@ static void dump_common_audit_data(struct audit_buffer *ab,
 		if (a->u.net->sk) {
 			struct sock *sk = a->u.net->sk;
 			struct unix_sock *u;
+			struct unix_address *addr;
 			int len = 0;
 			char *p = NULL;
 
@@ -351,14 +352,15 @@ static void dump_common_audit_data(struct audit_buffer *ab,
 #endif
 			case AF_UNIX:
 				u = unix_sk(sk);
+				addr = smp_load_acquire(&u->addr);
+				if (!addr)
+					break;
 				if (u->path.dentry) {
 					audit_log_d_path(ab, " path=", &u->path);
 					break;
 				}
-				if (!u->addr)
-					break;
-				len = u->addr->len-sizeof(short);
-				p = &u->addr->name->sun_path[0];
+				len = addr->len-sizeof(short);
+				p = &addr->name->sun_path[0];
 				audit_log_format(ab, " path=");
 				if (*p)
 					audit_log_untrustedstring(ab, p);
-- 
2.20.1


[-- Attachment #3: net_50.mbox --]
[-- Type: Application/Octet-Stream, Size: 111029 bytes --]

From a1bcccf0503af0b8cb0e1bf21729b06544e97ea1 Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Wed, 6 Mar 2019 14:46:27 +0800
Subject: [PATCH 01/30] connector: fix unsafe usage of ->real_parent

[ Upstream commit 6d2b0f02f5a07a4bf02e4cbc90d7eaa85cac2986 ]

proc_exit_connector() uses ->real_parent lockless. This is not
safe that its parent can go away at any moment, so use RCU to
protect it, and ensure that this task is not released.

[  747.624551] ==================================================================
[  747.632946] BUG: KASAN: use-after-free in proc_exit_connector+0x1f7/0x310
[  747.640686] Read of size 4 at addr ffff88a0276988e0 by task sshd/2882
[  747.648032]
[  747.649804] CPU: 11 PID: 2882 Comm: sshd Tainted: G            E     4.19.26-rc2 #11
[  747.658629] Hardware name: IBM x3550M4 -[7914OFV]-/00AM544, BIOS -[D7E142BUS-1.71]- 07/31/2014
[  747.668419] Call Trace:
[  747.671269]  dump_stack+0xf0/0x19b
[  747.675186]  ? show_regs_print_info+0x5/0x5
[  747.679988]  ? kmsg_dump_rewind_nolock+0x59/0x59
[  747.685302]  print_address_description+0x6a/0x270
[  747.691162]  kasan_report+0x258/0x380
[  747.695835]  ? proc_exit_connector+0x1f7/0x310
[  747.701402]  proc_exit_connector+0x1f7/0x310
[  747.706767]  ? proc_coredump_connector+0x2d0/0x2d0
[  747.712715]  ? _raw_write_unlock_irq+0x29/0x50
[  747.718270]  ? _raw_write_unlock_irq+0x29/0x50
[  747.723820]  ? ___preempt_schedule+0x16/0x18
[  747.729193]  ? ___preempt_schedule+0x16/0x18
[  747.734574]  do_exit+0xa11/0x14f0
[  747.738880]  ? mm_update_next_owner+0x590/0x590
[  747.744525]  ? debug_show_all_locks+0x3c0/0x3c0
[  747.761448]  ? ktime_get_coarse_real_ts64+0xeb/0x1c0
[  747.767589]  ? lockdep_hardirqs_on+0x1a6/0x290
[  747.773154]  ? check_chain_key+0x139/0x1f0
[  747.778345]  ? check_flags.part.35+0x240/0x240
[  747.783908]  ? __lock_acquire+0x2300/0x2300
[  747.789171]  ? _raw_spin_unlock_irqrestore+0x59/0x70
[  747.795316]  ? _raw_spin_unlock_irqrestore+0x59/0x70
[  747.801457]  ? do_raw_spin_unlock+0x10f/0x1e0
[  747.806914]  ? do_raw_spin_trylock+0x120/0x120
[  747.812481]  ? preempt_count_sub+0x14/0xc0
[  747.817645]  ? _raw_spin_unlock+0x2e/0x50
[  747.822708]  ? __handle_mm_fault+0x12db/0x1fa0
[  747.828367]  ? __pmd_alloc+0x2d0/0x2d0
[  747.833143]  ? check_noncircular+0x50/0x50
[  747.838309]  ? match_held_lock+0x7f/0x340
[  747.843380]  ? check_noncircular+0x50/0x50
[  747.848561]  ? handle_mm_fault+0x21a/0x5f0
[  747.853730]  ? check_flags.part.35+0x240/0x240
[  747.859290]  ? check_chain_key+0x139/0x1f0
[  747.864474]  ? __do_page_fault+0x40f/0x760
[  747.869655]  ? __audit_syscall_entry+0x4b/0x1f0
[  747.875319]  ? syscall_trace_enter+0x1d5/0x7b0
[  747.880877]  ? trace_raw_output_preemptirq_template+0x90/0x90
[  747.887895]  ? trace_raw_output_sys_exit+0x80/0x80
[  747.893860]  ? up_read+0x3b/0x90
[  747.898142]  ? stop_critical_timings+0x260/0x260
[  747.903909]  do_group_exit+0xe0/0x1c0
[  747.908591]  ? __x64_sys_exit+0x30/0x30
[  747.913460]  ? trace_raw_output_preemptirq_template+0x90/0x90
[  747.920485]  ? tracer_hardirqs_on+0x270/0x270
[  747.925956]  __x64_sys_exit_group+0x28/0x30
[  747.931214]  do_syscall_64+0x117/0x400
[  747.935988]  ? syscall_return_slowpath+0x2f0/0x2f0
[  747.941931]  ? trace_hardirqs_off_thunk+0x1a/0x1c
[  747.947788]  ? trace_hardirqs_on_caller+0x1d0/0x1d0
[  747.953838]  ? lockdep_sys_exit+0x16/0x8e
[  747.958915]  ? trace_hardirqs_off_thunk+0x1a/0x1c
[  747.964784]  entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  747.971021] RIP: 0033:0x7f572f154c68
[  747.975606] Code: Bad RIP value.
[  747.979791] RSP: 002b:00007ffed2dfaa58 EFLAGS: 00000246 ORIG_RAX: 00000000000000e7
[  747.989324] RAX: ffffffffffffffda RBX: 00007f572f431840 RCX: 00007f572f154c68
[  747.997910] RDX: 0000000000000001 RSI: 000000000000003c RDI: 0000000000000001
[  748.006495] RBP: 0000000000000001 R08: 00000000000000e7 R09: fffffffffffffee0
[  748.015079] R10: 00007f572f4387e8 R11: 0000000000000246 R12: 00007f572f431840
[  748.023664] R13: 000055a7f90f2c50 R14: 000055a7f96e2310 R15: 000055a7f96e2310
[  748.032287]
[  748.034509] Allocated by task 2300:
[  748.038982]  kasan_kmalloc+0xa0/0xd0
[  748.043562]  kmem_cache_alloc_node+0xf5/0x2e0
[  748.049018]  copy_process+0x1781/0x4790
[  748.053884]  _do_fork+0x166/0x9a0
[  748.058163]  do_syscall_64+0x117/0x400
[  748.062943]  entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  748.069180]
[  748.071405] Freed by task 15395:
[  748.075591]  __kasan_slab_free+0x130/0x180
[  748.080752]  kmem_cache_free+0xc2/0x310
[  748.085619]  free_task+0xea/0x130
[  748.089901]  __put_task_struct+0x177/0x230
[  748.095063]  finish_task_switch+0x51b/0x5d0
[  748.100315]  __schedule+0x506/0xfa0
[  748.104791]  schedule+0xca/0x260
[  748.108978]  futex_wait_queue_me+0x27e/0x420
[  748.114333]  futex_wait+0x251/0x550
[  748.118814]  do_futex+0x75b/0xf80
[  748.123097]  __x64_sys_futex+0x231/0x2a0
[  748.128065]  do_syscall_64+0x117/0x400
[  748.132835]  entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  748.139066]
[  748.141289] The buggy address belongs to the object at ffff88a027698000
[  748.141289]  which belongs to the cache task_struct of size 12160
[  748.156589] The buggy address is located 2272 bytes inside of
[  748.156589]  12160-byte region [ffff88a027698000, ffff88a02769af80)
[  748.171114] The buggy address belongs to the page:
[  748.177055] page:ffffea00809da600 count:1 mapcount:0 mapping:ffff888107d01e00 index:0x0 compound_mapcount: 0
[  748.189136] flags: 0x57ffffc0008100(slab|head)
[  748.194688] raw: 0057ffffc0008100 ffffea00809a3200 0000000300000003 ffff888107d01e00
[  748.204424] raw: 0000000000000000 0000000000020002 00000001ffffffff 0000000000000000
[  748.214146] page dumped because: kasan: bad access detected
[  748.220976]
[  748.223197] Memory state around the buggy address:
[  748.229128]  ffff88a027698780: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  748.238271]  ffff88a027698800: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  748.247414] >ffff88a027698880: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  748.256564]                                                        ^
[  748.264267]  ffff88a027698900: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  748.273493]  ffff88a027698980: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  748.282630] ==================================================================

Fixes: b086ff87251b4a4 ("connector: add parent pid and tgid to coredump and exit events")
Signed-off-by: Zhang Yu <zhangyu31@baidu.com>
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Acked-by: Evgeniy Polyakov <zbr@ioremap.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/connector/cn_proc.c | 22 ++++++++++++++++++----
 1 file changed, 18 insertions(+), 4 deletions(-)

diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c
index ed5e42461094..ad48fd52cb53 100644
--- a/drivers/connector/cn_proc.c
+++ b/drivers/connector/cn_proc.c
@@ -250,6 +250,7 @@ void proc_coredump_connector(struct task_struct *task)
 {
 	struct cn_msg *msg;
 	struct proc_event *ev;
+	struct task_struct *parent;
 	__u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
 
 	if (atomic_read(&proc_event_num_listeners) < 1)
@@ -262,8 +263,14 @@ void proc_coredump_connector(struct task_struct *task)
 	ev->what = PROC_EVENT_COREDUMP;
 	ev->event_data.coredump.process_pid = task->pid;
 	ev->event_data.coredump.process_tgid = task->tgid;
-	ev->event_data.coredump.parent_pid = task->real_parent->pid;
-	ev->event_data.coredump.parent_tgid = task->real_parent->tgid;
+
+	rcu_read_lock();
+	if (pid_alive(task)) {
+		parent = rcu_dereference(task->real_parent);
+		ev->event_data.coredump.parent_pid = parent->pid;
+		ev->event_data.coredump.parent_tgid = parent->tgid;
+	}
+	rcu_read_unlock();
 
 	memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
 	msg->ack = 0; /* not used */
@@ -276,6 +283,7 @@ void proc_exit_connector(struct task_struct *task)
 {
 	struct cn_msg *msg;
 	struct proc_event *ev;
+	struct task_struct *parent;
 	__u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
 
 	if (atomic_read(&proc_event_num_listeners) < 1)
@@ -290,8 +298,14 @@ void proc_exit_connector(struct task_struct *task)
 	ev->event_data.exit.process_tgid = task->tgid;
 	ev->event_data.exit.exit_code = task->exit_code;
 	ev->event_data.exit.exit_signal = task->exit_signal;
-	ev->event_data.exit.parent_pid = task->real_parent->pid;
-	ev->event_data.exit.parent_tgid = task->real_parent->tgid;
+
+	rcu_read_lock();
+	if (pid_alive(task)) {
+		parent = rcu_dereference(task->real_parent);
+		ev->event_data.exit.parent_pid = parent->pid;
+		ev->event_data.exit.parent_tgid = parent->tgid;
+	}
+	rcu_read_unlock();
 
 	memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
 	msg->ack = 0; /* not used */
-- 
2.20.1


From 3850a7bc1171c0c1a58f9e2814012ac9a1e2876a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 6 Mar 2019 10:41:00 -0800
Subject: [PATCH 02/30] fou, fou6: avoid uninit-value in gue_err() and
 gue6_err()

[ Upstream commit 5355ed6388e23b69a00d48398a68d022135e6486 ]

My prior commit missed the fact that these functions
were using udp_hdr() (aka skb_transport_header())
to get access to GUE header.

Since pskb_transport_may_pull() does not exist yet, we have to add
transport_offset to our pskb_may_pull() calls.

BUG: KMSAN: uninit-value in gue_err+0x514/0xfa0 net/ipv4/fou.c:1032
CPU: 1 PID: 10648 Comm: syz-executor.1 Not tainted 5.0.0+ #11
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x173/0x1d0 lib/dump_stack.c:113
 kmsan_report+0x12e/0x2a0 mm/kmsan/kmsan.c:600
 __msan_warning+0x82/0xf0 mm/kmsan/kmsan_instr.c:313
 gue_err+0x514/0xfa0 net/ipv4/fou.c:1032
 __udp4_lib_err_encap_no_sk net/ipv4/udp.c:571 [inline]
 __udp4_lib_err_encap net/ipv4/udp.c:626 [inline]
 __udp4_lib_err+0x12e6/0x1d40 net/ipv4/udp.c:665
 udp_err+0x74/0x90 net/ipv4/udp.c:737
 icmp_socket_deliver net/ipv4/icmp.c:767 [inline]
 icmp_unreach+0xb65/0x1070 net/ipv4/icmp.c:884
 icmp_rcv+0x11a1/0x1950 net/ipv4/icmp.c:1066
 ip_protocol_deliver_rcu+0x584/0xbb0 net/ipv4/ip_input.c:208
 ip_local_deliver_finish net/ipv4/ip_input.c:234 [inline]
 NF_HOOK include/linux/netfilter.h:289 [inline]
 ip_local_deliver+0x624/0x7b0 net/ipv4/ip_input.c:255
 dst_input include/net/dst.h:450 [inline]
 ip_rcv_finish net/ipv4/ip_input.c:414 [inline]
 NF_HOOK include/linux/netfilter.h:289 [inline]
 ip_rcv+0x6bd/0x740 net/ipv4/ip_input.c:524
 __netif_receive_skb_one_core net/core/dev.c:4973 [inline]
 __netif_receive_skb net/core/dev.c:5083 [inline]
 process_backlog+0x756/0x10e0 net/core/dev.c:5923
 napi_poll net/core/dev.c:6346 [inline]
 net_rx_action+0x78b/0x1a60 net/core/dev.c:6412
 __do_softirq+0x53f/0x93a kernel/softirq.c:293
 invoke_softirq kernel/softirq.c:375 [inline]
 irq_exit+0x214/0x250 kernel/softirq.c:416
 exiting_irq+0xe/0x10 arch/x86/include/asm/apic.h:536
 smp_apic_timer_interrupt+0x48/0x70 arch/x86/kernel/apic/apic.c:1064
 apic_timer_interrupt+0x2e/0x40 arch/x86/entry/entry_64.S:814
 </IRQ>
RIP: 0010:finish_lock_switch+0x2b/0x40 kernel/sched/core.c:2597
Code: 48 89 e5 53 48 89 fb e8 63 e7 95 00 8b b8 88 0c 00 00 48 8b 00 48 85 c0 75 12 48 89 df e8 dd db 95 00 c6 00 00 c6 03 00 fb 5b <5d> c3 e8 4e e6 95 00 eb e7 66 90 66 2e 0f 1f 84 00 00 00 00 00 55
RSP: 0018:ffff888081a0fc80 EFLAGS: 00000296 ORIG_RAX: ffffffffffffff13
RAX: ffff88821fd6bd80 RBX: ffff888027898000 RCX: ccccccccccccd000
RDX: ffff88821fca8d80 RSI: ffff888000000000 RDI: 00000000000004a0
RBP: ffff888081a0fc80 R08: 0000000000000002 R09: ffff888081a0fb08
R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000001
R13: ffff88811130e388 R14: ffff88811130da00 R15: ffff88812fdb7d80
 finish_task_switch+0xfc/0x2d0 kernel/sched/core.c:2698
 context_switch kernel/sched/core.c:2851 [inline]
 __schedule+0x6cc/0x800 kernel/sched/core.c:3491
 schedule+0x15b/0x240 kernel/sched/core.c:3535
 freezable_schedule include/linux/freezer.h:172 [inline]
 do_nanosleep+0x2ba/0x980 kernel/time/hrtimer.c:1679
 hrtimer_nanosleep kernel/time/hrtimer.c:1733 [inline]
 __do_sys_nanosleep kernel/time/hrtimer.c:1767 [inline]
 __se_sys_nanosleep+0x746/0x960 kernel/time/hrtimer.c:1754
 __x64_sys_nanosleep+0x3e/0x60 kernel/time/hrtimer.c:1754
 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291
 entry_SYSCALL_64_after_hwframe+0x63/0xe7
RIP: 0033:0x4855a0
Code: 00 00 48 c7 c0 d4 ff ff ff 64 c7 00 16 00 00 00 31 c0 eb be 66 0f 1f 44 00 00 83 3d b1 11 5d 00 00 75 14 b8 23 00 00 00 0f 05 <48> 3d 01 f0 ff ff 0f 83 04 e2 f8 ff c3 48 83 ec 08 e8 3a 55 fd ff
RSP: 002b:0000000000a4fd58 EFLAGS: 00000246 ORIG_RAX: 0000000000000023
RAX: ffffffffffffffda RBX: 0000000000085780 RCX: 00000000004855a0
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000a4fd60
RBP: 00000000000007ec R08: 0000000000000001 R09: 0000000000ceb940
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000008
R13: 0000000000a4fdb0 R14: 0000000000085711 R15: 0000000000a4fdc0

Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:205 [inline]
 kmsan_internal_poison_shadow+0x92/0x150 mm/kmsan/kmsan.c:159
 kmsan_kmalloc+0xa6/0x130 mm/kmsan/kmsan_hooks.c:176
 kmsan_slab_alloc+0xe/0x10 mm/kmsan/kmsan_hooks.c:185
 slab_post_alloc_hook mm/slab.h:445 [inline]
 slab_alloc_node mm/slub.c:2773 [inline]
 __kmalloc_node_track_caller+0xe9e/0xff0 mm/slub.c:4398
 __kmalloc_reserve net/core/skbuff.c:140 [inline]
 __alloc_skb+0x309/0xa20 net/core/skbuff.c:208
 alloc_skb include/linux/skbuff.h:1012 [inline]
 alloc_skb_with_frags+0x186/0xa60 net/core/skbuff.c:5287
 sock_alloc_send_pskb+0xafd/0x10a0 net/core/sock.c:2091
 sock_alloc_send_skb+0xca/0xe0 net/core/sock.c:2108
 __ip_append_data+0x34cd/0x5000 net/ipv4/ip_output.c:998
 ip_append_data+0x324/0x480 net/ipv4/ip_output.c:1220
 icmp_push_reply+0x23d/0x7e0 net/ipv4/icmp.c:375
 __icmp_send+0x2ea3/0x30f0 net/ipv4/icmp.c:737
 icmp_send include/net/icmp.h:47 [inline]
 ipv4_link_failure+0x6d/0x230 net/ipv4/route.c:1190
 dst_link_failure include/net/dst.h:427 [inline]
 arp_error_report+0x106/0x1a0 net/ipv4/arp.c:297
 neigh_invalidate+0x359/0x8e0 net/core/neighbour.c:992
 neigh_timer_handler+0xdf2/0x1280 net/core/neighbour.c:1078
 call_timer_fn+0x285/0x600 kernel/time/timer.c:1325
 expire_timers kernel/time/timer.c:1362 [inline]
 __run_timers+0xdb4/0x11d0 kernel/time/timer.c:1681
 run_timer_softirq+0x2e/0x50 kernel/time/timer.c:1694
 __do_softirq+0x53f/0x93a kernel/softirq.c:293

Fixes: 26fc181e6cac ("fou, fou6: do not assume linear skbs")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Stefano Brivio <sbrivio@redhat.com>
Cc: Sabrina Dubroca <sd@queasysnail.net>
Acked-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fou.c  | 4 ++--
 net/ipv6/fou6.c | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 437070d1ffb1..79e98e21cdd7 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -1024,7 +1024,7 @@ static int gue_err(struct sk_buff *skb, u32 info)
 	int ret;
 
 	len = sizeof(struct udphdr) + sizeof(struct guehdr);
-	if (!pskb_may_pull(skb, len))
+	if (!pskb_may_pull(skb, transport_offset + len))
 		return -EINVAL;
 
 	guehdr = (struct guehdr *)&udp_hdr(skb)[1];
@@ -1059,7 +1059,7 @@ static int gue_err(struct sk_buff *skb, u32 info)
 
 	optlen = guehdr->hlen << 2;
 
-	if (!pskb_may_pull(skb, len + optlen))
+	if (!pskb_may_pull(skb, transport_offset + len + optlen))
 		return -EINVAL;
 
 	guehdr = (struct guehdr *)&udp_hdr(skb)[1];
diff --git a/net/ipv6/fou6.c b/net/ipv6/fou6.c
index 867474abe269..ec4e2ed95f36 100644
--- a/net/ipv6/fou6.c
+++ b/net/ipv6/fou6.c
@@ -94,7 +94,7 @@ static int gue6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	int ret;
 
 	len = sizeof(struct udphdr) + sizeof(struct guehdr);
-	if (!pskb_may_pull(skb, len))
+	if (!pskb_may_pull(skb, transport_offset + len))
 		return -EINVAL;
 
 	guehdr = (struct guehdr *)&udp_hdr(skb)[1];
@@ -129,7 +129,7 @@ static int gue6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 
 	optlen = guehdr->hlen << 2;
 
-	if (!pskb_may_pull(skb, len + optlen))
+	if (!pskb_may_pull(skb, transport_offset + len + optlen))
 		return -EINVAL;
 
 	guehdr = (struct guehdr *)&udp_hdr(skb)[1];
-- 
2.20.1


From f360d2dd305dfe3a80516705d0e52465be512a89 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 10 Mar 2019 10:39:37 -0700
Subject: [PATCH 03/30] gro_cells: make sure device is up in
 gro_cells_receive()

[ Upstream commit 2a5ff07a0eb945f291e361aa6f6becca8340ba46 ]

We keep receiving syzbot reports [1] that show that tunnels do not play
the rcu/IFF_UP rules properly.

At device dismantle phase, gro_cells_destroy() will be called
only after a full rcu grace period is observed after IFF_UP
has been cleared.

This means that IFF_UP needs to be tested before queueing packets
into netif_rx() or gro_cells.

This patch implements the test in gro_cells_receive() because
too many callers do not seem to bother enough.

[1]
BUG: unable to handle kernel paging request at fffff4ca0b9ffffe
PGD 0 P4D 0
Oops: 0000 [#1] PREEMPT SMP KASAN
CPU: 0 PID: 21 Comm: kworker/u4:1 Not tainted 5.0.0+ #97
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Workqueue: netns cleanup_net
RIP: 0010:__skb_unlink include/linux/skbuff.h:1929 [inline]
RIP: 0010:__skb_dequeue include/linux/skbuff.h:1945 [inline]
RIP: 0010:__skb_queue_purge include/linux/skbuff.h:2656 [inline]
RIP: 0010:gro_cells_destroy net/core/gro_cells.c:89 [inline]
RIP: 0010:gro_cells_destroy+0x19d/0x360 net/core/gro_cells.c:78
Code: 03 42 80 3c 20 00 0f 85 53 01 00 00 48 8d 7a 08 49 8b 47 08 49 c7 07 00 00 00 00 48 89 f9 49 c7 47 08 00 00 00 00 48 c1 e9 03 <42> 80 3c 21 00 0f 85 10 01 00 00 48 89 c1 48 89 42 08 48 c1 e9 03
RSP: 0018:ffff8880aa3f79a8 EFLAGS: 00010a02
RAX: 00ffffffffffffe8 RBX: ffffe8ffffc64b70 RCX: 1ffff8ca0b9ffffe
RDX: ffffc6505cffffe8 RSI: ffffffff858410ca RDI: ffffc6505cfffff0
RBP: ffff8880aa3f7a08 R08: ffff8880aa3e8580 R09: fffffbfff1263645
R10: fffffbfff1263644 R11: ffffffff8931b223 R12: dffffc0000000000
R13: 0000000000000000 R14: ffffe8ffffc64b80 R15: ffffe8ffffc64b75
kobject: 'loop2' (000000004bd7d84a): kobject_uevent_env
FS:  0000000000000000(0000) GS:ffff8880ae800000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: fffff4ca0b9ffffe CR3: 0000000094941000 CR4: 00000000001406f0
Call Trace:
kobject: 'loop2' (000000004bd7d84a): fill_kobj_path: path = '/devices/virtual/block/loop2'
 ip_tunnel_dev_free+0x19/0x60 net/ipv4/ip_tunnel.c:1010
 netdev_run_todo+0x51c/0x7d0 net/core/dev.c:8970
 rtnl_unlock+0xe/0x10 net/core/rtnetlink.c:116
 ip_tunnel_delete_nets+0x423/0x5f0 net/ipv4/ip_tunnel.c:1124
 vti_exit_batch_net+0x23/0x30 net/ipv4/ip_vti.c:495
 ops_exit_list.isra.0+0x105/0x160 net/core/net_namespace.c:156
 cleanup_net+0x3fb/0x960 net/core/net_namespace.c:551
 process_one_work+0x98e/0x1790 kernel/workqueue.c:2173
 worker_thread+0x98/0xe40 kernel/workqueue.c:2319
 kthread+0x357/0x430 kernel/kthread.c:246
 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:352
Modules linked in:
CR2: fffff4ca0b9ffffe
   [ end trace 513fc9c1338d1cb3 ]
RIP: 0010:__skb_unlink include/linux/skbuff.h:1929 [inline]
RIP: 0010:__skb_dequeue include/linux/skbuff.h:1945 [inline]
RIP: 0010:__skb_queue_purge include/linux/skbuff.h:2656 [inline]
RIP: 0010:gro_cells_destroy net/core/gro_cells.c:89 [inline]
RIP: 0010:gro_cells_destroy+0x19d/0x360 net/core/gro_cells.c:78
Code: 03 42 80 3c 20 00 0f 85 53 01 00 00 48 8d 7a 08 49 8b 47 08 49 c7 07 00 00 00 00 48 89 f9 49 c7 47 08 00 00 00 00 48 c1 e9 03 <42> 80 3c 21 00 0f 85 10 01 00 00 48 89 c1 48 89 42 08 48 c1 e9 03
RSP: 0018:ffff8880aa3f79a8 EFLAGS: 00010a02
RAX: 00ffffffffffffe8 RBX: ffffe8ffffc64b70 RCX: 1ffff8ca0b9ffffe
RDX: ffffc6505cffffe8 RSI: ffffffff858410ca RDI: ffffc6505cfffff0
RBP: ffff8880aa3f7a08 R08: ffff8880aa3e8580 R09: fffffbfff1263645
R10: fffffbfff1263644 R11: ffffffff8931b223 R12: dffffc0000000000
kobject: 'loop3' (00000000e4ee57a6): kobject_uevent_env
R13: 0000000000000000 R14: ffffe8ffffc64b80 R15: ffffe8ffffc64b75
FS:  0000000000000000(0000) GS:ffff8880ae800000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: fffff4ca0b9ffffe CR3: 0000000094941000 CR4: 00000000001406f0

Fixes: c9e6bc644e55 ("net: add gro_cells infrastructure")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/gro_cells.c | 22 ++++++++++++++++++----
 1 file changed, 18 insertions(+), 4 deletions(-)

diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c
index acf45ddbe924..e095fb871d91 100644
--- a/net/core/gro_cells.c
+++ b/net/core/gro_cells.c
@@ -13,22 +13,36 @@ int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb)
 {
 	struct net_device *dev = skb->dev;
 	struct gro_cell *cell;
+	int res;
 
-	if (!gcells->cells || skb_cloned(skb) || netif_elide_gro(dev))
-		return netif_rx(skb);
+	rcu_read_lock();
+	if (unlikely(!(dev->flags & IFF_UP)))
+		goto drop;
+
+	if (!gcells->cells || skb_cloned(skb) || netif_elide_gro(dev)) {
+		res = netif_rx(skb);
+		goto unlock;
+	}
 
 	cell = this_cpu_ptr(gcells->cells);
 
 	if (skb_queue_len(&cell->napi_skbs) > netdev_max_backlog) {
+drop:
 		atomic_long_inc(&dev->rx_dropped);
 		kfree_skb(skb);
-		return NET_RX_DROP;
+		res = NET_RX_DROP;
+		goto unlock;
 	}
 
 	__skb_queue_tail(&cell->napi_skbs, skb);
 	if (skb_queue_len(&cell->napi_skbs) == 1)
 		napi_schedule(&cell->napi);
-	return NET_RX_SUCCESS;
+
+	res = NET_RX_SUCCESS;
+
+unlock:
+	rcu_read_unlock();
+	return res;
 }
 EXPORT_SYMBOL(gro_cells_receive);
 
-- 
2.20.1


From 9f043d1d79058b76d8ba073fbbb6e1a5523db553 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 6 Mar 2019 10:42:53 +0100
Subject: [PATCH 04/30] ipv4/route: fail early when inet dev is missing

[ Upstream commit 22c74764aa2943ecdf9f07c900d8a9c8ba6c9265 ]

If a non local multicast packet reaches ip_route_input_rcu() while
the ingress device IPv4 private data (in_dev) is NULL, we end up
doing a NULL pointer dereference in IN_DEV_MFORWARD().

Since the later call to ip_route_input_mc() is going to fail if
!in_dev, we can fail early in such scenario and avoid the dangerous
code path.

v1 -> v2:
 - clarified the commit message, no code changes

Reported-by: Tianhao Zhao <tizhao@redhat.com>
Fixes: e58e41596811 ("net: Enable support for VRF with ipv4 multicast")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 7bb9128c8363..e40e56e014a0 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2144,12 +2144,13 @@ int ip_route_input_rcu(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 		int our = 0;
 		int err = -EINVAL;
 
-		if (in_dev)
-			our = ip_check_mc_rcu(in_dev, daddr, saddr,
-					      ip_hdr(skb)->protocol);
+		if (!in_dev)
+			return err;
+		our = ip_check_mc_rcu(in_dev, daddr, saddr,
+				      ip_hdr(skb)->protocol);
 
 		/* check l3 master if no match yet */
-		if ((!in_dev || !our) && netif_is_l3_slave(dev)) {
+		if (!our && netif_is_l3_slave(dev)) {
 			struct in_device *l3_in_dev;
 
 			l3_in_dev = __in_dev_get_rcu(skb->dev);
-- 
2.20.1


From 8bc90dcb078a549654bdf935b349deebcc814e2f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 12 Mar 2019 06:50:11 -0700
Subject: [PATCH 05/30] l2tp: fix infoleak in l2tp_ip6_recvmsg()

[ Upstream commit 163d1c3d6f17556ed3c340d3789ea93be95d6c28 ]

Back in 2013 Hannes took care of most of such leaks in commit
bceaa90240b6 ("inet: prevent leakage of uninitialized memory to user in recv syscalls")

But the bug in l2tp_ip6_recvmsg() has not been fixed.

syzbot report :

BUG: KMSAN: kernel-infoleak in _copy_to_user+0x16b/0x1f0 lib/usercopy.c:32
CPU: 1 PID: 10996 Comm: syz-executor362 Not tainted 5.0.0+ #11
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x173/0x1d0 lib/dump_stack.c:113
 kmsan_report+0x12e/0x2a0 mm/kmsan/kmsan.c:600
 kmsan_internal_check_memory+0x9f4/0xb10 mm/kmsan/kmsan.c:694
 kmsan_copy_to_user+0xab/0xc0 mm/kmsan/kmsan_hooks.c:601
 _copy_to_user+0x16b/0x1f0 lib/usercopy.c:32
 copy_to_user include/linux/uaccess.h:174 [inline]
 move_addr_to_user+0x311/0x570 net/socket.c:227
 ___sys_recvmsg+0xb65/0x1310 net/socket.c:2283
 do_recvmmsg+0x646/0x10c0 net/socket.c:2390
 __sys_recvmmsg net/socket.c:2469 [inline]
 __do_sys_recvmmsg net/socket.c:2492 [inline]
 __se_sys_recvmmsg+0x1d1/0x350 net/socket.c:2485
 __x64_sys_recvmmsg+0x62/0x80 net/socket.c:2485
 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291
 entry_SYSCALL_64_after_hwframe+0x63/0xe7
RIP: 0033:0x445819
Code: e8 6c b6 02 00 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 2b 12 fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f64453eddb8 EFLAGS: 00000246 ORIG_RAX: 000000000000012b
RAX: ffffffffffffffda RBX: 00000000006dac28 RCX: 0000000000445819
RDX: 0000000000000005 RSI: 0000000020002f80 RDI: 0000000000000003
RBP: 00000000006dac20 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00000000006dac2c
R13: 00007ffeba8f87af R14: 00007f64453ee9c0 R15: 20c49ba5e353f7cf

Local variable description: ----addr@___sys_recvmsg
Variable was created at:
 ___sys_recvmsg+0xf6/0x1310 net/socket.c:2244
 do_recvmmsg+0x646/0x10c0 net/socket.c:2390

Bytes 0-31 of 32 are uninitialized
Memory access of size 32 starts at ffff8880ae62fbb0
Data copied to user address 0000000020000000

Fixes: a32e0eec7042 ("l2tp: introduce L2TPv3 IP encapsulation support for IPv6")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ip6.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 0ae6899edac0..37a69df17cab 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -674,9 +674,6 @@ static int l2tp_ip6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	if (flags & MSG_OOB)
 		goto out;
 
-	if (addr_len)
-		*addr_len = sizeof(*lsa);
-
 	if (flags & MSG_ERRQUEUE)
 		return ipv6_recv_error(sk, msg, len, addr_len);
 
@@ -706,6 +703,7 @@ static int l2tp_ip6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		lsa->l2tp_conn_id = 0;
 		if (ipv6_addr_type(&lsa->l2tp_addr) & IPV6_ADDR_LINKLOCAL)
 			lsa->l2tp_scope_id = inet6_iif(skb);
+		*addr_len = sizeof(*lsa);
 	}
 
 	if (np->rxopt.all)
-- 
2.20.1


From 15d3020c3747d73611c77715514fe7e146c5bcf7 Mon Sep 17 00:00:00 2001
From: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Date: Mon, 11 Mar 2019 13:39:39 -0400
Subject: [PATCH 06/30] lan743x: Fix RX Kernel Panic

[ Upstream commit dd9d9f5907bb475f8b1796c47d4ecc7fb9b72136 ]

It has been noticed that running the speed test at
www.speedtest.net occasionally causes a kernel panic.

Investigation revealed that under this test RX buffer allocation
sometimes fails and returns NULL. But the lan743x driver did
not handle this case.

This patch fixes this issue by attempting to allocate a buffer
before sending the new rx packet to the OS. If the allocation
fails then the new rx packet is dropped and the existing buffer
is reused in the DMA ring.

Updates for v2:
    Additional 2 locations where allocation was not checked,
        has been changed to reuse existing buffer.

Fixes: 23f0703c125b ("lan743x: Add main source files for new lan743x driver")
Signed-off-by: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/lan743x_main.c | 46 +++++++++++++------
 1 file changed, 32 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index 4d1b4a24907f..2876bab642e2 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -1902,7 +1902,17 @@ static int lan743x_rx_next_index(struct lan743x_rx *rx, int index)
 	return ((++index) % rx->ring_size);
 }
 
-static int lan743x_rx_allocate_ring_element(struct lan743x_rx *rx, int index)
+static struct sk_buff *lan743x_rx_allocate_skb(struct lan743x_rx *rx)
+{
+	int length = 0;
+
+	length = (LAN743X_MAX_FRAME_SIZE + ETH_HLEN + 4 + RX_HEAD_PADDING);
+	return __netdev_alloc_skb(rx->adapter->netdev,
+				  length, GFP_ATOMIC | GFP_DMA);
+}
+
+static int lan743x_rx_init_ring_element(struct lan743x_rx *rx, int index,
+					struct sk_buff *skb)
 {
 	struct lan743x_rx_buffer_info *buffer_info;
 	struct lan743x_rx_descriptor *descriptor;
@@ -1911,9 +1921,7 @@ static int lan743x_rx_allocate_ring_element(struct lan743x_rx *rx, int index)
 	length = (LAN743X_MAX_FRAME_SIZE + ETH_HLEN + 4 + RX_HEAD_PADDING);
 	descriptor = &rx->ring_cpu_ptr[index];
 	buffer_info = &rx->buffer_info[index];
-	buffer_info->skb = __netdev_alloc_skb(rx->adapter->netdev,
-					      length,
-					      GFP_ATOMIC | GFP_DMA);
+	buffer_info->skb = skb;
 	if (!(buffer_info->skb))
 		return -ENOMEM;
 	buffer_info->dma_ptr = dma_map_single(&rx->adapter->pdev->dev,
@@ -2060,8 +2068,19 @@ static int lan743x_rx_process_packet(struct lan743x_rx *rx)
 		/* packet is available */
 		if (first_index == last_index) {
 			/* single buffer packet */
+			struct sk_buff *new_skb = NULL;
 			int packet_length;
 
+			new_skb = lan743x_rx_allocate_skb(rx);
+			if (!new_skb) {
+				/* failed to allocate next skb.
+				 * Memory is very low.
+				 * Drop this packet and reuse buffer.
+				 */
+				lan743x_rx_reuse_ring_element(rx, first_index);
+				goto process_extension;
+			}
+
 			buffer_info = &rx->buffer_info[first_index];
 			skb = buffer_info->skb;
 			descriptor = &rx->ring_cpu_ptr[first_index];
@@ -2081,7 +2100,7 @@ static int lan743x_rx_process_packet(struct lan743x_rx *rx)
 			skb_put(skb, packet_length - 4);
 			skb->protocol = eth_type_trans(skb,
 						       rx->adapter->netdev);
-			lan743x_rx_allocate_ring_element(rx, first_index);
+			lan743x_rx_init_ring_element(rx, first_index, new_skb);
 		} else {
 			int index = first_index;
 
@@ -2094,26 +2113,23 @@ static int lan743x_rx_process_packet(struct lan743x_rx *rx)
 			if (first_index <= last_index) {
 				while ((index >= first_index) &&
 				       (index <= last_index)) {
-					lan743x_rx_release_ring_element(rx,
-									index);
-					lan743x_rx_allocate_ring_element(rx,
-									 index);
+					lan743x_rx_reuse_ring_element(rx,
+								      index);
 					index = lan743x_rx_next_index(rx,
 								      index);
 				}
 			} else {
 				while ((index >= first_index) ||
 				       (index <= last_index)) {
-					lan743x_rx_release_ring_element(rx,
-									index);
-					lan743x_rx_allocate_ring_element(rx,
-									 index);
+					lan743x_rx_reuse_ring_element(rx,
+								      index);
 					index = lan743x_rx_next_index(rx,
 								      index);
 				}
 			}
 		}
 
+process_extension:
 		if (extension_index >= 0) {
 			descriptor = &rx->ring_cpu_ptr[extension_index];
 			buffer_info = &rx->buffer_info[extension_index];
@@ -2290,7 +2306,9 @@ static int lan743x_rx_ring_init(struct lan743x_rx *rx)
 
 	rx->last_head = 0;
 	for (index = 0; index < rx->ring_size; index++) {
-		ret = lan743x_rx_allocate_ring_element(rx, index);
+		struct sk_buff *new_skb = lan743x_rx_allocate_skb(rx);
+
+		ret = lan743x_rx_init_ring_element(rx, index, new_skb);
 		if (ret)
 			goto cleanup;
 	}
-- 
2.20.1


From b2f2a1017bcc9e2426cc2f5b36ced24088a90a3f Mon Sep 17 00:00:00 2001
From: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Date: Wed, 13 Mar 2019 15:55:48 -0400
Subject: [PATCH 07/30] lan743x: Fix TX Stall Issue

[ Upstream commit deb6bfabdbb634e91f36a4e9cb00a7137d72d886 ]

It has been observed that tx queue may stall while downloading
from certain web sites (example www.speedtest.net)

The cause has been tracked down to a corner case where
the tx interrupt vector was disabled automatically, but
was not re enabled later.

The lan743x has two mechanisms to enable/disable individual
interrupts. Interrupts can be enabled/disabled by individual
source, and they can also be enabled/disabled by individual
vector which has been mapped to the source. Both must be
enabled for interrupts to work properly.

The TX code path, primarily uses the interrupt enable/disable of
the TX source bit, while leaving the vector enabled all the time.

However, while investigating this issue it was noticed that
the driver requested the use of the vector auto clear feature.

The test above revealed a case where the vector enable was
cleared unintentionally.

This patch fixes the issue by deleting the lines that request
the vector auto clear feature to be used.

Fixes: 23f0703c125b ("lan743x: Add main source files for new lan743x driver")
Signed-off-by: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/lan743x_main.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index 2876bab642e2..13e6bf13ac4d 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -585,8 +585,7 @@ static int lan743x_intr_open(struct lan743x_adapter *adapter)
 
 		if (adapter->csr.flags &
 		   LAN743X_CSR_FLAG_SUPPORTS_INTR_AUTO_SET_CLR) {
-			flags = LAN743X_VECTOR_FLAG_VECTOR_ENABLE_AUTO_CLEAR |
-				LAN743X_VECTOR_FLAG_VECTOR_ENABLE_AUTO_SET |
+			flags = LAN743X_VECTOR_FLAG_VECTOR_ENABLE_AUTO_SET |
 				LAN743X_VECTOR_FLAG_SOURCE_ENABLE_AUTO_SET |
 				LAN743X_VECTOR_FLAG_SOURCE_ENABLE_AUTO_CLEAR |
 				LAN743X_VECTOR_FLAG_SOURCE_STATUS_AUTO_CLEAR;
@@ -599,12 +598,6 @@ static int lan743x_intr_open(struct lan743x_adapter *adapter)
 			/* map TX interrupt to vector */
 			int_vec_map1 |= INT_VEC_MAP1_TX_VEC_(index, vector);
 			lan743x_csr_write(adapter, INT_VEC_MAP1, int_vec_map1);
-			if (flags &
-			    LAN743X_VECTOR_FLAG_VECTOR_ENABLE_AUTO_CLEAR) {
-				int_vec_en_auto_clr |= INT_VEC_EN_(vector);
-				lan743x_csr_write(adapter, INT_VEC_EN_AUTO_CLR,
-						  int_vec_en_auto_clr);
-			}
 
 			/* Remove TX interrupt from shared mask */
 			intr->vector_list[0].int_mask &= ~int_bit;
-- 
2.20.1


From 6d75abb3b68e2690ad131dbc35cb8b56d15eb884 Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Wed, 6 Mar 2019 11:26:37 +0800
Subject: [PATCH 08/30] net: hns3: add dma_rmb() for rx description

[ Upstream commit d394d33bee22421b39a0bcdc51ca6d68ba308625 ]

HW can not guarantee complete write desc->rx.size, even though
HNS3_RXD_VLD_B has been set. Driver needs to add dma_rmb()
instruction to make sure desc->rx.size is always valid.

Fixes: e55970950556 ("net: hns3: Add handling of GRO Pkts not fully RX'ed in NAPI poll")
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 1bf7a5f116a0..882d2d2acdfa 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -2476,6 +2476,8 @@ static int hns3_add_frag(struct hns3_enet_ring *ring, struct hns3_desc *desc,
 		desc = &ring->desc[ring->next_to_clean];
 		desc_cb = &ring->desc_cb[ring->next_to_clean];
 		bd_base_info = le32_to_cpu(desc->rx.bd_base_info);
+		/* make sure HW write desc complete */
+		dma_rmb();
 		if (!hnae3_get_bit(bd_base_info, HNS3_RXD_VLD_B))
 			return -ENXIO;
 
-- 
2.20.1


From e0bdb58f7b31b953b3502d31c13cbd64fed00c45 Mon Sep 17 00:00:00 2001
From: Mao Wenan <maowenan@huawei.com>
Date: Wed, 6 Mar 2019 22:45:01 +0800
Subject: [PATCH 09/30] net: hsr: fix memory leak in hsr_dev_finalize()

[ Upstream commit 3dc6da493a29dbeda9f13b637bd9c02c414b2261 ]

If hsr_add_port(hsr, hsr_dev, HSR_PT_MASTER) failed to
add port, it directly returns res and forgets to free the node
that allocated in hsr_create_self_node(), and forgets to delete
the node->mac_list linked in hsr->self_node_db.

BUG: memory leak
unreferenced object 0xffff8881cfa0c780 (size 64):
  comm "syz-executor.0", pid 2077, jiffies 4294717969 (age 2415.377s)
  hex dump (first 32 bytes):
    e0 c7 a0 cf 81 88 ff ff 00 02 00 00 00 00 ad de  ................
    00 e6 49 cd 81 88 ff ff c0 9b 87 d0 81 88 ff ff  ..I.............
  backtrace:
    [<00000000e2ff5070>] hsr_dev_finalize+0x736/0x960 [hsr]
    [<000000003ed2e597>] hsr_newlink+0x2b2/0x3e0 [hsr]
    [<000000003fa8c6b6>] __rtnl_newlink+0xf1f/0x1600 net/core/rtnetlink.c:3182
    [<000000001247a7ad>] rtnl_newlink+0x66/0x90 net/core/rtnetlink.c:3240
    [<00000000e7d1b61d>] rtnetlink_rcv_msg+0x54e/0xb90 net/core/rtnetlink.c:5130
    [<000000005556bd3a>] netlink_rcv_skb+0x129/0x340 net/netlink/af_netlink.c:2477
    [<00000000741d5ee6>] netlink_unicast_kernel net/netlink/af_netlink.c:1310 [inline]
    [<00000000741d5ee6>] netlink_unicast+0x49a/0x650 net/netlink/af_netlink.c:1336
    [<000000009d56f9b7>] netlink_sendmsg+0x88b/0xdf0 net/netlink/af_netlink.c:1917
    [<0000000046b35c59>] sock_sendmsg_nosec net/socket.c:621 [inline]
    [<0000000046b35c59>] sock_sendmsg+0xc3/0x100 net/socket.c:631
    [<00000000d208adc9>] __sys_sendto+0x33e/0x560 net/socket.c:1786
    [<00000000b582837a>] __do_sys_sendto net/socket.c:1798 [inline]
    [<00000000b582837a>] __se_sys_sendto net/socket.c:1794 [inline]
    [<00000000b582837a>] __x64_sys_sendto+0xdd/0x1b0 net/socket.c:1794
    [<00000000c866801d>] do_syscall_64+0x147/0x600 arch/x86/entry/common.c:290
    [<00000000fea382d9>] entry_SYSCALL_64_after_hwframe+0x49/0xbe
    [<00000000e01dacb3>] 0xffffffffffffffff

Fixes: c5a759117210 ("net/hsr: Use list_head (and rcu) instead of array for slave devices.")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Mao Wenan <maowenan@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/hsr/hsr_device.c   |  4 +++-
 net/hsr/hsr_framereg.c | 12 ++++++++++++
 net/hsr/hsr_framereg.h |  1 +
 3 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index b8cd43c9ed5b..c4676bacb8db 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -486,7 +486,7 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2],
 
 	res = hsr_add_port(hsr, hsr_dev, HSR_PT_MASTER);
 	if (res)
-		return res;
+		goto err_add_port;
 
 	res = register_netdevice(hsr_dev);
 	if (res)
@@ -506,6 +506,8 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2],
 fail:
 	hsr_for_each_port(hsr, port)
 		hsr_del_port(port);
+err_add_port:
+	hsr_del_node(&hsr->self_node_db);
 
 	return res;
 }
diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c
index 286ceb41ac0c..9af16cb68f76 100644
--- a/net/hsr/hsr_framereg.c
+++ b/net/hsr/hsr_framereg.c
@@ -124,6 +124,18 @@ int hsr_create_self_node(struct list_head *self_node_db,
 	return 0;
 }
 
+void hsr_del_node(struct list_head *self_node_db)
+{
+	struct hsr_node *node;
+
+	rcu_read_lock();
+	node = list_first_or_null_rcu(self_node_db, struct hsr_node, mac_list);
+	rcu_read_unlock();
+	if (node) {
+		list_del_rcu(&node->mac_list);
+		kfree(node);
+	}
+}
 
 /* Allocate an hsr_node and add it to node_db. 'addr' is the node's AddressA;
  * seq_out is used to initialize filtering of outgoing duplicate frames
diff --git a/net/hsr/hsr_framereg.h b/net/hsr/hsr_framereg.h
index 370b45998121..531fd3dfcac1 100644
--- a/net/hsr/hsr_framereg.h
+++ b/net/hsr/hsr_framereg.h
@@ -16,6 +16,7 @@
 
 struct hsr_node;
 
+void hsr_del_node(struct list_head *self_node_db);
 struct hsr_node *hsr_add_node(struct list_head *node_db, unsigned char addr[],
 			      u16 seq_out);
 struct hsr_node *hsr_get_node(struct hsr_port *port, struct sk_buff *skb,
-- 
2.20.1


From 47d4253bbee7608b662195a54bc3e6c53506b1c5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 7 Mar 2019 09:36:33 -0800
Subject: [PATCH 10/30] net/hsr: fix possible crash in add_timer()

[ Upstream commit 1e027960edfaa6a43f9ca31081729b716598112b ]

syzbot found another add_timer() issue, this time in net/hsr [1]

Let's use mod_timer() which is safe.

[1]
kernel BUG at kernel/time/timer.c:1136!
invalid opcode: 0000 [#1] PREEMPT SMP KASAN
CPU: 0 PID: 15909 Comm: syz-executor.3 Not tainted 5.0.0+ #97
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
kobject: 'loop2' (00000000f5629718): kobject_uevent_env
RIP: 0010:add_timer kernel/time/timer.c:1136 [inline]
RIP: 0010:add_timer+0x654/0xbe0 kernel/time/timer.c:1134
Code: 0f 94 c5 31 ff 44 89 ee e8 09 61 0f 00 45 84 ed 0f 84 77 fd ff ff e8 bb 5f 0f 00 e8 07 10 a0 ff e9 68 fd ff ff e8 ac 5f 0f 00 <0f> 0b e8 a5 5f 0f 00 0f 0b e8 9e 5f 0f 00 4c 89 b5 58 ff ff ff e9
RSP: 0018:ffff8880656eeca0 EFLAGS: 00010246
kobject: 'loop2' (00000000f5629718): fill_kobj_path: path = '/devices/virtual/block/loop2'
RAX: 0000000000040000 RBX: 1ffff1100caddd9a RCX: ffffc9000c436000
RDX: 0000000000040000 RSI: ffffffff816056c4 RDI: ffff88806a2f6cc8
RBP: ffff8880656eed58 R08: ffff888067f4a300 R09: ffff888067f4abc8
R10: 0000000000000000 R11: 0000000000000000 R12: ffff88806a2f6cc0
R13: dffffc0000000000 R14: 0000000000000001 R15: ffff8880656eed30
FS:  00007fc2019bf700(0000) GS:ffff8880ae800000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000738000 CR3: 0000000067e8e000 CR4: 00000000001406f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 hsr_check_announce net/hsr/hsr_device.c:99 [inline]
 hsr_check_carrier_and_operstate+0x567/0x6f0 net/hsr/hsr_device.c:120
 hsr_netdev_notify+0x297/0xa00 net/hsr/hsr_main.c:51
 notifier_call_chain+0xc7/0x240 kernel/notifier.c:93
 __raw_notifier_call_chain kernel/notifier.c:394 [inline]
 raw_notifier_call_chain+0x2e/0x40 kernel/notifier.c:401
 call_netdevice_notifiers_info+0x3f/0x90 net/core/dev.c:1739
 call_netdevice_notifiers_extack net/core/dev.c:1751 [inline]
 call_netdevice_notifiers net/core/dev.c:1765 [inline]
 dev_open net/core/dev.c:1436 [inline]
 dev_open+0x143/0x160 net/core/dev.c:1424
 team_port_add drivers/net/team/team.c:1203 [inline]
 team_add_slave+0xa07/0x15d0 drivers/net/team/team.c:1933
 do_set_master net/core/rtnetlink.c:2358 [inline]
 do_set_master+0x1d4/0x230 net/core/rtnetlink.c:2332
 do_setlink+0x966/0x3510 net/core/rtnetlink.c:2493
 rtnl_setlink+0x271/0x3b0 net/core/rtnetlink.c:2747
 rtnetlink_rcv_msg+0x465/0xb00 net/core/rtnetlink.c:5192
 netlink_rcv_skb+0x17a/0x460 net/netlink/af_netlink.c:2485
 rtnetlink_rcv+0x1d/0x30 net/core/rtnetlink.c:5210
 netlink_unicast_kernel net/netlink/af_netlink.c:1310 [inline]
 netlink_unicast+0x536/0x720 net/netlink/af_netlink.c:1336
 netlink_sendmsg+0x8ae/0xd70 net/netlink/af_netlink.c:1925
 sock_sendmsg_nosec net/socket.c:622 [inline]
 sock_sendmsg+0xdd/0x130 net/socket.c:632
 sock_write_iter+0x27c/0x3e0 net/socket.c:923
 call_write_iter include/linux/fs.h:1869 [inline]
 do_iter_readv_writev+0x5e0/0x8e0 fs/read_write.c:680
 do_iter_write fs/read_write.c:956 [inline]
 do_iter_write+0x184/0x610 fs/read_write.c:937
 vfs_writev+0x1b3/0x2f0 fs/read_write.c:1001
 do_writev+0xf6/0x290 fs/read_write.c:1036
 __do_sys_writev fs/read_write.c:1109 [inline]
 __se_sys_writev fs/read_write.c:1106 [inline]
 __x64_sys_writev+0x75/0xb0 fs/read_write.c:1106
 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x457f29
Code: ad b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007fc2019bec78 EFLAGS: 00000246 ORIG_RAX: 0000000000000014
RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000457f29
RDX: 0000000000000001 RSI: 00000000200000c0 RDI: 0000000000000003
RBP: 000000000073bf00 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00007fc2019bf6d4
R13: 00000000004c4a60 R14: 00000000004dd218 R15: 00000000ffffffff

Fixes: f421436a591d ("net/hsr: Add support for the High-availability Seamless Redundancy protocol (HSRv0)")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Arvid Brodin <arvid.brodin@alten.se>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/hsr/hsr_device.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index c4676bacb8db..a97bf326b231 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -94,9 +94,8 @@ static void hsr_check_announce(struct net_device *hsr_dev,
 			&& (old_operstate != IF_OPER_UP)) {
 		/* Went up */
 		hsr->announce_count = 0;
-		hsr->announce_timer.expires = jiffies +
-				msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL);
-		add_timer(&hsr->announce_timer);
+		mod_timer(&hsr->announce_timer,
+			  jiffies + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL));
 	}
 
 	if ((hsr_dev->operstate != IF_OPER_UP) && (old_operstate == IF_OPER_UP))
@@ -332,6 +331,7 @@ static void hsr_announce(struct timer_list *t)
 {
 	struct hsr_priv *hsr;
 	struct hsr_port *master;
+	unsigned long interval;
 
 	hsr = from_timer(hsr, t, announce_timer);
 
@@ -343,18 +343,16 @@ static void hsr_announce(struct timer_list *t)
 				hsr->protVersion);
 		hsr->announce_count++;
 
-		hsr->announce_timer.expires = jiffies +
-				msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL);
+		interval = msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL);
 	} else {
 		send_hsr_supervision_frame(master, HSR_TLV_LIFE_CHECK,
 				hsr->protVersion);
 
-		hsr->announce_timer.expires = jiffies +
-				msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL);
+		interval = msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL);
 	}
 
 	if (is_admin_up(master->dev))
-		add_timer(&hsr->announce_timer);
+		mod_timer(&hsr->announce_timer, jiffies + interval);
 
 	rcu_read_unlock();
 }
-- 
2.20.1


From 5bc1f73ab9ca8772663a6aaebb72de624f776673 Mon Sep 17 00:00:00 2001
From: Miaohe Lin <linmiaohe@huawei.com>
Date: Mon, 11 Mar 2019 16:29:32 +0800
Subject: [PATCH 11/30] net: sit: fix UBSAN Undefined behaviour in check_6rd

[ Upstream commit a843dc4ebaecd15fca1f4d35a97210f72ea1473b ]

In func check_6rd,tunnel->ip6rd.relay_prefixlen may equal to
32,so UBSAN complain about it.

UBSAN: Undefined behaviour in net/ipv6/sit.c:781:47
shift exponent 32 is too large for 32-bit type 'unsigned int'
CPU: 6 PID: 20036 Comm: syz-executor.0 Not tainted 4.19.27 #2
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1
04/01/2014
Call Trace:
__dump_stack lib/dump_stack.c:77 [inline]
dump_stack+0xca/0x13e lib/dump_stack.c:113
ubsan_epilogue+0xe/0x81 lib/ubsan.c:159
__ubsan_handle_shift_out_of_bounds+0x293/0x2e8 lib/ubsan.c:425
check_6rd.constprop.9+0x433/0x4e0 net/ipv6/sit.c:781
try_6rd net/ipv6/sit.c:806 [inline]
ipip6_tunnel_xmit net/ipv6/sit.c:866 [inline]
sit_tunnel_xmit+0x141c/0x2720 net/ipv6/sit.c:1033
__netdev_start_xmit include/linux/netdevice.h:4300 [inline]
netdev_start_xmit include/linux/netdevice.h:4309 [inline]
xmit_one net/core/dev.c:3243 [inline]
dev_hard_start_xmit+0x17c/0x780 net/core/dev.c:3259
__dev_queue_xmit+0x1656/0x2500 net/core/dev.c:3829
neigh_output include/net/neighbour.h:501 [inline]
ip6_finish_output2+0xa36/0x2290 net/ipv6/ip6_output.c:120
ip6_finish_output+0x3e7/0xa20 net/ipv6/ip6_output.c:154
NF_HOOK_COND include/linux/netfilter.h:278 [inline]
ip6_output+0x1e2/0x720 net/ipv6/ip6_output.c:171
dst_output include/net/dst.h:444 [inline]
ip6_local_out+0x99/0x170 net/ipv6/output_core.c:176
ip6_send_skb+0x9d/0x2f0 net/ipv6/ip6_output.c:1697
ip6_push_pending_frames+0xc0/0x100 net/ipv6/ip6_output.c:1717
rawv6_push_pending_frames net/ipv6/raw.c:616 [inline]
rawv6_sendmsg+0x2435/0x3530 net/ipv6/raw.c:946
inet_sendmsg+0xf8/0x5c0 net/ipv4/af_inet.c:798
sock_sendmsg_nosec net/socket.c:621 [inline]
sock_sendmsg+0xc8/0x110 net/socket.c:631
___sys_sendmsg+0x6cf/0x890 net/socket.c:2114
__sys_sendmsg+0xf0/0x1b0 net/socket.c:2152
do_syscall_64+0xc8/0x580 arch/x86/entry/common.c:290
entry_SYSCALL_64_after_hwframe+0x49/0xbe

Signed-off-by: linmiaohe <linmiaohe@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 09e440e8dfae..07e21a82ce4c 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -778,8 +778,9 @@ static bool check_6rd(struct ip_tunnel *tunnel, const struct in6_addr *v6dst,
 		pbw0 = tunnel->ip6rd.prefixlen >> 5;
 		pbi0 = tunnel->ip6rd.prefixlen & 0x1f;
 
-		d = (ntohl(v6dst->s6_addr32[pbw0]) << pbi0) >>
-		    tunnel->ip6rd.relay_prefixlen;
+		d = tunnel->ip6rd.relay_prefixlen < 32 ?
+			(ntohl(v6dst->s6_addr32[pbw0]) << pbi0) >>
+		    tunnel->ip6rd.relay_prefixlen : 0;
 
 		pbi1 = pbi0 - tunnel->ip6rd.relay_prefixlen;
 		if (pbi1 > 0)
-- 
2.20.1


From 069028bef510e48c28257af9f2afbf1a86e24177 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 10 Mar 2019 09:07:14 -0700
Subject: [PATCH 12/30] net/x25: fix use-after-free in x25_device_event()

[ Upstream commit 95d6ebd53c79522bf9502dbc7e89e0d63f94dae4 ]

In case of failure x25_connect() does a x25_neigh_put(x25->neighbour)
but forgets to clear x25->neighbour pointer, thus triggering use-after-free.

Since the socket is visible in x25_list, we need to hold x25_list_lock
to protect the operation.

syzbot report :

BUG: KASAN: use-after-free in x25_kill_by_device net/x25/af_x25.c:217 [inline]
BUG: KASAN: use-after-free in x25_device_event+0x296/0x2b0 net/x25/af_x25.c:252
Read of size 8 at addr ffff8880a030edd0 by task syz-executor003/7854

CPU: 0 PID: 7854 Comm: syz-executor003 Not tainted 5.0.0+ #97
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 print_address_description.cold+0x7c/0x20d mm/kasan/report.c:187
 kasan_report.cold+0x1b/0x40 mm/kasan/report.c:317
 __asan_report_load8_noabort+0x14/0x20 mm/kasan/generic_report.c:135
 x25_kill_by_device net/x25/af_x25.c:217 [inline]
 x25_device_event+0x296/0x2b0 net/x25/af_x25.c:252
 notifier_call_chain+0xc7/0x240 kernel/notifier.c:93
 __raw_notifier_call_chain kernel/notifier.c:394 [inline]
 raw_notifier_call_chain+0x2e/0x40 kernel/notifier.c:401
 call_netdevice_notifiers_info+0x3f/0x90 net/core/dev.c:1739
 call_netdevice_notifiers_extack net/core/dev.c:1751 [inline]
 call_netdevice_notifiers net/core/dev.c:1765 [inline]
 __dev_notify_flags+0x1e9/0x2c0 net/core/dev.c:7607
 dev_change_flags+0x10d/0x170 net/core/dev.c:7643
 dev_ifsioc+0x2b0/0x940 net/core/dev_ioctl.c:237
 dev_ioctl+0x1b8/0xc70 net/core/dev_ioctl.c:488
 sock_do_ioctl+0x1bd/0x300 net/socket.c:995
 sock_ioctl+0x32b/0x610 net/socket.c:1096
 vfs_ioctl fs/ioctl.c:46 [inline]
 file_ioctl fs/ioctl.c:509 [inline]
 do_vfs_ioctl+0xd6e/0x1390 fs/ioctl.c:696
 ksys_ioctl+0xab/0xd0 fs/ioctl.c:713
 __do_sys_ioctl fs/ioctl.c:720 [inline]
 __se_sys_ioctl fs/ioctl.c:718 [inline]
 __x64_sys_ioctl+0x73/0xb0 fs/ioctl.c:718
 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x4467c9
Code: e8 0c e8 ff ff 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 5b 07 fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007fdbea222d98 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 00000000006dbc58 RCX: 00000000004467c9
RDX: 0000000020000340 RSI: 0000000000008914 RDI: 0000000000000003
RBP: 00000000006dbc50 R08: 00007fdbea223700 R09: 0000000000000000
R10: 00007fdbea223700 R11: 0000000000000246 R12: 00000000006dbc5c
R13: 6000030030626669 R14: 0000000000000000 R15: 0000000030626669

Allocated by task 7843:
 save_stack+0x45/0xd0 mm/kasan/common.c:73
 set_track mm/kasan/common.c:85 [inline]
 __kasan_kmalloc mm/kasan/common.c:495 [inline]
 __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:468
 kasan_kmalloc+0x9/0x10 mm/kasan/common.c:509
 kmem_cache_alloc_trace+0x151/0x760 mm/slab.c:3615
 kmalloc include/linux/slab.h:545 [inline]
 x25_link_device_up+0x46/0x3f0 net/x25/x25_link.c:249
 x25_device_event+0x116/0x2b0 net/x25/af_x25.c:242
 notifier_call_chain+0xc7/0x240 kernel/notifier.c:93
 __raw_notifier_call_chain kernel/notifier.c:394 [inline]
 raw_notifier_call_chain+0x2e/0x40 kernel/notifier.c:401
 call_netdevice_notifiers_info+0x3f/0x90 net/core/dev.c:1739
 call_netdevice_notifiers_extack net/core/dev.c:1751 [inline]
 call_netdevice_notifiers net/core/dev.c:1765 [inline]
 __dev_notify_flags+0x121/0x2c0 net/core/dev.c:7605
 dev_change_flags+0x10d/0x170 net/core/dev.c:7643
 dev_ifsioc+0x2b0/0x940 net/core/dev_ioctl.c:237
 dev_ioctl+0x1b8/0xc70 net/core/dev_ioctl.c:488
 sock_do_ioctl+0x1bd/0x300 net/socket.c:995
 sock_ioctl+0x32b/0x610 net/socket.c:1096
 vfs_ioctl fs/ioctl.c:46 [inline]
 file_ioctl fs/ioctl.c:509 [inline]
 do_vfs_ioctl+0xd6e/0x1390 fs/ioctl.c:696
 ksys_ioctl+0xab/0xd0 fs/ioctl.c:713
 __do_sys_ioctl fs/ioctl.c:720 [inline]
 __se_sys_ioctl fs/ioctl.c:718 [inline]
 __x64_sys_ioctl+0x73/0xb0 fs/ioctl.c:718
 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Freed by task 7865:
 save_stack+0x45/0xd0 mm/kasan/common.c:73
 set_track mm/kasan/common.c:85 [inline]
 __kasan_slab_free+0x102/0x150 mm/kasan/common.c:457
 kasan_slab_free+0xe/0x10 mm/kasan/common.c:465
 __cache_free mm/slab.c:3494 [inline]
 kfree+0xcf/0x230 mm/slab.c:3811
 x25_neigh_put include/net/x25.h:253 [inline]
 x25_connect+0x8d8/0xde0 net/x25/af_x25.c:824
 __sys_connect+0x266/0x330 net/socket.c:1685
 __do_sys_connect net/socket.c:1696 [inline]
 __se_sys_connect net/socket.c:1693 [inline]
 __x64_sys_connect+0x73/0xb0 net/socket.c:1693
 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

The buggy address belongs to the object at ffff8880a030edc0
 which belongs to the cache kmalloc-256 of size 256
The buggy address is located 16 bytes inside of
 256-byte region [ffff8880a030edc0, ffff8880a030eec0)
The buggy address belongs to the page:
page:ffffea000280c380 count:1 mapcount:0 mapping:ffff88812c3f07c0 index:0x0
flags: 0x1fffc0000000200(slab)
raw: 01fffc0000000200 ffffea0002806788 ffffea00027f0188 ffff88812c3f07c0
raw: 0000000000000000 ffff8880a030e000 000000010000000c 0000000000000000
page dumped because: kasan: bad access detected

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot+04babcefcd396fabec37@syzkaller.appspotmail.com
Cc: andrew hendry <andrew.hendry@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/x25/af_x25.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index eff31348e20b..27171ac6fe3b 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -820,8 +820,12 @@ static int x25_connect(struct socket *sock, struct sockaddr *uaddr,
 	sock->state = SS_CONNECTED;
 	rc = 0;
 out_put_neigh:
-	if (rc)
+	if (rc) {
+		read_lock_bh(&x25_list_lock);
 		x25_neigh_put(x25->neighbour);
+		x25->neighbour = NULL;
+		read_unlock_bh(&x25_list_lock);
+	}
 out_put_route:
 	x25_route_put(rt);
 out:
-- 
2.20.1


From c288d87c5c9ecd979f3c1d3ecb82cdd7cd1674c0 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 11 Mar 2019 13:48:44 -0700
Subject: [PATCH 13/30] net/x25: reset state in x25_connect()

[ Upstream commit ee74d0bd4325efb41e38affe5955f920ed973f23 ]

In case x25_connect() fails and frees the socket neighbour,
we also need to undo the change done to x25->state.

Before my last bug fix, we had use-after-free so this
patch fixes a latent bug.

syzbot report :

kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] PREEMPT SMP KASAN
CPU: 1 PID: 16137 Comm: syz-executor.1 Not tainted 5.0.0+ #117
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:x25_write_internal+0x1e8/0xdf0 net/x25/x25_subr.c:173
Code: 00 40 88 b5 e0 fe ff ff 0f 85 01 0b 00 00 48 8b 8b 80 04 00 00 48 ba 00 00 00 00 00 fc ff df 48 8d 79 1c 48 89 fe 48 c1 ee 03 <0f> b6 34 16 48 89 fa 83 e2 07 83 c2 03 40 38 f2 7c 09 40 84 f6 0f
RSP: 0018:ffff888076717a08 EFLAGS: 00010207
RAX: ffff88805f2f2292 RBX: ffff8880a0ae6000 RCX: 0000000000000000
kobject: 'loop5' (0000000018d0d0ee): kobject_uevent_env
RDX: dffffc0000000000 RSI: 0000000000000003 RDI: 000000000000001c
RBP: ffff888076717b40 R08: ffff8880950e0580 R09: ffffed100be5e46d
R10: ffffed100be5e46c R11: ffff88805f2f2363 R12: ffff888065579840
kobject: 'loop5' (0000000018d0d0ee): fill_kobj_path: path = '/devices/virtual/block/loop5'
R13: 1ffff1100ece2f47 R14: 0000000000000013 R15: 0000000000000013
FS:  00007fb88cf43700(0000) GS:ffff8880ae900000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f9a42a41028 CR3: 0000000087a67000 CR4: 00000000001406e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 x25_release+0xd0/0x340 net/x25/af_x25.c:658
 __sock_release+0xd3/0x2b0 net/socket.c:579
 sock_close+0x1b/0x30 net/socket.c:1162
 __fput+0x2df/0x8d0 fs/file_table.c:278
 ____fput+0x16/0x20 fs/file_table.c:309
 task_work_run+0x14a/0x1c0 kernel/task_work.c:113
 get_signal+0x1961/0x1d50 kernel/signal.c:2388
 do_signal+0x87/0x1940 arch/x86/kernel/signal.c:816
 exit_to_usermode_loop+0x244/0x2c0 arch/x86/entry/common.c:162
 prepare_exit_to_usermode arch/x86/entry/common.c:197 [inline]
 syscall_return_slowpath arch/x86/entry/common.c:268 [inline]
 do_syscall_64+0x52d/0x610 arch/x86/entry/common.c:293
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x457f29
Code: ad b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007fb88cf42c78 EFLAGS: 00000246 ORIG_RAX: 000000000000002a
RAX: fffffffffffffe00 RBX: 0000000000000003 RCX: 0000000000457f29
RDX: 0000000000000012 RSI: 0000000020000080 RDI: 0000000000000004
RBP: 000000000073bf00 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00007fb88cf436d4
R13: 00000000004be462 R14: 00000000004cec98 R15: 00000000ffffffff
Modules linked in:

Fixes: 95d6ebd53c79 ("net/x25: fix use-after-free in x25_device_event()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: andrew hendry <andrew.hendry@gmail.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/x25/af_x25.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 27171ac6fe3b..20a511398389 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -825,6 +825,7 @@ static int x25_connect(struct socket *sock, struct sockaddr *uaddr,
 		x25_neigh_put(x25->neighbour);
 		x25->neighbour = NULL;
 		read_unlock_bh(&x25_list_lock);
+		x25->state = X25_STATE_0;
 	}
 out_put_route:
 	x25_route_put(rt);
-- 
2.20.1


From 2e1cc8f92727e68e1039b845725a2d77e9683b17 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 13 Mar 2019 17:00:48 +0800
Subject: [PATCH 14/30] pptp: dst_release sk_dst_cache in pptp_sock_destruct

[ Upstream commit 9417d81f4f8adfe20a12dd1fadf73a618cbd945d ]

sk_setup_caps() is called to set sk->sk_dst_cache in pptp_connect,
so we have to dst_release(sk->sk_dst_cache) in pptp_sock_destruct,
otherwise, the dst refcnt will leak.

It can be reproduced by this syz log:

  r1 = socket$pptp(0x18, 0x1, 0x2)
  bind$pptp(r1, &(0x7f0000000100)={0x18, 0x2, {0x0, @local}}, 0x1e)
  connect$pptp(r1, &(0x7f0000000000)={0x18, 0x2, {0x3, @remote}}, 0x1e)

Consecutive dmesg warnings will occur:

  unregister_netdevice: waiting for lo to become free. Usage count = 1

v1->v2:
  - use rcu_dereference_protected() instead of rcu_dereference_check(),
    as suggested by Eric.

Fixes: 00959ade36ac ("PPTP: PPP over IPv4 (Point-to-Point Tunneling Protocol)")
Reported-by: Xiumei Mu <xmu@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pptp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index 8f09edd811e9..50c60550f295 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -532,6 +532,7 @@ static void pptp_sock_destruct(struct sock *sk)
 		pppox_unbind_sock(sk);
 	}
 	skb_queue_purge(&sk->sk_receive_queue);
+	dst_release(rcu_dereference_protected(sk->sk_dst_cache, 1));
 }
 
 static int pptp_create(struct net *net, struct socket *sock, int kern)
-- 
2.20.1


From ef66cde251a48aaa5efa35858ea169caff663290 Mon Sep 17 00:00:00 2001
From: Masaru Nagai <masaru.nagai.vx@renesas.com>
Date: Thu, 7 Mar 2019 11:24:47 +0100
Subject: [PATCH 15/30] ravb: Decrease TxFIFO depth of Q3 and Q2 to one

[ Upstream commit ae9819e339b451da7a86ab6fe38ecfcb6814e78a ]

Hardware has the CBS (Credit Based Shaper) which affects only Q3
and Q2. When updating the CBS settings, even if the driver does so
after waiting for Tx DMA finished, there is a possibility that frame
data still remains in TxFIFO.

To avoid this, decrease TxFIFO depth of Q3 and Q2 to one.

This patch has been exercised this using netperf TCP_MAERTS, TCP_STREAM
and UDP_STREAM tests run on an Ebisu board. No performance change was
detected, outside of noise in the tests, both in terms of throughput and
CPU utilisation.

Fixes: c156633f1353 ("Renesas Ethernet AVB driver proper")
Signed-off-by: Masaru Nagai <masaru.nagai.vx@renesas.com>
Signed-off-by: Kazuya Mizuguchi <kazuya.mizuguchi.ks@renesas.com>
[simon: updated changelog]
Signed-off-by: Simon Horman <horms+renesas@verge.net.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/ravb_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index d28c8f9ca55b..8154b38c08f7 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -458,7 +458,7 @@ static int ravb_dmac_init(struct net_device *ndev)
 		   RCR_EFFS | RCR_ENCF | RCR_ETS0 | RCR_ESF | 0x18000000, RCR);
 
 	/* Set FIFO size */
-	ravb_write(ndev, TGC_TQP_AVBMODE1 | 0x00222200, TGC);
+	ravb_write(ndev, TGC_TQP_AVBMODE1 | 0x00112200, TGC);
 
 	/* Timestamp enable */
 	ravb_write(ndev, TCCR_TFEN, TCCR);
-- 
2.20.1


From 03dd7142273859aeb10f0e8015c4b1e7e9eed6e7 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Fri, 8 Mar 2019 14:50:54 +0800
Subject: [PATCH 16/30] route: set the deleted fnhe fnhe_daddr to 0 in
 ip_del_fnhe to fix a race

[ Upstream commit ee60ad219f5c7c4fb2f047f88037770063ef785f ]

The race occurs in __mkroute_output() when 2 threads lookup a dst:

  CPU A                 CPU B
  find_exception()
                        find_exception() [fnhe expires]
                        ip_del_fnhe() [fnhe is deleted]
  rt_bind_exception()

In rt_bind_exception() it will bind a deleted fnhe with the new dst, and
this dst will get no chance to be freed. It causes a dev defcnt leak and
consecutive dmesg warnings:

  unregister_netdevice: waiting for ethX to become free. Usage count = 1

Especially thanks Jon to identify the issue.

This patch fixes it by setting fnhe_daddr to 0 in ip_del_fnhe() to stop
binding the deleted fnhe with a new dst when checking fnhe's fnhe_daddr
and daddr in rt_bind_exception().

It works as both ip_del_fnhe() and rt_bind_exception() are protected by
fnhe_lock and the fhne is freed by kfree_rcu().

Fixes: deed49df7390 ("route: check and remove route cache when we get route")
Signed-off-by: Jon Maxwell <jmaxwell37@gmail.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index e40e56e014a0..e04cdb58a602 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1303,6 +1303,10 @@ static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
 		if (fnhe->fnhe_daddr == daddr) {
 			rcu_assign_pointer(*fnhe_p, rcu_dereference_protected(
 				fnhe->fnhe_next, lockdep_is_held(&fnhe_lock)));
+			/* set fnhe_daddr to 0 to ensure it won't bind with
+			 * new dsts in rt_bind_exception().
+			 */
+			fnhe->fnhe_daddr = 0;
 			fnhe_flush_routes(fnhe);
 			kfree_rcu(fnhe, rcu);
 			break;
-- 
2.20.1


From 74b7b5ffe32280a0d8df8eba3755addbc3c348f4 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Sat, 9 Mar 2019 00:29:58 +0000
Subject: [PATCH 17/30] rxrpc: Fix client call queueing, waiting for channel

[ Upstream commit 69ffaebb90369ce08657b5aea4896777b9d6e8fc ]

rxrpc_get_client_conn() adds a new call to the front of the waiting_calls
queue if the connection it's going to use already exists.  This is bad as
it allows calls to get starved out.

Fix this by adding to the tail instead.

Also change the other enqueue point in the same function to put it on the
front (ie. when we have a new connection).  This makes the point that in
the case of a new connection the new call goes at the front (though it
doesn't actually matter since the queue should be unoccupied).

Fixes: 45025bceef17 ("rxrpc: Improve management and caching of client connection objects")
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Marc Dionne <marc.dionne@auristor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/conn_client.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index b2adfa825363..5cf6d9f4761d 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -353,7 +353,7 @@ static int rxrpc_get_client_conn(struct rxrpc_sock *rx,
 	 * normally have to take channel_lock but we do this before anyone else
 	 * can see the connection.
 	 */
-	list_add_tail(&call->chan_wait_link, &candidate->waiting_calls);
+	list_add(&call->chan_wait_link, &candidate->waiting_calls);
 
 	if (cp->exclusive) {
 		call->conn = candidate;
@@ -432,7 +432,7 @@ static int rxrpc_get_client_conn(struct rxrpc_sock *rx,
 	call->conn = conn;
 	call->security_ix = conn->security_ix;
 	call->service_id = conn->service_id;
-	list_add(&call->chan_wait_link, &conn->waiting_calls);
+	list_add_tail(&call->chan_wait_link, &conn->waiting_calls);
 	spin_unlock(&conn->channel_lock);
 	_leave(" = 0 [extant %d]", conn->debug_id);
 	return 0;
-- 
2.20.1


From 21368982d300077b6760ceb77512426115f3e0a3 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Fri, 8 Mar 2019 15:49:16 +0800
Subject: [PATCH 18/30] sctp: remove sched init from sctp_stream_init

[ Upstream commit 2e990dfd13974d9eae493006f42ffb48707970ef ]

syzbot reported a NULL-ptr deref caused by that sched->init() in
sctp_stream_init() set stream->rr_next = NULL.

  kasan: GPF could be caused by NULL-ptr deref or user memory access
  RIP: 0010:sctp_sched_rr_dequeue+0xd3/0x170 net/sctp/stream_sched_rr.c:141
  Call Trace:
    sctp_outq_dequeue_data net/sctp/outqueue.c:90 [inline]
    sctp_outq_flush_data net/sctp/outqueue.c:1079 [inline]
    sctp_outq_flush+0xba2/0x2790 net/sctp/outqueue.c:1205

All sched info is saved in sout->ext now, in sctp_stream_init()
sctp_stream_alloc_out() will not change it, there's no need to
call sched->init() again, since sctp_outq_init() has already
done it.

Fixes: 5bbbbe32a431 ("sctp: introduce stream scheduler foundations")
Reported-by: syzbot+4c9934f20522c0efd657@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/stream.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index 2936ed17bf9e..3b47457862cc 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -230,8 +230,6 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt,
 	for (i = 0; i < stream->outcnt; i++)
 		SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN;
 
-	sched->init(stream);
-
 in:
 	sctp_stream_interleave_init(stream);
 	if (!incnt)
-- 
2.20.1


From 3e13da182fb3aa192689d2531b4d958e74db43dc Mon Sep 17 00:00:00 2001
From: Soheil Hassas Yeganeh <soheil@google.com>
Date: Wed, 6 Mar 2019 13:01:36 -0500
Subject: [PATCH 19/30] tcp: do not report TCP_CM_INQ of 0 for closed
 connections

[ Upstream commit 6466e715651f9f358e60c5ea4880e4731325827f ]

Returning 0 as inq to userspace indicates there is no more data to
read, and the application needs to wait for EPOLLIN. For a connection
that has received FIN from the remote peer, however, the application
must continue reading until getting EOF (return value of 0
from tcp_recvmsg) or an error, if edge-triggered epoll (EPOLLET) is
being used. Otherwise, the application will never receive a new
EPOLLIN, since there is no epoll edge after the FIN.

Return 1 when there is no data left on the queue but the
connection has received FIN, so that the applications continue
reading.

Fixes: b75eba76d3d72 (tcp: send in-queue bytes in cmsg upon read)
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index cf3c5095c10e..ce365cbba1d1 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1914,6 +1914,11 @@ static int tcp_inq_hint(struct sock *sk)
 		inq = tp->rcv_nxt - tp->copied_seq;
 		release_sock(sk);
 	}
+	/* After receiving a FIN, tell the user-space to continue reading
+	 * by returning a non-zero inq.
+	 */
+	if (inq == 0 && sock_flag(sk, SOCK_DONE))
+		inq = 1;
 	return inq;
 }
 
-- 
2.20.1


From eed55e9f63f6e2617ee51909ab644513ae51252b Mon Sep 17 00:00:00 2001
From: Christoph Paasch <cpaasch@apple.com>
Date: Mon, 11 Mar 2019 11:41:05 -0700
Subject: [PATCH 20/30] tcp: Don't access TCP_SKB_CB before initializing it

[ Upstream commit f2feaefdabb0a6253aa020f65e7388f07a9ed47c ]

Since commit eeea10b83a13 ("tcp: add
tcp_v4_fill_cb()/tcp_v4_restore_cb()"), tcp_vX_fill_cb is only called
after tcp_filter(). That means, TCP_SKB_CB(skb)->end_seq still points to
the IP-part of the cb.

We thus should not mock with it, as this can trigger bugs (thanks
syzkaller):
[   12.349396] ==================================================================
[   12.350188] BUG: KASAN: slab-out-of-bounds in ip6_datagram_recv_specific_ctl+0x19b3/0x1a20
[   12.351035] Read of size 1 at addr ffff88006adbc208 by task test_ip6_datagr/1799

Setting end_seq is actually no more necessary in tcp_filter as it gets
initialized later on in tcp_vX_fill_cb.

Cc: Eric Dumazet <edumazet@google.com>
Fixes: eeea10b83a13 ("tcp: add tcp_v4_fill_cb()/tcp_v4_restore_cb()")
Signed-off-by: Christoph Paasch <cpaasch@apple.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index ec3cea9d6828..1aae9ab57fe9 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1734,15 +1734,8 @@ EXPORT_SYMBOL(tcp_add_backlog);
 int tcp_filter(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcphdr *th = (struct tcphdr *)skb->data;
-	unsigned int eaten = skb->len;
-	int err;
 
-	err = sk_filter_trim_cap(sk, skb, th->doff * 4);
-	if (!err) {
-		eaten -= skb->len;
-		TCP_SKB_CB(skb)->end_seq -= eaten;
-	}
-	return err;
+	return sk_filter_trim_cap(sk, skb, th->doff * 4);
 }
 EXPORT_SYMBOL(tcp_filter);
 
-- 
2.20.1


From 80f77ed902f6fddec03317973f6041c3758e8515 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Fri, 8 Mar 2019 22:09:47 +0100
Subject: [PATCH 21/30] tcp: handle inet_csk_reqsk_queue_add() failures

[  Upstream commit 9d3e1368bb45893a75a5dfb7cd21fdebfa6b47af ]

Commit 7716682cc58e ("tcp/dccp: fix another race at listener
dismantle") let inet_csk_reqsk_queue_add() fail, and adjusted
{tcp,dccp}_check_req() accordingly. However, TFO and syncookies
weren't modified, thus leaking allocated resources on error.

Contrary to tcp_check_req(), in both syncookies and TFO cases,
we need to drop the request socket. Also, since the child socket is
created with inet_csk_clone_lock(), we have to unlock it and drop an
extra reference (->sk_refcount is initially set to 2 and
inet_csk_reqsk_queue_add() drops only one ref).

For TFO, we also need to revert the work done by tcp_try_fastopen()
(with reqsk_fastopen_remove()).

Fixes: 7716682cc58e ("tcp/dccp: fix another race at listener dismantle")
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/syncookies.c | 7 ++++++-
 net/ipv4/tcp_input.c  | 8 +++++++-
 2 files changed, 13 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 606f868d9f3f..e531344611a0 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -216,7 +216,12 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb,
 		refcount_set(&req->rsk_refcnt, 1);
 		tcp_sk(child)->tsoffset = tsoff;
 		sock_rps_save_rxhash(child, skb);
-		inet_csk_reqsk_queue_add(sk, req, child);
+		if (!inet_csk_reqsk_queue_add(sk, req, child)) {
+			bh_unlock_sock(child);
+			sock_put(child);
+			child = NULL;
+			reqsk_put(req);
+		}
 	} else {
 		reqsk_free(req);
 	}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 76858b14ebe9..7b1ef897b398 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6519,7 +6519,13 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 		af_ops->send_synack(fastopen_sk, dst, &fl, req,
 				    &foc, TCP_SYNACK_FASTOPEN);
 		/* Add the child socket directly into the accept queue */
-		inet_csk_reqsk_queue_add(sk, req, fastopen_sk);
+		if (!inet_csk_reqsk_queue_add(sk, req, fastopen_sk)) {
+			reqsk_fastopen_remove(fastopen_sk, req, false);
+			bh_unlock_sock(fastopen_sk);
+			sock_put(fastopen_sk);
+			reqsk_put(req);
+			goto drop;
+		}
 		sk->sk_data_ready(sk);
 		bh_unlock_sock(fastopen_sk);
 		sock_put(fastopen_sk);
-- 
2.20.1


From 648b094119b8e0dbf4993e11cfe2115123725637 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Fri, 8 Mar 2019 16:40:57 +0100
Subject: [PATCH 22/30] vxlan: Fix GRO cells race condition between receive and
 link delete

[ Upstream commit ad6c9986bcb627c7c22b8f9e9a934becc27df87c ]

If we receive a packet while deleting a VXLAN device, there's a chance
vxlan_rcv() is called at the same time as vxlan_dellink(). This is fine,
except that vxlan_dellink() should never ever touch stuff that's still in
use, such as the GRO cells list.

Otherwise, vxlan_rcv() crashes while queueing packets via
gro_cells_receive().

Move the gro_cells_destroy() to vxlan_uninit(), which runs after the RCU
grace period is elapsed and nothing needs the gro_cells anymore.

This is now done in the same way as commit 8e816df87997 ("geneve: Use GRO
cells infrastructure.") originally implemented for GENEVE.

Reported-by: Jianlin Shi <jishi@redhat.com>
Fixes: 58ce31cca1ff ("vxlan: GRO support at tunnel layer")
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 2aae11feff0c..6d11e49db773 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2693,6 +2693,8 @@ static void vxlan_uninit(struct net_device *dev)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 
+	gro_cells_destroy(&vxlan->gro_cells);
+
 	vxlan_fdb_delete_default(vxlan, vxlan->cfg.vni);
 
 	free_percpu(dev->tstats);
@@ -3794,7 +3796,6 @@ static void vxlan_dellink(struct net_device *dev, struct list_head *head)
 
 	vxlan_flush(vxlan, true);
 
-	gro_cells_destroy(&vxlan->gro_cells);
 	list_del(&vxlan->next);
 	unregister_netdevice_queue(dev, head);
 }
-- 
2.20.1


From f81afe4d460c4c9891d55b4770180e20a34dad4b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 10 Mar 2019 10:36:40 -0700
Subject: [PATCH 23/30] vxlan: test dev->flags & IFF_UP before calling
 gro_cells_receive()

[ Upstream commit 59cbf56fcd98ba2a715b6e97c4e43f773f956393 ]

Same reasons than the ones explained in commit 4179cb5a4c92
("vxlan: test dev->flags & IFF_UP before calling netif_rx()")

netif_rx() or gro_cells_receive() must be called under a strict contract.

At device dismantle phase, core networking clears IFF_UP
and flush_all_backlogs() is called after rcu grace period
to make sure no incoming packet might be in a cpu backlog
and still referencing the device.

A similar protocol is used for gro_cells infrastructure, as
gro_cells_destroy() will be called only after a full rcu
grace period is observed after IFF_UP has been cleared.

Most drivers call netif_rx() from their interrupt handler,
and since the interrupts are disabled at device dismantle,
netif_rx() does not have to check dev->flags & IFF_UP

Virtual drivers do not have this guarantee, and must
therefore make the check themselves.

Otherwise we risk use-after-free and/or crashes.

Fixes: d342894c5d2f ("vxlan: virtual extensible lan")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 6d11e49db773..d6fb6a89f9b3 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1657,6 +1657,14 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb)
 		goto drop;
 	}
 
+	rcu_read_lock();
+
+	if (unlikely(!(vxlan->dev->flags & IFF_UP))) {
+		rcu_read_unlock();
+		atomic_long_inc(&vxlan->dev->rx_dropped);
+		goto drop;
+	}
+
 	stats = this_cpu_ptr(vxlan->dev->tstats);
 	u64_stats_update_begin(&stats->syncp);
 	stats->rx_packets++;
@@ -1664,6 +1672,9 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb)
 	u64_stats_update_end(&stats->syncp);
 
 	gro_cells_receive(&vxlan->gro_cells, skb);
+
+	rcu_read_unlock();
+
 	return 0;
 
 drop:
-- 
2.20.1


From 91a1cbb9e7e96e9e16344145540fc2fc9d41ccaa Mon Sep 17 00:00:00 2001
From: Jack Morgenstein <jackm@dev.mellanox.co.il>
Date: Tue, 12 Mar 2019 17:05:47 +0200
Subject: [PATCH 24/30] net/mlx4_core: Fix reset flow when in command polling
 mode

[ Upstream commit e15ce4b8d11227007577e6dc1364d288b8874fbe ]

As part of unloading a device, the driver switches from
FW command event mode to FW command polling mode.

Part of switching over to polling mode is freeing the command context array
memory (unfortunately, currently, without NULLing the command context array
pointer).

The reset flow calls "complete" to complete all outstanding fw commands
(if we are in event mode). The check for event vs. polling mode here
is to test if the command context array pointer is NULL.

If the reset flow is activated after the switch to polling mode, it will
attempt (incorrectly) to complete all the commands in the context array --
because the pointer was not NULLed when the driver switched over to polling
mode.

As a result, we have a use-after-free situation, which results in a
kernel crash.

For example:
BUG: unable to handle kernel NULL pointer dereference at           (null)
IP: [<ffffffff876c4a8e>] __wake_up_common+0x2e/0x90
PGD 0
Oops: 0000 [#1] SMP
Modules linked in: netconsole nfsv3 nfs_acl nfs lockd grace ...
CPU: 2 PID: 940 Comm: kworker/2:3 Kdump: loaded Not tainted 3.10.0-862.el7.x86_64 #1
Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS 090006  04/28/2016
Workqueue: events hv_eject_device_work [pci_hyperv]
task: ffff8d1734ca0fd0 ti: ffff8d17354bc000 task.ti: ffff8d17354bc000
RIP: 0010:[<ffffffff876c4a8e>]  [<ffffffff876c4a8e>] __wake_up_common+0x2e/0x90
RSP: 0018:ffff8d17354bfa38  EFLAGS: 00010082
RAX: 0000000000000000 RBX: ffff8d17362d42c8 RCX: 0000000000000000
RDX: 0000000000000001 RSI: 0000000000000003 RDI: ffff8d17362d42c8
RBP: ffff8d17354bfa70 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000298 R11: ffff8d173610e000 R12: ffff8d17362d42d0
R13: 0000000000000246 R14: 0000000000000000 R15: 0000000000000003
FS:  0000000000000000(0000) GS:ffff8d1802680000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000000 CR3: 00000000f16d8000 CR4: 00000000001406e0
Call Trace:
 [<ffffffff876c7adc>] complete+0x3c/0x50
 [<ffffffffc04242f0>] mlx4_cmd_wake_completions+0x70/0x90 [mlx4_core]
 [<ffffffffc041e7b1>] mlx4_enter_error_state+0xe1/0x380 [mlx4_core]
 [<ffffffffc041fa4b>] mlx4_comm_cmd+0x29b/0x360 [mlx4_core]
 [<ffffffffc041ff51>] __mlx4_cmd+0x441/0x920 [mlx4_core]
 [<ffffffff877f62b1>] ? __slab_free+0x81/0x2f0
 [<ffffffff87951384>] ? __radix_tree_lookup+0x84/0xf0
 [<ffffffffc043a8eb>] mlx4_free_mtt_range+0x5b/0xb0 [mlx4_core]
 [<ffffffffc043a957>] mlx4_mtt_cleanup+0x17/0x20 [mlx4_core]
 [<ffffffffc04272c7>] mlx4_free_eq+0xa7/0x1c0 [mlx4_core]
 [<ffffffffc042803e>] mlx4_cleanup_eq_table+0xde/0x130 [mlx4_core]
 [<ffffffffc0433e08>] mlx4_unload_one+0x118/0x300 [mlx4_core]
 [<ffffffffc0434191>] mlx4_remove_one+0x91/0x1f0 [mlx4_core]

The fix is to set the command context array pointer to NULL after freeing
the array.

Fixes: f5aef5aa3506 ("net/mlx4_core: Activate reset flow upon fatal command cases")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/cmd.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index e65bc3c95630..24143ee05427 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -2689,6 +2689,7 @@ void mlx4_cmd_use_polling(struct mlx4_dev *dev)
 		down(&priv->cmd.event_sem);
 
 	kfree(priv->cmd.context);
+	priv->cmd.context = NULL;
 
 	up(&priv->cmd.poll_sem);
 	up_write(&priv->cmd.switch_sem);
-- 
2.20.1


From 46a7eb46a6b053ab2c88b05122daa188582b29cc Mon Sep 17 00:00:00 2001
From: Jack Morgenstein <jackm@dev.mellanox.co.il>
Date: Tue, 12 Mar 2019 17:05:48 +0200
Subject: [PATCH 25/30] net/mlx4_core: Fix locking in SRIOV mode when switching
 between events and polling

[ Upstream commit c07d27927f2f2e96fcd27bb9fb330c9ea65612d0 ]

In procedures mlx4_cmd_use_events() and mlx4_cmd_use_polling(), we need to
guarantee that there are no FW commands in progress on the comm channel
(for VFs) or wrapped FW commands (on the PF) when SRIOV is active.

We do this by also taking the slave_cmd_mutex when SRIOV is active.

This is especially important when switching from event to polling, since we
free the command-context array during the switch.  If there are FW commands
in progress (e.g., waiting for a completion event), the completion event
handler will access freed memory.

Since the decision to use comm_wait or comm_poll is taken before grabbing
the event_sem/poll_sem in mlx4_comm_cmd_wait/poll, we must take the
slave_cmd_mutex as well (to guarantee that the decision to use events or
polling and the call to the appropriate cmd function are atomic).

Fixes: a7e1f04905e5 ("net/mlx4_core: Fix deadlock when switching between polling and event fw commands")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/cmd.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 24143ee05427..857588e2488d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -2645,6 +2645,8 @@ int mlx4_cmd_use_events(struct mlx4_dev *dev)
 	if (!priv->cmd.context)
 		return -ENOMEM;
 
+	if (mlx4_is_mfunc(dev))
+		mutex_lock(&priv->cmd.slave_cmd_mutex);
 	down_write(&priv->cmd.switch_sem);
 	for (i = 0; i < priv->cmd.max_cmds; ++i) {
 		priv->cmd.context[i].token = i;
@@ -2670,6 +2672,8 @@ int mlx4_cmd_use_events(struct mlx4_dev *dev)
 	down(&priv->cmd.poll_sem);
 	priv->cmd.use_events = 1;
 	up_write(&priv->cmd.switch_sem);
+	if (mlx4_is_mfunc(dev))
+		mutex_unlock(&priv->cmd.slave_cmd_mutex);
 
 	return err;
 }
@@ -2682,6 +2686,8 @@ void mlx4_cmd_use_polling(struct mlx4_dev *dev)
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	int i;
 
+	if (mlx4_is_mfunc(dev))
+		mutex_lock(&priv->cmd.slave_cmd_mutex);
 	down_write(&priv->cmd.switch_sem);
 	priv->cmd.use_events = 0;
 
@@ -2693,6 +2699,8 @@ void mlx4_cmd_use_polling(struct mlx4_dev *dev)
 
 	up(&priv->cmd.poll_sem);
 	up_write(&priv->cmd.switch_sem);
+	if (mlx4_is_mfunc(dev))
+		mutex_unlock(&priv->cmd.slave_cmd_mutex);
 }
 
 struct mlx4_cmd_mailbox *mlx4_alloc_cmd_mailbox(struct mlx4_dev *dev)
-- 
2.20.1


From e24072bef027a51b37bbe93e6a62652bda29955a Mon Sep 17 00:00:00 2001
From: Jack Morgenstein <jackm@dev.mellanox.co.il>
Date: Tue, 12 Mar 2019 17:05:49 +0200
Subject: [PATCH 26/30] net/mlx4_core: Fix qp mtt size calculation

[ Upstream commit 8511a653e9250ef36b95803c375a7be0e2edb628 ]

Calculation of qp mtt size (in function mlx4_RST2INIT_wrapper)
ultimately depends on function roundup_pow_of_two.

If the amount of memory required by the QP is less than one page,
roundup_pow_of_two is called with argument zero.  In this case, the
roundup_pow_of_two result is undefined.

Calling roundup_pow_of_two with a zero argument resulted in the
following stack trace:

UBSAN: Undefined behaviour in ./include/linux/log2.h:61:13
shift exponent 64 is too large for 64-bit type 'long unsigned int'
CPU: 4 PID: 26939 Comm: rping Tainted: G OE 4.19.0-rc1
Hardware name: Supermicro X9DR3-F/X9DR3-F, BIOS 3.2a 07/09/2015
Call Trace:
dump_stack+0x9a/0xeb
ubsan_epilogue+0x9/0x7c
__ubsan_handle_shift_out_of_bounds+0x254/0x29d
? __ubsan_handle_load_invalid_value+0x180/0x180
? debug_show_all_locks+0x310/0x310
? sched_clock+0x5/0x10
? sched_clock+0x5/0x10
? sched_clock_cpu+0x18/0x260
? find_held_lock+0x35/0x1e0
? mlx4_RST2INIT_QP_wrapper+0xfb1/0x1440 [mlx4_core]
mlx4_RST2INIT_QP_wrapper+0xfb1/0x1440 [mlx4_core]

Fix this by explicitly testing for zero, and returning one if the
argument is zero (assuming that the next higher power of 2 in this case
should be one).

Fixes: c82e9aa0a8bc ("mlx4_core: resource tracking for HCA resources used by guests")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/resource_tracker.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index eb13d3618162..4356f3a58002 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -2719,13 +2719,13 @@ static int qp_get_mtt_size(struct mlx4_qp_context *qpc)
 	int total_pages;
 	int total_mem;
 	int page_offset = (be32_to_cpu(qpc->params2) >> 6) & 0x3f;
+	int tot;
 
 	sq_size = 1 << (log_sq_size + log_sq_sride + 4);
 	rq_size = (srq|rss|xrc) ? 0 : (1 << (log_rq_size + log_rq_stride + 4));
 	total_mem = sq_size + rq_size;
-	total_pages =
-		roundup_pow_of_two((total_mem + (page_offset << 6)) >>
-				   page_shift);
+	tot = (total_mem + (page_offset << 6)) >> page_shift;
+	total_pages = !tot ? 1 : roundup_pow_of_two(tot);
 
 	return total_pages;
 }
-- 
2.20.1


From 03b442a544c7d358e232761f30585bcb765850ae Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Fri, 8 Mar 2019 01:21:27 +0100
Subject: [PATCH 27/30] net: dsa: mv88e6xxx: Set correct interface mode for
 CPU/DSA ports

[ Upstream commit 7cbbee050c959f41b512599bafd99685f419ce26 ]

By default, the switch driver is expected to configure CPU and DSA
ports to their maximum speed. For the 6341 and 6390 families, the
ports interface mode has to be configured as well. The 6390X range
support 10G ports using XAUI, while the 6341 and 6390 supports
2500BaseX, as their maximum speed.

Fixes: 787799a9d555 ("net: dsa: mv88e6xxx: Default ports 9/10 6390X CMODE to 1000BaseX")
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 11 +++++++++++
 drivers/net/dsa/mv88e6xxx/chip.h |  3 +++
 drivers/net/dsa/mv88e6xxx/port.c | 24 ++++++++++++++++++++++++
 drivers/net/dsa/mv88e6xxx/port.h |  4 ++++
 4 files changed, 42 insertions(+)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 76cc163b3cf1..4a0ec8e87c7a 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -559,6 +559,9 @@ static int mv88e6xxx_port_setup_mac(struct mv88e6xxx_chip *chip, int port,
 			goto restore_link;
 	}
 
+	if (speed == SPEED_MAX && chip->info->ops->port_max_speed_mode)
+		mode = chip->info->ops->port_max_speed_mode(port);
+
 	if (chip->info->ops->port_set_pause) {
 		err = chip->info->ops->port_set_pause(chip, port, pause);
 		if (err)
@@ -3042,6 +3045,7 @@ static const struct mv88e6xxx_ops mv88e6141_ops = {
 	.port_set_duplex = mv88e6xxx_port_set_duplex,
 	.port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay,
 	.port_set_speed = mv88e6341_port_set_speed,
+	.port_max_speed_mode = mv88e6341_port_max_speed_mode,
 	.port_tag_remap = mv88e6095_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
 	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
@@ -3360,6 +3364,7 @@ static const struct mv88e6xxx_ops mv88e6190_ops = {
 	.port_set_duplex = mv88e6xxx_port_set_duplex,
 	.port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay,
 	.port_set_speed = mv88e6390_port_set_speed,
+	.port_max_speed_mode = mv88e6390_port_max_speed_mode,
 	.port_tag_remap = mv88e6390_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
 	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
@@ -3404,6 +3409,7 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = {
 	.port_set_duplex = mv88e6xxx_port_set_duplex,
 	.port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay,
 	.port_set_speed = mv88e6390x_port_set_speed,
+	.port_max_speed_mode = mv88e6390x_port_max_speed_mode,
 	.port_tag_remap = mv88e6390_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
 	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
@@ -3448,6 +3454,7 @@ static const struct mv88e6xxx_ops mv88e6191_ops = {
 	.port_set_duplex = mv88e6xxx_port_set_duplex,
 	.port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay,
 	.port_set_speed = mv88e6390_port_set_speed,
+	.port_max_speed_mode = mv88e6390_port_max_speed_mode,
 	.port_tag_remap = mv88e6390_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
 	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
@@ -3541,6 +3548,7 @@ static const struct mv88e6xxx_ops mv88e6290_ops = {
 	.port_set_duplex = mv88e6xxx_port_set_duplex,
 	.port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay,
 	.port_set_speed = mv88e6390_port_set_speed,
+	.port_max_speed_mode = mv88e6390_port_max_speed_mode,
 	.port_tag_remap = mv88e6390_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
 	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
@@ -3672,6 +3680,7 @@ static const struct mv88e6xxx_ops mv88e6341_ops = {
 	.port_set_duplex = mv88e6xxx_port_set_duplex,
 	.port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay,
 	.port_set_speed = mv88e6341_port_set_speed,
+	.port_max_speed_mode = mv88e6341_port_max_speed_mode,
 	.port_tag_remap = mv88e6095_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
 	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
@@ -3847,6 +3856,7 @@ static const struct mv88e6xxx_ops mv88e6390_ops = {
 	.port_set_duplex = mv88e6xxx_port_set_duplex,
 	.port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay,
 	.port_set_speed = mv88e6390_port_set_speed,
+	.port_max_speed_mode = mv88e6390_port_max_speed_mode,
 	.port_tag_remap = mv88e6390_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
 	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
@@ -3895,6 +3905,7 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = {
 	.port_set_duplex = mv88e6xxx_port_set_duplex,
 	.port_set_rgmii_delay = mv88e6390_port_set_rgmii_delay,
 	.port_set_speed = mv88e6390x_port_set_speed,
+	.port_max_speed_mode = mv88e6390x_port_max_speed_mode,
 	.port_tag_remap = mv88e6390_port_tag_remap,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
 	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h
index 546651d8c3e1..dfb1af65c205 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.h
+++ b/drivers/net/dsa/mv88e6xxx/chip.h
@@ -377,6 +377,9 @@ struct mv88e6xxx_ops {
 	 */
 	int (*port_set_speed)(struct mv88e6xxx_chip *chip, int port, int speed);
 
+	/* What interface mode should be used for maximum speed? */
+	phy_interface_t (*port_max_speed_mode)(int port);
+
 	int (*port_tag_remap)(struct mv88e6xxx_chip *chip, int port);
 
 	int (*port_set_frame_mode)(struct mv88e6xxx_chip *chip, int port,
diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c
index 184c2b1b3115..5e921bb6c214 100644
--- a/drivers/net/dsa/mv88e6xxx/port.c
+++ b/drivers/net/dsa/mv88e6xxx/port.c
@@ -312,6 +312,14 @@ int mv88e6341_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed)
 	return mv88e6xxx_port_set_speed(chip, port, speed, !port, true);
 }
 
+phy_interface_t mv88e6341_port_max_speed_mode(int port)
+{
+	if (port == 5)
+		return PHY_INTERFACE_MODE_2500BASEX;
+
+	return PHY_INTERFACE_MODE_NA;
+}
+
 /* Support 10, 100, 200, 1000 Mbps (e.g. 88E6352 family) */
 int mv88e6352_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed)
 {
@@ -345,6 +353,14 @@ int mv88e6390_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed)
 	return mv88e6xxx_port_set_speed(chip, port, speed, true, true);
 }
 
+phy_interface_t mv88e6390_port_max_speed_mode(int port)
+{
+	if (port == 9 || port == 10)
+		return PHY_INTERFACE_MODE_2500BASEX;
+
+	return PHY_INTERFACE_MODE_NA;
+}
+
 /* Support 10, 100, 200, 1000, 2500, 10000 Mbps (e.g. 88E6190X) */
 int mv88e6390x_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed)
 {
@@ -360,6 +376,14 @@ int mv88e6390x_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed)
 	return mv88e6xxx_port_set_speed(chip, port, speed, true, true);
 }
 
+phy_interface_t mv88e6390x_port_max_speed_mode(int port)
+{
+	if (port == 9 || port == 10)
+		return PHY_INTERFACE_MODE_XAUI;
+
+	return PHY_INTERFACE_MODE_NA;
+}
+
 int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 			      phy_interface_t mode)
 {
diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h
index 4aadf321edb7..c7bed263a0f4 100644
--- a/drivers/net/dsa/mv88e6xxx/port.h
+++ b/drivers/net/dsa/mv88e6xxx/port.h
@@ -285,6 +285,10 @@ int mv88e6352_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed);
 int mv88e6390_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed);
 int mv88e6390x_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed);
 
+phy_interface_t mv88e6341_port_max_speed_mode(int port);
+phy_interface_t mv88e6390_port_max_speed_mode(int port);
+phy_interface_t mv88e6390x_port_max_speed_mode(int port);
+
 int mv88e6xxx_port_set_state(struct mv88e6xxx_chip *chip, int port, u8 state);
 
 int mv88e6xxx_port_set_vlan_map(struct mv88e6xxx_chip *chip, int port, u16 map);
-- 
2.20.1


From abb7f187e6ae20586a16cd61506c52d1b7b8f371 Mon Sep 17 00:00:00 2001
From: Shiju Jose <shiju.jose@huawei.com>
Date: Sun, 10 Mar 2019 14:47:51 +0800
Subject: [PATCH 28/30] net: hns3: fix to stop multiple HNS reset due to the
 AER changes

[ Upstream commit 69b51bbb03f73e04c486f79d1556b2d9becf4dbc ]

The commit bfcb79fca19d
("PCI/ERR: Run error recovery callbacks for all affected devices")
affected the non-fatal error recovery logic for the HNS and RDMA devices.
This is because each HNS PF under PCIe bus receive callbacks
from the AER driver when an error is reported for one of the PF.
This causes unwanted PF resets because
the HNS decides which PF to reset based on the reset type set.
The HNS error handling code sets the reset type based on the hw error
type detected.

This patch provides fix for the above issue for the recovery of
the hw errors in the HNS and RDMA devices.

This patch needs backporting to the kernel v5.0+

Fixes: 332fbf576579 ("net: hns3: add handling of hw ras errors using new set of commands")
Reported-by: Xiaofei Tan <tanxiaofei@huawei.com>
Signed-off-by: Shiju Jose <shiju.jose@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hnae3.h            | 1 +
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c        | 4 +++-
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c | 9 +++++++--
 3 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 36eab37d8a40..09c774fe8853 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -192,6 +192,7 @@ struct hnae3_ae_dev {
 	const struct hnae3_ae_ops *ops;
 	struct list_head node;
 	u32 flag;
+	u8 override_pci_need_reset; /* fix to stop multiple reset happening */
 	enum hnae3_dev_type dev_type;
 	enum hnae3_reset_type reset_type;
 	void *priv;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 882d2d2acdfa..d84c50068f66 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -1852,7 +1852,9 @@ static pci_ers_result_t hns3_slot_reset(struct pci_dev *pdev)
 
 	/* request the reset */
 	if (ae_dev->ops->reset_event) {
-		ae_dev->ops->reset_event(pdev, NULL);
+		if (!ae_dev->override_pci_need_reset)
+			ae_dev->ops->reset_event(pdev, NULL);
+
 		return PCI_ERS_RESULT_RECOVERED;
 	}
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
index d0f654123b9b..efb6c1a25171 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
@@ -1259,8 +1259,10 @@ pci_ers_result_t hclge_handle_hw_ras_error(struct hnae3_ae_dev *ae_dev)
 		hclge_handle_all_ras_errors(hdev);
 	} else {
 		if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) ||
-		    hdev->pdev->revision < 0x21)
+		    hdev->pdev->revision < 0x21) {
+			ae_dev->override_pci_need_reset = 1;
 			return PCI_ERS_RESULT_RECOVERED;
+		}
 	}
 
 	if (status & HCLGE_RAS_REG_ROCEE_ERR_MASK) {
@@ -1269,8 +1271,11 @@ pci_ers_result_t hclge_handle_hw_ras_error(struct hnae3_ae_dev *ae_dev)
 	}
 
 	if (status & HCLGE_RAS_REG_NFE_MASK ||
-	    status & HCLGE_RAS_REG_ROCEE_ERR_MASK)
+	    status & HCLGE_RAS_REG_ROCEE_ERR_MASK) {
+		ae_dev->override_pci_need_reset = 0;
 		return PCI_ERS_RESULT_NEED_RESET;
+	}
+	ae_dev->override_pci_need_reset = 1;
 
 	return PCI_ERS_RESULT_RECOVERED;
 }
-- 
2.20.1


From c55742b66d73d844c867d49920ceb3001e6cf110 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Adalbert=20Laz=C4=83r?= <alazar@bitdefender.com>
Date: Wed, 6 Mar 2019 12:13:53 +0200
Subject: [PATCH 29/30] vsock/virtio: fix kernel panic from
 virtio_transport_reset_no_sock
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 4c404ce23358d5d8fbdeb7a6021a9b33d3c3c167 ]

Previous to commit 22b5c0b63f32 ("vsock/virtio: fix kernel panic
after device hot-unplug"), vsock_core_init() was called from
virtio_vsock_probe(). Now, virtio_transport_reset_no_sock() can be called
before vsock_core_init() has the chance to run.

[Wed Feb 27 14:17:09 2019] BUG: unable to handle kernel NULL pointer dereference at 0000000000000110
[Wed Feb 27 14:17:09 2019] #PF error: [normal kernel read fault]
[Wed Feb 27 14:17:09 2019] PGD 0 P4D 0
[Wed Feb 27 14:17:09 2019] Oops: 0000 [#1] SMP PTI
[Wed Feb 27 14:17:09 2019] CPU: 3 PID: 59 Comm: kworker/3:1 Not tainted 5.0.0-rc7-390-generic-hvi #390
[Wed Feb 27 14:17:09 2019] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014
[Wed Feb 27 14:17:09 2019] Workqueue: virtio_vsock virtio_transport_rx_work [vmw_vsock_virtio_transport]
[Wed Feb 27 14:17:09 2019] RIP: 0010:virtio_transport_reset_no_sock+0x8c/0xc0 [vmw_vsock_virtio_transport_common]
[Wed Feb 27 14:17:09 2019] Code: 35 8b 4f 14 48 8b 57 08 31 f6 44 8b 4f 10 44 8b 07 48 8d 7d c8 e8 84 f8 ff ff 48 85 c0 48 89 c3 74 2a e8 f7 31 03 00 48 89 df <48> 8b 80 10 01 00 00 e8 68 fb 69 ed 48 8b 75 f0 65 48 33 34 25 28
[Wed Feb 27 14:17:09 2019] RSP: 0018:ffffb42701ab7d40 EFLAGS: 00010282
[Wed Feb 27 14:17:09 2019] RAX: 0000000000000000 RBX: ffff9d79637ee080 RCX: 0000000000000003
[Wed Feb 27 14:17:09 2019] RDX: 0000000000000001 RSI: 0000000000000002 RDI: ffff9d79637ee080
[Wed Feb 27 14:17:09 2019] RBP: ffffb42701ab7d78 R08: ffff9d796fae70e0 R09: ffff9d796f403500
[Wed Feb 27 14:17:09 2019] R10: ffffb42701ab7d90 R11: 0000000000000000 R12: ffff9d7969d09240
[Wed Feb 27 14:17:09 2019] R13: ffff9d79624e6840 R14: ffff9d7969d09318 R15: ffff9d796d48ff80
[Wed Feb 27 14:17:09 2019] FS:  0000000000000000(0000) GS:ffff9d796fac0000(0000) knlGS:0000000000000000
[Wed Feb 27 14:17:09 2019] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[Wed Feb 27 14:17:09 2019] CR2: 0000000000000110 CR3: 0000000427f22000 CR4: 00000000000006e0
[Wed Feb 27 14:17:09 2019] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[Wed Feb 27 14:17:09 2019] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[Wed Feb 27 14:17:09 2019] Call Trace:
[Wed Feb 27 14:17:09 2019]  virtio_transport_recv_pkt+0x63/0x820 [vmw_vsock_virtio_transport_common]
[Wed Feb 27 14:17:09 2019]  ? kfree+0x17e/0x190
[Wed Feb 27 14:17:09 2019]  ? detach_buf_split+0x145/0x160
[Wed Feb 27 14:17:09 2019]  ? __switch_to_asm+0x40/0x70
[Wed Feb 27 14:17:09 2019]  virtio_transport_rx_work+0xa0/0x106 [vmw_vsock_virtio_transport]
[Wed Feb 27 14:17:09 2019] NET: Registered protocol family 40
[Wed Feb 27 14:17:09 2019]  process_one_work+0x167/0x410
[Wed Feb 27 14:17:09 2019]  worker_thread+0x4d/0x460
[Wed Feb 27 14:17:09 2019]  kthread+0x105/0x140
[Wed Feb 27 14:17:09 2019]  ? rescuer_thread+0x360/0x360
[Wed Feb 27 14:17:09 2019]  ? kthread_destroy_worker+0x50/0x50
[Wed Feb 27 14:17:09 2019]  ret_from_fork+0x35/0x40
[Wed Feb 27 14:17:09 2019] Modules linked in: vmw_vsock_virtio_transport vmw_vsock_virtio_transport_common input_leds vsock serio_raw i2c_piix4 mac_hid qemu_fw_cfg autofs4 cirrus ttm drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops virtio_net psmouse drm net_failover pata_acpi virtio_blk failover floppy

Fixes: 22b5c0b63f32 ("vsock/virtio: fix kernel panic after device hot-unplug")
Reported-by: Alexandru Herghelegiu <aherghelegiu@bitdefender.com>
Signed-off-by: Adalbert Lazăr <alazar@bitdefender.com>
Co-developed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/vmw_vsock/virtio_transport_common.c | 22 +++++++++++++++-------
 1 file changed, 15 insertions(+), 7 deletions(-)

diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 3ae3a33da70b..602715fc9a75 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -662,6 +662,8 @@ static int virtio_transport_reset(struct vsock_sock *vsk,
  */
 static int virtio_transport_reset_no_sock(struct virtio_vsock_pkt *pkt)
 {
+	const struct virtio_transport *t;
+	struct virtio_vsock_pkt *reply;
 	struct virtio_vsock_pkt_info info = {
 		.op = VIRTIO_VSOCK_OP_RST,
 		.type = le16_to_cpu(pkt->hdr.type),
@@ -672,15 +674,21 @@ static int virtio_transport_reset_no_sock(struct virtio_vsock_pkt *pkt)
 	if (le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_RST)
 		return 0;
 
-	pkt = virtio_transport_alloc_pkt(&info, 0,
-					 le64_to_cpu(pkt->hdr.dst_cid),
-					 le32_to_cpu(pkt->hdr.dst_port),
-					 le64_to_cpu(pkt->hdr.src_cid),
-					 le32_to_cpu(pkt->hdr.src_port));
-	if (!pkt)
+	reply = virtio_transport_alloc_pkt(&info, 0,
+					   le64_to_cpu(pkt->hdr.dst_cid),
+					   le32_to_cpu(pkt->hdr.dst_port),
+					   le64_to_cpu(pkt->hdr.src_cid),
+					   le32_to_cpu(pkt->hdr.src_port));
+	if (!reply)
 		return -ENOMEM;
 
-	return virtio_transport_get_ops()->send_pkt(pkt);
+	t = virtio_transport_get_ops();
+	if (!t) {
+		virtio_transport_free_pkt(reply);
+		return -ENOTCONN;
+	}
+
+	return t->send_pkt(reply);
 }
 
 static void virtio_transport_wait_close(struct sock *sk, long timeout)
-- 
2.20.1


From 3963ab74f6c8daf4a014b7b5848dbd3f60c56570 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Wed, 6 Mar 2019 16:22:12 +0200
Subject: [PATCH 30/30] net: sched: flower: insert new filter to idr after
 setting its mask

[ Upstream commit ecb3dea400d3beaf611ce76ac7a51d4230492cf2 ]

When adding new filter to flower classifier, fl_change() inserts it to
handle_idr before initializing filter extensions and assigning it a mask.
Normally this ordering doesn't matter because all flower classifier ops
callbacks assume rtnl lock protection. However, when filter has an action
that doesn't have its kernel module loaded, rtnl lock is released before
call to request_module(). During this time the filter can be accessed bu
concurrent task before its initialization is completed, which can lead to a
crash.

Example case of NULL pointer dereference in concurrent dump:

Task 1                           Task 2

tc_new_tfilter()
 fl_change()
  idr_alloc_u32(fnew)
  fl_set_parms()
   tcf_exts_validate()
    tcf_action_init()
     tcf_action_init_1()
      rtnl_unlock()
      request_module()
      ...                        rtnl_lock()
      				 tc_dump_tfilter()
      				  tcf_chain_dump()
				   fl_walk()
				    idr_get_next_ul()
				    tcf_node_dump()
				     tcf_fill_node()
				      fl_dump()
				       mask = &f->mask->key; <- NULL ptr
      rtnl_lock()

Extension initialization and mask assignment don't depend on fnew->handle
that is allocated by idr_alloc_u32(). Move idr allocation code after action
creation and mask assignment in fl_change() to prevent concurrent access
to not fully initialized filter when rtnl lock is released to load action
module.

Fixes: 01683a146999 ("net: sched: refactor flower walk to iterate over idr")
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_flower.c | 43 +++++++++++++++++++++---------------------
 1 file changed, 22 insertions(+), 21 deletions(-)

diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 12ca9d13db83..bf67ae5ac1c3 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -1327,46 +1327,46 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
 	if (err < 0)
 		goto errout;
 
-	if (!handle) {
-		handle = 1;
-		err = idr_alloc_u32(&head->handle_idr, fnew, &handle,
-				    INT_MAX, GFP_KERNEL);
-	} else if (!fold) {
-		/* user specifies a handle and it doesn't exist */
-		err = idr_alloc_u32(&head->handle_idr, fnew, &handle,
-				    handle, GFP_KERNEL);
-	}
-	if (err)
-		goto errout;
-	fnew->handle = handle;
-
 	if (tb[TCA_FLOWER_FLAGS]) {
 		fnew->flags = nla_get_u32(tb[TCA_FLOWER_FLAGS]);
 
 		if (!tc_flags_valid(fnew->flags)) {
 			err = -EINVAL;
-			goto errout_idr;
+			goto errout;
 		}
 	}
 
 	err = fl_set_parms(net, tp, fnew, mask, base, tb, tca[TCA_RATE], ovr,
 			   tp->chain->tmplt_priv, extack);
 	if (err)
-		goto errout_idr;
+		goto errout;
 
 	err = fl_check_assign_mask(head, fnew, fold, mask);
 	if (err)
-		goto errout_idr;
+		goto errout;
+
+	if (!handle) {
+		handle = 1;
+		err = idr_alloc_u32(&head->handle_idr, fnew, &handle,
+				    INT_MAX, GFP_KERNEL);
+	} else if (!fold) {
+		/* user specifies a handle and it doesn't exist */
+		err = idr_alloc_u32(&head->handle_idr, fnew, &handle,
+				    handle, GFP_KERNEL);
+	}
+	if (err)
+		goto errout_mask;
+	fnew->handle = handle;
 
 	if (!fold && __fl_lookup(fnew->mask, &fnew->mkey)) {
 		err = -EEXIST;
-		goto errout_mask;
+		goto errout_idr;
 	}
 
 	err = rhashtable_insert_fast(&fnew->mask->ht, &fnew->ht_node,
 				     fnew->mask->filter_ht_params);
 	if (err)
-		goto errout_mask;
+		goto errout_idr;
 
 	if (!tc_skip_hw(fnew->flags)) {
 		err = fl_hw_replace_filter(tp, fnew, extack);
@@ -1405,12 +1405,13 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
 	rhashtable_remove_fast(&fnew->mask->ht, &fnew->ht_node,
 			       fnew->mask->filter_ht_params);
 
-errout_mask:
-	fl_mask_put(head, fnew->mask, false);
-
 errout_idr:
 	if (!fold)
 		idr_remove(&head->handle_idr, fnew->handle);
+
+errout_mask:
+	fl_mask_put(head, fnew->mask, false);
+
 errout:
 	tcf_exts_destroy(&fnew->exts);
 	kfree(fnew);
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Thu, Mar 14, 2019 at 06:47:45PM -0700, David Miller wrote:
> 
> Please queue up the following bug fixes for v4.20 and v5.0 -stable,
> respectively.

All queued up, thanks!

greg k-h

Re: [PATCHES] Networking

[Greg KH]

On Thu, Mar 14, 2019 at 11:30:46PM -0700, Greg KH wrote:
> On Thu, Mar 14, 2019 at 06:47:45PM -0700, David Miller wrote:
> > 
> > Please queue up the following bug fixes for v4.20 and v5.0 -stable,
> > respectively.
> 
> All queued up, thanks!

Note, 4.20 is now end-of-life, so no need for any 4.20.y patches
anymore, thanks.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 103 bytes --]


Please queue up the following networking bug fixes for v4.19 and v5.0
-stable, respectively.

Thanks!

[-- Attachment #2: net_419.mbox --]
[-- Type: Application/Octet-Stream, Size: 64759 bytes --]

From 519b71619f355ca99a0c3521a9ced7a0c29ad752 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 19 Mar 2019 05:46:18 -0700
Subject: [PATCH 01/29] dccp: do not use ipv6 header for ipv4 flow

[ Upstream commit e0aa67709f89d08c8d8e5bdd9e0b649df61d0090 ]

When a dual stack dccp listener accepts an ipv4 flow,
it should not attempt to use an ipv6 header or
inet6_iif() helper.

Fixes: 3df80d9320bc ("[DCCP]: Introduce DCCPv6")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ipv6.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 6344f1b18a6a..58a401e9cf09 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -433,8 +433,8 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk,
 		newnp->ipv6_mc_list = NULL;
 		newnp->ipv6_ac_list = NULL;
 		newnp->ipv6_fl_list = NULL;
-		newnp->mcast_oif   = inet6_iif(skb);
-		newnp->mcast_hops  = ipv6_hdr(skb)->hop_limit;
+		newnp->mcast_oif   = inet_iif(skb);
+		newnp->mcast_hops  = ip_hdr(skb)->ttl;
 
 		/*
 		 * No need to charge this sock to the relevant IPv6 refcnt debug socks count
-- 
2.20.1


From b99478c71d9bacb3e3f4fc62acce9fe37553d4bb Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Thu, 21 Mar 2019 15:02:50 +0800
Subject: [PATCH 02/29] genetlink: Fix a memory leak on error path

[ Upstream commit ceabee6c59943bdd5e1da1a6a20dc7ee5f8113a2 ]

In genl_register_family(), when idr_alloc() fails,
we forget to free the memory we possibly allocate for
family->attrbuf.

Reported-by: Hulk Robot <hulkci@huawei.com>
Fixes: 2ae0f17df1cd ("genetlink: use idr to track families")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Reviewed-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/genetlink.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 25eeb6d2a75a..f0ec068e1d02 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -366,7 +366,7 @@ int genl_register_family(struct genl_family *family)
 			       start, end + 1, GFP_KERNEL);
 	if (family->id < 0) {
 		err = family->id;
-		goto errout_locked;
+		goto errout_free;
 	}
 
 	err = genl_validate_assign_mc_groups(family);
@@ -385,6 +385,7 @@ int genl_register_family(struct genl_family *family)
 
 errout_remove:
 	idr_remove(&genl_fam_idr, family->id);
+errout_free:
 	kfree(family->attrbuf);
 errout_locked:
 	genl_unlock_all();
-- 
2.20.1


From 9ea4e95ffd9a0af5db23bbd5748d50aa992dc3a5 Mon Sep 17 00:00:00 2001
From: Matteo Croce <mcroce@redhat.com>
Date: Sat, 16 Mar 2019 01:00:50 +0100
Subject: [PATCH 03/29] gtp: change NET_UDP_TUNNEL dependency to select

[ Upstream commit c22da36688d6298f2e546dcc43fdc1ad35036467 ]

Similarly to commit a7603ac1fc8c ("geneve: change NET_UDP_TUNNEL
dependency to select"), GTP has a dependency on NET_UDP_TUNNEL which
makes impossible to compile it if no other protocol depending on
NET_UDP_TUNNEL is selected.

Fix this by changing the depends to a select, and drop NET_IP_TUNNEL from
the select list, as it already depends on NET_UDP_TUNNEL.

Signed-off-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/Kconfig | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index d03775100f7d..619bf1498a66 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -213,8 +213,8 @@ config GENEVE
 
 config GTP
 	tristate "GPRS Tunneling Protocol datapath (GTP-U)"
-	depends on INET && NET_UDP_TUNNEL
-	select NET_IP_TUNNEL
+	depends on INET
+	select NET_UDP_TUNNEL
 	---help---
 	  This allows one to create gtp virtual interfaces that provide
 	  the GPRS Tunneling Protocol datapath (GTP-U). This tunneling protocol
-- 
2.20.1


From a9efc98e13d6477ff20fd6631ec4226119e4398c Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 20 Mar 2019 14:45:48 +0800
Subject: [PATCH 04/29] ipv6: make ip6_create_rt_rcu return ip6_null_entry
 instead of NULL

[ Upstream commit 1c87e79a002f6a159396138cd3f3ab554a2a8887 ]

Jianlin reported a crash:

  [  381.484332] BUG: unable to handle kernel NULL pointer dereference at 0000000000000068
  [  381.619802] RIP: 0010:fib6_rule_lookup+0xa3/0x160
  [  382.009615] Call Trace:
  [  382.020762]  <IRQ>
  [  382.030174]  ip6_route_redirect.isra.52+0xc9/0xf0
  [  382.050984]  ip6_redirect+0xb6/0xf0
  [  382.066731]  icmpv6_notify+0xca/0x190
  [  382.083185]  ndisc_redirect_rcv+0x10f/0x160
  [  382.102569]  ndisc_rcv+0xfb/0x100
  [  382.117725]  icmpv6_rcv+0x3f2/0x520
  [  382.133637]  ip6_input_finish+0xbf/0x460
  [  382.151634]  ip6_input+0x3b/0xb0
  [  382.166097]  ipv6_rcv+0x378/0x4e0

It was caused by the lookup function __ip6_route_redirect() returns NULL in
fib6_rule_lookup() when ip6_create_rt_rcu() returns NULL.

So we fix it by simply making ip6_create_rt_rcu() return ip6_null_entry
instead of NULL.

v1->v2:
  - move down 'fallback:' to make it more readable.

Fixes: e873e4b9cc7e ("ipv6: use fib6_info_hold_safe() when necessary")
Reported-by: Jianlin Shi <jishi@redhat.com>
Suggested-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Acked-by: Wei Wang <weiwan@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 66cc94427437..9006bb3c9e72 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1048,14 +1048,20 @@ static struct rt6_info *ip6_create_rt_rcu(struct fib6_info *rt)
 	struct rt6_info *nrt;
 
 	if (!fib6_info_hold_safe(rt))
-		return NULL;
+		goto fallback;
 
 	nrt = ip6_dst_alloc(dev_net(dev), dev, flags);
-	if (nrt)
-		ip6_rt_copy_init(nrt, rt);
-	else
+	if (!nrt) {
 		fib6_info_release(rt);
+		goto fallback;
+	}
 
+	ip6_rt_copy_init(nrt, rt);
+	return nrt;
+
+fallback:
+	nrt = dev_net(dev)->ipv6.ip6_null_entry;
+	dst_hold(&nrt->dst);
 	return nrt;
 }
 
@@ -1104,10 +1110,6 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net,
 		dst_hold(&rt->dst);
 	} else {
 		rt = ip6_create_rt_rcu(f6i);
-		if (!rt) {
-			rt = net->ipv6.ip6_null_entry;
-			dst_hold(&rt->dst);
-		}
 	}
 
 	rcu_read_unlock();
-- 
2.20.1


From 0c1c0616d9f73f2bcd546a9ae521ee0fc987009c Mon Sep 17 00:00:00 2001
From: Finn Thain <fthain@telegraphics.com.au>
Date: Sat, 16 Mar 2019 14:21:19 +1100
Subject: [PATCH 05/29] mac8390: Fix mmio access size probe

[ Upstream commit bb9e5c5bcd76f4474eac3baf643d7a39f7bac7bb ]

The bug that Stan reported is as follows. After a restart, a 16-bit NIC
may be incorrectly identified as a 32-bit NIC and stop working.

mac8390 slot.E: Memory length resource not found, probing
mac8390 slot.E: Farallon EtherMac II-C (type farallon)
mac8390 slot.E: MAC 00:00:c5:30:c2:99, IRQ 61, 32 KB shared memory at 0xfeed0000, 32-bit access.

The bug never arises after a cold start and only intermittently after a
warm start. (I didn't investigate why the bug is intermittent.)

It turns out that memcpy_toio() is deprecated and memcmp_withio() also
has issues. Replacing these calls with mmio accessors fixes the problem.

Reported-and-tested-by: Stan Johnson <userm57@yahoo.com>
Fixes: 2964db0f5904 ("m68k: Mac DP8390 update")
Signed-off-by: Finn Thain <fthain@telegraphics.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/8390/mac8390.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/8390/mac8390.c b/drivers/net/ethernet/8390/mac8390.c
index 342ae08ec3c2..d60a86aa8aa8 100644
--- a/drivers/net/ethernet/8390/mac8390.c
+++ b/drivers/net/ethernet/8390/mac8390.c
@@ -153,8 +153,6 @@ static void dayna_block_input(struct net_device *dev, int count,
 static void dayna_block_output(struct net_device *dev, int count,
 			       const unsigned char *buf, int start_page);
 
-#define memcmp_withio(a, b, c)	memcmp((a), (void *)(b), (c))
-
 /* Slow Sane (16-bit chunk memory read/write) Cabletron uses this */
 static void slow_sane_get_8390_hdr(struct net_device *dev,
 				   struct e8390_pkt_hdr *hdr, int ring_page);
@@ -233,19 +231,26 @@ static enum mac8390_type mac8390_ident(struct nubus_rsrc *fres)
 
 static enum mac8390_access mac8390_testio(unsigned long membase)
 {
-	unsigned long outdata = 0xA5A0B5B0;
-	unsigned long indata =  0x00000000;
+	u32 outdata = 0xA5A0B5B0;
+	u32 indata = 0;
+
 	/* Try writing 32 bits */
-	memcpy_toio((void __iomem *)membase, &outdata, 4);
-	/* Now compare them */
-	if (memcmp_withio(&outdata, membase, 4) == 0)
+	nubus_writel(outdata, membase);
+	/* Now read it back */
+	indata = nubus_readl(membase);
+	if (outdata == indata)
 		return ACCESS_32;
+
+	outdata = 0xC5C0D5D0;
+	indata = 0;
+
 	/* Write 16 bit output */
 	word_memcpy_tocard(membase, &outdata, 4);
 	/* Now read it back */
 	word_memcpy_fromcard(&indata, membase, 4);
 	if (outdata == indata)
 		return ACCESS_16;
+
 	return ACCESS_UNKNOWN;
 }
 
-- 
2.20.1


From a33fe700c16a6368e10a1fa14cf0be8678695d20 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Mon, 18 Mar 2019 08:51:06 -0500
Subject: [PATCH 06/29] mISDN: hfcpci: Test both vendor & device ID for Digium
 HFC4S

[ Upstream commit fae846e2b7124d4b076ef17791c73addf3b26350 ]

The device ID alone does not uniquely identify a device.  Test both the
vendor and device ID to make sure we don't mistakenly think some other
vendor's 0xB410 device is a Digium HFC4S.  Also, instead of the bare hex
ID, use the same constant (PCI_DEVICE_ID_DIGIUM_HFC4S) used in the device
ID table.

No functional change intended.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/hardware/mISDN/hfcmulti.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/isdn/hardware/mISDN/hfcmulti.c b/drivers/isdn/hardware/mISDN/hfcmulti.c
index 4d85645c87f7..0928fd1f0e0c 100644
--- a/drivers/isdn/hardware/mISDN/hfcmulti.c
+++ b/drivers/isdn/hardware/mISDN/hfcmulti.c
@@ -4365,7 +4365,8 @@ setup_pci(struct hfc_multi *hc, struct pci_dev *pdev,
 	if (m->clock2)
 		test_and_set_bit(HFC_CHIP_CLOCK2, &hc->chip);
 
-	if (ent->device == 0xB410) {
+	if (ent->vendor == PCI_VENDOR_ID_DIGIUM &&
+	    ent->device == PCI_DEVICE_ID_DIGIUM_HFC4S) {
 		test_and_set_bit(HFC_CHIP_B410P, &hc->chip);
 		test_and_set_bit(HFC_CHIP_PCM_MASTER, &hc->chip);
 		test_and_clear_bit(HFC_CHIP_PCM_SLAVE, &hc->chip);
-- 
2.20.1


From 60a1150ded4012392512d9f60ada0c819c66d06c Mon Sep 17 00:00:00 2001
From: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Date: Sat, 16 Mar 2019 08:28:18 +0000
Subject: [PATCH 07/29] net: aquantia: fix rx checksum offload for UDP/TCP over
 IPv6

[ Upstream commit a7faaa0c5dc7d091cc9f72b870d7edcdd6f43f12 ]

TCP/UDP checksum validity was propagated to skb
only if IP checksum is valid.
But for IPv6 there is no validity as there is no checksum in IPv6.
This patch propagates TCP/UDP checksum validity regardless of IP checksum.

Fixes: 018423e90bee ("net: ethernet: aquantia: Add ring support code")
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: Nikita Danilov <nikita.danilov@aquantia.com>
Signed-off-by: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/aq_ring.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index 7134d0d4cdf7..6f3312350cac 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -186,11 +186,12 @@ static void aq_rx_checksum(struct aq_ring_s *self,
 	}
 	if (buff->is_ip_cso) {
 		__skb_incr_checksum_unnecessary(skb);
-		if (buff->is_udp_cso || buff->is_tcp_cso)
-			__skb_incr_checksum_unnecessary(skb);
 	} else {
 		skb->ip_summed = CHECKSUM_NONE;
 	}
+
+	if (buff->is_udp_cso || buff->is_tcp_cso)
+		__skb_incr_checksum_unnecessary(skb);
 }
 
 #define AQ_SKB_ALIGN SKB_DATA_ALIGN(sizeof(struct skb_shared_info))
-- 
2.20.1


From f038f6710301e51c19789eeaaf7055ececa5edf5 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 25 Mar 2019 14:18:06 +0100
Subject: [PATCH 08/29] net: datagram: fix unbounded loop in
 __skb_try_recv_datagram()

[ Upstream commit 0b91bce1ebfc797ff3de60c8f4a1e6219a8a3187 ]

Christoph reported a stall while peeking datagram with an offset when
busy polling is enabled. __skb_try_recv_datagram() uses as the loop
termination condition 'queue empty'. When peeking, the socket
queue can be not empty, even when no additional packets are received.

Address the issue explicitly checking for receive queue changes,
as currently done by __skb_wait_for_more_packets().

Fixes: 2b5cd0dfa384 ("net: Change return type of sk_busy_loop from bool to void")
Reported-and-tested-by: Christoph Paasch <cpaasch@apple.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/datagram.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/datagram.c b/net/core/datagram.c
index 57f3a6fcfc1e..a487df53a453 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -279,7 +279,7 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags,
 			break;
 
 		sk_busy_loop(sk, flags & MSG_DONTWAIT);
-	} while (!skb_queue_empty(&sk->sk_receive_queue));
+	} while (sk->sk_receive_queue.prev != *last);
 
 	error = -EAGAIN;
 
-- 
2.20.1


From 80a12180424aba6b8ca2b167263871c5e9a67626 Mon Sep 17 00:00:00 2001
From: Christoph Paasch <cpaasch@apple.com>
Date: Mon, 18 Mar 2019 23:14:52 -0700
Subject: [PATCH 09/29] net/packet: Set __GFP_NOWARN upon allocation in
 alloc_pg_vec

[ Upstream commit 398f0132c14754fcd03c1c4f8e7176d001ce8ea1 ]

Since commit fc62814d690c ("net/packet: fix 4gb buffer limit due to overflow check")
one can now allocate packet ring buffers >= UINT_MAX. However, syzkaller
found that that triggers a warning:

[   21.100000] WARNING: CPU: 2 PID: 2075 at mm/page_alloc.c:4584 __alloc_pages_nod0
[   21.101490] Modules linked in:
[   21.101921] CPU: 2 PID: 2075 Comm: syz-executor.0 Not tainted 5.0.0 #146
[   21.102784] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 0.5.1 01/01/2011
[   21.103887] RIP: 0010:__alloc_pages_nodemask+0x2a0/0x630
[   21.104640] Code: fe ff ff 65 48 8b 04 25 c0 de 01 00 48 05 90 0f 00 00 41 bd 01 00 00 00 48 89 44 24 48 e9 9c fe 3
[   21.107121] RSP: 0018:ffff88805e1cf920 EFLAGS: 00010246
[   21.107819] RAX: 0000000000000000 RBX: ffffffff85a488a0 RCX: 0000000000000000
[   21.108753] RDX: 0000000000000000 RSI: dffffc0000000000 RDI: 0000000000000000
[   21.109699] RBP: 1ffff1100bc39f28 R08: ffffed100bcefb67 R09: ffffed100bcefb67
[   21.110646] R10: 0000000000000001 R11: ffffed100bcefb66 R12: 000000000000000d
[   21.111623] R13: 0000000000000000 R14: ffff88805e77d888 R15: 000000000000000d
[   21.112552] FS:  00007f7c7de05700(0000) GS:ffff88806d100000(0000) knlGS:0000000000000000
[   21.113612] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   21.114405] CR2: 000000000065c000 CR3: 000000005e58e006 CR4: 00000000001606e0
[   21.115367] Call Trace:
[   21.115705]  ? __alloc_pages_slowpath+0x21c0/0x21c0
[   21.116362]  alloc_pages_current+0xac/0x1e0
[   21.116923]  kmalloc_order+0x18/0x70
[   21.117393]  kmalloc_order_trace+0x18/0x110
[   21.117949]  packet_set_ring+0x9d5/0x1770
[   21.118524]  ? packet_rcv_spkt+0x440/0x440
[   21.119094]  ? lock_downgrade+0x620/0x620
[   21.119646]  ? __might_fault+0x177/0x1b0
[   21.120177]  packet_setsockopt+0x981/0x2940
[   21.120753]  ? __fget+0x2fb/0x4b0
[   21.121209]  ? packet_release+0xab0/0xab0
[   21.121740]  ? sock_has_perm+0x1cd/0x260
[   21.122297]  ? selinux_secmark_relabel_packet+0xd0/0xd0
[   21.123013]  ? __fget+0x324/0x4b0
[   21.123451]  ? selinux_netlbl_socket_setsockopt+0x101/0x320
[   21.124186]  ? selinux_netlbl_sock_rcv_skb+0x3a0/0x3a0
[   21.124908]  ? __lock_acquire+0x529/0x3200
[   21.125453]  ? selinux_socket_setsockopt+0x5d/0x70
[   21.126075]  ? __sys_setsockopt+0x131/0x210
[   21.126533]  ? packet_release+0xab0/0xab0
[   21.127004]  __sys_setsockopt+0x131/0x210
[   21.127449]  ? kernel_accept+0x2f0/0x2f0
[   21.127911]  ? ret_from_fork+0x8/0x50
[   21.128313]  ? do_raw_spin_lock+0x11b/0x280
[   21.128800]  __x64_sys_setsockopt+0xba/0x150
[   21.129271]  ? lockdep_hardirqs_on+0x37f/0x560
[   21.129769]  do_syscall_64+0x9f/0x450
[   21.130182]  entry_SYSCALL_64_after_hwframe+0x49/0xbe

We should allocate with __GFP_NOWARN to handle this.

Cc: Kal Conley <kal.conley@dectris.com>
Cc: Andrey Konovalov <andreyknvl@google.com>
Fixes: fc62814d690c ("net/packet: fix 4gb buffer limit due to overflow check")
Signed-off-by: Christoph Paasch <cpaasch@apple.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index fd16fb836df2..03f7e1614173 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -4194,7 +4194,7 @@ static struct pgv *alloc_pg_vec(struct tpacket_req *req, int order)
 	struct pgv *pg_vec;
 	int i;
 
-	pg_vec = kcalloc(block_nr, sizeof(struct pgv), GFP_KERNEL);
+	pg_vec = kcalloc(block_nr, sizeof(struct pgv), GFP_KERNEL | __GFP_NOWARN);
 	if (unlikely(!pg_vec))
 		goto out;
 
-- 
2.20.1


From 254ba4c3c5a4c375b857982b8590464186e28ac1 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Thu, 14 Mar 2019 14:49:45 +0100
Subject: [PATCH 10/29] net: phy: meson-gxl: fix interrupt support

[ Upstream commit daa5c4d0167a308306525fd5ab9a5e18e21f4f74 ]

If an interrupt is already pending when the interrupt is enabled on the
GXL phy, no IRQ will ever be triggered.

The fix is simply to make sure pending IRQs are cleared before setting
up the irq mask.

Fixes: cf127ff20af1 ("net: phy: meson-gxl: add interrupt support")
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/meson-gxl.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/phy/meson-gxl.c b/drivers/net/phy/meson-gxl.c
index ddc2c5ea3787..7ceebbc4bcc2 100644
--- a/drivers/net/phy/meson-gxl.c
+++ b/drivers/net/phy/meson-gxl.c
@@ -211,6 +211,7 @@ static int meson_gxl_ack_interrupt(struct phy_device *phydev)
 static int meson_gxl_config_intr(struct phy_device *phydev)
 {
 	u16 val;
+	int ret;
 
 	if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
 		val = INTSRC_ANEG_PR
@@ -223,6 +224,11 @@ static int meson_gxl_config_intr(struct phy_device *phydev)
 		val = 0;
 	}
 
+	/* Ack any pending IRQ */
+	ret = meson_gxl_ack_interrupt(phydev);
+	if (ret)
+		return ret;
+
 	return phy_write(phydev, INTSRC_MASK, val);
 }
 
-- 
2.20.1


From 4b0aae593dc5041fdf60430dd5efd2796be302cc Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 15 Mar 2019 10:41:14 -0700
Subject: [PATCH 11/29] net: rose: fix a possible stack overflow

[ Upstream commit e5dcc0c3223c45c94100f05f28d8ef814db3d82c ]

rose_write_internal() uses a temp buffer of 100 bytes, but a manual
inspection showed that given arbitrary input, rose_create_facilities()
can fill up to 110 bytes.

Lets use a tailroom of 256 bytes for peace of mind, and remove
the bounce buffer : we can simply allocate a big enough skb
and adjust its length as needed.

syzbot report :

BUG: KASAN: stack-out-of-bounds in memcpy include/linux/string.h:352 [inline]
BUG: KASAN: stack-out-of-bounds in rose_create_facilities net/rose/rose_subr.c:521 [inline]
BUG: KASAN: stack-out-of-bounds in rose_write_internal+0x597/0x15d0 net/rose/rose_subr.c:116
Write of size 7 at addr ffff88808b1ffbef by task syz-executor.0/24854

CPU: 0 PID: 24854 Comm: syz-executor.0 Not tainted 5.0.0+ #97
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 print_address_description.cold+0x7c/0x20d mm/kasan/report.c:187
 kasan_report.cold+0x1b/0x40 mm/kasan/report.c:317
 check_memory_region_inline mm/kasan/generic.c:185 [inline]
 check_memory_region+0x123/0x190 mm/kasan/generic.c:191
 memcpy+0x38/0x50 mm/kasan/common.c:131
 memcpy include/linux/string.h:352 [inline]
 rose_create_facilities net/rose/rose_subr.c:521 [inline]
 rose_write_internal+0x597/0x15d0 net/rose/rose_subr.c:116
 rose_connect+0x7cb/0x1510 net/rose/af_rose.c:826
 __sys_connect+0x266/0x330 net/socket.c:1685
 __do_sys_connect net/socket.c:1696 [inline]
 __se_sys_connect net/socket.c:1693 [inline]
 __x64_sys_connect+0x73/0xb0 net/socket.c:1693
 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x458079
Code: ad b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f47b8d9dc78 EFLAGS: 00000246 ORIG_RAX: 000000000000002a
RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000458079
RDX: 000000000000001c RSI: 0000000020000040 RDI: 0000000000000004
RBP: 000000000073bf00 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00007f47b8d9e6d4
R13: 00000000004be4a4 R14: 00000000004ceca8 R15: 00000000ffffffff

The buggy address belongs to the page:
page:ffffea00022c7fc0 count:0 mapcount:0 mapping:0000000000000000 index:0x0
flags: 0x1fffc0000000000()
raw: 01fffc0000000000 0000000000000000 ffffffff022c0101 0000000000000000
raw: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff88808b1ffa80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
 ffff88808b1ffb00: 00 00 00 00 00 00 00 00 f1 f1 f1 f1 00 00 00 03
>ffff88808b1ffb80: f2 f2 00 00 00 00 00 00 00 00 00 00 00 00 04 f3
                                                             ^
 ffff88808b1ffc00: f3 f3 f3 f3 00 00 00 00 00 00 00 00 00 00 00 00
 ffff88808b1ffc80: 00 00 00 00 00 00 00 f1 f1 f1 f1 f1 f1 01 f2 01

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rose/rose_subr.c | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/net/rose/rose_subr.c b/net/rose/rose_subr.c
index 7ca57741b2fb..7849f286bb93 100644
--- a/net/rose/rose_subr.c
+++ b/net/rose/rose_subr.c
@@ -105,16 +105,17 @@ void rose_write_internal(struct sock *sk, int frametype)
 	struct sk_buff *skb;
 	unsigned char  *dptr;
 	unsigned char  lci1, lci2;
-	char buffer[100];
-	int len, faclen = 0;
+	int maxfaclen = 0;
+	int len, faclen;
+	int reserve;
 
-	len = AX25_BPQ_HEADER_LEN + AX25_MAX_HEADER_LEN + ROSE_MIN_LEN + 1;
+	reserve = AX25_BPQ_HEADER_LEN + AX25_MAX_HEADER_LEN + 1;
+	len = ROSE_MIN_LEN;
 
 	switch (frametype) {
 	case ROSE_CALL_REQUEST:
 		len   += 1 + ROSE_ADDR_LEN + ROSE_ADDR_LEN;
-		faclen = rose_create_facilities(buffer, rose);
-		len   += faclen;
+		maxfaclen = 256;
 		break;
 	case ROSE_CALL_ACCEPTED:
 	case ROSE_CLEAR_REQUEST:
@@ -123,15 +124,16 @@ void rose_write_internal(struct sock *sk, int frametype)
 		break;
 	}
 
-	if ((skb = alloc_skb(len, GFP_ATOMIC)) == NULL)
+	skb = alloc_skb(reserve + len + maxfaclen, GFP_ATOMIC);
+	if (!skb)
 		return;
 
 	/*
 	 *	Space for AX.25 header and PID.
 	 */
-	skb_reserve(skb, AX25_BPQ_HEADER_LEN + AX25_MAX_HEADER_LEN + 1);
+	skb_reserve(skb, reserve);
 
-	dptr = skb_put(skb, skb_tailroom(skb));
+	dptr = skb_put(skb, len);
 
 	lci1 = (rose->lci >> 8) & 0x0F;
 	lci2 = (rose->lci >> 0) & 0xFF;
@@ -146,7 +148,8 @@ void rose_write_internal(struct sock *sk, int frametype)
 		dptr   += ROSE_ADDR_LEN;
 		memcpy(dptr, &rose->source_addr, ROSE_ADDR_LEN);
 		dptr   += ROSE_ADDR_LEN;
-		memcpy(dptr, buffer, faclen);
+		faclen = rose_create_facilities(dptr, rose);
+		skb_put(skb, faclen);
 		dptr   += faclen;
 		break;
 
-- 
2.20.1


From 494b8e6f156756ba5d440197097624265703c00c Mon Sep 17 00:00:00 2001
From: Aaro Koskinen <aaro.koskinen@nokia.com>
Date: Mon, 18 Mar 2019 23:36:08 +0200
Subject: [PATCH 12/29] net: stmmac: fix memory corruption with large MTUs

[ Upstream commit 223a960c01227e4dbcb6f9fa06b47d73bda21274 ]

When using 16K DMA buffers and ring mode, the DES3 refill is not working
correctly as the function is using a bogus pointer for checking the
private data. As a result stale pointers will remain in the RX descriptor
ring, so DMA will now likely overwrite/corrupt some already freed memory.

As simple reproducer, just receive some UDP traffic:

	# ifconfig eth0 down; ifconfig eth0 mtu 9000; ifconfig eth0 up
	# iperf3 -c 192.168.253.40 -u -b 0 -R

If you didn't crash by now check the RX descriptors to find non-contiguous
RX buffers:

	cat /sys/kernel/debug/stmmaceth/eth0/descriptors_status
	[...]
	1 [0x2be5020]: 0xa3220321 0x9ffc1ffc 0x72d70082 0x130e207e
					     ^^^^^^^^^^^^^^^^^^^^^
	2 [0x2be5040]: 0xa3220321 0x9ffc1ffc 0x72998082 0x1311a07e
					     ^^^^^^^^^^^^^^^^^^^^^

A simple ping test will now report bad data:

	# ping -s 8200 192.168.253.40
	PING 192.168.253.40 (192.168.253.40) 8200(8228) bytes of data.
	8208 bytes from 192.168.253.40: icmp_seq=1 ttl=64 time=1.00 ms
	wrong data byte #8144 should be 0xd0 but was 0x88

Fix the wrong pointer. Also we must refill DES3 only if the DMA buffer
size is 16K.

Fixes: 54139cf3bb33 ("net: stmmac: adding multiple buffers for rx")
Signed-off-by: Aaro Koskinen <aaro.koskinen@nokia.com>
Acked-by: Jose Abreu <joabreu@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/ring_mode.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
index bc83ced94e1b..afed0f0f4027 100644
--- a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
+++ b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
@@ -111,10 +111,11 @@ static unsigned int is_jumbo_frm(int len, int enh_desc)
 
 static void refill_desc3(void *priv_ptr, struct dma_desc *p)
 {
-	struct stmmac_priv *priv = (struct stmmac_priv *)priv_ptr;
+	struct stmmac_rx_queue *rx_q = priv_ptr;
+	struct stmmac_priv *priv = rx_q->priv_data;
 
 	/* Fill DES3 in case of RING mode */
-	if (priv->dma_buf_sz >= BUF_SIZE_8KiB)
+	if (priv->dma_buf_sz == BUF_SIZE_16KiB)
 		p->des3 = cpu_to_le32(le32_to_cpu(p->des2) + BUF_SIZE_8KiB);
 }
 
-- 
2.20.1


From b2702ce3b1dec3945ab8a937f34708195dcf6328 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Tue, 19 Mar 2019 10:16:53 +0800
Subject: [PATCH 13/29] net-sysfs: call dev_hold if kobject_init_and_add
 success

[ Upstream commit a3e23f719f5c4a38ffb3d30c8d7632a4ed8ccd9e ]

In netdev_queue_add_kobject and rx_queue_add_kobject,
if sysfs_create_group failed, kobject_put will call
netdev_queue_release to decrease dev refcont, however
dev_hold has not be called. So we will see this while
unregistering dev:

unregister_netdevice: waiting for bcsh0 to become free. Usage count = -1

Reported-by: Hulk Robot <hulkci@huawei.com>
Fixes: d0d668371679 ("net: don't decrement kobj reference count on init failure")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/net-sysfs.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 2aabb7eb0854..bf9a3b6ac885 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -934,6 +934,8 @@ static int rx_queue_add_kobject(struct net_device *dev, int index)
 	if (error)
 		return error;
 
+	dev_hold(queue->dev);
+
 	if (dev->sysfs_rx_queue_group) {
 		error = sysfs_create_group(kobj, dev->sysfs_rx_queue_group);
 		if (error) {
@@ -943,7 +945,6 @@ static int rx_queue_add_kobject(struct net_device *dev, int index)
 	}
 
 	kobject_uevent(kobj, KOBJ_ADD);
-	dev_hold(queue->dev);
 
 	return error;
 }
@@ -1472,6 +1473,8 @@ static int netdev_queue_add_kobject(struct net_device *dev, int index)
 	if (error)
 		return error;
 
+	dev_hold(queue->dev);
+
 #ifdef CONFIG_BQL
 	error = sysfs_create_group(kobj, &dql_group);
 	if (error) {
@@ -1481,7 +1484,6 @@ static int netdev_queue_add_kobject(struct net_device *dev, int index)
 #endif
 
 	kobject_uevent(kobj, KOBJ_ADD);
-	dev_hold(queue->dev);
 
 	return 0;
 }
-- 
2.20.1


From 150ac30e7d703244bb7418849f942150db959bf3 Mon Sep 17 00:00:00 2001
From: Wang Hai <wanghai26@huawei.com>
Date: Wed, 20 Mar 2019 14:25:05 -0400
Subject: [PATCH 14/29] net-sysfs: Fix memory leak in netdev_register_kobject

[ Upstream commit 6b70fc94afd165342876e53fc4b2f7d085009945 ]

When registering struct net_device, it will call
	register_netdevice ->
		netdev_register_kobject ->
			device_initialize(dev);
			dev_set_name(dev, "%s", ndev->name)
			device_add(dev)
			register_queue_kobjects(ndev)

In netdev_register_kobject(), if device_add(dev) or
register_queue_kobjects(ndev) failed. Register_netdevice()
will return error, causing netdev_freemem(ndev) to be
called to free net_device, however put_device(&dev->dev)->..->
kobject_cleanup() won't be called, resulting in a memory leak.

syzkaller report this:
BUG: memory leak
unreferenced object 0xffff8881f4fad168 (size 8):
comm "syz-executor.0", pid 3575, jiffies 4294778002 (age 20.134s)
hex dump (first 8 bytes):
  77 70 61 6e 30 00 ff ff                          wpan0...
backtrace:
  [<000000006d2d91d7>] kstrdup_const+0x3d/0x50 mm/util.c:73
  [<00000000ba9ff953>] kvasprintf_const+0x112/0x170 lib/kasprintf.c:48
  [<000000005555ec09>] kobject_set_name_vargs+0x55/0x130 lib/kobject.c:281
  [<0000000098d28ec3>] dev_set_name+0xbb/0xf0 drivers/base/core.c:1915
  [<00000000b7553017>] netdev_register_kobject+0xc0/0x410 net/core/net-sysfs.c:1727
  [<00000000c826a797>] register_netdevice+0xa51/0xeb0 net/core/dev.c:8711
  [<00000000857bfcfd>] cfg802154_update_iface_num.isra.2+0x13/0x90 [ieee802154]
  [<000000003126e453>] ieee802154_llsec_fill_key_id+0x1d5/0x570 [ieee802154]
  [<00000000e4b3df51>] 0xffffffffc1500e0e
  [<00000000b4319776>] platform_drv_probe+0xc6/0x180 drivers/base/platform.c:614
  [<0000000037669347>] really_probe+0x491/0x7c0 drivers/base/dd.c:509
  [<000000008fed8862>] driver_probe_device+0xdc/0x240 drivers/base/dd.c:671
  [<00000000baf52041>] device_driver_attach+0xf2/0x130 drivers/base/dd.c:945
  [<00000000c7cc8dec>] __driver_attach+0x10e/0x210 drivers/base/dd.c:1022
  [<0000000057a757c2>] bus_for_each_dev+0x154/0x1e0 drivers/base/bus.c:304
  [<000000005f5ae04b>] bus_add_driver+0x427/0x5e0 drivers/base/bus.c:645

Reported-by: Hulk Robot <hulkci@huawei.com>
Fixes: 1fa5ae857bb1 ("driver core: get rid of struct device's bus_id string array")
Signed-off-by: Wang Hai <wanghai26@huawei.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/net-sysfs.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index bf9a3b6ac885..dd2a2cb7f8f1 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1755,16 +1755,20 @@ int netdev_register_kobject(struct net_device *ndev)
 
 	error = device_add(dev);
 	if (error)
-		return error;
+		goto error_put_device;
 
 	error = register_queue_kobjects(ndev);
-	if (error) {
-		device_del(dev);
-		return error;
-	}
+	if (error)
+		goto error_device_del;
 
 	pm_runtime_set_memalloc_noio(dev, true);
 
+	return 0;
+
+error_device_del:
+	device_del(dev);
+error_put_device:
+	put_device(dev);
 	return error;
 }
 
-- 
2.20.1


From d855121b712d3b5c32808c52c0297fb465f0a8ab Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Sat, 16 Mar 2019 14:41:30 +0100
Subject: [PATCH 15/29] packets: Always register packet sk in the same order

[ Upstream commit a4dc6a49156b1f8d6e17251ffda17c9e6a5db78a ]

When using fanouts with AF_PACKET, the demux functions such as
fanout_demux_cpu will return an index in the fanout socket array, which
corresponds to the selected socket.

The ordering of this array depends on the order the sockets were added
to a given fanout group, so for FANOUT_CPU this means sockets are bound
to cpus in the order they are configured, which is OK.

However, when stopping then restarting the interface these sockets are
bound to, the sockets are reassigned to the fanout group in the reverse
order, due to the fact that they were inserted at the head of the
interface's AF_PACKET socket list.

This means that traffic that was directed to the first socket in the
fanout group is now directed to the last one after an interface restart.

In the case of FANOUT_CPU, traffic from CPU0 will be directed to the
socket that used to receive traffic from the last CPU after an interface
restart.

This commit introduces a helper to add a socket at the tail of a list,
then uses it to register AF_PACKET sockets.

Note that this changes the order in which sockets are listed in /proc and
with sock_diag.

Fixes: dc99f600698d ("packet: Add fanout support")
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h     | 6 ++++++
 net/packet/af_packet.c | 2 +-
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index 6cb5a545df7d..1ece7736c49c 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -710,6 +710,12 @@ static inline void sk_add_node_rcu(struct sock *sk, struct hlist_head *list)
 		hlist_add_head_rcu(&sk->sk_node, list);
 }
 
+static inline void sk_add_node_tail_rcu(struct sock *sk, struct hlist_head *list)
+{
+	sock_hold(sk);
+	hlist_add_tail_rcu(&sk->sk_node, list);
+}
+
 static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
 {
 	hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list);
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 03f7e1614173..a0d295478e69 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3245,7 +3245,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol,
 	}
 
 	mutex_lock(&net->packet.sklist_lock);
-	sk_add_node_rcu(sk, &net->packet.sklist);
+	sk_add_node_tail_rcu(sk, &net->packet.sklist);
 	mutex_unlock(&net->packet.sklist_lock);
 
 	preempt_disable();
-- 
2.20.1


From 6d4fc6f358f9e957c503379f0ecac53a6d389331 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Thu, 21 Mar 2019 09:39:52 +0800
Subject: [PATCH 16/29] rhashtable: Still do rehash when we get EEXIST

[ Upstream commit 408f13ef358aa5ad56dc6230c2c7deb92cf462b1 ]

As it stands if a shrink is delayed because of an outstanding
rehash, we will go into a rescheduling loop without ever doing
the rehash.

This patch fixes this by still carrying out the rehash and then
rescheduling so that we can shrink after the completion of the
rehash should it still be necessary.

The return value of EEXIST captures this case and other cases
(e.g., another thread expanded/rehashed the table at the same
time) where we should still proceed with the rehash.

Fixes: da20420f83ea ("rhashtable: Add nested tables")
Reported-by: Josh Elsasser <jelsasser@appneta.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Tested-by: Josh Elsasser <jelsasser@appneta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 lib/rhashtable.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 30526afa8343..6410c857b048 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -416,8 +416,12 @@ static void rht_deferred_worker(struct work_struct *work)
 	else if (tbl->nest)
 		err = rhashtable_rehash_alloc(ht, tbl, tbl->size);
 
-	if (!err)
-		err = rhashtable_rehash_table(ht);
+	if (!err || err == -EEXIST) {
+		int nerr;
+
+		nerr = rhashtable_rehash_table(ht);
+		err = err ?: nerr;
+	}
 
 	mutex_unlock(&ht->mutex);
 
-- 
2.20.1


From dd7359170b2e885813e3e86d99aa6ecc23fac6af Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 18 Mar 2019 19:47:00 +0800
Subject: [PATCH 17/29] sctp: get sctphdr by offset in sctp_compute_cksum

[ Upstream commit 273160ffc6b993c7c91627f5a84799c66dfe4dee ]

sctp_hdr(skb) only works when skb->transport_header is set properly.

But in Netfilter, skb->transport_header for ipv6 is not guaranteed
to be right value for sctphdr. It would cause to fail to check the
checksum for sctp packets.

So fix it by using offset, which is always right in all places.

v1->v2:
  - Fix the changelog.

Fixes: e6d8b64b34aa ("net: sctp: fix and consolidate SCTP checksumming code")
Reported-by: Li Shuang <shuali@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/checksum.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/sctp/checksum.h b/include/net/sctp/checksum.h
index 32ee65a30aff..1c6e6c0766ca 100644
--- a/include/net/sctp/checksum.h
+++ b/include/net/sctp/checksum.h
@@ -61,7 +61,7 @@ static inline __wsum sctp_csum_combine(__wsum csum, __wsum csum2,
 static inline __le32 sctp_compute_cksum(const struct sk_buff *skb,
 					unsigned int offset)
 {
-	struct sctphdr *sh = sctp_hdr(skb);
+	struct sctphdr *sh = (struct sctphdr *)(skb->data + offset);
 	const struct skb_checksum_ops ops = {
 		.update  = sctp_csum_update,
 		.combine = sctp_csum_combine,
-- 
2.20.1


From 6a20fe9d6197f77679570cb04c14e1171d78df8b Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 20 Mar 2019 14:49:38 +0800
Subject: [PATCH 18/29] sctp: use memdup_user instead of vmemdup_user

[ Upstream commit ef82bcfa671b9a635bab5fa669005663d8b177c5 ]

In sctp_setsockopt_bindx()/__sctp_setsockopt_connectx(), it allocates
memory with addrs_size which is passed from userspace. We used flag
GFP_USER to put some more restrictions on it in Commit cacc06215271
("sctp: use GFP_USER for user-controlled kmalloc").

However, since Commit c981f254cc82 ("sctp: use vmemdup_user() rather
than badly open-coding memdup_user()"), vmemdup_user() has been used,
which doesn't check GFP_USER flag when goes to vmalloc_*(). So when
addrs_size is a huge value, it could exhaust memory and even trigger
oom killer.

This patch is to use memdup_user() instead, in which GFP_USER would
work to limit the memory allocation with a huge addrs_size.

Note we can't fix it by limiting 'addrs_size', as there's no demand
for it from RFC.

Reported-by: syzbot+ec1b7575afef85a0e5ca@syzkaller.appspotmail.com
Fixes: c981f254cc82 ("sctp: use vmemdup_user() rather than badly open-coding memdup_user()")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 1b16250c5718..8c00a7ef1bcd 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1017,7 +1017,7 @@ static int sctp_setsockopt_bindx(struct sock *sk,
 	if (unlikely(addrs_size <= 0))
 		return -EINVAL;
 
-	kaddrs = vmemdup_user(addrs, addrs_size);
+	kaddrs = memdup_user(addrs, addrs_size);
 	if (unlikely(IS_ERR(kaddrs)))
 		return PTR_ERR(kaddrs);
 
@@ -1025,7 +1025,7 @@ static int sctp_setsockopt_bindx(struct sock *sk,
 	addr_buf = kaddrs;
 	while (walk_size < addrs_size) {
 		if (walk_size + sizeof(sa_family_t) > addrs_size) {
-			kvfree(kaddrs);
+			kfree(kaddrs);
 			return -EINVAL;
 		}
 
@@ -1036,7 +1036,7 @@ static int sctp_setsockopt_bindx(struct sock *sk,
 		 * causes the address buffer to overflow return EINVAL.
 		 */
 		if (!af || (walk_size + af->sockaddr_len) > addrs_size) {
-			kvfree(kaddrs);
+			kfree(kaddrs);
 			return -EINVAL;
 		}
 		addrcnt++;
@@ -1072,7 +1072,7 @@ static int sctp_setsockopt_bindx(struct sock *sk,
 	}
 
 out:
-	kvfree(kaddrs);
+	kfree(kaddrs);
 
 	return err;
 }
@@ -1347,7 +1347,7 @@ static int __sctp_setsockopt_connectx(struct sock *sk,
 	if (unlikely(addrs_size <= 0))
 		return -EINVAL;
 
-	kaddrs = vmemdup_user(addrs, addrs_size);
+	kaddrs = memdup_user(addrs, addrs_size);
 	if (unlikely(IS_ERR(kaddrs)))
 		return PTR_ERR(kaddrs);
 
@@ -1367,7 +1367,7 @@ static int __sctp_setsockopt_connectx(struct sock *sk,
 	err = __sctp_connect(sk, kaddrs, addrs_size, flags, assoc_id);
 
 out_free:
-	kvfree(kaddrs);
+	kfree(kaddrs);
 
 	return err;
 }
-- 
2.20.1


From 0e2dea7a8eaf347c982aef8d4f987a0322a562fe Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 19 Mar 2019 05:45:35 -0700
Subject: [PATCH 19/29] tcp: do not use ipv6 header for ipv4 flow

[ Upstream commit 89e4130939a20304f4059ab72179da81f5347528 ]

When a dual stack tcp listener accepts an ipv4 flow,
it should not attempt to use an ipv6 header or tcp_v6_iif() helper.

Fixes: 1397ed35f22d ("ipv6: add flowinfo for tcp6 pkt_options for all cases")
Fixes: df3687ffc665 ("ipv6: add the IPV6_FL_F_REFLECT flag to IPV6_FL_A_GET")
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/tcp_ipv6.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 03e6b7a2bc53..e7cdfa92c382 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1108,11 +1108,11 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 		newnp->ipv6_fl_list = NULL;
 		newnp->pktoptions  = NULL;
 		newnp->opt	   = NULL;
-		newnp->mcast_oif   = tcp_v6_iif(skb);
-		newnp->mcast_hops  = ipv6_hdr(skb)->hop_limit;
-		newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb));
+		newnp->mcast_oif   = inet_iif(skb);
+		newnp->mcast_hops  = ip_hdr(skb)->ttl;
+		newnp->rcv_flowinfo = 0;
 		if (np->repflow)
-			newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb));
+			newnp->flow_label = 0;
 
 		/*
 		 * No need to charge this sock to the relevant IPv6 refcnt debug socks count
-- 
2.20.1


From d1b149fb136d995da0ada7cea073c28a23a05896 Mon Sep 17 00:00:00 2001
From: Erik Hugne <erik.hugne@gmail.com>
Date: Sun, 17 Mar 2019 18:46:42 +0100
Subject: [PATCH 20/29] tipc: allow service ranges to be connect()'ed on
 RDM/DGRAM

[ Upstream commit ea239314fe42ace880bdd834256834679346c80e ]

We move the check that prevents connecting service ranges to after
the RDM/DGRAM check, and move address sanity control to a separate
function that also validates the service range.

Fixes: 23998835be98 ("tipc: improve address sanity check in tipc_connect()")
Signed-off-by: Erik Hugne <erik.hugne@gmail.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/socket.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 88c307ef1318..67a7b312a499 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2310,6 +2310,16 @@ static int tipc_wait_for_connect(struct socket *sock, long *timeo_p)
 	return 0;
 }
 
+static bool tipc_sockaddr_is_sane(struct sockaddr_tipc *addr)
+{
+	if (addr->family != AF_TIPC)
+		return false;
+	if (addr->addrtype == TIPC_SERVICE_RANGE)
+		return (addr->addr.nameseq.lower <= addr->addr.nameseq.upper);
+	return (addr->addrtype == TIPC_SERVICE_ADDR ||
+		addr->addrtype == TIPC_SOCKET_ADDR);
+}
+
 /**
  * tipc_connect - establish a connection to another TIPC port
  * @sock: socket structure
@@ -2345,18 +2355,18 @@ static int tipc_connect(struct socket *sock, struct sockaddr *dest,
 		if (!tipc_sk_type_connectionless(sk))
 			res = -EINVAL;
 		goto exit;
-	} else if (dst->family != AF_TIPC) {
-		res = -EINVAL;
 	}
-	if (dst->addrtype != TIPC_ADDR_ID && dst->addrtype != TIPC_ADDR_NAME)
+	if (!tipc_sockaddr_is_sane(dst)) {
 		res = -EINVAL;
-	if (res)
 		goto exit;
-
+	}
 	/* DGRAM/RDM connect(), just save the destaddr */
 	if (tipc_sk_type_connectionless(sk)) {
 		memcpy(&tsk->peer, dest, destlen);
 		goto exit;
+	} else if (dst->addrtype == TIPC_SERVICE_RANGE) {
+		res = -EINVAL;
+		goto exit;
 	}
 
 	previous = sk->sk_state;
-- 
2.20.1


From a779f11093132b455ca1c6eb8a26ecd658ed7601 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 24 Mar 2019 00:48:22 +0800
Subject: [PATCH 21/29] tipc: change to check tipc_own_id to return in
 tipc_net_stop

[ Upstream commit 9926cb5f8b0f0aea535735185600d74db7608550 ]

When running a syz script, a panic occurred:

[  156.088228] BUG: KASAN: use-after-free in tipc_disc_timeout+0x9c9/0xb20 [tipc]
[  156.094315] Call Trace:
[  156.094844]  <IRQ>
[  156.095306]  dump_stack+0x7c/0xc0
[  156.097346]  print_address_description+0x65/0x22e
[  156.100445]  kasan_report.cold.3+0x37/0x7a
[  156.102402]  tipc_disc_timeout+0x9c9/0xb20 [tipc]
[  156.106517]  call_timer_fn+0x19a/0x610
[  156.112749]  run_timer_softirq+0xb51/0x1090

It was caused by the netns freed without deleting the discoverer timer,
while later on the netns would be accessed in the timer handler.

The timer should have been deleted by tipc_net_stop() when cleaning up a
netns. However, tipc has been able to enable a bearer and start d->timer
without the local node_addr set since Commit 52dfae5c85a4 ("tipc: obtain
node identity from interface by default"), which caused the timer not to
be deleted in tipc_net_stop() then.

So fix it in tipc_net_stop() by changing to check local node_id instead
of local node_addr, as Jon suggested.

While at it, remove the calling of tipc_nametbl_withdraw() there, since
tipc_nametbl_stop() will take of the nametbl's freeing after.

Fixes: 52dfae5c85a4 ("tipc: obtain node identity from interface by default")
Reported-by: syzbot+a25307ad099309f1c2b9@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/net.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/net/tipc/net.c b/net/tipc/net.c
index f076edb74338..7ce1e86b024f 100644
--- a/net/tipc/net.c
+++ b/net/tipc/net.c
@@ -163,12 +163,9 @@ void tipc_sched_net_finalize(struct net *net, u32 addr)
 
 void tipc_net_stop(struct net *net)
 {
-	u32 self = tipc_own_addr(net);
-
-	if (!self)
+	if (!tipc_own_id(net))
 		return;
 
-	tipc_nametbl_withdraw(net, TIPC_CFG_SRV, self, self, self);
 	rtnl_lock();
 	tipc_bearer_stop(net);
 	tipc_node_stop(net);
-- 
2.20.1


From 8d8c97d53f2a0251ef7a04566bea688d73b7ddd3 Mon Sep 17 00:00:00 2001
From: Erik Hugne <erik.hugne@gmail.com>
Date: Thu, 21 Mar 2019 09:11:59 +0100
Subject: [PATCH 22/29] tipc: fix cancellation of topology subscriptions

[ Upstream commit 33872d79f5d1cbedaaab79669cc38f16097a9450 ]

When cancelling a subscription, we have to clear the cancel bit in the
request before iterating over any established subscriptions with memcmp.
Otherwise no subscription will ever be found, and it will not be
possible to explicitly unsubscribe individual subscriptions.

Fixes: 8985ecc7c1e0 ("tipc: simplify endianness handling in topology subscriber")
Signed-off-by: Erik Hugne <erik.hugne@gmail.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/topsrv.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c
index d65eed88c495..2301b09df234 100644
--- a/net/tipc/topsrv.c
+++ b/net/tipc/topsrv.c
@@ -371,6 +371,7 @@ static int tipc_conn_rcv_sub(struct tipc_topsrv *srv,
 	struct tipc_subscription *sub;
 
 	if (tipc_sub_read(s, filter) & TIPC_SUB_CANCEL) {
+		s->filter &= __constant_ntohl(~TIPC_SUB_CANCEL);
 		tipc_conn_delete_sub(con, s);
 		return 0;
 	}
-- 
2.20.1


From 0c43f859d02873c9458a43bd3c3c9934d6fc7fad Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 14 Mar 2019 20:19:47 -0700
Subject: [PATCH 23/29] tun: properly test for IFF_UP

[ Upstream commit 4477138fa0ae4e1b699786ef0600863ea6e6c61c ]

Same reasons than the ones explained in commit 4179cb5a4c92
("vxlan: test dev->flags & IFF_UP before calling netif_rx()")

netif_rx_ni() or napi_gro_frags() must be called under a strict contract.

At device dismantle phase, core networking clears IFF_UP
and flush_all_backlogs() is called after rcu grace period
to make sure no incoming packet might be in a cpu backlog
and still referencing the device.

A similar protocol is used for gro layer.

Most drivers call netif_rx() from their interrupt handler,
and since the interrupts are disabled at device dismantle,
netif_rx() does not have to check dev->flags & IFF_UP

Virtual drivers do not have this guarantee, and must
therefore make the check themselves.

Fixes: 1bd4978a88ac ("tun: honor IFF_UP in tun_get_user()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index f3293355c784..76dd8580e287 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1718,9 +1718,6 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	int skb_xdp = 1;
 	bool frags = tun_napi_frags_enabled(tfile);
 
-	if (!(tun->dev->flags & IFF_UP))
-		return -EIO;
-
 	if (!(tun->flags & IFF_NO_PI)) {
 		if (len < sizeof(pi))
 			return -EINVAL;
@@ -1822,6 +1819,8 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 			err = skb_copy_datagram_from_iter(skb, 0, from, len);
 
 		if (err) {
+			err = -EFAULT;
+drop:
 			this_cpu_inc(tun->pcpu_stats->rx_dropped);
 			kfree_skb(skb);
 			if (frags) {
@@ -1829,7 +1828,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 				mutex_unlock(&tfile->napi_mutex);
 			}
 
-			return -EFAULT;
+			return err;
 		}
 	}
 
@@ -1913,6 +1912,12 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	    !tfile->detached)
 		rxhash = __skb_get_hash_symmetric(skb);
 
+	rcu_read_lock();
+	if (unlikely(!(tun->dev->flags & IFF_UP))) {
+		err = -EIO;
+		goto drop;
+	}
+
 	if (frags) {
 		/* Exercise flow dissector code path. */
 		u32 headlen = eth_get_headlen(skb->data, skb_headlen(skb));
@@ -1920,6 +1925,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 		if (unlikely(headlen > skb_headlen(skb))) {
 			this_cpu_inc(tun->pcpu_stats->rx_dropped);
 			napi_free_frags(&tfile->napi);
+			rcu_read_unlock();
 			mutex_unlock(&tfile->napi_mutex);
 			WARN_ON(1);
 			return -ENOMEM;
@@ -1947,6 +1953,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	} else {
 		netif_rx_ni(skb);
 	}
+	rcu_read_unlock();
 
 	stats = get_cpu_ptr(tun->pcpu_stats);
 	u64_stats_update_begin(&stats->syncp);
-- 
2.20.1


From 776fe121c30084ba10809f5609a8e8d8b13ea690 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 26 Mar 2019 18:22:16 +0100
Subject: [PATCH 24/29] vrf: prevent adding upper devices

[ Upstream commit 1017e0987117c32783ba7c10fe2e7ff1456ba1dc ]

VRF devices don't work with upper devices. Currently, it's possible to
add a VRF device to a bridge or team, and to create macvlan, macsec, or
ipvlan devices on top of a VRF (bond and vlan are prevented respectively
by the lack of an ndo_set_mac_address op and the NETIF_F_VLAN_CHALLENGED
feature flag).

Fix this by setting the IFF_NO_RX_HANDLER flag (introduced in commit
f5426250a6ec ("net: introduce IFF_NO_RX_HANDLER")).

Cc: David Ahern <dsahern@gmail.com>
Fixes: 193125dbd8eb ("net: Introduce VRF device driver")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index f93547f257fb..449fc52f9a89 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -1262,6 +1262,7 @@ static void vrf_setup(struct net_device *dev)
 
 	/* default to no qdisc; user can add if desired */
 	dev->priv_flags |= IFF_NO_QUEUE;
+	dev->priv_flags |= IFF_NO_RX_HANDLER;
 }
 
 static int vrf_validate(struct nlattr *tb[], struct nlattr *data[],
-- 
2.20.1


From 66092a69b20b750418e8a9b309fda76b2837b665 Mon Sep 17 00:00:00 2001
From: Zhiqiang Liu <liuzhiqiang26@huawei.com>
Date: Sat, 16 Mar 2019 17:02:54 +0800
Subject: [PATCH 25/29] vxlan: Don't call gro_cells_destroy() before device is
 unregistered

[ Upstream commit cc4807bb609230d8959fd732b0bf3bd4c2de8eac ]

Commit ad6c9986bcb62 ("vxlan: Fix GRO cells race condition between
receive and link delete") fixed a race condition for the typical case a vxlan
device is dismantled from the current netns. But if a netns is dismantled,
vxlan_destroy_tunnels() is called to schedule a unregister_netdevice_queue()
of all the vxlan tunnels that are related to this netns.

In vxlan_destroy_tunnels(), gro_cells_destroy() is called and finished before
unregister_netdevice_queue(). This means that the gro_cells_destroy() call is
done too soon, for the same reasons explained in above commit.

So we need to fully respect the RCU rules, and thus must remove the
gro_cells_destroy() call or risk use after-free.

Fixes: 58ce31cca1ff ("vxlan: GRO support at tunnel layer")
Signed-off-by: Suanming.Mou <mousuanming@huawei.com>
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Zhiqiang Liu <liuzhiqiang26@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 52387f7f12ed..0b1ec44acbf9 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -3798,10 +3798,8 @@ static void vxlan_destroy_tunnels(struct net *net, struct list_head *head)
 		/* If vxlan->dev is in the same netns, it has already been added
 		 * to the list by the previous loop.
 		 */
-		if (!net_eq(dev_net(vxlan->dev), net)) {
-			gro_cells_destroy(&vxlan->gro_cells);
+		if (!net_eq(dev_net(vxlan->dev), net))
 			unregister_netdevice_queue(vxlan->dev, head);
-		}
 	}
 
 	for (h = 0; h < PORT_HASH_SIZE; ++h)
-- 
2.20.1


From 38b34790033b1800f76dbc8e8c10b6e152a6db5d Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Tue, 26 Mar 2019 13:50:14 +0800
Subject: [PATCH 26/29] ila: Fix rhashtable walker list corruption

[ Upstream commit b5f9bd15b88563b55a99ed588416881367a0ce5f ]

ila_xlat_nl_cmd_flush uses rhashtable walkers allocated from the
stack but it never frees them.  This corrupts the walker list of
the hash table.

This patch fixes it.

Reported-by: syzbot+dae72a112334aa65a159@syzkaller.appspotmail.com
Fixes: b6e71bdebb12 ("ila: Flush netlink command to clear xlat...")
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ila/ila_xlat.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c
index 17c455ff69ff..7858fa9ea103 100644
--- a/net/ipv6/ila/ila_xlat.c
+++ b/net/ipv6/ila/ila_xlat.c
@@ -420,6 +420,7 @@ int ila_xlat_nl_cmd_flush(struct sk_buff *skb, struct genl_info *info)
 
 done:
 	rhashtable_walk_stop(&iter);
+	rhashtable_walk_exit(&iter);
 	return ret;
 }
 
-- 
2.20.1


From 78f0769132575a14fb0d1f6f78fd843830c96fb3 Mon Sep 17 00:00:00 2001
From: John Hurley <john.hurley@netronome.com>
Date: Fri, 22 Mar 2019 12:37:35 +0000
Subject: [PATCH 27/29] net: sched: fix cleanup NULL pointer exception in
 act_mirr

[ Upstream commit 064c5d6881e897077639e04973de26440ee205e6 ]

A new mirred action is created by the tcf_mirred_init function. This
contains a list head struct which is inserted into a global list on
successful creation of a new action. However, after a creation, it is
still possible to error out and call the tcf_idr_release function. This,
in turn, calls the act_mirr cleanup function via __tcf_idr_release and
__tcf_action_put. This cleanup function tries to delete the list entry
which is as yet uninitialised, leading to a NULL pointer exception.

Fix this by initialising the list entry on creation of a new action.

Bug report:

BUG: unable to handle kernel NULL pointer dereference at 0000000000000008
PGD 8000000840c73067 P4D 8000000840c73067 PUD 858dcc067 PMD 0
Oops: 0002 [#1] SMP PTI
CPU: 32 PID: 5636 Comm: handler194 Tainted: G           OE     5.0.0+ #186
Hardware name: Dell Inc. PowerEdge R730/0599V5, BIOS 1.3.6 06/03/2015
RIP: 0010:tcf_mirred_release+0x42/0xa7 [act_mirred]
Code: f0 90 39 c0 e8 52 04 57 c8 48 c7 c7 b8 80 39 c0 e8 94 fa d4 c7 48 8b 93 d0 00 00 00 48 8b 83 d8 00 00 00 48 c7 c7 f0 90 39 c0 <48> 89 42 08 48 89 10 48 b8 00 01 00 00 00 00 ad de 48 89 83 d0 00
RSP: 0018:ffffac4aa059f688 EFLAGS: 00010282
RAX: 0000000000000000 RBX: ffff9dcd1b214d00 RCX: 0000000000000000
RDX: 0000000000000000 RSI: ffff9dcd1fa165f8 RDI: ffffffffc03990f0
RBP: ffff9dccf9c7af80 R08: 0000000000000a3b R09: 0000000000000000
R10: ffff9dccfa11f420 R11: 0000000000000000 R12: 0000000000000001
R13: ffff9dcd16b433c0 R14: ffff9dcd1b214d80 R15: 0000000000000000
FS:  00007f441bfff700(0000) GS:ffff9dcd1fa00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000008 CR3: 0000000839e64004 CR4: 00000000001606e0
Call Trace:
tcf_action_cleanup+0x59/0xca
__tcf_action_put+0x54/0x6b
__tcf_idr_release.cold.33+0x9/0x12
tcf_mirred_init.cold.20+0x22e/0x3b0 [act_mirred]
tcf_action_init_1+0x3d0/0x4c0
tcf_action_init+0x9c/0x130
tcf_exts_validate+0xab/0xc0
fl_change+0x1ca/0x982 [cls_flower]
tc_new_tfilter+0x647/0x8d0
? load_balance+0x14b/0x9e0
rtnetlink_rcv_msg+0xe3/0x370
? __switch_to_asm+0x40/0x70
? __switch_to_asm+0x34/0x70
? _cond_resched+0x15/0x30
? __kmalloc_node_track_caller+0x1d4/0x2b0
? rtnl_calcit.isra.31+0xf0/0xf0
netlink_rcv_skb+0x49/0x110
netlink_unicast+0x16f/0x210
netlink_sendmsg+0x1df/0x390
sock_sendmsg+0x36/0x40
___sys_sendmsg+0x27b/0x2c0
? futex_wake+0x80/0x140
? do_futex+0x2b9/0xac0
? ep_scan_ready_list.constprop.22+0x1f2/0x210
? ep_poll+0x7a/0x430
__sys_sendmsg+0x47/0x80
do_syscall_64+0x55/0x100
entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 4e232818bd32 ("net: sched: act_mirred: remove dependency on rtnl lock")
Signed-off-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_mirred.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 8bf66d0a6800..f767e78e38c9 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -159,6 +159,9 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 	}
 	m = to_mirred(*a);
 
+	if (ret == ACT_P_CREATED)
+		INIT_LIST_HEAD(&m->tcfm_list);
+
 	spin_lock_bh(&m->tcf_lock);
 	m->tcf_action = parm->action;
 	m->tcfm_eaction = parm->eaction;
-- 
2.20.1


From f4a95491ea3126f00c567440a3583217c20fd64d Mon Sep 17 00:00:00 2001
From: Dean Nelson <dnelson@redhat.com>
Date: Tue, 26 Mar 2019 11:53:19 -0400
Subject: [PATCH 28/29] thunderx: enable page recycling for non-XDP case

[ Upstream commit b3e208069477588c06f4d5d986164b435bb06e6d ]

Commit 773225388dae15e72790 ("net: thunderx: Optimize page recycling for XDP")
added code to nicvf_alloc_page() that inadvertently disables receive buffer
page recycling for the non-XDP case by always NULL'ng the page pointer.

This patch corrects two if-conditionals to allow for the recycling of non-XDP
mode pages by only setting the page pointer to NULL when the page is not ready
for recycling.

Fixes: 773225388dae ("net: thunderx: Optimize page recycling for XDP")
Signed-off-by: Dean Nelson <dnelson@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/cavium/thunder/nicvf_queues.c    | 23 +++++++++----------
 1 file changed, 11 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index fcaf18fa3904..ade1ff355836 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -105,20 +105,19 @@ static inline struct pgcache *nicvf_alloc_page(struct nicvf *nic,
 	/* Check if page can be recycled */
 	if (page) {
 		ref_count = page_ref_count(page);
-		/* Check if this page has been used once i.e 'put_page'
-		 * called after packet transmission i.e internal ref_count
-		 * and page's ref_count are equal i.e page can be recycled.
+		/* This page can be recycled if internal ref_count and page's
+		 * ref_count are equal, indicating that the page has been used
+		 * once for packet transmission. For non-XDP mode, internal
+		 * ref_count is always '1'.
 		 */
-		if (rbdr->is_xdp && (ref_count == pgcache->ref_count))
-			pgcache->ref_count--;
-		else
-			page = NULL;
-
-		/* In non-XDP mode, page's ref_count needs to be '1' for it
-		 * to be recycled.
-		 */
-		if (!rbdr->is_xdp && (ref_count != 1))
+		if (rbdr->is_xdp) {
+			if (ref_count == pgcache->ref_count)
+				pgcache->ref_count--;
+			else
+				page = NULL;
+		} else if (ref_count != 1) {
 			page = NULL;
+		}
 	}
 
 	if (!page) {
-- 
2.20.1


From 67d7697fee909a8b1b5d3d68787dc2bf6dc883af Mon Sep 17 00:00:00 2001
From: Dean Nelson <dnelson@redhat.com>
Date: Tue, 26 Mar 2019 11:53:26 -0400
Subject: [PATCH 29/29] thunderx: eliminate extra calls to put_page() for pages
 held for recycling

[ Upstream commit cd35ef91490ad8049dd180bb060aff7ee192eda9 ]

For the non-XDP case, commit 773225388dae15e72790 ("net: thunderx: Optimize
page recycling for XDP") added code to nicvf_free_rbdr() that, when releasing
the additional receive buffer page reference held for recycling, repeatedly
calls put_page() until the page's _refcount goes to zero. Which results in
the page being freed.

This is not okay if the page's _refcount was greater than 1 (in the non-XDP
case), because nicvf_free_rbdr() should not be subtracting more than what
nicvf_alloc_page() had previously added to the page's _refcount, which was
only 1 (in the non-XDP case).

This can arise if a received packet is still being processed and the receive
buffer (i.e., skb->head) has not yet been freed via skb_free_head() when
nicvf_free_rbdr() is spinning through the aforementioned put_page() loop.

If this should occur, when the received packet finishes processing and
skb_free_head() is called, various problems can ensue. Exactly what, depends on
whether the page has already been reallocated or not, anything from "BUG: Bad
page state ... ", to "Unable to handle kernel NULL pointer dereference ..." or
"Unable to handle kernel paging request...".

So this patch changes nicvf_free_rbdr() to only call put_page() once for pages
held for recycling (in the non-XDP case).

Fixes: 773225388dae ("net: thunderx: Optimize page recycling for XDP")
Signed-off-by: Dean Nelson <dnelson@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/thunder/nicvf_queues.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index ade1ff355836..9a4cfa61ed93 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -364,11 +364,10 @@ static void nicvf_free_rbdr(struct nicvf *nic, struct rbdr *rbdr)
 	while (head < rbdr->pgcnt) {
 		pgcache = &rbdr->pgcache[head];
 		if (pgcache->page && page_ref_count(pgcache->page) != 0) {
-			if (!rbdr->is_xdp) {
-				put_page(pgcache->page);
-				continue;
+			if (rbdr->is_xdp) {
+				page_ref_sub(pgcache->page,
+					     pgcache->ref_count - 1);
 			}
-			page_ref_sub(pgcache->page, pgcache->ref_count - 1);
 			put_page(pgcache->page);
 		}
 		head++;
-- 
2.20.1


[-- Attachment #3: net_50.mbox --]
[-- Type: Application/Octet-Stream, Size: 71305 bytes --]

From cb02458becb72849d160557be961b665ab0a1510 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 19 Mar 2019 05:46:18 -0700
Subject: [PATCH 01/33] dccp: do not use ipv6 header for ipv4 flow

[ Upstream commit e0aa67709f89d08c8d8e5bdd9e0b649df61d0090 ]

When a dual stack dccp listener accepts an ipv4 flow,
it should not attempt to use an ipv6 header or
inet6_iif() helper.

Fixes: 3df80d9320bc ("[DCCP]: Introduce DCCPv6")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ipv6.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index d5740bad5b18..57d84e9b7b6f 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -436,8 +436,8 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk,
 		newnp->ipv6_mc_list = NULL;
 		newnp->ipv6_ac_list = NULL;
 		newnp->ipv6_fl_list = NULL;
-		newnp->mcast_oif   = inet6_iif(skb);
-		newnp->mcast_hops  = ipv6_hdr(skb)->hop_limit;
+		newnp->mcast_oif   = inet_iif(skb);
+		newnp->mcast_hops  = ip_hdr(skb)->ttl;
 
 		/*
 		 * No need to charge this sock to the relevant IPv6 refcnt debug socks count
-- 
2.20.1


From 8c96dd136b01d1f2762853f6cf7eed0b979a84cc Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Thu, 21 Mar 2019 15:02:50 +0800
Subject: [PATCH 02/33] genetlink: Fix a memory leak on error path

[ Upstream commit ceabee6c59943bdd5e1da1a6a20dc7ee5f8113a2 ]

In genl_register_family(), when idr_alloc() fails,
we forget to free the memory we possibly allocate for
family->attrbuf.

Reported-by: Hulk Robot <hulkci@huawei.com>
Fixes: 2ae0f17df1cd ("genetlink: use idr to track families")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Reviewed-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/genetlink.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 25eeb6d2a75a..f0ec068e1d02 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -366,7 +366,7 @@ int genl_register_family(struct genl_family *family)
 			       start, end + 1, GFP_KERNEL);
 	if (family->id < 0) {
 		err = family->id;
-		goto errout_locked;
+		goto errout_free;
 	}
 
 	err = genl_validate_assign_mc_groups(family);
@@ -385,6 +385,7 @@ int genl_register_family(struct genl_family *family)
 
 errout_remove:
 	idr_remove(&genl_fam_idr, family->id);
+errout_free:
 	kfree(family->attrbuf);
 errout_locked:
 	genl_unlock_all();
-- 
2.20.1


From 8b664a61474f18ea1b927b04f107d7dfa33bfa36 Mon Sep 17 00:00:00 2001
From: Matteo Croce <mcroce@redhat.com>
Date: Sat, 16 Mar 2019 01:00:50 +0100
Subject: [PATCH 03/33] gtp: change NET_UDP_TUNNEL dependency to select

[ Upstream commit c22da36688d6298f2e546dcc43fdc1ad35036467 ]

Similarly to commit a7603ac1fc8c ("geneve: change NET_UDP_TUNNEL
dependency to select"), GTP has a dependency on NET_UDP_TUNNEL which
makes impossible to compile it if no other protocol depending on
NET_UDP_TUNNEL is selected.

Fix this by changing the depends to a select, and drop NET_IP_TUNNEL from
the select list, as it already depends on NET_UDP_TUNNEL.

Signed-off-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/Kconfig | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 21bf8ac78380..390e896dadc7 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -213,8 +213,8 @@ config GENEVE
 
 config GTP
 	tristate "GPRS Tunneling Protocol datapath (GTP-U)"
-	depends on INET && NET_UDP_TUNNEL
-	select NET_IP_TUNNEL
+	depends on INET
+	select NET_UDP_TUNNEL
 	---help---
 	  This allows one to create gtp virtual interfaces that provide
 	  the GPRS Tunneling Protocol datapath (GTP-U). This tunneling protocol
-- 
2.20.1


From 7a2f116160a3c6df51a31485afd0df886f227c0d Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 20 Mar 2019 14:45:48 +0800
Subject: [PATCH 04/33] ipv6: make ip6_create_rt_rcu return ip6_null_entry
 instead of NULL

[ Upstream commit 1c87e79a002f6a159396138cd3f3ab554a2a8887 ]

Jianlin reported a crash:

  [  381.484332] BUG: unable to handle kernel NULL pointer dereference at 0000000000000068
  [  381.619802] RIP: 0010:fib6_rule_lookup+0xa3/0x160
  [  382.009615] Call Trace:
  [  382.020762]  <IRQ>
  [  382.030174]  ip6_route_redirect.isra.52+0xc9/0xf0
  [  382.050984]  ip6_redirect+0xb6/0xf0
  [  382.066731]  icmpv6_notify+0xca/0x190
  [  382.083185]  ndisc_redirect_rcv+0x10f/0x160
  [  382.102569]  ndisc_rcv+0xfb/0x100
  [  382.117725]  icmpv6_rcv+0x3f2/0x520
  [  382.133637]  ip6_input_finish+0xbf/0x460
  [  382.151634]  ip6_input+0x3b/0xb0
  [  382.166097]  ipv6_rcv+0x378/0x4e0

It was caused by the lookup function __ip6_route_redirect() returns NULL in
fib6_rule_lookup() when ip6_create_rt_rcu() returns NULL.

So we fix it by simply making ip6_create_rt_rcu() return ip6_null_entry
instead of NULL.

v1->v2:
  - move down 'fallback:' to make it more readable.

Fixes: e873e4b9cc7e ("ipv6: use fib6_info_hold_safe() when necessary")
Reported-by: Jianlin Shi <jishi@redhat.com>
Suggested-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Acked-by: Wei Wang <weiwan@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 8dad1d690b78..0086acc16f3c 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1040,14 +1040,20 @@ static struct rt6_info *ip6_create_rt_rcu(struct fib6_info *rt)
 	struct rt6_info *nrt;
 
 	if (!fib6_info_hold_safe(rt))
-		return NULL;
+		goto fallback;
 
 	nrt = ip6_dst_alloc(dev_net(dev), dev, flags);
-	if (nrt)
-		ip6_rt_copy_init(nrt, rt);
-	else
+	if (!nrt) {
 		fib6_info_release(rt);
+		goto fallback;
+	}
 
+	ip6_rt_copy_init(nrt, rt);
+	return nrt;
+
+fallback:
+	nrt = dev_net(dev)->ipv6.ip6_null_entry;
+	dst_hold(&nrt->dst);
 	return nrt;
 }
 
@@ -1096,10 +1102,6 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net,
 		dst_hold(&rt->dst);
 	} else {
 		rt = ip6_create_rt_rcu(f6i);
-		if (!rt) {
-			rt = net->ipv6.ip6_null_entry;
-			dst_hold(&rt->dst);
-		}
 	}
 
 	rcu_read_unlock();
-- 
2.20.1


From fcbbea8dd7768f948171a3707d60a5c35d5f28a4 Mon Sep 17 00:00:00 2001
From: Finn Thain <fthain@telegraphics.com.au>
Date: Sat, 16 Mar 2019 14:21:19 +1100
Subject: [PATCH 05/33] mac8390: Fix mmio access size probe

[ Upstream commit bb9e5c5bcd76f4474eac3baf643d7a39f7bac7bb ]

The bug that Stan reported is as follows. After a restart, a 16-bit NIC
may be incorrectly identified as a 32-bit NIC and stop working.

mac8390 slot.E: Memory length resource not found, probing
mac8390 slot.E: Farallon EtherMac II-C (type farallon)
mac8390 slot.E: MAC 00:00:c5:30:c2:99, IRQ 61, 32 KB shared memory at 0xfeed0000, 32-bit access.

The bug never arises after a cold start and only intermittently after a
warm start. (I didn't investigate why the bug is intermittent.)

It turns out that memcpy_toio() is deprecated and memcmp_withio() also
has issues. Replacing these calls with mmio accessors fixes the problem.

Reported-and-tested-by: Stan Johnson <userm57@yahoo.com>
Fixes: 2964db0f5904 ("m68k: Mac DP8390 update")
Signed-off-by: Finn Thain <fthain@telegraphics.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/8390/mac8390.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/8390/mac8390.c b/drivers/net/ethernet/8390/mac8390.c
index 342ae08ec3c2..d60a86aa8aa8 100644
--- a/drivers/net/ethernet/8390/mac8390.c
+++ b/drivers/net/ethernet/8390/mac8390.c
@@ -153,8 +153,6 @@ static void dayna_block_input(struct net_device *dev, int count,
 static void dayna_block_output(struct net_device *dev, int count,
 			       const unsigned char *buf, int start_page);
 
-#define memcmp_withio(a, b, c)	memcmp((a), (void *)(b), (c))
-
 /* Slow Sane (16-bit chunk memory read/write) Cabletron uses this */
 static void slow_sane_get_8390_hdr(struct net_device *dev,
 				   struct e8390_pkt_hdr *hdr, int ring_page);
@@ -233,19 +231,26 @@ static enum mac8390_type mac8390_ident(struct nubus_rsrc *fres)
 
 static enum mac8390_access mac8390_testio(unsigned long membase)
 {
-	unsigned long outdata = 0xA5A0B5B0;
-	unsigned long indata =  0x00000000;
+	u32 outdata = 0xA5A0B5B0;
+	u32 indata = 0;
+
 	/* Try writing 32 bits */
-	memcpy_toio((void __iomem *)membase, &outdata, 4);
-	/* Now compare them */
-	if (memcmp_withio(&outdata, membase, 4) == 0)
+	nubus_writel(outdata, membase);
+	/* Now read it back */
+	indata = nubus_readl(membase);
+	if (outdata == indata)
 		return ACCESS_32;
+
+	outdata = 0xC5C0D5D0;
+	indata = 0;
+
 	/* Write 16 bit output */
 	word_memcpy_tocard(membase, &outdata, 4);
 	/* Now read it back */
 	word_memcpy_fromcard(&indata, membase, 4);
 	if (outdata == indata)
 		return ACCESS_16;
+
 	return ACCESS_UNKNOWN;
 }
 
-- 
2.20.1


From f08e7e54ea88997c17cd955e563bcdcfe7495b40 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Mon, 18 Mar 2019 08:51:06 -0500
Subject: [PATCH 06/33] mISDN: hfcpci: Test both vendor & device ID for Digium
 HFC4S

[ Upstream commit fae846e2b7124d4b076ef17791c73addf3b26350 ]

The device ID alone does not uniquely identify a device.  Test both the
vendor and device ID to make sure we don't mistakenly think some other
vendor's 0xB410 device is a Digium HFC4S.  Also, instead of the bare hex
ID, use the same constant (PCI_DEVICE_ID_DIGIUM_HFC4S) used in the device
ID table.

No functional change intended.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/hardware/mISDN/hfcmulti.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/isdn/hardware/mISDN/hfcmulti.c b/drivers/isdn/hardware/mISDN/hfcmulti.c
index 4d85645c87f7..0928fd1f0e0c 100644
--- a/drivers/isdn/hardware/mISDN/hfcmulti.c
+++ b/drivers/isdn/hardware/mISDN/hfcmulti.c
@@ -4365,7 +4365,8 @@ setup_pci(struct hfc_multi *hc, struct pci_dev *pdev,
 	if (m->clock2)
 		test_and_set_bit(HFC_CHIP_CLOCK2, &hc->chip);
 
-	if (ent->device == 0xB410) {
+	if (ent->vendor == PCI_VENDOR_ID_DIGIUM &&
+	    ent->device == PCI_DEVICE_ID_DIGIUM_HFC4S) {
 		test_and_set_bit(HFC_CHIP_B410P, &hc->chip);
 		test_and_set_bit(HFC_CHIP_PCM_MASTER, &hc->chip);
 		test_and_clear_bit(HFC_CHIP_PCM_SLAVE, &hc->chip);
-- 
2.20.1


From 7b4683ac08743d8f07671db6f3ddc4ee9961edee Mon Sep 17 00:00:00 2001
From: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Date: Sat, 16 Mar 2019 08:28:18 +0000
Subject: [PATCH 07/33] net: aquantia: fix rx checksum offload for UDP/TCP over
 IPv6

[ Upstream commit a7faaa0c5dc7d091cc9f72b870d7edcdd6f43f12 ]

TCP/UDP checksum validity was propagated to skb
only if IP checksum is valid.
But for IPv6 there is no validity as there is no checksum in IPv6.
This patch propagates TCP/UDP checksum validity regardless of IP checksum.

Fixes: 018423e90bee ("net: ethernet: aquantia: Add ring support code")
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: Nikita Danilov <nikita.danilov@aquantia.com>
Signed-off-by: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/aq_ring.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index 74550ccc7a20..e2ffb159cbe2 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -186,11 +186,12 @@ static void aq_rx_checksum(struct aq_ring_s *self,
 	}
 	if (buff->is_ip_cso) {
 		__skb_incr_checksum_unnecessary(skb);
-		if (buff->is_udp_cso || buff->is_tcp_cso)
-			__skb_incr_checksum_unnecessary(skb);
 	} else {
 		skb->ip_summed = CHECKSUM_NONE;
 	}
+
+	if (buff->is_udp_cso || buff->is_tcp_cso)
+		__skb_incr_checksum_unnecessary(skb);
 }
 
 #define AQ_SKB_ALIGN SKB_DATA_ALIGN(sizeof(struct skb_shared_info))
-- 
2.20.1


From 45fbae0b787c3face46d9f66d4023cf6900dfec9 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 25 Mar 2019 14:18:06 +0100
Subject: [PATCH 08/33] net: datagram: fix unbounded loop in
 __skb_try_recv_datagram()

[ Upstream commit 0b91bce1ebfc797ff3de60c8f4a1e6219a8a3187 ]

Christoph reported a stall while peeking datagram with an offset when
busy polling is enabled. __skb_try_recv_datagram() uses as the loop
termination condition 'queue empty'. When peeking, the socket
queue can be not empty, even when no additional packets are received.

Address the issue explicitly checking for receive queue changes,
as currently done by __skb_wait_for_more_packets().

Fixes: 2b5cd0dfa384 ("net: Change return type of sk_busy_loop from bool to void")
Reported-and-tested-by: Christoph Paasch <cpaasch@apple.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/datagram.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/datagram.c b/net/core/datagram.c
index b2651bb6d2a3..e657289db4ac 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -279,7 +279,7 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags,
 			break;
 
 		sk_busy_loop(sk, flags & MSG_DONTWAIT);
-	} while (!skb_queue_empty(&sk->sk_receive_queue));
+	} while (sk->sk_receive_queue.prev != *last);
 
 	error = -EAGAIN;
 
-- 
2.20.1


From 956bca774ac79ce23673f5216759b963402bd37d Mon Sep 17 00:00:00 2001
From: Christoph Paasch <cpaasch@apple.com>
Date: Mon, 18 Mar 2019 23:14:52 -0700
Subject: [PATCH 09/33] net/packet: Set __GFP_NOWARN upon allocation in
 alloc_pg_vec

[ Upstream commit 398f0132c14754fcd03c1c4f8e7176d001ce8ea1 ]

Since commit fc62814d690c ("net/packet: fix 4gb buffer limit due to overflow check")
one can now allocate packet ring buffers >= UINT_MAX. However, syzkaller
found that that triggers a warning:

[   21.100000] WARNING: CPU: 2 PID: 2075 at mm/page_alloc.c:4584 __alloc_pages_nod0
[   21.101490] Modules linked in:
[   21.101921] CPU: 2 PID: 2075 Comm: syz-executor.0 Not tainted 5.0.0 #146
[   21.102784] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 0.5.1 01/01/2011
[   21.103887] RIP: 0010:__alloc_pages_nodemask+0x2a0/0x630
[   21.104640] Code: fe ff ff 65 48 8b 04 25 c0 de 01 00 48 05 90 0f 00 00 41 bd 01 00 00 00 48 89 44 24 48 e9 9c fe 3
[   21.107121] RSP: 0018:ffff88805e1cf920 EFLAGS: 00010246
[   21.107819] RAX: 0000000000000000 RBX: ffffffff85a488a0 RCX: 0000000000000000
[   21.108753] RDX: 0000000000000000 RSI: dffffc0000000000 RDI: 0000000000000000
[   21.109699] RBP: 1ffff1100bc39f28 R08: ffffed100bcefb67 R09: ffffed100bcefb67
[   21.110646] R10: 0000000000000001 R11: ffffed100bcefb66 R12: 000000000000000d
[   21.111623] R13: 0000000000000000 R14: ffff88805e77d888 R15: 000000000000000d
[   21.112552] FS:  00007f7c7de05700(0000) GS:ffff88806d100000(0000) knlGS:0000000000000000
[   21.113612] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   21.114405] CR2: 000000000065c000 CR3: 000000005e58e006 CR4: 00000000001606e0
[   21.115367] Call Trace:
[   21.115705]  ? __alloc_pages_slowpath+0x21c0/0x21c0
[   21.116362]  alloc_pages_current+0xac/0x1e0
[   21.116923]  kmalloc_order+0x18/0x70
[   21.117393]  kmalloc_order_trace+0x18/0x110
[   21.117949]  packet_set_ring+0x9d5/0x1770
[   21.118524]  ? packet_rcv_spkt+0x440/0x440
[   21.119094]  ? lock_downgrade+0x620/0x620
[   21.119646]  ? __might_fault+0x177/0x1b0
[   21.120177]  packet_setsockopt+0x981/0x2940
[   21.120753]  ? __fget+0x2fb/0x4b0
[   21.121209]  ? packet_release+0xab0/0xab0
[   21.121740]  ? sock_has_perm+0x1cd/0x260
[   21.122297]  ? selinux_secmark_relabel_packet+0xd0/0xd0
[   21.123013]  ? __fget+0x324/0x4b0
[   21.123451]  ? selinux_netlbl_socket_setsockopt+0x101/0x320
[   21.124186]  ? selinux_netlbl_sock_rcv_skb+0x3a0/0x3a0
[   21.124908]  ? __lock_acquire+0x529/0x3200
[   21.125453]  ? selinux_socket_setsockopt+0x5d/0x70
[   21.126075]  ? __sys_setsockopt+0x131/0x210
[   21.126533]  ? packet_release+0xab0/0xab0
[   21.127004]  __sys_setsockopt+0x131/0x210
[   21.127449]  ? kernel_accept+0x2f0/0x2f0
[   21.127911]  ? ret_from_fork+0x8/0x50
[   21.128313]  ? do_raw_spin_lock+0x11b/0x280
[   21.128800]  __x64_sys_setsockopt+0xba/0x150
[   21.129271]  ? lockdep_hardirqs_on+0x37f/0x560
[   21.129769]  do_syscall_64+0x9f/0x450
[   21.130182]  entry_SYSCALL_64_after_hwframe+0x49/0xbe

We should allocate with __GFP_NOWARN to handle this.

Cc: Kal Conley <kal.conley@dectris.com>
Cc: Andrey Konovalov <andreyknvl@google.com>
Fixes: fc62814d690c ("net/packet: fix 4gb buffer limit due to overflow check")
Signed-off-by: Christoph Paasch <cpaasch@apple.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 1cd1d83a4be0..2784bfa1bc9b 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -4211,7 +4211,7 @@ static struct pgv *alloc_pg_vec(struct tpacket_req *req, int order)
 	struct pgv *pg_vec;
 	int i;
 
-	pg_vec = kcalloc(block_nr, sizeof(struct pgv), GFP_KERNEL);
+	pg_vec = kcalloc(block_nr, sizeof(struct pgv), GFP_KERNEL | __GFP_NOWARN);
 	if (unlikely(!pg_vec))
 		goto out;
 
-- 
2.20.1


From 680240a1a0b75bc911a72920bb1e47cd483b0755 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Thu, 14 Mar 2019 14:49:45 +0100
Subject: [PATCH 10/33] net: phy: meson-gxl: fix interrupt support

[ Upstream commit daa5c4d0167a308306525fd5ab9a5e18e21f4f74 ]

If an interrupt is already pending when the interrupt is enabled on the
GXL phy, no IRQ will ever be triggered.

The fix is simply to make sure pending IRQs are cleared before setting
up the irq mask.

Fixes: cf127ff20af1 ("net: phy: meson-gxl: add interrupt support")
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/meson-gxl.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/phy/meson-gxl.c b/drivers/net/phy/meson-gxl.c
index 3ddaf9595697..68af4c75ffb3 100644
--- a/drivers/net/phy/meson-gxl.c
+++ b/drivers/net/phy/meson-gxl.c
@@ -211,6 +211,7 @@ static int meson_gxl_ack_interrupt(struct phy_device *phydev)
 static int meson_gxl_config_intr(struct phy_device *phydev)
 {
 	u16 val;
+	int ret;
 
 	if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
 		val = INTSRC_ANEG_PR
@@ -223,6 +224,11 @@ static int meson_gxl_config_intr(struct phy_device *phydev)
 		val = 0;
 	}
 
+	/* Ack any pending IRQ */
+	ret = meson_gxl_ack_interrupt(phydev);
+	if (ret)
+		return ret;
+
 	return phy_write(phydev, INTSRC_MASK, val);
 }
 
-- 
2.20.1


From f66feaada5f0889802a56af97727d541bc171ca9 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 15 Mar 2019 10:41:14 -0700
Subject: [PATCH 11/33] net: rose: fix a possible stack overflow

[ Upstream commit e5dcc0c3223c45c94100f05f28d8ef814db3d82c ]

rose_write_internal() uses a temp buffer of 100 bytes, but a manual
inspection showed that given arbitrary input, rose_create_facilities()
can fill up to 110 bytes.

Lets use a tailroom of 256 bytes for peace of mind, and remove
the bounce buffer : we can simply allocate a big enough skb
and adjust its length as needed.

syzbot report :

BUG: KASAN: stack-out-of-bounds in memcpy include/linux/string.h:352 [inline]
BUG: KASAN: stack-out-of-bounds in rose_create_facilities net/rose/rose_subr.c:521 [inline]
BUG: KASAN: stack-out-of-bounds in rose_write_internal+0x597/0x15d0 net/rose/rose_subr.c:116
Write of size 7 at addr ffff88808b1ffbef by task syz-executor.0/24854

CPU: 0 PID: 24854 Comm: syz-executor.0 Not tainted 5.0.0+ #97
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 print_address_description.cold+0x7c/0x20d mm/kasan/report.c:187
 kasan_report.cold+0x1b/0x40 mm/kasan/report.c:317
 check_memory_region_inline mm/kasan/generic.c:185 [inline]
 check_memory_region+0x123/0x190 mm/kasan/generic.c:191
 memcpy+0x38/0x50 mm/kasan/common.c:131
 memcpy include/linux/string.h:352 [inline]
 rose_create_facilities net/rose/rose_subr.c:521 [inline]
 rose_write_internal+0x597/0x15d0 net/rose/rose_subr.c:116
 rose_connect+0x7cb/0x1510 net/rose/af_rose.c:826
 __sys_connect+0x266/0x330 net/socket.c:1685
 __do_sys_connect net/socket.c:1696 [inline]
 __se_sys_connect net/socket.c:1693 [inline]
 __x64_sys_connect+0x73/0xb0 net/socket.c:1693
 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x458079
Code: ad b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f47b8d9dc78 EFLAGS: 00000246 ORIG_RAX: 000000000000002a
RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000458079
RDX: 000000000000001c RSI: 0000000020000040 RDI: 0000000000000004
RBP: 000000000073bf00 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00007f47b8d9e6d4
R13: 00000000004be4a4 R14: 00000000004ceca8 R15: 00000000ffffffff

The buggy address belongs to the page:
page:ffffea00022c7fc0 count:0 mapcount:0 mapping:0000000000000000 index:0x0
flags: 0x1fffc0000000000()
raw: 01fffc0000000000 0000000000000000 ffffffff022c0101 0000000000000000
raw: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff88808b1ffa80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
 ffff88808b1ffb00: 00 00 00 00 00 00 00 00 f1 f1 f1 f1 00 00 00 03
>ffff88808b1ffb80: f2 f2 00 00 00 00 00 00 00 00 00 00 00 00 04 f3
                                                             ^
 ffff88808b1ffc00: f3 f3 f3 f3 00 00 00 00 00 00 00 00 00 00 00 00
 ffff88808b1ffc80: 00 00 00 00 00 00 00 f1 f1 f1 f1 f1 f1 01 f2 01

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rose/rose_subr.c | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/net/rose/rose_subr.c b/net/rose/rose_subr.c
index 7ca57741b2fb..7849f286bb93 100644
--- a/net/rose/rose_subr.c
+++ b/net/rose/rose_subr.c
@@ -105,16 +105,17 @@ void rose_write_internal(struct sock *sk, int frametype)
 	struct sk_buff *skb;
 	unsigned char  *dptr;
 	unsigned char  lci1, lci2;
-	char buffer[100];
-	int len, faclen = 0;
+	int maxfaclen = 0;
+	int len, faclen;
+	int reserve;
 
-	len = AX25_BPQ_HEADER_LEN + AX25_MAX_HEADER_LEN + ROSE_MIN_LEN + 1;
+	reserve = AX25_BPQ_HEADER_LEN + AX25_MAX_HEADER_LEN + 1;
+	len = ROSE_MIN_LEN;
 
 	switch (frametype) {
 	case ROSE_CALL_REQUEST:
 		len   += 1 + ROSE_ADDR_LEN + ROSE_ADDR_LEN;
-		faclen = rose_create_facilities(buffer, rose);
-		len   += faclen;
+		maxfaclen = 256;
 		break;
 	case ROSE_CALL_ACCEPTED:
 	case ROSE_CLEAR_REQUEST:
@@ -123,15 +124,16 @@ void rose_write_internal(struct sock *sk, int frametype)
 		break;
 	}
 
-	if ((skb = alloc_skb(len, GFP_ATOMIC)) == NULL)
+	skb = alloc_skb(reserve + len + maxfaclen, GFP_ATOMIC);
+	if (!skb)
 		return;
 
 	/*
 	 *	Space for AX.25 header and PID.
 	 */
-	skb_reserve(skb, AX25_BPQ_HEADER_LEN + AX25_MAX_HEADER_LEN + 1);
+	skb_reserve(skb, reserve);
 
-	dptr = skb_put(skb, skb_tailroom(skb));
+	dptr = skb_put(skb, len);
 
 	lci1 = (rose->lci >> 8) & 0x0F;
 	lci2 = (rose->lci >> 0) & 0xFF;
@@ -146,7 +148,8 @@ void rose_write_internal(struct sock *sk, int frametype)
 		dptr   += ROSE_ADDR_LEN;
 		memcpy(dptr, &rose->source_addr, ROSE_ADDR_LEN);
 		dptr   += ROSE_ADDR_LEN;
-		memcpy(dptr, buffer, faclen);
+		faclen = rose_create_facilities(dptr, rose);
+		skb_put(skb, faclen);
 		dptr   += faclen;
 		break;
 
-- 
2.20.1


From 5496a518a646dc93aeb3055a89f099fadf7be7c5 Mon Sep 17 00:00:00 2001
From: Aaro Koskinen <aaro.koskinen@nokia.com>
Date: Mon, 18 Mar 2019 23:36:08 +0200
Subject: [PATCH 12/33] net: stmmac: fix memory corruption with large MTUs

[ Upstream commit 223a960c01227e4dbcb6f9fa06b47d73bda21274 ]

When using 16K DMA buffers and ring mode, the DES3 refill is not working
correctly as the function is using a bogus pointer for checking the
private data. As a result stale pointers will remain in the RX descriptor
ring, so DMA will now likely overwrite/corrupt some already freed memory.

As simple reproducer, just receive some UDP traffic:

	# ifconfig eth0 down; ifconfig eth0 mtu 9000; ifconfig eth0 up
	# iperf3 -c 192.168.253.40 -u -b 0 -R

If you didn't crash by now check the RX descriptors to find non-contiguous
RX buffers:

	cat /sys/kernel/debug/stmmaceth/eth0/descriptors_status
	[...]
	1 [0x2be5020]: 0xa3220321 0x9ffc1ffc 0x72d70082 0x130e207e
					     ^^^^^^^^^^^^^^^^^^^^^
	2 [0x2be5040]: 0xa3220321 0x9ffc1ffc 0x72998082 0x1311a07e
					     ^^^^^^^^^^^^^^^^^^^^^

A simple ping test will now report bad data:

	# ping -s 8200 192.168.253.40
	PING 192.168.253.40 (192.168.253.40) 8200(8228) bytes of data.
	8208 bytes from 192.168.253.40: icmp_seq=1 ttl=64 time=1.00 ms
	wrong data byte #8144 should be 0xd0 but was 0x88

Fix the wrong pointer. Also we must refill DES3 only if the DMA buffer
size is 16K.

Fixes: 54139cf3bb33 ("net: stmmac: adding multiple buffers for rx")
Signed-off-by: Aaro Koskinen <aaro.koskinen@nokia.com>
Acked-by: Jose Abreu <joabreu@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/ring_mode.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
index d8c5bc412219..c0c75c111abb 100644
--- a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
+++ b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
@@ -111,10 +111,11 @@ static unsigned int is_jumbo_frm(int len, int enh_desc)
 
 static void refill_desc3(void *priv_ptr, struct dma_desc *p)
 {
-	struct stmmac_priv *priv = (struct stmmac_priv *)priv_ptr;
+	struct stmmac_rx_queue *rx_q = priv_ptr;
+	struct stmmac_priv *priv = rx_q->priv_data;
 
 	/* Fill DES3 in case of RING mode */
-	if (priv->dma_buf_sz >= BUF_SIZE_8KiB)
+	if (priv->dma_buf_sz == BUF_SIZE_16KiB)
 		p->des3 = cpu_to_le32(le32_to_cpu(p->des2) + BUF_SIZE_8KiB);
 }
 
-- 
2.20.1


From 3c21a26eff302aea1cb36143a459f8b6c132063e Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Tue, 19 Mar 2019 10:16:53 +0800
Subject: [PATCH 13/33] net-sysfs: call dev_hold if kobject_init_and_add
 success

[ Upstream commit a3e23f719f5c4a38ffb3d30c8d7632a4ed8ccd9e ]

In netdev_queue_add_kobject and rx_queue_add_kobject,
if sysfs_create_group failed, kobject_put will call
netdev_queue_release to decrease dev refcont, however
dev_hold has not be called. So we will see this while
unregistering dev:

unregister_netdevice: waiting for bcsh0 to become free. Usage count = -1

Reported-by: Hulk Robot <hulkci@huawei.com>
Fixes: d0d668371679 ("net: don't decrement kobj reference count on init failure")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/net-sysfs.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 73ad7607dcd1..aec26584f0ca 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -934,6 +934,8 @@ static int rx_queue_add_kobject(struct net_device *dev, int index)
 	if (error)
 		return error;
 
+	dev_hold(queue->dev);
+
 	if (dev->sysfs_rx_queue_group) {
 		error = sysfs_create_group(kobj, dev->sysfs_rx_queue_group);
 		if (error) {
@@ -943,7 +945,6 @@ static int rx_queue_add_kobject(struct net_device *dev, int index)
 	}
 
 	kobject_uevent(kobj, KOBJ_ADD);
-	dev_hold(queue->dev);
 
 	return error;
 }
@@ -1472,6 +1473,8 @@ static int netdev_queue_add_kobject(struct net_device *dev, int index)
 	if (error)
 		return error;
 
+	dev_hold(queue->dev);
+
 #ifdef CONFIG_BQL
 	error = sysfs_create_group(kobj, &dql_group);
 	if (error) {
@@ -1481,7 +1484,6 @@ static int netdev_queue_add_kobject(struct net_device *dev, int index)
 #endif
 
 	kobject_uevent(kobj, KOBJ_ADD);
-	dev_hold(queue->dev);
 
 	return 0;
 }
-- 
2.20.1


From 314466c6df31bae8865182f9c13f80352faf0cc4 Mon Sep 17 00:00:00 2001
From: Wang Hai <wanghai26@huawei.com>
Date: Wed, 20 Mar 2019 14:25:05 -0400
Subject: [PATCH 14/33] net-sysfs: Fix memory leak in netdev_register_kobject

[ Upstream commit 6b70fc94afd165342876e53fc4b2f7d085009945 ]

When registering struct net_device, it will call
	register_netdevice ->
		netdev_register_kobject ->
			device_initialize(dev);
			dev_set_name(dev, "%s", ndev->name)
			device_add(dev)
			register_queue_kobjects(ndev)

In netdev_register_kobject(), if device_add(dev) or
register_queue_kobjects(ndev) failed. Register_netdevice()
will return error, causing netdev_freemem(ndev) to be
called to free net_device, however put_device(&dev->dev)->..->
kobject_cleanup() won't be called, resulting in a memory leak.

syzkaller report this:
BUG: memory leak
unreferenced object 0xffff8881f4fad168 (size 8):
comm "syz-executor.0", pid 3575, jiffies 4294778002 (age 20.134s)
hex dump (first 8 bytes):
  77 70 61 6e 30 00 ff ff                          wpan0...
backtrace:
  [<000000006d2d91d7>] kstrdup_const+0x3d/0x50 mm/util.c:73
  [<00000000ba9ff953>] kvasprintf_const+0x112/0x170 lib/kasprintf.c:48
  [<000000005555ec09>] kobject_set_name_vargs+0x55/0x130 lib/kobject.c:281
  [<0000000098d28ec3>] dev_set_name+0xbb/0xf0 drivers/base/core.c:1915
  [<00000000b7553017>] netdev_register_kobject+0xc0/0x410 net/core/net-sysfs.c:1727
  [<00000000c826a797>] register_netdevice+0xa51/0xeb0 net/core/dev.c:8711
  [<00000000857bfcfd>] cfg802154_update_iface_num.isra.2+0x13/0x90 [ieee802154]
  [<000000003126e453>] ieee802154_llsec_fill_key_id+0x1d5/0x570 [ieee802154]
  [<00000000e4b3df51>] 0xffffffffc1500e0e
  [<00000000b4319776>] platform_drv_probe+0xc6/0x180 drivers/base/platform.c:614
  [<0000000037669347>] really_probe+0x491/0x7c0 drivers/base/dd.c:509
  [<000000008fed8862>] driver_probe_device+0xdc/0x240 drivers/base/dd.c:671
  [<00000000baf52041>] device_driver_attach+0xf2/0x130 drivers/base/dd.c:945
  [<00000000c7cc8dec>] __driver_attach+0x10e/0x210 drivers/base/dd.c:1022
  [<0000000057a757c2>] bus_for_each_dev+0x154/0x1e0 drivers/base/bus.c:304
  [<000000005f5ae04b>] bus_add_driver+0x427/0x5e0 drivers/base/bus.c:645

Reported-by: Hulk Robot <hulkci@huawei.com>
Fixes: 1fa5ae857bb1 ("driver core: get rid of struct device's bus_id string array")
Signed-off-by: Wang Hai <wanghai26@huawei.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/net-sysfs.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index aec26584f0ca..d62a7e5129c9 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1755,16 +1755,20 @@ int netdev_register_kobject(struct net_device *ndev)
 
 	error = device_add(dev);
 	if (error)
-		return error;
+		goto error_put_device;
 
 	error = register_queue_kobjects(ndev);
-	if (error) {
-		device_del(dev);
-		return error;
-	}
+	if (error)
+		goto error_device_del;
 
 	pm_runtime_set_memalloc_noio(dev, true);
 
+	return 0;
+
+error_device_del:
+	device_del(dev);
+error_put_device:
+	put_device(dev);
 	return error;
 }
 
-- 
2.20.1


From 1ac4da8b55b41a291cb4da567943d1fe7bb736d9 Mon Sep 17 00:00:00 2001
From: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Date: Sat, 23 Mar 2019 13:59:53 +0000
Subject: [PATCH 15/33] net: usb: aqc111: Extend HWID table by QNAP device

[ Upstream commit b7ebee2f95fb0fa2862d5ed2de707f872c311393 ]

New device of QNAP based on aqc111u
Add this ID to blacklist of cdc_ether driver as well

Signed-off-by: Dmitry Bezrukov <dmitry.bezrukov@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/aqc111.c    | 15 +++++++++++++++
 drivers/net/usb/cdc_ether.c |  8 ++++++++
 2 files changed, 23 insertions(+)

diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index 820a2fe7d027..aff995be2a31 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -1301,6 +1301,20 @@ static const struct driver_info trendnet_info = {
 	.tx_fixup	= aqc111_tx_fixup,
 };
 
+static const struct driver_info qnap_info = {
+	.description	= "QNAP QNA-UC5G1T USB to 5GbE Adapter",
+	.bind		= aqc111_bind,
+	.unbind		= aqc111_unbind,
+	.status		= aqc111_status,
+	.link_reset	= aqc111_link_reset,
+	.reset		= aqc111_reset,
+	.stop		= aqc111_stop,
+	.flags		= FLAG_ETHER | FLAG_FRAMING_AX |
+			  FLAG_AVOID_UNLINK_URBS | FLAG_MULTI_PACKET,
+	.rx_fixup	= aqc111_rx_fixup,
+	.tx_fixup	= aqc111_tx_fixup,
+};
+
 static int aqc111_suspend(struct usb_interface *intf, pm_message_t message)
 {
 	struct usbnet *dev = usb_get_intfdata(intf);
@@ -1455,6 +1469,7 @@ static const struct usb_device_id products[] = {
 	{AQC111_USB_ETH_DEV(0x0b95, 0x2790, asix111_info)},
 	{AQC111_USB_ETH_DEV(0x0b95, 0x2791, asix112_info)},
 	{AQC111_USB_ETH_DEV(0x20f4, 0xe05a, trendnet_info)},
+	{AQC111_USB_ETH_DEV(0x1c04, 0x0015, qnap_info)},
 	{ },/* END */
 };
 MODULE_DEVICE_TABLE(usb, products);
diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index 5512a1038721..3e9b2c319e45 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -851,6 +851,14 @@ static const struct usb_device_id	products[] = {
 	.driver_info = 0,
 },
 
+/* QNAP QNA-UC5G1T USB to 5GbE Adapter (based on AQC111U) */
+{
+	USB_DEVICE_AND_INTERFACE_INFO(0x1c04, 0x0015, USB_CLASS_COMM,
+				      USB_CDC_SUBCLASS_ETHERNET,
+				      USB_CDC_PROTO_NONE),
+	.driver_info = 0,
+},
+
 /* WHITELIST!!!
  *
  * CDC Ether uses two interfaces, not necessarily consecutive.
-- 
2.20.1


From 73d1d480a0f99b2489a8cdd00cec6432b7b9d0be Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Sat, 16 Mar 2019 14:41:30 +0100
Subject: [PATCH 16/33] packets: Always register packet sk in the same order

[ Upstream commit a4dc6a49156b1f8d6e17251ffda17c9e6a5db78a ]

When using fanouts with AF_PACKET, the demux functions such as
fanout_demux_cpu will return an index in the fanout socket array, which
corresponds to the selected socket.

The ordering of this array depends on the order the sockets were added
to a given fanout group, so for FANOUT_CPU this means sockets are bound
to cpus in the order they are configured, which is OK.

However, when stopping then restarting the interface these sockets are
bound to, the sockets are reassigned to the fanout group in the reverse
order, due to the fact that they were inserted at the head of the
interface's AF_PACKET socket list.

This means that traffic that was directed to the first socket in the
fanout group is now directed to the last one after an interface restart.

In the case of FANOUT_CPU, traffic from CPU0 will be directed to the
socket that used to receive traffic from the last CPU after an interface
restart.

This commit introduces a helper to add a socket at the tail of a list,
then uses it to register AF_PACKET sockets.

Note that this changes the order in which sockets are listed in /proc and
with sock_diag.

Fixes: dc99f600698d ("packet: Add fanout support")
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h     | 6 ++++++
 net/packet/af_packet.c | 2 +-
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index f43f935cb113..89d0d94d5db2 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -710,6 +710,12 @@ static inline void sk_add_node_rcu(struct sock *sk, struct hlist_head *list)
 		hlist_add_head_rcu(&sk->sk_node, list);
 }
 
+static inline void sk_add_node_tail_rcu(struct sock *sk, struct hlist_head *list)
+{
+	sock_hold(sk);
+	hlist_add_tail_rcu(&sk->sk_node, list);
+}
+
 static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
 {
 	hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list);
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 2784bfa1bc9b..8406bf11eef4 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3245,7 +3245,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol,
 	}
 
 	mutex_lock(&net->packet.sklist_lock);
-	sk_add_node_rcu(sk, &net->packet.sklist);
+	sk_add_node_tail_rcu(sk, &net->packet.sklist);
 	mutex_unlock(&net->packet.sklist_lock);
 
 	preempt_disable();
-- 
2.20.1


From 02274d691a2dd70bb4ef3ebffce2ae1028f06c08 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Thu, 21 Mar 2019 09:39:52 +0800
Subject: [PATCH 17/33] rhashtable: Still do rehash when we get EEXIST

[ Upstream commit 408f13ef358aa5ad56dc6230c2c7deb92cf462b1 ]

As it stands if a shrink is delayed because of an outstanding
rehash, we will go into a rescheduling loop without ever doing
the rehash.

This patch fixes this by still carrying out the rehash and then
rescheduling so that we can shrink after the completion of the
rehash should it still be necessary.

The return value of EEXIST captures this case and other cases
(e.g., another thread expanded/rehashed the table at the same
time) where we should still proceed with the rehash.

Fixes: da20420f83ea ("rhashtable: Add nested tables")
Reported-by: Josh Elsasser <jelsasser@appneta.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Tested-by: Josh Elsasser <jelsasser@appneta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 lib/rhashtable.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 852ffa5160f1..4edcf3310513 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -416,8 +416,12 @@ static void rht_deferred_worker(struct work_struct *work)
 	else if (tbl->nest)
 		err = rhashtable_rehash_alloc(ht, tbl, tbl->size);
 
-	if (!err)
-		err = rhashtable_rehash_table(ht);
+	if (!err || err == -EEXIST) {
+		int nerr;
+
+		nerr = rhashtable_rehash_table(ht);
+		err = err ?: nerr;
+	}
 
 	mutex_unlock(&ht->mutex);
 
-- 
2.20.1


From 477951059c780e3d8a2435f56d3644dd07f16952 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 18 Mar 2019 19:47:00 +0800
Subject: [PATCH 18/33] sctp: get sctphdr by offset in sctp_compute_cksum

[ Upstream commit 273160ffc6b993c7c91627f5a84799c66dfe4dee ]

sctp_hdr(skb) only works when skb->transport_header is set properly.

But in Netfilter, skb->transport_header for ipv6 is not guaranteed
to be right value for sctphdr. It would cause to fail to check the
checksum for sctp packets.

So fix it by using offset, which is always right in all places.

v1->v2:
  - Fix the changelog.

Fixes: e6d8b64b34aa ("net: sctp: fix and consolidate SCTP checksumming code")
Reported-by: Li Shuang <shuali@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/checksum.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/sctp/checksum.h b/include/net/sctp/checksum.h
index 32ee65a30aff..1c6e6c0766ca 100644
--- a/include/net/sctp/checksum.h
+++ b/include/net/sctp/checksum.h
@@ -61,7 +61,7 @@ static inline __wsum sctp_csum_combine(__wsum csum, __wsum csum2,
 static inline __le32 sctp_compute_cksum(const struct sk_buff *skb,
 					unsigned int offset)
 {
-	struct sctphdr *sh = sctp_hdr(skb);
+	struct sctphdr *sh = (struct sctphdr *)(skb->data + offset);
 	const struct skb_checksum_ops ops = {
 		.update  = sctp_csum_update,
 		.combine = sctp_csum_combine,
-- 
2.20.1


From a84cd776fda23d8f4f610223466ed97222bcd521 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 20 Mar 2019 14:49:38 +0800
Subject: [PATCH 19/33] sctp: use memdup_user instead of vmemdup_user

[ Upstream commit ef82bcfa671b9a635bab5fa669005663d8b177c5 ]

In sctp_setsockopt_bindx()/__sctp_setsockopt_connectx(), it allocates
memory with addrs_size which is passed from userspace. We used flag
GFP_USER to put some more restrictions on it in Commit cacc06215271
("sctp: use GFP_USER for user-controlled kmalloc").

However, since Commit c981f254cc82 ("sctp: use vmemdup_user() rather
than badly open-coding memdup_user()"), vmemdup_user() has been used,
which doesn't check GFP_USER flag when goes to vmalloc_*(). So when
addrs_size is a huge value, it could exhaust memory and even trigger
oom killer.

This patch is to use memdup_user() instead, in which GFP_USER would
work to limit the memory allocation with a huge addrs_size.

Note we can't fix it by limiting 'addrs_size', as there's no demand
for it from RFC.

Reported-by: syzbot+ec1b7575afef85a0e5ca@syzkaller.appspotmail.com
Fixes: c981f254cc82 ("sctp: use vmemdup_user() rather than badly open-coding memdup_user()")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index a2771b3b3c14..5f68420b4b0d 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -999,7 +999,7 @@ static int sctp_setsockopt_bindx(struct sock *sk,
 	if (unlikely(addrs_size <= 0))
 		return -EINVAL;
 
-	kaddrs = vmemdup_user(addrs, addrs_size);
+	kaddrs = memdup_user(addrs, addrs_size);
 	if (unlikely(IS_ERR(kaddrs)))
 		return PTR_ERR(kaddrs);
 
@@ -1007,7 +1007,7 @@ static int sctp_setsockopt_bindx(struct sock *sk,
 	addr_buf = kaddrs;
 	while (walk_size < addrs_size) {
 		if (walk_size + sizeof(sa_family_t) > addrs_size) {
-			kvfree(kaddrs);
+			kfree(kaddrs);
 			return -EINVAL;
 		}
 
@@ -1018,7 +1018,7 @@ static int sctp_setsockopt_bindx(struct sock *sk,
 		 * causes the address buffer to overflow return EINVAL.
 		 */
 		if (!af || (walk_size + af->sockaddr_len) > addrs_size) {
-			kvfree(kaddrs);
+			kfree(kaddrs);
 			return -EINVAL;
 		}
 		addrcnt++;
@@ -1054,7 +1054,7 @@ static int sctp_setsockopt_bindx(struct sock *sk,
 	}
 
 out:
-	kvfree(kaddrs);
+	kfree(kaddrs);
 
 	return err;
 }
@@ -1329,7 +1329,7 @@ static int __sctp_setsockopt_connectx(struct sock *sk,
 	if (unlikely(addrs_size <= 0))
 		return -EINVAL;
 
-	kaddrs = vmemdup_user(addrs, addrs_size);
+	kaddrs = memdup_user(addrs, addrs_size);
 	if (unlikely(IS_ERR(kaddrs)))
 		return PTR_ERR(kaddrs);
 
@@ -1349,7 +1349,7 @@ static int __sctp_setsockopt_connectx(struct sock *sk,
 	err = __sctp_connect(sk, kaddrs, addrs_size, flags, assoc_id);
 
 out_free:
-	kvfree(kaddrs);
+	kfree(kaddrs);
 
 	return err;
 }
-- 
2.20.1


From ddc2a6c2c95b9dfafd6210be8bb0352ec7a82d70 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 19 Mar 2019 05:45:35 -0700
Subject: [PATCH 20/33] tcp: do not use ipv6 header for ipv4 flow

[ Upstream commit 89e4130939a20304f4059ab72179da81f5347528 ]

When a dual stack tcp listener accepts an ipv4 flow,
it should not attempt to use an ipv6 header or tcp_v6_iif() helper.

Fixes: 1397ed35f22d ("ipv6: add flowinfo for tcp6 pkt_options for all cases")
Fixes: df3687ffc665 ("ipv6: add the IPV6_FL_F_REFLECT flag to IPV6_FL_A_GET")
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/tcp_ipv6.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index b81eb7cb815e..8505d96483d5 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1112,11 +1112,11 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 		newnp->ipv6_fl_list = NULL;
 		newnp->pktoptions  = NULL;
 		newnp->opt	   = NULL;
-		newnp->mcast_oif   = tcp_v6_iif(skb);
-		newnp->mcast_hops  = ipv6_hdr(skb)->hop_limit;
-		newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb));
+		newnp->mcast_oif   = inet_iif(skb);
+		newnp->mcast_hops  = ip_hdr(skb)->ttl;
+		newnp->rcv_flowinfo = 0;
 		if (np->repflow)
-			newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb));
+			newnp->flow_label = 0;
 
 		/*
 		 * No need to charge this sock to the relevant IPv6 refcnt debug socks count
-- 
2.20.1


From 9250c055c7012bc1995522f1f983810e651b44be Mon Sep 17 00:00:00 2001
From: Erik Hugne <erik.hugne@gmail.com>
Date: Sun, 17 Mar 2019 18:46:42 +0100
Subject: [PATCH 21/33] tipc: allow service ranges to be connect()'ed on
 RDM/DGRAM

[ Upstream commit ea239314fe42ace880bdd834256834679346c80e ]

We move the check that prevents connecting service ranges to after
the RDM/DGRAM check, and move address sanity control to a separate
function that also validates the service range.

Fixes: 23998835be98 ("tipc: improve address sanity check in tipc_connect()")
Signed-off-by: Erik Hugne <erik.hugne@gmail.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/socket.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 139694f2c576..4dca9161f99b 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2349,6 +2349,16 @@ static int tipc_wait_for_connect(struct socket *sock, long *timeo_p)
 	return 0;
 }
 
+static bool tipc_sockaddr_is_sane(struct sockaddr_tipc *addr)
+{
+	if (addr->family != AF_TIPC)
+		return false;
+	if (addr->addrtype == TIPC_SERVICE_RANGE)
+		return (addr->addr.nameseq.lower <= addr->addr.nameseq.upper);
+	return (addr->addrtype == TIPC_SERVICE_ADDR ||
+		addr->addrtype == TIPC_SOCKET_ADDR);
+}
+
 /**
  * tipc_connect - establish a connection to another TIPC port
  * @sock: socket structure
@@ -2384,18 +2394,18 @@ static int tipc_connect(struct socket *sock, struct sockaddr *dest,
 		if (!tipc_sk_type_connectionless(sk))
 			res = -EINVAL;
 		goto exit;
-	} else if (dst->family != AF_TIPC) {
-		res = -EINVAL;
 	}
-	if (dst->addrtype != TIPC_ADDR_ID && dst->addrtype != TIPC_ADDR_NAME)
+	if (!tipc_sockaddr_is_sane(dst)) {
 		res = -EINVAL;
-	if (res)
 		goto exit;
-
+	}
 	/* DGRAM/RDM connect(), just save the destaddr */
 	if (tipc_sk_type_connectionless(sk)) {
 		memcpy(&tsk->peer, dest, destlen);
 		goto exit;
+	} else if (dst->addrtype == TIPC_SERVICE_RANGE) {
+		res = -EINVAL;
+		goto exit;
 	}
 
 	previous = sk->sk_state;
-- 
2.20.1


From 6c49a878989cd796df2b6a8fa491ec4830ed8857 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 24 Mar 2019 00:48:22 +0800
Subject: [PATCH 22/33] tipc: change to check tipc_own_id to return in
 tipc_net_stop

[ Upstream commit 9926cb5f8b0f0aea535735185600d74db7608550 ]

When running a syz script, a panic occurred:

[  156.088228] BUG: KASAN: use-after-free in tipc_disc_timeout+0x9c9/0xb20 [tipc]
[  156.094315] Call Trace:
[  156.094844]  <IRQ>
[  156.095306]  dump_stack+0x7c/0xc0
[  156.097346]  print_address_description+0x65/0x22e
[  156.100445]  kasan_report.cold.3+0x37/0x7a
[  156.102402]  tipc_disc_timeout+0x9c9/0xb20 [tipc]
[  156.106517]  call_timer_fn+0x19a/0x610
[  156.112749]  run_timer_softirq+0xb51/0x1090

It was caused by the netns freed without deleting the discoverer timer,
while later on the netns would be accessed in the timer handler.

The timer should have been deleted by tipc_net_stop() when cleaning up a
netns. However, tipc has been able to enable a bearer and start d->timer
without the local node_addr set since Commit 52dfae5c85a4 ("tipc: obtain
node identity from interface by default"), which caused the timer not to
be deleted in tipc_net_stop() then.

So fix it in tipc_net_stop() by changing to check local node_id instead
of local node_addr, as Jon suggested.

While at it, remove the calling of tipc_nametbl_withdraw() there, since
tipc_nametbl_stop() will take of the nametbl's freeing after.

Fixes: 52dfae5c85a4 ("tipc: obtain node identity from interface by default")
Reported-by: syzbot+a25307ad099309f1c2b9@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/net.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/net/tipc/net.c b/net/tipc/net.c
index f076edb74338..7ce1e86b024f 100644
--- a/net/tipc/net.c
+++ b/net/tipc/net.c
@@ -163,12 +163,9 @@ void tipc_sched_net_finalize(struct net *net, u32 addr)
 
 void tipc_net_stop(struct net *net)
 {
-	u32 self = tipc_own_addr(net);
-
-	if (!self)
+	if (!tipc_own_id(net))
 		return;
 
-	tipc_nametbl_withdraw(net, TIPC_CFG_SRV, self, self, self);
 	rtnl_lock();
 	tipc_bearer_stop(net);
 	tipc_node_stop(net);
-- 
2.20.1


From 4f514c40c14d10abf345507d0bd53d9a23dd6aab Mon Sep 17 00:00:00 2001
From: Erik Hugne <erik.hugne@gmail.com>
Date: Thu, 21 Mar 2019 09:11:59 +0100
Subject: [PATCH 23/33] tipc: fix cancellation of topology subscriptions

[ Upstream commit 33872d79f5d1cbedaaab79669cc38f16097a9450 ]

When cancelling a subscription, we have to clear the cancel bit in the
request before iterating over any established subscriptions with memcmp.
Otherwise no subscription will ever be found, and it will not be
possible to explicitly unsubscribe individual subscriptions.

Fixes: 8985ecc7c1e0 ("tipc: simplify endianness handling in topology subscriber")
Signed-off-by: Erik Hugne <erik.hugne@gmail.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/topsrv.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c
index a457c0fbbef1..f5edb213d760 100644
--- a/net/tipc/topsrv.c
+++ b/net/tipc/topsrv.c
@@ -365,6 +365,7 @@ static int tipc_conn_rcv_sub(struct tipc_topsrv *srv,
 	struct tipc_subscription *sub;
 
 	if (tipc_sub_read(s, filter) & TIPC_SUB_CANCEL) {
+		s->filter &= __constant_ntohl(~TIPC_SUB_CANCEL);
 		tipc_conn_delete_sub(con, s);
 		return 0;
 	}
-- 
2.20.1


From 0a34fcbba2c855fe715dfbc74140ebbe1d6b67a7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 14 Mar 2019 20:19:47 -0700
Subject: [PATCH 24/33] tun: properly test for IFF_UP

[ Upstream commit 4477138fa0ae4e1b699786ef0600863ea6e6c61c ]

Same reasons than the ones explained in commit 4179cb5a4c92
("vxlan: test dev->flags & IFF_UP before calling netif_rx()")

netif_rx_ni() or napi_gro_frags() must be called under a strict contract.

At device dismantle phase, core networking clears IFF_UP
and flush_all_backlogs() is called after rcu grace period
to make sure no incoming packet might be in a cpu backlog
and still referencing the device.

A similar protocol is used for gro layer.

Most drivers call netif_rx() from their interrupt handler,
and since the interrupts are disabled at device dismantle,
netif_rx() does not have to check dev->flags & IFF_UP

Virtual drivers do not have this guarantee, and must
therefore make the check themselves.

Fixes: 1bd4978a88ac ("tun: honor IFF_UP in tun_get_user()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 53f4f37b0ffd..f4126ce58878 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1763,9 +1763,6 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	int skb_xdp = 1;
 	bool frags = tun_napi_frags_enabled(tfile);
 
-	if (!(tun->dev->flags & IFF_UP))
-		return -EIO;
-
 	if (!(tun->flags & IFF_NO_PI)) {
 		if (len < sizeof(pi))
 			return -EINVAL;
@@ -1867,6 +1864,8 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 			err = skb_copy_datagram_from_iter(skb, 0, from, len);
 
 		if (err) {
+			err = -EFAULT;
+drop:
 			this_cpu_inc(tun->pcpu_stats->rx_dropped);
 			kfree_skb(skb);
 			if (frags) {
@@ -1874,7 +1873,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 				mutex_unlock(&tfile->napi_mutex);
 			}
 
-			return -EFAULT;
+			return err;
 		}
 	}
 
@@ -1958,6 +1957,12 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	    !tfile->detached)
 		rxhash = __skb_get_hash_symmetric(skb);
 
+	rcu_read_lock();
+	if (unlikely(!(tun->dev->flags & IFF_UP))) {
+		err = -EIO;
+		goto drop;
+	}
+
 	if (frags) {
 		/* Exercise flow dissector code path. */
 		u32 headlen = eth_get_headlen(skb->data, skb_headlen(skb));
@@ -1965,6 +1970,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 		if (unlikely(headlen > skb_headlen(skb))) {
 			this_cpu_inc(tun->pcpu_stats->rx_dropped);
 			napi_free_frags(&tfile->napi);
+			rcu_read_unlock();
 			mutex_unlock(&tfile->napi_mutex);
 			WARN_ON(1);
 			return -ENOMEM;
@@ -1992,6 +1998,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	} else {
 		netif_rx_ni(skb);
 	}
+	rcu_read_unlock();
 
 	stats = get_cpu_ptr(tun->pcpu_stats);
 	u64_stats_update_begin(&stats->syncp);
-- 
2.20.1


From 5c389a928a31fe188427b965e5211a8f7810606e Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 26 Mar 2019 18:22:16 +0100
Subject: [PATCH 25/33] vrf: prevent adding upper devices

[ Upstream commit 1017e0987117c32783ba7c10fe2e7ff1456ba1dc ]

VRF devices don't work with upper devices. Currently, it's possible to
add a VRF device to a bridge or team, and to create macvlan, macsec, or
ipvlan devices on top of a VRF (bond and vlan are prevented respectively
by the lack of an ndo_set_mac_address op and the NETIF_F_VLAN_CHALLENGED
feature flag).

Fix this by setting the IFF_NO_RX_HANDLER flag (introduced in commit
f5426250a6ec ("net: introduce IFF_NO_RX_HANDLER")).

Cc: David Ahern <dsahern@gmail.com>
Fixes: 193125dbd8eb ("net: Introduce VRF device driver")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 7c1430ed0244..6d1a1abbed27 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -1273,6 +1273,7 @@ static void vrf_setup(struct net_device *dev)
 
 	/* default to no qdisc; user can add if desired */
 	dev->priv_flags |= IFF_NO_QUEUE;
+	dev->priv_flags |= IFF_NO_RX_HANDLER;
 
 	dev->min_mtu = 0;
 	dev->max_mtu = 0;
-- 
2.20.1


From 5455f15f1ad41faf2de4cf9757db568c89795c2e Mon Sep 17 00:00:00 2001
From: Zhiqiang Liu <liuzhiqiang26@huawei.com>
Date: Sat, 16 Mar 2019 17:02:54 +0800
Subject: [PATCH 26/33] vxlan: Don't call gro_cells_destroy() before device is
 unregistered

[ Upstream commit cc4807bb609230d8959fd732b0bf3bd4c2de8eac ]

Commit ad6c9986bcb62 ("vxlan: Fix GRO cells race condition between
receive and link delete") fixed a race condition for the typical case a vxlan
device is dismantled from the current netns. But if a netns is dismantled,
vxlan_destroy_tunnels() is called to schedule a unregister_netdevice_queue()
of all the vxlan tunnels that are related to this netns.

In vxlan_destroy_tunnels(), gro_cells_destroy() is called and finished before
unregister_netdevice_queue(). This means that the gro_cells_destroy() call is
done too soon, for the same reasons explained in above commit.

So we need to fully respect the RCU rules, and thus must remove the
gro_cells_destroy() call or risk use after-free.

Fixes: 58ce31cca1ff ("vxlan: GRO support at tunnel layer")
Signed-off-by: Suanming.Mou <mousuanming@huawei.com>
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Zhiqiang Liu <liuzhiqiang26@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index d6fb6a89f9b3..5006daed2e96 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -4184,10 +4184,8 @@ static void vxlan_destroy_tunnels(struct net *net, struct list_head *head)
 		/* If vxlan->dev is in the same netns, it has already been added
 		 * to the list by the previous loop.
 		 */
-		if (!net_eq(dev_net(vxlan->dev), net)) {
-			gro_cells_destroy(&vxlan->gro_cells);
+		if (!net_eq(dev_net(vxlan->dev), net))
 			unregister_netdevice_queue(vxlan->dev, head);
-		}
 	}
 
 	for (h = 0; h < PORT_HASH_SIZE; ++h)
-- 
2.20.1


From 43e2c37c3ef109394bb3ec3672a8f6b7130fd7ba Mon Sep 17 00:00:00 2001
From: Dean Nelson <dnelson@redhat.com>
Date: Tue, 26 Mar 2019 11:53:19 -0400
Subject: [PATCH 27/33] thunderx: enable page recycling for non-XDP case

[ Upstream commit b3e208069477588c06f4d5d986164b435bb06e6d ]

Commit 773225388dae15e72790 ("net: thunderx: Optimize page recycling for XDP")
added code to nicvf_alloc_page() that inadvertently disables receive buffer
page recycling for the non-XDP case by always NULL'ng the page pointer.

This patch corrects two if-conditionals to allow for the recycling of non-XDP
mode pages by only setting the page pointer to NULL when the page is not ready
for recycling.

Fixes: 773225388dae ("net: thunderx: Optimize page recycling for XDP")
Signed-off-by: Dean Nelson <dnelson@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/cavium/thunder/nicvf_queues.c    | 23 +++++++++----------
 1 file changed, 11 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index 5b4d3badcb73..55dbf02c42af 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -105,20 +105,19 @@ static inline struct pgcache *nicvf_alloc_page(struct nicvf *nic,
 	/* Check if page can be recycled */
 	if (page) {
 		ref_count = page_ref_count(page);
-		/* Check if this page has been used once i.e 'put_page'
-		 * called after packet transmission i.e internal ref_count
-		 * and page's ref_count are equal i.e page can be recycled.
+		/* This page can be recycled if internal ref_count and page's
+		 * ref_count are equal, indicating that the page has been used
+		 * once for packet transmission. For non-XDP mode, internal
+		 * ref_count is always '1'.
 		 */
-		if (rbdr->is_xdp && (ref_count == pgcache->ref_count))
-			pgcache->ref_count--;
-		else
-			page = NULL;
-
-		/* In non-XDP mode, page's ref_count needs to be '1' for it
-		 * to be recycled.
-		 */
-		if (!rbdr->is_xdp && (ref_count != 1))
+		if (rbdr->is_xdp) {
+			if (ref_count == pgcache->ref_count)
+				pgcache->ref_count--;
+			else
+				page = NULL;
+		} else if (ref_count != 1) {
 			page = NULL;
+		}
 	}
 
 	if (!page) {
-- 
2.20.1


From 0f4520cc0f8d287c2a3f08e85125395290cfbbcb Mon Sep 17 00:00:00 2001
From: Dean Nelson <dnelson@redhat.com>
Date: Tue, 26 Mar 2019 11:53:26 -0400
Subject: [PATCH 28/33] thunderx: eliminate extra calls to put_page() for pages
 held for recycling

[ Upstream commit cd35ef91490ad8049dd180bb060aff7ee192eda9 ]

For the non-XDP case, commit 773225388dae15e72790 ("net: thunderx: Optimize
page recycling for XDP") added code to nicvf_free_rbdr() that, when releasing
the additional receive buffer page reference held for recycling, repeatedly
calls put_page() until the page's _refcount goes to zero. Which results in
the page being freed.

This is not okay if the page's _refcount was greater than 1 (in the non-XDP
case), because nicvf_free_rbdr() should not be subtracting more than what
nicvf_alloc_page() had previously added to the page's _refcount, which was
only 1 (in the non-XDP case).

This can arise if a received packet is still being processed and the receive
buffer (i.e., skb->head) has not yet been freed via skb_free_head() when
nicvf_free_rbdr() is spinning through the aforementioned put_page() loop.

If this should occur, when the received packet finishes processing and
skb_free_head() is called, various problems can ensue. Exactly what, depends on
whether the page has already been reallocated or not, anything from "BUG: Bad
page state ... ", to "Unable to handle kernel NULL pointer dereference ..." or
"Unable to handle kernel paging request...".

So this patch changes nicvf_free_rbdr() to only call put_page() once for pages
held for recycling (in the non-XDP case).

Fixes: 773225388dae ("net: thunderx: Optimize page recycling for XDP")
Signed-off-by: Dean Nelson <dnelson@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/thunder/nicvf_queues.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index 55dbf02c42af..e246f9733bb8 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -364,11 +364,10 @@ static void nicvf_free_rbdr(struct nicvf *nic, struct rbdr *rbdr)
 	while (head < rbdr->pgcnt) {
 		pgcache = &rbdr->pgcache[head];
 		if (pgcache->page && page_ref_count(pgcache->page) != 0) {
-			if (!rbdr->is_xdp) {
-				put_page(pgcache->page);
-				continue;
+			if (rbdr->is_xdp) {
+				page_ref_sub(pgcache->page,
+					     pgcache->ref_count - 1);
 			}
-			page_ref_sub(pgcache->page, pgcache->ref_count - 1);
 			put_page(pgcache->page);
 		}
 		head++;
-- 
2.20.1


From fd57c75ba611cec68803373141ad70587e9ad557 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 23 Mar 2019 19:41:32 +0100
Subject: [PATCH 29/33] net: dsa: mv88e6xxx: fix few issues in
 mv88e6390x_port_set_cmode

[ Upstream commit 5ceaeb99ffb4dc002d20f6ac243c19a85e2c7a76 ]

This patches fixes few issues in mv88e6390x_port_set_cmode().

1. When entering the function the old cmode may be 0, in this case
   mv88e6390x_serdes_get_lane() returns -ENODEV. As result we bail
   out and have no chance to set a new mode. Therefore deal properly
   with -ENODEV.

2. Once we have disabled power and irq, let's set the cached cmode to 0.
   This reflects the actual status and is cleaner if we bail out with an
   error in the following function calls.

3. The cached cmode is used by mv88e6390x_serdes_get_lane(),
   mv88e6390_serdes_power_lane() and mv88e6390_serdes_irq_enable().
   Currently we set the cached mode to the new one at the very end of
   the function only, means until then we use the old one what may be
   wrong.

4. When calling mv88e6390_serdes_irq_enable() we use the lane value
   belonging to the old cmode. Get the lane belonging to the new cmode
   before calling this function.

It's hard to provide a good "Fixes" tag because quite a few smaller
changes have been done to the code in question recently.

Fixes: d235c48b40d3 ("net: dsa: mv88e6xxx: power serdes on/off for 10G interfaces on 6390X")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/port.c | 24 ++++++++++++++++--------
 1 file changed, 16 insertions(+), 8 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c
index 5e921bb6c214..41eee62fed25 100644
--- a/drivers/net/dsa/mv88e6xxx/port.c
+++ b/drivers/net/dsa/mv88e6xxx/port.c
@@ -427,18 +427,22 @@ int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 		return 0;
 
 	lane = mv88e6390x_serdes_get_lane(chip, port);
-	if (lane < 0)
+	if (lane < 0 && lane != -ENODEV)
 		return lane;
 
-	if (chip->ports[port].serdes_irq) {
-		err = mv88e6390_serdes_irq_disable(chip, port, lane);
+	if (lane >= 0) {
+		if (chip->ports[port].serdes_irq) {
+			err = mv88e6390_serdes_irq_disable(chip, port, lane);
+			if (err)
+				return err;
+		}
+
+		err = mv88e6390x_serdes_power(chip, port, false);
 		if (err)
 			return err;
 	}
 
-	err = mv88e6390x_serdes_power(chip, port, false);
-	if (err)
-		return err;
+	chip->ports[port].cmode = 0;
 
 	if (cmode) {
 		err = mv88e6xxx_port_read(chip, port, MV88E6XXX_PORT_STS, &reg);
@@ -452,6 +456,12 @@ int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 		if (err)
 			return err;
 
+		chip->ports[port].cmode = cmode;
+
+		lane = mv88e6390x_serdes_get_lane(chip, port);
+		if (lane < 0)
+			return lane;
+
 		err = mv88e6390x_serdes_power(chip, port, true);
 		if (err)
 			return err;
@@ -463,8 +473,6 @@ int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 		}
 	}
 
-	chip->ports[port].cmode = cmode;
-
 	return 0;
 }
 
-- 
2.20.1


From 436dc8c7286d8a5d5377c5ab67e05f0554a5d5d0 Mon Sep 17 00:00:00 2001
From: Claudiu Manoil <claudiu.manoil@nxp.com>
Date: Tue, 26 Mar 2019 11:48:57 +0200
Subject: [PATCH 30/33] net: mii: Fix PAUSE cap advertisement from
 linkmode_adv_to_lcl_adv_t() helper

[ Upstream commit 7f07e5f1f778605e98cf2156d4db1ff3a3a1a74a ]

With a recent link mode advertisement code update this helper
providing local pause capability translation used for flow
control link mode negotiation got broken.
For eth drivers using this helper, the issue is apparent only
if either PAUSE or ASYM_PAUSE is being advertised.

Fixes: 3c1bcc8614db ("net: ethernet: Convert phydev advertize and supported from u32 to link mode")
Signed-off-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/mii.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/mii.h b/include/linux/mii.h
index 6fee8b1a4400..5cd824c1c0ca 100644
--- a/include/linux/mii.h
+++ b/include/linux/mii.h
@@ -469,7 +469,7 @@ static inline u32 linkmode_adv_to_lcl_adv_t(unsigned long *advertising)
 	if (linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT,
 			      advertising))
 		lcl_adv |= ADVERTISE_PAUSE_CAP;
-	if (linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT,
+	if (linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
 			      advertising))
 		lcl_adv |= ADVERTISE_PAUSE_ASYM;
 
-- 
2.20.1


From f653c877a843dc5542dc2187ced113a19498e391 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 22 Mar 2019 20:00:20 +0100
Subject: [PATCH 31/33] net: phy: don't clear BMCR in genphy_soft_reset

[ Upstream commit d29f5aa0bc0c321e1b9e4658a2a7e08e885da52a ]

So far we effectively clear the BMCR register. Some PHY's can deal
with this (e.g. because they reset BMCR to a default as part of a
soft-reset) whilst on others this causes issues because e.g. the
autoneg bit is cleared. Marvell is an example, see also thread [0].
So let's be a little bit more gentle and leave all bits we're not
interested in as-is. This change is needed for PHY drivers to
properly deal with the original patch.

[0] https://marc.info/?t=155264050700001&r=1&w=2

Fixes: 6e2d85ec0559 ("net: phy: Stop with excessive soft reset")
Tested-by: Phil Reid <preid@electromag.com.au>
Tested-by: liweihang <liweihang@hisilicon.com>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 46c86725a693..739434fe04fa 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1827,7 +1827,7 @@ int genphy_soft_reset(struct phy_device *phydev)
 {
 	int ret;
 
-	ret = phy_write(phydev, MII_BMCR, BMCR_RESET);
+	ret = phy_set_bits(phydev, MII_BMCR, BMCR_RESET);
 	if (ret < 0)
 		return ret;
 
-- 
2.20.1


From 972c96152d2a04aecd9704f0c249632f8ac812c7 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 22 Mar 2019 07:39:35 +0100
Subject: [PATCH 32/33] r8169: fix cable re-plugging issue

[ Upstream commit 23c78343ec36990709b636a9e02bad814f4384ad ]

Bartek reported that after few cable unplug/replug cycles suddenly
replug isn't detected any longer. His system uses a RTL8106, I wasn't
able to reproduce the issue with RTL8168g. According to his bisect
the referenced commit caused the regression. As Realtek doesn't
release datasheets or errata it's hard to say what's the actual root
cause, but this change was reported to fix the issue.

Fixes: 38caff5a445b ("r8169: handle all interrupt events in the hard irq handler")
Reported-by: Bartosz Skrzypczak <barteks2x@gmail.com>
Suggested-by: Bartosz Skrzypczak <barteks2x@gmail.com>
Tested-by: Bartosz Skrzypczak <barteks2x@gmail.com>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 6e36b88ca7c9..f55d177ae894 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -6435,7 +6435,7 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance)
 		set_bit(RTL_FLAG_TASK_RESET_PENDING, tp->wk.flags);
 	}
 
-	if (status & RTL_EVENT_NAPI) {
+	if (status & (RTL_EVENT_NAPI | LinkChg)) {
 		rtl_irq_disable(tp);
 		napi_schedule_irqoff(&tp->napi);
 	}
-- 
2.20.1


From c183d6cf17a82dbbd049004a2536f3885041889f Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Tue, 26 Mar 2019 13:50:14 +0800
Subject: [PATCH 33/33] ila: Fix rhashtable walker list corruption

[ Upstream commit b5f9bd15b88563b55a99ed588416881367a0ce5f ]

ila_xlat_nl_cmd_flush uses rhashtable walkers allocated from the
stack but it never frees them.  This corrupts the walker list of
the hash table.

This patch fixes it.

Reported-by: syzbot+dae72a112334aa65a159@syzkaller.appspotmail.com
Fixes: b6e71bdebb12 ("ila: Flush netlink command to clear xlat...")
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ila/ila_xlat.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c
index 17c455ff69ff..7858fa9ea103 100644
--- a/net/ipv6/ila/ila_xlat.c
+++ b/net/ipv6/ila/ila_xlat.c
@@ -420,6 +420,7 @@ int ila_xlat_nl_cmd_flush(struct sk_buff *skb, struct genl_info *info)
 
 done:
 	rhashtable_walk_stop(&iter);
+	rhashtable_walk_exit(&iter);
 	return ret;
 }
 
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Thu, Mar 28, 2019 at 12:24:07PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.19 and v5.0
> -stable, respectively.

Now queued up, thanks.

greg k-h

Re: [PATCHES] Networking

[Greg KH]

On Thu, Mar 28, 2019 at 09:55:25PM +0100, Greg KH wrote:
> On Thu, Mar 28, 2019 at 12:24:07PM -0700, David Miller wrote:
> > 
> > Please queue up the following networking bug fixes for v4.19 and v5.0
> > -stable, respectively.
> 
> Now queued up, thanks.

Hm, looks like the tun patch needs a call to rcu_read_unlock() in the
error path.  Should I drop that patch for now until a fix hits Linus's
tree, or just leave it as-is for now and take the fix later?

thanks,

greg k-h

Re: [PATCHES] Networking

[David Miller]

From: Greg KH <gregkh@linuxfoundation.org>
Date: Thu, 28 Mar 2019 22:51:49 +0100

> On Thu, Mar 28, 2019 at 09:55:25PM +0100, Greg KH wrote:
>> On Thu, Mar 28, 2019 at 12:24:07PM -0700, David Miller wrote:
>> > 
>> > Please queue up the following networking bug fixes for v4.19 and v5.0
>> > -stable, respectively.
>> 
>> Now queued up, thanks.
> 
> Hm, looks like the tun patch needs a call to rcu_read_unlock() in the
> error path.  Should I drop that patch for now until a fix hits Linus's
> tree, or just leave it as-is for now and take the fix later?

Hmmm, I thought I included the:

From 9180bb4f046064dfa4541488102703b402bb04e1 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 16 Mar 2019 13:09:53 -0700
Subject: [PATCH] tun: add a missing rcu_read_unlock() in error path

[ Upstream commit 9180bb4f046064dfa4541488102703b402bb04e1 ]

In my latest patch I missed one rcu_read_unlock(), in case
device is down.

Fixes: 4477138fa0ae ("tun: properly test for IFF_UP")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 0d343359f647..e9ca1c088d0b 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1960,6 +1960,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	rcu_read_lock();
 	if (unlikely(!(tun->dev->flags & IFF_UP))) {
 		err = -EIO;
+		rcu_read_unlock();
 		goto drop;
 	}
 
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Thu, Mar 28, 2019 at 04:18:14PM -0700, David Miller wrote:
> From: Greg KH <gregkh@linuxfoundation.org>
> Date: Thu, 28 Mar 2019 22:51:49 +0100
> 
> > On Thu, Mar 28, 2019 at 09:55:25PM +0100, Greg KH wrote:
> >> On Thu, Mar 28, 2019 at 12:24:07PM -0700, David Miller wrote:
> >> > 
> >> > Please queue up the following networking bug fixes for v4.19 and v5.0
> >> > -stable, respectively.
> >> 
> >> Now queued up, thanks.
> > 
> > Hm, looks like the tun patch needs a call to rcu_read_unlock() in the
> > error path.  Should I drop that patch for now until a fix hits Linus's
> > tree, or just leave it as-is for now and take the fix later?
> 
> Hmmm, I thought I included the:
> 
> >From 9180bb4f046064dfa4541488102703b402bb04e1 Mon Sep 17 00:00:00 2001
> From: Eric Dumazet <edumazet@google.com>
> Date: Sat, 16 Mar 2019 13:09:53 -0700
> Subject: [PATCH] tun: add a missing rcu_read_unlock() in error path
> 
> [ Upstream commit 9180bb4f046064dfa4541488102703b402bb04e1 ]
> 
> In my latest patch I missed one rcu_read_unlock(), in case
> device is down.
> 
> Fixes: 4477138fa0ae ("tun: properly test for IFF_UP")
> Signed-off-by: Eric Dumazet <edumazet@google.com>
> Reported-by: syzbot <syzkaller@googlegroups.com>
> Signed-off-by: David S. Miller <davem@davemloft.net>
> ---
>  drivers/net/tun.c | 1 +
>  1 file changed, 1 insertion(+)
> 
> diff --git a/drivers/net/tun.c b/drivers/net/tun.c
> index 0d343359f647..e9ca1c088d0b 100644
> --- a/drivers/net/tun.c
> +++ b/drivers/net/tun.c
> @@ -1960,6 +1960,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
>  	rcu_read_lock();
>  	if (unlikely(!(tun->dev->flags & IFF_UP))) {
>  		err = -EIO;
> +		rcu_read_unlock();
>  		goto drop;
>  	}
>  
> -- 
> 2.20.1

Wonderful, thanks for this, now queued up.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 104 bytes --]


Please queue up the following networking bug fixes for v4.19 and v5.0
stable respectively.

Thank you!

[-- Attachment #2: net_419.mbox --]
[-- Type: Application/Octet-Stream, Size: 97002 bytes --]

From dbc31eac1e034f278e9e5d7e67bf419fa3e0e422 Mon Sep 17 00:00:00 2001
From: Haiyang Zhang <haiyangz@microsoft.com>
Date: Thu, 28 Mar 2019 19:40:36 +0000
Subject: [PATCH 01/33] hv_netvsc: Fix unwanted wakeup after tx_disable

[ Upstream commit 1b704c4a1ba95574832e730f23817b651db2aa59 ]

After queue stopped, the wakeup mechanism may wake it up again
when ring buffer usage is lower than a threshold. This may cause
send path panic on NULL pointer when we stopped all tx queues in
netvsc_detach and start removing the netvsc device.

This patch fix it by adding a tx_disable flag to prevent unwanted
queue wakeup.

Fixes: 7b2ee50c0cd5 ("hv_netvsc: common detach logic")
Reported-by: Mohammed Gamal <mgamal@redhat.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/hyperv_net.h |  1 +
 drivers/net/hyperv/netvsc.c     |  6 ++++--
 drivers/net/hyperv/netvsc_drv.c | 32 ++++++++++++++++++++++++++------
 3 files changed, 31 insertions(+), 8 deletions(-)

diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 42d284669b03..31d8d83c25ac 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -970,6 +970,7 @@ struct netvsc_device {
 
 	wait_queue_head_t wait_drain;
 	bool destroy;
+	bool tx_disable; /* if true, do not wake up queue again */
 
 	/* Receive buffer allocated by us but manages by NetVSP */
 	void *recv_buf;
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 1a942feab954..fb12b63439c6 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -110,6 +110,7 @@ static struct netvsc_device *alloc_net_device(void)
 
 	init_waitqueue_head(&net_device->wait_drain);
 	net_device->destroy = false;
+	net_device->tx_disable = false;
 
 	net_device->max_pkt = RNDIS_MAX_PKT_DEFAULT;
 	net_device->pkt_align = RNDIS_PKT_ALIGN_DEFAULT;
@@ -716,7 +717,7 @@ static void netvsc_send_tx_complete(struct net_device *ndev,
 	} else {
 		struct netdev_queue *txq = netdev_get_tx_queue(ndev, q_idx);
 
-		if (netif_tx_queue_stopped(txq) &&
+		if (netif_tx_queue_stopped(txq) && !net_device->tx_disable &&
 		    (hv_get_avail_to_write_percent(&channel->outbound) >
 		     RING_AVAIL_PERCENT_HIWATER || queue_sends < 1)) {
 			netif_tx_wake_queue(txq);
@@ -871,7 +872,8 @@ static inline int netvsc_send_pkt(
 	} else if (ret == -EAGAIN) {
 		netif_tx_stop_queue(txq);
 		ndev_ctx->eth_stats.stop_queue++;
-		if (atomic_read(&nvchan->queue_sends) < 1) {
+		if (atomic_read(&nvchan->queue_sends) < 1 &&
+		    !net_device->tx_disable) {
 			netif_tx_wake_queue(txq);
 			ndev_ctx->eth_stats.wake_queue++;
 			ret = -ENOSPC;
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index c8320405c8f1..9d699bd5f715 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -109,6 +109,15 @@ static void netvsc_set_rx_mode(struct net_device *net)
 	rcu_read_unlock();
 }
 
+static void netvsc_tx_enable(struct netvsc_device *nvscdev,
+			     struct net_device *ndev)
+{
+	nvscdev->tx_disable = false;
+	virt_wmb(); /* ensure queue wake up mechanism is on */
+
+	netif_tx_wake_all_queues(ndev);
+}
+
 static int netvsc_open(struct net_device *net)
 {
 	struct net_device_context *ndev_ctx = netdev_priv(net);
@@ -129,7 +138,7 @@ static int netvsc_open(struct net_device *net)
 	rdev = nvdev->extension;
 	if (!rdev->link_state) {
 		netif_carrier_on(net);
-		netif_tx_wake_all_queues(net);
+		netvsc_tx_enable(nvdev, net);
 	}
 
 	if (vf_netdev) {
@@ -184,6 +193,17 @@ static int netvsc_wait_until_empty(struct netvsc_device *nvdev)
 	}
 }
 
+static void netvsc_tx_disable(struct netvsc_device *nvscdev,
+			      struct net_device *ndev)
+{
+	if (nvscdev) {
+		nvscdev->tx_disable = true;
+		virt_wmb(); /* ensure txq will not wake up after stop */
+	}
+
+	netif_tx_disable(ndev);
+}
+
 static int netvsc_close(struct net_device *net)
 {
 	struct net_device_context *net_device_ctx = netdev_priv(net);
@@ -192,7 +212,7 @@ static int netvsc_close(struct net_device *net)
 	struct netvsc_device *nvdev = rtnl_dereference(net_device_ctx->nvdev);
 	int ret;
 
-	netif_tx_disable(net);
+	netvsc_tx_disable(nvdev, net);
 
 	/* No need to close rndis filter if it is removed already */
 	if (!nvdev)
@@ -918,7 +938,7 @@ static int netvsc_detach(struct net_device *ndev,
 
 	/* If device was up (receiving) then shutdown */
 	if (netif_running(ndev)) {
-		netif_tx_disable(ndev);
+		netvsc_tx_disable(nvdev, ndev);
 
 		ret = rndis_filter_close(nvdev);
 		if (ret) {
@@ -1899,7 +1919,7 @@ static void netvsc_link_change(struct work_struct *w)
 		if (rdev->link_state) {
 			rdev->link_state = false;
 			netif_carrier_on(net);
-			netif_tx_wake_all_queues(net);
+			netvsc_tx_enable(net_device, net);
 		} else {
 			notify = true;
 		}
@@ -1909,7 +1929,7 @@ static void netvsc_link_change(struct work_struct *w)
 		if (!rdev->link_state) {
 			rdev->link_state = true;
 			netif_carrier_off(net);
-			netif_tx_stop_all_queues(net);
+			netvsc_tx_disable(net_device, net);
 		}
 		kfree(event);
 		break;
@@ -1918,7 +1938,7 @@ static void netvsc_link_change(struct work_struct *w)
 		if (!rdev->link_state) {
 			rdev->link_state = true;
 			netif_carrier_off(net);
-			netif_tx_stop_all_queues(net);
+			netvsc_tx_disable(net_device, net);
 			event->event = RNDIS_STATUS_MEDIA_CONNECT;
 			spin_lock_irqsave(&ndev_ctx->lock, flags);
 			list_add(&event->list, &ndev_ctx->reconfig_events);
-- 
2.20.1


From 10ae973d7ad2da967710c5ac2c31881d98c94cb7 Mon Sep 17 00:00:00 2001
From: Thomas Falcon <tlfalcon@linux.ibm.com>
Date: Thu, 4 Apr 2019 18:58:26 -0500
Subject: [PATCH 02/33] ibmvnic: Fix completion structure initialization

[ Upstream commit bbd669a868bba591ffd38b7bc75a7b361bb54b04 ]

Fix device initialization completion handling for vNIC adapters.
Initialize the completion structure on probe and reinitialize when needed.
This also fixes a race condition during kdump where the driver can attempt
to access the completion struct before it is initialized:

Unable to handle kernel paging request for data at address 0x00000000
Faulting instruction address: 0xc0000000081acbe0
Oops: Kernel access of bad area, sig: 11 [#1]
LE SMP NR_CPUS=2048 NUMA pSeries
Modules linked in: ibmvnic(+) ibmveth sunrpc overlay squashfs loop
CPU: 19 PID: 301 Comm: systemd-udevd Not tainted 4.18.0-64.el8.ppc64le #1
NIP:  c0000000081acbe0 LR: c0000000081ad964 CTR: c0000000081ad900
REGS: c000000027f3f990 TRAP: 0300   Not tainted  (4.18.0-64.el8.ppc64le)
MSR:  800000010280b033 <SF,VEC,VSX,EE,FP,ME,IR,DR,RI,LE,TM[E]> CR: 28228288  XER: 00000006
CFAR: c000000008008934 DAR: 0000000000000000 DSISR: 40000000 IRQMASK: 1
GPR00: c0000000081ad964 c000000027f3fc10 c0000000095b5800 c0000000221b4e58
GPR04: 0000000000000003 0000000000000001 000049a086918581 00000000000000d4
GPR08: 0000000000000007 0000000000000000 ffffffffffffffe8 d0000000014dde28
GPR12: c0000000081ad900 c000000009a00c00 0000000000000001 0000000000000100
GPR16: 0000000000000038 0000000000000007 c0000000095e2230 0000000000000006
GPR20: 0000000000400140 0000000000000001 c00000000910c880 0000000000000000
GPR24: 0000000000000000 0000000000000006 0000000000000000 0000000000000003
GPR28: 0000000000000001 0000000000000001 c0000000221b4e60 c0000000221b4e58
NIP [c0000000081acbe0] __wake_up_locked+0x50/0x100
LR [c0000000081ad964] complete+0x64/0xa0
Call Trace:
[c000000027f3fc10] [c000000027f3fc60] 0xc000000027f3fc60 (unreliable)
[c000000027f3fc60] [c0000000081ad964] complete+0x64/0xa0
[c000000027f3fca0] [d0000000014dad58] ibmvnic_handle_crq+0xce0/0x1160 [ibmvnic]
[c000000027f3fd50] [d0000000014db270] ibmvnic_tasklet+0x98/0x130 [ibmvnic]
[c000000027f3fda0] [c00000000813f334] tasklet_action_common.isra.3+0xc4/0x1a0
[c000000027f3fe00] [c000000008cd13f4] __do_softirq+0x164/0x400
[c000000027f3fef0] [c00000000813ed64] irq_exit+0x184/0x1c0
[c000000027f3ff20] [c0000000080188e8] __do_irq+0xb8/0x210
[c000000027f3ff90] [c00000000802d0a4] call_do_irq+0x14/0x24
[c000000026a5b010] [c000000008018adc] do_IRQ+0x9c/0x130
[c000000026a5b060] [c000000008008ce4] hardware_interrupt_common+0x114/0x120

Signed-off-by: Thomas Falcon <tlfalcon@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ibm/ibmvnic.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index c8704b1690eb..a475f36ddf8c 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -1888,6 +1888,7 @@ static int do_hard_reset(struct ibmvnic_adapter *adapter,
 	 */
 	adapter->state = VNIC_PROBED;
 
+	reinit_completion(&adapter->init_done);
 	rc = init_crq_queue(adapter);
 	if (rc) {
 		netdev_err(adapter->netdev,
@@ -4569,7 +4570,7 @@ static int ibmvnic_reset_init(struct ibmvnic_adapter *adapter)
 	old_num_rx_queues = adapter->req_rx_queues;
 	old_num_tx_queues = adapter->req_tx_queues;
 
-	init_completion(&adapter->init_done);
+	reinit_completion(&adapter->init_done);
 	adapter->init_done_rc = 0;
 	ibmvnic_send_crq_init(adapter);
 	if (!wait_for_completion_timeout(&adapter->init_done, timeout)) {
@@ -4624,7 +4625,6 @@ static int ibmvnic_init(struct ibmvnic_adapter *adapter)
 
 	adapter->from_passive_init = false;
 
-	init_completion(&adapter->init_done);
 	adapter->init_done_rc = 0;
 	ibmvnic_send_crq_init(adapter);
 	if (!wait_for_completion_timeout(&adapter->init_done, timeout)) {
@@ -4703,6 +4703,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	INIT_WORK(&adapter->ibmvnic_reset, __ibmvnic_reset);
 	INIT_LIST_HEAD(&adapter->rwi_list);
 	spin_lock_init(&adapter->rwi_lock);
+	init_completion(&adapter->init_done);
 	adapter->resetting = false;
 
 	adapter->mac_change_pending = false;
-- 
2.20.1


From e6a88205a0197b002205305fc8844346dcf80354 Mon Sep 17 00:00:00 2001
From: Sheena Mira-ato <sheena.mira-ato@alliedtelesis.co.nz>
Date: Mon, 1 Apr 2019 13:04:42 +1300
Subject: [PATCH 03/33] ip6_tunnel: Match to ARPHRD_TUNNEL6 for dev type

[ Upstream commit b2e54b09a3d29c4db883b920274ca8dca4d9f04d ]

The device type for ip6 tunnels is set to
ARPHRD_TUNNEL6. However, the ip4ip6_err function
is expecting the device type of the tunnel to be
ARPHRD_TUNNEL.  Since the device types do not
match, the function exits and the ICMP error
packet is not sent to the originating host. Note
that the device type for IPv4 tunnels is set to
ARPHRD_TUNNEL.

Fix is to expect a tunnel device type of
ARPHRD_TUNNEL6 instead.  Now the tunnel device
type matches and the ICMP error packet is sent
to the originating host.

Signed-off-by: Sheena Mira-ato <sheena.mira-ato@alliedtelesis.co.nz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 0c6403cf8b52..ade1390c6348 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -627,7 +627,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL,
 					   eiph->daddr, eiph->saddr, 0, 0,
 					   IPPROTO_IPIP, RT_TOS(eiph->tos), 0);
-		if (IS_ERR(rt) || rt->dst.dev->type != ARPHRD_TUNNEL) {
+		if (IS_ERR(rt) || rt->dst.dev->type != ARPHRD_TUNNEL6) {
 			if (!IS_ERR(rt))
 				ip_rt_put(rt);
 			goto out;
@@ -636,7 +636,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	} else {
 		if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos,
 				   skb2->dev) ||
-		    skb_dst(skb2)->dev->type != ARPHRD_TUNNEL)
+		    skb_dst(skb2)->dev->type != ARPHRD_TUNNEL6)
 			goto out;
 	}
 
-- 
2.20.1


From bc1b99b282916a48c937a0ac5a35827ede7c98b7 Mon Sep 17 00:00:00 2001
From: Junwei Hu <hujunwei4@huawei.com>
Date: Tue, 2 Apr 2019 19:38:04 +0800
Subject: [PATCH 04/33] ipv6: Fix dangling pointer when ipv6 fragment

[ Upstream commit ef0efcd3bd3fd0589732b67fb586ffd3c8705806 ]

At the beginning of ip6_fragment func, the prevhdr pointer is
obtained in the ip6_find_1stfragopt func.
However, all the pointers pointing into skb header may change
when calling skb_checksum_help func with
skb->ip_summed = CHECKSUM_PARTIAL condition.
The prevhdr pointe will be dangling if it is not reloaded after
calling __skb_linearize func in skb_checksum_help func.

Here, I add a variable, nexthdr_offset, to evaluate the offset,
which does not changes even after calling __skb_linearize func.

Fixes: 405c92f7a541 ("ipv6: add defensive check for CHECKSUM_PARTIAL skbs in ip_fragment")
Signed-off-by: Junwei Hu <hujunwei4@huawei.com>
Reported-by: Wenhao Zhang <zhangwenhao8@huawei.com>
Reported-by: syzbot+e8ce541d095e486074fc@syzkaller.appspotmail.com
Reviewed-by: Zhiqiang Liu <liuzhiqiang26@huawei.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_output.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 0bb87f3a10c7..eed9231c90ad 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -587,7 +587,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 				inet6_sk(skb->sk) : NULL;
 	struct ipv6hdr *tmp_hdr;
 	struct frag_hdr *fh;
-	unsigned int mtu, hlen, left, len;
+	unsigned int mtu, hlen, left, len, nexthdr_offset;
 	int hroom, troom;
 	__be32 frag_id;
 	int ptr, offset = 0, err = 0;
@@ -598,6 +598,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		goto fail;
 	hlen = err;
 	nexthdr = *prevhdr;
+	nexthdr_offset = prevhdr - skb_network_header(skb);
 
 	mtu = ip6_skb_dst_mtu(skb);
 
@@ -632,6 +633,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 	    (err = skb_checksum_help(skb)))
 		goto fail;
 
+	prevhdr = skb_network_header(skb) + nexthdr_offset;
 	hroom = LL_RESERVED_SPACE(rt->dst.dev);
 	if (skb_has_frag_list(skb)) {
 		unsigned int first_len = skb_pagelen(skb);
-- 
2.20.1


From eada46c4283f8b215bc90ff6e22fe4573f839aa1 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Thu, 4 Apr 2019 16:37:53 +0200
Subject: [PATCH 05/33] ipv6: sit: reset ip header pointer in ipip6_rcv

[ Upstream commit bb9bd814ebf04f579be466ba61fc922625508807 ]

ipip6 tunnels run iptunnel_pull_header on received skbs. This can
determine the following use-after-free accessing iph pointer since
the packet will be 'uncloned' running pskb_expand_head if it is a
cloned gso skb (e.g if the packet has been sent though a veth device)

[  706.369655] BUG: KASAN: use-after-free in ipip6_rcv+0x1678/0x16e0 [sit]
[  706.449056] Read of size 1 at addr ffffe01b6bd855f5 by task ksoftirqd/1/=
[  706.669494] Hardware name: HPE ProLiant m400 Server/ProLiant m400 Server, BIOS U02 08/19/2016
[  706.771839] Call trace:
[  706.801159]  dump_backtrace+0x0/0x2f8
[  706.845079]  show_stack+0x24/0x30
[  706.884833]  dump_stack+0xe0/0x11c
[  706.925629]  print_address_description+0x68/0x260
[  706.982070]  kasan_report+0x178/0x340
[  707.025995]  __asan_report_load1_noabort+0x30/0x40
[  707.083481]  ipip6_rcv+0x1678/0x16e0 [sit]
[  707.132623]  tunnel64_rcv+0xd4/0x200 [tunnel4]
[  707.185940]  ip_local_deliver_finish+0x3b8/0x988
[  707.241338]  ip_local_deliver+0x144/0x470
[  707.289436]  ip_rcv_finish+0x43c/0x14b0
[  707.335447]  ip_rcv+0x628/0x1138
[  707.374151]  __netif_receive_skb_core+0x1670/0x2600
[  707.432680]  __netif_receive_skb+0x28/0x190
[  707.482859]  process_backlog+0x1d0/0x610
[  707.529913]  net_rx_action+0x37c/0xf68
[  707.574882]  __do_softirq+0x288/0x1018
[  707.619852]  run_ksoftirqd+0x70/0xa8
[  707.662734]  smpboot_thread_fn+0x3a4/0x9e8
[  707.711875]  kthread+0x2c8/0x350
[  707.750583]  ret_from_fork+0x10/0x18

[  707.811302] Allocated by task 16982:
[  707.854182]  kasan_kmalloc.part.1+0x40/0x108
[  707.905405]  kasan_kmalloc+0xb4/0xc8
[  707.948291]  kasan_slab_alloc+0x14/0x20
[  707.994309]  __kmalloc_node_track_caller+0x158/0x5e0
[  708.053902]  __kmalloc_reserve.isra.8+0x54/0xe0
[  708.108280]  __alloc_skb+0xd8/0x400
[  708.150139]  sk_stream_alloc_skb+0xa4/0x638
[  708.200346]  tcp_sendmsg_locked+0x818/0x2b90
[  708.251581]  tcp_sendmsg+0x40/0x60
[  708.292376]  inet_sendmsg+0xf0/0x520
[  708.335259]  sock_sendmsg+0xac/0xf8
[  708.377096]  sock_write_iter+0x1c0/0x2c0
[  708.424154]  new_sync_write+0x358/0x4a8
[  708.470162]  __vfs_write+0xc4/0xf8
[  708.510950]  vfs_write+0x12c/0x3d0
[  708.551739]  ksys_write+0xcc/0x178
[  708.592533]  __arm64_sys_write+0x70/0xa0
[  708.639593]  el0_svc_handler+0x13c/0x298
[  708.686646]  el0_svc+0x8/0xc

[  708.739019] Freed by task 17:
[  708.774597]  __kasan_slab_free+0x114/0x228
[  708.823736]  kasan_slab_free+0x10/0x18
[  708.868703]  kfree+0x100/0x3d8
[  708.905320]  skb_free_head+0x7c/0x98
[  708.948204]  skb_release_data+0x320/0x490
[  708.996301]  pskb_expand_head+0x60c/0x970
[  709.044399]  __iptunnel_pull_header+0x3b8/0x5d0
[  709.098770]  ipip6_rcv+0x41c/0x16e0 [sit]
[  709.146873]  tunnel64_rcv+0xd4/0x200 [tunnel4]
[  709.200195]  ip_local_deliver_finish+0x3b8/0x988
[  709.255596]  ip_local_deliver+0x144/0x470
[  709.303692]  ip_rcv_finish+0x43c/0x14b0
[  709.349705]  ip_rcv+0x628/0x1138
[  709.388413]  __netif_receive_skb_core+0x1670/0x2600
[  709.446943]  __netif_receive_skb+0x28/0x190
[  709.497120]  process_backlog+0x1d0/0x610
[  709.544169]  net_rx_action+0x37c/0xf68
[  709.589131]  __do_softirq+0x288/0x1018

[  709.651938] The buggy address belongs to the object at ffffe01b6bd85580
                which belongs to the cache kmalloc-1024 of size 1024
[  709.804356] The buggy address is located 117 bytes inside of
                1024-byte region [ffffe01b6bd85580, ffffe01b6bd85980)
[  709.946340] The buggy address belongs to the page:
[  710.003824] page:ffff7ff806daf600 count:1 mapcount:0 mapping:ffffe01c4001f600 index:0x0
[  710.099914] flags: 0xfffff8000000100(slab)
[  710.149059] raw: 0fffff8000000100 dead000000000100 dead000000000200 ffffe01c4001f600
[  710.242011] raw: 0000000000000000 0000000000380038 00000001ffffffff 0000000000000000
[  710.334966] page dumped because: kasan: bad access detected

Fix it resetting iph pointer after iptunnel_pull_header

Fixes: a09a4c8dd1ec ("tunnels: Remove encapsulation offloads on decap")
Tested-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index de9aa5cb295c..8f6cf8e6b5c1 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -669,6 +669,10 @@ static int ipip6_rcv(struct sk_buff *skb)
 		    !net_eq(tunnel->net, dev_net(tunnel->dev))))
 			goto out;
 
+		/* skb can be uncloned in iptunnel_pull_header, so
+		 * old iph is no longer valid
+		 */
+		iph = (const struct iphdr *)skb_mac_header(skb);
 		err = IP_ECN_decapsulate(iph, skb);
 		if (unlikely(err)) {
 			if (log_ecn_error)
-- 
2.20.1


From 0b2625f12f6ae7bbf5031ae7a2090bf8811fbe5c Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jslaby@suse.cz>
Date: Fri, 29 Mar 2019 12:19:46 +0100
Subject: [PATCH 06/33] kcm: switch order of device registration to fix a crash

[ Upstream commit 3c446e6f96997f2a95bf0037ef463802162d2323 ]

When kcm is loaded while many processes try to create a KCM socket, a
crash occurs:
 BUG: unable to handle kernel NULL pointer dereference at 000000000000000e
 IP: mutex_lock+0x27/0x40 kernel/locking/mutex.c:240
 PGD 8000000016ef2067 P4D 8000000016ef2067 PUD 3d6e9067 PMD 0
 Oops: 0002 [#1] SMP KASAN PTI
 CPU: 0 PID: 7005 Comm: syz-executor.5 Not tainted 4.12.14-396-default #1 SLE15-SP1 (unreleased)
 RIP: 0010:mutex_lock+0x27/0x40 kernel/locking/mutex.c:240
 RSP: 0018:ffff88000d487a00 EFLAGS: 00010246
 RAX: 0000000000000000 RBX: 000000000000000e RCX: 1ffff100082b0719
 ...
 CR2: 000000000000000e CR3: 000000004b1bc003 CR4: 0000000000060ef0
 Call Trace:
  kcm_create+0x600/0xbf0 [kcm]
  __sock_create+0x324/0x750 net/socket.c:1272
 ...

This is due to race between sock_create and unfinished
register_pernet_device. kcm_create tries to do "net_generic(net,
kcm_net_id)". but kcm_net_id is not initialized yet.

So switch the order of the two to close the race.

This can be reproduced with mutiple processes doing socket(PF_KCM, ...)
and one process doing module removal.

Fixes: ab7ac4eb9832 ("kcm: Kernel Connection Multiplexor module")
Reviewed-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/kcm/kcmsock.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 571d824e4e24..b919db02c7f9 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -2054,14 +2054,14 @@ static int __init kcm_init(void)
 	if (err)
 		goto fail;
 
-	err = sock_register(&kcm_family_ops);
-	if (err)
-		goto sock_register_fail;
-
 	err = register_pernet_device(&kcm_net_ops);
 	if (err)
 		goto net_ops_fail;
 
+	err = sock_register(&kcm_family_ops);
+	if (err)
+		goto sock_register_fail;
+
 	err = kcm_proc_init();
 	if (err)
 		goto proc_init_fail;
@@ -2069,12 +2069,12 @@ static int __init kcm_init(void)
 	return 0;
 
 proc_init_fail:
-	unregister_pernet_device(&kcm_net_ops);
-
-net_ops_fail:
 	sock_unregister(PF_KCM);
 
 sock_register_fail:
+	unregister_pernet_device(&kcm_net_ops);
+
+net_ops_fail:
 	proto_unregister(&kcm_proto);
 
 fail:
@@ -2090,8 +2090,8 @@ static int __init kcm_init(void)
 static void __exit kcm_exit(void)
 {
 	kcm_proc_exit();
-	unregister_pernet_device(&kcm_net_ops);
 	sock_unregister(PF_KCM);
+	unregister_pernet_device(&kcm_net_ops);
 	proto_unregister(&kcm_proto);
 	destroy_workqueue(kcm_wq);
 
-- 
2.20.1


From 6dab0dc78a7ce96d43d32b0ac2973b491301b860 Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Fri, 29 Mar 2019 09:18:02 +0800
Subject: [PATCH 07/33] net: ethtool: not call vzalloc for zero sized memory
 request

[ Upstream commit 3d8830266ffc28c16032b859e38a0252e014b631 ]

NULL or ZERO_SIZE_PTR will be returned for zero sized memory
request, and derefencing them will lead to a segfault

so it is unnecessory to call vzalloc for zero sized memory
request and not call functions which maybe derefence the
NULL allocated memory

this also fixes a possible memory leak if phy_ethtool_get_stats
returns error, memory should be freed before exit

Signed-off-by: Li RongQing <lirongqing@baidu.com>
Reviewed-by: Wang Li <wangli39@baidu.com>
Reviewed-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/ethtool.c | 46 ++++++++++++++++++++++++++++++----------------
 1 file changed, 30 insertions(+), 16 deletions(-)

diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index aeabc4831fca..7cc97f43f138 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -1863,11 +1863,16 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr)
 	WARN_ON_ONCE(!ret);
 
 	gstrings.len = ret;
-	data = vzalloc(array_size(gstrings.len, ETH_GSTRING_LEN));
-	if (gstrings.len && !data)
-		return -ENOMEM;
 
-	__ethtool_get_strings(dev, gstrings.string_set, data);
+	if (gstrings.len) {
+		data = vzalloc(array_size(gstrings.len, ETH_GSTRING_LEN));
+		if (!data)
+			return -ENOMEM;
+
+		__ethtool_get_strings(dev, gstrings.string_set, data);
+	} else {
+		data = NULL;
+	}
 
 	ret = -EFAULT;
 	if (copy_to_user(useraddr, &gstrings, sizeof(gstrings)))
@@ -1963,11 +1968,15 @@ static int ethtool_get_stats(struct net_device *dev, void __user *useraddr)
 		return -EFAULT;
 
 	stats.n_stats = n_stats;
-	data = vzalloc(array_size(n_stats, sizeof(u64)));
-	if (n_stats && !data)
-		return -ENOMEM;
 
-	ops->get_ethtool_stats(dev, &stats, data);
+	if (n_stats) {
+		data = vzalloc(array_size(n_stats, sizeof(u64)));
+		if (!data)
+			return -ENOMEM;
+		ops->get_ethtool_stats(dev, &stats, data);
+	} else {
+		data = NULL;
+	}
 
 	ret = -EFAULT;
 	if (copy_to_user(useraddr, &stats, sizeof(stats)))
@@ -2007,16 +2016,21 @@ static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr)
 		return -EFAULT;
 
 	stats.n_stats = n_stats;
-	data = vzalloc(array_size(n_stats, sizeof(u64)));
-	if (n_stats && !data)
-		return -ENOMEM;
 
-	if (dev->phydev && !ops->get_ethtool_phy_stats) {
-		ret = phy_ethtool_get_stats(dev->phydev, &stats, data);
-		if (ret < 0)
-			return ret;
+	if (n_stats) {
+		data = vzalloc(array_size(n_stats, sizeof(u64)));
+		if (!data)
+			return -ENOMEM;
+
+		if (dev->phydev && !ops->get_ethtool_phy_stats) {
+			ret = phy_ethtool_get_stats(dev->phydev, &stats, data);
+			if (ret < 0)
+				goto out;
+		} else {
+			ops->get_ethtool_phy_stats(dev, &stats, data);
+		}
 	} else {
-		ops->get_ethtool_phy_stats(dev, &stats, data);
+		data = NULL;
 	}
 
 	ret = -EFAULT;
-- 
2.20.1


From 07d7294211cde3641ddb70ebef70d89dc85b1e48 Mon Sep 17 00:00:00 2001
From: Steffen Klassert <steffen.klassert@secunet.com>
Date: Tue, 2 Apr 2019 08:16:03 +0200
Subject: [PATCH 08/33] net-gro: Fix GRO flush when receiving a GSO packet.

[ Upstream commit 0ab03f353d3613ea49d1f924faf98559003670a8 ]

Currently we may merge incorrectly a received GSO packet
or a packet with frag_list into a packet sitting in the
gro_hash list. skb_segment() may crash case because
the assumptions on the skb layout are not met.
The correct behaviour would be to flush the packet in the
gro_hash list and send the received GSO packet directly
afterwards. Commit d61d072e87c8e ("net-gro: avoid reorders")
sets NAPI_GRO_CB(skb)->flush in this case, but this is not
checked before merging. This patch makes sure to check this
flag and to not merge in that case.

Fixes: d61d072e87c8e ("net-gro: avoid reorders")
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 8656b1e20d35..ceee28e184af 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3832,7 +3832,7 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
 	unsigned int delta_truesize;
 	struct sk_buff *lp;
 
-	if (unlikely(p->len + len >= 65536))
+	if (unlikely(p->len + len >= 65536 || NAPI_GRO_CB(skb)->flush))
 		return -E2BIG;
 
 	lp = NAPI_GRO_CB(p)->last;
-- 
2.20.1


From b916d41773245b4f25fb3c013f89b4c870a88d26 Mon Sep 17 00:00:00 2001
From: Artemy Kovalyov <artemyko@mellanox.com>
Date: Tue, 19 Mar 2019 11:24:38 +0200
Subject: [PATCH 09/33] net/mlx5: Decrease default mr cache size

[ Upstream commit e8b26b2135dedc0284490bfeac06dfc4418d0105 ]

Delete initialization of high order entries in mr cache to decrease initial
memory footprint. When required, the administrator can populate the
entries with memory keys via the /sys interface.

This approach is very helpful to significantly reduce the per HW function
memory footprint in virtualization environments such as SRIOV.

Fixes: 9603b61de1ee ("mlx5: Move pci device handling from mlx5_ib to mlx5_core")
Signed-off-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reported-by:  Shalom Toledo <shalomt@mellanox.com>
Acked-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/main.c    | 20 -------------------
 1 file changed, 20 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 563ce3fedab4..0e820cf92f8a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -162,26 +162,6 @@ static struct mlx5_profile profile[] = {
 			.size	= 8,
 			.limit	= 4
 		},
-		.mr_cache[16]	= {
-			.size	= 8,
-			.limit	= 4
-		},
-		.mr_cache[17]	= {
-			.size	= 8,
-			.limit	= 4
-		},
-		.mr_cache[18]	= {
-			.size	= 8,
-			.limit	= 4
-		},
-		.mr_cache[19]	= {
-			.size	= 4,
-			.limit	= 2
-		},
-		.mr_cache[20]	= {
-			.size	= 4,
-			.limit	= 2
-		},
 	},
 };
 
-- 
2.20.1


From 1429b7b7ce4a4171b1a64ecfba86fe5aa8e9d338 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 27 Mar 2019 08:21:30 -0700
Subject: [PATCH 10/33] netns: provide pure entropy for net_hash_mix()

[ Upstream commit 355b98553789b646ed97ad801a619ff898471b92 ]

net_hash_mix() currently uses kernel address of a struct net,
and is used in many places that could be used to reveal this
address to a patient attacker, thus defeating KASLR, for
the typical case (initial net namespace, &init_net is
not dynamically allocated)

I believe the original implementation tried to avoid spending
too many cycles in this function, but security comes first.

Also provide entropy regardless of CONFIG_NET_NS.

Fixes: 0b4419162aa6 ("netns: introduce the net_hash_mix "salt" for hashes")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Amit Klein <aksecurity@gmail.com>
Reported-by: Benny Pinkas <benny@pinkas.net>
Cc: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/net_namespace.h |  1 +
 include/net/netns/hash.h    | 10 ++--------
 net/core/net_namespace.c    |  1 +
 3 files changed, 4 insertions(+), 8 deletions(-)

diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 9b5fdc50519a..3f7b166262d7 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -57,6 +57,7 @@ struct net {
 						 */
 	spinlock_t		rules_mod_lock;
 
+	u32			hash_mix;
 	atomic64_t		cookie_gen;
 
 	struct list_head	list;		/* list of network namespaces */
diff --git a/include/net/netns/hash.h b/include/net/netns/hash.h
index 16a842456189..d9b665151f3d 100644
--- a/include/net/netns/hash.h
+++ b/include/net/netns/hash.h
@@ -2,16 +2,10 @@
 #ifndef __NET_NS_HASH_H__
 #define __NET_NS_HASH_H__
 
-#include <asm/cache.h>
-
-struct net;
+#include <net/net_namespace.h>
 
 static inline u32 net_hash_mix(const struct net *net)
 {
-#ifdef CONFIG_NET_NS
-	return (u32)(((unsigned long)net) >> ilog2(sizeof(*net)));
-#else
-	return 0;
-#endif
+	return net->hash_mix;
 }
 #endif
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 670c84b1bfc2..7320f0844a50 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -304,6 +304,7 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns)
 
 	refcount_set(&net->count, 1);
 	refcount_set(&net->passive, 1);
+	get_random_bytes(&net->hash_mix, sizeof(u32));
 	net->dev_base_seq = 1;
 	net->user_ns = user_ns;
 	idr_init(&net->netns_ids);
-- 
2.20.1


From 633ffb1a4dec0bf175bf8ec351aeccfc8314cde8 Mon Sep 17 00:00:00 2001
From: Mao Wenan <maowenan@huawei.com>
Date: Thu, 28 Mar 2019 17:10:56 +0800
Subject: [PATCH 11/33] net: rds: force to destroy connection if t_sock is NULL
 in rds_tcp_kill_sock().

[ Upstream commit cb66ddd156203daefb8d71158036b27b0e2caf63 ]

When it is to cleanup net namespace, rds_tcp_exit_net() will call
rds_tcp_kill_sock(), if t_sock is NULL, it will not call
rds_conn_destroy(), rds_conn_path_destroy() and rds_tcp_conn_free() to free
connection, and the worker cp_conn_w is not stopped, afterwards the net is freed in
net_drop_ns(); While cp_conn_w rds_connect_worker() will call rds_tcp_conn_path_connect()
and reference 'net' which has already been freed.

In rds_tcp_conn_path_connect(), rds_tcp_set_callbacks() will set t_sock = sock before
sock->ops->connect, but if connect() is failed, it will call
rds_tcp_restore_callbacks() and set t_sock = NULL, if connect is always
failed, rds_connect_worker() will try to reconnect all the time, so
rds_tcp_kill_sock() will never to cancel worker cp_conn_w and free the
connections.

Therefore, the condition !tc->t_sock is not needed if it is going to do
cleanup_net->rds_tcp_exit_net->rds_tcp_kill_sock, because tc->t_sock is always
NULL, and there is on other path to cancel cp_conn_w and free
connection. So this patch is to fix this.

rds_tcp_kill_sock():
...
if (net != c_net || !tc->t_sock)
...
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>

==================================================================
BUG: KASAN: use-after-free in inet_create+0xbcc/0xd28
net/ipv4/af_inet.c:340
Read of size 4 at addr ffff8003496a4684 by task kworker/u8:4/3721

CPU: 3 PID: 3721 Comm: kworker/u8:4 Not tainted 5.1.0 #11
Hardware name: linux,dummy-virt (DT)
Workqueue: krdsd rds_connect_worker
Call trace:
 dump_backtrace+0x0/0x3c0 arch/arm64/kernel/time.c:53
 show_stack+0x28/0x38 arch/arm64/kernel/traps.c:152
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x120/0x188 lib/dump_stack.c:113
 print_address_description+0x68/0x278 mm/kasan/report.c:253
 kasan_report_error mm/kasan/report.c:351 [inline]
 kasan_report+0x21c/0x348 mm/kasan/report.c:409
 __asan_report_load4_noabort+0x30/0x40 mm/kasan/report.c:429
 inet_create+0xbcc/0xd28 net/ipv4/af_inet.c:340
 __sock_create+0x4f8/0x770 net/socket.c:1276
 sock_create_kern+0x50/0x68 net/socket.c:1322
 rds_tcp_conn_path_connect+0x2b4/0x690 net/rds/tcp_connect.c:114
 rds_connect_worker+0x108/0x1d0 net/rds/threads.c:175
 process_one_work+0x6e8/0x1700 kernel/workqueue.c:2153
 worker_thread+0x3b0/0xdd0 kernel/workqueue.c:2296
 kthread+0x2f0/0x378 kernel/kthread.c:255
 ret_from_fork+0x10/0x18 arch/arm64/kernel/entry.S:1117

Allocated by task 687:
 save_stack mm/kasan/kasan.c:448 [inline]
 set_track mm/kasan/kasan.c:460 [inline]
 kasan_kmalloc+0xd4/0x180 mm/kasan/kasan.c:553
 kasan_slab_alloc+0x14/0x20 mm/kasan/kasan.c:490
 slab_post_alloc_hook mm/slab.h:444 [inline]
 slab_alloc_node mm/slub.c:2705 [inline]
 slab_alloc mm/slub.c:2713 [inline]
 kmem_cache_alloc+0x14c/0x388 mm/slub.c:2718
 kmem_cache_zalloc include/linux/slab.h:697 [inline]
 net_alloc net/core/net_namespace.c:384 [inline]
 copy_net_ns+0xc4/0x2d0 net/core/net_namespace.c:424
 create_new_namespaces+0x300/0x658 kernel/nsproxy.c:107
 unshare_nsproxy_namespaces+0xa0/0x198 kernel/nsproxy.c:206
 ksys_unshare+0x340/0x628 kernel/fork.c:2577
 __do_sys_unshare kernel/fork.c:2645 [inline]
 __se_sys_unshare kernel/fork.c:2643 [inline]
 __arm64_sys_unshare+0x38/0x58 kernel/fork.c:2643
 __invoke_syscall arch/arm64/kernel/syscall.c:35 [inline]
 invoke_syscall arch/arm64/kernel/syscall.c:47 [inline]
 el0_svc_common+0x168/0x390 arch/arm64/kernel/syscall.c:83
 el0_svc_handler+0x60/0xd0 arch/arm64/kernel/syscall.c:129
 el0_svc+0x8/0xc arch/arm64/kernel/entry.S:960

Freed by task 264:
 save_stack mm/kasan/kasan.c:448 [inline]
 set_track mm/kasan/kasan.c:460 [inline]
 __kasan_slab_free+0x114/0x220 mm/kasan/kasan.c:521
 kasan_slab_free+0x10/0x18 mm/kasan/kasan.c:528
 slab_free_hook mm/slub.c:1370 [inline]
 slab_free_freelist_hook mm/slub.c:1397 [inline]
 slab_free mm/slub.c:2952 [inline]
 kmem_cache_free+0xb8/0x3a8 mm/slub.c:2968
 net_free net/core/net_namespace.c:400 [inline]
 net_drop_ns.part.6+0x78/0x90 net/core/net_namespace.c:407
 net_drop_ns net/core/net_namespace.c:406 [inline]
 cleanup_net+0x53c/0x6d8 net/core/net_namespace.c:569
 process_one_work+0x6e8/0x1700 kernel/workqueue.c:2153
 worker_thread+0x3b0/0xdd0 kernel/workqueue.c:2296
 kthread+0x2f0/0x378 kernel/kthread.c:255
 ret_from_fork+0x10/0x18 arch/arm64/kernel/entry.S:1117

The buggy address belongs to the object at ffff8003496a3f80
 which belongs to the cache net_namespace of size 7872
The buggy address is located 1796 bytes inside of
 7872-byte region [ffff8003496a3f80, ffff8003496a5e40)
The buggy address belongs to the page:
page:ffff7e000d25a800 count:1 mapcount:0 mapping:ffff80036ce4b000
index:0x0 compound_mapcount: 0
flags: 0xffffe0000008100(slab|head)
raw: 0ffffe0000008100 dead000000000100 dead000000000200 ffff80036ce4b000
raw: 0000000000000000 0000000080040004 00000001ffffffff 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff8003496a4580: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff8003496a4600: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff8003496a4680: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                   ^
 ffff8003496a4700: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff8003496a4780: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
==================================================================

Fixes: 467fa15356ac("RDS-TCP: Support multiple RDS-TCP listen endpoints, one per netns.")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Mao Wenan <maowenan@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/tcp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index b9bbcf3d6c63..18bb522df282 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -600,7 +600,7 @@ static void rds_tcp_kill_sock(struct net *net)
 	list_for_each_entry_safe(tc, _tc, &rds_tcp_conn_list, t_tcp_node) {
 		struct net *c_net = read_pnet(&tc->t_cpath->cp_conn->c_net);
 
-		if (net != c_net || !tc->t_sock)
+		if (net != c_net)
 			continue;
 		if (!list_has_conn(&tmp_list, tc->t_cpath->cp_conn)) {
 			list_move_tail(&tc->t_tcp_node, &tmp_list);
-- 
2.20.1


From 391dcdc27173625049067a17a64a485c037aa58a Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Thu, 4 Apr 2019 12:31:35 +0200
Subject: [PATCH 12/33] net/sched: act_sample: fix divide by zero in the
 traffic path

[ Upstream commit fae2708174ae95d98d19f194e03d6e8f688ae195 ]

the control path of 'sample' action does not validate the value of 'rate'
provided by the user, but then it uses it as divisor in the traffic path.
Validate it in tcf_sample_init(), and return -EINVAL with a proper extack
message in case that value is zero, to fix a splat with the script below:

 # tc f a dev test0 egress matchall action sample rate 0 group 1 index 2
 # tc -s a s action sample
 total acts 1

         action order 0: sample rate 1/0 group 1 pipe
          index 2 ref 1 bind 1 installed 19 sec used 19 sec
         Action statistics:
         Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
         backlog 0b 0p requeues 0
 # ping 192.0.2.1 -I test0 -c1 -q

 divide error: 0000 [#1] SMP PTI
 CPU: 1 PID: 6192 Comm: ping Not tainted 5.1.0-rc2.diag2+ #591
 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
 RIP: 0010:tcf_sample_act+0x9e/0x1e0 [act_sample]
 Code: 6a f1 85 c0 74 0d 80 3d 83 1a 00 00 00 0f 84 9c 00 00 00 4d 85 e4 0f 84 85 00 00 00 e8 9b d7 9c f1 44 8b 8b e0 00 00 00 31 d2 <41> f7 f1 85 d2 75 70 f6 85 83 00 00 00 10 48 8b 45 10 8b 88 08 01
 RSP: 0018:ffffae320190ba30 EFLAGS: 00010246
 RAX: 00000000b0677d21 RBX: ffff8af1ed9ec000 RCX: 0000000059a9fe49
 RDX: 0000000000000000 RSI: 000000000c7e33b7 RDI: ffff8af23daa0af0
 RBP: ffff8af1ee11b200 R08: 0000000074fcaf7e R09: 0000000000000000
 R10: 0000000000000050 R11: ffffffffb3088680 R12: ffff8af232307f80
 R13: 0000000000000003 R14: ffff8af1ed9ec000 R15: 0000000000000000
 FS:  00007fe9c6d2f740(0000) GS:ffff8af23da80000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 00007fff6772f000 CR3: 00000000746a2004 CR4: 00000000001606e0
 Call Trace:
  tcf_action_exec+0x7c/0x1c0
  tcf_classify+0x57/0x160
  __dev_queue_xmit+0x3dc/0xd10
  ip_finish_output2+0x257/0x6d0
  ip_output+0x75/0x280
  ip_send_skb+0x15/0x40
  raw_sendmsg+0xae3/0x1410
  sock_sendmsg+0x36/0x40
  __sys_sendto+0x10e/0x140
  __x64_sys_sendto+0x24/0x30
  do_syscall_64+0x60/0x210
  entry_SYSCALL_64_after_hwframe+0x49/0xbe
  [...]
  Kernel panic - not syncing: Fatal exception in interrupt

Add a TDC selftest to document that 'rate' is now being validated.

Reported-by: Matteo Croce <mcroce@redhat.com>
Fixes: 5c5670fae430 ("net/sched: Introduce sample tc action")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Yotam Gigi <yotam.gi@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_sample.c                        | 10 ++++++--
 .../tc-testing/tc-tests/actions/sample.json   | 24 +++++++++++++++++++
 2 files changed, 32 insertions(+), 2 deletions(-)

diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 6b67aa13d2dd..c7f5d630d97c 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -43,8 +43,8 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 	struct tc_action_net *tn = net_generic(net, sample_net_id);
 	struct nlattr *tb[TCA_SAMPLE_MAX + 1];
 	struct psample_group *psample_group;
+	u32 psample_group_num, rate;
 	struct tc_sample *parm;
-	u32 psample_group_num;
 	struct tcf_sample *s;
 	bool exists = false;
 	int ret, err;
@@ -80,6 +80,12 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 		return -EEXIST;
 	}
 
+	rate = nla_get_u32(tb[TCA_SAMPLE_RATE]);
+	if (!rate) {
+		NL_SET_ERR_MSG(extack, "invalid sample rate");
+		tcf_idr_release(*a, bind);
+		return -EINVAL;
+	}
 	psample_group_num = nla_get_u32(tb[TCA_SAMPLE_PSAMPLE_GROUP]);
 	psample_group = psample_group_get(net, psample_group_num);
 	if (!psample_group) {
@@ -91,7 +97,7 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 
 	spin_lock_bh(&s->tcf_lock);
 	s->tcf_action = parm->action;
-	s->rate = nla_get_u32(tb[TCA_SAMPLE_RATE]);
+	s->rate = rate;
 	s->psample_group_num = psample_group_num;
 	RCU_INIT_POINTER(s->psample_group, psample_group);
 
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json b/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json
index 3aca33c00039..618def9bdf0e 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json
@@ -143,6 +143,30 @@
             "$TC actions flush action sample"
         ]
     },
+    {
+        "id": "7571",
+        "name": "Add sample action with invalid rate",
+        "category": [
+            "actions",
+            "sample"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action sample",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action sample rate 0 group 1 index 2",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action sample index 2",
+        "matchPattern": "action order [0-9]+: sample rate 1/0 group 1.*index 2 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action sample"
+        ]
+    },
     {
         "id": "b6d4",
         "name": "Add sample action with mandatory arguments and invalid control action",
-- 
2.20.1


From 787b80bce83b2db1706fd82c3b96d5a41928d073 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Thu, 28 Mar 2019 10:35:06 +0100
Subject: [PATCH 13/33] net/sched: fix ->get helper of the matchall cls

[ Upstream commit 0db6f8befc32c68bb13d7ffbb2e563c79e913e13 ]

It returned always NULL, thus it was never possible to get the filter.

Example:
$ ip link add foo type dummy
$ ip link add bar type dummy
$ tc qdisc add dev foo clsact
$ tc filter add dev foo protocol all pref 1 ingress handle 1234 \
	matchall action mirred ingress mirror dev bar

Before the patch:
$ tc filter get dev foo protocol all pref 1 ingress handle 1234 matchall
Error: Specified filter handle not found.
We have an error talking to the kernel

After:
$ tc filter get dev foo protocol all pref 1 ingress handle 1234 matchall
filter ingress protocol all pref 1 matchall chain 0 handle 0x4d2
  not_in_hw
        action order 1: mirred (Ingress Mirror to device bar) pipe
        index 1 ref 1 bind 1

CC: Yotam Gigi <yotamg@mellanox.com>
CC: Jiri Pirko <jiri@mellanox.com>
Fixes: fd62d9f5c575 ("net/sched: matchall: Fix configuration race")
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_matchall.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index 856fa79d4ffd..621bc1d5b057 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -126,6 +126,11 @@ static void mall_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack)
 
 static void *mall_get(struct tcf_proto *tp, u32 handle)
 {
+	struct cls_mall_head *head = rtnl_dereference(tp->root);
+
+	if (head && head->handle == handle)
+		return head;
+
 	return NULL;
 }
 
-- 
2.20.1


From 648b2da8369afe23669b8822ace61a3916f29306 Mon Sep 17 00:00:00 2001
From: Andrea Righi <andrea.righi@canonical.com>
Date: Thu, 28 Mar 2019 07:36:00 +0100
Subject: [PATCH 14/33] openvswitch: fix flow actions reallocation

[ Upstream commit f28cd2af22a0c134e4aa1c64a70f70d815d473fb ]

The flow action buffer can be resized if it's not big enough to contain
all the requested flow actions. However, this resize doesn't take into
account the new requested size, the buffer is only increased by a factor
of 2x. This might be not enough to contain the new data, causing a
buffer overflow, for example:

[   42.044472] =============================================================================
[   42.045608] BUG kmalloc-96 (Not tainted): Redzone overwritten
[   42.046415] -----------------------------------------------------------------------------

[   42.047715] Disabling lock debugging due to kernel taint
[   42.047716] INFO: 0x8bf2c4a5-0x720c0928. First byte 0x0 instead of 0xcc
[   42.048677] INFO: Slab 0xbc6d2040 objects=29 used=18 fp=0xdc07dec4 flags=0x2808101
[   42.049743] INFO: Object 0xd53a3464 @offset=2528 fp=0xccdcdebb

[   42.050747] Redzone 76f1b237: cc cc cc cc cc cc cc cc                          ........
[   42.051839] Object d53a3464: 6b 6b 6b 6b 6b 6b 6b 6b 0c 00 00 00 6c 00 00 00  kkkkkkkk....l...
[   42.053015] Object f49a30cc: 6c 00 0c 00 00 00 00 00 00 00 00 03 78 a3 15 f6  l...........x...
[   42.054203] Object acfe4220: 20 00 02 00 ff ff ff ff 00 00 00 00 00 00 00 00   ...............
[   42.055370] Object 21024e91: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
[   42.056541] Object 070e04c3: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
[   42.057797] Object 948a777a: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
[   42.059061] Redzone 8bf2c4a5: 00 00 00 00                                      ....
[   42.060189] Padding a681b46e: 5a 5a 5a 5a 5a 5a 5a 5a                          ZZZZZZZZ

Fix by making sure the new buffer is properly resized to contain all the
requested data.

BugLink: https://bugs.launchpad.net/bugs/1813244
Signed-off-by: Andrea Righi <andrea.righi@canonical.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/flow_netlink.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index c7b6010b2c09..eab5e8eaddaa 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -2306,14 +2306,14 @@ static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa,
 
 	struct sw_flow_actions *acts;
 	int new_acts_size;
-	int req_size = NLA_ALIGN(attr_len);
+	size_t req_size = NLA_ALIGN(attr_len);
 	int next_offset = offsetof(struct sw_flow_actions, actions) +
 					(*sfa)->actions_len;
 
 	if (req_size <= (ksize(*sfa) - next_offset))
 		goto out;
 
-	new_acts_size = ksize(*sfa) * 2;
+	new_acts_size = max(next_offset + req_size, ksize(*sfa) * 2);
 
 	if (new_acts_size > MAX_ACTIONS_BUFSIZE) {
 		if ((MAX_ACTIONS_BUFSIZE - next_offset) < req_size) {
-- 
2.20.1


From e914ff629c46859e8799bef5d93cc89219d6db00 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Wed, 27 Mar 2019 15:26:01 +0100
Subject: [PATCH 15/33] qmi_wwan: add Olicard 600
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 6289d0facd9ebce4cc83e5da39e15643ee998dc5 ]

This is a Qualcomm based device with a QMI function on interface 4.
It is mode switched from 2020:2030 using a standard eject message.

T:  Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#=  6 Spd=480  MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=2020 ProdID=2031 Rev= 2.32
S:  Manufacturer=Mobile Connect
S:  Product=Mobile Connect
S:  SerialNumber=0123456789ABCDEF
C:* #Ifs= 6 Cfg#= 1 Atr=80 MxPwr=500mA
I:* If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none)
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=(none)
E:  Ad=83(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=(none)
E:  Ad=85(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=(none)
E:  Ad=87(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none)
E:  Ad=89(I) Atr=03(Int.) MxPS=   8 Ivl=32ms
E:  Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 5 Alt= 0 #EPs= 2 Cls=08(stor.) Sub=06 Prot=50 Driver=(none)
E:  Ad=8a(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=06(O) Atr=02(Bulk) MxPS= 512 Ivl=125us

Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 74bebbdb4b15..9195f3476b1d 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1203,6 +1203,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x19d2, 0x2002, 4)},	/* ZTE (Vodafone) K3765-Z */
 	{QMI_FIXED_INTF(0x2001, 0x7e19, 4)},	/* D-Link DWM-221 B1 */
 	{QMI_FIXED_INTF(0x2001, 0x7e35, 4)},	/* D-Link DWM-222 */
+	{QMI_FIXED_INTF(0x2020, 0x2031, 4)},	/* Olicard 600 */
 	{QMI_FIXED_INTF(0x2020, 0x2033, 4)},	/* BroadMobi BM806U */
 	{QMI_FIXED_INTF(0x0f3d, 0x68a2, 8)},    /* Sierra Wireless MC7700 */
 	{QMI_FIXED_INTF(0x114f, 0x68a2, 8)},    /* Sierra Wireless MC7750 */
-- 
2.20.1


From ea36bd6dca72e29a561aecefff279701671efc79 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 5 Apr 2019 20:46:46 +0200
Subject: [PATCH 16/33] r8169: disable ASPM again

[ Upstream commit b75bb8a5b755d0c7bf1ac071e4df2349a7644a1e ]

There's a significant number of reports that re-enabling ASPM causes
different issues, ranging from decreased performance to system not
booting at all. This affects only a minority of users, but the number
of affected users is big enough that we better switch off ASPM again.

This will hurt notebook users who are not affected by the issues, they
may see decreased battery runtime w/o ASPM. With the PCI core folks is
being discussed to add generic sysfs attributes to control ASPM.
Once this is in place brave enough users can re-enable ASPM on their
system.

Fixes: a99790bf5c7f ("r8169: Reinstate ASPM Support")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 5f45ffeeecb4..1d24884e9897 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -28,6 +28,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/firmware.h>
 #include <linux/prefetch.h>
+#include <linux/pci-aspm.h>
 #include <linux/ipv6.h>
 #include <net/ip6_checksum.h>
 
@@ -7324,6 +7325,11 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 			return rc;
 	}
 
+	/* Disable ASPM completely as that cause random device stop working
+	 * problems as well as full system hangs for some PCIe devices users.
+	 */
+	pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1);
+
 	/* enable device (incl. PCI PM wakeup and hotplug setup) */
 	rc = pcim_enable_device(pdev);
 	if (rc < 0) {
-- 
2.20.1


From 0ebcd69cfaf7bcc07b44e8382a506f3ff40fad68 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 31 Mar 2019 16:58:15 +0800
Subject: [PATCH 17/33] sctp: initialize _pad of sockaddr_in before copying to
 user memory

[ Upstream commit 09279e615c81ce55e04835970601ae286e3facbe ]

Syzbot report a kernel-infoleak:

  BUG: KMSAN: kernel-infoleak in _copy_to_user+0x16b/0x1f0 lib/usercopy.c:32
  Call Trace:
    _copy_to_user+0x16b/0x1f0 lib/usercopy.c:32
    copy_to_user include/linux/uaccess.h:174 [inline]
    sctp_getsockopt_peer_addrs net/sctp/socket.c:5911 [inline]
    sctp_getsockopt+0x1668e/0x17f70 net/sctp/socket.c:7562
    ...
  Uninit was stored to memory at:
    sctp_transport_init net/sctp/transport.c:61 [inline]
    sctp_transport_new+0x16d/0x9a0 net/sctp/transport.c:115
    sctp_assoc_add_peer+0x532/0x1f70 net/sctp/associola.c:637
    sctp_process_param net/sctp/sm_make_chunk.c:2548 [inline]
    sctp_process_init+0x1a1b/0x3ed0 net/sctp/sm_make_chunk.c:2361
    ...
  Bytes 8-15 of 16 are uninitialized

It was caused by that th _pad field (the 8-15 bytes) of a v4 addr (saved in
struct sockaddr_in) wasn't initialized, but directly copied to user memory
in sctp_getsockopt_peer_addrs().

So fix it by calling memset(addr->v4.sin_zero, 0, 8) to initialize _pad of
sockaddr_in before copying it to user memory in sctp_v4_addr_to_user(), as
sctp_v6_addr_to_user() does.

Reported-by: syzbot+86b5c7c236a22616a72f@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Tested-by: Alexander Potapenko <glider@google.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/protocol.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 1c9f079e8a50..d97b2b4b7a8b 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -600,6 +600,7 @@ static struct sock *sctp_v4_create_accept_sk(struct sock *sk,
 static int sctp_v4_addr_to_user(struct sctp_sock *sp, union sctp_addr *addr)
 {
 	/* No address mapping for V4 sockets */
+	memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
 	return sizeof(struct sockaddr_in);
 }
 
-- 
2.20.1


From 4ebdcd70eea24074611a45d5429ea88ba7a08074 Mon Sep 17 00:00:00 2001
From: Koen De Schepper <koen.de_schepper@nokia-bell-labs.com>
Date: Thu, 4 Apr 2019 12:24:02 +0000
Subject: [PATCH 18/33] tcp: Ensure DCTCP reacts to losses
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit aecfde23108b8e637d9f5c5e523b24fb97035dc3 ]

RFC8257 §3.5 explicitly states that "A DCTCP sender MUST react to
loss episodes in the same way as conventional TCP".

Currently, Linux DCTCP performs no cwnd reduction when losses
are encountered. Optionally, the dctcp_clamp_alpha_on_loss resets
alpha to its maximal value if a RTO happens. This behavior
is sub-optimal for at least two reasons: i) it ignores losses
triggering fast retransmissions; and ii) it causes unnecessary large
cwnd reduction in the future if the loss was isolated as it resets
the historical term of DCTCP's alpha EWMA to its maximal value (i.e.,
denoting a total congestion). The second reason has an especially
noticeable effect when using DCTCP in high BDP environments, where
alpha normally stays at low values.

This patch replace the clamping of alpha by setting ssthresh to
half of cwnd for both fast retransmissions and RTOs, at most once
per RTT. Consequently, the dctcp_clamp_alpha_on_loss module parameter
has been removed.

The table below shows experimental results where we measured the
drop probability of a PIE AQM (not applying ECN marks) at a
bottleneck in the presence of a single TCP flow with either the
alpha-clamping option enabled or the cwnd halving proposed by this
patch. Results using reno or cubic are given for comparison.

                          |  Link   |   RTT    |    Drop
                 TCP CC   |  speed  | base+AQM | probability
        ==================|=========|==========|============
                    CUBIC |  40Mbps |  7+20ms  |    0.21%
                     RENO |         |          |    0.19%
        DCTCP-CLAMP-ALPHA |         |          |   25.80%
         DCTCP-HALVE-CWND |         |          |    0.22%
        ------------------|---------|----------|------------
                    CUBIC | 100Mbps |  7+20ms  |    0.03%
                     RENO |         |          |    0.02%
        DCTCP-CLAMP-ALPHA |         |          |   23.30%
         DCTCP-HALVE-CWND |         |          |    0.04%
        ------------------|---------|----------|------------
                    CUBIC | 800Mbps |   1+1ms  |    0.04%
                     RENO |         |          |    0.05%
        DCTCP-CLAMP-ALPHA |         |          |   18.70%
         DCTCP-HALVE-CWND |         |          |    0.06%

We see that, without halving its cwnd for all source of losses,
DCTCP drives the AQM to large drop probabilities in order to keep
the queue length under control (i.e., it repeatedly faces RTOs).
Instead, if DCTCP reacts to all source of losses, it can then be
controlled by the AQM using similar drop levels than cubic or reno.

Signed-off-by: Koen De Schepper <koen.de_schepper@nokia-bell-labs.com>
Signed-off-by: Olivier Tilmans <olivier.tilmans@nokia-bell-labs.com>
Cc: Bob Briscoe <research@bobbriscoe.net>
Cc: Lawrence Brakmo <brakmo@fb.com>
Cc: Florian Westphal <fw@strlen.de>
Cc: Daniel Borkmann <borkmann@iogearbox.net>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Andrew Shewmaker <agshew@gmail.com>
Cc: Glenn Judd <glenn.judd@morganstanley.com>
Acked-by: Florian Westphal <fw@strlen.de>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_dctcp.c | 36 ++++++++++++++++++------------------
 1 file changed, 18 insertions(+), 18 deletions(-)

diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index ca61e2a659e7..5205c5a5d8d5 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -66,11 +66,6 @@ static unsigned int dctcp_alpha_on_init __read_mostly = DCTCP_MAX_ALPHA;
 module_param(dctcp_alpha_on_init, uint, 0644);
 MODULE_PARM_DESC(dctcp_alpha_on_init, "parameter for initial alpha value");
 
-static unsigned int dctcp_clamp_alpha_on_loss __read_mostly;
-module_param(dctcp_clamp_alpha_on_loss, uint, 0644);
-MODULE_PARM_DESC(dctcp_clamp_alpha_on_loss,
-		 "parameter for clamping alpha on loss");
-
 static struct tcp_congestion_ops dctcp_reno;
 
 static void dctcp_reset(const struct tcp_sock *tp, struct dctcp *ca)
@@ -211,21 +206,23 @@ static void dctcp_update_alpha(struct sock *sk, u32 flags)
 	}
 }
 
-static void dctcp_state(struct sock *sk, u8 new_state)
+static void dctcp_react_to_loss(struct sock *sk)
 {
-	if (dctcp_clamp_alpha_on_loss && new_state == TCP_CA_Loss) {
-		struct dctcp *ca = inet_csk_ca(sk);
+	struct dctcp *ca = inet_csk_ca(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
 
-		/* If this extension is enabled, we clamp dctcp_alpha to
-		 * max on packet loss; the motivation is that dctcp_alpha
-		 * is an indicator to the extend of congestion and packet
-		 * loss is an indicator of extreme congestion; setting
-		 * this in practice turned out to be beneficial, and
-		 * effectively assumes total congestion which reduces the
-		 * window by half.
-		 */
-		ca->dctcp_alpha = DCTCP_MAX_ALPHA;
-	}
+	ca->loss_cwnd = tp->snd_cwnd;
+	tp->snd_ssthresh = max(tp->snd_cwnd >> 1U, 2U);
+}
+
+static void dctcp_state(struct sock *sk, u8 new_state)
+{
+	if (new_state == TCP_CA_Recovery &&
+	    new_state != inet_csk(sk)->icsk_ca_state)
+		dctcp_react_to_loss(sk);
+	/* We handle RTO in dctcp_cwnd_event to ensure that we perform only
+	 * one loss-adjustment per RTT.
+	 */
 }
 
 static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
@@ -237,6 +234,9 @@ static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
 	case CA_EVENT_ECN_NO_CE:
 		dctcp_ce_state_1_to_0(sk);
 		break;
+	case CA_EVENT_LOSS:
+		dctcp_react_to_loss(sk);
+		break;
 	default:
 		/* Don't care for the rest. */
 		break;
-- 
2.20.1


From f607373ad4297df48b7e998a0e261e26805de939 Mon Sep 17 00:00:00 2001
From: Dust Li <dust.li@linux.alibaba.com>
Date: Mon, 1 Apr 2019 16:04:53 +0800
Subject: [PATCH 19/33] tcp: fix a potential NULL pointer dereference in
 tcp_sk_exit

[ Upstream commit b506bc975f60f06e13e74adb35e708a23dc4e87c ]

 When tcp_sk_init() failed in inet_ctl_sock_create(),
 'net->ipv4.tcp_congestion_control' will be left
 uninitialized, but tcp_sk_exit() hasn't check for
 that.

 This patch add checking on 'net->ipv4.tcp_congestion_control'
 in tcp_sk_exit() to prevent NULL-ptr dereference.

Fixes: 6670e1524477 ("tcp: Namespace-ify sysctl_tcp_default_congestion_control")
Signed-off-by: Dust Li <dust.li@linux.alibaba.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 30fdf891940b..11101cf8693b 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2490,7 +2490,8 @@ static void __net_exit tcp_sk_exit(struct net *net)
 {
 	int cpu;
 
-	module_put(net->ipv4.tcp_congestion_control->owner);
+	if (net->ipv4.tcp_congestion_control)
+		module_put(net->ipv4.tcp_congestion_control->owner);
 
 	for_each_possible_cpu(cpu)
 		inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu));
-- 
2.20.1


From 84f60c616788e4fe2ee518b0fbf2ce5afe1ac800 Mon Sep 17 00:00:00 2001
From: Stephen Suryaputra <ssuryaextr@gmail.com>
Date: Mon, 1 Apr 2019 09:17:32 -0400
Subject: [PATCH 20/33] vrf: check accept_source_route on the original
 netdevice

[ Upstream commit 8c83f2df9c6578ea4c5b940d8238ad8a41b87e9e ]

Configuration check to accept source route IP options should be made on
the incoming netdevice when the skb->dev is an l3mdev master. The route
lookup for the source route next hop also needs the incoming netdev.

v2->v3:
- Simplify by passing the original netdevice down the stack (per David
  Ahern).

Signed-off-by: Stephen Suryaputra <ssuryaextr@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h      | 2 +-
 net/ipv4/ip_input.c   | 7 +++----
 net/ipv4/ip_options.c | 4 ++--
 3 files changed, 6 insertions(+), 7 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index 71d31e4d4391..cfc3dd5ff085 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -648,7 +648,7 @@ int ip_options_get_from_user(struct net *net, struct ip_options_rcu **optp,
 			     unsigned char __user *data, int optlen);
 void ip_options_undo(struct ip_options *opt);
 void ip_forward_options(struct sk_buff *skb);
-int ip_options_rcv_srr(struct sk_buff *skb);
+int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev);
 
 /*
  *	Functions provided by ip_sockglue.c
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index bd8ef4f87c79..c3a0683e83df 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -258,11 +258,10 @@ int ip_local_deliver(struct sk_buff *skb)
 		       ip_local_deliver_finish);
 }
 
-static inline bool ip_rcv_options(struct sk_buff *skb)
+static inline bool ip_rcv_options(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ip_options *opt;
 	const struct iphdr *iph;
-	struct net_device *dev = skb->dev;
 
 	/* It looks as overkill, because not all
 	   IP options require packet mangling.
@@ -298,7 +297,7 @@ static inline bool ip_rcv_options(struct sk_buff *skb)
 			}
 		}
 
-		if (ip_options_rcv_srr(skb))
+		if (ip_options_rcv_srr(skb, dev))
 			goto drop;
 	}
 
@@ -354,7 +353,7 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk,
 	}
 #endif
 
-	if (iph->ihl > 5 && ip_rcv_options(skb))
+	if (iph->ihl > 5 && ip_rcv_options(skb, dev))
 		goto drop;
 
 	rt = skb_rtable(skb);
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index 32a35043c9f5..3db31bb9df50 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -612,7 +612,7 @@ void ip_forward_options(struct sk_buff *skb)
 	}
 }
 
-int ip_options_rcv_srr(struct sk_buff *skb)
+int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ip_options *opt = &(IPCB(skb)->opt);
 	int srrspace, srrptr;
@@ -647,7 +647,7 @@ int ip_options_rcv_srr(struct sk_buff *skb)
 
 		orefdst = skb->_skb_refdst;
 		skb_dst_set(skb, NULL);
-		err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, skb->dev);
+		err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, dev);
 		rt2 = skb_rtable(skb);
 		if (err || (rt2->rt_type != RTN_UNICAST && rt2->rt_type != RTN_LOCAL)) {
 			skb_dst_drop(skb);
-- 
2.20.1


From 83204b0691612d9e197bdecf7b229b1ab3e960df Mon Sep 17 00:00:00 2001
From: Gavi Teitz <gavi@mellanox.com>
Date: Mon, 11 Mar 2019 11:56:34 +0200
Subject: [PATCH 21/33] net/mlx5e: Fix error handling when refreshing TIRs

[ Upstream commit bc87a0036826a37b43489b029af8143bd07c6cca ]

Previously, a false positive would be caught if the TIRs list is
empty, since the err value was initialized to -ENOMEM, and was only
updated if a TIR is refreshed. This is resolved by initializing the
err value to zero.

Fixes: b676f653896a ("net/mlx5e: Refactor refresh TIRs")
Signed-off-by: Gavi Teitz <gavi@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_common.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
index db3278cc052b..1e28866e3924 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
@@ -141,15 +141,17 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5e_tir *tir;
-	int err  = -ENOMEM;
+	int err  = 0;
 	u32 tirn = 0;
 	int inlen;
 	void *in;
 
 	inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
 	in = kvzalloc(inlen, GFP_KERNEL);
-	if (!in)
+	if (!in) {
+		err = -ENOMEM;
 		goto out;
+	}
 
 	if (enable_uc_lb)
 		MLX5_SET(modify_tir_in, in, ctx.self_lb_block,
-- 
2.20.1


From bea4b06ef8aaa0020819b972dc696437bb624567 Mon Sep 17 00:00:00 2001
From: Yuval Avnery <yuvalav@mellanox.com>
Date: Mon, 11 Mar 2019 06:18:24 +0200
Subject: [PATCH 22/33] net/mlx5e: Add a lock on tir list

[ Upstream commit 80a2a9026b24c6bd34b8d58256973e22270bedec ]

Refresh tirs is looping over a global list of tirs while netdevs are
adding and removing tirs from that list. That is why a lock is
required.

Fixes: 724b2aa15126 ("net/mlx5e: TIRs management refactoring")
Signed-off-by: Yuval Avnery <yuvalav@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_common.c | 7 +++++++
 include/linux/mlx5/driver.h                         | 2 ++
 2 files changed, 9 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
index 1e28866e3924..124e4567a4ee 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
@@ -45,7 +45,9 @@ int mlx5e_create_tir(struct mlx5_core_dev *mdev,
 	if (err)
 		return err;
 
+	mutex_lock(&mdev->mlx5e_res.td.list_lock);
 	list_add(&tir->list, &mdev->mlx5e_res.td.tirs_list);
+	mutex_unlock(&mdev->mlx5e_res.td.list_lock);
 
 	return 0;
 }
@@ -53,8 +55,10 @@ int mlx5e_create_tir(struct mlx5_core_dev *mdev,
 void mlx5e_destroy_tir(struct mlx5_core_dev *mdev,
 		       struct mlx5e_tir *tir)
 {
+	mutex_lock(&mdev->mlx5e_res.td.list_lock);
 	mlx5_core_destroy_tir(mdev, tir->tirn);
 	list_del(&tir->list);
+	mutex_unlock(&mdev->mlx5e_res.td.list_lock);
 }
 
 static int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn,
@@ -114,6 +118,7 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev)
 	}
 
 	INIT_LIST_HEAD(&mdev->mlx5e_res.td.tirs_list);
+	mutex_init(&mdev->mlx5e_res.td.list_lock);
 
 	return 0;
 
@@ -159,6 +164,7 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb)
 
 	MLX5_SET(modify_tir_in, in, bitmask.self_lb_en, 1);
 
+	mutex_lock(&mdev->mlx5e_res.td.list_lock);
 	list_for_each_entry(tir, &mdev->mlx5e_res.td.tirs_list, list) {
 		tirn = tir->tirn;
 		err = mlx5_core_modify_tir(mdev, tirn, in, inlen);
@@ -170,6 +176,7 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb)
 	kvfree(in);
 	if (err)
 		netdev_err(priv->netdev, "refresh tir(0x%x) failed, %d\n", tirn, err);
+	mutex_unlock(&mdev->mlx5e_res.td.list_lock);
 
 	return err;
 }
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index bbcfe2e5fd91..e8b92dee5a72 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -776,6 +776,8 @@ struct mlx5_pagefault {
 };
 
 struct mlx5_td {
+	/* protects tirs list changes while tirs refresh */
+	struct mutex     list_lock;
 	struct list_head tirs_list;
 	u32              tdn;
 };
-- 
2.20.1


From 775645676ddf16c8f856ae3334d11cf89cf0c7f7 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 27 Mar 2019 11:38:38 -0700
Subject: [PATCH 23/33] nfp: validate the return code from dev_queue_xmit()

[ Upstream commit c8ba5b91a04e3e2643e48501c114108802f21cda ]

dev_queue_xmit() may return error codes as well as netdev_tx_t,
and it always consumes the skb.  Make sure we always return a
correct netdev_tx_t value.

Fixes: eadfa4c3be99 ("nfp: add stats and xmit helpers for representors")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net_repr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
index 18a09cdcd9c6..e0d73b385563 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
@@ -225,7 +225,7 @@ static netdev_tx_t nfp_repr_xmit(struct sk_buff *skb, struct net_device *netdev)
 	ret = dev_queue_xmit(skb);
 	nfp_repr_inc_tx_stats(netdev, len, ret);
 
-	return ret;
+	return NETDEV_TX_OK;
 }
 
 static int nfp_repr_stop(struct net_device *netdev)
-- 
2.20.1


From 48cd62bd4446b5c7a33ac5bd2d5753beac73d40e Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 27 Mar 2019 11:38:39 -0700
Subject: [PATCH 24/33] nfp: disable netpoll on representors

[ Upstream commit c3e1f7fff69c78169c8ac40cc74ac4307f74e36d ]

NFP reprs are software device on top of the PF's vNIC.
The comment above __dev_queue_xmit() sayeth:

 When calling this method, interrupts MUST be enabled.  This is because
 the BH enable code must have IRQs enabled so that it will not deadlock.

For netconsole we can't guarantee IRQ state, let's just
disable netpoll on representors to be on the safe side.

When the initial implementation of NFP reprs was added by the
commit 5de73ee46704 ("nfp: general representor implementation")
.ndo_poll_controller was required for netpoll to be enabled.

Fixes: ac3d9dd034e5 ("netpoll: make ndo_poll_controller() optional")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net_repr.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
index e0d73b385563..aa5869eb2e3f 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
@@ -329,6 +329,8 @@ int nfp_repr_init(struct nfp_app *app, struct net_device *netdev,
 
 	SWITCHDEV_SET_OPS(netdev, &nfp_port_switchdev_ops);
 
+	netdev->priv_flags |= IFF_DISABLE_NETPOLL;
+
 	if (nfp_app_has_tc(app)) {
 		netdev->features |= NETIF_F_HW_TC;
 		netdev->hw_features |= NETIF_F_HW_TC;
-- 
2.20.1


From 762bc14ddaff46728909a9bae0df40c371b7b908 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Mon, 8 Apr 2019 17:39:54 -0400
Subject: [PATCH 25/33] bnxt_en: Improve RX consumer index validity check.

[ Upstream commit a1b0e4e684e9c300b9e759b46cb7a0147e61ddff ]

There is logic to check that the RX/TPA consumer index is the expected
index to work around a hardware problem.  However, the potentially bad
consumer index is first used to index into an array to reference an entry.
This can potentially crash if the bad consumer index is beyond legal
range.  Improve the logic to use the consumer index for dereferencing
after the validity check and log an error message.

Fixes: fa7e28127a5a ("bnxt_en: Add workaround to detect bad opaque in rx completion (part 2)")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 0bd93bb7d1a2..a8abb47178be 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1092,6 +1092,8 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 	tpa_info = &rxr->rx_tpa[agg_id];
 
 	if (unlikely(cons != rxr->rx_next_cons)) {
+		netdev_warn(bp->dev, "TPA cons %x != expected cons %x\n",
+			    cons, rxr->rx_next_cons);
 		bnxt_sched_reset(bp, rxr);
 		return;
 	}
@@ -1544,15 +1546,17 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_napi *bnapi, u32 *raw_cons,
 	}
 
 	cons = rxcmp->rx_cmp_opaque;
-	rx_buf = &rxr->rx_buf_ring[cons];
-	data = rx_buf->data;
-	data_ptr = rx_buf->data_ptr;
 	if (unlikely(cons != rxr->rx_next_cons)) {
 		int rc1 = bnxt_discard_rx(bp, bnapi, raw_cons, rxcmp);
 
+		netdev_warn(bp->dev, "RX cons %x != expected cons %x\n",
+			    cons, rxr->rx_next_cons);
 		bnxt_sched_reset(bp, rxr);
 		return rc1;
 	}
+	rx_buf = &rxr->rx_buf_ring[cons];
+	data = rx_buf->data;
+	data_ptr = rx_buf->data_ptr;
 	prefetch(data_ptr);
 
 	misc = le32_to_cpu(rxcmp->rx_cmp_misc_v1);
-- 
2.20.1


From 1b8831f1ea4e3eabae1f4c791c833f33e89a8d87 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Mon, 8 Apr 2019 17:39:55 -0400
Subject: [PATCH 26/33] bnxt_en: Reset device on RX buffer errors.

[ Upstream commit 8e44e96c6c8e8fb80b84a2ca11798a8554f710f2 ]

If the RX completion indicates RX buffers errors, the RX ring will be
disabled by firmware and no packets will be received on that ring from
that point on.  Recover by resetting the device.

Fixes: c0c050c58d84 ("bnxt_en: New Broadcom ethernet driver.")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index a8abb47178be..581ad0a17d0c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1573,11 +1573,17 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_napi *bnapi, u32 *raw_cons,
 
 	rx_buf->data = NULL;
 	if (rxcmp1->rx_cmp_cfa_code_errors_v2 & RX_CMP_L2_ERRORS) {
+		u32 rx_err = le32_to_cpu(rxcmp1->rx_cmp_cfa_code_errors_v2);
+
 		bnxt_reuse_rx_data(rxr, cons, data);
 		if (agg_bufs)
 			bnxt_reuse_rx_agg_bufs(bnapi, cp_cons, agg_bufs);
 
 		rc = -EIO;
+		if (rx_err & RX_CMPL_ERRORS_BUFFER_ERROR_MASK) {
+			netdev_warn(bp->dev, "RX buffer error %x\n", rx_err);
+			bnxt_sched_reset(bp, rxr);
+		}
 		goto next_rx;
 	}
 
-- 
2.20.1


From 593baa342512b7988b34b5395de2d195f2c8740f Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Sat, 6 Apr 2019 17:16:52 +0200
Subject: [PATCH 27/33] net: ip_gre: fix possible use-after-free in erspan_rcv

[ Upstream commit 492b67e28ee5f2a2522fb72e3d3bcb990e461514 ]

erspan tunnels run __iptunnel_pull_header on received skbs to remove
gre and erspan headers. This can determine a possible use-after-free
accessing pkt_md pointer in erspan_rcv since the packet will be 'uncloned'
running pskb_expand_head if it is a cloned gso skb (e.g if the packet has
been sent though a veth device). Fix it resetting pkt_md pointer after
__iptunnel_pull_header

Fixes: 1d7e2ed22f8d ("net: erspan: refactor existing erspan code")
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_gre.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index f199945f6e4a..3c734832bb7c 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -260,7 +260,6 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 	struct net *net = dev_net(skb->dev);
 	struct metadata_dst *tun_dst = NULL;
 	struct erspan_base_hdr *ershdr;
-	struct erspan_metadata *pkt_md;
 	struct ip_tunnel_net *itn;
 	struct ip_tunnel *tunnel;
 	const struct iphdr *iph;
@@ -283,9 +282,6 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 		if (unlikely(!pskb_may_pull(skb, len)))
 			return PACKET_REJECT;
 
-		ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len);
-		pkt_md = (struct erspan_metadata *)(ershdr + 1);
-
 		if (__iptunnel_pull_header(skb,
 					   len,
 					   htons(ETH_P_TEB),
@@ -293,8 +289,9 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 			goto drop;
 
 		if (tunnel->collect_md) {
+			struct erspan_metadata *pkt_md, *md;
 			struct ip_tunnel_info *info;
-			struct erspan_metadata *md;
+			unsigned char *gh;
 			__be64 tun_id;
 			__be16 flags;
 
@@ -307,6 +304,14 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 			if (!tun_dst)
 				return PACKET_REJECT;
 
+			/* skb can be uncloned in __iptunnel_pull_header, so
+			 * old pkt_md is no longer valid and we need to reset
+			 * it
+			 */
+			gh = skb_network_header(skb) +
+			     skb_network_header_len(skb);
+			pkt_md = (struct erspan_metadata *)(gh + gre_hdr_len +
+							    sizeof(*ershdr));
 			md = ip_tunnel_info_opts(&tun_dst->u.tun_info);
 			md->version = ver;
 			md2 = &md->u.md2;
-- 
2.20.1


From d99f61bd68936266c930a1f4fc4e9309ce2832a2 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Sat, 6 Apr 2019 17:16:53 +0200
Subject: [PATCH 28/33] net: ip6_gre: fix possible use-after-free in
 ip6erspan_rcv

[ Upstream commit 2a3cabae4536edbcb21d344e7aa8be7a584d2afb ]

erspan_v6 tunnels run __iptunnel_pull_header on received skbs to remove
erspan header. This can determine a possible use-after-free accessing
pkt_md pointer in ip6erspan_rcv since the packet will be 'uncloned'
running pskb_expand_head if it is a cloned gso skb (e.g if the packet has
been sent though a veth device). Fix it resetting pkt_md pointer after
__iptunnel_pull_header

Fixes: 1d7e2ed22f8d ("net: erspan: refactor existing erspan code")
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 21 +++++++++++++--------
 1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index faed98dab913..c4a7db62658e 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -540,11 +540,10 @@ static int ip6gre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi)
 	return PACKET_REJECT;
 }
 
-static int ip6erspan_rcv(struct sk_buff *skb, int gre_hdr_len,
-			 struct tnl_ptk_info *tpi)
+static int ip6erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
+			 int gre_hdr_len)
 {
 	struct erspan_base_hdr *ershdr;
-	struct erspan_metadata *pkt_md;
 	const struct ipv6hdr *ipv6h;
 	struct erspan_md2 *md2;
 	struct ip6_tnl *tunnel;
@@ -563,18 +562,16 @@ static int ip6erspan_rcv(struct sk_buff *skb, int gre_hdr_len,
 		if (unlikely(!pskb_may_pull(skb, len)))
 			return PACKET_REJECT;
 
-		ershdr = (struct erspan_base_hdr *)skb->data;
-		pkt_md = (struct erspan_metadata *)(ershdr + 1);
-
 		if (__iptunnel_pull_header(skb, len,
 					   htons(ETH_P_TEB),
 					   false, false) < 0)
 			return PACKET_REJECT;
 
 		if (tunnel->parms.collect_md) {
+			struct erspan_metadata *pkt_md, *md;
 			struct metadata_dst *tun_dst;
 			struct ip_tunnel_info *info;
-			struct erspan_metadata *md;
+			unsigned char *gh;
 			__be64 tun_id;
 			__be16 flags;
 
@@ -587,6 +584,14 @@ static int ip6erspan_rcv(struct sk_buff *skb, int gre_hdr_len,
 			if (!tun_dst)
 				return PACKET_REJECT;
 
+			/* skb can be uncloned in __iptunnel_pull_header, so
+			 * old pkt_md is no longer valid and we need to reset
+			 * it
+			 */
+			gh = skb_network_header(skb) +
+			     skb_network_header_len(skb);
+			pkt_md = (struct erspan_metadata *)(gh + gre_hdr_len +
+							    sizeof(*ershdr));
 			info = &tun_dst->u.tun_info;
 			md = ip_tunnel_info_opts(info);
 			md->version = ver;
@@ -623,7 +628,7 @@ static int gre_rcv(struct sk_buff *skb)
 
 	if (unlikely(tpi.proto == htons(ETH_P_ERSPAN) ||
 		     tpi.proto == htons(ETH_P_ERSPAN2))) {
-		if (ip6erspan_rcv(skb, hdr_len, &tpi) == PACKET_RCVD)
+		if (ip6erspan_rcv(skb, &tpi, hdr_len) == PACKET_RCVD)
 			return 0;
 		goto out;
 	}
-- 
2.20.1


From b3fb53594b7d6fd6e59a7e55e463f2c5dddbeac9 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <alobakin@dlink.ru>
Date: Thu, 28 Mar 2019 18:23:04 +0300
Subject: [PATCH 29/33] net: core: netif_receive_skb_list: unlist skb before
 passing to pt->func

[ Upstream commit 9a5a90d167b0e5fe3d47af16b68fd09ce64085cd ]

__netif_receive_skb_list_ptype() leaves skb->next poisoned before passing
it to pt_prev->func handler, what may produce (in certain cases, e.g. DSA
setup) crashes like:

[ 88.606777] CPU 0 Unable to handle kernel paging request at virtual address 0000000e, epc == 80687078, ra == 8052cc7c
[ 88.618666] Oops[#1]:
[ 88.621196] CPU: 0 PID: 0 Comm: swapper Not tainted 5.1.0-rc2-dlink-00206-g4192a172-dirty #1473
[ 88.630885] $ 0 : 00000000 10000400 00000002 864d7850
[ 88.636709] $ 4 : 87c0ddf0 864d7800 87c0ddf0 00000000
[ 88.642526] $ 8 : 00000000 49600000 00000001 00000001
[ 88.648342] $12 : 00000000 c288617b dadbee27 25d17c41
[ 88.654159] $16 : 87c0ddf0 85cff080 80790000 fffffffd
[ 88.659975] $20 : 80797b20 ffffffff 00000001 864d7800
[ 88.665793] $24 : 00000000 8011e658
[ 88.671609] $28 : 80790000 87c0dbc0 87cabf00 8052cc7c
[ 88.677427] Hi : 00000003
[ 88.680622] Lo : 7b5b4220
[ 88.683840] epc : 80687078 vlan_dev_hard_start_xmit+0x1c/0x1a0
[ 88.690532] ra : 8052cc7c dev_hard_start_xmit+0xac/0x188
[ 88.696734] Status: 10000404	IEp
[ 88.700422] Cause : 50000008 (ExcCode 02)
[ 88.704874] BadVA : 0000000e
[ 88.708069] PrId : 0001a120 (MIPS interAptiv (multi))
[ 88.713005] Modules linked in:
[ 88.716407] Process swapper (pid: 0, threadinfo=(ptrval), task=(ptrval), tls=00000000)
[ 88.725219] Stack : 85f61c28 00000000 0000000e 80780000 87c0ddf0 85cff080 80790000 8052cc7c
[ 88.734529] 87cabf00 00000000 00000001 85f5fb40 807b0000 864d7850 87cabf00 807d0000
[ 88.743839] 864d7800 8655f600 00000000 85cff080 87c1c000 0000006a 00000000 8052d96c
[ 88.753149] 807a0000 8057adb8 87c0dcc8 87c0dc50 85cfff08 00000558 87cabf00 85f58c50
[ 88.762460] 00000002 85f58c00 864d7800 80543308 fffffff4 00000001 85f58c00 864d7800
[ 88.771770] ...
[ 88.774483] Call Trace:
[ 88.777199] [<80687078>] vlan_dev_hard_start_xmit+0x1c/0x1a0
[ 88.783504] [<8052cc7c>] dev_hard_start_xmit+0xac/0x188
[ 88.789326] [<8052d96c>] __dev_queue_xmit+0x6e8/0x7d4
[ 88.794955] [<805a8640>] ip_finish_output2+0x238/0x4d0
[ 88.800677] [<805ab6a0>] ip_output+0xc8/0x140
[ 88.805526] [<805a68f4>] ip_forward+0x364/0x560
[ 88.810567] [<805a4ff8>] ip_rcv+0x48/0xe4
[ 88.815030] [<80528d44>] __netif_receive_skb_one_core+0x44/0x58
[ 88.821635] [<8067f220>] dsa_switch_rcv+0x108/0x1ac
[ 88.827067] [<80528f80>] __netif_receive_skb_list_core+0x228/0x26c
[ 88.833951] [<8052ed84>] netif_receive_skb_list+0x1d4/0x394
[ 88.840160] [<80355a88>] lunar_rx_poll+0x38c/0x828
[ 88.845496] [<8052fa78>] net_rx_action+0x14c/0x3cc
[ 88.850835] [<806ad300>] __do_softirq+0x178/0x338
[ 88.856077] [<8012a2d4>] irq_exit+0xbc/0x100
[ 88.860846] [<802f8b70>] plat_irq_dispatch+0xc0/0x144
[ 88.866477] [<80105974>] handle_int+0x14c/0x158
[ 88.871516] [<806acfb0>] r4k_wait+0x30/0x40
[ 88.876462] Code: afb10014 8c8200a0 00803025 <9443000c> 94a20468 00000000 10620042 00a08025 9605046a
[ 88.887332]
[ 88.888982] ---[ end trace eb863d007da11cf1 ]---
[ 88.894122] Kernel panic - not syncing: Fatal exception in interrupt
[ 88.901202] ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]---

Fix this by pulling skb off the sublist and zeroing skb->next pointer
before calling ptype callback.

Fixes: 88eb1944e18c ("net: core: propagate SKB lists through packet_type lookup")
Reviewed-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: Alexander Lobakin <alobakin@dlink.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 5c8c0a572ee9..d47554307a6d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4959,8 +4959,10 @@ static inline void __netif_receive_skb_list_ptype(struct list_head *head,
 	if (pt_prev->list_func != NULL)
 		pt_prev->list_func(head, pt_prev, orig_dev);
 	else
-		list_for_each_entry_safe(skb, next, head, list)
+		list_for_each_entry_safe(skb, next, head, list) {
+			skb_list_del_init(skb);
 			pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
+		}
 }
 
 static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemalloc)
-- 
2.20.1


From 41ac9396a61bc95757b2bbc9eb89cdc91f8e0ed6 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 30 Mar 2019 17:13:24 +0100
Subject: [PATCH 30/33] r8169: disable default rx interrupt coalescing on
 RTL8168

[ Upstream commit 288ac524cf70a8e7ed851a61ed2a9744039dae8d ]

It was reported that re-introducing ASPM, in combination with RX
interrupt coalescing, results in significantly increased packet
latency, see [0]. Disabling ASPM or RX interrupt coalescing fixes
the issue. Therefore change the driver's default to disable RX
interrupt coalescing. Users still have the option to enable RX
coalescing via ethtool.

[0] https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=925496

Fixes: a99790bf5c7f ("r8169: Reinstate ASPM Support")
Reported-by: Mike Crowe <mac@mcrowe.com>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 1d24884e9897..7a50b911b180 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -5418,7 +5418,7 @@ static void rtl_hw_start_8168(struct rtl8169_private *tp)
 	tp->cp_cmd |= PktCntrDisable | INTT_1;
 	RTL_W16(tp, CPlusCmd, tp->cp_cmd);
 
-	RTL_W16(tp, IntrMitigate, 0x5151);
+	RTL_W16(tp, IntrMitigate, 0x5100);
 
 	/* Work around for RxFIFO overflow. */
 	if (tp->mac_version == RTL_GIGA_MAC_VER_11) {
-- 
2.20.1


From 1c0933ee29a90e94f0eb9df381772d97b5a9cdd8 Mon Sep 17 00:00:00 2001
From: Aditya Pakki <pakki001@umn.edu>
Date: Tue, 19 Mar 2019 16:42:40 -0500
Subject: [PATCH 31/33] net: mlx5: Add a missing check on idr_find, free buf

[ Upstream commit 8e949363f017e2011464812a714fb29710fb95b4 ]

idr_find() can return a NULL value to 'flow' which is used without a
check. The patch adds a check to avoid potential NULL pointer dereference.

In case of mlx5_fpga_sbu_conn_sendmsg() failure, free buf allocated
using kzalloc.

Fixes: ab412e1dd7db ("net/mlx5: Accel, add TLS rx offload routines")
Signed-off-by: Aditya Pakki <pakki001@umn.edu>
Reviewed-by: Yuval Shaia <yuval.shaia@oracle.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
index 5cf5f2a9d51f..8de64e88c670 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
@@ -217,15 +217,21 @@ int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
 	void *cmd;
 	int ret;
 
+	rcu_read_lock();
+	flow = idr_find(&mdev->fpga->tls->rx_idr, ntohl(handle));
+	rcu_read_unlock();
+
+	if (!flow) {
+		WARN_ONCE(1, "Received NULL pointer for handle\n");
+		return -EINVAL;
+	}
+
 	buf = kzalloc(size, GFP_ATOMIC);
 	if (!buf)
 		return -ENOMEM;
 
 	cmd = (buf + 1);
 
-	rcu_read_lock();
-	flow = idr_find(&mdev->fpga->tls->rx_idr, ntohl(handle));
-	rcu_read_unlock();
 	mlx5_fpga_tls_flow_to_cmd(flow, cmd);
 
 	MLX5_SET(tls_cmd, cmd, swid, ntohl(handle));
@@ -238,6 +244,8 @@ int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
 	buf->complete = mlx_tls_kfree_complete;
 
 	ret = mlx5_fpga_sbu_conn_sendmsg(mdev->fpga->tls->conn, buf);
+	if (ret < 0)
+		kfree(buf);
 
 	return ret;
 }
-- 
2.20.1


From 3811bf161e7840528ee305f4ce05665abbfd8e9e Mon Sep 17 00:00:00 2001
From: Huy Nguyen <huyn@mellanox.com>
Date: Thu, 7 Mar 2019 14:49:50 -0600
Subject: [PATCH 32/33] net/mlx5e: Update xoff formula

[ Upstream commit 5ec983e924c7978aaec3cf8679ece9436508bb20 ]

Set minimum speed in xoff threshold formula to 40Gbps

Fixes: 0696d60853d5 ("net/mlx5e: Receive buffer configuration")
Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en/port_buffer.c  | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
index eac245a93f91..f00de0c987cd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
@@ -122,7 +122,9 @@ static int port_set_buffer(struct mlx5e_priv *priv,
 	return err;
 }
 
-/* xoff = ((301+2.16 * len [m]) * speed [Gbps] + 2.72 MTU [B]) */
+/* xoff = ((301+2.16 * len [m]) * speed [Gbps] + 2.72 MTU [B])
+ * minimum speed value is 40Gbps
+ */
 static u32 calculate_xoff(struct mlx5e_priv *priv, unsigned int mtu)
 {
 	u32 speed;
@@ -130,10 +132,9 @@ static u32 calculate_xoff(struct mlx5e_priv *priv, unsigned int mtu)
 	int err;
 
 	err = mlx5e_port_linkspeed(priv->mdev, &speed);
-	if (err) {
-		mlx5_core_warn(priv->mdev, "cannot get port speed\n");
-		return 0;
-	}
+	if (err)
+		speed = SPEED_40000;
+	speed = max_t(u32, speed, SPEED_40000);
 
 	xoff = (301 + 216 * priv->dcbx.cable_len / 100) * speed / 1000 + 272 * mtu / 100;
 
-- 
2.20.1


From f8b73f2f6ac61de8f61d87489fe63c74cee1f06d Mon Sep 17 00:00:00 2001
From: Huy Nguyen <huyn@mellanox.com>
Date: Thu, 7 Mar 2019 14:07:32 -0600
Subject: [PATCH 33/33] net/mlx5e: Update xon formula

[ Upstream commit e28408e98bced123038857b6e3c81fa12a2e3e68 ]

Set xon = xoff - netdev's max_mtu.
netdev's max_mtu will give enough time for the pause frame to
arrive at the sender.

Fixes: 0696d60853d5 ("net/mlx5e: Receive buffer configuration")
Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../mellanox/mlx5/core/en/port_buffer.c       | 28 +++++++++++--------
 1 file changed, 16 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
index f00de0c987cd..4ab0d030b544 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
@@ -143,7 +143,7 @@ static u32 calculate_xoff(struct mlx5e_priv *priv, unsigned int mtu)
 }
 
 static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer,
-				 u32 xoff, unsigned int mtu)
+				 u32 xoff, unsigned int max_mtu)
 {
 	int i;
 
@@ -155,11 +155,12 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer,
 		}
 
 		if (port_buffer->buffer[i].size <
-		    (xoff + mtu + (1 << MLX5E_BUFFER_CELL_SHIFT)))
+		    (xoff + max_mtu + (1 << MLX5E_BUFFER_CELL_SHIFT)))
 			return -ENOMEM;
 
 		port_buffer->buffer[i].xoff = port_buffer->buffer[i].size - xoff;
-		port_buffer->buffer[i].xon  = port_buffer->buffer[i].xoff - mtu;
+		port_buffer->buffer[i].xon  =
+			port_buffer->buffer[i].xoff - max_mtu;
 	}
 
 	return 0;
@@ -167,7 +168,7 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer,
 
 /**
  * update_buffer_lossy()
- *   mtu: device's MTU
+ *   max_mtu: netdev's max_mtu
  *   pfc_en: <input> current pfc configuration
  *   buffer: <input> current prio to buffer mapping
  *   xoff:   <input> xoff value
@@ -184,7 +185,7 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer,
  *     Return 0 if no error.
  *     Set change to true if buffer configuration is modified.
  */
-static int update_buffer_lossy(unsigned int mtu,
+static int update_buffer_lossy(unsigned int max_mtu,
 			       u8 pfc_en, u8 *buffer, u32 xoff,
 			       struct mlx5e_port_buffer *port_buffer,
 			       bool *change)
@@ -221,7 +222,7 @@ static int update_buffer_lossy(unsigned int mtu,
 	}
 
 	if (changed) {
-		err = update_xoff_threshold(port_buffer, xoff, mtu);
+		err = update_xoff_threshold(port_buffer, xoff, max_mtu);
 		if (err)
 			return err;
 
@@ -231,6 +232,7 @@ static int update_buffer_lossy(unsigned int mtu,
 	return 0;
 }
 
+#define MINIMUM_MAX_MTU 9216
 int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 				    u32 change, unsigned int mtu,
 				    struct ieee_pfc *pfc,
@@ -242,12 +244,14 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 	bool update_prio2buffer = false;
 	u8 buffer[MLX5E_MAX_PRIORITY];
 	bool update_buffer = false;
+	unsigned int max_mtu;
 	u32 total_used = 0;
 	u8 curr_pfc_en;
 	int err;
 	int i;
 
 	mlx5e_dbg(HW, priv, "%s: change=%x\n", __func__, change);
+	max_mtu = max_t(unsigned int, priv->netdev->max_mtu, MINIMUM_MAX_MTU);
 
 	err = mlx5e_port_query_buffer(priv, &port_buffer);
 	if (err)
@@ -255,7 +259,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 
 	if (change & MLX5E_PORT_BUFFER_CABLE_LEN) {
 		update_buffer = true;
-		err = update_xoff_threshold(&port_buffer, xoff, mtu);
+		err = update_xoff_threshold(&port_buffer, xoff, max_mtu);
 		if (err)
 			return err;
 	}
@@ -265,7 +269,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 		if (err)
 			return err;
 
-		err = update_buffer_lossy(mtu, pfc->pfc_en, buffer, xoff,
+		err = update_buffer_lossy(max_mtu, pfc->pfc_en, buffer, xoff,
 					  &port_buffer, &update_buffer);
 		if (err)
 			return err;
@@ -277,8 +281,8 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 		if (err)
 			return err;
 
-		err = update_buffer_lossy(mtu, curr_pfc_en, prio2buffer, xoff,
-					  &port_buffer, &update_buffer);
+		err = update_buffer_lossy(max_mtu, curr_pfc_en, prio2buffer,
+					  xoff, &port_buffer, &update_buffer);
 		if (err)
 			return err;
 	}
@@ -302,7 +306,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 			return -EINVAL;
 
 		update_buffer = true;
-		err = update_xoff_threshold(&port_buffer, xoff, mtu);
+		err = update_xoff_threshold(&port_buffer, xoff, max_mtu);
 		if (err)
 			return err;
 	}
@@ -310,7 +314,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 	/* Need to update buffer configuration if xoff value is changed */
 	if (!update_buffer && xoff != priv->dcbx.xoff) {
 		update_buffer = true;
-		err = update_xoff_threshold(&port_buffer, xoff, mtu);
+		err = update_xoff_threshold(&port_buffer, xoff, max_mtu);
 		if (err)
 			return err;
 	}
-- 
2.20.1


[-- Attachment #3: net_50.mbox --]
[-- Type: Application/Octet-Stream, Size: 106427 bytes --]

From bebafc65bddf73bfc9c81cd246c57ff007a572db Mon Sep 17 00:00:00 2001
From: Haiyang Zhang <haiyangz@microsoft.com>
Date: Thu, 28 Mar 2019 19:40:36 +0000
Subject: [PATCH 01/36] hv_netvsc: Fix unwanted wakeup after tx_disable

[ Upstream commit 1b704c4a1ba95574832e730f23817b651db2aa59 ]

After queue stopped, the wakeup mechanism may wake it up again
when ring buffer usage is lower than a threshold. This may cause
send path panic on NULL pointer when we stopped all tx queues in
netvsc_detach and start removing the netvsc device.

This patch fix it by adding a tx_disable flag to prevent unwanted
queue wakeup.

Fixes: 7b2ee50c0cd5 ("hv_netvsc: common detach logic")
Reported-by: Mohammed Gamal <mgamal@redhat.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/hyperv_net.h |  1 +
 drivers/net/hyperv/netvsc.c     |  6 ++++--
 drivers/net/hyperv/netvsc_drv.c | 32 ++++++++++++++++++++++++++------
 3 files changed, 31 insertions(+), 8 deletions(-)

diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index e859ae2e42d5..49f41b64077b 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -987,6 +987,7 @@ struct netvsc_device {
 
 	wait_queue_head_t wait_drain;
 	bool destroy;
+	bool tx_disable; /* if true, do not wake up queue again */
 
 	/* Receive buffer allocated by us but manages by NetVSP */
 	void *recv_buf;
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 813d195bbd57..e0dce373cdd9 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -110,6 +110,7 @@ static struct netvsc_device *alloc_net_device(void)
 
 	init_waitqueue_head(&net_device->wait_drain);
 	net_device->destroy = false;
+	net_device->tx_disable = false;
 
 	net_device->max_pkt = RNDIS_MAX_PKT_DEFAULT;
 	net_device->pkt_align = RNDIS_PKT_ALIGN_DEFAULT;
@@ -719,7 +720,7 @@ static void netvsc_send_tx_complete(struct net_device *ndev,
 	} else {
 		struct netdev_queue *txq = netdev_get_tx_queue(ndev, q_idx);
 
-		if (netif_tx_queue_stopped(txq) &&
+		if (netif_tx_queue_stopped(txq) && !net_device->tx_disable &&
 		    (hv_get_avail_to_write_percent(&channel->outbound) >
 		     RING_AVAIL_PERCENT_HIWATER || queue_sends < 1)) {
 			netif_tx_wake_queue(txq);
@@ -874,7 +875,8 @@ static inline int netvsc_send_pkt(
 	} else if (ret == -EAGAIN) {
 		netif_tx_stop_queue(txq);
 		ndev_ctx->eth_stats.stop_queue++;
-		if (atomic_read(&nvchan->queue_sends) < 1) {
+		if (atomic_read(&nvchan->queue_sends) < 1 &&
+		    !net_device->tx_disable) {
 			netif_tx_wake_queue(txq);
 			ndev_ctx->eth_stats.wake_queue++;
 			ret = -ENOSPC;
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index cf4897043e83..b20fb0fb595b 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -109,6 +109,15 @@ static void netvsc_set_rx_mode(struct net_device *net)
 	rcu_read_unlock();
 }
 
+static void netvsc_tx_enable(struct netvsc_device *nvscdev,
+			     struct net_device *ndev)
+{
+	nvscdev->tx_disable = false;
+	virt_wmb(); /* ensure queue wake up mechanism is on */
+
+	netif_tx_wake_all_queues(ndev);
+}
+
 static int netvsc_open(struct net_device *net)
 {
 	struct net_device_context *ndev_ctx = netdev_priv(net);
@@ -129,7 +138,7 @@ static int netvsc_open(struct net_device *net)
 	rdev = nvdev->extension;
 	if (!rdev->link_state) {
 		netif_carrier_on(net);
-		netif_tx_wake_all_queues(net);
+		netvsc_tx_enable(nvdev, net);
 	}
 
 	if (vf_netdev) {
@@ -184,6 +193,17 @@ static int netvsc_wait_until_empty(struct netvsc_device *nvdev)
 	}
 }
 
+static void netvsc_tx_disable(struct netvsc_device *nvscdev,
+			      struct net_device *ndev)
+{
+	if (nvscdev) {
+		nvscdev->tx_disable = true;
+		virt_wmb(); /* ensure txq will not wake up after stop */
+	}
+
+	netif_tx_disable(ndev);
+}
+
 static int netvsc_close(struct net_device *net)
 {
 	struct net_device_context *net_device_ctx = netdev_priv(net);
@@ -192,7 +212,7 @@ static int netvsc_close(struct net_device *net)
 	struct netvsc_device *nvdev = rtnl_dereference(net_device_ctx->nvdev);
 	int ret;
 
-	netif_tx_disable(net);
+	netvsc_tx_disable(nvdev, net);
 
 	/* No need to close rndis filter if it is removed already */
 	if (!nvdev)
@@ -920,7 +940,7 @@ static int netvsc_detach(struct net_device *ndev,
 
 	/* If device was up (receiving) then shutdown */
 	if (netif_running(ndev)) {
-		netif_tx_disable(ndev);
+		netvsc_tx_disable(nvdev, ndev);
 
 		ret = rndis_filter_close(nvdev);
 		if (ret) {
@@ -1908,7 +1928,7 @@ static void netvsc_link_change(struct work_struct *w)
 		if (rdev->link_state) {
 			rdev->link_state = false;
 			netif_carrier_on(net);
-			netif_tx_wake_all_queues(net);
+			netvsc_tx_enable(net_device, net);
 		} else {
 			notify = true;
 		}
@@ -1918,7 +1938,7 @@ static void netvsc_link_change(struct work_struct *w)
 		if (!rdev->link_state) {
 			rdev->link_state = true;
 			netif_carrier_off(net);
-			netif_tx_stop_all_queues(net);
+			netvsc_tx_disable(net_device, net);
 		}
 		kfree(event);
 		break;
@@ -1927,7 +1947,7 @@ static void netvsc_link_change(struct work_struct *w)
 		if (!rdev->link_state) {
 			rdev->link_state = true;
 			netif_carrier_off(net);
-			netif_tx_stop_all_queues(net);
+			netvsc_tx_disable(net_device, net);
 			event->event = RNDIS_STATUS_MEDIA_CONNECT;
 			spin_lock_irqsave(&ndev_ctx->lock, flags);
 			list_add(&event->list, &ndev_ctx->reconfig_events);
-- 
2.20.1


From d0453887d79e02aa7d8bbd8189ebc2462181cbc4 Mon Sep 17 00:00:00 2001
From: Thomas Falcon <tlfalcon@linux.ibm.com>
Date: Thu, 4 Apr 2019 18:58:26 -0500
Subject: [PATCH 02/36] ibmvnic: Fix completion structure initialization

[ Upstream commit bbd669a868bba591ffd38b7bc75a7b361bb54b04 ]

Fix device initialization completion handling for vNIC adapters.
Initialize the completion structure on probe and reinitialize when needed.
This also fixes a race condition during kdump where the driver can attempt
to access the completion struct before it is initialized:

Unable to handle kernel paging request for data at address 0x00000000
Faulting instruction address: 0xc0000000081acbe0
Oops: Kernel access of bad area, sig: 11 [#1]
LE SMP NR_CPUS=2048 NUMA pSeries
Modules linked in: ibmvnic(+) ibmveth sunrpc overlay squashfs loop
CPU: 19 PID: 301 Comm: systemd-udevd Not tainted 4.18.0-64.el8.ppc64le #1
NIP:  c0000000081acbe0 LR: c0000000081ad964 CTR: c0000000081ad900
REGS: c000000027f3f990 TRAP: 0300   Not tainted  (4.18.0-64.el8.ppc64le)
MSR:  800000010280b033 <SF,VEC,VSX,EE,FP,ME,IR,DR,RI,LE,TM[E]> CR: 28228288  XER: 00000006
CFAR: c000000008008934 DAR: 0000000000000000 DSISR: 40000000 IRQMASK: 1
GPR00: c0000000081ad964 c000000027f3fc10 c0000000095b5800 c0000000221b4e58
GPR04: 0000000000000003 0000000000000001 000049a086918581 00000000000000d4
GPR08: 0000000000000007 0000000000000000 ffffffffffffffe8 d0000000014dde28
GPR12: c0000000081ad900 c000000009a00c00 0000000000000001 0000000000000100
GPR16: 0000000000000038 0000000000000007 c0000000095e2230 0000000000000006
GPR20: 0000000000400140 0000000000000001 c00000000910c880 0000000000000000
GPR24: 0000000000000000 0000000000000006 0000000000000000 0000000000000003
GPR28: 0000000000000001 0000000000000001 c0000000221b4e60 c0000000221b4e58
NIP [c0000000081acbe0] __wake_up_locked+0x50/0x100
LR [c0000000081ad964] complete+0x64/0xa0
Call Trace:
[c000000027f3fc10] [c000000027f3fc60] 0xc000000027f3fc60 (unreliable)
[c000000027f3fc60] [c0000000081ad964] complete+0x64/0xa0
[c000000027f3fca0] [d0000000014dad58] ibmvnic_handle_crq+0xce0/0x1160 [ibmvnic]
[c000000027f3fd50] [d0000000014db270] ibmvnic_tasklet+0x98/0x130 [ibmvnic]
[c000000027f3fda0] [c00000000813f334] tasklet_action_common.isra.3+0xc4/0x1a0
[c000000027f3fe00] [c000000008cd13f4] __do_softirq+0x164/0x400
[c000000027f3fef0] [c00000000813ed64] irq_exit+0x184/0x1c0
[c000000027f3ff20] [c0000000080188e8] __do_irq+0xb8/0x210
[c000000027f3ff90] [c00000000802d0a4] call_do_irq+0x14/0x24
[c000000026a5b010] [c000000008018adc] do_IRQ+0x9c/0x130
[c000000026a5b060] [c000000008008ce4] hardware_interrupt_common+0x114/0x120

Signed-off-by: Thomas Falcon <tlfalcon@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ibm/ibmvnic.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 5ecbb1adcf3b..51cfe95f3e24 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -1885,6 +1885,7 @@ static int do_hard_reset(struct ibmvnic_adapter *adapter,
 	 */
 	adapter->state = VNIC_PROBED;
 
+	reinit_completion(&adapter->init_done);
 	rc = init_crq_queue(adapter);
 	if (rc) {
 		netdev_err(adapter->netdev,
@@ -4625,7 +4626,7 @@ static int ibmvnic_reset_init(struct ibmvnic_adapter *adapter)
 	old_num_rx_queues = adapter->req_rx_queues;
 	old_num_tx_queues = adapter->req_tx_queues;
 
-	init_completion(&adapter->init_done);
+	reinit_completion(&adapter->init_done);
 	adapter->init_done_rc = 0;
 	ibmvnic_send_crq_init(adapter);
 	if (!wait_for_completion_timeout(&adapter->init_done, timeout)) {
@@ -4680,7 +4681,6 @@ static int ibmvnic_init(struct ibmvnic_adapter *adapter)
 
 	adapter->from_passive_init = false;
 
-	init_completion(&adapter->init_done);
 	adapter->init_done_rc = 0;
 	ibmvnic_send_crq_init(adapter);
 	if (!wait_for_completion_timeout(&adapter->init_done, timeout)) {
@@ -4759,6 +4759,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	INIT_WORK(&adapter->ibmvnic_reset, __ibmvnic_reset);
 	INIT_LIST_HEAD(&adapter->rwi_list);
 	spin_lock_init(&adapter->rwi_lock);
+	init_completion(&adapter->init_done);
 	adapter->resetting = false;
 
 	adapter->mac_change_pending = false;
-- 
2.20.1


From b3a743cb982d6308346cd1ce803b55839726d356 Mon Sep 17 00:00:00 2001
From: Sheena Mira-ato <sheena.mira-ato@alliedtelesis.co.nz>
Date: Mon, 1 Apr 2019 13:04:42 +1300
Subject: [PATCH 03/36] ip6_tunnel: Match to ARPHRD_TUNNEL6 for dev type

[ Upstream commit b2e54b09a3d29c4db883b920274ca8dca4d9f04d ]

The device type for ip6 tunnels is set to
ARPHRD_TUNNEL6. However, the ip4ip6_err function
is expecting the device type of the tunnel to be
ARPHRD_TUNNEL.  Since the device types do not
match, the function exits and the ICMP error
packet is not sent to the originating host. Note
that the device type for IPv4 tunnels is set to
ARPHRD_TUNNEL.

Fix is to expect a tunnel device type of
ARPHRD_TUNNEL6 instead.  Now the tunnel device
type matches and the ICMP error packet is sent
to the originating host.

Signed-off-by: Sheena Mira-ato <sheena.mira-ato@alliedtelesis.co.nz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 0c6403cf8b52..ade1390c6348 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -627,7 +627,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL,
 					   eiph->daddr, eiph->saddr, 0, 0,
 					   IPPROTO_IPIP, RT_TOS(eiph->tos), 0);
-		if (IS_ERR(rt) || rt->dst.dev->type != ARPHRD_TUNNEL) {
+		if (IS_ERR(rt) || rt->dst.dev->type != ARPHRD_TUNNEL6) {
 			if (!IS_ERR(rt))
 				ip_rt_put(rt);
 			goto out;
@@ -636,7 +636,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	} else {
 		if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos,
 				   skb2->dev) ||
-		    skb_dst(skb2)->dev->type != ARPHRD_TUNNEL)
+		    skb_dst(skb2)->dev->type != ARPHRD_TUNNEL6)
 			goto out;
 	}
 
-- 
2.20.1


From 217dea4b45729da9f8a28e416051d2a94b92e339 Mon Sep 17 00:00:00 2001
From: Junwei Hu <hujunwei4@huawei.com>
Date: Tue, 2 Apr 2019 19:38:04 +0800
Subject: [PATCH 04/36] ipv6: Fix dangling pointer when ipv6 fragment

[ Upstream commit ef0efcd3bd3fd0589732b67fb586ffd3c8705806 ]

At the beginning of ip6_fragment func, the prevhdr pointer is
obtained in the ip6_find_1stfragopt func.
However, all the pointers pointing into skb header may change
when calling skb_checksum_help func with
skb->ip_summed = CHECKSUM_PARTIAL condition.
The prevhdr pointe will be dangling if it is not reloaded after
calling __skb_linearize func in skb_checksum_help func.

Here, I add a variable, nexthdr_offset, to evaluate the offset,
which does not changes even after calling __skb_linearize func.

Fixes: 405c92f7a541 ("ipv6: add defensive check for CHECKSUM_PARTIAL skbs in ip_fragment")
Signed-off-by: Junwei Hu <hujunwei4@huawei.com>
Reported-by: Wenhao Zhang <zhangwenhao8@huawei.com>
Reported-by: syzbot+e8ce541d095e486074fc@syzkaller.appspotmail.com
Reviewed-by: Zhiqiang Liu <liuzhiqiang26@huawei.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_output.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 5f9fa0302b5a..e71227390bec 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -595,7 +595,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 				inet6_sk(skb->sk) : NULL;
 	struct ipv6hdr *tmp_hdr;
 	struct frag_hdr *fh;
-	unsigned int mtu, hlen, left, len;
+	unsigned int mtu, hlen, left, len, nexthdr_offset;
 	int hroom, troom;
 	__be32 frag_id;
 	int ptr, offset = 0, err = 0;
@@ -606,6 +606,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		goto fail;
 	hlen = err;
 	nexthdr = *prevhdr;
+	nexthdr_offset = prevhdr - skb_network_header(skb);
 
 	mtu = ip6_skb_dst_mtu(skb);
 
@@ -640,6 +641,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 	    (err = skb_checksum_help(skb)))
 		goto fail;
 
+	prevhdr = skb_network_header(skb) + nexthdr_offset;
 	hroom = LL_RESERVED_SPACE(rt->dst.dev);
 	if (skb_has_frag_list(skb)) {
 		unsigned int first_len = skb_pagelen(skb);
-- 
2.20.1


From a14ba0c05b08e94f928ff5ddaeb811c2d90b8187 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Thu, 4 Apr 2019 16:37:53 +0200
Subject: [PATCH 05/36] ipv6: sit: reset ip header pointer in ipip6_rcv

[ Upstream commit bb9bd814ebf04f579be466ba61fc922625508807 ]

ipip6 tunnels run iptunnel_pull_header on received skbs. This can
determine the following use-after-free accessing iph pointer since
the packet will be 'uncloned' running pskb_expand_head if it is a
cloned gso skb (e.g if the packet has been sent though a veth device)

[  706.369655] BUG: KASAN: use-after-free in ipip6_rcv+0x1678/0x16e0 [sit]
[  706.449056] Read of size 1 at addr ffffe01b6bd855f5 by task ksoftirqd/1/=
[  706.669494] Hardware name: HPE ProLiant m400 Server/ProLiant m400 Server, BIOS U02 08/19/2016
[  706.771839] Call trace:
[  706.801159]  dump_backtrace+0x0/0x2f8
[  706.845079]  show_stack+0x24/0x30
[  706.884833]  dump_stack+0xe0/0x11c
[  706.925629]  print_address_description+0x68/0x260
[  706.982070]  kasan_report+0x178/0x340
[  707.025995]  __asan_report_load1_noabort+0x30/0x40
[  707.083481]  ipip6_rcv+0x1678/0x16e0 [sit]
[  707.132623]  tunnel64_rcv+0xd4/0x200 [tunnel4]
[  707.185940]  ip_local_deliver_finish+0x3b8/0x988
[  707.241338]  ip_local_deliver+0x144/0x470
[  707.289436]  ip_rcv_finish+0x43c/0x14b0
[  707.335447]  ip_rcv+0x628/0x1138
[  707.374151]  __netif_receive_skb_core+0x1670/0x2600
[  707.432680]  __netif_receive_skb+0x28/0x190
[  707.482859]  process_backlog+0x1d0/0x610
[  707.529913]  net_rx_action+0x37c/0xf68
[  707.574882]  __do_softirq+0x288/0x1018
[  707.619852]  run_ksoftirqd+0x70/0xa8
[  707.662734]  smpboot_thread_fn+0x3a4/0x9e8
[  707.711875]  kthread+0x2c8/0x350
[  707.750583]  ret_from_fork+0x10/0x18

[  707.811302] Allocated by task 16982:
[  707.854182]  kasan_kmalloc.part.1+0x40/0x108
[  707.905405]  kasan_kmalloc+0xb4/0xc8
[  707.948291]  kasan_slab_alloc+0x14/0x20
[  707.994309]  __kmalloc_node_track_caller+0x158/0x5e0
[  708.053902]  __kmalloc_reserve.isra.8+0x54/0xe0
[  708.108280]  __alloc_skb+0xd8/0x400
[  708.150139]  sk_stream_alloc_skb+0xa4/0x638
[  708.200346]  tcp_sendmsg_locked+0x818/0x2b90
[  708.251581]  tcp_sendmsg+0x40/0x60
[  708.292376]  inet_sendmsg+0xf0/0x520
[  708.335259]  sock_sendmsg+0xac/0xf8
[  708.377096]  sock_write_iter+0x1c0/0x2c0
[  708.424154]  new_sync_write+0x358/0x4a8
[  708.470162]  __vfs_write+0xc4/0xf8
[  708.510950]  vfs_write+0x12c/0x3d0
[  708.551739]  ksys_write+0xcc/0x178
[  708.592533]  __arm64_sys_write+0x70/0xa0
[  708.639593]  el0_svc_handler+0x13c/0x298
[  708.686646]  el0_svc+0x8/0xc

[  708.739019] Freed by task 17:
[  708.774597]  __kasan_slab_free+0x114/0x228
[  708.823736]  kasan_slab_free+0x10/0x18
[  708.868703]  kfree+0x100/0x3d8
[  708.905320]  skb_free_head+0x7c/0x98
[  708.948204]  skb_release_data+0x320/0x490
[  708.996301]  pskb_expand_head+0x60c/0x970
[  709.044399]  __iptunnel_pull_header+0x3b8/0x5d0
[  709.098770]  ipip6_rcv+0x41c/0x16e0 [sit]
[  709.146873]  tunnel64_rcv+0xd4/0x200 [tunnel4]
[  709.200195]  ip_local_deliver_finish+0x3b8/0x988
[  709.255596]  ip_local_deliver+0x144/0x470
[  709.303692]  ip_rcv_finish+0x43c/0x14b0
[  709.349705]  ip_rcv+0x628/0x1138
[  709.388413]  __netif_receive_skb_core+0x1670/0x2600
[  709.446943]  __netif_receive_skb+0x28/0x190
[  709.497120]  process_backlog+0x1d0/0x610
[  709.544169]  net_rx_action+0x37c/0xf68
[  709.589131]  __do_softirq+0x288/0x1018

[  709.651938] The buggy address belongs to the object at ffffe01b6bd85580
                which belongs to the cache kmalloc-1024 of size 1024
[  709.804356] The buggy address is located 117 bytes inside of
                1024-byte region [ffffe01b6bd85580, ffffe01b6bd85980)
[  709.946340] The buggy address belongs to the page:
[  710.003824] page:ffff7ff806daf600 count:1 mapcount:0 mapping:ffffe01c4001f600 index:0x0
[  710.099914] flags: 0xfffff8000000100(slab)
[  710.149059] raw: 0fffff8000000100 dead000000000100 dead000000000200 ffffe01c4001f600
[  710.242011] raw: 0000000000000000 0000000000380038 00000001ffffffff 0000000000000000
[  710.334966] page dumped because: kasan: bad access detected

Fix it resetting iph pointer after iptunnel_pull_header

Fixes: a09a4c8dd1ec ("tunnels: Remove encapsulation offloads on decap")
Tested-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 07e21a82ce4c..b2109b74857d 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -669,6 +669,10 @@ static int ipip6_rcv(struct sk_buff *skb)
 		    !net_eq(tunnel->net, dev_net(tunnel->dev))))
 			goto out;
 
+		/* skb can be uncloned in iptunnel_pull_header, so
+		 * old iph is no longer valid
+		 */
+		iph = (const struct iphdr *)skb_mac_header(skb);
 		err = IP_ECN_decapsulate(iph, skb);
 		if (unlikely(err)) {
 			if (log_ecn_error)
-- 
2.20.1


From fd12df7ae02ac3189d6d0210484da0ae9c4a75cc Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jslaby@suse.cz>
Date: Fri, 29 Mar 2019 12:19:46 +0100
Subject: [PATCH 06/36] kcm: switch order of device registration to fix a crash

[ Upstream commit 3c446e6f96997f2a95bf0037ef463802162d2323 ]

When kcm is loaded while many processes try to create a KCM socket, a
crash occurs:
 BUG: unable to handle kernel NULL pointer dereference at 000000000000000e
 IP: mutex_lock+0x27/0x40 kernel/locking/mutex.c:240
 PGD 8000000016ef2067 P4D 8000000016ef2067 PUD 3d6e9067 PMD 0
 Oops: 0002 [#1] SMP KASAN PTI
 CPU: 0 PID: 7005 Comm: syz-executor.5 Not tainted 4.12.14-396-default #1 SLE15-SP1 (unreleased)
 RIP: 0010:mutex_lock+0x27/0x40 kernel/locking/mutex.c:240
 RSP: 0018:ffff88000d487a00 EFLAGS: 00010246
 RAX: 0000000000000000 RBX: 000000000000000e RCX: 1ffff100082b0719
 ...
 CR2: 000000000000000e CR3: 000000004b1bc003 CR4: 0000000000060ef0
 Call Trace:
  kcm_create+0x600/0xbf0 [kcm]
  __sock_create+0x324/0x750 net/socket.c:1272
 ...

This is due to race between sock_create and unfinished
register_pernet_device. kcm_create tries to do "net_generic(net,
kcm_net_id)". but kcm_net_id is not initialized yet.

So switch the order of the two to close the race.

This can be reproduced with mutiple processes doing socket(PF_KCM, ...)
and one process doing module removal.

Fixes: ab7ac4eb9832 ("kcm: Kernel Connection Multiplexor module")
Reviewed-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/kcm/kcmsock.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 571d824e4e24..b919db02c7f9 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -2054,14 +2054,14 @@ static int __init kcm_init(void)
 	if (err)
 		goto fail;
 
-	err = sock_register(&kcm_family_ops);
-	if (err)
-		goto sock_register_fail;
-
 	err = register_pernet_device(&kcm_net_ops);
 	if (err)
 		goto net_ops_fail;
 
+	err = sock_register(&kcm_family_ops);
+	if (err)
+		goto sock_register_fail;
+
 	err = kcm_proc_init();
 	if (err)
 		goto proc_init_fail;
@@ -2069,12 +2069,12 @@ static int __init kcm_init(void)
 	return 0;
 
 proc_init_fail:
-	unregister_pernet_device(&kcm_net_ops);
-
-net_ops_fail:
 	sock_unregister(PF_KCM);
 
 sock_register_fail:
+	unregister_pernet_device(&kcm_net_ops);
+
+net_ops_fail:
 	proto_unregister(&kcm_proto);
 
 fail:
@@ -2090,8 +2090,8 @@ static int __init kcm_init(void)
 static void __exit kcm_exit(void)
 {
 	kcm_proc_exit();
-	unregister_pernet_device(&kcm_net_ops);
 	sock_unregister(PF_KCM);
+	unregister_pernet_device(&kcm_net_ops);
 	proto_unregister(&kcm_proto);
 	destroy_workqueue(kcm_wq);
 
-- 
2.20.1


From 97a020a73b4b970b740fbcf8f6d26305a9eb5dd0 Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Fri, 29 Mar 2019 09:18:02 +0800
Subject: [PATCH 07/36] net: ethtool: not call vzalloc for zero sized memory
 request

[ Upstream commit 3d8830266ffc28c16032b859e38a0252e014b631 ]

NULL or ZERO_SIZE_PTR will be returned for zero sized memory
request, and derefencing them will lead to a segfault

so it is unnecessory to call vzalloc for zero sized memory
request and not call functions which maybe derefence the
NULL allocated memory

this also fixes a possible memory leak if phy_ethtool_get_stats
returns error, memory should be freed before exit

Signed-off-by: Li RongQing <lirongqing@baidu.com>
Reviewed-by: Wang Li <wangli39@baidu.com>
Reviewed-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/ethtool.c | 46 ++++++++++++++++++++++++++++++----------------
 1 file changed, 30 insertions(+), 16 deletions(-)

diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 158264f7cfaf..3a7f19a61768 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -1794,11 +1794,16 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr)
 	WARN_ON_ONCE(!ret);
 
 	gstrings.len = ret;
-	data = vzalloc(array_size(gstrings.len, ETH_GSTRING_LEN));
-	if (gstrings.len && !data)
-		return -ENOMEM;
 
-	__ethtool_get_strings(dev, gstrings.string_set, data);
+	if (gstrings.len) {
+		data = vzalloc(array_size(gstrings.len, ETH_GSTRING_LEN));
+		if (!data)
+			return -ENOMEM;
+
+		__ethtool_get_strings(dev, gstrings.string_set, data);
+	} else {
+		data = NULL;
+	}
 
 	ret = -EFAULT;
 	if (copy_to_user(useraddr, &gstrings, sizeof(gstrings)))
@@ -1894,11 +1899,15 @@ static int ethtool_get_stats(struct net_device *dev, void __user *useraddr)
 		return -EFAULT;
 
 	stats.n_stats = n_stats;
-	data = vzalloc(array_size(n_stats, sizeof(u64)));
-	if (n_stats && !data)
-		return -ENOMEM;
 
-	ops->get_ethtool_stats(dev, &stats, data);
+	if (n_stats) {
+		data = vzalloc(array_size(n_stats, sizeof(u64)));
+		if (!data)
+			return -ENOMEM;
+		ops->get_ethtool_stats(dev, &stats, data);
+	} else {
+		data = NULL;
+	}
 
 	ret = -EFAULT;
 	if (copy_to_user(useraddr, &stats, sizeof(stats)))
@@ -1938,16 +1947,21 @@ static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr)
 		return -EFAULT;
 
 	stats.n_stats = n_stats;
-	data = vzalloc(array_size(n_stats, sizeof(u64)));
-	if (n_stats && !data)
-		return -ENOMEM;
 
-	if (dev->phydev && !ops->get_ethtool_phy_stats) {
-		ret = phy_ethtool_get_stats(dev->phydev, &stats, data);
-		if (ret < 0)
-			return ret;
+	if (n_stats) {
+		data = vzalloc(array_size(n_stats, sizeof(u64)));
+		if (!data)
+			return -ENOMEM;
+
+		if (dev->phydev && !ops->get_ethtool_phy_stats) {
+			ret = phy_ethtool_get_stats(dev->phydev, &stats, data);
+			if (ret < 0)
+				goto out;
+		} else {
+			ops->get_ethtool_phy_stats(dev, &stats, data);
+		}
 	} else {
-		ops->get_ethtool_phy_stats(dev, &stats, data);
+		data = NULL;
 	}
 
 	ret = -EFAULT;
-- 
2.20.1


From e86fde84a7b8e4a9476e1337a96fc0b7b0b953ef Mon Sep 17 00:00:00 2001
From: Steffen Klassert <steffen.klassert@secunet.com>
Date: Tue, 2 Apr 2019 08:16:03 +0200
Subject: [PATCH 08/36] net-gro: Fix GRO flush when receiving a GSO packet.

[ Upstream commit 0ab03f353d3613ea49d1f924faf98559003670a8 ]

Currently we may merge incorrectly a received GSO packet
or a packet with frag_list into a packet sitting in the
gro_hash list. skb_segment() may crash case because
the assumptions on the skb layout are not met.
The correct behaviour would be to flush the packet in the
gro_hash list and send the received GSO packet directly
afterwards. Commit d61d072e87c8e ("net-gro: avoid reorders")
sets NAPI_GRO_CB(skb)->flush in this case, but this is not
checked before merging. This patch makes sure to check this
flag and to not merge in that case.

Fixes: d61d072e87c8e ("net-gro: avoid reorders")
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 2415d9cb9b89..ef2cd5712098 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3801,7 +3801,7 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
 	unsigned int delta_truesize;
 	struct sk_buff *lp;
 
-	if (unlikely(p->len + len >= 65536))
+	if (unlikely(p->len + len >= 65536 || NAPI_GRO_CB(skb)->flush))
 		return -E2BIG;
 
 	lp = NAPI_GRO_CB(p)->last;
-- 
2.20.1


From a781ae97b05d1884b5379a13b9d890d78976503f Mon Sep 17 00:00:00 2001
From: Artemy Kovalyov <artemyko@mellanox.com>
Date: Tue, 19 Mar 2019 11:24:38 +0200
Subject: [PATCH 09/36] net/mlx5: Decrease default mr cache size

[ Upstream commit e8b26b2135dedc0284490bfeac06dfc4418d0105 ]

Delete initialization of high order entries in mr cache to decrease initial
memory footprint. When required, the administrator can populate the
entries with memory keys via the /sys interface.

This approach is very helpful to significantly reduce the per HW function
memory footprint in virtualization environments such as SRIOV.

Fixes: 9603b61de1ee ("mlx5: Move pci device handling from mlx5_ib to mlx5_core")
Signed-off-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reported-by:  Shalom Toledo <shalomt@mellanox.com>
Acked-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/main.c    | 20 -------------------
 1 file changed, 20 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index be81b319b0dc..694edd899322 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -163,26 +163,6 @@ static struct mlx5_profile profile[] = {
 			.size	= 8,
 			.limit	= 4
 		},
-		.mr_cache[16]	= {
-			.size	= 8,
-			.limit	= 4
-		},
-		.mr_cache[17]	= {
-			.size	= 8,
-			.limit	= 4
-		},
-		.mr_cache[18]	= {
-			.size	= 8,
-			.limit	= 4
-		},
-		.mr_cache[19]	= {
-			.size	= 4,
-			.limit	= 2
-		},
-		.mr_cache[20]	= {
-			.size	= 4,
-			.limit	= 2
-		},
 	},
 };
 
-- 
2.20.1


From 772e2a7ccc73a48ea17eee88b60991ad248aeeea Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 27 Mar 2019 08:21:30 -0700
Subject: [PATCH 10/36] netns: provide pure entropy for net_hash_mix()

[ Upstream commit 355b98553789b646ed97ad801a619ff898471b92 ]

net_hash_mix() currently uses kernel address of a struct net,
and is used in many places that could be used to reveal this
address to a patient attacker, thus defeating KASLR, for
the typical case (initial net namespace, &init_net is
not dynamically allocated)

I believe the original implementation tried to avoid spending
too many cycles in this function, but security comes first.

Also provide entropy regardless of CONFIG_NET_NS.

Fixes: 0b4419162aa6 ("netns: introduce the net_hash_mix "salt" for hashes")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Amit Klein <aksecurity@gmail.com>
Reported-by: Benny Pinkas <benny@pinkas.net>
Cc: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/net_namespace.h |  1 +
 include/net/netns/hash.h    | 10 ++--------
 net/core/net_namespace.c    |  1 +
 3 files changed, 4 insertions(+), 8 deletions(-)

diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 99d4148e0f90..1c3126c14930 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -58,6 +58,7 @@ struct net {
 						 */
 	spinlock_t		rules_mod_lock;
 
+	u32			hash_mix;
 	atomic64_t		cookie_gen;
 
 	struct list_head	list;		/* list of network namespaces */
diff --git a/include/net/netns/hash.h b/include/net/netns/hash.h
index 16a842456189..d9b665151f3d 100644
--- a/include/net/netns/hash.h
+++ b/include/net/netns/hash.h
@@ -2,16 +2,10 @@
 #ifndef __NET_NS_HASH_H__
 #define __NET_NS_HASH_H__
 
-#include <asm/cache.h>
-
-struct net;
+#include <net/net_namespace.h>
 
 static inline u32 net_hash_mix(const struct net *net)
 {
-#ifdef CONFIG_NET_NS
-	return (u32)(((unsigned long)net) >> ilog2(sizeof(*net)));
-#else
-	return 0;
-#endif
+	return net->hash_mix;
 }
 #endif
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index b02fb19df2cc..40c249c574c1 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -304,6 +304,7 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns)
 
 	refcount_set(&net->count, 1);
 	refcount_set(&net->passive, 1);
+	get_random_bytes(&net->hash_mix, sizeof(u32));
 	net->dev_base_seq = 1;
 	net->user_ns = user_ns;
 	idr_init(&net->netns_ids);
-- 
2.20.1


From b82ce3fc28ea3adbd2f2f753434fcee3e75c15e8 Mon Sep 17 00:00:00 2001
From: Mao Wenan <maowenan@huawei.com>
Date: Thu, 28 Mar 2019 17:10:56 +0800
Subject: [PATCH 11/36] net: rds: force to destroy connection if t_sock is NULL
 in rds_tcp_kill_sock().

[ Upstream commit cb66ddd156203daefb8d71158036b27b0e2caf63 ]

When it is to cleanup net namespace, rds_tcp_exit_net() will call
rds_tcp_kill_sock(), if t_sock is NULL, it will not call
rds_conn_destroy(), rds_conn_path_destroy() and rds_tcp_conn_free() to free
connection, and the worker cp_conn_w is not stopped, afterwards the net is freed in
net_drop_ns(); While cp_conn_w rds_connect_worker() will call rds_tcp_conn_path_connect()
and reference 'net' which has already been freed.

In rds_tcp_conn_path_connect(), rds_tcp_set_callbacks() will set t_sock = sock before
sock->ops->connect, but if connect() is failed, it will call
rds_tcp_restore_callbacks() and set t_sock = NULL, if connect is always
failed, rds_connect_worker() will try to reconnect all the time, so
rds_tcp_kill_sock() will never to cancel worker cp_conn_w and free the
connections.

Therefore, the condition !tc->t_sock is not needed if it is going to do
cleanup_net->rds_tcp_exit_net->rds_tcp_kill_sock, because tc->t_sock is always
NULL, and there is on other path to cancel cp_conn_w and free
connection. So this patch is to fix this.

rds_tcp_kill_sock():
...
if (net != c_net || !tc->t_sock)
...
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>

==================================================================
BUG: KASAN: use-after-free in inet_create+0xbcc/0xd28
net/ipv4/af_inet.c:340
Read of size 4 at addr ffff8003496a4684 by task kworker/u8:4/3721

CPU: 3 PID: 3721 Comm: kworker/u8:4 Not tainted 5.1.0 #11
Hardware name: linux,dummy-virt (DT)
Workqueue: krdsd rds_connect_worker
Call trace:
 dump_backtrace+0x0/0x3c0 arch/arm64/kernel/time.c:53
 show_stack+0x28/0x38 arch/arm64/kernel/traps.c:152
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x120/0x188 lib/dump_stack.c:113
 print_address_description+0x68/0x278 mm/kasan/report.c:253
 kasan_report_error mm/kasan/report.c:351 [inline]
 kasan_report+0x21c/0x348 mm/kasan/report.c:409
 __asan_report_load4_noabort+0x30/0x40 mm/kasan/report.c:429
 inet_create+0xbcc/0xd28 net/ipv4/af_inet.c:340
 __sock_create+0x4f8/0x770 net/socket.c:1276
 sock_create_kern+0x50/0x68 net/socket.c:1322
 rds_tcp_conn_path_connect+0x2b4/0x690 net/rds/tcp_connect.c:114
 rds_connect_worker+0x108/0x1d0 net/rds/threads.c:175
 process_one_work+0x6e8/0x1700 kernel/workqueue.c:2153
 worker_thread+0x3b0/0xdd0 kernel/workqueue.c:2296
 kthread+0x2f0/0x378 kernel/kthread.c:255
 ret_from_fork+0x10/0x18 arch/arm64/kernel/entry.S:1117

Allocated by task 687:
 save_stack mm/kasan/kasan.c:448 [inline]
 set_track mm/kasan/kasan.c:460 [inline]
 kasan_kmalloc+0xd4/0x180 mm/kasan/kasan.c:553
 kasan_slab_alloc+0x14/0x20 mm/kasan/kasan.c:490
 slab_post_alloc_hook mm/slab.h:444 [inline]
 slab_alloc_node mm/slub.c:2705 [inline]
 slab_alloc mm/slub.c:2713 [inline]
 kmem_cache_alloc+0x14c/0x388 mm/slub.c:2718
 kmem_cache_zalloc include/linux/slab.h:697 [inline]
 net_alloc net/core/net_namespace.c:384 [inline]
 copy_net_ns+0xc4/0x2d0 net/core/net_namespace.c:424
 create_new_namespaces+0x300/0x658 kernel/nsproxy.c:107
 unshare_nsproxy_namespaces+0xa0/0x198 kernel/nsproxy.c:206
 ksys_unshare+0x340/0x628 kernel/fork.c:2577
 __do_sys_unshare kernel/fork.c:2645 [inline]
 __se_sys_unshare kernel/fork.c:2643 [inline]
 __arm64_sys_unshare+0x38/0x58 kernel/fork.c:2643
 __invoke_syscall arch/arm64/kernel/syscall.c:35 [inline]
 invoke_syscall arch/arm64/kernel/syscall.c:47 [inline]
 el0_svc_common+0x168/0x390 arch/arm64/kernel/syscall.c:83
 el0_svc_handler+0x60/0xd0 arch/arm64/kernel/syscall.c:129
 el0_svc+0x8/0xc arch/arm64/kernel/entry.S:960

Freed by task 264:
 save_stack mm/kasan/kasan.c:448 [inline]
 set_track mm/kasan/kasan.c:460 [inline]
 __kasan_slab_free+0x114/0x220 mm/kasan/kasan.c:521
 kasan_slab_free+0x10/0x18 mm/kasan/kasan.c:528
 slab_free_hook mm/slub.c:1370 [inline]
 slab_free_freelist_hook mm/slub.c:1397 [inline]
 slab_free mm/slub.c:2952 [inline]
 kmem_cache_free+0xb8/0x3a8 mm/slub.c:2968
 net_free net/core/net_namespace.c:400 [inline]
 net_drop_ns.part.6+0x78/0x90 net/core/net_namespace.c:407
 net_drop_ns net/core/net_namespace.c:406 [inline]
 cleanup_net+0x53c/0x6d8 net/core/net_namespace.c:569
 process_one_work+0x6e8/0x1700 kernel/workqueue.c:2153
 worker_thread+0x3b0/0xdd0 kernel/workqueue.c:2296
 kthread+0x2f0/0x378 kernel/kthread.c:255
 ret_from_fork+0x10/0x18 arch/arm64/kernel/entry.S:1117

The buggy address belongs to the object at ffff8003496a3f80
 which belongs to the cache net_namespace of size 7872
The buggy address is located 1796 bytes inside of
 7872-byte region [ffff8003496a3f80, ffff8003496a5e40)
The buggy address belongs to the page:
page:ffff7e000d25a800 count:1 mapcount:0 mapping:ffff80036ce4b000
index:0x0 compound_mapcount: 0
flags: 0xffffe0000008100(slab|head)
raw: 0ffffe0000008100 dead000000000100 dead000000000200 ffff80036ce4b000
raw: 0000000000000000 0000000080040004 00000001ffffffff 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff8003496a4580: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff8003496a4600: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff8003496a4680: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                   ^
 ffff8003496a4700: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff8003496a4780: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
==================================================================

Fixes: 467fa15356ac("RDS-TCP: Support multiple RDS-TCP listen endpoints, one per netns.")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Mao Wenan <maowenan@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/tcp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index c16f0a362c32..a729c47db781 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -600,7 +600,7 @@ static void rds_tcp_kill_sock(struct net *net)
 	list_for_each_entry_safe(tc, _tc, &rds_tcp_conn_list, t_tcp_node) {
 		struct net *c_net = read_pnet(&tc->t_cpath->cp_conn->c_net);
 
-		if (net != c_net || !tc->t_sock)
+		if (net != c_net)
 			continue;
 		if (!list_has_conn(&tmp_list, tc->t_cpath->cp_conn)) {
 			list_move_tail(&tc->t_tcp_node, &tmp_list);
-- 
2.20.1


From 70b8ff685f736491bee98f399f14033e7dd402db Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Thu, 4 Apr 2019 12:31:35 +0200
Subject: [PATCH 12/36] net/sched: act_sample: fix divide by zero in the
 traffic path

[ Upstream commit fae2708174ae95d98d19f194e03d6e8f688ae195 ]

the control path of 'sample' action does not validate the value of 'rate'
provided by the user, but then it uses it as divisor in the traffic path.
Validate it in tcf_sample_init(), and return -EINVAL with a proper extack
message in case that value is zero, to fix a splat with the script below:

 # tc f a dev test0 egress matchall action sample rate 0 group 1 index 2
 # tc -s a s action sample
 total acts 1

         action order 0: sample rate 1/0 group 1 pipe
          index 2 ref 1 bind 1 installed 19 sec used 19 sec
         Action statistics:
         Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
         backlog 0b 0p requeues 0
 # ping 192.0.2.1 -I test0 -c1 -q

 divide error: 0000 [#1] SMP PTI
 CPU: 1 PID: 6192 Comm: ping Not tainted 5.1.0-rc2.diag2+ #591
 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
 RIP: 0010:tcf_sample_act+0x9e/0x1e0 [act_sample]
 Code: 6a f1 85 c0 74 0d 80 3d 83 1a 00 00 00 0f 84 9c 00 00 00 4d 85 e4 0f 84 85 00 00 00 e8 9b d7 9c f1 44 8b 8b e0 00 00 00 31 d2 <41> f7 f1 85 d2 75 70 f6 85 83 00 00 00 10 48 8b 45 10 8b 88 08 01
 RSP: 0018:ffffae320190ba30 EFLAGS: 00010246
 RAX: 00000000b0677d21 RBX: ffff8af1ed9ec000 RCX: 0000000059a9fe49
 RDX: 0000000000000000 RSI: 000000000c7e33b7 RDI: ffff8af23daa0af0
 RBP: ffff8af1ee11b200 R08: 0000000074fcaf7e R09: 0000000000000000
 R10: 0000000000000050 R11: ffffffffb3088680 R12: ffff8af232307f80
 R13: 0000000000000003 R14: ffff8af1ed9ec000 R15: 0000000000000000
 FS:  00007fe9c6d2f740(0000) GS:ffff8af23da80000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 00007fff6772f000 CR3: 00000000746a2004 CR4: 00000000001606e0
 Call Trace:
  tcf_action_exec+0x7c/0x1c0
  tcf_classify+0x57/0x160
  __dev_queue_xmit+0x3dc/0xd10
  ip_finish_output2+0x257/0x6d0
  ip_output+0x75/0x280
  ip_send_skb+0x15/0x40
  raw_sendmsg+0xae3/0x1410
  sock_sendmsg+0x36/0x40
  __sys_sendto+0x10e/0x140
  __x64_sys_sendto+0x24/0x30
  do_syscall_64+0x60/0x210
  entry_SYSCALL_64_after_hwframe+0x49/0xbe
  [...]
  Kernel panic - not syncing: Fatal exception in interrupt

Add a TDC selftest to document that 'rate' is now being validated.

Reported-by: Matteo Croce <mcroce@redhat.com>
Fixes: 5c5670fae430 ("net/sched: Introduce sample tc action")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Yotam Gigi <yotam.gi@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_sample.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 1a0c682fd734..fd62fe6c8e73 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -43,8 +43,8 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 	struct tc_action_net *tn = net_generic(net, sample_net_id);
 	struct nlattr *tb[TCA_SAMPLE_MAX + 1];
 	struct psample_group *psample_group;
+	u32 psample_group_num, rate;
 	struct tc_sample *parm;
-	u32 psample_group_num;
 	struct tcf_sample *s;
 	bool exists = false;
 	int ret, err;
@@ -80,6 +80,12 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 		return -EEXIST;
 	}
 
+	rate = nla_get_u32(tb[TCA_SAMPLE_RATE]);
+	if (!rate) {
+		NL_SET_ERR_MSG(extack, "invalid sample rate");
+		tcf_idr_release(*a, bind);
+		return -EINVAL;
+	}
 	psample_group_num = nla_get_u32(tb[TCA_SAMPLE_PSAMPLE_GROUP]);
 	psample_group = psample_group_get(net, psample_group_num);
 	if (!psample_group) {
@@ -91,7 +97,7 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 
 	spin_lock_bh(&s->tcf_lock);
 	s->tcf_action = parm->action;
-	s->rate = nla_get_u32(tb[TCA_SAMPLE_RATE]);
+	s->rate = rate;
 	s->psample_group_num = psample_group_num;
 	RCU_INIT_POINTER(s->psample_group, psample_group);
 
-- 
2.20.1


From fa1b7ccc8760d43387b2737234f32ecb1a89cc09 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Thu, 28 Mar 2019 10:35:06 +0100
Subject: [PATCH 13/36] net/sched: fix ->get helper of the matchall cls

[ Upstream commit 0db6f8befc32c68bb13d7ffbb2e563c79e913e13 ]

It returned always NULL, thus it was never possible to get the filter.

Example:
$ ip link add foo type dummy
$ ip link add bar type dummy
$ tc qdisc add dev foo clsact
$ tc filter add dev foo protocol all pref 1 ingress handle 1234 \
	matchall action mirred ingress mirror dev bar

Before the patch:
$ tc filter get dev foo protocol all pref 1 ingress handle 1234 matchall
Error: Specified filter handle not found.
We have an error talking to the kernel

After:
$ tc filter get dev foo protocol all pref 1 ingress handle 1234 matchall
filter ingress protocol all pref 1 matchall chain 0 handle 0x4d2
  not_in_hw
        action order 1: mirred (Ingress Mirror to device bar) pipe
        index 1 ref 1 bind 1

CC: Yotam Gigi <yotamg@mellanox.com>
CC: Jiri Pirko <jiri@mellanox.com>
Fixes: fd62d9f5c575 ("net/sched: matchall: Fix configuration race")
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_matchall.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index 0e408ee9dcec..5ba07cd11e31 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -125,6 +125,11 @@ static void mall_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack)
 
 static void *mall_get(struct tcf_proto *tp, u32 handle)
 {
+	struct cls_mall_head *head = rtnl_dereference(tp->root);
+
+	if (head && head->handle == handle)
+		return head;
+
 	return NULL;
 }
 
-- 
2.20.1


From a35f27526cd6ebd12812a83f224fa0e60d76ae52 Mon Sep 17 00:00:00 2001
From: Andrea Righi <andrea.righi@canonical.com>
Date: Thu, 28 Mar 2019 07:36:00 +0100
Subject: [PATCH 14/36] openvswitch: fix flow actions reallocation

[ Upstream commit f28cd2af22a0c134e4aa1c64a70f70d815d473fb ]

The flow action buffer can be resized if it's not big enough to contain
all the requested flow actions. However, this resize doesn't take into
account the new requested size, the buffer is only increased by a factor
of 2x. This might be not enough to contain the new data, causing a
buffer overflow, for example:

[   42.044472] =============================================================================
[   42.045608] BUG kmalloc-96 (Not tainted): Redzone overwritten
[   42.046415] -----------------------------------------------------------------------------

[   42.047715] Disabling lock debugging due to kernel taint
[   42.047716] INFO: 0x8bf2c4a5-0x720c0928. First byte 0x0 instead of 0xcc
[   42.048677] INFO: Slab 0xbc6d2040 objects=29 used=18 fp=0xdc07dec4 flags=0x2808101
[   42.049743] INFO: Object 0xd53a3464 @offset=2528 fp=0xccdcdebb

[   42.050747] Redzone 76f1b237: cc cc cc cc cc cc cc cc                          ........
[   42.051839] Object d53a3464: 6b 6b 6b 6b 6b 6b 6b 6b 0c 00 00 00 6c 00 00 00  kkkkkkkk....l...
[   42.053015] Object f49a30cc: 6c 00 0c 00 00 00 00 00 00 00 00 03 78 a3 15 f6  l...........x...
[   42.054203] Object acfe4220: 20 00 02 00 ff ff ff ff 00 00 00 00 00 00 00 00   ...............
[   42.055370] Object 21024e91: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
[   42.056541] Object 070e04c3: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
[   42.057797] Object 948a777a: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
[   42.059061] Redzone 8bf2c4a5: 00 00 00 00                                      ....
[   42.060189] Padding a681b46e: 5a 5a 5a 5a 5a 5a 5a 5a                          ZZZZZZZZ

Fix by making sure the new buffer is properly resized to contain all the
requested data.

BugLink: https://bugs.launchpad.net/bugs/1813244
Signed-off-by: Andrea Righi <andrea.righi@canonical.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/flow_netlink.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 691da853bef5..4bdf5e3ac208 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -2306,14 +2306,14 @@ static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa,
 
 	struct sw_flow_actions *acts;
 	int new_acts_size;
-	int req_size = NLA_ALIGN(attr_len);
+	size_t req_size = NLA_ALIGN(attr_len);
 	int next_offset = offsetof(struct sw_flow_actions, actions) +
 					(*sfa)->actions_len;
 
 	if (req_size <= (ksize(*sfa) - next_offset))
 		goto out;
 
-	new_acts_size = ksize(*sfa) * 2;
+	new_acts_size = max(next_offset + req_size, ksize(*sfa) * 2);
 
 	if (new_acts_size > MAX_ACTIONS_BUFSIZE) {
 		if ((MAX_ACTIONS_BUFSIZE - next_offset) < req_size) {
-- 
2.20.1


From 081a22d5c9ad32b4f7847ef5af09dfb7b52e2124 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Wed, 27 Mar 2019 15:26:01 +0100
Subject: [PATCH 15/36] qmi_wwan: add Olicard 600
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 6289d0facd9ebce4cc83e5da39e15643ee998dc5 ]

This is a Qualcomm based device with a QMI function on interface 4.
It is mode switched from 2020:2030 using a standard eject message.

T:  Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#=  6 Spd=480  MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=2020 ProdID=2031 Rev= 2.32
S:  Manufacturer=Mobile Connect
S:  Product=Mobile Connect
S:  SerialNumber=0123456789ABCDEF
C:* #Ifs= 6 Cfg#= 1 Atr=80 MxPwr=500mA
I:* If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none)
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=(none)
E:  Ad=83(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=(none)
E:  Ad=85(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=(none)
E:  Ad=87(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none)
E:  Ad=89(I) Atr=03(Int.) MxPS=   8 Ivl=32ms
E:  Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 5 Alt= 0 #EPs= 2 Cls=08(stor.) Sub=06 Prot=50 Driver=(none)
E:  Ad=8a(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=06(O) Atr=02(Bulk) MxPS= 512 Ivl=125us

Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 74bebbdb4b15..9195f3476b1d 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1203,6 +1203,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x19d2, 0x2002, 4)},	/* ZTE (Vodafone) K3765-Z */
 	{QMI_FIXED_INTF(0x2001, 0x7e19, 4)},	/* D-Link DWM-221 B1 */
 	{QMI_FIXED_INTF(0x2001, 0x7e35, 4)},	/* D-Link DWM-222 */
+	{QMI_FIXED_INTF(0x2020, 0x2031, 4)},	/* Olicard 600 */
 	{QMI_FIXED_INTF(0x2020, 0x2033, 4)},	/* BroadMobi BM806U */
 	{QMI_FIXED_INTF(0x0f3d, 0x68a2, 8)},    /* Sierra Wireless MC7700 */
 	{QMI_FIXED_INTF(0x114f, 0x68a2, 8)},    /* Sierra Wireless MC7750 */
-- 
2.20.1


From 07a38681c3d1638daeb15da6a7c2f782bbaf76fd Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 5 Apr 2019 20:46:46 +0200
Subject: [PATCH 16/36] r8169: disable ASPM again

[ Upstream commit b75bb8a5b755d0c7bf1ac071e4df2349a7644a1e ]

There's a significant number of reports that re-enabling ASPM causes
different issues, ranging from decreased performance to system not
booting at all. This affects only a minority of users, but the number
of affected users is big enough that we better switch off ASPM again.

This will hurt notebook users who are not affected by the issues, they
may see decreased battery runtime w/o ASPM. With the PCI core folks is
being discussed to add generic sysfs attributes to control ASPM.
Once this is in place brave enough users can re-enable ASPM on their
system.

Fixes: a99790bf5c7f ("r8169: Reinstate ASPM Support")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index f55d177ae894..5adb00f521db 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -28,6 +28,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/firmware.h>
 #include <linux/prefetch.h>
+#include <linux/pci-aspm.h>
 #include <linux/ipv6.h>
 #include <net/ip6_checksum.h>
 
@@ -7224,6 +7225,11 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 			return rc;
 	}
 
+	/* Disable ASPM completely as that cause random device stop working
+	 * problems as well as full system hangs for some PCIe devices users.
+	 */
+	pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1);
+
 	/* enable device (incl. PCI PM wakeup and hotplug setup) */
 	rc = pcim_enable_device(pdev);
 	if (rc < 0) {
-- 
2.20.1


From 03bf962ea549a82fea55642b548419673cdee027 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 31 Mar 2019 16:58:15 +0800
Subject: [PATCH 17/36] sctp: initialize _pad of sockaddr_in before copying to
 user memory

[ Upstream commit 09279e615c81ce55e04835970601ae286e3facbe ]

Syzbot report a kernel-infoleak:

  BUG: KMSAN: kernel-infoleak in _copy_to_user+0x16b/0x1f0 lib/usercopy.c:32
  Call Trace:
    _copy_to_user+0x16b/0x1f0 lib/usercopy.c:32
    copy_to_user include/linux/uaccess.h:174 [inline]
    sctp_getsockopt_peer_addrs net/sctp/socket.c:5911 [inline]
    sctp_getsockopt+0x1668e/0x17f70 net/sctp/socket.c:7562
    ...
  Uninit was stored to memory at:
    sctp_transport_init net/sctp/transport.c:61 [inline]
    sctp_transport_new+0x16d/0x9a0 net/sctp/transport.c:115
    sctp_assoc_add_peer+0x532/0x1f70 net/sctp/associola.c:637
    sctp_process_param net/sctp/sm_make_chunk.c:2548 [inline]
    sctp_process_init+0x1a1b/0x3ed0 net/sctp/sm_make_chunk.c:2361
    ...
  Bytes 8-15 of 16 are uninitialized

It was caused by that th _pad field (the 8-15 bytes) of a v4 addr (saved in
struct sockaddr_in) wasn't initialized, but directly copied to user memory
in sctp_getsockopt_peer_addrs().

So fix it by calling memset(addr->v4.sin_zero, 0, 8) to initialize _pad of
sockaddr_in before copying it to user memory in sctp_v4_addr_to_user(), as
sctp_v6_addr_to_user() does.

Reported-by: syzbot+86b5c7c236a22616a72f@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Tested-by: Alexander Potapenko <glider@google.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/protocol.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 6abc8b274270..951afdeea5e9 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -600,6 +600,7 @@ static struct sock *sctp_v4_create_accept_sk(struct sock *sk,
 static int sctp_v4_addr_to_user(struct sctp_sock *sp, union sctp_addr *addr)
 {
 	/* No address mapping for V4 sockets */
+	memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
 	return sizeof(struct sockaddr_in);
 }
 
-- 
2.20.1


From f24ced63fedf72114bdb5c6423298483ec49bc35 Mon Sep 17 00:00:00 2001
From: Koen De Schepper <koen.de_schepper@nokia-bell-labs.com>
Date: Thu, 4 Apr 2019 12:24:02 +0000
Subject: [PATCH 18/36] tcp: Ensure DCTCP reacts to losses
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit aecfde23108b8e637d9f5c5e523b24fb97035dc3 ]

RFC8257 §3.5 explicitly states that "A DCTCP sender MUST react to
loss episodes in the same way as conventional TCP".

Currently, Linux DCTCP performs no cwnd reduction when losses
are encountered. Optionally, the dctcp_clamp_alpha_on_loss resets
alpha to its maximal value if a RTO happens. This behavior
is sub-optimal for at least two reasons: i) it ignores losses
triggering fast retransmissions; and ii) it causes unnecessary large
cwnd reduction in the future if the loss was isolated as it resets
the historical term of DCTCP's alpha EWMA to its maximal value (i.e.,
denoting a total congestion). The second reason has an especially
noticeable effect when using DCTCP in high BDP environments, where
alpha normally stays at low values.

This patch replace the clamping of alpha by setting ssthresh to
half of cwnd for both fast retransmissions and RTOs, at most once
per RTT. Consequently, the dctcp_clamp_alpha_on_loss module parameter
has been removed.

The table below shows experimental results where we measured the
drop probability of a PIE AQM (not applying ECN marks) at a
bottleneck in the presence of a single TCP flow with either the
alpha-clamping option enabled or the cwnd halving proposed by this
patch. Results using reno or cubic are given for comparison.

                          |  Link   |   RTT    |    Drop
                 TCP CC   |  speed  | base+AQM | probability
        ==================|=========|==========|============
                    CUBIC |  40Mbps |  7+20ms  |    0.21%
                     RENO |         |          |    0.19%
        DCTCP-CLAMP-ALPHA |         |          |   25.80%
         DCTCP-HALVE-CWND |         |          |    0.22%
        ------------------|---------|----------|------------
                    CUBIC | 100Mbps |  7+20ms  |    0.03%
                     RENO |         |          |    0.02%
        DCTCP-CLAMP-ALPHA |         |          |   23.30%
         DCTCP-HALVE-CWND |         |          |    0.04%
        ------------------|---------|----------|------------
                    CUBIC | 800Mbps |   1+1ms  |    0.04%
                     RENO |         |          |    0.05%
        DCTCP-CLAMP-ALPHA |         |          |   18.70%
         DCTCP-HALVE-CWND |         |          |    0.06%

We see that, without halving its cwnd for all source of losses,
DCTCP drives the AQM to large drop probabilities in order to keep
the queue length under control (i.e., it repeatedly faces RTOs).
Instead, if DCTCP reacts to all source of losses, it can then be
controlled by the AQM using similar drop levels than cubic or reno.

Signed-off-by: Koen De Schepper <koen.de_schepper@nokia-bell-labs.com>
Signed-off-by: Olivier Tilmans <olivier.tilmans@nokia-bell-labs.com>
Cc: Bob Briscoe <research@bobbriscoe.net>
Cc: Lawrence Brakmo <brakmo@fb.com>
Cc: Florian Westphal <fw@strlen.de>
Cc: Daniel Borkmann <borkmann@iogearbox.net>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Andrew Shewmaker <agshew@gmail.com>
Cc: Glenn Judd <glenn.judd@morganstanley.com>
Acked-by: Florian Westphal <fw@strlen.de>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_dctcp.c | 36 ++++++++++++++++++------------------
 1 file changed, 18 insertions(+), 18 deletions(-)

diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index cd4814f7e962..359da68d7c06 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -67,11 +67,6 @@ static unsigned int dctcp_alpha_on_init __read_mostly = DCTCP_MAX_ALPHA;
 module_param(dctcp_alpha_on_init, uint, 0644);
 MODULE_PARM_DESC(dctcp_alpha_on_init, "parameter for initial alpha value");
 
-static unsigned int dctcp_clamp_alpha_on_loss __read_mostly;
-module_param(dctcp_clamp_alpha_on_loss, uint, 0644);
-MODULE_PARM_DESC(dctcp_clamp_alpha_on_loss,
-		 "parameter for clamping alpha on loss");
-
 static struct tcp_congestion_ops dctcp_reno;
 
 static void dctcp_reset(const struct tcp_sock *tp, struct dctcp *ca)
@@ -164,21 +159,23 @@ static void dctcp_update_alpha(struct sock *sk, u32 flags)
 	}
 }
 
-static void dctcp_state(struct sock *sk, u8 new_state)
+static void dctcp_react_to_loss(struct sock *sk)
 {
-	if (dctcp_clamp_alpha_on_loss && new_state == TCP_CA_Loss) {
-		struct dctcp *ca = inet_csk_ca(sk);
+	struct dctcp *ca = inet_csk_ca(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
 
-		/* If this extension is enabled, we clamp dctcp_alpha to
-		 * max on packet loss; the motivation is that dctcp_alpha
-		 * is an indicator to the extend of congestion and packet
-		 * loss is an indicator of extreme congestion; setting
-		 * this in practice turned out to be beneficial, and
-		 * effectively assumes total congestion which reduces the
-		 * window by half.
-		 */
-		ca->dctcp_alpha = DCTCP_MAX_ALPHA;
-	}
+	ca->loss_cwnd = tp->snd_cwnd;
+	tp->snd_ssthresh = max(tp->snd_cwnd >> 1U, 2U);
+}
+
+static void dctcp_state(struct sock *sk, u8 new_state)
+{
+	if (new_state == TCP_CA_Recovery &&
+	    new_state != inet_csk(sk)->icsk_ca_state)
+		dctcp_react_to_loss(sk);
+	/* We handle RTO in dctcp_cwnd_event to ensure that we perform only
+	 * one loss-adjustment per RTT.
+	 */
 }
 
 static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
@@ -190,6 +187,9 @@ static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
 	case CA_EVENT_ECN_NO_CE:
 		dctcp_ece_ack_update(sk, ev, &ca->prior_rcv_nxt, &ca->ce_state);
 		break;
+	case CA_EVENT_LOSS:
+		dctcp_react_to_loss(sk);
+		break;
 	default:
 		/* Don't care for the rest. */
 		break;
-- 
2.20.1


From fded755f2dab83d4d3478bcb4db16ad34e3fe9f7 Mon Sep 17 00:00:00 2001
From: Dust Li <dust.li@linux.alibaba.com>
Date: Mon, 1 Apr 2019 16:04:53 +0800
Subject: [PATCH 19/36] tcp: fix a potential NULL pointer dereference in
 tcp_sk_exit

[ Upstream commit b506bc975f60f06e13e74adb35e708a23dc4e87c ]

 When tcp_sk_init() failed in inet_ctl_sock_create(),
 'net->ipv4.tcp_congestion_control' will be left
 uninitialized, but tcp_sk_exit() hasn't check for
 that.

 This patch add checking on 'net->ipv4.tcp_congestion_control'
 in tcp_sk_exit() to prevent NULL-ptr dereference.

Fixes: 6670e1524477 ("tcp: Namespace-ify sysctl_tcp_default_congestion_control")
Signed-off-by: Dust Li <dust.li@linux.alibaba.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 1aae9ab57fe9..00852f47a73d 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2578,7 +2578,8 @@ static void __net_exit tcp_sk_exit(struct net *net)
 {
 	int cpu;
 
-	module_put(net->ipv4.tcp_congestion_control->owner);
+	if (net->ipv4.tcp_congestion_control)
+		module_put(net->ipv4.tcp_congestion_control->owner);
 
 	for_each_possible_cpu(cpu)
 		inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu));
-- 
2.20.1


From f8e056f528850e06f0b53567f9b41a412ff4d9f6 Mon Sep 17 00:00:00 2001
From: Stephen Suryaputra <ssuryaextr@gmail.com>
Date: Mon, 1 Apr 2019 09:17:32 -0400
Subject: [PATCH 20/36] vrf: check accept_source_route on the original
 netdevice

[ Upstream commit 8c83f2df9c6578ea4c5b940d8238ad8a41b87e9e ]

Configuration check to accept source route IP options should be made on
the incoming netdevice when the skb->dev is an l3mdev master. The route
lookup for the source route next hop also needs the incoming netdev.

v2->v3:
- Simplify by passing the original netdevice down the stack (per David
  Ahern).

Signed-off-by: Stephen Suryaputra <ssuryaextr@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h      | 2 +-
 net/ipv4/ip_input.c   | 7 +++----
 net/ipv4/ip_options.c | 4 ++--
 3 files changed, 6 insertions(+), 7 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index be3cad9c2e4c..583526aad1d0 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -677,7 +677,7 @@ int ip_options_get_from_user(struct net *net, struct ip_options_rcu **optp,
 			     unsigned char __user *data, int optlen);
 void ip_options_undo(struct ip_options *opt);
 void ip_forward_options(struct sk_buff *skb);
-int ip_options_rcv_srr(struct sk_buff *skb);
+int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev);
 
 /*
  *	Functions provided by ip_sockglue.c
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 1f4737b77067..ccf0d31b6ce5 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -257,11 +257,10 @@ int ip_local_deliver(struct sk_buff *skb)
 		       ip_local_deliver_finish);
 }
 
-static inline bool ip_rcv_options(struct sk_buff *skb)
+static inline bool ip_rcv_options(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ip_options *opt;
 	const struct iphdr *iph;
-	struct net_device *dev = skb->dev;
 
 	/* It looks as overkill, because not all
 	   IP options require packet mangling.
@@ -297,7 +296,7 @@ static inline bool ip_rcv_options(struct sk_buff *skb)
 			}
 		}
 
-		if (ip_options_rcv_srr(skb))
+		if (ip_options_rcv_srr(skb, dev))
 			goto drop;
 	}
 
@@ -353,7 +352,7 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk,
 	}
 #endif
 
-	if (iph->ihl > 5 && ip_rcv_options(skb))
+	if (iph->ihl > 5 && ip_rcv_options(skb, dev))
 		goto drop;
 
 	rt = skb_rtable(skb);
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index 32a35043c9f5..3db31bb9df50 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -612,7 +612,7 @@ void ip_forward_options(struct sk_buff *skb)
 	}
 }
 
-int ip_options_rcv_srr(struct sk_buff *skb)
+int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ip_options *opt = &(IPCB(skb)->opt);
 	int srrspace, srrptr;
@@ -647,7 +647,7 @@ int ip_options_rcv_srr(struct sk_buff *skb)
 
 		orefdst = skb->_skb_refdst;
 		skb_dst_set(skb, NULL);
-		err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, skb->dev);
+		err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, dev);
 		rt2 = skb_rtable(skb);
 		if (err || (rt2->rt_type != RTN_UNICAST && rt2->rt_type != RTN_LOCAL)) {
 			skb_dst_drop(skb);
-- 
2.20.1


From 7f0257ab530138b57136ad6afa601f3062c98111 Mon Sep 17 00:00:00 2001
From: Gavi Teitz <gavi@mellanox.com>
Date: Mon, 11 Mar 2019 11:56:34 +0200
Subject: [PATCH 21/36] net/mlx5e: Fix error handling when refreshing TIRs

[ Upstream commit bc87a0036826a37b43489b029af8143bd07c6cca ]

Previously, a false positive would be caught if the TIRs list is
empty, since the err value was initialized to -ENOMEM, and was only
updated if a TIR is refreshed. This is resolved by initializing the
err value to zero.

Fixes: b676f653896a ("net/mlx5e: Refactor refresh TIRs")
Signed-off-by: Gavi Teitz <gavi@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_common.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
index 3078491cc0d0..8100786f6fb5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
@@ -141,15 +141,17 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5e_tir *tir;
-	int err  = -ENOMEM;
+	int err  = 0;
 	u32 tirn = 0;
 	int inlen;
 	void *in;
 
 	inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
 	in = kvzalloc(inlen, GFP_KERNEL);
-	if (!in)
+	if (!in) {
+		err = -ENOMEM;
 		goto out;
+	}
 
 	if (enable_uc_lb)
 		MLX5_SET(modify_tir_in, in, ctx.self_lb_block,
-- 
2.20.1


From 67277f572fe93a9f7fc186f293f43a493b2d212c Mon Sep 17 00:00:00 2001
From: Yuval Avnery <yuvalav@mellanox.com>
Date: Mon, 11 Mar 2019 06:18:24 +0200
Subject: [PATCH 22/36] net/mlx5e: Add a lock on tir list

[ Upstream commit 80a2a9026b24c6bd34b8d58256973e22270bedec ]

Refresh tirs is looping over a global list of tirs while netdevs are
adding and removing tirs from that list. That is why a lock is
required.

Fixes: 724b2aa15126 ("net/mlx5e: TIRs management refactoring")
Signed-off-by: Yuval Avnery <yuvalav@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_common.c | 7 +++++++
 include/linux/mlx5/driver.h                         | 2 ++
 2 files changed, 9 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
index 8100786f6fb5..1539cf3de5dc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
@@ -45,7 +45,9 @@ int mlx5e_create_tir(struct mlx5_core_dev *mdev,
 	if (err)
 		return err;
 
+	mutex_lock(&mdev->mlx5e_res.td.list_lock);
 	list_add(&tir->list, &mdev->mlx5e_res.td.tirs_list);
+	mutex_unlock(&mdev->mlx5e_res.td.list_lock);
 
 	return 0;
 }
@@ -53,8 +55,10 @@ int mlx5e_create_tir(struct mlx5_core_dev *mdev,
 void mlx5e_destroy_tir(struct mlx5_core_dev *mdev,
 		       struct mlx5e_tir *tir)
 {
+	mutex_lock(&mdev->mlx5e_res.td.list_lock);
 	mlx5_core_destroy_tir(mdev, tir->tirn);
 	list_del(&tir->list);
+	mutex_unlock(&mdev->mlx5e_res.td.list_lock);
 }
 
 static int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn,
@@ -114,6 +118,7 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev)
 	}
 
 	INIT_LIST_HEAD(&mdev->mlx5e_res.td.tirs_list);
+	mutex_init(&mdev->mlx5e_res.td.list_lock);
 
 	return 0;
 
@@ -159,6 +164,7 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb)
 
 	MLX5_SET(modify_tir_in, in, bitmask.self_lb_en, 1);
 
+	mutex_lock(&mdev->mlx5e_res.td.list_lock);
 	list_for_each_entry(tir, &mdev->mlx5e_res.td.tirs_list, list) {
 		tirn = tir->tirn;
 		err = mlx5_core_modify_tir(mdev, tirn, in, inlen);
@@ -170,6 +176,7 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb)
 	kvfree(in);
 	if (err)
 		netdev_err(priv->netdev, "refresh tir(0x%x) failed, %d\n", tirn, err);
+	mutex_unlock(&mdev->mlx5e_res.td.list_lock);
 
 	return err;
 }
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 54299251d40d..4f001619f854 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -591,6 +591,8 @@ enum mlx5_pagefault_type_flags {
 };
 
 struct mlx5_td {
+	/* protects tirs list changes while tirs refresh */
+	struct mutex     list_lock;
 	struct list_head tirs_list;
 	u32              tdn;
 };
-- 
2.20.1


From fb6c1d07c38bcbbbbab8b7dc7f7ef28d64489eca Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 27 Mar 2019 11:38:38 -0700
Subject: [PATCH 23/36] nfp: validate the return code from dev_queue_xmit()

[ Upstream commit c8ba5b91a04e3e2643e48501c114108802f21cda ]

dev_queue_xmit() may return error codes as well as netdev_tx_t,
and it always consumes the skb.  Make sure we always return a
correct netdev_tx_t value.

Fixes: eadfa4c3be99 ("nfp: add stats and xmit helpers for representors")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net_repr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
index 69d7aebda09b..7d62e3698f08 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
@@ -196,7 +196,7 @@ static netdev_tx_t nfp_repr_xmit(struct sk_buff *skb, struct net_device *netdev)
 	ret = dev_queue_xmit(skb);
 	nfp_repr_inc_tx_stats(netdev, len, ret);
 
-	return ret;
+	return NETDEV_TX_OK;
 }
 
 static int nfp_repr_stop(struct net_device *netdev)
-- 
2.20.1


From fb125d09bb936dbde2f66fb10369bdcc1a69404b Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 27 Mar 2019 11:38:39 -0700
Subject: [PATCH 24/36] nfp: disable netpoll on representors

[ Upstream commit c3e1f7fff69c78169c8ac40cc74ac4307f74e36d ]

NFP reprs are software device on top of the PF's vNIC.
The comment above __dev_queue_xmit() sayeth:

 When calling this method, interrupts MUST be enabled.  This is because
 the BH enable code must have IRQs enabled so that it will not deadlock.

For netconsole we can't guarantee IRQ state, let's just
disable netpoll on representors to be on the safe side.

When the initial implementation of NFP reprs was added by the
commit 5de73ee46704 ("nfp: general representor implementation")
.ndo_poll_controller was required for netpoll to be enabled.

Fixes: ac3d9dd034e5 ("netpoll: make ndo_poll_controller() optional")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net_repr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
index 7d62e3698f08..73db94e55fd0 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
@@ -384,7 +384,7 @@ int nfp_repr_init(struct nfp_app *app, struct net_device *netdev,
 	netdev->features &= ~(NETIF_F_TSO | NETIF_F_TSO6);
 	netdev->gso_max_segs = NFP_NET_LSO_MAX_SEGS;
 
-	netdev->priv_flags |= IFF_NO_QUEUE;
+	netdev->priv_flags |= IFF_NO_QUEUE | IFF_DISABLE_NETPOLL;
 	netdev->features |= NETIF_F_LLTX;
 
 	if (nfp_app_has_tc(app)) {
-- 
2.20.1


From 8c4020e67e1e06776e09adbf906a8d50ce500a1b Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Mon, 8 Apr 2019 17:39:54 -0400
Subject: [PATCH 25/36] bnxt_en: Improve RX consumer index validity check.

[ Upstream commit a1b0e4e684e9c300b9e759b46cb7a0147e61ddff ]

There is logic to check that the RX/TPA consumer index is the expected
index to work around a hardware problem.  However, the potentially bad
consumer index is first used to index into an array to reference an entry.
This can potentially crash if the bad consumer index is beyond legal
range.  Improve the logic to use the consumer index for dereferencing
after the validity check and log an error message.

Fixes: fa7e28127a5a ("bnxt_en: Add workaround to detect bad opaque in rx completion (part 2)")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 803f7990d32b..351417e74ae2 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1129,6 +1129,8 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 	tpa_info = &rxr->rx_tpa[agg_id];
 
 	if (unlikely(cons != rxr->rx_next_cons)) {
+		netdev_warn(bp->dev, "TPA cons %x != expected cons %x\n",
+			    cons, rxr->rx_next_cons);
 		bnxt_sched_reset(bp, rxr);
 		return;
 	}
@@ -1581,15 +1583,17 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	}
 
 	cons = rxcmp->rx_cmp_opaque;
-	rx_buf = &rxr->rx_buf_ring[cons];
-	data = rx_buf->data;
-	data_ptr = rx_buf->data_ptr;
 	if (unlikely(cons != rxr->rx_next_cons)) {
 		int rc1 = bnxt_discard_rx(bp, cpr, raw_cons, rxcmp);
 
+		netdev_warn(bp->dev, "RX cons %x != expected cons %x\n",
+			    cons, rxr->rx_next_cons);
 		bnxt_sched_reset(bp, rxr);
 		return rc1;
 	}
+	rx_buf = &rxr->rx_buf_ring[cons];
+	data = rx_buf->data;
+	data_ptr = rx_buf->data_ptr;
 	prefetch(data_ptr);
 
 	misc = le32_to_cpu(rxcmp->rx_cmp_misc_v1);
-- 
2.20.1


From 2bf6150ab4749c4fe7c7e2cc340ea5da0beabd71 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Mon, 8 Apr 2019 17:39:55 -0400
Subject: [PATCH 26/36] bnxt_en: Reset device on RX buffer errors.

[ Upstream commit 8e44e96c6c8e8fb80b84a2ca11798a8554f710f2 ]

If the RX completion indicates RX buffers errors, the RX ring will be
disabled by firmware and no packets will be received on that ring from
that point on.  Recover by resetting the device.

Fixes: c0c050c58d84 ("bnxt_en: New Broadcom ethernet driver.")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 351417e74ae2..40ca339ec3df 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1610,11 +1610,17 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 
 	rx_buf->data = NULL;
 	if (rxcmp1->rx_cmp_cfa_code_errors_v2 & RX_CMP_L2_ERRORS) {
+		u32 rx_err = le32_to_cpu(rxcmp1->rx_cmp_cfa_code_errors_v2);
+
 		bnxt_reuse_rx_data(rxr, cons, data);
 		if (agg_bufs)
 			bnxt_reuse_rx_agg_bufs(cpr, cp_cons, agg_bufs);
 
 		rc = -EIO;
+		if (rx_err & RX_CMPL_ERRORS_BUFFER_ERROR_MASK) {
+			netdev_warn(bp->dev, "RX buffer error %x\n", rx_err);
+			bnxt_sched_reset(bp, rxr);
+		}
 		goto next_rx;
 	}
 
-- 
2.20.1


From 2616f64d6afa854ee05e7867e31a5fe4479a3ed2 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Sat, 6 Apr 2019 17:16:52 +0200
Subject: [PATCH 27/36] net: ip_gre: fix possible use-after-free in erspan_rcv

[ Upstream commit 492b67e28ee5f2a2522fb72e3d3bcb990e461514 ]

erspan tunnels run __iptunnel_pull_header on received skbs to remove
gre and erspan headers. This can determine a possible use-after-free
accessing pkt_md pointer in erspan_rcv since the packet will be 'uncloned'
running pskb_expand_head if it is a cloned gso skb (e.g if the packet has
been sent though a veth device). Fix it resetting pkt_md pointer after
__iptunnel_pull_header

Fixes: 1d7e2ed22f8d ("net: erspan: refactor existing erspan code")
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_gre.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 6ae89f2b541b..2d5734079e6b 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -259,7 +259,6 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 	struct net *net = dev_net(skb->dev);
 	struct metadata_dst *tun_dst = NULL;
 	struct erspan_base_hdr *ershdr;
-	struct erspan_metadata *pkt_md;
 	struct ip_tunnel_net *itn;
 	struct ip_tunnel *tunnel;
 	const struct iphdr *iph;
@@ -282,9 +281,6 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 		if (unlikely(!pskb_may_pull(skb, len)))
 			return PACKET_REJECT;
 
-		ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len);
-		pkt_md = (struct erspan_metadata *)(ershdr + 1);
-
 		if (__iptunnel_pull_header(skb,
 					   len,
 					   htons(ETH_P_TEB),
@@ -292,8 +288,9 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 			goto drop;
 
 		if (tunnel->collect_md) {
+			struct erspan_metadata *pkt_md, *md;
 			struct ip_tunnel_info *info;
-			struct erspan_metadata *md;
+			unsigned char *gh;
 			__be64 tun_id;
 			__be16 flags;
 
@@ -306,6 +303,14 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 			if (!tun_dst)
 				return PACKET_REJECT;
 
+			/* skb can be uncloned in __iptunnel_pull_header, so
+			 * old pkt_md is no longer valid and we need to reset
+			 * it
+			 */
+			gh = skb_network_header(skb) +
+			     skb_network_header_len(skb);
+			pkt_md = (struct erspan_metadata *)(gh + gre_hdr_len +
+							    sizeof(*ershdr));
 			md = ip_tunnel_info_opts(&tun_dst->u.tun_info);
 			md->version = ver;
 			md2 = &md->u.md2;
-- 
2.20.1


From 8a6641db68881dfa22fff50a2320f042ee59608b Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Sat, 6 Apr 2019 17:16:53 +0200
Subject: [PATCH 28/36] net: ip6_gre: fix possible use-after-free in
 ip6erspan_rcv

[ Upstream commit 2a3cabae4536edbcb21d344e7aa8be7a584d2afb ]

erspan_v6 tunnels run __iptunnel_pull_header on received skbs to remove
erspan header. This can determine a possible use-after-free accessing
pkt_md pointer in ip6erspan_rcv since the packet will be 'uncloned'
running pskb_expand_head if it is a cloned gso skb (e.g if the packet has
been sent though a veth device). Fix it resetting pkt_md pointer after
__iptunnel_pull_header

Fixes: 1d7e2ed22f8d ("net: erspan: refactor existing erspan code")
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 21 +++++++++++++--------
 1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 26f25b6e2833..438f1a5fd19a 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -524,11 +524,10 @@ static int ip6gre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi)
 	return PACKET_REJECT;
 }
 
-static int ip6erspan_rcv(struct sk_buff *skb, int gre_hdr_len,
-			 struct tnl_ptk_info *tpi)
+static int ip6erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
+			 int gre_hdr_len)
 {
 	struct erspan_base_hdr *ershdr;
-	struct erspan_metadata *pkt_md;
 	const struct ipv6hdr *ipv6h;
 	struct erspan_md2 *md2;
 	struct ip6_tnl *tunnel;
@@ -547,18 +546,16 @@ static int ip6erspan_rcv(struct sk_buff *skb, int gre_hdr_len,
 		if (unlikely(!pskb_may_pull(skb, len)))
 			return PACKET_REJECT;
 
-		ershdr = (struct erspan_base_hdr *)skb->data;
-		pkt_md = (struct erspan_metadata *)(ershdr + 1);
-
 		if (__iptunnel_pull_header(skb, len,
 					   htons(ETH_P_TEB),
 					   false, false) < 0)
 			return PACKET_REJECT;
 
 		if (tunnel->parms.collect_md) {
+			struct erspan_metadata *pkt_md, *md;
 			struct metadata_dst *tun_dst;
 			struct ip_tunnel_info *info;
-			struct erspan_metadata *md;
+			unsigned char *gh;
 			__be64 tun_id;
 			__be16 flags;
 
@@ -571,6 +568,14 @@ static int ip6erspan_rcv(struct sk_buff *skb, int gre_hdr_len,
 			if (!tun_dst)
 				return PACKET_REJECT;
 
+			/* skb can be uncloned in __iptunnel_pull_header, so
+			 * old pkt_md is no longer valid and we need to reset
+			 * it
+			 */
+			gh = skb_network_header(skb) +
+			     skb_network_header_len(skb);
+			pkt_md = (struct erspan_metadata *)(gh + gre_hdr_len +
+							    sizeof(*ershdr));
 			info = &tun_dst->u.tun_info;
 			md = ip_tunnel_info_opts(info);
 			md->version = ver;
@@ -607,7 +612,7 @@ static int gre_rcv(struct sk_buff *skb)
 
 	if (unlikely(tpi.proto == htons(ETH_P_ERSPAN) ||
 		     tpi.proto == htons(ETH_P_ERSPAN2))) {
-		if (ip6erspan_rcv(skb, hdr_len, &tpi) == PACKET_RCVD)
+		if (ip6erspan_rcv(skb, &tpi, hdr_len) == PACKET_RCVD)
 			return 0;
 		goto out;
 	}
-- 
2.20.1


From d3bddc06897e94ad453e408c348aedd109c0733e Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Wed, 3 Apr 2019 23:27:24 +0300
Subject: [PATCH 29/36] net: bridge: always clear mcast matching struct on
 reports and leaves

[ Upstream commit 1515a63fc413f160d20574ab0894e7f1020c7be2 ]

We need to be careful and always zero the whole br_ip struct when it is
used for matching since the rhashtable change. This patch fixes all the
places which didn't properly clear it which in turn might've caused
mismatches.

Thanks for the great bug report with reproducing steps and bisection.

Steps to reproduce (from the bug report):
ip link add br0 type bridge mcast_querier 1
ip link set br0 up

ip link add v2 type veth peer name v3
ip link set v2 master br0
ip link set v2 up
ip link set v3 up
ip addr add 3.0.0.2/24 dev v3

ip netns add test
ip link add v1 type veth peer name v1 netns test
ip link set v1 master br0
ip link set v1 up
ip -n test link set v1 up
ip -n test addr add 3.0.0.1/24 dev v1

# Multicast receiver
ip netns exec test socat
UDP4-RECVFROM:5588,ip-add-membership=224.224.224.224:3.0.0.1,fork -

# Multicast sender
echo hello | nc -u -s 3.0.0.2 224.224.224.224 5588

Reported-by: liam.mcbirnie@boeing.com
Fixes: 19e3a9c90c53 ("net: bridge: convert multicast to generic rhashtable")
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index ac92b2eb32b1..e4777614a8a0 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -599,6 +599,7 @@ static int br_ip4_multicast_add_group(struct net_bridge *br,
 	if (ipv4_is_local_multicast(group))
 		return 0;
 
+	memset(&br_group, 0, sizeof(br_group));
 	br_group.u.ip4 = group;
 	br_group.proto = htons(ETH_P_IP);
 	br_group.vid = vid;
@@ -1489,6 +1490,7 @@ static void br_ip4_multicast_leave_group(struct net_bridge *br,
 
 	own_query = port ? &port->ip4_own_query : &br->ip4_own_query;
 
+	memset(&br_group, 0, sizeof(br_group));
 	br_group.u.ip4 = group;
 	br_group.proto = htons(ETH_P_IP);
 	br_group.vid = vid;
@@ -1512,6 +1514,7 @@ static void br_ip6_multicast_leave_group(struct net_bridge *br,
 
 	own_query = port ? &port->ip6_own_query : &br->ip6_own_query;
 
+	memset(&br_group, 0, sizeof(br_group));
 	br_group.u.ip6 = *group;
 	br_group.proto = htons(ETH_P_IPV6);
 	br_group.vid = vid;
-- 
2.20.1


From a09accdc99c74617a857b123d95784dd42adc5f8 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Thu, 4 Apr 2019 12:16:27 +0200
Subject: [PATCH 30/36] net: thunderx: fix NULL pointer dereference in
 nicvf_open/nicvf_stop

[ Upstream commit 2ec1ed2aa68782b342458681aa4d16b65c9014d6 ]

When a bpf program is uploaded, the driver computes the number of
xdp tx queues resulting in the allocation of additional qsets.
Starting from commit '2ecbe4f4a027 ("net: thunderx: replace global
nicvf_rx_mode_wq work queue for all VFs to private for each of them")'
the driver runs link state polling for each VF resulting in the
following NULL pointer dereference:

[   56.169256] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000020
[   56.178032] Mem abort info:
[   56.180834]   ESR = 0x96000005
[   56.183877]   Exception class = DABT (current EL), IL = 32 bits
[   56.189792]   SET = 0, FnV = 0
[   56.192834]   EA = 0, S1PTW = 0
[   56.195963] Data abort info:
[   56.198831]   ISV = 0, ISS = 0x00000005
[   56.202662]   CM = 0, WnR = 0
[   56.205619] user pgtable: 64k pages, 48-bit VAs, pgdp = 0000000021f0c7a0
[   56.212315] [0000000000000020] pgd=0000000000000000, pud=0000000000000000
[   56.219094] Internal error: Oops: 96000005 [#1] SMP
[   56.260459] CPU: 39 PID: 2034 Comm: ip Not tainted 5.1.0-rc3+ #3
[   56.266452] Hardware name: GIGABYTE R120-T33/MT30-GS1, BIOS T49 02/02/2018
[   56.273315] pstate: 80000005 (Nzcv daif -PAN -UAO)
[   56.278098] pc : __ll_sc___cmpxchg_case_acq_64+0x4/0x20
[   56.283312] lr : mutex_lock+0x2c/0x50
[   56.286962] sp : ffff0000219af1b0
[   56.290264] x29: ffff0000219af1b0 x28: ffff800f64de49a0
[   56.295565] x27: 0000000000000000 x26: 0000000000000015
[   56.300865] x25: 0000000000000000 x24: 0000000000000000
[   56.306165] x23: 0000000000000000 x22: ffff000011117000
[   56.311465] x21: ffff800f64dfc080 x20: 0000000000000020
[   56.316766] x19: 0000000000000020 x18: 0000000000000001
[   56.322066] x17: 0000000000000000 x16: ffff800f2e077080
[   56.327367] x15: 0000000000000004 x14: 0000000000000000
[   56.332667] x13: ffff000010964438 x12: 0000000000000002
[   56.337967] x11: 0000000000000000 x10: 0000000000000c70
[   56.343268] x9 : ffff0000219af120 x8 : ffff800f2e077d50
[   56.348568] x7 : 0000000000000027 x6 : 000000062a9d6a84
[   56.353869] x5 : 0000000000000000 x4 : ffff800f2e077480
[   56.359169] x3 : 0000000000000008 x2 : ffff800f2e077080
[   56.364469] x1 : 0000000000000000 x0 : 0000000000000020
[   56.369770] Process ip (pid: 2034, stack limit = 0x00000000c862da3a)
[   56.376110] Call trace:
[   56.378546]  __ll_sc___cmpxchg_case_acq_64+0x4/0x20
[   56.383414]  drain_workqueue+0x34/0x198
[   56.387247]  nicvf_open+0x48/0x9e8 [nicvf]
[   56.391334]  nicvf_open+0x898/0x9e8 [nicvf]
[   56.395507]  nicvf_xdp+0x1bc/0x238 [nicvf]
[   56.399595]  dev_xdp_install+0x68/0x90
[   56.403333]  dev_change_xdp_fd+0xc8/0x240
[   56.407333]  do_setlink+0x8e0/0xbe8
[   56.410810]  __rtnl_newlink+0x5b8/0x6d8
[   56.414634]  rtnl_newlink+0x54/0x80
[   56.418112]  rtnetlink_rcv_msg+0x22c/0x2f8
[   56.422199]  netlink_rcv_skb+0x60/0x120
[   56.426023]  rtnetlink_rcv+0x28/0x38
[   56.429587]  netlink_unicast+0x1c8/0x258
[   56.433498]  netlink_sendmsg+0x1b4/0x350
[   56.437410]  sock_sendmsg+0x4c/0x68
[   56.440887]  ___sys_sendmsg+0x240/0x280
[   56.444711]  __sys_sendmsg+0x68/0xb0
[   56.448275]  __arm64_sys_sendmsg+0x2c/0x38
[   56.452361]  el0_svc_handler+0x9c/0x128
[   56.456186]  el0_svc+0x8/0xc
[   56.459056] Code: 35ffff91 2a1003e0 d65f03c0 f9800011 (c85ffc10)
[   56.465166] ---[ end trace 4a57fdc27b0a572c ]---
[   56.469772] Kernel panic - not syncing: Fatal exception

Fix it by checking nicvf_rx_mode_wq pointer in nicvf_open and nicvf_stop

Fixes: 2ecbe4f4a027 ("net: thunderx: replace global nicvf_rx_mode_wq work queue for all VFs to private for each of them")
Fixes: 2c632ad8bc74 ("net: thunderx: move link state polling function to VF")
Reported-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Tested-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/cavium/thunder/nicvf_main.c  | 20 +++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 503cfadff4ac..d4ee9f9c8c34 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -1328,10 +1328,11 @@ int nicvf_stop(struct net_device *netdev)
 	struct nicvf_cq_poll *cq_poll = NULL;
 	union nic_mbx mbx = {};
 
-	cancel_delayed_work_sync(&nic->link_change_work);
-
 	/* wait till all queued set_rx_mode tasks completes */
-	drain_workqueue(nic->nicvf_rx_mode_wq);
+	if (nic->nicvf_rx_mode_wq) {
+		cancel_delayed_work_sync(&nic->link_change_work);
+		drain_workqueue(nic->nicvf_rx_mode_wq);
+	}
 
 	mbx.msg.msg = NIC_MBOX_MSG_SHUTDOWN;
 	nicvf_send_msg_to_pf(nic, &mbx);
@@ -1452,7 +1453,8 @@ int nicvf_open(struct net_device *netdev)
 	struct nicvf_cq_poll *cq_poll = NULL;
 
 	/* wait till all queued set_rx_mode tasks completes if any */
-	drain_workqueue(nic->nicvf_rx_mode_wq);
+	if (nic->nicvf_rx_mode_wq)
+		drain_workqueue(nic->nicvf_rx_mode_wq);
 
 	netif_carrier_off(netdev);
 
@@ -1550,10 +1552,12 @@ int nicvf_open(struct net_device *netdev)
 	/* Send VF config done msg to PF */
 	nicvf_send_cfg_done(nic);
 
-	INIT_DELAYED_WORK(&nic->link_change_work,
-			  nicvf_link_status_check_task);
-	queue_delayed_work(nic->nicvf_rx_mode_wq,
-			   &nic->link_change_work, 0);
+	if (nic->nicvf_rx_mode_wq) {
+		INIT_DELAYED_WORK(&nic->link_change_work,
+				  nicvf_link_status_check_task);
+		queue_delayed_work(nic->nicvf_rx_mode_wq,
+				   &nic->link_change_work, 0);
+	}
 
 	return 0;
 cleanup:
-- 
2.20.1


From f7befc89c5262bf1d82e83ce2b490b5e79ac0979 Mon Sep 17 00:00:00 2001
From: Miaohe Lin <linmiaohe@huawei.com>
Date: Mon, 8 Apr 2019 10:04:20 +0800
Subject: [PATCH 31/36] net: vrf: Fix ping failed when vrf mtu is set to 0

[ Upstream commit 5055376a3b44c4021de8830c9157f086a97731df ]

When the mtu of a vrf device is set to 0, it would cause ping
failed. So I think we should limit vrf mtu in a reasonable range
to solve this problem. I set dev->min_mtu to IPV6_MIN_MTU, so it
will works for both ipv4 and ipv6. And if dev->max_mtu still be 0
can be confusing, so I set dev->max_mtu to ETH_MAX_MTU.

Here is the reproduce step:

1.Config vrf interface and set mtu to 0:
3: enp4s0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc fq_codel
master vrf1 state UP mode DEFAULT group default qlen 1000
    link/ether 52:54:00:9e:dd:c1 brd ff:ff:ff:ff:ff:ff

2.Ping peer:
3: enp4s0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc fq_codel
master vrf1 state UP group default qlen 1000
    link/ether 52:54:00:9e:dd:c1 brd ff:ff:ff:ff:ff:ff
    inet 10.0.0.1/16 scope global enp4s0
       valid_lft forever preferred_lft forever
connect: Network is unreachable

3.Set mtu to default value, ping works:
PING 10.0.0.2 (10.0.0.2) 56(84) bytes of data.
64 bytes from 10.0.0.2: icmp_seq=1 ttl=64 time=1.88 ms

Fixes: ad49bc6361ca2 ("net: vrf: remove MTU limits for vrf device")
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 6d1a1abbed27..cd15c32b2e43 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -1275,8 +1275,12 @@ static void vrf_setup(struct net_device *dev)
 	dev->priv_flags |= IFF_NO_QUEUE;
 	dev->priv_flags |= IFF_NO_RX_HANDLER;
 
-	dev->min_mtu = 0;
-	dev->max_mtu = 0;
+	/* VRF devices do not care about MTU, but if the MTU is set
+	 * too low then the ipv4 and ipv6 protocols are disabled
+	 * which breaks networking.
+	 */
+	dev->min_mtu = IPV6_MIN_MTU;
+	dev->max_mtu = ETH_MAX_MTU;
 }
 
 static int vrf_validate(struct nlattr *tb[], struct nlattr *data[],
-- 
2.20.1


From d87c1012e09a307b36521faa95f357e44ab8a597 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <alobakin@dlink.ru>
Date: Thu, 28 Mar 2019 18:23:04 +0300
Subject: [PATCH 32/36] net: core: netif_receive_skb_list: unlist skb before
 passing to pt->func

[ Upstream commit 9a5a90d167b0e5fe3d47af16b68fd09ce64085cd ]

__netif_receive_skb_list_ptype() leaves skb->next poisoned before passing
it to pt_prev->func handler, what may produce (in certain cases, e.g. DSA
setup) crashes like:

[ 88.606777] CPU 0 Unable to handle kernel paging request at virtual address 0000000e, epc == 80687078, ra == 8052cc7c
[ 88.618666] Oops[#1]:
[ 88.621196] CPU: 0 PID: 0 Comm: swapper Not tainted 5.1.0-rc2-dlink-00206-g4192a172-dirty #1473
[ 88.630885] $ 0 : 00000000 10000400 00000002 864d7850
[ 88.636709] $ 4 : 87c0ddf0 864d7800 87c0ddf0 00000000
[ 88.642526] $ 8 : 00000000 49600000 00000001 00000001
[ 88.648342] $12 : 00000000 c288617b dadbee27 25d17c41
[ 88.654159] $16 : 87c0ddf0 85cff080 80790000 fffffffd
[ 88.659975] $20 : 80797b20 ffffffff 00000001 864d7800
[ 88.665793] $24 : 00000000 8011e658
[ 88.671609] $28 : 80790000 87c0dbc0 87cabf00 8052cc7c
[ 88.677427] Hi : 00000003
[ 88.680622] Lo : 7b5b4220
[ 88.683840] epc : 80687078 vlan_dev_hard_start_xmit+0x1c/0x1a0
[ 88.690532] ra : 8052cc7c dev_hard_start_xmit+0xac/0x188
[ 88.696734] Status: 10000404	IEp
[ 88.700422] Cause : 50000008 (ExcCode 02)
[ 88.704874] BadVA : 0000000e
[ 88.708069] PrId : 0001a120 (MIPS interAptiv (multi))
[ 88.713005] Modules linked in:
[ 88.716407] Process swapper (pid: 0, threadinfo=(ptrval), task=(ptrval), tls=00000000)
[ 88.725219] Stack : 85f61c28 00000000 0000000e 80780000 87c0ddf0 85cff080 80790000 8052cc7c
[ 88.734529] 87cabf00 00000000 00000001 85f5fb40 807b0000 864d7850 87cabf00 807d0000
[ 88.743839] 864d7800 8655f600 00000000 85cff080 87c1c000 0000006a 00000000 8052d96c
[ 88.753149] 807a0000 8057adb8 87c0dcc8 87c0dc50 85cfff08 00000558 87cabf00 85f58c50
[ 88.762460] 00000002 85f58c00 864d7800 80543308 fffffff4 00000001 85f58c00 864d7800
[ 88.771770] ...
[ 88.774483] Call Trace:
[ 88.777199] [<80687078>] vlan_dev_hard_start_xmit+0x1c/0x1a0
[ 88.783504] [<8052cc7c>] dev_hard_start_xmit+0xac/0x188
[ 88.789326] [<8052d96c>] __dev_queue_xmit+0x6e8/0x7d4
[ 88.794955] [<805a8640>] ip_finish_output2+0x238/0x4d0
[ 88.800677] [<805ab6a0>] ip_output+0xc8/0x140
[ 88.805526] [<805a68f4>] ip_forward+0x364/0x560
[ 88.810567] [<805a4ff8>] ip_rcv+0x48/0xe4
[ 88.815030] [<80528d44>] __netif_receive_skb_one_core+0x44/0x58
[ 88.821635] [<8067f220>] dsa_switch_rcv+0x108/0x1ac
[ 88.827067] [<80528f80>] __netif_receive_skb_list_core+0x228/0x26c
[ 88.833951] [<8052ed84>] netif_receive_skb_list+0x1d4/0x394
[ 88.840160] [<80355a88>] lunar_rx_poll+0x38c/0x828
[ 88.845496] [<8052fa78>] net_rx_action+0x14c/0x3cc
[ 88.850835] [<806ad300>] __do_softirq+0x178/0x338
[ 88.856077] [<8012a2d4>] irq_exit+0xbc/0x100
[ 88.860846] [<802f8b70>] plat_irq_dispatch+0xc0/0x144
[ 88.866477] [<80105974>] handle_int+0x14c/0x158
[ 88.871516] [<806acfb0>] r4k_wait+0x30/0x40
[ 88.876462] Code: afb10014 8c8200a0 00803025 <9443000c> 94a20468 00000000 10620042 00a08025 9605046a
[ 88.887332]
[ 88.888982] ---[ end trace eb863d007da11cf1 ]---
[ 88.894122] Kernel panic - not syncing: Fatal exception in interrupt
[ 88.901202] ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]---

Fix this by pulling skb off the sublist and zeroing skb->next pointer
before calling ptype callback.

Fixes: 88eb1944e18c ("net: core: propagate SKB lists through packet_type lookup")
Reviewed-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: Alexander Lobakin <alobakin@dlink.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 5d03889502eb..12824e007e06 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5014,8 +5014,10 @@ static inline void __netif_receive_skb_list_ptype(struct list_head *head,
 	if (pt_prev->list_func != NULL)
 		pt_prev->list_func(head, pt_prev, orig_dev);
 	else
-		list_for_each_entry_safe(skb, next, head, list)
+		list_for_each_entry_safe(skb, next, head, list) {
+			skb_list_del_init(skb);
 			pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
+		}
 }
 
 static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemalloc)
-- 
2.20.1


From 4bf3b8fc8a708e8888ca7401cf50c5b460e1b271 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 30 Mar 2019 17:13:24 +0100
Subject: [PATCH 33/36] r8169: disable default rx interrupt coalescing on
 RTL8168

[ Upstream commit 288ac524cf70a8e7ed851a61ed2a9744039dae8d ]

It was reported that re-introducing ASPM, in combination with RX
interrupt coalescing, results in significantly increased packet
latency, see [0]. Disabling ASPM or RX interrupt coalescing fixes
the issue. Therefore change the driver's default to disable RX
interrupt coalescing. Users still have the option to enable RX
coalescing via ethtool.

[0] https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=925496

Fixes: a99790bf5c7f ("r8169: Reinstate ASPM Support")
Reported-by: Mike Crowe <mac@mcrowe.com>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 5adb00f521db..365cddbfc684 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -5333,7 +5333,7 @@ static void rtl_hw_start_8168(struct rtl8169_private *tp)
 	tp->cp_cmd |= PktCntrDisable | INTT_1;
 	RTL_W16(tp, CPlusCmd, tp->cp_cmd);
 
-	RTL_W16(tp, IntrMitigate, 0x5151);
+	RTL_W16(tp, IntrMitigate, 0x5100);
 
 	/* Work around for RxFIFO overflow. */
 	if (tp->mac_version == RTL_GIGA_MAC_VER_11) {
-- 
2.20.1


From 97dbdb9550a26dfdf92353b495cca552dffd6941 Mon Sep 17 00:00:00 2001
From: Aditya Pakki <pakki001@umn.edu>
Date: Tue, 19 Mar 2019 16:42:40 -0500
Subject: [PATCH 34/36] net: mlx5: Add a missing check on idr_find, free buf

[ Upstream commit 8e949363f017e2011464812a714fb29710fb95b4 ]

idr_find() can return a NULL value to 'flow' which is used without a
check. The patch adds a check to avoid potential NULL pointer dereference.

In case of mlx5_fpga_sbu_conn_sendmsg() failure, free buf allocated
using kzalloc.

Fixes: ab412e1dd7db ("net/mlx5: Accel, add TLS rx offload routines")
Signed-off-by: Aditya Pakki <pakki001@umn.edu>
Reviewed-by: Yuval Shaia <yuval.shaia@oracle.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
index 5cf5f2a9d51f..8de64e88c670 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
@@ -217,15 +217,21 @@ int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
 	void *cmd;
 	int ret;
 
+	rcu_read_lock();
+	flow = idr_find(&mdev->fpga->tls->rx_idr, ntohl(handle));
+	rcu_read_unlock();
+
+	if (!flow) {
+		WARN_ONCE(1, "Received NULL pointer for handle\n");
+		return -EINVAL;
+	}
+
 	buf = kzalloc(size, GFP_ATOMIC);
 	if (!buf)
 		return -ENOMEM;
 
 	cmd = (buf + 1);
 
-	rcu_read_lock();
-	flow = idr_find(&mdev->fpga->tls->rx_idr, ntohl(handle));
-	rcu_read_unlock();
 	mlx5_fpga_tls_flow_to_cmd(flow, cmd);
 
 	MLX5_SET(tls_cmd, cmd, swid, ntohl(handle));
@@ -238,6 +244,8 @@ int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
 	buf->complete = mlx_tls_kfree_complete;
 
 	ret = mlx5_fpga_sbu_conn_sendmsg(mdev->fpga->tls->conn, buf);
+	if (ret < 0)
+		kfree(buf);
 
 	return ret;
 }
-- 
2.20.1


From 5768cdf43c88f8c74d524670c1f5434e583e5e7e Mon Sep 17 00:00:00 2001
From: Huy Nguyen <huyn@mellanox.com>
Date: Thu, 7 Mar 2019 14:49:50 -0600
Subject: [PATCH 35/36] net/mlx5e: Update xoff formula

[ Upstream commit 5ec983e924c7978aaec3cf8679ece9436508bb20 ]

Set minimum speed in xoff threshold formula to 40Gbps

Fixes: 0696d60853d5 ("net/mlx5e: Receive buffer configuration")
Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en/port_buffer.c  | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
index eac245a93f91..f00de0c987cd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
@@ -122,7 +122,9 @@ static int port_set_buffer(struct mlx5e_priv *priv,
 	return err;
 }
 
-/* xoff = ((301+2.16 * len [m]) * speed [Gbps] + 2.72 MTU [B]) */
+/* xoff = ((301+2.16 * len [m]) * speed [Gbps] + 2.72 MTU [B])
+ * minimum speed value is 40Gbps
+ */
 static u32 calculate_xoff(struct mlx5e_priv *priv, unsigned int mtu)
 {
 	u32 speed;
@@ -130,10 +132,9 @@ static u32 calculate_xoff(struct mlx5e_priv *priv, unsigned int mtu)
 	int err;
 
 	err = mlx5e_port_linkspeed(priv->mdev, &speed);
-	if (err) {
-		mlx5_core_warn(priv->mdev, "cannot get port speed\n");
-		return 0;
-	}
+	if (err)
+		speed = SPEED_40000;
+	speed = max_t(u32, speed, SPEED_40000);
 
 	xoff = (301 + 216 * priv->dcbx.cable_len / 100) * speed / 1000 + 272 * mtu / 100;
 
-- 
2.20.1


From 2b7f8be5e609b9ee37753c58e9e2db62a1794f10 Mon Sep 17 00:00:00 2001
From: Huy Nguyen <huyn@mellanox.com>
Date: Thu, 7 Mar 2019 14:07:32 -0600
Subject: [PATCH 36/36] net/mlx5e: Update xon formula

[ Upstream commit e28408e98bced123038857b6e3c81fa12a2e3e68 ]

Set xon = xoff - netdev's max_mtu.
netdev's max_mtu will give enough time for the pause frame to
arrive at the sender.

Fixes: 0696d60853d5 ("net/mlx5e: Receive buffer configuration")
Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../mellanox/mlx5/core/en/port_buffer.c       | 28 +++++++++++--------
 1 file changed, 16 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
index f00de0c987cd..4ab0d030b544 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
@@ -143,7 +143,7 @@ static u32 calculate_xoff(struct mlx5e_priv *priv, unsigned int mtu)
 }
 
 static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer,
-				 u32 xoff, unsigned int mtu)
+				 u32 xoff, unsigned int max_mtu)
 {
 	int i;
 
@@ -155,11 +155,12 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer,
 		}
 
 		if (port_buffer->buffer[i].size <
-		    (xoff + mtu + (1 << MLX5E_BUFFER_CELL_SHIFT)))
+		    (xoff + max_mtu + (1 << MLX5E_BUFFER_CELL_SHIFT)))
 			return -ENOMEM;
 
 		port_buffer->buffer[i].xoff = port_buffer->buffer[i].size - xoff;
-		port_buffer->buffer[i].xon  = port_buffer->buffer[i].xoff - mtu;
+		port_buffer->buffer[i].xon  =
+			port_buffer->buffer[i].xoff - max_mtu;
 	}
 
 	return 0;
@@ -167,7 +168,7 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer,
 
 /**
  * update_buffer_lossy()
- *   mtu: device's MTU
+ *   max_mtu: netdev's max_mtu
  *   pfc_en: <input> current pfc configuration
  *   buffer: <input> current prio to buffer mapping
  *   xoff:   <input> xoff value
@@ -184,7 +185,7 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer,
  *     Return 0 if no error.
  *     Set change to true if buffer configuration is modified.
  */
-static int update_buffer_lossy(unsigned int mtu,
+static int update_buffer_lossy(unsigned int max_mtu,
 			       u8 pfc_en, u8 *buffer, u32 xoff,
 			       struct mlx5e_port_buffer *port_buffer,
 			       bool *change)
@@ -221,7 +222,7 @@ static int update_buffer_lossy(unsigned int mtu,
 	}
 
 	if (changed) {
-		err = update_xoff_threshold(port_buffer, xoff, mtu);
+		err = update_xoff_threshold(port_buffer, xoff, max_mtu);
 		if (err)
 			return err;
 
@@ -231,6 +232,7 @@ static int update_buffer_lossy(unsigned int mtu,
 	return 0;
 }
 
+#define MINIMUM_MAX_MTU 9216
 int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 				    u32 change, unsigned int mtu,
 				    struct ieee_pfc *pfc,
@@ -242,12 +244,14 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 	bool update_prio2buffer = false;
 	u8 buffer[MLX5E_MAX_PRIORITY];
 	bool update_buffer = false;
+	unsigned int max_mtu;
 	u32 total_used = 0;
 	u8 curr_pfc_en;
 	int err;
 	int i;
 
 	mlx5e_dbg(HW, priv, "%s: change=%x\n", __func__, change);
+	max_mtu = max_t(unsigned int, priv->netdev->max_mtu, MINIMUM_MAX_MTU);
 
 	err = mlx5e_port_query_buffer(priv, &port_buffer);
 	if (err)
@@ -255,7 +259,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 
 	if (change & MLX5E_PORT_BUFFER_CABLE_LEN) {
 		update_buffer = true;
-		err = update_xoff_threshold(&port_buffer, xoff, mtu);
+		err = update_xoff_threshold(&port_buffer, xoff, max_mtu);
 		if (err)
 			return err;
 	}
@@ -265,7 +269,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 		if (err)
 			return err;
 
-		err = update_buffer_lossy(mtu, pfc->pfc_en, buffer, xoff,
+		err = update_buffer_lossy(max_mtu, pfc->pfc_en, buffer, xoff,
 					  &port_buffer, &update_buffer);
 		if (err)
 			return err;
@@ -277,8 +281,8 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 		if (err)
 			return err;
 
-		err = update_buffer_lossy(mtu, curr_pfc_en, prio2buffer, xoff,
-					  &port_buffer, &update_buffer);
+		err = update_buffer_lossy(max_mtu, curr_pfc_en, prio2buffer,
+					  xoff, &port_buffer, &update_buffer);
 		if (err)
 			return err;
 	}
@@ -302,7 +306,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 			return -EINVAL;
 
 		update_buffer = true;
-		err = update_xoff_threshold(&port_buffer, xoff, mtu);
+		err = update_xoff_threshold(&port_buffer, xoff, max_mtu);
 		if (err)
 			return err;
 	}
@@ -310,7 +314,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 	/* Need to update buffer configuration if xoff value is changed */
 	if (!update_buffer && xoff != priv->dcbx.xoff) {
 		update_buffer = true;
-		err = update_xoff_threshold(&port_buffer, xoff, mtu);
+		err = update_xoff_threshold(&port_buffer, xoff, max_mtu);
 		if (err)
 			return err;
 	}
-- 
2.20.1

Re: [PATCHES] Networking

[Sasha Levin]

On Tue, Apr 09, 2019 at 08:55:38PM -0700, David Miller wrote:
>
>Please queue up the following networking bug fixes for v4.19 and v5.0
>stable respectively.
>
>Thank you!

Queued both, thank you!

--
Thanks,
Sasha

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 106 bytes --]


Please queue up the following networking bug fixes for v4.19 and
v5.0 -stable, respectively.

Thank you!

[-- Attachment #2: net_419.mbox --]
[-- Type: Application/Octet-Stream, Size: 54295 bytes --]

From b953fab32dce52adc1fd01a6a67e6a9ac8c5dd35 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 12 Apr 2019 15:04:10 +0200
Subject: [PATCH 01/24] bonding: fix event handling for stacked bonds

[ Upstream commit 92480b3977fd3884649d404cbbaf839b70035699 ]

When a bond is enslaved to another bond, bond_netdev_event() only
handles the event as if the bond is a master, and skips treating the
bond as a slave.

This leads to a refcount leak on the slave, since we don't remove the
adjacency to its master and the master holds a reference on the slave.

Reproducer:
  ip link add bondL type bond
  ip link add bondU type bond
  ip link set bondL master bondU
  ip link del bondL

No "Fixes:" tag, this code is older than git history.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index b2c42cae3081..091b454e83fc 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3198,8 +3198,12 @@ static int bond_netdev_event(struct notifier_block *this,
 		return NOTIFY_DONE;
 
 	if (event_dev->flags & IFF_MASTER) {
+		int ret;
+
 		netdev_dbg(event_dev, "IFF_MASTER\n");
-		return bond_master_netdev_event(event, event_dev);
+		ret = bond_master_netdev_event(event, event_dev);
+		if (ret != NOTIFY_DONE)
+			return ret;
 	}
 
 	if (event_dev->flags & IFF_SLAVE) {
-- 
2.20.1


From b631e35bedd8f51bf88e955c71b67fc24c72cec6 Mon Sep 17 00:00:00 2001
From: Si-Wei Liu <si-wei.liu@oracle.com>
Date: Mon, 8 Apr 2019 19:45:27 -0400
Subject: [PATCH 02/24] failover: allow name change on IFF_UP slave interfaces

[ Upstream commit 8065a779f17e94536a1c4dcee4f9d88011672f97 ]

When a netdev appears through hot plug then gets enslaved by a failover
master that is already up and running, the slave will be opened
right away after getting enslaved. Today there's a race that userspace
(udev) may fail to rename the slave if the kernel (net_failover)
opens the slave earlier than when the userspace rename happens.
Unlike bond or team, the primary slave of failover can't be renamed by
userspace ahead of time, since the kernel initiated auto-enslavement is
unable to, or rather, is never meant to be synchronized with the rename
request from userspace.

As the failover slave interfaces are not designed to be operated
directly by userspace apps: IP configuration, filter rules with
regard to network traffic passing and etc., should all be done on master
interface. In general, userspace apps only care about the
name of master interface, while slave names are less important as long
as admin users can see reliable names that may carry
other information describing the netdev. For e.g., they can infer that
"ens3nsby" is a standby slave of "ens3", while for a
name like "eth0" they can't tell which master it belongs to.

Historically the name of IFF_UP interface can't be changed because
there might be admin script or management software that is already
relying on such behavior and assumes that the slave name can't be
changed once UP. But failover is special: with the in-kernel
auto-enslavement mechanism, the userspace expectation for device
enumeration and bring-up order is already broken. Previously initramfs
and various userspace config tools were modified to bypass failover
slaves because of auto-enslavement and duplicate MAC address. Similarly,
in case that users care about seeing reliable slave name, the new type
of failover slaves needs to be taken care of specifically in userspace
anyway.

It's less risky to lift up the rename restriction on failover slave
which is already UP. Although it's possible this change may potentially
break userspace component (most likely configuration scripts or
management software) that assumes slave name can't be changed while
UP, it's relatively a limited and controllable set among all userspace
components, which can be fixed specifically to listen for the rename
events on failover slaves. Userspace component interacting with slaves
is expected to be changed to operate on failover master interface
instead, as the failover slave is dynamic in nature which may come and
go at any point.  The goal is to make the role of failover slaves less
relevant, and userspace components should only deal with failover master
in the long run.

Fixes: 30c8bd5aa8b2 ("net: Introduce generic failover module")
Signed-off-by: Si-Wei Liu <si-wei.liu@oracle.com>
Reviewed-by: Liran Alon <liran.alon@oracle.com>
Acked-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  3 +++
 net/core/dev.c            | 16 +++++++++++++++-
 net/core/failover.c       |  6 +++---
 3 files changed, 21 insertions(+), 4 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 21fef8c5eca7..8c2fec0bcb26 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1456,6 +1456,7 @@ struct net_device_ops {
  * @IFF_FAILOVER: device is a failover master device
  * @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device
  * @IFF_L3MDEV_RX_HANDLER: only invoke the rx handler of L3 master device
+ * @IFF_LIVE_RENAME_OK: rename is allowed while device is up and running
  */
 enum netdev_priv_flags {
 	IFF_802_1Q_VLAN			= 1<<0,
@@ -1488,6 +1489,7 @@ enum netdev_priv_flags {
 	IFF_FAILOVER			= 1<<27,
 	IFF_FAILOVER_SLAVE		= 1<<28,
 	IFF_L3MDEV_RX_HANDLER		= 1<<29,
+	IFF_LIVE_RENAME_OK		= 1<<30,
 };
 
 #define IFF_802_1Q_VLAN			IFF_802_1Q_VLAN
@@ -1519,6 +1521,7 @@ enum netdev_priv_flags {
 #define IFF_FAILOVER			IFF_FAILOVER
 #define IFF_FAILOVER_SLAVE		IFF_FAILOVER_SLAVE
 #define IFF_L3MDEV_RX_HANDLER		IFF_L3MDEV_RX_HANDLER
+#define IFF_LIVE_RENAME_OK		IFF_LIVE_RENAME_OK
 
 /**
  *	struct net_device - The DEVICE structure.
diff --git a/net/core/dev.c b/net/core/dev.c
index d47554307a6d..3bcec116a5f2 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1180,7 +1180,21 @@ int dev_change_name(struct net_device *dev, const char *newname)
 	BUG_ON(!dev_net(dev));
 
 	net = dev_net(dev);
-	if (dev->flags & IFF_UP)
+
+	/* Some auto-enslaved devices e.g. failover slaves are
+	 * special, as userspace might rename the device after
+	 * the interface had been brought up and running since
+	 * the point kernel initiated auto-enslavement. Allow
+	 * live name change even when these slave devices are
+	 * up and running.
+	 *
+	 * Typically, users of these auto-enslaving devices
+	 * don't actually care about slave name change, as
+	 * they are supposed to operate on master interface
+	 * directly.
+	 */
+	if (dev->flags & IFF_UP &&
+	    likely(!(dev->priv_flags & IFF_LIVE_RENAME_OK)))
 		return -EBUSY;
 
 	write_seqcount_begin(&devnet_rename_seq);
diff --git a/net/core/failover.c b/net/core/failover.c
index 4a92a98ccce9..b5cd3c727285 100644
--- a/net/core/failover.c
+++ b/net/core/failover.c
@@ -80,14 +80,14 @@ static int failover_slave_register(struct net_device *slave_dev)
 		goto err_upper_link;
 	}
 
-	slave_dev->priv_flags |= IFF_FAILOVER_SLAVE;
+	slave_dev->priv_flags |= (IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK);
 
 	if (fops && fops->slave_register &&
 	    !fops->slave_register(slave_dev, failover_dev))
 		return NOTIFY_OK;
 
 	netdev_upper_dev_unlink(slave_dev, failover_dev);
-	slave_dev->priv_flags &= ~IFF_FAILOVER_SLAVE;
+	slave_dev->priv_flags &= ~(IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK);
 err_upper_link:
 	netdev_rx_handler_unregister(slave_dev);
 done:
@@ -121,7 +121,7 @@ int failover_slave_unregister(struct net_device *slave_dev)
 
 	netdev_rx_handler_unregister(slave_dev);
 	netdev_upper_dev_unlink(slave_dev, failover_dev);
-	slave_dev->priv_flags &= ~IFF_FAILOVER_SLAVE;
+	slave_dev->priv_flags &= ~(IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK);
 
 	if (fops && fops->slave_unregister &&
 	    !fops->slave_unregister(slave_dev, failover_dev))
-- 
2.20.1


From e8d77f207ba127a8ccf044b177e574377515af6d Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 15 Apr 2019 15:57:23 -0500
Subject: [PATCH 03/24] net: atm: Fix potential Spectre v1 vulnerabilities

[ Upstream commit 899537b73557aafbdd11050b501cf54b4f5c45af ]

arg is controlled by user-space, hence leading to a potential
exploitation of the Spectre variant 1 vulnerability.

This issue was detected with the help of Smatch:

net/atm/lec.c:715 lec_mcast_attach() warn: potential spectre issue 'dev_lec' [r] (local cap)

Fix this by sanitizing arg before using it to index dev_lec.

Notice that given that speculation windows are large, the policy is
to kill the speculation on the first load and not worry if it can be
completed with a dependent load/store [1].

[1] https://lore.kernel.org/lkml/20180423164740.GY17484@dhcp22.suse.cz/

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/atm/lec.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/atm/lec.c b/net/atm/lec.c
index d7f5cf5b7594..ad4f829193f0 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -710,7 +710,10 @@ static int lec_vcc_attach(struct atm_vcc *vcc, void __user *arg)
 
 static int lec_mcast_attach(struct atm_vcc *vcc, int arg)
 {
-	if (arg < 0 || arg >= MAX_LEC_ITF || !dev_lec[arg])
+	if (arg < 0 || arg >= MAX_LEC_ITF)
+		return -EINVAL;
+	arg = array_index_nospec(arg, MAX_LEC_ITF);
+	if (!dev_lec[arg])
 		return -EINVAL;
 	vcc->proto_data = dev_lec[arg];
 	return lec_mcast_make(netdev_priv(dev_lec[arg]), vcc);
@@ -728,6 +731,7 @@ static int lecd_attach(struct atm_vcc *vcc, int arg)
 		i = arg;
 	if (arg >= MAX_LEC_ITF)
 		return -EINVAL;
+	i = array_index_nospec(arg, MAX_LEC_ITF);
 	if (!dev_lec[i]) {
 		int size;
 
-- 
2.20.1


From 49694e080d8f4fdbc2518d4795cce8fdc36924f4 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Thu, 11 Apr 2019 13:56:39 +0300
Subject: [PATCH 04/24] net: bridge: fix per-port af_packet sockets

[ Upstream commit 3b2e2904deb314cc77a2192f506f2fd44e3d10d0 ]

When the commit below was introduced it changed two visible things:
 - the skb was no longer passed through the protocol handlers with the
   original device
 - the skb was passed up the stack with skb->dev = bridge

The first change broke af_packet sockets on bridge ports. For example we
use them for hostapd which listens for ETH_P_PAE packets on the ports.
We discussed two possible fixes:
 - create a clone and pass it through NF_HOOK(), act on the original skb
   based on the result
 - somehow signal to the caller from the okfn() that it was called,
   meaning the skb is ok to be passed, which this patch is trying to
   implement via returning 1 from the bridge link-local okfn()

Note that we rely on the fact that NF_QUEUE/STOLEN would return 0 and
drop/error would return < 0 thus the okfn() is called only when the
return was 1, so we signal to the caller that it was called by preserving
the return value from nf_hook().

Fixes: 8626c56c8279 ("bridge: fix potential use-after-free when hook returns QUEUE or STOLEN verdict")
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_input.c | 23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)

diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 72074276c088..fed0ff446abb 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -195,13 +195,10 @@ static void __br_handle_local_finish(struct sk_buff *skb)
 /* note: already called with rcu_read_lock */
 static int br_handle_local_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
-	struct net_bridge_port *p = br_port_get_rcu(skb->dev);
-
 	__br_handle_local_finish(skb);
 
-	BR_INPUT_SKB_CB(skb)->brdev = p->br->dev;
-	br_pass_frame_up(skb);
-	return 0;
+	/* return 1 to signal the okfn() was called so it's ok to use the skb */
+	return 1;
 }
 
 /*
@@ -278,10 +275,18 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
 				goto forward;
 		}
 
-		/* Deliver packet to local host only */
-		NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, dev_net(skb->dev),
-			NULL, skb, skb->dev, NULL, br_handle_local_finish);
-		return RX_HANDLER_CONSUMED;
+		/* The else clause should be hit when nf_hook():
+		 *   - returns < 0 (drop/error)
+		 *   - returns = 0 (stolen/nf_queue)
+		 * Thus return 1 from the okfn() to signal the skb is ok to pass
+		 */
+		if (NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN,
+			    dev_net(skb->dev), NULL, skb, skb->dev, NULL,
+			    br_handle_local_finish) == 1) {
+			return RX_HANDLER_PASS;
+		} else {
+			return RX_HANDLER_CONSUMED;
+		}
 	}
 
 forward:
-- 
2.20.1


From a57f919346a820bdcad95cae1302dcc92bdd8dd3 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Thu, 11 Apr 2019 15:08:25 +0300
Subject: [PATCH 05/24] net: bridge: multicast: use rcu to access port list
 from br_multicast_start_querier

[ Upstream commit c5b493ce192bd7a4e7bd073b5685aad121eeef82 ]

br_multicast_start_querier() walks over the port list but it can be
called from a timer with only multicast_lock held which doesn't protect
the port list, so use RCU to walk over it.

Fixes: c83b8fab06fc ("bridge: Restart queries when last querier expires")
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 20ed7adcf1cc..75901c4641b1 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -2152,7 +2152,8 @@ static void br_multicast_start_querier(struct net_bridge *br,
 
 	__br_multicast_open(br, query);
 
-	list_for_each_entry(port, &br->port_list, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(port, &br->port_list, list) {
 		if (port->state == BR_STATE_DISABLED ||
 		    port->state == BR_STATE_BLOCKING)
 			continue;
@@ -2164,6 +2165,7 @@ static void br_multicast_start_querier(struct net_bridge *br,
 			br_multicast_enable(&port->ip6_own_query);
 #endif
 	}
+	rcu_read_unlock();
 }
 
 int br_multicast_toggle(struct net_bridge *br, unsigned long val)
-- 
2.20.1


From 5df8ebb29408f10f374e14a7cc68ddfb3fed3df5 Mon Sep 17 00:00:00 2001
From: Yuya Kusakabe <yuya.kusakabe@gmail.com>
Date: Tue, 16 Apr 2019 10:22:28 +0900
Subject: [PATCH 06/24] net: Fix missing meta data in skb with vlan packet

[ Upstream commit d85e8be2a5a02869f815dd0ac2d743deb4cd7957 ]

skb_reorder_vlan_header() should move XDP meta data with ethernet header
if XDP meta data exists.

Fixes: de8f3a83b0a0 ("bpf: add meta pointer for direct access")
Signed-off-by: Yuya Kusakabe <yuya.kusakabe@gmail.com>
Signed-off-by: Takeru Hayasaka <taketarou2@gmail.com>
Co-developed-by: Takeru Hayasaka <taketarou2@gmail.com>
Reviewed-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index ceee28e184af..8b5768113acd 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5071,7 +5071,8 @@ EXPORT_SYMBOL_GPL(skb_gso_validate_mac_len);
 
 static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb)
 {
-	int mac_len;
+	int mac_len, meta_len;
+	void *meta;
 
 	if (skb_cow(skb, skb_headroom(skb)) < 0) {
 		kfree_skb(skb);
@@ -5083,6 +5084,13 @@ static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb)
 		memmove(skb_mac_header(skb) + VLAN_HLEN, skb_mac_header(skb),
 			mac_len - VLAN_HLEN - ETH_TLEN);
 	}
+
+	meta_len = skb_metadata_len(skb);
+	if (meta_len) {
+		meta = skb_metadata_end(skb) - meta_len;
+		memmove(meta + VLAN_HLEN, meta, meta_len);
+	}
+
 	skb->mac_header += VLAN_HLEN;
 	return skb;
 }
-- 
2.20.1


From fe31af228d2d7f38d8240f0d4696fbf06db63ddb Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Tue, 9 Apr 2019 11:47:20 +0200
Subject: [PATCH 07/24] net: fou: do not use guehdr after
 iptunnel_pull_offloads in gue_udp_recv

[ Upstream commit 988dc4a9a3b66be75b30405a5494faf0dc7cffb6 ]

gue tunnels run iptunnel_pull_offloads on received skbs. This can
determine a possible use-after-free accessing guehdr pointer since
the packet will be 'uncloned' running pskb_expand_head if it is a
cloned gso skb (e.g if the packet has been sent though a veth device)

Fixes: a09a4c8dd1ec ("tunnels: Remove encapsulation offloads on decap")
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fou.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 500a59906b87..854ff1e4c41f 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -120,6 +120,7 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb)
 	struct guehdr *guehdr;
 	void *data;
 	u16 doffset = 0;
+	u8 proto_ctype;
 
 	if (!fou)
 		return 1;
@@ -211,13 +212,14 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb)
 	if (unlikely(guehdr->control))
 		return gue_control_message(skb, guehdr);
 
+	proto_ctype = guehdr->proto_ctype;
 	__skb_pull(skb, sizeof(struct udphdr) + hdrlen);
 	skb_reset_transport_header(skb);
 
 	if (iptunnel_pull_offloads(skb))
 		goto drop;
 
-	return -guehdr->proto_ctype;
+	return -proto_ctype;
 
 drop:
 	kfree_skb(skb);
-- 
2.20.1


From 5022104b2aeb25b1454e50ef27eb4898af63e0c0 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 16 Apr 2019 10:55:20 -0700
Subject: [PATCH 08/24] tcp: tcp_grow_window() needs to respect tcp_space()

[ Upstream commit 50ce163a72d817a99e8974222dcf2886d5deb1ae ]

For some reason, tcp_grow_window() correctly tests if enough room
is present before attempting to increase tp->rcv_ssthresh,
but does not prevent it to grow past tcp_space()

This is causing hard to debug issues, like failing
the (__tcp_select_window(sk) >= tp->rcv_wnd) test
in __tcp_ack_snd_check(), causing ACK delays and possibly
slow flows.

Depending on tcp_rmem[2], MTU, skb->len/skb->truesize ratio,
we can see the problem happening on "netperf -t TCP_RR -- -r 2000,2000"
after about 60 round trips, when the active side no longer sends
immediate acks.

This bug predates git history.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Wei Wang <weiwan@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 572f79abd393..cfdd70e32755 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -402,11 +402,12 @@ static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb)
 static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	int room;
+
+	room = min_t(int, tp->window_clamp, tcp_space(sk)) - tp->rcv_ssthresh;
 
 	/* Check #1 */
-	if (tp->rcv_ssthresh < tp->window_clamp &&
-	    (int)tp->rcv_ssthresh < tcp_space(sk) &&
-	    !tcp_under_memory_pressure(sk)) {
+	if (room > 0 && !tcp_under_memory_pressure(sk)) {
 		int incr;
 
 		/* Check #2. Increase window, if skb with such overhead
@@ -419,8 +420,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb)
 
 		if (incr) {
 			incr = max_t(int, incr, 2 * skb->len);
-			tp->rcv_ssthresh = min(tp->rcv_ssthresh + incr,
-					       tp->window_clamp);
+			tp->rcv_ssthresh += min(room, incr);
 			inet_csk(sk)->icsk_ack.quick |= 1;
 		}
 	}
-- 
2.20.1


From 5d0c145a8b9a351119b8980aef950433dd547db2 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Mon, 8 Apr 2019 16:45:17 +0800
Subject: [PATCH 09/24] team: set slave to promisc if team is already in
 promisc mode

[ Upstream commit 43c2adb9df7ddd6560fd3546d925b42cef92daa0 ]

After adding a team interface to bridge, the team interface will enter
promisc mode. Then if we add a new slave to team0, the slave will keep
promisc off. Fix it by setting slave to promisc on if team master is
already in promisc mode, also do the same for allmulti.

v2: add promisc and allmulti checking when delete ports

Fixes: 3d249d4ca7d0 ("net: introduce ethernet teaming device")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 95ee9d815d76..e23eaf3f6d03 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1250,6 +1250,23 @@ static int team_port_add(struct team *team, struct net_device *port_dev,
 		goto err_option_port_add;
 	}
 
+	/* set promiscuity level to new slave */
+	if (dev->flags & IFF_PROMISC) {
+		err = dev_set_promiscuity(port_dev, 1);
+		if (err)
+			goto err_set_slave_promisc;
+	}
+
+	/* set allmulti level to new slave */
+	if (dev->flags & IFF_ALLMULTI) {
+		err = dev_set_allmulti(port_dev, 1);
+		if (err) {
+			if (dev->flags & IFF_PROMISC)
+				dev_set_promiscuity(port_dev, -1);
+			goto err_set_slave_promisc;
+		}
+	}
+
 	netif_addr_lock_bh(dev);
 	dev_uc_sync_multiple(port_dev, dev);
 	dev_mc_sync_multiple(port_dev, dev);
@@ -1266,6 +1283,9 @@ static int team_port_add(struct team *team, struct net_device *port_dev,
 
 	return 0;
 
+err_set_slave_promisc:
+	__team_option_inst_del_port(team, port);
+
 err_option_port_add:
 	team_upper_dev_unlink(team, port);
 
@@ -1311,6 +1331,12 @@ static int team_port_del(struct team *team, struct net_device *port_dev)
 
 	team_port_disable(team, port);
 	list_del_rcu(&port->list);
+
+	if (dev->flags & IFF_PROMISC)
+		dev_set_promiscuity(port_dev, -1);
+	if (dev->flags & IFF_ALLMULTI)
+		dev_set_allmulti(port_dev, -1);
+
 	team_upper_dev_unlink(team, port);
 	netdev_rx_handler_unregister(port_dev);
 	team_port_disable_netpoll(port);
-- 
2.20.1


From d51e4be0124d9823bde9d77391a2b2053c6af7e3 Mon Sep 17 00:00:00 2001
From: Hoang Le <hoang.h.le@dektech.com.au>
Date: Tue, 9 Apr 2019 14:59:24 +0700
Subject: [PATCH 10/24] tipc: missing entries in name table of publications

[ Upstream commit d1841533e54876f152a30ac398a34f47ad6590b1 ]

When binding multiple services with specific type 1Ki, 2Ki..,
this leads to some entries in the name table of publications
missing when listed out via 'tipc name show'.

The problem is at identify zero last_type conditional provided
via netlink. The first is initial 'type' when starting name table
dummping. The second is continuously with zero type (node state
service type). Then, lookup function failure to finding node state
service type in next iteration.

To solve this, adding more conditional to marked as dirty type and
lookup correct service type for the next iteration instead of select
the first service as initial 'type' zero.

Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Hoang Le <hoang.h.le@dektech.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/name_table.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index 66d5b2c5987a..d72985ca1d55 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -908,7 +908,8 @@ static int tipc_nl_service_list(struct net *net, struct tipc_nl_msg *msg,
 	for (; i < TIPC_NAMETBL_SIZE; i++) {
 		head = &tn->nametbl->services[i];
 
-		if (*last_type) {
+		if (*last_type ||
+		    (!i && *last_key && (*last_lower == *last_key))) {
 			service = tipc_service_find(net, *last_type);
 			if (!service)
 				return -EPIPE;
-- 
2.20.1


From da0a8e544c92ebfa4e13e4fcf236fd23da4e9d75 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Tue, 9 Apr 2019 12:10:25 +0800
Subject: [PATCH 11/24] vhost: reject zero size iova range

[ Upstream commit 813dbeb656d6c90266f251d8bd2b02d445afa63f ]

We used to accept zero size iova range which will lead a infinite loop
in translate_desc(). Fixing this by failing the request in this case.

Reported-by: syzbot+d21e6e297322a900c128@syzkaller.appspotmail.com
Fixes: 6b1e6cc7 ("vhost: new device IOTLB API")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/vhost.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index b214a72d5caa..c163bc15976a 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -911,8 +911,12 @@ static int vhost_new_umem_range(struct vhost_umem *umem,
 				u64 start, u64 size, u64 end,
 				u64 userspace_addr, int perm)
 {
-	struct vhost_umem_node *tmp, *node = kmalloc(sizeof(*node), GFP_ATOMIC);
+	struct vhost_umem_node *tmp, *node;
 
+	if (!size)
+		return -EFAULT;
+
+	node = kmalloc(sizeof(*node), GFP_ATOMIC);
 	if (!node)
 		return -ENOMEM;
 
-- 
2.20.1


From 5e20b6a1cf988b727db6298ea677c8f1b019e073 Mon Sep 17 00:00:00 2001
From: Stephen Suryaputra <ssuryaextr@gmail.com>
Date: Fri, 12 Apr 2019 16:19:27 -0400
Subject: [PATCH 12/24] ipv4: recompile ip options in ipv4_link_failure

[ Upstream commit ed0de45a1008991fdaa27a0152befcb74d126a8b ]

Recompile IP options since IPCB may not be valid anymore when
ipv4_link_failure is called from arp_error_report.

Refer to the commit 3da1ed7ac398 ("net: avoid use IPCB in cipso_v4_error")
and the commit before that (9ef6b42ad6fd) for a similar issue.

Signed-off-by: Stephen Suryaputra <ssuryaextr@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 7a556e459375..444e0d0aa20b 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1188,8 +1188,16 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
 static void ipv4_link_failure(struct sk_buff *skb)
 {
 	struct rtable *rt;
+	struct ip_options opt;
 
-	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);
+	/* Recompile ip options since IPCB may not be valid anymore.
+	 */
+	memset(&opt, 0, sizeof(opt));
+	opt.optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr);
+	if (__ip_options_compile(dev_net(skb->dev), &opt, skb, NULL))
+		return;
+
+	__icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0, &opt);
 
 	rt = skb_rtable(skb);
 	if (rt)
-- 
2.20.1


From f4769e697875582006a9556285529c1d9873cc05 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 13 Apr 2019 17:32:21 -0700
Subject: [PATCH 13/24] ipv4: ensure rcu_read_lock() in ipv4_link_failure()

[ Upstream commit c543cb4a5f07e09237ec0fc2c60c9f131b2c79ad ]

fib_compute_spec_dst() needs to be called under rcu protection.

syzbot reported :

WARNING: suspicious RCU usage
5.1.0-rc4+ #165 Not tainted
include/linux/inetdevice.h:220 suspicious rcu_dereference_check() usage!

other info that might help us debug this:

rcu_scheduler_active = 2, debug_locks = 1
1 lock held by swapper/0/0:
 #0: 0000000051b67925 ((&n->timer)){+.-.}, at: lockdep_copy_map include/linux/lockdep.h:170 [inline]
 #0: 0000000051b67925 ((&n->timer)){+.-.}, at: call_timer_fn+0xda/0x720 kernel/time/timer.c:1315

stack backtrace:
CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.1.0-rc4+ #165
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 lockdep_rcu_suspicious+0x153/0x15d kernel/locking/lockdep.c:5162
 __in_dev_get_rcu include/linux/inetdevice.h:220 [inline]
 fib_compute_spec_dst+0xbbd/0x1030 net/ipv4/fib_frontend.c:294
 spec_dst_fill net/ipv4/ip_options.c:245 [inline]
 __ip_options_compile+0x15a7/0x1a10 net/ipv4/ip_options.c:343
 ipv4_link_failure+0x172/0x400 net/ipv4/route.c:1195
 dst_link_failure include/net/dst.h:427 [inline]
 arp_error_report+0xd1/0x1c0 net/ipv4/arp.c:297
 neigh_invalidate+0x24b/0x570 net/core/neighbour.c:995
 neigh_timer_handler+0xc35/0xf30 net/core/neighbour.c:1081
 call_timer_fn+0x190/0x720 kernel/time/timer.c:1325
 expire_timers kernel/time/timer.c:1362 [inline]
 __run_timers kernel/time/timer.c:1681 [inline]
 __run_timers kernel/time/timer.c:1649 [inline]
 run_timer_softirq+0x652/0x1700 kernel/time/timer.c:1694
 __do_softirq+0x266/0x95a kernel/softirq.c:293
 invoke_softirq kernel/softirq.c:374 [inline]
 irq_exit+0x180/0x1d0 kernel/softirq.c:414
 exiting_irq arch/x86/include/asm/apic.h:536 [inline]
 smp_apic_timer_interrupt+0x14a/0x570 arch/x86/kernel/apic/apic.c:1062
 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:807

Fixes: ed0de45a1008 ("ipv4: recompile ip options in ipv4_link_failure")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Stephen Suryaputra <ssuryaextr@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 444e0d0aa20b..98c81c21b753 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1187,14 +1187,20 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
 
 static void ipv4_link_failure(struct sk_buff *skb)
 {
-	struct rtable *rt;
 	struct ip_options opt;
+	struct rtable *rt;
+	int res;
 
 	/* Recompile ip options since IPCB may not be valid anymore.
 	 */
 	memset(&opt, 0, sizeof(opt));
 	opt.optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr);
-	if (__ip_options_compile(dev_net(skb->dev), &opt, skb, NULL))
+
+	rcu_read_lock();
+	res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL);
+	rcu_read_unlock();
+
+	if (res)
 		return;
 
 	__icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0, &opt);
-- 
2.20.1


From 17dc97ea54f1ee2da7c367144ad0643f7654faad Mon Sep 17 00:00:00 2001
From: Matteo Croce <mcroce@redhat.com>
Date: Thu, 11 Apr 2019 12:26:32 +0200
Subject: [PATCH 14/24] net: thunderx: raise XDP MTU to 1508

[ Upstream commit 5ee15c101f29e0093ffb5448773ccbc786eb313b ]

The thunderx driver splits frames bigger than 1530 bytes to multiple
pages, making impossible to run an eBPF program on it.
This leads to a maximum MTU of 1508 if QinQ is in use.

The thunderx driver forbids to load an eBPF program if the MTU is higher
than 1500 bytes. Raise the limit to 1508 so it is possible to use L2
protocols which need some more headroom.

Fixes: 05c773f52b96e ("net: thunderx: Add basic XDP support")
Signed-off-by: Matteo Croce <mcroce@redhat.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/thunder/nicvf_main.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 9800738448ec..c9491dbea4d2 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -32,6 +32,13 @@
 #define DRV_NAME	"nicvf"
 #define DRV_VERSION	"1.0"
 
+/* NOTE: Packets bigger than 1530 are split across multiple pages and XDP needs
+ * the buffer to be contiguous. Allow XDP to be set up only if we don't exceed
+ * this value, keeping headroom for the 14 byte Ethernet header and two
+ * VLAN tags (for QinQ)
+ */
+#define MAX_XDP_MTU	(1530 - ETH_HLEN - VLAN_HLEN * 2)
+
 /* Supported devices */
 static const struct pci_device_id nicvf_id_table[] = {
 	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM,
@@ -1795,8 +1802,10 @@ static int nicvf_xdp_setup(struct nicvf *nic, struct bpf_prog *prog)
 	bool bpf_attached = false;
 	int ret = 0;
 
-	/* For now just support only the usual MTU sized frames */
-	if (prog && (dev->mtu > 1500)) {
+	/* For now just support only the usual MTU sized frames,
+	 * plus some headroom for VLAN, QinQ.
+	 */
+	if (prog && dev->mtu > MAX_XDP_MTU) {
 		netdev_warn(dev, "Jumbo frames not yet supported with XDP, current MTU %d.\n",
 			    dev->mtu);
 		return -EOPNOTSUPP;
-- 
2.20.1


From a14c1bd650d1b66a7a789dc6dbe246f909869786 Mon Sep 17 00:00:00 2001
From: Matteo Croce <mcroce@redhat.com>
Date: Thu, 11 Apr 2019 12:26:33 +0200
Subject: [PATCH 15/24] net: thunderx: don't allow jumbo frames with XDP

[ Upstream commit 1f227d16083b2e280b7dde4ca78883d75593f2fd ]

The thunderx driver forbids to load an eBPF program if the MTU is too high,
but this can be circumvented by loading the eBPF, then raising the MTU.

Fix this by limiting the MTU if an eBPF program is already loaded.

Fixes: 05c773f52b96e ("net: thunderx: Add basic XDP support")
Signed-off-by: Matteo Croce <mcroce@redhat.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/thunder/nicvf_main.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index c9491dbea4d2..dca02b35c231 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -1554,6 +1554,15 @@ static int nicvf_change_mtu(struct net_device *netdev, int new_mtu)
 	struct nicvf *nic = netdev_priv(netdev);
 	int orig_mtu = netdev->mtu;
 
+	/* For now just support only the usual MTU sized frames,
+	 * plus some headroom for VLAN, QinQ.
+	 */
+	if (nic->xdp_prog && new_mtu > MAX_XDP_MTU) {
+		netdev_warn(netdev, "Jumbo frames not yet supported with XDP, current MTU %d.\n",
+			    netdev->mtu);
+		return -EINVAL;
+	}
+
 	netdev->mtu = new_mtu;
 
 	if (!netif_running(netdev))
-- 
2.20.1


From b855e6ea2a1cc8f2b85d62c0abf3a00c88327234 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Tue, 19 Mar 2019 22:09:05 -0700
Subject: [PATCH 16/24] net/mlx5: FPGA, tls, hold rcu read lock a bit longer

[ Upstream commit 31634bf5dcc418b5b2cacd954394c0c4620db6a2 ]

To avoid use-after-free, hold the rcu read lock until we are done copying
flow data into the command buffer.

Fixes: ab412e1dd7db ("net/mlx5: Accel, add TLS rx offload routines")
Reported-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/fpga/tls.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
index 8de64e88c670..08aa7266c8c0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
@@ -217,22 +217,22 @@ int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
 	void *cmd;
 	int ret;
 
-	rcu_read_lock();
-	flow = idr_find(&mdev->fpga->tls->rx_idr, ntohl(handle));
-	rcu_read_unlock();
-
-	if (!flow) {
-		WARN_ONCE(1, "Received NULL pointer for handle\n");
-		return -EINVAL;
-	}
-
 	buf = kzalloc(size, GFP_ATOMIC);
 	if (!buf)
 		return -ENOMEM;
 
 	cmd = (buf + 1);
 
+	rcu_read_lock();
+	flow = idr_find(&mdev->fpga->tls->rx_idr, ntohl(handle));
+	if (unlikely(!flow)) {
+		rcu_read_unlock();
+		WARN_ONCE(1, "Received NULL pointer for handle\n");
+		kfree(buf);
+		return -EINVAL;
+	}
 	mlx5_fpga_tls_flow_to_cmd(flow, cmd);
+	rcu_read_unlock();
 
 	MLX5_SET(tls_cmd, cmd, swid, ntohl(handle));
 	MLX5_SET64(tls_cmd, cmd, tls_rcd_sn, be64_to_cpu(rcd_sn));
-- 
2.20.1


From 959431d96e25d2e7933e28e015a4317e68dcb29d Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 8 Apr 2019 17:59:50 -0700
Subject: [PATCH 17/24] net/tls: prevent bad memory access in
 tls_is_sk_tx_device_offloaded()

[ Upstream commit b4f47f3848eb70986f75d06112af7b48b7f5f462 ]

Unlike '&&' operator, the '&' does not have short-circuit
evaluation semantics.  IOW both sides of the operator always
get evaluated.  Fix the wrong operator in
tls_is_sk_tx_device_offloaded(), which would lead to
out-of-bounds access for for non-full sockets.

Fixes: 4799ac81e52a ("tls: Add rx inline crypto offload")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/tls.h b/include/net/tls.h
index 0a769cf2f5f3..c423b7d0b6ab 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -317,7 +317,7 @@ tls_validate_xmit_skb(struct sock *sk, struct net_device *dev,
 static inline bool tls_is_sk_tx_device_offloaded(struct sock *sk)
 {
 #ifdef CONFIG_SOCK_VALIDATE_XMIT
-	return sk_fullsock(sk) &
+	return sk_fullsock(sk) &&
 	       (smp_load_acquire(&sk->sk_validate_xmit_skb) ==
 	       &tls_validate_xmit_skb);
 #else
-- 
2.20.1


From fb21f434a5ad26993ec7277d59acb797d61a3752 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Tue, 19 Mar 2019 01:05:41 -0700
Subject: [PATCH 18/24] net/mlx5: FPGA, tls, idr remove on flow delete

[ Upstream commit df3a8344d404a810b4aadbf19b08c8232fbaa715 ]

Flow is kfreed on mlx5_fpga_tls_del_flow but kept in the idr data
structure, this is risky and can cause use-after-free, since the
idr_remove is delayed until tls_send_teardown_cmd completion.

Instead of delaying idr_remove, in this patch we do it on
mlx5_fpga_tls_del_flow, before actually kfree(flow).

Added synchronize_rcu before kfree(flow)

Fixes: ab412e1dd7db ("net/mlx5: Accel, add TLS rx offload routines")
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../ethernet/mellanox/mlx5/core/fpga/tls.c    | 43 +++++++------------
 1 file changed, 15 insertions(+), 28 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
index 08aa7266c8c0..22a2ef111514 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
@@ -148,14 +148,16 @@ static int mlx5_fpga_tls_alloc_swid(struct idr *idr, spinlock_t *idr_spinlock,
 	return ret;
 }
 
-static void mlx5_fpga_tls_release_swid(struct idr *idr,
-				       spinlock_t *idr_spinlock, u32 swid)
+static void *mlx5_fpga_tls_release_swid(struct idr *idr,
+					spinlock_t *idr_spinlock, u32 swid)
 {
 	unsigned long flags;
+	void *ptr;
 
 	spin_lock_irqsave(idr_spinlock, flags);
-	idr_remove(idr, swid);
+	ptr = idr_remove(idr, swid);
 	spin_unlock_irqrestore(idr_spinlock, flags);
+	return ptr;
 }
 
 static void mlx_tls_kfree_complete(struct mlx5_fpga_conn *conn,
@@ -165,20 +167,12 @@ static void mlx_tls_kfree_complete(struct mlx5_fpga_conn *conn,
 	kfree(buf);
 }
 
-struct mlx5_teardown_stream_context {
-	struct mlx5_fpga_tls_command_context cmd;
-	u32 swid;
-};
-
 static void
 mlx5_fpga_tls_teardown_completion(struct mlx5_fpga_conn *conn,
 				  struct mlx5_fpga_device *fdev,
 				  struct mlx5_fpga_tls_command_context *cmd,
 				  struct mlx5_fpga_dma_buf *resp)
 {
-	struct mlx5_teardown_stream_context *ctx =
-		    container_of(cmd, struct mlx5_teardown_stream_context, cmd);
-
 	if (resp) {
 		u32 syndrome = MLX5_GET(tls_resp, resp->sg[0].data, syndrome);
 
@@ -186,14 +180,6 @@ mlx5_fpga_tls_teardown_completion(struct mlx5_fpga_conn *conn,
 			mlx5_fpga_err(fdev,
 				      "Teardown stream failed with syndrome = %d",
 				      syndrome);
-		else if (MLX5_GET(tls_cmd, cmd->buf.sg[0].data, direction_sx))
-			mlx5_fpga_tls_release_swid(&fdev->tls->tx_idr,
-						   &fdev->tls->tx_idr_spinlock,
-						   ctx->swid);
-		else
-			mlx5_fpga_tls_release_swid(&fdev->tls->rx_idr,
-						   &fdev->tls->rx_idr_spinlock,
-						   ctx->swid);
 	}
 	mlx5_fpga_tls_put_command_ctx(cmd);
 }
@@ -253,7 +239,7 @@ int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
 static void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev,
 					    void *flow, u32 swid, gfp_t flags)
 {
-	struct mlx5_teardown_stream_context *ctx;
+	struct mlx5_fpga_tls_command_context *ctx;
 	struct mlx5_fpga_dma_buf *buf;
 	void *cmd;
 
@@ -261,7 +247,7 @@ static void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev,
 	if (!ctx)
 		return;
 
-	buf = &ctx->cmd.buf;
+	buf = &ctx->buf;
 	cmd = (ctx + 1);
 	MLX5_SET(tls_cmd, cmd, command_type, CMD_TEARDOWN_STREAM);
 	MLX5_SET(tls_cmd, cmd, swid, swid);
@@ -272,8 +258,7 @@ static void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev,
 	buf->sg[0].data = cmd;
 	buf->sg[0].size = MLX5_TLS_COMMAND_SIZE;
 
-	ctx->swid = swid;
-	mlx5_fpga_tls_cmd_send(mdev->fpga, &ctx->cmd,
+	mlx5_fpga_tls_cmd_send(mdev->fpga, ctx,
 			       mlx5_fpga_tls_teardown_completion);
 }
 
@@ -283,13 +268,14 @@ void mlx5_fpga_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
 	struct mlx5_fpga_tls *tls = mdev->fpga->tls;
 	void *flow;
 
-	rcu_read_lock();
 	if (direction_sx)
-		flow = idr_find(&tls->tx_idr, swid);
+		flow = mlx5_fpga_tls_release_swid(&tls->tx_idr,
+						  &tls->tx_idr_spinlock,
+						  swid);
 	else
-		flow = idr_find(&tls->rx_idr, swid);
-
-	rcu_read_unlock();
+		flow = mlx5_fpga_tls_release_swid(&tls->rx_idr,
+						  &tls->rx_idr_spinlock,
+						  swid);
 
 	if (!flow) {
 		mlx5_fpga_err(mdev->fpga, "No flow information for swid %u\n",
@@ -297,6 +283,7 @@ void mlx5_fpga_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
 		return;
 	}
 
+	synchronize_rcu(); /* before kfree(flow) */
 	mlx5_fpga_tls_send_teardown_cmd(mdev, flow, swid, flags);
 }
 
-- 
2.20.1


From 31527b872400d981e805a89b3ac9de42312a52f6 Mon Sep 17 00:00:00 2001
From: Jonathan Lemon <jonathan.lemon@gmail.com>
Date: Sun, 14 Apr 2019 14:21:29 -0700
Subject: [PATCH 19/24] route: Avoid crash from dereferencing NULL rt->from

[ Upstream commit 9c69a13205151c0d801de9f9d83a818e6e8f60ec ]

When __ip6_rt_update_pmtu() is called, rt->from is RCU dereferenced, but is
never checked for null - rt6_flush_exceptions() may have removed the entry.

[ 1913.989004] RIP: 0010:ip6_rt_cache_alloc+0x13/0x170
[ 1914.209410] Call Trace:
[ 1914.214798]  <IRQ>
[ 1914.219226]  __ip6_rt_update_pmtu+0xb0/0x190
[ 1914.228649]  ip6_tnl_xmit+0x2c2/0x970 [ip6_tunnel]
[ 1914.239223]  ? ip6_tnl_parse_tlv_enc_lim+0x32/0x1a0 [ip6_tunnel]
[ 1914.252489]  ? __gre6_xmit+0x148/0x530 [ip6_gre]
[ 1914.262678]  ip6gre_tunnel_xmit+0x17e/0x3c7 [ip6_gre]
[ 1914.273831]  dev_hard_start_xmit+0x8d/0x1f0
[ 1914.283061]  sch_direct_xmit+0xfa/0x230
[ 1914.291521]  __qdisc_run+0x154/0x4b0
[ 1914.299407]  net_tx_action+0x10e/0x1f0
[ 1914.307678]  __do_softirq+0xca/0x297
[ 1914.315567]  irq_exit+0x96/0xa0
[ 1914.322494]  smp_apic_timer_interrupt+0x68/0x130
[ 1914.332683]  apic_timer_interrupt+0xf/0x20
[ 1914.341721]  </IRQ>

Fixes: a68886a69180 ("net/ipv6: Make from in rt6_info rcu protected")
Signed-off-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 9006bb3c9e72..06fa8425d82c 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2367,6 +2367,10 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
 
 		rcu_read_lock();
 		from = rcu_dereference(rt6->from);
+		if (!from) {
+			rcu_read_unlock();
+			return;
+		}
 		nrt6 = ip6_rt_cache_alloc(from, daddr, saddr);
 		if (nrt6) {
 			rt6_do_update_pmtu(nrt6, mtu);
-- 
2.20.1


From 9f651225a873170d8ac1ff01beeaa54f19ef7ec0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
Date: Thu, 4 Apr 2019 15:01:33 +0200
Subject: [PATCH 20/24] sch_cake: Use tc_skb_protocol() helper for getting
 packet protocol
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit b2100cc56fca8c51d28aa42a9f1fbcb2cf351996 ]

We shouldn't be using skb->protocol directly as that will miss cases with
hardware-accelerated VLAN tags. Use the helper instead to get the right
protocol number.

Reported-by: Kevin Darbyshire-Bryant <kevin@darbyshire-bryant.me.uk>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
---
 net/sched/sch_cake.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 793016d722ec..c5e87d1c26eb 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -1526,7 +1526,7 @@ static u8 cake_handle_diffserv(struct sk_buff *skb, u16 wash)
 {
 	u8 dscp;
 
-	switch (skb->protocol) {
+	switch (tc_skb_protocol(skb)) {
 	case htons(ETH_P_IP):
 		dscp = ipv4_get_dsfield(ip_hdr(skb)) >> 2;
 		if (wash && dscp)
-- 
2.20.1


From ea977e4cb6b0e2a91c3b43fde0f613bc034a9074 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
Date: Thu, 4 Apr 2019 15:01:33 +0200
Subject: [PATCH 21/24] sch_cake: Make sure we can write the IP header before
 changing DSCP bits
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit c87b4ecdbe8db27867a7b7f840291cd843406bd7 ]

There is not actually any guarantee that the IP headers are valid before we
access the DSCP bits of the packets. Fix this using the same approach taken
in sch_dsmark.

Reported-by: Kevin Darbyshire-Bryant <kevin@darbyshire-bryant.me.uk>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
---
 net/sched/sch_cake.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index c5e87d1c26eb..75ca80909cf8 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -1524,16 +1524,27 @@ static void cake_wash_diffserv(struct sk_buff *skb)
 
 static u8 cake_handle_diffserv(struct sk_buff *skb, u16 wash)
 {
+	int wlen = skb_network_offset(skb);
 	u8 dscp;
 
 	switch (tc_skb_protocol(skb)) {
 	case htons(ETH_P_IP):
+		wlen += sizeof(struct iphdr);
+		if (!pskb_may_pull(skb, wlen) ||
+		    skb_try_make_writable(skb, wlen))
+			return 0;
+
 		dscp = ipv4_get_dsfield(ip_hdr(skb)) >> 2;
 		if (wash && dscp)
 			ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, 0);
 		return dscp;
 
 	case htons(ETH_P_IPV6):
+		wlen += sizeof(struct ipv6hdr);
+		if (!pskb_may_pull(skb, wlen) ||
+		    skb_try_make_writable(skb, wlen))
+			return 0;
+
 		dscp = ipv6_get_dsfield(ipv6_hdr(skb)) >> 2;
 		if (wash && dscp)
 			ipv6_change_dsfield(ipv6_hdr(skb), INET_ECN_MASK, 0);
-- 
2.20.1


From 33b74193684505720865603c886cf3766ce53be3 Mon Sep 17 00:00:00 2001
From: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Date: Mon, 1 Apr 2019 19:36:33 -0700
Subject: [PATCH 22/24] nfp: flower: replace CFI with vlan present

[ Upstream commit f7ee799a51ddbcc205ef615fe424fb5084e9e0aa ]

Replace vlan CFI bit with a vlan present bit that indicates the
presence of a vlan tag. Previously the driver incorrectly assumed
that an vlan id of 0 is not matchable, therefore we indicate vlan
presence with a vlan present bit.

Fixes: 5571e8c9f241 ("nfp: extend flower matching capabilities")
Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Signed-off-by: Louis Peens <louis.peens@netronome.com>
---
 drivers/net/ethernet/netronome/nfp/flower/cmsg.h  |  2 +-
 drivers/net/ethernet/netronome/nfp/flower/match.c | 14 ++++++--------
 2 files changed, 7 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
index 325954b829c8..3b7a8630530a 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
@@ -55,7 +55,7 @@
 #define NFP_FLOWER_LAYER2_GENEVE_OP	BIT(6)
 
 #define NFP_FLOWER_MASK_VLAN_PRIO	GENMASK(15, 13)
-#define NFP_FLOWER_MASK_VLAN_CFI	BIT(12)
+#define NFP_FLOWER_MASK_VLAN_PRESENT	BIT(12)
 #define NFP_FLOWER_MASK_VLAN_VID	GENMASK(11, 0)
 
 #define NFP_FLOWER_MASK_MPLS_LB		GENMASK(31, 12)
diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c
index 17acb8cc6044..b99d55cf81f1 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/match.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/match.c
@@ -56,14 +56,12 @@ nfp_flower_compile_meta_tci(struct nfp_flower_meta_tci *frame,
 						      FLOW_DISSECTOR_KEY_VLAN,
 						      target);
 		/* Populate the tci field. */
-		if (flow_vlan->vlan_id || flow_vlan->vlan_priority) {
-			tmp_tci = FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO,
-					     flow_vlan->vlan_priority) |
-				  FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID,
-					     flow_vlan->vlan_id) |
-				  NFP_FLOWER_MASK_VLAN_CFI;
-			frame->tci = cpu_to_be16(tmp_tci);
-		}
+		tmp_tci = NFP_FLOWER_MASK_VLAN_PRESENT;
+		tmp_tci |= FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO,
+				      flow_vlan->vlan_priority) |
+			   FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID,
+				      flow_vlan->vlan_id);
+		frame->tci = cpu_to_be16(tmp_tci);
 	}
 }
 
-- 
2.20.1


From 67420562cf89aa229349d48715ea2d686afdd50a Mon Sep 17 00:00:00 2001
From: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Date: Mon, 1 Apr 2019 19:36:34 -0700
Subject: [PATCH 23/24] nfp: flower: remove vlan CFI bit from push vlan action

[ Upstream commit 42cd5484a22f1a1b947e21e2af65fa7dab09d017 ]

We no longer set CFI when pushing vlan tags, therefore we remove
the CFI bit from push vlan.

Fixes: 1a1e586f54bf ("nfp: add basic action capabilities to flower offloads")
Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Signed-off-by: Louis Peens <louis.peens@netronome.com>
---
 drivers/net/ethernet/netronome/nfp/flower/action.c | 3 +--
 drivers/net/ethernet/netronome/nfp/flower/cmsg.h   | 1 -
 2 files changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c
index 7a1e9cd9cc62..777b99416062 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/action.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/action.c
@@ -80,8 +80,7 @@ nfp_fl_push_vlan(struct nfp_fl_push_vlan *push_vlan,
 
 	tmp_push_vlan_tci =
 		FIELD_PREP(NFP_FL_PUSH_VLAN_PRIO, tcf_vlan_push_prio(action)) |
-		FIELD_PREP(NFP_FL_PUSH_VLAN_VID, tcf_vlan_push_vid(action)) |
-		NFP_FL_PUSH_VLAN_CFI;
+		FIELD_PREP(NFP_FL_PUSH_VLAN_VID, tcf_vlan_push_vid(action));
 	push_vlan->vlan_tci = cpu_to_be16(tmp_push_vlan_tci);
 }
 
diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
index 3b7a8630530a..9b018321e24e 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
@@ -109,7 +109,6 @@
 #define NFP_FL_OUT_FLAGS_TYPE_IDX	GENMASK(2, 0)
 
 #define NFP_FL_PUSH_VLAN_PRIO		GENMASK(15, 13)
-#define NFP_FL_PUSH_VLAN_CFI		BIT(12)
 #define NFP_FL_PUSH_VLAN_VID		GENMASK(11, 0)
 
 /* LAG ports */
-- 
2.20.1


From 0621304b976ba29a3fa93b355e3ae2fb8f5e8578 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
Date: Fri, 5 Apr 2019 15:01:59 +0200
Subject: [PATCH 24/24] sch_cake: Simplify logic in cake_select_tin()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 4976e3c683f328bc6f2edef555a4ffee6524486f ]

The logic in cake_select_tin() was getting a bit hairy, and it turns out we
can simplify it quite a bit. This also allows us to get rid of one of the
two diffserv parsing functions, which has the added benefit that
already-zeroed DSCP fields won't get re-written.

Suggested-by: Kevin Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
---
 net/sched/sch_cake.c | 44 ++++++++++++++++----------------------------
 1 file changed, 16 insertions(+), 28 deletions(-)

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 75ca80909cf8..9fd37d91b5ed 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -1508,20 +1508,6 @@ static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free)
 	return idx + (tin << 16);
 }
 
-static void cake_wash_diffserv(struct sk_buff *skb)
-{
-	switch (skb->protocol) {
-	case htons(ETH_P_IP):
-		ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, 0);
-		break;
-	case htons(ETH_P_IPV6):
-		ipv6_change_dsfield(ipv6_hdr(skb), INET_ECN_MASK, 0);
-		break;
-	default:
-		break;
-	}
-}
-
 static u8 cake_handle_diffserv(struct sk_buff *skb, u16 wash)
 {
 	int wlen = skb_network_offset(skb);
@@ -1564,25 +1550,27 @@ static struct cake_tin_data *cake_select_tin(struct Qdisc *sch,
 {
 	struct cake_sched_data *q = qdisc_priv(sch);
 	u32 tin;
+	u8 dscp;
 
-	if (TC_H_MAJ(skb->priority) == sch->handle &&
-	    TC_H_MIN(skb->priority) > 0 &&
-	    TC_H_MIN(skb->priority) <= q->tin_cnt) {
+	/* Tin selection: Default to diffserv-based selection, allow overriding
+	 * using firewall marks or skb->priority.
+	 */
+	dscp = cake_handle_diffserv(skb,
+				    q->rate_flags & CAKE_FLAG_WASH);
+
+	if (q->tin_mode == CAKE_DIFFSERV_BESTEFFORT)
+		tin = 0;
+
+	else if (TC_H_MAJ(skb->priority) == sch->handle &&
+		 TC_H_MIN(skb->priority) > 0 &&
+		 TC_H_MIN(skb->priority) <= q->tin_cnt)
 		tin = q->tin_order[TC_H_MIN(skb->priority) - 1];
 
-		if (q->rate_flags & CAKE_FLAG_WASH)
-			cake_wash_diffserv(skb);
-	} else if (q->tin_mode != CAKE_DIFFSERV_BESTEFFORT) {
-		/* extract the Diffserv Precedence field, if it exists */
-		/* and clear DSCP bits if washing */
-		tin = q->tin_index[cake_handle_diffserv(skb,
-				q->rate_flags & CAKE_FLAG_WASH)];
+	else {
+		tin = q->tin_index[dscp];
+
 		if (unlikely(tin >= q->tin_cnt))
 			tin = 0;
-	} else {
-		tin = 0;
-		if (q->rate_flags & CAKE_FLAG_WASH)
-			cake_wash_diffserv(skb);
 	}
 
 	return &q->tins[tin];
-- 
2.20.1


[-- Attachment #3: net_50.mbox --]
[-- Type: Application/Octet-Stream, Size: 102211 bytes --]

From 013728d69feb9f3b0a973b0572ae1bee18d07a4d Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 12 Apr 2019 15:04:10 +0200
Subject: [PATCH 01/43] bonding: fix event handling for stacked bonds

[ Upstream commit 92480b3977fd3884649d404cbbaf839b70035699 ]

When a bond is enslaved to another bond, bond_netdev_event() only
handles the event as if the bond is a master, and skips treating the
bond as a slave.

This leads to a refcount leak on the slave, since we don't remove the
adjacency to its master and the master holds a reference on the slave.

Reproducer:
  ip link add bondL type bond
  ip link add bondU type bond
  ip link set bondL master bondU
  ip link del bondL

No "Fixes:" tag, this code is older than git history.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 537c90c8eb0a..f89fc6ea6078 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3214,8 +3214,12 @@ static int bond_netdev_event(struct notifier_block *this,
 		return NOTIFY_DONE;
 
 	if (event_dev->flags & IFF_MASTER) {
+		int ret;
+
 		netdev_dbg(event_dev, "IFF_MASTER\n");
-		return bond_master_netdev_event(event, event_dev);
+		ret = bond_master_netdev_event(event, event_dev);
+		if (ret != NOTIFY_DONE)
+			return ret;
 	}
 
 	if (event_dev->flags & IFF_SLAVE) {
-- 
2.20.1


From 23708d1903d08dba8cf5baa0379931516d555b91 Mon Sep 17 00:00:00 2001
From: Si-Wei Liu <si-wei.liu@oracle.com>
Date: Mon, 8 Apr 2019 19:45:27 -0400
Subject: [PATCH 02/43] failover: allow name change on IFF_UP slave interfaces

[ Upstream commit 8065a779f17e94536a1c4dcee4f9d88011672f97 ]

When a netdev appears through hot plug then gets enslaved by a failover
master that is already up and running, the slave will be opened
right away after getting enslaved. Today there's a race that userspace
(udev) may fail to rename the slave if the kernel (net_failover)
opens the slave earlier than when the userspace rename happens.
Unlike bond or team, the primary slave of failover can't be renamed by
userspace ahead of time, since the kernel initiated auto-enslavement is
unable to, or rather, is never meant to be synchronized with the rename
request from userspace.

As the failover slave interfaces are not designed to be operated
directly by userspace apps: IP configuration, filter rules with
regard to network traffic passing and etc., should all be done on master
interface. In general, userspace apps only care about the
name of master interface, while slave names are less important as long
as admin users can see reliable names that may carry
other information describing the netdev. For e.g., they can infer that
"ens3nsby" is a standby slave of "ens3", while for a
name like "eth0" they can't tell which master it belongs to.

Historically the name of IFF_UP interface can't be changed because
there might be admin script or management software that is already
relying on such behavior and assumes that the slave name can't be
changed once UP. But failover is special: with the in-kernel
auto-enslavement mechanism, the userspace expectation for device
enumeration and bring-up order is already broken. Previously initramfs
and various userspace config tools were modified to bypass failover
slaves because of auto-enslavement and duplicate MAC address. Similarly,
in case that users care about seeing reliable slave name, the new type
of failover slaves needs to be taken care of specifically in userspace
anyway.

It's less risky to lift up the rename restriction on failover slave
which is already UP. Although it's possible this change may potentially
break userspace component (most likely configuration scripts or
management software) that assumes slave name can't be changed while
UP, it's relatively a limited and controllable set among all userspace
components, which can be fixed specifically to listen for the rename
events on failover slaves. Userspace component interacting with slaves
is expected to be changed to operate on failover master interface
instead, as the failover slave is dynamic in nature which may come and
go at any point.  The goal is to make the role of failover slaves less
relevant, and userspace components should only deal with failover master
in the long run.

Fixes: 30c8bd5aa8b2 ("net: Introduce generic failover module")
Signed-off-by: Si-Wei Liu <si-wei.liu@oracle.com>
Reviewed-by: Liran Alon <liran.alon@oracle.com>
Acked-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  3 +++
 net/core/dev.c            | 16 +++++++++++++++-
 net/core/failover.c       |  6 +++---
 3 files changed, 21 insertions(+), 4 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 848b54b7ec91..7df56decae37 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1484,6 +1484,7 @@ struct net_device_ops {
  * @IFF_FAILOVER: device is a failover master device
  * @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device
  * @IFF_L3MDEV_RX_HANDLER: only invoke the rx handler of L3 master device
+ * @IFF_LIVE_RENAME_OK: rename is allowed while device is up and running
  */
 enum netdev_priv_flags {
 	IFF_802_1Q_VLAN			= 1<<0,
@@ -1516,6 +1517,7 @@ enum netdev_priv_flags {
 	IFF_FAILOVER			= 1<<27,
 	IFF_FAILOVER_SLAVE		= 1<<28,
 	IFF_L3MDEV_RX_HANDLER		= 1<<29,
+	IFF_LIVE_RENAME_OK		= 1<<30,
 };
 
 #define IFF_802_1Q_VLAN			IFF_802_1Q_VLAN
@@ -1547,6 +1549,7 @@ enum netdev_priv_flags {
 #define IFF_FAILOVER			IFF_FAILOVER
 #define IFF_FAILOVER_SLAVE		IFF_FAILOVER_SLAVE
 #define IFF_L3MDEV_RX_HANDLER		IFF_L3MDEV_RX_HANDLER
+#define IFF_LIVE_RENAME_OK		IFF_LIVE_RENAME_OK
 
 /**
  *	struct net_device - The DEVICE structure.
diff --git a/net/core/dev.c b/net/core/dev.c
index 12824e007e06..7277dd393c00 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1184,7 +1184,21 @@ int dev_change_name(struct net_device *dev, const char *newname)
 	BUG_ON(!dev_net(dev));
 
 	net = dev_net(dev);
-	if (dev->flags & IFF_UP)
+
+	/* Some auto-enslaved devices e.g. failover slaves are
+	 * special, as userspace might rename the device after
+	 * the interface had been brought up and running since
+	 * the point kernel initiated auto-enslavement. Allow
+	 * live name change even when these slave devices are
+	 * up and running.
+	 *
+	 * Typically, users of these auto-enslaving devices
+	 * don't actually care about slave name change, as
+	 * they are supposed to operate on master interface
+	 * directly.
+	 */
+	if (dev->flags & IFF_UP &&
+	    likely(!(dev->priv_flags & IFF_LIVE_RENAME_OK)))
 		return -EBUSY;
 
 	write_seqcount_begin(&devnet_rename_seq);
diff --git a/net/core/failover.c b/net/core/failover.c
index 4a92a98ccce9..b5cd3c727285 100644
--- a/net/core/failover.c
+++ b/net/core/failover.c
@@ -80,14 +80,14 @@ static int failover_slave_register(struct net_device *slave_dev)
 		goto err_upper_link;
 	}
 
-	slave_dev->priv_flags |= IFF_FAILOVER_SLAVE;
+	slave_dev->priv_flags |= (IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK);
 
 	if (fops && fops->slave_register &&
 	    !fops->slave_register(slave_dev, failover_dev))
 		return NOTIFY_OK;
 
 	netdev_upper_dev_unlink(slave_dev, failover_dev);
-	slave_dev->priv_flags &= ~IFF_FAILOVER_SLAVE;
+	slave_dev->priv_flags &= ~(IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK);
 err_upper_link:
 	netdev_rx_handler_unregister(slave_dev);
 done:
@@ -121,7 +121,7 @@ int failover_slave_unregister(struct net_device *slave_dev)
 
 	netdev_rx_handler_unregister(slave_dev);
 	netdev_upper_dev_unlink(slave_dev, failover_dev);
-	slave_dev->priv_flags &= ~IFF_FAILOVER_SLAVE;
+	slave_dev->priv_flags &= ~(IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK);
 
 	if (fops && fops->slave_unregister &&
 	    !fops->slave_unregister(slave_dev, failover_dev))
-- 
2.20.1


From 857fe2b46b5465ff4cc21e139a163c71f3563b55 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 15 Apr 2019 15:57:23 -0500
Subject: [PATCH 03/43] net: atm: Fix potential Spectre v1 vulnerabilities

[ Upstream commit 899537b73557aafbdd11050b501cf54b4f5c45af ]

arg is controlled by user-space, hence leading to a potential
exploitation of the Spectre variant 1 vulnerability.

This issue was detected with the help of Smatch:

net/atm/lec.c:715 lec_mcast_attach() warn: potential spectre issue 'dev_lec' [r] (local cap)

Fix this by sanitizing arg before using it to index dev_lec.

Notice that given that speculation windows are large, the policy is
to kill the speculation on the first load and not worry if it can be
completed with a dependent load/store [1].

[1] https://lore.kernel.org/lkml/20180423164740.GY17484@dhcp22.suse.cz/

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/atm/lec.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/atm/lec.c b/net/atm/lec.c
index d7f5cf5b7594..ad4f829193f0 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -710,7 +710,10 @@ static int lec_vcc_attach(struct atm_vcc *vcc, void __user *arg)
 
 static int lec_mcast_attach(struct atm_vcc *vcc, int arg)
 {
-	if (arg < 0 || arg >= MAX_LEC_ITF || !dev_lec[arg])
+	if (arg < 0 || arg >= MAX_LEC_ITF)
+		return -EINVAL;
+	arg = array_index_nospec(arg, MAX_LEC_ITF);
+	if (!dev_lec[arg])
 		return -EINVAL;
 	vcc->proto_data = dev_lec[arg];
 	return lec_mcast_make(netdev_priv(dev_lec[arg]), vcc);
@@ -728,6 +731,7 @@ static int lecd_attach(struct atm_vcc *vcc, int arg)
 		i = arg;
 	if (arg >= MAX_LEC_ITF)
 		return -EINVAL;
+	i = array_index_nospec(arg, MAX_LEC_ITF);
 	if (!dev_lec[i]) {
 		int size;
 
-- 
2.20.1


From 610c95032980660f29ff03a391aa08a2eb1afdcc Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Thu, 11 Apr 2019 13:56:39 +0300
Subject: [PATCH 04/43] net: bridge: fix per-port af_packet sockets

[ Upstream commit 3b2e2904deb314cc77a2192f506f2fd44e3d10d0 ]

When the commit below was introduced it changed two visible things:
 - the skb was no longer passed through the protocol handlers with the
   original device
 - the skb was passed up the stack with skb->dev = bridge

The first change broke af_packet sockets on bridge ports. For example we
use them for hostapd which listens for ETH_P_PAE packets on the ports.
We discussed two possible fixes:
 - create a clone and pass it through NF_HOOK(), act on the original skb
   based on the result
 - somehow signal to the caller from the okfn() that it was called,
   meaning the skb is ok to be passed, which this patch is trying to
   implement via returning 1 from the bridge link-local okfn()

Note that we rely on the fact that NF_QUEUE/STOLEN would return 0 and
drop/error would return < 0 thus the okfn() is called only when the
return was 1, so we signal to the caller that it was called by preserving
the return value from nf_hook().

Fixes: 8626c56c8279 ("bridge: fix potential use-after-free when hook returns QUEUE or STOLEN verdict")
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_input.c | 23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)

diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 5ea7e56119c1..ba303ee99b9b 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -197,13 +197,10 @@ static void __br_handle_local_finish(struct sk_buff *skb)
 /* note: already called with rcu_read_lock */
 static int br_handle_local_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
-	struct net_bridge_port *p = br_port_get_rcu(skb->dev);
-
 	__br_handle_local_finish(skb);
 
-	BR_INPUT_SKB_CB(skb)->brdev = p->br->dev;
-	br_pass_frame_up(skb);
-	return 0;
+	/* return 1 to signal the okfn() was called so it's ok to use the skb */
+	return 1;
 }
 
 /*
@@ -280,10 +277,18 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
 				goto forward;
 		}
 
-		/* Deliver packet to local host only */
-		NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, dev_net(skb->dev),
-			NULL, skb, skb->dev, NULL, br_handle_local_finish);
-		return RX_HANDLER_CONSUMED;
+		/* The else clause should be hit when nf_hook():
+		 *   - returns < 0 (drop/error)
+		 *   - returns = 0 (stolen/nf_queue)
+		 * Thus return 1 from the okfn() to signal the skb is ok to pass
+		 */
+		if (NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN,
+			    dev_net(skb->dev), NULL, skb, skb->dev, NULL,
+			    br_handle_local_finish) == 1) {
+			return RX_HANDLER_PASS;
+		} else {
+			return RX_HANDLER_CONSUMED;
+		}
 	}
 
 forward:
-- 
2.20.1


From e56652145c6e2b4b15c747fb4143472d12dfc6b0 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Thu, 11 Apr 2019 15:08:25 +0300
Subject: [PATCH 05/43] net: bridge: multicast: use rcu to access port list
 from br_multicast_start_querier

[ Upstream commit c5b493ce192bd7a4e7bd073b5685aad121eeef82 ]

br_multicast_start_querier() walks over the port list but it can be
called from a timer with only multicast_lock held which doesn't protect
the port list, so use RCU to walk over it.

Fixes: c83b8fab06fc ("bridge: Restart queries when last querier expires")
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index e4777614a8a0..61ff0d497da6 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1916,7 +1916,8 @@ static void br_multicast_start_querier(struct net_bridge *br,
 
 	__br_multicast_open(br, query);
 
-	list_for_each_entry(port, &br->port_list, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(port, &br->port_list, list) {
 		if (port->state == BR_STATE_DISABLED ||
 		    port->state == BR_STATE_BLOCKING)
 			continue;
@@ -1928,6 +1929,7 @@ static void br_multicast_start_querier(struct net_bridge *br,
 			br_multicast_enable(&port->ip6_own_query);
 #endif
 	}
+	rcu_read_unlock();
 }
 
 int br_multicast_toggle(struct net_bridge *br, unsigned long val)
-- 
2.20.1


From d8a6bbf17c63af1dd31acce674116ba49a1f4ca2 Mon Sep 17 00:00:00 2001
From: Andy Duan <fugang.duan@nxp.com>
Date: Tue, 9 Apr 2019 03:40:56 +0000
Subject: [PATCH 06/43] net: fec: manage ahb clock in runtime pm

[ Upstream commit d7c3a206e6338e4ccdf030719dec028e26a521d5 ]

Some SOC like i.MX6SX clock have some limits:
- ahb clock should be disabled before ipg.
- ahb and ipg clocks are required for MAC MII bus.
So, move the ahb clock to runtime management together with
ipg clock.

Signed-off-by: Fugang Duan <fugang.duan@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_main.c | 30 ++++++++++++++++-------
 1 file changed, 21 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 697c2427f2b7..a96ad20ee484 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -1840,13 +1840,9 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable)
 	int ret;
 
 	if (enable) {
-		ret = clk_prepare_enable(fep->clk_ahb);
-		if (ret)
-			return ret;
-
 		ret = clk_prepare_enable(fep->clk_enet_out);
 		if (ret)
-			goto failed_clk_enet_out;
+			return ret;
 
 		if (fep->clk_ptp) {
 			mutex_lock(&fep->ptp_clk_mutex);
@@ -1866,7 +1862,6 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable)
 
 		phy_reset_after_clk_enable(ndev->phydev);
 	} else {
-		clk_disable_unprepare(fep->clk_ahb);
 		clk_disable_unprepare(fep->clk_enet_out);
 		if (fep->clk_ptp) {
 			mutex_lock(&fep->ptp_clk_mutex);
@@ -1885,8 +1880,6 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable)
 failed_clk_ptp:
 	if (fep->clk_enet_out)
 		clk_disable_unprepare(fep->clk_enet_out);
-failed_clk_enet_out:
-		clk_disable_unprepare(fep->clk_ahb);
 
 	return ret;
 }
@@ -3470,6 +3463,9 @@ fec_probe(struct platform_device *pdev)
 	ret = clk_prepare_enable(fep->clk_ipg);
 	if (ret)
 		goto failed_clk_ipg;
+	ret = clk_prepare_enable(fep->clk_ahb);
+	if (ret)
+		goto failed_clk_ahb;
 
 	fep->reg_phy = devm_regulator_get_optional(&pdev->dev, "phy");
 	if (!IS_ERR(fep->reg_phy)) {
@@ -3563,6 +3559,9 @@ fec_probe(struct platform_device *pdev)
 	pm_runtime_put(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 failed_regulator:
+	clk_disable_unprepare(fep->clk_ahb);
+failed_clk_ahb:
+	clk_disable_unprepare(fep->clk_ipg);
 failed_clk_ipg:
 	fec_enet_clk_enable(ndev, false);
 failed_clk:
@@ -3686,6 +3685,7 @@ static int __maybe_unused fec_runtime_suspend(struct device *dev)
 	struct net_device *ndev = dev_get_drvdata(dev);
 	struct fec_enet_private *fep = netdev_priv(ndev);
 
+	clk_disable_unprepare(fep->clk_ahb);
 	clk_disable_unprepare(fep->clk_ipg);
 
 	return 0;
@@ -3695,8 +3695,20 @@ static int __maybe_unused fec_runtime_resume(struct device *dev)
 {
 	struct net_device *ndev = dev_get_drvdata(dev);
 	struct fec_enet_private *fep = netdev_priv(ndev);
+	int ret;
 
-	return clk_prepare_enable(fep->clk_ipg);
+	ret = clk_prepare_enable(fep->clk_ahb);
+	if (ret)
+		return ret;
+	ret = clk_prepare_enable(fep->clk_ipg);
+	if (ret)
+		goto failed_clk_ipg;
+
+	return 0;
+
+failed_clk_ipg:
+	clk_disable_unprepare(fep->clk_ahb);
+	return ret;
 }
 
 static const struct dev_pm_ops fec_pm_ops = {
-- 
2.20.1


From 0470687cb8bbec4ae7f47d52bdbc6f4e0ee5e642 Mon Sep 17 00:00:00 2001
From: Yuya Kusakabe <yuya.kusakabe@gmail.com>
Date: Tue, 16 Apr 2019 10:22:28 +0900
Subject: [PATCH 07/43] net: Fix missing meta data in skb with vlan packet

[ Upstream commit d85e8be2a5a02869f815dd0ac2d743deb4cd7957 ]

skb_reorder_vlan_header() should move XDP meta data with ethernet header
if XDP meta data exists.

Fixes: de8f3a83b0a0 ("bpf: add meta pointer for direct access")
Signed-off-by: Yuya Kusakabe <yuya.kusakabe@gmail.com>
Signed-off-by: Takeru Hayasaka <taketarou2@gmail.com>
Co-developed-by: Takeru Hayasaka <taketarou2@gmail.com>
Reviewed-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index ef2cd5712098..40796b8bf820 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5083,7 +5083,8 @@ EXPORT_SYMBOL_GPL(skb_gso_validate_mac_len);
 
 static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb)
 {
-	int mac_len;
+	int mac_len, meta_len;
+	void *meta;
 
 	if (skb_cow(skb, skb_headroom(skb)) < 0) {
 		kfree_skb(skb);
@@ -5095,6 +5096,13 @@ static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb)
 		memmove(skb_mac_header(skb) + VLAN_HLEN, skb_mac_header(skb),
 			mac_len - VLAN_HLEN - ETH_TLEN);
 	}
+
+	meta_len = skb_metadata_len(skb);
+	if (meta_len) {
+		meta = skb_metadata_end(skb) - meta_len;
+		memmove(meta + VLAN_HLEN, meta, meta_len);
+	}
+
 	skb->mac_header += VLAN_HLEN;
 	return skb;
 }
-- 
2.20.1


From 71250bde3ad4962938ce1f204c5f2198a1c9f502 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Tue, 9 Apr 2019 11:47:20 +0200
Subject: [PATCH 08/43] net: fou: do not use guehdr after
 iptunnel_pull_offloads in gue_udp_recv

[ Upstream commit 988dc4a9a3b66be75b30405a5494faf0dc7cffb6 ]

gue tunnels run iptunnel_pull_offloads on received skbs. This can
determine a possible use-after-free accessing guehdr pointer since
the packet will be 'uncloned' running pskb_expand_head if it is a
cloned gso skb (e.g if the packet has been sent though a veth device)

Fixes: a09a4c8dd1ec ("tunnels: Remove encapsulation offloads on decap")
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fou.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 79e98e21cdd7..12ce6c526d72 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -121,6 +121,7 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb)
 	struct guehdr *guehdr;
 	void *data;
 	u16 doffset = 0;
+	u8 proto_ctype;
 
 	if (!fou)
 		return 1;
@@ -212,13 +213,14 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb)
 	if (unlikely(guehdr->control))
 		return gue_control_message(skb, guehdr);
 
+	proto_ctype = guehdr->proto_ctype;
 	__skb_pull(skb, sizeof(struct udphdr) + hdrlen);
 	skb_reset_transport_header(skb);
 
 	if (iptunnel_pull_offloads(skb))
 		goto drop;
 
-	return -guehdr->proto_ctype;
+	return -proto_ctype;
 
 drop:
 	kfree_skb(skb);
-- 
2.20.1


From 16ba5f0296e4172c120a6cdf6107b3c26a791448 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 16 Apr 2019 10:55:20 -0700
Subject: [PATCH 09/43] tcp: tcp_grow_window() needs to respect tcp_space()

[ Upstream commit 50ce163a72d817a99e8974222dcf2886d5deb1ae ]

For some reason, tcp_grow_window() correctly tests if enough room
is present before attempting to increase tp->rcv_ssthresh,
but does not prevent it to grow past tcp_space()

This is causing hard to debug issues, like failing
the (__tcp_select_window(sk) >= tp->rcv_wnd) test
in __tcp_ack_snd_check(), causing ACK delays and possibly
slow flows.

Depending on tcp_rmem[2], MTU, skb->len/skb->truesize ratio,
we can see the problem happening on "netperf -t TCP_RR -- -r 2000,2000"
after about 60 round trips, when the active side no longer sends
immediate acks.

This bug predates git history.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Wei Wang <weiwan@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 7b1ef897b398..95b2e31fff08 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -402,11 +402,12 @@ static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb)
 static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	int room;
+
+	room = min_t(int, tp->window_clamp, tcp_space(sk)) - tp->rcv_ssthresh;
 
 	/* Check #1 */
-	if (tp->rcv_ssthresh < tp->window_clamp &&
-	    (int)tp->rcv_ssthresh < tcp_space(sk) &&
-	    !tcp_under_memory_pressure(sk)) {
+	if (room > 0 && !tcp_under_memory_pressure(sk)) {
 		int incr;
 
 		/* Check #2. Increase window, if skb with such overhead
@@ -419,8 +420,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb)
 
 		if (incr) {
 			incr = max_t(int, incr, 2 * skb->len);
-			tp->rcv_ssthresh = min(tp->rcv_ssthresh + incr,
-					       tp->window_clamp);
+			tp->rcv_ssthresh += min(room, incr);
 			inet_csk(sk)->icsk_ack.quick |= 1;
 		}
 	}
-- 
2.20.1


From 17389db94ca89663ad7175d19731ebd19b3b9dec Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Mon, 8 Apr 2019 16:45:17 +0800
Subject: [PATCH 10/43] team: set slave to promisc if team is already in
 promisc mode

[ Upstream commit 43c2adb9df7ddd6560fd3546d925b42cef92daa0 ]

After adding a team interface to bridge, the team interface will enter
promisc mode. Then if we add a new slave to team0, the slave will keep
promisc off. Fix it by setting slave to promisc on if team master is
already in promisc mode, also do the same for allmulti.

v2: add promisc and allmulti checking when delete ports

Fixes: 3d249d4ca7d0 ("net: introduce ethernet teaming device")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 6ce3f666d142..1283632091d5 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1247,6 +1247,23 @@ static int team_port_add(struct team *team, struct net_device *port_dev,
 		goto err_option_port_add;
 	}
 
+	/* set promiscuity level to new slave */
+	if (dev->flags & IFF_PROMISC) {
+		err = dev_set_promiscuity(port_dev, 1);
+		if (err)
+			goto err_set_slave_promisc;
+	}
+
+	/* set allmulti level to new slave */
+	if (dev->flags & IFF_ALLMULTI) {
+		err = dev_set_allmulti(port_dev, 1);
+		if (err) {
+			if (dev->flags & IFF_PROMISC)
+				dev_set_promiscuity(port_dev, -1);
+			goto err_set_slave_promisc;
+		}
+	}
+
 	netif_addr_lock_bh(dev);
 	dev_uc_sync_multiple(port_dev, dev);
 	dev_mc_sync_multiple(port_dev, dev);
@@ -1263,6 +1280,9 @@ static int team_port_add(struct team *team, struct net_device *port_dev,
 
 	return 0;
 
+err_set_slave_promisc:
+	__team_option_inst_del_port(team, port);
+
 err_option_port_add:
 	team_upper_dev_unlink(team, port);
 
@@ -1308,6 +1328,12 @@ static int team_port_del(struct team *team, struct net_device *port_dev)
 
 	team_port_disable(team, port);
 	list_del_rcu(&port->list);
+
+	if (dev->flags & IFF_PROMISC)
+		dev_set_promiscuity(port_dev, -1);
+	if (dev->flags & IFF_ALLMULTI)
+		dev_set_allmulti(port_dev, -1);
+
 	team_upper_dev_unlink(team, port);
 	netdev_rx_handler_unregister(port_dev);
 	team_port_disable_netpoll(port);
-- 
2.20.1


From 72c8dbafa11663dcd884aecd71ef26524d96203f Mon Sep 17 00:00:00 2001
From: Hoang Le <hoang.h.le@dektech.com.au>
Date: Tue, 9 Apr 2019 14:59:24 +0700
Subject: [PATCH 11/43] tipc: missing entries in name table of publications

[ Upstream commit d1841533e54876f152a30ac398a34f47ad6590b1 ]

When binding multiple services with specific type 1Ki, 2Ki..,
this leads to some entries in the name table of publications
missing when listed out via 'tipc name show'.

The problem is at identify zero last_type conditional provided
via netlink. The first is initial 'type' when starting name table
dummping. The second is continuously with zero type (node state
service type). Then, lookup function failure to finding node state
service type in next iteration.

To solve this, adding more conditional to marked as dirty type and
lookup correct service type for the next iteration instead of select
the first service as initial 'type' zero.

Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Hoang Le <hoang.h.le@dektech.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/name_table.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index bff241f03525..89993afe0fbd 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -909,7 +909,8 @@ static int tipc_nl_service_list(struct net *net, struct tipc_nl_msg *msg,
 	for (; i < TIPC_NAMETBL_SIZE; i++) {
 		head = &tn->nametbl->services[i];
 
-		if (*last_type) {
+		if (*last_type ||
+		    (!i && *last_key && (*last_lower == *last_key))) {
 			service = tipc_service_find(net, *last_type);
 			if (!service)
 				return -EPIPE;
-- 
2.20.1


From a59ab44a104ebd3367c756706d2f9d069d855ba1 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Tue, 9 Apr 2019 12:10:25 +0800
Subject: [PATCH 12/43] vhost: reject zero size iova range

[ Upstream commit 813dbeb656d6c90266f251d8bd2b02d445afa63f ]

We used to accept zero size iova range which will lead a infinite loop
in translate_desc(). Fixing this by failing the request in this case.

Reported-by: syzbot+d21e6e297322a900c128@syzkaller.appspotmail.com
Fixes: 6b1e6cc7 ("vhost: new device IOTLB API")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/vhost.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index a2e5dc7716e2..674cfc5a4084 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -911,8 +911,12 @@ static int vhost_new_umem_range(struct vhost_umem *umem,
 				u64 start, u64 size, u64 end,
 				u64 userspace_addr, int perm)
 {
-	struct vhost_umem_node *tmp, *node = kmalloc(sizeof(*node), GFP_ATOMIC);
+	struct vhost_umem_node *tmp, *node;
 
+	if (!size)
+		return -EFAULT;
+
+	node = kmalloc(sizeof(*node), GFP_ATOMIC);
 	if (!node)
 		return -ENOMEM;
 
-- 
2.20.1


From bf3e9c0ddfd919bf320ab18654c94efa520c1ba7 Mon Sep 17 00:00:00 2001
From: Stephen Suryaputra <ssuryaextr@gmail.com>
Date: Fri, 12 Apr 2019 16:19:27 -0400
Subject: [PATCH 13/43] ipv4: recompile ip options in ipv4_link_failure

[ Upstream commit ed0de45a1008991fdaa27a0152befcb74d126a8b ]

Recompile IP options since IPCB may not be valid anymore when
ipv4_link_failure is called from arp_error_report.

Refer to the commit 3da1ed7ac398 ("net: avoid use IPCB in cipso_v4_error")
and the commit before that (9ef6b42ad6fd) for a similar issue.

Signed-off-by: Stephen Suryaputra <ssuryaextr@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index e04cdb58a602..6bc427adcb06 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1186,8 +1186,16 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
 static void ipv4_link_failure(struct sk_buff *skb)
 {
 	struct rtable *rt;
+	struct ip_options opt;
 
-	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);
+	/* Recompile ip options since IPCB may not be valid anymore.
+	 */
+	memset(&opt, 0, sizeof(opt));
+	opt.optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr);
+	if (__ip_options_compile(dev_net(skb->dev), &opt, skb, NULL))
+		return;
+
+	__icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0, &opt);
 
 	rt = skb_rtable(skb);
 	if (rt)
-- 
2.20.1


From fa2be55e9084d778fbd8c22b2f40cabf2443a811 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 13 Apr 2019 17:32:21 -0700
Subject: [PATCH 14/43] ipv4: ensure rcu_read_lock() in ipv4_link_failure()

[ Upstream commit c543cb4a5f07e09237ec0fc2c60c9f131b2c79ad ]

fib_compute_spec_dst() needs to be called under rcu protection.

syzbot reported :

WARNING: suspicious RCU usage
5.1.0-rc4+ #165 Not tainted
include/linux/inetdevice.h:220 suspicious rcu_dereference_check() usage!

other info that might help us debug this:

rcu_scheduler_active = 2, debug_locks = 1
1 lock held by swapper/0/0:
 #0: 0000000051b67925 ((&n->timer)){+.-.}, at: lockdep_copy_map include/linux/lockdep.h:170 [inline]
 #0: 0000000051b67925 ((&n->timer)){+.-.}, at: call_timer_fn+0xda/0x720 kernel/time/timer.c:1315

stack backtrace:
CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.1.0-rc4+ #165
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 lockdep_rcu_suspicious+0x153/0x15d kernel/locking/lockdep.c:5162
 __in_dev_get_rcu include/linux/inetdevice.h:220 [inline]
 fib_compute_spec_dst+0xbbd/0x1030 net/ipv4/fib_frontend.c:294
 spec_dst_fill net/ipv4/ip_options.c:245 [inline]
 __ip_options_compile+0x15a7/0x1a10 net/ipv4/ip_options.c:343
 ipv4_link_failure+0x172/0x400 net/ipv4/route.c:1195
 dst_link_failure include/net/dst.h:427 [inline]
 arp_error_report+0xd1/0x1c0 net/ipv4/arp.c:297
 neigh_invalidate+0x24b/0x570 net/core/neighbour.c:995
 neigh_timer_handler+0xc35/0xf30 net/core/neighbour.c:1081
 call_timer_fn+0x190/0x720 kernel/time/timer.c:1325
 expire_timers kernel/time/timer.c:1362 [inline]
 __run_timers kernel/time/timer.c:1681 [inline]
 __run_timers kernel/time/timer.c:1649 [inline]
 run_timer_softirq+0x652/0x1700 kernel/time/timer.c:1694
 __do_softirq+0x266/0x95a kernel/softirq.c:293
 invoke_softirq kernel/softirq.c:374 [inline]
 irq_exit+0x180/0x1d0 kernel/softirq.c:414
 exiting_irq arch/x86/include/asm/apic.h:536 [inline]
 smp_apic_timer_interrupt+0x14a/0x570 arch/x86/kernel/apic/apic.c:1062
 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:807

Fixes: ed0de45a1008 ("ipv4: recompile ip options in ipv4_link_failure")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Stephen Suryaputra <ssuryaextr@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 6bc427adcb06..25d9bef27d03 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1185,14 +1185,20 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
 
 static void ipv4_link_failure(struct sk_buff *skb)
 {
-	struct rtable *rt;
 	struct ip_options opt;
+	struct rtable *rt;
+	int res;
 
 	/* Recompile ip options since IPCB may not be valid anymore.
 	 */
 	memset(&opt, 0, sizeof(opt));
 	opt.optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr);
-	if (__ip_options_compile(dev_net(skb->dev), &opt, skb, NULL))
+
+	rcu_read_lock();
+	res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL);
+	rcu_read_unlock();
+
+	if (res)
 		return;
 
 	__icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0, &opt);
-- 
2.20.1


From a641defdb5e27b8ed79d6907d497c1f63acc6b26 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 10 Apr 2019 06:58:12 +0000
Subject: [PATCH 15/43] mlxsw: spectrum_switchdev: Add MDB entries in prepare
 phase

[ Upstream commit d4d0e40977ac450f32f2db5e4d8e23c9d2578899 ]

The driver cannot guarantee in the prepare phase that it will be able to
write an MDB entry to the device. In case the driver returned success
during the prepare phase, but then failed to add the entry in the commit
phase, a WARNING [1] will be generated by the switchdev core.

Fix this by doing the work in the prepare phase instead.

[1]
[  358.544486] swp12s0: Commit of object (id=2) failed.
[  358.550061] WARNING: CPU: 0 PID: 30 at net/switchdev/switchdev.c:281 switchdev_port_obj_add_now+0x9b/0xe0
[  358.560754] CPU: 0 PID: 30 Comm: kworker/0:1 Not tainted 5.0.0-custom-13382-gf2449babf221 #1350
[  358.570472] Hardware name: Mellanox Technologies Ltd. MSN2100-CB2FO/SA001017, BIOS 5.6.5 06/07/2016
[  358.580582] Workqueue: events switchdev_deferred_process_work
[  358.587001] RIP: 0010:switchdev_port_obj_add_now+0x9b/0xe0
...
[  358.614109] RSP: 0018:ffffa6b900d6fe18 EFLAGS: 00010286
[  358.619943] RAX: 0000000000000000 RBX: ffff8b00797ff000 RCX: 0000000000000000
[  358.627912] RDX: ffff8b00b7a1d4c0 RSI: ffff8b00b7a152e8 RDI: ffff8b00b7a152e8
[  358.635881] RBP: ffff8b005c3f5bc0 R08: 000000000000022b R09: 0000000000000000
[  358.643850] R10: 0000000000000000 R11: ffffa6b900d6fcc8 R12: 0000000000000000
[  358.651819] R13: dead000000000100 R14: ffff8b00b65a23c0 R15: 0ffff8b00b7a2200
[  358.659790] FS:  0000000000000000(0000) GS:ffff8b00b7a00000(0000) knlGS:0000000000000000
[  358.668820] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  358.675228] CR2: 00007f00aad90de0 CR3: 00000001ca80d000 CR4: 00000000001006f0
[  358.683188] Call Trace:
[  358.685918]  switchdev_port_obj_add_deferred+0x13/0x60
[  358.691655]  switchdev_deferred_process+0x6b/0xf0
[  358.696907]  switchdev_deferred_process_work+0xa/0x10
[  358.702548]  process_one_work+0x1f5/0x3f0
[  358.707022]  worker_thread+0x28/0x3c0
[  358.711099]  ? process_one_work+0x3f0/0x3f0
[  358.715768]  kthread+0x10d/0x130
[  358.719369]  ? __kthread_create_on_node+0x180/0x180
[  358.724815]  ret_from_fork+0x35/0x40

Fixes: 3a49b4fde2a1 ("mlxsw: Adding layer 2 multicast support")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Alex Kushnarov <alexanderk@mellanox.com>
Tested-by: Alex Kushnarov <alexanderk@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index c772109b638d..f5a10e286400 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -1654,7 +1654,7 @@ static int mlxsw_sp_port_mdb_add(struct mlxsw_sp_port *mlxsw_sp_port,
 	u16 fid_index;
 	int err = 0;
 
-	if (switchdev_trans_ph_prepare(trans))
+	if (switchdev_trans_ph_commit(trans))
 		return 0;
 
 	bridge_port = mlxsw_sp_bridge_port_find(mlxsw_sp->bridge, orig_dev);
-- 
2.20.1


From b0f0a184550717db3944c6f2176765c730363625 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 10 Apr 2019 06:58:13 +0000
Subject: [PATCH 16/43] mlxsw: core: Do not use WQ_MEM_RECLAIM for EMAD
 workqueue

[ Upstream commit a8c133b06183c529c51cd0d54eb57d6b7078370c ]

The EMAD workqueue is used to handle retransmission of EMAD packets that
contain configuration data for the device's firmware.

Given the workers need to allocate these packets and that the code is
not called as part of memory reclaim path, remove the WQ_MEM_RECLAIM
flag.

Fixes: d965465b60ba ("mlxsw: core: Fix possible deadlock")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index ddedf8ab5b64..3be9da4b8f73 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -568,7 +568,7 @@ static int mlxsw_emad_init(struct mlxsw_core *mlxsw_core)
 	if (!(mlxsw_core->bus->features & MLXSW_BUS_F_TXRX))
 		return 0;
 
-	emad_wq = alloc_workqueue("mlxsw_core_emad", WQ_MEM_RECLAIM, 0);
+	emad_wq = alloc_workqueue("mlxsw_core_emad", 0, 0);
 	if (!emad_wq)
 		return -ENOMEM;
 	mlxsw_core->emad_wq = emad_wq;
-- 
2.20.1


From b421a67f756717ecacb07c7847b10e682b1316e4 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 10 Apr 2019 06:58:14 +0000
Subject: [PATCH 17/43] mlxsw: core: Do not use WQ_MEM_RECLAIM for mlxsw
 ordered workqueue

[ Upstream commit 4af0699782e2cc7d0d89db9eb6f8844dd3df82dc ]

The ordered workqueue is used to offload various objects such as routes
and neighbours in the order they are notified.

It should not be called as part of memory reclaim path, so remove the
WQ_MEM_RECLAIM flag. This can also result in a warning [1], if a worker
tries to flush a non-WQ_MEM_RECLAIM workqueue.

[1]
[97703.542861] workqueue: WQ_MEM_RECLAIM mlxsw_core_ordered:mlxsw_sp_router_fib6_event_work [mlxsw_spectrum] is flushing !WQ_MEM_RECLAIM events:rht_deferred_worker
[97703.542884] WARNING: CPU: 1 PID: 32492 at kernel/workqueue.c:2605 check_flush_dependency+0xb5/0x130
...
[97703.542988] Hardware name: Mellanox Technologies Ltd. MSN3700C/VMOD0008, BIOS 5.11 10/10/2018
[97703.543049] Workqueue: mlxsw_core_ordered mlxsw_sp_router_fib6_event_work [mlxsw_spectrum]
[97703.543061] RIP: 0010:check_flush_dependency+0xb5/0x130
...
[97703.543071] RSP: 0018:ffffb3f08137bc00 EFLAGS: 00010086
[97703.543076] RAX: 0000000000000000 RBX: ffff96e07740ae00 RCX: 0000000000000000
[97703.543080] RDX: 0000000000000094 RSI: ffffffff82dc1934 RDI: 0000000000000046
[97703.543084] RBP: ffffb3f08137bc20 R08: ffffffff82dc18a0 R09: 00000000000225c0
[97703.543087] R10: 0000000000000000 R11: 0000000000007eec R12: ffffffff816e4ee0
[97703.543091] R13: ffff96e06f6a5c00 R14: ffff96e077ba7700 R15: ffffffff812ab0c0
[97703.543097] FS: 0000000000000000(0000) GS:ffff96e077a80000(0000) knlGS:0000000000000000
[97703.543101] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[97703.543104] CR2: 00007f8cd135b280 CR3: 00000001e860e003 CR4: 00000000003606e0
[97703.543109] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[97703.543112] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[97703.543115] Call Trace:
[97703.543129] __flush_work+0xbd/0x1e0
[97703.543137] ? __cancel_work_timer+0x136/0x1b0
[97703.543145] ? pwq_dec_nr_in_flight+0x49/0xa0
[97703.543154] __cancel_work_timer+0x136/0x1b0
[97703.543175] ? mlxsw_reg_trans_bulk_wait+0x145/0x400 [mlxsw_core]
[97703.543184] cancel_work_sync+0x10/0x20
[97703.543191] rhashtable_free_and_destroy+0x23/0x140
[97703.543198] rhashtable_destroy+0xd/0x10
[97703.543254] mlxsw_sp_fib_destroy+0xb1/0xf0 [mlxsw_spectrum]
[97703.543310] mlxsw_sp_vr_put+0xa8/0xc0 [mlxsw_spectrum]
[97703.543364] mlxsw_sp_fib_node_put+0xbf/0x140 [mlxsw_spectrum]
[97703.543418] ? mlxsw_sp_fib6_entry_destroy+0xe8/0x110 [mlxsw_spectrum]
[97703.543475] mlxsw_sp_router_fib6_event_work+0x6cd/0x7f0 [mlxsw_spectrum]
[97703.543484] process_one_work+0x1fd/0x400
[97703.543493] worker_thread+0x34/0x410
[97703.543500] kthread+0x121/0x140
[97703.543507] ? process_one_work+0x400/0x400
[97703.543512] ? kthread_park+0x90/0x90
[97703.543523] ret_from_fork+0x35/0x40

Fixes: a3832b31898f ("mlxsw: core: Create an ordered workqueue for FIB offload")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Semion Lisyansky <semionl@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index 3be9da4b8f73..0cd58359e0c3 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -1915,7 +1915,7 @@ static int __init mlxsw_core_module_init(void)
 	mlxsw_wq = alloc_workqueue(mlxsw_core_driver_name, WQ_MEM_RECLAIM, 0);
 	if (!mlxsw_wq)
 		return -ENOMEM;
-	mlxsw_owq = alloc_ordered_workqueue("%s_ordered", WQ_MEM_RECLAIM,
+	mlxsw_owq = alloc_ordered_workqueue("%s_ordered", 0,
 					    mlxsw_core_driver_name);
 	if (!mlxsw_owq) {
 		err = -ENOMEM;
-- 
2.20.1


From bf457d5f226a03226cf0576a6aeb61e9671f1018 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 10 Apr 2019 06:58:15 +0000
Subject: [PATCH 18/43] mlxsw: core: Do not use WQ_MEM_RECLAIM for mlxsw
 workqueue

[ Upstream commit b442fed1b724af0de087912a5718ddde1b87acbb ]

The workqueue is used to periodically update the networking stack about
activity / statistics of various objects such as neighbours and TC
actions.

It should not be called as part of memory reclaim path, so remove the
WQ_MEM_RECLAIM flag.

Fixes: 3d5479e92087 ("mlxsw: core: Remove deprecated create_workqueue")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index 0cd58359e0c3..fc643fde5a4a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -1912,7 +1912,7 @@ static int __init mlxsw_core_module_init(void)
 {
 	int err;
 
-	mlxsw_wq = alloc_workqueue(mlxsw_core_driver_name, WQ_MEM_RECLAIM, 0);
+	mlxsw_wq = alloc_workqueue(mlxsw_core_driver_name, 0, 0);
 	if (!mlxsw_wq)
 		return -ENOMEM;
 	mlxsw_owq = alloc_ordered_workqueue("%s_ordered", 0,
-- 
2.20.1


From 704b274c8cbee9e01a50b72fdee5965e41277f55 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 10 Apr 2019 06:58:15 +0000
Subject: [PATCH 19/43] mlxsw: spectrum_router: Do not check VRF MAC address

[ Upstream commit 972fae683cbad5cf348268e76abc6d55cfb3ba87 ]

Commit 74bc99397438 ("mlxsw: spectrum_router: Veto unsupported RIF MAC
addresses") enabled the driver to veto router interface (RIF) MAC
addresses that it cannot support.

This check should only be performed for interfaces for which the driver
actually configures a RIF. A VRF upper is not one of them, so ignore it.

Without this patch it is not possible to set an IP address on the VRF
device and use it as a loopback.

Fixes: 74bc99397438 ("mlxsw: spectrum_router: Veto unsupported RIF MAC addresses")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Alexander Petrovskiy <alexpe@mellanox.com>
Tested-by: Alexander Petrovskiy <alexpe@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 98e5ffd71b91..2f6afbfd689f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -6745,7 +6745,7 @@ static int mlxsw_sp_router_port_check_rif_addr(struct mlxsw_sp *mlxsw_sp,
 	/* A RIF is not created for macvlan netdevs. Their MAC is used to
 	 * populate the FDB
 	 */
-	if (netif_is_macvlan(dev))
+	if (netif_is_macvlan(dev) || netif_is_l3_master(dev))
 		return 0;
 
 	for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) {
-- 
2.20.1


From 5f89fdcdfa61546623b8c487c471170da828a5fc Mon Sep 17 00:00:00 2001
From: Matteo Croce <mcroce@redhat.com>
Date: Thu, 11 Apr 2019 12:26:32 +0200
Subject: [PATCH 20/43] net: thunderx: raise XDP MTU to 1508

[ Upstream commit 5ee15c101f29e0093ffb5448773ccbc786eb313b ]

The thunderx driver splits frames bigger than 1530 bytes to multiple
pages, making impossible to run an eBPF program on it.
This leads to a maximum MTU of 1508 if QinQ is in use.

The thunderx driver forbids to load an eBPF program if the MTU is higher
than 1500 bytes. Raise the limit to 1508 so it is possible to use L2
protocols which need some more headroom.

Fixes: 05c773f52b96e ("net: thunderx: Add basic XDP support")
Signed-off-by: Matteo Croce <mcroce@redhat.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/thunder/nicvf_main.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index d4ee9f9c8c34..4fed3e88874c 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -32,6 +32,13 @@
 #define DRV_NAME	"nicvf"
 #define DRV_VERSION	"1.0"
 
+/* NOTE: Packets bigger than 1530 are split across multiple pages and XDP needs
+ * the buffer to be contiguous. Allow XDP to be set up only if we don't exceed
+ * this value, keeping headroom for the 14 byte Ethernet header and two
+ * VLAN tags (for QinQ)
+ */
+#define MAX_XDP_MTU	(1530 - ETH_HLEN - VLAN_HLEN * 2)
+
 /* Supported devices */
 static const struct pci_device_id nicvf_id_table[] = {
 	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM,
@@ -1830,8 +1837,10 @@ static int nicvf_xdp_setup(struct nicvf *nic, struct bpf_prog *prog)
 	bool bpf_attached = false;
 	int ret = 0;
 
-	/* For now just support only the usual MTU sized frames */
-	if (prog && (dev->mtu > 1500)) {
+	/* For now just support only the usual MTU sized frames,
+	 * plus some headroom for VLAN, QinQ.
+	 */
+	if (prog && dev->mtu > MAX_XDP_MTU) {
 		netdev_warn(dev, "Jumbo frames not yet supported with XDP, current MTU %d.\n",
 			    dev->mtu);
 		return -EOPNOTSUPP;
-- 
2.20.1


From 27673174ee57d5e3b81d59de3c554903487b75b0 Mon Sep 17 00:00:00 2001
From: Matteo Croce <mcroce@redhat.com>
Date: Thu, 11 Apr 2019 12:26:33 +0200
Subject: [PATCH 21/43] net: thunderx: don't allow jumbo frames with XDP

[ Upstream commit 1f227d16083b2e280b7dde4ca78883d75593f2fd ]

The thunderx driver forbids to load an eBPF program if the MTU is too high,
but this can be circumvented by loading the eBPF, then raising the MTU.

Fix this by limiting the MTU if an eBPF program is already loaded.

Fixes: 05c773f52b96e ("net: thunderx: Add basic XDP support")
Signed-off-by: Matteo Croce <mcroce@redhat.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/thunder/nicvf_main.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 4fed3e88874c..36263c77df46 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -1589,6 +1589,15 @@ static int nicvf_change_mtu(struct net_device *netdev, int new_mtu)
 	struct nicvf *nic = netdev_priv(netdev);
 	int orig_mtu = netdev->mtu;
 
+	/* For now just support only the usual MTU sized frames,
+	 * plus some headroom for VLAN, QinQ.
+	 */
+	if (nic->xdp_prog && new_mtu > MAX_XDP_MTU) {
+		netdev_warn(netdev, "Jumbo frames not yet supported with XDP, current MTU %d.\n",
+			    netdev->mtu);
+		return -EINVAL;
+	}
+
 	netdev->mtu = new_mtu;
 
 	if (!netif_running(netdev))
-- 
2.20.1


From aa8bb23c8f4b9605ab5af656558ddbfe43e73eb9 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 10 Apr 2019 11:04:30 -0700
Subject: [PATCH 22/43] net/tls: fix the IV leaks

[ Upstream commit 5a03bc73abed6ae196c15e9950afde19d48be12c ]

Commit f66de3ee2c16 ("net/tls: Split conf to rx + tx") made
freeing of IV and record sequence number conditional to SW
path only, but commit e8f69799810c ("net/tls: Add generic NIC
offload infrastructure") also allocates that state for the
device offload configuration.  Remember to free it.

Fixes: e8f69799810c ("net/tls: Add generic NIC offload infrastructure")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_device.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index d753e362d2d9..4a7f4da69b34 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -52,8 +52,11 @@ static DEFINE_SPINLOCK(tls_device_lock);
 
 static void tls_device_free_ctx(struct tls_context *ctx)
 {
-	if (ctx->tx_conf == TLS_HW)
+	if (ctx->tx_conf == TLS_HW) {
 		kfree(tls_offload_ctx_tx(ctx));
+		kfree(ctx->tx.rec_seq);
+		kfree(ctx->tx.iv);
+	}
 
 	if (ctx->rx_conf == TLS_HW)
 		kfree(tls_offload_ctx_rx(ctx));
-- 
2.20.1


From 192cfe7514038deff87547b85ab066b3372e269b Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 10 Apr 2019 11:04:31 -0700
Subject: [PATCH 23/43] net/tls: don't leak partially sent record in device
 mode

[ Upstream commit 35b71a34ada62c9573847a324bf06a133fe11b11 ]

David reports that tls triggers warnings related to
sk->sk_forward_alloc not being zero at destruction time:

WARNING: CPU: 5 PID: 6831 at net/core/stream.c:206 sk_stream_kill_queues+0x103/0x110
WARNING: CPU: 5 PID: 6831 at net/ipv4/af_inet.c:160 inet_sock_destruct+0x15b/0x170

When sender fills up the write buffer and dies from
SIGPIPE.  This is due to the device implementation
not cleaning up the partially_sent_record.

This is because commit a42055e8d2c3 ("net/tls: Add support for async encryption of records for performance")
moved the partial record cleanup to the SW-only path.

Fixes: a42055e8d2c3 ("net/tls: Add support for async encryption of records for performance")
Reported-by: David Beckett <david.beckett@netronome.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h    |  2 ++
 net/tls/tls_device.c |  7 +++++++
 net/tls/tls_main.c   | 22 ++++++++++++++++++++++
 net/tls/tls_sw.c     | 15 +--------------
 4 files changed, 32 insertions(+), 14 deletions(-)

diff --git a/include/net/tls.h b/include/net/tls.h
index 1486b60c4de8..02418e72b8b2 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -289,6 +289,7 @@ int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
 int tls_device_sendpage(struct sock *sk, struct page *page,
 			int offset, size_t size, int flags);
 void tls_device_sk_destruct(struct sock *sk);
+void tls_device_free_resources_tx(struct sock *sk);
 void tls_device_init(void);
 void tls_device_cleanup(void);
 int tls_tx_records(struct sock *sk, int flags);
@@ -312,6 +313,7 @@ int tls_push_sg(struct sock *sk, struct tls_context *ctx,
 		int flags);
 int tls_push_partial_record(struct sock *sk, struct tls_context *ctx,
 			    int flags);
+bool tls_free_partial_record(struct sock *sk, struct tls_context *ctx);
 
 int tls_push_pending_closed_record(struct sock *sk, struct tls_context *ctx,
 				   int flags, long *timeo);
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 4a7f4da69b34..4b5ff3d44912 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -219,6 +219,13 @@ void tls_device_sk_destruct(struct sock *sk)
 }
 EXPORT_SYMBOL(tls_device_sk_destruct);
 
+void tls_device_free_resources_tx(struct sock *sk)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+
+	tls_free_partial_record(sk, tls_ctx);
+}
+
 static void tls_append_frag(struct tls_record_info *record,
 			    struct page_frag *pfrag,
 			    int size)
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 78cb4a584080..8f3df7da99d9 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -220,6 +220,26 @@ int tls_push_pending_closed_record(struct sock *sk,
 		return tls_ctx->push_pending_record(sk, flags);
 }
 
+bool tls_free_partial_record(struct sock *sk, struct tls_context *ctx)
+{
+	struct scatterlist *sg;
+
+	sg = ctx->partially_sent_record;
+	if (!sg)
+		return false;
+
+	while (1) {
+		put_page(sg_page(sg));
+		sk_mem_uncharge(sk, sg->length);
+
+		if (sg_is_last(sg))
+			break;
+		sg++;
+	}
+	ctx->partially_sent_record = NULL;
+	return true;
+}
+
 static void tls_write_space(struct sock *sk)
 {
 	struct tls_context *ctx = tls_get_ctx(sk);
@@ -278,6 +298,8 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
 		kfree(ctx->tx.rec_seq);
 		kfree(ctx->tx.iv);
 		tls_sw_free_resources_tx(sk);
+	} else if (ctx->tx_conf == TLS_HW) {
+		tls_device_free_resources_tx(sk);
 	}
 
 	if (ctx->rx_conf == TLS_SW) {
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index bf5b54b513bc..d2d4f7c0d4be 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1804,20 +1804,7 @@ void tls_sw_free_resources_tx(struct sock *sk)
 	/* Free up un-sent records in tx_list. First, free
 	 * the partially sent record if any at head of tx_list.
 	 */
-	if (tls_ctx->partially_sent_record) {
-		struct scatterlist *sg = tls_ctx->partially_sent_record;
-
-		while (1) {
-			put_page(sg_page(sg));
-			sk_mem_uncharge(sk, sg->length);
-
-			if (sg_is_last(sg))
-				break;
-			sg++;
-		}
-
-		tls_ctx->partially_sent_record = NULL;
-
+	if (tls_free_partial_record(sk, tls_ctx)) {
 		rec = list_first_entry(&ctx->tx_list,
 				       struct tls_rec, list);
 		list_del(&rec->list);
-- 
2.20.1


From 8478612644563f8d39f7ef67730ce9d225e4042e Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 10 Apr 2019 11:04:32 -0700
Subject: [PATCH 24/43] net: strparser: partially revert "strparser: Call
 skb_unclone conditionally"

[ Upstream commit 4a9c2e3746e6151fd5d077259d79ce9ca86d47d7 ]

This reverts the first part of commit 4e485d06bb8c ("strparser: Call
skb_unclone conditionally").  To build a message with multiple
fragments we need our own root of frag_list.  We can't simply
use the frag_list of orig_skb, because it will lead to linking
all orig_skbs together creating very long frag chains, and causing
stack overflow on kfree_skb() (which is called recursively on
the frag_lists).

BUG: stack guard page was hit at 00000000d40fad41 (stack is 0000000029dde9f4..000000008cce03d5)
kernel stack overflow (double-fault): 0000 [#1] PREEMPT SMP
RIP: 0010:free_one_page+0x2b/0x490

Call Trace:
  __free_pages_ok+0x143/0x2c0
  skb_release_data+0x8e/0x140
  ? skb_release_data+0xad/0x140
  kfree_skb+0x32/0xb0

  [...]

  skb_release_data+0xad/0x140
  ? skb_release_data+0xad/0x140
  kfree_skb+0x32/0xb0
  skb_release_data+0xad/0x140
  ? skb_release_data+0xad/0x140
  kfree_skb+0x32/0xb0
  skb_release_data+0xad/0x140
  ? skb_release_data+0xad/0x140
  kfree_skb+0x32/0xb0
  skb_release_data+0xad/0x140
  ? skb_release_data+0xad/0x140
  kfree_skb+0x32/0xb0
  skb_release_data+0xad/0x140
  __kfree_skb+0xe/0x20
  tcp_disconnect+0xd6/0x4d0
  tcp_close+0xf4/0x430
  ? tcp_check_oom+0xf0/0xf0
  tls_sk_proto_close+0xe4/0x1e0 [tls]
  inet_release+0x36/0x60
  __sock_release+0x37/0xa0
  sock_close+0x11/0x20
  __fput+0xa2/0x1d0
  task_work_run+0x89/0xb0
  exit_to_usermode_loop+0x9a/0xa0
  do_syscall_64+0xc0/0xf0
  entry_SYSCALL_64_after_hwframe+0x44/0xa9

Let's leave the second unclone conditional, as I'm not entirely
sure what is its purpose :)

Fixes: 4e485d06bb8c ("strparser: Call skb_unclone conditionally")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/strparser/strparser.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index da1a676860ca..0f4e42792878 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -140,13 +140,11 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb,
 			/* We are going to append to the frags_list of head.
 			 * Need to unshare the frag_list.
 			 */
-			if (skb_has_frag_list(head)) {
-				err = skb_unclone(head, GFP_ATOMIC);
-				if (err) {
-					STRP_STATS_INCR(strp->stats.mem_fail);
-					desc->error = err;
-					return 0;
-				}
+			err = skb_unclone(head, GFP_ATOMIC);
+			if (err) {
+				STRP_STATS_INCR(strp->stats.mem_fail);
+				desc->error = err;
+				return 0;
 			}
 
 			if (unlikely(skb_shinfo(head)->frag_list)) {
-- 
2.20.1


From cde113a455924c42b3c8d166b2ea2d9a4849c066 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 10 Apr 2019 16:23:39 -0700
Subject: [PATCH 25/43] net/tls: fix build without CONFIG_TLS_DEVICE

[ Upstream commit 903f1a187776bb8d79b13618ec05b25f86318885 ]

buildbot noticed that TLS_HW is not defined if CONFIG_TLS_DEVICE=n.
Wrap the cleanup branch into an ifdef, tls_device_free_resources_tx()
wouldn't be compiled either in this case.

Fixes: 35b71a34ada6 ("net/tls: don't leak partially sent record in device mode")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 8f3df7da99d9..96dbac91ac6e 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -298,8 +298,10 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
 		kfree(ctx->tx.rec_seq);
 		kfree(ctx->tx.iv);
 		tls_sw_free_resources_tx(sk);
+#ifdef CONFIG_TLS_DEVICE
 	} else if (ctx->tx_conf == TLS_HW) {
 		tls_device_free_resources_tx(sk);
+#endif
 	}
 
 	if (ctx->rx_conf == TLS_SW) {
-- 
2.20.1


From 96d6660c09f3d020e7be38610737e462d02d8b2f Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Tue, 16 Apr 2019 16:15:56 +0300
Subject: [PATCH 26/43] net: bridge: fix netlink export of vlan_stats_per_port
 option

[ Upstream commit 600bea7dba1a72874ae0cd9bc66bf2abfe43b49d ]

Since the introduction of the vlan_stats_per_port option the netlink
export of it has been broken since I made a typo and used the ifla
attribute instead of the bridge option to retrieve its state.
Sysfs export is fine, only netlink export has been affected.

Fixes: 9163a0fc1f0c0 ("net: bridge: add support for per-port vlan stats")
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_netlink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 9c07591b0232..7104cf13da84 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -1441,7 +1441,7 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev)
 	    nla_put_u8(skb, IFLA_BR_VLAN_STATS_ENABLED,
 		       br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) ||
 	    nla_put_u8(skb, IFLA_BR_VLAN_STATS_PER_PORT,
-		       br_opt_get(br, IFLA_BR_VLAN_STATS_PER_PORT)))
+		       br_opt_get(br, BROPT_VLAN_STATS_PER_PORT)))
 		return -EMSGSIZE;
 #endif
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
-- 
2.20.1


From c4f69c4770e9a1a75283ce0f3e3673e86cb37edb Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Thu, 21 Mar 2019 19:07:20 -0700
Subject: [PATCH 27/43] net/mlx5e: XDP, Avoid checksum complete when XDP prog
 is loaded

[ Upstream commit 5d0bb3bac4b9f6c22280b04545626fdfd99edc6b ]

XDP programs might change packets data contents which will make the
reported skb checksum (checksum complete) invalid.

When XDP programs are loaded/unloaded set/clear rx RQs
MLX5E_RQ_STATE_NO_CSUM_COMPLETE flag.

Fixes: 86994156c736 ("net/mlx5e: XDP fast RX drop bpf programs support")
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 3 ++-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c    | 6 +++++-
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c      | 3 ++-
 3 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index e6099f51d25f..3b9e5f0d0212 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1665,7 +1665,8 @@ static int set_pflag_rx_no_csum_complete(struct net_device *netdev, bool enable)
 	struct mlx5e_channel *c;
 	int i;
 
-	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state) ||
+	    priv->channels.params.xdp_prog)
 		return 0;
 
 	for (i = 0; i < channels->num; i++) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 93e50ccd44c3..3ea541f30ee0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -950,7 +950,11 @@ static int mlx5e_open_rq(struct mlx5e_channel *c,
 	if (params->rx_dim_enabled)
 		__set_bit(MLX5E_RQ_STATE_AM, &c->rq.state);
 
-	if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_NO_CSUM_COMPLETE))
+	/* We disable csum_complete when XDP is enabled since
+	 * XDP programs might manipulate packets which will render
+	 * skb->checksum incorrect.
+	 */
+	if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_NO_CSUM_COMPLETE) || c->xdp)
 		__set_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &c->rq.state);
 
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index f86e4804e83e..4cbf15da8eb3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -753,7 +753,8 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 		return;
 	}
 
-	if (unlikely(test_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &rq->state)))
+	/* True when explicitly set via priv flag, or XDP prog is loaded */
+	if (test_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &rq->state))
 		goto csum_unnecessary;
 
 	/* CQE csum doesn't cover padding octets in short ethernet
-- 
2.20.1


From d4df64dad9d5e63080e117feee3b833713cabb21 Mon Sep 17 00:00:00 2001
From: Dmytro Linkin <dmitrolin@mellanox.com>
Date: Fri, 29 Mar 2019 12:50:37 +0000
Subject: [PATCH 28/43] net/mlx5e: Protect against non-uplink representor for
 encap

[ Upstream commit 5e0060b1491b299b1706414e61ede0b02265680e ]

TC encap offload is supported only for the physical uplink
representor. Fail for non uplink representor.

Fixes: 3e621b19b0bb ("net/mlx5e: Support TC encapsulation offloads with upper devices")
Signed-off-by: Dmytro Linkin <dmitrolin@mellanox.com>
Reviewed-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Vlad Buslov <vladbu@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index f3c7ab6faea5..b8521e2f64ac 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -39,6 +39,10 @@ static int get_route_and_out_devs(struct mlx5e_priv *priv,
 			return -EOPNOTSUPP;
 	}
 
+	if (!(mlx5e_eswitch_rep(*out_dev) &&
+	      mlx5e_is_uplink_rep(netdev_priv(*out_dev))))
+		return -EOPNOTSUPP;
+
 	return 0;
 }
 
-- 
2.20.1


From 0dc4d7f89e7fdb22d7715b3a0a803c5ed2036946 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Date: Fri, 31 Aug 2018 14:29:16 +0300
Subject: [PATCH 29/43] net/mlx5e: Switch to Toeplitz RSS hash by default

[ Upstream commit 7ee2ace9c544a0886e02b54b625e521df8692d20 ]

Although XOR hash function can perform very well on some special use
cases, to align with all drivers, mlx5 driver should use Toeplitz hash
by default.
Toeplitz is more stable for the general use case and it is more standard
and reliable.

On top of that, since XOR (MLX5_RX_HASH_FN_INVERTED_XOR8) gives only a
repeated 8 bits pattern. When used for udp tunneling RSS source port
manipulation it results in fixed source port, which will cause bad RSS
spread.

Fixes: 2be6967cdbc9 ("net/mlx5e: Support ETH_RSS_HASH_XOR")
Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 3ea541f30ee0..0cb19e4dd439 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4574,7 +4574,7 @@ void mlx5e_build_rss_params(struct mlx5e_rss_params *rss_params,
 {
 	enum mlx5e_traffic_types tt;
 
-	rss_params->hfunc = ETH_RSS_HASH_XOR;
+	rss_params->hfunc = ETH_RSS_HASH_TOP;
 	netdev_rss_key_fill(rss_params->toeplitz_hash_key,
 			    sizeof(rss_params->toeplitz_hash_key));
 	mlx5e_build_default_indir_rqt(rss_params->indirection_rqt,
-- 
2.20.1


From 9963458ce8a1f3d6504fdb78c3084e7be66bc796 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Tue, 12 Mar 2019 00:24:52 -0700
Subject: [PATCH 30/43] net/mlx5e: Rx, Fixup skb checksum for packets with tail
 padding

[ Upstream commit 0aa1d18615c163f92935b806dcaff9157645233a ]

When an ethernet frame with ip payload is padded, the padding octets are
not covered by the hardware checksum.

Prior to the cited commit, skb checksum was forced to be CHECKSUM_NONE
when padding is detected. After it, the kernel will try to trim the
padding bytes and subtract their checksum from skb->csum.

In this patch we fixup skb->csum for any ip packet with tail padding of
any size, if any padding found.
FCS case is just one special case of this general purpose patch, hence,
it is removed.

Fixes: 88078d98d1bb ("net: pskb_trim_rcsum() and CHECKSUM_COMPLETE are friends"),
Cc: Eric Dumazet <edumazet@google.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en_rx.c   | 79 +++++++++++++++----
 .../ethernet/mellanox/mlx5/core/en_stats.c    |  6 ++
 .../ethernet/mellanox/mlx5/core/en_stats.h    |  4 +
 3 files changed, 74 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 4cbf15da8eb3..31a7b3d8e5d3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -713,17 +713,6 @@ static inline void mlx5e_enable_ecn(struct mlx5e_rq *rq, struct sk_buff *skb)
 	rq->stats->ecn_mark += !!rc;
 }
 
-static u32 mlx5e_get_fcs(const struct sk_buff *skb)
-{
-	const void *fcs_bytes;
-	u32 _fcs_bytes;
-
-	fcs_bytes = skb_header_pointer(skb, skb->len - ETH_FCS_LEN,
-				       ETH_FCS_LEN, &_fcs_bytes);
-
-	return __get_unaligned_cpu32(fcs_bytes);
-}
-
 static u8 get_ip_proto(struct sk_buff *skb, int network_depth, __be16 proto)
 {
 	void *ip_p = skb->data + network_depth;
@@ -734,6 +723,68 @@ static u8 get_ip_proto(struct sk_buff *skb, int network_depth, __be16 proto)
 
 #define short_frame(size) ((size) <= ETH_ZLEN + ETH_FCS_LEN)
 
+#define MAX_PADDING 8
+
+static void
+tail_padding_csum_slow(struct sk_buff *skb, int offset, int len,
+		       struct mlx5e_rq_stats *stats)
+{
+	stats->csum_complete_tail_slow++;
+	skb->csum = csum_block_add(skb->csum,
+				   skb_checksum(skb, offset, len, 0),
+				   offset);
+}
+
+static void
+tail_padding_csum(struct sk_buff *skb, int offset,
+		  struct mlx5e_rq_stats *stats)
+{
+	u8 tail_padding[MAX_PADDING];
+	int len = skb->len - offset;
+	void *tail;
+
+	if (unlikely(len > MAX_PADDING)) {
+		tail_padding_csum_slow(skb, offset, len, stats);
+		return;
+	}
+
+	tail = skb_header_pointer(skb, offset, len, tail_padding);
+	if (unlikely(!tail)) {
+		tail_padding_csum_slow(skb, offset, len, stats);
+		return;
+	}
+
+	stats->csum_complete_tail++;
+	skb->csum = csum_block_add(skb->csum, csum_partial(tail, len, 0), offset);
+}
+
+static void
+mlx5e_skb_padding_csum(struct sk_buff *skb, int network_depth, __be16 proto,
+		       struct mlx5e_rq_stats *stats)
+{
+	struct ipv6hdr *ip6;
+	struct iphdr   *ip4;
+	int pkt_len;
+
+	switch (proto) {
+	case htons(ETH_P_IP):
+		ip4 = (struct iphdr *)(skb->data + network_depth);
+		pkt_len = network_depth + ntohs(ip4->tot_len);
+		break;
+	case htons(ETH_P_IPV6):
+		ip6 = (struct ipv6hdr *)(skb->data + network_depth);
+		pkt_len = network_depth + sizeof(*ip6) + ntohs(ip6->payload_len);
+		break;
+	default:
+		return;
+	}
+
+	if (likely(pkt_len >= skb->len))
+		return;
+
+	tail_padding_csum(skb, pkt_len, stats);
+}
+
 static inline void mlx5e_handle_csum(struct net_device *netdev,
 				     struct mlx5_cqe64 *cqe,
 				     struct mlx5e_rq *rq,
@@ -782,10 +833,8 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 			skb->csum = csum_partial(skb->data + ETH_HLEN,
 						 network_depth - ETH_HLEN,
 						 skb->csum);
-		if (unlikely(netdev->features & NETIF_F_RXFCS))
-			skb->csum = csum_block_add(skb->csum,
-						   (__force __wsum)mlx5e_get_fcs(skb),
-						   skb->len - ETH_FCS_LEN);
+
+		mlx5e_skb_padding_csum(skb, network_depth, proto, stats);
 		stats->csum_complete++;
 		return;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index d3fe48ff9da9..4461b44acafc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -59,6 +59,8 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_none) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_complete) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_complete_tail) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_complete_tail_slow) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary_inner) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_drop) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_redirect) },
@@ -151,6 +153,8 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 		s->rx_removed_vlan_packets += rq_stats->removed_vlan_packets;
 		s->rx_csum_none	+= rq_stats->csum_none;
 		s->rx_csum_complete += rq_stats->csum_complete;
+		s->rx_csum_complete_tail += rq_stats->csum_complete_tail;
+		s->rx_csum_complete_tail_slow += rq_stats->csum_complete_tail_slow;
 		s->rx_csum_unnecessary += rq_stats->csum_unnecessary;
 		s->rx_csum_unnecessary_inner += rq_stats->csum_unnecessary_inner;
 		s->rx_xdp_drop     += rq_stats->xdp_drop;
@@ -1192,6 +1196,8 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, packets) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, bytes) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_complete) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_complete_tail) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_complete_tail_slow) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary_inner) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_none) },
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index fe91ec06e3c7..714303bf0797 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -71,6 +71,8 @@ struct mlx5e_sw_stats {
 	u64 rx_csum_unnecessary;
 	u64 rx_csum_none;
 	u64 rx_csum_complete;
+	u64 rx_csum_complete_tail;
+	u64 rx_csum_complete_tail_slow;
 	u64 rx_csum_unnecessary_inner;
 	u64 rx_xdp_drop;
 	u64 rx_xdp_redirect;
@@ -181,6 +183,8 @@ struct mlx5e_rq_stats {
 	u64 packets;
 	u64 bytes;
 	u64 csum_complete;
+	u64 csum_complete_tail;
+	u64 csum_complete_tail_slow;
 	u64 csum_unnecessary;
 	u64 csum_unnecessary_inner;
 	u64 csum_none;
-- 
2.20.1


From 68647c0499c932e1112cd1a06724100926d19788 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 25 Mar 2019 22:10:59 -0700
Subject: [PATCH 31/43] net/mlx5e: Rx, Check ip headers sanity

[ Upstream commit 0318a7b7fcad9765931146efa7ca3a034194737c ]

In the two places is_last_ethertype_ip is being called, the caller will
be looking inside the ip header, to be safe, add ip{4,6} header sanity
check. And return true only on valid ip headers, i.e: the whole header
is contained in the linear part of the skb.

Note: Such situation is very rare and hard to reproduce, since mlx5e
allocates a large enough headroom to contain the largest header one can
imagine.

Fixes: fe1dc069990c ("net/mlx5e: don't set CHECKSUM_COMPLETE on SCTP packets")
Reported-by: Cong Wang <xiyou.wangcong@gmail.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 31a7b3d8e5d3..1c7ef919f546 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -693,7 +693,14 @@ static inline bool is_last_ethertype_ip(struct sk_buff *skb, int *network_depth,
 {
 	*proto = ((struct ethhdr *)skb->data)->h_proto;
 	*proto = __vlan_get_protocol(skb, *proto, network_depth);
-	return (*proto == htons(ETH_P_IP) || *proto == htons(ETH_P_IPV6));
+
+	if (*proto == htons(ETH_P_IP))
+		return pskb_may_pull(skb, *network_depth + sizeof(struct iphdr));
+
+	if (*proto == htons(ETH_P_IPV6))
+		return pskb_may_pull(skb, *network_depth + sizeof(struct ipv6hdr));
+
+	return false;
 }
 
 static inline void mlx5e_enable_ecn(struct mlx5e_rq *rq, struct sk_buff *skb)
-- 
2.20.1


From 14dd4b2eb5a5eb8fb45e630d2b83636ce3a78366 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Sun, 31 Mar 2019 12:53:03 +0000
Subject: [PATCH 32/43] Revert "net/mlx5e: Enable reporting checksum
 unnecessary also for L3 packets"

[ Upstream commit 8c8811d46d00d119ffbe039a6e52a0b504df1c2c ]

This reverts commit b820e6fb0978f9c2ac438c199d2bb2f35950e9c9.

Prior the commit we are reverting, checksum unnecessary was only set when
both the L3 OK and L4 OK bits are set on the CQE. This caused packets
of IP protocols such as SCTP which are not dealt by the current HW L4
parser (hence the L4 OK bit is not set, but the L4 header type none bit
is set) to go through the checksum none code, where currently we wrongly
report checksum unnecessary for them, a regression. Fix this by a revert.

Note that on our usual track we report checksum complete, so the revert
isn't expected to have any notable performance impact. Also, when we are
not on the checksum complete track, the L4 protocols for which we report
checksum none are not high performance ones, we will still report
checksum unnecessary for UDP/TCP.

Fixes: b820e6fb0978 ("net/mlx5e: Enable reporting checksum unnecessary also for L3 packets")
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reported-by: Avi Urman <aviu@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 1c7ef919f546..2cbda8abd8b9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -848,8 +848,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 
 csum_unnecessary:
 	if (likely((cqe->hds_ip_ext & CQE_L3_OK) &&
-		   ((cqe->hds_ip_ext & CQE_L4_OK) ||
-		    (get_cqe_l4_hdr_type(cqe) == CQE_L4_HDR_TYPE_NONE)))) {
+		   (cqe->hds_ip_ext & CQE_L4_OK))) {
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
 		if (cqe_is_tunneled(cqe)) {
 			skb->csum_level = 1;
-- 
2.20.1


From 5a26b22829b786a440a3effd9d3b2e7a8b4d0fbd Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Tue, 19 Mar 2019 22:09:05 -0700
Subject: [PATCH 33/43] net/mlx5: FPGA, tls, hold rcu read lock a bit longer

[ Upstream commit 31634bf5dcc418b5b2cacd954394c0c4620db6a2 ]

To avoid use-after-free, hold the rcu read lock until we are done copying
flow data into the command buffer.

Fixes: ab412e1dd7db ("net/mlx5: Accel, add TLS rx offload routines")
Reported-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/fpga/tls.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
index 8de64e88c670..08aa7266c8c0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
@@ -217,22 +217,22 @@ int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
 	void *cmd;
 	int ret;
 
-	rcu_read_lock();
-	flow = idr_find(&mdev->fpga->tls->rx_idr, ntohl(handle));
-	rcu_read_unlock();
-
-	if (!flow) {
-		WARN_ONCE(1, "Received NULL pointer for handle\n");
-		return -EINVAL;
-	}
-
 	buf = kzalloc(size, GFP_ATOMIC);
 	if (!buf)
 		return -ENOMEM;
 
 	cmd = (buf + 1);
 
+	rcu_read_lock();
+	flow = idr_find(&mdev->fpga->tls->rx_idr, ntohl(handle));
+	if (unlikely(!flow)) {
+		rcu_read_unlock();
+		WARN_ONCE(1, "Received NULL pointer for handle\n");
+		kfree(buf);
+		return -EINVAL;
+	}
 	mlx5_fpga_tls_flow_to_cmd(flow, cmd);
+	rcu_read_unlock();
 
 	MLX5_SET(tls_cmd, cmd, swid, ntohl(handle));
 	MLX5_SET64(tls_cmd, cmd, tls_rcd_sn, be64_to_cpu(rcd_sn));
-- 
2.20.1


From 10ce5625f86a74f3aa01ca21f9e7f5c577d42b11 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 8 Apr 2019 17:59:50 -0700
Subject: [PATCH 34/43] net/tls: prevent bad memory access in
 tls_is_sk_tx_device_offloaded()

[ Upstream commit b4f47f3848eb70986f75d06112af7b48b7f5f462 ]

Unlike '&&' operator, the '&' does not have short-circuit
evaluation semantics.  IOW both sides of the operator always
get evaluated.  Fix the wrong operator in
tls_is_sk_tx_device_offloaded(), which would lead to
out-of-bounds access for for non-full sockets.

Fixes: 4799ac81e52a ("tls: Add rx inline crypto offload")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/tls.h b/include/net/tls.h
index 02418e72b8b2..8b3d10917d99 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -366,7 +366,7 @@ tls_validate_xmit_skb(struct sock *sk, struct net_device *dev,
 static inline bool tls_is_sk_tx_device_offloaded(struct sock *sk)
 {
 #ifdef CONFIG_SOCK_VALIDATE_XMIT
-	return sk_fullsock(sk) &
+	return sk_fullsock(sk) &&
 	       (smp_load_acquire(&sk->sk_validate_xmit_skb) ==
 	       &tls_validate_xmit_skb);
 #else
-- 
2.20.1


From 27a6fb26dfd4c1ec7e3c6290e44ef4a573c0d261 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Tue, 19 Mar 2019 01:05:41 -0700
Subject: [PATCH 35/43] net/mlx5: FPGA, tls, idr remove on flow delete

[ Upstream commit df3a8344d404a810b4aadbf19b08c8232fbaa715 ]

Flow is kfreed on mlx5_fpga_tls_del_flow but kept in the idr data
structure, this is risky and can cause use-after-free, since the
idr_remove is delayed until tls_send_teardown_cmd completion.

Instead of delaying idr_remove, in this patch we do it on
mlx5_fpga_tls_del_flow, before actually kfree(flow).

Added synchronize_rcu before kfree(flow)

Fixes: ab412e1dd7db ("net/mlx5: Accel, add TLS rx offload routines")
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../ethernet/mellanox/mlx5/core/fpga/tls.c    | 43 +++++++------------
 1 file changed, 15 insertions(+), 28 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
index 08aa7266c8c0..22a2ef111514 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
@@ -148,14 +148,16 @@ static int mlx5_fpga_tls_alloc_swid(struct idr *idr, spinlock_t *idr_spinlock,
 	return ret;
 }
 
-static void mlx5_fpga_tls_release_swid(struct idr *idr,
-				       spinlock_t *idr_spinlock, u32 swid)
+static void *mlx5_fpga_tls_release_swid(struct idr *idr,
+					spinlock_t *idr_spinlock, u32 swid)
 {
 	unsigned long flags;
+	void *ptr;
 
 	spin_lock_irqsave(idr_spinlock, flags);
-	idr_remove(idr, swid);
+	ptr = idr_remove(idr, swid);
 	spin_unlock_irqrestore(idr_spinlock, flags);
+	return ptr;
 }
 
 static void mlx_tls_kfree_complete(struct mlx5_fpga_conn *conn,
@@ -165,20 +167,12 @@ static void mlx_tls_kfree_complete(struct mlx5_fpga_conn *conn,
 	kfree(buf);
 }
 
-struct mlx5_teardown_stream_context {
-	struct mlx5_fpga_tls_command_context cmd;
-	u32 swid;
-};
-
 static void
 mlx5_fpga_tls_teardown_completion(struct mlx5_fpga_conn *conn,
 				  struct mlx5_fpga_device *fdev,
 				  struct mlx5_fpga_tls_command_context *cmd,
 				  struct mlx5_fpga_dma_buf *resp)
 {
-	struct mlx5_teardown_stream_context *ctx =
-		    container_of(cmd, struct mlx5_teardown_stream_context, cmd);
-
 	if (resp) {
 		u32 syndrome = MLX5_GET(tls_resp, resp->sg[0].data, syndrome);
 
@@ -186,14 +180,6 @@ mlx5_fpga_tls_teardown_completion(struct mlx5_fpga_conn *conn,
 			mlx5_fpga_err(fdev,
 				      "Teardown stream failed with syndrome = %d",
 				      syndrome);
-		else if (MLX5_GET(tls_cmd, cmd->buf.sg[0].data, direction_sx))
-			mlx5_fpga_tls_release_swid(&fdev->tls->tx_idr,
-						   &fdev->tls->tx_idr_spinlock,
-						   ctx->swid);
-		else
-			mlx5_fpga_tls_release_swid(&fdev->tls->rx_idr,
-						   &fdev->tls->rx_idr_spinlock,
-						   ctx->swid);
 	}
 	mlx5_fpga_tls_put_command_ctx(cmd);
 }
@@ -253,7 +239,7 @@ int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
 static void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev,
 					    void *flow, u32 swid, gfp_t flags)
 {
-	struct mlx5_teardown_stream_context *ctx;
+	struct mlx5_fpga_tls_command_context *ctx;
 	struct mlx5_fpga_dma_buf *buf;
 	void *cmd;
 
@@ -261,7 +247,7 @@ static void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev,
 	if (!ctx)
 		return;
 
-	buf = &ctx->cmd.buf;
+	buf = &ctx->buf;
 	cmd = (ctx + 1);
 	MLX5_SET(tls_cmd, cmd, command_type, CMD_TEARDOWN_STREAM);
 	MLX5_SET(tls_cmd, cmd, swid, swid);
@@ -272,8 +258,7 @@ static void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev,
 	buf->sg[0].data = cmd;
 	buf->sg[0].size = MLX5_TLS_COMMAND_SIZE;
 
-	ctx->swid = swid;
-	mlx5_fpga_tls_cmd_send(mdev->fpga, &ctx->cmd,
+	mlx5_fpga_tls_cmd_send(mdev->fpga, ctx,
 			       mlx5_fpga_tls_teardown_completion);
 }
 
@@ -283,13 +268,14 @@ void mlx5_fpga_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
 	struct mlx5_fpga_tls *tls = mdev->fpga->tls;
 	void *flow;
 
-	rcu_read_lock();
 	if (direction_sx)
-		flow = idr_find(&tls->tx_idr, swid);
+		flow = mlx5_fpga_tls_release_swid(&tls->tx_idr,
+						  &tls->tx_idr_spinlock,
+						  swid);
 	else
-		flow = idr_find(&tls->rx_idr, swid);
-
-	rcu_read_unlock();
+		flow = mlx5_fpga_tls_release_swid(&tls->rx_idr,
+						  &tls->rx_idr_spinlock,
+						  swid);
 
 	if (!flow) {
 		mlx5_fpga_err(mdev->fpga, "No flow information for swid %u\n",
@@ -297,6 +283,7 @@ void mlx5_fpga_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
 		return;
 	}
 
+	synchronize_rcu(); /* before kfree(flow) */
 	mlx5_fpga_tls_send_teardown_cmd(mdev, flow, swid, flags);
 }
 
-- 
2.20.1


From 8b9ce7b7fbe16f4408c97c8dc8e7f3b65e040b4b Mon Sep 17 00:00:00 2001
From: Jonathan Lemon <jonathan.lemon@gmail.com>
Date: Sun, 14 Apr 2019 14:21:29 -0700
Subject: [PATCH 36/43] route: Avoid crash from dereferencing NULL rt->from

[ Upstream commit 9c69a13205151c0d801de9f9d83a818e6e8f60ec ]

When __ip6_rt_update_pmtu() is called, rt->from is RCU dereferenced, but is
never checked for null - rt6_flush_exceptions() may have removed the entry.

[ 1913.989004] RIP: 0010:ip6_rt_cache_alloc+0x13/0x170
[ 1914.209410] Call Trace:
[ 1914.214798]  <IRQ>
[ 1914.219226]  __ip6_rt_update_pmtu+0xb0/0x190
[ 1914.228649]  ip6_tnl_xmit+0x2c2/0x970 [ip6_tunnel]
[ 1914.239223]  ? ip6_tnl_parse_tlv_enc_lim+0x32/0x1a0 [ip6_tunnel]
[ 1914.252489]  ? __gre6_xmit+0x148/0x530 [ip6_gre]
[ 1914.262678]  ip6gre_tunnel_xmit+0x17e/0x3c7 [ip6_gre]
[ 1914.273831]  dev_hard_start_xmit+0x8d/0x1f0
[ 1914.283061]  sch_direct_xmit+0xfa/0x230
[ 1914.291521]  __qdisc_run+0x154/0x4b0
[ 1914.299407]  net_tx_action+0x10e/0x1f0
[ 1914.307678]  __do_softirq+0xca/0x297
[ 1914.315567]  irq_exit+0x96/0xa0
[ 1914.322494]  smp_apic_timer_interrupt+0x68/0x130
[ 1914.332683]  apic_timer_interrupt+0xf/0x20
[ 1914.341721]  </IRQ>

Fixes: a68886a69180 ("net/ipv6: Make from in rt6_info rcu protected")
Signed-off-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 0086acc16f3c..b6a97115a906 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2336,6 +2336,10 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
 
 		rcu_read_lock();
 		from = rcu_dereference(rt6->from);
+		if (!from) {
+			rcu_read_unlock();
+			return;
+		}
 		nrt6 = ip6_rt_cache_alloc(from, daddr, saddr);
 		if (nrt6) {
 			rt6_do_update_pmtu(nrt6, mtu);
-- 
2.20.1


From f82664086eb069e1cc762f7c778924d28a9c6e94 Mon Sep 17 00:00:00 2001
From: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Date: Mon, 1 Apr 2019 19:36:33 -0700
Subject: [PATCH 37/43] nfp: flower: replace CFI with vlan present

[ Upstream commit f7ee799a51ddbcc205ef615fe424fb5084e9e0aa ]

Replace vlan CFI bit with a vlan present bit that indicates the
presence of a vlan tag. Previously the driver incorrectly assumed
that an vlan id of 0 is not matchable, therefore we indicate vlan
presence with a vlan present bit.

Fixes: 5571e8c9f241 ("nfp: extend flower matching capabilities")
Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Signed-off-by: Louis Peens <louis.peens@netronome.com>
---
 drivers/net/ethernet/netronome/nfp/flower/cmsg.h  |  2 +-
 drivers/net/ethernet/netronome/nfp/flower/match.c | 14 ++++++--------
 2 files changed, 7 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
index 15f41cfef9f1..bf06458288f3 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
@@ -26,7 +26,7 @@
 #define NFP_FLOWER_LAYER2_GENEVE_OP	BIT(6)
 
 #define NFP_FLOWER_MASK_VLAN_PRIO	GENMASK(15, 13)
-#define NFP_FLOWER_MASK_VLAN_CFI	BIT(12)
+#define NFP_FLOWER_MASK_VLAN_PRESENT	BIT(12)
 #define NFP_FLOWER_MASK_VLAN_VID	GENMASK(11, 0)
 
 #define NFP_FLOWER_MASK_MPLS_LB		GENMASK(31, 12)
diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c
index cdf75595f627..571cc8ced33e 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/match.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/match.c
@@ -26,14 +26,12 @@ nfp_flower_compile_meta_tci(struct nfp_flower_meta_tci *frame,
 						      FLOW_DISSECTOR_KEY_VLAN,
 						      target);
 		/* Populate the tci field. */
-		if (flow_vlan->vlan_id || flow_vlan->vlan_priority) {
-			tmp_tci = FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO,
-					     flow_vlan->vlan_priority) |
-				  FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID,
-					     flow_vlan->vlan_id) |
-				  NFP_FLOWER_MASK_VLAN_CFI;
-			frame->tci = cpu_to_be16(tmp_tci);
-		}
+		tmp_tci = NFP_FLOWER_MASK_VLAN_PRESENT;
+		tmp_tci |= FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO,
+				      flow_vlan->vlan_priority) |
+			   FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID,
+				      flow_vlan->vlan_id);
+		frame->tci = cpu_to_be16(tmp_tci);
 	}
 }
 
-- 
2.20.1


From 15a4d52fcf6b27bf3e3a2464de6d94fc6c6cf4ca Mon Sep 17 00:00:00 2001
From: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Date: Mon, 1 Apr 2019 19:36:34 -0700
Subject: [PATCH 38/43] nfp: flower: remove vlan CFI bit from push vlan action

[ Upstream commit 42cd5484a22f1a1b947e21e2af65fa7dab09d017 ]

We no longer set CFI when pushing vlan tags, therefore we remove
the CFI bit from push vlan.

Fixes: 1a1e586f54bf ("nfp: add basic action capabilities to flower offloads")
Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Signed-off-by: Louis Peens <louis.peens@netronome.com>
---
 drivers/net/ethernet/netronome/nfp/flower/action.c | 3 +--
 drivers/net/ethernet/netronome/nfp/flower/cmsg.h   | 1 -
 2 files changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c
index 8d54b36afee8..2bbc5b8f92c2 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/action.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/action.c
@@ -49,8 +49,7 @@ nfp_fl_push_vlan(struct nfp_fl_push_vlan *push_vlan,
 
 	tmp_push_vlan_tci =
 		FIELD_PREP(NFP_FL_PUSH_VLAN_PRIO, tcf_vlan_push_prio(action)) |
-		FIELD_PREP(NFP_FL_PUSH_VLAN_VID, tcf_vlan_push_vid(action)) |
-		NFP_FL_PUSH_VLAN_CFI;
+		FIELD_PREP(NFP_FL_PUSH_VLAN_VID, tcf_vlan_push_vid(action));
 	push_vlan->vlan_tci = cpu_to_be16(tmp_push_vlan_tci);
 }
 
diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
index bf06458288f3..ab07d76b4186 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
@@ -82,7 +82,6 @@
 #define NFP_FL_OUT_FLAGS_TYPE_IDX	GENMASK(2, 0)
 
 #define NFP_FL_PUSH_VLAN_PRIO		GENMASK(15, 13)
-#define NFP_FL_PUSH_VLAN_CFI		BIT(12)
 #define NFP_FL_PUSH_VLAN_VID		GENMASK(11, 0)
 
 #define IPV6_FLOW_LABEL_MASK		cpu_to_be32(0x000fffff)
-- 
2.20.1


From 951291fd7188999538a1e2ccf16e3a3809eeeb71 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
Date: Thu, 4 Apr 2019 15:01:33 +0200
Subject: [PATCH 39/43] sch_cake: Use tc_skb_protocol() helper for getting
 packet protocol
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit b2100cc56fca8c51d28aa42a9f1fbcb2cf351996 ]

We shouldn't be using skb->protocol directly as that will miss cases with
hardware-accelerated VLAN tags. Use the helper instead to get the right
protocol number.

Reported-by: Kevin Darbyshire-Bryant <kevin@darbyshire-bryant.me.uk>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
---
 net/sched/sch_cake.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 73940293700d..c55fd5c932d4 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -1526,7 +1526,7 @@ static u8 cake_handle_diffserv(struct sk_buff *skb, u16 wash)
 {
 	u8 dscp;
 
-	switch (skb->protocol) {
+	switch (tc_skb_protocol(skb)) {
 	case htons(ETH_P_IP):
 		dscp = ipv4_get_dsfield(ip_hdr(skb)) >> 2;
 		if (wash && dscp)
-- 
2.20.1


From ad64e6252daf663c57ffba0d00c157c5141da34d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
Date: Thu, 4 Apr 2019 15:01:33 +0200
Subject: [PATCH 40/43] sch_cake: Make sure we can write the IP header before
 changing DSCP bits
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit c87b4ecdbe8db27867a7b7f840291cd843406bd7 ]

There is not actually any guarantee that the IP headers are valid before we
access the DSCP bits of the packets. Fix this using the same approach taken
in sch_dsmark.

Reported-by: Kevin Darbyshire-Bryant <kevin@darbyshire-bryant.me.uk>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
---
 net/sched/sch_cake.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index c55fd5c932d4..9a1b0a93534d 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -1524,16 +1524,27 @@ static void cake_wash_diffserv(struct sk_buff *skb)
 
 static u8 cake_handle_diffserv(struct sk_buff *skb, u16 wash)
 {
+	int wlen = skb_network_offset(skb);
 	u8 dscp;
 
 	switch (tc_skb_protocol(skb)) {
 	case htons(ETH_P_IP):
+		wlen += sizeof(struct iphdr);
+		if (!pskb_may_pull(skb, wlen) ||
+		    skb_try_make_writable(skb, wlen))
+			return 0;
+
 		dscp = ipv4_get_dsfield(ip_hdr(skb)) >> 2;
 		if (wash && dscp)
 			ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, 0);
 		return dscp;
 
 	case htons(ETH_P_IPV6):
+		wlen += sizeof(struct ipv6hdr);
+		if (!pskb_may_pull(skb, wlen) ||
+		    skb_try_make_writable(skb, wlen))
+			return 0;
+
 		dscp = ipv6_get_dsfield(ipv6_hdr(skb)) >> 2;
 		if (wash && dscp)
 			ipv6_change_dsfield(ipv6_hdr(skb), INET_ECN_MASK, 0);
-- 
2.20.1


From 39ac3987b49726bf01ba1d6613b7ff34519bd6d8 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 3 Apr 2019 10:12:48 +0300
Subject: [PATCH 41/43] NFC: nci: Add some bounds checking in
 nci_hci_cmd_received()

[ Upstream commit d7ee81ad09f072eab1681877fc71ec05f9c1ae92 ]

This is similar to commit 674d9de02aa7 ("NFC: Fix possible memory
corruption when handling SHDLC I-Frame commands").

I'm not totally sure, but I think that commit description may have
overstated the danger.  I was under the impression that this data came
from the firmware?  If you can't trust your networking firmware, then
you're already in trouble.

Anyway, these days we add bounds checking where ever we can and we call
it kernel hardening.  Better safe than sorry.

Fixes: 11f54f228643 ("NFC: nci: Add HCI over NCI protocol support")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
---
 net/nfc/nci/hci.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c
index ddfc52ac1f9b..c0d323b58e73 100644
--- a/net/nfc/nci/hci.c
+++ b/net/nfc/nci/hci.c
@@ -312,6 +312,10 @@ static void nci_hci_cmd_received(struct nci_dev *ndev, u8 pipe,
 		create_info = (struct nci_hci_create_pipe_resp *)skb->data;
 		dest_gate = create_info->dest_gate;
 		new_pipe = create_info->pipe;
+		if (new_pipe >= NCI_HCI_MAX_PIPES) {
+			status = NCI_HCI_ANY_E_NOK;
+			goto exit;
+		}
 
 		/* Save the new created pipe and bind with local gate,
 		 * the description for skb->data[3] is destination gate id
@@ -336,6 +340,10 @@ static void nci_hci_cmd_received(struct nci_dev *ndev, u8 pipe,
 			goto exit;
 		}
 		delete_info = (struct nci_hci_delete_pipe_noti *)skb->data;
+		if (delete_info->pipe >= NCI_HCI_MAX_PIPES) {
+			status = NCI_HCI_ANY_E_NOK;
+			goto exit;
+		}
 
 		ndev->hci_dev->pipes[delete_info->pipe].gate =
 						NCI_HCI_INVALID_GATE;
-- 
2.20.1


From a955ab46168f68a924f2a4c793e68ec4ee3b0b16 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 3 Apr 2019 10:13:51 +0300
Subject: [PATCH 42/43] nfc: nci: Potential off by one in ->pipes[] array

[ Upstream commit 6491d698396fd5da4941980a35ca7c162a672016 ]

This is similar to commit e285d5bfb7e9 ("NFC: Fix the number of pipes")
where we changed NFC_HCI_MAX_PIPES from 127 to 128.

As the comment next to the define explains, the pipe identifier is 7
bits long.  The highest possible pipe is 127, but the number of possible
pipes is 128.  As the code is now, then there is potential for an
out of bounds array access:

    net/nfc/nci/hci.c:297 nci_hci_cmd_received() warn: array off by one?
    'ndev->hci_dev->pipes[pipe]' '0-127 == 127'

Fixes: 11f54f228643 ("NFC: nci: Add HCI over NCI protocol support")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
---
 include/net/nfc/nci_core.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h
index 87499b6b35d6..df5c69db68af 100644
--- a/include/net/nfc/nci_core.h
+++ b/include/net/nfc/nci_core.h
@@ -166,7 +166,7 @@ struct nci_conn_info {
  * According to specification 102 622 chapter 4.4 Pipes,
  * the pipe identifier is 7 bits long.
  */
-#define NCI_HCI_MAX_PIPES          127
+#define NCI_HCI_MAX_PIPES          128
 
 struct nci_hci_gate {
 	u8 gate;
-- 
2.20.1


From 0ce66040ef423a83641d1e6fd44e9038013a94df Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
Date: Fri, 5 Apr 2019 15:01:59 +0200
Subject: [PATCH 43/43] sch_cake: Simplify logic in cake_select_tin()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 4976e3c683f328bc6f2edef555a4ffee6524486f ]

The logic in cake_select_tin() was getting a bit hairy, and it turns out we
can simplify it quite a bit. This also allows us to get rid of one of the
two diffserv parsing functions, which has the added benefit that
already-zeroed DSCP fields won't get re-written.

Suggested-by: Kevin Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
---
 net/sched/sch_cake.c | 44 ++++++++++++++++----------------------------
 1 file changed, 16 insertions(+), 28 deletions(-)

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 9a1b0a93534d..7b5ce1343474 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -1508,20 +1508,6 @@ static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free)
 	return idx + (tin << 16);
 }
 
-static void cake_wash_diffserv(struct sk_buff *skb)
-{
-	switch (skb->protocol) {
-	case htons(ETH_P_IP):
-		ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, 0);
-		break;
-	case htons(ETH_P_IPV6):
-		ipv6_change_dsfield(ipv6_hdr(skb), INET_ECN_MASK, 0);
-		break;
-	default:
-		break;
-	}
-}
-
 static u8 cake_handle_diffserv(struct sk_buff *skb, u16 wash)
 {
 	int wlen = skb_network_offset(skb);
@@ -1564,25 +1550,27 @@ static struct cake_tin_data *cake_select_tin(struct Qdisc *sch,
 {
 	struct cake_sched_data *q = qdisc_priv(sch);
 	u32 tin;
+	u8 dscp;
 
-	if (TC_H_MAJ(skb->priority) == sch->handle &&
-	    TC_H_MIN(skb->priority) > 0 &&
-	    TC_H_MIN(skb->priority) <= q->tin_cnt) {
+	/* Tin selection: Default to diffserv-based selection, allow overriding
+	 * using firewall marks or skb->priority.
+	 */
+	dscp = cake_handle_diffserv(skb,
+				    q->rate_flags & CAKE_FLAG_WASH);
+
+	if (q->tin_mode == CAKE_DIFFSERV_BESTEFFORT)
+		tin = 0;
+
+	else if (TC_H_MAJ(skb->priority) == sch->handle &&
+		 TC_H_MIN(skb->priority) > 0 &&
+		 TC_H_MIN(skb->priority) <= q->tin_cnt)
 		tin = q->tin_order[TC_H_MIN(skb->priority) - 1];
 
-		if (q->rate_flags & CAKE_FLAG_WASH)
-			cake_wash_diffserv(skb);
-	} else if (q->tin_mode != CAKE_DIFFSERV_BESTEFFORT) {
-		/* extract the Diffserv Precedence field, if it exists */
-		/* and clear DSCP bits if washing */
-		tin = q->tin_index[cake_handle_diffserv(skb,
-				q->rate_flags & CAKE_FLAG_WASH)];
+	else {
+		tin = q->tin_index[dscp];
+
 		if (unlikely(tin >= q->tin_cnt))
 			tin = 0;
-	} else {
-		tin = 0;
-		if (q->rate_flags & CAKE_FLAG_WASH)
-			cake_wash_diffserv(skb);
 	}
 
 	return &q->tins[tin];
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Thu, Apr 18, 2019 at 03:53:40PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.19 and
> v5.0 -stable, respectively.

Thanks for these, all now queued up.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 105 bytes --]


Please queue up the following neworking bug fixes for
v4.19 and v5.0 -stable, respectively.

Thank you!

[-- Attachment #2: net_419.mbox --]
[-- Type: Application/Octet-Stream, Size: 52424 bytes --]

From bf9dd7602af2fbb6415e9ab1cfcef19248be09ff Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 24 Apr 2019 08:04:05 -0700
Subject: [PATCH 01/18] ipv4: add sanity checks in ipv4_link_failure()

[ Upstream commit 20ff83f10f113c88d0bb74589389b05250994c16 ]

Before calling __ip_options_compile(), we need to ensure the network
header is a an IPv4 one, and that it is already pulled in skb->head.

RAW sockets going through a tunnel can end up calling ipv4_link_failure()
with total garbage in the skb, or arbitrary lengthes.

syzbot report :

BUG: KASAN: stack-out-of-bounds in memcpy include/linux/string.h:355 [inline]
BUG: KASAN: stack-out-of-bounds in __ip_options_echo+0x294/0x1120 net/ipv4/ip_options.c:123
Write of size 69 at addr ffff888096abf068 by task syz-executor.4/9204

CPU: 0 PID: 9204 Comm: syz-executor.4 Not tainted 5.1.0-rc5+ #77
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 print_address_description.cold+0x7c/0x20d mm/kasan/report.c:187
 kasan_report.cold+0x1b/0x40 mm/kasan/report.c:317
 check_memory_region_inline mm/kasan/generic.c:185 [inline]
 check_memory_region+0x123/0x190 mm/kasan/generic.c:191
 memcpy+0x38/0x50 mm/kasan/common.c:133
 memcpy include/linux/string.h:355 [inline]
 __ip_options_echo+0x294/0x1120 net/ipv4/ip_options.c:123
 __icmp_send+0x725/0x1400 net/ipv4/icmp.c:695
 ipv4_link_failure+0x29f/0x550 net/ipv4/route.c:1204
 dst_link_failure include/net/dst.h:427 [inline]
 vti6_xmit net/ipv6/ip6_vti.c:514 [inline]
 vti6_tnl_xmit+0x10d4/0x1c0c net/ipv6/ip6_vti.c:553
 __netdev_start_xmit include/linux/netdevice.h:4414 [inline]
 netdev_start_xmit include/linux/netdevice.h:4423 [inline]
 xmit_one net/core/dev.c:3292 [inline]
 dev_hard_start_xmit+0x1b2/0x980 net/core/dev.c:3308
 __dev_queue_xmit+0x271d/0x3060 net/core/dev.c:3878
 dev_queue_xmit+0x18/0x20 net/core/dev.c:3911
 neigh_direct_output+0x16/0x20 net/core/neighbour.c:1527
 neigh_output include/net/neighbour.h:508 [inline]
 ip_finish_output2+0x949/0x1740 net/ipv4/ip_output.c:229
 ip_finish_output+0x73c/0xd50 net/ipv4/ip_output.c:317
 NF_HOOK_COND include/linux/netfilter.h:278 [inline]
 ip_output+0x21f/0x670 net/ipv4/ip_output.c:405
 dst_output include/net/dst.h:444 [inline]
 NF_HOOK include/linux/netfilter.h:289 [inline]
 raw_send_hdrinc net/ipv4/raw.c:432 [inline]
 raw_sendmsg+0x1d2b/0x2f20 net/ipv4/raw.c:663
 inet_sendmsg+0x147/0x5d0 net/ipv4/af_inet.c:798
 sock_sendmsg_nosec net/socket.c:651 [inline]
 sock_sendmsg+0xdd/0x130 net/socket.c:661
 sock_write_iter+0x27c/0x3e0 net/socket.c:988
 call_write_iter include/linux/fs.h:1866 [inline]
 new_sync_write+0x4c7/0x760 fs/read_write.c:474
 __vfs_write+0xe4/0x110 fs/read_write.c:487
 vfs_write+0x20c/0x580 fs/read_write.c:549
 ksys_write+0x14f/0x2d0 fs/read_write.c:599
 __do_sys_write fs/read_write.c:611 [inline]
 __se_sys_write fs/read_write.c:608 [inline]
 __x64_sys_write+0x73/0xb0 fs/read_write.c:608
 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x458c29
Code: ad b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f293b44bc78 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000458c29
RDX: 0000000000000014 RSI: 00000000200002c0 RDI: 0000000000000003
RBP: 000000000073bf00 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00007f293b44c6d4
R13: 00000000004c8623 R14: 00000000004ded68 R15: 00000000ffffffff

The buggy address belongs to the page:
page:ffffea00025aafc0 count:0 mapcount:0 mapping:0000000000000000 index:0x0
flags: 0x1fffc0000000000()
raw: 01fffc0000000000 0000000000000000 ffffffff025a0101 0000000000000000
raw: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff888096abef80: 00 00 00 f2 f2 f2 f2 f2 00 00 00 00 00 00 00 f2
 ffff888096abf000: f2 f2 f2 f2 00 00 00 00 00 00 00 00 00 00 00 00
>ffff888096abf080: 00 00 f3 f3 f3 f3 00 00 00 00 00 00 00 00 00 00
                         ^
 ffff888096abf100: 00 00 00 00 f1 f1 f1 f1 00 00 f3 f3 00 00 00 00
 ffff888096abf180: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00

Fixes: ed0de45a1008 ("ipv4: recompile ip options in ipv4_link_failure")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Stephen Suryaputra <ssuryaextr@gmail.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 32 +++++++++++++++++++++++---------
 1 file changed, 23 insertions(+), 9 deletions(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 98c81c21b753..8bacbcd2db90 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1185,25 +1185,39 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
 	return dst;
 }
 
-static void ipv4_link_failure(struct sk_buff *skb)
+static void ipv4_send_dest_unreach(struct sk_buff *skb)
 {
 	struct ip_options opt;
-	struct rtable *rt;
 	int res;
 
 	/* Recompile ip options since IPCB may not be valid anymore.
+	 * Also check we have a reasonable ipv4 header.
 	 */
-	memset(&opt, 0, sizeof(opt));
-	opt.optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr);
+	if (!pskb_network_may_pull(skb, sizeof(struct iphdr)) ||
+	    ip_hdr(skb)->version != 4 || ip_hdr(skb)->ihl < 5)
+		return;
 
-	rcu_read_lock();
-	res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL);
-	rcu_read_unlock();
+	memset(&opt, 0, sizeof(opt));
+	if (ip_hdr(skb)->ihl > 5) {
+		if (!pskb_network_may_pull(skb, ip_hdr(skb)->ihl * 4))
+			return;
+		opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr);
 
-	if (res)
-		return;
+		rcu_read_lock();
+		res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL);
+		rcu_read_unlock();
 
+		if (res)
+			return;
+	}
 	__icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0, &opt);
+}
+
+static void ipv4_link_failure(struct sk_buff *skb)
+{
+	struct rtable *rt;
+
+	ipv4_send_dest_unreach(skb);
 
 	rt = skb_rtable(skb);
 	if (rt)
-- 
2.20.1


From afdc20fc0e20a5d43367f3d9e403bbb5a1a8be98 Mon Sep 17 00:00:00 2001
From: ZhangXiaoxu <zhangxiaoxu5@huawei.com>
Date: Tue, 16 Apr 2019 09:47:24 +0800
Subject: [PATCH 02/18] ipv4: set the tcp_min_rtt_wlen range from 0 to one day

[ Upstream commit 19fad20d15a6494f47f85d869f00b11343ee5c78 ]

There is a UBSAN report as below:
UBSAN: Undefined behaviour in net/ipv4/tcp_input.c:2877:56
signed integer overflow:
2147483647 * 1000 cannot be represented in type 'int'
CPU: 3 PID: 0 Comm: swapper/3 Not tainted 5.1.0-rc4-00058-g582549e #1
Call Trace:
 <IRQ>
 dump_stack+0x8c/0xba
 ubsan_epilogue+0x11/0x60
 handle_overflow+0x12d/0x170
 ? ttwu_do_wakeup+0x21/0x320
 __ubsan_handle_mul_overflow+0x12/0x20
 tcp_ack_update_rtt+0x76c/0x780
 tcp_clean_rtx_queue+0x499/0x14d0
 tcp_ack+0x69e/0x1240
 ? __wake_up_sync_key+0x2c/0x50
 ? update_group_capacity+0x50/0x680
 tcp_rcv_established+0x4e2/0xe10
 tcp_v4_do_rcv+0x22b/0x420
 tcp_v4_rcv+0xfe8/0x1190
 ip_protocol_deliver_rcu+0x36/0x180
 ip_local_deliver+0x15b/0x1a0
 ip_rcv+0xac/0xd0
 __netif_receive_skb_one_core+0x7f/0xb0
 __netif_receive_skb+0x33/0xc0
 netif_receive_skb_internal+0x84/0x1c0
 napi_gro_receive+0x2a0/0x300
 receive_buf+0x3d4/0x2350
 ? detach_buf_split+0x159/0x390
 virtnet_poll+0x198/0x840
 ? reweight_entity+0x243/0x4b0
 net_rx_action+0x25c/0x770
 __do_softirq+0x19b/0x66d
 irq_exit+0x1eb/0x230
 do_IRQ+0x7a/0x150
 common_interrupt+0xf/0xf
 </IRQ>

It can be reproduced by:
  echo 2147483647 > /proc/sys/net/ipv4/tcp_min_rtt_wlen

Fixes: f672258391b42 ("tcp: track min RTT using windowed min-filter")
Signed-off-by: ZhangXiaoxu <zhangxiaoxu5@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt | 1 +
 net/ipv4/sysctl_net_ipv4.c             | 5 ++++-
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 960de8fe3f40..2c31208528d5 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -410,6 +410,7 @@ tcp_min_rtt_wlen - INTEGER
 	minimum RTT when it is moved to a longer path (e.g., due to traffic
 	engineering). A longer window makes the filter more resistant to RTT
 	inflations such as transient congestion. The unit is seconds.
+	Possible values: 0 - 86400 (1 day)
 	Default: 300
 
 tcp_moderate_rcvbuf - BOOLEAN
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 891ed2f91467..ce64453d337d 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -49,6 +49,7 @@ static int ip_ping_group_range_min[] = { 0, 0 };
 static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
 static int comp_sack_nr_max = 255;
 static u32 u32_max_div_HZ = UINT_MAX / HZ;
+static int one_day_secs = 24 * 3600;
 
 /* obsolete */
 static int sysctl_tcp_low_latency __read_mostly;
@@ -1140,7 +1141,9 @@ static struct ctl_table ipv4_net_table[] = {
 		.data		= &init_net.ipv4.sysctl_tcp_min_rtt_wlen,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one_day_secs
 	},
 	{
 		.procname	= "tcp_autocorking",
-- 
2.20.1


From bb62bb6eefc941bb002a074002300d59acff6650 Mon Sep 17 00:00:00 2001
From: Amit Cohen <amitc@mellanox.com>
Date: Thu, 18 Apr 2019 07:14:16 +0000
Subject: [PATCH 03/18] mlxsw: spectrum: Fix autoneg status in ethtool

[ Upstream commit 151f0dddbbfe4c35c9c5b64873115aafd436af9d ]

If link is down and autoneg is set to on/off, the status in ethtool does
not change.

The reason is when the link is down the function returns with zero
before changing autoneg value.

Move the checking of link state (up/down) to be performed after setting
autoneg value, in order to be sure that autoneg will change in any case.

Fixes: 56ade8fe3fe1 ("mlxsw: spectrum: Add initial support for Spectrum ASIC")
Signed-off-by: Amit Cohen <amitc@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index f9bef030ee05..b379d4219483 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -2504,11 +2504,11 @@ mlxsw_sp_port_set_link_ksettings(struct net_device *dev,
 	if (err)
 		return err;
 
+	mlxsw_sp_port->link.autoneg = autoneg;
+
 	if (!netif_running(dev))
 		return 0;
 
-	mlxsw_sp_port->link.autoneg = autoneg;
-
 	mlxsw_sp_port_admin_status_set(mlxsw_sp_port, false);
 	mlxsw_sp_port_admin_status_set(mlxsw_sp_port, true);
 
-- 
2.20.1


From 2e10f90cdb222465fbaa3d8e227fe63b7e90b3e3 Mon Sep 17 00:00:00 2001
From: Erez Alfasi <ereza@mellanox.com>
Date: Thu, 11 Apr 2019 10:41:03 +0300
Subject: [PATCH 04/18] net/mlx5e: ethtool, Remove unsupported SFP EEPROM high
 pages query

[ Upstream commit ace329f4ab3ba434be2adf618073c752d083b524 ]

Querying EEPROM high pages data for SFP module is currently
not supported by our driver and yet queried, resulting in
invalid FW queries.

Set the EEPROM ethtool data length to 256 for SFP module will
limit the reading for page 0 only and prevent invalid FW queries.

Fixes: bb64143eee8c ("net/mlx5e: Add ethtool support for dump module EEPROM")
Signed-off-by: Erez Alfasi <ereza@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/port.c       | 4 ----
 2 files changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 5e5423076b03..9ca4f88d7cf6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1317,7 +1317,7 @@ static int mlx5e_get_module_info(struct net_device *netdev,
 		break;
 	case MLX5_MODULE_ID_SFP:
 		modinfo->type       = ETH_MODULE_SFF_8472;
-		modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN;
+		modinfo->eeprom_len = MLX5_EEPROM_PAGE_LENGTH;
 		break;
 	default:
 		netdev_err(priv->netdev, "%s: cable type not recognized:0x%x\n",
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index 31a9cbd85689..09b6b1bfbfa8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -404,10 +404,6 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev,
 		size -= offset + size - MLX5_EEPROM_PAGE_LENGTH;
 
 	i2c_addr = MLX5_I2C_ADDR_LOW;
-	if (offset >= MLX5_EEPROM_PAGE_LENGTH) {
-		i2c_addr = MLX5_I2C_ADDR_HIGH;
-		offset -= MLX5_EEPROM_PAGE_LENGTH;
-	}
 
 	MLX5_SET(mcia_reg, in, l, 0);
 	MLX5_SET(mcia_reg, in, module, module_num);
-- 
2.20.1


From 1d5428cd6a974d99ad0a63902a782b3997ace129 Mon Sep 17 00:00:00 2001
From: Zhu Yanjun <yanjun.zhu@oracle.com>
Date: Wed, 24 Apr 2019 02:56:42 -0400
Subject: [PATCH 05/18] net: rds: exchange of 8K and 1M pool

[ Upstream commit 4b9fc7146249a6e0e3175d0acc033fdcd2bfcb17 ]

Before the commit 490ea5967b0d ("RDS: IB: move FMR code to its own file"),
when the dirty_count is greater than 9/10 of max_items of 8K pool,
1M pool is used, Vice versa. After the commit 490ea5967b0d ("RDS: IB: move
FMR code to its own file"), the above is removed. When we make the
following tests.

Server:
  rds-stress -r 1.1.1.16 -D 1M

Client:
  rds-stress -r 1.1.1.14 -s 1.1.1.16 -D 1M

The following will appear.
"
connecting to 1.1.1.16:4000
negotiated options, tasks will start in 2 seconds
Starting up..header from 1.1.1.166:4001 to id 4001 bogus
..
tsks  tx/s  rx/s tx+rx K/s  mbi K/s  mbo K/s tx us/c  rtt us
cpu %
   1    0    0     0.00     0.00     0.00    0.00 0.00 -1.00
   1    0    0     0.00     0.00     0.00    0.00 0.00 -1.00
   1    0    0     0.00     0.00     0.00    0.00 0.00 -1.00
   1    0    0     0.00     0.00     0.00    0.00 0.00 -1.00
   1    0    0     0.00     0.00     0.00    0.00 0.00 -1.00
...
"
So this exchange between 8K and 1M pool is added back.

Fixes: commit 490ea5967b0d ("RDS: IB: move FMR code to its own file")
Signed-off-by: Zhu Yanjun <yanjun.zhu@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/ib_fmr.c  | 11 +++++++++++
 net/rds/ib_rdma.c |  3 ---
 2 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/net/rds/ib_fmr.c b/net/rds/ib_fmr.c
index e0f70c4051b6..01e764f8f224 100644
--- a/net/rds/ib_fmr.c
+++ b/net/rds/ib_fmr.c
@@ -44,6 +44,17 @@ struct rds_ib_mr *rds_ib_alloc_fmr(struct rds_ib_device *rds_ibdev, int npages)
 	else
 		pool = rds_ibdev->mr_1m_pool;
 
+	if (atomic_read(&pool->dirty_count) >= pool->max_items / 10)
+		queue_delayed_work(rds_ib_mr_wq, &pool->flush_worker, 10);
+
+	/* Switch pools if one of the pool is reaching upper limit */
+	if (atomic_read(&pool->dirty_count) >=  pool->max_items * 9 / 10) {
+		if (pool->pool_type == RDS_IB_MR_8K_POOL)
+			pool = rds_ibdev->mr_1m_pool;
+		else
+			pool = rds_ibdev->mr_8k_pool;
+	}
+
 	ibmr = rds_ib_try_reuse_ibmr(pool);
 	if (ibmr)
 		return ibmr;
diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c
index 63c8d107adcf..d664e9ade74d 100644
--- a/net/rds/ib_rdma.c
+++ b/net/rds/ib_rdma.c
@@ -454,9 +454,6 @@ struct rds_ib_mr *rds_ib_try_reuse_ibmr(struct rds_ib_mr_pool *pool)
 	struct rds_ib_mr *ibmr = NULL;
 	int iter = 0;
 
-	if (atomic_read(&pool->dirty_count) >= pool->max_items_soft / 10)
-		queue_delayed_work(rds_ib_mr_wq, &pool->flush_worker, 10);
-
 	while (1) {
 		ibmr = rds_ib_reuse_mr(pool);
 		if (ibmr)
-- 
2.20.1


From d0325bb4787ddd7639fa841233c49aec601e3841 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 24 Apr 2019 05:35:00 -0700
Subject: [PATCH 06/18] net/rose: fix unbound loop in rose_loopback_timer()

[ Upstream commit 0453c682459583910d611a96de928f4442205493 ]

This patch adds a limit on the number of skbs that fuzzers can queue
into loopback_queue. 1000 packets for rose loopback seems more than enough.

Then, since we now have multiple cpus in most linux hosts,
we also need to limit the number of skbs rose_loopback_timer()
can dequeue at each round.

rose_loopback_queue() can be drop-monitor friendly, calling
consume_skb() or kfree_skb() appropriately.

Finally, use mod_timer() instead of del_timer() + add_timer()

syzbot report was :

rcu: INFO: rcu_preempt self-detected stall on CPU
rcu:    0-...!: (10499 ticks this GP) idle=536/1/0x4000000000000002 softirq=103291/103291 fqs=34
rcu:     (t=10500 jiffies g=140321 q=323)
rcu: rcu_preempt kthread starved for 10426 jiffies! g140321 f0x0 RCU_GP_WAIT_FQS(5) ->state=0x402 ->cpu=1
rcu: RCU grace-period kthread stack dump:
rcu_preempt     I29168    10      2 0x80000000
Call Trace:
 context_switch kernel/sched/core.c:2877 [inline]
 __schedule+0x813/0x1cc0 kernel/sched/core.c:3518
 schedule+0x92/0x180 kernel/sched/core.c:3562
 schedule_timeout+0x4db/0xfd0 kernel/time/timer.c:1803
 rcu_gp_fqs_loop kernel/rcu/tree.c:1971 [inline]
 rcu_gp_kthread+0x962/0x17b0 kernel/rcu/tree.c:2128
 kthread+0x357/0x430 kernel/kthread.c:253
 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:352
NMI backtrace for cpu 0
CPU: 0 PID: 7632 Comm: kworker/0:4 Not tainted 5.1.0-rc5+ #172
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Workqueue: events iterate_cleanup_work
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 nmi_cpu_backtrace.cold+0x63/0xa4 lib/nmi_backtrace.c:101
 nmi_trigger_cpumask_backtrace+0x1be/0x236 lib/nmi_backtrace.c:62
 arch_trigger_cpumask_backtrace+0x14/0x20 arch/x86/kernel/apic/hw_nmi.c:38
 trigger_single_cpu_backtrace include/linux/nmi.h:164 [inline]
 rcu_dump_cpu_stacks+0x183/0x1cf kernel/rcu/tree.c:1223
 print_cpu_stall kernel/rcu/tree.c:1360 [inline]
 check_cpu_stall kernel/rcu/tree.c:1434 [inline]
 rcu_pending kernel/rcu/tree.c:3103 [inline]
 rcu_sched_clock_irq.cold+0x500/0xa4a kernel/rcu/tree.c:2544
 update_process_times+0x32/0x80 kernel/time/timer.c:1635
 tick_sched_handle+0xa2/0x190 kernel/time/tick-sched.c:161
 tick_sched_timer+0x47/0x130 kernel/time/tick-sched.c:1271
 __run_hrtimer kernel/time/hrtimer.c:1389 [inline]
 __hrtimer_run_queues+0x33e/0xde0 kernel/time/hrtimer.c:1451
 hrtimer_interrupt+0x314/0x770 kernel/time/hrtimer.c:1509
 local_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1035 [inline]
 smp_apic_timer_interrupt+0x120/0x570 arch/x86/kernel/apic/apic.c:1060
 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:807
RIP: 0010:__sanitizer_cov_trace_pc+0x0/0x50 kernel/kcov.c:95
Code: 89 25 b4 6e ec 08 41 bc f4 ff ff ff e8 cd 5d ea ff 48 c7 05 9e 6e ec 08 00 00 00 00 e9 a4 e9 ff ff 90 90 90 90 90 90 90 90 90 <55> 48 89 e5 48 8b 75 08 65 48 8b 04 25 00 ee 01 00 65 8b 15 c8 60
RSP: 0018:ffff8880ae807ce0 EFLAGS: 00000286 ORIG_RAX: ffffffffffffff13
RAX: ffff88806fd40640 RBX: dffffc0000000000 RCX: ffffffff863fbc56
RDX: 0000000000000100 RSI: ffffffff863fbc1d RDI: ffff88808cf94228
RBP: ffff8880ae807d10 R08: ffff88806fd40640 R09: ffffed1015d00f8b
R10: ffffed1015d00f8a R11: 0000000000000003 R12: ffff88808cf941c0
R13: 00000000fffff034 R14: ffff8882166cd840 R15: 0000000000000000
 rose_loopback_timer+0x30d/0x3f0 net/rose/rose_loopback.c:91
 call_timer_fn+0x190/0x720 kernel/time/timer.c:1325
 expire_timers kernel/time/timer.c:1362 [inline]
 __run_timers kernel/time/timer.c:1681 [inline]
 __run_timers kernel/time/timer.c:1649 [inline]
 run_timer_softirq+0x652/0x1700 kernel/time/timer.c:1694
 __do_softirq+0x266/0x95a kernel/softirq.c:293
 do_softirq_own_stack+0x2a/0x40 arch/x86/entry/entry_64.S:1027

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rose/rose_loopback.c | 27 ++++++++++++++++-----------
 1 file changed, 16 insertions(+), 11 deletions(-)

diff --git a/net/rose/rose_loopback.c b/net/rose/rose_loopback.c
index 7af4f99c4a93..094a6621f8e8 100644
--- a/net/rose/rose_loopback.c
+++ b/net/rose/rose_loopback.c
@@ -16,6 +16,7 @@
 #include <linux/init.h>
 
 static struct sk_buff_head loopback_queue;
+#define ROSE_LOOPBACK_LIMIT 1000
 static struct timer_list loopback_timer;
 
 static void rose_set_loopback_timer(void);
@@ -35,29 +36,27 @@ static int rose_loopback_running(void)
 
 int rose_loopback_queue(struct sk_buff *skb, struct rose_neigh *neigh)
 {
-	struct sk_buff *skbn;
+	struct sk_buff *skbn = NULL;
 
-	skbn = skb_clone(skb, GFP_ATOMIC);
+	if (skb_queue_len(&loopback_queue) < ROSE_LOOPBACK_LIMIT)
+		skbn = skb_clone(skb, GFP_ATOMIC);
 
-	kfree_skb(skb);
-
-	if (skbn != NULL) {
+	if (skbn) {
+		consume_skb(skb);
 		skb_queue_tail(&loopback_queue, skbn);
 
 		if (!rose_loopback_running())
 			rose_set_loopback_timer();
+	} else {
+		kfree_skb(skb);
 	}
 
 	return 1;
 }
 
-
 static void rose_set_loopback_timer(void)
 {
-	del_timer(&loopback_timer);
-
-	loopback_timer.expires  = jiffies + 10;
-	add_timer(&loopback_timer);
+	mod_timer(&loopback_timer, jiffies + 10);
 }
 
 static void rose_loopback_timer(struct timer_list *unused)
@@ -68,8 +67,12 @@ static void rose_loopback_timer(struct timer_list *unused)
 	struct sock *sk;
 	unsigned short frametype;
 	unsigned int lci_i, lci_o;
+	int count;
 
-	while ((skb = skb_dequeue(&loopback_queue)) != NULL) {
+	for (count = 0; count < ROSE_LOOPBACK_LIMIT; count++) {
+		skb = skb_dequeue(&loopback_queue);
+		if (!skb)
+			return;
 		if (skb->len < ROSE_MIN_LEN) {
 			kfree_skb(skb);
 			continue;
@@ -106,6 +109,8 @@ static void rose_loopback_timer(struct timer_list *unused)
 			kfree_skb(skb);
 		}
 	}
+	if (!skb_queue_empty(&loopback_queue))
+		mod_timer(&loopback_timer, jiffies + 1);
 }
 
 void __exit rose_loopback_clear(void)
-- 
2.20.1


From fa7c1b6e4ad7e7047d4c210b6fcd1ee4b2dce003 Mon Sep 17 00:00:00 2001
From: Vinod Koul <vkoul@kernel.org>
Date: Mon, 22 Apr 2019 15:15:32 +0530
Subject: [PATCH 07/18] net: stmmac: move stmmac_check_ether_addr() to driver
 probe

[ Upstream commit b561af36b1841088552464cdc3f6371d92f17710 ]

stmmac_check_ether_addr() checks the MAC address and assigns one in
driver open(). In many cases when we create slave netdevice, the dev
addr is inherited from master but the master dev addr maybe NULL at
that time, so move this call to driver probe so that address is
always valid.

Signed-off-by: Xiaofei Shen <xiaofeis@codeaurora.org>
Tested-by: Xiaofei Shen <xiaofeis@codeaurora.org>
Signed-off-by: Sneh Shah <snehshah@codeaurora.org>
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 886176be818e..62460a5b4ad9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2595,8 +2595,6 @@ static int stmmac_open(struct net_device *dev)
 	u32 chan;
 	int ret;
 
-	stmmac_check_ether_addr(priv);
-
 	if (priv->hw->pcs != STMMAC_PCS_RGMII &&
 	    priv->hw->pcs != STMMAC_PCS_TBI &&
 	    priv->hw->pcs != STMMAC_PCS_RTBI) {
@@ -4296,6 +4294,8 @@ int stmmac_dvr_probe(struct device *device,
 	if (ret)
 		goto error_hw_init;
 
+	stmmac_check_ether_addr(priv);
+
 	/* Configure real RX and TX queues */
 	netif_set_real_num_rx_queues(ndev, priv->plat->rx_queues_to_use);
 	netif_set_real_num_tx_queues(ndev, priv->plat->tx_queues_to_use);
-- 
2.20.1


From 107da02b46087fe5ae0876a51460fa99a1dd625a Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 17 Apr 2019 10:51:19 -0700
Subject: [PATCH 08/18] net/tls: fix refcount adjustment in fallback

[ Upstream commit 9188d5ca454fd665145904267e726e9e8d122f5c ]

Unlike atomic_add(), refcount_add() does not deal well
with a negative argument.  TLS fallback code reallocates
the skb and is very likely to shrink the truesize, leading to:

[  189.513254] WARNING: CPU: 5 PID: 0 at lib/refcount.c:81 refcount_add_not_zero_checked+0x15c/0x180
 Call Trace:
  refcount_add_checked+0x6/0x40
  tls_enc_skb+0xb93/0x13e0 [tls]

Once wmem_allocated count saturates the application can no longer
send data on the socket.  This is similar to Eric's fixes for GSO,
TCP:
commit 7ec318feeed1 ("tcp: gso: avoid refcount_t warning from tcp_gso_segment()")
and UDP:
commit 575b65bc5bff ("udp: avoid refcount_t saturation in __udp_gso_segment()").

Unlike the GSO case, for TLS fallback it's likely that the skb has
shrunk, so the "likely" annotation is the other way around (likely
branch being "sub").

Fixes: e8f69799810c ("net/tls: Add generic NIC offload infrastructure")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_device_fallback.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c
index 450a6dbc5a88..ef8934fd8698 100644
--- a/net/tls/tls_device_fallback.c
+++ b/net/tls/tls_device_fallback.c
@@ -193,6 +193,9 @@ static void update_chksum(struct sk_buff *skb, int headln)
 
 static void complete_skb(struct sk_buff *nskb, struct sk_buff *skb, int headln)
 {
+	struct sock *sk = skb->sk;
+	int delta;
+
 	skb_copy_header(nskb, skb);
 
 	skb_put(nskb, skb->len);
@@ -200,11 +203,15 @@ static void complete_skb(struct sk_buff *nskb, struct sk_buff *skb, int headln)
 	update_chksum(nskb, headln);
 
 	nskb->destructor = skb->destructor;
-	nskb->sk = skb->sk;
+	nskb->sk = sk;
 	skb->destructor = NULL;
 	skb->sk = NULL;
-	refcount_add(nskb->truesize - skb->truesize,
-		     &nskb->sk->sk_wmem_alloc);
+
+	delta = nskb->truesize - skb->truesize;
+	if (likely(delta < 0))
+		WARN_ON_ONCE(refcount_sub_and_test(-delta, &sk->sk_wmem_alloc));
+	else if (delta)
+		refcount_add(delta, &sk->sk_wmem_alloc);
 }
 
 /* This function may be called after the user socket is already
-- 
2.20.1


From f66b220dfd16f62cbfc6d0402ba4c168fa26bb93 Mon Sep 17 00:00:00 2001
From: Su Bao Cheng <baocheng.su@siemens.com>
Date: Thu, 18 Apr 2019 11:14:56 +0200
Subject: [PATCH 09/18] stmmac: pci: Adjust IOT2000 matching

[ Upstream commit e0c1d14a1a3211dccf0540a6703ffbd5d2a75bdb ]

Since there are more IOT2040 variants with identical hardware but
different asset tags, the asset tag matching should be adjusted to
support them.

For the board name "SIMATIC IOT2000", currently there are 2 types of
hardware, IOT2020 and IOT2040. The IOT2020 is identified by its unique
asset tag. Match on it first. If we then match on the board name only,
we will catch all IOT2040 variants. In the future there will be no other
devices with the "SIMATIC IOT2000" DMI board name but different
hardware.

Signed-off-by: Su Bao Cheng <baocheng.su@siemens.com>
Reviewed-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
index d819e8eaba12..cc1e887e47b5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
@@ -159,6 +159,12 @@ static const struct dmi_system_id quark_pci_dmi[] = {
 		},
 		.driver_data = (void *)&galileo_stmmac_dmi_data,
 	},
+	/*
+	 * There are 2 types of SIMATIC IOT2000: IOT20202 and IOT2040.
+	 * The asset tag "6ES7647-0AA00-0YA2" is only for IOT2020 which
+	 * has only one pci network device while other asset tags are
+	 * for IOT2040 which has two.
+	 */
 	{
 		.matches = {
 			DMI_EXACT_MATCH(DMI_BOARD_NAME, "SIMATIC IOT2000"),
@@ -170,8 +176,6 @@ static const struct dmi_system_id quark_pci_dmi[] = {
 	{
 		.matches = {
 			DMI_EXACT_MATCH(DMI_BOARD_NAME, "SIMATIC IOT2000"),
-			DMI_EXACT_MATCH(DMI_BOARD_ASSET_TAG,
-					"6ES7647-0AA00-1YA2"),
 		},
 		.driver_data = (void *)&iot2040_stmmac_dmi_data,
 	},
-- 
2.20.1


From b19f5134d048815d89b5ed7af54350cf820297ec Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Fri, 19 Apr 2019 14:31:00 +0800
Subject: [PATCH 10/18] team: fix possible recursive locking when add slaves

[ Upstream commit 925b0c841e066b488cc3a60272472b2c56300704 ]

If we add a bond device which is already the master of the team interface,
we will hold the team->lock in team_add_slave() first and then request the
lock in team_set_mac_address() again. The functions are called like:

- team_add_slave()
 - team_port_add()
   - team_port_enter()
     - team_modeop_port_enter()
       - __set_port_dev_addr()
         - dev_set_mac_address()
           - bond_set_mac_address()
             - dev_set_mac_address()
  	       - team_set_mac_address

Although team_upper_dev_link() would check the upper devices but it is
called too late. Fix it by adding a checking before processing the slave.

v2: Do not split the string in netdev_err()

Fixes: 3d249d4ca7d0 ("net: introduce ethernet teaming device")
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index e23eaf3f6d03..6c6230b44bcd 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1160,6 +1160,13 @@ static int team_port_add(struct team *team, struct net_device *port_dev,
 		return -EINVAL;
 	}
 
+	if (netdev_has_upper_dev(dev, port_dev)) {
+		NL_SET_ERR_MSG(extack, "Device is already an upper device of the team interface");
+		netdev_err(dev, "Device %s is already an upper device of the team interface\n",
+			   portname);
+		return -EBUSY;
+	}
+
 	if (port_dev->features & NETIF_F_VLAN_CHALLENGED &&
 	    vlan_uses_dev(dev)) {
 		NL_SET_ERR_MSG(extack, "Device is VLAN challenged and team device has VLAN set up");
-- 
2.20.1


From 40739d8d442031e41fdf08975f7ad322b2f46860 Mon Sep 17 00:00:00 2001
From: Jun Xiao <xiaojun2@hisilicon.com>
Date: Tue, 23 Apr 2019 00:48:57 +0800
Subject: [PATCH 11/18] net: hns: Fix WARNING when hns modules installed

Commit dfdf26babc98 upstream

this patch need merge to 4.19.y stable kernel

Fix Conflict:already fixed the confilct dfdf26babc98 with Yonglong Liu

stable candidate:user cannot connect to the internet via hns dev
by default setting without this patch

we have already verified this patch on kunpeng916 platform,
and it works well.

Signed-off-by: Yonglong Liu <liuyonglong@huawei.com>
Signed-off-by: Jun Xiao <xiaojun2@hisilicon.com>
---
 drivers/net/ethernet/hisilicon/hns/hns_enet.c | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index b043370c2685..cc84133c184d 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -1169,6 +1169,12 @@ int hns_nic_init_phy(struct net_device *ndev, struct hnae_handle *h)
 	if (!h->phy_dev)
 		return 0;
 
+	phy_dev->supported &= h->if_support;
+	phy_dev->advertising = phy_dev->supported;
+
+	if (h->phy_if == PHY_INTERFACE_MODE_XGMII)
+		phy_dev->autoneg = false;
+
 	if (h->phy_if != PHY_INTERFACE_MODE_XGMII) {
 		phy_dev->dev_flags = 0;
 
@@ -1180,15 +1186,6 @@ int hns_nic_init_phy(struct net_device *ndev, struct hnae_handle *h)
 	if (unlikely(ret))
 		return -ENODEV;
 
-	phy_dev->supported &= h->if_support;
-	phy_dev->advertising = phy_dev->supported;
-
-	if (h->phy_if == PHY_INTERFACE_MODE_XGMII)
-		phy_dev->autoneg = false;
-
-	if (h->phy_if == PHY_INTERFACE_MODE_SGMII)
-		phy_stop(phy_dev);
-
 	return 0;
 }
 
-- 
2.20.1


From aba61a5a9b98f5451b5a8a333fd6ab28e6dcf880 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Thu, 18 Apr 2019 07:14:14 +0000
Subject: [PATCH 12/18] mlxsw: pci: Reincrease PCI reset timeout

[ Upstream commit 1ab3030193d25878b3b1409060e1e0a879800c95 ]

During driver initialization the driver sends a reset to the device and
waits for the firmware to signal that it is ready to continue.

Commit d2f372ba0914 ("mlxsw: pci: Increase PCI SW reset timeout")
increased the timeout to 13 seconds due to longer PHY calibration in
Spectrum-2 compared to Spectrum-1.

Recently it became apparent that this timeout is too short and therefore
this patch increases it again to a safer limit that will be reduced in
the future.

Fixes: c3ab435466d5 ("mlxsw: spectrum: Extend to support Spectrum-2 ASIC")
Fixes: d2f372ba0914 ("mlxsw: pci: Increase PCI SW reset timeout")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/pci_hw.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
index 72cdaa01d56d..100618531021 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
@@ -27,7 +27,7 @@
 
 #define MLXSW_PCI_SW_RESET			0xF0010
 #define MLXSW_PCI_SW_RESET_RST_BIT		BIT(0)
-#define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS	13000
+#define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS	20000
 #define MLXSW_PCI_SW_RESET_WAIT_MSECS		100
 #define MLXSW_PCI_FW_READY			0xA1844
 #define MLXSW_PCI_FW_READY_MASK			0xFFFF
-- 
2.20.1


From 60fd60bbc49deab9905add76600571e8448de0fa Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 18 Apr 2019 07:14:13 +0000
Subject: [PATCH 13/18] mlxsw: spectrum: Put MC TCs into DWRR mode

[ Upstream commit f476b3f809fa02f47af6333ed63715058c3fc348 ]

Both Spectrum-1 and Spectrum-2 chips are currently configured such that
pairs of TC n (which is used for UC traffic) and TC n+8 (which is used
for MC traffic) are feeding into the same subgroup. Strict
prioritization is configured between the two TCs, and by enabling
MC-aware mode on the switch, the lower-numbered (UC) TCs are favored
over the higher-numbered (MC) TCs.

On Spectrum-2 however, there is an issue in configuration of the
MC-aware mode. As a result, MC traffic is prioritized over UC traffic.
To work around the issue, configure the MC TCs with DWRR mode (while
keeping the UC TCs in strict mode).

With this patch, the multicast-unicast arbitration results in the same
behavior on both Spectrum-1 and Spectrum-2 chips.

Fixes: 7b8195306694 ("mlxsw: spectrum: Configure MC-aware mode on mlxsw ports")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index b379d4219483..c5b82e283d13 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -2783,7 +2783,7 @@ static int mlxsw_sp_port_ets_init(struct mlxsw_sp_port *mlxsw_sp_port)
 		err = mlxsw_sp_port_ets_set(mlxsw_sp_port,
 					    MLXSW_REG_QEEC_HIERARCY_TC,
 					    i + 8, i,
-					    false, 0);
+					    true, 100);
 		if (err)
 			return err;
 	}
-- 
2.20.1


From 6d05e76c0fce86432b0953057ffb3d256d4d23fb Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Mon, 8 Apr 2019 15:12:45 +0300
Subject: [PATCH 14/18] net/mlx5e: Fix the max MTU check in case of XDP

[ Upstream commit d460c2718906252a2a69bc6f89b537071f792e6e ]

MLX5E_XDP_MAX_MTU was calculated incorrectly. It didn't account for
NET_IP_ALIGN and MLX5E_HW2SW_MTU, and it also misused MLX5_SKB_FRAG_SZ.
This commit fixes the calculations and adds a brief explanation for the
formula used.

Fixes: a26a5bdf3ee2d ("net/mlx5e: Restrict the combination of large MTU and XDP")
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en/xdp.c  | 20 +++++++++++++++++++
 .../net/ethernet/mellanox/mlx5/core/en/xdp.h  |  3 +--
 .../net/ethernet/mellanox/mlx5/core/en_main.c |  5 +++--
 3 files changed, 24 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 4a33c9a7cac7..ca08443f744d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -33,6 +33,26 @@
 #include <linux/bpf_trace.h>
 #include "en/xdp.h"
 
+int mlx5e_xdp_max_mtu(struct mlx5e_params *params)
+{
+	int hr = NET_IP_ALIGN + XDP_PACKET_HEADROOM;
+
+	/* Let S := SKB_DATA_ALIGN(sizeof(struct skb_shared_info)).
+	 * The condition checked in mlx5e_rx_is_linear_skb is:
+	 *   SKB_DATA_ALIGN(sw_mtu + hard_mtu + hr) + S <= PAGE_SIZE         (1)
+	 *   (Note that hw_mtu == sw_mtu + hard_mtu.)
+	 * What is returned from this function is:
+	 *   max_mtu = PAGE_SIZE - S - hr - hard_mtu                         (2)
+	 * After assigning sw_mtu := max_mtu, the left side of (1) turns to
+	 * SKB_DATA_ALIGN(PAGE_SIZE - S) + S, which is equal to PAGE_SIZE,
+	 * because both PAGE_SIZE and S are already aligned. Any number greater
+	 * than max_mtu would make the left side of (1) greater than PAGE_SIZE,
+	 * so max_mtu is the maximum MTU allowed.
+	 */
+
+	return MLX5E_HW2SW_MTU(params, SKB_MAX_HEAD(hr));
+}
+
 static inline bool
 mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_dma_info *di,
 		    struct xdp_buff *xdp)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index 4d096623178b..827ceef5fa93 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -34,12 +34,11 @@
 
 #include "en.h"
 
-#define MLX5E_XDP_MAX_MTU ((int)(PAGE_SIZE - \
-				 MLX5_SKB_FRAG_SZ(XDP_PACKET_HEADROOM)))
 #define MLX5E_XDP_MIN_INLINE (ETH_HLEN + VLAN_HLEN)
 #define MLX5E_XDP_TX_DS_COUNT \
 	((sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS) + 1 /* SG DS */)
 
+int mlx5e_xdp_max_mtu(struct mlx5e_params *params);
 bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
 		      void *va, u16 *rx_headroom, u32 *len);
 bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 637d59c01fe5..b190c447aeb0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3761,7 +3761,7 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu,
 	if (params->xdp_prog &&
 	    !mlx5e_rx_is_linear_skb(priv->mdev, &new_channels.params)) {
 		netdev_err(netdev, "MTU(%d) > %d is not allowed while XDP enabled\n",
-			   new_mtu, MLX5E_XDP_MAX_MTU);
+			   new_mtu, mlx5e_xdp_max_mtu(params));
 		err = -EINVAL;
 		goto out;
 	}
@@ -4227,7 +4227,8 @@ static int mlx5e_xdp_allowed(struct mlx5e_priv *priv, struct bpf_prog *prog)
 
 	if (!mlx5e_rx_is_linear_skb(priv->mdev, &new_channels.params)) {
 		netdev_warn(netdev, "XDP is not allowed with MTU(%d) > %d\n",
-			    new_channels.params.sw_mtu, MLX5E_XDP_MAX_MTU);
+			    new_channels.params.sw_mtu,
+			    mlx5e_xdp_max_mtu(&new_channels.params));
 		return -EINVAL;
 	}
 
-- 
2.20.1


From 5142bca3e81257dc22362e77106257546ee5deab Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Fri, 15 Mar 2019 16:41:43 +0200
Subject: [PATCH 15/18] net/mlx5e: Fix use-after-free after xdp_return_frame

[ Upstream commit 12fc512f5741443a03adde2ead20724da8ad550a ]

xdp_return_frame releases the frame. It leads to releasing the page, so
it's not allowed to access xdpi.xdpf->len after that, because xdpi.xdpf
is at xdp->data_hard_start after convert_to_xdp_frame. This patch moves
the memory access to precede the return of the frame.

Fixes: 58b99ee3e3ebe ("net/mlx5e: Add support for XDP_REDIRECT in device-out side")
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index ca08443f744d..599114ab7821 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -227,9 +227,9 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
 			sqcc++;
 
 			if (is_redirect) {
-				xdp_return_frame(xdpi->xdpf);
 				dma_unmap_single(sq->pdev, xdpi->dma_addr,
 						 xdpi->xdpf->len, DMA_TO_DEVICE);
+				xdp_return_frame(xdpi->xdpf);
 			} else {
 				/* Recycle RX page */
 				mlx5e_page_release(rq, &xdpi->di, true);
@@ -263,9 +263,9 @@ void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq)
 		sq->cc++;
 
 		if (is_redirect) {
-			xdp_return_frame(xdpi->xdpf);
 			dma_unmap_single(sq->pdev, xdpi->dma_addr,
 					 xdpi->xdpf->len, DMA_TO_DEVICE);
+			xdp_return_frame(xdpi->xdpf);
 		} else {
 			/* Recycle RX page */
 			mlx5e_page_release(rq, &xdpi->di, false);
-- 
2.20.1


From 49f00bcecca40e27340e3e16bd26ea8a945792eb Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 19 Apr 2019 16:51:38 -0700
Subject: [PATCH 16/18] net/tls: avoid potential deadlock in
 tls_set_device_offload_rx()

[ Upstream commit 62ef81d5632634d5e310ed25b9b940b2b6612b46 ]

If device supports offload, but offload fails tls_set_device_offload_rx()
will call tls_sw_free_resources_rx() which (unhelpfully) releases
and reacquires the socket lock.

For a small fix release and reacquire the device_offload_lock.

Fixes: 4799ac81e52a ("tls: Add rx inline crypto offload")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_device.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 961b07d4d41c..b61b893e9204 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -874,7 +874,9 @@ int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx)
 	goto release_netdev;
 
 free_sw_resources:
+	up_read(&device_offload_lock);
 	tls_sw_free_resources_rx(sk);
+	down_read(&device_offload_lock);
 release_ctx:
 	ctx->priv_ctx_rx = NULL;
 release_netdev:
-- 
2.20.1


From 6af7538176d0390f6b766058ad8ea10b00801cb5 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 19 Apr 2019 16:52:19 -0700
Subject: [PATCH 17/18] net/tls: don't leak IV and record seq when offload
 fails

[ Upstream commit 12c7686111326148b4b5db189130522a4ad1be4a ]

When device refuses the offload in tls_set_device_offload_rx()
it calls tls_sw_free_resources_rx() to clean up software context
state.

Unfortunately, tls_sw_free_resources_rx() does not free all
the state tls_set_sw_offload() allocated - it leaks IV and
sequence number buffers.  All other code paths which lead to
tls_sw_release_resources_rx() (which tls_sw_free_resources_rx()
calls) free those right before the call.

Avoid the leak by moving freeing of iv and rec_seq into
tls_sw_release_resources_rx().

Fixes: 4799ac81e52a ("tls: Add rx inline crypto offload")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_device.c | 2 --
 net/tls/tls_main.c   | 5 +----
 net/tls/tls_sw.c     | 3 +++
 3 files changed, 4 insertions(+), 6 deletions(-)

diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index b61b893e9204..c9588b682db4 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -911,8 +911,6 @@ void tls_device_offload_cleanup_rx(struct sock *sk)
 	}
 out:
 	up_read(&device_offload_lock);
-	kfree(tls_ctx->rx.rec_seq);
-	kfree(tls_ctx->rx.iv);
 	tls_sw_release_resources_rx(sk);
 }
 
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index a091c03abcb2..25b3fb585777 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -290,11 +290,8 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
 		tls_sw_free_resources_tx(sk);
 	}
 
-	if (ctx->rx_conf == TLS_SW) {
-		kfree(ctx->rx.rec_seq);
-		kfree(ctx->rx.iv);
+	if (ctx->rx_conf == TLS_SW)
 		tls_sw_free_resources_rx(sk);
-	}
 
 #ifdef CONFIG_TLS_DEVICE
 	if (ctx->rx_conf == TLS_HW)
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index b9c6ecfbcfea..6848a8196711 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1118,6 +1118,9 @@ void tls_sw_release_resources_rx(struct sock *sk)
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
 
+	kfree(tls_ctx->rx.rec_seq);
+	kfree(tls_ctx->rx.iv);
+
 	if (ctx->aead_recv) {
 		kfree_skb(ctx->recv_pkt);
 		ctx->recv_pkt = NULL;
-- 
2.20.1


From 9172f780377064d0c6e0cd55f3e065a26c51c616 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 24 Apr 2019 09:44:11 -0700
Subject: [PATCH 18/18] rxrpc: fix race condition in rxrpc_input_packet()

[ Upstream commit 032be5f19a94de51093851757089133dcc1e92aa ]

After commit 5271953cad31 ("rxrpc: Use the UDP encap_rcv hook"),
rxrpc_input_packet() is directly called from lockless UDP receive
path, under rcu_read_lock() protection.

It must therefore use RCU rules :

- udp_sk->sk_user_data can be cleared at any point in this function.
  rcu_dereference_sk_user_data() is what we need here.

- Also, since sk_user_data might have been set in rxrpc_open_socket()
  we must observe a proper RCU grace period before kfree(local) in
  rxrpc_lookup_local()

v4: @local can be NULL in xrpc_lookup_local() as reported by kbuild test robot <lkp@intel.com>
        and Julia Lawall <julia.lawall@lip6.fr>, thanks !

v3,v2 : addressed David Howells feedback, thanks !

syzbot reported :

kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] PREEMPT SMP KASAN
CPU: 0 PID: 19236 Comm: syz-executor703 Not tainted 5.1.0-rc6 #79
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:__lock_acquire+0xbef/0x3fb0 kernel/locking/lockdep.c:3573
Code: 00 0f 85 a5 1f 00 00 48 81 c4 10 01 00 00 5b 41 5c 41 5d 41 5e 41 5f 5d c3 48 b8 00 00 00 00 00 fc ff df 4c 89 ea 48 c1 ea 03 <80> 3c 02 00 0f 85 4a 21 00 00 49 81 7d 00 20 54 9c 89 0f 84 cf f4
RSP: 0018:ffff88809d7aef58 EFLAGS: 00010002
RAX: dffffc0000000000 RBX: 0000000000000000 RCX: 0000000000000000
RDX: 0000000000000026 RSI: 0000000000000000 RDI: 0000000000000001
RBP: ffff88809d7af090 R08: 0000000000000001 R09: 0000000000000001
R10: ffffed1015d05bc7 R11: ffff888089428600 R12: 0000000000000000
R13: 0000000000000130 R14: 0000000000000001 R15: 0000000000000001
FS:  00007f059044d700(0000) GS:ffff8880ae800000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000004b6040 CR3: 00000000955ca000 CR4: 00000000001406f0
Call Trace:
 lock_acquire+0x16f/0x3f0 kernel/locking/lockdep.c:4211
 __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline]
 _raw_spin_lock_irqsave+0x95/0xcd kernel/locking/spinlock.c:152
 skb_queue_tail+0x26/0x150 net/core/skbuff.c:2972
 rxrpc_reject_packet net/rxrpc/input.c:1126 [inline]
 rxrpc_input_packet+0x4a0/0x5536 net/rxrpc/input.c:1414
 udp_queue_rcv_one_skb+0xaf2/0x1780 net/ipv4/udp.c:2011
 udp_queue_rcv_skb+0x128/0x730 net/ipv4/udp.c:2085
 udp_unicast_rcv_skb.isra.0+0xb9/0x360 net/ipv4/udp.c:2245
 __udp4_lib_rcv+0x701/0x2ca0 net/ipv4/udp.c:2301
 udp_rcv+0x22/0x30 net/ipv4/udp.c:2482
 ip_protocol_deliver_rcu+0x60/0x8f0 net/ipv4/ip_input.c:208
 ip_local_deliver_finish+0x23b/0x390 net/ipv4/ip_input.c:234
 NF_HOOK include/linux/netfilter.h:289 [inline]
 NF_HOOK include/linux/netfilter.h:283 [inline]
 ip_local_deliver+0x1e9/0x520 net/ipv4/ip_input.c:255
 dst_input include/net/dst.h:450 [inline]
 ip_rcv_finish+0x1e1/0x300 net/ipv4/ip_input.c:413
 NF_HOOK include/linux/netfilter.h:289 [inline]
 NF_HOOK include/linux/netfilter.h:283 [inline]
 ip_rcv+0xe8/0x3f0 net/ipv4/ip_input.c:523
 __netif_receive_skb_one_core+0x115/0x1a0 net/core/dev.c:4987
 __netif_receive_skb+0x2c/0x1c0 net/core/dev.c:5099
 netif_receive_skb_internal+0x117/0x660 net/core/dev.c:5202
 napi_frags_finish net/core/dev.c:5769 [inline]
 napi_gro_frags+0xade/0xd10 net/core/dev.c:5843
 tun_get_user+0x2f24/0x3fb0 drivers/net/tun.c:1981
 tun_chr_write_iter+0xbd/0x156 drivers/net/tun.c:2027
 call_write_iter include/linux/fs.h:1866 [inline]
 do_iter_readv_writev+0x5e1/0x8e0 fs/read_write.c:681
 do_iter_write fs/read_write.c:957 [inline]
 do_iter_write+0x184/0x610 fs/read_write.c:938
 vfs_writev+0x1b3/0x2f0 fs/read_write.c:1002
 do_writev+0x15e/0x370 fs/read_write.c:1037
 __do_sys_writev fs/read_write.c:1110 [inline]
 __se_sys_writev fs/read_write.c:1107 [inline]
 __x64_sys_writev+0x75/0xb0 fs/read_write.c:1107
 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Fixes: 5271953cad31 ("rxrpc: Use the UDP encap_rcv hook")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/input.c        | 12 ++++++++----
 net/rxrpc/local_object.c |  3 ++-
 2 files changed, 10 insertions(+), 5 deletions(-)

diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 570b49d2da42..d591f54cb91f 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -1155,19 +1155,19 @@ int rxrpc_extract_header(struct rxrpc_skb_priv *sp, struct sk_buff *skb)
  * handle data received on the local endpoint
  * - may be called in interrupt context
  *
- * The socket is locked by the caller and this prevents the socket from being
- * shut down and the local endpoint from going away, thus sk_user_data will not
- * be cleared until this function returns.
+ * [!] Note that as this is called from the encap_rcv hook, the socket is not
+ * held locked by the caller and nothing prevents sk_user_data on the UDP from
+ * being cleared in the middle of processing this function.
  *
  * Called with the RCU read lock held from the IP layer via UDP.
  */
 int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb)
 {
+	struct rxrpc_local *local = rcu_dereference_sk_user_data(udp_sk);
 	struct rxrpc_connection *conn;
 	struct rxrpc_channel *chan;
 	struct rxrpc_call *call = NULL;
 	struct rxrpc_skb_priv *sp;
-	struct rxrpc_local *local = udp_sk->sk_user_data;
 	struct rxrpc_peer *peer = NULL;
 	struct rxrpc_sock *rx = NULL;
 	unsigned int channel;
@@ -1175,6 +1175,10 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb)
 
 	_enter("%p", udp_sk);
 
+	if (unlikely(!local)) {
+		kfree_skb(skb);
+		return 0;
+	}
 	if (skb->tstamp == 0)
 		skb->tstamp = ktime_get_real();
 
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index 0906e51d3cfb..10317dbdab5f 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -304,7 +304,8 @@ struct rxrpc_local *rxrpc_lookup_local(struct net *net,
 	ret = -ENOMEM;
 sock_error:
 	mutex_unlock(&rxnet->local_mutex);
-	kfree(local);
+	if (local)
+		call_rcu(&local->rcu, rxrpc_local_rcu);
 	_leave(" = %d", ret);
 	return ERR_PTR(ret);
 
-- 
2.20.1


[-- Attachment #3: net_50.mbox --]
[-- Type: Application/Octet-Stream, Size: 55989 bytes --]

From 996a4d192150345743846f7e312c85b2d51d0a9b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 24 Apr 2019 08:04:05 -0700
Subject: [PATCH 01/19] ipv4: add sanity checks in ipv4_link_failure()

[ Upstream commit 20ff83f10f113c88d0bb74589389b05250994c16 ]

Before calling __ip_options_compile(), we need to ensure the network
header is a an IPv4 one, and that it is already pulled in skb->head.

RAW sockets going through a tunnel can end up calling ipv4_link_failure()
with total garbage in the skb, or arbitrary lengthes.

syzbot report :

BUG: KASAN: stack-out-of-bounds in memcpy include/linux/string.h:355 [inline]
BUG: KASAN: stack-out-of-bounds in __ip_options_echo+0x294/0x1120 net/ipv4/ip_options.c:123
Write of size 69 at addr ffff888096abf068 by task syz-executor.4/9204

CPU: 0 PID: 9204 Comm: syz-executor.4 Not tainted 5.1.0-rc5+ #77
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 print_address_description.cold+0x7c/0x20d mm/kasan/report.c:187
 kasan_report.cold+0x1b/0x40 mm/kasan/report.c:317
 check_memory_region_inline mm/kasan/generic.c:185 [inline]
 check_memory_region+0x123/0x190 mm/kasan/generic.c:191
 memcpy+0x38/0x50 mm/kasan/common.c:133
 memcpy include/linux/string.h:355 [inline]
 __ip_options_echo+0x294/0x1120 net/ipv4/ip_options.c:123
 __icmp_send+0x725/0x1400 net/ipv4/icmp.c:695
 ipv4_link_failure+0x29f/0x550 net/ipv4/route.c:1204
 dst_link_failure include/net/dst.h:427 [inline]
 vti6_xmit net/ipv6/ip6_vti.c:514 [inline]
 vti6_tnl_xmit+0x10d4/0x1c0c net/ipv6/ip6_vti.c:553
 __netdev_start_xmit include/linux/netdevice.h:4414 [inline]
 netdev_start_xmit include/linux/netdevice.h:4423 [inline]
 xmit_one net/core/dev.c:3292 [inline]
 dev_hard_start_xmit+0x1b2/0x980 net/core/dev.c:3308
 __dev_queue_xmit+0x271d/0x3060 net/core/dev.c:3878
 dev_queue_xmit+0x18/0x20 net/core/dev.c:3911
 neigh_direct_output+0x16/0x20 net/core/neighbour.c:1527
 neigh_output include/net/neighbour.h:508 [inline]
 ip_finish_output2+0x949/0x1740 net/ipv4/ip_output.c:229
 ip_finish_output+0x73c/0xd50 net/ipv4/ip_output.c:317
 NF_HOOK_COND include/linux/netfilter.h:278 [inline]
 ip_output+0x21f/0x670 net/ipv4/ip_output.c:405
 dst_output include/net/dst.h:444 [inline]
 NF_HOOK include/linux/netfilter.h:289 [inline]
 raw_send_hdrinc net/ipv4/raw.c:432 [inline]
 raw_sendmsg+0x1d2b/0x2f20 net/ipv4/raw.c:663
 inet_sendmsg+0x147/0x5d0 net/ipv4/af_inet.c:798
 sock_sendmsg_nosec net/socket.c:651 [inline]
 sock_sendmsg+0xdd/0x130 net/socket.c:661
 sock_write_iter+0x27c/0x3e0 net/socket.c:988
 call_write_iter include/linux/fs.h:1866 [inline]
 new_sync_write+0x4c7/0x760 fs/read_write.c:474
 __vfs_write+0xe4/0x110 fs/read_write.c:487
 vfs_write+0x20c/0x580 fs/read_write.c:549
 ksys_write+0x14f/0x2d0 fs/read_write.c:599
 __do_sys_write fs/read_write.c:611 [inline]
 __se_sys_write fs/read_write.c:608 [inline]
 __x64_sys_write+0x73/0xb0 fs/read_write.c:608
 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x458c29
Code: ad b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f293b44bc78 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000458c29
RDX: 0000000000000014 RSI: 00000000200002c0 RDI: 0000000000000003
RBP: 000000000073bf00 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00007f293b44c6d4
R13: 00000000004c8623 R14: 00000000004ded68 R15: 00000000ffffffff

The buggy address belongs to the page:
page:ffffea00025aafc0 count:0 mapcount:0 mapping:0000000000000000 index:0x0
flags: 0x1fffc0000000000()
raw: 01fffc0000000000 0000000000000000 ffffffff025a0101 0000000000000000
raw: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff888096abef80: 00 00 00 f2 f2 f2 f2 f2 00 00 00 00 00 00 00 f2
 ffff888096abf000: f2 f2 f2 f2 00 00 00 00 00 00 00 00 00 00 00 00
>ffff888096abf080: 00 00 f3 f3 f3 f3 00 00 00 00 00 00 00 00 00 00
                         ^
 ffff888096abf100: 00 00 00 00 f1 f1 f1 f1 00 00 f3 f3 00 00 00 00
 ffff888096abf180: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00

Fixes: ed0de45a1008 ("ipv4: recompile ip options in ipv4_link_failure")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Stephen Suryaputra <ssuryaextr@gmail.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 32 +++++++++++++++++++++++---------
 1 file changed, 23 insertions(+), 9 deletions(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 25d9bef27d03..3c89ca325947 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1183,25 +1183,39 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
 	return dst;
 }
 
-static void ipv4_link_failure(struct sk_buff *skb)
+static void ipv4_send_dest_unreach(struct sk_buff *skb)
 {
 	struct ip_options opt;
-	struct rtable *rt;
 	int res;
 
 	/* Recompile ip options since IPCB may not be valid anymore.
+	 * Also check we have a reasonable ipv4 header.
 	 */
-	memset(&opt, 0, sizeof(opt));
-	opt.optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr);
+	if (!pskb_network_may_pull(skb, sizeof(struct iphdr)) ||
+	    ip_hdr(skb)->version != 4 || ip_hdr(skb)->ihl < 5)
+		return;
 
-	rcu_read_lock();
-	res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL);
-	rcu_read_unlock();
+	memset(&opt, 0, sizeof(opt));
+	if (ip_hdr(skb)->ihl > 5) {
+		if (!pskb_network_may_pull(skb, ip_hdr(skb)->ihl * 4))
+			return;
+		opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr);
 
-	if (res)
-		return;
+		rcu_read_lock();
+		res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL);
+		rcu_read_unlock();
 
+		if (res)
+			return;
+	}
 	__icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0, &opt);
+}
+
+static void ipv4_link_failure(struct sk_buff *skb)
+{
+	struct rtable *rt;
+
+	ipv4_send_dest_unreach(skb);
 
 	rt = skb_rtable(skb);
 	if (rt)
-- 
2.20.1


From ebdfc31c4e7d12ecc69c5876c2245c62f183632d Mon Sep 17 00:00:00 2001
From: ZhangXiaoxu <zhangxiaoxu5@huawei.com>
Date: Tue, 16 Apr 2019 09:47:24 +0800
Subject: [PATCH 02/19] ipv4: set the tcp_min_rtt_wlen range from 0 to one day

[ Upstream commit 19fad20d15a6494f47f85d869f00b11343ee5c78 ]

There is a UBSAN report as below:
UBSAN: Undefined behaviour in net/ipv4/tcp_input.c:2877:56
signed integer overflow:
2147483647 * 1000 cannot be represented in type 'int'
CPU: 3 PID: 0 Comm: swapper/3 Not tainted 5.1.0-rc4-00058-g582549e #1
Call Trace:
 <IRQ>
 dump_stack+0x8c/0xba
 ubsan_epilogue+0x11/0x60
 handle_overflow+0x12d/0x170
 ? ttwu_do_wakeup+0x21/0x320
 __ubsan_handle_mul_overflow+0x12/0x20
 tcp_ack_update_rtt+0x76c/0x780
 tcp_clean_rtx_queue+0x499/0x14d0
 tcp_ack+0x69e/0x1240
 ? __wake_up_sync_key+0x2c/0x50
 ? update_group_capacity+0x50/0x680
 tcp_rcv_established+0x4e2/0xe10
 tcp_v4_do_rcv+0x22b/0x420
 tcp_v4_rcv+0xfe8/0x1190
 ip_protocol_deliver_rcu+0x36/0x180
 ip_local_deliver+0x15b/0x1a0
 ip_rcv+0xac/0xd0
 __netif_receive_skb_one_core+0x7f/0xb0
 __netif_receive_skb+0x33/0xc0
 netif_receive_skb_internal+0x84/0x1c0
 napi_gro_receive+0x2a0/0x300
 receive_buf+0x3d4/0x2350
 ? detach_buf_split+0x159/0x390
 virtnet_poll+0x198/0x840
 ? reweight_entity+0x243/0x4b0
 net_rx_action+0x25c/0x770
 __do_softirq+0x19b/0x66d
 irq_exit+0x1eb/0x230
 do_IRQ+0x7a/0x150
 common_interrupt+0xf/0xf
 </IRQ>

It can be reproduced by:
  echo 2147483647 > /proc/sys/net/ipv4/tcp_min_rtt_wlen

Fixes: f672258391b42 ("tcp: track min RTT using windowed min-filter")
Signed-off-by: ZhangXiaoxu <zhangxiaoxu5@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt | 1 +
 net/ipv4/sysctl_net_ipv4.c             | 5 ++++-
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index acdfb5d2bcaa..e2142fe40cda 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -422,6 +422,7 @@ tcp_min_rtt_wlen - INTEGER
 	minimum RTT when it is moved to a longer path (e.g., due to traffic
 	engineering). A longer window makes the filter more resistant to RTT
 	inflations such as transient congestion. The unit is seconds.
+	Possible values: 0 - 86400 (1 day)
 	Default: 300
 
 tcp_moderate_rcvbuf - BOOLEAN
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index ba0fc4b18465..eeb4041fa5f9 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -49,6 +49,7 @@ static int ip_ping_group_range_min[] = { 0, 0 };
 static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
 static int comp_sack_nr_max = 255;
 static u32 u32_max_div_HZ = UINT_MAX / HZ;
+static int one_day_secs = 24 * 3600;
 
 /* obsolete */
 static int sysctl_tcp_low_latency __read_mostly;
@@ -1151,7 +1152,9 @@ static struct ctl_table ipv4_net_table[] = {
 		.data		= &init_net.ipv4.sysctl_tcp_min_rtt_wlen,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one_day_secs
 	},
 	{
 		.procname	= "tcp_autocorking",
-- 
2.20.1


From 457e23ebd70dc45cc8c8af670e762a16533bd4ce Mon Sep 17 00:00:00 2001
From: Amit Cohen <amitc@mellanox.com>
Date: Thu, 18 Apr 2019 07:14:16 +0000
Subject: [PATCH 03/19] mlxsw: spectrum: Fix autoneg status in ethtool

[ Upstream commit 151f0dddbbfe4c35c9c5b64873115aafd436af9d ]

If link is down and autoneg is set to on/off, the status in ethtool does
not change.

The reason is when the link is down the function returns with zero
before changing autoneg value.

Move the checking of link state (up/down) to be performed after setting
autoneg value, in order to be sure that autoneg will change in any case.

Fixes: 56ade8fe3fe1 ("mlxsw: spectrum: Add initial support for Spectrum ASIC")
Signed-off-by: Amit Cohen <amitc@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index cbdee5164be7..9183c84da72c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -2667,11 +2667,11 @@ mlxsw_sp_port_set_link_ksettings(struct net_device *dev,
 	if (err)
 		return err;
 
+	mlxsw_sp_port->link.autoneg = autoneg;
+
 	if (!netif_running(dev))
 		return 0;
 
-	mlxsw_sp_port->link.autoneg = autoneg;
-
 	mlxsw_sp_port_admin_status_set(mlxsw_sp_port, false);
 	mlxsw_sp_port_admin_status_set(mlxsw_sp_port, true);
 
-- 
2.20.1


From 239b0c232a005624e76f19ff2cda1295339c5f75 Mon Sep 17 00:00:00 2001
From: Erez Alfasi <ereza@mellanox.com>
Date: Thu, 11 Apr 2019 10:41:03 +0300
Subject: [PATCH 04/19] net/mlx5e: ethtool, Remove unsupported SFP EEPROM high
 pages query

[ Upstream commit ace329f4ab3ba434be2adf618073c752d083b524 ]

Querying EEPROM high pages data for SFP module is currently
not supported by our driver and yet queried, resulting in
invalid FW queries.

Set the EEPROM ethtool data length to 256 for SFP module will
limit the reading for page 0 only and prevent invalid FW queries.

Fixes: bb64143eee8c ("net/mlx5e: Add ethtool support for dump module EEPROM")
Signed-off-by: Erez Alfasi <ereza@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/port.c       | 4 ----
 2 files changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 3b9e5f0d0212..253496c4a3db 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1470,7 +1470,7 @@ static int mlx5e_get_module_info(struct net_device *netdev,
 		break;
 	case MLX5_MODULE_ID_SFP:
 		modinfo->type       = ETH_MODULE_SFF_8472;
-		modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN;
+		modinfo->eeprom_len = MLX5_EEPROM_PAGE_LENGTH;
 		break;
 	default:
 		netdev_err(priv->netdev, "%s: cable type not recognized:0x%x\n",
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index 2b82f35f4c35..efce1fa37f6f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -404,10 +404,6 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev,
 		size -= offset + size - MLX5_EEPROM_PAGE_LENGTH;
 
 	i2c_addr = MLX5_I2C_ADDR_LOW;
-	if (offset >= MLX5_EEPROM_PAGE_LENGTH) {
-		i2c_addr = MLX5_I2C_ADDR_HIGH;
-		offset -= MLX5_EEPROM_PAGE_LENGTH;
-	}
 
 	MLX5_SET(mcia_reg, in, l, 0);
 	MLX5_SET(mcia_reg, in, module, module_num);
-- 
2.20.1


From 12a4d06d109fe6740a37b88a7aeff1ceb737d9e1 Mon Sep 17 00:00:00 2001
From: Zhu Yanjun <yanjun.zhu@oracle.com>
Date: Wed, 24 Apr 2019 02:56:42 -0400
Subject: [PATCH 05/19] net: rds: exchange of 8K and 1M pool

[ Upstream commit 4b9fc7146249a6e0e3175d0acc033fdcd2bfcb17 ]

Before the commit 490ea5967b0d ("RDS: IB: move FMR code to its own file"),
when the dirty_count is greater than 9/10 of max_items of 8K pool,
1M pool is used, Vice versa. After the commit 490ea5967b0d ("RDS: IB: move
FMR code to its own file"), the above is removed. When we make the
following tests.

Server:
  rds-stress -r 1.1.1.16 -D 1M

Client:
  rds-stress -r 1.1.1.14 -s 1.1.1.16 -D 1M

The following will appear.
"
connecting to 1.1.1.16:4000
negotiated options, tasks will start in 2 seconds
Starting up..header from 1.1.1.166:4001 to id 4001 bogus
..
tsks  tx/s  rx/s tx+rx K/s  mbi K/s  mbo K/s tx us/c  rtt us
cpu %
   1    0    0     0.00     0.00     0.00    0.00 0.00 -1.00
   1    0    0     0.00     0.00     0.00    0.00 0.00 -1.00
   1    0    0     0.00     0.00     0.00    0.00 0.00 -1.00
   1    0    0     0.00     0.00     0.00    0.00 0.00 -1.00
   1    0    0     0.00     0.00     0.00    0.00 0.00 -1.00
...
"
So this exchange between 8K and 1M pool is added back.

Fixes: commit 490ea5967b0d ("RDS: IB: move FMR code to its own file")
Signed-off-by: Zhu Yanjun <yanjun.zhu@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/ib_fmr.c  | 11 +++++++++++
 net/rds/ib_rdma.c |  3 ---
 2 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/net/rds/ib_fmr.c b/net/rds/ib_fmr.c
index e0f70c4051b6..01e764f8f224 100644
--- a/net/rds/ib_fmr.c
+++ b/net/rds/ib_fmr.c
@@ -44,6 +44,17 @@ struct rds_ib_mr *rds_ib_alloc_fmr(struct rds_ib_device *rds_ibdev, int npages)
 	else
 		pool = rds_ibdev->mr_1m_pool;
 
+	if (atomic_read(&pool->dirty_count) >= pool->max_items / 10)
+		queue_delayed_work(rds_ib_mr_wq, &pool->flush_worker, 10);
+
+	/* Switch pools if one of the pool is reaching upper limit */
+	if (atomic_read(&pool->dirty_count) >=  pool->max_items * 9 / 10) {
+		if (pool->pool_type == RDS_IB_MR_8K_POOL)
+			pool = rds_ibdev->mr_1m_pool;
+		else
+			pool = rds_ibdev->mr_8k_pool;
+	}
+
 	ibmr = rds_ib_try_reuse_ibmr(pool);
 	if (ibmr)
 		return ibmr;
diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c
index 63c8d107adcf..d664e9ade74d 100644
--- a/net/rds/ib_rdma.c
+++ b/net/rds/ib_rdma.c
@@ -454,9 +454,6 @@ struct rds_ib_mr *rds_ib_try_reuse_ibmr(struct rds_ib_mr_pool *pool)
 	struct rds_ib_mr *ibmr = NULL;
 	int iter = 0;
 
-	if (atomic_read(&pool->dirty_count) >= pool->max_items_soft / 10)
-		queue_delayed_work(rds_ib_mr_wq, &pool->flush_worker, 10);
-
 	while (1) {
 		ibmr = rds_ib_reuse_mr(pool);
 		if (ibmr)
-- 
2.20.1


From 5b4ae0557244f465d86a6445ea13d33132e8e43a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 24 Apr 2019 05:35:00 -0700
Subject: [PATCH 06/19] net/rose: fix unbound loop in rose_loopback_timer()

[ Upstream commit 0453c682459583910d611a96de928f4442205493 ]

This patch adds a limit on the number of skbs that fuzzers can queue
into loopback_queue. 1000 packets for rose loopback seems more than enough.

Then, since we now have multiple cpus in most linux hosts,
we also need to limit the number of skbs rose_loopback_timer()
can dequeue at each round.

rose_loopback_queue() can be drop-monitor friendly, calling
consume_skb() or kfree_skb() appropriately.

Finally, use mod_timer() instead of del_timer() + add_timer()

syzbot report was :

rcu: INFO: rcu_preempt self-detected stall on CPU
rcu:    0-...!: (10499 ticks this GP) idle=536/1/0x4000000000000002 softirq=103291/103291 fqs=34
rcu:     (t=10500 jiffies g=140321 q=323)
rcu: rcu_preempt kthread starved for 10426 jiffies! g140321 f0x0 RCU_GP_WAIT_FQS(5) ->state=0x402 ->cpu=1
rcu: RCU grace-period kthread stack dump:
rcu_preempt     I29168    10      2 0x80000000
Call Trace:
 context_switch kernel/sched/core.c:2877 [inline]
 __schedule+0x813/0x1cc0 kernel/sched/core.c:3518
 schedule+0x92/0x180 kernel/sched/core.c:3562
 schedule_timeout+0x4db/0xfd0 kernel/time/timer.c:1803
 rcu_gp_fqs_loop kernel/rcu/tree.c:1971 [inline]
 rcu_gp_kthread+0x962/0x17b0 kernel/rcu/tree.c:2128
 kthread+0x357/0x430 kernel/kthread.c:253
 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:352
NMI backtrace for cpu 0
CPU: 0 PID: 7632 Comm: kworker/0:4 Not tainted 5.1.0-rc5+ #172
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Workqueue: events iterate_cleanup_work
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 nmi_cpu_backtrace.cold+0x63/0xa4 lib/nmi_backtrace.c:101
 nmi_trigger_cpumask_backtrace+0x1be/0x236 lib/nmi_backtrace.c:62
 arch_trigger_cpumask_backtrace+0x14/0x20 arch/x86/kernel/apic/hw_nmi.c:38
 trigger_single_cpu_backtrace include/linux/nmi.h:164 [inline]
 rcu_dump_cpu_stacks+0x183/0x1cf kernel/rcu/tree.c:1223
 print_cpu_stall kernel/rcu/tree.c:1360 [inline]
 check_cpu_stall kernel/rcu/tree.c:1434 [inline]
 rcu_pending kernel/rcu/tree.c:3103 [inline]
 rcu_sched_clock_irq.cold+0x500/0xa4a kernel/rcu/tree.c:2544
 update_process_times+0x32/0x80 kernel/time/timer.c:1635
 tick_sched_handle+0xa2/0x190 kernel/time/tick-sched.c:161
 tick_sched_timer+0x47/0x130 kernel/time/tick-sched.c:1271
 __run_hrtimer kernel/time/hrtimer.c:1389 [inline]
 __hrtimer_run_queues+0x33e/0xde0 kernel/time/hrtimer.c:1451
 hrtimer_interrupt+0x314/0x770 kernel/time/hrtimer.c:1509
 local_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1035 [inline]
 smp_apic_timer_interrupt+0x120/0x570 arch/x86/kernel/apic/apic.c:1060
 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:807
RIP: 0010:__sanitizer_cov_trace_pc+0x0/0x50 kernel/kcov.c:95
Code: 89 25 b4 6e ec 08 41 bc f4 ff ff ff e8 cd 5d ea ff 48 c7 05 9e 6e ec 08 00 00 00 00 e9 a4 e9 ff ff 90 90 90 90 90 90 90 90 90 <55> 48 89 e5 48 8b 75 08 65 48 8b 04 25 00 ee 01 00 65 8b 15 c8 60
RSP: 0018:ffff8880ae807ce0 EFLAGS: 00000286 ORIG_RAX: ffffffffffffff13
RAX: ffff88806fd40640 RBX: dffffc0000000000 RCX: ffffffff863fbc56
RDX: 0000000000000100 RSI: ffffffff863fbc1d RDI: ffff88808cf94228
RBP: ffff8880ae807d10 R08: ffff88806fd40640 R09: ffffed1015d00f8b
R10: ffffed1015d00f8a R11: 0000000000000003 R12: ffff88808cf941c0
R13: 00000000fffff034 R14: ffff8882166cd840 R15: 0000000000000000
 rose_loopback_timer+0x30d/0x3f0 net/rose/rose_loopback.c:91
 call_timer_fn+0x190/0x720 kernel/time/timer.c:1325
 expire_timers kernel/time/timer.c:1362 [inline]
 __run_timers kernel/time/timer.c:1681 [inline]
 __run_timers kernel/time/timer.c:1649 [inline]
 run_timer_softirq+0x652/0x1700 kernel/time/timer.c:1694
 __do_softirq+0x266/0x95a kernel/softirq.c:293
 do_softirq_own_stack+0x2a/0x40 arch/x86/entry/entry_64.S:1027

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rose/rose_loopback.c | 27 ++++++++++++++++-----------
 1 file changed, 16 insertions(+), 11 deletions(-)

diff --git a/net/rose/rose_loopback.c b/net/rose/rose_loopback.c
index 7af4f99c4a93..094a6621f8e8 100644
--- a/net/rose/rose_loopback.c
+++ b/net/rose/rose_loopback.c
@@ -16,6 +16,7 @@
 #include <linux/init.h>
 
 static struct sk_buff_head loopback_queue;
+#define ROSE_LOOPBACK_LIMIT 1000
 static struct timer_list loopback_timer;
 
 static void rose_set_loopback_timer(void);
@@ -35,29 +36,27 @@ static int rose_loopback_running(void)
 
 int rose_loopback_queue(struct sk_buff *skb, struct rose_neigh *neigh)
 {
-	struct sk_buff *skbn;
+	struct sk_buff *skbn = NULL;
 
-	skbn = skb_clone(skb, GFP_ATOMIC);
+	if (skb_queue_len(&loopback_queue) < ROSE_LOOPBACK_LIMIT)
+		skbn = skb_clone(skb, GFP_ATOMIC);
 
-	kfree_skb(skb);
-
-	if (skbn != NULL) {
+	if (skbn) {
+		consume_skb(skb);
 		skb_queue_tail(&loopback_queue, skbn);
 
 		if (!rose_loopback_running())
 			rose_set_loopback_timer();
+	} else {
+		kfree_skb(skb);
 	}
 
 	return 1;
 }
 
-
 static void rose_set_loopback_timer(void)
 {
-	del_timer(&loopback_timer);
-
-	loopback_timer.expires  = jiffies + 10;
-	add_timer(&loopback_timer);
+	mod_timer(&loopback_timer, jiffies + 10);
 }
 
 static void rose_loopback_timer(struct timer_list *unused)
@@ -68,8 +67,12 @@ static void rose_loopback_timer(struct timer_list *unused)
 	struct sock *sk;
 	unsigned short frametype;
 	unsigned int lci_i, lci_o;
+	int count;
 
-	while ((skb = skb_dequeue(&loopback_queue)) != NULL) {
+	for (count = 0; count < ROSE_LOOPBACK_LIMIT; count++) {
+		skb = skb_dequeue(&loopback_queue);
+		if (!skb)
+			return;
 		if (skb->len < ROSE_MIN_LEN) {
 			kfree_skb(skb);
 			continue;
@@ -106,6 +109,8 @@ static void rose_loopback_timer(struct timer_list *unused)
 			kfree_skb(skb);
 		}
 	}
+	if (!skb_queue_empty(&loopback_queue))
+		mod_timer(&loopback_timer, jiffies + 1);
 }
 
 void __exit rose_loopback_clear(void)
-- 
2.20.1


From ebf6438caf5675a8241cbd53b9e5566fa4858012 Mon Sep 17 00:00:00 2001
From: Vinod Koul <vkoul@kernel.org>
Date: Mon, 22 Apr 2019 15:15:32 +0530
Subject: [PATCH 07/19] net: stmmac: move stmmac_check_ether_addr() to driver
 probe

[ Upstream commit b561af36b1841088552464cdc3f6371d92f17710 ]

stmmac_check_ether_addr() checks the MAC address and assigns one in
driver open(). In many cases when we create slave netdevice, the dev
addr is inherited from master but the master dev addr maybe NULL at
that time, so move this call to driver probe so that address is
always valid.

Signed-off-by: Xiaofei Shen <xiaofeis@codeaurora.org>
Tested-by: Xiaofei Shen <xiaofeis@codeaurora.org>
Signed-off-by: Sneh Shah <snehshah@codeaurora.org>
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 019ab99e65bb..1d8d6f2ddfd6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2590,8 +2590,6 @@ static int stmmac_open(struct net_device *dev)
 	u32 chan;
 	int ret;
 
-	stmmac_check_ether_addr(priv);
-
 	if (priv->hw->pcs != STMMAC_PCS_RGMII &&
 	    priv->hw->pcs != STMMAC_PCS_TBI &&
 	    priv->hw->pcs != STMMAC_PCS_RTBI) {
@@ -4265,6 +4263,8 @@ int stmmac_dvr_probe(struct device *device,
 	if (ret)
 		goto error_hw_init;
 
+	stmmac_check_ether_addr(priv);
+
 	/* Configure real RX and TX queues */
 	netif_set_real_num_rx_queues(ndev, priv->plat->rx_queues_to_use);
 	netif_set_real_num_tx_queues(ndev, priv->plat->tx_queues_to_use);
-- 
2.20.1


From 8d2df07516a041dbbe3b3b8563a920de022cdffe Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 17 Apr 2019 10:51:19 -0700
Subject: [PATCH 08/19] net/tls: fix refcount adjustment in fallback

[ Upstream commit 9188d5ca454fd665145904267e726e9e8d122f5c ]

Unlike atomic_add(), refcount_add() does not deal well
with a negative argument.  TLS fallback code reallocates
the skb and is very likely to shrink the truesize, leading to:

[  189.513254] WARNING: CPU: 5 PID: 0 at lib/refcount.c:81 refcount_add_not_zero_checked+0x15c/0x180
 Call Trace:
  refcount_add_checked+0x6/0x40
  tls_enc_skb+0xb93/0x13e0 [tls]

Once wmem_allocated count saturates the application can no longer
send data on the socket.  This is similar to Eric's fixes for GSO,
TCP:
commit 7ec318feeed1 ("tcp: gso: avoid refcount_t warning from tcp_gso_segment()")
and UDP:
commit 575b65bc5bff ("udp: avoid refcount_t saturation in __udp_gso_segment()").

Unlike the GSO case, for TLS fallback it's likely that the skb has
shrunk, so the "likely" annotation is the other way around (likely
branch being "sub").

Fixes: e8f69799810c ("net/tls: Add generic NIC offload infrastructure")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_device_fallback.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c
index 450a6dbc5a88..ef8934fd8698 100644
--- a/net/tls/tls_device_fallback.c
+++ b/net/tls/tls_device_fallback.c
@@ -193,6 +193,9 @@ static void update_chksum(struct sk_buff *skb, int headln)
 
 static void complete_skb(struct sk_buff *nskb, struct sk_buff *skb, int headln)
 {
+	struct sock *sk = skb->sk;
+	int delta;
+
 	skb_copy_header(nskb, skb);
 
 	skb_put(nskb, skb->len);
@@ -200,11 +203,15 @@ static void complete_skb(struct sk_buff *nskb, struct sk_buff *skb, int headln)
 	update_chksum(nskb, headln);
 
 	nskb->destructor = skb->destructor;
-	nskb->sk = skb->sk;
+	nskb->sk = sk;
 	skb->destructor = NULL;
 	skb->sk = NULL;
-	refcount_add(nskb->truesize - skb->truesize,
-		     &nskb->sk->sk_wmem_alloc);
+
+	delta = nskb->truesize - skb->truesize;
+	if (likely(delta < 0))
+		WARN_ON_ONCE(refcount_sub_and_test(-delta, &sk->sk_wmem_alloc));
+	else if (delta)
+		refcount_add(delta, &sk->sk_wmem_alloc);
 }
 
 /* This function may be called after the user socket is already
-- 
2.20.1


From f1c22b7694ae5655b86e4eab19a0a91d05a093da Mon Sep 17 00:00:00 2001
From: Su Bao Cheng <baocheng.su@siemens.com>
Date: Thu, 18 Apr 2019 11:14:56 +0200
Subject: [PATCH 09/19] stmmac: pci: Adjust IOT2000 matching

[ Upstream commit e0c1d14a1a3211dccf0540a6703ffbd5d2a75bdb ]

Since there are more IOT2040 variants with identical hardware but
different asset tags, the asset tag matching should be adjusted to
support them.

For the board name "SIMATIC IOT2000", currently there are 2 types of
hardware, IOT2020 and IOT2040. The IOT2020 is identified by its unique
asset tag. Match on it first. If we then match on the board name only,
we will catch all IOT2040 variants. In the future there will be no other
devices with the "SIMATIC IOT2000" DMI board name but different
hardware.

Signed-off-by: Su Bao Cheng <baocheng.su@siemens.com>
Reviewed-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
index d819e8eaba12..cc1e887e47b5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
@@ -159,6 +159,12 @@ static const struct dmi_system_id quark_pci_dmi[] = {
 		},
 		.driver_data = (void *)&galileo_stmmac_dmi_data,
 	},
+	/*
+	 * There are 2 types of SIMATIC IOT2000: IOT20202 and IOT2040.
+	 * The asset tag "6ES7647-0AA00-0YA2" is only for IOT2020 which
+	 * has only one pci network device while other asset tags are
+	 * for IOT2040 which has two.
+	 */
 	{
 		.matches = {
 			DMI_EXACT_MATCH(DMI_BOARD_NAME, "SIMATIC IOT2000"),
@@ -170,8 +176,6 @@ static const struct dmi_system_id quark_pci_dmi[] = {
 	{
 		.matches = {
 			DMI_EXACT_MATCH(DMI_BOARD_NAME, "SIMATIC IOT2000"),
-			DMI_EXACT_MATCH(DMI_BOARD_ASSET_TAG,
-					"6ES7647-0AA00-1YA2"),
 		},
 		.driver_data = (void *)&iot2040_stmmac_dmi_data,
 	},
-- 
2.20.1


From 1b9d633087136811faae534306b07a2e935398aa Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Fri, 19 Apr 2019 14:31:00 +0800
Subject: [PATCH 10/19] team: fix possible recursive locking when add slaves

[ Upstream commit 925b0c841e066b488cc3a60272472b2c56300704 ]

If we add a bond device which is already the master of the team interface,
we will hold the team->lock in team_add_slave() first and then request the
lock in team_set_mac_address() again. The functions are called like:

- team_add_slave()
 - team_port_add()
   - team_port_enter()
     - team_modeop_port_enter()
       - __set_port_dev_addr()
         - dev_set_mac_address()
           - bond_set_mac_address()
             - dev_set_mac_address()
  	       - team_set_mac_address

Although team_upper_dev_link() would check the upper devices but it is
called too late. Fix it by adding a checking before processing the slave.

v2: Do not split the string in netdev_err()

Fixes: 3d249d4ca7d0 ("net: introduce ethernet teaming device")
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 1283632091d5..7dcda9364009 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1157,6 +1157,13 @@ static int team_port_add(struct team *team, struct net_device *port_dev,
 		return -EINVAL;
 	}
 
+	if (netdev_has_upper_dev(dev, port_dev)) {
+		NL_SET_ERR_MSG(extack, "Device is already an upper device of the team interface");
+		netdev_err(dev, "Device %s is already an upper device of the team interface\n",
+			   portname);
+		return -EBUSY;
+	}
+
 	if (port_dev->features & NETIF_F_VLAN_CHALLENGED &&
 	    vlan_uses_dev(dev)) {
 		NL_SET_ERR_MSG(extack, "Device is VLAN challenged and team device has VLAN set up");
-- 
2.20.1


From 34acd801ceab44d199535f540392f10e0765778b Mon Sep 17 00:00:00 2001
From: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Date: Tue, 23 Apr 2019 09:01:41 +0300
Subject: [PATCH 11/19] net: socionext: replace napi_alloc_frag with the netdev
 variant on init

[ Upstream commit ffbf9870dcf1342592a1a26f4cf70bda39046134 ]

The netdev variant is usable on any context since it disables interrupts.
The napi variant of the call should only be used within softirq context.
Replace napi_alloc_frag on driver init with the correct netdev_alloc_frag
call

Changes since v1:
- Adjusted commit message

Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Acked-by: Jassi Brar <jaswinder.singh@linaro.org>
Fixes: 4acb20b46214 ("net: socionext: different approach on DMA")
Signed-off-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/socionext/netsec.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index a18149720aa2..cba5881b2746 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -673,7 +673,8 @@ static void netsec_process_tx(struct netsec_priv *priv)
 }
 
 static void *netsec_alloc_rx_data(struct netsec_priv *priv,
-				  dma_addr_t *dma_handle, u16 *desc_len)
+				  dma_addr_t *dma_handle, u16 *desc_len,
+				  bool napi)
 {
 	size_t total_len = SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 	size_t payload_len = NETSEC_RX_BUF_SZ;
@@ -682,7 +683,7 @@ static void *netsec_alloc_rx_data(struct netsec_priv *priv,
 
 	total_len += SKB_DATA_ALIGN(payload_len + NETSEC_SKB_PAD);
 
-	buf = napi_alloc_frag(total_len);
+	buf = napi ? napi_alloc_frag(total_len) : netdev_alloc_frag(total_len);
 	if (!buf)
 		return NULL;
 
@@ -765,7 +766,8 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 		/* allocate a fresh buffer and map it to the hardware.
 		 * This will eventually replace the old buffer in the hardware
 		 */
-		buf_addr = netsec_alloc_rx_data(priv, &dma_handle, &desc_len);
+		buf_addr = netsec_alloc_rx_data(priv, &dma_handle, &desc_len,
+						true);
 		if (unlikely(!buf_addr))
 			break;
 
@@ -1069,7 +1071,8 @@ static int netsec_setup_rx_dring(struct netsec_priv *priv)
 		void *buf;
 		u16 len;
 
-		buf = netsec_alloc_rx_data(priv, &dma_handle, &len);
+		buf = netsec_alloc_rx_data(priv, &dma_handle, &len,
+					   false);
 		if (!buf) {
 			netsec_uninit_pkt_dring(priv, NETSEC_RING_RX);
 			goto err_out;
-- 
2.20.1


From 179667e9e79cd69e710bf18eca830ec7fd259f28 Mon Sep 17 00:00:00 2001
From: Tao Ren <taoren@fb.com>
Date: Wed, 24 Apr 2019 01:43:32 +0000
Subject: [PATCH 12/19] net/ncsi: handle overflow when incrementing mac address

[ Upstream commit 1c5c12ee308aacf635c8819cd4baa3bd58f8a8b7 ]

Previously BMC's MAC address is calculated by simply adding 1 to the
last byte of network controller's MAC address, and it produces incorrect
result when network controller's MAC address ends with 0xFF.

The problem can be fixed by calling eth_addr_inc() function to increment
MAC address; besides, the MAC address is also validated before assigning
to BMC.

Fixes: cb10c7c0dfd9 ("net/ncsi: Add NCSI Broadcom OEM command")
Signed-off-by: Tao Ren <taoren@fb.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Samuel Mendoza-Jonas <sam@mendozajonas.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/etherdevice.h | 12 ++++++++++++
 net/ncsi/ncsi-rsp.c         |  6 +++++-
 2 files changed, 17 insertions(+), 1 deletion(-)

diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index 2c0af7b00715..c94ab8b53a23 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -447,6 +447,18 @@ static inline void eth_addr_dec(u8 *addr)
 	u64_to_ether_addr(u, addr);
 }
 
+/**
+ * eth_addr_inc() - Increment the given MAC address.
+ * @addr: Pointer to a six-byte array containing Ethernet address to increment.
+ */
+static inline void eth_addr_inc(u8 *addr)
+{
+	u64 u = ether_addr_to_u64(addr);
+
+	u++;
+	u64_to_ether_addr(u, addr);
+}
+
 /**
  * is_etherdev_addr - Tell if given Ethernet address belongs to the device.
  * @dev: Pointer to a device structure
diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c
index dc07fcc7938e..802db01e3075 100644
--- a/net/ncsi/ncsi-rsp.c
+++ b/net/ncsi/ncsi-rsp.c
@@ -11,6 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/netdevice.h>
+#include <linux/etherdevice.h>
 #include <linux/skbuff.h>
 
 #include <net/ncsi.h>
@@ -667,7 +668,10 @@ static int ncsi_rsp_handler_oem_bcm_gma(struct ncsi_request *nr)
 	ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 	memcpy(saddr.sa_data, &rsp->data[BCM_MAC_ADDR_OFFSET], ETH_ALEN);
 	/* Increase mac address by 1 for BMC's address */
-	saddr.sa_data[ETH_ALEN - 1]++;
+	eth_addr_inc((u8 *)saddr.sa_data);
+	if (!is_valid_ether_addr((const u8 *)saddr.sa_data))
+		return -ENXIO;
+
 	ret = ops->ndo_set_mac_address(ndev, &saddr);
 	if (ret < 0)
 		netdev_warn(ndev, "NCSI: 'Writing mac address to device failed\n");
-- 
2.20.1


From 88fcaa83ae7edc8f68636928443d06a495e53673 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Thu, 18 Apr 2019 07:14:14 +0000
Subject: [PATCH 13/19] mlxsw: pci: Reincrease PCI reset timeout

[ Upstream commit 1ab3030193d25878b3b1409060e1e0a879800c95 ]

During driver initialization the driver sends a reset to the device and
waits for the firmware to signal that it is ready to continue.

Commit d2f372ba0914 ("mlxsw: pci: Increase PCI SW reset timeout")
increased the timeout to 13 seconds due to longer PHY calibration in
Spectrum-2 compared to Spectrum-1.

Recently it became apparent that this timeout is too short and therefore
this patch increases it again to a safer limit that will be reduced in
the future.

Fixes: c3ab435466d5 ("mlxsw: spectrum: Extend to support Spectrum-2 ASIC")
Fixes: d2f372ba0914 ("mlxsw: pci: Increase PCI SW reset timeout")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/pci_hw.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
index ffee38e36ce8..8648ca171254 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
@@ -27,7 +27,7 @@
 
 #define MLXSW_PCI_SW_RESET			0xF0010
 #define MLXSW_PCI_SW_RESET_RST_BIT		BIT(0)
-#define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS	13000
+#define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS	20000
 #define MLXSW_PCI_SW_RESET_WAIT_MSECS		100
 #define MLXSW_PCI_FW_READY			0xA1844
 #define MLXSW_PCI_FW_READY_MASK			0xFFFF
-- 
2.20.1


From 46e74c903ff10ebedc77f02bb5a707362872d557 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 18 Apr 2019 07:14:13 +0000
Subject: [PATCH 14/19] mlxsw: spectrum: Put MC TCs into DWRR mode

[ Upstream commit f476b3f809fa02f47af6333ed63715058c3fc348 ]

Both Spectrum-1 and Spectrum-2 chips are currently configured such that
pairs of TC n (which is used for UC traffic) and TC n+8 (which is used
for MC traffic) are feeding into the same subgroup. Strict
prioritization is configured between the two TCs, and by enabling
MC-aware mode on the switch, the lower-numbered (UC) TCs are favored
over the higher-numbered (MC) TCs.

On Spectrum-2 however, there is an issue in configuration of the
MC-aware mode. As a result, MC traffic is prioritized over UC traffic.
To work around the issue, configure the MC TCs with DWRR mode (while
keeping the UC TCs in strict mode).

With this patch, the multicast-unicast arbitration results in the same
behavior on both Spectrum-1 and Spectrum-2 chips.

Fixes: 7b8195306694 ("mlxsw: spectrum: Configure MC-aware mode on mlxsw ports")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 9183c84da72c..ce49504e1f9c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -2961,7 +2961,7 @@ static int mlxsw_sp_port_ets_init(struct mlxsw_sp_port *mlxsw_sp_port)
 		err = mlxsw_sp_port_ets_set(mlxsw_sp_port,
 					    MLXSW_REG_QEEC_HIERARCY_TC,
 					    i + 8, i,
-					    false, 0);
+					    true, 100);
 		if (err)
 			return err;
 	}
-- 
2.20.1


From 5b674a39ddf87f96cb62b49b965d76a56b11db2c Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Mon, 8 Apr 2019 15:12:45 +0300
Subject: [PATCH 15/19] net/mlx5e: Fix the max MTU check in case of XDP

[ Upstream commit d460c2718906252a2a69bc6f89b537071f792e6e ]

MLX5E_XDP_MAX_MTU was calculated incorrectly. It didn't account for
NET_IP_ALIGN and MLX5E_HW2SW_MTU, and it also misused MLX5_SKB_FRAG_SZ.
This commit fixes the calculations and adds a brief explanation for the
formula used.

Fixes: a26a5bdf3ee2d ("net/mlx5e: Restrict the combination of large MTU and XDP")
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en/xdp.c  | 20 +++++++++++++++++++
 .../net/ethernet/mellanox/mlx5/core/en/xdp.h  |  3 +--
 .../net/ethernet/mellanox/mlx5/core/en_main.c |  5 +++--
 3 files changed, 24 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 03b2a9f9c589..6536ad6ee371 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -33,6 +33,26 @@
 #include <linux/bpf_trace.h>
 #include "en/xdp.h"
 
+int mlx5e_xdp_max_mtu(struct mlx5e_params *params)
+{
+	int hr = NET_IP_ALIGN + XDP_PACKET_HEADROOM;
+
+	/* Let S := SKB_DATA_ALIGN(sizeof(struct skb_shared_info)).
+	 * The condition checked in mlx5e_rx_is_linear_skb is:
+	 *   SKB_DATA_ALIGN(sw_mtu + hard_mtu + hr) + S <= PAGE_SIZE         (1)
+	 *   (Note that hw_mtu == sw_mtu + hard_mtu.)
+	 * What is returned from this function is:
+	 *   max_mtu = PAGE_SIZE - S - hr - hard_mtu                         (2)
+	 * After assigning sw_mtu := max_mtu, the left side of (1) turns to
+	 * SKB_DATA_ALIGN(PAGE_SIZE - S) + S, which is equal to PAGE_SIZE,
+	 * because both PAGE_SIZE and S are already aligned. Any number greater
+	 * than max_mtu would make the left side of (1) greater than PAGE_SIZE,
+	 * so max_mtu is the maximum MTU allowed.
+	 */
+
+	return MLX5E_HW2SW_MTU(params, SKB_MAX_HEAD(hr));
+}
+
 static inline bool
 mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_dma_info *di,
 		    struct xdp_buff *xdp)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index ee27a7c8cd87..553956cadc8a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -34,13 +34,12 @@
 
 #include "en.h"
 
-#define MLX5E_XDP_MAX_MTU ((int)(PAGE_SIZE - \
-				 MLX5_SKB_FRAG_SZ(XDP_PACKET_HEADROOM)))
 #define MLX5E_XDP_MIN_INLINE (ETH_HLEN + VLAN_HLEN)
 #define MLX5E_XDP_TX_EMPTY_DS_COUNT \
 	(sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS)
 #define MLX5E_XDP_TX_DS_COUNT (MLX5E_XDP_TX_EMPTY_DS_COUNT + 1 /* SG DS */)
 
+int mlx5e_xdp_max_mtu(struct mlx5e_params *params);
 bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
 		      void *va, u16 *rx_headroom, u32 *len);
 bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 0cb19e4dd439..2d269acdbc8e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3816,7 +3816,7 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu,
 	if (params->xdp_prog &&
 	    !mlx5e_rx_is_linear_skb(priv->mdev, &new_channels.params)) {
 		netdev_err(netdev, "MTU(%d) > %d is not allowed while XDP enabled\n",
-			   new_mtu, MLX5E_XDP_MAX_MTU);
+			   new_mtu, mlx5e_xdp_max_mtu(params));
 		err = -EINVAL;
 		goto out;
 	}
@@ -4280,7 +4280,8 @@ static int mlx5e_xdp_allowed(struct mlx5e_priv *priv, struct bpf_prog *prog)
 
 	if (!mlx5e_rx_is_linear_skb(priv->mdev, &new_channels.params)) {
 		netdev_warn(netdev, "XDP is not allowed with MTU(%d) > %d\n",
-			    new_channels.params.sw_mtu, MLX5E_XDP_MAX_MTU);
+			    new_channels.params.sw_mtu,
+			    mlx5e_xdp_max_mtu(&new_channels.params));
 		return -EINVAL;
 	}
 
-- 
2.20.1


From 523bb88208625250ba8c044dc54732ce11b520aa Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Fri, 15 Mar 2019 16:41:43 +0200
Subject: [PATCH 16/19] net/mlx5e: Fix use-after-free after xdp_return_frame

[ Upstream commit 12fc512f5741443a03adde2ead20724da8ad550a ]

xdp_return_frame releases the frame. It leads to releasing the page, so
it's not allowed to access xdpi.xdpf->len after that, because xdpi.xdpf
is at xdp->data_hard_start after convert_to_xdp_frame. This patch moves
the memory access to precede the return of the frame.

Fixes: 58b99ee3e3ebe ("net/mlx5e: Add support for XDP_REDIRECT in device-out side")
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 6536ad6ee371..cad34d6f5f45 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -324,9 +324,9 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq)
 					mlx5e_xdpi_fifo_pop(xdpi_fifo);
 
 				if (is_redirect) {
-					xdp_return_frame(xdpi.xdpf);
 					dma_unmap_single(sq->pdev, xdpi.dma_addr,
 							 xdpi.xdpf->len, DMA_TO_DEVICE);
+					xdp_return_frame(xdpi.xdpf);
 				} else {
 					/* Recycle RX page */
 					mlx5e_page_release(rq, &xdpi.di, true);
@@ -365,9 +365,9 @@ void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq)
 				mlx5e_xdpi_fifo_pop(xdpi_fifo);
 
 			if (is_redirect) {
-				xdp_return_frame(xdpi.xdpf);
 				dma_unmap_single(sq->pdev, xdpi.dma_addr,
 						 xdpi.xdpf->len, DMA_TO_DEVICE);
+				xdp_return_frame(xdpi.xdpf);
 			} else {
 				/* Recycle RX page */
 				mlx5e_page_release(rq, &xdpi.di, false);
-- 
2.20.1


From 08600c0c53c8cfcd99165afd635429574db089d6 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 19 Apr 2019 16:51:38 -0700
Subject: [PATCH 17/19] net/tls: avoid potential deadlock in
 tls_set_device_offload_rx()

[ Upstream commit 62ef81d5632634d5e310ed25b9b940b2b6612b46 ]

If device supports offload, but offload fails tls_set_device_offload_rx()
will call tls_sw_free_resources_rx() which (unhelpfully) releases
and reacquires the socket lock.

For a small fix release and reacquire the device_offload_lock.

Fixes: 4799ac81e52a ("tls: Add rx inline crypto offload")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_device.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 4b5ff3d44912..b81b201304f7 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -884,7 +884,9 @@ int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx)
 	goto release_netdev;
 
 free_sw_resources:
+	up_read(&device_offload_lock);
 	tls_sw_free_resources_rx(sk);
+	down_read(&device_offload_lock);
 release_ctx:
 	ctx->priv_ctx_rx = NULL;
 release_netdev:
-- 
2.20.1


From ed27828eceebaa370111c72c1114de40816f2021 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 19 Apr 2019 16:52:19 -0700
Subject: [PATCH 18/19] net/tls: don't leak IV and record seq when offload
 fails

[ Upstream commit 12c7686111326148b4b5db189130522a4ad1be4a ]

When device refuses the offload in tls_set_device_offload_rx()
it calls tls_sw_free_resources_rx() to clean up software context
state.

Unfortunately, tls_sw_free_resources_rx() does not free all
the state tls_set_sw_offload() allocated - it leaks IV and
sequence number buffers.  All other code paths which lead to
tls_sw_release_resources_rx() (which tls_sw_free_resources_rx()
calls) free those right before the call.

Avoid the leak by moving freeing of iv and rec_seq into
tls_sw_release_resources_rx().

Fixes: 4799ac81e52a ("tls: Add rx inline crypto offload")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_device.c | 2 --
 net/tls/tls_main.c   | 5 +----
 net/tls/tls_sw.c     | 3 +++
 3 files changed, 4 insertions(+), 6 deletions(-)

diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index b81b201304f7..5f1d937c4be9 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -921,8 +921,6 @@ void tls_device_offload_cleanup_rx(struct sock *sk)
 	}
 out:
 	up_read(&device_offload_lock);
-	kfree(tls_ctx->rx.rec_seq);
-	kfree(tls_ctx->rx.iv);
 	tls_sw_release_resources_rx(sk);
 }
 
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 96dbac91ac6e..ce5dd79365a7 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -304,11 +304,8 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
 #endif
 	}
 
-	if (ctx->rx_conf == TLS_SW) {
-		kfree(ctx->rx.rec_seq);
-		kfree(ctx->rx.iv);
+	if (ctx->rx_conf == TLS_SW)
 		tls_sw_free_resources_rx(sk);
-	}
 
 #ifdef CONFIG_TLS_DEVICE
 	if (ctx->rx_conf == TLS_HW)
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index d2d4f7c0d4be..839a0a0b5dfa 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1830,6 +1830,9 @@ void tls_sw_release_resources_rx(struct sock *sk)
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
 
+	kfree(tls_ctx->rx.rec_seq);
+	kfree(tls_ctx->rx.iv);
+
 	if (ctx->aead_recv) {
 		kfree_skb(ctx->recv_pkt);
 		ctx->recv_pkt = NULL;
-- 
2.20.1


From 57d92a6afecc7b929bc3add79013fdb93d5c42f2 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 24 Apr 2019 09:44:11 -0700
Subject: [PATCH 19/19] rxrpc: fix race condition in rxrpc_input_packet()

[ Upstream commit 032be5f19a94de51093851757089133dcc1e92aa ]

After commit 5271953cad31 ("rxrpc: Use the UDP encap_rcv hook"),
rxrpc_input_packet() is directly called from lockless UDP receive
path, under rcu_read_lock() protection.

It must therefore use RCU rules :

- udp_sk->sk_user_data can be cleared at any point in this function.
  rcu_dereference_sk_user_data() is what we need here.

- Also, since sk_user_data might have been set in rxrpc_open_socket()
  we must observe a proper RCU grace period before kfree(local) in
  rxrpc_lookup_local()

v4: @local can be NULL in xrpc_lookup_local() as reported by kbuild test robot <lkp@intel.com>
        and Julia Lawall <julia.lawall@lip6.fr>, thanks !

v3,v2 : addressed David Howells feedback, thanks !

syzbot reported :

kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] PREEMPT SMP KASAN
CPU: 0 PID: 19236 Comm: syz-executor703 Not tainted 5.1.0-rc6 #79
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:__lock_acquire+0xbef/0x3fb0 kernel/locking/lockdep.c:3573
Code: 00 0f 85 a5 1f 00 00 48 81 c4 10 01 00 00 5b 41 5c 41 5d 41 5e 41 5f 5d c3 48 b8 00 00 00 00 00 fc ff df 4c 89 ea 48 c1 ea 03 <80> 3c 02 00 0f 85 4a 21 00 00 49 81 7d 00 20 54 9c 89 0f 84 cf f4
RSP: 0018:ffff88809d7aef58 EFLAGS: 00010002
RAX: dffffc0000000000 RBX: 0000000000000000 RCX: 0000000000000000
RDX: 0000000000000026 RSI: 0000000000000000 RDI: 0000000000000001
RBP: ffff88809d7af090 R08: 0000000000000001 R09: 0000000000000001
R10: ffffed1015d05bc7 R11: ffff888089428600 R12: 0000000000000000
R13: 0000000000000130 R14: 0000000000000001 R15: 0000000000000001
FS:  00007f059044d700(0000) GS:ffff8880ae800000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000004b6040 CR3: 00000000955ca000 CR4: 00000000001406f0
Call Trace:
 lock_acquire+0x16f/0x3f0 kernel/locking/lockdep.c:4211
 __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline]
 _raw_spin_lock_irqsave+0x95/0xcd kernel/locking/spinlock.c:152
 skb_queue_tail+0x26/0x150 net/core/skbuff.c:2972
 rxrpc_reject_packet net/rxrpc/input.c:1126 [inline]
 rxrpc_input_packet+0x4a0/0x5536 net/rxrpc/input.c:1414
 udp_queue_rcv_one_skb+0xaf2/0x1780 net/ipv4/udp.c:2011
 udp_queue_rcv_skb+0x128/0x730 net/ipv4/udp.c:2085
 udp_unicast_rcv_skb.isra.0+0xb9/0x360 net/ipv4/udp.c:2245
 __udp4_lib_rcv+0x701/0x2ca0 net/ipv4/udp.c:2301
 udp_rcv+0x22/0x30 net/ipv4/udp.c:2482
 ip_protocol_deliver_rcu+0x60/0x8f0 net/ipv4/ip_input.c:208
 ip_local_deliver_finish+0x23b/0x390 net/ipv4/ip_input.c:234
 NF_HOOK include/linux/netfilter.h:289 [inline]
 NF_HOOK include/linux/netfilter.h:283 [inline]
 ip_local_deliver+0x1e9/0x520 net/ipv4/ip_input.c:255
 dst_input include/net/dst.h:450 [inline]
 ip_rcv_finish+0x1e1/0x300 net/ipv4/ip_input.c:413
 NF_HOOK include/linux/netfilter.h:289 [inline]
 NF_HOOK include/linux/netfilter.h:283 [inline]
 ip_rcv+0xe8/0x3f0 net/ipv4/ip_input.c:523
 __netif_receive_skb_one_core+0x115/0x1a0 net/core/dev.c:4987
 __netif_receive_skb+0x2c/0x1c0 net/core/dev.c:5099
 netif_receive_skb_internal+0x117/0x660 net/core/dev.c:5202
 napi_frags_finish net/core/dev.c:5769 [inline]
 napi_gro_frags+0xade/0xd10 net/core/dev.c:5843
 tun_get_user+0x2f24/0x3fb0 drivers/net/tun.c:1981
 tun_chr_write_iter+0xbd/0x156 drivers/net/tun.c:2027
 call_write_iter include/linux/fs.h:1866 [inline]
 do_iter_readv_writev+0x5e1/0x8e0 fs/read_write.c:681
 do_iter_write fs/read_write.c:957 [inline]
 do_iter_write+0x184/0x610 fs/read_write.c:938
 vfs_writev+0x1b3/0x2f0 fs/read_write.c:1002
 do_writev+0x15e/0x370 fs/read_write.c:1037
 __do_sys_writev fs/read_write.c:1110 [inline]
 __se_sys_writev fs/read_write.c:1107 [inline]
 __x64_sys_writev+0x75/0xb0 fs/read_write.c:1107
 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Fixes: 5271953cad31 ("rxrpc: Use the UDP encap_rcv hook")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/input.c        | 12 ++++++++----
 net/rxrpc/local_object.c |  3 ++-
 2 files changed, 10 insertions(+), 5 deletions(-)

diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 9128aa0e40aa..b4ffb81223ad 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -1155,19 +1155,19 @@ int rxrpc_extract_header(struct rxrpc_skb_priv *sp, struct sk_buff *skb)
  * handle data received on the local endpoint
  * - may be called in interrupt context
  *
- * The socket is locked by the caller and this prevents the socket from being
- * shut down and the local endpoint from going away, thus sk_user_data will not
- * be cleared until this function returns.
+ * [!] Note that as this is called from the encap_rcv hook, the socket is not
+ * held locked by the caller and nothing prevents sk_user_data on the UDP from
+ * being cleared in the middle of processing this function.
  *
  * Called with the RCU read lock held from the IP layer via UDP.
  */
 int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb)
 {
+	struct rxrpc_local *local = rcu_dereference_sk_user_data(udp_sk);
 	struct rxrpc_connection *conn;
 	struct rxrpc_channel *chan;
 	struct rxrpc_call *call = NULL;
 	struct rxrpc_skb_priv *sp;
-	struct rxrpc_local *local = udp_sk->sk_user_data;
 	struct rxrpc_peer *peer = NULL;
 	struct rxrpc_sock *rx = NULL;
 	unsigned int channel;
@@ -1175,6 +1175,10 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb)
 
 	_enter("%p", udp_sk);
 
+	if (unlikely(!local)) {
+		kfree_skb(skb);
+		return 0;
+	}
 	if (skb->tstamp == 0)
 		skb->tstamp = ktime_get_real();
 
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index 0906e51d3cfb..10317dbdab5f 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -304,7 +304,8 @@ struct rxrpc_local *rxrpc_lookup_local(struct net *net,
 	ret = -ENOMEM;
 sock_error:
 	mutex_unlock(&rxnet->local_mutex);
-	kfree(local);
+	if (local)
+		call_rcu(&local->rcu, rxrpc_local_rcu);
 	_leave(" = %d", ret);
 	return ERR_PTR(ret);
 
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Mon, Apr 29, 2019 at 10:06:29PM -0400, David Miller wrote:
> 
> Please queue up the following neworking bug fixes for
> v4.19 and v5.0 -stable, respectively.

Thanks for these, all now queued up.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 106 bytes --]


Please queue up the following networking bug fixes for v4.19 and
v5.0 -stable, respectively.

Thank you.

[-- Attachment #2: net_419.mbox --]
[-- Type: Application/Octet-Stream, Size: 53539 bytes --]

From 7e005f0b8231690bd2401ffd0d00212480b055e2 Mon Sep 17 00:00:00 2001
From: Shmulik Ladkani <shmulik@metanetworks.com>
Date: Mon, 29 Apr 2019 16:39:30 +0300
Subject: [PATCH 01/19] ipv4: ip_do_fragment: Preserve skb_iif during
 fragmentation

[ Upstream commit d2f0c961148f65bc73eda72b9fa3a4e80973cb49 ]

Previously, during fragmentation after forwarding, skb->skb_iif isn't
preserved, i.e. 'ip_copy_metadata' does not copy skb_iif from given
'from' skb.

As a result, ip_do_fragment's creates fragments with zero skb_iif,
leading to inconsistent behavior.

Assume for example an eBPF program attached at tc egress (post
forwarding) that examines __sk_buff->ingress_ifindex:
 - the correct iif is observed if forwarding path does not involve
   fragmentation/refragmentation
 - a bogus iif is observed if forwarding path involves
   fragmentation/refragmentatiom

Fix, by preserving skb_iif during 'ip_copy_metadata'.

Signed-off-by: Shmulik Ladkani <shmulik.ladkani@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_output.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 9c4e72e9c60a..73894ed12a70 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -519,6 +519,7 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	to->pkt_type = from->pkt_type;
 	to->priority = from->priority;
 	to->protocol = from->protocol;
+	to->skb_iif = from->skb_iif;
 	skb_dst_drop(to);
 	skb_dst_copy(to, from);
 	to->dev = from->dev;
-- 
2.20.1


From bc729f80728a1b64916a79f870ecc65fb3c10566 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Tue, 30 Apr 2019 10:45:12 -0700
Subject: [PATCH 02/19] ipv6: A few fixes on dereferencing rt->from

[ Upstream commit 886b7a50100a50f1cbd08a6f8ec5884dfbe082dc ]

It is a followup after the fix in
commit 9c69a1320515 ("route: Avoid crash from dereferencing NULL rt->from")

rt6_do_redirect():
1. NULL checking is needed on rt->from because a parallel
   fib6_info delete could happen that sets rt->from to NULL.
   (e.g. rt6_remove_exception() and fib6_drop_pcpu_from()).

2. fib6_info_hold() is not enough.  Same reason as (1).
   Meaning, holding dst->__refcnt cannot ensure
   rt->from is not NULL or rt->from->fib6_ref is not 0.

   Instead of using fib6_info_hold_safe() which ip6_rt_cache_alloc()
   is already doing, this patch chooses to extend the rcu section
   to keep "from" dereference-able after checking for NULL.

inet6_rtm_getroute():
1. NULL checking is also needed on rt->from for a similar reason.
   Note that inet6_rtm_getroute() is using RTNL_FLAG_DOIT_UNLOCKED.

Fixes: a68886a69180 ("net/ipv6: Make from in rt6_info rcu protected")
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Wei Wang <weiwan@google.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 38 ++++++++++++++++++--------------------
 1 file changed, 18 insertions(+), 20 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 06fa8425d82c..12a263dc0d21 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3454,11 +3454,8 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
 
 	rcu_read_lock();
 	from = rcu_dereference(rt->from);
-	/* This fib6_info_hold() is safe here because we hold reference to rt
-	 * and rt already holds reference to fib6_info.
-	 */
-	fib6_info_hold(from);
-	rcu_read_unlock();
+	if (!from)
+		goto out;
 
 	nrt = ip6_rt_cache_alloc(from, &msg->dest, NULL);
 	if (!nrt)
@@ -3470,10 +3467,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
 
 	nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key;
 
-	/* No need to remove rt from the exception table if rt is
-	 * a cached route because rt6_insert_exception() will
-	 * takes care of it
-	 */
+	/* rt6_insert_exception() will take care of duplicated exceptions */
 	if (rt6_insert_exception(nrt, from)) {
 		dst_release_immediate(&nrt->dst);
 		goto out;
@@ -3486,7 +3480,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
 	call_netevent_notifiers(NETEVENT_REDIRECT, &netevent);
 
 out:
-	fib6_info_release(from);
+	rcu_read_unlock();
 	neigh_release(neigh);
 }
 
@@ -4991,16 +4985,20 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 
 	rcu_read_lock();
 	from = rcu_dereference(rt->from);
-
-	if (fibmatch)
-		err = rt6_fill_node(net, skb, from, NULL, NULL, NULL, iif,
-				    RTM_NEWROUTE, NETLINK_CB(in_skb).portid,
-				    nlh->nlmsg_seq, 0);
-	else
-		err = rt6_fill_node(net, skb, from, dst, &fl6.daddr,
-				    &fl6.saddr, iif, RTM_NEWROUTE,
-				    NETLINK_CB(in_skb).portid, nlh->nlmsg_seq,
-				    0);
+	if (from) {
+		if (fibmatch)
+			err = rt6_fill_node(net, skb, from, NULL, NULL, NULL,
+					    iif, RTM_NEWROUTE,
+					    NETLINK_CB(in_skb).portid,
+					    nlh->nlmsg_seq, 0);
+		else
+			err = rt6_fill_node(net, skb, from, dst, &fl6.daddr,
+					    &fl6.saddr, iif, RTM_NEWROUTE,
+					    NETLINK_CB(in_skb).portid,
+					    nlh->nlmsg_seq, 0);
+	} else {
+		err = -ENETUNREACH;
+	}
 	rcu_read_unlock();
 
 	if (err < 0) {
-- 
2.20.1


From 00b8daa6b3ab377065f6c3eda04963651a0ec48e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 28 Apr 2019 12:22:25 -0700
Subject: [PATCH 03/19] ipv6: fix races in ip6_dst_destroy()

[ Upstream commit 0e2338749192ce0e52e7174c5352f627632f478a ]

We had many syzbot reports that seem to be caused by use-after-free
of struct fib6_info.

ip6_dst_destroy(), fib6_drop_pcpu_from() and rt6_remove_exception()
are writers vs rt->from, and use non consistent synchronization among
themselves.

Switching to xchg() will solve the issues with no possible
lockdep issues.

BUG: KASAN: user-memory-access in atomic_dec_and_test include/asm-generic/atomic-instrumented.h:747 [inline]
BUG: KASAN: user-memory-access in fib6_info_release include/net/ip6_fib.h:294 [inline]
BUG: KASAN: user-memory-access in fib6_info_release include/net/ip6_fib.h:292 [inline]
BUG: KASAN: user-memory-access in fib6_drop_pcpu_from net/ipv6/ip6_fib.c:927 [inline]
BUG: KASAN: user-memory-access in fib6_purge_rt+0x4f6/0x670 net/ipv6/ip6_fib.c:960
Write of size 4 at addr 0000000000ffffb4 by task syz-executor.1/7649

CPU: 0 PID: 7649 Comm: syz-executor.1 Not tainted 5.1.0-rc6+ #183
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 kasan_report.cold+0x5/0x40 mm/kasan/report.c:321
 check_memory_region_inline mm/kasan/generic.c:185 [inline]
 check_memory_region+0x123/0x190 mm/kasan/generic.c:191
 kasan_check_write+0x14/0x20 mm/kasan/common.c:108
 atomic_dec_and_test include/asm-generic/atomic-instrumented.h:747 [inline]
 fib6_info_release include/net/ip6_fib.h:294 [inline]
 fib6_info_release include/net/ip6_fib.h:292 [inline]
 fib6_drop_pcpu_from net/ipv6/ip6_fib.c:927 [inline]
 fib6_purge_rt+0x4f6/0x670 net/ipv6/ip6_fib.c:960
 fib6_del_route net/ipv6/ip6_fib.c:1813 [inline]
 fib6_del+0xac2/0x10a0 net/ipv6/ip6_fib.c:1844
 fib6_clean_node+0x3a8/0x590 net/ipv6/ip6_fib.c:2006
 fib6_walk_continue+0x495/0x900 net/ipv6/ip6_fib.c:1928
 fib6_walk+0x9d/0x100 net/ipv6/ip6_fib.c:1976
 fib6_clean_tree+0xe0/0x120 net/ipv6/ip6_fib.c:2055
 __fib6_clean_all+0x118/0x2a0 net/ipv6/ip6_fib.c:2071
 fib6_clean_all+0x2b/0x40 net/ipv6/ip6_fib.c:2082
 rt6_sync_down_dev+0x134/0x150 net/ipv6/route.c:4057
 rt6_disable_ip+0x27/0x5f0 net/ipv6/route.c:4062
 addrconf_ifdown+0xa2/0x1220 net/ipv6/addrconf.c:3705
 addrconf_notify+0x19a/0x2260 net/ipv6/addrconf.c:3630
 notifier_call_chain+0xc7/0x240 kernel/notifier.c:93
 __raw_notifier_call_chain kernel/notifier.c:394 [inline]
 raw_notifier_call_chain+0x2e/0x40 kernel/notifier.c:401
 call_netdevice_notifiers_info+0x3f/0x90 net/core/dev.c:1753
 call_netdevice_notifiers_extack net/core/dev.c:1765 [inline]
 call_netdevice_notifiers net/core/dev.c:1779 [inline]
 dev_close_many+0x33f/0x6f0 net/core/dev.c:1522
 rollback_registered_many+0x43b/0xfd0 net/core/dev.c:8177
 rollback_registered+0x109/0x1d0 net/core/dev.c:8242
 unregister_netdevice_queue net/core/dev.c:9289 [inline]
 unregister_netdevice_queue+0x1ee/0x2c0 net/core/dev.c:9282
 unregister_netdevice include/linux/netdevice.h:2658 [inline]
 __tun_detach+0xd5b/0x1000 drivers/net/tun.c:727
 tun_detach drivers/net/tun.c:744 [inline]
 tun_chr_close+0xe0/0x180 drivers/net/tun.c:3443
 __fput+0x2e5/0x8d0 fs/file_table.c:278
 ____fput+0x16/0x20 fs/file_table.c:309
 task_work_run+0x14a/0x1c0 kernel/task_work.c:113
 exit_task_work include/linux/task_work.h:22 [inline]
 do_exit+0x90a/0x2fa0 kernel/exit.c:876
 do_group_exit+0x135/0x370 kernel/exit.c:980
 __do_sys_exit_group kernel/exit.c:991 [inline]
 __se_sys_exit_group kernel/exit.c:989 [inline]
 __x64_sys_exit_group+0x44/0x50 kernel/exit.c:989
 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x458da9
Code: ad b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007ffeafc2a6a8 EFLAGS: 00000246 ORIG_RAX: 00000000000000e7
RAX: ffffffffffffffda RBX: 000000000000001c RCX: 0000000000458da9
RDX: 0000000000412a80 RSI: 0000000000a54ef0 RDI: 0000000000000043
RBP: 00000000004be552 R08: 000000000000000c R09: 000000000004c0d1
R10: 0000000002341940 R11: 0000000000000246 R12: 00000000ffffffff
R13: 00007ffeafc2a7f0 R14: 000000000004c065 R15: 00007ffeafc2a800

Fixes: a68886a69180 ("net/ipv6: Make from in rt6_info rcu protected")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: David Ahern <dsahern@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Wei Wang <weiwan@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_fib.c | 4 +---
 net/ipv6/route.c   | 9 ++-------
 2 files changed, 3 insertions(+), 10 deletions(-)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index cbe46175bb59..3e2a9bd3459c 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -889,9 +889,7 @@ static void fib6_drop_pcpu_from(struct fib6_info *f6i,
 		if (pcpu_rt) {
 			struct fib6_info *from;
 
-			from = rcu_dereference_protected(pcpu_rt->from,
-					     lockdep_is_held(&table->tb6_lock));
-			rcu_assign_pointer(pcpu_rt->from, NULL);
+			from = xchg((__force struct fib6_info **)&pcpu_rt->from, NULL);
 			fib6_info_release(from);
 		}
 	}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 12a263dc0d21..2e519f7b983c 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -382,11 +382,8 @@ static void ip6_dst_destroy(struct dst_entry *dst)
 		in6_dev_put(idev);
 	}
 
-	rcu_read_lock();
-	from = rcu_dereference(rt->from);
-	rcu_assign_pointer(rt->from, NULL);
+	from = xchg((__force struct fib6_info **)&rt->from, NULL);
 	fib6_info_release(from);
-	rcu_read_unlock();
 }
 
 static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
@@ -1296,9 +1293,7 @@ static void rt6_remove_exception(struct rt6_exception_bucket *bucket,
 	/* purge completely the exception to allow releasing the held resources:
 	 * some [sk] cache may keep the dst around for unlimited time
 	 */
-	from = rcu_dereference_protected(rt6_ex->rt6i->from,
-					 lockdep_is_held(&rt6_exception_lock));
-	rcu_assign_pointer(rt6_ex->rt6i->from, NULL);
+	from = xchg((__force struct fib6_info **)&rt6_ex->rt6i->from, NULL);
 	fib6_info_release(from);
 	dst_dev_put(&rt6_ex->rt6i->dst);
 
-- 
2.20.1


From 24927967316ddaf21de5dd3c52bc3fc9ca303931 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 27 Apr 2019 16:49:06 -0700
Subject: [PATCH 04/19] ipv6/flowlabel: wait rcu grace period before put_pid()

[ Upstream commit 6c0afef5fb0c27758f4d52b2210c61b6bd8b4470 ]

syzbot was able to catch a use-after-free read in pid_nr_ns() [1]

ip6fl_seq_show() seems to use RCU protection, dereferencing fl->owner.pid
but fl_free() releases fl->owner.pid before rcu grace period is started.

[1]

BUG: KASAN: use-after-free in pid_nr_ns+0x128/0x140 kernel/pid.c:407
Read of size 4 at addr ffff888094012a04 by task syz-executor.0/18087

CPU: 0 PID: 18087 Comm: syz-executor.0 Not tainted 5.1.0-rc6+ #89
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 print_address_description.cold+0x7c/0x20d mm/kasan/report.c:187
 kasan_report.cold+0x1b/0x40 mm/kasan/report.c:317
 __asan_report_load4_noabort+0x14/0x20 mm/kasan/generic_report.c:131
 pid_nr_ns+0x128/0x140 kernel/pid.c:407
 ip6fl_seq_show+0x2f8/0x4f0 net/ipv6/ip6_flowlabel.c:794
 seq_read+0xad3/0x1130 fs/seq_file.c:268
 proc_reg_read+0x1fe/0x2c0 fs/proc/inode.c:227
 do_loop_readv_writev fs/read_write.c:701 [inline]
 do_loop_readv_writev fs/read_write.c:688 [inline]
 do_iter_read+0x4a9/0x660 fs/read_write.c:922
 vfs_readv+0xf0/0x160 fs/read_write.c:984
 kernel_readv fs/splice.c:358 [inline]
 default_file_splice_read+0x475/0x890 fs/splice.c:413
 do_splice_to+0x12a/0x190 fs/splice.c:876
 splice_direct_to_actor+0x2d2/0x970 fs/splice.c:953
 do_splice_direct+0x1da/0x2a0 fs/splice.c:1062
 do_sendfile+0x597/0xd00 fs/read_write.c:1443
 __do_sys_sendfile64 fs/read_write.c:1498 [inline]
 __se_sys_sendfile64 fs/read_write.c:1490 [inline]
 __x64_sys_sendfile64+0x15a/0x220 fs/read_write.c:1490
 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x458da9
Code: ad b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f300d24bc78 EFLAGS: 00000246 ORIG_RAX: 0000000000000028
RAX: ffffffffffffffda RBX: 0000000000000004 RCX: 0000000000458da9
RDX: 00000000200000c0 RSI: 0000000000000008 RDI: 0000000000000007
RBP: 000000000073bf00 R08: 0000000000000000 R09: 0000000000000000
R10: 000000000000005a R11: 0000000000000246 R12: 00007f300d24c6d4
R13: 00000000004c5fa3 R14: 00000000004da748 R15: 00000000ffffffff

Allocated by task 17543:
 save_stack+0x45/0xd0 mm/kasan/common.c:75
 set_track mm/kasan/common.c:87 [inline]
 __kasan_kmalloc mm/kasan/common.c:497 [inline]
 __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:470
 kasan_slab_alloc+0xf/0x20 mm/kasan/common.c:505
 slab_post_alloc_hook mm/slab.h:437 [inline]
 slab_alloc mm/slab.c:3393 [inline]
 kmem_cache_alloc+0x11a/0x6f0 mm/slab.c:3555
 alloc_pid+0x55/0x8f0 kernel/pid.c:168
 copy_process.part.0+0x3b08/0x7980 kernel/fork.c:1932
 copy_process kernel/fork.c:1709 [inline]
 _do_fork+0x257/0xfd0 kernel/fork.c:2226
 __do_sys_clone kernel/fork.c:2333 [inline]
 __se_sys_clone kernel/fork.c:2327 [inline]
 __x64_sys_clone+0xbf/0x150 kernel/fork.c:2327
 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Freed by task 7789:
 save_stack+0x45/0xd0 mm/kasan/common.c:75
 set_track mm/kasan/common.c:87 [inline]
 __kasan_slab_free+0x102/0x150 mm/kasan/common.c:459
 kasan_slab_free+0xe/0x10 mm/kasan/common.c:467
 __cache_free mm/slab.c:3499 [inline]
 kmem_cache_free+0x86/0x260 mm/slab.c:3765
 put_pid.part.0+0x111/0x150 kernel/pid.c:111
 put_pid+0x20/0x30 kernel/pid.c:105
 fl_free+0xbe/0xe0 net/ipv6/ip6_flowlabel.c:102
 ip6_fl_gc+0x295/0x3e0 net/ipv6/ip6_flowlabel.c:152
 call_timer_fn+0x190/0x720 kernel/time/timer.c:1325
 expire_timers kernel/time/timer.c:1362 [inline]
 __run_timers kernel/time/timer.c:1681 [inline]
 __run_timers kernel/time/timer.c:1649 [inline]
 run_timer_softirq+0x652/0x1700 kernel/time/timer.c:1694
 __do_softirq+0x266/0x95a kernel/softirq.c:293

The buggy address belongs to the object at ffff888094012a00
 which belongs to the cache pid_2 of size 88
The buggy address is located 4 bytes inside of
 88-byte region [ffff888094012a00, ffff888094012a58)
The buggy address belongs to the page:
page:ffffea0002500480 count:1 mapcount:0 mapping:ffff88809a483080 index:0xffff888094012980
flags: 0x1fffc0000000200(slab)
raw: 01fffc0000000200 ffffea00018a3508 ffffea0002524a88 ffff88809a483080
raw: ffff888094012980 ffff888094012000 000000010000001b 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff888094012900: fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc fc
 ffff888094012980: fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc fc
>ffff888094012a00: fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc fc
                   ^
 ffff888094012a80: fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc fc
 ffff888094012b00: fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc fc

Fixes: 4f82f45730c6 ("net ip6 flowlabel: Make owner a union of struct pid * and kuid_t")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_flowlabel.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index cb54a8a3c273..23a525c0a9be 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -94,15 +94,21 @@ static struct ip6_flowlabel *fl_lookup(struct net *net, __be32 label)
 	return fl;
 }
 
+static void fl_free_rcu(struct rcu_head *head)
+{
+	struct ip6_flowlabel *fl = container_of(head, struct ip6_flowlabel, rcu);
+
+	if (fl->share == IPV6_FL_S_PROCESS)
+		put_pid(fl->owner.pid);
+	kfree(fl->opt);
+	kfree(fl);
+}
+
 
 static void fl_free(struct ip6_flowlabel *fl)
 {
-	if (fl) {
-		if (fl->share == IPV6_FL_S_PROCESS)
-			put_pid(fl->owner.pid);
-		kfree(fl->opt);
-		kfree_rcu(fl, rcu);
-	}
+	if (fl)
+		call_rcu(&fl->rcu, fl_free_rcu);
 }
 
 static void fl_release(struct ip6_flowlabel *fl)
-- 
2.20.1


From 09506b42edcf9eff1c5ca0c2d1a7864d94c61308 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Thu, 25 Apr 2019 12:06:54 -0400
Subject: [PATCH 05/19] ipv6: invert flowlabel sharing check in process and
 user mode

[ Upstream commit 95c169251bf734aa555a1e8043e4d88ec97a04ec ]

A request for a flowlabel fails in process or user exclusive mode must
fail if the caller pid or uid does not match. Invert the test.

Previously, the test was unsafe wrt PID recycling, but indeed tested
for inequality: fl1->owner != fl->owner

Fixes: 4f82f45730c68 ("net ip6 flowlabel: Make owner a union of struct pid* and kuid_t")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_flowlabel.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 23a525c0a9be..be5f3d7ceb96 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -639,9 +639,9 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
 				if (fl1->share == IPV6_FL_S_EXCL ||
 				    fl1->share != fl->share ||
 				    ((fl1->share == IPV6_FL_S_PROCESS) &&
-				     (fl1->owner.pid == fl->owner.pid)) ||
+				     (fl1->owner.pid != fl->owner.pid)) ||
 				    ((fl1->share == IPV6_FL_S_USER) &&
-				     uid_eq(fl1->owner.uid, fl->owner.uid)))
+				     !uid_eq(fl1->owner.uid, fl->owner.uid)))
 					goto release;
 
 				err = -ENOMEM;
-- 
2.20.1


From f11aa6fe401c5075b8b36e5616867ba84be73331 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 30 Apr 2019 06:27:58 -0700
Subject: [PATCH 06/19] l2ip: fix possible use-after-free

[ Upstream commit a622b40035d16196bf19b2b33b854862595245fc ]

Before taking a refcount on a rcu protected structure,
we need to make sure the refcount is not zero.

syzbot reported :

refcount_t: increment on 0; use-after-free.
WARNING: CPU: 1 PID: 23533 at lib/refcount.c:156 refcount_inc_checked lib/refcount.c:156 [inline]
WARNING: CPU: 1 PID: 23533 at lib/refcount.c:156 refcount_inc_checked+0x61/0x70 lib/refcount.c:154
Kernel panic - not syncing: panic_on_warn set ...
CPU: 1 PID: 23533 Comm: syz-executor.2 Not tainted 5.1.0-rc7+ #93
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 panic+0x2cb/0x65c kernel/panic.c:214
 __warn.cold+0x20/0x45 kernel/panic.c:571
 report_bug+0x263/0x2b0 lib/bug.c:186
 fixup_bug arch/x86/kernel/traps.c:179 [inline]
 fixup_bug arch/x86/kernel/traps.c:174 [inline]
 do_error_trap+0x11b/0x200 arch/x86/kernel/traps.c:272
 do_invalid_op+0x37/0x50 arch/x86/kernel/traps.c:291
 invalid_op+0x14/0x20 arch/x86/entry/entry_64.S:973
RIP: 0010:refcount_inc_checked lib/refcount.c:156 [inline]
RIP: 0010:refcount_inc_checked+0x61/0x70 lib/refcount.c:154
Code: 1d 98 2b 2a 06 31 ff 89 de e8 db 2c 40 fe 84 db 75 dd e8 92 2b 40 fe 48 c7 c7 20 7a a1 87 c6 05 78 2b 2a 06 01 e8 7d d9 12 fe <0f> 0b eb c1 90 90 90 90 90 90 90 90 90 90 90 55 48 89 e5 41 57 41
RSP: 0018:ffff888069f0fba8 EFLAGS: 00010286
RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000
RDX: 000000000000f353 RSI: ffffffff815afcb6 RDI: ffffed100d3e1f67
RBP: ffff888069f0fbb8 R08: ffff88809b1845c0 R09: ffffed1015d23ef1
R10: ffffed1015d23ef0 R11: ffff8880ae91f787 R12: ffff8880a8f26968
R13: 0000000000000004 R14: dffffc0000000000 R15: ffff8880a49a6440
 l2tp_tunnel_inc_refcount net/l2tp/l2tp_core.h:240 [inline]
 l2tp_tunnel_get+0x250/0x580 net/l2tp/l2tp_core.c:173
 pppol2tp_connect+0xc00/0x1c70 net/l2tp/l2tp_ppp.c:702
 __sys_connect+0x266/0x330 net/socket.c:1808
 __do_sys_connect net/socket.c:1819 [inline]
 __se_sys_connect net/socket.c:1816 [inline]
 __x64_sys_connect+0x73/0xb0 net/socket.c:1816

Fixes: 54652eb12c1b ("l2tp: hold tunnel while looking up sessions in l2tp_netlink")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index fed6becc5daf..fa789c082c3e 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -169,8 +169,8 @@ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id)
 
 	rcu_read_lock_bh();
 	list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
-		if (tunnel->tunnel_id == tunnel_id) {
-			l2tp_tunnel_inc_refcount(tunnel);
+		if (tunnel->tunnel_id == tunnel_id &&
+		    refcount_inc_not_zero(&tunnel->ref_count)) {
 			rcu_read_unlock_bh();
 
 			return tunnel;
@@ -190,8 +190,8 @@ struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth)
 
 	rcu_read_lock_bh();
 	list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
-		if (++count > nth) {
-			l2tp_tunnel_inc_refcount(tunnel);
+		if (++count > nth &&
+		    refcount_inc_not_zero(&tunnel->ref_count)) {
 			rcu_read_unlock_bh();
 			return tunnel;
 		}
-- 
2.20.1


From bf53b326b7d1a320676c4fcf20065bf5688ec2ce Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 23 Apr 2019 09:43:26 -0700
Subject: [PATCH 07/19] l2tp: use rcu_dereference_sk_user_data() in
 l2tp_udp_encap_recv()

[ Upstream commit c1c477217882c610a2ba0268f5faf36c9c092528 ]

Canonical way to fetch sk_user_data from an encap_rcv() handler called
from UDP stack in rcu protected section is to use rcu_dereference_sk_user_data(),
otherwise compiler might read it multiple times.

Fixes: d00fa9adc528 ("il2tp: fix races with tunnel socket close")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: James Chapman <jchapman@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index fa789c082c3e..52b5a2797c0c 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -909,7 +909,7 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 {
 	struct l2tp_tunnel *tunnel;
 
-	tunnel = l2tp_tunnel(sk);
+	tunnel = rcu_dereference_sk_user_data(sk);
 	if (tunnel == NULL)
 		goto pass_up;
 
-- 
2.20.1


From 5844ae77d50c9688836d81aa12ca4a1e5aa4e951 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Tue, 30 Apr 2019 13:44:19 +0300
Subject: [PATCH 08/19] net: dsa: bcm_sf2: fix buffer overflow doing set_rxnfc

[ Upstream commit f949a12fd697479f68d99dc65e9bbab68ee49043 ]

The "fs->location" is a u32 that comes from the user in ethtool_set_rxnfc().
We can't pass unclamped values to test_bit() or it results in an out of
bounds access beyond the end of the bitmap.

Fixes: 7318166cacad ("net: dsa: bcm_sf2: Add support for ethtool::rxnfc")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2_cfp.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c
index 47c5f272a084..21db1804e85d 100644
--- a/drivers/net/dsa/bcm_sf2_cfp.c
+++ b/drivers/net/dsa/bcm_sf2_cfp.c
@@ -742,6 +742,9 @@ static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
 	     fs->m_ext.data[1]))
 		return -EINVAL;
 
+	if (fs->location != RX_CLS_LOC_ANY && fs->location >= CFP_NUM_RULES)
+		return -EINVAL;
+
 	if (fs->location != RX_CLS_LOC_ANY &&
 	    test_bit(fs->location, priv->cfp.used))
 		return -EBUSY;
@@ -836,6 +839,9 @@ static int bcm_sf2_cfp_rule_del(struct bcm_sf2_priv *priv, int port,
 	u32 next_loc = 0;
 	int ret;
 
+	if (loc >= CFP_NUM_RULES)
+		return -EINVAL;
+
 	/* Refuse deleting unused rules, and those that are not unique since
 	 * that could leave IPv6 rules with one of the chained rule in the
 	 * table.
-- 
2.20.1


From 8927315f0e58c6eb5e4605435b24adaeda7bc9bf Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Thu, 25 Apr 2019 00:33:00 +0200
Subject: [PATCH 09/19] net: phy: marvell: Fix buffer overrun with stats
 counters

[ Upstream commit fdfdf86720a34527f777cbe0d8599bf0528fa146 ]

marvell_get_sset_count() returns how many statistics counters there
are. If the PHY supports fibre, there are 3, otherwise two.

marvell_get_strings() does not make this distinction, and always
returns 3 strings. This then often results in writing past the end
of the buffer for the strings.

Fixes: 2170fef78a40 ("Marvell phy: add field to get errors from fiber link.")
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/marvell.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index 73813c7afa49..bb6107f3b947 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -1513,9 +1513,10 @@ static int marvell_get_sset_count(struct phy_device *phydev)
 
 static void marvell_get_strings(struct phy_device *phydev, u8 *data)
 {
+	int count = marvell_get_sset_count(phydev);
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(marvell_hw_stats); i++) {
+	for (i = 0; i < count; i++) {
 		strlcpy(data + i * ETH_GSTRING_LEN,
 			marvell_hw_stats[i].string, ETH_GSTRING_LEN);
 	}
@@ -1543,9 +1544,10 @@ static u64 marvell_get_stat(struct phy_device *phydev, int i)
 static void marvell_get_stats(struct phy_device *phydev,
 			      struct ethtool_stats *stats, u64 *data)
 {
+	int count = marvell_get_sset_count(phydev);
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(marvell_hw_stats); i++)
+	for (i = 0; i < count; i++)
 		data[i] = marvell_get_stat(phydev, i);
 }
 
-- 
2.20.1


From 9f3250019c4f406d17241856c041d467226d96ed Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 29 Apr 2019 12:19:12 -0700
Subject: [PATCH 10/19] net/tls: avoid NULL pointer deref on nskb->sk in
 fallback

[ Upstream commit 2dcb003314032c6efb13a065ffae60d164b2dd35 ]

update_chksum() accesses nskb->sk before it has been set
by complete_skb(), move the init up.

Fixes: e8f69799810c ("net/tls: Add generic NIC offload infrastructure")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_device_fallback.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c
index ef8934fd8698..426dd97725e4 100644
--- a/net/tls/tls_device_fallback.c
+++ b/net/tls/tls_device_fallback.c
@@ -200,13 +200,14 @@ static void complete_skb(struct sk_buff *nskb, struct sk_buff *skb, int headln)
 
 	skb_put(nskb, skb->len);
 	memcpy(nskb->data, skb->data, headln);
-	update_chksum(nskb, headln);
 
 	nskb->destructor = skb->destructor;
 	nskb->sk = sk;
 	skb->destructor = NULL;
 	skb->sk = NULL;
 
+	update_chksum(nskb, headln);
+
 	delta = nskb->truesize - skb->truesize;
 	if (likely(delta < 0))
 		WARN_ON_ONCE(refcount_sub_and_test(-delta, &sk->sk_wmem_alloc));
-- 
2.20.1


From dc292ca0eeb72e029a644ea4393bd3c83b92b73c Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 30 Apr 2019 08:34:08 +0100
Subject: [PATCH 11/19] rxrpc: Fix net namespace cleanup

[ Upstream commit b13023421b5179413421333f602850914f6a7ad8 ]

In rxrpc_destroy_all_calls(), there are two phases: (1) make sure the
->calls list is empty, emitting error messages if not, and (2) wait for the
RCU cleanup to happen on outstanding calls (ie. ->nr_calls becomes 0).

To avoid taking the call_lock, the function prechecks ->calls and if empty,
it returns to avoid taking the lock - this is wrong, however: it still
needs to go and do the second phase and wait for ->nr_calls to become 0.

Without this, the rxrpc_net struct may get deallocated before we get to the
RCU cleanup for the last calls.  This can lead to:

  Slab corruption (Not tainted): kmalloc-16k start=ffff88802b178000, len=16384
  050: 6b 6b 6b 6b 6b 6b 6b 6b 61 6b 6b 6b 6b 6b 6b 6b  kkkkkkkkakkkkkkk

Note the "61" at offset 0x58.  This corresponds to the ->nr_calls member of
struct rxrpc_net (which is >9k in size, and thus allocated out of the 16k
slab).

Fix this by flipping the condition on the if-statement, putting the locked
section inside the if-body and dropping the return from there.  The
function will then always go on to wait for the RCU cleanup on outstanding
calls.

Fixes: 2baec2c3f854 ("rxrpc: Support network namespacing")
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/call_object.c | 32 ++++++++++++++++----------------
 1 file changed, 16 insertions(+), 16 deletions(-)

diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 8f1a8f85b1f9..215f4d98baa0 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -701,30 +701,30 @@ void rxrpc_destroy_all_calls(struct rxrpc_net *rxnet)
 
 	_enter("");
 
-	if (list_empty(&rxnet->calls))
-		return;
+	if (!list_empty(&rxnet->calls)) {
+		write_lock(&rxnet->call_lock);
 
-	write_lock(&rxnet->call_lock);
+		while (!list_empty(&rxnet->calls)) {
+			call = list_entry(rxnet->calls.next,
+					  struct rxrpc_call, link);
+			_debug("Zapping call %p", call);
 
-	while (!list_empty(&rxnet->calls)) {
-		call = list_entry(rxnet->calls.next, struct rxrpc_call, link);
-		_debug("Zapping call %p", call);
+			rxrpc_see_call(call);
+			list_del_init(&call->link);
 
-		rxrpc_see_call(call);
-		list_del_init(&call->link);
+			pr_err("Call %p still in use (%d,%s,%lx,%lx)!\n",
+			       call, atomic_read(&call->usage),
+			       rxrpc_call_states[call->state],
+			       call->flags, call->events);
 
-		pr_err("Call %p still in use (%d,%s,%lx,%lx)!\n",
-		       call, atomic_read(&call->usage),
-		       rxrpc_call_states[call->state],
-		       call->flags, call->events);
+			write_unlock(&rxnet->call_lock);
+			cond_resched();
+			write_lock(&rxnet->call_lock);
+		}
 
 		write_unlock(&rxnet->call_lock);
-		cond_resched();
-		write_lock(&rxnet->call_lock);
 	}
 
-	write_unlock(&rxnet->call_lock);
-
 	atomic_dec(&rxnet->nr_calls);
 	wait_var_event(&rxnet->nr_calls, !atomic_read(&rxnet->nr_calls));
 }
-- 
2.20.1


From 4b158f1705503922fdd82f01f31b71c44e376c21 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 29 Apr 2019 14:16:19 +0800
Subject: [PATCH 12/19] sctp: avoid running the sctp state machine recursively

[ Upstream commit fbd019737d71e405f86549fd738f81e2ff3dd073 ]

Ying triggered a call trace when doing an asconf testing:

  BUG: scheduling while atomic: swapper/12/0/0x10000100
  Call Trace:
   <IRQ>  [<ffffffffa4375904>] dump_stack+0x19/0x1b
   [<ffffffffa436fcaf>] __schedule_bug+0x64/0x72
   [<ffffffffa437b93a>] __schedule+0x9ba/0xa00
   [<ffffffffa3cd5326>] __cond_resched+0x26/0x30
   [<ffffffffa437bc4a>] _cond_resched+0x3a/0x50
   [<ffffffffa3e22be8>] kmem_cache_alloc_node+0x38/0x200
   [<ffffffffa423512d>] __alloc_skb+0x5d/0x2d0
   [<ffffffffc0995320>] sctp_packet_transmit+0x610/0xa20 [sctp]
   [<ffffffffc098510e>] sctp_outq_flush+0x2ce/0xc00 [sctp]
   [<ffffffffc098646c>] sctp_outq_uncork+0x1c/0x20 [sctp]
   [<ffffffffc0977338>] sctp_cmd_interpreter.isra.22+0xc8/0x1460 [sctp]
   [<ffffffffc0976ad1>] sctp_do_sm+0xe1/0x350 [sctp]
   [<ffffffffc099443d>] sctp_primitive_ASCONF+0x3d/0x50 [sctp]
   [<ffffffffc0977384>] sctp_cmd_interpreter.isra.22+0x114/0x1460 [sctp]
   [<ffffffffc0976ad1>] sctp_do_sm+0xe1/0x350 [sctp]
   [<ffffffffc097b3a4>] sctp_assoc_bh_rcv+0xf4/0x1b0 [sctp]
   [<ffffffffc09840f1>] sctp_inq_push+0x51/0x70 [sctp]
   [<ffffffffc099732b>] sctp_rcv+0xa8b/0xbd0 [sctp]

As it shows, the first sctp_do_sm() running under atomic context (NET_RX
softirq) invoked sctp_primitive_ASCONF() that uses GFP_KERNEL flag later,
and this flag is supposed to be used in non-atomic context only. Besides,
sctp_do_sm() was called recursively, which is not expected.

Vlad tried to fix this recursive call in Commit c0786693404c ("sctp: Fix
oops when sending queued ASCONF chunks") by introducing a new command
SCTP_CMD_SEND_NEXT_ASCONF. But it didn't work as this command is still
used in the first sctp_do_sm() call, and sctp_primitive_ASCONF() will
be called in this command again.

To avoid calling sctp_do_sm() recursively, we send the next queued ASCONF
not by sctp_primitive_ASCONF(), but by sctp_sf_do_prm_asconf() in the 1st
sctp_do_sm() directly.

Reported-by: Ying Xu <yinxu@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/command.h |  1 -
 net/sctp/sm_sideeffect.c   | 29 -----------------------------
 net/sctp/sm_statefuns.c    | 35 +++++++++++++++++++++++++++--------
 3 files changed, 27 insertions(+), 38 deletions(-)

diff --git a/include/net/sctp/command.h b/include/net/sctp/command.h
index 6640f84fe536..6d5beac29bc1 100644
--- a/include/net/sctp/command.h
+++ b/include/net/sctp/command.h
@@ -105,7 +105,6 @@ enum sctp_verb {
 	SCTP_CMD_T1_RETRAN,	 /* Mark for retransmission after T1 timeout  */
 	SCTP_CMD_UPDATE_INITTAG, /* Update peer inittag */
 	SCTP_CMD_SEND_MSG,	 /* Send the whole use message */
-	SCTP_CMD_SEND_NEXT_ASCONF, /* Send the next ASCONF after ACK */
 	SCTP_CMD_PURGE_ASCONF_QUEUE, /* Purge all asconf queues.*/
 	SCTP_CMD_SET_ASOC,	 /* Restore association context */
 	SCTP_CMD_LAST
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index 85d393090238..48fe8f01265f 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -1112,32 +1112,6 @@ static void sctp_cmd_send_msg(struct sctp_association *asoc,
 }
 
 
-/* Sent the next ASCONF packet currently stored in the association.
- * This happens after the ASCONF_ACK was succeffully processed.
- */
-static void sctp_cmd_send_asconf(struct sctp_association *asoc)
-{
-	struct net *net = sock_net(asoc->base.sk);
-
-	/* Send the next asconf chunk from the addip chunk
-	 * queue.
-	 */
-	if (!list_empty(&asoc->addip_chunk_list)) {
-		struct list_head *entry = asoc->addip_chunk_list.next;
-		struct sctp_chunk *asconf = list_entry(entry,
-						struct sctp_chunk, list);
-		list_del_init(entry);
-
-		/* Hold the chunk until an ASCONF_ACK is received. */
-		sctp_chunk_hold(asconf);
-		if (sctp_primitive_ASCONF(net, asoc, asconf))
-			sctp_chunk_free(asconf);
-		else
-			asoc->addip_last_asconf = asconf;
-	}
-}
-
-
 /* These three macros allow us to pull the debugging code out of the
  * main flow of sctp_do_sm() to keep attention focused on the real
  * functionality there.
@@ -1783,9 +1757,6 @@ static int sctp_cmd_interpreter(enum sctp_event event_type,
 			}
 			sctp_cmd_send_msg(asoc, cmd->obj.msg, gfp);
 			break;
-		case SCTP_CMD_SEND_NEXT_ASCONF:
-			sctp_cmd_send_asconf(asoc);
-			break;
 		case SCTP_CMD_PURGE_ASCONF_QUEUE:
 			sctp_asconf_queue_teardown(asoc);
 			break;
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index c9ae3404b1bb..713a669d2058 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -3824,6 +3824,29 @@ enum sctp_disposition sctp_sf_do_asconf(struct net *net,
 	return SCTP_DISPOSITION_CONSUME;
 }
 
+static enum sctp_disposition sctp_send_next_asconf(
+					struct net *net,
+					const struct sctp_endpoint *ep,
+					struct sctp_association *asoc,
+					const union sctp_subtype type,
+					struct sctp_cmd_seq *commands)
+{
+	struct sctp_chunk *asconf;
+	struct list_head *entry;
+
+	if (list_empty(&asoc->addip_chunk_list))
+		return SCTP_DISPOSITION_CONSUME;
+
+	entry = asoc->addip_chunk_list.next;
+	asconf = list_entry(entry, struct sctp_chunk, list);
+
+	list_del_init(entry);
+	sctp_chunk_hold(asconf);
+	asoc->addip_last_asconf = asconf;
+
+	return sctp_sf_do_prm_asconf(net, ep, asoc, type, asconf, commands);
+}
+
 /*
  * ADDIP Section 4.3 General rules for address manipulation
  * When building TLV parameters for the ASCONF Chunk that will add or
@@ -3915,14 +3938,10 @@ enum sctp_disposition sctp_sf_do_asconf_ack(struct net *net,
 				SCTP_TO(SCTP_EVENT_TIMEOUT_T4_RTO));
 
 		if (!sctp_process_asconf_ack((struct sctp_association *)asoc,
-					     asconf_ack)) {
-			/* Successfully processed ASCONF_ACK.  We can
-			 * release the next asconf if we have one.
-			 */
-			sctp_add_cmd_sf(commands, SCTP_CMD_SEND_NEXT_ASCONF,
-					SCTP_NULL());
-			return SCTP_DISPOSITION_CONSUME;
-		}
+					     asconf_ack))
+			return sctp_send_next_asconf(net, ep,
+					(struct sctp_association *)asoc,
+							type, commands);
 
 		abort = sctp_make_abort(asoc, asconf_ack,
 					sizeof(struct sctp_errhdr));
-- 
2.20.1


From 7c54b44ad8b05af6be1ae6e539b2fa48b5d97a20 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Tue, 30 Apr 2019 10:46:10 +0800
Subject: [PATCH 13/19] selftests: fib_rule_tests: print the result and return
 1 if any tests failed

[ Upstream commit f68d7c44e76532e46f292ad941aa3706cb9e6e40 ]

Fixes: 65b2b4939a64 ("selftests: net: initial fib rule tests")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/fib_rule_tests.sh | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh
index d4cfb6a7a086..d84193bdc307 100755
--- a/tools/testing/selftests/net/fib_rule_tests.sh
+++ b/tools/testing/selftests/net/fib_rule_tests.sh
@@ -27,6 +27,7 @@ log_test()
 		nsuccess=$((nsuccess+1))
 		printf "\n    TEST: %-50s  [ OK ]\n" "${msg}"
 	else
+		ret=1
 		nfail=$((nfail+1))
 		printf "\n    TEST: %-50s  [FAIL]\n" "${msg}"
 		if [ "${PAUSE_ON_FAIL}" = "yes" ]; then
@@ -245,4 +246,9 @@ setup
 run_fibrule_tests
 cleanup
 
+if [ "$TESTS" != "none" ]; then
+	printf "\nTests passed: %3d\n" ${nsuccess}
+	printf "Tests failed: %3d\n"   ${nfail}
+fi
+
 exit $ret
-- 
2.20.1


From 2dba3da435b8d7d8f36c7e774e274d16ef674076 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Mon, 29 Apr 2019 11:53:18 -0400
Subject: [PATCH 14/19] packet: validate msg_namelen in send directly

[ Upstream commit 486efdc8f6ce802b27e15921d2353cc740c55451 ]

Packet sockets in datagram mode take a destination address. Verify its
length before passing to dev_hard_header.

Prior to 2.6.14-rc3, the send code ignored sll_halen. This is
established behavior. Directly compare msg_namelen to dev->addr_len.

Change v1->v2: initialize addr in all paths

Fixes: 6b8d95f1795c4 ("packet: validate address length if non-zero")
Suggested-by: David Laight <David.Laight@aculab.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 24 ++++++++++++++----------
 1 file changed, 14 insertions(+), 10 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index a0d295478e69..ebbb30064251 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2603,8 +2603,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 	void *ph;
 	DECLARE_SOCKADDR(struct sockaddr_ll *, saddr, msg->msg_name);
 	bool need_wait = !(msg->msg_flags & MSG_DONTWAIT);
+	unsigned char *addr = NULL;
 	int tp_len, size_max;
-	unsigned char *addr;
 	void *data;
 	int len_sum = 0;
 	int status = TP_STATUS_AVAILABLE;
@@ -2615,7 +2615,6 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 	if (likely(saddr == NULL)) {
 		dev	= packet_cached_dev_get(po);
 		proto	= po->num;
-		addr	= NULL;
 	} else {
 		err = -EINVAL;
 		if (msg->msg_namelen < sizeof(struct sockaddr_ll))
@@ -2625,10 +2624,13 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 						sll_addr)))
 			goto out;
 		proto	= saddr->sll_protocol;
-		addr	= saddr->sll_halen ? saddr->sll_addr : NULL;
 		dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex);
-		if (addr && dev && saddr->sll_halen < dev->addr_len)
-			goto out_put;
+		if (po->sk.sk_socket->type == SOCK_DGRAM) {
+			if (dev && msg->msg_namelen < dev->addr_len +
+				   offsetof(struct sockaddr_ll, sll_addr))
+				goto out_put;
+			addr = saddr->sll_addr;
+		}
 	}
 
 	err = -ENXIO;
@@ -2800,7 +2802,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	struct sk_buff *skb;
 	struct net_device *dev;
 	__be16 proto;
-	unsigned char *addr;
+	unsigned char *addr = NULL;
 	int err, reserve = 0;
 	struct sockcm_cookie sockc;
 	struct virtio_net_hdr vnet_hdr = { 0 };
@@ -2817,7 +2819,6 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	if (likely(saddr == NULL)) {
 		dev	= packet_cached_dev_get(po);
 		proto	= po->num;
-		addr	= NULL;
 	} else {
 		err = -EINVAL;
 		if (msg->msg_namelen < sizeof(struct sockaddr_ll))
@@ -2825,10 +2826,13 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		if (msg->msg_namelen < (saddr->sll_halen + offsetof(struct sockaddr_ll, sll_addr)))
 			goto out;
 		proto	= saddr->sll_protocol;
-		addr	= saddr->sll_halen ? saddr->sll_addr : NULL;
 		dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex);
-		if (addr && dev && saddr->sll_halen < dev->addr_len)
-			goto out_unlock;
+		if (sock->type == SOCK_DGRAM) {
+			if (dev && msg->msg_namelen < dev->addr_len +
+				   offsetof(struct sockaddr_ll, sll_addr))
+				goto out_unlock;
+			addr = saddr->sll_addr;
+		}
 	}
 
 	err = -ENXIO;
-- 
2.20.1


From 08d5653948bf909014b66f7559b2fc4202ae5806 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Thu, 25 Apr 2019 22:31:50 -0400
Subject: [PATCH 15/19] bnxt_en: Improve multicast address setup logic.

[ Upstream commit b4e30e8e7ea1d1e35ffd64ca46f7d9a7f227b4bf ]

The driver builds a list of multicast addresses and sends it to the
firmware when the driver's ndo_set_rx_mode() is called.  In rare
cases, the firmware can fail this call if internal resources to
add multicast addresses are exhausted.  In that case, we should
try the call again by setting the ALL_MCAST flag which is more
guaranteed to succeed.

Fixes: c0c050c58d84 ("bnxt_en: New Broadcom ethernet driver.")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 581ad0a17d0c..02680357bb5f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -7441,8 +7441,15 @@ static int bnxt_cfg_rx_mode(struct bnxt *bp)
 
 skip_uc:
 	rc = bnxt_hwrm_cfa_l2_set_rx_mask(bp, 0);
+	if (rc && vnic->mc_list_count) {
+		netdev_info(bp->dev, "Failed setting MC filters rc: %d, turning on ALL_MCAST mode\n",
+			    rc);
+		vnic->rx_mask |= CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST;
+		vnic->mc_list_count = 0;
+		rc = bnxt_hwrm_cfa_l2_set_rx_mask(bp, 0);
+	}
 	if (rc)
-		netdev_err(bp->dev, "HWRM cfa l2 rx mask failure rc: %x\n",
+		netdev_err(bp->dev, "HWRM cfa l2 rx mask failure rc: %d\n",
 			   rc);
 
 	return rc;
-- 
2.20.1


From 307391c95f57bc107b6f7cde4293d1a435227b27 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Thu, 25 Apr 2019 22:31:51 -0400
Subject: [PATCH 16/19] bnxt_en: Free short FW command HWRM memory in error
 path in bnxt_init_one()

[ Upstream commit f9099d611449836a51a65f40ea7dc9cb5f2f665e ]

In the bnxt_init_one() error path, short FW command request memory
is not freed. This patch fixes it.

Fixes: e605db801bde ("bnxt_en: Support for Short Firmware Message")
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 02680357bb5f..90436c5abbc9 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -9084,6 +9084,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	bnxt_clear_int_mode(bp);
 
 init_err_pci_clean:
+	bnxt_free_hwrm_short_cmd_req(bp);
 	bnxt_free_hwrm_resources(bp);
 	bnxt_cleanup_pci(bp);
 
-- 
2.20.1


From cbe76ec735f531edb766210c346853724fbfda28 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Thu, 25 Apr 2019 22:31:55 -0400
Subject: [PATCH 17/19] bnxt_en: Fix uninitialized variable usage in
 bnxt_rx_pkt().

[ Upstream commit 0b397b17a4120cb80f7bf89eb30587b3dd9b0d1d ]

In bnxt_rx_pkt(), if the driver encounters BD errors, it will recycle
the buffers and jump to the end where the uninitailized variable "len"
is referenced.  Fix it by adding a new jump label that will skip
the length update.  This is the most correct fix since the length
may not be valid when we get this type of error.

Fixes: 6a8788f25625 ("bnxt_en: add support for software dynamic interrupt moderation")
Reported-by: Nathan Chancellor <natechancellor@gmail.com>
Cc: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Reviewed-by: Nathan Chancellor <natechancellor@gmail.com>
Tested-by: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 90436c5abbc9..de46331aefc1 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1584,7 +1584,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_napi *bnapi, u32 *raw_cons,
 			netdev_warn(bp->dev, "RX buffer error %x\n", rx_err);
 			bnxt_sched_reset(bp, rxr);
 		}
-		goto next_rx;
+		goto next_rx_no_len;
 	}
 
 	len = le32_to_cpu(rxcmp->rx_cmp_len_flags_type) >> RX_CMP_LEN_SHIFT;
@@ -1665,12 +1665,13 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_napi *bnapi, u32 *raw_cons,
 	rc = 1;
 
 next_rx:
-	rxr->rx_prod = NEXT_RX(prod);
-	rxr->rx_next_cons = NEXT_RX(cons);
-
 	cpr->rx_packets += 1;
 	cpr->rx_bytes += len;
 
+next_rx_no_len:
+	rxr->rx_prod = NEXT_RX(prod);
+	rxr->rx_next_cons = NEXT_RX(cons);
+
 next_rx_no_prod_no_len:
 	*raw_cons = tmp_raw_cons;
 
-- 
2.20.1


From a84734ffde3a34d333b43b275fa9e288e2ac6aaf Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu, 25 Apr 2019 17:35:09 -0700
Subject: [PATCH 18/19] net/tls: don't copy negative amounts of data in
 reencrypt

[ Upstream commit 97e1caa517e22d62a283b876fb8aa5f4672c83dd ]

There is no guarantee the record starts before the skb frags.
If we don't check for this condition copy amount will get
negative, leading to reads and writes to random memory locations.
Familiar hilarity ensues.

Fixes: 4799ac81e52a ("tls: Add rx inline crypto offload")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_device.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index c9588b682db4..8538ee22a582 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -600,14 +600,16 @@ static int tls_device_reencrypt(struct sock *sk, struct sk_buff *skb)
 	else
 		err = 0;
 
-	copy = min_t(int, skb_pagelen(skb) - offset,
-		     rxm->full_len - TLS_CIPHER_AES_GCM_128_TAG_SIZE);
+	if (skb_pagelen(skb) > offset) {
+		copy = min_t(int, skb_pagelen(skb) - offset,
+			     rxm->full_len - TLS_CIPHER_AES_GCM_128_TAG_SIZE);
 
-	if (skb->decrypted)
-		skb_store_bits(skb, offset, buf, copy);
+		if (skb->decrypted)
+			skb_store_bits(skb, offset, buf, copy);
 
-	offset += copy;
-	buf += copy;
+		offset += copy;
+		buf += copy;
+	}
 
 	skb_walk_frags(skb, skb_iter) {
 		copy = min_t(int, skb_iter->len,
-- 
2.20.1


From d98f48b7def51c09b91f044ebc8fefd9530571a2 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu, 25 Apr 2019 17:35:10 -0700
Subject: [PATCH 19/19] net/tls: fix copy to fragments in reencrypt

[ Upstream commit eb3d38d5adb520435d4e4af32529ccb13ccc9935 ]

Fragments may contain data from other records so we have to account
for that when we calculate the destination and max length of copy we
can perform.  Note that 'offset' is the offset within the message,
so it can't be passed as offset within the frag..

Here skb_store_bits() would have realised the call is wrong and
simply not copy data.

Fixes: 4799ac81e52a ("tls: Add rx inline crypto offload")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_device.c | 29 ++++++++++++++++++++++-------
 1 file changed, 22 insertions(+), 7 deletions(-)

diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 8538ee22a582..f4a19eac975d 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -569,7 +569,7 @@ void handle_device_resync(struct sock *sk, u32 seq, u64 rcd_sn)
 static int tls_device_reencrypt(struct sock *sk, struct sk_buff *skb)
 {
 	struct strp_msg *rxm = strp_msg(skb);
-	int err = 0, offset = rxm->offset, copy, nsg;
+	int err = 0, offset = rxm->offset, copy, nsg, data_len, pos;
 	struct sk_buff *skb_iter, *unused;
 	struct scatterlist sg[1];
 	char *orig_buf, *buf;
@@ -600,9 +600,10 @@ static int tls_device_reencrypt(struct sock *sk, struct sk_buff *skb)
 	else
 		err = 0;
 
+	data_len = rxm->full_len - TLS_CIPHER_AES_GCM_128_TAG_SIZE;
+
 	if (skb_pagelen(skb) > offset) {
-		copy = min_t(int, skb_pagelen(skb) - offset,
-			     rxm->full_len - TLS_CIPHER_AES_GCM_128_TAG_SIZE);
+		copy = min_t(int, skb_pagelen(skb) - offset, data_len);
 
 		if (skb->decrypted)
 			skb_store_bits(skb, offset, buf, copy);
@@ -611,16 +612,30 @@ static int tls_device_reencrypt(struct sock *sk, struct sk_buff *skb)
 		buf += copy;
 	}
 
+	pos = skb_pagelen(skb);
 	skb_walk_frags(skb, skb_iter) {
-		copy = min_t(int, skb_iter->len,
-			     rxm->full_len - offset + rxm->offset -
-			     TLS_CIPHER_AES_GCM_128_TAG_SIZE);
+		int frag_pos;
+
+		/* Practically all frags must belong to msg if reencrypt
+		 * is needed with current strparser and coalescing logic,
+		 * but strparser may "get optimized", so let's be safe.
+		 */
+		if (pos + skb_iter->len <= offset)
+			goto done_with_frag;
+		if (pos >= data_len + rxm->offset)
+			break;
+
+		frag_pos = offset - pos;
+		copy = min_t(int, skb_iter->len - frag_pos,
+			     data_len + rxm->offset - offset);
 
 		if (skb_iter->decrypted)
-			skb_store_bits(skb_iter, offset, buf, copy);
+			skb_store_bits(skb_iter, frag_pos, buf, copy);
 
 		offset += copy;
 		buf += copy;
+done_with_frag:
+		pos += skb_iter->len;
 	}
 
 free_buf:
-- 
2.20.1


[-- Attachment #3: net_50.mbox --]
[-- Type: Application/Octet-Stream, Size: 78372 bytes --]

From 53a720e1f54f889b5357581dbde2d192317f707e Mon Sep 17 00:00:00 2001
From: Shmulik Ladkani <shmulik@metanetworks.com>
Date: Mon, 29 Apr 2019 16:39:30 +0300
Subject: [PATCH 01/27] ipv4: ip_do_fragment: Preserve skb_iif during
 fragmentation

[ Upstream commit d2f0c961148f65bc73eda72b9fa3a4e80973cb49 ]

Previously, during fragmentation after forwarding, skb->skb_iif isn't
preserved, i.e. 'ip_copy_metadata' does not copy skb_iif from given
'from' skb.

As a result, ip_do_fragment's creates fragments with zero skb_iif,
leading to inconsistent behavior.

Assume for example an eBPF program attached at tc egress (post
forwarding) that examines __sk_buff->ingress_ifindex:
 - the correct iif is observed if forwarding path does not involve
   fragmentation/refragmentation
 - a bogus iif is observed if forwarding path involves
   fragmentation/refragmentatiom

Fix, by preserving skb_iif during 'ip_copy_metadata'.

Signed-off-by: Shmulik Ladkani <shmulik.ladkani@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_output.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index c80188875f39..e8bb2e85c5a4 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -519,6 +519,7 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	to->pkt_type = from->pkt_type;
 	to->priority = from->priority;
 	to->protocol = from->protocol;
+	to->skb_iif = from->skb_iif;
 	skb_dst_drop(to);
 	skb_dst_copy(to, from);
 	to->dev = from->dev;
-- 
2.20.1


From 068a5b04d8a45294562d557e5be6cb5f71ef5784 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Tue, 30 Apr 2019 10:45:12 -0700
Subject: [PATCH 02/27] ipv6: A few fixes on dereferencing rt->from

[ Upstream commit 886b7a50100a50f1cbd08a6f8ec5884dfbe082dc ]

It is a followup after the fix in
commit 9c69a1320515 ("route: Avoid crash from dereferencing NULL rt->from")

rt6_do_redirect():
1. NULL checking is needed on rt->from because a parallel
   fib6_info delete could happen that sets rt->from to NULL.
   (e.g. rt6_remove_exception() and fib6_drop_pcpu_from()).

2. fib6_info_hold() is not enough.  Same reason as (1).
   Meaning, holding dst->__refcnt cannot ensure
   rt->from is not NULL or rt->from->fib6_ref is not 0.

   Instead of using fib6_info_hold_safe() which ip6_rt_cache_alloc()
   is already doing, this patch chooses to extend the rcu section
   to keep "from" dereference-able after checking for NULL.

inet6_rtm_getroute():
1. NULL checking is also needed on rt->from for a similar reason.
   Note that inet6_rtm_getroute() is using RTNL_FLAG_DOIT_UNLOCKED.

Fixes: a68886a69180 ("net/ipv6: Make from in rt6_info rcu protected")
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Wei Wang <weiwan@google.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 38 ++++++++++++++++++--------------------
 1 file changed, 18 insertions(+), 20 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index b6a97115a906..9f132e471d7a 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3403,11 +3403,8 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
 
 	rcu_read_lock();
 	from = rcu_dereference(rt->from);
-	/* This fib6_info_hold() is safe here because we hold reference to rt
-	 * and rt already holds reference to fib6_info.
-	 */
-	fib6_info_hold(from);
-	rcu_read_unlock();
+	if (!from)
+		goto out;
 
 	nrt = ip6_rt_cache_alloc(from, &msg->dest, NULL);
 	if (!nrt)
@@ -3419,10 +3416,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
 
 	nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key;
 
-	/* No need to remove rt from the exception table if rt is
-	 * a cached route because rt6_insert_exception() will
-	 * takes care of it
-	 */
+	/* rt6_insert_exception() will take care of duplicated exceptions */
 	if (rt6_insert_exception(nrt, from)) {
 		dst_release_immediate(&nrt->dst);
 		goto out;
@@ -3435,7 +3429,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
 	call_netevent_notifiers(NETEVENT_REDIRECT, &netevent);
 
 out:
-	fib6_info_release(from);
+	rcu_read_unlock();
 	neigh_release(neigh);
 }
 
@@ -4957,16 +4951,20 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 
 	rcu_read_lock();
 	from = rcu_dereference(rt->from);
-
-	if (fibmatch)
-		err = rt6_fill_node(net, skb, from, NULL, NULL, NULL, iif,
-				    RTM_NEWROUTE, NETLINK_CB(in_skb).portid,
-				    nlh->nlmsg_seq, 0);
-	else
-		err = rt6_fill_node(net, skb, from, dst, &fl6.daddr,
-				    &fl6.saddr, iif, RTM_NEWROUTE,
-				    NETLINK_CB(in_skb).portid, nlh->nlmsg_seq,
-				    0);
+	if (from) {
+		if (fibmatch)
+			err = rt6_fill_node(net, skb, from, NULL, NULL, NULL,
+					    iif, RTM_NEWROUTE,
+					    NETLINK_CB(in_skb).portid,
+					    nlh->nlmsg_seq, 0);
+		else
+			err = rt6_fill_node(net, skb, from, dst, &fl6.daddr,
+					    &fl6.saddr, iif, RTM_NEWROUTE,
+					    NETLINK_CB(in_skb).portid,
+					    nlh->nlmsg_seq, 0);
+	} else {
+		err = -ENETUNREACH;
+	}
 	rcu_read_unlock();
 
 	if (err < 0) {
-- 
2.20.1


From a68c5de39c292f81b641dea868436889ae3dce95 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 28 Apr 2019 12:22:25 -0700
Subject: [PATCH 03/27] ipv6: fix races in ip6_dst_destroy()

[ Upstream commit 0e2338749192ce0e52e7174c5352f627632f478a ]

We had many syzbot reports that seem to be caused by use-after-free
of struct fib6_info.

ip6_dst_destroy(), fib6_drop_pcpu_from() and rt6_remove_exception()
are writers vs rt->from, and use non consistent synchronization among
themselves.

Switching to xchg() will solve the issues with no possible
lockdep issues.

BUG: KASAN: user-memory-access in atomic_dec_and_test include/asm-generic/atomic-instrumented.h:747 [inline]
BUG: KASAN: user-memory-access in fib6_info_release include/net/ip6_fib.h:294 [inline]
BUG: KASAN: user-memory-access in fib6_info_release include/net/ip6_fib.h:292 [inline]
BUG: KASAN: user-memory-access in fib6_drop_pcpu_from net/ipv6/ip6_fib.c:927 [inline]
BUG: KASAN: user-memory-access in fib6_purge_rt+0x4f6/0x670 net/ipv6/ip6_fib.c:960
Write of size 4 at addr 0000000000ffffb4 by task syz-executor.1/7649

CPU: 0 PID: 7649 Comm: syz-executor.1 Not tainted 5.1.0-rc6+ #183
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 kasan_report.cold+0x5/0x40 mm/kasan/report.c:321
 check_memory_region_inline mm/kasan/generic.c:185 [inline]
 check_memory_region+0x123/0x190 mm/kasan/generic.c:191
 kasan_check_write+0x14/0x20 mm/kasan/common.c:108
 atomic_dec_and_test include/asm-generic/atomic-instrumented.h:747 [inline]
 fib6_info_release include/net/ip6_fib.h:294 [inline]
 fib6_info_release include/net/ip6_fib.h:292 [inline]
 fib6_drop_pcpu_from net/ipv6/ip6_fib.c:927 [inline]
 fib6_purge_rt+0x4f6/0x670 net/ipv6/ip6_fib.c:960
 fib6_del_route net/ipv6/ip6_fib.c:1813 [inline]
 fib6_del+0xac2/0x10a0 net/ipv6/ip6_fib.c:1844
 fib6_clean_node+0x3a8/0x590 net/ipv6/ip6_fib.c:2006
 fib6_walk_continue+0x495/0x900 net/ipv6/ip6_fib.c:1928
 fib6_walk+0x9d/0x100 net/ipv6/ip6_fib.c:1976
 fib6_clean_tree+0xe0/0x120 net/ipv6/ip6_fib.c:2055
 __fib6_clean_all+0x118/0x2a0 net/ipv6/ip6_fib.c:2071
 fib6_clean_all+0x2b/0x40 net/ipv6/ip6_fib.c:2082
 rt6_sync_down_dev+0x134/0x150 net/ipv6/route.c:4057
 rt6_disable_ip+0x27/0x5f0 net/ipv6/route.c:4062
 addrconf_ifdown+0xa2/0x1220 net/ipv6/addrconf.c:3705
 addrconf_notify+0x19a/0x2260 net/ipv6/addrconf.c:3630
 notifier_call_chain+0xc7/0x240 kernel/notifier.c:93
 __raw_notifier_call_chain kernel/notifier.c:394 [inline]
 raw_notifier_call_chain+0x2e/0x40 kernel/notifier.c:401
 call_netdevice_notifiers_info+0x3f/0x90 net/core/dev.c:1753
 call_netdevice_notifiers_extack net/core/dev.c:1765 [inline]
 call_netdevice_notifiers net/core/dev.c:1779 [inline]
 dev_close_many+0x33f/0x6f0 net/core/dev.c:1522
 rollback_registered_many+0x43b/0xfd0 net/core/dev.c:8177
 rollback_registered+0x109/0x1d0 net/core/dev.c:8242
 unregister_netdevice_queue net/core/dev.c:9289 [inline]
 unregister_netdevice_queue+0x1ee/0x2c0 net/core/dev.c:9282
 unregister_netdevice include/linux/netdevice.h:2658 [inline]
 __tun_detach+0xd5b/0x1000 drivers/net/tun.c:727
 tun_detach drivers/net/tun.c:744 [inline]
 tun_chr_close+0xe0/0x180 drivers/net/tun.c:3443
 __fput+0x2e5/0x8d0 fs/file_table.c:278
 ____fput+0x16/0x20 fs/file_table.c:309
 task_work_run+0x14a/0x1c0 kernel/task_work.c:113
 exit_task_work include/linux/task_work.h:22 [inline]
 do_exit+0x90a/0x2fa0 kernel/exit.c:876
 do_group_exit+0x135/0x370 kernel/exit.c:980
 __do_sys_exit_group kernel/exit.c:991 [inline]
 __se_sys_exit_group kernel/exit.c:989 [inline]
 __x64_sys_exit_group+0x44/0x50 kernel/exit.c:989
 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x458da9
Code: ad b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007ffeafc2a6a8 EFLAGS: 00000246 ORIG_RAX: 00000000000000e7
RAX: ffffffffffffffda RBX: 000000000000001c RCX: 0000000000458da9
RDX: 0000000000412a80 RSI: 0000000000a54ef0 RDI: 0000000000000043
RBP: 00000000004be552 R08: 000000000000000c R09: 000000000004c0d1
R10: 0000000002341940 R11: 0000000000000246 R12: 00000000ffffffff
R13: 00007ffeafc2a7f0 R14: 000000000004c065 R15: 00007ffeafc2a800

Fixes: a68886a69180 ("net/ipv6: Make from in rt6_info rcu protected")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: David Ahern <dsahern@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Wei Wang <weiwan@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_fib.c | 4 +---
 net/ipv6/route.c   | 9 ++-------
 2 files changed, 3 insertions(+), 10 deletions(-)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 6613d8dbb0e5..91247a6fc67f 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -921,9 +921,7 @@ static void fib6_drop_pcpu_from(struct fib6_info *f6i,
 		if (pcpu_rt) {
 			struct fib6_info *from;
 
-			from = rcu_dereference_protected(pcpu_rt->from,
-					     lockdep_is_held(&table->tb6_lock));
-			rcu_assign_pointer(pcpu_rt->from, NULL);
+			from = xchg((__force struct fib6_info **)&pcpu_rt->from, NULL);
 			fib6_info_release(from);
 		}
 	}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 9f132e471d7a..59c90bba048c 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -379,11 +379,8 @@ static void ip6_dst_destroy(struct dst_entry *dst)
 		in6_dev_put(idev);
 	}
 
-	rcu_read_lock();
-	from = rcu_dereference(rt->from);
-	rcu_assign_pointer(rt->from, NULL);
+	from = xchg((__force struct fib6_info **)&rt->from, NULL);
 	fib6_info_release(from);
-	rcu_read_unlock();
 }
 
 static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
@@ -1288,9 +1285,7 @@ static void rt6_remove_exception(struct rt6_exception_bucket *bucket,
 	/* purge completely the exception to allow releasing the held resources:
 	 * some [sk] cache may keep the dst around for unlimited time
 	 */
-	from = rcu_dereference_protected(rt6_ex->rt6i->from,
-					 lockdep_is_held(&rt6_exception_lock));
-	rcu_assign_pointer(rt6_ex->rt6i->from, NULL);
+	from = xchg((__force struct fib6_info **)&rt6_ex->rt6i->from, NULL);
 	fib6_info_release(from);
 	dst_dev_put(&rt6_ex->rt6i->dst);
 
-- 
2.20.1


From 208f1b1c6a02d5af4a1e1161dbd0971cde446905 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 27 Apr 2019 16:49:06 -0700
Subject: [PATCH 04/27] ipv6/flowlabel: wait rcu grace period before put_pid()

[ Upstream commit 6c0afef5fb0c27758f4d52b2210c61b6bd8b4470 ]

syzbot was able to catch a use-after-free read in pid_nr_ns() [1]

ip6fl_seq_show() seems to use RCU protection, dereferencing fl->owner.pid
but fl_free() releases fl->owner.pid before rcu grace period is started.

[1]

BUG: KASAN: use-after-free in pid_nr_ns+0x128/0x140 kernel/pid.c:407
Read of size 4 at addr ffff888094012a04 by task syz-executor.0/18087

CPU: 0 PID: 18087 Comm: syz-executor.0 Not tainted 5.1.0-rc6+ #89
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 print_address_description.cold+0x7c/0x20d mm/kasan/report.c:187
 kasan_report.cold+0x1b/0x40 mm/kasan/report.c:317
 __asan_report_load4_noabort+0x14/0x20 mm/kasan/generic_report.c:131
 pid_nr_ns+0x128/0x140 kernel/pid.c:407
 ip6fl_seq_show+0x2f8/0x4f0 net/ipv6/ip6_flowlabel.c:794
 seq_read+0xad3/0x1130 fs/seq_file.c:268
 proc_reg_read+0x1fe/0x2c0 fs/proc/inode.c:227
 do_loop_readv_writev fs/read_write.c:701 [inline]
 do_loop_readv_writev fs/read_write.c:688 [inline]
 do_iter_read+0x4a9/0x660 fs/read_write.c:922
 vfs_readv+0xf0/0x160 fs/read_write.c:984
 kernel_readv fs/splice.c:358 [inline]
 default_file_splice_read+0x475/0x890 fs/splice.c:413
 do_splice_to+0x12a/0x190 fs/splice.c:876
 splice_direct_to_actor+0x2d2/0x970 fs/splice.c:953
 do_splice_direct+0x1da/0x2a0 fs/splice.c:1062
 do_sendfile+0x597/0xd00 fs/read_write.c:1443
 __do_sys_sendfile64 fs/read_write.c:1498 [inline]
 __se_sys_sendfile64 fs/read_write.c:1490 [inline]
 __x64_sys_sendfile64+0x15a/0x220 fs/read_write.c:1490
 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x458da9
Code: ad b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f300d24bc78 EFLAGS: 00000246 ORIG_RAX: 0000000000000028
RAX: ffffffffffffffda RBX: 0000000000000004 RCX: 0000000000458da9
RDX: 00000000200000c0 RSI: 0000000000000008 RDI: 0000000000000007
RBP: 000000000073bf00 R08: 0000000000000000 R09: 0000000000000000
R10: 000000000000005a R11: 0000000000000246 R12: 00007f300d24c6d4
R13: 00000000004c5fa3 R14: 00000000004da748 R15: 00000000ffffffff

Allocated by task 17543:
 save_stack+0x45/0xd0 mm/kasan/common.c:75
 set_track mm/kasan/common.c:87 [inline]
 __kasan_kmalloc mm/kasan/common.c:497 [inline]
 __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:470
 kasan_slab_alloc+0xf/0x20 mm/kasan/common.c:505
 slab_post_alloc_hook mm/slab.h:437 [inline]
 slab_alloc mm/slab.c:3393 [inline]
 kmem_cache_alloc+0x11a/0x6f0 mm/slab.c:3555
 alloc_pid+0x55/0x8f0 kernel/pid.c:168
 copy_process.part.0+0x3b08/0x7980 kernel/fork.c:1932
 copy_process kernel/fork.c:1709 [inline]
 _do_fork+0x257/0xfd0 kernel/fork.c:2226
 __do_sys_clone kernel/fork.c:2333 [inline]
 __se_sys_clone kernel/fork.c:2327 [inline]
 __x64_sys_clone+0xbf/0x150 kernel/fork.c:2327
 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Freed by task 7789:
 save_stack+0x45/0xd0 mm/kasan/common.c:75
 set_track mm/kasan/common.c:87 [inline]
 __kasan_slab_free+0x102/0x150 mm/kasan/common.c:459
 kasan_slab_free+0xe/0x10 mm/kasan/common.c:467
 __cache_free mm/slab.c:3499 [inline]
 kmem_cache_free+0x86/0x260 mm/slab.c:3765
 put_pid.part.0+0x111/0x150 kernel/pid.c:111
 put_pid+0x20/0x30 kernel/pid.c:105
 fl_free+0xbe/0xe0 net/ipv6/ip6_flowlabel.c:102
 ip6_fl_gc+0x295/0x3e0 net/ipv6/ip6_flowlabel.c:152
 call_timer_fn+0x190/0x720 kernel/time/timer.c:1325
 expire_timers kernel/time/timer.c:1362 [inline]
 __run_timers kernel/time/timer.c:1681 [inline]
 __run_timers kernel/time/timer.c:1649 [inline]
 run_timer_softirq+0x652/0x1700 kernel/time/timer.c:1694
 __do_softirq+0x266/0x95a kernel/softirq.c:293

The buggy address belongs to the object at ffff888094012a00
 which belongs to the cache pid_2 of size 88
The buggy address is located 4 bytes inside of
 88-byte region [ffff888094012a00, ffff888094012a58)
The buggy address belongs to the page:
page:ffffea0002500480 count:1 mapcount:0 mapping:ffff88809a483080 index:0xffff888094012980
flags: 0x1fffc0000000200(slab)
raw: 01fffc0000000200 ffffea00018a3508 ffffea0002524a88 ffff88809a483080
raw: ffff888094012980 ffff888094012000 000000010000001b 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff888094012900: fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc fc
 ffff888094012980: fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc fc
>ffff888094012a00: fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc fc
                   ^
 ffff888094012a80: fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc fc
 ffff888094012b00: fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc fc

Fixes: 4f82f45730c6 ("net ip6 flowlabel: Make owner a union of struct pid * and kuid_t")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_flowlabel.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index cb54a8a3c273..23a525c0a9be 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -94,15 +94,21 @@ static struct ip6_flowlabel *fl_lookup(struct net *net, __be32 label)
 	return fl;
 }
 
+static void fl_free_rcu(struct rcu_head *head)
+{
+	struct ip6_flowlabel *fl = container_of(head, struct ip6_flowlabel, rcu);
+
+	if (fl->share == IPV6_FL_S_PROCESS)
+		put_pid(fl->owner.pid);
+	kfree(fl->opt);
+	kfree(fl);
+}
+
 
 static void fl_free(struct ip6_flowlabel *fl)
 {
-	if (fl) {
-		if (fl->share == IPV6_FL_S_PROCESS)
-			put_pid(fl->owner.pid);
-		kfree(fl->opt);
-		kfree_rcu(fl, rcu);
-	}
+	if (fl)
+		call_rcu(&fl->rcu, fl_free_rcu);
 }
 
 static void fl_release(struct ip6_flowlabel *fl)
-- 
2.20.1


From 352311eeebad02587e5bb90a26bd71bfe58d03e7 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Thu, 25 Apr 2019 12:06:54 -0400
Subject: [PATCH 05/27] ipv6: invert flowlabel sharing check in process and
 user mode

[ Upstream commit 95c169251bf734aa555a1e8043e4d88ec97a04ec ]

A request for a flowlabel fails in process or user exclusive mode must
fail if the caller pid or uid does not match. Invert the test.

Previously, the test was unsafe wrt PID recycling, but indeed tested
for inequality: fl1->owner != fl->owner

Fixes: 4f82f45730c68 ("net ip6 flowlabel: Make owner a union of struct pid* and kuid_t")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_flowlabel.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 23a525c0a9be..be5f3d7ceb96 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -639,9 +639,9 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
 				if (fl1->share == IPV6_FL_S_EXCL ||
 				    fl1->share != fl->share ||
 				    ((fl1->share == IPV6_FL_S_PROCESS) &&
-				     (fl1->owner.pid == fl->owner.pid)) ||
+				     (fl1->owner.pid != fl->owner.pid)) ||
 				    ((fl1->share == IPV6_FL_S_USER) &&
-				     uid_eq(fl1->owner.uid, fl->owner.uid)))
+				     !uid_eq(fl1->owner.uid, fl->owner.uid)))
 					goto release;
 
 				err = -ENOMEM;
-- 
2.20.1


From d8cd23cbaaf3eba1f9cf2303e96eb0ff84067e78 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 30 Apr 2019 06:27:58 -0700
Subject: [PATCH 06/27] l2ip: fix possible use-after-free

[ Upstream commit a622b40035d16196bf19b2b33b854862595245fc ]

Before taking a refcount on a rcu protected structure,
we need to make sure the refcount is not zero.

syzbot reported :

refcount_t: increment on 0; use-after-free.
WARNING: CPU: 1 PID: 23533 at lib/refcount.c:156 refcount_inc_checked lib/refcount.c:156 [inline]
WARNING: CPU: 1 PID: 23533 at lib/refcount.c:156 refcount_inc_checked+0x61/0x70 lib/refcount.c:154
Kernel panic - not syncing: panic_on_warn set ...
CPU: 1 PID: 23533 Comm: syz-executor.2 Not tainted 5.1.0-rc7+ #93
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 panic+0x2cb/0x65c kernel/panic.c:214
 __warn.cold+0x20/0x45 kernel/panic.c:571
 report_bug+0x263/0x2b0 lib/bug.c:186
 fixup_bug arch/x86/kernel/traps.c:179 [inline]
 fixup_bug arch/x86/kernel/traps.c:174 [inline]
 do_error_trap+0x11b/0x200 arch/x86/kernel/traps.c:272
 do_invalid_op+0x37/0x50 arch/x86/kernel/traps.c:291
 invalid_op+0x14/0x20 arch/x86/entry/entry_64.S:973
RIP: 0010:refcount_inc_checked lib/refcount.c:156 [inline]
RIP: 0010:refcount_inc_checked+0x61/0x70 lib/refcount.c:154
Code: 1d 98 2b 2a 06 31 ff 89 de e8 db 2c 40 fe 84 db 75 dd e8 92 2b 40 fe 48 c7 c7 20 7a a1 87 c6 05 78 2b 2a 06 01 e8 7d d9 12 fe <0f> 0b eb c1 90 90 90 90 90 90 90 90 90 90 90 55 48 89 e5 41 57 41
RSP: 0018:ffff888069f0fba8 EFLAGS: 00010286
RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000
RDX: 000000000000f353 RSI: ffffffff815afcb6 RDI: ffffed100d3e1f67
RBP: ffff888069f0fbb8 R08: ffff88809b1845c0 R09: ffffed1015d23ef1
R10: ffffed1015d23ef0 R11: ffff8880ae91f787 R12: ffff8880a8f26968
R13: 0000000000000004 R14: dffffc0000000000 R15: ffff8880a49a6440
 l2tp_tunnel_inc_refcount net/l2tp/l2tp_core.h:240 [inline]
 l2tp_tunnel_get+0x250/0x580 net/l2tp/l2tp_core.c:173
 pppol2tp_connect+0xc00/0x1c70 net/l2tp/l2tp_ppp.c:702
 __sys_connect+0x266/0x330 net/socket.c:1808
 __do_sys_connect net/socket.c:1819 [inline]
 __se_sys_connect net/socket.c:1816 [inline]
 __x64_sys_connect+0x73/0xb0 net/socket.c:1816

Fixes: 54652eb12c1b ("l2tp: hold tunnel while looking up sessions in l2tp_netlink")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index fed6becc5daf..fa789c082c3e 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -169,8 +169,8 @@ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id)
 
 	rcu_read_lock_bh();
 	list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
-		if (tunnel->tunnel_id == tunnel_id) {
-			l2tp_tunnel_inc_refcount(tunnel);
+		if (tunnel->tunnel_id == tunnel_id &&
+		    refcount_inc_not_zero(&tunnel->ref_count)) {
 			rcu_read_unlock_bh();
 
 			return tunnel;
@@ -190,8 +190,8 @@ struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth)
 
 	rcu_read_lock_bh();
 	list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
-		if (++count > nth) {
-			l2tp_tunnel_inc_refcount(tunnel);
+		if (++count > nth &&
+		    refcount_inc_not_zero(&tunnel->ref_count)) {
 			rcu_read_unlock_bh();
 			return tunnel;
 		}
-- 
2.20.1


From 3da000e8fb959d13be8ee1304117733ced697ced Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 23 Apr 2019 09:43:26 -0700
Subject: [PATCH 07/27] l2tp: use rcu_dereference_sk_user_data() in
 l2tp_udp_encap_recv()

[ Upstream commit c1c477217882c610a2ba0268f5faf36c9c092528 ]

Canonical way to fetch sk_user_data from an encap_rcv() handler called
from UDP stack in rcu protected section is to use rcu_dereference_sk_user_data(),
otherwise compiler might read it multiple times.

Fixes: d00fa9adc528 ("il2tp: fix races with tunnel socket close")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: James Chapman <jchapman@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index fa789c082c3e..52b5a2797c0c 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -909,7 +909,7 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 {
 	struct l2tp_tunnel *tunnel;
 
-	tunnel = l2tp_tunnel(sk);
+	tunnel = rcu_dereference_sk_user_data(sk);
 	if (tunnel == NULL)
 		goto pass_up;
 
-- 
2.20.1


From 1a4aefae8c70031334b7ea23d89f63d16adc0b3b Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Tue, 30 Apr 2019 13:44:19 +0300
Subject: [PATCH 08/27] net: dsa: bcm_sf2: fix buffer overflow doing set_rxnfc

[ Upstream commit f949a12fd697479f68d99dc65e9bbab68ee49043 ]

The "fs->location" is a u32 that comes from the user in ethtool_set_rxnfc().
We can't pass unclamped values to test_bit() or it results in an out of
bounds access beyond the end of the bitmap.

Fixes: 7318166cacad ("net: dsa: bcm_sf2: Add support for ethtool::rxnfc")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2_cfp.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c
index e14663ab6dbc..8dd74700a2ef 100644
--- a/drivers/net/dsa/bcm_sf2_cfp.c
+++ b/drivers/net/dsa/bcm_sf2_cfp.c
@@ -854,6 +854,9 @@ static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
 	     fs->m_ext.data[1]))
 		return -EINVAL;
 
+	if (fs->location != RX_CLS_LOC_ANY && fs->location >= CFP_NUM_RULES)
+		return -EINVAL;
+
 	if (fs->location != RX_CLS_LOC_ANY &&
 	    test_bit(fs->location, priv->cfp.used))
 		return -EBUSY;
@@ -942,6 +945,9 @@ static int bcm_sf2_cfp_rule_del(struct bcm_sf2_priv *priv, int port, u32 loc)
 	struct cfp_rule *rule;
 	int ret;
 
+	if (loc >= CFP_NUM_RULES)
+		return -EINVAL;
+
 	/* Refuse deleting unused rules, and those that are not unique since
 	 * that could leave IPv6 rules with one of the chained rule in the
 	 * table.
-- 
2.20.1


From a3868c743d4d3bee8775a61a1876d3fc16c676a4 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Thu, 25 Apr 2019 00:33:00 +0200
Subject: [PATCH 09/27] net: phy: marvell: Fix buffer overrun with stats
 counters

[ Upstream commit fdfdf86720a34527f777cbe0d8599bf0528fa146 ]

marvell_get_sset_count() returns how many statistics counters there
are. If the PHY supports fibre, there are 3, otherwise two.

marvell_get_strings() does not make this distinction, and always
returns 3 strings. This then often results in writing past the end
of the buffer for the strings.

Fixes: 2170fef78a40 ("Marvell phy: add field to get errors from fiber link.")
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/marvell.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index abb7876a8776..66573a218df5 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -1494,9 +1494,10 @@ static int marvell_get_sset_count(struct phy_device *phydev)
 
 static void marvell_get_strings(struct phy_device *phydev, u8 *data)
 {
+	int count = marvell_get_sset_count(phydev);
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(marvell_hw_stats); i++) {
+	for (i = 0; i < count; i++) {
 		strlcpy(data + i * ETH_GSTRING_LEN,
 			marvell_hw_stats[i].string, ETH_GSTRING_LEN);
 	}
@@ -1524,9 +1525,10 @@ static u64 marvell_get_stat(struct phy_device *phydev, int i)
 static void marvell_get_stats(struct phy_device *phydev,
 			      struct ethtool_stats *stats, u64 *data)
 {
+	int count = marvell_get_sset_count(phydev);
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(marvell_hw_stats); i++)
+	for (i = 0; i < count; i++)
 		data[i] = marvell_get_stat(phydev, i);
 }
 
-- 
2.20.1


From fec094683d639baeac638edf73d09e8d885efc68 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 29 Apr 2019 12:19:12 -0700
Subject: [PATCH 10/27] net/tls: avoid NULL pointer deref on nskb->sk in
 fallback

[ Upstream commit 2dcb003314032c6efb13a065ffae60d164b2dd35 ]

update_chksum() accesses nskb->sk before it has been set
by complete_skb(), move the init up.

Fixes: e8f69799810c ("net/tls: Add generic NIC offload infrastructure")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_device_fallback.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c
index ef8934fd8698..426dd97725e4 100644
--- a/net/tls/tls_device_fallback.c
+++ b/net/tls/tls_device_fallback.c
@@ -200,13 +200,14 @@ static void complete_skb(struct sk_buff *nskb, struct sk_buff *skb, int headln)
 
 	skb_put(nskb, skb->len);
 	memcpy(nskb->data, skb->data, headln);
-	update_chksum(nskb, headln);
 
 	nskb->destructor = skb->destructor;
 	nskb->sk = sk;
 	skb->destructor = NULL;
 	skb->sk = NULL;
 
+	update_chksum(nskb, headln);
+
 	delta = nskb->truesize - skb->truesize;
 	if (likely(delta < 0))
 		WARN_ON_ONCE(refcount_sub_and_test(-delta, &sk->sk_wmem_alloc));
-- 
2.20.1


From b6112f849fa5c14d9038b8834e08486657291d45 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 30 Apr 2019 08:34:08 +0100
Subject: [PATCH 11/27] rxrpc: Fix net namespace cleanup

[ Upstream commit b13023421b5179413421333f602850914f6a7ad8 ]

In rxrpc_destroy_all_calls(), there are two phases: (1) make sure the
->calls list is empty, emitting error messages if not, and (2) wait for the
RCU cleanup to happen on outstanding calls (ie. ->nr_calls becomes 0).

To avoid taking the call_lock, the function prechecks ->calls and if empty,
it returns to avoid taking the lock - this is wrong, however: it still
needs to go and do the second phase and wait for ->nr_calls to become 0.

Without this, the rxrpc_net struct may get deallocated before we get to the
RCU cleanup for the last calls.  This can lead to:

  Slab corruption (Not tainted): kmalloc-16k start=ffff88802b178000, len=16384
  050: 6b 6b 6b 6b 6b 6b 6b 6b 61 6b 6b 6b 6b 6b 6b 6b  kkkkkkkkakkkkkkk

Note the "61" at offset 0x58.  This corresponds to the ->nr_calls member of
struct rxrpc_net (which is >9k in size, and thus allocated out of the 16k
slab).

Fix this by flipping the condition on the if-statement, putting the locked
section inside the if-body and dropping the return from there.  The
function will then always go on to wait for the RCU cleanup on outstanding
calls.

Fixes: 2baec2c3f854 ("rxrpc: Support network namespacing")
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/call_object.c | 32 ++++++++++++++++----------------
 1 file changed, 16 insertions(+), 16 deletions(-)

diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 8aa2937b069f..fe96881a334d 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -604,30 +604,30 @@ void rxrpc_destroy_all_calls(struct rxrpc_net *rxnet)
 
 	_enter("");
 
-	if (list_empty(&rxnet->calls))
-		return;
+	if (!list_empty(&rxnet->calls)) {
+		write_lock(&rxnet->call_lock);
 
-	write_lock(&rxnet->call_lock);
+		while (!list_empty(&rxnet->calls)) {
+			call = list_entry(rxnet->calls.next,
+					  struct rxrpc_call, link);
+			_debug("Zapping call %p", call);
 
-	while (!list_empty(&rxnet->calls)) {
-		call = list_entry(rxnet->calls.next, struct rxrpc_call, link);
-		_debug("Zapping call %p", call);
+			rxrpc_see_call(call);
+			list_del_init(&call->link);
 
-		rxrpc_see_call(call);
-		list_del_init(&call->link);
+			pr_err("Call %p still in use (%d,%s,%lx,%lx)!\n",
+			       call, atomic_read(&call->usage),
+			       rxrpc_call_states[call->state],
+			       call->flags, call->events);
 
-		pr_err("Call %p still in use (%d,%s,%lx,%lx)!\n",
-		       call, atomic_read(&call->usage),
-		       rxrpc_call_states[call->state],
-		       call->flags, call->events);
+			write_unlock(&rxnet->call_lock);
+			cond_resched();
+			write_lock(&rxnet->call_lock);
+		}
 
 		write_unlock(&rxnet->call_lock);
-		cond_resched();
-		write_lock(&rxnet->call_lock);
 	}
 
-	write_unlock(&rxnet->call_lock);
-
 	atomic_dec(&rxnet->nr_calls);
 	wait_var_event(&rxnet->nr_calls, !atomic_read(&rxnet->nr_calls));
 }
-- 
2.20.1


From 08a4d9e8bc4d2803f283e9024013e4695e2db7ef Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 29 Apr 2019 14:16:19 +0800
Subject: [PATCH 12/27] sctp: avoid running the sctp state machine recursively

[ Upstream commit fbd019737d71e405f86549fd738f81e2ff3dd073 ]

Ying triggered a call trace when doing an asconf testing:

  BUG: scheduling while atomic: swapper/12/0/0x10000100
  Call Trace:
   <IRQ>  [<ffffffffa4375904>] dump_stack+0x19/0x1b
   [<ffffffffa436fcaf>] __schedule_bug+0x64/0x72
   [<ffffffffa437b93a>] __schedule+0x9ba/0xa00
   [<ffffffffa3cd5326>] __cond_resched+0x26/0x30
   [<ffffffffa437bc4a>] _cond_resched+0x3a/0x50
   [<ffffffffa3e22be8>] kmem_cache_alloc_node+0x38/0x200
   [<ffffffffa423512d>] __alloc_skb+0x5d/0x2d0
   [<ffffffffc0995320>] sctp_packet_transmit+0x610/0xa20 [sctp]
   [<ffffffffc098510e>] sctp_outq_flush+0x2ce/0xc00 [sctp]
   [<ffffffffc098646c>] sctp_outq_uncork+0x1c/0x20 [sctp]
   [<ffffffffc0977338>] sctp_cmd_interpreter.isra.22+0xc8/0x1460 [sctp]
   [<ffffffffc0976ad1>] sctp_do_sm+0xe1/0x350 [sctp]
   [<ffffffffc099443d>] sctp_primitive_ASCONF+0x3d/0x50 [sctp]
   [<ffffffffc0977384>] sctp_cmd_interpreter.isra.22+0x114/0x1460 [sctp]
   [<ffffffffc0976ad1>] sctp_do_sm+0xe1/0x350 [sctp]
   [<ffffffffc097b3a4>] sctp_assoc_bh_rcv+0xf4/0x1b0 [sctp]
   [<ffffffffc09840f1>] sctp_inq_push+0x51/0x70 [sctp]
   [<ffffffffc099732b>] sctp_rcv+0xa8b/0xbd0 [sctp]

As it shows, the first sctp_do_sm() running under atomic context (NET_RX
softirq) invoked sctp_primitive_ASCONF() that uses GFP_KERNEL flag later,
and this flag is supposed to be used in non-atomic context only. Besides,
sctp_do_sm() was called recursively, which is not expected.

Vlad tried to fix this recursive call in Commit c0786693404c ("sctp: Fix
oops when sending queued ASCONF chunks") by introducing a new command
SCTP_CMD_SEND_NEXT_ASCONF. But it didn't work as this command is still
used in the first sctp_do_sm() call, and sctp_primitive_ASCONF() will
be called in this command again.

To avoid calling sctp_do_sm() recursively, we send the next queued ASCONF
not by sctp_primitive_ASCONF(), but by sctp_sf_do_prm_asconf() in the 1st
sctp_do_sm() directly.

Reported-by: Ying Xu <yinxu@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/command.h |  1 -
 net/sctp/sm_sideeffect.c   | 29 -----------------------------
 net/sctp/sm_statefuns.c    | 35 +++++++++++++++++++++++++++--------
 3 files changed, 27 insertions(+), 38 deletions(-)

diff --git a/include/net/sctp/command.h b/include/net/sctp/command.h
index 6640f84fe536..6d5beac29bc1 100644
--- a/include/net/sctp/command.h
+++ b/include/net/sctp/command.h
@@ -105,7 +105,6 @@ enum sctp_verb {
 	SCTP_CMD_T1_RETRAN,	 /* Mark for retransmission after T1 timeout  */
 	SCTP_CMD_UPDATE_INITTAG, /* Update peer inittag */
 	SCTP_CMD_SEND_MSG,	 /* Send the whole use message */
-	SCTP_CMD_SEND_NEXT_ASCONF, /* Send the next ASCONF after ACK */
 	SCTP_CMD_PURGE_ASCONF_QUEUE, /* Purge all asconf queues.*/
 	SCTP_CMD_SET_ASOC,	 /* Restore association context */
 	SCTP_CMD_LAST
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index 1d143bc3f73d..4aa03588f87b 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -1112,32 +1112,6 @@ static void sctp_cmd_send_msg(struct sctp_association *asoc,
 }
 
 
-/* Sent the next ASCONF packet currently stored in the association.
- * This happens after the ASCONF_ACK was succeffully processed.
- */
-static void sctp_cmd_send_asconf(struct sctp_association *asoc)
-{
-	struct net *net = sock_net(asoc->base.sk);
-
-	/* Send the next asconf chunk from the addip chunk
-	 * queue.
-	 */
-	if (!list_empty(&asoc->addip_chunk_list)) {
-		struct list_head *entry = asoc->addip_chunk_list.next;
-		struct sctp_chunk *asconf = list_entry(entry,
-						struct sctp_chunk, list);
-		list_del_init(entry);
-
-		/* Hold the chunk until an ASCONF_ACK is received. */
-		sctp_chunk_hold(asconf);
-		if (sctp_primitive_ASCONF(net, asoc, asconf))
-			sctp_chunk_free(asconf);
-		else
-			asoc->addip_last_asconf = asconf;
-	}
-}
-
-
 /* These three macros allow us to pull the debugging code out of the
  * main flow of sctp_do_sm() to keep attention focused on the real
  * functionality there.
@@ -1783,9 +1757,6 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type,
 			}
 			sctp_cmd_send_msg(asoc, cmd->obj.msg, gfp);
 			break;
-		case SCTP_CMD_SEND_NEXT_ASCONF:
-			sctp_cmd_send_asconf(asoc);
-			break;
 		case SCTP_CMD_PURGE_ASCONF_QUEUE:
 			sctp_asconf_queue_teardown(asoc);
 			break;
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index c9ae3404b1bb..713a669d2058 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -3824,6 +3824,29 @@ enum sctp_disposition sctp_sf_do_asconf(struct net *net,
 	return SCTP_DISPOSITION_CONSUME;
 }
 
+static enum sctp_disposition sctp_send_next_asconf(
+					struct net *net,
+					const struct sctp_endpoint *ep,
+					struct sctp_association *asoc,
+					const union sctp_subtype type,
+					struct sctp_cmd_seq *commands)
+{
+	struct sctp_chunk *asconf;
+	struct list_head *entry;
+
+	if (list_empty(&asoc->addip_chunk_list))
+		return SCTP_DISPOSITION_CONSUME;
+
+	entry = asoc->addip_chunk_list.next;
+	asconf = list_entry(entry, struct sctp_chunk, list);
+
+	list_del_init(entry);
+	sctp_chunk_hold(asconf);
+	asoc->addip_last_asconf = asconf;
+
+	return sctp_sf_do_prm_asconf(net, ep, asoc, type, asconf, commands);
+}
+
 /*
  * ADDIP Section 4.3 General rules for address manipulation
  * When building TLV parameters for the ASCONF Chunk that will add or
@@ -3915,14 +3938,10 @@ enum sctp_disposition sctp_sf_do_asconf_ack(struct net *net,
 				SCTP_TO(SCTP_EVENT_TIMEOUT_T4_RTO));
 
 		if (!sctp_process_asconf_ack((struct sctp_association *)asoc,
-					     asconf_ack)) {
-			/* Successfully processed ASCONF_ACK.  We can
-			 * release the next asconf if we have one.
-			 */
-			sctp_add_cmd_sf(commands, SCTP_CMD_SEND_NEXT_ASCONF,
-					SCTP_NULL());
-			return SCTP_DISPOSITION_CONSUME;
-		}
+					     asconf_ack))
+			return sctp_send_next_asconf(net, ep,
+					(struct sctp_association *)asoc,
+							type, commands);
 
 		abort = sctp_make_abort(asoc, asconf_ack,
 					sizeof(struct sctp_errhdr));
-- 
2.20.1


From 80e3f509d18a4ccdffec19489b4b0917b34eabb2 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Tue, 30 Apr 2019 10:46:10 +0800
Subject: [PATCH 13/27] selftests: fib_rule_tests: print the result and return
 1 if any tests failed

[ Upstream commit f68d7c44e76532e46f292ad941aa3706cb9e6e40 ]

Fixes: 65b2b4939a64 ("selftests: net: initial fib rule tests")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/fib_rule_tests.sh | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh
index d4cfb6a7a086..d84193bdc307 100755
--- a/tools/testing/selftests/net/fib_rule_tests.sh
+++ b/tools/testing/selftests/net/fib_rule_tests.sh
@@ -27,6 +27,7 @@ log_test()
 		nsuccess=$((nsuccess+1))
 		printf "\n    TEST: %-50s  [ OK ]\n" "${msg}"
 	else
+		ret=1
 		nfail=$((nfail+1))
 		printf "\n    TEST: %-50s  [FAIL]\n" "${msg}"
 		if [ "${PAUSE_ON_FAIL}" = "yes" ]; then
@@ -245,4 +246,9 @@ setup
 run_fibrule_tests
 cleanup
 
+if [ "$TESTS" != "none" ]; then
+	printf "\nTests passed: %3d\n" ${nsuccess}
+	printf "Tests failed: %3d\n"   ${nfail}
+fi
+
 exit $ret
-- 
2.20.1


From 46aab835e63b2631347d693fcb62eb67434885b8 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Mon, 29 Apr 2019 11:53:18 -0400
Subject: [PATCH 14/27] packet: validate msg_namelen in send directly

[ Upstream commit 486efdc8f6ce802b27e15921d2353cc740c55451 ]

Packet sockets in datagram mode take a destination address. Verify its
length before passing to dev_hard_header.

Prior to 2.6.14-rc3, the send code ignored sll_halen. This is
established behavior. Directly compare msg_namelen to dev->addr_len.

Change v1->v2: initialize addr in all paths

Fixes: 6b8d95f1795c4 ("packet: validate address length if non-zero")
Suggested-by: David Laight <David.Laight@aculab.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 24 ++++++++++++++----------
 1 file changed, 14 insertions(+), 10 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 8406bf11eef4..97f79580ae38 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2603,8 +2603,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 	void *ph;
 	DECLARE_SOCKADDR(struct sockaddr_ll *, saddr, msg->msg_name);
 	bool need_wait = !(msg->msg_flags & MSG_DONTWAIT);
+	unsigned char *addr = NULL;
 	int tp_len, size_max;
-	unsigned char *addr;
 	void *data;
 	int len_sum = 0;
 	int status = TP_STATUS_AVAILABLE;
@@ -2615,7 +2615,6 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 	if (likely(saddr == NULL)) {
 		dev	= packet_cached_dev_get(po);
 		proto	= po->num;
-		addr	= NULL;
 	} else {
 		err = -EINVAL;
 		if (msg->msg_namelen < sizeof(struct sockaddr_ll))
@@ -2625,10 +2624,13 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 						sll_addr)))
 			goto out;
 		proto	= saddr->sll_protocol;
-		addr	= saddr->sll_halen ? saddr->sll_addr : NULL;
 		dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex);
-		if (addr && dev && saddr->sll_halen < dev->addr_len)
-			goto out_put;
+		if (po->sk.sk_socket->type == SOCK_DGRAM) {
+			if (dev && msg->msg_namelen < dev->addr_len +
+				   offsetof(struct sockaddr_ll, sll_addr))
+				goto out_put;
+			addr = saddr->sll_addr;
+		}
 	}
 
 	err = -ENXIO;
@@ -2800,7 +2802,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	struct sk_buff *skb;
 	struct net_device *dev;
 	__be16 proto;
-	unsigned char *addr;
+	unsigned char *addr = NULL;
 	int err, reserve = 0;
 	struct sockcm_cookie sockc;
 	struct virtio_net_hdr vnet_hdr = { 0 };
@@ -2817,7 +2819,6 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	if (likely(saddr == NULL)) {
 		dev	= packet_cached_dev_get(po);
 		proto	= po->num;
-		addr	= NULL;
 	} else {
 		err = -EINVAL;
 		if (msg->msg_namelen < sizeof(struct sockaddr_ll))
@@ -2825,10 +2826,13 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		if (msg->msg_namelen < (saddr->sll_halen + offsetof(struct sockaddr_ll, sll_addr)))
 			goto out;
 		proto	= saddr->sll_protocol;
-		addr	= saddr->sll_halen ? saddr->sll_addr : NULL;
 		dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex);
-		if (addr && dev && saddr->sll_halen < dev->addr_len)
-			goto out_unlock;
+		if (sock->type == SOCK_DGRAM) {
+			if (dev && msg->msg_namelen < dev->addr_len +
+				   offsetof(struct sockaddr_ll, sll_addr))
+				goto out_unlock;
+			addr = saddr->sll_addr;
+		}
 	}
 
 	err = -ENXIO;
-- 
2.20.1


From f4070efe582da5a2d9278f6d4b92088bbba918b6 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Mon, 29 Apr 2019 11:46:55 -0400
Subject: [PATCH 15/27] packet: in recvmsg msg_name return at least sizeof
 sockaddr_ll

[ Upstream commit b2cf86e1563e33a14a1c69b3e508d15dc12f804c ]

Packet send checks that msg_name is at least sizeof sockaddr_ll.
Packet recv must return at least this length, so that its output
can be passed unmodified to packet send.

This ceased to be true since adding support for lladdr longer than
sll_addr. Since, the return value uses true address length.

Always return at least sizeof sockaddr_ll, even if address length
is shorter. Zero the padding bytes.

Change v1->v2: do not overwrite zeroed padding again. use copy_len.

Fixes: 0fb375fb9b93 ("[AF_PACKET]: Allow for > 8 byte hardware addresses.")
Suggested-by: David Laight <David.Laight@aculab.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 97f79580ae38..faa2bc50cfa0 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3349,20 +3349,29 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	sock_recv_ts_and_drops(msg, sk, skb);
 
 	if (msg->msg_name) {
+		int copy_len;
+
 		/* If the address length field is there to be filled
 		 * in, we fill it in now.
 		 */
 		if (sock->type == SOCK_PACKET) {
 			__sockaddr_check_size(sizeof(struct sockaddr_pkt));
 			msg->msg_namelen = sizeof(struct sockaddr_pkt);
+			copy_len = msg->msg_namelen;
 		} else {
 			struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll;
 
 			msg->msg_namelen = sll->sll_halen +
 				offsetof(struct sockaddr_ll, sll_addr);
+			copy_len = msg->msg_namelen;
+			if (msg->msg_namelen < sizeof(struct sockaddr_ll)) {
+				memset(msg->msg_name +
+				       offsetof(struct sockaddr_ll, sll_addr),
+				       0, sizeof(sll->sll_addr));
+				msg->msg_namelen = sizeof(struct sockaddr_ll);
+			}
 		}
-		memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa,
-		       msg->msg_namelen);
+		memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa, copy_len);
 	}
 
 	if (pkt_sk(sk)->auxdata) {
-- 
2.20.1


From 2760c60ff3ec0a5cd80e3531a7fe0dbae8cd03f5 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Mon, 29 Apr 2019 10:30:09 -0700
Subject: [PATCH 16/27] selftests: fib_rule_tests: Fix icmp proto with ipv6

[ Upstream commit 15d55bae4e3c43cd9f87fd93c73a263e172d34e1 ]

A recent commit returns an error if icmp is used as the ip-proto for
IPv6 fib rules. Update fib_rule_tests to send ipv6-icmp instead of icmp.

Fixes: 5e1a99eae8499 ("ipv4: Add ICMPv6 support when parse route ipproto")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/fib_rule_tests.sh | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh
index d84193bdc307..4b7e107865bf 100755
--- a/tools/testing/selftests/net/fib_rule_tests.sh
+++ b/tools/testing/selftests/net/fib_rule_tests.sh
@@ -148,8 +148,8 @@ fib_rule6_test()
 
 	fib_check_iproute_support "ipproto" "ipproto"
 	if [ $? -eq 0 ]; then
-		match="ipproto icmp"
-		fib_rule6_test_match_n_redirect "$match" "$match" "ipproto icmp match"
+		match="ipproto ipv6-icmp"
+		fib_rule6_test_match_n_redirect "$match" "$match" "ipproto ipv6-icmp match"
 	fi
 }
 
-- 
2.20.1


From b77e7427557257ff117ef12ab19091b6fd7814f0 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 26 Apr 2019 10:10:05 -0700
Subject: [PATCH 17/27] tcp: add sanity tests in tcp_add_backlog()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit ca2fe2956acef2f87f6c55549874fdd2e92d9824 ]

Richard and Bruno both reported that my commit added a bug,
and Bruno was able to determine the problem came when a segment
wih a FIN packet was coalesced to a prior one in tcp backlog queue.

It turns out the header prediction in tcp_rcv_established()
looks back to TCP headers in the packet, not in the metadata
(aka TCP_SKB_CB(skb)->tcp_flags)

The fast path in tcp_rcv_established() is not supposed to
handle a FIN flag (it does not call tcp_fin())

Therefore we need to make sure to propagate the FIN flag,
so that the coalesced packet does not go through the fast path,
the same than a GRO packet carrying a FIN flag.

While we are at it, make sure we do not coalesce packets with
RST or SYN, or if they do not have ACK set.

Many thanks to Richard and Bruno for pinpointing the bad commit,
and to Richard for providing a first version of the fix.

Fixes: 4f693b55c3d2 ("tcp: implement coalescing on backlog queue")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Richard Purdie <richard.purdie@linuxfoundation.org>
Reported-by: Bruno Prémont <bonbons@sysophe.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 00852f47a73d..9a2ff79a93ad 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1673,7 +1673,9 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 	if (TCP_SKB_CB(tail)->end_seq != TCP_SKB_CB(skb)->seq ||
 	    TCP_SKB_CB(tail)->ip_dsfield != TCP_SKB_CB(skb)->ip_dsfield ||
 	    ((TCP_SKB_CB(tail)->tcp_flags |
-	      TCP_SKB_CB(skb)->tcp_flags) & TCPHDR_URG) ||
+	      TCP_SKB_CB(skb)->tcp_flags) & (TCPHDR_SYN | TCPHDR_RST | TCPHDR_URG)) ||
+	    !((TCP_SKB_CB(tail)->tcp_flags &
+	      TCP_SKB_CB(skb)->tcp_flags) & TCPHDR_ACK) ||
 	    ((TCP_SKB_CB(tail)->tcp_flags ^
 	      TCP_SKB_CB(skb)->tcp_flags) & (TCPHDR_ECE | TCPHDR_CWR)) ||
 #ifdef CONFIG_TLS_DEVICE
@@ -1692,6 +1694,15 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 		if (after(TCP_SKB_CB(skb)->ack_seq, TCP_SKB_CB(tail)->ack_seq))
 			TCP_SKB_CB(tail)->ack_seq = TCP_SKB_CB(skb)->ack_seq;
 
+		/* We have to update both TCP_SKB_CB(tail)->tcp_flags and
+		 * thtail->fin, so that the fast path in tcp_rcv_established()
+		 * is not entered if we append a packet with a FIN.
+		 * SYN, RST, URG are not present.
+		 * ACK is set on both packets.
+		 * PSH : we do not really care in TCP stack,
+		 *       at least for 'GRO' packets.
+		 */
+		thtail->fin |= th->fin;
 		TCP_SKB_CB(tail)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags;
 
 		if (TCP_SKB_CB(skb)->has_rxtstamp) {
-- 
2.20.1


From f17aae655842abfadefdf0142b70abaedbc1f314 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 26 Apr 2019 12:50:44 +0200
Subject: [PATCH 18/27] udp: fix GRO reception in case of length mismatch

[ Upstream commit 21f1b8a6636c4dbde4aa1ec0343f42eaf653ffcc ]

Currently, the UDP GRO code path does bad things on some edge
conditions - Aggregation can happen even on packet with different
lengths.

Fix the above by rewriting the 'complete' condition for GRO
packets. While at it, note explicitly that we allow merging the
first packet per burst below gso_size.

Reported-by: Sean Tong <seantong114@gmail.com>
Fixes: e20cf8d3f1f7 ("udp: implement GRO for plain UDP sockets.")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp_offload.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 64f9715173ac..d8776b2110c1 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -377,13 +377,14 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
 
 		/* Terminate the flow on len mismatch or if it grow "too much".
 		 * Under small packet flood GRO count could elsewhere grow a lot
-		 * leading to execessive truesize values
+		 * leading to execessive truesize values.
+		 * On len mismatch merge the first packet shorter than gso_size,
+		 * otherwise complete the GRO packet.
 		 */
-		if (!skb_gro_receive(p, skb) &&
+		if (uh->len > uh2->len || skb_gro_receive(p, skb) ||
+		    uh->len != uh2->len ||
 		    NAPI_GRO_CB(p)->count >= UDP_GRO_CNT_MAX)
 			pp = p;
-		else if (uh->len != uh2->len)
-			pp = p;
 
 		return pp;
 	}
-- 
2.20.1


From 015465bea2d26f7691bacb519aaa4f7a3bc5665b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 1 May 2019 18:56:28 -0700
Subject: [PATCH 19/27] udp: fix GRO packet of death

[ Upstream commit 4dd2b82d5adfbe0b1587ccad7a8f76d826120f37 ]

syzbot was able to crash host by sending UDP packets with a 0 payload.

TCP does not have this issue since we do not aggregate packets without
payload.

Since dev_gro_receive() sets gso_size based on skb_gro_len(skb)
it seems not worth trying to cope with padded packets.

BUG: KASAN: slab-out-of-bounds in skb_gro_receive+0xf5f/0x10e0 net/core/skbuff.c:3826
Read of size 16 at addr ffff88808893fff0 by task syz-executor612/7889

CPU: 0 PID: 7889 Comm: syz-executor612 Not tainted 5.1.0-rc7+ #96
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 print_address_description.cold+0x7c/0x20d mm/kasan/report.c:187
 kasan_report.cold+0x1b/0x40 mm/kasan/report.c:317
 __asan_report_load16_noabort+0x14/0x20 mm/kasan/generic_report.c:133
 skb_gro_receive+0xf5f/0x10e0 net/core/skbuff.c:3826
 udp_gro_receive_segment net/ipv4/udp_offload.c:382 [inline]
 call_gro_receive include/linux/netdevice.h:2349 [inline]
 udp_gro_receive+0xb61/0xfd0 net/ipv4/udp_offload.c:414
 udp4_gro_receive+0x763/0xeb0 net/ipv4/udp_offload.c:478
 inet_gro_receive+0xe72/0x1110 net/ipv4/af_inet.c:1510
 dev_gro_receive+0x1cd0/0x23c0 net/core/dev.c:5581
 napi_gro_frags+0x36b/0xd10 net/core/dev.c:5843
 tun_get_user+0x2f24/0x3fb0 drivers/net/tun.c:1981
 tun_chr_write_iter+0xbd/0x156 drivers/net/tun.c:2027
 call_write_iter include/linux/fs.h:1866 [inline]
 do_iter_readv_writev+0x5e1/0x8e0 fs/read_write.c:681
 do_iter_write fs/read_write.c:957 [inline]
 do_iter_write+0x184/0x610 fs/read_write.c:938
 vfs_writev+0x1b3/0x2f0 fs/read_write.c:1002
 do_writev+0x15e/0x370 fs/read_write.c:1037
 __do_sys_writev fs/read_write.c:1110 [inline]
 __se_sys_writev fs/read_write.c:1107 [inline]
 __x64_sys_writev+0x75/0xb0 fs/read_write.c:1107
 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x441cc0
Code: 05 48 3d 01 f0 ff ff 0f 83 9d 09 fc ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 83 3d 51 93 29 00 00 75 14 b8 14 00 00 00 0f 05 <48> 3d 01 f0 ff ff 0f 83 74 09 fc ff c3 48 83 ec 08 e8 ba 2b 00 00
RSP: 002b:00007ffe8c716118 EFLAGS: 00000246 ORIG_RAX: 0000000000000014
RAX: ffffffffffffffda RBX: 00007ffe8c716150 RCX: 0000000000441cc0
RDX: 0000000000000001 RSI: 00007ffe8c716170 RDI: 00000000000000f0
RBP: 0000000000000000 R08: 000000000000ffff R09: 0000000000a64668
R10: 0000000020000040 R11: 0000000000000246 R12: 000000000000c2d9
R13: 0000000000402b50 R14: 0000000000000000 R15: 0000000000000000

Allocated by task 5143:
 save_stack+0x45/0xd0 mm/kasan/common.c:75
 set_track mm/kasan/common.c:87 [inline]
 __kasan_kmalloc mm/kasan/common.c:497 [inline]
 __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:470
 kasan_slab_alloc+0xf/0x20 mm/kasan/common.c:505
 slab_post_alloc_hook mm/slab.h:437 [inline]
 slab_alloc mm/slab.c:3393 [inline]
 kmem_cache_alloc+0x11a/0x6f0 mm/slab.c:3555
 mm_alloc+0x1d/0xd0 kernel/fork.c:1030
 bprm_mm_init fs/exec.c:363 [inline]
 __do_execve_file.isra.0+0xaa3/0x23f0 fs/exec.c:1791
 do_execveat_common fs/exec.c:1865 [inline]
 do_execve fs/exec.c:1882 [inline]
 __do_sys_execve fs/exec.c:1958 [inline]
 __se_sys_execve fs/exec.c:1953 [inline]
 __x64_sys_execve+0x8f/0xc0 fs/exec.c:1953
 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Freed by task 5351:
 save_stack+0x45/0xd0 mm/kasan/common.c:75
 set_track mm/kasan/common.c:87 [inline]
 __kasan_slab_free+0x102/0x150 mm/kasan/common.c:459
 kasan_slab_free+0xe/0x10 mm/kasan/common.c:467
 __cache_free mm/slab.c:3499 [inline]
 kmem_cache_free+0x86/0x260 mm/slab.c:3765
 __mmdrop+0x238/0x320 kernel/fork.c:677
 mmdrop include/linux/sched/mm.h:49 [inline]
 finish_task_switch+0x47b/0x780 kernel/sched/core.c:2746
 context_switch kernel/sched/core.c:2880 [inline]
 __schedule+0x81b/0x1cc0 kernel/sched/core.c:3518
 preempt_schedule_irq+0xb5/0x140 kernel/sched/core.c:3745
 retint_kernel+0x1b/0x2d
 arch_local_irq_restore arch/x86/include/asm/paravirt.h:767 [inline]
 kmem_cache_free+0xab/0x260 mm/slab.c:3766
 anon_vma_chain_free mm/rmap.c:134 [inline]
 unlink_anon_vmas+0x2ba/0x870 mm/rmap.c:401
 free_pgtables+0x1af/0x2f0 mm/memory.c:394
 exit_mmap+0x2d1/0x530 mm/mmap.c:3144
 __mmput kernel/fork.c:1046 [inline]
 mmput+0x15f/0x4c0 kernel/fork.c:1067
 exec_mmap fs/exec.c:1046 [inline]
 flush_old_exec+0x8d9/0x1c20 fs/exec.c:1279
 load_elf_binary+0x9bc/0x53f0 fs/binfmt_elf.c:864
 search_binary_handler fs/exec.c:1656 [inline]
 search_binary_handler+0x17f/0x570 fs/exec.c:1634
 exec_binprm fs/exec.c:1698 [inline]
 __do_execve_file.isra.0+0x1394/0x23f0 fs/exec.c:1818
 do_execveat_common fs/exec.c:1865 [inline]
 do_execve fs/exec.c:1882 [inline]
 __do_sys_execve fs/exec.c:1958 [inline]
 __se_sys_execve fs/exec.c:1953 [inline]
 __x64_sys_execve+0x8f/0xc0 fs/exec.c:1953
 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

The buggy address belongs to the object at ffff88808893f7c0
 which belongs to the cache mm_struct of size 1496
The buggy address is located 600 bytes to the right of
 1496-byte region [ffff88808893f7c0, ffff88808893fd98)
The buggy address belongs to the page:
page:ffffea0002224f80 count:1 mapcount:0 mapping:ffff88821bc40ac0 index:0xffff88808893f7c0 compound_mapcount: 0
flags: 0x1fffc0000010200(slab|head)
raw: 01fffc0000010200 ffffea00025b4f08 ffffea00027b9d08 ffff88821bc40ac0
raw: ffff88808893f7c0 ffff88808893e440 0000000100000001 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff88808893fe80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 ffff88808893ff00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
>ffff88808893ff80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
                                                             ^
 ffff888088940000: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
 ffff888088940080: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00

Fixes: e20cf8d3f1f7 ("udp: implement GRO for plain UDP sockets.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Paolo Abeni <pabeni@redhat.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp_offload.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index d8776b2110c1..065334b41d57 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -352,6 +352,7 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
 	struct sk_buff *pp = NULL;
 	struct udphdr *uh2;
 	struct sk_buff *p;
+	unsigned int ulen;
 
 	/* requires non zero csum, for symmetry with GSO */
 	if (!uh->check) {
@@ -359,6 +360,12 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
 		return NULL;
 	}
 
+	/* Do not deal with padded or malicious packets, sorry ! */
+	ulen = ntohs(uh->len);
+	if (ulen <= sizeof(*uh) || ulen != skb_gro_len(skb)) {
+		NAPI_GRO_CB(skb)->flush = 1;
+		return NULL;
+	}
 	/* pull encapsulating udp header */
 	skb_gro_pull(skb, sizeof(struct udphdr));
 	skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr));
@@ -377,12 +384,12 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
 
 		/* Terminate the flow on len mismatch or if it grow "too much".
 		 * Under small packet flood GRO count could elsewhere grow a lot
-		 * leading to execessive truesize values.
+		 * leading to excessive truesize values.
 		 * On len mismatch merge the first packet shorter than gso_size,
 		 * otherwise complete the GRO packet.
 		 */
-		if (uh->len > uh2->len || skb_gro_receive(p, skb) ||
-		    uh->len != uh2->len ||
+		if (ulen > ntohs(uh2->len) || skb_gro_receive(p, skb) ||
+		    ulen != ntohs(uh2->len) ||
 		    NAPI_GRO_CB(p)->count >= UDP_GRO_CNT_MAX)
 			pp = p;
 
-- 
2.20.1


From acb2021983130a83b9770778df6b1def661e0c1b Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Thu, 25 Apr 2019 22:31:50 -0400
Subject: [PATCH 20/27] bnxt_en: Improve multicast address setup logic.

[ Upstream commit b4e30e8e7ea1d1e35ffd64ca46f7d9a7f227b4bf ]

The driver builds a list of multicast addresses and sends it to the
firmware when the driver's ndo_set_rx_mode() is called.  In rare
cases, the firmware can fail this call if internal resources to
add multicast addresses are exhausted.  In that case, we should
try the call again by setting the ALL_MCAST flag which is more
guaranteed to succeed.

Fixes: c0c050c58d84 ("bnxt_en: New Broadcom ethernet driver.")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 40ca339ec3df..ef07baacc762 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -8889,8 +8889,15 @@ static int bnxt_cfg_rx_mode(struct bnxt *bp)
 
 skip_uc:
 	rc = bnxt_hwrm_cfa_l2_set_rx_mask(bp, 0);
+	if (rc && vnic->mc_list_count) {
+		netdev_info(bp->dev, "Failed setting MC filters rc: %d, turning on ALL_MCAST mode\n",
+			    rc);
+		vnic->rx_mask |= CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST;
+		vnic->mc_list_count = 0;
+		rc = bnxt_hwrm_cfa_l2_set_rx_mask(bp, 0);
+	}
 	if (rc)
-		netdev_err(bp->dev, "HWRM cfa l2 rx mask failure rc: %x\n",
+		netdev_err(bp->dev, "HWRM cfa l2 rx mask failure rc: %d\n",
 			   rc);
 
 	return rc;
-- 
2.20.1


From 5585dfeaabae8d46d3e864549621b81f30ffceb9 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Thu, 25 Apr 2019 22:31:51 -0400
Subject: [PATCH 21/27] bnxt_en: Free short FW command HWRM memory in error
 path in bnxt_init_one()

[ Upstream commit f9099d611449836a51a65f40ea7dc9cb5f2f665e ]

In the bnxt_init_one() error path, short FW command request memory
is not freed. This patch fixes it.

Fixes: e605db801bde ("bnxt_en: Support for Short Firmware Message")
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index ef07baacc762..32097f838d2a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -10632,6 +10632,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	bnxt_clear_int_mode(bp);
 
 init_err_pci_clean:
+	bnxt_free_hwrm_short_cmd_req(bp);
 	bnxt_free_hwrm_resources(bp);
 	bnxt_free_ctx_mem(bp);
 	kfree(bp->ctx);
-- 
2.20.1


From 87da53358f4fdf07cb9d07847ee0da8005eaf462 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Thu, 25 Apr 2019 22:31:52 -0400
Subject: [PATCH 22/27] bnxt_en: Fix possible crash in bnxt_hwrm_ring_free()
 under error conditions.

[ Upstream commit 1f83391bd6fc48f92f627b0ec0bce686d100c6a5 ]

If we encounter errors during open and proceed to clean up,
bnxt_hwrm_ring_free() may crash if the rings we try to free have never
been allocated.  bnxt_cp_ring_for_rx() or bnxt_cp_ring_for_tx()
may reference pointers that have not been allocated.

Fix it by checking for valid fw_ring_id first before calling
bnxt_cp_ring_for_rx() or bnxt_cp_ring_for_tx().

Fixes: 2c61d2117ecb ("bnxt_en: Add helper functions to get firmware CP ring ID.")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 32097f838d2a..e943f4138929 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -5131,10 +5131,10 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 	for (i = 0; i < bp->tx_nr_rings; i++) {
 		struct bnxt_tx_ring_info *txr = &bp->tx_ring[i];
 		struct bnxt_ring_struct *ring = &txr->tx_ring_struct;
-		u32 cmpl_ring_id;
 
-		cmpl_ring_id = bnxt_cp_ring_for_tx(bp, txr);
 		if (ring->fw_ring_id != INVALID_HW_RING_ID) {
+			u32 cmpl_ring_id = bnxt_cp_ring_for_tx(bp, txr);
+
 			hwrm_ring_free_send_msg(bp, ring,
 						RING_FREE_REQ_RING_TYPE_TX,
 						close_path ? cmpl_ring_id :
@@ -5147,10 +5147,10 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 		struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i];
 		struct bnxt_ring_struct *ring = &rxr->rx_ring_struct;
 		u32 grp_idx = rxr->bnapi->index;
-		u32 cmpl_ring_id;
 
-		cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr);
 		if (ring->fw_ring_id != INVALID_HW_RING_ID) {
+			u32 cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr);
+
 			hwrm_ring_free_send_msg(bp, ring,
 						RING_FREE_REQ_RING_TYPE_RX,
 						close_path ? cmpl_ring_id :
@@ -5169,10 +5169,10 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 		struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i];
 		struct bnxt_ring_struct *ring = &rxr->rx_agg_ring_struct;
 		u32 grp_idx = rxr->bnapi->index;
-		u32 cmpl_ring_id;
 
-		cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr);
 		if (ring->fw_ring_id != INVALID_HW_RING_ID) {
+			u32 cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr);
+
 			hwrm_ring_free_send_msg(bp, ring, type,
 						close_path ? cmpl_ring_id :
 						INVALID_HW_RING_ID);
-- 
2.20.1


From 04b19d7a5f65dbc028cb7ff2fb2cec1ed2b4949d Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Thu, 25 Apr 2019 22:31:53 -0400
Subject: [PATCH 23/27] bnxt_en: Pass correct extended TX port statistics size
 to firmware.

[ Upstream commit ad361adf0d08f1135f3845c6b3a36be7cc0bfda5 ]

If driver determines that extended TX port statistics are not supported
or allocation of the data structure fails, make sure to pass 0 TX stats
size to firmware to disable it.  The firmware returned TX stats size should
also be set to 0 for consistency.  This will prevent
bnxt_get_ethtool_stats() from accessing the NULL TX stats pointer in
case there is mismatch between firmware and driver.

Fixes: 36e53349b60b ("bnxt_en: Add additional extended port statistics.")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index e943f4138929..ab200d8bc119 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -6745,6 +6745,7 @@ static int bnxt_hwrm_port_qstats_ext(struct bnxt *bp)
 	struct hwrm_queue_pri2cos_qcfg_input req2 = {0};
 	struct hwrm_port_qstats_ext_input req = {0};
 	struct bnxt_pf_info *pf = &bp->pf;
+	u32 tx_stat_size;
 	int rc;
 
 	if (!(bp->flags & BNXT_FLAG_PORT_STATS_EXT))
@@ -6754,13 +6755,16 @@ static int bnxt_hwrm_port_qstats_ext(struct bnxt *bp)
 	req.port_id = cpu_to_le16(pf->port_id);
 	req.rx_stat_size = cpu_to_le16(sizeof(struct rx_port_stats_ext));
 	req.rx_stat_host_addr = cpu_to_le64(bp->hw_rx_port_stats_ext_map);
-	req.tx_stat_size = cpu_to_le16(sizeof(struct tx_port_stats_ext));
+	tx_stat_size = bp->hw_tx_port_stats_ext ?
+		       sizeof(*bp->hw_tx_port_stats_ext) : 0;
+	req.tx_stat_size = cpu_to_le16(tx_stat_size);
 	req.tx_stat_host_addr = cpu_to_le64(bp->hw_tx_port_stats_ext_map);
 	mutex_lock(&bp->hwrm_cmd_lock);
 	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 	if (!rc) {
 		bp->fw_rx_stats_ext_size = le16_to_cpu(resp->rx_stat_size) / 8;
-		bp->fw_tx_stats_ext_size = le16_to_cpu(resp->tx_stat_size) / 8;
+		bp->fw_tx_stats_ext_size = tx_stat_size ?
+			le16_to_cpu(resp->tx_stat_size) / 8 : 0;
 	} else {
 		bp->fw_rx_stats_ext_size = 0;
 		bp->fw_tx_stats_ext_size = 0;
-- 
2.20.1


From aeda54ce91998300db37e28875b7ade57427f84a Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Thu, 25 Apr 2019 22:31:54 -0400
Subject: [PATCH 24/27] bnxt_en: Fix statistics context reservation logic.

[ Upstream commit 3f93cd3f098e284c851acb89265ebe35b994a5c8 ]

In an earlier commit that fixes the number of stats contexts to
reserve for the RDMA driver, we added a function parameter to pass in
the number of stats contexts to all the relevant functions.  The passed
in parameter should have been used to set the enables field of the
firmware message.

Fixes: 780baad44f0f ("bnxt_en: Reserve 1 stat_ctx for RDMA driver.")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index ab200d8bc119..4dd99c28ab5b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -5311,17 +5311,16 @@ __bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, struct hwrm_func_cfg_input *req,
 	req->num_tx_rings = cpu_to_le16(tx_rings);
 	if (BNXT_NEW_RM(bp)) {
 		enables |= rx_rings ? FUNC_CFG_REQ_ENABLES_NUM_RX_RINGS : 0;
+		enables |= stats ? FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
 		if (bp->flags & BNXT_FLAG_CHIP_P5) {
 			enables |= cp_rings ? FUNC_CFG_REQ_ENABLES_NUM_MSIX : 0;
 			enables |= tx_rings + ring_grps ?
-				   FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS |
-				   FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
+				   FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS : 0;
 			enables |= rx_rings ?
 				FUNC_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS : 0;
 		} else {
 			enables |= cp_rings ?
-				   FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS |
-				   FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
+				   FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS : 0;
 			enables |= ring_grps ?
 				   FUNC_CFG_REQ_ENABLES_NUM_HW_RING_GRPS |
 				   FUNC_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS : 0;
@@ -5361,14 +5360,13 @@ __bnxt_hwrm_reserve_vf_rings(struct bnxt *bp,
 	enables |= tx_rings ? FUNC_VF_CFG_REQ_ENABLES_NUM_TX_RINGS : 0;
 	enables |= rx_rings ? FUNC_VF_CFG_REQ_ENABLES_NUM_RX_RINGS |
 			      FUNC_VF_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS : 0;
+	enables |= stats ? FUNC_VF_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
 	if (bp->flags & BNXT_FLAG_CHIP_P5) {
 		enables |= tx_rings + ring_grps ?
-			   FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS |
-			   FUNC_VF_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
+			   FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS : 0;
 	} else {
 		enables |= cp_rings ?
-			   FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS |
-			   FUNC_VF_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
+			   FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS : 0;
 		enables |= ring_grps ?
 			   FUNC_VF_CFG_REQ_ENABLES_NUM_HW_RING_GRPS : 0;
 	}
-- 
2.20.1


From f18bc67074cb91848e2b187e81dea6f0c539bd4a Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Thu, 25 Apr 2019 22:31:55 -0400
Subject: [PATCH 25/27] bnxt_en: Fix uninitialized variable usage in
 bnxt_rx_pkt().

[ Upstream commit 0b397b17a4120cb80f7bf89eb30587b3dd9b0d1d ]

In bnxt_rx_pkt(), if the driver encounters BD errors, it will recycle
the buffers and jump to the end where the uninitailized variable "len"
is referenced.  Fix it by adding a new jump label that will skip
the length update.  This is the most correct fix since the length
may not be valid when we get this type of error.

Fixes: 6a8788f25625 ("bnxt_en: add support for software dynamic interrupt moderation")
Reported-by: Nathan Chancellor <natechancellor@gmail.com>
Cc: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Reviewed-by: Nathan Chancellor <natechancellor@gmail.com>
Tested-by: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 4dd99c28ab5b..c6ddbc0e084e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1621,7 +1621,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 			netdev_warn(bp->dev, "RX buffer error %x\n", rx_err);
 			bnxt_sched_reset(bp, rxr);
 		}
-		goto next_rx;
+		goto next_rx_no_len;
 	}
 
 	len = le32_to_cpu(rxcmp->rx_cmp_len_flags_type) >> RX_CMP_LEN_SHIFT;
@@ -1702,12 +1702,13 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	rc = 1;
 
 next_rx:
-	rxr->rx_prod = NEXT_RX(prod);
-	rxr->rx_next_cons = NEXT_RX(cons);
-
 	cpr->rx_packets += 1;
 	cpr->rx_bytes += len;
 
+next_rx_no_len:
+	rxr->rx_prod = NEXT_RX(prod);
+	rxr->rx_next_cons = NEXT_RX(cons);
+
 next_rx_no_prod_no_len:
 	*raw_cons = tmp_raw_cons;
 
-- 
2.20.1


From c8893273cb0c9a689427a0d6bf05bb9bb55879ac Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu, 25 Apr 2019 17:35:09 -0700
Subject: [PATCH 26/27] net/tls: don't copy negative amounts of data in
 reencrypt

[ Upstream commit 97e1caa517e22d62a283b876fb8aa5f4672c83dd ]

There is no guarantee the record starts before the skb frags.
If we don't check for this condition copy amount will get
negative, leading to reads and writes to random memory locations.
Familiar hilarity ensues.

Fixes: 4799ac81e52a ("tls: Add rx inline crypto offload")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_device.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 5f1d937c4be9..4068101d43ea 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -610,14 +610,16 @@ static int tls_device_reencrypt(struct sock *sk, struct sk_buff *skb)
 	else
 		err = 0;
 
-	copy = min_t(int, skb_pagelen(skb) - offset,
-		     rxm->full_len - TLS_CIPHER_AES_GCM_128_TAG_SIZE);
+	if (skb_pagelen(skb) > offset) {
+		copy = min_t(int, skb_pagelen(skb) - offset,
+			     rxm->full_len - TLS_CIPHER_AES_GCM_128_TAG_SIZE);
 
-	if (skb->decrypted)
-		skb_store_bits(skb, offset, buf, copy);
+		if (skb->decrypted)
+			skb_store_bits(skb, offset, buf, copy);
 
-	offset += copy;
-	buf += copy;
+		offset += copy;
+		buf += copy;
+	}
 
 	skb_walk_frags(skb, skb_iter) {
 		copy = min_t(int, skb_iter->len,
-- 
2.20.1


From 4772f7e2813ab903c639c60f504a14720659eaef Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu, 25 Apr 2019 17:35:10 -0700
Subject: [PATCH 27/27] net/tls: fix copy to fragments in reencrypt

[ Upstream commit eb3d38d5adb520435d4e4af32529ccb13ccc9935 ]

Fragments may contain data from other records so we have to account
for that when we calculate the destination and max length of copy we
can perform.  Note that 'offset' is the offset within the message,
so it can't be passed as offset within the frag..

Here skb_store_bits() would have realised the call is wrong and
simply not copy data.

Fixes: 4799ac81e52a ("tls: Add rx inline crypto offload")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_device.c | 29 ++++++++++++++++++++++-------
 1 file changed, 22 insertions(+), 7 deletions(-)

diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 4068101d43ea..7d5136ecee78 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -579,7 +579,7 @@ void handle_device_resync(struct sock *sk, u32 seq, u64 rcd_sn)
 static int tls_device_reencrypt(struct sock *sk, struct sk_buff *skb)
 {
 	struct strp_msg *rxm = strp_msg(skb);
-	int err = 0, offset = rxm->offset, copy, nsg;
+	int err = 0, offset = rxm->offset, copy, nsg, data_len, pos;
 	struct sk_buff *skb_iter, *unused;
 	struct scatterlist sg[1];
 	char *orig_buf, *buf;
@@ -610,9 +610,10 @@ static int tls_device_reencrypt(struct sock *sk, struct sk_buff *skb)
 	else
 		err = 0;
 
+	data_len = rxm->full_len - TLS_CIPHER_AES_GCM_128_TAG_SIZE;
+
 	if (skb_pagelen(skb) > offset) {
-		copy = min_t(int, skb_pagelen(skb) - offset,
-			     rxm->full_len - TLS_CIPHER_AES_GCM_128_TAG_SIZE);
+		copy = min_t(int, skb_pagelen(skb) - offset, data_len);
 
 		if (skb->decrypted)
 			skb_store_bits(skb, offset, buf, copy);
@@ -621,16 +622,30 @@ static int tls_device_reencrypt(struct sock *sk, struct sk_buff *skb)
 		buf += copy;
 	}
 
+	pos = skb_pagelen(skb);
 	skb_walk_frags(skb, skb_iter) {
-		copy = min_t(int, skb_iter->len,
-			     rxm->full_len - offset + rxm->offset -
-			     TLS_CIPHER_AES_GCM_128_TAG_SIZE);
+		int frag_pos;
+
+		/* Practically all frags must belong to msg if reencrypt
+		 * is needed with current strparser and coalescing logic,
+		 * but strparser may "get optimized", so let's be safe.
+		 */
+		if (pos + skb_iter->len <= offset)
+			goto done_with_frag;
+		if (pos >= data_len + rxm->offset)
+			break;
+
+		frag_pos = offset - pos;
+		copy = min_t(int, skb_iter->len - frag_pos,
+			     data_len + rxm->offset - offset);
 
 		if (skb_iter->decrypted)
-			skb_store_bits(skb_iter, offset, buf, copy);
+			skb_store_bits(skb_iter, frag_pos, buf, copy);
 
 		offset += copy;
 		buf += copy;
+done_with_frag:
+		pos += skb_iter->len;
 	}
 
 free_buf:
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Sat, May 04, 2019 at 03:01:18AM -0400, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.19 and
> v5.0 -stable, respectively.
> 
> Thank you.

Thanks for these, all now queued up.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 105 bytes --]


Please queue up the following networking bug fixes for v5.0 and v5.1
-stable, respectively.

Thank you.

[-- Attachment #2: net_50.mbox --]
[-- Type: Application/Octet-Stream, Size: 52897 bytes --]

From 78e7973692762082b41cd0268aa724b650f921bc Mon Sep 17 00:00:00 2001
From: Jarod Wilson <jarod@redhat.com>
Date: Fri, 10 May 2019 17:57:09 -0400
Subject: [PATCH 01/23] bonding: fix arp_validate toggling in active-backup
 mode

[ Upstream commit a9b8a2b39ce65df45687cf9ef648885c2a99fe75 ]

There's currently a problem with toggling arp_validate on and off with an
active-backup bond. At the moment, you can start up a bond, like so:

modprobe bonding mode=1 arp_interval=100 arp_validate=0 arp_ip_targets=192.168.1.1
ip link set bond0 down
echo "ens4f0" > /sys/class/net/bond0/bonding/slaves
echo "ens4f1" > /sys/class/net/bond0/bonding/slaves
ip link set bond0 up
ip addr add 192.168.1.2/24 dev bond0

Pings to 192.168.1.1 work just fine. Now turn on arp_validate:

echo 1 > /sys/class/net/bond0/bonding/arp_validate

Pings to 192.168.1.1 continue to work just fine. Now when you go to turn
arp_validate off again, the link falls flat on it's face:

echo 0 > /sys/class/net/bond0/bonding/arp_validate
dmesg
...
[133191.911987] bond0: Setting arp_validate to none (0)
[133194.257793] bond0: bond_should_notify_peers: slave ens4f0
[133194.258031] bond0: link status definitely down for interface ens4f0, disabling it
[133194.259000] bond0: making interface ens4f1 the new active one
[133197.330130] bond0: link status definitely down for interface ens4f1, disabling it
[133197.331191] bond0: now running without any active interface!

The problem lies in bond_options.c, where passing in arp_validate=0
results in bond->recv_probe getting set to NULL. This flies directly in
the face of commit 3fe68df97c7f, which says we need to set recv_probe =
bond_arp_recv, even if we're not using arp_validate. Said commit fixed
this in bond_option_arp_interval_set, but missed that we can get to that
same state in bond_option_arp_validate_set as well.

One solution would be to universally set recv_probe = bond_arp_recv here
as well, but I don't think bond_option_arp_validate_set has any business
touching recv_probe at all, and that should be left to the arp_interval
code, so we can just make things much tidier here.

Fixes: 3fe68df97c7f ("bonding: always set recv_probe to bond_arp_rcv in arp monitor")
CC: Jay Vosburgh <j.vosburgh@gmail.com>
CC: Veaceslav Falico <vfalico@gmail.com>
CC: Andy Gospodarek <andy@greyhouse.net>
CC: "David S. Miller" <davem@davemloft.net>
CC: netdev@vger.kernel.org
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Signed-off-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_options.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 4d5d01cb8141..80867bd8f44c 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -1098,13 +1098,6 @@ static int bond_option_arp_validate_set(struct bonding *bond,
 {
 	netdev_dbg(bond->dev, "Setting arp_validate to %s (%llu)\n",
 		   newval->string, newval->value);
-
-	if (bond->dev->flags & IFF_UP) {
-		if (!newval->value)
-			bond->recv_probe = NULL;
-		else if (bond->params.arp_interval)
-			bond->recv_probe = bond_arp_rcv;
-	}
 	bond->params.arp_validate = newval->value;
 
 	return 0;
-- 
2.20.1


From 2ba93147485071a9866d16fb518627026aac8562 Mon Sep 17 00:00:00 2001
From: "Tobin C. Harding" <tobin@kernel.org>
Date: Fri, 10 May 2019 12:52:12 +1000
Subject: [PATCH 02/23] bridge: Fix error path for kobject_init_and_add()

[ Upstream commit bdfad5aec1392b93495b77b864d58d7f101dc1c1 ]

Currently error return from kobject_init_and_add() is not followed by a
call to kobject_put().  This means there is a memory leak.  We currently
set p to NULL so that kfree() may be called on it as a noop, the code is
arguably clearer if we move the kfree() up closer to where it is
called (instead of after goto jump).

Remove a goto label 'err1' and jump to call to kobject_put() in error
return from kobject_init_and_add() fixing the memory leak.  Re-name goto
label 'put_back' to 'err1' now that we don't use err1, following current
nomenclature (err1, err2 ...).  Move call to kfree out of the error
code at bottom of function up to closer to where memory was allocated.
Add comment to clarify call to kfree().

Signed-off-by: Tobin C. Harding <tobin@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_if.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 41f0a696a65f..0cb0aa0313a8 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -602,13 +602,15 @@ int br_add_if(struct net_bridge *br, struct net_device *dev,
 	call_netdevice_notifiers(NETDEV_JOIN, dev);
 
 	err = dev_set_allmulti(dev, 1);
-	if (err)
-		goto put_back;
+	if (err) {
+		kfree(p);	/* kobject not yet init'd, manually free */
+		goto err1;
+	}
 
 	err = kobject_init_and_add(&p->kobj, &brport_ktype, &(dev->dev.kobj),
 				   SYSFS_BRIDGE_PORT_ATTR);
 	if (err)
-		goto err1;
+		goto err2;
 
 	err = br_sysfs_addif(p);
 	if (err)
@@ -700,12 +702,9 @@ int br_add_if(struct net_bridge *br, struct net_device *dev,
 	sysfs_remove_link(br->ifobj, p->dev->name);
 err2:
 	kobject_put(&p->kobj);
-	p = NULL; /* kobject_put frees */
-err1:
 	dev_set_allmulti(dev, -1);
-put_back:
+err1:
 	dev_put(dev);
-	kfree(p);
 	return err;
 }
 
-- 
2.20.1


From f5f5e90697de0b306d3e799eabe4c856b8bdfc44 Mon Sep 17 00:00:00 2001
From: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Date: Fri, 3 May 2019 16:03:11 +0300
Subject: [PATCH 03/23] dpaa_eth: fix SG frame cleanup

[ Upstream commit 17170e6570c082717c142733d9a638bcd20551f8 ]

Fix issue with the entry indexing in the sg frame cleanup code being
off-by-1. This problem showed up when doing some basic iperf tests and
manifested in traffic coming to a halt.

Signed-off-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Acked-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index dfebc30c4841..d3f2408dc9e8 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -1648,7 +1648,7 @@ static struct sk_buff *dpaa_cleanup_tx_fd(const struct dpaa_priv *priv,
 				 qm_sg_entry_get_len(&sgt[0]), dma_dir);
 
 		/* remaining pages were mapped with skb_frag_dma_map() */
-		for (i = 1; i < nr_frags; i++) {
+		for (i = 1; i <= nr_frags; i++) {
 			WARN_ON(qm_sg_entry_is_ext(&sgt[i]));
 
 			dma_unmap_page(dev, qm_sg_addr(&sgt[i]),
-- 
2.20.1


From 987edd235ebd1115f930c0d51024bc1b55ce5155 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Tue, 7 May 2019 17:11:18 +0800
Subject: [PATCH 04/23] fib_rules: return 0 directly if an exactly same rule
 exists when NLM_F_EXCL not supplied

[ Upstream commit e9919a24d3022f72bcadc407e73a6ef17093a849 ]

With commit 153380ec4b9 ("fib_rules: Added NLM_F_EXCL support to
fib_nl_newrule") we now able to check if a rule already exists. But this
only works with iproute2. For other tools like libnl, NetworkManager,
it still could add duplicate rules with only NLM_F_CREATE flag, like

[localhost ~ ]# ip rule
0:      from all lookup local
32766:  from all lookup main
32767:  from all lookup default
100000: from 192.168.7.5 lookup 5
100000: from 192.168.7.5 lookup 5

As it doesn't make sense to create two duplicate rules, let's just return
0 if the rule exists.

Fixes: 153380ec4b9 ("fib_rules: Added NLM_F_EXCL support to fib_nl_newrule")
Reported-by: Thomas Haller <thaller@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/fib_rules.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index ffbb827723a2..c49b752ea7eb 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -756,9 +756,9 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (err)
 		goto errout;
 
-	if ((nlh->nlmsg_flags & NLM_F_EXCL) &&
-	    rule_exists(ops, frh, tb, rule)) {
-		err = -EEXIST;
+	if (rule_exists(ops, frh, tb, rule)) {
+		if (nlh->nlmsg_flags & NLM_F_EXCL)
+			err = -EEXIST;
 		goto errout_free;
 	}
 
-- 
2.20.1


From 5cc59a552c2a237b29274f5670495813d4c6224d Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 7 May 2019 20:44:59 -0700
Subject: [PATCH 05/23] ipv4: Fix raw socket lookup for local traffic

[ Upstream commit 19e4e768064a87b073a4b4c138b55db70e0cfb9f ]

inet_iif should be used for the raw socket lookup. inet_iif considers
rt_iif which handles the case of local traffic.

As it stands, ping to a local address with the '-I <dev>' option fails
ever since ping was changed to use SO_BINDTODEVICE instead of
cmsg + IP_PKTINFO.

IPv6 works fine.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/raw.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index c55a5432cf37..dc91c27bb788 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -173,6 +173,7 @@ static int icmp_filter(const struct sock *sk, const struct sk_buff *skb)
 static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash)
 {
 	int sdif = inet_sdif(skb);
+	int dif = inet_iif(skb);
 	struct sock *sk;
 	struct hlist_head *head;
 	int delivered = 0;
@@ -185,8 +186,7 @@ static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash)
 
 	net = dev_net(skb->dev);
 	sk = __raw_v4_lookup(net, __sk_head(head), iph->protocol,
-			     iph->saddr, iph->daddr,
-			     skb->dev->ifindex, sdif);
+			     iph->saddr, iph->daddr, dif, sdif);
 
 	while (sk) {
 		delivered = 1;
-- 
2.20.1


From d3fc5c3f9ee841c0e9965e180514f63904ca4fe5 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Mon, 6 May 2019 23:25:29 +0800
Subject: [PATCH 06/23] net: dsa: Fix error cleanup path in dsa_init_module

[ Upstream commit 68be930249d051fd54d3d99156b3dcadcb2a1f9b ]

BUG: unable to handle kernel paging request at ffffffffa01c5430
PGD 3270067 P4D 3270067 PUD 3271063 PMD 230bc5067 PTE 0
Oops: 0000 [#1
CPU: 0 PID: 6159 Comm: modprobe Not tainted 5.1.0+ #33
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.3-0-ge2fc41e-prebuilt.qemu-project.org 04/01/2014
RIP: 0010:raw_notifier_chain_register+0x16/0x40
Code: 63 f8 66 90 e9 5d ff ff ff 90 90 90 90 90 90 90 90 90 90 90 55 48 8b 07 48 89 e5 48 85 c0 74 1c 8b 56 10 3b 50 10 7e 07 eb 12 <39> 50 10 7c 0d 48 8d 78 08 48 8b 40 08 48 85 c0 75 ee 48 89 46 08
RSP: 0018:ffffc90001c33c08 EFLAGS: 00010282
RAX: ffffffffa01c5420 RBX: ffffffffa01db420 RCX: 4fcef45928070a8b
RDX: 0000000000000000 RSI: ffffffffa01db420 RDI: ffffffffa01b0068
RBP: ffffc90001c33c08 R08: 000000003e0a33d0 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000094443661 R12: ffff88822c320700
R13: ffff88823109be80 R14: 0000000000000000 R15: ffffc90001c33e78
FS:  00007fab8bd08540(0000) GS:ffff888237a00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffffffffa01c5430 CR3: 00000002297ea000 CR4: 00000000000006f0
Call Trace:
 register_netdevice_notifier+0x43/0x250
 ? 0xffffffffa01e0000
 dsa_slave_register_notifier+0x13/0x70 [dsa_core
 ? 0xffffffffa01e0000
 dsa_init_module+0x2e/0x1000 [dsa_core
 do_one_initcall+0x6c/0x3cc
 ? do_init_module+0x22/0x1f1
 ? rcu_read_lock_sched_held+0x97/0xb0
 ? kmem_cache_alloc_trace+0x325/0x3b0
 do_init_module+0x5b/0x1f1
 load_module+0x1db1/0x2690
 ? m_show+0x1d0/0x1d0
 __do_sys_finit_module+0xc5/0xd0
 __x64_sys_finit_module+0x15/0x20
 do_syscall_64+0x6b/0x1d0
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Cleanup allocated resourses if there are errors,
otherwise it will trgger memleak.

Fixes: c9eb3e0f8701 ("net: dsa: Add support for learning FDB through notification")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Reviewed-by: Vivien Didelot <vivien.didelot@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/dsa.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index aee909bcddc4..41d534d3f42b 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -342,15 +342,22 @@ static int __init dsa_init_module(void)
 
 	rc = dsa_slave_register_notifier();
 	if (rc)
-		return rc;
+		goto register_notifier_fail;
 
 	rc = dsa_legacy_register();
 	if (rc)
-		return rc;
+		goto legacy_register_fail;
 
 	dev_add_pack(&dsa_pack_type);
 
 	return 0;
+
+legacy_register_fail:
+	dsa_slave_unregister_notifier();
+register_notifier_fail:
+	destroy_workqueue(dsa_owq);
+
+	return rc;
 }
 module_init(dsa_init_module);
 
-- 
2.20.1


From 495523238d3ab3866e57d03cedf01050819a26d4 Mon Sep 17 00:00:00 2001
From: Corentin Labbe <clabbe@baylibre.com>
Date: Mon, 13 May 2019 13:06:39 +0000
Subject: [PATCH 07/23] net: ethernet: stmmac: dwmac-sun8i: enable support of
 unicast filtering

[ Upstream commit d4c26eb6e721683a0f93e346ce55bc8dc3cbb175 ]

When adding more MAC addresses to a dwmac-sun8i interface, the device goes
directly in promiscuous mode.
This is due to IFF_UNICAST_FLT missing flag.

So since the hardware support unicast filtering, let's add IFF_UNICAST_FLT.

Fixes: 9f93ac8d4085 ("net-next: stmmac: Add dwmac-sun8i")
Signed-off-by: Corentin Labbe <clabbe@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index 0f660af01a4b..49a896a16391 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -1015,6 +1015,8 @@ static struct mac_device_info *sun8i_dwmac_setup(void *ppriv)
 	mac->mac = &sun8i_dwmac_ops;
 	mac->dma = &sun8i_dwmac_dma_ops;
 
+	priv->dev->priv_flags |= IFF_UNICAST_FLT;
+
 	/* The loopback bit seems to be re-set when link change
 	 * Simply mask it each time
 	 * Speed 10/100/1000 are set in BIT(2)/BIT(3)
-- 
2.20.1


From 6ccafbbb27c980c52fe836a98ca1dfab1de3f14b Mon Sep 17 00:00:00 2001
From: Harini Katakam <harini.katakam@xilinx.com>
Date: Tue, 7 May 2019 19:59:10 +0530
Subject: [PATCH 08/23] net: macb: Change interrupt and napi enable order in
 open

[ Upstream commit 0504453139ef5a593c9587e1e851febee859c7d8 ]

Current order in open:
-> Enable interrupts (macb_init_hw)
-> Enable NAPI
-> Start PHY

Sequence of RX handling:
-> RX interrupt occurs
-> Interrupt is cleared and interrupt bits disabled in handler
-> NAPI is scheduled
-> In NAPI, RX budget is processed and RX interrupts are re-enabled

With the above, on QEMU or fixed link setups (where PHY state doesn't
matter), there's a chance macb RX interrupt occurs before NAPI is
enabled. This will result in NAPI being scheduled before it is enabled.
Fix this macb open by changing the order.

Fixes: ae1f2a56d273 ("net: macb: Added support for many RX queues")
Signed-off-by: Harini Katakam <harini.katakam@xilinx.com>
Acked-by: Nicolas Ferre <nicolas.ferre@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 6cbe515bfdeb..8a57888e9765 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -2414,12 +2414,12 @@ static int macb_open(struct net_device *dev)
 		return err;
 	}
 
-	bp->macbgem_ops.mog_init_rings(bp);
-	macb_init_hw(bp);
-
 	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
 		napi_enable(&queue->napi);
 
+	bp->macbgem_ops.mog_init_rings(bp);
+	macb_init_hw(bp);
+
 	/* schedule a link state check */
 	phy_start(dev->phydev);
 
-- 
2.20.1


From 0d6690871afc76d5a5749eca9f21a7dd0bb82110 Mon Sep 17 00:00:00 2001
From: Thomas Bogendoerfer <tbogendoerfer@suse.de>
Date: Mon, 13 May 2019 13:15:17 +0200
Subject: [PATCH 09/23] net: seeq: fix crash caused by not set dev.parent

[ Upstream commit 5afcd14cfc7fed1bcc8abcee2cef82732772bfc2 ]

The old MIPS implementation of dma_cache_sync() didn't use the dev argument,
but commit c9eb6172c328 ("dma-mapping: turn dma_cache_sync into a
dma_map_ops method") changed that, so we now need to set dev.parent.

Signed-off-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/seeq/sgiseeq.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/seeq/sgiseeq.c b/drivers/net/ethernet/seeq/sgiseeq.c
index 70cce63a6081..696037d5ac3d 100644
--- a/drivers/net/ethernet/seeq/sgiseeq.c
+++ b/drivers/net/ethernet/seeq/sgiseeq.c
@@ -735,6 +735,7 @@ static int sgiseeq_probe(struct platform_device *pdev)
 	}
 
 	platform_set_drvdata(pdev, dev);
+	SET_NETDEV_DEV(dev, &pdev->dev);
 	sp = netdev_priv(dev);
 
 	/* Make private data page aligned */
-- 
2.20.1


From b01783adb7852e0452ff87eeb595ef72b4799834 Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@c-s.fr>
Date: Fri, 3 May 2019 13:33:23 +0000
Subject: [PATCH 10/23] net: ucc_geth - fix Oops when changing number of
 buffers in the ring

[ Upstream commit ee0df19305d9fabd9479b785918966f6e25b733b ]

When changing the number of buffers in the RX ring while the interface
is running, the following Oops is encountered due to the new number
of buffers being taken into account immediately while their allocation
is done when opening the device only.

[   69.882706] Unable to handle kernel paging request for data at address 0xf0000100
[   69.890172] Faulting instruction address: 0xc033e164
[   69.895122] Oops: Kernel access of bad area, sig: 11 [#1]
[   69.900494] BE PREEMPT CMPCPRO
[   69.907120] CPU: 0 PID: 0 Comm: swapper Not tainted 4.14.115-00006-g179ade8ce3-dirty #269
[   69.915956] task: c0684310 task.stack: c06da000
[   69.920470] NIP:  c033e164 LR: c02e44d0 CTR: c02e41fc
[   69.925504] REGS: dfff1e20 TRAP: 0300   Not tainted  (4.14.115-00006-g179ade8ce3-dirty)
[   69.934161] MSR:  00009032 <EE,ME,IR,DR,RI>  CR: 22004428  XER: 20000000
[   69.940869] DAR: f0000100 DSISR: 20000000
[   69.940869] GPR00: c0352d70 dfff1ed0 c0684310 f00000a4 00000040 dfff1f68 00000000 0000001f
[   69.940869] GPR08: df53f410 1cc00040 00000021 c0781640 42004424 100c82b6 f00000a4 df53f5b0
[   69.940869] GPR16: df53f6c0 c05daf84 00000040 00000000 00000040 c0782be4 00000000 00000001
[   69.940869] GPR24: 00000000 df53f400 000001b0 df53f410 df53f000 0000003f df708220 1cc00044
[   69.978348] NIP [c033e164] skb_put+0x0/0x5c
[   69.982528] LR [c02e44d0] ucc_geth_poll+0x2d4/0x3f8
[   69.987384] Call Trace:
[   69.989830] [dfff1ed0] [c02e4554] ucc_geth_poll+0x358/0x3f8 (unreliable)
[   69.996522] [dfff1f20] [c0352d70] net_rx_action+0x248/0x30c
[   70.002099] [dfff1f80] [c04e93e4] __do_softirq+0xfc/0x310
[   70.007492] [dfff1fe0] [c0021124] irq_exit+0xd0/0xd4
[   70.012458] [dfff1ff0] [c000e7e0] call_do_irq+0x24/0x3c
[   70.017683] [c06dbe80] [c0006bac] do_IRQ+0x64/0xc4
[   70.022474] [c06dbea0] [c001097c] ret_from_except+0x0/0x14
[   70.027964] --- interrupt: 501 at rcu_idle_exit+0x84/0x90
[   70.027964]     LR = rcu_idle_exit+0x74/0x90
[   70.037585] [c06dbf60] [20000000] 0x20000000 (unreliable)
[   70.042984] [c06dbf80] [c004bb0c] do_idle+0xb4/0x11c
[   70.047945] [c06dbfa0] [c004bd14] cpu_startup_entry+0x18/0x1c
[   70.053682] [c06dbfb0] [c05fb034] start_kernel+0x370/0x384
[   70.059153] [c06dbff0] [00003438] 0x3438
[   70.063062] Instruction dump:
[   70.066023] 38a00000 38800000 90010014 4bfff015 80010014 7c0803a6 3123ffff 7c691910
[   70.073767] 38210010 4e800020 38600000 4e800020 <80e3005c> 80c30098 3107ffff 7d083910
[   70.081690] ---[ end trace be7ccd9c1e1a9f12 ]---

This patch forbids the modification of the number of buffers in the
ring while the interface is running.

Fixes: ac421852b3a0 ("ucc_geth: add ethtool support")
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/ucc_geth_ethtool.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/freescale/ucc_geth_ethtool.c b/drivers/net/ethernet/freescale/ucc_geth_ethtool.c
index 0beee2cc2ddd..722b6de24816 100644
--- a/drivers/net/ethernet/freescale/ucc_geth_ethtool.c
+++ b/drivers/net/ethernet/freescale/ucc_geth_ethtool.c
@@ -252,14 +252,12 @@ uec_set_ringparam(struct net_device *netdev,
 		return -EINVAL;
 	}
 
+	if (netif_running(netdev))
+		return -EBUSY;
+
 	ug_info->bdRingLenRx[queue] = ring->rx_pending;
 	ug_info->bdRingLenTx[queue] = ring->tx_pending;
 
-	if (netif_running(netdev)) {
-		/* FIXME: restart automatically */
-		netdev_info(netdev, "Please re-open the interface\n");
-	}
-
 	return ret;
 }
 
-- 
2.20.1


From baa06865cb64c879c8a8ea66c5d89e8607c878b9 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Thu, 9 May 2019 22:52:20 +0800
Subject: [PATCH 11/23] packet: Fix error path in packet_init

[ Upstream commit 36096f2f4fa05f7678bc87397665491700bae757 ]

kernel BUG at lib/list_debug.c:47!
invalid opcode: 0000 [#1
CPU: 0 PID: 12914 Comm: rmmod Tainted: G        W         5.1.0+ #47
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.3-0-ge2fc41e-prebuilt.qemu-project.org 04/01/2014
RIP: 0010:__list_del_entry_valid+0x53/0x90
Code: 48 8b 32 48 39 fe 75 35 48 8b 50 08 48 39 f2 75 40 b8 01 00 00 00 5d c3 48
89 fe 48 89 c2 48 c7 c7 18 75 fe 82 e8 cb 34 78 ff <0f> 0b 48 89 fe 48 c7 c7 50 75 fe 82 e8 ba 34 78 ff 0f 0b 48 89 f2
RSP: 0018:ffffc90001c2fe40 EFLAGS: 00010286
RAX: 000000000000004e RBX: ffffffffa0184000 RCX: 0000000000000000
RDX: 0000000000000000 RSI: ffff888237a17788 RDI: 00000000ffffffff
RBP: ffffc90001c2fe40 R08: 0000000000000000 R09: 0000000000000000
R10: ffffc90001c2fe10 R11: 0000000000000000 R12: 0000000000000000
R13: ffffc90001c2fe50 R14: ffffffffa0184000 R15: 0000000000000000
FS:  00007f3d83634540(0000) GS:ffff888237a00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000555c350ea818 CR3: 0000000231677000 CR4: 00000000000006f0
Call Trace:
 unregister_pernet_operations+0x34/0x120
 unregister_pernet_subsys+0x1c/0x30
 packet_exit+0x1c/0x369 [af_packet
 __x64_sys_delete_module+0x156/0x260
 ? lockdep_hardirqs_on+0x133/0x1b0
 ? do_syscall_64+0x12/0x1f0
 do_syscall_64+0x6e/0x1f0
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

When modprobe af_packet, register_pernet_subsys
fails and does a cleanup, ops->list is set to LIST_POISON1,
but the module init is considered to success, then while rmmod it,
BUG() is triggered in __list_del_entry_valid which is called from
unregister_pernet_subsys. This patch fix error handing path in
packet_init to avoid possilbe issue if some error occur.

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 25 ++++++++++++++++++++-----
 1 file changed, 20 insertions(+), 5 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index faa2bc50cfa0..b6c23af4a315 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -4604,14 +4604,29 @@ static void __exit packet_exit(void)
 
 static int __init packet_init(void)
 {
-	int rc = proto_register(&packet_proto, 0);
+	int rc;
 
-	if (rc != 0)
+	rc = proto_register(&packet_proto, 0);
+	if (rc)
 		goto out;
+	rc = sock_register(&packet_family_ops);
+	if (rc)
+		goto out_proto;
+	rc = register_pernet_subsys(&packet_net_ops);
+	if (rc)
+		goto out_sock;
+	rc = register_netdevice_notifier(&packet_netdev_notifier);
+	if (rc)
+		goto out_pernet;
 
-	sock_register(&packet_family_ops);
-	register_pernet_subsys(&packet_net_ops);
-	register_netdevice_notifier(&packet_netdev_notifier);
+	return 0;
+
+out_pernet:
+	unregister_pernet_subsys(&packet_net_ops);
+out_sock:
+	sock_unregister(PF_PACKET);
+out_proto:
+	proto_unregister(&packet_proto);
 out:
 	return rc;
 }
-- 
2.20.1


From 4e55af493a01184be8e931e45b9e3466f370f497 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 8 May 2019 15:32:51 +0200
Subject: [PATCH 12/23] selinux: do not report error on connect(AF_UNSPEC)

[ Upstream commit c7e0d6cca86581092cbbf2cd868b3601495554cf ]

calling connect(AF_UNSPEC) on an already connected TCP socket is an
established way to disconnect() such socket. After commit 68741a8adab9
("selinux: Fix ltp test connect-syscall failure") it no longer works
and, in the above scenario connect() fails with EAFNOSUPPORT.

Fix the above falling back to the generic/old code when the address family
is not AF_INET{4,6}, but leave the SCTP code path untouched, as it has
specific constraints.

Fixes: 68741a8adab9 ("selinux: Fix ltp test connect-syscall failure")
Reported-by: Tom Deseyn <tdeseyn@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 security/selinux/hooks.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index b005283f0090..bc4aec97723a 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -4586,7 +4586,7 @@ static int selinux_socket_connect_helper(struct socket *sock,
 		struct lsm_network_audit net = {0,};
 		struct sockaddr_in *addr4 = NULL;
 		struct sockaddr_in6 *addr6 = NULL;
-		unsigned short snum;
+		unsigned short snum = 0;
 		u32 sid, perm;
 
 		/* sctp_connectx(3) calls via selinux_sctp_bind_connect()
@@ -4609,12 +4609,12 @@ static int selinux_socket_connect_helper(struct socket *sock,
 			break;
 		default:
 			/* Note that SCTP services expect -EINVAL, whereas
-			 * others expect -EAFNOSUPPORT.
+			 * others must handle this at the protocol level:
+			 * connect(AF_UNSPEC) on a connected socket is
+			 * a documented way disconnect the socket.
 			 */
 			if (sksec->sclass == SECCLASS_SCTP_SOCKET)
 				return -EINVAL;
-			else
-				return -EAFNOSUPPORT;
 		}
 
 		err = sel_netport_sid(sk->sk_protocol, snum, &sid);
-- 
2.20.1


From 0cacd1b33d00259762fb794dbced0f9f5dd0866e Mon Sep 17 00:00:00 2001
From: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@gmail.com>
Date: Thu, 9 May 2019 07:13:42 +0200
Subject: [PATCH 13/23] tipc: fix hanging clients using poll with EPOLLOUT flag

[ Upstream commit ff946833b70e0c7f93de9a3f5b329b5ae2287b38 ]

commit 517d7c79bdb398 ("tipc: fix hanging poll() for stream sockets")
introduced a regression for clients using non-blocking sockets.
After the commit, we send EPOLLOUT event to the client even in
TIPC_CONNECTING state. This causes the subsequent send() to fail
with ENOTCONN, as the socket is still not in TIPC_ESTABLISHED state.

In this commit, we:
- improve the fix for hanging poll() by replacing sk_data_ready()
  with sk_state_change() to wake up all clients.
- revert the faulty updates introduced by commit 517d7c79bdb398
  ("tipc: fix hanging poll() for stream sockets").

Fixes: 517d7c79bdb398 ("tipc: fix hanging poll() for stream sockets")
Signed-off-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@gmail.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.se>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/socket.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 4dca9161f99b..020477ff91a2 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -734,11 +734,11 @@ static __poll_t tipc_poll(struct file *file, struct socket *sock,
 
 	switch (sk->sk_state) {
 	case TIPC_ESTABLISHED:
-	case TIPC_CONNECTING:
 		if (!tsk->cong_link_cnt && !tsk_conn_cong(tsk))
 			revents |= EPOLLOUT;
 		/* fall thru' */
 	case TIPC_LISTEN:
+	case TIPC_CONNECTING:
 		if (!skb_queue_empty(&sk->sk_receive_queue))
 			revents |= EPOLLIN | EPOLLRDNORM;
 		break;
@@ -2041,7 +2041,7 @@ static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb)
 			if (msg_data_sz(hdr))
 				return true;
 			/* Empty ACK-, - wake up sleeping connect() and drop */
-			sk->sk_data_ready(sk);
+			sk->sk_state_change(sk);
 			msg_set_dest_droppable(hdr, 1);
 			return false;
 		}
-- 
2.20.1


From 478ecc1683eeceaa9639d5f8943e7b40b204bf93 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Thu, 9 May 2019 14:55:07 +0800
Subject: [PATCH 14/23] vlan: disable SIOCSHWTSTAMP in container

[ Upstream commit 873017af778439f2f8e3d87f28ddb1fcaf244a76 ]

With NET_ADMIN enabled in container, a normal user could be mapped to
root and is able to change the real device's rx filter via ioctl on
vlan, which would affect the other ptp process on host. Fix it by
disabling SIOCSHWTSTAMP in container.

Fixes: a6111d3c93d0 ("vlan: Pass SIOC[SG]HWTSTAMP ioctls to real device")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/8021q/vlan_dev.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index b2d9c8f27cd7..1991ce2eb268 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -368,10 +368,12 @@ static int vlan_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	ifrr.ifr_ifru = ifr->ifr_ifru;
 
 	switch (cmd) {
+	case SIOCSHWTSTAMP:
+		if (!net_eq(dev_net(dev), &init_net))
+			break;
 	case SIOCGMIIPHY:
 	case SIOCGMIIREG:
 	case SIOCSMIIREG:
-	case SIOCSHWTSTAMP:
 	case SIOCGHWTSTAMP:
 		if (netif_device_present(real_dev) && ops->ndo_do_ioctl)
 			err = ops->ndo_do_ioctl(real_dev, &ifrr, cmd);
-- 
2.20.1


From 45446751f140687655ecce76662f11c4dfed10bd Mon Sep 17 00:00:00 2001
From: Stephen Suryaputra <ssuryaextr@gmail.com>
Date: Mon, 6 May 2019 15:00:01 -0400
Subject: [PATCH 15/23] vrf: sit mtu should not be updated when vrf netdev is
 the link

[ Upstream commit ff6ab32bd4e073976e4d8797b4d514a172cfe6cb ]

VRF netdev mtu isn't typically set and have an mtu of 65536. When the
link of a tunnel is set, the tunnel mtu is changed from 1480 to the link
mtu minus tunnel header. In the case of VRF netdev is the link, then the
tunnel mtu becomes 65516. So, fix it by not setting the tunnel mtu in
this case.

Signed-off-by: Stephen Suryaputra <ssuryaextr@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index b2109b74857d..971d60bf9640 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1084,7 +1084,7 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev)
 	if (!tdev && tunnel->parms.link)
 		tdev = __dev_get_by_index(tunnel->net, tunnel->parms.link);
 
-	if (tdev) {
+	if (tdev && !netif_is_l3_master(tdev)) {
 		int t_hlen = tunnel->hlen + sizeof(struct iphdr);
 
 		dev->hard_header_len = tdev->hard_header_len + sizeof(struct iphdr);
-- 
2.20.1


From cfb879e92b75f1bd504f81415ed97284c0ef5171 Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.com>
Date: Thu, 9 May 2019 11:08:16 +0200
Subject: [PATCH 16/23] aqc111: fix endianness issue in aqc111_change_mtu

[ Upstream commit b8b277525e9df2fd2dc3d1f4fe01c6796bb107fc ]

If the MTU is large enough, the first write to the device
is just repeated. On BE architectures, however, the first
word of the command will be swapped a second time and garbage
will be written. Avoid that.

Signed-off-by: Oliver Neukum <oneukum@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/aqc111.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index aff995be2a31..408df2d335e3 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -453,6 +453,8 @@ static int aqc111_change_mtu(struct net_device *net, int new_mtu)
 		reg16 = 0x1420;
 	else if (dev->net->mtu <= 16334)
 		reg16 = 0x1A20;
+	else
+		return 0;
 
 	aqc111_write16_cmd(dev, AQ_ACCESS_MAC, SFR_PAUSE_WATERLVL_LOW,
 			   2, &reg16);
-- 
2.20.1


From 511071a6a48b95bb1a9feb1355d1864ecaac537c Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.com>
Date: Thu, 9 May 2019 11:08:17 +0200
Subject: [PATCH 17/23] aqc111: fix writing to the phy on BE

[ Upstream commit 369b46e9fbcfa5136f2cb5f486c90e5f7fa92630 ]

When writing to the phy on BE architectures an internal data structure
was directly given, leading to it being byte swapped in the wrong
way for the CPU in 50% of all cases. A temporary buffer must be used.

Signed-off-by: Oliver Neukum <oneukum@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/aqc111.c | 23 +++++++++++++++++------
 1 file changed, 17 insertions(+), 6 deletions(-)

diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index 408df2d335e3..599d560a8450 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -320,6 +320,7 @@ static int aqc111_get_link_ksettings(struct net_device *net,
 static void aqc111_set_phy_speed(struct usbnet *dev, u8 autoneg, u16 speed)
 {
 	struct aqc111_data *aqc111_data = dev->driver_priv;
+	u32 phy_on_the_wire;
 
 	aqc111_data->phy_cfg &= ~AQ_ADV_MASK;
 	aqc111_data->phy_cfg |= AQ_PAUSE;
@@ -361,7 +362,8 @@ static void aqc111_set_phy_speed(struct usbnet *dev, u8 autoneg, u16 speed)
 		}
 	}
 
-	aqc111_write32_cmd(dev, AQ_PHY_OPS, 0, 0, &aqc111_data->phy_cfg);
+	phy_on_the_wire = aqc111_data->phy_cfg;
+	aqc111_write32_cmd(dev, AQ_PHY_OPS, 0, 0, &phy_on_the_wire);
 }
 
 static int aqc111_set_link_ksettings(struct net_device *net,
@@ -755,6 +757,7 @@ static void aqc111_unbind(struct usbnet *dev, struct usb_interface *intf)
 {
 	struct aqc111_data *aqc111_data = dev->driver_priv;
 	u16 reg16;
+	u32 phy_on_the_wire;
 
 	/* Force bz */
 	reg16 = SFR_PHYPWR_RSTCTL_BZ;
@@ -768,8 +771,9 @@ static void aqc111_unbind(struct usbnet *dev, struct usb_interface *intf)
 	aqc111_data->phy_cfg &= ~AQ_ADV_MASK;
 	aqc111_data->phy_cfg |= AQ_LOW_POWER;
 	aqc111_data->phy_cfg &= ~AQ_PHY_POWER_EN;
+	phy_on_the_wire = aqc111_data->phy_cfg;
 	aqc111_write32_cmd_nopm(dev, AQ_PHY_OPS, 0, 0,
-				&aqc111_data->phy_cfg);
+				&phy_on_the_wire);
 
 	kfree(aqc111_data);
 }
@@ -992,6 +996,7 @@ static int aqc111_reset(struct usbnet *dev)
 {
 	struct aqc111_data *aqc111_data = dev->driver_priv;
 	u8 reg8 = 0;
+	u32 phy_on_the_wire;
 
 	dev->rx_urb_size = URB_SIZE;
 
@@ -1004,8 +1009,9 @@ static int aqc111_reset(struct usbnet *dev)
 
 	/* Power up ethernet PHY */
 	aqc111_data->phy_cfg = AQ_PHY_POWER_EN;
+	phy_on_the_wire = aqc111_data->phy_cfg;
 	aqc111_write32_cmd(dev, AQ_PHY_OPS, 0, 0,
-			   &aqc111_data->phy_cfg);
+			   &phy_on_the_wire);
 
 	/* Set the MAC address */
 	aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_NODE_ID, ETH_ALEN,
@@ -1036,6 +1042,7 @@ static int aqc111_stop(struct usbnet *dev)
 {
 	struct aqc111_data *aqc111_data = dev->driver_priv;
 	u16 reg16 = 0;
+	u32 phy_on_the_wire;
 
 	aqc111_read16_cmd(dev, AQ_ACCESS_MAC, SFR_MEDIUM_STATUS_MODE,
 			  2, &reg16);
@@ -1047,8 +1054,9 @@ static int aqc111_stop(struct usbnet *dev)
 
 	/* Put PHY to low power*/
 	aqc111_data->phy_cfg |= AQ_LOW_POWER;
+	phy_on_the_wire = aqc111_data->phy_cfg;
 	aqc111_write32_cmd(dev, AQ_PHY_OPS, 0, 0,
-			   &aqc111_data->phy_cfg);
+			   &phy_on_the_wire);
 
 	netif_carrier_off(dev->net);
 
@@ -1324,6 +1332,7 @@ static int aqc111_suspend(struct usb_interface *intf, pm_message_t message)
 	u16 temp_rx_ctrl = 0x00;
 	u16 reg16;
 	u8 reg8;
+	u32 phy_on_the_wire;
 
 	usbnet_suspend(intf, message);
 
@@ -1395,12 +1404,14 @@ static int aqc111_suspend(struct usb_interface *intf, pm_message_t message)
 
 		aqc111_write_cmd(dev, AQ_WOL_CFG, 0, 0,
 				 WOL_CFG_SIZE, &wol_cfg);
+		phy_on_the_wire = aqc111_data->phy_cfg;
 		aqc111_write32_cmd(dev, AQ_PHY_OPS, 0, 0,
-				   &aqc111_data->phy_cfg);
+				   &phy_on_the_wire);
 	} else {
 		aqc111_data->phy_cfg |= AQ_LOW_POWER;
+		phy_on_the_wire = aqc111_data->phy_cfg;
 		aqc111_write32_cmd(dev, AQ_PHY_OPS, 0, 0,
-				   &aqc111_data->phy_cfg);
+				   &phy_on_the_wire);
 
 		/* Disable RX path */
 		aqc111_read16_cmd_nopm(dev, AQ_ACCESS_MAC,
-- 
2.20.1


From 7b67ae2a629b5900c92d70771c056708052152ea Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.com>
Date: Thu, 9 May 2019 11:08:18 +0200
Subject: [PATCH 18/23] aqc111: fix double endianness swap on BE

[ Upstream commit 2cf672709beb005f6e90cb4edbed6f2218ba953e ]

If you are using a function that does a swap in place,
you cannot just reuse the buffer on the assumption that it has
not been changed.

Signed-off-by: Oliver Neukum <oneukum@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/aqc111.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index 599d560a8450..b86c5ce9a92a 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -1428,7 +1428,7 @@ static int aqc111_resume(struct usb_interface *intf)
 {
 	struct usbnet *dev = usb_get_intfdata(intf);
 	struct aqc111_data *aqc111_data = dev->driver_priv;
-	u16 reg16;
+	u16 reg16, oldreg16;
 	u8 reg8;
 
 	netif_carrier_off(dev->net);
@@ -1444,9 +1444,11 @@ static int aqc111_resume(struct usb_interface *intf)
 	/* Configure RX control register => start operation */
 	reg16 = aqc111_data->rxctl;
 	reg16 &= ~SFR_RX_CTL_START;
+	/* needs to be saved in case endianness is swapped */
+	oldreg16 = reg16;
 	aqc111_write16_cmd_nopm(dev, AQ_ACCESS_MAC, SFR_RX_CTL, 2, &reg16);
 
-	reg16 |= SFR_RX_CTL_START;
+	reg16 = oldreg16 | SFR_RX_CTL_START;
 	aqc111_write16_cmd_nopm(dev, AQ_ACCESS_MAC, SFR_RX_CTL, 2, &reg16);
 
 	aqc111_set_phy_speed(dev, aqc111_data->autoneg,
-- 
2.20.1


From bc994cd915d3357e677a6a6d9f1aeef2bfe9f67b Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Wed, 8 May 2019 23:20:17 -0400
Subject: [PATCH 19/23] tuntap: fix dividing by zero in ebpf queue selection

[ Upstream commit a35d310f03a692bf4798eb309a1950a06a150620 ]

We need check if tun->numqueues is zero (e.g for the persist device)
before trying to use it for modular arithmetic.

Reported-by: Eric Dumazet <eric.dumazet@gmail.com>
Fixes: 96f84061620c6("tun: add eBPF based queue selection method")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 448d5439ff6a..58175dc8d1ff 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -596,13 +596,18 @@ static u16 tun_automq_select_queue(struct tun_struct *tun, struct sk_buff *skb)
 static u16 tun_ebpf_select_queue(struct tun_struct *tun, struct sk_buff *skb)
 {
 	struct tun_prog *prog;
+	u32 numqueues;
 	u16 ret = 0;
 
+	numqueues = READ_ONCE(tun->numqueues);
+	if (!numqueues)
+		return 0;
+
 	prog = rcu_dereference(tun->steering_prog);
 	if (prog)
 		ret = bpf_prog_run_clear_cb(prog->prog, skb);
 
-	return ret % tun->numqueues;
+	return ret % numqueues;
 }
 
 static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb,
-- 
2.20.1


From 345af61a36a6667a1af7d075938a9310e7d242e5 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Wed, 8 May 2019 23:20:18 -0400
Subject: [PATCH 20/23] tuntap: synchronize through tfiles array instead of
 tun->numqueues

[ Upstream commit 9871a9e47a2646fe30ae7fd2e67668a8d30912f6 ]

When a queue(tfile) is detached through __tun_detach(), we move the
last enabled tfile to the position where detached one sit but don't
NULL out last position. We expect to synchronize the datapath through
tun->numqueues. Unfortunately, this won't work since we're lacking
sufficient mechanism to order or synchronize the access to
tun->numqueues.

To fix this, NULL out the last position during detaching and check
RCU protected tfile against NULL instead of checking tun->numqueues in
datapath.

Cc: YueHaibing <yuehaibing@huawei.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: weiyongjun (A) <weiyongjun1@huawei.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Fixes: c8d68e6be1c3b ("tuntap: multiqueue support")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 58175dc8d1ff..8888c097375b 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -705,6 +705,8 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
 				   tun->tfiles[tun->numqueues - 1]);
 		ntfile = rtnl_dereference(tun->tfiles[index]);
 		ntfile->queue_index = index;
+		rcu_assign_pointer(tun->tfiles[tun->numqueues - 1],
+				   NULL);
 
 		--tun->numqueues;
 		if (clean) {
@@ -1087,7 +1089,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 	tfile = rcu_dereference(tun->tfiles[txq]);
 
 	/* Drop packet if interface is not attached */
-	if (txq >= tun->numqueues)
+	if (!tfile)
 		goto drop;
 
 	if (!rcu_dereference(tun->steering_prog))
@@ -1310,6 +1312,7 @@ static int tun_xdp_xmit(struct net_device *dev, int n,
 
 	rcu_read_lock();
 
+resample:
 	numqueues = READ_ONCE(tun->numqueues);
 	if (!numqueues) {
 		rcu_read_unlock();
@@ -1318,6 +1321,8 @@ static int tun_xdp_xmit(struct net_device *dev, int n,
 
 	tfile = rcu_dereference(tun->tfiles[smp_processor_id() %
 					    numqueues]);
+	if (unlikely(!tfile))
+		goto resample;
 
 	spin_lock(&tfile->tx_ring.producer_lock);
 	for (i = 0; i < n; i++) {
-- 
2.20.1


From e933ad4eaad2fdd22c72ed80e8853d30d52d8c58 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Wed, 1 May 2019 21:54:28 +0200
Subject: [PATCH 21/23] net: phy: fix phy_validate_pause

[ Upstream commit b4010af981ac8cdf1f7f58eb6b131c482e5dee02 ]

We have valid scenarios where ETHTOOL_LINK_MODE_Pause_BIT doesn't
need to be supported. Therefore extend the first check to check
for rx_pause being set.

See also phy_set_asym_pause:
rx=0 and tx=1: advertise asym pause only
rx=0 and tx=0: stop advertising both pause modes

The fixed commit isn't wrong, it's just the one that introduced the
linkmode bitmaps.

Fixes: 3c1bcc8614db ("net: ethernet: Convert phydev advertize and supported from u32 to link mode")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index adf79614c2db..ff2426e00682 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -2083,11 +2083,14 @@ bool phy_validate_pause(struct phy_device *phydev,
 			struct ethtool_pauseparam *pp)
 {
 	if (!linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT,
-			       phydev->supported) ||
-	    (!linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
-				phydev->supported) &&
-	     pp->rx_pause != pp->tx_pause))
+			       phydev->supported) && pp->rx_pause)
 		return false;
+
+	if (!linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
+			       phydev->supported) &&
+	    pp->rx_pause != pp->tx_pause)
+		return false;
+
 	return true;
 }
 EXPORT_SYMBOL(phy_validate_pause);
-- 
2.20.1


From f646055092a8c5ab1834c80b8d55b59bbf566b52 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 13 May 2019 09:38:55 -0700
Subject: [PATCH 22/23] flow_dissector: disable preemption around BPF calls

[ Upstream commit b1c17a9a353878602fd5bfe9103e4afe5e9a3f96 ]

Various things in eBPF really require us to disable preemption
before running an eBPF program.

syzbot reported :

BUG: assuming atomic context at net/core/flow_dissector.c:737
in_atomic(): 0, irqs_disabled(): 0, pid: 24710, name: syz-executor.3
2 locks held by syz-executor.3/24710:
 #0: 00000000e81a4bf1 (&tfile->napi_mutex){+.+.}, at: tun_get_user+0x168e/0x3ff0 drivers/net/tun.c:1850
 #1: 00000000254afebd (rcu_read_lock){....}, at: __skb_flow_dissect+0x1e1/0x4bb0 net/core/flow_dissector.c:822
CPU: 1 PID: 24710 Comm: syz-executor.3 Not tainted 5.1.0+ #6
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 __cant_sleep kernel/sched/core.c:6165 [inline]
 __cant_sleep.cold+0xa3/0xbb kernel/sched/core.c:6142
 bpf_flow_dissect+0xfe/0x390 net/core/flow_dissector.c:737
 __skb_flow_dissect+0x362/0x4bb0 net/core/flow_dissector.c:853
 skb_flow_dissect_flow_keys_basic include/linux/skbuff.h:1322 [inline]
 skb_probe_transport_header include/linux/skbuff.h:2500 [inline]
 skb_probe_transport_header include/linux/skbuff.h:2493 [inline]
 tun_get_user+0x2cfe/0x3ff0 drivers/net/tun.c:1940
 tun_chr_write_iter+0xbd/0x156 drivers/net/tun.c:2037
 call_write_iter include/linux/fs.h:1872 [inline]
 do_iter_readv_writev+0x5fd/0x900 fs/read_write.c:693
 do_iter_write fs/read_write.c:970 [inline]
 do_iter_write+0x184/0x610 fs/read_write.c:951
 vfs_writev+0x1b3/0x2f0 fs/read_write.c:1015
 do_writev+0x15b/0x330 fs/read_write.c:1058
 __do_sys_writev fs/read_write.c:1131 [inline]
 __se_sys_writev fs/read_write.c:1128 [inline]
 __x64_sys_writev+0x75/0xb0 fs/read_write.c:1128
 do_syscall_64+0x103/0x670 arch/x86/entry/common.c:298
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Fixes: d58e468b1112 ("flow_dissector: implements flow dissector BPF hook")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Petar Penkov <ppenkov@google.com>
Cc: Stanislav Fomichev <sdf@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/flow_dissector.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 9f2840510e63..afc6e025c85c 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -786,7 +786,10 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
 		flow_keys.thoff = nhoff;
 
 		bpf_compute_data_pointers((struct sk_buff *)skb);
+
+		preempt_disable();
 		result = BPF_PROG_RUN(attached, skb);
+		preempt_enable();
 
 		/* Restore state */
 		memcpy(cb, &cb_saved, sizeof(cb_saved));
-- 
2.20.1


From caf81fbf68de9b15c40e2d74f0d5a5fa0fd7a854 Mon Sep 17 00:00:00 2001
From: Paul Bolle <pebolle@tiscali.nl>
Date: Wed, 1 May 2019 23:19:03 +0200
Subject: [PATCH 23/23] isdn: bas_gigaset: use usb_fill_int_urb() properly

[ Upstream commit 4014dfae3ccaaf3ec19c9ae0691a3f14e7132eae ]

The switch to make bas_gigaset use usb_fill_int_urb() - instead of
filling that urb "by hand" - missed the subtle ordering of the previous
code.

See, before the switch urb->dev was set to a member somewhere deep in a
complicated structure and then supplied to usb_rcvisocpipe() and
usb_sndisocpipe(). After that switch urb->dev wasn't set to anything
specific before being supplied to those two macros. This triggers a
nasty oops:

    BUG: unable to handle kernel NULL pointer dereference at 00000000
    #PF error: [normal kernel read fault]
    *pde = 00000000
    Oops: 0000 [#1] SMP
    CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.1.0-0.rc4.1.local0.fc28.i686 #1
    Hardware name: IBM 2525FAG/2525FAG, BIOS 74ET64WW (2.09 ) 12/14/2006
    EIP: gigaset_init_bchannel+0x89/0x320 [bas_gigaset]
    Code: 75 07 83 8b 84 00 00 00 40 8d 47 74 c7 07 01 00 00 00 89 45 f0 8b 44 b7 68 85 c0 0f 84 6a 02 00 00 8b 48 28 8b 93 88 00 00 00 <8b> 09 8d 54 12 03 c1 e2 0f c1 e1 08 09 ca 8b 8b 8c 00 00 00 80 ca
    EAX: f05ec200 EBX: ed404200 ECX: 00000000 EDX: 00000000
    ESI: 00000000 EDI: f065a000 EBP: f30c9f40 ESP: f30c9f20
    DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 EFLAGS: 00010086
    CR0: 80050033 CR2: 00000000 CR3: 0ddc7000 CR4: 000006d0
    Call Trace:
     <SOFTIRQ>
     ? gigaset_isdn_connD+0xf6/0x140 [gigaset]
     gigaset_handle_event+0x173e/0x1b90 [gigaset]
     tasklet_action_common.isra.16+0x4e/0xf0
     tasklet_action+0x1e/0x20
     __do_softirq+0xb2/0x293
     ? __irqentry_text_end+0x3/0x3
     call_on_stack+0x45/0x50
     </SOFTIRQ>
     ? irq_exit+0xb5/0xc0
     ? do_IRQ+0x78/0xd0
     ? acpi_idle_enter_s2idle+0x50/0x50
     ? common_interrupt+0xd4/0xdc
     ? acpi_idle_enter_s2idle+0x50/0x50
     ? sched_cpu_activate+0x1b/0xf0
     ? acpi_fan_resume.cold.7+0x9/0x18
     ? cpuidle_enter_state+0x152/0x4c0
     ? cpuidle_enter+0x14/0x20
     ? call_cpuidle+0x21/0x40
     ? do_idle+0x1c8/0x200
     ? cpu_startup_entry+0x25/0x30
     ? rest_init+0x88/0x8a
     ? arch_call_rest_init+0xd/0x19
     ? start_kernel+0x42f/0x448
     ? i386_start_kernel+0xac/0xb0
     ? startup_32_smp+0x164/0x168
    Modules linked in: ppp_generic slhc capi bas_gigaset gigaset kernelcapi nf_conntrack_netbios_ns nf_conntrack_broadcast xt_CT ip6t_rpfilter ip6t_REJECT nf_reject_ipv6 xt_conntrack ip_set nfnetlink ebtable_nat ebtable_broute bridge stp llc ip6table_nat ip6table_mangle ip6table_raw ip6table_security iptable_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 libcrc32c iptable_mangle iptable_raw iptable_security ebtable_filter ebtables ip6table_filter ip6_tables sunrpc ipw2200 iTCO_wdt gpio_ich snd_intel8x0 libipw iTCO_vendor_support snd_ac97_codec lib80211 ppdev ac97_bus snd_seq cfg80211 snd_seq_device pcspkr thinkpad_acpi lpc_ich snd_pcm i2c_i801 snd_timer ledtrig_audio snd soundcore rfkill parport_pc parport pcc_cpufreq acpi_cpufreq i915 i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sdhci_pci sysimgblt cqhci fb_sys_fops drm sdhci mmc_core tg3 ata_generic serio_raw yenta_socket pata_acpi video
    CR2: 0000000000000000
    ---[ end trace 1fe07487b9200c73 ]---
    EIP: gigaset_init_bchannel+0x89/0x320 [bas_gigaset]
    Code: 75 07 83 8b 84 00 00 00 40 8d 47 74 c7 07 01 00 00 00 89 45 f0 8b 44 b7 68 85 c0 0f 84 6a 02 00 00 8b 48 28 8b 93 88 00 00 00 <8b> 09 8d 54 12 03 c1 e2 0f c1 e1 08 09 ca 8b 8b 8c 00 00 00 80 ca
    EAX: f05ec200 EBX: ed404200 ECX: 00000000 EDX: 00000000
    ESI: 00000000 EDI: f065a000 EBP: f30c9f40 ESP: cddcb3bc
    DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 EFLAGS: 00010086
    CR0: 80050033 CR2: 00000000 CR3: 0ddc7000 CR4: 000006d0
    Kernel panic - not syncing: Fatal exception in interrupt
    Kernel Offset: 0xcc00000 from 0xc0400000 (relocation range: 0xc0000000-0xf6ffdfff)
    ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]---

No-one noticed because this Oops is apparently only triggered by setting
up an ISDN data connection on a live ISDN line on a gigaset base (ie,
the PBX that the gigaset driver support). Very few people do that
running present day kernels.

Anyhow, a little code reorganization makes this problem go away, while
avoiding the subtle ordering that was used in the past. So let's do
that.

Fixes: 78c696c19578 ("isdn: gigaset: use usb_fill_int_urb()")
Signed-off-by: Paul Bolle <pebolle@tiscali.nl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/gigaset/bas-gigaset.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/isdn/gigaset/bas-gigaset.c b/drivers/isdn/gigaset/bas-gigaset.c
index ecdeb89645d0..149b1aca52a2 100644
--- a/drivers/isdn/gigaset/bas-gigaset.c
+++ b/drivers/isdn/gigaset/bas-gigaset.c
@@ -958,6 +958,7 @@ static void write_iso_callback(struct urb *urb)
  */
 static int starturbs(struct bc_state *bcs)
 {
+	struct usb_device *udev = bcs->cs->hw.bas->udev;
 	struct bas_bc_state *ubc = bcs->hw.bas;
 	struct urb *urb;
 	int j, k;
@@ -975,8 +976,8 @@ static int starturbs(struct bc_state *bcs)
 			rc = -EFAULT;
 			goto error;
 		}
-		usb_fill_int_urb(urb, bcs->cs->hw.bas->udev,
-				 usb_rcvisocpipe(urb->dev, 3 + 2 * bcs->channel),
+		usb_fill_int_urb(urb, udev,
+				 usb_rcvisocpipe(udev, 3 + 2 * bcs->channel),
 				 ubc->isoinbuf + k * BAS_INBUFSIZE,
 				 BAS_INBUFSIZE, read_iso_callback, bcs,
 				 BAS_FRAMETIME);
@@ -1006,8 +1007,8 @@ static int starturbs(struct bc_state *bcs)
 			rc = -EFAULT;
 			goto error;
 		}
-		usb_fill_int_urb(urb, bcs->cs->hw.bas->udev,
-				 usb_sndisocpipe(urb->dev, 4 + 2 * bcs->channel),
+		usb_fill_int_urb(urb, udev,
+				 usb_sndisocpipe(udev, 4 + 2 * bcs->channel),
 				 ubc->isooutbuf->data,
 				 sizeof(ubc->isooutbuf->data),
 				 write_iso_callback, &ubc->isoouturbs[k],
-- 
2.20.1


[-- Attachment #3: net_51.mbox --]
[-- Type: Application/Octet-Stream, Size: 52902 bytes --]

From 5cac873d73fdf6fc8926acbd603da368fef1b7e4 Mon Sep 17 00:00:00 2001
From: Jarod Wilson <jarod@redhat.com>
Date: Fri, 10 May 2019 17:57:09 -0400
Subject: [PATCH 01/23] bonding: fix arp_validate toggling in active-backup
 mode

[ Upstream commit a9b8a2b39ce65df45687cf9ef648885c2a99fe75 ]

There's currently a problem with toggling arp_validate on and off with an
active-backup bond. At the moment, you can start up a bond, like so:

modprobe bonding mode=1 arp_interval=100 arp_validate=0 arp_ip_targets=192.168.1.1
ip link set bond0 down
echo "ens4f0" > /sys/class/net/bond0/bonding/slaves
echo "ens4f1" > /sys/class/net/bond0/bonding/slaves
ip link set bond0 up
ip addr add 192.168.1.2/24 dev bond0

Pings to 192.168.1.1 work just fine. Now turn on arp_validate:

echo 1 > /sys/class/net/bond0/bonding/arp_validate

Pings to 192.168.1.1 continue to work just fine. Now when you go to turn
arp_validate off again, the link falls flat on it's face:

echo 0 > /sys/class/net/bond0/bonding/arp_validate
dmesg
...
[133191.911987] bond0: Setting arp_validate to none (0)
[133194.257793] bond0: bond_should_notify_peers: slave ens4f0
[133194.258031] bond0: link status definitely down for interface ens4f0, disabling it
[133194.259000] bond0: making interface ens4f1 the new active one
[133197.330130] bond0: link status definitely down for interface ens4f1, disabling it
[133197.331191] bond0: now running without any active interface!

The problem lies in bond_options.c, where passing in arp_validate=0
results in bond->recv_probe getting set to NULL. This flies directly in
the face of commit 3fe68df97c7f, which says we need to set recv_probe =
bond_arp_recv, even if we're not using arp_validate. Said commit fixed
this in bond_option_arp_interval_set, but missed that we can get to that
same state in bond_option_arp_validate_set as well.

One solution would be to universally set recv_probe = bond_arp_recv here
as well, but I don't think bond_option_arp_validate_set has any business
touching recv_probe at all, and that should be left to the arp_interval
code, so we can just make things much tidier here.

Fixes: 3fe68df97c7f ("bonding: always set recv_probe to bond_arp_rcv in arp monitor")
CC: Jay Vosburgh <j.vosburgh@gmail.com>
CC: Veaceslav Falico <vfalico@gmail.com>
CC: Andy Gospodarek <andy@greyhouse.net>
CC: "David S. Miller" <davem@davemloft.net>
CC: netdev@vger.kernel.org
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Signed-off-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_options.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index da1fc17295d9..b996967af8d9 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -1098,13 +1098,6 @@ static int bond_option_arp_validate_set(struct bonding *bond,
 {
 	netdev_dbg(bond->dev, "Setting arp_validate to %s (%llu)\n",
 		   newval->string, newval->value);
-
-	if (bond->dev->flags & IFF_UP) {
-		if (!newval->value)
-			bond->recv_probe = NULL;
-		else if (bond->params.arp_interval)
-			bond->recv_probe = bond_arp_rcv;
-	}
 	bond->params.arp_validate = newval->value;
 
 	return 0;
-- 
2.20.1


From c197751496d51b6cd2faaf22c1f10c4df70e5154 Mon Sep 17 00:00:00 2001
From: "Tobin C. Harding" <tobin@kernel.org>
Date: Fri, 10 May 2019 12:52:12 +1000
Subject: [PATCH 02/23] bridge: Fix error path for kobject_init_and_add()

[ Upstream commit bdfad5aec1392b93495b77b864d58d7f101dc1c1 ]

Currently error return from kobject_init_and_add() is not followed by a
call to kobject_put().  This means there is a memory leak.  We currently
set p to NULL so that kfree() may be called on it as a noop, the code is
arguably clearer if we move the kfree() up closer to where it is
called (instead of after goto jump).

Remove a goto label 'err1' and jump to call to kobject_put() in error
return from kobject_init_and_add() fixing the memory leak.  Re-name goto
label 'put_back' to 'err1' now that we don't use err1, following current
nomenclature (err1, err2 ...).  Move call to kfree out of the error
code at bottom of function up to closer to where memory was allocated.
Add comment to clarify call to kfree().

Signed-off-by: Tobin C. Harding <tobin@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_if.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 41f0a696a65f..0cb0aa0313a8 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -602,13 +602,15 @@ int br_add_if(struct net_bridge *br, struct net_device *dev,
 	call_netdevice_notifiers(NETDEV_JOIN, dev);
 
 	err = dev_set_allmulti(dev, 1);
-	if (err)
-		goto put_back;
+	if (err) {
+		kfree(p);	/* kobject not yet init'd, manually free */
+		goto err1;
+	}
 
 	err = kobject_init_and_add(&p->kobj, &brport_ktype, &(dev->dev.kobj),
 				   SYSFS_BRIDGE_PORT_ATTR);
 	if (err)
-		goto err1;
+		goto err2;
 
 	err = br_sysfs_addif(p);
 	if (err)
@@ -700,12 +702,9 @@ int br_add_if(struct net_bridge *br, struct net_device *dev,
 	sysfs_remove_link(br->ifobj, p->dev->name);
 err2:
 	kobject_put(&p->kobj);
-	p = NULL; /* kobject_put frees */
-err1:
 	dev_set_allmulti(dev, -1);
-put_back:
+err1:
 	dev_put(dev);
-	kfree(p);
 	return err;
 }
 
-- 
2.20.1


From e087537270d65f9dd99aaefc24b244ce5beb21ef Mon Sep 17 00:00:00 2001
From: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Date: Fri, 3 May 2019 16:03:11 +0300
Subject: [PATCH 03/23] dpaa_eth: fix SG frame cleanup

[ Upstream commit 17170e6570c082717c142733d9a638bcd20551f8 ]

Fix issue with the entry indexing in the sg frame cleanup code being
off-by-1. This problem showed up when doing some basic iperf tests and
manifested in traffic coming to a halt.

Signed-off-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Acked-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index dfebc30c4841..d3f2408dc9e8 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -1648,7 +1648,7 @@ static struct sk_buff *dpaa_cleanup_tx_fd(const struct dpaa_priv *priv,
 				 qm_sg_entry_get_len(&sgt[0]), dma_dir);
 
 		/* remaining pages were mapped with skb_frag_dma_map() */
-		for (i = 1; i < nr_frags; i++) {
+		for (i = 1; i <= nr_frags; i++) {
 			WARN_ON(qm_sg_entry_is_ext(&sgt[i]));
 
 			dma_unmap_page(dev, qm_sg_addr(&sgt[i]),
-- 
2.20.1


From be7a0f3cb385e5bc151867b337d207e9280904d5 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Tue, 7 May 2019 17:11:18 +0800
Subject: [PATCH 04/23] fib_rules: return 0 directly if an exactly same rule
 exists when NLM_F_EXCL not supplied

[ Upstream commit e9919a24d3022f72bcadc407e73a6ef17093a849 ]

With commit 153380ec4b9 ("fib_rules: Added NLM_F_EXCL support to
fib_nl_newrule") we now able to check if a rule already exists. But this
only works with iproute2. For other tools like libnl, NetworkManager,
it still could add duplicate rules with only NLM_F_CREATE flag, like

[localhost ~ ]# ip rule
0:      from all lookup local
32766:  from all lookup main
32767:  from all lookup default
100000: from 192.168.7.5 lookup 5
100000: from 192.168.7.5 lookup 5

As it doesn't make sense to create two duplicate rules, let's just return
0 if the rule exists.

Fixes: 153380ec4b9 ("fib_rules: Added NLM_F_EXCL support to fib_nl_newrule")
Reported-by: Thomas Haller <thaller@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/fib_rules.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index ffbb827723a2..c49b752ea7eb 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -756,9 +756,9 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (err)
 		goto errout;
 
-	if ((nlh->nlmsg_flags & NLM_F_EXCL) &&
-	    rule_exists(ops, frh, tb, rule)) {
-		err = -EEXIST;
+	if (rule_exists(ops, frh, tb, rule)) {
+		if (nlh->nlmsg_flags & NLM_F_EXCL)
+			err = -EEXIST;
 		goto errout_free;
 	}
 
-- 
2.20.1


From 0759eb33a5f3c3d6746b95a903906a2185a92f0c Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 7 May 2019 20:44:59 -0700
Subject: [PATCH 05/23] ipv4: Fix raw socket lookup for local traffic

[ Upstream commit 19e4e768064a87b073a4b4c138b55db70e0cfb9f ]

inet_iif should be used for the raw socket lookup. inet_iif considers
rt_iif which handles the case of local traffic.

As it stands, ping to a local address with the '-I <dev>' option fails
ever since ping was changed to use SO_BINDTODEVICE instead of
cmsg + IP_PKTINFO.

IPv6 works fine.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/raw.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index c55a5432cf37..dc91c27bb788 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -173,6 +173,7 @@ static int icmp_filter(const struct sock *sk, const struct sk_buff *skb)
 static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash)
 {
 	int sdif = inet_sdif(skb);
+	int dif = inet_iif(skb);
 	struct sock *sk;
 	struct hlist_head *head;
 	int delivered = 0;
@@ -185,8 +186,7 @@ static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash)
 
 	net = dev_net(skb->dev);
 	sk = __raw_v4_lookup(net, __sk_head(head), iph->protocol,
-			     iph->saddr, iph->daddr,
-			     skb->dev->ifindex, sdif);
+			     iph->saddr, iph->daddr, dif, sdif);
 
 	while (sk) {
 		delivered = 1;
-- 
2.20.1


From 2bb94098cbad149296f61f6d2a62642f93ba0735 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Mon, 6 May 2019 23:25:29 +0800
Subject: [PATCH 06/23] net: dsa: Fix error cleanup path in dsa_init_module

[ Upstream commit 68be930249d051fd54d3d99156b3dcadcb2a1f9b ]

BUG: unable to handle kernel paging request at ffffffffa01c5430
PGD 3270067 P4D 3270067 PUD 3271063 PMD 230bc5067 PTE 0
Oops: 0000 [#1
CPU: 0 PID: 6159 Comm: modprobe Not tainted 5.1.0+ #33
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.3-0-ge2fc41e-prebuilt.qemu-project.org 04/01/2014
RIP: 0010:raw_notifier_chain_register+0x16/0x40
Code: 63 f8 66 90 e9 5d ff ff ff 90 90 90 90 90 90 90 90 90 90 90 55 48 8b 07 48 89 e5 48 85 c0 74 1c 8b 56 10 3b 50 10 7e 07 eb 12 <39> 50 10 7c 0d 48 8d 78 08 48 8b 40 08 48 85 c0 75 ee 48 89 46 08
RSP: 0018:ffffc90001c33c08 EFLAGS: 00010282
RAX: ffffffffa01c5420 RBX: ffffffffa01db420 RCX: 4fcef45928070a8b
RDX: 0000000000000000 RSI: ffffffffa01db420 RDI: ffffffffa01b0068
RBP: ffffc90001c33c08 R08: 000000003e0a33d0 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000094443661 R12: ffff88822c320700
R13: ffff88823109be80 R14: 0000000000000000 R15: ffffc90001c33e78
FS:  00007fab8bd08540(0000) GS:ffff888237a00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffffffffa01c5430 CR3: 00000002297ea000 CR4: 00000000000006f0
Call Trace:
 register_netdevice_notifier+0x43/0x250
 ? 0xffffffffa01e0000
 dsa_slave_register_notifier+0x13/0x70 [dsa_core
 ? 0xffffffffa01e0000
 dsa_init_module+0x2e/0x1000 [dsa_core
 do_one_initcall+0x6c/0x3cc
 ? do_init_module+0x22/0x1f1
 ? rcu_read_lock_sched_held+0x97/0xb0
 ? kmem_cache_alloc_trace+0x325/0x3b0
 do_init_module+0x5b/0x1f1
 load_module+0x1db1/0x2690
 ? m_show+0x1d0/0x1d0
 __do_sys_finit_module+0xc5/0xd0
 __x64_sys_finit_module+0x15/0x20
 do_syscall_64+0x6b/0x1d0
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Cleanup allocated resourses if there are errors,
otherwise it will trgger memleak.

Fixes: c9eb3e0f8701 ("net: dsa: Add support for learning FDB through notification")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Reviewed-by: Vivien Didelot <vivien.didelot@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/dsa.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 36de4f2a3366..cb080efdc7b3 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -344,15 +344,22 @@ static int __init dsa_init_module(void)
 
 	rc = dsa_slave_register_notifier();
 	if (rc)
-		return rc;
+		goto register_notifier_fail;
 
 	rc = dsa_legacy_register();
 	if (rc)
-		return rc;
+		goto legacy_register_fail;
 
 	dev_add_pack(&dsa_pack_type);
 
 	return 0;
+
+legacy_register_fail:
+	dsa_slave_unregister_notifier();
+register_notifier_fail:
+	destroy_workqueue(dsa_owq);
+
+	return rc;
 }
 module_init(dsa_init_module);
 
-- 
2.20.1


From 628fa4a070ad0b0a045adbd4a3d69d812d200a55 Mon Sep 17 00:00:00 2001
From: Corentin Labbe <clabbe@baylibre.com>
Date: Mon, 13 May 2019 13:06:39 +0000
Subject: [PATCH 07/23] net: ethernet: stmmac: dwmac-sun8i: enable support of
 unicast filtering

[ Upstream commit d4c26eb6e721683a0f93e346ce55bc8dc3cbb175 ]

When adding more MAC addresses to a dwmac-sun8i interface, the device goes
directly in promiscuous mode.
This is due to IFF_UNICAST_FLT missing flag.

So since the hardware support unicast filtering, let's add IFF_UNICAST_FLT.

Fixes: 9f93ac8d4085 ("net-next: stmmac: Add dwmac-sun8i")
Signed-off-by: Corentin Labbe <clabbe@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index 195669f550f0..ba124a4da793 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -1015,6 +1015,8 @@ static struct mac_device_info *sun8i_dwmac_setup(void *ppriv)
 	mac->mac = &sun8i_dwmac_ops;
 	mac->dma = &sun8i_dwmac_dma_ops;
 
+	priv->dev->priv_flags |= IFF_UNICAST_FLT;
+
 	/* The loopback bit seems to be re-set when link change
 	 * Simply mask it each time
 	 * Speed 10/100/1000 are set in BIT(2)/BIT(3)
-- 
2.20.1


From 7f0c2d69813995cf1239ca11458abe6f4aaac807 Mon Sep 17 00:00:00 2001
From: Harini Katakam <harini.katakam@xilinx.com>
Date: Tue, 7 May 2019 19:59:10 +0530
Subject: [PATCH 08/23] net: macb: Change interrupt and napi enable order in
 open

[ Upstream commit 0504453139ef5a593c9587e1e851febee859c7d8 ]

Current order in open:
-> Enable interrupts (macb_init_hw)
-> Enable NAPI
-> Start PHY

Sequence of RX handling:
-> RX interrupt occurs
-> Interrupt is cleared and interrupt bits disabled in handler
-> NAPI is scheduled
-> In NAPI, RX budget is processed and RX interrupts are re-enabled

With the above, on QEMU or fixed link setups (where PHY state doesn't
matter), there's a chance macb RX interrupt occurs before NAPI is
enabled. This will result in NAPI being scheduled before it is enabled.
Fix this macb open by changing the order.

Fixes: ae1f2a56d273 ("net: macb: Added support for many RX queues")
Signed-off-by: Harini Katakam <harini.katakam@xilinx.com>
Acked-by: Nicolas Ferre <nicolas.ferre@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 3da2795e2486..a6535e226d84 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -2461,12 +2461,12 @@ static int macb_open(struct net_device *dev)
 		goto pm_exit;
 	}
 
-	bp->macbgem_ops.mog_init_rings(bp);
-	macb_init_hw(bp);
-
 	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
 		napi_enable(&queue->napi);
 
+	bp->macbgem_ops.mog_init_rings(bp);
+	macb_init_hw(bp);
+
 	/* schedule a link state check */
 	phy_start(dev->phydev);
 
-- 
2.20.1


From 37ebe67e46cb03f093f204fd46eee6e6bd68b624 Mon Sep 17 00:00:00 2001
From: Thomas Bogendoerfer <tbogendoerfer@suse.de>
Date: Mon, 13 May 2019 13:15:17 +0200
Subject: [PATCH 09/23] net: seeq: fix crash caused by not set dev.parent

[ Upstream commit 5afcd14cfc7fed1bcc8abcee2cef82732772bfc2 ]

The old MIPS implementation of dma_cache_sync() didn't use the dev argument,
but commit c9eb6172c328 ("dma-mapping: turn dma_cache_sync into a
dma_map_ops method") changed that, so we now need to set dev.parent.

Signed-off-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/seeq/sgiseeq.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/seeq/sgiseeq.c b/drivers/net/ethernet/seeq/sgiseeq.c
index 70cce63a6081..696037d5ac3d 100644
--- a/drivers/net/ethernet/seeq/sgiseeq.c
+++ b/drivers/net/ethernet/seeq/sgiseeq.c
@@ -735,6 +735,7 @@ static int sgiseeq_probe(struct platform_device *pdev)
 	}
 
 	platform_set_drvdata(pdev, dev);
+	SET_NETDEV_DEV(dev, &pdev->dev);
 	sp = netdev_priv(dev);
 
 	/* Make private data page aligned */
-- 
2.20.1


From e9d9923b54f4c52c82afbd62200b9b76211895ed Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@c-s.fr>
Date: Fri, 3 May 2019 13:33:23 +0000
Subject: [PATCH 10/23] net: ucc_geth - fix Oops when changing number of
 buffers in the ring

[ Upstream commit ee0df19305d9fabd9479b785918966f6e25b733b ]

When changing the number of buffers in the RX ring while the interface
is running, the following Oops is encountered due to the new number
of buffers being taken into account immediately while their allocation
is done when opening the device only.

[   69.882706] Unable to handle kernel paging request for data at address 0xf0000100
[   69.890172] Faulting instruction address: 0xc033e164
[   69.895122] Oops: Kernel access of bad area, sig: 11 [#1]
[   69.900494] BE PREEMPT CMPCPRO
[   69.907120] CPU: 0 PID: 0 Comm: swapper Not tainted 4.14.115-00006-g179ade8ce3-dirty #269
[   69.915956] task: c0684310 task.stack: c06da000
[   69.920470] NIP:  c033e164 LR: c02e44d0 CTR: c02e41fc
[   69.925504] REGS: dfff1e20 TRAP: 0300   Not tainted  (4.14.115-00006-g179ade8ce3-dirty)
[   69.934161] MSR:  00009032 <EE,ME,IR,DR,RI>  CR: 22004428  XER: 20000000
[   69.940869] DAR: f0000100 DSISR: 20000000
[   69.940869] GPR00: c0352d70 dfff1ed0 c0684310 f00000a4 00000040 dfff1f68 00000000 0000001f
[   69.940869] GPR08: df53f410 1cc00040 00000021 c0781640 42004424 100c82b6 f00000a4 df53f5b0
[   69.940869] GPR16: df53f6c0 c05daf84 00000040 00000000 00000040 c0782be4 00000000 00000001
[   69.940869] GPR24: 00000000 df53f400 000001b0 df53f410 df53f000 0000003f df708220 1cc00044
[   69.978348] NIP [c033e164] skb_put+0x0/0x5c
[   69.982528] LR [c02e44d0] ucc_geth_poll+0x2d4/0x3f8
[   69.987384] Call Trace:
[   69.989830] [dfff1ed0] [c02e4554] ucc_geth_poll+0x358/0x3f8 (unreliable)
[   69.996522] [dfff1f20] [c0352d70] net_rx_action+0x248/0x30c
[   70.002099] [dfff1f80] [c04e93e4] __do_softirq+0xfc/0x310
[   70.007492] [dfff1fe0] [c0021124] irq_exit+0xd0/0xd4
[   70.012458] [dfff1ff0] [c000e7e0] call_do_irq+0x24/0x3c
[   70.017683] [c06dbe80] [c0006bac] do_IRQ+0x64/0xc4
[   70.022474] [c06dbea0] [c001097c] ret_from_except+0x0/0x14
[   70.027964] --- interrupt: 501 at rcu_idle_exit+0x84/0x90
[   70.027964]     LR = rcu_idle_exit+0x74/0x90
[   70.037585] [c06dbf60] [20000000] 0x20000000 (unreliable)
[   70.042984] [c06dbf80] [c004bb0c] do_idle+0xb4/0x11c
[   70.047945] [c06dbfa0] [c004bd14] cpu_startup_entry+0x18/0x1c
[   70.053682] [c06dbfb0] [c05fb034] start_kernel+0x370/0x384
[   70.059153] [c06dbff0] [00003438] 0x3438
[   70.063062] Instruction dump:
[   70.066023] 38a00000 38800000 90010014 4bfff015 80010014 7c0803a6 3123ffff 7c691910
[   70.073767] 38210010 4e800020 38600000 4e800020 <80e3005c> 80c30098 3107ffff 7d083910
[   70.081690] ---[ end trace be7ccd9c1e1a9f12 ]---

This patch forbids the modification of the number of buffers in the
ring while the interface is running.

Fixes: ac421852b3a0 ("ucc_geth: add ethtool support")
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/ucc_geth_ethtool.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/freescale/ucc_geth_ethtool.c b/drivers/net/ethernet/freescale/ucc_geth_ethtool.c
index 0beee2cc2ddd..722b6de24816 100644
--- a/drivers/net/ethernet/freescale/ucc_geth_ethtool.c
+++ b/drivers/net/ethernet/freescale/ucc_geth_ethtool.c
@@ -252,14 +252,12 @@ uec_set_ringparam(struct net_device *netdev,
 		return -EINVAL;
 	}
 
+	if (netif_running(netdev))
+		return -EBUSY;
+
 	ug_info->bdRingLenRx[queue] = ring->rx_pending;
 	ug_info->bdRingLenTx[queue] = ring->tx_pending;
 
-	if (netif_running(netdev)) {
-		/* FIXME: restart automatically */
-		netdev_info(netdev, "Please re-open the interface\n");
-	}
-
 	return ret;
 }
 
-- 
2.20.1


From c2125ef8eeb47a703fa3d609e0e93cca5ab35a20 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Thu, 9 May 2019 22:52:20 +0800
Subject: [PATCH 11/23] packet: Fix error path in packet_init

[ Upstream commit 36096f2f4fa05f7678bc87397665491700bae757 ]

kernel BUG at lib/list_debug.c:47!
invalid opcode: 0000 [#1
CPU: 0 PID: 12914 Comm: rmmod Tainted: G        W         5.1.0+ #47
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.3-0-ge2fc41e-prebuilt.qemu-project.org 04/01/2014
RIP: 0010:__list_del_entry_valid+0x53/0x90
Code: 48 8b 32 48 39 fe 75 35 48 8b 50 08 48 39 f2 75 40 b8 01 00 00 00 5d c3 48
89 fe 48 89 c2 48 c7 c7 18 75 fe 82 e8 cb 34 78 ff <0f> 0b 48 89 fe 48 c7 c7 50 75 fe 82 e8 ba 34 78 ff 0f 0b 48 89 f2
RSP: 0018:ffffc90001c2fe40 EFLAGS: 00010286
RAX: 000000000000004e RBX: ffffffffa0184000 RCX: 0000000000000000
RDX: 0000000000000000 RSI: ffff888237a17788 RDI: 00000000ffffffff
RBP: ffffc90001c2fe40 R08: 0000000000000000 R09: 0000000000000000
R10: ffffc90001c2fe10 R11: 0000000000000000 R12: 0000000000000000
R13: ffffc90001c2fe50 R14: ffffffffa0184000 R15: 0000000000000000
FS:  00007f3d83634540(0000) GS:ffff888237a00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000555c350ea818 CR3: 0000000231677000 CR4: 00000000000006f0
Call Trace:
 unregister_pernet_operations+0x34/0x120
 unregister_pernet_subsys+0x1c/0x30
 packet_exit+0x1c/0x369 [af_packet
 __x64_sys_delete_module+0x156/0x260
 ? lockdep_hardirqs_on+0x133/0x1b0
 ? do_syscall_64+0x12/0x1f0
 do_syscall_64+0x6e/0x1f0
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

When modprobe af_packet, register_pernet_subsys
fails and does a cleanup, ops->list is set to LIST_POISON1,
but the module init is considered to success, then while rmmod it,
BUG() is triggered in __list_del_entry_valid which is called from
unregister_pernet_subsys. This patch fix error handing path in
packet_init to avoid possilbe issue if some error occur.

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 25 ++++++++++++++++++++-----
 1 file changed, 20 insertions(+), 5 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 9b81813dd16a..59da6f5b717d 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -4603,14 +4603,29 @@ static void __exit packet_exit(void)
 
 static int __init packet_init(void)
 {
-	int rc = proto_register(&packet_proto, 0);
+	int rc;
 
-	if (rc != 0)
+	rc = proto_register(&packet_proto, 0);
+	if (rc)
 		goto out;
+	rc = sock_register(&packet_family_ops);
+	if (rc)
+		goto out_proto;
+	rc = register_pernet_subsys(&packet_net_ops);
+	if (rc)
+		goto out_sock;
+	rc = register_netdevice_notifier(&packet_netdev_notifier);
+	if (rc)
+		goto out_pernet;
 
-	sock_register(&packet_family_ops);
-	register_pernet_subsys(&packet_net_ops);
-	register_netdevice_notifier(&packet_netdev_notifier);
+	return 0;
+
+out_pernet:
+	unregister_pernet_subsys(&packet_net_ops);
+out_sock:
+	sock_unregister(PF_PACKET);
+out_proto:
+	proto_unregister(&packet_proto);
 out:
 	return rc;
 }
-- 
2.20.1


From 148011f1a3ffa4edd35287d1097b851abfe93d80 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 8 May 2019 15:32:51 +0200
Subject: [PATCH 12/23] selinux: do not report error on connect(AF_UNSPEC)

[ Upstream commit c7e0d6cca86581092cbbf2cd868b3601495554cf ]

calling connect(AF_UNSPEC) on an already connected TCP socket is an
established way to disconnect() such socket. After commit 68741a8adab9
("selinux: Fix ltp test connect-syscall failure") it no longer works
and, in the above scenario connect() fails with EAFNOSUPPORT.

Fix the above falling back to the generic/old code when the address family
is not AF_INET{4,6}, but leave the SCTP code path untouched, as it has
specific constraints.

Fixes: 68741a8adab9 ("selinux: Fix ltp test connect-syscall failure")
Reported-by: Tom Deseyn <tdeseyn@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 security/selinux/hooks.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 1d0b37af2444..28bff30c2f15 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -4572,7 +4572,7 @@ static int selinux_socket_connect_helper(struct socket *sock,
 		struct lsm_network_audit net = {0,};
 		struct sockaddr_in *addr4 = NULL;
 		struct sockaddr_in6 *addr6 = NULL;
-		unsigned short snum;
+		unsigned short snum = 0;
 		u32 sid, perm;
 
 		/* sctp_connectx(3) calls via selinux_sctp_bind_connect()
@@ -4595,12 +4595,12 @@ static int selinux_socket_connect_helper(struct socket *sock,
 			break;
 		default:
 			/* Note that SCTP services expect -EINVAL, whereas
-			 * others expect -EAFNOSUPPORT.
+			 * others must handle this at the protocol level:
+			 * connect(AF_UNSPEC) on a connected socket is
+			 * a documented way disconnect the socket.
 			 */
 			if (sksec->sclass == SECCLASS_SCTP_SOCKET)
 				return -EINVAL;
-			else
-				return -EAFNOSUPPORT;
 		}
 
 		err = sel_netport_sid(sk->sk_protocol, snum, &sid);
-- 
2.20.1


From c5095b6293e0fa23856c131b7717107e2b382b6e Mon Sep 17 00:00:00 2001
From: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@gmail.com>
Date: Thu, 9 May 2019 07:13:42 +0200
Subject: [PATCH 13/23] tipc: fix hanging clients using poll with EPOLLOUT flag

[ Upstream commit ff946833b70e0c7f93de9a3f5b329b5ae2287b38 ]

commit 517d7c79bdb398 ("tipc: fix hanging poll() for stream sockets")
introduced a regression for clients using non-blocking sockets.
After the commit, we send EPOLLOUT event to the client even in
TIPC_CONNECTING state. This causes the subsequent send() to fail
with ENOTCONN, as the socket is still not in TIPC_ESTABLISHED state.

In this commit, we:
- improve the fix for hanging poll() by replacing sk_data_ready()
  with sk_state_change() to wake up all clients.
- revert the faulty updates introduced by commit 517d7c79bdb398
  ("tipc: fix hanging poll() for stream sockets").

Fixes: 517d7c79bdb398 ("tipc: fix hanging poll() for stream sockets")
Signed-off-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@gmail.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.se>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/socket.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index b542f14ed444..2851937f6e32 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -734,11 +734,11 @@ static __poll_t tipc_poll(struct file *file, struct socket *sock,
 
 	switch (sk->sk_state) {
 	case TIPC_ESTABLISHED:
-	case TIPC_CONNECTING:
 		if (!tsk->cong_link_cnt && !tsk_conn_cong(tsk))
 			revents |= EPOLLOUT;
 		/* fall through */
 	case TIPC_LISTEN:
+	case TIPC_CONNECTING:
 		if (!skb_queue_empty(&sk->sk_receive_queue))
 			revents |= EPOLLIN | EPOLLRDNORM;
 		break;
@@ -2041,7 +2041,7 @@ static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb)
 			if (msg_data_sz(hdr))
 				return true;
 			/* Empty ACK-, - wake up sleeping connect() and drop */
-			sk->sk_data_ready(sk);
+			sk->sk_state_change(sk);
 			msg_set_dest_droppable(hdr, 1);
 			return false;
 		}
-- 
2.20.1


From b3682d223f7beabd0a8f5cb1399ae9b42c99c764 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Thu, 9 May 2019 14:55:07 +0800
Subject: [PATCH 14/23] vlan: disable SIOCSHWTSTAMP in container

[ Upstream commit 873017af778439f2f8e3d87f28ddb1fcaf244a76 ]

With NET_ADMIN enabled in container, a normal user could be mapped to
root and is able to change the real device's rx filter via ioctl on
vlan, which would affect the other ptp process on host. Fix it by
disabling SIOCSHWTSTAMP in container.

Fixes: a6111d3c93d0 ("vlan: Pass SIOC[SG]HWTSTAMP ioctls to real device")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/8021q/vlan_dev.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 8d77b6ee4477..eb98be23423e 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -367,10 +367,12 @@ static int vlan_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	ifrr.ifr_ifru = ifr->ifr_ifru;
 
 	switch (cmd) {
+	case SIOCSHWTSTAMP:
+		if (!net_eq(dev_net(dev), &init_net))
+			break;
 	case SIOCGMIIPHY:
 	case SIOCGMIIREG:
 	case SIOCSMIIREG:
-	case SIOCSHWTSTAMP:
 	case SIOCGHWTSTAMP:
 		if (netif_device_present(real_dev) && ops->ndo_do_ioctl)
 			err = ops->ndo_do_ioctl(real_dev, &ifrr, cmd);
-- 
2.20.1


From 4d715afb2be51b955b21e8c063d630737339b0e4 Mon Sep 17 00:00:00 2001
From: Stephen Suryaputra <ssuryaextr@gmail.com>
Date: Mon, 6 May 2019 15:00:01 -0400
Subject: [PATCH 15/23] vrf: sit mtu should not be updated when vrf netdev is
 the link

[ Upstream commit ff6ab32bd4e073976e4d8797b4d514a172cfe6cb ]

VRF netdev mtu isn't typically set and have an mtu of 65536. When the
link of a tunnel is set, the tunnel mtu is changed from 1480 to the link
mtu minus tunnel header. In the case of VRF netdev is the link, then the
tunnel mtu becomes 65516. So, fix it by not setting the tunnel mtu in
this case.

Signed-off-by: Stephen Suryaputra <ssuryaextr@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index b2109b74857d..971d60bf9640 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1084,7 +1084,7 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev)
 	if (!tdev && tunnel->parms.link)
 		tdev = __dev_get_by_index(tunnel->net, tunnel->parms.link);
 
-	if (tdev) {
+	if (tdev && !netif_is_l3_master(tdev)) {
 		int t_hlen = tunnel->hlen + sizeof(struct iphdr);
 
 		dev->hard_header_len = tdev->hard_header_len + sizeof(struct iphdr);
-- 
2.20.1


From a3cc923fa2825af9ac91d232b14de323485dfb0f Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.com>
Date: Thu, 9 May 2019 11:08:16 +0200
Subject: [PATCH 16/23] aqc111: fix endianness issue in aqc111_change_mtu

[ Upstream commit b8b277525e9df2fd2dc3d1f4fe01c6796bb107fc ]

If the MTU is large enough, the first write to the device
is just repeated. On BE architectures, however, the first
word of the command will be swapped a second time and garbage
will be written. Avoid that.

Signed-off-by: Oliver Neukum <oneukum@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/aqc111.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index aff995be2a31..408df2d335e3 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -453,6 +453,8 @@ static int aqc111_change_mtu(struct net_device *net, int new_mtu)
 		reg16 = 0x1420;
 	else if (dev->net->mtu <= 16334)
 		reg16 = 0x1A20;
+	else
+		return 0;
 
 	aqc111_write16_cmd(dev, AQ_ACCESS_MAC, SFR_PAUSE_WATERLVL_LOW,
 			   2, &reg16);
-- 
2.20.1


From bd40f7a3dc63a54e26e994f38fa8d61521d03129 Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.com>
Date: Thu, 9 May 2019 11:08:17 +0200
Subject: [PATCH 17/23] aqc111: fix writing to the phy on BE

[ Upstream commit 369b46e9fbcfa5136f2cb5f486c90e5f7fa92630 ]

When writing to the phy on BE architectures an internal data structure
was directly given, leading to it being byte swapped in the wrong
way for the CPU in 50% of all cases. A temporary buffer must be used.

Signed-off-by: Oliver Neukum <oneukum@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/aqc111.c | 23 +++++++++++++++++------
 1 file changed, 17 insertions(+), 6 deletions(-)

diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index 408df2d335e3..599d560a8450 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -320,6 +320,7 @@ static int aqc111_get_link_ksettings(struct net_device *net,
 static void aqc111_set_phy_speed(struct usbnet *dev, u8 autoneg, u16 speed)
 {
 	struct aqc111_data *aqc111_data = dev->driver_priv;
+	u32 phy_on_the_wire;
 
 	aqc111_data->phy_cfg &= ~AQ_ADV_MASK;
 	aqc111_data->phy_cfg |= AQ_PAUSE;
@@ -361,7 +362,8 @@ static void aqc111_set_phy_speed(struct usbnet *dev, u8 autoneg, u16 speed)
 		}
 	}
 
-	aqc111_write32_cmd(dev, AQ_PHY_OPS, 0, 0, &aqc111_data->phy_cfg);
+	phy_on_the_wire = aqc111_data->phy_cfg;
+	aqc111_write32_cmd(dev, AQ_PHY_OPS, 0, 0, &phy_on_the_wire);
 }
 
 static int aqc111_set_link_ksettings(struct net_device *net,
@@ -755,6 +757,7 @@ static void aqc111_unbind(struct usbnet *dev, struct usb_interface *intf)
 {
 	struct aqc111_data *aqc111_data = dev->driver_priv;
 	u16 reg16;
+	u32 phy_on_the_wire;
 
 	/* Force bz */
 	reg16 = SFR_PHYPWR_RSTCTL_BZ;
@@ -768,8 +771,9 @@ static void aqc111_unbind(struct usbnet *dev, struct usb_interface *intf)
 	aqc111_data->phy_cfg &= ~AQ_ADV_MASK;
 	aqc111_data->phy_cfg |= AQ_LOW_POWER;
 	aqc111_data->phy_cfg &= ~AQ_PHY_POWER_EN;
+	phy_on_the_wire = aqc111_data->phy_cfg;
 	aqc111_write32_cmd_nopm(dev, AQ_PHY_OPS, 0, 0,
-				&aqc111_data->phy_cfg);
+				&phy_on_the_wire);
 
 	kfree(aqc111_data);
 }
@@ -992,6 +996,7 @@ static int aqc111_reset(struct usbnet *dev)
 {
 	struct aqc111_data *aqc111_data = dev->driver_priv;
 	u8 reg8 = 0;
+	u32 phy_on_the_wire;
 
 	dev->rx_urb_size = URB_SIZE;
 
@@ -1004,8 +1009,9 @@ static int aqc111_reset(struct usbnet *dev)
 
 	/* Power up ethernet PHY */
 	aqc111_data->phy_cfg = AQ_PHY_POWER_EN;
+	phy_on_the_wire = aqc111_data->phy_cfg;
 	aqc111_write32_cmd(dev, AQ_PHY_OPS, 0, 0,
-			   &aqc111_data->phy_cfg);
+			   &phy_on_the_wire);
 
 	/* Set the MAC address */
 	aqc111_write_cmd(dev, AQ_ACCESS_MAC, SFR_NODE_ID, ETH_ALEN,
@@ -1036,6 +1042,7 @@ static int aqc111_stop(struct usbnet *dev)
 {
 	struct aqc111_data *aqc111_data = dev->driver_priv;
 	u16 reg16 = 0;
+	u32 phy_on_the_wire;
 
 	aqc111_read16_cmd(dev, AQ_ACCESS_MAC, SFR_MEDIUM_STATUS_MODE,
 			  2, &reg16);
@@ -1047,8 +1054,9 @@ static int aqc111_stop(struct usbnet *dev)
 
 	/* Put PHY to low power*/
 	aqc111_data->phy_cfg |= AQ_LOW_POWER;
+	phy_on_the_wire = aqc111_data->phy_cfg;
 	aqc111_write32_cmd(dev, AQ_PHY_OPS, 0, 0,
-			   &aqc111_data->phy_cfg);
+			   &phy_on_the_wire);
 
 	netif_carrier_off(dev->net);
 
@@ -1324,6 +1332,7 @@ static int aqc111_suspend(struct usb_interface *intf, pm_message_t message)
 	u16 temp_rx_ctrl = 0x00;
 	u16 reg16;
 	u8 reg8;
+	u32 phy_on_the_wire;
 
 	usbnet_suspend(intf, message);
 
@@ -1395,12 +1404,14 @@ static int aqc111_suspend(struct usb_interface *intf, pm_message_t message)
 
 		aqc111_write_cmd(dev, AQ_WOL_CFG, 0, 0,
 				 WOL_CFG_SIZE, &wol_cfg);
+		phy_on_the_wire = aqc111_data->phy_cfg;
 		aqc111_write32_cmd(dev, AQ_PHY_OPS, 0, 0,
-				   &aqc111_data->phy_cfg);
+				   &phy_on_the_wire);
 	} else {
 		aqc111_data->phy_cfg |= AQ_LOW_POWER;
+		phy_on_the_wire = aqc111_data->phy_cfg;
 		aqc111_write32_cmd(dev, AQ_PHY_OPS, 0, 0,
-				   &aqc111_data->phy_cfg);
+				   &phy_on_the_wire);
 
 		/* Disable RX path */
 		aqc111_read16_cmd_nopm(dev, AQ_ACCESS_MAC,
-- 
2.20.1


From 8cb7f42e32cbfb80dacebf92a14824239c570f0a Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.com>
Date: Thu, 9 May 2019 11:08:18 +0200
Subject: [PATCH 18/23] aqc111: fix double endianness swap on BE

[ Upstream commit 2cf672709beb005f6e90cb4edbed6f2218ba953e ]

If you are using a function that does a swap in place,
you cannot just reuse the buffer on the assumption that it has
not been changed.

Signed-off-by: Oliver Neukum <oneukum@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/aqc111.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index 599d560a8450..b86c5ce9a92a 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -1428,7 +1428,7 @@ static int aqc111_resume(struct usb_interface *intf)
 {
 	struct usbnet *dev = usb_get_intfdata(intf);
 	struct aqc111_data *aqc111_data = dev->driver_priv;
-	u16 reg16;
+	u16 reg16, oldreg16;
 	u8 reg8;
 
 	netif_carrier_off(dev->net);
@@ -1444,9 +1444,11 @@ static int aqc111_resume(struct usb_interface *intf)
 	/* Configure RX control register => start operation */
 	reg16 = aqc111_data->rxctl;
 	reg16 &= ~SFR_RX_CTL_START;
+	/* needs to be saved in case endianness is swapped */
+	oldreg16 = reg16;
 	aqc111_write16_cmd_nopm(dev, AQ_ACCESS_MAC, SFR_RX_CTL, 2, &reg16);
 
-	reg16 |= SFR_RX_CTL_START;
+	reg16 = oldreg16 | SFR_RX_CTL_START;
 	aqc111_write16_cmd_nopm(dev, AQ_ACCESS_MAC, SFR_RX_CTL, 2, &reg16);
 
 	aqc111_set_phy_speed(dev, aqc111_data->autoneg,
-- 
2.20.1


From b5d9be5d403bf8a103d213739b1f847d5b45a67d Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Wed, 8 May 2019 23:20:17 -0400
Subject: [PATCH 19/23] tuntap: fix dividing by zero in ebpf queue selection

[ Upstream commit a35d310f03a692bf4798eb309a1950a06a150620 ]

We need check if tun->numqueues is zero (e.g for the persist device)
before trying to use it for modular arithmetic.

Reported-by: Eric Dumazet <eric.dumazet@gmail.com>
Fixes: 96f84061620c6("tun: add eBPF based queue selection method")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index e9ca1c088d0b..dc62fc3c5a95 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -596,13 +596,18 @@ static u16 tun_automq_select_queue(struct tun_struct *tun, struct sk_buff *skb)
 static u16 tun_ebpf_select_queue(struct tun_struct *tun, struct sk_buff *skb)
 {
 	struct tun_prog *prog;
+	u32 numqueues;
 	u16 ret = 0;
 
+	numqueues = READ_ONCE(tun->numqueues);
+	if (!numqueues)
+		return 0;
+
 	prog = rcu_dereference(tun->steering_prog);
 	if (prog)
 		ret = bpf_prog_run_clear_cb(prog->prog, skb);
 
-	return ret % tun->numqueues;
+	return ret % numqueues;
 }
 
 static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb,
-- 
2.20.1


From 7de7407472144aa0270b488054afdd410b10ece7 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Wed, 8 May 2019 23:20:18 -0400
Subject: [PATCH 20/23] tuntap: synchronize through tfiles array instead of
 tun->numqueues

[ Upstream commit 9871a9e47a2646fe30ae7fd2e67668a8d30912f6 ]

When a queue(tfile) is detached through __tun_detach(), we move the
last enabled tfile to the position where detached one sit but don't
NULL out last position. We expect to synchronize the datapath through
tun->numqueues. Unfortunately, this won't work since we're lacking
sufficient mechanism to order or synchronize the access to
tun->numqueues.

To fix this, NULL out the last position during detaching and check
RCU protected tfile against NULL instead of checking tun->numqueues in
datapath.

Cc: YueHaibing <yuehaibing@huawei.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: weiyongjun (A) <weiyongjun1@huawei.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Fixes: c8d68e6be1c3b ("tuntap: multiqueue support")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index dc62fc3c5a95..f4c933ac6edf 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -705,6 +705,8 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
 				   tun->tfiles[tun->numqueues - 1]);
 		ntfile = rtnl_dereference(tun->tfiles[index]);
 		ntfile->queue_index = index;
+		rcu_assign_pointer(tun->tfiles[tun->numqueues - 1],
+				   NULL);
 
 		--tun->numqueues;
 		if (clean) {
@@ -1087,7 +1089,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 	tfile = rcu_dereference(tun->tfiles[txq]);
 
 	/* Drop packet if interface is not attached */
-	if (txq >= tun->numqueues)
+	if (!tfile)
 		goto drop;
 
 	if (!rcu_dereference(tun->steering_prog))
@@ -1310,6 +1312,7 @@ static int tun_xdp_xmit(struct net_device *dev, int n,
 
 	rcu_read_lock();
 
+resample:
 	numqueues = READ_ONCE(tun->numqueues);
 	if (!numqueues) {
 		rcu_read_unlock();
@@ -1318,6 +1321,8 @@ static int tun_xdp_xmit(struct net_device *dev, int n,
 
 	tfile = rcu_dereference(tun->tfiles[smp_processor_id() %
 					    numqueues]);
+	if (unlikely(!tfile))
+		goto resample;
 
 	spin_lock(&tfile->tx_ring.producer_lock);
 	for (i = 0; i < n; i++) {
-- 
2.20.1


From 5a03ffed5998db443e2364b88a01f6efb3ac6ba7 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Wed, 1 May 2019 21:54:28 +0200
Subject: [PATCH 21/23] net: phy: fix phy_validate_pause

[ Upstream commit b4010af981ac8cdf1f7f58eb6b131c482e5dee02 ]

We have valid scenarios where ETHTOOL_LINK_MODE_Pause_BIT doesn't
need to be supported. Therefore extend the first check to check
for rx_pause being set.

See also phy_set_asym_pause:
rx=0 and tx=1: advertise asym pause only
rx=0 and tx=0: stop advertising both pause modes

The fixed commit isn't wrong, it's just the one that introduced the
linkmode bitmaps.

Fixes: 3c1bcc8614db ("net: ethernet: Convert phydev advertize and supported from u32 to link mode")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 77068c545de0..cd5966b0db57 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -2044,11 +2044,14 @@ bool phy_validate_pause(struct phy_device *phydev,
 			struct ethtool_pauseparam *pp)
 {
 	if (!linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT,
-			       phydev->supported) ||
-	    (!linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
-				phydev->supported) &&
-	     pp->rx_pause != pp->tx_pause))
+			       phydev->supported) && pp->rx_pause)
 		return false;
+
+	if (!linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
+			       phydev->supported) &&
+	    pp->rx_pause != pp->tx_pause)
+		return false;
+
 	return true;
 }
 EXPORT_SYMBOL(phy_validate_pause);
-- 
2.20.1


From eed4820d41e67250cff095be726161d8764121cb Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 13 May 2019 09:38:55 -0700
Subject: [PATCH 22/23] flow_dissector: disable preemption around BPF calls

[ Upstream commit b1c17a9a353878602fd5bfe9103e4afe5e9a3f96 ]

Various things in eBPF really require us to disable preemption
before running an eBPF program.

syzbot reported :

BUG: assuming atomic context at net/core/flow_dissector.c:737
in_atomic(): 0, irqs_disabled(): 0, pid: 24710, name: syz-executor.3
2 locks held by syz-executor.3/24710:
 #0: 00000000e81a4bf1 (&tfile->napi_mutex){+.+.}, at: tun_get_user+0x168e/0x3ff0 drivers/net/tun.c:1850
 #1: 00000000254afebd (rcu_read_lock){....}, at: __skb_flow_dissect+0x1e1/0x4bb0 net/core/flow_dissector.c:822
CPU: 1 PID: 24710 Comm: syz-executor.3 Not tainted 5.1.0+ #6
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 __cant_sleep kernel/sched/core.c:6165 [inline]
 __cant_sleep.cold+0xa3/0xbb kernel/sched/core.c:6142
 bpf_flow_dissect+0xfe/0x390 net/core/flow_dissector.c:737
 __skb_flow_dissect+0x362/0x4bb0 net/core/flow_dissector.c:853
 skb_flow_dissect_flow_keys_basic include/linux/skbuff.h:1322 [inline]
 skb_probe_transport_header include/linux/skbuff.h:2500 [inline]
 skb_probe_transport_header include/linux/skbuff.h:2493 [inline]
 tun_get_user+0x2cfe/0x3ff0 drivers/net/tun.c:1940
 tun_chr_write_iter+0xbd/0x156 drivers/net/tun.c:2037
 call_write_iter include/linux/fs.h:1872 [inline]
 do_iter_readv_writev+0x5fd/0x900 fs/read_write.c:693
 do_iter_write fs/read_write.c:970 [inline]
 do_iter_write+0x184/0x610 fs/read_write.c:951
 vfs_writev+0x1b3/0x2f0 fs/read_write.c:1015
 do_writev+0x15b/0x330 fs/read_write.c:1058
 __do_sys_writev fs/read_write.c:1131 [inline]
 __se_sys_writev fs/read_write.c:1128 [inline]
 __x64_sys_writev+0x75/0xb0 fs/read_write.c:1128
 do_syscall_64+0x103/0x670 arch/x86/entry/common.c:298
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Fixes: d58e468b1112 ("flow_dissector: implements flow dissector BPF hook")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Petar Penkov <ppenkov@google.com>
Cc: Stanislav Fomichev <sdf@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/flow_dissector.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 94a450b2191a..139470d8d3c0 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -712,7 +712,10 @@ bool __skb_flow_bpf_dissect(struct bpf_prog *prog,
 	flow_keys->thoff = flow_keys->nhoff;
 
 	bpf_compute_data_pointers((struct sk_buff *)skb);
+
+	preempt_disable();
 	result = BPF_PROG_RUN(prog, skb);
+	preempt_enable();
 
 	/* Restore state */
 	memcpy(cb, &cb_saved, sizeof(cb_saved));
-- 
2.20.1


From a91c7715a6c8ac07f4a84bbc43b658606b9eb6f3 Mon Sep 17 00:00:00 2001
From: Paul Bolle <pebolle@tiscali.nl>
Date: Wed, 1 May 2019 23:19:03 +0200
Subject: [PATCH 23/23] isdn: bas_gigaset: use usb_fill_int_urb() properly

[ Upstream commit 4014dfae3ccaaf3ec19c9ae0691a3f14e7132eae ]

The switch to make bas_gigaset use usb_fill_int_urb() - instead of
filling that urb "by hand" - missed the subtle ordering of the previous
code.

See, before the switch urb->dev was set to a member somewhere deep in a
complicated structure and then supplied to usb_rcvisocpipe() and
usb_sndisocpipe(). After that switch urb->dev wasn't set to anything
specific before being supplied to those two macros. This triggers a
nasty oops:

    BUG: unable to handle kernel NULL pointer dereference at 00000000
    #PF error: [normal kernel read fault]
    *pde = 00000000
    Oops: 0000 [#1] SMP
    CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.1.0-0.rc4.1.local0.fc28.i686 #1
    Hardware name: IBM 2525FAG/2525FAG, BIOS 74ET64WW (2.09 ) 12/14/2006
    EIP: gigaset_init_bchannel+0x89/0x320 [bas_gigaset]
    Code: 75 07 83 8b 84 00 00 00 40 8d 47 74 c7 07 01 00 00 00 89 45 f0 8b 44 b7 68 85 c0 0f 84 6a 02 00 00 8b 48 28 8b 93 88 00 00 00 <8b> 09 8d 54 12 03 c1 e2 0f c1 e1 08 09 ca 8b 8b 8c 00 00 00 80 ca
    EAX: f05ec200 EBX: ed404200 ECX: 00000000 EDX: 00000000
    ESI: 00000000 EDI: f065a000 EBP: f30c9f40 ESP: f30c9f20
    DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 EFLAGS: 00010086
    CR0: 80050033 CR2: 00000000 CR3: 0ddc7000 CR4: 000006d0
    Call Trace:
     <SOFTIRQ>
     ? gigaset_isdn_connD+0xf6/0x140 [gigaset]
     gigaset_handle_event+0x173e/0x1b90 [gigaset]
     tasklet_action_common.isra.16+0x4e/0xf0
     tasklet_action+0x1e/0x20
     __do_softirq+0xb2/0x293
     ? __irqentry_text_end+0x3/0x3
     call_on_stack+0x45/0x50
     </SOFTIRQ>
     ? irq_exit+0xb5/0xc0
     ? do_IRQ+0x78/0xd0
     ? acpi_idle_enter_s2idle+0x50/0x50
     ? common_interrupt+0xd4/0xdc
     ? acpi_idle_enter_s2idle+0x50/0x50
     ? sched_cpu_activate+0x1b/0xf0
     ? acpi_fan_resume.cold.7+0x9/0x18
     ? cpuidle_enter_state+0x152/0x4c0
     ? cpuidle_enter+0x14/0x20
     ? call_cpuidle+0x21/0x40
     ? do_idle+0x1c8/0x200
     ? cpu_startup_entry+0x25/0x30
     ? rest_init+0x88/0x8a
     ? arch_call_rest_init+0xd/0x19
     ? start_kernel+0x42f/0x448
     ? i386_start_kernel+0xac/0xb0
     ? startup_32_smp+0x164/0x168
    Modules linked in: ppp_generic slhc capi bas_gigaset gigaset kernelcapi nf_conntrack_netbios_ns nf_conntrack_broadcast xt_CT ip6t_rpfilter ip6t_REJECT nf_reject_ipv6 xt_conntrack ip_set nfnetlink ebtable_nat ebtable_broute bridge stp llc ip6table_nat ip6table_mangle ip6table_raw ip6table_security iptable_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 libcrc32c iptable_mangle iptable_raw iptable_security ebtable_filter ebtables ip6table_filter ip6_tables sunrpc ipw2200 iTCO_wdt gpio_ich snd_intel8x0 libipw iTCO_vendor_support snd_ac97_codec lib80211 ppdev ac97_bus snd_seq cfg80211 snd_seq_device pcspkr thinkpad_acpi lpc_ich snd_pcm i2c_i801 snd_timer ledtrig_audio snd soundcore rfkill parport_pc parport pcc_cpufreq acpi_cpufreq i915 i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sdhci_pci sysimgblt cqhci fb_sys_fops drm sdhci mmc_core tg3 ata_generic serio_raw yenta_socket pata_acpi video
    CR2: 0000000000000000
    ---[ end trace 1fe07487b9200c73 ]---
    EIP: gigaset_init_bchannel+0x89/0x320 [bas_gigaset]
    Code: 75 07 83 8b 84 00 00 00 40 8d 47 74 c7 07 01 00 00 00 89 45 f0 8b 44 b7 68 85 c0 0f 84 6a 02 00 00 8b 48 28 8b 93 88 00 00 00 <8b> 09 8d 54 12 03 c1 e2 0f c1 e1 08 09 ca 8b 8b 8c 00 00 00 80 ca
    EAX: f05ec200 EBX: ed404200 ECX: 00000000 EDX: 00000000
    ESI: 00000000 EDI: f065a000 EBP: f30c9f40 ESP: cddcb3bc
    DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 EFLAGS: 00010086
    CR0: 80050033 CR2: 00000000 CR3: 0ddc7000 CR4: 000006d0
    Kernel panic - not syncing: Fatal exception in interrupt
    Kernel Offset: 0xcc00000 from 0xc0400000 (relocation range: 0xc0000000-0xf6ffdfff)
    ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]---

No-one noticed because this Oops is apparently only triggered by setting
up an ISDN data connection on a live ISDN line on a gigaset base (ie,
the PBX that the gigaset driver support). Very few people do that
running present day kernels.

Anyhow, a little code reorganization makes this problem go away, while
avoiding the subtle ordering that was used in the past. So let's do
that.

Fixes: 78c696c19578 ("isdn: gigaset: use usb_fill_int_urb()")
Signed-off-by: Paul Bolle <pebolle@tiscali.nl>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/gigaset/bas-gigaset.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/isdn/gigaset/bas-gigaset.c b/drivers/isdn/gigaset/bas-gigaset.c
index ecdeb89645d0..149b1aca52a2 100644
--- a/drivers/isdn/gigaset/bas-gigaset.c
+++ b/drivers/isdn/gigaset/bas-gigaset.c
@@ -958,6 +958,7 @@ static void write_iso_callback(struct urb *urb)
  */
 static int starturbs(struct bc_state *bcs)
 {
+	struct usb_device *udev = bcs->cs->hw.bas->udev;
 	struct bas_bc_state *ubc = bcs->hw.bas;
 	struct urb *urb;
 	int j, k;
@@ -975,8 +976,8 @@ static int starturbs(struct bc_state *bcs)
 			rc = -EFAULT;
 			goto error;
 		}
-		usb_fill_int_urb(urb, bcs->cs->hw.bas->udev,
-				 usb_rcvisocpipe(urb->dev, 3 + 2 * bcs->channel),
+		usb_fill_int_urb(urb, udev,
+				 usb_rcvisocpipe(udev, 3 + 2 * bcs->channel),
 				 ubc->isoinbuf + k * BAS_INBUFSIZE,
 				 BAS_INBUFSIZE, read_iso_callback, bcs,
 				 BAS_FRAMETIME);
@@ -1006,8 +1007,8 @@ static int starturbs(struct bc_state *bcs)
 			rc = -EFAULT;
 			goto error;
 		}
-		usb_fill_int_urb(urb, bcs->cs->hw.bas->udev,
-				 usb_sndisocpipe(urb->dev, 4 + 2 * bcs->channel),
+		usb_fill_int_urb(urb, udev,
+				 usb_sndisocpipe(udev, 4 + 2 * bcs->channel),
 				 ubc->isooutbuf->data,
 				 sizeof(ubc->isooutbuf->data),
 				 write_iso_callback, &ubc->isoouturbs[k],
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Tue, May 14, 2019 at 12:58:49PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v5.0 and v5.1
> -stable, respectively.
> 
> Thank you.


All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 105 bytes --]


Please queue up the following networking bug fixes for v5.0 and v5.1
-stable, respectively.

Thank you!

[-- Attachment #2: net_50.mbox --]
[-- Type: Application/Octet-Stream, Size: 45296 bytes --]

From 21da880d301d2892afd7787f5fb0c50965b7b3d1 Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Thu, 16 May 2019 13:30:54 -0700
Subject: [PATCH 01/18] ipv6: fix src addr routing with the exception table

[ Upstream commit 510e2ceda031eed97a7a0f9aad65d271a58b460d ]

When inserting route cache into the exception table, the key is
generated with both src_addr and dest_addr with src addr routing.
However, current logic always assumes the src_addr used to generate the
key is a /128 host address. This is not true in the following scenarios:
1. When the route is a gateway route or does not have next hop.
   (rt6_is_gw_or_nonexthop() == false)
2. When calling ip6_rt_cache_alloc(), saddr is passed in as NULL.
This means, when looking for a route cache in the exception table, we
have to do the lookup twice: first time with the passed in /128 host
address, second time with the src_addr stored in fib6_info.

This solves the pmtu discovery issue reported by Mikael Magnusson where
a route cache with a lower mtu info is created for a gateway route with
src addr. However, the lookup code is not able to find this route cache.

Fixes: 2b760fcf5cfb ("ipv6: hook up exception table to store dst cache")
Reported-by: Mikael Magnusson <mikael.kernel@lists.m7n.se>
Bisected-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Wei Wang <weiwan@google.com>
Cc: Martin Lau <kafai@fb.com>
Cc: Eric Dumazet <edumazet@google.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 51 +++++++++++++++++++++++++-----------------------
 1 file changed, 27 insertions(+), 24 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 59c90bba048c..7ab9889fced3 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -110,8 +110,8 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 			 int iif, int type, u32 portid, u32 seq,
 			 unsigned int flags);
 static struct rt6_info *rt6_find_cached_rt(struct fib6_info *rt,
-					   struct in6_addr *daddr,
-					   struct in6_addr *saddr);
+					   const struct in6_addr *daddr,
+					   const struct in6_addr *saddr);
 
 #ifdef CONFIG_IPV6_ROUTE_INFO
 static struct fib6_info *rt6_add_route_info(struct net *net,
@@ -1529,31 +1529,44 @@ void rt6_flush_exceptions(struct fib6_info *rt)
  * Caller has to hold rcu_read_lock()
  */
 static struct rt6_info *rt6_find_cached_rt(struct fib6_info *rt,
-					   struct in6_addr *daddr,
-					   struct in6_addr *saddr)
+					   const struct in6_addr *daddr,
+					   const struct in6_addr *saddr)
 {
+	const struct in6_addr *src_key = NULL;
 	struct rt6_exception_bucket *bucket;
-	struct in6_addr *src_key = NULL;
 	struct rt6_exception *rt6_ex;
 	struct rt6_info *res = NULL;
 
-	bucket = rcu_dereference(rt->rt6i_exception_bucket);
-
 #ifdef CONFIG_IPV6_SUBTREES
 	/* rt6i_src.plen != 0 indicates rt is in subtree
 	 * and exception table is indexed by a hash of
 	 * both rt6i_dst and rt6i_src.
-	 * Otherwise, the exception table is indexed by
-	 * a hash of only rt6i_dst.
+	 * However, the src addr used to create the hash
+	 * might not be exactly the passed in saddr which
+	 * is a /128 addr from the flow.
+	 * So we need to use f6i->fib6_src to redo lookup
+	 * if the passed in saddr does not find anything.
+	 * (See the logic in ip6_rt_cache_alloc() on how
+	 * rt->rt6i_src is updated.)
 	 */
 	if (rt->fib6_src.plen)
 		src_key = saddr;
+find_ex:
 #endif
+	bucket = rcu_dereference(rt->rt6i_exception_bucket);
 	rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key);
 
 	if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i))
 		res = rt6_ex->rt6i;
 
+#ifdef CONFIG_IPV6_SUBTREES
+	/* Use fib6_src as src_key and redo lookup */
+	if (!res && src_key && src_key != &rt->fib6_src.addr) {
+		src_key = &rt->fib6_src.addr;
+		goto find_ex;
+	}
+#endif
+
 	return res;
 }
 
@@ -2614,10 +2627,8 @@ static unsigned int ip6_mtu(const struct dst_entry *dst)
 u32 ip6_mtu_from_fib6(struct fib6_info *f6i, struct in6_addr *daddr,
 		      struct in6_addr *saddr)
 {
-	struct rt6_exception_bucket *bucket;
-	struct rt6_exception *rt6_ex;
-	struct in6_addr *src_key;
 	struct inet6_dev *idev;
+	struct rt6_info *rt;
 	u32 mtu = 0;
 
 	if (unlikely(fib6_metric_locked(f6i, RTAX_MTU))) {
@@ -2626,18 +2637,10 @@ u32 ip6_mtu_from_fib6(struct fib6_info *f6i, struct in6_addr *daddr,
 			goto out;
 	}
 
-	src_key = NULL;
-#ifdef CONFIG_IPV6_SUBTREES
-	if (f6i->fib6_src.plen)
-		src_key = saddr;
-#endif
-
-	bucket = rcu_dereference(f6i->rt6i_exception_bucket);
-	rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key);
-	if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i))
-		mtu = dst_metric_raw(&rt6_ex->rt6i->dst, RTAX_MTU);
-
-	if (likely(!mtu)) {
+	rt = rt6_find_cached_rt(f6i, daddr, saddr);
+	if (unlikely(rt)) {
+		mtu = dst_metric_raw(&rt->dst, RTAX_MTU);
+	} else {
 		struct net_device *dev = fib6_info_nh_dev(f6i);
 
 		mtu = IPV6_MIN_MTU;
-- 
2.20.1


From 7157fa2f347abcdbed019788a9245453239714ca Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 15 May 2019 19:39:52 -0700
Subject: [PATCH 02/18] ipv6: prevent possible fib6 leaks

[ Upstream commit 61fb0d01680771f72cc9d39783fb2c122aaad51e ]

At ipv6 route dismantle, fib6_drop_pcpu_from() is responsible
for finding all percpu routes and set their ->from pointer
to NULL, so that fib6_ref can reach its expected value (1).

The problem right now is that other cpus can still catch the
route being deleted, since there is no rcu grace period
between the route deletion and call to fib6_drop_pcpu_from()

This can leak the fib6 and associated resources, since no
notifier will take care of removing the last reference(s).

I decided to add another boolean (fib6_destroying) instead
of reusing/renaming exception_bucket_flushed to ease stable backports,
and properly document the memory barriers used to implement this fix.

This patch has been co-developped with Wei Wang.

Fixes: 93531c674315 ("net/ipv6: separate handling of FIB entries from dst based routes")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Wei Wang <weiwan@google.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Martin Lau <kafai@fb.com>
Acked-by: Wei Wang <weiwan@google.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h |  3 ++-
 net/ipv6/ip6_fib.c    | 12 +++++++++---
 net/ipv6/route.c      |  7 +++++++
 3 files changed, 18 insertions(+), 4 deletions(-)

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 84097010237c..b5e3add90e99 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -171,7 +171,8 @@ struct fib6_info {
 					dst_nocount:1,
 					dst_nopolicy:1,
 					dst_host:1,
-					unused:3;
+					fib6_destroying:1,
+					unused:2;
 
 	struct fib6_nh			fib6_nh;
 	struct rcu_head			rcu;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 91247a6fc67f..9915f64b38a0 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -909,6 +909,12 @@ static void fib6_drop_pcpu_from(struct fib6_info *f6i,
 {
 	int cpu;
 
+	/* Make sure rt6_make_pcpu_route() wont add other percpu routes
+	 * while we are cleaning them here.
+	 */
+	f6i->fib6_destroying = 1;
+	mb(); /* paired with the cmpxchg() in rt6_make_pcpu_route() */
+
 	/* release the reference to this fib entry from
 	 * all of its cached pcpu routes
 	 */
@@ -932,6 +938,9 @@ static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn,
 {
 	struct fib6_table *table = rt->fib6_table;
 
+	if (rt->rt6i_pcpu)
+		fib6_drop_pcpu_from(rt, table);
+
 	if (atomic_read(&rt->fib6_ref) != 1) {
 		/* This route is used as dummy address holder in some split
 		 * nodes. It is not leaked, but it still holds other resources,
@@ -953,9 +962,6 @@ static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn,
 			fn = rcu_dereference_protected(fn->parent,
 				    lockdep_is_held(&table->tb6_lock));
 		}
-
-		if (rt->rt6i_pcpu)
-			fib6_drop_pcpu_from(rt, table);
 	}
 }
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 7ab9889fced3..b471afce1330 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1260,6 +1260,13 @@ static struct rt6_info *rt6_make_pcpu_route(struct net *net,
 	prev = cmpxchg(p, NULL, pcpu_rt);
 	BUG_ON(prev);
 
+	if (rt->fib6_destroying) {
+		struct fib6_info *from;
+
+		from = xchg((__force struct fib6_info **)&pcpu_rt->from, NULL);
+		fib6_info_release(from);
+	}
+
 	return pcpu_rt;
 }
 
-- 
2.20.1


From 2d86a650bc713e93f2e1d729b8d7d31f405de9a5 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Mon, 13 May 2019 14:06:24 -0700
Subject: [PATCH 03/18] net: Always descend into dsa/

[ Upstream commit 0fe9f173d6cda95874edeb413b1fa9907b5ae830 ]

Jiri reported that with a kernel built with CONFIG_FIXED_PHY=y,
CONFIG_NET_DSA=m and CONFIG_NET_DSA_LOOP=m, we would not get to a
functional state where the mock-up driver is registered. Turns out that
we are not descending into drivers/net/dsa/ unconditionally, and we
won't be able to link-in dsa_loop_bdinfo.o which does the actual mock-up
mdio device registration.

Reported-by: Jiri Pirko <jiri@resnulli.us>
Fixes: 40013ff20b1b ("net: dsa: Fix functional dsa-loop dependency on FIXED_PHY")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Vivien Didelot <vivien.didelot@gmail.com>
Tested-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index 21cde7e78621..0d3ba056cda3 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -40,7 +40,7 @@ obj-$(CONFIG_ARCNET) += arcnet/
 obj-$(CONFIG_DEV_APPLETALK) += appletalk/
 obj-$(CONFIG_CAIF) += caif/
 obj-$(CONFIG_CAN) += can/
-obj-$(CONFIG_NET_DSA) += dsa/
+obj-y += dsa/
 obj-$(CONFIG_ETHERNET) += ethernet/
 obj-$(CONFIG_FDDI) += fddi/
 obj-$(CONFIG_HIPPI) += hippi/
-- 
2.20.1


From 67429c929649c0f8ca0cc39c1c8a6d24dbfab98e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 16 May 2019 08:09:57 -0700
Subject: [PATCH 04/18] net: avoid weird emergency message

[ Upstream commit d7c04b05c9ca14c55309eb139430283a45c4c25f ]

When host is under high stress, it is very possible thread
running netdev_wait_allrefs() returns from msleep(250)
10 seconds late.

This leads to these messages in the syslog :

[...] unregister_netdevice: waiting for syz_tun to become free. Usage count = 0

If the device refcount is zero, the wait is over.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 7277dd393c00..c8e672ac32cb 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8829,7 +8829,7 @@ static void netdev_wait_allrefs(struct net_device *dev)
 
 		refcnt = netdev_refcnt_read(dev);
 
-		if (time_after(jiffies, warning_time + 10 * HZ)) {
+		if (refcnt && time_after(jiffies, warning_time + 10 * HZ)) {
 			pr_emerg("unregister_netdevice: waiting for %s to become free. Usage count = %d\n",
 				 dev->name, refcnt);
 			warning_time = jiffies;
-- 
2.20.1


From 462c680da92655247b00b1faf0a871b2bf08d6f1 Mon Sep 17 00:00:00 2001
From: Yunjian Wang <wangyunjian@huawei.com>
Date: Tue, 14 May 2019 19:03:19 +0800
Subject: [PATCH 05/18] net/mlx4_core: Change the error print to info print

[ Upstream commit 00f9fec48157f3734e52130a119846e67a12314b ]

The error print within mlx4_flow_steer_promisc_add() should
be a info print.

Fixes: 592e49dda812 ('net/mlx4: Implement promiscuous mode with device managed flow-steering')
Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/mcg.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c
index ffed2d4c9403..9c481823b3e8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mcg.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c
@@ -1492,7 +1492,7 @@ int mlx4_flow_steer_promisc_add(struct mlx4_dev *dev, u8 port,
 	rule.port = port;
 	rule.qpn = qpn;
 	INIT_LIST_HEAD(&rule.list);
-	mlx4_err(dev, "going promisc on %x\n", port);
+	mlx4_info(dev, "going promisc on %x\n", port);
 
 	return  mlx4_flow_attach(dev, &rule, regid_p);
 }
-- 
2.20.1


From f13fdf05ecb8b01f255936149b070840c497afa0 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 15 May 2019 13:29:16 -0400
Subject: [PATCH 06/18] net: test nouarg before dereferencing zerocopy pointers

[ Upstream commit 185ce5c38ea76f29b6bd9c7c8c7a5e5408834920 ]

Zerocopy skbs without completion notification were added for packet
sockets with PACKET_TX_RING user buffers. Those signal completion
through the TP_STATUS_USER bit in the ring. Zerocopy annotation was
added only to avoid premature notification after clone or orphan, by
triggering a copy on these paths for these packets.

The mechanism had to define a special "no-uarg" mode because packet
sockets already use skb_uarg(skb) == skb_shinfo(skb)->destructor_arg
for a different pointer.

Before deferencing skb_uarg(skb), verify that it is a real pointer.

Fixes: 5cd8d46ea1562 ("packet: copy user buffers before orphan or clone")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index b8679dcba96f..3b1a8f38a1ef 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1366,10 +1366,12 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy)
 	struct ubuf_info *uarg = skb_zcopy(skb);
 
 	if (uarg) {
-		if (uarg->callback == sock_zerocopy_callback) {
+		if (skb_zcopy_is_nouarg(skb)) {
+			/* no notification callback */
+		} else if (uarg->callback == sock_zerocopy_callback) {
 			uarg->zerocopy = uarg->zerocopy && zerocopy;
 			sock_zerocopy_put(uarg);
-		} else if (!skb_zcopy_is_nouarg(skb)) {
+		} else {
 			uarg->callback(uarg, zerocopy);
 		}
 
@@ -2627,7 +2629,8 @@ static inline int skb_orphan_frags(struct sk_buff *skb, gfp_t gfp_mask)
 {
 	if (likely(!skb_zcopy(skb)))
 		return 0;
-	if (skb_uarg(skb)->callback == sock_zerocopy_callback)
+	if (!skb_zcopy_is_nouarg(skb) &&
+	    skb_uarg(skb)->callback == sock_zerocopy_callback)
 		return 0;
 	return skb_copy_ubufs(skb, gfp_mask);
 }
-- 
2.20.1


From fa84aeaf92833408c17dbd123a80b2b00c624351 Mon Sep 17 00:00:00 2001
From: Daniele Palmas <dnlplm@gmail.com>
Date: Wed, 15 May 2019 17:29:43 +0200
Subject: [PATCH 07/18] net: usb: qmi_wwan: add Telit 0x1260 and 0x1261
 compositions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit b4e467c82f8c12af78b6f6fa5730cb7dea7af1b4 ]

Added support for Telit LE910Cx 0x1260 and 0x1261 compositions.

Signed-off-by: Daniele Palmas <dnlplm@gmail.com>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 9195f3476b1d..94389c84ede6 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1240,6 +1240,8 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1bc7, 0x1101, 3)},	/* Telit ME910 dual modem */
 	{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)},	/* Telit LE920 */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1201, 2)},	/* Telit LE920, LE920A4 */
+	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1260, 2)},	/* Telit LE910Cx */
+	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1261, 2)},	/* Telit LE910Cx */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1900, 1)},	/* Telit LN940 series */
 	{QMI_FIXED_INTF(0x1c9e, 0x9801, 3)},	/* Telewell TW-3G HSPA+ */
 	{QMI_FIXED_INTF(0x1c9e, 0x9803, 4)},	/* Telewell TW-3G HSPA+ */
-- 
2.20.1


From 29c7555deb5ec54d34d084ca577f1a48b3f468bd Mon Sep 17 00:00:00 2001
From: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Date: Tue, 14 May 2019 14:28:19 -0700
Subject: [PATCH 08/18] nfp: flower: add rcu locks when accessing netdev for
 tunnels

[ Upstream commit cb07d915bf278a7a3938b983bbcb4921366b5eff ]

Add rcu locks when accessing netdev when processing route request
and tunnel keep alive messages received from hardware.

Fixes: 8e6a9046b66a ("nfp: flower vxlan neighbour offload")
Fixes: 856f5b135758 ("nfp: flower vxlan neighbour keep-alive")
Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/netronome/nfp/flower/tunnel_conf.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
index 2d9f26a725c2..37bd2dbcd206 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
@@ -164,6 +164,7 @@ void nfp_tunnel_keep_alive(struct nfp_app *app, struct sk_buff *skb)
 		return;
 	}
 
+	rcu_read_lock();
 	for (i = 0; i < count; i++) {
 		ipv4_addr = payload->tun_info[i].ipv4;
 		port = be32_to_cpu(payload->tun_info[i].egress_port);
@@ -179,6 +180,7 @@ void nfp_tunnel_keep_alive(struct nfp_app *app, struct sk_buff *skb)
 		neigh_event_send(n, NULL);
 		neigh_release(n);
 	}
+	rcu_read_unlock();
 }
 
 static int
@@ -362,9 +364,10 @@ void nfp_tunnel_request_route(struct nfp_app *app, struct sk_buff *skb)
 
 	payload = nfp_flower_cmsg_get_data(skb);
 
+	rcu_read_lock();
 	netdev = nfp_app_repr_get(app, be32_to_cpu(payload->ingress_port));
 	if (!netdev)
-		goto route_fail_warning;
+		goto fail_rcu_unlock;
 
 	flow.daddr = payload->ipv4_addr;
 	flow.flowi4_proto = IPPROTO_UDP;
@@ -374,21 +377,23 @@ void nfp_tunnel_request_route(struct nfp_app *app, struct sk_buff *skb)
 	rt = ip_route_output_key(dev_net(netdev), &flow);
 	err = PTR_ERR_OR_ZERO(rt);
 	if (err)
-		goto route_fail_warning;
+		goto fail_rcu_unlock;
 #else
-	goto route_fail_warning;
+	goto fail_rcu_unlock;
 #endif
 
 	/* Get the neighbour entry for the lookup */
 	n = dst_neigh_lookup(&rt->dst, &flow.daddr);
 	ip_rt_put(rt);
 	if (!n)
-		goto route_fail_warning;
-	nfp_tun_write_neigh(n->dev, app, &flow, n, GFP_KERNEL);
+		goto fail_rcu_unlock;
+	nfp_tun_write_neigh(n->dev, app, &flow, n, GFP_ATOMIC);
 	neigh_release(n);
+	rcu_read_unlock();
 	return;
 
-route_fail_warning:
+fail_rcu_unlock:
+	rcu_read_unlock();
 	nfp_flower_cmsg_warn(app, "Requested route not found.\n");
 }
 
-- 
2.20.1


From d63ad63bf15fe13af17735b4a31e48cc427e94ab Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Tue, 14 May 2019 22:55:32 +0800
Subject: [PATCH 09/18] ppp: deflate: Fix possible crash in deflate_init

[ Upstream commit 3ebe1bca58c85325c97a22d4fc3f5b5420752e6f ]

BUG: unable to handle kernel paging request at ffffffffa018f000
PGD 3270067 P4D 3270067 PUD 3271063 PMD 2307eb067 PTE 0
Oops: 0000 [#1] PREEMPT SMP
CPU: 0 PID: 4138 Comm: modprobe Not tainted 5.1.0-rc7+ #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS
rel-1.9.3-0-ge2fc41e-prebuilt.qemu-project.org 04/01/2014
RIP: 0010:ppp_register_compressor+0x3e/0xd0 [ppp_generic]
Code: 98 4a 3f e2 48 8b 15 c1 67 00 00 41 8b 0c 24 48 81 fa 40 f0 19 a0
75 0e eb 35 48 8b 12 48 81 fa 40 f0 19 a0 74
RSP: 0018:ffffc90000d93c68 EFLAGS: 00010287
RAX: ffffffffa018f000 RBX: ffffffffa01a3000 RCX: 000000000000001a
RDX: ffff888230c750a0 RSI: 0000000000000000 RDI: ffffffffa019f000
RBP: ffffc90000d93c80 R08: 0000000000000001 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: ffffffffa0194080
R13: ffff88822ee1a700 R14: 0000000000000000 R15: ffffc90000d93e78
FS:  00007f2339557540(0000) GS:ffff888237a00000(0000)
knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffffffffa018f000 CR3: 000000022bde4000 CR4: 00000000000006f0
Call Trace:
 ? 0xffffffffa01a3000
 deflate_init+0x11/0x1000 [ppp_deflate]
 ? 0xffffffffa01a3000
 do_one_initcall+0x6c/0x3cc
 ? kmem_cache_alloc_trace+0x248/0x3b0
 do_init_module+0x5b/0x1f1
 load_module+0x1db1/0x2690
 ? m_show+0x1d0/0x1d0
 __do_sys_finit_module+0xc5/0xd0
 __x64_sys_finit_module+0x15/0x20
 do_syscall_64+0x6b/0x1d0
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

If ppp_deflate fails to register in deflate_init,
module initialization failed out, however
ppp_deflate_draft may has been regiestred and not
unregistered before return.
Then the seconed modprobe will trigger crash like this.

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/ppp_deflate.c | 20 ++++++++++++++------
 1 file changed, 14 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ppp/ppp_deflate.c b/drivers/net/ppp/ppp_deflate.c
index b5edc7f96a39..685e875f5164 100644
--- a/drivers/net/ppp/ppp_deflate.c
+++ b/drivers/net/ppp/ppp_deflate.c
@@ -610,12 +610,20 @@ static struct compressor ppp_deflate_draft = {
 
 static int __init deflate_init(void)
 {
-        int answer = ppp_register_compressor(&ppp_deflate);
-        if (answer == 0)
-                printk(KERN_INFO
-		       "PPP Deflate Compression module registered\n");
-	ppp_register_compressor(&ppp_deflate_draft);
-        return answer;
+	int rc;
+
+	rc = ppp_register_compressor(&ppp_deflate);
+	if (rc)
+		return rc;
+
+	rc = ppp_register_compressor(&ppp_deflate_draft);
+	if (rc) {
+		ppp_unregister_compressor(&ppp_deflate);
+		return rc;
+	}
+
+	pr_info("PPP Deflate Compression module registered\n");
+	return 0;
 }
 
 static void __exit deflate_cleanup(void)
-- 
2.20.1


From 9d7110d643b5716bca5d277cb570e6df02c0ead4 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 14 May 2019 15:12:19 +0200
Subject: [PATCH 10/18] rtnetlink: always put IFLA_LINK for links with a
 link-netnsid

[ Upstream commit feadc4b6cf42a53a8a93c918a569a0b7e62bd350 ]

Currently, nla_put_iflink() doesn't put the IFLA_LINK attribute when
iflink == ifindex.

In some cases, a device can be created in a different netns with the
same ifindex as its parent. That device will not dump its IFLA_LINK
attribute, which can confuse some userspace software that expects it.
For example, if the last ifindex created in init_net and foo are both
8, these commands will trigger the issue:

    ip link add parent type dummy                   # ifindex 9
    ip link add link parent netns foo type macvlan  # ifindex 9 in ns foo

So, in case a device puts the IFLA_LINK_NETNSID attribute in a dump,
always put the IFLA_LINK attribute as well.

Thanks to Dan Winship for analyzing the original OpenShift bug down to
the missing netlink attribute.

v2: change Fixes tag, it's been here forever, as Nicolas Dichtel said
    add Nicolas' ack
v3: change Fixes tag
    fix subject typo, spotted by Edward Cree

Analyzed-by: Dan Winship <danw@redhat.com>
Fixes: d8a5ec672768 ("[NET]: netlink support for moving devices between network namespaces.")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 5ea1bed08ede..fd449017c55e 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1502,14 +1502,15 @@ static int put_master_ifindex(struct sk_buff *skb, struct net_device *dev)
 	return ret;
 }
 
-static int nla_put_iflink(struct sk_buff *skb, const struct net_device *dev)
+static int nla_put_iflink(struct sk_buff *skb, const struct net_device *dev,
+			  bool force)
 {
 	int ifindex = dev_get_iflink(dev);
 
-	if (dev->ifindex == ifindex)
-		return 0;
+	if (force || dev->ifindex != ifindex)
+		return nla_put_u32(skb, IFLA_LINK, ifindex);
 
-	return nla_put_u32(skb, IFLA_LINK, ifindex);
+	return 0;
 }
 
 static noinline_for_stack int nla_put_ifalias(struct sk_buff *skb,
@@ -1526,6 +1527,8 @@ static int rtnl_fill_link_netnsid(struct sk_buff *skb,
 				  const struct net_device *dev,
 				  struct net *src_net)
 {
+	bool put_iflink = false;
+
 	if (dev->rtnl_link_ops && dev->rtnl_link_ops->get_link_net) {
 		struct net *link_net = dev->rtnl_link_ops->get_link_net(dev);
 
@@ -1534,10 +1537,12 @@ static int rtnl_fill_link_netnsid(struct sk_buff *skb,
 
 			if (nla_put_s32(skb, IFLA_LINK_NETNSID, id))
 				return -EMSGSIZE;
+
+			put_iflink = true;
 		}
 	}
 
-	return 0;
+	return nla_put_iflink(skb, dev, put_iflink);
 }
 
 static int rtnl_fill_link_af(struct sk_buff *skb,
@@ -1623,7 +1628,6 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
 #ifdef CONFIG_RPS
 	    nla_put_u32(skb, IFLA_NUM_RX_QUEUES, dev->num_rx_queues) ||
 #endif
-	    nla_put_iflink(skb, dev) ||
 	    put_master_ifindex(skb, dev) ||
 	    nla_put_u8(skb, IFLA_CARRIER, netif_carrier_ok(dev)) ||
 	    (dev->qdisc &&
-- 
2.20.1


From 36241aaee8dbc401c6096f04f41eeb69969b8a90 Mon Sep 17 00:00:00 2001
From: Junwei Hu <hujunwei4@huawei.com>
Date: Thu, 16 May 2019 10:51:15 +0800
Subject: [PATCH 11/18] tipc: switch order of device registration to fix a
 crash

[ Upstream commit 7e27e8d6130c5e88fac9ddec4249f7f2337fe7f8 ]

When tipc is loaded while many processes try to create a TIPC socket,
a crash occurs:
 PANIC: Unable to handle kernel paging request at virtual
 address "dfff20000000021d"
 pc : tipc_sk_create+0x374/0x1180 [tipc]
 lr : tipc_sk_create+0x374/0x1180 [tipc]
   Exception class = DABT (current EL), IL = 32 bits
 Call trace:
  tipc_sk_create+0x374/0x1180 [tipc]
  __sock_create+0x1cc/0x408
  __sys_socket+0xec/0x1f0
  __arm64_sys_socket+0x74/0xa8
 ...

This is due to race between sock_create and unfinished
register_pernet_device. tipc_sk_insert tries to do
"net_generic(net, tipc_net_id)".
but tipc_net_id is not initialized yet.

So switch the order of the two to close the race.

This can be reproduced with multiple processes doing socket(AF_TIPC, ...)
and one process doing module removal.

Fixes: a62fbccecd62 ("tipc: make subscriber server support net namespace")
Signed-off-by: Junwei Hu <hujunwei4@huawei.com>
Reported-by: Wang Wang <wangwang2@huawei.com>
Reviewed-by: Xiaogang Wang <wangxiaogang3@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/core.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/net/tipc/core.c b/net/tipc/core.c
index 5b38f5164281..dbfc1e8b2866 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -129,10 +129,6 @@ static int __init tipc_init(void)
 	if (err)
 		goto out_netlink_compat;
 
-	err = tipc_socket_init();
-	if (err)
-		goto out_socket;
-
 	err = tipc_register_sysctl();
 	if (err)
 		goto out_sysctl;
@@ -141,6 +137,10 @@ static int __init tipc_init(void)
 	if (err)
 		goto out_pernet;
 
+	err = tipc_socket_init();
+	if (err)
+		goto out_socket;
+
 	err = tipc_bearer_setup();
 	if (err)
 		goto out_bearer;
@@ -148,12 +148,12 @@ static int __init tipc_init(void)
 	pr_info("Started in single node mode\n");
 	return 0;
 out_bearer:
+	tipc_socket_stop();
+out_socket:
 	unregister_pernet_subsys(&tipc_net_ops);
 out_pernet:
 	tipc_unregister_sysctl();
 out_sysctl:
-	tipc_socket_stop();
-out_socket:
 	tipc_netlink_compat_stop();
 out_netlink_compat:
 	tipc_netlink_stop();
@@ -165,10 +165,10 @@ static int __init tipc_init(void)
 static void __exit tipc_exit(void)
 {
 	tipc_bearer_cleanup();
+	tipc_socket_stop();
 	unregister_pernet_subsys(&tipc_net_ops);
 	tipc_netlink_stop();
 	tipc_netlink_compat_stop();
-	tipc_socket_stop();
 	tipc_unregister_sysctl();
 
 	pr_info("Deactivated\n");
-- 
2.20.1


From 4f1fc66d32491849b88f5ea2b79b2c118b8a47f5 Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Fri, 17 May 2019 16:45:43 +0200
Subject: [PATCH 12/18] vsock/virtio: free packets during the socket release

[ Upstream commit ac03046ece2b158ebd204dfc4896fd9f39f0e6c8 ]

When the socket is released, we should free all packets
queued in the per-socket list in order to avoid a memory
leak.

Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/vmw_vsock/virtio_transport_common.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 602715fc9a75..f3f3d06cb6d8 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -786,12 +786,19 @@ static bool virtio_transport_close(struct vsock_sock *vsk)
 
 void virtio_transport_release(struct vsock_sock *vsk)
 {
+	struct virtio_vsock_sock *vvs = vsk->trans;
+	struct virtio_vsock_pkt *pkt, *tmp;
 	struct sock *sk = &vsk->sk;
 	bool remove_sock = true;
 
 	lock_sock(sk);
 	if (sk->sk_type == SOCK_STREAM)
 		remove_sock = virtio_transport_close(vsk);
+
+	list_for_each_entry_safe(pkt, tmp, &vvs->rx_queue, list) {
+		list_del(&pkt->list);
+		virtio_transport_free_pkt(pkt);
+	}
 	release_sock(sk);
 
 	if (remove_sock)
-- 
2.20.1


From 77c56b89f07a2727f683c0087dccfac87124bbf2 Mon Sep 17 00:00:00 2001
From: Junwei Hu <hujunwei4@huawei.com>
Date: Fri, 17 May 2019 19:27:34 +0800
Subject: [PATCH 13/18] tipc: fix modprobe tipc failed after switch order of
 device registration

[ Upstream commit 532b0f7ece4cb2ffd24dc723ddf55242d1188e5e ]

Error message printed:
modprobe: ERROR: could not insert 'tipc': Address family not
supported by protocol.
when modprobe tipc after the following patch: switch order of
device registration, commit 7e27e8d6130c
("tipc: switch order of device registration to fix a crash")

Because sock_create_kern(net, AF_TIPC, ...) is called by
tipc_topsrv_create_listener() in the initialization process
of tipc_net_ops, tipc_socket_init() must be execute before that.

I move tipc_socket_init() into function tipc_init_net().

Fixes: 7e27e8d6130c
("tipc: switch order of device registration to fix a crash")
Signed-off-by: Junwei Hu <hujunwei4@huawei.com>
Reported-by: Wang Wang <wangwang2@huawei.com>
Reviewed-by: Kang Zhou <zhoukang7@huawei.com>
Reviewed-by: Suanming Mou <mousuanming@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/core.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/net/tipc/core.c b/net/tipc/core.c
index dbfc1e8b2866..d7b0688c98dd 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -66,6 +66,10 @@ static int __net_init tipc_init_net(struct net *net)
 	INIT_LIST_HEAD(&tn->node_list);
 	spin_lock_init(&tn->node_list_lock);
 
+	err = tipc_socket_init();
+	if (err)
+		goto out_socket;
+
 	err = tipc_sk_rht_init(net);
 	if (err)
 		goto out_sk_rht;
@@ -92,6 +96,8 @@ static int __net_init tipc_init_net(struct net *net)
 out_nametbl:
 	tipc_sk_rht_destroy(net);
 out_sk_rht:
+	tipc_socket_stop();
+out_socket:
 	return err;
 }
 
@@ -102,6 +108,7 @@ static void __net_exit tipc_exit_net(struct net *net)
 	tipc_bcast_stop(net);
 	tipc_nametbl_stop(net);
 	tipc_sk_rht_destroy(net);
+	tipc_socket_stop();
 }
 
 static struct pernet_operations tipc_net_ops = {
@@ -137,10 +144,6 @@ static int __init tipc_init(void)
 	if (err)
 		goto out_pernet;
 
-	err = tipc_socket_init();
-	if (err)
-		goto out_socket;
-
 	err = tipc_bearer_setup();
 	if (err)
 		goto out_bearer;
@@ -148,8 +151,6 @@ static int __init tipc_init(void)
 	pr_info("Started in single node mode\n");
 	return 0;
 out_bearer:
-	tipc_socket_stop();
-out_socket:
 	unregister_pernet_subsys(&tipc_net_ops);
 out_pernet:
 	tipc_unregister_sysctl();
@@ -165,7 +166,6 @@ static int __init tipc_init(void)
 static void __exit tipc_exit(void)
 {
 	tipc_bearer_cleanup();
-	tipc_socket_stop();
 	unregister_pernet_subsys(&tipc_net_ops);
 	tipc_netlink_stop();
 	tipc_netlink_compat_stop();
-- 
2.20.1


From f44991cb2ff7b4e07183ddc197b750925b1a98ec Mon Sep 17 00:00:00 2001
From: "Jorge E. Moreira" <jemoreira@google.com>
Date: Thu, 16 May 2019 13:51:07 -0700
Subject: [PATCH 14/18] vsock/virtio: Initialize core virtio vsock before
 registering the driver

[ Upstream commit ba95e5dfd36647622d8897a2a0470dde60e59ffd ]

Avoid a race in which static variables in net/vmw_vsock/af_vsock.c are
accessed (while handling interrupts) before they are initialized.

[    4.201410] BUG: unable to handle kernel paging request at ffffffffffffffe8
[    4.207829] IP: vsock_addr_equals_addr+0x3/0x20
[    4.211379] PGD 28210067 P4D 28210067 PUD 28212067 PMD 0
[    4.211379] Oops: 0000 [#1] PREEMPT SMP PTI
[    4.211379] Modules linked in:
[    4.211379] CPU: 1 PID: 30 Comm: kworker/1:1 Not tainted 4.14.106-419297-gd7e28cc1f241 #1
[    4.211379] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014
[    4.211379] Workqueue: virtio_vsock virtio_transport_rx_work
[    4.211379] task: ffffa3273d175280 task.stack: ffffaea1800e8000
[    4.211379] RIP: 0010:vsock_addr_equals_addr+0x3/0x20
[    4.211379] RSP: 0000:ffffaea1800ebd28 EFLAGS: 00010286
[    4.211379] RAX: 0000000000000002 RBX: 0000000000000000 RCX: ffffffffb94e42f0
[    4.211379] RDX: 0000000000000400 RSI: ffffffffffffffe0 RDI: ffffaea1800ebdd0
[    4.211379] RBP: ffffaea1800ebd58 R08: 0000000000000001 R09: 0000000000000001
[    4.211379] R10: 0000000000000000 R11: ffffffffb89d5d60 R12: ffffaea1800ebdd0
[    4.211379] R13: 00000000828cbfbf R14: 0000000000000000 R15: ffffaea1800ebdc0
[    4.211379] FS:  0000000000000000(0000) GS:ffffa3273fd00000(0000) knlGS:0000000000000000
[    4.211379] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    4.211379] CR2: ffffffffffffffe8 CR3: 000000002820e001 CR4: 00000000001606e0
[    4.211379] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[    4.211379] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[    4.211379] Call Trace:
[    4.211379]  ? vsock_find_connected_socket+0x6c/0xe0
[    4.211379]  virtio_transport_recv_pkt+0x15f/0x740
[    4.211379]  ? detach_buf+0x1b5/0x210
[    4.211379]  virtio_transport_rx_work+0xb7/0x140
[    4.211379]  process_one_work+0x1ef/0x480
[    4.211379]  worker_thread+0x312/0x460
[    4.211379]  kthread+0x132/0x140
[    4.211379]  ? process_one_work+0x480/0x480
[    4.211379]  ? kthread_destroy_worker+0xd0/0xd0
[    4.211379]  ret_from_fork+0x35/0x40
[    4.211379] Code: c7 47 08 00 00 00 00 66 c7 07 28 00 c7 47 08 ff ff ff ff c7 47 04 ff ff ff ff c3 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 8b 47 08 <3b> 46 08 75 0a 8b 47 04 3b 46 04 0f 94 c0 c3 31 c0 c3 90 66 2e
[    4.211379] RIP: vsock_addr_equals_addr+0x3/0x20 RSP: ffffaea1800ebd28
[    4.211379] CR2: ffffffffffffffe8
[    4.211379] ---[ end trace f31cc4a2e6df3689 ]---
[    4.211379] Kernel panic - not syncing: Fatal exception in interrupt
[    4.211379] Kernel Offset: 0x37000000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff)
[    4.211379] Rebooting in 5 seconds..

Fixes: 22b5c0b63f32 ("vsock/virtio: fix kernel panic after device hot-unplug")
Cc: Stefan Hajnoczi <stefanha@redhat.com>
Cc: Stefano Garzarella <sgarzare@redhat.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: kvm@vger.kernel.org
Cc: virtualization@lists.linux-foundation.org
Cc: netdev@vger.kernel.org
Cc: kernel-team@android.com
Cc: stable@vger.kernel.org [4.9+]
Signed-off-by: Jorge E. Moreira <jemoreira@google.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/vmw_vsock/virtio_transport.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 15eb5d3d4750..96ab344f17bb 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -702,28 +702,27 @@ static int __init virtio_vsock_init(void)
 	if (!virtio_vsock_workqueue)
 		return -ENOMEM;
 
-	ret = register_virtio_driver(&virtio_vsock_driver);
+	ret = vsock_core_init(&virtio_transport.transport);
 	if (ret)
 		goto out_wq;
 
-	ret = vsock_core_init(&virtio_transport.transport);
+	ret = register_virtio_driver(&virtio_vsock_driver);
 	if (ret)
-		goto out_vdr;
+		goto out_vci;
 
 	return 0;
 
-out_vdr:
-	unregister_virtio_driver(&virtio_vsock_driver);
+out_vci:
+	vsock_core_exit();
 out_wq:
 	destroy_workqueue(virtio_vsock_workqueue);
 	return ret;
-
 }
 
 static void __exit virtio_vsock_exit(void)
 {
-	vsock_core_exit();
 	unregister_virtio_driver(&virtio_vsock_driver);
+	vsock_core_exit();
 	destroy_workqueue(virtio_vsock_workqueue);
 }
 
-- 
2.20.1


From d8add353e9934fcd03e5efe1ff80c43085a5cd65 Mon Sep 17 00:00:00 2001
From: Dmytro Linkin <dmitrolin@mellanox.com>
Date: Thu, 25 Apr 2019 08:52:02 +0000
Subject: [PATCH 15/18] net/mlx5e: Add missing ethtool driver info for
 representors

[ Upstream commit cf83c8fdcd4756644595521f48748ec22f7efede ]

For all representors added firmware version info to show in
ethtool driver info.
For uplink representor, because only it is tied to the pci device
sysfs, added pci bus info.

Fixes: ff9b85de5d5d ("net/mlx5e: Add some ethtool port control entries to the uplink rep netdev")
Signed-off-by: Dmytro Linkin <dmitrolin@mellanox.com>
Reviewed-by: Gavi Teitz <gavi@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en_rep.c  | 19 ++++++++++++++++++-
 1 file changed, 18 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index ef9e472daffb..3977f763b6ed 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -64,9 +64,26 @@ static void mlx5e_rep_indr_unregister_block(struct mlx5e_rep_priv *rpriv,
 static void mlx5e_rep_get_drvinfo(struct net_device *dev,
 				  struct ethtool_drvinfo *drvinfo)
 {
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5_core_dev *mdev = priv->mdev;
+
 	strlcpy(drvinfo->driver, mlx5e_rep_driver_name,
 		sizeof(drvinfo->driver));
 	strlcpy(drvinfo->version, UTS_RELEASE, sizeof(drvinfo->version));
+	snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
+		 "%d.%d.%04d (%.16s)",
+		 fw_rev_maj(mdev), fw_rev_min(mdev),
+		 fw_rev_sub(mdev), mdev->board_id);
+}
+
+static void mlx5e_uplink_rep_get_drvinfo(struct net_device *dev,
+					 struct ethtool_drvinfo *drvinfo)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+
+	mlx5e_rep_get_drvinfo(dev, drvinfo);
+	strlcpy(drvinfo->bus_info, pci_name(priv->mdev->pdev),
+		sizeof(drvinfo->bus_info));
 }
 
 static const struct counter_desc sw_rep_stats_desc[] = {
@@ -374,7 +391,7 @@ static const struct ethtool_ops mlx5e_vf_rep_ethtool_ops = {
 };
 
 static const struct ethtool_ops mlx5e_uplink_rep_ethtool_ops = {
-	.get_drvinfo	   = mlx5e_rep_get_drvinfo,
+	.get_drvinfo	   = mlx5e_uplink_rep_get_drvinfo,
 	.get_link	   = ethtool_op_get_link,
 	.get_strings       = mlx5e_rep_get_strings,
 	.get_sset_count    = mlx5e_rep_get_sset_count,
-- 
2.20.1


From 9c0e37391d72b4bb2f8cd4010977789bc079acde Mon Sep 17 00:00:00 2001
From: Dmytro Linkin <dmitrolin@mellanox.com>
Date: Thu, 2 May 2019 15:21:38 +0000
Subject: [PATCH 16/18] net/mlx5e: Additional check for flow destination
 comparison

[ Upstream commit c979c445a88e1c9dd7d8f90838c10456ae4ecd09 ]

Flow destination comparison has an inaccuracy: code see no
difference between same vf ports, which belong to different pfs.

Example: If start ping from VF0 (PF1) to VF1 (PF1) and mirror
all traffic to VF0 (PF2), icmp reply to VF0 (PF1) and mirrored
flow to VF0 (PF2) would be determined as same destination. It lead
to creating flow handler with rule nodes, which not added to node
tree. When later driver try to delete this flow rules we got
kernel crash.

Add comparison of vhca_id field to avoid this.

Fixes: 1228e912c934 ("net/mlx5: Consider encapsulation properties when comparing destinations")
Signed-off-by: Dmytro Linkin <dmitrolin@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 79f122b45def..abbdd4906984 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -1375,6 +1375,8 @@ static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1,
 		if ((d1->type == MLX5_FLOW_DESTINATION_TYPE_VPORT &&
 		     d1->vport.num == d2->vport.num &&
 		     d1->vport.flags == d2->vport.flags &&
+		     ((d1->vport.flags & MLX5_FLOW_DEST_VPORT_VHCA_ID) ?
+		      (d1->vport.vhca_id == d2->vport.vhca_id) : true) &&
 		     ((d1->vport.flags & MLX5_FLOW_DEST_VPORT_REFORMAT_ID) ?
 		      (d1->vport.reformat_id == d2->vport.reformat_id) : true)) ||
 		    (d1->type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE &&
-- 
2.20.1


From 4bef01fad7af2017c4c7b7f9be3e0b0019ad7f8e Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Tue, 7 May 2019 13:15:20 -0700
Subject: [PATCH 17/18] net/mlx5: Imply MLXFW in mlx5_core

[ Upstream commit bad861f31bb15a99becef31aab59640eaeb247e2 ]

mlxfw can be compiled as external module while mlx5_core can be
builtin, in such case mlx5 will act like mlxfw is disabled.

Since mlxfw is just a service library for mlx* drivers,
imply it in mlx5_core to make it always reachable if it was enabled.

Fixes: 3ffaabecd1a1 ("net/mlx5e: Support the flash device ethtool callback")
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index 37a551436e4a..b7e3b8902e7e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -8,6 +8,7 @@ config MLX5_CORE
 	depends on PCI
 	imply PTP_1588_CLOCK
 	imply VXLAN
+	imply MLXFW
 	default n
 	---help---
 	  Core driver for low level functionality of the ConnectX-4 and
-- 
2.20.1


From e000ee4f56afb30e39cd3e1b8e9beb9bdff2e23e Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Tue, 7 May 2019 12:59:38 -0700
Subject: [PATCH 18/18] net/mlx5e: Fix ethtool rxfh commands when
 CONFIG_MLX5_EN_RXNFC is disabled

[ Upstream commit 8f0916c6dc5cd5e3bc52416fa2a9ff4075080180 ]

ethtool user spaces needs to know ring count via ETHTOOL_GRXRINGS when
executing (ethtool -x) which is retrieved via ethtool get_rxnfc callback,
in mlx5 this callback is disabled when CONFIG_MLX5_EN_RXNFC=n.

This patch allows only ETHTOOL_GRXRINGS command on mlx5e_get_rxnfc() when
CONFIG_MLX5_EN_RXNFC is disabled, so ethtool -x will continue working.

Fixes: fe6d86b3c316 ("net/mlx5e: Add CONFIG_MLX5_EN_RXNFC for ethtool rx nfc")
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../ethernet/mellanox/mlx5/core/en_ethtool.c   | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 253496c4a3db..a908e29ddb7b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1802,6 +1802,22 @@ static int mlx5e_flash_device(struct net_device *dev,
 	return mlx5e_ethtool_flash_device(priv, flash);
 }
 
+#ifndef CONFIG_MLX5_EN_RXNFC
+/* When CONFIG_MLX5_EN_RXNFC=n we only support ETHTOOL_GRXRINGS
+ * otherwise this function will be defined from en_fs_ethtool.c
+ */
+static int mlx5e_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, u32 *rule_locs)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+
+	if (info->cmd != ETHTOOL_GRXRINGS)
+		return -EOPNOTSUPP;
+	/* ring_count is needed by ethtool -x */
+	info->data = priv->channels.params.num_channels;
+	return 0;
+}
+#endif
+
 const struct ethtool_ops mlx5e_ethtool_ops = {
 	.get_drvinfo       = mlx5e_get_drvinfo,
 	.get_link          = ethtool_op_get_link,
@@ -1820,8 +1836,8 @@ const struct ethtool_ops mlx5e_ethtool_ops = {
 	.get_rxfh_indir_size = mlx5e_get_rxfh_indir_size,
 	.get_rxfh          = mlx5e_get_rxfh,
 	.set_rxfh          = mlx5e_set_rxfh,
-#ifdef CONFIG_MLX5_EN_RXNFC
 	.get_rxnfc         = mlx5e_get_rxnfc,
+#ifdef CONFIG_MLX5_EN_RXNFC
 	.set_rxnfc         = mlx5e_set_rxnfc,
 #endif
 	.flash_device      = mlx5e_flash_device,
-- 
2.20.1


[-- Attachment #3: net_51.mbox --]
[-- Type: Application/Octet-Stream, Size: 57390 bytes --]

From 3ca6cdc80d02560ec15c950ecddb8df5a7f94f4e Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Thu, 16 May 2019 13:30:54 -0700
Subject: [PATCH 01/23] ipv6: fix src addr routing with the exception table

[ Upstream commit 510e2ceda031eed97a7a0f9aad65d271a58b460d ]

When inserting route cache into the exception table, the key is
generated with both src_addr and dest_addr with src addr routing.
However, current logic always assumes the src_addr used to generate the
key is a /128 host address. This is not true in the following scenarios:
1. When the route is a gateway route or does not have next hop.
   (rt6_is_gw_or_nonexthop() == false)
2. When calling ip6_rt_cache_alloc(), saddr is passed in as NULL.
This means, when looking for a route cache in the exception table, we
have to do the lookup twice: first time with the passed in /128 host
address, second time with the src_addr stored in fib6_info.

This solves the pmtu discovery issue reported by Mikael Magnusson where
a route cache with a lower mtu info is created for a gateway route with
src addr. However, the lookup code is not able to find this route cache.

Fixes: 2b760fcf5cfb ("ipv6: hook up exception table to store dst cache")
Reported-by: Mikael Magnusson <mikael.kernel@lists.m7n.se>
Bisected-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Wei Wang <weiwan@google.com>
Cc: Martin Lau <kafai@fb.com>
Cc: Eric Dumazet <edumazet@google.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 51 +++++++++++++++++++++++++-----------------------
 1 file changed, 27 insertions(+), 24 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 0520aca3354b..4ede79018481 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -110,8 +110,8 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 			 int iif, int type, u32 portid, u32 seq,
 			 unsigned int flags);
 static struct rt6_info *rt6_find_cached_rt(struct fib6_info *rt,
-					   struct in6_addr *daddr,
-					   struct in6_addr *saddr);
+					   const struct in6_addr *daddr,
+					   const struct in6_addr *saddr);
 
 #ifdef CONFIG_IPV6_ROUTE_INFO
 static struct fib6_info *rt6_add_route_info(struct net *net,
@@ -1529,31 +1529,44 @@ void rt6_flush_exceptions(struct fib6_info *rt)
  * Caller has to hold rcu_read_lock()
  */
 static struct rt6_info *rt6_find_cached_rt(struct fib6_info *rt,
-					   struct in6_addr *daddr,
-					   struct in6_addr *saddr)
+					   const struct in6_addr *daddr,
+					   const struct in6_addr *saddr)
 {
+	const struct in6_addr *src_key = NULL;
 	struct rt6_exception_bucket *bucket;
-	struct in6_addr *src_key = NULL;
 	struct rt6_exception *rt6_ex;
 	struct rt6_info *res = NULL;
 
-	bucket = rcu_dereference(rt->rt6i_exception_bucket);
-
 #ifdef CONFIG_IPV6_SUBTREES
 	/* rt6i_src.plen != 0 indicates rt is in subtree
 	 * and exception table is indexed by a hash of
 	 * both rt6i_dst and rt6i_src.
-	 * Otherwise, the exception table is indexed by
-	 * a hash of only rt6i_dst.
+	 * However, the src addr used to create the hash
+	 * might not be exactly the passed in saddr which
+	 * is a /128 addr from the flow.
+	 * So we need to use f6i->fib6_src to redo lookup
+	 * if the passed in saddr does not find anything.
+	 * (See the logic in ip6_rt_cache_alloc() on how
+	 * rt->rt6i_src is updated.)
 	 */
 	if (rt->fib6_src.plen)
 		src_key = saddr;
+find_ex:
 #endif
+	bucket = rcu_dereference(rt->rt6i_exception_bucket);
 	rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key);
 
 	if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i))
 		res = rt6_ex->rt6i;
 
+#ifdef CONFIG_IPV6_SUBTREES
+	/* Use fib6_src as src_key and redo lookup */
+	if (!res && src_key && src_key != &rt->fib6_src.addr) {
+		src_key = &rt->fib6_src.addr;
+		goto find_ex;
+	}
+#endif
+
 	return res;
 }
 
@@ -2608,10 +2621,8 @@ static unsigned int ip6_mtu(const struct dst_entry *dst)
 u32 ip6_mtu_from_fib6(struct fib6_info *f6i, struct in6_addr *daddr,
 		      struct in6_addr *saddr)
 {
-	struct rt6_exception_bucket *bucket;
-	struct rt6_exception *rt6_ex;
-	struct in6_addr *src_key;
 	struct inet6_dev *idev;
+	struct rt6_info *rt;
 	u32 mtu = 0;
 
 	if (unlikely(fib6_metric_locked(f6i, RTAX_MTU))) {
@@ -2620,18 +2631,10 @@ u32 ip6_mtu_from_fib6(struct fib6_info *f6i, struct in6_addr *daddr,
 			goto out;
 	}
 
-	src_key = NULL;
-#ifdef CONFIG_IPV6_SUBTREES
-	if (f6i->fib6_src.plen)
-		src_key = saddr;
-#endif
-
-	bucket = rcu_dereference(f6i->rt6i_exception_bucket);
-	rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key);
-	if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i))
-		mtu = dst_metric_raw(&rt6_ex->rt6i->dst, RTAX_MTU);
-
-	if (likely(!mtu)) {
+	rt = rt6_find_cached_rt(f6i, daddr, saddr);
+	if (unlikely(rt)) {
+		mtu = dst_metric_raw(&rt->dst, RTAX_MTU);
+	} else {
 		struct net_device *dev = fib6_info_nh_dev(f6i);
 
 		mtu = IPV6_MIN_MTU;
-- 
2.20.1


From 8909532df30d468f8b0f2ed1b45f84b1c72b1cd1 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 15 May 2019 19:39:52 -0700
Subject: [PATCH 02/23] ipv6: prevent possible fib6 leaks

[ Upstream commit 61fb0d01680771f72cc9d39783fb2c122aaad51e ]

At ipv6 route dismantle, fib6_drop_pcpu_from() is responsible
for finding all percpu routes and set their ->from pointer
to NULL, so that fib6_ref can reach its expected value (1).

The problem right now is that other cpus can still catch the
route being deleted, since there is no rcu grace period
between the route deletion and call to fib6_drop_pcpu_from()

This can leak the fib6 and associated resources, since no
notifier will take care of removing the last reference(s).

I decided to add another boolean (fib6_destroying) instead
of reusing/renaming exception_bucket_flushed to ease stable backports,
and properly document the memory barriers used to implement this fix.

This patch has been co-developped with Wei Wang.

Fixes: 93531c674315 ("net/ipv6: separate handling of FIB entries from dst based routes")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Wei Wang <weiwan@google.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Martin Lau <kafai@fb.com>
Acked-by: Wei Wang <weiwan@google.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h |  3 ++-
 net/ipv6/ip6_fib.c    | 12 +++++++++---
 net/ipv6/route.c      |  7 +++++++
 3 files changed, 18 insertions(+), 4 deletions(-)

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 84097010237c..b5e3add90e99 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -171,7 +171,8 @@ struct fib6_info {
 					dst_nocount:1,
 					dst_nopolicy:1,
 					dst_host:1,
-					unused:3;
+					fib6_destroying:1,
+					unused:2;
 
 	struct fib6_nh			fib6_nh;
 	struct rcu_head			rcu;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 91247a6fc67f..9915f64b38a0 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -909,6 +909,12 @@ static void fib6_drop_pcpu_from(struct fib6_info *f6i,
 {
 	int cpu;
 
+	/* Make sure rt6_make_pcpu_route() wont add other percpu routes
+	 * while we are cleaning them here.
+	 */
+	f6i->fib6_destroying = 1;
+	mb(); /* paired with the cmpxchg() in rt6_make_pcpu_route() */
+
 	/* release the reference to this fib entry from
 	 * all of its cached pcpu routes
 	 */
@@ -932,6 +938,9 @@ static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn,
 {
 	struct fib6_table *table = rt->fib6_table;
 
+	if (rt->rt6i_pcpu)
+		fib6_drop_pcpu_from(rt, table);
+
 	if (atomic_read(&rt->fib6_ref) != 1) {
 		/* This route is used as dummy address holder in some split
 		 * nodes. It is not leaked, but it still holds other resources,
@@ -953,9 +962,6 @@ static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn,
 			fn = rcu_dereference_protected(fn->parent,
 				    lockdep_is_held(&table->tb6_lock));
 		}
-
-		if (rt->rt6i_pcpu)
-			fib6_drop_pcpu_from(rt, table);
 	}
 }
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 4ede79018481..e470589fb93b 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1260,6 +1260,13 @@ static struct rt6_info *rt6_make_pcpu_route(struct net *net,
 	prev = cmpxchg(p, NULL, pcpu_rt);
 	BUG_ON(prev);
 
+	if (rt->fib6_destroying) {
+		struct fib6_info *from;
+
+		from = xchg((__force struct fib6_info **)&pcpu_rt->from, NULL);
+		fib6_info_release(from);
+	}
+
 	return pcpu_rt;
 }
 
-- 
2.20.1


From 5ea4f89741d8f734b8bff44a09706cadeaaabc1a Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Mon, 13 May 2019 14:06:24 -0700
Subject: [PATCH 03/23] net: Always descend into dsa/

[ Upstream commit 0fe9f173d6cda95874edeb413b1fa9907b5ae830 ]

Jiri reported that with a kernel built with CONFIG_FIXED_PHY=y,
CONFIG_NET_DSA=m and CONFIG_NET_DSA_LOOP=m, we would not get to a
functional state where the mock-up driver is registered. Turns out that
we are not descending into drivers/net/dsa/ unconditionally, and we
won't be able to link-in dsa_loop_bdinfo.o which does the actual mock-up
mdio device registration.

Reported-by: Jiri Pirko <jiri@resnulli.us>
Fixes: 40013ff20b1b ("net: dsa: Fix functional dsa-loop dependency on FIXED_PHY")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Vivien Didelot <vivien.didelot@gmail.com>
Tested-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index 21cde7e78621..0d3ba056cda3 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -40,7 +40,7 @@ obj-$(CONFIG_ARCNET) += arcnet/
 obj-$(CONFIG_DEV_APPLETALK) += appletalk/
 obj-$(CONFIG_CAIF) += caif/
 obj-$(CONFIG_CAN) += can/
-obj-$(CONFIG_NET_DSA) += dsa/
+obj-y += dsa/
 obj-$(CONFIG_ETHERNET) += ethernet/
 obj-$(CONFIG_FDDI) += fddi/
 obj-$(CONFIG_HIPPI) += hippi/
-- 
2.20.1


From c0a0c28e75d1190a980529378e4ba926d357962e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 16 May 2019 08:09:57 -0700
Subject: [PATCH 04/23] net: avoid weird emergency message

[ Upstream commit d7c04b05c9ca14c55309eb139430283a45c4c25f ]

When host is under high stress, it is very possible thread
running netdev_wait_allrefs() returns from msleep(250)
10 seconds late.

This leads to these messages in the syslog :

[...] unregister_netdevice: waiting for syz_tun to become free. Usage count = 0

If the device refcount is zero, the wait is over.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index f409406254dd..255f99cb7c48 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8911,7 +8911,7 @@ static void netdev_wait_allrefs(struct net_device *dev)
 
 		refcnt = netdev_refcnt_read(dev);
 
-		if (time_after(jiffies, warning_time + 10 * HZ)) {
+		if (refcnt && time_after(jiffies, warning_time + 10 * HZ)) {
 			pr_emerg("unregister_netdevice: waiting for %s to become free. Usage count = %d\n",
 				 dev->name, refcnt);
 			warning_time = jiffies;
-- 
2.20.1


From ffa6084ed4d260057fe28d66bd9dec8b79574daf Mon Sep 17 00:00:00 2001
From: Yunjian Wang <wangyunjian@huawei.com>
Date: Tue, 14 May 2019 19:03:19 +0800
Subject: [PATCH 05/23] net/mlx4_core: Change the error print to info print

[ Upstream commit 00f9fec48157f3734e52130a119846e67a12314b ]

The error print within mlx4_flow_steer_promisc_add() should
be a info print.

Fixes: 592e49dda812 ('net/mlx4: Implement promiscuous mode with device managed flow-steering')
Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/mcg.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c
index ffed2d4c9403..9c481823b3e8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mcg.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c
@@ -1492,7 +1492,7 @@ int mlx4_flow_steer_promisc_add(struct mlx4_dev *dev, u8 port,
 	rule.port = port;
 	rule.qpn = qpn;
 	INIT_LIST_HEAD(&rule.list);
-	mlx4_err(dev, "going promisc on %x\n", port);
+	mlx4_info(dev, "going promisc on %x\n", port);
 
 	return  mlx4_flow_attach(dev, &rule, regid_p);
 }
-- 
2.20.1


From 8101018ec8a99816193eee31684cc95fa9179e56 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 15 May 2019 13:29:16 -0400
Subject: [PATCH 06/23] net: test nouarg before dereferencing zerocopy pointers

[ Upstream commit 185ce5c38ea76f29b6bd9c7c8c7a5e5408834920 ]

Zerocopy skbs without completion notification were added for packet
sockets with PACKET_TX_RING user buffers. Those signal completion
through the TP_STATUS_USER bit in the ring. Zerocopy annotation was
added only to avoid premature notification after clone or orphan, by
triggering a copy on these paths for these packets.

The mechanism had to define a special "no-uarg" mode because packet
sockets already use skb_uarg(skb) == skb_shinfo(skb)->destructor_arg
for a different pointer.

Before deferencing skb_uarg(skb), verify that it is a real pointer.

Fixes: 5cd8d46ea1562 ("packet: copy user buffers before orphan or clone")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 9027a8c4219f..20a4c2280308 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1425,10 +1425,12 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy)
 	struct ubuf_info *uarg = skb_zcopy(skb);
 
 	if (uarg) {
-		if (uarg->callback == sock_zerocopy_callback) {
+		if (skb_zcopy_is_nouarg(skb)) {
+			/* no notification callback */
+		} else if (uarg->callback == sock_zerocopy_callback) {
 			uarg->zerocopy = uarg->zerocopy && zerocopy;
 			sock_zerocopy_put(uarg);
-		} else if (!skb_zcopy_is_nouarg(skb)) {
+		} else {
 			uarg->callback(uarg, zerocopy);
 		}
 
@@ -2683,7 +2685,8 @@ static inline int skb_orphan_frags(struct sk_buff *skb, gfp_t gfp_mask)
 {
 	if (likely(!skb_zcopy(skb)))
 		return 0;
-	if (skb_uarg(skb)->callback == sock_zerocopy_callback)
+	if (!skb_zcopy_is_nouarg(skb) &&
+	    skb_uarg(skb)->callback == sock_zerocopy_callback)
 		return 0;
 	return skb_copy_ubufs(skb, gfp_mask);
 }
-- 
2.20.1


From d5a4c9f1101a1abc5eea172f9006b5fc4f395fbf Mon Sep 17 00:00:00 2001
From: Daniele Palmas <dnlplm@gmail.com>
Date: Wed, 15 May 2019 17:29:43 +0200
Subject: [PATCH 07/23] net: usb: qmi_wwan: add Telit 0x1260 and 0x1261
 compositions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit b4e467c82f8c12af78b6f6fa5730cb7dea7af1b4 ]

Added support for Telit LE910Cx 0x1260 and 0x1261 compositions.

Signed-off-by: Daniele Palmas <dnlplm@gmail.com>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 679e404a5224..366217263d70 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1250,6 +1250,8 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1bc7, 0x1101, 3)},	/* Telit ME910 dual modem */
 	{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)},	/* Telit LE920 */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1201, 2)},	/* Telit LE920, LE920A4 */
+	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1260, 2)},	/* Telit LE910Cx */
+	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1261, 2)},	/* Telit LE910Cx */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1900, 1)},	/* Telit LN940 series */
 	{QMI_FIXED_INTF(0x1c9e, 0x9801, 3)},	/* Telewell TW-3G HSPA+ */
 	{QMI_FIXED_INTF(0x1c9e, 0x9803, 4)},	/* Telewell TW-3G HSPA+ */
-- 
2.20.1


From 009274f96292520392d29254d0f18bc370bf4dd0 Mon Sep 17 00:00:00 2001
From: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Date: Tue, 14 May 2019 14:28:19 -0700
Subject: [PATCH 08/23] nfp: flower: add rcu locks when accessing netdev for
 tunnels

[ Upstream commit cb07d915bf278a7a3938b983bbcb4921366b5eff ]

Add rcu locks when accessing netdev when processing route request
and tunnel keep alive messages received from hardware.

Fixes: 8e6a9046b66a ("nfp: flower vxlan neighbour offload")
Fixes: 856f5b135758 ("nfp: flower vxlan neighbour keep-alive")
Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/netronome/nfp/flower/tunnel_conf.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
index 4d78be4ec4e9..843ddf548f26 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
@@ -168,6 +168,7 @@ void nfp_tunnel_keep_alive(struct nfp_app *app, struct sk_buff *skb)
 		return;
 	}
 
+	rcu_read_lock();
 	for (i = 0; i < count; i++) {
 		ipv4_addr = payload->tun_info[i].ipv4;
 		port = be32_to_cpu(payload->tun_info[i].egress_port);
@@ -183,6 +184,7 @@ void nfp_tunnel_keep_alive(struct nfp_app *app, struct sk_buff *skb)
 		neigh_event_send(n, NULL);
 		neigh_release(n);
 	}
+	rcu_read_unlock();
 }
 
 static int
@@ -366,9 +368,10 @@ void nfp_tunnel_request_route(struct nfp_app *app, struct sk_buff *skb)
 
 	payload = nfp_flower_cmsg_get_data(skb);
 
+	rcu_read_lock();
 	netdev = nfp_app_repr_get(app, be32_to_cpu(payload->ingress_port));
 	if (!netdev)
-		goto route_fail_warning;
+		goto fail_rcu_unlock;
 
 	flow.daddr = payload->ipv4_addr;
 	flow.flowi4_proto = IPPROTO_UDP;
@@ -378,21 +381,23 @@ void nfp_tunnel_request_route(struct nfp_app *app, struct sk_buff *skb)
 	rt = ip_route_output_key(dev_net(netdev), &flow);
 	err = PTR_ERR_OR_ZERO(rt);
 	if (err)
-		goto route_fail_warning;
+		goto fail_rcu_unlock;
 #else
-	goto route_fail_warning;
+	goto fail_rcu_unlock;
 #endif
 
 	/* Get the neighbour entry for the lookup */
 	n = dst_neigh_lookup(&rt->dst, &flow.daddr);
 	ip_rt_put(rt);
 	if (!n)
-		goto route_fail_warning;
-	nfp_tun_write_neigh(n->dev, app, &flow, n, GFP_KERNEL);
+		goto fail_rcu_unlock;
+	nfp_tun_write_neigh(n->dev, app, &flow, n, GFP_ATOMIC);
 	neigh_release(n);
+	rcu_read_unlock();
 	return;
 
-route_fail_warning:
+fail_rcu_unlock:
+	rcu_read_unlock();
 	nfp_flower_cmsg_warn(app, "Requested route not found.\n");
 }
 
-- 
2.20.1


From ee40adc4a9401bfe7fd86052ad7eb3f67311202c Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Tue, 14 May 2019 22:55:32 +0800
Subject: [PATCH 09/23] ppp: deflate: Fix possible crash in deflate_init

[ Upstream commit 3ebe1bca58c85325c97a22d4fc3f5b5420752e6f ]

BUG: unable to handle kernel paging request at ffffffffa018f000
PGD 3270067 P4D 3270067 PUD 3271063 PMD 2307eb067 PTE 0
Oops: 0000 [#1] PREEMPT SMP
CPU: 0 PID: 4138 Comm: modprobe Not tainted 5.1.0-rc7+ #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS
rel-1.9.3-0-ge2fc41e-prebuilt.qemu-project.org 04/01/2014
RIP: 0010:ppp_register_compressor+0x3e/0xd0 [ppp_generic]
Code: 98 4a 3f e2 48 8b 15 c1 67 00 00 41 8b 0c 24 48 81 fa 40 f0 19 a0
75 0e eb 35 48 8b 12 48 81 fa 40 f0 19 a0 74
RSP: 0018:ffffc90000d93c68 EFLAGS: 00010287
RAX: ffffffffa018f000 RBX: ffffffffa01a3000 RCX: 000000000000001a
RDX: ffff888230c750a0 RSI: 0000000000000000 RDI: ffffffffa019f000
RBP: ffffc90000d93c80 R08: 0000000000000001 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: ffffffffa0194080
R13: ffff88822ee1a700 R14: 0000000000000000 R15: ffffc90000d93e78
FS:  00007f2339557540(0000) GS:ffff888237a00000(0000)
knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffffffffa018f000 CR3: 000000022bde4000 CR4: 00000000000006f0
Call Trace:
 ? 0xffffffffa01a3000
 deflate_init+0x11/0x1000 [ppp_deflate]
 ? 0xffffffffa01a3000
 do_one_initcall+0x6c/0x3cc
 ? kmem_cache_alloc_trace+0x248/0x3b0
 do_init_module+0x5b/0x1f1
 load_module+0x1db1/0x2690
 ? m_show+0x1d0/0x1d0
 __do_sys_finit_module+0xc5/0xd0
 __x64_sys_finit_module+0x15/0x20
 do_syscall_64+0x6b/0x1d0
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

If ppp_deflate fails to register in deflate_init,
module initialization failed out, however
ppp_deflate_draft may has been regiestred and not
unregistered before return.
Then the seconed modprobe will trigger crash like this.

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/ppp_deflate.c | 20 ++++++++++++++------
 1 file changed, 14 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ppp/ppp_deflate.c b/drivers/net/ppp/ppp_deflate.c
index b5edc7f96a39..685e875f5164 100644
--- a/drivers/net/ppp/ppp_deflate.c
+++ b/drivers/net/ppp/ppp_deflate.c
@@ -610,12 +610,20 @@ static struct compressor ppp_deflate_draft = {
 
 static int __init deflate_init(void)
 {
-        int answer = ppp_register_compressor(&ppp_deflate);
-        if (answer == 0)
-                printk(KERN_INFO
-		       "PPP Deflate Compression module registered\n");
-	ppp_register_compressor(&ppp_deflate_draft);
-        return answer;
+	int rc;
+
+	rc = ppp_register_compressor(&ppp_deflate);
+	if (rc)
+		return rc;
+
+	rc = ppp_register_compressor(&ppp_deflate_draft);
+	if (rc) {
+		ppp_unregister_compressor(&ppp_deflate);
+		return rc;
+	}
+
+	pr_info("PPP Deflate Compression module registered\n");
+	return 0;
 }
 
 static void __exit deflate_cleanup(void)
-- 
2.20.1


From 1a7897bf079e709423b87183baec654f07a343d8 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 14 May 2019 15:12:19 +0200
Subject: [PATCH 10/23] rtnetlink: always put IFLA_LINK for links with a
 link-netnsid

[ Upstream commit feadc4b6cf42a53a8a93c918a569a0b7e62bd350 ]

Currently, nla_put_iflink() doesn't put the IFLA_LINK attribute when
iflink == ifindex.

In some cases, a device can be created in a different netns with the
same ifindex as its parent. That device will not dump its IFLA_LINK
attribute, which can confuse some userspace software that expects it.
For example, if the last ifindex created in init_net and foo are both
8, these commands will trigger the issue:

    ip link add parent type dummy                   # ifindex 9
    ip link add link parent netns foo type macvlan  # ifindex 9 in ns foo

So, in case a device puts the IFLA_LINK_NETNSID attribute in a dump,
always put the IFLA_LINK attribute as well.

Thanks to Dan Winship for analyzing the original OpenShift bug down to
the missing netlink attribute.

v2: change Fixes tag, it's been here forever, as Nicolas Dichtel said
    add Nicolas' ack
v3: change Fixes tag
    fix subject typo, spotted by Edward Cree

Analyzed-by: Dan Winship <danw@redhat.com>
Fixes: d8a5ec672768 ("[NET]: netlink support for moving devices between network namespaces.")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 220c56e93659..467d771ac6ba 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1496,14 +1496,15 @@ static int put_master_ifindex(struct sk_buff *skb, struct net_device *dev)
 	return ret;
 }
 
-static int nla_put_iflink(struct sk_buff *skb, const struct net_device *dev)
+static int nla_put_iflink(struct sk_buff *skb, const struct net_device *dev,
+			  bool force)
 {
 	int ifindex = dev_get_iflink(dev);
 
-	if (dev->ifindex == ifindex)
-		return 0;
+	if (force || dev->ifindex != ifindex)
+		return nla_put_u32(skb, IFLA_LINK, ifindex);
 
-	return nla_put_u32(skb, IFLA_LINK, ifindex);
+	return 0;
 }
 
 static noinline_for_stack int nla_put_ifalias(struct sk_buff *skb,
@@ -1520,6 +1521,8 @@ static int rtnl_fill_link_netnsid(struct sk_buff *skb,
 				  const struct net_device *dev,
 				  struct net *src_net)
 {
+	bool put_iflink = false;
+
 	if (dev->rtnl_link_ops && dev->rtnl_link_ops->get_link_net) {
 		struct net *link_net = dev->rtnl_link_ops->get_link_net(dev);
 
@@ -1528,10 +1531,12 @@ static int rtnl_fill_link_netnsid(struct sk_buff *skb,
 
 			if (nla_put_s32(skb, IFLA_LINK_NETNSID, id))
 				return -EMSGSIZE;
+
+			put_iflink = true;
 		}
 	}
 
-	return 0;
+	return nla_put_iflink(skb, dev, put_iflink);
 }
 
 static int rtnl_fill_link_af(struct sk_buff *skb,
@@ -1617,7 +1622,6 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
 #ifdef CONFIG_RPS
 	    nla_put_u32(skb, IFLA_NUM_RX_QUEUES, dev->num_rx_queues) ||
 #endif
-	    nla_put_iflink(skb, dev) ||
 	    put_master_ifindex(skb, dev) ||
 	    nla_put_u8(skb, IFLA_CARRIER, netif_carrier_ok(dev)) ||
 	    (dev->qdisc &&
-- 
2.20.1


From f72f3d00b1a5d89b7e29bb2a156fe23e0eeb8fbf Mon Sep 17 00:00:00 2001
From: Junwei Hu <hujunwei4@huawei.com>
Date: Thu, 16 May 2019 10:51:15 +0800
Subject: [PATCH 11/23] tipc: switch order of device registration to fix a
 crash

[ Upstream commit 7e27e8d6130c5e88fac9ddec4249f7f2337fe7f8 ]

When tipc is loaded while many processes try to create a TIPC socket,
a crash occurs:
 PANIC: Unable to handle kernel paging request at virtual
 address "dfff20000000021d"
 pc : tipc_sk_create+0x374/0x1180 [tipc]
 lr : tipc_sk_create+0x374/0x1180 [tipc]
   Exception class = DABT (current EL), IL = 32 bits
 Call trace:
  tipc_sk_create+0x374/0x1180 [tipc]
  __sock_create+0x1cc/0x408
  __sys_socket+0xec/0x1f0
  __arm64_sys_socket+0x74/0xa8
 ...

This is due to race between sock_create and unfinished
register_pernet_device. tipc_sk_insert tries to do
"net_generic(net, tipc_net_id)".
but tipc_net_id is not initialized yet.

So switch the order of the two to close the race.

This can be reproduced with multiple processes doing socket(AF_TIPC, ...)
and one process doing module removal.

Fixes: a62fbccecd62 ("tipc: make subscriber server support net namespace")
Signed-off-by: Junwei Hu <hujunwei4@huawei.com>
Reported-by: Wang Wang <wangwang2@huawei.com>
Reviewed-by: Xiaogang Wang <wangxiaogang3@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/core.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/net/tipc/core.c b/net/tipc/core.c
index 5b38f5164281..dbfc1e8b2866 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -129,10 +129,6 @@ static int __init tipc_init(void)
 	if (err)
 		goto out_netlink_compat;
 
-	err = tipc_socket_init();
-	if (err)
-		goto out_socket;
-
 	err = tipc_register_sysctl();
 	if (err)
 		goto out_sysctl;
@@ -141,6 +137,10 @@ static int __init tipc_init(void)
 	if (err)
 		goto out_pernet;
 
+	err = tipc_socket_init();
+	if (err)
+		goto out_socket;
+
 	err = tipc_bearer_setup();
 	if (err)
 		goto out_bearer;
@@ -148,12 +148,12 @@ static int __init tipc_init(void)
 	pr_info("Started in single node mode\n");
 	return 0;
 out_bearer:
+	tipc_socket_stop();
+out_socket:
 	unregister_pernet_subsys(&tipc_net_ops);
 out_pernet:
 	tipc_unregister_sysctl();
 out_sysctl:
-	tipc_socket_stop();
-out_socket:
 	tipc_netlink_compat_stop();
 out_netlink_compat:
 	tipc_netlink_stop();
@@ -165,10 +165,10 @@ static int __init tipc_init(void)
 static void __exit tipc_exit(void)
 {
 	tipc_bearer_cleanup();
+	tipc_socket_stop();
 	unregister_pernet_subsys(&tipc_net_ops);
 	tipc_netlink_stop();
 	tipc_netlink_compat_stop();
-	tipc_socket_stop();
 	tipc_unregister_sysctl();
 
 	pr_info("Deactivated\n");
-- 
2.20.1


From f42d037d50315d1aaad9c44cbb03e49b3c1117eb Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Fri, 17 May 2019 16:45:43 +0200
Subject: [PATCH 12/23] vsock/virtio: free packets during the socket release

[ Upstream commit ac03046ece2b158ebd204dfc4896fd9f39f0e6c8 ]

When the socket is released, we should free all packets
queued in the per-socket list in order to avoid a memory
leak.

Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/vmw_vsock/virtio_transport_common.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 602715fc9a75..f3f3d06cb6d8 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -786,12 +786,19 @@ static bool virtio_transport_close(struct vsock_sock *vsk)
 
 void virtio_transport_release(struct vsock_sock *vsk)
 {
+	struct virtio_vsock_sock *vvs = vsk->trans;
+	struct virtio_vsock_pkt *pkt, *tmp;
 	struct sock *sk = &vsk->sk;
 	bool remove_sock = true;
 
 	lock_sock(sk);
 	if (sk->sk_type == SOCK_STREAM)
 		remove_sock = virtio_transport_close(vsk);
+
+	list_for_each_entry_safe(pkt, tmp, &vvs->rx_queue, list) {
+		list_del(&pkt->list);
+		virtio_transport_free_pkt(pkt);
+	}
 	release_sock(sk);
 
 	if (remove_sock)
-- 
2.20.1


From cfd4034d3157550c36d5a11009eb3adbd629e785 Mon Sep 17 00:00:00 2001
From: Junwei Hu <hujunwei4@huawei.com>
Date: Fri, 17 May 2019 19:27:34 +0800
Subject: [PATCH 13/23] tipc: fix modprobe tipc failed after switch order of
 device registration

[ Upstream commit 532b0f7ece4cb2ffd24dc723ddf55242d1188e5e ]

Error message printed:
modprobe: ERROR: could not insert 'tipc': Address family not
supported by protocol.
when modprobe tipc after the following patch: switch order of
device registration, commit 7e27e8d6130c
("tipc: switch order of device registration to fix a crash")

Because sock_create_kern(net, AF_TIPC, ...) is called by
tipc_topsrv_create_listener() in the initialization process
of tipc_net_ops, tipc_socket_init() must be execute before that.

I move tipc_socket_init() into function tipc_init_net().

Fixes: 7e27e8d6130c
("tipc: switch order of device registration to fix a crash")
Signed-off-by: Junwei Hu <hujunwei4@huawei.com>
Reported-by: Wang Wang <wangwang2@huawei.com>
Reviewed-by: Kang Zhou <zhoukang7@huawei.com>
Reviewed-by: Suanming Mou <mousuanming@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/core.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/net/tipc/core.c b/net/tipc/core.c
index dbfc1e8b2866..d7b0688c98dd 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -66,6 +66,10 @@ static int __net_init tipc_init_net(struct net *net)
 	INIT_LIST_HEAD(&tn->node_list);
 	spin_lock_init(&tn->node_list_lock);
 
+	err = tipc_socket_init();
+	if (err)
+		goto out_socket;
+
 	err = tipc_sk_rht_init(net);
 	if (err)
 		goto out_sk_rht;
@@ -92,6 +96,8 @@ static int __net_init tipc_init_net(struct net *net)
 out_nametbl:
 	tipc_sk_rht_destroy(net);
 out_sk_rht:
+	tipc_socket_stop();
+out_socket:
 	return err;
 }
 
@@ -102,6 +108,7 @@ static void __net_exit tipc_exit_net(struct net *net)
 	tipc_bcast_stop(net);
 	tipc_nametbl_stop(net);
 	tipc_sk_rht_destroy(net);
+	tipc_socket_stop();
 }
 
 static struct pernet_operations tipc_net_ops = {
@@ -137,10 +144,6 @@ static int __init tipc_init(void)
 	if (err)
 		goto out_pernet;
 
-	err = tipc_socket_init();
-	if (err)
-		goto out_socket;
-
 	err = tipc_bearer_setup();
 	if (err)
 		goto out_bearer;
@@ -148,8 +151,6 @@ static int __init tipc_init(void)
 	pr_info("Started in single node mode\n");
 	return 0;
 out_bearer:
-	tipc_socket_stop();
-out_socket:
 	unregister_pernet_subsys(&tipc_net_ops);
 out_pernet:
 	tipc_unregister_sysctl();
@@ -165,7 +166,6 @@ static int __init tipc_init(void)
 static void __exit tipc_exit(void)
 {
 	tipc_bearer_cleanup();
-	tipc_socket_stop();
 	unregister_pernet_subsys(&tipc_net_ops);
 	tipc_netlink_stop();
 	tipc_netlink_compat_stop();
-- 
2.20.1


From 3220f01e4f21a3d438c295be0bcc5ff19adaa163 Mon Sep 17 00:00:00 2001
From: Vadim Pasternak <vadimp@mellanox.com>
Date: Sat, 18 May 2019 18:58:28 +0300
Subject: [PATCH 14/23] mlxsw: core: Prevent QSFP module initialization for old
 hardware

[ Upstream commit c52ecff7e6439ca8c9b03282e8869a005aa94831 ]

Old Mellanox silicons, like switchx-2, switch-ib do not support reading
QSFP modules temperature through MTMP register. Attempt to access this
register on systems equipped with the this kind of silicon will cause
initialization flow failure.
Test for hardware resource capability is added in order to distinct
between old and new silicon - old silicons do not have such capability.

Fixes: 6a79507cfe94 ("mlxsw: core: Extend thermal module with per QSFP module thermal zones")
Fixes: 5c42eaa07bd0 ("mlxsw: core: Extend hwmon interface with QSFP module temperature attributes")
Reported-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Vadim Pasternak <vadimp@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/core.c         | 6 ++++++
 drivers/net/ethernet/mellanox/mlxsw/core.h         | 2 ++
 drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c   | 3 +++
 drivers/net/ethernet/mellanox/mlxsw/core_thermal.c | 6 ++++++
 4 files changed, 17 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index f26a4ca29363..0b56291d22c6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -122,6 +122,12 @@ void *mlxsw_core_driver_priv(struct mlxsw_core *mlxsw_core)
 }
 EXPORT_SYMBOL(mlxsw_core_driver_priv);
 
+bool mlxsw_core_res_query_enabled(const struct mlxsw_core *mlxsw_core)
+{
+	return mlxsw_core->driver->res_query_enabled;
+}
+EXPORT_SYMBOL(mlxsw_core_res_query_enabled);
+
 struct mlxsw_rx_listener_item {
 	struct list_head list;
 	struct mlxsw_rx_listener rxl;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h
index 8ec53f027575..62b8de9305af 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.h
@@ -28,6 +28,8 @@ unsigned int mlxsw_core_max_ports(const struct mlxsw_core *mlxsw_core);
 
 void *mlxsw_core_driver_priv(struct mlxsw_core *mlxsw_core);
 
+bool mlxsw_core_res_query_enabled(const struct mlxsw_core *mlxsw_core);
+
 int mlxsw_core_driver_register(struct mlxsw_driver *mlxsw_driver);
 void mlxsw_core_driver_unregister(struct mlxsw_driver *mlxsw_driver);
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
index 6956bbebe2f1..496dc904c5ed 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
@@ -518,6 +518,9 @@ static int mlxsw_hwmon_module_init(struct mlxsw_hwmon *mlxsw_hwmon)
 	u8 width;
 	int err;
 
+	if (!mlxsw_core_res_query_enabled(mlxsw_hwmon->core))
+		return 0;
+
 	/* Add extra attributes for module temperature. Sensor index is
 	 * assigned to sensor_count value, while all indexed before
 	 * sensor_count are already utilized by the sensors connected through
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index 472f63f9fac5..d3e851e7ca72 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -740,6 +740,9 @@ mlxsw_thermal_modules_init(struct device *dev, struct mlxsw_core *core,
 	struct mlxsw_thermal_module *module_tz;
 	int i, err;
 
+	if (!mlxsw_core_res_query_enabled(core))
+		return 0;
+
 	thermal->tz_module_arr = kcalloc(module_count,
 					 sizeof(*thermal->tz_module_arr),
 					 GFP_KERNEL);
@@ -776,6 +779,9 @@ mlxsw_thermal_modules_fini(struct mlxsw_thermal *thermal)
 	unsigned int module_count = mlxsw_core_max_ports(thermal->core);
 	int i;
 
+	if (!mlxsw_core_res_query_enabled(thermal->core))
+		return;
+
 	for (i = module_count - 1; i >= 0; i--)
 		mlxsw_thermal_module_fini(&thermal->tz_module_arr[i]);
 	kfree(thermal->tz_module_arr);
-- 
2.20.1


From e3eb25f59cd65a0dcb797f87f7a1bb94d39032de Mon Sep 17 00:00:00 2001
From: Vadim Pasternak <vadimp@mellanox.com>
Date: Sat, 18 May 2019 18:58:29 +0300
Subject: [PATCH 15/23] mlxsw: core: Prevent reading unsupported slave address
 from SFP EEPROM

[ Upstream commit f1436c8036fa3632b2ee78841cf5184b7ef0ad87 ]

Prevent reading unsupported slave address from SFP EEPROM by testing
Diagnostic Monitoring Type byte in EEPROM. Read only page zero of
EEPROM, in case this byte is zero.

If some SFP transceiver does not support Digital Optical Monitoring
(DOM), reading SFP EEPROM slave address 0x51 could return an error.
Availability of DOM support is verified by reading from zero page
Diagnostic Monitoring Type byte describing how diagnostic monitoring is
implemented by transceiver. If bit 6 of this byte is set, it indicates
that digital diagnostic monitoring has been implemented. Otherwise it is
not and transceiver could fail to reply to transaction for slave address
0x51 [1010001X (A2h)], which is used to access measurements page.

Such issue has been observed when reading cable MCP2M00-xxxx,
MCP7F00-xxxx, and few others.

Fixes: 2ea109039cd3 ("mlxsw: spectrum: Add support for access cable info via ethtool")
Fixes: 4400081b631a ("mlxsw: spectrum: Fix EEPROM access in case of SFP/SFP+")
Signed-off-by: Vadim Pasternak <vadimp@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/core_env.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.c b/drivers/net/ethernet/mellanox/mlxsw/core_env.c
index c1c1965d7acc..72539a9a3847 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_env.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.c
@@ -3,6 +3,7 @@
 
 #include <linux/kernel.h>
 #include <linux/err.h>
+#include <linux/sfp.h>
 
 #include "core.h"
 #include "core_env.h"
@@ -162,7 +163,7 @@ int mlxsw_env_get_module_info(struct mlxsw_core *mlxsw_core, int module,
 {
 	u8 module_info[MLXSW_REG_MCIA_EEPROM_MODULE_INFO_SIZE];
 	u16 offset = MLXSW_REG_MCIA_EEPROM_MODULE_INFO_SIZE;
-	u8 module_rev_id, module_id;
+	u8 module_rev_id, module_id, diag_mon;
 	unsigned int read_size;
 	int err;
 
@@ -195,8 +196,21 @@ int mlxsw_env_get_module_info(struct mlxsw_core *mlxsw_core, int module,
 		}
 		break;
 	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_SFP:
+		/* Verify if transceiver provides diagnostic monitoring page */
+		err = mlxsw_env_query_module_eeprom(mlxsw_core, module,
+						    SFP_DIAGMON, 1, &diag_mon,
+						    &read_size);
+		if (err)
+			return err;
+
+		if (read_size < 1)
+			return -EIO;
+
 		modinfo->type       = ETH_MODULE_SFF_8472;
-		modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN;
+		if (diag_mon)
+			modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN;
+		else
+			modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN / 2;
 		break;
 	default:
 		return -EINVAL;
-- 
2.20.1


From 58ffbb0604453d3cd4ebbdaded70c5cda53431d9 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Tue, 14 May 2019 21:18:12 +0100
Subject: [PATCH 16/23] flow_offload: support CVLAN match

[ Upstream commit bae9ed69029c7d499c57485593b2faae475fd704 ]

Plumb it through from the flow_dissector.

Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow_offload.h | 2 ++
 net/core/flow_offload.c    | 7 +++++++
 2 files changed, 9 insertions(+)

diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h
index d035183c8d03..cc32b9d9ecec 100644
--- a/include/net/flow_offload.h
+++ b/include/net/flow_offload.h
@@ -71,6 +71,8 @@ void flow_rule_match_eth_addrs(const struct flow_rule *rule,
 			       struct flow_match_eth_addrs *out);
 void flow_rule_match_vlan(const struct flow_rule *rule,
 			  struct flow_match_vlan *out);
+void flow_rule_match_cvlan(const struct flow_rule *rule,
+			   struct flow_match_vlan *out);
 void flow_rule_match_ipv4_addrs(const struct flow_rule *rule,
 				struct flow_match_ipv4_addrs *out);
 void flow_rule_match_ipv6_addrs(const struct flow_rule *rule,
diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c
index c3a00eac4804..5ce7d47a960e 100644
--- a/net/core/flow_offload.c
+++ b/net/core/flow_offload.c
@@ -54,6 +54,13 @@ void flow_rule_match_vlan(const struct flow_rule *rule,
 }
 EXPORT_SYMBOL(flow_rule_match_vlan);
 
+void flow_rule_match_cvlan(const struct flow_rule *rule,
+			   struct flow_match_vlan *out)
+{
+	FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_CVLAN, out);
+}
+EXPORT_SYMBOL(flow_rule_match_cvlan);
+
 void flow_rule_match_ipv4_addrs(const struct flow_rule *rule,
 				struct flow_match_ipv4_addrs *out)
 {
-- 
2.20.1


From a6a2810df7dbebbf01f3621a3dfe30569f60ff10 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@mellanox.com>
Date: Tue, 14 May 2019 21:18:50 +0100
Subject: [PATCH 17/23] net/mlx5e: Fix calling wrong function to get inner vlan
 key and mask

[ Upstream commit 12d5cbf89a6599f6bbd7b373dba0e74b5bd9c505 ]

When flow_rule_match_XYZ() functions were first introduced,
flow_rule_match_cvlan() for inner vlan is missing.

In mlx5_core driver, to get inner vlan key and mask, flow_rule_match_vlan()
is just called, which is wrong because it obtains outer vlan information by
FLOW_DISSECTOR_KEY_VLAN.

This commit fixes this by changing to call flow_rule_match_cvlan() after
it's added.

Fixes: 8f2566225ae2 ("flow_offload: add flow_rule and flow_match structures and use them")
Signed-off-by: Jianbo Liu <jianbol@mellanox.com>
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index d75dc44eb2ff..4cb23631616b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1561,7 +1561,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CVLAN)) {
 		struct flow_match_vlan match;
 
-		flow_rule_match_vlan(rule, &match);
+		flow_rule_match_cvlan(rule, &match);
 		if (match.mask->vlan_id ||
 		    match.mask->vlan_priority ||
 		    match.mask->vlan_tpid) {
-- 
2.20.1


From 999fb68ecf5cd4319d1bd47e8f86b8191feecad6 Mon Sep 17 00:00:00 2001
From: Bodong Wang <bodong@mellanox.com>
Date: Mon, 29 Apr 2019 09:56:18 -0500
Subject: [PATCH 18/23] net/mlx5: Fix peer pf disable hca command

[ Upstream commit dd06486710d251140edc86ec3bbef0c25dcec1cb ]

The command was mistakenly using enable_hca in embedded CPU field.

Fixes: 22e939a91dcb (net/mlx5: Update enable HCA dependency)
Signed-off-by: Bodong Wang <bodong@mellanox.com>
Reported-by: Alex Rosenbaum <alexr@mellanox.com>
Signed-off-by: Alex Rosenbaum <alexr@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/ecpf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c
index 4746f2d28fb6..0ccd6d40baf7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c
@@ -26,7 +26,7 @@ static int mlx5_peer_pf_disable_hca(struct mlx5_core_dev *dev)
 
 	MLX5_SET(disable_hca_in, in, opcode, MLX5_CMD_OP_DISABLE_HCA);
 	MLX5_SET(disable_hca_in, in, function_id, 0);
-	MLX5_SET(enable_hca_in, in, embedded_cpu_function, 0);
+	MLX5_SET(disable_hca_in, in, embedded_cpu_function, 0);
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 }
 
-- 
2.20.1


From 6c578fb29ae9e3ac032c67e8d25f6dde37168dbd Mon Sep 17 00:00:00 2001
From: "Jorge E. Moreira" <jemoreira@google.com>
Date: Thu, 16 May 2019 13:51:07 -0700
Subject: [PATCH 19/23] vsock/virtio: Initialize core virtio vsock before
 registering the driver

[ Upstream commit ba95e5dfd36647622d8897a2a0470dde60e59ffd ]

Avoid a race in which static variables in net/vmw_vsock/af_vsock.c are
accessed (while handling interrupts) before they are initialized.

[    4.201410] BUG: unable to handle kernel paging request at ffffffffffffffe8
[    4.207829] IP: vsock_addr_equals_addr+0x3/0x20
[    4.211379] PGD 28210067 P4D 28210067 PUD 28212067 PMD 0
[    4.211379] Oops: 0000 [#1] PREEMPT SMP PTI
[    4.211379] Modules linked in:
[    4.211379] CPU: 1 PID: 30 Comm: kworker/1:1 Not tainted 4.14.106-419297-gd7e28cc1f241 #1
[    4.211379] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014
[    4.211379] Workqueue: virtio_vsock virtio_transport_rx_work
[    4.211379] task: ffffa3273d175280 task.stack: ffffaea1800e8000
[    4.211379] RIP: 0010:vsock_addr_equals_addr+0x3/0x20
[    4.211379] RSP: 0000:ffffaea1800ebd28 EFLAGS: 00010286
[    4.211379] RAX: 0000000000000002 RBX: 0000000000000000 RCX: ffffffffb94e42f0
[    4.211379] RDX: 0000000000000400 RSI: ffffffffffffffe0 RDI: ffffaea1800ebdd0
[    4.211379] RBP: ffffaea1800ebd58 R08: 0000000000000001 R09: 0000000000000001
[    4.211379] R10: 0000000000000000 R11: ffffffffb89d5d60 R12: ffffaea1800ebdd0
[    4.211379] R13: 00000000828cbfbf R14: 0000000000000000 R15: ffffaea1800ebdc0
[    4.211379] FS:  0000000000000000(0000) GS:ffffa3273fd00000(0000) knlGS:0000000000000000
[    4.211379] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    4.211379] CR2: ffffffffffffffe8 CR3: 000000002820e001 CR4: 00000000001606e0
[    4.211379] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[    4.211379] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[    4.211379] Call Trace:
[    4.211379]  ? vsock_find_connected_socket+0x6c/0xe0
[    4.211379]  virtio_transport_recv_pkt+0x15f/0x740
[    4.211379]  ? detach_buf+0x1b5/0x210
[    4.211379]  virtio_transport_rx_work+0xb7/0x140
[    4.211379]  process_one_work+0x1ef/0x480
[    4.211379]  worker_thread+0x312/0x460
[    4.211379]  kthread+0x132/0x140
[    4.211379]  ? process_one_work+0x480/0x480
[    4.211379]  ? kthread_destroy_worker+0xd0/0xd0
[    4.211379]  ret_from_fork+0x35/0x40
[    4.211379] Code: c7 47 08 00 00 00 00 66 c7 07 28 00 c7 47 08 ff ff ff ff c7 47 04 ff ff ff ff c3 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 8b 47 08 <3b> 46 08 75 0a 8b 47 04 3b 46 04 0f 94 c0 c3 31 c0 c3 90 66 2e
[    4.211379] RIP: vsock_addr_equals_addr+0x3/0x20 RSP: ffffaea1800ebd28
[    4.211379] CR2: ffffffffffffffe8
[    4.211379] ---[ end trace f31cc4a2e6df3689 ]---
[    4.211379] Kernel panic - not syncing: Fatal exception in interrupt
[    4.211379] Kernel Offset: 0x37000000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff)
[    4.211379] Rebooting in 5 seconds..

Fixes: 22b5c0b63f32 ("vsock/virtio: fix kernel panic after device hot-unplug")
Cc: Stefan Hajnoczi <stefanha@redhat.com>
Cc: Stefano Garzarella <sgarzare@redhat.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: kvm@vger.kernel.org
Cc: virtualization@lists.linux-foundation.org
Cc: netdev@vger.kernel.org
Cc: kernel-team@android.com
Cc: stable@vger.kernel.org [4.9+]
Signed-off-by: Jorge E. Moreira <jemoreira@google.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/vmw_vsock/virtio_transport.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 15eb5d3d4750..96ab344f17bb 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -702,28 +702,27 @@ static int __init virtio_vsock_init(void)
 	if (!virtio_vsock_workqueue)
 		return -ENOMEM;
 
-	ret = register_virtio_driver(&virtio_vsock_driver);
+	ret = vsock_core_init(&virtio_transport.transport);
 	if (ret)
 		goto out_wq;
 
-	ret = vsock_core_init(&virtio_transport.transport);
+	ret = register_virtio_driver(&virtio_vsock_driver);
 	if (ret)
-		goto out_vdr;
+		goto out_vci;
 
 	return 0;
 
-out_vdr:
-	unregister_virtio_driver(&virtio_vsock_driver);
+out_vci:
+	vsock_core_exit();
 out_wq:
 	destroy_workqueue(virtio_vsock_workqueue);
 	return ret;
-
 }
 
 static void __exit virtio_vsock_exit(void)
 {
-	vsock_core_exit();
 	unregister_virtio_driver(&virtio_vsock_driver);
+	vsock_core_exit();
 	destroy_workqueue(virtio_vsock_workqueue);
 }
 
-- 
2.20.1


From aac026e6ad5d476b56a65dcc918313bb0cfdb021 Mon Sep 17 00:00:00 2001
From: Dmytro Linkin <dmitrolin@mellanox.com>
Date: Thu, 25 Apr 2019 08:52:02 +0000
Subject: [PATCH 20/23] net/mlx5e: Add missing ethtool driver info for
 representors

[ Upstream commit cf83c8fdcd4756644595521f48748ec22f7efede ]

For all representors added firmware version info to show in
ethtool driver info.
For uplink representor, because only it is tied to the pci device
sysfs, added pci bus info.

Fixes: ff9b85de5d5d ("net/mlx5e: Add some ethtool port control entries to the uplink rep netdev")
Signed-off-by: Dmytro Linkin <dmitrolin@mellanox.com>
Reviewed-by: Gavi Teitz <gavi@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en_rep.c  | 19 ++++++++++++++++++-
 1 file changed, 18 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index a66b6ed80b30..0b09fa91019d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -65,9 +65,26 @@ static void mlx5e_rep_indr_unregister_block(struct mlx5e_rep_priv *rpriv,
 static void mlx5e_rep_get_drvinfo(struct net_device *dev,
 				  struct ethtool_drvinfo *drvinfo)
 {
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5_core_dev *mdev = priv->mdev;
+
 	strlcpy(drvinfo->driver, mlx5e_rep_driver_name,
 		sizeof(drvinfo->driver));
 	strlcpy(drvinfo->version, UTS_RELEASE, sizeof(drvinfo->version));
+	snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
+		 "%d.%d.%04d (%.16s)",
+		 fw_rev_maj(mdev), fw_rev_min(mdev),
+		 fw_rev_sub(mdev), mdev->board_id);
+}
+
+static void mlx5e_uplink_rep_get_drvinfo(struct net_device *dev,
+					 struct ethtool_drvinfo *drvinfo)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+
+	mlx5e_rep_get_drvinfo(dev, drvinfo);
+	strlcpy(drvinfo->bus_info, pci_name(priv->mdev->pdev),
+		sizeof(drvinfo->bus_info));
 }
 
 static const struct counter_desc sw_rep_stats_desc[] = {
@@ -363,7 +380,7 @@ static const struct ethtool_ops mlx5e_vf_rep_ethtool_ops = {
 };
 
 static const struct ethtool_ops mlx5e_uplink_rep_ethtool_ops = {
-	.get_drvinfo	   = mlx5e_rep_get_drvinfo,
+	.get_drvinfo	   = mlx5e_uplink_rep_get_drvinfo,
 	.get_link	   = ethtool_op_get_link,
 	.get_strings       = mlx5e_rep_get_strings,
 	.get_sset_count    = mlx5e_rep_get_sset_count,
-- 
2.20.1


From b8bd31c96021be4479e8c3fdac94d0c2f2e43e57 Mon Sep 17 00:00:00 2001
From: Dmytro Linkin <dmitrolin@mellanox.com>
Date: Thu, 2 May 2019 15:21:38 +0000
Subject: [PATCH 21/23] net/mlx5e: Additional check for flow destination
 comparison

[ Upstream commit c979c445a88e1c9dd7d8f90838c10456ae4ecd09 ]

Flow destination comparison has an inaccuracy: code see no
difference between same vf ports, which belong to different pfs.

Example: If start ping from VF0 (PF1) to VF1 (PF1) and mirror
all traffic to VF0 (PF2), icmp reply to VF0 (PF1) and mirrored
flow to VF0 (PF2) would be determined as same destination. It lead
to creating flow handler with rule nodes, which not added to node
tree. When later driver try to delete this flow rules we got
kernel crash.

Add comparison of vhca_id field to avoid this.

Fixes: 1228e912c934 ("net/mlx5: Consider encapsulation properties when comparing destinations")
Signed-off-by: Dmytro Linkin <dmitrolin@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 0be3eb86dd84..581cc145795d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -1386,6 +1386,8 @@ static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1,
 		if ((d1->type == MLX5_FLOW_DESTINATION_TYPE_VPORT &&
 		     d1->vport.num == d2->vport.num &&
 		     d1->vport.flags == d2->vport.flags &&
+		     ((d1->vport.flags & MLX5_FLOW_DEST_VPORT_VHCA_ID) ?
+		      (d1->vport.vhca_id == d2->vport.vhca_id) : true) &&
 		     ((d1->vport.flags & MLX5_FLOW_DEST_VPORT_REFORMAT_ID) ?
 		      (d1->vport.reformat_id == d2->vport.reformat_id) : true)) ||
 		    (d1->type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE &&
-- 
2.20.1


From 5f5f179142d84c4f9be44e9d39e1639be269c56d Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Tue, 7 May 2019 13:15:20 -0700
Subject: [PATCH 22/23] net/mlx5: Imply MLXFW in mlx5_core

[ Upstream commit bad861f31bb15a99becef31aab59640eaeb247e2 ]

mlxfw can be compiled as external module while mlx5_core can be
builtin, in such case mlx5 will act like mlxfw is disabled.

Since mlxfw is just a service library for mlx* drivers,
imply it in mlx5_core to make it always reachable if it was enabled.

Fixes: 3ffaabecd1a1 ("net/mlx5e: Support the flash device ethtool callback")
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index 6debffb8336b..430c2eab6fc3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -7,6 +7,7 @@ config MLX5_CORE
 	depends on PCI
 	imply PTP_1588_CLOCK
 	imply VXLAN
+	imply MLXFW
 	default n
 	---help---
 	  Core driver for low level functionality of the ConnectX-4 and
-- 
2.20.1


From 8a6beab900c73f5dd459f6ece83cd33d83bb1134 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Tue, 7 May 2019 12:59:38 -0700
Subject: [PATCH 23/23] net/mlx5e: Fix ethtool rxfh commands when
 CONFIG_MLX5_EN_RXNFC is disabled

[ Upstream commit 8f0916c6dc5cd5e3bc52416fa2a9ff4075080180 ]

ethtool user spaces needs to know ring count via ETHTOOL_GRXRINGS when
executing (ethtool -x) which is retrieved via ethtool get_rxnfc callback,
in mlx5 this callback is disabled when CONFIG_MLX5_EN_RXNFC=n.

This patch allows only ETHTOOL_GRXRINGS command on mlx5e_get_rxnfc() when
CONFIG_MLX5_EN_RXNFC is disabled, so ethtool -x will continue working.

Fixes: fe6d86b3c316 ("net/mlx5e: Add CONFIG_MLX5_EN_RXNFC for ethtool rx nfc")
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../ethernet/mellanox/mlx5/core/en_ethtool.c   | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 78dc8fe2a83c..2821208119c0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1901,6 +1901,22 @@ static int mlx5e_flash_device(struct net_device *dev,
 	return mlx5e_ethtool_flash_device(priv, flash);
 }
 
+#ifndef CONFIG_MLX5_EN_RXNFC
+/* When CONFIG_MLX5_EN_RXNFC=n we only support ETHTOOL_GRXRINGS
+ * otherwise this function will be defined from en_fs_ethtool.c
+ */
+static int mlx5e_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, u32 *rule_locs)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+
+	if (info->cmd != ETHTOOL_GRXRINGS)
+		return -EOPNOTSUPP;
+	/* ring_count is needed by ethtool -x */
+	info->data = priv->channels.params.num_channels;
+	return 0;
+}
+#endif
+
 const struct ethtool_ops mlx5e_ethtool_ops = {
 	.get_drvinfo       = mlx5e_get_drvinfo,
 	.get_link          = ethtool_op_get_link,
@@ -1919,8 +1935,8 @@ const struct ethtool_ops mlx5e_ethtool_ops = {
 	.get_rxfh_indir_size = mlx5e_get_rxfh_indir_size,
 	.get_rxfh          = mlx5e_get_rxfh,
 	.set_rxfh          = mlx5e_set_rxfh,
-#ifdef CONFIG_MLX5_EN_RXNFC
 	.get_rxnfc         = mlx5e_get_rxnfc,
+#ifdef CONFIG_MLX5_EN_RXNFC
 	.set_rxnfc         = mlx5e_set_rxnfc,
 #endif
 	.flash_device      = mlx5e_flash_device,
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Mon, May 20, 2019 at 11:37:45PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v5.0 and v5.1
> -stable, respectively.

All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 106 bytes --]


Please queue up the following networking bug fixes for v4.19 and v5.2
-stable, respectively.

Thank you.

[-- Attachment #2: net_419.mbox --]
[-- Type: Application/Octet-Stream, Size: 44248 bytes --]

From 82d4f9300ae5ee9f26b19ecd3f876c2e6890f19a Mon Sep 17 00:00:00 2001
From: Matteo Croce <mcroce@redhat.com>
Date: Thu, 2 May 2019 10:51:05 +0200
Subject: [PATCH 01/18] cls_matchall: avoid panic when receiving a packet
 before filter set

[ Upstream commit 25426043ec9e22b90c789407c28e40f32a9d1985 ]

When a matchall classifier is added, there is a small time interval in
which tp->root is NULL. If we receive a packet in this small time slice
a NULL pointer dereference will happen, leading to a kernel panic:

    # tc qdisc replace dev eth0 ingress
    # tc filter add dev eth0 parent ffff: matchall action gact drop
    Unable to handle kernel NULL pointer dereference at virtual address 0000000000000034
    Mem abort info:
      ESR = 0x96000005
      Exception class = DABT (current EL), IL = 32 bits
      SET = 0, FnV = 0
      EA = 0, S1PTW = 0
    Data abort info:
      ISV = 0, ISS = 0x00000005
      CM = 0, WnR = 0
    user pgtable: 4k pages, 39-bit VAs, pgdp = 00000000a623d530
    [0000000000000034] pgd=0000000000000000, pud=0000000000000000
    Internal error: Oops: 96000005 [#1] SMP
    Modules linked in: cls_matchall sch_ingress nls_iso8859_1 nls_cp437 vfat fat m25p80 spi_nor mtd xhci_plat_hcd xhci_hcd phy_generic sfp mdio_i2c usbcore i2c_mv64xxx marvell10g mvpp2 usb_common spi_orion mvmdio i2c_core sbsa_gwdt phylink ip_tables x_tables autofs4
    Process ksoftirqd/0 (pid: 9, stack limit = 0x0000000009de7d62)
    CPU: 0 PID: 9 Comm: ksoftirqd/0 Not tainted 5.1.0-rc6 #21
    Hardware name: Marvell 8040 MACCHIATOBin Double-shot (DT)
    pstate: 40000005 (nZcv daif -PAN -UAO)
    pc : mall_classify+0x28/0x78 [cls_matchall]
    lr : tcf_classify+0x78/0x138
    sp : ffffff80109db9d0
    x29: ffffff80109db9d0 x28: ffffffc426058800
    x27: 0000000000000000 x26: ffffffc425b0dd00
    x25: 0000000020000000 x24: 0000000000000000
    x23: ffffff80109dbac0 x22: 0000000000000001
    x21: ffffffc428ab5100 x20: ffffffc425b0dd00
    x19: ffffff80109dbac0 x18: 0000000000000000
    x17: 0000000000000000 x16: 0000000000000000
    x15: 0000000000000000 x14: 0000000000000000
    x13: ffffffbf108ad288 x12: dead000000000200
    x11: 00000000f0000000 x10: 0000000000000001
    x9 : ffffffbf1089a220 x8 : 0000000000000001
    x7 : ffffffbebffaa950 x6 : 0000000000000000
    x5 : 000000442d6ba000 x4 : 0000000000000000
    x3 : ffffff8008735ad8 x2 : ffffff80109dbac0
    x1 : ffffffc425b0dd00 x0 : ffffff8010592078
    Call trace:
     mall_classify+0x28/0x78 [cls_matchall]
     tcf_classify+0x78/0x138
     __netif_receive_skb_core+0x29c/0xa20
     __netif_receive_skb_one_core+0x34/0x60
     __netif_receive_skb+0x28/0x78
     netif_receive_skb_internal+0x2c/0xc0
     napi_gro_receive+0x1a0/0x1d8
     mvpp2_poll+0x928/0xb18 [mvpp2]
     net_rx_action+0x108/0x378
     __do_softirq+0x128/0x320
     run_ksoftirqd+0x44/0x60
     smpboot_thread_fn+0x168/0x1b0
     kthread+0x12c/0x130
     ret_from_fork+0x10/0x1c
    Code: aa0203f3 aa1e03e0 d503201f f9400684 (b9403480)
    ---[ end trace fc71e2ef7b8ab5a5 ]---
    Kernel panic - not syncing: Fatal exception in interrupt
    SMP: stopping secondary CPUs
    Kernel Offset: disabled
    CPU features: 0x002,00002000
    Memory Limit: none
    Rebooting in 1 seconds..

Fix this by adding a NULL check in mall_classify().

Fixes: ed76f5edccc9 ("net: sched: protect filter_chain list with filter_chain_lock mutex")
Signed-off-by: Matteo Croce <mcroce@redhat.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_matchall.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index 621bc1d5b057..570295a8bf7d 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -30,6 +30,9 @@ static int mall_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 {
 	struct cls_mall_head *head = rcu_dereference_bh(tp->root);
 
+	if (unlikely(!head))
+		return -1;
+
 	if (tc_skip_sw(head->flags))
 		return -1;
 
-- 
2.20.1


From ca42ee43e18b9b56ef9055c8ed22d40e9619c982 Mon Sep 17 00:00:00 2001
From: Vivien Didelot <vivien.didelot@gmail.com>
Date: Mon, 3 Jun 2019 16:57:13 -0400
Subject: [PATCH 02/18] ethtool: fix potential userspace buffer overflow

[ Upstream commit 0ee4e76937d69128a6a66861ba393ebdc2ffc8a2 ]

ethtool_get_regs() allocates a buffer of size ops->get_regs_len(),
and pass it to the kernel driver via ops->get_regs() for filling.

There is no restriction about what the kernel drivers can or cannot do
with the open ethtool_regs structure. They usually set regs->version
and ignore regs->len or set it to the same size as ops->get_regs_len().

But if userspace allocates a smaller buffer for the registers dump,
we would cause a userspace buffer overflow in the final copy_to_user()
call, which uses the regs.len value potentially reset by the driver.

To fix this, make this case obvious and store regs.len before calling
ops->get_regs(), to only copy as much data as requested by userspace,
up to the value returned by ops->get_regs_len().

While at it, remove the redundant check for non-null regbuf.

Signed-off-by: Vivien Didelot <vivien.didelot@gmail.com>
Reviewed-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/ethtool.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 7cc97f43f138..da0f3e306f35 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -1434,13 +1434,16 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr)
 			return -ENOMEM;
 	}
 
+	if (regs.len < reglen)
+		reglen = regs.len;
+
 	ops->get_regs(dev, &regs, regbuf);
 
 	ret = -EFAULT;
 	if (copy_to_user(useraddr, &regs, sizeof(regs)))
 		goto out;
 	useraddr += offsetof(struct ethtool_regs, data);
-	if (regbuf && copy_to_user(useraddr, regbuf, regs.len))
+	if (copy_to_user(useraddr, regbuf, reglen))
 		goto out;
 	ret = 0;
 
-- 
2.20.1


From 582e46a255545478a0fd1dffa4922e9b2a58b65a Mon Sep 17 00:00:00 2001
From: Neil Horman <nhorman@tuxdriver.com>
Date: Mon, 3 Jun 2019 16:32:59 -0400
Subject: [PATCH 03/18] Fix memory leak in sctp_process_init

[ Upstream commit 0a8dd9f67cd0da7dc284f48b032ce00db1a68791 ]

syzbot found the following leak in sctp_process_init
BUG: memory leak
unreferenced object 0xffff88810ef68400 (size 1024):
  comm "syz-executor273", pid 7046, jiffies 4294945598 (age 28.770s)
  hex dump (first 32 bytes):
    1d de 28 8d de 0b 1b e3 b5 c2 f9 68 fd 1a 97 25  ..(........h...%
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<00000000a02cebbd>] kmemleak_alloc_recursive include/linux/kmemleak.h:55
[inline]
    [<00000000a02cebbd>] slab_post_alloc_hook mm/slab.h:439 [inline]
    [<00000000a02cebbd>] slab_alloc mm/slab.c:3326 [inline]
    [<00000000a02cebbd>] __do_kmalloc mm/slab.c:3658 [inline]
    [<00000000a02cebbd>] __kmalloc_track_caller+0x15d/0x2c0 mm/slab.c:3675
    [<000000009e6245e6>] kmemdup+0x27/0x60 mm/util.c:119
    [<00000000dfdc5d2d>] kmemdup include/linux/string.h:432 [inline]
    [<00000000dfdc5d2d>] sctp_process_init+0xa7e/0xc20
net/sctp/sm_make_chunk.c:2437
    [<00000000b58b62f8>] sctp_cmd_process_init net/sctp/sm_sideeffect.c:682
[inline]
    [<00000000b58b62f8>] sctp_cmd_interpreter net/sctp/sm_sideeffect.c:1384
[inline]
    [<00000000b58b62f8>] sctp_side_effects net/sctp/sm_sideeffect.c:1194
[inline]
    [<00000000b58b62f8>] sctp_do_sm+0xbdc/0x1d60 net/sctp/sm_sideeffect.c:1165
    [<0000000044e11f96>] sctp_assoc_bh_rcv+0x13c/0x200
net/sctp/associola.c:1074
    [<00000000ec43804d>] sctp_inq_push+0x7f/0xb0 net/sctp/inqueue.c:95
    [<00000000726aa954>] sctp_backlog_rcv+0x5e/0x2a0 net/sctp/input.c:354
    [<00000000d9e249a8>] sk_backlog_rcv include/net/sock.h:950 [inline]
    [<00000000d9e249a8>] __release_sock+0xab/0x110 net/core/sock.c:2418
    [<00000000acae44fa>] release_sock+0x37/0xd0 net/core/sock.c:2934
    [<00000000963cc9ae>] sctp_sendmsg+0x2c0/0x990 net/sctp/socket.c:2122
    [<00000000a7fc7565>] inet_sendmsg+0x64/0x120 net/ipv4/af_inet.c:802
    [<00000000b732cbd3>] sock_sendmsg_nosec net/socket.c:652 [inline]
    [<00000000b732cbd3>] sock_sendmsg+0x54/0x70 net/socket.c:671
    [<00000000274c57ab>] ___sys_sendmsg+0x393/0x3c0 net/socket.c:2292
    [<000000008252aedb>] __sys_sendmsg+0x80/0xf0 net/socket.c:2330
    [<00000000f7bf23d1>] __do_sys_sendmsg net/socket.c:2339 [inline]
    [<00000000f7bf23d1>] __se_sys_sendmsg net/socket.c:2337 [inline]
    [<00000000f7bf23d1>] __x64_sys_sendmsg+0x23/0x30 net/socket.c:2337
    [<00000000a8b4131f>] do_syscall_64+0x76/0x1a0 arch/x86/entry/common.c:3

The problem was that the peer.cookie value points to an skb allocated
area on the first pass through this function, at which point it is
overwritten with a heap allocated value, but in certain cases, where a
COOKIE_ECHO chunk is included in the packet, a second pass through
sctp_process_init is made, where the cookie value is re-allocated,
leaking the first allocation.

Fix is to always allocate the cookie value, and free it when we are done
using it.

Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Reported-by: syzbot+f7e9153b037eac9b1df8@syzkaller.appspotmail.com
CC: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
CC: "David S. Miller" <davem@davemloft.net>
CC: netdev@vger.kernel.org
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sm_make_chunk.c | 13 +++----------
 net/sctp/sm_sideeffect.c |  5 +++++
 2 files changed, 8 insertions(+), 10 deletions(-)

diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index d05c57664e36..ae65a1cfa596 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -2329,7 +2329,6 @@ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk,
 	union sctp_addr addr;
 	struct sctp_af *af;
 	int src_match = 0;
-	char *cookie;
 
 	/* We must include the address that the INIT packet came from.
 	 * This is the only address that matters for an INIT packet.
@@ -2433,14 +2432,6 @@ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk,
 	/* Peer Rwnd   : Current calculated value of the peer's rwnd.  */
 	asoc->peer.rwnd = asoc->peer.i.a_rwnd;
 
-	/* Copy cookie in case we need to resend COOKIE-ECHO. */
-	cookie = asoc->peer.cookie;
-	if (cookie) {
-		asoc->peer.cookie = kmemdup(cookie, asoc->peer.cookie_len, gfp);
-		if (!asoc->peer.cookie)
-			goto clean_up;
-	}
-
 	/* RFC 2960 7.2.1 The initial value of ssthresh MAY be arbitrarily
 	 * high (for example, implementations MAY use the size of the receiver
 	 * advertised window).
@@ -2609,7 +2600,9 @@ static int sctp_process_param(struct sctp_association *asoc,
 	case SCTP_PARAM_STATE_COOKIE:
 		asoc->peer.cookie_len =
 			ntohs(param.p->length) - sizeof(struct sctp_paramhdr);
-		asoc->peer.cookie = param.cookie->body;
+		asoc->peer.cookie = kmemdup(param.cookie->body, asoc->peer.cookie_len, gfp);
+		if (!asoc->peer.cookie)
+			retval = 0;
 		break;
 
 	case SCTP_PARAM_HEARTBEAT_INFO:
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index 48fe8f01265f..3131b4154c74 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -898,6 +898,11 @@ static void sctp_cmd_new_state(struct sctp_cmd_seq *cmds,
 						asoc->rto_initial;
 	}
 
+	if (sctp_state(asoc, ESTABLISHED)) {
+		kfree(asoc->peer.cookie);
+		asoc->peer.cookie = NULL;
+	}
+
 	if (sctp_state(asoc, ESTABLISHED) ||
 	    sctp_state(asoc, CLOSED) ||
 	    sctp_state(asoc, SHUTDOWN_RECEIVED)) {
-- 
2.20.1


From b43f1f9d7f03c735bffca3c391d7cab88ef9f2c6 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 2 Jun 2019 19:10:24 +0800
Subject: [PATCH 04/18] ipv4: not do cache for local delivery if bc_forwarding
 is enabled

[ Upstream commit 0a90478b93a46bdcd56ba33c37566a993e455d54 ]

With the topo:

    h1 ---| rp1            |
          |     route  rp3 |--- h3 (192.168.200.1)
    h2 ---| rp2            |

If rp1 bc_forwarding is set while rp2 bc_forwarding is not, after
doing "ping 192.168.200.255" on h1, then ping 192.168.200.255 on
h2, and the packets can still be forwared.

This issue was caused by the input route cache. It should only do
the cache for either bc forwarding or local delivery. Otherwise,
local delivery can use the route cache for bc forwarding of other
interfaces.

This patch is to fix it by not doing cache for local delivery if
all.bc_forwarding is enabled.

Note that we don't fix it by checking route cache local flag after
rt_cache_valid() in "local_input:" and "ip_mkroute_input", as the
common route code shouldn't be touched for bc_forwarding.

Fixes: 5cbf777cfdf6 ("route: add support for directed broadcast forwarding")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 40bf19f7ae1a..232581c140a0 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1960,7 +1960,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	u32		itag = 0;
 	struct rtable	*rth;
 	struct flowi4	fl4;
-	bool do_cache;
+	bool do_cache = true;
 
 	/* IP on this device is disabled. */
 
@@ -2037,6 +2037,9 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	if (res->type == RTN_BROADCAST) {
 		if (IN_DEV_BFORWARD(in_dev))
 			goto make_route;
+		/* not do cache if bc_forwarding is enabled */
+		if (IPV4_DEVCONF_ALL(net, BC_FORWARDING))
+			do_cache = false;
 		goto brd_input;
 	}
 
@@ -2074,16 +2077,13 @@ out:	return err;
 	RT_CACHE_STAT_INC(in_brd);
 
 local_input:
-	do_cache = false;
-	if (res->fi) {
-		if (!itag) {
-			rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
-			if (rt_cache_valid(rth)) {
-				skb_dst_set_noref(skb, &rth->dst);
-				err = 0;
-				goto out;
-			}
-			do_cache = true;
+	do_cache &= res->fi && !itag;
+	if (do_cache) {
+		rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
+		if (rt_cache_valid(rth)) {
+			skb_dst_set_noref(skb, &rth->dst);
+			err = 0;
+			goto out;
 		}
 	}
 
-- 
2.20.1


From 0623b5816d4d6b2051672f191d202771de0cfd05 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 2 Jun 2019 19:10:46 +0800
Subject: [PATCH 05/18] ipv6: fix the check before getting the cookie in
 rt6_get_cookie

[ Upstream commit b7999b07726c16974ba9ca3bb9fe98ecbec5f81c ]

In Jianlin's testing, netperf was broken with 'Connection reset by peer',
as the cookie check failed in rt6_check() and ip6_dst_check() always
returned NULL.

It's caused by Commit 93531c674315 ("net/ipv6: separate handling of FIB
entries from dst based routes"), where the cookie can be got only when
'c1'(see below) for setting dst_cookie whereas rt6_check() is called
when !'c1' for checking dst_cookie, as we can see in ip6_dst_check().

Since in ip6_dst_check() both rt6_dst_from_check() (c1) and rt6_check()
(!c1) will check the 'from' cookie, this patch is to remove the c1 check
in rt6_get_cookie(), so that the dst_cookie can always be set properly.

c1:
  (rt->rt6i_flags & RTF_PCPU || unlikely(!list_empty(&rt->rt6i_uncached)))

Fixes: 93531c674315 ("net/ipv6: separate handling of FIB entries from dst based routes")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 983f7a1a3f1d..62c936230cc8 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -260,8 +260,7 @@ static inline u32 rt6_get_cookie(const struct rt6_info *rt)
 	rcu_read_lock();
 
 	from = rcu_dereference(rt->from);
-	if (from && (rt->rt6i_flags & RTF_PCPU ||
-	    unlikely(!list_empty(&rt->rt6i_uncached))))
+	if (from)
 		fib6_get_cookie_safe(from, &cookie);
 
 	rcu_read_unlock();
-- 
2.20.1


From c9e9ac2afe1e74fffe2910ce2d0927d8bb35c122 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 1 May 2019 18:18:42 -0700
Subject: [PATCH 06/18] neighbor: Call __ipv4_neigh_lookup_noref in neigh_xmit

[ Upstream commit 4b2a2bfeb3f056461a90bd621e8bd7d03fa47f60 ]

Commit cd9ff4de0107 changed the key for IFF_POINTOPOINT devices to
INADDR_ANY but neigh_xmit which is used for MPLS encapsulations was not
updated to use the altered key. The result is that every packet Tx does
a lookup on the gateway address which does not find an entry, a new one
is created only to find the existing one in the table right before the
insert since arp_constructor was updated to reset the primary key. This
is seen in the allocs and destroys counters:
    ip -s -4 ntable show | head -10 | grep alloc

which increase for each packet showing the unnecessary overhread.

Fix by having neigh_xmit use __ipv4_neigh_lookup_noref for NEIGH_ARP_TABLE.

Fixes: cd9ff4de0107 ("ipv4: Make neigh lookup keys for loopback/point-to-point devices be INADDR_ANY")
Reported-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Tested-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 4e07824eec5e..4e4ac77c6816 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -30,6 +30,7 @@
 #include <linux/times.h>
 #include <net/net_namespace.h>
 #include <net/neighbour.h>
+#include <net/arp.h>
 #include <net/dst.h>
 #include <net/sock.h>
 #include <net/netevent.h>
@@ -2536,7 +2537,13 @@ int neigh_xmit(int index, struct net_device *dev,
 		if (!tbl)
 			goto out;
 		rcu_read_lock_bh();
-		neigh = __neigh_lookup_noref(tbl, addr, dev);
+		if (index == NEIGH_ARP_TABLE) {
+			u32 key = *((u32 *)addr);
+
+			neigh = __ipv4_neigh_lookup_noref(dev, key);
+		} else {
+			neigh = __neigh_lookup_noref(tbl, addr, dev);
+		}
 		if (!neigh)
 			neigh = __neigh_create(tbl, addr, dev, false);
 		err = PTR_ERR(neigh);
-- 
2.20.1


From 8a135e771fe55991e9382f3856e2930a15167b35 Mon Sep 17 00:00:00 2001
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Fri, 31 May 2019 16:47:25 +0300
Subject: [PATCH 07/18] net: ethernet: ti: cpsw_ethtool: fix ethtool ring param
 set

[ Upstream commit 09faf5a7d7c0bcb07faba072f611937af9dd5788 ]

Fix ability to set RX descriptor number, the reason - initially
"tx_max_pending" was set incorrectly, but the issue appears after
adding sanity check, so fix is for "sanity" patch.

Fixes: 37e2d99b59c476 ("ethtool: Ensure new ring parameters are within bounds during SRINGPARAM")
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 832bce07c385..1afed85550c0 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -2978,7 +2978,7 @@ static void cpsw_get_ringparam(struct net_device *ndev,
 	struct cpsw_common *cpsw = priv->cpsw;
 
 	/* not supported */
-	ering->tx_max_pending = 0;
+	ering->tx_max_pending = descs_pool_size - CPSW_MAX_QUEUES;
 	ering->tx_pending = cpdma_get_num_tx_descs(cpsw->dma);
 	ering->rx_max_pending = descs_pool_size - CPSW_MAX_QUEUES;
 	ering->rx_pending = cpdma_get_num_rx_descs(cpsw->dma);
-- 
2.20.1


From 1167570e1c8b297270fc86d8ff1453d09aee6291 Mon Sep 17 00:00:00 2001
From: Erez Alfasi <ereza@mellanox.com>
Date: Mon, 20 May 2019 17:42:52 +0300
Subject: [PATCH 08/18] net/mlx4_en: ethtool, Remove unsupported SFP EEPROM
 high pages query

[ Upstream commit 135dd9594f127c8a82d141c3c8430e9e2143216a ]

Querying EEPROM high pages data for SFP module is currently
not supported by our driver but is still tried, resulting in
invalid FW queries.

Set the EEPROM ethtool data length to 256 for SFP module to
limit the reading for page 0 only and prevent invalid FW queries.

Fixes: 7202da8b7f71 ("ethtool, net/mlx4_en: Cable info, get_module_info/eeprom ethtool support")
Signed-off-by: Erez Alfasi <ereza@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 4 +++-
 drivers/net/ethernet/mellanox/mlx4/port.c       | 5 -----
 2 files changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index d290f0787dfb..94c59939a8cf 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -2010,6 +2010,8 @@ static int mlx4_en_set_tunable(struct net_device *dev,
 	return ret;
 }
 
+#define MLX4_EEPROM_PAGE_LEN 256
+
 static int mlx4_en_get_module_info(struct net_device *dev,
 				   struct ethtool_modinfo *modinfo)
 {
@@ -2044,7 +2046,7 @@ static int mlx4_en_get_module_info(struct net_device *dev,
 		break;
 	case MLX4_MODULE_ID_SFP:
 		modinfo->type = ETH_MODULE_SFF_8472;
-		modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN;
+		modinfo->eeprom_len = MLX4_EEPROM_PAGE_LEN;
 		break;
 	default:
 		return -EINVAL;
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index 10fcc22f4590..ba6ac31a339d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -2077,11 +2077,6 @@ int mlx4_get_module_info(struct mlx4_dev *dev, u8 port,
 		size -= offset + size - I2C_PAGE_SIZE;
 
 	i2c_addr = I2C_ADDR_LOW;
-	if (offset >= I2C_PAGE_SIZE) {
-		/* Reset offset to high page */
-		i2c_addr = I2C_ADDR_HIGH;
-		offset -= I2C_PAGE_SIZE;
-	}
 
 	cable_info = (struct mlx4_cable_info *)inmad->data;
 	cable_info->dev_mem_address = cpu_to_be16(offset);
-- 
2.20.1


From 0459f0e5301210c10af64470a51fe884e9b39a6a Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 6 Jun 2019 10:42:56 +0200
Subject: [PATCH 09/18] net: mvpp2: Use strscpy to handle stat strings

[ Upstream commit d37acd5aa99c57505b64913e0e2624ec3daed8c5 ]

Use a safe strscpy call to copy the ethtool stat strings into the
relevant buffers, instead of a memcpy that will be accessing
out-of-bound data.

Fixes: 118d6298f6f0 ("net: mvpp2: add ethtool GOP statistics")
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 59212d3d9587..df5b74f289e1 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -1310,8 +1310,8 @@ static void mvpp2_ethtool_get_strings(struct net_device *netdev, u32 sset,
 		int i;
 
 		for (i = 0; i < ARRAY_SIZE(mvpp2_ethtool_regs); i++)
-			memcpy(data + i * ETH_GSTRING_LEN,
-			       &mvpp2_ethtool_regs[i].string, ETH_GSTRING_LEN);
+			strscpy(data + i * ETH_GSTRING_LEN,
+			        mvpp2_ethtool_regs[i].string, ETH_GSTRING_LEN);
 	}
 }
 
-- 
2.20.1


From c8922c8950474cb6a95b632e6d520f835e03432b Mon Sep 17 00:00:00 2001
From: Zhu Yanjun <yanjun.zhu@oracle.com>
Date: Thu, 6 Jun 2019 04:00:03 -0400
Subject: [PATCH 10/18] net: rds: fix memory leak in rds_ib_flush_mr_pool

[ Upstream commit 85cb928787eab6a2f4ca9d2a798b6f3bed53ced1 ]

When the following tests last for several hours, the problem will occur.

Server:
    rds-stress -r 1.1.1.16 -D 1M
Client:
    rds-stress -r 1.1.1.14 -s 1.1.1.16 -D 1M -T 30

The following will occur.

"
Starting up....
tsks   tx/s   rx/s  tx+rx K/s    mbi K/s    mbo K/s tx us/c   rtt us cpu
%
  1      0      0       0.00       0.00       0.00    0.00 0.00 -1.00
  1      0      0       0.00       0.00       0.00    0.00 0.00 -1.00
  1      0      0       0.00       0.00       0.00    0.00 0.00 -1.00
  1      0      0       0.00       0.00       0.00    0.00 0.00 -1.00
"
>From vmcore, we can find that clean_list is NULL.

>From the source code, rds_mr_flushd calls rds_ib_mr_pool_flush_worker.
Then rds_ib_mr_pool_flush_worker calls
"
 rds_ib_flush_mr_pool(pool, 0, NULL);
"
Then in function
"
int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *pool,
                         int free_all, struct rds_ib_mr **ibmr_ret)
"
ibmr_ret is NULL.

In the source code,
"
...
list_to_llist_nodes(pool, &unmap_list, &clean_nodes, &clean_tail);
if (ibmr_ret)
        *ibmr_ret = llist_entry(clean_nodes, struct rds_ib_mr, llnode);

/* more than one entry in llist nodes */
if (clean_nodes->next)
        llist_add_batch(clean_nodes->next, clean_tail, &pool->clean_list);
...
"
When ibmr_ret is NULL, llist_entry is not executed. clean_nodes->next
instead of clean_nodes is added in clean_list.
So clean_nodes is discarded. It can not be used again.
The workqueue is executed periodically. So more and more clean_nodes are
discarded. Finally the clean_list is NULL.
Then this problem will occur.

Fixes: 1bc144b62524 ("net, rds, Replace xlist in net/rds/xlist.h with llist")
Signed-off-by: Zhu Yanjun <yanjun.zhu@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/ib_rdma.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c
index d664e9ade74d..0b347f46b2f4 100644
--- a/net/rds/ib_rdma.c
+++ b/net/rds/ib_rdma.c
@@ -428,12 +428,14 @@ int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *pool,
 		wait_clean_list_grace();
 
 		list_to_llist_nodes(pool, &unmap_list, &clean_nodes, &clean_tail);
-		if (ibmr_ret)
+		if (ibmr_ret) {
 			*ibmr_ret = llist_entry(clean_nodes, struct rds_ib_mr, llnode);
-
+			clean_nodes = clean_nodes->next;
+		}
 		/* more than one entry in llist nodes */
-		if (clean_nodes->next)
-			llist_add_batch(clean_nodes->next, clean_tail, &pool->clean_list);
+		if (clean_nodes)
+			llist_add_batch(clean_nodes, clean_tail,
+					&pool->clean_list);
 
 	}
 
-- 
2.20.1


From 17af69d2a8f68ec4e82ca0f1910bd048f1a3444b Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Sun, 2 Jun 2019 15:13:00 +0100
Subject: [PATCH 11/18] net: sfp: read eeprom in maximum 16 byte increments

[ Upstream commit 28e74a7cfd6403f0d1c0f8b10b45d6fae37b227e ]

Some SFP modules do not like reads longer than 16 bytes, so read the
EEPROM in chunks of 16 bytes at a time.  This behaviour is not specified
in the SFP MSAs, which specifies:

 "The serial interface uses the 2-wire serial CMOS E2PROM protocol
  defined for the ATMEL AT24C01A/02/04 family of components."

and

 "As long as the SFP+ receives an acknowledge, it shall serially clock
  out sequential data words. The sequence is terminated when the host
  responds with a NACK and a STOP instead of an acknowledge."

We must avoid breaking a read across a 16-bit quantity in the diagnostic
page, thankfully all 16-bit quantities in that page are naturally
aligned.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/sfp.c | 24 ++++++++++++++++++++----
 1 file changed, 20 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index 68c8fbf099f8..8807a806cc47 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -280,6 +280,7 @@ static int sfp_i2c_read(struct sfp *sfp, bool a2, u8 dev_addr, void *buf,
 {
 	struct i2c_msg msgs[2];
 	u8 bus_addr = a2 ? 0x51 : 0x50;
+	size_t this_len;
 	int ret;
 
 	msgs[0].addr = bus_addr;
@@ -291,11 +292,26 @@ static int sfp_i2c_read(struct sfp *sfp, bool a2, u8 dev_addr, void *buf,
 	msgs[1].len = len;
 	msgs[1].buf = buf;
 
-	ret = i2c_transfer(sfp->i2c, msgs, ARRAY_SIZE(msgs));
-	if (ret < 0)
-		return ret;
+	while (len) {
+		this_len = len;
+		if (this_len > 16)
+			this_len = 16;
 
-	return ret == ARRAY_SIZE(msgs) ? len : 0;
+		msgs[1].len = this_len;
+
+		ret = i2c_transfer(sfp->i2c, msgs, ARRAY_SIZE(msgs));
+		if (ret < 0)
+			return ret;
+
+		if (ret != ARRAY_SIZE(msgs))
+			break;
+
+		msgs[1].buf += this_len;
+		dev_addr += this_len;
+		len -= this_len;
+	}
+
+	return msgs[1].buf - (u8 *)buf;
 }
 
 static int sfp_i2c_write(struct sfp *sfp, bool a2, u8 dev_addr, void *buf,
-- 
2.20.1


From 1935d84d453d1393880a2086302e3ae3e15e900a Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 4 Jun 2019 12:00:12 -0700
Subject: [PATCH 12/18] net/tls: replace the sleeping lock around RX resync
 with a bit lock

[ Upstream commit e52972c11d6b1262964db96d65934196db621685 ]

Commit 38030d7cb779 ("net/tls: avoid NULL-deref on resync during device removal")
tried to fix a potential NULL-dereference by taking the
context rwsem.  Unfortunately the RX resync may get called
from soft IRQ, so we can't use the rwsem to protect from
the device disappearing.  Because we are guaranteed there
can be only one resync at a time (it's called from strparser)
use a bit to indicate resync is busy and make device
removal wait for the bit to get cleared.

Note that there is a leftover "flags" field in struct
tls_context already.

Fixes: 4799ac81e52a ("tls: Add rx inline crypto offload")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h    |  4 ++++
 net/tls/tls_device.c | 27 +++++++++++++++++++++------
 2 files changed, 25 insertions(+), 6 deletions(-)

diff --git a/include/net/tls.h b/include/net/tls.h
index c423b7d0b6ab..954110575891 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -161,6 +161,10 @@ enum {
 	TLS_PENDING_CLOSED_RECORD
 };
 
+enum tls_context_flags {
+	TLS_RX_SYNC_RUNNING = 0,
+};
+
 struct cipher_context {
 	u16 prepend_size;
 	u16 tag_size;
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 8035bf495eb2..ead29c2aefa7 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -545,10 +545,22 @@ static int tls_device_push_pending_record(struct sock *sk, int flags)
 	return tls_push_data(sk, &msg_iter, 0, flags, TLS_RECORD_TYPE_DATA);
 }
 
+static void tls_device_resync_rx(struct tls_context *tls_ctx,
+				 struct sock *sk, u32 seq, u64 rcd_sn)
+{
+	struct net_device *netdev;
+
+	if (WARN_ON(test_and_set_bit(TLS_RX_SYNC_RUNNING, &tls_ctx->flags)))
+		return;
+	netdev = READ_ONCE(tls_ctx->netdev);
+	if (netdev)
+		netdev->tlsdev_ops->tls_dev_resync_rx(netdev, sk, seq, rcd_sn);
+	clear_bit_unlock(TLS_RX_SYNC_RUNNING, &tls_ctx->flags);
+}
+
 void handle_device_resync(struct sock *sk, u32 seq, u64 rcd_sn)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
-	struct net_device *netdev = tls_ctx->netdev;
 	struct tls_offload_context_rx *rx_ctx;
 	u32 is_req_pending;
 	s64 resync_req;
@@ -563,10 +575,10 @@ void handle_device_resync(struct sock *sk, u32 seq, u64 rcd_sn)
 	is_req_pending = resync_req;
 
 	if (unlikely(is_req_pending) && req_seq == seq &&
-	    atomic64_try_cmpxchg(&rx_ctx->resync_req, &resync_req, 0))
-		netdev->tlsdev_ops->tls_dev_resync_rx(netdev, sk,
-						      seq + TLS_HEADER_SIZE - 1,
-						      rcd_sn);
+	    atomic64_try_cmpxchg(&rx_ctx->resync_req, &resync_req, 0)) {
+		seq += TLS_HEADER_SIZE - 1;
+		tls_device_resync_rx(tls_ctx, sk, seq, rcd_sn);
+	}
 }
 
 static int tls_device_reencrypt(struct sock *sk, struct sk_buff *skb)
@@ -954,7 +966,10 @@ static int tls_device_down(struct net_device *netdev)
 		if (ctx->rx_conf == TLS_HW)
 			netdev->tlsdev_ops->tls_dev_del(netdev, ctx,
 							TLS_OFFLOAD_CTX_DIR_RX);
-		ctx->netdev = NULL;
+		WRITE_ONCE(ctx->netdev, NULL);
+		smp_mb__before_atomic(); /* pairs with test_and_set_bit() */
+		while (test_bit(TLS_RX_SYNC_RUNNING, &ctx->flags))
+			usleep_range(10, 200);
 		dev_put(netdev);
 		list_del_init(&ctx->list);
 
-- 
2.20.1


From 93ae2770994ed53c24c09f29ea1145ac30f0fd7b Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 31 May 2019 12:37:23 -0400
Subject: [PATCH 13/18] packet: unconditionally free po->rollover

[ Upstream commit afa0925c6fcc6a8f610e996ca09bc3215048033c ]

Rollover used to use a complex RCU mechanism for assignment, which had
a race condition. The below patch fixed the bug and greatly simplified
the logic.

The feature depends on fanout, but the state is private to the socket.
Fanout_release returns f only when the last member leaves and the
fanout struct is to be freed.

Destroy rollover unconditionally, regardless of fanout state.

Fixes: 57f015f5eccf2 ("packet: fix crash in fanout_demux_rollover()")
Reported-by: syzbot <syzkaller@googlegroups.com>
Diagnosed-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 18df3bce73da..d98fcf926166 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3017,8 +3017,8 @@ static int packet_release(struct socket *sock)
 
 	synchronize_net();
 
+	kfree(po->rollover);
 	if (f) {
-		kfree(po->rollover);
 		fanout_release_data(f);
 		kfree(f);
 	}
-- 
2.20.1


From b12e777b6eeb724819a5b1f30d638f7268e35776 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 6 Jun 2019 15:45:03 +0200
Subject: [PATCH 14/18] pktgen: do not sleep with the thread lock held.

[ Upstream commit 720f1de4021f09898b8c8443f3b3e995991b6e3a ]

Currently, the process issuing a "start" command on the pktgen procfs
interface, acquires the pktgen thread lock and never release it, until
all pktgen threads are completed. The above can blocks indefinitely any
other pktgen command and any (even unrelated) netdevice removal - as
the pktgen netdev notifier acquires the same lock.

The issue is demonstrated by the following script, reported by Matteo:

ip -b - <<'EOF'
	link add type dummy
	link add type veth
	link set dummy0 up
EOF
modprobe pktgen
echo reset >/proc/net/pktgen/pgctrl
{
	echo rem_device_all
	echo add_device dummy0
} >/proc/net/pktgen/kpktgend_0
echo count 0 >/proc/net/pktgen/dummy0
echo start >/proc/net/pktgen/pgctrl &
sleep 1
rmmod veth

Fix the above releasing the thread lock around the sleep call.

Additionally we must prevent racing with forcefull rmmod - as the
thread lock no more protects from them. Instead, acquire a self-reference
before waiting for any thread. As a side effect, running

rmmod pktgen

while some thread is running now fails with "module in use" error,
before this patch such command hanged indefinitely.

Note: the issue predates the commit reported in the fixes tag, but
this fix can't be applied before the mentioned commit.

v1 -> v2:
 - no need to check for thread existence after flipping the lock,
   pktgen threads are freed only at net exit time
 -

Fixes: 6146e6a43b35 ("[PKTGEN]: Removes thread_{un,}lock() macros.")
Reported-and-tested-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/pktgen.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 7f6938405fa1..092fa3d75b32 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -3065,7 +3065,13 @@ static int pktgen_wait_thread_run(struct pktgen_thread *t)
 {
 	while (thread_is_running(t)) {
 
+		/* note: 't' will still be around even after the unlock/lock
+		 * cycle because pktgen_thread threads are only cleared at
+		 * net exit
+		 */
+		mutex_unlock(&pktgen_thread_lock);
 		msleep_interruptible(100);
+		mutex_lock(&pktgen_thread_lock);
 
 		if (signal_pending(current))
 			goto signal;
@@ -3080,6 +3086,10 @@ static int pktgen_wait_all_threads_run(struct pktgen_net *pn)
 	struct pktgen_thread *t;
 	int sig = 1;
 
+	/* prevent from racing with rmmod */
+	if (!try_module_get(THIS_MODULE))
+		return sig;
+
 	mutex_lock(&pktgen_thread_lock);
 
 	list_for_each_entry(t, &pn->pktgen_threads, th_list) {
@@ -3093,6 +3103,7 @@ static int pktgen_wait_all_threads_run(struct pktgen_net *pn)
 			t->control |= (T_STOP);
 
 	mutex_unlock(&pktgen_thread_lock);
+	module_put(THIS_MODULE);
 	return sig;
 }
 
-- 
2.20.1


From c7f13a67459810408a8ac4c3270c242c25f8ab30 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Wed, 5 Jun 2019 12:27:14 +0800
Subject: [PATCH 15/18] Revert "fib_rules: return 0 directly if an exactly same
 rule exists when NLM_F_EXCL not supplied"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 4970b42d5c362bf873982db7d93245c5281e58f4 ]

This reverts commit e9919a24d3022f72bcadc407e73a6ef17093a849.

Nathan reported the new behaviour breaks Android, as Android just add
new rules and delete old ones.

If we return 0 without adding dup rules, Android will remove the new
added rules and causing system to soft-reboot.

Fixes: e9919a24d302 ("fib_rules: return 0 directly if an exactly same rule exists when NLM_F_EXCL not supplied")
Reported-by: Nathan Chancellor <natechancellor@gmail.com>
Reported-by: Yaro Slav <yaro330@gmail.com>
Reported-by: Maciej Żenczykowski <zenczykowski@gmail.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Nathan Chancellor <natechancellor@gmail.com>
Tested-by: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/fib_rules.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 338147b14d0e..0ff3953f64aa 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -756,9 +756,9 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (err)
 		goto errout;
 
-	if (rule_exists(ops, frh, tb, rule)) {
-		if (nlh->nlmsg_flags & NLM_F_EXCL)
-			err = -EEXIST;
+	if ((nlh->nlmsg_flags & NLM_F_EXCL) &&
+	    rule_exists(ops, frh, tb, rule)) {
+		err = -EEXIST;
 		goto errout_free;
 	}
 
-- 
2.20.1


From f798ffaa710b48a4411e7a3a0dea4745652aa657 Mon Sep 17 00:00:00 2001
From: James Clarke <jrtc27@jrtc27.com>
Date: Wed, 29 May 2019 22:31:31 +0100
Subject: [PATCH 16/18] sparc64: Fix regression in non-hypervisor TLB flush
 xcall

[ Upstream commit d3c976c14ad8af421134c428b0a89ff8dd3bd8f8 ]

Previously, %g2 would end up with the value PAGE_SIZE, but after the
commit mentioned below it ends up with the value 1 due to being reused
for a different purpose. We need it to be PAGE_SIZE as we use it to step
through pages in our demap loop, otherwise we set different flags in the
low 12 bits of the address written to, thereby doing things other than a
nucleus page flush.

Fixes: a74ad5e660a9 ("sparc64: Handle extremely large kernel TLB range flushes more gracefully.")
Reported-by: Meelis Roos <mroos@linux.ee>
Tested-by: Meelis Roos <mroos@linux.ee>
Signed-off-by: James Clarke <jrtc27@jrtc27.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/sparc/mm/ultra.S | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/sparc/mm/ultra.S b/arch/sparc/mm/ultra.S
index d245f89d1395..d220b6848746 100644
--- a/arch/sparc/mm/ultra.S
+++ b/arch/sparc/mm/ultra.S
@@ -587,7 +587,7 @@ xcall_flush_tlb_kernel_range:	/* 44 insns */
 	sub		%g7, %g1, %g3
 	srlx		%g3, 18, %g2
 	brnz,pn		%g2, 2f
-	 add		%g2, 1, %g2
+	 sethi		%hi(PAGE_SIZE), %g2
 	sub		%g3, %g2, %g3
 	or		%g1, 0x20, %g1		! Nucleus
 1:	stxa		%g0, [%g1 + %g3] ASI_DMMU_DEMAP
@@ -751,7 +751,7 @@ __cheetah_xcall_flush_tlb_kernel_range:	/* 44 insns */
 	sub		%g7, %g1, %g3
 	srlx		%g3, 18, %g2
 	brnz,pn		%g2, 2f
-	 add		%g2, 1, %g2
+	 sethi		%hi(PAGE_SIZE), %g2
 	sub		%g3, %g2, %g3
 	or		%g1, 0x20, %g1		! Nucleus
 1:	stxa		%g0, [%g1 + %g3] ASI_DMMU_DEMAP
-- 
2.20.1


From 675a24dc3ed1e69f3b1be373a4bf9c6b597a014c Mon Sep 17 00:00:00 2001
From: Olivier Matz <olivier.matz@6wind.com>
Date: Thu, 6 Jun 2019 09:15:18 +0200
Subject: [PATCH 17/18] ipv6: use READ_ONCE() for inet->hdrincl as in ipv4

[ Upstream commit 59e3e4b52663a9d97efbce7307f62e4bc5c9ce91 ]

As it was done in commit 8f659a03a0ba ("net: ipv4: fix for a race
condition in raw_sendmsg") and commit 20b50d79974e ("net: ipv4: emulate
READ_ONCE() on ->hdrincl bit-field in raw_sendmsg()") for ipv4, copy the
value of inet->hdrincl in a local variable, to avoid introducing a race
condition in the next commit.

Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/raw.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 5833d4af7311..2133f26a2185 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -782,6 +782,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	struct flowi6 fl6;
 	struct ipcm6_cookie ipc6;
 	int addr_len = msg->msg_namelen;
+	int hdrincl;
 	u16 proto;
 	int err;
 
@@ -795,6 +796,13 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	if (msg->msg_flags & MSG_OOB)
 		return -EOPNOTSUPP;
 
+	/* hdrincl should be READ_ONCE(inet->hdrincl)
+	 * but READ_ONCE() doesn't work with bit fields.
+	 * Doing this indirectly yields the same result.
+	 */
+	hdrincl = inet->hdrincl;
+	hdrincl = READ_ONCE(hdrincl);
+
 	/*
 	 *	Get and verify the address.
 	 */
@@ -907,7 +915,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		fl6.flowi6_oif = np->ucast_oif;
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
-	if (inet->hdrincl)
+	if (hdrincl)
 		fl6.flowi6_flags |= FLOWI_FLAG_KNOWN_NH;
 
 	if (ipc6.tclass < 0)
@@ -930,7 +938,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		goto do_confirm;
 
 back_from_confirm:
-	if (inet->hdrincl)
+	if (hdrincl)
 		err = rawv6_send_hdrinc(sk, msg, len, &fl6, &dst,
 					msg->msg_flags, &ipc6.sockc);
 	else {
-- 
2.20.1


From dce1d94b2d223f85c26740be862e3709226087a2 Mon Sep 17 00:00:00 2001
From: Olivier Matz <olivier.matz@6wind.com>
Date: Thu, 6 Jun 2019 09:15:19 +0200
Subject: [PATCH 18/18] ipv6: fix EFAULT on sendto with icmpv6 and hdrincl

[ Upstream commit b9aa52c4cb457e7416cc0c95f475e72ef4a61336 ]

The following code returns EFAULT (Bad address):

  s = socket(AF_INET6, SOCK_RAW, IPPROTO_ICMPV6);
  setsockopt(s, SOL_IPV6, IPV6_HDRINCL, 1);
  sendto(ipv6_icmp6_packet, addr);   /* returns -1, errno = EFAULT */

The IPv4 equivalent code works. A workaround is to use IPPROTO_RAW
instead of IPPROTO_ICMPV6.

The failure happens because 2 bytes are eaten from the msghdr by
rawv6_probe_proto_opt() starting from commit 19e3c66b52ca ("ipv6
equivalent of "ipv4: Avoid reading user iov twice after
raw_probe_proto_opt""), but at that time it was not a problem because
IPV6_HDRINCL was not yet introduced.

Only eat these 2 bytes if hdrincl == 0.

Fixes: 715f504b1189 ("ipv6: add IPV6_HDRINCL option for raw sockets")
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/raw.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 2133f26a2185..4856d9320b28 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -894,11 +894,14 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	opt = ipv6_fixup_options(&opt_space, opt);
 
 	fl6.flowi6_proto = proto;
-	rfv.msg = msg;
-	rfv.hlen = 0;
-	err = rawv6_probe_proto_opt(&rfv, &fl6);
-	if (err)
-		goto out;
+
+	if (!hdrincl) {
+		rfv.msg = msg;
+		rfv.hlen = 0;
+		err = rawv6_probe_proto_opt(&rfv, &fl6);
+		if (err)
+			goto out;
+	}
 
 	if (!ipv6_addr_any(daddr))
 		fl6.daddr = *daddr;
-- 
2.20.1


[-- Attachment #3: net_51.mbox --]
[-- Type: Application/Octet-Stream, Size: 52487 bytes --]

From 9b3fc6e94ffec92079f705fa63b927d5078ae238 Mon Sep 17 00:00:00 2001
From: Vivien Didelot <vivien.didelot@gmail.com>
Date: Mon, 3 Jun 2019 16:57:13 -0400
Subject: [PATCH 01/22] ethtool: fix potential userspace buffer overflow

[ Upstream commit 0ee4e76937d69128a6a66861ba393ebdc2ffc8a2 ]

ethtool_get_regs() allocates a buffer of size ops->get_regs_len(),
and pass it to the kernel driver via ops->get_regs() for filling.

There is no restriction about what the kernel drivers can or cannot do
with the open ethtool_regs structure. They usually set regs->version
and ignore regs->len or set it to the same size as ops->get_regs_len().

But if userspace allocates a smaller buffer for the registers dump,
we would cause a userspace buffer overflow in the final copy_to_user()
call, which uses the regs.len value potentially reset by the driver.

To fix this, make this case obvious and store regs.len before calling
ops->get_regs(), to only copy as much data as requested by userspace,
up to the value returned by ops->get_regs_len().

While at it, remove the redundant check for non-null regbuf.

Signed-off-by: Vivien Didelot <vivien.didelot@gmail.com>
Reviewed-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/ethtool.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 014dcd63b451..7285a19bb135 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -1358,13 +1358,16 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr)
 	if (!regbuf)
 		return -ENOMEM;
 
+	if (regs.len < reglen)
+		reglen = regs.len;
+
 	ops->get_regs(dev, &regs, regbuf);
 
 	ret = -EFAULT;
 	if (copy_to_user(useraddr, &regs, sizeof(regs)))
 		goto out;
 	useraddr += offsetof(struct ethtool_regs, data);
-	if (regbuf && copy_to_user(useraddr, regbuf, regs.len))
+	if (copy_to_user(useraddr, regbuf, reglen))
 		goto out;
 	ret = 0;
 
-- 
2.20.1


From 2861f1f83bbf12223bfe2138854b3958131e222f Mon Sep 17 00:00:00 2001
From: Neil Horman <nhorman@tuxdriver.com>
Date: Mon, 3 Jun 2019 16:32:59 -0400
Subject: [PATCH 02/22] Fix memory leak in sctp_process_init

[ Upstream commit 0a8dd9f67cd0da7dc284f48b032ce00db1a68791 ]

syzbot found the following leak in sctp_process_init
BUG: memory leak
unreferenced object 0xffff88810ef68400 (size 1024):
  comm "syz-executor273", pid 7046, jiffies 4294945598 (age 28.770s)
  hex dump (first 32 bytes):
    1d de 28 8d de 0b 1b e3 b5 c2 f9 68 fd 1a 97 25  ..(........h...%
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<00000000a02cebbd>] kmemleak_alloc_recursive include/linux/kmemleak.h:55
[inline]
    [<00000000a02cebbd>] slab_post_alloc_hook mm/slab.h:439 [inline]
    [<00000000a02cebbd>] slab_alloc mm/slab.c:3326 [inline]
    [<00000000a02cebbd>] __do_kmalloc mm/slab.c:3658 [inline]
    [<00000000a02cebbd>] __kmalloc_track_caller+0x15d/0x2c0 mm/slab.c:3675
    [<000000009e6245e6>] kmemdup+0x27/0x60 mm/util.c:119
    [<00000000dfdc5d2d>] kmemdup include/linux/string.h:432 [inline]
    [<00000000dfdc5d2d>] sctp_process_init+0xa7e/0xc20
net/sctp/sm_make_chunk.c:2437
    [<00000000b58b62f8>] sctp_cmd_process_init net/sctp/sm_sideeffect.c:682
[inline]
    [<00000000b58b62f8>] sctp_cmd_interpreter net/sctp/sm_sideeffect.c:1384
[inline]
    [<00000000b58b62f8>] sctp_side_effects net/sctp/sm_sideeffect.c:1194
[inline]
    [<00000000b58b62f8>] sctp_do_sm+0xbdc/0x1d60 net/sctp/sm_sideeffect.c:1165
    [<0000000044e11f96>] sctp_assoc_bh_rcv+0x13c/0x200
net/sctp/associola.c:1074
    [<00000000ec43804d>] sctp_inq_push+0x7f/0xb0 net/sctp/inqueue.c:95
    [<00000000726aa954>] sctp_backlog_rcv+0x5e/0x2a0 net/sctp/input.c:354
    [<00000000d9e249a8>] sk_backlog_rcv include/net/sock.h:950 [inline]
    [<00000000d9e249a8>] __release_sock+0xab/0x110 net/core/sock.c:2418
    [<00000000acae44fa>] release_sock+0x37/0xd0 net/core/sock.c:2934
    [<00000000963cc9ae>] sctp_sendmsg+0x2c0/0x990 net/sctp/socket.c:2122
    [<00000000a7fc7565>] inet_sendmsg+0x64/0x120 net/ipv4/af_inet.c:802
    [<00000000b732cbd3>] sock_sendmsg_nosec net/socket.c:652 [inline]
    [<00000000b732cbd3>] sock_sendmsg+0x54/0x70 net/socket.c:671
    [<00000000274c57ab>] ___sys_sendmsg+0x393/0x3c0 net/socket.c:2292
    [<000000008252aedb>] __sys_sendmsg+0x80/0xf0 net/socket.c:2330
    [<00000000f7bf23d1>] __do_sys_sendmsg net/socket.c:2339 [inline]
    [<00000000f7bf23d1>] __se_sys_sendmsg net/socket.c:2337 [inline]
    [<00000000f7bf23d1>] __x64_sys_sendmsg+0x23/0x30 net/socket.c:2337
    [<00000000a8b4131f>] do_syscall_64+0x76/0x1a0 arch/x86/entry/common.c:3

The problem was that the peer.cookie value points to an skb allocated
area on the first pass through this function, at which point it is
overwritten with a heap allocated value, but in certain cases, where a
COOKIE_ECHO chunk is included in the packet, a second pass through
sctp_process_init is made, where the cookie value is re-allocated,
leaking the first allocation.

Fix is to always allocate the cookie value, and free it when we are done
using it.

Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Reported-by: syzbot+f7e9153b037eac9b1df8@syzkaller.appspotmail.com
CC: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
CC: "David S. Miller" <davem@davemloft.net>
CC: netdev@vger.kernel.org
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sm_make_chunk.c | 13 +++----------
 net/sctp/sm_sideeffect.c |  5 +++++
 2 files changed, 8 insertions(+), 10 deletions(-)

diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index d05c57664e36..ae65a1cfa596 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -2329,7 +2329,6 @@ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk,
 	union sctp_addr addr;
 	struct sctp_af *af;
 	int src_match = 0;
-	char *cookie;
 
 	/* We must include the address that the INIT packet came from.
 	 * This is the only address that matters for an INIT packet.
@@ -2433,14 +2432,6 @@ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk,
 	/* Peer Rwnd   : Current calculated value of the peer's rwnd.  */
 	asoc->peer.rwnd = asoc->peer.i.a_rwnd;
 
-	/* Copy cookie in case we need to resend COOKIE-ECHO. */
-	cookie = asoc->peer.cookie;
-	if (cookie) {
-		asoc->peer.cookie = kmemdup(cookie, asoc->peer.cookie_len, gfp);
-		if (!asoc->peer.cookie)
-			goto clean_up;
-	}
-
 	/* RFC 2960 7.2.1 The initial value of ssthresh MAY be arbitrarily
 	 * high (for example, implementations MAY use the size of the receiver
 	 * advertised window).
@@ -2609,7 +2600,9 @@ static int sctp_process_param(struct sctp_association *asoc,
 	case SCTP_PARAM_STATE_COOKIE:
 		asoc->peer.cookie_len =
 			ntohs(param.p->length) - sizeof(struct sctp_paramhdr);
-		asoc->peer.cookie = param.cookie->body;
+		asoc->peer.cookie = kmemdup(param.cookie->body, asoc->peer.cookie_len, gfp);
+		if (!asoc->peer.cookie)
+			retval = 0;
 		break;
 
 	case SCTP_PARAM_HEARTBEAT_INFO:
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index 4aa03588f87b..27ddf2d8f001 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -898,6 +898,11 @@ static void sctp_cmd_new_state(struct sctp_cmd_seq *cmds,
 						asoc->rto_initial;
 	}
 
+	if (sctp_state(asoc, ESTABLISHED)) {
+		kfree(asoc->peer.cookie);
+		asoc->peer.cookie = NULL;
+	}
+
 	if (sctp_state(asoc, ESTABLISHED) ||
 	    sctp_state(asoc, CLOSED) ||
 	    sctp_state(asoc, SHUTDOWN_RECEIVED)) {
-- 
2.20.1


From 8d4db76ee66adcbe4b859e91e00d93029e096b32 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 2 Jun 2019 19:10:24 +0800
Subject: [PATCH 03/22] ipv4: not do cache for local delivery if bc_forwarding
 is enabled

[ Upstream commit 0a90478b93a46bdcd56ba33c37566a993e455d54 ]

With the topo:

    h1 ---| rp1            |
          |     route  rp3 |--- h3 (192.168.200.1)
    h2 ---| rp2            |

If rp1 bc_forwarding is set while rp2 bc_forwarding is not, after
doing "ping 192.168.200.255" on h1, then ping 192.168.200.255 on
h2, and the packets can still be forwared.

This issue was caused by the input route cache. It should only do
the cache for either bc forwarding or local delivery. Otherwise,
local delivery can use the route cache for bc forwarding of other
interfaces.

This patch is to fix it by not doing cache for local delivery if
all.bc_forwarding is enabled.

Note that we don't fix it by checking route cache local flag after
rt_cache_valid() in "local_input:" and "ip_mkroute_input", as the
common route code shouldn't be touched for bc_forwarding.

Fixes: 5cbf777cfdf6 ("route: add support for directed broadcast forwarding")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index df6afb092936..1cd512ac84ba 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1954,7 +1954,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	u32		itag = 0;
 	struct rtable	*rth;
 	struct flowi4	fl4;
-	bool do_cache;
+	bool do_cache = true;
 
 	/* IP on this device is disabled. */
 
@@ -2031,6 +2031,9 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	if (res->type == RTN_BROADCAST) {
 		if (IN_DEV_BFORWARD(in_dev))
 			goto make_route;
+		/* not do cache if bc_forwarding is enabled */
+		if (IPV4_DEVCONF_ALL(net, BC_FORWARDING))
+			do_cache = false;
 		goto brd_input;
 	}
 
@@ -2068,16 +2071,13 @@ out:	return err;
 	RT_CACHE_STAT_INC(in_brd);
 
 local_input:
-	do_cache = false;
-	if (res->fi) {
-		if (!itag) {
-			rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
-			if (rt_cache_valid(rth)) {
-				skb_dst_set_noref(skb, &rth->dst);
-				err = 0;
-				goto out;
-			}
-			do_cache = true;
+	do_cache &= res->fi && !itag;
+	if (do_cache) {
+		rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
+		if (rt_cache_valid(rth)) {
+			skb_dst_set_noref(skb, &rth->dst);
+			err = 0;
+			goto out;
 		}
 	}
 
-- 
2.20.1


From eb34db849cc25012cf28540d4380d0f6fc5998bc Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 2 Jun 2019 19:10:46 +0800
Subject: [PATCH 04/22] ipv6: fix the check before getting the cookie in
 rt6_get_cookie

[ Upstream commit b7999b07726c16974ba9ca3bb9fe98ecbec5f81c ]

In Jianlin's testing, netperf was broken with 'Connection reset by peer',
as the cookie check failed in rt6_check() and ip6_dst_check() always
returned NULL.

It's caused by Commit 93531c674315 ("net/ipv6: separate handling of FIB
entries from dst based routes"), where the cookie can be got only when
'c1'(see below) for setting dst_cookie whereas rt6_check() is called
when !'c1' for checking dst_cookie, as we can see in ip6_dst_check().

Since in ip6_dst_check() both rt6_dst_from_check() (c1) and rt6_check()
(!c1) will check the 'from' cookie, this patch is to remove the c1 check
in rt6_get_cookie(), so that the dst_cookie can always be set properly.

c1:
  (rt->rt6i_flags & RTF_PCPU || unlikely(!list_empty(&rt->rt6i_uncached)))

Fixes: 93531c674315 ("net/ipv6: separate handling of FIB entries from dst based routes")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index b5e3add90e99..4c59fff718c1 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -259,8 +259,7 @@ static inline u32 rt6_get_cookie(const struct rt6_info *rt)
 	rcu_read_lock();
 
 	from = rcu_dereference(rt->from);
-	if (from && (rt->rt6i_flags & RTF_PCPU ||
-	    unlikely(!list_empty(&rt->rt6i_uncached))))
+	if (from)
 		fib6_get_cookie_safe(from, &cookie);
 
 	rcu_read_unlock();
-- 
2.20.1


From afa13334028b9ec05a2ef9bf65e940acf09f2d44 Mon Sep 17 00:00:00 2001
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Fri, 31 May 2019 16:47:25 +0300
Subject: [PATCH 05/22] net: ethernet: ti: cpsw_ethtool: fix ethtool ring param
 set

[ Upstream commit 09faf5a7d7c0bcb07faba072f611937af9dd5788 ]

Fix ability to set RX descriptor number, the reason - initially
"tx_max_pending" was set incorrectly, but the issue appears after
adding sanity check, so fix is for "sanity" patch.

Fixes: 37e2d99b59c476 ("ethtool: Ensure new ring parameters are within bounds during SRINGPARAM")
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index dd12b73a8853..1285f282d3ac 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -3130,6 +3130,7 @@ static void cpsw_get_ringparam(struct net_device *ndev,
 	struct cpsw_common *cpsw = priv->cpsw;
 
 	/* not supported */
+	ering->tx_max_pending = descs_pool_size - CPSW_MAX_QUEUES;
 	ering->tx_max_pending = 0;
 	ering->tx_pending = cpdma_get_num_tx_descs(cpsw->dma);
 	ering->rx_max_pending = descs_pool_size - CPSW_MAX_QUEUES;
-- 
2.20.1


From e8bf4364055cba3f73e9143507677c3f2553eb7d Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 6 Jun 2019 10:42:56 +0200
Subject: [PATCH 06/22] net: mvpp2: Use strscpy to handle stat strings

[ Upstream commit d37acd5aa99c57505b64913e0e2624ec3daed8c5 ]

Use a safe strscpy call to copy the ethtool stat strings into the
relevant buffers, instead of a memcpy that will be accessing
out-of-bound data.

Fixes: 118d6298f6f0 ("net: mvpp2: add ethtool GOP statistics")
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index f4f076d7090e..906f080d9559 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -1304,8 +1304,8 @@ static void mvpp2_ethtool_get_strings(struct net_device *netdev, u32 sset,
 		int i;
 
 		for (i = 0; i < ARRAY_SIZE(mvpp2_ethtool_regs); i++)
-			memcpy(data + i * ETH_GSTRING_LEN,
-			       &mvpp2_ethtool_regs[i].string, ETH_GSTRING_LEN);
+			strscpy(data + i * ETH_GSTRING_LEN,
+			        mvpp2_ethtool_regs[i].string, ETH_GSTRING_LEN);
 	}
 }
 
-- 
2.20.1


From d7f01193291fbf7c4bd11ad81d262897274e3335 Mon Sep 17 00:00:00 2001
From: Zhu Yanjun <yanjun.zhu@oracle.com>
Date: Thu, 6 Jun 2019 04:00:03 -0400
Subject: [PATCH 07/22] net: rds: fix memory leak in rds_ib_flush_mr_pool

[ Upstream commit 85cb928787eab6a2f4ca9d2a798b6f3bed53ced1 ]

When the following tests last for several hours, the problem will occur.

Server:
    rds-stress -r 1.1.1.16 -D 1M
Client:
    rds-stress -r 1.1.1.14 -s 1.1.1.16 -D 1M -T 30

The following will occur.

"
Starting up....
tsks   tx/s   rx/s  tx+rx K/s    mbi K/s    mbo K/s tx us/c   rtt us cpu
%
  1      0      0       0.00       0.00       0.00    0.00 0.00 -1.00
  1      0      0       0.00       0.00       0.00    0.00 0.00 -1.00
  1      0      0       0.00       0.00       0.00    0.00 0.00 -1.00
  1      0      0       0.00       0.00       0.00    0.00 0.00 -1.00
"
>From vmcore, we can find that clean_list is NULL.

>From the source code, rds_mr_flushd calls rds_ib_mr_pool_flush_worker.
Then rds_ib_mr_pool_flush_worker calls
"
 rds_ib_flush_mr_pool(pool, 0, NULL);
"
Then in function
"
int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *pool,
                         int free_all, struct rds_ib_mr **ibmr_ret)
"
ibmr_ret is NULL.

In the source code,
"
...
list_to_llist_nodes(pool, &unmap_list, &clean_nodes, &clean_tail);
if (ibmr_ret)
        *ibmr_ret = llist_entry(clean_nodes, struct rds_ib_mr, llnode);

/* more than one entry in llist nodes */
if (clean_nodes->next)
        llist_add_batch(clean_nodes->next, clean_tail, &pool->clean_list);
...
"
When ibmr_ret is NULL, llist_entry is not executed. clean_nodes->next
instead of clean_nodes is added in clean_list.
So clean_nodes is discarded. It can not be used again.
The workqueue is executed periodically. So more and more clean_nodes are
discarded. Finally the clean_list is NULL.
Then this problem will occur.

Fixes: 1bc144b62524 ("net, rds, Replace xlist in net/rds/xlist.h with llist")
Signed-off-by: Zhu Yanjun <yanjun.zhu@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/ib_rdma.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c
index d664e9ade74d..0b347f46b2f4 100644
--- a/net/rds/ib_rdma.c
+++ b/net/rds/ib_rdma.c
@@ -428,12 +428,14 @@ int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *pool,
 		wait_clean_list_grace();
 
 		list_to_llist_nodes(pool, &unmap_list, &clean_nodes, &clean_tail);
-		if (ibmr_ret)
+		if (ibmr_ret) {
 			*ibmr_ret = llist_entry(clean_nodes, struct rds_ib_mr, llnode);
-
+			clean_nodes = clean_nodes->next;
+		}
 		/* more than one entry in llist nodes */
-		if (clean_nodes->next)
-			llist_add_batch(clean_nodes->next, clean_tail, &pool->clean_list);
+		if (clean_nodes)
+			llist_add_batch(clean_nodes, clean_tail,
+					&pool->clean_list);
 
 	}
 
-- 
2.20.1


From 820cf56bf75335ec76dd07f7f0926127ff2b0e3a Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Sun, 2 Jun 2019 15:13:00 +0100
Subject: [PATCH 08/22] net: sfp: read eeprom in maximum 16 byte increments

[ Upstream commit 28e74a7cfd6403f0d1c0f8b10b45d6fae37b227e ]

Some SFP modules do not like reads longer than 16 bytes, so read the
EEPROM in chunks of 16 bytes at a time.  This behaviour is not specified
in the SFP MSAs, which specifies:

 "The serial interface uses the 2-wire serial CMOS E2PROM protocol
  defined for the ATMEL AT24C01A/02/04 family of components."

and

 "As long as the SFP+ receives an acknowledge, it shall serially clock
  out sequential data words. The sequence is terminated when the host
  responds with a NACK and a STOP instead of an acknowledge."

We must avoid breaking a read across a 16-bit quantity in the diagnostic
page, thankfully all 16-bit quantities in that page are naturally
aligned.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/sfp.c | 24 ++++++++++++++++++++----
 1 file changed, 20 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index d4635c2178d1..71812be0ac64 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -281,6 +281,7 @@ static int sfp_i2c_read(struct sfp *sfp, bool a2, u8 dev_addr, void *buf,
 {
 	struct i2c_msg msgs[2];
 	u8 bus_addr = a2 ? 0x51 : 0x50;
+	size_t this_len;
 	int ret;
 
 	msgs[0].addr = bus_addr;
@@ -292,11 +293,26 @@ static int sfp_i2c_read(struct sfp *sfp, bool a2, u8 dev_addr, void *buf,
 	msgs[1].len = len;
 	msgs[1].buf = buf;
 
-	ret = i2c_transfer(sfp->i2c, msgs, ARRAY_SIZE(msgs));
-	if (ret < 0)
-		return ret;
+	while (len) {
+		this_len = len;
+		if (this_len > 16)
+			this_len = 16;
 
-	return ret == ARRAY_SIZE(msgs) ? len : 0;
+		msgs[1].len = this_len;
+
+		ret = i2c_transfer(sfp->i2c, msgs, ARRAY_SIZE(msgs));
+		if (ret < 0)
+			return ret;
+
+		if (ret != ARRAY_SIZE(msgs))
+			break;
+
+		msgs[1].buf += this_len;
+		dev_addr += this_len;
+		len -= this_len;
+	}
+
+	return msgs[1].buf - (u8 *)buf;
 }
 
 static int sfp_i2c_write(struct sfp *sfp, bool a2, u8 dev_addr, void *buf,
-- 
2.20.1


From 77d5144bf57a9af3c13ca439cb840234d9557e64 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 31 May 2019 12:37:23 -0400
Subject: [PATCH 09/22] packet: unconditionally free po->rollover

[ Upstream commit afa0925c6fcc6a8f610e996ca09bc3215048033c ]

Rollover used to use a complex RCU mechanism for assignment, which had
a race condition. The below patch fixed the bug and greatly simplified
the logic.

The feature depends on fanout, but the state is private to the socket.
Fanout_release returns f only when the last member leaves and the
fanout struct is to be freed.

Destroy rollover unconditionally, regardless of fanout state.

Fixes: 57f015f5eccf2 ("packet: fix crash in fanout_demux_rollover()")
Reported-by: syzbot <syzkaller@googlegroups.com>
Diagnosed-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 59da6f5b717d..71d5544243d2 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3016,8 +3016,8 @@ static int packet_release(struct socket *sock)
 
 	synchronize_net();
 
+	kfree(po->rollover);
 	if (f) {
-		kfree(po->rollover);
 		fanout_release_data(f);
 		kfree(f);
 	}
-- 
2.20.1


From f7059b38b5d27375042c1f88e456ceb211c0dfa9 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 6 Jun 2019 15:45:03 +0200
Subject: [PATCH 10/22] pktgen: do not sleep with the thread lock held.

[ Upstream commit 720f1de4021f09898b8c8443f3b3e995991b6e3a ]

Currently, the process issuing a "start" command on the pktgen procfs
interface, acquires the pktgen thread lock and never release it, until
all pktgen threads are completed. The above can blocks indefinitely any
other pktgen command and any (even unrelated) netdevice removal - as
the pktgen netdev notifier acquires the same lock.

The issue is demonstrated by the following script, reported by Matteo:

ip -b - <<'EOF'
	link add type dummy
	link add type veth
	link set dummy0 up
EOF
modprobe pktgen
echo reset >/proc/net/pktgen/pgctrl
{
	echo rem_device_all
	echo add_device dummy0
} >/proc/net/pktgen/kpktgend_0
echo count 0 >/proc/net/pktgen/dummy0
echo start >/proc/net/pktgen/pgctrl &
sleep 1
rmmod veth

Fix the above releasing the thread lock around the sleep call.

Additionally we must prevent racing with forcefull rmmod - as the
thread lock no more protects from them. Instead, acquire a self-reference
before waiting for any thread. As a side effect, running

rmmod pktgen

while some thread is running now fails with "module in use" error,
before this patch such command hanged indefinitely.

Note: the issue predates the commit reported in the fixes tag, but
this fix can't be applied before the mentioned commit.

v1 -> v2:
 - no need to check for thread existence after flipping the lock,
   pktgen threads are freed only at net exit time
 -

Fixes: 6146e6a43b35 ("[PKTGEN]: Removes thread_{un,}lock() macros.")
Reported-and-tested-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/pktgen.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index f3f5a78cd062..f19c498f4ecb 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -3066,7 +3066,13 @@ static int pktgen_wait_thread_run(struct pktgen_thread *t)
 {
 	while (thread_is_running(t)) {
 
+		/* note: 't' will still be around even after the unlock/lock
+		 * cycle because pktgen_thread threads are only cleared at
+		 * net exit
+		 */
+		mutex_unlock(&pktgen_thread_lock);
 		msleep_interruptible(100);
+		mutex_lock(&pktgen_thread_lock);
 
 		if (signal_pending(current))
 			goto signal;
@@ -3081,6 +3087,10 @@ static int pktgen_wait_all_threads_run(struct pktgen_net *pn)
 	struct pktgen_thread *t;
 	int sig = 1;
 
+	/* prevent from racing with rmmod */
+	if (!try_module_get(THIS_MODULE))
+		return sig;
+
 	mutex_lock(&pktgen_thread_lock);
 
 	list_for_each_entry(t, &pn->pktgen_threads, th_list) {
@@ -3094,6 +3104,7 @@ static int pktgen_wait_all_threads_run(struct pktgen_net *pn)
 			t->control |= (T_STOP);
 
 	mutex_unlock(&pktgen_thread_lock);
+	module_put(THIS_MODULE);
 	return sig;
 }
 
-- 
2.20.1


From 142c5916e712f241f4436af9fe2f81b9318791b3 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Wed, 5 Jun 2019 12:27:14 +0800
Subject: [PATCH 11/22] Revert "fib_rules: return 0 directly if an exactly same
 rule exists when NLM_F_EXCL not supplied"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 4970b42d5c362bf873982db7d93245c5281e58f4 ]

This reverts commit e9919a24d3022f72bcadc407e73a6ef17093a849.

Nathan reported the new behaviour breaks Android, as Android just add
new rules and delete old ones.

If we return 0 without adding dup rules, Android will remove the new
added rules and causing system to soft-reboot.

Fixes: e9919a24d302 ("fib_rules: return 0 directly if an exactly same rule exists when NLM_F_EXCL not supplied")
Reported-by: Nathan Chancellor <natechancellor@gmail.com>
Reported-by: Yaro Slav <yaro330@gmail.com>
Reported-by: Maciej Żenczykowski <zenczykowski@gmail.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Nathan Chancellor <natechancellor@gmail.com>
Tested-by: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/fib_rules.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index c49b752ea7eb..ffbb827723a2 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -756,9 +756,9 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (err)
 		goto errout;
 
-	if (rule_exists(ops, frh, tb, rule)) {
-		if (nlh->nlmsg_flags & NLM_F_EXCL)
-			err = -EEXIST;
+	if ((nlh->nlmsg_flags & NLM_F_EXCL) &&
+	    rule_exists(ops, frh, tb, rule)) {
+		err = -EEXIST;
 		goto errout_free;
 	}
 
-- 
2.20.1


From 01e8f3fab3975190a6514af53fb375b9d2a5f3b4 Mon Sep 17 00:00:00 2001
From: James Clarke <jrtc27@jrtc27.com>
Date: Wed, 29 May 2019 22:31:31 +0100
Subject: [PATCH 12/22] sparc64: Fix regression in non-hypervisor TLB flush
 xcall

[ Upstream commit d3c976c14ad8af421134c428b0a89ff8dd3bd8f8 ]

Previously, %g2 would end up with the value PAGE_SIZE, but after the
commit mentioned below it ends up with the value 1 due to being reused
for a different purpose. We need it to be PAGE_SIZE as we use it to step
through pages in our demap loop, otherwise we set different flags in the
low 12 bits of the address written to, thereby doing things other than a
nucleus page flush.

Fixes: a74ad5e660a9 ("sparc64: Handle extremely large kernel TLB range flushes more gracefully.")
Reported-by: Meelis Roos <mroos@linux.ee>
Tested-by: Meelis Roos <mroos@linux.ee>
Signed-off-by: James Clarke <jrtc27@jrtc27.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/sparc/mm/ultra.S | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/sparc/mm/ultra.S b/arch/sparc/mm/ultra.S
index d245f89d1395..d220b6848746 100644
--- a/arch/sparc/mm/ultra.S
+++ b/arch/sparc/mm/ultra.S
@@ -587,7 +587,7 @@ xcall_flush_tlb_kernel_range:	/* 44 insns */
 	sub		%g7, %g1, %g3
 	srlx		%g3, 18, %g2
 	brnz,pn		%g2, 2f
-	 add		%g2, 1, %g2
+	 sethi		%hi(PAGE_SIZE), %g2
 	sub		%g3, %g2, %g3
 	or		%g1, 0x20, %g1		! Nucleus
 1:	stxa		%g0, [%g1 + %g3] ASI_DMMU_DEMAP
@@ -751,7 +751,7 @@ __cheetah_xcall_flush_tlb_kernel_range:	/* 44 insns */
 	sub		%g7, %g1, %g3
 	srlx		%g3, 18, %g2
 	brnz,pn		%g2, 2f
-	 add		%g2, 1, %g2
+	 sethi		%hi(PAGE_SIZE), %g2
 	sub		%g3, %g2, %g3
 	or		%g1, 0x20, %g1		! Nucleus
 1:	stxa		%g0, [%g1 + %g3] ASI_DMMU_DEMAP
-- 
2.20.1


From e41b401ba8de8b6cc6b603a24ec69f1a7203622b Mon Sep 17 00:00:00 2001
From: Tim Beale <timbeale@catalyst.net.nz>
Date: Tue, 4 Jun 2019 13:56:23 +1200
Subject: [PATCH 13/22] udp: only choose unbound UDP socket for multicast when
 not in a VRF

[ Upstream commit 82ba25c6de200d7a9e9c970c998cdd6dfa8637ae ]

By default, packets received in another VRF should not be passed to an
unbound socket in the default VRF. This patch updates the IPv4 UDP
multicast logic to match the unicast VRF logic (in compute_score()),
as well as the IPv6 mcast logic (in __udp_v6_is_mcast_sock()).

The particular case I noticed was DHCP discover packets going
to the 255.255.255.255 address, which are handled by
__udp4_lib_mcast_deliver(). The previous code meant that running
multiple different DHCP server or relay agent instances across VRFs
did not work correctly - any server/relay agent in the default VRF
received DHCP discover packets for all other VRFs.

Fixes: 6da5b0f027a8 ("net: ensure unbound datagram socket to be chosen when not in a VRF")
Signed-off-by: Tim Beale <timbeale@catalyst.net.nz>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 372fdc5381a9..3b179ce6170f 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -538,8 +538,7 @@ static inline bool __udp_is_mcast_sock(struct net *net, struct sock *sk,
 	    (inet->inet_dport != rmt_port && inet->inet_dport) ||
 	    (inet->inet_rcv_saddr && inet->inet_rcv_saddr != loc_addr) ||
 	    ipv6_only_sock(sk) ||
-	    (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif &&
-	     sk->sk_bound_dev_if != sdif))
+	    !udp_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif))
 		return false;
 	if (!ip_mc_sf_allow(sk, loc_addr, rmt_addr, dif, sdif))
 		return false;
-- 
2.20.1


From 673635111fe20b33cb6e36d841359aa75a702fb0 Mon Sep 17 00:00:00 2001
From: Olivier Matz <olivier.matz@6wind.com>
Date: Thu, 6 Jun 2019 09:15:18 +0200
Subject: [PATCH 14/22] ipv6: use READ_ONCE() for inet->hdrincl as in ipv4

[ Upstream commit 59e3e4b52663a9d97efbce7307f62e4bc5c9ce91 ]

As it was done in commit 8f659a03a0ba ("net: ipv4: fix for a race
condition in raw_sendmsg") and commit 20b50d79974e ("net: ipv4: emulate
READ_ONCE() on ->hdrincl bit-field in raw_sendmsg()") for ipv4, copy the
value of inet->hdrincl in a local variable, to avoid introducing a race
condition in the next commit.

Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/raw.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 5cb14eabfc65..a79fd1b4b392 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -783,6 +783,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	struct flowi6 fl6;
 	struct ipcm6_cookie ipc6;
 	int addr_len = msg->msg_namelen;
+	int hdrincl;
 	u16 proto;
 	int err;
 
@@ -796,6 +797,13 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	if (msg->msg_flags & MSG_OOB)
 		return -EOPNOTSUPP;
 
+	/* hdrincl should be READ_ONCE(inet->hdrincl)
+	 * but READ_ONCE() doesn't work with bit fields.
+	 * Doing this indirectly yields the same result.
+	 */
+	hdrincl = inet->hdrincl;
+	hdrincl = READ_ONCE(hdrincl);
+
 	/*
 	 *	Get and verify the address.
 	 */
@@ -908,7 +916,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		fl6.flowi6_oif = np->ucast_oif;
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
-	if (inet->hdrincl)
+	if (hdrincl)
 		fl6.flowi6_flags |= FLOWI_FLAG_KNOWN_NH;
 
 	if (ipc6.tclass < 0)
@@ -931,7 +939,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		goto do_confirm;
 
 back_from_confirm:
-	if (inet->hdrincl)
+	if (hdrincl)
 		err = rawv6_send_hdrinc(sk, msg, len, &fl6, &dst,
 					msg->msg_flags, &ipc6.sockc);
 	else {
-- 
2.20.1


From cd2dbee8c36f3c4b82090fe502291247b8460fa8 Mon Sep 17 00:00:00 2001
From: Olivier Matz <olivier.matz@6wind.com>
Date: Thu, 6 Jun 2019 09:15:19 +0200
Subject: [PATCH 15/22] ipv6: fix EFAULT on sendto with icmpv6 and hdrincl

[ Upstream commit b9aa52c4cb457e7416cc0c95f475e72ef4a61336 ]

The following code returns EFAULT (Bad address):

  s = socket(AF_INET6, SOCK_RAW, IPPROTO_ICMPV6);
  setsockopt(s, SOL_IPV6, IPV6_HDRINCL, 1);
  sendto(ipv6_icmp6_packet, addr);   /* returns -1, errno = EFAULT */

The IPv4 equivalent code works. A workaround is to use IPPROTO_RAW
instead of IPPROTO_ICMPV6.

The failure happens because 2 bytes are eaten from the msghdr by
rawv6_probe_proto_opt() starting from commit 19e3c66b52ca ("ipv6
equivalent of "ipv4: Avoid reading user iov twice after
raw_probe_proto_opt""), but at that time it was not a problem because
IPV6_HDRINCL was not yet introduced.

Only eat these 2 bytes if hdrincl == 0.

Fixes: 715f504b1189 ("ipv6: add IPV6_HDRINCL option for raw sockets")
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/raw.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index a79fd1b4b392..5f8fe98b435b 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -895,11 +895,14 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	opt = ipv6_fixup_options(&opt_space, opt);
 
 	fl6.flowi6_proto = proto;
-	rfv.msg = msg;
-	rfv.hlen = 0;
-	err = rawv6_probe_proto_opt(&rfv, &fl6);
-	if (err)
-		goto out;
+
+	if (!hdrincl) {
+		rfv.msg = msg;
+		rfv.hlen = 0;
+		err = rawv6_probe_proto_opt(&rfv, &fl6);
+		if (err)
+			goto out;
+	}
 
 	if (!ipv6_addr_any(daddr))
 		fl6.daddr = *daddr;
-- 
2.20.1


From f9bf6aadd04ae2b5d741b6c8093bae76f2d235d3 Mon Sep 17 00:00:00 2001
From: Nikita Danilov <nikita.danilov@aquantia.com>
Date: Tue, 4 Jun 2019 13:23:49 +0000
Subject: [PATCH 16/22] net: aquantia: fix wol configuration not applied
 sometimes

[ Upstream commit 930b9a0543385d4eb8ef887e88cf84d95a844577 ]

WoL magic packet configuration sometimes does not work due to
couple of leakages found.

Mainly there was a regression introduced during readx_poll refactoring.

Next, fw request waiting time was too small. Sometimes that
caused sleep proxy config function to return with an error
and to skip WoL configuration.
At last, WoL data were passed to FW from not clean buffer.
That could cause FW to accept garbage as a random configuration data.

Fixes: 6a7f2277313b ("net: aquantia: replace AQ_HW_WAIT_FOR with readx_poll_timeout_atomic")
Signed-off-by: Nikita Danilov <nikita.danilov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../aquantia/atlantic/hw_atl/hw_atl_utils.c        | 14 +++++++-------
 .../aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c   |  4 +++-
 2 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
index eb4b99d56081..33d3c3789209 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
@@ -335,13 +335,13 @@ static int hw_atl_utils_fw_upload_dwords(struct aq_hw_s *self, u32 a, u32 *p,
 {
 	u32 val;
 	int err = 0;
-	bool is_locked;
 
-	is_locked = hw_atl_sem_ram_get(self);
-	if (!is_locked) {
-		err = -ETIME;
+	err = readx_poll_timeout_atomic(hw_atl_sem_ram_get, self,
+					val, val == 1U,
+					10U, 100000U);
+	if (err < 0)
 		goto err_exit;
-	}
+
 	if (IS_CHIP_FEATURE(REVISION_B1)) {
 		u32 offset = 0;
 
@@ -353,8 +353,8 @@ static int hw_atl_utils_fw_upload_dwords(struct aq_hw_s *self, u32 a, u32 *p,
 			/* 1000 times by 10us = 10ms */
 			err = readx_poll_timeout_atomic(hw_atl_scrpad12_get,
 							self, val,
-							(val & 0xF0000000) ==
-							 0x80000000,
+							(val & 0xF0000000) !=
+							0x80000000,
 							10U, 10000U);
 		}
 	} else {
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
index fe6c5658e016..9d0292aa071d 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
@@ -349,7 +349,7 @@ static int aq_fw2x_set_sleep_proxy(struct aq_hw_s *self, u8 *mac)
 	err = readx_poll_timeout_atomic(aq_fw2x_state2_get,
 					self, val,
 					val & HW_ATL_FW2X_CTRL_SLEEP_PROXY,
-					1U, 10000U);
+					1U, 100000U);
 
 err_exit:
 	return err;
@@ -369,6 +369,8 @@ static int aq_fw2x_set_wol_params(struct aq_hw_s *self, u8 *mac)
 
 	msg = (struct fw2x_msg_wol *)rpc;
 
+	memset(msg, 0, sizeof(*msg));
+
 	msg->msg_id = HAL_ATLANTIC_UTILS_FW2X_MSG_WOL;
 	msg->magic_packet_enabled = true;
 	memcpy(msg->hw_addr, mac, ETH_ALEN);
-- 
2.20.1


From 61020257b8fa2dad2ad5186429830d5dc416dcf0 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 1 May 2019 18:08:34 -0700
Subject: [PATCH 17/22] neighbor: Reset gc_entries counter if new entry is
 released before insert

[ Upstream commit 64c6f4bbca748c3b2101469a76d88b7cd1c00476 ]

Ian and Alan both reported seeing overflows after upgrades to 5.x kernels:
  neighbour: arp_cache: neighbor table overflow!

Alan's mpls script helped get to the bottom of this bug. When a new entry
is created the gc_entries counter is bumped in neigh_alloc to check if a
new one is allowed to be created. ___neigh_create then searches for an
existing entry before inserting the just allocated one. If an entry
already exists, the new one is dropped in favor of the existing one. In
this case the cleanup path needs to drop the gc_entries counter. There
is no memory leak, only a counter leak.

Fixes: 58956317c8d ("neighbor: Improve garbage collection")
Reported-by: Ian Kumlien <ian.kumlien@gmail.com>
Reported-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Tested-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 30f6fd8f68e0..aff051e5521d 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -663,6 +663,8 @@ static struct neighbour *___neigh_create(struct neigh_table *tbl,
 out_tbl_unlock:
 	write_unlock_bh(&tbl->lock);
 out_neigh_release:
+	if (!exempt_from_gc)
+		atomic_dec(&tbl->gc_entries);
 	neigh_release(n);
 	goto out;
 }
-- 
2.20.1


From c4b3a4ec889f3770725861f58c485e37ce8256e8 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 1 May 2019 18:18:42 -0700
Subject: [PATCH 18/22] neighbor: Call __ipv4_neigh_lookup_noref in neigh_xmit

[ Upstream commit 4b2a2bfeb3f056461a90bd621e8bd7d03fa47f60 ]

Commit cd9ff4de0107 changed the key for IFF_POINTOPOINT devices to
INADDR_ANY but neigh_xmit which is used for MPLS encapsulations was not
updated to use the altered key. The result is that every packet Tx does
a lookup on the gateway address which does not find an entry, a new one
is created only to find the existing one in the table right before the
insert since arp_constructor was updated to reset the primary key. This
is seen in the allocs and destroys counters:
    ip -s -4 ntable show | head -10 | grep alloc

which increase for each packet showing the unnecessary overhread.

Fix by having neigh_xmit use __ipv4_neigh_lookup_noref for NEIGH_ARP_TABLE.

Fixes: cd9ff4de0107 ("ipv4: Make neigh lookup keys for loopback/point-to-point devices be INADDR_ANY")
Reported-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Tested-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index aff051e5521d..9b9da5142613 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -31,6 +31,7 @@
 #include <linux/times.h>
 #include <net/net_namespace.h>
 #include <net/neighbour.h>
+#include <net/arp.h>
 #include <net/dst.h>
 #include <net/sock.h>
 #include <net/netevent.h>
@@ -2984,7 +2985,13 @@ int neigh_xmit(int index, struct net_device *dev,
 		if (!tbl)
 			goto out;
 		rcu_read_lock_bh();
-		neigh = __neigh_lookup_noref(tbl, addr, dev);
+		if (index == NEIGH_ARP_TABLE) {
+			u32 key = *((u32 *)addr);
+
+			neigh = __ipv4_neigh_lookup_noref(dev, key);
+		} else {
+			neigh = __neigh_lookup_noref(tbl, addr, dev);
+		}
 		if (!neigh)
 			neigh = __neigh_create(tbl, addr, dev, false);
 		err = PTR_ERR(neigh);
-- 
2.20.1


From eef06910d98f8dfe6159add493bcc784af7bda2f Mon Sep 17 00:00:00 2001
From: Matteo Croce <mcroce@redhat.com>
Date: Thu, 2 May 2019 10:51:05 +0200
Subject: [PATCH 19/22] cls_matchall: avoid panic when receiving a packet
 before filter set

[ Upstream commit 25426043ec9e22b90c789407c28e40f32a9d1985 ]

When a matchall classifier is added, there is a small time interval in
which tp->root is NULL. If we receive a packet in this small time slice
a NULL pointer dereference will happen, leading to a kernel panic:

    # tc qdisc replace dev eth0 ingress
    # tc filter add dev eth0 parent ffff: matchall action gact drop
    Unable to handle kernel NULL pointer dereference at virtual address 0000000000000034
    Mem abort info:
      ESR = 0x96000005
      Exception class = DABT (current EL), IL = 32 bits
      SET = 0, FnV = 0
      EA = 0, S1PTW = 0
    Data abort info:
      ISV = 0, ISS = 0x00000005
      CM = 0, WnR = 0
    user pgtable: 4k pages, 39-bit VAs, pgdp = 00000000a623d530
    [0000000000000034] pgd=0000000000000000, pud=0000000000000000
    Internal error: Oops: 96000005 [#1] SMP
    Modules linked in: cls_matchall sch_ingress nls_iso8859_1 nls_cp437 vfat fat m25p80 spi_nor mtd xhci_plat_hcd xhci_hcd phy_generic sfp mdio_i2c usbcore i2c_mv64xxx marvell10g mvpp2 usb_common spi_orion mvmdio i2c_core sbsa_gwdt phylink ip_tables x_tables autofs4
    Process ksoftirqd/0 (pid: 9, stack limit = 0x0000000009de7d62)
    CPU: 0 PID: 9 Comm: ksoftirqd/0 Not tainted 5.1.0-rc6 #21
    Hardware name: Marvell 8040 MACCHIATOBin Double-shot (DT)
    pstate: 40000005 (nZcv daif -PAN -UAO)
    pc : mall_classify+0x28/0x78 [cls_matchall]
    lr : tcf_classify+0x78/0x138
    sp : ffffff80109db9d0
    x29: ffffff80109db9d0 x28: ffffffc426058800
    x27: 0000000000000000 x26: ffffffc425b0dd00
    x25: 0000000020000000 x24: 0000000000000000
    x23: ffffff80109dbac0 x22: 0000000000000001
    x21: ffffffc428ab5100 x20: ffffffc425b0dd00
    x19: ffffff80109dbac0 x18: 0000000000000000
    x17: 0000000000000000 x16: 0000000000000000
    x15: 0000000000000000 x14: 0000000000000000
    x13: ffffffbf108ad288 x12: dead000000000200
    x11: 00000000f0000000 x10: 0000000000000001
    x9 : ffffffbf1089a220 x8 : 0000000000000001
    x7 : ffffffbebffaa950 x6 : 0000000000000000
    x5 : 000000442d6ba000 x4 : 0000000000000000
    x3 : ffffff8008735ad8 x2 : ffffff80109dbac0
    x1 : ffffffc425b0dd00 x0 : ffffff8010592078
    Call trace:
     mall_classify+0x28/0x78 [cls_matchall]
     tcf_classify+0x78/0x138
     __netif_receive_skb_core+0x29c/0xa20
     __netif_receive_skb_one_core+0x34/0x60
     __netif_receive_skb+0x28/0x78
     netif_receive_skb_internal+0x2c/0xc0
     napi_gro_receive+0x1a0/0x1d8
     mvpp2_poll+0x928/0xb18 [mvpp2]
     net_rx_action+0x108/0x378
     __do_softirq+0x128/0x320
     run_ksoftirqd+0x44/0x60
     smpboot_thread_fn+0x168/0x1b0
     kthread+0x12c/0x130
     ret_from_fork+0x10/0x1c
    Code: aa0203f3 aa1e03e0 d503201f f9400684 (b9403480)
    ---[ end trace fc71e2ef7b8ab5a5 ]---
    Kernel panic - not syncing: Fatal exception in interrupt
    SMP: stopping secondary CPUs
    Kernel Offset: disabled
    CPU features: 0x002,00002000
    Memory Limit: none
    Rebooting in 1 seconds..

Fix this by adding a NULL check in mall_classify().

Fixes: ed76f5edccc9 ("net: sched: protect filter_chain list with filter_chain_lock mutex")
Signed-off-by: Matteo Croce <mcroce@redhat.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_matchall.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index a13bc351a414..3d021f2aad1c 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -32,6 +32,9 @@ static int mall_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 {
 	struct cls_mall_head *head = rcu_dereference_bh(tp->root);
 
+	if (unlikely(!head))
+		return -1;
+
 	if (tc_skip_sw(head->flags))
 		return -1;
 
-- 
2.20.1


From f284d07083521bde1645c6b21d86311c34695afa Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Thu, 2 May 2019 15:14:15 -0700
Subject: [PATCH 20/22] ipmr_base: Do not reset index in mr_table_dump

[ Upstream commit 7fcd1e033dacedd520abebc943c960dcf5add3ae ]

e is the counter used to save the location of a dump when an
skb is filled. Once the walk of the table is complete, mr_table_dump
needs to return without resetting that index to 0. Dump of a specific
table is looping because of the reset because there is no way to
indicate the walk of the table is done.

Move the reset to the caller so the dump of each table starts at 0,
but the loop counter is maintained if a dump fills an skb.

Fixes: e1cedae1ba6b0 ("ipmr: Refactor mr_rtm_dumproute")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ipmr_base.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c
index 3e614cc824f7..3a1af50bd0a5 100644
--- a/net/ipv4/ipmr_base.c
+++ b/net/ipv4/ipmr_base.c
@@ -335,8 +335,6 @@ int mr_table_dump(struct mr_table *mrt, struct sk_buff *skb,
 	}
 	spin_unlock_bh(lock);
 	err = 0;
-	e = 0;
-
 out:
 	cb->args[1] = e;
 	return err;
@@ -374,6 +372,7 @@ int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb,
 		err = mr_table_dump(mrt, skb, cb, fill, lock, filter);
 		if (err < 0)
 			break;
+		cb->args[1] = 0;
 next_table:
 		t++;
 	}
-- 
2.20.1


From b8aebf827dd4496a85a9d16214932a94b20fa197 Mon Sep 17 00:00:00 2001
From: Erez Alfasi <ereza@mellanox.com>
Date: Mon, 20 May 2019 17:42:52 +0300
Subject: [PATCH 21/22] net/mlx4_en: ethtool, Remove unsupported SFP EEPROM
 high pages query

[ Upstream commit 135dd9594f127c8a82d141c3c8430e9e2143216a ]

Querying EEPROM high pages data for SFP module is currently
not supported by our driver but is still tried, resulting in
invalid FW queries.

Set the EEPROM ethtool data length to 256 for SFP module to
limit the reading for page 0 only and prevent invalid FW queries.

Fixes: 7202da8b7f71 ("ethtool, net/mlx4_en: Cable info, get_module_info/eeprom ethtool support")
Signed-off-by: Erez Alfasi <ereza@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 4 +++-
 drivers/net/ethernet/mellanox/mlx4/port.c       | 5 -----
 2 files changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index d290f0787dfb..94c59939a8cf 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -2010,6 +2010,8 @@ static int mlx4_en_set_tunable(struct net_device *dev,
 	return ret;
 }
 
+#define MLX4_EEPROM_PAGE_LEN 256
+
 static int mlx4_en_get_module_info(struct net_device *dev,
 				   struct ethtool_modinfo *modinfo)
 {
@@ -2044,7 +2046,7 @@ static int mlx4_en_get_module_info(struct net_device *dev,
 		break;
 	case MLX4_MODULE_ID_SFP:
 		modinfo->type = ETH_MODULE_SFF_8472;
-		modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN;
+		modinfo->eeprom_len = MLX4_EEPROM_PAGE_LEN;
 		break;
 	default:
 		return -EINVAL;
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index 10fcc22f4590..ba6ac31a339d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -2077,11 +2077,6 @@ int mlx4_get_module_info(struct mlx4_dev *dev, u8 port,
 		size -= offset + size - I2C_PAGE_SIZE;
 
 	i2c_addr = I2C_ADDR_LOW;
-	if (offset >= I2C_PAGE_SIZE) {
-		/* Reset offset to high page */
-		i2c_addr = I2C_ADDR_HIGH;
-		offset -= I2C_PAGE_SIZE;
-	}
 
 	cable_info = (struct mlx4_cable_info *)inmad->data;
 	cable_info->dev_mem_address = cpu_to_be16(offset);
-- 
2.20.1


From 9fa980bee9681b583e157819567b0d3ac32bb9f1 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 4 Jun 2019 12:00:12 -0700
Subject: [PATCH 22/22] net/tls: replace the sleeping lock around RX resync
 with a bit lock

[ Upstream commit e52972c11d6b1262964db96d65934196db621685 ]

Commit 38030d7cb779 ("net/tls: avoid NULL-deref on resync during device removal")
tried to fix a potential NULL-dereference by taking the
context rwsem.  Unfortunately the RX resync may get called
from soft IRQ, so we can't use the rwsem to protect from
the device disappearing.  Because we are guaranteed there
can be only one resync at a time (it's called from strparser)
use a bit to indicate resync is busy and make device
removal wait for the bit to get cleared.

Note that there is a leftover "flags" field in struct
tls_context already.

Fixes: 4799ac81e52a ("tls: Add rx inline crypto offload")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h    |  4 ++++
 net/tls/tls_device.c | 27 +++++++++++++++++++++------
 2 files changed, 25 insertions(+), 6 deletions(-)

diff --git a/include/net/tls.h b/include/net/tls.h
index 5934246b2c6f..053082d98906 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -199,6 +199,10 @@ struct tls_offload_context_tx {
 	(ALIGN(sizeof(struct tls_offload_context_tx), sizeof(void *)) +        \
 	 TLS_DRIVER_STATE_SIZE)
 
+enum tls_context_flags {
+	TLS_RX_SYNC_RUNNING = 0,
+};
+
 struct cipher_context {
 	char *iv;
 	char *rec_seq;
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 0fd8f0997ff5..12454f0d5a63 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -570,10 +570,22 @@ void tls_device_write_space(struct sock *sk, struct tls_context *ctx)
 	}
 }
 
+static void tls_device_resync_rx(struct tls_context *tls_ctx,
+				 struct sock *sk, u32 seq, u64 rcd_sn)
+{
+	struct net_device *netdev;
+
+	if (WARN_ON(test_and_set_bit(TLS_RX_SYNC_RUNNING, &tls_ctx->flags)))
+		return;
+	netdev = READ_ONCE(tls_ctx->netdev);
+	if (netdev)
+		netdev->tlsdev_ops->tls_dev_resync_rx(netdev, sk, seq, rcd_sn);
+	clear_bit_unlock(TLS_RX_SYNC_RUNNING, &tls_ctx->flags);
+}
+
 void handle_device_resync(struct sock *sk, u32 seq, u64 rcd_sn)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
-	struct net_device *netdev = tls_ctx->netdev;
 	struct tls_offload_context_rx *rx_ctx;
 	u32 is_req_pending;
 	s64 resync_req;
@@ -588,10 +600,10 @@ void handle_device_resync(struct sock *sk, u32 seq, u64 rcd_sn)
 	is_req_pending = resync_req;
 
 	if (unlikely(is_req_pending) && req_seq == seq &&
-	    atomic64_try_cmpxchg(&rx_ctx->resync_req, &resync_req, 0))
-		netdev->tlsdev_ops->tls_dev_resync_rx(netdev, sk,
-						      seq + TLS_HEADER_SIZE - 1,
-						      rcd_sn);
+	    atomic64_try_cmpxchg(&rx_ctx->resync_req, &resync_req, 0)) {
+		seq += TLS_HEADER_SIZE - 1;
+		tls_device_resync_rx(tls_ctx, sk, seq, rcd_sn);
+	}
 }
 
 static int tls_device_reencrypt(struct sock *sk, struct sk_buff *skb)
@@ -981,7 +993,10 @@ static int tls_device_down(struct net_device *netdev)
 		if (ctx->rx_conf == TLS_HW)
 			netdev->tlsdev_ops->tls_dev_del(netdev, ctx,
 							TLS_OFFLOAD_CTX_DIR_RX);
-		ctx->netdev = NULL;
+		WRITE_ONCE(ctx->netdev, NULL);
+		smp_mb__before_atomic(); /* pairs with test_and_set_bit() */
+		while (test_bit(TLS_RX_SYNC_RUNNING, &ctx->flags))
+			usleep_range(10, 200);
 		dev_put(netdev);
 		list_del_init(&ctx->list);
 
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Sat, Jun 08, 2019 at 04:27:22PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.19 and v5.2
> -stable, respectively.

All now queued up, except for the duplicate sparc64 patch that you sent
last week which I already applied :)

thanks,

greg k-h

Re: [PATCHES] Networking

[David Miller]

From: Greg KH <greg@kroah.com>
Date: Sun, 9 Jun 2019 09:26:10 +0200

> On Sat, Jun 08, 2019 at 04:27:22PM -0700, David Miller wrote:
>> 
>> Please queue up the following networking bug fixes for v4.19 and v5.2
>> -stable, respectively.
> 
> All now queued up, except for the duplicate sparc64 patch that you sent
> last week which I already applied :)

Oops, my bad!

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 106 bytes --]


Please queue up the following networking bug fixes for v4.19 and v5.1
-stable, respectively.

Thank you.

[-- Attachment #2: net_419.mbox --]
[-- Type: Application/Octet-Stream, Size: 44484 bytes --]

From 950ea0b739083cd71bca0cab19d0b036072cc713 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 15 Jun 2019 16:40:52 -0700
Subject: [PATCH 01/17] ax25: fix inconsistent lock state in ax25_destroy_timer

[ Upstream commit d4d5d8e83c9616aeef28a2869cea49cc3fb35526 ]

Before thread in process context uses bh_lock_sock()
we must disable bh.

sysbot reported :

WARNING: inconsistent lock state
5.2.0-rc3+ #32 Not tainted

inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage.
blkid/26581 [HC0[0]:SC1[1]:HE1:SE0] takes:
00000000e0da85ee (slock-AF_AX25){+.?.}, at: spin_lock include/linux/spinlock.h:338 [inline]
00000000e0da85ee (slock-AF_AX25){+.?.}, at: ax25_destroy_timer+0x53/0xc0 net/ax25/af_ax25.c:275
{SOFTIRQ-ON-W} state was registered at:
  lock_acquire+0x16f/0x3f0 kernel/locking/lockdep.c:4303
  __raw_spin_lock include/linux/spinlock_api_smp.h:142 [inline]
  _raw_spin_lock+0x2f/0x40 kernel/locking/spinlock.c:151
  spin_lock include/linux/spinlock.h:338 [inline]
  ax25_rt_autobind+0x3ca/0x720 net/ax25/ax25_route.c:429
  ax25_connect.cold+0x30/0xa4 net/ax25/af_ax25.c:1221
  __sys_connect+0x264/0x330 net/socket.c:1834
  __do_sys_connect net/socket.c:1845 [inline]
  __se_sys_connect net/socket.c:1842 [inline]
  __x64_sys_connect+0x73/0xb0 net/socket.c:1842
  do_syscall_64+0xfd/0x680 arch/x86/entry/common.c:301
  entry_SYSCALL_64_after_hwframe+0x49/0xbe
irq event stamp: 2272
hardirqs last  enabled at (2272): [<ffffffff810065f3>] trace_hardirqs_on_thunk+0x1a/0x1c
hardirqs last disabled at (2271): [<ffffffff8100660f>] trace_hardirqs_off_thunk+0x1a/0x1c
softirqs last  enabled at (1522): [<ffffffff87400654>] __do_softirq+0x654/0x94c kernel/softirq.c:320
softirqs last disabled at (2267): [<ffffffff81449010>] invoke_softirq kernel/softirq.c:374 [inline]
softirqs last disabled at (2267): [<ffffffff81449010>] irq_exit+0x180/0x1d0 kernel/softirq.c:414

other info that might help us debug this:
 Possible unsafe locking scenario:

       CPU0
       ----
  lock(slock-AF_AX25);
  <Interrupt>
    lock(slock-AF_AX25);

 *** DEADLOCK ***

1 lock held by blkid/26581:
 #0: 0000000010fd154d ((&ax25->dtimer)){+.-.}, at: lockdep_copy_map include/linux/lockdep.h:175 [inline]
 #0: 0000000010fd154d ((&ax25->dtimer)){+.-.}, at: call_timer_fn+0xe0/0x720 kernel/time/timer.c:1312

stack backtrace:
CPU: 1 PID: 26581 Comm: blkid Not tainted 5.2.0-rc3+ #32
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 print_usage_bug.cold+0x393/0x4a2 kernel/locking/lockdep.c:2935
 valid_state kernel/locking/lockdep.c:2948 [inline]
 mark_lock_irq kernel/locking/lockdep.c:3138 [inline]
 mark_lock+0xd46/0x1370 kernel/locking/lockdep.c:3513
 mark_irqflags kernel/locking/lockdep.c:3391 [inline]
 __lock_acquire+0x159f/0x5490 kernel/locking/lockdep.c:3745
 lock_acquire+0x16f/0x3f0 kernel/locking/lockdep.c:4303
 __raw_spin_lock include/linux/spinlock_api_smp.h:142 [inline]
 _raw_spin_lock+0x2f/0x40 kernel/locking/spinlock.c:151
 spin_lock include/linux/spinlock.h:338 [inline]
 ax25_destroy_timer+0x53/0xc0 net/ax25/af_ax25.c:275
 call_timer_fn+0x193/0x720 kernel/time/timer.c:1322
 expire_timers kernel/time/timer.c:1366 [inline]
 __run_timers kernel/time/timer.c:1685 [inline]
 __run_timers kernel/time/timer.c:1653 [inline]
 run_timer_softirq+0x66f/0x1740 kernel/time/timer.c:1698
 __do_softirq+0x25c/0x94c kernel/softirq.c:293
 invoke_softirq kernel/softirq.c:374 [inline]
 irq_exit+0x180/0x1d0 kernel/softirq.c:414
 exiting_irq arch/x86/include/asm/apic.h:536 [inline]
 smp_apic_timer_interrupt+0x13b/0x550 arch/x86/kernel/apic/apic.c:1068
 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:806
 </IRQ>
RIP: 0033:0x7f858d5c3232
Code: 8b 61 08 48 8b 84 24 d8 00 00 00 4c 89 44 24 28 48 8b ac 24 d0 00 00 00 4c 8b b4 24 e8 00 00 00 48 89 7c 24 68 48 89 4c 24 78 <48> 89 44 24 58 8b 84 24 e0 00 00 00 89 84 24 84 00 00 00 8b 84 24
RSP: 002b:00007ffcaf0cf5c0 EFLAGS: 00000206 ORIG_RAX: ffffffffffffff13
RAX: 00007f858d7d27a8 RBX: 00007f858d7d8820 RCX: 00007f858d3940d8
RDX: 00007ffcaf0cf798 RSI: 00000000f5e616f3 RDI: 00007f858d394fee
RBP: 0000000000000000 R08: 00007ffcaf0cf780 R09: 00007f858d7db480
R10: 0000000000000000 R11: 0000000009691a75 R12: 0000000000000005
R13: 00000000f5e616f3 R14: 0000000000000000 R15: 00007ffcaf0cf798

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ax25/ax25_route.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ax25/ax25_route.c b/net/ax25/ax25_route.c
index 66f74c85cf6b..66d54fc11831 100644
--- a/net/ax25/ax25_route.c
+++ b/net/ax25/ax25_route.c
@@ -429,9 +429,11 @@ int ax25_rt_autobind(ax25_cb *ax25, ax25_address *addr)
 	}
 
 	if (ax25->sk != NULL) {
+		local_bh_disable();
 		bh_lock_sock(ax25->sk);
 		sock_reset_flag(ax25->sk, SOCK_ZAPPED);
 		bh_unlock_sock(ax25->sk);
+		local_bh_enable();
 	}
 
 put:
-- 
2.20.1


From db87de0084da2c70a7609ceafc34652537b13286 Mon Sep 17 00:00:00 2001
From: Ivan Vecera <ivecera@redhat.com>
Date: Fri, 14 Jun 2019 17:48:36 +0200
Subject: [PATCH 02/17] be2net: Fix number of Rx queues used for flow hashing

[ Upstream commit 718f4a2537089ea41903bf357071306163bc7c04 ]

Number of Rx queues used for flow hashing returned by the driver is
incorrect and this bug prevents user to use the last Rx queue in
indirection table.

Let's say we have a NIC with 6 combined queues:

[root@sm-03 ~]# ethtool -l enp4s0f0
Channel parameters for enp4s0f0:
Pre-set maximums:
RX:             5
TX:             5
Other:          0
Combined:       6
Current hardware settings:
RX:             0
TX:             0
Other:          0
Combined:       6

Default indirection table maps all (6) queues equally but the driver
reports only 5 rings available.

[root@sm-03 ~]# ethtool -x enp4s0f0
RX flow hash indirection table for enp4s0f0 with 5 RX ring(s):
    0:      0     1     2     3     4     5     0     1
    8:      2     3     4     5     0     1     2     3
   16:      4     5     0     1     2     3     4     5
   24:      0     1     2     3     4     5     0     1
...

Now change indirection table somehow:

[root@sm-03 ~]# ethtool -X enp4s0f0 weight 1 1
[root@sm-03 ~]# ethtool -x enp4s0f0
RX flow hash indirection table for enp4s0f0 with 6 RX ring(s):
    0:      0     0     0     0     0     0     0     0
...
   64:      1     1     1     1     1     1     1     1
...

Now it is not possible to change mapping back to equal (default) state:

[root@sm-03 ~]# ethtool -X enp4s0f0 equal 6
Cannot set RX flow hash configuration: Invalid argument

Fixes: 594ad54a2c3b ("be2net: Add support for setting and getting rx flow hash options")
Reported-by: Tianhao <tizhao@redhat.com>
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/emulex/benet/be_ethtool.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c
index 3f6749fc889f..bfb16a474490 100644
--- a/drivers/net/ethernet/emulex/benet/be_ethtool.c
+++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c
@@ -1105,7 +1105,7 @@ static int be_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd,
 		cmd->data = be_get_rss_hash_opts(adapter, cmd->flow_type);
 		break;
 	case ETHTOOL_GRXRINGS:
-		cmd->data = adapter->num_rx_qs - 1;
+		cmd->data = adapter->num_rx_qs;
 		break;
 	default:
 		return -EINVAL;
-- 
2.20.1


From c16f2f5f5534676fe06eed4bc6e39a248f9b6125 Mon Sep 17 00:00:00 2001
From: Haiyang Zhang <haiyangz@microsoft.com>
Date: Thu, 13 Jun 2019 21:06:53 +0000
Subject: [PATCH 03/17] hv_netvsc: Set probe mode to sync

[ Upstream commit 9a33629ba6b26caebd73e3c581ba1e6068c696a7 ]

For better consistency of synthetic NIC names, we set the probe mode to
PROBE_FORCE_SYNCHRONOUS. So the names can be aligned with the vmbus
channel offer sequence.

Fixes: af0a5646cb8d ("use the new async probing feature for the hyperv drivers")
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/netvsc_drv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 9d699bd5f715..cf6b9b1771f1 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -2405,7 +2405,7 @@ static struct  hv_driver netvsc_drv = {
 	.probe = netvsc_probe,
 	.remove = netvsc_remove,
 	.driver = {
-		.probe_type = PROBE_PREFER_ASYNCHRONOUS,
+		.probe_type = PROBE_FORCE_SYNCHRONOUS,
 	},
 };
 
-- 
2.20.1


From 09f8ed943ed4627f54988181b5b8027d46a584a1 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 6 Jun 2019 14:32:34 -0700
Subject: [PATCH 04/17] ipv6: flowlabel: fl6_sock_lookup() must use
 atomic_inc_not_zero

[ Upstream commit 65a3c497c0e965a552008db8bc2653f62bc925a1 ]

Before taking a refcount, make sure the object is not already
scheduled for deletion.

Same fix is needed in ipv6_flowlabel_opt()

Fixes: 18367681a10b ("ipv6 flowlabel: Convert np->ipv6_fl_list to RCU.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_flowlabel.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index be5f3d7ceb96..f994f50e1516 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -254,9 +254,9 @@ struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label)
 	rcu_read_lock_bh();
 	for_each_sk_fl_rcu(np, sfl) {
 		struct ip6_flowlabel *fl = sfl->fl;
-		if (fl->label == label) {
+
+		if (fl->label == label && atomic_inc_not_zero(&fl->users)) {
 			fl->lastuse = jiffies;
-			atomic_inc(&fl->users);
 			rcu_read_unlock_bh();
 			return fl;
 		}
@@ -622,7 +622,8 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
 						goto done;
 					}
 					fl1 = sfl->fl;
-					atomic_inc(&fl1->users);
+					if (!atomic_inc_not_zero(&fl1->users))
+						fl1 = NULL;
 					break;
 				}
 			}
-- 
2.20.1


From a6401729c3ad726363f22145ac89ec02d9214922 Mon Sep 17 00:00:00 2001
From: Jeremy Sowden <jeremy@azazel.net>
Date: Sun, 16 Jun 2019 16:54:37 +0100
Subject: [PATCH 05/17] lapb: fixed leak of control-blocks.

[ Upstream commit 6be8e297f9bcea666ea85ac7a6cd9d52d6deaf92 ]

lapb_register calls lapb_create_cb, which initializes the control-
block's ref-count to one, and __lapb_insert_cb, which increments it when
adding the new block to the list of blocks.

lapb_unregister calls __lapb_remove_cb, which decrements the ref-count
when removing control-block from the list of blocks, and calls lapb_put
itself to decrement the ref-count before returning.

However, lapb_unregister also calls __lapb_devtostruct to look up the
right control-block for the given net_device, and __lapb_devtostruct
also bumps the ref-count, which means that when lapb_unregister returns
the ref-count is still 1 and the control-block is leaked.

Call lapb_put after __lapb_devtostruct to fix leak.

Reported-by: syzbot+afb980676c836b4a0afa@syzkaller.appspotmail.com
Signed-off-by: Jeremy Sowden <jeremy@azazel.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/lapb/lapb_iface.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/lapb/lapb_iface.c b/net/lapb/lapb_iface.c
index db6e0afe3a20..1740f852002e 100644
--- a/net/lapb/lapb_iface.c
+++ b/net/lapb/lapb_iface.c
@@ -182,6 +182,7 @@ int lapb_unregister(struct net_device *dev)
 	lapb = __lapb_devtostruct(dev);
 	if (!lapb)
 		goto out;
+	lapb_put(lapb);
 
 	lapb_stop_t1timer(lapb);
 	lapb_stop_t2timer(lapb);
-- 
2.20.1


From 2ee042e2e9ffee7eb757fcf1f2ef8c48cd757974 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 15 Jun 2019 16:28:48 -0700
Subject: [PATCH 06/17] neigh: fix use-after-free read in pneigh_get_next

[ Upstream commit f3e92cb8e2eb8c27d109e6fd73d3a69a8c09e288 ]

Nine years ago, I added RCU handling to neighbours, not pneighbours.
(pneigh are not commonly used)

Unfortunately I missed that /proc dump operations would use a
common entry and exit point : neigh_seq_start() and neigh_seq_stop()

We need to read_lock(tbl->lock) or risk use-after-free while
iterating the pneigh structures.

We might later convert pneigh to RCU and revert this patch.

sysbot reported :

BUG: KASAN: use-after-free in pneigh_get_next.isra.0+0x24b/0x280 net/core/neighbour.c:3158
Read of size 8 at addr ffff888097f2a700 by task syz-executor.0/9825

CPU: 1 PID: 9825 Comm: syz-executor.0 Not tainted 5.2.0-rc4+ #32
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 print_address_description.cold+0x7c/0x20d mm/kasan/report.c:188
 __kasan_report.cold+0x1b/0x40 mm/kasan/report.c:317
 kasan_report+0x12/0x20 mm/kasan/common.c:614
 __asan_report_load8_noabort+0x14/0x20 mm/kasan/generic_report.c:132
 pneigh_get_next.isra.0+0x24b/0x280 net/core/neighbour.c:3158
 neigh_seq_next+0xdb/0x210 net/core/neighbour.c:3240
 seq_read+0x9cf/0x1110 fs/seq_file.c:258
 proc_reg_read+0x1fc/0x2c0 fs/proc/inode.c:221
 do_loop_readv_writev fs/read_write.c:714 [inline]
 do_loop_readv_writev fs/read_write.c:701 [inline]
 do_iter_read+0x4a4/0x660 fs/read_write.c:935
 vfs_readv+0xf0/0x160 fs/read_write.c:997
 kernel_readv fs/splice.c:359 [inline]
 default_file_splice_read+0x475/0x890 fs/splice.c:414
 do_splice_to+0x127/0x180 fs/splice.c:877
 splice_direct_to_actor+0x2d2/0x970 fs/splice.c:954
 do_splice_direct+0x1da/0x2a0 fs/splice.c:1063
 do_sendfile+0x597/0xd00 fs/read_write.c:1464
 __do_sys_sendfile64 fs/read_write.c:1525 [inline]
 __se_sys_sendfile64 fs/read_write.c:1511 [inline]
 __x64_sys_sendfile64+0x1dd/0x220 fs/read_write.c:1511
 do_syscall_64+0xfd/0x680 arch/x86/entry/common.c:301
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x4592c9
Code: fd b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 cb b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f4aab51dc78 EFLAGS: 00000246 ORIG_RAX: 0000000000000028
RAX: ffffffffffffffda RBX: 0000000000000004 RCX: 00000000004592c9
RDX: 0000000000000000 RSI: 0000000000000004 RDI: 0000000000000005
RBP: 000000000075bf20 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000080000000 R11: 0000000000000246 R12: 00007f4aab51e6d4
R13: 00000000004c689d R14: 00000000004db828 R15: 00000000ffffffff

Allocated by task 9827:
 save_stack+0x23/0x90 mm/kasan/common.c:71
 set_track mm/kasan/common.c:79 [inline]
 __kasan_kmalloc mm/kasan/common.c:489 [inline]
 __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:462
 kasan_kmalloc+0x9/0x10 mm/kasan/common.c:503
 __do_kmalloc mm/slab.c:3660 [inline]
 __kmalloc+0x15c/0x740 mm/slab.c:3669
 kmalloc include/linux/slab.h:552 [inline]
 pneigh_lookup+0x19c/0x4a0 net/core/neighbour.c:731
 arp_req_set_public net/ipv4/arp.c:1010 [inline]
 arp_req_set+0x613/0x720 net/ipv4/arp.c:1026
 arp_ioctl+0x652/0x7f0 net/ipv4/arp.c:1226
 inet_ioctl+0x2a0/0x340 net/ipv4/af_inet.c:926
 sock_do_ioctl+0xd8/0x2f0 net/socket.c:1043
 sock_ioctl+0x3ed/0x780 net/socket.c:1194
 vfs_ioctl fs/ioctl.c:46 [inline]
 file_ioctl fs/ioctl.c:509 [inline]
 do_vfs_ioctl+0xd5f/0x1380 fs/ioctl.c:696
 ksys_ioctl+0xab/0xd0 fs/ioctl.c:713
 __do_sys_ioctl fs/ioctl.c:720 [inline]
 __se_sys_ioctl fs/ioctl.c:718 [inline]
 __x64_sys_ioctl+0x73/0xb0 fs/ioctl.c:718
 do_syscall_64+0xfd/0x680 arch/x86/entry/common.c:301
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Freed by task 9824:
 save_stack+0x23/0x90 mm/kasan/common.c:71
 set_track mm/kasan/common.c:79 [inline]
 __kasan_slab_free+0x102/0x150 mm/kasan/common.c:451
 kasan_slab_free+0xe/0x10 mm/kasan/common.c:459
 __cache_free mm/slab.c:3432 [inline]
 kfree+0xcf/0x220 mm/slab.c:3755
 pneigh_ifdown_and_unlock net/core/neighbour.c:812 [inline]
 __neigh_ifdown+0x236/0x2f0 net/core/neighbour.c:356
 neigh_ifdown+0x20/0x30 net/core/neighbour.c:372
 arp_ifdown+0x1d/0x21 net/ipv4/arp.c:1274
 inetdev_destroy net/ipv4/devinet.c:319 [inline]
 inetdev_event+0xa14/0x11f0 net/ipv4/devinet.c:1544
 notifier_call_chain+0xc2/0x230 kernel/notifier.c:95
 __raw_notifier_call_chain kernel/notifier.c:396 [inline]
 raw_notifier_call_chain+0x2e/0x40 kernel/notifier.c:403
 call_netdevice_notifiers_info+0x3f/0x90 net/core/dev.c:1749
 call_netdevice_notifiers_extack net/core/dev.c:1761 [inline]
 call_netdevice_notifiers net/core/dev.c:1775 [inline]
 rollback_registered_many+0x9b9/0xfc0 net/core/dev.c:8178
 rollback_registered+0x109/0x1d0 net/core/dev.c:8220
 unregister_netdevice_queue net/core/dev.c:9267 [inline]
 unregister_netdevice_queue+0x1ee/0x2c0 net/core/dev.c:9260
 unregister_netdevice include/linux/netdevice.h:2631 [inline]
 __tun_detach+0xd8a/0x1040 drivers/net/tun.c:724
 tun_detach drivers/net/tun.c:741 [inline]
 tun_chr_close+0xe0/0x180 drivers/net/tun.c:3451
 __fput+0x2ff/0x890 fs/file_table.c:280
 ____fput+0x16/0x20 fs/file_table.c:313
 task_work_run+0x145/0x1c0 kernel/task_work.c:113
 tracehook_notify_resume include/linux/tracehook.h:185 [inline]
 exit_to_usermode_loop+0x273/0x2c0 arch/x86/entry/common.c:168
 prepare_exit_to_usermode arch/x86/entry/common.c:199 [inline]
 syscall_return_slowpath arch/x86/entry/common.c:279 [inline]
 do_syscall_64+0x58e/0x680 arch/x86/entry/common.c:304
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

The buggy address belongs to the object at ffff888097f2a700
 which belongs to the cache kmalloc-64 of size 64
The buggy address is located 0 bytes inside of
 64-byte region [ffff888097f2a700, ffff888097f2a740)
The buggy address belongs to the page:
page:ffffea00025fca80 refcount:1 mapcount:0 mapping:ffff8880aa400340 index:0x0
flags: 0x1fffc0000000200(slab)
raw: 01fffc0000000200 ffffea000250d548 ffffea00025726c8 ffff8880aa400340
raw: 0000000000000000 ffff888097f2a000 0000000100000020 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff888097f2a600: 00 00 00 00 00 00 00 00 fc fc fc fc fc fc fc fc
 ffff888097f2a680: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
>ffff888097f2a700: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
                   ^
 ffff888097f2a780: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
 ffff888097f2a800: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc

Fixes: 767e97e1e0db ("neigh: RCU conversion of struct neighbour")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 4e4ac77c6816..cd9e991f21d7 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2751,6 +2751,7 @@ static void *neigh_get_idx_any(struct seq_file *seq, loff_t *pos)
 }
 
 void *neigh_seq_start(struct seq_file *seq, loff_t *pos, struct neigh_table *tbl, unsigned int neigh_seq_flags)
+	__acquires(tbl->lock)
 	__acquires(rcu_bh)
 {
 	struct neigh_seq_state *state = seq->private;
@@ -2761,6 +2762,7 @@ void *neigh_seq_start(struct seq_file *seq, loff_t *pos, struct neigh_table *tbl
 
 	rcu_read_lock_bh();
 	state->nht = rcu_dereference_bh(tbl->nht);
+	read_lock(&tbl->lock);
 
 	return *pos ? neigh_get_idx_any(seq, pos) : SEQ_START_TOKEN;
 }
@@ -2794,8 +2796,13 @@ void *neigh_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 EXPORT_SYMBOL(neigh_seq_next);
 
 void neigh_seq_stop(struct seq_file *seq, void *v)
+	__releases(tbl->lock)
 	__releases(rcu_bh)
 {
+	struct neigh_seq_state *state = seq->private;
+	struct neigh_table *tbl = state->tbl;
+
+	read_unlock(&tbl->lock);
 	rcu_read_unlock_bh();
 }
 EXPORT_SYMBOL(neigh_seq_stop);
-- 
2.20.1


From 4227ddfcd5c6fc13ef992bd907b58eb0f456f688 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Fri, 14 Jun 2019 00:25:20 +0200
Subject: [PATCH 07/17] net: dsa: rtl8366: Fix up VLAN filtering

[ Upstream commit 760c80b70bed2cd01630e8595d1bbde910339f31 ]

We get this regression when using RTL8366RB as part of a bridge
with OpenWrt:

WARNING: CPU: 0 PID: 1347 at net/switchdev/switchdev.c:291
	 switchdev_port_attr_set_now+0x80/0xa4
lan0: Commit of attribute (id=7) failed.
(...)
realtek-smi switch lan0: failed to initialize vlan filtering on this port

This is because it is trying to disable VLAN filtering
on VLAN0, as we have forgot to add 1 to the port number
to get the right VLAN in rtl8366_vlan_filtering(): when
we initialize the VLAN we associate VLAN1 with port 0,
VLAN2 with port 1 etc, so we need to add 1 to the port
offset.

Fixes: d8652956cf37 ("net: dsa: realtek-smi: Add Realtek SMI driver")
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/rtl8366.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/dsa/rtl8366.c b/drivers/net/dsa/rtl8366.c
index 6dedd43442cc..35b767baf21f 100644
--- a/drivers/net/dsa/rtl8366.c
+++ b/drivers/net/dsa/rtl8366.c
@@ -307,7 +307,8 @@ int rtl8366_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering)
 	struct rtl8366_vlan_4k vlan4k;
 	int ret;
 
-	if (!smi->ops->is_vlan_valid(smi, port))
+	/* Use VLAN nr port + 1 since VLAN0 is not valid */
+	if (!smi->ops->is_vlan_valid(smi, port + 1))
 		return -EINVAL;
 
 	dev_info(smi->dev, "%s filtering on port %d\n",
@@ -318,12 +319,12 @@ int rtl8366_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering)
 	 * The hardware support filter ID (FID) 0..7, I have no clue how to
 	 * support this in the driver when the callback only says on/off.
 	 */
-	ret = smi->ops->get_vlan_4k(smi, port, &vlan4k);
+	ret = smi->ops->get_vlan_4k(smi, port + 1, &vlan4k);
 	if (ret)
 		return ret;
 
 	/* Just set the filter to FID 1 for now then */
-	ret = rtl8366_set_vlan(smi, port,
+	ret = rtl8366_set_vlan(smi, port + 1,
 			       vlan4k.member,
 			       vlan4k.untag,
 			       1);
-- 
2.20.1


From b442ed82b0d1b7e10b21c923e71cbcbeb45cb30e Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Sun, 9 Jun 2019 23:26:21 +0900
Subject: [PATCH 08/17] net: openvswitch: do not free vport if
 register_netdevice() is failed.

[ Upstream commit 309b66970ee2abf721ecd0876a48940fa0b99a35 ]

In order to create an internal vport, internal_dev_create() is used and
that calls register_netdevice() internally.
If register_netdevice() fails, it calls dev->priv_destructor() to free
private data of netdev. actually, a private data of this is a vport.

Hence internal_dev_create() should not free and use a vport after failure
of register_netdevice().

Test command
    ovs-dpctl add-dp bonding_masters

Splat looks like:
[ 1035.667767] kasan: GPF could be caused by NULL-ptr deref or user memory access
[ 1035.675958] general protection fault: 0000 [#1] SMP DEBUG_PAGEALLOC KASAN PTI
[ 1035.676916] CPU: 1 PID: 1028 Comm: ovs-vswitchd Tainted: G    B             5.2.0-rc3+ #240
[ 1035.676916] RIP: 0010:internal_dev_create+0x2e5/0x4e0 [openvswitch]
[ 1035.676916] Code: 48 c1 ea 03 80 3c 02 00 0f 85 9f 01 00 00 4c 8b 23 48 b8 00 00 00 00 00 fc ff df 49 8d bc 24 60 05 00 00 48 89 fa 48 c1 ea 03 <80> 3c 02 00 0f 85 86 01 00 00 49 8b bc 24 60 05 00 00 e8 e4 68 f4
[ 1035.713720] RSP: 0018:ffff88810dcb7578 EFLAGS: 00010206
[ 1035.713720] RAX: dffffc0000000000 RBX: ffff88810d13fe08 RCX: ffffffff84297704
[ 1035.713720] RDX: 00000000000000ac RSI: 0000000000000000 RDI: 0000000000000560
[ 1035.713720] RBP: 00000000ffffffef R08: fffffbfff0d3b881 R09: fffffbfff0d3b881
[ 1035.713720] R10: 0000000000000001 R11: fffffbfff0d3b880 R12: 0000000000000000
[ 1035.768776] R13: 0000607ee460b900 R14: ffff88810dcb7690 R15: ffff88810dcb7698
[ 1035.777709] FS:  00007f02095fc980(0000) GS:ffff88811b400000(0000) knlGS:0000000000000000
[ 1035.777709] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 1035.777709] CR2: 00007ffdf01d2f28 CR3: 0000000108258000 CR4: 00000000001006e0
[ 1035.777709] Call Trace:
[ 1035.777709]  ovs_vport_add+0x267/0x4f0 [openvswitch]
[ 1035.777709]  new_vport+0x15/0x1e0 [openvswitch]
[ 1035.777709]  ovs_vport_cmd_new+0x567/0xd10 [openvswitch]
[ 1035.777709]  ? ovs_dp_cmd_dump+0x490/0x490 [openvswitch]
[ 1035.777709]  ? __kmalloc+0x131/0x2e0
[ 1035.777709]  ? genl_family_rcv_msg+0xa54/0x1030
[ 1035.777709]  genl_family_rcv_msg+0x63a/0x1030
[ 1035.777709]  ? genl_unregister_family+0x630/0x630
[ 1035.841681]  ? debug_show_all_locks+0x2d0/0x2d0
[ ... ]

Fixes: cf124db566e6 ("net: Fix inconsistent teardown and release of private netdev state.")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Reviewed-by: Greg Rose <gvrose8192@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/vport-internal_dev.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c
index bb95c43aae76..5a304cfc8423 100644
--- a/net/openvswitch/vport-internal_dev.c
+++ b/net/openvswitch/vport-internal_dev.c
@@ -169,7 +169,9 @@ static struct vport *internal_dev_create(const struct vport_parms *parms)
 {
 	struct vport *vport;
 	struct internal_dev *internal_dev;
+	struct net_device *dev;
 	int err;
+	bool free_vport = true;
 
 	vport = ovs_vport_alloc(0, &ovs_internal_vport_ops, parms);
 	if (IS_ERR(vport)) {
@@ -177,8 +179,9 @@ static struct vport *internal_dev_create(const struct vport_parms *parms)
 		goto error;
 	}
 
-	vport->dev = alloc_netdev(sizeof(struct internal_dev),
-				  parms->name, NET_NAME_USER, do_setup);
+	dev = alloc_netdev(sizeof(struct internal_dev),
+			   parms->name, NET_NAME_USER, do_setup);
+	vport->dev = dev;
 	if (!vport->dev) {
 		err = -ENOMEM;
 		goto error_free_vport;
@@ -199,8 +202,10 @@ static struct vport *internal_dev_create(const struct vport_parms *parms)
 
 	rtnl_lock();
 	err = register_netdevice(vport->dev);
-	if (err)
+	if (err) {
+		free_vport = false;
 		goto error_unlock;
+	}
 
 	dev_set_promiscuity(vport->dev, 1);
 	rtnl_unlock();
@@ -210,11 +215,12 @@ static struct vport *internal_dev_create(const struct vport_parms *parms)
 
 error_unlock:
 	rtnl_unlock();
-	free_percpu(vport->dev->tstats);
+	free_percpu(dev->tstats);
 error_free_netdev:
-	free_netdev(vport->dev);
+	free_netdev(dev);
 error_free_vport:
-	ovs_vport_free(vport);
+	if (free_vport)
+		ovs_vport_free(vport);
 error:
 	return ERR_PTR(err);
 }
-- 
2.20.1


From b9b7ff883f389c6d4ebdd2e914a917087973a0bb Mon Sep 17 00:00:00 2001
From: Ioana Ciornei <ioana.ciornei@nxp.com>
Date: Thu, 13 Jun 2019 09:37:51 +0300
Subject: [PATCH 09/17] net: phylink: set the autoneg state in
 phylink_phy_change

[ Upstream commit ef7bfa84725d891bbdb88707ed55b2cbf94942bb ]

The phy_state field of phylink should carry only valid information
especially when this can be passed to the .mac_config callback.
Update the an_enabled field with the autoneg state in the
phylink_phy_change function.

Fixes: 9525ae83959b ("phylink: add phylink infrastructure")
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phylink.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index f6e70f2dfd12..c5a509129ae6 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -662,6 +662,7 @@ static void phylink_phy_change(struct phy_device *phydev, bool up,
 		pl->phy_state.pause |= MLO_PAUSE_ASYM;
 	pl->phy_state.interface = phydev->interface;
 	pl->phy_state.link = up;
+	pl->phy_state.an_enabled = phydev->autoneg;
 	mutex_unlock(&pl->state_mutex);
 
 	phylink_run_resolve(pl);
-- 
2.20.1


From 8e2b739ed8c7235093eb9812f30b154b9836b5ed Mon Sep 17 00:00:00 2001
From: Young Xiao <92siuyang@gmail.com>
Date: Fri, 14 Jun 2019 15:13:02 +0800
Subject: [PATCH 10/17] nfc: Ensure presence of required attributes in the
 deactivate_target handler

[ Upstream commit 385097a3675749cbc9e97c085c0e5dfe4269ca51 ]

Check that the NFC_ATTR_TARGET_INDEX attributes (in addition to
NFC_ATTR_DEVICE_INDEX) are provided by the netlink client prior to
accessing them. This prevents potential unhandled NULL pointer dereference
exceptions which can be triggered by malicious user-mode programs,
if they omit one or both of these attributes.

Signed-off-by: Young Xiao <92siuyang@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/nfc/netlink.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index 376181cc1def..9f2875efb4ac 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -922,7 +922,8 @@ static int nfc_genl_deactivate_target(struct sk_buff *skb,
 	u32 device_idx, target_idx;
 	int rc;
 
-	if (!info->attrs[NFC_ATTR_DEVICE_INDEX])
+	if (!info->attrs[NFC_ATTR_DEVICE_INDEX] ||
+	    !info->attrs[NFC_ATTR_TARGET_INDEX])
 		return -EINVAL;
 
 	device_idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]);
-- 
2.20.1


From 94132f5cbb07fcffc869d3b1184ec9a8535ad49b Mon Sep 17 00:00:00 2001
From: Neil Horman <nhorman@tuxdriver.com>
Date: Thu, 13 Jun 2019 06:35:59 -0400
Subject: [PATCH 11/17] sctp: Free cookie before we memdup a new one

[ Upstream commit ce950f1050cece5e406a5cde723c69bba60e1b26 ]

Based on comments from Xin, even after fixes for our recent syzbot
report of cookie memory leaks, its possible to get a resend of an INIT
chunk which would lead to us leaking cookie memory.

To ensure that we don't leak cookie memory, free any previously
allocated cookie first.

Change notes
v1->v2
update subsystem tag in subject (davem)
repeat kfree check for peer_random and peer_hmacs (xin)

v2->v3
net->sctp
also free peer_chunks

v3->v4
fix subject tags

v4->v5
remove cut line

Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Reported-by: syzbot+f7e9153b037eac9b1df8@syzkaller.appspotmail.com
CC: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
CC: Xin Long <lucien.xin@gmail.com>
CC: "David S. Miller" <davem@davemloft.net>
CC: netdev@vger.kernel.org
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sm_make_chunk.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index ae65a1cfa596..fb546b2d67ca 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -2600,6 +2600,8 @@ static int sctp_process_param(struct sctp_association *asoc,
 	case SCTP_PARAM_STATE_COOKIE:
 		asoc->peer.cookie_len =
 			ntohs(param.p->length) - sizeof(struct sctp_paramhdr);
+		if (asoc->peer.cookie)
+			kfree(asoc->peer.cookie);
 		asoc->peer.cookie = kmemdup(param.cookie->body, asoc->peer.cookie_len, gfp);
 		if (!asoc->peer.cookie)
 			retval = 0;
@@ -2664,6 +2666,8 @@ static int sctp_process_param(struct sctp_association *asoc,
 			goto fall_through;
 
 		/* Save peer's random parameter */
+		if (asoc->peer.peer_random)
+			kfree(asoc->peer.peer_random);
 		asoc->peer.peer_random = kmemdup(param.p,
 					    ntohs(param.p->length), gfp);
 		if (!asoc->peer.peer_random) {
@@ -2677,6 +2681,8 @@ static int sctp_process_param(struct sctp_association *asoc,
 			goto fall_through;
 
 		/* Save peer's HMAC list */
+		if (asoc->peer.peer_hmacs)
+			kfree(asoc->peer.peer_hmacs);
 		asoc->peer.peer_hmacs = kmemdup(param.p,
 					    ntohs(param.p->length), gfp);
 		if (!asoc->peer.peer_hmacs) {
@@ -2692,6 +2698,8 @@ static int sctp_process_param(struct sctp_association *asoc,
 		if (!ep->auth_enable)
 			goto fall_through;
 
+		if (asoc->peer.peer_chunks)
+			kfree(asoc->peer.peer_chunks);
 		asoc->peer.peer_chunks = kmemdup(param.p,
 					    ntohs(param.p->length), gfp);
 		if (!asoc->peer.peer_chunks)
-- 
2.20.1


From b78413f3002c01789bbdfb3b08b4d8cf826a3d4d Mon Sep 17 00:00:00 2001
From: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Date: Tue, 11 Jun 2019 17:38:37 +0200
Subject: [PATCH 12/17] sunhv: Fix device naming inconsistency between
 sunhv_console and sunhv_reg

[ Upstream commit 07a6d63eb1b54b5fb38092780fe618dfe1d96e23 ]

In d5a2aa24, the name in struct console sunhv_console was changed from "ttyS"
to "ttyHV" while the name in struct uart_ops sunhv_pops remained unchanged.

This results in the hypervisor console device to be listed as "ttyHV0" under
/proc/consoles while the device node is still named "ttyS0":

root@osaka:~# cat /proc/consoles
ttyHV0               -W- (EC p  )    4:64
tty0                 -WU (E     )    4:1
root@osaka:~# readlink /sys/dev/char/4:64
../../devices/root/f02836f0/f0285690/tty/ttyS0
root@osaka:~#

This means that any userland code which tries to determine the name of the
device file of the hypervisor console device can not rely on the information
provided by /proc/consoles. In particular, booting current versions of debian-
installer inside a SPARC LDOM will fail with the installer unable to determine
the console device.

After renaming the device in struct uart_ops sunhv_pops to "ttyHV" as well,
the inconsistency is fixed and it is possible again to determine the name
of the device file of the hypervisor console device by reading the contents
of /proc/console:

root@osaka:~# cat /proc/consoles
ttyHV0               -W- (EC p  )    4:64
tty0                 -WU (E     )    4:1
root@osaka:~# readlink /sys/dev/char/4:64
../../devices/root/f02836f0/f0285690/tty/ttyHV0
root@osaka:~#

With this change, debian-installer works correctly when installing inside
a SPARC LDOM.

Signed-off-by: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/tty/serial/sunhv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/tty/serial/sunhv.c b/drivers/tty/serial/sunhv.c
index 63e34d868de8..f8503f8fc44e 100644
--- a/drivers/tty/serial/sunhv.c
+++ b/drivers/tty/serial/sunhv.c
@@ -397,7 +397,7 @@ static const struct uart_ops sunhv_pops = {
 static struct uart_driver sunhv_reg = {
 	.owner			= THIS_MODULE,
 	.driver_name		= "sunhv",
-	.dev_name		= "ttyS",
+	.dev_name		= "ttyHV",
 	.major			= TTY_MAJOR,
 };
 
-- 
2.20.1


From 9824911a374c0c2166aedf29689331964a9a195e Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 16 Jun 2019 17:24:07 +0800
Subject: [PATCH 13/17] tipc: purge deferredq list for each grp member in
 tipc_group_delete

[ Upstream commit 5cf02612b33f104fe1015b2dfaf1758ad3675588 ]

Syzbot reported a memleak caused by grp members' deferredq list not
purged when the grp is be deleted.

The issue occurs when more(msg_grp_bc_seqno(hdr), m->bc_rcv_nxt) in
tipc_group_filter_msg() and the skb will stay in deferredq.

So fix it by calling __skb_queue_purge for each member's deferredq
in tipc_group_delete() when a tipc sk leaves the grp.

Fixes: b87a5ea31c93 ("tipc: guarantee group unicast doesn't bypass group broadcast")
Reported-by: syzbot+78fbe679c8ca8d264a8d@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/group.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/tipc/group.c b/net/tipc/group.c
index 06fee142f09f..3ee93b5c19b6 100644
--- a/net/tipc/group.c
+++ b/net/tipc/group.c
@@ -218,6 +218,7 @@ void tipc_group_delete(struct net *net, struct tipc_group *grp)
 
 	rbtree_postorder_for_each_entry_safe(m, tmp, tree, tree_node) {
 		tipc_group_proto_xmit(grp, m, GRP_LEAVE_MSG, &xmitq);
+		__skb_queue_purge(&m->deferredq);
 		list_del(&m->list);
 		kfree(m);
 	}
-- 
2.20.1


From f1e1b3da58c81024d9ff02d82201290057a846db Mon Sep 17 00:00:00 2001
From: Stephen Barber <smbarber@chromium.org>
Date: Fri, 14 Jun 2019 23:42:37 -0700
Subject: [PATCH 14/17] vsock/virtio: set SOCK_DONE on peer shutdown

[ Upstream commit 42f5cda5eaf4396a939ae9bb43bb8d1d09c1b15c ]

Set the SOCK_DONE flag to match the TCP_CLOSING state when a peer has
shut down and there is nothing left to read.

This fixes the following bug:
1) Peer sends SHUTDOWN(RDWR).
2) Socket enters TCP_CLOSING but SOCK_DONE is not set.
3) read() returns -ENOTCONN until close() is called, then returns 0.

Signed-off-by: Stephen Barber <smbarber@chromium.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/vmw_vsock/virtio_transport_common.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index f3f3d06cb6d8..e30f53728725 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -871,8 +871,10 @@ virtio_transport_recv_connected(struct sock *sk,
 		if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SHUTDOWN_SEND)
 			vsk->peer_shutdown |= SEND_SHUTDOWN;
 		if (vsk->peer_shutdown == SHUTDOWN_MASK &&
-		    vsock_stream_has_data(vsk) <= 0)
+		    vsock_stream_has_data(vsk) <= 0) {
+			sock_set_flag(sk, SOCK_DONE);
 			sk->sk_state = TCP_CLOSING;
+		}
 		if (le32_to_cpu(pkt->hdr.flags))
 			sk->sk_state_change(sk);
 		break;
-- 
2.20.1


From f17e451c782ca29f9ddf975cee90d71034dcebeb Mon Sep 17 00:00:00 2001
From: Alaa Hleihel <alaa@mellanox.com>
Date: Sun, 19 May 2019 11:11:49 +0300
Subject: [PATCH 15/17] net/mlx5: Avoid reloading already removed devices

Prior to reloading a device we must first verify that it was not already
removed. Otherwise, the attempt to remove the device will do nothing, and
in that case we will end up proceeding with adding an new device that no
one was expecting to remove, leaving behind used resources such as EQs that
causes a failure to destroy comp EQs and syndrome (0x30f433).

Fix that by making sure that we try to remove and add a device (based on a
protocol) only if the device is already added.

Fixes: c5447c70594b ("net/mlx5: E-Switch, Reload IB interface when switching devlink modes")
Signed-off-by: Alaa Hleihel <alaa@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/dev.c | 25 +++++++++++++++++--
 1 file changed, 23 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
index 37ba7c78859d..1c225be9c7db 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -342,11 +342,32 @@ void mlx5_unregister_interface(struct mlx5_interface *intf)
 }
 EXPORT_SYMBOL(mlx5_unregister_interface);
 
+/* Must be called with intf_mutex held */
+static bool mlx5_has_added_dev_by_protocol(struct mlx5_core_dev *mdev, int protocol)
+{
+	struct mlx5_device_context *dev_ctx;
+	struct mlx5_interface *intf;
+	bool found = false;
+
+	list_for_each_entry(intf, &intf_list, list) {
+		if (intf->protocol == protocol) {
+			dev_ctx = mlx5_get_device(intf, &mdev->priv);
+			if (dev_ctx && test_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state))
+				found = true;
+			break;
+		}
+	}
+
+	return found;
+}
+
 void mlx5_reload_interface(struct mlx5_core_dev *mdev, int protocol)
 {
 	mutex_lock(&mlx5_intf_mutex);
-	mlx5_remove_dev_by_protocol(mdev, protocol);
-	mlx5_add_dev_by_protocol(mdev, protocol);
+	if (mlx5_has_added_dev_by_protocol(mdev, protocol)) {
+		mlx5_remove_dev_by_protocol(mdev, protocol);
+		mlx5_add_dev_by_protocol(mdev, protocol);
+	}
 	mutex_unlock(&mlx5_intf_mutex);
 }
 
-- 
2.20.1


From 7eb939c0d74ca049ba5ef688f6050f511a4f5cba Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Tue, 11 Jun 2019 11:51:42 +0200
Subject: [PATCH 16/17] net: mvpp2: prs: Fix parser range for VID filtering

[ Upstream commit 46b0090a6636cf34c0e856f15dd03e15ba4cdda6 ]

VID filtering is implemented in the Header Parser, with one range of 11
vids being assigned for each no-loopback port.

Make sure we use the per-port range when looking for existing entries in
the Parser.

Since we used a global range instead of a per-port one, this causes VIDs
to be removed from the whitelist from all ports of the same PPv2
instance.

Fixes: 56beda3db602 ("net: mvpp2: Add hardware offloading for VLAN filtering")
Suggested-by: Yuri Chipchev <yuric@marvell.com>
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
index 392fd895f278..e0da4db3bf56 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
@@ -1905,8 +1905,7 @@ static int mvpp2_prs_ip6_init(struct mvpp2 *priv)
 }
 
 /* Find tcam entry with matched pair <vid,port> */
-static int mvpp2_prs_vid_range_find(struct mvpp2 *priv, int pmap, u16 vid,
-				    u16 mask)
+static int mvpp2_prs_vid_range_find(struct mvpp2_port *port, u16 vid, u16 mask)
 {
 	unsigned char byte[2], enable[2];
 	struct mvpp2_prs_entry pe;
@@ -1914,13 +1913,13 @@ static int mvpp2_prs_vid_range_find(struct mvpp2 *priv, int pmap, u16 vid,
 	int tid;
 
 	/* Go through the all entries with MVPP2_PRS_LU_VID */
-	for (tid = MVPP2_PE_VID_FILT_RANGE_START;
-	     tid <= MVPP2_PE_VID_FILT_RANGE_END; tid++) {
-		if (!priv->prs_shadow[tid].valid ||
-		    priv->prs_shadow[tid].lu != MVPP2_PRS_LU_VID)
+	for (tid = MVPP2_PRS_VID_PORT_FIRST(port->id);
+	     tid <= MVPP2_PRS_VID_PORT_LAST(port->id); tid++) {
+		if (!port->priv->prs_shadow[tid].valid ||
+		    port->priv->prs_shadow[tid].lu != MVPP2_PRS_LU_VID)
 			continue;
 
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		mvpp2_prs_init_from_hw(port->priv, &pe, tid);
 
 		mvpp2_prs_tcam_data_byte_get(&pe, 2, &byte[0], &enable[0]);
 		mvpp2_prs_tcam_data_byte_get(&pe, 3, &byte[1], &enable[1]);
@@ -1950,7 +1949,7 @@ int mvpp2_prs_vid_entry_add(struct mvpp2_port *port, u16 vid)
 	memset(&pe, 0, sizeof(pe));
 
 	/* Scan TCAM and see if entry with this <vid,port> already exist */
-	tid = mvpp2_prs_vid_range_find(priv, (1 << port->id), vid, mask);
+	tid = mvpp2_prs_vid_range_find(port, vid, mask);
 
 	reg_val = mvpp2_read(priv, MVPP2_MH_REG(port->id));
 	if (reg_val & MVPP2_DSA_EXTENDED)
@@ -2008,7 +2007,7 @@ void mvpp2_prs_vid_entry_remove(struct mvpp2_port *port, u16 vid)
 	int tid;
 
 	/* Scan TCAM and see if entry with this <vid,port> already exist */
-	tid = mvpp2_prs_vid_range_find(priv, (1 << port->id), vid, 0xfff);
+	tid = mvpp2_prs_vid_range_find(port, vid, 0xfff);
 
 	/* No such entry */
 	if (tid < 0)
-- 
2.20.1


From 78a8f55dfc1905606803b957a93442121e211f67 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Tue, 11 Jun 2019 11:51:43 +0200
Subject: [PATCH 17/17] net: mvpp2: prs: Use the correct helpers when removing
 all VID filters

[ Upstream commit 6b7a3430c163455cf8a514d636bda52b04654972 ]

When removing all VID filters, the mvpp2_prs_vid_entry_remove would be
called with the TCAM id incorrectly used as a VID, causing the wrong
TCAM entries to be invalidated.

Fix this by directly invalidating entries in the VID range.

Fixes: 56beda3db602 ("net: mvpp2: Add hardware offloading for VLAN filtering")
Suggested-by: Yuri Chipchev <yuric@marvell.com>
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
index e0da4db3bf56..ae2240074d8e 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
@@ -2025,8 +2025,10 @@ void mvpp2_prs_vid_remove_all(struct mvpp2_port *port)
 
 	for (tid = MVPP2_PRS_VID_PORT_FIRST(port->id);
 	     tid <= MVPP2_PRS_VID_PORT_LAST(port->id); tid++) {
-		if (priv->prs_shadow[tid].valid)
-			mvpp2_prs_vid_entry_remove(port, tid);
+		if (priv->prs_shadow[tid].valid) {
+			mvpp2_prs_hw_inv(priv, tid);
+			priv->prs_shadow[tid].valid = false;
+		}
 	}
 }
 
-- 
2.20.1


[-- Attachment #3: net_51.mbox --]
[-- Type: Application/Octet-Stream, Size: 74633 bytes --]

From ef388376cf5e75d5ce8653d58e53b8972bdcbb0c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 15 Jun 2019 16:40:52 -0700
Subject: [PATCH 01/31] ax25: fix inconsistent lock state in ax25_destroy_timer

[ Upstream commit d4d5d8e83c9616aeef28a2869cea49cc3fb35526 ]

Before thread in process context uses bh_lock_sock()
we must disable bh.

sysbot reported :

WARNING: inconsistent lock state
5.2.0-rc3+ #32 Not tainted

inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage.
blkid/26581 [HC0[0]:SC1[1]:HE1:SE0] takes:
00000000e0da85ee (slock-AF_AX25){+.?.}, at: spin_lock include/linux/spinlock.h:338 [inline]
00000000e0da85ee (slock-AF_AX25){+.?.}, at: ax25_destroy_timer+0x53/0xc0 net/ax25/af_ax25.c:275
{SOFTIRQ-ON-W} state was registered at:
  lock_acquire+0x16f/0x3f0 kernel/locking/lockdep.c:4303
  __raw_spin_lock include/linux/spinlock_api_smp.h:142 [inline]
  _raw_spin_lock+0x2f/0x40 kernel/locking/spinlock.c:151
  spin_lock include/linux/spinlock.h:338 [inline]
  ax25_rt_autobind+0x3ca/0x720 net/ax25/ax25_route.c:429
  ax25_connect.cold+0x30/0xa4 net/ax25/af_ax25.c:1221
  __sys_connect+0x264/0x330 net/socket.c:1834
  __do_sys_connect net/socket.c:1845 [inline]
  __se_sys_connect net/socket.c:1842 [inline]
  __x64_sys_connect+0x73/0xb0 net/socket.c:1842
  do_syscall_64+0xfd/0x680 arch/x86/entry/common.c:301
  entry_SYSCALL_64_after_hwframe+0x49/0xbe
irq event stamp: 2272
hardirqs last  enabled at (2272): [<ffffffff810065f3>] trace_hardirqs_on_thunk+0x1a/0x1c
hardirqs last disabled at (2271): [<ffffffff8100660f>] trace_hardirqs_off_thunk+0x1a/0x1c
softirqs last  enabled at (1522): [<ffffffff87400654>] __do_softirq+0x654/0x94c kernel/softirq.c:320
softirqs last disabled at (2267): [<ffffffff81449010>] invoke_softirq kernel/softirq.c:374 [inline]
softirqs last disabled at (2267): [<ffffffff81449010>] irq_exit+0x180/0x1d0 kernel/softirq.c:414

other info that might help us debug this:
 Possible unsafe locking scenario:

       CPU0
       ----
  lock(slock-AF_AX25);
  <Interrupt>
    lock(slock-AF_AX25);

 *** DEADLOCK ***

1 lock held by blkid/26581:
 #0: 0000000010fd154d ((&ax25->dtimer)){+.-.}, at: lockdep_copy_map include/linux/lockdep.h:175 [inline]
 #0: 0000000010fd154d ((&ax25->dtimer)){+.-.}, at: call_timer_fn+0xe0/0x720 kernel/time/timer.c:1312

stack backtrace:
CPU: 1 PID: 26581 Comm: blkid Not tainted 5.2.0-rc3+ #32
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 print_usage_bug.cold+0x393/0x4a2 kernel/locking/lockdep.c:2935
 valid_state kernel/locking/lockdep.c:2948 [inline]
 mark_lock_irq kernel/locking/lockdep.c:3138 [inline]
 mark_lock+0xd46/0x1370 kernel/locking/lockdep.c:3513
 mark_irqflags kernel/locking/lockdep.c:3391 [inline]
 __lock_acquire+0x159f/0x5490 kernel/locking/lockdep.c:3745
 lock_acquire+0x16f/0x3f0 kernel/locking/lockdep.c:4303
 __raw_spin_lock include/linux/spinlock_api_smp.h:142 [inline]
 _raw_spin_lock+0x2f/0x40 kernel/locking/spinlock.c:151
 spin_lock include/linux/spinlock.h:338 [inline]
 ax25_destroy_timer+0x53/0xc0 net/ax25/af_ax25.c:275
 call_timer_fn+0x193/0x720 kernel/time/timer.c:1322
 expire_timers kernel/time/timer.c:1366 [inline]
 __run_timers kernel/time/timer.c:1685 [inline]
 __run_timers kernel/time/timer.c:1653 [inline]
 run_timer_softirq+0x66f/0x1740 kernel/time/timer.c:1698
 __do_softirq+0x25c/0x94c kernel/softirq.c:293
 invoke_softirq kernel/softirq.c:374 [inline]
 irq_exit+0x180/0x1d0 kernel/softirq.c:414
 exiting_irq arch/x86/include/asm/apic.h:536 [inline]
 smp_apic_timer_interrupt+0x13b/0x550 arch/x86/kernel/apic/apic.c:1068
 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:806
 </IRQ>
RIP: 0033:0x7f858d5c3232
Code: 8b 61 08 48 8b 84 24 d8 00 00 00 4c 89 44 24 28 48 8b ac 24 d0 00 00 00 4c 8b b4 24 e8 00 00 00 48 89 7c 24 68 48 89 4c 24 78 <48> 89 44 24 58 8b 84 24 e0 00 00 00 89 84 24 84 00 00 00 8b 84 24
RSP: 002b:00007ffcaf0cf5c0 EFLAGS: 00000206 ORIG_RAX: ffffffffffffff13
RAX: 00007f858d7d27a8 RBX: 00007f858d7d8820 RCX: 00007f858d3940d8
RDX: 00007ffcaf0cf798 RSI: 00000000f5e616f3 RDI: 00007f858d394fee
RBP: 0000000000000000 R08: 00007ffcaf0cf780 R09: 00007f858d7db480
R10: 0000000000000000 R11: 0000000009691a75 R12: 0000000000000005
R13: 00000000f5e616f3 R14: 0000000000000000 R15: 00007ffcaf0cf798

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ax25/ax25_route.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ax25/ax25_route.c b/net/ax25/ax25_route.c
index 66f74c85cf6b..66d54fc11831 100644
--- a/net/ax25/ax25_route.c
+++ b/net/ax25/ax25_route.c
@@ -429,9 +429,11 @@ int ax25_rt_autobind(ax25_cb *ax25, ax25_address *addr)
 	}
 
 	if (ax25->sk != NULL) {
+		local_bh_disable();
 		bh_lock_sock(ax25->sk);
 		sock_reset_flag(ax25->sk, SOCK_ZAPPED);
 		bh_unlock_sock(ax25->sk);
+		local_bh_enable();
 	}
 
 put:
-- 
2.20.1


From a371c73b1fb2a77632c2016293a1db568ee51ee6 Mon Sep 17 00:00:00 2001
From: Ivan Vecera <ivecera@redhat.com>
Date: Fri, 14 Jun 2019 17:48:36 +0200
Subject: [PATCH 02/31] be2net: Fix number of Rx queues used for flow hashing

[ Upstream commit 718f4a2537089ea41903bf357071306163bc7c04 ]

Number of Rx queues used for flow hashing returned by the driver is
incorrect and this bug prevents user to use the last Rx queue in
indirection table.

Let's say we have a NIC with 6 combined queues:

[root@sm-03 ~]# ethtool -l enp4s0f0
Channel parameters for enp4s0f0:
Pre-set maximums:
RX:             5
TX:             5
Other:          0
Combined:       6
Current hardware settings:
RX:             0
TX:             0
Other:          0
Combined:       6

Default indirection table maps all (6) queues equally but the driver
reports only 5 rings available.

[root@sm-03 ~]# ethtool -x enp4s0f0
RX flow hash indirection table for enp4s0f0 with 5 RX ring(s):
    0:      0     1     2     3     4     5     0     1
    8:      2     3     4     5     0     1     2     3
   16:      4     5     0     1     2     3     4     5
   24:      0     1     2     3     4     5     0     1
...

Now change indirection table somehow:

[root@sm-03 ~]# ethtool -X enp4s0f0 weight 1 1
[root@sm-03 ~]# ethtool -x enp4s0f0
RX flow hash indirection table for enp4s0f0 with 6 RX ring(s):
    0:      0     0     0     0     0     0     0     0
...
   64:      1     1     1     1     1     1     1     1
...

Now it is not possible to change mapping back to equal (default) state:

[root@sm-03 ~]# ethtool -X enp4s0f0 equal 6
Cannot set RX flow hash configuration: Invalid argument

Fixes: 594ad54a2c3b ("be2net: Add support for setting and getting rx flow hash options")
Reported-by: Tianhao <tizhao@redhat.com>
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/emulex/benet/be_ethtool.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c
index 4c218341c51b..6e635debc7fd 100644
--- a/drivers/net/ethernet/emulex/benet/be_ethtool.c
+++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c
@@ -1105,7 +1105,7 @@ static int be_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd,
 		cmd->data = be_get_rss_hash_opts(adapter, cmd->flow_type);
 		break;
 	case ETHTOOL_GRXRINGS:
-		cmd->data = adapter->num_rx_qs - 1;
+		cmd->data = adapter->num_rx_qs;
 		break;
 	default:
 		return -EINVAL;
-- 
2.20.1


From 8356529e4184a89aee670e9448295dfc811c14a0 Mon Sep 17 00:00:00 2001
From: Haiyang Zhang <haiyangz@microsoft.com>
Date: Thu, 13 Jun 2019 21:06:53 +0000
Subject: [PATCH 03/31] hv_netvsc: Set probe mode to sync

[ Upstream commit 9a33629ba6b26caebd73e3c581ba1e6068c696a7 ]

For better consistency of synthetic NIC names, we set the probe mode to
PROBE_FORCE_SYNCHRONOUS. So the names can be aligned with the vmbus
channel offer sequence.

Fixes: af0a5646cb8d ("use the new async probing feature for the hyperv drivers")
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/netvsc_drv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index b20fb0fb595b..e7d8884b1a10 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -2414,7 +2414,7 @@ static struct  hv_driver netvsc_drv = {
 	.probe = netvsc_probe,
 	.remove = netvsc_remove,
 	.driver = {
-		.probe_type = PROBE_PREFER_ASYNCHRONOUS,
+		.probe_type = PROBE_FORCE_SYNCHRONOUS,
 	},
 };
 
-- 
2.20.1


From 81d5157baa260316f8772512b849e6e4256dff66 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 6 Jun 2019 14:32:34 -0700
Subject: [PATCH 04/31] ipv6: flowlabel: fl6_sock_lookup() must use
 atomic_inc_not_zero

[ Upstream commit 65a3c497c0e965a552008db8bc2653f62bc925a1 ]

Before taking a refcount, make sure the object is not already
scheduled for deletion.

Same fix is needed in ipv6_flowlabel_opt()

Fixes: 18367681a10b ("ipv6 flowlabel: Convert np->ipv6_fl_list to RCU.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_flowlabel.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index be5f3d7ceb96..f994f50e1516 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -254,9 +254,9 @@ struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label)
 	rcu_read_lock_bh();
 	for_each_sk_fl_rcu(np, sfl) {
 		struct ip6_flowlabel *fl = sfl->fl;
-		if (fl->label == label) {
+
+		if (fl->label == label && atomic_inc_not_zero(&fl->users)) {
 			fl->lastuse = jiffies;
-			atomic_inc(&fl->users);
 			rcu_read_unlock_bh();
 			return fl;
 		}
@@ -622,7 +622,8 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
 						goto done;
 					}
 					fl1 = sfl->fl;
-					atomic_inc(&fl1->users);
+					if (!atomic_inc_not_zero(&fl1->users))
+						fl1 = NULL;
 					break;
 				}
 			}
-- 
2.20.1


From 2510448bab002ceb9fa5574e167204130f92cbcb Mon Sep 17 00:00:00 2001
From: Jeremy Sowden <jeremy@azazel.net>
Date: Sun, 16 Jun 2019 16:54:37 +0100
Subject: [PATCH 05/31] lapb: fixed leak of control-blocks.

[ Upstream commit 6be8e297f9bcea666ea85ac7a6cd9d52d6deaf92 ]

lapb_register calls lapb_create_cb, which initializes the control-
block's ref-count to one, and __lapb_insert_cb, which increments it when
adding the new block to the list of blocks.

lapb_unregister calls __lapb_remove_cb, which decrements the ref-count
when removing control-block from the list of blocks, and calls lapb_put
itself to decrement the ref-count before returning.

However, lapb_unregister also calls __lapb_devtostruct to look up the
right control-block for the given net_device, and __lapb_devtostruct
also bumps the ref-count, which means that when lapb_unregister returns
the ref-count is still 1 and the control-block is leaked.

Call lapb_put after __lapb_devtostruct to fix leak.

Reported-by: syzbot+afb980676c836b4a0afa@syzkaller.appspotmail.com
Signed-off-by: Jeremy Sowden <jeremy@azazel.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/lapb/lapb_iface.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/lapb/lapb_iface.c b/net/lapb/lapb_iface.c
index db6e0afe3a20..1740f852002e 100644
--- a/net/lapb/lapb_iface.c
+++ b/net/lapb/lapb_iface.c
@@ -182,6 +182,7 @@ int lapb_unregister(struct net_device *dev)
 	lapb = __lapb_devtostruct(dev);
 	if (!lapb)
 		goto out;
+	lapb_put(lapb);
 
 	lapb_stop_t1timer(lapb);
 	lapb_stop_t2timer(lapb);
-- 
2.20.1


From 47279542d45090e3b7576148854363c58eeb9813 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 15 Jun 2019 16:28:48 -0700
Subject: [PATCH 06/31] neigh: fix use-after-free read in pneigh_get_next

[ Upstream commit f3e92cb8e2eb8c27d109e6fd73d3a69a8c09e288 ]

Nine years ago, I added RCU handling to neighbours, not pneighbours.
(pneigh are not commonly used)

Unfortunately I missed that /proc dump operations would use a
common entry and exit point : neigh_seq_start() and neigh_seq_stop()

We need to read_lock(tbl->lock) or risk use-after-free while
iterating the pneigh structures.

We might later convert pneigh to RCU and revert this patch.

sysbot reported :

BUG: KASAN: use-after-free in pneigh_get_next.isra.0+0x24b/0x280 net/core/neighbour.c:3158
Read of size 8 at addr ffff888097f2a700 by task syz-executor.0/9825

CPU: 1 PID: 9825 Comm: syz-executor.0 Not tainted 5.2.0-rc4+ #32
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 print_address_description.cold+0x7c/0x20d mm/kasan/report.c:188
 __kasan_report.cold+0x1b/0x40 mm/kasan/report.c:317
 kasan_report+0x12/0x20 mm/kasan/common.c:614
 __asan_report_load8_noabort+0x14/0x20 mm/kasan/generic_report.c:132
 pneigh_get_next.isra.0+0x24b/0x280 net/core/neighbour.c:3158
 neigh_seq_next+0xdb/0x210 net/core/neighbour.c:3240
 seq_read+0x9cf/0x1110 fs/seq_file.c:258
 proc_reg_read+0x1fc/0x2c0 fs/proc/inode.c:221
 do_loop_readv_writev fs/read_write.c:714 [inline]
 do_loop_readv_writev fs/read_write.c:701 [inline]
 do_iter_read+0x4a4/0x660 fs/read_write.c:935
 vfs_readv+0xf0/0x160 fs/read_write.c:997
 kernel_readv fs/splice.c:359 [inline]
 default_file_splice_read+0x475/0x890 fs/splice.c:414
 do_splice_to+0x127/0x180 fs/splice.c:877
 splice_direct_to_actor+0x2d2/0x970 fs/splice.c:954
 do_splice_direct+0x1da/0x2a0 fs/splice.c:1063
 do_sendfile+0x597/0xd00 fs/read_write.c:1464
 __do_sys_sendfile64 fs/read_write.c:1525 [inline]
 __se_sys_sendfile64 fs/read_write.c:1511 [inline]
 __x64_sys_sendfile64+0x1dd/0x220 fs/read_write.c:1511
 do_syscall_64+0xfd/0x680 arch/x86/entry/common.c:301
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x4592c9
Code: fd b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 cb b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f4aab51dc78 EFLAGS: 00000246 ORIG_RAX: 0000000000000028
RAX: ffffffffffffffda RBX: 0000000000000004 RCX: 00000000004592c9
RDX: 0000000000000000 RSI: 0000000000000004 RDI: 0000000000000005
RBP: 000000000075bf20 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000080000000 R11: 0000000000000246 R12: 00007f4aab51e6d4
R13: 00000000004c689d R14: 00000000004db828 R15: 00000000ffffffff

Allocated by task 9827:
 save_stack+0x23/0x90 mm/kasan/common.c:71
 set_track mm/kasan/common.c:79 [inline]
 __kasan_kmalloc mm/kasan/common.c:489 [inline]
 __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:462
 kasan_kmalloc+0x9/0x10 mm/kasan/common.c:503
 __do_kmalloc mm/slab.c:3660 [inline]
 __kmalloc+0x15c/0x740 mm/slab.c:3669
 kmalloc include/linux/slab.h:552 [inline]
 pneigh_lookup+0x19c/0x4a0 net/core/neighbour.c:731
 arp_req_set_public net/ipv4/arp.c:1010 [inline]
 arp_req_set+0x613/0x720 net/ipv4/arp.c:1026
 arp_ioctl+0x652/0x7f0 net/ipv4/arp.c:1226
 inet_ioctl+0x2a0/0x340 net/ipv4/af_inet.c:926
 sock_do_ioctl+0xd8/0x2f0 net/socket.c:1043
 sock_ioctl+0x3ed/0x780 net/socket.c:1194
 vfs_ioctl fs/ioctl.c:46 [inline]
 file_ioctl fs/ioctl.c:509 [inline]
 do_vfs_ioctl+0xd5f/0x1380 fs/ioctl.c:696
 ksys_ioctl+0xab/0xd0 fs/ioctl.c:713
 __do_sys_ioctl fs/ioctl.c:720 [inline]
 __se_sys_ioctl fs/ioctl.c:718 [inline]
 __x64_sys_ioctl+0x73/0xb0 fs/ioctl.c:718
 do_syscall_64+0xfd/0x680 arch/x86/entry/common.c:301
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Freed by task 9824:
 save_stack+0x23/0x90 mm/kasan/common.c:71
 set_track mm/kasan/common.c:79 [inline]
 __kasan_slab_free+0x102/0x150 mm/kasan/common.c:451
 kasan_slab_free+0xe/0x10 mm/kasan/common.c:459
 __cache_free mm/slab.c:3432 [inline]
 kfree+0xcf/0x220 mm/slab.c:3755
 pneigh_ifdown_and_unlock net/core/neighbour.c:812 [inline]
 __neigh_ifdown+0x236/0x2f0 net/core/neighbour.c:356
 neigh_ifdown+0x20/0x30 net/core/neighbour.c:372
 arp_ifdown+0x1d/0x21 net/ipv4/arp.c:1274
 inetdev_destroy net/ipv4/devinet.c:319 [inline]
 inetdev_event+0xa14/0x11f0 net/ipv4/devinet.c:1544
 notifier_call_chain+0xc2/0x230 kernel/notifier.c:95
 __raw_notifier_call_chain kernel/notifier.c:396 [inline]
 raw_notifier_call_chain+0x2e/0x40 kernel/notifier.c:403
 call_netdevice_notifiers_info+0x3f/0x90 net/core/dev.c:1749
 call_netdevice_notifiers_extack net/core/dev.c:1761 [inline]
 call_netdevice_notifiers net/core/dev.c:1775 [inline]
 rollback_registered_many+0x9b9/0xfc0 net/core/dev.c:8178
 rollback_registered+0x109/0x1d0 net/core/dev.c:8220
 unregister_netdevice_queue net/core/dev.c:9267 [inline]
 unregister_netdevice_queue+0x1ee/0x2c0 net/core/dev.c:9260
 unregister_netdevice include/linux/netdevice.h:2631 [inline]
 __tun_detach+0xd8a/0x1040 drivers/net/tun.c:724
 tun_detach drivers/net/tun.c:741 [inline]
 tun_chr_close+0xe0/0x180 drivers/net/tun.c:3451
 __fput+0x2ff/0x890 fs/file_table.c:280
 ____fput+0x16/0x20 fs/file_table.c:313
 task_work_run+0x145/0x1c0 kernel/task_work.c:113
 tracehook_notify_resume include/linux/tracehook.h:185 [inline]
 exit_to_usermode_loop+0x273/0x2c0 arch/x86/entry/common.c:168
 prepare_exit_to_usermode arch/x86/entry/common.c:199 [inline]
 syscall_return_slowpath arch/x86/entry/common.c:279 [inline]
 do_syscall_64+0x58e/0x680 arch/x86/entry/common.c:304
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

The buggy address belongs to the object at ffff888097f2a700
 which belongs to the cache kmalloc-64 of size 64
The buggy address is located 0 bytes inside of
 64-byte region [ffff888097f2a700, ffff888097f2a740)
The buggy address belongs to the page:
page:ffffea00025fca80 refcount:1 mapcount:0 mapping:ffff8880aa400340 index:0x0
flags: 0x1fffc0000000200(slab)
raw: 01fffc0000000200 ffffea000250d548 ffffea00025726c8 ffff8880aa400340
raw: 0000000000000000 ffff888097f2a000 0000000100000020 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff888097f2a600: 00 00 00 00 00 00 00 00 fc fc fc fc fc fc fc fc
 ffff888097f2a680: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
>ffff888097f2a700: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
                   ^
 ffff888097f2a780: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
 ffff888097f2a800: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc

Fixes: 767e97e1e0db ("neigh: RCU conversion of struct neighbour")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 9b9da5142613..cce4fbcd7dcb 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -3199,6 +3199,7 @@ static void *neigh_get_idx_any(struct seq_file *seq, loff_t *pos)
 }
 
 void *neigh_seq_start(struct seq_file *seq, loff_t *pos, struct neigh_table *tbl, unsigned int neigh_seq_flags)
+	__acquires(tbl->lock)
 	__acquires(rcu_bh)
 {
 	struct neigh_seq_state *state = seq->private;
@@ -3209,6 +3210,7 @@ void *neigh_seq_start(struct seq_file *seq, loff_t *pos, struct neigh_table *tbl
 
 	rcu_read_lock_bh();
 	state->nht = rcu_dereference_bh(tbl->nht);
+	read_lock(&tbl->lock);
 
 	return *pos ? neigh_get_idx_any(seq, pos) : SEQ_START_TOKEN;
 }
@@ -3242,8 +3244,13 @@ void *neigh_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 EXPORT_SYMBOL(neigh_seq_next);
 
 void neigh_seq_stop(struct seq_file *seq, void *v)
+	__releases(tbl->lock)
 	__releases(rcu_bh)
 {
+	struct neigh_seq_state *state = seq->private;
+	struct neigh_table *tbl = state->tbl;
+
+	read_unlock(&tbl->lock);
 	rcu_read_unlock_bh();
 }
 EXPORT_SYMBOL(neigh_seq_stop);
-- 
2.20.1


From d94fcef9ab80ff050d05efad91608aae2442eaa0 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Fri, 14 Jun 2019 00:25:20 +0200
Subject: [PATCH 07/31] net: dsa: rtl8366: Fix up VLAN filtering

[ Upstream commit 760c80b70bed2cd01630e8595d1bbde910339f31 ]

We get this regression when using RTL8366RB as part of a bridge
with OpenWrt:

WARNING: CPU: 0 PID: 1347 at net/switchdev/switchdev.c:291
	 switchdev_port_attr_set_now+0x80/0xa4
lan0: Commit of attribute (id=7) failed.
(...)
realtek-smi switch lan0: failed to initialize vlan filtering on this port

This is because it is trying to disable VLAN filtering
on VLAN0, as we have forgot to add 1 to the port number
to get the right VLAN in rtl8366_vlan_filtering(): when
we initialize the VLAN we associate VLAN1 with port 0,
VLAN2 with port 1 etc, so we need to add 1 to the port
offset.

Fixes: d8652956cf37 ("net: dsa: realtek-smi: Add Realtek SMI driver")
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/rtl8366.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/dsa/rtl8366.c b/drivers/net/dsa/rtl8366.c
index 6dedd43442cc..35b767baf21f 100644
--- a/drivers/net/dsa/rtl8366.c
+++ b/drivers/net/dsa/rtl8366.c
@@ -307,7 +307,8 @@ int rtl8366_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering)
 	struct rtl8366_vlan_4k vlan4k;
 	int ret;
 
-	if (!smi->ops->is_vlan_valid(smi, port))
+	/* Use VLAN nr port + 1 since VLAN0 is not valid */
+	if (!smi->ops->is_vlan_valid(smi, port + 1))
 		return -EINVAL;
 
 	dev_info(smi->dev, "%s filtering on port %d\n",
@@ -318,12 +319,12 @@ int rtl8366_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering)
 	 * The hardware support filter ID (FID) 0..7, I have no clue how to
 	 * support this in the driver when the callback only says on/off.
 	 */
-	ret = smi->ops->get_vlan_4k(smi, port, &vlan4k);
+	ret = smi->ops->get_vlan_4k(smi, port + 1, &vlan4k);
 	if (ret)
 		return ret;
 
 	/* Just set the filter to FID 1 for now then */
-	ret = rtl8366_set_vlan(smi, port,
+	ret = rtl8366_set_vlan(smi, port + 1,
 			       vlan4k.member,
 			       vlan4k.untag,
 			       1);
-- 
2.20.1


From c18fe70603f190c9974140e0f00252c0d83dc31b Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Sun, 9 Jun 2019 23:26:21 +0900
Subject: [PATCH 08/31] net: openvswitch: do not free vport if
 register_netdevice() is failed.

[ Upstream commit 309b66970ee2abf721ecd0876a48940fa0b99a35 ]

In order to create an internal vport, internal_dev_create() is used and
that calls register_netdevice() internally.
If register_netdevice() fails, it calls dev->priv_destructor() to free
private data of netdev. actually, a private data of this is a vport.

Hence internal_dev_create() should not free and use a vport after failure
of register_netdevice().

Test command
    ovs-dpctl add-dp bonding_masters

Splat looks like:
[ 1035.667767] kasan: GPF could be caused by NULL-ptr deref or user memory access
[ 1035.675958] general protection fault: 0000 [#1] SMP DEBUG_PAGEALLOC KASAN PTI
[ 1035.676916] CPU: 1 PID: 1028 Comm: ovs-vswitchd Tainted: G    B             5.2.0-rc3+ #240
[ 1035.676916] RIP: 0010:internal_dev_create+0x2e5/0x4e0 [openvswitch]
[ 1035.676916] Code: 48 c1 ea 03 80 3c 02 00 0f 85 9f 01 00 00 4c 8b 23 48 b8 00 00 00 00 00 fc ff df 49 8d bc 24 60 05 00 00 48 89 fa 48 c1 ea 03 <80> 3c 02 00 0f 85 86 01 00 00 49 8b bc 24 60 05 00 00 e8 e4 68 f4
[ 1035.713720] RSP: 0018:ffff88810dcb7578 EFLAGS: 00010206
[ 1035.713720] RAX: dffffc0000000000 RBX: ffff88810d13fe08 RCX: ffffffff84297704
[ 1035.713720] RDX: 00000000000000ac RSI: 0000000000000000 RDI: 0000000000000560
[ 1035.713720] RBP: 00000000ffffffef R08: fffffbfff0d3b881 R09: fffffbfff0d3b881
[ 1035.713720] R10: 0000000000000001 R11: fffffbfff0d3b880 R12: 0000000000000000
[ 1035.768776] R13: 0000607ee460b900 R14: ffff88810dcb7690 R15: ffff88810dcb7698
[ 1035.777709] FS:  00007f02095fc980(0000) GS:ffff88811b400000(0000) knlGS:0000000000000000
[ 1035.777709] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 1035.777709] CR2: 00007ffdf01d2f28 CR3: 0000000108258000 CR4: 00000000001006e0
[ 1035.777709] Call Trace:
[ 1035.777709]  ovs_vport_add+0x267/0x4f0 [openvswitch]
[ 1035.777709]  new_vport+0x15/0x1e0 [openvswitch]
[ 1035.777709]  ovs_vport_cmd_new+0x567/0xd10 [openvswitch]
[ 1035.777709]  ? ovs_dp_cmd_dump+0x490/0x490 [openvswitch]
[ 1035.777709]  ? __kmalloc+0x131/0x2e0
[ 1035.777709]  ? genl_family_rcv_msg+0xa54/0x1030
[ 1035.777709]  genl_family_rcv_msg+0x63a/0x1030
[ 1035.777709]  ? genl_unregister_family+0x630/0x630
[ 1035.841681]  ? debug_show_all_locks+0x2d0/0x2d0
[ ... ]

Fixes: cf124db566e6 ("net: Fix inconsistent teardown and release of private netdev state.")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Reviewed-by: Greg Rose <gvrose8192@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/vport-internal_dev.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c
index 26f71cbf7527..5993405c25c1 100644
--- a/net/openvswitch/vport-internal_dev.c
+++ b/net/openvswitch/vport-internal_dev.c
@@ -170,7 +170,9 @@ static struct vport *internal_dev_create(const struct vport_parms *parms)
 {
 	struct vport *vport;
 	struct internal_dev *internal_dev;
+	struct net_device *dev;
 	int err;
+	bool free_vport = true;
 
 	vport = ovs_vport_alloc(0, &ovs_internal_vport_ops, parms);
 	if (IS_ERR(vport)) {
@@ -178,8 +180,9 @@ static struct vport *internal_dev_create(const struct vport_parms *parms)
 		goto error;
 	}
 
-	vport->dev = alloc_netdev(sizeof(struct internal_dev),
-				  parms->name, NET_NAME_USER, do_setup);
+	dev = alloc_netdev(sizeof(struct internal_dev),
+			   parms->name, NET_NAME_USER, do_setup);
+	vport->dev = dev;
 	if (!vport->dev) {
 		err = -ENOMEM;
 		goto error_free_vport;
@@ -200,8 +203,10 @@ static struct vport *internal_dev_create(const struct vport_parms *parms)
 
 	rtnl_lock();
 	err = register_netdevice(vport->dev);
-	if (err)
+	if (err) {
+		free_vport = false;
 		goto error_unlock;
+	}
 
 	dev_set_promiscuity(vport->dev, 1);
 	rtnl_unlock();
@@ -211,11 +216,12 @@ static struct vport *internal_dev_create(const struct vport_parms *parms)
 
 error_unlock:
 	rtnl_unlock();
-	free_percpu(vport->dev->tstats);
+	free_percpu(dev->tstats);
 error_free_netdev:
-	free_netdev(vport->dev);
+	free_netdev(dev);
 error_free_vport:
-	ovs_vport_free(vport);
+	if (free_vport)
+		ovs_vport_free(vport);
 error:
 	return ERR_PTR(err);
 }
-- 
2.20.1


From b9229b065b7a1c7e0c0871f2d7677a01caef6d1d Mon Sep 17 00:00:00 2001
From: Ioana Ciornei <ioana.ciornei@nxp.com>
Date: Thu, 13 Jun 2019 09:37:51 +0300
Subject: [PATCH 09/31] net: phylink: set the autoneg state in
 phylink_phy_change

[ Upstream commit ef7bfa84725d891bbdb88707ed55b2cbf94942bb ]

The phy_state field of phylink should carry only valid information
especially when this can be passed to the .mac_config callback.
Update the an_enabled field with the autoneg state in the
phylink_phy_change function.

Fixes: 9525ae83959b ("phylink: add phylink infrastructure")
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phylink.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 89750c7dfd6f..d8f919fe49fd 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -638,6 +638,7 @@ static void phylink_phy_change(struct phy_device *phydev, bool up,
 		pl->phy_state.pause |= MLO_PAUSE_ASYM;
 	pl->phy_state.interface = phydev->interface;
 	pl->phy_state.link = up;
+	pl->phy_state.an_enabled = phydev->autoneg;
 	mutex_unlock(&pl->state_mutex);
 
 	phylink_run_resolve(pl);
-- 
2.20.1


From f21434f78d0c05b955b36f0b24018964eb7b87f7 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Wed, 12 Jun 2019 17:23:57 +0000
Subject: [PATCH 10/31] net: tls, correctly account for copied bytes with
 multiple sk_msgs

[ Upstream commit 648ee6cea7dde4a5cdf817e5d964fd60b22006a4 ]

tls_sw_do_sendpage needs to return the total number of bytes sent
regardless of how many sk_msgs are allocated. Unfortunately, copied
(the value we return up the stack) is zero'd before each new sk_msg
is allocated so we only return the copied size of the last sk_msg used.

The caller (splice, etc.) of sendpage will then believe only part
of its data was sent and send the missing chunks again. However,
because the data actually was sent the receiver will get multiple
copies of the same data.

To reproduce this do multiple sendfile calls with a length close to
the max record size. This will in turn call splice/sendpage, sendpage
may use multiple sk_msg in this case and then returns the incorrect
number of bytes. This will cause splice to resend creating duplicate
data on the receiver. Andre created a C program that can easily
generate this case so we will push a similar selftest for this to
bpf-next shortly.

The fix is to _not_ zero the copied field so that the total sent
bytes is returned.

Reported-by: Steinar H. Gunderson <steinar+kernel@gunderson.no>
Reported-by: Andre Tomt <andre@tomt.net>
Tested-by: Andre Tomt <andre@tomt.net>
Fixes: d829e9c4112b ("tls: convert to generic sk_msg interface")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index d350ff73a391..41e17ed0c94e 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1128,7 +1128,6 @@ static int tls_sw_do_sendpage(struct sock *sk, struct page *page,
 
 		full_record = false;
 		record_room = TLS_MAX_PAYLOAD_SIZE - msg_pl->sg.size;
-		copied = 0;
 		copy = size;
 		if (copy >= record_room) {
 			copy = record_room;
-- 
2.20.1


From c1c281cceea2098d68538eec47c62d7ca793a473 Mon Sep 17 00:00:00 2001
From: Young Xiao <92siuyang@gmail.com>
Date: Fri, 14 Jun 2019 15:13:02 +0800
Subject: [PATCH 11/31] nfc: Ensure presence of required attributes in the
 deactivate_target handler

[ Upstream commit 385097a3675749cbc9e97c085c0e5dfe4269ca51 ]

Check that the NFC_ATTR_TARGET_INDEX attributes (in addition to
NFC_ATTR_DEVICE_INDEX) are provided by the netlink client prior to
accessing them. This prevents potential unhandled NULL pointer dereference
exceptions which can be triggered by malicious user-mode programs,
if they omit one or both of these attributes.

Signed-off-by: Young Xiao <92siuyang@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/nfc/netlink.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index 376181cc1def..9f2875efb4ac 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -922,7 +922,8 @@ static int nfc_genl_deactivate_target(struct sk_buff *skb,
 	u32 device_idx, target_idx;
 	int rc;
 
-	if (!info->attrs[NFC_ATTR_DEVICE_INDEX])
+	if (!info->attrs[NFC_ATTR_DEVICE_INDEX] ||
+	    !info->attrs[NFC_ATTR_TARGET_INDEX])
 		return -EINVAL;
 
 	device_idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]);
-- 
2.20.1


From 096224a39e62237ea9f65cc430645e5a2c24a0fd Mon Sep 17 00:00:00 2001
From: Neil Horman <nhorman@tuxdriver.com>
Date: Thu, 13 Jun 2019 06:35:59 -0400
Subject: [PATCH 12/31] sctp: Free cookie before we memdup a new one

[ Upstream commit ce950f1050cece5e406a5cde723c69bba60e1b26 ]

Based on comments from Xin, even after fixes for our recent syzbot
report of cookie memory leaks, its possible to get a resend of an INIT
chunk which would lead to us leaking cookie memory.

To ensure that we don't leak cookie memory, free any previously
allocated cookie first.

Change notes
v1->v2
update subsystem tag in subject (davem)
repeat kfree check for peer_random and peer_hmacs (xin)

v2->v3
net->sctp
also free peer_chunks

v3->v4
fix subject tags

v4->v5
remove cut line

Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Reported-by: syzbot+f7e9153b037eac9b1df8@syzkaller.appspotmail.com
CC: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
CC: Xin Long <lucien.xin@gmail.com>
CC: "David S. Miller" <davem@davemloft.net>
CC: netdev@vger.kernel.org
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sm_make_chunk.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index ae65a1cfa596..fb546b2d67ca 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -2600,6 +2600,8 @@ static int sctp_process_param(struct sctp_association *asoc,
 	case SCTP_PARAM_STATE_COOKIE:
 		asoc->peer.cookie_len =
 			ntohs(param.p->length) - sizeof(struct sctp_paramhdr);
+		if (asoc->peer.cookie)
+			kfree(asoc->peer.cookie);
 		asoc->peer.cookie = kmemdup(param.cookie->body, asoc->peer.cookie_len, gfp);
 		if (!asoc->peer.cookie)
 			retval = 0;
@@ -2664,6 +2666,8 @@ static int sctp_process_param(struct sctp_association *asoc,
 			goto fall_through;
 
 		/* Save peer's random parameter */
+		if (asoc->peer.peer_random)
+			kfree(asoc->peer.peer_random);
 		asoc->peer.peer_random = kmemdup(param.p,
 					    ntohs(param.p->length), gfp);
 		if (!asoc->peer.peer_random) {
@@ -2677,6 +2681,8 @@ static int sctp_process_param(struct sctp_association *asoc,
 			goto fall_through;
 
 		/* Save peer's HMAC list */
+		if (asoc->peer.peer_hmacs)
+			kfree(asoc->peer.peer_hmacs);
 		asoc->peer.peer_hmacs = kmemdup(param.p,
 					    ntohs(param.p->length), gfp);
 		if (!asoc->peer.peer_hmacs) {
@@ -2692,6 +2698,8 @@ static int sctp_process_param(struct sctp_association *asoc,
 		if (!ep->auth_enable)
 			goto fall_through;
 
+		if (asoc->peer.peer_chunks)
+			kfree(asoc->peer.peer_chunks);
 		asoc->peer.peer_chunks = kmemdup(param.p,
 					    ntohs(param.p->length), gfp);
 		if (!asoc->peer.peer_chunks)
-- 
2.20.1


From e10a0ca8dcbf414cf22737625d33c40e14cd2c10 Mon Sep 17 00:00:00 2001
From: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Date: Tue, 11 Jun 2019 17:38:37 +0200
Subject: [PATCH 13/31] sunhv: Fix device naming inconsistency between
 sunhv_console and sunhv_reg

[ Upstream commit 07a6d63eb1b54b5fb38092780fe618dfe1d96e23 ]

In d5a2aa24, the name in struct console sunhv_console was changed from "ttyS"
to "ttyHV" while the name in struct uart_ops sunhv_pops remained unchanged.

This results in the hypervisor console device to be listed as "ttyHV0" under
/proc/consoles while the device node is still named "ttyS0":

root@osaka:~# cat /proc/consoles
ttyHV0               -W- (EC p  )    4:64
tty0                 -WU (E     )    4:1
root@osaka:~# readlink /sys/dev/char/4:64
../../devices/root/f02836f0/f0285690/tty/ttyS0
root@osaka:~#

This means that any userland code which tries to determine the name of the
device file of the hypervisor console device can not rely on the information
provided by /proc/consoles. In particular, booting current versions of debian-
installer inside a SPARC LDOM will fail with the installer unable to determine
the console device.

After renaming the device in struct uart_ops sunhv_pops to "ttyHV" as well,
the inconsistency is fixed and it is possible again to determine the name
of the device file of the hypervisor console device by reading the contents
of /proc/console:

root@osaka:~# cat /proc/consoles
ttyHV0               -W- (EC p  )    4:64
tty0                 -WU (E     )    4:1
root@osaka:~# readlink /sys/dev/char/4:64
../../devices/root/f02836f0/f0285690/tty/ttyHV0
root@osaka:~#

With this change, debian-installer works correctly when installing inside
a SPARC LDOM.

Signed-off-by: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/tty/serial/sunhv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/tty/serial/sunhv.c b/drivers/tty/serial/sunhv.c
index 63e34d868de8..f8503f8fc44e 100644
--- a/drivers/tty/serial/sunhv.c
+++ b/drivers/tty/serial/sunhv.c
@@ -397,7 +397,7 @@ static const struct uart_ops sunhv_pops = {
 static struct uart_driver sunhv_reg = {
 	.owner			= THIS_MODULE,
 	.driver_name		= "sunhv",
-	.dev_name		= "ttyS",
+	.dev_name		= "ttyHV",
 	.major			= TTY_MAJOR,
 };
 
-- 
2.20.1


From ae632a51842be8a340b30e5b1c90de9cac526319 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 16 Jun 2019 17:24:07 +0800
Subject: [PATCH 14/31] tipc: purge deferredq list for each grp member in
 tipc_group_delete

[ Upstream commit 5cf02612b33f104fe1015b2dfaf1758ad3675588 ]

Syzbot reported a memleak caused by grp members' deferredq list not
purged when the grp is be deleted.

The issue occurs when more(msg_grp_bc_seqno(hdr), m->bc_rcv_nxt) in
tipc_group_filter_msg() and the skb will stay in deferredq.

So fix it by calling __skb_queue_purge for each member's deferredq
in tipc_group_delete() when a tipc sk leaves the grp.

Fixes: b87a5ea31c93 ("tipc: guarantee group unicast doesn't bypass group broadcast")
Reported-by: syzbot+78fbe679c8ca8d264a8d@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/group.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/tipc/group.c b/net/tipc/group.c
index 63f39201e41e..df0c0c4b38d5 100644
--- a/net/tipc/group.c
+++ b/net/tipc/group.c
@@ -218,6 +218,7 @@ void tipc_group_delete(struct net *net, struct tipc_group *grp)
 
 	rbtree_postorder_for_each_entry_safe(m, tmp, tree, tree_node) {
 		tipc_group_proto_xmit(grp, m, GRP_LEAVE_MSG, &xmitq);
+		__skb_queue_purge(&m->deferredq);
 		list_del(&m->list);
 		kfree(m);
 	}
-- 
2.20.1


From dbea03aa0f6a3ae26c7253f305d64ac2724a2649 Mon Sep 17 00:00:00 2001
From: Stephen Barber <smbarber@chromium.org>
Date: Fri, 14 Jun 2019 23:42:37 -0700
Subject: [PATCH 15/31] vsock/virtio: set SOCK_DONE on peer shutdown

[ Upstream commit 42f5cda5eaf4396a939ae9bb43bb8d1d09c1b15c ]

Set the SOCK_DONE flag to match the TCP_CLOSING state when a peer has
shut down and there is nothing left to read.

This fixes the following bug:
1) Peer sends SHUTDOWN(RDWR).
2) Socket enters TCP_CLOSING but SOCK_DONE is not set.
3) read() returns -ENOTCONN until close() is called, then returns 0.

Signed-off-by: Stephen Barber <smbarber@chromium.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/vmw_vsock/virtio_transport_common.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index f3f3d06cb6d8..e30f53728725 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -871,8 +871,10 @@ virtio_transport_recv_connected(struct sock *sk,
 		if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SHUTDOWN_SEND)
 			vsk->peer_shutdown |= SEND_SHUTDOWN;
 		if (vsk->peer_shutdown == SHUTDOWN_MASK &&
-		    vsock_stream_has_data(vsk) <= 0)
+		    vsock_stream_has_data(vsk) <= 0) {
+			sock_set_flag(sk, SOCK_DONE);
 			sk->sk_state = TCP_CLOSING;
+		}
 		if (le32_to_cpu(pkt->hdr.flags))
 			sk->sk_state_change(sk);
 		break;
-- 
2.20.1


From bb29ee3a175ccd6180fd84e88f555e96934f19d4 Mon Sep 17 00:00:00 2001
From: Alaa Hleihel <alaa@mellanox.com>
Date: Sun, 19 May 2019 11:11:49 +0300
Subject: [PATCH 16/31] net/mlx5: Avoid reloading already removed devices

Prior to reloading a device we must first verify that it was not already
removed. Otherwise, the attempt to remove the device will do nothing, and
in that case we will end up proceeding with adding an new device that no
one was expecting to remove, leaving behind used resources such as EQs that
causes a failure to destroy comp EQs and syndrome (0x30f433).

Fix that by making sure that we try to remove and add a device (based on a
protocol) only if the device is already added.

Fixes: c5447c70594b ("net/mlx5: E-Switch, Reload IB interface when switching devlink modes")
Signed-off-by: Alaa Hleihel <alaa@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/dev.c | 25 +++++++++++++++++--
 1 file changed, 23 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
index ebc046fa97d3..f6b1da99e6c2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -248,11 +248,32 @@ void mlx5_unregister_interface(struct mlx5_interface *intf)
 }
 EXPORT_SYMBOL(mlx5_unregister_interface);
 
+/* Must be called with intf_mutex held */
+static bool mlx5_has_added_dev_by_protocol(struct mlx5_core_dev *mdev, int protocol)
+{
+	struct mlx5_device_context *dev_ctx;
+	struct mlx5_interface *intf;
+	bool found = false;
+
+	list_for_each_entry(intf, &intf_list, list) {
+		if (intf->protocol == protocol) {
+			dev_ctx = mlx5_get_device(intf, &mdev->priv);
+			if (dev_ctx && test_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state))
+				found = true;
+			break;
+		}
+	}
+
+	return found;
+}
+
 void mlx5_reload_interface(struct mlx5_core_dev *mdev, int protocol)
 {
 	mutex_lock(&mlx5_intf_mutex);
-	mlx5_remove_dev_by_protocol(mdev, protocol);
-	mlx5_add_dev_by_protocol(mdev, protocol);
+	if (mlx5_has_added_dev_by_protocol(mdev, protocol)) {
+		mlx5_remove_dev_by_protocol(mdev, protocol);
+		mlx5_add_dev_by_protocol(mdev, protocol);
+	}
 	mutex_unlock(&mlx5_intf_mutex);
 }
 
-- 
2.20.1


From 17da0544cfd0684348f6bdebbac563d541f185eb Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Tue, 11 Jun 2019 00:27:05 +0200
Subject: [PATCH 17/31] vxlan: Don't assume linear buffers in error handler

[ Upstream commit 8399a6930d12f5965230f4ff058228a4cc80c0b9 ]

In commit c3a43b9fec8a ("vxlan: ICMP error lookup handler") I wrongly
assumed buffers from icmp_socket_deliver() would be linear. This is not
the case: icmp_socket_deliver() only guarantees we have 8 bytes of linear
data.

Eric fixed this same issue for fou and fou6 in commits 26fc181e6cac
("fou, fou6: do not assume linear skbs") and 5355ed6388e2 ("fou, fou6:
avoid uninit-value in gue_err() and gue6_err()").

Use pskb_may_pull() instead of checking skb->len, and take into account
the fact we later access the VXLAN header with udp_hdr(), so we also
need to sum skb_transport_header() here.

Reported-by: Guillaume Nault <gnault@redhat.com>
Fixes: c3a43b9fec8a ("vxlan: ICMP error lookup handler")
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index d76dfed8d9bb..38ecb66fb3e9 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1765,7 +1765,7 @@ static int vxlan_err_lookup(struct sock *sk, struct sk_buff *skb)
 	struct vxlanhdr *hdr;
 	__be32 vni;
 
-	if (skb->len < VXLAN_HLEN)
+	if (!pskb_may_pull(skb, skb_transport_offset(skb) + VXLAN_HLEN))
 		return -EINVAL;
 
 	hdr = vxlan_hdr(skb);
-- 
2.20.1


From f00d416b7a07a30929844b2b88a83e0baf9bd6a2 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Tue, 11 Jun 2019 00:27:06 +0200
Subject: [PATCH 18/31] geneve: Don't assume linear buffers in error handler

[ Upstream commit eccc73a6b2cb6c04bfbc40a0769f3c428dfba232 ]

In commit a07966447f39 ("geneve: ICMP error lookup handler") I wrongly
assumed buffers from icmp_socket_deliver() would be linear. This is not
the case: icmp_socket_deliver() only guarantees we have 8 bytes of linear
data.

Eric fixed this same issue for fou and fou6 in commits 26fc181e6cac
("fou, fou6: do not assume linear skbs") and 5355ed6388e2 ("fou, fou6:
avoid uninit-value in gue_err() and gue6_err()").

Use pskb_may_pull() instead of checking skb->len, and take into account
the fact we later access the GENEVE header with udp_hdr(), so we also
need to sum skb_transport_header() here.

Reported-by: Guillaume Nault <gnault@redhat.com>
Fixes: a07966447f39 ("geneve: ICMP error lookup handler")
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 5583d993480d..ffe421944429 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -396,7 +396,7 @@ static int geneve_udp_encap_err_lookup(struct sock *sk, struct sk_buff *skb)
 	u8 zero_vni[3] = { 0 };
 	u8 *vni = zero_vni;
 
-	if (skb->len < GENEVE_BASE_HLEN)
+	if (!pskb_may_pull(skb, skb_transport_offset(skb) + GENEVE_BASE_HLEN))
 		return -EINVAL;
 
 	geneveh = geneve_hdr(skb);
-- 
2.20.1


From 1e75e503ba435bb688995a3ef3f4d78bbd702e42 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Tue, 11 Jun 2019 11:51:42 +0200
Subject: [PATCH 19/31] net: mvpp2: prs: Fix parser range for VID filtering

[ Upstream commit 46b0090a6636cf34c0e856f15dd03e15ba4cdda6 ]

VID filtering is implemented in the Header Parser, with one range of 11
vids being assigned for each no-loopback port.

Make sure we use the per-port range when looking for existing entries in
the Parser.

Since we used a global range instead of a per-port one, this causes VIDs
to be removed from the whitelist from all ports of the same PPv2
instance.

Fixes: 56beda3db602 ("net: mvpp2: Add hardware offloading for VLAN filtering")
Suggested-by: Yuri Chipchev <yuric@marvell.com>
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
index 392fd895f278..e0da4db3bf56 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
@@ -1905,8 +1905,7 @@ static int mvpp2_prs_ip6_init(struct mvpp2 *priv)
 }
 
 /* Find tcam entry with matched pair <vid,port> */
-static int mvpp2_prs_vid_range_find(struct mvpp2 *priv, int pmap, u16 vid,
-				    u16 mask)
+static int mvpp2_prs_vid_range_find(struct mvpp2_port *port, u16 vid, u16 mask)
 {
 	unsigned char byte[2], enable[2];
 	struct mvpp2_prs_entry pe;
@@ -1914,13 +1913,13 @@ static int mvpp2_prs_vid_range_find(struct mvpp2 *priv, int pmap, u16 vid,
 	int tid;
 
 	/* Go through the all entries with MVPP2_PRS_LU_VID */
-	for (tid = MVPP2_PE_VID_FILT_RANGE_START;
-	     tid <= MVPP2_PE_VID_FILT_RANGE_END; tid++) {
-		if (!priv->prs_shadow[tid].valid ||
-		    priv->prs_shadow[tid].lu != MVPP2_PRS_LU_VID)
+	for (tid = MVPP2_PRS_VID_PORT_FIRST(port->id);
+	     tid <= MVPP2_PRS_VID_PORT_LAST(port->id); tid++) {
+		if (!port->priv->prs_shadow[tid].valid ||
+		    port->priv->prs_shadow[tid].lu != MVPP2_PRS_LU_VID)
 			continue;
 
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		mvpp2_prs_init_from_hw(port->priv, &pe, tid);
 
 		mvpp2_prs_tcam_data_byte_get(&pe, 2, &byte[0], &enable[0]);
 		mvpp2_prs_tcam_data_byte_get(&pe, 3, &byte[1], &enable[1]);
@@ -1950,7 +1949,7 @@ int mvpp2_prs_vid_entry_add(struct mvpp2_port *port, u16 vid)
 	memset(&pe, 0, sizeof(pe));
 
 	/* Scan TCAM and see if entry with this <vid,port> already exist */
-	tid = mvpp2_prs_vid_range_find(priv, (1 << port->id), vid, mask);
+	tid = mvpp2_prs_vid_range_find(port, vid, mask);
 
 	reg_val = mvpp2_read(priv, MVPP2_MH_REG(port->id));
 	if (reg_val & MVPP2_DSA_EXTENDED)
@@ -2008,7 +2007,7 @@ void mvpp2_prs_vid_entry_remove(struct mvpp2_port *port, u16 vid)
 	int tid;
 
 	/* Scan TCAM and see if entry with this <vid,port> already exist */
-	tid = mvpp2_prs_vid_range_find(priv, (1 << port->id), vid, 0xfff);
+	tid = mvpp2_prs_vid_range_find(port, vid, 0xfff);
 
 	/* No such entry */
 	if (tid < 0)
-- 
2.20.1


From 01d1012c34097bafa2a066f38b1707ff8ed87c24 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Tue, 11 Jun 2019 11:51:43 +0200
Subject: [PATCH 20/31] net: mvpp2: prs: Use the correct helpers when removing
 all VID filters

[ Upstream commit 6b7a3430c163455cf8a514d636bda52b04654972 ]

When removing all VID filters, the mvpp2_prs_vid_entry_remove would be
called with the TCAM id incorrectly used as a VID, causing the wrong
TCAM entries to be invalidated.

Fix this by directly invalidating entries in the VID range.

Fixes: 56beda3db602 ("net: mvpp2: Add hardware offloading for VLAN filtering")
Suggested-by: Yuri Chipchev <yuric@marvell.com>
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
index e0da4db3bf56..ae2240074d8e 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
@@ -2025,8 +2025,10 @@ void mvpp2_prs_vid_remove_all(struct mvpp2_port *port)
 
 	for (tid = MVPP2_PRS_VID_PORT_FIRST(port->id);
 	     tid <= MVPP2_PRS_VID_PORT_LAST(port->id); tid++) {
-		if (priv->prs_shadow[tid].valid)
-			mvpp2_prs_vid_entry_remove(port, tid);
+		if (priv->prs_shadow[tid].valid) {
+			mvpp2_prs_hw_inv(priv, tid);
+			priv->prs_shadow[tid].valid = false;
+		}
 	}
 }
 
-- 
2.20.1


From a78310bf47dd3bd1c230edf4cf69d641c88f1bf9 Mon Sep 17 00:00:00 2001
From: Robert Hancock <hancock@sedsystems.ca>
Date: Wed, 12 Jun 2019 14:33:32 -0600
Subject: [PATCH 21/31] net: dsa: microchip: Don't try to read stats for unused
 ports

[ Upstream commit 6bb9e376c2a4cc5120c3bf5fd3048b9a0a6ec1f8 ]

If some of the switch ports were not listed in the device tree, due to
being unused, the ksz_mib_read_work function ended up accessing a NULL
dp->slave pointer and causing an oops. Skip checking statistics for any
unused ports.

Fixes: 7c6ff470aa867f53 ("net: dsa: microchip: add MIB counter reading support")
Signed-off-by: Robert Hancock <hancock@sedsystems.ca>
Reviewed-by: Vivien Didelot <vivien.didelot@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/microchip/ksz_common.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index 39dace8e3512..f46086fa9064 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -83,6 +83,9 @@ static void ksz_mib_read_work(struct work_struct *work)
 	int i;
 
 	for (i = 0; i < dev->mib_port_cnt; i++) {
+		if (dsa_is_unused_port(dev->ds, i))
+			continue;
+
 		p = &dev->ports[i];
 		mib = &p->mib;
 		mutex_lock(&mib->cnt_mutex);
-- 
2.20.1


From 213d5be282723a8091881a30a1b2c8917643147a Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Wed, 12 Jun 2019 17:18:38 +0200
Subject: [PATCH 22/31] net: ethtool: Allow matching on vlan DEI bit
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit f0d2ca1531377e7da888913e277eefac05a59b6f ]

Using ethtool, users can specify a classification action matching on the
full vlan tag, which includes the DEI bit (also previously called CFI).

However, when converting the ethool_flow_spec to a flow_rule, we use
dissector keys to represent the matching patterns.

Since the vlan dissector key doesn't include the DEI bit, this
information was silently discarded when translating the ethtool
flow spec in to a flow_rule.

This commit adds the DEI bit into the vlan dissector key, and allows
propagating the information to the driver when parsing the ethtool flow
spec.

Fixes: eca4205f9ec3 ("ethtool: add ethtool_rx_flow_spec to flow_rule structure translator")
Reported-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow_dissector.h | 1 +
 net/core/ethtool.c           | 5 +++++
 2 files changed, 6 insertions(+)

diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index 2b26979efb48..fc0d471af4b9 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -46,6 +46,7 @@ struct flow_dissector_key_tags {
 
 struct flow_dissector_key_vlan {
 	u16	vlan_id:12,
+		vlan_dei:1,
 		vlan_priority:3;
 	__be16	vlan_tpid;
 };
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 7285a19bb135..7b84e014633a 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -3022,6 +3022,11 @@ ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input)
 			match->mask.vlan.vlan_id =
 				ntohs(ext_m_spec->vlan_tci) & 0x0fff;
 
+			match->key.vlan.vlan_dei =
+				!!(ext_h_spec->vlan_tci & htons(0x1000));
+			match->mask.vlan.vlan_dei =
+				!!(ext_m_spec->vlan_tci & htons(0x1000));
+
 			match->key.vlan.vlan_priority =
 				(ntohs(ext_h_spec->vlan_tci) & 0xe000) >> 13;
 			match->mask.vlan.vlan_priority =
-- 
2.20.1


From 5fe21cb74263f935571711823ed571c326a436be Mon Sep 17 00:00:00 2001
From: Edward Srouji <edwards@mellanox.com>
Date: Thu, 23 May 2019 19:45:38 +0300
Subject: [PATCH 23/31] net/mlx5: Update pci error handler entries and command
 translation

Add missing entries for create/destroy UCTX and UMEM commands.
This could get us wrong "unknown FW command" error in flows
where we unbind the device or reset the driver.

Also the translation of these commands from opcodes to string
was missing.

Fixes: 6e3722baac04 ("IB/mlx5: Use the correct commands for UMEM and UCTX allocation")
Signed-off-by: Edward Srouji <edwards@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index be48c6440251..c205a80abdec 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -441,6 +441,10 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_CREATE_GENERAL_OBJECT:
 	case MLX5_CMD_OP_MODIFY_GENERAL_OBJECT:
 	case MLX5_CMD_OP_QUERY_GENERAL_OBJECT:
+	case MLX5_CMD_OP_CREATE_UCTX:
+	case MLX5_CMD_OP_DESTROY_UCTX:
+	case MLX5_CMD_OP_CREATE_UMEM:
+	case MLX5_CMD_OP_DESTROY_UMEM:
 	case MLX5_CMD_OP_ALLOC_MEMIC:
 		*status = MLX5_DRIVER_STATUS_ABORTED;
 		*synd = MLX5_DRIVER_SYND;
@@ -629,6 +633,10 @@ const char *mlx5_command_str(int command)
 	MLX5_COMMAND_STR_CASE(ALLOC_MEMIC);
 	MLX5_COMMAND_STR_CASE(DEALLOC_MEMIC);
 	MLX5_COMMAND_STR_CASE(QUERY_HOST_PARAMS);
+	MLX5_COMMAND_STR_CASE(CREATE_UCTX);
+	MLX5_COMMAND_STR_CASE(DESTROY_UCTX);
+	MLX5_COMMAND_STR_CASE(CREATE_UMEM);
+	MLX5_COMMAND_STR_CASE(DESTROY_UMEM);
 	default: return "unknown command opcode";
 	}
 }
-- 
2.20.1


From 85963ab815267cea714cb009795b712215f3154b Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Tue, 11 Jun 2019 10:19:41 +0300
Subject: [PATCH 24/31] mlxsw: spectrum_router: Refresh nexthop neighbour when
 it becomes dead

The driver tries to periodically refresh neighbours that are used to
reach nexthops. This is done by periodically calling neigh_event_send().

However, if the neighbour becomes dead, there is nothing we can do to
return it to a connected state and the above function call is basically
a NOP.

This results in the nexthop never being written to the device's
adjacency table and therefore never used to forward packets.

Fix this by dropping our reference from the dead neighbour and
associating the nexthop with a new neigbhour which we will try to
refresh.

Fixes: a7ff87acd995 ("mlxsw: spectrum_router: Implement next-hop routing")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Alex Veber <alexve@mellanox.com>
Tested-by: Alex Veber <alexve@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/spectrum_router.c | 73 ++++++++++++++++++-
 1 file changed, 70 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 902e766a8ed3..18d29b8f763f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -2363,7 +2363,7 @@ static void mlxsw_sp_router_probe_unresolved_nexthops(struct work_struct *work)
 static void
 mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp *mlxsw_sp,
 			      struct mlxsw_sp_neigh_entry *neigh_entry,
-			      bool removing);
+			      bool removing, bool dead);
 
 static enum mlxsw_reg_rauht_op mlxsw_sp_rauht_op(bool adding)
 {
@@ -2494,7 +2494,8 @@ static void mlxsw_sp_router_neigh_event_work(struct work_struct *work)
 
 	memcpy(neigh_entry->ha, ha, ETH_ALEN);
 	mlxsw_sp_neigh_entry_update(mlxsw_sp, neigh_entry, entry_connected);
-	mlxsw_sp_nexthop_neigh_update(mlxsw_sp, neigh_entry, !entry_connected);
+	mlxsw_sp_nexthop_neigh_update(mlxsw_sp, neigh_entry, !entry_connected,
+				      dead);
 
 	if (!neigh_entry->connected && list_empty(&neigh_entry->nexthop_list))
 		mlxsw_sp_neigh_entry_destroy(mlxsw_sp, neigh_entry);
@@ -3458,13 +3459,79 @@ static void __mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp_nexthop *nh,
 	nh->update = 1;
 }
 
+static int
+mlxsw_sp_nexthop_dead_neigh_replace(struct mlxsw_sp *mlxsw_sp,
+				    struct mlxsw_sp_neigh_entry *neigh_entry)
+{
+	struct neighbour *n, *old_n = neigh_entry->key.n;
+	struct mlxsw_sp_nexthop *nh;
+	bool entry_connected;
+	u8 nud_state, dead;
+	int err;
+
+	nh = list_first_entry(&neigh_entry->nexthop_list,
+			      struct mlxsw_sp_nexthop, neigh_list_node);
+
+	n = neigh_lookup(nh->nh_grp->neigh_tbl, &nh->gw_addr, nh->rif->dev);
+	if (!n) {
+		n = neigh_create(nh->nh_grp->neigh_tbl, &nh->gw_addr,
+				 nh->rif->dev);
+		if (IS_ERR(n))
+			return PTR_ERR(n);
+		neigh_event_send(n, NULL);
+	}
+
+	mlxsw_sp_neigh_entry_remove(mlxsw_sp, neigh_entry);
+	neigh_entry->key.n = n;
+	err = mlxsw_sp_neigh_entry_insert(mlxsw_sp, neigh_entry);
+	if (err)
+		goto err_neigh_entry_insert;
+
+	read_lock_bh(&n->lock);
+	nud_state = n->nud_state;
+	dead = n->dead;
+	read_unlock_bh(&n->lock);
+	entry_connected = nud_state & NUD_VALID && !dead;
+
+	list_for_each_entry(nh, &neigh_entry->nexthop_list,
+			    neigh_list_node) {
+		neigh_release(old_n);
+		neigh_clone(n);
+		__mlxsw_sp_nexthop_neigh_update(nh, !entry_connected);
+		mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nh_grp);
+	}
+
+	neigh_release(n);
+
+	return 0;
+
+err_neigh_entry_insert:
+	neigh_entry->key.n = old_n;
+	mlxsw_sp_neigh_entry_insert(mlxsw_sp, neigh_entry);
+	neigh_release(n);
+	return err;
+}
+
 static void
 mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp *mlxsw_sp,
 			      struct mlxsw_sp_neigh_entry *neigh_entry,
-			      bool removing)
+			      bool removing, bool dead)
 {
 	struct mlxsw_sp_nexthop *nh;
 
+	if (list_empty(&neigh_entry->nexthop_list))
+		return;
+
+	if (dead) {
+		int err;
+
+		err = mlxsw_sp_nexthop_dead_neigh_replace(mlxsw_sp,
+							  neigh_entry);
+		if (err)
+			dev_err(mlxsw_sp->bus_info->dev, "Failed to replace dead neigh\n");
+		return;
+	}
+
 	list_for_each_entry(nh, &neigh_entry->nexthop_list,
 			    neigh_list_node) {
 		__mlxsw_sp_nexthop_neigh_update(nh, removing);
-- 
2.20.1


From 89c4f1649cef23a00072fef8c21f84e289a5defe Mon Sep 17 00:00:00 2001
From: Chris Mi <chrism@mellanox.com>
Date: Thu, 16 May 2019 17:36:43 +0800
Subject: [PATCH 25/31] net/mlx5e: Add ndo_set_feature for uplink representor

After we have a dedicated uplink representor, the new netdev ops
doesn't support ndo_set_feature. Because of that, we can't change
some features, eg. rxvlan. Now add it back.

In this patch, I also do a cleanup for the features flag handling,
eg. remove duplicate NETIF_F_HW_TC flag setting.

Fixes: aec002f6f82c ("net/mlx5e: Uninstantiate esw manager vport netdev on switchdev mode")
Signed-off-by: Chris Mi <chrism@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      |  1 +
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c |  3 +--
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c  | 10 ++++++----
 3 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index d3eaf2ceaa39..a80031b2cfaf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -1059,6 +1059,7 @@ void mlx5e_del_vxlan_port(struct net_device *netdev, struct udp_tunnel_info *ti)
 netdev_features_t mlx5e_features_check(struct sk_buff *skb,
 				       struct net_device *netdev,
 				       netdev_features_t features);
+int mlx5e_set_features(struct net_device *netdev, netdev_features_t features);
 #ifdef CONFIG_MLX5_ESWITCH
 int mlx5e_set_vf_mac(struct net_device *dev, int vf, u8 *mac);
 int mlx5e_set_vf_rate(struct net_device *dev, int vf, int min_tx_rate, int max_tx_rate);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 1e2688e2ed47..7aa900630d67 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3698,8 +3698,7 @@ static int mlx5e_handle_feature(struct net_device *netdev,
 	return 0;
 }
 
-static int mlx5e_set_features(struct net_device *netdev,
-			      netdev_features_t features)
+int mlx5e_set_features(struct net_device *netdev, netdev_features_t features)
 {
 	netdev_features_t oper_features = netdev->features;
 	int err = 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 0b09fa91019d..fd8cede040b8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1350,6 +1350,7 @@ static const struct net_device_ops mlx5e_netdev_ops_uplink_rep = {
 	.ndo_get_vf_stats        = mlx5e_get_vf_stats,
 	.ndo_set_vf_vlan         = mlx5e_uplink_rep_set_vf_vlan,
 	.ndo_get_port_parent_id	 = mlx5e_rep_get_port_parent_id,
+	.ndo_set_features        = mlx5e_set_features,
 };
 
 bool mlx5e_eswitch_rep(struct net_device *netdev)
@@ -1423,10 +1424,9 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev)
 
 	netdev->watchdog_timeo    = 15 * HZ;
 
+	netdev->features       |= NETIF_F_NETNS_LOCAL;
 
-	netdev->features	 |= NETIF_F_HW_TC | NETIF_F_NETNS_LOCAL;
-	netdev->hw_features      |= NETIF_F_HW_TC;
-
+	netdev->hw_features    |= NETIF_F_HW_TC;
 	netdev->hw_features    |= NETIF_F_SG;
 	netdev->hw_features    |= NETIF_F_IP_CSUM;
 	netdev->hw_features    |= NETIF_F_IPV6_CSUM;
@@ -1435,7 +1435,9 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev)
 	netdev->hw_features    |= NETIF_F_TSO6;
 	netdev->hw_features    |= NETIF_F_RXCSUM;
 
-	if (rep->vport != MLX5_VPORT_UPLINK)
+	if (rep->vport == MLX5_VPORT_UPLINK)
+		netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX;
+	else
 		netdev->features |= NETIF_F_VLAN_CHALLENGED;
 
 	netdev->features |= netdev->hw_features;
-- 
2.20.1


From 912ed09c5d79ede9912890a95fe644bb7a7b21d3 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Tue, 11 Jun 2019 10:19:43 +0300
Subject: [PATCH 26/31] mlxsw: spectrum_flower: Fix TOS matching

The TOS value was not extracted correctly. Fix it.

Fixes: 87996f91f739 ("mlxsw: spectrum_flower: Add support for ip tos")
Reported-by: Alexander Petrovskiy <alexpe@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
index 15f804453cd6..96b23c856f4d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
@@ -247,8 +247,8 @@ static int mlxsw_sp_flower_parse_ip(struct mlxsw_sp *mlxsw_sp,
 				       match.mask->tos & 0x3);
 
 	mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_IP_DSCP,
-				       match.key->tos >> 6,
-				       match.mask->tos >> 6);
+				       match.key->tos >> 2,
+				       match.mask->tos >> 2);
 
 	return 0;
 }
-- 
2.20.1


From ad580668508bbc6eb476d84010cac626432bb7be Mon Sep 17 00:00:00 2001
From: Raed Salem <raeds@mellanox.com>
Date: Sun, 2 Jun 2019 12:04:08 +0300
Subject: [PATCH 27/31] net/mlx5e: Fix source port matching in fdb peer flow
 rule

The cited commit changed the initialization placement of the eswitch
attributes so it is done prior to parse tc actions function call,
including among others the in_rep and in_mdev fields which are mistakenly
reassigned inside the parse actions function.

This breaks the source port matching criteria of the peer redirect rule.

Fix by removing the now redundant reassignment of the already initialized
fields.

Fixes: 988ab9c7363a ("net/mlx5e: Introduce mlx5e_flow_esw_attr_init() helper")
Signed-off-by: Raed Salem <raeds@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 4cb23631616b..a43ddfc0ff0b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2572,9 +2572,6 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 	if (!flow_action_has_entries(flow_action))
 		return -EINVAL;
 
-	attr->in_rep = rpriv->rep;
-	attr->in_mdev = priv->mdev;
-
 	flow_action_for_each(i, act, flow_action) {
 		switch (act->id) {
 		case FLOW_ACTION_DROP:
-- 
2.20.1


From 1a4cd57a5462ae46bb58229b6336adba8d0f78d2 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Tue, 11 Jun 2019 10:19:45 +0300
Subject: [PATCH 28/31] mlxsw: spectrum_buffers: Reduce pool size on Spectrum-2

Due to an issue on Spectrum-2, in front-panel ports split four ways, 2 out
of 32 port buffers cannot be used. To work around this, the next FW release
will mark them as unused, and will report correspondingly lower total
shared buffer size. mlxsw will pick up the new value through a query to
cap_total_buffer_size resource. However the initial size for shared buffer
pool 0 is hard-coded and therefore needs to be updated.

Thus reduce the pool size by 2.7 MiB (which corresponds to 2/32 of the
total size of 42 MiB), and round down to the whole number of cells.

Fixes: fe099bf682ab ("mlxsw: spectrum_buffers: Add Spectrum-2 shared buffer configuration")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
index d633bef5f105..77fe3ed38d1b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
@@ -411,9 +411,9 @@ static const struct mlxsw_sp_sb_pr mlxsw_sp1_sb_prs[] = {
 	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, MLXSW_SP_SB_INFI),
 };
 
-#define MLXSW_SP2_SB_PR_INGRESS_SIZE	40960000
+#define MLXSW_SP2_SB_PR_INGRESS_SIZE	38128752
+#define MLXSW_SP2_SB_PR_EGRESS_SIZE	38128752
 #define MLXSW_SP2_SB_PR_INGRESS_MNG_SIZE (200 * 1000)
-#define MLXSW_SP2_SB_PR_EGRESS_SIZE	40960000
 
 static const struct mlxsw_sp_sb_pr mlxsw_sp2_sb_prs[] = {
 	/* Ingress pools. */
-- 
2.20.1


From 2ed0a95050dacab48f4468ed40dc2746dbcb31bc Mon Sep 17 00:00:00 2001
From: Eli Britstein <elibr@mellanox.com>
Date: Sun, 2 Jun 2019 13:47:59 +0000
Subject: [PATCH 29/31] net/mlx5e: Support tagged tunnel over bond

Stacked devices like bond interface may have a VLAN device on top of
them. Detect lag state correctly under this condition, and return the
correct routed net device, according to it the encap header is built.

Fixes: e32ee6c78efa ("net/mlx5e: Support tunnel encap over tagged Ethernet")
Signed-off-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index eec07b34b4ad..5efe9b5d9086 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -11,24 +11,25 @@ static int get_route_and_out_devs(struct mlx5e_priv *priv,
 				  struct net_device **route_dev,
 				  struct net_device **out_dev)
 {
+	struct net_device *uplink_dev, *uplink_upper, *real_dev;
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-	struct net_device *uplink_dev, *uplink_upper;
 	bool dst_is_lag_dev;
 
+	real_dev = is_vlan_dev(dev) ? vlan_dev_real_dev(dev) : dev;
 	uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH);
 	uplink_upper = netdev_master_upper_dev_get(uplink_dev);
 	dst_is_lag_dev = (uplink_upper &&
 			  netif_is_lag_master(uplink_upper) &&
-			  dev == uplink_upper &&
+			  real_dev == uplink_upper &&
 			  mlx5_lag_is_sriov(priv->mdev));
 
 	/* if the egress device isn't on the same HW e-switch or
 	 * it's a LAG device, use the uplink
 	 */
-	if (!netdev_port_same_parent_id(priv->netdev, dev) ||
+	if (!netdev_port_same_parent_id(priv->netdev, real_dev) ||
 	    dst_is_lag_dev) {
-		*route_dev = uplink_dev;
-		*out_dev = *route_dev;
+		*route_dev = dev;
+		*out_dev = uplink_dev;
 	} else {
 		*route_dev = dev;
 		if (is_vlan_dev(*route_dev))
-- 
2.20.1


From 1116c2e1d200ad80e9aea49bbf129636726c8014 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 7 Jun 2019 17:57:48 -0400
Subject: [PATCH 30/31] net: correct udp zerocopy refcnt also when zerocopy
 only on append

[ Upstream commit 522924b583082f51b8a2406624a2f27c22119b20 ]

The below patch fixes an incorrect zerocopy refcnt increment when
appending with MSG_MORE to an existing zerocopy udp skb.

  send(.., MSG_ZEROCOPY | MSG_MORE);	// refcnt 1
  send(.., MSG_ZEROCOPY | MSG_MORE);	// refcnt still 1 (bar frags)

But it missed that zerocopy need not be passed at the first send. The
right test whether the uarg is newly allocated and thus has extra
refcnt 1 is not !skb, but !skb_zcopy.

  send(.., MSG_MORE);			// <no uarg>
  send(.., MSG_ZEROCOPY);		// refcnt 1

Fixes: 100f6d8e09905 ("net: correct zerocopy refcnt with udp MSG_MORE")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_output.c  | 2 +-
 net/ipv6/ip6_output.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index ac770940adb9..1086c3ccb601 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -923,7 +923,7 @@ static int __ip_append_data(struct sock *sk,
 		uarg = sock_zerocopy_realloc(sk, length, skb_zcopy(skb));
 		if (!uarg)
 			return -ENOBUFS;
-		extra_uref = !skb;	/* only extra ref if !MSG_MORE */
+		extra_uref = !skb_zcopy(skb);	/* only ref on new uarg */
 		if (rt->dst.dev->features & NETIF_F_SG &&
 		    csummode == CHECKSUM_PARTIAL) {
 			paged = true;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index b5e0c85bcd57..ed9f6a7d224b 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1344,7 +1344,7 @@ static int __ip6_append_data(struct sock *sk,
 		uarg = sock_zerocopy_realloc(sk, length, skb_zcopy(skb));
 		if (!uarg)
 			return -ENOBUFS;
-		extra_uref = !skb;	/* only extra ref if !MSG_MORE */
+		extra_uref = !skb_zcopy(skb);	/* only ref on new uarg */
 		if (rt->dst.dev->features & NETIF_F_SG &&
 		    csummode == CHECKSUM_PARTIAL) {
 			paged = true;
-- 
2.20.1


From 6379b256d6f5c19a01d0141e001ebb0fa81f5b9f Mon Sep 17 00:00:00 2001
From: Alaa Hleihel <alaa@mellanox.com>
Date: Sun, 26 May 2019 11:56:27 +0300
Subject: [PATCH 31/31] net/mlx5e: Avoid detaching non-existing netdev under
 switchdev mode

After introducing dedicated uplink representor, the netdev instance
set over the esw manager vport (PF) became no longer in use, so it was
removed in the cited commit once we're on switchdev mode.
However, the mlx5e_detach function was not updated accordingly, and it
still tries to detach a non-existing netdev, causing a kernel crash.

This patch fixes this issue.

Fixes: aec002f6f82c ("net/mlx5e: Uninstantiate esw manager vport netdev on switchdev mode")
Signed-off-by: Alaa Hleihel <alaa@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 7aa900630d67..6a8dc73855c9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -5165,6 +5165,11 @@ static void mlx5e_detach(struct mlx5_core_dev *mdev, void *vpriv)
 	struct mlx5e_priv *priv = vpriv;
 	struct net_device *netdev = priv->netdev;
 
+#ifdef CONFIG_MLX5_ESWITCH
+	if (MLX5_ESWITCH_MANAGER(mdev) && vpriv == mdev)
+		return;
+#endif
+
 	if (!netif_device_present(netdev))
 		return;
 
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Mon, Jun 17, 2019 at 09:23:43PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.19 and v5.1
> -stable, respectively.

All now applied, thanks.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 91 bytes --]


Please apply the following bug fixes to v4.19 and v5.1 -stable,
respectively.

Thank you.

[-- Attachment #2: net_419.mbox --]
[-- Type: Application/Octet-Stream, Size: 31358 bytes --]

From 587d456dd1153d024c91468376e7a27666264f4c Mon Sep 17 00:00:00 2001
From: Neil Horman <nhorman@tuxdriver.com>
Date: Tue, 25 Jun 2019 17:57:49 -0400
Subject: [PATCH 01/13] af_packet: Block execution of tasks waiting for
 transmit to complete in AF_PACKET

[ Upstream commit 89ed5b519004a7706f50b70f611edbd3aaacff2c ]

When an application is run that:
a) Sets its scheduler to be SCHED_FIFO
and
b) Opens a memory mapped AF_PACKET socket, and sends frames with the
MSG_DONTWAIT flag cleared, its possible for the application to hang
forever in the kernel.  This occurs because when waiting, the code in
tpacket_snd calls schedule, which under normal circumstances allows
other tasks to run, including ksoftirqd, which in some cases is
responsible for freeing the transmitted skb (which in AF_PACKET calls a
destructor that flips the status bit of the transmitted frame back to
available, allowing the transmitting task to complete).

However, when the calling application is SCHED_FIFO, its priority is
such that the schedule call immediately places the task back on the cpu,
preventing ksoftirqd from freeing the skb, which in turn prevents the
transmitting task from detecting that the transmission is complete.

We can fix this by converting the schedule call to a completion
mechanism.  By using a completion queue, we force the calling task, when
it detects there are no more frames to send, to schedule itself off the
cpu until such time as the last transmitted skb is freed, allowing
forward progress to be made.

Tested by myself and the reporter, with good results

Change Notes:

V1->V2:
	Enhance the sleep logic to support being interruptible and
allowing for honoring to SK_SNDTIMEO (Willem de Bruijn)

V2->V3:
	Rearrage the point at which we wait for the completion queue, to
avoid needing to check for ph/skb being null at the end of the loop.
Also move the complete call to the skb destructor to avoid needing to
modify __packet_set_status.  Also gate calling complete on
packet_read_pending returning zero to avoid multiple calls to complete.
(Willem de Bruijn)

	Move timeo computation within loop, to re-fetch the socket
timeout since we also use the timeo variable to record the return code
from the wait_for_complete call (Neil Horman)

V3->V4:
	Willem has requested that the control flow be restored to the
previous state.  Doing so lets us eliminate the need for the
po->wait_on_complete flag variable, and lets us get rid of the
packet_next_frame function, but introduces another complexity.
Specifically, but using the packet pending count, we can, if an
applications calls sendmsg multiple times with MSG_DONTWAIT set, each
set of transmitted frames, when complete, will cause
tpacket_destruct_skb to issue a complete call, for which there will
never be a wait_on_completion call.  This imbalance will lead to any
future call to wait_for_completion here to return early, when the frames
they sent may not have completed.  To correct this, we need to re-init
the completion queue on every call to tpacket_snd before we enter the
loop so as to ensure we wait properly for the frames we send in this
iteration.

	Change the timeout and interrupted gotos to out_put rather than
out_status so that we don't try to free a non-existant skb
	Clean up some extra newlines (Willem de Bruijn)

Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Reported-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 20 +++++++++++++++++---
 net/packet/internal.h  |  1 +
 2 files changed, 18 insertions(+), 3 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index d98fcf926166..5ad6111657f8 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2399,6 +2399,9 @@ static void tpacket_destruct_skb(struct sk_buff *skb)
 
 		ts = __packet_set_timestamp(po, ph, skb);
 		__packet_set_status(po, ph, TP_STATUS_AVAILABLE | ts);
+
+		if (!packet_read_pending(&po->tx_ring))
+			complete(&po->skb_completion);
 	}
 
 	sock_wfree(skb);
@@ -2594,7 +2597,7 @@ static int tpacket_parse_header(struct packet_sock *po, void *frame,
 
 static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 {
-	struct sk_buff *skb;
+	struct sk_buff *skb = NULL;
 	struct net_device *dev;
 	struct virtio_net_hdr *vnet_hdr = NULL;
 	struct sockcm_cookie sockc;
@@ -2609,6 +2612,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 	int len_sum = 0;
 	int status = TP_STATUS_AVAILABLE;
 	int hlen, tlen, copylen = 0;
+	long timeo = 0;
 
 	mutex_lock(&po->pg_vec_lock);
 
@@ -2655,12 +2659,21 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 	if ((size_max > dev->mtu + reserve + VLAN_HLEN) && !po->has_vnet_hdr)
 		size_max = dev->mtu + reserve + VLAN_HLEN;
 
+	reinit_completion(&po->skb_completion);
+
 	do {
 		ph = packet_current_frame(po, &po->tx_ring,
 					  TP_STATUS_SEND_REQUEST);
 		if (unlikely(ph == NULL)) {
-			if (need_wait && need_resched())
-				schedule();
+			if (need_wait && skb) {
+				timeo = sock_sndtimeo(&po->sk, msg->msg_flags & MSG_DONTWAIT);
+				timeo = wait_for_completion_interruptible_timeout(&po->skb_completion, timeo);
+				if (timeo <= 0) {
+					err = !timeo ? -ETIMEDOUT : -ERESTARTSYS;
+					goto out_put;
+				}
+			}
+			/* check for additional frames */
 			continue;
 		}
 
@@ -3216,6 +3229,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol,
 	sock_init_data(sock, sk);
 
 	po = pkt_sk(sk);
+	init_completion(&po->skb_completion);
 	sk->sk_family = PF_PACKET;
 	po->num = proto;
 	po->xmit = dev_queue_xmit;
diff --git a/net/packet/internal.h b/net/packet/internal.h
index 3bb7c5fb3bff..c70a2794456f 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -128,6 +128,7 @@ struct packet_sock {
 	unsigned int		tp_hdrlen;
 	unsigned int		tp_reserve;
 	unsigned int		tp_tstamp;
+	struct completion	skb_completion;
 	struct net_device __rcu	*cached_dev;
 	int			(*xmit)(struct sk_buff *skb);
 	struct packet_type	prot_hook ____cacheline_aligned_in_smp;
-- 
2.20.1


From d2f21ebc4bd259f5bef13765de0b42896bb8ed53 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 26 Jun 2019 16:08:44 +0800
Subject: [PATCH 02/13] bonding: Always enable vlan tx offload

[ Upstream commit 30d8177e8ac776d89d387fad547af6a0f599210e ]

We build vlan on top of bonding interface, which vlan offload
is off, bond mode is 802.3ad (LACP) and xmit_hash_policy is
BOND_XMIT_POLICY_ENCAP34.

Because vlan tx offload is off, vlan tci is cleared and skb push
the vlan header in validate_xmit_vlan() while sending from vlan
devices. Then in bond_xmit_hash, __skb_flow_dissect() fails to
get information from protocol headers encapsulated within vlan,
because 'nhoff' is points to IP header, so bond hashing is based
on layer 2 info, which fails to distribute packets across slaves.

This patch always enable bonding's vlan tx offload, pass the vlan
packets to the slave devices with vlan tci, let them to handle
vlan implementation.

Fixes: 278339a42a1b ("bonding: propogate vlan_features to bonding master")
Suggested-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 039beb5e0fa2..7e162fff01ab 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -4307,12 +4307,12 @@ void bond_setup(struct net_device *bond_dev)
 	bond_dev->features |= NETIF_F_NETNS_LOCAL;
 
 	bond_dev->hw_features = BOND_VLAN_FEATURES |
-				NETIF_F_HW_VLAN_CTAG_TX |
 				NETIF_F_HW_VLAN_CTAG_RX |
 				NETIF_F_HW_VLAN_CTAG_FILTER;
 
 	bond_dev->hw_features |= NETIF_F_GSO_ENCAP_ALL | NETIF_F_GSO_UDP_L4;
 	bond_dev->features |= bond_dev->hw_features;
+	bond_dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
 }
 
 /* Destroy a bonding device.
-- 
2.20.1


From 4cbb5ae78a5882f8681b16422a323dbb2119e982 Mon Sep 17 00:00:00 2001
From: Stephen Suryaputra <ssuryaextr@gmail.com>
Date: Mon, 24 Jun 2019 20:14:06 -0400
Subject: [PATCH 03/13] ipv4: Use return value of inet_iif() for
 __raw_v4_lookup in the while loop

[ Upstream commit 38c73529de13e1e10914de7030b659a2f8b01c3b ]

In commit 19e4e768064a8 ("ipv4: Fix raw socket lookup for local
traffic"), the dif argument to __raw_v4_lookup() is coming from the
returned value of inet_iif() but the change was done only for the first
lookup. Subsequent lookups in the while loop still use skb->dev->ifIndex.

Fixes: 19e4e768064a8 ("ipv4: Fix raw socket lookup for local traffic")
Signed-off-by: Stephen Suryaputra <ssuryaextr@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/raw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 711a5c75bd4b..21800979ed62 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -202,7 +202,7 @@ static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash)
 		}
 		sk = __raw_v4_lookup(net, sk_next(sk), iph->protocol,
 				     iph->saddr, iph->daddr,
-				     skb->dev->ifindex, sdif);
+				     dif, sdif);
 	}
 out:
 	read_unlock(&raw_v4_hashinfo.lock);
-- 
2.20.1


From f2b6d65b8396e8488c6c309bdc25f2aeab95d909 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 24 Jun 2019 02:38:20 -0700
Subject: [PATCH 04/13] net/packet: fix memory leak in packet_set_ring()

[ Upstream commit 55655e3d1197fff16a7a05088fb0e5eba50eac55 ]

syzbot found we can leak memory in packet_set_ring(), if user application
provides buggy parameters.

Fixes: 7f953ab2ba46 ("af_packet: TX_RING support for TPACKET_V3")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 5ad6111657f8..93b5a4200585 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -4316,7 +4316,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 				    req3->tp_sizeof_priv ||
 				    req3->tp_feature_req_word) {
 					err = -EINVAL;
-					goto out;
+					goto out_free_pg_vec;
 				}
 			}
 			break;
@@ -4380,6 +4380,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 			prb_shutdown_retire_blk_timer(po, rb_queue);
 	}
 
+out_free_pg_vec:
 	if (pg_vec)
 		free_pg_vec(pg_vec, order, req->tp_block_nr);
 out:
-- 
2.20.1


From db4dd4b01632500a1747ff8f2c201bc0799978ed Mon Sep 17 00:00:00 2001
From: JingYi Hou <houjingyi647@gmail.com>
Date: Mon, 17 Jun 2019 14:56:05 +0800
Subject: [PATCH 05/13] net: remove duplicate fetch in sock_getsockopt

[ Upstream commit d0bae4a0e3d8c5690a885204d7eb2341a5b4884d ]

In sock_getsockopt(), 'optlen' is fetched the first time from userspace.
'len < 0' is then checked. Then in condition 'SO_MEMINFO', 'optlen' is
fetched the second time from userspace.

If change it between two fetches may cause security problems or unexpected
behaivor, and there is no reason to fetch it a second time.

To fix this, we need to remove the second fetch.

Signed-off-by: JingYi Hou <houjingyi647@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index c9668dcb5eb9..9c32e8eb64da 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1348,9 +1348,6 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 	{
 		u32 meminfo[SK_MEMINFO_VARS];
 
-		if (get_user(len, optlen))
-			return -EFAULT;
-
 		sk_get_meminfo(sk, meminfo);
 
 		len = min_t(unsigned int, len, sizeof(meminfo));
-- 
2.20.1


From d9f0b41a49cabc30cdaeb0cd53b654959c7f78de Mon Sep 17 00:00:00 2001
From: Roland Hii <roland.king.guan.hii@intel.com>
Date: Wed, 19 Jun 2019 22:13:48 +0800
Subject: [PATCH 06/13] net: stmmac: fixed new system time seconds value
 calculation

[ Upstream commit a1e5388b4d5fc78688e5e9ee6641f779721d6291 ]

When ADDSUB bit is set, the system time seconds field is calculated as
the complement of the seconds part of the update value.

For example, if 3.000000001 seconds need to be subtracted from the
system time, this field is calculated as
2^32 - 3 = 4294967296 - 3 = 0x100000000 - 3 = 0xFFFFFFFD

Previously, the 0x100000000 is mistakenly written as 100000000.

This is further simplified from
  sec = (0x100000000ULL - sec);
to
  sec = -sec;

Fixes: ba1ffd74df74 ("stmmac: fix PTP support for GMAC4")
Signed-off-by: Roland Hii <roland.king.guan.hii@intel.com>
Signed-off-by: Ong Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: Voon Weifeng <weifeng.voon@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
index 8d9cc2157afd..7423262ce590 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
@@ -122,7 +122,7 @@ static int adjust_systime(void __iomem *ioaddr, u32 sec, u32 nsec,
 		 * programmed with (2^32 – <new_sec_value>)
 		 */
 		if (gmac4)
-			sec = (100000000ULL - sec);
+			sec = -sec;
 
 		value = readl(ioaddr + PTP_TCR);
 		if (value & PTP_TCR_TSCTRLSSR)
-- 
2.20.1


From 2f3f50741ce36d919b86fc7d14d137273ca6ffd8 Mon Sep 17 00:00:00 2001
From: Roland Hii <roland.king.guan.hii@intel.com>
Date: Wed, 19 Jun 2019 22:41:48 +0800
Subject: [PATCH 07/13] net: stmmac: set IC bit when transmitting frames with
 HW timestamp

[ Upstream commit d0bb82fd60183868f46c8ccc595a3d61c3334a18 ]

When transmitting certain PTP frames, e.g. SYNC and DELAY_REQ, the
PTP daemon, e.g. ptp4l, is polling the driver for the frame transmit
hardware timestamp. The polling will most likely timeout if the tx
coalesce is enabled due to the Interrupt-on-Completion (IC) bit is
not set in tx descriptor for those frames.

This patch will ignore the tx coalesce parameter and set the IC bit
when transmitting PTP frames which need to report out the frame
transmit hardware timestamp to user space.

Fixes: f748be531d70 ("net: stmmac: Rework coalesce timer and fix multi-queue races")
Signed-off-by: Roland Hii <roland.king.guan.hii@intel.com>
Signed-off-by: Ong Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: Voon Weifeng <weifeng.voon@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/stmicro/stmmac/stmmac_main.c | 22 ++++++++++++-------
 1 file changed, 14 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 45e64d71a93f..5c18874614ba 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2938,12 +2938,15 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	/* Manage tx mitigation */
 	tx_q->tx_count_frames += nfrags + 1;
-	if (priv->tx_coal_frames <= tx_q->tx_count_frames) {
+	if (likely(priv->tx_coal_frames > tx_q->tx_count_frames) &&
+	    !(priv->synopsys_id >= DWMAC_CORE_4_00 &&
+	    (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
+	    priv->hwts_tx_en)) {
+		stmmac_tx_timer_arm(priv, queue);
+	} else {
+		tx_q->tx_count_frames = 0;
 		stmmac_set_tx_ic(priv, desc);
 		priv->xstats.tx_set_ic_bit++;
-		tx_q->tx_count_frames = 0;
-	} else {
-		stmmac_tx_timer_arm(priv, queue);
 	}
 
 	skb_tx_timestamp(skb);
@@ -3157,12 +3160,15 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 	 * element in case of no SG.
 	 */
 	tx_q->tx_count_frames += nfrags + 1;
-	if (priv->tx_coal_frames <= tx_q->tx_count_frames) {
+	if (likely(priv->tx_coal_frames > tx_q->tx_count_frames) &&
+	    !(priv->synopsys_id >= DWMAC_CORE_4_00 &&
+	    (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
+	    priv->hwts_tx_en)) {
+		stmmac_tx_timer_arm(priv, queue);
+	} else {
+		tx_q->tx_count_frames = 0;
 		stmmac_set_tx_ic(priv, desc);
 		priv->xstats.tx_set_ic_bit++;
-		tx_q->tx_count_frames = 0;
-	} else {
-		stmmac_tx_timer_arm(priv, queue);
 	}
 
 	skb_tx_timestamp(skb);
-- 
2.20.1


From 94d5ee31c76ade379386c0a6b5c9a806ac89676f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Mon, 24 Jun 2019 18:45:11 +0200
Subject: [PATCH 08/13] qmi_wwan: Fix out-of-bounds read
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 904d88d743b0c94092c5117955eab695df8109e8 ]

The syzbot reported

 Call Trace:
  __dump_stack lib/dump_stack.c:77 [inline]
  dump_stack+0xca/0x13e lib/dump_stack.c:113
  print_address_description+0x67/0x231 mm/kasan/report.c:188
  __kasan_report.cold+0x1a/0x32 mm/kasan/report.c:317
  kasan_report+0xe/0x20 mm/kasan/common.c:614
  qmi_wwan_probe+0x342/0x360 drivers/net/usb/qmi_wwan.c:1417
  usb_probe_interface+0x305/0x7a0 drivers/usb/core/driver.c:361
  really_probe+0x281/0x660 drivers/base/dd.c:509
  driver_probe_device+0x104/0x210 drivers/base/dd.c:670
  __device_attach_driver+0x1c2/0x220 drivers/base/dd.c:777
  bus_for_each_drv+0x15c/0x1e0 drivers/base/bus.c:454

Caused by too many confusing indirections and casts.
id->driver_info is a pointer stored in a long.  We want the
pointer here, not the address of it.

Thanks-to: Hillf Danton <hdanton@sina.com>
Reported-by: syzbot+b68605d7fadd21510de1@syzkaller.appspotmail.com
Cc: Kristian Evensen <kristian.evensen@gmail.com>
Fixes: e4bf63482c30 ("qmi_wwan: Add quirk for Quectel dynamic config")
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index d9a6699abe59..e657d8947125 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1412,7 +1412,7 @@ static int qmi_wwan_probe(struct usb_interface *intf,
 	 * different. Ignore the current interface if the number of endpoints
 	 * equals the number for the diag interface (two).
 	 */
-	info = (void *)&id->driver_info;
+	info = (void *)id->driver_info;
 
 	if (info->data & QMI_WWAN_QUIRK_QUECTEL_DYNCFG) {
 		if (desc->bNumEndpoints == 2)
-- 
2.20.1


From 0402f6b22767c3baad534cb7b70f7740d1915168 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 25 Jun 2019 00:21:45 +0800
Subject: [PATCH 09/13] sctp: change to hold sk after auth shkey is created
 successfully

[ Upstream commit 25bff6d5478b2a02368097015b7d8eb727c87e16 ]

Now in sctp_endpoint_init(), it holds the sk then creates auth
shkey. But when the creation fails, it doesn't release the sk,
which causes a sk defcnf leak,

Here to fix it by only holding the sk when auth shkey is created
successfully.

Fixes: a29a5bd4f5c3 ("[SCTP]: Implement SCTP-AUTH initializations.")
Reported-by: syzbot+afabda3890cc2f765041@syzkaller.appspotmail.com
Reported-by: syzbot+276ca1c77a19977c0130@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/endpointola.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c
index 40c7eb941bc9..c99114eaf42e 100644
--- a/net/sctp/endpointola.c
+++ b/net/sctp/endpointola.c
@@ -126,10 +126,6 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep,
 	/* Initialize the bind addr area */
 	sctp_bind_addr_init(&ep->base.bind_addr, 0);
 
-	/* Remember who we are attached to.  */
-	ep->base.sk = sk;
-	sock_hold(ep->base.sk);
-
 	/* Create the lists of associations.  */
 	INIT_LIST_HEAD(&ep->asocs);
 
@@ -167,6 +163,10 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep,
 	ep->prsctp_enable = net->sctp.prsctp_enable;
 	ep->reconf_enable = net->sctp.reconf_enable;
 
+	/* Remember who we are attached to.  */
+	ep->base.sk = sk;
+	sock_hold(ep->base.sk);
+
 	return ep;
 
 nomem_hmacs:
-- 
2.20.1


From 41193d373bb3fe50f9733b8d3f9f2f2b209d14c3 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Thu, 27 Jun 2019 00:03:39 +0800
Subject: [PATCH 10/13] team: Always enable vlan tx offload

[ Upstream commit ee4297420d56a0033a8593e80b33fcc93fda8509 ]

We should rather have vlan_tci filled all the way down
to the transmitting netdevice and let it do the hw/sw
vlan implementation.

Suggested-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 6c6230b44bcd..dc30f11f4766 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -2139,12 +2139,12 @@ static void team_setup(struct net_device *dev)
 	dev->features |= NETIF_F_NETNS_LOCAL;
 
 	dev->hw_features = TEAM_VLAN_FEATURES |
-			   NETIF_F_HW_VLAN_CTAG_TX |
 			   NETIF_F_HW_VLAN_CTAG_RX |
 			   NETIF_F_HW_VLAN_CTAG_FILTER;
 
 	dev->hw_features |= NETIF_F_GSO_ENCAP_ALL | NETIF_F_GSO_UDP_L4;
 	dev->features |= dev->hw_features;
+	dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
 }
 
 static int team_newlink(struct net *src_net, struct net_device *dev,
-- 
2.20.1


From b9f2f03a6324567be028bc65f0d30b72303a6a4e Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 20 Jun 2019 18:39:28 +0800
Subject: [PATCH 11/13] tipc: change to use register_pernet_device

[ Upstream commit c492d4c74dd3f87559883ffa0f94a8f1ae3fe5f5 ]

This patch is to fix a dst defcnt leak, which can be reproduced by doing:

  # ip net a c; ip net a s; modprobe tipc
  # ip net e s ip l a n eth1 type veth peer n eth1 netns c
  # ip net e c ip l s lo up; ip net e c ip l s eth1 up
  # ip net e s ip l s lo up; ip net e s ip l s eth1 up
  # ip net e c ip a a 1.1.1.2/8 dev eth1
  # ip net e s ip a a 1.1.1.1/8 dev eth1
  # ip net e c tipc b e m udp n u1 localip 1.1.1.2
  # ip net e s tipc b e m udp n u1 localip 1.1.1.1
  # ip net d c; ip net d s; rmmod tipc

and it will get stuck and keep logging the error:

  unregister_netdevice: waiting for lo to become free. Usage count = 1

The cause is that a dst is held by the udp sock's sk_rx_dst set on udp rx
path with udp_early_demux == 1, and this dst (eventually holding lo dev)
can't be released as bearer's removal in tipc pernet .exit happens after
lo dev's removal, default_device pernet .exit.

 "There are two distinct types of pernet_operations recognized: subsys and
  device.  At creation all subsys init functions are called before device
  init functions, and at destruction all device exit functions are called
  before subsys exit function."

So by calling register_pernet_device instead to register tipc_net_ops, the
pernet .exit() will be invoked earlier than loopback dev's removal when a
netns is being destroyed, as fou/gue does.

Note that vxlan and geneve udp tunnels don't have this issue, as the udp
sock is released in their device ndo_stop().

This fix is also necessary for tipc dst_cache, which will hold dsts on tx
path and I will introduce in my next patch.

Reported-by: Li Shuang <shuali@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/core.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/tipc/core.c b/net/tipc/core.c
index 3ecca3b88bf8..eb0f701f9bf1 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -132,7 +132,7 @@ static int __init tipc_init(void)
 	if (err)
 		goto out_sysctl;
 
-	err = register_pernet_subsys(&tipc_net_ops);
+	err = register_pernet_device(&tipc_net_ops);
 	if (err)
 		goto out_pernet;
 
@@ -140,7 +140,7 @@ static int __init tipc_init(void)
 	if (err)
 		goto out_socket;
 
-	err = register_pernet_subsys(&tipc_topsrv_net_ops);
+	err = register_pernet_device(&tipc_topsrv_net_ops);
 	if (err)
 		goto out_pernet_topsrv;
 
@@ -151,11 +151,11 @@ static int __init tipc_init(void)
 	pr_info("Started in single node mode\n");
 	return 0;
 out_bearer:
-	unregister_pernet_subsys(&tipc_topsrv_net_ops);
+	unregister_pernet_device(&tipc_topsrv_net_ops);
 out_pernet_topsrv:
 	tipc_socket_stop();
 out_socket:
-	unregister_pernet_subsys(&tipc_net_ops);
+	unregister_pernet_device(&tipc_net_ops);
 out_pernet:
 	tipc_unregister_sysctl();
 out_sysctl:
@@ -170,9 +170,9 @@ static int __init tipc_init(void)
 static void __exit tipc_exit(void)
 {
 	tipc_bearer_cleanup();
-	unregister_pernet_subsys(&tipc_topsrv_net_ops);
+	unregister_pernet_device(&tipc_topsrv_net_ops);
 	tipc_socket_stop();
-	unregister_pernet_subsys(&tipc_net_ops);
+	unregister_pernet_device(&tipc_net_ops);
 	tipc_netlink_stop();
 	tipc_netlink_compat_stop();
 	tipc_unregister_sysctl();
-- 
2.20.1


From c249fafb837362e99bb344cad8ae117d7dd6798f Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 25 Jun 2019 00:28:19 +0800
Subject: [PATCH 12/13] tipc: check msg->req data len in
 tipc_nl_compat_bearer_disable

[ Upstream commit 4f07b80c973348a99b5d2a32476a2e7877e94a05 ]

This patch is to fix an uninit-value issue, reported by syzbot:

  BUG: KMSAN: uninit-value in memchr+0xce/0x110 lib/string.c:981
  Call Trace:
    __dump_stack lib/dump_stack.c:77 [inline]
    dump_stack+0x191/0x1f0 lib/dump_stack.c:113
    kmsan_report+0x130/0x2a0 mm/kmsan/kmsan.c:622
    __msan_warning+0x75/0xe0 mm/kmsan/kmsan_instr.c:310
    memchr+0xce/0x110 lib/string.c:981
    string_is_valid net/tipc/netlink_compat.c:176 [inline]
    tipc_nl_compat_bearer_disable+0x2a1/0x480 net/tipc/netlink_compat.c:449
    __tipc_nl_compat_doit net/tipc/netlink_compat.c:327 [inline]
    tipc_nl_compat_doit+0x3ac/0xb00 net/tipc/netlink_compat.c:360
    tipc_nl_compat_handle net/tipc/netlink_compat.c:1178 [inline]
    tipc_nl_compat_recv+0x1b1b/0x27b0 net/tipc/netlink_compat.c:1281

TLV_GET_DATA_LEN() may return a negtive int value, which will be
used as size_t (becoming a big unsigned long) passed into memchr,
cause this issue.

Similar to what it does in tipc_nl_compat_bearer_enable(), this
fix is to return -EINVAL when TLV_GET_DATA_LEN() is negtive in
tipc_nl_compat_bearer_disable(), as well as in
tipc_nl_compat_link_stat_dump() and tipc_nl_compat_link_reset_stats().

v1->v2:
  - add the missing Fixes tags per Eric's request.

Fixes: 0762216c0ad2 ("tipc: fix uninit-value in tipc_nl_compat_bearer_enable")
Fixes: 8b66fee7f8ee ("tipc: fix uninit-value in tipc_nl_compat_link_reset_stats")
Reported-by: syzbot+30eaa8bf392f7fafffaf@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/netlink_compat.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 588d5aa14c41..85ebb675600c 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -445,7 +445,11 @@ static int tipc_nl_compat_bearer_disable(struct tipc_nl_compat_cmd_doit *cmd,
 	if (!bearer)
 		return -EMSGSIZE;
 
-	len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_BEARER_NAME);
+	len = TLV_GET_DATA_LEN(msg->req);
+	if (len <= 0)
+		return -EINVAL;
+
+	len = min_t(int, len, TIPC_MAX_BEARER_NAME);
 	if (!string_is_valid(name, len))
 		return -EINVAL;
 
@@ -537,7 +541,11 @@ static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg,
 
 	name = (char *)TLV_DATA(msg->req);
 
-	len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_LINK_NAME);
+	len = TLV_GET_DATA_LEN(msg->req);
+	if (len <= 0)
+		return -EINVAL;
+
+	len = min_t(int, len, TIPC_MAX_BEARER_NAME);
 	if (!string_is_valid(name, len))
 		return -EINVAL;
 
@@ -815,7 +823,11 @@ static int tipc_nl_compat_link_reset_stats(struct tipc_nl_compat_cmd_doit *cmd,
 	if (!link)
 		return -EMSGSIZE;
 
-	len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_LINK_NAME);
+	len = TLV_GET_DATA_LEN(msg->req);
+	if (len <= 0)
+		return -EINVAL;
+
+	len = min_t(int, len, TIPC_MAX_BEARER_NAME);
 	if (!string_is_valid(name, len))
 		return -EINVAL;
 
-- 
2.20.1


From 357c9c731145d14b94a1b9370e0d7d2bc788b3a6 Mon Sep 17 00:00:00 2001
From: Fei Li <lifei.shirley@bytedance.com>
Date: Mon, 17 Jun 2019 21:26:36 +0800
Subject: [PATCH 13/13] tun: wake up waitqueues after IFF_UP is set

[ Upstream commit 72b319dc08b4924a29f5e2560ef6d966fa54c429 ]

Currently after setting tap0 link up, the tun code wakes tx/rx waited
queues up in tun_net_open() when .ndo_open() is called, however the
IFF_UP flag has not been set yet. If there's already a wait queue, it
would fail to transmit when checking the IFF_UP flag in tun_sendmsg().
Then the saving vhost_poll_start() will add the wq into wqh until it
is waken up again. Although this works when IFF_UP flag has been set
when tun_chr_poll detects; this is not true if IFF_UP flag has not
been set at that time. Sadly the latter case is a fatal error, as
the wq will never be waken up in future unless later manually
setting link up on purpose.

Fix this by moving the wakeup process into the NETDEV_UP event
notifying process, this makes sure IFF_UP has been set before all
waited queues been waken up.

Signed-off-by: Fei Li <lifei.shirley@bytedance.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 78d34e0306e0..b67fee56ec81 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1024,18 +1024,8 @@ static void tun_net_uninit(struct net_device *dev)
 /* Net device open. */
 static int tun_net_open(struct net_device *dev)
 {
-	struct tun_struct *tun = netdev_priv(dev);
-	int i;
-
 	netif_tx_start_all_queues(dev);
 
-	for (i = 0; i < tun->numqueues; i++) {
-		struct tun_file *tfile;
-
-		tfile = rtnl_dereference(tun->tfiles[i]);
-		tfile->socket.sk->sk_write_space(tfile->socket.sk);
-	}
-
 	return 0;
 }
 
@@ -3443,6 +3433,7 @@ static int tun_device_event(struct notifier_block *unused,
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct tun_struct *tun = netdev_priv(dev);
+	int i;
 
 	if (dev->rtnl_link_ops != &tun_link_ops)
 		return NOTIFY_DONE;
@@ -3452,6 +3443,14 @@ static int tun_device_event(struct notifier_block *unused,
 		if (tun_queue_resize(tun))
 			return NOTIFY_BAD;
 		break;
+	case NETDEV_UP:
+		for (i = 0; i < tun->numqueues; i++) {
+			struct tun_file *tfile;
+
+			tfile = rtnl_dereference(tun->tfiles[i]);
+			tfile->socket.sk->sk_write_space(tfile->socket.sk);
+		}
+		break;
 	default:
 		break;
 	}
-- 
2.20.1


[-- Attachment #3: net_51.mbox --]
[-- Type: Application/Octet-Stream, Size: 40609 bytes --]

From e3bb85d694007647fb494cc9605eaf218c560e97 Mon Sep 17 00:00:00 2001
From: Neil Horman <nhorman@tuxdriver.com>
Date: Tue, 25 Jun 2019 17:57:49 -0400
Subject: [PATCH 01/15] af_packet: Block execution of tasks waiting for
 transmit to complete in AF_PACKET

[ Upstream commit 89ed5b519004a7706f50b70f611edbd3aaacff2c ]

When an application is run that:
a) Sets its scheduler to be SCHED_FIFO
and
b) Opens a memory mapped AF_PACKET socket, and sends frames with the
MSG_DONTWAIT flag cleared, its possible for the application to hang
forever in the kernel.  This occurs because when waiting, the code in
tpacket_snd calls schedule, which under normal circumstances allows
other tasks to run, including ksoftirqd, which in some cases is
responsible for freeing the transmitted skb (which in AF_PACKET calls a
destructor that flips the status bit of the transmitted frame back to
available, allowing the transmitting task to complete).

However, when the calling application is SCHED_FIFO, its priority is
such that the schedule call immediately places the task back on the cpu,
preventing ksoftirqd from freeing the skb, which in turn prevents the
transmitting task from detecting that the transmission is complete.

We can fix this by converting the schedule call to a completion
mechanism.  By using a completion queue, we force the calling task, when
it detects there are no more frames to send, to schedule itself off the
cpu until such time as the last transmitted skb is freed, allowing
forward progress to be made.

Tested by myself and the reporter, with good results

Change Notes:

V1->V2:
	Enhance the sleep logic to support being interruptible and
allowing for honoring to SK_SNDTIMEO (Willem de Bruijn)

V2->V3:
	Rearrage the point at which we wait for the completion queue, to
avoid needing to check for ph/skb being null at the end of the loop.
Also move the complete call to the skb destructor to avoid needing to
modify __packet_set_status.  Also gate calling complete on
packet_read_pending returning zero to avoid multiple calls to complete.
(Willem de Bruijn)

	Move timeo computation within loop, to re-fetch the socket
timeout since we also use the timeo variable to record the return code
from the wait_for_complete call (Neil Horman)

V3->V4:
	Willem has requested that the control flow be restored to the
previous state.  Doing so lets us eliminate the need for the
po->wait_on_complete flag variable, and lets us get rid of the
packet_next_frame function, but introduces another complexity.
Specifically, but using the packet pending count, we can, if an
applications calls sendmsg multiple times with MSG_DONTWAIT set, each
set of transmitted frames, when complete, will cause
tpacket_destruct_skb to issue a complete call, for which there will
never be a wait_on_completion call.  This imbalance will lead to any
future call to wait_for_completion here to return early, when the frames
they sent may not have completed.  To correct this, we need to re-init
the completion queue on every call to tpacket_snd before we enter the
loop so as to ensure we wait properly for the frames we send in this
iteration.

	Change the timeout and interrupted gotos to out_put rather than
out_status so that we don't try to free a non-existant skb
	Clean up some extra newlines (Willem de Bruijn)

Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Reported-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 20 +++++++++++++++++---
 net/packet/internal.h  |  1 +
 2 files changed, 18 insertions(+), 3 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 71d5544243d2..3385f4c6eb74 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2409,6 +2409,9 @@ static void tpacket_destruct_skb(struct sk_buff *skb)
 
 		ts = __packet_set_timestamp(po, ph, skb);
 		__packet_set_status(po, ph, TP_STATUS_AVAILABLE | ts);
+
+		if (!packet_read_pending(&po->tx_ring))
+			complete(&po->skb_completion);
 	}
 
 	sock_wfree(skb);
@@ -2593,7 +2596,7 @@ static int tpacket_parse_header(struct packet_sock *po, void *frame,
 
 static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 {
-	struct sk_buff *skb;
+	struct sk_buff *skb = NULL;
 	struct net_device *dev;
 	struct virtio_net_hdr *vnet_hdr = NULL;
 	struct sockcm_cookie sockc;
@@ -2608,6 +2611,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 	int len_sum = 0;
 	int status = TP_STATUS_AVAILABLE;
 	int hlen, tlen, copylen = 0;
+	long timeo = 0;
 
 	mutex_lock(&po->pg_vec_lock);
 
@@ -2654,12 +2658,21 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 	if ((size_max > dev->mtu + reserve + VLAN_HLEN) && !po->has_vnet_hdr)
 		size_max = dev->mtu + reserve + VLAN_HLEN;
 
+	reinit_completion(&po->skb_completion);
+
 	do {
 		ph = packet_current_frame(po, &po->tx_ring,
 					  TP_STATUS_SEND_REQUEST);
 		if (unlikely(ph == NULL)) {
-			if (need_wait && need_resched())
-				schedule();
+			if (need_wait && skb) {
+				timeo = sock_sndtimeo(&po->sk, msg->msg_flags & MSG_DONTWAIT);
+				timeo = wait_for_completion_interruptible_timeout(&po->skb_completion, timeo);
+				if (timeo <= 0) {
+					err = !timeo ? -ETIMEDOUT : -ERESTARTSYS;
+					goto out_put;
+				}
+			}
+			/* check for additional frames */
 			continue;
 		}
 
@@ -3215,6 +3228,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol,
 	sock_init_data(sock, sk);
 
 	po = pkt_sk(sk);
+	init_completion(&po->skb_completion);
 	sk->sk_family = PF_PACKET;
 	po->num = proto;
 	po->xmit = dev_queue_xmit;
diff --git a/net/packet/internal.h b/net/packet/internal.h
index 3bb7c5fb3bff..c70a2794456f 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -128,6 +128,7 @@ struct packet_sock {
 	unsigned int		tp_hdrlen;
 	unsigned int		tp_reserve;
 	unsigned int		tp_tstamp;
+	struct completion	skb_completion;
 	struct net_device __rcu	*cached_dev;
 	int			(*xmit)(struct sk_buff *skb);
 	struct packet_type	prot_hook ____cacheline_aligned_in_smp;
-- 
2.20.1


From 6de4c80f9e1d44a198697cb5893d2c2ed3e4e244 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 26 Jun 2019 16:08:44 +0800
Subject: [PATCH 02/15] bonding: Always enable vlan tx offload

[ Upstream commit 30d8177e8ac776d89d387fad547af6a0f599210e ]

We build vlan on top of bonding interface, which vlan offload
is off, bond mode is 802.3ad (LACP) and xmit_hash_policy is
BOND_XMIT_POLICY_ENCAP34.

Because vlan tx offload is off, vlan tci is cleared and skb push
the vlan header in validate_xmit_vlan() while sending from vlan
devices. Then in bond_xmit_hash, __skb_flow_dissect() fails to
get information from protocol headers encapsulated within vlan,
because 'nhoff' is points to IP header, so bond hashing is based
on layer 2 info, which fails to distribute packets across slaves.

This patch always enable bonding's vlan tx offload, pass the vlan
packets to the slave devices with vlan tci, let them to handle
vlan implementation.

Fixes: 278339a42a1b ("bonding: propogate vlan_features to bonding master")
Suggested-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index f96efa363d34..59e919b92873 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -4321,12 +4321,12 @@ void bond_setup(struct net_device *bond_dev)
 	bond_dev->features |= NETIF_F_NETNS_LOCAL;
 
 	bond_dev->hw_features = BOND_VLAN_FEATURES |
-				NETIF_F_HW_VLAN_CTAG_TX |
 				NETIF_F_HW_VLAN_CTAG_RX |
 				NETIF_F_HW_VLAN_CTAG_FILTER;
 
 	bond_dev->hw_features |= NETIF_F_GSO_ENCAP_ALL | NETIF_F_GSO_UDP_L4;
 	bond_dev->features |= bond_dev->hw_features;
+	bond_dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
 }
 
 /* Destroy a bonding device.
-- 
2.20.1


From 676c401bb70f06a1bc64262754d20d07ce8d233d Mon Sep 17 00:00:00 2001
From: Stephen Suryaputra <ssuryaextr@gmail.com>
Date: Mon, 24 Jun 2019 20:14:06 -0400
Subject: [PATCH 03/15] ipv4: Use return value of inet_iif() for
 __raw_v4_lookup in the while loop

[ Upstream commit 38c73529de13e1e10914de7030b659a2f8b01c3b ]

In commit 19e4e768064a8 ("ipv4: Fix raw socket lookup for local
traffic"), the dif argument to __raw_v4_lookup() is coming from the
returned value of inet_iif() but the change was done only for the first
lookup. Subsequent lookups in the while loop still use skb->dev->ifIndex.

Fixes: 19e4e768064a8 ("ipv4: Fix raw socket lookup for local traffic")
Signed-off-by: Stephen Suryaputra <ssuryaextr@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/raw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index dc91c27bb788..3f6e95cb21b0 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -201,7 +201,7 @@ static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash)
 		}
 		sk = __raw_v4_lookup(net, sk_next(sk), iph->protocol,
 				     iph->saddr, iph->daddr,
-				     skb->dev->ifindex, sdif);
+				     dif, sdif);
 	}
 out:
 	read_unlock(&raw_v4_hashinfo.lock);
-- 
2.20.1


From 7fb3edc71e2f7cfbba4a8e7bccbc97f6fb4f59ac Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 24 Jun 2019 02:38:20 -0700
Subject: [PATCH 04/15] net/packet: fix memory leak in packet_set_ring()

[ Upstream commit 55655e3d1197fff16a7a05088fb0e5eba50eac55 ]

syzbot found we can leak memory in packet_set_ring(), if user application
provides buggy parameters.

Fixes: 7f953ab2ba46 ("af_packet: TX_RING support for TPACKET_V3")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 3385f4c6eb74..21814acb862d 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -4341,7 +4341,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 				    req3->tp_sizeof_priv ||
 				    req3->tp_feature_req_word) {
 					err = -EINVAL;
-					goto out;
+					goto out_free_pg_vec;
 				}
 			}
 			break;
@@ -4405,6 +4405,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 			prb_shutdown_retire_blk_timer(po, rb_queue);
 	}
 
+out_free_pg_vec:
 	if (pg_vec)
 		free_pg_vec(pg_vec, order, req->tp_block_nr);
 out:
-- 
2.20.1


From b7d1e359d1c0ec82000aeac47fb3c1ddd0993e76 Mon Sep 17 00:00:00 2001
From: JingYi Hou <houjingyi647@gmail.com>
Date: Mon, 17 Jun 2019 14:56:05 +0800
Subject: [PATCH 05/15] net: remove duplicate fetch in sock_getsockopt

[ Upstream commit d0bae4a0e3d8c5690a885204d7eb2341a5b4884d ]

In sock_getsockopt(), 'optlen' is fetched the first time from userspace.
'len < 0' is then checked. Then in condition 'SO_MEMINFO', 'optlen' is
fetched the second time from userspace.

If change it between two fetches may cause security problems or unexpected
behaivor, and there is no reason to fetch it a second time.

To fix this, we need to remove the second fetch.

Signed-off-by: JingYi Hou <houjingyi647@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index 067878a1e4c5..30afb072eecf 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1482,9 +1482,6 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 	{
 		u32 meminfo[SK_MEMINFO_VARS];
 
-		if (get_user(len, optlen))
-			return -EFAULT;
-
 		sk_get_meminfo(sk, meminfo);
 
 		len = min_t(unsigned int, len, sizeof(meminfo));
-- 
2.20.1


From b1675037d359473d59cdcf972940c4323148c8e3 Mon Sep 17 00:00:00 2001
From: Roland Hii <roland.king.guan.hii@intel.com>
Date: Wed, 19 Jun 2019 22:13:48 +0800
Subject: [PATCH 06/15] net: stmmac: fixed new system time seconds value
 calculation

[ Upstream commit a1e5388b4d5fc78688e5e9ee6641f779721d6291 ]

When ADDSUB bit is set, the system time seconds field is calculated as
the complement of the seconds part of the update value.

For example, if 3.000000001 seconds need to be subtracted from the
system time, this field is calculated as
2^32 - 3 = 4294967296 - 3 = 0x100000000 - 3 = 0xFFFFFFFD

Previously, the 0x100000000 is mistakenly written as 100000000.

This is further simplified from
  sec = (0x100000000ULL - sec);
to
  sec = -sec;

Fixes: ba1ffd74df74 ("stmmac: fix PTP support for GMAC4")
Signed-off-by: Roland Hii <roland.king.guan.hii@intel.com>
Signed-off-by: Ong Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: Voon Weifeng <weifeng.voon@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
index 8d9cc2157afd..7423262ce590 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
@@ -122,7 +122,7 @@ static int adjust_systime(void __iomem *ioaddr, u32 sec, u32 nsec,
 		 * programmed with (2^32 – <new_sec_value>)
 		 */
 		if (gmac4)
-			sec = (100000000ULL - sec);
+			sec = -sec;
 
 		value = readl(ioaddr + PTP_TCR);
 		if (value & PTP_TCR_TSCTRLSSR)
-- 
2.20.1


From d7ff1e42569b97870fc4bd668ef3d5f44eec2b91 Mon Sep 17 00:00:00 2001
From: Roland Hii <roland.king.guan.hii@intel.com>
Date: Wed, 19 Jun 2019 22:41:48 +0800
Subject: [PATCH 07/15] net: stmmac: set IC bit when transmitting frames with
 HW timestamp

[ Upstream commit d0bb82fd60183868f46c8ccc595a3d61c3334a18 ]

When transmitting certain PTP frames, e.g. SYNC and DELAY_REQ, the
PTP daemon, e.g. ptp4l, is polling the driver for the frame transmit
hardware timestamp. The polling will most likely timeout if the tx
coalesce is enabled due to the Interrupt-on-Completion (IC) bit is
not set in tx descriptor for those frames.

This patch will ignore the tx coalesce parameter and set the IC bit
when transmitting PTP frames which need to report out the frame
transmit hardware timestamp to user space.

Fixes: f748be531d70 ("net: stmmac: Rework coalesce timer and fix multi-queue races")
Signed-off-by: Roland Hii <roland.king.guan.hii@intel.com>
Signed-off-by: Ong Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: Voon Weifeng <weifeng.voon@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/stmicro/stmmac/stmmac_main.c | 22 ++++++++++++-------
 1 file changed, 14 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 635d88d82610..a634054dcb11 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2957,12 +2957,15 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	/* Manage tx mitigation */
 	tx_q->tx_count_frames += nfrags + 1;
-	if (priv->tx_coal_frames <= tx_q->tx_count_frames) {
+	if (likely(priv->tx_coal_frames > tx_q->tx_count_frames) &&
+	    !(priv->synopsys_id >= DWMAC_CORE_4_00 &&
+	    (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
+	    priv->hwts_tx_en)) {
+		stmmac_tx_timer_arm(priv, queue);
+	} else {
+		tx_q->tx_count_frames = 0;
 		stmmac_set_tx_ic(priv, desc);
 		priv->xstats.tx_set_ic_bit++;
-		tx_q->tx_count_frames = 0;
-	} else {
-		stmmac_tx_timer_arm(priv, queue);
 	}
 
 	skb_tx_timestamp(skb);
@@ -3176,12 +3179,15 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 	 * element in case of no SG.
 	 */
 	tx_q->tx_count_frames += nfrags + 1;
-	if (priv->tx_coal_frames <= tx_q->tx_count_frames) {
+	if (likely(priv->tx_coal_frames > tx_q->tx_count_frames) &&
+	    !(priv->synopsys_id >= DWMAC_CORE_4_00 &&
+	    (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
+	    priv->hwts_tx_en)) {
+		stmmac_tx_timer_arm(priv, queue);
+	} else {
+		tx_q->tx_count_frames = 0;
 		stmmac_set_tx_ic(priv, desc);
 		priv->xstats.tx_set_ic_bit++;
-		tx_q->tx_count_frames = 0;
-	} else {
-		stmmac_tx_timer_arm(priv, queue);
 	}
 
 	skb_tx_timestamp(skb);
-- 
2.20.1


From fb6af8d16bb8e294682e7d14e5b0ba2bf75e0a4c Mon Sep 17 00:00:00 2001
From: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Date: Sun, 23 Jun 2019 21:26:58 -0700
Subject: [PATCH 08/15] net/tls: fix page double free on TX cleanup

[ Upstream commit 9354544cbccf68da1b047f8fb7b47630e3c8a59d ]

With commit 94850257cf0f ("tls: Fix tls_device handling of partial records")
a new path was introduced to cleanup partial records during sk_proto_close.
This path does not handle the SW KTLS tx_list cleanup.

This is unnecessary though since the free_resources calls for both
SW and offload paths will cleanup a partial record.

The visible effect is the following warning, but this bug also causes
a page double free.

    WARNING: CPU: 7 PID: 4000 at net/core/stream.c:206 sk_stream_kill_queues+0x103/0x110
    RIP: 0010:sk_stream_kill_queues+0x103/0x110
    RSP: 0018:ffffb6df87e07bd0 EFLAGS: 00010206
    RAX: 0000000000000000 RBX: ffff8c21db4971c0 RCX: 0000000000000007
    RDX: ffffffffffffffa0 RSI: 000000000000001d RDI: ffff8c21db497270
    RBP: ffff8c21db497270 R08: ffff8c29f4748600 R09: 000000010020001a
    R10: ffffb6df87e07aa0 R11: ffffffff9a445600 R12: 0000000000000007
    R13: 0000000000000000 R14: ffff8c21f03f2900 R15: ffff8c21f03b8df0
    Call Trace:
     inet_csk_destroy_sock+0x55/0x100
     tcp_close+0x25d/0x400
     ? tcp_check_oom+0x120/0x120
     tls_sk_proto_close+0x127/0x1c0
     inet_release+0x3c/0x60
     __sock_release+0x3d/0xb0
     sock_close+0x11/0x20
     __fput+0xd8/0x210
     task_work_run+0x84/0xa0
     do_exit+0x2dc/0xb90
     ? release_sock+0x43/0x90
     do_group_exit+0x3a/0xa0
     get_signal+0x295/0x720
     do_signal+0x36/0x610
     ? SYSC_recvfrom+0x11d/0x130
     exit_to_usermode_loop+0x69/0xb0
     do_syscall_64+0x173/0x180
     entry_SYSCALL_64_after_hwframe+0x3d/0xa2
    RIP: 0033:0x7fe9b9abc10d
    RSP: 002b:00007fe9b19a1d48 EFLAGS: 00000246 ORIG_RAX: 00000000000000ca
    RAX: fffffffffffffe00 RBX: 0000000000000006 RCX: 00007fe9b9abc10d
    RDX: 0000000000000002 RSI: 0000000000000080 RDI: 00007fe948003430
    RBP: 00007fe948003410 R08: 00007fe948003430 R09: 0000000000000000
    R10: 0000000000000000 R11: 0000000000000246 R12: 00005603739d9080
    R13: 00007fe9b9ab9f90 R14: 00007fe948003430 R15: 0000000000000000

Fixes: 94850257cf0f ("tls: Fix tls_device handling of partial records")
Signed-off-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h  | 15 ---------------
 net/tls/tls_main.c |  3 ++-
 2 files changed, 2 insertions(+), 16 deletions(-)

diff --git a/include/net/tls.h b/include/net/tls.h
index 053082d98906..a67ad7d56ff2 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -347,21 +347,6 @@ static inline bool tls_is_partially_sent_record(struct tls_context *ctx)
 	return !!ctx->partially_sent_record;
 }
 
-static inline int tls_complete_pending_work(struct sock *sk,
-					    struct tls_context *ctx,
-					    int flags, long *timeo)
-{
-	int rc = 0;
-
-	if (unlikely(sk->sk_write_pending))
-		rc = wait_on_pending_writer(sk, timeo);
-
-	if (!rc && tls_is_partially_sent_record(ctx))
-		rc = tls_push_partial_record(sk, ctx, flags);
-
-	return rc;
-}
-
 static inline bool tls_is_pending_open_record(struct tls_context *tls_ctx)
 {
 	return tls_ctx->pending_open_record_frags;
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 478603f43964..f4f632824247 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -279,7 +279,8 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
 		goto skip_tx_cleanup;
 	}
 
-	if (!tls_complete_pending_work(sk, ctx, 0, &timeo))
+	if (unlikely(sk->sk_write_pending) &&
+	    !wait_on_pending_writer(sk, &timeo))
 		tls_handle_open_record(sk, 0);
 
 	/* We need these for tls_sw_fallback handling of other packets */
-- 
2.20.1


From 7709ceeb1556d7c516565de20e3364c0e13d3424 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Mon, 24 Jun 2019 18:45:11 +0200
Subject: [PATCH 09/15] qmi_wwan: Fix out-of-bounds read
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 904d88d743b0c94092c5117955eab695df8109e8 ]

The syzbot reported

 Call Trace:
  __dump_stack lib/dump_stack.c:77 [inline]
  dump_stack+0xca/0x13e lib/dump_stack.c:113
  print_address_description+0x67/0x231 mm/kasan/report.c:188
  __kasan_report.cold+0x1a/0x32 mm/kasan/report.c:317
  kasan_report+0xe/0x20 mm/kasan/common.c:614
  qmi_wwan_probe+0x342/0x360 drivers/net/usb/qmi_wwan.c:1417
  usb_probe_interface+0x305/0x7a0 drivers/usb/core/driver.c:361
  really_probe+0x281/0x660 drivers/base/dd.c:509
  driver_probe_device+0x104/0x210 drivers/base/dd.c:670
  __device_attach_driver+0x1c2/0x220 drivers/base/dd.c:777
  bus_for_each_drv+0x15c/0x1e0 drivers/base/bus.c:454

Caused by too many confusing indirections and casts.
id->driver_info is a pointer stored in a long.  We want the
pointer here, not the address of it.

Thanks-to: Hillf Danton <hdanton@sina.com>
Reported-by: syzbot+b68605d7fadd21510de1@syzkaller.appspotmail.com
Cc: Kristian Evensen <kristian.evensen@gmail.com>
Fixes: e4bf63482c30 ("qmi_wwan: Add quirk for Quectel dynamic config")
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index d9a6699abe59..e657d8947125 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1412,7 +1412,7 @@ static int qmi_wwan_probe(struct usb_interface *intf,
 	 * different. Ignore the current interface if the number of endpoints
 	 * equals the number for the diag interface (two).
 	 */
-	info = (void *)&id->driver_info;
+	info = (void *)id->driver_info;
 
 	if (info->data & QMI_WWAN_QUIRK_QUECTEL_DYNCFG) {
 		if (desc->bNumEndpoints == 2)
-- 
2.20.1


From 30f278a1f1a5b938d97044e0b2c887aaa4aa1dd5 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 25 Jun 2019 00:21:45 +0800
Subject: [PATCH 10/15] sctp: change to hold sk after auth shkey is created
 successfully

[ Upstream commit 25bff6d5478b2a02368097015b7d8eb727c87e16 ]

Now in sctp_endpoint_init(), it holds the sk then creates auth
shkey. But when the creation fails, it doesn't release the sk,
which causes a sk defcnf leak,

Here to fix it by only holding the sk when auth shkey is created
successfully.

Fixes: a29a5bd4f5c3 ("[SCTP]: Implement SCTP-AUTH initializations.")
Reported-by: syzbot+afabda3890cc2f765041@syzkaller.appspotmail.com
Reported-by: syzbot+276ca1c77a19977c0130@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/endpointola.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c
index 0448b68fce74..bcfc81ee153d 100644
--- a/net/sctp/endpointola.c
+++ b/net/sctp/endpointola.c
@@ -133,10 +133,6 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep,
 	/* Initialize the bind addr area */
 	sctp_bind_addr_init(&ep->base.bind_addr, 0);
 
-	/* Remember who we are attached to.  */
-	ep->base.sk = sk;
-	sock_hold(ep->base.sk);
-
 	/* Create the lists of associations.  */
 	INIT_LIST_HEAD(&ep->asocs);
 
@@ -169,6 +165,10 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep,
 	ep->prsctp_enable = net->sctp.prsctp_enable;
 	ep->reconf_enable = net->sctp.reconf_enable;
 
+	/* Remember who we are attached to.  */
+	ep->base.sk = sk;
+	sock_hold(ep->base.sk);
+
 	return ep;
 
 nomem_shkey:
-- 
2.20.1


From 38c23c9fe0ae5c15c97fd1eea4aee4ff0ab1432e Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Thu, 27 Jun 2019 00:03:39 +0800
Subject: [PATCH 11/15] team: Always enable vlan tx offload

[ Upstream commit ee4297420d56a0033a8593e80b33fcc93fda8509 ]

We should rather have vlan_tci filled all the way down
to the transmitting netdevice and let it do the hw/sw
vlan implementation.

Suggested-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 16963f7a88f7..351f25e1fc48 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -2135,12 +2135,12 @@ static void team_setup(struct net_device *dev)
 	dev->features |= NETIF_F_NETNS_LOCAL;
 
 	dev->hw_features = TEAM_VLAN_FEATURES |
-			   NETIF_F_HW_VLAN_CTAG_TX |
 			   NETIF_F_HW_VLAN_CTAG_RX |
 			   NETIF_F_HW_VLAN_CTAG_FILTER;
 
 	dev->hw_features |= NETIF_F_GSO_ENCAP_ALL | NETIF_F_GSO_UDP_L4;
 	dev->features |= dev->hw_features;
+	dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
 }
 
 static int team_newlink(struct net *src_net, struct net_device *dev,
-- 
2.20.1


From b5e73e45e80663f0c7bc011985044564e2dce98c Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 20 Jun 2019 18:39:28 +0800
Subject: [PATCH 12/15] tipc: change to use register_pernet_device

[ Upstream commit c492d4c74dd3f87559883ffa0f94a8f1ae3fe5f5 ]

This patch is to fix a dst defcnt leak, which can be reproduced by doing:

  # ip net a c; ip net a s; modprobe tipc
  # ip net e s ip l a n eth1 type veth peer n eth1 netns c
  # ip net e c ip l s lo up; ip net e c ip l s eth1 up
  # ip net e s ip l s lo up; ip net e s ip l s eth1 up
  # ip net e c ip a a 1.1.1.2/8 dev eth1
  # ip net e s ip a a 1.1.1.1/8 dev eth1
  # ip net e c tipc b e m udp n u1 localip 1.1.1.2
  # ip net e s tipc b e m udp n u1 localip 1.1.1.1
  # ip net d c; ip net d s; rmmod tipc

and it will get stuck and keep logging the error:

  unregister_netdevice: waiting for lo to become free. Usage count = 1

The cause is that a dst is held by the udp sock's sk_rx_dst set on udp rx
path with udp_early_demux == 1, and this dst (eventually holding lo dev)
can't be released as bearer's removal in tipc pernet .exit happens after
lo dev's removal, default_device pernet .exit.

 "There are two distinct types of pernet_operations recognized: subsys and
  device.  At creation all subsys init functions are called before device
  init functions, and at destruction all device exit functions are called
  before subsys exit function."

So by calling register_pernet_device instead to register tipc_net_ops, the
pernet .exit() will be invoked earlier than loopback dev's removal when a
netns is being destroyed, as fou/gue does.

Note that vxlan and geneve udp tunnels don't have this issue, as the udp
sock is released in their device ndo_stop().

This fix is also necessary for tipc dst_cache, which will hold dsts on tx
path and I will introduce in my next patch.

Reported-by: Li Shuang <shuali@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/core.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/tipc/core.c b/net/tipc/core.c
index 3ecca3b88bf8..eb0f701f9bf1 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -132,7 +132,7 @@ static int __init tipc_init(void)
 	if (err)
 		goto out_sysctl;
 
-	err = register_pernet_subsys(&tipc_net_ops);
+	err = register_pernet_device(&tipc_net_ops);
 	if (err)
 		goto out_pernet;
 
@@ -140,7 +140,7 @@ static int __init tipc_init(void)
 	if (err)
 		goto out_socket;
 
-	err = register_pernet_subsys(&tipc_topsrv_net_ops);
+	err = register_pernet_device(&tipc_topsrv_net_ops);
 	if (err)
 		goto out_pernet_topsrv;
 
@@ -151,11 +151,11 @@ static int __init tipc_init(void)
 	pr_info("Started in single node mode\n");
 	return 0;
 out_bearer:
-	unregister_pernet_subsys(&tipc_topsrv_net_ops);
+	unregister_pernet_device(&tipc_topsrv_net_ops);
 out_pernet_topsrv:
 	tipc_socket_stop();
 out_socket:
-	unregister_pernet_subsys(&tipc_net_ops);
+	unregister_pernet_device(&tipc_net_ops);
 out_pernet:
 	tipc_unregister_sysctl();
 out_sysctl:
@@ -170,9 +170,9 @@ static int __init tipc_init(void)
 static void __exit tipc_exit(void)
 {
 	tipc_bearer_cleanup();
-	unregister_pernet_subsys(&tipc_topsrv_net_ops);
+	unregister_pernet_device(&tipc_topsrv_net_ops);
 	tipc_socket_stop();
-	unregister_pernet_subsys(&tipc_net_ops);
+	unregister_pernet_device(&tipc_net_ops);
 	tipc_netlink_stop();
 	tipc_netlink_compat_stop();
 	tipc_unregister_sysctl();
-- 
2.20.1


From 168868205774af7589ca71ae4586c28df39ca5f9 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 25 Jun 2019 00:28:19 +0800
Subject: [PATCH 13/15] tipc: check msg->req data len in
 tipc_nl_compat_bearer_disable

[ Upstream commit 4f07b80c973348a99b5d2a32476a2e7877e94a05 ]

This patch is to fix an uninit-value issue, reported by syzbot:

  BUG: KMSAN: uninit-value in memchr+0xce/0x110 lib/string.c:981
  Call Trace:
    __dump_stack lib/dump_stack.c:77 [inline]
    dump_stack+0x191/0x1f0 lib/dump_stack.c:113
    kmsan_report+0x130/0x2a0 mm/kmsan/kmsan.c:622
    __msan_warning+0x75/0xe0 mm/kmsan/kmsan_instr.c:310
    memchr+0xce/0x110 lib/string.c:981
    string_is_valid net/tipc/netlink_compat.c:176 [inline]
    tipc_nl_compat_bearer_disable+0x2a1/0x480 net/tipc/netlink_compat.c:449
    __tipc_nl_compat_doit net/tipc/netlink_compat.c:327 [inline]
    tipc_nl_compat_doit+0x3ac/0xb00 net/tipc/netlink_compat.c:360
    tipc_nl_compat_handle net/tipc/netlink_compat.c:1178 [inline]
    tipc_nl_compat_recv+0x1b1b/0x27b0 net/tipc/netlink_compat.c:1281

TLV_GET_DATA_LEN() may return a negtive int value, which will be
used as size_t (becoming a big unsigned long) passed into memchr,
cause this issue.

Similar to what it does in tipc_nl_compat_bearer_enable(), this
fix is to return -EINVAL when TLV_GET_DATA_LEN() is negtive in
tipc_nl_compat_bearer_disable(), as well as in
tipc_nl_compat_link_stat_dump() and tipc_nl_compat_link_reset_stats().

v1->v2:
  - add the missing Fixes tags per Eric's request.

Fixes: 0762216c0ad2 ("tipc: fix uninit-value in tipc_nl_compat_bearer_enable")
Fixes: 8b66fee7f8ee ("tipc: fix uninit-value in tipc_nl_compat_link_reset_stats")
Reported-by: syzbot+30eaa8bf392f7fafffaf@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/netlink_compat.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 340a6e7c43a7..8836aebd6180 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -445,7 +445,11 @@ static int tipc_nl_compat_bearer_disable(struct tipc_nl_compat_cmd_doit *cmd,
 	if (!bearer)
 		return -EMSGSIZE;
 
-	len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_BEARER_NAME);
+	len = TLV_GET_DATA_LEN(msg->req);
+	if (len <= 0)
+		return -EINVAL;
+
+	len = min_t(int, len, TIPC_MAX_BEARER_NAME);
 	if (!string_is_valid(name, len))
 		return -EINVAL;
 
@@ -537,7 +541,11 @@ static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg,
 
 	name = (char *)TLV_DATA(msg->req);
 
-	len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_LINK_NAME);
+	len = TLV_GET_DATA_LEN(msg->req);
+	if (len <= 0)
+		return -EINVAL;
+
+	len = min_t(int, len, TIPC_MAX_BEARER_NAME);
 	if (!string_is_valid(name, len))
 		return -EINVAL;
 
@@ -815,7 +823,11 @@ static int tipc_nl_compat_link_reset_stats(struct tipc_nl_compat_cmd_doit *cmd,
 	if (!link)
 		return -EMSGSIZE;
 
-	len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_LINK_NAME);
+	len = TLV_GET_DATA_LEN(msg->req);
+	if (len <= 0)
+		return -EINVAL;
+
+	len = min_t(int, len, TIPC_MAX_BEARER_NAME);
 	if (!string_is_valid(name, len))
 		return -EINVAL;
 
-- 
2.20.1


From ae3b62a796c6c1ddc031c953b9dc00b17366e188 Mon Sep 17 00:00:00 2001
From: Fei Li <lifei.shirley@bytedance.com>
Date: Mon, 17 Jun 2019 21:26:36 +0800
Subject: [PATCH 14/15] tun: wake up waitqueues after IFF_UP is set

[ Upstream commit 72b319dc08b4924a29f5e2560ef6d966fa54c429 ]

Currently after setting tap0 link up, the tun code wakes tx/rx waited
queues up in tun_net_open() when .ndo_open() is called, however the
IFF_UP flag has not been set yet. If there's already a wait queue, it
would fail to transmit when checking the IFF_UP flag in tun_sendmsg().
Then the saving vhost_poll_start() will add the wq into wqh until it
is waken up again. Although this works when IFF_UP flag has been set
when tun_chr_poll detects; this is not true if IFF_UP flag has not
been set at that time. Sadly the latter case is a fatal error, as
the wq will never be waken up in future unless later manually
setting link up on purpose.

Fix this by moving the wakeup process into the NETDEV_UP event
notifying process, this makes sure IFF_UP has been set before all
waited queues been waken up.

Signed-off-by: Fei Li <lifei.shirley@bytedance.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index f4c933ac6edf..d1cafb29eca9 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1024,18 +1024,8 @@ static void tun_net_uninit(struct net_device *dev)
 /* Net device open. */
 static int tun_net_open(struct net_device *dev)
 {
-	struct tun_struct *tun = netdev_priv(dev);
-	int i;
-
 	netif_tx_start_all_queues(dev);
 
-	for (i = 0; i < tun->numqueues; i++) {
-		struct tun_file *tfile;
-
-		tfile = rtnl_dereference(tun->tfiles[i]);
-		tfile->socket.sk->sk_write_space(tfile->socket.sk);
-	}
-
 	return 0;
 }
 
@@ -3636,6 +3626,7 @@ static int tun_device_event(struct notifier_block *unused,
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct tun_struct *tun = netdev_priv(dev);
+	int i;
 
 	if (dev->rtnl_link_ops != &tun_link_ops)
 		return NOTIFY_DONE;
@@ -3645,6 +3636,14 @@ static int tun_device_event(struct notifier_block *unused,
 		if (tun_queue_resize(tun))
 			return NOTIFY_BAD;
 		break;
+	case NETDEV_UP:
+		for (i = 0; i < tun->numqueues; i++) {
+			struct tun_file *tfile;
+
+			tfile = rtnl_dereference(tun->tfiles[i]);
+			tfile->socket.sk->sk_write_space(tfile->socket.sk);
+		}
+		break;
 	default:
 		break;
 	}
-- 
2.20.1


From 84eaddab9e30b15ff374e1cc77d7c7be0b1d9d49 Mon Sep 17 00:00:00 2001
From: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Date: Sat, 22 Jun 2019 08:46:37 +0000
Subject: [PATCH 15/15] net: aquantia: fix vlans not working over bridged
 network

[ Upstream commit 48dd73d08d4dda47ee31cc8611fb16840fc16803 ]

In configuration of vlan over bridge over aquantia device
it was found that vlan tagged traffic is dropped on chip.

The reason is that bridge device enables promisc mode,
but in atlantic chip vlan filters will still apply.
So we have to corellate promisc settings with vlan configuration.

The solution is to track in a separate state variable the
need of vlan forced promisc. And also consider generic
promisc configuration when doing vlan filter config.

Fixes: 7975d2aff5af ("net: aquantia: add support of rx-vlan-filter offload")
Signed-off-by: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/aquantia/atlantic/aq_filters.c   | 10 ++++++++--
 .../net/ethernet/aquantia/atlantic/aq_nic.c   |  1 +
 .../net/ethernet/aquantia/atlantic/aq_nic.h   |  1 +
 .../aquantia/atlantic/hw_atl/hw_atl_b0.c      | 19 +++++++++++++------
 4 files changed, 23 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_filters.c b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c
index 18bc035da850..1fff462a4175 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_filters.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c
@@ -843,9 +843,14 @@ int aq_filters_vlans_update(struct aq_nic_s *aq_nic)
 		return err;
 
 	if (aq_nic->ndev->features & NETIF_F_HW_VLAN_CTAG_FILTER) {
-		if (hweight < AQ_VLAN_MAX_FILTERS)
-			err = aq_hw_ops->hw_filter_vlan_ctrl(aq_hw, true);
+		if (hweight < AQ_VLAN_MAX_FILTERS && hweight > 0) {
+			err = aq_hw_ops->hw_filter_vlan_ctrl(aq_hw,
+				!(aq_nic->packet_filter & IFF_PROMISC));
+			aq_nic->aq_nic_cfg.is_vlan_force_promisc = false;
+		} else {
 		/* otherwise left in promiscue mode */
+			aq_nic->aq_nic_cfg.is_vlan_force_promisc = true;
+		}
 	}
 
 	return err;
@@ -866,6 +871,7 @@ int aq_filters_vlan_offload_off(struct aq_nic_s *aq_nic)
 	if (unlikely(!aq_hw_ops->hw_filter_vlan_ctrl))
 		return -EOPNOTSUPP;
 
+	aq_nic->aq_nic_cfg.is_vlan_force_promisc = true;
 	err = aq_hw_ops->hw_filter_vlan_ctrl(aq_hw, false);
 	if (err)
 		return err;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index ff83667410bd..550abfe6973d 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -117,6 +117,7 @@ void aq_nic_cfg_start(struct aq_nic_s *self)
 
 	cfg->link_speed_msk &= cfg->aq_hw_caps->link_speed_msk;
 	cfg->features = cfg->aq_hw_caps->hw_features;
+	cfg->is_vlan_force_promisc = true;
 }
 
 static int aq_nic_update_link_status(struct aq_nic_s *self)
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
index 8e34c1e49bf2..65e681be9b5d 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
@@ -36,6 +36,7 @@ struct aq_nic_cfg_s {
 	u32 flow_control;
 	u32 link_speed_msk;
 	u32 wol;
+	bool is_vlan_force_promisc;
 	u16 is_mc_list_enabled;
 	u16 mc_list_count;
 	bool is_autoneg;
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index ec302fdfec63..a4cc04741115 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -771,8 +771,15 @@ static int hw_atl_b0_hw_packet_filter_set(struct aq_hw_s *self,
 					  unsigned int packet_filter)
 {
 	unsigned int i = 0U;
+	struct aq_nic_cfg_s *cfg = self->aq_nic_cfg;
+
+	hw_atl_rpfl2promiscuous_mode_en_set(self,
+					    IS_FILTER_ENABLED(IFF_PROMISC));
+
+	hw_atl_rpf_vlan_prom_mode_en_set(self,
+				     IS_FILTER_ENABLED(IFF_PROMISC) ||
+				     cfg->is_vlan_force_promisc);
 
-	hw_atl_rpfl2promiscuous_mode_en_set(self, IS_FILTER_ENABLED(IFF_PROMISC));
 	hw_atl_rpfl2multicast_flr_en_set(self,
 					 IS_FILTER_ENABLED(IFF_ALLMULTI), 0);
 
@@ -781,13 +788,13 @@ static int hw_atl_b0_hw_packet_filter_set(struct aq_hw_s *self,
 
 	hw_atl_rpfl2broadcast_en_set(self, IS_FILTER_ENABLED(IFF_BROADCAST));
 
-	self->aq_nic_cfg->is_mc_list_enabled = IS_FILTER_ENABLED(IFF_MULTICAST);
+	cfg->is_mc_list_enabled = IS_FILTER_ENABLED(IFF_MULTICAST);
 
 	for (i = HW_ATL_B0_MAC_MIN; i < HW_ATL_B0_MAC_MAX; ++i)
 		hw_atl_rpfl2_uc_flr_en_set(self,
-					   (self->aq_nic_cfg->is_mc_list_enabled &&
-				    (i <= self->aq_nic_cfg->mc_list_count)) ?
-				    1U : 0U, i);
+					   (cfg->is_mc_list_enabled &&
+					    (i <= cfg->mc_list_count)) ?
+					   1U : 0U, i);
 
 	return aq_hw_err_from_flags(self);
 }
@@ -1079,7 +1086,7 @@ static int hw_atl_b0_hw_vlan_set(struct aq_hw_s *self,
 static int hw_atl_b0_hw_vlan_ctrl(struct aq_hw_s *self, bool enable)
 {
 	/* set promisc in case of disabing the vland filter */
-	hw_atl_rpf_vlan_prom_mode_en_set(self, !!!enable);
+	hw_atl_rpf_vlan_prom_mode_en_set(self, !enable);
 
 	return aq_hw_err_from_flags(self);
 }
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Mon, Jul 01, 2019 at 06:52:55PM -0700, David Miller wrote:
> 
> Please apply the following bug fixes to v4.19 and v5.1 -stable,
> respectively.

All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 105 bytes --]


Please queue up the following networking bug fixes for v5.1 and v5.2
-stable, respectively.

Thank you.

[-- Attachment #2: net_51.mbox --]
[-- Type: Application/Octet-Stream, Size: 117080 bytes --]

From 51c5cb3c943852221d073c7cddf0b2bd22d56ee7 Mon Sep 17 00:00:00 2001
From: Brian King <brking@linux.vnet.ibm.com>
Date: Mon, 15 Jul 2019 16:41:50 -0500
Subject: [PATCH 01/45] bnx2x: Prevent load reordering in tx completion
 processing

[ Upstream commit ea811b795df24644a8eb760b493c43fba4450677 ]

This patch fixes an issue seen on Power systems with bnx2x which results
in the skb is NULL WARN_ON in bnx2x_free_tx_pkt firing due to the skb
pointer getting loaded in bnx2x_free_tx_pkt prior to the hw_cons
load in bnx2x_tx_int. Adding a read memory barrier resolves the issue.

Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index ecb1bd7eb508..52851217dd99 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -285,6 +285,9 @@ int bnx2x_tx_int(struct bnx2x *bp, struct bnx2x_fp_txdata *txdata)
 	hw_cons = le16_to_cpu(*txdata->tx_cons_sb);
 	sw_cons = txdata->tx_pkt_cons;
 
+	/* Ensure subsequent loads occur after hw_cons */
+	smp_rmb();
+
 	while (sw_cons != hw_cons) {
 		u16 pkt_cons;
 
-- 
2.20.1


From 31a3080c956aaccc8c152cb8cdb47f5fbe1ea4bf Mon Sep 17 00:00:00 2001
From: "Guilherme G. Piccoli" <gpiccoli@canonical.com>
Date: Thu, 27 Jun 2019 13:31:33 -0300
Subject: [PATCH 02/45] bnx2x: Prevent ptp_task to be rescheduled indefinitely

[ Upstream commit 3c91f25c2f72ba6001775a5932857c1d2131c531 ]

Currently bnx2x ptp worker tries to read a register with timestamp
information in case of TX packet timestamping and in case it fails,
the routine reschedules itself indefinitely. This was reported as a
kworker always at 100% of CPU usage, which was narrowed down to be
bnx2x ptp_task.

By following the ioctl handler, we could narrow down the problem to
an NTP tool (chrony) requesting HW timestamping from bnx2x NIC with
RX filter zeroed; this isn't reproducible for example with ptp4l
(from linuxptp) since this tool requests a supported RX filter.
It seems NIC FW timestamp mechanism cannot work well with
RX_FILTER_NONE - driver's PTP filter init routine skips a register
write to the adapter if there's not a supported filter request.

This patch addresses the problem of bnx2x ptp thread's everlasting
reschedule by retrying the register read 10 times; between the read
attempts the thread sleeps for an increasing amount of time starting
in 1ms to give FW some time to perform the timestamping. If it still
fails after all retries, we bail out in order to prevent an unbound
resource consumption from bnx2x.

The patch also adds an ethtool statistic for accounting the skipped
TX timestamp packets and it reduces the priority of timestamping
error messages to prevent log flooding. The code was tested using
both linuxptp and chrony.

Reported-and-tested-by: Przemyslaw Hausman <przemyslaw.hausman@canonical.com>
Suggested-by: Sudarsana Reddy Kalluru <skalluru@marvell.com>
Signed-off-by: Guilherme G. Piccoli <gpiccoli@canonical.com>
Acked-by: Sudarsana Reddy Kalluru <skalluru@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/broadcom/bnx2x/bnx2x_cmn.c   |  5 ++-
 .../ethernet/broadcom/bnx2x/bnx2x_ethtool.c   |  4 ++-
 .../net/ethernet/broadcom/bnx2x/bnx2x_main.c  | 33 ++++++++++++++-----
 .../net/ethernet/broadcom/bnx2x/bnx2x_stats.h |  3 ++
 4 files changed, 34 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 52851217dd99..9f07b85091f3 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -3861,9 +3861,12 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) {
 		if (!(bp->flags & TX_TIMESTAMPING_EN)) {
+			bp->eth_stats.ptp_skip_tx_ts++;
 			BNX2X_ERR("Tx timestamping was not enabled, this packet will not be timestamped\n");
 		} else if (bp->ptp_tx_skb) {
-			BNX2X_ERR("The device supports only a single outstanding packet to timestamp, this packet will not be timestamped\n");
+			bp->eth_stats.ptp_skip_tx_ts++;
+			netdev_err_once(bp->dev,
+					"Device supports only a single outstanding packet to timestamp, this packet won't be timestamped\n");
 		} else {
 			skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 			/* schedule check for Tx timestamp */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
index 59f227fcc68b..0e1b884a5344 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -182,7 +182,9 @@ static const struct {
 	{ STATS_OFFSET32(driver_filtered_tx_pkt),
 				4, false, "driver_filtered_tx_pkt" },
 	{ STATS_OFFSET32(eee_tx_lpi),
-				4, true, "Tx LPI entry count"}
+				4, true, "Tx LPI entry count"},
+	{ STATS_OFFSET32(ptp_skip_tx_ts),
+				4, false, "ptp_skipped_tx_tstamp" },
 };
 
 #define BNX2X_NUM_STATS		ARRAY_SIZE(bnx2x_stats_arr)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 626b491f7674..7a075f1f1242 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -15243,11 +15243,24 @@ static void bnx2x_ptp_task(struct work_struct *work)
 	u32 val_seq;
 	u64 timestamp, ns;
 	struct skb_shared_hwtstamps shhwtstamps;
+	bool bail = true;
+	int i;
+
+	/* FW may take a while to complete timestamping; try a bit and if it's
+	 * still not complete, may indicate an error state - bail out then.
+	 */
+	for (i = 0; i < 10; i++) {
+		/* Read Tx timestamp registers */
+		val_seq = REG_RD(bp, port ? NIG_REG_P1_TLLH_PTP_BUF_SEQID :
+				 NIG_REG_P0_TLLH_PTP_BUF_SEQID);
+		if (val_seq & 0x10000) {
+			bail = false;
+			break;
+		}
+		msleep(1 << i);
+	}
 
-	/* Read Tx timestamp registers */
-	val_seq = REG_RD(bp, port ? NIG_REG_P1_TLLH_PTP_BUF_SEQID :
-			 NIG_REG_P0_TLLH_PTP_BUF_SEQID);
-	if (val_seq & 0x10000) {
+	if (!bail) {
 		/* There is a valid timestamp value */
 		timestamp = REG_RD(bp, port ? NIG_REG_P1_TLLH_PTP_BUF_TS_MSB :
 				   NIG_REG_P0_TLLH_PTP_BUF_TS_MSB);
@@ -15262,16 +15275,18 @@ static void bnx2x_ptp_task(struct work_struct *work)
 		memset(&shhwtstamps, 0, sizeof(shhwtstamps));
 		shhwtstamps.hwtstamp = ns_to_ktime(ns);
 		skb_tstamp_tx(bp->ptp_tx_skb, &shhwtstamps);
-		dev_kfree_skb_any(bp->ptp_tx_skb);
-		bp->ptp_tx_skb = NULL;
 
 		DP(BNX2X_MSG_PTP, "Tx timestamp, timestamp cycles = %llu, ns = %llu\n",
 		   timestamp, ns);
 	} else {
-		DP(BNX2X_MSG_PTP, "There is no valid Tx timestamp yet\n");
-		/* Reschedule to keep checking for a valid timestamp value */
-		schedule_work(&bp->ptp_task);
+		DP(BNX2X_MSG_PTP,
+		   "Tx timestamp is not recorded (register read=%u)\n",
+		   val_seq);
+		bp->eth_stats.ptp_skip_tx_ts++;
 	}
+
+	dev_kfree_skb_any(bp->ptp_tx_skb);
+	bp->ptp_tx_skb = NULL;
 }
 
 void bnx2x_set_rx_ts(struct bnx2x *bp, struct sk_buff *skb)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h
index b2644ed13d06..d55e63692cf3 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h
@@ -207,6 +207,9 @@ struct bnx2x_eth_stats {
 	u32 driver_filtered_tx_pkt;
 	/* src: Clear-on-Read register; Will not survive PMF Migration */
 	u32 eee_tx_lpi;
+
+	/* PTP */
+	u32 ptp_skip_tx_ts;
 };
 
 struct bnx2x_eth_q_stats {
-- 
2.20.1


From f6425a94e5c1f1349c185743304fb32855d28e9b Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 1 Jul 2019 20:40:24 -0700
Subject: [PATCH 03/45] bonding: validate ip header before check IPPROTO_IGMP

[ Upstream commit 9d1bc24b52fb8c5d859f9a47084bf1179470e04c ]

bond_xmit_roundrobin() checks for IGMP packets but it parses
the IP header even before checking skb->protocol.

We should validate the IP header with pskb_may_pull() before
using iph->protocol.

Reported-and-tested-by: syzbot+e5be16aa39ad6e755391@syzkaller.appspotmail.com
Fixes: a2fd940f4cff ("bonding: fix broken multicast with round-robin mode")
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Cc: Veaceslav Falico <vfalico@gmail.com>
Cc: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 37 ++++++++++++++++++++-------------
 1 file changed, 23 insertions(+), 14 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 59e919b92873..7b9a18e36a93 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3866,8 +3866,8 @@ static netdev_tx_t bond_xmit_roundrobin(struct sk_buff *skb,
 					struct net_device *bond_dev)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
-	struct iphdr *iph = ip_hdr(skb);
 	struct slave *slave;
+	int slave_cnt;
 	u32 slave_id;
 
 	/* Start with the curr_active_slave that joined the bond as the
@@ -3876,23 +3876,32 @@ static netdev_tx_t bond_xmit_roundrobin(struct sk_buff *skb,
 	 * send the join/membership reports.  The curr_active_slave found
 	 * will send all of this type of traffic.
 	 */
-	if (iph->protocol == IPPROTO_IGMP && skb->protocol == htons(ETH_P_IP)) {
-		slave = rcu_dereference(bond->curr_active_slave);
-		if (slave)
-			bond_dev_queue_xmit(bond, skb, slave->dev);
-		else
-			bond_xmit_slave_id(bond, skb, 0);
-	} else {
-		int slave_cnt = READ_ONCE(bond->slave_cnt);
+	if (skb->protocol == htons(ETH_P_IP)) {
+		int noff = skb_network_offset(skb);
+		struct iphdr *iph;
 
-		if (likely(slave_cnt)) {
-			slave_id = bond_rr_gen_slave_id(bond);
-			bond_xmit_slave_id(bond, skb, slave_id % slave_cnt);
-		} else {
-			bond_tx_drop(bond_dev, skb);
+		if (unlikely(!pskb_may_pull(skb, noff + sizeof(*iph))))
+			goto non_igmp;
+
+		iph = ip_hdr(skb);
+		if (iph->protocol == IPPROTO_IGMP) {
+			slave = rcu_dereference(bond->curr_active_slave);
+			if (slave)
+				bond_dev_queue_xmit(bond, skb, slave->dev);
+			else
+				bond_xmit_slave_id(bond, skb, 0);
+			return NETDEV_TX_OK;
 		}
 	}
 
+non_igmp:
+	slave_cnt = READ_ONCE(bond->slave_cnt);
+	if (likely(slave_cnt)) {
+		slave_id = bond_rr_gen_slave_id(bond);
+		bond_xmit_slave_id(bond, skb, slave_id % slave_cnt);
+	} else {
+		bond_tx_drop(bond_dev, skb);
+	}
 	return NETDEV_TX_OK;
 }
 
-- 
2.20.1


From 0dc65ebb7ccfa42831ed4abed713f6082040bc65 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Mon, 15 Jul 2019 14:10:17 +0900
Subject: [PATCH 04/45] caif-hsi: fix possible deadlock in cfhsi_exit_module()

[ Upstream commit fdd258d49e88a9e0b49ef04a506a796f1c768a8e ]

cfhsi_exit_module() calls unregister_netdev() under rtnl_lock().
but unregister_netdev() internally calls rtnl_lock().
So deadlock would occur.

Fixes: c41254006377 ("caif-hsi: Add rtnl support")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/caif/caif_hsi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/caif/caif_hsi.c b/drivers/net/caif/caif_hsi.c
index 433a14b9f731..253a1bbe37e8 100644
--- a/drivers/net/caif/caif_hsi.c
+++ b/drivers/net/caif/caif_hsi.c
@@ -1455,7 +1455,7 @@ static void __exit cfhsi_exit_module(void)
 	rtnl_lock();
 	list_for_each_safe(list_node, n, &cfhsi_list) {
 		cfhsi = list_entry(list_node, struct cfhsi, list);
-		unregister_netdev(cfhsi->ndev);
+		unregister_netdevice(cfhsi->ndev);
 	}
 	rtnl_unlock();
 }
-- 
2.20.1


From b9a93d2d91ab56640b31aa699c393c44fa7c9919 Mon Sep 17 00:00:00 2001
From: Haiyang Zhang <haiyangz@microsoft.com>
Date: Fri, 19 Jul 2019 17:33:51 +0000
Subject: [PATCH 05/45] hv_netvsc: Fix extra rcu_read_unlock in
 netvsc_recv_callback()

[ Upstream commit be4363bdf0ce9530f15aa0a03d1060304d116b15 ]

There is an extra rcu_read_unlock left in netvsc_recv_callback(),
after a previous patch that removes RCU from this function.
This patch removes the extra RCU unlock.

Fixes: 345ac08990b8 ("hv_netvsc: pass netvsc_device to receive callback")
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/netvsc_drv.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index e7d8884b1a10..e60a620f9e31 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -849,7 +849,6 @@ int netvsc_recv_callback(struct net_device *net,
 
 	if (unlikely(!skb)) {
 		++net_device_ctx->eth_stats.rx_no_memory;
-		rcu_read_unlock();
 		return NVSP_STAT_FAIL;
 	}
 
-- 
2.20.1


From 77cb411df42fe2a1a87285c82cb62dffded23f04 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 27 Jun 2019 01:27:01 -0700
Subject: [PATCH 06/45] igmp: fix memory leak in igmpv3_del_delrec()

[ Upstream commit e5b1c6c6277d5a283290a8c033c72544746f9b5b ]

im->tomb and/or im->sources might not be NULL, but we
currently overwrite their values blindly.

Using swap() will make sure the following call to kfree_pmc(pmc)
will properly free the psf structures.

Tested with the C repro provided by syzbot, which basically does :

 socket(PF_INET, SOCK_DGRAM, IPPROTO_IP) = 3
 setsockopt(3, SOL_IP, IP_ADD_MEMBERSHIP, "\340\0\0\2\177\0\0\1\0\0\0\0", 12) = 0
 ioctl(3, SIOCSIFFLAGS, {ifr_name="lo", ifr_flags=0}) = 0
 setsockopt(3, SOL_IP, IP_MSFILTER, "\340\0\0\2\177\0\0\1\1\0\0\0\1\0\0\0\377\377\377\377", 20) = 0
 ioctl(3, SIOCSIFFLAGS, {ifr_name="lo", ifr_flags=IFF_UP}) = 0
 exit_group(0)                    = ?

BUG: memory leak
unreferenced object 0xffff88811450f140 (size 64):
  comm "softirq", pid 0, jiffies 4294942448 (age 32.070s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 ff ff ff ff 00 00 00 00  ................
    00 00 00 00 00 00 00 00 01 00 00 00 00 00 00 00  ................
  backtrace:
    [<00000000c7bad083>] kmemleak_alloc_recursive include/linux/kmemleak.h:43 [inline]
    [<00000000c7bad083>] slab_post_alloc_hook mm/slab.h:439 [inline]
    [<00000000c7bad083>] slab_alloc mm/slab.c:3326 [inline]
    [<00000000c7bad083>] kmem_cache_alloc_trace+0x13d/0x280 mm/slab.c:3553
    [<000000009acc4151>] kmalloc include/linux/slab.h:547 [inline]
    [<000000009acc4151>] kzalloc include/linux/slab.h:742 [inline]
    [<000000009acc4151>] ip_mc_add1_src net/ipv4/igmp.c:1976 [inline]
    [<000000009acc4151>] ip_mc_add_src+0x36b/0x400 net/ipv4/igmp.c:2100
    [<000000004ac14566>] ip_mc_msfilter+0x22d/0x310 net/ipv4/igmp.c:2484
    [<0000000052d8f995>] do_ip_setsockopt.isra.0+0x1795/0x1930 net/ipv4/ip_sockglue.c:959
    [<000000004ee1e21f>] ip_setsockopt+0x3b/0xb0 net/ipv4/ip_sockglue.c:1248
    [<0000000066cdfe74>] udp_setsockopt+0x4e/0x90 net/ipv4/udp.c:2618
    [<000000009383a786>] sock_common_setsockopt+0x38/0x50 net/core/sock.c:3126
    [<00000000d8ac0c94>] __sys_setsockopt+0x98/0x120 net/socket.c:2072
    [<000000001b1e9666>] __do_sys_setsockopt net/socket.c:2083 [inline]
    [<000000001b1e9666>] __se_sys_setsockopt net/socket.c:2080 [inline]
    [<000000001b1e9666>] __x64_sys_setsockopt+0x26/0x30 net/socket.c:2080
    [<00000000420d395e>] do_syscall_64+0x76/0x1a0 arch/x86/entry/common.c:301
    [<000000007fd83a4b>] entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 24803f38a5c0 ("igmp: do not remove igmp souce list info when set link down")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Hangbin Liu <liuhangbin@gmail.com>
Reported-by: syzbot+6ca1abd0db68b5173a4f@syzkaller.appspotmail.com
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/igmp.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index eb03153dfe12..792d16f7b62d 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -1232,12 +1232,8 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im)
 	if (pmc) {
 		im->interface = pmc->interface;
 		if (im->sfmode == MCAST_INCLUDE) {
-			im->tomb = pmc->tomb;
-			pmc->tomb = NULL;
-
-			im->sources = pmc->sources;
-			pmc->sources = NULL;
-
+			swap(im->tomb, pmc->tomb);
+			swap(im->sources, pmc->sources);
 			for (psf = im->sources; psf; psf = psf->sf_next)
 				psf->sf_crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
 		} else {
-- 
2.20.1


From 7e471ac7af3cec2594308944a6d85cf1012280ea Mon Sep 17 00:00:00 2001
From: Matteo Croce <mcroce@redhat.com>
Date: Mon, 1 Jul 2019 19:01:55 +0200
Subject: [PATCH 07/45] ipv4: don't set IPv6 only flags to IPv4 addresses

[ Upstream commit 2e60546368165c2449564d71f6005dda9205b5fb ]

Avoid the situation where an IPV6 only flag is applied to an IPv4 address:

    # ip addr add 192.0.2.1/24 dev dummy0 nodad home mngtmpaddr noprefixroute
    # ip -4 addr show dev dummy0
    2: dummy0: <BROADCAST,NOARP,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN group default qlen 1000
        inet 192.0.2.1/24 scope global noprefixroute dummy0
           valid_lft forever preferred_lft forever

Or worse, by sending a malicious netlink command:

    # ip -4 addr show dev dummy0
    2: dummy0: <BROADCAST,NOARP,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN group default qlen 1000
        inet 192.0.2.1/24 scope global nodad optimistic dadfailed home tentative mngtmpaddr noprefixroute stable-privacy dummy0
           valid_lft forever preferred_lft forever

Signed-off-by: Matteo Croce <mcroce@redhat.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/devinet.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index eb514f312e6f..83944b7480c8 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -66,6 +66,11 @@
 #include <net/net_namespace.h>
 #include <net/addrconf.h>
 
+#define IPV6ONLY_FLAGS	\
+		(IFA_F_NODAD | IFA_F_OPTIMISTIC | IFA_F_DADFAILED | \
+		 IFA_F_HOMEADDRESS | IFA_F_TENTATIVE | \
+		 IFA_F_MANAGETEMPADDR | IFA_F_STABLE_PRIVACY)
+
 static struct ipv4_devconf ipv4_devconf = {
 	.data = {
 		[IPV4_DEVCONF_ACCEPT_REDIRECTS - 1] = 1,
@@ -472,6 +477,9 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh,
 	ifa->ifa_flags &= ~IFA_F_SECONDARY;
 	last_primary = &in_dev->ifa_list;
 
+	/* Don't set IPv6 only flags to IPv4 addresses */
+	ifa->ifa_flags &= ~IPV6ONLY_FLAGS;
+
 	for (ifap = &in_dev->ifa_list; (ifa1 = *ifap) != NULL;
 	     ifap = &ifa1->ifa_next) {
 		if (!(ifa1->ifa_flags & IFA_F_SECONDARY) &&
-- 
2.20.1


From 084e2051ba9468f0385aafcf15174c3f9d720474 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 17 Jul 2019 15:08:43 -0700
Subject: [PATCH 08/45] ipv6: rt6_check should return NULL if 'from' is NULL

[ Upstream commit 49d05fe2c9d1b4a27761c9807fec39b8155bef9e ]

Paul reported that l2tp sessions were broken after the commit referenced
in the Fixes tag. Prior to this commit rt6_check returned NULL if the
rt6_info 'from' was NULL - ie., the dst_entry was disconnected from a FIB
entry. Restore that behavior.

Fixes: 93531c674315 ("net/ipv6: separate handling of FIB entries from dst based routes")
Reported-by: Paul Donohue <linux-kernel@PaulSD.com>
Tested-by: Paul Donohue <linux-kernel@PaulSD.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index ab348489bd8a..9fc2d803c684 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2183,7 +2183,7 @@ static struct dst_entry *rt6_check(struct rt6_info *rt,
 {
 	u32 rt_cookie = 0;
 
-	if ((from && !fib6_get_cookie_safe(from, &rt_cookie)) ||
+	if (!from || !fib6_get_cookie_safe(from, &rt_cookie) ||
 	    rt_cookie != cookie)
 		return NULL;
 
-- 
2.20.1


From e6c23ee5fa775103d756289f9e037868e7c1b284 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 17 Jul 2019 23:39:33 +0300
Subject: [PATCH 09/45] ipv6: Unlink sibling route in case of failure

[ Upstream commit 54851aa90cf27041d64b12f65ac72e9f97bd90fd ]

When a route needs to be appended to an existing multipath route,
fib6_add_rt2node() first appends it to the siblings list and increments
the number of sibling routes on each sibling.

Later, the function notifies the route via call_fib6_entry_notifiers().
In case the notification is vetoed, the route is not unlinked from the
siblings list, which can result in a use-after-free.

Fix this by unlinking the route from the siblings list before returning
an error.

Audited the rest of the call sites from which the FIB notification chain
is called and could not find more problems.

Fixes: 2233000cba40 ("net/ipv6: Move call_fib6_entry_notifiers up for route adds")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Alexander Petrovskiy <alexpe@mellanox.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_fib.c | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 9915f64b38a0..4b1a898982d0 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1113,8 +1113,24 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
 		err = call_fib6_entry_notifiers(info->nl_net,
 						FIB_EVENT_ENTRY_ADD,
 						rt, extack);
-		if (err)
+		if (err) {
+			struct fib6_info *sibling, *next_sibling;
+
+			/* If the route has siblings, then it first
+			 * needs to be unlinked from them.
+			 */
+			if (!rt->fib6_nsiblings)
+				return err;
+
+			list_for_each_entry_safe(sibling, next_sibling,
+						 &rt->fib6_siblings,
+						 fib6_siblings)
+				sibling->fib6_nsiblings--;
+			rt->fib6_nsiblings = 0;
+			list_del_init(&rt->fib6_siblings);
+			rt6_multipath_rebalance(next_sibling);
 			return err;
+		}
 
 		rcu_assign_pointer(rt->fib6_next, iter);
 		atomic_inc(&rt->fib6_ref);
-- 
2.20.1


From 5a8364831d1f42fc36d35039df73bba86dc2b9cf Mon Sep 17 00:00:00 2001
From: Justin Chen <justinpopo6@gmail.com>
Date: Wed, 17 Jul 2019 14:58:53 -0700
Subject: [PATCH 10/45] net: bcmgenet: use promisc for unsupported filters

[ Upstream commit 35cbef9863640f06107144687bd13151bc2e8ce3 ]

Currently we silently ignore filters if we cannot meet the filter
requirements. This will lead to the MAC dropping packets that are
expected to pass. A better solution would be to set the NIC to promisc
mode when the required filters cannot be met.

Also correct the number of MDF filters supported. It should be 17,
not 16.

Signed-off-by: Justin Chen <justinpopo6@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/broadcom/genet/bcmgenet.c    | 57 +++++++++----------
 1 file changed, 26 insertions(+), 31 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 983245c0867c..2b79ef17e846 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -3086,39 +3086,42 @@ static void bcmgenet_timeout(struct net_device *dev)
 	netif_tx_wake_all_queues(dev);
 }
 
-#define MAX_MC_COUNT	16
+#define MAX_MDF_FILTER	17
 
 static inline void bcmgenet_set_mdf_addr(struct bcmgenet_priv *priv,
 					 unsigned char *addr,
-					 int *i,
-					 int *mc)
+					 int *i)
 {
-	u32 reg;
-
 	bcmgenet_umac_writel(priv, addr[0] << 8 | addr[1],
 			     UMAC_MDF_ADDR + (*i * 4));
 	bcmgenet_umac_writel(priv, addr[2] << 24 | addr[3] << 16 |
 			     addr[4] << 8 | addr[5],
 			     UMAC_MDF_ADDR + ((*i + 1) * 4));
-	reg = bcmgenet_umac_readl(priv, UMAC_MDF_CTRL);
-	reg |= (1 << (MAX_MC_COUNT - *mc));
-	bcmgenet_umac_writel(priv, reg, UMAC_MDF_CTRL);
 	*i += 2;
-	(*mc)++;
 }
 
 static void bcmgenet_set_rx_mode(struct net_device *dev)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	struct netdev_hw_addr *ha;
-	int i, mc;
+	int i, nfilter;
 	u32 reg;
 
 	netif_dbg(priv, hw, dev, "%s: %08X\n", __func__, dev->flags);
 
-	/* Promiscuous mode */
+	/* Number of filters needed */
+	nfilter = netdev_uc_count(dev) + netdev_mc_count(dev) + 2;
+
+	/*
+	 * Turn on promicuous mode for three scenarios
+	 * 1. IFF_PROMISC flag is set
+	 * 2. IFF_ALLMULTI flag is set
+	 * 3. The number of filters needed exceeds the number filters
+	 *    supported by the hardware.
+	*/
 	reg = bcmgenet_umac_readl(priv, UMAC_CMD);
-	if (dev->flags & IFF_PROMISC) {
+	if ((dev->flags & (IFF_PROMISC | IFF_ALLMULTI)) ||
+	    (nfilter > MAX_MDF_FILTER)) {
 		reg |= CMD_PROMISC;
 		bcmgenet_umac_writel(priv, reg, UMAC_CMD);
 		bcmgenet_umac_writel(priv, 0, UMAC_MDF_CTRL);
@@ -3128,32 +3131,24 @@ static void bcmgenet_set_rx_mode(struct net_device *dev)
 		bcmgenet_umac_writel(priv, reg, UMAC_CMD);
 	}
 
-	/* UniMac doesn't support ALLMULTI */
-	if (dev->flags & IFF_ALLMULTI) {
-		netdev_warn(dev, "ALLMULTI is not supported\n");
-		return;
-	}
-
 	/* update MDF filter */
 	i = 0;
-	mc = 0;
 	/* Broadcast */
-	bcmgenet_set_mdf_addr(priv, dev->broadcast, &i, &mc);
+	bcmgenet_set_mdf_addr(priv, dev->broadcast, &i);
 	/* my own address.*/
-	bcmgenet_set_mdf_addr(priv, dev->dev_addr, &i, &mc);
-	/* Unicast list*/
-	if (netdev_uc_count(dev) > (MAX_MC_COUNT - mc))
-		return;
+	bcmgenet_set_mdf_addr(priv, dev->dev_addr, &i);
 
-	if (!netdev_uc_empty(dev))
-		netdev_for_each_uc_addr(ha, dev)
-			bcmgenet_set_mdf_addr(priv, ha->addr, &i, &mc);
-	/* Multicast */
-	if (netdev_mc_empty(dev) || netdev_mc_count(dev) >= (MAX_MC_COUNT - mc))
-		return;
+	/* Unicast */
+	netdev_for_each_uc_addr(ha, dev)
+		bcmgenet_set_mdf_addr(priv, ha->addr, &i);
 
+	/* Multicast */
 	netdev_for_each_mc_addr(ha, dev)
-		bcmgenet_set_mdf_addr(priv, ha->addr, &i, &mc);
+		bcmgenet_set_mdf_addr(priv, ha->addr, &i);
+
+	/* Enable filters */
+	reg = GENMASK(MAX_MDF_FILTER - 1, MAX_MDF_FILTER - nfilter);
+	bcmgenet_umac_writel(priv, reg, UMAC_MDF_CTRL);
 }
 
 /* Set the hardware MAC address. */
-- 
2.20.1


From 92848a260ba16e8917b9140c87f555f453c2d1f0 Mon Sep 17 00:00:00 2001
From: Baruch Siach <baruch@tkos.co.il>
Date: Thu, 27 Jun 2019 21:17:39 +0300
Subject: [PATCH 11/45] net: dsa: mv88e6xxx: wait after reset deactivation

[ Upstream commit 7b75e49de424ceb53d13e60f35d0a73765626fda ]

Add a 1ms delay after reset deactivation. Otherwise the chip returns
bogus ID value. This is observed with 88E6390 (Peridot) chip.

Signed-off-by: Baruch Siach <baruch@tkos.co.il>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index ae750ab9a4d7..5f81d9a3a2a6 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -4910,6 +4910,8 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev)
 		err = PTR_ERR(chip->reset);
 		goto out;
 	}
+	if (chip->reset)
+		usleep_range(1000, 2000);
 
 	err = mv88e6xxx_detect(chip);
 	if (err)
-- 
2.20.1


From 9adc419dbdf678a038f4159d964389862bcd4add Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 26 Jun 2019 20:40:45 +0200
Subject: [PATCH 12/45] net: make skb_dst_force return true when dst is
 refcounted

[ Upstream commit b60a77386b1d4868f72f6353d35dabe5fbe981f2 ]

netfilter did not expect that skb_dst_force() can cause skb to lose its
dst entry.

I got a bug report with a skb->dst NULL dereference in netfilter
output path.  The backtrace contains nf_reinject(), so the dst might have
been cleared when skb got queued to userspace.

Other users were fixed via
if (skb_dst(skb)) {
	skb_dst_force(skb);
	if (!skb_dst(skb))
		goto handle_err;
}

But I think its preferable to make the 'dst might be cleared' part
of the function explicit.

In netfilter case, skb with a null dst is expected when queueing in
prerouting hook, so drop skb for the other hooks.

v2:
 v1 of this patch returned true in case skb had no dst entry.
 Eric said:
   Say if we have two skb_dst_force() calls for some reason
   on the same skb, only the first one will return false.

 This now returns false even when skb had no dst, as per Erics
 suggestion, so callers might need to check skb_dst() first before
 skb_dst_force().

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst.h        | 5 ++++-
 net/netfilter/nf_queue.c | 6 +++++-
 2 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/include/net/dst.h b/include/net/dst.h
index 6cf0870414c7..ffc8ee0ea5e5 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -313,8 +313,9 @@ static inline bool dst_hold_safe(struct dst_entry *dst)
  * @skb: buffer
  *
  * If dst is not yet refcounted and not destroyed, grab a ref on it.
+ * Returns true if dst is refcounted.
  */
-static inline void skb_dst_force(struct sk_buff *skb)
+static inline bool skb_dst_force(struct sk_buff *skb)
 {
 	if (skb_dst_is_noref(skb)) {
 		struct dst_entry *dst = skb_dst(skb);
@@ -325,6 +326,8 @@ static inline void skb_dst_force(struct sk_buff *skb)
 
 		skb->_skb_refdst = (unsigned long)dst;
 	}
+
+	return skb->_skb_refdst != 0UL;
 }
 
 
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index 5b86574e7b89..12a008cf8865 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -190,6 +190,11 @@ static int __nf_queue(struct sk_buff *skb, const struct nf_hook_state *state,
 		goto err;
 	}
 
+	if (!skb_dst_force(skb) && state->hook != NF_INET_PRE_ROUTING) {
+		status = -ENETDOWN;
+		goto err;
+	}
+
 	*entry = (struct nf_queue_entry) {
 		.skb	= skb,
 		.state	= *state,
@@ -198,7 +203,6 @@ static int __nf_queue(struct sk_buff *skb, const struct nf_hook_state *state,
 	};
 
 	nf_queue_entry_get_refs(entry);
-	skb_dst_force(skb);
 
 	switch (entry->state.pf) {
 	case AF_INET:
-- 
2.20.1


From 0d829cfeeb5d6b6a1ab89f5662ec7f4e5023398a Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Sun, 14 Jul 2019 23:36:11 +0200
Subject: [PATCH 13/45] net: neigh: fix multiple neigh timer scheduling

[ Upstream commit 071c37983d99da07797294ea78e9da1a6e287144 ]

Neigh timer can be scheduled multiple times from userspace adding
multiple neigh entries and forcing the neigh timer scheduling passing
NTF_USE in the netlink requests.
This will result in a refcount leak and in the following dump stack:

[   32.465295] NEIGH: BUG, double timer add, state is 8
[   32.465308] CPU: 0 PID: 416 Comm: double_timer_ad Not tainted 5.2.0+ #65
[   32.465311] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.12.0-2.fc30 04/01/2014
[   32.465313] Call Trace:
[   32.465318]  dump_stack+0x7c/0xc0
[   32.465323]  __neigh_event_send+0x20c/0x880
[   32.465326]  ? ___neigh_create+0x846/0xfb0
[   32.465329]  ? neigh_lookup+0x2a9/0x410
[   32.465332]  ? neightbl_fill_info.constprop.0+0x800/0x800
[   32.465334]  neigh_add+0x4f8/0x5e0
[   32.465337]  ? neigh_xmit+0x620/0x620
[   32.465341]  ? find_held_lock+0x85/0xa0
[   32.465345]  rtnetlink_rcv_msg+0x204/0x570
[   32.465348]  ? rtnl_dellink+0x450/0x450
[   32.465351]  ? mark_held_locks+0x90/0x90
[   32.465354]  ? match_held_lock+0x1b/0x230
[   32.465357]  netlink_rcv_skb+0xc4/0x1d0
[   32.465360]  ? rtnl_dellink+0x450/0x450
[   32.465363]  ? netlink_ack+0x420/0x420
[   32.465366]  ? netlink_deliver_tap+0x115/0x560
[   32.465369]  ? __alloc_skb+0xc9/0x2f0
[   32.465372]  netlink_unicast+0x270/0x330
[   32.465375]  ? netlink_attachskb+0x2f0/0x2f0
[   32.465378]  netlink_sendmsg+0x34f/0x5a0
[   32.465381]  ? netlink_unicast+0x330/0x330
[   32.465385]  ? move_addr_to_kernel.part.0+0x20/0x20
[   32.465388]  ? netlink_unicast+0x330/0x330
[   32.465391]  sock_sendmsg+0x91/0xa0
[   32.465394]  ___sys_sendmsg+0x407/0x480
[   32.465397]  ? copy_msghdr_from_user+0x200/0x200
[   32.465401]  ? _raw_spin_unlock_irqrestore+0x37/0x40
[   32.465404]  ? lockdep_hardirqs_on+0x17d/0x250
[   32.465407]  ? __wake_up_common_lock+0xcb/0x110
[   32.465410]  ? __wake_up_common+0x230/0x230
[   32.465413]  ? netlink_bind+0x3e1/0x490
[   32.465416]  ? netlink_setsockopt+0x540/0x540
[   32.465420]  ? __fget_light+0x9c/0xf0
[   32.465423]  ? sockfd_lookup_light+0x8c/0xb0
[   32.465426]  __sys_sendmsg+0xa5/0x110
[   32.465429]  ? __ia32_sys_shutdown+0x30/0x30
[   32.465432]  ? __fd_install+0xe1/0x2c0
[   32.465435]  ? lockdep_hardirqs_off+0xb5/0x100
[   32.465438]  ? mark_held_locks+0x24/0x90
[   32.465441]  ? do_syscall_64+0xf/0x270
[   32.465444]  do_syscall_64+0x63/0x270
[   32.465448]  entry_SYSCALL_64_after_hwframe+0x49/0xbe

Fix the issue unscheduling neigh_timer if selected entry is in 'IN_TIMER'
receiving a netlink request with NTF_USE flag set

Reported-by: Marek Majkowski <marek@cloudflare.com>
Fixes: 0c5c2d308906 ("neigh: Allow for user space users of the neighbour table")
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index cce4fbcd7dcb..2f693f1168e1 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1126,6 +1126,7 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
 
 			atomic_set(&neigh->probes,
 				   NEIGH_VAR(neigh->parms, UCAST_PROBES));
+			neigh_del_timer(neigh);
 			neigh->nud_state     = NUD_INCOMPLETE;
 			neigh->updated = now;
 			next = now + max(NEIGH_VAR(neigh->parms, RETRANS_TIME),
@@ -1142,6 +1143,7 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
 		}
 	} else if (neigh->nud_state & NUD_STALE) {
 		neigh_dbg(2, "neigh %p is delayed\n", neigh);
+		neigh_del_timer(neigh);
 		neigh->nud_state = NUD_DELAY;
 		neigh->updated = jiffies;
 		neigh_add_timer(neigh, jiffies +
-- 
2.20.1


From 52b16efecb6da453577e3c279a569eaf1dece8c8 Mon Sep 17 00:00:00 2001
From: John Hurley <john.hurley@netronome.com>
Date: Thu, 27 Jun 2019 14:37:30 +0100
Subject: [PATCH 14/45] net: openvswitch: fix csum updates for MPLS actions

[ Upstream commit 0e3183cd2a64843a95b62f8bd4a83605a4cf0615 ]

Skbs may have their checksum value populated by HW. If this is a checksum
calculated over the entire packet then the CHECKSUM_COMPLETE field is
marked. Changes to the data pointer on the skb throughout the network
stack still try to maintain this complete csum value if it is required
through functions such as skb_postpush_rcsum.

The MPLS actions in Open vSwitch modify a CHECKSUM_COMPLETE value when
changes are made to packet data without a push or a pull. This occurs when
the ethertype of the MAC header is changed or when MPLS lse fields are
modified.

The modification is carried out using the csum_partial function to get the
csum of a buffer and add it into the larger checksum. The buffer is an
inversion of the data to be removed followed by the new data. Because the
csum is calculated over 16 bits and these values align with 16 bits, the
effect is the removal of the old value from the CHECKSUM_COMPLETE and
addition of the new value.

However, the csum fed into the function and the outcome of the
calculation are also inverted. This would only make sense if it was the
new value rather than the old that was inverted in the input buffer.

Fix the issue by removing the bit inverts in the csum_partial calculation.

The bug was verified and the fix tested by comparing the folded value of
the updated CHECKSUM_COMPLETE value with the folded value of a full
software checksum calculation (reset skb->csum to 0 and run
skb_checksum_complete(skb)). Prior to the fix the outcomes differed but
after they produce the same result.

Fixes: 25cd9ba0abc0 ("openvswitch: Add basic MPLS support to kernel")
Fixes: bc7cc5999fd3 ("openvswitch: update checksum in {push,pop}_mpls")
Signed-off-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/actions.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index e47ebbbe71b8..b85b37518fc5 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -175,8 +175,7 @@ static void update_ethertype(struct sk_buff *skb, struct ethhdr *hdr,
 	if (skb->ip_summed == CHECKSUM_COMPLETE) {
 		__be16 diff[] = { ~(hdr->h_proto), ethertype };
 
-		skb->csum = ~csum_partial((char *)diff, sizeof(diff),
-					~skb->csum);
+		skb->csum = csum_partial((char *)diff, sizeof(diff), skb->csum);
 	}
 
 	hdr->h_proto = ethertype;
@@ -268,8 +267,7 @@ static int set_mpls(struct sk_buff *skb, struct sw_flow_key *flow_key,
 	if (skb->ip_summed == CHECKSUM_COMPLETE) {
 		__be32 diff[] = { ~(stack->label_stack_entry), lse };
 
-		skb->csum = ~csum_partial((char *)diff, sizeof(diff),
-					  ~skb->csum);
+		skb->csum = csum_partial((char *)diff, sizeof(diff), skb->csum);
 	}
 
 	stack->label_stack_entry = lse;
-- 
2.20.1


From 22d32437a60870d53872c0a5bb93fc381fbea4e3 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sun, 21 Jul 2019 18:50:08 +0200
Subject: [PATCH 15/45] net: phy: sfp: hwmon: Fix scaling of RX power

[ Upstream commit 0cea0e1148fe134a4a3aaf0b1496f09241fb943a ]

The RX power read from the SFP uses units of 0.1uW. This must be
scaled to units of uW for HWMON. This requires a divide by 10, not the
current 100.

With this change in place, sensors(1) and ethtool -m agree:

sff2-isa-0000
Adapter: ISA adapter
in0:          +3.23 V
temp1:        +33.1 C
power1:      270.00 uW
power2:      200.00 uW
curr1:        +0.01 A

        Laser output power                        : 0.2743 mW / -5.62 dBm
        Receiver signal average optical power     : 0.2014 mW / -6.96 dBm

Reported-by: chris.healy@zii.aero
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Fixes: 1323061a018a ("net: phy: sfp: Add HWMON support for module sensors")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/sfp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index 71812be0ac64..825857efcc4e 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -514,7 +514,7 @@ static int sfp_hwmon_read_sensor(struct sfp *sfp, int reg, long *value)
 
 static void sfp_hwmon_to_rx_power(long *value)
 {
-	*value = DIV_ROUND_CLOSEST(*value, 100);
+	*value = DIV_ROUND_CLOSEST(*value, 10);
 }
 
 static void sfp_hwmon_calibrate(struct sfp *sfp, unsigned int slope, int offset,
-- 
2.20.1


From e2b7e35c74211f31893910494cee3ee18635193a Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Tue, 16 Jul 2019 13:57:30 -0700
Subject: [PATCH 16/45] net_sched: unset TCQ_F_CAN_BYPASS when adding filters

[ Upstream commit 3f05e6886a595c9a29a309c52f45326be917823c ]

For qdisc's that support TC filters and set TCQ_F_CAN_BYPASS,
notably fq_codel, it makes no sense to let packets bypass the TC
filters we setup in any scenario, otherwise our packets steering
policy could not be enforced.

This can be reproduced easily with the following script:

 ip li add dev dummy0 type dummy
 ifconfig dummy0 up
 tc qd add dev dummy0 root fq_codel
 tc filter add dev dummy0 parent 8001: protocol arp basic action mirred egress redirect dev lo
 tc filter add dev dummy0 parent 8001: protocol ip basic action mirred egress redirect dev lo
 ping -I dummy0 192.168.112.1

Without this patch, packets are sent directly to dummy0 without
hitting any of the filters. With this patch, packets are redirected
to loopback as expected.

This fix is not perfect, it only unsets the flag but does not set it back
because we have to save the information somewhere in the qdisc if we
really want that. Note, both fq_codel and sfq clear this flag in their
->bind_tcf() but this is clearly not sufficient when we don't use any
class ID.

Fixes: 23624935e0c4 ("net_sched: TCQ_F_CAN_BYPASS generalization")
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c      | 1 +
 net/sched/sch_fq_codel.c | 2 --
 net/sched/sch_sfq.c      | 2 --
 3 files changed, 1 insertion(+), 4 deletions(-)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 99ae30c177c7..93912a6001dc 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -2162,6 +2162,7 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
 		tfilter_notify(net, skb, n, tp, block, q, parent, fh,
 			       RTM_NEWTFILTER, false, rtnl_held);
 		tfilter_put(tp, fh);
+		q->flags &= ~TCQ_F_CAN_BYPASS;
 	}
 
 errout:
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index cd04d40c30b6..1971f3a29730 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -600,8 +600,6 @@ static unsigned long fq_codel_find(struct Qdisc *sch, u32 classid)
 static unsigned long fq_codel_bind(struct Qdisc *sch, unsigned long parent,
 			      u32 classid)
 {
-	/* we cannot bypass queue discipline anymore */
-	sch->flags &= ~TCQ_F_CAN_BYPASS;
 	return 0;
 }
 
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 2f2678197760..650f21463853 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -828,8 +828,6 @@ static unsigned long sfq_find(struct Qdisc *sch, u32 classid)
 static unsigned long sfq_bind(struct Qdisc *sch, unsigned long parent,
 			      u32 classid)
 {
-	/* we cannot bypass queue discipline anymore */
-	sch->flags &= ~TCQ_F_CAN_BYPASS;
 	return 0;
 }
 
-- 
2.20.1


From d042b4bf809b790d1a1b676206d9e811d707b04d Mon Sep 17 00:00:00 2001
From: Jose Abreu <Jose.Abreu@synopsys.com>
Date: Mon, 8 Jul 2019 14:26:28 +0200
Subject: [PATCH 17/45] net: stmmac: Re-work the queue selection for TSO
 packets

[ Upstream commit 4993e5b37e8bcb55ac90f76eb6d2432647273747 ]

Ben Hutchings says:
	"This is the wrong place to change the queue mapping.
	stmmac_xmit() is called with a specific TX queue locked,
	and accessing a different TX queue results in a data race
	for all of that queue's state.

	I think this commit should be reverted upstream and in all
	stable branches.  Instead, the driver should implement the
	ndo_select_queue operation and override the queue mapping there."

Fixes: c5acdbee22a1 ("net: stmmac: Send TSO packets always from Queue 0")
Suggested-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/stmicro/stmmac/stmmac_main.c | 29 ++++++++++++-------
 1 file changed, 19 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index a634054dcb11..ba423b852fd7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3055,17 +3055,8 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	/* Manage oversized TCP frames for GMAC4 device */
 	if (skb_is_gso(skb) && priv->tso) {
-		if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) {
-			/*
-			 * There is no way to determine the number of TSO
-			 * capable Queues. Let's use always the Queue 0
-			 * because if TSO is supported then at least this
-			 * one will be capable.
-			 */
-			skb_set_queue_mapping(skb, 0);
-
+		if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))
 			return stmmac_tso_xmit(skb, dev);
-		}
 	}
 
 	if (unlikely(stmmac_tx_avail(priv, queue) < nfrags + 1)) {
@@ -3882,6 +3873,23 @@ static int stmmac_setup_tc(struct net_device *ndev, enum tc_setup_type type,
 	}
 }
 
+static u16 stmmac_select_queue(struct net_device *dev, struct sk_buff *skb,
+			       struct net_device *sb_dev,
+			       select_queue_fallback_t fallback)
+{
+	if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) {
+		/*
+		 * There is no way to determine the number of TSO
+		 * capable Queues. Let's use always the Queue 0
+		 * because if TSO is supported then at least this
+		 * one will be capable.
+		 */
+		return 0;
+	}
+
+	return fallback(dev, skb, NULL) % dev->real_num_tx_queues;
+}
+
 static int stmmac_set_mac_address(struct net_device *ndev, void *addr)
 {
 	struct stmmac_priv *priv = netdev_priv(ndev);
@@ -4098,6 +4106,7 @@ static const struct net_device_ops stmmac_netdev_ops = {
 	.ndo_tx_timeout = stmmac_tx_timeout,
 	.ndo_do_ioctl = stmmac_ioctl,
 	.ndo_setup_tc = stmmac_setup_tc,
+	.ndo_select_queue = stmmac_select_queue,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = stmmac_poll_controller,
 #endif
-- 
2.20.1


From 5fad592e0be3b9f912c9397f9e1bd09c5d3f0c7a Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 28 Jun 2019 16:11:39 -0700
Subject: [PATCH 18/45] net/tls: make sure offload also gets the keys wiped

[ Upstream commit acd3e96d53a24d219f720ed4012b62723ae05da1 ]

Commit 86029d10af18 ("tls: zero the crypto information from tls_context
before freeing") added memzero_explicit() calls to clear the key material
before freeing struct tls_context, but it missed tls_device.c has its
own way of freeing this structure. Replace the missing free.

Fixes: 86029d10af18 ("tls: zero the crypto information from tls_context before freeing")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h    | 1 +
 net/tls/tls_device.c | 2 +-
 net/tls/tls_main.c   | 4 ++--
 3 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/include/net/tls.h b/include/net/tls.h
index a67ad7d56ff2..22de0f06d455 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -285,6 +285,7 @@ struct tls_offload_context_rx {
 	(ALIGN(sizeof(struct tls_offload_context_rx), sizeof(void *)) + \
 	 TLS_DRIVER_STATE_SIZE)
 
+void tls_ctx_free(struct tls_context *ctx);
 int wait_on_pending_writer(struct sock *sk, long *timeo);
 int tls_sk_query(struct sock *sk, int optname, char __user *optval,
 		int __user *optlen);
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 12454f0d5a63..f6e258e37611 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -61,7 +61,7 @@ static void tls_device_free_ctx(struct tls_context *ctx)
 	if (ctx->rx_conf == TLS_HW)
 		kfree(tls_offload_ctx_rx(ctx));
 
-	kfree(ctx);
+	tls_ctx_free(ctx);
 }
 
 static void tls_device_gc_task(struct work_struct *work)
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index f4f632824247..0c22af7b113f 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -251,7 +251,7 @@ static void tls_write_space(struct sock *sk)
 	ctx->sk_write_space(sk);
 }
 
-static void tls_ctx_free(struct tls_context *ctx)
+void tls_ctx_free(struct tls_context *ctx)
 {
 	if (!ctx)
 		return;
@@ -638,7 +638,7 @@ static void tls_hw_sk_destruct(struct sock *sk)
 
 	ctx->sk_destruct(sk);
 	/* Free ctx */
-	kfree(ctx);
+	tls_ctx_free(ctx);
 	icsk->icsk_ulp_data = NULL;
 }
 
-- 
2.20.1


From 1c649619e1b5496ccd72e2893ea36e6fe497a775 Mon Sep 17 00:00:00 2001
From: Yang Wei <albin_yang@163.com>
Date: Mon, 8 Jul 2019 22:57:39 +0800
Subject: [PATCH 19/45] nfc: fix potential illegal memory access

[ Upstream commit dd006fc434e107ef90f7de0db9907cbc1c521645 ]

The frags_q is not properly initialized, it may result in illegal memory
access when conn_info is NULL.
The "goto free_exit" should be replaced by "goto exit".

Signed-off-by: Yang Wei <albin_yang@163.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/nfc/nci/data.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/nfc/nci/data.c b/net/nfc/nci/data.c
index 908f25e3773e..5405d073804c 100644
--- a/net/nfc/nci/data.c
+++ b/net/nfc/nci/data.c
@@ -119,7 +119,7 @@ static int nci_queue_tx_data_frags(struct nci_dev *ndev,
 	conn_info = nci_get_conn_info_by_conn_id(ndev, conn_id);
 	if (!conn_info) {
 		rc = -EPROTO;
-		goto free_exit;
+		goto exit;
 	}
 
 	__skb_queue_head_init(&frags_q);
-- 
2.20.1


From cdd4c5baed39d9aaa5e22fa73d67b717ce247eca Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 13 Jul 2019 13:45:47 +0200
Subject: [PATCH 20/45] r8169: fix issue with confused RX unit after PHY
 power-down on RTL8411b

[ Upstream commit fe4e8db0392a6c2e795eb89ef5fcd86522e66248 ]

On RTL8411b the RX unit gets confused if the PHY is powered-down.
This was reported in [0] and confirmed by Realtek. Realtek provided
a sequence to fix the RX unit after PHY wakeup.

The issue itself seems to have been there longer, the Fixes tag
refers to where the fix applies properly.

[0] https://bugzilla.redhat.com/show_bug.cgi?id=1692075

Fixes: a99790bf5c7f ("r8169: Reinstate ASPM Support")
Tested-by: Ionut Radu <ionut.radu@gmail.com>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 137 +++++++++++++++++++++++++++
 1 file changed, 137 insertions(+)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 6d176be51a6b..309400fbf69d 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -5241,6 +5241,143 @@ static void rtl_hw_start_8411_2(struct rtl8169_private *tp)
 	/* disable aspm and clock request before access ephy */
 	rtl_hw_aspm_clkreq_enable(tp, false);
 	rtl_ephy_init(tp, e_info_8411_2, ARRAY_SIZE(e_info_8411_2));
+
+	/* The following Realtek-provided magic fixes an issue with the RX unit
+	 * getting confused after the PHY having been powered-down.
+	 */
+	r8168_mac_ocp_write(tp, 0xFC28, 0x0000);
+	r8168_mac_ocp_write(tp, 0xFC2A, 0x0000);
+	r8168_mac_ocp_write(tp, 0xFC2C, 0x0000);
+	r8168_mac_ocp_write(tp, 0xFC2E, 0x0000);
+	r8168_mac_ocp_write(tp, 0xFC30, 0x0000);
+	r8168_mac_ocp_write(tp, 0xFC32, 0x0000);
+	r8168_mac_ocp_write(tp, 0xFC34, 0x0000);
+	r8168_mac_ocp_write(tp, 0xFC36, 0x0000);
+	mdelay(3);
+	r8168_mac_ocp_write(tp, 0xFC26, 0x0000);
+
+	r8168_mac_ocp_write(tp, 0xF800, 0xE008);
+	r8168_mac_ocp_write(tp, 0xF802, 0xE00A);
+	r8168_mac_ocp_write(tp, 0xF804, 0xE00C);
+	r8168_mac_ocp_write(tp, 0xF806, 0xE00E);
+	r8168_mac_ocp_write(tp, 0xF808, 0xE027);
+	r8168_mac_ocp_write(tp, 0xF80A, 0xE04F);
+	r8168_mac_ocp_write(tp, 0xF80C, 0xE05E);
+	r8168_mac_ocp_write(tp, 0xF80E, 0xE065);
+	r8168_mac_ocp_write(tp, 0xF810, 0xC602);
+	r8168_mac_ocp_write(tp, 0xF812, 0xBE00);
+	r8168_mac_ocp_write(tp, 0xF814, 0x0000);
+	r8168_mac_ocp_write(tp, 0xF816, 0xC502);
+	r8168_mac_ocp_write(tp, 0xF818, 0xBD00);
+	r8168_mac_ocp_write(tp, 0xF81A, 0x074C);
+	r8168_mac_ocp_write(tp, 0xF81C, 0xC302);
+	r8168_mac_ocp_write(tp, 0xF81E, 0xBB00);
+	r8168_mac_ocp_write(tp, 0xF820, 0x080A);
+	r8168_mac_ocp_write(tp, 0xF822, 0x6420);
+	r8168_mac_ocp_write(tp, 0xF824, 0x48C2);
+	r8168_mac_ocp_write(tp, 0xF826, 0x8C20);
+	r8168_mac_ocp_write(tp, 0xF828, 0xC516);
+	r8168_mac_ocp_write(tp, 0xF82A, 0x64A4);
+	r8168_mac_ocp_write(tp, 0xF82C, 0x49C0);
+	r8168_mac_ocp_write(tp, 0xF82E, 0xF009);
+	r8168_mac_ocp_write(tp, 0xF830, 0x74A2);
+	r8168_mac_ocp_write(tp, 0xF832, 0x8CA5);
+	r8168_mac_ocp_write(tp, 0xF834, 0x74A0);
+	r8168_mac_ocp_write(tp, 0xF836, 0xC50E);
+	r8168_mac_ocp_write(tp, 0xF838, 0x9CA2);
+	r8168_mac_ocp_write(tp, 0xF83A, 0x1C11);
+	r8168_mac_ocp_write(tp, 0xF83C, 0x9CA0);
+	r8168_mac_ocp_write(tp, 0xF83E, 0xE006);
+	r8168_mac_ocp_write(tp, 0xF840, 0x74F8);
+	r8168_mac_ocp_write(tp, 0xF842, 0x48C4);
+	r8168_mac_ocp_write(tp, 0xF844, 0x8CF8);
+	r8168_mac_ocp_write(tp, 0xF846, 0xC404);
+	r8168_mac_ocp_write(tp, 0xF848, 0xBC00);
+	r8168_mac_ocp_write(tp, 0xF84A, 0xC403);
+	r8168_mac_ocp_write(tp, 0xF84C, 0xBC00);
+	r8168_mac_ocp_write(tp, 0xF84E, 0x0BF2);
+	r8168_mac_ocp_write(tp, 0xF850, 0x0C0A);
+	r8168_mac_ocp_write(tp, 0xF852, 0xE434);
+	r8168_mac_ocp_write(tp, 0xF854, 0xD3C0);
+	r8168_mac_ocp_write(tp, 0xF856, 0x49D9);
+	r8168_mac_ocp_write(tp, 0xF858, 0xF01F);
+	r8168_mac_ocp_write(tp, 0xF85A, 0xC526);
+	r8168_mac_ocp_write(tp, 0xF85C, 0x64A5);
+	r8168_mac_ocp_write(tp, 0xF85E, 0x1400);
+	r8168_mac_ocp_write(tp, 0xF860, 0xF007);
+	r8168_mac_ocp_write(tp, 0xF862, 0x0C01);
+	r8168_mac_ocp_write(tp, 0xF864, 0x8CA5);
+	r8168_mac_ocp_write(tp, 0xF866, 0x1C15);
+	r8168_mac_ocp_write(tp, 0xF868, 0xC51B);
+	r8168_mac_ocp_write(tp, 0xF86A, 0x9CA0);
+	r8168_mac_ocp_write(tp, 0xF86C, 0xE013);
+	r8168_mac_ocp_write(tp, 0xF86E, 0xC519);
+	r8168_mac_ocp_write(tp, 0xF870, 0x74A0);
+	r8168_mac_ocp_write(tp, 0xF872, 0x48C4);
+	r8168_mac_ocp_write(tp, 0xF874, 0x8CA0);
+	r8168_mac_ocp_write(tp, 0xF876, 0xC516);
+	r8168_mac_ocp_write(tp, 0xF878, 0x74A4);
+	r8168_mac_ocp_write(tp, 0xF87A, 0x48C8);
+	r8168_mac_ocp_write(tp, 0xF87C, 0x48CA);
+	r8168_mac_ocp_write(tp, 0xF87E, 0x9CA4);
+	r8168_mac_ocp_write(tp, 0xF880, 0xC512);
+	r8168_mac_ocp_write(tp, 0xF882, 0x1B00);
+	r8168_mac_ocp_write(tp, 0xF884, 0x9BA0);
+	r8168_mac_ocp_write(tp, 0xF886, 0x1B1C);
+	r8168_mac_ocp_write(tp, 0xF888, 0x483F);
+	r8168_mac_ocp_write(tp, 0xF88A, 0x9BA2);
+	r8168_mac_ocp_write(tp, 0xF88C, 0x1B04);
+	r8168_mac_ocp_write(tp, 0xF88E, 0xC508);
+	r8168_mac_ocp_write(tp, 0xF890, 0x9BA0);
+	r8168_mac_ocp_write(tp, 0xF892, 0xC505);
+	r8168_mac_ocp_write(tp, 0xF894, 0xBD00);
+	r8168_mac_ocp_write(tp, 0xF896, 0xC502);
+	r8168_mac_ocp_write(tp, 0xF898, 0xBD00);
+	r8168_mac_ocp_write(tp, 0xF89A, 0x0300);
+	r8168_mac_ocp_write(tp, 0xF89C, 0x051E);
+	r8168_mac_ocp_write(tp, 0xF89E, 0xE434);
+	r8168_mac_ocp_write(tp, 0xF8A0, 0xE018);
+	r8168_mac_ocp_write(tp, 0xF8A2, 0xE092);
+	r8168_mac_ocp_write(tp, 0xF8A4, 0xDE20);
+	r8168_mac_ocp_write(tp, 0xF8A6, 0xD3C0);
+	r8168_mac_ocp_write(tp, 0xF8A8, 0xC50F);
+	r8168_mac_ocp_write(tp, 0xF8AA, 0x76A4);
+	r8168_mac_ocp_write(tp, 0xF8AC, 0x49E3);
+	r8168_mac_ocp_write(tp, 0xF8AE, 0xF007);
+	r8168_mac_ocp_write(tp, 0xF8B0, 0x49C0);
+	r8168_mac_ocp_write(tp, 0xF8B2, 0xF103);
+	r8168_mac_ocp_write(tp, 0xF8B4, 0xC607);
+	r8168_mac_ocp_write(tp, 0xF8B6, 0xBE00);
+	r8168_mac_ocp_write(tp, 0xF8B8, 0xC606);
+	r8168_mac_ocp_write(tp, 0xF8BA, 0xBE00);
+	r8168_mac_ocp_write(tp, 0xF8BC, 0xC602);
+	r8168_mac_ocp_write(tp, 0xF8BE, 0xBE00);
+	r8168_mac_ocp_write(tp, 0xF8C0, 0x0C4C);
+	r8168_mac_ocp_write(tp, 0xF8C2, 0x0C28);
+	r8168_mac_ocp_write(tp, 0xF8C4, 0x0C2C);
+	r8168_mac_ocp_write(tp, 0xF8C6, 0xDC00);
+	r8168_mac_ocp_write(tp, 0xF8C8, 0xC707);
+	r8168_mac_ocp_write(tp, 0xF8CA, 0x1D00);
+	r8168_mac_ocp_write(tp, 0xF8CC, 0x8DE2);
+	r8168_mac_ocp_write(tp, 0xF8CE, 0x48C1);
+	r8168_mac_ocp_write(tp, 0xF8D0, 0xC502);
+	r8168_mac_ocp_write(tp, 0xF8D2, 0xBD00);
+	r8168_mac_ocp_write(tp, 0xF8D4, 0x00AA);
+	r8168_mac_ocp_write(tp, 0xF8D6, 0xE0C0);
+	r8168_mac_ocp_write(tp, 0xF8D8, 0xC502);
+	r8168_mac_ocp_write(tp, 0xF8DA, 0xBD00);
+	r8168_mac_ocp_write(tp, 0xF8DC, 0x0132);
+
+	r8168_mac_ocp_write(tp, 0xFC26, 0x8000);
+
+	r8168_mac_ocp_write(tp, 0xFC2A, 0x0743);
+	r8168_mac_ocp_write(tp, 0xFC2C, 0x0801);
+	r8168_mac_ocp_write(tp, 0xFC2E, 0x0BE9);
+	r8168_mac_ocp_write(tp, 0xFC30, 0x02FD);
+	r8168_mac_ocp_write(tp, 0xFC32, 0x0C25);
+	r8168_mac_ocp_write(tp, 0xFC34, 0x00A9);
+	r8168_mac_ocp_write(tp, 0xFC36, 0x012D);
+
 	rtl_hw_aspm_clkreq_enable(tp, true);
 }
 
-- 
2.20.1


From e894eba6fc040e702c7229b0cff9b297937afff3 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 2 Jul 2019 15:59:12 +0100
Subject: [PATCH 21/45] rxrpc: Fix send on a connected, but unbound socket

[ Upstream commit e835ada07091f40dcfb1bc735082bd0a7c005e59 ]

If sendmsg() or sendmmsg() is called on a connected socket that hasn't had
bind() called on it, then an oops will occur when the kernel tries to
connect the call because no local endpoint has been allocated.

Fix this by implicitly binding the socket if it is in the
RXRPC_CLIENT_UNBOUND state, just like it does for the RXRPC_UNBOUND state.

Further, the state should be transitioned to RXRPC_CLIENT_BOUND after this
to prevent further attempts to bind it.

This can be tested with:

	#include <stdio.h>
	#include <stdlib.h>
	#include <string.h>
	#include <sys/socket.h>
	#include <arpa/inet.h>
	#include <linux/rxrpc.h>
	static const unsigned char inet6_addr[16] = {
		0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -1, -1, 0xac, 0x14, 0x14, 0xaa
	};
	int main(void)
	{
		struct sockaddr_rxrpc srx;
		struct cmsghdr *cm;
		struct msghdr msg;
		unsigned char control[16];
		int fd;
		memset(&srx, 0, sizeof(srx));
		srx.srx_family = 0x21;
		srx.srx_service = 0;
		srx.transport_type = AF_INET;
		srx.transport_len = 0x1c;
		srx.transport.sin6.sin6_family = AF_INET6;
		srx.transport.sin6.sin6_port = htons(0x4e22);
		srx.transport.sin6.sin6_flowinfo = htons(0x4e22);
		srx.transport.sin6.sin6_scope_id = htons(0xaa3b);
		memcpy(&srx.transport.sin6.sin6_addr, inet6_addr, 16);
		cm = (struct cmsghdr *)control;
		cm->cmsg_len	= CMSG_LEN(sizeof(unsigned long));
		cm->cmsg_level	= SOL_RXRPC;
		cm->cmsg_type	= RXRPC_USER_CALL_ID;
		*(unsigned long *)CMSG_DATA(cm) = 0;
		msg.msg_name = NULL;
		msg.msg_namelen = 0;
		msg.msg_iov = NULL;
		msg.msg_iovlen = 0;
		msg.msg_control = control;
		msg.msg_controllen = cm->cmsg_len;
		msg.msg_flags = 0;
		fd = socket(AF_RXRPC, SOCK_DGRAM, AF_INET);
		connect(fd, (struct sockaddr *)&srx, sizeof(srx));
		sendmsg(fd, &msg, 0);
		return 0;
	}

Leading to the following oops:

	BUG: kernel NULL pointer dereference, address: 0000000000000018
	#PF: supervisor read access in kernel mode
	#PF: error_code(0x0000) - not-present page
	...
	RIP: 0010:rxrpc_connect_call+0x42/0xa01
	...
	Call Trace:
	 ? mark_held_locks+0x47/0x59
	 ? __local_bh_enable_ip+0xb6/0xba
	 rxrpc_new_client_call+0x3b1/0x762
	 ? rxrpc_do_sendmsg+0x3c0/0x92e
	 rxrpc_do_sendmsg+0x3c0/0x92e
	 rxrpc_sendmsg+0x16b/0x1b5
	 sock_sendmsg+0x2d/0x39
	 ___sys_sendmsg+0x1a4/0x22a
	 ? release_sock+0x19/0x9e
	 ? reacquire_held_locks+0x136/0x160
	 ? release_sock+0x19/0x9e
	 ? find_held_lock+0x2b/0x6e
	 ? __lock_acquire+0x268/0xf73
	 ? rxrpc_connect+0xdd/0xe4
	 ? __local_bh_enable_ip+0xb6/0xba
	 __sys_sendmsg+0x5e/0x94
	 do_syscall_64+0x7d/0x1bf
	 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Fixes: 2341e0775747 ("rxrpc: Simplify connect() implementation and simplify sendmsg() op")
Reported-by: syzbot+7966f2a0b2c7da8939b4@syzkaller.appspotmail.com
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Marc Dionne <marc.dionne@auristor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/af_rxrpc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index ae8c5d7f3bf1..c77476273179 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -521,6 +521,7 @@ static int rxrpc_sendmsg(struct socket *sock, struct msghdr *m, size_t len)
 
 	switch (rx->sk.sk_state) {
 	case RXRPC_UNBOUND:
+	case RXRPC_CLIENT_UNBOUND:
 		rx->srx.srx_family = AF_RXRPC;
 		rx->srx.srx_service = 0;
 		rx->srx.transport_type = SOCK_DGRAM;
@@ -545,10 +546,9 @@ static int rxrpc_sendmsg(struct socket *sock, struct msghdr *m, size_t len)
 		}
 
 		rx->local = local;
-		rx->sk.sk_state = RXRPC_CLIENT_UNBOUND;
+		rx->sk.sk_state = RXRPC_CLIENT_BOUND;
 		/* Fall through */
 
-	case RXRPC_CLIENT_UNBOUND:
 	case RXRPC_CLIENT_BOUND:
 		if (!m->msg_name &&
 		    test_bit(RXRPC_SOCK_CONNECTED, &rx->flags)) {
-- 
2.20.1


From 631353366e9c20a9d8734bc0e8bdfd63b10333b1 Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Thu, 27 Jun 2019 19:48:10 -0300
Subject: [PATCH 22/45] sctp: fix error handling on stream scheduler
 initialization

[ Upstream commit 4d1415811e492d9a8238f8a92dd0d51612c788e9 ]

It allocates the extended area for outbound streams only on sendmsg
calls, if they are not yet allocated.  When using the priority
stream scheduler, this initialization may imply into a subsequent
allocation, which may fail.  In this case, it was aborting the stream
scheduler initialization but leaving the ->ext pointer (allocated) in
there, thus in a partially initialized state.  On a subsequent call to
sendmsg, it would notice the ->ext pointer in there, and trip on
uninitialized stuff when trying to schedule the data chunk.

The fix is undo the ->ext initialization if the stream scheduler
initialization fails and avoid the partially initialized state.

Although syzkaller bisected this to commit 4ff40b86262b ("sctp: set
chunk transport correctly when it's a new asoc"), this bug was actually
introduced on the commit I marked below.

Reported-by: syzbot+c1a380d42b190ad1e559@syzkaller.appspotmail.com
Fixes: 5bbbbe32a431 ("sctp: introduce stream scheduler foundations")
Tested-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Neil Horman <nhorman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/stream.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index b6bb68adac6e..f72dfda4025d 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -168,13 +168,20 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt,
 int sctp_stream_init_ext(struct sctp_stream *stream, __u16 sid)
 {
 	struct sctp_stream_out_ext *soute;
+	int ret;
 
 	soute = kzalloc(sizeof(*soute), GFP_KERNEL);
 	if (!soute)
 		return -ENOMEM;
 	SCTP_SO(stream, sid)->ext = soute;
 
-	return sctp_sched_init_sid(stream, sid, GFP_KERNEL);
+	ret = sctp_sched_init_sid(stream, sid, GFP_KERNEL);
+	if (ret) {
+		kfree(SCTP_SO(stream, sid)->ext);
+		SCTP_SO(stream, sid)->ext = NULL;
+	}
+
+	return ret;
 }
 
 void sctp_stream_free(struct sctp_stream *stream)
-- 
2.20.1


From f385f1b020cf063196c8be5c2afe0eb8d54c5051 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 26 Jun 2019 16:31:39 +0800
Subject: [PATCH 23/45] sctp: not bind the socket in sctp_connect

[ Upstream commit 9b6c08878e23adb7cc84bdca94d8a944b03f099e ]

Now when sctp_connect() is called with a wrong sa_family, it binds
to a port but doesn't set bp->port, then sctp_get_af_specific will
return NULL and sctp_connect() returns -EINVAL.

Then if sctp_bind() is called to bind to another port, the last
port it has bound will leak due to bp->port is NULL by then.

sctp_connect() doesn't need to bind ports, as later __sctp_connect
will do it if bp->port is NULL. So remove it from sctp_connect().
While at it, remove the unnecessary sockaddr.sa_family len check
as it's already done in sctp_inet_connect.

Fixes: 644fbdeacf1d ("sctp: fix the issue that flags are ignored when using kernel_connect")
Reported-by: syzbot+079bf326b38072f849d9@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 24 +++---------------------
 1 file changed, 3 insertions(+), 21 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 4583fa914e62..e33382b3f82a 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4828,35 +4828,17 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname,
 static int sctp_connect(struct sock *sk, struct sockaddr *addr,
 			int addr_len, int flags)
 {
-	struct inet_sock *inet = inet_sk(sk);
 	struct sctp_af *af;
-	int err = 0;
+	int err = -EINVAL;
 
 	lock_sock(sk);
-
 	pr_debug("%s: sk:%p, sockaddr:%p, addr_len:%d\n", __func__, sk,
 		 addr, addr_len);
 
-	/* We may need to bind the socket. */
-	if (!inet->inet_num) {
-		if (sk->sk_prot->get_port(sk, 0)) {
-			release_sock(sk);
-			return -EAGAIN;
-		}
-		inet->inet_sport = htons(inet->inet_num);
-	}
-
 	/* Validate addr_len before calling common connect/connectx routine. */
-	af = addr_len < offsetofend(struct sockaddr, sa_family) ? NULL :
-		sctp_get_af_specific(addr->sa_family);
-	if (!af || addr_len < af->sockaddr_len) {
-		err = -EINVAL;
-	} else {
-		/* Pass correct addr len to common routine (so it knows there
-		 * is only one address being passed.
-		 */
+	af = sctp_get_af_specific(addr->sa_family);
+	if (af && addr_len >= af->sockaddr_len)
 		err = __sctp_connect(sk, addr, af->sockaddr_len, flags, NULL);
-	}
 
 	release_sock(sk);
 	return err;
-- 
2.20.1


From 26be49f6f89f4275e040f85c0b738e50785d45cb Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 23 Jul 2019 17:15:25 +0200
Subject: [PATCH 24/45] sky2: Disable MSI on ASUS P6T

[ Upstream commit a261e3797506bd561700be643fe1a85bf81e9661 ]

The onboard sky2 NIC on ASUS P6T WS PRO doesn't work after PM resume
due to the infamous IRQ problem.  Disabling MSI works around it, so
let's add it to the blacklist.

Unfortunately the BIOS on the machine doesn't fill the standard
DMI_SYS_* entry, so we pick up DMI_BOARD_* entries instead.

BugLink: https://bugzilla.suse.com/show_bug.cgi?id=1142496
Reported-and-tested-by: Marcus Seyfarth <m.seyfarth@gmail.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/sky2.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index 8b3495ee2b6e..d097530af78a 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -4933,6 +4933,13 @@ static const struct dmi_system_id msi_blacklist[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "P-79"),
 		},
 	},
+	{
+		.ident = "ASUS P6T",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."),
+			DMI_MATCH(DMI_BOARD_NAME, "P6T"),
+		},
+	},
 	{}
 };
 
-- 
2.20.1


From a94bc17880f4543f656f904fc242cf289ba5c4bd Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 19 Jul 2019 11:52:33 -0700
Subject: [PATCH 25/45] tcp: be more careful in tcp_fragment()

[ Upstream commit b617158dc096709d8600c53b6052144d12b89fab ]

Some applications set tiny SO_SNDBUF values and expect
TCP to just work. Recent patches to address CVE-2019-11478
broke them in case of losses, since retransmits might
be prevented.

We should allow these flows to make progress.

This patch allows the first and last skb in retransmit queue
to be split even if memory limits are hit.

It also adds the some room due to the fact that tcp_sendmsg()
and tcp_sendpage() might overshoot sk_wmem_queued by about one full
TSO skb (64KB size). Note this allowance was already present
in stable backports for kernels < 4.15

Note for < 4.15 backports :
 tcp_rtx_queue_tail() will probably look like :

static inline struct sk_buff *tcp_rtx_queue_tail(const struct sock *sk)
{
	struct sk_buff *skb = tcp_send_head(sk);

	return skb ? tcp_write_queue_prev(sk, skb) : tcp_write_queue_tail(sk);
}

Fixes: f070ef2ac667 ("tcp: tcp_fragment() should apply sane memory limits")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrew Prout <aprout@ll.mit.edu>
Tested-by: Andrew Prout <aprout@ll.mit.edu>
Tested-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Tested-by: Michal Kubecek <mkubecek@suse.cz>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Christoph Paasch <cpaasch@apple.com>
Cc: Jonathan Looney <jtl@netflix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h     |  5 +++++
 net/ipv4/tcp_output.c | 13 +++++++++++--
 2 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 36fcd0ad0515..21a90fd17853 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1679,6 +1679,11 @@ static inline struct sk_buff *tcp_rtx_queue_head(const struct sock *sk)
 	return skb_rb_first(&sk->tcp_rtx_queue);
 }
 
+static inline struct sk_buff *tcp_rtx_queue_tail(const struct sock *sk)
+{
+	return skb_rb_last(&sk->tcp_rtx_queue);
+}
+
 static inline struct sk_buff *tcp_write_queue_head(const struct sock *sk)
 {
 	return skb_peek(&sk->sk_write_queue);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index b8b4ae555e34..32bd52e06ef1 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1289,6 +1289,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *buff;
 	int nsize, old_factor;
+	long limit;
 	int nlen;
 	u8 flags;
 
@@ -1299,8 +1300,16 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
 	if (nsize < 0)
 		nsize = 0;
 
-	if (unlikely((sk->sk_wmem_queued >> 1) > sk->sk_sndbuf &&
-		     tcp_queue != TCP_FRAG_IN_WRITE_QUEUE)) {
+	/* tcp_sendmsg() can overshoot sk_wmem_queued by one full size skb.
+	 * We need some allowance to not penalize applications setting small
+	 * SO_SNDBUF values.
+	 * Also allow first and last skb in retransmit queue to be split.
+	 */
+	limit = sk->sk_sndbuf + 2 * SKB_TRUESIZE(GSO_MAX_SIZE);
+	if (unlikely((sk->sk_wmem_queued >> 1) > limit &&
+		     tcp_queue != TCP_FRAG_IN_WRITE_QUEUE &&
+		     skb != tcp_rtx_queue_head(sk) &&
+		     skb != tcp_rtx_queue_tail(sk))) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPWQUEUETOOBIG);
 		return -ENOMEM;
 	}
-- 
2.20.1


From ad3c43161e2b58f4ad403229f99a1e5da7e89887 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 18 Jul 2019 19:28:14 -0700
Subject: [PATCH 26/45] tcp: fix tcp_set_congestion_control() use from bpf hook

[ Upstream commit 8d650cdedaabb33e85e9b7c517c0c71fcecc1de9 ]

Neal reported incorrect use of ns_capable() from bpf hook.

bpf_setsockopt(...TCP_CONGESTION...)
  -> tcp_set_congestion_control()
   -> ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)
    -> ns_capable_common()
     -> current_cred()
      -> rcu_dereference_protected(current->cred, 1)

Accessing 'current' in bpf context makes no sense, since packets
are processed from softirq context.

As Neal stated : The capability check in tcp_set_congestion_control()
was written assuming a system call context, and then was reused from
a BPF call site.

The fix is to add a new parameter to tcp_set_congestion_control(),
so that the ns_capable() call is only performed under the right
context.

Fixes: 91b5b21c7c16 ("bpf: Add support for changing congestion control")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Lawrence Brakmo <brakmo@fb.com>
Reported-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Lawrence Brakmo <brakmo@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h   | 3 ++-
 net/core/filter.c   | 2 +-
 net/ipv4/tcp.c      | 4 +++-
 net/ipv4/tcp_cong.c | 6 +++---
 4 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 21a90fd17853..51f07f57ffa4 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1067,7 +1067,8 @@ void tcp_get_default_congestion_control(struct net *net, char *name);
 void tcp_get_available_congestion_control(char *buf, size_t len);
 void tcp_get_allowed_congestion_control(char *buf, size_t len);
 int tcp_set_allowed_congestion_control(char *allowed);
-int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, bool reinit);
+int tcp_set_congestion_control(struct sock *sk, const char *name, bool load,
+			       bool reinit, bool cap_net_admin);
 u32 tcp_slow_start(struct tcp_sock *tp, u32 acked);
 void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked);
 
diff --git a/net/core/filter.c b/net/core/filter.c
index b76f14197128..b8893566339f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4211,7 +4211,7 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 						    TCP_CA_NAME_MAX-1));
 			name[TCP_CA_NAME_MAX-1] = 0;
 			ret = tcp_set_congestion_control(sk, name, false,
-							 reinit);
+							 reinit, true);
 		} else {
 			struct tcp_sock *tp = tcp_sk(sk);
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 365c8490b34b..05fa7b7aee1e 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2784,7 +2784,9 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		name[val] = 0;
 
 		lock_sock(sk);
-		err = tcp_set_congestion_control(sk, name, true, true);
+		err = tcp_set_congestion_control(sk, name, true, true,
+						 ns_capable(sock_net(sk)->user_ns,
+							    CAP_NET_ADMIN));
 		release_sock(sk);
 		return err;
 	}
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index bc6c02f16243..48f79db446a0 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -332,7 +332,8 @@ int tcp_set_allowed_congestion_control(char *val)
  * tcp_reinit_congestion_control (if the current congestion control was
  * already initialized.
  */
-int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, bool reinit)
+int tcp_set_congestion_control(struct sock *sk, const char *name, bool load,
+			       bool reinit, bool cap_net_admin)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	const struct tcp_congestion_ops *ca;
@@ -368,8 +369,7 @@ int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, boo
 		} else {
 			err = -EBUSY;
 		}
-	} else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) ||
-		     ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))) {
+	} else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || cap_net_admin)) {
 		err = -EPERM;
 	} else if (!try_module_get(ca->owner)) {
 		err = -EBUSY;
-- 
2.20.1


From f322a63599513aec1adf0f39b39d70b64d7f737b Mon Sep 17 00:00:00 2001
From: Christoph Paasch <cpaasch@apple.com>
Date: Sat, 6 Jul 2019 16:13:07 -0700
Subject: [PATCH 27/45] tcp: Reset bytes_acked and bytes_received when
 disconnecting

[ Upstream commit e858faf556d4e14c750ba1e8852783c6f9520a0e ]

If an app is playing tricks to reuse a socket via tcp_disconnect(),
bytes_acked/received needs to be reset to 0. Otherwise tcp_info will
report the sum of the current and the old connection..

Cc: Eric Dumazet <edumazet@google.com>
Fixes: 0df48c26d841 ("tcp: add tcpi_bytes_acked to tcp_info")
Fixes: bdd1f9edacb5 ("tcp: add tcpi_bytes_received to tcp_info")
Signed-off-by: Christoph Paasch <cpaasch@apple.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 05fa7b7aee1e..caac580e1f1d 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2630,6 +2630,8 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tcp_saved_syn_free(tp);
 	tp->compressed_ack = 0;
 	tp->bytes_sent = 0;
+	tp->bytes_acked = 0;
+	tp->bytes_received = 0;
 	tp->bytes_retrans = 0;
 	tp->duplicate_sack[0].start_seq = 0;
 	tp->duplicate_sack[0].end_seq = 0;
-- 
2.20.1


From 18244f0dc4611c16e3a5c99ec932a17418a48f99 Mon Sep 17 00:00:00 2001
From: Peter Kosyh <p.kosyh@gmail.com>
Date: Fri, 19 Jul 2019 11:11:47 +0300
Subject: [PATCH 28/45] vrf: make sure skb->data contains ip header to make
 routing

[ Upstream commit 107e47cc80ec37cb332bd41b22b1c7779e22e018 ]

vrf_process_v4_outbound() and vrf_process_v6_outbound() do routing
using ip/ipv6 addresses, but don't make sure the header is available
in skb->data[] (skb_headlen() is less then header size).

Case:

1) igb driver from intel.
2) Packet size is greater then 255.
3) MPLS forwards to VRF device.

So, patch adds pskb_may_pull() calls in vrf_process_v4/v6_outbound()
functions.

Signed-off-by: Peter Kosyh <p.kosyh@gmail.com>
Reviewed-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 58 ++++++++++++++++++++++++++++-------------------
 1 file changed, 35 insertions(+), 23 deletions(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 9ee4d7402ca2..b4ac87aa09fd 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -169,23 +169,29 @@ static int vrf_ip6_local_out(struct net *net, struct sock *sk,
 static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
 					   struct net_device *dev)
 {
-	const struct ipv6hdr *iph = ipv6_hdr(skb);
+	const struct ipv6hdr *iph;
 	struct net *net = dev_net(skb->dev);
-	struct flowi6 fl6 = {
-		/* needed to match OIF rule */
-		.flowi6_oif = dev->ifindex,
-		.flowi6_iif = LOOPBACK_IFINDEX,
-		.daddr = iph->daddr,
-		.saddr = iph->saddr,
-		.flowlabel = ip6_flowinfo(iph),
-		.flowi6_mark = skb->mark,
-		.flowi6_proto = iph->nexthdr,
-		.flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF,
-	};
+	struct flowi6 fl6;
 	int ret = NET_XMIT_DROP;
 	struct dst_entry *dst;
 	struct dst_entry *dst_null = &net->ipv6.ip6_null_entry->dst;
 
+	if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct ipv6hdr)))
+		goto err;
+
+	iph = ipv6_hdr(skb);
+
+	memset(&fl6, 0, sizeof(fl6));
+	/* needed to match OIF rule */
+	fl6.flowi6_oif = dev->ifindex;
+	fl6.flowi6_iif = LOOPBACK_IFINDEX;
+	fl6.daddr = iph->daddr;
+	fl6.saddr = iph->saddr;
+	fl6.flowlabel = ip6_flowinfo(iph);
+	fl6.flowi6_mark = skb->mark;
+	fl6.flowi6_proto = iph->nexthdr;
+	fl6.flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF;
+
 	dst = ip6_route_output(net, NULL, &fl6);
 	if (dst == dst_null)
 		goto err;
@@ -241,21 +247,27 @@ static int vrf_ip_local_out(struct net *net, struct sock *sk,
 static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb,
 					   struct net_device *vrf_dev)
 {
-	struct iphdr *ip4h = ip_hdr(skb);
+	struct iphdr *ip4h;
 	int ret = NET_XMIT_DROP;
-	struct flowi4 fl4 = {
-		/* needed to match OIF rule */
-		.flowi4_oif = vrf_dev->ifindex,
-		.flowi4_iif = LOOPBACK_IFINDEX,
-		.flowi4_tos = RT_TOS(ip4h->tos),
-		.flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_SKIP_NH_OIF,
-		.flowi4_proto = ip4h->protocol,
-		.daddr = ip4h->daddr,
-		.saddr = ip4h->saddr,
-	};
+	struct flowi4 fl4;
 	struct net *net = dev_net(vrf_dev);
 	struct rtable *rt;
 
+	if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct iphdr)))
+		goto err;
+
+	ip4h = ip_hdr(skb);
+
+	memset(&fl4, 0, sizeof(fl4));
+	/* needed to match OIF rule */
+	fl4.flowi4_oif = vrf_dev->ifindex;
+	fl4.flowi4_iif = LOOPBACK_IFINDEX;
+	fl4.flowi4_tos = RT_TOS(ip4h->tos);
+	fl4.flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_SKIP_NH_OIF;
+	fl4.flowi4_proto = ip4h->protocol;
+	fl4.daddr = ip4h->daddr;
+	fl4.saddr = ip4h->saddr;
+
 	rt = ip_route_output_flow(net, &fl4, NULL);
 	if (IS_ERR(rt))
 		goto err;
-- 
2.20.1


From 862a2421cafa975a63b378457933106acde021a0 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Fri, 28 Jun 2019 14:07:25 +0900
Subject: [PATCH 29/45] vxlan: do not destroy fdb if register_netdevice() is
 failed

[ Upstream commit 7c31e54aeee517d1318dfc0bde9fa7de75893dc6 ]

__vxlan_dev_create() destroys FDB using specific pointer which indicates
a fdb when error occurs.
But that pointer should not be used when register_netdevice() fails because
register_netdevice() internally destroys fdb when error occurs.

This patch makes vxlan_fdb_create() to do not link fdb entry to vxlan dev
internally.
Instead, a new function vxlan_fdb_insert() is added to link fdb to vxlan
dev.

vxlan_fdb_insert() is called after calling register_netdevice().
This routine can avoid situation that ->ndo_uninit() destroys fdb entry
in error path of register_netdevice().
Hence, error path of __vxlan_dev_create() routine can have an opportunity
to destroy default fdb entry by hand.

Test command
    ip link add bonding_masters type vxlan id 0 group 239.1.1.1 \
	    dev enp0s9 dstport 4789

Splat looks like:
[  213.392816] kasan: GPF could be caused by NULL-ptr deref or user memory access
[  213.401257] general protection fault: 0000 [#1] SMP DEBUG_PAGEALLOC KASAN PTI
[  213.402178] CPU: 0 PID: 1414 Comm: ip Not tainted 5.2.0-rc5+ #256
[  213.402178] RIP: 0010:vxlan_fdb_destroy+0x120/0x220 [vxlan]
[  213.402178] Code: df 48 8b 2b 48 89 fa 48 c1 ea 03 80 3c 02 00 0f 85 06 01 00 00 4c 8b 63 08 48 b8 00 00 00 00 00 fc d
[  213.402178] RSP: 0018:ffff88810cb9f0a0 EFLAGS: 00010202
[  213.402178] RAX: dffffc0000000000 RBX: ffff888101d4a8c8 RCX: 0000000000000000
[  213.402178] RDX: 1bd5a00000000040 RSI: ffff888101d4a8c8 RDI: ffff888101d4a8d0
[  213.402178] RBP: 0000000000000000 R08: fffffbfff22b72d9 R09: 0000000000000000
[  213.402178] R10: 00000000ffffffef R11: 0000000000000000 R12: dead000000000200
[  213.402178] R13: ffff88810cb9f1f8 R14: ffff88810efccda0 R15: ffff88810efccda0
[  213.402178] FS:  00007f7f6621a0c0(0000) GS:ffff88811b000000(0000) knlGS:0000000000000000
[  213.402178] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  213.402178] CR2: 000055746f0807d0 CR3: 00000001123e0000 CR4: 00000000001006f0
[  213.402178] Call Trace:
[  213.402178]  __vxlan_dev_create+0x3a9/0x7d0 [vxlan]
[  213.402178]  ? vxlan_changelink+0x740/0x740 [vxlan]
[  213.402178]  ? rcu_read_unlock+0x60/0x60 [vxlan]
[  213.402178]  ? __kasan_kmalloc.constprop.3+0xa0/0xd0
[  213.402178]  vxlan_newlink+0x8d/0xc0 [vxlan]
[  213.402178]  ? __vxlan_dev_create+0x7d0/0x7d0 [vxlan]
[  213.554119]  ? __netlink_ns_capable+0xc3/0xf0
[  213.554119]  __rtnl_newlink+0xb75/0x1180
[  213.554119]  ? rtnl_link_unregister+0x230/0x230
[ ... ]

Fixes: 0241b836732f ("vxlan: fix default fdb entry netlink notify ordering during netdev create")
Suggested-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Acked-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 37 +++++++++++++++++++++++++++----------
 1 file changed, 27 insertions(+), 10 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 38ecb66fb3e9..82c25f07261f 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -806,6 +806,14 @@ static struct vxlan_fdb *vxlan_fdb_alloc(struct vxlan_dev *vxlan,
 	return f;
 }
 
+static void vxlan_fdb_insert(struct vxlan_dev *vxlan, const u8 *mac,
+			     __be32 src_vni, struct vxlan_fdb *f)
+{
+	++vxlan->addrcnt;
+	hlist_add_head_rcu(&f->hlist,
+			   vxlan_fdb_head(vxlan, mac, src_vni));
+}
+
 static int vxlan_fdb_create(struct vxlan_dev *vxlan,
 			    const u8 *mac, union vxlan_addr *ip,
 			    __u16 state, __be16 port, __be32 src_vni,
@@ -831,18 +839,13 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan,
 		return rc;
 	}
 
-	++vxlan->addrcnt;
-	hlist_add_head_rcu(&f->hlist,
-			   vxlan_fdb_head(vxlan, mac, src_vni));
-
 	*fdb = f;
 
 	return 0;
 }
 
-static void vxlan_fdb_free(struct rcu_head *head)
+static void __vxlan_fdb_free(struct vxlan_fdb *f)
 {
-	struct vxlan_fdb *f = container_of(head, struct vxlan_fdb, rcu);
 	struct vxlan_rdst *rd, *nd;
 
 	list_for_each_entry_safe(rd, nd, &f->remotes, list) {
@@ -852,6 +855,13 @@ static void vxlan_fdb_free(struct rcu_head *head)
 	kfree(f);
 }
 
+static void vxlan_fdb_free(struct rcu_head *head)
+{
+	struct vxlan_fdb *f = container_of(head, struct vxlan_fdb, rcu);
+
+	__vxlan_fdb_free(f);
+}
+
 static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f,
 			      bool do_notify, bool swdev_notify)
 {
@@ -979,6 +989,7 @@ static int vxlan_fdb_update_create(struct vxlan_dev *vxlan,
 	if (rc < 0)
 		return rc;
 
+	vxlan_fdb_insert(vxlan, mac, src_vni, f);
 	rc = vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH,
 			      swdev_notify, extack);
 	if (rc)
@@ -3573,12 +3584,17 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev,
 	if (err)
 		goto errout;
 
-	/* notify default fdb entry */
 	if (f) {
+		vxlan_fdb_insert(vxlan, all_zeros_mac,
+				 vxlan->default_dst.remote_vni, f);
+
+		/* notify default fdb entry */
 		err = vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f),
 				       RTM_NEWNEIGH, true, extack);
-		if (err)
-			goto errout;
+		if (err) {
+			vxlan_fdb_destroy(vxlan, f, false, false);
+			goto unregister;
+		}
 	}
 
 	list_add(&vxlan->next, &vn->vxlan_list);
@@ -3590,7 +3606,8 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev,
 	 * destroy the entry by hand here.
 	 */
 	if (f)
-		vxlan_fdb_destroy(vxlan, f, false, false);
+		__vxlan_fdb_free(f);
+unregister:
 	if (unregister)
 		unregister_netdevice(dev);
 	return err;
-- 
2.20.1


From f47ba281cad8b7f2247992004ff87c23a66fc250 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Sun, 7 Jul 2019 16:57:06 +0300
Subject: [PATCH 30/45] net/mlx5e: IPoIB, Add error path in mlx5_rdma_setup_rn

[ Upstream commit ef1ce7d7b67b46661091c7ccc0396186b7a247ef ]

Check return value from mlx5e_attach_netdev, add error path on failure.

Fixes: 48935bbb7ae8 ("net/mlx5e: IPoIB, Add netdevice profile skeleton")
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Feras Daoud <ferasda@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 4eac42555c7d..5d0783e55f42 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -698,7 +698,9 @@ static int mlx5_rdma_setup_rn(struct ib_device *ibdev, u8 port_num,
 
 	prof->init(mdev, netdev, prof, ipriv);
 
-	mlx5e_attach_netdev(epriv);
+	err = mlx5e_attach_netdev(epriv);
+	if (err)
+		goto detach;
 	netif_carrier_off(netdev);
 
 	/* set rdma_netdev func pointers */
@@ -714,6 +716,11 @@ static int mlx5_rdma_setup_rn(struct ib_device *ibdev, u8 port_num,
 
 	return 0;
 
+detach:
+	prof->cleanup(epriv);
+	if (ipriv->sub_interface)
+		return err;
+	mlx5e_destroy_mdev_resources(mdev);
 destroy_ht:
 	mlx5i_pkey_qpn_ht_cleanup(netdev);
 	return err;
-- 
2.20.1


From 6a1953100038678980133e700f2c716c1ed72c77 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Tue, 2 Jul 2019 15:00:18 +0300
Subject: [PATCH 31/45] net: bridge: mcast: fix stale nsrcs pointer in
 igmp3/mld2 report handling

[ Upstream commit e57f61858b7cf478ed6fa23ed4b3876b1c9625c4 ]

We take a pointer to grec prior to calling pskb_may_pull and use it
afterwards to get nsrcs so record nsrcs before the pull when handling
igmp3 and we get a pointer to nsrcs and call pskb_may_pull when handling
mld2 which again could lead to reading 2 bytes out-of-bounds.

 ==================================================================
 BUG: KASAN: use-after-free in br_multicast_rcv+0x480c/0x4ad0 [bridge]
 Read of size 2 at addr ffff8880421302b4 by task ksoftirqd/1/16

 CPU: 1 PID: 16 Comm: ksoftirqd/1 Tainted: G           OE     5.2.0-rc6+ #1
 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014
 Call Trace:
  dump_stack+0x71/0xab
  print_address_description+0x6a/0x280
  ? br_multicast_rcv+0x480c/0x4ad0 [bridge]
  __kasan_report+0x152/0x1aa
  ? br_multicast_rcv+0x480c/0x4ad0 [bridge]
  ? br_multicast_rcv+0x480c/0x4ad0 [bridge]
  kasan_report+0xe/0x20
  br_multicast_rcv+0x480c/0x4ad0 [bridge]
  ? br_multicast_disable_port+0x150/0x150 [bridge]
  ? ktime_get_with_offset+0xb4/0x150
  ? __kasan_kmalloc.constprop.6+0xa6/0xf0
  ? __netif_receive_skb+0x1b0/0x1b0
  ? br_fdb_update+0x10e/0x6e0 [bridge]
  ? br_handle_frame_finish+0x3c6/0x11d0 [bridge]
  br_handle_frame_finish+0x3c6/0x11d0 [bridge]
  ? br_pass_frame_up+0x3a0/0x3a0 [bridge]
  ? virtnet_probe+0x1c80/0x1c80 [virtio_net]
  br_handle_frame+0x731/0xd90 [bridge]
  ? select_idle_sibling+0x25/0x7d0
  ? br_handle_frame_finish+0x11d0/0x11d0 [bridge]
  __netif_receive_skb_core+0xced/0x2d70
  ? virtqueue_get_buf_ctx+0x230/0x1130 [virtio_ring]
  ? do_xdp_generic+0x20/0x20
  ? virtqueue_napi_complete+0x39/0x70 [virtio_net]
  ? virtnet_poll+0x94d/0xc78 [virtio_net]
  ? receive_buf+0x5120/0x5120 [virtio_net]
  ? __netif_receive_skb_one_core+0x97/0x1d0
  __netif_receive_skb_one_core+0x97/0x1d0
  ? __netif_receive_skb_core+0x2d70/0x2d70
  ? _raw_write_trylock+0x100/0x100
  ? __queue_work+0x41e/0xbe0
  process_backlog+0x19c/0x650
  ? _raw_read_lock_irq+0x40/0x40
  net_rx_action+0x71e/0xbc0
  ? __switch_to_asm+0x40/0x70
  ? napi_complete_done+0x360/0x360
  ? __switch_to_asm+0x34/0x70
  ? __switch_to_asm+0x40/0x70
  ? __schedule+0x85e/0x14d0
  __do_softirq+0x1db/0x5f9
  ? takeover_tasklets+0x5f0/0x5f0
  run_ksoftirqd+0x26/0x40
  smpboot_thread_fn+0x443/0x680
  ? sort_range+0x20/0x20
  ? schedule+0x94/0x210
  ? __kthread_parkme+0x78/0xf0
  ? sort_range+0x20/0x20
  kthread+0x2ae/0x3a0
  ? kthread_create_worker_on_cpu+0xc0/0xc0
  ret_from_fork+0x35/0x40

 The buggy address belongs to the page:
 page:ffffea0001084c00 refcount:0 mapcount:-128 mapping:0000000000000000 index:0x0
 flags: 0xffffc000000000()
 raw: 00ffffc000000000 ffffea0000cfca08 ffffea0001098608 0000000000000000
 raw: 0000000000000000 0000000000000003 00000000ffffff7f 0000000000000000
 page dumped because: kasan: bad access detected

 Memory state around the buggy address:
 ffff888042130180: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
 ffff888042130200: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
 > ffff888042130280: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
                                     ^
 ffff888042130300: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
 ffff888042130380: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
 ==================================================================
 Disabling lock debugging due to kernel taint

Fixes: bc8c20acaea1 ("bridge: multicast: treat igmpv3 report with INCLUDE and no sources as a leave")
Reported-by: Martin Weinelt <martin@linuxlounge.net>
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Tested-by: Martin Weinelt <martin@linuxlounge.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 45e7f4173bba..805d8e52d20b 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -934,6 +934,7 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br,
 	int type;
 	int err = 0;
 	__be32 group;
+	u16 nsrcs;
 
 	ih = igmpv3_report_hdr(skb);
 	num = ntohs(ih->ngrec);
@@ -947,8 +948,9 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br,
 		grec = (void *)(skb->data + len - sizeof(*grec));
 		group = grec->grec_mca;
 		type = grec->grec_type;
+		nsrcs = ntohs(grec->grec_nsrcs);
 
-		len += ntohs(grec->grec_nsrcs) * 4;
+		len += nsrcs * 4;
 		if (!ip_mc_may_pull(skb, len))
 			return -EINVAL;
 
@@ -969,7 +971,7 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br,
 		src = eth_hdr(skb)->h_source;
 		if ((type == IGMPV3_CHANGE_TO_INCLUDE ||
 		     type == IGMPV3_MODE_IS_INCLUDE) &&
-		    ntohs(grec->grec_nsrcs) == 0) {
+		    nsrcs == 0) {
 			br_ip4_multicast_leave_group(br, port, group, vid, src);
 		} else {
 			err = br_ip4_multicast_add_group(br, port, group, vid,
@@ -1006,7 +1008,8 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br,
 	len = skb_transport_offset(skb) + sizeof(*icmp6h);
 
 	for (i = 0; i < num; i++) {
-		__be16 *nsrcs, _nsrcs;
+		__be16 *_nsrcs, __nsrcs;
+		u16 nsrcs;
 
 		nsrcs_offset = len + offsetof(struct mld2_grec, grec_nsrcs);
 
@@ -1014,12 +1017,13 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br,
 		    nsrcs_offset + sizeof(_nsrcs))
 			return -EINVAL;
 
-		nsrcs = skb_header_pointer(skb, nsrcs_offset,
-					   sizeof(_nsrcs), &_nsrcs);
-		if (!nsrcs)
+		_nsrcs = skb_header_pointer(skb, nsrcs_offset,
+					    sizeof(__nsrcs), &__nsrcs);
+		if (!_nsrcs)
 			return -EINVAL;
 
-		grec_len = struct_size(grec, grec_src, ntohs(*nsrcs));
+		nsrcs = ntohs(*_nsrcs);
+		grec_len = struct_size(grec, grec_src, nsrcs);
 
 		if (!ipv6_mc_may_pull(skb, len + grec_len))
 			return -EINVAL;
@@ -1044,7 +1048,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br,
 		src = eth_hdr(skb)->h_source;
 		if ((grec->grec_type == MLD2_CHANGE_TO_INCLUDE ||
 		     grec->grec_type == MLD2_MODE_IS_INCLUDE) &&
-		    ntohs(*nsrcs) == 0) {
+		    nsrcs == 0) {
 			br_ip6_multicast_leave_group(br, port, &grec->grec_mca,
 						     vid, src);
 		} else {
-- 
2.20.1


From 8c8d2907299ef7654e99c759ffa08904dc5ddd4e Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Tue, 2 Jul 2019 15:00:19 +0300
Subject: [PATCH 32/45] net: bridge: mcast: fix stale ipv6 hdr pointer when
 handling v6 query

[ Upstream commit 3b26a5d03d35d8f732d75951218983c0f7f68dff ]

We get a pointer to the ipv6 hdr in br_ip6_multicast_query but we may
call pskb_may_pull afterwards and end up using a stale pointer.
So use the header directly, it's just 1 place where it's needed.

Fixes: 08b202b67264 ("bridge br_multicast: IPv6 MLD support.")
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Tested-by: Martin Weinelt <martin@linuxlounge.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 805d8e52d20b..0ef4092202d0 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1302,7 +1302,6 @@ static int br_ip6_multicast_query(struct net_bridge *br,
 				  u16 vid)
 {
 	unsigned int transport_len = ipv6_transport_len(skb);
-	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
 	struct mld_msg *mld;
 	struct net_bridge_mdb_entry *mp;
 	struct mld2_query *mld2q;
@@ -1346,7 +1345,7 @@ static int br_ip6_multicast_query(struct net_bridge *br,
 
 	if (is_general_query) {
 		saddr.proto = htons(ETH_P_IPV6);
-		saddr.u.ip6 = ip6h->saddr;
+		saddr.u.ip6 = ipv6_hdr(skb)->saddr;
 
 		br_multicast_query_received(br, port, &br->ip6_other_query,
 					    &saddr, max_delay);
-- 
2.20.1


From 7d67fe7107d91e0baae2782dc5e0def9f5ea76ff Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Tue, 2 Jul 2019 15:00:20 +0300
Subject: [PATCH 33/45] net: bridge: don't cache ether dest pointer on input

[ Upstream commit 3d26eb8ad1e9b906433903ce05f775cf038e747f ]

We would cache ether dst pointer on input in br_handle_frame_finish but
after the neigh suppress code that could lead to a stale pointer since
both ipv4 and ipv6 suppress code do pskb_may_pull. This means we have to
always reload it after the suppress code so there's no point in having
it cached just retrieve it directly.

Fixes: 057658cb33fbf ("bridge: suppress arp pkts on BR_NEIGH_SUPPRESS ports")
Fixes: ed842faeb2bd ("bridge: suppress nd pkts on BR_NEIGH_SUPPRESS ports")
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_input.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index ba303ee99b9b..6a9f48322bb9 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -79,7 +79,6 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
 	struct net_bridge_fdb_entry *dst = NULL;
 	struct net_bridge_mdb_entry *mdst;
 	bool local_rcv, mcast_hit = false;
-	const unsigned char *dest;
 	struct net_bridge *br;
 	u16 vid = 0;
 
@@ -97,10 +96,9 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
 		br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, false);
 
 	local_rcv = !!(br->dev->flags & IFF_PROMISC);
-	dest = eth_hdr(skb)->h_dest;
-	if (is_multicast_ether_addr(dest)) {
+	if (is_multicast_ether_addr(eth_hdr(skb)->h_dest)) {
 		/* by definition the broadcast is also a multicast address */
-		if (is_broadcast_ether_addr(dest)) {
+		if (is_broadcast_ether_addr(eth_hdr(skb)->h_dest)) {
 			pkt_type = BR_PKT_BROADCAST;
 			local_rcv = true;
 		} else {
@@ -150,7 +148,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
 		}
 		break;
 	case BR_PKT_UNICAST:
-		dst = br_fdb_find_rcu(br, dest, vid);
+		dst = br_fdb_find_rcu(br, eth_hdr(skb)->h_dest, vid);
 	default:
 		break;
 	}
-- 
2.20.1


From 8d37ee0b948214c0a2c51ff7d78ef04d48ac1cad Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Tue, 2 Jul 2019 15:00:21 +0300
Subject: [PATCH 34/45] net: bridge: stp: don't cache eth dest pointer before
 skb pull

[ Upstream commit 2446a68ae6a8cee6d480e2f5b52f5007c7c41312 ]

Don't cache eth dest pointer before calling pskb_may_pull.

Fixes: cf0f02d04a83 ("[BRIDGE]: use llc for receiving STP packets")
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_stp_bpdu.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/bridge/br_stp_bpdu.c b/net/bridge/br_stp_bpdu.c
index 1b75d6bf12bd..37ddcea3fc96 100644
--- a/net/bridge/br_stp_bpdu.c
+++ b/net/bridge/br_stp_bpdu.c
@@ -147,7 +147,6 @@ void br_send_tcn_bpdu(struct net_bridge_port *p)
 void br_stp_rcv(const struct stp_proto *proto, struct sk_buff *skb,
 		struct net_device *dev)
 {
-	const unsigned char *dest = eth_hdr(skb)->h_dest;
 	struct net_bridge_port *p;
 	struct net_bridge *br;
 	const unsigned char *buf;
@@ -176,7 +175,7 @@ void br_stp_rcv(const struct stp_proto *proto, struct sk_buff *skb,
 	if (p->state == BR_STATE_DISABLED)
 		goto out;
 
-	if (!ether_addr_equal(dest, br->group_addr))
+	if (!ether_addr_equal(eth_hdr(skb)->h_dest, br->group_addr))
 		goto out;
 
 	if (p->flags & BR_BPDU_GUARD) {
-- 
2.20.1


From 826e714c25e11cf2622af4431b1611a8fffda777 Mon Sep 17 00:00:00 2001
From: Andreas Steinmetz <ast@domdv.de>
Date: Sun, 30 Jun 2019 22:46:42 +0200
Subject: [PATCH 35/45] macsec: fix use-after-free of skb during RX

[ Upstream commit 095c02da80a41cf6d311c504d8955d6d1c2add10 ]

Fix use-after-free of skb when rx_handler returns RX_HANDLER_PASS.

Signed-off-by: Andreas Steinmetz <ast@domdv.de>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macsec.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 64a982563d59..df86bcb7bc2e 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -1103,10 +1103,9 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb)
 	}
 
 	skb = skb_unshare(skb, GFP_ATOMIC);
-	if (!skb) {
-		*pskb = NULL;
+	*pskb = skb;
+	if (!skb)
 		return RX_HANDLER_CONSUMED;
-	}
 
 	pulled_sci = pskb_may_pull(skb, macsec_extra_len(true));
 	if (!pulled_sci) {
-- 
2.20.1


From 16008c280e5a78948a661ac4f701d0d1594250c4 Mon Sep 17 00:00:00 2001
From: Andreas Steinmetz <ast@domdv.de>
Date: Sun, 30 Jun 2019 22:46:45 +0200
Subject: [PATCH 36/45] macsec: fix checksumming after decryption

[ Upstream commit 7d8b16b9facb0dd81d1469808dd9a575fa1d525a ]

Fix checksumming after decryption.

Signed-off-by: Andreas Steinmetz <ast@domdv.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macsec.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index df86bcb7bc2e..bb65eaccbfad 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -869,6 +869,7 @@ static void macsec_reset_skb(struct sk_buff *skb, struct net_device *dev)
 
 static void macsec_finalize_skb(struct sk_buff *skb, u8 icv_len, u8 hdr_len)
 {
+	skb->ip_summed = CHECKSUM_NONE;
 	memmove(skb->data + hdr_len, skb->data, 2 * ETH_ALEN);
 	skb_pull(skb, hdr_len);
 	pskb_trim_unique(skb, skb->len - icv_len);
-- 
2.20.1


From ea07b7a952c44f261d0919b4554c861cd2dcc183 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 27 Jun 2019 14:30:58 -0700
Subject: [PATCH 37/45] netrom: fix a memory leak in nr_rx_frame()

[ Upstream commit c8c8218ec5af5d2598381883acbefbf604e56b5e ]

When the skb is associated with a new sock, just assigning
it to skb->sk is not sufficient, we have to set its destructor
to free the sock properly too.

Reported-by: syzbot+d6636a36d3c34bd88938@syzkaller.appspotmail.com
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netrom/af_netrom.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 71ffd1a6dc7c..f11b6747e18c 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -872,7 +872,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev)
 	unsigned short frametype, flags, window, timeout;
 	int ret;
 
-	skb->sk = NULL;		/* Initially we don't know who it's for */
+	skb_orphan(skb);
 
 	/*
 	 *	skb->data points to the netrom frame start
@@ -971,6 +971,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev)
 	window = skb->data[20];
 
 	skb->sk             = make;
+	skb->destructor     = sock_efree;
 	make->sk_state	    = TCP_ESTABLISHED;
 
 	/* Fill in his circuit details */
-- 
2.20.1


From 232c647a1dcea91b76407592db1ce839c6faf765 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 22 Jul 2019 20:41:22 -0700
Subject: [PATCH 38/45] netrom: hold sock when setting skb->destructor

[ Upstream commit 4638faac032756f7eab5524be7be56bee77e426b ]

sock_efree() releases the sock refcnt, if we don't hold this refcnt
when setting skb->destructor to it, the refcnt would not be balanced.
This leads to several bug reports from syzbot.

I have checked other users of sock_efree(), all of them hold the
sock refcnt.

Fixes: c8c8218ec5af ("netrom: fix a memory leak in nr_rx_frame()")
Reported-and-tested-by: <syzbot+622bdabb128acc33427d@syzkaller.appspotmail.com>
Reported-and-tested-by: <syzbot+6eaef7158b19e3fec3a0@syzkaller.appspotmail.com>
Reported-and-tested-by: <syzbot+9399c158fcc09b21d0d2@syzkaller.appspotmail.com>
Reported-and-tested-by: <syzbot+a34e5f3d0300163f0c87@syzkaller.appspotmail.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netrom/af_netrom.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index f11b6747e18c..43910e50752c 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -970,6 +970,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev)
 
 	window = skb->data[20];
 
+	sock_hold(make);
 	skb->sk             = make;
 	skb->destructor     = sock_efree;
 	make->sk_state	    = TCP_ESTABLISHED;
-- 
2.20.1


From 79a8fe84c62840ad3207ae883fac08a3cca7a6d2 Mon Sep 17 00:00:00 2001
From: Frank de Brabander <debrabander@gmail.com>
Date: Fri, 5 Jul 2019 13:43:14 +0200
Subject: [PATCH 39/45] selftests: txring_overwrite: fix incorrect test of
 mmap() return value

[ Upstream commit cecaa76b2919aac2aa584ce476e9fcd5b084add5 ]

If mmap() fails it returns MAP_FAILED, which is defined as ((void *) -1).
The current if-statement incorrectly tests if *ring is NULL.

Fixes: 358be656406d ("selftests/net: add txring_overwrite")
Signed-off-by: Frank de Brabander <debrabander@gmail.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/txring_overwrite.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/txring_overwrite.c b/tools/testing/selftests/net/txring_overwrite.c
index fd8b1c663c39..7d9ea039450a 100644
--- a/tools/testing/selftests/net/txring_overwrite.c
+++ b/tools/testing/selftests/net/txring_overwrite.c
@@ -113,7 +113,7 @@ static int setup_tx(char **ring)
 
 	*ring = mmap(0, req.tp_block_size * req.tp_block_nr,
 		     PROT_READ | PROT_WRITE, MAP_SHARED, fdt, 0);
-	if (!*ring)
+	if (*ring == MAP_FAILED)
 		error(1, errno, "mmap");
 
 	return fdt;
-- 
2.20.1


From cbef9b5641d6b7aedc5bbeb4104bcec3ac797d67 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu, 4 Jul 2019 14:50:36 -0700
Subject: [PATCH 40/45] net/tls: fix poll ignoring partially copied records

[ Upstream commit 13aecb17acabc2a92187d08f7ca93bb8aad62c6f ]

David reports that RPC applications which use epoll() occasionally
get stuck, and that TLS ULP causes the kernel to not wake applications,
even though read() will return data.

This is indeed true. The ctx->rx_list which holds partially copied
records is not consulted when deciding whether socket is readable.

Note that SO_RCVLOWAT with epoll() is and has always been broken for
kernel TLS. We'd need to parse all records from the TCP layer, instead
of just the first one.

Fixes: 692d7b5d1f91 ("tls: Fix recvmsg() to be able to peek across multiple records")
Reported-by: David Beckett <david.beckett@netronome.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 41e17ed0c94e..fd931294f66f 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1931,7 +1931,8 @@ bool tls_sw_stream_read(const struct sock *sk)
 		ingress_empty = list_empty(&psock->ingress_msg);
 	rcu_read_unlock();
 
-	return !ingress_empty || ctx->recv_pkt;
+	return !ingress_empty || ctx->recv_pkt ||
+		!skb_queue_empty(&ctx->rx_list);
 }
 
 static int tls_read_size(struct strparser *strp, struct sk_buff *skb)
-- 
2.20.1


From 7805dbff24d006c54fff2cf9303fdf5fbdb5c0c6 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 28 Jun 2019 16:07:59 -0700
Subject: [PATCH 41/45] net/tls: reject offload of TLS 1.3

[ Upstream commit 618bac45937a3dc6126ac0652747481e97000f99 ]

Neither drivers nor the tls offload code currently supports TLS
version 1.3. Check the TLS version when installing connection
state. TLS 1.3 will just fallback to the kernel crypto for now.

Fixes: 130b392c6cd6 ("net: tls: Add tls 1.3 support")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_device.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index f6e258e37611..fdcf18c78bb5 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -746,6 +746,11 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx)
 	}
 
 	crypto_info = &ctx->crypto_send.info;
+	if (crypto_info->version != TLS_1_2_VERSION) {
+		rc = -EOPNOTSUPP;
+		goto free_offload_ctx;
+	}
+
 	switch (crypto_info->cipher_type) {
 	case TLS_CIPHER_AES_GCM_128:
 		nonce_size = TLS_CIPHER_AES_GCM_128_IV_SIZE;
@@ -880,6 +885,9 @@ int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx)
 	struct net_device *netdev;
 	int rc = 0;
 
+	if (ctx->crypto_recv.info.version != TLS_1_2_VERSION)
+		return -EOPNOTSUPP;
+
 	/* We support starting offload on multiple sockets
 	 * concurrently, so we only need a read lock here.
 	 * This lock must precede get_netdev_for_sock to prevent races between
-- 
2.20.1


From 8cc50a8192b305fe1a95f39ef0b42e198eebf575 Mon Sep 17 00:00:00 2001
From: Eli Britstein <elibr@mellanox.com>
Date: Sun, 2 Jun 2019 06:19:03 +0000
Subject: [PATCH 42/45] net/mlx5e: Fix port tunnel GRE entropy control

[ Upstream commit 914adbb1bcf89478ac138318d28b302704564d59 ]

GRE entropy calculation is a single bit per card, and not per port.
Force disable GRE entropy calculation upon the first GRE encap rule,
and release the force at the last GRE encap rule removal. This is done
per port.

Fixes: 97417f6182f8 ("net/mlx5e: Fix GRE key by controlling port tunnel entropy calculation")
Signed-off-by: Eli Britstein <elibr@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../mellanox/mlx5/core/lib/port_tun.c         | 23 ++++---------------
 1 file changed, 4 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.c
index 40f4a19b1ce1..5e2cea26f335 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.c
@@ -100,27 +100,12 @@ static int mlx5_set_entropy(struct mlx5_tun_entropy *tun_entropy,
 	 */
 	if (entropy_flags.gre_calc_supported &&
 	    reformat_type == MLX5_REFORMAT_TYPE_L2_TO_NVGRE) {
-		/* Other applications may change the global FW entropy
-		 * calculations settings. Check that the current entropy value
-		 * is the negative of the updated value.
-		 */
-		if (entropy_flags.force_enabled &&
-		    enable == entropy_flags.gre_calc_enabled) {
-			mlx5_core_warn(tun_entropy->mdev,
-				       "Unexpected GRE entropy calc setting - expected %d",
-				       !entropy_flags.gre_calc_enabled);
-			return -EOPNOTSUPP;
-		}
-		err = mlx5_set_port_gre_tun_entropy_calc(tun_entropy->mdev, enable,
-							 entropy_flags.force_supported);
+		if (!entropy_flags.force_supported)
+			return 0;
+		err = mlx5_set_port_gre_tun_entropy_calc(tun_entropy->mdev,
+							 enable, !enable);
 		if (err)
 			return err;
-		/* if we turn on the entropy we don't need to force it anymore */
-		if (entropy_flags.force_supported && enable) {
-			err = mlx5_set_port_gre_tun_entropy_calc(tun_entropy->mdev, 1, 0);
-			if (err)
-				return err;
-		}
 	} else if (entropy_flags.calc_supported) {
 		/* Other applications may change the global FW entropy
 		 * calculations settings. Check that the current entropy value
-- 
2.20.1


From 8b36e50ba8043c064dd94a903d134cd8f2174edb Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Fri, 3 May 2019 13:14:59 -0700
Subject: [PATCH 43/45] net/mlx5e: Rx, Fix checksum calculation for new
 hardware

[ Upstream commit db849faa9bef993a1379dc510623f750a72fa7ce ]

CQE checksum full mode in new HW, provides a full checksum of rx frame.
Covering bytes starting from eth protocol up to last byte in the received
frame (frame_size - ETH_HLEN), as expected by the stack.

Fixing up skb->csum by the driver is not required in such case. This fix
is to avoid wrong checksum calculation in drivers which already support
the new hardware with the new checksum mode.

Fixes: 85327a9c4150 ("net/mlx5: Update the list of the PCI supported devices")
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      | 1 +
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 3 +++
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c   | 7 ++++++-
 include/linux/mlx5/mlx5_ifc.h                     | 3 ++-
 4 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index a80031b2cfaf..9a1a21a8ae45 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -294,6 +294,7 @@ enum {
 	MLX5E_RQ_STATE_ENABLED,
 	MLX5E_RQ_STATE_AM,
 	MLX5E_RQ_STATE_NO_CSUM_COMPLETE,
+	MLX5E_RQ_STATE_CSUM_FULL, /* cqe_csum_full hw bit is set */
 };
 
 struct mlx5e_cq {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 6a8dc73855c9..2793e4036953 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -948,6 +948,9 @@ static int mlx5e_open_rq(struct mlx5e_channel *c,
 	if (err)
 		goto err_destroy_rq;
 
+	if (MLX5_CAP_ETH(c->mdev, cqe_checksum_full))
+		__set_bit(MLX5E_RQ_STATE_CSUM_FULL, &c->rq.state);
+
 	if (params->rx_dim_enabled)
 		__set_bit(MLX5E_RQ_STATE_AM, &c->rq.state);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index c3b3002ff62f..e8a3656d631d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -829,8 +829,14 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 		if (unlikely(get_ip_proto(skb, network_depth, proto) == IPPROTO_SCTP))
 			goto csum_unnecessary;
 
+		stats->csum_complete++;
 		skb->ip_summed = CHECKSUM_COMPLETE;
 		skb->csum = csum_unfold((__force __sum16)cqe->check_sum);
+
+		if (test_bit(MLX5E_RQ_STATE_CSUM_FULL, &rq->state))
+			return; /* CQE csum covers all received bytes */
+
+		/* csum might need some fixups ...*/
 		if (network_depth > ETH_HLEN)
 			/* CQE csum is calculated from the IP header and does
 			 * not cover VLAN headers (if present). This will add
@@ -841,7 +847,6 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 						 skb->csum);
 
 		mlx5e_skb_padding_csum(skb, network_depth, proto, stats);
-		stats->csum_complete++;
 		return;
 	}
 
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 3b83288749c6..c5dabaff1732 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -716,7 +716,8 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits {
 	u8         swp[0x1];
 	u8         swp_csum[0x1];
 	u8         swp_lso[0x1];
-	u8         reserved_at_23[0xd];
+	u8         cqe_checksum_full[0x1];
+	u8         reserved_at_24[0xc];
 	u8         max_vxlan_udp_ports[0x8];
 	u8         reserved_at_38[0x6];
 	u8         max_geneve_opt_len[0x1];
-- 
2.20.1


From d1d12692445798d60ea99becfdb489d43542df8e Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Mon, 17 Jun 2019 12:01:45 +0300
Subject: [PATCH 44/45] net/mlx5e: Fix return value from timeout recover
 function

[ Upstream commit 39825350ae2a52f8513741b36e42118bd80dd689 ]

Fix timeout recover function to return a meaningful return value.
When an interrupt was not sent by the FW, return IO error instead of
'true'.

Fixes: c7981bea48fb ("net/mlx5e: Fix return status of TX reporter timeout recover")
Signed-off-by: Aya Levin <ayal@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index 476dd97f7f2f..a778c15e5324 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -142,22 +142,20 @@ static int mlx5e_tx_reporter_timeout_recover(struct mlx5e_txqsq *sq)
 {
 	struct mlx5_eq_comp *eq = sq->cq.mcq.eq;
 	u32 eqe_count;
-	int ret;
 
 	netdev_err(sq->channel->netdev, "EQ 0x%x: Cons = 0x%x, irqn = 0x%x\n",
 		   eq->core.eqn, eq->core.cons_index, eq->core.irqn);
 
 	eqe_count = mlx5_eq_poll_irq_disabled(eq);
-	ret = eqe_count ? false : true;
 	if (!eqe_count) {
 		clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
-		return ret;
+		return -EIO;
 	}
 
 	netdev_err(sq->channel->netdev, "Recover %d eqes on EQ 0x%x\n",
 		   eqe_count, eq->core.eqn);
 	sq->channel->stats->eq_rearm++;
-	return ret;
+	return 0;
 }
 
 int mlx5e_tx_reporter_timeout(struct mlx5e_txqsq *sq)
-- 
2.20.1


From 15bc1806ddd5692964582a85569688b09626890d Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Sun, 30 Jun 2019 11:11:26 +0300
Subject: [PATCH 45/45] net/mlx5e: Fix error flow in tx reporter diagnose

[ Upstream commit 99d31cbd8953c6929da978bf049ab0f0b4e503d9 ]

Fix tx reporter's diagnose callback. Propagate error when failing to
gather diagnostics information or failing to print diagnostic data per
queue.

Fixes: de8650a82071 ("net/mlx5e: Add tx reporter support")
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index a778c15e5324..f3d98748b211 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -262,13 +262,13 @@ static int mlx5e_tx_reporter_diagnose(struct devlink_health_reporter *reporter,
 
 		err = mlx5_core_query_sq_state(priv->mdev, sq->sqn, &state);
 		if (err)
-			break;
+			goto unlock;
 
 		err = mlx5e_tx_reporter_build_diagnose_output(fmsg, sq->sqn,
 							      state,
 							      netif_xmit_stopped(sq->txq));
 		if (err)
-			break;
+			goto unlock;
 	}
 	err = devlink_fmsg_arr_pair_nest_end(fmsg);
 	if (err)
-- 
2.20.1


[-- Attachment #3: net_52.mbox --]
[-- Type: Application/Octet-Stream, Size: 129393 bytes --]

From 7935f070d8aaa27caa98f97601366b80fc5ac18f Mon Sep 17 00:00:00 2001
From: Brian King <brking@linux.vnet.ibm.com>
Date: Mon, 15 Jul 2019 16:41:50 -0500
Subject: [PATCH 01/49] bnx2x: Prevent load reordering in tx completion
 processing

[ Upstream commit ea811b795df24644a8eb760b493c43fba4450677 ]

This patch fixes an issue seen on Power systems with bnx2x which results
in the skb is NULL WARN_ON in bnx2x_free_tx_pkt firing due to the skb
pointer getting loaded in bnx2x_free_tx_pkt prior to the hw_cons
load in bnx2x_tx_int. Adding a read memory barrier resolves the issue.

Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 008ad0ca89ba..df166feba0a4 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -285,6 +285,9 @@ int bnx2x_tx_int(struct bnx2x *bp, struct bnx2x_fp_txdata *txdata)
 	hw_cons = le16_to_cpu(*txdata->tx_cons_sb);
 	sw_cons = txdata->tx_pkt_cons;
 
+	/* Ensure subsequent loads occur after hw_cons */
+	smp_rmb();
+
 	while (sw_cons != hw_cons) {
 		u16 pkt_cons;
 
-- 
2.20.1


From 9bff91a428bc46e4b05c6a46a405bb378ff006e9 Mon Sep 17 00:00:00 2001
From: "Guilherme G. Piccoli" <gpiccoli@canonical.com>
Date: Thu, 27 Jun 2019 13:31:33 -0300
Subject: [PATCH 02/49] bnx2x: Prevent ptp_task to be rescheduled indefinitely

[ Upstream commit 3c91f25c2f72ba6001775a5932857c1d2131c531 ]

Currently bnx2x ptp worker tries to read a register with timestamp
information in case of TX packet timestamping and in case it fails,
the routine reschedules itself indefinitely. This was reported as a
kworker always at 100% of CPU usage, which was narrowed down to be
bnx2x ptp_task.

By following the ioctl handler, we could narrow down the problem to
an NTP tool (chrony) requesting HW timestamping from bnx2x NIC with
RX filter zeroed; this isn't reproducible for example with ptp4l
(from linuxptp) since this tool requests a supported RX filter.
It seems NIC FW timestamp mechanism cannot work well with
RX_FILTER_NONE - driver's PTP filter init routine skips a register
write to the adapter if there's not a supported filter request.

This patch addresses the problem of bnx2x ptp thread's everlasting
reschedule by retrying the register read 10 times; between the read
attempts the thread sleeps for an increasing amount of time starting
in 1ms to give FW some time to perform the timestamping. If it still
fails after all retries, we bail out in order to prevent an unbound
resource consumption from bnx2x.

The patch also adds an ethtool statistic for accounting the skipped
TX timestamp packets and it reduces the priority of timestamping
error messages to prevent log flooding. The code was tested using
both linuxptp and chrony.

Reported-and-tested-by: Przemyslaw Hausman <przemyslaw.hausman@canonical.com>
Suggested-by: Sudarsana Reddy Kalluru <skalluru@marvell.com>
Signed-off-by: Guilherme G. Piccoli <gpiccoli@canonical.com>
Acked-by: Sudarsana Reddy Kalluru <skalluru@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/broadcom/bnx2x/bnx2x_cmn.c   |  5 ++-
 .../ethernet/broadcom/bnx2x/bnx2x_ethtool.c   |  4 ++-
 .../net/ethernet/broadcom/bnx2x/bnx2x_main.c  | 33 ++++++++++++++-----
 .../net/ethernet/broadcom/bnx2x/bnx2x_stats.h |  3 ++
 4 files changed, 34 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index df166feba0a4..bf39fc83d577 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -3860,9 +3860,12 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) {
 		if (!(bp->flags & TX_TIMESTAMPING_EN)) {
+			bp->eth_stats.ptp_skip_tx_ts++;
 			BNX2X_ERR("Tx timestamping was not enabled, this packet will not be timestamped\n");
 		} else if (bp->ptp_tx_skb) {
-			BNX2X_ERR("The device supports only a single outstanding packet to timestamp, this packet will not be timestamped\n");
+			bp->eth_stats.ptp_skip_tx_ts++;
+			netdev_err_once(bp->dev,
+					"Device supports only a single outstanding packet to timestamp, this packet won't be timestamped\n");
 		} else {
 			skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 			/* schedule check for Tx timestamp */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
index 51fc845de31a..4a0ba6801c9e 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -182,7 +182,9 @@ static const struct {
 	{ STATS_OFFSET32(driver_filtered_tx_pkt),
 				4, false, "driver_filtered_tx_pkt" },
 	{ STATS_OFFSET32(eee_tx_lpi),
-				4, true, "Tx LPI entry count"}
+				4, true, "Tx LPI entry count"},
+	{ STATS_OFFSET32(ptp_skip_tx_ts),
+				4, false, "ptp_skipped_tx_tstamp" },
 };
 
 #define BNX2X_NUM_STATS		ARRAY_SIZE(bnx2x_stats_arr)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 03ac10b1cd1e..2cc14db8f0ec 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -15214,11 +15214,24 @@ static void bnx2x_ptp_task(struct work_struct *work)
 	u32 val_seq;
 	u64 timestamp, ns;
 	struct skb_shared_hwtstamps shhwtstamps;
+	bool bail = true;
+	int i;
+
+	/* FW may take a while to complete timestamping; try a bit and if it's
+	 * still not complete, may indicate an error state - bail out then.
+	 */
+	for (i = 0; i < 10; i++) {
+		/* Read Tx timestamp registers */
+		val_seq = REG_RD(bp, port ? NIG_REG_P1_TLLH_PTP_BUF_SEQID :
+				 NIG_REG_P0_TLLH_PTP_BUF_SEQID);
+		if (val_seq & 0x10000) {
+			bail = false;
+			break;
+		}
+		msleep(1 << i);
+	}
 
-	/* Read Tx timestamp registers */
-	val_seq = REG_RD(bp, port ? NIG_REG_P1_TLLH_PTP_BUF_SEQID :
-			 NIG_REG_P0_TLLH_PTP_BUF_SEQID);
-	if (val_seq & 0x10000) {
+	if (!bail) {
 		/* There is a valid timestamp value */
 		timestamp = REG_RD(bp, port ? NIG_REG_P1_TLLH_PTP_BUF_TS_MSB :
 				   NIG_REG_P0_TLLH_PTP_BUF_TS_MSB);
@@ -15233,16 +15246,18 @@ static void bnx2x_ptp_task(struct work_struct *work)
 		memset(&shhwtstamps, 0, sizeof(shhwtstamps));
 		shhwtstamps.hwtstamp = ns_to_ktime(ns);
 		skb_tstamp_tx(bp->ptp_tx_skb, &shhwtstamps);
-		dev_kfree_skb_any(bp->ptp_tx_skb);
-		bp->ptp_tx_skb = NULL;
 
 		DP(BNX2X_MSG_PTP, "Tx timestamp, timestamp cycles = %llu, ns = %llu\n",
 		   timestamp, ns);
 	} else {
-		DP(BNX2X_MSG_PTP, "There is no valid Tx timestamp yet\n");
-		/* Reschedule to keep checking for a valid timestamp value */
-		schedule_work(&bp->ptp_task);
+		DP(BNX2X_MSG_PTP,
+		   "Tx timestamp is not recorded (register read=%u)\n",
+		   val_seq);
+		bp->eth_stats.ptp_skip_tx_ts++;
 	}
+
+	dev_kfree_skb_any(bp->ptp_tx_skb);
+	bp->ptp_tx_skb = NULL;
 }
 
 void bnx2x_set_rx_ts(struct bnx2x *bp, struct sk_buff *skb)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h
index b2644ed13d06..d55e63692cf3 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h
@@ -207,6 +207,9 @@ struct bnx2x_eth_stats {
 	u32 driver_filtered_tx_pkt;
 	/* src: Clear-on-Read register; Will not survive PMF Migration */
 	u32 eee_tx_lpi;
+
+	/* PTP */
+	u32 ptp_skip_tx_ts;
 };
 
 struct bnx2x_eth_q_stats {
-- 
2.20.1


From 70d92ad51e14b8072921bb347371c8f6b8335306 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 1 Jul 2019 20:40:24 -0700
Subject: [PATCH 03/49] bonding: validate ip header before check IPPROTO_IGMP

[ Upstream commit 9d1bc24b52fb8c5d859f9a47084bf1179470e04c ]

bond_xmit_roundrobin() checks for IGMP packets but it parses
the IP header even before checking skb->protocol.

We should validate the IP header with pskb_may_pull() before
using iph->protocol.

Reported-and-tested-by: syzbot+e5be16aa39ad6e755391@syzkaller.appspotmail.com
Fixes: a2fd940f4cff ("bonding: fix broken multicast with round-robin mode")
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Cc: Veaceslav Falico <vfalico@gmail.com>
Cc: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 37 ++++++++++++++++++++-------------
 1 file changed, 23 insertions(+), 14 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 799fc38c5c34..b0aab3a0a1bf 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3866,8 +3866,8 @@ static netdev_tx_t bond_xmit_roundrobin(struct sk_buff *skb,
 					struct net_device *bond_dev)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
-	struct iphdr *iph = ip_hdr(skb);
 	struct slave *slave;
+	int slave_cnt;
 	u32 slave_id;
 
 	/* Start with the curr_active_slave that joined the bond as the
@@ -3876,23 +3876,32 @@ static netdev_tx_t bond_xmit_roundrobin(struct sk_buff *skb,
 	 * send the join/membership reports.  The curr_active_slave found
 	 * will send all of this type of traffic.
 	 */
-	if (iph->protocol == IPPROTO_IGMP && skb->protocol == htons(ETH_P_IP)) {
-		slave = rcu_dereference(bond->curr_active_slave);
-		if (slave)
-			bond_dev_queue_xmit(bond, skb, slave->dev);
-		else
-			bond_xmit_slave_id(bond, skb, 0);
-	} else {
-		int slave_cnt = READ_ONCE(bond->slave_cnt);
+	if (skb->protocol == htons(ETH_P_IP)) {
+		int noff = skb_network_offset(skb);
+		struct iphdr *iph;
 
-		if (likely(slave_cnt)) {
-			slave_id = bond_rr_gen_slave_id(bond);
-			bond_xmit_slave_id(bond, skb, slave_id % slave_cnt);
-		} else {
-			bond_tx_drop(bond_dev, skb);
+		if (unlikely(!pskb_may_pull(skb, noff + sizeof(*iph))))
+			goto non_igmp;
+
+		iph = ip_hdr(skb);
+		if (iph->protocol == IPPROTO_IGMP) {
+			slave = rcu_dereference(bond->curr_active_slave);
+			if (slave)
+				bond_dev_queue_xmit(bond, skb, slave->dev);
+			else
+				bond_xmit_slave_id(bond, skb, 0);
+			return NETDEV_TX_OK;
 		}
 	}
 
+non_igmp:
+	slave_cnt = READ_ONCE(bond->slave_cnt);
+	if (likely(slave_cnt)) {
+		slave_id = bond_rr_gen_slave_id(bond);
+		bond_xmit_slave_id(bond, skb, slave_id % slave_cnt);
+	} else {
+		bond_tx_drop(bond_dev, skb);
+	}
 	return NETDEV_TX_OK;
 }
 
-- 
2.20.1


From bfe60f459b92df0eb4353adf6ae87518aea65d42 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Mon, 15 Jul 2019 14:10:17 +0900
Subject: [PATCH 04/49] caif-hsi: fix possible deadlock in cfhsi_exit_module()

[ Upstream commit fdd258d49e88a9e0b49ef04a506a796f1c768a8e ]

cfhsi_exit_module() calls unregister_netdev() under rtnl_lock().
but unregister_netdev() internally calls rtnl_lock().
So deadlock would occur.

Fixes: c41254006377 ("caif-hsi: Add rtnl support")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/caif/caif_hsi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/caif/caif_hsi.c b/drivers/net/caif/caif_hsi.c
index b2f10b6ad6e5..bbb2575d4728 100644
--- a/drivers/net/caif/caif_hsi.c
+++ b/drivers/net/caif/caif_hsi.c
@@ -1455,7 +1455,7 @@ static void __exit cfhsi_exit_module(void)
 	rtnl_lock();
 	list_for_each_safe(list_node, n, &cfhsi_list) {
 		cfhsi = list_entry(list_node, struct cfhsi, list);
-		unregister_netdev(cfhsi->ndev);
+		unregister_netdevice(cfhsi->ndev);
 	}
 	rtnl_unlock();
 }
-- 
2.20.1


From 6d6af2e587f4169b16e96fedd96de962a32a9a13 Mon Sep 17 00:00:00 2001
From: Haiyang Zhang <haiyangz@microsoft.com>
Date: Fri, 19 Jul 2019 17:33:51 +0000
Subject: [PATCH 05/49] hv_netvsc: Fix extra rcu_read_unlock in
 netvsc_recv_callback()

[ Upstream commit be4363bdf0ce9530f15aa0a03d1060304d116b15 ]

There is an extra rcu_read_unlock left in netvsc_recv_callback(),
after a previous patch that removes RCU from this function.
This patch removes the extra RCU unlock.

Fixes: 345ac08990b8 ("hv_netvsc: pass netvsc_device to receive callback")
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/netvsc_drv.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index afdcc5664ea6..3544e1991579 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -836,7 +836,6 @@ int netvsc_recv_callback(struct net_device *net,
 
 	if (unlikely(!skb)) {
 		++net_device_ctx->eth_stats.rx_no_memory;
-		rcu_read_unlock();
 		return NVSP_STAT_FAIL;
 	}
 
-- 
2.20.1


From fe3b1161a52d32e967530f1a7a576cb00fbab25a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 27 Jun 2019 01:27:01 -0700
Subject: [PATCH 06/49] igmp: fix memory leak in igmpv3_del_delrec()

[ Upstream commit e5b1c6c6277d5a283290a8c033c72544746f9b5b ]

im->tomb and/or im->sources might not be NULL, but we
currently overwrite their values blindly.

Using swap() will make sure the following call to kfree_pmc(pmc)
will properly free the psf structures.

Tested with the C repro provided by syzbot, which basically does :

 socket(PF_INET, SOCK_DGRAM, IPPROTO_IP) = 3
 setsockopt(3, SOL_IP, IP_ADD_MEMBERSHIP, "\340\0\0\2\177\0\0\1\0\0\0\0", 12) = 0
 ioctl(3, SIOCSIFFLAGS, {ifr_name="lo", ifr_flags=0}) = 0
 setsockopt(3, SOL_IP, IP_MSFILTER, "\340\0\0\2\177\0\0\1\1\0\0\0\1\0\0\0\377\377\377\377", 20) = 0
 ioctl(3, SIOCSIFFLAGS, {ifr_name="lo", ifr_flags=IFF_UP}) = 0
 exit_group(0)                    = ?

BUG: memory leak
unreferenced object 0xffff88811450f140 (size 64):
  comm "softirq", pid 0, jiffies 4294942448 (age 32.070s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 ff ff ff ff 00 00 00 00  ................
    00 00 00 00 00 00 00 00 01 00 00 00 00 00 00 00  ................
  backtrace:
    [<00000000c7bad083>] kmemleak_alloc_recursive include/linux/kmemleak.h:43 [inline]
    [<00000000c7bad083>] slab_post_alloc_hook mm/slab.h:439 [inline]
    [<00000000c7bad083>] slab_alloc mm/slab.c:3326 [inline]
    [<00000000c7bad083>] kmem_cache_alloc_trace+0x13d/0x280 mm/slab.c:3553
    [<000000009acc4151>] kmalloc include/linux/slab.h:547 [inline]
    [<000000009acc4151>] kzalloc include/linux/slab.h:742 [inline]
    [<000000009acc4151>] ip_mc_add1_src net/ipv4/igmp.c:1976 [inline]
    [<000000009acc4151>] ip_mc_add_src+0x36b/0x400 net/ipv4/igmp.c:2100
    [<000000004ac14566>] ip_mc_msfilter+0x22d/0x310 net/ipv4/igmp.c:2484
    [<0000000052d8f995>] do_ip_setsockopt.isra.0+0x1795/0x1930 net/ipv4/ip_sockglue.c:959
    [<000000004ee1e21f>] ip_setsockopt+0x3b/0xb0 net/ipv4/ip_sockglue.c:1248
    [<0000000066cdfe74>] udp_setsockopt+0x4e/0x90 net/ipv4/udp.c:2618
    [<000000009383a786>] sock_common_setsockopt+0x38/0x50 net/core/sock.c:3126
    [<00000000d8ac0c94>] __sys_setsockopt+0x98/0x120 net/socket.c:2072
    [<000000001b1e9666>] __do_sys_setsockopt net/socket.c:2083 [inline]
    [<000000001b1e9666>] __se_sys_setsockopt net/socket.c:2080 [inline]
    [<000000001b1e9666>] __x64_sys_setsockopt+0x26/0x30 net/socket.c:2080
    [<00000000420d395e>] do_syscall_64+0x76/0x1a0 arch/x86/entry/common.c:301
    [<000000007fd83a4b>] entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 24803f38a5c0 ("igmp: do not remove igmp souce list info when set link down")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Hangbin Liu <liuhangbin@gmail.com>
Reported-by: syzbot+6ca1abd0db68b5173a4f@syzkaller.appspotmail.com
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/igmp.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index a57f0d69eadb..85107bf812f2 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -1228,12 +1228,8 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im)
 	if (pmc) {
 		im->interface = pmc->interface;
 		if (im->sfmode == MCAST_INCLUDE) {
-			im->tomb = pmc->tomb;
-			pmc->tomb = NULL;
-
-			im->sources = pmc->sources;
-			pmc->sources = NULL;
-
+			swap(im->tomb, pmc->tomb);
+			swap(im->sources, pmc->sources);
 			for (psf = im->sources; psf; psf = psf->sf_next)
 				psf->sf_crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
 		} else {
-- 
2.20.1


From 624655e39bd317fc0cb9009e71ceaf463de2a0f7 Mon Sep 17 00:00:00 2001
From: Matteo Croce <mcroce@redhat.com>
Date: Mon, 1 Jul 2019 19:01:55 +0200
Subject: [PATCH 07/49] ipv4: don't set IPv6 only flags to IPv4 addresses

[ Upstream commit 2e60546368165c2449564d71f6005dda9205b5fb ]

Avoid the situation where an IPV6 only flag is applied to an IPv4 address:

    # ip addr add 192.0.2.1/24 dev dummy0 nodad home mngtmpaddr noprefixroute
    # ip -4 addr show dev dummy0
    2: dummy0: <BROADCAST,NOARP,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN group default qlen 1000
        inet 192.0.2.1/24 scope global noprefixroute dummy0
           valid_lft forever preferred_lft forever

Or worse, by sending a malicious netlink command:

    # ip -4 addr show dev dummy0
    2: dummy0: <BROADCAST,NOARP,UP,LOWER_UP> mtu 1500 qdisc noqueue state UNKNOWN group default qlen 1000
        inet 192.0.2.1/24 scope global nodad optimistic dadfailed home tentative mngtmpaddr noprefixroute stable-privacy dummy0
           valid_lft forever preferred_lft forever

Signed-off-by: Matteo Croce <mcroce@redhat.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/devinet.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index c6bd0f7a020a..c5ebfa199794 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -62,6 +62,11 @@
 #include <net/net_namespace.h>
 #include <net/addrconf.h>
 
+#define IPV6ONLY_FLAGS	\
+		(IFA_F_NODAD | IFA_F_OPTIMISTIC | IFA_F_DADFAILED | \
+		 IFA_F_HOMEADDRESS | IFA_F_TENTATIVE | \
+		 IFA_F_MANAGETEMPADDR | IFA_F_STABLE_PRIVACY)
+
 static struct ipv4_devconf ipv4_devconf = {
 	.data = {
 		[IPV4_DEVCONF_ACCEPT_REDIRECTS - 1] = 1,
@@ -468,6 +473,9 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh,
 	ifa->ifa_flags &= ~IFA_F_SECONDARY;
 	last_primary = &in_dev->ifa_list;
 
+	/* Don't set IPv6 only flags to IPv4 addresses */
+	ifa->ifa_flags &= ~IPV6ONLY_FLAGS;
+
 	for (ifap = &in_dev->ifa_list; (ifa1 = *ifap) != NULL;
 	     ifap = &ifa1->ifa_next) {
 		if (!(ifa1->ifa_flags & IFA_F_SECONDARY) &&
-- 
2.20.1


From 92479408898a09bc4c167b54d163ecbc25f0184b Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 17 Jul 2019 15:08:43 -0700
Subject: [PATCH 08/49] ipv6: rt6_check should return NULL if 'from' is NULL

[ Upstream commit 49d05fe2c9d1b4a27761c9807fec39b8155bef9e ]

Paul reported that l2tp sessions were broken after the commit referenced
in the Fixes tag. Prior to this commit rt6_check returned NULL if the
rt6_info 'from' was NULL - ie., the dst_entry was disconnected from a FIB
entry. Restore that behavior.

Fixes: 93531c674315 ("net/ipv6: separate handling of FIB entries from dst based routes")
Reported-by: Paul Donohue <linux-kernel@PaulSD.com>
Tested-by: Paul Donohue <linux-kernel@PaulSD.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 97a843cf164c..5f5a0a42ce60 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2215,7 +2215,7 @@ static struct dst_entry *rt6_check(struct rt6_info *rt,
 {
 	u32 rt_cookie = 0;
 
-	if ((from && !fib6_get_cookie_safe(from, &rt_cookie)) ||
+	if (!from || !fib6_get_cookie_safe(from, &rt_cookie) ||
 	    rt_cookie != cookie)
 		return NULL;
 
-- 
2.20.1


From 1370885ea55a1795d1a587832f597122508131cb Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 17 Jul 2019 23:39:33 +0300
Subject: [PATCH 09/49] ipv6: Unlink sibling route in case of failure

[ Upstream commit 54851aa90cf27041d64b12f65ac72e9f97bd90fd ]

When a route needs to be appended to an existing multipath route,
fib6_add_rt2node() first appends it to the siblings list and increments
the number of sibling routes on each sibling.

Later, the function notifies the route via call_fib6_entry_notifiers().
In case the notification is vetoed, the route is not unlinked from the
siblings list, which can result in a use-after-free.

Fix this by unlinking the route from the siblings list before returning
an error.

Audited the rest of the call sites from which the FIB notification chain
is called and could not find more problems.

Fixes: 2233000cba40 ("net/ipv6: Move call_fib6_entry_notifiers up for route adds")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Alexander Petrovskiy <alexpe@mellanox.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_fib.c | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 9180c8b6f764..455f1292e479 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1104,8 +1104,24 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
 		err = call_fib6_entry_notifiers(info->nl_net,
 						FIB_EVENT_ENTRY_ADD,
 						rt, extack);
-		if (err)
+		if (err) {
+			struct fib6_info *sibling, *next_sibling;
+
+			/* If the route has siblings, then it first
+			 * needs to be unlinked from them.
+			 */
+			if (!rt->fib6_nsiblings)
+				return err;
+
+			list_for_each_entry_safe(sibling, next_sibling,
+						 &rt->fib6_siblings,
+						 fib6_siblings)
+				sibling->fib6_nsiblings--;
+			rt->fib6_nsiblings = 0;
+			list_del_init(&rt->fib6_siblings);
+			rt6_multipath_rebalance(next_sibling);
 			return err;
+		}
 
 		rcu_assign_pointer(rt->fib6_next, iter);
 		fib6_info_hold(rt);
-- 
2.20.1


From 30ee0dd2ca8ada4679a942f615e3eb015b9eb7d2 Mon Sep 17 00:00:00 2001
From: Justin Chen <justinpopo6@gmail.com>
Date: Wed, 17 Jul 2019 14:58:53 -0700
Subject: [PATCH 10/49] net: bcmgenet: use promisc for unsupported filters

[ Upstream commit 35cbef9863640f06107144687bd13151bc2e8ce3 ]

Currently we silently ignore filters if we cannot meet the filter
requirements. This will lead to the MAC dropping packets that are
expected to pass. A better solution would be to set the NIC to promisc
mode when the required filters cannot be met.

Also correct the number of MDF filters supported. It should be 17,
not 16.

Signed-off-by: Justin Chen <justinpopo6@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/broadcom/genet/bcmgenet.c    | 57 +++++++++----------
 1 file changed, 26 insertions(+), 31 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 41b50e6570ea..2369b4bd63e3 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -3083,39 +3083,42 @@ static void bcmgenet_timeout(struct net_device *dev)
 	netif_tx_wake_all_queues(dev);
 }
 
-#define MAX_MC_COUNT	16
+#define MAX_MDF_FILTER	17
 
 static inline void bcmgenet_set_mdf_addr(struct bcmgenet_priv *priv,
 					 unsigned char *addr,
-					 int *i,
-					 int *mc)
+					 int *i)
 {
-	u32 reg;
-
 	bcmgenet_umac_writel(priv, addr[0] << 8 | addr[1],
 			     UMAC_MDF_ADDR + (*i * 4));
 	bcmgenet_umac_writel(priv, addr[2] << 24 | addr[3] << 16 |
 			     addr[4] << 8 | addr[5],
 			     UMAC_MDF_ADDR + ((*i + 1) * 4));
-	reg = bcmgenet_umac_readl(priv, UMAC_MDF_CTRL);
-	reg |= (1 << (MAX_MC_COUNT - *mc));
-	bcmgenet_umac_writel(priv, reg, UMAC_MDF_CTRL);
 	*i += 2;
-	(*mc)++;
 }
 
 static void bcmgenet_set_rx_mode(struct net_device *dev)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	struct netdev_hw_addr *ha;
-	int i, mc;
+	int i, nfilter;
 	u32 reg;
 
 	netif_dbg(priv, hw, dev, "%s: %08X\n", __func__, dev->flags);
 
-	/* Promiscuous mode */
+	/* Number of filters needed */
+	nfilter = netdev_uc_count(dev) + netdev_mc_count(dev) + 2;
+
+	/*
+	 * Turn on promicuous mode for three scenarios
+	 * 1. IFF_PROMISC flag is set
+	 * 2. IFF_ALLMULTI flag is set
+	 * 3. The number of filters needed exceeds the number filters
+	 *    supported by the hardware.
+	*/
 	reg = bcmgenet_umac_readl(priv, UMAC_CMD);
-	if (dev->flags & IFF_PROMISC) {
+	if ((dev->flags & (IFF_PROMISC | IFF_ALLMULTI)) ||
+	    (nfilter > MAX_MDF_FILTER)) {
 		reg |= CMD_PROMISC;
 		bcmgenet_umac_writel(priv, reg, UMAC_CMD);
 		bcmgenet_umac_writel(priv, 0, UMAC_MDF_CTRL);
@@ -3125,32 +3128,24 @@ static void bcmgenet_set_rx_mode(struct net_device *dev)
 		bcmgenet_umac_writel(priv, reg, UMAC_CMD);
 	}
 
-	/* UniMac doesn't support ALLMULTI */
-	if (dev->flags & IFF_ALLMULTI) {
-		netdev_warn(dev, "ALLMULTI is not supported\n");
-		return;
-	}
-
 	/* update MDF filter */
 	i = 0;
-	mc = 0;
 	/* Broadcast */
-	bcmgenet_set_mdf_addr(priv, dev->broadcast, &i, &mc);
+	bcmgenet_set_mdf_addr(priv, dev->broadcast, &i);
 	/* my own address.*/
-	bcmgenet_set_mdf_addr(priv, dev->dev_addr, &i, &mc);
-	/* Unicast list*/
-	if (netdev_uc_count(dev) > (MAX_MC_COUNT - mc))
-		return;
+	bcmgenet_set_mdf_addr(priv, dev->dev_addr, &i);
 
-	if (!netdev_uc_empty(dev))
-		netdev_for_each_uc_addr(ha, dev)
-			bcmgenet_set_mdf_addr(priv, ha->addr, &i, &mc);
-	/* Multicast */
-	if (netdev_mc_empty(dev) || netdev_mc_count(dev) >= (MAX_MC_COUNT - mc))
-		return;
+	/* Unicast */
+	netdev_for_each_uc_addr(ha, dev)
+		bcmgenet_set_mdf_addr(priv, ha->addr, &i);
 
+	/* Multicast */
 	netdev_for_each_mc_addr(ha, dev)
-		bcmgenet_set_mdf_addr(priv, ha->addr, &i, &mc);
+		bcmgenet_set_mdf_addr(priv, ha->addr, &i);
+
+	/* Enable filters */
+	reg = GENMASK(MAX_MDF_FILTER - 1, MAX_MDF_FILTER - nfilter);
+	bcmgenet_umac_writel(priv, reg, UMAC_MDF_CTRL);
 }
 
 /* Set the hardware MAC address. */
-- 
2.20.1


From 775710204b54acfd8e148a855161303aa7ba4307 Mon Sep 17 00:00:00 2001
From: Baruch Siach <baruch@tkos.co.il>
Date: Thu, 27 Jun 2019 21:17:39 +0300
Subject: [PATCH 11/49] net: dsa: mv88e6xxx: wait after reset deactivation

[ Upstream commit 7b75e49de424ceb53d13e60f35d0a73765626fda ]

Add a 1ms delay after reset deactivation. Otherwise the chip returns
bogus ID value. This is observed with 88E6390 (Peridot) chip.

Signed-off-by: Baruch Siach <baruch@tkos.co.il>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 063c7a671b41..2e8b1ab2c6f7 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -4711,6 +4711,8 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev)
 		err = PTR_ERR(chip->reset);
 		goto out;
 	}
+	if (chip->reset)
+		usleep_range(1000, 2000);
 
 	err = mv88e6xxx_detect(chip);
 	if (err)
-- 
2.20.1


From 5581382d77387f5dabcfe311f4d5d29336d75da9 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 26 Jun 2019 20:40:45 +0200
Subject: [PATCH 12/49] net: make skb_dst_force return true when dst is
 refcounted

[ Upstream commit b60a77386b1d4868f72f6353d35dabe5fbe981f2 ]

netfilter did not expect that skb_dst_force() can cause skb to lose its
dst entry.

I got a bug report with a skb->dst NULL dereference in netfilter
output path.  The backtrace contains nf_reinject(), so the dst might have
been cleared when skb got queued to userspace.

Other users were fixed via
if (skb_dst(skb)) {
	skb_dst_force(skb);
	if (!skb_dst(skb))
		goto handle_err;
}

But I think its preferable to make the 'dst might be cleared' part
of the function explicit.

In netfilter case, skb with a null dst is expected when queueing in
prerouting hook, so drop skb for the other hooks.

v2:
 v1 of this patch returned true in case skb had no dst entry.
 Eric said:
   Say if we have two skb_dst_force() calls for some reason
   on the same skb, only the first one will return false.

 This now returns false even when skb had no dst, as per Erics
 suggestion, so callers might need to check skb_dst() first before
 skb_dst_force().

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst.h        | 5 ++++-
 net/netfilter/nf_queue.c | 6 +++++-
 2 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/include/net/dst.h b/include/net/dst.h
index 12b31c602cb0..f8206d3fed2f 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -302,8 +302,9 @@ static inline bool dst_hold_safe(struct dst_entry *dst)
  * @skb: buffer
  *
  * If dst is not yet refcounted and not destroyed, grab a ref on it.
+ * Returns true if dst is refcounted.
  */
-static inline void skb_dst_force(struct sk_buff *skb)
+static inline bool skb_dst_force(struct sk_buff *skb)
 {
 	if (skb_dst_is_noref(skb)) {
 		struct dst_entry *dst = skb_dst(skb);
@@ -314,6 +315,8 @@ static inline void skb_dst_force(struct sk_buff *skb)
 
 		skb->_skb_refdst = (unsigned long)dst;
 	}
+
+	return skb->_skb_refdst != 0UL;
 }
 
 
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index b5b2be55ca82..2c440015ff0c 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -190,6 +190,11 @@ static int __nf_queue(struct sk_buff *skb, const struct nf_hook_state *state,
 		goto err;
 	}
 
+	if (!skb_dst_force(skb) && state->hook != NF_INET_PRE_ROUTING) {
+		status = -ENETDOWN;
+		goto err;
+	}
+
 	*entry = (struct nf_queue_entry) {
 		.skb	= skb,
 		.state	= *state,
@@ -198,7 +203,6 @@ static int __nf_queue(struct sk_buff *skb, const struct nf_hook_state *state,
 	};
 
 	nf_queue_entry_get_refs(entry);
-	skb_dst_force(skb);
 
 	switch (entry->state.pf) {
 	case AF_INET:
-- 
2.20.1


From 039a54e2bd76ec6c92f52606cc46edb751421fc5 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Sun, 14 Jul 2019 23:36:11 +0200
Subject: [PATCH 13/49] net: neigh: fix multiple neigh timer scheduling

[ Upstream commit 071c37983d99da07797294ea78e9da1a6e287144 ]

Neigh timer can be scheduled multiple times from userspace adding
multiple neigh entries and forcing the neigh timer scheduling passing
NTF_USE in the netlink requests.
This will result in a refcount leak and in the following dump stack:

[   32.465295] NEIGH: BUG, double timer add, state is 8
[   32.465308] CPU: 0 PID: 416 Comm: double_timer_ad Not tainted 5.2.0+ #65
[   32.465311] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.12.0-2.fc30 04/01/2014
[   32.465313] Call Trace:
[   32.465318]  dump_stack+0x7c/0xc0
[   32.465323]  __neigh_event_send+0x20c/0x880
[   32.465326]  ? ___neigh_create+0x846/0xfb0
[   32.465329]  ? neigh_lookup+0x2a9/0x410
[   32.465332]  ? neightbl_fill_info.constprop.0+0x800/0x800
[   32.465334]  neigh_add+0x4f8/0x5e0
[   32.465337]  ? neigh_xmit+0x620/0x620
[   32.465341]  ? find_held_lock+0x85/0xa0
[   32.465345]  rtnetlink_rcv_msg+0x204/0x570
[   32.465348]  ? rtnl_dellink+0x450/0x450
[   32.465351]  ? mark_held_locks+0x90/0x90
[   32.465354]  ? match_held_lock+0x1b/0x230
[   32.465357]  netlink_rcv_skb+0xc4/0x1d0
[   32.465360]  ? rtnl_dellink+0x450/0x450
[   32.465363]  ? netlink_ack+0x420/0x420
[   32.465366]  ? netlink_deliver_tap+0x115/0x560
[   32.465369]  ? __alloc_skb+0xc9/0x2f0
[   32.465372]  netlink_unicast+0x270/0x330
[   32.465375]  ? netlink_attachskb+0x2f0/0x2f0
[   32.465378]  netlink_sendmsg+0x34f/0x5a0
[   32.465381]  ? netlink_unicast+0x330/0x330
[   32.465385]  ? move_addr_to_kernel.part.0+0x20/0x20
[   32.465388]  ? netlink_unicast+0x330/0x330
[   32.465391]  sock_sendmsg+0x91/0xa0
[   32.465394]  ___sys_sendmsg+0x407/0x480
[   32.465397]  ? copy_msghdr_from_user+0x200/0x200
[   32.465401]  ? _raw_spin_unlock_irqrestore+0x37/0x40
[   32.465404]  ? lockdep_hardirqs_on+0x17d/0x250
[   32.465407]  ? __wake_up_common_lock+0xcb/0x110
[   32.465410]  ? __wake_up_common+0x230/0x230
[   32.465413]  ? netlink_bind+0x3e1/0x490
[   32.465416]  ? netlink_setsockopt+0x540/0x540
[   32.465420]  ? __fget_light+0x9c/0xf0
[   32.465423]  ? sockfd_lookup_light+0x8c/0xb0
[   32.465426]  __sys_sendmsg+0xa5/0x110
[   32.465429]  ? __ia32_sys_shutdown+0x30/0x30
[   32.465432]  ? __fd_install+0xe1/0x2c0
[   32.465435]  ? lockdep_hardirqs_off+0xb5/0x100
[   32.465438]  ? mark_held_locks+0x24/0x90
[   32.465441]  ? do_syscall_64+0xf/0x270
[   32.465444]  do_syscall_64+0x63/0x270
[   32.465448]  entry_SYSCALL_64_after_hwframe+0x49/0xbe

Fix the issue unscheduling neigh_timer if selected entry is in 'IN_TIMER'
receiving a netlink request with NTF_USE flag set

Reported-by: Marek Majkowski <marek@cloudflare.com>
Fixes: 0c5c2d308906 ("neigh: Allow for user space users of the neighbour table")
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 9e7fc929bc50..5bb0a1aee50e 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1122,6 +1122,7 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
 
 			atomic_set(&neigh->probes,
 				   NEIGH_VAR(neigh->parms, UCAST_PROBES));
+			neigh_del_timer(neigh);
 			neigh->nud_state     = NUD_INCOMPLETE;
 			neigh->updated = now;
 			next = now + max(NEIGH_VAR(neigh->parms, RETRANS_TIME),
@@ -1138,6 +1139,7 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
 		}
 	} else if (neigh->nud_state & NUD_STALE) {
 		neigh_dbg(2, "neigh %p is delayed\n", neigh);
+		neigh_del_timer(neigh);
 		neigh->nud_state = NUD_DELAY;
 		neigh->updated = jiffies;
 		neigh_add_timer(neigh, jiffies +
-- 
2.20.1


From 124e07dc067aaeb7f6c0aa559a77903949d6d87b Mon Sep 17 00:00:00 2001
From: John Hurley <john.hurley@netronome.com>
Date: Thu, 27 Jun 2019 14:37:30 +0100
Subject: [PATCH 14/49] net: openvswitch: fix csum updates for MPLS actions

[ Upstream commit 0e3183cd2a64843a95b62f8bd4a83605a4cf0615 ]

Skbs may have their checksum value populated by HW. If this is a checksum
calculated over the entire packet then the CHECKSUM_COMPLETE field is
marked. Changes to the data pointer on the skb throughout the network
stack still try to maintain this complete csum value if it is required
through functions such as skb_postpush_rcsum.

The MPLS actions in Open vSwitch modify a CHECKSUM_COMPLETE value when
changes are made to packet data without a push or a pull. This occurs when
the ethertype of the MAC header is changed or when MPLS lse fields are
modified.

The modification is carried out using the csum_partial function to get the
csum of a buffer and add it into the larger checksum. The buffer is an
inversion of the data to be removed followed by the new data. Because the
csum is calculated over 16 bits and these values align with 16 bits, the
effect is the removal of the old value from the CHECKSUM_COMPLETE and
addition of the new value.

However, the csum fed into the function and the outcome of the
calculation are also inverted. This would only make sense if it was the
new value rather than the old that was inverted in the input buffer.

Fix the issue by removing the bit inverts in the csum_partial calculation.

The bug was verified and the fix tested by comparing the folded value of
the updated CHECKSUM_COMPLETE value with the folded value of a full
software checksum calculation (reset skb->csum to 0 and run
skb_checksum_complete(skb)). Prior to the fix the outcomes differed but
after they produce the same result.

Fixes: 25cd9ba0abc0 ("openvswitch: Add basic MPLS support to kernel")
Fixes: bc7cc5999fd3 ("openvswitch: update checksum in {push,pop}_mpls")
Signed-off-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/actions.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 151518dbabad..bd131469e4ca 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -166,8 +166,7 @@ static void update_ethertype(struct sk_buff *skb, struct ethhdr *hdr,
 	if (skb->ip_summed == CHECKSUM_COMPLETE) {
 		__be16 diff[] = { ~(hdr->h_proto), ethertype };
 
-		skb->csum = ~csum_partial((char *)diff, sizeof(diff),
-					~skb->csum);
+		skb->csum = csum_partial((char *)diff, sizeof(diff), skb->csum);
 	}
 
 	hdr->h_proto = ethertype;
@@ -259,8 +258,7 @@ static int set_mpls(struct sk_buff *skb, struct sw_flow_key *flow_key,
 	if (skb->ip_summed == CHECKSUM_COMPLETE) {
 		__be32 diff[] = { ~(stack->label_stack_entry), lse };
 
-		skb->csum = ~csum_partial((char *)diff, sizeof(diff),
-					  ~skb->csum);
+		skb->csum = csum_partial((char *)diff, sizeof(diff), skb->csum);
 	}
 
 	stack->label_stack_entry = lse;
-- 
2.20.1


From 60a49ed2c566303b194ec94b74206a0b4bdc803e Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sun, 21 Jul 2019 18:50:08 +0200
Subject: [PATCH 15/49] net: phy: sfp: hwmon: Fix scaling of RX power

[ Upstream commit 0cea0e1148fe134a4a3aaf0b1496f09241fb943a ]

The RX power read from the SFP uses units of 0.1uW. This must be
scaled to units of uW for HWMON. This requires a divide by 10, not the
current 100.

With this change in place, sensors(1) and ethtool -m agree:

sff2-isa-0000
Adapter: ISA adapter
in0:          +3.23 V
temp1:        +33.1 C
power1:      270.00 uW
power2:      200.00 uW
curr1:        +0.01 A

        Laser output power                        : 0.2743 mW / -5.62 dBm
        Receiver signal average optical power     : 0.2014 mW / -6.96 dBm

Reported-by: chris.healy@zii.aero
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Fixes: 1323061a018a ("net: phy: sfp: Add HWMON support for module sensors")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/sfp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index 71812be0ac64..825857efcc4e 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -514,7 +514,7 @@ static int sfp_hwmon_read_sensor(struct sfp *sfp, int reg, long *value)
 
 static void sfp_hwmon_to_rx_power(long *value)
 {
-	*value = DIV_ROUND_CLOSEST(*value, 100);
+	*value = DIV_ROUND_CLOSEST(*value, 10);
 }
 
 static void sfp_hwmon_calibrate(struct sfp *sfp, unsigned int slope, int offset,
-- 
2.20.1


From e0604bac9a71afd8e77cf49a83ab2f03fa152694 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Tue, 16 Jul 2019 13:57:30 -0700
Subject: [PATCH 16/49] net_sched: unset TCQ_F_CAN_BYPASS when adding filters

[ Upstream commit 3f05e6886a595c9a29a309c52f45326be917823c ]

For qdisc's that support TC filters and set TCQ_F_CAN_BYPASS,
notably fq_codel, it makes no sense to let packets bypass the TC
filters we setup in any scenario, otherwise our packets steering
policy could not be enforced.

This can be reproduced easily with the following script:

 ip li add dev dummy0 type dummy
 ifconfig dummy0 up
 tc qd add dev dummy0 root fq_codel
 tc filter add dev dummy0 parent 8001: protocol arp basic action mirred egress redirect dev lo
 tc filter add dev dummy0 parent 8001: protocol ip basic action mirred egress redirect dev lo
 ping -I dummy0 192.168.112.1

Without this patch, packets are sent directly to dummy0 without
hitting any of the filters. With this patch, packets are redirected
to loopback as expected.

This fix is not perfect, it only unsets the flag but does not set it back
because we have to save the information somewhere in the qdisc if we
really want that. Note, both fq_codel and sfq clear this flag in their
->bind_tcf() but this is clearly not sufficient when we don't use any
class ID.

Fixes: 23624935e0c4 ("net_sched: TCQ_F_CAN_BYPASS generalization")
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c      | 1 +
 net/sched/sch_fq_codel.c | 2 --
 net/sched/sch_sfq.c      | 2 --
 3 files changed, 1 insertion(+), 4 deletions(-)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index ad36bbcc583e..81b0d9f38659 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -2160,6 +2160,7 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
 		tfilter_notify(net, skb, n, tp, block, q, parent, fh,
 			       RTM_NEWTFILTER, false, rtnl_held);
 		tfilter_put(tp, fh);
+		q->flags &= ~TCQ_F_CAN_BYPASS;
 	}
 
 errout:
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index e2faf33d282b..d59fbcc745d1 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -596,8 +596,6 @@ static unsigned long fq_codel_find(struct Qdisc *sch, u32 classid)
 static unsigned long fq_codel_bind(struct Qdisc *sch, unsigned long parent,
 			      u32 classid)
 {
-	/* we cannot bypass queue discipline anymore */
-	sch->flags &= ~TCQ_F_CAN_BYPASS;
 	return 0;
 }
 
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 420bd8411677..68404a9d2ce4 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -824,8 +824,6 @@ static unsigned long sfq_find(struct Qdisc *sch, u32 classid)
 static unsigned long sfq_bind(struct Qdisc *sch, unsigned long parent,
 			      u32 classid)
 {
-	/* we cannot bypass queue discipline anymore */
-	sch->flags &= ~TCQ_F_CAN_BYPASS;
 	return 0;
 }
 
-- 
2.20.1


From 8510d0674b8d17bff79f3143264d621ebd311b00 Mon Sep 17 00:00:00 2001
From: Jose Abreu <Jose.Abreu@synopsys.com>
Date: Mon, 8 Jul 2019 14:26:28 +0200
Subject: [PATCH 17/49] net: stmmac: Re-work the queue selection for TSO
 packets

[ Upstream commit 4993e5b37e8bcb55ac90f76eb6d2432647273747 ]

Ben Hutchings says:
	"This is the wrong place to change the queue mapping.
	stmmac_xmit() is called with a specific TX queue locked,
	and accessing a different TX queue results in a data race
	for all of that queue's state.

	I think this commit should be reverted upstream and in all
	stable branches.  Instead, the driver should implement the
	ndo_select_queue operation and override the queue mapping there."

Fixes: c5acdbee22a1 ("net: stmmac: Send TSO packets always from Queue 0")
Suggested-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/stmicro/stmmac/stmmac_main.c | 28 ++++++++++++-------
 1 file changed, 18 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 06358fe5b245..11b6feb33b54 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3045,17 +3045,8 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	/* Manage oversized TCP frames for GMAC4 device */
 	if (skb_is_gso(skb) && priv->tso) {
-		if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) {
-			/*
-			 * There is no way to determine the number of TSO
-			 * capable Queues. Let's use always the Queue 0
-			 * because if TSO is supported then at least this
-			 * one will be capable.
-			 */
-			skb_set_queue_mapping(skb, 0);
-
+		if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))
 			return stmmac_tso_xmit(skb, dev);
-		}
 	}
 
 	if (unlikely(stmmac_tx_avail(priv, queue) < nfrags + 1)) {
@@ -3872,6 +3863,22 @@ static int stmmac_setup_tc(struct net_device *ndev, enum tc_setup_type type,
 	}
 }
 
+static u16 stmmac_select_queue(struct net_device *dev, struct sk_buff *skb,
+			       struct net_device *sb_dev)
+{
+	if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) {
+		/*
+		 * There is no way to determine the number of TSO
+		 * capable Queues. Let's use always the Queue 0
+		 * because if TSO is supported then at least this
+		 * one will be capable.
+		 */
+		return 0;
+	}
+
+	return netdev_pick_tx(dev, skb, NULL) % dev->real_num_tx_queues;
+}
+
 static int stmmac_set_mac_address(struct net_device *ndev, void *addr)
 {
 	struct stmmac_priv *priv = netdev_priv(ndev);
@@ -4088,6 +4095,7 @@ static const struct net_device_ops stmmac_netdev_ops = {
 	.ndo_tx_timeout = stmmac_tx_timeout,
 	.ndo_do_ioctl = stmmac_ioctl,
 	.ndo_setup_tc = stmmac_setup_tc,
+	.ndo_select_queue = stmmac_select_queue,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = stmmac_poll_controller,
 #endif
-- 
2.20.1


From 93cc541fbd1a906bb50be6365de011edf8ac80a8 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 28 Jun 2019 16:11:39 -0700
Subject: [PATCH 18/49] net/tls: make sure offload also gets the keys wiped

[ Upstream commit acd3e96d53a24d219f720ed4012b62723ae05da1 ]

Commit 86029d10af18 ("tls: zero the crypto information from tls_context
before freeing") added memzero_explicit() calls to clear the key material
before freeing struct tls_context, but it missed tls_device.c has its
own way of freeing this structure. Replace the missing free.

Fixes: 86029d10af18 ("tls: zero the crypto information from tls_context before freeing")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h    | 1 +
 net/tls/tls_device.c | 2 +-
 net/tls/tls_main.c   | 4 ++--
 3 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/include/net/tls.h b/include/net/tls.h
index 53d96bca220d..889df0312cd1 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -313,6 +313,7 @@ struct tls_offload_context_rx {
 	(ALIGN(sizeof(struct tls_offload_context_rx), sizeof(void *)) + \
 	 TLS_DRIVER_STATE_SIZE)
 
+void tls_ctx_free(struct tls_context *ctx);
 int wait_on_pending_writer(struct sock *sk, long *timeo);
 int tls_sk_query(struct sock *sk, int optname, char __user *optval,
 		int __user *optlen);
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 1f9cf57d9754..359a515fd193 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -61,7 +61,7 @@ static void tls_device_free_ctx(struct tls_context *ctx)
 	if (ctx->rx_conf == TLS_HW)
 		kfree(tls_offload_ctx_rx(ctx));
 
-	kfree(ctx);
+	tls_ctx_free(ctx);
 }
 
 static void tls_device_gc_task(struct work_struct *work)
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index e2b69e805d46..4674e57e66b0 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -251,7 +251,7 @@ static void tls_write_space(struct sock *sk)
 	ctx->sk_write_space(sk);
 }
 
-static void tls_ctx_free(struct tls_context *ctx)
+void tls_ctx_free(struct tls_context *ctx)
 {
 	if (!ctx)
 		return;
@@ -643,7 +643,7 @@ static void tls_hw_sk_destruct(struct sock *sk)
 
 	ctx->sk_destruct(sk);
 	/* Free ctx */
-	kfree(ctx);
+	tls_ctx_free(ctx);
 	icsk->icsk_ulp_data = NULL;
 }
 
-- 
2.20.1


From a5f9484c93843fd69409f66e6594a89bd6386cb4 Mon Sep 17 00:00:00 2001
From: Yang Wei <albin_yang@163.com>
Date: Mon, 8 Jul 2019 22:57:39 +0800
Subject: [PATCH 19/49] nfc: fix potential illegal memory access

[ Upstream commit dd006fc434e107ef90f7de0db9907cbc1c521645 ]

The frags_q is not properly initialized, it may result in illegal memory
access when conn_info is NULL.
The "goto free_exit" should be replaced by "goto exit".

Signed-off-by: Yang Wei <albin_yang@163.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/nfc/nci/data.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/nfc/nci/data.c b/net/nfc/nci/data.c
index 0a0c265baaa4..ce3382be937f 100644
--- a/net/nfc/nci/data.c
+++ b/net/nfc/nci/data.c
@@ -107,7 +107,7 @@ static int nci_queue_tx_data_frags(struct nci_dev *ndev,
 	conn_info = nci_get_conn_info_by_conn_id(ndev, conn_id);
 	if (!conn_info) {
 		rc = -EPROTO;
-		goto free_exit;
+		goto exit;
 	}
 
 	__skb_queue_head_init(&frags_q);
-- 
2.20.1


From 413caf4addc374cef5158ef678154ff95f37dca5 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 13 Jul 2019 13:45:47 +0200
Subject: [PATCH 20/49] r8169: fix issue with confused RX unit after PHY
 power-down on RTL8411b

[ Upstream commit fe4e8db0392a6c2e795eb89ef5fcd86522e66248 ]

On RTL8411b the RX unit gets confused if the PHY is powered-down.
This was reported in [0] and confirmed by Realtek. Realtek provided
a sequence to fix the RX unit after PHY wakeup.

The issue itself seems to have been there longer, the Fixes tag
refers to where the fix applies properly.

[0] https://bugzilla.redhat.com/show_bug.cgi?id=1692075

Fixes: a99790bf5c7f ("r8169: Reinstate ASPM Support")
Tested-by: Ionut Radu <ionut.radu@gmail.com>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 137 +++++++++++++++++++++++++++
 1 file changed, 137 insertions(+)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index d06a61f00e78..96637fcbe65d 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -5157,6 +5157,143 @@ static void rtl_hw_start_8411_2(struct rtl8169_private *tp)
 	/* disable aspm and clock request before access ephy */
 	rtl_hw_aspm_clkreq_enable(tp, false);
 	rtl_ephy_init(tp, e_info_8411_2);
+
+	/* The following Realtek-provided magic fixes an issue with the RX unit
+	 * getting confused after the PHY having been powered-down.
+	 */
+	r8168_mac_ocp_write(tp, 0xFC28, 0x0000);
+	r8168_mac_ocp_write(tp, 0xFC2A, 0x0000);
+	r8168_mac_ocp_write(tp, 0xFC2C, 0x0000);
+	r8168_mac_ocp_write(tp, 0xFC2E, 0x0000);
+	r8168_mac_ocp_write(tp, 0xFC30, 0x0000);
+	r8168_mac_ocp_write(tp, 0xFC32, 0x0000);
+	r8168_mac_ocp_write(tp, 0xFC34, 0x0000);
+	r8168_mac_ocp_write(tp, 0xFC36, 0x0000);
+	mdelay(3);
+	r8168_mac_ocp_write(tp, 0xFC26, 0x0000);
+
+	r8168_mac_ocp_write(tp, 0xF800, 0xE008);
+	r8168_mac_ocp_write(tp, 0xF802, 0xE00A);
+	r8168_mac_ocp_write(tp, 0xF804, 0xE00C);
+	r8168_mac_ocp_write(tp, 0xF806, 0xE00E);
+	r8168_mac_ocp_write(tp, 0xF808, 0xE027);
+	r8168_mac_ocp_write(tp, 0xF80A, 0xE04F);
+	r8168_mac_ocp_write(tp, 0xF80C, 0xE05E);
+	r8168_mac_ocp_write(tp, 0xF80E, 0xE065);
+	r8168_mac_ocp_write(tp, 0xF810, 0xC602);
+	r8168_mac_ocp_write(tp, 0xF812, 0xBE00);
+	r8168_mac_ocp_write(tp, 0xF814, 0x0000);
+	r8168_mac_ocp_write(tp, 0xF816, 0xC502);
+	r8168_mac_ocp_write(tp, 0xF818, 0xBD00);
+	r8168_mac_ocp_write(tp, 0xF81A, 0x074C);
+	r8168_mac_ocp_write(tp, 0xF81C, 0xC302);
+	r8168_mac_ocp_write(tp, 0xF81E, 0xBB00);
+	r8168_mac_ocp_write(tp, 0xF820, 0x080A);
+	r8168_mac_ocp_write(tp, 0xF822, 0x6420);
+	r8168_mac_ocp_write(tp, 0xF824, 0x48C2);
+	r8168_mac_ocp_write(tp, 0xF826, 0x8C20);
+	r8168_mac_ocp_write(tp, 0xF828, 0xC516);
+	r8168_mac_ocp_write(tp, 0xF82A, 0x64A4);
+	r8168_mac_ocp_write(tp, 0xF82C, 0x49C0);
+	r8168_mac_ocp_write(tp, 0xF82E, 0xF009);
+	r8168_mac_ocp_write(tp, 0xF830, 0x74A2);
+	r8168_mac_ocp_write(tp, 0xF832, 0x8CA5);
+	r8168_mac_ocp_write(tp, 0xF834, 0x74A0);
+	r8168_mac_ocp_write(tp, 0xF836, 0xC50E);
+	r8168_mac_ocp_write(tp, 0xF838, 0x9CA2);
+	r8168_mac_ocp_write(tp, 0xF83A, 0x1C11);
+	r8168_mac_ocp_write(tp, 0xF83C, 0x9CA0);
+	r8168_mac_ocp_write(tp, 0xF83E, 0xE006);
+	r8168_mac_ocp_write(tp, 0xF840, 0x74F8);
+	r8168_mac_ocp_write(tp, 0xF842, 0x48C4);
+	r8168_mac_ocp_write(tp, 0xF844, 0x8CF8);
+	r8168_mac_ocp_write(tp, 0xF846, 0xC404);
+	r8168_mac_ocp_write(tp, 0xF848, 0xBC00);
+	r8168_mac_ocp_write(tp, 0xF84A, 0xC403);
+	r8168_mac_ocp_write(tp, 0xF84C, 0xBC00);
+	r8168_mac_ocp_write(tp, 0xF84E, 0x0BF2);
+	r8168_mac_ocp_write(tp, 0xF850, 0x0C0A);
+	r8168_mac_ocp_write(tp, 0xF852, 0xE434);
+	r8168_mac_ocp_write(tp, 0xF854, 0xD3C0);
+	r8168_mac_ocp_write(tp, 0xF856, 0x49D9);
+	r8168_mac_ocp_write(tp, 0xF858, 0xF01F);
+	r8168_mac_ocp_write(tp, 0xF85A, 0xC526);
+	r8168_mac_ocp_write(tp, 0xF85C, 0x64A5);
+	r8168_mac_ocp_write(tp, 0xF85E, 0x1400);
+	r8168_mac_ocp_write(tp, 0xF860, 0xF007);
+	r8168_mac_ocp_write(tp, 0xF862, 0x0C01);
+	r8168_mac_ocp_write(tp, 0xF864, 0x8CA5);
+	r8168_mac_ocp_write(tp, 0xF866, 0x1C15);
+	r8168_mac_ocp_write(tp, 0xF868, 0xC51B);
+	r8168_mac_ocp_write(tp, 0xF86A, 0x9CA0);
+	r8168_mac_ocp_write(tp, 0xF86C, 0xE013);
+	r8168_mac_ocp_write(tp, 0xF86E, 0xC519);
+	r8168_mac_ocp_write(tp, 0xF870, 0x74A0);
+	r8168_mac_ocp_write(tp, 0xF872, 0x48C4);
+	r8168_mac_ocp_write(tp, 0xF874, 0x8CA0);
+	r8168_mac_ocp_write(tp, 0xF876, 0xC516);
+	r8168_mac_ocp_write(tp, 0xF878, 0x74A4);
+	r8168_mac_ocp_write(tp, 0xF87A, 0x48C8);
+	r8168_mac_ocp_write(tp, 0xF87C, 0x48CA);
+	r8168_mac_ocp_write(tp, 0xF87E, 0x9CA4);
+	r8168_mac_ocp_write(tp, 0xF880, 0xC512);
+	r8168_mac_ocp_write(tp, 0xF882, 0x1B00);
+	r8168_mac_ocp_write(tp, 0xF884, 0x9BA0);
+	r8168_mac_ocp_write(tp, 0xF886, 0x1B1C);
+	r8168_mac_ocp_write(tp, 0xF888, 0x483F);
+	r8168_mac_ocp_write(tp, 0xF88A, 0x9BA2);
+	r8168_mac_ocp_write(tp, 0xF88C, 0x1B04);
+	r8168_mac_ocp_write(tp, 0xF88E, 0xC508);
+	r8168_mac_ocp_write(tp, 0xF890, 0x9BA0);
+	r8168_mac_ocp_write(tp, 0xF892, 0xC505);
+	r8168_mac_ocp_write(tp, 0xF894, 0xBD00);
+	r8168_mac_ocp_write(tp, 0xF896, 0xC502);
+	r8168_mac_ocp_write(tp, 0xF898, 0xBD00);
+	r8168_mac_ocp_write(tp, 0xF89A, 0x0300);
+	r8168_mac_ocp_write(tp, 0xF89C, 0x051E);
+	r8168_mac_ocp_write(tp, 0xF89E, 0xE434);
+	r8168_mac_ocp_write(tp, 0xF8A0, 0xE018);
+	r8168_mac_ocp_write(tp, 0xF8A2, 0xE092);
+	r8168_mac_ocp_write(tp, 0xF8A4, 0xDE20);
+	r8168_mac_ocp_write(tp, 0xF8A6, 0xD3C0);
+	r8168_mac_ocp_write(tp, 0xF8A8, 0xC50F);
+	r8168_mac_ocp_write(tp, 0xF8AA, 0x76A4);
+	r8168_mac_ocp_write(tp, 0xF8AC, 0x49E3);
+	r8168_mac_ocp_write(tp, 0xF8AE, 0xF007);
+	r8168_mac_ocp_write(tp, 0xF8B0, 0x49C0);
+	r8168_mac_ocp_write(tp, 0xF8B2, 0xF103);
+	r8168_mac_ocp_write(tp, 0xF8B4, 0xC607);
+	r8168_mac_ocp_write(tp, 0xF8B6, 0xBE00);
+	r8168_mac_ocp_write(tp, 0xF8B8, 0xC606);
+	r8168_mac_ocp_write(tp, 0xF8BA, 0xBE00);
+	r8168_mac_ocp_write(tp, 0xF8BC, 0xC602);
+	r8168_mac_ocp_write(tp, 0xF8BE, 0xBE00);
+	r8168_mac_ocp_write(tp, 0xF8C0, 0x0C4C);
+	r8168_mac_ocp_write(tp, 0xF8C2, 0x0C28);
+	r8168_mac_ocp_write(tp, 0xF8C4, 0x0C2C);
+	r8168_mac_ocp_write(tp, 0xF8C6, 0xDC00);
+	r8168_mac_ocp_write(tp, 0xF8C8, 0xC707);
+	r8168_mac_ocp_write(tp, 0xF8CA, 0x1D00);
+	r8168_mac_ocp_write(tp, 0xF8CC, 0x8DE2);
+	r8168_mac_ocp_write(tp, 0xF8CE, 0x48C1);
+	r8168_mac_ocp_write(tp, 0xF8D0, 0xC502);
+	r8168_mac_ocp_write(tp, 0xF8D2, 0xBD00);
+	r8168_mac_ocp_write(tp, 0xF8D4, 0x00AA);
+	r8168_mac_ocp_write(tp, 0xF8D6, 0xE0C0);
+	r8168_mac_ocp_write(tp, 0xF8D8, 0xC502);
+	r8168_mac_ocp_write(tp, 0xF8DA, 0xBD00);
+	r8168_mac_ocp_write(tp, 0xF8DC, 0x0132);
+
+	r8168_mac_ocp_write(tp, 0xFC26, 0x8000);
+
+	r8168_mac_ocp_write(tp, 0xFC2A, 0x0743);
+	r8168_mac_ocp_write(tp, 0xFC2C, 0x0801);
+	r8168_mac_ocp_write(tp, 0xFC2E, 0x0BE9);
+	r8168_mac_ocp_write(tp, 0xFC30, 0x02FD);
+	r8168_mac_ocp_write(tp, 0xFC32, 0x0C25);
+	r8168_mac_ocp_write(tp, 0xFC34, 0x00A9);
+	r8168_mac_ocp_write(tp, 0xFC36, 0x012D);
+
 	rtl_hw_aspm_clkreq_enable(tp, true);
 }
 
-- 
2.20.1


From d84b8349d4f9a95b20a1a1bfdc52f11c368f510d Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 2 Jul 2019 15:59:12 +0100
Subject: [PATCH 21/49] rxrpc: Fix send on a connected, but unbound socket

[ Upstream commit e835ada07091f40dcfb1bc735082bd0a7c005e59 ]

If sendmsg() or sendmmsg() is called on a connected socket that hasn't had
bind() called on it, then an oops will occur when the kernel tries to
connect the call because no local endpoint has been allocated.

Fix this by implicitly binding the socket if it is in the
RXRPC_CLIENT_UNBOUND state, just like it does for the RXRPC_UNBOUND state.

Further, the state should be transitioned to RXRPC_CLIENT_BOUND after this
to prevent further attempts to bind it.

This can be tested with:

	#include <stdio.h>
	#include <stdlib.h>
	#include <string.h>
	#include <sys/socket.h>
	#include <arpa/inet.h>
	#include <linux/rxrpc.h>
	static const unsigned char inet6_addr[16] = {
		0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -1, -1, 0xac, 0x14, 0x14, 0xaa
	};
	int main(void)
	{
		struct sockaddr_rxrpc srx;
		struct cmsghdr *cm;
		struct msghdr msg;
		unsigned char control[16];
		int fd;
		memset(&srx, 0, sizeof(srx));
		srx.srx_family = 0x21;
		srx.srx_service = 0;
		srx.transport_type = AF_INET;
		srx.transport_len = 0x1c;
		srx.transport.sin6.sin6_family = AF_INET6;
		srx.transport.sin6.sin6_port = htons(0x4e22);
		srx.transport.sin6.sin6_flowinfo = htons(0x4e22);
		srx.transport.sin6.sin6_scope_id = htons(0xaa3b);
		memcpy(&srx.transport.sin6.sin6_addr, inet6_addr, 16);
		cm = (struct cmsghdr *)control;
		cm->cmsg_len	= CMSG_LEN(sizeof(unsigned long));
		cm->cmsg_level	= SOL_RXRPC;
		cm->cmsg_type	= RXRPC_USER_CALL_ID;
		*(unsigned long *)CMSG_DATA(cm) = 0;
		msg.msg_name = NULL;
		msg.msg_namelen = 0;
		msg.msg_iov = NULL;
		msg.msg_iovlen = 0;
		msg.msg_control = control;
		msg.msg_controllen = cm->cmsg_len;
		msg.msg_flags = 0;
		fd = socket(AF_RXRPC, SOCK_DGRAM, AF_INET);
		connect(fd, (struct sockaddr *)&srx, sizeof(srx));
		sendmsg(fd, &msg, 0);
		return 0;
	}

Leading to the following oops:

	BUG: kernel NULL pointer dereference, address: 0000000000000018
	#PF: supervisor read access in kernel mode
	#PF: error_code(0x0000) - not-present page
	...
	RIP: 0010:rxrpc_connect_call+0x42/0xa01
	...
	Call Trace:
	 ? mark_held_locks+0x47/0x59
	 ? __local_bh_enable_ip+0xb6/0xba
	 rxrpc_new_client_call+0x3b1/0x762
	 ? rxrpc_do_sendmsg+0x3c0/0x92e
	 rxrpc_do_sendmsg+0x3c0/0x92e
	 rxrpc_sendmsg+0x16b/0x1b5
	 sock_sendmsg+0x2d/0x39
	 ___sys_sendmsg+0x1a4/0x22a
	 ? release_sock+0x19/0x9e
	 ? reacquire_held_locks+0x136/0x160
	 ? release_sock+0x19/0x9e
	 ? find_held_lock+0x2b/0x6e
	 ? __lock_acquire+0x268/0xf73
	 ? rxrpc_connect+0xdd/0xe4
	 ? __local_bh_enable_ip+0xb6/0xba
	 __sys_sendmsg+0x5e/0x94
	 do_syscall_64+0x7d/0x1bf
	 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Fixes: 2341e0775747 ("rxrpc: Simplify connect() implementation and simplify sendmsg() op")
Reported-by: syzbot+7966f2a0b2c7da8939b4@syzkaller.appspotmail.com
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Marc Dionne <marc.dionne@auristor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/af_rxrpc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index f9f4721cdfa7..d09eaf153544 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -545,6 +545,7 @@ static int rxrpc_sendmsg(struct socket *sock, struct msghdr *m, size_t len)
 
 	switch (rx->sk.sk_state) {
 	case RXRPC_UNBOUND:
+	case RXRPC_CLIENT_UNBOUND:
 		rx->srx.srx_family = AF_RXRPC;
 		rx->srx.srx_service = 0;
 		rx->srx.transport_type = SOCK_DGRAM;
@@ -569,10 +570,9 @@ static int rxrpc_sendmsg(struct socket *sock, struct msghdr *m, size_t len)
 		}
 
 		rx->local = local;
-		rx->sk.sk_state = RXRPC_CLIENT_UNBOUND;
+		rx->sk.sk_state = RXRPC_CLIENT_BOUND;
 		/* Fall through */
 
-	case RXRPC_CLIENT_UNBOUND:
 	case RXRPC_CLIENT_BOUND:
 		if (!m->msg_name &&
 		    test_bit(RXRPC_SOCK_CONNECTED, &rx->flags)) {
-- 
2.20.1


From 63f2ad06eee47480b2edece8daae07a1771b4a97 Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Thu, 27 Jun 2019 19:48:10 -0300
Subject: [PATCH 22/49] sctp: fix error handling on stream scheduler
 initialization

[ Upstream commit 4d1415811e492d9a8238f8a92dd0d51612c788e9 ]

It allocates the extended area for outbound streams only on sendmsg
calls, if they are not yet allocated.  When using the priority
stream scheduler, this initialization may imply into a subsequent
allocation, which may fail.  In this case, it was aborting the stream
scheduler initialization but leaving the ->ext pointer (allocated) in
there, thus in a partially initialized state.  On a subsequent call to
sendmsg, it would notice the ->ext pointer in there, and trip on
uninitialized stuff when trying to schedule the data chunk.

The fix is undo the ->ext initialization if the stream scheduler
initialization fails and avoid the partially initialized state.

Although syzkaller bisected this to commit 4ff40b86262b ("sctp: set
chunk transport correctly when it's a new asoc"), this bug was actually
introduced on the commit I marked below.

Reported-by: syzbot+c1a380d42b190ad1e559@syzkaller.appspotmail.com
Fixes: 5bbbbe32a431 ("sctp: introduce stream scheduler foundations")
Tested-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Neil Horman <nhorman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/stream.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index 93ed07877337..25946604af85 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -153,13 +153,20 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt,
 int sctp_stream_init_ext(struct sctp_stream *stream, __u16 sid)
 {
 	struct sctp_stream_out_ext *soute;
+	int ret;
 
 	soute = kzalloc(sizeof(*soute), GFP_KERNEL);
 	if (!soute)
 		return -ENOMEM;
 	SCTP_SO(stream, sid)->ext = soute;
 
-	return sctp_sched_init_sid(stream, sid, GFP_KERNEL);
+	ret = sctp_sched_init_sid(stream, sid, GFP_KERNEL);
+	if (ret) {
+		kfree(SCTP_SO(stream, sid)->ext);
+		SCTP_SO(stream, sid)->ext = NULL;
+	}
+
+	return ret;
 }
 
 void sctp_stream_free(struct sctp_stream *stream)
-- 
2.20.1


From 7e3583e4ecf68bb57fc61531e31d7584c4fca516 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 26 Jun 2019 16:31:39 +0800
Subject: [PATCH 23/49] sctp: not bind the socket in sctp_connect

[ Upstream commit 9b6c08878e23adb7cc84bdca94d8a944b03f099e ]

Now when sctp_connect() is called with a wrong sa_family, it binds
to a port but doesn't set bp->port, then sctp_get_af_specific will
return NULL and sctp_connect() returns -EINVAL.

Then if sctp_bind() is called to bind to another port, the last
port it has bound will leak due to bp->port is NULL by then.

sctp_connect() doesn't need to bind ports, as later __sctp_connect
will do it if bp->port is NULL. So remove it from sctp_connect().
While at it, remove the unnecessary sockaddr.sa_family len check
as it's already done in sctp_inet_connect.

Fixes: 644fbdeacf1d ("sctp: fix the issue that flags are ignored when using kernel_connect")
Reported-by: syzbot+079bf326b38072f849d9@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 24 +++---------------------
 1 file changed, 3 insertions(+), 21 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 39ea0a37af09..f33aa9ee9e27 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4816,35 +4816,17 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname,
 static int sctp_connect(struct sock *sk, struct sockaddr *addr,
 			int addr_len, int flags)
 {
-	struct inet_sock *inet = inet_sk(sk);
 	struct sctp_af *af;
-	int err = 0;
+	int err = -EINVAL;
 
 	lock_sock(sk);
-
 	pr_debug("%s: sk:%p, sockaddr:%p, addr_len:%d\n", __func__, sk,
 		 addr, addr_len);
 
-	/* We may need to bind the socket. */
-	if (!inet->inet_num) {
-		if (sk->sk_prot->get_port(sk, 0)) {
-			release_sock(sk);
-			return -EAGAIN;
-		}
-		inet->inet_sport = htons(inet->inet_num);
-	}
-
 	/* Validate addr_len before calling common connect/connectx routine. */
-	af = addr_len < offsetofend(struct sockaddr, sa_family) ? NULL :
-		sctp_get_af_specific(addr->sa_family);
-	if (!af || addr_len < af->sockaddr_len) {
-		err = -EINVAL;
-	} else {
-		/* Pass correct addr len to common routine (so it knows there
-		 * is only one address being passed.
-		 */
+	af = sctp_get_af_specific(addr->sa_family);
+	if (af && addr_len >= af->sockaddr_len)
 		err = __sctp_connect(sk, addr, af->sockaddr_len, flags, NULL);
-	}
 
 	release_sock(sk);
 	return err;
-- 
2.20.1


From c354754dd9b3bc60ab12b9682fca70c4ccad8930 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 23 Jul 2019 17:15:25 +0200
Subject: [PATCH 24/49] sky2: Disable MSI on ASUS P6T

[ Upstream commit a261e3797506bd561700be643fe1a85bf81e9661 ]

The onboard sky2 NIC on ASUS P6T WS PRO doesn't work after PM resume
due to the infamous IRQ problem.  Disabling MSI works around it, so
let's add it to the blacklist.

Unfortunately the BIOS on the machine doesn't fill the standard
DMI_SYS_* entry, so we pick up DMI_BOARD_* entries instead.

BugLink: https://bugzilla.suse.com/show_bug.cgi?id=1142496
Reported-and-tested-by: Marcus Seyfarth <m.seyfarth@gmail.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/sky2.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index fe518c854d1f..c93a6f9b735b 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -4917,6 +4917,13 @@ static const struct dmi_system_id msi_blacklist[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "P-79"),
 		},
 	},
+	{
+		.ident = "ASUS P6T",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."),
+			DMI_MATCH(DMI_BOARD_NAME, "P6T"),
+		},
+	},
 	{}
 };
 
-- 
2.20.1


From 7a07b933c20347a3ec45ea099dc96aaf665566e2 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 19 Jul 2019 11:52:33 -0700
Subject: [PATCH 25/49] tcp: be more careful in tcp_fragment()

[ Upstream commit b617158dc096709d8600c53b6052144d12b89fab ]

Some applications set tiny SO_SNDBUF values and expect
TCP to just work. Recent patches to address CVE-2019-11478
broke them in case of losses, since retransmits might
be prevented.

We should allow these flows to make progress.

This patch allows the first and last skb in retransmit queue
to be split even if memory limits are hit.

It also adds the some room due to the fact that tcp_sendmsg()
and tcp_sendpage() might overshoot sk_wmem_queued by about one full
TSO skb (64KB size). Note this allowance was already present
in stable backports for kernels < 4.15

Note for < 4.15 backports :
 tcp_rtx_queue_tail() will probably look like :

static inline struct sk_buff *tcp_rtx_queue_tail(const struct sock *sk)
{
	struct sk_buff *skb = tcp_send_head(sk);

	return skb ? tcp_write_queue_prev(sk, skb) : tcp_write_queue_tail(sk);
}

Fixes: f070ef2ac667 ("tcp: tcp_fragment() should apply sane memory limits")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrew Prout <aprout@ll.mit.edu>
Tested-by: Andrew Prout <aprout@ll.mit.edu>
Tested-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Tested-by: Michal Kubecek <mkubecek@suse.cz>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Christoph Paasch <cpaasch@apple.com>
Cc: Jonathan Looney <jtl@netflix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h     |  5 +++++
 net/ipv4/tcp_output.c | 13 +++++++++++--
 2 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 582c0caa9811..dd8e472362e3 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1675,6 +1675,11 @@ static inline struct sk_buff *tcp_rtx_queue_head(const struct sock *sk)
 	return skb_rb_first(&sk->tcp_rtx_queue);
 }
 
+static inline struct sk_buff *tcp_rtx_queue_tail(const struct sock *sk)
+{
+	return skb_rb_last(&sk->tcp_rtx_queue);
+}
+
 static inline struct sk_buff *tcp_write_queue_head(const struct sock *sk)
 {
 	return skb_peek(&sk->sk_write_queue);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 0ebc33d1c9e5..7d0be046cbc1 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1286,6 +1286,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *buff;
 	int nsize, old_factor;
+	long limit;
 	int nlen;
 	u8 flags;
 
@@ -1296,8 +1297,16 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
 	if (nsize < 0)
 		nsize = 0;
 
-	if (unlikely((sk->sk_wmem_queued >> 1) > sk->sk_sndbuf &&
-		     tcp_queue != TCP_FRAG_IN_WRITE_QUEUE)) {
+	/* tcp_sendmsg() can overshoot sk_wmem_queued by one full size skb.
+	 * We need some allowance to not penalize applications setting small
+	 * SO_SNDBUF values.
+	 * Also allow first and last skb in retransmit queue to be split.
+	 */
+	limit = sk->sk_sndbuf + 2 * SKB_TRUESIZE(GSO_MAX_SIZE);
+	if (unlikely((sk->sk_wmem_queued >> 1) > limit &&
+		     tcp_queue != TCP_FRAG_IN_WRITE_QUEUE &&
+		     skb != tcp_rtx_queue_head(sk) &&
+		     skb != tcp_rtx_queue_tail(sk))) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPWQUEUETOOBIG);
 		return -ENOMEM;
 	}
-- 
2.20.1


From be94698eae7091145cddccee326c563700c2d792 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 18 Jul 2019 19:28:14 -0700
Subject: [PATCH 26/49] tcp: fix tcp_set_congestion_control() use from bpf hook

[ Upstream commit 8d650cdedaabb33e85e9b7c517c0c71fcecc1de9 ]

Neal reported incorrect use of ns_capable() from bpf hook.

bpf_setsockopt(...TCP_CONGESTION...)
  -> tcp_set_congestion_control()
   -> ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)
    -> ns_capable_common()
     -> current_cred()
      -> rcu_dereference_protected(current->cred, 1)

Accessing 'current' in bpf context makes no sense, since packets
are processed from softirq context.

As Neal stated : The capability check in tcp_set_congestion_control()
was written assuming a system call context, and then was reused from
a BPF call site.

The fix is to add a new parameter to tcp_set_congestion_control(),
so that the ns_capable() call is only performed under the right
context.

Fixes: 91b5b21c7c16 ("bpf: Add support for changing congestion control")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Lawrence Brakmo <brakmo@fb.com>
Reported-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Lawrence Brakmo <brakmo@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h   | 3 ++-
 net/core/filter.c   | 2 +-
 net/ipv4/tcp.c      | 4 +++-
 net/ipv4/tcp_cong.c | 6 +++---
 4 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index dd8e472362e3..2ee06191c488 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1063,7 +1063,8 @@ void tcp_get_default_congestion_control(struct net *net, char *name);
 void tcp_get_available_congestion_control(char *buf, size_t len);
 void tcp_get_allowed_congestion_control(char *buf, size_t len);
 int tcp_set_allowed_congestion_control(char *allowed);
-int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, bool reinit);
+int tcp_set_congestion_control(struct sock *sk, const char *name, bool load,
+			       bool reinit, bool cap_net_admin);
 u32 tcp_slow_start(struct tcp_sock *tp, u32 acked);
 void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked);
 
diff --git a/net/core/filter.c b/net/core/filter.c
index f615e42cf4ef..f681fb772940 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4332,7 +4332,7 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 						    TCP_CA_NAME_MAX-1));
 			name[TCP_CA_NAME_MAX-1] = 0;
 			ret = tcp_set_congestion_control(sk, name, false,
-							 reinit);
+							 reinit, true);
 		} else {
 			struct tcp_sock *tp = tcp_sk(sk);
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 7dc9ab84bb69..7df8744ee88f 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2768,7 +2768,9 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		name[val] = 0;
 
 		lock_sock(sk);
-		err = tcp_set_congestion_control(sk, name, true, true);
+		err = tcp_set_congestion_control(sk, name, true, true,
+						 ns_capable(sock_net(sk)->user_ns,
+							    CAP_NET_ADMIN));
 		release_sock(sk);
 		return err;
 	}
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index e1862b64a90f..c445a81d144e 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -333,7 +333,8 @@ int tcp_set_allowed_congestion_control(char *val)
  * tcp_reinit_congestion_control (if the current congestion control was
  * already initialized.
  */
-int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, bool reinit)
+int tcp_set_congestion_control(struct sock *sk, const char *name, bool load,
+			       bool reinit, bool cap_net_admin)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	const struct tcp_congestion_ops *ca;
@@ -369,8 +370,7 @@ int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, boo
 		} else {
 			err = -EBUSY;
 		}
-	} else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) ||
-		     ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))) {
+	} else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || cap_net_admin)) {
 		err = -EPERM;
 	} else if (!try_module_get(ca->owner)) {
 		err = -EBUSY;
-- 
2.20.1


From cade934746d4629191a3d90b03782ee671cd3891 Mon Sep 17 00:00:00 2001
From: Christoph Paasch <cpaasch@apple.com>
Date: Sat, 6 Jul 2019 16:13:07 -0700
Subject: [PATCH 27/49] tcp: Reset bytes_acked and bytes_received when
 disconnecting

[ Upstream commit e858faf556d4e14c750ba1e8852783c6f9520a0e ]

If an app is playing tricks to reuse a socket via tcp_disconnect(),
bytes_acked/received needs to be reset to 0. Otherwise tcp_info will
report the sum of the current and the old connection..

Cc: Eric Dumazet <edumazet@google.com>
Fixes: 0df48c26d841 ("tcp: add tcpi_bytes_acked to tcp_info")
Fixes: bdd1f9edacb5 ("tcp: add tcpi_bytes_received to tcp_info")
Signed-off-by: Christoph Paasch <cpaasch@apple.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 7df8744ee88f..5264f064a87e 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2614,6 +2614,8 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tcp_saved_syn_free(tp);
 	tp->compressed_ack = 0;
 	tp->bytes_sent = 0;
+	tp->bytes_acked = 0;
+	tp->bytes_received = 0;
 	tp->bytes_retrans = 0;
 	tp->duplicate_sack[0].start_seq = 0;
 	tp->duplicate_sack[0].end_seq = 0;
-- 
2.20.1


From 10bb08001c609e04870208eec6927f975114ec6c Mon Sep 17 00:00:00 2001
From: Peter Kosyh <p.kosyh@gmail.com>
Date: Fri, 19 Jul 2019 11:11:47 +0300
Subject: [PATCH 28/49] vrf: make sure skb->data contains ip header to make
 routing

[ Upstream commit 107e47cc80ec37cb332bd41b22b1c7779e22e018 ]

vrf_process_v4_outbound() and vrf_process_v6_outbound() do routing
using ip/ipv6 addresses, but don't make sure the header is available
in skb->data[] (skb_headlen() is less then header size).

Case:

1) igb driver from intel.
2) Packet size is greater then 255.
3) MPLS forwards to VRF device.

So, patch adds pskb_may_pull() calls in vrf_process_v4/v6_outbound()
functions.

Signed-off-by: Peter Kosyh <p.kosyh@gmail.com>
Reviewed-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 58 ++++++++++++++++++++++++++++-------------------
 1 file changed, 35 insertions(+), 23 deletions(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 311b0cc6eb98..97fb0cb1b97a 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -165,23 +165,29 @@ static int vrf_ip6_local_out(struct net *net, struct sock *sk,
 static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
 					   struct net_device *dev)
 {
-	const struct ipv6hdr *iph = ipv6_hdr(skb);
+	const struct ipv6hdr *iph;
 	struct net *net = dev_net(skb->dev);
-	struct flowi6 fl6 = {
-		/* needed to match OIF rule */
-		.flowi6_oif = dev->ifindex,
-		.flowi6_iif = LOOPBACK_IFINDEX,
-		.daddr = iph->daddr,
-		.saddr = iph->saddr,
-		.flowlabel = ip6_flowinfo(iph),
-		.flowi6_mark = skb->mark,
-		.flowi6_proto = iph->nexthdr,
-		.flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF,
-	};
+	struct flowi6 fl6;
 	int ret = NET_XMIT_DROP;
 	struct dst_entry *dst;
 	struct dst_entry *dst_null = &net->ipv6.ip6_null_entry->dst;
 
+	if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct ipv6hdr)))
+		goto err;
+
+	iph = ipv6_hdr(skb);
+
+	memset(&fl6, 0, sizeof(fl6));
+	/* needed to match OIF rule */
+	fl6.flowi6_oif = dev->ifindex;
+	fl6.flowi6_iif = LOOPBACK_IFINDEX;
+	fl6.daddr = iph->daddr;
+	fl6.saddr = iph->saddr;
+	fl6.flowlabel = ip6_flowinfo(iph);
+	fl6.flowi6_mark = skb->mark;
+	fl6.flowi6_proto = iph->nexthdr;
+	fl6.flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF;
+
 	dst = ip6_route_output(net, NULL, &fl6);
 	if (dst == dst_null)
 		goto err;
@@ -237,21 +243,27 @@ static int vrf_ip_local_out(struct net *net, struct sock *sk,
 static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb,
 					   struct net_device *vrf_dev)
 {
-	struct iphdr *ip4h = ip_hdr(skb);
+	struct iphdr *ip4h;
 	int ret = NET_XMIT_DROP;
-	struct flowi4 fl4 = {
-		/* needed to match OIF rule */
-		.flowi4_oif = vrf_dev->ifindex,
-		.flowi4_iif = LOOPBACK_IFINDEX,
-		.flowi4_tos = RT_TOS(ip4h->tos),
-		.flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_SKIP_NH_OIF,
-		.flowi4_proto = ip4h->protocol,
-		.daddr = ip4h->daddr,
-		.saddr = ip4h->saddr,
-	};
+	struct flowi4 fl4;
 	struct net *net = dev_net(vrf_dev);
 	struct rtable *rt;
 
+	if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct iphdr)))
+		goto err;
+
+	ip4h = ip_hdr(skb);
+
+	memset(&fl4, 0, sizeof(fl4));
+	/* needed to match OIF rule */
+	fl4.flowi4_oif = vrf_dev->ifindex;
+	fl4.flowi4_iif = LOOPBACK_IFINDEX;
+	fl4.flowi4_tos = RT_TOS(ip4h->tos);
+	fl4.flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_SKIP_NH_OIF;
+	fl4.flowi4_proto = ip4h->protocol;
+	fl4.daddr = ip4h->daddr;
+	fl4.saddr = ip4h->saddr;
+
 	rt = ip_route_output_flow(net, &fl4, NULL);
 	if (IS_ERR(rt))
 		goto err;
-- 
2.20.1


From 9600457062900f30ddb4be80d7d099da239ea4e1 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Fri, 28 Jun 2019 14:07:25 +0900
Subject: [PATCH 29/49] vxlan: do not destroy fdb if register_netdevice() is
 failed

[ Upstream commit 7c31e54aeee517d1318dfc0bde9fa7de75893dc6 ]

__vxlan_dev_create() destroys FDB using specific pointer which indicates
a fdb when error occurs.
But that pointer should not be used when register_netdevice() fails because
register_netdevice() internally destroys fdb when error occurs.

This patch makes vxlan_fdb_create() to do not link fdb entry to vxlan dev
internally.
Instead, a new function vxlan_fdb_insert() is added to link fdb to vxlan
dev.

vxlan_fdb_insert() is called after calling register_netdevice().
This routine can avoid situation that ->ndo_uninit() destroys fdb entry
in error path of register_netdevice().
Hence, error path of __vxlan_dev_create() routine can have an opportunity
to destroy default fdb entry by hand.

Test command
    ip link add bonding_masters type vxlan id 0 group 239.1.1.1 \
	    dev enp0s9 dstport 4789

Splat looks like:
[  213.392816] kasan: GPF could be caused by NULL-ptr deref or user memory access
[  213.401257] general protection fault: 0000 [#1] SMP DEBUG_PAGEALLOC KASAN PTI
[  213.402178] CPU: 0 PID: 1414 Comm: ip Not tainted 5.2.0-rc5+ #256
[  213.402178] RIP: 0010:vxlan_fdb_destroy+0x120/0x220 [vxlan]
[  213.402178] Code: df 48 8b 2b 48 89 fa 48 c1 ea 03 80 3c 02 00 0f 85 06 01 00 00 4c 8b 63 08 48 b8 00 00 00 00 00 fc d
[  213.402178] RSP: 0018:ffff88810cb9f0a0 EFLAGS: 00010202
[  213.402178] RAX: dffffc0000000000 RBX: ffff888101d4a8c8 RCX: 0000000000000000
[  213.402178] RDX: 1bd5a00000000040 RSI: ffff888101d4a8c8 RDI: ffff888101d4a8d0
[  213.402178] RBP: 0000000000000000 R08: fffffbfff22b72d9 R09: 0000000000000000
[  213.402178] R10: 00000000ffffffef R11: 0000000000000000 R12: dead000000000200
[  213.402178] R13: ffff88810cb9f1f8 R14: ffff88810efccda0 R15: ffff88810efccda0
[  213.402178] FS:  00007f7f6621a0c0(0000) GS:ffff88811b000000(0000) knlGS:0000000000000000
[  213.402178] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  213.402178] CR2: 000055746f0807d0 CR3: 00000001123e0000 CR4: 00000000001006f0
[  213.402178] Call Trace:
[  213.402178]  __vxlan_dev_create+0x3a9/0x7d0 [vxlan]
[  213.402178]  ? vxlan_changelink+0x740/0x740 [vxlan]
[  213.402178]  ? rcu_read_unlock+0x60/0x60 [vxlan]
[  213.402178]  ? __kasan_kmalloc.constprop.3+0xa0/0xd0
[  213.402178]  vxlan_newlink+0x8d/0xc0 [vxlan]
[  213.402178]  ? __vxlan_dev_create+0x7d0/0x7d0 [vxlan]
[  213.554119]  ? __netlink_ns_capable+0xc3/0xf0
[  213.554119]  __rtnl_newlink+0xb75/0x1180
[  213.554119]  ? rtnl_link_unregister+0x230/0x230
[ ... ]

Fixes: 0241b836732f ("vxlan: fix default fdb entry netlink notify ordering during netdev create")
Suggested-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Acked-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 37 +++++++++++++++++++++++++++----------
 1 file changed, 27 insertions(+), 10 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 083f3f0bf37f..b4283f52a09d 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -804,6 +804,14 @@ static struct vxlan_fdb *vxlan_fdb_alloc(struct vxlan_dev *vxlan,
 	return f;
 }
 
+static void vxlan_fdb_insert(struct vxlan_dev *vxlan, const u8 *mac,
+			     __be32 src_vni, struct vxlan_fdb *f)
+{
+	++vxlan->addrcnt;
+	hlist_add_head_rcu(&f->hlist,
+			   vxlan_fdb_head(vxlan, mac, src_vni));
+}
+
 static int vxlan_fdb_create(struct vxlan_dev *vxlan,
 			    const u8 *mac, union vxlan_addr *ip,
 			    __u16 state, __be16 port, __be32 src_vni,
@@ -829,18 +837,13 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan,
 		return rc;
 	}
 
-	++vxlan->addrcnt;
-	hlist_add_head_rcu(&f->hlist,
-			   vxlan_fdb_head(vxlan, mac, src_vni));
-
 	*fdb = f;
 
 	return 0;
 }
 
-static void vxlan_fdb_free(struct rcu_head *head)
+static void __vxlan_fdb_free(struct vxlan_fdb *f)
 {
-	struct vxlan_fdb *f = container_of(head, struct vxlan_fdb, rcu);
 	struct vxlan_rdst *rd, *nd;
 
 	list_for_each_entry_safe(rd, nd, &f->remotes, list) {
@@ -850,6 +853,13 @@ static void vxlan_fdb_free(struct rcu_head *head)
 	kfree(f);
 }
 
+static void vxlan_fdb_free(struct rcu_head *head)
+{
+	struct vxlan_fdb *f = container_of(head, struct vxlan_fdb, rcu);
+
+	__vxlan_fdb_free(f);
+}
+
 static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f,
 			      bool do_notify, bool swdev_notify)
 {
@@ -977,6 +987,7 @@ static int vxlan_fdb_update_create(struct vxlan_dev *vxlan,
 	if (rc < 0)
 		return rc;
 
+	vxlan_fdb_insert(vxlan, mac, src_vni, f);
 	rc = vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH,
 			      swdev_notify, extack);
 	if (rc)
@@ -3571,12 +3582,17 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev,
 	if (err)
 		goto errout;
 
-	/* notify default fdb entry */
 	if (f) {
+		vxlan_fdb_insert(vxlan, all_zeros_mac,
+				 vxlan->default_dst.remote_vni, f);
+
+		/* notify default fdb entry */
 		err = vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f),
 				       RTM_NEWNEIGH, true, extack);
-		if (err)
-			goto errout;
+		if (err) {
+			vxlan_fdb_destroy(vxlan, f, false, false);
+			goto unregister;
+		}
 	}
 
 	list_add(&vxlan->next, &vn->vxlan_list);
@@ -3588,7 +3604,8 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev,
 	 * destroy the entry by hand here.
 	 */
 	if (f)
-		vxlan_fdb_destroy(vxlan, f, false, false);
+		__vxlan_fdb_free(f);
+unregister:
 	if (unregister)
 		unregister_netdevice(dev);
 	return err;
-- 
2.20.1


From e18575a2a8f9b1b857e97b0e69e60b26ce6ca745 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Sun, 7 Jul 2019 16:57:06 +0300
Subject: [PATCH 30/49] net/mlx5e: IPoIB, Add error path in mlx5_rdma_setup_rn

[ Upstream commit ef1ce7d7b67b46661091c7ccc0396186b7a247ef ]

Check return value from mlx5e_attach_netdev, add error path on failure.

Fixes: 48935bbb7ae8 ("net/mlx5e: IPoIB, Add netdevice profile skeleton")
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Feras Daoud <ferasda@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 9ca492b430d8..603d294757b4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -698,7 +698,9 @@ static int mlx5_rdma_setup_rn(struct ib_device *ibdev, u8 port_num,
 
 	prof->init(mdev, netdev, prof, ipriv);
 
-	mlx5e_attach_netdev(epriv);
+	err = mlx5e_attach_netdev(epriv);
+	if (err)
+		goto detach;
 	netif_carrier_off(netdev);
 
 	/* set rdma_netdev func pointers */
@@ -714,6 +716,11 @@ static int mlx5_rdma_setup_rn(struct ib_device *ibdev, u8 port_num,
 
 	return 0;
 
+detach:
+	prof->cleanup(epriv);
+	if (ipriv->sub_interface)
+		return err;
+	mlx5e_destroy_mdev_resources(mdev);
 destroy_ht:
 	mlx5i_pkey_qpn_ht_cleanup(netdev);
 	return err;
-- 
2.20.1


From a679f1a1f082ccea7d157bc364896ed1735a8bd5 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Tue, 2 Jul 2019 15:00:18 +0300
Subject: [PATCH 31/49] net: bridge: mcast: fix stale nsrcs pointer in
 igmp3/mld2 report handling

[ Upstream commit e57f61858b7cf478ed6fa23ed4b3876b1c9625c4 ]

We take a pointer to grec prior to calling pskb_may_pull and use it
afterwards to get nsrcs so record nsrcs before the pull when handling
igmp3 and we get a pointer to nsrcs and call pskb_may_pull when handling
mld2 which again could lead to reading 2 bytes out-of-bounds.

 ==================================================================
 BUG: KASAN: use-after-free in br_multicast_rcv+0x480c/0x4ad0 [bridge]
 Read of size 2 at addr ffff8880421302b4 by task ksoftirqd/1/16

 CPU: 1 PID: 16 Comm: ksoftirqd/1 Tainted: G           OE     5.2.0-rc6+ #1
 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014
 Call Trace:
  dump_stack+0x71/0xab
  print_address_description+0x6a/0x280
  ? br_multicast_rcv+0x480c/0x4ad0 [bridge]
  __kasan_report+0x152/0x1aa
  ? br_multicast_rcv+0x480c/0x4ad0 [bridge]
  ? br_multicast_rcv+0x480c/0x4ad0 [bridge]
  kasan_report+0xe/0x20
  br_multicast_rcv+0x480c/0x4ad0 [bridge]
  ? br_multicast_disable_port+0x150/0x150 [bridge]
  ? ktime_get_with_offset+0xb4/0x150
  ? __kasan_kmalloc.constprop.6+0xa6/0xf0
  ? __netif_receive_skb+0x1b0/0x1b0
  ? br_fdb_update+0x10e/0x6e0 [bridge]
  ? br_handle_frame_finish+0x3c6/0x11d0 [bridge]
  br_handle_frame_finish+0x3c6/0x11d0 [bridge]
  ? br_pass_frame_up+0x3a0/0x3a0 [bridge]
  ? virtnet_probe+0x1c80/0x1c80 [virtio_net]
  br_handle_frame+0x731/0xd90 [bridge]
  ? select_idle_sibling+0x25/0x7d0
  ? br_handle_frame_finish+0x11d0/0x11d0 [bridge]
  __netif_receive_skb_core+0xced/0x2d70
  ? virtqueue_get_buf_ctx+0x230/0x1130 [virtio_ring]
  ? do_xdp_generic+0x20/0x20
  ? virtqueue_napi_complete+0x39/0x70 [virtio_net]
  ? virtnet_poll+0x94d/0xc78 [virtio_net]
  ? receive_buf+0x5120/0x5120 [virtio_net]
  ? __netif_receive_skb_one_core+0x97/0x1d0
  __netif_receive_skb_one_core+0x97/0x1d0
  ? __netif_receive_skb_core+0x2d70/0x2d70
  ? _raw_write_trylock+0x100/0x100
  ? __queue_work+0x41e/0xbe0
  process_backlog+0x19c/0x650
  ? _raw_read_lock_irq+0x40/0x40
  net_rx_action+0x71e/0xbc0
  ? __switch_to_asm+0x40/0x70
  ? napi_complete_done+0x360/0x360
  ? __switch_to_asm+0x34/0x70
  ? __switch_to_asm+0x40/0x70
  ? __schedule+0x85e/0x14d0
  __do_softirq+0x1db/0x5f9
  ? takeover_tasklets+0x5f0/0x5f0
  run_ksoftirqd+0x26/0x40
  smpboot_thread_fn+0x443/0x680
  ? sort_range+0x20/0x20
  ? schedule+0x94/0x210
  ? __kthread_parkme+0x78/0xf0
  ? sort_range+0x20/0x20
  kthread+0x2ae/0x3a0
  ? kthread_create_worker_on_cpu+0xc0/0xc0
  ret_from_fork+0x35/0x40

 The buggy address belongs to the page:
 page:ffffea0001084c00 refcount:0 mapcount:-128 mapping:0000000000000000 index:0x0
 flags: 0xffffc000000000()
 raw: 00ffffc000000000 ffffea0000cfca08 ffffea0001098608 0000000000000000
 raw: 0000000000000000 0000000000000003 00000000ffffff7f 0000000000000000
 page dumped because: kasan: bad access detected

 Memory state around the buggy address:
 ffff888042130180: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
 ffff888042130200: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
 > ffff888042130280: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
                                     ^
 ffff888042130300: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
 ffff888042130380: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
 ==================================================================
 Disabling lock debugging due to kernel taint

Fixes: bc8c20acaea1 ("bridge: multicast: treat igmpv3 report with INCLUDE and no sources as a leave")
Reported-by: Martin Weinelt <martin@linuxlounge.net>
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Tested-by: Martin Weinelt <martin@linuxlounge.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index de22c8fbbb15..f37897e7b97b 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -911,6 +911,7 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br,
 	int type;
 	int err = 0;
 	__be32 group;
+	u16 nsrcs;
 
 	ih = igmpv3_report_hdr(skb);
 	num = ntohs(ih->ngrec);
@@ -924,8 +925,9 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br,
 		grec = (void *)(skb->data + len - sizeof(*grec));
 		group = grec->grec_mca;
 		type = grec->grec_type;
+		nsrcs = ntohs(grec->grec_nsrcs);
 
-		len += ntohs(grec->grec_nsrcs) * 4;
+		len += nsrcs * 4;
 		if (!ip_mc_may_pull(skb, len))
 			return -EINVAL;
 
@@ -946,7 +948,7 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br,
 		src = eth_hdr(skb)->h_source;
 		if ((type == IGMPV3_CHANGE_TO_INCLUDE ||
 		     type == IGMPV3_MODE_IS_INCLUDE) &&
-		    ntohs(grec->grec_nsrcs) == 0) {
+		    nsrcs == 0) {
 			br_ip4_multicast_leave_group(br, port, group, vid, src);
 		} else {
 			err = br_ip4_multicast_add_group(br, port, group, vid,
@@ -983,7 +985,8 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br,
 	len = skb_transport_offset(skb) + sizeof(*icmp6h);
 
 	for (i = 0; i < num; i++) {
-		__be16 *nsrcs, _nsrcs;
+		__be16 *_nsrcs, __nsrcs;
+		u16 nsrcs;
 
 		nsrcs_offset = len + offsetof(struct mld2_grec, grec_nsrcs);
 
@@ -991,12 +994,13 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br,
 		    nsrcs_offset + sizeof(_nsrcs))
 			return -EINVAL;
 
-		nsrcs = skb_header_pointer(skb, nsrcs_offset,
-					   sizeof(_nsrcs), &_nsrcs);
-		if (!nsrcs)
+		_nsrcs = skb_header_pointer(skb, nsrcs_offset,
+					    sizeof(__nsrcs), &__nsrcs);
+		if (!_nsrcs)
 			return -EINVAL;
 
-		grec_len = struct_size(grec, grec_src, ntohs(*nsrcs));
+		nsrcs = ntohs(*_nsrcs);
+		grec_len = struct_size(grec, grec_src, nsrcs);
 
 		if (!ipv6_mc_may_pull(skb, len + grec_len))
 			return -EINVAL;
@@ -1021,7 +1025,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br,
 		src = eth_hdr(skb)->h_source;
 		if ((grec->grec_type == MLD2_CHANGE_TO_INCLUDE ||
 		     grec->grec_type == MLD2_MODE_IS_INCLUDE) &&
-		    ntohs(*nsrcs) == 0) {
+		    nsrcs == 0) {
 			br_ip6_multicast_leave_group(br, port, &grec->grec_mca,
 						     vid, src);
 		} else {
-- 
2.20.1


From 7d3318ce3d8bd0732f35e6971b790b49299d330c Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Tue, 2 Jul 2019 15:00:19 +0300
Subject: [PATCH 32/49] net: bridge: mcast: fix stale ipv6 hdr pointer when
 handling v6 query

[ Upstream commit 3b26a5d03d35d8f732d75951218983c0f7f68dff ]

We get a pointer to the ipv6 hdr in br_ip6_multicast_query but we may
call pskb_may_pull afterwards and end up using a stale pointer.
So use the header directly, it's just 1 place where it's needed.

Fixes: 08b202b67264 ("bridge br_multicast: IPv6 MLD support.")
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Tested-by: Martin Weinelt <martin@linuxlounge.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index f37897e7b97b..3d8deac2353d 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1279,7 +1279,6 @@ static int br_ip6_multicast_query(struct net_bridge *br,
 				  u16 vid)
 {
 	unsigned int transport_len = ipv6_transport_len(skb);
-	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
 	struct mld_msg *mld;
 	struct net_bridge_mdb_entry *mp;
 	struct mld2_query *mld2q;
@@ -1323,7 +1322,7 @@ static int br_ip6_multicast_query(struct net_bridge *br,
 
 	if (is_general_query) {
 		saddr.proto = htons(ETH_P_IPV6);
-		saddr.u.ip6 = ip6h->saddr;
+		saddr.u.ip6 = ipv6_hdr(skb)->saddr;
 
 		br_multicast_query_received(br, port, &br->ip6_other_query,
 					    &saddr, max_delay);
-- 
2.20.1


From 19f33959e7e656ef8d5bbdb76a28328ff46504a7 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Tue, 2 Jul 2019 15:00:20 +0300
Subject: [PATCH 33/49] net: bridge: don't cache ether dest pointer on input

[ Upstream commit 3d26eb8ad1e9b906433903ce05f775cf038e747f ]

We would cache ether dst pointer on input in br_handle_frame_finish but
after the neigh suppress code that could lead to a stale pointer since
both ipv4 and ipv6 suppress code do pskb_may_pull. This means we have to
always reload it after the suppress code so there's no point in having
it cached just retrieve it directly.

Fixes: 057658cb33fbf ("bridge: suppress arp pkts on BR_NEIGH_SUPPRESS ports")
Fixes: ed842faeb2bd ("bridge: suppress nd pkts on BR_NEIGH_SUPPRESS ports")
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_input.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 21b74e7a7b2f..52c712984cc7 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -74,7 +74,6 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
 	struct net_bridge_fdb_entry *dst = NULL;
 	struct net_bridge_mdb_entry *mdst;
 	bool local_rcv, mcast_hit = false;
-	const unsigned char *dest;
 	struct net_bridge *br;
 	u16 vid = 0;
 
@@ -92,10 +91,9 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
 		br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, false);
 
 	local_rcv = !!(br->dev->flags & IFF_PROMISC);
-	dest = eth_hdr(skb)->h_dest;
-	if (is_multicast_ether_addr(dest)) {
+	if (is_multicast_ether_addr(eth_hdr(skb)->h_dest)) {
 		/* by definition the broadcast is also a multicast address */
-		if (is_broadcast_ether_addr(dest)) {
+		if (is_broadcast_ether_addr(eth_hdr(skb)->h_dest)) {
 			pkt_type = BR_PKT_BROADCAST;
 			local_rcv = true;
 		} else {
@@ -145,7 +143,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
 		}
 		break;
 	case BR_PKT_UNICAST:
-		dst = br_fdb_find_rcu(br, dest, vid);
+		dst = br_fdb_find_rcu(br, eth_hdr(skb)->h_dest, vid);
 	default:
 		break;
 	}
-- 
2.20.1


From a8255630616715375c3143a0765d6779d36a3b74 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Tue, 2 Jul 2019 15:00:21 +0300
Subject: [PATCH 34/49] net: bridge: stp: don't cache eth dest pointer before
 skb pull

[ Upstream commit 2446a68ae6a8cee6d480e2f5b52f5007c7c41312 ]

Don't cache eth dest pointer before calling pskb_may_pull.

Fixes: cf0f02d04a83 ("[BRIDGE]: use llc for receiving STP packets")
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_stp_bpdu.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/bridge/br_stp_bpdu.c b/net/bridge/br_stp_bpdu.c
index 68a6922b4141..7796dd9d42d7 100644
--- a/net/bridge/br_stp_bpdu.c
+++ b/net/bridge/br_stp_bpdu.c
@@ -143,7 +143,6 @@ void br_send_tcn_bpdu(struct net_bridge_port *p)
 void br_stp_rcv(const struct stp_proto *proto, struct sk_buff *skb,
 		struct net_device *dev)
 {
-	const unsigned char *dest = eth_hdr(skb)->h_dest;
 	struct net_bridge_port *p;
 	struct net_bridge *br;
 	const unsigned char *buf;
@@ -172,7 +171,7 @@ void br_stp_rcv(const struct stp_proto *proto, struct sk_buff *skb,
 	if (p->state == BR_STATE_DISABLED)
 		goto out;
 
-	if (!ether_addr_equal(dest, br->group_addr))
+	if (!ether_addr_equal(eth_hdr(skb)->h_dest, br->group_addr))
 		goto out;
 
 	if (p->flags & BR_BPDU_GUARD) {
-- 
2.20.1


From e4921e4335008edd17a74d2c5e8a44309f8858e0 Mon Sep 17 00:00:00 2001
From: Andreas Steinmetz <ast@domdv.de>
Date: Sun, 30 Jun 2019 22:46:42 +0200
Subject: [PATCH 35/49] macsec: fix use-after-free of skb during RX

[ Upstream commit 095c02da80a41cf6d311c504d8955d6d1c2add10 ]

Fix use-after-free of skb when rx_handler returns RX_HANDLER_PASS.

Signed-off-by: Andreas Steinmetz <ast@domdv.de>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macsec.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 75aebf65cd09..8ec73d677123 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -1099,10 +1099,9 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb)
 	}
 
 	skb = skb_unshare(skb, GFP_ATOMIC);
-	if (!skb) {
-		*pskb = NULL;
+	*pskb = skb;
+	if (!skb)
 		return RX_HANDLER_CONSUMED;
-	}
 
 	pulled_sci = pskb_may_pull(skb, macsec_extra_len(true));
 	if (!pulled_sci) {
-- 
2.20.1


From f24a4162afe9ecb6b762403baa572032acc4e769 Mon Sep 17 00:00:00 2001
From: Andreas Steinmetz <ast@domdv.de>
Date: Sun, 30 Jun 2019 22:46:45 +0200
Subject: [PATCH 36/49] macsec: fix checksumming after decryption

[ Upstream commit 7d8b16b9facb0dd81d1469808dd9a575fa1d525a ]

Fix checksumming after decryption.

Signed-off-by: Andreas Steinmetz <ast@domdv.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macsec.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 8ec73d677123..8f46aa1ddec0 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -865,6 +865,7 @@ static void macsec_reset_skb(struct sk_buff *skb, struct net_device *dev)
 
 static void macsec_finalize_skb(struct sk_buff *skb, u8 icv_len, u8 hdr_len)
 {
+	skb->ip_summed = CHECKSUM_NONE;
 	memmove(skb->data + hdr_len, skb->data, 2 * ETH_ALEN);
 	skb_pull(skb, hdr_len);
 	pskb_trim_unique(skb, skb->len - icv_len);
-- 
2.20.1


From 7d5631cb3a675c22e5e5483e29c08647a2af4c41 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 27 Jun 2019 14:30:58 -0700
Subject: [PATCH 37/49] netrom: fix a memory leak in nr_rx_frame()

[ Upstream commit c8c8218ec5af5d2598381883acbefbf604e56b5e ]

When the skb is associated with a new sock, just assigning
it to skb->sk is not sufficient, we have to set its destructor
to free the sock properly too.

Reported-by: syzbot+d6636a36d3c34bd88938@syzkaller.appspotmail.com
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netrom/af_netrom.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 86b87925ef34..96740d389377 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -869,7 +869,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev)
 	unsigned short frametype, flags, window, timeout;
 	int ret;
 
-	skb->sk = NULL;		/* Initially we don't know who it's for */
+	skb_orphan(skb);
 
 	/*
 	 *	skb->data points to the netrom frame start
@@ -968,6 +968,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev)
 	window = skb->data[20];
 
 	skb->sk             = make;
+	skb->destructor     = sock_efree;
 	make->sk_state	    = TCP_ESTABLISHED;
 
 	/* Fill in his circuit details */
-- 
2.20.1


From 2f81124d85b9e5dabc5e90372dbb49ee408f1b13 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 22 Jul 2019 20:41:22 -0700
Subject: [PATCH 38/49] netrom: hold sock when setting skb->destructor

[ Upstream commit 4638faac032756f7eab5524be7be56bee77e426b ]

sock_efree() releases the sock refcnt, if we don't hold this refcnt
when setting skb->destructor to it, the refcnt would not be balanced.
This leads to several bug reports from syzbot.

I have checked other users of sock_efree(), all of them hold the
sock refcnt.

Fixes: c8c8218ec5af ("netrom: fix a memory leak in nr_rx_frame()")
Reported-and-tested-by: <syzbot+622bdabb128acc33427d@syzkaller.appspotmail.com>
Reported-and-tested-by: <syzbot+6eaef7158b19e3fec3a0@syzkaller.appspotmail.com>
Reported-and-tested-by: <syzbot+9399c158fcc09b21d0d2@syzkaller.appspotmail.com>
Reported-and-tested-by: <syzbot+a34e5f3d0300163f0c87@syzkaller.appspotmail.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netrom/af_netrom.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 96740d389377..c4f54ad2b98a 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -967,6 +967,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev)
 
 	window = skb->data[20];
 
+	sock_hold(make);
 	skb->sk             = make;
 	skb->destructor     = sock_efree;
 	make->sk_state	    = TCP_ESTABLISHED;
-- 
2.20.1


From 83111b80a9ed2f5c0d77a7587e68ac49f0ada656 Mon Sep 17 00:00:00 2001
From: Frank de Brabander <debrabander@gmail.com>
Date: Fri, 5 Jul 2019 13:43:14 +0200
Subject: [PATCH 39/49] selftests: txring_overwrite: fix incorrect test of
 mmap() return value

[ Upstream commit cecaa76b2919aac2aa584ce476e9fcd5b084add5 ]

If mmap() fails it returns MAP_FAILED, which is defined as ((void *) -1).
The current if-statement incorrectly tests if *ring is NULL.

Fixes: 358be656406d ("selftests/net: add txring_overwrite")
Signed-off-by: Frank de Brabander <debrabander@gmail.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/txring_overwrite.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/txring_overwrite.c b/tools/testing/selftests/net/txring_overwrite.c
index fd8b1c663c39..7d9ea039450a 100644
--- a/tools/testing/selftests/net/txring_overwrite.c
+++ b/tools/testing/selftests/net/txring_overwrite.c
@@ -113,7 +113,7 @@ static int setup_tx(char **ring)
 
 	*ring = mmap(0, req.tp_block_size * req.tp_block_nr,
 		     PROT_READ | PROT_WRITE, MAP_SHARED, fdt, 0);
-	if (!*ring)
+	if (*ring == MAP_FAILED)
 		error(1, errno, "mmap");
 
 	return fdt;
-- 
2.20.1


From 044b3adb51d84be97c57e883abb0a9bdb6bb577b Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu, 4 Jul 2019 14:50:36 -0700
Subject: [PATCH 40/49] net/tls: fix poll ignoring partially copied records

[ Upstream commit 13aecb17acabc2a92187d08f7ca93bb8aad62c6f ]

David reports that RPC applications which use epoll() occasionally
get stuck, and that TLS ULP causes the kernel to not wake applications,
even though read() will return data.

This is indeed true. The ctx->rx_list which holds partially copied
records is not consulted when deciding whether socket is readable.

Note that SO_RCVLOWAT with epoll() is and has always been broken for
kernel TLS. We'd need to parse all records from the TCP layer, instead
of just the first one.

Fixes: 692d7b5d1f91 ("tls: Fix recvmsg() to be able to peek across multiple records")
Reported-by: David Beckett <david.beckett@netronome.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 455a782c7658..e2385183526e 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1958,7 +1958,8 @@ bool tls_sw_stream_read(const struct sock *sk)
 		ingress_empty = list_empty(&psock->ingress_msg);
 	rcu_read_unlock();
 
-	return !ingress_empty || ctx->recv_pkt;
+	return !ingress_empty || ctx->recv_pkt ||
+		!skb_queue_empty(&ctx->rx_list);
 }
 
 static int tls_read_size(struct strparser *strp, struct sk_buff *skb)
-- 
2.20.1


From 95beee2bbb12d00a88a212ff345c86f2d10db229 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 28 Jun 2019 16:07:59 -0700
Subject: [PATCH 41/49] net/tls: reject offload of TLS 1.3

[ Upstream commit 618bac45937a3dc6126ac0652747481e97000f99 ]

Neither drivers nor the tls offload code currently supports TLS
version 1.3. Check the TLS version when installing connection
state. TLS 1.3 will just fallback to the kernel crypto for now.

Fixes: 130b392c6cd6 ("net: tls: Add tls 1.3 support")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_device.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 359a515fd193..eb8f24f420f0 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -742,6 +742,11 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx)
 	}
 
 	crypto_info = &ctx->crypto_send.info;
+	if (crypto_info->version != TLS_1_2_VERSION) {
+		rc = -EOPNOTSUPP;
+		goto free_offload_ctx;
+	}
+
 	switch (crypto_info->cipher_type) {
 	case TLS_CIPHER_AES_GCM_128:
 		nonce_size = TLS_CIPHER_AES_GCM_128_IV_SIZE;
@@ -876,6 +881,9 @@ int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx)
 	struct net_device *netdev;
 	int rc = 0;
 
+	if (ctx->crypto_recv.info.version != TLS_1_2_VERSION)
+		return -EOPNOTSUPP;
+
 	/* We support starting offload on multiple sockets
 	 * concurrently, so we only need a read lock here.
 	 * This lock must precede get_netdev_for_sock to prevent races between
-- 
2.20.1


From 52a4607c4bae39f6be88da0fd67d8fa78c73f8fb Mon Sep 17 00:00:00 2001
From: Eli Britstein <elibr@mellanox.com>
Date: Sun, 2 Jun 2019 06:19:03 +0000
Subject: [PATCH 42/49] net/mlx5e: Fix port tunnel GRE entropy control

[ Upstream commit 914adbb1bcf89478ac138318d28b302704564d59 ]

GRE entropy calculation is a single bit per card, and not per port.
Force disable GRE entropy calculation upon the first GRE encap rule,
and release the force at the last GRE encap rule removal. This is done
per port.

Fixes: 97417f6182f8 ("net/mlx5e: Fix GRE key by controlling port tunnel entropy calculation")
Signed-off-by: Eli Britstein <elibr@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../mellanox/mlx5/core/lib/port_tun.c         | 23 ++++---------------
 1 file changed, 4 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.c
index be69c1d7941a..48b5c847b642 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.c
@@ -98,27 +98,12 @@ static int mlx5_set_entropy(struct mlx5_tun_entropy *tun_entropy,
 	 */
 	if (entropy_flags.gre_calc_supported &&
 	    reformat_type == MLX5_REFORMAT_TYPE_L2_TO_NVGRE) {
-		/* Other applications may change the global FW entropy
-		 * calculations settings. Check that the current entropy value
-		 * is the negative of the updated value.
-		 */
-		if (entropy_flags.force_enabled &&
-		    enable == entropy_flags.gre_calc_enabled) {
-			mlx5_core_warn(tun_entropy->mdev,
-				       "Unexpected GRE entropy calc setting - expected %d",
-				       !entropy_flags.gre_calc_enabled);
-			return -EOPNOTSUPP;
-		}
-		err = mlx5_set_port_gre_tun_entropy_calc(tun_entropy->mdev, enable,
-							 entropy_flags.force_supported);
+		if (!entropy_flags.force_supported)
+			return 0;
+		err = mlx5_set_port_gre_tun_entropy_calc(tun_entropy->mdev,
+							 enable, !enable);
 		if (err)
 			return err;
-		/* if we turn on the entropy we don't need to force it anymore */
-		if (entropy_flags.force_supported && enable) {
-			err = mlx5_set_port_gre_tun_entropy_calc(tun_entropy->mdev, 1, 0);
-			if (err)
-				return err;
-		}
 	} else if (entropy_flags.calc_supported) {
 		/* Other applications may change the global FW entropy
 		 * calculations settings. Check that the current entropy value
-- 
2.20.1


From 9a7dcdf70e2f98dd6d6011eebbbaedc71fb4b223 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Fri, 3 May 2019 13:14:59 -0700
Subject: [PATCH 43/49] net/mlx5e: Rx, Fix checksum calculation for new
 hardware

[ Upstream commit db849faa9bef993a1379dc510623f750a72fa7ce ]

CQE checksum full mode in new HW, provides a full checksum of rx frame.
Covering bytes starting from eth protocol up to last byte in the received
frame (frame_size - ETH_HLEN), as expected by the stack.

Fixing up skb->csum by the driver is not required in such case. This fix
is to avoid wrong checksum calculation in drivers which already support
the new hardware with the new checksum mode.

Fixes: 85327a9c4150 ("net/mlx5: Update the list of the PCI supported devices")
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      | 1 +
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 3 +++
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c   | 7 ++++++-
 include/linux/mlx5/mlx5_ifc.h                     | 3 ++-
 4 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index cc6797e24571..cc227a7aa79f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -294,6 +294,7 @@ enum {
 	MLX5E_RQ_STATE_ENABLED,
 	MLX5E_RQ_STATE_AM,
 	MLX5E_RQ_STATE_NO_CSUM_COMPLETE,
+	MLX5E_RQ_STATE_CSUM_FULL, /* cqe_csum_full hw bit is set */
 };
 
 struct mlx5e_cq {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index a8e8350b38aa..98d75271fc73 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -855,6 +855,9 @@ static int mlx5e_open_rq(struct mlx5e_channel *c,
 	if (err)
 		goto err_destroy_rq;
 
+	if (MLX5_CAP_ETH(c->mdev, cqe_checksum_full))
+		__set_bit(MLX5E_RQ_STATE_CSUM_FULL, &c->rq.state);
+
 	if (params->rx_dim_enabled)
 		__set_bit(MLX5E_RQ_STATE_AM, &c->rq.state);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 13133e7f088e..8a5f9411cac6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -873,8 +873,14 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 		if (unlikely(get_ip_proto(skb, network_depth, proto) == IPPROTO_SCTP))
 			goto csum_unnecessary;
 
+		stats->csum_complete++;
 		skb->ip_summed = CHECKSUM_COMPLETE;
 		skb->csum = csum_unfold((__force __sum16)cqe->check_sum);
+
+		if (test_bit(MLX5E_RQ_STATE_CSUM_FULL, &rq->state))
+			return; /* CQE csum covers all received bytes */
+
+		/* csum might need some fixups ...*/
 		if (network_depth > ETH_HLEN)
 			/* CQE csum is calculated from the IP header and does
 			 * not cover VLAN headers (if present). This will add
@@ -885,7 +891,6 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 						 skb->csum);
 
 		mlx5e_skb_padding_csum(skb, network_depth, proto, stats);
-		stats->csum_complete++;
 		return;
 	}
 
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 5e74305e2e57..7e42efa143a0 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -749,7 +749,8 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits {
 	u8         swp[0x1];
 	u8         swp_csum[0x1];
 	u8         swp_lso[0x1];
-	u8         reserved_at_23[0xd];
+	u8         cqe_checksum_full[0x1];
+	u8         reserved_at_24[0xc];
 	u8         max_vxlan_udp_ports[0x8];
 	u8         reserved_at_38[0x6];
 	u8         max_geneve_opt_len[0x1];
-- 
2.20.1


From 5082ef533b57a58272491cd3fdfbb9ede87ce01b Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Mon, 17 Jun 2019 12:01:45 +0300
Subject: [PATCH 44/49] net/mlx5e: Fix return value from timeout recover
 function

[ Upstream commit 39825350ae2a52f8513741b36e42118bd80dd689 ]

Fix timeout recover function to return a meaningful return value.
When an interrupt was not sent by the FW, return IO error instead of
'true'.

Fixes: c7981bea48fb ("net/mlx5e: Fix return status of TX reporter timeout recover")
Signed-off-by: Aya Levin <ayal@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index 476dd97f7f2f..a778c15e5324 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -142,22 +142,20 @@ static int mlx5e_tx_reporter_timeout_recover(struct mlx5e_txqsq *sq)
 {
 	struct mlx5_eq_comp *eq = sq->cq.mcq.eq;
 	u32 eqe_count;
-	int ret;
 
 	netdev_err(sq->channel->netdev, "EQ 0x%x: Cons = 0x%x, irqn = 0x%x\n",
 		   eq->core.eqn, eq->core.cons_index, eq->core.irqn);
 
 	eqe_count = mlx5_eq_poll_irq_disabled(eq);
-	ret = eqe_count ? false : true;
 	if (!eqe_count) {
 		clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
-		return ret;
+		return -EIO;
 	}
 
 	netdev_err(sq->channel->netdev, "Recover %d eqes on EQ 0x%x\n",
 		   eqe_count, eq->core.eqn);
 	sq->channel->stats->eq_rearm++;
-	return ret;
+	return 0;
 }
 
 int mlx5e_tx_reporter_timeout(struct mlx5e_txqsq *sq)
-- 
2.20.1


From aaa3b3a19eadaf7acdf69112fe9a7943996e0236 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Sun, 30 Jun 2019 11:11:26 +0300
Subject: [PATCH 45/49] net/mlx5e: Fix error flow in tx reporter diagnose

[ Upstream commit 99d31cbd8953c6929da978bf049ab0f0b4e503d9 ]

Fix tx reporter's diagnose callback. Propagate error when failing to
gather diagnostics information or failing to print diagnostic data per
queue.

Fixes: de8650a82071 ("net/mlx5e: Add tx reporter support")
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index a778c15e5324..f3d98748b211 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -262,13 +262,13 @@ static int mlx5e_tx_reporter_diagnose(struct devlink_health_reporter *reporter,
 
 		err = mlx5_core_query_sq_state(priv->mdev, sq->sqn, &state);
 		if (err)
-			break;
+			goto unlock;
 
 		err = mlx5e_tx_reporter_build_diagnose_output(fmsg, sq->sqn,
 							      state,
 							      netif_xmit_stopped(sq->txq));
 		if (err)
-			break;
+			goto unlock;
 	}
 	err = devlink_fmsg_arr_pair_nest_end(fmsg);
 	if (err)
-- 
2.20.1


From e92ec00c7e7ec21e3abd1eba22e2145fcc86760f Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Wed, 17 Jul 2019 03:07:23 -0400
Subject: [PATCH 46/49] bnxt_en: Fix VNIC accounting when enabling aRFS on
 57500 chips.

[ Upstream commit 9b3d15e6b05e0b916be5fbd915f90300a403098b ]

Unlike legacy chips, 57500 chips don't need additional VNIC resources
for aRFS/ntuple.  Fix the code accordingly so that we don't reserve
and allocate additional VNICs on 57500 chips.  Without this patch,
the driver is failing to initialize when it tries to allocate extra
VNICs.

Fixes: ac33906c67e2 ("bnxt_en: Add support for aRFS on 57500 chips.")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index f758b2e0591f..9a2a0d24d20d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -3022,7 +3022,7 @@ static int bnxt_alloc_vnics(struct bnxt *bp)
 	int num_vnics = 1;
 
 #ifdef CONFIG_RFS_ACCEL
-	if (bp->flags & BNXT_FLAG_RFS)
+	if ((bp->flags & (BNXT_FLAG_RFS | BNXT_FLAG_CHIP_P5)) == BNXT_FLAG_RFS)
 		num_vnics += bp->rx_nr_rings;
 #endif
 
@@ -7124,6 +7124,9 @@ static int bnxt_alloc_rfs_vnics(struct bnxt *bp)
 #ifdef CONFIG_RFS_ACCEL
 	int i, rc = 0;
 
+	if (bp->flags & BNXT_FLAG_CHIP_P5)
+		return 0;
+
 	for (i = 0; i < bp->rx_nr_rings; i++) {
 		struct bnxt_vnic_info *vnic;
 		u16 vnic_id = i + 1;
@@ -9587,7 +9590,7 @@ int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs,
 		return -ENOMEM;
 
 	vnics = 1;
-	if (bp->flags & BNXT_FLAG_RFS)
+	if ((bp->flags & (BNXT_FLAG_RFS | BNXT_FLAG_CHIP_P5)) == BNXT_FLAG_RFS)
 		vnics += rx_rings;
 
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
-- 
2.20.1


From 778bbd0b324cf0b37a36fac39439deeddd4245e4 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Wed, 17 Jul 2019 23:29:07 +0300
Subject: [PATCH 47/49] mlxsw: spectrum_dcb: Configure DSCP map as the last
 rule is removed

[ Upstream commit dedfde2fe1c4ccf27179fcb234e2112d065c39bb ]

Spectrum systems use DSCP rewrite map to update DSCP field in egressing
packets to correspond to priority that the packet has. Whether rewriting
will take place is determined at the point when the packet ingresses the
switch: if the port is in Trust L3 mode, packet priority is determined from
the DSCP map at the port, and DSCP rewrite will happen. If the port is in
Trust L2 mode, 802.1p is used for packet prioritization, and no DSCP
rewrite will happen.

The driver determines the port trust mode based on whether any DSCP
prioritization rules are in effect at given port. If there are any, trust
level is L3, otherwise it's L2. When the last DSCP rule is removed, the
port is switched to trust L2. Under that scenario, if DSCP of a packet
should be rewritten, it should be rewritten to 0.

However, when switching to Trust L2, the driver neglects to also update the
DSCP rewrite map. The last DSCP rule thus remains in effect, and packets
egressing through this port, if they have the right priority, will have
their DSCP set according to this rule.

Fix by first configuring the rewrite map, and only then switching to trust
L2 and bailing out.

Fixes: b2b1dab6884e ("mlxsw: spectrum: Support ieee_setapp, ieee_delapp")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reported-by: Alex Veber <alexve@mellanox.com>
Tested-by: Alex Veber <alexve@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_dcb.c   | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c
index b25048c6c761..21296fa7f7fb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c
@@ -408,14 +408,6 @@ static int mlxsw_sp_port_dcb_app_update(struct mlxsw_sp_port *mlxsw_sp_port)
 	have_dscp = mlxsw_sp_port_dcb_app_prio_dscp_map(mlxsw_sp_port,
 							&prio_map);
 
-	if (!have_dscp) {
-		err = mlxsw_sp_port_dcb_toggle_trust(mlxsw_sp_port,
-					MLXSW_REG_QPTS_TRUST_STATE_PCP);
-		if (err)
-			netdev_err(mlxsw_sp_port->dev, "Couldn't switch to trust L2\n");
-		return err;
-	}
-
 	mlxsw_sp_port_dcb_app_dscp_prio_map(mlxsw_sp_port, default_prio,
 					    &dscp_map);
 	err = mlxsw_sp_port_dcb_app_update_qpdpm(mlxsw_sp_port,
@@ -432,6 +424,14 @@ static int mlxsw_sp_port_dcb_app_update(struct mlxsw_sp_port *mlxsw_sp_port)
 		return err;
 	}
 
+	if (!have_dscp) {
+		err = mlxsw_sp_port_dcb_toggle_trust(mlxsw_sp_port,
+					MLXSW_REG_QPTS_TRUST_STATE_PCP);
+		if (err)
+			netdev_err(mlxsw_sp_port->dev, "Couldn't switch to trust L2\n");
+		return err;
+	}
+
 	err = mlxsw_sp_port_dcb_toggle_trust(mlxsw_sp_port,
 					     MLXSW_REG_QPTS_TRUST_STATE_DSCP);
 	if (err) {
-- 
2.20.1


From aac51a97eca1336f7a43d9ce0275bc560fd1c6e1 Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@mellanox.com>
Date: Mon, 17 Jun 2019 13:22:28 +0300
Subject: [PATCH 48/49] net/mlx5: E-Switch, Fix default encap mode

[ Upstream commit 9a64144d683a4395f57562d90247c61a0bf5105f ]

Encap mode is related to switchdev mode only. Move the init of
the encap mode to eswitch_offloads. Before this change, we reported
that eswitch supports encap, even tough the device was in non
SRIOV mode.

Fixes: 7768d1971de67 ('net/mlx5: E-Switch, Add control for encapsulation')
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c          | 5 -----
 drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 7 +++++++
 2 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 6a921e24cd5e..e9339e7d6a18 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1882,11 +1882,6 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 	esw->enabled_vports = 0;
 	esw->mode = SRIOV_NONE;
 	esw->offloads.inline_mode = MLX5_INLINE_MODE_NONE;
-	if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, reformat) &&
-	    MLX5_CAP_ESW_FLOWTABLE_FDB(dev, decap))
-		esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_BASIC;
-	else
-		esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;
 
 	dev->priv.eswitch = esw;
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 47b446d30f71..c2beadc41c40 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -1840,6 +1840,12 @@ int esw_offloads_init(struct mlx5_eswitch *esw, int vf_nvports,
 {
 	int err;
 
+	if (MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, reformat) &&
+	    MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, decap))
+		esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_BASIC;
+	else
+		esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;
+
 	err = esw_offloads_steering_init(esw, vf_nvports, total_nvports);
 	if (err)
 		return err;
@@ -1901,6 +1907,7 @@ void esw_offloads_cleanup(struct mlx5_eswitch *esw)
 	esw_offloads_devcom_cleanup(esw);
 	esw_offloads_unload_all_reps(esw, num_vfs);
 	esw_offloads_steering_cleanup(esw);
+	esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;
 }
 
 static int esw_mode_from_devlink(u16 mode, u16 *mlx5_mode)
-- 
2.20.1


From c48dafce538df2a2592a56d1996cbc5feb76a4e7 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 17 Jul 2019 23:29:08 +0300
Subject: [PATCH 49/49] mlxsw: spectrum: Do not process learned records with a
 dummy FID

[ Upstream commit 577fa14d210073ba1ce6237c659a8820312104ad ]

The switch periodically sends notifications about learned FDB entries.
Among other things, the notification includes the FID (Filtering
Identifier) and the port on which the MAC was learned.

In case the driver does not have the FID defined on the relevant port,
the following error will be periodically generated:

mlxsw_spectrum2 0000:06:00.0 swp32: Failed to find a matching {Port, VID} following FDB notification

This is not supposed to happen under normal conditions, but can happen
if an ingress tc filter with a redirect action is installed on a bridged
port. The redirect action will cause the packet's FID to be changed to
the dummy FID and a learning notification will be emitted with this FID
- which is not defined on the bridged port.

Fix this by having the driver ignore learning notifications generated
with the dummy FID and delete them from the device.

Another option is to chain an ignore action after the redirect action
which will cause the device to disable learning, but this means that we
need to consume another action whenever a redirect action is used. In
addition, the scenario described above is merely a corner case.

Fixes: cedbb8b25948 ("mlxsw: spectrum_flower: Set dummy FID before forward action")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Alex Kushnarov <alexanderk@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Tested-by: Alex Kushnarov <alexanderk@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h         |  1 +
 drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c     | 10 ++++++++++
 .../net/ethernet/mellanox/mlxsw/spectrum_switchdev.c   |  6 ++++++
 3 files changed, 17 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 8601b3041acd..332195d96c62 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -805,6 +805,7 @@ int mlxsw_sp_setup_tc_prio(struct mlxsw_sp_port *mlxsw_sp_port,
 			   struct tc_prio_qopt_offload *p);
 
 /* spectrum_fid.c */
+bool mlxsw_sp_fid_is_dummy(struct mlxsw_sp *mlxsw_sp, u16 fid_index);
 bool mlxsw_sp_fid_lag_vid_valid(const struct mlxsw_sp_fid *fid);
 struct mlxsw_sp_fid *mlxsw_sp_fid_lookup_by_index(struct mlxsw_sp *mlxsw_sp,
 						  u16 fid_index);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
index 46baf3b44309..8df3cb21baa6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
@@ -126,6 +126,16 @@ static const int *mlxsw_sp_packet_type_sfgc_types[] = {
 	[MLXSW_SP_FLOOD_TYPE_MC]	= mlxsw_sp_sfgc_mc_packet_types,
 };
 
+bool mlxsw_sp_fid_is_dummy(struct mlxsw_sp *mlxsw_sp, u16 fid_index)
+{
+	enum mlxsw_sp_fid_type fid_type = MLXSW_SP_FID_TYPE_DUMMY;
+	struct mlxsw_sp_fid_family *fid_family;
+
+	fid_family = mlxsw_sp->fid_core->fid_family_arr[fid_type];
+
+	return fid_family->start_index == fid_index;
+}
+
 bool mlxsw_sp_fid_lag_vid_valid(const struct mlxsw_sp_fid *fid)
 {
 	return fid->fid_family->lag_vid_valid;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 50111f228d77..5ecb45118400 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -2468,6 +2468,9 @@ static void mlxsw_sp_fdb_notify_mac_process(struct mlxsw_sp *mlxsw_sp,
 		goto just_remove;
 	}
 
+	if (mlxsw_sp_fid_is_dummy(mlxsw_sp, fid))
+		goto just_remove;
+
 	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_fid(mlxsw_sp_port, fid);
 	if (!mlxsw_sp_port_vlan) {
 		netdev_err(mlxsw_sp_port->dev, "Failed to find a matching {Port, VID} following FDB notification\n");
@@ -2527,6 +2530,9 @@ static void mlxsw_sp_fdb_notify_mac_lag_process(struct mlxsw_sp *mlxsw_sp,
 		goto just_remove;
 	}
 
+	if (mlxsw_sp_fid_is_dummy(mlxsw_sp, fid))
+		goto just_remove;
+
 	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_fid(mlxsw_sp_port, fid);
 	if (!mlxsw_sp_port_vlan) {
 		netdev_err(mlxsw_sp_port->dev, "Failed to find a matching {Port, VID} following FDB notification\n");
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Wed, Jul 24, 2019 at 06:55:42PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v5.1 and v5.2
> -stable, respectively.

All now queued up, thanks!

No need to do any more patches for 5.1.y anymore, this is going to be
the last release of that kernel branch.

thanks,

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 106 bytes --]


Please queue up the following networking bug fixes for v4.19 and v5.2
-stable, respectively.

Thank you.

[-- Attachment #2: net_419.mbox --]
[-- Type: Application/Octet-Stream, Size: 86986 bytes --]

From f1cb00b5d4443b1e96976f5708d472902fa79dd7 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 30 Jul 2019 22:21:41 -0500
Subject: [PATCH 01/28] atm: iphase: Fix Spectre v1 vulnerability

[ Upstream commit ea443e5e98b5b74e317ef3d26bcaea54931ccdee ]

board is controlled by user-space, hence leading to a potential
exploitation of the Spectre variant 1 vulnerability.

This issue was detected with the help of Smatch:

drivers/atm/iphase.c:2765 ia_ioctl() warn: potential spectre issue 'ia_dev' [r] (local cap)
drivers/atm/iphase.c:2774 ia_ioctl() warn: possible spectre second half.  'iadev'
drivers/atm/iphase.c:2782 ia_ioctl() warn: possible spectre second half.  'iadev'
drivers/atm/iphase.c:2816 ia_ioctl() warn: possible spectre second half.  'iadev'
drivers/atm/iphase.c:2823 ia_ioctl() warn: possible spectre second half.  'iadev'
drivers/atm/iphase.c:2830 ia_ioctl() warn: potential spectre issue '_ia_dev' [r] (local cap)
drivers/atm/iphase.c:2845 ia_ioctl() warn: possible spectre second half.  'iadev'
drivers/atm/iphase.c:2856 ia_ioctl() warn: possible spectre second half.  'iadev'

Fix this by sanitizing board before using it to index ia_dev and _ia_dev

Notice that given that speculation windows are large, the policy is
to kill the speculation on the first load and not worry if it can be
completed with a dependent load/store [1].

[1] https://lore.kernel.org/lkml/20180423164740.GY17484@dhcp22.suse.cz/

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/atm/iphase.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/atm/iphase.c b/drivers/atm/iphase.c
index 82532c299bb5..008905d4152a 100644
--- a/drivers/atm/iphase.c
+++ b/drivers/atm/iphase.c
@@ -63,6 +63,7 @@
 #include <asm/byteorder.h>  
 #include <linux/vmalloc.h>
 #include <linux/jiffies.h>
+#include <linux/nospec.h>
 #include "iphase.h"		  
 #include "suni.h"		  
 #define swap_byte_order(x) (((x & 0xff) << 8) | ((x & 0xff00) >> 8))
@@ -2760,8 +2761,11 @@ static int ia_ioctl(struct atm_dev *dev, unsigned int cmd, void __user *arg)
    }
    if (copy_from_user(&ia_cmds, arg, sizeof ia_cmds)) return -EFAULT; 
    board = ia_cmds.status;
-   if ((board < 0) || (board > iadev_count))
-         board = 0;    
+
+	if ((board < 0) || (board > iadev_count))
+		board = 0;
+	board = array_index_nospec(board, iadev_count + 1);
+
    iadev = ia_dev[board];
    switch (ia_cmds.cmd) {
    case MEMDUMP:
-- 
2.20.1


From 2fc2e54c713dad1ad808b5bfe696fbcf4f47269a Mon Sep 17 00:00:00 2001
From: Sudarsana Reddy Kalluru <skalluru@marvell.com>
Date: Tue, 23 Jul 2019 19:32:41 -0700
Subject: [PATCH 02/28] bnx2x: Disable multi-cos feature.

[ Upstream commit d1f0b5dce8fda09a7f5f04c1878f181d548e42f5 ]

Commit 3968d38917eb ("bnx2x: Fix Multi-Cos.") which enabled multi-cos
feature after prolonged time in driver added some regression causing
numerous issues (sudden reboots, tx timeout etc.) reported by customers.
We plan to backout this commit and submit proper fix once we have root
cause of issues reported with this feature enabled.

Fixes: 3968d38917eb ("bnx2x: Fix Multi-Cos.")
Signed-off-by: Sudarsana Reddy Kalluru <skalluru@marvell.com>
Signed-off-by: Manish Chopra <manishc@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 3edb81a4f075..33baa17fa9d5 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -1936,8 +1936,7 @@ u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
 	}
 
 	/* select a non-FCoE queue */
-	return fallback(dev, skb, NULL) %
-	       (BNX2X_NUM_ETH_QUEUES(bp) * bp->max_cos);
+	return fallback(dev, skb, NULL) % (BNX2X_NUM_ETH_QUEUES(bp));
 }
 
 void bnx2x_set_num_queues(struct bnx2x *bp)
-- 
2.20.1


From 3ec3c6d478501f5267a78cd4323f8cf4cc5db78f Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 22 Jul 2019 21:43:00 -0700
Subject: [PATCH 03/28] ife: error out when nla attributes are empty

[ Upstream commit c8ec4632c6ac9cda0e8c3d51aa41eeab66585bd5 ]

act_ife at least requires TCA_IFE_PARMS, so we have to bail out
when there is no attribute passed in.

Reported-by: syzbot+fbb5b288c9cb6a2eeac4@syzkaller.appspotmail.com
Fixes: ef6980b6becb ("introduce IFE action")
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ife.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 06a3d4801878..915b6e94da63 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -484,6 +484,11 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	int ret = 0;
 	int err;
 
+	if (!nla) {
+		NL_SET_ERR_MSG_MOD(extack, "IFE requires attributes to be passed");
+		return -EINVAL;
+	}
+
 	err = nla_parse_nested(tb, TCA_IFE_MAX, nla, ife_policy, NULL);
 	if (err < 0)
 		return err;
-- 
2.20.1


From da31250a7f8f68c324f156c5192ecc64b9a8015b Mon Sep 17 00:00:00 2001
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Wed, 24 Jul 2019 20:00:42 +0800
Subject: [PATCH 04/28] ip6_gre: reload ipv6h in prepare_ip6gre_xmit_ipv6

[ Upstream commit 3bc817d665ac6d9de89f59df522ad86f5b5dfc03 ]

Since ip6_tnl_parse_tlv_enc_lim() can call pskb_may_pull()
which may change skb->data, so we need to re-load ipv6h at
the right place.

Fixes: 898b29798e36 ("ip6_gre: Refactor ip6gre xmit codes")
Cc: William Tu <u9012063@gmail.com>
Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Acked-by: William Tu <u9012063@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 01ecd510014f..a53ef079a539 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -680,12 +680,13 @@ static int prepare_ip6gre_xmit_ipv6(struct sk_buff *skb,
 				    struct flowi6 *fl6, __u8 *dsfield,
 				    int *encap_limit)
 {
-	struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+	struct ipv6hdr *ipv6h;
 	struct ip6_tnl *t = netdev_priv(dev);
 	__u16 offset;
 
 	offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb));
 	/* ip6_tnl_parse_tlv_enc_lim() might have reallocated skb->head */
+	ipv6h = ipv6_hdr(skb);
 
 	if (offset > 0) {
 		struct ipv6_tlv_tnl_enc_lim *tel;
-- 
2.20.1


From a858e3fec94a0c8ffb354945b455abce30f0ee31 Mon Sep 17 00:00:00 2001
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Fri, 26 Jul 2019 00:40:17 +0800
Subject: [PATCH 05/28] ip6_tunnel: fix possible use-after-free on xmit

[ Upstream commit 01f5bffad555f8e22a61f4b1261fe09cf1b96994 ]

ip4ip6/ip6ip6 tunnels run iptunnel_handle_offloads on xmit which
can cause a possible use-after-free accessing iph/ipv6h pointer
since the packet will be 'uncloned' running pskb_expand_head if
it is a cloned gso skb.

Fixes: 0e9a709560db ("ip6_tunnel, ip6_gre: fix setting of DSCP on encapsulated packets")
Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index ade1390c6348..d0ad85b8650d 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1283,12 +1283,11 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
+	dsfield = INET_ECN_encapsulate(dsfield, ipv4_get_dsfield(iph));
 
 	if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6))
 		return -1;
 
-	dsfield = INET_ECN_encapsulate(dsfield, ipv4_get_dsfield(iph));
-
 	skb_set_inner_ipproto(skb, IPPROTO_IPIP);
 
 	err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu,
@@ -1372,12 +1371,11 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
+	dsfield = INET_ECN_encapsulate(dsfield, ipv6_get_dsfield(ipv6h));
 
 	if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6))
 		return -1;
 
-	dsfield = INET_ECN_encapsulate(dsfield, ipv6_get_dsfield(ipv6h));
-
 	skb_set_inner_ipproto(skb, IPPROTO_IPV6);
 
 	err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu,
-- 
2.20.1


From a28bcd5ba4cc63be2f6b79648de5b6bdad8c67c0 Mon Sep 17 00:00:00 2001
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Thu, 25 Jul 2019 11:07:56 +0800
Subject: [PATCH 06/28] ipip: validate header length in ipip_tunnel_xmit

[ Upstream commit 47d858d0bdcd47cc1c6c9eeca91b091dd9e55637 ]

We need the same checks introduced by commit cb9f1b783850
("ip: validate header length on virtual device xmit") for
ipip tunnel.

Fixes: cb9f1b783850b ("ip: validate header length on virtual device xmit")
Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ipip.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index c891235b4966..4368282eb6f8 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -281,6 +281,9 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb,
 	const struct iphdr  *tiph = &tunnel->parms.iph;
 	u8 ipproto;
 
+	if (!pskb_inet_may_pull(skb))
+		goto tx_error;
+
 	switch (skb->protocol) {
 	case htons(ETH_P_IP):
 		ipproto = IPPROTO_IPIP;
-- 
2.20.1


From ca6431c94842320c7eae08fce8955cb67576e6e6 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 31 Jul 2019 09:33:14 +0300
Subject: [PATCH 07/28] mlxsw: spectrum: Fix error path in
 mlxsw_sp_module_init()

[ Upstream commit 28fe79000e9b0a6f99959869947f1ca305f14599 ]

In case of sp2 pci driver registration fail, fix the error path to
start with sp1 pci driver unregister.

Fixes: c3ab435466d5 ("mlxsw: spectrum: Extend to support Spectrum-2 ASIC")
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 0cab06046e5d..ee126bcf7c35 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -5032,7 +5032,7 @@ static int __init mlxsw_sp_module_init(void)
 	return 0;
 
 err_sp2_pci_driver_register:
-	mlxsw_pci_driver_unregister(&mlxsw_sp2_pci_driver);
+	mlxsw_pci_driver_unregister(&mlxsw_sp1_pci_driver);
 err_sp1_pci_driver_register:
 	mlxsw_core_driver_unregister(&mlxsw_sp2_driver);
 err_sp2_core_driver_register:
-- 
2.20.1


From 2f4cb9d81fbf2bcfb0f3e9b55c0a7c26eb3d0fb8 Mon Sep 17 00:00:00 2001
From: Matteo Croce <mcroce@redhat.com>
Date: Thu, 1 Aug 2019 14:13:30 +0200
Subject: [PATCH 08/28] mvpp2: fix panic on module removal

[ Upstream commit 944a83a2669ae8aa2c7664e79376ca7468eb0a2b ]

mvpp2 uses a delayed workqueue to gather traffic statistics.
On module removal the workqueue can be destroyed before calling
cancel_delayed_work_sync() on its works.
Fix it by moving the destroy_workqueue() call after mvpp2_port_remove().
Also remove an unneeded call to flush_workqueue()

    # rmmod mvpp2
    [ 2743.311722] mvpp2 f4000000.ethernet eth1: phy link down 10gbase-kr/10Gbps/Full
    [ 2743.320063] mvpp2 f4000000.ethernet eth1: Link is Down
    [ 2743.572263] mvpp2 f4000000.ethernet eth2: phy link down sgmii/1Gbps/Full
    [ 2743.580076] mvpp2 f4000000.ethernet eth2: Link is Down
    [ 2744.102169] mvpp2 f2000000.ethernet eth0: phy link down 10gbase-kr/10Gbps/Full
    [ 2744.110441] mvpp2 f2000000.ethernet eth0: Link is Down
    [ 2744.115614] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000
    [ 2744.115615] Mem abort info:
    [ 2744.115616]   ESR = 0x96000005
    [ 2744.115617]   Exception class = DABT (current EL), IL = 32 bits
    [ 2744.115618]   SET = 0, FnV = 0
    [ 2744.115619]   EA = 0, S1PTW = 0
    [ 2744.115620] Data abort info:
    [ 2744.115621]   ISV = 0, ISS = 0x00000005
    [ 2744.115622]   CM = 0, WnR = 0
    [ 2744.115624] user pgtable: 4k pages, 39-bit VAs, pgdp=0000000422681000
    [ 2744.115626] [0000000000000000] pgd=0000000000000000, pud=0000000000000000
    [ 2744.115630] Internal error: Oops: 96000005 [#1] SMP
    [ 2744.115632] Modules linked in: mvpp2(-) algif_hash af_alg nls_iso8859_1 nls_cp437 vfat fat xhci_plat_hcd m25p80 spi_nor xhci_hcd mtd usbcore i2c_mv64xxx sfp usb_common marvell10g phy_generic spi_orion mdio_i2c i2c_core mvmdio phylink sbsa_gwdt ip_tables x_tables autofs4 [last unloaded: mvpp2]
    [ 2744.115654] CPU: 3 PID: 8357 Comm: kworker/3:2 Not tainted 5.3.0-rc2 #1
    [ 2744.115655] Hardware name: Marvell 8040 MACCHIATOBin Double-shot (DT)
    [ 2744.115665] Workqueue: events_power_efficient phylink_resolve [phylink]
    [ 2744.115669] pstate: a0000085 (NzCv daIf -PAN -UAO)
    [ 2744.115675] pc : __queue_work+0x9c/0x4d8
    [ 2744.115677] lr : __queue_work+0x170/0x4d8
    [ 2744.115678] sp : ffffff801001bd50
    [ 2744.115680] x29: ffffff801001bd50 x28: ffffffc422597600
    [ 2744.115684] x27: ffffff80109ae6f0 x26: ffffff80108e4018
    [ 2744.115688] x25: 0000000000000003 x24: 0000000000000004
    [ 2744.115691] x23: ffffff80109ae6e0 x22: 0000000000000017
    [ 2744.115694] x21: ffffffc42c030000 x20: ffffffc42209e8f8
    [ 2744.115697] x19: 0000000000000000 x18: 0000000000000000
    [ 2744.115699] x17: 0000000000000000 x16: 0000000000000000
    [ 2744.115701] x15: 0000000000000010 x14: ffffffffffffffff
    [ 2744.115702] x13: ffffff8090e2b95f x12: ffffff8010e2b967
    [ 2744.115704] x11: ffffff8010906000 x10: 0000000000000040
    [ 2744.115706] x9 : ffffff80109223b8 x8 : ffffff80109223b0
    [ 2744.115707] x7 : ffffffc42bc00068 x6 : 0000000000000000
    [ 2744.115709] x5 : ffffffc42bc00000 x4 : 0000000000000000
    [ 2744.115710] x3 : 0000000000000000 x2 : 0000000000000000
    [ 2744.115712] x1 : 0000000000000008 x0 : ffffffc42c030000
    [ 2744.115714] Call trace:
    [ 2744.115716]  __queue_work+0x9c/0x4d8
    [ 2744.115718]  delayed_work_timer_fn+0x28/0x38
    [ 2744.115722]  call_timer_fn+0x3c/0x180
    [ 2744.115723]  expire_timers+0x60/0x168
    [ 2744.115724]  run_timer_softirq+0xbc/0x1e8
    [ 2744.115727]  __do_softirq+0x128/0x320
    [ 2744.115731]  irq_exit+0xa4/0xc0
    [ 2744.115734]  __handle_domain_irq+0x70/0xc0
    [ 2744.115735]  gic_handle_irq+0x58/0xa8
    [ 2744.115737]  el1_irq+0xb8/0x140
    [ 2744.115738]  console_unlock+0x3a0/0x568
    [ 2744.115740]  vprintk_emit+0x200/0x2a0
    [ 2744.115744]  dev_vprintk_emit+0x1c8/0x1e4
    [ 2744.115747]  dev_printk_emit+0x6c/0x7c
    [ 2744.115751]  __netdev_printk+0x104/0x1d8
    [ 2744.115752]  netdev_printk+0x60/0x70
    [ 2744.115756]  phylink_resolve+0x38c/0x3c8 [phylink]
    [ 2744.115758]  process_one_work+0x1f8/0x448
    [ 2744.115760]  worker_thread+0x54/0x500
    [ 2744.115762]  kthread+0x12c/0x130
    [ 2744.115764]  ret_from_fork+0x10/0x1c
    [ 2744.115768] Code: aa1403e0 97fffbbe aa0003f5 b4000700 (f9400261)

Fixes: 118d6298f6f0 ("net: mvpp2: add ethtool GOP statistics")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Matteo Croce <mcroce@redhat.com>
Acked-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index df5b74f289e1..c357aafee106 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -5358,9 +5358,6 @@ static int mvpp2_remove(struct platform_device *pdev)
 
 	mvpp2_dbgfs_cleanup(priv);
 
-	flush_workqueue(priv->stats_queue);
-	destroy_workqueue(priv->stats_queue);
-
 	fwnode_for_each_available_child_node(fwnode, port_fwnode) {
 		if (priv->port_list[i]) {
 			mutex_destroy(&priv->port_list[i]->gather_stats_lock);
@@ -5369,6 +5366,8 @@ static int mvpp2_remove(struct platform_device *pdev)
 		i++;
 	}
 
+	destroy_workqueue(priv->stats_queue);
+
 	for (i = 0; i < MVPP2_BM_POOLS_NUM; i++) {
 		struct mvpp2_bm_pool *bm_pool = &priv->bm_pools[i];
 
-- 
2.20.1


From 71dc888287f81d62b5421f5273a7431091964012 Mon Sep 17 00:00:00 2001
From: Matteo Croce <mcroce@redhat.com>
Date: Sun, 28 Jul 2019 02:46:45 +0200
Subject: [PATCH 09/28] mvpp2: refactor MTU change code

[ Upstream commit 230bd958c2c846ee292aa38bc6b006296c24ca01 ]

The MTU change code can call napi_disable() with the device already down,
leading to a deadlock. Also, lot of code is duplicated unnecessarily.

Rework mvpp2_change_mtu() to avoid the deadlock and remove duplicated code.

Fixes: 3f518509dedc ("ethernet: Add new driver for Marvell Armada 375 network unit")
Signed-off-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/marvell/mvpp2/mvpp2_main.c   | 41 ++++++-------------
 1 file changed, 13 insertions(+), 28 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index c357aafee106..6455511457ca 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -3501,6 +3501,7 @@ static int mvpp2_set_mac_address(struct net_device *dev, void *p)
 static int mvpp2_change_mtu(struct net_device *dev, int mtu)
 {
 	struct mvpp2_port *port = netdev_priv(dev);
+	bool running = netif_running(dev);
 	int err;
 
 	if (!IS_ALIGNED(MVPP2_RX_PKT_SIZE(mtu), 8)) {
@@ -3509,40 +3510,24 @@ static int mvpp2_change_mtu(struct net_device *dev, int mtu)
 		mtu = ALIGN(MVPP2_RX_PKT_SIZE(mtu), 8);
 	}
 
-	if (!netif_running(dev)) {
-		err = mvpp2_bm_update_mtu(dev, mtu);
-		if (!err) {
-			port->pkt_size =  MVPP2_RX_PKT_SIZE(mtu);
-			return 0;
-		}
-
-		/* Reconfigure BM to the original MTU */
-		err = mvpp2_bm_update_mtu(dev, dev->mtu);
-		if (err)
-			goto log_error;
-	}
-
-	mvpp2_stop_dev(port);
+	if (running)
+		mvpp2_stop_dev(port);
 
 	err = mvpp2_bm_update_mtu(dev, mtu);
-	if (!err) {
+	if (err) {
+		netdev_err(dev, "failed to change MTU\n");
+		/* Reconfigure BM to the original MTU */
+		mvpp2_bm_update_mtu(dev, dev->mtu);
+	} else {
 		port->pkt_size =  MVPP2_RX_PKT_SIZE(mtu);
-		goto out_start;
 	}
 
-	/* Reconfigure BM to the original MTU */
-	err = mvpp2_bm_update_mtu(dev, dev->mtu);
-	if (err)
-		goto log_error;
-
-out_start:
-	mvpp2_start_dev(port);
-	mvpp2_egress_enable(port);
-	mvpp2_ingress_enable(port);
+	if (running) {
+		mvpp2_start_dev(port);
+		mvpp2_egress_enable(port);
+		mvpp2_ingress_enable(port);
+	}
 
-	return 0;
-log_error:
-	netdev_err(dev, "failed to change MTU\n");
 	return err;
 }
 
-- 
2.20.1


From 09adf05b2dea9b6226ba77369d5ae10b4400cea7 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Mon, 29 Jul 2019 12:28:41 +0300
Subject: [PATCH 10/28] net: bridge: delete local fdb on device init failure

[ Upstream commit d7bae09fa008c6c9a489580db0a5a12063b97f97 ]

On initialization failure we have to delete the local fdb which was
inserted due to the default pvid creation. This problem has been present
since the inception of default_pvid. Note that currently there are 2 cases:
1) in br_dev_init() when br_multicast_init() fails
2) if register_netdevice() fails after calling ndo_init()

This patch takes care of both since br_vlan_flush() is called on both
occasions. Also the new fdb delete would be a no-op on normal bridge
device destruction since the local fdb would've been already flushed by
br_dev_delete(). This is not an issue for ports since nbp_vlan_init() is
called last when adding a port thus nothing can fail after it.

Reported-by: syzbot+88533dc8b582309bf3ee@syzkaller.appspotmail.com
Fixes: 5be5a2df40f0 ("bridge: Add filtering support for default_pvid")
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_vlan.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 7df269092103..5f3950f00f73 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -677,6 +677,11 @@ void br_vlan_flush(struct net_bridge *br)
 
 	ASSERT_RTNL();
 
+	/* delete auto-added default pvid local fdb before flushing vlans
+	 * otherwise it will be leaked on bridge device init failure
+	 */
+	br_fdb_delete_by_port(br, NULL, 0, 1);
+
 	vg = br_vlan_group(br);
 	__vlan_flush(vg);
 	RCU_INIT_POINTER(br->vlgrp, NULL);
-- 
2.20.1


From 631f4b3b06839f6d28ddae9eaff6975af6f36c7b Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Tue, 30 Jul 2019 14:21:00 +0300
Subject: [PATCH 11/28] net: bridge: mcast: don't delete permanent entries when
 fast leave is enabled

[ Upstream commit 5c725b6b65067909548ac9ca9bc777098ec9883d ]

When permanent entries were introduced by the commit below, they were
exempt from timing out and thus igmp leave wouldn't affect them unless
fast leave was enabled on the port which was added before permanent
entries existed. It shouldn't matter if fast leave is enabled or not
if the user added a permanent entry it shouldn't be deleted on igmp
leave.

Before:
$ echo 1 > /sys/class/net/eth4/brport/multicast_fast_leave
$ bridge mdb add dev br0 port eth4 grp 229.1.1.1 permanent
$ bridge mdb show
dev br0 port eth4 grp 229.1.1.1 permanent

< join and leave 229.1.1.1 on eth4 >

$ bridge mdb show
$

After:
$ echo 1 > /sys/class/net/eth4/brport/multicast_fast_leave
$ bridge mdb add dev br0 port eth4 grp 229.1.1.1 permanent
$ bridge mdb show
dev br0 port eth4 grp 229.1.1.1 permanent

< join and leave 229.1.1.1 on eth4 >

$ bridge mdb show
dev br0 port eth4 grp 229.1.1.1 permanent

Fixes: ccb1c31a7a87 ("bridge: add flags to distinguish permanent mdb entires")
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index fb54d32321ec..6a362da211e1 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1621,6 +1621,9 @@ br_multicast_leave_group(struct net_bridge *br,
 			if (!br_port_group_equal(p, port, src))
 				continue;
 
+			if (p->flags & MDB_PG_FLAGS_PERMANENT)
+				break;
+
 			rcu_assign_pointer(*pp, p->next);
 			hlist_del_init(&p->mglist);
 			del_timer(&p->timer);
-- 
2.20.1


From 4e35083430656d7cd3fd15ab10c39c8f6217382e Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sun, 28 Jul 2019 14:56:36 +0200
Subject: [PATCH 12/28] net: fix ifindex collision during namespace removal

[ Upstream commit 55b40dbf0e76b4bfb9d8b3a16a0208640a9a45df ]

Commit aca51397d014 ("netns: Fix arbitrary net_device-s corruptions
on net_ns stop.") introduced a possibility to hit a BUG in case device
is returning back to init_net and two following conditions are met:
1) dev->ifindex value is used in a name of another "dev%d"
   device in init_net.
2) dev->name is used by another device in init_net.

Under real life circumstances this is hard to get. Therefore this has
been present happily for over 10 years. To reproduce:

$ ip a
1: lo: <LOOPBACK,UP,LOWER_UP> mtu 65536 qdisc noqueue state UNKNOWN group default qlen 1000
    link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00
    inet 127.0.0.1/8 scope host lo
       valid_lft forever preferred_lft forever
    inet6 ::1/128 scope host
       valid_lft forever preferred_lft forever
2: dummy0: <BROADCAST,NOARP> mtu 1500 qdisc noop state DOWN group default qlen 1000
    link/ether 86:89:3f:86:61:29 brd ff:ff:ff:ff:ff:ff
3: enp0s2: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN group default qlen 1000
    link/ether 52:54:00:12:34:56 brd ff:ff:ff:ff:ff:ff
$ ip netns add ns1
$ ip -n ns1 link add dummy1ns1 type dummy
$ ip -n ns1 link add dummy2ns1 type dummy
$ ip link set enp0s2 netns ns1
$ ip -n ns1 link set enp0s2 name dummy0
[  100.858894] virtio_net virtio0 dummy0: renamed from enp0s2
$ ip link add dev4 type dummy
$ ip -n ns1 a
1: lo: <LOOPBACK> mtu 65536 qdisc noop state DOWN group default qlen 1000
    link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00
2: dummy1ns1: <BROADCAST,NOARP> mtu 1500 qdisc noop state DOWN group default qlen 1000
    link/ether 16:63:4c:38:3e:ff brd ff:ff:ff:ff:ff:ff
3: dummy2ns1: <BROADCAST,NOARP> mtu 1500 qdisc noop state DOWN group default qlen 1000
    link/ether aa:9e:86:dd:6b:5d brd ff:ff:ff:ff:ff:ff
4: dummy0: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN group default qlen 1000
    link/ether 52:54:00:12:34:56 brd ff:ff:ff:ff:ff:ff
$ ip a
1: lo: <LOOPBACK,UP,LOWER_UP> mtu 65536 qdisc noqueue state UNKNOWN group default qlen 1000
    link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00
    inet 127.0.0.1/8 scope host lo
       valid_lft forever preferred_lft forever
    inet6 ::1/128 scope host
       valid_lft forever preferred_lft forever
2: dummy0: <BROADCAST,NOARP> mtu 1500 qdisc noop state DOWN group default qlen 1000
    link/ether 86:89:3f:86:61:29 brd ff:ff:ff:ff:ff:ff
4: dev4: <BROADCAST,NOARP> mtu 1500 qdisc noop state DOWN group default qlen 1000
    link/ether 5a:e1:4a:b6:ec:f8 brd ff:ff:ff:ff:ff:ff
$ ip netns del ns1
[  158.717795] default_device_exit: failed to move dummy0 to init_net: -17
[  158.719316] ------------[ cut here ]------------
[  158.720591] kernel BUG at net/core/dev.c:9824!
[  158.722260] invalid opcode: 0000 [#1] SMP KASAN PTI
[  158.723728] CPU: 0 PID: 56 Comm: kworker/u2:1 Not tainted 5.3.0-rc1+ #18
[  158.725422] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-2.fc30 04/01/2014
[  158.727508] Workqueue: netns cleanup_net
[  158.728915] RIP: 0010:default_device_exit.cold+0x1d/0x1f
[  158.730683] Code: 84 e8 18 c9 3e fe 0f 0b e9 70 90 ff ff e8 36 e4 52 fe 89 d9 4c 89 e2 48 c7 c6 80 d6 25 84 48 c7 c7 20 c0 25 84 e8 f4 c8 3e
[  158.736854] RSP: 0018:ffff8880347e7b90 EFLAGS: 00010282
[  158.738752] RAX: 000000000000003b RBX: 00000000ffffffef RCX: 0000000000000000
[  158.741369] RDX: 0000000000000000 RSI: ffffffff8128013d RDI: ffffed10068fcf64
[  158.743418] RBP: ffff888033550170 R08: 000000000000003b R09: fffffbfff0b94b9c
[  158.745626] R10: fffffbfff0b94b9b R11: ffffffff85ca5cdf R12: ffff888032f28000
[  158.748405] R13: dffffc0000000000 R14: ffff8880335501b8 R15: 1ffff110068fcf72
[  158.750638] FS:  0000000000000000(0000) GS:ffff888036000000(0000) knlGS:0000000000000000
[  158.752944] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  158.755245] CR2: 00007fe8b45d21d0 CR3: 00000000340b4005 CR4: 0000000000360ef0
[  158.757654] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  158.760012] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[  158.762758] Call Trace:
[  158.763882]  ? dev_change_net_namespace+0xbb0/0xbb0
[  158.766148]  ? devlink_nl_cmd_set_doit+0x520/0x520
[  158.768034]  ? dev_change_net_namespace+0xbb0/0xbb0
[  158.769870]  ops_exit_list.isra.0+0xa8/0x150
[  158.771544]  cleanup_net+0x446/0x8f0
[  158.772945]  ? unregister_pernet_operations+0x4a0/0x4a0
[  158.775294]  process_one_work+0xa1a/0x1740
[  158.776896]  ? pwq_dec_nr_in_flight+0x310/0x310
[  158.779143]  ? do_raw_spin_lock+0x11b/0x280
[  158.780848]  worker_thread+0x9e/0x1060
[  158.782500]  ? process_one_work+0x1740/0x1740
[  158.784454]  kthread+0x31b/0x420
[  158.786082]  ? __kthread_create_on_node+0x3f0/0x3f0
[  158.788286]  ret_from_fork+0x3a/0x50
[  158.789871] ---[ end trace defd6c657c71f936 ]---
[  158.792273] RIP: 0010:default_device_exit.cold+0x1d/0x1f
[  158.795478] Code: 84 e8 18 c9 3e fe 0f 0b e9 70 90 ff ff e8 36 e4 52 fe 89 d9 4c 89 e2 48 c7 c6 80 d6 25 84 48 c7 c7 20 c0 25 84 e8 f4 c8 3e
[  158.804854] RSP: 0018:ffff8880347e7b90 EFLAGS: 00010282
[  158.807865] RAX: 000000000000003b RBX: 00000000ffffffef RCX: 0000000000000000
[  158.811794] RDX: 0000000000000000 RSI: ffffffff8128013d RDI: ffffed10068fcf64
[  158.816652] RBP: ffff888033550170 R08: 000000000000003b R09: fffffbfff0b94b9c
[  158.820930] R10: fffffbfff0b94b9b R11: ffffffff85ca5cdf R12: ffff888032f28000
[  158.825113] R13: dffffc0000000000 R14: ffff8880335501b8 R15: 1ffff110068fcf72
[  158.829899] FS:  0000000000000000(0000) GS:ffff888036000000(0000) knlGS:0000000000000000
[  158.834923] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  158.838164] CR2: 00007fe8b45d21d0 CR3: 00000000340b4005 CR4: 0000000000360ef0
[  158.841917] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  158.845149] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400

Fix this by checking if a device with the same name exists in init_net
and fallback to original code - dev%d to allocate name - in case it does.

This was found using syzkaller.

Fixes: aca51397d014 ("netns: Fix arbitrary net_device-s corruptions on net_ns stop.")
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/core/dev.c b/net/core/dev.c
index 138951d28643..e4b4cb40da00 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -9510,6 +9510,8 @@ static void __net_exit default_device_exit(struct net *net)
 
 		/* Push remaining network devices to init_net */
 		snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex);
+		if (__dev_get_by_name(&init_net, fb_name))
+			snprintf(fb_name, IFNAMSIZ, "dev%%d");
 		err = dev_change_net_namespace(dev, &init_net, fb_name);
 		if (err) {
 			pr_emerg("%s: failed to move %s to init_net: %d\n",
-- 
2.20.1


From 8039d419133ac0ea47c9eac5f28c018b77121ee9 Mon Sep 17 00:00:00 2001
From: Qian Cai <cai@lca.pw>
Date: Thu, 1 Aug 2019 09:52:54 -0400
Subject: [PATCH 13/28] net/mlx5e: always initialize frag->last_in_page

[ Upstream commit 60d60c8fbd8d1acf25b041ecd72ae4fa16e9405b ]

The commit 069d11465a80 ("net/mlx5e: RX, Enhance legacy Receive Queue
memory scheme") introduced an undefined behaviour below due to
"frag->last_in_page" is only initialized in mlx5e_init_frags_partition()
when,

if (next_frag.offset + frag_info[f].frag_stride > PAGE_SIZE)

or after bailed out the loop,

for (i = 0; i < mlx5_wq_cyc_get_size(&rq->wqe.wq); i++)

As the result, there could be some "frag" have uninitialized
value of "last_in_page".

Later, get_frag() obtains those "frag" and check "frag->last_in_page" in
mlx5e_put_rx_frag() and triggers the error during boot. Fix it by always
initializing "frag->last_in_page" to "false" in
mlx5e_init_frags_partition().

UBSAN: Undefined behaviour in
drivers/net/ethernet/mellanox/mlx5/core/en_rx.c:325:12
load of value 170 is not a valid value for type 'bool' (aka '_Bool')
Call trace:
 dump_backtrace+0x0/0x264
 show_stack+0x20/0x2c
 dump_stack+0xb0/0x104
 __ubsan_handle_load_invalid_value+0x104/0x128
 mlx5e_handle_rx_cqe+0x8e8/0x12cc [mlx5_core]
 mlx5e_poll_rx_cq+0xca8/0x1a94 [mlx5_core]
 mlx5e_napi_poll+0x17c/0xa30 [mlx5_core]
 net_rx_action+0x248/0x940
 __do_softirq+0x350/0x7b8
 irq_exit+0x200/0x26c
 __handle_domain_irq+0xc8/0x128
 gic_handle_irq+0x138/0x228
 el1_irq+0xb8/0x140
 arch_cpu_idle+0x1a4/0x348
 do_idle+0x114/0x1b0
 cpu_startup_entry+0x24/0x28
 rest_init+0x1ac/0x1dc
 arch_call_rest_init+0x10/0x18
 start_kernel+0x4d4/0x57c

Fixes: 069d11465a80 ("net/mlx5e: RX, Enhance legacy Receive Queue memory scheme")
Signed-off-by: Qian Cai <cai@lca.pw>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 0f1c296c3ce4..83ab2c0e6b61 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -420,12 +420,11 @@ static inline u64 mlx5e_get_mpwqe_offset(struct mlx5e_rq *rq, u16 wqe_ix)
 
 static void mlx5e_init_frags_partition(struct mlx5e_rq *rq)
 {
-	struct mlx5e_wqe_frag_info next_frag, *prev;
+	struct mlx5e_wqe_frag_info next_frag = {};
+	struct mlx5e_wqe_frag_info *prev = NULL;
 	int i;
 
 	next_frag.di = &rq->wqe.di[0];
-	next_frag.offset = 0;
-	prev = NULL;
 
 	for (i = 0; i < mlx5_wq_cyc_get_size(&rq->wqe.wq); i++) {
 		struct mlx5e_rq_frag_info *frag_info = &rq->wqe.info.arr[0];
-- 
2.20.1


From 163d5e63c85c861f8370741a688b36c03cbc9bf3 Mon Sep 17 00:00:00 2001
From: Mark Zhang <markz@mellanox.com>
Date: Tue, 9 Jul 2019 05:37:12 +0300
Subject: [PATCH 14/28] net/mlx5: Use reversed order when unregister devices

[ Upstream commit 08aa5e7da6bce1a1963f63cf32c2e7ad434ad578 ]

When lag is active, which is controlled by the bonded mlx5e netdev, mlx5
interface unregestering must happen in the reverse order where rdma is
unregistered (unloaded) first, to guarantee all references to the lag
context in hardware is removed, then remove mlx5e netdev interface which
will cleanup the lag context from hardware.

Without this fix during destroy of LAG interface, we observed following
errors:
 * mlx5_cmd_check:752:(pid 12556): DESTROY_LAG(0x843) op_mod(0x0) failed,
   status bad parameter(0x3), syndrome (0xe4ac33)
 * mlx5_cmd_check:752:(pid 12556): DESTROY_LAG(0x843) op_mod(0x0) failed,
   status bad parameter(0x3), syndrome (0xa5aee8).

Fixes: a31208b1e11d ("net/mlx5_core: New init and exit flow for mlx5_core")
Reviewed-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Mark Zhang <markz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
index 1c225be9c7db..3692d6a1cce8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -307,7 +307,7 @@ void mlx5_unregister_device(struct mlx5_core_dev *dev)
 	struct mlx5_interface *intf;
 
 	mutex_lock(&mlx5_intf_mutex);
-	list_for_each_entry(intf, &intf_list, list)
+	list_for_each_entry_reverse(intf, &intf_list, list)
 		mlx5_remove_device(intf, priv);
 	list_del(&priv->dev_list);
 	mutex_unlock(&mlx5_intf_mutex);
-- 
2.20.1


From 8fce402c7b80564c57ec02fa1b336062c2e84558 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ren=C3=A9=20van=20Dorst?= <opensource@vdorst.com>
Date: Sat, 27 Jul 2019 11:40:11 +0200
Subject: [PATCH 15/28] net: phylink: Fix flow control for fixed-link
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 8aace4f3eba2a3ceb431e18683ea0e1ecbade5cd ]

In phylink_parse_fixedlink() the pl->link_config.advertising bits are AND
with pl->supported, pl->supported is zeroed and only the speed/duplex
modes and MII bits are set.
So pl->link_config.advertising always loses the flow control/pause bits.

By setting Pause and Asym_Pause bits in pl->supported, the flow control
work again when devicetree "pause" is set in fixes-link node and the MAC
advertise that is supports pause.

Results with this patch.

Legend:
- DT = 'Pause' is set in the fixed-link in devicetree.
- validate() = ‘Yes’ means phylink_set(mask, Pause) is set in the
  validate().
- flow = results reported my link is Up line.

+-----+------------+-------+
| DT  | validate() | flow  |
+-----+------------+-------+
| Yes | Yes        | rx/tx |
| No  | Yes        | off   |
| Yes | No         | off   |
+-----+------------+-------+

Fixes: 9525ae83959b ("phylink: add phylink infrastructure")
Signed-off-by: René van Dorst <opensource@vdorst.com>
Acked-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phylink.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index e029c7977a56..2e8056d48f4a 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -226,6 +226,8 @@ static int phylink_parse_fixedlink(struct phylink *pl,
 			       __ETHTOOL_LINK_MODE_MASK_NBITS, true);
 	linkmode_zero(pl->supported);
 	phylink_set(pl->supported, MII);
+	phylink_set(pl->supported, Pause);
+	phylink_set(pl->supported, Asym_Pause);
 	if (s) {
 		__set_bit(s->bit, pl->supported);
 	} else {
-- 
2.20.1


From 8707d97f204ddad9891951bb4a42e3ffe4b4ca73 Mon Sep 17 00:00:00 2001
From: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Date: Thu, 25 Jul 2019 12:07:12 -0600
Subject: [PATCH 16/28] net: qualcomm: rmnet: Fix incorrect UL checksum offload
 logic

[ Upstream commit a7cf3d24ee6081930feb4c830a7f6f16ebe31c49 ]

The udp_ip4_ind bit is set only for IPv4 UDP non-fragmented packets
so that the hardware can flip the checksum to 0xFFFF if the computed
checksum is 0 per RFC768.

However, this bit had to be set for IPv6 UDP non fragmented packets
as well per hardware requirements. Otherwise, IPv6 UDP packets
with computed checksum as 0 were transmitted by hardware and were
dropped in the network.

In addition to setting this bit for IPv6 UDP, the field is also
appropriately renamed to udp_ind as part of this change.

Fixes: 5eb5f8608ef1 ("net: qualcomm: rmnet: Add support for TX checksum offload")
Cc: Sean Tranchetti <stranche@codeaurora.org>
Signed-off-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h     |  2 +-
 .../net/ethernet/qualcomm/rmnet/rmnet_map_data.c    | 13 +++++++++----
 2 files changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h
index 884f1f52dcc2..70879a3ab567 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h
@@ -59,7 +59,7 @@ struct rmnet_map_dl_csum_trailer {
 struct rmnet_map_ul_csum_header {
 	__be16 csum_start_offset;
 	u16 csum_insert_offset:14;
-	u16 udp_ip4_ind:1;
+	u16 udp_ind:1;
 	u16 csum_enabled:1;
 } __aligned(1);
 
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c
index 57a9c314a665..b2090cedd2e9 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c
@@ -215,9 +215,9 @@ rmnet_map_ipv4_ul_csum_header(void *iphdr,
 	ul_header->csum_insert_offset = skb->csum_offset;
 	ul_header->csum_enabled = 1;
 	if (ip4h->protocol == IPPROTO_UDP)
-		ul_header->udp_ip4_ind = 1;
+		ul_header->udp_ind = 1;
 	else
-		ul_header->udp_ip4_ind = 0;
+		ul_header->udp_ind = 0;
 
 	/* Changing remaining fields to network order */
 	hdr++;
@@ -248,6 +248,7 @@ rmnet_map_ipv6_ul_csum_header(void *ip6hdr,
 			      struct rmnet_map_ul_csum_header *ul_header,
 			      struct sk_buff *skb)
 {
+	struct ipv6hdr *ip6h = (struct ipv6hdr *)ip6hdr;
 	__be16 *hdr = (__be16 *)ul_header, offset;
 
 	offset = htons((__force u16)(skb_transport_header(skb) -
@@ -255,7 +256,11 @@ rmnet_map_ipv6_ul_csum_header(void *ip6hdr,
 	ul_header->csum_start_offset = offset;
 	ul_header->csum_insert_offset = skb->csum_offset;
 	ul_header->csum_enabled = 1;
-	ul_header->udp_ip4_ind = 0;
+
+	if (ip6h->nexthdr == IPPROTO_UDP)
+		ul_header->udp_ind = 1;
+	else
+		ul_header->udp_ind = 0;
 
 	/* Changing remaining fields to network order */
 	hdr++;
@@ -428,7 +433,7 @@ void rmnet_map_checksum_uplink_packet(struct sk_buff *skb,
 	ul_header->csum_start_offset = 0;
 	ul_header->csum_insert_offset = 0;
 	ul_header->csum_enabled = 0;
-	ul_header->udp_ip4_ind = 0;
+	ul_header->udp_ind = 0;
 
 	priv->stats.csum_sw++;
 }
-- 
2.20.1


From 5d03107e4146d7d377f0b0ba61b0334eab695ebe Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Mon, 29 Jul 2019 16:24:33 +0800
Subject: [PATCH 17/28] net: sched: Fix a possible null-pointer dereference in
 dequeue_func()

[ Upstream commit 051c7b39be4a91f6b7d8c4548444e4b850f1f56c ]

In dequeue_func(), there is an if statement on line 74 to check whether
skb is NULL:
    if (skb)

When skb is NULL, it is used on line 77:
    prefetch(&skb->end);

Thus, a possible null-pointer dereference may occur.

To fix this bug, skb->end is used when skb is not NULL.

This bug is found by a static analysis tool STCheck written by us.

Fixes: 76e3cc126bb2 ("codel: Controlled Delay AQM")
Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_codel.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c
index 17cd81f84b5d..77fae0b7c6ee 100644
--- a/net/sched/sch_codel.c
+++ b/net/sched/sch_codel.c
@@ -71,10 +71,10 @@ static struct sk_buff *dequeue_func(struct codel_vars *vars, void *ctx)
 	struct Qdisc *sch = ctx;
 	struct sk_buff *skb = __qdisc_dequeue_head(&sch->q);
 
-	if (skb)
+	if (skb) {
 		sch->qstats.backlog -= qdisc_pkt_len(skb);
-
-	prefetch(&skb->end); /* we'll need skb_shinfo() */
+		prefetch(&skb->end); /* we'll need skb_shinfo() */
+	}
 	return skb;
 }
 
-- 
2.20.1


From 6ac3c813619e918d57fdf74250a0c23f383bb361 Mon Sep 17 00:00:00 2001
From: Roman Mashak <mrv@mojatatu.com>
Date: Fri, 2 Aug 2019 15:16:46 -0400
Subject: [PATCH 18/28] net sched: update vlan action for batched events
 operations

[ Upstream commit b35475c5491a14c8ce7a5046ef7bcda8a860581a ]

Add get_fill_size() routine used to calculate the action size
when building a batch of events.

Fixes: c7e2b9689 ("sched: introduce vlan action")
Signed-off-by: Roman Mashak <mrv@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_vlan.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 033d273afe50..20a7d4dc381c 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -296,6 +296,14 @@ static int tcf_vlan_search(struct net *net, struct tc_action **a, u32 index,
 	return tcf_idr_search(tn, a, index);
 }
 
+static size_t tcf_vlan_get_fill_size(const struct tc_action *act)
+{
+	return nla_total_size(sizeof(struct tc_vlan))
+		+ nla_total_size(sizeof(u16)) /* TCA_VLAN_PUSH_VLAN_ID */
+		+ nla_total_size(sizeof(u16)) /* TCA_VLAN_PUSH_VLAN_PROTOCOL */
+		+ nla_total_size(sizeof(u8)); /* TCA_VLAN_PUSH_VLAN_PRIORITY */
+}
+
 static struct tc_action_ops act_vlan_ops = {
 	.kind		=	"vlan",
 	.type		=	TCA_ACT_VLAN,
@@ -305,6 +313,7 @@ static struct tc_action_ops act_vlan_ops = {
 	.init		=	tcf_vlan_init,
 	.cleanup	=	tcf_vlan_cleanup,
 	.walk		=	tcf_vlan_walker,
+	.get_fill_size	=	tcf_vlan_get_fill_size,
 	.lookup		=	tcf_vlan_search,
 	.size		=	sizeof(struct tcf_vlan),
 };
-- 
2.20.1


From 158c444deb2719f7cd09f7665cc0a8d1bbab3349 Mon Sep 17 00:00:00 2001
From: Dmytro Linkin <dmitrolin@mellanox.com>
Date: Thu, 1 Aug 2019 13:02:51 +0000
Subject: [PATCH 19/28] net: sched: use temporary variable for actions indexes

[ Upstream commit 7be8ef2cdbfe41a2e524b7c6cc3f8e6cfaa906e4 ]

Currently init call of all actions (except ipt) init their 'parm'
structure as a direct pointer to nla data in skb. This leads to race
condition when some of the filter actions were initialized successfully
(and were assigned with idr action index that was written directly
into nla data), but then were deleted and retried (due to following
action module missing or classifier-initiated retry), in which case
action init code tries to insert action to idr with index that was
assigned on previous iteration. During retry the index can be reused
by another action that was inserted concurrently, which causes
unintended action sharing between filters.
To fix described race condition, save action idr index to temporary
stack-allocated variable instead on nla data.

Fixes: 0190c1d452a9 ("net: sched: atomically check-allocate action")
Signed-off-by: Dmytro Linkin <dmitrolin@mellanox.com>
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_bpf.c        |  9 +++++----
 net/sched/act_connmark.c   |  9 +++++----
 net/sched/act_csum.c       |  9 +++++----
 net/sched/act_gact.c       |  8 +++++---
 net/sched/act_ife.c        |  8 +++++---
 net/sched/act_mirred.c     | 13 +++++++------
 net/sched/act_nat.c        |  9 +++++----
 net/sched/act_pedit.c      | 10 ++++++----
 net/sched/act_police.c     |  8 +++++---
 net/sched/act_sample.c     | 10 +++++-----
 net/sched/act_simple.c     | 10 ++++++----
 net/sched/act_skbedit.c    | 11 ++++++-----
 net/sched/act_skbmod.c     | 11 ++++++-----
 net/sched/act_tunnel_key.c |  8 +++++---
 net/sched/act_vlan.c       | 16 +++++++++-------
 15 files changed, 85 insertions(+), 64 deletions(-)

diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 0c68bc9cf0b4..20fae5ca87fa 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -287,6 +287,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 	struct tcf_bpf *prog;
 	bool is_bpf, is_ebpf;
 	int ret, res = 0;
+	u32 index;
 
 	if (!nla)
 		return -EINVAL;
@@ -299,13 +300,13 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 		return -EINVAL;
 
 	parm = nla_data(tb[TCA_ACT_BPF_PARMS]);
-
-	ret = tcf_idr_check_alloc(tn, &parm->index, act, bind);
+	index = parm->index;
+	ret = tcf_idr_check_alloc(tn, &index, act, bind);
 	if (!ret) {
-		ret = tcf_idr_create(tn, parm->index, est, act,
+		ret = tcf_idr_create(tn, index, est, act,
 				     &act_bpf_ops, bind, true);
 		if (ret < 0) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index 6f0f273f1139..605436747978 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -104,6 +104,7 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla,
 	struct tcf_connmark_info *ci;
 	struct tc_connmark *parm;
 	int ret = 0;
+	u32 index;
 
 	if (!nla)
 		return -EINVAL;
@@ -117,13 +118,13 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla,
 		return -EINVAL;
 
 	parm = nla_data(tb[TCA_CONNMARK_PARMS]);
-
-	ret = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	ret = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (!ret) {
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_connmark_ops, bind, false);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index b8a67ae3105a..40437197e053 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -55,6 +55,7 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla,
 	struct tc_csum *parm;
 	struct tcf_csum *p;
 	int ret = 0, err;
+	u32 index;
 
 	if (nla == NULL)
 		return -EINVAL;
@@ -66,13 +67,13 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla,
 	if (tb[TCA_CSUM_PARMS] == NULL)
 		return -EINVAL;
 	parm = nla_data(tb[TCA_CSUM_PARMS]);
-
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (!err) {
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_csum_ops, bind, true);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 		ret = ACT_P_CREATED;
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index cd1d9bd32ef9..72d3347bdd41 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -64,6 +64,7 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
 	struct tc_gact *parm;
 	struct tcf_gact *gact;
 	int ret = 0;
+	u32 index;
 	int err;
 #ifdef CONFIG_GACT_PROB
 	struct tc_gact_p *p_parm = NULL;
@@ -79,6 +80,7 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
 	if (tb[TCA_GACT_PARMS] == NULL)
 		return -EINVAL;
 	parm = nla_data(tb[TCA_GACT_PARMS]);
+	index = parm->index;
 
 #ifndef CONFIG_GACT_PROB
 	if (tb[TCA_GACT_PROB] != NULL)
@@ -91,12 +93,12 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
 	}
 #endif
 
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (!err) {
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_gact_ops, bind, true);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 		ret = ACT_P_CREATED;
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 915b6e94da63..24047e0e5db0 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -482,6 +482,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	u8 *saddr = NULL;
 	bool exists = false;
 	int ret = 0;
+	u32 index;
 	int err;
 
 	if (!nla) {
@@ -509,7 +510,8 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	if (!p)
 		return -ENOMEM;
 
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (err < 0) {
 		kfree(p);
 		return err;
@@ -521,10 +523,10 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	}
 
 	if (!exists) {
-		ret = tcf_idr_create(tn, parm->index, est, a, &act_ife_ops,
+		ret = tcf_idr_create(tn, index, est, a, &act_ife_ops,
 				     bind, true);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			kfree(p);
 			return ret;
 		}
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index f767e78e38c9..548614bd9366 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -104,6 +104,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 	struct net_device *dev;
 	bool exists = false;
 	int ret, err;
+	u32 index;
 
 	if (!nla) {
 		NL_SET_ERR_MSG_MOD(extack, "Mirred requires attributes to be passed");
@@ -117,8 +118,8 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 		return -EINVAL;
 	}
 	parm = nla_data(tb[TCA_MIRRED_PARMS]);
-
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (err < 0)
 		return err;
 	exists = err;
@@ -135,21 +136,21 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 		if (exists)
 			tcf_idr_release(*a, bind);
 		else
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 		NL_SET_ERR_MSG_MOD(extack, "Unknown mirred option");
 		return -EINVAL;
 	}
 
 	if (!exists) {
 		if (!parm->ifindex) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			NL_SET_ERR_MSG_MOD(extack, "Specified device does not exist");
 			return -EINVAL;
 		}
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_mirred_ops, bind, true);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 		ret = ACT_P_CREATED;
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 4313aa102440..619828920b97 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -45,6 +45,7 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
 	struct tc_nat *parm;
 	int ret = 0, err;
 	struct tcf_nat *p;
+	u32 index;
 
 	if (nla == NULL)
 		return -EINVAL;
@@ -56,13 +57,13 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
 	if (tb[TCA_NAT_PARMS] == NULL)
 		return -EINVAL;
 	parm = nla_data(tb[TCA_NAT_PARMS]);
-
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (!err) {
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_nat_ops, bind, false);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 		ret = ACT_P_CREATED;
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index ca535a8585bc..82d258b2a75a 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -149,6 +149,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 	struct tcf_pedit *p;
 	int ret = 0, err;
 	int ksize;
+	u32 index;
 
 	if (!nla) {
 		NL_SET_ERR_MSG_MOD(extack, "Pedit requires attributes to be passed");
@@ -178,18 +179,19 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 	if (IS_ERR(keys_ex))
 		return PTR_ERR(keys_ex);
 
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (!err) {
 		if (!parm->nkeys) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed");
 			ret = -EINVAL;
 			goto out_free;
 		}
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_pedit_ops, bind, false);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			goto out_free;
 		}
 		ret = ACT_P_CREATED;
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 5d8bfa878477..997c34db1491 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -85,6 +85,7 @@ static int tcf_police_init(struct net *net, struct nlattr *nla,
 	struct qdisc_rate_table *R_tab = NULL, *P_tab = NULL;
 	struct tc_action_net *tn = net_generic(net, police_net_id);
 	bool exists = false;
+	u32 index;
 	int size;
 
 	if (nla == NULL)
@@ -101,7 +102,8 @@ static int tcf_police_init(struct net *net, struct nlattr *nla,
 		return -EINVAL;
 
 	parm = nla_data(tb[TCA_POLICE_TBF]);
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (err < 0)
 		return err;
 	exists = err;
@@ -109,10 +111,10 @@ static int tcf_police_init(struct net *net, struct nlattr *nla,
 		return 0;
 
 	if (!exists) {
-		ret = tcf_idr_create(tn, parm->index, NULL, a,
+		ret = tcf_idr_create(tn, index, NULL, a,
 				     &act_police_ops, bind, false);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 		ret = ACT_P_CREATED;
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index c7f5d630d97c..ac37654ca292 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -43,7 +43,7 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 	struct tc_action_net *tn = net_generic(net, sample_net_id);
 	struct nlattr *tb[TCA_SAMPLE_MAX + 1];
 	struct psample_group *psample_group;
-	u32 psample_group_num, rate;
+	u32 psample_group_num, rate, index;
 	struct tc_sample *parm;
 	struct tcf_sample *s;
 	bool exists = false;
@@ -59,8 +59,8 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 		return -EINVAL;
 
 	parm = nla_data(tb[TCA_SAMPLE_PARMS]);
-
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (err < 0)
 		return err;
 	exists = err;
@@ -68,10 +68,10 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 		return 0;
 
 	if (!exists) {
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_sample_ops, bind, true);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 		ret = ACT_P_CREATED;
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 52400d49f81f..658efae71a09 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -88,6 +88,7 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
 	struct tcf_defact *d;
 	bool exists = false;
 	int ret = 0, err;
+	u32 index;
 
 	if (nla == NULL)
 		return -EINVAL;
@@ -100,7 +101,8 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
 		return -EINVAL;
 
 	parm = nla_data(tb[TCA_DEF_PARMS]);
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (err < 0)
 		return err;
 	exists = err;
@@ -111,15 +113,15 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
 		if (exists)
 			tcf_idr_release(*a, bind);
 		else
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 		return -EINVAL;
 	}
 
 	if (!exists) {
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_simp_ops, bind, false);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 86d90fc5e97e..7709710a41f7 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -107,6 +107,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 	u16 *queue_mapping = NULL, *ptype = NULL;
 	bool exists = false;
 	int ret = 0, err;
+	u32 index;
 
 	if (nla == NULL)
 		return -EINVAL;
@@ -153,8 +154,8 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 	}
 
 	parm = nla_data(tb[TCA_SKBEDIT_PARMS]);
-
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (err < 0)
 		return err;
 	exists = err;
@@ -165,15 +166,15 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 		if (exists)
 			tcf_idr_release(*a, bind);
 		else
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 		return -EINVAL;
 	}
 
 	if (!exists) {
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_skbedit_ops, bind, true);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index 588077fafd6c..3038493d18ca 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -88,12 +88,12 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
 	struct nlattr *tb[TCA_SKBMOD_MAX + 1];
 	struct tcf_skbmod_params *p, *p_old;
 	struct tc_skbmod *parm;
+	u32 lflags = 0, index;
 	struct tcf_skbmod *d;
 	bool exists = false;
 	u8 *daddr = NULL;
 	u8 *saddr = NULL;
 	u16 eth_type = 0;
-	u32 lflags = 0;
 	int ret = 0, err;
 
 	if (!nla)
@@ -122,10 +122,11 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
 	}
 
 	parm = nla_data(tb[TCA_SKBMOD_PARMS]);
+	index = parm->index;
 	if (parm->flags & SKBMOD_F_SWAPMAC)
 		lflags = SKBMOD_F_SWAPMAC;
 
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (err < 0)
 		return err;
 	exists = err;
@@ -136,15 +137,15 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
 		if (exists)
 			tcf_idr_release(*a, bind);
 		else
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 		return -EINVAL;
 	}
 
 	if (!exists) {
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_skbmod_ops, bind, true);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 72d9c432e8b4..66bfe57e74ae 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -224,6 +224,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 	__be16 flags;
 	u8 tos, ttl;
 	int ret = 0;
+	u32 index;
 	int err;
 
 	if (!nla) {
@@ -244,7 +245,8 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 	}
 
 	parm = nla_data(tb[TCA_TUNNEL_KEY_PARMS]);
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (err < 0)
 		return err;
 	exists = err;
@@ -338,7 +340,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 	}
 
 	if (!exists) {
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_tunnel_key_ops, bind, true);
 		if (ret) {
 			NL_SET_ERR_MSG(extack, "Cannot create TC IDR");
@@ -384,7 +386,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 	if (exists)
 		tcf_idr_release(*a, bind);
 	else
-		tcf_idr_cleanup(tn, parm->index);
+		tcf_idr_cleanup(tn, index);
 	return ret;
 }
 
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 20a7d4dc381c..da993edd2e40 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -118,6 +118,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 	u8 push_prio = 0;
 	bool exists = false;
 	int ret = 0, err;
+	u32 index;
 
 	if (!nla)
 		return -EINVAL;
@@ -129,7 +130,8 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 	if (!tb[TCA_VLAN_PARMS])
 		return -EINVAL;
 	parm = nla_data(tb[TCA_VLAN_PARMS]);
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (err < 0)
 		return err;
 	exists = err;
@@ -145,7 +147,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 			if (exists)
 				tcf_idr_release(*a, bind);
 			else
-				tcf_idr_cleanup(tn, parm->index);
+				tcf_idr_cleanup(tn, index);
 			return -EINVAL;
 		}
 		push_vid = nla_get_u16(tb[TCA_VLAN_PUSH_VLAN_ID]);
@@ -153,7 +155,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 			if (exists)
 				tcf_idr_release(*a, bind);
 			else
-				tcf_idr_cleanup(tn, parm->index);
+				tcf_idr_cleanup(tn, index);
 			return -ERANGE;
 		}
 
@@ -167,7 +169,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 				if (exists)
 					tcf_idr_release(*a, bind);
 				else
-					tcf_idr_cleanup(tn, parm->index);
+					tcf_idr_cleanup(tn, index);
 				return -EPROTONOSUPPORT;
 			}
 		} else {
@@ -181,16 +183,16 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 		if (exists)
 			tcf_idr_release(*a, bind);
 		else
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 		return -EINVAL;
 	}
 	action = parm->v_action;
 
 	if (!exists) {
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_vlan_ops, bind, true);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 
-- 
2.20.1


From 5ec774dbd9e8facf597d3d594f039890826b8742 Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.ibm.com>
Date: Fri, 2 Aug 2019 10:16:38 +0200
Subject: [PATCH 20/28] net/smc: do not schedule tx_work in SMC_CLOSED state

[ Upstream commit f9cedf1a9b1cdcfb0c52edb391d01771e43994a4 ]

The setsockopts options TCP_NODELAY and TCP_CORK may schedule the
tx worker. Make sure the socket is not yet moved into SMC_CLOSED
state (for instance by a shutdown SHUT_RDWR call).

Reported-by: syzbot+92209502e7aab127c75f@syzkaller.appspotmail.com
Reported-by: syzbot+b972214bb803a343f4fe@syzkaller.appspotmail.com
Fixes: 01d2f7e2cdd31 ("net/smc: sockopts TCP_NODELAY and TCP_CORK")
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/af_smc.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 9bbab6ba2dab..26dcd02b2d0c 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1680,14 +1680,18 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
 		}
 		break;
 	case TCP_NODELAY:
-		if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) {
+		if (sk->sk_state != SMC_INIT &&
+		    sk->sk_state != SMC_LISTEN &&
+		    sk->sk_state != SMC_CLOSED) {
 			if (val && !smc->use_fallback)
 				mod_delayed_work(system_wq, &smc->conn.tx_work,
 						 0);
 		}
 		break;
 	case TCP_CORK:
-		if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) {
+		if (sk->sk_state != SMC_INIT &&
+		    sk->sk_state != SMC_LISTEN &&
+		    sk->sk_state != SMC_CLOSED) {
 			if (!val && !smc->use_fallback)
 				mod_delayed_work(system_wq, &smc->conn.tx_work,
 						 0);
-- 
2.20.1


From d970c499bf972871e7dcc760e83e18583a2e7b2d Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 5 Aug 2019 12:00:55 +0200
Subject: [PATCH 21/28] NFC: nfcmrvl: fix gpio-handling regression

[ Upstream commit c3953a3c2d3175d2f9f0304c9a1ba89e7743c5e4 ]

Fix two reset-gpio sanity checks which were never converted to use
gpio_is_valid(), and make sure to use -EINVAL to indicate a missing
reset line also for the UART-driver module parameter and for the USB
driver.

This specifically prevents the UART and USB drivers from incidentally
trying to request and use gpio 0, and also avoids triggering a WARN() in
gpio_to_desc() during probe when no valid reset line has been specified.

Fixes: e33a3f84f88f ("NFC: nfcmrvl: allow gpio 0 for reset signalling")
Reported-by: syzbot+cf35b76f35e068a1107f@syzkaller.appspotmail.com
Tested-by: syzbot+cf35b76f35e068a1107f@syzkaller.appspotmail.com
Signed-off-by: Johan Hovold <johan@kernel.org>
---
 drivers/nfc/nfcmrvl/main.c | 4 ++--
 drivers/nfc/nfcmrvl/uart.c | 4 ++--
 drivers/nfc/nfcmrvl/usb.c  | 1 +
 3 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/nfc/nfcmrvl/main.c b/drivers/nfc/nfcmrvl/main.c
index e65d027b91fa..529be35ac178 100644
--- a/drivers/nfc/nfcmrvl/main.c
+++ b/drivers/nfc/nfcmrvl/main.c
@@ -244,7 +244,7 @@ void nfcmrvl_chip_reset(struct nfcmrvl_private *priv)
 	/* Reset possible fault of previous session */
 	clear_bit(NFCMRVL_PHY_ERROR, &priv->flags);
 
-	if (priv->config.reset_n_io) {
+	if (gpio_is_valid(priv->config.reset_n_io)) {
 		nfc_info(priv->dev, "reset the chip\n");
 		gpio_set_value(priv->config.reset_n_io, 0);
 		usleep_range(5000, 10000);
@@ -255,7 +255,7 @@ void nfcmrvl_chip_reset(struct nfcmrvl_private *priv)
 
 void nfcmrvl_chip_halt(struct nfcmrvl_private *priv)
 {
-	if (priv->config.reset_n_io)
+	if (gpio_is_valid(priv->config.reset_n_io))
 		gpio_set_value(priv->config.reset_n_io, 0);
 }
 
diff --git a/drivers/nfc/nfcmrvl/uart.c b/drivers/nfc/nfcmrvl/uart.c
index 9a22056e8d9e..e5a622ce4b95 100644
--- a/drivers/nfc/nfcmrvl/uart.c
+++ b/drivers/nfc/nfcmrvl/uart.c
@@ -26,7 +26,7 @@
 static unsigned int hci_muxed;
 static unsigned int flow_control;
 static unsigned int break_control;
-static unsigned int reset_n_io;
+static int reset_n_io = -EINVAL;
 
 /*
 ** NFCMRVL NCI OPS
@@ -231,5 +231,5 @@ MODULE_PARM_DESC(break_control, "Tell if UART driver must drive break signal.");
 module_param(hci_muxed, uint, 0);
 MODULE_PARM_DESC(hci_muxed, "Tell if transport is muxed in HCI one.");
 
-module_param(reset_n_io, uint, 0);
+module_param(reset_n_io, int, 0);
 MODULE_PARM_DESC(reset_n_io, "GPIO that is wired to RESET_N signal.");
diff --git a/drivers/nfc/nfcmrvl/usb.c b/drivers/nfc/nfcmrvl/usb.c
index 945cc903d8f1..888e298f610b 100644
--- a/drivers/nfc/nfcmrvl/usb.c
+++ b/drivers/nfc/nfcmrvl/usb.c
@@ -305,6 +305,7 @@ static int nfcmrvl_probe(struct usb_interface *intf,
 
 	/* No configuration for USB */
 	memset(&config, 0, sizeof(config));
+	config.reset_n_io = -EINVAL;
 
 	nfc_info(&udev->dev, "intf %p id %p\n", intf, id);
 
-- 
2.20.1


From 152f2afd266765f8340d719885dfbd1ac0d6e3b7 Mon Sep 17 00:00:00 2001
From: Claudiu Manoil <claudiu.manoil@nxp.com>
Date: Thu, 25 Jul 2019 16:33:18 +0300
Subject: [PATCH 22/28] ocelot: Cancel delayed work before wq destruction

[ Upstream commit c5d139697d5d9ecf9c7cd92d7d7838a173508900 ]

Make sure the delayed work for stats update is not pending before
wq destruction.
This fixes the module unload path.
The issue is there since day 1.

Fixes: a556c76adc05 ("net: mscc: Add initial Ocelot switch support")

Signed-off-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Reviewed-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 10291198decd..732ba21d3369 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -1767,6 +1767,7 @@ EXPORT_SYMBOL(ocelot_init);
 
 void ocelot_deinit(struct ocelot *ocelot)
 {
+	cancel_delayed_work(&ocelot->stats_work);
 	destroy_workqueue(ocelot->stats_queue);
 	mutex_destroy(&ocelot->stats_lock);
 }
-- 
2.20.1


From 50d6b10cdf31c8702dd13705da4f644a13c15563 Mon Sep 17 00:00:00 2001
From: Taras Kondratiuk <takondra@cisco.com>
Date: Mon, 29 Jul 2019 22:15:07 +0000
Subject: [PATCH 23/28] tipc: compat: allow tipc commands without arguments

[ Upstream commit 4da5f0018eef4c0de31675b670c80e82e13e99d1 ]

Commit 2753ca5d9009 ("tipc: fix uninit-value in tipc_nl_compat_doit")
broke older tipc tools that use compat interface (e.g. tipc-config from
tipcutils package):

% tipc-config -p
operation not supported

The commit started to reject TIPC netlink compat messages that do not
have attributes. It is too restrictive because some of such messages are
valid (they don't need any arguments):

% grep 'tx none' include/uapi/linux/tipc_config.h
#define  TIPC_CMD_NOOP              0x0000    /* tx none, rx none */
#define  TIPC_CMD_GET_MEDIA_NAMES   0x0002    /* tx none, rx media_name(s) */
#define  TIPC_CMD_GET_BEARER_NAMES  0x0003    /* tx none, rx bearer_name(s) */
#define  TIPC_CMD_SHOW_PORTS        0x0006    /* tx none, rx ultra_string */
#define  TIPC_CMD_GET_REMOTE_MNG    0x4003    /* tx none, rx unsigned */
#define  TIPC_CMD_GET_MAX_PORTS     0x4004    /* tx none, rx unsigned */
#define  TIPC_CMD_GET_NETID         0x400B    /* tx none, rx unsigned */
#define  TIPC_CMD_NOT_NET_ADMIN     0xC001    /* tx none, rx none */

This patch relaxes the original fix and rejects messages without
arguments only if such arguments are expected by a command (reg_type is
non zero).

Fixes: 2753ca5d9009 ("tipc: fix uninit-value in tipc_nl_compat_doit")
Cc: stable@vger.kernel.org
Signed-off-by: Taras Kondratiuk <takondra@cisco.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/netlink_compat.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 85ebb675600c..318c541970ec 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -55,6 +55,7 @@ struct tipc_nl_compat_msg {
 	int rep_type;
 	int rep_size;
 	int req_type;
+	int req_size;
 	struct net *net;
 	struct sk_buff *rep;
 	struct tlv_desc *req;
@@ -257,7 +258,8 @@ static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd,
 	int err;
 	struct sk_buff *arg;
 
-	if (msg->req_type && !TLV_CHECK_TYPE(msg->req, msg->req_type))
+	if (msg->req_type && (!msg->req_size ||
+			      !TLV_CHECK_TYPE(msg->req, msg->req_type)))
 		return -EINVAL;
 
 	msg->rep = tipc_tlv_alloc(msg->rep_size);
@@ -354,7 +356,8 @@ static int tipc_nl_compat_doit(struct tipc_nl_compat_cmd_doit *cmd,
 {
 	int err;
 
-	if (msg->req_type && !TLV_CHECK_TYPE(msg->req, msg->req_type))
+	if (msg->req_type && (!msg->req_size ||
+			      !TLV_CHECK_TYPE(msg->req, msg->req_type)))
 		return -EINVAL;
 
 	err = __tipc_nl_compat_doit(cmd, msg);
@@ -1276,8 +1279,8 @@ static int tipc_nl_compat_recv(struct sk_buff *skb, struct genl_info *info)
 		goto send;
 	}
 
-	len = nlmsg_attrlen(req_nlh, GENL_HDRLEN + TIPC_GENL_HDRLEN);
-	if (!len || !TLV_OK(msg.req, len)) {
+	msg.req_size = nlmsg_attrlen(req_nlh, GENL_HDRLEN + TIPC_GENL_HDRLEN);
+	if (msg.req_size && !TLV_OK(msg.req, msg.req_size)) {
 		msg.rep = tipc_get_err_tlv(TIPC_CFG_NOT_SUPPORTED);
 		err = -EOPNOTSUPP;
 		goto send;
-- 
2.20.1


From dda760b6f93e95bc2db418dbd7bfe74f7ec813ca Mon Sep 17 00:00:00 2001
From: Alexis Bauvin <abauvin@scaleway.com>
Date: Tue, 23 Jul 2019 16:23:01 +0200
Subject: [PATCH 24/28] tun: mark small packets as owned by the tap sock

[ Upstream commit 4b663366246be1d1d4b1b8b01245b2e88ad9e706 ]

- v1 -> v2: Move skb_set_owner_w to __tun_build_skb to reduce patch size

Small packets going out of a tap device go through an optimized code
path that uses build_skb() rather than sock_alloc_send_pskb(). The
latter calls skb_set_owner_w(), but the small packet code path does not.

The net effect is that small packets are not owned by the userland
application's socket (e.g. QEMU), while large packets are.
This can be seen with a TCP session, where packets are not owned when
the window size is small enough (around PAGE_SIZE), while they are once
the window grows (note that this requires the host to support virtio
tso for the guest to offload segmentation).
All this leads to inconsistent behaviour in the kernel, especially on
netfilter modules that uses sk->socket (e.g. xt_owner).

Fixes: 66ccbc9c87c2 ("tap: use build_skb() for small packet")
Signed-off-by: Alexis Bauvin <abauvin@scaleway.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index b67fee56ec81..5fa7047ea361 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1682,6 +1682,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 
 	skb_reserve(skb, pad - delta);
 	skb_put(skb, len);
+	skb_set_owner_w(skb, tfile->socket.sk);
 	get_page(alloc_frag->page);
 	alloc_frag->offset += buflen;
 
-- 
2.20.1


From 08ec293e8bac4c2fa06bc56e4a3cb96b19985205 Mon Sep 17 00:00:00 2001
From: Edward Srouji <edwards@mellanox.com>
Date: Tue, 23 Jul 2019 10:12:55 +0300
Subject: [PATCH 25/28] net/mlx5: Fix modify_cq_in alignment

[ Upstream commit 7a32f2962c56d9d8a836b4469855caeee8766bd4 ]

Fix modify_cq_in alignment to match the device specification.
After this fix the 'cq_umem_valid' field will be in the right offset.

Cc: <stable@vger.kernel.org> # 4.19
Fixes: bd37197554eb ("net/mlx5: Update mlx5_ifc with DEVX UID bits")
Signed-off-by: Edward Srouji <edwards@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 include/linux/mlx5/mlx5_ifc.h | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index f043d65b9bac..3c4d194275d5 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -5623,7 +5623,12 @@ struct mlx5_ifc_modify_cq_in_bits {
 
 	struct mlx5_ifc_cqc_bits cq_context;
 
-	u8         reserved_at_280[0x600];
+	u8         reserved_at_280[0x60];
+ 
+ 	u8         cq_umem_valid[0x1];
+	u8         reserved_at_2e1[0x1f];
+
+	u8         reserved_at_300[0x580];
 
 	u8         pas[0][0x40];
 };
-- 
2.20.1


From 71feaf906ff5d059830c744bad0b480dbeafd9db Mon Sep 17 00:00:00 2001
From: Ariel Levkovich <lariel@mellanox.com>
Date: Sat, 6 Jul 2019 18:06:15 +0300
Subject: [PATCH 26/28] net/mlx5e: Prevent encap flow counter update async to
 user query

[ Upstream commit 90bb769291161cf25a818d69cf608c181654473e ]

This patch prevents a race between user invoked cached counters
query and a neighbor last usage updater.

The cached flow counter stats can be queried by calling
"mlx5_fc_query_cached" which provides the number of bytes and
packets that passed via this flow since the last time this counter
was queried.
It does so by reducting the last saved stats from the current, cached
stats and then updating the last saved stats with the cached stats.
It also provide the lastuse value for that flow.

Since "mlx5e_tc_update_neigh_used_value" needs to retrieve the
last usage time of encapsulation flows, it calls the flow counter
query method periodically and async to user queries of the flow counter
using cls_flower.
This call is causing the driver to update the last reported bytes and
packets from the cache and therefore, future user queries of the flow
stats will return lower than expected number for bytes and packets
since the last saved stats in the driver was updated async to the last
saved stats in cls_flower.

This causes wrong stats presentation of encapsulation flows to user.

Since the neighbor usage updater only needs the lastuse stats from the
cached counter, the fix is to use a dedicated lastuse query call that
returns the lastuse value without synching between the cached stats and
the last saved stats.

Fixes: f6dfb4c3f216 ("net/mlx5e: Update neighbour 'used' state using HW flow rules counters")
Signed-off-by: Ariel Levkovich <lariel@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c       | 4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c | 5 +++++
 include/linux/mlx5/fs.h                               | 1 +
 3 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 9f7f8425f676..c8928ce69185 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -992,13 +992,13 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv,
 void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe)
 {
 	struct mlx5e_neigh *m_neigh = &nhe->m_neigh;
-	u64 bytes, packets, lastuse = 0;
 	struct mlx5e_tc_flow *flow;
 	struct mlx5e_encap_entry *e;
 	struct mlx5_fc *counter;
 	struct neigh_table *tbl;
 	bool neigh_used = false;
 	struct neighbour *n;
+	u64 lastuse;
 
 	if (m_neigh->family == AF_INET)
 		tbl = &arp_tbl;
@@ -1015,7 +1015,7 @@ void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe)
 		list_for_each_entry(flow, &e->flows, encap) {
 			if (flow->flags & MLX5E_TC_FLOW_OFFLOADED) {
 				counter = mlx5_flow_rule_counter(flow->rule[0]);
-				mlx5_fc_query_cached(counter, &bytes, &packets, &lastuse);
+				lastuse = mlx5_fc_query_lastuse(counter);
 				if (time_after((unsigned long)lastuse, nhe->reported_lastuse)) {
 					neigh_used = true;
 					break;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
index 58af6be13dfa..808ddd732e04 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
@@ -321,6 +321,11 @@ int mlx5_fc_query(struct mlx5_core_dev *dev, struct mlx5_fc *counter,
 }
 EXPORT_SYMBOL(mlx5_fc_query);
 
+u64 mlx5_fc_query_lastuse(struct mlx5_fc *counter)
+{
+	return counter->cache.lastuse;
+}
+
 void mlx5_fc_query_cached(struct mlx5_fc *counter,
 			  u64 *bytes, u64 *packets, u64 *lastuse)
 {
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 804516e4f483..3386399feadc 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -188,6 +188,7 @@ int mlx5_modify_rule_destination(struct mlx5_flow_handle *handler,
 struct mlx5_fc *mlx5_flow_rule_counter(struct mlx5_flow_handle *handler);
 struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging);
 void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter);
+u64 mlx5_fc_query_lastuse(struct mlx5_fc *counter);
 void mlx5_fc_query_cached(struct mlx5_fc *counter,
 			  u64 *bytes, u64 *packets, u64 *lastuse);
 int mlx5_fc_query(struct mlx5_core_dev *dev, struct mlx5_fc *counter,
-- 
2.20.1


From 4b21d8253629976eb718b5238da96bf73d889c8e Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 27 Jul 2019 12:45:10 +0200
Subject: [PATCH 27/28] r8169: don't use MSI before RTL8168d
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 003bd5b4a7b4a94b501e3a1e2e7c9df6b2a94ed4 ]

It was reported that after resuming from suspend network fails with
error "do_IRQ: 3.38 No irq handler for vector", see [0]. Enabling WoL
can work around the issue, but the only actual fix is to disable MSI.
So let's mimic the behavior of the vendor driver and disable MSI on
all chip versions before RTL8168d.

[0] https://bugzilla.kernel.org/show_bug.cgi?id=204079

Fixes: 6c6aa15fdea5 ("r8169: improve interrupt handling")
Reported-by: Dušan Dragić <dragic.dusan@gmail.com>
Tested-by: Dušan Dragić <dragic.dusan@gmail.com>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
---
 drivers/net/ethernet/realtek/r8169.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index a6992c4c7313..0c8b7146637e 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -7239,13 +7239,18 @@ static int rtl_alloc_irq(struct rtl8169_private *tp)
 {
 	unsigned int flags;
 
-	if (tp->mac_version <= RTL_GIGA_MAC_VER_06) {
+	switch (tp->mac_version) {
+	case RTL_GIGA_MAC_VER_02 ... RTL_GIGA_MAC_VER_06:
 		RTL_W8(tp, Cfg9346, Cfg9346_Unlock);
 		RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~MSIEnable);
 		RTL_W8(tp, Cfg9346, Cfg9346_Lock);
+		/* fall through */
+	case RTL_GIGA_MAC_VER_07 ... RTL_GIGA_MAC_VER_24:
 		flags = PCI_IRQ_LEGACY;
-	} else {
+		break;
+	default:
 		flags = PCI_IRQ_ALL_TYPES;
+		break;
 	}
 
 	return pci_alloc_irq_vectors(tp->pci_dev, 1, 1, flags);
-- 
2.20.1


From f84776575dff638122843b3a0b0e76228fde52f2 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 30 Jul 2019 21:25:20 +0200
Subject: [PATCH 28/28] compat_ioctl: pppoe: fix PPPOEIOCSFWD handling

[ Upstream commit 055d88242a6046a1ceac3167290f054c72571cd9 ]

Support for handling the PPPOEIOCSFWD ioctl in compat mode was added in
linux-2.5.69 along with hundreds of other commands, but was always broken
sincen only the structure is compatible, but the command number is not,
due to the size being sizeof(size_t), or at first sizeof(sizeof((struct
sockaddr_pppox)), which is different on 64-bit architectures.

Guillaume Nault adds:

  And the implementation was broken until 2016 (see 29e73269aa4d ("pppoe:
  fix reference counting in PPPoE proxy")), and nobody ever noticed. I
  should probably have removed this ioctl entirely instead of fixing it.
  Clearly, it has never been used.

Fix it by adding a compat_ioctl handler for all pppoe variants that
translates the command number and then calls the regular ioctl function.

All other ioctl commands handled by pppoe are compatible between 32-bit
and 64-bit, and require compat_ptr() conversion.

This should apply to all stable kernels.

Acked-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pppoe.c  |  3 +++
 drivers/net/ppp/pppox.c  | 13 +++++++++++++
 drivers/net/ppp/pptp.c   |  3 +++
 fs/compat_ioctl.c        |  3 ---
 include/linux/if_pppox.h |  3 +++
 net/l2tp/l2tp_ppp.c      |  3 +++
 6 files changed, 25 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index f22639f0116a..c04f3dc17d76 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -1120,6 +1120,9 @@ static const struct proto_ops pppoe_ops = {
 	.recvmsg	= pppoe_recvmsg,
 	.mmap		= sock_no_mmap,
 	.ioctl		= pppox_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= pppox_compat_ioctl,
+#endif
 };
 
 static const struct pppox_proto pppoe_proto = {
diff --git a/drivers/net/ppp/pppox.c b/drivers/net/ppp/pppox.c
index c0599b3b23c0..9128e42e33e7 100644
--- a/drivers/net/ppp/pppox.c
+++ b/drivers/net/ppp/pppox.c
@@ -22,6 +22,7 @@
 #include <linux/string.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
+#include <linux/compat.h>
 #include <linux/errno.h>
 #include <linux/netdevice.h>
 #include <linux/net.h>
@@ -103,6 +104,18 @@ int pppox_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 
 EXPORT_SYMBOL(pppox_ioctl);
 
+#ifdef CONFIG_COMPAT
+int pppox_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
+{
+	if (cmd == PPPOEIOCSFWD32)
+		cmd = PPPOEIOCSFWD;
+
+	return pppox_ioctl(sock, cmd, (unsigned long)compat_ptr(arg));
+}
+
+EXPORT_SYMBOL(pppox_compat_ioctl);
+#endif
+
 static int pppox_create(struct net *net, struct socket *sock, int protocol,
 			int kern)
 {
diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index 7321a4eca235..9ad3ff40a563 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -633,6 +633,9 @@ static const struct proto_ops pptp_ops = {
 	.recvmsg    = sock_no_recvmsg,
 	.mmap       = sock_no_mmap,
 	.ioctl      = pppox_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = pppox_compat_ioctl,
+#endif
 };
 
 static const struct pppox_proto pppox_pptp_proto = {
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index a9b00942e87d..8f08095ee54e 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -894,9 +894,6 @@ COMPATIBLE_IOCTL(PPPIOCDISCONN)
 COMPATIBLE_IOCTL(PPPIOCATTCHAN)
 COMPATIBLE_IOCTL(PPPIOCGCHAN)
 COMPATIBLE_IOCTL(PPPIOCGL2TPSTATS)
-/* PPPOX */
-COMPATIBLE_IOCTL(PPPOEIOCSFWD)
-COMPATIBLE_IOCTL(PPPOEIOCDFWD)
 /* Big A */
 /* sparc only */
 /* Big Q for sound/OSS */
diff --git a/include/linux/if_pppox.h b/include/linux/if_pppox.h
index ba7a9b0c7c57..24e9b360da65 100644
--- a/include/linux/if_pppox.h
+++ b/include/linux/if_pppox.h
@@ -84,6 +84,9 @@ extern int register_pppox_proto(int proto_num, const struct pppox_proto *pp);
 extern void unregister_pppox_proto(int proto_num);
 extern void pppox_unbind_sock(struct sock *sk);/* delete ppp-channel binding */
 extern int pppox_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
+extern int pppox_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
+
+#define PPPOEIOCSFWD32    _IOW(0xB1 ,0, compat_size_t)
 
 /* PPPoX socket states */
 enum {
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 04d9946dcdba..c0956781665e 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1686,6 +1686,9 @@ static const struct proto_ops pppol2tp_ops = {
 	.recvmsg	= pppol2tp_recvmsg,
 	.mmap		= sock_no_mmap,
 	.ioctl		= pppox_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = pppox_compat_ioctl,
+#endif
 };
 
 static const struct pppox_proto pppol2tp_proto = {
-- 
2.20.1


[-- Attachment #3: net_52.mbox --]
[-- Type: Application/Octet-Stream, Size: 148175 bytes --]

From 383667fbad545f7f82d1c3479b310baa4c297edb Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 30 Jul 2019 22:21:41 -0500
Subject: [PATCH 01/46] atm: iphase: Fix Spectre v1 vulnerability

[ Upstream commit ea443e5e98b5b74e317ef3d26bcaea54931ccdee ]

board is controlled by user-space, hence leading to a potential
exploitation of the Spectre variant 1 vulnerability.

This issue was detected with the help of Smatch:

drivers/atm/iphase.c:2765 ia_ioctl() warn: potential spectre issue 'ia_dev' [r] (local cap)
drivers/atm/iphase.c:2774 ia_ioctl() warn: possible spectre second half.  'iadev'
drivers/atm/iphase.c:2782 ia_ioctl() warn: possible spectre second half.  'iadev'
drivers/atm/iphase.c:2816 ia_ioctl() warn: possible spectre second half.  'iadev'
drivers/atm/iphase.c:2823 ia_ioctl() warn: possible spectre second half.  'iadev'
drivers/atm/iphase.c:2830 ia_ioctl() warn: potential spectre issue '_ia_dev' [r] (local cap)
drivers/atm/iphase.c:2845 ia_ioctl() warn: possible spectre second half.  'iadev'
drivers/atm/iphase.c:2856 ia_ioctl() warn: possible spectre second half.  'iadev'

Fix this by sanitizing board before using it to index ia_dev and _ia_dev

Notice that given that speculation windows are large, the policy is
to kill the speculation on the first load and not worry if it can be
completed with a dependent load/store [1].

[1] https://lore.kernel.org/lkml/20180423164740.GY17484@dhcp22.suse.cz/

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/atm/iphase.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/atm/iphase.c b/drivers/atm/iphase.c
index 302cf0ba1600..8c7a996d1f16 100644
--- a/drivers/atm/iphase.c
+++ b/drivers/atm/iphase.c
@@ -63,6 +63,7 @@
 #include <asm/byteorder.h>  
 #include <linux/vmalloc.h>
 #include <linux/jiffies.h>
+#include <linux/nospec.h>
 #include "iphase.h"		  
 #include "suni.h"		  
 #define swap_byte_order(x) (((x & 0xff) << 8) | ((x & 0xff00) >> 8))
@@ -2760,8 +2761,11 @@ static int ia_ioctl(struct atm_dev *dev, unsigned int cmd, void __user *arg)
    }
    if (copy_from_user(&ia_cmds, arg, sizeof ia_cmds)) return -EFAULT; 
    board = ia_cmds.status;
-   if ((board < 0) || (board > iadev_count))
-         board = 0;    
+
+	if ((board < 0) || (board > iadev_count))
+		board = 0;
+	board = array_index_nospec(board, iadev_count + 1);
+
    iadev = ia_dev[board];
    switch (ia_cmds.cmd) {
    case MEMDUMP:
-- 
2.20.1


From de51f48d79cda51da829fe175ffb762548ac994b Mon Sep 17 00:00:00 2001
From: Sudarsana Reddy Kalluru <skalluru@marvell.com>
Date: Tue, 23 Jul 2019 19:32:41 -0700
Subject: [PATCH 02/46] bnx2x: Disable multi-cos feature.

[ Upstream commit d1f0b5dce8fda09a7f5f04c1878f181d548e42f5 ]

Commit 3968d38917eb ("bnx2x: Fix Multi-Cos.") which enabled multi-cos
feature after prolonged time in driver added some regression causing
numerous issues (sudden reboots, tx timeout etc.) reported by customers.
We plan to backout this commit and submit proper fix once we have root
cause of issues reported with this feature enabled.

Fixes: 3968d38917eb ("bnx2x: Fix Multi-Cos.")
Signed-off-by: Sudarsana Reddy Kalluru <skalluru@marvell.com>
Signed-off-by: Manish Chopra <manishc@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index bf39fc83d577..4039a9599d79 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -1934,8 +1934,7 @@ u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
 	}
 
 	/* select a non-FCoE queue */
-	return netdev_pick_tx(dev, skb, NULL) %
-	       (BNX2X_NUM_ETH_QUEUES(bp) * bp->max_cos);
+	return netdev_pick_tx(dev, skb, NULL) % (BNX2X_NUM_ETH_QUEUES(bp));
 }
 
 void bnx2x_set_num_queues(struct bnx2x *bp)
-- 
2.20.1


From 7d8dbf96cfbc53b401142daf3ad8380d48079e6f Mon Sep 17 00:00:00 2001
From: "Arnaud Patard (Rtp)" <arnaud.patard@rtp-net.org>
Date: Fri, 2 Aug 2019 10:32:40 +0200
Subject: [PATCH 03/46] drivers/net/ethernet/marvell/mvmdio.c: Fix non OF case

[ Upstream commit d934423ac26ed373dfe089734d505dca5ff679b6 ]

Orion5.x systems are still using machine files and not device-tree.
Commit 96cb4342382290c9 ("net: mvmdio: allow up to three clocks to be
specified for orion-mdio") has replaced devm_clk_get() with of_clk_get(),
leading to a oops at boot and not working network, as reported in
https://lists.debian.org/debian-arm/2019/07/msg00088.html and possibly in
https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=908712.

Link: https://lists.debian.org/debian-arm/2019/07/msg00088.html
Fixes: 96cb4342382290c9 ("net: mvmdio: allow up to three clocks to be specified for orion-mdio")
Signed-off-by: Arnaud Patard <arnaud.patard@rtp-net.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvmdio.c | 28 +++++++++++++++++++++------
 1 file changed, 22 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c
index ee7857298361..aca878a3f81f 100644
--- a/drivers/net/ethernet/marvell/mvmdio.c
+++ b/drivers/net/ethernet/marvell/mvmdio.c
@@ -319,15 +319,31 @@ static int orion_mdio_probe(struct platform_device *pdev)
 
 	init_waitqueue_head(&dev->smi_busy_wait);
 
-	for (i = 0; i < ARRAY_SIZE(dev->clk); i++) {
-		dev->clk[i] = of_clk_get(pdev->dev.of_node, i);
-		if (PTR_ERR(dev->clk[i]) == -EPROBE_DEFER) {
+	if (pdev->dev.of_node) {
+		for (i = 0; i < ARRAY_SIZE(dev->clk); i++) {
+			dev->clk[i] = of_clk_get(pdev->dev.of_node, i);
+			if (PTR_ERR(dev->clk[i]) == -EPROBE_DEFER) {
+				ret = -EPROBE_DEFER;
+				goto out_clk;
+			}
+			if (IS_ERR(dev->clk[i]))
+				break;
+			clk_prepare_enable(dev->clk[i]);
+		}
+
+		if (!IS_ERR(of_clk_get(pdev->dev.of_node,
+				       ARRAY_SIZE(dev->clk))))
+			dev_warn(&pdev->dev,
+				 "unsupported number of clocks, limiting to the first "
+				 __stringify(ARRAY_SIZE(dev->clk)) "\n");
+	} else {
+		dev->clk[0] = clk_get(&pdev->dev, NULL);
+		if (PTR_ERR(dev->clk[0]) == -EPROBE_DEFER) {
 			ret = -EPROBE_DEFER;
 			goto out_clk;
 		}
-		if (IS_ERR(dev->clk[i]))
-			break;
-		clk_prepare_enable(dev->clk[i]);
+		if (!IS_ERR(dev->clk[0]))
+			clk_prepare_enable(dev->clk[0]);
 	}
 
 	dev->err_interrupt = platform_get_irq(pdev, 0);
-- 
2.20.1


From 0771c21d2d2d36091dd6c60a46850ac5625506a3 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 22 Jul 2019 21:43:00 -0700
Subject: [PATCH 04/46] ife: error out when nla attributes are empty

[ Upstream commit c8ec4632c6ac9cda0e8c3d51aa41eeab66585bd5 ]

act_ife at least requires TCA_IFE_PARMS, so we have to bail out
when there is no attribute passed in.

Reported-by: syzbot+fbb5b288c9cb6a2eeac4@syzkaller.appspotmail.com
Fixes: ef6980b6becb ("introduce IFE action")
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ife.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 41d5398dd2f2..3578196d1600 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -481,6 +481,11 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	int ret = 0;
 	int err;
 
+	if (!nla) {
+		NL_SET_ERR_MSG_MOD(extack, "IFE requires attributes to be passed");
+		return -EINVAL;
+	}
+
 	err = nla_parse_nested_deprecated(tb, TCA_IFE_MAX, nla, ife_policy,
 					  NULL);
 	if (err < 0)
-- 
2.20.1


From 22df0e94ab7ef0090af9d000c816edf50ec1c40c Mon Sep 17 00:00:00 2001
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Wed, 24 Jul 2019 20:00:42 +0800
Subject: [PATCH 05/46] ip6_gre: reload ipv6h in prepare_ip6gre_xmit_ipv6

[ Upstream commit 3bc817d665ac6d9de89f59df522ad86f5b5dfc03 ]

Since ip6_tnl_parse_tlv_enc_lim() can call pskb_may_pull()
which may change skb->data, so we need to re-load ipv6h at
the right place.

Fixes: 898b29798e36 ("ip6_gre: Refactor ip6gre xmit codes")
Cc: William Tu <u9012063@gmail.com>
Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Acked-by: William Tu <u9012063@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index c2049c72f3e5..dd2d0b963260 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -660,12 +660,13 @@ static int prepare_ip6gre_xmit_ipv6(struct sk_buff *skb,
 				    struct flowi6 *fl6, __u8 *dsfield,
 				    int *encap_limit)
 {
-	struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+	struct ipv6hdr *ipv6h;
 	struct ip6_tnl *t = netdev_priv(dev);
 	__u16 offset;
 
 	offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb));
 	/* ip6_tnl_parse_tlv_enc_lim() might have reallocated skb->head */
+	ipv6h = ipv6_hdr(skb);
 
 	if (offset > 0) {
 		struct ipv6_tlv_tnl_enc_lim *tel;
-- 
2.20.1


From d802d4223946a8fe9898b0adc61f129c6731ec74 Mon Sep 17 00:00:00 2001
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Fri, 26 Jul 2019 00:40:17 +0800
Subject: [PATCH 06/46] ip6_tunnel: fix possible use-after-free on xmit

[ Upstream commit 01f5bffad555f8e22a61f4b1261fe09cf1b96994 ]

ip4ip6/ip6ip6 tunnels run iptunnel_handle_offloads on xmit which
can cause a possible use-after-free accessing iph/ipv6h pointer
since the packet will be 'uncloned' running pskb_expand_head if
it is a cloned gso skb.

Fixes: 0e9a709560db ("ip6_tunnel, ip6_gre: fix setting of DSCP on encapsulated packets")
Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index b80fde1bc005..d10a9e40729f 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1278,12 +1278,11 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
+	dsfield = INET_ECN_encapsulate(dsfield, ipv4_get_dsfield(iph));
 
 	if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6))
 		return -1;
 
-	dsfield = INET_ECN_encapsulate(dsfield, ipv4_get_dsfield(iph));
-
 	skb_set_inner_ipproto(skb, IPPROTO_IPIP);
 
 	err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu,
@@ -1367,12 +1366,11 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
+	dsfield = INET_ECN_encapsulate(dsfield, ipv6_get_dsfield(ipv6h));
 
 	if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6))
 		return -1;
 
-	dsfield = INET_ECN_encapsulate(dsfield, ipv6_get_dsfield(ipv6h));
-
 	skb_set_inner_ipproto(skb, IPPROTO_IPV6);
 
 	err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu,
-- 
2.20.1


From 9e5103c4179c2a40e9af95ad81d6240707ddcdad Mon Sep 17 00:00:00 2001
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Thu, 25 Jul 2019 11:07:56 +0800
Subject: [PATCH 07/46] ipip: validate header length in ipip_tunnel_xmit

[ Upstream commit 47d858d0bdcd47cc1c6c9eeca91b091dd9e55637 ]

We need the same checks introduced by commit cb9f1b783850
("ip: validate header length on virtual device xmit") for
ipip tunnel.

Fixes: cb9f1b783850b ("ip: validate header length on virtual device xmit")
Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ipip.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 43adfc1641ba..2f01cf6fa0de 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -275,6 +275,9 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb,
 	const struct iphdr  *tiph = &tunnel->parms.iph;
 	u8 ipproto;
 
+	if (!pskb_inet_may_pull(skb))
+		goto tx_error;
+
 	switch (skb->protocol) {
 	case htons(ETH_P_IP):
 		ipproto = IPPROTO_IPIP;
-- 
2.20.1


From 128e27d860fc4a0c0f32532a876f5c3e4ce4f5ce Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 31 Jul 2019 09:33:14 +0300
Subject: [PATCH 08/46] mlxsw: spectrum: Fix error path in
 mlxsw_sp_module_init()

[ Upstream commit 28fe79000e9b0a6f99959869947f1ca305f14599 ]

In case of sp2 pci driver registration fail, fix the error path to
start with sp1 pci driver unregister.

Fixes: c3ab435466d5 ("mlxsw: spectrum: Extend to support Spectrum-2 ASIC")
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 23204356ad88..d51442e63aba 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -5989,7 +5989,7 @@ static int __init mlxsw_sp_module_init(void)
 	return 0;
 
 err_sp2_pci_driver_register:
-	mlxsw_pci_driver_unregister(&mlxsw_sp2_pci_driver);
+	mlxsw_pci_driver_unregister(&mlxsw_sp1_pci_driver);
 err_sp1_pci_driver_register:
 	mlxsw_core_driver_unregister(&mlxsw_sp2_driver);
 err_sp2_core_driver_register:
-- 
2.20.1


From c435495ded4d95075a0062ca2edae14fffc8a7ab Mon Sep 17 00:00:00 2001
From: Matteo Croce <mcroce@redhat.com>
Date: Thu, 1 Aug 2019 14:13:30 +0200
Subject: [PATCH 09/46] mvpp2: fix panic on module removal

[ Upstream commit 944a83a2669ae8aa2c7664e79376ca7468eb0a2b ]

mvpp2 uses a delayed workqueue to gather traffic statistics.
On module removal the workqueue can be destroyed before calling
cancel_delayed_work_sync() on its works.
Fix it by moving the destroy_workqueue() call after mvpp2_port_remove().
Also remove an unneeded call to flush_workqueue()

    # rmmod mvpp2
    [ 2743.311722] mvpp2 f4000000.ethernet eth1: phy link down 10gbase-kr/10Gbps/Full
    [ 2743.320063] mvpp2 f4000000.ethernet eth1: Link is Down
    [ 2743.572263] mvpp2 f4000000.ethernet eth2: phy link down sgmii/1Gbps/Full
    [ 2743.580076] mvpp2 f4000000.ethernet eth2: Link is Down
    [ 2744.102169] mvpp2 f2000000.ethernet eth0: phy link down 10gbase-kr/10Gbps/Full
    [ 2744.110441] mvpp2 f2000000.ethernet eth0: Link is Down
    [ 2744.115614] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000
    [ 2744.115615] Mem abort info:
    [ 2744.115616]   ESR = 0x96000005
    [ 2744.115617]   Exception class = DABT (current EL), IL = 32 bits
    [ 2744.115618]   SET = 0, FnV = 0
    [ 2744.115619]   EA = 0, S1PTW = 0
    [ 2744.115620] Data abort info:
    [ 2744.115621]   ISV = 0, ISS = 0x00000005
    [ 2744.115622]   CM = 0, WnR = 0
    [ 2744.115624] user pgtable: 4k pages, 39-bit VAs, pgdp=0000000422681000
    [ 2744.115626] [0000000000000000] pgd=0000000000000000, pud=0000000000000000
    [ 2744.115630] Internal error: Oops: 96000005 [#1] SMP
    [ 2744.115632] Modules linked in: mvpp2(-) algif_hash af_alg nls_iso8859_1 nls_cp437 vfat fat xhci_plat_hcd m25p80 spi_nor xhci_hcd mtd usbcore i2c_mv64xxx sfp usb_common marvell10g phy_generic spi_orion mdio_i2c i2c_core mvmdio phylink sbsa_gwdt ip_tables x_tables autofs4 [last unloaded: mvpp2]
    [ 2744.115654] CPU: 3 PID: 8357 Comm: kworker/3:2 Not tainted 5.3.0-rc2 #1
    [ 2744.115655] Hardware name: Marvell 8040 MACCHIATOBin Double-shot (DT)
    [ 2744.115665] Workqueue: events_power_efficient phylink_resolve [phylink]
    [ 2744.115669] pstate: a0000085 (NzCv daIf -PAN -UAO)
    [ 2744.115675] pc : __queue_work+0x9c/0x4d8
    [ 2744.115677] lr : __queue_work+0x170/0x4d8
    [ 2744.115678] sp : ffffff801001bd50
    [ 2744.115680] x29: ffffff801001bd50 x28: ffffffc422597600
    [ 2744.115684] x27: ffffff80109ae6f0 x26: ffffff80108e4018
    [ 2744.115688] x25: 0000000000000003 x24: 0000000000000004
    [ 2744.115691] x23: ffffff80109ae6e0 x22: 0000000000000017
    [ 2744.115694] x21: ffffffc42c030000 x20: ffffffc42209e8f8
    [ 2744.115697] x19: 0000000000000000 x18: 0000000000000000
    [ 2744.115699] x17: 0000000000000000 x16: 0000000000000000
    [ 2744.115701] x15: 0000000000000010 x14: ffffffffffffffff
    [ 2744.115702] x13: ffffff8090e2b95f x12: ffffff8010e2b967
    [ 2744.115704] x11: ffffff8010906000 x10: 0000000000000040
    [ 2744.115706] x9 : ffffff80109223b8 x8 : ffffff80109223b0
    [ 2744.115707] x7 : ffffffc42bc00068 x6 : 0000000000000000
    [ 2744.115709] x5 : ffffffc42bc00000 x4 : 0000000000000000
    [ 2744.115710] x3 : 0000000000000000 x2 : 0000000000000000
    [ 2744.115712] x1 : 0000000000000008 x0 : ffffffc42c030000
    [ 2744.115714] Call trace:
    [ 2744.115716]  __queue_work+0x9c/0x4d8
    [ 2744.115718]  delayed_work_timer_fn+0x28/0x38
    [ 2744.115722]  call_timer_fn+0x3c/0x180
    [ 2744.115723]  expire_timers+0x60/0x168
    [ 2744.115724]  run_timer_softirq+0xbc/0x1e8
    [ 2744.115727]  __do_softirq+0x128/0x320
    [ 2744.115731]  irq_exit+0xa4/0xc0
    [ 2744.115734]  __handle_domain_irq+0x70/0xc0
    [ 2744.115735]  gic_handle_irq+0x58/0xa8
    [ 2744.115737]  el1_irq+0xb8/0x140
    [ 2744.115738]  console_unlock+0x3a0/0x568
    [ 2744.115740]  vprintk_emit+0x200/0x2a0
    [ 2744.115744]  dev_vprintk_emit+0x1c8/0x1e4
    [ 2744.115747]  dev_printk_emit+0x6c/0x7c
    [ 2744.115751]  __netdev_printk+0x104/0x1d8
    [ 2744.115752]  netdev_printk+0x60/0x70
    [ 2744.115756]  phylink_resolve+0x38c/0x3c8 [phylink]
    [ 2744.115758]  process_one_work+0x1f8/0x448
    [ 2744.115760]  worker_thread+0x54/0x500
    [ 2744.115762]  kthread+0x12c/0x130
    [ 2744.115764]  ret_from_fork+0x10/0x1c
    [ 2744.115768] Code: aa1403e0 97fffbbe aa0003f5 b4000700 (f9400261)

Fixes: 118d6298f6f0 ("net: mvpp2: add ethtool GOP statistics")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Matteo Croce <mcroce@redhat.com>
Acked-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index d8e5241097a9..56dc191f289c 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -5609,9 +5609,6 @@ static int mvpp2_remove(struct platform_device *pdev)
 
 	mvpp2_dbgfs_cleanup(priv);
 
-	flush_workqueue(priv->stats_queue);
-	destroy_workqueue(priv->stats_queue);
-
 	fwnode_for_each_available_child_node(fwnode, port_fwnode) {
 		if (priv->port_list[i]) {
 			mutex_destroy(&priv->port_list[i]->gather_stats_lock);
@@ -5620,6 +5617,8 @@ static int mvpp2_remove(struct platform_device *pdev)
 		i++;
 	}
 
+	destroy_workqueue(priv->stats_queue);
+
 	for (i = 0; i < MVPP2_BM_POOLS_NUM; i++) {
 		struct mvpp2_bm_pool *bm_pool = &priv->bm_pools[i];
 
-- 
2.20.1


From 59814425eabd88d1c2e2e269a9be135906eed944 Mon Sep 17 00:00:00 2001
From: Matteo Croce <mcroce@redhat.com>
Date: Sun, 28 Jul 2019 02:46:45 +0200
Subject: [PATCH 10/46] mvpp2: refactor MTU change code

[ Upstream commit 230bd958c2c846ee292aa38bc6b006296c24ca01 ]

The MTU change code can call napi_disable() with the device already down,
leading to a deadlock. Also, lot of code is duplicated unnecessarily.

Rework mvpp2_change_mtu() to avoid the deadlock and remove duplicated code.

Fixes: 3f518509dedc ("ethernet: Add new driver for Marvell Armada 375 network unit")
Signed-off-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/marvell/mvpp2/mvpp2_main.c   | 41 ++++++-------------
 1 file changed, 13 insertions(+), 28 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 56dc191f289c..50ed1bdb632d 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -3609,6 +3609,7 @@ static int mvpp2_set_mac_address(struct net_device *dev, void *p)
 static int mvpp2_change_mtu(struct net_device *dev, int mtu)
 {
 	struct mvpp2_port *port = netdev_priv(dev);
+	bool running = netif_running(dev);
 	int err;
 
 	if (!IS_ALIGNED(MVPP2_RX_PKT_SIZE(mtu), 8)) {
@@ -3617,40 +3618,24 @@ static int mvpp2_change_mtu(struct net_device *dev, int mtu)
 		mtu = ALIGN(MVPP2_RX_PKT_SIZE(mtu), 8);
 	}
 
-	if (!netif_running(dev)) {
-		err = mvpp2_bm_update_mtu(dev, mtu);
-		if (!err) {
-			port->pkt_size =  MVPP2_RX_PKT_SIZE(mtu);
-			return 0;
-		}
-
-		/* Reconfigure BM to the original MTU */
-		err = mvpp2_bm_update_mtu(dev, dev->mtu);
-		if (err)
-			goto log_error;
-	}
-
-	mvpp2_stop_dev(port);
+	if (running)
+		mvpp2_stop_dev(port);
 
 	err = mvpp2_bm_update_mtu(dev, mtu);
-	if (!err) {
+	if (err) {
+		netdev_err(dev, "failed to change MTU\n");
+		/* Reconfigure BM to the original MTU */
+		mvpp2_bm_update_mtu(dev, dev->mtu);
+	} else {
 		port->pkt_size =  MVPP2_RX_PKT_SIZE(mtu);
-		goto out_start;
 	}
 
-	/* Reconfigure BM to the original MTU */
-	err = mvpp2_bm_update_mtu(dev, dev->mtu);
-	if (err)
-		goto log_error;
-
-out_start:
-	mvpp2_start_dev(port);
-	mvpp2_egress_enable(port);
-	mvpp2_ingress_enable(port);
+	if (running) {
+		mvpp2_start_dev(port);
+		mvpp2_egress_enable(port);
+		mvpp2_ingress_enable(port);
+	}
 
-	return 0;
-log_error:
-	netdev_err(dev, "failed to change MTU\n");
 	return err;
 }
 
-- 
2.20.1


From e1a22dab47d819dda2947f766af2acf0a008beb7 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Mon, 29 Jul 2019 12:28:41 +0300
Subject: [PATCH 11/46] net: bridge: delete local fdb on device init failure

[ Upstream commit d7bae09fa008c6c9a489580db0a5a12063b97f97 ]

On initialization failure we have to delete the local fdb which was
inserted due to the default pvid creation. This problem has been present
since the inception of default_pvid. Note that currently there are 2 cases:
1) in br_dev_init() when br_multicast_init() fails
2) if register_netdevice() fails after calling ndo_init()

This patch takes care of both since br_vlan_flush() is called on both
occasions. Also the new fdb delete would be a no-op on normal bridge
device destruction since the local fdb would've been already flushed by
br_dev_delete(). This is not an issue for ports since nbp_vlan_init() is
called last when adding a port thus nothing can fail after it.

Reported-by: syzbot+88533dc8b582309bf3ee@syzkaller.appspotmail.com
Fixes: 5be5a2df40f0 ("bridge: Add filtering support for default_pvid")
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_vlan.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index f47f526b4f19..a764459f4b66 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -715,6 +715,11 @@ void br_vlan_flush(struct net_bridge *br)
 
 	ASSERT_RTNL();
 
+	/* delete auto-added default pvid local fdb before flushing vlans
+	 * otherwise it will be leaked on bridge device init failure
+	 */
+	br_fdb_delete_by_port(br, NULL, 0, 1);
+
 	vg = br_vlan_group(br);
 	__vlan_flush(vg);
 	RCU_INIT_POINTER(br->vlgrp, NULL);
-- 
2.20.1


From 4692c32494b0e660f41da39a4a8d192d73049f2b Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Tue, 30 Jul 2019 14:21:00 +0300
Subject: [PATCH 12/46] net: bridge: mcast: don't delete permanent entries when
 fast leave is enabled

[ Upstream commit 5c725b6b65067909548ac9ca9bc777098ec9883d ]

When permanent entries were introduced by the commit below, they were
exempt from timing out and thus igmp leave wouldn't affect them unless
fast leave was enabled on the port which was added before permanent
entries existed. It shouldn't matter if fast leave is enabled or not
if the user added a permanent entry it shouldn't be deleted on igmp
leave.

Before:
$ echo 1 > /sys/class/net/eth4/brport/multicast_fast_leave
$ bridge mdb add dev br0 port eth4 grp 229.1.1.1 permanent
$ bridge mdb show
dev br0 port eth4 grp 229.1.1.1 permanent

< join and leave 229.1.1.1 on eth4 >

$ bridge mdb show
$

After:
$ echo 1 > /sys/class/net/eth4/brport/multicast_fast_leave
$ bridge mdb add dev br0 port eth4 grp 229.1.1.1 permanent
$ bridge mdb show
dev br0 port eth4 grp 229.1.1.1 permanent

< join and leave 229.1.1.1 on eth4 >

$ bridge mdb show
dev br0 port eth4 grp 229.1.1.1 permanent

Fixes: ccb1c31a7a87 ("bridge: add flags to distinguish permanent mdb entires")
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 3d8deac2353d..f8cac3702712 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1388,6 +1388,9 @@ br_multicast_leave_group(struct net_bridge *br,
 			if (!br_port_group_equal(p, port, src))
 				continue;
 
+			if (p->flags & MDB_PG_FLAGS_PERMANENT)
+				break;
+
 			rcu_assign_pointer(*pp, p->next);
 			hlist_del_init(&p->mglist);
 			del_timer(&p->timer);
-- 
2.20.1


From f5f183e6508920452d791814433ab6e886902162 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Fri, 2 Aug 2019 13:57:36 +0300
Subject: [PATCH 13/46] net: bridge: move default pvid init/deinit to
 NETDEV_REGISTER/UNREGISTER

[ Upstream commit 091adf9ba6cdb432cbcc217b47e4ffb8aa0d8865 ]

Most of the bridge device's vlan init bugs come from the fact that its
default pvid is created at the wrong time, way too early in ndo_init()
before the device is even assigned an ifindex. It introduces a bug when the
bridge's dev_addr is added as fdb during the initial default pvid creation
the notification has ifindex/NDA_MASTER both equal to 0 (see example below)
which really makes no sense for user-space[0] and is wrong.
Usually user-space software would ignore such entries, but they are
actually valid and will eventually have all necessary attributes.
It makes much more sense to send a notification *after* the device has
registered and has a proper ifindex allocated rather than before when
there's a chance that the registration might still fail or to receive
it with ifindex/NDA_MASTER == 0. Note that we can remove the fdb flush
from br_vlan_flush() since that case can no longer happen. At
NETDEV_REGISTER br->default_pvid is always == 1 as it's initialized by
br_vlan_init() before that and at NETDEV_UNREGISTER it can be anything
depending why it was called (if called due to NETDEV_REGISTER error
it'll still be == 1, otherwise it could be any value changed during the
device life time).

For the demonstration below a small change to iproute2 for printing all fdb
notifications is added, because it contained a workaround not to show
entries with ifindex == 0.
Command executed while monitoring: $ ip l add br0 type bridge
Before (both ifindex and master == 0):
$ bridge monitor fdb
36:7e:8a:b3:56:ba dev * vlan 1 master * permanent

After (proper br0 ifindex):
$ bridge monitor fdb
e6:2a:ae:7a:b7:48 dev br0 vlan 1 master br0 permanent

v4: move only the default pvid init/deinit to NETDEV_REGISTER/UNREGISTER
v3: send the correct v2 patch with all changes (stub should return 0)
v2: on error in br_vlan_init set br->vlgrp to NULL and return 0 in
    the br_vlan_bridge_event stub when bridge vlans are disabled

[0] https://bugzilla.kernel.org/show_bug.cgi?id=204389

Reported-by: michael-dev <michael-dev@fami-braun.de>
Fixes: 5be5a2df40f0 ("bridge: Add filtering support for default_pvid")
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Acked-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br.c         |  5 ++++-
 net/bridge/br_private.h |  9 +++++----
 net/bridge/br_vlan.c    | 34 ++++++++++++++++------------------
 3 files changed, 25 insertions(+), 23 deletions(-)

diff --git a/net/bridge/br.c b/net/bridge/br.c
index d164f63a4345..8a8f9e5f264f 100644
--- a/net/bridge/br.c
+++ b/net/bridge/br.c
@@ -37,12 +37,15 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v
 	int err;
 
 	if (dev->priv_flags & IFF_EBRIDGE) {
+		err = br_vlan_bridge_event(dev, event, ptr);
+		if (err)
+			return notifier_from_errno(err);
+
 		if (event == NETDEV_REGISTER) {
 			/* register of bridge completed, add sysfs entries */
 			br_sysfs_addbr(dev);
 			return NOTIFY_DONE;
 		}
-		br_vlan_bridge_event(dev, event, ptr);
 	}
 
 	/* not a port of a bridge */
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 159a0e2cb0f6..9564a953bdf9 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -893,8 +893,8 @@ int nbp_get_num_vlan_infos(struct net_bridge_port *p, u32 filter_mask);
 void br_vlan_get_stats(const struct net_bridge_vlan *v,
 		       struct br_vlan_stats *stats);
 void br_vlan_port_event(struct net_bridge_port *p, unsigned long event);
-void br_vlan_bridge_event(struct net_device *dev, unsigned long event,
-			  void *ptr);
+int br_vlan_bridge_event(struct net_device *dev, unsigned long event,
+			 void *ptr);
 
 static inline struct net_bridge_vlan_group *br_vlan_group(
 					const struct net_bridge *br)
@@ -1084,9 +1084,10 @@ static inline void br_vlan_port_event(struct net_bridge_port *p,
 {
 }
 
-static inline void br_vlan_bridge_event(struct net_device *dev,
-					unsigned long event, void *ptr)
+static inline int br_vlan_bridge_event(struct net_device *dev,
+				       unsigned long event, void *ptr)
 {
+	return 0;
 }
 #endif
 
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index a764459f4b66..6b2c48b07e04 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -715,11 +715,6 @@ void br_vlan_flush(struct net_bridge *br)
 
 	ASSERT_RTNL();
 
-	/* delete auto-added default pvid local fdb before flushing vlans
-	 * otherwise it will be leaked on bridge device init failure
-	 */
-	br_fdb_delete_by_port(br, NULL, 0, 1);
-
 	vg = br_vlan_group(br);
 	__vlan_flush(vg);
 	RCU_INIT_POINTER(br->vlgrp, NULL);
@@ -1048,7 +1043,6 @@ int br_vlan_init(struct net_bridge *br)
 {
 	struct net_bridge_vlan_group *vg;
 	int ret = -ENOMEM;
-	bool changed;
 
 	vg = kzalloc(sizeof(*vg), GFP_KERNEL);
 	if (!vg)
@@ -1063,17 +1057,10 @@ int br_vlan_init(struct net_bridge *br)
 	br->vlan_proto = htons(ETH_P_8021Q);
 	br->default_pvid = 1;
 	rcu_assign_pointer(br->vlgrp, vg);
-	ret = br_vlan_add(br, 1,
-			  BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED |
-			  BRIDGE_VLAN_INFO_BRENTRY, &changed, NULL);
-	if (ret)
-		goto err_vlan_add;
 
 out:
 	return ret;
 
-err_vlan_add:
-	vlan_tunnel_deinit(vg);
 err_tunnel_init:
 	rhashtable_destroy(&vg->vlan_hash);
 err_rhtbl:
@@ -1448,13 +1435,23 @@ static void nbp_vlan_set_vlan_dev_state(struct net_bridge_port *p, u16 vid)
 }
 
 /* Must be protected by RTNL. */
-void br_vlan_bridge_event(struct net_device *dev, unsigned long event,
-			  void *ptr)
+int br_vlan_bridge_event(struct net_device *dev, unsigned long event, void *ptr)
 {
 	struct netdev_notifier_changeupper_info *info;
-	struct net_bridge *br;
+	struct net_bridge *br = netdev_priv(dev);
+	bool changed;
+	int ret = 0;
 
 	switch (event) {
+	case NETDEV_REGISTER:
+		ret = br_vlan_add(br, br->default_pvid,
+				  BRIDGE_VLAN_INFO_PVID |
+				  BRIDGE_VLAN_INFO_UNTAGGED |
+				  BRIDGE_VLAN_INFO_BRENTRY, &changed, NULL);
+		break;
+	case NETDEV_UNREGISTER:
+		br_vlan_delete(br, br->default_pvid);
+		break;
 	case NETDEV_CHANGEUPPER:
 		info = ptr;
 		br_vlan_upper_change(dev, info->upper_dev, info->linking);
@@ -1462,12 +1459,13 @@ void br_vlan_bridge_event(struct net_device *dev, unsigned long event,
 
 	case NETDEV_CHANGE:
 	case NETDEV_UP:
-		br = netdev_priv(dev);
 		if (!br_opt_get(br, BROPT_VLAN_BRIDGE_BINDING))
-			return;
+			break;
 		br_vlan_link_state_change(dev, br);
 		break;
 	}
+
+	return ret;
 }
 
 /* Must be protected by RTNL. */
-- 
2.20.1


From 648d26b89e8565c84128d33fb05d74c26b88c292 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sun, 28 Jul 2019 14:56:36 +0200
Subject: [PATCH 14/46] net: fix ifindex collision during namespace removal

[ Upstream commit 55b40dbf0e76b4bfb9d8b3a16a0208640a9a45df ]

Commit aca51397d014 ("netns: Fix arbitrary net_device-s corruptions
on net_ns stop.") introduced a possibility to hit a BUG in case device
is returning back to init_net and two following conditions are met:
1) dev->ifindex value is used in a name of another "dev%d"
   device in init_net.
2) dev->name is used by another device in init_net.

Under real life circumstances this is hard to get. Therefore this has
been present happily for over 10 years. To reproduce:

$ ip a
1: lo: <LOOPBACK,UP,LOWER_UP> mtu 65536 qdisc noqueue state UNKNOWN group default qlen 1000
    link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00
    inet 127.0.0.1/8 scope host lo
       valid_lft forever preferred_lft forever
    inet6 ::1/128 scope host
       valid_lft forever preferred_lft forever
2: dummy0: <BROADCAST,NOARP> mtu 1500 qdisc noop state DOWN group default qlen 1000
    link/ether 86:89:3f:86:61:29 brd ff:ff:ff:ff:ff:ff
3: enp0s2: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN group default qlen 1000
    link/ether 52:54:00:12:34:56 brd ff:ff:ff:ff:ff:ff
$ ip netns add ns1
$ ip -n ns1 link add dummy1ns1 type dummy
$ ip -n ns1 link add dummy2ns1 type dummy
$ ip link set enp0s2 netns ns1
$ ip -n ns1 link set enp0s2 name dummy0
[  100.858894] virtio_net virtio0 dummy0: renamed from enp0s2
$ ip link add dev4 type dummy
$ ip -n ns1 a
1: lo: <LOOPBACK> mtu 65536 qdisc noop state DOWN group default qlen 1000
    link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00
2: dummy1ns1: <BROADCAST,NOARP> mtu 1500 qdisc noop state DOWN group default qlen 1000
    link/ether 16:63:4c:38:3e:ff brd ff:ff:ff:ff:ff:ff
3: dummy2ns1: <BROADCAST,NOARP> mtu 1500 qdisc noop state DOWN group default qlen 1000
    link/ether aa:9e:86:dd:6b:5d brd ff:ff:ff:ff:ff:ff
4: dummy0: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN group default qlen 1000
    link/ether 52:54:00:12:34:56 brd ff:ff:ff:ff:ff:ff
$ ip a
1: lo: <LOOPBACK,UP,LOWER_UP> mtu 65536 qdisc noqueue state UNKNOWN group default qlen 1000
    link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00
    inet 127.0.0.1/8 scope host lo
       valid_lft forever preferred_lft forever
    inet6 ::1/128 scope host
       valid_lft forever preferred_lft forever
2: dummy0: <BROADCAST,NOARP> mtu 1500 qdisc noop state DOWN group default qlen 1000
    link/ether 86:89:3f:86:61:29 brd ff:ff:ff:ff:ff:ff
4: dev4: <BROADCAST,NOARP> mtu 1500 qdisc noop state DOWN group default qlen 1000
    link/ether 5a:e1:4a:b6:ec:f8 brd ff:ff:ff:ff:ff:ff
$ ip netns del ns1
[  158.717795] default_device_exit: failed to move dummy0 to init_net: -17
[  158.719316] ------------[ cut here ]------------
[  158.720591] kernel BUG at net/core/dev.c:9824!
[  158.722260] invalid opcode: 0000 [#1] SMP KASAN PTI
[  158.723728] CPU: 0 PID: 56 Comm: kworker/u2:1 Not tainted 5.3.0-rc1+ #18
[  158.725422] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-2.fc30 04/01/2014
[  158.727508] Workqueue: netns cleanup_net
[  158.728915] RIP: 0010:default_device_exit.cold+0x1d/0x1f
[  158.730683] Code: 84 e8 18 c9 3e fe 0f 0b e9 70 90 ff ff e8 36 e4 52 fe 89 d9 4c 89 e2 48 c7 c6 80 d6 25 84 48 c7 c7 20 c0 25 84 e8 f4 c8 3e
[  158.736854] RSP: 0018:ffff8880347e7b90 EFLAGS: 00010282
[  158.738752] RAX: 000000000000003b RBX: 00000000ffffffef RCX: 0000000000000000
[  158.741369] RDX: 0000000000000000 RSI: ffffffff8128013d RDI: ffffed10068fcf64
[  158.743418] RBP: ffff888033550170 R08: 000000000000003b R09: fffffbfff0b94b9c
[  158.745626] R10: fffffbfff0b94b9b R11: ffffffff85ca5cdf R12: ffff888032f28000
[  158.748405] R13: dffffc0000000000 R14: ffff8880335501b8 R15: 1ffff110068fcf72
[  158.750638] FS:  0000000000000000(0000) GS:ffff888036000000(0000) knlGS:0000000000000000
[  158.752944] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  158.755245] CR2: 00007fe8b45d21d0 CR3: 00000000340b4005 CR4: 0000000000360ef0
[  158.757654] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  158.760012] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[  158.762758] Call Trace:
[  158.763882]  ? dev_change_net_namespace+0xbb0/0xbb0
[  158.766148]  ? devlink_nl_cmd_set_doit+0x520/0x520
[  158.768034]  ? dev_change_net_namespace+0xbb0/0xbb0
[  158.769870]  ops_exit_list.isra.0+0xa8/0x150
[  158.771544]  cleanup_net+0x446/0x8f0
[  158.772945]  ? unregister_pernet_operations+0x4a0/0x4a0
[  158.775294]  process_one_work+0xa1a/0x1740
[  158.776896]  ? pwq_dec_nr_in_flight+0x310/0x310
[  158.779143]  ? do_raw_spin_lock+0x11b/0x280
[  158.780848]  worker_thread+0x9e/0x1060
[  158.782500]  ? process_one_work+0x1740/0x1740
[  158.784454]  kthread+0x31b/0x420
[  158.786082]  ? __kthread_create_on_node+0x3f0/0x3f0
[  158.788286]  ret_from_fork+0x3a/0x50
[  158.789871] ---[ end trace defd6c657c71f936 ]---
[  158.792273] RIP: 0010:default_device_exit.cold+0x1d/0x1f
[  158.795478] Code: 84 e8 18 c9 3e fe 0f 0b e9 70 90 ff ff e8 36 e4 52 fe 89 d9 4c 89 e2 48 c7 c6 80 d6 25 84 48 c7 c7 20 c0 25 84 e8 f4 c8 3e
[  158.804854] RSP: 0018:ffff8880347e7b90 EFLAGS: 00010282
[  158.807865] RAX: 000000000000003b RBX: 00000000ffffffef RCX: 0000000000000000
[  158.811794] RDX: 0000000000000000 RSI: ffffffff8128013d RDI: ffffed10068fcf64
[  158.816652] RBP: ffff888033550170 R08: 000000000000003b R09: fffffbfff0b94b9c
[  158.820930] R10: fffffbfff0b94b9b R11: ffffffff85ca5cdf R12: ffff888032f28000
[  158.825113] R13: dffffc0000000000 R14: ffff8880335501b8 R15: 1ffff110068fcf72
[  158.829899] FS:  0000000000000000(0000) GS:ffff888036000000(0000) knlGS:0000000000000000
[  158.834923] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  158.838164] CR2: 00007fe8b45d21d0 CR3: 00000000340b4005 CR4: 0000000000360ef0
[  158.841917] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  158.845149] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400

Fix this by checking if a device with the same name exists in init_net
and fallback to original code - dev%d to allocate name - in case it does.

This was found using syzkaller.

Fixes: aca51397d014 ("netns: Fix arbitrary net_device-s corruptions on net_ns stop.")
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/core/dev.c b/net/core/dev.c
index d6edd218babd..d490c7b0ca2b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -9711,6 +9711,8 @@ static void __net_exit default_device_exit(struct net *net)
 
 		/* Push remaining network devices to init_net */
 		snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex);
+		if (__dev_get_by_name(&init_net, fb_name))
+			snprintf(fb_name, IFNAMSIZ, "dev%%d");
 		err = dev_change_net_namespace(dev, &init_net, fb_name);
 		if (err) {
 			pr_emerg("%s: failed to move %s to init_net: %d\n",
-- 
2.20.1


From 2bcf5642d839cc84a50e8a35327ae2f1e06c8cfd Mon Sep 17 00:00:00 2001
From: Qian Cai <cai@lca.pw>
Date: Thu, 1 Aug 2019 09:52:54 -0400
Subject: [PATCH 15/46] net/mlx5e: always initialize frag->last_in_page

[ Upstream commit 60d60c8fbd8d1acf25b041ecd72ae4fa16e9405b ]

The commit 069d11465a80 ("net/mlx5e: RX, Enhance legacy Receive Queue
memory scheme") introduced an undefined behaviour below due to
"frag->last_in_page" is only initialized in mlx5e_init_frags_partition()
when,

if (next_frag.offset + frag_info[f].frag_stride > PAGE_SIZE)

or after bailed out the loop,

for (i = 0; i < mlx5_wq_cyc_get_size(&rq->wqe.wq); i++)

As the result, there could be some "frag" have uninitialized
value of "last_in_page".

Later, get_frag() obtains those "frag" and check "frag->last_in_page" in
mlx5e_put_rx_frag() and triggers the error during boot. Fix it by always
initializing "frag->last_in_page" to "false" in
mlx5e_init_frags_partition().

UBSAN: Undefined behaviour in
drivers/net/ethernet/mellanox/mlx5/core/en_rx.c:325:12
load of value 170 is not a valid value for type 'bool' (aka '_Bool')
Call trace:
 dump_backtrace+0x0/0x264
 show_stack+0x20/0x2c
 dump_stack+0xb0/0x104
 __ubsan_handle_load_invalid_value+0x104/0x128
 mlx5e_handle_rx_cqe+0x8e8/0x12cc [mlx5_core]
 mlx5e_poll_rx_cq+0xca8/0x1a94 [mlx5_core]
 mlx5e_napi_poll+0x17c/0xa30 [mlx5_core]
 net_rx_action+0x248/0x940
 __do_softirq+0x350/0x7b8
 irq_exit+0x200/0x26c
 __handle_domain_irq+0xc8/0x128
 gic_handle_irq+0x138/0x228
 el1_irq+0xb8/0x140
 arch_cpu_idle+0x1a4/0x348
 do_idle+0x114/0x1b0
 cpu_startup_entry+0x24/0x28
 rest_init+0x1ac/0x1dc
 arch_call_rest_init+0x10/0x18
 start_kernel+0x4d4/0x57c

Fixes: 069d11465a80 ("net/mlx5e: RX, Enhance legacy Receive Queue memory scheme")
Signed-off-by: Qian Cai <cai@lca.pw>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index a44c24280128..882d26b8095d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -340,12 +340,11 @@ static inline u64 mlx5e_get_mpwqe_offset(struct mlx5e_rq *rq, u16 wqe_ix)
 
 static void mlx5e_init_frags_partition(struct mlx5e_rq *rq)
 {
-	struct mlx5e_wqe_frag_info next_frag, *prev;
+	struct mlx5e_wqe_frag_info next_frag = {};
+	struct mlx5e_wqe_frag_info *prev = NULL;
 	int i;
 
 	next_frag.di = &rq->wqe.di[0];
-	next_frag.offset = 0;
-	prev = NULL;
 
 	for (i = 0; i < mlx5_wq_cyc_get_size(&rq->wqe.wq); i++) {
 		struct mlx5e_rq_frag_info *frag_info = &rq->wqe.info.arr[0];
-- 
2.20.1


From f88b6ed2baaf098227caf406c892abd84a01f94f Mon Sep 17 00:00:00 2001
From: Mark Zhang <markz@mellanox.com>
Date: Tue, 9 Jul 2019 05:37:12 +0300
Subject: [PATCH 16/46] net/mlx5: Use reversed order when unregister devices

[ Upstream commit 08aa5e7da6bce1a1963f63cf32c2e7ad434ad578 ]

When lag is active, which is controlled by the bonded mlx5e netdev, mlx5
interface unregestering must happen in the reverse order where rdma is
unregistered (unloaded) first, to guarantee all references to the lag
context in hardware is removed, then remove mlx5e netdev interface which
will cleanup the lag context from hardware.

Without this fix during destroy of LAG interface, we observed following
errors:
 * mlx5_cmd_check:752:(pid 12556): DESTROY_LAG(0x843) op_mod(0x0) failed,
   status bad parameter(0x3), syndrome (0xe4ac33)
 * mlx5_cmd_check:752:(pid 12556): DESTROY_LAG(0x843) op_mod(0x0) failed,
   status bad parameter(0x3), syndrome (0xa5aee8).

Fixes: a31208b1e11d ("net/mlx5_core: New init and exit flow for mlx5_core")
Reviewed-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Mark Zhang <markz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
index f6b1da99e6c2..ba5f46da1c5c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -213,7 +213,7 @@ void mlx5_unregister_device(struct mlx5_core_dev *dev)
 	struct mlx5_interface *intf;
 
 	mutex_lock(&mlx5_intf_mutex);
-	list_for_each_entry(intf, &intf_list, list)
+	list_for_each_entry_reverse(intf, &intf_list, list)
 		mlx5_remove_device(intf, priv);
 	list_del(&priv->dev_list);
 	mutex_unlock(&mlx5_intf_mutex);
-- 
2.20.1


From 602af9a77431d632087244f31f23ef81e33cbd18 Mon Sep 17 00:00:00 2001
From: Hubert Feurstein <h.feurstein@gmail.com>
Date: Tue, 30 Jul 2019 11:46:23 +0200
Subject: [PATCH 17/46] net: phy: fixed_phy: print gpio error only if gpio node
 is present

[ Upstream commit ab98c008ac761752cdc27f9eb053419feadeb2f7 ]

It is perfectly ok to not have an gpio attached to the fixed-link node. So
the driver should not throw an error message when the gpio is missing.

Fixes: 5468e82f7034 ("net: phy: fixed-phy: Drop GPIO from fixed_phy_add()")
Signed-off-by: Hubert Feurstein <h.feurstein@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/fixed_phy.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c
index 3ffe46df249e..7c5265fd2b94 100644
--- a/drivers/net/phy/fixed_phy.c
+++ b/drivers/net/phy/fixed_phy.c
@@ -216,8 +216,10 @@ static struct gpio_desc *fixed_phy_get_gpiod(struct device_node *np)
 	if (IS_ERR(gpiod)) {
 		if (PTR_ERR(gpiod) == -EPROBE_DEFER)
 			return gpiod;
-		pr_err("error getting GPIO for fixed link %pOF, proceed without\n",
-		       fixed_link_node);
+
+		if (PTR_ERR(gpiod) != -ENOENT)
+			pr_err("error getting GPIO for fixed link %pOF, proceed without\n",
+			       fixed_link_node);
 		gpiod = NULL;
 	}
 
-- 
2.20.1


From b6313500ed7dd7790e2e1eb44ea6872b513b47d0 Mon Sep 17 00:00:00 2001
From: Arseny Solokha <asolokha@kb.kras.ru>
Date: Wed, 24 Jul 2019 20:31:39 +0700
Subject: [PATCH 18/46] net: phylink: don't start and stop SGMII PHYs in SFP
 modules twice

[ Upstream commit c7fa7f567cab6532be285a5df104617d80bce245 ]

SFP modules connected using the SGMII interface have their own PHYs which
are handled by the struct phylink's phydev field. On the other hand, for
the modules connected using 1000Base-X interface that field is not set.

Since commit ce0aa27ff3f6 ("sfp: add sfp-bus to bridge between network
devices and sfp cages") phylink_start() ends up setting the phydev field
using the sfp-bus infrastructure, which eventually calls phy_start() on it,
and then calling phy_start() again on the same phydev from phylink_start()
itself. Similar call sequence holds for phylink_stop(), only in the reverse
order. This results in WARNs during network interface bringup and shutdown
when a copper SFP module is connected, as phy_start() and phy_stop() are
called twice in a row for the same phy_device:

  % ip link set up dev eth0
  ------------[ cut here ]------------
  called from state UP
  WARNING: CPU: 1 PID: 155 at drivers/net/phy/phy.c:895 phy_start+0x74/0xc0
  Modules linked in:
  CPU: 1 PID: 155 Comm: backend Not tainted 5.2.0+ #1
  NIP:  c0227bf0 LR: c0227bf0 CTR: c004d224
  REGS: df547720 TRAP: 0700   Not tainted  (5.2.0+)
  MSR:  00029000 <CE,EE,ME>  CR: 24002822  XER: 00000000

  GPR00: c0227bf0 df5477d8 df5d7080 00000014 df9d2370 df9d5ac4 1f4eb000 00000001
  GPR08: c061fe58 00000000 00000000 df5477d8 0000003c 100c8768 00000000 00000000
  GPR16: df486a00 c046f1c8 c046eea0 00000000 c046e904 c0239604 db68449c 00000000
  GPR24: e9083204 00000000 00000001 db684460 e9083404 00000000 db6dce00 db6dcc00
  NIP [c0227bf0] phy_start+0x74/0xc0
  LR [c0227bf0] phy_start+0x74/0xc0
  Call Trace:
  [df5477d8] [c0227bf0] phy_start+0x74/0xc0 (unreliable)
  [df5477e8] [c023cad0] startup_gfar+0x398/0x3f4
  [df547828] [c023cf08] gfar_enet_open+0x364/0x374
  [df547898] [c029d870] __dev_open+0xe4/0x140
  [df5478c8] [c029db70] __dev_change_flags+0xf0/0x188
  [df5478f8] [c029dc28] dev_change_flags+0x20/0x54
  [df547918] [c02ae304] do_setlink+0x310/0x818
  [df547a08] [c02b1eb8] __rtnl_newlink+0x384/0x6b0
  [df547c28] [c02b222c] rtnl_newlink+0x48/0x68
  [df547c48] [c02ad7c8] rtnetlink_rcv_msg+0x240/0x27c
  [df547c98] [c02cc068] netlink_rcv_skb+0x8c/0xf0
  [df547cd8] [c02cba3c] netlink_unicast+0x114/0x19c
  [df547d08] [c02cbd74] netlink_sendmsg+0x2b0/0x2c0
  [df547d58] [c027b668] sock_sendmsg_nosec+0x20/0x40
  [df547d68] [c027d080] ___sys_sendmsg+0x17c/0x1dc
  [df547e98] [c027df7c] __sys_sendmsg+0x68/0x84
  [df547ef8] [c027e430] sys_socketcall+0x1a0/0x204
  [df547f38] [c000d1d8] ret_from_syscall+0x0/0x38
  --- interrupt: c01 at 0xfd4e030
      LR = 0xfd4e010
  Instruction dump:
  813f0188 38800000 2b890005 419d0014 3d40c046 5529103a 394aa208 7c8a482e
  3c60c046 3863a1b8 4cc63182 4be009a1 <0fe00000> 48000030 3c60c046 3863a1d0
  ---[ end trace d4c095aeaf6ea998 ]---

and

  % ip link set down dev eth0
  ------------[ cut here ]------------
  called from state HALTED
  WARNING: CPU: 1 PID: 184 at drivers/net/phy/phy.c:858 phy_stop+0x3c/0x88

  <...>

  Call Trace:
  [df581788] [c0228450] phy_stop+0x3c/0x88 (unreliable)
  [df581798] [c022d548] sfp_sm_phy_detach+0x1c/0x44
  [df5817a8] [c022e8cc] sfp_sm_event+0x4b0/0x87c
  [df581848] [c022f04c] sfp_upstream_stop+0x34/0x44
  [df581858] [c0225608] phylink_stop+0x7c/0xe4
  [df581868] [c023c57c] stop_gfar+0x7c/0x94
  [df581888] [c023c5b8] gfar_close+0x24/0x94
  [df5818a8] [c0298688] __dev_close_many+0xdc/0xf8
  [df5818c8] [c029db58] __dev_change_flags+0xd8/0x188
  [df5818f8] [c029dc28] dev_change_flags+0x20/0x54
  [df581918] [c02ae304] do_setlink+0x310/0x818
  [df581a08] [c02b1eb8] __rtnl_newlink+0x384/0x6b0
  [df581c28] [c02b222c] rtnl_newlink+0x48/0x68
  [df581c48] [c02ad7c8] rtnetlink_rcv_msg+0x240/0x27c
  [df581c98] [c02cc068] netlink_rcv_skb+0x8c/0xf0
  [df581cd8] [c02cba3c] netlink_unicast+0x114/0x19c
  [df581d08] [c02cbd74] netlink_sendmsg+0x2b0/0x2c0
  [df581d58] [c027b668] sock_sendmsg_nosec+0x20/0x40
  [df581d68] [c027d080] ___sys_sendmsg+0x17c/0x1dc
  [df581e98] [c027df7c] __sys_sendmsg+0x68/0x84
  [df581ef8] [c027e430] sys_socketcall+0x1a0/0x204
  [df581f38] [c000d1d8] ret_from_syscall+0x0/0x38

  <...>

  ---[ end trace d4c095aeaf6ea999 ]---

SFP modules with the 1000Base-X interface are not affected.

Place explicit calls to phy_start() and phy_stop() before enabling or after
disabling an attached SFP module, where phydev is not yet set (or is
already unset), so they will be made only from the inside of sfp-bus, if
needed.

Fixes: 217962615662 ("net: phy: warn if phy_start is called from invalid state")
Signed-off-by: Arseny Solokha <asolokha@kb.kras.ru>
Acked-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phylink.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 4c0616ba314d..94449ff569fe 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -912,10 +912,10 @@ void phylink_start(struct phylink *pl)
 
 	if (pl->link_an_mode == MLO_AN_FIXED && !IS_ERR(pl->link_gpio))
 		mod_timer(&pl->link_poll, jiffies + HZ);
-	if (pl->sfp_bus)
-		sfp_upstream_start(pl->sfp_bus);
 	if (pl->phydev)
 		phy_start(pl->phydev);
+	if (pl->sfp_bus)
+		sfp_upstream_start(pl->sfp_bus);
 }
 EXPORT_SYMBOL_GPL(phylink_start);
 
@@ -932,10 +932,10 @@ void phylink_stop(struct phylink *pl)
 {
 	ASSERT_RTNL();
 
-	if (pl->phydev)
-		phy_stop(pl->phydev);
 	if (pl->sfp_bus)
 		sfp_upstream_stop(pl->sfp_bus);
+	if (pl->phydev)
+		phy_stop(pl->phydev);
 	if (pl->link_an_mode == MLO_AN_FIXED && !IS_ERR(pl->link_gpio))
 		del_timer_sync(&pl->link_poll);
 
-- 
2.20.1


From b65098080bb6efef31476901fdc6c4a7624e5946 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ren=C3=A9=20van=20Dorst?= <opensource@vdorst.com>
Date: Sat, 27 Jul 2019 11:40:11 +0200
Subject: [PATCH 19/46] net: phylink: Fix flow control for fixed-link
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 8aace4f3eba2a3ceb431e18683ea0e1ecbade5cd ]

In phylink_parse_fixedlink() the pl->link_config.advertising bits are AND
with pl->supported, pl->supported is zeroed and only the speed/duplex
modes and MII bits are set.
So pl->link_config.advertising always loses the flow control/pause bits.

By setting Pause and Asym_Pause bits in pl->supported, the flow control
work again when devicetree "pause" is set in fixes-link node and the MAC
advertise that is supports pause.

Results with this patch.

Legend:
- DT = 'Pause' is set in the fixed-link in devicetree.
- validate() = ‘Yes’ means phylink_set(mask, Pause) is set in the
  validate().
- flow = results reported my link is Up line.

+-----+------------+-------+
| DT  | validate() | flow  |
+-----+------------+-------+
| Yes | Yes        | rx/tx |
| No  | Yes        | off   |
| Yes | No         | off   |
+-----+------------+-------+

Fixes: 9525ae83959b ("phylink: add phylink infrastructure")
Signed-off-by: René van Dorst <opensource@vdorst.com>
Acked-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phylink.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 94449ff569fe..c45ee6e3fe01 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -195,6 +195,8 @@ static int phylink_parse_fixedlink(struct phylink *pl,
 			       pl->supported, true);
 	linkmode_zero(pl->supported);
 	phylink_set(pl->supported, MII);
+	phylink_set(pl->supported, Pause);
+	phylink_set(pl->supported, Asym_Pause);
 	if (s) {
 		__set_bit(s->bit, pl->supported);
 	} else {
-- 
2.20.1


From 9378feaca0ba6d46ac1907fdc221af8d4560b943 Mon Sep 17 00:00:00 2001
From: Andreas Schwab <schwab@suse.de>
Date: Wed, 24 Jul 2019 17:32:57 +0200
Subject: [PATCH 20/46] net: phy: mscc: initialize stats array

[ Upstream commit f972037e71246c5e0916eef835174d58ffc517e4 ]

The memory allocated for the stats array may contain arbitrary data.

Fixes: e4f9ba642f0b ("net: phy: mscc: add support for VSC8514 PHY.")
Fixes: 00d70d8e0e78 ("net: phy: mscc: add support for VSC8574 PHY")
Fixes: a5afc1678044 ("net: phy: mscc: add support for VSC8584 PHY")
Fixes: f76178dc5218 ("net: phy: mscc: add ethtool statistics counters")
Signed-off-by: Andreas Schwab <schwab@suse.de>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mscc.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/net/phy/mscc.c b/drivers/net/phy/mscc.c
index 28676af97b42..645d354ffb48 100644
--- a/drivers/net/phy/mscc.c
+++ b/drivers/net/phy/mscc.c
@@ -2226,8 +2226,8 @@ static int vsc8514_probe(struct phy_device *phydev)
 	vsc8531->supp_led_modes = VSC85XX_SUPP_LED_MODES;
 	vsc8531->hw_stats = vsc85xx_hw_stats;
 	vsc8531->nstats = ARRAY_SIZE(vsc85xx_hw_stats);
-	vsc8531->stats = devm_kmalloc_array(&phydev->mdio.dev, vsc8531->nstats,
-					    sizeof(u64), GFP_KERNEL);
+	vsc8531->stats = devm_kcalloc(&phydev->mdio.dev, vsc8531->nstats,
+				      sizeof(u64), GFP_KERNEL);
 	if (!vsc8531->stats)
 		return -ENOMEM;
 
@@ -2251,8 +2251,8 @@ static int vsc8574_probe(struct phy_device *phydev)
 	vsc8531->supp_led_modes = VSC8584_SUPP_LED_MODES;
 	vsc8531->hw_stats = vsc8584_hw_stats;
 	vsc8531->nstats = ARRAY_SIZE(vsc8584_hw_stats);
-	vsc8531->stats = devm_kmalloc_array(&phydev->mdio.dev, vsc8531->nstats,
-					    sizeof(u64), GFP_KERNEL);
+	vsc8531->stats = devm_kcalloc(&phydev->mdio.dev, vsc8531->nstats,
+				      sizeof(u64), GFP_KERNEL);
 	if (!vsc8531->stats)
 		return -ENOMEM;
 
@@ -2281,8 +2281,8 @@ static int vsc8584_probe(struct phy_device *phydev)
 	vsc8531->supp_led_modes = VSC8584_SUPP_LED_MODES;
 	vsc8531->hw_stats = vsc8584_hw_stats;
 	vsc8531->nstats = ARRAY_SIZE(vsc8584_hw_stats);
-	vsc8531->stats = devm_kmalloc_array(&phydev->mdio.dev, vsc8531->nstats,
-					    sizeof(u64), GFP_KERNEL);
+	vsc8531->stats = devm_kcalloc(&phydev->mdio.dev, vsc8531->nstats,
+				      sizeof(u64), GFP_KERNEL);
 	if (!vsc8531->stats)
 		return -ENOMEM;
 
@@ -2311,8 +2311,8 @@ static int vsc85xx_probe(struct phy_device *phydev)
 	vsc8531->supp_led_modes = VSC85XX_SUPP_LED_MODES;
 	vsc8531->hw_stats = vsc85xx_hw_stats;
 	vsc8531->nstats = ARRAY_SIZE(vsc85xx_hw_stats);
-	vsc8531->stats = devm_kmalloc_array(&phydev->mdio.dev, vsc8531->nstats,
-					    sizeof(u64), GFP_KERNEL);
+	vsc8531->stats = devm_kcalloc(&phydev->mdio.dev, vsc8531->nstats,
+				      sizeof(u64), GFP_KERNEL);
 	if (!vsc8531->stats)
 		return -ENOMEM;
 
-- 
2.20.1


From b8aca6961fd1db7fa97954e67bd7089e96600389 Mon Sep 17 00:00:00 2001
From: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Date: Thu, 25 Jul 2019 12:07:12 -0600
Subject: [PATCH 21/46] net: qualcomm: rmnet: Fix incorrect UL checksum offload
 logic

[ Upstream commit a7cf3d24ee6081930feb4c830a7f6f16ebe31c49 ]

The udp_ip4_ind bit is set only for IPv4 UDP non-fragmented packets
so that the hardware can flip the checksum to 0xFFFF if the computed
checksum is 0 per RFC768.

However, this bit had to be set for IPv6 UDP non fragmented packets
as well per hardware requirements. Otherwise, IPv6 UDP packets
with computed checksum as 0 were transmitted by hardware and were
dropped in the network.

In addition to setting this bit for IPv6 UDP, the field is also
appropriately renamed to udp_ind as part of this change.

Fixes: 5eb5f8608ef1 ("net: qualcomm: rmnet: Add support for TX checksum offload")
Cc: Sean Tranchetti <stranche@codeaurora.org>
Signed-off-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h     |  2 +-
 .../net/ethernet/qualcomm/rmnet/rmnet_map_data.c    | 13 +++++++++----
 2 files changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h
index 4bf20d0651c4..90ad5694e2af 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h
@@ -51,7 +51,7 @@ struct rmnet_map_dl_csum_trailer {
 struct rmnet_map_ul_csum_header {
 	__be16 csum_start_offset;
 	u16 csum_insert_offset:14;
-	u16 udp_ip4_ind:1;
+	u16 udp_ind:1;
 	u16 csum_enabled:1;
 } __aligned(1);
 
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c
index 60189923737a..21d38167f961 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c
@@ -206,9 +206,9 @@ rmnet_map_ipv4_ul_csum_header(void *iphdr,
 	ul_header->csum_insert_offset = skb->csum_offset;
 	ul_header->csum_enabled = 1;
 	if (ip4h->protocol == IPPROTO_UDP)
-		ul_header->udp_ip4_ind = 1;
+		ul_header->udp_ind = 1;
 	else
-		ul_header->udp_ip4_ind = 0;
+		ul_header->udp_ind = 0;
 
 	/* Changing remaining fields to network order */
 	hdr++;
@@ -239,6 +239,7 @@ rmnet_map_ipv6_ul_csum_header(void *ip6hdr,
 			      struct rmnet_map_ul_csum_header *ul_header,
 			      struct sk_buff *skb)
 {
+	struct ipv6hdr *ip6h = (struct ipv6hdr *)ip6hdr;
 	__be16 *hdr = (__be16 *)ul_header, offset;
 
 	offset = htons((__force u16)(skb_transport_header(skb) -
@@ -246,7 +247,11 @@ rmnet_map_ipv6_ul_csum_header(void *ip6hdr,
 	ul_header->csum_start_offset = offset;
 	ul_header->csum_insert_offset = skb->csum_offset;
 	ul_header->csum_enabled = 1;
-	ul_header->udp_ip4_ind = 0;
+
+	if (ip6h->nexthdr == IPPROTO_UDP)
+		ul_header->udp_ind = 1;
+	else
+		ul_header->udp_ind = 0;
 
 	/* Changing remaining fields to network order */
 	hdr++;
@@ -419,7 +424,7 @@ void rmnet_map_checksum_uplink_packet(struct sk_buff *skb,
 	ul_header->csum_start_offset = 0;
 	ul_header->csum_insert_offset = 0;
 	ul_header->csum_enabled = 0;
-	ul_header->udp_ip4_ind = 0;
+	ul_header->udp_ind = 0;
 
 	priv->stats.csum_sw++;
 }
-- 
2.20.1


From 3c299c52d1b5c29366a55e86344da604401fdd44 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Mon, 29 Jul 2019 16:24:33 +0800
Subject: [PATCH 22/46] net: sched: Fix a possible null-pointer dereference in
 dequeue_func()

[ Upstream commit 051c7b39be4a91f6b7d8c4548444e4b850f1f56c ]

In dequeue_func(), there is an if statement on line 74 to check whether
skb is NULL:
    if (skb)

When skb is NULL, it is used on line 77:
    prefetch(&skb->end);

Thus, a possible null-pointer dereference may occur.

To fix this bug, skb->end is used when skb is not NULL.

This bug is found by a static analysis tool STCheck written by us.

Fixes: 76e3cc126bb2 ("codel: Controlled Delay AQM")
Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_codel.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c
index 25ef172c23df..30169b3adbbb 100644
--- a/net/sched/sch_codel.c
+++ b/net/sched/sch_codel.c
@@ -71,10 +71,10 @@ static struct sk_buff *dequeue_func(struct codel_vars *vars, void *ctx)
 	struct Qdisc *sch = ctx;
 	struct sk_buff *skb = __qdisc_dequeue_head(&sch->q);
 
-	if (skb)
+	if (skb) {
 		sch->qstats.backlog -= qdisc_pkt_len(skb);
-
-	prefetch(&skb->end); /* we'll need skb_shinfo() */
+		prefetch(&skb->end); /* we'll need skb_shinfo() */
+	}
 	return skb;
 }
 
-- 
2.20.1


From 7914b2a0da0e782c25e082f95df1fbf8c46fbf2f Mon Sep 17 00:00:00 2001
From: Roman Mashak <mrv@mojatatu.com>
Date: Fri, 2 Aug 2019 15:16:46 -0400
Subject: [PATCH 23/46] net sched: update vlan action for batched events
 operations

[ Upstream commit b35475c5491a14c8ce7a5046ef7bcda8a860581a ]

Add get_fill_size() routine used to calculate the action size
when building a batch of events.

Fixes: c7e2b9689 ("sched: introduce vlan action")
Signed-off-by: Roman Mashak <mrv@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_vlan.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 9269d350fb8a..e0c97267bccb 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -306,6 +306,14 @@ static int tcf_vlan_search(struct net *net, struct tc_action **a, u32 index)
 	return tcf_idr_search(tn, a, index);
 }
 
+static size_t tcf_vlan_get_fill_size(const struct tc_action *act)
+{
+	return nla_total_size(sizeof(struct tc_vlan))
+		+ nla_total_size(sizeof(u16)) /* TCA_VLAN_PUSH_VLAN_ID */
+		+ nla_total_size(sizeof(u16)) /* TCA_VLAN_PUSH_VLAN_PROTOCOL */
+		+ nla_total_size(sizeof(u8)); /* TCA_VLAN_PUSH_VLAN_PRIORITY */
+}
+
 static struct tc_action_ops act_vlan_ops = {
 	.kind		=	"vlan",
 	.id		=	TCA_ID_VLAN,
@@ -315,6 +323,7 @@ static struct tc_action_ops act_vlan_ops = {
 	.init		=	tcf_vlan_init,
 	.cleanup	=	tcf_vlan_cleanup,
 	.walk		=	tcf_vlan_walker,
+	.get_fill_size	=	tcf_vlan_get_fill_size,
 	.lookup		=	tcf_vlan_search,
 	.size		=	sizeof(struct tcf_vlan),
 };
-- 
2.20.1


From 6fb0b80ab8b47b6ba441def4c4dd8de9641e39c0 Mon Sep 17 00:00:00 2001
From: Dmytro Linkin <dmitrolin@mellanox.com>
Date: Thu, 1 Aug 2019 13:02:51 +0000
Subject: [PATCH 24/46] net: sched: use temporary variable for actions indexes

[ Upstream commit 7be8ef2cdbfe41a2e524b7c6cc3f8e6cfaa906e4 ]

Currently init call of all actions (except ipt) init their 'parm'
structure as a direct pointer to nla data in skb. This leads to race
condition when some of the filter actions were initialized successfully
(and were assigned with idr action index that was written directly
into nla data), but then were deleted and retried (due to following
action module missing or classifier-initiated retry), in which case
action init code tries to insert action to idr with index that was
assigned on previous iteration. During retry the index can be reused
by another action that was inserted concurrently, which causes
unintended action sharing between filters.
To fix described race condition, save action idr index to temporary
stack-allocated variable instead on nla data.

Fixes: 0190c1d452a9 ("net: sched: atomically check-allocate action")
Signed-off-by: Dmytro Linkin <dmitrolin@mellanox.com>
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_bpf.c        |  9 +++++----
 net/sched/act_connmark.c   |  9 +++++----
 net/sched/act_csum.c       |  9 +++++----
 net/sched/act_gact.c       |  8 +++++---
 net/sched/act_ife.c        |  8 +++++---
 net/sched/act_mirred.c     | 13 +++++++------
 net/sched/act_nat.c        |  9 +++++----
 net/sched/act_pedit.c      | 10 ++++++----
 net/sched/act_police.c     |  8 +++++---
 net/sched/act_sample.c     | 10 +++++-----
 net/sched/act_simple.c     | 10 ++++++----
 net/sched/act_skbedit.c    | 11 ++++++-----
 net/sched/act_skbmod.c     | 11 ++++++-----
 net/sched/act_tunnel_key.c |  8 +++++---
 net/sched/act_vlan.c       | 16 +++++++++-------
 15 files changed, 85 insertions(+), 64 deletions(-)

diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 8126b26f125e..fd1f7e799e23 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -285,6 +285,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 	struct tcf_bpf *prog;
 	bool is_bpf, is_ebpf;
 	int ret, res = 0;
+	u32 index;
 
 	if (!nla)
 		return -EINVAL;
@@ -298,13 +299,13 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 		return -EINVAL;
 
 	parm = nla_data(tb[TCA_ACT_BPF_PARMS]);
-
-	ret = tcf_idr_check_alloc(tn, &parm->index, act, bind);
+	index = parm->index;
+	ret = tcf_idr_check_alloc(tn, &index, act, bind);
 	if (!ret) {
-		ret = tcf_idr_create(tn, parm->index, est, act,
+		ret = tcf_idr_create(tn, index, est, act,
 				     &act_bpf_ops, bind, true);
 		if (ret < 0) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index ce36b0f7e1dc..32ac04d77a45 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -103,6 +103,7 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla,
 	struct tcf_connmark_info *ci;
 	struct tc_connmark *parm;
 	int ret = 0, err;
+	u32 index;
 
 	if (!nla)
 		return -EINVAL;
@@ -116,13 +117,13 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla,
 		return -EINVAL;
 
 	parm = nla_data(tb[TCA_CONNMARK_PARMS]);
-
-	ret = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	ret = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (!ret) {
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_connmark_ops, bind, false);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 621fb22ce2a9..9b9288267a54 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -52,6 +52,7 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla,
 	struct tc_csum *parm;
 	struct tcf_csum *p;
 	int ret = 0, err;
+	u32 index;
 
 	if (nla == NULL)
 		return -EINVAL;
@@ -64,13 +65,13 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla,
 	if (tb[TCA_CSUM_PARMS] == NULL)
 		return -EINVAL;
 	parm = nla_data(tb[TCA_CSUM_PARMS]);
-
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (!err) {
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_csum_ops, bind, true);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 		ret = ACT_P_CREATED;
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index b2380c5284e6..8f0140c6ca58 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -61,6 +61,7 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
 	struct tc_gact *parm;
 	struct tcf_gact *gact;
 	int ret = 0;
+	u32 index;
 	int err;
 #ifdef CONFIG_GACT_PROB
 	struct tc_gact_p *p_parm = NULL;
@@ -77,6 +78,7 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
 	if (tb[TCA_GACT_PARMS] == NULL)
 		return -EINVAL;
 	parm = nla_data(tb[TCA_GACT_PARMS]);
+	index = parm->index;
 
 #ifndef CONFIG_GACT_PROB
 	if (tb[TCA_GACT_PROB] != NULL)
@@ -94,12 +96,12 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
 	}
 #endif
 
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (!err) {
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_gact_ops, bind, true);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 		ret = ACT_P_CREATED;
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 3578196d1600..92ee853d43e6 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -479,6 +479,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	u8 *saddr = NULL;
 	bool exists = false;
 	int ret = 0;
+	u32 index;
 	int err;
 
 	if (!nla) {
@@ -507,7 +508,8 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	if (!p)
 		return -ENOMEM;
 
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (err < 0) {
 		kfree(p);
 		return err;
@@ -519,10 +521,10 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	}
 
 	if (!exists) {
-		ret = tcf_idr_create(tn, parm->index, est, a, &act_ife_ops,
+		ret = tcf_idr_create(tn, index, est, a, &act_ife_ops,
 				     bind, true);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			kfree(p);
 			return ret;
 		}
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 58e7573dded4..d10dca7a13e1 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -101,6 +101,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 	struct net_device *dev;
 	bool exists = false;
 	int ret, err;
+	u32 index;
 
 	if (!nla) {
 		NL_SET_ERR_MSG_MOD(extack, "Mirred requires attributes to be passed");
@@ -115,8 +116,8 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 		return -EINVAL;
 	}
 	parm = nla_data(tb[TCA_MIRRED_PARMS]);
-
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (err < 0)
 		return err;
 	exists = err;
@@ -133,21 +134,21 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 		if (exists)
 			tcf_idr_release(*a, bind);
 		else
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 		NL_SET_ERR_MSG_MOD(extack, "Unknown mirred option");
 		return -EINVAL;
 	}
 
 	if (!exists) {
 		if (!parm->ifindex) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			NL_SET_ERR_MSG_MOD(extack, "Specified device does not exist");
 			return -EINVAL;
 		}
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_mirred_ops, bind, true);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 		ret = ACT_P_CREATED;
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 45923ebb7a4f..7b858c11b1b5 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -44,6 +44,7 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
 	struct tc_nat *parm;
 	int ret = 0, err;
 	struct tcf_nat *p;
+	u32 index;
 
 	if (nla == NULL)
 		return -EINVAL;
@@ -56,13 +57,13 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
 	if (tb[TCA_NAT_PARMS] == NULL)
 		return -EINVAL;
 	parm = nla_data(tb[TCA_NAT_PARMS]);
-
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (!err) {
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_nat_ops, bind, false);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 		ret = ACT_P_CREATED;
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 45e9d6bfddb3..17360c6faeaa 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -149,6 +149,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 	struct tcf_pedit *p;
 	int ret = 0, err;
 	int ksize;
+	u32 index;
 
 	if (!nla) {
 		NL_SET_ERR_MSG_MOD(extack, "Pedit requires attributes to be passed");
@@ -179,18 +180,19 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 	if (IS_ERR(keys_ex))
 		return PTR_ERR(keys_ex);
 
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (!err) {
 		if (!parm->nkeys) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed");
 			ret = -EINVAL;
 			goto out_free;
 		}
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_pedit_ops, bind, false);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			goto out_free;
 		}
 		ret = ACT_P_CREATED;
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index a065f62fa79c..49cec3e64a4d 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -57,6 +57,7 @@ static int tcf_police_init(struct net *net, struct nlattr *nla,
 	struct tc_action_net *tn = net_generic(net, police_net_id);
 	struct tcf_police_params *new;
 	bool exists = false;
+	u32 index;
 
 	if (nla == NULL)
 		return -EINVAL;
@@ -73,7 +74,8 @@ static int tcf_police_init(struct net *net, struct nlattr *nla,
 		return -EINVAL;
 
 	parm = nla_data(tb[TCA_POLICE_TBF]);
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (err < 0)
 		return err;
 	exists = err;
@@ -81,10 +83,10 @@ static int tcf_police_init(struct net *net, struct nlattr *nla,
 		return 0;
 
 	if (!exists) {
-		ret = tcf_idr_create(tn, parm->index, NULL, a,
+		ret = tcf_idr_create(tn, index, NULL, a,
 				     &act_police_ops, bind, true);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 		ret = ACT_P_CREATED;
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 274d7a0c0e25..595308d60133 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -41,8 +41,8 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 	struct tc_action_net *tn = net_generic(net, sample_net_id);
 	struct nlattr *tb[TCA_SAMPLE_MAX + 1];
 	struct psample_group *psample_group;
+	u32 psample_group_num, rate, index;
 	struct tcf_chain *goto_ch = NULL;
-	u32 psample_group_num, rate;
 	struct tc_sample *parm;
 	struct tcf_sample *s;
 	bool exists = false;
@@ -59,8 +59,8 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 		return -EINVAL;
 
 	parm = nla_data(tb[TCA_SAMPLE_PARMS]);
-
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (err < 0)
 		return err;
 	exists = err;
@@ -68,10 +68,10 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 		return 0;
 
 	if (!exists) {
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_sample_ops, bind, true);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 		ret = ACT_P_CREATED;
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index f28ddbabff76..33aefa25b545 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -95,6 +95,7 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
 	struct tcf_defact *d;
 	bool exists = false;
 	int ret = 0, err;
+	u32 index;
 
 	if (nla == NULL)
 		return -EINVAL;
@@ -108,7 +109,8 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
 		return -EINVAL;
 
 	parm = nla_data(tb[TCA_DEF_PARMS]);
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (err < 0)
 		return err;
 	exists = err;
@@ -119,15 +121,15 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
 		if (exists)
 			tcf_idr_release(*a, bind);
 		else
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 		return -EINVAL;
 	}
 
 	if (!exists) {
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_simp_ops, bind, false);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 215a06705cef..b100870f02a6 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -99,6 +99,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 	u16 *queue_mapping = NULL, *ptype = NULL;
 	bool exists = false;
 	int ret = 0, err;
+	u32 index;
 
 	if (nla == NULL)
 		return -EINVAL;
@@ -146,8 +147,8 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 	}
 
 	parm = nla_data(tb[TCA_SKBEDIT_PARMS]);
-
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (err < 0)
 		return err;
 	exists = err;
@@ -158,15 +159,15 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 		if (exists)
 			tcf_idr_release(*a, bind);
 		else
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 		return -EINVAL;
 	}
 
 	if (!exists) {
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_skbedit_ops, bind, true);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index 4f07706eff07..7da3518e18ef 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -87,12 +87,12 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
 	struct tcf_skbmod_params *p, *p_old;
 	struct tcf_chain *goto_ch = NULL;
 	struct tc_skbmod *parm;
+	u32 lflags = 0, index;
 	struct tcf_skbmod *d;
 	bool exists = false;
 	u8 *daddr = NULL;
 	u8 *saddr = NULL;
 	u16 eth_type = 0;
-	u32 lflags = 0;
 	int ret = 0, err;
 
 	if (!nla)
@@ -122,10 +122,11 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
 	}
 
 	parm = nla_data(tb[TCA_SKBMOD_PARMS]);
+	index = parm->index;
 	if (parm->flags & SKBMOD_F_SWAPMAC)
 		lflags = SKBMOD_F_SWAPMAC;
 
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (err < 0)
 		return err;
 	exists = err;
@@ -136,15 +137,15 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
 		if (exists)
 			tcf_idr_release(*a, bind);
 		else
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 		return -EINVAL;
 	}
 
 	if (!exists) {
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_skbmod_ops, bind, true);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 10dffda1d5cc..6d0debdc9b97 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -225,6 +225,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 	__be16 flags = 0;
 	u8 tos, ttl;
 	int ret = 0;
+	u32 index;
 	int err;
 
 	if (!nla) {
@@ -245,7 +246,8 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 	}
 
 	parm = nla_data(tb[TCA_TUNNEL_KEY_PARMS]);
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (err < 0)
 		return err;
 	exists = err;
@@ -345,7 +347,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 	}
 
 	if (!exists) {
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_tunnel_key_ops, bind, true);
 		if (ret) {
 			NL_SET_ERR_MSG(extack, "Cannot create TC IDR");
@@ -403,7 +405,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 	if (exists)
 		tcf_idr_release(*a, bind);
 	else
-		tcf_idr_cleanup(tn, parm->index);
+		tcf_idr_cleanup(tn, index);
 	return ret;
 }
 
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index e0c97267bccb..a3c9eea1ee8a 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -116,6 +116,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 	u8 push_prio = 0;
 	bool exists = false;
 	int ret = 0, err;
+	u32 index;
 
 	if (!nla)
 		return -EINVAL;
@@ -128,7 +129,8 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 	if (!tb[TCA_VLAN_PARMS])
 		return -EINVAL;
 	parm = nla_data(tb[TCA_VLAN_PARMS]);
-	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (err < 0)
 		return err;
 	exists = err;
@@ -144,7 +146,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 			if (exists)
 				tcf_idr_release(*a, bind);
 			else
-				tcf_idr_cleanup(tn, parm->index);
+				tcf_idr_cleanup(tn, index);
 			return -EINVAL;
 		}
 		push_vid = nla_get_u16(tb[TCA_VLAN_PUSH_VLAN_ID]);
@@ -152,7 +154,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 			if (exists)
 				tcf_idr_release(*a, bind);
 			else
-				tcf_idr_cleanup(tn, parm->index);
+				tcf_idr_cleanup(tn, index);
 			return -ERANGE;
 		}
 
@@ -166,7 +168,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 				if (exists)
 					tcf_idr_release(*a, bind);
 				else
-					tcf_idr_cleanup(tn, parm->index);
+					tcf_idr_cleanup(tn, index);
 				return -EPROTONOSUPPORT;
 			}
 		} else {
@@ -180,16 +182,16 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 		if (exists)
 			tcf_idr_release(*a, bind);
 		else
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 		return -EINVAL;
 	}
 	action = parm->v_action;
 
 	if (!exists) {
-		ret = tcf_idr_create(tn, parm->index, est, a,
+		ret = tcf_idr_create(tn, index, est, a,
 				     &act_vlan_ops, bind, true);
 		if (ret) {
-			tcf_idr_cleanup(tn, parm->index);
+			tcf_idr_cleanup(tn, index);
 			return ret;
 		}
 
-- 
2.20.1


From 553b2282448972b655e8fd456b2097b26e9f393b Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.ibm.com>
Date: Fri, 2 Aug 2019 10:16:38 +0200
Subject: [PATCH 25/46] net/smc: do not schedule tx_work in SMC_CLOSED state

[ Upstream commit f9cedf1a9b1cdcfb0c52edb391d01771e43994a4 ]

The setsockopts options TCP_NODELAY and TCP_CORK may schedule the
tx worker. Make sure the socket is not yet moved into SMC_CLOSED
state (for instance by a shutdown SHUT_RDWR call).

Reported-by: syzbot+92209502e7aab127c75f@syzkaller.appspotmail.com
Reported-by: syzbot+b972214bb803a343f4fe@syzkaller.appspotmail.com
Fixes: 01d2f7e2cdd31 ("net/smc: sockopts TCP_NODELAY and TCP_CORK")
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/af_smc.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 7621ec2f539c..4b2f555a0db2 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1741,14 +1741,18 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
 		}
 		break;
 	case TCP_NODELAY:
-		if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) {
+		if (sk->sk_state != SMC_INIT &&
+		    sk->sk_state != SMC_LISTEN &&
+		    sk->sk_state != SMC_CLOSED) {
 			if (val && !smc->use_fallback)
 				mod_delayed_work(system_wq, &smc->conn.tx_work,
 						 0);
 		}
 		break;
 	case TCP_CORK:
-		if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) {
+		if (sk->sk_state != SMC_INIT &&
+		    sk->sk_state != SMC_LISTEN &&
+		    sk->sk_state != SMC_CLOSED) {
 			if (!val && !smc->use_fallback)
 				mod_delayed_work(system_wq, &smc->conn.tx_work,
 						 0);
-- 
2.20.1


From fab4a7a0f15b840b4d01645d8c415d3cb49cab2a Mon Sep 17 00:00:00 2001
From: Frode Isaksen <fisaksen@baylibre.com>
Date: Tue, 30 Jul 2019 13:38:14 +0200
Subject: [PATCH 26/46] net: stmmac: Use netif_tx_napi_add() for TX polling
 function

[ Upstream commit 4d97972b45f080db4c6d27cc0b54321d9cd7be17 ]

This variant of netif_napi_add() should be used from drivers
using NAPI to exclusively poll a TX queue.

Signed-off-by: Frode Isaksen <fisaksen@baylibre.com>
Tested-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 932e54e25b71..b14f46a57154 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -4374,8 +4374,9 @@ int stmmac_dvr_probe(struct device *device,
 				       NAPI_POLL_WEIGHT);
 		}
 		if (queue < priv->plat->tx_queues_to_use) {
-			netif_napi_add(ndev, &ch->tx_napi, stmmac_napi_poll_tx,
-				       NAPI_POLL_WEIGHT);
+			netif_tx_napi_add(ndev, &ch->tx_napi,
+					  stmmac_napi_poll_tx,
+					  NAPI_POLL_WEIGHT);
 		}
 	}
 
-- 
2.20.1


From 2019573471fe7cc533c6411c1f80969a8b56648c Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 5 Aug 2019 12:00:55 +0200
Subject: [PATCH 27/46] NFC: nfcmrvl: fix gpio-handling regression

[ Upstream commit c3953a3c2d3175d2f9f0304c9a1ba89e7743c5e4 ]

Fix two reset-gpio sanity checks which were never converted to use
gpio_is_valid(), and make sure to use -EINVAL to indicate a missing
reset line also for the UART-driver module parameter and for the USB
driver.

This specifically prevents the UART and USB drivers from incidentally
trying to request and use gpio 0, and also avoids triggering a WARN() in
gpio_to_desc() during probe when no valid reset line has been specified.

Fixes: e33a3f84f88f ("NFC: nfcmrvl: allow gpio 0 for reset signalling")
Reported-by: syzbot+cf35b76f35e068a1107f@syzkaller.appspotmail.com
Tested-by: syzbot+cf35b76f35e068a1107f@syzkaller.appspotmail.com
Signed-off-by: Johan Hovold <johan@kernel.org>
---
 drivers/nfc/nfcmrvl/main.c | 4 ++--
 drivers/nfc/nfcmrvl/uart.c | 4 ++--
 drivers/nfc/nfcmrvl/usb.c  | 1 +
 3 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/nfc/nfcmrvl/main.c b/drivers/nfc/nfcmrvl/main.c
index e65d027b91fa..529be35ac178 100644
--- a/drivers/nfc/nfcmrvl/main.c
+++ b/drivers/nfc/nfcmrvl/main.c
@@ -244,7 +244,7 @@ void nfcmrvl_chip_reset(struct nfcmrvl_private *priv)
 	/* Reset possible fault of previous session */
 	clear_bit(NFCMRVL_PHY_ERROR, &priv->flags);
 
-	if (priv->config.reset_n_io) {
+	if (gpio_is_valid(priv->config.reset_n_io)) {
 		nfc_info(priv->dev, "reset the chip\n");
 		gpio_set_value(priv->config.reset_n_io, 0);
 		usleep_range(5000, 10000);
@@ -255,7 +255,7 @@ void nfcmrvl_chip_reset(struct nfcmrvl_private *priv)
 
 void nfcmrvl_chip_halt(struct nfcmrvl_private *priv)
 {
-	if (priv->config.reset_n_io)
+	if (gpio_is_valid(priv->config.reset_n_io))
 		gpio_set_value(priv->config.reset_n_io, 0);
 }
 
diff --git a/drivers/nfc/nfcmrvl/uart.c b/drivers/nfc/nfcmrvl/uart.c
index 9a22056e8d9e..e5a622ce4b95 100644
--- a/drivers/nfc/nfcmrvl/uart.c
+++ b/drivers/nfc/nfcmrvl/uart.c
@@ -26,7 +26,7 @@
 static unsigned int hci_muxed;
 static unsigned int flow_control;
 static unsigned int break_control;
-static unsigned int reset_n_io;
+static int reset_n_io = -EINVAL;
 
 /*
 ** NFCMRVL NCI OPS
@@ -231,5 +231,5 @@ MODULE_PARM_DESC(break_control, "Tell if UART driver must drive break signal.");
 module_param(hci_muxed, uint, 0);
 MODULE_PARM_DESC(hci_muxed, "Tell if transport is muxed in HCI one.");
 
-module_param(reset_n_io, uint, 0);
+module_param(reset_n_io, int, 0);
 MODULE_PARM_DESC(reset_n_io, "GPIO that is wired to RESET_N signal.");
diff --git a/drivers/nfc/nfcmrvl/usb.c b/drivers/nfc/nfcmrvl/usb.c
index 945cc903d8f1..888e298f610b 100644
--- a/drivers/nfc/nfcmrvl/usb.c
+++ b/drivers/nfc/nfcmrvl/usb.c
@@ -305,6 +305,7 @@ static int nfcmrvl_probe(struct usb_interface *intf,
 
 	/* No configuration for USB */
 	memset(&config, 0, sizeof(config));
+	config.reset_n_io = -EINVAL;
 
 	nfc_info(&udev->dev, "intf %p id %p\n", intf, id);
 
-- 
2.20.1


From 3ecc5aac544b9cdae4d660e63d1b7e434991631f Mon Sep 17 00:00:00 2001
From: Claudiu Manoil <claudiu.manoil@nxp.com>
Date: Thu, 25 Jul 2019 16:33:18 +0300
Subject: [PATCH 28/46] ocelot: Cancel delayed work before wq destruction

[ Upstream commit c5d139697d5d9ecf9c7cd92d7d7838a173508900 ]

Make sure the delayed work for stats update is not pending before
wq destruction.
This fixes the module unload path.
The issue is there since day 1.

Fixes: a556c76adc05 ("net: mscc: Add initial Ocelot switch support")

Signed-off-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Reviewed-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 02ad11e0b0d8..58e76e7cb0d6 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -1797,6 +1797,7 @@ EXPORT_SYMBOL(ocelot_init);
 
 void ocelot_deinit(struct ocelot *ocelot)
 {
+	cancel_delayed_work(&ocelot->stats_work);
 	destroy_workqueue(ocelot->stats_queue);
 	mutex_destroy(&ocelot->stats_lock);
 }
-- 
2.20.1


From 9480e60427b779e78f782b5d5b1bee310ca7424b Mon Sep 17 00:00:00 2001
From: Taras Kondratiuk <takondra@cisco.com>
Date: Mon, 29 Jul 2019 22:15:07 +0000
Subject: [PATCH 29/46] tipc: compat: allow tipc commands without arguments

[ Upstream commit 4da5f0018eef4c0de31675b670c80e82e13e99d1 ]

Commit 2753ca5d9009 ("tipc: fix uninit-value in tipc_nl_compat_doit")
broke older tipc tools that use compat interface (e.g. tipc-config from
tipcutils package):

% tipc-config -p
operation not supported

The commit started to reject TIPC netlink compat messages that do not
have attributes. It is too restrictive because some of such messages are
valid (they don't need any arguments):

% grep 'tx none' include/uapi/linux/tipc_config.h
#define  TIPC_CMD_NOOP              0x0000    /* tx none, rx none */
#define  TIPC_CMD_GET_MEDIA_NAMES   0x0002    /* tx none, rx media_name(s) */
#define  TIPC_CMD_GET_BEARER_NAMES  0x0003    /* tx none, rx bearer_name(s) */
#define  TIPC_CMD_SHOW_PORTS        0x0006    /* tx none, rx ultra_string */
#define  TIPC_CMD_GET_REMOTE_MNG    0x4003    /* tx none, rx unsigned */
#define  TIPC_CMD_GET_MAX_PORTS     0x4004    /* tx none, rx unsigned */
#define  TIPC_CMD_GET_NETID         0x400B    /* tx none, rx unsigned */
#define  TIPC_CMD_NOT_NET_ADMIN     0xC001    /* tx none, rx none */

This patch relaxes the original fix and rejects messages without
arguments only if such arguments are expected by a command (reg_type is
non zero).

Fixes: 2753ca5d9009 ("tipc: fix uninit-value in tipc_nl_compat_doit")
Cc: stable@vger.kernel.org
Signed-off-by: Taras Kondratiuk <takondra@cisco.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/netlink_compat.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index cf155061c472..acd8a72169c1 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -55,6 +55,7 @@ struct tipc_nl_compat_msg {
 	int rep_type;
 	int rep_size;
 	int req_type;
+	int req_size;
 	struct net *net;
 	struct sk_buff *rep;
 	struct tlv_desc *req;
@@ -257,7 +258,8 @@ static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd,
 	int err;
 	struct sk_buff *arg;
 
-	if (msg->req_type && !TLV_CHECK_TYPE(msg->req, msg->req_type))
+	if (msg->req_type && (!msg->req_size ||
+			      !TLV_CHECK_TYPE(msg->req, msg->req_type)))
 		return -EINVAL;
 
 	msg->rep = tipc_tlv_alloc(msg->rep_size);
@@ -354,7 +356,8 @@ static int tipc_nl_compat_doit(struct tipc_nl_compat_cmd_doit *cmd,
 {
 	int err;
 
-	if (msg->req_type && !TLV_CHECK_TYPE(msg->req, msg->req_type))
+	if (msg->req_type && (!msg->req_size ||
+			      !TLV_CHECK_TYPE(msg->req, msg->req_type)))
 		return -EINVAL;
 
 	err = __tipc_nl_compat_doit(cmd, msg);
@@ -1288,8 +1291,8 @@ static int tipc_nl_compat_recv(struct sk_buff *skb, struct genl_info *info)
 		goto send;
 	}
 
-	len = nlmsg_attrlen(req_nlh, GENL_HDRLEN + TIPC_GENL_HDRLEN);
-	if (!len || !TLV_OK(msg.req, len)) {
+	msg.req_size = nlmsg_attrlen(req_nlh, GENL_HDRLEN + TIPC_GENL_HDRLEN);
+	if (msg.req_size && !TLV_OK(msg.req, msg.req_size)) {
 		msg.rep = tipc_get_err_tlv(TIPC_CFG_NOT_SUPPORTED);
 		err = -EOPNOTSUPP;
 		goto send;
-- 
2.20.1


From b4f889e3186ed23f57e58d3c057056686f6e6e9e Mon Sep 17 00:00:00 2001
From: Jon Maloy <jon.maloy@ericsson.com>
Date: Tue, 30 Jul 2019 20:19:10 +0200
Subject: [PATCH 30/46] tipc: fix unitilized skb list crash

[ Upstream commit 2948a1fcd77a8bb11604387e3fc52f0ebf5729e9 ]

Our test suite somtimes provokes the following crash:

Description of problem:
[ 1092.597234] BUG: unable to handle kernel NULL pointer dereference at 00000000000000e8
[ 1092.605072] PGD 0 P4D 0
[ 1092.607620] Oops: 0000 [#1] SMP PTI
[ 1092.611118] CPU: 37 PID: 0 Comm: swapper/37 Kdump: loaded Not tainted 4.18.0-122.el8.x86_64 #1
[ 1092.619724] Hardware name: Dell Inc. PowerEdge R740/08D89F, BIOS 1.3.7 02/08/2018
[ 1092.627215] RIP: 0010:tipc_mcast_filter_msg+0x93/0x2d0 [tipc]
[ 1092.632955] Code: 0f 84 aa 01 00 00 89 cf 4d 01 ca 4c 8b 26 c1 ef 19 83 e7 0f 83 ff 0c 4d 0f 45 d1 41 8b 6a 10 0f cd 4c 39 e6 0f 84 81 01 00 00 <4d> 8b 9c 24 e8 00 00 00 45 8b 13 41 0f ca 44 89 d7 c1 ef 13 83 e7
[ 1092.651703] RSP: 0018:ffff929e5fa83a18 EFLAGS: 00010282
[ 1092.656927] RAX: ffff929e3fb38100 RBX: 00000000069f29ee RCX: 00000000416c0045
[ 1092.664058] RDX: ffff929e5fa83a88 RSI: ffff929e31a28420 RDI: 0000000000000000
[ 1092.671209] RBP: 0000000029b11821 R08: 0000000000000000 R09: ffff929e39b4407a
[ 1092.678343] R10: ffff929e39b4407a R11: 0000000000000007 R12: 0000000000000000
[ 1092.685475] R13: 0000000000000001 R14: ffff929e3fb38100 R15: ffff929e39b4407a
[ 1092.692614] FS:  0000000000000000(0000) GS:ffff929e5fa80000(0000) knlGS:0000000000000000
[ 1092.700702] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 1092.706447] CR2: 00000000000000e8 CR3: 000000031300a004 CR4: 00000000007606e0
[ 1092.713579] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 1092.720712] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ 1092.727843] PKRU: 55555554
[ 1092.730556] Call Trace:
[ 1092.733010]  <IRQ>
[ 1092.735034]  tipc_sk_filter_rcv+0x7ca/0xb80 [tipc]
[ 1092.739828]  ? __kmalloc_node_track_caller+0x1cb/0x290
[ 1092.744974]  ? dev_hard_start_xmit+0xa5/0x210
[ 1092.749332]  tipc_sk_rcv+0x389/0x640 [tipc]
[ 1092.753519]  tipc_sk_mcast_rcv+0x23c/0x3a0 [tipc]
[ 1092.758224]  tipc_rcv+0x57a/0xf20 [tipc]
[ 1092.762154]  ? ktime_get_real_ts64+0x40/0xe0
[ 1092.766432]  ? tpacket_rcv+0x50/0x9f0
[ 1092.770098]  tipc_l2_rcv_msg+0x4a/0x70 [tipc]
[ 1092.774452]  __netif_receive_skb_core+0xb62/0xbd0
[ 1092.779164]  ? enqueue_entity+0xf6/0x630
[ 1092.783084]  ? kmem_cache_alloc+0x158/0x1c0
[ 1092.787272]  ? __build_skb+0x25/0xd0
[ 1092.790849]  netif_receive_skb_internal+0x42/0xf0
[ 1092.795557]  napi_gro_receive+0xba/0xe0
[ 1092.799417]  mlx5e_handle_rx_cqe+0x83/0xd0 [mlx5_core]
[ 1092.804564]  mlx5e_poll_rx_cq+0xd5/0x920 [mlx5_core]
[ 1092.809536]  mlx5e_napi_poll+0xb2/0xce0 [mlx5_core]
[ 1092.814415]  ? __wake_up_common_lock+0x89/0xc0
[ 1092.818861]  net_rx_action+0x149/0x3b0
[ 1092.822616]  __do_softirq+0xe3/0x30a
[ 1092.826193]  irq_exit+0x100/0x110
[ 1092.829512]  do_IRQ+0x85/0xd0
[ 1092.832483]  common_interrupt+0xf/0xf
[ 1092.836147]  </IRQ>
[ 1092.838255] RIP: 0010:cpuidle_enter_state+0xb7/0x2a0
[ 1092.843221] Code: e8 3e 79 a5 ff 80 7c 24 03 00 74 17 9c 58 0f 1f 44 00 00 f6 c4 02 0f 85 d7 01 00 00 31 ff e8 a0 6b ab ff fb 66 0f 1f 44 00 00 <48> b8 ff ff ff ff f3 01 00 00 4c 29 f3 ba ff ff ff 7f 48 39 c3 7f
[ 1092.861967] RSP: 0018:ffffaa5ec6533e98 EFLAGS: 00000246 ORIG_RAX: ffffffffffffffdd
[ 1092.869530] RAX: ffff929e5faa3100 RBX: 000000fe63dd2092 RCX: 000000000000001f
[ 1092.876665] RDX: 000000fe63dd2092 RSI: 000000003a518aaa RDI: 0000000000000000
[ 1092.883795] RBP: 0000000000000003 R08: 0000000000000004 R09: 0000000000022940
[ 1092.890929] R10: 0000040cb0666b56 R11: ffff929e5faa20a8 R12: ffff929e5faade78
[ 1092.898060] R13: ffffffffb59258f8 R14: 000000fe60f3228d R15: 0000000000000000
[ 1092.905196]  ? cpuidle_enter_state+0x92/0x2a0
[ 1092.909555]  do_idle+0x236/0x280
[ 1092.912785]  cpu_startup_entry+0x6f/0x80
[ 1092.916715]  start_secondary+0x1a7/0x200
[ 1092.920642]  secondary_startup_64+0xb7/0xc0
[...]

The reason is that the skb list tipc_socket::mc_method.deferredq only
is initialized for connectionless sockets, while nothing stops arriving
multicast messages from being filtered by connection oriented sockets,
with subsequent access to the said list.

We fix this by initializing the list unconditionally at socket creation.
This eliminates the crash, while the message still is dropped further
down in tipc_sk_filter_rcv() as it should be.

Reported-by: Li Shuang <shuali@redhat.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/socket.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index dd8537f988c4..83ae41d7e554 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -485,9 +485,8 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
 		tsk_set_unreturnable(tsk, true);
 		if (sock->type == SOCK_DGRAM)
 			tsk_set_unreliable(tsk, true);
-		__skb_queue_head_init(&tsk->mc_method.deferredq);
 	}
-
+	__skb_queue_head_init(&tsk->mc_method.deferredq);
 	trace_tipc_sk_create(sk, NULL, TIPC_DUMP_NONE, " ");
 	return 0;
 }
-- 
2.20.1


From 91a2164499602d5b5355dc21052c45303369474a Mon Sep 17 00:00:00 2001
From: Alexis Bauvin <abauvin@scaleway.com>
Date: Tue, 23 Jul 2019 16:23:01 +0200
Subject: [PATCH 31/46] tun: mark small packets as owned by the tap sock

[ Upstream commit 4b663366246be1d1d4b1b8b01245b2e88ad9e706 ]

- v1 -> v2: Move skb_set_owner_w to __tun_build_skb to reduce patch size

Small packets going out of a tap device go through an optimized code
path that uses build_skb() rather than sock_alloc_send_pskb(). The
latter calls skb_set_owner_w(), but the small packet code path does not.

The net effect is that small packets are not owned by the userland
application's socket (e.g. QEMU), while large packets are.
This can be seen with a TCP session, where packets are not owned when
the window size is small enough (around PAGE_SIZE), while they are once
the window grows (note that this requires the host to support virtio
tso for the guest to offload segmentation).
All this leads to inconsistent behaviour in the kernel, especially on
netfilter modules that uses sk->socket (e.g. xt_owner).

Fixes: 66ccbc9c87c2 ("tap: use build_skb() for small packet")
Signed-off-by: Alexis Bauvin <abauvin@scaleway.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index d7c55e0fa8f4..192ac47fd055 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1600,7 +1600,8 @@ static bool tun_can_build_skb(struct tun_struct *tun, struct tun_file *tfile,
 	return true;
 }
 
-static struct sk_buff *__tun_build_skb(struct page_frag *alloc_frag, char *buf,
+static struct sk_buff *__tun_build_skb(struct tun_file *tfile,
+				       struct page_frag *alloc_frag, char *buf,
 				       int buflen, int len, int pad)
 {
 	struct sk_buff *skb = build_skb(buf, buflen);
@@ -1610,6 +1611,7 @@ static struct sk_buff *__tun_build_skb(struct page_frag *alloc_frag, char *buf,
 
 	skb_reserve(skb, pad);
 	skb_put(skb, len);
+	skb_set_owner_w(skb, tfile->socket.sk);
 
 	get_page(alloc_frag->page);
 	alloc_frag->offset += buflen;
@@ -1687,7 +1689,8 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 	 */
 	if (hdr->gso_type || !xdp_prog) {
 		*skb_xdp = 1;
-		return __tun_build_skb(alloc_frag, buf, buflen, len, pad);
+		return __tun_build_skb(tfile, alloc_frag, buf, buflen, len,
+				       pad);
 	}
 
 	*skb_xdp = 0;
@@ -1724,7 +1727,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 	rcu_read_unlock();
 	local_bh_enable();
 
-	return __tun_build_skb(alloc_frag, buf, buflen, len, pad);
+	return __tun_build_skb(tfile, alloc_frag, buf, buflen, len, pad);
 
 err_xdp:
 	put_page(alloc_frag->page);
-- 
2.20.1


From 6ee8b36b6eecc40c446daf4fcafa8b6c4022a968 Mon Sep 17 00:00:00 2001
From: Edward Srouji <edwards@mellanox.com>
Date: Tue, 23 Jul 2019 10:12:55 +0300
Subject: [PATCH 32/46] net/mlx5: Fix modify_cq_in alignment

[ Upstream commit 7a32f2962c56d9d8a836b4469855caeee8766bd4 ]

Fix modify_cq_in alignment to match the device specification.
After this fix the 'cq_umem_valid' field will be in the right offset.

Cc: <stable@vger.kernel.org> # 4.19
Fixes: bd37197554eb ("net/mlx5: Update mlx5_ifc with DEVX UID bits")
Signed-off-by: Edward Srouji <edwards@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 include/linux/mlx5/mlx5_ifc.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 7e42efa143a0..29b55f8cd7b3 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -5865,10 +5865,12 @@ struct mlx5_ifc_modify_cq_in_bits {
 
 	struct mlx5_ifc_cqc_bits cq_context;
 
-	u8         reserved_at_280[0x40];
+	u8         reserved_at_280[0x60];
 
 	u8         cq_umem_valid[0x1];
-	u8         reserved_at_2c1[0x5bf];
+	u8         reserved_at_2e1[0x1f];
+
+	u8         reserved_at_300[0x580];
 
 	u8         pas[0][0x40];
 };
-- 
2.20.1


From 3af5defb0c096a17507d28ea46d467f4b9bed071 Mon Sep 17 00:00:00 2001
From: Ariel Levkovich <lariel@mellanox.com>
Date: Sat, 6 Jul 2019 18:06:15 +0300
Subject: [PATCH 33/46] net/mlx5e: Prevent encap flow counter update async to
 user query

[ Upstream commit 90bb769291161cf25a818d69cf608c181654473e ]

This patch prevents a race between user invoked cached counters
query and a neighbor last usage updater.

The cached flow counter stats can be queried by calling
"mlx5_fc_query_cached" which provides the number of bytes and
packets that passed via this flow since the last time this counter
was queried.
It does so by reducting the last saved stats from the current, cached
stats and then updating the last saved stats with the cached stats.
It also provide the lastuse value for that flow.

Since "mlx5e_tc_update_neigh_used_value" needs to retrieve the
last usage time of encapsulation flows, it calls the flow counter
query method periodically and async to user queries of the flow counter
using cls_flower.
This call is causing the driver to update the last reported bytes and
packets from the cache and therefore, future user queries of the flow
stats will return lower than expected number for bytes and packets
since the last saved stats in the driver was updated async to the last
saved stats in cls_flower.

This causes wrong stats presentation of encapsulation flows to user.

Since the neighbor usage updater only needs the lastuse stats from the
cached counter, the fix is to use a dedicated lastuse query call that
returns the lastuse value without synching between the cached stats and
the last saved stats.

Fixes: f6dfb4c3f216 ("net/mlx5e: Update neighbour 'used' state using HW flow rules counters")
Signed-off-by: Ariel Levkovich <lariel@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c       | 4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c | 5 +++++
 include/linux/mlx5/fs.h                               | 1 +
 3 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index e40c60d1631f..ee95f96ead4e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1210,13 +1210,13 @@ static struct mlx5_fc *mlx5e_tc_get_counter(struct mlx5e_tc_flow *flow)
 void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe)
 {
 	struct mlx5e_neigh *m_neigh = &nhe->m_neigh;
-	u64 bytes, packets, lastuse = 0;
 	struct mlx5e_tc_flow *flow;
 	struct mlx5e_encap_entry *e;
 	struct mlx5_fc *counter;
 	struct neigh_table *tbl;
 	bool neigh_used = false;
 	struct neighbour *n;
+	u64 lastuse;
 
 	if (m_neigh->family == AF_INET)
 		tbl = &arp_tbl;
@@ -1236,7 +1236,7 @@ void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe)
 					    encaps[efi->index]);
 			if (flow->flags & MLX5E_TC_FLOW_OFFLOADED) {
 				counter = mlx5e_tc_get_counter(flow);
-				mlx5_fc_query_cached(counter, &bytes, &packets, &lastuse);
+				lastuse = mlx5_fc_query_lastuse(counter);
 				if (time_after((unsigned long)lastuse, nhe->reported_lastuse)) {
 					neigh_used = true;
 					break;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
index c6c28f56aa29..add9db67028f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
@@ -367,6 +367,11 @@ int mlx5_fc_query(struct mlx5_core_dev *dev, struct mlx5_fc *counter,
 }
 EXPORT_SYMBOL(mlx5_fc_query);
 
+u64 mlx5_fc_query_lastuse(struct mlx5_fc *counter)
+{
+	return counter->cache.lastuse;
+}
+
 void mlx5_fc_query_cached(struct mlx5_fc *counter,
 			  u64 *bytes, u64 *packets, u64 *lastuse)
 {
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index e690ba0f965c..70185079f83e 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -211,6 +211,7 @@ int mlx5_modify_rule_destination(struct mlx5_flow_handle *handler,
 
 struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging);
 void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter);
+u64 mlx5_fc_query_lastuse(struct mlx5_fc *counter);
 void mlx5_fc_query_cached(struct mlx5_fc *counter,
 			  u64 *bytes, u64 *packets, u64 *lastuse);
 int mlx5_fc_query(struct mlx5_core_dev *dev, struct mlx5_fc *counter,
-- 
2.20.1


From 311b74097ddf180b67d67a44a1c9488e1d6f20cb Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 27 Jul 2019 12:45:10 +0200
Subject: [PATCH 34/46] r8169: don't use MSI before RTL8168d
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 003bd5b4a7b4a94b501e3a1e2e7c9df6b2a94ed4 ]

It was reported that after resuming from suspend network fails with
error "do_IRQ: 3.38 No irq handler for vector", see [0]. Enabling WoL
can work around the issue, but the only actual fix is to disable MSI.
So let's mimic the behavior of the vendor driver and disable MSI on
all chip versions before RTL8168d.

[0] https://bugzilla.kernel.org/show_bug.cgi?id=204079

Fixes: 6c6aa15fdea5 ("r8169: improve interrupt handling")
Reported-by: Dušan Dragić <dragic.dusan@gmail.com>
Tested-by: Dušan Dragić <dragic.dusan@gmail.com>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
---
 drivers/net/ethernet/realtek/r8169.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 96637fcbe65d..36261b2959b4 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -7050,13 +7050,18 @@ static int rtl_alloc_irq(struct rtl8169_private *tp)
 {
 	unsigned int flags;
 
-	if (tp->mac_version <= RTL_GIGA_MAC_VER_06) {
+	switch (tp->mac_version) {
+	case RTL_GIGA_MAC_VER_02 ... RTL_GIGA_MAC_VER_06:
 		rtl_unlock_config_regs(tp);
 		RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~MSIEnable);
 		rtl_lock_config_regs(tp);
+		/* fall through */
+	case RTL_GIGA_MAC_VER_07 ... RTL_GIGA_MAC_VER_24:
 		flags = PCI_IRQ_LEGACY;
-	} else {
+		break;
+	default:
 		flags = PCI_IRQ_ALL_TYPES;
+		break;
 	}
 
 	return pci_alloc_irq_vectors(tp->pci_dev, 1, 1, flags);
-- 
2.20.1


From 56bf323e91e3d742f02edaa5d6c45b990b34f226 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Thu, 1 Aug 2019 20:00:16 +0200
Subject: [PATCH 35/46] bpf: fix XDP vlan selftests test_xdp_vlan.sh

[ Upstream commit 4de9c89a4982431c4a02739743fd360dc5581f22 ]

Change BPF selftest test_xdp_vlan.sh to (default) use generic XDP.

This selftest was created together with a fix for generic XDP, in commit
297249569932 ("net: fix generic XDP to handle if eth header was
mangled"). And was suppose to catch if generic XDP was broken again.

The tests are using veth and assumed that veth driver didn't support
native driver XDP, thus it used the (ip link set) 'xdp' attach that fell
back to generic-XDP. But veth gained native-XDP support in 948d4f214fde
("veth: Add driver XDP"), which caused this test script to use
native-XDP.

Fixes: 948d4f214fde ("veth: Add driver XDP")
Fixes: 97396ff0bc2d ("selftests/bpf: add XDP selftests for modifying and popping VLAN headers")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/bpf/test_xdp_vlan.sh | 42 +++++++++++++++++---
 1 file changed, 36 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_xdp_vlan.sh b/tools/testing/selftests/bpf/test_xdp_vlan.sh
index 51a3a31d1aac..c8aed63b0ffe 100755
--- a/tools/testing/selftests/bpf/test_xdp_vlan.sh
+++ b/tools/testing/selftests/bpf/test_xdp_vlan.sh
@@ -1,7 +1,12 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Author: Jesper Dangaard Brouer <hawk@kernel.org>
 
 TESTNAME=xdp_vlan
 
+# Default XDP mode
+XDP_MODE=xdpgeneric
+
 usage() {
   echo "Testing XDP + TC eBPF VLAN manipulations: $TESTNAME"
   echo ""
@@ -9,9 +14,23 @@ usage() {
   echo "  -v | --verbose : Verbose"
   echo "  --flush        : Flush before starting (e.g. after --interactive)"
   echo "  --interactive  : Keep netns setup running after test-run"
+  echo "  --mode=XXX     : Choose XDP mode (xdp | xdpgeneric | xdpdrv)"
   echo ""
 }
 
+valid_xdp_mode()
+{
+	local mode=$1
+
+	case "$mode" in
+		xdpgeneric | xdpdrv | xdp)
+			return 0
+			;;
+		*)
+			return 1
+	esac
+}
+
 cleanup()
 {
 	local status=$?
@@ -37,7 +56,7 @@ cleanup()
 
 # Using external program "getopt" to get --long-options
 OPTIONS=$(getopt -o hvfi: \
-    --long verbose,flush,help,interactive,debug -- "$@")
+    --long verbose,flush,help,interactive,debug,mode: -- "$@")
 if (( $? != 0 )); then
     usage
     echo "selftests: $TESTNAME [FAILED] Error calling getopt, unknown option?"
@@ -60,6 +79,11 @@ while true; do
 		cleanup
 		shift
 		;;
+	    --mode )
+		shift
+		XDP_MODE=$1
+		shift
+		;;
 	    -- )
 		shift
 		break
@@ -81,8 +105,14 @@ if [ "$EUID" -ne 0 ]; then
 	exit 1
 fi
 
-ip link set dev lo xdp off 2>/dev/null > /dev/null
-if [ $? -ne 0 ];then
+valid_xdp_mode $XDP_MODE
+if [ $? -ne 0 ]; then
+	echo "selftests: $TESTNAME [FAILED] unknown XDP mode ($XDP_MODE)"
+	exit 1
+fi
+
+ip link set dev lo xdpgeneric off 2>/dev/null > /dev/null
+if [ $? -ne 0 ]; then
 	echo "selftests: $TESTNAME [SKIP] need ip xdp support"
 	exit 0
 fi
@@ -166,7 +196,7 @@ export FILE=test_xdp_vlan.o
 
 # First test: Remove VLAN by setting VLAN ID 0, using "xdp_vlan_change"
 export XDP_PROG=xdp_vlan_change
-ip netns exec ns1 ip link set $DEVNS1 xdp object $FILE section $XDP_PROG
+ip netns exec ns1 ip link set $DEVNS1 $XDP_MODE object $FILE section $XDP_PROG
 
 # In ns1: egress use TC to add back VLAN tag 4011
 #  (del cmd)
@@ -187,8 +217,8 @@ ip netns exec ns1 ping -W 2 -c 3 $IPADDR2
 # ETH_P_8021Q indication, and this cause overwriting of our changes.
 #
 export XDP_PROG=xdp_vlan_remove_outer2
-ip netns exec ns1 ip link set $DEVNS1 xdp off
-ip netns exec ns1 ip link set $DEVNS1 xdp object $FILE section $XDP_PROG
+ip netns exec ns1 ip link set $DEVNS1 $XDP_MODE off
+ip netns exec ns1 ip link set $DEVNS1 $XDP_MODE object $FILE section $XDP_PROG
 
 # Now the namespaces should still be able reach each-other, test with ping:
 ip netns exec ns2 ping -W 2 -c 3 $IPADDR1
-- 
2.20.1


From 8d0566b9e5712c2ef61c9e76b8736675bb34279f Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Thu, 1 Aug 2019 20:00:21 +0200
Subject: [PATCH 36/46] selftests/bpf: add wrapper scripts for test_xdp_vlan.sh

[ Upstream commit d35661fcf95d8818c1f9acc818a1bad23dda4e1c ]

In-order to test both native-XDP (xdpdrv) and generic-XDP (xdpgeneric)
create two wrapper test scripts, that start the test_xdp_vlan.sh script
with these modes.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/bpf/Makefile                     | 3 ++-
 tools/testing/selftests/bpf/test_xdp_vlan.sh             | 5 ++++-
 .../testing/selftests/bpf/test_xdp_vlan_mode_generic.sh  | 9 +++++++++
 tools/testing/selftests/bpf/test_xdp_vlan_mode_native.sh | 9 +++++++++
 4 files changed, 24 insertions(+), 2 deletions(-)
 create mode 100755 tools/testing/selftests/bpf/test_xdp_vlan_mode_generic.sh
 create mode 100755 tools/testing/selftests/bpf/test_xdp_vlan_mode_native.sh

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index f1573a11d3e4..b9e88ccc289b 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -51,7 +51,8 @@ TEST_PROGS := test_kmod.sh \
 	test_lirc_mode2.sh \
 	test_skb_cgroup_id.sh \
 	test_flow_dissector.sh \
-	test_xdp_vlan.sh \
+	test_xdp_vlan_mode_generic.sh \
+	test_xdp_vlan_mode_native.sh \
 	test_lwt_ip_encap.sh \
 	test_tcp_check_syncookie.sh \
 	test_tc_tunnel.sh \
diff --git a/tools/testing/selftests/bpf/test_xdp_vlan.sh b/tools/testing/selftests/bpf/test_xdp_vlan.sh
index c8aed63b0ffe..7348661be815 100755
--- a/tools/testing/selftests/bpf/test_xdp_vlan.sh
+++ b/tools/testing/selftests/bpf/test_xdp_vlan.sh
@@ -2,7 +2,10 @@
 # SPDX-License-Identifier: GPL-2.0
 # Author: Jesper Dangaard Brouer <hawk@kernel.org>
 
-TESTNAME=xdp_vlan
+# Allow wrapper scripts to name test
+if [ -z "$TESTNAME" ]; then
+    TESTNAME=xdp_vlan
+fi
 
 # Default XDP mode
 XDP_MODE=xdpgeneric
diff --git a/tools/testing/selftests/bpf/test_xdp_vlan_mode_generic.sh b/tools/testing/selftests/bpf/test_xdp_vlan_mode_generic.sh
new file mode 100755
index 000000000000..c515326d6d59
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_xdp_vlan_mode_generic.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Exit on failure
+set -e
+
+# Wrapper script to test generic-XDP
+export TESTNAME=xdp_vlan_mode_generic
+./test_xdp_vlan.sh --mode=xdpgeneric
diff --git a/tools/testing/selftests/bpf/test_xdp_vlan_mode_native.sh b/tools/testing/selftests/bpf/test_xdp_vlan_mode_native.sh
new file mode 100755
index 000000000000..5cf7ce1f16c1
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_xdp_vlan_mode_native.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Exit on failure
+set -e
+
+# Wrapper script to test native-XDP
+export TESTNAME=xdp_vlan_mode_native
+./test_xdp_vlan.sh --mode=xdpdrv
-- 
2.20.1


From 5b3e100f490e84d91d103e638801d9bf10842d5c Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Thu, 1 Aug 2019 20:00:26 +0200
Subject: [PATCH 37/46] selftests/bpf: reduce time to execute test_xdp_vlan.sh

[ Upstream commit 13978d1e73d2fcfb6addcf3392707ad68fa88ccb ]

Given the increasing number of BPF selftests, it makes sense to
reduce the time to execute these tests.  The ping parameters are
adjusted to reduce the time from measures 9 sec to approx 2.8 sec.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/bpf/test_xdp_vlan.sh | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_xdp_vlan.sh b/tools/testing/selftests/bpf/test_xdp_vlan.sh
index 7348661be815..bb8b0da91686 100755
--- a/tools/testing/selftests/bpf/test_xdp_vlan.sh
+++ b/tools/testing/selftests/bpf/test_xdp_vlan.sh
@@ -188,7 +188,7 @@ ip netns exec ns2 ip link set lo up
 # At this point, the hosts cannot reach each-other,
 # because ns2 are using VLAN tags on the packets.
 
-ip netns exec ns2 sh -c 'ping -W 1 -c 1 100.64.41.1 || echo "Okay ping fails"'
+ip netns exec ns2 sh -c 'ping -W 1 -c 1 100.64.41.1 || echo "Success: First ping must fail"'
 
 
 # Now we can use the test_xdp_vlan.c program to pop/push these VLAN tags
@@ -210,8 +210,8 @@ ip netns exec ns1 tc filter add dev $DEVNS1 egress \
   prio 1 handle 1 bpf da obj $FILE sec tc_vlan_push
 
 # Now the namespaces can reach each-other, test with ping:
-ip netns exec ns2 ping -W 2 -c 3 $IPADDR1
-ip netns exec ns1 ping -W 2 -c 3 $IPADDR2
+ip netns exec ns2 ping -i 0.2 -W 2 -c 2 $IPADDR1
+ip netns exec ns1 ping -i 0.2 -W 2 -c 2 $IPADDR2
 
 # Second test: Replace xdp prog, that fully remove vlan header
 #
@@ -224,5 +224,5 @@ ip netns exec ns1 ip link set $DEVNS1 $XDP_MODE off
 ip netns exec ns1 ip link set $DEVNS1 $XDP_MODE object $FILE section $XDP_PROG
 
 # Now the namespaces should still be able reach each-other, test with ping:
-ip netns exec ns2 ping -W 2 -c 3 $IPADDR1
-ip netns exec ns1 ping -W 2 -c 3 $IPADDR2
+ip netns exec ns2 ping -i 0.2 -W 2 -c 2 $IPADDR1
+ip netns exec ns1 ping -i 0.2 -W 2 -c 2 $IPADDR2
-- 
2.20.1


From 20222081b0a53fdfc2a8443d9d4da517d1cae21e Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Thu, 1 Aug 2019 20:00:31 +0200
Subject: [PATCH 38/46] net: fix bpf_xdp_adjust_head regression for generic-XDP

[ Upstream commit 065af355470519bd184019a93ac579f22b036045 ]

When generic-XDP was moved to a later processing step by commit
458bf2f224f0 ("net: core: support XDP generic on stacked devices.")
a regression was introduced when using bpf_xdp_adjust_head.

The issue is that after this commit the skb->network_header is now
changed prior to calling generic XDP and not after. Thus, if the header
is changed by XDP (via bpf_xdp_adjust_head), then skb->network_header
also need to be updated again.  Fix by calling skb_reset_network_header().

Fixes: 458bf2f224f0 ("net: core: support XDP generic on stacked devices.")
Reported-by: Brandon Cazander <brandon.cazander@multapplied.net>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index d490c7b0ca2b..29fcff2c3d51 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4382,12 +4382,17 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 
 	act = bpf_prog_run_xdp(xdp_prog, xdp);
 
+	/* check if bpf_xdp_adjust_head was used */
 	off = xdp->data - orig_data;
-	if (off > 0)
-		__skb_pull(skb, off);
-	else if (off < 0)
-		__skb_push(skb, -off);
-	skb->mac_header += off;
+	if (off) {
+		if (off > 0)
+			__skb_pull(skb, off);
+		else if (off < 0)
+			__skb_push(skb, -off);
+
+		skb->mac_header += off;
+		skb_reset_network_header(skb);
+	}
 
 	/* check if bpf_xdp_adjust_tail was used. it can only "shrink"
 	 * pckt.
-- 
2.20.1


From e6ceb1ecba02800a9ab12f35a2c061d85248348b Mon Sep 17 00:00:00 2001
From: Dexuan Cui <decui@microsoft.com>
Date: Wed, 31 Jul 2019 01:25:45 +0000
Subject: [PATCH 39/46] hv_sock: Fix hang when a connection is closed

[ Upstream commit 8c7885e5690be9a27231ebebf82ef29fbf46c4e4 ]

There is a race condition for an established connection that is being closed
by the guest: the refcnt is 4 at the end of hvs_release() (Note: here the
'remove_sock' is false):

1 for the initial value;
1 for the sk being in the bound list;
1 for the sk being in the connected list;
1 for the delayed close_work.

After hvs_release() finishes, __vsock_release() -> sock_put(sk) *may*
decrease the refcnt to 3.

Concurrently, hvs_close_connection() runs in another thread:
  calls vsock_remove_sock() to decrease the refcnt by 2;
  call sock_put() to decrease the refcnt to 0, and free the sk;
  next, the "release_sock(sk)" may hang due to use-after-free.

In the above, after hvs_release() finishes, if hvs_close_connection() runs
faster than "__vsock_release() -> sock_put(sk)", then there is not any issue,
because at the beginning of hvs_close_connection(), the refcnt is still 4.

The issue can be resolved if an extra reference is taken when the
connection is established.

Fixes: a9eeb998c28d ("hv_sock: Add support for delayed close")
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Sunil Muthuswamy <sunilmut@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/vmw_vsock/hyperv_transport.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c
index 62dcdf082349..6c81a911fc02 100644
--- a/net/vmw_vsock/hyperv_transport.c
+++ b/net/vmw_vsock/hyperv_transport.c
@@ -311,6 +311,11 @@ static void hvs_close_connection(struct vmbus_channel *chan)
 	lock_sock(sk);
 	hvs_do_close_lock_held(vsock_sk(sk), true);
 	release_sock(sk);
+
+	/* Release the refcnt for the channel that's opened in
+	 * hvs_open_connection().
+	 */
+	sock_put(sk);
 }
 
 static void hvs_open_connection(struct vmbus_channel *chan)
@@ -378,6 +383,9 @@ static void hvs_open_connection(struct vmbus_channel *chan)
 	}
 
 	set_per_channel_state(chan, conn_from_host ? new : sk);
+
+	/* This reference will be dropped by hvs_close_connection(). */
+	sock_hold(conn_from_host ? new : sk);
 	vmbus_set_chn_rescind_callback(chan, hvs_close_connection);
 
 	/* Set the pending send size to max packet size to always get
-- 
2.20.1


From 5a8b31d34b845d0aa25b3ad2d85441fb5dfee7d4 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Wed, 31 Jul 2019 23:05:10 +0200
Subject: [PATCH 40/46] net: phy: fix race in genphy_update_link

[ Upstream commit aa6b1956158f1afc52761137620d4b3f8a058d24 ]

In phy_start_aneg() autoneg is started, and immediately after that
link and autoneg status are read. As reported in [0] it can happen that
at time of this read the PHY has reset the "aneg complete" bit but not
yet the "link up" bit, what can result in a false link-up detection.
To fix this don't report link as up if we're in aneg mode and PHY
doesn't signal "aneg complete".

[0] https://marc.info/?t=156413509900003&r=1&w=2

Fixes: 4950c2ba49cc ("net: phy: fix autoneg mismatch case in genphy_read_status")
Reported-by: liuyonglong <liuyonglong@huawei.com>
Tested-by: liuyonglong <liuyonglong@huawei.com>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index a3f8740c6163..ffa402732aea 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1730,6 +1730,12 @@ int genphy_update_link(struct phy_device *phydev)
 	phydev->link = status & BMSR_LSTATUS ? 1 : 0;
 	phydev->autoneg_complete = status & BMSR_ANEGCOMPLETE ? 1 : 0;
 
+	/* Consider the case that autoneg was started and "aneg complete"
+	 * bit has been reset, but "link up" bit not yet.
+	 */
+	if (phydev->autoneg == AUTONEG_ENABLE && !phydev->autoneg_complete)
+		phydev->link = 0;
+
 	return 0;
 }
 EXPORT_SYMBOL(genphy_update_link);
-- 
2.20.1


From 2ec5ec024f88afeca6899a4a973a6a92b9b3f616 Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.ibm.com>
Date: Fri, 2 Aug 2019 10:47:50 +0200
Subject: [PATCH 41/46] net/smc: avoid fallback in case of non-blocking connect

[ Upstream commit cd2063604ea6a8c2683b4eb9b5f4c4da74592d87 ]

FASTOPEN is not possible with SMC. sendmsg() with msg_flag MSG_FASTOPEN
triggers a fallback to TCP if the socket is in state SMC_INIT.
But if a nonblocking connect is already started, fallback to TCP
is no longer possible, even though the socket may still be in state
SMC_INIT.
And if a nonblocking connect is already started, a listen() call
does not make sense.

Reported-by: syzbot+bd8cc73d665590a1fcad@syzkaller.appspotmail.com
Fixes: 50717a37db032 ("net/smc: nonblocking connect rework")
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/af_smc.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 4b2f555a0db2..a3cc879d2589 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -253,7 +253,7 @@ static int smc_bind(struct socket *sock, struct sockaddr *uaddr,
 
 	/* Check if socket is already active */
 	rc = -EINVAL;
-	if (sk->sk_state != SMC_INIT)
+	if (sk->sk_state != SMC_INIT || smc->connect_nonblock)
 		goto out_rel;
 
 	smc->clcsock->sk->sk_reuse = sk->sk_reuse;
@@ -1399,7 +1399,8 @@ static int smc_listen(struct socket *sock, int backlog)
 	lock_sock(sk);
 
 	rc = -EINVAL;
-	if ((sk->sk_state != SMC_INIT) && (sk->sk_state != SMC_LISTEN))
+	if ((sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) ||
+	    smc->connect_nonblock)
 		goto out;
 
 	rc = 0;
@@ -1527,7 +1528,7 @@ static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 		goto out;
 
 	if (msg->msg_flags & MSG_FASTOPEN) {
-		if (sk->sk_state == SMC_INIT) {
+		if (sk->sk_state == SMC_INIT && !smc->connect_nonblock) {
 			smc_switch_to_fallback(smc);
 			smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP;
 		} else {
-- 
2.20.1


From e07c33bb774230ce2804d6ed55b2bf8600954584 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Sun, 28 Jul 2019 00:37:26 +0100
Subject: [PATCH 42/46] rocker: fix memory leaks of fib_work on two error
 return paths

[ Upstream commit 011f175428d46461f94a65dacb9a416529d08dda ]

Currently there are two error return paths that leak memory allocated
to fib_work. Fix this by kfree'ing fib_work before returning.

Addresses-Coverity: ("Resource leak")
Fixes: 19a9d136f198 ("ipv4: Flag fib_info with a fib_nh using IPv6 gateway")
Fixes: dbcc4fa718ee ("rocker: Fail attempts to use routes with nexthop objects")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/rocker/rocker_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index 3e5bc1fc3c46..c245a0f15066 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -2208,6 +2208,7 @@ static int rocker_router_fib_event(struct notifier_block *nb,
 
 			if (fen_info->fi->fib_nh_is_v6) {
 				NL_SET_ERR_MSG_MOD(info->extack, "IPv6 gateway with IPv4 route is not supported");
+				kfree(fib_work);
 				return notifier_from_errno(-EINVAL);
 			}
 		}
-- 
2.20.1


From 26a895d7f2e8aee08a6ac0c1d11b54d783430eaf Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Wed, 31 Jul 2019 09:33:15 +0300
Subject: [PATCH 43/46] mlxsw: spectrum_buffers: Further reduce pool size on
 Spectrum-2

[ Upstream commit 744ad9a357280d03d567538cee7e1e457dedd481 ]

In commit e891ce1dd2a5 ("mlxsw: spectrum_buffers: Reduce pool size on
Spectrum-2"), pool size was reduced to mitigate a problem in port buffer
usage of ports split four ways. It turns out that this work around does not
solve the issue, and a further reduction is required.

Thus reduce the size of pool 0 by another 2.7 MiB, and round down to the
whole number of cells.

Fixes: e891ce1dd2a5 ("mlxsw: spectrum_buffers: Reduce pool size on Spectrum-2")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
index 1537f70bc26d..888ba4300bcc 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
@@ -437,8 +437,8 @@ static const struct mlxsw_sp_sb_pr mlxsw_sp1_sb_prs[] = {
 			   MLXSW_SP1_SB_PR_CPU_SIZE, true, false),
 };
 
-#define MLXSW_SP2_SB_PR_INGRESS_SIZE	38128752
-#define MLXSW_SP2_SB_PR_EGRESS_SIZE	38128752
+#define MLXSW_SP2_SB_PR_INGRESS_SIZE	35297568
+#define MLXSW_SP2_SB_PR_EGRESS_SIZE	35297568
 #define MLXSW_SP2_SB_PR_CPU_SIZE	(256 * 1000)
 
 /* Order according to mlxsw_sp2_sb_pool_dess */
-- 
2.20.1


From 4ef7adff67791e5261fa7f5d18b8b42514afc81d Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@mellanox.com>
Date: Sun, 14 Jul 2019 11:33:07 +0300
Subject: [PATCH 44/46] net/mlx5: Add missing RDMA_RX capabilities

[ Upstream commit 987f6c69dd923069d443f6a37225f5b1630a30f2 ]

New flow table type RDMA_RX was added but the MLX5_CAP_FLOW_TABLE_TYPE
didn't handle this new flow table type.
This means that MLX5_CAP_FLOW_TABLE_TYPE returns an empty capability to
this flow table type.

Update both the macro and the maximum supported flow table type to
RDMA_RX.

Fixes: d83eb50e29de ("net/mlx5: Add support in RDMA RX steering")
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index a08c3d09a50f..2664a05eee00 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -68,7 +68,7 @@ enum fs_flow_table_type {
 	FS_FT_SNIFFER_RX	= 0X5,
 	FS_FT_SNIFFER_TX	= 0X6,
 	FS_FT_RDMA_RX		= 0X7,
-	FS_FT_MAX_TYPE = FS_FT_SNIFFER_TX,
+	FS_FT_MAX_TYPE = FS_FT_RDMA_RX,
 };
 
 enum fs_flow_table_op_mod {
@@ -274,7 +274,8 @@ void mlx5_cleanup_fs(struct mlx5_core_dev *dev);
 	(type == FS_FT_FDB) ? MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) :		\
 	(type == FS_FT_SNIFFER_RX) ? MLX5_CAP_FLOWTABLE_SNIFFER_RX(mdev, cap) :		\
 	(type == FS_FT_SNIFFER_TX) ? MLX5_CAP_FLOWTABLE_SNIFFER_TX(mdev, cap) :		\
-	(BUILD_BUG_ON_ZERO(FS_FT_SNIFFER_TX != FS_FT_MAX_TYPE))\
+	(type == FS_FT_RDMA_RX) ? MLX5_CAP_FLOWTABLE_RDMA_RX(mdev, cap) :		\
+	(BUILD_BUG_ON_ZERO(FS_FT_RDMA_RX != FS_FT_MAX_TYPE))\
 	)
 
 #endif
-- 
2.20.1


From c61ea287ebc1942a61ff747c3d6dca247271436e Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Sun, 16 Jun 2019 13:20:29 +0300
Subject: [PATCH 45/46] net/mlx5e: Fix matching of speed to PRM link modes

[ Upstream commit 4b95840a6ced0634082f6d962ba9aa0ce797f12f ]

Speed translation is performed based on legacy or extended PTYS
register. Translate speed with respect to:
1) Capability bit of extended PTYS table.
2) User request:
 a) When auto-negotiation is turned on, inspect advertisement whether it
 contains extended link modes.
 b) When auto-negotiation is turned off, speed > 100Gbps (maximal
 speed supported in legacy mode).
With both conditions fulfilled translation is done with extended PTYS
table otherwise use legacy PTYS table.
Without this patch 25/50/100 Gbps speed cannot be set, since try to
configure in extended mode but read from legacy mode.

Fixes: dd1b9e09c12b ("net/mlx5: ethtool, Allow legacy link-modes configuration via non-extended ptys")
Signed-off-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en/port.c | 27 +++++---
 .../net/ethernet/mellanox/mlx5/core/en/port.h |  6 +-
 .../ethernet/mellanox/mlx5/core/en_ethtool.c  | 67 +++++++++++++------
 3 files changed, 68 insertions(+), 32 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
index d5e5afbdca6d..f777994f3005 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
@@ -78,9 +78,10 @@ static const u32 mlx5e_ext_link_speed[MLX5E_EXT_LINK_MODES_NUMBER] = {
 };
 
 static void mlx5e_port_get_speed_arr(struct mlx5_core_dev *mdev,
-				     const u32 **arr, u32 *size)
+				     const u32 **arr, u32 *size,
+				     bool force_legacy)
 {
-	bool ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+	bool ext = force_legacy ? false : MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
 
 	*size = ext ? ARRAY_SIZE(mlx5e_ext_link_speed) :
 		      ARRAY_SIZE(mlx5e_link_speed);
@@ -152,7 +153,8 @@ int mlx5_port_set_eth_ptys(struct mlx5_core_dev *dev, bool an_disable,
 			    sizeof(out), MLX5_REG_PTYS, 0, 1);
 }
 
-u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper)
+u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper,
+			  bool force_legacy)
 {
 	unsigned long temp = eth_proto_oper;
 	const u32 *table;
@@ -160,7 +162,7 @@ u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper)
 	u32 max_size;
 	int i;
 
-	mlx5e_port_get_speed_arr(mdev, &table, &max_size);
+	mlx5e_port_get_speed_arr(mdev, &table, &max_size, force_legacy);
 	i = find_first_bit(&temp, max_size);
 	if (i < max_size)
 		speed = table[i];
@@ -170,6 +172,7 @@ u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper)
 int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
 {
 	struct mlx5e_port_eth_proto eproto;
+	bool force_legacy = false;
 	bool ext;
 	int err;
 
@@ -177,8 +180,13 @@ int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
 	err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto);
 	if (err)
 		goto out;
-
-	*speed = mlx5e_port_ptys2speed(mdev, eproto.oper);
+	if (ext && !eproto.admin) {
+		force_legacy = true;
+		err = mlx5_port_query_eth_proto(mdev, 1, false, &eproto);
+		if (err)
+			goto out;
+	}
+	*speed = mlx5e_port_ptys2speed(mdev, eproto.oper, force_legacy);
 	if (!(*speed))
 		err = -EINVAL;
 
@@ -201,7 +209,7 @@ int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
 	if (err)
 		return err;
 
-	mlx5e_port_get_speed_arr(mdev, &table, &max_size);
+	mlx5e_port_get_speed_arr(mdev, &table, &max_size, false);
 	for (i = 0; i < max_size; ++i)
 		if (eproto.cap & MLX5E_PROT_MASK(i))
 			max_speed = max(max_speed, table[i]);
@@ -210,14 +218,15 @@ int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
 	return 0;
 }
 
-u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed)
+u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed,
+			       bool force_legacy)
 {
 	u32 link_modes = 0;
 	const u32 *table;
 	u32 max_size;
 	int i;
 
-	mlx5e_port_get_speed_arr(mdev, &table, &max_size);
+	mlx5e_port_get_speed_arr(mdev, &table, &max_size, force_legacy);
 	for (i = 0; i < max_size; ++i) {
 		if (table[i] == speed)
 			link_modes |= MLX5E_PROT_MASK(i);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
index 70f536ec51c4..4a7f4497692b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
@@ -48,10 +48,12 @@ void mlx5_port_query_eth_autoneg(struct mlx5_core_dev *dev, u8 *an_status,
 				 u8 *an_disable_cap, u8 *an_disable_admin);
 int mlx5_port_set_eth_ptys(struct mlx5_core_dev *dev, bool an_disable,
 			   u32 proto_admin, bool ext);
-u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper);
+u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper,
+			  bool force_legacy);
 int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
 int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
-u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed);
+u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed,
+			       bool force_legacy);
 
 int mlx5e_port_query_pbmc(struct mlx5_core_dev *mdev, void *out);
 int mlx5e_port_set_pbmc(struct mlx5_core_dev *mdev, void *in);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index dd764e0471f2..f637d81f08bc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -764,7 +764,7 @@ static void ptys2ethtool_supported_advertised_port(struct ethtool_link_ksettings
 }
 
 static void get_speed_duplex(struct net_device *netdev,
-			     u32 eth_proto_oper,
+			     u32 eth_proto_oper, bool force_legacy,
 			     struct ethtool_link_ksettings *link_ksettings)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -774,7 +774,7 @@ static void get_speed_duplex(struct net_device *netdev,
 	if (!netif_carrier_ok(netdev))
 		goto out;
 
-	speed = mlx5e_port_ptys2speed(priv->mdev, eth_proto_oper);
+	speed = mlx5e_port_ptys2speed(priv->mdev, eth_proto_oper, force_legacy);
 	if (!speed) {
 		speed = SPEED_UNKNOWN;
 		goto out;
@@ -893,8 +893,8 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv,
 	/* Fields: eth_proto_admin and ext_eth_proto_admin  are
 	 * mutually exclusive. Hence try reading legacy advertising
 	 * when extended advertising is zero.
-	 * admin_ext indicates how eth_proto_admin should be
-	 * interpreted
+	 * admin_ext indicates which proto_admin (ext vs. legacy)
+	 * should be read and interpreted
 	 */
 	admin_ext = ext;
 	if (ext && !eth_proto_admin) {
@@ -903,7 +903,7 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv,
 		admin_ext = false;
 	}
 
-	eth_proto_oper   = MLX5_GET_ETH_PROTO(ptys_reg, out, ext,
+	eth_proto_oper   = MLX5_GET_ETH_PROTO(ptys_reg, out, admin_ext,
 					      eth_proto_oper);
 	eth_proto_lp	    = MLX5_GET(ptys_reg, out, eth_proto_lp_advertise);
 	an_disable_admin    = MLX5_GET(ptys_reg, out, an_disable_admin);
@@ -918,7 +918,8 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv,
 	get_supported(mdev, eth_proto_cap, link_ksettings);
 	get_advertising(eth_proto_admin, tx_pause, rx_pause, link_ksettings,
 			admin_ext);
-	get_speed_duplex(priv->netdev, eth_proto_oper, link_ksettings);
+	get_speed_duplex(priv->netdev, eth_proto_oper, !admin_ext,
+			 link_ksettings);
 
 	eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap;
 
@@ -995,45 +996,69 @@ static u32 mlx5e_ethtool2ptys_ext_adver_link(const unsigned long *link_modes)
 	return ptys_modes;
 }
 
+static bool ext_link_mode_requested(const unsigned long *adver)
+{
+#define MLX5E_MIN_PTYS_EXT_LINK_MODE_BIT ETHTOOL_LINK_MODE_50000baseKR_Full_BIT
+	int size = __ETHTOOL_LINK_MODE_MASK_NBITS - MLX5E_MIN_PTYS_EXT_LINK_MODE_BIT;
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(modes);
+
+	bitmap_set(modes, MLX5E_MIN_PTYS_EXT_LINK_MODE_BIT, size);
+	return bitmap_intersects(modes, adver, __ETHTOOL_LINK_MODE_MASK_NBITS);
+}
+
+static bool ext_speed_requested(u32 speed)
+{
+#define MLX5E_MAX_PTYS_LEGACY_SPEED 100000
+	return !!(speed > MLX5E_MAX_PTYS_LEGACY_SPEED);
+}
+
+static bool ext_requested(u8 autoneg, const unsigned long *adver, u32 speed)
+{
+	bool ext_link_mode = ext_link_mode_requested(adver);
+	bool ext_speed = ext_speed_requested(speed);
+
+	return  autoneg == AUTONEG_ENABLE ? ext_link_mode : ext_speed;
+}
+
 int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 				     const struct ethtool_link_ksettings *link_ksettings)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5e_port_eth_proto eproto;
+	const unsigned long *adver;
 	bool an_changes = false;
 	u8 an_disable_admin;
 	bool ext_supported;
-	bool ext_requested;
 	u8 an_disable_cap;
 	bool an_disable;
 	u32 link_modes;
 	u8 an_status;
+	u8 autoneg;
 	u32 speed;
+	bool ext;
 	int err;
 
 	u32 (*ethtool2ptys_adver_func)(const unsigned long *adver);
 
-#define MLX5E_PTYS_EXT ((1ULL << ETHTOOL_LINK_MODE_50000baseKR_Full_BIT) - 1)
+	adver = link_ksettings->link_modes.advertising;
+	autoneg = link_ksettings->base.autoneg;
+	speed = link_ksettings->base.speed;
 
-	ext_requested = !!(link_ksettings->link_modes.advertising[0] >
-			MLX5E_PTYS_EXT ||
-			link_ksettings->link_modes.advertising[1]);
+	ext = ext_requested(autoneg, adver, speed),
 	ext_supported = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
-	ext_requested &= ext_supported;
+	if (!ext_supported && ext)
+		return -EOPNOTSUPP;
 
-	speed = link_ksettings->base.speed;
-	ethtool2ptys_adver_func = ext_requested ?
-				  mlx5e_ethtool2ptys_ext_adver_link :
+	ethtool2ptys_adver_func = ext ? mlx5e_ethtool2ptys_ext_adver_link :
 				  mlx5e_ethtool2ptys_adver_link;
-	err = mlx5_port_query_eth_proto(mdev, 1, ext_requested, &eproto);
+	err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto);
 	if (err) {
 		netdev_err(priv->netdev, "%s: query port eth proto failed: %d\n",
 			   __func__, err);
 		goto out;
 	}
-	link_modes = link_ksettings->base.autoneg == AUTONEG_ENABLE ?
-		ethtool2ptys_adver_func(link_ksettings->link_modes.advertising) :
-		mlx5e_port_speed2linkmodes(mdev, speed);
+	link_modes = autoneg == AUTONEG_ENABLE ? ethtool2ptys_adver_func(adver) :
+		mlx5e_port_speed2linkmodes(mdev, speed, !ext);
 
 	link_modes = link_modes & eproto.cap;
 	if (!link_modes) {
@@ -1046,14 +1071,14 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 	mlx5_port_query_eth_autoneg(mdev, &an_status, &an_disable_cap,
 				    &an_disable_admin);
 
-	an_disable = link_ksettings->base.autoneg == AUTONEG_DISABLE;
+	an_disable = autoneg == AUTONEG_DISABLE;
 	an_changes = ((!an_disable && an_disable_admin) ||
 		      (an_disable && !an_disable_admin));
 
 	if (!an_changes && link_modes == eproto.admin)
 		goto out;
 
-	mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext_requested);
+	mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext);
 	mlx5_toggle_port_link(mdev);
 
 out:
-- 
2.20.1


From fa2d7ac79a82a24c57fcc32a0de83eb666bd0cc4 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 30 Jul 2019 21:25:20 +0200
Subject: [PATCH 46/46] compat_ioctl: pppoe: fix PPPOEIOCSFWD handling

[ Upstream commit 055d88242a6046a1ceac3167290f054c72571cd9 ]

Support for handling the PPPOEIOCSFWD ioctl in compat mode was added in
linux-2.5.69 along with hundreds of other commands, but was always broken
sincen only the structure is compatible, but the command number is not,
due to the size being sizeof(size_t), or at first sizeof(sizeof((struct
sockaddr_pppox)), which is different on 64-bit architectures.

Guillaume Nault adds:

  And the implementation was broken until 2016 (see 29e73269aa4d ("pppoe:
  fix reference counting in PPPoE proxy")), and nobody ever noticed. I
  should probably have removed this ioctl entirely instead of fixing it.
  Clearly, it has never been used.

Fix it by adding a compat_ioctl handler for all pppoe variants that
translates the command number and then calls the regular ioctl function.

All other ioctl commands handled by pppoe are compatible between 32-bit
and 64-bit, and require compat_ptr() conversion.

This should apply to all stable kernels.

Acked-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pppoe.c  |  3 +++
 drivers/net/ppp/pppox.c  | 13 +++++++++++++
 drivers/net/ppp/pptp.c   |  3 +++
 fs/compat_ioctl.c        |  3 ---
 include/linux/if_pppox.h |  3 +++
 net/l2tp/l2tp_ppp.c      |  3 +++
 6 files changed, 25 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 1d902ecb4aa8..a44dd3c8af63 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -1115,6 +1115,9 @@ static const struct proto_ops pppoe_ops = {
 	.recvmsg	= pppoe_recvmsg,
 	.mmap		= sock_no_mmap,
 	.ioctl		= pppox_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= pppox_compat_ioctl,
+#endif
 };
 
 static const struct pppox_proto pppoe_proto = {
diff --git a/drivers/net/ppp/pppox.c b/drivers/net/ppp/pppox.c
index 5ef422a43d70..08364f10a43f 100644
--- a/drivers/net/ppp/pppox.c
+++ b/drivers/net/ppp/pppox.c
@@ -17,6 +17,7 @@
 #include <linux/string.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
+#include <linux/compat.h>
 #include <linux/errno.h>
 #include <linux/netdevice.h>
 #include <linux/net.h>
@@ -98,6 +99,18 @@ int pppox_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 
 EXPORT_SYMBOL(pppox_ioctl);
 
+#ifdef CONFIG_COMPAT
+int pppox_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
+{
+	if (cmd == PPPOEIOCSFWD32)
+		cmd = PPPOEIOCSFWD;
+
+	return pppox_ioctl(sock, cmd, (unsigned long)compat_ptr(arg));
+}
+
+EXPORT_SYMBOL(pppox_compat_ioctl);
+#endif
+
 static int pppox_create(struct net *net, struct socket *sock, int protocol,
 			int kern)
 {
diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index a8e52c8e4128..734de7de03f7 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -623,6 +623,9 @@ static const struct proto_ops pptp_ops = {
 	.recvmsg    = sock_no_recvmsg,
 	.mmap       = sock_no_mmap,
 	.ioctl      = pppox_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = pppox_compat_ioctl,
+#endif
 };
 
 static const struct pppox_proto pppox_pptp_proto = {
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index 6e30949d9f77..a7ec2d3dff92 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -638,9 +638,6 @@ COMPATIBLE_IOCTL(PPPIOCDISCONN)
 COMPATIBLE_IOCTL(PPPIOCATTCHAN)
 COMPATIBLE_IOCTL(PPPIOCGCHAN)
 COMPATIBLE_IOCTL(PPPIOCGL2TPSTATS)
-/* PPPOX */
-COMPATIBLE_IOCTL(PPPOEIOCSFWD)
-COMPATIBLE_IOCTL(PPPOEIOCDFWD)
 /* Big A */
 /* sparc only */
 /* Big Q for sound/OSS */
diff --git a/include/linux/if_pppox.h b/include/linux/if_pppox.h
index 8b728750a625..69e813bcb947 100644
--- a/include/linux/if_pppox.h
+++ b/include/linux/if_pppox.h
@@ -80,6 +80,9 @@ extern int register_pppox_proto(int proto_num, const struct pppox_proto *pp);
 extern void unregister_pppox_proto(int proto_num);
 extern void pppox_unbind_sock(struct sock *sk);/* delete ppp-channel binding */
 extern int pppox_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
+extern int pppox_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
+
+#define PPPOEIOCSFWD32    _IOW(0xB1 ,0, compat_size_t)
 
 /* PPPoX socket states */
 enum {
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 1d0e5904dedf..c54cb59593ef 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1681,6 +1681,9 @@ static const struct proto_ops pppol2tp_ops = {
 	.recvmsg	= pppol2tp_recvmsg,
 	.mmap		= sock_no_mmap,
 	.ioctl		= pppox_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = pppox_compat_ioctl,
+#endif
 };
 
 static const struct pppox_proto pppol2tp_proto = {
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Wed, Aug 07, 2019 at 04:27:57PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.19 and v5.2
> -stable, respectively.
> 
> Thank you.


All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 106 bytes --]


Please queue up the following networking bug fixes for v4.19 and
v5.2 -stable, respectively.

Thank you.

[-- Attachment #2: net_419.mbox --]
[-- Type: Application/Octet-Stream, Size: 32708 bytes --]

From cd069b53400b33791af96bc677cbad1bd3ef2322 Mon Sep 17 00:00:00 2001
From: Manish Chopra <manishc@marvell.com>
Date: Sun, 18 Aug 2019 07:25:48 -0700
Subject: [PATCH 01/12] bnx2x: Fix VF's VLAN reconfiguration in reload.

[ Upstream commit 4a4d2d372fb9b9229327e2ed01d5d9572eddf4de ]

Commit 04f05230c5c13 ("bnx2x: Remove configured vlans as
part of unload sequence."), introduced a regression in driver
that as a part of VF's reload flow, VLANs created on the VF
doesn't get re-configured in hardware as vlan metadata/info
was not getting cleared for the VFs which causes vlan PING to stop.

This patch clears the vlan metadata/info so that VLANs gets
re-configured back in the hardware in VF's reload flow and
PING/traffic continues for VLANs created over the VFs.

Fixes: 04f05230c5c13 ("bnx2x: Remove configured vlans as part of unload sequence.")
Signed-off-by: Manish Chopra <manishc@marvell.com>
Signed-off-by: Sudarsana Kalluru <skalluru@marvell.com>
Signed-off-by: Shahed Shaikh <shshaikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c |  7 ++++---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h |  2 ++
 .../net/ethernet/broadcom/bnx2x/bnx2x_main.c    | 17 ++++++++++++-----
 3 files changed, 18 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 33baa17fa9d5..cf01e73d1bcc 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -3058,12 +3058,13 @@ int bnx2x_nic_unload(struct bnx2x *bp, int unload_mode, bool keep_link)
 	/* if VF indicate to PF this function is going down (PF will delete sp
 	 * elements and clear initializations
 	 */
-	if (IS_VF(bp))
+	if (IS_VF(bp)) {
+		bnx2x_clear_vlan_info(bp);
 		bnx2x_vfpf_close_vf(bp);
-	else if (unload_mode != UNLOAD_RECOVERY)
+	} else if (unload_mode != UNLOAD_RECOVERY) {
 		/* if this is a normal/close unload need to clean up chip*/
 		bnx2x_chip_cleanup(bp, unload_mode, keep_link);
-	else {
+	} else {
 		/* Send the UNLOAD_REQUEST to the MCP */
 		bnx2x_send_unload_req(bp, unload_mode);
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index 0e508e5defce..ee5159ef837e 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -425,6 +425,8 @@ void bnx2x_set_reset_global(struct bnx2x *bp);
 void bnx2x_disable_close_the_gate(struct bnx2x *bp);
 int bnx2x_init_hw_func_cnic(struct bnx2x *bp);
 
+void bnx2x_clear_vlan_info(struct bnx2x *bp);
+
 /**
  * bnx2x_sp_event - handle ramrods completion.
  *
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 2c9af0f420e5..68c62e32e882 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -8488,11 +8488,21 @@ int bnx2x_set_vlan_one(struct bnx2x *bp, u16 vlan,
 	return rc;
 }
 
+void bnx2x_clear_vlan_info(struct bnx2x *bp)
+{
+	struct bnx2x_vlan_entry *vlan;
+
+	/* Mark that hw forgot all entries */
+	list_for_each_entry(vlan, &bp->vlan_reg, link)
+		vlan->hw = false;
+
+	bp->vlan_cnt = 0;
+}
+
 static int bnx2x_del_all_vlans(struct bnx2x *bp)
 {
 	struct bnx2x_vlan_mac_obj *vlan_obj = &bp->sp_objs[0].vlan_obj;
 	unsigned long ramrod_flags = 0, vlan_flags = 0;
-	struct bnx2x_vlan_entry *vlan;
 	int rc;
 
 	__set_bit(RAMROD_COMP_WAIT, &ramrod_flags);
@@ -8501,10 +8511,7 @@ static int bnx2x_del_all_vlans(struct bnx2x *bp)
 	if (rc)
 		return rc;
 
-	/* Mark that hw forgot all entries */
-	list_for_each_entry(vlan, &bp->vlan_reg, link)
-		vlan->hw = false;
-	bp->vlan_cnt = 0;
+	bnx2x_clear_vlan_info(bp);
 
 	return 0;
 }
-- 
2.20.1


From 2c2f33d0c60e72626366690a6d11e9be0ec4dcaa Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 7 Aug 2019 10:19:59 +0800
Subject: [PATCH 02/12] bonding: Add vlan tx offload to hw_enc_features

[ Upstream commit d595b03de2cb0bdf9bcdf35ff27840cc3a37158f ]

As commit 30d8177e8ac7 ("bonding: Always enable vlan tx offload")
said, we should always enable bonding's vlan tx offload, pass the
vlan packets to the slave devices with vlan tci, let them to handle
vlan implementation.

Now if encapsulation protocols like VXLAN is used, skb->encapsulation
may be set, then the packet is passed to vlan device which based on
bonding device. However in netif_skb_features(), the check of
hw_enc_features:

	 if (skb->encapsulation)
                 features &= dev->hw_enc_features;

clears NETIF_F_HW_VLAN_CTAG_TX/NETIF_F_HW_VLAN_STAG_TX. This results
in same issue in commit 30d8177e8ac7 like this:

vlan_dev_hard_start_xmit
  -->dev_queue_xmit
    -->validate_xmit_skb
      -->netif_skb_features //NETIF_F_HW_VLAN_CTAG_TX is cleared
      -->validate_xmit_vlan
        -->__vlan_hwaccel_push_inside //skb->tci is cleared
...
 --> bond_start_xmit
   --> bond_xmit_hash //BOND_XMIT_POLICY_ENCAP34
     --> __skb_flow_dissect // nhoff point to IP header
        -->  case htons(ETH_P_8021Q)
             // skb_vlan_tag_present is false, so
             vlan = __skb_header_pointer(skb, nhoff, sizeof(_vlan),
             //vlan point to ip header wrongly

Fixes: b2a103e6d0af ("bonding: convert to ndo_fix_features")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index be0b785becd0..8f14f85b8e95 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1102,6 +1102,8 @@ static void bond_compute_features(struct bonding *bond)
 done:
 	bond_dev->vlan_features = vlan_features;
 	bond_dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL |
+				    NETIF_F_HW_VLAN_CTAG_TX |
+				    NETIF_F_HW_VLAN_STAG_TX |
 				    NETIF_F_GSO_UDP_L4;
 	bond_dev->gso_max_segs = gso_max_segs;
 	netif_set_gso_max_size(bond_dev, gso_max_size);
-- 
2.20.1


From c1f45b318020537df82b32c9d8a3996bac7047dd Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wens@csie.org>
Date: Sun, 11 Aug 2019 22:18:25 +0800
Subject: [PATCH 03/12] net: dsa: Check existence of .port_mdb_add callback
 before calling it

[ Upstream commit 58799865be84e2a895dab72de0e1b996ed943f22 ]

The dsa framework has optional .port_mdb_{prepare,add,del} callback fields
for drivers to handle multicast database entries. When adding an entry, the
framework goes through a prepare phase, then a commit phase. Drivers not
providing these callbacks should be detected in the prepare phase.

DSA core may still bypass the bridge layer and call the dsa_port_mdb_add
function directly with no prepare phase or no switchdev trans object,
and the framework ends up calling an undefined .port_mdb_add callback.
This results in a NULL pointer dereference, as shown in the log below.

The other functions seem to be properly guarded. Do the same for
.port_mdb_add in dsa_switch_mdb_add_bitmap() as well.

    8<--- cut here ---
    Unable to handle kernel NULL pointer dereference at virtual address 00000000
    pgd = (ptrval)
    [00000000] *pgd=00000000
    Internal error: Oops: 80000005 [#1] SMP ARM
    Modules linked in: rtl8xxxu rtl8192cu rtl_usb rtl8192c_common rtlwifi mac80211 cfg80211
    CPU: 1 PID: 134 Comm: kworker/1:2 Not tainted 5.3.0-rc1-00247-gd3519030752a #1
    Hardware name: Allwinner sun7i (A20) Family
    Workqueue: events switchdev_deferred_process_work
    PC is at 0x0
    LR is at dsa_switch_event+0x570/0x620
    pc : [<00000000>]    lr : [<c08533ec>]    psr: 80070013
    sp : ee871db8  ip : 00000000  fp : ee98d0a4
    r10: 0000000c  r9 : 00000008  r8 : ee89f710
    r7 : ee98d040  r6 : ee98d088  r5 : c0f04c48  r4 : ee98d04c
    r3 : 00000000  r2 : ee89f710  r1 : 00000008  r0 : ee98d040
    Flags: Nzcv  IRQs on  FIQs on  Mode SVC_32  ISA ARM  Segment none
    Control: 10c5387d  Table: 6deb406a  DAC: 00000051
    Process kworker/1:2 (pid: 134, stack limit = 0x(ptrval))
    Stack: (0xee871db8 to 0xee872000)
    1da0:                                                       ee871e14 103ace2d
    1dc0: 00000000 ffffffff 00000000 ee871e14 00000005 00000000 c08524a0 00000000
    1de0: ffffe000 c014bdfc c0f04c48 ee871e98 c0f04c48 ee9e5000 c0851120 c014bef0
    1e00: 00000000 b643aea2 ee9b4068 c08509a8 ee2bf940 ee89f710 ee871ecb 00000000
    1e20: 00000008 103ace2d 00000000 c087e248 ee29c868 103ace2d 00000001 ffffffff
    1e40: 00000000 ee871e98 00000006 00000000 c0fb2a50 c087e2d0 ffffffff c08523c4
    1e60: ffffffff c014bdfc 00000006 c0fad2d0 ee871e98 ee89f710 00000000 c014c500
    1e80: 00000000 ee89f3c0 c0f04c48 00000000 ee9e5000 c087dfb4 ee9e5000 00000000
    1ea0: ee89f710 ee871ecb 00000001 103ace2d 00000000 c0f04c48 00000000 c087e0a8
    1ec0: 00000000 efd9a3e0 0089f3c0 103ace2d ee89f700 ee89f710 ee9e5000 00000122
    1ee0: 00000100 c087e130 ee89f700 c0fad2c8 c1003ef0 c087de4c 2e928000 c0fad2ec
    1f00: c0fad2ec ee839580 ef7a62c0 ef7a9400 00000000 c087def8 c0fad2ec c01447dc
    1f20: ef315640 ef7a62c0 00000008 ee839580 ee839594 ef7a62c0 00000008 c0f03d00
    1f40: ef7a62d8 ef7a62c0 ffffe000 c0145b84 ffffe000 c0fb2420 c0bfaa8c 00000000
    1f60: ffffe000 ee84b600 ee84b5c0 00000000 ee870000 ee839580 c0145b40 ef0e5ea4
    1f80: ee84b61c c014a6f8 00000001 ee84b5c0 c014a5b0 00000000 00000000 00000000
    1fa0: 00000000 00000000 00000000 c01010e8 00000000 00000000 00000000 00000000
    1fc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
    1fe0: 00000000 00000000 00000000 00000000 00000013 00000000 00000000 00000000
    [<c08533ec>] (dsa_switch_event) from [<c014bdfc>] (notifier_call_chain+0x48/0x84)
    [<c014bdfc>] (notifier_call_chain) from [<c014bef0>] (raw_notifier_call_chain+0x18/0x20)
    [<c014bef0>] (raw_notifier_call_chain) from [<c08509a8>] (dsa_port_mdb_add+0x48/0x74)
    [<c08509a8>] (dsa_port_mdb_add) from [<c087e248>] (__switchdev_handle_port_obj_add+0x54/0xd4)
    [<c087e248>] (__switchdev_handle_port_obj_add) from [<c087e2d0>] (switchdev_handle_port_obj_add+0x8/0x14)
    [<c087e2d0>] (switchdev_handle_port_obj_add) from [<c08523c4>] (dsa_slave_switchdev_blocking_event+0x94/0xa4)
    [<c08523c4>] (dsa_slave_switchdev_blocking_event) from [<c014bdfc>] (notifier_call_chain+0x48/0x84)
    [<c014bdfc>] (notifier_call_chain) from [<c014c500>] (blocking_notifier_call_chain+0x50/0x68)
    [<c014c500>] (blocking_notifier_call_chain) from [<c087dfb4>] (switchdev_port_obj_notify+0x44/0xa8)
    [<c087dfb4>] (switchdev_port_obj_notify) from [<c087e0a8>] (switchdev_port_obj_add_now+0x90/0x104)
    [<c087e0a8>] (switchdev_port_obj_add_now) from [<c087e130>] (switchdev_port_obj_add_deferred+0x14/0x5c)
    [<c087e130>] (switchdev_port_obj_add_deferred) from [<c087de4c>] (switchdev_deferred_process+0x64/0x104)
    [<c087de4c>] (switchdev_deferred_process) from [<c087def8>] (switchdev_deferred_process_work+0xc/0x14)
    [<c087def8>] (switchdev_deferred_process_work) from [<c01447dc>] (process_one_work+0x218/0x50c)
    [<c01447dc>] (process_one_work) from [<c0145b84>] (worker_thread+0x44/0x5bc)
    [<c0145b84>] (worker_thread) from [<c014a6f8>] (kthread+0x148/0x150)
    [<c014a6f8>] (kthread) from [<c01010e8>] (ret_from_fork+0x14/0x2c)
    Exception stack(0xee871fb0 to 0xee871ff8)
    1fa0:                                     00000000 00000000 00000000 00000000
    1fc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
    1fe0: 00000000 00000000 00000000 00000000 00000013 00000000
    Code: bad PC value
    ---[ end trace 1292c61abd17b130 ]---

    [<c08533ec>] (dsa_switch_event) from [<c014bdfc>] (notifier_call_chain+0x48/0x84)
    corresponds to

	$ arm-linux-gnueabihf-addr2line -C -i -e vmlinux c08533ec

	linux/net/dsa/switch.c:156
	linux/net/dsa/switch.c:178
	linux/net/dsa/switch.c:328

Fixes: e6db98db8a95 ("net: dsa: add switch mdb bitmap functions")
Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Reviewed-by: Vivien Didelot <vivien.didelot@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/switch.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/dsa/switch.c b/net/dsa/switch.c
index 142b294d3446..b0b9413fa5bf 100644
--- a/net/dsa/switch.c
+++ b/net/dsa/switch.c
@@ -127,6 +127,9 @@ static void dsa_switch_mdb_add_bitmap(struct dsa_switch *ds,
 {
 	int port;
 
+	if (!ds->ops->port_mdb_add)
+		return;
+
 	for_each_set_bit(port, bitmap, ds->num_ports)
 		ds->ops->port_mdb_add(ds, port, mdb);
 }
-- 
2.20.1


From f5ba2bae61bc4478b5a4bc0aa5930958f9b23986 Mon Sep 17 00:00:00 2001
From: Wenwen Wang <wenwen@cs.uga.edu>
Date: Mon, 12 Aug 2019 14:11:35 -0500
Subject: [PATCH 04/12] net/mlx4_en: fix a memory leak bug

[ Upstream commit 48ec7014c56e5eb2fbf6f479896143622d834f3b ]

In mlx4_en_config_rss_steer(), 'rss_map->indir_qp' is allocated through
kzalloc(). After that, mlx4_qp_alloc() is invoked to configure RSS
indirection. However, if mlx4_qp_alloc() fails, the allocated
'rss_map->indir_qp' is not deallocated, leading to a memory leak bug.

To fix the above issue, add the 'qp_alloc_err' label to free
'rss_map->indir_qp'.

Fixes: 4931c6ef04b4 ("net/mlx4_en: Optimized single ring steering")
Signed-off-by: Wenwen Wang <wenwen@cs.uga.edu>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/ethernet/mellanox/mlx4/en_rx.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index f5cd9539980f..45d9a5f8fa1b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -1190,7 +1190,7 @@ int mlx4_en_config_rss_steer(struct mlx4_en_priv *priv)
 	err = mlx4_qp_alloc(mdev->dev, priv->base_qpn, rss_map->indir_qp);
 	if (err) {
 		en_err(priv, "Failed to allocate RSS indirection QP\n");
-		goto rss_err;
+		goto qp_alloc_err;
 	}
 
 	rss_map->indir_qp->event = mlx4_en_sqp_event;
@@ -1244,6 +1244,7 @@ int mlx4_en_config_rss_steer(struct mlx4_en_priv *priv)
 		       MLX4_QP_STATE_RST, NULL, 0, 0, rss_map->indir_qp);
 	mlx4_qp_remove(mdev->dev, rss_map->indir_qp);
 	mlx4_qp_free(mdev->dev, rss_map->indir_qp);
+qp_alloc_err:
 	kfree(rss_map->indir_qp);
 	rss_map->indir_qp = NULL;
 rss_err:
-- 
2.20.1


From cba1f24f6c84ca1043737d4ca81438c53af1ef1f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 14 Aug 2019 02:11:57 -0700
Subject: [PATCH 05/12] net/packet: fix race in tpacket_snd()

[ Upstream commit 32d3182cd2cd29b2e7e04df7b0db350fbe11289f ]

packet_sendmsg() checks tx_ring.pg_vec to decide
if it must call tpacket_snd().

Problem is that the check is lockless, meaning another thread
can issue a concurrent setsockopt(PACKET_TX_RING ) to flip
tx_ring.pg_vec back to NULL.

Given that tpacket_snd() grabs pg_vec_lock mutex, we can
perform the check again to solve the race.

syzbot reported :

kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] PREEMPT SMP KASAN
CPU: 1 PID: 11429 Comm: syz-executor394 Not tainted 5.3.0-rc4+ #101
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:packet_lookup_frame+0x8d/0x270 net/packet/af_packet.c:474
Code: c1 ee 03 f7 73 0c 80 3c 0e 00 0f 85 cb 01 00 00 48 8b 0b 89 c0 4c 8d 24 c1 48 b8 00 00 00 00 00 fc ff df 4c 89 e1 48 c1 e9 03 <80> 3c 01 00 0f 85 94 01 00 00 48 8d 7b 10 4d 8b 3c 24 48 b8 00 00
RSP: 0018:ffff88809f82f7b8 EFLAGS: 00010246
RAX: dffffc0000000000 RBX: ffff8880a45c7030 RCX: 0000000000000000
RDX: 0000000000000000 RSI: 1ffff110148b8e06 RDI: ffff8880a45c703c
RBP: ffff88809f82f7e8 R08: ffff888087aea200 R09: fffffbfff134ae50
R10: fffffbfff134ae4f R11: ffffffff89a5727f R12: 0000000000000000
R13: 0000000000000001 R14: ffff8880a45c6ac0 R15: 0000000000000000
FS:  00007fa04716f700(0000) GS:ffff8880ae900000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007fa04716edb8 CR3: 0000000091eb4000 CR4: 00000000001406e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 packet_current_frame net/packet/af_packet.c:487 [inline]
 tpacket_snd net/packet/af_packet.c:2667 [inline]
 packet_sendmsg+0x590/0x6250 net/packet/af_packet.c:2975
 sock_sendmsg_nosec net/socket.c:637 [inline]
 sock_sendmsg+0xd7/0x130 net/socket.c:657
 ___sys_sendmsg+0x3e2/0x920 net/socket.c:2311
 __sys_sendmmsg+0x1bf/0x4d0 net/socket.c:2413
 __do_sys_sendmmsg net/socket.c:2442 [inline]
 __se_sys_sendmmsg net/socket.c:2439 [inline]
 __x64_sys_sendmmsg+0x9d/0x100 net/socket.c:2439
 do_syscall_64+0xfd/0x6a0 arch/x86/entry/common.c:296
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Fixes: 69e3c75f4d54 ("net: TX_RING and packet mmap")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 93b5a4200585..7204e7bbebb0 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2616,6 +2616,13 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 
 	mutex_lock(&po->pg_vec_lock);
 
+	/* packet_sendmsg() check on tx_ring.pg_vec was lockless,
+	 * we need to confirm it under protection of pg_vec_lock.
+	 */
+	if (unlikely(!po->tx_ring.pg_vec)) {
+		err = -EBUSY;
+		goto out;
+	}
 	if (likely(saddr == NULL)) {
 		dev	= packet_cached_dev_get(po);
 		proto	= po->num;
-- 
2.20.1


From 1b2254a0600e9d3898245f888c8e739ad2521e4a Mon Sep 17 00:00:00 2001
From: zhengbin <zhengbin13@huawei.com>
Date: Tue, 13 Aug 2019 22:05:50 +0800
Subject: [PATCH 06/12] sctp: fix memleak in sctp_send_reset_streams

[ Upstream commit 6d5afe20397b478192ed8c38ec0ee10fa3aec649 ]

If the stream outq is not empty, need to kfree nstr_list.

Fixes: d570a59c5b5f ("sctp: only allow the out stream reset when the stream outq is empty")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: zhengbin <zhengbin13@huawei.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/sctp/stream.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index 0da57938a6c5..87061a4bb44b 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -416,6 +416,7 @@ int sctp_send_reset_streams(struct sctp_association *asoc,
 		nstr_list[i] = htons(str_list[i]);
 
 	if (out && !sctp_stream_outq_is_empty(stream, str_nums, nstr_list)) {
+		kfree(nstr_list);
 		retval = -EAGAIN;
 		goto out;
 	}
-- 
2.20.1


From 81e33dd7da6d3736beecfb462630f92197141ced Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 12 Aug 2019 20:49:12 +0800
Subject: [PATCH 07/12] sctp: fix the transport error_count check

[ Upstream commit a1794de8b92ea6bc2037f445b296814ac826693e ]

As the annotation says in sctp_do_8_2_transport_strike():

  "If the transport error count is greater than the pf_retrans
   threshold, and less than pathmaxrtx ..."

It should be transport->error_count checked with pathmaxrxt,
instead of asoc->pf_retrans.

Fixes: 5aa93bcf66f4 ("sctp: Implement quick failover draft from tsvwg")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/sctp/sm_sideeffect.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index 3131b4154c74..28adac31f0ff 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -561,7 +561,7 @@ static void sctp_do_8_2_transport_strike(struct sctp_cmd_seq *commands,
 	 */
 	if (net->sctp.pf_enable &&
 	   (transport->state == SCTP_ACTIVE) &&
-	   (asoc->pf_retrans < transport->pathmaxrxt) &&
+	   (transport->error_count < transport->pathmaxrxt) &&
 	   (transport->error_count > asoc->pf_retrans)) {
 
 		sctp_assoc_control_transport(asoc, transport,
-- 
2.20.1


From eda2e4301663d9395072984a75b90f1f7060579c Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Thu, 8 Aug 2019 14:22:47 +0800
Subject: [PATCH 08/12] team: Add vlan tx offload to hw_enc_features

[ Upstream commit 227f2f030e28d8783c3d10ce70ff4ba79cad653f ]

We should also enable team's vlan tx offload in hw_enc_features,
pass the vlan packets to the slave devices with vlan tci, let the
slave handle vlan tunneling offload implementation.

Fixes: 3268e5cb494d ("team: Advertise tunneling offload features")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index dc30f11f4766..3feb49badda9 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1011,6 +1011,8 @@ static void __team_compute_features(struct team *team)
 
 	team->dev->vlan_features = vlan_features;
 	team->dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL |
+				     NETIF_F_HW_VLAN_CTAG_TX |
+				     NETIF_F_HW_VLAN_STAG_TX |
 				     NETIF_F_GSO_UDP_L4;
 	team->dev->hard_header_len = max_hard_header_len;
 
-- 
2.20.1


From e2b04fc3f6c6124d7836b55f72e13d3410878575 Mon Sep 17 00:00:00 2001
From: Chris Packham <chris.packham@alliedtelesis.co.nz>
Date: Mon, 12 Aug 2019 08:18:25 +1200
Subject: [PATCH 09/12] tipc: initialise addr_trail_end when setting node
 addresses

[ Upstream commit 8874ecae2977e5a2d4f0ba301364435b81c05938 ]

We set the field 'addr_trial_end' to 'jiffies', instead of the current
value 0, at the moment the node address is initialized. This guarantees
we don't inadvertently enter an address trial period when the node
address is explicitly set by the user.

Signed-off-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/addr.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/tipc/addr.c b/net/tipc/addr.c
index b88d48d00913..0f1eaed1bd1b 100644
--- a/net/tipc/addr.c
+++ b/net/tipc/addr.c
@@ -75,6 +75,7 @@ void tipc_set_node_addr(struct net *net, u32 addr)
 		tipc_set_node_id(net, node_id);
 	}
 	tn->trial_addr = addr;
+	tn->addr_trial_end = jiffies;
 	pr_info("32-bit node address hash set to %x\n", addr);
 }
 
-- 
2.20.1


From e6d1574bf9051c04d3f963059bcc0105ed5e6d6e Mon Sep 17 00:00:00 2001
From: Ross Lagerwall <ross.lagerwall@citrix.com>
Date: Mon, 5 Aug 2019 16:34:34 +0100
Subject: [PATCH 10/12] xen/netback: Reset nr_frags before freeing skb

[ Upstream commit 3a0233ddec554b886298de2428edb5c50a20e694 ]

At this point nr_frags has been incremented but the frag does not yet
have a page assigned so freeing the skb results in a crash. Reset
nr_frags before freeing the skb to prevent this.

Signed-off-by: Ross Lagerwall <ross.lagerwall@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netback/netback.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index d5081ffdc8f0..1c849106b793 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -925,6 +925,7 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue,
 			skb_shinfo(skb)->nr_frags = MAX_SKB_FRAGS;
 			nskb = xenvif_alloc_skb(0);
 			if (unlikely(nskb == NULL)) {
+				skb_shinfo(skb)->nr_frags = 0;
 				kfree_skb(skb);
 				xenvif_tx_err(queue, &txreq, extra_count, idx);
 				if (net_ratelimit())
@@ -940,6 +941,7 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue,
 
 			if (xenvif_set_skb_gso(queue->vif, skb, gso)) {
 				/* Failure in xenvif_set_skb_gso is fatal. */
+				skb_shinfo(skb)->nr_frags = 0;
 				kfree_skb(skb);
 				kfree_skb(nskb);
 				break;
-- 
2.20.1


From 0d13beeeb3717108c208c1816d7140e053d990a5 Mon Sep 17 00:00:00 2001
From: Huy Nguyen <huyn@mellanox.com>
Date: Thu, 1 Aug 2019 11:10:19 -0500
Subject: [PATCH 11/12] net/mlx5e: Only support tx/rx pause setting for port
 owner

[ Upstream commit 466df6eb4a9e813b3cfc674363316450c57a89c5 ]

Only support changing tx/rx pause frame setting if the net device
is the vport group manager.

Fixes: 3c2d18ef22df ("net/mlx5e: Support ethtool get/set_pauseparam")
Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 792bb8bc0cd3..2b9350f4c752 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1083,6 +1083,9 @@ static int mlx5e_set_pauseparam(struct net_device *netdev,
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int err;
 
+	if (!MLX5_CAP_GEN(mdev, vport_group_manager))
+		return -EOPNOTSUPP;
+
 	if (pauseparam->autoneg)
 		return -EINVAL;
 
-- 
2.20.1


From c7f7e7e696ba90609ead5193025715b9f2f6c339 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Fri, 5 Jul 2019 17:59:28 +0300
Subject: [PATCH 12/12] net/mlx5e: Use flow keys dissector to parse packets for
 ARFS

[ Upstream commit 405b93eb764367a670e729da18e54dc42db32620 ]

The current ARFS code relies on certain fields to be set in the SKB
(e.g. transport_header) and extracts IP addresses and ports by custom
code that parses the packet. The necessary SKB fields, however, are not
always set at that point, which leads to an out-of-bounds access. Use
skb_flow_dissect_flow_keys() to get the necessary information reliably,
fix the out-of-bounds access and reuse the code.

Fixes: 18c908e477dc ("net/mlx5e: Add accelerated RFS support")
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en_arfs.c | 97 +++++++------------
 1 file changed, 34 insertions(+), 63 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
index 45cdde694d20..a4be04debe67 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
@@ -437,12 +437,6 @@ arfs_hash_bucket(struct arfs_table *arfs_t, __be16 src_port,
 	return &arfs_t->rules_hash[bucket_idx];
 }
 
-static u8 arfs_get_ip_proto(const struct sk_buff *skb)
-{
-	return (skb->protocol == htons(ETH_P_IP)) ?
-		ip_hdr(skb)->protocol : ipv6_hdr(skb)->nexthdr;
-}
-
 static struct arfs_table *arfs_get_table(struct mlx5e_arfs_tables *arfs,
 					 u8 ip_proto, __be16 etype)
 {
@@ -599,31 +593,9 @@ static void arfs_handle_work(struct work_struct *work)
 	arfs_may_expire_flow(priv);
 }
 
-/* return L4 destination port from ip4/6 packets */
-static __be16 arfs_get_dst_port(const struct sk_buff *skb)
-{
-	char *transport_header;
-
-	transport_header = skb_transport_header(skb);
-	if (arfs_get_ip_proto(skb) == IPPROTO_TCP)
-		return ((struct tcphdr *)transport_header)->dest;
-	return ((struct udphdr *)transport_header)->dest;
-}
-
-/* return L4 source port from ip4/6 packets */
-static __be16 arfs_get_src_port(const struct sk_buff *skb)
-{
-	char *transport_header;
-
-	transport_header = skb_transport_header(skb);
-	if (arfs_get_ip_proto(skb) == IPPROTO_TCP)
-		return ((struct tcphdr *)transport_header)->source;
-	return ((struct udphdr *)transport_header)->source;
-}
-
 static struct arfs_rule *arfs_alloc_rule(struct mlx5e_priv *priv,
 					 struct arfs_table *arfs_t,
-					 const struct sk_buff *skb,
+					 const struct flow_keys *fk,
 					 u16 rxq, u32 flow_id)
 {
 	struct arfs_rule *rule;
@@ -638,19 +610,19 @@ static struct arfs_rule *arfs_alloc_rule(struct mlx5e_priv *priv,
 	INIT_WORK(&rule->arfs_work, arfs_handle_work);
 
 	tuple = &rule->tuple;
-	tuple->etype = skb->protocol;
+	tuple->etype = fk->basic.n_proto;
+	tuple->ip_proto = fk->basic.ip_proto;
 	if (tuple->etype == htons(ETH_P_IP)) {
-		tuple->src_ipv4 = ip_hdr(skb)->saddr;
-		tuple->dst_ipv4 = ip_hdr(skb)->daddr;
+		tuple->src_ipv4 = fk->addrs.v4addrs.src;
+		tuple->dst_ipv4 = fk->addrs.v4addrs.dst;
 	} else {
-		memcpy(&tuple->src_ipv6, &ipv6_hdr(skb)->saddr,
+		memcpy(&tuple->src_ipv6, &fk->addrs.v6addrs.src,
 		       sizeof(struct in6_addr));
-		memcpy(&tuple->dst_ipv6, &ipv6_hdr(skb)->daddr,
+		memcpy(&tuple->dst_ipv6, &fk->addrs.v6addrs.dst,
 		       sizeof(struct in6_addr));
 	}
-	tuple->ip_proto = arfs_get_ip_proto(skb);
-	tuple->src_port = arfs_get_src_port(skb);
-	tuple->dst_port = arfs_get_dst_port(skb);
+	tuple->src_port = fk->ports.src;
+	tuple->dst_port = fk->ports.dst;
 
 	rule->flow_id = flow_id;
 	rule->filter_id = priv->fs.arfs.last_filter_id++ % RPS_NO_FILTER;
@@ -661,37 +633,33 @@ static struct arfs_rule *arfs_alloc_rule(struct mlx5e_priv *priv,
 	return rule;
 }
 
-static bool arfs_cmp_ips(struct arfs_tuple *tuple,
-			 const struct sk_buff *skb)
+static bool arfs_cmp(const struct arfs_tuple *tuple, const struct flow_keys *fk)
 {
-	if (tuple->etype == htons(ETH_P_IP) &&
-	    tuple->src_ipv4 == ip_hdr(skb)->saddr &&
-	    tuple->dst_ipv4 == ip_hdr(skb)->daddr)
-		return true;
-	if (tuple->etype == htons(ETH_P_IPV6) &&
-	    (!memcmp(&tuple->src_ipv6, &ipv6_hdr(skb)->saddr,
-		     sizeof(struct in6_addr))) &&
-	    (!memcmp(&tuple->dst_ipv6, &ipv6_hdr(skb)->daddr,
-		     sizeof(struct in6_addr))))
-		return true;
+	if (tuple->src_port != fk->ports.src || tuple->dst_port != fk->ports.dst)
+		return false;
+	if (tuple->etype != fk->basic.n_proto)
+		return false;
+	if (tuple->etype == htons(ETH_P_IP))
+		return tuple->src_ipv4 == fk->addrs.v4addrs.src &&
+		       tuple->dst_ipv4 == fk->addrs.v4addrs.dst;
+	if (tuple->etype == htons(ETH_P_IPV6))
+		return !memcmp(&tuple->src_ipv6, &fk->addrs.v6addrs.src,
+			       sizeof(struct in6_addr)) &&
+		       !memcmp(&tuple->dst_ipv6, &fk->addrs.v6addrs.dst,
+			       sizeof(struct in6_addr));
 	return false;
 }
 
 static struct arfs_rule *arfs_find_rule(struct arfs_table *arfs_t,
-					const struct sk_buff *skb)
+					const struct flow_keys *fk)
 {
 	struct arfs_rule *arfs_rule;
 	struct hlist_head *head;
-	__be16 src_port = arfs_get_src_port(skb);
-	__be16 dst_port = arfs_get_dst_port(skb);
 
-	head = arfs_hash_bucket(arfs_t, src_port, dst_port);
+	head = arfs_hash_bucket(arfs_t, fk->ports.src, fk->ports.dst);
 	hlist_for_each_entry(arfs_rule, head, hlist) {
-		if (arfs_rule->tuple.src_port == src_port &&
-		    arfs_rule->tuple.dst_port == dst_port &&
-		    arfs_cmp_ips(&arfs_rule->tuple, skb)) {
+		if (arfs_cmp(&arfs_rule->tuple, fk))
 			return arfs_rule;
-		}
 	}
 
 	return NULL;
@@ -704,20 +672,24 @@ int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 	struct mlx5e_arfs_tables *arfs = &priv->fs.arfs;
 	struct arfs_table *arfs_t;
 	struct arfs_rule *arfs_rule;
+	struct flow_keys fk;
+
+	if (!skb_flow_dissect_flow_keys(skb, &fk, 0))
+		return -EPROTONOSUPPORT;
 
-	if (skb->protocol != htons(ETH_P_IP) &&
-	    skb->protocol != htons(ETH_P_IPV6))
+	if (fk.basic.n_proto != htons(ETH_P_IP) &&
+	    fk.basic.n_proto != htons(ETH_P_IPV6))
 		return -EPROTONOSUPPORT;
 
 	if (skb->encapsulation)
 		return -EPROTONOSUPPORT;
 
-	arfs_t = arfs_get_table(arfs, arfs_get_ip_proto(skb), skb->protocol);
+	arfs_t = arfs_get_table(arfs, fk.basic.ip_proto, fk.basic.n_proto);
 	if (!arfs_t)
 		return -EPROTONOSUPPORT;
 
 	spin_lock_bh(&arfs->arfs_lock);
-	arfs_rule = arfs_find_rule(arfs_t, skb);
+	arfs_rule = arfs_find_rule(arfs_t, &fk);
 	if (arfs_rule) {
 		if (arfs_rule->rxq == rxq_index) {
 			spin_unlock_bh(&arfs->arfs_lock);
@@ -725,8 +697,7 @@ int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 		}
 		arfs_rule->rxq = rxq_index;
 	} else {
-		arfs_rule = arfs_alloc_rule(priv, arfs_t, skb,
-					    rxq_index, flow_id);
+		arfs_rule = arfs_alloc_rule(priv, arfs_t, &fk, rxq_index, flow_id);
 		if (!arfs_rule) {
 			spin_unlock_bh(&arfs->arfs_lock);
 			return -ENOMEM;
-- 
2.20.1


[-- Attachment #3: net_52.mbox --]
[-- Type: Application/Octet-Stream, Size: 88769 bytes --]

From e726e20a46ff77db44619731742831eb59ece281 Mon Sep 17 00:00:00 2001
From: Manish Chopra <manishc@marvell.com>
Date: Sun, 18 Aug 2019 07:25:48 -0700
Subject: [PATCH 01/28] bnx2x: Fix VF's VLAN reconfiguration in reload.

[ Upstream commit 4a4d2d372fb9b9229327e2ed01d5d9572eddf4de ]

Commit 04f05230c5c13 ("bnx2x: Remove configured vlans as
part of unload sequence."), introduced a regression in driver
that as a part of VF's reload flow, VLANs created on the VF
doesn't get re-configured in hardware as vlan metadata/info
was not getting cleared for the VFs which causes vlan PING to stop.

This patch clears the vlan metadata/info so that VLANs gets
re-configured back in the hardware in VF's reload flow and
PING/traffic continues for VLANs created over the VFs.

Fixes: 04f05230c5c13 ("bnx2x: Remove configured vlans as part of unload sequence.")
Signed-off-by: Manish Chopra <manishc@marvell.com>
Signed-off-by: Sudarsana Kalluru <skalluru@marvell.com>
Signed-off-by: Shahed Shaikh <shshaikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c |  7 ++++---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h |  2 ++
 .../net/ethernet/broadcom/bnx2x/bnx2x_main.c    | 17 ++++++++++++-----
 3 files changed, 18 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 4039a9599d79..9d582b3ebc88 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -3057,12 +3057,13 @@ int bnx2x_nic_unload(struct bnx2x *bp, int unload_mode, bool keep_link)
 	/* if VF indicate to PF this function is going down (PF will delete sp
 	 * elements and clear initializations
 	 */
-	if (IS_VF(bp))
+	if (IS_VF(bp)) {
+		bnx2x_clear_vlan_info(bp);
 		bnx2x_vfpf_close_vf(bp);
-	else if (unload_mode != UNLOAD_RECOVERY)
+	} else if (unload_mode != UNLOAD_RECOVERY) {
 		/* if this is a normal/close unload need to clean up chip*/
 		bnx2x_chip_cleanup(bp, unload_mode, keep_link);
-	else {
+	} else {
 		/* Send the UNLOAD_REQUEST to the MCP */
 		bnx2x_send_unload_req(bp, unload_mode);
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index c2f6e44e9a3f..8b08cb18e363 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -425,6 +425,8 @@ void bnx2x_set_reset_global(struct bnx2x *bp);
 void bnx2x_disable_close_the_gate(struct bnx2x *bp);
 int bnx2x_init_hw_func_cnic(struct bnx2x *bp);
 
+void bnx2x_clear_vlan_info(struct bnx2x *bp);
+
 /**
  * bnx2x_sp_event - handle ramrods completion.
  *
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 2cc14db8f0ec..192ff8d5da32 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -8482,11 +8482,21 @@ int bnx2x_set_vlan_one(struct bnx2x *bp, u16 vlan,
 	return rc;
 }
 
+void bnx2x_clear_vlan_info(struct bnx2x *bp)
+{
+	struct bnx2x_vlan_entry *vlan;
+
+	/* Mark that hw forgot all entries */
+	list_for_each_entry(vlan, &bp->vlan_reg, link)
+		vlan->hw = false;
+
+	bp->vlan_cnt = 0;
+}
+
 static int bnx2x_del_all_vlans(struct bnx2x *bp)
 {
 	struct bnx2x_vlan_mac_obj *vlan_obj = &bp->sp_objs[0].vlan_obj;
 	unsigned long ramrod_flags = 0, vlan_flags = 0;
-	struct bnx2x_vlan_entry *vlan;
 	int rc;
 
 	__set_bit(RAMROD_COMP_WAIT, &ramrod_flags);
@@ -8495,10 +8505,7 @@ static int bnx2x_del_all_vlans(struct bnx2x *bp)
 	if (rc)
 		return rc;
 
-	/* Mark that hw forgot all entries */
-	list_for_each_entry(vlan, &bp->vlan_reg, link)
-		vlan->hw = false;
-	bp->vlan_cnt = 0;
+	bnx2x_clear_vlan_info(bp);
 
 	return 0;
 }
-- 
2.20.1


From e7bb7db7f61c0a6cb049b4c7df2e50553814100a Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 7 Aug 2019 10:19:59 +0800
Subject: [PATCH 02/28] bonding: Add vlan tx offload to hw_enc_features

[ Upstream commit d595b03de2cb0bdf9bcdf35ff27840cc3a37158f ]

As commit 30d8177e8ac7 ("bonding: Always enable vlan tx offload")
said, we should always enable bonding's vlan tx offload, pass the
vlan packets to the slave devices with vlan tci, let them to handle
vlan implementation.

Now if encapsulation protocols like VXLAN is used, skb->encapsulation
may be set, then the packet is passed to vlan device which based on
bonding device. However in netif_skb_features(), the check of
hw_enc_features:

	 if (skb->encapsulation)
                 features &= dev->hw_enc_features;

clears NETIF_F_HW_VLAN_CTAG_TX/NETIF_F_HW_VLAN_STAG_TX. This results
in same issue in commit 30d8177e8ac7 like this:

vlan_dev_hard_start_xmit
  -->dev_queue_xmit
    -->validate_xmit_skb
      -->netif_skb_features //NETIF_F_HW_VLAN_CTAG_TX is cleared
      -->validate_xmit_vlan
        -->__vlan_hwaccel_push_inside //skb->tci is cleared
...
 --> bond_start_xmit
   --> bond_xmit_hash //BOND_XMIT_POLICY_ENCAP34
     --> __skb_flow_dissect // nhoff point to IP header
        -->  case htons(ETH_P_8021Q)
             // skb_vlan_tag_present is false, so
             vlan = __skb_header_pointer(skb, nhoff, sizeof(_vlan),
             //vlan point to ip header wrongly

Fixes: b2a103e6d0af ("bonding: convert to ndo_fix_features")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index b0aab3a0a1bf..f183cadd14e3 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1113,6 +1113,8 @@ static void bond_compute_features(struct bonding *bond)
 done:
 	bond_dev->vlan_features = vlan_features;
 	bond_dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL |
+				    NETIF_F_HW_VLAN_CTAG_TX |
+				    NETIF_F_HW_VLAN_STAG_TX |
 				    NETIF_F_GSO_UDP_L4;
 	bond_dev->gso_max_segs = gso_max_segs;
 	netif_set_gso_max_size(bond_dev, gso_max_size);
-- 
2.20.1


From be9c30216c9a4f0bc686dea1600907fb503d6d44 Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wens@csie.org>
Date: Sun, 11 Aug 2019 22:18:25 +0800
Subject: [PATCH 03/28] net: dsa: Check existence of .port_mdb_add callback
 before calling it

[ Upstream commit 58799865be84e2a895dab72de0e1b996ed943f22 ]

The dsa framework has optional .port_mdb_{prepare,add,del} callback fields
for drivers to handle multicast database entries. When adding an entry, the
framework goes through a prepare phase, then a commit phase. Drivers not
providing these callbacks should be detected in the prepare phase.

DSA core may still bypass the bridge layer and call the dsa_port_mdb_add
function directly with no prepare phase or no switchdev trans object,
and the framework ends up calling an undefined .port_mdb_add callback.
This results in a NULL pointer dereference, as shown in the log below.

The other functions seem to be properly guarded. Do the same for
.port_mdb_add in dsa_switch_mdb_add_bitmap() as well.

    8<--- cut here ---
    Unable to handle kernel NULL pointer dereference at virtual address 00000000
    pgd = (ptrval)
    [00000000] *pgd=00000000
    Internal error: Oops: 80000005 [#1] SMP ARM
    Modules linked in: rtl8xxxu rtl8192cu rtl_usb rtl8192c_common rtlwifi mac80211 cfg80211
    CPU: 1 PID: 134 Comm: kworker/1:2 Not tainted 5.3.0-rc1-00247-gd3519030752a #1
    Hardware name: Allwinner sun7i (A20) Family
    Workqueue: events switchdev_deferred_process_work
    PC is at 0x0
    LR is at dsa_switch_event+0x570/0x620
    pc : [<00000000>]    lr : [<c08533ec>]    psr: 80070013
    sp : ee871db8  ip : 00000000  fp : ee98d0a4
    r10: 0000000c  r9 : 00000008  r8 : ee89f710
    r7 : ee98d040  r6 : ee98d088  r5 : c0f04c48  r4 : ee98d04c
    r3 : 00000000  r2 : ee89f710  r1 : 00000008  r0 : ee98d040
    Flags: Nzcv  IRQs on  FIQs on  Mode SVC_32  ISA ARM  Segment none
    Control: 10c5387d  Table: 6deb406a  DAC: 00000051
    Process kworker/1:2 (pid: 134, stack limit = 0x(ptrval))
    Stack: (0xee871db8 to 0xee872000)
    1da0:                                                       ee871e14 103ace2d
    1dc0: 00000000 ffffffff 00000000 ee871e14 00000005 00000000 c08524a0 00000000
    1de0: ffffe000 c014bdfc c0f04c48 ee871e98 c0f04c48 ee9e5000 c0851120 c014bef0
    1e00: 00000000 b643aea2 ee9b4068 c08509a8 ee2bf940 ee89f710 ee871ecb 00000000
    1e20: 00000008 103ace2d 00000000 c087e248 ee29c868 103ace2d 00000001 ffffffff
    1e40: 00000000 ee871e98 00000006 00000000 c0fb2a50 c087e2d0 ffffffff c08523c4
    1e60: ffffffff c014bdfc 00000006 c0fad2d0 ee871e98 ee89f710 00000000 c014c500
    1e80: 00000000 ee89f3c0 c0f04c48 00000000 ee9e5000 c087dfb4 ee9e5000 00000000
    1ea0: ee89f710 ee871ecb 00000001 103ace2d 00000000 c0f04c48 00000000 c087e0a8
    1ec0: 00000000 efd9a3e0 0089f3c0 103ace2d ee89f700 ee89f710 ee9e5000 00000122
    1ee0: 00000100 c087e130 ee89f700 c0fad2c8 c1003ef0 c087de4c 2e928000 c0fad2ec
    1f00: c0fad2ec ee839580 ef7a62c0 ef7a9400 00000000 c087def8 c0fad2ec c01447dc
    1f20: ef315640 ef7a62c0 00000008 ee839580 ee839594 ef7a62c0 00000008 c0f03d00
    1f40: ef7a62d8 ef7a62c0 ffffe000 c0145b84 ffffe000 c0fb2420 c0bfaa8c 00000000
    1f60: ffffe000 ee84b600 ee84b5c0 00000000 ee870000 ee839580 c0145b40 ef0e5ea4
    1f80: ee84b61c c014a6f8 00000001 ee84b5c0 c014a5b0 00000000 00000000 00000000
    1fa0: 00000000 00000000 00000000 c01010e8 00000000 00000000 00000000 00000000
    1fc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
    1fe0: 00000000 00000000 00000000 00000000 00000013 00000000 00000000 00000000
    [<c08533ec>] (dsa_switch_event) from [<c014bdfc>] (notifier_call_chain+0x48/0x84)
    [<c014bdfc>] (notifier_call_chain) from [<c014bef0>] (raw_notifier_call_chain+0x18/0x20)
    [<c014bef0>] (raw_notifier_call_chain) from [<c08509a8>] (dsa_port_mdb_add+0x48/0x74)
    [<c08509a8>] (dsa_port_mdb_add) from [<c087e248>] (__switchdev_handle_port_obj_add+0x54/0xd4)
    [<c087e248>] (__switchdev_handle_port_obj_add) from [<c087e2d0>] (switchdev_handle_port_obj_add+0x8/0x14)
    [<c087e2d0>] (switchdev_handle_port_obj_add) from [<c08523c4>] (dsa_slave_switchdev_blocking_event+0x94/0xa4)
    [<c08523c4>] (dsa_slave_switchdev_blocking_event) from [<c014bdfc>] (notifier_call_chain+0x48/0x84)
    [<c014bdfc>] (notifier_call_chain) from [<c014c500>] (blocking_notifier_call_chain+0x50/0x68)
    [<c014c500>] (blocking_notifier_call_chain) from [<c087dfb4>] (switchdev_port_obj_notify+0x44/0xa8)
    [<c087dfb4>] (switchdev_port_obj_notify) from [<c087e0a8>] (switchdev_port_obj_add_now+0x90/0x104)
    [<c087e0a8>] (switchdev_port_obj_add_now) from [<c087e130>] (switchdev_port_obj_add_deferred+0x14/0x5c)
    [<c087e130>] (switchdev_port_obj_add_deferred) from [<c087de4c>] (switchdev_deferred_process+0x64/0x104)
    [<c087de4c>] (switchdev_deferred_process) from [<c087def8>] (switchdev_deferred_process_work+0xc/0x14)
    [<c087def8>] (switchdev_deferred_process_work) from [<c01447dc>] (process_one_work+0x218/0x50c)
    [<c01447dc>] (process_one_work) from [<c0145b84>] (worker_thread+0x44/0x5bc)
    [<c0145b84>] (worker_thread) from [<c014a6f8>] (kthread+0x148/0x150)
    [<c014a6f8>] (kthread) from [<c01010e8>] (ret_from_fork+0x14/0x2c)
    Exception stack(0xee871fb0 to 0xee871ff8)
    1fa0:                                     00000000 00000000 00000000 00000000
    1fc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
    1fe0: 00000000 00000000 00000000 00000000 00000013 00000000
    Code: bad PC value
    ---[ end trace 1292c61abd17b130 ]---

    [<c08533ec>] (dsa_switch_event) from [<c014bdfc>] (notifier_call_chain+0x48/0x84)
    corresponds to

	$ arm-linux-gnueabihf-addr2line -C -i -e vmlinux c08533ec

	linux/net/dsa/switch.c:156
	linux/net/dsa/switch.c:178
	linux/net/dsa/switch.c:328

Fixes: e6db98db8a95 ("net: dsa: add switch mdb bitmap functions")
Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Reviewed-by: Vivien Didelot <vivien.didelot@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/switch.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/dsa/switch.c b/net/dsa/switch.c
index 4ec5b7f85d51..09d9286b27cc 100644
--- a/net/dsa/switch.c
+++ b/net/dsa/switch.c
@@ -153,6 +153,9 @@ static void dsa_switch_mdb_add_bitmap(struct dsa_switch *ds,
 {
 	int port;
 
+	if (!ds->ops->port_mdb_add)
+		return;
+
 	for_each_set_bit(port, bitmap, ds->num_ports)
 		ds->ops->port_mdb_add(ds, port, mdb);
 }
-- 
2.20.1


From 310a1b5d77a87fe4d8e45f42a4c106b7febdcdd3 Mon Sep 17 00:00:00 2001
From: Wenwen Wang <wenwen@cs.uga.edu>
Date: Mon, 12 Aug 2019 14:11:35 -0500
Subject: [PATCH 04/28] net/mlx4_en: fix a memory leak bug

[ Upstream commit 48ec7014c56e5eb2fbf6f479896143622d834f3b ]

In mlx4_en_config_rss_steer(), 'rss_map->indir_qp' is allocated through
kzalloc(). After that, mlx4_qp_alloc() is invoked to configure RSS
indirection. However, if mlx4_qp_alloc() fails, the allocated
'rss_map->indir_qp' is not deallocated, leading to a memory leak bug.

To fix the above issue, add the 'qp_alloc_err' label to free
'rss_map->indir_qp'.

Fixes: 4931c6ef04b4 ("net/mlx4_en: Optimized single ring steering")
Signed-off-by: Wenwen Wang <wenwen@cs.uga.edu>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/ethernet/mellanox/mlx4/en_rx.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 6c01314e87b0..db3552f2d087 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -1187,7 +1187,7 @@ int mlx4_en_config_rss_steer(struct mlx4_en_priv *priv)
 	err = mlx4_qp_alloc(mdev->dev, priv->base_qpn, rss_map->indir_qp);
 	if (err) {
 		en_err(priv, "Failed to allocate RSS indirection QP\n");
-		goto rss_err;
+		goto qp_alloc_err;
 	}
 
 	rss_map->indir_qp->event = mlx4_en_sqp_event;
@@ -1241,6 +1241,7 @@ int mlx4_en_config_rss_steer(struct mlx4_en_priv *priv)
 		       MLX4_QP_STATE_RST, NULL, 0, 0, rss_map->indir_qp);
 	mlx4_qp_remove(mdev->dev, rss_map->indir_qp);
 	mlx4_qp_free(mdev->dev, rss_map->indir_qp);
+qp_alloc_err:
 	kfree(rss_map->indir_qp);
 	rss_map->indir_qp = NULL;
 rss_err:
-- 
2.20.1


From b156325a50120533015c54876bf31edbee5bc8c2 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 14 Aug 2019 02:11:57 -0700
Subject: [PATCH 05/28] net/packet: fix race in tpacket_snd()

[ Upstream commit 32d3182cd2cd29b2e7e04df7b0db350fbe11289f ]

packet_sendmsg() checks tx_ring.pg_vec to decide
if it must call tpacket_snd().

Problem is that the check is lockless, meaning another thread
can issue a concurrent setsockopt(PACKET_TX_RING ) to flip
tx_ring.pg_vec back to NULL.

Given that tpacket_snd() grabs pg_vec_lock mutex, we can
perform the check again to solve the race.

syzbot reported :

kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] PREEMPT SMP KASAN
CPU: 1 PID: 11429 Comm: syz-executor394 Not tainted 5.3.0-rc4+ #101
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:packet_lookup_frame+0x8d/0x270 net/packet/af_packet.c:474
Code: c1 ee 03 f7 73 0c 80 3c 0e 00 0f 85 cb 01 00 00 48 8b 0b 89 c0 4c 8d 24 c1 48 b8 00 00 00 00 00 fc ff df 4c 89 e1 48 c1 e9 03 <80> 3c 01 00 0f 85 94 01 00 00 48 8d 7b 10 4d 8b 3c 24 48 b8 00 00
RSP: 0018:ffff88809f82f7b8 EFLAGS: 00010246
RAX: dffffc0000000000 RBX: ffff8880a45c7030 RCX: 0000000000000000
RDX: 0000000000000000 RSI: 1ffff110148b8e06 RDI: ffff8880a45c703c
RBP: ffff88809f82f7e8 R08: ffff888087aea200 R09: fffffbfff134ae50
R10: fffffbfff134ae4f R11: ffffffff89a5727f R12: 0000000000000000
R13: 0000000000000001 R14: ffff8880a45c6ac0 R15: 0000000000000000
FS:  00007fa04716f700(0000) GS:ffff8880ae900000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007fa04716edb8 CR3: 0000000091eb4000 CR4: 00000000001406e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 packet_current_frame net/packet/af_packet.c:487 [inline]
 tpacket_snd net/packet/af_packet.c:2667 [inline]
 packet_sendmsg+0x590/0x6250 net/packet/af_packet.c:2975
 sock_sendmsg_nosec net/socket.c:637 [inline]
 sock_sendmsg+0xd7/0x130 net/socket.c:657
 ___sys_sendmsg+0x3e2/0x920 net/socket.c:2311
 __sys_sendmmsg+0x1bf/0x4d0 net/socket.c:2413
 __do_sys_sendmmsg net/socket.c:2442 [inline]
 __se_sys_sendmmsg net/socket.c:2439 [inline]
 __x64_sys_sendmmsg+0x9d/0x100 net/socket.c:2439
 do_syscall_64+0xfd/0x6a0 arch/x86/entry/common.c:296
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Fixes: 69e3c75f4d54 ("net: TX_RING and packet mmap")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 5f78df080573..bad144dfabc5 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2607,6 +2607,13 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 
 	mutex_lock(&po->pg_vec_lock);
 
+	/* packet_sendmsg() check on tx_ring.pg_vec was lockless,
+	 * we need to confirm it under protection of pg_vec_lock.
+	 */
+	if (unlikely(!po->tx_ring.pg_vec)) {
+		err = -EBUSY;
+		goto out;
+	}
 	if (likely(saddr == NULL)) {
 		dev	= packet_cached_dev_get(po);
 		proto	= po->num;
-- 
2.20.1


From aff2c0ac1de1ea80c82f06c7b49d8a00b10b40ae Mon Sep 17 00:00:00 2001
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Wed, 7 Aug 2019 01:45:40 +0300
Subject: [PATCH 06/28] net: sched: sch_taprio: fix memleak in error path for
 sched list parse

[ Upstream commit 51650d33b2771acd505068da669cf85cffac369a ]

In error case, all entries should be freed from the sched list
before deleting it. For simplicity use rcu way.

Fixes: 5a781ccbd19e46 ("tc: Add support for configuring the taprio scheduler")
Acked-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_taprio.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 9ecfb8f5902a..8be89aa52b6e 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -849,7 +849,8 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 	spin_unlock_bh(qdisc_lock(sch));
 
 free_sched:
-	kfree(new_admin);
+	if (new_admin)
+		call_rcu(&new_admin->rcu, taprio_free_sched_cb);
 
 	return err;
 }
-- 
2.20.1


From ec462df0bad92733ab3b4a57058529be4f81d122 Mon Sep 17 00:00:00 2001
From: zhengbin <zhengbin13@huawei.com>
Date: Tue, 13 Aug 2019 22:05:50 +0800
Subject: [PATCH 07/28] sctp: fix memleak in sctp_send_reset_streams

[ Upstream commit 6d5afe20397b478192ed8c38ec0ee10fa3aec649 ]

If the stream outq is not empty, need to kfree nstr_list.

Fixes: d570a59c5b5f ("sctp: only allow the out stream reset when the stream outq is empty")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: zhengbin <zhengbin13@huawei.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/sctp/stream.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index 25946604af85..e83cdaa2ab76 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -316,6 +316,7 @@ int sctp_send_reset_streams(struct sctp_association *asoc,
 		nstr_list[i] = htons(str_list[i]);
 
 	if (out && !sctp_stream_outq_is_empty(stream, str_nums, nstr_list)) {
+		kfree(nstr_list);
 		retval = -EAGAIN;
 		goto out;
 	}
-- 
2.20.1


From 133fe0cb8f5cccf3e35609663b3ca2c18b9421e9 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 12 Aug 2019 20:49:12 +0800
Subject: [PATCH 08/28] sctp: fix the transport error_count check

[ Upstream commit a1794de8b92ea6bc2037f445b296814ac826693e ]

As the annotation says in sctp_do_8_2_transport_strike():

  "If the transport error count is greater than the pf_retrans
   threshold, and less than pathmaxrtx ..."

It should be transport->error_count checked with pathmaxrxt,
instead of asoc->pf_retrans.

Fixes: 5aa93bcf66f4 ("sctp: Implement quick failover draft from tsvwg")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/sctp/sm_sideeffect.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index a554d6d15d1b..1cf5bb5b73c4 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -546,7 +546,7 @@ static void sctp_do_8_2_transport_strike(struct sctp_cmd_seq *commands,
 	 */
 	if (net->sctp.pf_enable &&
 	   (transport->state == SCTP_ACTIVE) &&
-	   (asoc->pf_retrans < transport->pathmaxrxt) &&
+	   (transport->error_count < transport->pathmaxrxt) &&
 	   (transport->error_count > asoc->pf_retrans)) {
 
 		sctp_assoc_control_transport(asoc, transport,
-- 
2.20.1


From f9fa19f41dc21aa70436b4c366931052e0fca64e Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Thu, 8 Aug 2019 14:22:47 +0800
Subject: [PATCH 09/28] team: Add vlan tx offload to hw_enc_features

[ Upstream commit 227f2f030e28d8783c3d10ce70ff4ba79cad653f ]

We should also enable team's vlan tx offload in hw_enc_features,
pass the vlan packets to the slave devices with vlan tci, let the
slave handle vlan tunneling offload implementation.

Fixes: 3268e5cb494d ("team: Advertise tunneling offload features")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 36916bf51ee6..d1b4c7d8e2bc 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1004,6 +1004,8 @@ static void __team_compute_features(struct team *team)
 
 	team->dev->vlan_features = vlan_features;
 	team->dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL |
+				     NETIF_F_HW_VLAN_CTAG_TX |
+				     NETIF_F_HW_VLAN_STAG_TX |
 				     NETIF_F_GSO_UDP_L4;
 	team->dev->hard_header_len = max_hard_header_len;
 
-- 
2.20.1


From 5d943357faa3e1743f2ddf68aa47b77fa6b31492 Mon Sep 17 00:00:00 2001
From: Chris Packham <chris.packham@alliedtelesis.co.nz>
Date: Mon, 12 Aug 2019 08:18:25 +1200
Subject: [PATCH 10/28] tipc: initialise addr_trail_end when setting node
 addresses

[ Upstream commit 8874ecae2977e5a2d4f0ba301364435b81c05938 ]

We set the field 'addr_trial_end' to 'jiffies', instead of the current
value 0, at the moment the node address is initialized. This guarantees
we don't inadvertently enter an address trial period when the node
address is explicitly set by the user.

Signed-off-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/addr.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/tipc/addr.c b/net/tipc/addr.c
index b88d48d00913..0f1eaed1bd1b 100644
--- a/net/tipc/addr.c
+++ b/net/tipc/addr.c
@@ -75,6 +75,7 @@ void tipc_set_node_addr(struct net *net, u32 addr)
 		tipc_set_node_id(net, node_id);
 	}
 	tn->trial_addr = addr;
+	tn->addr_trial_end = jiffies;
 	pr_info("32-bit node address hash set to %x\n", addr);
 }
 
-- 
2.20.1


From c6168d42d77cdb816c8dd1dc57bc5bdf2517c47c Mon Sep 17 00:00:00 2001
From: Ross Lagerwall <ross.lagerwall@citrix.com>
Date: Mon, 5 Aug 2019 16:34:34 +0100
Subject: [PATCH 11/28] xen/netback: Reset nr_frags before freeing skb

[ Upstream commit 3a0233ddec554b886298de2428edb5c50a20e694 ]

At this point nr_frags has been incremented but the frag does not yet
have a page assigned so freeing the skb results in a crash. Reset
nr_frags before freeing the skb to prevent this.

Signed-off-by: Ross Lagerwall <ross.lagerwall@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netback/netback.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 1d9940d4e8c7..c9262ffeefe4 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -925,6 +925,7 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue,
 			skb_shinfo(skb)->nr_frags = MAX_SKB_FRAGS;
 			nskb = xenvif_alloc_skb(0);
 			if (unlikely(nskb == NULL)) {
+				skb_shinfo(skb)->nr_frags = 0;
 				kfree_skb(skb);
 				xenvif_tx_err(queue, &txreq, extra_count, idx);
 				if (net_ratelimit())
@@ -940,6 +941,7 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue,
 
 			if (xenvif_set_skb_gso(queue->vif, skb, gso)) {
 				/* Failure in xenvif_set_skb_gso is fatal. */
+				skb_shinfo(skb)->nr_frags = 0;
 				kfree_skb(skb);
 				kfree_skb(nskb);
 				break;
-- 
2.20.1


From ad20ca90d49a7b3b2143ea0b9806ee734d336baa Mon Sep 17 00:00:00 2001
From: Huy Nguyen <huyn@mellanox.com>
Date: Thu, 1 Aug 2019 11:10:19 -0500
Subject: [PATCH 12/28] net/mlx5e: Only support tx/rx pause setting for port
 owner

[ Upstream commit 466df6eb4a9e813b3cfc674363316450c57a89c5 ]

Only support changing tx/rx pause frame setting if the net device
is the vport group manager.

Fixes: 3c2d18ef22df ("net/mlx5e: Support ethtool get/set_pauseparam")
Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index f637d81f08bc..22d510176965 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1317,6 +1317,9 @@ int mlx5e_ethtool_set_pauseparam(struct mlx5e_priv *priv,
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int err;
 
+	if (!MLX5_CAP_GEN(mdev, vport_group_manager))
+		return -EOPNOTSUPP;
+
 	if (pauseparam->autoneg)
 		return -EINVAL;
 
-- 
2.20.1


From 702f5376da1406a7e854d4e889e3330084afaaec Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sat, 17 Aug 2019 17:04:47 -0400
Subject: [PATCH 13/28] bnxt_en: Fix VNIC clearing logic for 57500 chips.

[ Upstream commit a46ecb116fb7f722fa8cb2da01959c36e4e10c41 ]

During device shutdown, the VNIC clearing sequence needs to be modified
to free the VNIC first before freeing the RSS contexts.  The current
code is doing the reverse and we can get mis-directed RX completions
to CP ring ID 0 when the RSS contexts are freed and zeroed.  The clearing
of RSS contexts is not required with the new sequence.

Refactor the VNIC clearing logic into a new function bnxt_clear_vnic()
and do the chip specific VNIC clearing sequence.

Fixes: 7b3af4f75b81 ("bnxt_en: Add RSS support for 57500 chips.")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 26 ++++++++++++++++-------
 1 file changed, 18 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 7afae9d80e75..d9eaafa93970 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -6963,19 +6963,29 @@ static void bnxt_hwrm_clear_vnic_rss(struct bnxt *bp)
 		bnxt_hwrm_vnic_set_rss(bp, i, false);
 }
 
-static void bnxt_hwrm_resource_free(struct bnxt *bp, bool close_path,
-				    bool irq_re_init)
+static void bnxt_clear_vnic(struct bnxt *bp)
 {
-	if (bp->vnic_info) {
-		bnxt_hwrm_clear_vnic_filter(bp);
+	if (!bp->vnic_info)
+		return;
+
+	bnxt_hwrm_clear_vnic_filter(bp);
+	if (!(bp->flags & BNXT_FLAG_CHIP_P5)) {
 		/* clear all RSS setting before free vnic ctx */
 		bnxt_hwrm_clear_vnic_rss(bp);
 		bnxt_hwrm_vnic_ctx_free(bp);
-		/* before free the vnic, undo the vnic tpa settings */
-		if (bp->flags & BNXT_FLAG_TPA)
-			bnxt_set_tpa(bp, false);
-		bnxt_hwrm_vnic_free(bp);
 	}
+	/* before free the vnic, undo the vnic tpa settings */
+	if (bp->flags & BNXT_FLAG_TPA)
+		bnxt_set_tpa(bp, false);
+	bnxt_hwrm_vnic_free(bp);
+	if (bp->flags & BNXT_FLAG_CHIP_P5)
+		bnxt_hwrm_vnic_ctx_free(bp);
+}
+
+static void bnxt_hwrm_resource_free(struct bnxt *bp, bool close_path,
+				    bool irq_re_init)
+{
+	bnxt_clear_vnic(bp);
 	bnxt_hwrm_ring_free(bp, close_path);
 	bnxt_hwrm_ring_grp_free(bp);
 	if (irq_re_init) {
-- 
2.20.1


From 17b7e6049d4e78b3c4c3accef76e7b19649c02a5 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sat, 17 Aug 2019 17:04:48 -0400
Subject: [PATCH 14/28] bnxt_en: Improve RX doorbell sequence.

[ Upstream commit e8f267b063208372f7a329c6d5288d58944d873c ]

When both RX buffers and RX aggregation buffers have to be
replenished at the end of NAPI, post the RX aggregation buffers first
before RX buffers.  Otherwise, we may run into a situation where
there are only RX buffers without RX aggregation buffers for a split
second.  This will cause the hardware to abort the RX packet and
report buffer errors, which will cause unnecessary cleanup by the
driver.

Ringing the Aggregation ring doorbell first before the RX ring doorbell
will prevent some of these buffer errors.  Use the same sequence during
ring initialization as well.

Fixes: 697197e5a173 ("bnxt_en: Re-structure doorbells.")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index d9eaafa93970..36fe4f161cf1 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -2015,9 +2015,9 @@ static void __bnxt_poll_work_done(struct bnxt *bp, struct bnxt_napi *bnapi)
 	if (bnapi->events & BNXT_RX_EVENT) {
 		struct bnxt_rx_ring_info *rxr = bnapi->rx_ring;
 
-		bnxt_db_write(bp, &rxr->rx_db, rxr->rx_prod);
 		if (bnapi->events & BNXT_AGG_EVENT)
 			bnxt_db_write(bp, &rxr->rx_agg_db, rxr->rx_agg_prod);
+		bnxt_db_write(bp, &rxr->rx_db, rxr->rx_prod);
 	}
 	bnapi->events = 0;
 }
@@ -5011,6 +5011,7 @@ static void bnxt_set_db(struct bnxt *bp, struct bnxt_db_info *db, u32 ring_type,
 
 static int bnxt_hwrm_ring_alloc(struct bnxt *bp)
 {
+	bool agg_rings = !!(bp->flags & BNXT_FLAG_AGG_RINGS);
 	int i, rc = 0;
 	u32 type;
 
@@ -5086,7 +5087,9 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp)
 		if (rc)
 			goto err_out;
 		bnxt_set_db(bp, &rxr->rx_db, type, map_idx, ring->fw_ring_id);
-		bnxt_db_write(bp, &rxr->rx_db, rxr->rx_prod);
+		/* If we have agg rings, post agg buffers first. */
+		if (!agg_rings)
+			bnxt_db_write(bp, &rxr->rx_db, rxr->rx_prod);
 		bp->grp_info[map_idx].rx_fw_ring_id = ring->fw_ring_id;
 		if (bp->flags & BNXT_FLAG_CHIP_P5) {
 			struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
@@ -5105,7 +5108,7 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp)
 		}
 	}
 
-	if (bp->flags & BNXT_FLAG_AGG_RINGS) {
+	if (agg_rings) {
 		type = HWRM_RING_ALLOC_AGG;
 		for (i = 0; i < bp->rx_nr_rings; i++) {
 			struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i];
@@ -5121,6 +5124,7 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp)
 			bnxt_set_db(bp, &rxr->rx_agg_db, type, map_idx,
 				    ring->fw_ring_id);
 			bnxt_db_write(bp, &rxr->rx_agg_db, rxr->rx_agg_prod);
+			bnxt_db_write(bp, &rxr->rx_db, rxr->rx_prod);
 			bp->grp_info[grp_idx].agg_fw_ring_id = ring->fw_ring_id;
 		}
 	}
-- 
2.20.1


From 984e0165cf43bbbd741228f1afdc19d310f3e752 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Sat, 17 Aug 2019 17:04:49 -0400
Subject: [PATCH 15/28] bnxt_en: Fix handling FRAG_ERR when NVM_INSTALL_UPDATE
 cmd fails

[ Upstream commit dd2ebf3404c7c295014bc025dea23960960ceb1a ]

If FW returns FRAG_ERR in response error code, driver is resending the
command only when HWRM command returns success. Fix the code to resend
NVM_INSTALL_UPDATE command with DEFRAG install flags, if FW returns
FRAG_ERR in its response error code.

Fixes: cb4d1d626145 ("bnxt_en: Retry failed NVM_INSTALL_UPDATE with defragmentation flag enabled.")
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index a6c7baf38036..b761a2e28a10 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -2016,21 +2016,19 @@ static int bnxt_flash_package_from_file(struct net_device *dev,
 	mutex_lock(&bp->hwrm_cmd_lock);
 	hwrm_err = _hwrm_send_message(bp, &install, sizeof(install),
 				      INSTALL_PACKAGE_TIMEOUT);
-	if (hwrm_err)
-		goto flash_pkg_exit;
-
-	if (resp->error_code) {
+	if (hwrm_err) {
 		u8 error_code = ((struct hwrm_err_output *)resp)->cmd_err;
 
-		if (error_code == NVM_INSTALL_UPDATE_CMD_ERR_CODE_FRAG_ERR) {
+		if (resp->error_code && error_code ==
+		    NVM_INSTALL_UPDATE_CMD_ERR_CODE_FRAG_ERR) {
 			install.flags |= cpu_to_le16(
 			       NVM_INSTALL_UPDATE_REQ_FLAGS_ALLOWED_TO_DEFRAG);
 			hwrm_err = _hwrm_send_message(bp, &install,
 						      sizeof(install),
 						      INSTALL_PACKAGE_TIMEOUT);
-			if (hwrm_err)
-				goto flash_pkg_exit;
 		}
+		if (hwrm_err)
+			goto flash_pkg_exit;
 	}
 
 	if (resp->result) {
-- 
2.20.1


From 1e7718a8e5d3bbd92c2d3ec902d957060607aef1 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Sat, 17 Aug 2019 17:04:50 -0400
Subject: [PATCH 16/28] bnxt_en: Suppress HWRM errors for HWRM_NVM_GET_VARIABLE
 command

[ Upstream commit b703ba751dbb4bcd086509ed4b28102bc1670b35 ]

For newly added NVM parameters, older firmware may not have the support.
Suppress the error message to avoid the unncessary error message which is
triggered when devlink calls the driver during initialization.

Fixes: 782a624d00fa ("bnxt_en: Add bnxt_en initial params table and register it.")
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index 549c90d3e465..c05d663212b2 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -98,10 +98,13 @@ static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg,
 	if (idx)
 		req->dimensions = cpu_to_le16(1);
 
-	if (req->req_type == cpu_to_le16(HWRM_NVM_SET_VARIABLE))
+	if (req->req_type == cpu_to_le16(HWRM_NVM_SET_VARIABLE)) {
 		memcpy(data_addr, buf, bytesize);
-
-	rc = hwrm_send_message(bp, msg, msg_len, HWRM_CMD_TIMEOUT);
+		rc = hwrm_send_message(bp, msg, msg_len, HWRM_CMD_TIMEOUT);
+	} else {
+		rc = hwrm_send_message_silent(bp, msg, msg_len,
+					      HWRM_CMD_TIMEOUT);
+	}
 	if (!rc && req->req_type == cpu_to_le16(HWRM_NVM_GET_VARIABLE))
 		memcpy(buf, data_addr, bytesize);
 
-- 
2.20.1


From da52559f3efe0a7a054974dadd0daa8243357689 Mon Sep 17 00:00:00 2001
From: Venkat Duvvuru <venkatkumar.duvvuru@broadcom.com>
Date: Sat, 17 Aug 2019 17:04:51 -0400
Subject: [PATCH 17/28] bnxt_en: Use correct src_fid to determine direction of
 the flow

[ Upstream commit 685ec6a81bb0d47faf1dba49437d5bdaede2733d ]

Direction of the flow is determined using src_fid. For an RX flow,
src_fid is PF's fid and for TX flow, src_fid is VF's fid. Direction
of the flow must be specified, when getting statistics for that flow.
Currently, for DECAP flow, direction is determined incorrectly, i.e.,
direction is initialized as TX for DECAP flow, instead of RX. Because
of which, stats are not reported for this DECAP flow, though it is
offloaded and there is traffic for that flow, resulting in flow age out.

This patch fixes the problem by determining the DECAP flow's direction
using correct fid.  Set the flow direction in all cases for consistency
even if 64-bit flow handle is not used.

Fixes: abd43a13525d ("bnxt_en: Support for 64-bit flow handle.")
Signed-off-by: Venkat Duvvuru <venkatkumar.duvvuru@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
index 44d6c5743fb9..a25ed190b5b2 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
@@ -1285,9 +1285,7 @@ static int bnxt_tc_add_flow(struct bnxt *bp, u16 src_fid,
 		goto free_node;
 
 	bnxt_tc_set_src_fid(bp, flow, src_fid);
-
-	if (bp->fw_cap & BNXT_FW_CAP_OVS_64BIT_HANDLE)
-		bnxt_tc_set_flow_dir(bp, flow, src_fid);
+	bnxt_tc_set_flow_dir(bp, flow, flow->src_fid);
 
 	if (!bnxt_tc_can_offload(bp, flow)) {
 		rc = -EOPNOTSUPP;
-- 
2.20.1


From 9779f87dde7c98ddd1ff727a74d552cb08c5620c Mon Sep 17 00:00:00 2001
From: Somnath Kotur <somnath.kotur@broadcom.com>
Date: Sat, 17 Aug 2019 17:04:52 -0400
Subject: [PATCH 18/28] bnxt_en: Fix to include flow direction in L2 key

[ Upstream commit 9bf46566e80fd94845527d01ebd888eb49313551 ]

FW expects the driver to provide unique flow reference handles
for Tx or Rx flows. When a Tx flow and an Rx flow end up sharing
a reference handle, flow offload does not seem to work.
This could happen in the case of 2 flows having their L2 fields
wildcarded but in different direction.
Fix to incorporate the flow direction as part of the L2 key

v2: Move the dir field to the end of the bnxt_tc_l2_key struct to
fix the warning reported by kbuild test robot <lkp@intel.com>.
There is existing code that initializes the structure using
nested initializer and will warn with the new u8 field added to
the beginning.  The structure also packs nicer when this new u8 is
added to the end of the structure [MChan].

Fixes: abd43a13525d ("bnxt_en: Support for 64-bit flow handle.")
Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c | 4 ++--
 drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h | 6 +++---
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
index a25ed190b5b2..434470a6b9f3 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
@@ -1236,7 +1236,7 @@ static int __bnxt_tc_del_flow(struct bnxt *bp,
 static void bnxt_tc_set_flow_dir(struct bnxt *bp, struct bnxt_tc_flow *flow,
 				 u16 src_fid)
 {
-	flow->dir = (bp->pf.fw_fid == src_fid) ? BNXT_DIR_RX : BNXT_DIR_TX;
+	flow->l2_key.dir = (bp->pf.fw_fid == src_fid) ? BNXT_DIR_RX : BNXT_DIR_TX;
 }
 
 static void bnxt_tc_set_src_fid(struct bnxt *bp, struct bnxt_tc_flow *flow,
@@ -1405,7 +1405,7 @@ static void bnxt_fill_cfa_stats_req(struct bnxt *bp,
 		 * 2. 15th bit of flow_handle must specify the flow
 		 *    direction (TX/RX).
 		 */
-		if (flow_node->flow.dir == BNXT_DIR_RX)
+		if (flow_node->flow.l2_key.dir == BNXT_DIR_RX)
 			handle = CFA_FLOW_INFO_REQ_FLOW_HANDLE_DIR_RX |
 				 CFA_FLOW_INFO_REQ_FLOW_HANDLE_MAX_MASK;
 		else
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h
index 8a0968967bc5..8b0f1510bdc4 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h
@@ -23,6 +23,9 @@ struct bnxt_tc_l2_key {
 	__be16		inner_vlan_tci;
 	__be16		ether_type;
 	u8		num_vlans;
+	u8		dir;
+#define BNXT_DIR_RX	1
+#define BNXT_DIR_TX	0
 };
 
 struct bnxt_tc_l3_key {
@@ -98,9 +101,6 @@ struct bnxt_tc_flow {
 
 	/* flow applicable to pkts ingressing on this fid */
 	u16				src_fid;
-	u8				dir;
-#define BNXT_DIR_RX	1
-#define BNXT_DIR_TX	0
 	struct bnxt_tc_l2_key		l2_key;
 	struct bnxt_tc_l2_key		l2_mask;
 	struct bnxt_tc_l3_key		l3_key;
-- 
2.20.1


From 20d22a623fb2bbccd1076089a1ae46ade461fb87 Mon Sep 17 00:00:00 2001
From: Roman Mashak <mrv@mojatatu.com>
Date: Wed, 7 Aug 2019 15:57:28 -0400
Subject: [PATCH 19/28] net sched: update skbedit action for batched events
 operations

[ Upstream commit e1fea322fc6d4075254ca9c5f2afdace0281da2a ]

Add get_fill_size() routine used to calculate the action size
when building a batch of events.

Fixes: ca9b0e27e ("pkt_action: add new action skbedit")
Signed-off-by: Roman Mashak <mrv@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_skbedit.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index b100870f02a6..37dced00b63d 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -307,6 +307,17 @@ static int tcf_skbedit_search(struct net *net, struct tc_action **a, u32 index)
 	return tcf_idr_search(tn, a, index);
 }
 
+static size_t tcf_skbedit_get_fill_size(const struct tc_action *act)
+{
+	return nla_total_size(sizeof(struct tc_skbedit))
+		+ nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_PRIORITY */
+		+ nla_total_size(sizeof(u16)) /* TCA_SKBEDIT_QUEUE_MAPPING */
+		+ nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_MARK */
+		+ nla_total_size(sizeof(u16)) /* TCA_SKBEDIT_PTYPE */
+		+ nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_MASK */
+		+ nla_total_size_64bit(sizeof(u64)); /* TCA_SKBEDIT_FLAGS */
+}
+
 static struct tc_action_ops act_skbedit_ops = {
 	.kind		=	"skbedit",
 	.id		=	TCA_ID_SKBEDIT,
@@ -316,6 +327,7 @@ static struct tc_action_ops act_skbedit_ops = {
 	.init		=	tcf_skbedit_init,
 	.cleanup	=	tcf_skbedit_cleanup,
 	.walk		=	tcf_skbedit_walker,
+	.get_fill_size	=	tcf_skbedit_get_fill_size,
 	.lookup		=	tcf_skbedit_search,
 	.size		=	sizeof(struct tcf_skbedit),
 };
-- 
2.20.1


From de199252412a6fb4779a1d2ff041870d664431e0 Mon Sep 17 00:00:00 2001
From: Roman Mashak <mrv@mojatatu.com>
Date: Wed, 7 Aug 2019 15:57:29 -0400
Subject: [PATCH 20/28] tc-testing: updated skbedit action tests with batch
 create/delete

[ Upstream commit 7bc161846dcf4af0485f260930d17fdd892a4980 ]

Update TDC tests with cases varifying ability of TC to install or delete
batches of skbedit actions.

Signed-off-by: Roman Mashak <mrv@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../tc-testing/tc-tests/actions/skbedit.json  | 47 +++++++++++++++++++
 1 file changed, 47 insertions(+)

diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json
index ecd96eda7f6a..e11b7c1efda3 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json
@@ -509,5 +509,52 @@
         "teardown": [
             "$TC actions flush action skbedit"
         ]
+    },
+    {
+        "id": "630c",
+        "name": "Add batch of 32 skbedit actions with all parameters and cookie",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action skbedit queue_mapping 2 priority 10 mark 7/0xaabbccdd ptype host inheritdsfield index \\$i cookie aabbccddeeff112233445566778800a1 \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "^[ \t]+index [0-9]+ ref",
+        "matchCount": "32",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "706d",
+        "name": "Delete batch of 32 skbedit actions with all parameters",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ],
+            "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action skbedit queue_mapping 2 priority 10 mark 7/0xaabbccdd ptype host inheritdsfield index \\$i \\\"; args=\\\"\\$args\\$cmd\\\"; done && $TC actions add \\$args\""
+        ],
+        "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action skbedit index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions del \\$args\"",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "^[ \t]+index [0-9]+ ref",
+        "matchCount": "0",
+        "teardown": []
     }
 ]
-- 
2.20.1


From 3e1c0923cd27f10e621d94674cd9a89be89fd434 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 6 Aug 2019 12:15:17 -0700
Subject: [PATCH 21/28] netdevsim: Restore per-network namespace accounting for
 fib entries

[ Upstream commit 59c84b9fcf42c99a945d5fdc49220d854e539690 ]

Prior to the commit in the fixes tag, the resource controller in netdevsim
tracked fib entries and rules per network namespace. Restore that behavior.

Fixes: 5fc494225c1e ("netdevsim: create devlink instance per netdevsim instance")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/netdevsim/dev.c       |  63 ++++++++----------
 drivers/net/netdevsim/fib.c       | 102 ++++++++++++++++++------------
 drivers/net/netdevsim/netdev.c    |   9 ++-
 drivers/net/netdevsim/netdevsim.h |  10 ++-
 4 files changed, 98 insertions(+), 86 deletions(-)

diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index b509b941d5ca..6825254eb882 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -71,46 +71,47 @@ static void nsim_dev_port_debugfs_exit(struct nsim_dev_port *nsim_dev_port)
 	debugfs_remove_recursive(nsim_dev_port->ddir);
 }
 
+static struct net *nsim_devlink_net(struct devlink *devlink)
+{
+	return &init_net;
+}
+
 static u64 nsim_dev_ipv4_fib_resource_occ_get(void *priv)
 {
-	struct nsim_dev *nsim_dev = priv;
+	struct net *net = priv;
 
-	return nsim_fib_get_val(nsim_dev->fib_data,
-				NSIM_RESOURCE_IPV4_FIB, false);
+	return nsim_fib_get_val(net, NSIM_RESOURCE_IPV4_FIB, false);
 }
 
 static u64 nsim_dev_ipv4_fib_rules_res_occ_get(void *priv)
 {
-	struct nsim_dev *nsim_dev = priv;
+	struct net *net = priv;
 
-	return nsim_fib_get_val(nsim_dev->fib_data,
-				NSIM_RESOURCE_IPV4_FIB_RULES, false);
+	return nsim_fib_get_val(net, NSIM_RESOURCE_IPV4_FIB_RULES, false);
 }
 
 static u64 nsim_dev_ipv6_fib_resource_occ_get(void *priv)
 {
-	struct nsim_dev *nsim_dev = priv;
+	struct net *net = priv;
 
-	return nsim_fib_get_val(nsim_dev->fib_data,
-				NSIM_RESOURCE_IPV6_FIB, false);
+	return nsim_fib_get_val(net, NSIM_RESOURCE_IPV6_FIB, false);
 }
 
 static u64 nsim_dev_ipv6_fib_rules_res_occ_get(void *priv)
 {
-	struct nsim_dev *nsim_dev = priv;
+	struct net *net = priv;
 
-	return nsim_fib_get_val(nsim_dev->fib_data,
-				NSIM_RESOURCE_IPV6_FIB_RULES, false);
+	return nsim_fib_get_val(net, NSIM_RESOURCE_IPV6_FIB_RULES, false);
 }
 
 static int nsim_dev_resources_register(struct devlink *devlink)
 {
-	struct nsim_dev *nsim_dev = devlink_priv(devlink);
 	struct devlink_resource_size_params params = {
 		.size_max = (u64)-1,
 		.size_granularity = 1,
 		.unit = DEVLINK_RESOURCE_UNIT_ENTRY
 	};
+	struct net *net = nsim_devlink_net(devlink);
 	int err;
 	u64 n;
 
@@ -124,8 +125,7 @@ static int nsim_dev_resources_register(struct devlink *devlink)
 		goto out;
 	}
 
-	n = nsim_fib_get_val(nsim_dev->fib_data,
-			     NSIM_RESOURCE_IPV4_FIB, true);
+	n = nsim_fib_get_val(net, NSIM_RESOURCE_IPV4_FIB, true);
 	err = devlink_resource_register(devlink, "fib", n,
 					NSIM_RESOURCE_IPV4_FIB,
 					NSIM_RESOURCE_IPV4, &params);
@@ -134,8 +134,7 @@ static int nsim_dev_resources_register(struct devlink *devlink)
 		return err;
 	}
 
-	n = nsim_fib_get_val(nsim_dev->fib_data,
-			     NSIM_RESOURCE_IPV4_FIB_RULES, true);
+	n = nsim_fib_get_val(net, NSIM_RESOURCE_IPV4_FIB_RULES, true);
 	err = devlink_resource_register(devlink, "fib-rules", n,
 					NSIM_RESOURCE_IPV4_FIB_RULES,
 					NSIM_RESOURCE_IPV4, &params);
@@ -154,8 +153,7 @@ static int nsim_dev_resources_register(struct devlink *devlink)
 		goto out;
 	}
 
-	n = nsim_fib_get_val(nsim_dev->fib_data,
-			     NSIM_RESOURCE_IPV6_FIB, true);
+	n = nsim_fib_get_val(net, NSIM_RESOURCE_IPV6_FIB, true);
 	err = devlink_resource_register(devlink, "fib", n,
 					NSIM_RESOURCE_IPV6_FIB,
 					NSIM_RESOURCE_IPV6, &params);
@@ -164,8 +162,7 @@ static int nsim_dev_resources_register(struct devlink *devlink)
 		return err;
 	}
 
-	n = nsim_fib_get_val(nsim_dev->fib_data,
-			     NSIM_RESOURCE_IPV6_FIB_RULES, true);
+	n = nsim_fib_get_val(net, NSIM_RESOURCE_IPV6_FIB_RULES, true);
 	err = devlink_resource_register(devlink, "fib-rules", n,
 					NSIM_RESOURCE_IPV6_FIB_RULES,
 					NSIM_RESOURCE_IPV6, &params);
@@ -177,19 +174,19 @@ static int nsim_dev_resources_register(struct devlink *devlink)
 	devlink_resource_occ_get_register(devlink,
 					  NSIM_RESOURCE_IPV4_FIB,
 					  nsim_dev_ipv4_fib_resource_occ_get,
-					  nsim_dev);
+					  net);
 	devlink_resource_occ_get_register(devlink,
 					  NSIM_RESOURCE_IPV4_FIB_RULES,
 					  nsim_dev_ipv4_fib_rules_res_occ_get,
-					  nsim_dev);
+					  net);
 	devlink_resource_occ_get_register(devlink,
 					  NSIM_RESOURCE_IPV6_FIB,
 					  nsim_dev_ipv6_fib_resource_occ_get,
-					  nsim_dev);
+					  net);
 	devlink_resource_occ_get_register(devlink,
 					  NSIM_RESOURCE_IPV6_FIB_RULES,
 					  nsim_dev_ipv6_fib_rules_res_occ_get,
-					  nsim_dev);
+					  net);
 out:
 	return err;
 }
@@ -197,11 +194,11 @@ static int nsim_dev_resources_register(struct devlink *devlink)
 static int nsim_dev_reload(struct devlink *devlink,
 			   struct netlink_ext_ack *extack)
 {
-	struct nsim_dev *nsim_dev = devlink_priv(devlink);
 	enum nsim_resource_id res_ids[] = {
 		NSIM_RESOURCE_IPV4_FIB, NSIM_RESOURCE_IPV4_FIB_RULES,
 		NSIM_RESOURCE_IPV6_FIB, NSIM_RESOURCE_IPV6_FIB_RULES
 	};
+	struct net *net = nsim_devlink_net(devlink);
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(res_ids); ++i) {
@@ -210,8 +207,7 @@ static int nsim_dev_reload(struct devlink *devlink,
 
 		err = devlink_resource_size_get(devlink, res_ids[i], &val);
 		if (!err) {
-			err = nsim_fib_set_max(nsim_dev->fib_data,
-					       res_ids[i], val, extack);
+			err = nsim_fib_set_max(net, res_ids[i], val, extack);
 			if (err)
 				return err;
 		}
@@ -241,15 +237,9 @@ nsim_dev_create(struct nsim_bus_dev *nsim_bus_dev, unsigned int port_count)
 	INIT_LIST_HEAD(&nsim_dev->port_list);
 	mutex_init(&nsim_dev->port_list_lock);
 
-	nsim_dev->fib_data = nsim_fib_create();
-	if (IS_ERR(nsim_dev->fib_data)) {
-		err = PTR_ERR(nsim_dev->fib_data);
-		goto err_devlink_free;
-	}
-
 	err = nsim_dev_resources_register(devlink);
 	if (err)
-		goto err_fib_destroy;
+		goto err_devlink_free;
 
 	err = devlink_register(devlink, &nsim_bus_dev->dev);
 	if (err)
@@ -271,8 +261,6 @@ nsim_dev_create(struct nsim_bus_dev *nsim_bus_dev, unsigned int port_count)
 	devlink_unregister(devlink);
 err_resources_unregister:
 	devlink_resources_unregister(devlink, NULL);
-err_fib_destroy:
-	nsim_fib_destroy(nsim_dev->fib_data);
 err_devlink_free:
 	devlink_free(devlink);
 	return ERR_PTR(err);
@@ -286,7 +274,6 @@ static void nsim_dev_destroy(struct nsim_dev *nsim_dev)
 	nsim_dev_debugfs_exit(nsim_dev);
 	devlink_unregister(devlink);
 	devlink_resources_unregister(devlink, NULL);
-	nsim_fib_destroy(nsim_dev->fib_data);
 	mutex_destroy(&nsim_dev->port_list_lock);
 	devlink_free(devlink);
 }
diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c
index 8c57ba747772..f61d094746c0 100644
--- a/drivers/net/netdevsim/fib.c
+++ b/drivers/net/netdevsim/fib.c
@@ -18,6 +18,7 @@
 #include <net/ip_fib.h>
 #include <net/ip6_fib.h>
 #include <net/fib_rules.h>
+#include <net/netns/generic.h>
 
 #include "netdevsim.h"
 
@@ -32,14 +33,15 @@ struct nsim_per_fib_data {
 };
 
 struct nsim_fib_data {
-	struct notifier_block fib_nb;
 	struct nsim_per_fib_data ipv4;
 	struct nsim_per_fib_data ipv6;
 };
 
-u64 nsim_fib_get_val(struct nsim_fib_data *fib_data,
-		     enum nsim_resource_id res_id, bool max)
+static unsigned int nsim_fib_net_id;
+
+u64 nsim_fib_get_val(struct net *net, enum nsim_resource_id res_id, bool max)
 {
+	struct nsim_fib_data *fib_data = net_generic(net, nsim_fib_net_id);
 	struct nsim_fib_entry *entry;
 
 	switch (res_id) {
@@ -62,10 +64,10 @@ u64 nsim_fib_get_val(struct nsim_fib_data *fib_data,
 	return max ? entry->max : entry->num;
 }
 
-int nsim_fib_set_max(struct nsim_fib_data *fib_data,
-		     enum nsim_resource_id res_id, u64 val,
+int nsim_fib_set_max(struct net *net, enum nsim_resource_id res_id, u64 val,
 		     struct netlink_ext_ack *extack)
 {
+	struct nsim_fib_data *fib_data = net_generic(net, nsim_fib_net_id);
 	struct nsim_fib_entry *entry;
 	int err = 0;
 
@@ -118,9 +120,9 @@ static int nsim_fib_rule_account(struct nsim_fib_entry *entry, bool add,
 	return err;
 }
 
-static int nsim_fib_rule_event(struct nsim_fib_data *data,
-			       struct fib_notifier_info *info, bool add)
+static int nsim_fib_rule_event(struct fib_notifier_info *info, bool add)
 {
+	struct nsim_fib_data *data = net_generic(info->net, nsim_fib_net_id);
 	struct netlink_ext_ack *extack = info->extack;
 	int err = 0;
 
@@ -155,9 +157,9 @@ static int nsim_fib_account(struct nsim_fib_entry *entry, bool add,
 	return err;
 }
 
-static int nsim_fib_event(struct nsim_fib_data *data,
-			  struct fib_notifier_info *info, bool add)
+static int nsim_fib_event(struct fib_notifier_info *info, bool add)
 {
+	struct nsim_fib_data *data = net_generic(info->net, nsim_fib_net_id);
 	struct netlink_ext_ack *extack = info->extack;
 	int err = 0;
 
@@ -176,22 +178,18 @@ static int nsim_fib_event(struct nsim_fib_data *data,
 static int nsim_fib_event_nb(struct notifier_block *nb, unsigned long event,
 			     void *ptr)
 {
-	struct nsim_fib_data *data = container_of(nb, struct nsim_fib_data,
-						  fib_nb);
 	struct fib_notifier_info *info = ptr;
 	int err = 0;
 
 	switch (event) {
 	case FIB_EVENT_RULE_ADD: /* fall through */
 	case FIB_EVENT_RULE_DEL:
-		err = nsim_fib_rule_event(data, info,
-					  event == FIB_EVENT_RULE_ADD);
+		err = nsim_fib_rule_event(info, event == FIB_EVENT_RULE_ADD);
 		break;
 
 	case FIB_EVENT_ENTRY_ADD:  /* fall through */
 	case FIB_EVENT_ENTRY_DEL:
-		err = nsim_fib_event(data, info,
-				     event == FIB_EVENT_ENTRY_ADD);
+		err = nsim_fib_event(info, event == FIB_EVENT_ENTRY_ADD);
 		break;
 	}
 
@@ -201,23 +199,30 @@ static int nsim_fib_event_nb(struct notifier_block *nb, unsigned long event,
 /* inconsistent dump, trying again */
 static void nsim_fib_dump_inconsistent(struct notifier_block *nb)
 {
-	struct nsim_fib_data *data = container_of(nb, struct nsim_fib_data,
-						  fib_nb);
+	struct nsim_fib_data *data;
+	struct net *net;
+
+	rcu_read_lock();
+	for_each_net_rcu(net) {
+		data = net_generic(net, nsim_fib_net_id);
+
+		data->ipv4.fib.num = 0ULL;
+		data->ipv4.rules.num = 0ULL;
 
-	data->ipv4.fib.num = 0ULL;
-	data->ipv4.rules.num = 0ULL;
-	data->ipv6.fib.num = 0ULL;
-	data->ipv6.rules.num = 0ULL;
+		data->ipv6.fib.num = 0ULL;
+		data->ipv6.rules.num = 0ULL;
+	}
+	rcu_read_unlock();
 }
 
-struct nsim_fib_data *nsim_fib_create(void)
-{
-	struct nsim_fib_data *data;
-	int err;
+static struct notifier_block nsim_fib_nb = {
+	.notifier_call = nsim_fib_event_nb,
+};
 
-	data = kzalloc(sizeof(*data), GFP_KERNEL);
-	if (!data)
-		return ERR_PTR(-ENOMEM);
+/* Initialize per network namespace state */
+static int __net_init nsim_fib_netns_init(struct net *net)
+{
+	struct nsim_fib_data *data = net_generic(net, nsim_fib_net_id);
 
 	data->ipv4.fib.max = (u64)-1;
 	data->ipv4.rules.max = (u64)-1;
@@ -225,22 +230,37 @@ struct nsim_fib_data *nsim_fib_create(void)
 	data->ipv6.fib.max = (u64)-1;
 	data->ipv6.rules.max = (u64)-1;
 
-	data->fib_nb.notifier_call = nsim_fib_event_nb;
-	err = register_fib_notifier(&data->fib_nb, nsim_fib_dump_inconsistent);
-	if (err) {
-		pr_err("Failed to register fib notifier\n");
-		goto err_out;
-	}
+	return 0;
+}
 
-	return data;
+static struct pernet_operations nsim_fib_net_ops = {
+	.init = nsim_fib_netns_init,
+	.id   = &nsim_fib_net_id,
+	.size = sizeof(struct nsim_fib_data),
+};
 
-err_out:
-	kfree(data);
-	return ERR_PTR(err);
+void nsim_fib_exit(void)
+{
+	unregister_pernet_subsys(&nsim_fib_net_ops);
+	unregister_fib_notifier(&nsim_fib_nb);
 }
 
-void nsim_fib_destroy(struct nsim_fib_data *data)
+int nsim_fib_init(void)
 {
-	unregister_fib_notifier(&data->fib_nb);
-	kfree(data);
+	int err;
+
+	err = register_pernet_subsys(&nsim_fib_net_ops);
+	if (err < 0) {
+		pr_err("Failed to register pernet subsystem\n");
+		goto err_out;
+	}
+
+	err = register_fib_notifier(&nsim_fib_nb, nsim_fib_dump_inconsistent);
+	if (err < 0) {
+		pr_err("Failed to register fib notifier\n");
+		goto err_out;
+	}
+
+err_out:
+	return err;
 }
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index e5c8aa08e1cd..533a182eefca 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -370,12 +370,18 @@ static int __init nsim_module_init(void)
 	if (err)
 		goto err_dev_exit;
 
-	err = rtnl_link_register(&nsim_link_ops);
+	err = nsim_fib_init();
 	if (err)
 		goto err_bus_exit;
 
+	err = rtnl_link_register(&nsim_link_ops);
+	if (err)
+		goto err_fib_exit;
+
 	return 0;
 
+err_fib_exit:
+	nsim_fib_exit();
 err_bus_exit:
 	nsim_bus_exit();
 err_dev_exit:
@@ -386,6 +392,7 @@ static int __init nsim_module_init(void)
 static void __exit nsim_module_exit(void)
 {
 	rtnl_link_unregister(&nsim_link_ops);
+	nsim_fib_exit();
 	nsim_bus_exit();
 	nsim_dev_exit();
 }
diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
index 3f398797c2bc..f9253fe68c31 100644
--- a/drivers/net/netdevsim/netdevsim.h
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -168,12 +168,10 @@ int nsim_dev_port_add(struct nsim_bus_dev *nsim_bus_dev,
 int nsim_dev_port_del(struct nsim_bus_dev *nsim_bus_dev,
 		      unsigned int port_index);
 
-struct nsim_fib_data *nsim_fib_create(void);
-void nsim_fib_destroy(struct nsim_fib_data *fib_data);
-u64 nsim_fib_get_val(struct nsim_fib_data *fib_data,
-		     enum nsim_resource_id res_id, bool max);
-int nsim_fib_set_max(struct nsim_fib_data *fib_data,
-		     enum nsim_resource_id res_id, u64 val,
+int nsim_fib_init(void);
+void nsim_fib_exit(void);
+u64 nsim_fib_get_val(struct net *net, enum nsim_resource_id res_id, bool max);
+int nsim_fib_set_max(struct net *net, enum nsim_resource_id res_id, u64 val,
 		     struct netlink_ext_ack *extack);
 
 #if IS_ENABLED(CONFIG_XFRM_OFFLOAD)
-- 
2.20.1


From 1999af1b46e2a6dbf8c8b2eed919646da8e2a8bf Mon Sep 17 00:00:00 2001
From: Mohamad Heib <mohamadh@mellanox.com>
Date: Tue, 23 Apr 2019 21:13:48 +0300
Subject: [PATCH 22/28] net/mlx5e: ethtool, Avoid setting speed to 56GBASE when
 autoneg off

[ Upstream commit 5faf5b70c51dd9c9905bf8209e33cbd867486607 ]

Setting speed to 56GBASE is allowed only with auto-negotiation enabled.

This patch prevent setting speed to 56GBASE when auto-negotiation disabled.

Fixes: f62b8bb8f2d3 ("net/mlx5: Extend mlx5_core to support ConnectX-4 Ethernet functionality")
Signed-off-by: Mohamad Heib <mohamadh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 22d510176965..06f9bd6a45e3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1060,6 +1060,14 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 	link_modes = autoneg == AUTONEG_ENABLE ? ethtool2ptys_adver_func(adver) :
 		mlx5e_port_speed2linkmodes(mdev, speed, !ext);
 
+	if ((link_modes & MLX5E_PROT_MASK(MLX5E_56GBASE_R4)) &&
+	    autoneg != AUTONEG_ENABLE) {
+		netdev_err(priv->netdev, "%s: 56G link speed requires autoneg enabled\n",
+			   __func__);
+		err = -EINVAL;
+		goto out;
+	}
+
 	link_modes = link_modes & eproto.cap;
 	if (!link_modes) {
 		netdev_err(priv->netdev, "%s: Not supported link mode(s) requested",
-- 
2.20.1


From 8db3ffeff205ae621db895ada66a60cdfa698632 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Wed, 7 Aug 2019 15:59:06 +0300
Subject: [PATCH 23/28] net/mlx5e: Fix false negative indication on tx reporter
 CQE recovery

[ Upstream commit d9a2fcf53c76a7edb2bcf99e94507935561a83d5 ]

Remove wrong error return value when SQ is not in error state.
CQE recovery on TX reporter queries the sq state. If the sq is not in
error state, the sq is either in ready or reset state. Ready state is
good state which doesn't require recovery and reset state is a temporal
state which ends in ready state. With this patch, CQE recovery in this
scenario is successful.

Fixes: de8650a82071 ("net/mlx5e: Add tx reporter support")
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index f3d98748b211..b307234b4e05 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -86,10 +86,8 @@ static int mlx5e_tx_reporter_err_cqe_recover(struct mlx5e_txqsq *sq)
 		return err;
 	}
 
-	if (state != MLX5_SQC_STATE_ERR) {
-		netdev_err(dev, "SQ 0x%x not in ERROR state\n", sq->sqn);
-		return -EINVAL;
-	}
+	if (state != MLX5_SQC_STATE_ERR)
+		return 0;
 
 	mlx5e_tx_disable_queue(sq->txq);
 
-- 
2.20.1


From 7838429e071e2450966dd4c90a2c4efb3d461436 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Thu, 8 Aug 2019 15:55:48 +0300
Subject: [PATCH 24/28] net/mlx5e: Remove redundant check in CQE recovery flow
 of tx reporter

[ Upstream commit a4e508cab623951dc4754f346e5673714f3bbade ]

Remove check of recovery bit, in the beginning of the CQE recovery
function. This test is already performed right before the reporter
is invoked, when CQE error is detected.

Fixes: de8650a82071 ("net/mlx5e: Add tx reporter support")
Signed-off-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index b307234b4e05..c1caf14bc334 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -76,9 +76,6 @@ static int mlx5e_tx_reporter_err_cqe_recover(struct mlx5e_txqsq *sq)
 	u8 state;
 	int err;
 
-	if (!test_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state))
-		return 0;
-
 	err = mlx5_core_query_sq_state(mdev, sq->sqn, &state);
 	if (err) {
 		netdev_err(dev, "Failed to query SQ 0x%x state. err = %d\n",
-- 
2.20.1


From c0ac6e8770ba9f6f49e05bb6dadf1ff4dfdef3aa Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Fri, 5 Jul 2019 17:59:28 +0300
Subject: [PATCH 25/28] net/mlx5e: Use flow keys dissector to parse packets for
 ARFS

[ Upstream commit 405b93eb764367a670e729da18e54dc42db32620 ]

The current ARFS code relies on certain fields to be set in the SKB
(e.g. transport_header) and extracts IP addresses and ports by custom
code that parses the packet. The necessary SKB fields, however, are not
always set at that point, which leads to an out-of-bounds access. Use
skb_flow_dissect_flow_keys() to get the necessary information reliably,
fix the out-of-bounds access and reuse the code.

Fixes: 18c908e477dc ("net/mlx5e: Add accelerated RFS support")
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en_arfs.c | 97 +++++++------------
 1 file changed, 34 insertions(+), 63 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
index 8657e0f26995..2c75b2752f58 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
@@ -437,12 +437,6 @@ arfs_hash_bucket(struct arfs_table *arfs_t, __be16 src_port,
 	return &arfs_t->rules_hash[bucket_idx];
 }
 
-static u8 arfs_get_ip_proto(const struct sk_buff *skb)
-{
-	return (skb->protocol == htons(ETH_P_IP)) ?
-		ip_hdr(skb)->protocol : ipv6_hdr(skb)->nexthdr;
-}
-
 static struct arfs_table *arfs_get_table(struct mlx5e_arfs_tables *arfs,
 					 u8 ip_proto, __be16 etype)
 {
@@ -602,31 +596,9 @@ static void arfs_handle_work(struct work_struct *work)
 	arfs_may_expire_flow(priv);
 }
 
-/* return L4 destination port from ip4/6 packets */
-static __be16 arfs_get_dst_port(const struct sk_buff *skb)
-{
-	char *transport_header;
-
-	transport_header = skb_transport_header(skb);
-	if (arfs_get_ip_proto(skb) == IPPROTO_TCP)
-		return ((struct tcphdr *)transport_header)->dest;
-	return ((struct udphdr *)transport_header)->dest;
-}
-
-/* return L4 source port from ip4/6 packets */
-static __be16 arfs_get_src_port(const struct sk_buff *skb)
-{
-	char *transport_header;
-
-	transport_header = skb_transport_header(skb);
-	if (arfs_get_ip_proto(skb) == IPPROTO_TCP)
-		return ((struct tcphdr *)transport_header)->source;
-	return ((struct udphdr *)transport_header)->source;
-}
-
 static struct arfs_rule *arfs_alloc_rule(struct mlx5e_priv *priv,
 					 struct arfs_table *arfs_t,
-					 const struct sk_buff *skb,
+					 const struct flow_keys *fk,
 					 u16 rxq, u32 flow_id)
 {
 	struct arfs_rule *rule;
@@ -641,19 +613,19 @@ static struct arfs_rule *arfs_alloc_rule(struct mlx5e_priv *priv,
 	INIT_WORK(&rule->arfs_work, arfs_handle_work);
 
 	tuple = &rule->tuple;
-	tuple->etype = skb->protocol;
+	tuple->etype = fk->basic.n_proto;
+	tuple->ip_proto = fk->basic.ip_proto;
 	if (tuple->etype == htons(ETH_P_IP)) {
-		tuple->src_ipv4 = ip_hdr(skb)->saddr;
-		tuple->dst_ipv4 = ip_hdr(skb)->daddr;
+		tuple->src_ipv4 = fk->addrs.v4addrs.src;
+		tuple->dst_ipv4 = fk->addrs.v4addrs.dst;
 	} else {
-		memcpy(&tuple->src_ipv6, &ipv6_hdr(skb)->saddr,
+		memcpy(&tuple->src_ipv6, &fk->addrs.v6addrs.src,
 		       sizeof(struct in6_addr));
-		memcpy(&tuple->dst_ipv6, &ipv6_hdr(skb)->daddr,
+		memcpy(&tuple->dst_ipv6, &fk->addrs.v6addrs.dst,
 		       sizeof(struct in6_addr));
 	}
-	tuple->ip_proto = arfs_get_ip_proto(skb);
-	tuple->src_port = arfs_get_src_port(skb);
-	tuple->dst_port = arfs_get_dst_port(skb);
+	tuple->src_port = fk->ports.src;
+	tuple->dst_port = fk->ports.dst;
 
 	rule->flow_id = flow_id;
 	rule->filter_id = priv->fs.arfs.last_filter_id++ % RPS_NO_FILTER;
@@ -664,37 +636,33 @@ static struct arfs_rule *arfs_alloc_rule(struct mlx5e_priv *priv,
 	return rule;
 }
 
-static bool arfs_cmp_ips(struct arfs_tuple *tuple,
-			 const struct sk_buff *skb)
+static bool arfs_cmp(const struct arfs_tuple *tuple, const struct flow_keys *fk)
 {
-	if (tuple->etype == htons(ETH_P_IP) &&
-	    tuple->src_ipv4 == ip_hdr(skb)->saddr &&
-	    tuple->dst_ipv4 == ip_hdr(skb)->daddr)
-		return true;
-	if (tuple->etype == htons(ETH_P_IPV6) &&
-	    (!memcmp(&tuple->src_ipv6, &ipv6_hdr(skb)->saddr,
-		     sizeof(struct in6_addr))) &&
-	    (!memcmp(&tuple->dst_ipv6, &ipv6_hdr(skb)->daddr,
-		     sizeof(struct in6_addr))))
-		return true;
+	if (tuple->src_port != fk->ports.src || tuple->dst_port != fk->ports.dst)
+		return false;
+	if (tuple->etype != fk->basic.n_proto)
+		return false;
+	if (tuple->etype == htons(ETH_P_IP))
+		return tuple->src_ipv4 == fk->addrs.v4addrs.src &&
+		       tuple->dst_ipv4 == fk->addrs.v4addrs.dst;
+	if (tuple->etype == htons(ETH_P_IPV6))
+		return !memcmp(&tuple->src_ipv6, &fk->addrs.v6addrs.src,
+			       sizeof(struct in6_addr)) &&
+		       !memcmp(&tuple->dst_ipv6, &fk->addrs.v6addrs.dst,
+			       sizeof(struct in6_addr));
 	return false;
 }
 
 static struct arfs_rule *arfs_find_rule(struct arfs_table *arfs_t,
-					const struct sk_buff *skb)
+					const struct flow_keys *fk)
 {
 	struct arfs_rule *arfs_rule;
 	struct hlist_head *head;
-	__be16 src_port = arfs_get_src_port(skb);
-	__be16 dst_port = arfs_get_dst_port(skb);
 
-	head = arfs_hash_bucket(arfs_t, src_port, dst_port);
+	head = arfs_hash_bucket(arfs_t, fk->ports.src, fk->ports.dst);
 	hlist_for_each_entry(arfs_rule, head, hlist) {
-		if (arfs_rule->tuple.src_port == src_port &&
-		    arfs_rule->tuple.dst_port == dst_port &&
-		    arfs_cmp_ips(&arfs_rule->tuple, skb)) {
+		if (arfs_cmp(&arfs_rule->tuple, fk))
 			return arfs_rule;
-		}
 	}
 
 	return NULL;
@@ -707,20 +675,24 @@ int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 	struct mlx5e_arfs_tables *arfs = &priv->fs.arfs;
 	struct arfs_table *arfs_t;
 	struct arfs_rule *arfs_rule;
+	struct flow_keys fk;
+
+	if (!skb_flow_dissect_flow_keys(skb, &fk, 0))
+		return -EPROTONOSUPPORT;
 
-	if (skb->protocol != htons(ETH_P_IP) &&
-	    skb->protocol != htons(ETH_P_IPV6))
+	if (fk.basic.n_proto != htons(ETH_P_IP) &&
+	    fk.basic.n_proto != htons(ETH_P_IPV6))
 		return -EPROTONOSUPPORT;
 
 	if (skb->encapsulation)
 		return -EPROTONOSUPPORT;
 
-	arfs_t = arfs_get_table(arfs, arfs_get_ip_proto(skb), skb->protocol);
+	arfs_t = arfs_get_table(arfs, fk.basic.ip_proto, fk.basic.n_proto);
 	if (!arfs_t)
 		return -EPROTONOSUPPORT;
 
 	spin_lock_bh(&arfs->arfs_lock);
-	arfs_rule = arfs_find_rule(arfs_t, skb);
+	arfs_rule = arfs_find_rule(arfs_t, &fk);
 	if (arfs_rule) {
 		if (arfs_rule->rxq == rxq_index) {
 			spin_unlock_bh(&arfs->arfs_lock);
@@ -728,8 +700,7 @@ int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 		}
 		arfs_rule->rxq = rxq_index;
 	} else {
-		arfs_rule = arfs_alloc_rule(priv, arfs_t, skb,
-					    rxq_index, flow_id);
+		arfs_rule = arfs_alloc_rule(priv, arfs_t, &fk, rxq_index, flow_id);
 		if (!arfs_rule) {
 			spin_unlock_bh(&arfs->arfs_lock);
 			return -ENOMEM;
-- 
2.20.1


From caa8975646dae312bdc5bf6755cb1c697e8a3b48 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 7 Aug 2019 17:03:59 -0700
Subject: [PATCH 26/28] net/tls: prevent skb_orphan() from leaking TLS plain
 text with offload

[ Upstream commit 414776621d1006e57e80e6db7fdc3837897aaa64 ]

sk_validate_xmit_skb() and drivers depend on the sk member of
struct sk_buff to identify segments requiring encryption.
Any operation which removes or does not preserve the original TLS
socket such as skb_orphan() or skb_clone() will cause clear text
leaks.

Make the TCP socket underlying an offloaded TLS connection
mark all skbs as decrypted, if TLS TX is in offload mode.
Then in sk_validate_xmit_skb() catch skbs which have no socket
(or a socket with no validation) and decrypted flag set.

Note that CONFIG_SOCK_VALIDATE_XMIT, CONFIG_TLS_DEVICE and
sk->sk_validate_xmit_skb are slightly interchangeable right now,
they all imply TLS offload. The new checks are guarded by
CONFIG_TLS_DEVICE because that's the option guarding the
sk_buff->decrypted member.

Second, smaller issue with orphaning is that it breaks
the guarantee that packets will be delivered to device
queues in-order. All TLS offload drivers depend on that
scheduling property. This means skb_orphan_partial()'s
trick of preserving partial socket references will cause
issues in the drivers. We need a full orphan, and as a
result netem delay/throttling will cause all TLS offload
skbs to be dropped.

Reusing the sk_buff->decrypted flag also protects from
leaking clear text when incoming, decrypted skb is redirected
(e.g. by TC).

See commit 0608c69c9a80 ("bpf: sk_msg, sock{map|hash} redirect
through ULP") for justification why the internal flag is safe.
The only location which could leak the flag in is tcp_bpf_sendmsg(),
which is taken care of by clearing the previously unused bit.

v2:
 - remove superfluous decrypted mark copy (Willem);
 - remove the stale doc entry (Boris);
 - rely entirely on EOR marking to prevent coalescing (Boris);
 - use an internal sendpages flag instead of marking the socket
   (Boris).
v3 (Willem):
 - reorganize the can_skb_orphan_partial() condition;
 - fix the flag leak-in through tcp_bpf_sendmsg.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/tls-offload.rst | 18 ------------------
 include/linux/skbuff.h                   |  8 ++++++++
 include/linux/socket.h                   |  3 +++
 include/net/sock.h                       | 10 +++++++++-
 net/core/sock.c                          | 19 ++++++++++++++-----
 net/ipv4/tcp.c                           |  3 +++
 net/ipv4/tcp_bpf.c                       |  6 +++++-
 net/ipv4/tcp_output.c                    |  3 +++
 net/tls/tls_device.c                     |  9 +++++++--
 9 files changed, 52 insertions(+), 27 deletions(-)

diff --git a/Documentation/networking/tls-offload.rst b/Documentation/networking/tls-offload.rst
index cb85af559dff..178f4104f5cf 100644
--- a/Documentation/networking/tls-offload.rst
+++ b/Documentation/networking/tls-offload.rst
@@ -445,24 +445,6 @@ These flags will be acted upon accordingly by the core ``ktls`` code.
 TLS device feature flags only control adding of new TLS connection
 offloads, old connections will remain active after flags are cleared.
 
-Known bugs
-==========
-
-skb_orphan() leaks clear text
------------------------------
-
-Currently drivers depend on the :c:member:`sk` member of
-:c:type:`struct sk_buff <sk_buff>` to identify segments requiring
-encryption. Any operation which removes or does not preserve the socket
-association such as :c:func:`skb_orphan` or :c:func:`skb_clone`
-will cause the driver to miss the packets and lead to clear text leaks.
-
-Redirects leak clear text
--------------------------
-
-In the RX direction, if segment has already been decrypted by the device
-and it gets redirected or mirrored - clear text will be transmitted out.
-
 .. _pre_tls_data:
 
 Transmission of pre-TLS data
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 056f557d5194..64fa59b2c8d5 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1358,6 +1358,14 @@ static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from)
 	to->l4_hash = from->l4_hash;
 };
 
+static inline void skb_copy_decrypted(struct sk_buff *to,
+				      const struct sk_buff *from)
+{
+#ifdef CONFIG_TLS_DEVICE
+	to->decrypted = from->decrypted;
+#endif
+}
+
 #ifdef NET_SKBUFF_DATA_USES_OFFSET
 static inline unsigned char *skb_end_pointer(const struct sk_buff *skb)
 {
diff --git a/include/linux/socket.h b/include/linux/socket.h
index b57cd8bf96e2..810d5ec0ada3 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -291,6 +291,9 @@ struct ucred {
 #define MSG_BATCH	0x40000 /* sendmmsg(): more messages coming */
 #define MSG_EOF         MSG_FIN
 #define MSG_NO_SHARED_FRAGS 0x80000 /* sendpage() internal : page frags are not shared */
+#define MSG_SENDPAGE_DECRYPTED	0x100000 /* sendpage() internal : page may carry
+					  * plain text and require encryption
+					  */
 
 #define MSG_ZEROCOPY	0x4000000	/* Use user data in kernel path */
 #define MSG_FASTOPEN	0x20000000	/* Send data in TCP SYN */
diff --git a/include/net/sock.h b/include/net/sock.h
index 6cbc16136357..526de911cd91 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2482,6 +2482,7 @@ static inline bool sk_fullsock(const struct sock *sk)
 
 /* Checks if this SKB belongs to an HW offloaded socket
  * and whether any SW fallbacks are required based on dev.
+ * Check decrypted mark in case skb_orphan() cleared socket.
  */
 static inline struct sk_buff *sk_validate_xmit_skb(struct sk_buff *skb,
 						   struct net_device *dev)
@@ -2489,8 +2490,15 @@ static inline struct sk_buff *sk_validate_xmit_skb(struct sk_buff *skb,
 #ifdef CONFIG_SOCK_VALIDATE_XMIT
 	struct sock *sk = skb->sk;
 
-	if (sk && sk_fullsock(sk) && sk->sk_validate_xmit_skb)
+	if (sk && sk_fullsock(sk) && sk->sk_validate_xmit_skb) {
 		skb = sk->sk_validate_xmit_skb(sk, dev, skb);
+#ifdef CONFIG_TLS_DEVICE
+	} else if (unlikely(skb->decrypted)) {
+		pr_warn_ratelimited("unencrypted skb with no associated socket - dropping\n");
+		kfree_skb(skb);
+		skb = NULL;
+#endif
+	}
 #endif
 
 	return skb;
diff --git a/net/core/sock.c b/net/core/sock.c
index aa4a00d381e3..df7b38b60164 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1988,6 +1988,19 @@ void skb_set_owner_w(struct sk_buff *skb, struct sock *sk)
 }
 EXPORT_SYMBOL(skb_set_owner_w);
 
+static bool can_skb_orphan_partial(const struct sk_buff *skb)
+{
+#ifdef CONFIG_TLS_DEVICE
+	/* Drivers depend on in-order delivery for crypto offload,
+	 * partial orphan breaks out-of-order-OK logic.
+	 */
+	if (skb->decrypted)
+		return false;
+#endif
+	return (skb->destructor == sock_wfree ||
+		(IS_ENABLED(CONFIG_INET) && skb->destructor == tcp_wfree));
+}
+
 /* This helper is used by netem, as it can hold packets in its
  * delay queue. We want to allow the owner socket to send more
  * packets, as if they were already TX completed by a typical driver.
@@ -1999,11 +2012,7 @@ void skb_orphan_partial(struct sk_buff *skb)
 	if (skb_is_tcp_pure_ack(skb))
 		return;
 
-	if (skb->destructor == sock_wfree
-#ifdef CONFIG_INET
-	    || skb->destructor == tcp_wfree
-#endif
-		) {
+	if (can_skb_orphan_partial(skb)) {
 		struct sock *sk = skb->sk;
 
 		if (refcount_inc_not_zero(&sk->sk_refcnt)) {
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 5264f064a87e..b30f7f877181 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -984,6 +984,9 @@ ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
 			if (!skb)
 				goto wait_for_memory;
 
+#ifdef CONFIG_TLS_DEVICE
+			skb->decrypted = !!(flags & MSG_SENDPAGE_DECRYPTED);
+#endif
 			skb_entail(sk, skb);
 			copy = size_goal;
 		}
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 3d1e15401384..8a56e09cfb0e 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -398,10 +398,14 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,
 static int tcp_bpf_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 {
 	struct sk_msg tmp, *msg_tx = NULL;
-	int flags = msg->msg_flags | MSG_NO_SHARED_FRAGS;
 	int copied = 0, err = 0;
 	struct sk_psock *psock;
 	long timeo;
+	int flags;
+
+	/* Don't let internal do_tcp_sendpages() flags through */
+	flags = (msg->msg_flags & ~MSG_SENDPAGE_DECRYPTED);
+	flags |= MSG_NO_SHARED_FRAGS;
 
 	psock = sk_psock_get(sk);
 	if (unlikely(!psock))
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 7d0be046cbc1..359d298348c7 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1318,6 +1318,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
 	buff = sk_stream_alloc_skb(sk, nsize, gfp, true);
 	if (!buff)
 		return -ENOMEM; /* We'll just try again later. */
+	skb_copy_decrypted(buff, skb);
 
 	sk->sk_wmem_queued += buff->truesize;
 	sk_mem_charge(sk, buff->truesize);
@@ -1872,6 +1873,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
 	buff = sk_stream_alloc_skb(sk, 0, gfp, true);
 	if (unlikely(!buff))
 		return -ENOMEM;
+	skb_copy_decrypted(buff, skb);
 
 	sk->sk_wmem_queued += buff->truesize;
 	sk_mem_charge(sk, buff->truesize);
@@ -2141,6 +2143,7 @@ static int tcp_mtu_probe(struct sock *sk)
 	sk_mem_charge(sk, nskb->truesize);
 
 	skb = tcp_send_head(sk);
+	skb_copy_decrypted(nskb, skb);
 
 	TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(skb)->seq;
 	TCP_SKB_CB(nskb)->end_seq = TCP_SKB_CB(skb)->seq + probe_size;
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index eb8f24f420f0..4cfcce211c2f 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -342,9 +342,9 @@ static int tls_push_data(struct sock *sk,
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_prot_info *prot = &tls_ctx->prot_info;
 	struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx);
-	int tls_push_record_flags = flags | MSG_SENDPAGE_NOTLAST;
 	int more = flags & (MSG_SENDPAGE_NOTLAST | MSG_MORE);
 	struct tls_record_info *record = ctx->open_record;
+	int tls_push_record_flags;
 	struct page_frag *pfrag;
 	size_t orig_size = size;
 	u32 max_open_record_len;
@@ -359,6 +359,9 @@ static int tls_push_data(struct sock *sk,
 	if (sk->sk_err)
 		return -sk->sk_err;
 
+	flags |= MSG_SENDPAGE_DECRYPTED;
+	tls_push_record_flags = flags | MSG_SENDPAGE_NOTLAST;
+
 	timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
 	if (tls_is_partially_sent_record(tls_ctx)) {
 		rc = tls_push_partial_record(sk, tls_ctx, flags);
@@ -545,7 +548,9 @@ void tls_device_write_space(struct sock *sk, struct tls_context *ctx)
 		gfp_t sk_allocation = sk->sk_allocation;
 
 		sk->sk_allocation = GFP_ATOMIC;
-		tls_push_partial_record(sk, ctx, MSG_DONTWAIT | MSG_NOSIGNAL);
+		tls_push_partial_record(sk, ctx,
+					MSG_DONTWAIT | MSG_NOSIGNAL |
+					MSG_SENDPAGE_DECRYPTED);
 		sk->sk_allocation = sk_allocation;
 	}
 }
-- 
2.20.1


From 672317c5ad3d903cfbfef0e00ae52b739770666a Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 12 Aug 2019 21:20:02 +0200
Subject: [PATCH 27/28] net: phy: consider AN_RESTART status when reading link
 status

[ Upstream commit c36757eb9dee13681227ad3676d37f14b3a2b2af ]

After configuring and restarting aneg we immediately try to read the
link status. On some systems the PHY may not yet have cleared the
"aneg complete" and "link up" bits, resulting in a false link-up
signal. See [0] for a report.
Clause 22 and 45 both require the PHY to keep the AN_RESTART
bit set until the PHY actually starts auto-negotiation.
Let's consider this in the generic functions for reading link status.
The commit marked as fixed is the first one where the patch applies
cleanly.

[0] https://marc.info/?t=156518400300003&r=1&w=2

Fixes: c1164bb1a631 ("net: phy: check PMAPMD link status only in genphy_c45_read_link")
Tested-by: Yonglong Liu <liuyonglong@huawei.com>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/phy/phy-c45.c    | 14 ++++++++++++++
 drivers/net/phy/phy_device.c | 12 +++++++++++-
 2 files changed, 25 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c
index b9d4145781ca..58bb25e4af10 100644
--- a/drivers/net/phy/phy-c45.c
+++ b/drivers/net/phy/phy-c45.c
@@ -219,6 +219,20 @@ int genphy_c45_read_link(struct phy_device *phydev)
 	int val, devad;
 	bool link = true;
 
+	if (phydev->c45_ids.devices_in_package & MDIO_DEVS_AN) {
+		val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_CTRL1);
+		if (val < 0)
+			return val;
+
+		/* Autoneg is being started, therefore disregard current
+		 * link status and report link as down.
+		 */
+		if (val & MDIO_AN_CTRL1_RESTART) {
+			phydev->link = 0;
+			return 0;
+		}
+	}
+
 	while (mmd_mask && link) {
 		devad = __ffs(mmd_mask);
 		mmd_mask &= ~BIT(devad);
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index ffa402732aea..3af0af495cf1 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1708,7 +1708,17 @@ EXPORT_SYMBOL(genphy_aneg_done);
  */
 int genphy_update_link(struct phy_device *phydev)
 {
-	int status;
+	int status = 0, bmcr;
+
+	bmcr = phy_read(phydev, MII_BMCR);
+	if (bmcr < 0)
+		return bmcr;
+
+	/* Autoneg is being started, therefore disregard BMSR value and
+	 * report link as down.
+	 */
+	if (bmcr & BMCR_ANRESTART)
+		goto done;
 
 	/* The link state is latched low so that momentary link
 	 * drops can be detected. Do not double-read the status
-- 
2.20.1


From 710309cd6620963cee2221a1979d8a43ed1bebb8 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Mon, 12 Aug 2019 13:07:07 -0700
Subject: [PATCH 28/28] netlink: Fix nlmsg_parse as a wrapper for strict
 message parsing

[ Upstream commit d00ee64e1dcf09b3afefd1340f3e9eb637272714 ]

Eric reported a syzbot warning:

BUG: KMSAN: uninit-value in nh_valid_get_del_req+0x6f1/0x8c0 net/ipv4/nexthop.c:1510
CPU: 0 PID: 11812 Comm: syz-executor444 Not tainted 5.3.0-rc3+ #17
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x191/0x1f0 lib/dump_stack.c:113
 kmsan_report+0x162/0x2d0 mm/kmsan/kmsan_report.c:109
 __msan_warning+0x75/0xe0 mm/kmsan/kmsan_instr.c:294
 nh_valid_get_del_req+0x6f1/0x8c0 net/ipv4/nexthop.c:1510
 rtm_del_nexthop+0x1b1/0x610 net/ipv4/nexthop.c:1543
 rtnetlink_rcv_msg+0x115a/0x1580 net/core/rtnetlink.c:5223
 netlink_rcv_skb+0x431/0x620 net/netlink/af_netlink.c:2477
 rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:5241
 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
 netlink_unicast+0xf6c/0x1050 net/netlink/af_netlink.c:1328
 netlink_sendmsg+0x110f/0x1330 net/netlink/af_netlink.c:1917
 sock_sendmsg_nosec net/socket.c:637 [inline]
 sock_sendmsg net/socket.c:657 [inline]
 ___sys_sendmsg+0x14ff/0x1590 net/socket.c:2311
 __sys_sendmmsg+0x53a/0xae0 net/socket.c:2413
 __do_sys_sendmmsg net/socket.c:2442 [inline]
 __se_sys_sendmmsg+0xbd/0xe0 net/socket.c:2439
 __x64_sys_sendmmsg+0x56/0x70 net/socket.c:2439
 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:297
 entry_SYSCALL_64_after_hwframe+0x63/0xe7

The root cause is nlmsg_parse calling __nla_parse which means the
header struct size is not checked.

nlmsg_parse should be a wrapper around __nlmsg_parse with
NL_VALIDATE_STRICT for the validate argument very much like
nlmsg_parse_deprecated is for NL_VALIDATE_LIBERAL.

Fixes: 3de6440354465 ("netlink: re-add parse/validate functions in strict mode")
Reported-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 include/net/netlink.h | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/include/net/netlink.h b/include/net/netlink.h
index 395b4406f4b0..222af2046086 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -680,9 +680,8 @@ static inline int nlmsg_parse(const struct nlmsghdr *nlh, int hdrlen,
 			      const struct nla_policy *policy,
 			      struct netlink_ext_ack *extack)
 {
-	return __nla_parse(tb, maxtype, nlmsg_attrdata(nlh, hdrlen),
-			   nlmsg_attrlen(nlh, hdrlen), policy,
-			   NL_VALIDATE_STRICT, extack);
+	return __nlmsg_parse(nlh, hdrlen, tb, maxtype, policy,
+			     NL_VALIDATE_STRICT, extack);
 }
 
 /**
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Tue, Aug 20, 2019 at 04:01:55PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.19 and
> v5.2 -stable, respectively.

thanks, now queued up!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 90 bytes --]


Please queue up the following bug fixes for v4.19 and v5.2 -stable
respectively, thanks!

[-- Attachment #2: net_419.mbox --]
[-- Type: Application/Octet-Stream, Size: 15310 bytes --]

From 17a426eb88baf45c90c6806073ea1c3f5da445b9 Mon Sep 17 00:00:00 2001
From: Vakul Garg <vakul.garg@nxp.com>
Date: Mon, 10 Sep 2018 22:53:46 +0530
Subject: [PATCH 1/8] net/tls: Fixed return value when
 tls_complete_pending_work() fails

[ Upstream commit 150085791afb8054e11d2e080d4b9cd755dd7f69 ]

In tls_sw_sendmsg() and tls_sw_sendpage(), the variable 'ret' has
been set to return value of tls_complete_pending_work(). This allows
return of proper error code if tls_complete_pending_work() fails.

Fixes: 3c4d7559159b ("tls: kernel TLS support")
Signed-off-by: Vakul Garg <vakul.garg@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 6848a8196711..bbb2da70e870 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -354,7 +354,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
-	int ret = 0;
+	int ret;
 	int required_size;
 	long timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
 	bool eor = !(msg->msg_flags & MSG_MORE);
@@ -370,7 +370,8 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 
 	lock_sock(sk);
 
-	if (tls_complete_pending_work(sk, tls_ctx, msg->msg_flags, &timeo))
+	ret = tls_complete_pending_work(sk, tls_ctx, msg->msg_flags, &timeo);
+	if (ret)
 		goto send_end;
 
 	if (unlikely(msg->msg_controllen)) {
@@ -505,7 +506,7 @@ int tls_sw_sendpage(struct sock *sk, struct page *page,
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
-	int ret = 0;
+	int ret;
 	long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
 	bool eor;
 	size_t orig_size = size;
@@ -525,7 +526,8 @@ int tls_sw_sendpage(struct sock *sk, struct page *page,
 
 	sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
-	if (tls_complete_pending_work(sk, tls_ctx, flags, &timeo))
+	ret = tls_complete_pending_work(sk, tls_ctx, flags, &timeo);
+	if (ret)
 		goto sendpage_end;
 
 	/* Call the sk_stream functions to manage the sndbuf mem. */
-- 
2.20.1


From 27419d2611f46a12f77ded950ec7e4b79d1bbd98 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 9 Aug 2019 18:36:23 -0700
Subject: [PATCH 2/8] net/tls: swap sk_write_space on close

[ Upstream commit 57c722e932cfb82e9820bbaae1b1f7222ea97b52 ]

Now that we swap the original proto and clear the ULP pointer
on close we have to make sure no callback will try to access
the freed state. sk_write_space is not part of sk_prot, remember
to swap it.

Reported-by: syzbot+dcdc9deefaec44785f32@syzkaller.appspotmail.com
Fixes: 95fa145479fb ("bpf: sockmap/tls, close can race with map free")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 4c0ac79f82d4..f636aff11d51 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -301,6 +301,7 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
 #else
 	{
 #endif
+		sk->sk_write_space = ctx->sk_write_space;
 		tls_ctx_free(ctx);
 		ctx = NULL;
 	}
-- 
2.20.1


From 511b52bbe25acad5f88421afd7023128909da266 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Wed, 14 Aug 2019 05:31:54 +0000
Subject: [PATCH 3/8] net: tls, fix sk_write_space NULL write when tx disabled

[ Upstream commit d85f01775850a35eae47a0090839baf510c1ef12 ]

The ctx->sk_write_space pointer is only set when TLS tx mode is enabled.
When running without TX mode its a null pointer but we still set the
sk sk_write_space pointer on close().

Fix the close path to only overwrite sk->sk_write_space when the current
pointer is to the tls_write_space function indicating the tls module should
clean it up properly as well.

Reported-by: Hillf Danton <hdanton@sina.com>
Cc: Ying Xue <ying.xue@windriver.com>
Cc: Andrey Konovalov <andreyknvl@google.com>
Fixes: 57c722e932cfb ("net/tls: swap sk_write_space on close")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index f636aff11d51..3288bdff9889 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -301,7 +301,8 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
 #else
 	{
 #endif
-		sk->sk_write_space = ctx->sk_write_space;
+		if (sk->sk_write_space == tls_write_space)
+			sk->sk_write_space = ctx->sk_write_space;
 		tls_ctx_free(ctx);
 		ctx = NULL;
 	}
-- 
2.20.1


From 05f6759287dc11768c1da3ea0128f816110d65b3 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Tue, 20 Aug 2019 10:19:47 +0800
Subject: [PATCH 4/8] ipv6/addrconf: allow adding multicast addr if
 IFA_F_MCAUTOJOIN is set

[ Upstream commit f17f7648a49aa6728649ddf79bdbcac4f1970ce4 ]

In commit 93a714d6b53d ("multicast: Extend ip address command to enable
multicast group join/leave on") we added a new flag IFA_F_MCAUTOJOIN
to make user able to add multicast address on ethernet interface.

This works for IPv4, but not for IPv6. See the inet6_addr_add code.

static int inet6_addr_add()
{
	...
	if (cfg->ifa_flags & IFA_F_MCAUTOJOIN) {
		ipv6_mc_config(net->ipv6.mc_autojoin_sk, true...)
	}

	ifp = ipv6_add_addr(idev, cfg, true, extack); <- always fail with maddr
	if (!IS_ERR(ifp)) {
		...
	} else if (cfg->ifa_flags & IFA_F_MCAUTOJOIN) {
		ipv6_mc_config(net->ipv6.mc_autojoin_sk, false...)
	}
}

But in ipv6_add_addr() it will check the address type and reject multicast
address directly. So this feature is never worked for IPv6.

We should not remove the multicast address check totally in ipv6_add_addr(),
but could accept multicast address only when IFA_F_MCAUTOJOIN flag supplied.

v2: update commit description

Fixes: 93a714d6b53d ("multicast: Extend ip address command to enable multicast group join/leave on")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index c57efd5c5b38..49e2f6dac646 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -995,7 +995,8 @@ ipv6_add_addr(struct inet6_dev *idev, struct ifa6_config *cfg,
 	int err = 0;
 
 	if (addr_type == IPV6_ADDR_ANY ||
-	    addr_type & IPV6_ADDR_MULTICAST ||
+	    (addr_type & IPV6_ADDR_MULTICAST &&
+	     !(cfg->ifa_flags & IFA_F_MCAUTOJOIN)) ||
 	    (!(idev->dev->flags & IFF_LOOPBACK) &&
 	     addr_type & IPV6_ADDR_LOOPBACK))
 		return ERR_PTR(-EADDRNOTAVAIL);
-- 
2.20.1


From f5c105c2820b57ac4b729c19c6702f15eaf57b25 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 19 Jun 2019 10:50:24 -0700
Subject: [PATCH 5/8] ipv6: Default fib6_type to RTN_UNICAST when not set

[ Upstream commit c7036d97acd2527cef145b5ef9ad1a37ed21bbe6 ]

A user reported that routes are getting installed with type 0 (RTN_UNSPEC)
where before the routes were RTN_UNICAST. One example is from accel-ppp
which apparently still uses the ioctl interface and does not set
rtmsg_type. Another is the netlink interface where ipv6 does not require
rtm_type to be set (v4 does). Prior to the commit in the Fixes tag the
ipv6 stack converted type 0 to RTN_UNICAST, so restore that behavior.

Fixes: e8478e80e5a7 ("net/ipv6: Save route type in rt6_info")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 81220077d62f..c88586380134 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3109,7 +3109,7 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 	rt->fib6_metric = cfg->fc_metric;
 	rt->fib6_nh.nh_weight = 1;
 
-	rt->fib6_type = cfg->fc_type;
+	rt->fib6_type = cfg->fc_type ? : RTN_UNICAST;
 
 	/* We cannot add true routes via loopback here,
 	   they would result in kernel looping; promote them to reject routes
-- 
2.20.1


From a5be159bc7c8c1215412b6563cdaf89827e6f914 Mon Sep 17 00:00:00 2001
From: Jason Baron <jbaron@akamai.com>
Date: Mon, 19 Aug 2019 14:36:01 -0400
Subject: [PATCH 6/8] net/smc: make sure EPOLLOUT is raised

[ Upstream commit 4651d1802f7063e4d8c0bcad957f46ece0c04024 ]

Currently, we are only explicitly setting SOCK_NOSPACE on a write timeout
for non-blocking sockets. Epoll() edge-trigger mode relies on SOCK_NOSPACE
being set when -EAGAIN is returned to ensure that EPOLLOUT is raised.
Expand the setting of SOCK_NOSPACE to non-blocking sockets as well that can
use SO_SNDTIMEO to adjust their write timeout. This mirrors the behavior
that Eric Dumazet introduced for tcp sockets.

Signed-off-by: Jason Baron <jbaron@akamai.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Ursula Braun <ubraun@linux.ibm.com>
Cc: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/smc_tx.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index d8366ed51757..28361aef9982 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -75,13 +75,11 @@ static int smc_tx_wait(struct smc_sock *smc, int flags)
 	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 	struct smc_connection *conn = &smc->conn;
 	struct sock *sk = &smc->sk;
-	bool noblock;
 	long timeo;
 	int rc = 0;
 
 	/* similar to sk_stream_wait_memory */
 	timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
-	noblock = timeo ? false : true;
 	add_wait_queue(sk_sleep(sk), &wait);
 	while (1) {
 		sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
@@ -96,8 +94,8 @@ static int smc_tx_wait(struct smc_sock *smc, int flags)
 			break;
 		}
 		if (!timeo) {
-			if (noblock)
-				set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+			/* ensure EPOLLOUT is subsequently generated */
+			set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 			rc = -EAGAIN;
 			break;
 		}
-- 
2.20.1


From a140084b9d3e18c797697dfd8f724dcac192fb22 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 16 Aug 2019 21:26:22 -0700
Subject: [PATCH 7/8] tcp: make sure EPOLLOUT wont be missed

[ Upstream commit ef8d8ccdc216f797e66cb4a1372f5c4c285ce1e4 ]

As Jason Baron explained in commit 790ba4566c1a ("tcp: set SOCK_NOSPACE
under memory pressure"), it is crucial we properly set SOCK_NOSPACE
when needed.

However, Jason patch had a bug, because the 'nonblocking' status
as far as sk_stream_wait_memory() is concerned is governed
by MSG_DONTWAIT flag passed at sendmsg() time :

    long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);

So it is very possible that tcp sendmsg() calls sk_stream_wait_memory(),
and that sk_stream_wait_memory() returns -EAGAIN with SOCK_NOSPACE
cleared, if sk->sk_sndtimeo has been set to a small (but not zero)
value.

This patch removes the 'noblock' variable since we must always
set SOCK_NOSPACE if -EAGAIN is returned.

It also renames the do_nonblock label since we might reach this
code path even if we were in blocking mode.

Fixes: 790ba4566c1a ("tcp: set SOCK_NOSPACE under memory pressure")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jason Baron <jbaron@akamai.com>
Reported-by: Vladimir Rutsky  <rutsky@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Jason Baron <jbaron@akamai.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/stream.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/net/core/stream.c b/net/core/stream.c
index 7d329fb1f553..7f5eaa95a675 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -120,7 +120,6 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
 	int err = 0;
 	long vm_wait = 0;
 	long current_timeo = *timeo_p;
-	bool noblock = (*timeo_p ? false : true);
 	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 
 	if (sk_stream_memory_free(sk))
@@ -133,11 +132,8 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
 
 		if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
 			goto do_error;
-		if (!*timeo_p) {
-			if (noblock)
-				set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
-			goto do_nonblock;
-		}
+		if (!*timeo_p)
+			goto do_eagain;
 		if (signal_pending(current))
 			goto do_interrupted;
 		sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
@@ -169,7 +165,13 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
 do_error:
 	err = -EPIPE;
 	goto out;
-do_nonblock:
+do_eagain:
+	/* Make sure that whenever EAGAIN is returned, EPOLLOUT event can
+	 * be generated later.
+	 * When TCP receives ACK packets that make room, tcp_check_space()
+	 * only calls tcp_new_space() if SOCK_NOSPACE is set.
+	 */
+	set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 	err = -EAGAIN;
 	goto out;
 do_interrupted:
-- 
2.20.1


From 49674619919a1677b4812fa4fa2dbaccb8592bc0 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Thu, 22 Aug 2019 22:19:48 +0800
Subject: [PATCH 8/8] ipv4/icmp: fix rt dst dev null pointer dereference

[ Upstream commit e2c693934194fd3b4e795635934883354c06ebc9 ]

In __icmp_send() there is a possibility that the rt->dst.dev is NULL,
e,g, with tunnel collect_md mode, which will cause kernel crash.
Here is what the code path looks like, for GRE:

- ip6gre_tunnel_xmit
  - ip6gre_xmit_ipv4
    - __gre6_xmit
      - ip6_tnl_xmit
        - if skb->len - t->tun_hlen - eth_hlen > mtu; return -EMSGSIZE
    - icmp_send
      - net = dev_net(rt->dst.dev); <-- here

The reason is __metadata_dst_init() init dst->dev to NULL by default.
We could not fix it in __metadata_dst_init() as there is no dev supplied.
On the other hand, the reason we need rt->dst.dev is to get the net.
So we can just try get it from skb->dev when rt->dst.dev is NULL.

v4: Julian Anastasov remind skb->dev also could be NULL. We'd better
still use dst.dev and do a check to avoid crash.

v3: No changes.

v2: fix the issue in __icmp_send() instead of updating shared dst dev
in {ip_md, ip6}_tunnel_xmit.

Fixes: c8b34e680a09 ("ip_tunnel: Add tnl_update_pmtu in ip_md_tunnel_xmit")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Julian Anastasov <ja@ssi.bg>
Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/icmp.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index ad75c468ecfb..0167e23d1c8f 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -587,7 +587,13 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
 
 	if (!rt)
 		goto out;
-	net = dev_net(rt->dst.dev);
+
+	if (rt->dst.dev)
+		net = dev_net(rt->dst.dev);
+	else if (skb_in->dev)
+		net = dev_net(skb_in->dev);
+	else
+		goto out;
 
 	/*
 	 *	Find the original header. It is expected to be valid, of course.
-- 
2.20.1


[-- Attachment #3: net_52.mbox --]
[-- Type: Application/Octet-Stream, Size: 20390 bytes --]

From a300648a597baf1ff74863bed8dd27c768aa1d47 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Tue, 20 Aug 2019 10:19:47 +0800
Subject: [PATCH 01/10] ipv6/addrconf: allow adding multicast addr if
 IFA_F_MCAUTOJOIN is set

[ Upstream commit f17f7648a49aa6728649ddf79bdbcac4f1970ce4 ]

In commit 93a714d6b53d ("multicast: Extend ip address command to enable
multicast group join/leave on") we added a new flag IFA_F_MCAUTOJOIN
to make user able to add multicast address on ethernet interface.

This works for IPv4, but not for IPv6. See the inet6_addr_add code.

static int inet6_addr_add()
{
	...
	if (cfg->ifa_flags & IFA_F_MCAUTOJOIN) {
		ipv6_mc_config(net->ipv6.mc_autojoin_sk, true...)
	}

	ifp = ipv6_add_addr(idev, cfg, true, extack); <- always fail with maddr
	if (!IS_ERR(ifp)) {
		...
	} else if (cfg->ifa_flags & IFA_F_MCAUTOJOIN) {
		ipv6_mc_config(net->ipv6.mc_autojoin_sk, false...)
	}
}

But in ipv6_add_addr() it will check the address type and reject multicast
address directly. So this feature is never worked for IPv6.

We should not remove the multicast address check totally in ipv6_add_addr(),
but could accept multicast address only when IFA_F_MCAUTOJOIN flag supplied.

v2: update commit description

Fixes: 93a714d6b53d ("multicast: Extend ip address command to enable multicast group join/leave on")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 081bb517e40d..2454fce6fbfa 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1045,7 +1045,8 @@ ipv6_add_addr(struct inet6_dev *idev, struct ifa6_config *cfg,
 	int err = 0;
 
 	if (addr_type == IPV6_ADDR_ANY ||
-	    addr_type & IPV6_ADDR_MULTICAST ||
+	    (addr_type & IPV6_ADDR_MULTICAST &&
+	     !(cfg->ifa_flags & IFA_F_MCAUTOJOIN)) ||
 	    (!(idev->dev->flags & IFF_LOOPBACK) &&
 	     !netif_is_l3_master(idev->dev) &&
 	     addr_type & IPV6_ADDR_LOOPBACK))
-- 
2.20.1


From 75033ba359683a6bf1b41b585852b1a0cd3e069e Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Tue, 13 Aug 2019 00:46:01 +0200
Subject: [PATCH 02/10] ipv6: Fix return value of ipv6_mc_may_pull() for
 malformed packets

Commit ba5ea614622d ("bridge: simplify ip_mc_check_igmp() and
ipv6_mc_check_mld() calls") replaces direct calls to pskb_may_pull()
in br_ipv6_multicast_mld2_report() with calls to ipv6_mc_may_pull(),
that returns -EINVAL on buffers too short to be valid IPv6 packets,
while maintaining the previous handling of the return code.

This leads to the direct opposite of the intended effect: if the
packet is malformed, -EINVAL evaluates as true, and we'll happily
proceed with the processing.

Return 0 if the packet is too short, in the same way as this was
fixed for IPv4 by commit 083b78a9ed64 ("ip: fix ip_mc_may_pull()
return value").

I don't have a reproducer for this, unlike the one referred to by
the IPv4 commit, but this is clearly broken.

Fixes: ba5ea614622d ("bridge: simplify ip_mc_check_igmp() and ipv6_mc_check_mld() calls")
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Acked-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/addrconf.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index becdad576859..3f62b347b04a 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -206,7 +206,7 @@ static inline int ipv6_mc_may_pull(struct sk_buff *skb,
 				   unsigned int len)
 {
 	if (skb_transport_offset(skb) + ipv6_transport_len(skb) < len)
-		return -EINVAL;
+		return 0;
 
 	return pskb_may_pull(skb, len);
 }
-- 
2.20.1


From 1df551f4f383704a84b14e624f2703397ec77977 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Wed, 21 Aug 2019 16:41:23 +0200
Subject: [PATCH 03/10] net: cpsw: fix NULL pointer exception in the probe
 error path

[ Upstream commit 2d683eaaeeb9d33d23674ae635e0ef1448523d18 ]

In certain cases when the probe function fails the error path calls
cpsw_remove_dt() before calling platform_set_drvdata(). This is an
issue as cpsw_remove_dt() uses platform_get_drvdata() to retrieve the
cpsw_common data and leds to a NULL pointer exception. This patches
fixes it by calling platform_set_drvdata() earlier in the probe.

Fixes: 83a8471ba255 ("net: ethernet: ti: cpsw: refactor probe to group common hw initialization")
Reported-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 4e3026f9abed..962dbb3acd77 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -2372,6 +2372,7 @@ static int cpsw_probe(struct platform_device *pdev)
 	if (!cpsw)
 		return -ENOMEM;
 
+	platform_set_drvdata(pdev, cpsw);
 	cpsw->dev = dev;
 
 	mode = devm_gpiod_get_array_optional(dev, "mode", GPIOD_OUT_LOW);
@@ -2476,7 +2477,6 @@ static int cpsw_probe(struct platform_device *pdev)
 		goto clean_cpts;
 	}
 
-	platform_set_drvdata(pdev, ndev);
 	priv = netdev_priv(ndev);
 	priv->cpsw = cpsw;
 	priv->ndev = ndev;
-- 
2.20.1


From 26cc089066b7cf33204609050dd831d9d2d3f462 Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Tue, 20 Aug 2019 13:52:47 +0800
Subject: [PATCH 04/10] net: fix __ip_mc_inc_group usage

[ Upstream commit a1c4cd67840ef80f6ca5f73326fa9a6719303a95 ]

in ip_mc_inc_group, memory allocation flag, not mcast mode, is expected
by __ip_mc_inc_group

similar issue in __ip_mc_join_group, both mcase mode and gfp_t are needed
here, so use ____ip_mc_inc_group(...)

Fixes: 9fb20801dab4 ("net: Fix ip_mc_{dec,inc}_group allocation context")
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Zhang Yu <zhangyu31@baidu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/igmp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 85107bf812f2..b5b0834ec5ee 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -1474,7 +1474,7 @@ EXPORT_SYMBOL(__ip_mc_inc_group);
 
 void ip_mc_inc_group(struct in_device *in_dev, __be32 addr)
 {
-	__ip_mc_inc_group(in_dev, addr, MCAST_EXCLUDE);
+	__ip_mc_inc_group(in_dev, addr, GFP_KERNEL);
 }
 EXPORT_SYMBOL(ip_mc_inc_group);
 
@@ -2196,7 +2196,7 @@ static int __ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr,
 	iml->sflist = NULL;
 	iml->sfmode = mode;
 	rcu_assign_pointer(inet->mc_list, iml);
-	__ip_mc_inc_group(in_dev, addr, mode);
+	____ip_mc_inc_group(in_dev, addr, mode, GFP_KERNEL);
 	err = 0;
 done:
 	return err;
-- 
2.20.1


From b671f0dc5ed6ae23512fb0854460c10226e24244 Mon Sep 17 00:00:00 2001
From: Jason Baron <jbaron@akamai.com>
Date: Mon, 19 Aug 2019 14:36:01 -0400
Subject: [PATCH 05/10] net/smc: make sure EPOLLOUT is raised

[ Upstream commit 4651d1802f7063e4d8c0bcad957f46ece0c04024 ]

Currently, we are only explicitly setting SOCK_NOSPACE on a write timeout
for non-blocking sockets. Epoll() edge-trigger mode relies on SOCK_NOSPACE
being set when -EAGAIN is returned to ensure that EPOLLOUT is raised.
Expand the setting of SOCK_NOSPACE to non-blocking sockets as well that can
use SO_SNDTIMEO to adjust their write timeout. This mirrors the behavior
that Eric Dumazet introduced for tcp sockets.

Signed-off-by: Jason Baron <jbaron@akamai.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Ursula Braun <ubraun@linux.ibm.com>
Cc: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/smc_tx.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index f0de323d15d6..6c8f09c1ce51 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -76,13 +76,11 @@ static int smc_tx_wait(struct smc_sock *smc, int flags)
 	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 	struct smc_connection *conn = &smc->conn;
 	struct sock *sk = &smc->sk;
-	bool noblock;
 	long timeo;
 	int rc = 0;
 
 	/* similar to sk_stream_wait_memory */
 	timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
-	noblock = timeo ? false : true;
 	add_wait_queue(sk_sleep(sk), &wait);
 	while (1) {
 		sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
@@ -97,8 +95,8 @@ static int smc_tx_wait(struct smc_sock *smc, int flags)
 			break;
 		}
 		if (!timeo) {
-			if (noblock)
-				set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+			/* ensure EPOLLOUT is subsequently generated */
+			set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 			rc = -EAGAIN;
 			break;
 		}
-- 
2.20.1


From d29619a842f2759aa1ad0de7ff5f3f1ad199c7ec Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 16 Aug 2019 21:26:22 -0700
Subject: [PATCH 06/10] tcp: make sure EPOLLOUT wont be missed

[ Upstream commit ef8d8ccdc216f797e66cb4a1372f5c4c285ce1e4 ]

As Jason Baron explained in commit 790ba4566c1a ("tcp: set SOCK_NOSPACE
under memory pressure"), it is crucial we properly set SOCK_NOSPACE
when needed.

However, Jason patch had a bug, because the 'nonblocking' status
as far as sk_stream_wait_memory() is concerned is governed
by MSG_DONTWAIT flag passed at sendmsg() time :

    long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);

So it is very possible that tcp sendmsg() calls sk_stream_wait_memory(),
and that sk_stream_wait_memory() returns -EAGAIN with SOCK_NOSPACE
cleared, if sk->sk_sndtimeo has been set to a small (but not zero)
value.

This patch removes the 'noblock' variable since we must always
set SOCK_NOSPACE if -EAGAIN is returned.

It also renames the do_nonblock label since we might reach this
code path even if we were in blocking mode.

Fixes: 790ba4566c1a ("tcp: set SOCK_NOSPACE under memory pressure")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jason Baron <jbaron@akamai.com>
Reported-by: Vladimir Rutsky  <rutsky@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Jason Baron <jbaron@akamai.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/stream.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/net/core/stream.c b/net/core/stream.c
index e94bb02a5629..4f1d4aa5fb38 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -120,7 +120,6 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
 	int err = 0;
 	long vm_wait = 0;
 	long current_timeo = *timeo_p;
-	bool noblock = (*timeo_p ? false : true);
 	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 
 	if (sk_stream_memory_free(sk))
@@ -133,11 +132,8 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
 
 		if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
 			goto do_error;
-		if (!*timeo_p) {
-			if (noblock)
-				set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
-			goto do_nonblock;
-		}
+		if (!*timeo_p)
+			goto do_eagain;
 		if (signal_pending(current))
 			goto do_interrupted;
 		sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
@@ -169,7 +165,13 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
 do_error:
 	err = -EPIPE;
 	goto out;
-do_nonblock:
+do_eagain:
+	/* Make sure that whenever EAGAIN is returned, EPOLLOUT event can
+	 * be generated later.
+	 * When TCP receives ACK packets that make room, tcp_check_space()
+	 * only calls tcp_new_space() if SOCK_NOSPACE is set.
+	 */
+	set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 	err = -EAGAIN;
 	goto out;
 do_interrupted:
-- 
2.20.1


From 9f28ced2afb2662a3f5086bcc18e587187fbcd47 Mon Sep 17 00:00:00 2001
From: Alexey Kodanev <alexey.kodanev@oracle.com>
Date: Fri, 23 Aug 2019 20:51:43 +0300
Subject: [PATCH 07/10] ipv4: mpls: fix mpls_xmit for iptunnel

[ Upstream commit 803f3e22ae10003a83c781498c0ac34cfe3463ff ]

When using mpls over gre/gre6 setup, rt->rt_gw4 address is not set, the
same for rt->rt_gw_family.  Therefore, when rt->rt_gw_family is checked
in mpls_xmit(), neigh_xmit() call is skipped. As a result, such setup
doesn't work anymore.

This issue was found with LTP mpls03 tests.

Fixes: 1550c171935d ("ipv4: Prepare rtable for IPv6 gateway")
Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mpls/mpls_iptunnel.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c
index d25e91d7bdc1..44b675016393 100644
--- a/net/mpls/mpls_iptunnel.c
+++ b/net/mpls/mpls_iptunnel.c
@@ -133,12 +133,12 @@ static int mpls_xmit(struct sk_buff *skb)
 	mpls_stats_inc_outucastpkts(out_dev, skb);
 
 	if (rt) {
-		if (rt->rt_gw_family == AF_INET)
-			err = neigh_xmit(NEIGH_ARP_TABLE, out_dev, &rt->rt_gw4,
-					 skb);
-		else if (rt->rt_gw_family == AF_INET6)
+		if (rt->rt_gw_family == AF_INET6)
 			err = neigh_xmit(NEIGH_ND_TABLE, out_dev, &rt->rt_gw6,
 					 skb);
+		else
+			err = neigh_xmit(NEIGH_ARP_TABLE, out_dev, &rt->rt_gw4,
+					 skb);
 	} else if (rt6) {
 		if (ipv6_addr_v4mapped(&rt6->rt6i_gateway)) {
 			/* 6PE (RFC 4798) */
-- 
2.20.1


From 520ff3fd28ffd320ca5e9c058974893fd032f0c1 Mon Sep 17 00:00:00 2001
From: Yi-Hung Wei <yihung.wei@gmail.com>
Date: Thu, 22 Aug 2019 13:17:50 -0700
Subject: [PATCH 08/10] openvswitch: Fix conntrack cache with timeout

[ Upstream commit 7177895154e6a35179d332f4a584d396c50d0612 ]

This patch addresses a conntrack cache issue with timeout policy.
Currently, we do not check if the timeout extension is set properly in the
cached conntrack entry.  Thus, after packet recirculate from conntrack
action, the timeout policy is not applied properly.  This patch fixes the
aforementioned issue.

Fixes: 06bd2bdf19d2 ("openvswitch: Add timeout support to ct action")
Reported-by: kbuild test robot <lkp@intel.com>
Signed-off-by: Yi-Hung Wei <yihung.wei@gmail.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/conntrack.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 848c6eb55064..4d7896135e73 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -67,6 +67,7 @@ struct ovs_conntrack_info {
 	struct md_mark mark;
 	struct md_labels labels;
 	char timeout[CTNL_TIMEOUT_NAME_MAX];
+	struct nf_ct_timeout *nf_ct_timeout;
 #if IS_ENABLED(CONFIG_NF_NAT)
 	struct nf_nat_range2 range;  /* Only present for SRC NAT and DST NAT. */
 #endif
@@ -697,6 +698,14 @@ static bool skb_nfct_cached(struct net *net,
 		if (help && rcu_access_pointer(help->helper) != info->helper)
 			return false;
 	}
+	if (info->nf_ct_timeout) {
+		struct nf_conn_timeout *timeout_ext;
+
+		timeout_ext = nf_ct_timeout_find(ct);
+		if (!timeout_ext || info->nf_ct_timeout !=
+		    rcu_dereference(timeout_ext->timeout))
+			return false;
+	}
 	/* Force conntrack entry direction to the current packet? */
 	if (info->force && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) {
 		/* Delete the conntrack entry if confirmed, else just release
@@ -1657,6 +1666,10 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr,
 				      ct_info.timeout))
 			pr_info_ratelimited("Failed to associated timeout "
 					    "policy `%s'\n", ct_info.timeout);
+		else
+			ct_info.nf_ct_timeout = rcu_dereference(
+				nf_ct_timeout_find(ct_info.ct)->timeout);
+
 	}
 
 	if (helper) {
-- 
2.20.1


From 75e59bb6ea9a8171bf9e7b889ac9dc27f9fa0ccf Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Thu, 22 Aug 2019 22:19:48 +0800
Subject: [PATCH 09/10] ipv4/icmp: fix rt dst dev null pointer dereference

[ Upstream commit e2c693934194fd3b4e795635934883354c06ebc9 ]

In __icmp_send() there is a possibility that the rt->dst.dev is NULL,
e,g, with tunnel collect_md mode, which will cause kernel crash.
Here is what the code path looks like, for GRE:

- ip6gre_tunnel_xmit
  - ip6gre_xmit_ipv4
    - __gre6_xmit
      - ip6_tnl_xmit
        - if skb->len - t->tun_hlen - eth_hlen > mtu; return -EMSGSIZE
    - icmp_send
      - net = dev_net(rt->dst.dev); <-- here

The reason is __metadata_dst_init() init dst->dev to NULL by default.
We could not fix it in __metadata_dst_init() as there is no dev supplied.
On the other hand, the reason we need rt->dst.dev is to get the net.
So we can just try get it from skb->dev when rt->dst.dev is NULL.

v4: Julian Anastasov remind skb->dev also could be NULL. We'd better
still use dst.dev and do a check to avoid crash.

v3: No changes.

v2: fix the issue in __icmp_send() instead of updating shared dst dev
in {ip_md, ip6}_tunnel_xmit.

Fixes: c8b34e680a09 ("ip_tunnel: Add tnl_update_pmtu in ip_md_tunnel_xmit")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Julian Anastasov <ja@ssi.bg>
Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/icmp.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 7c857c72aad1..92b3d2d1139e 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -582,7 +582,13 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
 
 	if (!rt)
 		goto out;
-	net = dev_net(rt->dst.dev);
+
+	if (rt->dst.dev)
+		net = dev_net(rt->dst.dev);
+	else if (skb_in->dev)
+		net = dev_net(skb_in->dev);
+	else
+		goto out;
 
 	/*
 	 *	Find the original header. It is expected to be valid, of course.
-- 
2.20.1


From 46745ae2fe11d400a23ab9bc001c2aacca734a8c Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Thu, 22 Aug 2019 22:19:49 +0800
Subject: [PATCH 10/10] xfrm/xfrm_policy: fix dst dev null pointer dereference
 in collect_md mode

[ Upstream commit c3b4c3a47e05d5fecf7354d75824a9d1b37f3e84 ]

In decode_session{4,6} there is a possibility that the skb dst dev is NULL,
e,g, with tunnel collect_md mode, which will cause kernel crash.
Here is what the code path looks like, for GRE:

- ip6gre_tunnel_xmit
  - ip6gre_xmit_ipv6
    - __gre6_xmit
      - ip6_tnl_xmit
        - if skb->len - t->tun_hlen - eth_hlen > mtu; return -EMSGSIZE
    - icmpv6_send
      - icmpv6_route_lookup
        - xfrm_decode_session_reverse
          - decode_session4
            - oif = skb_dst(skb)->dev->ifindex; <-- here
          - decode_session6
            - oif = skb_dst(skb)->dev->ifindex; <-- here

The reason is __metadata_dst_init() init dst->dev to NULL by default.
We could not fix it in __metadata_dst_init() as there is no dev supplied.
On the other hand, the skb_dst(skb)->dev is actually not needed as we
called decode_session{4,6} via xfrm_decode_session_reverse(), so oif is not
used by: fl4->flowi4_oif = reverse ? skb->skb_iif : oif;

So make a dst dev check here should be clean and safe.

v4: No changes.

v3: No changes.

v2: fix the issue in decode_session{4,6} instead of updating shared dst dev
in {ip_md, ip6}_tunnel_xmit.

Fixes: 8d79266bc48c ("ip6_tunnel: add collect_md mode to IPv6 tunnels")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Tested-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/xfrm/xfrm_policy.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 82be7780bbe8..d5342687fdca 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -3272,7 +3272,7 @@ decode_session4(struct sk_buff *skb, struct flowi *fl, bool reverse)
 	struct flowi4 *fl4 = &fl->u.ip4;
 	int oif = 0;
 
-	if (skb_dst(skb))
+	if (skb_dst(skb) && skb_dst(skb)->dev)
 		oif = skb_dst(skb)->dev->ifindex;
 
 	memset(fl4, 0, sizeof(struct flowi4));
@@ -3390,7 +3390,7 @@ decode_session6(struct sk_buff *skb, struct flowi *fl, bool reverse)
 
 	nexthdr = nh[nhoff];
 
-	if (skb_dst(skb))
+	if (skb_dst(skb) && skb_dst(skb)->dev)
 		oif = skb_dst(skb)->dev->ifindex;
 
 	memset(fl6, 0, sizeof(struct flowi6));
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Tue, Aug 27, 2019 at 05:42:50PM -0700, David Miller wrote:
> 
> Please queue up the following bug fixes for v4.19 and v5.2 -stable
> respectively, thanks!


Now queued up, sorry for the delay.

greg k-h

Re: [PATCHES] Networking

[David Miller]

From: Greg KH <greg@kroah.com>
Date: Mon, 2 Sep 2019 18:30:16 +0200

> On Tue, Aug 27, 2019 at 05:42:50PM -0700, David Miller wrote:
>> 
>> Please queue up the following bug fixes for v4.19 and v5.2 -stable
>> respectively, thanks!
> 
> 
> Now queued up, sorry for the delay.

No worries, I'll probably be dumping another batch on you in the
next 24 hours anyways :)

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 106 bytes --]


Please queue up the following networking bug fixes for v4.19 and v5.2
-stable, respectively.

Thank you.

[-- Attachment #2: net_419.mbox --]
[-- Type: Application/Octet-Stream, Size: 29464 bytes --]

From ba2de03ed5aa88cadd3a5fdbc26f2af1301cd59c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 27 Aug 2019 03:33:12 -0700
Subject: [PATCH 1/8] mld: fix memory leak in mld_del_delrec()

[ Upstream commit a84d016479896b5526a2cc54784e6ffc41c9d6f6 ]

Similar to the fix done for IPv4 in commit e5b1c6c6277d
("igmp: fix memory leak in igmpv3_del_delrec()"), we need to
make sure mca_tomb and mca_sources are not blindly overwritten.

Using swap() then a call to ip6_mc_clear_src() will take care
of the missing free.

BUG: memory leak
unreferenced object 0xffff888117d9db00 (size 64):
  comm "syz-executor247", pid 6918, jiffies 4294943989 (age 25.350s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 fe 88 00 00 00 00 00 00  ................
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<000000005b463030>] kmemleak_alloc_recursive include/linux/kmemleak.h:43 [inline]
    [<000000005b463030>] slab_post_alloc_hook mm/slab.h:522 [inline]
    [<000000005b463030>] slab_alloc mm/slab.c:3319 [inline]
    [<000000005b463030>] kmem_cache_alloc_trace+0x145/0x2c0 mm/slab.c:3548
    [<00000000939cbf94>] kmalloc include/linux/slab.h:552 [inline]
    [<00000000939cbf94>] kzalloc include/linux/slab.h:748 [inline]
    [<00000000939cbf94>] ip6_mc_add1_src net/ipv6/mcast.c:2236 [inline]
    [<00000000939cbf94>] ip6_mc_add_src+0x31f/0x420 net/ipv6/mcast.c:2356
    [<00000000d8972221>] ip6_mc_source+0x4a8/0x600 net/ipv6/mcast.c:449
    [<000000002b203d0d>] do_ipv6_setsockopt.isra.0+0x1b92/0x1dd0 net/ipv6/ipv6_sockglue.c:748
    [<000000001f1e2d54>] ipv6_setsockopt+0x89/0xd0 net/ipv6/ipv6_sockglue.c:944
    [<00000000c8f7bdf9>] udpv6_setsockopt+0x4e/0x90 net/ipv6/udp.c:1558
    [<000000005a9a0c5e>] sock_common_setsockopt+0x38/0x50 net/core/sock.c:3139
    [<00000000910b37b2>] __sys_setsockopt+0x10f/0x220 net/socket.c:2084
    [<00000000e9108023>] __do_sys_setsockopt net/socket.c:2100 [inline]
    [<00000000e9108023>] __se_sys_setsockopt net/socket.c:2097 [inline]
    [<00000000e9108023>] __x64_sys_setsockopt+0x26/0x30 net/socket.c:2097
    [<00000000f4818160>] do_syscall_64+0x76/0x1a0 arch/x86/entry/common.c:296
    [<000000008d367e8f>] entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 1666d49e1d41 ("mld: do not remove mld souce list info when set link down")
Fixes: 9c8bb163ae78 ("igmp, mld: Fix memory leak in igmpv3/mld_del_delrec()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/mcast.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index dbab62e3f0d7..2d80e913b82f 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -791,14 +791,15 @@ static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im)
 	if (pmc) {
 		im->idev = pmc->idev;
 		if (im->mca_sfmode == MCAST_INCLUDE) {
-			im->mca_tomb = pmc->mca_tomb;
-			im->mca_sources = pmc->mca_sources;
+			swap(im->mca_tomb, pmc->mca_tomb);
+			swap(im->mca_sources, pmc->mca_sources);
 			for (psf = im->mca_sources; psf; psf = psf->sf_next)
 				psf->sf_crcount = idev->mc_qrv;
 		} else {
 			im->mca_crcount = idev->mc_qrv;
 		}
 		in6_dev_put(pmc->idev);
+		ip6_mc_clear_src(pmc);
 		kfree(pmc);
 	}
 	spin_unlock_bh(&im->mca_lock);
-- 
2.21.0


From b2c6a434ff9e89991c850d05ca615aa32024f454 Mon Sep 17 00:00:00 2001
From: Feng Sun <loyou85@gmail.com>
Date: Mon, 26 Aug 2019 14:46:04 +0800
Subject: [PATCH 2/8] net: fix skb use after free in netpoll

[ Upstream commit 2c1644cf6d46a8267d79ed95cb9b563839346562 ]

After commit baeababb5b85d5c4e6c917efe2a1504179438d3b
("tun: return NET_XMIT_DROP for dropped packets"),
when tun_net_xmit drop packets, it will free skb and return NET_XMIT_DROP,
netpoll_send_skb_on_dev will run into following use after free cases:
1. retry netpoll_start_xmit with freed skb;
2. queue freed skb in npinfo->txq.
queue_process will also run into use after free case.

hit netpoll_send_skb_on_dev first case with following kernel log:

[  117.864773] kernel BUG at mm/slub.c:306!
[  117.864773] invalid opcode: 0000 [#1] SMP PTI
[  117.864774] CPU: 3 PID: 2627 Comm: loop_printmsg Kdump: loaded Tainted: P           OE     5.3.0-050300rc5-generic #201908182231
[  117.864775] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014
[  117.864775] RIP: 0010:kmem_cache_free+0x28d/0x2b0
[  117.864781] Call Trace:
[  117.864781]  ? tun_net_xmit+0x21c/0x460
[  117.864781]  kfree_skbmem+0x4e/0x60
[  117.864782]  kfree_skb+0x3a/0xa0
[  117.864782]  tun_net_xmit+0x21c/0x460
[  117.864782]  netpoll_start_xmit+0x11d/0x1b0
[  117.864788]  netpoll_send_skb_on_dev+0x1b8/0x200
[  117.864789]  __br_forward+0x1b9/0x1e0 [bridge]
[  117.864789]  ? skb_clone+0x53/0xd0
[  117.864790]  ? __skb_clone+0x2e/0x120
[  117.864790]  deliver_clone+0x37/0x50 [bridge]
[  117.864790]  maybe_deliver+0x89/0xc0 [bridge]
[  117.864791]  br_flood+0x6c/0x130 [bridge]
[  117.864791]  br_dev_xmit+0x315/0x3c0 [bridge]
[  117.864792]  netpoll_start_xmit+0x11d/0x1b0
[  117.864792]  netpoll_send_skb_on_dev+0x1b8/0x200
[  117.864792]  netpoll_send_udp+0x2c6/0x3e8
[  117.864793]  write_msg+0xd9/0xf0 [netconsole]
[  117.864793]  console_unlock+0x386/0x4e0
[  117.864793]  vprintk_emit+0x17e/0x280
[  117.864794]  vprintk_default+0x29/0x50
[  117.864794]  vprintk_func+0x4c/0xbc
[  117.864794]  printk+0x58/0x6f
[  117.864795]  loop_fun+0x24/0x41 [printmsg_loop]
[  117.864795]  kthread+0x104/0x140
[  117.864795]  ? 0xffffffffc05b1000
[  117.864796]  ? kthread_park+0x80/0x80
[  117.864796]  ret_from_fork+0x35/0x40

Signed-off-by: Feng Sun <loyou85@gmail.com>
Signed-off-by: Xiaojun Zhao <xiaojunzhao141@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/netpoll.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 3ae899805f8b..a581cf101cd9 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -122,7 +122,7 @@ static void queue_process(struct work_struct *work)
 		txq = netdev_get_tx_queue(dev, q_index);
 		HARD_TX_LOCK(dev, txq, smp_processor_id());
 		if (netif_xmit_frozen_or_stopped(txq) ||
-		    netpoll_start_xmit(skb, dev, txq) != NETDEV_TX_OK) {
+		    !dev_xmit_complete(netpoll_start_xmit(skb, dev, txq))) {
 			skb_queue_head(&npinfo->txq, skb);
 			HARD_TX_UNLOCK(dev, txq);
 			local_irq_restore(flags);
@@ -335,7 +335,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
 
 				HARD_TX_UNLOCK(dev, txq);
 
-				if (status == NETDEV_TX_OK)
+				if (dev_xmit_complete(status))
 					break;
 
 			}
@@ -352,7 +352,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
 
 	}
 
-	if (status != NETDEV_TX_OK) {
+	if (!dev_xmit_complete(status)) {
 		skb_queue_tail(&npinfo->txq, skb);
 		schedule_delayed_work(&npinfo->tx_work,0);
 	}
-- 
2.21.0


From b9428deba54f499ea8be1235e470a55ca06234fd Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Tue, 27 Aug 2019 21:49:38 +0300
Subject: [PATCH 3/8] net: sched: act_sample: fix psample group handling on
 overwrite

[ Upstream commit dbf47a2a094edf58983265e323ca4bdcdb58b5ee ]

Action sample doesn't properly handle psample_group pointer in overwrite
case. Following issues need to be fixed:

- In tcf_sample_init() function RCU_INIT_POINTER() is used to set
  s->psample_group, even though we neither setting the pointer to NULL, nor
  preventing concurrent readers from accessing the pointer in some way.
  Use rcu_swap_protected() instead to safely reset the pointer.

- Old value of s->psample_group is not released or deallocated in any way,
  which results resource leak. Use psample_group_put() on non-NULL value
  obtained with rcu_swap_protected().

- The function psample_group_put() that released reference to struct
  psample_group pointed by rcu-pointer s->psample_group doesn't respect rcu
  grace period when deallocating it. Extend struct psample_group with rcu
  head and use kfree_rcu when freeing it.

Fixes: 5c5670fae430 ("net/sched: Introduce sample tc action")
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/psample.h  | 1 +
 net/psample/psample.c  | 2 +-
 net/sched/act_sample.c | 5 ++++-
 3 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/include/net/psample.h b/include/net/psample.h
index 9b80f814ab04..94cb37a7bf75 100644
--- a/include/net/psample.h
+++ b/include/net/psample.h
@@ -12,6 +12,7 @@ struct psample_group {
 	u32 group_num;
 	u32 refcount;
 	u32 seq;
+	struct rcu_head rcu;
 };
 
 struct psample_group *psample_group_get(struct net *net, u32 group_num);
diff --git a/net/psample/psample.c b/net/psample/psample.c
index 64f95624f219..4cea353221da 100644
--- a/net/psample/psample.c
+++ b/net/psample/psample.c
@@ -156,7 +156,7 @@ static void psample_group_destroy(struct psample_group *group)
 {
 	psample_group_notify(group, PSAMPLE_CMD_DEL_GROUP);
 	list_del(&group->list);
-	kfree(group);
+	kfree_rcu(group, rcu);
 }
 
 static struct psample_group *
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index ac37654ca292..34ff6c30d1e6 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -99,7 +99,8 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 	s->tcf_action = parm->action;
 	s->rate = rate;
 	s->psample_group_num = psample_group_num;
-	RCU_INIT_POINTER(s->psample_group, psample_group);
+	rcu_swap_protected(s->psample_group, psample_group,
+			   lockdep_is_held(&s->tcf_lock));
 
 	if (tb[TCA_SAMPLE_TRUNC_SIZE]) {
 		s->truncate = true;
@@ -107,6 +108,8 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 	}
 	spin_unlock_bh(&s->tcf_lock);
 
+	if (psample_group)
+		psample_group_put(psample_group);
 	if (ret == ACT_P_CREATED)
 		tcf_idr_insert(tn, *a);
 	return ret;
-- 
2.21.0


From 50012278df8fb0c9164e50f7db2d8bfb05bbbe2f Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sun, 25 Aug 2019 10:01:32 -0700
Subject: [PATCH 4/8] net_sched: fix a NULL pointer deref in ipt action

[ Upstream commit 981471bd3abf4d572097645d765391533aac327d ]

The net pointer in struct xt_tgdtor_param is not explicitly
initialized therefore is still NULL when dereferencing it.
So we have to find a way to pass the correct net pointer to
ipt_destroy_target().

The best way I find is just saving the net pointer inside the per
netns struct tcf_idrinfo, which could make this patch smaller.

Fixes: 0c66dc1ea3f0 ("netfilter: conntrack: register hooks in netns when needed by ruleset")
Reported-and-tested-by: itugrok@yahoo.com
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/act_api.h      |  4 +++-
 net/sched/act_bpf.c        |  2 +-
 net/sched/act_connmark.c   |  2 +-
 net/sched/act_csum.c       |  2 +-
 net/sched/act_gact.c       |  2 +-
 net/sched/act_ife.c        |  2 +-
 net/sched/act_ipt.c        | 11 ++++++-----
 net/sched/act_mirred.c     |  2 +-
 net/sched/act_nat.c        |  2 +-
 net/sched/act_pedit.c      |  2 +-
 net/sched/act_police.c     |  2 +-
 net/sched/act_sample.c     |  2 +-
 net/sched/act_simple.c     |  2 +-
 net/sched/act_skbedit.c    |  2 +-
 net/sched/act_skbmod.c     |  2 +-
 net/sched/act_tunnel_key.c |  2 +-
 net/sched/act_vlan.c       |  2 +-
 17 files changed, 24 insertions(+), 21 deletions(-)

diff --git a/include/net/act_api.h b/include/net/act_api.h
index 970303448c90..0c82d7ea6ee1 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -15,6 +15,7 @@
 struct tcf_idrinfo {
 	spinlock_t	lock;
 	struct idr	action_idr;
+	struct net	*net;
 };
 
 struct tc_action_ops;
@@ -107,7 +108,7 @@ struct tc_action_net {
 };
 
 static inline
-int tc_action_net_init(struct tc_action_net *tn,
+int tc_action_net_init(struct net *net, struct tc_action_net *tn,
 		       const struct tc_action_ops *ops)
 {
 	int err = 0;
@@ -116,6 +117,7 @@ int tc_action_net_init(struct tc_action_net *tn,
 	if (!tn->idrinfo)
 		return -ENOMEM;
 	tn->ops = ops;
+	tn->idrinfo->net = net;
 	spin_lock_init(&tn->idrinfo->lock);
 	idr_init(&tn->idrinfo->action_idr);
 	return err;
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 20fae5ca87fa..800846d77a56 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -413,7 +413,7 @@ static __net_init int bpf_init_net(struct net *net)
 {
 	struct tc_action_net *tn = net_generic(net, bpf_net_id);
 
-	return tc_action_net_init(tn, &act_bpf_ops);
+	return tc_action_net_init(net, tn, &act_bpf_ops);
 }
 
 static void __net_exit bpf_exit_net(struct list_head *net_list)
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index 605436747978..538dedd84e21 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -215,7 +215,7 @@ static __net_init int connmark_init_net(struct net *net)
 {
 	struct tc_action_net *tn = net_generic(net, connmark_net_id);
 
-	return tc_action_net_init(tn, &act_connmark_ops);
+	return tc_action_net_init(net, tn, &act_connmark_ops);
 }
 
 static void __net_exit connmark_exit_net(struct list_head *net_list)
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 40437197e053..1e269441065a 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -678,7 +678,7 @@ static __net_init int csum_init_net(struct net *net)
 {
 	struct tc_action_net *tn = net_generic(net, csum_net_id);
 
-	return tc_action_net_init(tn, &act_csum_ops);
+	return tc_action_net_init(net, tn, &act_csum_ops);
 }
 
 static void __net_exit csum_exit_net(struct list_head *net_list)
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index 72d3347bdd41..dfef9621375e 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -263,7 +263,7 @@ static __net_init int gact_init_net(struct net *net)
 {
 	struct tc_action_net *tn = net_generic(net, gact_net_id);
 
-	return tc_action_net_init(tn, &act_gact_ops);
+	return tc_action_net_init(net, tn, &act_gact_ops);
 }
 
 static void __net_exit gact_exit_net(struct list_head *net_list)
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 24047e0e5db0..bac353bea02f 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -887,7 +887,7 @@ static __net_init int ife_init_net(struct net *net)
 {
 	struct tc_action_net *tn = net_generic(net, ife_net_id);
 
-	return tc_action_net_init(tn, &act_ife_ops);
+	return tc_action_net_init(net, tn, &act_ife_ops);
 }
 
 static void __net_exit ife_exit_net(struct list_head *net_list)
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 334f3a057671..01d3669ef498 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -65,12 +65,13 @@ static int ipt_init_target(struct net *net, struct xt_entry_target *t,
 	return 0;
 }
 
-static void ipt_destroy_target(struct xt_entry_target *t)
+static void ipt_destroy_target(struct xt_entry_target *t, struct net *net)
 {
 	struct xt_tgdtor_param par = {
 		.target   = t->u.kernel.target,
 		.targinfo = t->data,
 		.family   = NFPROTO_IPV4,
+		.net      = net,
 	};
 	if (par.target->destroy != NULL)
 		par.target->destroy(&par);
@@ -82,7 +83,7 @@ static void tcf_ipt_release(struct tc_action *a)
 	struct tcf_ipt *ipt = to_ipt(a);
 
 	if (ipt->tcfi_t) {
-		ipt_destroy_target(ipt->tcfi_t);
+		ipt_destroy_target(ipt->tcfi_t, a->idrinfo->net);
 		kfree(ipt->tcfi_t);
 	}
 	kfree(ipt->tcfi_tname);
@@ -182,7 +183,7 @@ static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla,
 
 	spin_lock_bh(&ipt->tcf_lock);
 	if (ret != ACT_P_CREATED) {
-		ipt_destroy_target(ipt->tcfi_t);
+		ipt_destroy_target(ipt->tcfi_t, net);
 		kfree(ipt->tcfi_tname);
 		kfree(ipt->tcfi_t);
 	}
@@ -353,7 +354,7 @@ static __net_init int ipt_init_net(struct net *net)
 {
 	struct tc_action_net *tn = net_generic(net, ipt_net_id);
 
-	return tc_action_net_init(tn, &act_ipt_ops);
+	return tc_action_net_init(net, tn, &act_ipt_ops);
 }
 
 static void __net_exit ipt_exit_net(struct list_head *net_list)
@@ -403,7 +404,7 @@ static __net_init int xt_init_net(struct net *net)
 {
 	struct tc_action_net *tn = net_generic(net, xt_net_id);
 
-	return tc_action_net_init(tn, &act_xt_ops);
+	return tc_action_net_init(net, tn, &act_xt_ops);
 }
 
 static void __net_exit xt_exit_net(struct list_head *net_list)
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 548614bd9366..399e3beae6cf 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -419,7 +419,7 @@ static __net_init int mirred_init_net(struct net *net)
 {
 	struct tc_action_net *tn = net_generic(net, mirred_net_id);
 
-	return tc_action_net_init(tn, &act_mirred_ops);
+	return tc_action_net_init(net, tn, &act_mirred_ops);
 }
 
 static void __net_exit mirred_exit_net(struct list_head *net_list)
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 619828920b97..d1b47a1b145c 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -317,7 +317,7 @@ static __net_init int nat_init_net(struct net *net)
 {
 	struct tc_action_net *tn = net_generic(net, nat_net_id);
 
-	return tc_action_net_init(tn, &act_nat_ops);
+	return tc_action_net_init(net, tn, &act_nat_ops);
 }
 
 static void __net_exit nat_exit_net(struct list_head *net_list)
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 82d258b2a75a..33c0cc5ef229 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -488,7 +488,7 @@ static __net_init int pedit_init_net(struct net *net)
 {
 	struct tc_action_net *tn = net_generic(net, pedit_net_id);
 
-	return tc_action_net_init(tn, &act_pedit_ops);
+	return tc_action_net_init(net, tn, &act_pedit_ops);
 }
 
 static void __net_exit pedit_exit_net(struct list_head *net_list)
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 997c34db1491..4db25959e156 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -342,7 +342,7 @@ static __net_init int police_init_net(struct net *net)
 {
 	struct tc_action_net *tn = net_generic(net, police_net_id);
 
-	return tc_action_net_init(tn, &act_police_ops);
+	return tc_action_net_init(net, tn, &act_police_ops);
 }
 
 static void __net_exit police_exit_net(struct list_head *net_list)
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 34ff6c30d1e6..98635311a5a0 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -258,7 +258,7 @@ static __net_init int sample_init_net(struct net *net)
 {
 	struct tc_action_net *tn = net_generic(net, sample_net_id);
 
-	return tc_action_net_init(tn, &act_sample_ops);
+	return tc_action_net_init(net, tn, &act_sample_ops);
 }
 
 static void __net_exit sample_exit_net(struct list_head *net_list)
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 658efae71a09..b418ef62e0a4 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -215,7 +215,7 @@ static __net_init int simp_init_net(struct net *net)
 {
 	struct tc_action_net *tn = net_generic(net, simp_net_id);
 
-	return tc_action_net_init(tn, &act_simp_ops);
+	return tc_action_net_init(net, tn, &act_simp_ops);
 }
 
 static void __net_exit simp_exit_net(struct list_head *net_list)
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 7709710a41f7..a80179c1075f 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -316,7 +316,7 @@ static __net_init int skbedit_init_net(struct net *net)
 {
 	struct tc_action_net *tn = net_generic(net, skbedit_net_id);
 
-	return tc_action_net_init(tn, &act_skbedit_ops);
+	return tc_action_net_init(net, tn, &act_skbedit_ops);
 }
 
 static void __net_exit skbedit_exit_net(struct list_head *net_list)
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index 3038493d18ca..21d195296121 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -277,7 +277,7 @@ static __net_init int skbmod_init_net(struct net *net)
 {
 	struct tc_action_net *tn = net_generic(net, skbmod_net_id);
 
-	return tc_action_net_init(tn, &act_skbmod_ops);
+	return tc_action_net_init(net, tn, &act_skbmod_ops);
 }
 
 static void __net_exit skbmod_exit_net(struct list_head *net_list)
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 66bfe57e74ae..43309ff2b5dc 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -579,7 +579,7 @@ static __net_init int tunnel_key_init_net(struct net *net)
 {
 	struct tc_action_net *tn = net_generic(net, tunnel_key_net_id);
 
-	return tc_action_net_init(tn, &act_tunnel_key_ops);
+	return tc_action_net_init(net, tn, &act_tunnel_key_ops);
 }
 
 static void __net_exit tunnel_key_exit_net(struct list_head *net_list)
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index da993edd2e40..41528b966440 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -324,7 +324,7 @@ static __net_init int vlan_init_net(struct net *net)
 {
 	struct tc_action_net *tn = net_generic(net, vlan_net_id);
 
-	return tc_action_net_init(tn, &act_vlan_ops);
+	return tc_action_net_init(net, tn, &act_vlan_ops);
 }
 
 static void __net_exit vlan_exit_net(struct list_head *net_list)
-- 
2.21.0


From 42ea0102e8ff1408f3117ca021d67735dfda01aa Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wens@csie.org>
Date: Thu, 29 Aug 2019 11:17:24 +0800
Subject: [PATCH 5/8] net: stmmac: dwmac-rk: Don't fail if phy regulator is
 absent

[ Upstream commit 3b25528e1e355c803e73aa326ce657b5606cda73 ]

The devicetree binding lists the phy phy as optional. As such, the
driver should not bail out if it can't find a regulator. Instead it
should just skip the remaining regulator related code and continue
on normally.

Skip the remainder of phy_power_on() if a regulator supply isn't
available. This also gets rid of the bogus return code.

Fixes: 2e12f536635f ("net: stmmac: dwmac-rk: Use standard devicetree property for phy regulator")
Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index 3b174eae77c1..f45df6df6932 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -1203,10 +1203,8 @@ static int phy_power_on(struct rk_priv_data *bsp_priv, bool enable)
 	int ret;
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (!ldo) {
-		dev_err(dev, "no regulator found\n");
-		return -1;
-	}
+	if (!ldo)
+		return 0;
 
 	if (enable) {
 		ret = regulator_enable(ldo);
-- 
2.21.0


From 43ad1ecbb5d6fbacf703cb65db50628e79a68e3e Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Tue, 27 Aug 2019 15:09:33 -0400
Subject: [PATCH 6/8] tcp: inherit timestamp on mtu probe

[ Upstream commit 888a5c53c0d8be6e98bc85b677f179f77a647873 ]

TCP associates tx timestamp requests with a byte in the bytestream.
If merging skbs in tcp_mtu_probe, migrate the tstamp request.

Similar to MSG_EOR, do not allow moving a timestamp from any segment
in the probe but the last. This to avoid merging multiple timestamps.

Tested with the packetdrill script at
https://github.com/wdebruij/packetdrill/commits/mtu_probe-1

Link: http://patchwork.ozlabs.org/patch/1143278/#2232897
Fixes: 4ed2d765dfac ("net-timestamp: TCP timestamping")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 88c7e821fd11..2697e4397e46 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2046,7 +2046,7 @@ static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len)
 		if (len <= skb->len)
 			break;
 
-		if (unlikely(TCP_SKB_CB(skb)->eor))
+		if (unlikely(TCP_SKB_CB(skb)->eor) || tcp_has_tx_tstamp(skb))
 			return false;
 
 		len -= skb->len;
@@ -2162,6 +2162,7 @@ static int tcp_mtu_probe(struct sock *sk)
 			 * we need to propagate it to the new skb.
 			 */
 			TCP_SKB_CB(nskb)->eor = TCP_SKB_CB(skb)->eor;
+			tcp_skb_collapse_tstamp(nskb, skb);
 			tcp_unlink_write_queue(skb, sk);
 			sk_wmem_free_skb(sk, skb);
 		} else {
-- 
2.21.0


From eab41431fc76863465d00ddf8b7f377107b3ba8d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 26 Aug 2019 09:19:15 -0700
Subject: [PATCH 7/8] tcp: remove empty skb from write queue in error cases

[ Upstream commit fdfc5c8594c24c5df883583ebd286321a80e0a67 ]

Vladimir Rutsky reported stuck TCP sessions after memory pressure
events. Edge Trigger epoll() user would never receive an EPOLLOUT
notification allowing them to retry a sendmsg().

Jason tested the case of sk_stream_alloc_skb() returning NULL,
but there are other paths that could lead both sendmsg() and sendpage()
to return -1 (EAGAIN), with an empty skb queued on the write queue.

This patch makes sure we remove this empty skb so that
Jason code can detect that the queue is empty, and
call sk->sk_write_space(sk) accordingly.

Fixes: ce5ec440994b ("tcp: ensure epoll edge trigger wakeup when write queue is empty")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jason Baron <jbaron@akamai.com>
Reported-by: Vladimir Rutsky <rutsky@google.com>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 29 ++++++++++++++++++++---------
 1 file changed, 20 insertions(+), 9 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index b7ef367fe6a1..611ba174265c 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -934,6 +934,22 @@ static int tcp_send_mss(struct sock *sk, int *size_goal, int flags)
 	return mss_now;
 }
 
+/* In some cases, both sendpage() and sendmsg() could have added
+ * an skb to the write queue, but failed adding payload on it.
+ * We need to remove it to consume less memory, but more
+ * importantly be able to generate EPOLLOUT for Edge Trigger epoll()
+ * users.
+ */
+static void tcp_remove_empty_skb(struct sock *sk, struct sk_buff *skb)
+{
+	if (skb && !skb->len) {
+		tcp_unlink_write_queue(skb, sk);
+		if (tcp_write_queue_empty(sk))
+			tcp_chrono_stop(sk, TCP_CHRONO_BUSY);
+		sk_wmem_free_skb(sk, skb);
+	}
+}
+
 ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
 			 size_t size, int flags)
 {
@@ -1056,6 +1072,7 @@ ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
 	return copied;
 
 do_error:
+	tcp_remove_empty_skb(sk, tcp_write_queue_tail(sk));
 	if (copied)
 		goto out;
 out_err:
@@ -1409,17 +1426,11 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 	sock_zerocopy_put(uarg);
 	return copied + copied_syn;
 
+do_error:
+	skb = tcp_write_queue_tail(sk);
 do_fault:
-	if (!skb->len) {
-		tcp_unlink_write_queue(skb, sk);
-		/* It is the one place in all of TCP, except connection
-		 * reset, where we can be unlinking the send_head.
-		 */
-		tcp_check_send_head(sk, skb);
-		sk_wmem_free_skb(sk, skb);
-	}
+	tcp_remove_empty_skb(sk, skb);
 
-do_error:
 	if (copied + copied_syn)
 		goto out;
 out_err:
-- 
2.21.0


From cc2958dde55cc18b994ca315d08ad272a74c7338 Mon Sep 17 00:00:00 2001
From: Ka-Cheong Poon <ka-cheong.poon@oracle.com>
Date: Mon, 26 Aug 2019 02:39:12 -0700
Subject: [PATCH 8/8] net/rds: Fix info leak in rds6_inc_info_copy()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 7d0a06586b2686ba80c4a2da5f91cb10ffbea736 ]

The rds6_inc_info_copy() function has a couple struct members which
are leaking stack information.  The ->tos field should hold actual
information and the ->flags field needs to be zeroed out.

Fixes: 3eb450367d08 ("rds: add type of service(tos) infrastructure")
Fixes: b7ff8b1036f0 ("rds: Extend RDS API for IPv6 support")
Reported-by: 黄ID蝴蝶 <butterflyhuangxx@gmail.com>
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Ka-Cheong Poon <ka-cheong.poon@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/recv.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/rds/recv.c b/net/rds/recv.c
index 504cd6bcc54c..c0b945516cdb 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2006, 2019 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -803,6 +803,7 @@ void rds6_inc_info_copy(struct rds_incoming *inc,
 
 	minfo6.seq = be64_to_cpu(inc->i_hdr.h_sequence);
 	minfo6.len = be32_to_cpu(inc->i_hdr.h_len);
+	minfo6.tos = 0;
 
 	if (flip) {
 		minfo6.laddr = *daddr;
@@ -816,6 +817,8 @@ void rds6_inc_info_copy(struct rds_incoming *inc,
 		minfo6.fport = inc->i_hdr.h_dport;
 	}
 
+	minfo6.flags = 0;
+
 	rds_info_copy(iter, &minfo6, sizeof(minfo6));
 }
 #endif
-- 
2.21.0


[-- Attachment #3: net_52.mbox --]
[-- Type: Application/Octet-Stream, Size: 59863 bytes --]

From 6df2c6a9c63a90c7c31e9859c9ebdd8057cb9e1d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 27 Aug 2019 03:33:12 -0700
Subject: [PATCH 01/19] mld: fix memory leak in mld_del_delrec()

[ Upstream commit a84d016479896b5526a2cc54784e6ffc41c9d6f6 ]

Similar to the fix done for IPv4 in commit e5b1c6c6277d
("igmp: fix memory leak in igmpv3_del_delrec()"), we need to
make sure mca_tomb and mca_sources are not blindly overwritten.

Using swap() then a call to ip6_mc_clear_src() will take care
of the missing free.

BUG: memory leak
unreferenced object 0xffff888117d9db00 (size 64):
  comm "syz-executor247", pid 6918, jiffies 4294943989 (age 25.350s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 fe 88 00 00 00 00 00 00  ................
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<000000005b463030>] kmemleak_alloc_recursive include/linux/kmemleak.h:43 [inline]
    [<000000005b463030>] slab_post_alloc_hook mm/slab.h:522 [inline]
    [<000000005b463030>] slab_alloc mm/slab.c:3319 [inline]
    [<000000005b463030>] kmem_cache_alloc_trace+0x145/0x2c0 mm/slab.c:3548
    [<00000000939cbf94>] kmalloc include/linux/slab.h:552 [inline]
    [<00000000939cbf94>] kzalloc include/linux/slab.h:748 [inline]
    [<00000000939cbf94>] ip6_mc_add1_src net/ipv6/mcast.c:2236 [inline]
    [<00000000939cbf94>] ip6_mc_add_src+0x31f/0x420 net/ipv6/mcast.c:2356
    [<00000000d8972221>] ip6_mc_source+0x4a8/0x600 net/ipv6/mcast.c:449
    [<000000002b203d0d>] do_ipv6_setsockopt.isra.0+0x1b92/0x1dd0 net/ipv6/ipv6_sockglue.c:748
    [<000000001f1e2d54>] ipv6_setsockopt+0x89/0xd0 net/ipv6/ipv6_sockglue.c:944
    [<00000000c8f7bdf9>] udpv6_setsockopt+0x4e/0x90 net/ipv6/udp.c:1558
    [<000000005a9a0c5e>] sock_common_setsockopt+0x38/0x50 net/core/sock.c:3139
    [<00000000910b37b2>] __sys_setsockopt+0x10f/0x220 net/socket.c:2084
    [<00000000e9108023>] __do_sys_setsockopt net/socket.c:2100 [inline]
    [<00000000e9108023>] __se_sys_setsockopt net/socket.c:2097 [inline]
    [<00000000e9108023>] __x64_sys_setsockopt+0x26/0x30 net/socket.c:2097
    [<00000000f4818160>] do_syscall_64+0x76/0x1a0 arch/x86/entry/common.c:296
    [<000000008d367e8f>] entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 1666d49e1d41 ("mld: do not remove mld souce list info when set link down")
Fixes: 9c8bb163ae78 ("igmp, mld: Fix memory leak in igmpv3/mld_del_delrec()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/mcast.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 7f3f13c37916..eaa4c2cc2fbb 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -787,14 +787,15 @@ static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im)
 	if (pmc) {
 		im->idev = pmc->idev;
 		if (im->mca_sfmode == MCAST_INCLUDE) {
-			im->mca_tomb = pmc->mca_tomb;
-			im->mca_sources = pmc->mca_sources;
+			swap(im->mca_tomb, pmc->mca_tomb);
+			swap(im->mca_sources, pmc->mca_sources);
 			for (psf = im->mca_sources; psf; psf = psf->sf_next)
 				psf->sf_crcount = idev->mc_qrv;
 		} else {
 			im->mca_crcount = idev->mc_qrv;
 		}
 		in6_dev_put(pmc->idev);
+		ip6_mc_clear_src(pmc);
 		kfree(pmc);
 	}
 	spin_unlock_bh(&im->mca_lock);
-- 
2.21.0


From b165ae30a385e3aef8d4c7c7da2bb6f548f1e62e Mon Sep 17 00:00:00 2001
From: Feng Sun <loyou85@gmail.com>
Date: Mon, 26 Aug 2019 14:46:04 +0800
Subject: [PATCH 02/19] net: fix skb use after free in netpoll

[ Upstream commit 2c1644cf6d46a8267d79ed95cb9b563839346562 ]

After commit baeababb5b85d5c4e6c917efe2a1504179438d3b
("tun: return NET_XMIT_DROP for dropped packets"),
when tun_net_xmit drop packets, it will free skb and return NET_XMIT_DROP,
netpoll_send_skb_on_dev will run into following use after free cases:
1. retry netpoll_start_xmit with freed skb;
2. queue freed skb in npinfo->txq.
queue_process will also run into use after free case.

hit netpoll_send_skb_on_dev first case with following kernel log:

[  117.864773] kernel BUG at mm/slub.c:306!
[  117.864773] invalid opcode: 0000 [#1] SMP PTI
[  117.864774] CPU: 3 PID: 2627 Comm: loop_printmsg Kdump: loaded Tainted: P           OE     5.3.0-050300rc5-generic #201908182231
[  117.864775] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014
[  117.864775] RIP: 0010:kmem_cache_free+0x28d/0x2b0
[  117.864781] Call Trace:
[  117.864781]  ? tun_net_xmit+0x21c/0x460
[  117.864781]  kfree_skbmem+0x4e/0x60
[  117.864782]  kfree_skb+0x3a/0xa0
[  117.864782]  tun_net_xmit+0x21c/0x460
[  117.864782]  netpoll_start_xmit+0x11d/0x1b0
[  117.864788]  netpoll_send_skb_on_dev+0x1b8/0x200
[  117.864789]  __br_forward+0x1b9/0x1e0 [bridge]
[  117.864789]  ? skb_clone+0x53/0xd0
[  117.864790]  ? __skb_clone+0x2e/0x120
[  117.864790]  deliver_clone+0x37/0x50 [bridge]
[  117.864790]  maybe_deliver+0x89/0xc0 [bridge]
[  117.864791]  br_flood+0x6c/0x130 [bridge]
[  117.864791]  br_dev_xmit+0x315/0x3c0 [bridge]
[  117.864792]  netpoll_start_xmit+0x11d/0x1b0
[  117.864792]  netpoll_send_skb_on_dev+0x1b8/0x200
[  117.864792]  netpoll_send_udp+0x2c6/0x3e8
[  117.864793]  write_msg+0xd9/0xf0 [netconsole]
[  117.864793]  console_unlock+0x386/0x4e0
[  117.864793]  vprintk_emit+0x17e/0x280
[  117.864794]  vprintk_default+0x29/0x50
[  117.864794]  vprintk_func+0x4c/0xbc
[  117.864794]  printk+0x58/0x6f
[  117.864795]  loop_fun+0x24/0x41 [printmsg_loop]
[  117.864795]  kthread+0x104/0x140
[  117.864795]  ? 0xffffffffc05b1000
[  117.864796]  ? kthread_park+0x80/0x80
[  117.864796]  ret_from_fork+0x35/0x40

Signed-off-by: Feng Sun <loyou85@gmail.com>
Signed-off-by: Xiaojun Zhao <xiaojunzhao141@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/netpoll.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index dd8b1a460d64..cb36d01ea0dd 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -122,7 +122,7 @@ static void queue_process(struct work_struct *work)
 		txq = netdev_get_tx_queue(dev, q_index);
 		HARD_TX_LOCK(dev, txq, smp_processor_id());
 		if (netif_xmit_frozen_or_stopped(txq) ||
-		    netpoll_start_xmit(skb, dev, txq) != NETDEV_TX_OK) {
+		    !dev_xmit_complete(netpoll_start_xmit(skb, dev, txq))) {
 			skb_queue_head(&npinfo->txq, skb);
 			HARD_TX_UNLOCK(dev, txq);
 			local_irq_restore(flags);
@@ -335,7 +335,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
 
 				HARD_TX_UNLOCK(dev, txq);
 
-				if (status == NETDEV_TX_OK)
+				if (dev_xmit_complete(status))
 					break;
 
 			}
@@ -352,7 +352,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
 
 	}
 
-	if (status != NETDEV_TX_OK) {
+	if (!dev_xmit_complete(status)) {
 		skb_queue_tail(&npinfo->txq, skb);
 		schedule_delayed_work(&npinfo->tx_work,0);
 	}
-- 
2.21.0


From 695b0a4cc7d35b7362a81ad78f69da779267f16e Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Tue, 27 Aug 2019 21:49:38 +0300
Subject: [PATCH 03/19] net: sched: act_sample: fix psample group handling on
 overwrite

[ Upstream commit dbf47a2a094edf58983265e323ca4bdcdb58b5ee ]

Action sample doesn't properly handle psample_group pointer in overwrite
case. Following issues need to be fixed:

- In tcf_sample_init() function RCU_INIT_POINTER() is used to set
  s->psample_group, even though we neither setting the pointer to NULL, nor
  preventing concurrent readers from accessing the pointer in some way.
  Use rcu_swap_protected() instead to safely reset the pointer.

- Old value of s->psample_group is not released or deallocated in any way,
  which results resource leak. Use psample_group_put() on non-NULL value
  obtained with rcu_swap_protected().

- The function psample_group_put() that released reference to struct
  psample_group pointed by rcu-pointer s->psample_group doesn't respect rcu
  grace period when deallocating it. Extend struct psample_group with rcu
  head and use kfree_rcu when freeing it.

Fixes: 5c5670fae430 ("net/sched: Introduce sample tc action")
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/psample.h  | 1 +
 net/psample/psample.c  | 2 +-
 net/sched/act_sample.c | 6 +++++-
 3 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/include/net/psample.h b/include/net/psample.h
index 37a4df2325b2..6b578ce69cd8 100644
--- a/include/net/psample.h
+++ b/include/net/psample.h
@@ -11,6 +11,7 @@ struct psample_group {
 	u32 group_num;
 	u32 refcount;
 	u32 seq;
+	struct rcu_head rcu;
 };
 
 struct psample_group *psample_group_get(struct net *net, u32 group_num);
diff --git a/net/psample/psample.c b/net/psample/psample.c
index 841f198ea1a8..66e4b61a350d 100644
--- a/net/psample/psample.c
+++ b/net/psample/psample.c
@@ -154,7 +154,7 @@ static void psample_group_destroy(struct psample_group *group)
 {
 	psample_group_notify(group, PSAMPLE_CMD_DEL_GROUP);
 	list_del(&group->list);
-	kfree(group);
+	kfree_rcu(group, rcu);
 }
 
 static struct psample_group *
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 595308d60133..b75377d8c596 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -102,13 +102,17 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
 	s->rate = rate;
 	s->psample_group_num = psample_group_num;
-	RCU_INIT_POINTER(s->psample_group, psample_group);
+	rcu_swap_protected(s->psample_group, psample_group,
+			   lockdep_is_held(&s->tcf_lock));
 
 	if (tb[TCA_SAMPLE_TRUNC_SIZE]) {
 		s->truncate = true;
 		s->trunc_size = nla_get_u32(tb[TCA_SAMPLE_TRUNC_SIZE]);
 	}
 	spin_unlock_bh(&s->tcf_lock);
+
+	if (psample_group)
+		psample_group_put(psample_group);
 	if (goto_ch)
 		tcf_chain_put_by_act(goto_ch);
 
-- 
2.21.0


From 6faae2ccdcd84b05adcef48807dbeae665930a4c Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sun, 25 Aug 2019 10:01:32 -0700
Subject: [PATCH 04/19] net_sched: fix a NULL pointer deref in ipt action

[ Upstream commit 981471bd3abf4d572097645d765391533aac327d ]

The net pointer in struct xt_tgdtor_param is not explicitly
initialized therefore is still NULL when dereferencing it.
So we have to find a way to pass the correct net pointer to
ipt_destroy_target().

The best way I find is just saving the net pointer inside the per
netns struct tcf_idrinfo, which could make this patch smaller.

Fixes: 0c66dc1ea3f0 ("netfilter: conntrack: register hooks in netns when needed by ruleset")
Reported-and-tested-by: itugrok@yahoo.com
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/act_api.h      |  4 +++-
 net/sched/act_bpf.c        |  2 +-
 net/sched/act_connmark.c   |  2 +-
 net/sched/act_csum.c       |  2 +-
 net/sched/act_gact.c       |  2 +-
 net/sched/act_ife.c        |  2 +-
 net/sched/act_ipt.c        | 11 ++++++-----
 net/sched/act_mirred.c     |  2 +-
 net/sched/act_nat.c        |  2 +-
 net/sched/act_pedit.c      |  2 +-
 net/sched/act_police.c     |  2 +-
 net/sched/act_sample.c     |  2 +-
 net/sched/act_simple.c     |  2 +-
 net/sched/act_skbedit.c    |  2 +-
 net/sched/act_skbmod.c     |  2 +-
 net/sched/act_tunnel_key.c |  2 +-
 net/sched/act_vlan.c       |  2 +-
 17 files changed, 24 insertions(+), 21 deletions(-)

diff --git a/include/net/act_api.h b/include/net/act_api.h
index c61a1bf4e3de..3a1a72990fce 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -15,6 +15,7 @@
 struct tcf_idrinfo {
 	struct mutex	lock;
 	struct idr	action_idr;
+	struct net	*net;
 };
 
 struct tc_action_ops;
@@ -108,7 +109,7 @@ struct tc_action_net {
 };
 
 static inline
-int tc_action_net_init(struct tc_action_net *tn,
+int tc_action_net_init(struct net *net, struct tc_action_net *tn,
 		       const struct tc_action_ops *ops)
 {
 	int err = 0;
@@ -117,6 +118,7 @@ int tc_action_net_init(struct tc_action_net *tn,
 	if (!tn->idrinfo)
 		return -ENOMEM;
 	tn->ops = ops;
+	tn->idrinfo->net = net;
 	mutex_init(&tn->idrinfo->lock);
 	idr_init(&tn->idrinfo->action_idr);
 	return err;
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index fd1f7e799e23..04b7bd4ec751 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -422,7 +422,7 @@ static __net_init int bpf_init_net(struct net *net)
 {
 	struct tc_action_net *tn = net_generic(net, bpf_net_id);
 
-	return tc_action_net_init(tn, &act_bpf_ops);
+	return tc_action_net_init(net, tn, &act_bpf_ops);
 }
 
 static void __net_exit bpf_exit_net(struct list_head *net_list)
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index 32ac04d77a45..2b43cacf82af 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -231,7 +231,7 @@ static __net_init int connmark_init_net(struct net *net)
 {
 	struct tc_action_net *tn = net_generic(net, connmark_net_id);
 
-	return tc_action_net_init(tn, &act_connmark_ops);
+	return tc_action_net_init(net, tn, &act_connmark_ops);
 }
 
 static void __net_exit connmark_exit_net(struct list_head *net_list)
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 9b9288267a54..d3cfad88dc3a 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -714,7 +714,7 @@ static __net_init int csum_init_net(struct net *net)
 {
 	struct tc_action_net *tn = net_generic(net, csum_net_id);
 
-	return tc_action_net_init(tn, &act_csum_ops);
+	return tc_action_net_init(net, tn, &act_csum_ops);
 }
 
 static void __net_exit csum_exit_net(struct list_head *net_list)
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index 8f0140c6ca58..324f1d1f6d47 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -278,7 +278,7 @@ static __net_init int gact_init_net(struct net *net)
 {
 	struct tc_action_net *tn = net_generic(net, gact_net_id);
 
-	return tc_action_net_init(tn, &act_gact_ops);
+	return tc_action_net_init(net, tn, &act_gact_ops);
 }
 
 static void __net_exit gact_exit_net(struct list_head *net_list)
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 92ee853d43e6..3a31e241c647 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -890,7 +890,7 @@ static __net_init int ife_init_net(struct net *net)
 {
 	struct tc_action_net *tn = net_generic(net, ife_net_id);
 
-	return tc_action_net_init(tn, &act_ife_ops);
+	return tc_action_net_init(net, tn, &act_ife_ops);
 }
 
 static void __net_exit ife_exit_net(struct list_head *net_list)
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index ce2c30a591d2..214a03d405cf 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -61,12 +61,13 @@ static int ipt_init_target(struct net *net, struct xt_entry_target *t,
 	return 0;
 }
 
-static void ipt_destroy_target(struct xt_entry_target *t)
+static void ipt_destroy_target(struct xt_entry_target *t, struct net *net)
 {
 	struct xt_tgdtor_param par = {
 		.target   = t->u.kernel.target,
 		.targinfo = t->data,
 		.family   = NFPROTO_IPV4,
+		.net      = net,
 	};
 	if (par.target->destroy != NULL)
 		par.target->destroy(&par);
@@ -78,7 +79,7 @@ static void tcf_ipt_release(struct tc_action *a)
 	struct tcf_ipt *ipt = to_ipt(a);
 
 	if (ipt->tcfi_t) {
-		ipt_destroy_target(ipt->tcfi_t);
+		ipt_destroy_target(ipt->tcfi_t, a->idrinfo->net);
 		kfree(ipt->tcfi_t);
 	}
 	kfree(ipt->tcfi_tname);
@@ -180,7 +181,7 @@ static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla,
 
 	spin_lock_bh(&ipt->tcf_lock);
 	if (ret != ACT_P_CREATED) {
-		ipt_destroy_target(ipt->tcfi_t);
+		ipt_destroy_target(ipt->tcfi_t, net);
 		kfree(ipt->tcfi_tname);
 		kfree(ipt->tcfi_t);
 	}
@@ -350,7 +351,7 @@ static __net_init int ipt_init_net(struct net *net)
 {
 	struct tc_action_net *tn = net_generic(net, ipt_net_id);
 
-	return tc_action_net_init(tn, &act_ipt_ops);
+	return tc_action_net_init(net, tn, &act_ipt_ops);
 }
 
 static void __net_exit ipt_exit_net(struct list_head *net_list)
@@ -399,7 +400,7 @@ static __net_init int xt_init_net(struct net *net)
 {
 	struct tc_action_net *tn = net_generic(net, xt_net_id);
 
-	return tc_action_net_init(tn, &act_xt_ops);
+	return tc_action_net_init(net, tn, &act_xt_ops);
 }
 
 static void __net_exit xt_exit_net(struct list_head *net_list)
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index d10dca7a13e1..bd3178a95cb9 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -432,7 +432,7 @@ static __net_init int mirred_init_net(struct net *net)
 {
 	struct tc_action_net *tn = net_generic(net, mirred_net_id);
 
-	return tc_action_net_init(tn, &act_mirred_ops);
+	return tc_action_net_init(net, tn, &act_mirred_ops);
 }
 
 static void __net_exit mirred_exit_net(struct list_head *net_list)
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 7b858c11b1b5..ea4c5359e7df 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -327,7 +327,7 @@ static __net_init int nat_init_net(struct net *net)
 {
 	struct tc_action_net *tn = net_generic(net, nat_net_id);
 
-	return tc_action_net_init(tn, &act_nat_ops);
+	return tc_action_net_init(net, tn, &act_nat_ops);
 }
 
 static void __net_exit nat_exit_net(struct list_head *net_list)
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 17360c6faeaa..cdfaa79382a2 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -498,7 +498,7 @@ static __net_init int pedit_init_net(struct net *net)
 {
 	struct tc_action_net *tn = net_generic(net, pedit_net_id);
 
-	return tc_action_net_init(tn, &act_pedit_ops);
+	return tc_action_net_init(net, tn, &act_pedit_ops);
 }
 
 static void __net_exit pedit_exit_net(struct list_head *net_list)
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 49cec3e64a4d..6315e0f8d26e 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -371,7 +371,7 @@ static __net_init int police_init_net(struct net *net)
 {
 	struct tc_action_net *tn = net_generic(net, police_net_id);
 
-	return tc_action_net_init(tn, &act_police_ops);
+	return tc_action_net_init(net, tn, &act_police_ops);
 }
 
 static void __net_exit police_exit_net(struct list_head *net_list)
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index b75377d8c596..10229124a992 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -269,7 +269,7 @@ static __net_init int sample_init_net(struct net *net)
 {
 	struct tc_action_net *tn = net_generic(net, sample_net_id);
 
-	return tc_action_net_init(tn, &act_sample_ops);
+	return tc_action_net_init(net, tn, &act_sample_ops);
 }
 
 static void __net_exit sample_exit_net(struct list_head *net_list)
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 33aefa25b545..6120e56117ca 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -232,7 +232,7 @@ static __net_init int simp_init_net(struct net *net)
 {
 	struct tc_action_net *tn = net_generic(net, simp_net_id);
 
-	return tc_action_net_init(tn, &act_simp_ops);
+	return tc_action_net_init(net, tn, &act_simp_ops);
 }
 
 static void __net_exit simp_exit_net(struct list_head *net_list)
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 37dced00b63d..6a8d3337c577 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -336,7 +336,7 @@ static __net_init int skbedit_init_net(struct net *net)
 {
 	struct tc_action_net *tn = net_generic(net, skbedit_net_id);
 
-	return tc_action_net_init(tn, &act_skbedit_ops);
+	return tc_action_net_init(net, tn, &act_skbedit_ops);
 }
 
 static void __net_exit skbedit_exit_net(struct list_head *net_list)
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index 7da3518e18ef..888437f97ba6 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -287,7 +287,7 @@ static __net_init int skbmod_init_net(struct net *net)
 {
 	struct tc_action_net *tn = net_generic(net, skbmod_net_id);
 
-	return tc_action_net_init(tn, &act_skbmod_ops);
+	return tc_action_net_init(net, tn, &act_skbmod_ops);
 }
 
 static void __net_exit skbmod_exit_net(struct list_head *net_list)
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 6d0debdc9b97..2f83a79f76aa 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -600,7 +600,7 @@ static __net_init int tunnel_key_init_net(struct net *net)
 {
 	struct tc_action_net *tn = net_generic(net, tunnel_key_net_id);
 
-	return tc_action_net_init(tn, &act_tunnel_key_ops);
+	return tc_action_net_init(net, tn, &act_tunnel_key_ops);
 }
 
 static void __net_exit tunnel_key_exit_net(struct list_head *net_list)
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index a3c9eea1ee8a..287a30bf8930 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -334,7 +334,7 @@ static __net_init int vlan_init_net(struct net *net)
 {
 	struct tc_action_net *tn = net_generic(net, vlan_net_id);
 
-	return tc_action_net_init(tn, &act_vlan_ops);
+	return tc_action_net_init(net, tn, &act_vlan_ops);
 }
 
 static void __net_exit vlan_exit_net(struct list_head *net_list)
-- 
2.21.0


From be52a057493e5e85c9783ae7ec2a3dda91a1ca0d Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wens@csie.org>
Date: Thu, 29 Aug 2019 11:17:24 +0800
Subject: [PATCH 05/19] net: stmmac: dwmac-rk: Don't fail if phy regulator is
 absent

[ Upstream commit 3b25528e1e355c803e73aa326ce657b5606cda73 ]

The devicetree binding lists the phy phy as optional. As such, the
driver should not bail out if it can't find a regulator. Instead it
should just skip the remaining regulator related code and continue
on normally.

Skip the remainder of phy_power_on() if a regulator supply isn't
available. This also gets rid of the bogus return code.

Fixes: 2e12f536635f ("net: stmmac: dwmac-rk: Use standard devicetree property for phy regulator")
Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index 4644b2aeeba1..e2e469c37a4d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -1194,10 +1194,8 @@ static int phy_power_on(struct rk_priv_data *bsp_priv, bool enable)
 	int ret;
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (!ldo) {
-		dev_err(dev, "no regulator found\n");
-		return -1;
-	}
+	if (!ldo)
+		return 0;
 
 	if (enable) {
 		ret = regulator_enable(ldo);
-- 
2.21.0


From c5112ee84012742fdcbb080c9cec6ea09e57ada8 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Tue, 27 Aug 2019 15:09:33 -0400
Subject: [PATCH 06/19] tcp: inherit timestamp on mtu probe

[ Upstream commit 888a5c53c0d8be6e98bc85b677f179f77a647873 ]

TCP associates tx timestamp requests with a byte in the bytestream.
If merging skbs in tcp_mtu_probe, migrate the tstamp request.

Similar to MSG_EOR, do not allow moving a timestamp from any segment
in the probe but the last. This to avoid merging multiple timestamps.

Tested with the packetdrill script at
https://github.com/wdebruij/packetdrill/commits/mtu_probe-1

Link: http://patchwork.ozlabs.org/patch/1143278/#2232897
Fixes: 4ed2d765dfac ("net-timestamp: TCP timestamping")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 359d298348c7..37c2f1204c1a 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2051,7 +2051,7 @@ static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len)
 		if (len <= skb->len)
 			break;
 
-		if (unlikely(TCP_SKB_CB(skb)->eor))
+		if (unlikely(TCP_SKB_CB(skb)->eor) || tcp_has_tx_tstamp(skb))
 			return false;
 
 		len -= skb->len;
@@ -2168,6 +2168,7 @@ static int tcp_mtu_probe(struct sock *sk)
 			 * we need to propagate it to the new skb.
 			 */
 			TCP_SKB_CB(nskb)->eor = TCP_SKB_CB(skb)->eor;
+			tcp_skb_collapse_tstamp(nskb, skb);
 			tcp_unlink_write_queue(skb, sk);
 			sk_wmem_free_skb(sk, skb);
 		} else {
-- 
2.21.0


From b2d2e33dcdaa3e40d8477381361de874e3751891 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 26 Aug 2019 09:19:15 -0700
Subject: [PATCH 07/19] tcp: remove empty skb from write queue in error cases

[ Upstream commit fdfc5c8594c24c5df883583ebd286321a80e0a67 ]

Vladimir Rutsky reported stuck TCP sessions after memory pressure
events. Edge Trigger epoll() user would never receive an EPOLLOUT
notification allowing them to retry a sendmsg().

Jason tested the case of sk_stream_alloc_skb() returning NULL,
but there are other paths that could lead both sendmsg() and sendpage()
to return -1 (EAGAIN), with an empty skb queued on the write queue.

This patch makes sure we remove this empty skb so that
Jason code can detect that the queue is empty, and
call sk->sk_write_space(sk) accordingly.

Fixes: ce5ec440994b ("tcp: ensure epoll edge trigger wakeup when write queue is empty")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jason Baron <jbaron@akamai.com>
Reported-by: Vladimir Rutsky <rutsky@google.com>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 30 ++++++++++++++++++++----------
 1 file changed, 20 insertions(+), 10 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index b30f7f877181..b2f0d2988a8e 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -935,6 +935,22 @@ static int tcp_send_mss(struct sock *sk, int *size_goal, int flags)
 	return mss_now;
 }
 
+/* In some cases, both sendpage() and sendmsg() could have added
+ * an skb to the write queue, but failed adding payload on it.
+ * We need to remove it to consume less memory, but more
+ * importantly be able to generate EPOLLOUT for Edge Trigger epoll()
+ * users.
+ */
+static void tcp_remove_empty_skb(struct sock *sk, struct sk_buff *skb)
+{
+	if (skb && !skb->len) {
+		tcp_unlink_write_queue(skb, sk);
+		if (tcp_write_queue_empty(sk))
+			tcp_chrono_stop(sk, TCP_CHRONO_BUSY);
+		sk_wmem_free_skb(sk, skb);
+	}
+}
+
 ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
 			 size_t size, int flags)
 {
@@ -1064,6 +1080,7 @@ ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
 	return copied;
 
 do_error:
+	tcp_remove_empty_skb(sk, tcp_write_queue_tail(sk));
 	if (copied)
 		goto out;
 out_err:
@@ -1388,18 +1405,11 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 	sock_zerocopy_put(uarg);
 	return copied + copied_syn;
 
+do_error:
+	skb = tcp_write_queue_tail(sk);
 do_fault:
-	if (!skb->len) {
-		tcp_unlink_write_queue(skb, sk);
-		/* It is the one place in all of TCP, except connection
-		 * reset, where we can be unlinking the send_head.
-		 */
-		if (tcp_write_queue_empty(sk))
-			tcp_chrono_stop(sk, TCP_CHRONO_BUSY);
-		sk_wmem_free_skb(sk, skb);
-	}
+	tcp_remove_empty_skb(sk, skb);
 
-do_error:
 	if (copied + copied_syn)
 		goto out;
 out_err:
-- 
2.21.0


From 592022e404cbffadf5af8e978be2a65fed8c453a Mon Sep 17 00:00:00 2001
From: John Hurley <john.hurley@netronome.com>
Date: Tue, 27 Aug 2019 22:56:29 -0700
Subject: [PATCH 08/19] nfp: flower: prevent ingress block binds on internal
 ports

[ Upstream commit 739d7c5752b255e89ddbb1b0474f3b88ef5cd343 ]

Internal port TC offload is implemented through user-space applications
(such as OvS) by adding filters at egress via TC clsact qdiscs. Indirect
block offload support in the NFP driver accepts both ingress qdisc binds
and egress binds if the device is an internal port. However, clsact sends
bind notification for both ingress and egress block binds which can lead
to the driver registering multiple callbacks and receiving multiple
notifications of new filters.

Fix this by rejecting ingress block bind callbacks when the port is
internal and only adding filter callbacks for egress binds.

Fixes: 4d12ba42787b ("nfp: flower: allow offloading of matches on 'internal' ports")
Signed-off-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/offload.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index 1fbfeb43c538..f5ebd9403d72 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -1280,9 +1280,10 @@ nfp_flower_setup_indr_tc_block(struct net_device *netdev, struct nfp_app *app,
 	struct nfp_flower_priv *priv = app->priv;
 	int err;
 
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS &&
-	    !(f->binder_type == TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS &&
-	      nfp_flower_internal_port_can_offload(app, netdev)))
+	if ((f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS &&
+	     !nfp_flower_internal_port_can_offload(app, netdev)) ||
+	    (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS &&
+	     nfp_flower_internal_port_can_offload(app, netdev)))
 		return -EOPNOTSUPP;
 
 	switch (f->command) {
-- 
2.21.0


From 56f6ef0b026ee26a5ce5241679f735a95788bc31 Mon Sep 17 00:00:00 2001
From: John Hurley <john.hurley@netronome.com>
Date: Tue, 27 Aug 2019 22:56:30 -0700
Subject: [PATCH 09/19] nfp: flower: handle neighbour events on internal ports

[ Upstream commit e8024cb483abb2b0290b3ef5e34c736e9de2492f ]

Recent code changes to NFP allowed the offload of neighbour entries to FW
when the next hop device was an internal port. This allows for offload of
tunnel encap when the end-point IP address is applied to such a port.

Unfortunately, the neighbour event handler still rejects events that are
not associated with a repr dev and so the firmware neighbour table may get
out of sync for internal ports.

Fix this by allowing internal port neighbour events to be correctly
processed.

Fixes: 45756dfedab5 ("nfp: flower: allow tunnels to output to internal port")
Signed-off-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
index 8c67505865a4..43faad1893f7 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
@@ -329,13 +329,13 @@ nfp_tun_neigh_event_handler(struct notifier_block *nb, unsigned long event,
 
 	flow.daddr = *(__be32 *)n->primary_key;
 
-	/* Only concerned with route changes for representors. */
-	if (!nfp_netdev_is_nfp_repr(n->dev))
-		return NOTIFY_DONE;
-
 	app_priv = container_of(nb, struct nfp_flower_priv, tun.neigh_nb);
 	app = app_priv->app;
 
+	if (!nfp_netdev_is_nfp_repr(n->dev) &&
+	    !nfp_flower_internal_port_can_offload(app, n->dev))
+		return NOTIFY_DONE;
+
 	/* Only concerned with changes to routes already added to NFP. */
 	if (!nfp_tun_has_route(app, flow.daddr))
 		return NOTIFY_DONE;
-- 
2.21.0


From a7b444171ca1905d7f410a2c02fb7bb77d9cd16b Mon Sep 17 00:00:00 2001
From: Hayes Wang <hayeswang@realtek.com>
Date: Wed, 28 Aug 2019 09:51:41 +0800
Subject: [PATCH 10/19] Revert "r8152: napi hangup fix after disconnect"

[ Upstream commit 49d4b14113cae1410eb4654ada5b9583bad971c4 ]

This reverts commit 0ee1f4734967af8321ecebaf9c74221ace34f2d5.

The commit 0ee1f4734967 ("r8152: napi hangup fix after
disconnect") adds a check about RTL8152_UNPLUG to determine
if calling napi_disable() is invalid in rtl8152_close(),
when rtl8152_disconnect() is called. This avoids to use
napi_disable() after calling netif_napi_del().

Howver, commit ffa9fec30ca0 ("r8152: set RTL8152_UNPLUG
only for real disconnection") causes that RTL8152_UNPLUG
is not always set when calling rtl8152_disconnect().
Therefore, I have to revert commit 0ee1f4734967 ("r8152:
napi hangup fix after disconnect"), first. And submit
another patch to fix it.

Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index e0dcb681cfe5..a2f63d10bcfe 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -3987,8 +3987,7 @@ static int rtl8152_close(struct net_device *netdev)
 #ifdef CONFIG_PM_SLEEP
 	unregister_pm_notifier(&tp->pm_notifier);
 #endif
-	if (!test_bit(RTL8152_UNPLUG, &tp->flags))
-		napi_disable(&tp->napi);
+	napi_disable(&tp->napi);
 	clear_bit(WORK_ENABLE, &tp->flags);
 	usb_kill_urb(tp->intr_urb);
 	cancel_delayed_work_sync(&tp->schedule);
-- 
2.21.0


From 8270ef42f08d9f574d9a5e3997bffea48a89e26c Mon Sep 17 00:00:00 2001
From: Hayes Wang <hayeswang@realtek.com>
Date: Wed, 28 Aug 2019 09:51:42 +0800
Subject: [PATCH 11/19] r8152: remove calling netif_napi_del

[ Upstream commit 973dc6cfc0e2c43ff29ca5645ceaf1ae694ea110 ]

Remove unnecessary use of netif_napi_del. This also avoids to call
napi_disable() after netif_napi_del().

Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index a2f63d10bcfe..1a7b7bd412f9 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -5309,7 +5309,6 @@ static int rtl8152_probe(struct usb_interface *intf,
 	return 0;
 
 out1:
-	netif_napi_del(&tp->napi);
 	usb_set_intfdata(intf, NULL);
 out:
 	free_netdev(netdev);
@@ -5327,7 +5326,6 @@ static void rtl8152_disconnect(struct usb_interface *intf)
 		if (udev->state == USB_STATE_NOTATTACHED)
 			set_bit(RTL8152_UNPLUG, &tp->flags);
 
-		netif_napi_del(&tp->napi);
 		unregister_netdev(tp->netdev);
 		cancel_delayed_work_sync(&tp->hw_phy_work);
 		tp->rtl_ops.unload(tp);
-- 
2.21.0


From a47cbb0896e8ad61bfc7e4d641eec7f0244b97c3 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Fri, 30 Aug 2019 04:07:21 +0300
Subject: [PATCH 12/19] taprio: Fix kernel panic in taprio_destroy

taprio_init may fail earlier than this line:

	list_add(&q->taprio_list, &taprio_list);

i.e. due to the net device not being multi queue.

Attempting to remove q from the global taprio_list when it is not part
of it will result in a kernel panic.

Fix it by matching list_add and list_del better to one another in the
order of operations. This way we can keep the deletion unconditional
and with lower complexity - O(1).

Cc: Leandro Dorileo <leandro.maciel.dorileo@intel.com>
Fixes: 7b9eba7ba0c1 ("net/sched: taprio: fix picos_per_byte miscalculation")
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Acked-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_taprio.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 8be89aa52b6e..0f7d575e5e8b 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -903,6 +903,10 @@ static int taprio_init(struct Qdisc *sch, struct nlattr *opt,
 	 */
 	q->clockid = -1;
 
+	spin_lock(&taprio_list_lock);
+	list_add(&q->taprio_list, &taprio_list);
+	spin_unlock(&taprio_list_lock);
+
 	if (sch->parent != TC_H_ROOT)
 		return -EOPNOTSUPP;
 
@@ -920,10 +924,6 @@ static int taprio_init(struct Qdisc *sch, struct nlattr *opt,
 	if (!opt)
 		return -EINVAL;
 
-	spin_lock(&taprio_list_lock);
-	list_add(&q->taprio_list, &taprio_list);
-	spin_unlock(&taprio_list_lock);
-
 	for (i = 0; i < dev->num_tx_queues; i++) {
 		struct netdev_queue *dev_queue;
 		struct Qdisc *qdisc;
-- 
2.21.0


From fd353187b34588ba71d8611232d629b367adc0ff Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Fri, 30 Aug 2019 04:07:22 +0300
Subject: [PATCH 13/19] taprio: Set default link speed to 10 Mbps in
 taprio_set_picos_per_byte

The taprio budget needs to be adapted at runtime according to interface
link speed. But that handling is problematic.

For one thing, installing a qdisc on an interface that doesn't have
carrier is not illegal. But taprio prints the following stack trace:

[   31.851373] ------------[ cut here ]------------
[   31.856024] WARNING: CPU: 1 PID: 207 at net/sched/sch_taprio.c:481 taprio_dequeue+0x1a8/0x2d4
[   31.864566] taprio: dequeue() called with unknown picos per byte.
[   31.864570] Modules linked in:
[   31.873701] CPU: 1 PID: 207 Comm: tc Not tainted 5.3.0-rc5-01199-g8838fe023cd6 #1689
[   31.881398] Hardware name: Freescale LS1021A
[   31.885661] [<c03133a4>] (unwind_backtrace) from [<c030d8cc>] (show_stack+0x10/0x14)
[   31.893368] [<c030d8cc>] (show_stack) from [<c10ac958>] (dump_stack+0xb4/0xc8)
[   31.900555] [<c10ac958>] (dump_stack) from [<c0349d04>] (__warn+0xe0/0xf8)
[   31.907395] [<c0349d04>] (__warn) from [<c0349d64>] (warn_slowpath_fmt+0x48/0x6c)
[   31.914841] [<c0349d64>] (warn_slowpath_fmt) from [<c0f38db4>] (taprio_dequeue+0x1a8/0x2d4)
[   31.923150] [<c0f38db4>] (taprio_dequeue) from [<c0f227b0>] (__qdisc_run+0x90/0x61c)
[   31.930856] [<c0f227b0>] (__qdisc_run) from [<c0ec82ac>] (net_tx_action+0x12c/0x2bc)
[   31.938560] [<c0ec82ac>] (net_tx_action) from [<c0302298>] (__do_softirq+0x130/0x3c8)
[   31.946350] [<c0302298>] (__do_softirq) from [<c03502a0>] (irq_exit+0xbc/0xd8)
[   31.953536] [<c03502a0>] (irq_exit) from [<c03a4808>] (__handle_domain_irq+0x60/0xb4)
[   31.961328] [<c03a4808>] (__handle_domain_irq) from [<c0754478>] (gic_handle_irq+0x58/0x9c)
[   31.969638] [<c0754478>] (gic_handle_irq) from [<c0301a8c>] (__irq_svc+0x6c/0x90)
[   31.977076] Exception stack(0xe8167b20 to 0xe8167b68)
[   31.982100] 7b20: e9d4bd80 00000cc0 000000cf 00000000 e9d4bd80 c1f38958 00000cc0 c1f38960
[   31.990234] 7b40: 00000001 000000cf 00000004 e9dc0800 00000000 e8167b70 c0f478ec c0f46d94
[   31.998363] 7b60: 60070013 ffffffff
[   32.001833] [<c0301a8c>] (__irq_svc) from [<c0f46d94>] (netlink_trim+0x18/0xd8)
[   32.009104] [<c0f46d94>] (netlink_trim) from [<c0f478ec>] (netlink_broadcast_filtered+0x34/0x414)
[   32.017930] [<c0f478ec>] (netlink_broadcast_filtered) from [<c0f47cec>] (netlink_broadcast+0x20/0x28)
[   32.027102] [<c0f47cec>] (netlink_broadcast) from [<c0eea378>] (rtnetlink_send+0x34/0x88)
[   32.035238] [<c0eea378>] (rtnetlink_send) from [<c0f25890>] (notify_and_destroy+0x2c/0x44)
[   32.043461] [<c0f25890>] (notify_and_destroy) from [<c0f25e08>] (qdisc_graft+0x398/0x470)
[   32.051595] [<c0f25e08>] (qdisc_graft) from [<c0f27a00>] (tc_modify_qdisc+0x3a4/0x724)
[   32.059470] [<c0f27a00>] (tc_modify_qdisc) from [<c0ee4c84>] (rtnetlink_rcv_msg+0x260/0x2ec)
[   32.067864] [<c0ee4c84>] (rtnetlink_rcv_msg) from [<c0f4a988>] (netlink_rcv_skb+0xb8/0x110)
[   32.076172] [<c0f4a988>] (netlink_rcv_skb) from [<c0f4a170>] (netlink_unicast+0x1b4/0x22c)
[   32.084392] [<c0f4a170>] (netlink_unicast) from [<c0f4a5e4>] (netlink_sendmsg+0x33c/0x380)
[   32.092614] [<c0f4a5e4>] (netlink_sendmsg) from [<c0ea9f40>] (sock_sendmsg+0x14/0x24)
[   32.100403] [<c0ea9f40>] (sock_sendmsg) from [<c0eaa780>] (___sys_sendmsg+0x214/0x228)
[   32.108279] [<c0eaa780>] (___sys_sendmsg) from [<c0eabad0>] (__sys_sendmsg+0x50/0x8c)
[   32.116068] [<c0eabad0>] (__sys_sendmsg) from [<c0301000>] (ret_fast_syscall+0x0/0x54)
[   32.123938] Exception stack(0xe8167fa8 to 0xe8167ff0)
[   32.128960] 7fa0:                   b6fa68c8 000000f8 00000003 bea142d0 00000000 00000000
[   32.137093] 7fc0: b6fa68c8 000000f8 0052154c 00000128 5d6468a2 00000000 00000028 00558c9c
[   32.145224] 7fe0: 00000070 bea14278 00530d64 b6e17e64
[   32.150659] ---[ end trace 2139c9827c3e5177 ]---

This happens because the qdisc ->dequeue callback gets called. Which
again is not illegal, the qdisc will dequeue even when the interface is
up but doesn't have carrier (and hence SPEED_UNKNOWN), and the frames
will be dropped further down the stack in dev_direct_xmit().

And, at the end of the day, for what? For calculating the initial budget
of an interface which is non-operational at the moment and where frames
will get dropped anyway.

So if we can't figure out the link speed, default to SPEED_10 and move
along. We can also remove the runtime check now.

Cc: Leandro Dorileo <leandro.maciel.dorileo@intel.com>
Fixes: 7b9eba7ba0c1 ("net/sched: taprio: fix picos_per_byte miscalculation")
Acked-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_taprio.c | 23 +++++++++++++----------
 1 file changed, 13 insertions(+), 10 deletions(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 0f7d575e5e8b..11c2873ec68b 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -205,11 +205,6 @@ static struct sk_buff *taprio_dequeue(struct Qdisc *sch)
 	u32 gate_mask;
 	int i;
 
-	if (atomic64_read(&q->picos_per_byte) == -1) {
-		WARN_ONCE(1, "taprio: dequeue() called with unknown picos per byte.");
-		return NULL;
-	}
-
 	rcu_read_lock();
 	entry = rcu_dereference(q->current_entry);
 	/* if there's no entry, it means that the schedule didn't
@@ -665,12 +660,20 @@ static void taprio_set_picos_per_byte(struct net_device *dev,
 				      struct taprio_sched *q)
 {
 	struct ethtool_link_ksettings ecmd;
-	int picos_per_byte = -1;
+	int speed = SPEED_10;
+	int picos_per_byte;
+	int err;
+
+	err = __ethtool_get_link_ksettings(dev, &ecmd);
+	if (err < 0)
+		goto skip;
+
+	if (ecmd.base.speed != SPEED_UNKNOWN)
+		speed = ecmd.base.speed;
 
-	if (!__ethtool_get_link_ksettings(dev, &ecmd) &&
-	    ecmd.base.speed != SPEED_UNKNOWN)
-		picos_per_byte = div64_s64(NSEC_PER_SEC * 1000LL * 8,
-					   ecmd.base.speed * 1000 * 1000);
+skip:
+	picos_per_byte = div64_s64(NSEC_PER_SEC * 1000LL * 8,
+				   speed * 1000 * 1000);
 
 	atomic64_set(&q->picos_per_byte, picos_per_byte);
 	netdev_dbg(dev, "taprio: set %s's picos_per_byte to: %lld, linkspeed: %d\n",
-- 
2.21.0


From fbff806a6b1d82bef039688b752bb8f292df6dc6 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Fri, 30 Aug 2019 04:07:23 +0300
Subject: [PATCH 14/19] net/sched: cbs: Set default link speed to 10 Mbps in
 cbs_set_port_rate

The discussion to be made is absolutely the same as in the case of
previous patch ("taprio: Set default link speed to 10 Mbps in
taprio_set_picos_per_byte"). Nothing is lost when setting a default.

Cc: Leandro Dorileo <leandro.maciel.dorileo@intel.com>
Fixes: e0a7683d30e9 ("net/sched: cbs: fix port_rate miscalculation")
Acked-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_cbs.c | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c
index 732e109c3055..810645b5c086 100644
--- a/net/sched/sch_cbs.c
+++ b/net/sched/sch_cbs.c
@@ -181,11 +181,6 @@ static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch)
 	s64 credits;
 	int len;
 
-	if (atomic64_read(&q->port_rate) == -1) {
-		WARN_ONCE(1, "cbs: dequeue() called with unknown port rate.");
-		return NULL;
-	}
-
 	if (q->credits < 0) {
 		credits = timediff_to_credits(now - q->last, q->idleslope);
 
@@ -303,11 +298,19 @@ static int cbs_enable_offload(struct net_device *dev, struct cbs_sched_data *q,
 static void cbs_set_port_rate(struct net_device *dev, struct cbs_sched_data *q)
 {
 	struct ethtool_link_ksettings ecmd;
+	int speed = SPEED_10;
 	int port_rate = -1;
+	int err;
+
+	err = __ethtool_get_link_ksettings(dev, &ecmd);
+	if (err < 0)
+		goto skip;
+
+	if (ecmd.base.speed != SPEED_UNKNOWN)
+		speed = ecmd.base.speed;
 
-	if (!__ethtool_get_link_ksettings(dev, &ecmd) &&
-	    ecmd.base.speed != SPEED_UNKNOWN)
-		port_rate = ecmd.base.speed * 1000 * BYTES_PER_KBIT;
+skip:
+	port_rate = speed * 1000 * BYTES_PER_KBIT;
 
 	atomic64_set(&q->port_rate, port_rate);
 	netdev_dbg(dev, "cbs: set %s's port_rate to: %lld, linkspeed: %d\n",
-- 
2.21.0


From 8264e42746ae3289875a48d88ec1f98f6a1b1184 Mon Sep 17 00:00:00 2001
From: Marco Hartmann <marco.hartmann@nxp.com>
Date: Wed, 21 Aug 2019 11:00:46 +0000
Subject: [PATCH 15/19] Add genphy_c45_config_aneg() function to phy-c45.c

[ Upstream commit 2ebb991641d3f64b70fec0156e2b6933810177e9 ]

Commit 34786005eca3 ("net: phy: prevent PHYs w/o Clause 22 regs from calling
genphy_config_aneg") introduced a check that aborts phy_config_aneg()
if the phy is a C45 phy.
This causes phy_state_machine() to call phy_error() so that the phy
ends up in PHY_HALTED state.

Instead of returning -EOPNOTSUPP, call genphy_c45_config_aneg()
(analogous to the C22 case) so that the state machine can run
correctly.

genphy_c45_config_aneg() closely resembles mv3310_config_aneg()
in drivers/net/phy/marvell10g.c, excluding vendor specific
configurations for 1000BaseT.

Fixes: 22b56e827093 ("net: phy: replace genphy_10g_driver with genphy_c45_driver")

Signed-off-by: Marco Hartmann <marco.hartmann@nxp.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy-c45.c | 26 ++++++++++++++++++++++++++
 drivers/net/phy/phy.c     |  2 +-
 include/linux/phy.h       |  1 +
 3 files changed, 28 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c
index 58bb25e4af10..7935593debb1 100644
--- a/drivers/net/phy/phy-c45.c
+++ b/drivers/net/phy/phy-c45.c
@@ -523,6 +523,32 @@ int genphy_c45_read_status(struct phy_device *phydev)
 }
 EXPORT_SYMBOL_GPL(genphy_c45_read_status);
 
+/**
+ * genphy_c45_config_aneg - restart auto-negotiation or forced setup
+ * @phydev: target phy_device struct
+ *
+ * Description: If auto-negotiation is enabled, we configure the
+ *   advertising, and then restart auto-negotiation.  If it is not
+ *   enabled, then we force a configuration.
+ */
+int genphy_c45_config_aneg(struct phy_device *phydev)
+{
+	bool changed = false;
+	int ret;
+
+	if (phydev->autoneg == AUTONEG_DISABLE)
+		return genphy_c45_pma_setup_forced(phydev);
+
+	ret = genphy_c45_an_config_aneg(phydev);
+	if (ret < 0)
+		return ret;
+	if (ret > 0)
+		changed = true;
+
+	return genphy_c45_check_and_restart_aneg(phydev, changed);
+}
+EXPORT_SYMBOL_GPL(genphy_c45_config_aneg);
+
 /* The gen10g_* functions are the old Clause 45 stub */
 
 int gen10g_config_aneg(struct phy_device *phydev)
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index e8885429293a..57b337687782 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -499,7 +499,7 @@ static int phy_config_aneg(struct phy_device *phydev)
 	 * allowed to call genphy_config_aneg()
 	 */
 	if (phydev->is_c45 && !(phydev->c45_ids.devices_in_package & BIT(0)))
-		return -EOPNOTSUPP;
+		return genphy_c45_config_aneg(phydev);
 
 	return genphy_config_aneg(phydev);
 }
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 6424586fe2d6..7c5a9fb9c9f4 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1108,6 +1108,7 @@ int genphy_c45_an_disable_aneg(struct phy_device *phydev);
 int genphy_c45_read_mdix(struct phy_device *phydev);
 int genphy_c45_pma_read_abilities(struct phy_device *phydev);
 int genphy_c45_read_status(struct phy_device *phydev);
+int genphy_c45_config_aneg(struct phy_device *phydev);
 
 /* The gen10g_* functions are the old Clause 45 stub */
 int gen10g_config_aneg(struct phy_device *phydev);
-- 
2.21.0


From 54aece06895d18a581960bb4048f45896b1a6c30 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Sun, 25 Aug 2019 21:32:12 +0300
Subject: [PATCH 16/19] net: dsa: tag_8021q: Future-proof the reserved fields
 in the custom VID

[ Upstream commit bcccb0a535bb99616e4b992568371efab1ab14e8 ]

After witnessing the discussion in https://lkml.org/lkml/2019/8/14/151
w.r.t. ioctl extensibility, it became clear that such an issue might
prevent that the 3 RSV bits inside the DSA 802.1Q tag might also suffer
the same fate and be useless for further extension.

So clearly specify that the reserved bits should currently be
transmitted as zero and ignored on receive. The DSA tagger already does
this (and has always did), and is the only known user so far (no
Wireshark dissection plugin, etc). So there should be no incompatibility
to speak of.

Fixes: 0471dd429cea ("net: dsa: tag_8021q: Create a stable binary format")
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/tag_8021q.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c
index 65a35e976d7b..4d0312b97cce 100644
--- a/net/dsa/tag_8021q.c
+++ b/net/dsa/tag_8021q.c
@@ -28,6 +28,7 @@
  *
  * RSV - VID[9]:
  *	To be used for further expansion of SWITCH_ID or for other purposes.
+ *	Must be transmitted as zero and ignored on receive.
  *
  * SWITCH_ID - VID[8:6]:
  *	Index of switch within DSA tree. Must be between 0 and
@@ -35,6 +36,7 @@
  *
  * RSV - VID[5:4]:
  *	To be used for further expansion of PORT or for other purposes.
+ *	Must be transmitted as zero and ignored on receive.
  *
  * PORT - VID[3:0]:
  *	Index of switch port. Must be between 0 and DSA_MAX_PORTS - 1.
-- 
2.21.0


From 938256487c813542fca9494c4ca14cd278d01400 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Tue, 27 Aug 2019 23:18:53 +0200
Subject: [PATCH 17/19] net/sched: pfifo_fast: fix wrong dereference in
 pfifo_fast_enqueue

[ Upstream commit 092e22e586236bba106a82113826a68080a03506 ]

Now that 'TCQ_F_CPUSTATS' bit can be cleared, depending on the value of
'TCQ_F_NOLOCK' bit in the parent qdisc, we can't assume anymore that
per-cpu counters are there in the error path of skb_array_produce().
Otherwise, the following splat can be seen:

 Unable to handle kernel paging request at virtual address 0000600dea430008
 Mem abort info:
   ESR = 0x96000005
   Exception class = DABT (current EL), IL = 32 bits
   SET = 0, FnV = 0
   EA = 0, S1PTW = 0
 Data abort info:
   ISV = 0, ISS = 0x00000005
   CM = 0, WnR = 0
 user pgtable: 64k pages, 48-bit VAs, pgdp = 000000007b97530e
 [0000600dea430008] pgd=0000000000000000, pud=0000000000000000
 Internal error: Oops: 96000005 [#1] SMP
[...]
 pstate: 10000005 (nzcV daif -PAN -UAO)
 pc : pfifo_fast_enqueue+0x524/0x6e8
 lr : pfifo_fast_enqueue+0x46c/0x6e8
 sp : ffff800d39376fe0
 x29: ffff800d39376fe0 x28: 1ffff001a07d1e40
 x27: ffff800d03e8f188 x26: ffff800d03e8f200
 x25: 0000000000000062 x24: ffff800d393772f0
 x23: 0000000000000000 x22: 0000000000000403
 x21: ffff800cca569a00 x20: ffff800d03e8ee00
 x19: ffff800cca569a10 x18: 00000000000000bf
 x17: 0000000000000000 x16: 0000000000000000
 x15: 0000000000000000 x14: ffff1001a726edd0
 x13: 1fffe4000276a9a4 x12: 0000000000000000
 x11: dfff200000000000 x10: ffff800d03e8f1a0
 x9 : 0000000000000003 x8 : 0000000000000000
 x7 : 00000000f1f1f1f1 x6 : ffff1001a726edea
 x5 : ffff800cca56a53c x4 : 1ffff001bf9a8003
 x3 : 1ffff001bf9a8003 x2 : 1ffff001a07d1dcb
 x1 : 0000600dea430000 x0 : 0000600dea430008
 Process ping (pid: 6067, stack limit = 0x00000000dc0aa557)
 Call trace:
  pfifo_fast_enqueue+0x524/0x6e8
  htb_enqueue+0x660/0x10e0 [sch_htb]
  __dev_queue_xmit+0x123c/0x2de0
  dev_queue_xmit+0x24/0x30
  ip_finish_output2+0xc48/0x1720
  ip_finish_output+0x548/0x9d8
  ip_output+0x334/0x788
  ip_local_out+0x90/0x138
  ip_send_skb+0x44/0x1d0
  ip_push_pending_frames+0x5c/0x78
  raw_sendmsg+0xed8/0x28d0
  inet_sendmsg+0xc4/0x5c0
  sock_sendmsg+0xac/0x108
  __sys_sendto+0x1ac/0x2a0
  __arm64_sys_sendto+0xc4/0x138
  el0_svc_handler+0x13c/0x298
  el0_svc+0x8/0xc
 Code: f9402e80 d538d081 91002000 8b010000 (885f7c03)

Fix this by testing the value of 'TCQ_F_CPUSTATS' bit in 'qdisc->flags',
before dereferencing 'qdisc->cpu_qstats'.

Fixes: 8a53e616de29 ("net: sched: when clearing NOLOCK, clear TCQ_F_CPUSTATS, too")
CC: Paolo Abeni <pabeni@redhat.com>
CC: Stefano Brivio <sbrivio@redhat.com>
Reported-by: Li Shuang <shuali@redhat.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_generic.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 11c03cf4aa74..26c50aa412c7 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -624,8 +624,12 @@ static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc,
 
 	err = skb_array_produce(q, skb);
 
-	if (unlikely(err))
-		return qdisc_drop_cpu(skb, qdisc, to_free);
+	if (unlikely(err)) {
+		if (qdisc_is_percpu_stats(qdisc))
+			return qdisc_drop_cpu(skb, qdisc, to_free);
+		else
+			return qdisc_drop(skb, qdisc, to_free);
+	}
 
 	qdisc_update_stats_at_enqueue(qdisc, pkt_len);
 	return NET_XMIT_SUCCESS;
-- 
2.21.0


From 814d1944a85868e76553c4cd90cf24972ec71d0d Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Tue, 27 Aug 2019 12:29:09 +0200
Subject: [PATCH 18/19] net/sched: pfifo_fast: fix wrong dereference when qdisc
 is reset

[ Upstream commit 04d37cf46a773910f75fefaa9f9488f42bfe1fe2 ]

Now that 'TCQ_F_CPUSTATS' bit can be cleared, depending on the value of
'TCQ_F_NOLOCK' bit in the parent qdisc, we need to be sure that per-cpu
counters are present when 'reset()' is called for pfifo_fast qdiscs.
Otherwise, the following script:

 # tc q a dev lo handle 1: root htb default 100
 # tc c a dev lo parent 1: classid 1:100 htb \
 > rate 95Mbit ceil 100Mbit burst 64k
 [...]
 # tc f a dev lo parent 1: protocol arp basic classid 1:100
 [...]
 # tc q a dev lo parent 1:100 handle 100: pfifo_fast
 [...]
 # tc q d dev lo root

can generate the following splat:

 Unable to handle kernel paging request at virtual address dfff2c01bd148000
 Mem abort info:
   ESR = 0x96000004
   Exception class = DABT (current EL), IL = 32 bits
   SET = 0, FnV = 0
   EA = 0, S1PTW = 0
 Data abort info:
   ISV = 0, ISS = 0x00000004
   CM = 0, WnR = 0
 [dfff2c01bd148000] address between user and kernel address ranges
 Internal error: Oops: 96000004 [#1] SMP
 [...]
 pstate: 80000005 (Nzcv daif -PAN -UAO)
 pc : pfifo_fast_reset+0x280/0x4d8
 lr : pfifo_fast_reset+0x21c/0x4d8
 sp : ffff800d09676fa0
 x29: ffff800d09676fa0 x28: ffff200012ee22e4
 x27: dfff200000000000 x26: 0000000000000000
 x25: ffff800ca0799958 x24: ffff1001940f332b
 x23: 0000000000000007 x22: ffff200012ee1ab8
 x21: 0000600de8a40000 x20: 0000000000000000
 x19: ffff800ca0799900 x18: 0000000000000000
 x17: 0000000000000002 x16: 0000000000000000
 x15: 0000000000000000 x14: 0000000000000000
 x13: 0000000000000000 x12: ffff1001b922e6e2
 x11: 1ffff001b922e6e1 x10: 0000000000000000
 x9 : 1ffff001b922e6e1 x8 : dfff200000000000
 x7 : 0000000000000000 x6 : 0000000000000000
 x5 : 1fffe400025dc45c x4 : 1fffe400025dc357
 x3 : 00000c01bd148000 x2 : 0000600de8a40000
 x1 : 0000000000000007 x0 : 0000600de8a40004
 Call trace:
  pfifo_fast_reset+0x280/0x4d8
  qdisc_reset+0x6c/0x370
  htb_reset+0x150/0x3b8 [sch_htb]
  qdisc_reset+0x6c/0x370
  dev_deactivate_queue.constprop.5+0xe0/0x1a8
  dev_deactivate_many+0xd8/0x908
  dev_deactivate+0xe4/0x190
  qdisc_graft+0x88c/0xbd0
  tc_get_qdisc+0x418/0x8a8
  rtnetlink_rcv_msg+0x3a8/0xa78
  netlink_rcv_skb+0x18c/0x328
  rtnetlink_rcv+0x28/0x38
  netlink_unicast+0x3c4/0x538
  netlink_sendmsg+0x538/0x9a0
  sock_sendmsg+0xac/0xf8
  ___sys_sendmsg+0x53c/0x658
  __sys_sendmsg+0xc8/0x140
  __arm64_sys_sendmsg+0x74/0xa8
  el0_svc_handler+0x164/0x468
  el0_svc+0x10/0x14
 Code: 910012a0 92400801 d343fc03 11000c21 (38fb6863)

Fix this by testing the value of 'TCQ_F_CPUSTATS' bit in 'qdisc->flags',
before dereferencing 'qdisc->cpu_qstats'.

Changes since v1:
 - coding style improvements, thanks to Stefano Brivio

Fixes: 8a53e616de29 ("net: sched: when clearing NOLOCK, clear TCQ_F_CPUSTATS, too")
CC: Paolo Abeni <pabeni@redhat.com>
Reported-by: Li Shuang <shuali@redhat.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_generic.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 26c50aa412c7..137db1cbde85 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -692,11 +692,14 @@ static void pfifo_fast_reset(struct Qdisc *qdisc)
 			kfree_skb(skb);
 	}
 
-	for_each_possible_cpu(i) {
-		struct gnet_stats_queue *q = per_cpu_ptr(qdisc->cpu_qstats, i);
+	if (qdisc_is_percpu_stats(qdisc)) {
+		for_each_possible_cpu(i) {
+			struct gnet_stats_queue *q;
 
-		q->backlog = 0;
-		q->qlen = 0;
+			q = per_cpu_ptr(qdisc->cpu_qstats, i);
+			q->backlog = 0;
+			q->qlen = 0;
+		}
 	}
 }
 
-- 
2.21.0


From 8a41b14d8805cfcb41fcb3c86c60c646f46e04b8 Mon Sep 17 00:00:00 2001
From: Ka-Cheong Poon <ka-cheong.poon@oracle.com>
Date: Mon, 26 Aug 2019 02:39:12 -0700
Subject: [PATCH 19/19] net/rds: Fix info leak in rds6_inc_info_copy()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 7d0a06586b2686ba80c4a2da5f91cb10ffbea736 ]

The rds6_inc_info_copy() function has a couple struct members which
are leaking stack information.  The ->tos field should hold actual
information and the ->flags field needs to be zeroed out.

Fixes: 3eb450367d08 ("rds: add type of service(tos) infrastructure")
Fixes: b7ff8b1036f0 ("rds: Extend RDS API for IPv6 support")
Reported-by: 黄ID蝴蝶 <butterflyhuangxx@gmail.com>
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Ka-Cheong Poon <ka-cheong.poon@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/recv.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/rds/recv.c b/net/rds/recv.c
index 853de4876088..a42ba7fa06d5 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2006, 2019 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -811,6 +811,7 @@ void rds6_inc_info_copy(struct rds_incoming *inc,
 
 	minfo6.seq = be64_to_cpu(inc->i_hdr.h_sequence);
 	minfo6.len = be32_to_cpu(inc->i_hdr.h_len);
+	minfo6.tos = inc->i_conn->c_tos;
 
 	if (flip) {
 		minfo6.laddr = *daddr;
@@ -824,6 +825,8 @@ void rds6_inc_info_copy(struct rds_incoming *inc,
 		minfo6.fport = inc->i_hdr.h_dport;
 	}
 
+	minfo6.flags = 0;
+
 	rds_info_copy(iter, &minfo6, sizeof(minfo6));
 }
 #endif
-- 
2.21.0

Re: [PATCHES] Networking

[Greg KH]

On Thu, Sep 05, 2019 at 12:23:47AM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.19 and v5.2
> -stable, respectively.

All now queued up, thanks.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 106 bytes --]


Please queue up the following networking bug fixes for v4.19
and v5.2 -stable, respectively.

Thank you!

[-- Attachment #2: net_419.mbox --]
[-- Type: Application/Octet-Stream, Size: 40891 bytes --]

From 91f4774ccd0612b0287763a42bfee1314f95086d Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Fri, 6 Sep 2019 11:47:02 +0200
Subject: [PATCH 01/15] bridge/mdb: remove wrong use of NLM_F_MULTI

[ Upstream commit 94a72b3f024fc7e9ab640897a1e38583a470659d ]

NLM_F_MULTI must be used only when a NLMSG_DONE message is sent at the end.
In fact, NLMSG_DONE is sent only at the end of a dump.

Libraries like libnl will wait forever for NLMSG_DONE.

Fixes: 949f1e39a617 ("bridge: mdb: notify on router port add and del")
CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_mdb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index 6d9f48bd374a..55198818e3e5 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -419,7 +419,7 @@ static int nlmsg_populate_rtr_fill(struct sk_buff *skb,
 	struct nlmsghdr *nlh;
 	struct nlattr *nest;
 
-	nlh = nlmsg_put(skb, pid, seq, type, sizeof(*bpm), NLM_F_MULTI);
+	nlh = nlmsg_put(skb, pid, seq, type, sizeof(*bpm), 0);
 	if (!nlh)
 		return -EMSGSIZE;
 
-- 
2.21.0


From 34dd1d25d76e464c534db409ea7ed425ab05c826 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Thu, 12 Sep 2019 10:42:00 +0200
Subject: [PATCH 02/15] cdc_ether: fix rndis support for Mediatek based
 smartphones
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 4d7ffcf3bf1be98d876c570cab8fc31d9fa92725 ]

A Mediatek based smartphone owner reports problems with USB
tethering in Linux.  The verbose USB listing shows a rndis_host
interface pair (e0/01/03 + 10/00/00), but the driver fails to
bind with

[  355.960428] usb 1-4: bad CDC descriptors

The problem is a failsafe test intended to filter out ACM serial
functions using the same 02/02/ff class/subclass/protocol as RNDIS.
The serial functions are recognized by their non-zero bmCapabilities.

No RNDIS function with non-zero bmCapabilities were known at the time
this failsafe was added. But it turns out that some Wireless class
RNDIS functions are using the bmCapabilities field. These functions
are uniquely identified as RNDIS by their class/subclass/protocol, so
the failing test can safely be disabled.  The same applies to the two
types of Misc class RNDIS functions.

Applying the failsafe to Communication class functions only retains
the original functionality, and fixes the problem for the Mediatek based
smartphone.

Tow examples of CDC functional descriptors with non-zero bmCapabilities
from Wireless class RNDIS functions are:

0e8d:000a  Mediatek Crosscall Spider X5 3G Phone

      CDC Header:
        bcdCDC               1.10
      CDC ACM:
        bmCapabilities       0x0f
          connection notifications
          sends break
          line coding and serial state
          get/set/clear comm features
      CDC Union:
        bMasterInterface        0
        bSlaveInterface         1
      CDC Call Management:
        bmCapabilities       0x03
          call management
          use DataInterface
        bDataInterface          1

and

19d2:1023  ZTE K4201-z

      CDC Header:
        bcdCDC               1.10
      CDC ACM:
        bmCapabilities       0x02
          line coding and serial state
      CDC Call Management:
        bmCapabilities       0x03
          call management
          use DataInterface
        bDataInterface          1
      CDC Union:
        bMasterInterface        0
        bSlaveInterface         1

The Mediatek example is believed to apply to most smartphones with
Mediatek firmware.  The ZTE example is most likely also part of a larger
family of devices/firmwares.

Suggested-by: Lars Melin <larsm17@gmail.com>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ether.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index 5c42cf81a08b..85fba64c3fcf 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -221,9 +221,16 @@ int usbnet_generic_cdc_bind(struct usbnet *dev, struct usb_interface *intf)
 		goto bad_desc;
 	}
 skip:
-	if (	rndis &&
-		header.usb_cdc_acm_descriptor &&
-		header.usb_cdc_acm_descriptor->bmCapabilities) {
+	/* Communcation class functions with bmCapabilities are not
+	 * RNDIS.  But some Wireless class RNDIS functions use
+	 * bmCapabilities for their own purpose. The failsafe is
+	 * therefore applied only to Communication class RNDIS
+	 * functions.  The rndis test is redundant, but a cheap
+	 * optimization.
+	 */
+	if (rndis && is_rndis(&intf->cur_altsetting->desc) &&
+	    header.usb_cdc_acm_descriptor &&
+	    header.usb_cdc_acm_descriptor->bmCapabilities) {
 			dev_dbg(&intf->dev,
 				"ACM capabilities %02x, not really RNDIS?\n",
 				header.usb_cdc_acm_descriptor->bmCapabilities);
-- 
2.21.0


From fa9f8be8dd5ab7d15672691e8d14e33a5c619134 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Tue, 10 Sep 2019 13:29:59 +0200
Subject: [PATCH 03/15] ipv6: Fix the link time qualifier of
 'ping_v6_proc_exit_net()'

[ Upstream commit d23dbc479a8e813db4161a695d67da0e36557846 ]

The '.exit' functions from 'pernet_operations' structure should be marked
as __net_exit, not __net_init.

Fixes: d862e5461423 ("net: ipv6: Implement /proc/net/icmp6.")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ping.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 4c04bccc7417..5c9be8594483 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -228,7 +228,7 @@ static int __net_init ping_v6_proc_init_net(struct net *net)
 	return 0;
 }
 
-static void __net_init ping_v6_proc_exit_net(struct net *net)
+static void __net_exit ping_v6_proc_exit_net(struct net *net)
 {
 	remove_proc_entry("icmp6", net->proc_net);
 }
-- 
2.21.0


From c5f8f598a9c1affc5df33ad1cc7561b820e52369 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Thu, 5 Sep 2019 19:36:37 -0700
Subject: [PATCH 04/15] isdn/capi: check message length in capi_write()

[ Upstream commit fe163e534e5eecdfd7b5920b0dfd24c458ee85d6 ]

syzbot reported:

    BUG: KMSAN: uninit-value in capi_write+0x791/0xa90 drivers/isdn/capi/capi.c:700
    CPU: 0 PID: 10025 Comm: syz-executor379 Not tainted 4.20.0-rc7+ #2
    Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
    Call Trace:
      __dump_stack lib/dump_stack.c:77 [inline]
      dump_stack+0x173/0x1d0 lib/dump_stack.c:113
      kmsan_report+0x12e/0x2a0 mm/kmsan/kmsan.c:613
      __msan_warning+0x82/0xf0 mm/kmsan/kmsan_instr.c:313
      capi_write+0x791/0xa90 drivers/isdn/capi/capi.c:700
      do_loop_readv_writev fs/read_write.c:703 [inline]
      do_iter_write+0x83e/0xd80 fs/read_write.c:961
      vfs_writev fs/read_write.c:1004 [inline]
      do_writev+0x397/0x840 fs/read_write.c:1039
      __do_sys_writev fs/read_write.c:1112 [inline]
      __se_sys_writev+0x9b/0xb0 fs/read_write.c:1109
      __x64_sys_writev+0x4a/0x70 fs/read_write.c:1109
      do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291
      entry_SYSCALL_64_after_hwframe+0x63/0xe7
    [...]

The problem is that capi_write() is reading past the end of the message.
Fix it by checking the message's length in the needed places.

Reported-and-tested-by: syzbot+0849c524d9c634f5ae66@syzkaller.appspotmail.com
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/capi/capi.c          | 10 +++++++++-
 include/uapi/linux/isdn/capicmd.h |  1 +
 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/isdn/capi/capi.c b/drivers/isdn/capi/capi.c
index ef5560b848ab..21786a442368 100644
--- a/drivers/isdn/capi/capi.c
+++ b/drivers/isdn/capi/capi.c
@@ -688,6 +688,9 @@ capi_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos
 	if (!cdev->ap.applid)
 		return -ENODEV;
 
+	if (count < CAPIMSG_BASELEN)
+		return -EINVAL;
+
 	skb = alloc_skb(count, GFP_USER);
 	if (!skb)
 		return -ENOMEM;
@@ -698,7 +701,8 @@ capi_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos
 	}
 	mlen = CAPIMSG_LEN(skb->data);
 	if (CAPIMSG_CMD(skb->data) == CAPI_DATA_B3_REQ) {
-		if ((size_t)(mlen + CAPIMSG_DATALEN(skb->data)) != count) {
+		if (count < CAPI_DATA_B3_REQ_LEN ||
+		    (size_t)(mlen + CAPIMSG_DATALEN(skb->data)) != count) {
 			kfree_skb(skb);
 			return -EINVAL;
 		}
@@ -711,6 +715,10 @@ capi_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos
 	CAPIMSG_SETAPPID(skb->data, cdev->ap.applid);
 
 	if (CAPIMSG_CMD(skb->data) == CAPI_DISCONNECT_B3_RESP) {
+		if (count < CAPI_DISCONNECT_B3_RESP_LEN) {
+			kfree_skb(skb);
+			return -EINVAL;
+		}
 		mutex_lock(&cdev->lock);
 		capincci_free(cdev, CAPIMSG_NCCI(skb->data));
 		mutex_unlock(&cdev->lock);
diff --git a/include/uapi/linux/isdn/capicmd.h b/include/uapi/linux/isdn/capicmd.h
index 4941628a4fb9..5ec88e7548a9 100644
--- a/include/uapi/linux/isdn/capicmd.h
+++ b/include/uapi/linux/isdn/capicmd.h
@@ -16,6 +16,7 @@
 #define CAPI_MSG_BASELEN		8
 #define CAPI_DATA_B3_REQ_LEN		(CAPI_MSG_BASELEN+4+4+2+2+2)
 #define CAPI_DATA_B3_RESP_LEN		(CAPI_MSG_BASELEN+4+2)
+#define CAPI_DISCONNECT_B3_RESP_LEN	(CAPI_MSG_BASELEN+4)
 
 /*----- CAPI commands -----*/
 #define CAPI_ALERT		    0x01
-- 
2.21.0


From 81377aee09653da3006d312f4647478b6573b051 Mon Sep 17 00:00:00 2001
From: Steffen Klassert <steffen.klassert@secunet.com>
Date: Thu, 12 Sep 2019 13:01:44 +0200
Subject: [PATCH 05/15] ixgbe: Fix secpath usage for IPsec TX offload.

[ Upstream commit f39b683d35dfa93a58f1b400a8ec0ff81296b37c ]

The ixgbe driver currently does IPsec TX offloading
based on an existing secpath. However, the secpath
can also come from the RX side, in this case it is
misinterpreted for TX offload and the packets are
dropped with a "bad sa_idx" error. Fix this by using
the xfrm_offload() function to test for TX offload.

Fixes: 592594704761 ("ixgbe: process the Tx ipsec offload")
Reported-by: Michael Marley <michael@michaelmarley.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 410d5d3aa393..2c3da1516036 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -34,6 +34,7 @@
 #include <net/tc_act/tc_mirred.h>
 #include <net/vxlan.h>
 #include <net/mpls.h>
+#include <net/xfrm.h>
 
 #include "ixgbe.h"
 #include "ixgbe_common.h"
@@ -8599,7 +8600,8 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb,
 #endif /* IXGBE_FCOE */
 
 #ifdef CONFIG_XFRM_OFFLOAD
-	if (skb->sp && !ixgbe_ipsec_tx(tx_ring, first, &ipsec_tx))
+	if (xfrm_offload(skb) &&
+	    !ixgbe_ipsec_tx(tx_ring, first, &ipsec_tx))
 		goto out_drop;
 #endif
 	tso = ixgbe_tso(tx_ring, first, &hdr_len, &ipsec_tx);
-- 
2.21.0


From acfa8892de6e235458b038fa21686b5517089856 Mon Sep 17 00:00:00 2001
From: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Date: Tue, 10 Sep 2019 14:02:57 -0600
Subject: [PATCH 06/15] net: Fix null de-reference of device refcount

[ Upstream commit 10cc514f451a0f239aa34f91bc9dc954a9397840 ]

In event of failure during register_netdevice, free_netdev is
invoked immediately. free_netdev assumes that all the netdevice
refcounts have been dropped prior to it being called and as a
result frees and clears out the refcount pointer.

However, this is not necessarily true as some of the operations
in the NETDEV_UNREGISTER notifier handlers queue RCU callbacks for
invocation after a grace period. The IPv4 callback in_dev_rcu_put
tries to access the refcount after free_netdev is called which
leads to a null de-reference-

44837.761523:   <6> Unable to handle kernel paging request at
                    virtual address 0000004a88287000
44837.761651:   <2> pc : in_dev_finish_destroy+0x4c/0xc8
44837.761654:   <2> lr : in_dev_finish_destroy+0x2c/0xc8
44837.762393:   <2> Call trace:
44837.762398:   <2>  in_dev_finish_destroy+0x4c/0xc8
44837.762404:   <2>  in_dev_rcu_put+0x24/0x30
44837.762412:   <2>  rcu_nocb_kthread+0x43c/0x468
44837.762418:   <2>  kthread+0x118/0x128
44837.762424:   <2>  ret_from_fork+0x10/0x1c

Fix this by waiting for the completion of the call_rcu() in
case of register_netdevice errors.

Fixes: 93ee31f14f6f ("[NET]: Fix free_netdev on register_netdev failure.")
Cc: Sean Tranchetti <stranche@codeaurora.org>
Signed-off-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/core/dev.c b/net/core/dev.c
index e4b4cb40da00..ddd8aab20adf 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8562,6 +8562,8 @@ int register_netdevice(struct net_device *dev)
 	ret = notifier_to_errno(ret);
 	if (ret) {
 		rollback_registered(dev);
+		rcu_barrier();
+
 		dev->reg_state = NETREG_UNREGISTERED;
 	}
 	/*
-- 
2.21.0


From 78a7586cd144681929a6c15c2821177c47a2ea8a Mon Sep 17 00:00:00 2001
From: Shmulik Ladkani <shmulik@metanetworks.com>
Date: Fri, 6 Sep 2019 12:23:50 +0300
Subject: [PATCH 07/15] net: gso: Fix skb_segment splat when splitting gso_size
 mangled skb having linear-headed frag_list

[ Upstream commit 3dcbdb134f329842a38f0e6797191b885ab00a00 ]

Historically, support for frag_list packets entering skb_segment() was
limited to frag_list members terminating on exact same gso_size
boundaries. This is verified with a BUG_ON since commit 89319d3801d1
("net: Add frag_list support to skb_segment"), quote:

    As such we require all frag_list members terminate on exact MSS
    boundaries.  This is checked using BUG_ON.
    As there should only be one producer in the kernel of such packets,
    namely GRO, this requirement should not be difficult to maintain.

However, since commit 6578171a7ff0 ("bpf: add bpf_skb_change_proto helper"),
the "exact MSS boundaries" assumption no longer holds:
An eBPF program using bpf_skb_change_proto() DOES modify 'gso_size', but
leaves the frag_list members as originally merged by GRO with the
original 'gso_size'. Example of such programs are bpf-based NAT46 or
NAT64.

This lead to a kernel BUG_ON for flows involving:
 - GRO generating a frag_list skb
 - bpf program performing bpf_skb_change_proto() or bpf_skb_adjust_room()
 - skb_segment() of the skb

See example BUG_ON reports in [0].

In commit 13acc94eff12 ("net: permit skb_segment on head_frag frag_list skb"),
skb_segment() was modified to support the "gso_size mangling" case of
a frag_list GRO'ed skb, but *only* for frag_list members having
head_frag==true (having a page-fragment head).

Alas, GRO packets having frag_list members with a linear kmalloced head
(head_frag==false) still hit the BUG_ON.

This commit adds support to skb_segment() for a 'head_skb' packet having
a frag_list whose members are *non* head_frag, with gso_size mangled, by
disabling SG and thus falling-back to copying the data from the given
'head_skb' into the generated segmented skbs - as suggested by Willem de
Bruijn [1].

Since this approach involves the penalty of skb_copy_and_csum_bits()
when building the segments, care was taken in order to enable this
solution only when required:
 - untrusted gso_size, by testing SKB_GSO_DODGY is set
   (SKB_GSO_DODGY is set by any gso_size mangling functions in
    net/core/filter.c)
 - the frag_list is non empty, its item is a non head_frag, *and* the
   headlen of the given 'head_skb' does not match the gso_size.

[0]
https://lore.kernel.org/netdev/20190826170724.25ff616f@pixies/
https://lore.kernel.org/netdev/9265b93f-253d-6b8c-f2b8-4b54eff1835c@fb.com/

[1]
https://lore.kernel.org/netdev/CA+FuTSfVsgNDi7c=GUU8nMg2hWxF2SjCNLXetHeVPdnxAW5K-w@mail.gmail.com/

Fixes: 6578171a7ff0 ("bpf: add bpf_skb_change_proto helper")
Suggested-by: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Alexander Duyck <alexander.duyck@gmail.com>
Signed-off-by: Shmulik Ladkani <shmulik.ladkani@gmail.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 9b9f696281a9..0629ca89ab74 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3530,6 +3530,25 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 	int pos;
 	int dummy;
 
+	if (list_skb && !list_skb->head_frag && skb_headlen(list_skb) &&
+	    (skb_shinfo(head_skb)->gso_type & SKB_GSO_DODGY)) {
+		/* gso_size is untrusted, and we have a frag_list with a linear
+		 * non head_frag head.
+		 *
+		 * (we assume checking the first list_skb member suffices;
+		 * i.e if either of the list_skb members have non head_frag
+		 * head, then the first one has too).
+		 *
+		 * If head_skb's headlen does not fit requested gso_size, it
+		 * means that the frag_list members do NOT terminate on exact
+		 * gso_size boundaries. Hence we cannot perform skb_frag_t page
+		 * sharing. Therefore we must fallback to copying the frag_list
+		 * skbs; we do so by disabling SG.
+		 */
+		if (mss != GSO_BY_FRAGS && mss != skb_headlen(head_skb))
+			features &= ~NETIF_F_SG;
+	}
+
 	__skb_push(head_skb, doffset);
 	proto = skb_network_protocol(head_skb, &dummy);
 	if (unlikely(!proto))
-- 
2.21.0


From a81e3a4952f8b6c756666fe41320c3919505f0cc Mon Sep 17 00:00:00 2001
From: Stefan Chulski <stefanc@marvell.com>
Date: Thu, 5 Sep 2019 19:46:18 +0300
Subject: [PATCH 08/15] net: phylink: Fix flow control resolution

[ Upstream commit 63b2ed4e10b2e6c913e1d8cdd728e7fba4115a3d ]

Regarding to IEEE 802.3-2015 standard section 2
28B.3 Priority resolution - Table 28-3 - Pause resolution

In case of Local device Pause=1 AsymDir=0, Link partner
Pause=1 AsymDir=1, Local device resolution should be enable PAUSE
transmit, disable PAUSE receive.
And in case of Local device Pause=1 AsymDir=1, Link partner
Pause=1 AsymDir=0, Local device resolution should be enable PAUSE
receive, disable PAUSE transmit.

Fixes: 9525ae83959b ("phylink: add phylink infrastructure")
Signed-off-by: Stefan Chulski <stefanc@marvell.com>
Reported-by: Shaul Ben-Mayor <shaulb@marvell.com>
Acked-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phylink.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 2e8056d48f4a..723611ac9102 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -380,8 +380,8 @@ static void phylink_get_fixed_state(struct phylink *pl, struct phylink_link_stat
  *  Local device  Link partner
  *  Pause AsymDir Pause AsymDir Result
  *    1     X       1     X     TX+RX
- *    0     1       1     1     RX
- *    1     1       0     1     TX
+ *    0     1       1     1     TX
+ *    1     1       0     1     RX
  */
 static void phylink_resolve_flow(struct phylink *pl,
 				 struct phylink_link_state *state)
@@ -402,7 +402,7 @@ static void phylink_resolve_flow(struct phylink *pl,
 			new_pause = MLO_PAUSE_TX | MLO_PAUSE_RX;
 		else if (pause & MLO_PAUSE_ASYM)
 			new_pause = state->pause & MLO_PAUSE_SYM ?
-				 MLO_PAUSE_RX : MLO_PAUSE_TX;
+				 MLO_PAUSE_TX : MLO_PAUSE_RX;
 	} else {
 		new_pause = pl->link_config.pause & MLO_PAUSE_TXRX_MASK;
 	}
-- 
2.21.0


From 7f14cdbb1b046b9e253b8a762156e051d9e23d5c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 5 Sep 2019 05:20:22 -0700
Subject: [PATCH 09/15] net: sched: fix reordering issues

[ Upstream commit b88dd52c62bb5c5d58f0963287f41fd084352c57 ]

Whenever MQ is not used on a multiqueue device, we experience
serious reordering problems. Bisection found the cited
commit.

The issue can be described this way :

- A single qdisc hierarchy is shared by all transmit queues.
  (eg : tc qdisc replace dev eth0 root fq_codel)

- When/if try_bulk_dequeue_skb_slow() dequeues a packet targetting
  a different transmit queue than the one used to build a packet train,
  we stop building the current list and save the 'bad' skb (P1) in a
  special queue. (bad_txq)

- When dequeue_skb() calls qdisc_dequeue_skb_bad_txq() and finds this
  skb (P1), it checks if the associated transmit queues is still in frozen
  state. If the queue is still blocked (by BQL or NIC tx ring full),
  we leave the skb in bad_txq and return NULL.

- dequeue_skb() calls q->dequeue() to get another packet (P2)

  The other packet can target the problematic queue (that we found
  in frozen state for the bad_txq packet), but another cpu just ran
  TX completion and made room in the txq that is now ready to accept
  new packets.

- Packet P2 is sent while P1 is still held in bad_txq, P1 might be sent
  at next round. In practice P2 is the lead of a big packet train
  (P2,P3,P4 ...) filling the BQL budget and delaying P1 by many packets :/

To solve this problem, we have to block the dequeue process as long
as the first packet in bad_txq can not be sent. Reordering issues
disappear and no side effects have been seen.

Fixes: a53851e2c321 ("net: sched: explicit locking in gso_cpu fallback")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: John Fastabend <john.fastabend@gmail.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_generic.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 77b289da7763..875f521bce0d 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -49,6 +49,8 @@ EXPORT_SYMBOL(default_qdisc_ops);
  * - updates to tree and tree walking are only done under the rtnl mutex.
  */
 
+#define SKB_XOFF_MAGIC ((struct sk_buff *)1UL)
+
 static inline struct sk_buff *__skb_dequeue_bad_txq(struct Qdisc *q)
 {
 	const struct netdev_queue *txq = q->dev_queue;
@@ -74,7 +76,7 @@ static inline struct sk_buff *__skb_dequeue_bad_txq(struct Qdisc *q)
 				q->q.qlen--;
 			}
 		} else {
-			skb = NULL;
+			skb = SKB_XOFF_MAGIC;
 		}
 	}
 
@@ -272,8 +274,11 @@ static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate,
 		return skb;
 
 	skb = qdisc_dequeue_skb_bad_txq(q);
-	if (unlikely(skb))
+	if (unlikely(skb)) {
+		if (skb == SKB_XOFF_MAGIC)
+			return NULL;
 		goto bulk;
+	}
 	skb = q->dequeue(q);
 	if (skb) {
 bulk:
-- 
2.21.0


From 78875685b4f86f2cafcd02de577cde6c72f86c1b Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sun, 8 Sep 2019 13:40:51 -0700
Subject: [PATCH 10/15] sch_hhf: ensure quantum and hhf_non_hh_weight are
 non-zero

[ Upstream commit d4d6ec6dac07f263f06d847d6f732d6855522845 ]

In case of TCA_HHF_NON_HH_WEIGHT or TCA_HHF_QUANTUM is zero,
it would make no progress inside the loop in hhf_dequeue() thus
kernel would get stuck.

Fix this by checking this corner case in hhf_change().

Fixes: 10239edf86f1 ("net-qdisc-hhf: Heavy-Hitter Filter (HHF) qdisc")
Reported-by: syzbot+bc6297c11f19ee807dc2@syzkaller.appspotmail.com
Reported-by: syzbot+041483004a7f45f1f20a@syzkaller.appspotmail.com
Reported-by: syzbot+55be5f513bed37fc4367@syzkaller.appspotmail.com
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Cc: Terry Lam <vtlam@google.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_hhf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c
index c3a8388dcdf6..a80fe8aa8527 100644
--- a/net/sched/sch_hhf.c
+++ b/net/sched/sch_hhf.c
@@ -529,7 +529,7 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt,
 		new_hhf_non_hh_weight = nla_get_u32(tb[TCA_HHF_NON_HH_WEIGHT]);
 
 	non_hh_quantum = (u64)new_quantum * new_hhf_non_hh_weight;
-	if (non_hh_quantum > INT_MAX)
+	if (non_hh_quantum == 0 || non_hh_quantum > INT_MAX)
 		return -EINVAL;
 
 	sch_tree_lock(sch);
-- 
2.21.0


From 3b90d0731ba96546659b92e9d5482020c9187a4f Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Wed, 11 Sep 2019 18:02:39 +0200
Subject: [PATCH 11/15] sctp: Fix the link time qualifier of
 'sctp_ctrlsock_exit()'

[ Upstream commit b456d72412ca8797234449c25815e82f4e1426c0 ]

The '.exit' functions from 'pernet_operations' structure should be marked
as __net_exit, not __net_init.

Fixes: 8e2d61e0aed2 ("sctp: fix race on protocol/netns initialization")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/protocol.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index d97b2b4b7a8b..6d36f74ad295 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -1350,7 +1350,7 @@ static int __net_init sctp_ctrlsock_init(struct net *net)
 	return status;
 }
 
-static void __net_init sctp_ctrlsock_exit(struct net *net)
+static void __net_exit sctp_ctrlsock_exit(struct net *net)
 {
 	/* Free the control endpoint.  */
 	inet_ctl_sock_destroy(net->sctp.ctl_sock);
-- 
2.21.0


From dde8e25667af4394e2fdc3f0c23768a5097fba8e Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 2 Sep 2019 23:24:21 +0800
Subject: [PATCH 12/15] sctp: use transport pf_retrans in
 sctp_do_8_2_transport_strike

[ Upstream commit 10eb56c582c557c629271f1ee31e15e7a9b2558b ]

Transport should use its own pf_retrans to do the error_count
check, instead of asoc's. Otherwise, it's meaningless to make
pf_retrans per transport.

Fixes: 5aa93bcf66f4 ("sctp: Implement quick failover draft from tsvwg")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sm_sideeffect.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index 28adac31f0ff..de8a82bc6b42 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -562,7 +562,7 @@ static void sctp_do_8_2_transport_strike(struct sctp_cmd_seq *commands,
 	if (net->sctp.pf_enable &&
 	   (transport->state == SCTP_ACTIVE) &&
 	   (transport->error_count < transport->pathmaxrxt) &&
-	   (transport->error_count > asoc->pf_retrans)) {
+	   (transport->error_count > transport->pf_retrans)) {
 
 		sctp_assoc_control_transport(asoc, transport,
 					     SCTP_TRANSPORT_PF,
-- 
2.21.0


From c0445ee2bf8bb2a91cc6726fe6a64450eebbb460 Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Mon, 9 Sep 2019 16:56:02 -0400
Subject: [PATCH 13/15] tcp: fix tcp_ecn_withdraw_cwr() to clear
 TCP_ECN_QUEUE_CWR

[ Upstream commit af38d07ed391b21f7405fa1f936ca9686787d6d2 ]

Fix tcp_ecn_withdraw_cwr() to clear the correct bit:
TCP_ECN_QUEUE_CWR.

Rationale: basically, TCP_ECN_DEMAND_CWR is a bit that is purely about
the behavior of data receivers, and deciding whether to reflect
incoming IP ECN CE marks as outgoing TCP th->ece marks. The
TCP_ECN_QUEUE_CWR bit is purely about the behavior of data senders,
and deciding whether to send CWR. The tcp_ecn_withdraw_cwr() function
is only called from tcp_undo_cwnd_reduction() by data senders during
an undo, so it should zero the sender-side state,
TCP_ECN_QUEUE_CWR. It does not make sense to stop the reflection of
incoming CE bits on incoming data packets just because outgoing
packets were spuriously retransmitted.

The bug has been reproduced with packetdrill to manifest in a scenario
with RFC3168 ECN, with an incoming data packet with CE bit set and
carrying a TCP timestamp value that causes cwnd undo. Before this fix,
the IP CE bit was ignored and not reflected in the TCP ECE header bit,
and sender sent a TCP CWR ('W') bit on the next outgoing data packet,
even though the cwnd reduction had been undone.  After this fix, the
sender properly reflects the CE bit and does not set the W bit.

Note: the bug actually predates 2005 git history; this Fixes footer is
chosen to be the oldest SHA1 I have tested (from Sep 2007) for which
the patch applies cleanly (since before this commit the code was in a
.h file).

Fixes: bdf1ee5d3bd3 ("[TCP]: Move code from tcp_ecn.h to tcp*.c and tcp.h & remove it")
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 4a8869d39662..14a6a489937c 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -260,7 +260,7 @@ static void tcp_ecn_accept_cwr(struct sock *sk, const struct sk_buff *skb)
 
 static void tcp_ecn_withdraw_cwr(struct tcp_sock *tp)
 {
-	tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
+	tp->ecn_flags &= ~TCP_ECN_QUEUE_CWR;
 }
 
 static void __tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb)
-- 
2.21.0


From af0114b790bfef73fc3a5b54896db354a3fb3c51 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 3 Sep 2019 17:53:12 +0800
Subject: [PATCH 14/15] tipc: add NULL pointer check before calling kfree_rcu

[ Upstream commit 42dec1dbe38239cf91cc1f4df7830c66276ced37 ]

Unlike kfree(p), kfree_rcu(p, rcu) won't do NULL pointer check. When
tipc_nametbl_remove_publ returns NULL, the panic below happens:

   BUG: unable to handle kernel NULL pointer dereference at 0000000000000068
   RIP: 0010:__call_rcu+0x1d/0x290
   Call Trace:
    <IRQ>
    tipc_publ_notify+0xa9/0x170 [tipc]
    tipc_node_write_unlock+0x8d/0x100 [tipc]
    tipc_node_link_down+0xae/0x1d0 [tipc]
    tipc_node_check_dest+0x3ea/0x8f0 [tipc]
    ? tipc_disc_rcv+0x2c7/0x430 [tipc]
    tipc_disc_rcv+0x2c7/0x430 [tipc]
    ? tipc_rcv+0x6bb/0xf20 [tipc]
    tipc_rcv+0x6bb/0xf20 [tipc]
    ? ip_route_input_slow+0x9cf/0xb10
    tipc_udp_recv+0x195/0x1e0 [tipc]
    ? tipc_udp_is_known_peer+0x80/0x80 [tipc]
    udp_queue_rcv_skb+0x180/0x460
    udp_unicast_rcv_skb.isra.56+0x75/0x90
    __udp4_lib_rcv+0x4ce/0xb90
    ip_local_deliver_finish+0x11c/0x210
    ip_local_deliver+0x6b/0xe0
    ? ip_rcv_finish+0xa9/0x410
    ip_rcv+0x273/0x362

Fixes: 97ede29e80ee ("tipc: convert name table read-write lock to RCU")
Reported-by: Li Shuang <shuali@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/name_distr.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c
index 3cfeb9df64b0..e0a3dd424d8c 100644
--- a/net/tipc/name_distr.c
+++ b/net/tipc/name_distr.c
@@ -221,7 +221,8 @@ static void tipc_publ_purge(struct net *net, struct publication *publ, u32 addr)
 		       publ->key);
 	}
 
-	kfree_rcu(p, rcu);
+	if (p)
+		kfree_rcu(p, rcu);
 }
 
 /**
-- 
2.21.0


From d8a60d98347396b13da43161fe38d89805bcbf96 Mon Sep 17 00:00:00 2001
From: Yang Yingliang <yangyingliang@huawei.com>
Date: Tue, 10 Sep 2019 18:56:57 +0800
Subject: [PATCH 15/15] tun: fix use-after-free when register netdev failed

[ Upstream commit 77f22f92dff8e7b45c7786a430626d38071d4670 ]

I got a UAF repport in tun driver when doing fuzzy test:

[  466.269490] ==================================================================
[  466.271792] BUG: KASAN: use-after-free in tun_chr_read_iter+0x2ca/0x2d0
[  466.271806] Read of size 8 at addr ffff888372139250 by task tun-test/2699
[  466.271810]
[  466.271824] CPU: 1 PID: 2699 Comm: tun-test Not tainted 5.3.0-rc1-00001-g5a9433db2614-dirty #427
[  466.271833] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014
[  466.271838] Call Trace:
[  466.271858]  dump_stack+0xca/0x13e
[  466.271871]  ? tun_chr_read_iter+0x2ca/0x2d0
[  466.271890]  print_address_description+0x79/0x440
[  466.271906]  ? vprintk_func+0x5e/0xf0
[  466.271920]  ? tun_chr_read_iter+0x2ca/0x2d0
[  466.271935]  __kasan_report+0x15c/0x1df
[  466.271958]  ? tun_chr_read_iter+0x2ca/0x2d0
[  466.271976]  kasan_report+0xe/0x20
[  466.271987]  tun_chr_read_iter+0x2ca/0x2d0
[  466.272013]  do_iter_readv_writev+0x4b7/0x740
[  466.272032]  ? default_llseek+0x2d0/0x2d0
[  466.272072]  do_iter_read+0x1c5/0x5e0
[  466.272110]  vfs_readv+0x108/0x180
[  466.299007]  ? compat_rw_copy_check_uvector+0x440/0x440
[  466.299020]  ? fsnotify+0x888/0xd50
[  466.299040]  ? __fsnotify_parent+0xd0/0x350
[  466.299064]  ? fsnotify_first_mark+0x1e0/0x1e0
[  466.304548]  ? vfs_write+0x264/0x510
[  466.304569]  ? ksys_write+0x101/0x210
[  466.304591]  ? do_preadv+0x116/0x1a0
[  466.304609]  do_preadv+0x116/0x1a0
[  466.309829]  do_syscall_64+0xc8/0x600
[  466.309849]  entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  466.309861] RIP: 0033:0x4560f9
[  466.309875] Code: 00 00 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48
[  466.309889] RSP: 002b:00007ffffa5166e8 EFLAGS: 00000206 ORIG_RAX: 0000000000000127
[  466.322992] RAX: ffffffffffffffda RBX: 0000000000400460 RCX: 00000000004560f9
[  466.322999] RDX: 0000000000000003 RSI: 00000000200008c0 RDI: 0000000000000003
[  466.323007] RBP: 00007ffffa516700 R08: 0000000000000004 R09: 0000000000000000
[  466.323014] R10: 0000000000000000 R11: 0000000000000206 R12: 000000000040cb10
[  466.323021] R13: 0000000000000000 R14: 00000000006d7018 R15: 0000000000000000
[  466.323057]
[  466.323064] Allocated by task 2605:
[  466.335165]  save_stack+0x19/0x80
[  466.336240]  __kasan_kmalloc.constprop.8+0xa0/0xd0
[  466.337755]  kmem_cache_alloc+0xe8/0x320
[  466.339050]  getname_flags+0xca/0x560
[  466.340229]  user_path_at_empty+0x2c/0x50
[  466.341508]  vfs_statx+0xe6/0x190
[  466.342619]  __do_sys_newstat+0x81/0x100
[  466.343908]  do_syscall_64+0xc8/0x600
[  466.345303]  entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  466.347034]
[  466.347517] Freed by task 2605:
[  466.348471]  save_stack+0x19/0x80
[  466.349476]  __kasan_slab_free+0x12e/0x180
[  466.350726]  kmem_cache_free+0xc8/0x430
[  466.351874]  putname+0xe2/0x120
[  466.352921]  filename_lookup+0x257/0x3e0
[  466.354319]  vfs_statx+0xe6/0x190
[  466.355498]  __do_sys_newstat+0x81/0x100
[  466.356889]  do_syscall_64+0xc8/0x600
[  466.358037]  entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  466.359567]
[  466.360050] The buggy address belongs to the object at ffff888372139100
[  466.360050]  which belongs to the cache names_cache of size 4096
[  466.363735] The buggy address is located 336 bytes inside of
[  466.363735]  4096-byte region [ffff888372139100, ffff88837213a100)
[  466.367179] The buggy address belongs to the page:
[  466.368604] page:ffffea000dc84e00 refcount:1 mapcount:0 mapping:ffff8883df1b4f00 index:0x0 compound_mapcount: 0
[  466.371582] flags: 0x2fffff80010200(slab|head)
[  466.372910] raw: 002fffff80010200 dead000000000100 dead000000000122 ffff8883df1b4f00
[  466.375209] raw: 0000000000000000 0000000000070007 00000001ffffffff 0000000000000000
[  466.377778] page dumped because: kasan: bad access detected
[  466.379730]
[  466.380288] Memory state around the buggy address:
[  466.381844]  ffff888372139100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  466.384009]  ffff888372139180: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  466.386131] >ffff888372139200: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  466.388257]                                                  ^
[  466.390234]  ffff888372139280: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  466.392512]  ffff888372139300: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  466.394667] ==================================================================

tun_chr_read_iter() accessed the memory which freed by free_netdev()
called by tun_set_iff():

        CPUA                                           CPUB
  tun_set_iff()
    alloc_netdev_mqs()
    tun_attach()
                                                  tun_chr_read_iter()
                                                    tun_get()
                                                    tun_do_read()
                                                      tun_ring_recv()
    register_netdevice() <-- inject error
    goto err_detach
    tun_detach_all() <-- set RCV_SHUTDOWN
    free_netdev() <-- called from
                     err_free_dev path
      netdev_freemem() <-- free the memory
                        without check refcount
      (In this path, the refcount cannot prevent
       freeing the memory of dev, and the memory
       will be used by dev_put() called by
       tun_chr_read_iter() on CPUB.)
                                                     (Break from tun_ring_recv(),
                                                     because RCV_SHUTDOWN is set)
                                                   tun_put()
                                                     dev_put() <-- use the memory
                                                                   freed by netdev_freemem()

Put the publishing of tfile->tun after register_netdevice(),
so tun_get() won't get the tun pointer that freed by
err_detach path if register_netdevice() failed.

Fixes: eb0fb363f920 ("tuntap: attach queue 0 before registering netdevice")
Reported-by: Hulk Robot <hulkci@huawei.com>
Suggested-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 5fa7047ea361..e1ac1c57089f 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -801,7 +801,8 @@ static void tun_detach_all(struct net_device *dev)
 }
 
 static int tun_attach(struct tun_struct *tun, struct file *file,
-		      bool skip_filter, bool napi, bool napi_frags)
+		      bool skip_filter, bool napi, bool napi_frags,
+		      bool publish_tun)
 {
 	struct tun_file *tfile = file->private_data;
 	struct net_device *dev = tun->dev;
@@ -881,7 +882,8 @@ static int tun_attach(struct tun_struct *tun, struct file *file,
 	 * initialized tfile; otherwise we risk using half-initialized
 	 * object.
 	 */
-	rcu_assign_pointer(tfile->tun, tun);
+	if (publish_tun)
+		rcu_assign_pointer(tfile->tun, tun);
 	rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile);
 	tun->numqueues++;
 	tun_set_real_num_queues(tun);
@@ -2553,7 +2555,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 
 		err = tun_attach(tun, file, ifr->ifr_flags & IFF_NOFILTER,
 				 ifr->ifr_flags & IFF_NAPI,
-				 ifr->ifr_flags & IFF_NAPI_FRAGS);
+				 ifr->ifr_flags & IFF_NAPI_FRAGS, true);
 		if (err < 0)
 			return err;
 
@@ -2652,13 +2654,17 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 
 		INIT_LIST_HEAD(&tun->disabled);
 		err = tun_attach(tun, file, false, ifr->ifr_flags & IFF_NAPI,
-				 ifr->ifr_flags & IFF_NAPI_FRAGS);
+				 ifr->ifr_flags & IFF_NAPI_FRAGS, false);
 		if (err < 0)
 			goto err_free_flow;
 
 		err = register_netdevice(tun->dev);
 		if (err < 0)
 			goto err_detach;
+		/* free_netdev() won't check refcnt, to aovid race
+		 * with dev_put() we need publish tun after registration.
+		 */
+		rcu_assign_pointer(tfile->tun, tun);
 	}
 
 	netif_carrier_on(tun->dev);
@@ -2802,7 +2808,7 @@ static int tun_set_queue(struct file *file, struct ifreq *ifr)
 		if (ret < 0)
 			goto unlock;
 		ret = tun_attach(tun, file, false, tun->flags & IFF_NAPI,
-				 tun->flags & IFF_NAPI_FRAGS);
+				 tun->flags & IFF_NAPI_FRAGS, true);
 	} else if (ifr->ifr_flags & IFF_DETACH_QUEUE) {
 		tun = rtnl_dereference(tfile->tun);
 		if (!tun || !(tun->flags & IFF_MULTI_QUEUE) || tfile->detached)
-- 
2.21.0


[-- Attachment #3: net_52.mbox --]
[-- Type: Application/Octet-Stream, Size: 51025 bytes --]

From 8138bac1bbb180e66a6034f809c71b7ae7704170 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Fri, 6 Sep 2019 11:47:02 +0200
Subject: [PATCH 01/21] bridge/mdb: remove wrong use of NLM_F_MULTI

[ Upstream commit 94a72b3f024fc7e9ab640897a1e38583a470659d ]

NLM_F_MULTI must be used only when a NLMSG_DONE message is sent at the end.
In fact, NLMSG_DONE is sent only at the end of a dump.

Libraries like libnl will wait forever for NLMSG_DONE.

Fixes: 949f1e39a617 ("bridge: mdb: notify on router port add and del")
CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_mdb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index bf6acd34234d..63f9c08625f0 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -437,7 +437,7 @@ static int nlmsg_populate_rtr_fill(struct sk_buff *skb,
 	struct nlmsghdr *nlh;
 	struct nlattr *nest;
 
-	nlh = nlmsg_put(skb, pid, seq, type, sizeof(*bpm), NLM_F_MULTI);
+	nlh = nlmsg_put(skb, pid, seq, type, sizeof(*bpm), 0);
 	if (!nlh)
 		return -EMSGSIZE;
 
-- 
2.21.0


From adb8fe50931fcce3897f8b99f16c26ee1a2837a7 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Thu, 12 Sep 2019 10:42:00 +0200
Subject: [PATCH 02/21] cdc_ether: fix rndis support for Mediatek based
 smartphones
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 4d7ffcf3bf1be98d876c570cab8fc31d9fa92725 ]

A Mediatek based smartphone owner reports problems with USB
tethering in Linux.  The verbose USB listing shows a rndis_host
interface pair (e0/01/03 + 10/00/00), but the driver fails to
bind with

[  355.960428] usb 1-4: bad CDC descriptors

The problem is a failsafe test intended to filter out ACM serial
functions using the same 02/02/ff class/subclass/protocol as RNDIS.
The serial functions are recognized by their non-zero bmCapabilities.

No RNDIS function with non-zero bmCapabilities were known at the time
this failsafe was added. But it turns out that some Wireless class
RNDIS functions are using the bmCapabilities field. These functions
are uniquely identified as RNDIS by their class/subclass/protocol, so
the failing test can safely be disabled.  The same applies to the two
types of Misc class RNDIS functions.

Applying the failsafe to Communication class functions only retains
the original functionality, and fixes the problem for the Mediatek based
smartphone.

Tow examples of CDC functional descriptors with non-zero bmCapabilities
from Wireless class RNDIS functions are:

0e8d:000a  Mediatek Crosscall Spider X5 3G Phone

      CDC Header:
        bcdCDC               1.10
      CDC ACM:
        bmCapabilities       0x0f
          connection notifications
          sends break
          line coding and serial state
          get/set/clear comm features
      CDC Union:
        bMasterInterface        0
        bSlaveInterface         1
      CDC Call Management:
        bmCapabilities       0x03
          call management
          use DataInterface
        bDataInterface          1

and

19d2:1023  ZTE K4201-z

      CDC Header:
        bcdCDC               1.10
      CDC ACM:
        bmCapabilities       0x02
          line coding and serial state
      CDC Call Management:
        bmCapabilities       0x03
          call management
          use DataInterface
        bDataInterface          1
      CDC Union:
        bMasterInterface        0
        bSlaveInterface         1

The Mediatek example is believed to apply to most smartphones with
Mediatek firmware.  The ZTE example is most likely also part of a larger
family of devices/firmwares.

Suggested-by: Lars Melin <larsm17@gmail.com>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ether.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index 8458e88c18e9..32f53de5b1fe 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -206,7 +206,15 @@ int usbnet_generic_cdc_bind(struct usbnet *dev, struct usb_interface *intf)
 		goto bad_desc;
 	}
 skip:
-	if (rndis && header.usb_cdc_acm_descriptor &&
+	/* Communcation class functions with bmCapabilities are not
+	 * RNDIS.  But some Wireless class RNDIS functions use
+	 * bmCapabilities for their own purpose. The failsafe is
+	 * therefore applied only to Communication class RNDIS
+	 * functions.  The rndis test is redundant, but a cheap
+	 * optimization.
+	 */
+	if (rndis && is_rndis(&intf->cur_altsetting->desc) &&
+	    header.usb_cdc_acm_descriptor &&
 	    header.usb_cdc_acm_descriptor->bmCapabilities) {
 		dev_dbg(&intf->dev,
 			"ACM capabilities %02x, not really RNDIS?\n",
-- 
2.21.0


From cef8f304ef1275cdfd023825b56c0738dbdf0722 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Tue, 10 Sep 2019 13:29:59 +0200
Subject: [PATCH 03/21] ipv6: Fix the link time qualifier of
 'ping_v6_proc_exit_net()'

[ Upstream commit d23dbc479a8e813db4161a695d67da0e36557846 ]

The '.exit' functions from 'pernet_operations' structure should be marked
as __net_exit, not __net_init.

Fixes: d862e5461423 ("net: ipv6: Implement /proc/net/icmp6.")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ping.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 87d2d8c1db7c..98ac32b49d8c 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -223,7 +223,7 @@ static int __net_init ping_v6_proc_init_net(struct net *net)
 	return 0;
 }
 
-static void __net_init ping_v6_proc_exit_net(struct net *net)
+static void __net_exit ping_v6_proc_exit_net(struct net *net)
 {
 	remove_proc_entry("icmp6", net->proc_net);
 }
-- 
2.21.0


From 64fa75938354f231d66708a3570c360fbb3d87e4 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Thu, 5 Sep 2019 19:36:37 -0700
Subject: [PATCH 04/21] isdn/capi: check message length in capi_write()

[ Upstream commit fe163e534e5eecdfd7b5920b0dfd24c458ee85d6 ]

syzbot reported:

    BUG: KMSAN: uninit-value in capi_write+0x791/0xa90 drivers/isdn/capi/capi.c:700
    CPU: 0 PID: 10025 Comm: syz-executor379 Not tainted 4.20.0-rc7+ #2
    Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
    Call Trace:
      __dump_stack lib/dump_stack.c:77 [inline]
      dump_stack+0x173/0x1d0 lib/dump_stack.c:113
      kmsan_report+0x12e/0x2a0 mm/kmsan/kmsan.c:613
      __msan_warning+0x82/0xf0 mm/kmsan/kmsan_instr.c:313
      capi_write+0x791/0xa90 drivers/isdn/capi/capi.c:700
      do_loop_readv_writev fs/read_write.c:703 [inline]
      do_iter_write+0x83e/0xd80 fs/read_write.c:961
      vfs_writev fs/read_write.c:1004 [inline]
      do_writev+0x397/0x840 fs/read_write.c:1039
      __do_sys_writev fs/read_write.c:1112 [inline]
      __se_sys_writev+0x9b/0xb0 fs/read_write.c:1109
      __x64_sys_writev+0x4a/0x70 fs/read_write.c:1109
      do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291
      entry_SYSCALL_64_after_hwframe+0x63/0xe7
    [...]

The problem is that capi_write() is reading past the end of the message.
Fix it by checking the message's length in the needed places.

Reported-and-tested-by: syzbot+0849c524d9c634f5ae66@syzkaller.appspotmail.com
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/capi/capi.c          | 10 +++++++++-
 include/uapi/linux/isdn/capicmd.h |  1 +
 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/isdn/capi/capi.c b/drivers/isdn/capi/capi.c
index 3c3ad42f22bf..c92b405b7646 100644
--- a/drivers/isdn/capi/capi.c
+++ b/drivers/isdn/capi/capi.c
@@ -688,6 +688,9 @@ capi_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos
 	if (!cdev->ap.applid)
 		return -ENODEV;
 
+	if (count < CAPIMSG_BASELEN)
+		return -EINVAL;
+
 	skb = alloc_skb(count, GFP_USER);
 	if (!skb)
 		return -ENOMEM;
@@ -698,7 +701,8 @@ capi_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos
 	}
 	mlen = CAPIMSG_LEN(skb->data);
 	if (CAPIMSG_CMD(skb->data) == CAPI_DATA_B3_REQ) {
-		if ((size_t)(mlen + CAPIMSG_DATALEN(skb->data)) != count) {
+		if (count < CAPI_DATA_B3_REQ_LEN ||
+		    (size_t)(mlen + CAPIMSG_DATALEN(skb->data)) != count) {
 			kfree_skb(skb);
 			return -EINVAL;
 		}
@@ -711,6 +715,10 @@ capi_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos
 	CAPIMSG_SETAPPID(skb->data, cdev->ap.applid);
 
 	if (CAPIMSG_CMD(skb->data) == CAPI_DISCONNECT_B3_RESP) {
+		if (count < CAPI_DISCONNECT_B3_RESP_LEN) {
+			kfree_skb(skb);
+			return -EINVAL;
+		}
 		mutex_lock(&cdev->lock);
 		capincci_free(cdev, CAPIMSG_NCCI(skb->data));
 		mutex_unlock(&cdev->lock);
diff --git a/include/uapi/linux/isdn/capicmd.h b/include/uapi/linux/isdn/capicmd.h
index 4941628a4fb9..5ec88e7548a9 100644
--- a/include/uapi/linux/isdn/capicmd.h
+++ b/include/uapi/linux/isdn/capicmd.h
@@ -16,6 +16,7 @@
 #define CAPI_MSG_BASELEN		8
 #define CAPI_DATA_B3_REQ_LEN		(CAPI_MSG_BASELEN+4+4+2+2+2)
 #define CAPI_DATA_B3_RESP_LEN		(CAPI_MSG_BASELEN+4+2)
+#define CAPI_DISCONNECT_B3_RESP_LEN	(CAPI_MSG_BASELEN+4)
 
 /*----- CAPI commands -----*/
 #define CAPI_ALERT		    0x01
-- 
2.21.0


From d34c5ae0a821d9b724a2ef88884f9d85dc1cbe03 Mon Sep 17 00:00:00 2001
From: Steffen Klassert <steffen.klassert@secunet.com>
Date: Thu, 12 Sep 2019 13:01:44 +0200
Subject: [PATCH 05/21] ixgbe: Fix secpath usage for IPsec TX offload.

[ Upstream commit f39b683d35dfa93a58f1b400a8ec0ff81296b37c ]

The ixgbe driver currently does IPsec TX offloading
based on an existing secpath. However, the secpath
can also come from the RX side, in this case it is
misinterpreted for TX offload and the packets are
dropped with a "bad sa_idx" error. Fix this by using
the xfrm_offload() function to test for TX offload.

Fixes: 592594704761 ("ixgbe: process the Tx ipsec offload")
Reported-by: Michael Marley <michael@michaelmarley.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index f7c049559c1a..1375213630f2 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -36,6 +36,7 @@
 #include <net/vxlan.h>
 #include <net/mpls.h>
 #include <net/xdp_sock.h>
+#include <net/xfrm.h>
 
 #include "ixgbe.h"
 #include "ixgbe_common.h"
@@ -8691,7 +8692,7 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb,
 #endif /* IXGBE_FCOE */
 
 #ifdef CONFIG_IXGBE_IPSEC
-	if (secpath_exists(skb) &&
+	if (xfrm_offload(skb) &&
 	    !ixgbe_ipsec_tx(tx_ring, first, &ipsec_tx))
 		goto out_drop;
 #endif
-- 
2.21.0


From 5cf7efa841d895e215c9698402e0c2bf731809ef Mon Sep 17 00:00:00 2001
From: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Date: Thu, 12 Sep 2019 12:07:34 -0700
Subject: [PATCH 06/21] ixgbevf: Fix secpath usage for IPsec Tx offload

[ Upstream commit 8f6617badcc96a582678ea36ea96490c5ff26eb4 ]

Port the same fix for ixgbe to ixgbevf.

The ixgbevf driver currently does IPsec Tx offloading
based on an existing secpath. However, the secpath
can also come from the Rx side, in this case it is
misinterpreted for Tx offload and the packets are
dropped with a "bad sa_idx" error. Fix this by using
the xfrm_offload() function to test for Tx offload.

CC: Shannon Nelson <snelson@pensando.io>
Fixes: 7f68d4306701 ("ixgbevf: enable VF IPsec offload operations")
Reported-by: Jonathan Tooker <jonathan@reliablehosting.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Acked-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index d189ed247665..ac6c18821958 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -30,6 +30,7 @@
 #include <linux/bpf.h>
 #include <linux/bpf_trace.h>
 #include <linux/atomic.h>
+#include <net/xfrm.h>
 
 #include "ixgbevf.h"
 
@@ -4158,7 +4159,7 @@ static int ixgbevf_xmit_frame_ring(struct sk_buff *skb,
 	first->protocol = vlan_get_protocol(skb);
 
 #ifdef CONFIG_IXGBEVF_IPSEC
-	if (secpath_exists(skb) && !ixgbevf_ipsec_tx(tx_ring, first, &ipsec_tx))
+	if (xfrm_offload(skb) && !ixgbevf_ipsec_tx(tx_ring, first, &ipsec_tx))
 		goto out_drop;
 #endif
 	tso = ixgbevf_tso(tx_ring, first, &hdr_len, &ipsec_tx);
-- 
2.21.0


From 1899b560d77c84f70f38975333a49a96c67f08cc Mon Sep 17 00:00:00 2001
From: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Date: Tue, 10 Sep 2019 14:02:57 -0600
Subject: [PATCH 07/21] net: Fix null de-reference of device refcount

[ Upstream commit 10cc514f451a0f239aa34f91bc9dc954a9397840 ]

In event of failure during register_netdevice, free_netdev is
invoked immediately. free_netdev assumes that all the netdevice
refcounts have been dropped prior to it being called and as a
result frees and clears out the refcount pointer.

However, this is not necessarily true as some of the operations
in the NETDEV_UNREGISTER notifier handlers queue RCU callbacks for
invocation after a grace period. The IPv4 callback in_dev_rcu_put
tries to access the refcount after free_netdev is called which
leads to a null de-reference-

44837.761523:   <6> Unable to handle kernel paging request at
                    virtual address 0000004a88287000
44837.761651:   <2> pc : in_dev_finish_destroy+0x4c/0xc8
44837.761654:   <2> lr : in_dev_finish_destroy+0x2c/0xc8
44837.762393:   <2> Call trace:
44837.762398:   <2>  in_dev_finish_destroy+0x4c/0xc8
44837.762404:   <2>  in_dev_rcu_put+0x24/0x30
44837.762412:   <2>  rcu_nocb_kthread+0x43c/0x468
44837.762418:   <2>  kthread+0x118/0x128
44837.762424:   <2>  ret_from_fork+0x10/0x1c

Fix this by waiting for the completion of the call_rcu() in
case of register_netdevice errors.

Fixes: 93ee31f14f6f ("[NET]: Fix free_netdev on register_netdev failure.")
Cc: Sean Tranchetti <stranche@codeaurora.org>
Signed-off-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/core/dev.c b/net/core/dev.c
index 29fcff2c3d51..2ff556906b5d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8768,6 +8768,8 @@ int register_netdevice(struct net_device *dev)
 	ret = notifier_to_errno(ret);
 	if (ret) {
 		rollback_registered(dev);
+		rcu_barrier();
+
 		dev->reg_state = NETREG_UNREGISTERED;
 	}
 	/*
-- 
2.21.0


From 293be52d761ca02558ef7ebd1782da3255d6391d Mon Sep 17 00:00:00 2001
From: Shmulik Ladkani <shmulik@metanetworks.com>
Date: Fri, 6 Sep 2019 12:23:50 +0300
Subject: [PATCH 08/21] net: gso: Fix skb_segment splat when splitting gso_size
 mangled skb having linear-headed frag_list

[ Upstream commit 3dcbdb134f329842a38f0e6797191b885ab00a00 ]

Historically, support for frag_list packets entering skb_segment() was
limited to frag_list members terminating on exact same gso_size
boundaries. This is verified with a BUG_ON since commit 89319d3801d1
("net: Add frag_list support to skb_segment"), quote:

    As such we require all frag_list members terminate on exact MSS
    boundaries.  This is checked using BUG_ON.
    As there should only be one producer in the kernel of such packets,
    namely GRO, this requirement should not be difficult to maintain.

However, since commit 6578171a7ff0 ("bpf: add bpf_skb_change_proto helper"),
the "exact MSS boundaries" assumption no longer holds:
An eBPF program using bpf_skb_change_proto() DOES modify 'gso_size', but
leaves the frag_list members as originally merged by GRO with the
original 'gso_size'. Example of such programs are bpf-based NAT46 or
NAT64.

This lead to a kernel BUG_ON for flows involving:
 - GRO generating a frag_list skb
 - bpf program performing bpf_skb_change_proto() or bpf_skb_adjust_room()
 - skb_segment() of the skb

See example BUG_ON reports in [0].

In commit 13acc94eff12 ("net: permit skb_segment on head_frag frag_list skb"),
skb_segment() was modified to support the "gso_size mangling" case of
a frag_list GRO'ed skb, but *only* for frag_list members having
head_frag==true (having a page-fragment head).

Alas, GRO packets having frag_list members with a linear kmalloced head
(head_frag==false) still hit the BUG_ON.

This commit adds support to skb_segment() for a 'head_skb' packet having
a frag_list whose members are *non* head_frag, with gso_size mangled, by
disabling SG and thus falling-back to copying the data from the given
'head_skb' into the generated segmented skbs - as suggested by Willem de
Bruijn [1].

Since this approach involves the penalty of skb_copy_and_csum_bits()
when building the segments, care was taken in order to enable this
solution only when required:
 - untrusted gso_size, by testing SKB_GSO_DODGY is set
   (SKB_GSO_DODGY is set by any gso_size mangling functions in
    net/core/filter.c)
 - the frag_list is non empty, its item is a non head_frag, *and* the
   headlen of the given 'head_skb' does not match the gso_size.

[0]
https://lore.kernel.org/netdev/20190826170724.25ff616f@pixies/
https://lore.kernel.org/netdev/9265b93f-253d-6b8c-f2b8-4b54eff1835c@fb.com/

[1]
https://lore.kernel.org/netdev/CA+FuTSfVsgNDi7c=GUU8nMg2hWxF2SjCNLXetHeVPdnxAW5K-w@mail.gmail.com/

Fixes: 6578171a7ff0 ("bpf: add bpf_skb_change_proto helper")
Suggested-by: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Alexander Duyck <alexander.duyck@gmail.com>
Signed-off-by: Shmulik Ladkani <shmulik.ladkani@gmail.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index c8cd99c3603f..74efd63f15e2 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3531,6 +3531,25 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 	int pos;
 	int dummy;
 
+	if (list_skb && !list_skb->head_frag && skb_headlen(list_skb) &&
+	    (skb_shinfo(head_skb)->gso_type & SKB_GSO_DODGY)) {
+		/* gso_size is untrusted, and we have a frag_list with a linear
+		 * non head_frag head.
+		 *
+		 * (we assume checking the first list_skb member suffices;
+		 * i.e if either of the list_skb members have non head_frag
+		 * head, then the first one has too).
+		 *
+		 * If head_skb's headlen does not fit requested gso_size, it
+		 * means that the frag_list members do NOT terminate on exact
+		 * gso_size boundaries. Hence we cannot perform skb_frag_t page
+		 * sharing. Therefore we must fallback to copying the frag_list
+		 * skbs; we do so by disabling SG.
+		 */
+		if (mss != GSO_BY_FRAGS && mss != skb_headlen(head_skb))
+			features &= ~NETIF_F_SG;
+	}
+
 	__skb_push(head_skb, doffset);
 	proto = skb_network_protocol(head_skb, &dummy);
 	if (unlikely(!proto))
-- 
2.21.0


From 0774490e980dcc8dbd6df7d9f730b5cffbcbb767 Mon Sep 17 00:00:00 2001
From: Stefan Chulski <stefanc@marvell.com>
Date: Thu, 5 Sep 2019 19:46:18 +0300
Subject: [PATCH 09/21] net: phylink: Fix flow control resolution

[ Upstream commit 63b2ed4e10b2e6c913e1d8cdd728e7fba4115a3d ]

Regarding to IEEE 802.3-2015 standard section 2
28B.3 Priority resolution - Table 28-3 - Pause resolution

In case of Local device Pause=1 AsymDir=0, Link partner
Pause=1 AsymDir=1, Local device resolution should be enable PAUSE
transmit, disable PAUSE receive.
And in case of Local device Pause=1 AsymDir=1, Link partner
Pause=1 AsymDir=0, Local device resolution should be enable PAUSE
receive, disable PAUSE transmit.

Fixes: 9525ae83959b ("phylink: add phylink infrastructure")
Signed-off-by: Stefan Chulski <stefanc@marvell.com>
Reported-by: Shaul Ben-Mayor <shaulb@marvell.com>
Acked-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phylink.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index c45ee6e3fe01..a094d7197015 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -356,8 +356,8 @@ static void phylink_get_fixed_state(struct phylink *pl, struct phylink_link_stat
  *  Local device  Link partner
  *  Pause AsymDir Pause AsymDir Result
  *    1     X       1     X     TX+RX
- *    0     1       1     1     RX
- *    1     1       0     1     TX
+ *    0     1       1     1     TX
+ *    1     1       0     1     RX
  */
 static void phylink_resolve_flow(struct phylink *pl,
 				 struct phylink_link_state *state)
@@ -378,7 +378,7 @@ static void phylink_resolve_flow(struct phylink *pl,
 			new_pause = MLO_PAUSE_TX | MLO_PAUSE_RX;
 		else if (pause & MLO_PAUSE_ASYM)
 			new_pause = state->pause & MLO_PAUSE_SYM ?
-				 MLO_PAUSE_RX : MLO_PAUSE_TX;
+				 MLO_PAUSE_TX : MLO_PAUSE_RX;
 	} else {
 		new_pause = pl->link_config.pause & MLO_PAUSE_TXRX_MASK;
 	}
-- 
2.21.0


From d7f1aaee09cb91a125cf850d2c9f6d5136ca566f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 5 Sep 2019 05:20:22 -0700
Subject: [PATCH 10/21] net: sched: fix reordering issues

[ Upstream commit b88dd52c62bb5c5d58f0963287f41fd084352c57 ]

Whenever MQ is not used on a multiqueue device, we experience
serious reordering problems. Bisection found the cited
commit.

The issue can be described this way :

- A single qdisc hierarchy is shared by all transmit queues.
  (eg : tc qdisc replace dev eth0 root fq_codel)

- When/if try_bulk_dequeue_skb_slow() dequeues a packet targetting
  a different transmit queue than the one used to build a packet train,
  we stop building the current list and save the 'bad' skb (P1) in a
  special queue. (bad_txq)

- When dequeue_skb() calls qdisc_dequeue_skb_bad_txq() and finds this
  skb (P1), it checks if the associated transmit queues is still in frozen
  state. If the queue is still blocked (by BQL or NIC tx ring full),
  we leave the skb in bad_txq and return NULL.

- dequeue_skb() calls q->dequeue() to get another packet (P2)

  The other packet can target the problematic queue (that we found
  in frozen state for the bad_txq packet), but another cpu just ran
  TX completion and made room in the txq that is now ready to accept
  new packets.

- Packet P2 is sent while P1 is still held in bad_txq, P1 might be sent
  at next round. In practice P2 is the lead of a big packet train
  (P2,P3,P4 ...) filling the BQL budget and delaying P1 by many packets :/

To solve this problem, we have to block the dequeue process as long
as the first packet in bad_txq can not be sent. Reordering issues
disappear and no side effects have been seen.

Fixes: a53851e2c321 ("net: sched: explicit locking in gso_cpu fallback")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: John Fastabend <john.fastabend@gmail.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_generic.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 137db1cbde85..ac28f6a5d70e 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -46,6 +46,8 @@ EXPORT_SYMBOL(default_qdisc_ops);
  * - updates to tree and tree walking are only done under the rtnl mutex.
  */
 
+#define SKB_XOFF_MAGIC ((struct sk_buff *)1UL)
+
 static inline struct sk_buff *__skb_dequeue_bad_txq(struct Qdisc *q)
 {
 	const struct netdev_queue *txq = q->dev_queue;
@@ -71,7 +73,7 @@ static inline struct sk_buff *__skb_dequeue_bad_txq(struct Qdisc *q)
 				q->q.qlen--;
 			}
 		} else {
-			skb = NULL;
+			skb = SKB_XOFF_MAGIC;
 		}
 	}
 
@@ -253,8 +255,11 @@ static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate,
 		return skb;
 
 	skb = qdisc_dequeue_skb_bad_txq(q);
-	if (unlikely(skb))
+	if (unlikely(skb)) {
+		if (skb == SKB_XOFF_MAGIC)
+			return NULL;
 		goto bulk;
+	}
 	skb = q->dequeue(q);
 	if (skb) {
 bulk:
-- 
2.21.0


From 18444d2820c56f812d0537308c3b38d5479cb1b6 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sun, 8 Sep 2019 13:40:51 -0700
Subject: [PATCH 11/21] sch_hhf: ensure quantum and hhf_non_hh_weight are
 non-zero

[ Upstream commit d4d6ec6dac07f263f06d847d6f732d6855522845 ]

In case of TCA_HHF_NON_HH_WEIGHT or TCA_HHF_QUANTUM is zero,
it would make no progress inside the loop in hhf_dequeue() thus
kernel would get stuck.

Fix this by checking this corner case in hhf_change().

Fixes: 10239edf86f1 ("net-qdisc-hhf: Heavy-Hitter Filter (HHF) qdisc")
Reported-by: syzbot+bc6297c11f19ee807dc2@syzkaller.appspotmail.com
Reported-by: syzbot+041483004a7f45f1f20a@syzkaller.appspotmail.com
Reported-by: syzbot+55be5f513bed37fc4367@syzkaller.appspotmail.com
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Cc: Terry Lam <vtlam@google.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_hhf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c
index cee6971c1c82..23cd1c873a2c 100644
--- a/net/sched/sch_hhf.c
+++ b/net/sched/sch_hhf.c
@@ -531,7 +531,7 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt,
 		new_hhf_non_hh_weight = nla_get_u32(tb[TCA_HHF_NON_HH_WEIGHT]);
 
 	non_hh_quantum = (u64)new_quantum * new_hhf_non_hh_weight;
-	if (non_hh_quantum > INT_MAX)
+	if (non_hh_quantum == 0 || non_hh_quantum > INT_MAX)
 		return -EINVAL;
 
 	sch_tree_lock(sch);
-- 
2.21.0


From a8c4fa57a722ea4b904a8ef038bbe5ce04f2d210 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Wed, 11 Sep 2019 18:02:39 +0200
Subject: [PATCH 12/21] sctp: Fix the link time qualifier of
 'sctp_ctrlsock_exit()'

[ Upstream commit b456d72412ca8797234449c25815e82f4e1426c0 ]

The '.exit' functions from 'pernet_operations' structure should be marked
as __net_exit, not __net_init.

Fixes: 8e2d61e0aed2 ("sctp: fix race on protocol/netns initialization")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/protocol.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 23af232c0a25..e2b4a440416b 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -1336,7 +1336,7 @@ static int __net_init sctp_ctrlsock_init(struct net *net)
 	return status;
 }
 
-static void __net_init sctp_ctrlsock_exit(struct net *net)
+static void __net_exit sctp_ctrlsock_exit(struct net *net)
 {
 	/* Free the control endpoint.  */
 	inet_ctl_sock_destroy(net->sctp.ctl_sock);
-- 
2.21.0


From d66c59f80ec5efa1c2bdd2465d313399fd4dbbbb Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 2 Sep 2019 23:24:21 +0800
Subject: [PATCH 13/21] sctp: use transport pf_retrans in
 sctp_do_8_2_transport_strike

[ Upstream commit 10eb56c582c557c629271f1ee31e15e7a9b2558b ]

Transport should use its own pf_retrans to do the error_count
check, instead of asoc's. Otherwise, it's meaningless to make
pf_retrans per transport.

Fixes: 5aa93bcf66f4 ("sctp: Implement quick failover draft from tsvwg")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sm_sideeffect.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index 1cf5bb5b73c4..e52b2128e43b 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -547,7 +547,7 @@ static void sctp_do_8_2_transport_strike(struct sctp_cmd_seq *commands,
 	if (net->sctp.pf_enable &&
 	   (transport->state == SCTP_ACTIVE) &&
 	   (transport->error_count < transport->pathmaxrxt) &&
-	   (transport->error_count > asoc->pf_retrans)) {
+	   (transport->error_count > transport->pf_retrans)) {
 
 		sctp_assoc_control_transport(asoc, transport,
 					     SCTP_TRANSPORT_PF,
-- 
2.21.0


From dfe714e705030da2d3fe004aa7892e457c2f465b Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Mon, 9 Sep 2019 16:56:02 -0400
Subject: [PATCH 14/21] tcp: fix tcp_ecn_withdraw_cwr() to clear
 TCP_ECN_QUEUE_CWR

[ Upstream commit af38d07ed391b21f7405fa1f936ca9686787d6d2 ]

Fix tcp_ecn_withdraw_cwr() to clear the correct bit:
TCP_ECN_QUEUE_CWR.

Rationale: basically, TCP_ECN_DEMAND_CWR is a bit that is purely about
the behavior of data receivers, and deciding whether to reflect
incoming IP ECN CE marks as outgoing TCP th->ece marks. The
TCP_ECN_QUEUE_CWR bit is purely about the behavior of data senders,
and deciding whether to send CWR. The tcp_ecn_withdraw_cwr() function
is only called from tcp_undo_cwnd_reduction() by data senders during
an undo, so it should zero the sender-side state,
TCP_ECN_QUEUE_CWR. It does not make sense to stop the reflection of
incoming CE bits on incoming data packets just because outgoing
packets were spuriously retransmitted.

The bug has been reproduced with packetdrill to manifest in a scenario
with RFC3168 ECN, with an incoming data packet with CE bit set and
carrying a TCP timestamp value that causes cwnd undo. Before this fix,
the IP CE bit was ignored and not reflected in the TCP ECE header bit,
and sender sent a TCP CWR ('W') bit on the next outgoing data packet,
even though the cwnd reduction had been undone.  After this fix, the
sender properly reflects the CE bit and does not set the W bit.

Note: the bug actually predates 2005 git history; this Fixes footer is
chosen to be the oldest SHA1 I have tested (from Sep 2007) for which
the patch applies cleanly (since before this commit the code was in a
.h file).

Fixes: bdf1ee5d3bd3 ("[TCP]: Move code from tcp_ecn.h to tcp*.c and tcp.h & remove it")
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index d95ee40df6c2..21ed010d7551 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -266,7 +266,7 @@ static void tcp_ecn_accept_cwr(struct sock *sk, const struct sk_buff *skb)
 
 static void tcp_ecn_withdraw_cwr(struct tcp_sock *tp)
 {
-	tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
+	tp->ecn_flags &= ~TCP_ECN_QUEUE_CWR;
 }
 
 static void __tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb)
-- 
2.21.0


From 8f80ddb24f04a1d3121f6e659753135686423955 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 3 Sep 2019 17:53:12 +0800
Subject: [PATCH 15/21] tipc: add NULL pointer check before calling kfree_rcu

[ Upstream commit 42dec1dbe38239cf91cc1f4df7830c66276ced37 ]

Unlike kfree(p), kfree_rcu(p, rcu) won't do NULL pointer check. When
tipc_nametbl_remove_publ returns NULL, the panic below happens:

   BUG: unable to handle kernel NULL pointer dereference at 0000000000000068
   RIP: 0010:__call_rcu+0x1d/0x290
   Call Trace:
    <IRQ>
    tipc_publ_notify+0xa9/0x170 [tipc]
    tipc_node_write_unlock+0x8d/0x100 [tipc]
    tipc_node_link_down+0xae/0x1d0 [tipc]
    tipc_node_check_dest+0x3ea/0x8f0 [tipc]
    ? tipc_disc_rcv+0x2c7/0x430 [tipc]
    tipc_disc_rcv+0x2c7/0x430 [tipc]
    ? tipc_rcv+0x6bb/0xf20 [tipc]
    tipc_rcv+0x6bb/0xf20 [tipc]
    ? ip_route_input_slow+0x9cf/0xb10
    tipc_udp_recv+0x195/0x1e0 [tipc]
    ? tipc_udp_is_known_peer+0x80/0x80 [tipc]
    udp_queue_rcv_skb+0x180/0x460
    udp_unicast_rcv_skb.isra.56+0x75/0x90
    __udp4_lib_rcv+0x4ce/0xb90
    ip_local_deliver_finish+0x11c/0x210
    ip_local_deliver+0x6b/0xe0
    ? ip_rcv_finish+0xa9/0x410
    ip_rcv+0x273/0x362

Fixes: 97ede29e80ee ("tipc: convert name table read-write lock to RCU")
Reported-by: Li Shuang <shuali@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/name_distr.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c
index 61219f0b9677..836e629e8f4a 100644
--- a/net/tipc/name_distr.c
+++ b/net/tipc/name_distr.c
@@ -223,7 +223,8 @@ static void tipc_publ_purge(struct net *net, struct publication *publ, u32 addr)
 		       publ->key);
 	}
 
-	kfree_rcu(p, rcu);
+	if (p)
+		kfree_rcu(p, rcu);
 }
 
 /**
-- 
2.21.0


From 7cf01615cfb89329b11b132c4758e0cb54dea401 Mon Sep 17 00:00:00 2001
From: Yang Yingliang <yangyingliang@huawei.com>
Date: Tue, 10 Sep 2019 18:56:57 +0800
Subject: [PATCH 16/21] tun: fix use-after-free when register netdev failed

[ Upstream commit 77f22f92dff8e7b45c7786a430626d38071d4670 ]

I got a UAF repport in tun driver when doing fuzzy test:

[  466.269490] ==================================================================
[  466.271792] BUG: KASAN: use-after-free in tun_chr_read_iter+0x2ca/0x2d0
[  466.271806] Read of size 8 at addr ffff888372139250 by task tun-test/2699
[  466.271810]
[  466.271824] CPU: 1 PID: 2699 Comm: tun-test Not tainted 5.3.0-rc1-00001-g5a9433db2614-dirty #427
[  466.271833] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014
[  466.271838] Call Trace:
[  466.271858]  dump_stack+0xca/0x13e
[  466.271871]  ? tun_chr_read_iter+0x2ca/0x2d0
[  466.271890]  print_address_description+0x79/0x440
[  466.271906]  ? vprintk_func+0x5e/0xf0
[  466.271920]  ? tun_chr_read_iter+0x2ca/0x2d0
[  466.271935]  __kasan_report+0x15c/0x1df
[  466.271958]  ? tun_chr_read_iter+0x2ca/0x2d0
[  466.271976]  kasan_report+0xe/0x20
[  466.271987]  tun_chr_read_iter+0x2ca/0x2d0
[  466.272013]  do_iter_readv_writev+0x4b7/0x740
[  466.272032]  ? default_llseek+0x2d0/0x2d0
[  466.272072]  do_iter_read+0x1c5/0x5e0
[  466.272110]  vfs_readv+0x108/0x180
[  466.299007]  ? compat_rw_copy_check_uvector+0x440/0x440
[  466.299020]  ? fsnotify+0x888/0xd50
[  466.299040]  ? __fsnotify_parent+0xd0/0x350
[  466.299064]  ? fsnotify_first_mark+0x1e0/0x1e0
[  466.304548]  ? vfs_write+0x264/0x510
[  466.304569]  ? ksys_write+0x101/0x210
[  466.304591]  ? do_preadv+0x116/0x1a0
[  466.304609]  do_preadv+0x116/0x1a0
[  466.309829]  do_syscall_64+0xc8/0x600
[  466.309849]  entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  466.309861] RIP: 0033:0x4560f9
[  466.309875] Code: 00 00 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48
[  466.309889] RSP: 002b:00007ffffa5166e8 EFLAGS: 00000206 ORIG_RAX: 0000000000000127
[  466.322992] RAX: ffffffffffffffda RBX: 0000000000400460 RCX: 00000000004560f9
[  466.322999] RDX: 0000000000000003 RSI: 00000000200008c0 RDI: 0000000000000003
[  466.323007] RBP: 00007ffffa516700 R08: 0000000000000004 R09: 0000000000000000
[  466.323014] R10: 0000000000000000 R11: 0000000000000206 R12: 000000000040cb10
[  466.323021] R13: 0000000000000000 R14: 00000000006d7018 R15: 0000000000000000
[  466.323057]
[  466.323064] Allocated by task 2605:
[  466.335165]  save_stack+0x19/0x80
[  466.336240]  __kasan_kmalloc.constprop.8+0xa0/0xd0
[  466.337755]  kmem_cache_alloc+0xe8/0x320
[  466.339050]  getname_flags+0xca/0x560
[  466.340229]  user_path_at_empty+0x2c/0x50
[  466.341508]  vfs_statx+0xe6/0x190
[  466.342619]  __do_sys_newstat+0x81/0x100
[  466.343908]  do_syscall_64+0xc8/0x600
[  466.345303]  entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  466.347034]
[  466.347517] Freed by task 2605:
[  466.348471]  save_stack+0x19/0x80
[  466.349476]  __kasan_slab_free+0x12e/0x180
[  466.350726]  kmem_cache_free+0xc8/0x430
[  466.351874]  putname+0xe2/0x120
[  466.352921]  filename_lookup+0x257/0x3e0
[  466.354319]  vfs_statx+0xe6/0x190
[  466.355498]  __do_sys_newstat+0x81/0x100
[  466.356889]  do_syscall_64+0xc8/0x600
[  466.358037]  entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  466.359567]
[  466.360050] The buggy address belongs to the object at ffff888372139100
[  466.360050]  which belongs to the cache names_cache of size 4096
[  466.363735] The buggy address is located 336 bytes inside of
[  466.363735]  4096-byte region [ffff888372139100, ffff88837213a100)
[  466.367179] The buggy address belongs to the page:
[  466.368604] page:ffffea000dc84e00 refcount:1 mapcount:0 mapping:ffff8883df1b4f00 index:0x0 compound_mapcount: 0
[  466.371582] flags: 0x2fffff80010200(slab|head)
[  466.372910] raw: 002fffff80010200 dead000000000100 dead000000000122 ffff8883df1b4f00
[  466.375209] raw: 0000000000000000 0000000000070007 00000001ffffffff 0000000000000000
[  466.377778] page dumped because: kasan: bad access detected
[  466.379730]
[  466.380288] Memory state around the buggy address:
[  466.381844]  ffff888372139100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  466.384009]  ffff888372139180: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  466.386131] >ffff888372139200: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  466.388257]                                                  ^
[  466.390234]  ffff888372139280: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  466.392512]  ffff888372139300: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  466.394667] ==================================================================

tun_chr_read_iter() accessed the memory which freed by free_netdev()
called by tun_set_iff():

        CPUA                                           CPUB
  tun_set_iff()
    alloc_netdev_mqs()
    tun_attach()
                                                  tun_chr_read_iter()
                                                    tun_get()
                                                    tun_do_read()
                                                      tun_ring_recv()
    register_netdevice() <-- inject error
    goto err_detach
    tun_detach_all() <-- set RCV_SHUTDOWN
    free_netdev() <-- called from
                     err_free_dev path
      netdev_freemem() <-- free the memory
                        without check refcount
      (In this path, the refcount cannot prevent
       freeing the memory of dev, and the memory
       will be used by dev_put() called by
       tun_chr_read_iter() on CPUB.)
                                                     (Break from tun_ring_recv(),
                                                     because RCV_SHUTDOWN is set)
                                                   tun_put()
                                                     dev_put() <-- use the memory
                                                                   freed by netdev_freemem()

Put the publishing of tfile->tun after register_netdevice(),
so tun_get() won't get the tun pointer that freed by
err_detach path if register_netdevice() failed.

Fixes: eb0fb363f920 ("tuntap: attach queue 0 before registering netdevice")
Reported-by: Hulk Robot <hulkci@huawei.com>
Suggested-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 192ac47fd055..3f42cd433605 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -788,7 +788,8 @@ static void tun_detach_all(struct net_device *dev)
 }
 
 static int tun_attach(struct tun_struct *tun, struct file *file,
-		      bool skip_filter, bool napi, bool napi_frags)
+		      bool skip_filter, bool napi, bool napi_frags,
+		      bool publish_tun)
 {
 	struct tun_file *tfile = file->private_data;
 	struct net_device *dev = tun->dev;
@@ -871,7 +872,8 @@ static int tun_attach(struct tun_struct *tun, struct file *file,
 	 * initialized tfile; otherwise we risk using half-initialized
 	 * object.
 	 */
-	rcu_assign_pointer(tfile->tun, tun);
+	if (publish_tun)
+		rcu_assign_pointer(tfile->tun, tun);
 	rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile);
 	tun->numqueues++;
 	tun_set_real_num_queues(tun);
@@ -2731,7 +2733,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 
 		err = tun_attach(tun, file, ifr->ifr_flags & IFF_NOFILTER,
 				 ifr->ifr_flags & IFF_NAPI,
-				 ifr->ifr_flags & IFF_NAPI_FRAGS);
+				 ifr->ifr_flags & IFF_NAPI_FRAGS, true);
 		if (err < 0)
 			return err;
 
@@ -2830,13 +2832,17 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 
 		INIT_LIST_HEAD(&tun->disabled);
 		err = tun_attach(tun, file, false, ifr->ifr_flags & IFF_NAPI,
-				 ifr->ifr_flags & IFF_NAPI_FRAGS);
+				 ifr->ifr_flags & IFF_NAPI_FRAGS, false);
 		if (err < 0)
 			goto err_free_flow;
 
 		err = register_netdevice(tun->dev);
 		if (err < 0)
 			goto err_detach;
+		/* free_netdev() won't check refcnt, to aovid race
+		 * with dev_put() we need publish tun after registration.
+		 */
+		rcu_assign_pointer(tfile->tun, tun);
 	}
 
 	netif_carrier_on(tun->dev);
@@ -2979,7 +2985,7 @@ static int tun_set_queue(struct file *file, struct ifreq *ifr)
 		if (ret < 0)
 			goto unlock;
 		ret = tun_attach(tun, file, false, tun->flags & IFF_NAPI,
-				 tun->flags & IFF_NAPI_FRAGS);
+				 tun->flags & IFF_NAPI_FRAGS, true);
 	} else if (ifr->ifr_flags & IFF_DETACH_QUEUE) {
 		tun = rtnl_dereference(tfile->tun);
 		if (!tun || !(tun->flags & IFF_MULTI_QUEUE) || tfile->detached)
-- 
2.21.0


From 0699a189467dd7045f27e7f54c205df7107df4d6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Maciej=20=C5=BBenczykowski?= <maze@google.com>
Date: Mon, 2 Sep 2019 09:23:36 -0700
Subject: [PATCH 17/21] net-ipv6: fix excessive RTF_ADDRCONF flag on ::1/128
 local route (and others)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit d55a2e374a94fa34a3048c6a2be535266e506d97 ]

There is a subtle change in behaviour introduced by:
  commit c7a1ce397adacaf5d4bb2eab0a738b5f80dc3e43
  'ipv6: Change addrconf_f6i_alloc to use ip6_route_info_create'

Before that patch /proc/net/ipv6_route includes:
00000000000000000000000000000001 80 00000000000000000000000000000000 00 00000000000000000000000000000000 00000000 00000003 00000000 80200001 lo

Afterwards /proc/net/ipv6_route includes:
00000000000000000000000000000001 80 00000000000000000000000000000000 00 00000000000000000000000000000000 00000000 00000002 00000000 80240001 lo

ie. the above commit causes the ::1/128 local (automatic) route to be flagged with RTF_ADDRCONF (0x040000).

AFAICT, this is incorrect since these routes are *not* coming from RA's.

As such, this patch restores the old behaviour.

Fixes: c7a1ce397ada ("ipv6: Change addrconf_f6i_alloc to use ip6_route_info_create")
Cc: David Ahern <dsahern@gmail.com>
Cc: Lorenzo Colitti <lorenzo@google.com>
Signed-off-by: Maciej Żenczykowski <maze@google.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 5f5a0a42ce60..97a350041f18 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3841,13 +3841,14 @@ struct fib6_info *addrconf_f6i_alloc(struct net *net,
 	struct fib6_config cfg = {
 		.fc_table = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL,
 		.fc_ifindex = idev->dev->ifindex,
-		.fc_flags = RTF_UP | RTF_ADDRCONF | RTF_NONEXTHOP,
+		.fc_flags = RTF_UP | RTF_NONEXTHOP,
 		.fc_dst = *addr,
 		.fc_dst_len = 128,
 		.fc_protocol = RTPROT_KERNEL,
 		.fc_nlinfo.nl_net = net,
 		.fc_ignore_dev_down = true,
 	};
+	struct fib6_info *f6i;
 
 	if (anycast) {
 		cfg.fc_type = RTN_ANYCAST;
@@ -3857,7 +3858,10 @@ struct fib6_info *addrconf_f6i_alloc(struct net *net,
 		cfg.fc_flags |= RTF_LOCAL;
 	}
 
-	return ip6_route_info_create(&cfg, gfp_flags, NULL);
+	f6i = ip6_route_info_create(&cfg, gfp_flags, NULL);
+	if (f6i)
+		f6i->dst_nocount = true;
+	return f6i;
 }
 
 /* remove deleted ip from prefsrc entries */
-- 
2.21.0


From 24c5877b145f087321da21897fcb65a6642d6421 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Maciej=20=C5=BBenczykowski?= <maze@google.com>
Date: Thu, 5 Sep 2019 20:56:37 -0700
Subject: [PATCH 18/21] ipv6: addrconf_f6i_alloc - fix non-null pointer check
 to !IS_ERR()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 8652f17c658d03f5c87b8dee6e8e52480c6cd37d ]

Fixes a stupid bug I recently introduced...
ip6_route_info_create() returns an ERR_PTR(err) and not a NULL on error.

Fixes: d55a2e374a94 ("net-ipv6: fix excessive RTF_ADDRCONF flag on ::1/128 local route (and others)'")
Cc: David Ahern <dsahern@gmail.com>
Cc: Lorenzo Colitti <lorenzo@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Maciej Żenczykowski <maze@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 97a350041f18..6a6e403c71ac 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3859,7 +3859,7 @@ struct fib6_info *addrconf_f6i_alloc(struct net *net,
 	}
 
 	f6i = ip6_route_info_create(&cfg, gfp_flags, NULL);
-	if (f6i)
+	if (!IS_ERR(f6i))
 		f6i->dst_nocount = true;
 	return f6i;
 }
-- 
2.21.0


From c477039a19d32b877802f9b88bdd09b8137a817e Mon Sep 17 00:00:00 2001
From: Moritz Fischer <mdf@kernel.org>
Date: Tue, 3 Sep 2019 11:46:52 -0700
Subject: [PATCH 19/21] net: fixed_phy: Add forward declaration for struct
 gpio_desc;

[ Upstream commit ebe26aca98fcf9fbe5017b5cbe216413cee69df5 ]

Add forward declaration for struct gpio_desc in order to address
the following:

./include/linux/phy_fixed.h:48:17: error: 'struct gpio_desc' declared inside parameter list [-Werror]
./include/linux/phy_fixed.h:48:17: error: its scope is only this definition or declaration, which is probably not what you want [-Werror]

Fixes: 71bd106d2567 ("net: fixed-phy: Add fixed_phy_register_with_gpiod() API")
Signed-off-by: Moritz Fischer <mdf@kernel.org>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/phy_fixed.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/linux/phy_fixed.h b/include/linux/phy_fixed.h
index 1e5d86ebdaeb..52bc8e487ef7 100644
--- a/include/linux/phy_fixed.h
+++ b/include/linux/phy_fixed.h
@@ -11,6 +11,7 @@ struct fixed_phy_status {
 };
 
 struct device_node;
+struct gpio_desc;
 
 #if IS_ENABLED(CONFIG_FIXED_PHY)
 extern int fixed_phy_change_carrier(struct net_device *dev, bool new_carrier);
-- 
2.21.0


From 8e5985ebf94e0c9cb37b8509399e61ea3010d731 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 9 Sep 2019 15:33:29 +0800
Subject: [PATCH 20/21] sctp: fix the missing put_user when dumping transport
 thresholds

[ Upstream commit f794dc2304d83ab998c2eee5bab0549aff5c53a2 ]

This issue causes SCTP_PEER_ADDR_THLDS sockopt not to be able to dump
a transport thresholds info.

Fix it by adding 'goto' put_user in sctp_getsockopt_paddr_thresholds.

Fixes: 8add543e369d ("sctp: add SCTP_FUTURE_ASSOC for SCTP_PEER_ADDR_THLDS sockopt")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index f33aa9ee9e27..d0324796f0b3 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -7176,7 +7176,7 @@ static int sctp_getsockopt_paddr_thresholds(struct sock *sk,
 		val.spt_pathmaxrxt = trans->pathmaxrxt;
 		val.spt_pathpfthld = trans->pf_retrans;
 
-		return 0;
+		goto out;
 	}
 
 	asoc = sctp_id2assoc(sk, val.spt_assoc_id);
@@ -7194,6 +7194,7 @@ static int sctp_getsockopt_paddr_thresholds(struct sock *sk,
 		val.spt_pathmaxrxt = sp->pathmaxrxt;
 	}
 
+out:
 	if (put_user(len, optlen) || copy_to_user(optval, &val, len))
 		return -EFAULT;
 
-- 
2.21.0


From 786642d7c905d1e3c3f1be4c2c8ea91c158ede23 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Tue, 3 Sep 2019 13:24:50 -0700
Subject: [PATCH 21/21] net: sock_map, fix missing ulp check in sock hash case

[ Upstream commit 44580a0118d3ede95fec4dce32df5f75f73cd663 ]

sock_map and ULP only work together when ULP is loaded after the sock
map is loaded. In the sock_map case we added a check for this to fail
the load if ULP is already set. However, we missed the check on the
sock_hash side.

Add a ULP check to the sock_hash update path.

Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface")
Reported-by: syzbot+7a6ee4d0078eac6bf782@syzkaller.appspotmail.com
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock_map.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 8a4a45e7c29d..3b14de0e36d2 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -661,6 +661,7 @@ static int sock_hash_update_common(struct bpf_map *map, void *key,
 				   struct sock *sk, u64 flags)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+	struct inet_connection_sock *icsk = inet_csk(sk);
 	u32 key_size = map->key_size, hash;
 	struct bpf_htab_elem *elem, *elem_new;
 	struct bpf_htab_bucket *bucket;
@@ -671,6 +672,8 @@ static int sock_hash_update_common(struct bpf_map *map, void *key,
 	WARN_ON_ONCE(!rcu_read_lock_held());
 	if (unlikely(flags > BPF_EXIST))
 		return -EINVAL;
+	if (unlikely(icsk->icsk_ulp_data))
+		return -EINVAL;
 
 	link = sk_psock_init_link();
 	if (!link)
-- 
2.21.0

Re: [PATCHES] Networking

[Greg KH]

On Sun, Sep 15, 2019 at 08:37:22PM +0100, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.19
> and v5.2 -stable, respectively.

All queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 105 bytes --]


Please queue up the following networking bug fixes for v5.2 and v5.3 -stable,
respectively.

Thank you.

[-- Attachment #2: net_52.mbox --]
[-- Type: Application/Octet-Stream, Size: 16291 bytes --]

From e86981e145e8374dbe9b6844fc9dee9a6122996e Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Fri, 13 Sep 2019 17:45:47 +0800
Subject: [PATCH 1/6] ip6_gre: fix a dst leak in ip6erspan_tunnel_xmit

[ Upstream commit 28e486037747c2180470b77c290d4090ad42f259 ]

In ip6erspan_tunnel_xmit(), if the skb will not be sent out, it has to
be freed on the tx_err path. Otherwise when deleting a netns, it would
cause dst/dev to leak, and dmesg shows:

  unregister_netdevice: waiting for lo to become free. Usage count = 1

Fixes: ef7baf5e083c ("ip6_gre: add ip6 erspan collect_md mode")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: William Tu <u9012063@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index dd2d0b963260..d5779d6a6065 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -968,7 +968,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 		if (unlikely(!tun_info ||
 			     !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
 			     ip_tunnel_info_af(tun_info) != AF_INET6))
-			return -EINVAL;
+			goto tx_err;
 
 		key = &tun_info->key;
 		memset(&fl6, 0, sizeof(fl6));
-- 
2.21.0


From d7bf08904987abab784feb4d17ad17cd5b7d940e Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 12 Sep 2019 12:02:42 +0200
Subject: [PATCH 2/6] net/sched: fix race between deactivation and dequeue for
 NOLOCK qdisc

[ Upstream commit d518d2ed8640c1cbbbb6f63939e3e65471817367 ]

The test implemented by some_qdisc_is_busy() is somewhat loosy for
NOLOCK qdisc, as we may hit the following scenario:

CPU1						CPU2
// in net_tx_action()
clear_bit(__QDISC_STATE_SCHED...);
						// in some_qdisc_is_busy()
						val = (qdisc_is_running(q) ||
						       test_bit(__QDISC_STATE_SCHED,
								&q->state));
						// here val is 0 but...
qdisc_run(q)
// ... CPU1 is going to run the qdisc next

As a conseguence qdisc_run() in net_tx_action() can race with qdisc_reset()
in dev_qdisc_reset(). Such race is not possible for !NOLOCK qdisc as
both the above bit operations are under the root qdisc lock().

After commit 021a17ed796b ("pfifo_fast: drop unneeded additional lock on dequeue")
the race can cause use after free and/or null ptr dereference, but the root
cause is likely older.

This patch addresses the issue explicitly checking for deactivation under
the seqlock for NOLOCK qdisc, so that the qdisc_run() in the critical
scenario becomes a no-op.

Note that the enqueue() op can still execute concurrently with dev_qdisc_reset(),
but that is safe due to the skb_array() locking, and we can't avoid that
for NOLOCK qdiscs.

Fixes: 021a17ed796b ("pfifo_fast: drop unneeded additional lock on dequeue")
Reported-by: Li Shuang <shuali@redhat.com>
Reported-and-tested-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/pkt_sched.h |  7 ++++++-
 net/core/dev.c          | 16 ++++++++++------
 2 files changed, 16 insertions(+), 7 deletions(-)

diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index a16fbe9a2a67..aa99c73c3fbd 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -118,7 +118,12 @@ void __qdisc_run(struct Qdisc *q);
 static inline void qdisc_run(struct Qdisc *q)
 {
 	if (qdisc_run_begin(q)) {
-		__qdisc_run(q);
+		/* NOLOCK qdisc must check 'state' under the qdisc seqlock
+		 * to avoid racing with dev_qdisc_reset()
+		 */
+		if (!(q->flags & TCQ_F_NOLOCK) ||
+		    likely(!test_bit(__QDISC_STATE_DEACTIVATED, &q->state)))
+			__qdisc_run(q);
 		qdisc_run_end(q);
 	}
 }
diff --git a/net/core/dev.c b/net/core/dev.c
index 2ff556906b5d..828ecca03c07 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3475,18 +3475,22 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 	qdisc_calculate_pkt_len(skb, q);
 
 	if (q->flags & TCQ_F_NOLOCK) {
-		if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) {
-			__qdisc_drop(skb, &to_free);
-			rc = NET_XMIT_DROP;
-		} else if ((q->flags & TCQ_F_CAN_BYPASS) && q->empty &&
-			   qdisc_run_begin(q)) {
+		if ((q->flags & TCQ_F_CAN_BYPASS) && q->empty &&
+		    qdisc_run_begin(q)) {
+			if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED,
+					      &q->state))) {
+				__qdisc_drop(skb, &to_free);
+				rc = NET_XMIT_DROP;
+				goto end_run;
+			}
 			qdisc_bstats_cpu_update(q, skb);
 
+			rc = NET_XMIT_SUCCESS;
 			if (sch_direct_xmit(skb, q, dev, txq, NULL, true))
 				__qdisc_run(q);
 
+end_run:
 			qdisc_run_end(q);
-			rc = NET_XMIT_SUCCESS;
 		} else {
 			rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
 			qdisc_run(q);
-- 
2.21.0


From fbafffc420280746db88a92eee03c72315734073 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 12 Sep 2019 10:22:30 -0700
Subject: [PATCH 3/6] net_sched: let qdisc_put() accept NULL pointer

[ Upstream commit 6efb971ba8edfbd80b666f29de12882852f095ae ]

When tcf_block_get() fails in sfb_init(), q->qdisc is still a NULL
pointer which leads to a crash in sfb_destroy(). Similar for
sch_dsmark.

Instead of fixing each separately, Linus suggested to just accept
NULL pointer in qdisc_put(), which would make callers easier.

(For sch_dsmark, the bug probably exists long before commit
6529eaba33f0.)

Fixes: 6529eaba33f0 ("net: sched: introduce tcf block infractructure")
Reported-by: syzbot+d5870a903591faaca4ae@syzkaller.appspotmail.com
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_generic.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index ac28f6a5d70e..17bd8f539bc7 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -985,6 +985,9 @@ static void qdisc_destroy(struct Qdisc *qdisc)
 
 void qdisc_put(struct Qdisc *qdisc)
 {
+	if (!qdisc)
+		return;
+
 	if (qdisc->flags & TCQ_F_BUILTIN ||
 	    !refcount_dec_and_test(&qdisc->refcnt))
 		return;
-- 
2.21.0


From a22bcaea3d7f96b751a2b054338fc11c2c2016ee Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Thu, 12 Sep 2019 21:16:39 -0400
Subject: [PATCH 4/6] udp: correct reuseport selection with connected sockets

[ Upstream commit acdcecc61285faed359f1a3568c32089cc3a8329 ]

UDP reuseport groups can hold a mix unconnected and connected sockets.
Ensure that connections only receive all traffic to their 4-tuple.

Fast reuseport returns on the first reuseport match on the assumption
that all matches are equal. Only if connections are present, return to
the previous behavior of scoring all sockets.

Record if connections are present and if so (1) treat such connected
sockets as an independent match from the group, (2) only return
2-tuple matches from reuseport and (3) do not return on the first
2-tuple reuseport match to allow for a higher scoring match later.

New field has_conns is set without locks. No other fields in the
bitmap are modified at runtime and the field is only ever set
unconditionally, so an RMW cannot miss a change.

Fixes: e32ea7e74727 ("soreuseport: fast reuseport UDP socket selection")
Link: http://lkml.kernel.org/r/CA+FuTSfRP09aJNYRt04SS6qj22ViiOEWaWmLAwX0psk8-PGNxw@mail.gmail.com
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Craig Gallek <kraig@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock_reuseport.h | 21 ++++++++++++++++++++-
 net/core/sock_reuseport.c    | 15 +++++++++++++--
 net/ipv4/datagram.c          |  2 ++
 net/ipv4/udp.c               |  5 +++--
 net/ipv6/datagram.c          |  2 ++
 net/ipv6/udp.c               |  5 +++--
 6 files changed, 43 insertions(+), 7 deletions(-)

diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h
index 8a5f70c7cdf2..5e69fba181bc 100644
--- a/include/net/sock_reuseport.h
+++ b/include/net/sock_reuseport.h
@@ -21,7 +21,8 @@ struct sock_reuseport {
 	unsigned int		synq_overflow_ts;
 	/* ID stays the same even after the size of socks[] grows. */
 	unsigned int		reuseport_id;
-	bool			bind_inany;
+	unsigned int		bind_inany:1;
+	unsigned int		has_conns:1;
 	struct bpf_prog __rcu	*prog;		/* optional BPF sock selector */
 	struct sock		*socks[0];	/* array of sock pointers */
 };
@@ -35,6 +36,24 @@ extern struct sock *reuseport_select_sock(struct sock *sk,
 					  struct sk_buff *skb,
 					  int hdr_len);
 extern int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog);
+
+static inline bool reuseport_has_conns(struct sock *sk, bool set)
+{
+	struct sock_reuseport *reuse;
+	bool ret = false;
+
+	rcu_read_lock();
+	reuse = rcu_dereference(sk->sk_reuseport_cb);
+	if (reuse) {
+		if (set)
+			reuse->has_conns = 1;
+		ret = reuse->has_conns;
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
 int reuseport_get_id(struct sock_reuseport *reuse);
 
 #endif  /* _SOCK_REUSEPORT_H */
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index dc4aefdf2a08..2f89777763ad 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -295,8 +295,19 @@ struct sock *reuseport_select_sock(struct sock *sk,
 
 select_by_hash:
 		/* no bpf or invalid bpf result: fall back to hash usage */
-		if (!sk2)
-			sk2 = reuse->socks[reciprocal_scale(hash, socks)];
+		if (!sk2) {
+			int i, j;
+
+			i = j = reciprocal_scale(hash, socks);
+			while (reuse->socks[i]->sk_state == TCP_ESTABLISHED) {
+				i++;
+				if (i >= reuse->num_socks)
+					i = 0;
+				if (i == j)
+					goto out;
+			}
+			sk2 = reuse->socks[i];
+		}
 	}
 
 out:
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index 7bd29e694603..9a0fe0c2fa02 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -15,6 +15,7 @@
 #include <net/sock.h>
 #include <net/route.h>
 #include <net/tcp_states.h>
+#include <net/sock_reuseport.h>
 
 int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
@@ -69,6 +70,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len
 	}
 	inet->inet_daddr = fl4->daddr;
 	inet->inet_dport = usin->sin_port;
+	reuseport_has_conns(sk, true);
 	sk->sk_state = TCP_ESTABLISHED;
 	sk_set_txhash(sk);
 	inet->inet_id = jiffies;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index eed59c847722..acab7738f733 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -434,12 +434,13 @@ static struct sock *udp4_lib_lookup2(struct net *net,
 		score = compute_score(sk, net, saddr, sport,
 				      daddr, hnum, dif, sdif, exact_dif);
 		if (score > badness) {
-			if (sk->sk_reuseport) {
+			if (sk->sk_reuseport &&
+			    sk->sk_state != TCP_ESTABLISHED) {
 				hash = udp_ehashfn(net, daddr, hnum,
 						   saddr, sport);
 				result = reuseport_select_sock(sk, hash, skb,
 							sizeof(struct udphdr));
-				if (result)
+				if (result && !reuseport_has_conns(sk, false))
 					return result;
 			}
 			badness = score;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 9d78c907b918..694168e2302e 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -27,6 +27,7 @@
 #include <net/ip6_route.h>
 #include <net/tcp_states.h>
 #include <net/dsfield.h>
+#include <net/sock_reuseport.h>
 
 #include <linux/errqueue.h>
 #include <linux/uaccess.h>
@@ -254,6 +255,7 @@ int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr,
 		goto out;
 	}
 
+	reuseport_has_conns(sk, true);
 	sk->sk_state = TCP_ESTABLISHED;
 	sk_set_txhash(sk);
 out:
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 70b01bd95022..1258be19e186 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -168,13 +168,14 @@ static struct sock *udp6_lib_lookup2(struct net *net,
 		score = compute_score(sk, net, saddr, sport,
 				      daddr, hnum, dif, sdif, exact_dif);
 		if (score > badness) {
-			if (sk->sk_reuseport) {
+			if (sk->sk_reuseport &&
+			    sk->sk_state != TCP_ESTABLISHED) {
 				hash = udp6_ehashfn(net, daddr, hnum,
 						    saddr, sport);
 
 				result = reuseport_select_sock(sk, hash, skb,
 							sizeof(struct udphdr));
-				if (result)
+				if (result && !reuseport_has_conns(sk, false))
 					return result;
 			}
 			result = sk;
-- 
2.21.0


From 2fa4d9adcf4ec2a5930d29a10e658edb0fbc7cdd Mon Sep 17 00:00:00 2001
From: Dongli Zhang <dongli.zhang@oracle.com>
Date: Mon, 16 Sep 2019 11:46:59 +0800
Subject: [PATCH 5/6] xen-netfront: do not assume sk_buff_head list is empty in
 error handling

[ Upstream commit 00b368502d18f790ab715e055869fd4bb7484a9b ]

When skb_shinfo(skb) is not able to cache extra fragment (that is,
skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS), xennet_fill_frags() assumes
the sk_buff_head list is already empty. As a result, cons is increased only
by 1 and returns to error handling path in xennet_poll().

However, if the sk_buff_head list is not empty, queue->rx.rsp_cons may be
set incorrectly. That is, queue->rx.rsp_cons would point to the rx ring
buffer entries whose queue->rx_skbs[i] and queue->grant_rx_ref[i] are
already cleared to NULL. This leads to NULL pointer access in the next
iteration to process rx ring buffer entries.

Below is how xennet_poll() does error handling. All remaining entries in
tmpq are accounted to queue->rx.rsp_cons without assuming how many
outstanding skbs are remained in the list.

 985 static int xennet_poll(struct napi_struct *napi, int budget)
... ...
1032           if (unlikely(xennet_set_skb_gso(skb, gso))) {
1033                   __skb_queue_head(&tmpq, skb);
1034                   queue->rx.rsp_cons += skb_queue_len(&tmpq);
1035                   goto err;
1036           }

It is better to always have the error handling in the same way.

Fixes: ad4f15dc2c70 ("xen/netfront: don't bug in case of too many frags")
Signed-off-by: Dongli Zhang <dongli.zhang@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netfront.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 8d33970a2950..5f5722bf6762 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -906,7 +906,7 @@ static RING_IDX xennet_fill_frags(struct netfront_queue *queue,
 			__pskb_pull_tail(skb, pull_to - skb_headlen(skb));
 		}
 		if (unlikely(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS)) {
-			queue->rx.rsp_cons = ++cons;
+			queue->rx.rsp_cons = ++cons + skb_queue_len(list);
 			kfree_skb(nskb);
 			return ~0U;
 		}
-- 
2.21.0


From 29e355687f4a54bf34bcac2fbbe7208f6cf1f381 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Thu, 12 Sep 2019 15:16:45 +0200
Subject: [PATCH 6/6] net: dsa: Fix load order between DSA drivers and taggers

[ Upstream commit 23426a25e55a417dc104df08781b6eff95e65f3f ]

The DSA core, DSA taggers and DSA drivers all make use of
module_init(). Hence they get initialised at device_initcall() time.
The ordering is non-deterministic. It can be a DSA driver is bound to
a device before the needed tag driver has been initialised, resulting
in the message:

No tagger for this switch

Rather than have this be fatal, return -EPROBE_DEFER so that it is
tried again later once all the needed drivers have been loaded.

Fixes: d3b8c04988ca ("dsa: Add boilerplate helper to register DSA tag driver modules")
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/dsa2.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index 820dd8da57fc..1739b98a8f4b 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -577,6 +577,8 @@ static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master)
 	tag_protocol = ds->ops->get_tag_protocol(ds, dp->index);
 	tag_ops = dsa_tag_driver_get(tag_protocol);
 	if (IS_ERR(tag_ops)) {
+		if (PTR_ERR(tag_ops) == -ENOPROTOOPT)
+			return -EPROBE_DEFER;
 		dev_warn(ds->dev, "No tagger for this switch\n");
 		return PTR_ERR(tag_ops);
 	}
-- 
2.21.0


[-- Attachment #3: net_53.mbox --]
[-- Type: Application/Octet-Stream, Size: 18076 bytes --]

From 6bbe1af07c8b8475a59cbb2d064022b9d66063f0 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Fri, 13 Sep 2019 17:45:47 +0800
Subject: [PATCH 1/7] ip6_gre: fix a dst leak in ip6erspan_tunnel_xmit

[ Upstream commit 28e486037747c2180470b77c290d4090ad42f259 ]

In ip6erspan_tunnel_xmit(), if the skb will not be sent out, it has to
be freed on the tx_err path. Otherwise when deleting a netns, it would
cause dst/dev to leak, and dmesg shows:

  unregister_netdevice: waiting for lo to become free. Usage count = 1

Fixes: ef7baf5e083c ("ip6_gre: add ip6 erspan collect_md mode")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: William Tu <u9012063@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index dd2d0b963260..d5779d6a6065 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -968,7 +968,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 		if (unlikely(!tun_info ||
 			     !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
 			     ip_tunnel_info_af(tun_info) != AF_INET6))
-			return -EINVAL;
+			goto tx_err;
 
 		key = &tun_info->key;
 		memset(&fl6, 0, sizeof(fl6));
-- 
2.21.0


From d81ca4560881efb5d226ac2a7a098f6ff3caacae Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 12 Sep 2019 12:02:42 +0200
Subject: [PATCH 2/7] net/sched: fix race between deactivation and dequeue for
 NOLOCK qdisc

[ Upstream commit d518d2ed8640c1cbbbb6f63939e3e65471817367 ]

The test implemented by some_qdisc_is_busy() is somewhat loosy for
NOLOCK qdisc, as we may hit the following scenario:

CPU1						CPU2
// in net_tx_action()
clear_bit(__QDISC_STATE_SCHED...);
						// in some_qdisc_is_busy()
						val = (qdisc_is_running(q) ||
						       test_bit(__QDISC_STATE_SCHED,
								&q->state));
						// here val is 0 but...
qdisc_run(q)
// ... CPU1 is going to run the qdisc next

As a conseguence qdisc_run() in net_tx_action() can race with qdisc_reset()
in dev_qdisc_reset(). Such race is not possible for !NOLOCK qdisc as
both the above bit operations are under the root qdisc lock().

After commit 021a17ed796b ("pfifo_fast: drop unneeded additional lock on dequeue")
the race can cause use after free and/or null ptr dereference, but the root
cause is likely older.

This patch addresses the issue explicitly checking for deactivation under
the seqlock for NOLOCK qdisc, so that the qdisc_run() in the critical
scenario becomes a no-op.

Note that the enqueue() op can still execute concurrently with dev_qdisc_reset(),
but that is safe due to the skb_array() locking, and we can't avoid that
for NOLOCK qdiscs.

Fixes: 021a17ed796b ("pfifo_fast: drop unneeded additional lock on dequeue")
Reported-by: Li Shuang <shuali@redhat.com>
Reported-and-tested-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/pkt_sched.h |  7 ++++++-
 net/core/dev.c          | 16 ++++++++++------
 2 files changed, 16 insertions(+), 7 deletions(-)

diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index a16fbe9a2a67..aa99c73c3fbd 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -118,7 +118,12 @@ void __qdisc_run(struct Qdisc *q);
 static inline void qdisc_run(struct Qdisc *q)
 {
 	if (qdisc_run_begin(q)) {
-		__qdisc_run(q);
+		/* NOLOCK qdisc must check 'state' under the qdisc seqlock
+		 * to avoid racing with dev_qdisc_reset()
+		 */
+		if (!(q->flags & TCQ_F_NOLOCK) ||
+		    likely(!test_bit(__QDISC_STATE_DEACTIVATED, &q->state)))
+			__qdisc_run(q);
 		qdisc_run_end(q);
 	}
 }
diff --git a/net/core/dev.c b/net/core/dev.c
index 5156c0edebe8..4ed9df74eb8a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3467,18 +3467,22 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 	qdisc_calculate_pkt_len(skb, q);
 
 	if (q->flags & TCQ_F_NOLOCK) {
-		if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) {
-			__qdisc_drop(skb, &to_free);
-			rc = NET_XMIT_DROP;
-		} else if ((q->flags & TCQ_F_CAN_BYPASS) && q->empty &&
-			   qdisc_run_begin(q)) {
+		if ((q->flags & TCQ_F_CAN_BYPASS) && q->empty &&
+		    qdisc_run_begin(q)) {
+			if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED,
+					      &q->state))) {
+				__qdisc_drop(skb, &to_free);
+				rc = NET_XMIT_DROP;
+				goto end_run;
+			}
 			qdisc_bstats_cpu_update(q, skb);
 
+			rc = NET_XMIT_SUCCESS;
 			if (sch_direct_xmit(skb, q, dev, txq, NULL, true))
 				__qdisc_run(q);
 
+end_run:
 			qdisc_run_end(q);
-			rc = NET_XMIT_SUCCESS;
 		} else {
 			rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
 			qdisc_run(q);
-- 
2.21.0


From 3c34342ed8bd7d48f7f94bc728368227f51e08be Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 12 Sep 2019 10:22:30 -0700
Subject: [PATCH 3/7] net_sched: let qdisc_put() accept NULL pointer

[ Upstream commit 6efb971ba8edfbd80b666f29de12882852f095ae ]

When tcf_block_get() fails in sfb_init(), q->qdisc is still a NULL
pointer which leads to a crash in sfb_destroy(). Similar for
sch_dsmark.

Instead of fixing each separately, Linus suggested to just accept
NULL pointer in qdisc_put(), which would make callers easier.

(For sch_dsmark, the bug probably exists long before commit
6529eaba33f0.)

Fixes: 6529eaba33f0 ("net: sched: introduce tcf block infractructure")
Reported-by: syzbot+d5870a903591faaca4ae@syzkaller.appspotmail.com
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_generic.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index ac28f6a5d70e..17bd8f539bc7 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -985,6 +985,9 @@ static void qdisc_destroy(struct Qdisc *qdisc)
 
 void qdisc_put(struct Qdisc *qdisc)
 {
+	if (!qdisc)
+		return;
+
 	if (qdisc->flags & TCQ_F_BUILTIN ||
 	    !refcount_dec_and_test(&qdisc->refcnt))
 		return;
-- 
2.21.0


From 453a90557b504446bf2292e119219098e01e8bd6 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Thu, 12 Sep 2019 21:16:39 -0400
Subject: [PATCH 4/7] udp: correct reuseport selection with connected sockets

[ Upstream commit acdcecc61285faed359f1a3568c32089cc3a8329 ]

UDP reuseport groups can hold a mix unconnected and connected sockets.
Ensure that connections only receive all traffic to their 4-tuple.

Fast reuseport returns on the first reuseport match on the assumption
that all matches are equal. Only if connections are present, return to
the previous behavior of scoring all sockets.

Record if connections are present and if so (1) treat such connected
sockets as an independent match from the group, (2) only return
2-tuple matches from reuseport and (3) do not return on the first
2-tuple reuseport match to allow for a higher scoring match later.

New field has_conns is set without locks. No other fields in the
bitmap are modified at runtime and the field is only ever set
unconditionally, so an RMW cannot miss a change.

Fixes: e32ea7e74727 ("soreuseport: fast reuseport UDP socket selection")
Link: http://lkml.kernel.org/r/CA+FuTSfRP09aJNYRt04SS6qj22ViiOEWaWmLAwX0psk8-PGNxw@mail.gmail.com
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Craig Gallek <kraig@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock_reuseport.h | 20 +++++++++++++++++++-
 net/core/sock_reuseport.c    | 15 +++++++++++++--
 net/ipv4/datagram.c          |  2 ++
 net/ipv4/udp.c               |  5 +++--
 net/ipv6/datagram.c          |  2 ++
 net/ipv6/udp.c               |  5 +++--
 6 files changed, 42 insertions(+), 7 deletions(-)

diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h
index d9112de85261..43f4a818d88f 100644
--- a/include/net/sock_reuseport.h
+++ b/include/net/sock_reuseport.h
@@ -21,7 +21,8 @@ struct sock_reuseport {
 	unsigned int		synq_overflow_ts;
 	/* ID stays the same even after the size of socks[] grows. */
 	unsigned int		reuseport_id;
-	bool			bind_inany;
+	unsigned int		bind_inany:1;
+	unsigned int		has_conns:1;
 	struct bpf_prog __rcu	*prog;		/* optional BPF sock selector */
 	struct sock		*socks[0];	/* array of sock pointers */
 };
@@ -37,6 +38,23 @@ extern struct sock *reuseport_select_sock(struct sock *sk,
 extern int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog);
 extern int reuseport_detach_prog(struct sock *sk);
 
+static inline bool reuseport_has_conns(struct sock *sk, bool set)
+{
+	struct sock_reuseport *reuse;
+	bool ret = false;
+
+	rcu_read_lock();
+	reuse = rcu_dereference(sk->sk_reuseport_cb);
+	if (reuse) {
+		if (set)
+			reuse->has_conns = 1;
+		ret = reuse->has_conns;
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
 int reuseport_get_id(struct sock_reuseport *reuse);
 
 #endif  /* _SOCK_REUSEPORT_H */
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index 9408f9264d05..f3ceec93f392 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -295,8 +295,19 @@ struct sock *reuseport_select_sock(struct sock *sk,
 
 select_by_hash:
 		/* no bpf or invalid bpf result: fall back to hash usage */
-		if (!sk2)
-			sk2 = reuse->socks[reciprocal_scale(hash, socks)];
+		if (!sk2) {
+			int i, j;
+
+			i = j = reciprocal_scale(hash, socks);
+			while (reuse->socks[i]->sk_state == TCP_ESTABLISHED) {
+				i++;
+				if (i >= reuse->num_socks)
+					i = 0;
+				if (i == j)
+					goto out;
+			}
+			sk2 = reuse->socks[i];
+		}
 	}
 
 out:
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index 7bd29e694603..9a0fe0c2fa02 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -15,6 +15,7 @@
 #include <net/sock.h>
 #include <net/route.h>
 #include <net/tcp_states.h>
+#include <net/sock_reuseport.h>
 
 int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
@@ -69,6 +70,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len
 	}
 	inet->inet_daddr = fl4->daddr;
 	inet->inet_dport = usin->sin_port;
+	reuseport_has_conns(sk, true);
 	sk->sk_state = TCP_ESTABLISHED;
 	sk_set_txhash(sk);
 	inet->inet_id = jiffies;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index d88821c794fb..16486c8b708b 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -423,12 +423,13 @@ static struct sock *udp4_lib_lookup2(struct net *net,
 		score = compute_score(sk, net, saddr, sport,
 				      daddr, hnum, dif, sdif);
 		if (score > badness) {
-			if (sk->sk_reuseport) {
+			if (sk->sk_reuseport &&
+			    sk->sk_state != TCP_ESTABLISHED) {
 				hash = udp_ehashfn(net, daddr, hnum,
 						   saddr, sport);
 				result = reuseport_select_sock(sk, hash, skb,
 							sizeof(struct udphdr));
-				if (result)
+				if (result && !reuseport_has_conns(sk, false))
 					return result;
 			}
 			badness = score;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 9ab897ded4df..96f939248d2f 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -27,6 +27,7 @@
 #include <net/ip6_route.h>
 #include <net/tcp_states.h>
 #include <net/dsfield.h>
+#include <net/sock_reuseport.h>
 
 #include <linux/errqueue.h>
 #include <linux/uaccess.h>
@@ -254,6 +255,7 @@ int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr,
 		goto out;
 	}
 
+	reuseport_has_conns(sk, true);
 	sk->sk_state = TCP_ESTABLISHED;
 	sk_set_txhash(sk);
 out:
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 827fe7385078..5995fdc99d3f 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -158,13 +158,14 @@ static struct sock *udp6_lib_lookup2(struct net *net,
 		score = compute_score(sk, net, saddr, sport,
 				      daddr, hnum, dif, sdif);
 		if (score > badness) {
-			if (sk->sk_reuseport) {
+			if (sk->sk_reuseport &&
+			    sk->sk_state != TCP_ESTABLISHED) {
 				hash = udp6_ehashfn(net, daddr, hnum,
 						    saddr, sport);
 
 				result = reuseport_select_sock(sk, hash, skb,
 							sizeof(struct udphdr));
-				if (result)
+				if (result && !reuseport_has_conns(sk, false))
 					return result;
 			}
 			result = sk;
-- 
2.21.0


From d285fc27048a9f47fbf8d79b7157754f42d30b2f Mon Sep 17 00:00:00 2001
From: Dongli Zhang <dongli.zhang@oracle.com>
Date: Mon, 16 Sep 2019 11:46:59 +0800
Subject: [PATCH 5/7] xen-netfront: do not assume sk_buff_head list is empty in
 error handling

[ Upstream commit 00b368502d18f790ab715e055869fd4bb7484a9b ]

When skb_shinfo(skb) is not able to cache extra fragment (that is,
skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS), xennet_fill_frags() assumes
the sk_buff_head list is already empty. As a result, cons is increased only
by 1 and returns to error handling path in xennet_poll().

However, if the sk_buff_head list is not empty, queue->rx.rsp_cons may be
set incorrectly. That is, queue->rx.rsp_cons would point to the rx ring
buffer entries whose queue->rx_skbs[i] and queue->grant_rx_ref[i] are
already cleared to NULL. This leads to NULL pointer access in the next
iteration to process rx ring buffer entries.

Below is how xennet_poll() does error handling. All remaining entries in
tmpq are accounted to queue->rx.rsp_cons without assuming how many
outstanding skbs are remained in the list.

 985 static int xennet_poll(struct napi_struct *napi, int budget)
... ...
1032           if (unlikely(xennet_set_skb_gso(skb, gso))) {
1033                   __skb_queue_head(&tmpq, skb);
1034                   queue->rx.rsp_cons += skb_queue_len(&tmpq);
1035                   goto err;
1036           }

It is better to always have the error handling in the same way.

Fixes: ad4f15dc2c70 ("xen/netfront: don't bug in case of too many frags")
Signed-off-by: Dongli Zhang <dongli.zhang@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netfront.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 8d33970a2950..5f5722bf6762 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -906,7 +906,7 @@ static RING_IDX xennet_fill_frags(struct netfront_queue *queue,
 			__pskb_pull_tail(skb, pull_to - skb_headlen(skb));
 		}
 		if (unlikely(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS)) {
-			queue->rx.rsp_cons = ++cons;
+			queue->rx.rsp_cons = ++cons + skb_queue_len(list);
 			kfree_skb(nskb);
 			return ~0U;
 		}
-- 
2.21.0


From 96256c6cae1337dd2a34dbd2bc377d325ceea38e Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Thu, 12 Sep 2019 15:16:45 +0200
Subject: [PATCH 6/7] net: dsa: Fix load order between DSA drivers and taggers

[ Upstream commit 23426a25e55a417dc104df08781b6eff95e65f3f ]

The DSA core, DSA taggers and DSA drivers all make use of
module_init(). Hence they get initialised at device_initcall() time.
The ordering is non-deterministic. It can be a DSA driver is bound to
a device before the needed tag driver has been initialised, resulting
in the message:

No tagger for this switch

Rather than have this be fatal, return -EPROBE_DEFER so that it is
tried again later once all the needed drivers have been loaded.

Fixes: d3b8c04988ca ("dsa: Add boilerplate helper to register DSA tag driver modules")
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/dsa2.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index 3abd173ebacb..96f787cf9b6e 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -623,6 +623,8 @@ static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master)
 	tag_protocol = ds->ops->get_tag_protocol(ds, dp->index);
 	tag_ops = dsa_tag_driver_get(tag_protocol);
 	if (IS_ERR(tag_ops)) {
+		if (PTR_ERR(tag_ops) == -ENOPROTOOPT)
+			return -EPROBE_DEFER;
 		dev_warn(ds->dev, "No tagger for this switch\n");
 		return PTR_ERR(tag_ops);
 	}
-- 
2.21.0


From 11cf0ea12a672659751e68d0ce1c59e49b069e98 Mon Sep 17 00:00:00 2001
From: Jose Abreu <Jose.Abreu@synopsys.com>
Date: Fri, 13 Sep 2019 11:50:32 +0200
Subject: [PATCH 7/7] net: stmmac: Hold rtnl lock in suspend/resume callbacks

[ Upstream commit 19e13cb27b998ff49f07e399b5871bfe5ba7e3f0 ]

We need to hold rnl lock in suspend and resume callbacks because phylink
requires it. Otherwise we will get a WARN() in suspend and resume.

Also, move phylink start and stop callbacks to inside device's internal
lock so that we prevent concurrent HW accesses.

Fixes: 74371272f97f ("net: stmmac: Convert to phylink and remove phylib logic")
Reported-by: Christophe ROULLIER <christophe.roullier@st.com>
Tested-by: Christophe ROULLIER <christophe.roullier@st.com>
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index fd54c7c87485..b19ab09cb18f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -4451,10 +4451,12 @@ int stmmac_suspend(struct device *dev)
 	if (!ndev || !netif_running(ndev))
 		return 0;
 
-	phylink_stop(priv->phylink);
-
 	mutex_lock(&priv->lock);
 
+	rtnl_lock();
+	phylink_stop(priv->phylink);
+	rtnl_unlock();
+
 	netif_device_detach(ndev);
 	stmmac_stop_all_queues(priv);
 
@@ -4558,9 +4560,11 @@ int stmmac_resume(struct device *dev)
 
 	stmmac_start_all_queues(priv);
 
-	mutex_unlock(&priv->lock);
-
+	rtnl_lock();
 	phylink_start(priv->phylink);
+	rtnl_unlock();
+
+	mutex_unlock(&priv->lock);
 
 	return 0;
 }
-- 
2.21.0

Re: [PATCHES] Networking

[Greg KH]

On Thu, Sep 19, 2019 at 02:07:00PM +0200, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v5.2 and v5.3 -stable,
> respectively.

Thanks, now queued up!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 102 bytes --]


Please queue up the following networking bug fixes for v5.2
and v5.3 -stable, respectively.

Thanks!

[-- Attachment #2: net_52.mbox --]
[-- Type: Application/Octet-Stream, Size: 71738 bytes --]

From 3e7e232aa440cdef9bd8a0ff056db28df5d7cd79 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 20 Sep 2019 16:08:21 +0200
Subject: [PATCH 01/32] arcnet: provide a buffer big enough to actually receive
 packets
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 108639aac35eb57f1d0e8333f5fc8c7ff68df938 ]

struct archdr is only big enough to hold the header of various types of
arcnet packets. So to provide enough space to hold the data read from
hardware provide a buffer large enough to hold a packet with maximal
size.

The problem was noticed by the stack protector which makes the kernel
oops.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Michael Grzeschik <m.grzeschik@pengutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/arcnet/arcnet.c | 31 +++++++++++++++++--------------
 1 file changed, 17 insertions(+), 14 deletions(-)

diff --git a/drivers/net/arcnet/arcnet.c b/drivers/net/arcnet/arcnet.c
index 8459115d9d4e..553776cc1d29 100644
--- a/drivers/net/arcnet/arcnet.c
+++ b/drivers/net/arcnet/arcnet.c
@@ -1063,31 +1063,34 @@ EXPORT_SYMBOL(arcnet_interrupt);
 static void arcnet_rx(struct net_device *dev, int bufnum)
 {
 	struct arcnet_local *lp = netdev_priv(dev);
-	struct archdr pkt;
+	union {
+		struct archdr pkt;
+		char buf[512];
+	} rxdata;
 	struct arc_rfc1201 *soft;
 	int length, ofs;
 
-	soft = &pkt.soft.rfc1201;
+	soft = &rxdata.pkt.soft.rfc1201;
 
-	lp->hw.copy_from_card(dev, bufnum, 0, &pkt, ARC_HDR_SIZE);
-	if (pkt.hard.offset[0]) {
-		ofs = pkt.hard.offset[0];
+	lp->hw.copy_from_card(dev, bufnum, 0, &rxdata.pkt, ARC_HDR_SIZE);
+	if (rxdata.pkt.hard.offset[0]) {
+		ofs = rxdata.pkt.hard.offset[0];
 		length = 256 - ofs;
 	} else {
-		ofs = pkt.hard.offset[1];
+		ofs = rxdata.pkt.hard.offset[1];
 		length = 512 - ofs;
 	}
 
 	/* get the full header, if possible */
-	if (sizeof(pkt.soft) <= length) {
-		lp->hw.copy_from_card(dev, bufnum, ofs, soft, sizeof(pkt.soft));
+	if (sizeof(rxdata.pkt.soft) <= length) {
+		lp->hw.copy_from_card(dev, bufnum, ofs, soft, sizeof(rxdata.pkt.soft));
 	} else {
-		memset(&pkt.soft, 0, sizeof(pkt.soft));
+		memset(&rxdata.pkt.soft, 0, sizeof(rxdata.pkt.soft));
 		lp->hw.copy_from_card(dev, bufnum, ofs, soft, length);
 	}
 
 	arc_printk(D_DURING, dev, "Buffer #%d: received packet from %02Xh to %02Xh (%d+4 bytes)\n",
-		   bufnum, pkt.hard.source, pkt.hard.dest, length);
+		   bufnum, rxdata.pkt.hard.source, rxdata.pkt.hard.dest, length);
 
 	dev->stats.rx_packets++;
 	dev->stats.rx_bytes += length + ARC_HDR_SIZE;
@@ -1096,13 +1099,13 @@ static void arcnet_rx(struct net_device *dev, int bufnum)
 	if (arc_proto_map[soft->proto]->is_ip) {
 		if (BUGLVL(D_PROTO)) {
 			struct ArcProto
-			*oldp = arc_proto_map[lp->default_proto[pkt.hard.source]],
+			*oldp = arc_proto_map[lp->default_proto[rxdata.pkt.hard.source]],
 			*newp = arc_proto_map[soft->proto];
 
 			if (oldp != newp) {
 				arc_printk(D_PROTO, dev,
 					   "got protocol %02Xh; encap for host %02Xh is now '%c' (was '%c')\n",
-					   soft->proto, pkt.hard.source,
+					   soft->proto, rxdata.pkt.hard.source,
 					   newp->suffix, oldp->suffix);
 			}
 		}
@@ -1111,10 +1114,10 @@ static void arcnet_rx(struct net_device *dev, int bufnum)
 		lp->default_proto[0] = soft->proto;
 
 		/* in striking contrast, the following isn't a hack. */
-		lp->default_proto[pkt.hard.source] = soft->proto;
+		lp->default_proto[rxdata.pkt.hard.source] = soft->proto;
 	}
 	/* call the protocol-specific receiver. */
-	arc_proto_map[soft->proto]->rx(dev, bufnum, &pkt, length);
+	arc_proto_map[soft->proto]->rx(dev, bufnum, &rxdata.pkt, length);
 }
 
 static void null_rx(struct net_device *dev, int bufnum,
-- 
2.20.1


From b6c5221f0da28e1cd8d008a5a2c179da4e145b5a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Wed, 18 Sep 2019 14:01:46 +0200
Subject: [PATCH 02/32] cdc_ncm: fix divide-by-zero caused by invalid
 wMaxPacketSize
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 3fe4b3351301660653a2bc73f2226da0ebd2b95e ]

Endpoints with zero wMaxPacketSize are not usable for transferring
data. Ignore such endpoints when looking for valid in, out and
status pipes, to make the driver more robust against invalid and
meaningless descriptors.

The wMaxPacketSize of the out pipe is used as divisor. So this change
fixes a divide-by-zero bug.

Reported-by: syzbot+ce366e2b8296e25d84f5@syzkaller.appspotmail.com
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/usb/cdc_ncm.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 50c05d0f44cb..00cab3f43a4c 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -681,8 +681,12 @@ cdc_ncm_find_endpoints(struct usbnet *dev, struct usb_interface *intf)
 	u8 ep;
 
 	for (ep = 0; ep < intf->cur_altsetting->desc.bNumEndpoints; ep++) {
-
 		e = intf->cur_altsetting->endpoint + ep;
+
+		/* ignore endpoints which cannot transfer data */
+		if (!usb_endpoint_maxp(&e->desc))
+			continue;
+
 		switch (e->desc.bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) {
 		case USB_ENDPOINT_XFER_INT:
 			if (usb_endpoint_dir_in(&e->desc)) {
-- 
2.20.1


From 4f5075bd083b65e5b895bfc65331d154e30633f1 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Tue, 24 Sep 2019 16:01:28 +0200
Subject: [PATCH 03/32] ipv6: do not free rt if FIB_LOOKUP_NOREF is set on
 suppress rule

[ Upstream commit ca7a03c4175366a92cee0ccc4fec0038c3266e26 ]

Commit 7d9e5f422150 removed references from certain dsts, but accounting
for this never translated down into the fib6 suppression code. This bug
was triggered by WireGuard users who use wg-quick(8), which uses the
"suppress-prefix" directive to ip-rule(8) for routing all of their
internet traffic without routing loops. The test case added here
causes the reference underflow by causing packets to evaluate a suppress
rule.

Fixes: 7d9e5f422150 ("ipv6: convert major tx path to use RT6_LOOKUP_F_DST_NOREF")
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Acked-by: Wei Wang <weiwan@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/fib6_rules.c                    |  3 ++-
 tools/testing/selftests/net/fib_tests.sh | 17 ++++++++++++++++-
 2 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index bcfae13409b5..67b60b1da922 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -285,7 +285,8 @@ static bool fib6_rule_suppress(struct fib_rule *rule, struct fib_lookup_arg *arg
 	return false;
 
 suppress_route:
-	ip6_rt_put(rt);
+	if (!(arg->flags & FIB_LOOKUP_NOREF))
+		ip6_rt_put(rt);
 	return true;
 }
 
diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 9457aaeae092..0eca8fef2b9f 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -9,7 +9,7 @@ ret=0
 ksft_skip=4
 
 # all tests in this script. Can be overridden with -t option
-TESTS="unregister down carrier nexthop ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics ipv4_route_v6_gw"
+TESTS="unregister down carrier nexthop suppress ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics ipv4_route_v6_gw"
 
 VERBOSE=0
 PAUSE_ON_FAIL=no
@@ -582,6 +582,20 @@ fib_nexthop_test()
 	cleanup
 }
 
+fib_suppress_test()
+{
+	$IP link add dummy1 type dummy
+	$IP link set dummy1 up
+	$IP -6 route add default dev dummy1
+	$IP -6 rule add table main suppress_prefixlength 0
+	ping -f -c 1000 -W 1 1234::1 || true
+	$IP -6 rule del table main suppress_prefixlength 0
+	$IP link del dummy1
+
+	# If we got here without crashing, we're good.
+	return 0
+}
+
 ################################################################################
 # Tests on route add and replace
 
@@ -1558,6 +1572,7 @@ do
 	fib_down_test|down)		fib_down_test;;
 	fib_carrier_test|carrier)	fib_carrier_test;;
 	fib_nexthop_test|nexthop)	fib_nexthop_test;;
+	fib_suppress_test|suppress)	fib_suppress_test;;
 	ipv6_route_test|ipv6_rt)	ipv6_route_test;;
 	ipv4_route_test|ipv4_rt)	ipv4_route_test;;
 	ipv6_addr_metric)		ipv6_addr_metric_test;;
-- 
2.20.1


From b6ef69fe6ef74c0b75443b6712c326d8decdfdb2 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 23 Sep 2019 17:02:46 +0800
Subject: [PATCH 04/32] macsec: drop skb sk before calling gro_cells_receive

[ Upstream commit ba56d8ce38c8252fff5b745db3899cf092578ede ]

Fei Liu reported a crash when doing netperf on a topo of macsec
dev over veth:

  [  448.919128] refcount_t: underflow; use-after-free.
  [  449.090460] Call trace:
  [  449.092895]  refcount_sub_and_test+0xb4/0xc0
  [  449.097155]  tcp_wfree+0x2c/0x150
  [  449.100460]  ip_rcv+0x1d4/0x3a8
  [  449.103591]  __netif_receive_skb_core+0x554/0xae0
  [  449.108282]  __netif_receive_skb+0x28/0x78
  [  449.112366]  netif_receive_skb_internal+0x54/0x100
  [  449.117144]  napi_gro_complete+0x70/0xc0
  [  449.121054]  napi_gro_flush+0x6c/0x90
  [  449.124703]  napi_complete_done+0x50/0x130
  [  449.128788]  gro_cell_poll+0x8c/0xa8
  [  449.132351]  net_rx_action+0x16c/0x3f8
  [  449.136088]  __do_softirq+0x128/0x320

The issue was caused by skb's true_size changed without its sk's
sk_wmem_alloc increased in tcp/skb_gro_receive(). Later when the
skb is being freed and the skb's truesize is subtracted from its
sk's sk_wmem_alloc in tcp_wfree(), underflow occurs.

macsec is calling gro_cells_receive() to receive a packet, which
actually requires skb->sk to be NULL. However when macsec dev is
over veth, it's possible the skb->sk is still set if the skb was
not unshared or expanded from the peer veth.

ip_rcv() is calling skb_orphan() to drop the skb's sk for tproxy,
but it is too late for macsec's calling gro_cells_receive(). So
fix it by dropping the skb's sk earlier on rx path of macsec.

Fixes: 5491e7c6b1a9 ("macsec: enable GRO and RPS on macsec devices")
Reported-by: Xiumei Mu <xmu@redhat.com>
Reported-by: Fei Liu <feliu@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macsec.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 8f46aa1ddec0..cb7637364b40 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -1235,6 +1235,7 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb)
 		macsec_rxsa_put(rx_sa);
 	macsec_rxsc_put(rx_sc);
 
+	skb_orphan(skb);
 	ret = gro_cells_receive(&macsec->gro_cells, skb);
 	if (ret == NET_RX_SUCCESS)
 		count_rx(dev, skb->len);
-- 
2.20.1


From cc157883ce30664880d74cf58f42a7c9e1e2ba14 Mon Sep 17 00:00:00 2001
From: Peter Mamonov <pmamonov@gmail.com>
Date: Wed, 18 Sep 2019 19:27:55 +0300
Subject: [PATCH 05/32] net/phy: fix DP83865 10 Mbps HDX loopback disable
 function

[ Upstream commit e47488b2df7f9cb405789c7f5d4c27909fc597ae ]

According to the DP83865 datasheet "the 10 Mbps HDX loopback can be
disabled in the expanded memory register 0x1C0.1". The driver erroneously
used bit 0 instead of bit 1.

Fixes: 4621bf129856 ("phy: Add file missed in previous commit.")
Signed-off-by: Peter Mamonov <pmamonov@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/phy/national.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/phy/national.c b/drivers/net/phy/national.c
index a221dd552c3c..a5bf0874c7d8 100644
--- a/drivers/net/phy/national.c
+++ b/drivers/net/phy/national.c
@@ -105,14 +105,17 @@ static void ns_giga_speed_fallback(struct phy_device *phydev, int mode)
 
 static void ns_10_base_t_hdx_loopack(struct phy_device *phydev, int disable)
 {
+	u16 lb_dis = BIT(1);
+
 	if (disable)
-		ns_exp_write(phydev, 0x1c0, ns_exp_read(phydev, 0x1c0) | 1);
+		ns_exp_write(phydev, 0x1c0,
+			     ns_exp_read(phydev, 0x1c0) | lb_dis);
 	else
 		ns_exp_write(phydev, 0x1c0,
-			     ns_exp_read(phydev, 0x1c0) & 0xfffe);
+			     ns_exp_read(phydev, 0x1c0) & ~lb_dis);
 
 	pr_debug("10BASE-T HDX loopback %s\n",
-		 (ns_exp_read(phydev, 0x1c0) & 0x0001) ? "off" : "on");
+		 (ns_exp_read(phydev, 0x1c0) & lb_dis) ? "off" : "on");
 }
 
 static int ns_config_init(struct phy_device *phydev)
-- 
2.20.1


From 0b22be46e23bda3d32b4ce7cf78efe401abf2554 Mon Sep 17 00:00:00 2001
From: Bjorn Andersson <bjorn.andersson@linaro.org>
Date: Wed, 18 Sep 2019 10:21:17 -0700
Subject: [PATCH 06/32] net: qrtr: Stop rx_worker before freeing node

[ Upstream commit 73f0c11d11329a0d6d205d4312b6e5d2512af7c5 ]

As the endpoint is unregistered there might still be work pending to
handle incoming messages, which will result in a use after free
scenario. The plan is to remove the rx_worker, but until then (and for
stable@) ensure that the work is stopped before the node is freed.

Fixes: bdabad3e363d ("net: Add Qualcomm IPC router")
Cc: stable@vger.kernel.org
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/qrtr/qrtr.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index 6c8b0f6d28f9..88f98f27ad88 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -150,6 +150,7 @@ static void __qrtr_node_release(struct kref *kref)
 	list_del(&node->item);
 	mutex_unlock(&qrtr_node_lock);
 
+	cancel_work_sync(&node->work);
 	skb_queue_purge(&node->rx_queue);
 	kfree(node);
 }
-- 
2.20.1


From 346557acae2817ddea7c2b35efaa0718563bdac2 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Tue, 17 Sep 2019 11:30:55 +0200
Subject: [PATCH 07/32] net/sched: act_sample: don't push mac header on ip6gre
 ingress

[ Upstream commit 92974a1d006ad8b30d53047c70974c9e065eb7df ]

current 'sample' action doesn't push the mac header of ingress packets if
they are received by a layer 3 tunnel (like gre or sit); but it forgot to
check for gre over ipv6, so the following script:

 # tc q a dev $d clsact
 # tc f a dev $d ingress protocol ip flower ip_proto icmp action sample \
 > group 100 rate 1
 # psample -v -g 100

dumps everything, including outer header and mac, when $d is a gre tunnel
over ipv6. Fix this adding a missing label for ARPHRD_IP6GRE devices.

Fixes: 5c5670fae430 ("net/sched: Introduce sample tc action")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Reviewed-by: Yotam Gigi <yotam.gi@gmail.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/sched/act_sample.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 10229124a992..86344fd2ff1f 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -146,6 +146,7 @@ static bool tcf_sample_dev_ok_push(struct net_device *dev)
 	case ARPHRD_TUNNEL6:
 	case ARPHRD_SIT:
 	case ARPHRD_IPGRE:
+	case ARPHRD_IP6GRE:
 	case ARPHRD_VOID:
 	case ARPHRD_NONE:
 		return false;
-- 
2.20.1


From 239aa14c3c4a180dc02fca2f633a186fc2158198 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Wed, 18 Sep 2019 16:24:12 -0700
Subject: [PATCH 08/32] net_sched: add max len check for TCA_KIND

[ Upstream commit 62794fc4fbf52f2209dc094ea255eaef760e7d01 ]

The TCA_KIND attribute is of NLA_STRING which does not check
the NUL char. KMSAN reported an uninit-value of TCA_KIND which
is likely caused by the lack of NUL.

Change it to NLA_NUL_STRING and add a max len too.

Fixes: 8b4c3cdd9dd8 ("net: sched: Add policy validation for tc attributes")
Reported-and-tested-by: syzbot+618aacd49e8c8b8486bd@syzkaller.appspotmail.com
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/sched/sch_api.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 04faee7ccbce..dac9f2887694 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1390,7 +1390,8 @@ check_loop_fn(struct Qdisc *q, unsigned long cl, struct qdisc_walker *w)
 }
 
 const struct nla_policy rtm_tca_policy[TCA_MAX + 1] = {
-	[TCA_KIND]		= { .type = NLA_STRING },
+	[TCA_KIND]		= { .type = NLA_NUL_STRING,
+				    .len = IFNAMSIZ - 1 },
 	[TCA_RATE]		= { .type = NLA_BINARY,
 				    .len = sizeof(struct tc_estimator) },
 	[TCA_STAB]		= { .type = NLA_NESTED },
-- 
2.20.1


From d044ecc1293973f1dba2683010bf99155466d3cf Mon Sep 17 00:00:00 2001
From: Navid Emamdoost <navid.emamdoost@gmail.com>
Date: Wed, 25 Sep 2019 14:05:09 -0500
Subject: [PATCH 09/32] nfp: flower: fix memory leak in
 nfp_flower_spawn_vnic_reprs

[ Upstream commit 8ce39eb5a67aee25d9f05b40b673c95b23502e3e ]

In nfp_flower_spawn_vnic_reprs in the loop if initialization or the
allocations fail memory is leaked. Appropriate releases are added.

Fixes: b94524529741 ("nfp: flower: add per repr private data for LAG offload")
Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/main.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c
index eb846133943b..5331e01f373e 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.c
@@ -400,6 +400,7 @@ nfp_flower_spawn_vnic_reprs(struct nfp_app *app,
 		repr_priv = kzalloc(sizeof(*repr_priv), GFP_KERNEL);
 		if (!repr_priv) {
 			err = -ENOMEM;
+			nfp_repr_free(repr);
 			goto err_reprs_clean;
 		}
 
@@ -413,6 +414,7 @@ nfp_flower_spawn_vnic_reprs(struct nfp_app *app,
 		port = nfp_port_alloc(app, port_type, repr);
 		if (IS_ERR(port)) {
 			err = PTR_ERR(port);
+			kfree(repr_priv);
 			nfp_repr_free(repr);
 			goto err_reprs_clean;
 		}
@@ -433,6 +435,7 @@ nfp_flower_spawn_vnic_reprs(struct nfp_app *app,
 		err = nfp_repr_init(app, repr,
 				    port_id, port, priv->nn->dp.netdev);
 		if (err) {
+			kfree(repr_priv);
 			nfp_port_free(port);
 			nfp_repr_free(repr);
 			goto err_reprs_clean;
-- 
2.20.1


From 9d3c1118d4b1fa4f321a1d3ebc81bd1ae9618a4f Mon Sep 17 00:00:00 2001
From: Navid Emamdoost <navid.emamdoost@gmail.com>
Date: Wed, 25 Sep 2019 13:24:02 -0500
Subject: [PATCH 10/32] nfp: flower: prevent memory leak in
 nfp_flower_spawn_phy_reprs

[ Upstream commit 8572cea1461a006bce1d06c0c4b0575869125fa4 ]

In nfp_flower_spawn_phy_reprs, in the for loop over eth_tbl if any of
intermediate allocations or initializations fail memory is leaked.
requiered releases are added.

Fixes: b94524529741 ("nfp: flower: add per repr private data for LAG offload")
Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/main.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c
index 5331e01f373e..acb02e1513f2 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.c
@@ -518,6 +518,7 @@ nfp_flower_spawn_phy_reprs(struct nfp_app *app, struct nfp_flower_priv *priv)
 		repr_priv = kzalloc(sizeof(*repr_priv), GFP_KERNEL);
 		if (!repr_priv) {
 			err = -ENOMEM;
+			nfp_repr_free(repr);
 			goto err_reprs_clean;
 		}
 
@@ -528,11 +529,13 @@ nfp_flower_spawn_phy_reprs(struct nfp_app *app, struct nfp_flower_priv *priv)
 		port = nfp_port_alloc(app, NFP_PORT_PHYS_PORT, repr);
 		if (IS_ERR(port)) {
 			err = PTR_ERR(port);
+			kfree(repr_priv);
 			nfp_repr_free(repr);
 			goto err_reprs_clean;
 		}
 		err = nfp_port_init_phy_port(app->pf, app, port, i);
 		if (err) {
+			kfree(repr_priv);
 			nfp_port_free(port);
 			nfp_repr_free(repr);
 			goto err_reprs_clean;
@@ -545,6 +548,7 @@ nfp_flower_spawn_phy_reprs(struct nfp_app *app, struct nfp_flower_priv *priv)
 		err = nfp_repr_init(app, repr,
 				    cmsg_port_id, port, priv->nn->dp.netdev);
 		if (err) {
+			kfree(repr_priv);
 			nfp_port_free(port);
 			nfp_repr_free(repr);
 			goto err_reprs_clean;
-- 
2.20.1


From f21bfb713b79247361e0fd48645f31e0b3ac009a Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Tue, 24 Sep 2019 19:11:52 +0800
Subject: [PATCH 11/32] openvswitch: change type of UPCALL_PID attribute to
 NLA_UNSPEC

[ Upstream commit ea8564c865299815095bebeb4b25bef474218e4c ]

userspace openvswitch patch "(dpif-linux: Implement the API
functions to allow multiple handler threads read upcall)"
changes its type from U32 to UNSPEC, but leave the kernel
unchanged

and after kernel 6e237d099fac "(netlink: Relax attr validation
for fixed length types)", this bug is exposed by the below
warning

	[   57.215841] netlink: 'ovs-vswitchd': attribute type 5 has an invalid length.

Fixes: 5cd667b0a456 ("openvswitch: Allow each vport to have an array of 'port_id's")
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/datapath.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 6747bc57b6fa..c29e9f766bd3 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -2245,7 +2245,7 @@ static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = {
 	[OVS_VPORT_ATTR_STATS] = { .len = sizeof(struct ovs_vport_stats) },
 	[OVS_VPORT_ATTR_PORT_NO] = { .type = NLA_U32 },
 	[OVS_VPORT_ATTR_TYPE] = { .type = NLA_U32 },
-	[OVS_VPORT_ATTR_UPCALL_PID] = { .type = NLA_U32 },
+	[OVS_VPORT_ATTR_UPCALL_PID] = { .type = NLA_UNSPEC },
 	[OVS_VPORT_ATTR_OPTIONS] = { .type = NLA_NESTED },
 	[OVS_VPORT_ATTR_IFINDEX] = { .type = NLA_U32 },
 	[OVS_VPORT_ATTR_NETNSID] = { .type = NLA_S32 },
-- 
2.20.1


From 4378abc7122222edb0f918159d406dd1bccaa94e Mon Sep 17 00:00:00 2001
From: Takeshi Misawa <jeliantsurux@gmail.com>
Date: Sun, 22 Sep 2019 16:45:31 +0900
Subject: [PATCH 12/32] ppp: Fix memory leak in ppp_write

[ Upstream commit 4c247de564f1ff614d11b3bb5313fb70d7b9598b ]

When ppp is closing, __ppp_xmit_process() failed to enqueue skb
and skb allocated in ppp_write() is leaked.

syzbot reported :
BUG: memory leak
unreferenced object 0xffff88812a17bc00 (size 224):
  comm "syz-executor673", pid 6952, jiffies 4294942888 (age 13.040s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<00000000d110fff9>] kmemleak_alloc_recursive include/linux/kmemleak.h:43 [inline]
    [<00000000d110fff9>] slab_post_alloc_hook mm/slab.h:522 [inline]
    [<00000000d110fff9>] slab_alloc_node mm/slab.c:3262 [inline]
    [<00000000d110fff9>] kmem_cache_alloc_node+0x163/0x2f0 mm/slab.c:3574
    [<000000002d616113>] __alloc_skb+0x6e/0x210 net/core/skbuff.c:197
    [<000000000167fc45>] alloc_skb include/linux/skbuff.h:1055 [inline]
    [<000000000167fc45>] ppp_write+0x48/0x120 drivers/net/ppp/ppp_generic.c:502
    [<000000009ab42c0b>] __vfs_write+0x43/0xa0 fs/read_write.c:494
    [<00000000086b2e22>] vfs_write fs/read_write.c:558 [inline]
    [<00000000086b2e22>] vfs_write+0xee/0x210 fs/read_write.c:542
    [<00000000a2b70ef9>] ksys_write+0x7c/0x130 fs/read_write.c:611
    [<00000000ce5e0fdd>] __do_sys_write fs/read_write.c:623 [inline]
    [<00000000ce5e0fdd>] __se_sys_write fs/read_write.c:620 [inline]
    [<00000000ce5e0fdd>] __x64_sys_write+0x1e/0x30 fs/read_write.c:620
    [<00000000d9d7b370>] do_syscall_64+0x76/0x1a0 arch/x86/entry/common.c:296
    [<0000000006e6d506>] entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fix this by freeing skb, if ppp is closing.

Fixes: 6d066734e9f0 ("ppp: avoid loop in xmit recursion detection code")
Reported-and-tested-by: syzbot+d9c8bf24e56416d7ce2c@syzkaller.appspotmail.com
Signed-off-by: Takeshi Misawa <jeliantsurux@gmail.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Tested-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/ppp_generic.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index a30e41a56085..9a1b006904a7 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -1415,6 +1415,8 @@ static void __ppp_xmit_process(struct ppp *ppp, struct sk_buff *skb)
 			netif_wake_queue(ppp->dev);
 		else
 			netif_stop_queue(ppp->dev);
+	} else {
+		kfree_skb(skb);
 	}
 	ppp_xmit_unlock(ppp);
 }
-- 
2.20.1


From d2312debd5de06a825ae1085220a5765147bb71e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 18 Sep 2019 08:05:39 -0700
Subject: [PATCH 13/32] sch_netem: fix a divide by zero in tabledist()

[ Upstream commit b41d936b5ecfdb3a4abc525ce6402a6c49cffddc ]

syzbot managed to crash the kernel in tabledist() loading
an empty distribution table.

	t = dist->table[rnd % dist->size];

Simply return an error when such load is attempted.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/sched/sch_netem.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index b17f2ed970e2..f5cb35e550f8 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -777,7 +777,7 @@ static int get_dist_table(struct Qdisc *sch, struct disttable **tbl,
 	struct disttable *d;
 	int i;
 
-	if (n > NETEM_DIST_MAX)
+	if (!n || n > NETEM_DIST_MAX)
 		return -EINVAL;
 
 	d = kvmalloc(sizeof(struct disttable) + n * sizeof(s16), GFP_KERNEL);
-- 
2.20.1


From bece58707e2ebeb10401bd5be4b4c63918f835af Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 17 Sep 2019 10:30:21 -0700
Subject: [PATCH 14/32] selftests: Update fib_tests to handle missing ping6

[ Upstream commit 0360894a05ed52be268e3c4d40b2df9d94975fa6 ]

Some distributions (e.g., debian buster) do not install ping6. Re-use
the hook in pmtu.sh to detect this and fallback to ping.

Fixes: a0e11da78f48 ("fib_tests: Add tests for metrics on routes")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 tools/testing/selftests/net/fib_tests.sh | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 0eca8fef2b9f..df7a55d94b75 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -16,6 +16,8 @@ PAUSE_ON_FAIL=no
 PAUSE=no
 IP="ip -netns ns1"
 
+which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping)
+
 log_test()
 {
 	local rc=$1
@@ -1068,7 +1070,7 @@ ipv6_route_metrics_test()
 	log_test $rc 0 "Multipath route with mtu metric"
 
 	$IP -6 ro add 2001:db8:104::/64 via 2001:db8:101::2 mtu 1300
-	run_cmd "ip netns exec ns1 ping6 -w1 -c1 -s 1500 2001:db8:104::1"
+	run_cmd "ip netns exec ns1 ${ping6} -w1 -c1 -s 1500 2001:db8:104::1"
 	log_test $? 0 "Using route with mtu metric"
 
 	run_cmd "$IP -6 ro add 2001:db8:114::/64 via  2001:db8:101::2  congctl lock foo"
-- 
2.20.1


From e8085e1b7a70c633fc9744e175f01a20accdbb6f Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Fri, 20 Sep 2019 18:18:26 +0200
Subject: [PATCH 15/32] skge: fix checksum byte order

[ Upstream commit 5aafeb74b5bb65b34cc87c7623f9fa163a34fa3b ]

Running old skge driver on PowerPC causes checksum errors
because hardware reported 1's complement checksum is in little-endian
byte order.

Reported-by: Benoit <benoit.sansoni@gmail.com>
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/skge.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c
index 35a92fd2cf39..59bbb5a8401c 100644
--- a/drivers/net/ethernet/marvell/skge.c
+++ b/drivers/net/ethernet/marvell/skge.c
@@ -3110,7 +3110,7 @@ static struct sk_buff *skge_rx_get(struct net_device *dev,
 	skb_put(skb, len);
 
 	if (dev->features & NETIF_F_RXCSUM) {
-		skb->csum = csum;
+		skb->csum = le16_to_cpu(csum);
 		skb->ip_summed = CHECKSUM_COMPLETE;
 	}
 
-- 
2.20.1


From efc727199e0432bd1d9e04a0b2d9518f6b5f46de Mon Sep 17 00:00:00 2001
From: "Kevin(Yudong) Yang" <yyd@google.com>
Date: Thu, 26 Sep 2019 10:30:05 -0400
Subject: [PATCH 16/32] tcp_bbr: fix quantization code to not raise cwnd if not
 probing bandwidth

[ Upstream commit 6b3656a60f2067738d1a423328199720806f0c44 ]

There was a bug in the previous logic that attempted to ensure gain cycling
gets inflight above BDP even for small BDPs. This code correctly raised and
lowered target inflight values during the gain cycle. And this code
correctly ensured that cwnd was raised when probing bandwidth. However, it
did not correspondingly ensure that cwnd was *not* raised in this way when
*not* probing for bandwidth. The result was that small-BDP flows that were
always cwnd-bound could go for many cycles with a fixed cwnd, and not probe
or yield bandwidth at all. This meant that multiple small-BDP flows could
fail to converge in their bandwidth allocations.

Fixes: 3c346b233c68 ("tcp_bbr: fix bw probing to raise in-flight data for very small BDPs")
Signed-off-by: Kevin(Yudong) Yang <yyd@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Priyaranjan Jha <priyarjha@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_bbr.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 56be7d27f208..00ade9c185ea 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -386,7 +386,7 @@ static u32 bbr_bdp(struct sock *sk, u32 bw, int gain)
  * which allows 2 outstanding 2-packet sequences, to try to keep pipe
  * full even with ACK-every-other-packet delayed ACKs.
  */
-static u32 bbr_quantization_budget(struct sock *sk, u32 cwnd, int gain)
+static u32 bbr_quantization_budget(struct sock *sk, u32 cwnd)
 {
 	struct bbr *bbr = inet_csk_ca(sk);
 
@@ -397,7 +397,7 @@ static u32 bbr_quantization_budget(struct sock *sk, u32 cwnd, int gain)
 	cwnd = (cwnd + 1) & ~1U;
 
 	/* Ensure gain cycling gets inflight above BDP even for small BDPs. */
-	if (bbr->mode == BBR_PROBE_BW && gain > BBR_UNIT)
+	if (bbr->mode == BBR_PROBE_BW && bbr->cycle_idx == 0)
 		cwnd += 2;
 
 	return cwnd;
@@ -409,7 +409,7 @@ static u32 bbr_inflight(struct sock *sk, u32 bw, int gain)
 	u32 inflight;
 
 	inflight = bbr_bdp(sk, bw, gain);
-	inflight = bbr_quantization_budget(sk, inflight, gain);
+	inflight = bbr_quantization_budget(sk, inflight);
 
 	return inflight;
 }
@@ -529,7 +529,7 @@ static void bbr_set_cwnd(struct sock *sk, const struct rate_sample *rs,
 	 * due to aggregation (of data and/or ACKs) visible in the ACK stream.
 	 */
 	target_cwnd += bbr_ack_aggregation_cwnd(sk);
-	target_cwnd = bbr_quantization_budget(sk, target_cwnd, gain);
+	target_cwnd = bbr_quantization_budget(sk, target_cwnd);
 
 	/* If we're below target cwnd, slow start cwnd toward target cwnd. */
 	if (bbr_full_bw_reached(sk))  /* only cut cwnd if we filled the pipe */
-- 
2.20.1


From dc32704c45f34fd3548885d4c42d8273a06dfd1b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Wed, 18 Sep 2019 14:17:38 +0200
Subject: [PATCH 17/32] usbnet: ignore endpoints with invalid wMaxPacketSize
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 8d3d7c2029c1b360f1a6b0a2fca470b57eb575c0 ]

Endpoints with zero wMaxPacketSize are not usable for transferring
data. Ignore such endpoints when looking for valid in, out and
status pipes, to make the drivers more robust against invalid and
meaningless descriptors.

The wMaxPacketSize of these endpoints are used for memory allocations
and as divisors in many usbnet minidrivers. Avoiding zero is therefore
critical.

Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/usb/usbnet.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 72514c46b478..07c00e378a5c 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -100,6 +100,11 @@ int usbnet_get_endpoints(struct usbnet *dev, struct usb_interface *intf)
 			int				intr = 0;
 
 			e = alt->endpoint + ep;
+
+			/* ignore endpoints which cannot transfer data */
+			if (!usb_endpoint_maxp(&e->desc))
+				continue;
+
 			switch (e->desc.bmAttributes) {
 			case USB_ENDPOINT_XFER_INT:
 				if (!usb_endpoint_dir_in(&e->desc))
-- 
2.20.1


From d1d19f79e68593913138dafb10c604a5af9e4ca6 Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.com>
Date: Thu, 19 Sep 2019 10:23:08 +0200
Subject: [PATCH 18/32] usbnet: sanity checking of packet sizes and device mtu

[ Upstream commit 280ceaed79f18db930c0cc8bb21f6493490bf29c ]

After a reset packet sizes and device mtu can change and need
to be reevaluated to calculate queue sizes.
Malicious devices can set this to zero and we divide by it.
Introduce sanity checking.

Reported-and-tested-by:  syzbot+6102c120be558c885f04@syzkaller.appspotmail.com
Signed-off-by: Oliver Neukum <oneukum@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/usbnet.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 07c00e378a5c..ef1d667b0108 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -344,6 +344,8 @@ void usbnet_update_max_qlen(struct usbnet *dev)
 {
 	enum usb_device_speed speed = dev->udev->speed;
 
+	if (!dev->rx_urb_size || !dev->hard_mtu)
+		goto insanity;
 	switch (speed) {
 	case USB_SPEED_HIGH:
 		dev->rx_qlen = MAX_QUEUE_MEMORY / dev->rx_urb_size;
@@ -360,6 +362,7 @@ void usbnet_update_max_qlen(struct usbnet *dev)
 		dev->tx_qlen = 5 * MAX_QUEUE_MEMORY / dev->hard_mtu;
 		break;
 	default:
+insanity:
 		dev->rx_qlen = dev->tx_qlen = 4;
 	}
 }
-- 
2.20.1


From 673cea242c5f9206bd2214c80f7b332fd47b7edf Mon Sep 17 00:00:00 2001
From: Hans Andersson <hans.andersson@cellavision.se>
Date: Thu, 26 Sep 2019 09:54:37 +0200
Subject: [PATCH 19/32] net: phy: micrel: add Asym Pause workaround for KSZ9021

[ Upstream commit 407d8098cb1ab338199f4753162799a488d87d23 ]

The Micrel KSZ9031 PHY may fail to establish a link when the Asymmetric
Pause capability is set. This issue is described in a Silicon Errata
(DS80000691D or DS80000692D), which advises to always disable the
capability.

Micrel KSZ9021 has no errata, but has the same issue with Asymmetric Pause.
This patch apply the same workaround as the one for KSZ9031.

Fixes: 3aed3e2a143c ("net: phy: micrel: add Asym Pause workaround")
Signed-off-by: Hans Andersson <hans.andersson@cellavision.se>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/micrel.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 3c8186f269f9..2fea5541c35a 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -763,6 +763,8 @@ static int ksz9031_get_features(struct phy_device *phydev)
 	 * Whenever the device's Asymmetric Pause capability is set to 1,
 	 * link-up may fail after a link-up to link-down transition.
 	 *
+	 * The Errata Sheet is for ksz9031, but ksz9021 has the same issue
+	 *
 	 * Workaround:
 	 * Do not enable the Asymmetric Pause capability bit.
 	 */
@@ -1076,6 +1078,7 @@ static struct phy_driver ksphy_driver[] = {
 	/* PHY_GBIT_FEATURES */
 	.driver_data	= &ksz9021_type,
 	.probe		= kszphy_probe,
+	.get_features	= ksz9031_get_features,
 	.config_init	= ksz9021_config_init,
 	.ack_interrupt	= kszphy_ack_interrupt,
 	.config_intr	= kszphy_config_intr,
-- 
2.20.1


From d30bda82e59fe9a23d142bea852ca451fb90b77a Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Mon, 23 Sep 2019 22:04:58 -0700
Subject: [PATCH 20/32] net/sched: cbs: Fix not adding cbs instance to list

[ Upstream commit 3e8b9bfa110896f95d602d8c98d5f9d67e41d78c ]

When removing a cbs instance when offloading is enabled, the crash
below can be observed.

The problem happens because that when offloading is enabled, the cbs
instance is not added to the list.

Also, the current code doesn't handle correctly the case when offload
is disabled without removing the qdisc: if the link speed changes the
credit calculations will be wrong. When we create the cbs instance
with offloading enabled, it's not added to the notification list, when
later we disable offloading, it's not in the list, so link speed
changes will not affect it.

The solution for both issues is the same, add the cbs instance being
created unconditionally to the global list, even if the link state
notification isn't useful "right now".

Crash log:

[518758.189866] BUG: kernel NULL pointer dereference, address: 0000000000000000
[518758.189870] #PF: supervisor read access in kernel mode
[518758.189871] #PF: error_code(0x0000) - not-present page
[518758.189872] PGD 0 P4D 0
[518758.189874] Oops: 0000 [#1] SMP PTI
[518758.189876] CPU: 3 PID: 4825 Comm: tc Not tainted 5.2.9 #1
[518758.189877] Hardware name: Gigabyte Technology Co., Ltd. Z390 AORUS ULTRA/Z390 AORUS ULTRA-CF, BIOS F7 03/14/2019
[518758.189881] RIP: 0010:__list_del_entry_valid+0x29/0xa0
[518758.189883] Code: 90 48 b8 00 01 00 00 00 00 ad de 55 48 8b 17 4c 8b 47 08 48 89 e5 48 39 c2 74 27 48 b8 00 02 00 00 00 00 ad de 49 39 c0 74 2d <49> 8b 30 48 39 fe 75 3d 48 8b 52 08 48 39 f2 75 4c b8 01 00 00 00
[518758.189885] RSP: 0018:ffffa27e43903990 EFLAGS: 00010207
[518758.189887] RAX: dead000000000200 RBX: ffff8bce69f0f000 RCX: 0000000000000000
[518758.189888] RDX: 0000000000000000 RSI: ffff8bce69f0f064 RDI: ffff8bce69f0f1e0
[518758.189890] RBP: ffffa27e43903990 R08: 0000000000000000 R09: ffff8bce69e788c0
[518758.189891] R10: ffff8bce62acd400 R11: 00000000000003cb R12: ffff8bce69e78000
[518758.189892] R13: ffff8bce69f0f140 R14: 0000000000000000 R15: 0000000000000000
[518758.189894] FS:  00007fa1572c8f80(0000) GS:ffff8bce6e0c0000(0000) knlGS:0000000000000000
[518758.189895] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[518758.189896] CR2: 0000000000000000 CR3: 000000040a398006 CR4: 00000000003606e0
[518758.189898] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[518758.189899] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[518758.189900] Call Trace:
[518758.189904]  cbs_destroy+0x32/0xa0 [sch_cbs]
[518758.189906]  qdisc_destroy+0x45/0x120
[518758.189907]  qdisc_put+0x25/0x30
[518758.189908]  qdisc_graft+0x2c1/0x450
[518758.189910]  tc_get_qdisc+0x1c8/0x310
[518758.189912]  ? get_page_from_freelist+0x91a/0xcb0
[518758.189914]  rtnetlink_rcv_msg+0x293/0x360
[518758.189916]  ? kmem_cache_alloc_node_trace+0x178/0x260
[518758.189918]  ? __kmalloc_node_track_caller+0x38/0x50
[518758.189920]  ? rtnl_calcit.isra.0+0xf0/0xf0
[518758.189922]  netlink_rcv_skb+0x48/0x110
[518758.189923]  rtnetlink_rcv+0x10/0x20
[518758.189925]  netlink_unicast+0x15b/0x1d0
[518758.189926]  netlink_sendmsg+0x1ea/0x380
[518758.189929]  sock_sendmsg+0x2f/0x40
[518758.189930]  ___sys_sendmsg+0x295/0x2f0
[518758.189932]  ? ___sys_recvmsg+0x151/0x1e0
[518758.189933]  ? do_wp_page+0x7e/0x450
[518758.189935]  __sys_sendmsg+0x48/0x80
[518758.189937]  __x64_sys_sendmsg+0x1a/0x20
[518758.189939]  do_syscall_64+0x53/0x1f0
[518758.189941]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[518758.189942] RIP: 0033:0x7fa15755169a
[518758.189944] Code: 48 c7 c0 ff ff ff ff eb be 0f 1f 80 00 00 00 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 18 b8 2e 00 00 00 c5 fc 77 0f 05 <48> 3d 00 f0 ff ff 77 5e c3 0f 1f 44 00 00 48 83 ec 28 89 54 24 1c
[518758.189946] RSP: 002b:00007ffda58b60b8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
[518758.189948] RAX: ffffffffffffffda RBX: 000055e4b836d9a0 RCX: 00007fa15755169a
[518758.189949] RDX: 0000000000000000 RSI: 00007ffda58b6128 RDI: 0000000000000003
[518758.189951] RBP: 00007ffda58b6190 R08: 0000000000000001 R09: 000055e4b9d848a0
[518758.189952] R10: 0000000000000000 R11: 0000000000000246 R12: 000000005d654b49
[518758.189953] R13: 0000000000000000 R14: 00007ffda58b6230 R15: 00007ffda58b6210
[518758.189955] Modules linked in: sch_cbs sch_etf sch_mqprio netlink_diag unix_diag e1000e igb intel_pch_thermal thermal video backlight pcc_cpufreq
[518758.189960] CR2: 0000000000000000
[518758.189961] ---[ end trace 6a13f7aaf5376019 ]---
[518758.189963] RIP: 0010:__list_del_entry_valid+0x29/0xa0
[518758.189964] Code: 90 48 b8 00 01 00 00 00 00 ad de 55 48 8b 17 4c 8b 47 08 48 89 e5 48 39 c2 74 27 48 b8 00 02 00 00 00 00 ad de 49 39 c0 74 2d <49> 8b 30 48 39 fe 75 3d 48 8b 52 08 48 39 f2 75 4c b8 01 00 00 00
[518758.189967] RSP: 0018:ffffa27e43903990 EFLAGS: 00010207
[518758.189968] RAX: dead000000000200 RBX: ffff8bce69f0f000 RCX: 0000000000000000
[518758.189969] RDX: 0000000000000000 RSI: ffff8bce69f0f064 RDI: ffff8bce69f0f1e0
[518758.189971] RBP: ffffa27e43903990 R08: 0000000000000000 R09: ffff8bce69e788c0
[518758.189972] R10: ffff8bce62acd400 R11: 00000000000003cb R12: ffff8bce69e78000
[518758.189973] R13: ffff8bce69f0f140 R14: 0000000000000000 R15: 0000000000000000
[518758.189975] FS:  00007fa1572c8f80(0000) GS:ffff8bce6e0c0000(0000) knlGS:0000000000000000
[518758.189976] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[518758.189977] CR2: 0000000000000000 CR3: 000000040a398006 CR4: 00000000003606e0
[518758.189979] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[518758.189980] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400

Fixes: e0a7683d30e9 ("net/sched: cbs: fix port_rate miscalculation")
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_cbs.c | 30 +++++++++++++-----------------
 1 file changed, 13 insertions(+), 17 deletions(-)

diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c
index 810645b5c086..4a403d35438f 100644
--- a/net/sched/sch_cbs.c
+++ b/net/sched/sch_cbs.c
@@ -392,7 +392,6 @@ static int cbs_init(struct Qdisc *sch, struct nlattr *opt,
 {
 	struct cbs_sched_data *q = qdisc_priv(sch);
 	struct net_device *dev = qdisc_dev(sch);
-	int err;
 
 	if (!opt) {
 		NL_SET_ERR_MSG(extack, "Missing CBS qdisc options  which are mandatory");
@@ -404,6 +403,10 @@ static int cbs_init(struct Qdisc *sch, struct nlattr *opt,
 	if (!q->qdisc)
 		return -ENOMEM;
 
+	spin_lock(&cbs_list_lock);
+	list_add(&q->cbs_list, &cbs_list);
+	spin_unlock(&cbs_list_lock);
+
 	qdisc_hash_add(q->qdisc, false);
 
 	q->queue = sch->dev_queue - netdev_get_tx_queue(dev, 0);
@@ -413,17 +416,7 @@ static int cbs_init(struct Qdisc *sch, struct nlattr *opt,
 
 	qdisc_watchdog_init(&q->watchdog, sch);
 
-	err = cbs_change(sch, opt, extack);
-	if (err)
-		return err;
-
-	if (!q->offload) {
-		spin_lock(&cbs_list_lock);
-		list_add(&q->cbs_list, &cbs_list);
-		spin_unlock(&cbs_list_lock);
-	}
-
-	return 0;
+	return cbs_change(sch, opt, extack);
 }
 
 static void cbs_destroy(struct Qdisc *sch)
@@ -431,15 +424,18 @@ static void cbs_destroy(struct Qdisc *sch)
 	struct cbs_sched_data *q = qdisc_priv(sch);
 	struct net_device *dev = qdisc_dev(sch);
 
-	spin_lock(&cbs_list_lock);
-	list_del(&q->cbs_list);
-	spin_unlock(&cbs_list_lock);
+	/* Nothing to do if we couldn't create the underlying qdisc */
+	if (!q->qdisc)
+		return;
 
 	qdisc_watchdog_cancel(&q->watchdog);
 	cbs_disable_offload(dev, q);
 
-	if (q->qdisc)
-		qdisc_put(q->qdisc);
+	spin_lock(&cbs_list_lock);
+	list_del(&q->cbs_list);
+	spin_unlock(&cbs_list_lock);
+
+	qdisc_put(q->qdisc);
 }
 
 static int cbs_dump(struct Qdisc *sch, struct sk_buff *skb)
-- 
2.20.1


From c4a5560b116c3bf43cba42dc0371ad0a054c940e Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 17 Sep 2019 10:39:49 -0700
Subject: [PATCH 21/32] ipv4: Revert removal of rt_uses_gateway

[ Upstream commit 77d5bc7e6a6cf8bbeca31aab7f0c5449a5eee762 ]

Julian noted that rt_uses_gateway has a more subtle use than 'is gateway
set':
    https://lore.kernel.org/netdev/alpine.LFD.2.21.1909151104060.2546@ja.home.ssi.bg/

Revert that part of the commit referenced in the Fixes tag.

Currently, there are no u8 holes in 'struct rtable'. There is a 4-byte hole
in the second cacheline which contains the gateway declaration. So move
rt_gw_family down to the gateway declarations since they are always used
together, and then re-use that u8 for rt_uses_gateway. End result is that
rtable size is unchanged.

Fixes: 1550c171935d ("ipv4: Prepare rtable for IPv6 gateway")
Reported-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/infiniband/core/addr.c  |  2 +-
 include/net/route.h             |  3 ++-
 net/ipv4/inet_connection_sock.c |  4 ++--
 net/ipv4/ip_forward.c           |  2 +-
 net/ipv4/ip_output.c            |  2 +-
 net/ipv4/route.c                | 34 +++++++++++++++++++--------------
 net/ipv4/xfrm4_policy.c         |  1 +
 7 files changed, 28 insertions(+), 20 deletions(-)

diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 9b76a8fcdd24..bf539c34ccd3 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -352,7 +352,7 @@ static bool has_gateway(const struct dst_entry *dst, sa_family_t family)
 
 	if (family == AF_INET) {
 		rt = container_of(dst, struct rtable, dst);
-		return rt->rt_gw_family == AF_INET;
+		return rt->rt_uses_gateway;
 	}
 
 	rt6 = container_of(dst, struct rt6_info, dst);
diff --git a/include/net/route.h b/include/net/route.h
index 55ff71ffb796..2b34a3a4386f 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -53,10 +53,11 @@ struct rtable {
 	unsigned int		rt_flags;
 	__u16			rt_type;
 	__u8			rt_is_input;
-	u8			rt_gw_family;
+	__u8			rt_uses_gateway;
 
 	int			rt_iif;
 
+	u8			rt_gw_family;
 	/* Info on neighbour */
 	union {
 		__be32		rt_gw4;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 7fd6db3fe366..e4fa9e5833e4 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -560,7 +560,7 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk,
 	rt = ip_route_output_flow(net, fl4, sk);
 	if (IS_ERR(rt))
 		goto no_route;
-	if (opt && opt->opt.is_strictroute && rt->rt_gw_family)
+	if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway)
 		goto route_err;
 	rcu_read_unlock();
 	return &rt->dst;
@@ -598,7 +598,7 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
 	rt = ip_route_output_flow(net, fl4, sk);
 	if (IS_ERR(rt))
 		goto no_route;
-	if (opt && opt->opt.is_strictroute && rt->rt_gw_family)
+	if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway)
 		goto route_err;
 	return &rt->dst;
 
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 06f6f280b9ff..00ec819f949b 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -123,7 +123,7 @@ int ip_forward(struct sk_buff *skb)
 
 	rt = skb_rtable(skb);
 
-	if (opt->is_strictroute && rt->rt_gw_family)
+	if (opt->is_strictroute && rt->rt_uses_gateway)
 		goto sr_failed;
 
 	IPCB(skb)->flags |= IPSKB_FORWARDED;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 8c2ec35b6512..b6f3a9f0b8be 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -482,7 +482,7 @@ int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
 	skb_dst_set_noref(skb, &rt->dst);
 
 packet_routed:
-	if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_gw_family)
+	if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_uses_gateway)
 		goto no_route;
 
 	/* OK, we know where to send it, allocate and build IP header. */
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 8ea0735a6754..f6b7b11835ee 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -634,6 +634,7 @@ static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnh
 
 	if (fnhe->fnhe_gw) {
 		rt->rt_flags |= RTCF_REDIRECTED;
+		rt->rt_uses_gateway = 1;
 		rt->rt_gw_family = AF_INET;
 		rt->rt_gw4 = fnhe->fnhe_gw;
 	}
@@ -1312,7 +1313,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst)
 	mtu = READ_ONCE(dst->dev->mtu);
 
 	if (unlikely(ip_mtu_locked(dst))) {
-		if (rt->rt_gw_family && mtu > 576)
+		if (rt->rt_uses_gateway && mtu > 576)
 			mtu = 576;
 	}
 
@@ -1569,6 +1570,7 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
 		struct fib_nh_common *nhc = FIB_RES_NHC(*res);
 
 		if (nhc->nhc_gw_family && nhc->nhc_scope == RT_SCOPE_LINK) {
+			rt->rt_uses_gateway = 1;
 			rt->rt_gw_family = nhc->nhc_gw_family;
 			/* only INET and INET6 are supported */
 			if (likely(nhc->nhc_gw_family == AF_INET))
@@ -1634,6 +1636,7 @@ struct rtable *rt_dst_alloc(struct net_device *dev,
 		rt->rt_iif = 0;
 		rt->rt_pmtu = 0;
 		rt->rt_mtu_locked = 0;
+		rt->rt_uses_gateway = 0;
 		rt->rt_gw_family = 0;
 		rt->rt_gw4 = 0;
 		INIT_LIST_HEAD(&rt->rt_uncached);
@@ -2664,6 +2667,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
 		rt->rt_genid = rt_genid_ipv4(net);
 		rt->rt_flags = ort->rt_flags;
 		rt->rt_type = ort->rt_type;
+		rt->rt_uses_gateway = ort->rt_uses_gateway;
 		rt->rt_gw_family = ort->rt_gw_family;
 		if (rt->rt_gw_family == AF_INET)
 			rt->rt_gw4 = ort->rt_gw4;
@@ -2747,21 +2751,23 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src,
 		if (nla_put_in_addr(skb, RTA_PREFSRC, fl4->saddr))
 			goto nla_put_failure;
 	}
-	if (rt->rt_gw_family == AF_INET &&
-	    nla_put_in_addr(skb, RTA_GATEWAY, rt->rt_gw4)) {
-		goto nla_put_failure;
-	} else if (rt->rt_gw_family == AF_INET6) {
-		int alen = sizeof(struct in6_addr);
-		struct nlattr *nla;
-		struct rtvia *via;
-
-		nla = nla_reserve(skb, RTA_VIA, alen + 2);
-		if (!nla)
+	if (rt->rt_uses_gateway) {
+		if (rt->rt_gw_family == AF_INET &&
+		    nla_put_in_addr(skb, RTA_GATEWAY, rt->rt_gw4)) {
 			goto nla_put_failure;
+		} else if (rt->rt_gw_family == AF_INET6) {
+			int alen = sizeof(struct in6_addr);
+			struct nlattr *nla;
+			struct rtvia *via;
 
-		via = nla_data(nla);
-		via->rtvia_family = AF_INET6;
-		memcpy(via->rtvia_addr, &rt->rt_gw6, alen);
+			nla = nla_reserve(skb, RTA_VIA, alen + 2);
+			if (!nla)
+				goto nla_put_failure;
+
+			via = nla_data(nla);
+			via->rtvia_family = AF_INET6;
+			memcpy(via->rtvia_addr, &rt->rt_gw6, alen);
+		}
 	}
 
 	expires = rt->dst.expires;
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index cdef8f9a3b01..35b84b52b702 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -85,6 +85,7 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
 	xdst->u.rt.rt_flags = rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST |
 					      RTCF_LOCAL);
 	xdst->u.rt.rt_type = rt->rt_type;
+	xdst->u.rt.rt_uses_gateway = rt->rt_uses_gateway;
 	xdst->u.rt.rt_gw_family = rt->rt_gw_family;
 	if (rt->rt_gw_family == AF_INET)
 		xdst->u.rt.rt_gw4 = rt->rt_gw4;
-- 
2.20.1


From 88195ca533bdc35c02f61e84833da284f50d6aed Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Wed, 18 Sep 2019 18:44:43 -0700
Subject: [PATCH 22/32] net_sched: add policy validation for action attributes

[ Upstream commit 199ce850ce112315cfc68d42b694bcaa27b097b7 ]

Similar to commit 8b4c3cdd9dd8
("net: sched: Add policy validation for tc attributes"), we need
to add proper policy validation for TC action attributes too.

Cc: David Ahern <dsahern@gmail.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/sched/act_api.c | 34 ++++++++++++++++++----------------
 1 file changed, 18 insertions(+), 16 deletions(-)

diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 4e5d2e9ace5d..061e0d047f4f 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -828,6 +828,15 @@ static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb)
 	return c;
 }
 
+static const struct nla_policy tcf_action_policy[TCA_ACT_MAX + 1] = {
+	[TCA_ACT_KIND]		= { .type = NLA_NUL_STRING,
+				    .len = IFNAMSIZ - 1 },
+	[TCA_ACT_INDEX]		= { .type = NLA_U32 },
+	[TCA_ACT_COOKIE]	= { .type = NLA_BINARY,
+				    .len = TC_COOKIE_MAX_SIZE },
+	[TCA_ACT_OPTIONS]	= { .type = NLA_NESTED },
+};
+
 struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 				    struct nlattr *nla, struct nlattr *est,
 				    char *name, int ovr, int bind,
@@ -843,8 +852,8 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 	int err;
 
 	if (name == NULL) {
-		err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla, NULL,
-						  extack);
+		err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla,
+						  tcf_action_policy, extack);
 		if (err < 0)
 			goto err_out;
 		err = -EINVAL;
@@ -853,18 +862,9 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 			NL_SET_ERR_MSG(extack, "TC action kind must be specified");
 			goto err_out;
 		}
-		if (nla_strlcpy(act_name, kind, IFNAMSIZ) >= IFNAMSIZ) {
-			NL_SET_ERR_MSG(extack, "TC action name too long");
-			goto err_out;
-		}
-		if (tb[TCA_ACT_COOKIE]) {
-			int cklen = nla_len(tb[TCA_ACT_COOKIE]);
-
-			if (cklen > TC_COOKIE_MAX_SIZE) {
-				NL_SET_ERR_MSG(extack, "TC cookie size above the maximum");
-				goto err_out;
-			}
+		nla_strlcpy(act_name, kind, IFNAMSIZ);
 
+		if (tb[TCA_ACT_COOKIE]) {
 			cookie = nla_memdup_cookie(tb);
 			if (!cookie) {
 				NL_SET_ERR_MSG(extack, "No memory to generate TC cookie");
@@ -1095,7 +1095,8 @@ static struct tc_action *tcf_action_get_1(struct net *net, struct nlattr *nla,
 	int index;
 	int err;
 
-	err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla, NULL, extack);
+	err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla,
+					  tcf_action_policy, extack);
 	if (err < 0)
 		goto err_out;
 
@@ -1149,7 +1150,8 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
 
 	b = skb_tail_pointer(skb);
 
-	err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla, NULL, extack);
+	err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla,
+					  tcf_action_policy, extack);
 	if (err < 0)
 		goto err_out;
 
@@ -1437,7 +1439,7 @@ static struct nlattr *find_dump_kind(struct nlattr **nla)
 
 	if (tb[1] == NULL)
 		return NULL;
-	if (nla_parse_nested_deprecated(tb2, TCA_ACT_MAX, tb[1], NULL, NULL) < 0)
+	if (nla_parse_nested_deprecated(tb2, TCA_ACT_MAX, tb[1], tcf_action_policy, NULL) < 0)
 		return NULL;
 	kind = tb2[TCA_ACT_KIND];
 
-- 
2.20.1


From ace4b5310b92861aed35e8026652c9ad3f7f420e Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 25 Sep 2019 07:53:19 -0700
Subject: [PATCH 23/32] vrf: Do not attempt to create IPv6 mcast rule if IPv6
 is disabled

[ Upstream commit dac91170f8e9c73784af5fad6225e954b795601c ]

A user reported that vrf create fails when IPv6 is disabled at boot using
'ipv6.disable=1':
   https://bugzilla.kernel.org/show_bug.cgi?id=204903

The failure is adding fib rules at create time. Add RTNL_FAMILY_IP6MR to
the check in vrf_fib_rule if ipv6_mod_enabled is disabled.

Fixes: e4a38c0c4b27 ("ipv6: add vrf table handling code for ipv6 mcast")
Signed-off-by: David Ahern <dsahern@gmail.com>
Cc: Patrick Ruddy <pruddy@vyatta.att-mail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 97fb0cb1b97a..1a22165afb39 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -1153,7 +1153,8 @@ static int vrf_fib_rule(const struct net_device *dev, __u8 family, bool add_it)
 	struct sk_buff *skb;
 	int err;
 
-	if (family == AF_INET6 && !ipv6_mod_enabled())
+	if ((family == AF_INET6 || family == RTNL_FAMILY_IP6MR) &&
+	    !ipv6_mod_enabled())
 		return 0;
 
 	skb = nlmsg_new(vrf_fib_rule_nl_size(), GFP_KERNEL);
-- 
2.20.1


From ce2e6af47c431acbcc5e9a92461be5c66c6c09f4 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Wed, 11 Sep 2019 07:50:13 -0700
Subject: [PATCH 24/32] net/mlx5e: Fix traffic duplication in ethtool steering

[ Upstream commit d22fcc806b84b9818de08b32e494f3c05dd236c7 ]

Before this patch, when adding multiple ethtool steering rules with
identical classification, the driver used to append the new destination
to the already existing hw rule, which caused the hw to forward the
traffic to all destinations (rx queues).

Here we avoid this by setting the "no append" mlx5 fs core flag when
adding a new ethtool rule.

Fixes: 6dc6071cfcde ("net/mlx5e: Add ethtool flow steering support")
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index 4421c10f58ae..baed9e93794f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -397,10 +397,10 @@ add_ethtool_flow_rule(struct mlx5e_priv *priv,
 		      struct mlx5_flow_table *ft,
 		      struct ethtool_rx_flow_spec *fs)
 {
+	struct mlx5_flow_act flow_act = { .flags = FLOW_ACT_NO_APPEND };
 	struct mlx5_flow_destination *dst = NULL;
-	struct mlx5_flow_act flow_act = {0};
-	struct mlx5_flow_spec *spec;
 	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_spec *spec;
 	int err = 0;
 
 	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
-- 
2.20.1


From 2f100865dc866d4702da5c725f527c4e1853140e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 18 Sep 2019 12:57:04 -0700
Subject: [PATCH 25/32] net: sched: fix possible crash in tcf_action_destroy()

[ Upstream commit 3d66b89c30f9220a72e92847768fc8ba4d027d88 ]

If the allocation done in tcf_exts_init() failed,
we end up with a NULL pointer in exts->actions.

kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] PREEMPT SMP KASAN
CPU: 1 PID: 8198 Comm: syz-executor.3 Not tainted 5.3.0-rc8+ #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:tcf_action_destroy+0x71/0x160 net/sched/act_api.c:705
Code: c3 08 44 89 ee e8 4f cb bb fb 41 83 fd 20 0f 84 c9 00 00 00 e8 c0 c9 bb fb 48 89 d8 48 b9 00 00 00 00 00 fc ff df 48 c1 e8 03 <80> 3c 08 00 0f 85 c0 00 00 00 4c 8b 33 4d 85 f6 0f 84 9d 00 00 00
RSP: 0018:ffff888096e16ff0 EFLAGS: 00010246
RAX: 0000000000000000 RBX: 0000000000000000 RCX: dffffc0000000000
RDX: 0000000000040000 RSI: ffffffff85b6ab30 RDI: 0000000000000000
RBP: ffff888096e17020 R08: ffff8880993f6140 R09: fffffbfff11cae67
R10: fffffbfff11cae66 R11: ffffffff88e57333 R12: 0000000000000000
R13: 0000000000000000 R14: ffff888096e177a0 R15: 0000000000000001
FS:  00007f62bc84a700(0000) GS:ffff8880ae900000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000758040 CR3: 0000000088b64000 CR4: 00000000001426e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 tcf_exts_destroy+0x38/0xb0 net/sched/cls_api.c:3030
 tcindex_set_parms+0xf7f/0x1e50 net/sched/cls_tcindex.c:488
 tcindex_change+0x230/0x318 net/sched/cls_tcindex.c:519
 tc_new_tfilter+0xa4b/0x1c70 net/sched/cls_api.c:2152
 rtnetlink_rcv_msg+0x838/0xb00 net/core/rtnetlink.c:5214
 netlink_rcv_skb+0x177/0x450 net/netlink/af_netlink.c:2477
 rtnetlink_rcv+0x1d/0x30 net/core/rtnetlink.c:5241
 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
 netlink_unicast+0x531/0x710 net/netlink/af_netlink.c:1328
 netlink_sendmsg+0x8a5/0xd60 net/netlink/af_netlink.c:1917
 sock_sendmsg_nosec net/socket.c:637 [inline]
 sock_sendmsg+0xd7/0x130 net/socket.c:657
 ___sys_sendmsg+0x3e2/0x920 net/socket.c:2311
 __sys_sendmmsg+0x1bf/0x4d0 net/socket.c:2413
 __do_sys_sendmmsg net/socket.c:2442 [inline]

Fixes: 90b73b77d08e ("net: sched: change action API to use array of pointers to actions")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Vlad Buslov <vladbu@mellanox.com>
Cc: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index b67c456f26aa..526cb48e7b8a 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -3031,8 +3031,10 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb)
 void tcf_exts_destroy(struct tcf_exts *exts)
 {
 #ifdef CONFIG_NET_CLS_ACT
-	tcf_action_destroy(exts->actions, TCA_ACT_UNBIND);
-	kfree(exts->actions);
+	if (exts->actions) {
+		tcf_action_destroy(exts->actions, TCA_ACT_UNBIND);
+		kfree(exts->actions);
+	}
 	exts->nr_actions = 0;
 #endif
 }
-- 
2.20.1


From c03f8c660550f87a5a446b699129694d1bdd21aa Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 26 Sep 2019 15:42:51 -0700
Subject: [PATCH 26/32] tcp: better handle TCP_USER_TIMEOUT in SYN_SENT state

[ Upstream commit a66b10c05ee2d744189e9a2130394b070883d289 ]

Yuchung Cheng and Marek Majkowski independently reported a weird
behavior of TCP_USER_TIMEOUT option when used at connect() time.

When the TCP_USER_TIMEOUT is reached, tcp_write_timeout()
believes the flow should live, and the following condition
in tcp_clamp_rto_to_user_timeout() programs one jiffie timers :

    remaining = icsk->icsk_user_timeout - elapsed;
    if (remaining <= 0)
        return 1; /* user timeout has passed; fire ASAP */

This silly situation ends when the max syn rtx count is reached.

This patch makes sure we honor both TCP_SYNCNT and TCP_USER_TIMEOUT,
avoiding these spurious SYN packets.

Fixes: b701a99e431d ("tcp: Add tcp_clamp_rto_to_user_timeout() helper to improve accuracy")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Yuchung Cheng <ycheng@google.com>
Reported-by: Marek Majkowski <marek@cloudflare.com>
Cc: Jon Maxwell <jmaxwell37@gmail.com>
Link: https://marc.info/?l=linux-netdev&m=156940118307949&w=2
Acked-by: Jon Maxwell <jmaxwell37@gmail.com>
Tested-by: Marek Majkowski <marek@cloudflare.com>
Signed-off-by: Marek Majkowski <marek@cloudflare.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_timer.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index c801cd37cc2a..3e8b38c73d8c 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -210,7 +210,7 @@ static int tcp_write_timeout(struct sock *sk)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct net *net = sock_net(sk);
-	bool expired, do_reset;
+	bool expired = false, do_reset;
 	int retry_until;
 
 	if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
@@ -242,9 +242,10 @@ static int tcp_write_timeout(struct sock *sk)
 			if (tcp_out_of_resources(sk, do_reset))
 				return 1;
 		}
+	}
+	if (!expired)
 		expired = retransmits_timed_out(sk, retry_until,
 						icsk->icsk_user_timeout);
-	}
 	tcp_fastopen_active_detect_blackhole(sk, expired);
 
 	if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RTO_CB_FLAG))
-- 
2.20.1


From 89f513c4f1d956a5bfa909aa13c5947c66b0d907 Mon Sep 17 00:00:00 2001
From: Bodong Wang <bodong@mellanox.com>
Date: Mon, 26 Aug 2019 16:34:12 -0500
Subject: [PATCH 27/32] net/mlx5: Add device ID of upcoming BlueField-2

[ Upstream commit d19a79ee38c8fda6d297e4227e80db8bf51c71a6 ]

Add the device ID of upcoming BlueField-2 integrated ConnectX-6 Dx
network controller. Its VFs will be using the generic VF device ID:
0x101e "ConnectX Family mlx5Gen Virtual Function".

Fixes: 2e9d3e83ab82 ("net/mlx5: Update the list of the PCI supported devices")
Signed-off-by: Bodong Wang <bodong@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 23d53163ce15..41a8e44cc09c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1525,6 +1525,7 @@ static const struct pci_device_id mlx5_core_pci_table[] = {
 	{ PCI_VDEVICE(MELLANOX, 0x101e), MLX5_PCI_DEV_IS_VF},	/* ConnectX Family mlx5Gen Virtual Function */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d2) },			/* BlueField integrated ConnectX-5 network controller */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d3), MLX5_PCI_DEV_IS_VF},	/* BlueField integrated ConnectX-5 network controller VF */
+	{ PCI_VDEVICE(MELLANOX, 0xa2d6) },			/* BlueField-2 integrated ConnectX-6 Dx network controller */
 	{ 0, }
 };
 
-- 
2.20.1


From 81013834cb34f1f1343361c4cff1514cfc856e9a Mon Sep 17 00:00:00 2001
From: Ori Nimron <orinimron123@gmail.com>
Date: Fri, 20 Sep 2019 09:35:45 +0200
Subject: [PATCH 28/32] mISDN: enforce CAP_NET_RAW for raw sockets

[ Upstream commit b91ee4aa2a2199ba4d4650706c272985a5a32d80 ]

When creating a raw AF_ISDN socket, CAP_NET_RAW needs to be checked
first.

Signed-off-by: Ori Nimron <orinimron123@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/mISDN/socket.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c
index c6ba37df4b9d..dff4132b3702 100644
--- a/drivers/isdn/mISDN/socket.c
+++ b/drivers/isdn/mISDN/socket.c
@@ -754,6 +754,8 @@ base_sock_create(struct net *net, struct socket *sock, int protocol, int kern)
 
 	if (sock->type != SOCK_RAW)
 		return -ESOCKTNOSUPPORT;
+	if (!capable(CAP_NET_RAW))
+		return -EPERM;
 
 	sk = sk_alloc(net, PF_ISDN, GFP_KERNEL, &mISDN_proto, kern);
 	if (!sk)
-- 
2.20.1


From 0b279adc316b9d58c3d2e45179a770400cbb6d5c Mon Sep 17 00:00:00 2001
From: Ori Nimron <orinimron123@gmail.com>
Date: Fri, 20 Sep 2019 09:35:46 +0200
Subject: [PATCH 29/32] appletalk: enforce CAP_NET_RAW for raw sockets

[ Upstream commit 6cc03e8aa36c51f3b26a0d21a3c4ce2809c842ac ]

When creating a raw AF_APPLETALK socket, CAP_NET_RAW needs to be checked
first.

Signed-off-by: Ori Nimron <orinimron123@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/appletalk/ddp.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index a8cb6b2e20c1..5a203acdcae5 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1023,6 +1023,11 @@ static int atalk_create(struct net *net, struct socket *sock, int protocol,
 	 */
 	if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM)
 		goto out;
+
+	rc = -EPERM;
+	if (sock->type == SOCK_RAW && !kern && !capable(CAP_NET_RAW))
+		goto out;
+
 	rc = -ENOMEM;
 	sk = sk_alloc(net, PF_APPLETALK, GFP_KERNEL, &ddp_proto, kern);
 	if (!sk)
-- 
2.20.1


From 501248b7d506f66ff6eddd8101003d7c7bc7a125 Mon Sep 17 00:00:00 2001
From: Ori Nimron <orinimron123@gmail.com>
Date: Fri, 20 Sep 2019 09:35:47 +0200
Subject: [PATCH 30/32] ax25: enforce CAP_NET_RAW for raw sockets

[ Upstream commit 0614e2b73768b502fc32a75349823356d98aae2c ]

When creating a raw AF_AX25 socket, CAP_NET_RAW needs to be checked
first.

Signed-off-by: Ori Nimron <orinimron123@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ax25/af_ax25.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index ca5207767dc2..bb222b882b67 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -855,6 +855,8 @@ static int ax25_create(struct net *net, struct socket *sock, int protocol,
 		break;
 
 	case SOCK_RAW:
+		if (!capable(CAP_NET_RAW))
+			return -EPERM;
 		break;
 	default:
 		return -ESOCKTNOSUPPORT;
-- 
2.20.1


From 0108fbdc0c9d9ac7806d0688f6489c66e78da845 Mon Sep 17 00:00:00 2001
From: Ori Nimron <orinimron123@gmail.com>
Date: Fri, 20 Sep 2019 09:35:48 +0200
Subject: [PATCH 31/32] ieee802154: enforce CAP_NET_RAW for raw sockets

[ Upstream commit e69dbd4619e7674c1679cba49afd9dd9ac347eef ]

When creating a raw AF_IEEE802154 socket, CAP_NET_RAW needs to be
checked first.

Signed-off-by: Ori Nimron <orinimron123@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Stefan Schmidt <stefan@datenfreihafen.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ieee802154/socket.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c
index dacbd58e1799..0bce822b95d0 100644
--- a/net/ieee802154/socket.c
+++ b/net/ieee802154/socket.c
@@ -1008,6 +1008,9 @@ static int ieee802154_create(struct net *net, struct socket *sock,
 
 	switch (sock->type) {
 	case SOCK_RAW:
+		rc = -EPERM;
+		if (!capable(CAP_NET_RAW))
+			goto out;
 		proto = &ieee802154_raw_prot;
 		ops = &ieee802154_raw_ops;
 		break;
-- 
2.20.1


From 1ab45ba2a4450a0a02a92294084b41d52b6ee6d8 Mon Sep 17 00:00:00 2001
From: Ori Nimron <orinimron123@gmail.com>
Date: Fri, 20 Sep 2019 09:35:49 +0200
Subject: [PATCH 32/32] nfc: enforce CAP_NET_RAW for raw sockets

[ Upstream commit 3a359798b176183ef09efb7a3dc59abad1cc7104 ]

When creating a raw AF_NFC socket, CAP_NET_RAW needs to be checked
first.

Signed-off-by: Ori Nimron <orinimron123@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/nfc/llcp_sock.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index 9b8742947aff..8dfea26536c9 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -1004,10 +1004,13 @@ static int llcp_sock_create(struct net *net, struct socket *sock,
 	    sock->type != SOCK_RAW)
 		return -ESOCKTNOSUPPORT;
 
-	if (sock->type == SOCK_RAW)
+	if (sock->type == SOCK_RAW) {
+		if (!capable(CAP_NET_RAW))
+			return -EPERM;
 		sock->ops = &llcp_rawsock_ops;
-	else
+	} else {
 		sock->ops = &llcp_sock_ops;
+	}
 
 	sk = nfc_llcp_sock_alloc(sock, sock->type, GFP_ATOMIC, kern);
 	if (sk == NULL)
-- 
2.20.1


[-- Attachment #3: net_53.mbox --]
[-- Type: Application/Octet-Stream, Size: 84037 bytes --]

From 38ecd72d8da9c9f1fd47fd39b2c66caf8ff4edad Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Fri, 20 Sep 2019 16:08:21 +0200
Subject: [PATCH 01/37] arcnet: provide a buffer big enough to actually receive
 packets
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 108639aac35eb57f1d0e8333f5fc8c7ff68df938 ]

struct archdr is only big enough to hold the header of various types of
arcnet packets. So to provide enough space to hold the data read from
hardware provide a buffer large enough to hold a packet with maximal
size.

The problem was noticed by the stack protector which makes the kernel
oops.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Michael Grzeschik <m.grzeschik@pengutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/arcnet/arcnet.c | 31 +++++++++++++++++--------------
 1 file changed, 17 insertions(+), 14 deletions(-)

diff --git a/drivers/net/arcnet/arcnet.c b/drivers/net/arcnet/arcnet.c
index 8459115d9d4e..553776cc1d29 100644
--- a/drivers/net/arcnet/arcnet.c
+++ b/drivers/net/arcnet/arcnet.c
@@ -1063,31 +1063,34 @@ EXPORT_SYMBOL(arcnet_interrupt);
 static void arcnet_rx(struct net_device *dev, int bufnum)
 {
 	struct arcnet_local *lp = netdev_priv(dev);
-	struct archdr pkt;
+	union {
+		struct archdr pkt;
+		char buf[512];
+	} rxdata;
 	struct arc_rfc1201 *soft;
 	int length, ofs;
 
-	soft = &pkt.soft.rfc1201;
+	soft = &rxdata.pkt.soft.rfc1201;
 
-	lp->hw.copy_from_card(dev, bufnum, 0, &pkt, ARC_HDR_SIZE);
-	if (pkt.hard.offset[0]) {
-		ofs = pkt.hard.offset[0];
+	lp->hw.copy_from_card(dev, bufnum, 0, &rxdata.pkt, ARC_HDR_SIZE);
+	if (rxdata.pkt.hard.offset[0]) {
+		ofs = rxdata.pkt.hard.offset[0];
 		length = 256 - ofs;
 	} else {
-		ofs = pkt.hard.offset[1];
+		ofs = rxdata.pkt.hard.offset[1];
 		length = 512 - ofs;
 	}
 
 	/* get the full header, if possible */
-	if (sizeof(pkt.soft) <= length) {
-		lp->hw.copy_from_card(dev, bufnum, ofs, soft, sizeof(pkt.soft));
+	if (sizeof(rxdata.pkt.soft) <= length) {
+		lp->hw.copy_from_card(dev, bufnum, ofs, soft, sizeof(rxdata.pkt.soft));
 	} else {
-		memset(&pkt.soft, 0, sizeof(pkt.soft));
+		memset(&rxdata.pkt.soft, 0, sizeof(rxdata.pkt.soft));
 		lp->hw.copy_from_card(dev, bufnum, ofs, soft, length);
 	}
 
 	arc_printk(D_DURING, dev, "Buffer #%d: received packet from %02Xh to %02Xh (%d+4 bytes)\n",
-		   bufnum, pkt.hard.source, pkt.hard.dest, length);
+		   bufnum, rxdata.pkt.hard.source, rxdata.pkt.hard.dest, length);
 
 	dev->stats.rx_packets++;
 	dev->stats.rx_bytes += length + ARC_HDR_SIZE;
@@ -1096,13 +1099,13 @@ static void arcnet_rx(struct net_device *dev, int bufnum)
 	if (arc_proto_map[soft->proto]->is_ip) {
 		if (BUGLVL(D_PROTO)) {
 			struct ArcProto
-			*oldp = arc_proto_map[lp->default_proto[pkt.hard.source]],
+			*oldp = arc_proto_map[lp->default_proto[rxdata.pkt.hard.source]],
 			*newp = arc_proto_map[soft->proto];
 
 			if (oldp != newp) {
 				arc_printk(D_PROTO, dev,
 					   "got protocol %02Xh; encap for host %02Xh is now '%c' (was '%c')\n",
-					   soft->proto, pkt.hard.source,
+					   soft->proto, rxdata.pkt.hard.source,
 					   newp->suffix, oldp->suffix);
 			}
 		}
@@ -1111,10 +1114,10 @@ static void arcnet_rx(struct net_device *dev, int bufnum)
 		lp->default_proto[0] = soft->proto;
 
 		/* in striking contrast, the following isn't a hack. */
-		lp->default_proto[pkt.hard.source] = soft->proto;
+		lp->default_proto[rxdata.pkt.hard.source] = soft->proto;
 	}
 	/* call the protocol-specific receiver. */
-	arc_proto_map[soft->proto]->rx(dev, bufnum, &pkt, length);
+	arc_proto_map[soft->proto]->rx(dev, bufnum, &rxdata.pkt, length);
 }
 
 static void null_rx(struct net_device *dev, int bufnum,
-- 
2.20.1


From 4788948823821eed4c19ca232d254e9d95183f78 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Wed, 18 Sep 2019 14:01:46 +0200
Subject: [PATCH 02/37] cdc_ncm: fix divide-by-zero caused by invalid
 wMaxPacketSize
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 3fe4b3351301660653a2bc73f2226da0ebd2b95e ]

Endpoints with zero wMaxPacketSize are not usable for transferring
data. Ignore such endpoints when looking for valid in, out and
status pipes, to make the driver more robust against invalid and
meaningless descriptors.

The wMaxPacketSize of the out pipe is used as divisor. So this change
fixes a divide-by-zero bug.

Reported-by: syzbot+ce366e2b8296e25d84f5@syzkaller.appspotmail.com
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/usb/cdc_ncm.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 50c05d0f44cb..00cab3f43a4c 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -681,8 +681,12 @@ cdc_ncm_find_endpoints(struct usbnet *dev, struct usb_interface *intf)
 	u8 ep;
 
 	for (ep = 0; ep < intf->cur_altsetting->desc.bNumEndpoints; ep++) {
-
 		e = intf->cur_altsetting->endpoint + ep;
+
+		/* ignore endpoints which cannot transfer data */
+		if (!usb_endpoint_maxp(&e->desc))
+			continue;
+
 		switch (e->desc.bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) {
 		case USB_ENDPOINT_XFER_INT:
 			if (usb_endpoint_dir_in(&e->desc)) {
-- 
2.20.1


From ace2a2992dc423ffc22fb8cdbd021d2bb2c36f84 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Tue, 24 Sep 2019 16:01:28 +0200
Subject: [PATCH 03/37] ipv6: do not free rt if FIB_LOOKUP_NOREF is set on
 suppress rule

[ Upstream commit ca7a03c4175366a92cee0ccc4fec0038c3266e26 ]

Commit 7d9e5f422150 removed references from certain dsts, but accounting
for this never translated down into the fib6 suppression code. This bug
was triggered by WireGuard users who use wg-quick(8), which uses the
"suppress-prefix" directive to ip-rule(8) for routing all of their
internet traffic without routing loops. The test case added here
causes the reference underflow by causing packets to evaluate a suppress
rule.

Fixes: 7d9e5f422150 ("ipv6: convert major tx path to use RT6_LOOKUP_F_DST_NOREF")
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Acked-by: Wei Wang <weiwan@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/fib6_rules.c                    |  3 ++-
 tools/testing/selftests/net/fib_tests.sh | 17 ++++++++++++++++-
 2 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index d22b6c140f23..f9e8fe3ff0c5 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -287,7 +287,8 @@ static bool fib6_rule_suppress(struct fib_rule *rule, struct fib_lookup_arg *arg
 	return false;
 
 suppress_route:
-	ip6_rt_put(rt);
+	if (!(arg->flags & FIB_LOOKUP_NOREF))
+		ip6_rt_put(rt);
 	return true;
 }
 
diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 4465fc2dae14..c2c5f2bf0f95 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -9,7 +9,7 @@ ret=0
 ksft_skip=4
 
 # all tests in this script. Can be overridden with -t option
-TESTS="unregister down carrier nexthop ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics ipv4_route_v6_gw rp_filter"
+TESTS="unregister down carrier nexthop suppress ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics ipv4_route_v6_gw rp_filter"
 
 VERBOSE=0
 PAUSE_ON_FAIL=no
@@ -614,6 +614,20 @@ fib_nexthop_test()
 	cleanup
 }
 
+fib_suppress_test()
+{
+	$IP link add dummy1 type dummy
+	$IP link set dummy1 up
+	$IP -6 route add default dev dummy1
+	$IP -6 rule add table main suppress_prefixlength 0
+	ping -f -c 1000 -W 1 1234::1 || true
+	$IP -6 rule del table main suppress_prefixlength 0
+	$IP link del dummy1
+
+	# If we got here without crashing, we're good.
+	return 0
+}
+
 ################################################################################
 # Tests on route add and replace
 
@@ -1591,6 +1605,7 @@ do
 	fib_carrier_test|carrier)	fib_carrier_test;;
 	fib_rp_filter_test|rp_filter)	fib_rp_filter_test;;
 	fib_nexthop_test|nexthop)	fib_nexthop_test;;
+	fib_suppress_test|suppress)	fib_suppress_test;;
 	ipv6_route_test|ipv6_rt)	ipv6_route_test;;
 	ipv4_route_test|ipv4_rt)	ipv4_route_test;;
 	ipv6_addr_metric)		ipv6_addr_metric_test;;
-- 
2.20.1


From dc55224d93dc92e63d5561770d3c4cd25624c57f Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 23 Sep 2019 17:02:46 +0800
Subject: [PATCH 04/37] macsec: drop skb sk before calling gro_cells_receive

[ Upstream commit ba56d8ce38c8252fff5b745db3899cf092578ede ]

Fei Liu reported a crash when doing netperf on a topo of macsec
dev over veth:

  [  448.919128] refcount_t: underflow; use-after-free.
  [  449.090460] Call trace:
  [  449.092895]  refcount_sub_and_test+0xb4/0xc0
  [  449.097155]  tcp_wfree+0x2c/0x150
  [  449.100460]  ip_rcv+0x1d4/0x3a8
  [  449.103591]  __netif_receive_skb_core+0x554/0xae0
  [  449.108282]  __netif_receive_skb+0x28/0x78
  [  449.112366]  netif_receive_skb_internal+0x54/0x100
  [  449.117144]  napi_gro_complete+0x70/0xc0
  [  449.121054]  napi_gro_flush+0x6c/0x90
  [  449.124703]  napi_complete_done+0x50/0x130
  [  449.128788]  gro_cell_poll+0x8c/0xa8
  [  449.132351]  net_rx_action+0x16c/0x3f8
  [  449.136088]  __do_softirq+0x128/0x320

The issue was caused by skb's true_size changed without its sk's
sk_wmem_alloc increased in tcp/skb_gro_receive(). Later when the
skb is being freed and the skb's truesize is subtracted from its
sk's sk_wmem_alloc in tcp_wfree(), underflow occurs.

macsec is calling gro_cells_receive() to receive a packet, which
actually requires skb->sk to be NULL. However when macsec dev is
over veth, it's possible the skb->sk is still set if the skb was
not unshared or expanded from the peer veth.

ip_rcv() is calling skb_orphan() to drop the skb's sk for tproxy,
but it is too late for macsec's calling gro_cells_receive(). So
fix it by dropping the skb's sk earlier on rx path of macsec.

Fixes: 5491e7c6b1a9 ("macsec: enable GRO and RPS on macsec devices")
Reported-by: Xiumei Mu <xmu@redhat.com>
Reported-by: Fei Liu <feliu@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macsec.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 8f46aa1ddec0..cb7637364b40 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -1235,6 +1235,7 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb)
 		macsec_rxsa_put(rx_sa);
 	macsec_rxsc_put(rx_sc);
 
+	skb_orphan(skb);
 	ret = gro_cells_receive(&macsec->gro_cells, skb);
 	if (ret == NET_RX_SUCCESS)
 		count_rx(dev, skb->len);
-- 
2.20.1


From f10c900eba357e24cbbe5b5602e1f7a7db2197a0 Mon Sep 17 00:00:00 2001
From: Peter Mamonov <pmamonov@gmail.com>
Date: Wed, 18 Sep 2019 19:27:55 +0300
Subject: [PATCH 05/37] net/phy: fix DP83865 10 Mbps HDX loopback disable
 function

[ Upstream commit e47488b2df7f9cb405789c7f5d4c27909fc597ae ]

According to the DP83865 datasheet "the 10 Mbps HDX loopback can be
disabled in the expanded memory register 0x1C0.1". The driver erroneously
used bit 0 instead of bit 1.

Fixes: 4621bf129856 ("phy: Add file missed in previous commit.")
Signed-off-by: Peter Mamonov <pmamonov@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/phy/national.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/phy/national.c b/drivers/net/phy/national.c
index a221dd552c3c..a5bf0874c7d8 100644
--- a/drivers/net/phy/national.c
+++ b/drivers/net/phy/national.c
@@ -105,14 +105,17 @@ static void ns_giga_speed_fallback(struct phy_device *phydev, int mode)
 
 static void ns_10_base_t_hdx_loopack(struct phy_device *phydev, int disable)
 {
+	u16 lb_dis = BIT(1);
+
 	if (disable)
-		ns_exp_write(phydev, 0x1c0, ns_exp_read(phydev, 0x1c0) | 1);
+		ns_exp_write(phydev, 0x1c0,
+			     ns_exp_read(phydev, 0x1c0) | lb_dis);
 	else
 		ns_exp_write(phydev, 0x1c0,
-			     ns_exp_read(phydev, 0x1c0) & 0xfffe);
+			     ns_exp_read(phydev, 0x1c0) & ~lb_dis);
 
 	pr_debug("10BASE-T HDX loopback %s\n",
-		 (ns_exp_read(phydev, 0x1c0) & 0x0001) ? "off" : "on");
+		 (ns_exp_read(phydev, 0x1c0) & lb_dis) ? "off" : "on");
 }
 
 static int ns_config_init(struct phy_device *phydev)
-- 
2.20.1


From d4b288fd11925d742a878818e25686323b805525 Mon Sep 17 00:00:00 2001
From: Bjorn Andersson <bjorn.andersson@linaro.org>
Date: Wed, 18 Sep 2019 10:21:17 -0700
Subject: [PATCH 06/37] net: qrtr: Stop rx_worker before freeing node

[ Upstream commit 73f0c11d11329a0d6d205d4312b6e5d2512af7c5 ]

As the endpoint is unregistered there might still be work pending to
handle incoming messages, which will result in a use after free
scenario. The plan is to remove the rx_worker, but until then (and for
stable@) ensure that the work is stopped before the node is freed.

Fixes: bdabad3e363d ("net: Add Qualcomm IPC router")
Cc: stable@vger.kernel.org
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/qrtr/qrtr.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index 6c8b0f6d28f9..88f98f27ad88 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -150,6 +150,7 @@ static void __qrtr_node_release(struct kref *kref)
 	list_del(&node->item);
 	mutex_unlock(&qrtr_node_lock);
 
+	cancel_work_sync(&node->work);
 	skb_queue_purge(&node->rx_queue);
 	kfree(node);
 }
-- 
2.20.1


From cd9754a30c50daf9c04b24f2c3e25906d6278922 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Tue, 17 Sep 2019 11:30:55 +0200
Subject: [PATCH 07/37] net/sched: act_sample: don't push mac header on ip6gre
 ingress

[ Upstream commit 92974a1d006ad8b30d53047c70974c9e065eb7df ]

current 'sample' action doesn't push the mac header of ingress packets if
they are received by a layer 3 tunnel (like gre or sit); but it forgot to
check for gre over ipv6, so the following script:

 # tc q a dev $d clsact
 # tc f a dev $d ingress protocol ip flower ip_proto icmp action sample \
 > group 100 rate 1
 # psample -v -g 100

dumps everything, including outer header and mac, when $d is a gre tunnel
over ipv6. Fix this adding a missing label for ARPHRD_IP6GRE devices.

Fixes: 5c5670fae430 ("net/sched: Introduce sample tc action")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Reviewed-by: Yotam Gigi <yotam.gi@gmail.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/sched/act_sample.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 10229124a992..86344fd2ff1f 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -146,6 +146,7 @@ static bool tcf_sample_dev_ok_push(struct net_device *dev)
 	case ARPHRD_TUNNEL6:
 	case ARPHRD_SIT:
 	case ARPHRD_IPGRE:
+	case ARPHRD_IP6GRE:
 	case ARPHRD_VOID:
 	case ARPHRD_NONE:
 		return false;
-- 
2.20.1


From cbb447062e1c6e901484e87cacc3a0a51d2aeae0 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Wed, 18 Sep 2019 16:24:12 -0700
Subject: [PATCH 08/37] net_sched: add max len check for TCA_KIND

[ Upstream commit 62794fc4fbf52f2209dc094ea255eaef760e7d01 ]

The TCA_KIND attribute is of NLA_STRING which does not check
the NUL char. KMSAN reported an uninit-value of TCA_KIND which
is likely caused by the lack of NUL.

Change it to NLA_NUL_STRING and add a max len too.

Fixes: 8b4c3cdd9dd8 ("net: sched: Add policy validation for tc attributes")
Reported-and-tested-by: syzbot+618aacd49e8c8b8486bd@syzkaller.appspotmail.com
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/sched/sch_api.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 1047825d9f48..81d58b280612 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1390,7 +1390,8 @@ check_loop_fn(struct Qdisc *q, unsigned long cl, struct qdisc_walker *w)
 }
 
 const struct nla_policy rtm_tca_policy[TCA_MAX + 1] = {
-	[TCA_KIND]		= { .type = NLA_STRING },
+	[TCA_KIND]		= { .type = NLA_NUL_STRING,
+				    .len = IFNAMSIZ - 1 },
 	[TCA_RATE]		= { .type = NLA_BINARY,
 				    .len = sizeof(struct tc_estimator) },
 	[TCA_STAB]		= { .type = NLA_NESTED },
-- 
2.20.1


From afae1b4fd757e41791f2d7274026ce69370978ea Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Mon, 23 Sep 2019 11:59:15 +0200
Subject: [PATCH 09/37] net: stmmac: Fix page pool size

[ Upstream commit 4f28bd956e081fc018fe9b41ffa31573f17bfb61 ]

The size of individual pages in the page pool in given by an order. The
order is the binary logarithm of the number of pages that make up one of
the pages in the pool. However, the driver currently passes the number
of pages rather than the order, so it ends up wasting quite a bit of
memory.

Fix this by taking the binary logarithm and passing that in the order
field.

Fixes: 2af6106ae949 ("net: stmmac: Introducing support for Page Pool")
Signed-off-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index b19ab09cb18f..5c4408bdc843 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1532,13 +1532,15 @@ static int alloc_dma_rx_desc_resources(struct stmmac_priv *priv)
 	for (queue = 0; queue < rx_count; queue++) {
 		struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
 		struct page_pool_params pp_params = { 0 };
+		unsigned int num_pages;
 
 		rx_q->queue_index = queue;
 		rx_q->priv_data = priv;
 
 		pp_params.flags = PP_FLAG_DMA_MAP;
 		pp_params.pool_size = DMA_RX_SIZE;
-		pp_params.order = DIV_ROUND_UP(priv->dma_buf_sz, PAGE_SIZE);
+		num_pages = DIV_ROUND_UP(priv->dma_buf_sz, PAGE_SIZE);
+		pp_params.order = ilog2(num_pages);
 		pp_params.nid = dev_to_node(priv->device);
 		pp_params.dev = priv->device;
 		pp_params.dma_dir = DMA_FROM_DEVICE;
-- 
2.20.1


From b2919a801ebbe62c244bac7a0fb51f03cf390b7f Mon Sep 17 00:00:00 2001
From: Navid Emamdoost <navid.emamdoost@gmail.com>
Date: Wed, 25 Sep 2019 14:05:09 -0500
Subject: [PATCH 10/37] nfp: flower: fix memory leak in
 nfp_flower_spawn_vnic_reprs

[ Upstream commit 8ce39eb5a67aee25d9f05b40b673c95b23502e3e ]

In nfp_flower_spawn_vnic_reprs in the loop if initialization or the
allocations fail memory is leaked. Appropriate releases are added.

Fixes: b94524529741 ("nfp: flower: add per repr private data for LAG offload")
Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/main.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c
index eb846133943b..5331e01f373e 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.c
@@ -400,6 +400,7 @@ nfp_flower_spawn_vnic_reprs(struct nfp_app *app,
 		repr_priv = kzalloc(sizeof(*repr_priv), GFP_KERNEL);
 		if (!repr_priv) {
 			err = -ENOMEM;
+			nfp_repr_free(repr);
 			goto err_reprs_clean;
 		}
 
@@ -413,6 +414,7 @@ nfp_flower_spawn_vnic_reprs(struct nfp_app *app,
 		port = nfp_port_alloc(app, port_type, repr);
 		if (IS_ERR(port)) {
 			err = PTR_ERR(port);
+			kfree(repr_priv);
 			nfp_repr_free(repr);
 			goto err_reprs_clean;
 		}
@@ -433,6 +435,7 @@ nfp_flower_spawn_vnic_reprs(struct nfp_app *app,
 		err = nfp_repr_init(app, repr,
 				    port_id, port, priv->nn->dp.netdev);
 		if (err) {
+			kfree(repr_priv);
 			nfp_port_free(port);
 			nfp_repr_free(repr);
 			goto err_reprs_clean;
-- 
2.20.1


From 214cd785031a7ce03844ed09725cb5db65e3480f Mon Sep 17 00:00:00 2001
From: Navid Emamdoost <navid.emamdoost@gmail.com>
Date: Wed, 25 Sep 2019 13:24:02 -0500
Subject: [PATCH 11/37] nfp: flower: prevent memory leak in
 nfp_flower_spawn_phy_reprs

[ Upstream commit 8572cea1461a006bce1d06c0c4b0575869125fa4 ]

In nfp_flower_spawn_phy_reprs, in the for loop over eth_tbl if any of
intermediate allocations or initializations fail memory is leaked.
requiered releases are added.

Fixes: b94524529741 ("nfp: flower: add per repr private data for LAG offload")
Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/main.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c
index 5331e01f373e..acb02e1513f2 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.c
@@ -518,6 +518,7 @@ nfp_flower_spawn_phy_reprs(struct nfp_app *app, struct nfp_flower_priv *priv)
 		repr_priv = kzalloc(sizeof(*repr_priv), GFP_KERNEL);
 		if (!repr_priv) {
 			err = -ENOMEM;
+			nfp_repr_free(repr);
 			goto err_reprs_clean;
 		}
 
@@ -528,11 +529,13 @@ nfp_flower_spawn_phy_reprs(struct nfp_app *app, struct nfp_flower_priv *priv)
 		port = nfp_port_alloc(app, NFP_PORT_PHYS_PORT, repr);
 		if (IS_ERR(port)) {
 			err = PTR_ERR(port);
+			kfree(repr_priv);
 			nfp_repr_free(repr);
 			goto err_reprs_clean;
 		}
 		err = nfp_port_init_phy_port(app->pf, app, port, i);
 		if (err) {
+			kfree(repr_priv);
 			nfp_port_free(port);
 			nfp_repr_free(repr);
 			goto err_reprs_clean;
@@ -545,6 +548,7 @@ nfp_flower_spawn_phy_reprs(struct nfp_app *app, struct nfp_flower_priv *priv)
 		err = nfp_repr_init(app, repr,
 				    cmsg_port_id, port, priv->nn->dp.netdev);
 		if (err) {
+			kfree(repr_priv);
 			nfp_port_free(port);
 			nfp_repr_free(repr);
 			goto err_reprs_clean;
-- 
2.20.1


From 7306fb49b3b081f74b1dc1c620595588823d8851 Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Tue, 24 Sep 2019 19:11:52 +0800
Subject: [PATCH 12/37] openvswitch: change type of UPCALL_PID attribute to
 NLA_UNSPEC

[ Upstream commit ea8564c865299815095bebeb4b25bef474218e4c ]

userspace openvswitch patch "(dpif-linux: Implement the API
functions to allow multiple handler threads read upcall)"
changes its type from U32 to UNSPEC, but leave the kernel
unchanged

and after kernel 6e237d099fac "(netlink: Relax attr validation
for fixed length types)", this bug is exposed by the below
warning

	[   57.215841] netlink: 'ovs-vswitchd': attribute type 5 has an invalid length.

Fixes: 5cd667b0a456 ("openvswitch: Allow each vport to have an array of 'port_id's")
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/datapath.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index d01410e52097..f1e7041a5a60 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -2263,7 +2263,7 @@ static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = {
 	[OVS_VPORT_ATTR_STATS] = { .len = sizeof(struct ovs_vport_stats) },
 	[OVS_VPORT_ATTR_PORT_NO] = { .type = NLA_U32 },
 	[OVS_VPORT_ATTR_TYPE] = { .type = NLA_U32 },
-	[OVS_VPORT_ATTR_UPCALL_PID] = { .type = NLA_U32 },
+	[OVS_VPORT_ATTR_UPCALL_PID] = { .type = NLA_UNSPEC },
 	[OVS_VPORT_ATTR_OPTIONS] = { .type = NLA_NESTED },
 	[OVS_VPORT_ATTR_IFINDEX] = { .type = NLA_U32 },
 	[OVS_VPORT_ATTR_NETNSID] = { .type = NLA_S32 },
-- 
2.20.1


From 7529a7980acf9038f4af1504198a4d95cc9c49a1 Mon Sep 17 00:00:00 2001
From: Takeshi Misawa <jeliantsurux@gmail.com>
Date: Sun, 22 Sep 2019 16:45:31 +0900
Subject: [PATCH 13/37] ppp: Fix memory leak in ppp_write

[ Upstream commit 4c247de564f1ff614d11b3bb5313fb70d7b9598b ]

When ppp is closing, __ppp_xmit_process() failed to enqueue skb
and skb allocated in ppp_write() is leaked.

syzbot reported :
BUG: memory leak
unreferenced object 0xffff88812a17bc00 (size 224):
  comm "syz-executor673", pid 6952, jiffies 4294942888 (age 13.040s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<00000000d110fff9>] kmemleak_alloc_recursive include/linux/kmemleak.h:43 [inline]
    [<00000000d110fff9>] slab_post_alloc_hook mm/slab.h:522 [inline]
    [<00000000d110fff9>] slab_alloc_node mm/slab.c:3262 [inline]
    [<00000000d110fff9>] kmem_cache_alloc_node+0x163/0x2f0 mm/slab.c:3574
    [<000000002d616113>] __alloc_skb+0x6e/0x210 net/core/skbuff.c:197
    [<000000000167fc45>] alloc_skb include/linux/skbuff.h:1055 [inline]
    [<000000000167fc45>] ppp_write+0x48/0x120 drivers/net/ppp/ppp_generic.c:502
    [<000000009ab42c0b>] __vfs_write+0x43/0xa0 fs/read_write.c:494
    [<00000000086b2e22>] vfs_write fs/read_write.c:558 [inline]
    [<00000000086b2e22>] vfs_write+0xee/0x210 fs/read_write.c:542
    [<00000000a2b70ef9>] ksys_write+0x7c/0x130 fs/read_write.c:611
    [<00000000ce5e0fdd>] __do_sys_write fs/read_write.c:623 [inline]
    [<00000000ce5e0fdd>] __se_sys_write fs/read_write.c:620 [inline]
    [<00000000ce5e0fdd>] __x64_sys_write+0x1e/0x30 fs/read_write.c:620
    [<00000000d9d7b370>] do_syscall_64+0x76/0x1a0 arch/x86/entry/common.c:296
    [<0000000006e6d506>] entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fix this by freeing skb, if ppp is closing.

Fixes: 6d066734e9f0 ("ppp: avoid loop in xmit recursion detection code")
Reported-and-tested-by: syzbot+d9c8bf24e56416d7ce2c@syzkaller.appspotmail.com
Signed-off-by: Takeshi Misawa <jeliantsurux@gmail.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Tested-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/ppp_generic.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index a30e41a56085..9a1b006904a7 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -1415,6 +1415,8 @@ static void __ppp_xmit_process(struct ppp *ppp, struct sk_buff *skb)
 			netif_wake_queue(ppp->dev);
 		else
 			netif_stop_queue(ppp->dev);
+	} else {
+		kfree_skb(skb);
 	}
 	ppp_xmit_unlock(ppp);
 }
-- 
2.20.1


From f84af65628e623da63af54263ef753c8f5406a59 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 18 Sep 2019 08:05:39 -0700
Subject: [PATCH 14/37] sch_netem: fix a divide by zero in tabledist()

[ Upstream commit b41d936b5ecfdb3a4abc525ce6402a6c49cffddc ]

syzbot managed to crash the kernel in tabledist() loading
an empty distribution table.

	t = dist->table[rnd % dist->size];

Simply return an error when such load is attempted.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/sched/sch_netem.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index b17f2ed970e2..f5cb35e550f8 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -777,7 +777,7 @@ static int get_dist_table(struct Qdisc *sch, struct disttable **tbl,
 	struct disttable *d;
 	int i;
 
-	if (n > NETEM_DIST_MAX)
+	if (!n || n > NETEM_DIST_MAX)
 		return -EINVAL;
 
 	d = kvmalloc(sizeof(struct disttable) + n * sizeof(s16), GFP_KERNEL);
-- 
2.20.1


From 7e8b7a9f5c7db7f2faad138f292d1ed7f6ba82c9 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 17 Sep 2019 10:30:21 -0700
Subject: [PATCH 15/37] selftests: Update fib_tests to handle missing ping6

[ Upstream commit 0360894a05ed52be268e3c4d40b2df9d94975fa6 ]

Some distributions (e.g., debian buster) do not install ping6. Re-use
the hook in pmtu.sh to detect this and fallback to ping.

Fixes: a0e11da78f48 ("fib_tests: Add tests for metrics on routes")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 tools/testing/selftests/net/fib_tests.sh | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index c2c5f2bf0f95..c4ba0ff4a53f 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -17,6 +17,8 @@ PAUSE=no
 IP="ip -netns ns1"
 NS_EXEC="ip netns exec ns1"
 
+which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping)
+
 log_test()
 {
 	local rc=$1
@@ -1100,7 +1102,7 @@ ipv6_route_metrics_test()
 	log_test $rc 0 "Multipath route with mtu metric"
 
 	$IP -6 ro add 2001:db8:104::/64 via 2001:db8:101::2 mtu 1300
-	run_cmd "ip netns exec ns1 ping6 -w1 -c1 -s 1500 2001:db8:104::1"
+	run_cmd "ip netns exec ns1 ${ping6} -w1 -c1 -s 1500 2001:db8:104::1"
 	log_test $? 0 "Using route with mtu metric"
 
 	run_cmd "$IP -6 ro add 2001:db8:114::/64 via  2001:db8:101::2  congctl lock foo"
-- 
2.20.1


From 74123d73dd7198efc31697b0c8c5a00191f48c91 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Fri, 20 Sep 2019 18:18:26 +0200
Subject: [PATCH 16/37] skge: fix checksum byte order

[ Upstream commit 5aafeb74b5bb65b34cc87c7623f9fa163a34fa3b ]

Running old skge driver on PowerPC causes checksum errors
because hardware reported 1's complement checksum is in little-endian
byte order.

Reported-by: Benoit <benoit.sansoni@gmail.com>
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/skge.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c
index 9ac854c2b371..697321898e84 100644
--- a/drivers/net/ethernet/marvell/skge.c
+++ b/drivers/net/ethernet/marvell/skge.c
@@ -3108,7 +3108,7 @@ static struct sk_buff *skge_rx_get(struct net_device *dev,
 	skb_put(skb, len);
 
 	if (dev->features & NETIF_F_RXCSUM) {
-		skb->csum = csum;
+		skb->csum = le16_to_cpu(csum);
 		skb->ip_summed = CHECKSUM_COMPLETE;
 	}
 
-- 
2.20.1


From 185403610d3396f1a6e7e47539658eb4de2a5d73 Mon Sep 17 00:00:00 2001
From: "Kevin(Yudong) Yang" <yyd@google.com>
Date: Thu, 26 Sep 2019 10:30:05 -0400
Subject: [PATCH 17/37] tcp_bbr: fix quantization code to not raise cwnd if not
 probing bandwidth

[ Upstream commit 6b3656a60f2067738d1a423328199720806f0c44 ]

There was a bug in the previous logic that attempted to ensure gain cycling
gets inflight above BDP even for small BDPs. This code correctly raised and
lowered target inflight values during the gain cycle. And this code
correctly ensured that cwnd was raised when probing bandwidth. However, it
did not correspondingly ensure that cwnd was *not* raised in this way when
*not* probing for bandwidth. The result was that small-BDP flows that were
always cwnd-bound could go for many cycles with a fixed cwnd, and not probe
or yield bandwidth at all. This meant that multiple small-BDP flows could
fail to converge in their bandwidth allocations.

Fixes: 3c346b233c68 ("tcp_bbr: fix bw probing to raise in-flight data for very small BDPs")
Signed-off-by: Kevin(Yudong) Yang <yyd@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Priyaranjan Jha <priyarjha@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_bbr.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 56be7d27f208..00ade9c185ea 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -386,7 +386,7 @@ static u32 bbr_bdp(struct sock *sk, u32 bw, int gain)
  * which allows 2 outstanding 2-packet sequences, to try to keep pipe
  * full even with ACK-every-other-packet delayed ACKs.
  */
-static u32 bbr_quantization_budget(struct sock *sk, u32 cwnd, int gain)
+static u32 bbr_quantization_budget(struct sock *sk, u32 cwnd)
 {
 	struct bbr *bbr = inet_csk_ca(sk);
 
@@ -397,7 +397,7 @@ static u32 bbr_quantization_budget(struct sock *sk, u32 cwnd, int gain)
 	cwnd = (cwnd + 1) & ~1U;
 
 	/* Ensure gain cycling gets inflight above BDP even for small BDPs. */
-	if (bbr->mode == BBR_PROBE_BW && gain > BBR_UNIT)
+	if (bbr->mode == BBR_PROBE_BW && bbr->cycle_idx == 0)
 		cwnd += 2;
 
 	return cwnd;
@@ -409,7 +409,7 @@ static u32 bbr_inflight(struct sock *sk, u32 bw, int gain)
 	u32 inflight;
 
 	inflight = bbr_bdp(sk, bw, gain);
-	inflight = bbr_quantization_budget(sk, inflight, gain);
+	inflight = bbr_quantization_budget(sk, inflight);
 
 	return inflight;
 }
@@ -529,7 +529,7 @@ static void bbr_set_cwnd(struct sock *sk, const struct rate_sample *rs,
 	 * due to aggregation (of data and/or ACKs) visible in the ACK stream.
 	 */
 	target_cwnd += bbr_ack_aggregation_cwnd(sk);
-	target_cwnd = bbr_quantization_budget(sk, target_cwnd, gain);
+	target_cwnd = bbr_quantization_budget(sk, target_cwnd);
 
 	/* If we're below target cwnd, slow start cwnd toward target cwnd. */
 	if (bbr_full_bw_reached(sk))  /* only cut cwnd if we filled the pipe */
-- 
2.20.1


From b5a7ebf762fcdad5644ebd319666606bf7786e35 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Wed, 18 Sep 2019 14:17:38 +0200
Subject: [PATCH 18/37] usbnet: ignore endpoints with invalid wMaxPacketSize
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 8d3d7c2029c1b360f1a6b0a2fca470b57eb575c0 ]

Endpoints with zero wMaxPacketSize are not usable for transferring
data. Ignore such endpoints when looking for valid in, out and
status pipes, to make the drivers more robust against invalid and
meaningless descriptors.

The wMaxPacketSize of these endpoints are used for memory allocations
and as divisors in many usbnet minidrivers. Avoiding zero is therefore
critical.

Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/usb/usbnet.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 72514c46b478..07c00e378a5c 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -100,6 +100,11 @@ int usbnet_get_endpoints(struct usbnet *dev, struct usb_interface *intf)
 			int				intr = 0;
 
 			e = alt->endpoint + ep;
+
+			/* ignore endpoints which cannot transfer data */
+			if (!usb_endpoint_maxp(&e->desc))
+				continue;
+
 			switch (e->desc.bmAttributes) {
 			case USB_ENDPOINT_XFER_INT:
 				if (!usb_endpoint_dir_in(&e->desc))
-- 
2.20.1


From e6235240b9f3c751e6cfb6d98e9aa0f5c5cfbf49 Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.com>
Date: Thu, 19 Sep 2019 10:23:08 +0200
Subject: [PATCH 19/37] usbnet: sanity checking of packet sizes and device mtu

[ Upstream commit 280ceaed79f18db930c0cc8bb21f6493490bf29c ]

After a reset packet sizes and device mtu can change and need
to be reevaluated to calculate queue sizes.
Malicious devices can set this to zero and we divide by it.
Introduce sanity checking.

Reported-and-tested-by:  syzbot+6102c120be558c885f04@syzkaller.appspotmail.com
Signed-off-by: Oliver Neukum <oneukum@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/usbnet.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 07c00e378a5c..ef1d667b0108 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -344,6 +344,8 @@ void usbnet_update_max_qlen(struct usbnet *dev)
 {
 	enum usb_device_speed speed = dev->udev->speed;
 
+	if (!dev->rx_urb_size || !dev->hard_mtu)
+		goto insanity;
 	switch (speed) {
 	case USB_SPEED_HIGH:
 		dev->rx_qlen = MAX_QUEUE_MEMORY / dev->rx_urb_size;
@@ -360,6 +362,7 @@ void usbnet_update_max_qlen(struct usbnet *dev)
 		dev->tx_qlen = 5 * MAX_QUEUE_MEMORY / dev->hard_mtu;
 		break;
 	default:
+insanity:
 		dev->rx_qlen = dev->tx_qlen = 4;
 	}
 }
-- 
2.20.1


From a08abfe343e9ed686bd3657f289f42396729320a Mon Sep 17 00:00:00 2001
From: Ka-Cheong Poon <ka-cheong.poon@oracle.com>
Date: Tue, 24 Sep 2019 08:51:16 -0700
Subject: [PATCH 20/37] net/rds: Check laddr_check before calling it

[ Upstream commit 05733434ee9ae6548723a808647248583e347cca ]

In rds_bind(), laddr_check is called without checking if it is NULL or
not.  And rs_transport should be reset if rds_add_bound() fails.

Fixes: c5c1a030a7db ("net/rds: An rds_sock is added too early to the hash table")
Reported-by: syzbot+fae39afd2101a17ec624@syzkaller.appspotmail.com
Signed-off-by: Ka-Cheong Poon <ka-cheong.poon@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/bind.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/rds/bind.c b/net/rds/bind.c
index 05464fd7c17a..93e336535d3b 100644
--- a/net/rds/bind.c
+++ b/net/rds/bind.c
@@ -244,7 +244,8 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	 */
 	if (rs->rs_transport) {
 		trans = rs->rs_transport;
-		if (trans->laddr_check(sock_net(sock->sk),
+		if (!trans->laddr_check ||
+		    trans->laddr_check(sock_net(sock->sk),
 				       binding_addr, scope_id) != 0) {
 			ret = -ENOPROTOOPT;
 			goto out;
@@ -263,6 +264,8 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 
 	sock_set_flag(sk, SOCK_RCU_FREE);
 	ret = rds_add_bound(rs, binding_addr, &port, scope_id);
+	if (ret)
+		rs->rs_transport = NULL;
 
 out:
 	release_sock(sk);
-- 
2.20.1


From 98782c4d29a02869be214ee9e9c5534307c0d0ad Mon Sep 17 00:00:00 2001
From: Dmytro Linkin <dmitrolin@mellanox.com>
Date: Fri, 13 Sep 2019 10:42:21 +0000
Subject: [PATCH 21/37] net/mlx5e: Fix matching on tunnel addresses type

[ Upstream commit fe1587a7de94912ed75ba5ddbfabf0741f9f8239 ]

In mlx5 parse_tunnel_attr() function dispatch on encap IP address type
is performed by directly checking flow_rule_match_key() on
FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, and then on
FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS. However, since those are stored in
union, first check is always true if any type of encap address is set,
which leads to IPv6 tunnel encap address being parsed as IPv4 by mlx5.
Determine correct IP address type by checking control key first and if
it set, take address type from match.key->addr_type.

Fixes: d1bda7eecd88 ("net/mlx5e: Allow matching only enc_key_id/enc_dst_port for decapsulation action")
Signed-off-by: Dmytro Linkin <dmitrolin@mellanox.com>
Reviewed-by: Vlad Buslov <vladbu@mellanox.com>
Reviewed-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en_tc.c   | 89 +++++++++++--------
 1 file changed, 53 insertions(+), 36 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 00b2d4a86159..98be5fe33674 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1369,46 +1369,63 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
 		return err;
 	}
 
-	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) {
-		struct flow_match_ipv4_addrs match;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_CONTROL)) {
+		struct flow_match_control match;
+		u16 addr_type;
 
-		flow_rule_match_enc_ipv4_addrs(rule, &match);
-		MLX5_SET(fte_match_set_lyr_2_4, headers_c,
-			 src_ipv4_src_ipv6.ipv4_layout.ipv4,
-			 ntohl(match.mask->src));
-		MLX5_SET(fte_match_set_lyr_2_4, headers_v,
-			 src_ipv4_src_ipv6.ipv4_layout.ipv4,
-			 ntohl(match.key->src));
-
-		MLX5_SET(fte_match_set_lyr_2_4, headers_c,
-			 dst_ipv4_dst_ipv6.ipv4_layout.ipv4,
-			 ntohl(match.mask->dst));
-		MLX5_SET(fte_match_set_lyr_2_4, headers_v,
-			 dst_ipv4_dst_ipv6.ipv4_layout.ipv4,
-			 ntohl(match.key->dst));
-
-		MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ethertype);
-		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype, ETH_P_IP);
-	} else if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS)) {
-		struct flow_match_ipv6_addrs match;
+		flow_rule_match_enc_control(rule, &match);
+		addr_type = match.key->addr_type;
 
-		flow_rule_match_enc_ipv6_addrs(rule, &match);
-		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
-				    src_ipv4_src_ipv6.ipv6_layout.ipv6),
-		       &match.mask->src, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6));
-		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
-				    src_ipv4_src_ipv6.ipv6_layout.ipv6),
-		       &match.key->src, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6));
+		/* For tunnel addr_type used same key id`s as for non-tunnel */
+		if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
+			struct flow_match_ipv4_addrs match;
 
-		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
-				    dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
-		       &match.mask->dst, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6));
-		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
-				    dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
-		       &match.key->dst, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6));
+			flow_rule_match_enc_ipv4_addrs(rule, &match);
+			MLX5_SET(fte_match_set_lyr_2_4, headers_c,
+				 src_ipv4_src_ipv6.ipv4_layout.ipv4,
+				 ntohl(match.mask->src));
+			MLX5_SET(fte_match_set_lyr_2_4, headers_v,
+				 src_ipv4_src_ipv6.ipv4_layout.ipv4,
+				 ntohl(match.key->src));
 
-		MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ethertype);
-		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype, ETH_P_IPV6);
+			MLX5_SET(fte_match_set_lyr_2_4, headers_c,
+				 dst_ipv4_dst_ipv6.ipv4_layout.ipv4,
+				 ntohl(match.mask->dst));
+			MLX5_SET(fte_match_set_lyr_2_4, headers_v,
+				 dst_ipv4_dst_ipv6.ipv4_layout.ipv4,
+				 ntohl(match.key->dst));
+
+			MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c,
+					 ethertype);
+			MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype,
+				 ETH_P_IP);
+		} else if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
+			struct flow_match_ipv6_addrs match;
+
+			flow_rule_match_enc_ipv6_addrs(rule, &match);
+			memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
+					    src_ipv4_src_ipv6.ipv6_layout.ipv6),
+			       &match.mask->src, MLX5_FLD_SZ_BYTES(ipv6_layout,
+								   ipv6));
+			memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
+					    src_ipv4_src_ipv6.ipv6_layout.ipv6),
+			       &match.key->src, MLX5_FLD_SZ_BYTES(ipv6_layout,
+								  ipv6));
+
+			memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
+					    dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
+			       &match.mask->dst, MLX5_FLD_SZ_BYTES(ipv6_layout,
+								   ipv6));
+			memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
+					    dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
+			       &match.key->dst, MLX5_FLD_SZ_BYTES(ipv6_layout,
+								  ipv6));
+
+			MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c,
+					 ethertype);
+			MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype,
+				 ETH_P_IPV6);
+		}
 	}
 
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IP)) {
-- 
2.20.1


From bcf22f8e6d361c88b1a28d0e56d24896b3daeb8a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 19 Sep 2019 10:12:36 -0700
Subject: [PATCH 22/37] ipv6: fix a typo in fib6_rule_lookup()

[ Upstream commit 7b09c2d052db4b4ad0b27b97918b46a7746966fa ]

Yi Ren reported an issue discovered by syzkaller, and bisected
to the cited commit.

Many thanks to Yi, this trivial patch does not reflect the patient
work that has been done.

Fixes: d64a1f574a29 ("ipv6: honor RT6_LOOKUP_F_DST_NOREF in rule lookup logic")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Wei Wang <weiwan@google.com>
Bisected-and-reported-by: Yi Ren <c4tren@gmail.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/ipv6/ip6_fib.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 87f47bc55c5e..6e2af411cd9c 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -318,7 +318,7 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
 	if (rt->dst.error == -EAGAIN) {
 		ip6_rt_put_flags(rt, flags);
 		rt = net->ipv6.ip6_null_entry;
-		if (!(flags | RT6_LOOKUP_F_DST_NOREF))
+		if (!(flags & RT6_LOOKUP_F_DST_NOREF))
 			dst_hold(&rt->dst);
 	}
 
-- 
2.20.1


From 7c5a1f635038d7bc288d33b2fb9b1da8b200b02d Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 17 Sep 2019 10:30:35 -0700
Subject: [PATCH 23/37] selftests: Update fib_nexthop_multiprefix to handle
 missing ping6

[ Upstream commit e84622ce24482f6e9c1bf29d3bdd556eb587ff41 ]

Some distributions (e.g., debian buster) do not install ping6. Re-use
the hook in pmtu.sh to detect this and fallback to ping.

Fixes: 735ab2f65dce ("selftests: Add test with multiple prefixes using single nexthop")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 tools/testing/selftests/net/fib_nexthop_multiprefix.sh | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/fib_nexthop_multiprefix.sh b/tools/testing/selftests/net/fib_nexthop_multiprefix.sh
index e6828732843e..9dc35a16e415 100755
--- a/tools/testing/selftests/net/fib_nexthop_multiprefix.sh
+++ b/tools/testing/selftests/net/fib_nexthop_multiprefix.sh
@@ -15,6 +15,8 @@
 PAUSE_ON_FAIL=no
 VERBOSE=0
 
+which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping)
+
 ################################################################################
 # helpers
 
@@ -200,7 +202,7 @@ validate_v6_exception()
 	local rc
 
 	if [ ${ping_sz} != "0" ]; then
-		run_cmd ip netns exec h0 ping6 -s ${ping_sz} -c5 -w5 ${dst}
+		run_cmd ip netns exec h0 ${ping6} -s ${ping_sz} -c5 -w5 ${dst}
 	fi
 
 	if [ "$VERBOSE" = "1" ]; then
@@ -243,7 +245,7 @@ do
 		run_cmd taskset -c ${c} ip netns exec h0 ping -c1 -w1 172.16.10${i}.1
 		[ $? -ne 0 ] && printf "\nERROR: ping to h${i} failed\n" && ret=1
 
-		run_cmd taskset -c ${c} ip netns exec h0 ping6 -c1 -w1 2001:db8:10${i}::1
+		run_cmd taskset -c ${c} ip netns exec h0 ${ping6} -c1 -w1 2001:db8:10${i}::1
 		[ $? -ne 0 ] && printf "\nERROR: ping6 to h${i} failed\n" && ret=1
 
 		[ $ret -ne 0 ] && break
-- 
2.20.1


From 686274d5c5e6db2682fbea6b6433cf5add945715 Mon Sep 17 00:00:00 2001
From: Hans Andersson <hans.andersson@cellavision.se>
Date: Thu, 26 Sep 2019 09:54:37 +0200
Subject: [PATCH 24/37] net: phy: micrel: add Asym Pause workaround for KSZ9021

[ Upstream commit 407d8098cb1ab338199f4753162799a488d87d23 ]

The Micrel KSZ9031 PHY may fail to establish a link when the Asymmetric
Pause capability is set. This issue is described in a Silicon Errata
(DS80000691D or DS80000692D), which advises to always disable the
capability.

Micrel KSZ9021 has no errata, but has the same issue with Asymmetric Pause.
This patch apply the same workaround as the one for KSZ9031.

Fixes: 3aed3e2a143c ("net: phy: micrel: add Asym Pause workaround")
Signed-off-by: Hans Andersson <hans.andersson@cellavision.se>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/micrel.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 3c8186f269f9..2fea5541c35a 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -763,6 +763,8 @@ static int ksz9031_get_features(struct phy_device *phydev)
 	 * Whenever the device's Asymmetric Pause capability is set to 1,
 	 * link-up may fail after a link-up to link-down transition.
 	 *
+	 * The Errata Sheet is for ksz9031, but ksz9021 has the same issue
+	 *
 	 * Workaround:
 	 * Do not enable the Asymmetric Pause capability bit.
 	 */
@@ -1076,6 +1078,7 @@ static struct phy_driver ksphy_driver[] = {
 	/* PHY_GBIT_FEATURES */
 	.driver_data	= &ksz9021_type,
 	.probe		= kszphy_probe,
+	.get_features	= ksz9031_get_features,
 	.config_init	= ksz9021_config_init,
 	.ack_interrupt	= kszphy_ack_interrupt,
 	.config_intr	= kszphy_config_intr,
-- 
2.20.1


From 03dbbe28b33d5f0fe1272709f609e4116b0d4f3b Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Mon, 23 Sep 2019 22:04:58 -0700
Subject: [PATCH 25/37] net/sched: cbs: Fix not adding cbs instance to list

[ Upstream commit 3e8b9bfa110896f95d602d8c98d5f9d67e41d78c ]

When removing a cbs instance when offloading is enabled, the crash
below can be observed.

The problem happens because that when offloading is enabled, the cbs
instance is not added to the list.

Also, the current code doesn't handle correctly the case when offload
is disabled without removing the qdisc: if the link speed changes the
credit calculations will be wrong. When we create the cbs instance
with offloading enabled, it's not added to the notification list, when
later we disable offloading, it's not in the list, so link speed
changes will not affect it.

The solution for both issues is the same, add the cbs instance being
created unconditionally to the global list, even if the link state
notification isn't useful "right now".

Crash log:

[518758.189866] BUG: kernel NULL pointer dereference, address: 0000000000000000
[518758.189870] #PF: supervisor read access in kernel mode
[518758.189871] #PF: error_code(0x0000) - not-present page
[518758.189872] PGD 0 P4D 0
[518758.189874] Oops: 0000 [#1] SMP PTI
[518758.189876] CPU: 3 PID: 4825 Comm: tc Not tainted 5.2.9 #1
[518758.189877] Hardware name: Gigabyte Technology Co., Ltd. Z390 AORUS ULTRA/Z390 AORUS ULTRA-CF, BIOS F7 03/14/2019
[518758.189881] RIP: 0010:__list_del_entry_valid+0x29/0xa0
[518758.189883] Code: 90 48 b8 00 01 00 00 00 00 ad de 55 48 8b 17 4c 8b 47 08 48 89 e5 48 39 c2 74 27 48 b8 00 02 00 00 00 00 ad de 49 39 c0 74 2d <49> 8b 30 48 39 fe 75 3d 48 8b 52 08 48 39 f2 75 4c b8 01 00 00 00
[518758.189885] RSP: 0018:ffffa27e43903990 EFLAGS: 00010207
[518758.189887] RAX: dead000000000200 RBX: ffff8bce69f0f000 RCX: 0000000000000000
[518758.189888] RDX: 0000000000000000 RSI: ffff8bce69f0f064 RDI: ffff8bce69f0f1e0
[518758.189890] RBP: ffffa27e43903990 R08: 0000000000000000 R09: ffff8bce69e788c0
[518758.189891] R10: ffff8bce62acd400 R11: 00000000000003cb R12: ffff8bce69e78000
[518758.189892] R13: ffff8bce69f0f140 R14: 0000000000000000 R15: 0000000000000000
[518758.189894] FS:  00007fa1572c8f80(0000) GS:ffff8bce6e0c0000(0000) knlGS:0000000000000000
[518758.189895] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[518758.189896] CR2: 0000000000000000 CR3: 000000040a398006 CR4: 00000000003606e0
[518758.189898] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[518758.189899] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[518758.189900] Call Trace:
[518758.189904]  cbs_destroy+0x32/0xa0 [sch_cbs]
[518758.189906]  qdisc_destroy+0x45/0x120
[518758.189907]  qdisc_put+0x25/0x30
[518758.189908]  qdisc_graft+0x2c1/0x450
[518758.189910]  tc_get_qdisc+0x1c8/0x310
[518758.189912]  ? get_page_from_freelist+0x91a/0xcb0
[518758.189914]  rtnetlink_rcv_msg+0x293/0x360
[518758.189916]  ? kmem_cache_alloc_node_trace+0x178/0x260
[518758.189918]  ? __kmalloc_node_track_caller+0x38/0x50
[518758.189920]  ? rtnl_calcit.isra.0+0xf0/0xf0
[518758.189922]  netlink_rcv_skb+0x48/0x110
[518758.189923]  rtnetlink_rcv+0x10/0x20
[518758.189925]  netlink_unicast+0x15b/0x1d0
[518758.189926]  netlink_sendmsg+0x1ea/0x380
[518758.189929]  sock_sendmsg+0x2f/0x40
[518758.189930]  ___sys_sendmsg+0x295/0x2f0
[518758.189932]  ? ___sys_recvmsg+0x151/0x1e0
[518758.189933]  ? do_wp_page+0x7e/0x450
[518758.189935]  __sys_sendmsg+0x48/0x80
[518758.189937]  __x64_sys_sendmsg+0x1a/0x20
[518758.189939]  do_syscall_64+0x53/0x1f0
[518758.189941]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[518758.189942] RIP: 0033:0x7fa15755169a
[518758.189944] Code: 48 c7 c0 ff ff ff ff eb be 0f 1f 80 00 00 00 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 18 b8 2e 00 00 00 c5 fc 77 0f 05 <48> 3d 00 f0 ff ff 77 5e c3 0f 1f 44 00 00 48 83 ec 28 89 54 24 1c
[518758.189946] RSP: 002b:00007ffda58b60b8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
[518758.189948] RAX: ffffffffffffffda RBX: 000055e4b836d9a0 RCX: 00007fa15755169a
[518758.189949] RDX: 0000000000000000 RSI: 00007ffda58b6128 RDI: 0000000000000003
[518758.189951] RBP: 00007ffda58b6190 R08: 0000000000000001 R09: 000055e4b9d848a0
[518758.189952] R10: 0000000000000000 R11: 0000000000000246 R12: 000000005d654b49
[518758.189953] R13: 0000000000000000 R14: 00007ffda58b6230 R15: 00007ffda58b6210
[518758.189955] Modules linked in: sch_cbs sch_etf sch_mqprio netlink_diag unix_diag e1000e igb intel_pch_thermal thermal video backlight pcc_cpufreq
[518758.189960] CR2: 0000000000000000
[518758.189961] ---[ end trace 6a13f7aaf5376019 ]---
[518758.189963] RIP: 0010:__list_del_entry_valid+0x29/0xa0
[518758.189964] Code: 90 48 b8 00 01 00 00 00 00 ad de 55 48 8b 17 4c 8b 47 08 48 89 e5 48 39 c2 74 27 48 b8 00 02 00 00 00 00 ad de 49 39 c0 74 2d <49> 8b 30 48 39 fe 75 3d 48 8b 52 08 48 39 f2 75 4c b8 01 00 00 00
[518758.189967] RSP: 0018:ffffa27e43903990 EFLAGS: 00010207
[518758.189968] RAX: dead000000000200 RBX: ffff8bce69f0f000 RCX: 0000000000000000
[518758.189969] RDX: 0000000000000000 RSI: ffff8bce69f0f064 RDI: ffff8bce69f0f1e0
[518758.189971] RBP: ffffa27e43903990 R08: 0000000000000000 R09: ffff8bce69e788c0
[518758.189972] R10: ffff8bce62acd400 R11: 00000000000003cb R12: ffff8bce69e78000
[518758.189973] R13: ffff8bce69f0f140 R14: 0000000000000000 R15: 0000000000000000
[518758.189975] FS:  00007fa1572c8f80(0000) GS:ffff8bce6e0c0000(0000) knlGS:0000000000000000
[518758.189976] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[518758.189977] CR2: 0000000000000000 CR3: 000000040a398006 CR4: 00000000003606e0
[518758.189979] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[518758.189980] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400

Fixes: e0a7683d30e9 ("net/sched: cbs: fix port_rate miscalculation")
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_cbs.c | 30 +++++++++++++-----------------
 1 file changed, 13 insertions(+), 17 deletions(-)

diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c
index 810645b5c086..4a403d35438f 100644
--- a/net/sched/sch_cbs.c
+++ b/net/sched/sch_cbs.c
@@ -392,7 +392,6 @@ static int cbs_init(struct Qdisc *sch, struct nlattr *opt,
 {
 	struct cbs_sched_data *q = qdisc_priv(sch);
 	struct net_device *dev = qdisc_dev(sch);
-	int err;
 
 	if (!opt) {
 		NL_SET_ERR_MSG(extack, "Missing CBS qdisc options  which are mandatory");
@@ -404,6 +403,10 @@ static int cbs_init(struct Qdisc *sch, struct nlattr *opt,
 	if (!q->qdisc)
 		return -ENOMEM;
 
+	spin_lock(&cbs_list_lock);
+	list_add(&q->cbs_list, &cbs_list);
+	spin_unlock(&cbs_list_lock);
+
 	qdisc_hash_add(q->qdisc, false);
 
 	q->queue = sch->dev_queue - netdev_get_tx_queue(dev, 0);
@@ -413,17 +416,7 @@ static int cbs_init(struct Qdisc *sch, struct nlattr *opt,
 
 	qdisc_watchdog_init(&q->watchdog, sch);
 
-	err = cbs_change(sch, opt, extack);
-	if (err)
-		return err;
-
-	if (!q->offload) {
-		spin_lock(&cbs_list_lock);
-		list_add(&q->cbs_list, &cbs_list);
-		spin_unlock(&cbs_list_lock);
-	}
-
-	return 0;
+	return cbs_change(sch, opt, extack);
 }
 
 static void cbs_destroy(struct Qdisc *sch)
@@ -431,15 +424,18 @@ static void cbs_destroy(struct Qdisc *sch)
 	struct cbs_sched_data *q = qdisc_priv(sch);
 	struct net_device *dev = qdisc_dev(sch);
 
-	spin_lock(&cbs_list_lock);
-	list_del(&q->cbs_list);
-	spin_unlock(&cbs_list_lock);
+	/* Nothing to do if we couldn't create the underlying qdisc */
+	if (!q->qdisc)
+		return;
 
 	qdisc_watchdog_cancel(&q->watchdog);
 	cbs_disable_offload(dev, q);
 
-	if (q->qdisc)
-		qdisc_put(q->qdisc);
+	spin_lock(&cbs_list_lock);
+	list_del(&q->cbs_list);
+	spin_unlock(&cbs_list_lock);
+
+	qdisc_put(q->qdisc);
 }
 
 static int cbs_dump(struct Qdisc *sch, struct sk_buff *skb)
-- 
2.20.1


From a1707203a04b4cdbc42ddd6b88cc1c22629b4bc9 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 17 Sep 2019 10:39:49 -0700
Subject: [PATCH 26/37] ipv4: Revert removal of rt_uses_gateway

[ Upstream commit 77d5bc7e6a6cf8bbeca31aab7f0c5449a5eee762 ]

Julian noted that rt_uses_gateway has a more subtle use than 'is gateway
set':
    https://lore.kernel.org/netdev/alpine.LFD.2.21.1909151104060.2546@ja.home.ssi.bg/

Revert that part of the commit referenced in the Fixes tag.

Currently, there are no u8 holes in 'struct rtable'. There is a 4-byte hole
in the second cacheline which contains the gateway declaration. So move
rt_gw_family down to the gateway declarations since they are always used
together, and then re-use that u8 for rt_uses_gateway. End result is that
rtable size is unchanged.

Fixes: 1550c171935d ("ipv4: Prepare rtable for IPv6 gateway")
Reported-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/infiniband/core/addr.c  |  2 +-
 include/net/route.h             |  3 ++-
 net/ipv4/inet_connection_sock.c |  4 ++--
 net/ipv4/ip_forward.c           |  2 +-
 net/ipv4/ip_output.c            |  2 +-
 net/ipv4/route.c                | 36 +++++++++++++++++++--------------
 net/ipv4/xfrm4_policy.c         |  1 +
 7 files changed, 29 insertions(+), 21 deletions(-)

diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 9b76a8fcdd24..bf539c34ccd3 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -352,7 +352,7 @@ static bool has_gateway(const struct dst_entry *dst, sa_family_t family)
 
 	if (family == AF_INET) {
 		rt = container_of(dst, struct rtable, dst);
-		return rt->rt_gw_family == AF_INET;
+		return rt->rt_uses_gateway;
 	}
 
 	rt6 = container_of(dst, struct rt6_info, dst);
diff --git a/include/net/route.h b/include/net/route.h
index dfce19c9fa96..6c516840380d 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -53,10 +53,11 @@ struct rtable {
 	unsigned int		rt_flags;
 	__u16			rt_type;
 	__u8			rt_is_input;
-	u8			rt_gw_family;
+	__u8			rt_uses_gateway;
 
 	int			rt_iif;
 
+	u8			rt_gw_family;
 	/* Info on neighbour */
 	union {
 		__be32		rt_gw4;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index f5c163d4771b..a9183543ca30 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -560,7 +560,7 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk,
 	rt = ip_route_output_flow(net, fl4, sk);
 	if (IS_ERR(rt))
 		goto no_route;
-	if (opt && opt->opt.is_strictroute && rt->rt_gw_family)
+	if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway)
 		goto route_err;
 	rcu_read_unlock();
 	return &rt->dst;
@@ -598,7 +598,7 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
 	rt = ip_route_output_flow(net, fl4, sk);
 	if (IS_ERR(rt))
 		goto no_route;
-	if (opt && opt->opt.is_strictroute && rt->rt_gw_family)
+	if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway)
 		goto route_err;
 	return &rt->dst;
 
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 06f6f280b9ff..00ec819f949b 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -123,7 +123,7 @@ int ip_forward(struct sk_buff *skb)
 
 	rt = skb_rtable(skb);
 
-	if (opt->is_strictroute && rt->rt_gw_family)
+	if (opt->is_strictroute && rt->rt_uses_gateway)
 		goto sr_failed;
 
 	IPCB(skb)->flags |= IPSKB_FORWARDED;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index cc7ef0d05bbd..da521790cd63 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -499,7 +499,7 @@ int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
 	skb_dst_set_noref(skb, &rt->dst);
 
 packet_routed:
-	if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_gw_family)
+	if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_uses_gateway)
 		goto no_route;
 
 	/* OK, we know where to send it, allocate and build IP header. */
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index b6a6f18c3dd1..7dcce724c78b 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -635,6 +635,7 @@ static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnh
 
 	if (fnhe->fnhe_gw) {
 		rt->rt_flags |= RTCF_REDIRECTED;
+		rt->rt_uses_gateway = 1;
 		rt->rt_gw_family = AF_INET;
 		rt->rt_gw4 = fnhe->fnhe_gw;
 	}
@@ -1313,7 +1314,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst)
 	mtu = READ_ONCE(dst->dev->mtu);
 
 	if (unlikely(ip_mtu_locked(dst))) {
-		if (rt->rt_gw_family && mtu > 576)
+		if (rt->rt_uses_gateway && mtu > 576)
 			mtu = 576;
 	}
 
@@ -1569,6 +1570,7 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
 		struct fib_nh_common *nhc = FIB_RES_NHC(*res);
 
 		if (nhc->nhc_gw_family && nhc->nhc_scope == RT_SCOPE_LINK) {
+			rt->rt_uses_gateway = 1;
 			rt->rt_gw_family = nhc->nhc_gw_family;
 			/* only INET and INET6 are supported */
 			if (likely(nhc->nhc_gw_family == AF_INET))
@@ -1634,6 +1636,7 @@ struct rtable *rt_dst_alloc(struct net_device *dev,
 		rt->rt_iif = 0;
 		rt->rt_pmtu = 0;
 		rt->rt_mtu_locked = 0;
+		rt->rt_uses_gateway = 0;
 		rt->rt_gw_family = 0;
 		rt->rt_gw4 = 0;
 		INIT_LIST_HEAD(&rt->rt_uncached);
@@ -2694,6 +2697,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
 		rt->rt_genid = rt_genid_ipv4(net);
 		rt->rt_flags = ort->rt_flags;
 		rt->rt_type = ort->rt_type;
+		rt->rt_uses_gateway = ort->rt_uses_gateway;
 		rt->rt_gw_family = ort->rt_gw_family;
 		if (rt->rt_gw_family == AF_INET)
 			rt->rt_gw4 = ort->rt_gw4;
@@ -2778,21 +2782,23 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src,
 		if (nla_put_in_addr(skb, RTA_PREFSRC, fl4->saddr))
 			goto nla_put_failure;
 	}
-	if (rt->rt_gw_family == AF_INET &&
-	    nla_put_in_addr(skb, RTA_GATEWAY, rt->rt_gw4)) {
-		goto nla_put_failure;
-	} else if (rt->rt_gw_family == AF_INET6) {
-		int alen = sizeof(struct in6_addr);
-		struct nlattr *nla;
-		struct rtvia *via;
-
-		nla = nla_reserve(skb, RTA_VIA, alen + 2);
-		if (!nla)
+	if (rt->rt_uses_gateway) {
+		if (rt->rt_gw_family == AF_INET &&
+		    nla_put_in_addr(skb, RTA_GATEWAY, rt->rt_gw4)) {
 			goto nla_put_failure;
-
-		via = nla_data(nla);
-		via->rtvia_family = AF_INET6;
-		memcpy(via->rtvia_addr, &rt->rt_gw6, alen);
+		} else if (rt->rt_gw_family == AF_INET6) {
+			int alen = sizeof(struct in6_addr);
+			struct nlattr *nla;
+			struct rtvia *via;
+
+			nla = nla_reserve(skb, RTA_VIA, alen + 2);
+			if (!nla)
+				goto nla_put_failure;
+
+			via = nla_data(nla);
+			via->rtvia_family = AF_INET6;
+			memcpy(via->rtvia_addr, &rt->rt_gw6, alen);
+		}
 	}
 
 	expires = rt->dst.expires;
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index cdef8f9a3b01..35b84b52b702 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -85,6 +85,7 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
 	xdst->u.rt.rt_flags = rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST |
 					      RTCF_LOCAL);
 	xdst->u.rt.rt_type = rt->rt_type;
+	xdst->u.rt.rt_uses_gateway = rt->rt_uses_gateway;
 	xdst->u.rt.rt_gw_family = rt->rt_gw_family;
 	if (rt->rt_gw_family == AF_INET)
 		xdst->u.rt.rt_gw4 = rt->rt_gw4;
-- 
2.20.1


From edb5e49a96b90929c04610091d6b1c81101e3557 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Wed, 18 Sep 2019 18:44:43 -0700
Subject: [PATCH 27/37] net_sched: add policy validation for action attributes

[ Upstream commit 199ce850ce112315cfc68d42b694bcaa27b097b7 ]

Similar to commit 8b4c3cdd9dd8
("net: sched: Add policy validation for tc attributes"), we need
to add proper policy validation for TC action attributes too.

Cc: David Ahern <dsahern@gmail.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/sched/act_api.c | 34 ++++++++++++++++++----------------
 1 file changed, 18 insertions(+), 16 deletions(-)

diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 339712296164..2558f00f6b3e 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -831,6 +831,15 @@ static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb)
 	return c;
 }
 
+static const struct nla_policy tcf_action_policy[TCA_ACT_MAX + 1] = {
+	[TCA_ACT_KIND]		= { .type = NLA_NUL_STRING,
+				    .len = IFNAMSIZ - 1 },
+	[TCA_ACT_INDEX]		= { .type = NLA_U32 },
+	[TCA_ACT_COOKIE]	= { .type = NLA_BINARY,
+				    .len = TC_COOKIE_MAX_SIZE },
+	[TCA_ACT_OPTIONS]	= { .type = NLA_NESTED },
+};
+
 struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 				    struct nlattr *nla, struct nlattr *est,
 				    char *name, int ovr, int bind,
@@ -846,8 +855,8 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 	int err;
 
 	if (name == NULL) {
-		err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla, NULL,
-						  extack);
+		err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla,
+						  tcf_action_policy, extack);
 		if (err < 0)
 			goto err_out;
 		err = -EINVAL;
@@ -856,18 +865,9 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 			NL_SET_ERR_MSG(extack, "TC action kind must be specified");
 			goto err_out;
 		}
-		if (nla_strlcpy(act_name, kind, IFNAMSIZ) >= IFNAMSIZ) {
-			NL_SET_ERR_MSG(extack, "TC action name too long");
-			goto err_out;
-		}
-		if (tb[TCA_ACT_COOKIE]) {
-			int cklen = nla_len(tb[TCA_ACT_COOKIE]);
-
-			if (cklen > TC_COOKIE_MAX_SIZE) {
-				NL_SET_ERR_MSG(extack, "TC cookie size above the maximum");
-				goto err_out;
-			}
+		nla_strlcpy(act_name, kind, IFNAMSIZ);
 
+		if (tb[TCA_ACT_COOKIE]) {
 			cookie = nla_memdup_cookie(tb);
 			if (!cookie) {
 				NL_SET_ERR_MSG(extack, "No memory to generate TC cookie");
@@ -1098,7 +1098,8 @@ static struct tc_action *tcf_action_get_1(struct net *net, struct nlattr *nla,
 	int index;
 	int err;
 
-	err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla, NULL, extack);
+	err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla,
+					  tcf_action_policy, extack);
 	if (err < 0)
 		goto err_out;
 
@@ -1152,7 +1153,8 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
 
 	b = skb_tail_pointer(skb);
 
-	err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla, NULL, extack);
+	err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla,
+					  tcf_action_policy, extack);
 	if (err < 0)
 		goto err_out;
 
@@ -1440,7 +1442,7 @@ static struct nlattr *find_dump_kind(struct nlattr **nla)
 
 	if (tb[1] == NULL)
 		return NULL;
-	if (nla_parse_nested_deprecated(tb2, TCA_ACT_MAX, tb[1], NULL, NULL) < 0)
+	if (nla_parse_nested_deprecated(tb2, TCA_ACT_MAX, tb[1], tcf_action_policy, NULL) < 0)
 		return NULL;
 	kind = tb2[TCA_ACT_KIND];
 
-- 
2.20.1


From 749ca544bd42c0e5051d742b903a8dc26b19188c Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 25 Sep 2019 07:53:19 -0700
Subject: [PATCH 28/37] vrf: Do not attempt to create IPv6 mcast rule if IPv6
 is disabled

[ Upstream commit dac91170f8e9c73784af5fad6225e954b795601c ]

A user reported that vrf create fails when IPv6 is disabled at boot using
'ipv6.disable=1':
   https://bugzilla.kernel.org/show_bug.cgi?id=204903

The failure is adding fib rules at create time. Add RTNL_FAMILY_IP6MR to
the check in vrf_fib_rule if ipv6_mod_enabled is disabled.

Fixes: e4a38c0c4b27 ("ipv6: add vrf table handling code for ipv6 mcast")
Signed-off-by: David Ahern <dsahern@gmail.com>
Cc: Patrick Ruddy <pruddy@vyatta.att-mail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 6e84328bdd40..a4b38a980c3c 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -1154,7 +1154,8 @@ static int vrf_fib_rule(const struct net_device *dev, __u8 family, bool add_it)
 	struct sk_buff *skb;
 	int err;
 
-	if (family == AF_INET6 && !ipv6_mod_enabled())
+	if ((family == AF_INET6 || family == RTNL_FAMILY_IP6MR) &&
+	    !ipv6_mod_enabled())
 		return 0;
 
 	skb = nlmsg_new(vrf_fib_rule_nl_size(), GFP_KERNEL);
-- 
2.20.1


From 26e8bd0f8e5765f00daec0f22cfa928e7dd1e72b Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Wed, 11 Sep 2019 07:50:13 -0700
Subject: [PATCH 29/37] net/mlx5e: Fix traffic duplication in ethtool steering

[ Upstream commit d22fcc806b84b9818de08b32e494f3c05dd236c7 ]

Before this patch, when adding multiple ethtool steering rules with
identical classification, the driver used to append the new destination
to the already existing hw rule, which caused the hw to forward the
traffic to all destinations (rx queues).

Here we avoid this by setting the "no append" mlx5 fs core flag when
adding a new ethtool rule.

Fixes: 6dc6071cfcde ("net/mlx5e: Add ethtool flow steering support")
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index 94304abc49e9..39e90b873319 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -399,10 +399,10 @@ add_ethtool_flow_rule(struct mlx5e_priv *priv,
 		      struct mlx5_flow_table *ft,
 		      struct ethtool_rx_flow_spec *fs)
 {
+	struct mlx5_flow_act flow_act = { .flags = FLOW_ACT_NO_APPEND };
 	struct mlx5_flow_destination *dst = NULL;
-	struct mlx5_flow_act flow_act = {0};
-	struct mlx5_flow_spec *spec;
 	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_spec *spec;
 	int err = 0;
 
 	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
-- 
2.20.1


From df2a151a3b392f820e0e57b1a3d84650747525df Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 18 Sep 2019 12:57:04 -0700
Subject: [PATCH 30/37] net: sched: fix possible crash in tcf_action_destroy()

[ Upstream commit 3d66b89c30f9220a72e92847768fc8ba4d027d88 ]

If the allocation done in tcf_exts_init() failed,
we end up with a NULL pointer in exts->actions.

kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] PREEMPT SMP KASAN
CPU: 1 PID: 8198 Comm: syz-executor.3 Not tainted 5.3.0-rc8+ #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:tcf_action_destroy+0x71/0x160 net/sched/act_api.c:705
Code: c3 08 44 89 ee e8 4f cb bb fb 41 83 fd 20 0f 84 c9 00 00 00 e8 c0 c9 bb fb 48 89 d8 48 b9 00 00 00 00 00 fc ff df 48 c1 e8 03 <80> 3c 08 00 0f 85 c0 00 00 00 4c 8b 33 4d 85 f6 0f 84 9d 00 00 00
RSP: 0018:ffff888096e16ff0 EFLAGS: 00010246
RAX: 0000000000000000 RBX: 0000000000000000 RCX: dffffc0000000000
RDX: 0000000000040000 RSI: ffffffff85b6ab30 RDI: 0000000000000000
RBP: ffff888096e17020 R08: ffff8880993f6140 R09: fffffbfff11cae67
R10: fffffbfff11cae66 R11: ffffffff88e57333 R12: 0000000000000000
R13: 0000000000000000 R14: ffff888096e177a0 R15: 0000000000000001
FS:  00007f62bc84a700(0000) GS:ffff8880ae900000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000758040 CR3: 0000000088b64000 CR4: 00000000001426e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 tcf_exts_destroy+0x38/0xb0 net/sched/cls_api.c:3030
 tcindex_set_parms+0xf7f/0x1e50 net/sched/cls_tcindex.c:488
 tcindex_change+0x230/0x318 net/sched/cls_tcindex.c:519
 tc_new_tfilter+0xa4b/0x1c70 net/sched/cls_api.c:2152
 rtnetlink_rcv_msg+0x838/0xb00 net/core/rtnetlink.c:5214
 netlink_rcv_skb+0x177/0x450 net/netlink/af_netlink.c:2477
 rtnetlink_rcv+0x1d/0x30 net/core/rtnetlink.c:5241
 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
 netlink_unicast+0x531/0x710 net/netlink/af_netlink.c:1328
 netlink_sendmsg+0x8a5/0xd60 net/netlink/af_netlink.c:1917
 sock_sendmsg_nosec net/socket.c:637 [inline]
 sock_sendmsg+0xd7/0x130 net/socket.c:657
 ___sys_sendmsg+0x3e2/0x920 net/socket.c:2311
 __sys_sendmmsg+0x1bf/0x4d0 net/socket.c:2413
 __do_sys_sendmmsg net/socket.c:2442 [inline]

Fixes: 90b73b77d08e ("net: sched: change action API to use array of pointers to actions")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Vlad Buslov <vladbu@mellanox.com>
Cc: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index efd3cfb80a2a..9aef93300f1c 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -3027,8 +3027,10 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb)
 void tcf_exts_destroy(struct tcf_exts *exts)
 {
 #ifdef CONFIG_NET_CLS_ACT
-	tcf_action_destroy(exts->actions, TCA_ACT_UNBIND);
-	kfree(exts->actions);
+	if (exts->actions) {
+		tcf_action_destroy(exts->actions, TCA_ACT_UNBIND);
+		kfree(exts->actions);
+	}
 	exts->nr_actions = 0;
 #endif
 }
-- 
2.20.1


From 49a3681c17d6b6a69f80215edf812183e7dadaf3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 26 Sep 2019 15:42:51 -0700
Subject: [PATCH 31/37] tcp: better handle TCP_USER_TIMEOUT in SYN_SENT state

[ Upstream commit a66b10c05ee2d744189e9a2130394b070883d289 ]

Yuchung Cheng and Marek Majkowski independently reported a weird
behavior of TCP_USER_TIMEOUT option when used at connect() time.

When the TCP_USER_TIMEOUT is reached, tcp_write_timeout()
believes the flow should live, and the following condition
in tcp_clamp_rto_to_user_timeout() programs one jiffie timers :

    remaining = icsk->icsk_user_timeout - elapsed;
    if (remaining <= 0)
        return 1; /* user timeout has passed; fire ASAP */

This silly situation ends when the max syn rtx count is reached.

This patch makes sure we honor both TCP_SYNCNT and TCP_USER_TIMEOUT,
avoiding these spurious SYN packets.

Fixes: b701a99e431d ("tcp: Add tcp_clamp_rto_to_user_timeout() helper to improve accuracy")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Yuchung Cheng <ycheng@google.com>
Reported-by: Marek Majkowski <marek@cloudflare.com>
Cc: Jon Maxwell <jmaxwell37@gmail.com>
Link: https://marc.info/?l=linux-netdev&m=156940118307949&w=2
Acked-by: Jon Maxwell <jmaxwell37@gmail.com>
Tested-by: Marek Majkowski <marek@cloudflare.com>
Signed-off-by: Marek Majkowski <marek@cloudflare.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_timer.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index c801cd37cc2a..3e8b38c73d8c 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -210,7 +210,7 @@ static int tcp_write_timeout(struct sock *sk)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct net *net = sock_net(sk);
-	bool expired, do_reset;
+	bool expired = false, do_reset;
 	int retry_until;
 
 	if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
@@ -242,9 +242,10 @@ static int tcp_write_timeout(struct sock *sk)
 			if (tcp_out_of_resources(sk, do_reset))
 				return 1;
 		}
+	}
+	if (!expired)
 		expired = retransmits_timed_out(sk, retry_until,
 						icsk->icsk_user_timeout);
-	}
 	tcp_fastopen_active_detect_blackhole(sk, expired);
 
 	if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RTO_CB_FLAG))
-- 
2.20.1


From 87fb9c6925f050629bdc864e2d78b8de087fe2cb Mon Sep 17 00:00:00 2001
From: Bodong Wang <bodong@mellanox.com>
Date: Mon, 26 Aug 2019 16:34:12 -0500
Subject: [PATCH 32/37] net/mlx5: Add device ID of upcoming BlueField-2

[ Upstream commit d19a79ee38c8fda6d297e4227e80db8bf51c71a6 ]

Add the device ID of upcoming BlueField-2 integrated ConnectX-6 Dx
network controller. Its VFs will be using the generic VF device ID:
0x101e "ConnectX Family mlx5Gen Virtual Function".

Fixes: 2e9d3e83ab82 ("net/mlx5: Update the list of the PCI supported devices")
Signed-off-by: Bodong Wang <bodong@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index b15b27a497fc..fda4964c5cf4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1554,6 +1554,7 @@ static const struct pci_device_id mlx5_core_pci_table[] = {
 	{ PCI_VDEVICE(MELLANOX, 0x101e), MLX5_PCI_DEV_IS_VF},	/* ConnectX Family mlx5Gen Virtual Function */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d2) },			/* BlueField integrated ConnectX-5 network controller */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d3), MLX5_PCI_DEV_IS_VF},	/* BlueField integrated ConnectX-5 network controller VF */
+	{ PCI_VDEVICE(MELLANOX, 0xa2d6) },			/* BlueField-2 integrated ConnectX-6 Dx network controller */
 	{ 0, }
 };
 
-- 
2.20.1


From 904ac0328a654be83301fd77363b22cfa5e9ee57 Mon Sep 17 00:00:00 2001
From: Ori Nimron <orinimron123@gmail.com>
Date: Fri, 20 Sep 2019 09:35:45 +0200
Subject: [PATCH 33/37] mISDN: enforce CAP_NET_RAW for raw sockets

[ Upstream commit b91ee4aa2a2199ba4d4650706c272985a5a32d80 ]

When creating a raw AF_ISDN socket, CAP_NET_RAW needs to be checked
first.

Signed-off-by: Ori Nimron <orinimron123@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/mISDN/socket.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c
index c6ba37df4b9d..dff4132b3702 100644
--- a/drivers/isdn/mISDN/socket.c
+++ b/drivers/isdn/mISDN/socket.c
@@ -754,6 +754,8 @@ base_sock_create(struct net *net, struct socket *sock, int protocol, int kern)
 
 	if (sock->type != SOCK_RAW)
 		return -ESOCKTNOSUPPORT;
+	if (!capable(CAP_NET_RAW))
+		return -EPERM;
 
 	sk = sk_alloc(net, PF_ISDN, GFP_KERNEL, &mISDN_proto, kern);
 	if (!sk)
-- 
2.20.1


From 77799297fc68e920a4915965fe863da3370e1c5c Mon Sep 17 00:00:00 2001
From: Ori Nimron <orinimron123@gmail.com>
Date: Fri, 20 Sep 2019 09:35:46 +0200
Subject: [PATCH 34/37] appletalk: enforce CAP_NET_RAW for raw sockets

[ Upstream commit 6cc03e8aa36c51f3b26a0d21a3c4ce2809c842ac ]

When creating a raw AF_APPLETALK socket, CAP_NET_RAW needs to be checked
first.

Signed-off-by: Ori Nimron <orinimron123@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/appletalk/ddp.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index a8cb6b2e20c1..5a203acdcae5 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1023,6 +1023,11 @@ static int atalk_create(struct net *net, struct socket *sock, int protocol,
 	 */
 	if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM)
 		goto out;
+
+	rc = -EPERM;
+	if (sock->type == SOCK_RAW && !kern && !capable(CAP_NET_RAW))
+		goto out;
+
 	rc = -ENOMEM;
 	sk = sk_alloc(net, PF_APPLETALK, GFP_KERNEL, &ddp_proto, kern);
 	if (!sk)
-- 
2.20.1


From 6f722277356a9beab819fde6376d0668b50f016d Mon Sep 17 00:00:00 2001
From: Ori Nimron <orinimron123@gmail.com>
Date: Fri, 20 Sep 2019 09:35:47 +0200
Subject: [PATCH 35/37] ax25: enforce CAP_NET_RAW for raw sockets

[ Upstream commit 0614e2b73768b502fc32a75349823356d98aae2c ]

When creating a raw AF_AX25 socket, CAP_NET_RAW needs to be checked
first.

Signed-off-by: Ori Nimron <orinimron123@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ax25/af_ax25.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index ca5207767dc2..bb222b882b67 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -855,6 +855,8 @@ static int ax25_create(struct net *net, struct socket *sock, int protocol,
 		break;
 
 	case SOCK_RAW:
+		if (!capable(CAP_NET_RAW))
+			return -EPERM;
 		break;
 	default:
 		return -ESOCKTNOSUPPORT;
-- 
2.20.1


From f41cc5908f96e68736631e2ee487bea925ea17b1 Mon Sep 17 00:00:00 2001
From: Ori Nimron <orinimron123@gmail.com>
Date: Fri, 20 Sep 2019 09:35:48 +0200
Subject: [PATCH 36/37] ieee802154: enforce CAP_NET_RAW for raw sockets

[ Upstream commit e69dbd4619e7674c1679cba49afd9dd9ac347eef ]

When creating a raw AF_IEEE802154 socket, CAP_NET_RAW needs to be
checked first.

Signed-off-by: Ori Nimron <orinimron123@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Stefan Schmidt <stefan@datenfreihafen.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ieee802154/socket.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c
index badc5cfe4dc6..d93d4531aa9b 100644
--- a/net/ieee802154/socket.c
+++ b/net/ieee802154/socket.c
@@ -1008,6 +1008,9 @@ static int ieee802154_create(struct net *net, struct socket *sock,
 
 	switch (sock->type) {
 	case SOCK_RAW:
+		rc = -EPERM;
+		if (!capable(CAP_NET_RAW))
+			goto out;
 		proto = &ieee802154_raw_prot;
 		ops = &ieee802154_raw_ops;
 		break;
-- 
2.20.1


From 7c1d0b970ff2dae9c26384ae250c5c713508a7a1 Mon Sep 17 00:00:00 2001
From: Ori Nimron <orinimron123@gmail.com>
Date: Fri, 20 Sep 2019 09:35:49 +0200
Subject: [PATCH 37/37] nfc: enforce CAP_NET_RAW for raw sockets

[ Upstream commit 3a359798b176183ef09efb7a3dc59abad1cc7104 ]

When creating a raw AF_NFC socket, CAP_NET_RAW needs to be checked
first.

Signed-off-by: Ori Nimron <orinimron123@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/nfc/llcp_sock.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index 9b8742947aff..8dfea26536c9 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -1004,10 +1004,13 @@ static int llcp_sock_create(struct net *net, struct socket *sock,
 	    sock->type != SOCK_RAW)
 		return -ESOCKTNOSUPPORT;
 
-	if (sock->type == SOCK_RAW)
+	if (sock->type == SOCK_RAW) {
+		if (!capable(CAP_NET_RAW))
+			return -EPERM;
 		sock->ops = &llcp_rawsock_ops;
-	else
+	} else {
 		sock->ops = &llcp_sock_ops;
+	}
 
 	sk = nfc_llcp_sock_alloc(sock, sock->type, GFP_ATOMIC, kern);
 	if (sk == NULL)
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Sun, Sep 29, 2019 at 03:39:52PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v5.2
> and v5.3 -stable, respectively.

Now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 102 bytes --]


Please queue up the following networking bug fixes for v5.2 and
v5.3 -stable, respectively.

Thanks!

[-- Attachment #2: net_52.mbox --]
[-- Type: Application/Octet-Stream, Size: 70899 bytes --]

From 0cfc981a448cbb5ccf42c2fef6dfce52dc94eae2 Mon Sep 17 00:00:00 2001
From: Vishal Kulkarni <vishal@chelsio.com>
Date: Fri, 4 Oct 2019 04:06:15 +0530
Subject: [PATCH 01/25] cxgb4:Fix out-of-bounds MSI-X info array access

[ Upstream commit 6b517374f4ea5a3c6e307e1219ec5f35d42e6d00 ]

When fetching free MSI-X vectors for ULDs, check for the error code
before accessing MSI-X info array. Otherwise, an out-of-bounds access is
attempted, which results in kernel panic.

Fixes: 94cdb8bb993a ("cxgb4: Add support for dynamic allocation of resources for ULD")
Signed-off-by: Shahjada Abul Husain <shahjada@chelsio.com>
Signed-off-by: Vishal Kulkarni <vishal@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
index 6c685b920713..bf17cf3ef613 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
@@ -137,13 +137,12 @@ static int uldrx_handler(struct sge_rspq *q, const __be64 *rsp,
 static int alloc_uld_rxqs(struct adapter *adap,
 			  struct sge_uld_rxq_info *rxq_info, bool lro)
 {
-	struct sge *s = &adap->sge;
 	unsigned int nq = rxq_info->nrxq + rxq_info->nciq;
+	int i, err, msi_idx, que_idx = 0, bmap_idx = 0;
 	struct sge_ofld_rxq *q = rxq_info->uldrxq;
 	unsigned short *ids = rxq_info->rspq_id;
-	unsigned int bmap_idx = 0;
+	struct sge *s = &adap->sge;
 	unsigned int per_chan;
-	int i, err, msi_idx, que_idx = 0;
 
 	per_chan = rxq_info->nrxq / adap->params.nports;
 
@@ -161,6 +160,10 @@ static int alloc_uld_rxqs(struct adapter *adap,
 
 		if (msi_idx >= 0) {
 			bmap_idx = get_msix_idx_from_bmap(adap);
+			if (bmap_idx < 0) {
+				err = -ENOSPC;
+				goto freeout;
+			}
 			msi_idx = adap->msix_info_ulds[bmap_idx].idx;
 		}
 		err = t4_sge_alloc_rxq(adap, &q->rspq, false,
-- 
2.20.1


From 10c6d1e9bca56418fefe6d8a83cf8d9f5faf1e5a Mon Sep 17 00:00:00 2001
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Fri, 27 Sep 2019 14:58:20 +0800
Subject: [PATCH 02/25] erspan: remove the incorrect mtu limit for erspan

[ Upstream commit 0e141f757b2c78c983df893e9993313e2dc21e38 ]

erspan driver calls ether_setup(), after commit 61e84623ace3
("net: centralize net_device min/max MTU checking"), the range
of mtu is [min_mtu, max_mtu], which is [68, 1500] by default.

It causes the dev mtu of the erspan device to not be greater
than 1500, this limit value is not correct for ipgre tap device.

Tested:
Before patch:
# ip link set erspan0 mtu 1600
Error: mtu greater than device maximum.
After patch:
# ip link set erspan0 mtu 1600
# ip -d link show erspan0
21: erspan0@NONE: <BROADCAST,MULTICAST> mtu 1600 qdisc noop state DOWN
mode DEFAULT group default qlen 1000
    link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff promiscuity 0 minmtu 68 maxmtu 0

Fixes: 61e84623ace3 ("net: centralize net_device min/max MTU checking")
Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_gre.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index a53a543fe055..52690bb3e40f 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1446,6 +1446,7 @@ static void erspan_setup(struct net_device *dev)
 	struct ip_tunnel *t = netdev_priv(dev);
 
 	ether_setup(dev);
+	dev->max_mtu = 0;
 	dev->netdev_ops = &erspan_netdev_ops;
 	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
-- 
2.20.1


From 22fb16bf26228cf6fadfa60147bf7cb389b6c6a9 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 30 Sep 2019 17:12:41 +0200
Subject: [PATCH 03/25] hso: fix NULL-deref on tty open

[ Upstream commit 8353da9fa69722b54cba82b2ec740afd3d438748 ]

Fix NULL-pointer dereference on tty open due to a failure to handle a
missing interrupt-in endpoint when probing modem ports:

	BUG: kernel NULL pointer dereference, address: 0000000000000006
	...
	RIP: 0010:tiocmget_submit_urb+0x1c/0xe0 [hso]
	...
	Call Trace:
	hso_start_serial_device+0xdc/0x140 [hso]
	hso_serial_open+0x118/0x1b0 [hso]
	tty_open+0xf1/0x490

Fixes: 542f54823614 ("tty: Modem functions for the HSO driver")
Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/hso.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c
index ce78714f536f..a505b2ab88b8 100644
--- a/drivers/net/usb/hso.c
+++ b/drivers/net/usb/hso.c
@@ -2620,14 +2620,18 @@ static struct hso_device *hso_create_bulk_serial_device(
 		 */
 		if (serial->tiocmget) {
 			tiocmget = serial->tiocmget;
+			tiocmget->endp = hso_get_ep(interface,
+						    USB_ENDPOINT_XFER_INT,
+						    USB_DIR_IN);
+			if (!tiocmget->endp) {
+				dev_err(&interface->dev, "Failed to find INT IN ep\n");
+				goto exit;
+			}
+
 			tiocmget->urb = usb_alloc_urb(0, GFP_KERNEL);
 			if (tiocmget->urb) {
 				mutex_init(&tiocmget->mutex);
 				init_waitqueue_head(&tiocmget->waitq);
-				tiocmget->endp = hso_get_ep(
-					interface,
-					USB_ENDPOINT_XFER_INT,
-					USB_DIR_IN);
 			} else
 				hso_free_tiomget(serial);
 		}
-- 
2.20.1


From 339394b5afe25f0b50405a2272c7af1ca7d8e784 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 2 Oct 2019 09:38:55 -0700
Subject: [PATCH 04/25] ipv6: drop incoming packets having a v4mapped source
 address

[ Upstream commit 6af1799aaf3f1bc8defedddfa00df3192445bbf3 ]

This began with a syzbot report. syzkaller was injecting
IPv6 TCP SYN packets having a v4mapped source address.

After an unsuccessful 4-tuple lookup, TCP creates a request
socket (SYN_RECV) and calls reqsk_queue_hash_req()

reqsk_queue_hash_req() calls sk_ehashfn(sk)

At this point we have AF_INET6 sockets, and the heuristic
used by sk_ehashfn() to either hash the IPv4 or IPv6 addresses
is to use ipv6_addr_v4mapped(&sk->sk_v6_daddr)

For the particular spoofed packet, we end up hashing V4 addresses
which were not initialized by the TCP IPv6 stack, so KMSAN fired
a warning.

I first fixed sk_ehashfn() to test both source and destination addresses,
but then faced various problems, including user-space programs
like packetdrill that had similar assumptions.

Instead of trying to fix the whole ecosystem, it is better
to admit that we have a dual stack behavior, and that we
can not build linux kernels without V4 stack anyway.

The dual stack API automatically forces the traffic to be IPv4
if v4mapped addresses are used at bind() or connect(), so it makes
no sense to allow IPv6 traffic to use the same v4mapped class.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Florian Westphal <fw@strlen.de>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_input.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index fa014d5f1732..a593aaf25748 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -221,6 +221,16 @@ static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev,
 	if (ipv6_addr_is_multicast(&hdr->saddr))
 		goto err;
 
+	/* While RFC4291 is not explicit about v4mapped addresses
+	 * in IPv6 headers, it seems clear linux dual-stack
+	 * model can not deal properly with these.
+	 * Security models could be fooled by ::ffff:127.0.0.1 for example.
+	 *
+	 * https://tools.ietf.org/html/draft-itojun-v6ops-v4mapped-harmful-02
+	 */
+	if (ipv6_addr_v4mapped(&hdr->saddr))
+		goto err;
+
 	skb->transport_header = skb->network_header + sizeof(*hdr);
 	IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);
 
-- 
2.20.1


From 3e339ff05c9936db4147156fb5b3cf4c1c55282b Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Fri, 4 Oct 2019 08:03:09 -0700
Subject: [PATCH 05/25] ipv6: Handle missing host route in __ipv6_ifa_notify

[ Upstream commit 2d819d250a1393a3e725715425ab70a0e0772a71 ]

Rajendra reported a kernel panic when a link was taken down:

    [ 6870.263084] BUG: unable to handle kernel NULL pointer dereference at 00000000000000a8
    [ 6870.271856] IP: [<ffffffff8efc5764>] __ipv6_ifa_notify+0x154/0x290

    <snip>

    [ 6870.570501] Call Trace:
    [ 6870.573238] [<ffffffff8efc58c6>] ? ipv6_ifa_notify+0x26/0x40
    [ 6870.579665] [<ffffffff8efc98ec>] ? addrconf_dad_completed+0x4c/0x2c0
    [ 6870.586869] [<ffffffff8efe70c6>] ? ipv6_dev_mc_inc+0x196/0x260
    [ 6870.593491] [<ffffffff8efc9c6a>] ? addrconf_dad_work+0x10a/0x430
    [ 6870.600305] [<ffffffff8f01ade4>] ? __switch_to_asm+0x34/0x70
    [ 6870.606732] [<ffffffff8ea93a7a>] ? process_one_work+0x18a/0x430
    [ 6870.613449] [<ffffffff8ea93d6d>] ? worker_thread+0x4d/0x490
    [ 6870.619778] [<ffffffff8ea93d20>] ? process_one_work+0x430/0x430
    [ 6870.626495] [<ffffffff8ea99dd9>] ? kthread+0xd9/0xf0
    [ 6870.632145] [<ffffffff8f01ade4>] ? __switch_to_asm+0x34/0x70
    [ 6870.638573] [<ffffffff8ea99d00>] ? kthread_park+0x60/0x60
    [ 6870.644707] [<ffffffff8f01ae77>] ? ret_from_fork+0x57/0x70
    [ 6870.650936] Code: 31 c0 31 d2 41 b9 20 00 08 02 b9 09 00 00 0

addrconf_dad_work is kicked to be scheduled when a device is brought
up. There is a race between addrcond_dad_work getting scheduled and
taking the rtnl lock and a process taking the link down (under rtnl).
The latter removes the host route from the inet6_addr as part of
addrconf_ifdown which is run for NETDEV_DOWN. The former attempts
to use the host route in __ipv6_ifa_notify. If the down event removes
the host route due to the race to the rtnl, then the BUG listed above
occurs.

Since the DAD sequence can not be aborted, add a check for the missing
host route in __ipv6_ifa_notify. The only way this should happen is due
to the previously mentioned race. The host route is created when the
address is added to an interface; it is only removed on a down event
where the address is kept. Add a warning if the host route is missing
AND the device is up; this is a situation that should never happen.

Fixes: f1705ec197e7 ("net: ipv6: Make address flushing on ifdown optional")
Reported-by: Rajendra Dendukuri <rajendra.dendukuri@broadcom.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 2454fce6fbfa..c94bc461e268 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5962,13 +5962,20 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
 	switch (event) {
 	case RTM_NEWADDR:
 		/*
-		 * If the address was optimistic
-		 * we inserted the route at the start of
-		 * our DAD process, so we don't need
-		 * to do it again
+		 * If the address was optimistic we inserted the route at the
+		 * start of our DAD process, so we don't need to do it again.
+		 * If the device was taken down in the middle of the DAD
+		 * cycle there is a race where we could get here without a
+		 * host route, so nothing to insert. That will be fixed when
+		 * the device is brought up.
 		 */
-		if (!rcu_access_pointer(ifp->rt->fib6_node))
+		if (ifp->rt && !rcu_access_pointer(ifp->rt->fib6_node)) {
 			ip6_ins_rt(net, ifp->rt);
+		} else if (!ifp->rt && (ifp->idev->dev->flags & IFF_UP)) {
+			pr_warn("BUG: Address %pI6c on device %s is missing its host route.\n",
+				&ifp->addr, ifp->idev->dev->name);
+		}
+
 		if (ifp->idev->cnf.forwarding)
 			addrconf_join_anycast(ifp);
 		if (!ipv6_addr_any(&ifp->peer_addr))
-- 
2.20.1


From 2fb3bbd0870334252539ad59d663d615b29284fd Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 4 Oct 2019 15:11:17 +0200
Subject: [PATCH 06/25] net: ipv4: avoid mixed n_redirects and rate_tokens
 usage

[ Upstream commit b406472b5ad79ede8d10077f0c8f05505ace8b6d ]

Since commit c09551c6ff7f ("net: ipv4: use a dedicated counter
for icmp_v4 redirect packets") we use 'n_redirects' to account
for redirect packets, but we still use 'rate_tokens' to compute
the redirect packets exponential backoff.

If the device sent to the relevant peer any ICMP error packet
after sending a redirect, it will also update 'rate_token' according
to the leaking bucket schema; typically 'rate_token' will raise
above BITS_PER_LONG and the redirect packets backoff algorithm
will produce undefined behavior.

Fix the issue using 'n_redirects' to compute the exponential backoff
in ip_rt_send_redirect().

Note that we still clear rate_tokens after a redirect silence period,
to avoid changing an established behaviour.

The root cause predates git history; before the mentioned commit in
the critical scenario, the kernel stopped sending redirects, after
the mentioned commit the behavior more randomic.

Reported-by: Xiumei Mu <xmu@redhat.com>
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Fixes: c09551c6ff7f ("net: ipv4: use a dedicated counter for icmp_v4 redirect packets")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index f6b7b11835ee..148dfcb5cbd9 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -915,16 +915,15 @@ void ip_rt_send_redirect(struct sk_buff *skb)
 	if (peer->rate_tokens == 0 ||
 	    time_after(jiffies,
 		       (peer->rate_last +
-			(ip_rt_redirect_load << peer->rate_tokens)))) {
+			(ip_rt_redirect_load << peer->n_redirects)))) {
 		__be32 gw = rt_nexthop(rt, ip_hdr(skb)->daddr);
 
 		icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw);
 		peer->rate_last = jiffies;
-		++peer->rate_tokens;
 		++peer->n_redirects;
 #ifdef CONFIG_IP_ROUTE_VERBOSE
 		if (log_martians &&
-		    peer->rate_tokens == ip_rt_redirect_number)
+		    peer->n_redirects == ip_rt_redirect_number)
 			net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n",
 					     &ip_hdr(skb)->saddr, inet_iif(skb),
 					     &ip_hdr(skb)->daddr, &gw);
-- 
2.20.1


From 40ca8c78894fb04343bffce8920b37e5c5bf3b6d Mon Sep 17 00:00:00 2001
From: Navid Emamdoost <navid.emamdoost@gmail.com>
Date: Fri, 4 Oct 2019 15:24:39 -0500
Subject: [PATCH 07/25] net: qlogic: Fix memory leak in ql_alloc_large_buffers

[ Upstream commit 1acb8f2a7a9f10543868ddd737e37424d5c36cf4 ]

In ql_alloc_large_buffers, a new skb is allocated via netdev_alloc_skb.
This skb should be released if pci_dma_mapping_error fails.

Fixes: 0f8ab89e825f ("qla3xxx: Check return code from pci_map_single() in ql_release_to_lrg_buf_free_list(), ql_populate_free_queue(), ql_alloc_large_buffers(), and ql3xxx_send()")
Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qla3xxx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c
index 457444894d80..b4b8ba00ee01 100644
--- a/drivers/net/ethernet/qlogic/qla3xxx.c
+++ b/drivers/net/ethernet/qlogic/qla3xxx.c
@@ -2787,6 +2787,7 @@ static int ql_alloc_large_buffers(struct ql3_adapter *qdev)
 				netdev_err(qdev->ndev,
 					   "PCI mapping failed with error: %d\n",
 					   err);
+				dev_kfree_skb_irq(skb);
 				ql_free_large_buffers(qdev);
 				return -ENOMEM;
 			}
-- 
2.20.1


From fe260bf958b2e45b2755477041910bc2c664efde Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Sun, 29 Sep 2019 02:01:39 +0300
Subject: [PATCH 08/25] net: sched: taprio: Fix potential integer overflow in
 taprio_set_picos_per_byte

[ Upstream commit 68ce6688a5baefde30914fc07fc27292dbbe8320 ]

The speed divisor is used in a context expecting an s64, but it is
evaluated using 32-bit arithmetic.

To avoid that happening, instead of multiplying by 1,000,000 in the
first place, simplify the fraction and do a standard 32 bit division
instead.

Fixes: f04b514c0ce2 ("taprio: Set default link speed to 10 Mbps in taprio_set_picos_per_byte")
Reported-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Acked-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_taprio.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 11c2873ec68b..f3f959f5458b 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -672,8 +672,7 @@ static void taprio_set_picos_per_byte(struct net_device *dev,
 		speed = ecmd.base.speed;
 
 skip:
-	picos_per_byte = div64_s64(NSEC_PER_SEC * 1000LL * 8,
-				   speed * 1000 * 1000);
+	picos_per_byte = (USEC_PER_SEC * 8) / speed;
 
 	atomic64_set(&q->picos_per_byte, picos_per_byte);
 	netdev_dbg(dev, "taprio: set %s's picos_per_byte to: %lld, linkspeed: %d\n",
-- 
2.20.1


From e3bb4ac83f286ef90fdafbcd79e8cdf0fe5ca27d Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Fri, 27 Sep 2019 16:00:31 -0700
Subject: [PATCH 09/25] net: Unpublish sk from sk_reuseport_cb before call_rcu

[ Upstream commit 8c7138b33e5c690c308b2a7085f6313fdcb3f616 ]

The "reuse->sock[]" array is shared by multiple sockets.  The going away
sk must unpublish itself from "reuse->sock[]" before making call_rcu()
call.  However, this unpublish-action is currently done after a grace
period and it may cause use-after-free.

The fix is to move reuseport_detach_sock() to sk_destruct().
Due to the above reason, any socket with sk_reuseport_cb has
to go through the rcu grace period before freeing it.

It is a rather old bug (~3 yrs).  The Fixes tag is not necessary
the right commit but it is the one that introduced the SOCK_RCU_FREE
logic and this fix is depending on it.

Fixes: a4298e4522d6 ("net: add SOCK_RCU_FREE socket flag")
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index df7b38b60164..3d54153b8325 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1696,8 +1696,6 @@ static void __sk_destruct(struct rcu_head *head)
 		sk_filter_uncharge(sk, filter);
 		RCU_INIT_POINTER(sk->sk_filter, NULL);
 	}
-	if (rcu_access_pointer(sk->sk_reuseport_cb))
-		reuseport_detach_sock(sk);
 
 	sock_disable_timestamp(sk, SK_FLAGS_TIMESTAMP);
 
@@ -1724,7 +1722,14 @@ static void __sk_destruct(struct rcu_head *head)
 
 void sk_destruct(struct sock *sk)
 {
-	if (sock_flag(sk, SOCK_RCU_FREE))
+	bool use_call_rcu = sock_flag(sk, SOCK_RCU_FREE);
+
+	if (rcu_access_pointer(sk->sk_reuseport_cb)) {
+		reuseport_detach_sock(sk);
+		use_call_rcu = true;
+	}
+
+	if (use_call_rcu)
 		call_rcu(&sk->sk_rcu, __sk_destruct);
 	else
 		__sk_destruct(&sk->sk_rcu);
-- 
2.20.1


From cee133b3d1c6b353c5603e1b1d953e0b0efbbb7a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 4 Oct 2019 11:08:34 -0700
Subject: [PATCH 10/25] nfc: fix memory leak in llcp_sock_bind()

[ Upstream commit a0c2dc1fe63e2869b74c1c7f6a81d1745c8a695d ]

sysbot reported a memory leak after a bind() has failed.

While we are at it, abort the operation if kmemdup() has failed.

BUG: memory leak
unreferenced object 0xffff888105d83ec0 (size 32):
  comm "syz-executor067", pid 7207, jiffies 4294956228 (age 19.430s)
  hex dump (first 32 bytes):
    00 69 6c 65 20 72 65 61 64 00 6e 65 74 3a 5b 34  .ile read.net:[4
    30 32 36 35 33 33 30 39 37 5d 00 00 00 00 00 00  026533097]......
  backtrace:
    [<0000000036bac473>] kmemleak_alloc_recursive /./include/linux/kmemleak.h:43 [inline]
    [<0000000036bac473>] slab_post_alloc_hook /mm/slab.h:522 [inline]
    [<0000000036bac473>] slab_alloc /mm/slab.c:3319 [inline]
    [<0000000036bac473>] __do_kmalloc /mm/slab.c:3653 [inline]
    [<0000000036bac473>] __kmalloc_track_caller+0x169/0x2d0 /mm/slab.c:3670
    [<000000000cd39d07>] kmemdup+0x27/0x60 /mm/util.c:120
    [<000000008e57e5fc>] kmemdup /./include/linux/string.h:432 [inline]
    [<000000008e57e5fc>] llcp_sock_bind+0x1b3/0x230 /net/nfc/llcp_sock.c:107
    [<000000009cb0b5d3>] __sys_bind+0x11c/0x140 /net/socket.c:1647
    [<00000000492c3bbc>] __do_sys_bind /net/socket.c:1658 [inline]
    [<00000000492c3bbc>] __se_sys_bind /net/socket.c:1656 [inline]
    [<00000000492c3bbc>] __x64_sys_bind+0x1e/0x30 /net/socket.c:1656
    [<0000000008704b2a>] do_syscall_64+0x76/0x1a0 /arch/x86/entry/common.c:296
    [<000000009f4c57a4>] entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 30cc4587659e ("NFC: Move LLCP code to the NFC top level diirectory")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/nfc/llcp_sock.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index 8dfea26536c9..ccdd790e163a 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -107,9 +107,14 @@ static int llcp_sock_bind(struct socket *sock, struct sockaddr *addr, int alen)
 	llcp_sock->service_name = kmemdup(llcp_addr.service_name,
 					  llcp_sock->service_name_len,
 					  GFP_KERNEL);
-
+	if (!llcp_sock->service_name) {
+		ret = -ENOMEM;
+		goto put_dev;
+	}
 	llcp_sock->ssap = nfc_llcp_get_sdp_ssap(local, llcp_sock);
 	if (llcp_sock->ssap == LLCP_SAP_MAX) {
+		kfree(llcp_sock->service_name);
+		llcp_sock->service_name = NULL;
 		ret = -EADDRINUSE;
 		goto put_dev;
 	}
-- 
2.20.1


From 2d74400ef22c9bff36bda812951fe97c08ed6f1d Mon Sep 17 00:00:00 2001
From: Reinhard Speyerer <rspmn@arcor.de>
Date: Thu, 3 Oct 2019 18:34:39 +0200
Subject: [PATCH 11/25] qmi_wwan: add support for Cinterion CLS8 devices
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit cf74ac6db25d4002089e85cc623ad149ecc25614 ]

Add support for Cinterion CLS8 devices.
Use QMI_QUIRK_SET_DTR as required for Qualcomm MDM9x07 chipsets.

T:  Bus=01 Lev=03 Prnt=05 Port=01 Cnt=02 Dev#= 25 Spd=480  MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1e2d ProdID=00b0 Rev= 3.18
S:  Manufacturer=GEMALTO
S:  Product=USB Modem
C:* #Ifs= 5 Cfg#= 1 Atr=80 MxPwr=500mA
I:* If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=(none)
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E:  Ad=83(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E:  Ad=85(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E:  Ad=87(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
E:  Ad=89(I) Atr=03(Int.) MxPS=   8 Ivl=32ms
E:  Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms

Signed-off-by: Reinhard Speyerer <rspmn@arcor.de>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 26c5207466af..54390b77ae21 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1349,6 +1349,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1e2d, 0x0082, 4)},	/* Cinterion PHxx,PXxx (2 RmNet) */
 	{QMI_FIXED_INTF(0x1e2d, 0x0082, 5)},	/* Cinterion PHxx,PXxx (2 RmNet) */
 	{QMI_FIXED_INTF(0x1e2d, 0x0083, 4)},	/* Cinterion PHxx,PXxx (1 RmNet + USB Audio)*/
+	{QMI_QUIRK_SET_DTR(0x1e2d, 0x00b0, 4)},	/* Cinterion CLS8 */
 	{QMI_FIXED_INTF(0x413c, 0x81a2, 8)},	/* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card */
 	{QMI_FIXED_INTF(0x413c, 0x81a3, 8)},	/* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card */
 	{QMI_FIXED_INTF(0x413c, 0x81a4, 8)},	/* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */
-- 
2.20.1


From e4edf48c60e7d95453e993988a43b53153e22b18 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 3 Oct 2019 17:44:44 +0100
Subject: [PATCH 12/25] rxrpc: Fix rxrpc_recvmsg tracepoint

[ Upstream commit db9b2e0af605e7c994784527abfd9276cabd718a ]

Fix the rxrpc_recvmsg tracepoint to handle being called with a NULL call
parameter.

Fixes: a25e21f0bcd2 ("rxrpc, afs: Use debug_ids rather than pointers in traces")
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/trace/events/rxrpc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index fa06b528c73c..0972c48d81d7 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -1071,7 +1071,7 @@ TRACE_EVENT(rxrpc_recvmsg,
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call->debug_id;
+		    __entry->call = call ? call->debug_id : 0;
 		    __entry->why = why;
 		    __entry->seq = seq;
 		    __entry->offset = offset;
-- 
2.20.1


From 176b2a2a41e39913298e1dda8b6964bf30219c40 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 26 Sep 2019 18:24:43 -0700
Subject: [PATCH 13/25] sch_cbq: validate TCA_CBQ_WRROPT to avoid crash

[ Upstream commit e9789c7cc182484fc031fd88097eb14cb26c4596 ]

syzbot reported a crash in cbq_normalize_quanta() caused
by an out of range cl->priority.

iproute2 enforces this check, but malicious users do not.

kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] SMP KASAN PTI
Modules linked in:
CPU: 1 PID: 26447 Comm: syz-executor.1 Not tainted 5.3+ #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:cbq_normalize_quanta.part.0+0x1fd/0x430 net/sched/sch_cbq.c:902
RSP: 0018:ffff8801a5c333b0 EFLAGS: 00010206
RAX: 0000000020000003 RBX: 00000000fffffff8 RCX: ffffc9000712f000
RDX: 00000000000043bf RSI: ffffffff83be8962 RDI: 0000000100000018
RBP: ffff8801a5c33420 R08: 000000000000003a R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: 00000000000002ef
R13: ffff88018da95188 R14: dffffc0000000000 R15: 0000000000000015
FS:  00007f37d26b1700(0000) GS:ffff8801dad00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000004c7cec CR3: 00000001bcd0a006 CR4: 00000000001626f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 [<ffffffff83be9d57>] cbq_normalize_quanta include/net/pkt_sched.h:27 [inline]
 [<ffffffff83be9d57>] cbq_addprio net/sched/sch_cbq.c:1097 [inline]
 [<ffffffff83be9d57>] cbq_set_wrr+0x2d7/0x450 net/sched/sch_cbq.c:1115
 [<ffffffff83bee8a7>] cbq_change_class+0x987/0x225b net/sched/sch_cbq.c:1537
 [<ffffffff83b96985>] tc_ctl_tclass+0x555/0xcd0 net/sched/sch_api.c:2329
 [<ffffffff83a84655>] rtnetlink_rcv_msg+0x485/0xc10 net/core/rtnetlink.c:5248
 [<ffffffff83cadf0a>] netlink_rcv_skb+0x17a/0x460 net/netlink/af_netlink.c:2510
 [<ffffffff83a7db6d>] rtnetlink_rcv+0x1d/0x30 net/core/rtnetlink.c:5266
 [<ffffffff83cac2c6>] netlink_unicast_kernel net/netlink/af_netlink.c:1324 [inline]
 [<ffffffff83cac2c6>] netlink_unicast+0x536/0x720 net/netlink/af_netlink.c:1350
 [<ffffffff83cacd4a>] netlink_sendmsg+0x89a/0xd50 net/netlink/af_netlink.c:1939
 [<ffffffff8399d46e>] sock_sendmsg_nosec net/socket.c:673 [inline]
 [<ffffffff8399d46e>] sock_sendmsg+0x12e/0x170 net/socket.c:684
 [<ffffffff8399f1fd>] ___sys_sendmsg+0x81d/0x960 net/socket.c:2359
 [<ffffffff839a2d05>] __sys_sendmsg+0x105/0x1d0 net/socket.c:2397
 [<ffffffff839a2df9>] SYSC_sendmsg net/socket.c:2406 [inline]
 [<ffffffff839a2df9>] SyS_sendmsg+0x29/0x30 net/socket.c:2404
 [<ffffffff8101ccc8>] do_syscall_64+0x528/0x770 arch/x86/entry/common.c:305
 [<ffffffff84400091>] entry_SYSCALL_64_after_hwframe+0x42/0xb7

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_cbq.c | 43 +++++++++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 14 deletions(-)

diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 06c7a2da21bc..39b427dc7512 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1127,6 +1127,33 @@ static const struct nla_policy cbq_policy[TCA_CBQ_MAX + 1] = {
 	[TCA_CBQ_POLICE]	= { .len = sizeof(struct tc_cbq_police) },
 };
 
+static int cbq_opt_parse(struct nlattr *tb[TCA_CBQ_MAX + 1],
+			 struct nlattr *opt,
+			 struct netlink_ext_ack *extack)
+{
+	int err;
+
+	if (!opt) {
+		NL_SET_ERR_MSG(extack, "CBQ options are required for this operation");
+		return -EINVAL;
+	}
+
+	err = nla_parse_nested_deprecated(tb, TCA_CBQ_MAX, opt,
+					  cbq_policy, extack);
+	if (err < 0)
+		return err;
+
+	if (tb[TCA_CBQ_WRROPT]) {
+		const struct tc_cbq_wrropt *wrr = nla_data(tb[TCA_CBQ_WRROPT]);
+
+		if (wrr->priority > TC_CBQ_MAXPRIO) {
+			NL_SET_ERR_MSG(extack, "priority is bigger than TC_CBQ_MAXPRIO");
+			err = -EINVAL;
+		}
+	}
+	return err;
+}
+
 static int cbq_init(struct Qdisc *sch, struct nlattr *opt,
 		    struct netlink_ext_ack *extack)
 {
@@ -1139,13 +1166,7 @@ static int cbq_init(struct Qdisc *sch, struct nlattr *opt,
 	hrtimer_init(&q->delay_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
 	q->delay_timer.function = cbq_undelay;
 
-	if (!opt) {
-		NL_SET_ERR_MSG(extack, "CBQ options are required for this operation");
-		return -EINVAL;
-	}
-
-	err = nla_parse_nested_deprecated(tb, TCA_CBQ_MAX, opt, cbq_policy,
-					  extack);
+	err = cbq_opt_parse(tb, opt, extack);
 	if (err < 0)
 		return err;
 
@@ -1464,13 +1485,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t
 	struct cbq_class *parent;
 	struct qdisc_rate_table *rtab = NULL;
 
-	if (!opt) {
-		NL_SET_ERR_MSG(extack, "Mandatory qdisc options missing");
-		return -EINVAL;
-	}
-
-	err = nla_parse_nested_deprecated(tb, TCA_CBQ_MAX, opt, cbq_policy,
-					  extack);
+	err = cbq_opt_parse(tb, opt, extack);
 	if (err < 0)
 		return err;
 
-- 
2.20.1


From b4f1d2745953f36b461b7fbc65cd556ee025fd4b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 4 Oct 2019 10:34:45 -0700
Subject: [PATCH 14/25] sch_dsmark: fix potential NULL deref in dsmark_init()

[ Upstream commit 474f0813a3002cb299bb73a5a93aa1f537a80ca8 ]

Make sure TCA_DSMARK_INDICES was provided by the user.

syzbot reported :

kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] PREEMPT SMP KASAN
CPU: 1 PID: 8799 Comm: syz-executor235 Not tainted 5.3.0+ #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:nla_get_u16 include/net/netlink.h:1501 [inline]
RIP: 0010:dsmark_init net/sched/sch_dsmark.c:364 [inline]
RIP: 0010:dsmark_init+0x193/0x640 net/sched/sch_dsmark.c:339
Code: 85 db 58 0f 88 7d 03 00 00 e8 e9 1a ac fb 48 8b 9d 70 ff ff ff 48 b8 00 00 00 00 00 fc ff df 48 8d 7b 04 48 89 fa 48 c1 ea 03 <0f> b6 14 02 48 89 f8 83 e0 07 83 c0 01 38 d0 7c 08 84 d2 0f 85 ca
RSP: 0018:ffff88809426f3b8 EFLAGS: 00010247
RAX: dffffc0000000000 RBX: 0000000000000000 RCX: ffffffff85c6eb09
RDX: 0000000000000000 RSI: ffffffff85c6eb17 RDI: 0000000000000004
RBP: ffff88809426f4b0 R08: ffff88808c4085c0 R09: ffffed1015d26159
R10: ffffed1015d26158 R11: ffff8880ae930ac7 R12: ffff8880a7e96940
R13: dffffc0000000000 R14: ffff88809426f8c0 R15: 0000000000000000
FS:  0000000001292880(0000) GS:ffff8880ae900000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000020000080 CR3: 000000008ca1b000 CR4: 00000000001406e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 qdisc_create+0x4ee/0x1210 net/sched/sch_api.c:1237
 tc_modify_qdisc+0x524/0x1c50 net/sched/sch_api.c:1653
 rtnetlink_rcv_msg+0x463/0xb00 net/core/rtnetlink.c:5223
 netlink_rcv_skb+0x177/0x450 net/netlink/af_netlink.c:2477
 rtnetlink_rcv+0x1d/0x30 net/core/rtnetlink.c:5241
 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
 netlink_unicast+0x531/0x710 net/netlink/af_netlink.c:1328
 netlink_sendmsg+0x8a5/0xd60 net/netlink/af_netlink.c:1917
 sock_sendmsg_nosec net/socket.c:637 [inline]
 sock_sendmsg+0xd7/0x130 net/socket.c:657
 ___sys_sendmsg+0x803/0x920 net/socket.c:2311
 __sys_sendmsg+0x105/0x1d0 net/socket.c:2356
 __do_sys_sendmsg net/socket.c:2365 [inline]
 __se_sys_sendmsg net/socket.c:2363 [inline]
 __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2363
 do_syscall_64+0xfa/0x760 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x440369

Fixes: 758cc43c6d73 ("[PKT_SCHED]: Fix dsmark to apply changes consistent")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_dsmark.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index bad1cbe59a56..05605b30bef3 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -361,6 +361,8 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt,
 		goto errout;
 
 	err = -EINVAL;
+	if (!tb[TCA_DSMARK_INDICES])
+		goto errout;
 	indices = nla_get_u16(tb[TCA_DSMARK_INDICES]);
 
 	if (hweight32(indices) != 1)
-- 
2.20.1


From cd6576dbe79020115e094ff5527d383634f79605 Mon Sep 17 00:00:00 2001
From: Tuong Lien <tuong.t.lien@dektech.com.au>
Date: Wed, 2 Oct 2019 18:49:43 +0700
Subject: [PATCH 15/25] tipc: fix unlimited bundling of small messages

[ Upstream commit e95584a889e1902fdf1ded9712e2c3c3083baf96 ]

We have identified a problem with the "oversubscription" policy in the
link transmission code.

When small messages are transmitted, and the sending link has reached
the transmit window limit, those messages will be bundled and put into
the link backlog queue. However, bundles of data messages are counted
at the 'CRITICAL' level, so that the counter for that level, instead of
the counter for the real, bundled message's level is the one being
increased.
Subsequent, to-be-bundled data messages at non-CRITICAL levels continue
to be tested against the unchanged counter for their own level, while
contributing to an unrestrained increase at the CRITICAL backlog level.

This leaves a gap in congestion control algorithm for small messages
that can result in starvation for other users or a "real" CRITICAL
user. Even that eventually can lead to buffer exhaustion & link reset.

We fix this by keeping a 'target_bskb' buffer pointer at each levels,
then when bundling, we only bundle messages at the same importance
level only. This way, we know exactly how many slots a certain level
have occupied in the queue, so can manage level congestion accurately.

By bundling messages at the same level, we even have more benefits. Let
consider this:
- One socket sends 64-byte messages at the 'CRITICAL' level;
- Another sends 4096-byte messages at the 'LOW' level;

When a 64-byte message comes and is bundled the first time, we put the
overhead of message bundle to it (+ 40-byte header, data copy, etc.)
for later use, but the next message can be a 4096-byte one that cannot
be bundled to the previous one. This means the last bundle carries only
one payload message which is totally inefficient, as for the receiver
also! Later on, another 64-byte message comes, now we make a new bundle
and the same story repeats...

With the new bundling algorithm, this will not happen, the 64-byte
messages will be bundled together even when the 4096-byte message(s)
comes in between. However, if the 4096-byte messages are sent at the
same level i.e. 'CRITICAL', the bundling algorithm will again cause the
same overhead.

Also, the same will happen even with only one socket sending small
messages at a rate close to the link transmit's one, so that, when one
message is bundled, it's transmitted shortly. Then, another message
comes, a new bundle is created and so on...

We will solve this issue radically by another patch.

Fixes: 365ad353c256 ("tipc: reduce risk of user starvation during link congestion")
Reported-by: Hoang Le <hoang.h.le@dektech.com.au>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Tuong Lien <tuong.t.lien@dektech.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/link.c | 29 ++++++++++++++++++-----------
 net/tipc/msg.c  |  5 +----
 2 files changed, 19 insertions(+), 15 deletions(-)

diff --git a/net/tipc/link.c b/net/tipc/link.c
index 2050fd386642..fd9af899637d 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -163,6 +163,7 @@ struct tipc_link {
 	struct {
 		u16 len;
 		u16 limit;
+		struct sk_buff *target_bskb;
 	} backlog[5];
 	u16 snd_nxt;
 	u16 prev_from;
@@ -872,6 +873,7 @@ static void link_prepare_wakeup(struct tipc_link *l)
 void tipc_link_reset(struct tipc_link *l)
 {
 	struct sk_buff_head list;
+	u32 imp;
 
 	__skb_queue_head_init(&list);
 
@@ -893,11 +895,10 @@ void tipc_link_reset(struct tipc_link *l)
 	__skb_queue_purge(&l->deferdq);
 	__skb_queue_purge(&l->backlogq);
 	__skb_queue_purge(&l->failover_deferdq);
-	l->backlog[TIPC_LOW_IMPORTANCE].len = 0;
-	l->backlog[TIPC_MEDIUM_IMPORTANCE].len = 0;
-	l->backlog[TIPC_HIGH_IMPORTANCE].len = 0;
-	l->backlog[TIPC_CRITICAL_IMPORTANCE].len = 0;
-	l->backlog[TIPC_SYSTEM_IMPORTANCE].len = 0;
+	for (imp = 0; imp <= TIPC_SYSTEM_IMPORTANCE; imp++) {
+		l->backlog[imp].len = 0;
+		l->backlog[imp].target_bskb = NULL;
+	}
 	kfree_skb(l->reasm_buf);
 	kfree_skb(l->failover_reasm_skb);
 	l->reasm_buf = NULL;
@@ -938,7 +939,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
 	u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1;
 	struct sk_buff_head *transmq = &l->transmq;
 	struct sk_buff_head *backlogq = &l->backlogq;
-	struct sk_buff *skb, *_skb, *bskb;
+	struct sk_buff *skb, *_skb, **tskb;
 	int pkt_cnt = skb_queue_len(list);
 	int rc = 0;
 
@@ -988,19 +989,21 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
 			seqno++;
 			continue;
 		}
-		if (tipc_msg_bundle(skb_peek_tail(backlogq), hdr, mtu)) {
+		tskb = &l->backlog[imp].target_bskb;
+		if (tipc_msg_bundle(*tskb, hdr, mtu)) {
 			kfree_skb(__skb_dequeue(list));
 			l->stats.sent_bundled++;
 			continue;
 		}
-		if (tipc_msg_make_bundle(&bskb, hdr, mtu, l->addr)) {
+		if (tipc_msg_make_bundle(tskb, hdr, mtu, l->addr)) {
 			kfree_skb(__skb_dequeue(list));
-			__skb_queue_tail(backlogq, bskb);
-			l->backlog[msg_importance(buf_msg(bskb))].len++;
+			__skb_queue_tail(backlogq, *tskb);
+			l->backlog[imp].len++;
 			l->stats.sent_bundled++;
 			l->stats.sent_bundles++;
 			continue;
 		}
+		l->backlog[imp].target_bskb = NULL;
 		l->backlog[imp].len += skb_queue_len(list);
 		skb_queue_splice_tail_init(list, backlogq);
 	}
@@ -1016,6 +1019,7 @@ static void tipc_link_advance_backlog(struct tipc_link *l,
 	u16 seqno = l->snd_nxt;
 	u16 ack = l->rcv_nxt - 1;
 	u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1;
+	u32 imp;
 
 	while (skb_queue_len(&l->transmq) < l->window) {
 		skb = skb_peek(&l->backlogq);
@@ -1026,7 +1030,10 @@ static void tipc_link_advance_backlog(struct tipc_link *l,
 			break;
 		__skb_dequeue(&l->backlogq);
 		hdr = buf_msg(skb);
-		l->backlog[msg_importance(hdr)].len--;
+		imp = msg_importance(hdr);
+		l->backlog[imp].len--;
+		if (unlikely(skb == l->backlog[imp].target_bskb))
+			l->backlog[imp].target_bskb = NULL;
 		__skb_queue_tail(&l->transmq, skb);
 		/* next retransmit attempt */
 		if (link_is_bc_sndlink(l))
diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index f48e5857210f..b956ce4a40ef 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -484,10 +484,7 @@ bool tipc_msg_make_bundle(struct sk_buff **skb,  struct tipc_msg *msg,
 	bmsg = buf_msg(_skb);
 	tipc_msg_init(msg_prevnode(msg), bmsg, MSG_BUNDLER, 0,
 		      INT_H_SIZE, dnode);
-	if (msg_isdata(msg))
-		msg_set_importance(bmsg, TIPC_CRITICAL_IMPORTANCE);
-	else
-		msg_set_importance(bmsg, TIPC_SYSTEM_IMPORTANCE);
+	msg_set_importance(bmsg, msg_importance(msg));
 	msg_set_seqno(bmsg, msg_seqno(msg));
 	msg_set_ack(bmsg, msg_ack(msg));
 	msg_set_bcast_ack(bmsg, msg_bcast_ack(msg));
-- 
2.20.1


From 1a25862c3279cb727d1b0b2ca60355603f2a6669 Mon Sep 17 00:00:00 2001
From: Josh Hunt <johunt@akamai.com>
Date: Wed, 2 Oct 2019 13:29:22 -0400
Subject: [PATCH 16/25] udp: fix gso_segs calculations

[ Upstream commit 44b321e5020d782ad6e8ae8183f09b163be6e6e2 ]

Commit dfec0ee22c0a ("udp: Record gso_segs when supporting UDP segmentation offload")
added gso_segs calculation, but incorrectly got sizeof() the pointer and
not the underlying data type. In addition let's fix the v6 case.

Fixes: bec1f6f69736 ("udp: generate gso with UDP_SEGMENT")
Fixes: dfec0ee22c0a ("udp: Record gso_segs when supporting UDP segmentation offload")
Signed-off-by: Josh Hunt <johunt@akamai.com>
Reviewed-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 2 +-
 net/ipv6/udp.c | 2 ++
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index acab7738f733..b43075bd66d8 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -868,7 +868,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4,
 
 		skb_shinfo(skb)->gso_size = cork->gso_size;
 		skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
-		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(len - sizeof(uh),
+		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(len - sizeof(*uh),
 							 cork->gso_size);
 		goto csum_partial;
 	}
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 1258be19e186..7cf85955b996 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1156,6 +1156,8 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6,
 
 		skb_shinfo(skb)->gso_size = cork->gso_size;
 		skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
+		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(len - sizeof(*uh),
+							 cork->gso_size);
 		goto csum_partial;
 	}
 
-- 
2.20.1


From c6d8dce282947770d32191a123d6f3ae326011b3 Mon Sep 17 00:00:00 2001
From: Dexuan Cui <decui@microsoft.com>
Date: Mon, 30 Sep 2019 18:43:50 +0000
Subject: [PATCH 17/25] vsock: Fix a lockdep warning in __vsock_release()

[ Upstream commit 0d9138ffac24cf8b75366ede3a68c951e6dcc575 ]

Lockdep is unhappy if two locks from the same class are held.

Fix the below warning for hyperv and virtio sockets (vmci socket code
doesn't have the issue) by using lock_sock_nested() when __vsock_release()
is called recursively:

============================================
WARNING: possible recursive locking detected
5.3.0+ #1 Not tainted
--------------------------------------------
server/1795 is trying to acquire lock:
ffff8880c5158990 (sk_lock-AF_VSOCK){+.+.}, at: hvs_release+0x10/0x120 [hv_sock]

but task is already holding lock:
ffff8880c5158150 (sk_lock-AF_VSOCK){+.+.}, at: __vsock_release+0x2e/0xf0 [vsock]

other info that might help us debug this:
 Possible unsafe locking scenario:

       CPU0
       ----
  lock(sk_lock-AF_VSOCK);
  lock(sk_lock-AF_VSOCK);

 *** DEADLOCK ***

 May be due to missing lock nesting notation

2 locks held by server/1795:
 #0: ffff8880c5d05ff8 (&sb->s_type->i_mutex_key#10){+.+.}, at: __sock_release+0x2d/0xa0
 #1: ffff8880c5158150 (sk_lock-AF_VSOCK){+.+.}, at: __vsock_release+0x2e/0xf0 [vsock]

stack backtrace:
CPU: 5 PID: 1795 Comm: server Not tainted 5.3.0+ #1
Call Trace:
 dump_stack+0x67/0x90
 __lock_acquire.cold.67+0xd2/0x20b
 lock_acquire+0xb5/0x1c0
 lock_sock_nested+0x6d/0x90
 hvs_release+0x10/0x120 [hv_sock]
 __vsock_release+0x24/0xf0 [vsock]
 __vsock_release+0xa0/0xf0 [vsock]
 vsock_release+0x12/0x30 [vsock]
 __sock_release+0x37/0xa0
 sock_close+0x14/0x20
 __fput+0xc1/0x250
 task_work_run+0x98/0xc0
 do_exit+0x344/0xc60
 do_group_exit+0x47/0xb0
 get_signal+0x15c/0xc50
 do_signal+0x30/0x720
 exit_to_usermode_loop+0x50/0xa0
 do_syscall_64+0x24e/0x270
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x7f4184e85f31

Tested-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/vmw_vsock/af_vsock.c                | 16 ++++++++++++----
 net/vmw_vsock/hyperv_transport.c        |  2 +-
 net/vmw_vsock/virtio_transport_common.c |  2 +-
 3 files changed, 14 insertions(+), 6 deletions(-)

diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index ab47bf3ab66e..2ab43b2bba31 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -638,7 +638,7 @@ struct sock *__vsock_create(struct net *net,
 }
 EXPORT_SYMBOL_GPL(__vsock_create);
 
-static void __vsock_release(struct sock *sk)
+static void __vsock_release(struct sock *sk, int level)
 {
 	if (sk) {
 		struct sk_buff *skb;
@@ -648,9 +648,17 @@ static void __vsock_release(struct sock *sk)
 		vsk = vsock_sk(sk);
 		pending = NULL;	/* Compiler warning. */
 
+		/* The release call is supposed to use lock_sock_nested()
+		 * rather than lock_sock(), if a sock lock should be acquired.
+		 */
 		transport->release(vsk);
 
-		lock_sock(sk);
+		/* When "level" is SINGLE_DEPTH_NESTING, use the nested
+		 * version to avoid the warning "possible recursive locking
+		 * detected". When "level" is 0, lock_sock_nested(sk, level)
+		 * is the same as lock_sock(sk).
+		 */
+		lock_sock_nested(sk, level);
 		sock_orphan(sk);
 		sk->sk_shutdown = SHUTDOWN_MASK;
 
@@ -659,7 +667,7 @@ static void __vsock_release(struct sock *sk)
 
 		/* Clean up any sockets that never were accepted. */
 		while ((pending = vsock_dequeue_accept(sk)) != NULL) {
-			__vsock_release(pending);
+			__vsock_release(pending, SINGLE_DEPTH_NESTING);
 			sock_put(pending);
 		}
 
@@ -708,7 +716,7 @@ EXPORT_SYMBOL_GPL(vsock_stream_has_space);
 
 static int vsock_release(struct socket *sock)
 {
-	__vsock_release(sock->sk);
+	__vsock_release(sock->sk, 0);
 	sock->sk = NULL;
 	sock->state = SS_FREE;
 
diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c
index 6c81a911fc02..920f14705346 100644
--- a/net/vmw_vsock/hyperv_transport.c
+++ b/net/vmw_vsock/hyperv_transport.c
@@ -528,7 +528,7 @@ static void hvs_release(struct vsock_sock *vsk)
 	struct sock *sk = sk_vsock(vsk);
 	bool remove_sock;
 
-	lock_sock(sk);
+	lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
 	remove_sock = hvs_close_lock_held(vsk);
 	release_sock(sk);
 	if (remove_sock)
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 6f1a8aff65c5..a7adffd062c7 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -790,7 +790,7 @@ void virtio_transport_release(struct vsock_sock *vsk)
 	struct sock *sk = &vsk->sk;
 	bool remove_sock = true;
 
-	lock_sock(sk);
+	lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
 	if (sk->sk_type == SOCK_STREAM)
 		remove_sock = virtio_transport_close(vsk);
 
-- 
2.20.1


From 544e9fff4b8e9806526b1ba69a1eb690debda82f Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Tue, 1 Oct 2019 16:28:43 +0200
Subject: [PATCH 18/25] net: dsa: rtl8366: Check VLAN ID and not ports

[ Upstream commit e8521e53cca584ddf8ec4584d3c550a6c65f88c4 ]

There has been some confusion between the port number and
the VLAN ID in this driver. What we need to check for
validity is the VLAN ID, nothing else.

The current confusion came from assigning a few default
VLANs for default routing and we need to rewrite that
properly.

Instead of checking if the port number is a valid VLAN
ID, check the actual VLAN IDs passed in to the callback
one by one as expected.

Fixes: d8652956cf37 ("net: dsa: realtek-smi: Add Realtek SMI driver")
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/rtl8366.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/net/dsa/rtl8366.c b/drivers/net/dsa/rtl8366.c
index ca3d17e43ed8..ac88caca5ad4 100644
--- a/drivers/net/dsa/rtl8366.c
+++ b/drivers/net/dsa/rtl8366.c
@@ -339,10 +339,12 @@ int rtl8366_vlan_prepare(struct dsa_switch *ds, int port,
 			 const struct switchdev_obj_port_vlan *vlan)
 {
 	struct realtek_smi *smi = ds->priv;
+	u16 vid;
 	int ret;
 
-	if (!smi->ops->is_vlan_valid(smi, port))
-		return -EINVAL;
+	for (vid = vlan->vid_begin; vid < vlan->vid_end; vid++)
+		if (!smi->ops->is_vlan_valid(smi, vid))
+			return -EINVAL;
 
 	dev_info(smi->dev, "prepare VLANs %04x..%04x\n",
 		 vlan->vid_begin, vlan->vid_end);
@@ -370,8 +372,9 @@ void rtl8366_vlan_add(struct dsa_switch *ds, int port,
 	u16 vid;
 	int ret;
 
-	if (!smi->ops->is_vlan_valid(smi, port))
-		return;
+	for (vid = vlan->vid_begin; vid < vlan->vid_end; vid++)
+		if (!smi->ops->is_vlan_valid(smi, vid))
+			return;
 
 	dev_info(smi->dev, "add VLAN on port %d, %s, %s\n",
 		 port,
-- 
2.20.1


From b522ada23d96d491d825bd186f5106d5e0496e68 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 30 Sep 2019 15:44:44 -0700
Subject: [PATCH 19/25] tcp: adjust rto_base in retransmits_timed_out()

[ Upstream commit 3256a2d6ab1f71f9a1bd2d7f6f18eb8108c48d17 ]

The cited commit exposed an old retransmits_timed_out() bug
which assumed it could call tcp_model_timeout() with
TCP_RTO_MIN as rto_base for all states.

But flows in SYN_SENT or SYN_RECV state uses a different
RTO base (1 sec instead of 200 ms, unless BPF choses
another value)

This caused a reduction of SYN retransmits from 6 to 4 with
the default /proc/sys/net/ipv4/tcp_syn_retries value.

Fixes: a41e8a88b06e ("tcp: better handle TCP_USER_TIMEOUT in SYN_SENT state")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Marek Majkowski <marek@cloudflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_timer.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 3e8b38c73d8c..483323332d74 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -198,8 +198,13 @@ static bool retransmits_timed_out(struct sock *sk,
 		return false;
 
 	start_ts = tcp_sk(sk)->retrans_stamp;
-	if (likely(timeout == 0))
-		timeout = tcp_model_timeout(sk, boundary, TCP_RTO_MIN);
+	if (likely(timeout == 0)) {
+		unsigned int rto_base = TCP_RTO_MIN;
+
+		if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))
+			rto_base = tcp_timeout_init(sk);
+		timeout = tcp_model_timeout(sk, boundary, rto_base);
+	}
 
 	return (s32)(tcp_time_stamp(tcp_sk(sk)) - start_ts - timeout) >= 0;
 }
-- 
2.20.1


From db86ea98bba03d2c846d6b7f1a14da1dad3db77f Mon Sep 17 00:00:00 2001
From: Josh Hunt <johunt@akamai.com>
Date: Wed, 2 Oct 2019 13:29:23 -0400
Subject: [PATCH 20/25] udp: only do GSO if # of segs > 1

[ Upstream commit 4094871db1d65810acab3d57f6089aa39ef7f648 ]

Prior to this change an application sending <= 1MSS worth of data and
enabling UDP GSO would fail if the system had SW GSO enabled, but the
same send would succeed if HW GSO offload is enabled. In addition to this
inconsistency the error in the SW GSO case does not get back to the
application if sending out of a real device so the user is unaware of this
failure.

With this change we only perform GSO if the # of segments is > 1 even
if the application has enabled segmentation. I've also updated the
relevant udpgso selftests.

Fixes: bec1f6f69736 ("udp: generate gso with UDP_SEGMENT")
Signed-off-by: Josh Hunt <johunt@akamai.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c                       | 11 +++++++----
 net/ipv6/udp.c                       | 11 +++++++----
 tools/testing/selftests/net/udpgso.c | 16 ++++------------
 3 files changed, 18 insertions(+), 20 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index b43075bd66d8..665f26e32d77 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -833,6 +833,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4,
 	int is_udplite = IS_UDPLITE(sk);
 	int offset = skb_transport_offset(skb);
 	int len = skb->len - offset;
+	int datalen = len - sizeof(*uh);
 	__wsum csum = 0;
 
 	/*
@@ -866,10 +867,12 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4,
 			return -EIO;
 		}
 
-		skb_shinfo(skb)->gso_size = cork->gso_size;
-		skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
-		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(len - sizeof(*uh),
-							 cork->gso_size);
+		if (datalen > cork->gso_size) {
+			skb_shinfo(skb)->gso_size = cork->gso_size;
+			skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
+			skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(datalen,
+								 cork->gso_size);
+		}
 		goto csum_partial;
 	}
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 7cf85955b996..f0b5edd861d0 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1122,6 +1122,7 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6,
 	__wsum csum = 0;
 	int offset = skb_transport_offset(skb);
 	int len = skb->len - offset;
+	int datalen = len - sizeof(*uh);
 
 	/*
 	 * Create a UDP header
@@ -1154,10 +1155,12 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6,
 			return -EIO;
 		}
 
-		skb_shinfo(skb)->gso_size = cork->gso_size;
-		skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
-		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(len - sizeof(*uh),
-							 cork->gso_size);
+		if (datalen > cork->gso_size) {
+			skb_shinfo(skb)->gso_size = cork->gso_size;
+			skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
+			skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(datalen,
+								 cork->gso_size);
+		}
 		goto csum_partial;
 	}
 
diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c
index b8265ee9923f..614b31aad168 100644
--- a/tools/testing/selftests/net/udpgso.c
+++ b/tools/testing/selftests/net/udpgso.c
@@ -89,12 +89,9 @@ struct testcase testcases_v4[] = {
 		.tfail = true,
 	},
 	{
-		/* send a single MSS: will fail with GSO, because the segment
-		 * logic in udp4_ufo_fragment demands a gso skb to be > MTU
-		 */
+		/* send a single MSS: will fall back to no GSO */
 		.tlen = CONST_MSS_V4,
 		.gso_len = CONST_MSS_V4,
-		.tfail = true,
 		.r_num_mss = 1,
 	},
 	{
@@ -139,10 +136,9 @@ struct testcase testcases_v4[] = {
 		.tfail = true,
 	},
 	{
-		/* send a single 1B MSS: will fail, see single MSS above */
+		/* send a single 1B MSS: will fall back to no GSO */
 		.tlen = 1,
 		.gso_len = 1,
-		.tfail = true,
 		.r_num_mss = 1,
 	},
 	{
@@ -196,12 +192,9 @@ struct testcase testcases_v6[] = {
 		.tfail = true,
 	},
 	{
-		/* send a single MSS: will fail with GSO, because the segment
-		 * logic in udp4_ufo_fragment demands a gso skb to be > MTU
-		 */
+		/* send a single MSS: will fall back to no GSO */
 		.tlen = CONST_MSS_V6,
 		.gso_len = CONST_MSS_V6,
-		.tfail = true,
 		.r_num_mss = 1,
 	},
 	{
@@ -246,10 +239,9 @@ struct testcase testcases_v6[] = {
 		.tfail = true,
 	},
 	{
-		/* send a single 1B MSS: will fail, see single MSS above */
+		/* send a single 1B MSS: will fall back to no GSO */
 		.tlen = 1,
 		.gso_len = 1,
-		.tfail = true,
 		.r_num_mss = 1,
 	},
 	{
-- 
2.20.1


From a27a67199ae976592c901c62b7472f7851607880 Mon Sep 17 00:00:00 2001
From: Dotan Barak <dotanb@dev.mellanox.co.il>
Date: Tue, 1 Oct 2019 10:21:02 -0700
Subject: [PATCH 21/25] net/rds: Fix error handling in rds_ib_add_one()

[ Upstream commit d64bf89a75b65f83f06be9fb8f978e60d53752db ]

rds_ibdev:ipaddr_list and rds_ibdev:conn_list are initialized
after allocation some resources such as protection domain.
If allocation of such resources fail, then these uninitialized
variables are accessed in rds_ib_dev_free() in failure path. This
can potentially crash the system. The code has been updated to
initialize these variables very early in the function.

Signed-off-by: Dotan Barak <dotanb@dev.mellanox.co.il>
Signed-off-by: Sudhakar Dindukurti <sudhakar.dindukurti@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/ib.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/rds/ib.c b/net/rds/ib.c
index b8d581b779b2..992e03ceee9f 100644
--- a/net/rds/ib.c
+++ b/net/rds/ib.c
@@ -143,6 +143,9 @@ static void rds_ib_add_one(struct ib_device *device)
 	refcount_set(&rds_ibdev->refcount, 1);
 	INIT_WORK(&rds_ibdev->free_work, rds_ib_dev_free);
 
+	INIT_LIST_HEAD(&rds_ibdev->ipaddr_list);
+	INIT_LIST_HEAD(&rds_ibdev->conn_list);
+
 	rds_ibdev->max_wrs = device->attrs.max_qp_wr;
 	rds_ibdev->max_sge = min(device->attrs.max_send_sge, RDS_IB_MAX_SGE);
 
@@ -203,9 +206,6 @@ static void rds_ib_add_one(struct ib_device *device)
 		device->name,
 		rds_ibdev->use_fastreg ? "FRMR" : "FMR");
 
-	INIT_LIST_HEAD(&rds_ibdev->ipaddr_list);
-	INIT_LIST_HEAD(&rds_ibdev->conn_list);
-
 	down_write(&rds_ib_devices_lock);
 	list_add_tail_rcu(&rds_ibdev->list, &rds_ib_devices);
 	up_write(&rds_ib_devices_lock);
-- 
2.20.1


From b08dc9445231747a5645ce296b14be9329c8eba6 Mon Sep 17 00:00:00 2001
From: Dongli Zhang <dongli.zhang@oracle.com>
Date: Tue, 1 Oct 2019 21:56:41 +0800
Subject: [PATCH 22/25] xen-netfront: do not use ~0U as error return value for
 xennet_fill_frags()

[ Upstream commit a761129e3625688310aecf26e1be9e98e85f8eb5 ]

xennet_fill_frags() uses ~0U as return value when the sk_buff is not able
to cache extra fragments. This is incorrect because the return type of
xennet_fill_frags() is RING_IDX and 0xffffffff is an expected value for
ring buffer index.

In the situation when the rsp_cons is approaching 0xffffffff, the return
value of xennet_fill_frags() may become 0xffffffff which xennet_poll() (the
caller) would regard as error. As a result, queue->rx.rsp_cons is set
incorrectly because it is updated only when there is error. If there is no
error, xennet_poll() would be responsible to update queue->rx.rsp_cons.
Finally, queue->rx.rsp_cons would point to the rx ring buffer entries whose
queue->rx_skbs[i] and queue->grant_rx_ref[i] are already cleared to NULL.
This leads to NULL pointer access in the next iteration to process rx ring
buffer entries.

The symptom is similar to the one fixed in
commit 00b368502d18 ("xen-netfront: do not assume sk_buff_head list is
empty in error handling").

This patch changes the return type of xennet_fill_frags() to indicate
whether it is successful or failed. The queue->rx.rsp_cons will be
always updated inside this function.

Fixes: ad4f15dc2c70 ("xen/netfront: don't bug in case of too many frags")
Signed-off-by: Dongli Zhang <dongli.zhang@oracle.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netfront.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 5f5722bf6762..7370e06a0e4b 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -887,9 +887,9 @@ static int xennet_set_skb_gso(struct sk_buff *skb,
 	return 0;
 }
 
-static RING_IDX xennet_fill_frags(struct netfront_queue *queue,
-				  struct sk_buff *skb,
-				  struct sk_buff_head *list)
+static int xennet_fill_frags(struct netfront_queue *queue,
+			     struct sk_buff *skb,
+			     struct sk_buff_head *list)
 {
 	RING_IDX cons = queue->rx.rsp_cons;
 	struct sk_buff *nskb;
@@ -908,7 +908,7 @@ static RING_IDX xennet_fill_frags(struct netfront_queue *queue,
 		if (unlikely(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS)) {
 			queue->rx.rsp_cons = ++cons + skb_queue_len(list);
 			kfree_skb(nskb);
-			return ~0U;
+			return -ENOENT;
 		}
 
 		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
@@ -919,7 +919,9 @@ static RING_IDX xennet_fill_frags(struct netfront_queue *queue,
 		kfree_skb(nskb);
 	}
 
-	return cons;
+	queue->rx.rsp_cons = cons;
+
+	return 0;
 }
 
 static int checksum_setup(struct net_device *dev, struct sk_buff *skb)
@@ -1045,8 +1047,7 @@ static int xennet_poll(struct napi_struct *napi, int budget)
 		skb->data_len = rx->status;
 		skb->len += rx->status;
 
-		i = xennet_fill_frags(queue, skb, &tmpq);
-		if (unlikely(i == ~0U))
+		if (unlikely(xennet_fill_frags(queue, skb, &tmpq)))
 			goto err;
 
 		if (rx->flags & XEN_NETRXF_csum_blank)
@@ -1056,7 +1057,7 @@ static int xennet_poll(struct napi_struct *napi, int budget)
 
 		__skb_queue_tail(&rxq, skb);
 
-		queue->rx.rsp_cons = ++i;
+		i = ++queue->rx.rsp_cons;
 		work_done++;
 	}
 
-- 
2.20.1


From fa678f250c67066346cb777cc3e762aa1fde185e Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Tue, 1 Oct 2019 22:07:01 +0300
Subject: [PATCH 23/25] ptp_qoriq: Initialize the registers' spinlock before
 calling ptp_qoriq_settime

[ Upstream commit db34a4714c013b644eec2de0ec81b1f0373b8b93 ]

Because ptp_qoriq_settime is being called prior to spin_lock_init, the
following stack trace can be seen at driver probe time:

[    2.269117] the code is fine but needs lockdep annotation.
[    2.274569] turning off the locking correctness validator.
[    2.280027] CPU: 1 PID: 1 Comm: swapper/0 Not tainted 5.3.0-rc7-01478-g01eaa67a4797 #263
[    2.288073] Hardware name: Freescale LS1021A
[    2.292337] [<c0313cb4>] (unwind_backtrace) from [<c030e11c>] (show_stack+0x10/0x14)
[    2.300045] [<c030e11c>] (show_stack) from [<c1219440>] (dump_stack+0xcc/0xf8)
[    2.307235] [<c1219440>] (dump_stack) from [<c03b9b44>] (register_lock_class+0x730/0x73c)
[    2.315372] [<c03b9b44>] (register_lock_class) from [<c03b6190>] (__lock_acquire+0x78/0x270c)
[    2.323856] [<c03b6190>] (__lock_acquire) from [<c03b90cc>] (lock_acquire+0xe0/0x22c)
[    2.331649] [<c03b90cc>] (lock_acquire) from [<c123c310>] (_raw_spin_lock_irqsave+0x54/0x68)
[    2.340048] [<c123c310>] (_raw_spin_lock_irqsave) from [<c0e73fe4>] (ptp_qoriq_settime+0x38/0x80)
[    2.348878] [<c0e73fe4>] (ptp_qoriq_settime) from [<c0e746d4>] (ptp_qoriq_init+0x1f8/0x484)
[    2.357189] [<c0e746d4>] (ptp_qoriq_init) from [<c0e74aac>] (ptp_qoriq_probe+0xd0/0x184)
[    2.365243] [<c0e74aac>] (ptp_qoriq_probe) from [<c0b0a07c>] (platform_drv_probe+0x48/0x9c)
[    2.373555] [<c0b0a07c>] (platform_drv_probe) from [<c0b07a14>] (really_probe+0x1c4/0x400)
[    2.381779] [<c0b07a14>] (really_probe) from [<c0b07e28>] (driver_probe_device+0x78/0x1b8)
[    2.390003] [<c0b07e28>] (driver_probe_device) from [<c0b081d0>] (device_driver_attach+0x58/0x60)
[    2.398832] [<c0b081d0>] (device_driver_attach) from [<c0b082d4>] (__driver_attach+0xfc/0x160)
[    2.407402] [<c0b082d4>] (__driver_attach) from [<c0b05a84>] (bus_for_each_dev+0x68/0xb4)
[    2.415539] [<c0b05a84>] (bus_for_each_dev) from [<c0b06b68>] (bus_add_driver+0x104/0x20c)
[    2.423763] [<c0b06b68>] (bus_add_driver) from [<c0b0909c>] (driver_register+0x78/0x10c)
[    2.431815] [<c0b0909c>] (driver_register) from [<c030313c>] (do_one_initcall+0x8c/0x3ac)
[    2.439954] [<c030313c>] (do_one_initcall) from [<c1f013f4>] (kernel_init_freeable+0x468/0x548)
[    2.448610] [<c1f013f4>] (kernel_init_freeable) from [<c12344d8>] (kernel_init+0x8/0x10c)
[    2.456745] [<c12344d8>] (kernel_init) from [<c03010b4>] (ret_from_fork+0x14/0x20)
[    2.464273] Exception stack(0xea89ffb0 to 0xea89fff8)
[    2.469297] ffa0:                                     00000000 00000000 00000000 00000000
[    2.477432] ffc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
[    2.485566] ffe0: 00000000 00000000 00000000 00000000 00000013 00000000

Fixes: ff54571a747b ("ptp_qoriq: convert to use ptp_qoriq_init/free")
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/ptp/ptp_qoriq.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/ptp/ptp_qoriq.c b/drivers/ptp/ptp_qoriq.c
index c61f00b72e15..a577218d1ab7 100644
--- a/drivers/ptp/ptp_qoriq.c
+++ b/drivers/ptp/ptp_qoriq.c
@@ -507,6 +507,8 @@ int ptp_qoriq_init(struct ptp_qoriq *ptp_qoriq, void __iomem *base,
 		ptp_qoriq->regs.etts_regs = base + ETTS_REGS_OFFSET;
 	}
 
+	spin_lock_init(&ptp_qoriq->lock);
+
 	ktime_get_real_ts64(&now);
 	ptp_qoriq_settime(&ptp_qoriq->caps, &now);
 
@@ -514,7 +516,6 @@ int ptp_qoriq_init(struct ptp_qoriq *ptp_qoriq, void __iomem *base,
 	  (ptp_qoriq->tclk_period & TCLK_PERIOD_MASK) << TCLK_PERIOD_SHIFT |
 	  (ptp_qoriq->cksel & CKSEL_MASK) << CKSEL_SHIFT;
 
-	spin_lock_init(&ptp_qoriq->lock);
 	spin_lock_irqsave(&ptp_qoriq->lock, flags);
 
 	regs = &ptp_qoriq->regs;
-- 
2.20.1


From d8d1ef13b8752795fc75c719d8b188acfda2cfe6 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Sun, 29 Sep 2019 02:39:48 +0300
Subject: [PATCH 24/25] net: sched: cbs: Avoid division by zero when
 calculating the port rate

[ Upstream commit 83c8c3cf45163f0c823db37be6ab04dfcf8ac751 ]

As explained in the "net: sched: taprio: Avoid division by zero on
invalid link speed" commit, it is legal for the ethtool API to return
zero as a link speed. So guard against it to ensure we don't perform a
division by zero in kernel.

Fixes: e0a7683d30e9 ("net/sched: cbs: fix port_rate miscalculation")
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Acked-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_cbs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c
index 4a403d35438f..284ab2dcf47f 100644
--- a/net/sched/sch_cbs.c
+++ b/net/sched/sch_cbs.c
@@ -306,7 +306,7 @@ static void cbs_set_port_rate(struct net_device *dev, struct cbs_sched_data *q)
 	if (err < 0)
 		goto skip;
 
-	if (ecmd.base.speed != SPEED_UNKNOWN)
+	if (ecmd.base.speed && ecmd.base.speed != SPEED_UNKNOWN)
 		speed = ecmd.base.speed;
 
 skip:
-- 
2.20.1


From a1b9c242ac97c043cfa31cd9e3257f4c02bf9b3f Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Sun, 29 Sep 2019 02:37:22 +0300
Subject: [PATCH 25/25] net: sched: taprio: Avoid division by zero on invalid
 link speed

[ Upstream commit 9a9251a3534745d08a92abfeca0ca467b912b5f6 ]

The check in taprio_set_picos_per_byte is currently not robust enough
and will trigger this division by zero, due to e.g. PHYLINK not setting
kset->base.speed when there is no PHY connected:

[   27.109992] Division by zero in kernel.
[   27.113842] CPU: 1 PID: 198 Comm: tc Not tainted 5.3.0-rc5-01246-gc4006b8c2637-dirty #212
[   27.121974] Hardware name: Freescale LS1021A
[   27.126234] [<c03132e0>] (unwind_backtrace) from [<c030d8b8>] (show_stack+0x10/0x14)
[   27.133938] [<c030d8b8>] (show_stack) from [<c10b21b0>] (dump_stack+0xb0/0xc4)
[   27.141124] [<c10b21b0>] (dump_stack) from [<c10af97c>] (Ldiv0_64+0x8/0x18)
[   27.148052] [<c10af97c>] (Ldiv0_64) from [<c0700260>] (div64_u64+0xcc/0xf0)
[   27.154978] [<c0700260>] (div64_u64) from [<c07002d0>] (div64_s64+0x4c/0x68)
[   27.161993] [<c07002d0>] (div64_s64) from [<c0f3d890>] (taprio_set_picos_per_byte+0xe8/0xf4)
[   27.170388] [<c0f3d890>] (taprio_set_picos_per_byte) from [<c0f3f614>] (taprio_change+0x668/0xcec)
[   27.179302] [<c0f3f614>] (taprio_change) from [<c0f2bc24>] (qdisc_create+0x1fc/0x4f4)
[   27.187091] [<c0f2bc24>] (qdisc_create) from [<c0f2c0c8>] (tc_modify_qdisc+0x1ac/0x6f8)
[   27.195055] [<c0f2c0c8>] (tc_modify_qdisc) from [<c0ee9604>] (rtnetlink_rcv_msg+0x268/0x2dc)
[   27.203449] [<c0ee9604>] (rtnetlink_rcv_msg) from [<c0f4fef0>] (netlink_rcv_skb+0xe0/0x114)
[   27.211756] [<c0f4fef0>] (netlink_rcv_skb) from [<c0f4f6cc>] (netlink_unicast+0x1b4/0x22c)
[   27.219977] [<c0f4f6cc>] (netlink_unicast) from [<c0f4fa84>] (netlink_sendmsg+0x284/0x340)
[   27.228198] [<c0f4fa84>] (netlink_sendmsg) from [<c0eae5fc>] (sock_sendmsg+0x14/0x24)
[   27.235988] [<c0eae5fc>] (sock_sendmsg) from [<c0eaedf8>] (___sys_sendmsg+0x214/0x228)
[   27.243863] [<c0eaedf8>] (___sys_sendmsg) from [<c0eb015c>] (__sys_sendmsg+0x50/0x8c)
[   27.251652] [<c0eb015c>] (__sys_sendmsg) from [<c0301000>] (ret_fast_syscall+0x0/0x54)
[   27.259524] Exception stack(0xe8045fa8 to 0xe8045ff0)
[   27.264546] 5fa0:                   b6f608c8 000000f8 00000003 bed7e2f0 00000000 00000000
[   27.272681] 5fc0: b6f608c8 000000f8 004ce54c 00000128 5d3ce8c7 00000000 00000026 00505c9c
[   27.280812] 5fe0: 00000070 bed7e298 004ddd64 b6dd1e64

Russell King points out that the ethtool API says zero is a valid return
value of __ethtool_get_link_ksettings:

   * If it is enabled then they are read-only; if the link
   * is up they represent the negotiated link mode; if the link is down,
   * the speed is 0, %SPEED_UNKNOWN or the highest enabled speed and
   * @duplex is %DUPLEX_UNKNOWN or the best enabled duplex mode.

  So, it seems that taprio is not following the API... I'd suggest either
  fixing taprio, or getting agreement to change the ethtool API.

The chosen path was to fix taprio.

Fixes: 7b9eba7ba0c1 ("net/sched: taprio: fix picos_per_byte miscalculation")
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Acked-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_taprio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index f3f959f5458b..2f2967dcf15a 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -668,7 +668,7 @@ static void taprio_set_picos_per_byte(struct net_device *dev,
 	if (err < 0)
 		goto skip;
 
-	if (ecmd.base.speed != SPEED_UNKNOWN)
+	if (ecmd.base.speed && ecmd.base.speed != SPEED_UNKNOWN)
 		speed = ecmd.base.speed;
 
 skip:
-- 
2.20.1


[-- Attachment #3: net_53.mbox --]
[-- Type: Application/Octet-Stream, Size: 92792 bytes --]

From fa87e7b918cfb94709ebe2f33030d95ada91b96f Mon Sep 17 00:00:00 2001
From: Vishal Kulkarni <vishal@chelsio.com>
Date: Fri, 4 Oct 2019 04:06:15 +0530
Subject: [PATCH 01/30] cxgb4:Fix out-of-bounds MSI-X info array access

[ Upstream commit 6b517374f4ea5a3c6e307e1219ec5f35d42e6d00 ]

When fetching free MSI-X vectors for ULDs, check for the error code
before accessing MSI-X info array. Otherwise, an out-of-bounds access is
attempted, which results in kernel panic.

Fixes: 94cdb8bb993a ("cxgb4: Add support for dynamic allocation of resources for ULD")
Signed-off-by: Shahjada Abul Husain <shahjada@chelsio.com>
Signed-off-by: Vishal Kulkarni <vishal@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
index 5b602243d573..a4dead4ab0ed 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
@@ -137,13 +137,12 @@ static int uldrx_handler(struct sge_rspq *q, const __be64 *rsp,
 static int alloc_uld_rxqs(struct adapter *adap,
 			  struct sge_uld_rxq_info *rxq_info, bool lro)
 {
-	struct sge *s = &adap->sge;
 	unsigned int nq = rxq_info->nrxq + rxq_info->nciq;
+	int i, err, msi_idx, que_idx = 0, bmap_idx = 0;
 	struct sge_ofld_rxq *q = rxq_info->uldrxq;
 	unsigned short *ids = rxq_info->rspq_id;
-	unsigned int bmap_idx = 0;
+	struct sge *s = &adap->sge;
 	unsigned int per_chan;
-	int i, err, msi_idx, que_idx = 0;
 
 	per_chan = rxq_info->nrxq / adap->params.nports;
 
@@ -161,6 +160,10 @@ static int alloc_uld_rxqs(struct adapter *adap,
 
 		if (msi_idx >= 0) {
 			bmap_idx = get_msix_idx_from_bmap(adap);
+			if (bmap_idx < 0) {
+				err = -ENOSPC;
+				goto freeout;
+			}
 			msi_idx = adap->msix_info_ulds[bmap_idx].idx;
 		}
 		err = t4_sge_alloc_rxq(adap, &q->rspq, false,
-- 
2.20.1


From 10fee4861561f3c3870dac0aae63ab45b44323bc Mon Sep 17 00:00:00 2001
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Fri, 27 Sep 2019 14:58:20 +0800
Subject: [PATCH 02/30] erspan: remove the incorrect mtu limit for erspan

[ Upstream commit 0e141f757b2c78c983df893e9993313e2dc21e38 ]

erspan driver calls ether_setup(), after commit 61e84623ace3
("net: centralize net_device min/max MTU checking"), the range
of mtu is [min_mtu, max_mtu], which is [68, 1500] by default.

It causes the dev mtu of the erspan device to not be greater
than 1500, this limit value is not correct for ipgre tap device.

Tested:
Before patch:
# ip link set erspan0 mtu 1600
Error: mtu greater than device maximum.
After patch:
# ip link set erspan0 mtu 1600
# ip -d link show erspan0
21: erspan0@NONE: <BROADCAST,MULTICAST> mtu 1600 qdisc noop state DOWN
mode DEFAULT group default qlen 1000
    link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff promiscuity 0 minmtu 68 maxmtu 0

Fixes: 61e84623ace3 ("net: centralize net_device min/max MTU checking")
Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_gre.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index a53a543fe055..52690bb3e40f 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1446,6 +1446,7 @@ static void erspan_setup(struct net_device *dev)
 	struct ip_tunnel *t = netdev_priv(dev);
 
 	ether_setup(dev);
+	dev->max_mtu = 0;
 	dev->netdev_ops = &erspan_netdev_ops;
 	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
-- 
2.20.1


From 46d114e82fc23e707ad88f96b703b570e2c6bf04 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 30 Sep 2019 17:12:41 +0200
Subject: [PATCH 03/30] hso: fix NULL-deref on tty open

[ Upstream commit 8353da9fa69722b54cba82b2ec740afd3d438748 ]

Fix NULL-pointer dereference on tty open due to a failure to handle a
missing interrupt-in endpoint when probing modem ports:

	BUG: kernel NULL pointer dereference, address: 0000000000000006
	...
	RIP: 0010:tiocmget_submit_urb+0x1c/0xe0 [hso]
	...
	Call Trace:
	hso_start_serial_device+0xdc/0x140 [hso]
	hso_serial_open+0x118/0x1b0 [hso]
	tty_open+0xf1/0x490

Fixes: 542f54823614 ("tty: Modem functions for the HSO driver")
Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/hso.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c
index ce78714f536f..a505b2ab88b8 100644
--- a/drivers/net/usb/hso.c
+++ b/drivers/net/usb/hso.c
@@ -2620,14 +2620,18 @@ static struct hso_device *hso_create_bulk_serial_device(
 		 */
 		if (serial->tiocmget) {
 			tiocmget = serial->tiocmget;
+			tiocmget->endp = hso_get_ep(interface,
+						    USB_ENDPOINT_XFER_INT,
+						    USB_DIR_IN);
+			if (!tiocmget->endp) {
+				dev_err(&interface->dev, "Failed to find INT IN ep\n");
+				goto exit;
+			}
+
 			tiocmget->urb = usb_alloc_urb(0, GFP_KERNEL);
 			if (tiocmget->urb) {
 				mutex_init(&tiocmget->mutex);
 				init_waitqueue_head(&tiocmget->waitq);
-				tiocmget->endp = hso_get_ep(
-					interface,
-					USB_ENDPOINT_XFER_INT,
-					USB_DIR_IN);
 			} else
 				hso_free_tiomget(serial);
 		}
-- 
2.20.1


From b7c59f03ae2bdcfd8cab8375991a79a23ce92d73 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 2 Oct 2019 09:38:55 -0700
Subject: [PATCH 04/30] ipv6: drop incoming packets having a v4mapped source
 address

[ Upstream commit 6af1799aaf3f1bc8defedddfa00df3192445bbf3 ]

This began with a syzbot report. syzkaller was injecting
IPv6 TCP SYN packets having a v4mapped source address.

After an unsuccessful 4-tuple lookup, TCP creates a request
socket (SYN_RECV) and calls reqsk_queue_hash_req()

reqsk_queue_hash_req() calls sk_ehashfn(sk)

At this point we have AF_INET6 sockets, and the heuristic
used by sk_ehashfn() to either hash the IPv4 or IPv6 addresses
is to use ipv6_addr_v4mapped(&sk->sk_v6_daddr)

For the particular spoofed packet, we end up hashing V4 addresses
which were not initialized by the TCP IPv6 stack, so KMSAN fired
a warning.

I first fixed sk_ehashfn() to test both source and destination addresses,
but then faced various problems, including user-space programs
like packetdrill that had similar assumptions.

Instead of trying to fix the whole ecosystem, it is better
to admit that we have a dual stack behavior, and that we
can not build linux kernels without V4 stack anyway.

The dual stack API automatically forces the traffic to be IPv4
if v4mapped addresses are used at bind() or connect(), so it makes
no sense to allow IPv6 traffic to use the same v4mapped class.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Florian Westphal <fw@strlen.de>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_input.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index fa014d5f1732..a593aaf25748 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -221,6 +221,16 @@ static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev,
 	if (ipv6_addr_is_multicast(&hdr->saddr))
 		goto err;
 
+	/* While RFC4291 is not explicit about v4mapped addresses
+	 * in IPv6 headers, it seems clear linux dual-stack
+	 * model can not deal properly with these.
+	 * Security models could be fooled by ::ffff:127.0.0.1 for example.
+	 *
+	 * https://tools.ietf.org/html/draft-itojun-v6ops-v4mapped-harmful-02
+	 */
+	if (ipv6_addr_v4mapped(&hdr->saddr))
+		goto err;
+
 	skb->transport_header = skb->network_header + sizeof(*hdr);
 	IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);
 
-- 
2.20.1


From 75487c826b508a33bd7d66a2aef9e00903e883bf Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Fri, 4 Oct 2019 08:03:09 -0700
Subject: [PATCH 05/30] ipv6: Handle missing host route in __ipv6_ifa_notify

[ Upstream commit 2d819d250a1393a3e725715425ab70a0e0772a71 ]

Rajendra reported a kernel panic when a link was taken down:

    [ 6870.263084] BUG: unable to handle kernel NULL pointer dereference at 00000000000000a8
    [ 6870.271856] IP: [<ffffffff8efc5764>] __ipv6_ifa_notify+0x154/0x290

    <snip>

    [ 6870.570501] Call Trace:
    [ 6870.573238] [<ffffffff8efc58c6>] ? ipv6_ifa_notify+0x26/0x40
    [ 6870.579665] [<ffffffff8efc98ec>] ? addrconf_dad_completed+0x4c/0x2c0
    [ 6870.586869] [<ffffffff8efe70c6>] ? ipv6_dev_mc_inc+0x196/0x260
    [ 6870.593491] [<ffffffff8efc9c6a>] ? addrconf_dad_work+0x10a/0x430
    [ 6870.600305] [<ffffffff8f01ade4>] ? __switch_to_asm+0x34/0x70
    [ 6870.606732] [<ffffffff8ea93a7a>] ? process_one_work+0x18a/0x430
    [ 6870.613449] [<ffffffff8ea93d6d>] ? worker_thread+0x4d/0x490
    [ 6870.619778] [<ffffffff8ea93d20>] ? process_one_work+0x430/0x430
    [ 6870.626495] [<ffffffff8ea99dd9>] ? kthread+0xd9/0xf0
    [ 6870.632145] [<ffffffff8f01ade4>] ? __switch_to_asm+0x34/0x70
    [ 6870.638573] [<ffffffff8ea99d00>] ? kthread_park+0x60/0x60
    [ 6870.644707] [<ffffffff8f01ae77>] ? ret_from_fork+0x57/0x70
    [ 6870.650936] Code: 31 c0 31 d2 41 b9 20 00 08 02 b9 09 00 00 0

addrconf_dad_work is kicked to be scheduled when a device is brought
up. There is a race between addrcond_dad_work getting scheduled and
taking the rtnl lock and a process taking the link down (under rtnl).
The latter removes the host route from the inet6_addr as part of
addrconf_ifdown which is run for NETDEV_DOWN. The former attempts
to use the host route in __ipv6_ifa_notify. If the down event removes
the host route due to the race to the rtnl, then the BUG listed above
occurs.

Since the DAD sequence can not be aborted, add a check for the missing
host route in __ipv6_ifa_notify. The only way this should happen is due
to the previously mentioned race. The host route is created when the
address is added to an interface; it is only removed on a down event
where the address is kept. Add a warning if the host route is missing
AND the device is up; this is a situation that should never happen.

Fixes: f1705ec197e7 ("net: ipv6: Make address flushing on ifdown optional")
Reported-by: Rajendra Dendukuri <rajendra.dendukuri@broadcom.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 6a576ff92c39..34ccef18b40e 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5964,13 +5964,20 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
 	switch (event) {
 	case RTM_NEWADDR:
 		/*
-		 * If the address was optimistic
-		 * we inserted the route at the start of
-		 * our DAD process, so we don't need
-		 * to do it again
+		 * If the address was optimistic we inserted the route at the
+		 * start of our DAD process, so we don't need to do it again.
+		 * If the device was taken down in the middle of the DAD
+		 * cycle there is a race where we could get here without a
+		 * host route, so nothing to insert. That will be fixed when
+		 * the device is brought up.
 		 */
-		if (!rcu_access_pointer(ifp->rt->fib6_node))
+		if (ifp->rt && !rcu_access_pointer(ifp->rt->fib6_node)) {
 			ip6_ins_rt(net, ifp->rt);
+		} else if (!ifp->rt && (ifp->idev->dev->flags & IFF_UP)) {
+			pr_warn("BUG: Address %pI6c on device %s is missing its host route.\n",
+				&ifp->addr, ifp->idev->dev->name);
+		}
+
 		if (ifp->idev->cnf.forwarding)
 			addrconf_join_anycast(ifp);
 		if (!ipv6_addr_any(&ifp->peer_addr))
-- 
2.20.1


From 62a4732249ac74ee516a6a04d33147cb3cfb516d Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 4 Oct 2019 15:11:17 +0200
Subject: [PATCH 06/30] net: ipv4: avoid mixed n_redirects and rate_tokens
 usage

[ Upstream commit b406472b5ad79ede8d10077f0c8f05505ace8b6d ]

Since commit c09551c6ff7f ("net: ipv4: use a dedicated counter
for icmp_v4 redirect packets") we use 'n_redirects' to account
for redirect packets, but we still use 'rate_tokens' to compute
the redirect packets exponential backoff.

If the device sent to the relevant peer any ICMP error packet
after sending a redirect, it will also update 'rate_token' according
to the leaking bucket schema; typically 'rate_token' will raise
above BITS_PER_LONG and the redirect packets backoff algorithm
will produce undefined behavior.

Fix the issue using 'n_redirects' to compute the exponential backoff
in ip_rt_send_redirect().

Note that we still clear rate_tokens after a redirect silence period,
to avoid changing an established behaviour.

The root cause predates git history; before the mentioned commit in
the critical scenario, the kernel stopped sending redirects, after
the mentioned commit the behavior more randomic.

Reported-by: Xiumei Mu <xmu@redhat.com>
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Fixes: c09551c6ff7f ("net: ipv4: use a dedicated counter for icmp_v4 redirect packets")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 7dcce724c78b..14654876127e 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -916,16 +916,15 @@ void ip_rt_send_redirect(struct sk_buff *skb)
 	if (peer->rate_tokens == 0 ||
 	    time_after(jiffies,
 		       (peer->rate_last +
-			(ip_rt_redirect_load << peer->rate_tokens)))) {
+			(ip_rt_redirect_load << peer->n_redirects)))) {
 		__be32 gw = rt_nexthop(rt, ip_hdr(skb)->daddr);
 
 		icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw);
 		peer->rate_last = jiffies;
-		++peer->rate_tokens;
 		++peer->n_redirects;
 #ifdef CONFIG_IP_ROUTE_VERBOSE
 		if (log_martians &&
-		    peer->rate_tokens == ip_rt_redirect_number)
+		    peer->n_redirects == ip_rt_redirect_number)
 			net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n",
 					     &ip_hdr(skb)->saddr, inet_iif(skb),
 					     &ip_hdr(skb)->daddr, &gw);
-- 
2.20.1


From 1bf164c0a974cd6869a8462c91c730bea969e936 Mon Sep 17 00:00:00 2001
From: Navid Emamdoost <navid.emamdoost@gmail.com>
Date: Fri, 4 Oct 2019 15:24:39 -0500
Subject: [PATCH 07/30] net: qlogic: Fix memory leak in ql_alloc_large_buffers

[ Upstream commit 1acb8f2a7a9f10543868ddd737e37424d5c36cf4 ]

In ql_alloc_large_buffers, a new skb is allocated via netdev_alloc_skb.
This skb should be released if pci_dma_mapping_error fails.

Fixes: 0f8ab89e825f ("qla3xxx: Check return code from pci_map_single() in ql_release_to_lrg_buf_free_list(), ql_populate_free_queue(), ql_alloc_large_buffers(), and ql3xxx_send()")
Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qla3xxx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c
index 457444894d80..b4b8ba00ee01 100644
--- a/drivers/net/ethernet/qlogic/qla3xxx.c
+++ b/drivers/net/ethernet/qlogic/qla3xxx.c
@@ -2787,6 +2787,7 @@ static int ql_alloc_large_buffers(struct ql3_adapter *qdev)
 				netdev_err(qdev->ndev,
 					   "PCI mapping failed with error: %d\n",
 					   err);
+				dev_kfree_skb_irq(skb);
 				ql_free_large_buffers(qdev);
 				return -ENOMEM;
 			}
-- 
2.20.1


From 791603bec9ff1e53ad8f00981a92323bcff35fa2 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Sun, 29 Sep 2019 02:01:39 +0300
Subject: [PATCH 08/30] net: sched: taprio: Fix potential integer overflow in
 taprio_set_picos_per_byte

[ Upstream commit 68ce6688a5baefde30914fc07fc27292dbbe8320 ]

The speed divisor is used in a context expecting an s64, but it is
evaluated using 32-bit arithmetic.

To avoid that happening, instead of multiplying by 1,000,000 in the
first place, simplify the fraction and do a standard 32 bit division
instead.

Fixes: f04b514c0ce2 ("taprio: Set default link speed to 10 Mbps in taprio_set_picos_per_byte")
Reported-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Acked-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_taprio.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 8d8bc2ec5cd6..944b1af32156 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -965,8 +965,7 @@ static void taprio_set_picos_per_byte(struct net_device *dev,
 		speed = ecmd.base.speed;
 
 skip:
-	picos_per_byte = div64_s64(NSEC_PER_SEC * 1000LL * 8,
-				   speed * 1000 * 1000);
+	picos_per_byte = (USEC_PER_SEC * 8) / speed;
 
 	atomic64_set(&q->picos_per_byte, picos_per_byte);
 	netdev_dbg(dev, "taprio: set %s's picos_per_byte to: %lld, linkspeed: %d\n",
-- 
2.20.1


From a7c22edaf7192c4fd7bd9023281153f4d4802cde Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Fri, 27 Sep 2019 16:00:31 -0700
Subject: [PATCH 09/30] net: Unpublish sk from sk_reuseport_cb before call_rcu

[ Upstream commit 8c7138b33e5c690c308b2a7085f6313fdcb3f616 ]

The "reuse->sock[]" array is shared by multiple sockets.  The going away
sk must unpublish itself from "reuse->sock[]" before making call_rcu()
call.  However, this unpublish-action is currently done after a grace
period and it may cause use-after-free.

The fix is to move reuseport_detach_sock() to sk_destruct().
Due to the above reason, any socket with sk_reuseport_cb has
to go through the rcu grace period before freeing it.

It is a rather old bug (~3 yrs).  The Fixes tag is not necessary
the right commit but it is the one that introduced the SOCK_RCU_FREE
logic and this fix is depending on it.

Fixes: a4298e4522d6 ("net: add SOCK_RCU_FREE socket flag")
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index 545fac19a711..3aa93af51d48 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1700,8 +1700,6 @@ static void __sk_destruct(struct rcu_head *head)
 		sk_filter_uncharge(sk, filter);
 		RCU_INIT_POINTER(sk->sk_filter, NULL);
 	}
-	if (rcu_access_pointer(sk->sk_reuseport_cb))
-		reuseport_detach_sock(sk);
 
 	sock_disable_timestamp(sk, SK_FLAGS_TIMESTAMP);
 
@@ -1728,7 +1726,14 @@ static void __sk_destruct(struct rcu_head *head)
 
 void sk_destruct(struct sock *sk)
 {
-	if (sock_flag(sk, SOCK_RCU_FREE))
+	bool use_call_rcu = sock_flag(sk, SOCK_RCU_FREE);
+
+	if (rcu_access_pointer(sk->sk_reuseport_cb)) {
+		reuseport_detach_sock(sk);
+		use_call_rcu = true;
+	}
+
+	if (use_call_rcu)
 		call_rcu(&sk->sk_rcu, __sk_destruct);
 	else
 		__sk_destruct(&sk->sk_rcu);
-- 
2.20.1


From 3f1e8a371f7b8c1f846b377913a092f1228b77b0 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 4 Oct 2019 11:08:34 -0700
Subject: [PATCH 10/30] nfc: fix memory leak in llcp_sock_bind()

[ Upstream commit a0c2dc1fe63e2869b74c1c7f6a81d1745c8a695d ]

sysbot reported a memory leak after a bind() has failed.

While we are at it, abort the operation if kmemdup() has failed.

BUG: memory leak
unreferenced object 0xffff888105d83ec0 (size 32):
  comm "syz-executor067", pid 7207, jiffies 4294956228 (age 19.430s)
  hex dump (first 32 bytes):
    00 69 6c 65 20 72 65 61 64 00 6e 65 74 3a 5b 34  .ile read.net:[4
    30 32 36 35 33 33 30 39 37 5d 00 00 00 00 00 00  026533097]......
  backtrace:
    [<0000000036bac473>] kmemleak_alloc_recursive /./include/linux/kmemleak.h:43 [inline]
    [<0000000036bac473>] slab_post_alloc_hook /mm/slab.h:522 [inline]
    [<0000000036bac473>] slab_alloc /mm/slab.c:3319 [inline]
    [<0000000036bac473>] __do_kmalloc /mm/slab.c:3653 [inline]
    [<0000000036bac473>] __kmalloc_track_caller+0x169/0x2d0 /mm/slab.c:3670
    [<000000000cd39d07>] kmemdup+0x27/0x60 /mm/util.c:120
    [<000000008e57e5fc>] kmemdup /./include/linux/string.h:432 [inline]
    [<000000008e57e5fc>] llcp_sock_bind+0x1b3/0x230 /net/nfc/llcp_sock.c:107
    [<000000009cb0b5d3>] __sys_bind+0x11c/0x140 /net/socket.c:1647
    [<00000000492c3bbc>] __do_sys_bind /net/socket.c:1658 [inline]
    [<00000000492c3bbc>] __se_sys_bind /net/socket.c:1656 [inline]
    [<00000000492c3bbc>] __x64_sys_bind+0x1e/0x30 /net/socket.c:1656
    [<0000000008704b2a>] do_syscall_64+0x76/0x1a0 /arch/x86/entry/common.c:296
    [<000000009f4c57a4>] entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 30cc4587659e ("NFC: Move LLCP code to the NFC top level diirectory")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/nfc/llcp_sock.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index 8dfea26536c9..ccdd790e163a 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -107,9 +107,14 @@ static int llcp_sock_bind(struct socket *sock, struct sockaddr *addr, int alen)
 	llcp_sock->service_name = kmemdup(llcp_addr.service_name,
 					  llcp_sock->service_name_len,
 					  GFP_KERNEL);
-
+	if (!llcp_sock->service_name) {
+		ret = -ENOMEM;
+		goto put_dev;
+	}
 	llcp_sock->ssap = nfc_llcp_get_sdp_ssap(local, llcp_sock);
 	if (llcp_sock->ssap == LLCP_SAP_MAX) {
+		kfree(llcp_sock->service_name);
+		llcp_sock->service_name = NULL;
 		ret = -EADDRINUSE;
 		goto put_dev;
 	}
-- 
2.20.1


From 5a4cf338568683c29a7de9ffa18dc0115345e512 Mon Sep 17 00:00:00 2001
From: Reinhard Speyerer <rspmn@arcor.de>
Date: Thu, 3 Oct 2019 18:34:39 +0200
Subject: [PATCH 11/30] qmi_wwan: add support for Cinterion CLS8 devices
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit cf74ac6db25d4002089e85cc623ad149ecc25614 ]

Add support for Cinterion CLS8 devices.
Use QMI_QUIRK_SET_DTR as required for Qualcomm MDM9x07 chipsets.

T:  Bus=01 Lev=03 Prnt=05 Port=01 Cnt=02 Dev#= 25 Spd=480  MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1e2d ProdID=00b0 Rev= 3.18
S:  Manufacturer=GEMALTO
S:  Product=USB Modem
C:* #Ifs= 5 Cfg#= 1 Atr=80 MxPwr=500mA
I:* If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=(none)
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E:  Ad=83(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E:  Ad=85(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E:  Ad=87(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
E:  Ad=89(I) Atr=03(Int.) MxPS=   8 Ivl=32ms
E:  Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms

Signed-off-by: Reinhard Speyerer <rspmn@arcor.de>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index b6dc5d714b5e..3d77cd402ba9 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1350,6 +1350,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1e2d, 0x0082, 4)},	/* Cinterion PHxx,PXxx (2 RmNet) */
 	{QMI_FIXED_INTF(0x1e2d, 0x0082, 5)},	/* Cinterion PHxx,PXxx (2 RmNet) */
 	{QMI_FIXED_INTF(0x1e2d, 0x0083, 4)},	/* Cinterion PHxx,PXxx (1 RmNet + USB Audio)*/
+	{QMI_QUIRK_SET_DTR(0x1e2d, 0x00b0, 4)},	/* Cinterion CLS8 */
 	{QMI_FIXED_INTF(0x413c, 0x81a2, 8)},	/* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card */
 	{QMI_FIXED_INTF(0x413c, 0x81a3, 8)},	/* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card */
 	{QMI_FIXED_INTF(0x413c, 0x81a4, 8)},	/* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */
-- 
2.20.1


From 09b183e4137c4afef50d822f5a73b759e96ecdd6 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 3 Oct 2019 17:44:44 +0100
Subject: [PATCH 12/30] rxrpc: Fix rxrpc_recvmsg tracepoint

[ Upstream commit db9b2e0af605e7c994784527abfd9276cabd718a ]

Fix the rxrpc_recvmsg tracepoint to handle being called with a NULL call
parameter.

Fixes: a25e21f0bcd2 ("rxrpc, afs: Use debug_ids rather than pointers in traces")
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/trace/events/rxrpc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index a13a62db3565..edc5c887a44c 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -1068,7 +1068,7 @@ TRACE_EVENT(rxrpc_recvmsg,
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call->debug_id;
+		    __entry->call = call ? call->debug_id : 0;
 		    __entry->why = why;
 		    __entry->seq = seq;
 		    __entry->offset = offset;
-- 
2.20.1


From 0514f285cd8f1470f7e8c0bf50ef6910827f4f1e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 26 Sep 2019 18:24:43 -0700
Subject: [PATCH 13/30] sch_cbq: validate TCA_CBQ_WRROPT to avoid crash

[ Upstream commit e9789c7cc182484fc031fd88097eb14cb26c4596 ]

syzbot reported a crash in cbq_normalize_quanta() caused
by an out of range cl->priority.

iproute2 enforces this check, but malicious users do not.

kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] SMP KASAN PTI
Modules linked in:
CPU: 1 PID: 26447 Comm: syz-executor.1 Not tainted 5.3+ #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:cbq_normalize_quanta.part.0+0x1fd/0x430 net/sched/sch_cbq.c:902
RSP: 0018:ffff8801a5c333b0 EFLAGS: 00010206
RAX: 0000000020000003 RBX: 00000000fffffff8 RCX: ffffc9000712f000
RDX: 00000000000043bf RSI: ffffffff83be8962 RDI: 0000000100000018
RBP: ffff8801a5c33420 R08: 000000000000003a R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: 00000000000002ef
R13: ffff88018da95188 R14: dffffc0000000000 R15: 0000000000000015
FS:  00007f37d26b1700(0000) GS:ffff8801dad00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000004c7cec CR3: 00000001bcd0a006 CR4: 00000000001626f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 [<ffffffff83be9d57>] cbq_normalize_quanta include/net/pkt_sched.h:27 [inline]
 [<ffffffff83be9d57>] cbq_addprio net/sched/sch_cbq.c:1097 [inline]
 [<ffffffff83be9d57>] cbq_set_wrr+0x2d7/0x450 net/sched/sch_cbq.c:1115
 [<ffffffff83bee8a7>] cbq_change_class+0x987/0x225b net/sched/sch_cbq.c:1537
 [<ffffffff83b96985>] tc_ctl_tclass+0x555/0xcd0 net/sched/sch_api.c:2329
 [<ffffffff83a84655>] rtnetlink_rcv_msg+0x485/0xc10 net/core/rtnetlink.c:5248
 [<ffffffff83cadf0a>] netlink_rcv_skb+0x17a/0x460 net/netlink/af_netlink.c:2510
 [<ffffffff83a7db6d>] rtnetlink_rcv+0x1d/0x30 net/core/rtnetlink.c:5266
 [<ffffffff83cac2c6>] netlink_unicast_kernel net/netlink/af_netlink.c:1324 [inline]
 [<ffffffff83cac2c6>] netlink_unicast+0x536/0x720 net/netlink/af_netlink.c:1350
 [<ffffffff83cacd4a>] netlink_sendmsg+0x89a/0xd50 net/netlink/af_netlink.c:1939
 [<ffffffff8399d46e>] sock_sendmsg_nosec net/socket.c:673 [inline]
 [<ffffffff8399d46e>] sock_sendmsg+0x12e/0x170 net/socket.c:684
 [<ffffffff8399f1fd>] ___sys_sendmsg+0x81d/0x960 net/socket.c:2359
 [<ffffffff839a2d05>] __sys_sendmsg+0x105/0x1d0 net/socket.c:2397
 [<ffffffff839a2df9>] SYSC_sendmsg net/socket.c:2406 [inline]
 [<ffffffff839a2df9>] SyS_sendmsg+0x29/0x30 net/socket.c:2404
 [<ffffffff8101ccc8>] do_syscall_64+0x528/0x770 arch/x86/entry/common.c:305
 [<ffffffff84400091>] entry_SYSCALL_64_after_hwframe+0x42/0xb7

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_cbq.c | 43 +++++++++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 14 deletions(-)

diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 06c7a2da21bc..39b427dc7512 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1127,6 +1127,33 @@ static const struct nla_policy cbq_policy[TCA_CBQ_MAX + 1] = {
 	[TCA_CBQ_POLICE]	= { .len = sizeof(struct tc_cbq_police) },
 };
 
+static int cbq_opt_parse(struct nlattr *tb[TCA_CBQ_MAX + 1],
+			 struct nlattr *opt,
+			 struct netlink_ext_ack *extack)
+{
+	int err;
+
+	if (!opt) {
+		NL_SET_ERR_MSG(extack, "CBQ options are required for this operation");
+		return -EINVAL;
+	}
+
+	err = nla_parse_nested_deprecated(tb, TCA_CBQ_MAX, opt,
+					  cbq_policy, extack);
+	if (err < 0)
+		return err;
+
+	if (tb[TCA_CBQ_WRROPT]) {
+		const struct tc_cbq_wrropt *wrr = nla_data(tb[TCA_CBQ_WRROPT]);
+
+		if (wrr->priority > TC_CBQ_MAXPRIO) {
+			NL_SET_ERR_MSG(extack, "priority is bigger than TC_CBQ_MAXPRIO");
+			err = -EINVAL;
+		}
+	}
+	return err;
+}
+
 static int cbq_init(struct Qdisc *sch, struct nlattr *opt,
 		    struct netlink_ext_ack *extack)
 {
@@ -1139,13 +1166,7 @@ static int cbq_init(struct Qdisc *sch, struct nlattr *opt,
 	hrtimer_init(&q->delay_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
 	q->delay_timer.function = cbq_undelay;
 
-	if (!opt) {
-		NL_SET_ERR_MSG(extack, "CBQ options are required for this operation");
-		return -EINVAL;
-	}
-
-	err = nla_parse_nested_deprecated(tb, TCA_CBQ_MAX, opt, cbq_policy,
-					  extack);
+	err = cbq_opt_parse(tb, opt, extack);
 	if (err < 0)
 		return err;
 
@@ -1464,13 +1485,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t
 	struct cbq_class *parent;
 	struct qdisc_rate_table *rtab = NULL;
 
-	if (!opt) {
-		NL_SET_ERR_MSG(extack, "Mandatory qdisc options missing");
-		return -EINVAL;
-	}
-
-	err = nla_parse_nested_deprecated(tb, TCA_CBQ_MAX, opt, cbq_policy,
-					  extack);
+	err = cbq_opt_parse(tb, opt, extack);
 	if (err < 0)
 		return err;
 
-- 
2.20.1


From 4bef6eaa4446e1fa07dea543cfc149d33b8ee481 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 4 Oct 2019 10:34:45 -0700
Subject: [PATCH 14/30] sch_dsmark: fix potential NULL deref in dsmark_init()

[ Upstream commit 474f0813a3002cb299bb73a5a93aa1f537a80ca8 ]

Make sure TCA_DSMARK_INDICES was provided by the user.

syzbot reported :

kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] PREEMPT SMP KASAN
CPU: 1 PID: 8799 Comm: syz-executor235 Not tainted 5.3.0+ #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:nla_get_u16 include/net/netlink.h:1501 [inline]
RIP: 0010:dsmark_init net/sched/sch_dsmark.c:364 [inline]
RIP: 0010:dsmark_init+0x193/0x640 net/sched/sch_dsmark.c:339
Code: 85 db 58 0f 88 7d 03 00 00 e8 e9 1a ac fb 48 8b 9d 70 ff ff ff 48 b8 00 00 00 00 00 fc ff df 48 8d 7b 04 48 89 fa 48 c1 ea 03 <0f> b6 14 02 48 89 f8 83 e0 07 83 c0 01 38 d0 7c 08 84 d2 0f 85 ca
RSP: 0018:ffff88809426f3b8 EFLAGS: 00010247
RAX: dffffc0000000000 RBX: 0000000000000000 RCX: ffffffff85c6eb09
RDX: 0000000000000000 RSI: ffffffff85c6eb17 RDI: 0000000000000004
RBP: ffff88809426f4b0 R08: ffff88808c4085c0 R09: ffffed1015d26159
R10: ffffed1015d26158 R11: ffff8880ae930ac7 R12: ffff8880a7e96940
R13: dffffc0000000000 R14: ffff88809426f8c0 R15: 0000000000000000
FS:  0000000001292880(0000) GS:ffff8880ae900000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000020000080 CR3: 000000008ca1b000 CR4: 00000000001406e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 qdisc_create+0x4ee/0x1210 net/sched/sch_api.c:1237
 tc_modify_qdisc+0x524/0x1c50 net/sched/sch_api.c:1653
 rtnetlink_rcv_msg+0x463/0xb00 net/core/rtnetlink.c:5223
 netlink_rcv_skb+0x177/0x450 net/netlink/af_netlink.c:2477
 rtnetlink_rcv+0x1d/0x30 net/core/rtnetlink.c:5241
 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
 netlink_unicast+0x531/0x710 net/netlink/af_netlink.c:1328
 netlink_sendmsg+0x8a5/0xd60 net/netlink/af_netlink.c:1917
 sock_sendmsg_nosec net/socket.c:637 [inline]
 sock_sendmsg+0xd7/0x130 net/socket.c:657
 ___sys_sendmsg+0x803/0x920 net/socket.c:2311
 __sys_sendmsg+0x105/0x1d0 net/socket.c:2356
 __do_sys_sendmsg net/socket.c:2365 [inline]
 __se_sys_sendmsg net/socket.c:2363 [inline]
 __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2363
 do_syscall_64+0xfa/0x760 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x440369

Fixes: 758cc43c6d73 ("[PKT_SCHED]: Fix dsmark to apply changes consistent")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_dsmark.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index bad1cbe59a56..05605b30bef3 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -361,6 +361,8 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt,
 		goto errout;
 
 	err = -EINVAL;
+	if (!tb[TCA_DSMARK_INDICES])
+		goto errout;
 	indices = nla_get_u16(tb[TCA_DSMARK_INDICES]);
 
 	if (hweight32(indices) != 1)
-- 
2.20.1


From 5ad256c2a095b1fea33f4f61916657c8e08df567 Mon Sep 17 00:00:00 2001
From: Tuong Lien <tuong.t.lien@dektech.com.au>
Date: Wed, 2 Oct 2019 18:49:43 +0700
Subject: [PATCH 15/30] tipc: fix unlimited bundling of small messages

[ Upstream commit e95584a889e1902fdf1ded9712e2c3c3083baf96 ]

We have identified a problem with the "oversubscription" policy in the
link transmission code.

When small messages are transmitted, and the sending link has reached
the transmit window limit, those messages will be bundled and put into
the link backlog queue. However, bundles of data messages are counted
at the 'CRITICAL' level, so that the counter for that level, instead of
the counter for the real, bundled message's level is the one being
increased.
Subsequent, to-be-bundled data messages at non-CRITICAL levels continue
to be tested against the unchanged counter for their own level, while
contributing to an unrestrained increase at the CRITICAL backlog level.

This leaves a gap in congestion control algorithm for small messages
that can result in starvation for other users or a "real" CRITICAL
user. Even that eventually can lead to buffer exhaustion & link reset.

We fix this by keeping a 'target_bskb' buffer pointer at each levels,
then when bundling, we only bundle messages at the same importance
level only. This way, we know exactly how many slots a certain level
have occupied in the queue, so can manage level congestion accurately.

By bundling messages at the same level, we even have more benefits. Let
consider this:
- One socket sends 64-byte messages at the 'CRITICAL' level;
- Another sends 4096-byte messages at the 'LOW' level;

When a 64-byte message comes and is bundled the first time, we put the
overhead of message bundle to it (+ 40-byte header, data copy, etc.)
for later use, but the next message can be a 4096-byte one that cannot
be bundled to the previous one. This means the last bundle carries only
one payload message which is totally inefficient, as for the receiver
also! Later on, another 64-byte message comes, now we make a new bundle
and the same story repeats...

With the new bundling algorithm, this will not happen, the 64-byte
messages will be bundled together even when the 4096-byte message(s)
comes in between. However, if the 4096-byte messages are sent at the
same level i.e. 'CRITICAL', the bundling algorithm will again cause the
same overhead.

Also, the same will happen even with only one socket sending small
messages at a rate close to the link transmit's one, so that, when one
message is bundled, it's transmitted shortly. Then, another message
comes, a new bundle is created and so on...

We will solve this issue radically by another patch.

Fixes: 365ad353c256 ("tipc: reduce risk of user starvation during link congestion")
Reported-by: Hoang Le <hoang.h.le@dektech.com.au>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Tuong Lien <tuong.t.lien@dektech.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/link.c | 29 ++++++++++++++++++-----------
 net/tipc/msg.c  |  5 +----
 2 files changed, 19 insertions(+), 15 deletions(-)

diff --git a/net/tipc/link.c b/net/tipc/link.c
index c2c5c53cad22..b0063d05599e 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -160,6 +160,7 @@ struct tipc_link {
 	struct {
 		u16 len;
 		u16 limit;
+		struct sk_buff *target_bskb;
 	} backlog[5];
 	u16 snd_nxt;
 	u16 window;
@@ -866,6 +867,7 @@ static void link_prepare_wakeup(struct tipc_link *l)
 void tipc_link_reset(struct tipc_link *l)
 {
 	struct sk_buff_head list;
+	u32 imp;
 
 	__skb_queue_head_init(&list);
 
@@ -887,11 +889,10 @@ void tipc_link_reset(struct tipc_link *l)
 	__skb_queue_purge(&l->deferdq);
 	__skb_queue_purge(&l->backlogq);
 	__skb_queue_purge(&l->failover_deferdq);
-	l->backlog[TIPC_LOW_IMPORTANCE].len = 0;
-	l->backlog[TIPC_MEDIUM_IMPORTANCE].len = 0;
-	l->backlog[TIPC_HIGH_IMPORTANCE].len = 0;
-	l->backlog[TIPC_CRITICAL_IMPORTANCE].len = 0;
-	l->backlog[TIPC_SYSTEM_IMPORTANCE].len = 0;
+	for (imp = 0; imp <= TIPC_SYSTEM_IMPORTANCE; imp++) {
+		l->backlog[imp].len = 0;
+		l->backlog[imp].target_bskb = NULL;
+	}
 	kfree_skb(l->reasm_buf);
 	kfree_skb(l->failover_reasm_skb);
 	l->reasm_buf = NULL;
@@ -931,7 +932,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
 	u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1;
 	struct sk_buff_head *transmq = &l->transmq;
 	struct sk_buff_head *backlogq = &l->backlogq;
-	struct sk_buff *skb, *_skb, *bskb;
+	struct sk_buff *skb, *_skb, **tskb;
 	int pkt_cnt = skb_queue_len(list);
 	int rc = 0;
 
@@ -980,19 +981,21 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
 			seqno++;
 			continue;
 		}
-		if (tipc_msg_bundle(skb_peek_tail(backlogq), hdr, mtu)) {
+		tskb = &l->backlog[imp].target_bskb;
+		if (tipc_msg_bundle(*tskb, hdr, mtu)) {
 			kfree_skb(__skb_dequeue(list));
 			l->stats.sent_bundled++;
 			continue;
 		}
-		if (tipc_msg_make_bundle(&bskb, hdr, mtu, l->addr)) {
+		if (tipc_msg_make_bundle(tskb, hdr, mtu, l->addr)) {
 			kfree_skb(__skb_dequeue(list));
-			__skb_queue_tail(backlogq, bskb);
-			l->backlog[msg_importance(buf_msg(bskb))].len++;
+			__skb_queue_tail(backlogq, *tskb);
+			l->backlog[imp].len++;
 			l->stats.sent_bundled++;
 			l->stats.sent_bundles++;
 			continue;
 		}
+		l->backlog[imp].target_bskb = NULL;
 		l->backlog[imp].len += skb_queue_len(list);
 		skb_queue_splice_tail_init(list, backlogq);
 	}
@@ -1008,6 +1011,7 @@ static void tipc_link_advance_backlog(struct tipc_link *l,
 	u16 seqno = l->snd_nxt;
 	u16 ack = l->rcv_nxt - 1;
 	u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1;
+	u32 imp;
 
 	while (skb_queue_len(&l->transmq) < l->window) {
 		skb = skb_peek(&l->backlogq);
@@ -1018,7 +1022,10 @@ static void tipc_link_advance_backlog(struct tipc_link *l,
 			break;
 		__skb_dequeue(&l->backlogq);
 		hdr = buf_msg(skb);
-		l->backlog[msg_importance(hdr)].len--;
+		imp = msg_importance(hdr);
+		l->backlog[imp].len--;
+		if (unlikely(skb == l->backlog[imp].target_bskb))
+			l->backlog[imp].target_bskb = NULL;
 		__skb_queue_tail(&l->transmq, skb);
 		/* next retransmit attempt */
 		if (link_is_bc_sndlink(l))
diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index f48e5857210f..b956ce4a40ef 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -484,10 +484,7 @@ bool tipc_msg_make_bundle(struct sk_buff **skb,  struct tipc_msg *msg,
 	bmsg = buf_msg(_skb);
 	tipc_msg_init(msg_prevnode(msg), bmsg, MSG_BUNDLER, 0,
 		      INT_H_SIZE, dnode);
-	if (msg_isdata(msg))
-		msg_set_importance(bmsg, TIPC_CRITICAL_IMPORTANCE);
-	else
-		msg_set_importance(bmsg, TIPC_SYSTEM_IMPORTANCE);
+	msg_set_importance(bmsg, msg_importance(msg));
 	msg_set_seqno(bmsg, msg_seqno(msg));
 	msg_set_ack(bmsg, msg_ack(msg));
 	msg_set_bcast_ack(bmsg, msg_bcast_ack(msg));
-- 
2.20.1


From 5f33439961cc68a886e1ba7015b7c61e5f08ce43 Mon Sep 17 00:00:00 2001
From: Josh Hunt <johunt@akamai.com>
Date: Wed, 2 Oct 2019 13:29:22 -0400
Subject: [PATCH 16/30] udp: fix gso_segs calculations

[ Upstream commit 44b321e5020d782ad6e8ae8183f09b163be6e6e2 ]

Commit dfec0ee22c0a ("udp: Record gso_segs when supporting UDP segmentation offload")
added gso_segs calculation, but incorrectly got sizeof() the pointer and
not the underlying data type. In addition let's fix the v6 case.

Fixes: bec1f6f69736 ("udp: generate gso with UDP_SEGMENT")
Fixes: dfec0ee22c0a ("udp: Record gso_segs when supporting UDP segmentation offload")
Signed-off-by: Josh Hunt <johunt@akamai.com>
Reviewed-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 2 +-
 net/ipv6/udp.c | 2 ++
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 16486c8b708b..3dda209f9e79 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -856,7 +856,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4,
 
 		skb_shinfo(skb)->gso_size = cork->gso_size;
 		skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
-		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(len - sizeof(uh),
+		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(len - sizeof(*uh),
 							 cork->gso_size);
 		goto csum_partial;
 	}
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 5995fdc99d3f..a23580d2af8c 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1143,6 +1143,8 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6,
 
 		skb_shinfo(skb)->gso_size = cork->gso_size;
 		skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
+		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(len - sizeof(*uh),
+							 cork->gso_size);
 		goto csum_partial;
 	}
 
-- 
2.20.1


From ed08413cfb3742215d07014a6ea5ecf88336e952 Mon Sep 17 00:00:00 2001
From: Dexuan Cui <decui@microsoft.com>
Date: Mon, 30 Sep 2019 18:43:50 +0000
Subject: [PATCH 17/30] vsock: Fix a lockdep warning in __vsock_release()

[ Upstream commit 0d9138ffac24cf8b75366ede3a68c951e6dcc575 ]

Lockdep is unhappy if two locks from the same class are held.

Fix the below warning for hyperv and virtio sockets (vmci socket code
doesn't have the issue) by using lock_sock_nested() when __vsock_release()
is called recursively:

============================================
WARNING: possible recursive locking detected
5.3.0+ #1 Not tainted
--------------------------------------------
server/1795 is trying to acquire lock:
ffff8880c5158990 (sk_lock-AF_VSOCK){+.+.}, at: hvs_release+0x10/0x120 [hv_sock]

but task is already holding lock:
ffff8880c5158150 (sk_lock-AF_VSOCK){+.+.}, at: __vsock_release+0x2e/0xf0 [vsock]

other info that might help us debug this:
 Possible unsafe locking scenario:

       CPU0
       ----
  lock(sk_lock-AF_VSOCK);
  lock(sk_lock-AF_VSOCK);

 *** DEADLOCK ***

 May be due to missing lock nesting notation

2 locks held by server/1795:
 #0: ffff8880c5d05ff8 (&sb->s_type->i_mutex_key#10){+.+.}, at: __sock_release+0x2d/0xa0
 #1: ffff8880c5158150 (sk_lock-AF_VSOCK){+.+.}, at: __vsock_release+0x2e/0xf0 [vsock]

stack backtrace:
CPU: 5 PID: 1795 Comm: server Not tainted 5.3.0+ #1
Call Trace:
 dump_stack+0x67/0x90
 __lock_acquire.cold.67+0xd2/0x20b
 lock_acquire+0xb5/0x1c0
 lock_sock_nested+0x6d/0x90
 hvs_release+0x10/0x120 [hv_sock]
 __vsock_release+0x24/0xf0 [vsock]
 __vsock_release+0xa0/0xf0 [vsock]
 vsock_release+0x12/0x30 [vsock]
 __sock_release+0x37/0xa0
 sock_close+0x14/0x20
 __fput+0xc1/0x250
 task_work_run+0x98/0xc0
 do_exit+0x344/0xc60
 do_group_exit+0x47/0xb0
 get_signal+0x15c/0xc50
 do_signal+0x30/0x720
 exit_to_usermode_loop+0x50/0xa0
 do_syscall_64+0x24e/0x270
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x7f4184e85f31

Tested-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/vmw_vsock/af_vsock.c                | 16 ++++++++++++----
 net/vmw_vsock/hyperv_transport.c        |  2 +-
 net/vmw_vsock/virtio_transport_common.c |  2 +-
 3 files changed, 14 insertions(+), 6 deletions(-)

diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index ab47bf3ab66e..2ab43b2bba31 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -638,7 +638,7 @@ struct sock *__vsock_create(struct net *net,
 }
 EXPORT_SYMBOL_GPL(__vsock_create);
 
-static void __vsock_release(struct sock *sk)
+static void __vsock_release(struct sock *sk, int level)
 {
 	if (sk) {
 		struct sk_buff *skb;
@@ -648,9 +648,17 @@ static void __vsock_release(struct sock *sk)
 		vsk = vsock_sk(sk);
 		pending = NULL;	/* Compiler warning. */
 
+		/* The release call is supposed to use lock_sock_nested()
+		 * rather than lock_sock(), if a sock lock should be acquired.
+		 */
 		transport->release(vsk);
 
-		lock_sock(sk);
+		/* When "level" is SINGLE_DEPTH_NESTING, use the nested
+		 * version to avoid the warning "possible recursive locking
+		 * detected". When "level" is 0, lock_sock_nested(sk, level)
+		 * is the same as lock_sock(sk).
+		 */
+		lock_sock_nested(sk, level);
 		sock_orphan(sk);
 		sk->sk_shutdown = SHUTDOWN_MASK;
 
@@ -659,7 +667,7 @@ static void __vsock_release(struct sock *sk)
 
 		/* Clean up any sockets that never were accepted. */
 		while ((pending = vsock_dequeue_accept(sk)) != NULL) {
-			__vsock_release(pending);
+			__vsock_release(pending, SINGLE_DEPTH_NESTING);
 			sock_put(pending);
 		}
 
@@ -708,7 +716,7 @@ EXPORT_SYMBOL_GPL(vsock_stream_has_space);
 
 static int vsock_release(struct socket *sock)
 {
-	__vsock_release(sock->sk);
+	__vsock_release(sock->sk, 0);
 	sock->sk = NULL;
 	sock->state = SS_FREE;
 
diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c
index 9d864ebeb7b3..4b126b21b453 100644
--- a/net/vmw_vsock/hyperv_transport.c
+++ b/net/vmw_vsock/hyperv_transport.c
@@ -559,7 +559,7 @@ static void hvs_release(struct vsock_sock *vsk)
 	struct sock *sk = sk_vsock(vsk);
 	bool remove_sock;
 
-	lock_sock(sk);
+	lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
 	remove_sock = hvs_close_lock_held(vsk);
 	release_sock(sk);
 	if (remove_sock)
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 6f1a8aff65c5..a7adffd062c7 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -790,7 +790,7 @@ void virtio_transport_release(struct vsock_sock *vsk)
 	struct sock *sk = &vsk->sk;
 	bool remove_sock = true;
 
-	lock_sock(sk);
+	lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
 	if (sk->sk_type == SOCK_STREAM)
 		remove_sock = virtio_transport_close(vsk);
 
-- 
2.20.1


From 790ed71547e574e2d12010e7ca9e5e18a5806ea0 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Tue, 1 Oct 2019 16:28:43 +0200
Subject: [PATCH 18/30] net: dsa: rtl8366: Check VLAN ID and not ports

[ Upstream commit e8521e53cca584ddf8ec4584d3c550a6c65f88c4 ]

There has been some confusion between the port number and
the VLAN ID in this driver. What we need to check for
validity is the VLAN ID, nothing else.

The current confusion came from assigning a few default
VLANs for default routing and we need to rewrite that
properly.

Instead of checking if the port number is a valid VLAN
ID, check the actual VLAN IDs passed in to the callback
one by one as expected.

Fixes: d8652956cf37 ("net: dsa: realtek-smi: Add Realtek SMI driver")
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/rtl8366.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/net/dsa/rtl8366.c b/drivers/net/dsa/rtl8366.c
index ca3d17e43ed8..ac88caca5ad4 100644
--- a/drivers/net/dsa/rtl8366.c
+++ b/drivers/net/dsa/rtl8366.c
@@ -339,10 +339,12 @@ int rtl8366_vlan_prepare(struct dsa_switch *ds, int port,
 			 const struct switchdev_obj_port_vlan *vlan)
 {
 	struct realtek_smi *smi = ds->priv;
+	u16 vid;
 	int ret;
 
-	if (!smi->ops->is_vlan_valid(smi, port))
-		return -EINVAL;
+	for (vid = vlan->vid_begin; vid < vlan->vid_end; vid++)
+		if (!smi->ops->is_vlan_valid(smi, vid))
+			return -EINVAL;
 
 	dev_info(smi->dev, "prepare VLANs %04x..%04x\n",
 		 vlan->vid_begin, vlan->vid_end);
@@ -370,8 +372,9 @@ void rtl8366_vlan_add(struct dsa_switch *ds, int port,
 	u16 vid;
 	int ret;
 
-	if (!smi->ops->is_vlan_valid(smi, port))
-		return;
+	for (vid = vlan->vid_begin; vid < vlan->vid_end; vid++)
+		if (!smi->ops->is_vlan_valid(smi, vid))
+			return;
 
 	dev_info(smi->dev, "add VLAN on port %d, %s, %s\n",
 		 port,
-- 
2.20.1


From dfbe115d2a8770ce02b2454ea6ab225c2c69eb61 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 30 Sep 2019 15:44:44 -0700
Subject: [PATCH 19/30] tcp: adjust rto_base in retransmits_timed_out()

[ Upstream commit 3256a2d6ab1f71f9a1bd2d7f6f18eb8108c48d17 ]

The cited commit exposed an old retransmits_timed_out() bug
which assumed it could call tcp_model_timeout() with
TCP_RTO_MIN as rto_base for all states.

But flows in SYN_SENT or SYN_RECV state uses a different
RTO base (1 sec instead of 200 ms, unless BPF choses
another value)

This caused a reduction of SYN retransmits from 6 to 4 with
the default /proc/sys/net/ipv4/tcp_syn_retries value.

Fixes: a41e8a88b06e ("tcp: better handle TCP_USER_TIMEOUT in SYN_SENT state")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Marek Majkowski <marek@cloudflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_timer.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 3e8b38c73d8c..483323332d74 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -198,8 +198,13 @@ static bool retransmits_timed_out(struct sock *sk,
 		return false;
 
 	start_ts = tcp_sk(sk)->retrans_stamp;
-	if (likely(timeout == 0))
-		timeout = tcp_model_timeout(sk, boundary, TCP_RTO_MIN);
+	if (likely(timeout == 0)) {
+		unsigned int rto_base = TCP_RTO_MIN;
+
+		if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))
+			rto_base = tcp_timeout_init(sk);
+		timeout = tcp_model_timeout(sk, boundary, rto_base);
+	}
 
 	return (s32)(tcp_time_stamp(tcp_sk(sk)) - start_ts - timeout) >= 0;
 }
-- 
2.20.1


From 672d68d1c7e72a61fea1e738d1cb6ebd7f1d80a1 Mon Sep 17 00:00:00 2001
From: Josh Hunt <johunt@akamai.com>
Date: Wed, 2 Oct 2019 13:29:23 -0400
Subject: [PATCH 20/30] udp: only do GSO if # of segs > 1

[ Upstream commit 4094871db1d65810acab3d57f6089aa39ef7f648 ]

Prior to this change an application sending <= 1MSS worth of data and
enabling UDP GSO would fail if the system had SW GSO enabled, but the
same send would succeed if HW GSO offload is enabled. In addition to this
inconsistency the error in the SW GSO case does not get back to the
application if sending out of a real device so the user is unaware of this
failure.

With this change we only perform GSO if the # of segments is > 1 even
if the application has enabled segmentation. I've also updated the
relevant udpgso selftests.

Fixes: bec1f6f69736 ("udp: generate gso with UDP_SEGMENT")
Signed-off-by: Josh Hunt <johunt@akamai.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c                       | 11 +++++++----
 net/ipv6/udp.c                       | 11 +++++++----
 tools/testing/selftests/net/udpgso.c | 16 ++++------------
 3 files changed, 18 insertions(+), 20 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 3dda209f9e79..5e5d0575a43c 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -821,6 +821,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4,
 	int is_udplite = IS_UDPLITE(sk);
 	int offset = skb_transport_offset(skb);
 	int len = skb->len - offset;
+	int datalen = len - sizeof(*uh);
 	__wsum csum = 0;
 
 	/*
@@ -854,10 +855,12 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4,
 			return -EIO;
 		}
 
-		skb_shinfo(skb)->gso_size = cork->gso_size;
-		skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
-		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(len - sizeof(*uh),
-							 cork->gso_size);
+		if (datalen > cork->gso_size) {
+			skb_shinfo(skb)->gso_size = cork->gso_size;
+			skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
+			skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(datalen,
+								 cork->gso_size);
+		}
 		goto csum_partial;
 	}
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index a23580d2af8c..0454a8a3b39c 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1109,6 +1109,7 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6,
 	__wsum csum = 0;
 	int offset = skb_transport_offset(skb);
 	int len = skb->len - offset;
+	int datalen = len - sizeof(*uh);
 
 	/*
 	 * Create a UDP header
@@ -1141,10 +1142,12 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6,
 			return -EIO;
 		}
 
-		skb_shinfo(skb)->gso_size = cork->gso_size;
-		skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
-		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(len - sizeof(*uh),
-							 cork->gso_size);
+		if (datalen > cork->gso_size) {
+			skb_shinfo(skb)->gso_size = cork->gso_size;
+			skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
+			skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(datalen,
+								 cork->gso_size);
+		}
 		goto csum_partial;
 	}
 
diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c
index b8265ee9923f..614b31aad168 100644
--- a/tools/testing/selftests/net/udpgso.c
+++ b/tools/testing/selftests/net/udpgso.c
@@ -89,12 +89,9 @@ struct testcase testcases_v4[] = {
 		.tfail = true,
 	},
 	{
-		/* send a single MSS: will fail with GSO, because the segment
-		 * logic in udp4_ufo_fragment demands a gso skb to be > MTU
-		 */
+		/* send a single MSS: will fall back to no GSO */
 		.tlen = CONST_MSS_V4,
 		.gso_len = CONST_MSS_V4,
-		.tfail = true,
 		.r_num_mss = 1,
 	},
 	{
@@ -139,10 +136,9 @@ struct testcase testcases_v4[] = {
 		.tfail = true,
 	},
 	{
-		/* send a single 1B MSS: will fail, see single MSS above */
+		/* send a single 1B MSS: will fall back to no GSO */
 		.tlen = 1,
 		.gso_len = 1,
-		.tfail = true,
 		.r_num_mss = 1,
 	},
 	{
@@ -196,12 +192,9 @@ struct testcase testcases_v6[] = {
 		.tfail = true,
 	},
 	{
-		/* send a single MSS: will fail with GSO, because the segment
-		 * logic in udp4_ufo_fragment demands a gso skb to be > MTU
-		 */
+		/* send a single MSS: will fall back to no GSO */
 		.tlen = CONST_MSS_V6,
 		.gso_len = CONST_MSS_V6,
-		.tfail = true,
 		.r_num_mss = 1,
 	},
 	{
@@ -246,10 +239,9 @@ struct testcase testcases_v6[] = {
 		.tfail = true,
 	},
 	{
-		/* send a single 1B MSS: will fail, see single MSS above */
+		/* send a single 1B MSS: will fall back to no GSO */
 		.tlen = 1,
 		.gso_len = 1,
-		.tfail = true,
 		.r_num_mss = 1,
 	},
 	{
-- 
2.20.1


From b5247e2f230fc44d726bb3cf647033da62b1faac Mon Sep 17 00:00:00 2001
From: Dotan Barak <dotanb@dev.mellanox.co.il>
Date: Tue, 1 Oct 2019 10:21:02 -0700
Subject: [PATCH 21/30] net/rds: Fix error handling in rds_ib_add_one()

[ Upstream commit d64bf89a75b65f83f06be9fb8f978e60d53752db ]

rds_ibdev:ipaddr_list and rds_ibdev:conn_list are initialized
after allocation some resources such as protection domain.
If allocation of such resources fail, then these uninitialized
variables are accessed in rds_ib_dev_free() in failure path. This
can potentially crash the system. The code has been updated to
initialize these variables very early in the function.

Signed-off-by: Dotan Barak <dotanb@dev.mellanox.co.il>
Signed-off-by: Sudhakar Dindukurti <sudhakar.dindukurti@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/ib.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/rds/ib.c b/net/rds/ib.c
index 45acab2de0cf..9de2ae22d583 100644
--- a/net/rds/ib.c
+++ b/net/rds/ib.c
@@ -143,6 +143,9 @@ static void rds_ib_add_one(struct ib_device *device)
 	refcount_set(&rds_ibdev->refcount, 1);
 	INIT_WORK(&rds_ibdev->free_work, rds_ib_dev_free);
 
+	INIT_LIST_HEAD(&rds_ibdev->ipaddr_list);
+	INIT_LIST_HEAD(&rds_ibdev->conn_list);
+
 	rds_ibdev->max_wrs = device->attrs.max_qp_wr;
 	rds_ibdev->max_sge = min(device->attrs.max_send_sge, RDS_IB_MAX_SGE);
 
@@ -203,9 +206,6 @@ static void rds_ib_add_one(struct ib_device *device)
 		device->name,
 		rds_ibdev->use_fastreg ? "FRMR" : "FMR");
 
-	INIT_LIST_HEAD(&rds_ibdev->ipaddr_list);
-	INIT_LIST_HEAD(&rds_ibdev->conn_list);
-
 	down_write(&rds_ib_devices_lock);
 	list_add_tail_rcu(&rds_ibdev->list, &rds_ib_devices);
 	up_write(&rds_ib_devices_lock);
-- 
2.20.1


From 093df37b706f4f32370fed73ce80e6223ef87a4d Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Tue, 1 Oct 2019 21:58:18 +0300
Subject: [PATCH 22/30] net: dsa: sja1105: Initialize the meta_lock

[ Upstream commit d6530e5ad45089c018c3cc5b5957a34721249f6f ]

Otherwise, with CONFIG_DEBUG_SPINLOCK=y, this stack trace gets printed
when enabling RX timestamping and receiving a PTP frame:

[  318.537078] INFO: trying to register non-static key.
[  318.542040] the code is fine but needs lockdep annotation.
[  318.547500] turning off the locking correctness validator.
[  318.552972] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.3.0-13257-g0825b0669811-dirty #1962
[  318.561283] Hardware name: Freescale LS1021A
[  318.565566] [<c03144bc>] (unwind_backtrace) from [<c030e164>] (show_stack+0x10/0x14)
[  318.573289] [<c030e164>] (show_stack) from [<c11b9f50>] (dump_stack+0xd4/0x100)
[  318.580579] [<c11b9f50>] (dump_stack) from [<c03b9b40>] (register_lock_class+0x728/0x734)
[  318.588731] [<c03b9b40>] (register_lock_class) from [<c03b60c4>] (__lock_acquire+0x78/0x25cc)
[  318.597227] [<c03b60c4>] (__lock_acquire) from [<c03b8ef8>] (lock_acquire+0xd8/0x234)
[  318.605033] [<c03b8ef8>] (lock_acquire) from [<c11db934>] (_raw_spin_lock+0x44/0x54)
[  318.612755] [<c11db934>] (_raw_spin_lock) from [<c1164370>] (sja1105_rcv+0x1f8/0x4e8)
[  318.620561] [<c1164370>] (sja1105_rcv) from [<c115d7cc>] (dsa_switch_rcv+0x80/0x204)
[  318.628283] [<c115d7cc>] (dsa_switch_rcv) from [<c0f58c80>] (__netif_receive_skb_one_core+0x50/0x6c)
[  318.637386] [<c0f58c80>] (__netif_receive_skb_one_core) from [<c0f58f04>] (netif_receive_skb_internal+0xac/0x264)
[  318.647611] [<c0f58f04>] (netif_receive_skb_internal) from [<c0f59e98>] (napi_gro_receive+0x1d8/0x338)
[  318.656887] [<c0f59e98>] (napi_gro_receive) from [<c0c298a4>] (gfar_clean_rx_ring+0x328/0x724)
[  318.665472] [<c0c298a4>] (gfar_clean_rx_ring) from [<c0c29e60>] (gfar_poll_rx_sq+0x34/0x94)
[  318.673795] [<c0c29e60>] (gfar_poll_rx_sq) from [<c0f5b40c>] (net_rx_action+0x128/0x4f8)
[  318.681860] [<c0f5b40c>] (net_rx_action) from [<c03022f0>] (__do_softirq+0x148/0x5ac)
[  318.689666] [<c03022f0>] (__do_softirq) from [<c0355af4>] (irq_exit+0x160/0x170)
[  318.697040] [<c0355af4>] (irq_exit) from [<c03c6818>] (__handle_domain_irq+0x60/0xb4)
[  318.704847] [<c03c6818>] (__handle_domain_irq) from [<c07e9440>] (gic_handle_irq+0x58/0x9c)
[  318.713172] [<c07e9440>] (gic_handle_irq) from [<c0301a70>] (__irq_svc+0x70/0x98)
[  318.720622] Exception stack(0xc2001f18 to 0xc2001f60)
[  318.725656] 1f00:                                                       00000001 00000006
[  318.733805] 1f20: 00000000 c20165c0 ffffe000 c2010cac c2010cf4 00000001 00000000 c2010c88
[  318.741955] 1f40: c1f7a5a8 00000000 00000000 c2001f68 c03ba140 c030a288 200e0013 ffffffff
[  318.750110] [<c0301a70>] (__irq_svc) from [<c030a288>] (arch_cpu_idle+0x24/0x3c)
[  318.757486] [<c030a288>] (arch_cpu_idle) from [<c038a480>] (do_idle+0x1b8/0x2a4)
[  318.764859] [<c038a480>] (do_idle) from [<c038a94c>] (cpu_startup_entry+0x18/0x1c)
[  318.772407] [<c038a94c>] (cpu_startup_entry) from [<c1e00f10>] (start_kernel+0x4cc/0x4fc)

Fixes: 844d7edc6a34 ("net: dsa: sja1105: Add a global sja1105_tagger_data structure")
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/sja1105/sja1105_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index df976b259e43..96ab77bcd960 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -2165,6 +2165,7 @@ static int sja1105_probe(struct spi_device *spi)
 	tagger_data = &priv->tagger_data;
 	skb_queue_head_init(&tagger_data->skb_rxtstamp_queue);
 	INIT_WORK(&tagger_data->rxtstamp_work, sja1105_rxtstamp_work);
+	spin_lock_init(&tagger_data->meta_lock);
 
 	/* Connections between dsa_port and sja1105_port */
 	for (i = 0; i < SJA1105_NUM_PORTS; i++) {
-- 
2.20.1


From eb654b8fba127c074b32310eaa2675d3a0bf4edd Mon Sep 17 00:00:00 2001
From: Dongli Zhang <dongli.zhang@oracle.com>
Date: Tue, 1 Oct 2019 21:56:41 +0800
Subject: [PATCH 23/30] xen-netfront: do not use ~0U as error return value for
 xennet_fill_frags()

[ Upstream commit a761129e3625688310aecf26e1be9e98e85f8eb5 ]

xennet_fill_frags() uses ~0U as return value when the sk_buff is not able
to cache extra fragments. This is incorrect because the return type of
xennet_fill_frags() is RING_IDX and 0xffffffff is an expected value for
ring buffer index.

In the situation when the rsp_cons is approaching 0xffffffff, the return
value of xennet_fill_frags() may become 0xffffffff which xennet_poll() (the
caller) would regard as error. As a result, queue->rx.rsp_cons is set
incorrectly because it is updated only when there is error. If there is no
error, xennet_poll() would be responsible to update queue->rx.rsp_cons.
Finally, queue->rx.rsp_cons would point to the rx ring buffer entries whose
queue->rx_skbs[i] and queue->grant_rx_ref[i] are already cleared to NULL.
This leads to NULL pointer access in the next iteration to process rx ring
buffer entries.

The symptom is similar to the one fixed in
commit 00b368502d18 ("xen-netfront: do not assume sk_buff_head list is
empty in error handling").

This patch changes the return type of xennet_fill_frags() to indicate
whether it is successful or failed. The queue->rx.rsp_cons will be
always updated inside this function.

Fixes: ad4f15dc2c70 ("xen/netfront: don't bug in case of too many frags")
Signed-off-by: Dongli Zhang <dongli.zhang@oracle.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netfront.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 5f5722bf6762..7370e06a0e4b 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -887,9 +887,9 @@ static int xennet_set_skb_gso(struct sk_buff *skb,
 	return 0;
 }
 
-static RING_IDX xennet_fill_frags(struct netfront_queue *queue,
-				  struct sk_buff *skb,
-				  struct sk_buff_head *list)
+static int xennet_fill_frags(struct netfront_queue *queue,
+			     struct sk_buff *skb,
+			     struct sk_buff_head *list)
 {
 	RING_IDX cons = queue->rx.rsp_cons;
 	struct sk_buff *nskb;
@@ -908,7 +908,7 @@ static RING_IDX xennet_fill_frags(struct netfront_queue *queue,
 		if (unlikely(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS)) {
 			queue->rx.rsp_cons = ++cons + skb_queue_len(list);
 			kfree_skb(nskb);
-			return ~0U;
+			return -ENOENT;
 		}
 
 		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
@@ -919,7 +919,9 @@ static RING_IDX xennet_fill_frags(struct netfront_queue *queue,
 		kfree_skb(nskb);
 	}
 
-	return cons;
+	queue->rx.rsp_cons = cons;
+
+	return 0;
 }
 
 static int checksum_setup(struct net_device *dev, struct sk_buff *skb)
@@ -1045,8 +1047,7 @@ static int xennet_poll(struct napi_struct *napi, int budget)
 		skb->data_len = rx->status;
 		skb->len += rx->status;
 
-		i = xennet_fill_frags(queue, skb, &tmpq);
-		if (unlikely(i == ~0U))
+		if (unlikely(xennet_fill_frags(queue, skb, &tmpq)))
 			goto err;
 
 		if (rx->flags & XEN_NETRXF_csum_blank)
@@ -1056,7 +1057,7 @@ static int xennet_poll(struct napi_struct *napi, int budget)
 
 		__skb_queue_tail(&rxq, skb);
 
-		queue->rx.rsp_cons = ++i;
+		i = ++queue->rx.rsp_cons;
 		work_done++;
 	}
 
-- 
2.20.1


From 7df201c2ac6419b49c71188c46934771604081c5 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Tue, 1 Oct 2019 21:58:19 +0300
Subject: [PATCH 24/30] net: dsa: sja1105: Fix sleeping while atomic in
 .port_hwtstamp_set

[ Upstream commit 3e8db7e56082156a37b71d7334860c10fcea8025 ]

Currently this stack trace can be seen with CONFIG_DEBUG_ATOMIC_SLEEP=y:

[   41.568348] BUG: sleeping function called from invalid context at kernel/locking/mutex.c:909
[   41.576757] in_atomic(): 1, irqs_disabled(): 0, pid: 208, name: ptp4l
[   41.583212] INFO: lockdep is turned off.
[   41.587123] CPU: 1 PID: 208 Comm: ptp4l Not tainted 5.3.0-rc6-01445-ge950f2d4bc7f-dirty #1827
[   41.599873] [<c0313d7c>] (unwind_backtrace) from [<c030e13c>] (show_stack+0x10/0x14)
[   41.607584] [<c030e13c>] (show_stack) from [<c1212d50>] (dump_stack+0xd4/0x100)
[   41.614863] [<c1212d50>] (dump_stack) from [<c037dfc8>] (___might_sleep+0x1c8/0x2b4)
[   41.622574] [<c037dfc8>] (___might_sleep) from [<c122ea90>] (__mutex_lock+0x48/0xab8)
[   41.630368] [<c122ea90>] (__mutex_lock) from [<c122f51c>] (mutex_lock_nested+0x1c/0x24)
[   41.638340] [<c122f51c>] (mutex_lock_nested) from [<c0c6fe08>] (sja1105_static_config_reload+0x30/0x27c)
[   41.647779] [<c0c6fe08>] (sja1105_static_config_reload) from [<c0c7015c>] (sja1105_hwtstamp_set+0x108/0x1cc)
[   41.657562] [<c0c7015c>] (sja1105_hwtstamp_set) from [<c0feb650>] (dev_ifsioc+0x18c/0x330)
[   41.665788] [<c0feb650>] (dev_ifsioc) from [<c0febbd8>] (dev_ioctl+0x320/0x6e8)
[   41.673064] [<c0febbd8>] (dev_ioctl) from [<c0f8b1f4>] (sock_ioctl+0x334/0x5e8)
[   41.680340] [<c0f8b1f4>] (sock_ioctl) from [<c05404a8>] (do_vfs_ioctl+0xb0/0xa10)
[   41.687789] [<c05404a8>] (do_vfs_ioctl) from [<c0540e3c>] (ksys_ioctl+0x34/0x58)
[   41.695151] [<c0540e3c>] (ksys_ioctl) from [<c0301000>] (ret_fast_syscall+0x0/0x28)
[   41.702768] Exception stack(0xe8495fa8 to 0xe8495ff0)
[   41.707796] 5fa0:                   beff4a8c 00000001 00000011 000089b0 beff4a8c beff4a80
[   41.715933] 5fc0: beff4a8c 00000001 0000000c 00000036 b6fa98c8 004e19c1 00000001 00000000
[   41.724069] 5fe0: 004dcedc beff4a6c 004c0738 b6e7af4c
[   41.729860] BUG: scheduling while atomic: ptp4l/208/0x00000002
[   41.735682] INFO: lockdep is turned off.

Enabling RX timestamping will logically disturb the fastpath (processing
of meta frames). Replace bool hwts_rx_en with a bit that is checked
atomically from the fastpath and temporarily unset from the sleepable
context during a change of the RX timestamping process (a destructive
operation anyways, requires switch reset).
If found unset, the fastpath (net/dsa/tag_sja1105.c) will just drop any
received meta frame and not take the meta_lock at all.

Fixes: a602afd200f5 ("net: dsa: sja1105: Expose PTP timestamping ioctls to userspace")
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/sja1105/sja1105_main.c | 19 +++++++++++--------
 include/linux/dsa/sja1105.h            |  4 +++-
 net/dsa/tag_sja1105.c                  | 12 +++++++++++-
 3 files changed, 25 insertions(+), 10 deletions(-)

diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index 96ab77bcd960..3c26f7c45d88 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -1875,7 +1875,9 @@ static int sja1105_set_ageing_time(struct dsa_switch *ds,
 	return sja1105_static_config_reload(priv);
 }
 
-/* Caller must hold priv->tagger_data.meta_lock */
+/* Must be called only with priv->tagger_data.state bit
+ * SJA1105_HWTS_RX_EN cleared
+ */
 static int sja1105_change_rxtstamping(struct sja1105_private *priv,
 				      bool on)
 {
@@ -1932,16 +1934,17 @@ static int sja1105_hwtstamp_set(struct dsa_switch *ds, int port,
 		break;
 	}
 
-	if (rx_on != priv->tagger_data.hwts_rx_en) {
-		spin_lock(&priv->tagger_data.meta_lock);
+	if (rx_on != test_bit(SJA1105_HWTS_RX_EN, &priv->tagger_data.state)) {
+		clear_bit(SJA1105_HWTS_RX_EN, &priv->tagger_data.state);
+
 		rc = sja1105_change_rxtstamping(priv, rx_on);
-		spin_unlock(&priv->tagger_data.meta_lock);
 		if (rc < 0) {
 			dev_err(ds->dev,
 				"Failed to change RX timestamping: %d\n", rc);
-			return -EFAULT;
+			return rc;
 		}
-		priv->tagger_data.hwts_rx_en = rx_on;
+		if (rx_on)
+			set_bit(SJA1105_HWTS_RX_EN, &priv->tagger_data.state);
 	}
 
 	if (copy_to_user(ifr->ifr_data, &config, sizeof(config)))
@@ -1960,7 +1963,7 @@ static int sja1105_hwtstamp_get(struct dsa_switch *ds, int port,
 		config.tx_type = HWTSTAMP_TX_ON;
 	else
 		config.tx_type = HWTSTAMP_TX_OFF;
-	if (priv->tagger_data.hwts_rx_en)
+	if (test_bit(SJA1105_HWTS_RX_EN, &priv->tagger_data.state))
 		config.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT;
 	else
 		config.rx_filter = HWTSTAMP_FILTER_NONE;
@@ -2009,7 +2012,7 @@ static bool sja1105_port_rxtstamp(struct dsa_switch *ds, int port,
 	struct sja1105_private *priv = ds->priv;
 	struct sja1105_tagger_data *data = &priv->tagger_data;
 
-	if (!data->hwts_rx_en)
+	if (!test_bit(SJA1105_HWTS_RX_EN, &data->state))
 		return false;
 
 	/* We need to read the full PTP clock to reconstruct the Rx
diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h
index 79435cfc20eb..897e799dbcb9 100644
--- a/include/linux/dsa/sja1105.h
+++ b/include/linux/dsa/sja1105.h
@@ -31,6 +31,8 @@
 #define SJA1105_META_SMAC			0x222222222222ull
 #define SJA1105_META_DMAC			0x0180C200000Eull
 
+#define SJA1105_HWTS_RX_EN			0
+
 /* Global tagger data: each struct sja1105_port has a reference to
  * the structure defined in struct sja1105_private.
  */
@@ -42,7 +44,7 @@ struct sja1105_tagger_data {
 	 * from taggers running on multiple ports on SMP systems
 	 */
 	spinlock_t meta_lock;
-	bool hwts_rx_en;
+	unsigned long state;
 };
 
 struct sja1105_skb_cb {
diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c
index 47ee88163a9d..27fe80d07460 100644
--- a/net/dsa/tag_sja1105.c
+++ b/net/dsa/tag_sja1105.c
@@ -155,7 +155,11 @@ static struct sk_buff
 	/* Step 1: A timestampable frame was received.
 	 * Buffer it until we get its meta frame.
 	 */
-	if (is_link_local && sp->data->hwts_rx_en) {
+	if (is_link_local) {
+		if (!test_bit(SJA1105_HWTS_RX_EN, &sp->data->state))
+			/* Do normal processing. */
+			return skb;
+
 		spin_lock(&sp->data->meta_lock);
 		/* Was this a link-local frame instead of the meta
 		 * that we were expecting?
@@ -186,6 +190,12 @@ static struct sk_buff
 	} else if (is_meta) {
 		struct sk_buff *stampable_skb;
 
+		/* Drop the meta frame if we're not in the right state
+		 * to process it.
+		 */
+		if (!test_bit(SJA1105_HWTS_RX_EN, &sp->data->state))
+			return NULL;
+
 		spin_lock(&sp->data->meta_lock);
 
 		stampable_skb = sp->data->stampable_skb;
-- 
2.20.1


From 56ffd5b166030f266bdeb54547d10f932b9e3943 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Tue, 1 Oct 2019 22:07:01 +0300
Subject: [PATCH 25/30] ptp_qoriq: Initialize the registers' spinlock before
 calling ptp_qoriq_settime

[ Upstream commit db34a4714c013b644eec2de0ec81b1f0373b8b93 ]

Because ptp_qoriq_settime is being called prior to spin_lock_init, the
following stack trace can be seen at driver probe time:

[    2.269117] the code is fine but needs lockdep annotation.
[    2.274569] turning off the locking correctness validator.
[    2.280027] CPU: 1 PID: 1 Comm: swapper/0 Not tainted 5.3.0-rc7-01478-g01eaa67a4797 #263
[    2.288073] Hardware name: Freescale LS1021A
[    2.292337] [<c0313cb4>] (unwind_backtrace) from [<c030e11c>] (show_stack+0x10/0x14)
[    2.300045] [<c030e11c>] (show_stack) from [<c1219440>] (dump_stack+0xcc/0xf8)
[    2.307235] [<c1219440>] (dump_stack) from [<c03b9b44>] (register_lock_class+0x730/0x73c)
[    2.315372] [<c03b9b44>] (register_lock_class) from [<c03b6190>] (__lock_acquire+0x78/0x270c)
[    2.323856] [<c03b6190>] (__lock_acquire) from [<c03b90cc>] (lock_acquire+0xe0/0x22c)
[    2.331649] [<c03b90cc>] (lock_acquire) from [<c123c310>] (_raw_spin_lock_irqsave+0x54/0x68)
[    2.340048] [<c123c310>] (_raw_spin_lock_irqsave) from [<c0e73fe4>] (ptp_qoriq_settime+0x38/0x80)
[    2.348878] [<c0e73fe4>] (ptp_qoriq_settime) from [<c0e746d4>] (ptp_qoriq_init+0x1f8/0x484)
[    2.357189] [<c0e746d4>] (ptp_qoriq_init) from [<c0e74aac>] (ptp_qoriq_probe+0xd0/0x184)
[    2.365243] [<c0e74aac>] (ptp_qoriq_probe) from [<c0b0a07c>] (platform_drv_probe+0x48/0x9c)
[    2.373555] [<c0b0a07c>] (platform_drv_probe) from [<c0b07a14>] (really_probe+0x1c4/0x400)
[    2.381779] [<c0b07a14>] (really_probe) from [<c0b07e28>] (driver_probe_device+0x78/0x1b8)
[    2.390003] [<c0b07e28>] (driver_probe_device) from [<c0b081d0>] (device_driver_attach+0x58/0x60)
[    2.398832] [<c0b081d0>] (device_driver_attach) from [<c0b082d4>] (__driver_attach+0xfc/0x160)
[    2.407402] [<c0b082d4>] (__driver_attach) from [<c0b05a84>] (bus_for_each_dev+0x68/0xb4)
[    2.415539] [<c0b05a84>] (bus_for_each_dev) from [<c0b06b68>] (bus_add_driver+0x104/0x20c)
[    2.423763] [<c0b06b68>] (bus_add_driver) from [<c0b0909c>] (driver_register+0x78/0x10c)
[    2.431815] [<c0b0909c>] (driver_register) from [<c030313c>] (do_one_initcall+0x8c/0x3ac)
[    2.439954] [<c030313c>] (do_one_initcall) from [<c1f013f4>] (kernel_init_freeable+0x468/0x548)
[    2.448610] [<c1f013f4>] (kernel_init_freeable) from [<c12344d8>] (kernel_init+0x8/0x10c)
[    2.456745] [<c12344d8>] (kernel_init) from [<c03010b4>] (ret_from_fork+0x14/0x20)
[    2.464273] Exception stack(0xea89ffb0 to 0xea89fff8)
[    2.469297] ffa0:                                     00000000 00000000 00000000 00000000
[    2.477432] ffc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
[    2.485566] ffe0: 00000000 00000000 00000000 00000000 00000013 00000000

Fixes: ff54571a747b ("ptp_qoriq: convert to use ptp_qoriq_init/free")
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/ptp/ptp_qoriq.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/ptp/ptp_qoriq.c b/drivers/ptp/ptp_qoriq.c
index c61f00b72e15..a577218d1ab7 100644
--- a/drivers/ptp/ptp_qoriq.c
+++ b/drivers/ptp/ptp_qoriq.c
@@ -507,6 +507,8 @@ int ptp_qoriq_init(struct ptp_qoriq *ptp_qoriq, void __iomem *base,
 		ptp_qoriq->regs.etts_regs = base + ETTS_REGS_OFFSET;
 	}
 
+	spin_lock_init(&ptp_qoriq->lock);
+
 	ktime_get_real_ts64(&now);
 	ptp_qoriq_settime(&ptp_qoriq->caps, &now);
 
@@ -514,7 +516,6 @@ int ptp_qoriq_init(struct ptp_qoriq *ptp_qoriq, void __iomem *base,
 	  (ptp_qoriq->tclk_period & TCLK_PERIOD_MASK) << TCLK_PERIOD_SHIFT |
 	  (ptp_qoriq->cksel & CKSEL_MASK) << CKSEL_SHIFT;
 
-	spin_lock_init(&ptp_qoriq->lock);
 	spin_lock_irqsave(&ptp_qoriq->lock, flags);
 
 	regs = &ptp_qoriq->regs;
-- 
2.20.1


From 0a4f4f9257fa3eb37fe15f670b986c3da9e2147b Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Sun, 29 Sep 2019 01:08:17 +0300
Subject: [PATCH 26/30] net: dsa: sja1105: Ensure PTP time for rxtstamp
 reconstruction is not in the past

[ Upstream commit b6f2494d311a19b33b19708543e7ef6dea1de459 ]

Sometimes the PTP synchronization on the switch 'jumps':

  ptp4l[11241.155]: rms    8 max   16 freq -21732 +/-  11 delay   742 +/-   0
  ptp4l[11243.157]: rms    7 max   17 freq -21731 +/-  10 delay   744 +/-   0
  ptp4l[11245.160]: rms 33592410 max 134217731 freq +192422 +/- 8530253 delay   743 +/-   0
  ptp4l[11247.163]: rms 811631 max 964131 freq +10326 +/- 557785 delay   743 +/-   0
  ptp4l[11249.166]: rms 261936 max 533876 freq -304323 +/- 126371 delay   744 +/-   0
  ptp4l[11251.169]: rms 48700 max 57740 freq -20218 +/- 30532 delay   744 +/-   0
  ptp4l[11253.171]: rms 14570 max 30163 freq  -5568 +/- 7563 delay   742 +/-   0
  ptp4l[11255.174]: rms 2914 max 3440 freq -22001 +/- 1667 delay   744 +/-   1
  ptp4l[11257.177]: rms  811 max 1710 freq -22653 +/- 451 delay   744 +/-   1
  ptp4l[11259.180]: rms  177 max  218 freq -21695 +/-  89 delay   741 +/-   0
  ptp4l[11261.182]: rms   45 max   92 freq -21677 +/-  32 delay   742 +/-   0
  ptp4l[11263.186]: rms   14 max   32 freq -21733 +/-  11 delay   742 +/-   0
  ptp4l[11265.188]: rms    9 max   14 freq -21725 +/-  12 delay   742 +/-   0
  ptp4l[11267.191]: rms    9 max   16 freq -21727 +/-  13 delay   742 +/-   0
  ptp4l[11269.194]: rms    6 max   15 freq -21726 +/-   9 delay   743 +/-   0
  ptp4l[11271.197]: rms    8 max   15 freq -21728 +/-  11 delay   743 +/-   0
  ptp4l[11273.200]: rms    6 max   12 freq -21727 +/-   8 delay   743 +/-   0
  ptp4l[11275.202]: rms    9 max   17 freq -21720 +/-  11 delay   742 +/-   0
  ptp4l[11277.205]: rms    9 max   18 freq -21725 +/-  12 delay   742 +/-   0

Background: the switch only offers partial RX timestamps (24 bits) and
it is up to the driver to read the PTP clock to fill those timestamps up
to 64 bits. But the PTP clock readout needs to happen quickly enough (in
0.135 seconds, in fact), otherwise the PTP clock will wrap around 24
bits, condition which cannot be detected.

Looking at the 'max 134217731' value on output line 3, one can see that
in hex it is 0x8000003. Because the PTP clock resolution is 8 ns,
that means 0x1000000 in ticks, which is exactly 2^24. So indeed this is
a PTP clock wraparound, but the reason might be surprising.

What is going on is that sja1105_tstamp_reconstruct(priv, now, ts)
expects a "now" time that is later than the "ts" was snapshotted at.
This, of course, is obvious: we read the PTP time _after_ the partial RX
timestamp was received. However, the workqueue is processing frames from
a skb queue and reuses the same PTP time, read once at the beginning.
Normally the skb queue only contains one frame and all goes well. But
when the skb queue contains two frames, the second frame that gets
dequeued might have been partially timestamped by the RX MAC _after_ we
had read our PTP time initially.

The code was originally like that due to concerns that SPI access for
PTP time readout is a slow process, and we are time-constrained anyway
(aka: premature optimization). But some timing analysis reveals that the
time spent until the RX timestamp is completely reconstructed is 1 order
of magnitude lower than the 0.135 s deadline even under worst-case
conditions. So we can afford to read the PTP time for each frame in the
RX timestamping queue, which of course ensures that the full PTP time is
in the partial timestamp's future.

Fixes: f3097be21bf1 ("net: dsa: sja1105: Add a state machine for RX timestamping")
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/sja1105/sja1105_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index 3c26f7c45d88..296286f4fb39 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -1986,12 +1986,12 @@ static void sja1105_rxtstamp_work(struct work_struct *work)
 
 	mutex_lock(&priv->ptp_lock);
 
-	now = priv->tstamp_cc.read(&priv->tstamp_cc);
-
 	while ((skb = skb_dequeue(&data->skb_rxtstamp_queue)) != NULL) {
 		struct skb_shared_hwtstamps *shwt = skb_hwtstamps(skb);
 		u64 ts;
 
+		now = priv->tstamp_cc.read(&priv->tstamp_cc);
+
 		*shwt = (struct skb_shared_hwtstamps) {0};
 
 		ts = SJA1105_SKB_CB(skb)->meta_tstamp;
-- 
2.20.1


From a18d97dc2847d4ba5381594467de0e00135e13a5 Mon Sep 17 00:00:00 2001
From: Navid Emamdoost <navid.emamdoost@gmail.com>
Date: Sun, 29 Sep 2019 01:43:39 +0300
Subject: [PATCH 27/30] net: dsa: sja1105: Prevent leaking memory

[ Upstream commit 68501df92d116b760777a2cfda314789f926476f ]

In sja1105_static_config_upload, in two cases memory is leaked: when
static_config_buf_prepare_for_upload fails and when sja1105_inhibit_tx
fails. In both cases config_buf should be released.

Fixes: 8aa9ebccae87 ("net: dsa: Introduce driver for NXP SJA1105 5-port L2 switch")
Fixes: 1a4c69406cc1 ("net: dsa: sja1105: Prevent PHY jabbering during switch reset")
Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com>
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/sja1105/sja1105_spi.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/sja1105/sja1105_spi.c b/drivers/net/dsa/sja1105/sja1105_spi.c
index 84dc603138cf..58dd37ecde17 100644
--- a/drivers/net/dsa/sja1105/sja1105_spi.c
+++ b/drivers/net/dsa/sja1105/sja1105_spi.c
@@ -409,7 +409,8 @@ int sja1105_static_config_upload(struct sja1105_private *priv)
 	rc = static_config_buf_prepare_for_upload(priv, config_buf, buf_len);
 	if (rc < 0) {
 		dev_err(dev, "Invalid config, cannot upload\n");
-		return -EINVAL;
+		rc = -EINVAL;
+		goto out;
 	}
 	/* Prevent PHY jabbering during switch reset by inhibiting
 	 * Tx on all ports and waiting for current packet to drain.
@@ -418,7 +419,8 @@ int sja1105_static_config_upload(struct sja1105_private *priv)
 	rc = sja1105_inhibit_tx(priv, port_bitmap, true);
 	if (rc < 0) {
 		dev_err(dev, "Failed to inhibit Tx on ports\n");
-		return -ENXIO;
+		rc = -ENXIO;
+		goto out;
 	}
 	/* Wait for an eventual egress packet to finish transmission
 	 * (reach IFG). It is guaranteed that a second one will not
-- 
2.20.1


From 940782aee97a6a42ceeadae02e3ecc845bb2238c Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 1 Oct 2019 10:33:51 +0200
Subject: [PATCH 28/30] net: socionext: netsec: always grab descriptor lock
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 55131dec2b1c7417d216f861ea7a29dc7c4d2d20 ]

Always acquire tx descriptor spinlock even if a xdp program is not loaded
on the netsec device since ndo_xdp_xmit can run concurrently with
netsec_netdev_start_xmit and netsec_clean_tx_dring. This can happen
loading a xdp program on a different device (e.g virtio-net) and
xdp_do_redirect_map/xdp_do_redirect_slow can redirect to netsec even if
we do not have a xdp program on it.

Fixes: ba2b232108d3 ("net: netsec: add XDP support")
Tested-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/socionext/netsec.c | 30 ++++++-------------------
 1 file changed, 7 insertions(+), 23 deletions(-)

diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index 1502fe8b0456..b9ac45d9dee8 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -282,7 +282,6 @@ struct netsec_desc_ring {
 	void *vaddr;
 	u16 head, tail;
 	u16 xdp_xmit; /* netsec_xdp_xmit packets */
-	bool is_xdp;
 	struct page_pool *page_pool;
 	struct xdp_rxq_info xdp_rxq;
 	spinlock_t lock; /* XDP tx queue locking */
@@ -634,8 +633,7 @@ static bool netsec_clean_tx_dring(struct netsec_priv *priv)
 	unsigned int bytes;
 	int cnt = 0;
 
-	if (dring->is_xdp)
-		spin_lock(&dring->lock);
+	spin_lock(&dring->lock);
 
 	bytes = 0;
 	entry = dring->vaddr + DESC_SZ * tail;
@@ -682,8 +680,8 @@ static bool netsec_clean_tx_dring(struct netsec_priv *priv)
 		entry = dring->vaddr + DESC_SZ * tail;
 		cnt++;
 	}
-	if (dring->is_xdp)
-		spin_unlock(&dring->lock);
+
+	spin_unlock(&dring->lock);
 
 	if (!cnt)
 		return false;
@@ -799,9 +797,6 @@ static void netsec_set_tx_de(struct netsec_priv *priv,
 	de->data_buf_addr_lw = lower_32_bits(desc->dma_addr);
 	de->buf_len_info = (tx_ctrl->tcp_seg_len << 16) | desc->len;
 	de->attr = attr;
-	/* under spin_lock if using XDP */
-	if (!dring->is_xdp)
-		dma_wmb();
 
 	dring->desc[idx] = *desc;
 	if (desc->buf_type == TYPE_NETSEC_SKB)
@@ -1123,12 +1118,10 @@ static netdev_tx_t netsec_netdev_start_xmit(struct sk_buff *skb,
 	u16 tso_seg_len = 0;
 	int filled;
 
-	if (dring->is_xdp)
-		spin_lock_bh(&dring->lock);
+	spin_lock_bh(&dring->lock);
 	filled = netsec_desc_used(dring);
 	if (netsec_check_stop_tx(priv, filled)) {
-		if (dring->is_xdp)
-			spin_unlock_bh(&dring->lock);
+		spin_unlock_bh(&dring->lock);
 		net_warn_ratelimited("%s %s Tx queue full\n",
 				     dev_name(priv->dev), ndev->name);
 		return NETDEV_TX_BUSY;
@@ -1161,8 +1154,7 @@ static netdev_tx_t netsec_netdev_start_xmit(struct sk_buff *skb,
 	tx_desc.dma_addr = dma_map_single(priv->dev, skb->data,
 					  skb_headlen(skb), DMA_TO_DEVICE);
 	if (dma_mapping_error(priv->dev, tx_desc.dma_addr)) {
-		if (dring->is_xdp)
-			spin_unlock_bh(&dring->lock);
+		spin_unlock_bh(&dring->lock);
 		netif_err(priv, drv, priv->ndev,
 			  "%s: DMA mapping failed\n", __func__);
 		ndev->stats.tx_dropped++;
@@ -1177,8 +1169,7 @@ static netdev_tx_t netsec_netdev_start_xmit(struct sk_buff *skb,
 	netdev_sent_queue(priv->ndev, skb->len);
 
 	netsec_set_tx_de(priv, dring, &tx_ctrl, &tx_desc, skb);
-	if (dring->is_xdp)
-		spin_unlock_bh(&dring->lock);
+	spin_unlock_bh(&dring->lock);
 	netsec_write(priv, NETSEC_REG_NRM_TX_PKTCNT, 1); /* submit another tx */
 
 	return NETDEV_TX_OK;
@@ -1262,7 +1253,6 @@ static int netsec_alloc_dring(struct netsec_priv *priv, enum ring_id id)
 static void netsec_setup_tx_dring(struct netsec_priv *priv)
 {
 	struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_TX];
-	struct bpf_prog *xdp_prog = READ_ONCE(priv->xdp_prog);
 	int i;
 
 	for (i = 0; i < DESC_NUM; i++) {
@@ -1275,12 +1265,6 @@ static void netsec_setup_tx_dring(struct netsec_priv *priv)
 		 */
 		de->attr = 1U << NETSEC_TX_SHIFT_OWN_FIELD;
 	}
-
-	if (xdp_prog)
-		dring->is_xdp = true;
-	else
-		dring->is_xdp = false;
-
 }
 
 static int netsec_setup_rx_dring(struct netsec_priv *priv)
-- 
2.20.1


From 073f281ee7663cf88c967f900376a754bb5419e1 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Sun, 29 Sep 2019 02:39:48 +0300
Subject: [PATCH 29/30] net: sched: cbs: Avoid division by zero when
 calculating the port rate

[ Upstream commit 83c8c3cf45163f0c823db37be6ab04dfcf8ac751 ]

As explained in the "net: sched: taprio: Avoid division by zero on
invalid link speed" commit, it is legal for the ethtool API to return
zero as a link speed. So guard against it to ensure we don't perform a
division by zero in kernel.

Fixes: e0a7683d30e9 ("net/sched: cbs: fix port_rate miscalculation")
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Acked-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_cbs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c
index 4a403d35438f..284ab2dcf47f 100644
--- a/net/sched/sch_cbs.c
+++ b/net/sched/sch_cbs.c
@@ -306,7 +306,7 @@ static void cbs_set_port_rate(struct net_device *dev, struct cbs_sched_data *q)
 	if (err < 0)
 		goto skip;
 
-	if (ecmd.base.speed != SPEED_UNKNOWN)
+	if (ecmd.base.speed && ecmd.base.speed != SPEED_UNKNOWN)
 		speed = ecmd.base.speed;
 
 skip:
-- 
2.20.1


From 2edadf5650e8e173028e435a8a3e1d514798a9c2 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Sun, 29 Sep 2019 02:37:22 +0300
Subject: [PATCH 30/30] net: sched: taprio: Avoid division by zero on invalid
 link speed

[ Upstream commit 9a9251a3534745d08a92abfeca0ca467b912b5f6 ]

The check in taprio_set_picos_per_byte is currently not robust enough
and will trigger this division by zero, due to e.g. PHYLINK not setting
kset->base.speed when there is no PHY connected:

[   27.109992] Division by zero in kernel.
[   27.113842] CPU: 1 PID: 198 Comm: tc Not tainted 5.3.0-rc5-01246-gc4006b8c2637-dirty #212
[   27.121974] Hardware name: Freescale LS1021A
[   27.126234] [<c03132e0>] (unwind_backtrace) from [<c030d8b8>] (show_stack+0x10/0x14)
[   27.133938] [<c030d8b8>] (show_stack) from [<c10b21b0>] (dump_stack+0xb0/0xc4)
[   27.141124] [<c10b21b0>] (dump_stack) from [<c10af97c>] (Ldiv0_64+0x8/0x18)
[   27.148052] [<c10af97c>] (Ldiv0_64) from [<c0700260>] (div64_u64+0xcc/0xf0)
[   27.154978] [<c0700260>] (div64_u64) from [<c07002d0>] (div64_s64+0x4c/0x68)
[   27.161993] [<c07002d0>] (div64_s64) from [<c0f3d890>] (taprio_set_picos_per_byte+0xe8/0xf4)
[   27.170388] [<c0f3d890>] (taprio_set_picos_per_byte) from [<c0f3f614>] (taprio_change+0x668/0xcec)
[   27.179302] [<c0f3f614>] (taprio_change) from [<c0f2bc24>] (qdisc_create+0x1fc/0x4f4)
[   27.187091] [<c0f2bc24>] (qdisc_create) from [<c0f2c0c8>] (tc_modify_qdisc+0x1ac/0x6f8)
[   27.195055] [<c0f2c0c8>] (tc_modify_qdisc) from [<c0ee9604>] (rtnetlink_rcv_msg+0x268/0x2dc)
[   27.203449] [<c0ee9604>] (rtnetlink_rcv_msg) from [<c0f4fef0>] (netlink_rcv_skb+0xe0/0x114)
[   27.211756] [<c0f4fef0>] (netlink_rcv_skb) from [<c0f4f6cc>] (netlink_unicast+0x1b4/0x22c)
[   27.219977] [<c0f4f6cc>] (netlink_unicast) from [<c0f4fa84>] (netlink_sendmsg+0x284/0x340)
[   27.228198] [<c0f4fa84>] (netlink_sendmsg) from [<c0eae5fc>] (sock_sendmsg+0x14/0x24)
[   27.235988] [<c0eae5fc>] (sock_sendmsg) from [<c0eaedf8>] (___sys_sendmsg+0x214/0x228)
[   27.243863] [<c0eaedf8>] (___sys_sendmsg) from [<c0eb015c>] (__sys_sendmsg+0x50/0x8c)
[   27.251652] [<c0eb015c>] (__sys_sendmsg) from [<c0301000>] (ret_fast_syscall+0x0/0x54)
[   27.259524] Exception stack(0xe8045fa8 to 0xe8045ff0)
[   27.264546] 5fa0:                   b6f608c8 000000f8 00000003 bed7e2f0 00000000 00000000
[   27.272681] 5fc0: b6f608c8 000000f8 004ce54c 00000128 5d3ce8c7 00000000 00000026 00505c9c
[   27.280812] 5fe0: 00000070 bed7e298 004ddd64 b6dd1e64

Russell King points out that the ethtool API says zero is a valid return
value of __ethtool_get_link_ksettings:

   * If it is enabled then they are read-only; if the link
   * is up they represent the negotiated link mode; if the link is down,
   * the speed is 0, %SPEED_UNKNOWN or the highest enabled speed and
   * @duplex is %DUPLEX_UNKNOWN or the best enabled duplex mode.

  So, it seems that taprio is not following the API... I'd suggest either
  fixing taprio, or getting agreement to change the ethtool API.

The chosen path was to fix taprio.

Fixes: 7b9eba7ba0c1 ("net/sched: taprio: fix picos_per_byte miscalculation")
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Acked-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_taprio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 944b1af32156..76bebe516194 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -961,7 +961,7 @@ static void taprio_set_picos_per_byte(struct net_device *dev,
 	if (err < 0)
 		goto skip;
 
-	if (ecmd.base.speed != SPEED_UNKNOWN)
+	if (ecmd.base.speed && ecmd.base.speed != SPEED_UNKNOWN)
 		speed = ecmd.base.speed;
 
 skip:
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Sat, Oct 05, 2019 at 02:57:22PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v5.2 and
> v5.3 -stable, respectively.

Thanks for these, all now queued up.

Note, 5.2 is now going to be end-of-life after this next release, so no
need to make patches for it anymore.

thanks,

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 108 bytes --]


Please queue up the following networking bug fixes for 4.19.x and
5.3.x -stable, respectively.

Thank you!

[-- Attachment #2: net_419.mbox --]
[-- Type: Application/Octet-Stream, Size: 29719 bytes --]

From 1da8d6dafe71636ca77406823babb80b42babdcc Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Wed, 16 Oct 2019 12:03:15 -0700
Subject: [PATCH 01/10] ipv4: fix race condition between route lookup and
 invalidation

[ Upstream commit 5018c59607a511cdee743b629c76206d9c9e6d7b ]

Jesse and Ido reported the following race condition:
<CPU A, t0> - Received packet A is forwarded and cached dst entry is
taken from the nexthop ('nhc->nhc_rth_input'). Calls skb_dst_set()

<t1> - Given Jesse has busy routers ("ingesting full BGP routing tables
from multiple ISPs"), route is added / deleted and rt_cache_flush() is
called

<CPU B, t2> - Received packet B tries to use the same cached dst entry
from t0, but rt_cache_valid() is no longer true and it is replaced in
rt_cache_route() by the newer one. This calls dst_dev_put() on the
original dst entry which assigns the blackhole netdev to 'dst->dev'

<CPU A, t3> - dst_input(skb) is called on packet A and it is dropped due
to 'dst->dev' being the blackhole netdev

There are 2 issues in the v4 routing code:
1. A per-netns counter is used to do the validation of the route. That
means whenever a route is changed in the netns, users of all routes in
the netns needs to redo lookup. v6 has an implementation of only
updating fn_sernum for routes that are affected.
2. When rt_cache_valid() returns false, rt_cache_route() is called to
throw away the current cache, and create a new one. This seems
unnecessary because as long as this route does not change, the route
cache does not need to be recreated.

To fully solve the above 2 issues, it probably needs quite some code
changes and requires careful testing, and does not suite for net branch.

So this patch only tries to add the deleted cached rt into the uncached
list, so user could still be able to use it to receive packets until
it's done.

Fixes: 95c47f9cf5e0 ("ipv4: call dst_dev_put() properly")
Signed-off-by: Wei Wang <weiwan@google.com>
Reported-by: Ido Schimmel <idosch@idosch.org>
Reported-by: Jesse Hathaway <jesse@mbuki-mvuki.org>
Tested-by: Jesse Hathaway <jesse@mbuki-mvuki.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Cc: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 7065d68086ab..5e816228abcd 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1476,7 +1476,7 @@ static bool rt_cache_route(struct fib_nh *nh, struct rtable *rt)
 	prev = cmpxchg(p, orig, rt);
 	if (prev == orig) {
 		if (orig) {
-			dst_dev_put(&orig->dst);
+			rt_add_uncached_list(orig);
 			dst_release(&orig->dst);
 		}
 	} else {
-- 
2.20.1


From a3bf8287ed2636acd8f8c738824bd130dcb5eaab Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Wed, 16 Oct 2019 20:52:09 +0200
Subject: [PATCH 02/10] ipv4: Return -ENETUNREACH if we can't create route but
 saddr is valid

[ Upstream commit 595e0651d0296bad2491a4a29a7a43eae6328b02 ]

...instead of -EINVAL. An issue was found with older kernel versions
while unplugging a NFS client with pending RPCs, and the wrong error
code here prevented it from recovering once link is back up with a
configured address.

Incidentally, this is not an issue anymore since commit 4f8943f80883
("SUNRPC: Replace direct task wakeups from softirq context"), included
in 5.2-rc7, had the effect of decoupling the forwarding of this error
by using SO_ERROR in xs_wake_error(), as pointed out by Benjamin
Coddington.

To the best of my knowledge, this isn't currently causing any further
issue, but the error code doesn't look appropriate anyway, and we
might hit this in other paths as well.

In detail, as analysed by Gonzalo Siero, once the route is deleted
because the interface is down, and can't be resolved and we return
-EINVAL here, this ends up, courtesy of inet_sk_rebuild_header(),
as the socket error seen by tcp_write_err(), called by
tcp_retransmit_timer().

In turn, tcp_write_err() indirectly calls xs_error_report(), which
wakes up the RPC pending tasks with a status of -EINVAL. This is then
seen by call_status() in the SUN RPC implementation, which aborts the
RPC call calling rpc_exit(), instead of handling this as a
potentially temporary condition, i.e. as a timeout.

Return -EINVAL only if the input parameters passed to
ip_route_output_key_hash_rcu() are actually invalid (this is the case
if the specified source address is multicast, limited broadcast or
all zeroes), but return -ENETUNREACH in all cases where, at the given
moment, the given source address doesn't allow resolving the route.

While at it, drop the initialisation of err to -ENETUNREACH, which
was added to __ip_route_output_key() back then by commit
0315e3827048 ("net: Fix behaviour of unreachable, blackhole and
prohibit routes"), but actually had no effect, as it was, and is,
overwritten by the fib_lookup() return code assignment, and anyway
ignored in all other branches, including the if (fl4->saddr) one:
I find this rather confusing, as it would look like -ENETUNREACH is
the "default" error, while that statement has no effect.

Also note that after commit fc75fc8339e7 ("ipv4: dont create routes
on down devices"), we would get -ENETUNREACH if the device is down,
but -EINVAL if the source address is specified and we can't resolve
the route, and this appears to be rather inconsistent.

Reported-by: Stefan Walter <walteste@inf.ethz.ch>
Analysed-by: Benjamin Coddington <bcodding@redhat.com>
Analysed-by: Gonzalo Siero <gsierohu@redhat.com>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 5e816228abcd..69127f6039b2 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2381,14 +2381,17 @@ struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4,
 	int orig_oif = fl4->flowi4_oif;
 	unsigned int flags = 0;
 	struct rtable *rth;
-	int err = -ENETUNREACH;
+	int err;
 
 	if (fl4->saddr) {
-		rth = ERR_PTR(-EINVAL);
 		if (ipv4_is_multicast(fl4->saddr) ||
 		    ipv4_is_lbcast(fl4->saddr) ||
-		    ipv4_is_zeronet(fl4->saddr))
+		    ipv4_is_zeronet(fl4->saddr)) {
+			rth = ERR_PTR(-EINVAL);
 			goto out;
+		}
+
+		rth = ERR_PTR(-ENETUNREACH);
 
 		/* I removed check for oif == dev_out->oif here.
 		   It was wrong for two reasons:
-- 
2.20.1


From 4ac370aaf42074d3a45efa866fd301433ea6be6f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 14 Oct 2019 11:22:30 -0700
Subject: [PATCH 03/10] net: avoid potential infinite loop in tc_ctl_action()

[ Upstream commit 39f13ea2f61b439ebe0060393e9c39925c9ee28c ]

tc_ctl_action() has the ability to loop forever if tcf_action_add()
returns -EAGAIN.

This special case has been done in case a module needed to be loaded,
but it turns out that tcf_add_notify() could also return -EAGAIN
if the socket sk_rcvbuf limit is hit.

We need to separate the two cases, and only loop for the module
loading case.

While we are at it, add a limit of 10 attempts since unbounded
loops are always scary.

syzbot repro was something like :

socket(PF_NETLINK, SOCK_RAW|SOCK_NONBLOCK, NETLINK_ROUTE) = 3
write(3, ..., 38) = 38
setsockopt(3, SOL_SOCKET, SO_RCVBUF, [0], 4) = 0
sendmsg(3, {msg_name(0)=NULL, msg_iov(1)=[{..., 388}], msg_controllen=0, msg_flags=0x10}, ...)

NMI backtrace for cpu 0
CPU: 0 PID: 1054 Comm: khungtaskd Not tainted 5.4.0-rc1+ #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 nmi_cpu_backtrace.cold+0x70/0xb2 lib/nmi_backtrace.c:101
 nmi_trigger_cpumask_backtrace+0x23b/0x28b lib/nmi_backtrace.c:62
 arch_trigger_cpumask_backtrace+0x14/0x20 arch/x86/kernel/apic/hw_nmi.c:38
 trigger_all_cpu_backtrace include/linux/nmi.h:146 [inline]
 check_hung_uninterruptible_tasks kernel/hung_task.c:205 [inline]
 watchdog+0x9d0/0xef0 kernel/hung_task.c:289
 kthread+0x361/0x430 kernel/kthread.c:255
 ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:352
Sending NMI from CPU 0 to CPUs 1:
NMI backtrace for cpu 1
CPU: 1 PID: 8859 Comm: syz-executor910 Not tainted 5.4.0-rc1+ #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:arch_local_save_flags arch/x86/include/asm/paravirt.h:751 [inline]
RIP: 0010:lockdep_hardirqs_off+0x1df/0x2e0 kernel/locking/lockdep.c:3453
Code: 5c 08 00 00 5b 41 5c 41 5d 5d c3 48 c7 c0 58 1d f3 88 48 ba 00 00 00 00 00 fc ff df 48 c1 e8 03 80 3c 10 00 0f 85 d3 00 00 00 <48> 83 3d 21 9e 99 07 00 0f 84 b9 00 00 00 9c 58 0f 1f 44 00 00 f6
RSP: 0018:ffff8880a6f3f1b8 EFLAGS: 00000046
RAX: 1ffffffff11e63ab RBX: ffff88808c9c6080 RCX: 0000000000000000
RDX: dffffc0000000000 RSI: 0000000000000000 RDI: ffff88808c9c6914
RBP: ffff8880a6f3f1d0 R08: ffff88808c9c6080 R09: fffffbfff16be5d1
R10: fffffbfff16be5d0 R11: 0000000000000003 R12: ffffffff8746591f
R13: ffff88808c9c6080 R14: ffffffff8746591f R15: 0000000000000003
FS:  00000000011e4880(0000) GS:ffff8880ae900000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffffffffff600400 CR3: 00000000a8920000 CR4: 00000000001406e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 trace_hardirqs_off+0x62/0x240 kernel/trace/trace_preemptirq.c:45
 __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:108 [inline]
 _raw_spin_lock_irqsave+0x6f/0xcd kernel/locking/spinlock.c:159
 __wake_up_common_lock+0xc8/0x150 kernel/sched/wait.c:122
 __wake_up+0xe/0x10 kernel/sched/wait.c:142
 netlink_unlock_table net/netlink/af_netlink.c:466 [inline]
 netlink_unlock_table net/netlink/af_netlink.c:463 [inline]
 netlink_broadcast_filtered+0x705/0xb80 net/netlink/af_netlink.c:1514
 netlink_broadcast+0x3a/0x50 net/netlink/af_netlink.c:1534
 rtnetlink_send+0xdd/0x110 net/core/rtnetlink.c:714
 tcf_add_notify net/sched/act_api.c:1343 [inline]
 tcf_action_add+0x243/0x370 net/sched/act_api.c:1362
 tc_ctl_action+0x3b5/0x4bc net/sched/act_api.c:1410
 rtnetlink_rcv_msg+0x463/0xb00 net/core/rtnetlink.c:5386
 netlink_rcv_skb+0x177/0x450 net/netlink/af_netlink.c:2477
 rtnetlink_rcv+0x1d/0x30 net/core/rtnetlink.c:5404
 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
 netlink_unicast+0x531/0x710 net/netlink/af_netlink.c:1328
 netlink_sendmsg+0x8a5/0xd60 net/netlink/af_netlink.c:1917
 sock_sendmsg_nosec net/socket.c:637 [inline]
 sock_sendmsg+0xd7/0x130 net/socket.c:657
 ___sys_sendmsg+0x803/0x920 net/socket.c:2311
 __sys_sendmsg+0x105/0x1d0 net/socket.c:2356
 __do_sys_sendmsg net/socket.c:2365 [inline]
 __se_sys_sendmsg net/socket.c:2363 [inline]
 __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2363
 do_syscall_64+0xfa/0x760 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x440939

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot+cf0adbb9c28c8866c788@syzkaller.appspotmail.com
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_api.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 7c4a4b874248..f2c4bfc79663 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -1307,11 +1307,16 @@ static int tcf_action_add(struct net *net, struct nlattr *nla,
 			  struct netlink_ext_ack *extack)
 {
 	size_t attr_size = 0;
-	int ret = 0;
+	int loop, ret;
 	struct tc_action *actions[TCA_ACT_MAX_PRIO] = {};
 
-	ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, actions,
-			      &attr_size, true, extack);
+	for (loop = 0; loop < 10; loop++) {
+		ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0,
+				      actions, &attr_size, true, extack);
+		if (ret != -EAGAIN)
+			break;
+	}
+
 	if (ret < 0)
 		return ret;
 	ret = tcf_add_notify(net, n, actions, portid, attr_size, extack);
@@ -1361,11 +1366,8 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n,
 		 */
 		if (n->nlmsg_flags & NLM_F_REPLACE)
 			ovr = 1;
-replay:
 		ret = tcf_action_add(net, tca[TCA_ACT_TAB], n, portid, ovr,
 				     extack);
-		if (ret == -EAGAIN)
-			goto replay;
 		break;
 	case RTM_DELACTION:
 		ret = tca_action_gd(net, tca[TCA_ACT_TAB], n,
-- 
2.20.1


From a45804c9fb15b59735fc50f590f625b042b7f74c Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 15 Oct 2019 10:45:47 -0700
Subject: [PATCH 04/10] net: bcmgenet: Fix RGMII_MODE_EN value for GENET v1/2/3

[ Upstream commit efb86fede98cdc70b674692ff617b1162f642c49 ]

The RGMII_MODE_EN bit value was 0 for GENET versions 1 through 3, and
became 6 for GENET v4 and above, account for that difference.

Fixes: aa09677cba42 ("net: bcmgenet: add MDIO routines")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Acked-by: Doug Berger <opendmb@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.h | 1 +
 drivers/net/ethernet/broadcom/genet/bcmmii.c   | 6 +++++-
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 14b49612aa86..4dabf37319c8 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -369,6 +369,7 @@ struct bcmgenet_mib_counters {
 #define  EXT_PWR_DOWN_PHY_EN		(1 << 20)
 
 #define EXT_RGMII_OOB_CTRL		0x0C
+#define  RGMII_MODE_EN_V123		(1 << 0)
 #define  RGMII_LINK			(1 << 4)
 #define  OOB_DISABLE			(1 << 5)
 #define  RGMII_MODE_EN			(1 << 6)
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index de0e24d912fe..7b2fbbc33463 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -261,7 +261,11 @@ int bcmgenet_mii_config(struct net_device *dev, bool init)
 	 */
 	if (priv->ext_phy) {
 		reg = bcmgenet_ext_readl(priv, EXT_RGMII_OOB_CTRL);
-		reg |= RGMII_MODE_EN | id_mode_dis;
+		reg |= id_mode_dis;
+		if (GENET_IS_V1(priv) || GENET_IS_V2(priv) || GENET_IS_V3(priv))
+			reg |= RGMII_MODE_EN_V123;
+		else
+			reg |= RGMII_MODE_EN;
 		bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL);
 	}
 
-- 
2.20.1


From 42acbdb1c2638bba76c2de92f6966abf09c9b66a Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 11 Oct 2019 12:53:49 -0700
Subject: [PATCH 05/10] net: bcmgenet: Set phydev->dev_flags only for internal
 PHYs

[ Upstream commit 92696286f3bb37ba50e4bd8d1beb24afb759a799 ]

phydev->dev_flags is entirely dependent on the PHY device driver which
is going to be used, setting the internal GENET PHY revision in those
bits only makes sense when drivers/net/phy/bcm7xxx.c is the PHY driver
being used.

Fixes: 487320c54143 ("net: bcmgenet: communicate integrated PHY revision to PHY driver")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Acked-by: Doug Berger <opendmb@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmmii.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index 7b2fbbc33463..0d527fa5de61 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -280,11 +280,12 @@ int bcmgenet_mii_probe(struct net_device *dev)
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	struct device_node *dn = priv->pdev->dev.of_node;
 	struct phy_device *phydev;
-	u32 phy_flags;
+	u32 phy_flags = 0;
 	int ret;
 
 	/* Communicate the integrated PHY revision */
-	phy_flags = priv->gphy_rev;
+	if (priv->internal_phy)
+		phy_flags = priv->gphy_rev;
 
 	/* Initialize link state variables that bcmgenet_mii_setup() uses */
 	priv->old_link = -1;
-- 
2.20.1


From 6fbeafcad49fb2c68b79b1caaca303f07f4e285d Mon Sep 17 00:00:00 2001
From: Thomas Bogendoerfer <tbogendoerfer@suse.de>
Date: Tue, 15 Oct 2019 16:42:45 +0200
Subject: [PATCH 06/10] net: i82596: fix dma_alloc_attr for sni_82596

[ Upstream commit 61c1d33daf7b5146f44d4363b3322f8cda6a6c43 ]

Commit 7f683b920479 ("i825xx: switch to switch to dma_alloc_attrs")
switched dma allocation over to dma_alloc_attr, but didn't convert
the SNI part to request consistent DMA memory. This broke sni_82596
since driver doesn't do dma_cache_sync for performance reasons.
Fix this by using different DMA_ATTRs for lasi_82596 and sni_82596.

Fixes: 7f683b920479 ("i825xx: switch to switch to dma_alloc_attrs")
Signed-off-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/i825xx/lasi_82596.c | 4 +++-
 drivers/net/ethernet/i825xx/lib82596.c   | 4 ++--
 drivers/net/ethernet/i825xx/sni_82596.c  | 4 +++-
 3 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/i825xx/lasi_82596.c b/drivers/net/ethernet/i825xx/lasi_82596.c
index b69c622ba8b2..6f0e4019adef 100644
--- a/drivers/net/ethernet/i825xx/lasi_82596.c
+++ b/drivers/net/ethernet/i825xx/lasi_82596.c
@@ -96,6 +96,8 @@
 
 #define OPT_SWAP_PORT	0x0001	/* Need to wordswp on the MPU port */
 
+#define LIB82596_DMA_ATTR	DMA_ATTR_NON_CONSISTENT
+
 #define DMA_WBACK(ndev, addr, len) \
 	do { dma_cache_sync((ndev)->dev.parent, (void *)addr, len, DMA_TO_DEVICE); } while (0)
 
@@ -199,7 +201,7 @@ static int __exit lan_remove_chip(struct parisc_device *pdev)
 
 	unregister_netdev (dev);
 	dma_free_attrs(&pdev->dev, sizeof(struct i596_private), lp->dma,
-		       lp->dma_addr, DMA_ATTR_NON_CONSISTENT);
+		       lp->dma_addr, LIB82596_DMA_ATTR);
 	free_netdev (dev);
 	return 0;
 }
diff --git a/drivers/net/ethernet/i825xx/lib82596.c b/drivers/net/ethernet/i825xx/lib82596.c
index 2f7ae118217f..d0e8193ca470 100644
--- a/drivers/net/ethernet/i825xx/lib82596.c
+++ b/drivers/net/ethernet/i825xx/lib82596.c
@@ -1065,7 +1065,7 @@ static int i82596_probe(struct net_device *dev)
 
 	dma = dma_alloc_attrs(dev->dev.parent, sizeof(struct i596_dma),
 			      &lp->dma_addr, GFP_KERNEL,
-			      DMA_ATTR_NON_CONSISTENT);
+			      LIB82596_DMA_ATTR);
 	if (!dma) {
 		printk(KERN_ERR "%s: Couldn't get shared memory\n", __FILE__);
 		return -ENOMEM;
@@ -1087,7 +1087,7 @@ static int i82596_probe(struct net_device *dev)
 	i = register_netdev(dev);
 	if (i) {
 		dma_free_attrs(dev->dev.parent, sizeof(struct i596_dma),
-			       dma, lp->dma_addr, DMA_ATTR_NON_CONSISTENT);
+			       dma, lp->dma_addr, LIB82596_DMA_ATTR);
 		return i;
 	}
 
diff --git a/drivers/net/ethernet/i825xx/sni_82596.c b/drivers/net/ethernet/i825xx/sni_82596.c
index b2c04a789744..43c1fd18670b 100644
--- a/drivers/net/ethernet/i825xx/sni_82596.c
+++ b/drivers/net/ethernet/i825xx/sni_82596.c
@@ -23,6 +23,8 @@
 
 static const char sni_82596_string[] = "snirm_82596";
 
+#define LIB82596_DMA_ATTR	0
+
 #define DMA_WBACK(priv, addr, len)     do { } while (0)
 #define DMA_INV(priv, addr, len)       do { } while (0)
 #define DMA_WBACK_INV(priv, addr, len) do { } while (0)
@@ -151,7 +153,7 @@ static int sni_82596_driver_remove(struct platform_device *pdev)
 
 	unregister_netdev(dev);
 	dma_free_attrs(dev->dev.parent, sizeof(struct i596_private), lp->dma,
-		       lp->dma_addr, DMA_ATTR_NON_CONSISTENT);
+		       lp->dma_addr, LIB82596_DMA_ATTR);
 	iounmap(lp->ca);
 	iounmap(lp->mpu_port);
 	free_netdev (dev);
-- 
2.20.1


From a987148407aee3c087e43cd8176532e0a51d9fc4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= <clg@kaod.org>
Date: Fri, 11 Oct 2019 07:52:54 +0200
Subject: [PATCH 07/10] net/ibmvnic: Fix EOI when running in XIVE mode.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 11d49ce9f7946dfed4dcf5dbde865c78058b50ab ]

pSeries machines on POWER9 processors can run with the XICS (legacy)
interrupt mode or with the XIVE exploitation interrupt mode. These
interrupt contollers have different interfaces for interrupt
management : XICS uses hcalls and XIVE loads and stores on a page.
H_EOI being a XICS interface the enable_scrq_irq() routine can fail
when the machine runs in XIVE mode.

Fix that by calling the EOI handler of the interrupt chip.

Fixes: f23e0643cd0b ("ibmvnic: Clear pending interrupt after device reset")
Signed-off-by: Cédric Le Goater <clg@kaod.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ibm/ibmvnic.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index aa067a7a72d4..8fa14736449b 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -2731,12 +2731,10 @@ static int enable_scrq_irq(struct ibmvnic_adapter *adapter,
 
 	if (adapter->resetting &&
 	    adapter->reset_reason == VNIC_RESET_MOBILITY) {
-		u64 val = (0xff000000) | scrq->hw_irq;
+		struct irq_desc *desc = irq_to_desc(scrq->irq);
+		struct irq_chip *chip = irq_desc_get_chip(desc);
 
-		rc = plpar_hcall_norets(H_EOI, val);
-		if (rc)
-			dev_err(dev, "H_EOI FAILED irq 0x%llx. rc=%ld\n",
-				val, rc);
+		chip->irq_eoi(&desc->irq_data);
 	}
 
 	rc = plpar_hcall_norets(H_VIOCTL, adapter->vdev->unit_address,
-- 
2.20.1


From 61a1478e81506c2131f77033cc4f659f883da1d3 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Fri, 23 Aug 2019 19:33:03 +0800
Subject: [PATCH 08/10] net: ipv6: fix listify ip6_rcv_finish in case of
 forwarding

[ Upstream commit c7a42eb49212f93a800560662d17d5293960d3c3 ]

We need a similar fix for ipv6 as Commit 0761680d5215 ("net: ipv4: fix
listify ip_rcv_finish in case of forwarding") does for ipv4.

This issue can be reprocuded by syzbot since Commit 323ebb61e32b ("net:
use listified RX for handling GRO_NORMAL skbs") on net-next. The call
trace was:

  kernel BUG at include/linux/skbuff.h:2225!
  RIP: 0010:__skb_pull include/linux/skbuff.h:2225 [inline]
  RIP: 0010:skb_pull+0xea/0x110 net/core/skbuff.c:1902
  Call Trace:
    sctp_inq_pop+0x2f1/0xd80 net/sctp/inqueue.c:202
    sctp_endpoint_bh_rcv+0x184/0x8d0 net/sctp/endpointola.c:385
    sctp_inq_push+0x1e4/0x280 net/sctp/inqueue.c:80
    sctp_rcv+0x2807/0x3590 net/sctp/input.c:256
    sctp6_rcv+0x17/0x30 net/sctp/ipv6.c:1049
    ip6_protocol_deliver_rcu+0x2fe/0x1660 net/ipv6/ip6_input.c:397
    ip6_input_finish+0x84/0x170 net/ipv6/ip6_input.c:438
    NF_HOOK include/linux/netfilter.h:305 [inline]
    NF_HOOK include/linux/netfilter.h:299 [inline]
    ip6_input+0xe4/0x3f0 net/ipv6/ip6_input.c:447
    dst_input include/net/dst.h:442 [inline]
    ip6_sublist_rcv_finish+0x98/0x1e0 net/ipv6/ip6_input.c:84
    ip6_list_rcv_finish net/ipv6/ip6_input.c:118 [inline]
    ip6_sublist_rcv+0x80c/0xcf0 net/ipv6/ip6_input.c:282
    ipv6_list_rcv+0x373/0x4b0 net/ipv6/ip6_input.c:316
    __netif_receive_skb_list_ptype net/core/dev.c:5049 [inline]
    __netif_receive_skb_list_core+0x5fc/0x9d0 net/core/dev.c:5097
    __netif_receive_skb_list net/core/dev.c:5149 [inline]
    netif_receive_skb_list_internal+0x7eb/0xe60 net/core/dev.c:5244
    gro_normal_list.part.0+0x1e/0xb0 net/core/dev.c:5757
    gro_normal_list net/core/dev.c:5755 [inline]
    gro_normal_one net/core/dev.c:5769 [inline]
    napi_frags_finish net/core/dev.c:5782 [inline]
    napi_gro_frags+0xa6a/0xea0 net/core/dev.c:5855
    tun_get_user+0x2e98/0x3fa0 drivers/net/tun.c:1974
    tun_chr_write_iter+0xbd/0x156 drivers/net/tun.c:2020

Fixes: d8269e2cbf90 ("net: ipv6: listify ipv6_rcv() and ip6_rcv_finish()")
Fixes: 323ebb61e32b ("net: use listified RX for handling GRO_NORMAL skbs")
Reported-by: syzbot+eb349eeee854e389c36d@syzkaller.appspotmail.com
Reported-by: syzbot+4a0643a653ac375612d1@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_input.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 2b6d43022383..acf0749ee5bb 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -80,8 +80,10 @@ static void ip6_sublist_rcv_finish(struct list_head *head)
 {
 	struct sk_buff *skb, *next;
 
-	list_for_each_entry_safe(skb, next, head, list)
+	list_for_each_entry_safe(skb, next, head, list) {
+		skb_list_del_init(skb);
 		dst_input(skb);
+	}
 }
 
 static void ip6_list_rcv_finish(struct net *net, struct sock *sk,
-- 
2.20.1


From fae4482e35ba298bd2154e22276a7f2f7a7eb8bb Mon Sep 17 00:00:00 2001
From: Biao Huang <biao.huang@mediatek.com>
Date: Tue, 15 Oct 2019 11:24:44 +0800
Subject: [PATCH 09/10] net: stmmac: disable/enable ptp_ref_clk in
 suspend/resume flow

[ Upstream commit e497c20e203680aba9ccf7bb475959595908ca7e ]

disable ptp_ref_clk in suspend flow, and enable it in resume flow.

Fixes: f573c0b9c4e0 ("stmmac: move stmmac_clk, pclk, clk_ptp_ref and stmmac_rst to platform structure")
Signed-off-by: Biao Huang <biao.huang@mediatek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 0101ebaecf02..014fe93ed2d8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -4522,8 +4522,10 @@ int stmmac_suspend(struct device *dev)
 		stmmac_mac_set(priv, priv->ioaddr, false);
 		pinctrl_pm_select_sleep_state(priv->device);
 		/* Disable clock in case of PWM is off */
-		clk_disable(priv->plat->pclk);
-		clk_disable(priv->plat->stmmac_clk);
+		if (priv->plat->clk_ptp_ref)
+			clk_disable_unprepare(priv->plat->clk_ptp_ref);
+		clk_disable_unprepare(priv->plat->pclk);
+		clk_disable_unprepare(priv->plat->stmmac_clk);
 	}
 	mutex_unlock(&priv->lock);
 
@@ -4588,8 +4590,10 @@ int stmmac_resume(struct device *dev)
 	} else {
 		pinctrl_pm_select_default_state(priv->device);
 		/* enable the clk previously disabled */
-		clk_enable(priv->plat->stmmac_clk);
-		clk_enable(priv->plat->pclk);
+		clk_prepare_enable(priv->plat->stmmac_clk);
+		clk_prepare_enable(priv->plat->pclk);
+		if (priv->plat->clk_ptp_ref)
+			clk_prepare_enable(priv->plat->clk_ptp_ref);
 		/* reset the phy so that it's ready */
 		if (priv->mii)
 			stmmac_mdio_reset(priv->mii);
-- 
2.20.1


From eed70bdd30dcf449e108aafbd536218d56877853 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 15 Oct 2019 15:24:38 +0800
Subject: [PATCH 10/10] sctp: change sctp_prot .no_autobind with true

[ Upstream commit 63dfb7938b13fa2c2fbcb45f34d065769eb09414 ]

syzbot reported a memory leak:

  BUG: memory leak, unreferenced object 0xffff888120b3d380 (size 64):
  backtrace:

    [...] slab_alloc mm/slab.c:3319 [inline]
    [...] kmem_cache_alloc+0x13f/0x2c0 mm/slab.c:3483
    [...] sctp_bucket_create net/sctp/socket.c:8523 [inline]
    [...] sctp_get_port_local+0x189/0x5a0 net/sctp/socket.c:8270
    [...] sctp_do_bind+0xcc/0x200 net/sctp/socket.c:402
    [...] sctp_bindx_add+0x4b/0xd0 net/sctp/socket.c:497
    [...] sctp_setsockopt_bindx+0x156/0x1b0 net/sctp/socket.c:1022
    [...] sctp_setsockopt net/sctp/socket.c:4641 [inline]
    [...] sctp_setsockopt+0xaea/0x2dc0 net/sctp/socket.c:4611
    [...] sock_common_setsockopt+0x38/0x50 net/core/sock.c:3147
    [...] __sys_setsockopt+0x10f/0x220 net/socket.c:2084
    [...] __do_sys_setsockopt net/socket.c:2100 [inline]

It was caused by when sending msgs without binding a port, in the path:
inet_sendmsg() -> inet_send_prepare() -> inet_autobind() ->
.get_port/sctp_get_port(), sp->bind_hash will be set while bp->port is
not. Later when binding another port by sctp_setsockopt_bindx(), a new
bucket will be created as bp->port is not set.

sctp's autobind is supposed to call sctp_autobind() where it does all
things including setting bp->port. Since sctp_autobind() is called in
sctp_sendmsg() if the sk is not yet bound, it should have skipped the
auto bind.

THis patch is to avoid calling inet_autobind() in inet_send_prepare()
by changing sctp_prot .no_autobind with true, also remove the unused
.get_port.

Reported-by: syzbot+d44f7bbebdea49dbc84a@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 9f5b4e547b63..227b050cfe45 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -8957,7 +8957,7 @@ struct proto sctp_prot = {
 	.backlog_rcv =	sctp_backlog_rcv,
 	.hash        =	sctp_hash,
 	.unhash      =	sctp_unhash,
-	.get_port    =	sctp_get_port,
+	.no_autobind =	true,
 	.obj_size    =  sizeof(struct sctp_sock),
 	.useroffset  =  offsetof(struct sctp_sock, subscribe),
 	.usersize    =  offsetof(struct sctp_sock, initmsg) -
@@ -8999,7 +8999,7 @@ struct proto sctpv6_prot = {
 	.backlog_rcv	= sctp_backlog_rcv,
 	.hash		= sctp_hash,
 	.unhash		= sctp_unhash,
-	.get_port	= sctp_get_port,
+	.no_autobind	= true,
 	.obj_size	= sizeof(struct sctp6_sock),
 	.useroffset	= offsetof(struct sctp6_sock, sctp.subscribe),
 	.usersize	= offsetof(struct sctp6_sock, sctp.initmsg) -
-- 
2.20.1


[-- Attachment #3: net_53.mbox --]
[-- Type: Application/Octet-Stream, Size: 74032 bytes --]

From 8772e9ac231a6e6bb221a444cb0e75d01adb92d9 Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Wed, 16 Oct 2019 12:03:15 -0700
Subject: [PATCH 01/23] ipv4: fix race condition between route lookup and
 invalidation

[ Upstream commit 5018c59607a511cdee743b629c76206d9c9e6d7b ]

Jesse and Ido reported the following race condition:
<CPU A, t0> - Received packet A is forwarded and cached dst entry is
taken from the nexthop ('nhc->nhc_rth_input'). Calls skb_dst_set()

<t1> - Given Jesse has busy routers ("ingesting full BGP routing tables
from multiple ISPs"), route is added / deleted and rt_cache_flush() is
called

<CPU B, t2> - Received packet B tries to use the same cached dst entry
from t0, but rt_cache_valid() is no longer true and it is replaced in
rt_cache_route() by the newer one. This calls dst_dev_put() on the
original dst entry which assigns the blackhole netdev to 'dst->dev'

<CPU A, t3> - dst_input(skb) is called on packet A and it is dropped due
to 'dst->dev' being the blackhole netdev

There are 2 issues in the v4 routing code:
1. A per-netns counter is used to do the validation of the route. That
means whenever a route is changed in the netns, users of all routes in
the netns needs to redo lookup. v6 has an implementation of only
updating fn_sernum for routes that are affected.
2. When rt_cache_valid() returns false, rt_cache_route() is called to
throw away the current cache, and create a new one. This seems
unnecessary because as long as this route does not change, the route
cache does not need to be recreated.

To fully solve the above 2 issues, it probably needs quite some code
changes and requires careful testing, and does not suite for net branch.

So this patch only tries to add the deleted cached rt into the uncached
list, so user could still be able to use it to receive packets until
it's done.

Fixes: 95c47f9cf5e0 ("ipv4: call dst_dev_put() properly")
Signed-off-by: Wei Wang <weiwan@google.com>
Reported-by: Ido Schimmel <idosch@idosch.org>
Reported-by: Jesse Hathaway <jesse@mbuki-mvuki.org>
Tested-by: Jesse Hathaway <jesse@mbuki-mvuki.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Cc: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 14654876127e..9e0c8dff2cd6 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1482,7 +1482,7 @@ static bool rt_cache_route(struct fib_nh_common *nhc, struct rtable *rt)
 	prev = cmpxchg(p, orig, rt);
 	if (prev == orig) {
 		if (orig) {
-			dst_dev_put(&orig->dst);
+			rt_add_uncached_list(orig);
 			dst_release(&orig->dst);
 		}
 	} else {
-- 
2.20.1


From 8b179cdbd613984ec5af9372f7a144f57d3bec48 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Wed, 16 Oct 2019 20:52:09 +0200
Subject: [PATCH 02/23] ipv4: Return -ENETUNREACH if we can't create route but
 saddr is valid

[ Upstream commit 595e0651d0296bad2491a4a29a7a43eae6328b02 ]

...instead of -EINVAL. An issue was found with older kernel versions
while unplugging a NFS client with pending RPCs, and the wrong error
code here prevented it from recovering once link is back up with a
configured address.

Incidentally, this is not an issue anymore since commit 4f8943f80883
("SUNRPC: Replace direct task wakeups from softirq context"), included
in 5.2-rc7, had the effect of decoupling the forwarding of this error
by using SO_ERROR in xs_wake_error(), as pointed out by Benjamin
Coddington.

To the best of my knowledge, this isn't currently causing any further
issue, but the error code doesn't look appropriate anyway, and we
might hit this in other paths as well.

In detail, as analysed by Gonzalo Siero, once the route is deleted
because the interface is down, and can't be resolved and we return
-EINVAL here, this ends up, courtesy of inet_sk_rebuild_header(),
as the socket error seen by tcp_write_err(), called by
tcp_retransmit_timer().

In turn, tcp_write_err() indirectly calls xs_error_report(), which
wakes up the RPC pending tasks with a status of -EINVAL. This is then
seen by call_status() in the SUN RPC implementation, which aborts the
RPC call calling rpc_exit(), instead of handling this as a
potentially temporary condition, i.e. as a timeout.

Return -EINVAL only if the input parameters passed to
ip_route_output_key_hash_rcu() are actually invalid (this is the case
if the specified source address is multicast, limited broadcast or
all zeroes), but return -ENETUNREACH in all cases where, at the given
moment, the given source address doesn't allow resolving the route.

While at it, drop the initialisation of err to -ENETUNREACH, which
was added to __ip_route_output_key() back then by commit
0315e3827048 ("net: Fix behaviour of unreachable, blackhole and
prohibit routes"), but actually had no effect, as it was, and is,
overwritten by the fib_lookup() return code assignment, and anyway
ignored in all other branches, including the if (fl4->saddr) one:
I find this rather confusing, as it would look like -ENETUNREACH is
the "default" error, while that statement has no effect.

Also note that after commit fc75fc8339e7 ("ipv4: dont create routes
on down devices"), we would get -ENETUNREACH if the device is down,
but -EINVAL if the source address is specified and we can't resolve
the route, and this appears to be rather inconsistent.

Reported-by: Stefan Walter <walteste@inf.ethz.ch>
Analysed-by: Benjamin Coddington <bcodding@redhat.com>
Analysed-by: Gonzalo Siero <gsierohu@redhat.com>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 9e0c8dff2cd6..621f83434b24 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2470,14 +2470,17 @@ struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4,
 	int orig_oif = fl4->flowi4_oif;
 	unsigned int flags = 0;
 	struct rtable *rth;
-	int err = -ENETUNREACH;
+	int err;
 
 	if (fl4->saddr) {
-		rth = ERR_PTR(-EINVAL);
 		if (ipv4_is_multicast(fl4->saddr) ||
 		    ipv4_is_lbcast(fl4->saddr) ||
-		    ipv4_is_zeronet(fl4->saddr))
+		    ipv4_is_zeronet(fl4->saddr)) {
+			rth = ERR_PTR(-EINVAL);
 			goto out;
+		}
+
+		rth = ERR_PTR(-ENETUNREACH);
 
 		/* I removed check for oif == dev_out->oif here.
 		   It was wrong for two reasons:
-- 
2.20.1


From 66e887c0930e2e0fcf07566f633dfaa32f24a8ef Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 14 Oct 2019 11:22:30 -0700
Subject: [PATCH 03/23] net: avoid potential infinite loop in tc_ctl_action()

[ Upstream commit 39f13ea2f61b439ebe0060393e9c39925c9ee28c ]

tc_ctl_action() has the ability to loop forever if tcf_action_add()
returns -EAGAIN.

This special case has been done in case a module needed to be loaded,
but it turns out that tcf_add_notify() could also return -EAGAIN
if the socket sk_rcvbuf limit is hit.

We need to separate the two cases, and only loop for the module
loading case.

While we are at it, add a limit of 10 attempts since unbounded
loops are always scary.

syzbot repro was something like :

socket(PF_NETLINK, SOCK_RAW|SOCK_NONBLOCK, NETLINK_ROUTE) = 3
write(3, ..., 38) = 38
setsockopt(3, SOL_SOCKET, SO_RCVBUF, [0], 4) = 0
sendmsg(3, {msg_name(0)=NULL, msg_iov(1)=[{..., 388}], msg_controllen=0, msg_flags=0x10}, ...)

NMI backtrace for cpu 0
CPU: 0 PID: 1054 Comm: khungtaskd Not tainted 5.4.0-rc1+ #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 nmi_cpu_backtrace.cold+0x70/0xb2 lib/nmi_backtrace.c:101
 nmi_trigger_cpumask_backtrace+0x23b/0x28b lib/nmi_backtrace.c:62
 arch_trigger_cpumask_backtrace+0x14/0x20 arch/x86/kernel/apic/hw_nmi.c:38
 trigger_all_cpu_backtrace include/linux/nmi.h:146 [inline]
 check_hung_uninterruptible_tasks kernel/hung_task.c:205 [inline]
 watchdog+0x9d0/0xef0 kernel/hung_task.c:289
 kthread+0x361/0x430 kernel/kthread.c:255
 ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:352
Sending NMI from CPU 0 to CPUs 1:
NMI backtrace for cpu 1
CPU: 1 PID: 8859 Comm: syz-executor910 Not tainted 5.4.0-rc1+ #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:arch_local_save_flags arch/x86/include/asm/paravirt.h:751 [inline]
RIP: 0010:lockdep_hardirqs_off+0x1df/0x2e0 kernel/locking/lockdep.c:3453
Code: 5c 08 00 00 5b 41 5c 41 5d 5d c3 48 c7 c0 58 1d f3 88 48 ba 00 00 00 00 00 fc ff df 48 c1 e8 03 80 3c 10 00 0f 85 d3 00 00 00 <48> 83 3d 21 9e 99 07 00 0f 84 b9 00 00 00 9c 58 0f 1f 44 00 00 f6
RSP: 0018:ffff8880a6f3f1b8 EFLAGS: 00000046
RAX: 1ffffffff11e63ab RBX: ffff88808c9c6080 RCX: 0000000000000000
RDX: dffffc0000000000 RSI: 0000000000000000 RDI: ffff88808c9c6914
RBP: ffff8880a6f3f1d0 R08: ffff88808c9c6080 R09: fffffbfff16be5d1
R10: fffffbfff16be5d0 R11: 0000000000000003 R12: ffffffff8746591f
R13: ffff88808c9c6080 R14: ffffffff8746591f R15: 0000000000000003
FS:  00000000011e4880(0000) GS:ffff8880ae900000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffffffffff600400 CR3: 00000000a8920000 CR4: 00000000001406e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 trace_hardirqs_off+0x62/0x240 kernel/trace/trace_preemptirq.c:45
 __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:108 [inline]
 _raw_spin_lock_irqsave+0x6f/0xcd kernel/locking/spinlock.c:159
 __wake_up_common_lock+0xc8/0x150 kernel/sched/wait.c:122
 __wake_up+0xe/0x10 kernel/sched/wait.c:142
 netlink_unlock_table net/netlink/af_netlink.c:466 [inline]
 netlink_unlock_table net/netlink/af_netlink.c:463 [inline]
 netlink_broadcast_filtered+0x705/0xb80 net/netlink/af_netlink.c:1514
 netlink_broadcast+0x3a/0x50 net/netlink/af_netlink.c:1534
 rtnetlink_send+0xdd/0x110 net/core/rtnetlink.c:714
 tcf_add_notify net/sched/act_api.c:1343 [inline]
 tcf_action_add+0x243/0x370 net/sched/act_api.c:1362
 tc_ctl_action+0x3b5/0x4bc net/sched/act_api.c:1410
 rtnetlink_rcv_msg+0x463/0xb00 net/core/rtnetlink.c:5386
 netlink_rcv_skb+0x177/0x450 net/netlink/af_netlink.c:2477
 rtnetlink_rcv+0x1d/0x30 net/core/rtnetlink.c:5404
 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
 netlink_unicast+0x531/0x710 net/netlink/af_netlink.c:1328
 netlink_sendmsg+0x8a5/0xd60 net/netlink/af_netlink.c:1917
 sock_sendmsg_nosec net/socket.c:637 [inline]
 sock_sendmsg+0xd7/0x130 net/socket.c:657
 ___sys_sendmsg+0x803/0x920 net/socket.c:2311
 __sys_sendmsg+0x105/0x1d0 net/socket.c:2356
 __do_sys_sendmsg net/socket.c:2365 [inline]
 __se_sys_sendmsg net/socket.c:2363 [inline]
 __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2363
 do_syscall_64+0xfa/0x760 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x440939

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot+cf0adbb9c28c8866c788@syzkaller.appspotmail.com
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_api.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 2558f00f6b3e..6ef2cdc316d2 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -1352,11 +1352,16 @@ static int tcf_action_add(struct net *net, struct nlattr *nla,
 			  struct netlink_ext_ack *extack)
 {
 	size_t attr_size = 0;
-	int ret = 0;
+	int loop, ret;
 	struct tc_action *actions[TCA_ACT_MAX_PRIO] = {};
 
-	ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, actions,
-			      &attr_size, true, extack);
+	for (loop = 0; loop < 10; loop++) {
+		ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0,
+				      actions, &attr_size, true, extack);
+		if (ret != -EAGAIN)
+			break;
+	}
+
 	if (ret < 0)
 		return ret;
 	ret = tcf_add_notify(net, n, actions, portid, attr_size, extack);
@@ -1406,11 +1411,8 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n,
 		 */
 		if (n->nlmsg_flags & NLM_F_REPLACE)
 			ovr = 1;
-replay:
 		ret = tcf_action_add(net, tca[TCA_ACT_TAB], n, portid, ovr,
 				     extack);
-		if (ret == -EAGAIN)
-			goto replay;
 		break;
 	case RTM_DELACTION:
 		ret = tca_action_gd(net, tca[TCA_ACT_TAB], n,
-- 
2.20.1


From a8210a2373a950510200a5845b40a87673a11f37 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 15 Oct 2019 10:45:47 -0700
Subject: [PATCH 04/23] net: bcmgenet: Fix RGMII_MODE_EN value for GENET v1/2/3

[ Upstream commit efb86fede98cdc70b674692ff617b1162f642c49 ]

The RGMII_MODE_EN bit value was 0 for GENET versions 1 through 3, and
became 6 for GENET v4 and above, account for that difference.

Fixes: aa09677cba42 ("net: bcmgenet: add MDIO routines")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Acked-by: Doug Berger <opendmb@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.h | 1 +
 drivers/net/ethernet/broadcom/genet/bcmmii.c   | 6 +++++-
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 4a8fc03d82fd..dbc69d8fa05f 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -366,6 +366,7 @@ struct bcmgenet_mib_counters {
 #define  EXT_PWR_DOWN_PHY_EN		(1 << 20)
 
 #define EXT_RGMII_OOB_CTRL		0x0C
+#define  RGMII_MODE_EN_V123		(1 << 0)
 #define  RGMII_LINK			(1 << 4)
 #define  OOB_DISABLE			(1 << 5)
 #define  RGMII_MODE_EN			(1 << 6)
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index 970e478a9017..37b586b86334 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -258,7 +258,11 @@ int bcmgenet_mii_config(struct net_device *dev, bool init)
 	 */
 	if (priv->ext_phy) {
 		reg = bcmgenet_ext_readl(priv, EXT_RGMII_OOB_CTRL);
-		reg |= RGMII_MODE_EN | id_mode_dis;
+		reg |= id_mode_dis;
+		if (GENET_IS_V1(priv) || GENET_IS_V2(priv) || GENET_IS_V3(priv))
+			reg |= RGMII_MODE_EN_V123;
+		else
+			reg |= RGMII_MODE_EN;
 		bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL);
 	}
 
-- 
2.20.1


From f36afc603a9bfeddd6170611ff94890887db3518 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 11 Oct 2019 12:53:49 -0700
Subject: [PATCH 05/23] net: bcmgenet: Set phydev->dev_flags only for internal
 PHYs

[ Upstream commit 92696286f3bb37ba50e4bd8d1beb24afb759a799 ]

phydev->dev_flags is entirely dependent on the PHY device driver which
is going to be used, setting the internal GENET PHY revision in those
bits only makes sense when drivers/net/phy/bcm7xxx.c is the PHY driver
being used.

Fixes: 487320c54143 ("net: bcmgenet: communicate integrated PHY revision to PHY driver")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Acked-by: Doug Berger <opendmb@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmmii.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index 37b586b86334..e7c291bf4ed1 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -277,11 +277,12 @@ int bcmgenet_mii_probe(struct net_device *dev)
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	struct device_node *dn = priv->pdev->dev.of_node;
 	struct phy_device *phydev;
-	u32 phy_flags;
+	u32 phy_flags = 0;
 	int ret;
 
 	/* Communicate the integrated PHY revision */
-	phy_flags = priv->gphy_rev;
+	if (priv->internal_phy)
+		phy_flags = priv->gphy_rev;
 
 	/* Initialize link state variables that bcmgenet_mii_setup() uses */
 	priv->old_link = -1;
-- 
2.20.1


From 7d38f6596cee34b53dd1173d500029b7f2d29b55 Mon Sep 17 00:00:00 2001
From: Thomas Bogendoerfer <tbogendoerfer@suse.de>
Date: Tue, 15 Oct 2019 16:42:45 +0200
Subject: [PATCH 06/23] net: i82596: fix dma_alloc_attr for sni_82596

[ Upstream commit 61c1d33daf7b5146f44d4363b3322f8cda6a6c43 ]

Commit 7f683b920479 ("i825xx: switch to switch to dma_alloc_attrs")
switched dma allocation over to dma_alloc_attr, but didn't convert
the SNI part to request consistent DMA memory. This broke sni_82596
since driver doesn't do dma_cache_sync for performance reasons.
Fix this by using different DMA_ATTRs for lasi_82596 and sni_82596.

Fixes: 7f683b920479 ("i825xx: switch to switch to dma_alloc_attrs")
Signed-off-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/i825xx/lasi_82596.c | 4 +++-
 drivers/net/ethernet/i825xx/lib82596.c   | 4 ++--
 drivers/net/ethernet/i825xx/sni_82596.c  | 4 +++-
 3 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/i825xx/lasi_82596.c b/drivers/net/ethernet/i825xx/lasi_82596.c
index 211c5f74b4c8..aec7e98bcc85 100644
--- a/drivers/net/ethernet/i825xx/lasi_82596.c
+++ b/drivers/net/ethernet/i825xx/lasi_82596.c
@@ -96,6 +96,8 @@
 
 #define OPT_SWAP_PORT	0x0001	/* Need to wordswp on the MPU port */
 
+#define LIB82596_DMA_ATTR	DMA_ATTR_NON_CONSISTENT
+
 #define DMA_WBACK(ndev, addr, len) \
 	do { dma_cache_sync((ndev)->dev.parent, (void *)addr, len, DMA_TO_DEVICE); } while (0)
 
@@ -200,7 +202,7 @@ static int __exit lan_remove_chip(struct parisc_device *pdev)
 
 	unregister_netdev (dev);
 	dma_free_attrs(&pdev->dev, sizeof(struct i596_private), lp->dma,
-		       lp->dma_addr, DMA_ATTR_NON_CONSISTENT);
+		       lp->dma_addr, LIB82596_DMA_ATTR);
 	free_netdev (dev);
 	return 0;
 }
diff --git a/drivers/net/ethernet/i825xx/lib82596.c b/drivers/net/ethernet/i825xx/lib82596.c
index 1274ad24d6af..f9742af7f142 100644
--- a/drivers/net/ethernet/i825xx/lib82596.c
+++ b/drivers/net/ethernet/i825xx/lib82596.c
@@ -1065,7 +1065,7 @@ static int i82596_probe(struct net_device *dev)
 
 	dma = dma_alloc_attrs(dev->dev.parent, sizeof(struct i596_dma),
 			      &lp->dma_addr, GFP_KERNEL,
-			      DMA_ATTR_NON_CONSISTENT);
+			      LIB82596_DMA_ATTR);
 	if (!dma) {
 		printk(KERN_ERR "%s: Couldn't get shared memory\n", __FILE__);
 		return -ENOMEM;
@@ -1087,7 +1087,7 @@ static int i82596_probe(struct net_device *dev)
 	i = register_netdev(dev);
 	if (i) {
 		dma_free_attrs(dev->dev.parent, sizeof(struct i596_dma),
-			       dma, lp->dma_addr, DMA_ATTR_NON_CONSISTENT);
+			       dma, lp->dma_addr, LIB82596_DMA_ATTR);
 		return i;
 	}
 
diff --git a/drivers/net/ethernet/i825xx/sni_82596.c b/drivers/net/ethernet/i825xx/sni_82596.c
index 6eb6c2ff7f09..6436a98c5953 100644
--- a/drivers/net/ethernet/i825xx/sni_82596.c
+++ b/drivers/net/ethernet/i825xx/sni_82596.c
@@ -24,6 +24,8 @@
 
 static const char sni_82596_string[] = "snirm_82596";
 
+#define LIB82596_DMA_ATTR	0
+
 #define DMA_WBACK(priv, addr, len)     do { } while (0)
 #define DMA_INV(priv, addr, len)       do { } while (0)
 #define DMA_WBACK_INV(priv, addr, len) do { } while (0)
@@ -152,7 +154,7 @@ static int sni_82596_driver_remove(struct platform_device *pdev)
 
 	unregister_netdev(dev);
 	dma_free_attrs(dev->dev.parent, sizeof(struct i596_private), lp->dma,
-		       lp->dma_addr, DMA_ATTR_NON_CONSISTENT);
+		       lp->dma_addr, LIB82596_DMA_ATTR);
 	iounmap(lp->ca);
 	iounmap(lp->mpu_port);
 	free_netdev (dev);
-- 
2.20.1


From d781d3e6c350cf03835d84788682333e271f4dab Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= <clg@kaod.org>
Date: Fri, 11 Oct 2019 07:52:54 +0200
Subject: [PATCH 07/23] net/ibmvnic: Fix EOI when running in XIVE mode.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 11d49ce9f7946dfed4dcf5dbde865c78058b50ab ]

pSeries machines on POWER9 processors can run with the XICS (legacy)
interrupt mode or with the XIVE exploitation interrupt mode. These
interrupt contollers have different interfaces for interrupt
management : XICS uses hcalls and XIVE loads and stores on a page.
H_EOI being a XICS interface the enable_scrq_irq() routine can fail
when the machine runs in XIVE mode.

Fix that by calling the EOI handler of the interrupt chip.

Fixes: f23e0643cd0b ("ibmvnic: Clear pending interrupt after device reset")
Signed-off-by: Cédric Le Goater <clg@kaod.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ibm/ibmvnic.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 5cb55ea671e3..964e7d62f4b1 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -2772,12 +2772,10 @@ static int enable_scrq_irq(struct ibmvnic_adapter *adapter,
 
 	if (adapter->resetting &&
 	    adapter->reset_reason == VNIC_RESET_MOBILITY) {
-		u64 val = (0xff000000) | scrq->hw_irq;
+		struct irq_desc *desc = irq_to_desc(scrq->irq);
+		struct irq_chip *chip = irq_desc_get_chip(desc);
 
-		rc = plpar_hcall_norets(H_EOI, val);
-		if (rc)
-			dev_err(dev, "H_EOI FAILED irq 0x%llx. rc=%ld\n",
-				val, rc);
+		chip->irq_eoi(&desc->irq_data);
 	}
 
 	rc = plpar_hcall_norets(H_VIOCTL, adapter->vdev->unit_address,
-- 
2.20.1


From 8e64bbe6ebabb578d7eb98d0ece47443a45aa8da Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Fri, 23 Aug 2019 19:33:03 +0800
Subject: [PATCH 08/23] net: ipv6: fix listify ip6_rcv_finish in case of
 forwarding

[ Upstream commit c7a42eb49212f93a800560662d17d5293960d3c3 ]

We need a similar fix for ipv6 as Commit 0761680d5215 ("net: ipv4: fix
listify ip_rcv_finish in case of forwarding") does for ipv4.

This issue can be reprocuded by syzbot since Commit 323ebb61e32b ("net:
use listified RX for handling GRO_NORMAL skbs") on net-next. The call
trace was:

  kernel BUG at include/linux/skbuff.h:2225!
  RIP: 0010:__skb_pull include/linux/skbuff.h:2225 [inline]
  RIP: 0010:skb_pull+0xea/0x110 net/core/skbuff.c:1902
  Call Trace:
    sctp_inq_pop+0x2f1/0xd80 net/sctp/inqueue.c:202
    sctp_endpoint_bh_rcv+0x184/0x8d0 net/sctp/endpointola.c:385
    sctp_inq_push+0x1e4/0x280 net/sctp/inqueue.c:80
    sctp_rcv+0x2807/0x3590 net/sctp/input.c:256
    sctp6_rcv+0x17/0x30 net/sctp/ipv6.c:1049
    ip6_protocol_deliver_rcu+0x2fe/0x1660 net/ipv6/ip6_input.c:397
    ip6_input_finish+0x84/0x170 net/ipv6/ip6_input.c:438
    NF_HOOK include/linux/netfilter.h:305 [inline]
    NF_HOOK include/linux/netfilter.h:299 [inline]
    ip6_input+0xe4/0x3f0 net/ipv6/ip6_input.c:447
    dst_input include/net/dst.h:442 [inline]
    ip6_sublist_rcv_finish+0x98/0x1e0 net/ipv6/ip6_input.c:84
    ip6_list_rcv_finish net/ipv6/ip6_input.c:118 [inline]
    ip6_sublist_rcv+0x80c/0xcf0 net/ipv6/ip6_input.c:282
    ipv6_list_rcv+0x373/0x4b0 net/ipv6/ip6_input.c:316
    __netif_receive_skb_list_ptype net/core/dev.c:5049 [inline]
    __netif_receive_skb_list_core+0x5fc/0x9d0 net/core/dev.c:5097
    __netif_receive_skb_list net/core/dev.c:5149 [inline]
    netif_receive_skb_list_internal+0x7eb/0xe60 net/core/dev.c:5244
    gro_normal_list.part.0+0x1e/0xb0 net/core/dev.c:5757
    gro_normal_list net/core/dev.c:5755 [inline]
    gro_normal_one net/core/dev.c:5769 [inline]
    napi_frags_finish net/core/dev.c:5782 [inline]
    napi_gro_frags+0xa6a/0xea0 net/core/dev.c:5855
    tun_get_user+0x2e98/0x3fa0 drivers/net/tun.c:1974
    tun_chr_write_iter+0xbd/0x156 drivers/net/tun.c:2020

Fixes: d8269e2cbf90 ("net: ipv6: listify ipv6_rcv() and ip6_rcv_finish()")
Fixes: 323ebb61e32b ("net: use listified RX for handling GRO_NORMAL skbs")
Reported-by: syzbot+eb349eeee854e389c36d@syzkaller.appspotmail.com
Reported-by: syzbot+4a0643a653ac375612d1@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_input.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index a593aaf25748..2bb0b66181a7 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -80,8 +80,10 @@ static void ip6_sublist_rcv_finish(struct list_head *head)
 {
 	struct sk_buff *skb, *next;
 
-	list_for_each_entry_safe(skb, next, head, list)
+	list_for_each_entry_safe(skb, next, head, list) {
+		skb_list_del_init(skb);
 		dst_input(skb);
+	}
 }
 
 static void ip6_list_rcv_finish(struct net *net, struct sock *sk,
-- 
2.20.1


From f1b04a8f6c0b7a43d423cbc3a53a75512962e8d5 Mon Sep 17 00:00:00 2001
From: Biao Huang <biao.huang@mediatek.com>
Date: Tue, 15 Oct 2019 11:24:44 +0800
Subject: [PATCH 09/23] net: stmmac: disable/enable ptp_ref_clk in
 suspend/resume flow

[ Upstream commit e497c20e203680aba9ccf7bb475959595908ca7e ]

disable ptp_ref_clk in suspend flow, and enable it in resume flow.

Fixes: f573c0b9c4e0 ("stmmac: move stmmac_clk, pclk, clk_ptp_ref and stmmac_rst to platform structure")
Signed-off-by: Biao Huang <biao.huang@mediatek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 5c4408bdc843..374f9b49bcc1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -4475,8 +4475,10 @@ int stmmac_suspend(struct device *dev)
 		stmmac_mac_set(priv, priv->ioaddr, false);
 		pinctrl_pm_select_sleep_state(priv->device);
 		/* Disable clock in case of PWM is off */
-		clk_disable(priv->plat->pclk);
-		clk_disable(priv->plat->stmmac_clk);
+		if (priv->plat->clk_ptp_ref)
+			clk_disable_unprepare(priv->plat->clk_ptp_ref);
+		clk_disable_unprepare(priv->plat->pclk);
+		clk_disable_unprepare(priv->plat->stmmac_clk);
 	}
 	mutex_unlock(&priv->lock);
 
@@ -4539,8 +4541,10 @@ int stmmac_resume(struct device *dev)
 	} else {
 		pinctrl_pm_select_default_state(priv->device);
 		/* enable the clk previously disabled */
-		clk_enable(priv->plat->stmmac_clk);
-		clk_enable(priv->plat->pclk);
+		clk_prepare_enable(priv->plat->stmmac_clk);
+		clk_prepare_enable(priv->plat->pclk);
+		if (priv->plat->clk_ptp_ref)
+			clk_prepare_enable(priv->plat->clk_ptp_ref);
 		/* reset the phy so that it's ready */
 		if (priv->mii)
 			stmmac_mdio_reset(priv->mii);
-- 
2.20.1


From 1c9b6d8442fe07b29a1900a714ca0c23792948f9 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 10 Oct 2019 15:52:34 +0100
Subject: [PATCH 10/23] rxrpc: Fix possible NULL pointer access in ICMP
 handling

[ Upstream commit f0308fb0708078d6c1d8a4d533941a7a191af634 ]

If an ICMP packet comes in on the UDP socket backing an AF_RXRPC socket as
the UDP socket is being shut down, rxrpc_error_report() may get called to
deal with it after sk_user_data on the UDP socket has been cleared, leading
to a NULL pointer access when this local endpoint record gets accessed.

Fix this by just returning immediately if sk_user_data was NULL.

The oops looks like the following:

#PF: supervisor read access in kernel mode
#PF: error_code(0x0000) - not-present page
...
RIP: 0010:rxrpc_error_report+0x1bd/0x6a9
...
Call Trace:
 ? sock_queue_err_skb+0xbd/0xde
 ? __udp4_lib_err+0x313/0x34d
 __udp4_lib_err+0x313/0x34d
 icmp_unreach+0x1ee/0x207
 icmp_rcv+0x25b/0x28f
 ip_protocol_deliver_rcu+0x95/0x10e
 ip_local_deliver+0xe9/0x148
 __netif_receive_skb_one_core+0x52/0x6e
 process_backlog+0xdc/0x177
 net_rx_action+0xf9/0x270
 __do_softirq+0x1b6/0x39a
 ? smpboot_register_percpu_thread+0xce/0xce
 run_ksoftirqd+0x1d/0x42
 smpboot_thread_fn+0x19e/0x1b3
 kthread+0xf1/0xf6
 ? kthread_delayed_work_timer_fn+0x83/0x83
 ret_from_fork+0x24/0x30

Fixes: 17926a79320a ("[AF_RXRPC]: Provide secure RxRPC sockets for use by userspace and kernel both")
Reported-by: syzbot+611164843bd48cc2190c@syzkaller.appspotmail.com
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/peer_event.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index c97ebdc043e4..61451281d74a 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -151,6 +151,9 @@ void rxrpc_error_report(struct sock *sk)
 	struct rxrpc_peer *peer;
 	struct sk_buff *skb;
 
+	if (unlikely(!local))
+		return;
+
 	_enter("%p{%d}", sk, local->debug_id);
 
 	/* Clear the outstanding error value on the socket so that it doesn't
-- 
2.20.1


From dd5e1fc9355f374b53e403e2f1877bd601385de9 Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Mon, 14 Oct 2019 13:38:22 -0700
Subject: [PATCH 11/23] sched: etf: Fix ordering of packets with same txtime

[ Upstream commit 28aa7c86c2b49f659c8460a89e53b506c45979bb ]

When a application sends many packets with the same txtime, they may
be transmitted out of order (different from the order in which they
were enqueued).

This happens because when inserting elements into the tree, when the
txtime of two packets are the same, the new packet is inserted at the
left side of the tree, causing the reordering. The only effect of this
change should be that packets with the same txtime will be transmitted
in the order they are enqueued.

The application in question (the AVTP GStreamer plugin, still in
development) is sending video traffic, in which each video frame have
a single presentation time, the problem is that when packetizing,
multiple packets end up with the same txtime.

The receiving side was rejecting packets because they were being
received out of order.

Fixes: 25db26a91364 ("net/sched: Introduce the ETF Qdisc")
Reported-by: Ederson de Souza <ederson.desouza@intel.com>
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_etf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c
index cebfb65d8556..b1da5589a0c6 100644
--- a/net/sched/sch_etf.c
+++ b/net/sched/sch_etf.c
@@ -177,7 +177,7 @@ static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch,
 
 		parent = *p;
 		skb = rb_to_skb(parent);
-		if (ktime_after(txtime, skb->tstamp)) {
+		if (ktime_compare(txtime, skb->tstamp) >= 0) {
 			p = &parent->rb_right;
 			leftmost = false;
 		} else {
-- 
2.20.1


From 14197cf1bb1441fd7acaf5f766754033baecb825 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 15 Oct 2019 15:24:38 +0800
Subject: [PATCH 12/23] sctp: change sctp_prot .no_autobind with true

[ Upstream commit 63dfb7938b13fa2c2fbcb45f34d065769eb09414 ]

syzbot reported a memory leak:

  BUG: memory leak, unreferenced object 0xffff888120b3d380 (size 64):
  backtrace:

    [...] slab_alloc mm/slab.c:3319 [inline]
    [...] kmem_cache_alloc+0x13f/0x2c0 mm/slab.c:3483
    [...] sctp_bucket_create net/sctp/socket.c:8523 [inline]
    [...] sctp_get_port_local+0x189/0x5a0 net/sctp/socket.c:8270
    [...] sctp_do_bind+0xcc/0x200 net/sctp/socket.c:402
    [...] sctp_bindx_add+0x4b/0xd0 net/sctp/socket.c:497
    [...] sctp_setsockopt_bindx+0x156/0x1b0 net/sctp/socket.c:1022
    [...] sctp_setsockopt net/sctp/socket.c:4641 [inline]
    [...] sctp_setsockopt+0xaea/0x2dc0 net/sctp/socket.c:4611
    [...] sock_common_setsockopt+0x38/0x50 net/core/sock.c:3147
    [...] __sys_setsockopt+0x10f/0x220 net/socket.c:2084
    [...] __do_sys_setsockopt net/socket.c:2100 [inline]

It was caused by when sending msgs without binding a port, in the path:
inet_sendmsg() -> inet_send_prepare() -> inet_autobind() ->
.get_port/sctp_get_port(), sp->bind_hash will be set while bp->port is
not. Later when binding another port by sctp_setsockopt_bindx(), a new
bucket will be created as bp->port is not set.

sctp's autobind is supposed to call sctp_autobind() where it does all
things including setting bp->port. Since sctp_autobind() is called in
sctp_sendmsg() if the sk is not yet bound, it should have skipped the
auto bind.

THis patch is to avoid calling inet_autobind() in inet_send_prepare()
by changing sctp_prot .no_autobind with true, also remove the unused
.get_port.

Reported-by: syzbot+d44f7bbebdea49dbc84a@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index b083d4e66230..8fd7b0e6ce9f 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -9353,7 +9353,7 @@ struct proto sctp_prot = {
 	.backlog_rcv =	sctp_backlog_rcv,
 	.hash        =	sctp_hash,
 	.unhash      =	sctp_unhash,
-	.get_port    =	sctp_get_port,
+	.no_autobind =	true,
 	.obj_size    =  sizeof(struct sctp_sock),
 	.useroffset  =  offsetof(struct sctp_sock, subscribe),
 	.usersize    =  offsetof(struct sctp_sock, initmsg) -
@@ -9395,7 +9395,7 @@ struct proto sctpv6_prot = {
 	.backlog_rcv	= sctp_backlog_rcv,
 	.hash		= sctp_hash,
 	.unhash		= sctp_unhash,
-	.get_port	= sctp_get_port,
+	.no_autobind	= true,
 	.obj_size	= sizeof(struct sctp6_sock),
 	.useroffset	= offsetof(struct sctp6_sock, sctp.subscribe),
 	.usersize	= offsetof(struct sctp6_sock, sctp.initmsg) -
-- 
2.20.1


From 87101639412b68b556fa0c2d705936a2bd8ac5f4 Mon Sep 17 00:00:00 2001
From: Igor Russkikh <Igor.Russkikh@aquantia.com>
Date: Fri, 11 Oct 2019 13:45:19 +0000
Subject: [PATCH 13/23] net: aquantia: temperature retrieval fix
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 06b0d7fe7e5ff3ba4c7e265ef41135e8bcc232bb ]

Chip temperature is a two byte word, colocated internally with cable
length data. We do all readouts from HW memory by dwords, thus
we should clear extra high bytes, otherwise temperature output
gets weird as soon as we attach a cable to the NIC.

Fixes: 8f8940118654 ("net: aquantia: add infrastructure to readout chip temperature")
Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c   | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
index da726489e3c8..7bc51f8d6f2f 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
@@ -337,7 +337,7 @@ static int aq_fw2x_get_phy_temp(struct aq_hw_s *self, int *temp)
 	/* Convert PHY temperature from 1/256 degree Celsius
 	 * to 1/1000 degree Celsius.
 	 */
-	*temp = temp_res  * 1000 / 256;
+	*temp = (temp_res & 0xFFFF) * 1000 / 256;
 
 	return 0;
 }
-- 
2.20.1


From 7f6790c91517dc9ffeed20a6e180209447439775 Mon Sep 17 00:00:00 2001
From: Igor Russkikh <Igor.Russkikh@aquantia.com>
Date: Fri, 11 Oct 2019 13:45:20 +0000
Subject: [PATCH 14/23] net: aquantia: when cleaning hw cache it should be
 toggled

[ Upstream commit ed4d81c4b3f28ccf624f11fd66f67aec5b58859c ]

>From HW specification to correctly reset HW caches (this is a required
workaround when stopping the device), register bit should actually
be toggled.

It was previosly always just set. Due to the way driver stops HW this
never actually caused any issues, but it still may, so cleaning this up.

Fixes: 7a1bb49461b1 ("net: aquantia: fix potential IOMMU fault after driver unbind")
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../aquantia/atlantic/hw_atl/hw_atl_b0.c      | 16 ++++++++++++++--
 .../aquantia/atlantic/hw_atl/hw_atl_llh.c     | 17 +++++++++++++++--
 .../aquantia/atlantic/hw_atl/hw_atl_llh.h     |  7 +++++--
 .../atlantic/hw_atl/hw_atl_llh_internal.h     | 19 +++++++++++++++++++
 4 files changed, 53 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index 30f7fc4c97ff..3459fadb7ddd 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -968,14 +968,26 @@ static int hw_atl_b0_hw_interrupt_moderation_set(struct aq_hw_s *self)
 
 static int hw_atl_b0_hw_stop(struct aq_hw_s *self)
 {
+	int err;
+	u32 val;
+
 	hw_atl_b0_hw_irq_disable(self, HW_ATL_B0_INT_MASK);
 
 	/* Invalidate Descriptor Cache to prevent writing to the cached
 	 * descriptors and to the data pointer of those descriptors
 	 */
-	hw_atl_rdm_rx_dma_desc_cache_init_set(self, 1);
+	hw_atl_rdm_rx_dma_desc_cache_init_tgl(self);
 
-	return aq_hw_err_from_flags(self);
+	err = aq_hw_err_from_flags(self);
+
+	if (err)
+		goto err_exit;
+
+	readx_poll_timeout_atomic(hw_atl_rdm_rx_dma_desc_cache_init_done_get,
+				  self, val, val == 1, 1000U, 10000U);
+
+err_exit:
+	return err;
 }
 
 static int hw_atl_b0_hw_ring_tx_stop(struct aq_hw_s *self,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
index 1149812ae463..6f340695e6bd 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
@@ -606,12 +606,25 @@ void hw_atl_rpb_rx_flow_ctl_mode_set(struct aq_hw_s *aq_hw, u32 rx_flow_ctl_mode
 			    HW_ATL_RPB_RX_FC_MODE_SHIFT, rx_flow_ctl_mode);
 }
 
-void hw_atl_rdm_rx_dma_desc_cache_init_set(struct aq_hw_s *aq_hw, u32 init)
+void hw_atl_rdm_rx_dma_desc_cache_init_tgl(struct aq_hw_s *aq_hw)
 {
+	u32 val;
+
+	val = aq_hw_read_reg_bit(aq_hw, HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_ADR,
+				 HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_MSK,
+				 HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_SHIFT);
+
 	aq_hw_write_reg_bit(aq_hw, HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_ADR,
 			    HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_MSK,
 			    HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_SHIFT,
-			    init);
+			    val ^ 1);
+}
+
+u32 hw_atl_rdm_rx_dma_desc_cache_init_done_get(struct aq_hw_s *aq_hw)
+{
+	return aq_hw_read_reg_bit(aq_hw, RDM_RX_DMA_DESC_CACHE_INIT_DONE_ADR,
+				  RDM_RX_DMA_DESC_CACHE_INIT_DONE_MSK,
+				  RDM_RX_DMA_DESC_CACHE_INIT_DONE_SHIFT);
 }
 
 void hw_atl_rpb_rx_pkt_buff_size_per_tc_set(struct aq_hw_s *aq_hw,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h
index 0c37abbabca5..c3ee278c3747 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h
@@ -313,8 +313,11 @@ void hw_atl_rpb_rx_pkt_buff_size_per_tc_set(struct aq_hw_s *aq_hw,
 					    u32 rx_pkt_buff_size_per_tc,
 					    u32 buffer);
 
-/* set rdm rx dma descriptor cache init */
-void hw_atl_rdm_rx_dma_desc_cache_init_set(struct aq_hw_s *aq_hw, u32 init);
+/* toggle rdm rx dma descriptor cache init */
+void hw_atl_rdm_rx_dma_desc_cache_init_tgl(struct aq_hw_s *aq_hw);
+
+/* get rdm rx dma descriptor cache init done */
+u32 hw_atl_rdm_rx_dma_desc_cache_init_done_get(struct aq_hw_s *aq_hw);
 
 /* set rx xoff enable (per tc) */
 void hw_atl_rpb_rx_xoff_en_per_tc_set(struct aq_hw_s *aq_hw, u32 rx_xoff_en_per_tc,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h
index c3febcdfa92e..35887ad89025 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h
@@ -318,6 +318,25 @@
 /* default value of bitfield rdm_desc_init_i */
 #define HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_DEFAULT 0x0
 
+/* rdm_desc_init_done_i bitfield definitions
+ * preprocessor definitions for the bitfield rdm_desc_init_done_i.
+ * port="pif_rdm_desc_init_done_i"
+ */
+
+/* register address for bitfield rdm_desc_init_done_i */
+#define RDM_RX_DMA_DESC_CACHE_INIT_DONE_ADR 0x00005a10
+/* bitmask for bitfield rdm_desc_init_done_i */
+#define RDM_RX_DMA_DESC_CACHE_INIT_DONE_MSK 0x00000001U
+/* inverted bitmask for bitfield rdm_desc_init_done_i */
+#define RDM_RX_DMA_DESC_CACHE_INIT_DONE_MSKN 0xfffffffe
+/* lower bit position of bitfield  rdm_desc_init_done_i */
+#define RDM_RX_DMA_DESC_CACHE_INIT_DONE_SHIFT 0U
+/* width of bitfield rdm_desc_init_done_i */
+#define RDM_RX_DMA_DESC_CACHE_INIT_DONE_WIDTH 1
+/* default value of bitfield rdm_desc_init_done_i */
+#define RDM_RX_DMA_DESC_CACHE_INIT_DONE_DEFAULT 0x0
+
+
 /* rx int_desc_wrb_en bitfield definitions
  * preprocessor definitions for the bitfield "int_desc_wrb_en".
  * port="pif_rdm_int_desc_wrb_en_i"
-- 
2.20.1


From d1bd87d5c37f0469c739bedcb7e39530d5a97b7c Mon Sep 17 00:00:00 2001
From: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Date: Fri, 11 Oct 2019 13:45:22 +0000
Subject: [PATCH 15/23] net: aquantia: do not pass lro session with invalid tcp
 checksum

[ Upstream commit d08b9a0a3ebdf71b0aabe576c7dd48e57e80e0f0 ]

Individual descriptors on LRO TCP session should be checked
for CRC errors. It was discovered that HW recalculates
L4 checksums on LRO session and does not break it up on bad L4
csum.

Thus, driver should aggregate HW LRO L4 statuses from all individual
buffers of LRO session and drop packet if one of the buffers has bad
L4 checksum.

Fixes: f38f1ee8aeb2 ("net: aquantia: check rx csum for all packets in LRO session")
Signed-off-by: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/aq_ring.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index 3901d7994ca1..76bdbe1596d6 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -313,6 +313,7 @@ int aq_ring_rx_clean(struct aq_ring_s *self,
 					break;
 
 				buff->is_error |= buff_->is_error;
+				buff->is_cso_err |= buff_->is_cso_err;
 
 			} while (!buff_->is_eop);
 
@@ -320,7 +321,7 @@ int aq_ring_rx_clean(struct aq_ring_s *self,
 				err = 0;
 				goto err_exit;
 			}
-			if (buff->is_error) {
+			if (buff->is_error || buff->is_cso_err) {
 				buff_ = buff;
 				do {
 					next_ = buff_->next,
-- 
2.20.1


From a14f7ecd6c1ea463cb60c534e7dd53cf9aa6eac7 Mon Sep 17 00:00:00 2001
From: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Date: Fri, 11 Oct 2019 13:45:23 +0000
Subject: [PATCH 16/23] net: aquantia: correctly handle macvlan and multicast
 coexistence

[ Upstream commit 9f051db566da1e8110659ab4ab188af1c2510bb4 ]

macvlan and multicast handling is now mixed up.
The explicit issue is that macvlan interface gets broken (no traffic)
after clearing MULTICAST flag on the real interface.

We now do separate logic and consider both ALLMULTI and MULTICAST
flags on the device.

Fixes: 11ba961c9161 ("net: aquantia: Fix IFF_ALLMULTI flag functionality")
Signed-off-by: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/aquantia/atlantic/aq_main.c  |  4 +--
 .../net/ethernet/aquantia/atlantic/aq_nic.c   | 32 +++++++++----------
 .../aquantia/atlantic/hw_atl/hw_atl_b0.c      |  7 ++--
 3 files changed, 21 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
index b4a0fb281e69..bb65dd39f847 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
@@ -194,9 +194,7 @@ static void aq_ndev_set_multicast_settings(struct net_device *ndev)
 {
 	struct aq_nic_s *aq_nic = netdev_priv(ndev);
 
-	aq_nic_set_packet_filter(aq_nic, ndev->flags);
-
-	aq_nic_set_multicast_list(aq_nic, ndev);
+	(void)aq_nic_set_multicast_list(aq_nic, ndev);
 }
 
 static int aq_ndo_vlan_rx_add_vid(struct net_device *ndev, __be16 proto,
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 8f66e7817811..2a18439b36fb 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -631,9 +631,12 @@ int aq_nic_set_packet_filter(struct aq_nic_s *self, unsigned int flags)
 
 int aq_nic_set_multicast_list(struct aq_nic_s *self, struct net_device *ndev)
 {
-	unsigned int packet_filter = self->packet_filter;
+	const struct aq_hw_ops *hw_ops = self->aq_hw_ops;
+	struct aq_nic_cfg_s *cfg = &self->aq_nic_cfg;
+	unsigned int packet_filter = ndev->flags;
 	struct netdev_hw_addr *ha = NULL;
 	unsigned int i = 0U;
+	int err = 0;
 
 	self->mc_list.count = 0;
 	if (netdev_uc_count(ndev) > AQ_HW_MULTICAST_ADDRESS_MAX) {
@@ -641,29 +644,26 @@ int aq_nic_set_multicast_list(struct aq_nic_s *self, struct net_device *ndev)
 	} else {
 		netdev_for_each_uc_addr(ha, ndev) {
 			ether_addr_copy(self->mc_list.ar[i++], ha->addr);
-
-			if (i >= AQ_HW_MULTICAST_ADDRESS_MAX)
-				break;
 		}
 	}
 
-	if (i + netdev_mc_count(ndev) > AQ_HW_MULTICAST_ADDRESS_MAX) {
-		packet_filter |= IFF_ALLMULTI;
-	} else {
-		netdev_for_each_mc_addr(ha, ndev) {
-			ether_addr_copy(self->mc_list.ar[i++], ha->addr);
-
-			if (i >= AQ_HW_MULTICAST_ADDRESS_MAX)
-				break;
+	cfg->is_mc_list_enabled = !!(packet_filter & IFF_MULTICAST);
+	if (cfg->is_mc_list_enabled) {
+		if (i + netdev_mc_count(ndev) > AQ_HW_MULTICAST_ADDRESS_MAX) {
+			packet_filter |= IFF_ALLMULTI;
+		} else {
+			netdev_for_each_mc_addr(ha, ndev) {
+				ether_addr_copy(self->mc_list.ar[i++],
+						ha->addr);
+			}
 		}
 	}
 
 	if (i > 0 && i <= AQ_HW_MULTICAST_ADDRESS_MAX) {
-		packet_filter |= IFF_MULTICAST;
 		self->mc_list.count = i;
-		self->aq_hw_ops->hw_multicast_list_set(self->aq_hw,
-						       self->mc_list.ar,
-						       self->mc_list.count);
+		err = hw_ops->hw_multicast_list_set(self->aq_hw,
+						    self->mc_list.ar,
+						    self->mc_list.count);
 	}
 	return aq_nic_set_packet_filter(self, packet_filter);
 }
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index 3459fadb7ddd..2ad3fa6316ce 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -818,14 +818,15 @@ static int hw_atl_b0_hw_packet_filter_set(struct aq_hw_s *self,
 				     cfg->is_vlan_force_promisc);
 
 	hw_atl_rpfl2multicast_flr_en_set(self,
-					 IS_FILTER_ENABLED(IFF_ALLMULTI), 0);
+					 IS_FILTER_ENABLED(IFF_ALLMULTI) &&
+					 IS_FILTER_ENABLED(IFF_MULTICAST), 0);
 
 	hw_atl_rpfl2_accept_all_mc_packets_set(self,
-					       IS_FILTER_ENABLED(IFF_ALLMULTI));
+					      IS_FILTER_ENABLED(IFF_ALLMULTI) &&
+					      IS_FILTER_ENABLED(IFF_MULTICAST));
 
 	hw_atl_rpfl2broadcast_en_set(self, IS_FILTER_ENABLED(IFF_BROADCAST));
 
-	cfg->is_mc_list_enabled = IS_FILTER_ENABLED(IFF_MULTICAST);
 
 	for (i = HW_ATL_B0_MAC_MIN; i < HW_ATL_B0_MAC_MAX; ++i)
 		hw_atl_rpfl2_uc_flr_en_set(self,
-- 
2.20.1


From 888a092f74837eb334c30ecbd7086eb2b6278509 Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Wed, 16 Oct 2019 15:35:06 +0200
Subject: [PATCH 17/23] net: phy: micrel: Discern KSZ8051 and KSZ8795 PHYs

[ Upstream commit 8b95599c55ed24b36cf44a4720067cfe67edbcb4 ]

The KSZ8051 PHY and the KSZ8794/KSZ8795/KSZ8765 switch share exactly the
same PHY ID. Since KSZ8051 is higher in the ksphy_driver[] list of PHYs
in the micrel PHY driver, it is used even with the KSZ87xx switch. This
is wrong, since the KSZ8051 configures registers of the PHY which are
not present on the simplified KSZ87xx switch PHYs and misconfigures
other registers of the KSZ87xx switch PHYs.

Fortunatelly, it is possible to tell apart the KSZ8051 PHY from the
KSZ87xx switch by checking the Basic Status register Bit 0, which is
read-only and indicates presence of the Extended Capability Registers.
The KSZ8051 PHY has those registers while the KSZ87xx switch does not.

This patch implements simple check for the presence of this bit for
both the KSZ8051 PHY and KSZ87xx switch, to let both use the correct
PHY driver instance.

Fixes: 9d162ed69f51 ("net: phy: micrel: add support for KSZ8795")
Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: David S. Miller <davem@davemloft.net>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: George McCollister <george.mccollister@gmail.com>
Cc: Heiner Kallweit <hkallweit1@gmail.com>
Cc: Sean Nyekjaer <sean.nyekjaer@prevas.dk>
Cc: Tristram Ha <Tristram.Ha@microchip.com>
Cc: Woojung Huh <woojung.huh@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/micrel.c | 40 ++++++++++++++++++++++++++++++++++++----
 1 file changed, 36 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 2fea5541c35a..a0444e28c6e7 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -341,6 +341,35 @@ static int ksz8041_config_aneg(struct phy_device *phydev)
 	return genphy_config_aneg(phydev);
 }
 
+static int ksz8051_ksz8795_match_phy_device(struct phy_device *phydev,
+					    const u32 ksz_phy_id)
+{
+	int ret;
+
+	if ((phydev->phy_id & MICREL_PHY_ID_MASK) != ksz_phy_id)
+		return 0;
+
+	ret = phy_read(phydev, MII_BMSR);
+	if (ret < 0)
+		return ret;
+
+	/* KSZ8051 PHY and KSZ8794/KSZ8795/KSZ8765 switch share the same
+	 * exact PHY ID. However, they can be told apart by the extended
+	 * capability registers presence. The KSZ8051 PHY has them while
+	 * the switch does not.
+	 */
+	ret &= BMSR_ERCAP;
+	if (ksz_phy_id == PHY_ID_KSZ8051)
+		return ret;
+	else
+		return !ret;
+}
+
+static int ksz8051_match_phy_device(struct phy_device *phydev)
+{
+	return ksz8051_ksz8795_match_phy_device(phydev, PHY_ID_KSZ8051);
+}
+
 static int ksz8081_config_init(struct phy_device *phydev)
 {
 	/* KSZPHY_OMSO_FACTORY_TEST is set at de-assertion of the reset line
@@ -364,6 +393,11 @@ static int ksz8061_config_init(struct phy_device *phydev)
 	return kszphy_config_init(phydev);
 }
 
+static int ksz8795_match_phy_device(struct phy_device *phydev)
+{
+	return ksz8051_ksz8795_match_phy_device(phydev, PHY_ID_KSZ8795);
+}
+
 static int ksz9021_load_values_from_of(struct phy_device *phydev,
 				       const struct device_node *of_node,
 				       u16 reg,
@@ -1017,8 +1051,6 @@ static struct phy_driver ksphy_driver[] = {
 	.suspend	= genphy_suspend,
 	.resume		= genphy_resume,
 }, {
-	.phy_id		= PHY_ID_KSZ8051,
-	.phy_id_mask	= MICREL_PHY_ID_MASK,
 	.name		= "Micrel KSZ8051",
 	/* PHY_BASIC_FEATURES */
 	.driver_data	= &ksz8051_type,
@@ -1029,6 +1061,7 @@ static struct phy_driver ksphy_driver[] = {
 	.get_sset_count = kszphy_get_sset_count,
 	.get_strings	= kszphy_get_strings,
 	.get_stats	= kszphy_get_stats,
+	.match_phy_device = ksz8051_match_phy_device,
 	.suspend	= genphy_suspend,
 	.resume		= genphy_resume,
 }, {
@@ -1141,13 +1174,12 @@ static struct phy_driver ksphy_driver[] = {
 	.suspend	= genphy_suspend,
 	.resume		= genphy_resume,
 }, {
-	.phy_id		= PHY_ID_KSZ8795,
-	.phy_id_mask	= MICREL_PHY_ID_MASK,
 	.name		= "Micrel KSZ8795",
 	/* PHY_BASIC_FEATURES */
 	.config_init	= kszphy_config_init,
 	.config_aneg	= ksz8873mll_config_aneg,
 	.read_status	= ksz8873mll_read_status,
+	.match_phy_device = ksz8795_match_phy_device,
 	.suspend	= genphy_suspend,
 	.resume		= genphy_resume,
 }, {
-- 
2.20.1


From 0af7a20043101cf03e7f6d7b9f6875b457a5ff6b Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Wed, 16 Oct 2019 15:35:07 +0200
Subject: [PATCH 18/23] net: phy: micrel: Update KSZ87xx PHY name

[ Upstream commit 1d951ba3da67bbc7a9b0e05987e09552c2060e18 ]

The KSZ8795 PHY ID is in fact used by KSZ8794/KSZ8795/KSZ8765 switches.
Update the PHY ID and name to reflect that, as this family of switches
is commonly refered to as KSZ87xx

Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: David S. Miller <davem@davemloft.net>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: George McCollister <george.mccollister@gmail.com>
Cc: Heiner Kallweit <hkallweit1@gmail.com>
Cc: Sean Nyekjaer <sean.nyekjaer@prevas.dk>
Cc: Tristram Ha <Tristram.Ha@microchip.com>
Cc: Woojung Huh <woojung.huh@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/micrel.c   | 4 ++--
 include/linux/micrel_phy.h | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index a0444e28c6e7..63dedec0433d 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -395,7 +395,7 @@ static int ksz8061_config_init(struct phy_device *phydev)
 
 static int ksz8795_match_phy_device(struct phy_device *phydev)
 {
-	return ksz8051_ksz8795_match_phy_device(phydev, PHY_ID_KSZ8795);
+	return ksz8051_ksz8795_match_phy_device(phydev, PHY_ID_KSZ87XX);
 }
 
 static int ksz9021_load_values_from_of(struct phy_device *phydev,
@@ -1174,7 +1174,7 @@ static struct phy_driver ksphy_driver[] = {
 	.suspend	= genphy_suspend,
 	.resume		= genphy_resume,
 }, {
-	.name		= "Micrel KSZ8795",
+	.name		= "Micrel KSZ87XX Switch",
 	/* PHY_BASIC_FEATURES */
 	.config_init	= kszphy_config_init,
 	.config_aneg	= ksz8873mll_config_aneg,
diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h
index ad24554f11f9..75f880c25bb8 100644
--- a/include/linux/micrel_phy.h
+++ b/include/linux/micrel_phy.h
@@ -31,7 +31,7 @@
 #define PHY_ID_KSZ886X		0x00221430
 #define PHY_ID_KSZ8863		0x00221435
 
-#define PHY_ID_KSZ8795		0x00221550
+#define PHY_ID_KSZ87XX		0x00221550
 
 #define	PHY_ID_KSZ9477		0x00221631
 
-- 
2.20.1


From 2a1fda59005eab425a725c37e4c3e01cea5a4a1f Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Sat, 12 Oct 2019 13:55:06 +0200
Subject: [PATCH 19/23] net: avoid errors when trying to pop MLPS header on
 non-MPLS packets

[ Upstream commit dedc5a08da07874c6e0d411e7f39c5c2cf137014 ]

the following script:

 # tc qdisc add dev eth0 clsact
 # tc filter add dev eth0 egress matchall action mpls pop

implicitly makes the kernel drop all packets transmitted by eth0, if they
don't have a MPLS header. This behavior is uncommon: other encapsulations
(like VLAN) just let the packet pass unmodified. Since the result of MPLS
'pop' operation would be the same regardless of the presence / absence of
MPLS header(s) in the original packet, we can let skb_mpls_pop() return 0
when dealing with non-MPLS packets.

For the OVS use-case, this is acceptable because __ovs_nla_copy_actions()
already ensures that MPLS 'pop' operation only occurs with packets having
an MPLS Ethernet type (and there are no other callers in current code, so
the semantic change should be ok).

v2: better documentation of use-cases for skb_mpls_pop(), thanks to Simon
    Horman

Fixes: 2a2ea50870ba ("net: sched: add mpls manipulation actions to TC")
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Acked-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 982d8d12830e..9e371d93965b 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5524,7 +5524,7 @@ int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto)
 	int err;
 
 	if (unlikely(!eth_p_mpls(skb->protocol)))
-		return -EINVAL;
+		return 0;
 
 	err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN);
 	if (unlikely(err))
-- 
2.20.1


From 27633b3bdaa62946799995ec77b083dbe0ddd6f9 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Sat, 12 Oct 2019 13:55:07 +0200
Subject: [PATCH 20/23] net/sched: fix corrupted L2 header with MPLS 'push' and
 'pop' actions

[ Upstream commit fa4e0f8855fcba600e0be2575ee29c69166f74bd ]

the following script:

 # tc qdisc add dev eth0 clsact
 # tc filter add dev eth0 egress protocol ip matchall \
 > action mpls push protocol mpls_uc label 0x355aa bos 1

causes corruption of all IP packets transmitted by eth0. On TC egress, we
can't rely on the value of skb->mac_len, because it's 0 and a MPLS 'push'
operation will result in an overwrite of the first 4 octets in the packet
L2 header (e.g. the Destination Address if eth0 is an Ethernet); the same
error pattern is present also in the MPLS 'pop' operation. Fix this error
in act_mpls data plane, computing 'mac_len' as the difference between the
network header and the mac header (when not at TC ingress), and use it in
MPLS 'push'/'pop' core functions.

v2: unbreak 'make htmldocs' because of missing documentation of 'mac_len'
    in skb_mpls_pop(), reported by kbuild test robot

CC: Lorenzo Bianconi <lorenzo@kernel.org>
Fixes: 2a2ea50870ba ("net: sched: add mpls manipulation actions to TC")
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Acked-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h    |  5 +++--
 net/core/skbuff.c         | 19 +++++++++++--------
 net/openvswitch/actions.c |  5 +++--
 net/sched/act_mpls.c      | 12 ++++++++----
 4 files changed, 25 insertions(+), 16 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index ba5583522d24..9b18d33681c2 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3465,8 +3465,9 @@ int skb_ensure_writable(struct sk_buff *skb, int write_len);
 int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci);
 int skb_vlan_pop(struct sk_buff *skb);
 int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci);
-int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto);
-int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto);
+int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto,
+		  int mac_len);
+int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len);
 int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse);
 int skb_mpls_dec_ttl(struct sk_buff *skb);
 struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy,
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 9e371d93965b..d4a47c44daf0 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5465,12 +5465,14 @@ static void skb_mod_eth_type(struct sk_buff *skb, struct ethhdr *hdr,
  * @skb: buffer
  * @mpls_lse: MPLS label stack entry to push
  * @mpls_proto: ethertype of the new MPLS header (expects 0x8847 or 0x8848)
+ * @mac_len: length of the MAC header
  *
  * Expects skb->data at mac header.
  *
  * Returns 0 on success, -errno otherwise.
  */
-int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto)
+int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto,
+		  int mac_len)
 {
 	struct mpls_shim_hdr *lse;
 	int err;
@@ -5487,15 +5489,15 @@ int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto)
 		return err;
 
 	if (!skb->inner_protocol) {
-		skb_set_inner_network_header(skb, skb->mac_len);
+		skb_set_inner_network_header(skb, mac_len);
 		skb_set_inner_protocol(skb, skb->protocol);
 	}
 
 	skb_push(skb, MPLS_HLEN);
 	memmove(skb_mac_header(skb) - MPLS_HLEN, skb_mac_header(skb),
-		skb->mac_len);
+		mac_len);
 	skb_reset_mac_header(skb);
-	skb_set_network_header(skb, skb->mac_len);
+	skb_set_network_header(skb, mac_len);
 
 	lse = mpls_hdr(skb);
 	lse->label_stack_entry = mpls_lse;
@@ -5514,29 +5516,30 @@ EXPORT_SYMBOL_GPL(skb_mpls_push);
  *
  * @skb: buffer
  * @next_proto: ethertype of header after popped MPLS header
+ * @mac_len: length of the MAC header
  *
  * Expects skb->data at mac header.
  *
  * Returns 0 on success, -errno otherwise.
  */
-int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto)
+int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len)
 {
 	int err;
 
 	if (unlikely(!eth_p_mpls(skb->protocol)))
 		return 0;
 
-	err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN);
+	err = skb_ensure_writable(skb, mac_len + MPLS_HLEN);
 	if (unlikely(err))
 		return err;
 
 	skb_postpull_rcsum(skb, mpls_hdr(skb), MPLS_HLEN);
 	memmove(skb_mac_header(skb) + MPLS_HLEN, skb_mac_header(skb),
-		skb->mac_len);
+		mac_len);
 
 	__skb_pull(skb, MPLS_HLEN);
 	skb_reset_mac_header(skb);
-	skb_set_network_header(skb, skb->mac_len);
+	skb_set_network_header(skb, mac_len);
 
 	if (skb->dev && skb->dev->type == ARPHRD_ETHER) {
 		struct ethhdr *hdr;
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 3572e11b6f21..1c77f520f474 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -165,7 +165,8 @@ static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key,
 {
 	int err;
 
-	err = skb_mpls_push(skb, mpls->mpls_lse, mpls->mpls_ethertype);
+	err = skb_mpls_push(skb, mpls->mpls_lse, mpls->mpls_ethertype,
+			    skb->mac_len);
 	if (err)
 		return err;
 
@@ -178,7 +179,7 @@ static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key,
 {
 	int err;
 
-	err = skb_mpls_pop(skb, ethertype);
+	err = skb_mpls_pop(skb, ethertype, skb->mac_len);
 	if (err)
 		return err;
 
diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c
index e168df0e008a..4cf6c553bb0b 100644
--- a/net/sched/act_mpls.c
+++ b/net/sched/act_mpls.c
@@ -55,7 +55,7 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a,
 	struct tcf_mpls *m = to_mpls(a);
 	struct tcf_mpls_params *p;
 	__be32 new_lse;
-	int ret;
+	int ret, mac_len;
 
 	tcf_lastuse_update(&m->tcf_tm);
 	bstats_cpu_update(this_cpu_ptr(m->common.cpu_bstats), skb);
@@ -63,8 +63,12 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a,
 	/* Ensure 'data' points at mac_header prior calling mpls manipulating
 	 * functions.
 	 */
-	if (skb_at_tc_ingress(skb))
+	if (skb_at_tc_ingress(skb)) {
 		skb_push_rcsum(skb, skb->mac_len);
+		mac_len = skb->mac_len;
+	} else {
+		mac_len = skb_network_header(skb) - skb_mac_header(skb);
+	}
 
 	ret = READ_ONCE(m->tcf_action);
 
@@ -72,12 +76,12 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a,
 
 	switch (p->tcfm_action) {
 	case TCA_MPLS_ACT_POP:
-		if (skb_mpls_pop(skb, p->tcfm_proto))
+		if (skb_mpls_pop(skb, p->tcfm_proto, mac_len))
 			goto drop;
 		break;
 	case TCA_MPLS_ACT_PUSH:
 		new_lse = tcf_mpls_get_lse(NULL, p, !eth_p_mpls(skb->protocol));
-		if (skb_mpls_push(skb, new_lse, p->tcfm_proto))
+		if (skb_mpls_push(skb, new_lse, p->tcfm_proto, mac_len))
 			goto drop;
 		break;
 	case TCA_MPLS_ACT_MODIFY:
-- 
2.20.1


From a1e2023b7636c792cb55569b7bea0f486d898035 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Fri, 11 Oct 2019 17:46:53 +0800
Subject: [PATCH 21/23] netdevsim: Fix error handling in nsim_fib_init and
 nsim_fib_exit

[ Upstream commit 33902b4a4227877896dd9368ac10f4ca0d100de5 ]

In nsim_fib_init(), if register_fib_notifier failed, nsim_fib_net_ops
should be unregistered before return.

In nsim_fib_exit(), unregister_fib_notifier should be called before
nsim_fib_net_ops be unregistered, otherwise may cause use-after-free:

BUG: KASAN: use-after-free in nsim_fib_event_nb+0x342/0x570 [netdevsim]
Read of size 8 at addr ffff8881daaf4388 by task kworker/0:3/3499

CPU: 0 PID: 3499 Comm: kworker/0:3 Not tainted 5.3.0-rc7+ #30
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014
Workqueue: ipv6_addrconf addrconf_dad_work [ipv6]
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0xa9/0x10e lib/dump_stack.c:113
 print_address_description+0x65/0x380 mm/kasan/report.c:351
 __kasan_report+0x149/0x18d mm/kasan/report.c:482
 kasan_report+0xe/0x20 mm/kasan/common.c:618
 nsim_fib_event_nb+0x342/0x570 [netdevsim]
 notifier_call_chain+0x52/0xf0 kernel/notifier.c:95
 __atomic_notifier_call_chain+0x78/0x140 kernel/notifier.c:185
 call_fib_notifiers+0x30/0x60 net/core/fib_notifier.c:30
 call_fib6_entry_notifiers+0xc1/0x100 [ipv6]
 fib6_add+0x92e/0x1b10 [ipv6]
 __ip6_ins_rt+0x40/0x60 [ipv6]
 ip6_ins_rt+0x84/0xb0 [ipv6]
 __ipv6_ifa_notify+0x4b6/0x550 [ipv6]
 ipv6_ifa_notify+0xa5/0x180 [ipv6]
 addrconf_dad_completed+0xca/0x640 [ipv6]
 addrconf_dad_work+0x296/0x960 [ipv6]
 process_one_work+0x5c0/0xc00 kernel/workqueue.c:2269
 worker_thread+0x5c/0x670 kernel/workqueue.c:2415
 kthread+0x1d7/0x200 kernel/kthread.c:255
 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:352

Allocated by task 3388:
 save_stack+0x19/0x80 mm/kasan/common.c:69
 set_track mm/kasan/common.c:77 [inline]
 __kasan_kmalloc.constprop.3+0xa0/0xd0 mm/kasan/common.c:493
 kmalloc include/linux/slab.h:557 [inline]
 kzalloc include/linux/slab.h:748 [inline]
 ops_init+0xa9/0x220 net/core/net_namespace.c:127
 __register_pernet_operations net/core/net_namespace.c:1135 [inline]
 register_pernet_operations+0x1d4/0x420 net/core/net_namespace.c:1212
 register_pernet_subsys+0x24/0x40 net/core/net_namespace.c:1253
 nsim_fib_init+0x12/0x70 [netdevsim]
 veth_get_link_ksettings+0x2b/0x50 [veth]
 do_one_initcall+0xd4/0x454 init/main.c:939
 do_init_module+0xe0/0x330 kernel/module.c:3490
 load_module+0x3c2f/0x4620 kernel/module.c:3841
 __do_sys_finit_module+0x163/0x190 kernel/module.c:3931
 do_syscall_64+0x72/0x2e0 arch/x86/entry/common.c:296
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Freed by task 3534:
 save_stack+0x19/0x80 mm/kasan/common.c:69
 set_track mm/kasan/common.c:77 [inline]
 __kasan_slab_free+0x130/0x180 mm/kasan/common.c:455
 slab_free_hook mm/slub.c:1423 [inline]
 slab_free_freelist_hook mm/slub.c:1474 [inline]
 slab_free mm/slub.c:3016 [inline]
 kfree+0xe9/0x2d0 mm/slub.c:3957
 ops_free net/core/net_namespace.c:151 [inline]
 ops_free_list.part.7+0x156/0x220 net/core/net_namespace.c:184
 ops_free_list net/core/net_namespace.c:182 [inline]
 __unregister_pernet_operations net/core/net_namespace.c:1165 [inline]
 unregister_pernet_operations+0x221/0x2a0 net/core/net_namespace.c:1224
 unregister_pernet_subsys+0x1d/0x30 net/core/net_namespace.c:1271
 nsim_fib_exit+0x11/0x20 [netdevsim]
 nsim_module_exit+0x16/0x21 [netdevsim]
 __do_sys_delete_module kernel/module.c:1015 [inline]
 __se_sys_delete_module kernel/module.c:958 [inline]
 __x64_sys_delete_module+0x244/0x330 kernel/module.c:958
 do_syscall_64+0x72/0x2e0 arch/x86/entry/common.c:296
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Reported-by: Hulk Robot <hulkci@huawei.com>
Fixes: 59c84b9fcf42 ("netdevsim: Restore per-network namespace accounting for fib entries")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/netdevsim/fib.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c
index f61d094746c0..1a251f76d09b 100644
--- a/drivers/net/netdevsim/fib.c
+++ b/drivers/net/netdevsim/fib.c
@@ -241,8 +241,8 @@ static struct pernet_operations nsim_fib_net_ops = {
 
 void nsim_fib_exit(void)
 {
-	unregister_pernet_subsys(&nsim_fib_net_ops);
 	unregister_fib_notifier(&nsim_fib_nb);
+	unregister_pernet_subsys(&nsim_fib_net_ops);
 }
 
 int nsim_fib_init(void)
@@ -258,6 +258,7 @@ int nsim_fib_init(void)
 	err = register_fib_notifier(&nsim_fib_nb, nsim_fib_dump_inconsistent);
 	if (err < 0) {
 		pr_err("Failed to register fib notifier\n");
+		unregister_pernet_subsys(&nsim_fib_net_ops);
 		goto err_out;
 	}
 
-- 
2.20.1


From 0b398850fd849738c89c3f6c5b639d71e3cdd531 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 11 Oct 2019 21:03:33 -0700
Subject: [PATCH 22/23] net: ethernet: broadcom: have drivers select DIMLIB as
 needed
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit ddc790e92b3afa4e366ffb41818cfcd19015031e ]

NET_VENDOR_BROADCOM is intended to control a kconfig menu only.
It should not have anything to do with code generation.
As such, it should not select DIMLIB for all drivers under
NET_VENDOR_BROADCOM.  Instead each driver that needs DIMLIB should
select it (being the symbols SYSTEMPORT, BNXT, and BCMGENET).

Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1907021810220.13058@ramsan.of.borg/

Fixes: 4f75da3666c0 ("linux/dim: Move implementation to .c files")
Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Uwe Kleine-König <uwe@kleine-koenig.org>
Cc: Tal Gilboa <talgi@mellanox.com>
Cc: Saeed Mahameed <saeedm@mellanox.com>
Cc: netdev@vger.kernel.org
Cc: linux-rdma@vger.kernel.org
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jakub Kicinski <jakub.kicinski@netronome.com>
Cc: Doug Ledford <dledford@redhat.com>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: Leon Romanovsky <leonro@mellanox.com>
Cc: Or Gerlitz <ogerlitz@mellanox.com>
Cc: Sagi Grimberg <sagi@grimberg.me>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/Kconfig | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index e24f5d2b6afe..53055ce5dfd6 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -8,7 +8,6 @@ config NET_VENDOR_BROADCOM
 	default y
 	depends on (SSB_POSSIBLE && HAS_DMA) || PCI || BCM63XX || \
 		   SIBYTE_SB1xxx_SOC
-	select DIMLIB
 	---help---
 	  If you have a network (Ethernet) chipset belonging to this class,
 	  say Y.
@@ -69,6 +68,7 @@ config BCMGENET
 	select FIXED_PHY
 	select BCM7XXX_PHY
 	select MDIO_BCM_UNIMAC
+	select DIMLIB
 	help
 	  This driver supports the built-in Ethernet MACs found in the
 	  Broadcom BCM7xxx Set Top Box family chipset.
@@ -188,6 +188,7 @@ config SYSTEMPORT
 	select MII
 	select PHYLIB
 	select FIXED_PHY
+	select DIMLIB
 	help
 	  This driver supports the built-in Ethernet MACs found in the
 	  Broadcom BCM7xxx Set Top Box family chipset using an internal
@@ -200,6 +201,7 @@ config BNXT
 	select LIBCRC32C
 	select NET_DEVLINK
 	select PAGE_POOL
+	select DIMLIB
 	---help---
 	  This driver supports Broadcom NetXtreme-C/E 10/25/40/50 gigabit
 	  Ethernet cards.  To compile this driver as a module, choose M here:
-- 
2.20.1


From eb9ef96cf8382e1e5f03b856d9d59a0edfa2530a Mon Sep 17 00:00:00 2001
From: Yonglong Liu <liuyonglong@huawei.com>
Date: Wed, 16 Oct 2019 10:30:39 +0800
Subject: [PATCH 23/23] net: phy: Fix "link partner" information disappear
 issue

[ Upstream commit 3de5ae54712c75cf3c517a288e0a704784ec6cf5 ]

Some drivers just call phy_ethtool_ksettings_set() to set the
links, for those phy drivers that use genphy_read_status(), if
autoneg is on, and the link is up, than execute "ethtool -s
ethx autoneg on" will cause "link partner" information disappear.

The call trace is phy_ethtool_ksettings_set()->phy_start_aneg()
->linkmode_zero(phydev->lp_advertising)->genphy_read_status(),
the link didn't change, so genphy_read_status() just return, and
phydev->lp_advertising is zero now.

This patch moves the clear operation of lp_advertising from
phy_start_aneg() to genphy_read_lpa()/genphy_c45_read_lpa(), and
if autoneg on and autoneg not complete, just clear what the
generic functions care about.

Fixes: 88d6272acaaa ("net: phy: avoid unneeded MDIO reads in genphy_read_status")
Signed-off-by: Yonglong Liu <liuyonglong@huawei.com>
Reviewed-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy-c45.c    | 2 ++
 drivers/net/phy/phy.c        | 3 ---
 drivers/net/phy/phy_device.c | 9 ++++++++-
 3 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c
index 7935593debb1..a1caeee12236 100644
--- a/drivers/net/phy/phy-c45.c
+++ b/drivers/net/phy/phy-c45.c
@@ -323,6 +323,8 @@ int genphy_c45_read_pma(struct phy_device *phydev)
 {
 	int val;
 
+	linkmode_zero(phydev->lp_advertising);
+
 	val = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_CTRL1);
 	if (val < 0)
 		return val;
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 6b0f89369b46..519ed0ccf2f3 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -561,9 +561,6 @@ int phy_start_aneg(struct phy_device *phydev)
 	if (AUTONEG_DISABLE == phydev->autoneg)
 		phy_sanitize_settings(phydev);
 
-	/* Invalidate LP advertising flags */
-	linkmode_zero(phydev->lp_advertising);
-
 	err = phy_config_aneg(phydev);
 	if (err < 0)
 		goto out_unlock;
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 27ebc2c6c2d0..d6c9350b65bf 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1823,7 +1823,14 @@ int genphy_read_status(struct phy_device *phydev)
 
 	linkmode_zero(phydev->lp_advertising);
 
-	if (phydev->autoneg == AUTONEG_ENABLE && phydev->autoneg_complete) {
+	if (phydev->autoneg == AUTONEG_ENABLE) {
+		if (!phydev->autoneg_complete) {
+			mii_stat1000_mod_linkmode_lpa_t(phydev->lp_advertising,
+							0);
+			mii_lpa_mod_linkmode_lpa_t(phydev->lp_advertising, 0);
+			return 0;
+		}
+
 		if (phydev->is_gigabit_capable) {
 			lpagb = phy_read(phydev, MII_STAT1000);
 			if (lpagb < 0)
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Thu, Oct 24, 2019 at 02:30:18PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for 4.19.x and
> 5.3.x -stable, respectively.

All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 105 bytes --]


Please queue up the following networking bug fixes for v4.19 and v5.3
stable, respectively.

Thank you!

[-- Attachment #2: net_419.mbox --]
[-- Type: Application/Octet-Stream, Size: 44509 bytes --]

From 0a2a1007902c5a7ebf0d44c2045acc09736bb57e Mon Sep 17 00:00:00 2001
From: Jay Vosburgh <jay.vosburgh@canonical.com>
Date: Fri, 1 Nov 2019 21:56:42 -0700
Subject: [PATCH 01/15] bonding: fix state transition issue in link monitoring

[ Upstream commit 1899bb325149e481de31a4f32b59ea6f24e176ea ]

Since de77ecd4ef02 ("bonding: improve link-status update in
mii-monitoring"), the bonding driver has utilized two separate variables
to indicate the next link state a particular slave should transition to.
Each is used to communicate to a different portion of the link state
change commit logic; one to the bond_miimon_commit function itself, and
another to the state transition logic.

	Unfortunately, the two variables can become unsynchronized,
resulting in incorrect link state transitions within bonding.  This can
cause slaves to become stuck in an incorrect link state until a
subsequent carrier state transition.

	The issue occurs when a special case in bond_slave_netdev_event
sets slave->link directly to BOND_LINK_FAIL.  On the next pass through
bond_miimon_inspect after the slave goes carrier up, the BOND_LINK_FAIL
case will set the proposed next state (link_new_state) to BOND_LINK_UP,
but the new_link to BOND_LINK_DOWN.  The setting of the final link state
from new_link comes after that from link_new_state, and so the slave
will end up incorrectly in _DOWN state.

	Resolve this by combining the two variables into one.

Reported-by: Aleksei Zakharov <zakharov.a.g@yandex.ru>
Reported-by: Sha Zhang <zhangsha.zhang@huawei.com>
Cc: Mahesh Bandewar <maheshb@google.com>
Fixes: de77ecd4ef02 ("bonding: improve link-status update in mii-monitoring")
Signed-off-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 41 ++++++++++++++++-----------------
 include/net/bonding.h           |  3 +--
 2 files changed, 21 insertions(+), 23 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 2804e2d1ae5e..136a972ea903 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2074,8 +2074,7 @@ static int bond_miimon_inspect(struct bonding *bond)
 	ignore_updelay = !rcu_dereference(bond->curr_active_slave);
 
 	bond_for_each_slave_rcu(bond, slave, iter) {
-		slave->new_link = BOND_LINK_NOCHANGE;
-		slave->link_new_state = slave->link;
+		bond_propose_link_state(slave, BOND_LINK_NOCHANGE);
 
 		link_state = bond_check_dev_link(bond, slave->dev, 0);
 
@@ -2111,7 +2110,7 @@ static int bond_miimon_inspect(struct bonding *bond)
 			}
 
 			if (slave->delay <= 0) {
-				slave->new_link = BOND_LINK_DOWN;
+				bond_propose_link_state(slave, BOND_LINK_DOWN);
 				commit++;
 				continue;
 			}
@@ -2150,7 +2149,7 @@ static int bond_miimon_inspect(struct bonding *bond)
 				slave->delay = 0;
 
 			if (slave->delay <= 0) {
-				slave->new_link = BOND_LINK_UP;
+				bond_propose_link_state(slave, BOND_LINK_UP);
 				commit++;
 				ignore_updelay = false;
 				continue;
@@ -2188,7 +2187,7 @@ static void bond_miimon_commit(struct bonding *bond)
 	struct slave *slave, *primary;
 
 	bond_for_each_slave(bond, slave, iter) {
-		switch (slave->new_link) {
+		switch (slave->link_new_state) {
 		case BOND_LINK_NOCHANGE:
 			/* For 802.3ad mode, check current slave speed and
 			 * duplex again in case its port was disabled after
@@ -2263,8 +2262,8 @@ static void bond_miimon_commit(struct bonding *bond)
 
 		default:
 			netdev_err(bond->dev, "invalid new link %d on slave %s\n",
-				   slave->new_link, slave->dev->name);
-			slave->new_link = BOND_LINK_NOCHANGE;
+				   slave->link_new_state, slave->dev->name);
+			bond_propose_link_state(slave, BOND_LINK_NOCHANGE);
 
 			continue;
 		}
@@ -2664,13 +2663,13 @@ static void bond_loadbalance_arp_mon(struct bonding *bond)
 	bond_for_each_slave_rcu(bond, slave, iter) {
 		unsigned long trans_start = dev_trans_start(slave->dev);
 
-		slave->new_link = BOND_LINK_NOCHANGE;
+		bond_propose_link_state(slave, BOND_LINK_NOCHANGE);
 
 		if (slave->link != BOND_LINK_UP) {
 			if (bond_time_in_interval(bond, trans_start, 1) &&
 			    bond_time_in_interval(bond, slave->last_rx, 1)) {
 
-				slave->new_link = BOND_LINK_UP;
+				bond_propose_link_state(slave, BOND_LINK_UP);
 				slave_state_changed = 1;
 
 				/* primary_slave has no meaning in round-robin
@@ -2697,7 +2696,7 @@ static void bond_loadbalance_arp_mon(struct bonding *bond)
 			if (!bond_time_in_interval(bond, trans_start, 2) ||
 			    !bond_time_in_interval(bond, slave->last_rx, 2)) {
 
-				slave->new_link = BOND_LINK_DOWN;
+				bond_propose_link_state(slave, BOND_LINK_DOWN);
 				slave_state_changed = 1;
 
 				if (slave->link_failure_count < UINT_MAX)
@@ -2729,8 +2728,8 @@ static void bond_loadbalance_arp_mon(struct bonding *bond)
 			goto re_arm;
 
 		bond_for_each_slave(bond, slave, iter) {
-			if (slave->new_link != BOND_LINK_NOCHANGE)
-				slave->link = slave->new_link;
+			if (slave->link_new_state != BOND_LINK_NOCHANGE)
+				slave->link = slave->link_new_state;
 		}
 
 		if (slave_state_changed) {
@@ -2753,9 +2752,9 @@ static void bond_loadbalance_arp_mon(struct bonding *bond)
 }
 
 /* Called to inspect slaves for active-backup mode ARP monitor link state
- * changes.  Sets new_link in slaves to specify what action should take
- * place for the slave.  Returns 0 if no changes are found, >0 if changes
- * to link states must be committed.
+ * changes.  Sets proposed link state in slaves to specify what action
+ * should take place for the slave.  Returns 0 if no changes are found, >0
+ * if changes to link states must be committed.
  *
  * Called with rcu_read_lock held.
  */
@@ -2767,12 +2766,12 @@ static int bond_ab_arp_inspect(struct bonding *bond)
 	int commit = 0;
 
 	bond_for_each_slave_rcu(bond, slave, iter) {
-		slave->new_link = BOND_LINK_NOCHANGE;
+		bond_propose_link_state(slave, BOND_LINK_NOCHANGE);
 		last_rx = slave_last_rx(bond, slave);
 
 		if (slave->link != BOND_LINK_UP) {
 			if (bond_time_in_interval(bond, last_rx, 1)) {
-				slave->new_link = BOND_LINK_UP;
+				bond_propose_link_state(slave, BOND_LINK_UP);
 				commit++;
 			}
 			continue;
@@ -2800,7 +2799,7 @@ static int bond_ab_arp_inspect(struct bonding *bond)
 		if (!bond_is_active_slave(slave) &&
 		    !rcu_access_pointer(bond->current_arp_slave) &&
 		    !bond_time_in_interval(bond, last_rx, 3)) {
-			slave->new_link = BOND_LINK_DOWN;
+			bond_propose_link_state(slave, BOND_LINK_DOWN);
 			commit++;
 		}
 
@@ -2813,7 +2812,7 @@ static int bond_ab_arp_inspect(struct bonding *bond)
 		if (bond_is_active_slave(slave) &&
 		    (!bond_time_in_interval(bond, trans_start, 2) ||
 		     !bond_time_in_interval(bond, last_rx, 2))) {
-			slave->new_link = BOND_LINK_DOWN;
+			bond_propose_link_state(slave, BOND_LINK_DOWN);
 			commit++;
 		}
 	}
@@ -2833,7 +2832,7 @@ static void bond_ab_arp_commit(struct bonding *bond)
 	struct slave *slave;
 
 	bond_for_each_slave(bond, slave, iter) {
-		switch (slave->new_link) {
+		switch (slave->link_new_state) {
 		case BOND_LINK_NOCHANGE:
 			continue;
 
@@ -2886,7 +2885,7 @@ static void bond_ab_arp_commit(struct bonding *bond)
 
 		default:
 			netdev_err(bond->dev, "impossible: new_link %d on slave %s\n",
-				   slave->new_link, slave->dev->name);
+				   slave->link_new_state, slave->dev->name);
 			continue;
 		}
 
diff --git a/include/net/bonding.h b/include/net/bonding.h
index b46d68acf701..8116648873c3 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -149,7 +149,6 @@ struct slave {
 	unsigned long target_last_arp_rx[BOND_MAX_ARP_TARGETS];
 	s8     link;		/* one of BOND_LINK_XXXX */
 	s8     link_new_state;	/* one of BOND_LINK_XXXX */
-	s8     new_link;
 	u8     backup:1,   /* indicates backup slave. Value corresponds with
 			      BOND_STATE_ACTIVE and BOND_STATE_BACKUP */
 	       inactive:1, /* indicates inactive slave */
@@ -539,7 +538,7 @@ static inline void bond_propose_link_state(struct slave *slave, int state)
 
 static inline void bond_commit_link_state(struct slave *slave, bool notify)
 {
-	if (slave->link == slave->link_new_state)
+	if (slave->link_new_state == BOND_LINK_NOCHANGE)
 		return;
 
 	slave->link = slave->link_new_state;
-- 
2.20.1


From ae12328e0a6f39aa5d8cf46fac3786095bbd61d8 Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.com>
Date: Thu, 7 Nov 2019 09:48:01 +0100
Subject: [PATCH 02/15] CDC-NCM: handle incomplete transfer of MTU

[ Upstream commit 332f989a3b0041b810836c5c3747e59aad7e9d0b ]

A malicious device may give half an answer when asked
for its MTU. The driver will proceed after this with
a garbage MTU. Anything but a complete answer must be treated
as an error.

V2: used sizeof as request by Alexander

Reported-and-tested-by: syzbot+0631d878823ce2411636@syzkaller.appspotmail.com
Signed-off-by: Oliver Neukum <oneukum@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ncm.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index f53e3e4e25f3..a57d82ef0f81 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -578,8 +578,8 @@ static void cdc_ncm_set_dgram_size(struct usbnet *dev, int new_size)
 	/* read current mtu value from device */
 	err = usbnet_read_cmd(dev, USB_CDC_GET_MAX_DATAGRAM_SIZE,
 			      USB_TYPE_CLASS | USB_DIR_IN | USB_RECIP_INTERFACE,
-			      0, iface_no, &max_datagram_size, 2);
-	if (err < 0) {
+			      0, iface_no, &max_datagram_size, sizeof(max_datagram_size));
+	if (err < sizeof(max_datagram_size)) {
 		dev_dbg(&dev->intf->dev, "GET_MAX_DATAGRAM_SIZE failed\n");
 		goto out;
 	}
@@ -590,7 +590,7 @@ static void cdc_ncm_set_dgram_size(struct usbnet *dev, int new_size)
 	max_datagram_size = cpu_to_le16(ctx->max_datagram_size);
 	err = usbnet_write_cmd(dev, USB_CDC_SET_MAX_DATAGRAM_SIZE,
 			       USB_TYPE_CLASS | USB_DIR_OUT | USB_RECIP_INTERFACE,
-			       0, iface_no, &max_datagram_size, 2);
+			       0, iface_no, &max_datagram_size, sizeof(max_datagram_size));
 	if (err < 0)
 		dev_dbg(&dev->intf->dev, "SET_MAX_DATAGRAM_SIZE failed\n");
 
-- 
2.20.1


From ec9fe7c183f520c26c50112e26414bf19195ae20 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@kernel.org>
Date: Thu, 7 Nov 2019 18:29:52 +0000
Subject: [PATCH 03/15] ipv4: Fix table id reference in fib_sync_down_addr

[ Upstream commit e0a312629fefa943534fc46f7bfbe6de3fdaf463 ]

Hendrik reported routes in the main table using source address are not
removed when the address is removed. The problem is that fib_sync_down_addr
does not account for devices in the default VRF which are associated
with the main table. Fix by updating the table id reference.

Fixes: 5a56a0b3a45d ("net: Don't delete routes in different VRFs")
Reported-by: Hendrik Donner <hd@os-cillation.de>
Signed-off-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_semantics.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 446204ca7406..a8fc4e83cd95 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1421,8 +1421,8 @@ int fib_sync_down_addr(struct net_device *dev, __be32 local)
 	int ret = 0;
 	unsigned int hash = fib_laddr_hashfn(local);
 	struct hlist_head *head = &fib_info_laddrhash[hash];
+	int tb_id = l3mdev_fib_table(dev) ? : RT_TABLE_MAIN;
 	struct net *net = dev_net(dev);
-	int tb_id = l3mdev_fib_table(dev);
 	struct fib_info *fi;
 
 	if (!fib_info_laddrhash || local == 0)
-- 
2.20.1


From 5180e6b6050ece413952a172ddadc148fced7a8b Mon Sep 17 00:00:00 2001
From: Alexander Sverdlin <alexander.sverdlin@nokia.com>
Date: Fri, 8 Nov 2019 10:00:44 +0000
Subject: [PATCH 04/15] net: ethernet: octeon_mgmt: Account for second possible
 VLAN header

[ Upstream commit e4dd5608033efe7b6030cde359bfdbaeb73bc22d ]

Octeon's input ring-buffer entry has 14 bits-wide size field, so to account
for second possible VLAN header max_mtu must be further reduced.

Fixes: 109cc16526c6d ("ethernet/cavium: use core min/max MTU checking")
Signed-off-by: Alexander Sverdlin <alexander.sverdlin@nokia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/octeon/octeon_mgmt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
index bb43ddb7539e..592fb9e847b9 100644
--- a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
+++ b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
@@ -1495,7 +1495,7 @@ static int octeon_mgmt_probe(struct platform_device *pdev)
 	netdev->ethtool_ops = &octeon_mgmt_ethtool_ops;
 
 	netdev->min_mtu = 64 - OCTEON_MGMT_RX_HEADROOM;
-	netdev->max_mtu = 16383 - OCTEON_MGMT_RX_HEADROOM;
+	netdev->max_mtu = 16383 - OCTEON_MGMT_RX_HEADROOM - VLAN_HLEN;
 
 	mac = of_get_mac_address(pdev->dev.of_node);
 
-- 
2.20.1


From 5e0890f33d81079dba5d5bff8836d94fb74ebd37 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 7 Nov 2019 20:08:19 -0800
Subject: [PATCH 05/15] net: fix data-race in neigh_event_send()

[ Upstream commit 1b53d64435d56902fc234ff2507142d971a09687 ]

KCSAN reported the following data-race [1]

The fix will also prevent the compiler from optimizing out
the condition.

[1]

BUG: KCSAN: data-race in neigh_resolve_output / neigh_resolve_output

write to 0xffff8880a41dba78 of 8 bytes by interrupt on cpu 1:
 neigh_event_send include/net/neighbour.h:443 [inline]
 neigh_resolve_output+0x78/0x480 net/core/neighbour.c:1474
 neigh_output include/net/neighbour.h:511 [inline]
 ip_finish_output2+0x4af/0xe40 net/ipv4/ip_output.c:228
 __ip_finish_output net/ipv4/ip_output.c:308 [inline]
 __ip_finish_output+0x23a/0x490 net/ipv4/ip_output.c:290
 ip_finish_output+0x41/0x160 net/ipv4/ip_output.c:318
 NF_HOOK_COND include/linux/netfilter.h:294 [inline]
 ip_output+0xdf/0x210 net/ipv4/ip_output.c:432
 dst_output include/net/dst.h:436 [inline]
 ip_local_out+0x74/0x90 net/ipv4/ip_output.c:125
 __ip_queue_xmit+0x3a8/0xa40 net/ipv4/ip_output.c:532
 ip_queue_xmit+0x45/0x60 include/net/ip.h:237
 __tcp_transmit_skb+0xe81/0x1d60 net/ipv4/tcp_output.c:1169
 tcp_transmit_skb net/ipv4/tcp_output.c:1185 [inline]
 __tcp_retransmit_skb+0x4bd/0x15f0 net/ipv4/tcp_output.c:2976
 tcp_retransmit_skb+0x36/0x1a0 net/ipv4/tcp_output.c:2999
 tcp_retransmit_timer+0x719/0x16d0 net/ipv4/tcp_timer.c:515
 tcp_write_timer_handler+0x42d/0x510 net/ipv4/tcp_timer.c:598
 tcp_write_timer+0xd1/0xf0 net/ipv4/tcp_timer.c:618

read to 0xffff8880a41dba78 of 8 bytes by interrupt on cpu 0:
 neigh_event_send include/net/neighbour.h:442 [inline]
 neigh_resolve_output+0x57/0x480 net/core/neighbour.c:1474
 neigh_output include/net/neighbour.h:511 [inline]
 ip_finish_output2+0x4af/0xe40 net/ipv4/ip_output.c:228
 __ip_finish_output net/ipv4/ip_output.c:308 [inline]
 __ip_finish_output+0x23a/0x490 net/ipv4/ip_output.c:290
 ip_finish_output+0x41/0x160 net/ipv4/ip_output.c:318
 NF_HOOK_COND include/linux/netfilter.h:294 [inline]
 ip_output+0xdf/0x210 net/ipv4/ip_output.c:432
 dst_output include/net/dst.h:436 [inline]
 ip_local_out+0x74/0x90 net/ipv4/ip_output.c:125
 __ip_queue_xmit+0x3a8/0xa40 net/ipv4/ip_output.c:532
 ip_queue_xmit+0x45/0x60 include/net/ip.h:237
 __tcp_transmit_skb+0xe81/0x1d60 net/ipv4/tcp_output.c:1169
 tcp_transmit_skb net/ipv4/tcp_output.c:1185 [inline]
 __tcp_retransmit_skb+0x4bd/0x15f0 net/ipv4/tcp_output.c:2976
 tcp_retransmit_skb+0x36/0x1a0 net/ipv4/tcp_output.c:2999
 tcp_retransmit_timer+0x719/0x16d0 net/ipv4/tcp_timer.c:515
 tcp_write_timer_handler+0x42d/0x510 net/ipv4/tcp_timer.c:598

Reported by Kernel Concurrency Sanitizer on:
CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.4.0-rc3+ #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/neighbour.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index beeeed126872..c84807c1c5bd 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -430,8 +430,8 @@ static inline int neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
 {
 	unsigned long now = jiffies;
 	
-	if (neigh->used != now)
-		neigh->used = now;
+	if (READ_ONCE(neigh->used) != now)
+		WRITE_ONCE(neigh->used, now);
 	if (!(neigh->nud_state&(NUD_CONNECTED|NUD_DELAY|NUD_PROBE)))
 		return __neigh_event_send(neigh, skb);
 	return 0;
-- 
2.20.1


From c52bd6c9dc5139043b230057d8bb662a85a04445 Mon Sep 17 00:00:00 2001
From: Sean Tranchetti <stranche@codeaurora.org>
Date: Mon, 4 Nov 2019 17:54:22 -0700
Subject: [PATCH 06/15] net: qualcomm: rmnet: Fix potential UAF when
 unregistering

[ Upstream commit e7a86c687e64ab24f88330ad24ecc9442ce40c5a ]

During the exit/unregistration process of the RmNet driver, the function
rmnet_unregister_real_device() is called to handle freeing the driver's
internal state and removing the RX handler on the underlying physical
device. However, the order of operations this function performs is wrong
and can lead to a use after free of the rmnet_port structure.

Before calling netdev_rx_handler_unregister(), this port structure is
freed with kfree(). If packets are received on any RmNet devices before
synchronize_net() completes, they will attempt to use this already-freed
port structure when processing the packet. As such, before cleaning up any
other internal state, the RX handler must be unregistered in order to
guarantee that no further packets will arrive on the device.

Fixes: ceed73a2cf4a ("drivers: net: ethernet: qualcomm: rmnet: Initial implementation")
Signed-off-by: Sean Tranchetti <stranche@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
index 5f4e447c5dce..f66d1255e36a 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
@@ -66,10 +66,10 @@ static int rmnet_unregister_real_device(struct net_device *real_dev,
 	if (port->nr_rmnet_devs)
 		return -EINVAL;
 
-	kfree(port);
-
 	netdev_rx_handler_unregister(real_dev);
 
+	kfree(port);
+
 	/* release reference on real_dev */
 	dev_put(real_dev);
 
-- 
2.20.1


From af75b230cd7988deb8964356843932f70eb8809c Mon Sep 17 00:00:00 2001
From: Aleksander Morgado <aleksander@aleksander.es>
Date: Thu, 7 Nov 2019 11:57:01 +0100
Subject: [PATCH 07/15] net: usb: qmi_wwan: add support for DW5821e with eSIM
 support

[ Upstream commit e497df686e8fed8c1dd69179010656362858edb3 ]

Exactly same layout as the default DW5821e module, just a different
vid/pid.

The QMI interface is exposed in USB configuration #1:

P:  Vendor=413c ProdID=81e0 Rev=03.18
S:  Manufacturer=Dell Inc.
S:  Product=DW5821e-eSIM Snapdragon X20 LTE
S:  SerialNumber=0123456789ABCDEF
C:  #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=500mA
I:  If#=0x0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
I:  If#=0x1 Alt= 0 #EPs= 1 Cls=03(HID  ) Sub=00 Prot=00 Driver=usbhid
I:  If#=0x2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
I:  If#=0x3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
I:  If#=0x4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
I:  If#=0x5 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option

Signed-off-by: Aleksander Morgado <aleksander@aleksander.es>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 6f517e673020..9f037c50054d 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1297,6 +1297,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x413c, 0x81b6, 8)},	/* Dell Wireless 5811e */
 	{QMI_FIXED_INTF(0x413c, 0x81b6, 10)},	/* Dell Wireless 5811e */
 	{QMI_FIXED_INTF(0x413c, 0x81d7, 0)},	/* Dell Wireless 5821e */
+	{QMI_FIXED_INTF(0x413c, 0x81e0, 0)},	/* Dell Wireless 5821e with eSIM support*/
 	{QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)},	/* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */
 	{QMI_FIXED_INTF(0x03f0, 0x9d1d, 1)},	/* HP lt4120 Snapdragon X5 LTE */
 	{QMI_FIXED_INTF(0x22de, 0x9061, 3)},	/* WeTelecom WPD-600N */
-- 
2.20.1


From afa3c983cfd65abefd611550be83f7568aca0df2 Mon Sep 17 00:00:00 2001
From: Pan Bian <bianpan2016@163.com>
Date: Tue, 5 Nov 2019 16:34:07 +0800
Subject: [PATCH 08/15] NFC: fdp: fix incorrect free object

[ Upstream commit 517ce4e93368938b204451285e53014549804868 ]

The address of fw_vsc_cfg is on stack. Releasing it with devm_kfree() is
incorrect, which may result in a system crash or other security impacts.
The expected object to free is *fw_vsc_cfg.

Signed-off-by: Pan Bian <bianpan2016@163.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/nfc/fdp/i2c.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nfc/fdp/i2c.c b/drivers/nfc/fdp/i2c.c
index d8d70dd830b0..7f143387b9ff 100644
--- a/drivers/nfc/fdp/i2c.c
+++ b/drivers/nfc/fdp/i2c.c
@@ -267,7 +267,7 @@ static void fdp_nci_i2c_read_device_properties(struct device *dev,
 						  *fw_vsc_cfg, len);
 
 		if (r) {
-			devm_kfree(dev, fw_vsc_cfg);
+			devm_kfree(dev, *fw_vsc_cfg);
 			goto vsc_read_err;
 		}
 	} else {
-- 
2.20.1


From 85fbd5eff0ab6ed3ba6611b1aed60964c4544731 Mon Sep 17 00:00:00 2001
From: Pan Bian <bianpan2016@163.com>
Date: Thu, 7 Nov 2019 14:29:50 +0800
Subject: [PATCH 09/15] nfc: netlink: fix double device reference drop

[ Upstream commit 025ec40b81d785a98f76b8bdb509ac10773b4f12 ]

The function nfc_put_device(dev) is called twice to drop the reference
to dev when there is no associated local llcp. Remove one of them to fix
the bug.

Fixes: 52feb444a903 ("NFC: Extend netlink interface for LTO, RW, and MIUX parameters support")
Fixes: d9b8d8e19b07 ("NFC: llcp: Service Name Lookup netlink interface")
Signed-off-by: Pan Bian <bianpan2016@163.com>
Reviewed-by: Johan Hovold <johan@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/nfc/netlink.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index b3662264aa24..30938854bb8d 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -1110,7 +1110,6 @@ static int nfc_genl_llc_set_params(struct sk_buff *skb, struct genl_info *info)
 
 	local = nfc_llcp_find_local(dev);
 	if (!local) {
-		nfc_put_device(dev);
 		rc = -ENODEV;
 		goto exit;
 	}
@@ -1170,7 +1169,6 @@ static int nfc_genl_llc_sdreq(struct sk_buff *skb, struct genl_info *info)
 
 	local = nfc_llcp_find_local(dev);
 	if (!local) {
-		nfc_put_device(dev);
 		rc = -ENODEV;
 		goto exit;
 	}
-- 
2.20.1


From 4a52a9c6b7903358b0be14bb946d62eaa296a28f Mon Sep 17 00:00:00 2001
From: Pan Bian <bianpan2016@163.com>
Date: Thu, 7 Nov 2019 09:33:20 +0800
Subject: [PATCH 10/15] NFC: st21nfca: fix double free

[ Upstream commit 99a8efbb6e30b72ac98cecf81103f847abffb1e5 ]

The variable nfcid_skb is not changed in the callee nfc_hci_get_param()
if error occurs. Consequently, the freed variable nfcid_skb will be
freed again, resulting in a double free bug. Set nfcid_skb to NULL after
releasing it to fix the bug.

Signed-off-by: Pan Bian <bianpan2016@163.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/nfc/st21nfca/core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/nfc/st21nfca/core.c b/drivers/nfc/st21nfca/core.c
index e803fdfa9189..f37069b53b20 100644
--- a/drivers/nfc/st21nfca/core.c
+++ b/drivers/nfc/st21nfca/core.c
@@ -719,6 +719,7 @@ static int st21nfca_hci_complete_target_discovered(struct nfc_hci_dev *hdev,
 							NFC_PROTO_FELICA_MASK;
 		} else {
 			kfree_skb(nfcid_skb);
+			nfcid_skb = NULL;
 			/* P2P in type A */
 			r = nfc_hci_get_param(hdev, ST21NFCA_RF_READER_F_GATE,
 					ST21NFCA_RF_READER_F_NFCID1,
-- 
2.20.1


From 1029ccb46048699d02f26e6d0370c9ec87a5bf83 Mon Sep 17 00:00:00 2001
From: Manish Chopra <manishc@marvell.com>
Date: Fri, 8 Nov 2019 02:42:30 -0800
Subject: [PATCH 11/15] qede: fix NULL pointer deref in __qede_remove()

[ Upstream commit deabc87111c690097c03765ea017cd500f7376fc ]

While rebooting the system with SR-IOV vfs enabled leads
to below crash due to recurrence of __qede_remove() on the VF
devices (first from .shutdown() flow of the VF itself and
another from PF's .shutdown() flow executing pci_disable_sriov())

This patch adds a safeguard in __qede_remove() flow to fix this,
so that driver doesn't attempt to remove "already removed" devices.

[  194.360134] BUG: unable to handle kernel NULL pointer dereference at 00000000000008dc
[  194.360227] IP: [<ffffffffc03553c4>] __qede_remove+0x24/0x130 [qede]
[  194.360304] PGD 0
[  194.360325] Oops: 0000 [#1] SMP
[  194.360360] Modules linked in: tcp_lp fuse tun bridge stp llc devlink bonding ip_set nfnetlink ib_isert iscsi_target_mod ib_srpt target_core_mod ib_srp scsi_transport_srp scsi_tgt ib_ipoib ib_umad rpcrdma sunrpc rdma_ucm ib_uverbs ib_iser rdma_cm iw_cm ib_cm libiscsi scsi_transport_iscsi dell_smbios iTCO_wdt iTCO_vendor_support dell_wmi_descriptor dcdbas vfat fat pcc_cpufreq skx_edac intel_powerclamp coretemp intel_rapl iosf_mbi kvm_intel kvm irqbypass crc32_pclmul ghash_clmulni_intel aesni_intel lrw gf128mul glue_helper ablk_helper cryptd qedr ib_core pcspkr ses enclosure joydev ipmi_ssif sg i2c_i801 lpc_ich mei_me mei wmi ipmi_si ipmi_devintf ipmi_msghandler tpm_crb acpi_pad acpi_power_meter xfs libcrc32c sd_mod crc_t10dif crct10dif_generic crct10dif_pclmul crct10dif_common crc32c_intel mgag200
[  194.361044]  qede i2c_algo_bit drm_kms_helper qed syscopyarea sysfillrect nvme sysimgblt fb_sys_fops ttm nvme_core mpt3sas crc8 ptp drm pps_core ahci raid_class scsi_transport_sas libahci libata drm_panel_orientation_quirks nfit libnvdimm dm_mirror dm_region_hash dm_log dm_mod [last unloaded: ip_tables]
[  194.361297] CPU: 51 PID: 7996 Comm: reboot Kdump: loaded Not tainted 3.10.0-1062.el7.x86_64 #1
[  194.361359] Hardware name: Dell Inc. PowerEdge MX840c/0740HW, BIOS 2.4.6 10/15/2019
[  194.361412] task: ffff9cea9b360000 ti: ffff9ceabebdc000 task.ti: ffff9ceabebdc000
[  194.361463] RIP: 0010:[<ffffffffc03553c4>]  [<ffffffffc03553c4>] __qede_remove+0x24/0x130 [qede]
[  194.361534] RSP: 0018:ffff9ceabebdfac0  EFLAGS: 00010282
[  194.361570] RAX: 0000000000000000 RBX: ffff9cd013846098 RCX: 0000000000000000
[  194.361621] RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff9cd013846098
[  194.361668] RBP: ffff9ceabebdfae8 R08: 0000000000000000 R09: 0000000000000000
[  194.361715] R10: 00000000bfe14201 R11: ffff9ceabfe141e0 R12: 0000000000000000
[  194.361762] R13: ffff9cd013846098 R14: 0000000000000000 R15: ffff9ceab5e48000
[  194.361810] FS:  00007f799c02d880(0000) GS:ffff9ceacb0c0000(0000) knlGS:0000000000000000
[  194.361865] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  194.361903] CR2: 00000000000008dc CR3: 0000001bdac76000 CR4: 00000000007607e0
[  194.361953] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  194.362002] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[  194.362051] PKRU: 55555554
[  194.362073] Call Trace:
[  194.362109]  [<ffffffffc0355500>] qede_remove+0x10/0x20 [qede]
[  194.362180]  [<ffffffffb97d0f3e>] pci_device_remove+0x3e/0xc0
[  194.362240]  [<ffffffffb98b3c52>] __device_release_driver+0x82/0xf0
[  194.362285]  [<ffffffffb98b3ce3>] device_release_driver+0x23/0x30
[  194.362343]  [<ffffffffb97c86d4>] pci_stop_bus_device+0x84/0xa0
[  194.362388]  [<ffffffffb97c87e2>] pci_stop_and_remove_bus_device+0x12/0x20
[  194.362450]  [<ffffffffb97f153f>] pci_iov_remove_virtfn+0xaf/0x160
[  194.362496]  [<ffffffffb97f1aec>] sriov_disable+0x3c/0xf0
[  194.362534]  [<ffffffffb97f1bc3>] pci_disable_sriov+0x23/0x30
[  194.362599]  [<ffffffffc02f83c3>] qed_sriov_disable+0x5e3/0x650 [qed]
[  194.362658]  [<ffffffffb9622df6>] ? kfree+0x106/0x140
[  194.362709]  [<ffffffffc02cc0c0>] ? qed_free_stream_mem+0x70/0x90 [qed]
[  194.362754]  [<ffffffffb9622df6>] ? kfree+0x106/0x140
[  194.362803]  [<ffffffffc02cd659>] qed_slowpath_stop+0x1a9/0x1d0 [qed]
[  194.362854]  [<ffffffffc035544e>] __qede_remove+0xae/0x130 [qede]
[  194.362904]  [<ffffffffc03554e0>] qede_shutdown+0x10/0x20 [qede]
[  194.362956]  [<ffffffffb97cf90a>] pci_device_shutdown+0x3a/0x60
[  194.363010]  [<ffffffffb98b180b>] device_shutdown+0xfb/0x1f0
[  194.363066]  [<ffffffffb94b66c6>] kernel_restart_prepare+0x36/0x40
[  194.363107]  [<ffffffffb94b66e2>] kernel_restart+0x12/0x60
[  194.363146]  [<ffffffffb94b6959>] SYSC_reboot+0x229/0x260
[  194.363196]  [<ffffffffb95f200d>] ? handle_mm_fault+0x39d/0x9b0
[  194.363253]  [<ffffffffb942b621>] ? __switch_to+0x151/0x580
[  194.363304]  [<ffffffffb9b7ec28>] ? __schedule+0x448/0x9c0
[  194.363343]  [<ffffffffb94b69fe>] SyS_reboot+0xe/0x10
[  194.363387]  [<ffffffffb9b8bede>] system_call_fastpath+0x25/0x2a
[  194.363430] Code: f9 e9 37 ff ff ff 90 0f 1f 44 00 00 55 48 89 e5 41 57 41 56 41 55 4c 8d af 98 00 00 00 41 54 4c 89 ef 41 89 f4 53 e8 4c e4 55 f9 <80> b8 dc 08 00 00 01 48 89 c3 4c 8d b8 c0 08 00 00 4c 8b b0 c0
[  194.363712] RIP  [<ffffffffc03553c4>] __qede_remove+0x24/0x130 [qede]
[  194.363764]  RSP <ffff9ceabebdfac0>
[  194.363791] CR2: 00000000000008dc

Signed-off-by: Manish Chopra <manishc@marvell.com>
Signed-off-by: Ariel Elior <aelior@marvell.com>
Signed-off-by: Sudarsana Kalluru <skalluru@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qede/qede_main.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index f3d9c40c4115..630b13a9c3d5 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -1170,8 +1170,16 @@ enum qede_remove_mode {
 static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode)
 {
 	struct net_device *ndev = pci_get_drvdata(pdev);
-	struct qede_dev *edev = netdev_priv(ndev);
-	struct qed_dev *cdev = edev->cdev;
+	struct qede_dev *edev;
+	struct qed_dev *cdev;
+
+	if (!ndev) {
+		dev_info(&pdev->dev, "Device has already been removed\n");
+		return;
+	}
+
+	edev = netdev_priv(ndev);
+	cdev = edev->cdev;
 
 	DP_INFO(edev, "Starting qede_remove\n");
 
-- 
2.20.1


From 7b42f664ed106aeb93aa416f2339daf87ccfa112 Mon Sep 17 00:00:00 2001
From: Claudiu Manoil <claudiu.manoil@nxp.com>
Date: Tue, 5 Nov 2019 23:50:13 +0200
Subject: [PATCH 12/15] net: mscc: ocelot: don't handle netdev events for other
 netdevs

[ Upstream commit 7afb3e575e5aa9f5a200a3eb3f45d8130f6d6601 ]

The check that the event is actually for this device should be moved
from the "port" handler to the net device handler.

Otherwise the port handler will deny bonding configuration for other
net devices in the same system (like enetc in the LS1028A) that don't
have the lag_upper_info->tx_type restriction that ocelot has.

Fixes: dc96ee3730fc ("net: mscc: ocelot: add bonding support")
Signed-off-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 732ba21d3369..ad09db4ce68e 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -1506,9 +1506,6 @@ static int ocelot_netdevice_port_event(struct net_device *dev,
 	struct ocelot_port *ocelot_port = netdev_priv(dev);
 	int err = 0;
 
-	if (!ocelot_netdevice_dev_check(dev))
-		return 0;
-
 	switch (event) {
 	case NETDEV_CHANGEUPPER:
 		if (netif_is_bridge_master(info->upper_dev)) {
@@ -1545,6 +1542,9 @@ static int ocelot_netdevice_event(struct notifier_block *unused,
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	int ret = 0;
 
+	if (!ocelot_netdevice_dev_check(dev))
+		return 0;
+
 	if (event == NETDEV_PRECHANGEUPPER &&
 	    netif_is_lag_master(info->upper_dev)) {
 		struct netdev_lag_upper_info *lag_upper_info = info->upper_info;
-- 
2.20.1


From ec8bae6d86800fe0f31a45c061cb15c4c7bddfcc Mon Sep 17 00:00:00 2001
From: Claudiu Manoil <claudiu.manoil@nxp.com>
Date: Tue, 5 Nov 2019 23:50:14 +0200
Subject: [PATCH 13/15] net: mscc: ocelot: fix NULL pointer on LAG slave
 removal

[ Upstream commit 3b3eed8eec47259939ee6c3d58aea1c311ddee3b ]

lag_upper_info may be NULL on slave removal.

Fixes: dc96ee3730fc ("net: mscc: ocelot: add bonding support")
Signed-off-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index ad09db4ce68e..e05a59ae9a59 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -1550,7 +1550,8 @@ static int ocelot_netdevice_event(struct notifier_block *unused,
 		struct netdev_lag_upper_info *lag_upper_info = info->upper_info;
 		struct netlink_ext_ack *extack;
 
-		if (lag_upper_info->tx_type != NETDEV_LAG_TX_TYPE_HASH) {
+		if (lag_upper_info &&
+		    lag_upper_info->tx_type != NETDEV_LAG_TX_TYPE_HASH) {
 			extack = netdev_notifier_info_to_extack(&info->info);
 			NL_SET_ERR_MSG_MOD(extack, "LAG device using unsupported Tx type");
 
-- 
2.20.1


From 845864f416440ad1416b0f4ee593147a2ef79360 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 7 Nov 2019 09:26:19 -0800
Subject: [PATCH 14/15] ipv6: fixes rt6_probe() and fib6_nh->last_probe init

[ Upstream commit 1bef4c223b8588cf50433bdc2c6953d82949b3b3 ]

While looking at a syzbot KCSAN report [1], I found multiple
issues in this code :

1) fib6_nh->last_probe has an initial value of 0.

   While probably okay on 64bit kernels, this causes an issue
   on 32bit kernels since the time_after(jiffies, 0 + interval)
   might be false ~24 days after boot (for HZ=1000)

2) The data-race found by KCSAN
   I could use READ_ONCE() and WRITE_ONCE(), but we also can
   take the opportunity of not piling-up too many rt6_probe_deferred()
   works by using instead cmpxchg() so that only one cpu wins the race.

[1]
BUG: KCSAN: data-race in find_match / find_match

write to 0xffff8880bb7aabe8 of 8 bytes by interrupt on cpu 1:
 rt6_probe net/ipv6/route.c:663 [inline]
 find_match net/ipv6/route.c:757 [inline]
 find_match+0x5bd/0x790 net/ipv6/route.c:733
 __find_rr_leaf+0xe3/0x780 net/ipv6/route.c:831
 find_rr_leaf net/ipv6/route.c:852 [inline]
 rt6_select net/ipv6/route.c:896 [inline]
 fib6_table_lookup+0x383/0x650 net/ipv6/route.c:2164
 ip6_pol_route+0xee/0x5c0 net/ipv6/route.c:2200
 ip6_pol_route_output+0x48/0x60 net/ipv6/route.c:2452
 fib6_rule_lookup+0x3d6/0x470 net/ipv6/fib6_rules.c:117
 ip6_route_output_flags_noref+0x16b/0x230 net/ipv6/route.c:2484
 ip6_route_output_flags+0x50/0x1a0 net/ipv6/route.c:2497
 ip6_dst_lookup_tail+0x25d/0xc30 net/ipv6/ip6_output.c:1049
 ip6_dst_lookup_flow+0x68/0x120 net/ipv6/ip6_output.c:1150
 inet6_csk_route_socket+0x2f7/0x420 net/ipv6/inet6_connection_sock.c:106
 inet6_csk_xmit+0x91/0x1f0 net/ipv6/inet6_connection_sock.c:121
 __tcp_transmit_skb+0xe81/0x1d60 net/ipv4/tcp_output.c:1169
 tcp_transmit_skb net/ipv4/tcp_output.c:1185 [inline]
 tcp_xmit_probe_skb+0x19b/0x1d0 net/ipv4/tcp_output.c:3735

read to 0xffff8880bb7aabe8 of 8 bytes by interrupt on cpu 0:
 rt6_probe net/ipv6/route.c:657 [inline]
 find_match net/ipv6/route.c:757 [inline]
 find_match+0x521/0x790 net/ipv6/route.c:733
 __find_rr_leaf+0xe3/0x780 net/ipv6/route.c:831
 find_rr_leaf net/ipv6/route.c:852 [inline]
 rt6_select net/ipv6/route.c:896 [inline]
 fib6_table_lookup+0x383/0x650 net/ipv6/route.c:2164
 ip6_pol_route+0xee/0x5c0 net/ipv6/route.c:2200
 ip6_pol_route_output+0x48/0x60 net/ipv6/route.c:2452
 fib6_rule_lookup+0x3d6/0x470 net/ipv6/fib6_rules.c:117
 ip6_route_output_flags_noref+0x16b/0x230 net/ipv6/route.c:2484
 ip6_route_output_flags+0x50/0x1a0 net/ipv6/route.c:2497
 ip6_dst_lookup_tail+0x25d/0xc30 net/ipv6/ip6_output.c:1049
 ip6_dst_lookup_flow+0x68/0x120 net/ipv6/ip6_output.c:1150
 inet6_csk_route_socket+0x2f7/0x420 net/ipv6/inet6_connection_sock.c:106
 inet6_csk_xmit+0x91/0x1f0 net/ipv6/inet6_connection_sock.c:121
 __tcp_transmit_skb+0xe81/0x1d60 net/ipv4/tcp_output.c:1169

Reported by Kernel Concurrency Sanitizer on:
CPU: 0 PID: 18894 Comm: udevd Not tainted 5.4.0-rc3+ #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011

Fixes: cc3a86c802f0 ("ipv6: Change rt6_probe to take a fib6_nh")
Fixes: f547fac624be ("ipv6: rate-limit probes for neighbourless routes")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index c88586380134..076c21f6a645 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -521,6 +521,7 @@ static void rt6_probe(struct fib6_info *rt)
 {
 	struct __rt6_probe_work *work = NULL;
 	const struct in6_addr *nh_gw;
+	unsigned long last_probe;
 	struct neighbour *neigh;
 	struct net_device *dev;
 	struct inet6_dev *idev;
@@ -539,6 +540,7 @@ static void rt6_probe(struct fib6_info *rt)
 	nh_gw = &rt->fib6_nh.nh_gw;
 	dev = rt->fib6_nh.nh_dev;
 	rcu_read_lock_bh();
+	last_probe = READ_ONCE(rt->last_probe);
 	idev = __in6_dev_get(dev);
 	neigh = __ipv6_neigh_lookup_noref(dev, nh_gw);
 	if (neigh) {
@@ -554,13 +556,15 @@ static void rt6_probe(struct fib6_info *rt)
 				__neigh_set_probe_once(neigh);
 		}
 		write_unlock(&neigh->lock);
-	} else if (time_after(jiffies, rt->last_probe +
+	} else if (time_after(jiffies, last_probe +
 				       idev->cnf.rtr_probe_interval)) {
 		work = kmalloc(sizeof(*work), GFP_ATOMIC);
 	}
 
-	if (work) {
-		rt->last_probe = jiffies;
+	if (!work || cmpxchg(&rt->last_probe,
+			     last_probe, jiffies) != last_probe) {
+		kfree(work);
+	} else {
 		INIT_WORK(&work->work, rt6_probe_deferred);
 		work->target = *nh_gw;
 		dev_hold(dev);
@@ -3066,6 +3070,9 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 	if (!rt)
 		goto out;
 
+#ifdef CONFIG_IPV6_ROUTER_PREF
+	rt->last_probe = jiffies;
+#endif
 	if (cfg->fc_flags & RTF_ADDRCONF)
 		rt->dst_nocount = true;
 
-- 
2.20.1


From 5eeecb03f529107cd1ca658cd88f2928d51b4ffd Mon Sep 17 00:00:00 2001
From: Salil Mehta <salil.mehta@huawei.com>
Date: Thu, 7 Nov 2019 17:09:53 +0000
Subject: [PATCH 15/15] net: hns: Fix the stray netpoll locks causing deadlock
 in NAPI path

[ Upstream commit bf5a6b4c474c589244dc25ee1af2c3c829228ef8 ]

This patch fixes the problem of the spin locks, originally
meant for the netpoll path of hns driver, causing deadlock in
the normal NAPI poll path. The issue happened due to the presence
of the stray leftover spin lock code related to the netpoll,
whose support was earlier removed from the HNS[1], got activated
due to enabling of NET_POLL_CONTROLLER switch.

Earlier background:
The netpoll handling code originally had this bug(as identified
by Marc Zyngier[2]) of wrong spin lock API being used which did
not disable the interrupts and hence could cause locking issues.
i.e. if the lock were first acquired in context to thread like
'ip' util and this lock if ever got later acquired again in
context to the interrupt context like TX/RX (Interrupts could
always pre-empt the lock holding task and acquire the lock again)
and hence could cause deadlock.

Proposed Solution:
1. If the netpoll was enabled in the HNS driver, which is not
   right now, we could have simply used spin_[un]lock_irqsave()
2. But as netpoll is disabled, therefore, it is best to get rid
   of the existing locks and stray code for now. This should
   solve the problem reported by Marc.

[1] https://git.kernel.org/torvalds/c/4bd2c03be7
[2] https://patchwork.ozlabs.org/patch/1189139/

Fixes: 4bd2c03be707 ("net: hns: remove ndo_poll_controller")
Cc: lipeng <lipeng321@huawei.com>
Cc: Yisen Zhuang <yisen.zhuang@huawei.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: David S. Miller <davem@davemloft.net>
Reported-by: Marc Zyngier <maz@kernel.org>
Acked-by: Marc Zyngier <maz@kernel.org>
Tested-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns/hnae.c     |  1 -
 drivers/net/ethernet/hisilicon/hns/hnae.h     |  3 ---
 drivers/net/ethernet/hisilicon/hns/hns_enet.c | 22 +------------------
 3 files changed, 1 insertion(+), 25 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c
index c7fa97a7e1f4..b758b3e79337 100644
--- a/drivers/net/ethernet/hisilicon/hns/hnae.c
+++ b/drivers/net/ethernet/hisilicon/hns/hnae.c
@@ -203,7 +203,6 @@ hnae_init_ring(struct hnae_queue *q, struct hnae_ring *ring, int flags)
 
 	ring->q = q;
 	ring->flags = flags;
-	spin_lock_init(&ring->lock);
 	ring->coal_param = q->handle->coal_param;
 	assert(!ring->desc && !ring->desc_cb && !ring->desc_dma_addr);
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.h b/drivers/net/ethernet/hisilicon/hns/hnae.h
index 08a750fb60c4..c8cbbe5d5549 100644
--- a/drivers/net/ethernet/hisilicon/hns/hnae.h
+++ b/drivers/net/ethernet/hisilicon/hns/hnae.h
@@ -278,9 +278,6 @@ struct hnae_ring {
 	/* statistic */
 	struct ring_stats stats;
 
-	/* ring lock for poll one */
-	spinlock_t lock;
-
 	dma_addr_t desc_dma_addr;
 	u32 buf_size;       /* size for hnae_desc->addr, preset by AE */
 	u16 desc_num;       /* total number of desc */
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index 1c70f9aa0aa7..7f8cf809e02b 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -947,15 +947,6 @@ static int is_valid_clean_head(struct hnae_ring *ring, int h)
 	return u > c ? (h > c && h <= u) : (h > c || h <= u);
 }
 
-/* netif_tx_lock will turn down the performance, set only when necessary */
-#ifdef CONFIG_NET_POLL_CONTROLLER
-#define NETIF_TX_LOCK(ring) spin_lock(&(ring)->lock)
-#define NETIF_TX_UNLOCK(ring) spin_unlock(&(ring)->lock)
-#else
-#define NETIF_TX_LOCK(ring)
-#define NETIF_TX_UNLOCK(ring)
-#endif
-
 /* reclaim all desc in one budget
  * return error or number of desc left
  */
@@ -969,21 +960,16 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data,
 	int head;
 	int bytes, pkts;
 
-	NETIF_TX_LOCK(ring);
-
 	head = readl_relaxed(ring->io_base + RCB_REG_HEAD);
 	rmb(); /* make sure head is ready before touch any data */
 
-	if (is_ring_empty(ring) || head == ring->next_to_clean) {
-		NETIF_TX_UNLOCK(ring);
+	if (is_ring_empty(ring) || head == ring->next_to_clean)
 		return 0; /* no data to poll */
-	}
 
 	if (!is_valid_clean_head(ring, head)) {
 		netdev_err(ndev, "wrong head (%d, %d-%d)\n", head,
 			   ring->next_to_use, ring->next_to_clean);
 		ring->stats.io_err_cnt++;
-		NETIF_TX_UNLOCK(ring);
 		return -EIO;
 	}
 
@@ -998,8 +984,6 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data,
 	ring->stats.tx_pkts += pkts;
 	ring->stats.tx_bytes += bytes;
 
-	NETIF_TX_UNLOCK(ring);
-
 	dev_queue = netdev_get_tx_queue(ndev, ring_data->queue_index);
 	netdev_tx_completed_queue(dev_queue, pkts, bytes);
 
@@ -1059,16 +1043,12 @@ static void hns_nic_tx_clr_all_bufs(struct hns_nic_ring_data *ring_data)
 	int head;
 	int bytes, pkts;
 
-	NETIF_TX_LOCK(ring);
-
 	head = ring->next_to_use; /* ntu :soft setted ring position*/
 	bytes = 0;
 	pkts = 0;
 	while (head != ring->next_to_clean)
 		hns_nic_reclaim_one_desc(ring, &bytes, &pkts);
 
-	NETIF_TX_UNLOCK(ring);
-
 	dev_queue = netdev_get_tx_queue(ndev, ring_data->queue_index);
 	netdev_tx_reset_queue(dev_queue);
 }
-- 
2.20.1


[-- Attachment #3: net_53.mbox --]
[-- Type: Application/Octet-Stream, Size: 75743 bytes --]

From f2b2c60f7aa5379a39fbf217dc24e0a4d549c44b Mon Sep 17 00:00:00 2001
From: Jay Vosburgh <jay.vosburgh@canonical.com>
Date: Fri, 1 Nov 2019 21:56:42 -0700
Subject: [PATCH 01/24] bonding: fix state transition issue in link monitoring

[ Upstream commit 1899bb325149e481de31a4f32b59ea6f24e176ea ]

Since de77ecd4ef02 ("bonding: improve link-status update in
mii-monitoring"), the bonding driver has utilized two separate variables
to indicate the next link state a particular slave should transition to.
Each is used to communicate to a different portion of the link state
change commit logic; one to the bond_miimon_commit function itself, and
another to the state transition logic.

	Unfortunately, the two variables can become unsynchronized,
resulting in incorrect link state transitions within bonding.  This can
cause slaves to become stuck in an incorrect link state until a
subsequent carrier state transition.

	The issue occurs when a special case in bond_slave_netdev_event
sets slave->link directly to BOND_LINK_FAIL.  On the next pass through
bond_miimon_inspect after the slave goes carrier up, the BOND_LINK_FAIL
case will set the proposed next state (link_new_state) to BOND_LINK_UP,
but the new_link to BOND_LINK_DOWN.  The setting of the final link state
from new_link comes after that from link_new_state, and so the slave
will end up incorrectly in _DOWN state.

	Resolve this by combining the two variables into one.

Reported-by: Aleksei Zakharov <zakharov.a.g@yandex.ru>
Reported-by: Sha Zhang <zhangsha.zhang@huawei.com>
Cc: Mahesh Bandewar <maheshb@google.com>
Fixes: de77ecd4ef02 ("bonding: improve link-status update in mii-monitoring")
Signed-off-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 44 ++++++++++++++++-----------------
 include/net/bonding.h           |  3 +--
 2 files changed, 23 insertions(+), 24 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 21d8fcc83c9c..4edb69b1d126 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2086,8 +2086,7 @@ static int bond_miimon_inspect(struct bonding *bond)
 	ignore_updelay = !rcu_dereference(bond->curr_active_slave);
 
 	bond_for_each_slave_rcu(bond, slave, iter) {
-		slave->new_link = BOND_LINK_NOCHANGE;
-		slave->link_new_state = slave->link;
+		bond_propose_link_state(slave, BOND_LINK_NOCHANGE);
 
 		link_state = bond_check_dev_link(bond, slave->dev, 0);
 
@@ -2121,7 +2120,7 @@ static int bond_miimon_inspect(struct bonding *bond)
 			}
 
 			if (slave->delay <= 0) {
-				slave->new_link = BOND_LINK_DOWN;
+				bond_propose_link_state(slave, BOND_LINK_DOWN);
 				commit++;
 				continue;
 			}
@@ -2158,7 +2157,7 @@ static int bond_miimon_inspect(struct bonding *bond)
 				slave->delay = 0;
 
 			if (slave->delay <= 0) {
-				slave->new_link = BOND_LINK_UP;
+				bond_propose_link_state(slave, BOND_LINK_UP);
 				commit++;
 				ignore_updelay = false;
 				continue;
@@ -2196,7 +2195,7 @@ static void bond_miimon_commit(struct bonding *bond)
 	struct slave *slave, *primary;
 
 	bond_for_each_slave(bond, slave, iter) {
-		switch (slave->new_link) {
+		switch (slave->link_new_state) {
 		case BOND_LINK_NOCHANGE:
 			/* For 802.3ad mode, check current slave speed and
 			 * duplex again in case its port was disabled after
@@ -2268,8 +2267,8 @@ static void bond_miimon_commit(struct bonding *bond)
 
 		default:
 			slave_err(bond->dev, slave->dev, "invalid new link %d on slave\n",
-				  slave->new_link);
-			slave->new_link = BOND_LINK_NOCHANGE;
+				  slave->link_new_state);
+			bond_propose_link_state(slave, BOND_LINK_NOCHANGE);
 
 			continue;
 		}
@@ -2677,13 +2676,13 @@ static void bond_loadbalance_arp_mon(struct bonding *bond)
 	bond_for_each_slave_rcu(bond, slave, iter) {
 		unsigned long trans_start = dev_trans_start(slave->dev);
 
-		slave->new_link = BOND_LINK_NOCHANGE;
+		bond_propose_link_state(slave, BOND_LINK_NOCHANGE);
 
 		if (slave->link != BOND_LINK_UP) {
 			if (bond_time_in_interval(bond, trans_start, 1) &&
 			    bond_time_in_interval(bond, slave->last_rx, 1)) {
 
-				slave->new_link = BOND_LINK_UP;
+				bond_propose_link_state(slave, BOND_LINK_UP);
 				slave_state_changed = 1;
 
 				/* primary_slave has no meaning in round-robin
@@ -2708,7 +2707,7 @@ static void bond_loadbalance_arp_mon(struct bonding *bond)
 			if (!bond_time_in_interval(bond, trans_start, 2) ||
 			    !bond_time_in_interval(bond, slave->last_rx, 2)) {
 
-				slave->new_link = BOND_LINK_DOWN;
+				bond_propose_link_state(slave, BOND_LINK_DOWN);
 				slave_state_changed = 1;
 
 				if (slave->link_failure_count < UINT_MAX)
@@ -2739,8 +2738,8 @@ static void bond_loadbalance_arp_mon(struct bonding *bond)
 			goto re_arm;
 
 		bond_for_each_slave(bond, slave, iter) {
-			if (slave->new_link != BOND_LINK_NOCHANGE)
-				slave->link = slave->new_link;
+			if (slave->link_new_state != BOND_LINK_NOCHANGE)
+				slave->link = slave->link_new_state;
 		}
 
 		if (slave_state_changed) {
@@ -2763,9 +2762,9 @@ static void bond_loadbalance_arp_mon(struct bonding *bond)
 }
 
 /* Called to inspect slaves for active-backup mode ARP monitor link state
- * changes.  Sets new_link in slaves to specify what action should take
- * place for the slave.  Returns 0 if no changes are found, >0 if changes
- * to link states must be committed.
+ * changes.  Sets proposed link state in slaves to specify what action
+ * should take place for the slave.  Returns 0 if no changes are found, >0
+ * if changes to link states must be committed.
  *
  * Called with rcu_read_lock held.
  */
@@ -2777,12 +2776,12 @@ static int bond_ab_arp_inspect(struct bonding *bond)
 	int commit = 0;
 
 	bond_for_each_slave_rcu(bond, slave, iter) {
-		slave->new_link = BOND_LINK_NOCHANGE;
+		bond_propose_link_state(slave, BOND_LINK_NOCHANGE);
 		last_rx = slave_last_rx(bond, slave);
 
 		if (slave->link != BOND_LINK_UP) {
 			if (bond_time_in_interval(bond, last_rx, 1)) {
-				slave->new_link = BOND_LINK_UP;
+				bond_propose_link_state(slave, BOND_LINK_UP);
 				commit++;
 			}
 			continue;
@@ -2810,7 +2809,7 @@ static int bond_ab_arp_inspect(struct bonding *bond)
 		if (!bond_is_active_slave(slave) &&
 		    !rcu_access_pointer(bond->current_arp_slave) &&
 		    !bond_time_in_interval(bond, last_rx, 3)) {
-			slave->new_link = BOND_LINK_DOWN;
+			bond_propose_link_state(slave, BOND_LINK_DOWN);
 			commit++;
 		}
 
@@ -2823,7 +2822,7 @@ static int bond_ab_arp_inspect(struct bonding *bond)
 		if (bond_is_active_slave(slave) &&
 		    (!bond_time_in_interval(bond, trans_start, 2) ||
 		     !bond_time_in_interval(bond, last_rx, 2))) {
-			slave->new_link = BOND_LINK_DOWN;
+			bond_propose_link_state(slave, BOND_LINK_DOWN);
 			commit++;
 		}
 	}
@@ -2843,7 +2842,7 @@ static void bond_ab_arp_commit(struct bonding *bond)
 	struct slave *slave;
 
 	bond_for_each_slave(bond, slave, iter) {
-		switch (slave->new_link) {
+		switch (slave->link_new_state) {
 		case BOND_LINK_NOCHANGE:
 			continue;
 
@@ -2893,8 +2892,9 @@ static void bond_ab_arp_commit(struct bonding *bond)
 			continue;
 
 		default:
-			slave_err(bond->dev, slave->dev, "impossible: new_link %d on slave\n",
-				  slave->new_link);
+			slave_err(bond->dev, slave->dev,
+				  "impossible: link_new_state %d on slave\n",
+				  slave->link_new_state);
 			continue;
 		}
 
diff --git a/include/net/bonding.h b/include/net/bonding.h
index f7fe45689142..d416af72404b 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -159,7 +159,6 @@ struct slave {
 	unsigned long target_last_arp_rx[BOND_MAX_ARP_TARGETS];
 	s8     link;		/* one of BOND_LINK_XXXX */
 	s8     link_new_state;	/* one of BOND_LINK_XXXX */
-	s8     new_link;
 	u8     backup:1,   /* indicates backup slave. Value corresponds with
 			      BOND_STATE_ACTIVE and BOND_STATE_BACKUP */
 	       inactive:1, /* indicates inactive slave */
@@ -549,7 +548,7 @@ static inline void bond_propose_link_state(struct slave *slave, int state)
 
 static inline void bond_commit_link_state(struct slave *slave, bool notify)
 {
-	if (slave->link == slave->link_new_state)
+	if (slave->link_new_state == BOND_LINK_NOCHANGE)
 		return;
 
 	slave->link = slave->link_new_state;
-- 
2.20.1


From be2e6b21fc4382f8f3f0238ed07a4c10e591e032 Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.com>
Date: Thu, 7 Nov 2019 09:48:01 +0100
Subject: [PATCH 02/24] CDC-NCM: handle incomplete transfer of MTU

[ Upstream commit 332f989a3b0041b810836c5c3747e59aad7e9d0b ]

A malicious device may give half an answer when asked
for its MTU. The driver will proceed after this with
a garbage MTU. Anything but a complete answer must be treated
as an error.

V2: used sizeof as request by Alexander

Reported-and-tested-by: syzbot+0631d878823ce2411636@syzkaller.appspotmail.com
Signed-off-by: Oliver Neukum <oneukum@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ncm.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 00cab3f43a4c..a245597a3902 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -578,8 +578,8 @@ static void cdc_ncm_set_dgram_size(struct usbnet *dev, int new_size)
 	/* read current mtu value from device */
 	err = usbnet_read_cmd(dev, USB_CDC_GET_MAX_DATAGRAM_SIZE,
 			      USB_TYPE_CLASS | USB_DIR_IN | USB_RECIP_INTERFACE,
-			      0, iface_no, &max_datagram_size, 2);
-	if (err < 0) {
+			      0, iface_no, &max_datagram_size, sizeof(max_datagram_size));
+	if (err < sizeof(max_datagram_size)) {
 		dev_dbg(&dev->intf->dev, "GET_MAX_DATAGRAM_SIZE failed\n");
 		goto out;
 	}
@@ -590,7 +590,7 @@ static void cdc_ncm_set_dgram_size(struct usbnet *dev, int new_size)
 	max_datagram_size = cpu_to_le16(ctx->max_datagram_size);
 	err = usbnet_write_cmd(dev, USB_CDC_SET_MAX_DATAGRAM_SIZE,
 			       USB_TYPE_CLASS | USB_DIR_OUT | USB_RECIP_INTERFACE,
-			       0, iface_no, &max_datagram_size, 2);
+			       0, iface_no, &max_datagram_size, sizeof(max_datagram_size));
 	if (err < 0)
 		dev_dbg(&dev->intf->dev, "SET_MAX_DATAGRAM_SIZE failed\n");
 
-- 
2.20.1


From a43cb2026ccc06053b1160d3db9e0b9ce04a4d94 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@kernel.org>
Date: Thu, 7 Nov 2019 18:29:52 +0000
Subject: [PATCH 03/24] ipv4: Fix table id reference in fib_sync_down_addr

[ Upstream commit e0a312629fefa943534fc46f7bfbe6de3fdaf463 ]

Hendrik reported routes in the main table using source address are not
removed when the address is removed. The problem is that fib_sync_down_addr
does not account for devices in the default VRF which are associated
with the main table. Fix by updating the table id reference.

Fixes: 5a56a0b3a45d ("net: Don't delete routes in different VRFs")
Reported-by: Hendrik Donner <hd@os-cillation.de>
Signed-off-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_semantics.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 0913a090b2bf..f1888c683426 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1814,8 +1814,8 @@ int fib_sync_down_addr(struct net_device *dev, __be32 local)
 	int ret = 0;
 	unsigned int hash = fib_laddr_hashfn(local);
 	struct hlist_head *head = &fib_info_laddrhash[hash];
+	int tb_id = l3mdev_fib_table(dev) ? : RT_TABLE_MAIN;
 	struct net *net = dev_net(dev);
-	int tb_id = l3mdev_fib_table(dev);
 	struct fib_info *fi;
 
 	if (!fib_info_laddrhash || local == 0)
-- 
2.20.1


From 57a348a7d41ea9e1276c6dfe75ce82ebda7f57d8 Mon Sep 17 00:00:00 2001
From: Alexander Sverdlin <alexander.sverdlin@nokia.com>
Date: Fri, 8 Nov 2019 10:00:44 +0000
Subject: [PATCH 04/24] net: ethernet: octeon_mgmt: Account for second possible
 VLAN header

[ Upstream commit e4dd5608033efe7b6030cde359bfdbaeb73bc22d ]

Octeon's input ring-buffer entry has 14 bits-wide size field, so to account
for second possible VLAN header max_mtu must be further reduced.

Fixes: 109cc16526c6d ("ethernet/cavium: use core min/max MTU checking")
Signed-off-by: Alexander Sverdlin <alexander.sverdlin@nokia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/octeon/octeon_mgmt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
index 0e5de88fd6e8..cdd7e5da4a74 100644
--- a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
+++ b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
@@ -1499,7 +1499,7 @@ static int octeon_mgmt_probe(struct platform_device *pdev)
 	netdev->ethtool_ops = &octeon_mgmt_ethtool_ops;
 
 	netdev->min_mtu = 64 - OCTEON_MGMT_RX_HEADROOM;
-	netdev->max_mtu = 16383 - OCTEON_MGMT_RX_HEADROOM;
+	netdev->max_mtu = 16383 - OCTEON_MGMT_RX_HEADROOM - VLAN_HLEN;
 
 	mac = of_get_mac_address(pdev->dev.of_node);
 
-- 
2.20.1


From b69a010526cddbafad58dc09ff6c51b807caea62 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 7 Nov 2019 20:08:19 -0800
Subject: [PATCH 05/24] net: fix data-race in neigh_event_send()

[ Upstream commit 1b53d64435d56902fc234ff2507142d971a09687 ]

KCSAN reported the following data-race [1]

The fix will also prevent the compiler from optimizing out
the condition.

[1]

BUG: KCSAN: data-race in neigh_resolve_output / neigh_resolve_output

write to 0xffff8880a41dba78 of 8 bytes by interrupt on cpu 1:
 neigh_event_send include/net/neighbour.h:443 [inline]
 neigh_resolve_output+0x78/0x480 net/core/neighbour.c:1474
 neigh_output include/net/neighbour.h:511 [inline]
 ip_finish_output2+0x4af/0xe40 net/ipv4/ip_output.c:228
 __ip_finish_output net/ipv4/ip_output.c:308 [inline]
 __ip_finish_output+0x23a/0x490 net/ipv4/ip_output.c:290
 ip_finish_output+0x41/0x160 net/ipv4/ip_output.c:318
 NF_HOOK_COND include/linux/netfilter.h:294 [inline]
 ip_output+0xdf/0x210 net/ipv4/ip_output.c:432
 dst_output include/net/dst.h:436 [inline]
 ip_local_out+0x74/0x90 net/ipv4/ip_output.c:125
 __ip_queue_xmit+0x3a8/0xa40 net/ipv4/ip_output.c:532
 ip_queue_xmit+0x45/0x60 include/net/ip.h:237
 __tcp_transmit_skb+0xe81/0x1d60 net/ipv4/tcp_output.c:1169
 tcp_transmit_skb net/ipv4/tcp_output.c:1185 [inline]
 __tcp_retransmit_skb+0x4bd/0x15f0 net/ipv4/tcp_output.c:2976
 tcp_retransmit_skb+0x36/0x1a0 net/ipv4/tcp_output.c:2999
 tcp_retransmit_timer+0x719/0x16d0 net/ipv4/tcp_timer.c:515
 tcp_write_timer_handler+0x42d/0x510 net/ipv4/tcp_timer.c:598
 tcp_write_timer+0xd1/0xf0 net/ipv4/tcp_timer.c:618

read to 0xffff8880a41dba78 of 8 bytes by interrupt on cpu 0:
 neigh_event_send include/net/neighbour.h:442 [inline]
 neigh_resolve_output+0x57/0x480 net/core/neighbour.c:1474
 neigh_output include/net/neighbour.h:511 [inline]
 ip_finish_output2+0x4af/0xe40 net/ipv4/ip_output.c:228
 __ip_finish_output net/ipv4/ip_output.c:308 [inline]
 __ip_finish_output+0x23a/0x490 net/ipv4/ip_output.c:290
 ip_finish_output+0x41/0x160 net/ipv4/ip_output.c:318
 NF_HOOK_COND include/linux/netfilter.h:294 [inline]
 ip_output+0xdf/0x210 net/ipv4/ip_output.c:432
 dst_output include/net/dst.h:436 [inline]
 ip_local_out+0x74/0x90 net/ipv4/ip_output.c:125
 __ip_queue_xmit+0x3a8/0xa40 net/ipv4/ip_output.c:532
 ip_queue_xmit+0x45/0x60 include/net/ip.h:237
 __tcp_transmit_skb+0xe81/0x1d60 net/ipv4/tcp_output.c:1169
 tcp_transmit_skb net/ipv4/tcp_output.c:1185 [inline]
 __tcp_retransmit_skb+0x4bd/0x15f0 net/ipv4/tcp_output.c:2976
 tcp_retransmit_skb+0x36/0x1a0 net/ipv4/tcp_output.c:2999
 tcp_retransmit_timer+0x719/0x16d0 net/ipv4/tcp_timer.c:515
 tcp_write_timer_handler+0x42d/0x510 net/ipv4/tcp_timer.c:598

Reported by Kernel Concurrency Sanitizer on:
CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.4.0-rc3+ #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/neighbour.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 50a67bd6a434..b8452cc0e059 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -439,8 +439,8 @@ static inline int neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
 {
 	unsigned long now = jiffies;
 	
-	if (neigh->used != now)
-		neigh->used = now;
+	if (READ_ONCE(neigh->used) != now)
+		WRITE_ONCE(neigh->used, now);
 	if (!(neigh->nud_state&(NUD_CONNECTED|NUD_DELAY|NUD_PROBE)))
 		return __neigh_event_send(neigh, skb);
 	return 0;
-- 
2.20.1


From ba04d9de4db217c0ea1bd6913091a7f21a2eb918 Mon Sep 17 00:00:00 2001
From: Sean Tranchetti <stranche@codeaurora.org>
Date: Mon, 4 Nov 2019 17:54:22 -0700
Subject: [PATCH 06/24] net: qualcomm: rmnet: Fix potential UAF when
 unregistering

[ Upstream commit e7a86c687e64ab24f88330ad24ecc9442ce40c5a ]

During the exit/unregistration process of the RmNet driver, the function
rmnet_unregister_real_device() is called to handle freeing the driver's
internal state and removing the RX handler on the underlying physical
device. However, the order of operations this function performs is wrong
and can lead to a use after free of the rmnet_port structure.

Before calling netdev_rx_handler_unregister(), this port structure is
freed with kfree(). If packets are received on any RmNet devices before
synchronize_net() completes, they will attempt to use this already-freed
port structure when processing the packet. As such, before cleaning up any
other internal state, the RX handler must be unregistered in order to
guarantee that no further packets will arrive on the device.

Fixes: ceed73a2cf4a ("drivers: net: ethernet: qualcomm: rmnet: Initial implementation")
Signed-off-by: Sean Tranchetti <stranche@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
index 9c54b715228e..06de59521fc4 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
@@ -57,10 +57,10 @@ static int rmnet_unregister_real_device(struct net_device *real_dev,
 	if (port->nr_rmnet_devs)
 		return -EINVAL;
 
-	kfree(port);
-
 	netdev_rx_handler_unregister(real_dev);
 
+	kfree(port);
+
 	/* release reference on real_dev */
 	dev_put(real_dev);
 
-- 
2.20.1


From 0e07630a7c137752dc3ee495b5572b4ac8e01b91 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 4 Nov 2019 15:36:57 -0800
Subject: [PATCH 07/24] net/tls: fix sk_msg trim on fallback to copy mode

[ Upstream commit 683916f6a84023407761d843048f1aea486b2612 ]

sk_msg_trim() tries to only update curr pointer if it falls into
the trimmed region. The logic, however, does not take into the
account pointer wrapping that sk_msg_iter_var_prev() does nor
(as John points out) the fact that msg->sg is a ring buffer.

This means that when the message was trimmed completely, the new
curr pointer would have the value of MAX_MSG_FRAGS - 1, which is
neither smaller than any other value, nor would it actually be
correct.

Special case the trimming to 0 length a little bit and rework
the comparison between curr and end to take into account wrapping.

This bug caused the TLS code to not copy all of the message, if
zero copy filled in fewer sg entries than memcopy would need.

Big thanks to Alexander Potapenko for the non-KMSAN reproducer.

v2:
 - take into account that msg->sg is a ring buffer (John).

Link: https://lore.kernel.org/netdev/20191030160542.30295-1-jakub.kicinski@netronome.com/ (v1)

Fixes: d829e9c4112b ("tls: convert to generic sk_msg interface")
Reported-by: syzbot+f8495bff23a879a6d0bd@syzkaller.appspotmail.com
Reported-by: syzbot+6f50c99e8f6194bf363f@syzkaller.appspotmail.com
Co-developed-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skmsg.h |  9 ++++++---
 net/core/skmsg.c      | 20 +++++++++++++++-----
 2 files changed, 21 insertions(+), 8 deletions(-)

diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index e4b3fb4bb77c..ce7055259877 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -139,6 +139,11 @@ static inline void sk_msg_apply_bytes(struct sk_psock *psock, u32 bytes)
 	}
 }
 
+static inline u32 sk_msg_iter_dist(u32 start, u32 end)
+{
+	return end >= start ? end - start : end + (MAX_MSG_FRAGS - start);
+}
+
 #define sk_msg_iter_var_prev(var)			\
 	do {						\
 		if (var == 0)				\
@@ -198,9 +203,7 @@ static inline u32 sk_msg_elem_used(const struct sk_msg *msg)
 	if (sk_msg_full(msg))
 		return MAX_MSG_FRAGS;
 
-	return msg->sg.end >= msg->sg.start ?
-		msg->sg.end - msg->sg.start :
-		msg->sg.end + (MAX_MSG_FRAGS - msg->sg.start);
+	return sk_msg_iter_dist(msg->sg.start, msg->sg.end);
 }
 
 static inline struct scatterlist *sk_msg_elem(struct sk_msg *msg, int which)
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 6832eeb4b785..c10e3e56006e 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -271,18 +271,28 @@ void sk_msg_trim(struct sock *sk, struct sk_msg *msg, int len)
 
 	msg->sg.data[i].length -= trim;
 	sk_mem_uncharge(sk, trim);
+	/* Adjust copybreak if it falls into the trimmed part of last buf */
+	if (msg->sg.curr == i && msg->sg.copybreak > msg->sg.data[i].length)
+		msg->sg.copybreak = msg->sg.data[i].length;
 out:
-	/* If we trim data before curr pointer update copybreak and current
-	 * so that any future copy operations start at new copy location.
+	sk_msg_iter_var_next(i);
+	msg->sg.end = i;
+
+	/* If we trim data a full sg elem before curr pointer update
+	 * copybreak and current so that any future copy operations
+	 * start at new copy location.
 	 * However trimed data that has not yet been used in a copy op
 	 * does not require an update.
 	 */
-	if (msg->sg.curr >= i) {
+	if (!msg->sg.size) {
+		msg->sg.curr = msg->sg.start;
+		msg->sg.copybreak = 0;
+	} else if (sk_msg_iter_dist(msg->sg.start, msg->sg.curr) >=
+		   sk_msg_iter_dist(msg->sg.start, msg->sg.end)) {
+		sk_msg_iter_var_prev(i);
 		msg->sg.curr = i;
 		msg->sg.copybreak = msg->sg.data[i].length;
 	}
-	sk_msg_iter_var_next(i);
-	msg->sg.end = i;
 }
 EXPORT_SYMBOL_GPL(sk_msg_trim);
 
-- 
2.20.1


From 6953191c1b61f15896049032f5d33d020e0cbdd3 Mon Sep 17 00:00:00 2001
From: Aleksander Morgado <aleksander@aleksander.es>
Date: Thu, 7 Nov 2019 11:57:01 +0100
Subject: [PATCH 08/24] net: usb: qmi_wwan: add support for DW5821e with eSIM
 support

[ Upstream commit e497df686e8fed8c1dd69179010656362858edb3 ]

Exactly same layout as the default DW5821e module, just a different
vid/pid.

The QMI interface is exposed in USB configuration #1:

P:  Vendor=413c ProdID=81e0 Rev=03.18
S:  Manufacturer=Dell Inc.
S:  Product=DW5821e-eSIM Snapdragon X20 LTE
S:  SerialNumber=0123456789ABCDEF
C:  #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=500mA
I:  If#=0x0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
I:  If#=0x1 Alt= 0 #EPs= 1 Cls=03(HID  ) Sub=00 Prot=00 Driver=usbhid
I:  If#=0x2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
I:  If#=0x3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
I:  If#=0x4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
I:  If#=0x5 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option

Signed-off-by: Aleksander Morgado <aleksander@aleksander.es>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 3d77cd402ba9..ba682bba7851 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1361,6 +1361,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x413c, 0x81b6, 8)},	/* Dell Wireless 5811e */
 	{QMI_FIXED_INTF(0x413c, 0x81b6, 10)},	/* Dell Wireless 5811e */
 	{QMI_FIXED_INTF(0x413c, 0x81d7, 0)},	/* Dell Wireless 5821e */
+	{QMI_FIXED_INTF(0x413c, 0x81e0, 0)},	/* Dell Wireless 5821e with eSIM support*/
 	{QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)},	/* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */
 	{QMI_FIXED_INTF(0x03f0, 0x9d1d, 1)},	/* HP lt4120 Snapdragon X5 LTE */
 	{QMI_FIXED_INTF(0x22de, 0x9061, 3)},	/* WeTelecom WPD-600N */
-- 
2.20.1


From 3c8092a30290d0c59e976b542e7b50c0baff39df Mon Sep 17 00:00:00 2001
From: Pan Bian <bianpan2016@163.com>
Date: Tue, 5 Nov 2019 16:34:07 +0800
Subject: [PATCH 09/24] NFC: fdp: fix incorrect free object

[ Upstream commit 517ce4e93368938b204451285e53014549804868 ]

The address of fw_vsc_cfg is on stack. Releasing it with devm_kfree() is
incorrect, which may result in a system crash or other security impacts.
The expected object to free is *fw_vsc_cfg.

Signed-off-by: Pan Bian <bianpan2016@163.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/nfc/fdp/i2c.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nfc/fdp/i2c.c b/drivers/nfc/fdp/i2c.c
index 1cd113c8d7cb..ad0abb1f0bae 100644
--- a/drivers/nfc/fdp/i2c.c
+++ b/drivers/nfc/fdp/i2c.c
@@ -259,7 +259,7 @@ static void fdp_nci_i2c_read_device_properties(struct device *dev,
 						  *fw_vsc_cfg, len);
 
 		if (r) {
-			devm_kfree(dev, fw_vsc_cfg);
+			devm_kfree(dev, *fw_vsc_cfg);
 			goto vsc_read_err;
 		}
 	} else {
-- 
2.20.1


From 37764ee0b915d0da28e61263bfac1e7c1183f0e3 Mon Sep 17 00:00:00 2001
From: Pan Bian <bianpan2016@163.com>
Date: Thu, 7 Nov 2019 14:29:50 +0800
Subject: [PATCH 10/24] nfc: netlink: fix double device reference drop

[ Upstream commit 025ec40b81d785a98f76b8bdb509ac10773b4f12 ]

The function nfc_put_device(dev) is called twice to drop the reference
to dev when there is no associated local llcp. Remove one of them to fix
the bug.

Fixes: 52feb444a903 ("NFC: Extend netlink interface for LTO, RW, and MIUX parameters support")
Fixes: d9b8d8e19b07 ("NFC: llcp: Service Name Lookup netlink interface")
Signed-off-by: Pan Bian <bianpan2016@163.com>
Reviewed-by: Johan Hovold <johan@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/nfc/netlink.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index 17e6ca62f1be..afde0d763039 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -1099,7 +1099,6 @@ static int nfc_genl_llc_set_params(struct sk_buff *skb, struct genl_info *info)
 
 	local = nfc_llcp_find_local(dev);
 	if (!local) {
-		nfc_put_device(dev);
 		rc = -ENODEV;
 		goto exit;
 	}
@@ -1159,7 +1158,6 @@ static int nfc_genl_llc_sdreq(struct sk_buff *skb, struct genl_info *info)
 
 	local = nfc_llcp_find_local(dev);
 	if (!local) {
-		nfc_put_device(dev);
 		rc = -ENODEV;
 		goto exit;
 	}
-- 
2.20.1


From d73bfcdea2af839299a1c1e1bc83fc6976ec72e4 Mon Sep 17 00:00:00 2001
From: Pan Bian <bianpan2016@163.com>
Date: Thu, 7 Nov 2019 09:33:20 +0800
Subject: [PATCH 11/24] NFC: st21nfca: fix double free

[ Upstream commit 99a8efbb6e30b72ac98cecf81103f847abffb1e5 ]

The variable nfcid_skb is not changed in the callee nfc_hci_get_param()
if error occurs. Consequently, the freed variable nfcid_skb will be
freed again, resulting in a double free bug. Set nfcid_skb to NULL after
releasing it to fix the bug.

Signed-off-by: Pan Bian <bianpan2016@163.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/nfc/st21nfca/core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/nfc/st21nfca/core.c b/drivers/nfc/st21nfca/core.c
index f9ac176cf257..2ce17932a073 100644
--- a/drivers/nfc/st21nfca/core.c
+++ b/drivers/nfc/st21nfca/core.c
@@ -708,6 +708,7 @@ static int st21nfca_hci_complete_target_discovered(struct nfc_hci_dev *hdev,
 							NFC_PROTO_FELICA_MASK;
 		} else {
 			kfree_skb(nfcid_skb);
+			nfcid_skb = NULL;
 			/* P2P in type A */
 			r = nfc_hci_get_param(hdev, ST21NFCA_RF_READER_F_GATE,
 					ST21NFCA_RF_READER_F_NFCID1,
-- 
2.20.1


From 35ea24e545a02502022f62304cf7999b76726bc9 Mon Sep 17 00:00:00 2001
From: Manish Chopra <manishc@marvell.com>
Date: Fri, 8 Nov 2019 02:42:30 -0800
Subject: [PATCH 12/24] qede: fix NULL pointer deref in __qede_remove()

[ Upstream commit deabc87111c690097c03765ea017cd500f7376fc ]

While rebooting the system with SR-IOV vfs enabled leads
to below crash due to recurrence of __qede_remove() on the VF
devices (first from .shutdown() flow of the VF itself and
another from PF's .shutdown() flow executing pci_disable_sriov())

This patch adds a safeguard in __qede_remove() flow to fix this,
so that driver doesn't attempt to remove "already removed" devices.

[  194.360134] BUG: unable to handle kernel NULL pointer dereference at 00000000000008dc
[  194.360227] IP: [<ffffffffc03553c4>] __qede_remove+0x24/0x130 [qede]
[  194.360304] PGD 0
[  194.360325] Oops: 0000 [#1] SMP
[  194.360360] Modules linked in: tcp_lp fuse tun bridge stp llc devlink bonding ip_set nfnetlink ib_isert iscsi_target_mod ib_srpt target_core_mod ib_srp scsi_transport_srp scsi_tgt ib_ipoib ib_umad rpcrdma sunrpc rdma_ucm ib_uverbs ib_iser rdma_cm iw_cm ib_cm libiscsi scsi_transport_iscsi dell_smbios iTCO_wdt iTCO_vendor_support dell_wmi_descriptor dcdbas vfat fat pcc_cpufreq skx_edac intel_powerclamp coretemp intel_rapl iosf_mbi kvm_intel kvm irqbypass crc32_pclmul ghash_clmulni_intel aesni_intel lrw gf128mul glue_helper ablk_helper cryptd qedr ib_core pcspkr ses enclosure joydev ipmi_ssif sg i2c_i801 lpc_ich mei_me mei wmi ipmi_si ipmi_devintf ipmi_msghandler tpm_crb acpi_pad acpi_power_meter xfs libcrc32c sd_mod crc_t10dif crct10dif_generic crct10dif_pclmul crct10dif_common crc32c_intel mgag200
[  194.361044]  qede i2c_algo_bit drm_kms_helper qed syscopyarea sysfillrect nvme sysimgblt fb_sys_fops ttm nvme_core mpt3sas crc8 ptp drm pps_core ahci raid_class scsi_transport_sas libahci libata drm_panel_orientation_quirks nfit libnvdimm dm_mirror dm_region_hash dm_log dm_mod [last unloaded: ip_tables]
[  194.361297] CPU: 51 PID: 7996 Comm: reboot Kdump: loaded Not tainted 3.10.0-1062.el7.x86_64 #1
[  194.361359] Hardware name: Dell Inc. PowerEdge MX840c/0740HW, BIOS 2.4.6 10/15/2019
[  194.361412] task: ffff9cea9b360000 ti: ffff9ceabebdc000 task.ti: ffff9ceabebdc000
[  194.361463] RIP: 0010:[<ffffffffc03553c4>]  [<ffffffffc03553c4>] __qede_remove+0x24/0x130 [qede]
[  194.361534] RSP: 0018:ffff9ceabebdfac0  EFLAGS: 00010282
[  194.361570] RAX: 0000000000000000 RBX: ffff9cd013846098 RCX: 0000000000000000
[  194.361621] RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff9cd013846098
[  194.361668] RBP: ffff9ceabebdfae8 R08: 0000000000000000 R09: 0000000000000000
[  194.361715] R10: 00000000bfe14201 R11: ffff9ceabfe141e0 R12: 0000000000000000
[  194.361762] R13: ffff9cd013846098 R14: 0000000000000000 R15: ffff9ceab5e48000
[  194.361810] FS:  00007f799c02d880(0000) GS:ffff9ceacb0c0000(0000) knlGS:0000000000000000
[  194.361865] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  194.361903] CR2: 00000000000008dc CR3: 0000001bdac76000 CR4: 00000000007607e0
[  194.361953] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  194.362002] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[  194.362051] PKRU: 55555554
[  194.362073] Call Trace:
[  194.362109]  [<ffffffffc0355500>] qede_remove+0x10/0x20 [qede]
[  194.362180]  [<ffffffffb97d0f3e>] pci_device_remove+0x3e/0xc0
[  194.362240]  [<ffffffffb98b3c52>] __device_release_driver+0x82/0xf0
[  194.362285]  [<ffffffffb98b3ce3>] device_release_driver+0x23/0x30
[  194.362343]  [<ffffffffb97c86d4>] pci_stop_bus_device+0x84/0xa0
[  194.362388]  [<ffffffffb97c87e2>] pci_stop_and_remove_bus_device+0x12/0x20
[  194.362450]  [<ffffffffb97f153f>] pci_iov_remove_virtfn+0xaf/0x160
[  194.362496]  [<ffffffffb97f1aec>] sriov_disable+0x3c/0xf0
[  194.362534]  [<ffffffffb97f1bc3>] pci_disable_sriov+0x23/0x30
[  194.362599]  [<ffffffffc02f83c3>] qed_sriov_disable+0x5e3/0x650 [qed]
[  194.362658]  [<ffffffffb9622df6>] ? kfree+0x106/0x140
[  194.362709]  [<ffffffffc02cc0c0>] ? qed_free_stream_mem+0x70/0x90 [qed]
[  194.362754]  [<ffffffffb9622df6>] ? kfree+0x106/0x140
[  194.362803]  [<ffffffffc02cd659>] qed_slowpath_stop+0x1a9/0x1d0 [qed]
[  194.362854]  [<ffffffffc035544e>] __qede_remove+0xae/0x130 [qede]
[  194.362904]  [<ffffffffc03554e0>] qede_shutdown+0x10/0x20 [qede]
[  194.362956]  [<ffffffffb97cf90a>] pci_device_shutdown+0x3a/0x60
[  194.363010]  [<ffffffffb98b180b>] device_shutdown+0xfb/0x1f0
[  194.363066]  [<ffffffffb94b66c6>] kernel_restart_prepare+0x36/0x40
[  194.363107]  [<ffffffffb94b66e2>] kernel_restart+0x12/0x60
[  194.363146]  [<ffffffffb94b6959>] SYSC_reboot+0x229/0x260
[  194.363196]  [<ffffffffb95f200d>] ? handle_mm_fault+0x39d/0x9b0
[  194.363253]  [<ffffffffb942b621>] ? __switch_to+0x151/0x580
[  194.363304]  [<ffffffffb9b7ec28>] ? __schedule+0x448/0x9c0
[  194.363343]  [<ffffffffb94b69fe>] SyS_reboot+0xe/0x10
[  194.363387]  [<ffffffffb9b8bede>] system_call_fastpath+0x25/0x2a
[  194.363430] Code: f9 e9 37 ff ff ff 90 0f 1f 44 00 00 55 48 89 e5 41 57 41 56 41 55 4c 8d af 98 00 00 00 41 54 4c 89 ef 41 89 f4 53 e8 4c e4 55 f9 <80> b8 dc 08 00 00 01 48 89 c3 4c 8d b8 c0 08 00 00 4c 8b b0 c0
[  194.363712] RIP  [<ffffffffc03553c4>] __qede_remove+0x24/0x130 [qede]
[  194.363764]  RSP <ffff9ceabebdfac0>
[  194.363791] CR2: 00000000000008dc

Signed-off-by: Manish Chopra <manishc@marvell.com>
Signed-off-by: Ariel Elior <aelior@marvell.com>
Signed-off-by: Sudarsana Kalluru <skalluru@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qede/qede_main.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 8d1c208f778f..a220cc7c947a 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -1208,8 +1208,16 @@ enum qede_remove_mode {
 static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode)
 {
 	struct net_device *ndev = pci_get_drvdata(pdev);
-	struct qede_dev *edev = netdev_priv(ndev);
-	struct qed_dev *cdev = edev->cdev;
+	struct qede_dev *edev;
+	struct qed_dev *cdev;
+
+	if (!ndev) {
+		dev_info(&pdev->dev, "Device has already been removed\n");
+		return;
+	}
+
+	edev = netdev_priv(ndev);
+	cdev = edev->cdev;
 
 	DP_INFO(edev, "Starting qede_remove\n");
 
-- 
2.20.1


From 765a89443a12ca878e7f93ad4d12acb4589dcc46 Mon Sep 17 00:00:00 2001
From: Claudiu Manoil <claudiu.manoil@nxp.com>
Date: Tue, 5 Nov 2019 23:50:13 +0200
Subject: [PATCH 13/24] net: mscc: ocelot: don't handle netdev events for other
 netdevs

[ Upstream commit 7afb3e575e5aa9f5a200a3eb3f45d8130f6d6601 ]

The check that the event is actually for this device should be moved
from the "port" handler to the net device handler.

Otherwise the port handler will deny bonding configuration for other
net devices in the same system (like enetc in the LS1028A) that don't
have the lag_upper_info->tx_type restriction that ocelot has.

Fixes: dc96ee3730fc ("net: mscc: ocelot: add bonding support")
Signed-off-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 6932e615d4b0..f50724650388 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -1499,9 +1499,6 @@ static int ocelot_netdevice_port_event(struct net_device *dev,
 	struct ocelot_port *ocelot_port = netdev_priv(dev);
 	int err = 0;
 
-	if (!ocelot_netdevice_dev_check(dev))
-		return 0;
-
 	switch (event) {
 	case NETDEV_CHANGEUPPER:
 		if (netif_is_bridge_master(info->upper_dev)) {
@@ -1538,6 +1535,9 @@ static int ocelot_netdevice_event(struct notifier_block *unused,
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	int ret = 0;
 
+	if (!ocelot_netdevice_dev_check(dev))
+		return 0;
+
 	if (event == NETDEV_PRECHANGEUPPER &&
 	    netif_is_lag_master(info->upper_dev)) {
 		struct netdev_lag_upper_info *lag_upper_info = info->upper_info;
-- 
2.20.1


From 6e3ba44df17f577b8daa2443cfdc60e455034bb7 Mon Sep 17 00:00:00 2001
From: Claudiu Manoil <claudiu.manoil@nxp.com>
Date: Tue, 5 Nov 2019 23:50:14 +0200
Subject: [PATCH 14/24] net: mscc: ocelot: fix NULL pointer on LAG slave
 removal

[ Upstream commit 3b3eed8eec47259939ee6c3d58aea1c311ddee3b ]

lag_upper_info may be NULL on slave removal.

Fixes: dc96ee3730fc ("net: mscc: ocelot: add bonding support")
Signed-off-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index f50724650388..dc78940f08fb 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -1543,7 +1543,8 @@ static int ocelot_netdevice_event(struct notifier_block *unused,
 		struct netdev_lag_upper_info *lag_upper_info = info->upper_info;
 		struct netlink_ext_ack *extack;
 
-		if (lag_upper_info->tx_type != NETDEV_LAG_TX_TYPE_HASH) {
+		if (lag_upper_info &&
+		    lag_upper_info->tx_type != NETDEV_LAG_TX_TYPE_HASH) {
 			extack = netdev_notifier_info_to_extack(&info->info);
 			NL_SET_ERR_MSG_MOD(extack, "LAG device using unsupported Tx type");
 
-- 
2.20.1


From 32eed8b59c7be10d6aac951cf1845e6e5b6f4483 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 5 Nov 2019 14:24:34 -0800
Subject: [PATCH 15/24] net/tls: don't pay attention to sk_write_pending when
 pushing partial records

[ Upstream commit 02b1fa07bb58f5d1f349b5b09eb936739a7b20fc ]

sk_write_pending being not zero does not guarantee that partial
record will be pushed. If the thread waiting for memory times out
the pending record may get stuck.

In case of tls_device there is no path where parial record is
set and writer present in the first place. Partial record is
set only in tls_push_sg() and tls_push_sg() will return an
error immediately. All tls_device callers of tls_push_sg()
will return (and not wait for memory) if it failed.

Fixes: a42055e8d2c3 ("net/tls: Add support for async encryption of records for performance")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_device.c | 4 +++-
 net/tls/tls_sw.c     | 9 +++------
 2 files changed, 6 insertions(+), 7 deletions(-)

diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 43922d86e510..479ebc0ed866 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -575,9 +575,11 @@ static int tls_device_push_pending_record(struct sock *sk, int flags)
 
 void tls_device_write_space(struct sock *sk, struct tls_context *ctx)
 {
-	if (!sk->sk_write_pending && tls_is_partially_sent_record(ctx)) {
+	if (tls_is_partially_sent_record(ctx)) {
 		gfp_t sk_allocation = sk->sk_allocation;
 
+		WARN_ON_ONCE(sk->sk_write_pending);
+
 		sk->sk_allocation = GFP_ATOMIC;
 		tls_push_partial_record(sk, ctx,
 					MSG_DONTWAIT | MSG_NOSIGNAL |
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 91d21b048a9b..b751adc3876c 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -2182,12 +2182,9 @@ void tls_sw_write_space(struct sock *sk, struct tls_context *ctx)
 	struct tls_sw_context_tx *tx_ctx = tls_sw_ctx_tx(ctx);
 
 	/* Schedule the transmission if tx list is ready */
-	if (is_tx_ready(tx_ctx) && !sk->sk_write_pending) {
-		/* Schedule the transmission */
-		if (!test_and_set_bit(BIT_TX_SCHEDULED,
-				      &tx_ctx->tx_bitmask))
-			schedule_delayed_work(&tx_ctx->tx_work.work, 0);
-	}
+	if (is_tx_ready(tx_ctx) &&
+	    !test_and_set_bit(BIT_TX_SCHEDULED, &tx_ctx->tx_bitmask))
+		schedule_delayed_work(&tx_ctx->tx_work.work, 0);
 }
 
 void tls_sw_strparser_arm(struct sock *sk, struct tls_context *tls_ctx)
-- 
2.20.1


From 6fe18b90b1edbf61da3168f6a11bf7d02ca2ccc4 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 5 Nov 2019 14:24:35 -0800
Subject: [PATCH 16/24] net/tls: add a TX lock

[ Upstream commit 79ffe6087e9145d2377385cac48d0d6a6b4225a5 ]

TLS TX needs to release and re-acquire the socket lock if send buffer
fills up.

TLS SW TX path currently depends on only allowing one thread to enter
the function by the abuse of sk_write_pending. If another writer is
already waiting for memory no new ones are allowed in.

This has two problems:
 - writers don't wake other threads up when they leave the kernel;
   meaning that this scheme works for single extra thread (second
   application thread or delayed work) because memory becoming
   available will send a wake up request, but as Mallesham and
   Pooja report with larger number of threads it leads to threads
   being put to sleep indefinitely;
 - the delayed work does not get _scheduled_ but it may _run_ when
   other writers are present leading to crashes as writers don't
   expect state to change under their feet (same records get pushed
   and freed multiple times); it's hard to reliably bail from the
   work, however, because the mere presence of a writer does not
   guarantee that the writer will push pending records before exiting.

Ensuring wakeups always happen will make the code basically open
code a mutex. Just use a mutex.

The TLS HW TX path does not have any locking (not even the
sk_write_pending hack), yet it uses a per-socket sg_tx_data
array to push records.

Fixes: a42055e8d2c3 ("net/tls: Add support for async encryption of records for performance")
Reported-by: Mallesham  Jatharakonda <mallesh537@gmail.com>
Reported-by: Pooja Trivedi <poojatrivedi@gmail.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h    |  5 +++++
 net/tls/tls_device.c |  6 ++++++
 net/tls/tls_main.c   |  2 ++
 net/tls/tls_sw.c     | 21 +++++++--------------
 4 files changed, 20 insertions(+), 14 deletions(-)

diff --git a/include/net/tls.h b/include/net/tls.h
index 41b2d41bb1b8..bd1ef1a915e9 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -40,6 +40,7 @@
 #include <linux/socket.h>
 #include <linux/tcp.h>
 #include <linux/skmsg.h>
+#include <linux/mutex.h>
 #include <linux/netdevice.h>
 
 #include <net/tcp.h>
@@ -268,6 +269,10 @@ struct tls_context {
 
 	bool in_tcp_sendpages;
 	bool pending_open_record_frags;
+
+	struct mutex tx_lock; /* protects partially_sent_* fields and
+			       * per-type TX fields
+			       */
 	unsigned long flags;
 
 	/* cache cold stuff */
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 479ebc0ed866..6b0c9b798d9c 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -482,8 +482,10 @@ static int tls_push_data(struct sock *sk,
 int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 {
 	unsigned char record_type = TLS_RECORD_TYPE_DATA;
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	int rc;
 
+	mutex_lock(&tls_ctx->tx_lock);
 	lock_sock(sk);
 
 	if (unlikely(msg->msg_controllen)) {
@@ -497,12 +499,14 @@ int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 
 out:
 	release_sock(sk);
+	mutex_unlock(&tls_ctx->tx_lock);
 	return rc;
 }
 
 int tls_device_sendpage(struct sock *sk, struct page *page,
 			int offset, size_t size, int flags)
 {
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct iov_iter	msg_iter;
 	char *kaddr = kmap(page);
 	struct kvec iov;
@@ -511,6 +515,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page,
 	if (flags & MSG_SENDPAGE_NOTLAST)
 		flags |= MSG_MORE;
 
+	mutex_lock(&tls_ctx->tx_lock);
 	lock_sock(sk);
 
 	if (flags & MSG_OOB) {
@@ -527,6 +532,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page,
 
 out:
 	release_sock(sk);
+	mutex_unlock(&tls_ctx->tx_lock);
 	return rc;
 }
 
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 43252a801c3f..9313dd51023a 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -258,6 +258,7 @@ void tls_ctx_free(struct tls_context *ctx)
 
 	memzero_explicit(&ctx->crypto_send, sizeof(ctx->crypto_send));
 	memzero_explicit(&ctx->crypto_recv, sizeof(ctx->crypto_recv));
+	mutex_destroy(&ctx->tx_lock);
 	kfree(ctx);
 }
 
@@ -615,6 +616,7 @@ static struct tls_context *create_ctx(struct sock *sk)
 	ctx->getsockopt = sk->sk_prot->getsockopt;
 	ctx->sk_proto_close = sk->sk_prot->close;
 	ctx->unhash = sk->sk_prot->unhash;
+	mutex_init(&ctx->tx_lock);
 	return ctx;
 }
 
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index b751adc3876c..881f06f465f8 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -897,15 +897,9 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 	if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL))
 		return -ENOTSUPP;
 
+	mutex_lock(&tls_ctx->tx_lock);
 	lock_sock(sk);
 
-	/* Wait till there is any pending write on socket */
-	if (unlikely(sk->sk_write_pending)) {
-		ret = wait_on_pending_writer(sk, &timeo);
-		if (unlikely(ret))
-			goto send_end;
-	}
-
 	if (unlikely(msg->msg_controllen)) {
 		ret = tls_proccess_cmsg(sk, msg, &record_type);
 		if (ret) {
@@ -1091,6 +1085,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 	ret = sk_stream_error(sk, msg->msg_flags, ret);
 
 	release_sock(sk);
+	mutex_unlock(&tls_ctx->tx_lock);
 	return copied ? copied : ret;
 }
 
@@ -1114,13 +1109,6 @@ static int tls_sw_do_sendpage(struct sock *sk, struct page *page,
 	eor = !(flags & (MSG_MORE | MSG_SENDPAGE_NOTLAST));
 	sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
-	/* Wait till there is any pending write on socket */
-	if (unlikely(sk->sk_write_pending)) {
-		ret = wait_on_pending_writer(sk, &timeo);
-		if (unlikely(ret))
-			goto sendpage_end;
-	}
-
 	/* Call the sk_stream functions to manage the sndbuf mem. */
 	while (size > 0) {
 		size_t copy, required_size;
@@ -1219,15 +1207,18 @@ static int tls_sw_do_sendpage(struct sock *sk, struct page *page,
 int tls_sw_sendpage(struct sock *sk, struct page *page,
 		    int offset, size_t size, int flags)
 {
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	int ret;
 
 	if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
 		      MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY))
 		return -ENOTSUPP;
 
+	mutex_lock(&tls_ctx->tx_lock);
 	lock_sock(sk);
 	ret = tls_sw_do_sendpage(sk, page, offset, size, flags);
 	release_sock(sk);
+	mutex_unlock(&tls_ctx->tx_lock);
 	return ret;
 }
 
@@ -2172,9 +2163,11 @@ static void tx_work_handler(struct work_struct *work)
 
 	if (!test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask))
 		return;
+	mutex_lock(&tls_ctx->tx_lock);
 	lock_sock(sk);
 	tls_tx_records(sk, -1);
 	release_sock(sk);
+	mutex_unlock(&tls_ctx->tx_lock);
 }
 
 void tls_sw_write_space(struct sock *sk, struct tls_context *ctx)
-- 
2.20.1


From fd88e30aa0a322dfdb8c8463b36c1012b1e808a4 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 5 Nov 2019 14:24:36 -0800
Subject: [PATCH 17/24] selftests/tls: add test for concurrent recv and send

[ Upstream commit 41098af59d8d753aa8d3bb4310cc4ecb61fc82c7 ]

Add a test which spawns 16 threads and performs concurrent
send and recv calls on the same socket.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/tls.c | 108 ++++++++++++++++++++++++++++++
 1 file changed, 108 insertions(+)

diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 4c285b6e1db8..1c8f194d6556 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -898,6 +898,114 @@ TEST_F(tls, nonblocking)
 	}
 }
 
+static void
+test_mutliproc(struct __test_metadata *_metadata, struct _test_data_tls *self,
+	       bool sendpg, unsigned int n_readers, unsigned int n_writers)
+{
+	const unsigned int n_children = n_readers + n_writers;
+	const size_t data = 6 * 1000 * 1000;
+	const size_t file_sz = data / 100;
+	size_t read_bias, write_bias;
+	int i, fd, child_id;
+	char buf[file_sz];
+	pid_t pid;
+
+	/* Only allow multiples for simplicity */
+	ASSERT_EQ(!(n_readers % n_writers) || !(n_writers % n_readers), true);
+	read_bias = n_writers / n_readers ?: 1;
+	write_bias = n_readers / n_writers ?: 1;
+
+	/* prep a file to send */
+	fd = open("/tmp/", O_TMPFILE | O_RDWR, 0600);
+	ASSERT_GE(fd, 0);
+
+	memset(buf, 0xac, file_sz);
+	ASSERT_EQ(write(fd, buf, file_sz), file_sz);
+
+	/* spawn children */
+	for (child_id = 0; child_id < n_children; child_id++) {
+		pid = fork();
+		ASSERT_NE(pid, -1);
+		if (!pid)
+			break;
+	}
+
+	/* parent waits for all children */
+	if (pid) {
+		for (i = 0; i < n_children; i++) {
+			int status;
+
+			wait(&status);
+			EXPECT_EQ(status, 0);
+		}
+
+		return;
+	}
+
+	/* Split threads for reading and writing */
+	if (child_id < n_readers) {
+		size_t left = data * read_bias;
+		char rb[8001];
+
+		while (left) {
+			int res;
+
+			res = recv(self->cfd, rb,
+				   left > sizeof(rb) ? sizeof(rb) : left, 0);
+
+			EXPECT_GE(res, 0);
+			left -= res;
+		}
+	} else {
+		size_t left = data * write_bias;
+
+		while (left) {
+			int res;
+
+			ASSERT_EQ(lseek(fd, 0, SEEK_SET), 0);
+			if (sendpg)
+				res = sendfile(self->fd, fd, NULL,
+					       left > file_sz ? file_sz : left);
+			else
+				res = send(self->fd, buf,
+					   left > file_sz ? file_sz : left, 0);
+
+			EXPECT_GE(res, 0);
+			left -= res;
+		}
+	}
+}
+
+TEST_F(tls, mutliproc_even)
+{
+	test_mutliproc(_metadata, self, false, 6, 6);
+}
+
+TEST_F(tls, mutliproc_readers)
+{
+	test_mutliproc(_metadata, self, false, 4, 12);
+}
+
+TEST_F(tls, mutliproc_writers)
+{
+	test_mutliproc(_metadata, self, false, 10, 2);
+}
+
+TEST_F(tls, mutliproc_sendpage_even)
+{
+	test_mutliproc(_metadata, self, true, 6, 6);
+}
+
+TEST_F(tls, mutliproc_sendpage_readers)
+{
+	test_mutliproc(_metadata, self, true, 4, 12);
+}
+
+TEST_F(tls, mutliproc_sendpage_writers)
+{
+	test_mutliproc(_metadata, self, true, 10, 2);
+}
+
 TEST_F(tls, control_msg)
 {
 	if (self->notls)
-- 
2.20.1


From 11ca732af01adfe4a7804fe113562f5bd63894e3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 7 Nov 2019 09:26:19 -0800
Subject: [PATCH 18/24] ipv6: fixes rt6_probe() and fib6_nh->last_probe init

[ Upstream commit 1bef4c223b8588cf50433bdc2c6953d82949b3b3 ]

While looking at a syzbot KCSAN report [1], I found multiple
issues in this code :

1) fib6_nh->last_probe has an initial value of 0.

   While probably okay on 64bit kernels, this causes an issue
   on 32bit kernels since the time_after(jiffies, 0 + interval)
   might be false ~24 days after boot (for HZ=1000)

2) The data-race found by KCSAN
   I could use READ_ONCE() and WRITE_ONCE(), but we also can
   take the opportunity of not piling-up too many rt6_probe_deferred()
   works by using instead cmpxchg() so that only one cpu wins the race.

[1]
BUG: KCSAN: data-race in find_match / find_match

write to 0xffff8880bb7aabe8 of 8 bytes by interrupt on cpu 1:
 rt6_probe net/ipv6/route.c:663 [inline]
 find_match net/ipv6/route.c:757 [inline]
 find_match+0x5bd/0x790 net/ipv6/route.c:733
 __find_rr_leaf+0xe3/0x780 net/ipv6/route.c:831
 find_rr_leaf net/ipv6/route.c:852 [inline]
 rt6_select net/ipv6/route.c:896 [inline]
 fib6_table_lookup+0x383/0x650 net/ipv6/route.c:2164
 ip6_pol_route+0xee/0x5c0 net/ipv6/route.c:2200
 ip6_pol_route_output+0x48/0x60 net/ipv6/route.c:2452
 fib6_rule_lookup+0x3d6/0x470 net/ipv6/fib6_rules.c:117
 ip6_route_output_flags_noref+0x16b/0x230 net/ipv6/route.c:2484
 ip6_route_output_flags+0x50/0x1a0 net/ipv6/route.c:2497
 ip6_dst_lookup_tail+0x25d/0xc30 net/ipv6/ip6_output.c:1049
 ip6_dst_lookup_flow+0x68/0x120 net/ipv6/ip6_output.c:1150
 inet6_csk_route_socket+0x2f7/0x420 net/ipv6/inet6_connection_sock.c:106
 inet6_csk_xmit+0x91/0x1f0 net/ipv6/inet6_connection_sock.c:121
 __tcp_transmit_skb+0xe81/0x1d60 net/ipv4/tcp_output.c:1169
 tcp_transmit_skb net/ipv4/tcp_output.c:1185 [inline]
 tcp_xmit_probe_skb+0x19b/0x1d0 net/ipv4/tcp_output.c:3735

read to 0xffff8880bb7aabe8 of 8 bytes by interrupt on cpu 0:
 rt6_probe net/ipv6/route.c:657 [inline]
 find_match net/ipv6/route.c:757 [inline]
 find_match+0x521/0x790 net/ipv6/route.c:733
 __find_rr_leaf+0xe3/0x780 net/ipv6/route.c:831
 find_rr_leaf net/ipv6/route.c:852 [inline]
 rt6_select net/ipv6/route.c:896 [inline]
 fib6_table_lookup+0x383/0x650 net/ipv6/route.c:2164
 ip6_pol_route+0xee/0x5c0 net/ipv6/route.c:2200
 ip6_pol_route_output+0x48/0x60 net/ipv6/route.c:2452
 fib6_rule_lookup+0x3d6/0x470 net/ipv6/fib6_rules.c:117
 ip6_route_output_flags_noref+0x16b/0x230 net/ipv6/route.c:2484
 ip6_route_output_flags+0x50/0x1a0 net/ipv6/route.c:2497
 ip6_dst_lookup_tail+0x25d/0xc30 net/ipv6/ip6_output.c:1049
 ip6_dst_lookup_flow+0x68/0x120 net/ipv6/ip6_output.c:1150
 inet6_csk_route_socket+0x2f7/0x420 net/ipv6/inet6_connection_sock.c:106
 inet6_csk_xmit+0x91/0x1f0 net/ipv6/inet6_connection_sock.c:121
 __tcp_transmit_skb+0xe81/0x1d60 net/ipv4/tcp_output.c:1169

Reported by Kernel Concurrency Sanitizer on:
CPU: 0 PID: 18894 Comm: udevd Not tainted 5.4.0-rc3+ #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011

Fixes: cc3a86c802f0 ("ipv6: Change rt6_probe to take a fib6_nh")
Fixes: f547fac624be ("ipv6: rate-limit probes for neighbourless routes")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 546088e50815..2b25a0de0364 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -621,6 +621,7 @@ static void rt6_probe(struct fib6_nh *fib6_nh)
 {
 	struct __rt6_probe_work *work = NULL;
 	const struct in6_addr *nh_gw;
+	unsigned long last_probe;
 	struct neighbour *neigh;
 	struct net_device *dev;
 	struct inet6_dev *idev;
@@ -639,6 +640,7 @@ static void rt6_probe(struct fib6_nh *fib6_nh)
 	nh_gw = &fib6_nh->fib_nh_gw6;
 	dev = fib6_nh->fib_nh_dev;
 	rcu_read_lock_bh();
+	last_probe = READ_ONCE(fib6_nh->last_probe);
 	idev = __in6_dev_get(dev);
 	neigh = __ipv6_neigh_lookup_noref(dev, nh_gw);
 	if (neigh) {
@@ -654,13 +656,15 @@ static void rt6_probe(struct fib6_nh *fib6_nh)
 				__neigh_set_probe_once(neigh);
 		}
 		write_unlock(&neigh->lock);
-	} else if (time_after(jiffies, fib6_nh->last_probe +
+	} else if (time_after(jiffies, last_probe +
 				       idev->cnf.rtr_probe_interval)) {
 		work = kmalloc(sizeof(*work), GFP_ATOMIC);
 	}
 
-	if (work) {
-		fib6_nh->last_probe = jiffies;
+	if (!work || cmpxchg(&fib6_nh->last_probe,
+			     last_probe, jiffies) != last_probe) {
+		kfree(work);
+	} else {
 		INIT_WORK(&work->work, rt6_probe_deferred);
 		work->target = *nh_gw;
 		dev_hold(dev);
@@ -3385,6 +3389,9 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
 	int err;
 
 	fib6_nh->fib_nh_family = AF_INET6;
+#ifdef CONFIG_IPV6_ROUTER_PREF
+	fib6_nh->last_probe = jiffies;
+#endif
 
 	err = -ENODEV;
 	if (cfg->fc_ifindex) {
-- 
2.20.1


From 6523a46ad32af6c50b665bd0b78ad56dec7db9c9 Mon Sep 17 00:00:00 2001
From: Salil Mehta <salil.mehta@huawei.com>
Date: Thu, 7 Nov 2019 17:09:53 +0000
Subject: [PATCH 19/24] net: hns: Fix the stray netpoll locks causing deadlock
 in NAPI path

[ Upstream commit bf5a6b4c474c589244dc25ee1af2c3c829228ef8 ]

This patch fixes the problem of the spin locks, originally
meant for the netpoll path of hns driver, causing deadlock in
the normal NAPI poll path. The issue happened due to the presence
of the stray leftover spin lock code related to the netpoll,
whose support was earlier removed from the HNS[1], got activated
due to enabling of NET_POLL_CONTROLLER switch.

Earlier background:
The netpoll handling code originally had this bug(as identified
by Marc Zyngier[2]) of wrong spin lock API being used which did
not disable the interrupts and hence could cause locking issues.
i.e. if the lock were first acquired in context to thread like
'ip' util and this lock if ever got later acquired again in
context to the interrupt context like TX/RX (Interrupts could
always pre-empt the lock holding task and acquire the lock again)
and hence could cause deadlock.

Proposed Solution:
1. If the netpoll was enabled in the HNS driver, which is not
   right now, we could have simply used spin_[un]lock_irqsave()
2. But as netpoll is disabled, therefore, it is best to get rid
   of the existing locks and stray code for now. This should
   solve the problem reported by Marc.

[1] https://git.kernel.org/torvalds/c/4bd2c03be7
[2] https://patchwork.ozlabs.org/patch/1189139/

Fixes: 4bd2c03be707 ("net: hns: remove ndo_poll_controller")
Cc: lipeng <lipeng321@huawei.com>
Cc: Yisen Zhuang <yisen.zhuang@huawei.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: David S. Miller <davem@davemloft.net>
Reported-by: Marc Zyngier <maz@kernel.org>
Acked-by: Marc Zyngier <maz@kernel.org>
Tested-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns/hnae.c     |  1 -
 drivers/net/ethernet/hisilicon/hns/hnae.h     |  3 ---
 drivers/net/ethernet/hisilicon/hns/hns_enet.c | 22 +------------------
 3 files changed, 1 insertion(+), 25 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c
index 6d0457eb4faa..08339278c722 100644
--- a/drivers/net/ethernet/hisilicon/hns/hnae.c
+++ b/drivers/net/ethernet/hisilicon/hns/hnae.c
@@ -199,7 +199,6 @@ hnae_init_ring(struct hnae_queue *q, struct hnae_ring *ring, int flags)
 
 	ring->q = q;
 	ring->flags = flags;
-	spin_lock_init(&ring->lock);
 	ring->coal_param = q->handle->coal_param;
 	assert(!ring->desc && !ring->desc_cb && !ring->desc_dma_addr);
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.h b/drivers/net/ethernet/hisilicon/hns/hnae.h
index e9c67c06bfd2..6ab9458302e1 100644
--- a/drivers/net/ethernet/hisilicon/hns/hnae.h
+++ b/drivers/net/ethernet/hisilicon/hns/hnae.h
@@ -274,9 +274,6 @@ struct hnae_ring {
 	/* statistic */
 	struct ring_stats stats;
 
-	/* ring lock for poll one */
-	spinlock_t lock;
-
 	dma_addr_t desc_dma_addr;
 	u32 buf_size;       /* size for hnae_desc->addr, preset by AE */
 	u16 desc_num;       /* total number of desc */
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index 2235dd55fab2..56e8d4dee0e0 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -943,15 +943,6 @@ static int is_valid_clean_head(struct hnae_ring *ring, int h)
 	return u > c ? (h > c && h <= u) : (h > c || h <= u);
 }
 
-/* netif_tx_lock will turn down the performance, set only when necessary */
-#ifdef CONFIG_NET_POLL_CONTROLLER
-#define NETIF_TX_LOCK(ring) spin_lock(&(ring)->lock)
-#define NETIF_TX_UNLOCK(ring) spin_unlock(&(ring)->lock)
-#else
-#define NETIF_TX_LOCK(ring)
-#define NETIF_TX_UNLOCK(ring)
-#endif
-
 /* reclaim all desc in one budget
  * return error or number of desc left
  */
@@ -965,21 +956,16 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data,
 	int head;
 	int bytes, pkts;
 
-	NETIF_TX_LOCK(ring);
-
 	head = readl_relaxed(ring->io_base + RCB_REG_HEAD);
 	rmb(); /* make sure head is ready before touch any data */
 
-	if (is_ring_empty(ring) || head == ring->next_to_clean) {
-		NETIF_TX_UNLOCK(ring);
+	if (is_ring_empty(ring) || head == ring->next_to_clean)
 		return 0; /* no data to poll */
-	}
 
 	if (!is_valid_clean_head(ring, head)) {
 		netdev_err(ndev, "wrong head (%d, %d-%d)\n", head,
 			   ring->next_to_use, ring->next_to_clean);
 		ring->stats.io_err_cnt++;
-		NETIF_TX_UNLOCK(ring);
 		return -EIO;
 	}
 
@@ -994,8 +980,6 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data,
 	ring->stats.tx_pkts += pkts;
 	ring->stats.tx_bytes += bytes;
 
-	NETIF_TX_UNLOCK(ring);
-
 	dev_queue = netdev_get_tx_queue(ndev, ring_data->queue_index);
 	netdev_tx_completed_queue(dev_queue, pkts, bytes);
 
@@ -1055,16 +1039,12 @@ static void hns_nic_tx_clr_all_bufs(struct hns_nic_ring_data *ring_data)
 	int head;
 	int bytes, pkts;
 
-	NETIF_TX_LOCK(ring);
-
 	head = ring->next_to_use; /* ntu :soft setted ring position*/
 	bytes = 0;
 	pkts = 0;
 	while (head != ring->next_to_clean)
 		hns_nic_reclaim_one_desc(ring, &bytes, &pkts);
 
-	NETIF_TX_UNLOCK(ring);
-
 	dev_queue = netdev_get_tx_queue(ndev, ring_data->queue_index);
 	netdev_tx_reset_queue(dev_queue);
 }
-- 
2.20.1


From fd1ad2e5479f05b379313033e41c650b291ac2fb Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 4 Nov 2019 21:38:43 -0800
Subject: [PATCH 20/24] net: prevent load/store tearing on sk->sk_stamp

[ Upstream commit f75359f3ac855940c5718af10ba089b8977bf339 ]

Add a couple of READ_ONCE() and WRITE_ONCE() to prevent
load-tearing and store-tearing in sock_read_timestamp()
and sock_write_timestamp()

This might prevent another KCSAN report.

Fixes: 3a0ed3e96197 ("sock: Make sock->sk_stamp thread-safe")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Deepa Dinamani <deepa.kernel@gmail.com>
Acked-by: Deepa Dinamani <deepa.kernel@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index 2c53f1a1d905..184a7549e433 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2326,7 +2326,7 @@ static inline ktime_t sock_read_timestamp(struct sock *sk)
 
 	return kt;
 #else
-	return sk->sk_stamp;
+	return READ_ONCE(sk->sk_stamp);
 #endif
 }
 
@@ -2337,7 +2337,7 @@ static inline void sock_write_timestamp(struct sock *sk, ktime_t kt)
 	sk->sk_stamp = kt;
 	write_sequnlock(&sk->sk_stamp_seq);
 #else
-	sk->sk_stamp = kt;
+	WRITE_ONCE(sk->sk_stamp, kt);
 #endif
 }
 
-- 
2.20.1


From 4b6bd2a4886a684c9cebef3f7623a128c227139f Mon Sep 17 00:00:00 2001
From: John Hurley <john.hurley@netronome.com>
Date: Sat, 2 Nov 2019 14:17:47 +0000
Subject: [PATCH 21/24] net: sched: prevent duplicate flower rules from
 tcf_proto destroy race

[ Upstream commit 59eb87cb52c9f7164804bc8639c4d03ba9b0c169 ]

When a new filter is added to cls_api, the function
tcf_chain_tp_insert_unique() looks up the protocol/priority/chain to
determine if the tcf_proto is duplicated in the chain's hashtable. It then
creates a new entry or continues with an existing one. In cls_flower, this
allows the function fl_ht_insert_unque to determine if a filter is a
duplicate and reject appropriately, meaning that the duplicate will not be
passed to drivers via the offload hooks. However, when a tcf_proto is
destroyed it is removed from its chain before a hardware remove hook is
hit. This can lead to a race whereby the driver has not received the
remove message but duplicate flows can be accepted. This, in turn, can
lead to the offload driver receiving incorrect duplicate flows and out of
order add/delete messages.

Prevent duplicates by utilising an approach suggested by Vlad Buslov. A
hash table per block stores each unique chain/protocol/prio being
destroyed. This entry is only removed when the full destroy (and hardware
offload) has completed. If a new flow is being added with the same
identiers as a tc_proto being detroyed, then the add request is replayed
until the destroy is complete.

Fixes: 8b64678e0af8 ("net: sched: refactor tp insert/delete for concurrent execution")
Signed-off-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Reported-by: Louis Peens <louis.peens@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h |  4 ++
 net/sched/cls_api.c       | 83 +++++++++++++++++++++++++++++++++++++--
 2 files changed, 83 insertions(+), 4 deletions(-)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 58b1fbc884a7..50ea27d0f7c5 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -13,6 +13,7 @@
 #include <linux/refcount.h>
 #include <linux/workqueue.h>
 #include <linux/mutex.h>
+#include <linux/hashtable.h>
 #include <net/gen_stats.h>
 #include <net/rtnetlink.h>
 #include <net/flow_offload.h>
@@ -359,6 +360,7 @@ struct tcf_proto {
 	bool			deleting;
 	refcount_t		refcnt;
 	struct rcu_head		rcu;
+	struct hlist_node	destroy_ht_node;
 };
 
 struct qdisc_skb_cb {
@@ -409,6 +411,8 @@ struct tcf_block {
 		struct list_head filter_chain_list;
 	} chain0;
 	struct rcu_head rcu;
+	DECLARE_HASHTABLE(proto_destroy_ht, 7);
+	struct mutex proto_destroy_lock; /* Lock for proto_destroy hashtable. */
 };
 
 #ifdef CONFIG_PROVE_LOCKING
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 6b12883e04b8..5c1769999a92 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -21,6 +21,7 @@
 #include <linux/slab.h>
 #include <linux/idr.h>
 #include <linux/rhashtable.h>
+#include <linux/jhash.h>
 #include <net/net_namespace.h>
 #include <net/sock.h>
 #include <net/netlink.h>
@@ -45,6 +46,62 @@ static LIST_HEAD(tcf_proto_base);
 /* Protects list of registered TC modules. It is pure SMP lock. */
 static DEFINE_RWLOCK(cls_mod_lock);
 
+static u32 destroy_obj_hashfn(const struct tcf_proto *tp)
+{
+	return jhash_3words(tp->chain->index, tp->prio,
+			    (__force __u32)tp->protocol, 0);
+}
+
+static void tcf_proto_signal_destroying(struct tcf_chain *chain,
+					struct tcf_proto *tp)
+{
+	struct tcf_block *block = chain->block;
+
+	mutex_lock(&block->proto_destroy_lock);
+	hash_add_rcu(block->proto_destroy_ht, &tp->destroy_ht_node,
+		     destroy_obj_hashfn(tp));
+	mutex_unlock(&block->proto_destroy_lock);
+}
+
+static bool tcf_proto_cmp(const struct tcf_proto *tp1,
+			  const struct tcf_proto *tp2)
+{
+	return tp1->chain->index == tp2->chain->index &&
+	       tp1->prio == tp2->prio &&
+	       tp1->protocol == tp2->protocol;
+}
+
+static bool tcf_proto_exists_destroying(struct tcf_chain *chain,
+					struct tcf_proto *tp)
+{
+	u32 hash = destroy_obj_hashfn(tp);
+	struct tcf_proto *iter;
+	bool found = false;
+
+	rcu_read_lock();
+	hash_for_each_possible_rcu(chain->block->proto_destroy_ht, iter,
+				   destroy_ht_node, hash) {
+		if (tcf_proto_cmp(tp, iter)) {
+			found = true;
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+	return found;
+}
+
+static void
+tcf_proto_signal_destroyed(struct tcf_chain *chain, struct tcf_proto *tp)
+{
+	struct tcf_block *block = chain->block;
+
+	mutex_lock(&block->proto_destroy_lock);
+	if (hash_hashed(&tp->destroy_ht_node))
+		hash_del_rcu(&tp->destroy_ht_node);
+	mutex_unlock(&block->proto_destroy_lock);
+}
+
 /* Find classifier type by string name */
 
 static const struct tcf_proto_ops *__tcf_proto_lookup_ops(const char *kind)
@@ -232,9 +289,11 @@ static void tcf_proto_get(struct tcf_proto *tp)
 static void tcf_chain_put(struct tcf_chain *chain);
 
 static void tcf_proto_destroy(struct tcf_proto *tp, bool rtnl_held,
-			      struct netlink_ext_ack *extack)
+			      bool sig_destroy, struct netlink_ext_ack *extack)
 {
 	tp->ops->destroy(tp, rtnl_held, extack);
+	if (sig_destroy)
+		tcf_proto_signal_destroyed(tp->chain, tp);
 	tcf_chain_put(tp->chain);
 	module_put(tp->ops->owner);
 	kfree_rcu(tp, rcu);
@@ -244,7 +303,7 @@ static void tcf_proto_put(struct tcf_proto *tp, bool rtnl_held,
 			  struct netlink_ext_ack *extack)
 {
 	if (refcount_dec_and_test(&tp->refcnt))
-		tcf_proto_destroy(tp, rtnl_held, extack);
+		tcf_proto_destroy(tp, rtnl_held, true, extack);
 }
 
 static int walker_check_empty(struct tcf_proto *tp, void *fh,
@@ -368,6 +427,7 @@ static bool tcf_chain_detach(struct tcf_chain *chain)
 static void tcf_block_destroy(struct tcf_block *block)
 {
 	mutex_destroy(&block->lock);
+	mutex_destroy(&block->proto_destroy_lock);
 	kfree_rcu(block, rcu);
 }
 
@@ -543,6 +603,12 @@ static void tcf_chain_flush(struct tcf_chain *chain, bool rtnl_held)
 
 	mutex_lock(&chain->filter_chain_lock);
 	tp = tcf_chain_dereference(chain->filter_chain, chain);
+	while (tp) {
+		tp_next = rcu_dereference_protected(tp->next, 1);
+		tcf_proto_signal_destroying(chain, tp);
+		tp = tp_next;
+	}
+	tp = tcf_chain_dereference(chain->filter_chain, chain);
 	RCU_INIT_POINTER(chain->filter_chain, NULL);
 	tcf_chain0_head_change(chain, NULL);
 	chain->flushing = true;
@@ -1002,6 +1068,7 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q,
 		return ERR_PTR(-ENOMEM);
 	}
 	mutex_init(&block->lock);
+	mutex_init(&block->proto_destroy_lock);
 	flow_block_init(&block->flow_block);
 	INIT_LIST_HEAD(&block->chain_list);
 	INIT_LIST_HEAD(&block->owner_list);
@@ -1754,6 +1821,12 @@ static struct tcf_proto *tcf_chain_tp_insert_unique(struct tcf_chain *chain,
 
 	mutex_lock(&chain->filter_chain_lock);
 
+	if (tcf_proto_exists_destroying(chain, tp_new)) {
+		mutex_unlock(&chain->filter_chain_lock);
+		tcf_proto_destroy(tp_new, rtnl_held, false, NULL);
+		return ERR_PTR(-EAGAIN);
+	}
+
 	tp = tcf_chain_tp_find(chain, &chain_info,
 			       protocol, prio, false);
 	if (!tp)
@@ -1761,10 +1834,10 @@ static struct tcf_proto *tcf_chain_tp_insert_unique(struct tcf_chain *chain,
 	mutex_unlock(&chain->filter_chain_lock);
 
 	if (tp) {
-		tcf_proto_destroy(tp_new, rtnl_held, NULL);
+		tcf_proto_destroy(tp_new, rtnl_held, false, NULL);
 		tp_new = tp;
 	} else if (err) {
-		tcf_proto_destroy(tp_new, rtnl_held, NULL);
+		tcf_proto_destroy(tp_new, rtnl_held, false, NULL);
 		tp_new = ERR_PTR(err);
 	}
 
@@ -1802,6 +1875,7 @@ static void tcf_chain_tp_delete_empty(struct tcf_chain *chain,
 		return;
 	}
 
+	tcf_proto_signal_destroying(chain, tp);
 	next = tcf_chain_dereference(chain_info.next, chain);
 	if (tp == chain->filter_chain)
 		tcf_chain0_head_change(chain, next);
@@ -2321,6 +2395,7 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
 		err = -EINVAL;
 		goto errout_locked;
 	} else if (t->tcm_handle == 0) {
+		tcf_proto_signal_destroying(chain, tp);
 		tcf_chain_tp_remove(chain, &chain_info, tp);
 		mutex_unlock(&chain->filter_chain_lock);
 
-- 
2.20.1


From 0118a34c0b66c2306a722aec59042225ba88fa19 Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.ibm.com>
Date: Wed, 6 Nov 2019 10:49:57 +0100
Subject: [PATCH 22/24] net/smc: fix ethernet interface refcounting

[ Upstream commit 98f3375505b8d6517bd6710bc6d4f6289eeb30aa ]

If a pnet table entry is to be added mentioning a valid ethernet
interface, but an invalid infiniband or ISM device, the dev_put()
operation for the ethernet interface is called twice, resulting
in a negative refcount for the ethernet interface, which disables
removal of such a network interface.

This patch removes one of the dev_put() calls.

Fixes: 890a2cb4a966 ("net/smc: rework pnet table")
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/smc_pnet.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index bab2da8cf17a..a20594056fef 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -376,8 +376,6 @@ static int smc_pnet_fill_entry(struct net *net,
 	return 0;
 
 error:
-	if (pnetelem->ndev)
-		dev_put(pnetelem->ndev);
 	return rc;
 }
 
-- 
2.20.1


From 6d633f0cebda494710713ca33b60c6549a724c32 Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Fri, 8 Nov 2019 17:08:50 +0100
Subject: [PATCH 23/24] vsock/virtio: fix sock refcnt holding during the
 shutdown

[ Upstream commit ad8a7220355d39cddce8eac1cea9677333e8b821 ]

The "42f5cda5eaf4" commit rightly set SOCK_DONE on peer shutdown,
but there is an issue if we receive the SHUTDOWN(RDWR) while the
virtio_transport_close_timeout() is scheduled.
In this case, when the timeout fires, the SOCK_DONE is already
set and the virtio_transport_close_timeout() will not call
virtio_transport_reset() and virtio_transport_do_close().
This causes that both sockets remain open and will never be released,
preventing the unloading of [virtio|vhost]_transport modules.

This patch fixes this issue, calling virtio_transport_reset() and
virtio_transport_do_close() when we receive the SHUTDOWN(RDWR)
and there is nothing left to read.

Fixes: 42f5cda5eaf4 ("vsock/virtio: set SOCK_DONE on peer shutdown")
Cc: Stephen Barber <smbarber@chromium.org>
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/vmw_vsock/virtio_transport_common.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index a7adffd062c7..058d59fceddd 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -870,9 +870,11 @@ virtio_transport_recv_connected(struct sock *sk,
 		if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SHUTDOWN_SEND)
 			vsk->peer_shutdown |= SEND_SHUTDOWN;
 		if (vsk->peer_shutdown == SHUTDOWN_MASK &&
-		    vsock_stream_has_data(vsk) <= 0) {
-			sock_set_flag(sk, SOCK_DONE);
-			sk->sk_state = TCP_CLOSING;
+		    vsock_stream_has_data(vsk) <= 0 &&
+		    !sock_flag(sk, SOCK_DONE)) {
+			(void)virtio_transport_reset(vsk, NULL);
+
+			virtio_transport_do_close(vsk, true);
 		}
 		if (le32_to_cpu(pkt->hdr.flags))
 			sk->sk_state_change(sk);
-- 
2.20.1


From 442613b6b919600a38297231e61968636cf9e635 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Wed, 6 Nov 2019 21:51:31 +0100
Subject: [PATCH 24/24] r8169: fix page read in r8168g_mdio_read

[ Upstream commit 9c6850fea3edefef6e7153b2c466f09155399882 ]

Functions like phy_modify_paged() read the current page, on Realtek
PHY's this means reading the value of register 0x1f. Add special
handling for reading this register, similar to what we do already
in r8168g_mdio_write(). Currently we read a random value that by
chance seems to be 0 always.

Fixes: a2928d28643e ("r8169: use paged versions of phylib MDIO access functions")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index bae0074ab9aa..4129dcee63e6 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -863,6 +863,9 @@ static void r8168g_mdio_write(struct rtl8169_private *tp, int reg, int value)
 
 static int r8168g_mdio_read(struct rtl8169_private *tp, int reg)
 {
+	if (reg == 0x1f)
+		return tp->ocp_base == OCP_STD_PHY_BASE ? 0 : tp->ocp_base >> 4;
+
 	if (tp->ocp_base != OCP_STD_PHY_BASE)
 		reg -= 0x10;
 
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Sat, Nov 09, 2019 at 09:47:09PM -0800, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.19 and v5.3
> stable, respectively.

All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 106 bytes --]


Please queue up the following networking bug fixes for v4.19 and
v5.3 -stable, respectively.

Thank you.

[-- Attachment #2: net_419.mbox --]
[-- Type: Application/Octet-Stream, Size: 16395 bytes --]

From 4d71a27c53d82c746b83a211975f5dd41afa5a67 Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.com>
Date: Thu, 14 Nov 2019 11:16:01 +0100
Subject: [PATCH 1/6] ax88172a: fix information leak on short answers

[ Upstream commit a9a51bd727d141a67b589f375fe69d0e54c4fe22 ]

If a malicious device gives a short MAC it can elicit up to
5 bytes of leaked memory out of the driver. We need to check for
ETH_ALEN instead.

Reported-by: syzbot+a8d4acdad35e6bbca308@syzkaller.appspotmail.com
Signed-off-by: Oliver Neukum <oneukum@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/ax88172a.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/usb/ax88172a.c b/drivers/net/usb/ax88172a.c
index 501576f53854..914cac55a7ae 100644
--- a/drivers/net/usb/ax88172a.c
+++ b/drivers/net/usb/ax88172a.c
@@ -208,7 +208,7 @@ static int ax88172a_bind(struct usbnet *dev, struct usb_interface *intf)
 
 	/* Get the MAC address */
 	ret = asix_read_cmd(dev, AX_CMD_READ_NODE_ID, 0, 0, ETH_ALEN, buf, 0);
-	if (ret < 0) {
+	if (ret < ETH_ALEN) {
 		netdev_err(dev->net, "Failed to read MAC address: %d\n", ret);
 		goto free;
 	}
-- 
2.20.1


From ba16b203ace82320414d26f787e566ea57353ddd Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Fri, 15 Nov 2019 18:29:52 +0100
Subject: [PATCH 2/6] ipmr: Fix skb headroom in ipmr_get_route().

[ Upstream commit 7901cd97963d6cbde88fa25a4a446db3554c16c6 ]

In route.c, inet_rtm_getroute_build_skb() creates an skb with no
headroom. This skb is then used by inet_rtm_getroute() which may pass
it to rt_fill_info() and, from there, to ipmr_get_route(). The later
might try to reuse this skb by cloning it and prepending an IPv4
header. But since the original skb has no headroom, skb_push() triggers
skb_under_panic():

skbuff: skb_under_panic: text:00000000ca46ad8a len:80 put:20 head:00000000cd28494e data:000000009366fd6b tail:0x3c end:0xec0 dev:veth0
------------[ cut here ]------------
kernel BUG at net/core/skbuff.c:108!
invalid opcode: 0000 [#1] SMP KASAN PTI
CPU: 6 PID: 587 Comm: ip Not tainted 5.4.0-rc6+ #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-2.fc30 04/01/2014
RIP: 0010:skb_panic+0xbf/0xd0
Code: 41 a2 ff 8b 4b 70 4c 8b 4d d0 48 c7 c7 20 76 f5 8b 44 8b 45 bc 48 8b 55 c0 48 8b 75 c8 41 54 41 57 41 56 41 55 e8 75 dc 7a ff <0f> 0b 0f 1f 44 00 00 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00
RSP: 0018:ffff888059ddf0b0 EFLAGS: 00010286
RAX: 0000000000000086 RBX: ffff888060a315c0 RCX: ffffffff8abe4822
RDX: 0000000000000000 RSI: 0000000000000008 RDI: ffff88806c9a79cc
RBP: ffff888059ddf118 R08: ffffed100d9361b1 R09: ffffed100d9361b0
R10: ffff88805c68aee3 R11: ffffed100d9361b1 R12: ffff88805d218000
R13: ffff88805c689fec R14: 000000000000003c R15: 0000000000000ec0
FS:  00007f6af184b700(0000) GS:ffff88806c980000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007ffc8204a000 CR3: 0000000057b40006 CR4: 0000000000360ee0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 skb_push+0x7e/0x80
 ipmr_get_route+0x459/0x6fa
 rt_fill_info+0x692/0x9f0
 inet_rtm_getroute+0xd26/0xf20
 rtnetlink_rcv_msg+0x45d/0x630
 netlink_rcv_skb+0x1a5/0x220
 rtnetlink_rcv+0x15/0x20
 netlink_unicast+0x305/0x3a0
 netlink_sendmsg+0x575/0x730
 sock_sendmsg+0xb5/0xc0
 ___sys_sendmsg+0x497/0x4f0
 __sys_sendmsg+0xcb/0x150
 __x64_sys_sendmsg+0x48/0x50
 do_syscall_64+0xd2/0xac0
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Actually the original skb used to have enough headroom, but the
reserve_skb() call was lost with the introduction of
inet_rtm_getroute_build_skb() by commit 404eb77ea766 ("ipv4: support
sport, dport and ip_proto in RTM_GETROUTE").

We could reserve some headroom again in inet_rtm_getroute_build_skb(),
but this function shouldn't be responsible for handling the special
case of ipmr_get_route(). Let's handle that directly in
ipmr_get_route() by calling skb_realloc_headroom() instead of
skb_clone().

Fixes: 404eb77ea766 ("ipv4: support sport, dport and ip_proto in RTM_GETROUTE")
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ipmr.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index f6275aa19b6a..d235478d9ca3 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2278,7 +2278,8 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb,
 			rcu_read_unlock();
 			return -ENODEV;
 		}
-		skb2 = skb_clone(skb, GFP_ATOMIC);
+
+		skb2 = skb_realloc_headroom(skb, sizeof(struct iphdr));
 		if (!skb2) {
 			read_unlock(&mrt_lock);
 			rcu_read_unlock();
-- 
2.20.1


From b5504236f7a03d616708388dc46a08746479d9c6 Mon Sep 17 00:00:00 2001
From: Chuhong Yuan <hslester96@gmail.com>
Date: Fri, 15 Nov 2019 14:24:54 +0800
Subject: [PATCH 3/6] net: gemini: add missed free_netdev

[ Upstream commit 18d647ae74116bfee38953978501cea2960a0c25 ]

This driver forgets to free allocated netdev in remove like
what is done in probe failure.
Add the free to fix it.

Signed-off-by: Chuhong Yuan <hslester96@gmail.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cortina/gemini.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index dfd1ad0b1cb9..4af78de0e077 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -2530,6 +2530,7 @@ static int gemini_ethernet_port_remove(struct platform_device *pdev)
 	struct gemini_ethernet_port *port = platform_get_drvdata(pdev);
 
 	gemini_port_remove(port);
+	free_netdev(port->netdev);
 	return 0;
 }
 
-- 
2.20.1


From 4247787deb1e141d13edf4315f2c243240efef73 Mon Sep 17 00:00:00 2001
From: Aleksander Morgado <aleksander@aleksander.es>
Date: Wed, 13 Nov 2019 11:11:10 +0100
Subject: [PATCH 4/6] net: usb: qmi_wwan: add support for Foxconn T77W968 LTE
 modules
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 802753cb0b141cf5170ab97fe7e79f5ca10d06b0 ]

These are the Foxconn-branded variants of the Dell DW5821e modules,
same USB layout as those.

The QMI interface is exposed in USB configuration #1:

P:  Vendor=0489 ProdID=e0b4 Rev=03.18
S:  Manufacturer=FII
S:  Product=T77W968 LTE
S:  SerialNumber=0123456789ABCDEF
C:  #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=500mA
I:  If#=0x0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
I:  If#=0x1 Alt= 0 #EPs= 1 Cls=03(HID  ) Sub=00 Prot=00 Driver=usbhid
I:  If#=0x2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
I:  If#=0x3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
I:  If#=0x4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
I:  If#=0x5 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option

Signed-off-by: Aleksander Morgado <aleksander@aleksander.es>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 9f037c50054d..b55fd76348f9 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1306,6 +1306,8 @@ static const struct usb_device_id products[] = {
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0191, 4)},	/* Quectel EG91 */
 	{QMI_FIXED_INTF(0x2c7c, 0x0296, 4)},	/* Quectel BG96 */
 	{QMI_QUIRK_SET_DTR(0x2cb7, 0x0104, 4)},	/* Fibocom NL678 series */
+	{QMI_FIXED_INTF(0x0489, 0xe0b4, 0)},	/* Foxconn T77W968 LTE */
+	{QMI_FIXED_INTF(0x0489, 0xe0b5, 0)},	/* Foxconn T77W968 LTE with eSIM support*/
 
 	/* 4. Gobi 1000 devices */
 	{QMI_GOBI1K_DEVICE(0x05c6, 0x9212)},	/* Acer Gobi Modem Device */
-- 
2.20.1


From 1bdcfbc8d9b00b6d8f448f7adec3eef37b59ad72 Mon Sep 17 00:00:00 2001
From: Jouni Hogander <jouni.hogander@unikie.com>
Date: Wed, 13 Nov 2019 13:45:02 +0200
Subject: [PATCH 5/6] slip: Fix memory leak in slip_open error path

[ Upstream commit 3b5a39979dafea9d0cd69c7ae06088f7a84cdafa ]

Driver/net/can/slcan.c is derived from slip.c. Memory leak was detected
by Syzkaller in slcan. Same issue exists in slip.c and this patch is
addressing the leak in slip.c.

Here is the slcan memory leak trace reported by Syzkaller:

BUG: memory leak unreferenced object 0xffff888067f65500 (size 4096):
  comm "syz-executor043", pid 454, jiffies 4294759719 (age 11.930s)
  hex dump (first 32 bytes):
    73 6c 63 61 6e 30 00 00 00 00 00 00 00 00 00 00 slcan0..........
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
  backtrace:
    [<00000000a06eec0d>] __kmalloc+0x18b/0x2c0
    [<0000000083306e66>] kvmalloc_node+0x3a/0xc0
    [<000000006ac27f87>] alloc_netdev_mqs+0x17a/0x1080
    [<0000000061a996c9>] slcan_open+0x3ae/0x9a0
    [<000000001226f0f9>] tty_ldisc_open.isra.1+0x76/0xc0
    [<0000000019289631>] tty_set_ldisc+0x28c/0x5f0
    [<000000004de5a617>] tty_ioctl+0x48d/0x1590
    [<00000000daef496f>] do_vfs_ioctl+0x1c7/0x1510
    [<0000000059068dbc>] ksys_ioctl+0x99/0xb0
    [<000000009a6eb334>] __x64_sys_ioctl+0x78/0xb0
    [<0000000053d0332e>] do_syscall_64+0x16f/0x580
    [<0000000021b83b99>] entry_SYSCALL_64_after_hwframe+0x44/0xa9
    [<000000008ea75434>] 0xfffffffffffffff

Cc: "David S. Miller" <davem@davemloft.net>
Cc: Oliver Hartkopp <socketcan@hartkopp.net>
Cc: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Signed-off-by: Jouni Hogander <jouni.hogander@unikie.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/slip/slip.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c
index b008266e91ea..a5874059da9d 100644
--- a/drivers/net/slip/slip.c
+++ b/drivers/net/slip/slip.c
@@ -855,6 +855,7 @@ static int slip_open(struct tty_struct *tty)
 	sl->tty = NULL;
 	tty->disc_data = NULL;
 	clear_bit(SLF_INUSE, &sl->flags);
+	free_netdev(sl->dev);
 
 err_exit:
 	rtnl_unlock();
-- 
2.20.1


From e9eb513d7b0542a3612708ba2686b56d036aa2ac Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sat, 9 Nov 2019 11:29:46 +0100
Subject: [PATCH 6/6] devlink: disallow reload operation during device cleanup

[ Upstream commit 5a508a254bed9a2e36a5fb96c9065532a6bf1e9c ]

There is a race between driver code that does setup/cleanup of device
and devlink reload operation that in some drivers works with the same
code. Use after free could we easily obtained by running:

while true; do
        echo "0000:00:10.0" >/sys/bus/pci/drivers/mlxsw_spectrum2/bind
        devlink dev reload pci/0000:00:10.0 &
        echo "0000:00:10.0" >/sys/bus/pci/drivers/mlxsw_spectrum2/unbind
done

Fix this by enabling reload only after setup of device is complete and
disabling it at the beginning of the cleanup process.

Reported-by: Ido Schimmel <idosch@mellanox.com>
Fixes: 2d8dc5bbf4e7 ("devlink: Add support for reload")
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/main.c  |  3 ++
 drivers/net/ethernet/mellanox/mlxsw/core.c |  4 +++
 drivers/net/netdevsim/netdev.c             |  5 +++
 include/net/devlink.h                      |  3 ++
 net/core/devlink.c                         | 39 +++++++++++++++++++++-
 5 files changed, 53 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 6a046030e873..fc0f58cd3ca2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -3982,6 +3982,7 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (ret)
 		goto err_params_unregister;
 
+	devlink_reload_enable(devlink);
 	pci_save_state(pdev);
 	return 0;
 
@@ -4093,6 +4094,8 @@ static void mlx4_remove_one(struct pci_dev *pdev)
 	struct devlink *devlink = priv_to_devlink(priv);
 	int active_vfs = 0;
 
+	devlink_reload_disable(devlink);
+
 	if (mlx4_is_slave(dev))
 		persist->interface_state |= MLX4_INTERFACE_STATE_NOWAIT;
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index 2e6df5804b35..717a39ebc305 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -1054,6 +1054,8 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 		if (err)
 			goto err_driver_init;
 	}
+	if (!reload)
+		devlink_reload_enable(devlink);
 
 	return 0;
 
@@ -1088,6 +1090,8 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core,
 {
 	struct devlink *devlink = priv_to_devlink(mlxsw_core);
 
+	if (!reload)
+		devlink_reload_disable(devlink);
 	if (mlxsw_core->reload_fail) {
 		if (!reload)
 			/* Only the parts that were not de-initialized in the
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index 8d8e2b3f263e..4dc1e9490112 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -23,6 +23,7 @@
 #include <net/pkt_cls.h>
 #include <net/rtnetlink.h>
 #include <net/switchdev.h>
+#include <net/devlink.h>
 
 #include "netdevsim.h"
 
@@ -221,6 +222,8 @@ static int nsim_init(struct net_device *dev)
 		goto err_unreg_dev;
 
 	nsim_ipsec_init(ns);
+	if (ns->devlink)
+		devlink_reload_enable(ns->devlink);
 
 	return 0;
 
@@ -243,6 +246,8 @@ static void nsim_uninit(struct net_device *dev)
 {
 	struct netdevsim *ns = netdev_priv(dev);
 
+	if (ns->devlink)
+		devlink_reload_disable(ns->devlink);
 	nsim_ipsec_teardown(ns);
 	nsim_devlink_teardown(ns);
 	debugfs_remove_recursive(ns->ddir);
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 99efc156a309..16fdec6b42d6 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -35,6 +35,7 @@ struct devlink {
 	struct device *dev;
 	possible_net_t _net;
 	struct mutex lock;
+	u8 reload_enabled:1;
 	char priv[0] __aligned(NETDEV_ALIGN);
 };
 
@@ -477,6 +478,8 @@ struct ib_device;
 struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size);
 int devlink_register(struct devlink *devlink, struct device *dev);
 void devlink_unregister(struct devlink *devlink);
+void devlink_reload_enable(struct devlink *devlink);
+void devlink_reload_disable(struct devlink *devlink);
 void devlink_free(struct devlink *devlink);
 int devlink_port_register(struct devlink *devlink,
 			  struct devlink_port *devlink_port,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 6bc42933be4a..d413fe912eb3 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -2643,7 +2643,7 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info)
 	struct devlink *devlink = info->user_ptr[0];
 	int err;
 
-	if (!devlink->ops->reload)
+	if (!devlink->ops->reload || !devlink->reload_enabled)
 		return -EOPNOTSUPP;
 
 	err = devlink_resources_validate(devlink, NULL, info);
@@ -3889,12 +3889,49 @@ EXPORT_SYMBOL_GPL(devlink_register);
 void devlink_unregister(struct devlink *devlink)
 {
 	mutex_lock(&devlink_mutex);
+	WARN_ON(devlink->ops->reload &&
+		devlink->reload_enabled);
 	devlink_notify(devlink, DEVLINK_CMD_DEL);
 	list_del(&devlink->list);
 	mutex_unlock(&devlink_mutex);
 }
 EXPORT_SYMBOL_GPL(devlink_unregister);
 
+/**
+ *	devlink_reload_enable - Enable reload of devlink instance
+ *
+ *	@devlink: devlink
+ *
+ *	Should be called at end of device initialization
+ *	process when reload operation is supported.
+ */
+void devlink_reload_enable(struct devlink *devlink)
+{
+	mutex_lock(&devlink_mutex);
+	devlink->reload_enabled = true;
+	mutex_unlock(&devlink_mutex);
+}
+EXPORT_SYMBOL_GPL(devlink_reload_enable);
+
+/**
+ *	devlink_reload_disable - Disable reload of devlink instance
+ *
+ *	@devlink: devlink
+ *
+ *	Should be called at the beginning of device cleanup
+ *	process when reload operation is supported.
+ */
+void devlink_reload_disable(struct devlink *devlink)
+{
+	mutex_lock(&devlink_mutex);
+	/* Mutex is taken which ensures that no reload operation is in
+	 * progress while setting up forbidded flag.
+	 */
+	devlink->reload_enabled = false;
+	mutex_unlock(&devlink_mutex);
+}
+EXPORT_SYMBOL_GPL(devlink_reload_disable);
+
 /**
  *	devlink_free - Free devlink instance resources
  *
-- 
2.20.1


[-- Attachment #3: net_53.mbox --]
[-- Type: Application/Octet-Stream, Size: 26925 bytes --]

From 2bf345ec011b25a7b9a41c50afd089bb46c5f042 Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.com>
Date: Thu, 14 Nov 2019 11:16:01 +0100
Subject: [PATCH 01/12] ax88172a: fix information leak on short answers

[ Upstream commit a9a51bd727d141a67b589f375fe69d0e54c4fe22 ]

If a malicious device gives a short MAC it can elicit up to
5 bytes of leaked memory out of the driver. We need to check for
ETH_ALEN instead.

Reported-by: syzbot+a8d4acdad35e6bbca308@syzkaller.appspotmail.com
Signed-off-by: Oliver Neukum <oneukum@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/ax88172a.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/usb/ax88172a.c b/drivers/net/usb/ax88172a.c
index 011bd4cb546e..af3994e0853b 100644
--- a/drivers/net/usb/ax88172a.c
+++ b/drivers/net/usb/ax88172a.c
@@ -196,7 +196,7 @@ static int ax88172a_bind(struct usbnet *dev, struct usb_interface *intf)
 
 	/* Get the MAC address */
 	ret = asix_read_cmd(dev, AX_CMD_READ_NODE_ID, 0, 0, ETH_ALEN, buf, 0);
-	if (ret < 0) {
+	if (ret < ETH_ALEN) {
 		netdev_err(dev->net, "Failed to read MAC address: %d\n", ret);
 		goto free;
 	}
-- 
2.20.1


From 86ce1dee2d6ccbef9a3dc5997ae12905509caca2 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sat, 9 Nov 2019 11:29:46 +0100
Subject: [PATCH 02/12] devlink: disallow reload operation during device
 cleanup

[ Upstream commit 5a508a254bed9a2e36a5fb96c9065532a6bf1e9c ]

There is a race between driver code that does setup/cleanup of device
and devlink reload operation that in some drivers works with the same
code. Use after free could we easily obtained by running:

while true; do
        echo "0000:00:10.0" >/sys/bus/pci/drivers/mlxsw_spectrum2/bind
        devlink dev reload pci/0000:00:10.0 &
        echo "0000:00:10.0" >/sys/bus/pci/drivers/mlxsw_spectrum2/unbind
done

Fix this by enabling reload only after setup of device is complete and
disabling it at the beginning of the cleanup process.

Reported-by: Ido Schimmel <idosch@mellanox.com>
Fixes: 2d8dc5bbf4e7 ("devlink: Add support for reload")
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/main.c  |  3 ++
 drivers/net/ethernet/mellanox/mlxsw/core.c |  6 +++-
 drivers/net/netdevsim/dev.c                |  2 ++
 include/net/devlink.h                      |  3 ++
 net/core/devlink.c                         | 39 +++++++++++++++++++++-
 5 files changed, 51 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 309470ec0219..d3654c35d2dd 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -3982,6 +3982,7 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto err_params_unregister;
 
 	devlink_params_publish(devlink);
+	devlink_reload_enable(devlink);
 	pci_save_state(pdev);
 	return 0;
 
@@ -4093,6 +4094,8 @@ static void mlx4_remove_one(struct pci_dev *pdev)
 	struct devlink *devlink = priv_to_devlink(priv);
 	int active_vfs = 0;
 
+	devlink_reload_disable(devlink);
+
 	if (mlx4_is_slave(dev))
 		persist->interface_state |= MLX4_INTERFACE_STATE_NOWAIT;
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index b94cdbd7bb18..92ea4a289429 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -1128,8 +1128,10 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 	if (err)
 		goto err_thermal_init;
 
-	if (mlxsw_driver->params_register)
+	if (mlxsw_driver->params_register) {
 		devlink_params_publish(devlink);
+		devlink_reload_enable(devlink);
+	}
 
 	return 0;
 
@@ -1191,6 +1193,8 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core,
 {
 	struct devlink *devlink = priv_to_devlink(mlxsw_core);
 
+	if (!reload)
+		devlink_reload_disable(devlink);
 	if (mlxsw_core->reload_fail) {
 		if (!reload)
 			/* Only the parts that were not de-initialized in the
diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index bcc40a236624..b2fe271a4f5d 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -297,6 +297,7 @@ nsim_dev_create(struct nsim_bus_dev *nsim_bus_dev, unsigned int port_count)
 	if (err)
 		goto err_debugfs_exit;
 
+	devlink_reload_enable(devlink);
 	return nsim_dev;
 
 err_debugfs_exit:
@@ -314,6 +315,7 @@ static void nsim_dev_destroy(struct nsim_dev *nsim_dev)
 {
 	struct devlink *devlink = priv_to_devlink(nsim_dev);
 
+	devlink_reload_disable(devlink);
 	nsim_bpf_dev_exit(nsim_dev);
 	nsim_dev_debugfs_exit(nsim_dev);
 	devlink_unregister(devlink);
diff --git a/include/net/devlink.h b/include/net/devlink.h
index bc36f942a7d5..ffa506ae5018 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -35,6 +35,7 @@ struct devlink {
 	struct device *dev;
 	possible_net_t _net;
 	struct mutex lock;
+	u8 reload_enabled:1;
 	char priv[0] __aligned(NETDEV_ALIGN);
 };
 
@@ -594,6 +595,8 @@ struct ib_device;
 struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size);
 int devlink_register(struct devlink *devlink, struct device *dev);
 void devlink_unregister(struct devlink *devlink);
+void devlink_reload_enable(struct devlink *devlink);
+void devlink_reload_disable(struct devlink *devlink);
 void devlink_free(struct devlink *devlink);
 int devlink_port_register(struct devlink *devlink,
 			  struct devlink_port *devlink_port,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 4f40aeace902..707d160cc6ea 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -2677,7 +2677,7 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info)
 	struct devlink *devlink = info->user_ptr[0];
 	int err;
 
-	if (!devlink->ops->reload)
+	if (!devlink->ops->reload || !devlink->reload_enabled)
 		return -EOPNOTSUPP;
 
 	err = devlink_resources_validate(devlink, NULL, info);
@@ -5559,12 +5559,49 @@ EXPORT_SYMBOL_GPL(devlink_register);
 void devlink_unregister(struct devlink *devlink)
 {
 	mutex_lock(&devlink_mutex);
+	WARN_ON(devlink_reload_supported(devlink) &&
+		devlink->reload_enabled);
 	devlink_notify(devlink, DEVLINK_CMD_DEL);
 	list_del(&devlink->list);
 	mutex_unlock(&devlink_mutex);
 }
 EXPORT_SYMBOL_GPL(devlink_unregister);
 
+/**
+ *	devlink_reload_enable - Enable reload of devlink instance
+ *
+ *	@devlink: devlink
+ *
+ *	Should be called at end of device initialization
+ *	process when reload operation is supported.
+ */
+void devlink_reload_enable(struct devlink *devlink)
+{
+	mutex_lock(&devlink_mutex);
+	devlink->reload_enabled = true;
+	mutex_unlock(&devlink_mutex);
+}
+EXPORT_SYMBOL_GPL(devlink_reload_enable);
+
+/**
+ *	devlink_reload_disable - Disable reload of devlink instance
+ *
+ *	@devlink: devlink
+ *
+ *	Should be called at the beginning of device cleanup
+ *	process when reload operation is supported.
+ */
+void devlink_reload_disable(struct devlink *devlink)
+{
+	mutex_lock(&devlink_mutex);
+	/* Mutex is taken which ensures that no reload operation is in
+	 * progress while setting up forbidded flag.
+	 */
+	devlink->reload_enabled = false;
+	mutex_unlock(&devlink_mutex);
+}
+EXPORT_SYMBOL_GPL(devlink_reload_disable);
+
 /**
  *	devlink_free - Free devlink instance resources
  *
-- 
2.20.1


From ebb9553784b5b299413fbff11739de17f9276a1f Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Fri, 15 Nov 2019 18:29:52 +0100
Subject: [PATCH 03/12] ipmr: Fix skb headroom in ipmr_get_route().

[ Upstream commit 7901cd97963d6cbde88fa25a4a446db3554c16c6 ]

In route.c, inet_rtm_getroute_build_skb() creates an skb with no
headroom. This skb is then used by inet_rtm_getroute() which may pass
it to rt_fill_info() and, from there, to ipmr_get_route(). The later
might try to reuse this skb by cloning it and prepending an IPv4
header. But since the original skb has no headroom, skb_push() triggers
skb_under_panic():

skbuff: skb_under_panic: text:00000000ca46ad8a len:80 put:20 head:00000000cd28494e data:000000009366fd6b tail:0x3c end:0xec0 dev:veth0
------------[ cut here ]------------
kernel BUG at net/core/skbuff.c:108!
invalid opcode: 0000 [#1] SMP KASAN PTI
CPU: 6 PID: 587 Comm: ip Not tainted 5.4.0-rc6+ #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-2.fc30 04/01/2014
RIP: 0010:skb_panic+0xbf/0xd0
Code: 41 a2 ff 8b 4b 70 4c 8b 4d d0 48 c7 c7 20 76 f5 8b 44 8b 45 bc 48 8b 55 c0 48 8b 75 c8 41 54 41 57 41 56 41 55 e8 75 dc 7a ff <0f> 0b 0f 1f 44 00 00 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00
RSP: 0018:ffff888059ddf0b0 EFLAGS: 00010286
RAX: 0000000000000086 RBX: ffff888060a315c0 RCX: ffffffff8abe4822
RDX: 0000000000000000 RSI: 0000000000000008 RDI: ffff88806c9a79cc
RBP: ffff888059ddf118 R08: ffffed100d9361b1 R09: ffffed100d9361b0
R10: ffff88805c68aee3 R11: ffffed100d9361b1 R12: ffff88805d218000
R13: ffff88805c689fec R14: 000000000000003c R15: 0000000000000ec0
FS:  00007f6af184b700(0000) GS:ffff88806c980000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007ffc8204a000 CR3: 0000000057b40006 CR4: 0000000000360ee0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 skb_push+0x7e/0x80
 ipmr_get_route+0x459/0x6fa
 rt_fill_info+0x692/0x9f0
 inet_rtm_getroute+0xd26/0xf20
 rtnetlink_rcv_msg+0x45d/0x630
 netlink_rcv_skb+0x1a5/0x220
 rtnetlink_rcv+0x15/0x20
 netlink_unicast+0x305/0x3a0
 netlink_sendmsg+0x575/0x730
 sock_sendmsg+0xb5/0xc0
 ___sys_sendmsg+0x497/0x4f0
 __sys_sendmsg+0xcb/0x150
 __x64_sys_sendmsg+0x48/0x50
 do_syscall_64+0xd2/0xac0
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Actually the original skb used to have enough headroom, but the
reserve_skb() call was lost with the introduction of
inet_rtm_getroute_build_skb() by commit 404eb77ea766 ("ipv4: support
sport, dport and ip_proto in RTM_GETROUTE").

We could reserve some headroom again in inet_rtm_getroute_build_skb(),
but this function shouldn't be responsible for handling the special
case of ipmr_get_route(). Let's handle that directly in
ipmr_get_route() by calling skb_realloc_headroom() instead of
skb_clone().

Fixes: 404eb77ea766 ("ipv4: support sport, dport and ip_proto in RTM_GETROUTE")
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ipmr.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index c07bc82cbbe9..f2daddf1afac 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2289,7 +2289,8 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb,
 			rcu_read_unlock();
 			return -ENODEV;
 		}
-		skb2 = skb_clone(skb, GFP_ATOMIC);
+
+		skb2 = skb_realloc_headroom(skb, sizeof(struct iphdr));
 		if (!skb2) {
 			read_unlock(&mrt_lock);
 			rcu_read_unlock();
-- 
2.20.1


From 9bd49da48c620d719a8b6e8336c56bfac6ed1e1f Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sun, 10 Nov 2019 16:31:23 +0100
Subject: [PATCH 04/12] mlxsw: core: Enable devlink reload only on probe

[ Upstream commit 73a533ecf0af5f73ff72dd7c96d1c8598ca93649 ]

Call devlink enable only during probe time and avoid deadlock
during reload.

Reported-by: Shalom Toledo <shalomt@mellanox.com>
Fixes: 5a508a254bed ("devlink: disallow reload operation during device cleanup")
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Tested-by: Shalom Toledo <shalomt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/core.c | 5 +++--
 net/core/devlink.c                         | 2 +-
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index 92ea4a289429..6e8e7ca7ac76 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -1128,10 +1128,11 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 	if (err)
 		goto err_thermal_init;
 
-	if (mlxsw_driver->params_register) {
+	if (mlxsw_driver->params_register)
 		devlink_params_publish(devlink);
+
+	if (!reload)
 		devlink_reload_enable(devlink);
-	}
 
 	return 0;
 
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 707d160cc6ea..f5994f2a6457 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -5559,7 +5559,7 @@ EXPORT_SYMBOL_GPL(devlink_register);
 void devlink_unregister(struct devlink *devlink)
 {
 	mutex_lock(&devlink_mutex);
-	WARN_ON(devlink_reload_supported(devlink) &&
+	WARN_ON(devlink->ops->reload &&
 		devlink->reload_enabled);
 	devlink_notify(devlink, DEVLINK_CMD_DEL);
 	list_del(&devlink->list);
-- 
2.20.1


From 116afc87ef66e30993114d1cdd9a76f5a74c284f Mon Sep 17 00:00:00 2001
From: Chuhong Yuan <hslester96@gmail.com>
Date: Fri, 15 Nov 2019 14:24:54 +0800
Subject: [PATCH 05/12] net: gemini: add missed free_netdev

[ Upstream commit 18d647ae74116bfee38953978501cea2960a0c25 ]

This driver forgets to free allocated netdev in remove like
what is done in probe failure.
Add the free to fix it.

Signed-off-by: Chuhong Yuan <hslester96@gmail.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cortina/gemini.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index 9003eb6716cd..01e23a922982 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -2527,6 +2527,7 @@ static int gemini_ethernet_port_remove(struct platform_device *pdev)
 	struct gemini_ethernet_port *port = platform_get_drvdata(pdev);
 
 	gemini_port_remove(port);
+	free_netdev(port->netdev);
 	return 0;
 }
 
-- 
2.20.1


From ec3d7667ea8f45590c4b44c5eab793c1211d8abf Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.ibm.com>
Date: Fri, 15 Nov 2019 12:39:30 +0100
Subject: [PATCH 06/12] net/smc: fix fastopen for non-blocking connect()

[ Upstream commit 8204df72bea1a7d83d0777add6da98a41dfbdc34 ]

FASTOPEN does not work with SMC-sockets. Since SMC allows fallback to
TCP native during connection start, the FASTOPEN setsockopts trigger
this fallback, if the SMC-socket is still in state SMC_INIT.
But if a FASTOPEN setsockopt is called after a non-blocking connect(),
this is broken, and fallback does not make sense.
This change complements
commit cd2063604ea6 ("net/smc: avoid fallback in case of non-blocking connect")
and fixes the syzbot reported problem "WARNING in smc_unhash_sk".

Reported-by: syzbot+8488cc4cf1c9e09b8b86@syzkaller.appspotmail.com
Fixes: e1bbdd570474 ("net/smc: reduce sock_put() for fallback sockets")
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/af_smc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 47946f489fd4..5aec060a8581 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1731,7 +1731,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
 	case TCP_FASTOPEN_KEY:
 	case TCP_FASTOPEN_NO_COOKIE:
 		/* option not supported by SMC */
-		if (sk->sk_state == SMC_INIT) {
+		if (sk->sk_state == SMC_INIT && !smc->connect_nonblock) {
 			smc_switch_to_fallback(smc);
 			smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP;
 		} else {
-- 
2.20.1


From 4ec2975a2cab3db35ba72ded65c5ead1d8a0f269 Mon Sep 17 00:00:00 2001
From: Aleksander Morgado <aleksander@aleksander.es>
Date: Wed, 13 Nov 2019 11:11:10 +0100
Subject: [PATCH 07/12] net: usb: qmi_wwan: add support for Foxconn T77W968 LTE
 modules
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 802753cb0b141cf5170ab97fe7e79f5ca10d06b0 ]

These are the Foxconn-branded variants of the Dell DW5821e modules,
same USB layout as those.

The QMI interface is exposed in USB configuration #1:

P:  Vendor=0489 ProdID=e0b4 Rev=03.18
S:  Manufacturer=FII
S:  Product=T77W968 LTE
S:  SerialNumber=0123456789ABCDEF
C:  #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=500mA
I:  If#=0x0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
I:  If#=0x1 Alt= 0 #EPs= 1 Cls=03(HID  ) Sub=00 Prot=00 Driver=usbhid
I:  If#=0x2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
I:  If#=0x3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
I:  If#=0x4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
I:  If#=0x5 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option

Signed-off-by: Aleksander Morgado <aleksander@aleksander.es>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index ba682bba7851..44aee7a431ea 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1370,6 +1370,8 @@ static const struct usb_device_id products[] = {
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0191, 4)},	/* Quectel EG91 */
 	{QMI_FIXED_INTF(0x2c7c, 0x0296, 4)},	/* Quectel BG96 */
 	{QMI_QUIRK_SET_DTR(0x2cb7, 0x0104, 4)},	/* Fibocom NL678 series */
+	{QMI_FIXED_INTF(0x0489, 0xe0b4, 0)},	/* Foxconn T77W968 LTE */
+	{QMI_FIXED_INTF(0x0489, 0xe0b5, 0)},	/* Foxconn T77W968 LTE with eSIM support*/
 
 	/* 4. Gobi 1000 devices */
 	{QMI_GOBI1K_DEVICE(0x05c6, 0x9212)},	/* Acer Gobi Modem Device */
-- 
2.20.1


From 4094add62e40055b255626dce5165b8defdc9272 Mon Sep 17 00:00:00 2001
From: Jouni Hogander <jouni.hogander@unikie.com>
Date: Wed, 13 Nov 2019 13:45:02 +0200
Subject: [PATCH 08/12] slip: Fix memory leak in slip_open error path

[ Upstream commit 3b5a39979dafea9d0cd69c7ae06088f7a84cdafa ]

Driver/net/can/slcan.c is derived from slip.c. Memory leak was detected
by Syzkaller in slcan. Same issue exists in slip.c and this patch is
addressing the leak in slip.c.

Here is the slcan memory leak trace reported by Syzkaller:

BUG: memory leak unreferenced object 0xffff888067f65500 (size 4096):
  comm "syz-executor043", pid 454, jiffies 4294759719 (age 11.930s)
  hex dump (first 32 bytes):
    73 6c 63 61 6e 30 00 00 00 00 00 00 00 00 00 00 slcan0..........
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
  backtrace:
    [<00000000a06eec0d>] __kmalloc+0x18b/0x2c0
    [<0000000083306e66>] kvmalloc_node+0x3a/0xc0
    [<000000006ac27f87>] alloc_netdev_mqs+0x17a/0x1080
    [<0000000061a996c9>] slcan_open+0x3ae/0x9a0
    [<000000001226f0f9>] tty_ldisc_open.isra.1+0x76/0xc0
    [<0000000019289631>] tty_set_ldisc+0x28c/0x5f0
    [<000000004de5a617>] tty_ioctl+0x48d/0x1590
    [<00000000daef496f>] do_vfs_ioctl+0x1c7/0x1510
    [<0000000059068dbc>] ksys_ioctl+0x99/0xb0
    [<000000009a6eb334>] __x64_sys_ioctl+0x78/0xb0
    [<0000000053d0332e>] do_syscall_64+0x16f/0x580
    [<0000000021b83b99>] entry_SYSCALL_64_after_hwframe+0x44/0xa9
    [<000000008ea75434>] 0xfffffffffffffff

Cc: "David S. Miller" <davem@davemloft.net>
Cc: Oliver Hartkopp <socketcan@hartkopp.net>
Cc: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Signed-off-by: Jouni Hogander <jouni.hogander@unikie.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/slip/slip.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c
index cac64b96d545..4d479e3c817d 100644
--- a/drivers/net/slip/slip.c
+++ b/drivers/net/slip/slip.c
@@ -855,6 +855,7 @@ static int slip_open(struct tty_struct *tty)
 	sl->tty = NULL;
 	tty->disc_data = NULL;
 	clear_bit(SLF_INUSE, &sl->flags);
+	free_netdev(sl->dev);
 
 err_exit:
 	rtnl_unlock();
-- 
2.20.1


From beddf1edcb641611a8279cef07c679b2ac0a3004 Mon Sep 17 00:00:00 2001
From: Tony Lu <tonylu@linux.alibaba.com>
Date: Sat, 9 Nov 2019 18:43:06 +0800
Subject: [PATCH 09/12] tcp: remove redundant new line from tcp_event_sk_skb

[ Upstream commit dd3d792def0d4f33bbf319982b1878b0c8aaca34 ]

This removes '\n' from trace event class tcp_event_sk_skb to avoid
redundant new blank line and make output compact.

Fixes: af4325ecc24f ("tcp: expose sk_state in tcp_retransmit_skb tracepoint")
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Tony Lu <tonylu@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/trace/events/tcp.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h
index 2bc9960a31aa..cf97f6339acb 100644
--- a/include/trace/events/tcp.h
+++ b/include/trace/events/tcp.h
@@ -86,7 +86,7 @@ DECLARE_EVENT_CLASS(tcp_event_sk_skb,
 			      sk->sk_v6_rcv_saddr, sk->sk_v6_daddr);
 	),
 
-	TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c state=%s\n",
+	TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c state=%s",
 		  __entry->sport, __entry->dport, __entry->saddr, __entry->daddr,
 		  __entry->saddr_v6, __entry->daddr_v6,
 		  show_tcp_state_name(__entry->state))
-- 
2.20.1


From c8a7004c77a9eae4fcf58843220f13ba8c94d61d Mon Sep 17 00:00:00 2001
From: Ioana Ciornei <ioana.ciornei@nxp.com>
Date: Tue, 12 Nov 2019 18:21:52 +0200
Subject: [PATCH 10/12] dpaa2-eth: free already allocated channels on probe
 defer

[ Upstream commit 5aa4277d4368c099223bbcd3a9086f3351a12ce9 ]

The setup_dpio() function tries to allocate a number of channels equal
to the number of CPUs online. When there are not enough DPCON objects
already probed, the function will return EPROBE_DEFER. When this
happens, the already allocated channels are not freed. This results in
the incapacity of properly probing the next time around.
Fix this by freeing the channels on the error path.

Fixes: d7f5a9d89a55 ("dpaa2-eth: defer probe on object allocate")
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 0acb11557ed1..5d2da74e2306 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -2166,8 +2166,16 @@ static int setup_dpio(struct dpaa2_eth_priv *priv)
 err_service_reg:
 	free_channel(priv, channel);
 err_alloc_ch:
-	if (err == -EPROBE_DEFER)
+	if (err == -EPROBE_DEFER) {
+		for (i = 0; i < priv->num_channels; i++) {
+			channel = priv->channel[i];
+			nctx = &channel->nctx;
+			dpaa2_io_service_deregister(channel->dpio, nctx, dev);
+			free_channel(priv, channel);
+		}
+		priv->num_channels = 0;
 		return err;
+	}
 
 	if (cpumask_empty(&priv->dpio_cpumask)) {
 		dev_err(dev, "No cpu with an affine DPIO/DPCON\n");
-- 
2.20.1


From a18eec382a29b72e04527c343dab0059735c7a0c Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Sun, 10 Nov 2019 14:11:56 +0200
Subject: [PATCH 11/12] devlink: Add method for time-stamp on reporter's dump

[ Upstream commit d279505b723cba058b604ed8cf9cd4c854e2a041 ]

When setting the dump's time-stamp, use ktime_get_real in addition to
jiffies. This simplifies the user space implementation and bypasses
some inconsistent behavior with translating jiffies to current time.
The time taken is transformed into nsec, to comply with y2038 issue.

Fixes: c8e1da0bf923 ("devlink: Add health report functionality")
Signed-off-by: Aya Levin <ayal@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/devlink.h | 1 +
 net/core/devlink.c           | 6 ++++++
 2 files changed, 7 insertions(+)

diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index ffc993256527..f0953046bc17 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -348,6 +348,7 @@ enum devlink_attr {
 	DEVLINK_ATTR_PORT_PCI_PF_NUMBER,	/* u16 */
 	DEVLINK_ATTR_PORT_PCI_VF_NUMBER,	/* u16 */
 
+	DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS_NS,	/* u64 */
 	/* add new attributes above here, update the policy in devlink.c */
 
 	__DEVLINK_ATTR_MAX,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index f5994f2a6457..d40f6cc48690 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -4577,6 +4577,7 @@ struct devlink_health_reporter {
 	bool auto_recover;
 	u8 health_state;
 	u64 dump_ts;
+	u64 dump_real_ts;
 	u64 error_count;
 	u64 recovery_count;
 	u64 last_recovery_ts;
@@ -4749,6 +4750,7 @@ static int devlink_health_do_dump(struct devlink_health_reporter *reporter,
 		goto dump_err;
 
 	reporter->dump_ts = jiffies;
+	reporter->dump_real_ts = ktime_get_real_ns();
 
 	return 0;
 
@@ -4911,6 +4913,10 @@ devlink_nl_health_reporter_fill(struct sk_buff *msg,
 			      jiffies_to_msecs(reporter->dump_ts),
 			      DEVLINK_ATTR_PAD))
 		goto reporter_nest_cancel;
+	if (reporter->dump_fmsg &&
+	    nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS_NS,
+			      reporter->dump_real_ts, DEVLINK_ATTR_PAD))
+		goto reporter_nest_cancel;
 
 	nla_nest_end(msg, reporter_attr);
 	genlmsg_end(msg, hdr);
-- 
2.20.1


From b528615156750d1cefda56c0a5e4f26bf2005893 Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.ibm.com>
Date: Tue, 12 Nov 2019 16:03:41 +0100
Subject: [PATCH 12/12] net/smc: fix refcount non-blocking connect() -part 2

[ Upstream commit 6d6dd528d5af05dc2d0c773951ed68d630a0c3f1 ]

If an SMC socket is immediately terminated after a non-blocking connect()
has been called, a memory leak is possible.
Due to the sock_hold move in
commit 301428ea3708 ("net/smc: fix refcounting for non-blocking connect()")
an extra sock_put() is needed in smc_connect_work(), if the internal
TCP socket is aborted and cancels the sk_stream_wait_connect() of the
connect worker.

Reported-by: syzbot+4b73ad6fc767e576e275@syzkaller.appspotmail.com
Fixes: 301428ea3708 ("net/smc: fix refcounting for non-blocking connect()")
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/af_smc.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 5aec060a8581..737b49909a7a 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -796,6 +796,7 @@ static void smc_connect_work(struct work_struct *work)
 			smc->sk.sk_err = EPIPE;
 		else if (signal_pending(current))
 			smc->sk.sk_err = -sock_intr_errno(timeo);
+		sock_put(&smc->sk); /* passive closing */
 		goto out;
 	}
 
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Mon, Nov 18, 2019 at 12:08:01AM -0800, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.19 and
> v5.3 -stable, respectively.
> 
> Thank you.


All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 106 bytes --]


Please queue up the following networking bug fixes for v4.19 and v5.3
-stable, respectively.

Thank you!

[-- Attachment #2: net_419.mbox --]
[-- Type: Application/Octet-Stream, Size: 31388 bytes --]

From 042ad5ab0b3001fa50f8a0e64bb79c42c85434c3 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 18 Nov 2019 09:18:42 +0200
Subject: [PATCH 01/10] mlxsw: spectrum_router: Fix determining underlay for a
 GRE tunnel

[ Upstream commit 1fc1657775dc1b19e9ac1d46b4054ed8ae5d99ab ]

The helper mlxsw_sp_ipip_dev_ul_tb_id() determines the underlay VRF of a
GRE tunnel. For a tunnel without a bound device, it uses the same VRF that
the tunnel is in. However in Linux, a GRE tunnel without a bound device
uses the main VRF as the underlay. Fix the function accordingly.

mlxsw further assumed that moving a tunnel to a different VRF could cause
conflict in local tunnel endpoint address, which cannot be offloaded.
However, the only way that an underlay could be changed by moving the
tunnel device itself is if the tunnel device does not have a bound device.
But in that case the underlay is always the main VRF, so there is no
opportunity to introduce a conflict by moving such device. Thus this check
constitutes a dead code, and can be removed, which do.

Fixes: 6ddb7426a7d4 ("mlxsw: spectrum_router: Introduce loopback RIFs")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/spectrum_router.c | 19 +------------------
 1 file changed, 1 insertion(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 2ab9cf25a08a..3f54b3ca38ba 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -970,7 +970,7 @@ u32 mlxsw_sp_ipip_dev_ul_tb_id(const struct net_device *ol_dev)
 	if (d)
 		return l3mdev_fib_table(d) ? : RT_TABLE_MAIN;
 	else
-		return l3mdev_fib_table(ol_dev) ? : RT_TABLE_MAIN;
+		return RT_TABLE_MAIN;
 }
 
 static struct mlxsw_sp_rif *
@@ -1532,27 +1532,10 @@ static int mlxsw_sp_netdevice_ipip_ol_vrf_event(struct mlxsw_sp *mlxsw_sp,
 {
 	struct mlxsw_sp_ipip_entry *ipip_entry =
 		mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, ol_dev);
-	enum mlxsw_sp_l3proto ul_proto;
-	union mlxsw_sp_l3addr saddr;
-	u32 ul_tb_id;
 
 	if (!ipip_entry)
 		return 0;
 
-	/* For flat configuration cases, moving overlay to a different VRF might
-	 * cause local address conflict, and the conflicting tunnels need to be
-	 * demoted.
-	 */
-	ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(ol_dev);
-	ul_proto = mlxsw_sp->router->ipip_ops_arr[ipip_entry->ipipt]->ul_proto;
-	saddr = mlxsw_sp_ipip_netdev_saddr(ul_proto, ol_dev);
-	if (mlxsw_sp_ipip_demote_tunnel_by_saddr(mlxsw_sp, ul_proto,
-						 saddr, ul_tb_id,
-						 ipip_entry)) {
-		mlxsw_sp_ipip_entry_demote_tunnel(mlxsw_sp, ipip_entry);
-		return 0;
-	}
-
 	return __mlxsw_sp_ipip_entry_update_tunnel(mlxsw_sp, ipip_entry,
 						   true, false, false, extack);
 }
-- 
2.20.1


From 20b7370f4f4c156013a89bf31e1aef95b4b91442 Mon Sep 17 00:00:00 2001
From: Luigi Rizzo <lrizzo@google.com>
Date: Fri, 15 Nov 2019 12:12:25 -0800
Subject: [PATCH 02/10] net/mlx4_en: fix mlx4 ethtool -N insertion

[ Upstream commit 34e59836565e36fade1464e054a3551c1a0364be ]

ethtool expects ETHTOOL_GRXCLSRLALL to set ethtool_rxnfc->data with the
total number of entries in the rx classifier table.  Surprisingly, mlx4
is missing this part (in principle ethtool could still move forward and
try the insert).

Tested: compiled and run command:
	phh13:~# ethtool -N eth1 flow-type udp4  queue 4
	Added rule with ID 255

Signed-off-by: Luigi Rizzo <lrizzo@google.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 94c59939a8cf..949ec70b6c13 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1745,6 +1745,7 @@ static int mlx4_en_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 		err = mlx4_en_get_flow(dev, cmd, cmd->fs.location);
 		break;
 	case ETHTOOL_GRXCLSRLALL:
+		cmd->data = MAX_NUM_OF_FS_RULES;
 		while ((!err || err == -ENOENT) && priority < cmd->rule_cnt) {
 			err = mlx4_en_get_flow(dev, cmd, i);
 			if (!err)
-- 
2.20.1


From 81916ddaffa1e65b13f3700ba0fd383d4daed355 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Mon, 18 Nov 2019 11:41:04 +0200
Subject: [PATCH 03/10] net/mlx4_en: Fix wrong limitation for number of TX
 rings

[ Upstream commit 2744bf42680f64ebf2ee8a00354897857c073331 ]

XDP_TX rings should not be limited by max_num_tx_rings_p_up.
To make sure total number of TX rings never exceed MAX_TX_RINGS,
add similar check in mlx4_en_alloc_tx_queue_per_tc(), where
a new value is assigned for num_up.

Fixes: 7e1dc5e926d5 ("net/mlx4_en: Limit the number of TX rings")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 8 ++++----
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c  | 9 +++++++++
 2 files changed, 13 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 949ec70b6c13..e639a365ac2d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1812,6 +1812,7 @@ static int mlx4_en_set_channels(struct net_device *dev,
 	struct mlx4_en_dev *mdev = priv->mdev;
 	struct mlx4_en_port_profile new_prof;
 	struct mlx4_en_priv *tmp;
+	int total_tx_count;
 	int port_up = 0;
 	int xdp_count;
 	int err = 0;
@@ -1826,13 +1827,12 @@ static int mlx4_en_set_channels(struct net_device *dev,
 
 	mutex_lock(&mdev->state_lock);
 	xdp_count = priv->tx_ring_num[TX_XDP] ? channel->rx_count : 0;
-	if (channel->tx_count * priv->prof->num_up + xdp_count >
-	    priv->mdev->profile.max_num_tx_rings_p_up * priv->prof->num_up) {
+	total_tx_count = channel->tx_count * priv->prof->num_up + xdp_count;
+	if (total_tx_count > MAX_TX_RINGS) {
 		err = -EINVAL;
 		en_err(priv,
 		       "Total number of TX and XDP rings (%d) exceeds the maximum supported (%d)\n",
-		       channel->tx_count * priv->prof->num_up  + xdp_count,
-		       MAX_TX_RINGS);
+		       total_tx_count, MAX_TX_RINGS);
 		goto out;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 0d7fd3f043cf..5868ec11db1a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -92,6 +92,7 @@ int mlx4_en_alloc_tx_queue_per_tc(struct net_device *dev, u8 tc)
 	struct mlx4_en_dev *mdev = priv->mdev;
 	struct mlx4_en_port_profile new_prof;
 	struct mlx4_en_priv *tmp;
+	int total_count;
 	int port_up = 0;
 	int err = 0;
 
@@ -105,6 +106,14 @@ int mlx4_en_alloc_tx_queue_per_tc(struct net_device *dev, u8 tc)
 				      MLX4_EN_NUM_UP_HIGH;
 	new_prof.tx_ring_num[TX] = new_prof.num_tx_rings_p_up *
 				   new_prof.num_up;
+	total_count = new_prof.tx_ring_num[TX] + new_prof.tx_ring_num[TX_XDP];
+	if (total_count > MAX_TX_RINGS) {
+		err = -EINVAL;
+		en_err(priv,
+		       "Total number of TX and XDP rings (%d) exceeds the maximum supported (%d)\n",
+		       total_count, MAX_TX_RINGS);
+		goto out;
+	}
 	err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof, true);
 	if (err)
 		goto out;
-- 
2.20.1


From 9f58ba49e6e920e9ee1ac8c4f388dba1cb16bc32 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 20 Nov 2019 15:34:38 +0300
Subject: [PATCH 04/10] net: rtnetlink: prevent underflows in do_setvfinfo()

[ Upstream commit d658c8f56ec7b3de8051a24afb25da9ba3c388c5 ]

The "ivm->vf" variable is a u32, but the problem is that a number of
drivers cast it to an int and then forget to check for negatives.  An
example of this is in the cxgb4 driver.

drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
  2890  static int cxgb4_mgmt_get_vf_config(struct net_device *dev,
  2891                                      int vf, struct ifla_vf_info *ivi)
                                            ^^^^^^
  2892  {
  2893          struct port_info *pi = netdev_priv(dev);
  2894          struct adapter *adap = pi->adapter;
  2895          struct vf_info *vfinfo;
  2896
  2897          if (vf >= adap->num_vfs)
                    ^^^^^^^^^^^^^^^^^^^
  2898                  return -EINVAL;
  2899          vfinfo = &adap->vfinfo[vf];
                ^^^^^^^^^^^^^^^^^^^^^^^^^^

There are 48 functions affected.

drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c:8435 hclge_set_vf_vlan_filter() warn: can 'vfid' underflow 's32min-2147483646'
drivers/net/ethernet/freescale/enetc/enetc_pf.c:377 enetc_pf_set_vf_mac() warn: can 'vf' underflow 's32min-2147483646'
drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c:2899 cxgb4_mgmt_get_vf_config() warn: can 'vf' underflow 's32min-254'
drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c:2960 cxgb4_mgmt_set_vf_rate() warn: can 'vf' underflow 's32min-254'
drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c:3019 cxgb4_mgmt_set_vf_rate() warn: can 'vf' underflow 's32min-254'
drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c:3038 cxgb4_mgmt_set_vf_vlan() warn: can 'vf' underflow 's32min-254'
drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c:3086 cxgb4_mgmt_set_vf_link_state() warn: can 'vf' underflow 's32min-254'
drivers/net/ethernet/chelsio/cxgb/cxgb2.c:791 get_eeprom() warn: can 'i' underflow 's32min-(-4),0,4-s32max'
drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c:82 bnxt_set_vf_spoofchk() warn: can 'vf_id' underflow 's32min-65534'
drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c:164 bnxt_set_vf_trust() warn: can 'vf_id' underflow 's32min-65534'
drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c:186 bnxt_get_vf_config() warn: can 'vf_id' underflow 's32min-65534'
drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c:228 bnxt_set_vf_mac() warn: can 'vf_id' underflow 's32min-65534'
drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c:264 bnxt_set_vf_vlan() warn: can 'vf_id' underflow 's32min-65534'
drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c:293 bnxt_set_vf_bw() warn: can 'vf_id' underflow 's32min-65534'
drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c:333 bnxt_set_vf_link_state() warn: can 'vf_id' underflow 's32min-65534'
drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c:2595 bnx2x_vf_op_prep() warn: can 'vfidx' underflow 's32min-63'
drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c:2595 bnx2x_vf_op_prep() warn: can 'vfidx' underflow 's32min-63'
drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c:2281 bnx2x_post_vf_bulletin() warn: can 'vf' underflow 's32min-63'
drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c:2285 bnx2x_post_vf_bulletin() warn: can 'vf' underflow 's32min-63'
drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c:2286 bnx2x_post_vf_bulletin() warn: can 'vf' underflow 's32min-63'
drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c:2292 bnx2x_post_vf_bulletin() warn: can 'vf' underflow 's32min-63'
drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c:2297 bnx2x_post_vf_bulletin() warn: can 'vf' underflow 's32min-63'
drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c:1832 qlcnic_sriov_set_vf_mac() warn: can 'vf' underflow 's32min-254'
drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c:1864 qlcnic_sriov_set_vf_tx_rate() warn: can 'vf' underflow 's32min-254'
drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c:1937 qlcnic_sriov_set_vf_vlan() warn: can 'vf' underflow 's32min-254'
drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c:2005 qlcnic_sriov_get_vf_config() warn: can 'vf' underflow 's32min-254'
drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c:2036 qlcnic_sriov_set_vf_spoofchk() warn: can 'vf' underflow 's32min-254'
drivers/net/ethernet/emulex/benet/be_main.c:1914 be_get_vf_config() warn: can 'vf' underflow 's32min-65534'
drivers/net/ethernet/emulex/benet/be_main.c:1915 be_get_vf_config() warn: can 'vf' underflow 's32min-65534'
drivers/net/ethernet/emulex/benet/be_main.c:1922 be_set_vf_tvt() warn: can 'vf' underflow 's32min-65534'
drivers/net/ethernet/emulex/benet/be_main.c:1951 be_clear_vf_tvt() warn: can 'vf' underflow 's32min-65534'
drivers/net/ethernet/emulex/benet/be_main.c:2063 be_set_vf_tx_rate() warn: can 'vf' underflow 's32min-65534'
drivers/net/ethernet/emulex/benet/be_main.c:2091 be_set_vf_link_state() warn: can 'vf' underflow 's32min-65534'
drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c:2609 ice_set_vf_port_vlan() warn: can 'vf_id' underflow 's32min-65534'
drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c:3050 ice_get_vf_cfg() warn: can 'vf_id' underflow 's32min-65534'
drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c:3103 ice_set_vf_spoofchk() warn: can 'vf_id' underflow 's32min-65534'
drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c:3181 ice_set_vf_mac() warn: can 'vf_id' underflow 's32min-65534'
drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c:3237 ice_set_vf_trust() warn: can 'vf_id' underflow 's32min-65534'
drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c:3286 ice_set_vf_link_state() warn: can 'vf_id' underflow 's32min-65534'
drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c:3919 i40e_validate_vf() warn: can 'vf_id' underflow 's32min-2147483646'
drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c:3957 i40e_ndo_set_vf_mac() warn: can 'vf_id' underflow 's32min-2147483646'
drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c:4104 i40e_ndo_set_vf_port_vlan() warn: can 'vf_id' underflow 's32min-2147483646'
drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c:4263 i40e_ndo_set_vf_bw() warn: can 'vf_id' underflow 's32min-2147483646'
drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c:4309 i40e_ndo_get_vf_config() warn: can 'vf_id' underflow 's32min-2147483646'
drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c:4371 i40e_ndo_set_vf_link_state() warn: can 'vf_id' underflow 's32min-2147483646'
drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c:4441 i40e_ndo_set_vf_spoofchk() warn: can 'vf_id' underflow 's32min-2147483646'
drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c:4441 i40e_ndo_set_vf_spoofchk() warn: can 'vf_id' underflow 's32min-2147483646'
drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c:4504 i40e_ndo_set_vf_trust() warn: can 'vf_id' underflow 's32min-2147483646'

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 23 ++++++++++++++++++++++-
 1 file changed, 22 insertions(+), 1 deletion(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index c0de73b12580..dbb3c0c7c132 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2126,6 +2126,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
 	if (tb[IFLA_VF_MAC]) {
 		struct ifla_vf_mac *ivm = nla_data(tb[IFLA_VF_MAC]);
 
+		if (ivm->vf >= INT_MAX)
+			return -EINVAL;
 		err = -EOPNOTSUPP;
 		if (ops->ndo_set_vf_mac)
 			err = ops->ndo_set_vf_mac(dev, ivm->vf,
@@ -2137,6 +2139,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
 	if (tb[IFLA_VF_VLAN]) {
 		struct ifla_vf_vlan *ivv = nla_data(tb[IFLA_VF_VLAN]);
 
+		if (ivv->vf >= INT_MAX)
+			return -EINVAL;
 		err = -EOPNOTSUPP;
 		if (ops->ndo_set_vf_vlan)
 			err = ops->ndo_set_vf_vlan(dev, ivv->vf, ivv->vlan,
@@ -2169,6 +2173,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
 		if (len == 0)
 			return -EINVAL;
 
+		if (ivvl[0]->vf >= INT_MAX)
+			return -EINVAL;
 		err = ops->ndo_set_vf_vlan(dev, ivvl[0]->vf, ivvl[0]->vlan,
 					   ivvl[0]->qos, ivvl[0]->vlan_proto);
 		if (err < 0)
@@ -2179,6 +2185,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
 		struct ifla_vf_tx_rate *ivt = nla_data(tb[IFLA_VF_TX_RATE]);
 		struct ifla_vf_info ivf;
 
+		if (ivt->vf >= INT_MAX)
+			return -EINVAL;
 		err = -EOPNOTSUPP;
 		if (ops->ndo_get_vf_config)
 			err = ops->ndo_get_vf_config(dev, ivt->vf, &ivf);
@@ -2197,6 +2205,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
 	if (tb[IFLA_VF_RATE]) {
 		struct ifla_vf_rate *ivt = nla_data(tb[IFLA_VF_RATE]);
 
+		if (ivt->vf >= INT_MAX)
+			return -EINVAL;
 		err = -EOPNOTSUPP;
 		if (ops->ndo_set_vf_rate)
 			err = ops->ndo_set_vf_rate(dev, ivt->vf,
@@ -2209,6 +2219,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
 	if (tb[IFLA_VF_SPOOFCHK]) {
 		struct ifla_vf_spoofchk *ivs = nla_data(tb[IFLA_VF_SPOOFCHK]);
 
+		if (ivs->vf >= INT_MAX)
+			return -EINVAL;
 		err = -EOPNOTSUPP;
 		if (ops->ndo_set_vf_spoofchk)
 			err = ops->ndo_set_vf_spoofchk(dev, ivs->vf,
@@ -2220,6 +2232,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
 	if (tb[IFLA_VF_LINK_STATE]) {
 		struct ifla_vf_link_state *ivl = nla_data(tb[IFLA_VF_LINK_STATE]);
 
+		if (ivl->vf >= INT_MAX)
+			return -EINVAL;
 		err = -EOPNOTSUPP;
 		if (ops->ndo_set_vf_link_state)
 			err = ops->ndo_set_vf_link_state(dev, ivl->vf,
@@ -2233,6 +2247,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
 
 		err = -EOPNOTSUPP;
 		ivrssq_en = nla_data(tb[IFLA_VF_RSS_QUERY_EN]);
+		if (ivrssq_en->vf >= INT_MAX)
+			return -EINVAL;
 		if (ops->ndo_set_vf_rss_query_en)
 			err = ops->ndo_set_vf_rss_query_en(dev, ivrssq_en->vf,
 							   ivrssq_en->setting);
@@ -2243,6 +2259,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
 	if (tb[IFLA_VF_TRUST]) {
 		struct ifla_vf_trust *ivt = nla_data(tb[IFLA_VF_TRUST]);
 
+		if (ivt->vf >= INT_MAX)
+			return -EINVAL;
 		err = -EOPNOTSUPP;
 		if (ops->ndo_set_vf_trust)
 			err = ops->ndo_set_vf_trust(dev, ivt->vf, ivt->setting);
@@ -2253,15 +2271,18 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
 	if (tb[IFLA_VF_IB_NODE_GUID]) {
 		struct ifla_vf_guid *ivt = nla_data(tb[IFLA_VF_IB_NODE_GUID]);
 
+		if (ivt->vf >= INT_MAX)
+			return -EINVAL;
 		if (!ops->ndo_set_vf_guid)
 			return -EOPNOTSUPP;
-
 		return handle_vf_guid(dev, ivt, IFLA_VF_IB_NODE_GUID);
 	}
 
 	if (tb[IFLA_VF_IB_PORT_GUID]) {
 		struct ifla_vf_guid *ivt = nla_data(tb[IFLA_VF_IB_PORT_GUID]);
 
+		if (ivt->vf >= INT_MAX)
+			return -EINVAL;
 		if (!ops->ndo_set_vf_guid)
 			return -EOPNOTSUPP;
 
-- 
2.20.1


From 8e58f41d6d537cdb60d980e5cf70788bda39ae72 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Tue, 19 Nov 2019 23:47:33 +0100
Subject: [PATCH 05/10] net/sched: act_pedit: fix WARN() in the traffic path

[ Upstream commit f67169fef8dbcc1ac6a6a109ecaad0d3b259002c ]

when configuring act_pedit rules, the number of keys is validated only on
addition of a new entry. This is not sufficient to avoid hitting a WARN()
in the traffic path: for example, it is possible to replace a valid entry
with a new one having 0 extended keys, thus causing splats in dmesg like:

 pedit BUG: index 42
 WARNING: CPU: 2 PID: 4054 at net/sched/act_pedit.c:410 tcf_pedit_act+0xc84/0x1200 [act_pedit]
 [...]
 RIP: 0010:tcf_pedit_act+0xc84/0x1200 [act_pedit]
 Code: 89 fa 48 c1 ea 03 0f b6 04 02 84 c0 74 08 3c 03 0f 8e ac 00 00 00 48 8b 44 24 10 48 c7 c7 a0 c4 e4 c0 8b 70 18 e8 1c 30 95 ea <0f> 0b e9 a0 fa ff ff e8 00 03 f5 ea e9 14 f4 ff ff 48 89 58 40 e9
 RSP: 0018:ffff888077c9f320 EFLAGS: 00010286
 RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffffffffac2983a2
 RDX: 0000000000000001 RSI: 0000000000000008 RDI: ffff888053927bec
 RBP: dffffc0000000000 R08: ffffed100a726209 R09: ffffed100a726209
 R10: 0000000000000001 R11: ffffed100a726208 R12: ffff88804beea780
 R13: ffff888079a77400 R14: ffff88804beea780 R15: ffff888027ab2000
 FS:  00007fdeec9bd740(0000) GS:ffff888053900000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 00007ffdb3dfd000 CR3: 000000004adb4006 CR4: 00000000001606e0
 Call Trace:
  tcf_action_exec+0x105/0x3f0
  tcf_classify+0xf2/0x410
  __dev_queue_xmit+0xcbf/0x2ae0
  ip_finish_output2+0x711/0x1fb0
  ip_output+0x1bf/0x4b0
  ip_send_skb+0x37/0xa0
  raw_sendmsg+0x180c/0x2430
  sock_sendmsg+0xdb/0x110
  __sys_sendto+0x257/0x2b0
  __x64_sys_sendto+0xdd/0x1b0
  do_syscall_64+0xa5/0x4e0
  entry_SYSCALL_64_after_hwframe+0x49/0xbe
 RIP: 0033:0x7fdeeb72e993
 Code: 48 8b 0d e0 74 2c 00 f7 d8 64 89 01 48 83 c8 ff c3 66 0f 1f 44 00 00 83 3d 0d d6 2c 00 00 75 13 49 89 ca b8 2c 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 34 c3 48 83 ec 08 e8 4b cc 00 00 48 89 04 24
 RSP: 002b:00007ffdb3de8a18 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
 RAX: ffffffffffffffda RBX: 000055c81972b700 RCX: 00007fdeeb72e993
 RDX: 0000000000000040 RSI: 000055c81972b700 RDI: 0000000000000003
 RBP: 00007ffdb3dea130 R08: 000055c819728510 R09: 0000000000000010
 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000040
 R13: 000055c81972b6c0 R14: 000055c81972969c R15: 0000000000000080

Fix this moving the check on 'nkeys' earlier in tcf_pedit_init(), so that
attempts to install rules having 0 keys are always rejected with -EINVAL.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_pedit.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 33c0cc5ef229..ce14fafb36a1 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -46,7 +46,7 @@ static struct tcf_pedit_key_ex *tcf_pedit_keys_ex_parse(struct nlattr *nla,
 	int err = -EINVAL;
 	int rem;
 
-	if (!nla || !n)
+	if (!nla)
 		return NULL;
 
 	keys_ex = kcalloc(n, sizeof(*k), GFP_KERNEL);
@@ -169,6 +169,10 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 	}
 
 	parm = nla_data(pattr);
+	if (!parm->nkeys) {
+		NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed");
+		return -EINVAL;
+	}
 	ksize = parm->nkeys * sizeof(struct tc_pedit_key);
 	if (nla_len(pattr) < sizeof(*parm) + ksize) {
 		NL_SET_ERR_MSG_ATTR(extack, pattr, "Length of TCA_PEDIT_PARMS or TCA_PEDIT_PARMS_EX pedit attribute is invalid");
@@ -182,12 +186,6 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 	index = parm->index;
 	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (!err) {
-		if (!parm->nkeys) {
-			tcf_idr_cleanup(tn, index);
-			NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed");
-			ret = -EINVAL;
-			goto out_free;
-		}
 		ret = tcf_idr_create(tn, index, est, a,
 				     &act_pedit_ops, bind, false);
 		if (ret) {
-- 
2.20.1


From 22f716702ef8e48d9f55e70f01a110562c77fded Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 18 Nov 2019 17:39:34 +0800
Subject: [PATCH 06/10] net: sched: ensure opts_len <= IP_TUNNEL_OPTS_MAX in
 act_tunnel_key

[ Upstream commit 4f0e97d070984d487df027f163e52bb72d1713d8 ]

info->options_len is 'u8' type, and when opts_len with a value >
IP_TUNNEL_OPTS_MAX, 'info->options_len = opts_len' will cast int
to u8 and set a wrong value to info->options_len.

Kernel crashed in my test when doing:

  # opts="0102:80:00800022"
  # for i in {1..99}; do opts="$opts,0102:80:00800022"; done
  # ip link add name geneve0 type geneve dstport 0 external
  # tc qdisc add dev eth0 ingress
  # tc filter add dev eth0 protocol ip parent ffff: \
       flower indev eth0 ip_proto udp action tunnel_key \
       set src_ip 10.0.99.192 dst_ip 10.0.99.193 \
       dst_port 6081 id 11 geneve_opts $opts \
       action mirred egress redirect dev geneve0

So we should do the similar check as cls_flower does, return error
when opts_len > IP_TUNNEL_OPTS_MAX in tunnel_key_copy_opts().

Fixes: 0ed5269f9e41 ("net/sched: add tunnel option support to act_tunnel_key")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_tunnel_key.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 43309ff2b5dc..e4fc6b2bc29d 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -137,6 +137,10 @@ static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst,
 			if (opt_len < 0)
 				return opt_len;
 			opts_len += opt_len;
+			if (opts_len > IP_TUNNEL_OPTS_MAX) {
+				NL_SET_ERR_MSG(extack, "Tunnel options exceeds max size");
+				return -EINVAL;
+			}
 			if (dst) {
 				dst_len -= opt_len;
 				dst += opt_len;
-- 
2.20.1


From f5088ef8098cb2e9ac5ba7152cc2d5b3005df29e Mon Sep 17 00:00:00 2001
From: Martin Habets <mhabets@solarflare.com>
Date: Thu, 21 Nov 2019 17:52:15 +0000
Subject: [PATCH 07/10] sfc: Only cancel the PPS workqueue if it exists

[ Upstream commit 723eb53690041740a13ac78efeaf6804f5d684c9 ]

The workqueue only exists for the primary PF. For other functions
we hit a WARN_ON in kernel/workqueue.c.

Fixes: 7c236c43b838 ("sfc: Add support for IEEE-1588 PTP")
Signed-off-by: Martin Habets <mhabets@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/ptp.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c
index f21661532ed3..cc8fbf398c0d 100644
--- a/drivers/net/ethernet/sfc/ptp.c
+++ b/drivers/net/ethernet/sfc/ptp.c
@@ -1534,7 +1534,8 @@ void efx_ptp_remove(struct efx_nic *efx)
 	(void)efx_ptp_disable(efx);
 
 	cancel_work_sync(&efx->ptp_data->work);
-	cancel_work_sync(&efx->ptp_data->pps_work);
+	if (efx->ptp_data->pps_workwq)
+		cancel_work_sync(&efx->ptp_data->pps_work);
 
 	skb_queue_purge(&efx->ptp_data->rxq);
 	skb_queue_purge(&efx->ptp_data->txq);
-- 
2.20.1


From 6c35f01e9b9f648f06d688867ce6979416172231 Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@mellanox.com>
Date: Wed, 13 Nov 2019 14:42:00 +0200
Subject: [PATCH 08/10] net/mlx5e: Fix set vf link state error flow

[ Upstream commit 751021218f7e66ee9bbaa2be23056e447cd75ec4 ]

Before this commit the ndo always returned success.
Fix that.

Fixes: 1ab2068a4c66 ("net/mlx5: Implement vports admin state backup/restore")
Signed-off-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 55ccd90beeb0..7366033cd31c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1861,7 +1861,7 @@ int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw,
 
 unlock:
 	mutex_unlock(&esw->state_lock);
-	return 0;
+	return err;
 }
 
 int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw,
-- 
2.20.1


From a2e3a06ac64b0a2308e410bf6229675ce642c3ea Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Sun, 17 Nov 2019 10:18:59 +0200
Subject: [PATCH 09/10] net/mlxfw: Verify FSM error code translation doesn't
 exceed array size

[ Upstream commit 30e9e0550bf693c94bc15827781fe42dd60be634 ]

Array mlxfw_fsm_state_err_str contains value to string translation, when
values are provided by mlxfw_dev. If value is larger than
MLXFW_FSM_STATE_ERR_MAX, return "unknown error" as expected instead of
reading an address than exceed array size.

Fixes: 410ed13cae39 ("Add the mlxfw module for Mellanox firmware flash process")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c
index 2cf89126fb23..d765e7a69d6b 100644
--- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c
+++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c
@@ -86,6 +86,8 @@ static int mlxfw_fsm_state_wait(struct mlxfw_dev *mlxfw_dev, u32 fwhandle,
 		return err;
 
 	if (fsm_state_err != MLXFW_FSM_STATE_ERR_OK) {
+		fsm_state_err = min_t(enum mlxfw_fsm_state_err,
+				      fsm_state_err, MLXFW_FSM_STATE_ERR_MAX);
 		pr_err("Firmware flash failed: %s\n",
 		       mlxfw_fsm_state_err_str[fsm_state_err]);
 		return -EINVAL;
-- 
2.20.1


From 87aec2bba8e5f83876f5a2c2474b538d6ac126dc Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@mellanox.com>
Date: Thu, 5 Sep 2019 09:56:10 +0300
Subject: [PATCH 10/10] net/mlx5: Fix auto group size calculation

[ Upstream commit 97fd8da281f80e7e69e0114bc906575734d4dfaf ]

Once all the large flow groups (defined by the user when the flow table
is created - max_num_groups) were created, then all the following new
flow groups will have only one flow table entry, even though the flow table
has place to larger groups.
Fix the condition to prefer large flow group.

Fixes: f0d22d187473 ("net/mlx5_core: Introduce flow steering autogrouped flow table")
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 10 ++++++----
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.h |  1 +
 2 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index c079f85593d6..82a53317285d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -520,7 +520,7 @@ static void del_sw_flow_group(struct fs_node *node)
 
 	rhashtable_destroy(&fg->ftes_hash);
 	ida_destroy(&fg->fte_allocator);
-	if (ft->autogroup.active)
+	if (ft->autogroup.active && fg->max_ftes == ft->autogroup.group_size)
 		ft->autogroup.num_groups--;
 	err = rhltable_remove(&ft->fgs_hash,
 			      &fg->hash,
@@ -1065,6 +1065,8 @@ mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns,
 
 	ft->autogroup.active = true;
 	ft->autogroup.required_groups = max_num_groups;
+	/* We save place for flow groups in addition to max types */
+	ft->autogroup.group_size = ft->max_fte / (max_num_groups + 1);
 
 	return ft;
 }
@@ -1270,8 +1272,7 @@ static struct mlx5_flow_group *alloc_auto_flow_group(struct mlx5_flow_table  *ft
 		return ERR_PTR(-ENOENT);
 
 	if (ft->autogroup.num_groups < ft->autogroup.required_groups)
-		/* We save place for flow groups in addition to max types */
-		group_size = ft->max_fte / (ft->autogroup.required_groups + 1);
+		group_size = ft->autogroup.group_size;
 
 	/*  ft->max_fte == ft->autogroup.max_types */
 	if (group_size == 0)
@@ -1298,7 +1299,8 @@ static struct mlx5_flow_group *alloc_auto_flow_group(struct mlx5_flow_table  *ft
 	if (IS_ERR(fg))
 		goto out;
 
-	ft->autogroup.num_groups++;
+	if (group_size == ft->autogroup.group_size)
+		ft->autogroup.num_groups++;
 
 out:
 	return fg;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index 32070e5d993d..ba62fbce23a2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -121,6 +121,7 @@ struct mlx5_flow_table {
 	struct {
 		bool			active;
 		unsigned int		required_groups;
+		unsigned int		group_size;
 		unsigned int		num_groups;
 	} autogroup;
 	/* Protect fwd_rules */
-- 
2.20.1


[-- Attachment #3: net_53.mbox --]
[-- Type: Application/Octet-Stream, Size: 49666 bytes --]

From d0e106e1bd74f6d0e2e84d53976c8e812a7e2d86 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 18 Nov 2019 09:18:42 +0200
Subject: [PATCH 01/18] mlxsw: spectrum_router: Fix determining underlay for a
 GRE tunnel

[ Upstream commit 1fc1657775dc1b19e9ac1d46b4054ed8ae5d99ab ]

The helper mlxsw_sp_ipip_dev_ul_tb_id() determines the underlay VRF of a
GRE tunnel. For a tunnel without a bound device, it uses the same VRF that
the tunnel is in. However in Linux, a GRE tunnel without a bound device
uses the main VRF as the underlay. Fix the function accordingly.

mlxsw further assumed that moving a tunnel to a different VRF could cause
conflict in local tunnel endpoint address, which cannot be offloaded.
However, the only way that an underlay could be changed by moving the
tunnel device itself is if the tunnel device does not have a bound device.
But in that case the underlay is always the main VRF, so there is no
opportunity to introduce a conflict by moving such device. Thus this check
constitutes a dead code, and can be removed, which do.

Fixes: 6ddb7426a7d4 ("mlxsw: spectrum_router: Introduce loopback RIFs")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/spectrum_router.c | 19 +------------------
 1 file changed, 1 insertion(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index e618be7ce6c6..7b7e50d25d25 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -994,7 +994,7 @@ u32 mlxsw_sp_ipip_dev_ul_tb_id(const struct net_device *ol_dev)
 	if (d)
 		return l3mdev_fib_table(d) ? : RT_TABLE_MAIN;
 	else
-		return l3mdev_fib_table(ol_dev) ? : RT_TABLE_MAIN;
+		return RT_TABLE_MAIN;
 }
 
 static struct mlxsw_sp_rif *
@@ -1598,27 +1598,10 @@ static int mlxsw_sp_netdevice_ipip_ol_vrf_event(struct mlxsw_sp *mlxsw_sp,
 {
 	struct mlxsw_sp_ipip_entry *ipip_entry =
 		mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, ol_dev);
-	enum mlxsw_sp_l3proto ul_proto;
-	union mlxsw_sp_l3addr saddr;
-	u32 ul_tb_id;
 
 	if (!ipip_entry)
 		return 0;
 
-	/* For flat configuration cases, moving overlay to a different VRF might
-	 * cause local address conflict, and the conflicting tunnels need to be
-	 * demoted.
-	 */
-	ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(ol_dev);
-	ul_proto = mlxsw_sp->router->ipip_ops_arr[ipip_entry->ipipt]->ul_proto;
-	saddr = mlxsw_sp_ipip_netdev_saddr(ul_proto, ol_dev);
-	if (mlxsw_sp_ipip_demote_tunnel_by_saddr(mlxsw_sp, ul_proto,
-						 saddr, ul_tb_id,
-						 ipip_entry)) {
-		mlxsw_sp_ipip_entry_demote_tunnel(mlxsw_sp, ipip_entry);
-		return 0;
-	}
-
 	return __mlxsw_sp_ipip_entry_update_tunnel(mlxsw_sp, ipip_entry,
 						   true, false, false, extack);
 }
-- 
2.20.1


From 5a04802c5c77393906091d64d5ddc5a37311dd08 Mon Sep 17 00:00:00 2001
From: Luigi Rizzo <lrizzo@google.com>
Date: Fri, 15 Nov 2019 12:12:25 -0800
Subject: [PATCH 02/18] net/mlx4_en: fix mlx4 ethtool -N insertion

[ Upstream commit 34e59836565e36fade1464e054a3551c1a0364be ]

ethtool expects ETHTOOL_GRXCLSRLALL to set ethtool_rxnfc->data with the
total number of entries in the rx classifier table.  Surprisingly, mlx4
is missing this part (in principle ethtool could still move forward and
try the insert).

Tested: compiled and run command:
	phh13:~# ethtool -N eth1 flow-type udp4  queue 4
	Added rule with ID 255

Signed-off-by: Luigi Rizzo <lrizzo@google.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 94c59939a8cf..949ec70b6c13 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1745,6 +1745,7 @@ static int mlx4_en_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 		err = mlx4_en_get_flow(dev, cmd, cmd->fs.location);
 		break;
 	case ETHTOOL_GRXCLSRLALL:
+		cmd->data = MAX_NUM_OF_FS_RULES;
 		while ((!err || err == -ENOENT) && priority < cmd->rule_cnt) {
 			err = mlx4_en_get_flow(dev, cmd, i);
 			if (!err)
-- 
2.20.1


From 6685c59c4e596ef389e6c9f3f2067719f989a422 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Mon, 18 Nov 2019 11:41:04 +0200
Subject: [PATCH 03/18] net/mlx4_en: Fix wrong limitation for number of TX
 rings

[ Upstream commit 2744bf42680f64ebf2ee8a00354897857c073331 ]

XDP_TX rings should not be limited by max_num_tx_rings_p_up.
To make sure total number of TX rings never exceed MAX_TX_RINGS,
add similar check in mlx4_en_alloc_tx_queue_per_tc(), where
a new value is assigned for num_up.

Fixes: 7e1dc5e926d5 ("net/mlx4_en: Limit the number of TX rings")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 8 ++++----
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c  | 9 +++++++++
 2 files changed, 13 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 949ec70b6c13..e639a365ac2d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1812,6 +1812,7 @@ static int mlx4_en_set_channels(struct net_device *dev,
 	struct mlx4_en_dev *mdev = priv->mdev;
 	struct mlx4_en_port_profile new_prof;
 	struct mlx4_en_priv *tmp;
+	int total_tx_count;
 	int port_up = 0;
 	int xdp_count;
 	int err = 0;
@@ -1826,13 +1827,12 @@ static int mlx4_en_set_channels(struct net_device *dev,
 
 	mutex_lock(&mdev->state_lock);
 	xdp_count = priv->tx_ring_num[TX_XDP] ? channel->rx_count : 0;
-	if (channel->tx_count * priv->prof->num_up + xdp_count >
-	    priv->mdev->profile.max_num_tx_rings_p_up * priv->prof->num_up) {
+	total_tx_count = channel->tx_count * priv->prof->num_up + xdp_count;
+	if (total_tx_count > MAX_TX_RINGS) {
 		err = -EINVAL;
 		en_err(priv,
 		       "Total number of TX and XDP rings (%d) exceeds the maximum supported (%d)\n",
-		       channel->tx_count * priv->prof->num_up  + xdp_count,
-		       MAX_TX_RINGS);
+		       total_tx_count, MAX_TX_RINGS);
 		goto out;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index c1438ae52a11..ba4f195a36d6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -91,6 +91,7 @@ int mlx4_en_alloc_tx_queue_per_tc(struct net_device *dev, u8 tc)
 	struct mlx4_en_dev *mdev = priv->mdev;
 	struct mlx4_en_port_profile new_prof;
 	struct mlx4_en_priv *tmp;
+	int total_count;
 	int port_up = 0;
 	int err = 0;
 
@@ -104,6 +105,14 @@ int mlx4_en_alloc_tx_queue_per_tc(struct net_device *dev, u8 tc)
 				      MLX4_EN_NUM_UP_HIGH;
 	new_prof.tx_ring_num[TX] = new_prof.num_tx_rings_p_up *
 				   new_prof.num_up;
+	total_count = new_prof.tx_ring_num[TX] + new_prof.tx_ring_num[TX_XDP];
+	if (total_count > MAX_TX_RINGS) {
+		err = -EINVAL;
+		en_err(priv,
+		       "Total number of TX and XDP rings (%d) exceeds the maximum supported (%d)\n",
+		       total_count, MAX_TX_RINGS);
+		goto out;
+	}
 	err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof, true);
 	if (err)
 		goto out;
-- 
2.20.1


From ea590fdf19e112f7a64fbc4e15979efb80ae26eb Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 20 Nov 2019 15:34:38 +0300
Subject: [PATCH 04/18] net: rtnetlink: prevent underflows in do_setvfinfo()

[ Upstream commit d658c8f56ec7b3de8051a24afb25da9ba3c388c5 ]

The "ivm->vf" variable is a u32, but the problem is that a number of
drivers cast it to an int and then forget to check for negatives.  An
example of this is in the cxgb4 driver.

drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
  2890  static int cxgb4_mgmt_get_vf_config(struct net_device *dev,
  2891                                      int vf, struct ifla_vf_info *ivi)
                                            ^^^^^^
  2892  {
  2893          struct port_info *pi = netdev_priv(dev);
  2894          struct adapter *adap = pi->adapter;
  2895          struct vf_info *vfinfo;
  2896
  2897          if (vf >= adap->num_vfs)
                    ^^^^^^^^^^^^^^^^^^^
  2898                  return -EINVAL;
  2899          vfinfo = &adap->vfinfo[vf];
                ^^^^^^^^^^^^^^^^^^^^^^^^^^

There are 48 functions affected.

drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c:8435 hclge_set_vf_vlan_filter() warn: can 'vfid' underflow 's32min-2147483646'
drivers/net/ethernet/freescale/enetc/enetc_pf.c:377 enetc_pf_set_vf_mac() warn: can 'vf' underflow 's32min-2147483646'
drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c:2899 cxgb4_mgmt_get_vf_config() warn: can 'vf' underflow 's32min-254'
drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c:2960 cxgb4_mgmt_set_vf_rate() warn: can 'vf' underflow 's32min-254'
drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c:3019 cxgb4_mgmt_set_vf_rate() warn: can 'vf' underflow 's32min-254'
drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c:3038 cxgb4_mgmt_set_vf_vlan() warn: can 'vf' underflow 's32min-254'
drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c:3086 cxgb4_mgmt_set_vf_link_state() warn: can 'vf' underflow 's32min-254'
drivers/net/ethernet/chelsio/cxgb/cxgb2.c:791 get_eeprom() warn: can 'i' underflow 's32min-(-4),0,4-s32max'
drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c:82 bnxt_set_vf_spoofchk() warn: can 'vf_id' underflow 's32min-65534'
drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c:164 bnxt_set_vf_trust() warn: can 'vf_id' underflow 's32min-65534'
drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c:186 bnxt_get_vf_config() warn: can 'vf_id' underflow 's32min-65534'
drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c:228 bnxt_set_vf_mac() warn: can 'vf_id' underflow 's32min-65534'
drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c:264 bnxt_set_vf_vlan() warn: can 'vf_id' underflow 's32min-65534'
drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c:293 bnxt_set_vf_bw() warn: can 'vf_id' underflow 's32min-65534'
drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c:333 bnxt_set_vf_link_state() warn: can 'vf_id' underflow 's32min-65534'
drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c:2595 bnx2x_vf_op_prep() warn: can 'vfidx' underflow 's32min-63'
drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c:2595 bnx2x_vf_op_prep() warn: can 'vfidx' underflow 's32min-63'
drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c:2281 bnx2x_post_vf_bulletin() warn: can 'vf' underflow 's32min-63'
drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c:2285 bnx2x_post_vf_bulletin() warn: can 'vf' underflow 's32min-63'
drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c:2286 bnx2x_post_vf_bulletin() warn: can 'vf' underflow 's32min-63'
drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c:2292 bnx2x_post_vf_bulletin() warn: can 'vf' underflow 's32min-63'
drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c:2297 bnx2x_post_vf_bulletin() warn: can 'vf' underflow 's32min-63'
drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c:1832 qlcnic_sriov_set_vf_mac() warn: can 'vf' underflow 's32min-254'
drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c:1864 qlcnic_sriov_set_vf_tx_rate() warn: can 'vf' underflow 's32min-254'
drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c:1937 qlcnic_sriov_set_vf_vlan() warn: can 'vf' underflow 's32min-254'
drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c:2005 qlcnic_sriov_get_vf_config() warn: can 'vf' underflow 's32min-254'
drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c:2036 qlcnic_sriov_set_vf_spoofchk() warn: can 'vf' underflow 's32min-254'
drivers/net/ethernet/emulex/benet/be_main.c:1914 be_get_vf_config() warn: can 'vf' underflow 's32min-65534'
drivers/net/ethernet/emulex/benet/be_main.c:1915 be_get_vf_config() warn: can 'vf' underflow 's32min-65534'
drivers/net/ethernet/emulex/benet/be_main.c:1922 be_set_vf_tvt() warn: can 'vf' underflow 's32min-65534'
drivers/net/ethernet/emulex/benet/be_main.c:1951 be_clear_vf_tvt() warn: can 'vf' underflow 's32min-65534'
drivers/net/ethernet/emulex/benet/be_main.c:2063 be_set_vf_tx_rate() warn: can 'vf' underflow 's32min-65534'
drivers/net/ethernet/emulex/benet/be_main.c:2091 be_set_vf_link_state() warn: can 'vf' underflow 's32min-65534'
drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c:2609 ice_set_vf_port_vlan() warn: can 'vf_id' underflow 's32min-65534'
drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c:3050 ice_get_vf_cfg() warn: can 'vf_id' underflow 's32min-65534'
drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c:3103 ice_set_vf_spoofchk() warn: can 'vf_id' underflow 's32min-65534'
drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c:3181 ice_set_vf_mac() warn: can 'vf_id' underflow 's32min-65534'
drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c:3237 ice_set_vf_trust() warn: can 'vf_id' underflow 's32min-65534'
drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c:3286 ice_set_vf_link_state() warn: can 'vf_id' underflow 's32min-65534'
drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c:3919 i40e_validate_vf() warn: can 'vf_id' underflow 's32min-2147483646'
drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c:3957 i40e_ndo_set_vf_mac() warn: can 'vf_id' underflow 's32min-2147483646'
drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c:4104 i40e_ndo_set_vf_port_vlan() warn: can 'vf_id' underflow 's32min-2147483646'
drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c:4263 i40e_ndo_set_vf_bw() warn: can 'vf_id' underflow 's32min-2147483646'
drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c:4309 i40e_ndo_get_vf_config() warn: can 'vf_id' underflow 's32min-2147483646'
drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c:4371 i40e_ndo_set_vf_link_state() warn: can 'vf_id' underflow 's32min-2147483646'
drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c:4441 i40e_ndo_set_vf_spoofchk() warn: can 'vf_id' underflow 's32min-2147483646'
drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c:4441 i40e_ndo_set_vf_spoofchk() warn: can 'vf_id' underflow 's32min-2147483646'
drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c:4504 i40e_ndo_set_vf_trust() warn: can 'vf_id' underflow 's32min-2147483646'

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 23 ++++++++++++++++++++++-
 1 file changed, 22 insertions(+), 1 deletion(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 868a768f7300..60987be7fdaa 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2195,6 +2195,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
 	if (tb[IFLA_VF_MAC]) {
 		struct ifla_vf_mac *ivm = nla_data(tb[IFLA_VF_MAC]);
 
+		if (ivm->vf >= INT_MAX)
+			return -EINVAL;
 		err = -EOPNOTSUPP;
 		if (ops->ndo_set_vf_mac)
 			err = ops->ndo_set_vf_mac(dev, ivm->vf,
@@ -2206,6 +2208,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
 	if (tb[IFLA_VF_VLAN]) {
 		struct ifla_vf_vlan *ivv = nla_data(tb[IFLA_VF_VLAN]);
 
+		if (ivv->vf >= INT_MAX)
+			return -EINVAL;
 		err = -EOPNOTSUPP;
 		if (ops->ndo_set_vf_vlan)
 			err = ops->ndo_set_vf_vlan(dev, ivv->vf, ivv->vlan,
@@ -2238,6 +2242,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
 		if (len == 0)
 			return -EINVAL;
 
+		if (ivvl[0]->vf >= INT_MAX)
+			return -EINVAL;
 		err = ops->ndo_set_vf_vlan(dev, ivvl[0]->vf, ivvl[0]->vlan,
 					   ivvl[0]->qos, ivvl[0]->vlan_proto);
 		if (err < 0)
@@ -2248,6 +2254,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
 		struct ifla_vf_tx_rate *ivt = nla_data(tb[IFLA_VF_TX_RATE]);
 		struct ifla_vf_info ivf;
 
+		if (ivt->vf >= INT_MAX)
+			return -EINVAL;
 		err = -EOPNOTSUPP;
 		if (ops->ndo_get_vf_config)
 			err = ops->ndo_get_vf_config(dev, ivt->vf, &ivf);
@@ -2266,6 +2274,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
 	if (tb[IFLA_VF_RATE]) {
 		struct ifla_vf_rate *ivt = nla_data(tb[IFLA_VF_RATE]);
 
+		if (ivt->vf >= INT_MAX)
+			return -EINVAL;
 		err = -EOPNOTSUPP;
 		if (ops->ndo_set_vf_rate)
 			err = ops->ndo_set_vf_rate(dev, ivt->vf,
@@ -2278,6 +2288,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
 	if (tb[IFLA_VF_SPOOFCHK]) {
 		struct ifla_vf_spoofchk *ivs = nla_data(tb[IFLA_VF_SPOOFCHK]);
 
+		if (ivs->vf >= INT_MAX)
+			return -EINVAL;
 		err = -EOPNOTSUPP;
 		if (ops->ndo_set_vf_spoofchk)
 			err = ops->ndo_set_vf_spoofchk(dev, ivs->vf,
@@ -2289,6 +2301,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
 	if (tb[IFLA_VF_LINK_STATE]) {
 		struct ifla_vf_link_state *ivl = nla_data(tb[IFLA_VF_LINK_STATE]);
 
+		if (ivl->vf >= INT_MAX)
+			return -EINVAL;
 		err = -EOPNOTSUPP;
 		if (ops->ndo_set_vf_link_state)
 			err = ops->ndo_set_vf_link_state(dev, ivl->vf,
@@ -2302,6 +2316,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
 
 		err = -EOPNOTSUPP;
 		ivrssq_en = nla_data(tb[IFLA_VF_RSS_QUERY_EN]);
+		if (ivrssq_en->vf >= INT_MAX)
+			return -EINVAL;
 		if (ops->ndo_set_vf_rss_query_en)
 			err = ops->ndo_set_vf_rss_query_en(dev, ivrssq_en->vf,
 							   ivrssq_en->setting);
@@ -2312,6 +2328,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
 	if (tb[IFLA_VF_TRUST]) {
 		struct ifla_vf_trust *ivt = nla_data(tb[IFLA_VF_TRUST]);
 
+		if (ivt->vf >= INT_MAX)
+			return -EINVAL;
 		err = -EOPNOTSUPP;
 		if (ops->ndo_set_vf_trust)
 			err = ops->ndo_set_vf_trust(dev, ivt->vf, ivt->setting);
@@ -2322,15 +2340,18 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
 	if (tb[IFLA_VF_IB_NODE_GUID]) {
 		struct ifla_vf_guid *ivt = nla_data(tb[IFLA_VF_IB_NODE_GUID]);
 
+		if (ivt->vf >= INT_MAX)
+			return -EINVAL;
 		if (!ops->ndo_set_vf_guid)
 			return -EOPNOTSUPP;
-
 		return handle_vf_guid(dev, ivt, IFLA_VF_IB_NODE_GUID);
 	}
 
 	if (tb[IFLA_VF_IB_PORT_GUID]) {
 		struct ifla_vf_guid *ivt = nla_data(tb[IFLA_VF_IB_PORT_GUID]);
 
+		if (ivt->vf >= INT_MAX)
+			return -EINVAL;
 		if (!ops->ndo_set_vf_guid)
 			return -EOPNOTSUPP;
 
-- 
2.20.1


From b902cf422c217e6b6039d7d8b758f9c6475323f9 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Tue, 19 Nov 2019 23:47:33 +0100
Subject: [PATCH 05/18] net/sched: act_pedit: fix WARN() in the traffic path

[ Upstream commit f67169fef8dbcc1ac6a6a109ecaad0d3b259002c ]

when configuring act_pedit rules, the number of keys is validated only on
addition of a new entry. This is not sufficient to avoid hitting a WARN()
in the traffic path: for example, it is possible to replace a valid entry
with a new one having 0 extended keys, thus causing splats in dmesg like:

 pedit BUG: index 42
 WARNING: CPU: 2 PID: 4054 at net/sched/act_pedit.c:410 tcf_pedit_act+0xc84/0x1200 [act_pedit]
 [...]
 RIP: 0010:tcf_pedit_act+0xc84/0x1200 [act_pedit]
 Code: 89 fa 48 c1 ea 03 0f b6 04 02 84 c0 74 08 3c 03 0f 8e ac 00 00 00 48 8b 44 24 10 48 c7 c7 a0 c4 e4 c0 8b 70 18 e8 1c 30 95 ea <0f> 0b e9 a0 fa ff ff e8 00 03 f5 ea e9 14 f4 ff ff 48 89 58 40 e9
 RSP: 0018:ffff888077c9f320 EFLAGS: 00010286
 RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffffffffac2983a2
 RDX: 0000000000000001 RSI: 0000000000000008 RDI: ffff888053927bec
 RBP: dffffc0000000000 R08: ffffed100a726209 R09: ffffed100a726209
 R10: 0000000000000001 R11: ffffed100a726208 R12: ffff88804beea780
 R13: ffff888079a77400 R14: ffff88804beea780 R15: ffff888027ab2000
 FS:  00007fdeec9bd740(0000) GS:ffff888053900000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 00007ffdb3dfd000 CR3: 000000004adb4006 CR4: 00000000001606e0
 Call Trace:
  tcf_action_exec+0x105/0x3f0
  tcf_classify+0xf2/0x410
  __dev_queue_xmit+0xcbf/0x2ae0
  ip_finish_output2+0x711/0x1fb0
  ip_output+0x1bf/0x4b0
  ip_send_skb+0x37/0xa0
  raw_sendmsg+0x180c/0x2430
  sock_sendmsg+0xdb/0x110
  __sys_sendto+0x257/0x2b0
  __x64_sys_sendto+0xdd/0x1b0
  do_syscall_64+0xa5/0x4e0
  entry_SYSCALL_64_after_hwframe+0x49/0xbe
 RIP: 0033:0x7fdeeb72e993
 Code: 48 8b 0d e0 74 2c 00 f7 d8 64 89 01 48 83 c8 ff c3 66 0f 1f 44 00 00 83 3d 0d d6 2c 00 00 75 13 49 89 ca b8 2c 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 34 c3 48 83 ec 08 e8 4b cc 00 00 48 89 04 24
 RSP: 002b:00007ffdb3de8a18 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
 RAX: ffffffffffffffda RBX: 000055c81972b700 RCX: 00007fdeeb72e993
 RDX: 0000000000000040 RSI: 000055c81972b700 RDI: 0000000000000003
 RBP: 00007ffdb3dea130 R08: 000055c819728510 R09: 0000000000000010
 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000040
 R13: 000055c81972b6c0 R14: 000055c81972969c R15: 0000000000000080

Fix this moving the check on 'nkeys' earlier in tcf_pedit_init(), so that
attempts to install rules having 0 keys are always rejected with -EINVAL.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_pedit.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index cdfaa79382a2..b5bc631b96b7 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -43,7 +43,7 @@ static struct tcf_pedit_key_ex *tcf_pedit_keys_ex_parse(struct nlattr *nla,
 	int err = -EINVAL;
 	int rem;
 
-	if (!nla || !n)
+	if (!nla)
 		return NULL;
 
 	keys_ex = kcalloc(n, sizeof(*k), GFP_KERNEL);
@@ -170,6 +170,10 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 	}
 
 	parm = nla_data(pattr);
+	if (!parm->nkeys) {
+		NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed");
+		return -EINVAL;
+	}
 	ksize = parm->nkeys * sizeof(struct tc_pedit_key);
 	if (nla_len(pattr) < sizeof(*parm) + ksize) {
 		NL_SET_ERR_MSG_ATTR(extack, pattr, "Length of TCA_PEDIT_PARMS or TCA_PEDIT_PARMS_EX pedit attribute is invalid");
@@ -183,12 +187,6 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 	index = parm->index;
 	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (!err) {
-		if (!parm->nkeys) {
-			tcf_idr_cleanup(tn, index);
-			NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed");
-			ret = -EINVAL;
-			goto out_free;
-		}
 		ret = tcf_idr_create(tn, index, est, a,
 				     &act_pedit_ops, bind, false);
 		if (ret) {
-- 
2.20.1


From deb9631fdd74333b3847a313b99d7f0b385895d6 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 18 Nov 2019 17:39:34 +0800
Subject: [PATCH 06/18] net: sched: ensure opts_len <= IP_TUNNEL_OPTS_MAX in
 act_tunnel_key

[ Upstream commit 4f0e97d070984d487df027f163e52bb72d1713d8 ]

info->options_len is 'u8' type, and when opts_len with a value >
IP_TUNNEL_OPTS_MAX, 'info->options_len = opts_len' will cast int
to u8 and set a wrong value to info->options_len.

Kernel crashed in my test when doing:

  # opts="0102:80:00800022"
  # for i in {1..99}; do opts="$opts,0102:80:00800022"; done
  # ip link add name geneve0 type geneve dstport 0 external
  # tc qdisc add dev eth0 ingress
  # tc filter add dev eth0 protocol ip parent ffff: \
       flower indev eth0 ip_proto udp action tunnel_key \
       set src_ip 10.0.99.192 dst_ip 10.0.99.193 \
       dst_port 6081 id 11 geneve_opts $opts \
       action mirred egress redirect dev geneve0

So we should do the similar check as cls_flower does, return error
when opts_len > IP_TUNNEL_OPTS_MAX in tunnel_key_copy_opts().

Fixes: 0ed5269f9e41 ("net/sched: add tunnel option support to act_tunnel_key")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_tunnel_key.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 2f83a79f76aa..d55669e14741 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -135,6 +135,10 @@ static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst,
 			if (opt_len < 0)
 				return opt_len;
 			opts_len += opt_len;
+			if (opts_len > IP_TUNNEL_OPTS_MAX) {
+				NL_SET_ERR_MSG(extack, "Tunnel options exceeds max size");
+				return -EINVAL;
+			}
 			if (dst) {
 				dst_len -= opt_len;
 				dst += opt_len;
-- 
2.20.1


From d9c0a5777d52ba3c0203c999a4c722b38eb9375a Mon Sep 17 00:00:00 2001
From: Martin Habets <mhabets@solarflare.com>
Date: Thu, 21 Nov 2019 17:52:15 +0000
Subject: [PATCH 07/18] sfc: Only cancel the PPS workqueue if it exists

[ Upstream commit 723eb53690041740a13ac78efeaf6804f5d684c9 ]

The workqueue only exists for the primary PF. For other functions
we hit a WARN_ON in kernel/workqueue.c.

Fixes: 7c236c43b838 ("sfc: Add support for IEEE-1588 PTP")
Signed-off-by: Martin Habets <mhabets@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/ptp.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c
index 02ed6d1b716c..af15a737c675 100644
--- a/drivers/net/ethernet/sfc/ptp.c
+++ b/drivers/net/ethernet/sfc/ptp.c
@@ -1531,7 +1531,8 @@ void efx_ptp_remove(struct efx_nic *efx)
 	(void)efx_ptp_disable(efx);
 
 	cancel_work_sync(&efx->ptp_data->work);
-	cancel_work_sync(&efx->ptp_data->pps_work);
+	if (efx->ptp_data->pps_workwq)
+		cancel_work_sync(&efx->ptp_data->pps_work);
 
 	skb_queue_purge(&efx->ptp_data->rxq);
 	skb_queue_purge(&efx->ptp_data->txq);
-- 
2.20.1


From 140e04860dc83aa74d75f76ab585d9c565df9333 Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Sun, 17 Nov 2019 10:18:59 +0200
Subject: [PATCH 08/18] net/mlxfw: Verify FSM error code translation doesn't
 exceed array size

[ Upstream commit 30e9e0550bf693c94bc15827781fe42dd60be634 ]

Array mlxfw_fsm_state_err_str contains value to string translation, when
values are provided by mlxfw_dev. If value is larger than
MLXFW_FSM_STATE_ERR_MAX, return "unknown error" as expected instead of
reading an address than exceed array size.

Fixes: 410ed13cae39 ("Add the mlxfw module for Mellanox firmware flash process")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c
index 67990406cba2..29e95d0a6ad1 100644
--- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c
+++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c
@@ -66,6 +66,8 @@ static int mlxfw_fsm_state_wait(struct mlxfw_dev *mlxfw_dev, u32 fwhandle,
 		return err;
 
 	if (fsm_state_err != MLXFW_FSM_STATE_ERR_OK) {
+		fsm_state_err = min_t(enum mlxfw_fsm_state_err,
+				      fsm_state_err, MLXFW_FSM_STATE_ERR_MAX);
 		pr_err("Firmware flash failed: %s\n",
 		       mlxfw_fsm_state_err_str[fsm_state_err]);
 		NL_SET_ERR_MSG_MOD(extack, "Firmware flash failed");
-- 
2.20.1


From 0c166ce90909bde9bc6017319564cca6d4e8e6b0 Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@mellanox.com>
Date: Wed, 13 Nov 2019 14:42:00 +0200
Subject: [PATCH 09/18] net/mlx5e: Fix set vf link state error flow

[ Upstream commit 751021218f7e66ee9bbaa2be23056e447cd75ec4 ]

Before this commit the ndo always returned success.
Fix that.

Fixes: 1ab2068a4c66 ("net/mlx5: Implement vports admin state backup/restore")
Signed-off-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 1f3891fde2eb..a3b2ce112508 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -2044,7 +2044,7 @@ int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw,
 
 unlock:
 	mutex_unlock(&esw->state_lock);
-	return 0;
+	return err;
 }
 
 int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw,
-- 
2.20.1


From aa4d896c7c7a03164e37a0e4887cb04de7a9aaa8 Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@mellanox.com>
Date: Thu, 5 Sep 2019 09:56:10 +0300
Subject: [PATCH 10/18] net/mlx5: Fix auto group size calculation

[ Upstream commit 97fd8da281f80e7e69e0114bc906575734d4dfaf ]

Once all the large flow groups (defined by the user when the flow table
is created - max_num_groups) were created, then all the following new
flow groups will have only one flow table entry, even though the flow table
has place to larger groups.
Fix the condition to prefer large flow group.

Fixes: f0d22d187473 ("net/mlx5_core: Introduce flow steering autogrouped flow table")
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 10 ++++++----
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.h |  1 +
 2 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 3e99799bdb40..a6a64531bc43 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -549,7 +549,7 @@ static void del_sw_flow_group(struct fs_node *node)
 
 	rhashtable_destroy(&fg->ftes_hash);
 	ida_destroy(&fg->fte_allocator);
-	if (ft->autogroup.active)
+	if (ft->autogroup.active && fg->max_ftes == ft->autogroup.group_size)
 		ft->autogroup.num_groups--;
 	err = rhltable_remove(&ft->fgs_hash,
 			      &fg->hash,
@@ -1095,6 +1095,8 @@ mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns,
 
 	ft->autogroup.active = true;
 	ft->autogroup.required_groups = max_num_groups;
+	/* We save place for flow groups in addition to max types */
+	ft->autogroup.group_size = ft->max_fte / (max_num_groups + 1);
 
 	return ft;
 }
@@ -1297,8 +1299,7 @@ static struct mlx5_flow_group *alloc_auto_flow_group(struct mlx5_flow_table  *ft
 		return ERR_PTR(-ENOENT);
 
 	if (ft->autogroup.num_groups < ft->autogroup.required_groups)
-		/* We save place for flow groups in addition to max types */
-		group_size = ft->max_fte / (ft->autogroup.required_groups + 1);
+		group_size = ft->autogroup.group_size;
 
 	/*  ft->max_fte == ft->autogroup.max_types */
 	if (group_size == 0)
@@ -1325,7 +1326,8 @@ static struct mlx5_flow_group *alloc_auto_flow_group(struct mlx5_flow_table  *ft
 	if (IS_ERR(fg))
 		goto out;
 
-	ft->autogroup.num_groups++;
+	if (group_size == ft->autogroup.group_size)
+		ft->autogroup.num_groups++;
 
 out:
 	return fg;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index c1252d6be0ef..80906aff21d7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -137,6 +137,7 @@ struct mlx5_flow_table {
 	struct {
 		bool			active;
 		unsigned int		required_groups;
+		unsigned int		group_size;
 		unsigned int		num_groups;
 	} autogroup;
 	/* Protect fwd_rules */
-- 
2.20.1


From 855f1ebe3e7cd65f590988b48c30e24c82f527bc Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Mon, 18 Nov 2019 10:40:51 -0500
Subject: [PATCH 11/18] net/tls: enable sk_msg redirect to tls socket egress

[ Upstream commit d4ffb02dee2fcb20e0c8086a8d1305bf885820bb ]

Bring back tls_sw_sendpage_locked. sk_msg redirection into a socket
with TLS_TX takes the following path:

  tcp_bpf_sendmsg_redir
    tcp_bpf_push_locked
      tcp_bpf_push
        kernel_sendpage_locked
          sock->ops->sendpage_locked

Also update the flags test in tls_sw_sendpage_locked to allow flag
MSG_NO_SHARED_FRAGS. bpf_tcp_sendmsg sets this.

Link: https://lore.kernel.org/netdev/CA+FuTSdaAawmZ2N8nfDDKu3XLpXBbMtcCT0q4FntDD2gn8ASUw@mail.gmail.com/T/#t
Link: https://github.com/wdebruij/kerneltools/commits/icept.2
Fixes: 0608c69c9a80 ("bpf: sk_msg, sock{map|hash} redirect through ULP")
Fixes: f3de19af0f5b ("Revert \"net/tls: remove unused function tls_sw_sendpage_locked\"")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h  |  2 ++
 net/tls/tls_main.c |  1 +
 net/tls/tls_sw.c   | 11 +++++++++++
 3 files changed, 14 insertions(+)

diff --git a/include/net/tls.h b/include/net/tls.h
index bd1ef1a915e9..9bf04a74a6cb 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -364,6 +364,8 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx);
 void tls_sw_strparser_arm(struct sock *sk, struct tls_context *ctx);
 void tls_sw_strparser_done(struct tls_context *tls_ctx);
 int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
+int tls_sw_sendpage_locked(struct sock *sk, struct page *page,
+			   int offset, size_t size, int flags);
 int tls_sw_sendpage(struct sock *sk, struct page *page,
 		    int offset, size_t size, int flags);
 void tls_sw_cancel_work_tx(struct tls_context *tls_ctx);
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 9313dd51023a..ac2dfe36022d 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -852,6 +852,7 @@ static int __init tls_register(void)
 {
 	tls_sw_proto_ops = inet_stream_ops;
 	tls_sw_proto_ops.splice_read = tls_sw_splice_read;
+	tls_sw_proto_ops.sendpage_locked   = tls_sw_sendpage_locked,
 
 #ifdef CONFIG_TLS_DEVICE
 	tls_device_init();
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 881f06f465f8..41b2bdc05ba3 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1204,6 +1204,17 @@ static int tls_sw_do_sendpage(struct sock *sk, struct page *page,
 	return copied ? copied : ret;
 }
 
+int tls_sw_sendpage_locked(struct sock *sk, struct page *page,
+			   int offset, size_t size, int flags)
+{
+	if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
+		      MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY |
+		      MSG_NO_SHARED_FRAGS))
+		return -ENOTSUPP;
+
+	return tls_sw_do_sendpage(sk, page, offset, size, flags);
+}
+
 int tls_sw_sendpage(struct sock *sk, struct page *page,
 		    int offset, size_t size, int flags)
 {
-- 
2.20.1


From 09ded1f0ea19d87ce76536d6cdd4ce1d1c7667cf Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Wed, 20 Nov 2019 15:39:06 +0800
Subject: [PATCH 12/18] ipv6/route: return if there is no fib_nh_gw_family

[ Upstream commit 004b39427f945696db30abb2c4e1a3856ffff819 ]

Previously we will return directly if (!rt || !rt->fib6_nh.fib_nh_gw_family)
in function rt6_probe(), but after commit cc3a86c802f0
("ipv6: Change rt6_probe to take a fib6_nh"), the logic changed to
return if there is fib_nh_gw_family.

Fixes: cc3a86c802f0 ("ipv6: Change rt6_probe to take a fib6_nh")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 2b25a0de0364..56c8c990b6f2 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -634,7 +634,7 @@ static void rt6_probe(struct fib6_nh *fib6_nh)
 	 * Router Reachability Probe MUST be rate-limited
 	 * to no more than one per minute.
 	 */
-	if (fib6_nh->fib_nh_gw_family)
+	if (!fib6_nh->fib_nh_gw_family)
 		return;
 
 	nh_gw = &fib6_nh->fib_nh_gw6;
-- 
2.20.1


From 443802185cac3a4f0963b61f8692c2af2e327e43 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Marek=20Beh=C3=BAn?= <marek.behun@nic.cz>
Date: Mon, 18 Nov 2019 19:15:05 +0100
Subject: [PATCH 13/18] mdio_bus: fix mdio_register_device when
 RESET_CONTROLLER is disabled
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 075e238d12c21c8bde700d21fb48be7a3aa80194 ]

When CONFIG_RESET_CONTROLLER is disabled, the
devm_reset_control_get_exclusive function returns -ENOTSUPP. This is not
handled in subsequent check and then the mdio device fails to probe.

When CONFIG_RESET_CONTROLLER is enabled, its code checks in OF for reset
device, and since it is not present, returns -ENOENT. -ENOENT is handled.
Add -ENOTSUPP also.

This happened to me when upgrading kernel on Turris Omnia. You either
have to enable CONFIG_RESET_CONTROLLER or use this patch.

Signed-off-by: Marek Behún <marek.behun@nic.cz>
Fixes: 71dd6c0dff51b ("net: phy: add support for reset-controller")
Cc: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mdio_bus.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index bd04fe762056..2a79c7a7e920 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -68,11 +68,12 @@ static int mdiobus_register_reset(struct mdio_device *mdiodev)
 	if (mdiodev->dev.of_node)
 		reset = devm_reset_control_get_exclusive(&mdiodev->dev,
 							 "phy");
-	if (PTR_ERR(reset) == -ENOENT ||
-	    PTR_ERR(reset) == -ENOTSUPP)
-		reset = NULL;
-	else if (IS_ERR(reset))
-		return PTR_ERR(reset);
+	if (IS_ERR(reset)) {
+		if (PTR_ERR(reset) == -ENOENT || PTR_ERR(reset) == -ENOTSUPP)
+			reset = NULL;
+		else
+			return PTR_ERR(reset);
+	}
 
 	mdiodev->reset_ctrl = reset;
 
-- 
2.20.1


From a62ab1c878cb4777fe6fec162b91c9f8c7eddc4d Mon Sep 17 00:00:00 2001
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Tue, 19 Nov 2019 02:23:12 +0200
Subject: [PATCH 14/18] taprio: don't reject same mqprio settings

[ Upstream commit b5a0faa3572ac70bd374bd66190ac3ad4fddab20 ]

The taprio qdisc allows to set mqprio setting but only once. In case
if mqprio settings are provided next time the error is returned as
it's not allowed to change traffic class mapping in-flignt and that
is normal. But if configuration is absolutely the same - no need to
return error. It allows to provide same command couple times,
changing only base time for instance, or changing only scheds maps,
but leaving mqprio setting w/o modification. It more corresponds the
message: "Changing the traffic mapping of a running schedule is not
supported", so reject mqprio if it's really changed.

Also corrected TC_BITMASK + 1 for consistency, as proposed.

Fixes: a3d43c0d56f1 ("taprio: Add support adding an admin schedule")
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Tested-by: Vladimir Oltean <olteanv@gmail.com>
Acked-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_taprio.c | 28 ++++++++++++++++++++++++++--
 1 file changed, 26 insertions(+), 2 deletions(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 76bebe516194..92c0766d7f4f 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -842,7 +842,7 @@ static int taprio_parse_mqprio_opt(struct net_device *dev,
 	}
 
 	/* Verify priority mapping uses valid tcs */
-	for (i = 0; i < TC_BITMASK + 1; i++) {
+	for (i = 0; i <= TC_BITMASK; i++) {
 		if (qopt->prio_tc_map[i] >= qopt->num_tc) {
 			NL_SET_ERR_MSG(extack, "Invalid traffic class in priority to traffic class mapping");
 			return -EINVAL;
@@ -1014,6 +1014,26 @@ static void setup_txtime(struct taprio_sched *q,
 	}
 }
 
+static int taprio_mqprio_cmp(const struct net_device *dev,
+			     const struct tc_mqprio_qopt *mqprio)
+{
+	int i;
+
+	if (!mqprio || mqprio->num_tc != dev->num_tc)
+		return -1;
+
+	for (i = 0; i < mqprio->num_tc; i++)
+		if (dev->tc_to_txq[i].count != mqprio->count[i] ||
+		    dev->tc_to_txq[i].offset != mqprio->offset[i])
+			return -1;
+
+	for (i = 0; i <= TC_BITMASK; i++)
+		if (dev->prio_tc_map[i] != mqprio->prio_tc_map[i])
+			return -1;
+
+	return 0;
+}
+
 static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 			 struct netlink_ext_ack *extack)
 {
@@ -1065,6 +1085,10 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 	admin = rcu_dereference(q->admin_sched);
 	rcu_read_unlock();
 
+	/* no changes - no new mqprio settings */
+	if (!taprio_mqprio_cmp(dev, mqprio))
+		mqprio = NULL;
+
 	if (mqprio && (oper || admin)) {
 		NL_SET_ERR_MSG(extack, "Changing the traffic mapping of a running schedule is not supported");
 		err = -ENOTSUPP;
@@ -1132,7 +1156,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 					    mqprio->offset[i]);
 
 		/* Always use supplied priority mappings */
-		for (i = 0; i < TC_BITMASK + 1; i++)
+		for (i = 0; i <= TC_BITMASK; i++)
 			netdev_set_prio_tc_map(dev, i,
 					       mqprio->prio_tc_map[i]);
 	}
-- 
2.20.1


From 9ab7faefcc2bd0d1683ba52cb91a23c28992124d Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Mon, 18 Nov 2019 09:46:09 -0300
Subject: [PATCH 15/18] net/ipv4: fix sysctl max for fib_multipath_hash_policy

[ Upstream commit ca749bbb108c24a876014c804f9777c545be4d59 ]

Commit eec4844fae7c ("proc/sysctl: add shared variables for range
check") did:
-               .extra2         = &two,
+               .extra2         = SYSCTL_ONE,
here, which doesn't seem to be intentional, given the changelog.
This patch restores it to the previous, as the value of 2 still makes
sense (used in fib_multipath_hash()).

Fixes: eec4844fae7c ("proc/sysctl: add shared variables for range check")
Cc: Matteo Croce <mcroce@redhat.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/sysctl_net_ipv4.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 0b980e841927..c45b7d738cd1 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -1028,7 +1028,7 @@ static struct ctl_table ipv4_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_fib_multipath_hash_policy,
 		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_ONE,
+		.extra2		= &two,
 	},
 #endif
 	{
-- 
2.20.1


From 600191339efe5756bad447682051171d3ebcb748 Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.com>
Date: Thu, 31 Oct 2019 09:00:43 +0200
Subject: [PATCH 16/18] net/mlx5e: Fix error flow cleanup in
 mlx5e_tc_tun_create_header_ipv4/6

[ Upstream commit a86db2269fca8019074b720baf2e0a35cddac4e9 ]

Be sure to release the neighbour in case of failures after successful
route lookup.

Fixes: 101f4de9dd52 ("net/mlx5e: Move TC tunnel offloading code to separate source file")
Signed-off-by: Eli Cohen <eli@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../ethernet/mellanox/mlx5/core/en/tc_tun.c    | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index 310f65ef5446..d41c520ce0a8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -232,12 +232,15 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
 	if (max_encap_size < ipv4_encap_size) {
 		mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n",
 			       ipv4_encap_size, max_encap_size);
-		return -EOPNOTSUPP;
+		err = -EOPNOTSUPP;
+		goto out;
 	}
 
 	encap_header = kzalloc(ipv4_encap_size, GFP_KERNEL);
-	if (!encap_header)
-		return -ENOMEM;
+	if (!encap_header) {
+		err = -ENOMEM;
+		goto out;
+	}
 
 	/* used by mlx5e_detach_encap to lookup a neigh hash table
 	 * entry in the neigh hash table when a user deletes a rule
@@ -348,12 +351,15 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 	if (max_encap_size < ipv6_encap_size) {
 		mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n",
 			       ipv6_encap_size, max_encap_size);
-		return -EOPNOTSUPP;
+		err = -EOPNOTSUPP;
+		goto out;
 	}
 
 	encap_header = kzalloc(ipv6_encap_size, GFP_KERNEL);
-	if (!encap_header)
-		return -ENOMEM;
+	if (!encap_header) {
+		err = -ENOMEM;
+		goto out;
+	}
 
 	/* used by mlx5e_detach_encap to lookup a neigh hash table
 	 * entry in the neigh hash table when a user deletes a rule
-- 
2.20.1


From 6b9682179bb4ec9a37159e4bfda0cc5912141cc8 Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Sun, 17 Nov 2019 15:17:05 +0200
Subject: [PATCH 17/18] net/mlx5e: Do not use non-EXT link modes in EXT mode

[ Upstream commit 24960574505c49b102ca1dfa6bf109669bca2a66 ]

On some old Firmwares, connector type value was not supported, and value
read from FW was 0. For those, driver used link mode in order to set
connector type in link_ksetting.

After FW exposed the connector type, driver translated the value to ethtool
definitions. However, as 0 is a valid value, before returning PORT_OTHER,
driver run the check of link mode in order to maintain backward
compatibility.

Cited patch added support to EXT mode.  With both features (connector type
and EXT link modes) ,if connector_type read from FW is 0 and EXT mode is
set, driver mistakenly compare EXT link modes to non-EXT link mode.
Fixed that by skipping this comparison if we are in EXT mode, as connector
type value is valid in this scenario.

Fixes: 6a897372417e ("net/mlx5: ethtool, Add ethtool support for 50Gbps per lane link modes")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Reviewed-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index a9bb8e2b34a7..8d4856860365 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -708,9 +708,9 @@ static int get_fec_supported_advertised(struct mlx5_core_dev *dev,
 
 static void ptys2ethtool_supported_advertised_port(struct ethtool_link_ksettings *link_ksettings,
 						   u32 eth_proto_cap,
-						   u8 connector_type)
+						   u8 connector_type, bool ext)
 {
-	if (!connector_type || connector_type >= MLX5E_CONNECTOR_TYPE_NUMBER) {
+	if ((!connector_type && !ext) || connector_type >= MLX5E_CONNECTOR_TYPE_NUMBER) {
 		if (eth_proto_cap & (MLX5E_PROT_MASK(MLX5E_10GBASE_CR)
 				   | MLX5E_PROT_MASK(MLX5E_10GBASE_SR)
 				   | MLX5E_PROT_MASK(MLX5E_40GBASE_CR4)
@@ -842,9 +842,9 @@ static int ptys2connector_type[MLX5E_CONNECTOR_TYPE_NUMBER] = {
 		[MLX5E_PORT_OTHER]              = PORT_OTHER,
 	};
 
-static u8 get_connector_port(u32 eth_proto, u8 connector_type)
+static u8 get_connector_port(u32 eth_proto, u8 connector_type, bool ext)
 {
-	if (connector_type && connector_type < MLX5E_CONNECTOR_TYPE_NUMBER)
+	if ((connector_type || ext) && connector_type < MLX5E_CONNECTOR_TYPE_NUMBER)
 		return ptys2connector_type[connector_type];
 
 	if (eth_proto &
@@ -945,9 +945,9 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv,
 	eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap;
 
 	link_ksettings->base.port = get_connector_port(eth_proto_oper,
-						       connector_type);
+						       connector_type, ext);
 	ptys2ethtool_supported_advertised_port(link_ksettings, eth_proto_admin,
-					       connector_type);
+					       connector_type, ext);
 	get_lp_advertising(mdev, eth_proto_lp, link_ksettings);
 
 	if (an_status == MLX5_AN_COMPLETE)
-- 
2.20.1


From e9c1216a019ccbabdfffa7cda27896705cad642c Mon Sep 17 00:00:00 2001
From: Shani Shapp <shanish@mellanox.com>
Date: Tue, 12 Nov 2019 15:10:00 +0200
Subject: [PATCH 18/18] net/mlx5: Update the list of the PCI supported devices

[ Upstream commit b7eca940322f47fd30dafb70da04d193a0154090 ]

Add the upcoming ConnectX-6 LX device ID.

Fixes: 85327a9c4150 ("net/mlx5: Update the list of the PCI supported devices")
Signed-off-by: Shani Shapp <shanish@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index fda4964c5cf4..5e2b56305a3a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1552,6 +1552,7 @@ static const struct pci_device_id mlx5_core_pci_table[] = {
 	{ PCI_VDEVICE(MELLANOX, 0x101c), MLX5_PCI_DEV_IS_VF},	/* ConnectX-6 VF */
 	{ PCI_VDEVICE(MELLANOX, 0x101d) },			/* ConnectX-6 Dx */
 	{ PCI_VDEVICE(MELLANOX, 0x101e), MLX5_PCI_DEV_IS_VF},	/* ConnectX Family mlx5Gen Virtual Function */
+	{ PCI_VDEVICE(MELLANOX, 0x101f) },			/* ConnectX-6 LX */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d2) },			/* BlueField integrated ConnectX-5 network controller */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d3), MLX5_PCI_DEV_IS_VF},	/* BlueField integrated ConnectX-5 network controller VF */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d6) },			/* BlueField-2 integrated ConnectX-6 Dx network controller */
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Sun, Nov 24, 2019 at 09:54:49PM -0800, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.19 and v5.3
> -stable, respectively.

All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 105 bytes --]


Please queue up the following networking bug fixes for v5.3 and v5.4
-stable, respectively.

Thank you!

[-- Attachment #2: net_53.mbox --]
[-- Type: Application/Octet-Stream, Size: 61368 bytes --]

From 0be1ba148d18484e95a045920b1424ae7a1adc80 Mon Sep 17 00:00:00 2001
From: Jeroen de Borst <jeroendb@google.com>
Date: Tue, 26 Nov 2019 15:36:19 -0800
Subject: [PATCH 01/23] gve: Fix the queue page list allocated pages count

[ Upstream commit a95069ecb7092d03b2ea1c39ee04514fe9627540 ]

In gve_alloc_queue_page_list(), when a page allocation fails,
qpl->num_entries will be wrong.  In this case priv->num_registered_pages
can underflow in gve_free_queue_page_list(), causing subsequent calls
to gve_alloc_queue_page_list() to fail.

Fixes: f5cedc84a30d ("gve: Add transmit and receive support")
Signed-off-by: Jeroen de Borst <jeroendb@google.com>
Reviewed-by: Catherine Sullivan <csully@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/google/gve/gve_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index aca95f64bde8..9b7a8db9860f 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -544,7 +544,7 @@ static int gve_alloc_queue_page_list(struct gve_priv *priv, u32 id,
 	}
 
 	qpl->id = id;
-	qpl->num_entries = pages;
+	qpl->num_entries = 0;
 	qpl->pages = kvzalloc(pages * sizeof(*qpl->pages), GFP_KERNEL);
 	/* caller handles clean up */
 	if (!qpl->pages)
@@ -562,6 +562,7 @@ static int gve_alloc_queue_page_list(struct gve_priv *priv, u32 id,
 		/* caller handles clean up */
 		if (err)
 			return -ENOMEM;
+		qpl->num_entries++;
 	}
 	priv->num_registered_pages += pages;
 
-- 
2.20.1


From aec209eb864cbaff135da17e755549226d7eaff4 Mon Sep 17 00:00:00 2001
From: Menglong Dong <dong.menglong@zte.com.cn>
Date: Mon, 25 Nov 2019 16:58:09 +0800
Subject: [PATCH 02/23] macvlan: schedule bc_work even if error

[ Upstream commit 1d7ea55668878bb350979c377fc72509dd6f5b21 ]

While enqueueing a broadcast skb to port->bc_queue, schedule_work()
is called to add port->bc_work, which processes the skbs in
bc_queue, to "events" work queue. If port->bc_queue is full, the
skb will be discarded and schedule_work(&port->bc_work) won't be
called. However, if port->bc_queue is full and port->bc_work is not
running or pending, port->bc_queue will keep full and schedule_work()
won't be called any more, and all broadcast skbs to macvlan will be
discarded. This case can happen:

macvlan_process_broadcast() is the pending function of port->bc_work,
it moves all the skbs in port->bc_queue to the queue "list", and
processes the skbs in "list". During this, new skbs will keep being
added to port->bc_queue in macvlan_broadcast_enqueue(), and
port->bc_queue may already full when macvlan_process_broadcast()
return. This may happen, especially when there are a lot of real-time
threads and the process is preempted.

Fix this by calling schedule_work(&port->bc_work) even if
port->bc_work is full in macvlan_broadcast_enqueue().

Fixes: 412ca1550cbe ("macvlan: Move broadcasts into a work queue")
Signed-off-by: Menglong Dong <dong.menglong@zte.com.cn>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macvlan.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 940192c057b6..16b86fa60962 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -359,10 +359,11 @@ static void macvlan_broadcast_enqueue(struct macvlan_port *port,
 	}
 	spin_unlock(&port->bc_queue.lock);
 
+	schedule_work(&port->bc_work);
+
 	if (err)
 		goto free_nskb;
 
-	schedule_work(&port->bc_work);
 	return;
 
 free_nskb:
-- 
2.20.1


From 42fee7f520c17b4f6ca9120fb68838d2597bc502 Mon Sep 17 00:00:00 2001
From: David Bauer <mail@david-bauer.net>
Date: Fri, 22 Nov 2019 22:44:51 +0100
Subject: [PATCH 03/23] mdio_bus: don't use managed reset-controller

[ Upstream commit 32085f25d7b68404055f3525c780142fc72e543f ]

Geert Uytterhoeven reported that using devm_reset_controller_get leads
to a WARNING when probing a reset-controlled PHY. This is because the
device devm_reset_controller_get gets supplied is not actually the
one being probed.

Acquire an unmanaged reset-control as well as free the reset_control on
unregister to fix this.

Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
CC: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David Bauer <mail@david-bauer.net>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mdio_bus.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index 2a79c7a7e920..9fa1c93ece7a 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -66,8 +66,8 @@ static int mdiobus_register_reset(struct mdio_device *mdiodev)
 	struct reset_control *reset = NULL;
 
 	if (mdiodev->dev.of_node)
-		reset = devm_reset_control_get_exclusive(&mdiodev->dev,
-							 "phy");
+		reset = of_reset_control_get_exclusive(mdiodev->dev.of_node,
+						       "phy");
 	if (IS_ERR(reset)) {
 		if (PTR_ERR(reset) == -ENOENT || PTR_ERR(reset) == -ENOTSUPP)
 			reset = NULL;
@@ -111,6 +111,8 @@ int mdiobus_unregister_device(struct mdio_device *mdiodev)
 	if (mdiodev->bus->mdio_map[mdiodev->addr] != mdiodev)
 		return -EINVAL;
 
+	reset_control_put(mdiodev->reset_ctrl);
+
 	mdiodev->bus->mdio_map[mdiodev->addr] = NULL;
 
 	return 0;
-- 
2.20.1


From 898dfce11ad753581eb9c73c92ce9d4934908bb7 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Mon, 25 Nov 2019 12:43:51 +0100
Subject: [PATCH 04/23] net: dsa: sja1105: fix sja1105_parse_rgmii_delays()

[ Upstream commit 9bca3a0a923fc3f0fb9e41391be1d0f291e86858 ]

This function was using configuration of port 0 in devicetree for all ports.
In case CPU port was not 0, the delay settings was ignored. This resulted not
working communication between CPU and the switch.

Fixes: f5b8631c293b ("net: dsa: sja1105: Error out if RGMII delays are requested in DT")
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/sja1105/sja1105_main.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index 296286f4fb39..5763ae6c6c6a 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -591,15 +591,15 @@ static int sja1105_parse_rgmii_delays(struct sja1105_private *priv,
 	int i;
 
 	for (i = 0; i < SJA1105_NUM_PORTS; i++) {
-		if (ports->role == XMII_MAC)
+		if (ports[i].role == XMII_MAC)
 			continue;
 
-		if (ports->phy_mode == PHY_INTERFACE_MODE_RGMII_RXID ||
-		    ports->phy_mode == PHY_INTERFACE_MODE_RGMII_ID)
+		if (ports[i].phy_mode == PHY_INTERFACE_MODE_RGMII_RXID ||
+		    ports[i].phy_mode == PHY_INTERFACE_MODE_RGMII_ID)
 			priv->rgmii_rx_delay[i] = true;
 
-		if (ports->phy_mode == PHY_INTERFACE_MODE_RGMII_TXID ||
-		    ports->phy_mode == PHY_INTERFACE_MODE_RGMII_ID)
+		if (ports[i].phy_mode == PHY_INTERFACE_MODE_RGMII_TXID ||
+		    ports[i].phy_mode == PHY_INTERFACE_MODE_RGMII_ID)
 			priv->rgmii_tx_delay[i] = true;
 
 		if ((priv->rgmii_rx_delay[i] || priv->rgmii_tx_delay[i]) &&
-- 
2.20.1


From 3c46123b83841b88e711a064ffda6208a75bfa18 Mon Sep 17 00:00:00 2001
From: Chuhong Yuan <hslester96@gmail.com>
Date: Thu, 28 Nov 2019 10:00:21 +0800
Subject: [PATCH 05/23] net: macb: add missed tasklet_kill

[ Upstream commit 61183b056b49e2937ff92a1424291ba36a6f6d05 ]

This driver forgets to kill tasklet in remove.
Add the call to fix it.

Fixes: 032dc41ba6e2 ("net: macb: Handle HRESP error")
Signed-off-by: Chuhong Yuan <hslester96@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 35b59b5edf0f..a09a4be1d055 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -4393,6 +4393,7 @@ static int macb_remove(struct platform_device *pdev)
 		mdiobus_free(bp->mii_bus);
 
 		unregister_netdev(dev);
+		tasklet_kill(&bp->hresp_err_tasklet);
 		pm_runtime_disable(&pdev->dev);
 		pm_runtime_dont_use_autosuspend(&pdev->dev);
 		if (!pm_runtime_suspended(&pdev->dev)) {
-- 
2.20.1


From 67eb096a6229dc8deb9a8310a31d18a8c7550c5f Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Wed, 27 Nov 2019 00:16:44 +0200
Subject: [PATCH 06/23] net: psample: fix skb_over_panic

[ Upstream commit 7eb9d7675c08937cd11d32b0b40442d4d731c5ee ]

We need to calculate the skb size correctly otherwise we risk triggering
skb_over_panic[1]. The issue is that data_len is added to the skb in a
nl attribute, but we don't account for its header size (nlattr 4 bytes)
and alignment. We account for it when calculating the total size in
the > PSAMPLE_MAX_PACKET_SIZE comparison correctly, but not when
allocating after that. The fix is simple - use nla_total_size() for
data_len when allocating.

To reproduce:
 $ tc qdisc add dev eth1 clsact
 $ tc filter add dev eth1 egress matchall action sample rate 1 group 1 trunc 129
 $ mausezahn eth1 -b bcast -a rand -c 1 -p 129
 < skb_over_panic BUG(), tail is 4 bytes past skb->end >

[1] Trace:
 [   50.459526][ T3480] skbuff: skb_over_panic: text:(____ptrval____) len:196 put:136 head:(____ptrval____) data:(____ptrval____) tail:0xc4 end:0xc0 dev:<NULL>
 [   50.474339][ T3480] ------------[ cut here ]------------
 [   50.481132][ T3480] kernel BUG at net/core/skbuff.c:108!
 [   50.486059][ T3480] invalid opcode: 0000 [#1] PREEMPT SMP
 [   50.489463][ T3480] CPU: 3 PID: 3480 Comm: mausezahn Not tainted 5.4.0-rc7 #108
 [   50.492844][ T3480] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-2.fc30 04/01/2014
 [   50.496551][ T3480] RIP: 0010:skb_panic+0x79/0x7b
 [   50.498261][ T3480] Code: bc 00 00 00 41 57 4c 89 e6 48 c7 c7 90 29 9a 83 4c 8b 8b c0 00 00 00 50 8b 83 b8 00 00 00 50 ff b3 c8 00 00 00 e8 ae ef c0 fe <0f> 0b e8 2f df c8 fe 48 8b 55 08 44 89 f6 4c 89 e7 48 c7 c1 a0 22
 [   50.504111][ T3480] RSP: 0018:ffffc90000447a10 EFLAGS: 00010282
 [   50.505835][ T3480] RAX: 0000000000000087 RBX: ffff888039317d00 RCX: 0000000000000000
 [   50.507900][ T3480] RDX: 0000000000000000 RSI: ffffffff812716e1 RDI: 00000000ffffffff
 [   50.509820][ T3480] RBP: ffffc90000447a60 R08: 0000000000000001 R09: 0000000000000000
 [   50.511735][ T3480] R10: ffffffff81d4f940 R11: 0000000000000000 R12: ffffffff834a22b0
 [   50.513494][ T3480] R13: ffffffff82c10433 R14: 0000000000000088 R15: ffffffff838a8084
 [   50.515222][ T3480] FS:  00007f3536462700(0000) GS:ffff88803eac0000(0000) knlGS:0000000000000000
 [   50.517135][ T3480] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 [   50.518583][ T3480] CR2: 0000000000442008 CR3: 000000003b222000 CR4: 00000000000006e0
 [   50.520723][ T3480] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
 [   50.522709][ T3480] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
 [   50.524450][ T3480] Call Trace:
 [   50.525214][ T3480]  skb_put.cold+0x1b/0x1b
 [   50.526171][ T3480]  psample_sample_packet+0x1d3/0x340
 [   50.527307][ T3480]  tcf_sample_act+0x178/0x250
 [   50.528339][ T3480]  tcf_action_exec+0xb1/0x190
 [   50.529354][ T3480]  mall_classify+0x67/0x90
 [   50.530332][ T3480]  tcf_classify+0x72/0x160
 [   50.531286][ T3480]  __dev_queue_xmit+0x3db/0xd50
 [   50.532327][ T3480]  dev_queue_xmit+0x18/0x20
 [   50.533299][ T3480]  packet_sendmsg+0xee7/0x2090
 [   50.534331][ T3480]  sock_sendmsg+0x54/0x70
 [   50.535271][ T3480]  __sys_sendto+0x148/0x1f0
 [   50.536252][ T3480]  ? tomoyo_file_ioctl+0x23/0x30
 [   50.537334][ T3480]  ? ksys_ioctl+0x5e/0xb0
 [   50.540068][ T3480]  __x64_sys_sendto+0x2a/0x30
 [   50.542810][ T3480]  do_syscall_64+0x73/0x1f0
 [   50.545383][ T3480]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
 [   50.548477][ T3480] RIP: 0033:0x7f35357d6fb3
 [   50.551020][ T3480] Code: 48 8b 0d 18 90 20 00 f7 d8 64 89 01 48 83 c8 ff c3 66 0f 1f 44 00 00 83 3d f9 d3 20 00 00 75 13 49 89 ca b8 2c 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 34 c3 48 83 ec 08 e8 eb f6 ff ff 48 89 04 24
 [   50.558547][ T3480] RSP: 002b:00007ffe0c7212c8 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
 [   50.561870][ T3480] RAX: ffffffffffffffda RBX: 0000000001dac010 RCX: 00007f35357d6fb3
 [   50.565142][ T3480] RDX: 0000000000000082 RSI: 0000000001dac2a2 RDI: 0000000000000003
 [   50.568469][ T3480] RBP: 00007ffe0c7212f0 R08: 00007ffe0c7212d0 R09: 0000000000000014
 [   50.571731][ T3480] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000082
 [   50.574961][ T3480] R13: 0000000001dac2a2 R14: 0000000000000001 R15: 0000000000000003
 [   50.578170][ T3480] Modules linked in: sch_ingress virtio_net
 [   50.580976][ T3480] ---[ end trace 61a515626a595af6 ]---

CC: Yotam Gigi <yotamg@mellanox.com>
CC: Jiri Pirko <jiri@mellanox.com>
CC: Jamal Hadi Salim <jhs@mojatatu.com>
CC: Simon Horman <simon.horman@netronome.com>
CC: Roopa Prabhu <roopa@cumulusnetworks.com>
Fixes: 6ae0a6286171 ("net: Introduce psample, a new genetlink channel for packet sampling")
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/psample/psample.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/psample/psample.c b/net/psample/psample.c
index 66e4b61a350d..a3f7e35dccac 100644
--- a/net/psample/psample.c
+++ b/net/psample/psample.c
@@ -221,7 +221,7 @@ void psample_sample_packet(struct psample_group *group, struct sk_buff *skb,
 		data_len = PSAMPLE_MAX_PACKET_SIZE - meta_len - NLA_HDRLEN
 			    - NLA_ALIGNTO;
 
-	nl_skb = genlmsg_new(meta_len + data_len, GFP_ATOMIC);
+	nl_skb = genlmsg_new(meta_len + nla_total_size(data_len), GFP_ATOMIC);
 	if (unlikely(!nl_skb))
 		return;
 
-- 
2.20.1


From 8a1e9c33ab53ff6a01d4b6f2994208f9c40aff3a Mon Sep 17 00:00:00 2001
From: Dust Li <dust.li@linux.alibaba.com>
Date: Thu, 28 Nov 2019 14:29:09 +0800
Subject: [PATCH 07/23] net: sched: fix `tc -s class show` no bstats on class
 with nolock subqueues

[ Upstream commit 14e54ab9143fa60794d13ea0a66c792a2046a8f3 ]

When a classful qdisc's child qdisc has set the flag
TCQ_F_CPUSTATS (pfifo_fast for example), the child qdisc's
cpu_bstats should be passed to gnet_stats_copy_basic(),
but many classful qdisc didn't do that. As a result,
`tc -s class show dev DEV` always return 0 for bytes and
packets in this case.

Pass the child qdisc's cpu_bstats to gnet_stats_copy_basic()
to fix this issue.

The qstats also has this problem, but it has been fixed
in 5dd431b6b9 ("net: sched: introduce and use qstats read...")
and bstats still remains buggy.

Fixes: 22e0f8b9322c ("net: sched: make bstats per cpu and estimator RCU safe")
Signed-off-by: Dust Li <dust.li@linux.alibaba.com>
Signed-off-by: Tony Lu <tonylu@linux.alibaba.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_mq.c     | 3 ++-
 net/sched/sch_mqprio.c | 4 ++--
 net/sched/sch_multiq.c | 2 +-
 net/sched/sch_prio.c   | 2 +-
 4 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
index 0d578333e967..278c0b2dc523 100644
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -245,7 +245,8 @@ static int mq_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 	struct netdev_queue *dev_queue = mq_queue_get(sch, cl);
 
 	sch = dev_queue->qdisc_sleeping;
-	if (gnet_stats_copy_basic(&sch->running, d, NULL, &sch->bstats) < 0 ||
+	if (gnet_stats_copy_basic(&sch->running, d, sch->cpu_bstats,
+				  &sch->bstats) < 0 ||
 	    qdisc_qstats_copy(d, sch) < 0)
 		return -1;
 	return 0;
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index 46980b8d66c5..0d0113a24962 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -557,8 +557,8 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 		struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl);
 
 		sch = dev_queue->qdisc_sleeping;
-		if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
-					  d, NULL, &sch->bstats) < 0 ||
+		if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), d,
+					  sch->cpu_bstats, &sch->bstats) < 0 ||
 		    qdisc_qstats_copy(d, sch) < 0)
 			return -1;
 	}
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index e1087746f6a2..5cdf3b6abae6 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -330,7 +330,7 @@ static int multiq_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 
 	cl_q = q->queues[cl - 1];
 	if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
-				  d, NULL, &cl_q->bstats) < 0 ||
+				  d, cl_q->cpu_bstats, &cl_q->bstats) < 0 ||
 	    qdisc_qstats_copy(d, cl_q) < 0)
 		return -1;
 
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index 0f8fedb8809a..18b884cfdfe8 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -356,7 +356,7 @@ static int prio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 
 	cl_q = q->queues[cl - 1];
 	if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
-				  d, NULL, &cl_q->bstats) < 0 ||
+				  d, cl_q->cpu_bstats, &cl_q->bstats) < 0 ||
 	    qdisc_qstats_copy(d, cl_q) < 0)
 		return -1;
 
-- 
2.20.1


From 1fff291316d9edbf6649e7716112b9edc28d4edb Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 26 Nov 2019 12:55:50 +0100
Subject: [PATCH 08/23] openvswitch: fix flow command message size

[ Upstream commit 4e81c0b3fa93d07653e2415fa71656b080a112fd ]

When user-space sets the OVS_UFID_F_OMIT_* flags, and the relevant
flow has no UFID, we can exceed the computed size, as
ovs_nla_put_identifier() will always dump an OVS_FLOW_ATTR_KEY
attribute.
Take the above in account when computing the flow command message
size.

Fixes: 74ed7ab9264c ("openvswitch: Add support for unique flow IDs.")
Reported-by: Qi Jun Ding <qding@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/datapath.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 43aeca12208c..b3702b9b303f 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -701,9 +701,13 @@ static size_t ovs_flow_cmd_msg_size(const struct sw_flow_actions *acts,
 {
 	size_t len = NLMSG_ALIGN(sizeof(struct ovs_header));
 
-	/* OVS_FLOW_ATTR_UFID */
+	/* OVS_FLOW_ATTR_UFID, or unmasked flow key as fallback
+	 * see ovs_nla_put_identifier()
+	 */
 	if (sfid && ovs_identifier_is_ufid(sfid))
 		len += nla_total_size(sfid->ufid_len);
+	else
+		len += nla_total_size(ovs_key_attr_size());
 
 	/* OVS_FLOW_ATTR_KEY */
 	if (!sfid || should_fill_key(sfid, ufid_flags))
-- 
2.20.1


From 091cc6e4e512c12747c4cdbf0139511ba3c3cce9 Mon Sep 17 00:00:00 2001
From: Navid Emamdoost <navid.emamdoost@gmail.com>
Date: Fri, 22 Nov 2019 16:17:56 -0600
Subject: [PATCH 09/23] sctp: Fix memory leak in sctp_sf_do_5_2_4_dupcook

[ Upstream commit b6631c6031c746ed004c4221ec0616d7a520f441 ]

In the implementation of sctp_sf_do_5_2_4_dupcook() the allocated
new_asoc is leaked if security_sctp_assoc_request() fails. Release it
via sctp_association_free().

Fixes: 2277c7cd75e3 ("sctp: Add LSM hooks")
Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/sctp/sm_statefuns.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 2c244b29a199..9eeea0d8e4cf 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -2160,8 +2160,10 @@ enum sctp_disposition sctp_sf_do_5_2_4_dupcook(
 
 	/* Update socket peer label if first association. */
 	if (security_sctp_assoc_request((struct sctp_endpoint *)ep,
-					chunk->skb))
+					chunk->skb)) {
+		sctp_association_free(new_asoc);
 		return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+	}
 
 	/* Set temp so that it won't be added into hashtable */
 	new_asoc->temp = 1;
-- 
2.20.1


From 385d9e55c3dce94309db806ba1a2fdea143f6c21 Mon Sep 17 00:00:00 2001
From: Jouni Hogander <jouni.hogander@unikie.com>
Date: Mon, 25 Nov 2019 14:23:43 +0200
Subject: [PATCH 10/23] slip: Fix use-after-free Read in slip_open

[ Upstream commit e58c1912418980f57ba2060017583067f5f71e52 ]

Slip_open doesn't clean-up device which registration failed from the
slip_devs device list. On next open after failure this list is iterated
and freed device is accessed. Fix this by calling sl_free_netdev in error
path.

Here is the trace from the Syzbot:

__dump_stack lib/dump_stack.c:77 [inline]
dump_stack+0x197/0x210 lib/dump_stack.c:118
print_address_description.constprop.0.cold+0xd4/0x30b mm/kasan/report.c:374
__kasan_report.cold+0x1b/0x41 mm/kasan/report.c:506
kasan_report+0x12/0x20 mm/kasan/common.c:634
__asan_report_load8_noabort+0x14/0x20 mm/kasan/generic_report.c:132
sl_sync drivers/net/slip/slip.c:725 [inline]
slip_open+0xecd/0x11b7 drivers/net/slip/slip.c:801
tty_ldisc_open.isra.0+0xa3/0x110 drivers/tty/tty_ldisc.c:469
tty_set_ldisc+0x30e/0x6b0 drivers/tty/tty_ldisc.c:596
tiocsetd drivers/tty/tty_io.c:2334 [inline]
tty_ioctl+0xe8d/0x14f0 drivers/tty/tty_io.c:2594
vfs_ioctl fs/ioctl.c:46 [inline]
file_ioctl fs/ioctl.c:509 [inline]
do_vfs_ioctl+0xdb6/0x13e0 fs/ioctl.c:696
ksys_ioctl+0xab/0xd0 fs/ioctl.c:713
__do_sys_ioctl fs/ioctl.c:720 [inline]
__se_sys_ioctl fs/ioctl.c:718 [inline]
__x64_sys_ioctl+0x73/0xb0 fs/ioctl.c:718
do_syscall_64+0xfa/0x760 arch/x86/entry/common.c:290
entry_SYSCALL_64_after_hwframe+0x49/0xbe

Fixes: 3b5a39979daf ("slip: Fix memory leak in slip_open error path")
Reported-by: syzbot+4d5170758f3762109542@syzkaller.appspotmail.com
Cc: David Miller <davem@davemloft.net>
Cc: Oliver Hartkopp <socketcan@hartkopp.net>
Cc: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Signed-off-by: Jouni Hogander <jouni.hogander@unikie.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/slip/slip.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c
index 4d479e3c817d..2a91c192659f 100644
--- a/drivers/net/slip/slip.c
+++ b/drivers/net/slip/slip.c
@@ -855,6 +855,7 @@ static int slip_open(struct tty_struct *tty)
 	sl->tty = NULL;
 	tty->disc_data = NULL;
 	clear_bit(SLF_INUSE, &sl->flags);
+	sl_free_netdev(sl->dev);
 	free_netdev(sl->dev);
 
 err_exit:
-- 
2.20.1


From 89b03c33c463ad2577c1d4a8c8bb299a11965b77 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sat, 23 Nov 2019 11:56:49 +0800
Subject: [PATCH 11/23] sctp: cache netns in sctp_ep_common

[ Upstream commit 312434617cb16be5166316cf9d08ba760b1042a1 ]

This patch is to fix a data-race reported by syzbot:

  BUG: KCSAN: data-race in sctp_assoc_migrate / sctp_hash_obj

  write to 0xffff8880b67c0020 of 8 bytes by task 18908 on cpu 1:
    sctp_assoc_migrate+0x1a6/0x290 net/sctp/associola.c:1091
    sctp_sock_migrate+0x8aa/0x9b0 net/sctp/socket.c:9465
    sctp_accept+0x3c8/0x470 net/sctp/socket.c:4916
    inet_accept+0x7f/0x360 net/ipv4/af_inet.c:734
    __sys_accept4+0x224/0x430 net/socket.c:1754
    __do_sys_accept net/socket.c:1795 [inline]
    __se_sys_accept net/socket.c:1792 [inline]
    __x64_sys_accept+0x4e/0x60 net/socket.c:1792
    do_syscall_64+0xcc/0x370 arch/x86/entry/common.c:290
    entry_SYSCALL_64_after_hwframe+0x44/0xa9

  read to 0xffff8880b67c0020 of 8 bytes by task 12003 on cpu 0:
    sctp_hash_obj+0x4f/0x2d0 net/sctp/input.c:894
    rht_key_get_hash include/linux/rhashtable.h:133 [inline]
    rht_key_hashfn include/linux/rhashtable.h:159 [inline]
    rht_head_hashfn include/linux/rhashtable.h:174 [inline]
    head_hashfn lib/rhashtable.c:41 [inline]
    rhashtable_rehash_one lib/rhashtable.c:245 [inline]
    rhashtable_rehash_chain lib/rhashtable.c:276 [inline]
    rhashtable_rehash_table lib/rhashtable.c:316 [inline]
    rht_deferred_worker+0x468/0xab0 lib/rhashtable.c:420
    process_one_work+0x3d4/0x890 kernel/workqueue.c:2269
    worker_thread+0xa0/0x800 kernel/workqueue.c:2415
    kthread+0x1d4/0x200 drivers/block/aoe/aoecmd.c:1253
    ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:352

It was caused by rhashtable access asoc->base.sk when sctp_assoc_migrate
is changing its value. However, what rhashtable wants is netns from asoc
base.sk, and for an asoc, its netns won't change once set. So we can
simply fix it by caching netns since created.

Fixes: d6c0256a60e6 ("sctp: add the rhashtable apis for sctp global transport hashtable")
Reported-by: syzbot+e3b35fe7918ff0ee474e@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 include/net/sctp/structs.h | 3 +++
 net/sctp/associola.c       | 1 +
 net/sctp/endpointola.c     | 1 +
 net/sctp/input.c           | 4 ++--
 4 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index ba5c4f6eede5..eeee040b5397 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1239,6 +1239,9 @@ struct sctp_ep_common {
 	/* What socket does this endpoint belong to?  */
 	struct sock *sk;
 
+	/* Cache netns and it won't change once set */
+	struct net *net;
+
 	/* This is where we receive inbound chunks.  */
 	struct sctp_inq	  inqueue;
 
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 5010cce52c93..a40b80cdb4b3 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -65,6 +65,7 @@ static struct sctp_association *sctp_association_init(
 	/* Discarding const is appropriate here.  */
 	asoc->ep = (struct sctp_endpoint *)ep;
 	asoc->base.sk = (struct sock *)sk;
+	asoc->base.net = sock_net(sk);
 
 	sctp_endpoint_hold(asoc->ep);
 	sock_hold(asoc->base.sk);
diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c
index 69cebb2c998b..046da0bdc539 100644
--- a/net/sctp/endpointola.c
+++ b/net/sctp/endpointola.c
@@ -152,6 +152,7 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep,
 
 	/* Remember who we are attached to.  */
 	ep->base.sk = sk;
+	ep->base.net = sock_net(sk);
 	sock_hold(ep->base.sk);
 
 	return ep;
diff --git a/net/sctp/input.c b/net/sctp/input.c
index 1008cdc44dd6..2b43b5ed3241 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -876,7 +876,7 @@ static inline int sctp_hash_cmp(struct rhashtable_compare_arg *arg,
 	if (!sctp_transport_hold(t))
 		return err;
 
-	if (!net_eq(sock_net(t->asoc->base.sk), x->net))
+	if (!net_eq(t->asoc->base.net, x->net))
 		goto out;
 	if (x->lport != htons(t->asoc->base.bind_addr.port))
 		goto out;
@@ -891,7 +891,7 @@ static inline __u32 sctp_hash_obj(const void *data, u32 len, u32 seed)
 {
 	const struct sctp_transport *t = data;
 
-	return sctp_hashfn(sock_net(t->asoc->base.sk),
+	return sctp_hashfn(t->asoc->base.net,
 			   htons(t->asoc->base.bind_addr.port),
 			   &t->ipaddr, seed);
 }
-- 
2.20.1


From df157a3d0982124a5117ad180d95ac04b9fbae2a Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Sun, 1 Dec 2019 18:41:24 +0100
Subject: [PATCH 12/23] openvswitch: drop unneeded BUG_ON() in
 ovs_flow_cmd_build_info()

[ Upstream commit 8ffeb03fbba3b599690b361467bfd2373e8c450f ]

All the callers of ovs_flow_cmd_build_info() already deal with
error return code correctly, so we can handle the error condition
in a more gracefull way. Still dump a warning to preserve
debuggability.

v1 -> v2:
 - clarify the commit message
 - clean the skb and report the error (DaveM)

Fixes: ccb1352e76cf ("net: Add Open vSwitch kernel components.")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/datapath.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index b3702b9b303f..becadea649cc 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -883,7 +883,10 @@ static struct sk_buff *ovs_flow_cmd_build_info(const struct sw_flow *flow,
 	retval = ovs_flow_cmd_fill_info(flow, dp_ifindex, skb,
 					info->snd_portid, info->snd_seq, 0,
 					cmd, ufid_flags);
-	BUG_ON(retval < 0);
+	if (WARN_ON_ONCE(retval < 0)) {
+		kfree_skb(skb);
+		skb = ERR_PTR(retval);
+	}
 	return skb;
 }
 
-- 
2.20.1


From 4f1fe082f7488208ec15637ac3625605c4b0308a Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Sun, 1 Dec 2019 18:41:25 +0100
Subject: [PATCH 13/23] openvswitch: remove another BUG_ON()

[ Upstream commit 8a574f86652a4540a2433946ba826ccb87f398cc ]

If we can't build the flow del notification, we can simply delete
the flow, no need to crash the kernel. Still keep a WARN_ON to
preserve debuggability.

Note: the BUG_ON() predates the Fixes tag, but this change
can be applied only after the mentioned commit.

v1 -> v2:
 - do not leak an skb on error

Fixes: aed067783e50 ("openvswitch: Minimize ovs_flow_cmd_del critical section.")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/datapath.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index becadea649cc..f40757dbfb28 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -1350,7 +1350,10 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info)
 						     OVS_FLOW_CMD_DEL,
 						     ufid_flags);
 			rcu_read_unlock();
-			BUG_ON(err < 0);
+			if (WARN_ON_ONCE(err < 0)) {
+				kfree_skb(reply);
+				goto out_free;
+			}
 
 			ovs_notify(&dp_flow_genl_family, reply, info);
 		} else {
@@ -1358,6 +1361,7 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
+out_free:
 	ovs_flow_free(flow, true);
 	return 0;
 unlock:
-- 
2.20.1


From cc91fdb1654e7bf80b37ed48747772817865a5f2 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 27 Nov 2019 12:16:39 -0800
Subject: [PATCH 14/23] net/tls: take into account that bpf_exec_tx_verdict()
 may free the record

[ Upstream commit c329ef9684de9517d82af5b4758c9e1b64a8a11a ]

bpf_exec_tx_verdict() may free the record if tls_push_record()
fails, or if the entire record got consumed by BPF. Re-check
ctx->open_rec before touching the data.

Fixes: d3b18ad31f93 ("tls: add bpf support to sk_msg handling")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 41b2bdc05ba3..a337e22cfd30 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -979,7 +979,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 					num_async++;
 				else if (ret == -ENOMEM)
 					goto wait_for_memory;
-				else if (ret == -ENOSPC)
+				else if (ctx->open_rec && ret == -ENOSPC)
 					goto rollback_iter;
 				else if (ret != -EAGAIN)
 					goto send_end;
@@ -1048,11 +1048,12 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 		ret = sk_stream_wait_memory(sk, &timeo);
 		if (ret) {
 trim_sgl:
-			tls_trim_both_msgs(sk, orig_size);
+			if (ctx->open_rec)
+				tls_trim_both_msgs(sk, orig_size);
 			goto send_end;
 		}
 
-		if (msg_en->sg.size < required_size)
+		if (ctx->open_rec && msg_en->sg.size < required_size)
 			goto alloc_encrypted;
 	}
 
@@ -1185,11 +1186,13 @@ static int tls_sw_do_sendpage(struct sock *sk, struct page *page,
 wait_for_memory:
 		ret = sk_stream_wait_memory(sk, &timeo);
 		if (ret) {
-			tls_trim_both_msgs(sk, msg_pl->sg.size);
+			if (ctx->open_rec)
+				tls_trim_both_msgs(sk, msg_pl->sg.size);
 			goto sendpage_end;
 		}
 
-		goto alloc_payload;
+		if (ctx->open_rec)
+			goto alloc_payload;
 	}
 
 	if (num_async) {
-- 
2.20.1


From 325841ee5f18e91f239fa11c2f0dc78cba509f6e Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 27 Nov 2019 12:16:40 -0800
Subject: [PATCH 15/23] net/tls: free the record on encryption error

[ Upstream commit d10523d0b3d78153ee58d19853ced26c9004c8c4 ]

When tls_do_encryption() fails the SG lists are left with the
SG_END and SG_CHAIN marks in place. One could hope that once
encryption fails we will never see the record again, but that
is in fact not true. Commit d3b18ad31f93 ("tls: add bpf support
to sk_msg handling") added special handling to ENOMEM and ENOSPC
errors which mean we may see the same record re-submitted.

As suggested by John free the record, the BPF code is already
doing just that.

Reported-by: syzbot+df0d4ec12332661dd1f9@syzkaller.appspotmail.com
Fixes: d3b18ad31f93 ("tls: add bpf support to sk_msg handling")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index a337e22cfd30..8a7404c73bee 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -766,8 +766,14 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk,
 
 	policy = !(flags & MSG_SENDPAGE_NOPOLICY);
 	psock = sk_psock_get(sk);
-	if (!psock || !policy)
-		return tls_push_record(sk, flags, record_type);
+	if (!psock || !policy) {
+		err = tls_push_record(sk, flags, record_type);
+		if (err) {
+			*copied -= sk_msg_free(sk, msg);
+			tls_free_open_rec(sk);
+		}
+		return err;
+	}
 more_data:
 	enospc = sk_msg_full(msg);
 	if (psock->eval == __SK_NONE) {
-- 
2.20.1


From 741fc2940ae28cb706d6defd230712d1539c558e Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 27 Nov 2019 12:16:41 -0800
Subject: [PATCH 16/23] net: skmsg: fix TLS 1.3 crash with full sk_msg

[ Upstream commit 031097d9e079e40dce401031d1012e83d80eaf01 ]

TLS 1.3 started using the entry at the end of the SG array
for chaining-in the single byte content type entry. This mostly
works:

[ E E E E E E . . ]
  ^           ^
   start       end

                 E < content type
               /
[ E E E E E E C . ]
  ^           ^
   start       end

(Where E denotes a populated SG entry; C denotes a chaining entry.)

If the array is full, however, the end will point to the start:

[ E E E E E E E E ]
  ^
   start
   end

And we end up overwriting the start:

    E < content type
   /
[ C E E E E E E E ]
  ^
   start
   end

The sg array is supposed to be a circular buffer with start and
end markers pointing anywhere. In case where start > end
(i.e. the circular buffer has "wrapped") there is an extra entry
reserved at the end to chain the two halves together.

[ E E E E E E . . l ]

(Where l is the reserved entry for "looping" back to front.

As suggested by John, let's reserve another entry for chaining
SG entries after the main circular buffer. Note that this entry
has to be pointed to by the end entry so its position is not fixed.

Examples of full messages:

[ E E E E E E E E . l ]
  ^               ^
   start           end

   <---------------.
[ E E . E E E E E E l ]
      ^ ^
   end   start

Now the end will always point to an unused entry, so TLS 1.3
can always use it.

Fixes: 130b392c6cd6 ("net: tls: Add tls 1.3 support")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skmsg.h | 26 +++++++++++++-------------
 net/core/filter.c     |  8 ++++----
 net/core/skmsg.c      |  2 +-
 net/ipv4/tcp_bpf.c    |  2 +-
 4 files changed, 19 insertions(+), 19 deletions(-)

diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index ce7055259877..da4caff7efa4 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -14,6 +14,7 @@
 #include <net/strparser.h>
 
 #define MAX_MSG_FRAGS			MAX_SKB_FRAGS
+#define NR_MSG_FRAG_IDS			(MAX_MSG_FRAGS + 1)
 
 enum __sk_action {
 	__SK_DROP = 0,
@@ -29,11 +30,13 @@ struct sk_msg_sg {
 	u32				size;
 	u32				copybreak;
 	bool				copy[MAX_MSG_FRAGS];
-	/* The extra element is used for chaining the front and sections when
-	 * the list becomes partitioned (e.g. end < start). The crypto APIs
-	 * require the chaining.
+	/* The extra two elements:
+	 * 1) used for chaining the front and sections when the list becomes
+	 *    partitioned (e.g. end < start). The crypto APIs require the
+	 *    chaining;
+	 * 2) to chain tailer SG entries after the message.
 	 */
-	struct scatterlist		data[MAX_MSG_FRAGS + 1];
+	struct scatterlist		data[MAX_MSG_FRAGS + 2];
 };
 
 /* UAPI in filter.c depends on struct sk_msg_sg being first element. */
@@ -141,13 +144,13 @@ static inline void sk_msg_apply_bytes(struct sk_psock *psock, u32 bytes)
 
 static inline u32 sk_msg_iter_dist(u32 start, u32 end)
 {
-	return end >= start ? end - start : end + (MAX_MSG_FRAGS - start);
+	return end >= start ? end - start : end + (NR_MSG_FRAG_IDS - start);
 }
 
 #define sk_msg_iter_var_prev(var)			\
 	do {						\
 		if (var == 0)				\
-			var = MAX_MSG_FRAGS - 1;	\
+			var = NR_MSG_FRAG_IDS - 1;	\
 		else					\
 			var--;				\
 	} while (0)
@@ -155,7 +158,7 @@ static inline u32 sk_msg_iter_dist(u32 start, u32 end)
 #define sk_msg_iter_var_next(var)			\
 	do {						\
 		var++;					\
-		if (var == MAX_MSG_FRAGS)		\
+		if (var == NR_MSG_FRAG_IDS)		\
 			var = 0;			\
 	} while (0)
 
@@ -172,9 +175,9 @@ static inline void sk_msg_clear_meta(struct sk_msg *msg)
 
 static inline void sk_msg_init(struct sk_msg *msg)
 {
-	BUILD_BUG_ON(ARRAY_SIZE(msg->sg.data) - 1 != MAX_MSG_FRAGS);
+	BUILD_BUG_ON(ARRAY_SIZE(msg->sg.data) - 1 != NR_MSG_FRAG_IDS);
 	memset(msg, 0, sizeof(*msg));
-	sg_init_marker(msg->sg.data, MAX_MSG_FRAGS);
+	sg_init_marker(msg->sg.data, NR_MSG_FRAG_IDS);
 }
 
 static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src,
@@ -195,14 +198,11 @@ static inline void sk_msg_xfer_full(struct sk_msg *dst, struct sk_msg *src)
 
 static inline bool sk_msg_full(const struct sk_msg *msg)
 {
-	return (msg->sg.end == msg->sg.start) && msg->sg.size;
+	return sk_msg_iter_dist(msg->sg.start, msg->sg.end) == MAX_MSG_FRAGS;
 }
 
 static inline u32 sk_msg_elem_used(const struct sk_msg *msg)
 {
-	if (sk_msg_full(msg))
-		return MAX_MSG_FRAGS;
-
 	return sk_msg_iter_dist(msg->sg.start, msg->sg.end);
 }
 
diff --git a/net/core/filter.c b/net/core/filter.c
index 4c6a252d4212..d81a5a5090bd 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2299,7 +2299,7 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start,
 	WARN_ON_ONCE(last_sge == first_sge);
 	shift = last_sge > first_sge ?
 		last_sge - first_sge - 1 :
-		MAX_SKB_FRAGS - first_sge + last_sge - 1;
+		NR_MSG_FRAG_IDS - first_sge + last_sge - 1;
 	if (!shift)
 		goto out;
 
@@ -2308,8 +2308,8 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start,
 	do {
 		u32 move_from;
 
-		if (i + shift >= MAX_MSG_FRAGS)
-			move_from = i + shift - MAX_MSG_FRAGS;
+		if (i + shift >= NR_MSG_FRAG_IDS)
+			move_from = i + shift - NR_MSG_FRAG_IDS;
 		else
 			move_from = i + shift;
 		if (move_from == msg->sg.end)
@@ -2323,7 +2323,7 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start,
 	} while (1);
 
 	msg->sg.end = msg->sg.end - shift > msg->sg.end ?
-		      msg->sg.end - shift + MAX_MSG_FRAGS :
+		      msg->sg.end - shift + NR_MSG_FRAG_IDS :
 		      msg->sg.end - shift;
 out:
 	msg->data = sg_virt(&msg->sg.data[first_sge]) + start - offset;
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index c10e3e56006e..74c1f9909e88 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -422,7 +422,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb)
 	copied = skb->len;
 	msg->sg.start = 0;
 	msg->sg.size = copied;
-	msg->sg.end = num_sge == MAX_MSG_FRAGS ? 0 : num_sge;
+	msg->sg.end = num_sge;
 	msg->skb = skb;
 
 	sk_psock_queue_msg(psock, msg);
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 8a56e09cfb0e..e38705165ac9 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -301,7 +301,7 @@ EXPORT_SYMBOL_GPL(tcp_bpf_sendmsg_redir);
 static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,
 				struct sk_msg *msg, int *copied, int flags)
 {
-	bool cork = false, enospc = msg->sg.start == msg->sg.end;
+	bool cork = false, enospc = sk_msg_full(msg);
 	struct sock *sk_redir;
 	u32 tosend, delta = 0;
 	int ret;
-- 
2.20.1


From 96858635d2067b0714143a25ba1fead6f7f9357d Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 27 Nov 2019 12:16:42 -0800
Subject: [PATCH 17/23] selftests/tls: add a test for fragmented messages

[ Upstream commit 65190f77424d7b82c4aad7326c9cce6bd91a2fcc ]

Add a sendmsg test with very fragmented messages. This should
fill up sk_msg and test the boundary conditions.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/tls.c | 60 +++++++++++++++++++++++++++++++
 1 file changed, 60 insertions(+)

diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 1c8f194d6556..46abcae47dee 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -268,6 +268,38 @@ TEST_F(tls, sendmsg_single)
 	EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
 }
 
+#define MAX_FRAGS	64
+#define SEND_LEN	13
+TEST_F(tls, sendmsg_fragmented)
+{
+	char const *test_str = "test_sendmsg";
+	char buf[SEND_LEN * MAX_FRAGS];
+	struct iovec vec[MAX_FRAGS];
+	struct msghdr msg;
+	int i, frags;
+
+	for (frags = 1; frags <= MAX_FRAGS; frags++) {
+		for (i = 0; i < frags; i++) {
+			vec[i].iov_base = (char *)test_str;
+			vec[i].iov_len = SEND_LEN;
+		}
+
+		memset(&msg, 0, sizeof(struct msghdr));
+		msg.msg_iov = vec;
+		msg.msg_iovlen = frags;
+
+		EXPECT_EQ(sendmsg(self->fd, &msg, 0), SEND_LEN * frags);
+		EXPECT_EQ(recv(self->cfd, buf, SEND_LEN * frags, MSG_WAITALL),
+			  SEND_LEN * frags);
+
+		for (i = 0; i < frags; i++)
+			EXPECT_EQ(memcmp(buf + SEND_LEN * i,
+					 test_str, SEND_LEN), 0);
+	}
+}
+#undef MAX_FRAGS
+#undef SEND_LEN
+
 TEST_F(tls, sendmsg_large)
 {
 	void *mem = malloc(16384);
@@ -694,6 +726,34 @@ TEST_F(tls, recv_lowat)
 	EXPECT_EQ(memcmp(send_mem, recv_mem + 10, 5), 0);
 }
 
+TEST_F(tls, recv_rcvbuf)
+{
+	char send_mem[4096];
+	char recv_mem[4096];
+	int rcv_buf = 1024;
+
+	memset(send_mem, 0x1c, sizeof(send_mem));
+
+	EXPECT_EQ(setsockopt(self->cfd, SOL_SOCKET, SO_RCVBUF,
+			     &rcv_buf, sizeof(rcv_buf)), 0);
+
+	EXPECT_EQ(send(self->fd, send_mem, 512, 0), 512);
+	memset(recv_mem, 0, sizeof(recv_mem));
+	EXPECT_EQ(recv(self->cfd, recv_mem, sizeof(recv_mem), 0), 512);
+	EXPECT_EQ(memcmp(send_mem, recv_mem, 512), 0);
+
+	if (self->notls)
+		return;
+
+	EXPECT_EQ(send(self->fd, send_mem, 4096, 0), 4096);
+	memset(recv_mem, 0, sizeof(recv_mem));
+	EXPECT_EQ(recv(self->cfd, recv_mem, sizeof(recv_mem), 0), -1);
+	EXPECT_EQ(errno, EMSGSIZE);
+
+	EXPECT_EQ(recv(self->cfd, recv_mem, sizeof(recv_mem), 0), -1);
+	EXPECT_EQ(errno, EMSGSIZE);
+}
+
 TEST_F(tls, bidir)
 {
 	char const *test_str = "test_read";
-- 
2.20.1


From dbd49b07c729897c86d7d5053609d0af725389d9 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 27 Nov 2019 12:16:43 -0800
Subject: [PATCH 18/23] net/tls: remove the dead inplace_crypto code

[ Upstream commit 9e5ffed37df68d0ccfb2fdc528609e23a1e70ebe ]

Looks like when BPF support was added by commit d3b18ad31f93
("tls: add bpf support to sk_msg handling") and
commit d829e9c4112b ("tls: convert to generic sk_msg interface")
it broke/removed the support for in-place crypto as added by
commit 4e6d47206c32 ("tls: Add support for inplace records
encryption").

The inplace_crypto member of struct tls_rec is dead, inited
to zero, and sometimes set to zero again. It used to be
set to 1 when record was allocated, but the skmsg code doesn't
seem to have been written with the idea of in-place crypto
in mind.

Since non trivial effort is required to bring the feature back
and we don't really have the HW to measure the benefit just
remove the left over support for now to avoid confusing readers.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h | 1 -
 net/tls/tls_sw.c  | 6 +-----
 2 files changed, 1 insertion(+), 6 deletions(-)

diff --git a/include/net/tls.h b/include/net/tls.h
index 9bf04a74a6cb..4e426c18645f 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -121,7 +121,6 @@ struct tls_rec {
 	struct list_head list;
 	int tx_ready;
 	int tx_flags;
-	int inplace_crypto;
 
 	struct sk_msg msg_plaintext;
 	struct sk_msg msg_encrypted;
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 8a7404c73bee..0dda7d8ac4ef 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -705,8 +705,7 @@ static int tls_push_record(struct sock *sk, int flags,
 	}
 
 	i = msg_pl->sg.start;
-	sg_chain(rec->sg_aead_in, 2, rec->inplace_crypto ?
-		 &msg_en->sg.data[i] : &msg_pl->sg.data[i]);
+	sg_chain(rec->sg_aead_in, 2, &msg_pl->sg.data[i]);
 
 	i = msg_en->sg.end;
 	sk_msg_iter_var_prev(i);
@@ -971,8 +970,6 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 			if (ret)
 				goto fallback_to_reg_send;
 
-			rec->inplace_crypto = 0;
-
 			num_zc++;
 			copied += try_to_copy;
 
@@ -1171,7 +1168,6 @@ static int tls_sw_do_sendpage(struct sock *sk, struct page *page,
 
 		tls_ctx->pending_open_record_frags = true;
 		if (full_record || eor || sk_msg_full(msg_pl)) {
-			rec->inplace_crypto = 0;
 			ret = bpf_exec_tx_verdict(msg_pl, sk, full_record,
 						  record_type, &copied, flags);
 			if (ret) {
-- 
2.20.1


From 49e228e07d1601a5ef9e4ccad9f6a1989c312a02 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 27 Nov 2019 12:16:44 -0800
Subject: [PATCH 19/23] net/tls: use sg_next() to walk sg entries

[ Upstream commit c5daa6cccdc2f94aca2c9b3fa5f94e4469997293 ]

Partially sent record cleanup path increments an SG entry
directly instead of using sg_next(). This should not be a
problem today, as encrypted messages should be always
allocated as arrays. But given this is a cleanup path it's
easy to miss was this ever to change. Use sg_next(), and
simplify the code.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h  |  2 +-
 net/tls/tls_main.c | 13 ++-----------
 net/tls/tls_sw.c   |  3 ++-
 3 files changed, 5 insertions(+), 13 deletions(-)

diff --git a/include/net/tls.h b/include/net/tls.h
index 4e426c18645f..e46d4aa27ee7 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -407,7 +407,7 @@ int tls_push_sg(struct sock *sk, struct tls_context *ctx,
 		int flags);
 int tls_push_partial_record(struct sock *sk, struct tls_context *ctx,
 			    int flags);
-bool tls_free_partial_record(struct sock *sk, struct tls_context *ctx);
+void tls_free_partial_record(struct sock *sk, struct tls_context *ctx);
 
 static inline struct tls_msg *tls_msg(struct sk_buff *skb)
 {
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index ac2dfe36022d..c7ecd053d4e7 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -208,24 +208,15 @@ int tls_push_partial_record(struct sock *sk, struct tls_context *ctx,
 	return tls_push_sg(sk, ctx, sg, offset, flags);
 }
 
-bool tls_free_partial_record(struct sock *sk, struct tls_context *ctx)
+void tls_free_partial_record(struct sock *sk, struct tls_context *ctx)
 {
 	struct scatterlist *sg;
 
-	sg = ctx->partially_sent_record;
-	if (!sg)
-		return false;
-
-	while (1) {
+	for (sg = ctx->partially_sent_record; sg; sg = sg_next(sg)) {
 		put_page(sg_page(sg));
 		sk_mem_uncharge(sk, sg->length);
-
-		if (sg_is_last(sg))
-			break;
-		sg++;
 	}
 	ctx->partially_sent_record = NULL;
-	return true;
 }
 
 static void tls_write_space(struct sock *sk)
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 0dda7d8ac4ef..45e993c4e8f6 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -2086,7 +2086,8 @@ void tls_sw_release_resources_tx(struct sock *sk)
 	/* Free up un-sent records in tx_list. First, free
 	 * the partially sent record if any at head of tx_list.
 	 */
-	if (tls_free_partial_record(sk, tls_ctx)) {
+	if (tls_ctx->partially_sent_record) {
+		tls_free_partial_record(sk, tls_ctx);
 		rec = list_first_entry(&ctx->tx_list,
 				       struct tls_rec, list);
 		list_del(&rec->list);
-- 
2.20.1


From e08710d1097dcc306b90d036aa446105a8e8f028 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 27 Nov 2019 12:16:45 -0800
Subject: [PATCH 20/23] selftests: bpf: test_sockmap: handle file creation
 failures gracefully

[ Upstream commit 4b67c515036313f3c3ecba3cb2babb9cbddb3f85 ]

test_sockmap creates a temporary file to use for sendpage.
this may fail for various reasons. Handle the error rather
than segfault.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/bpf/test_sockmap.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 3845144e2c91..8b838e91cfe5 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -332,6 +332,10 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt,
 	int i, fp;
 
 	file = fopen(".sendpage_tst.tmp", "w+");
+	if (!file) {
+		perror("create file for sendpage");
+		return 1;
+	}
 	for (i = 0; i < iov_length * cnt; i++, k++)
 		fwrite(&k, sizeof(char), 1, file);
 	fflush(file);
@@ -339,6 +343,11 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt,
 	fclose(file);
 
 	fp = open(".sendpage_tst.tmp", O_RDONLY);
+	if (fp < 0) {
+		perror("reopen file for sendpage");
+		return 1;
+	}
+
 	clock_gettime(CLOCK_MONOTONIC, &s->start);
 	for (i = 0; i < cnt; i++) {
 		int sent = sendfile(fd, fp, NULL, iov_length);
-- 
2.20.1


From 5e7769a707de8e9075a4af750079388b23448f83 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 27 Nov 2019 12:16:46 -0800
Subject: [PATCH 21/23] selftests: bpf: correct perror strings

[ Upstream commit e5dc9dd3258098bf8b5ceb75fc3433b41eff618a ]

perror(str) is basically equivalent to
print("%s: %s\n", str, strerror(errno)).
New line or colon at the end of str is
a mistake/breaks formatting.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/bpf/test_sockmap.c | 38 +++++++++++-----------
 tools/testing/selftests/bpf/xdping.c       |  2 +-
 2 files changed, 20 insertions(+), 20 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 8b838e91cfe5..4a851513c842 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -240,14 +240,14 @@ static int sockmap_init_sockets(int verbose)
 	addr.sin_port = htons(S1_PORT);
 	err = bind(s1, (struct sockaddr *)&addr, sizeof(addr));
 	if (err < 0) {
-		perror("bind s1 failed()\n");
+		perror("bind s1 failed()");
 		return errno;
 	}
 
 	addr.sin_port = htons(S2_PORT);
 	err = bind(s2, (struct sockaddr *)&addr, sizeof(addr));
 	if (err < 0) {
-		perror("bind s2 failed()\n");
+		perror("bind s2 failed()");
 		return errno;
 	}
 
@@ -255,14 +255,14 @@ static int sockmap_init_sockets(int verbose)
 	addr.sin_port = htons(S1_PORT);
 	err = listen(s1, 32);
 	if (err < 0) {
-		perror("listen s1 failed()\n");
+		perror("listen s1 failed()");
 		return errno;
 	}
 
 	addr.sin_port = htons(S2_PORT);
 	err = listen(s2, 32);
 	if (err < 0) {
-		perror("listen s1 failed()\n");
+		perror("listen s1 failed()");
 		return errno;
 	}
 
@@ -270,14 +270,14 @@ static int sockmap_init_sockets(int verbose)
 	addr.sin_port = htons(S1_PORT);
 	err = connect(c1, (struct sockaddr *)&addr, sizeof(addr));
 	if (err < 0 && errno != EINPROGRESS) {
-		perror("connect c1 failed()\n");
+		perror("connect c1 failed()");
 		return errno;
 	}
 
 	addr.sin_port = htons(S2_PORT);
 	err = connect(c2, (struct sockaddr *)&addr, sizeof(addr));
 	if (err < 0 && errno != EINPROGRESS) {
-		perror("connect c2 failed()\n");
+		perror("connect c2 failed()");
 		return errno;
 	} else if (err < 0) {
 		err = 0;
@@ -286,13 +286,13 @@ static int sockmap_init_sockets(int verbose)
 	/* Accept Connecrtions */
 	p1 = accept(s1, NULL, NULL);
 	if (p1 < 0) {
-		perror("accept s1 failed()\n");
+		perror("accept s1 failed()");
 		return errno;
 	}
 
 	p2 = accept(s2, NULL, NULL);
 	if (p2 < 0) {
-		perror("accept s1 failed()\n");
+		perror("accept s1 failed()");
 		return errno;
 	}
 
@@ -353,7 +353,7 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt,
 		int sent = sendfile(fd, fp, NULL, iov_length);
 
 		if (!drop && sent < 0) {
-			perror("send loop error:");
+			perror("send loop error");
 			close(fp);
 			return sent;
 		} else if (drop && sent >= 0) {
@@ -472,7 +472,7 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 			int sent = sendmsg(fd, &msg, flags);
 
 			if (!drop && sent < 0) {
-				perror("send loop error:");
+				perror("send loop error");
 				goto out_errno;
 			} else if (drop && sent >= 0) {
 				printf("send loop error expected: %i\n", sent);
@@ -508,7 +508,7 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 		total_bytes -= txmsg_pop_total;
 		err = clock_gettime(CLOCK_MONOTONIC, &s->start);
 		if (err < 0)
-			perror("recv start time: ");
+			perror("recv start time");
 		while (s->bytes_recvd < total_bytes) {
 			if (txmsg_cork) {
 				timeout.tv_sec = 0;
@@ -552,7 +552,7 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 			if (recv < 0) {
 				if (errno != EWOULDBLOCK) {
 					clock_gettime(CLOCK_MONOTONIC, &s->end);
-					perror("recv failed()\n");
+					perror("recv failed()");
 					goto out_errno;
 				}
 			}
@@ -566,7 +566,7 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 
 				errno = msg_verify_data(&msg, recv, chunk_sz);
 				if (errno) {
-					perror("data verify msg failed\n");
+					perror("data verify msg failed");
 					goto out_errno;
 				}
 				if (recvp) {
@@ -574,7 +574,7 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 								recvp,
 								chunk_sz);
 					if (errno) {
-						perror("data verify msg_peek failed\n");
+						perror("data verify msg_peek failed");
 						goto out_errno;
 					}
 				}
@@ -663,7 +663,7 @@ static int sendmsg_test(struct sockmap_options *opt)
 			err = 0;
 		exit(err ? 1 : 0);
 	} else if (rxpid == -1) {
-		perror("msg_loop_rx: ");
+		perror("msg_loop_rx");
 		return errno;
 	}
 
@@ -690,7 +690,7 @@ static int sendmsg_test(struct sockmap_options *opt)
 				s.bytes_recvd, recvd_Bps, recvd_Bps/giga);
 		exit(err ? 1 : 0);
 	} else if (txpid == -1) {
-		perror("msg_loop_tx: ");
+		perror("msg_loop_tx");
 		return errno;
 	}
 
@@ -724,7 +724,7 @@ static int forever_ping_pong(int rate, struct sockmap_options *opt)
 	/* Ping/Pong data from client to server */
 	sc = send(c1, buf, sizeof(buf), 0);
 	if (sc < 0) {
-		perror("send failed()\n");
+		perror("send failed()");
 		return sc;
 	}
 
@@ -757,7 +757,7 @@ static int forever_ping_pong(int rate, struct sockmap_options *opt)
 			rc = recv(i, buf, sizeof(buf), 0);
 			if (rc < 0) {
 				if (errno != EWOULDBLOCK) {
-					perror("recv failed()\n");
+					perror("recv failed()");
 					return rc;
 				}
 			}
@@ -769,7 +769,7 @@ static int forever_ping_pong(int rate, struct sockmap_options *opt)
 
 			sc = send(i, buf, rc, 0);
 			if (sc < 0) {
-				perror("send failed()\n");
+				perror("send failed()");
 				return sc;
 			}
 		}
diff --git a/tools/testing/selftests/bpf/xdping.c b/tools/testing/selftests/bpf/xdping.c
index d60a343b1371..842d9155d36c 100644
--- a/tools/testing/selftests/bpf/xdping.c
+++ b/tools/testing/selftests/bpf/xdping.c
@@ -45,7 +45,7 @@ static int get_stats(int fd, __u16 count, __u32 raddr)
 	printf("\nXDP RTT data:\n");
 
 	if (bpf_map_lookup_elem(fd, &raddr, &pinginfo)) {
-		perror("bpf_map_lookup elem: ");
+		perror("bpf_map_lookup elem");
 		return 1;
 	}
 
-- 
2.20.1


From ce67e03cef38a3a515ab51bfe27f942c1dbc3574 Mon Sep 17 00:00:00 2001
From: John Rutherford <john.rutherford@dektech.com.au>
Date: Tue, 26 Nov 2019 13:52:55 +1100
Subject: [PATCH 22/23] tipc: fix link name length check

[ Upstream commit fd567ac20cb0377ff466d3337e6e9ac5d0cb15e4 ]

In commit 4f07b80c9733 ("tipc: check msg->req data len in
tipc_nl_compat_bearer_disable") the same patch code was copied into
routines: tipc_nl_compat_bearer_disable(),
tipc_nl_compat_link_stat_dump() and tipc_nl_compat_link_reset_stats().
The two link routine occurrences should have been modified to check
the maximum link name length and not bearer name length.

Fixes: 4f07b80c9733 ("tipc: check msg->reg data len in tipc_nl_compat_bearer_disable")
Signed-off-by: John Rutherford <john.rutherford@dektech.com.au>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/netlink_compat.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index e135d4e11231..d4d2928424e2 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -550,7 +550,7 @@ static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg,
 	if (len <= 0)
 		return -EINVAL;
 
-	len = min_t(int, len, TIPC_MAX_BEARER_NAME);
+	len = min_t(int, len, TIPC_MAX_LINK_NAME);
 	if (!string_is_valid(name, len))
 		return -EINVAL;
 
@@ -822,7 +822,7 @@ static int tipc_nl_compat_link_reset_stats(struct tipc_nl_compat_cmd_doit *cmd,
 	if (len <= 0)
 		return -EINVAL;
 
-	len = min_t(int, len, TIPC_MAX_BEARER_NAME);
+	len = min_t(int, len, TIPC_MAX_LINK_NAME);
 	if (!string_is_valid(name, len))
 		return -EINVAL;
 
-- 
2.20.1


From 6dc8ae03924a1a7ecbad972ad174ae9cad24da5d Mon Sep 17 00:00:00 2001
From: Thadeu Lima de Souza Cascardo <cascardo@canonical.com>
Date: Thu, 28 Nov 2019 15:58:06 -0300
Subject: [PATCH 23/23] selftests: pmtu: use -oneline for ip route list cache

[ Upstream commit 2745aea6750ff0d2c48285d25bdb00e5b636ec8b ]

Some versions of iproute2 will output more than one line per entry, which
will cause the test to fail, like:

TEST: ipv6: list and flush cached exceptions                        [FAIL]
  can't list cached exceptions

That happens, for example, with iproute2 4.15.0. When using the -oneline
option, this will work just fine:

TEST: ipv6: list and flush cached exceptions                        [ OK ]

This also works just fine with a more recent version of iproute2, like
5.4.0.

For some reason, two lines are printed for the IPv4 test no matter what
version of iproute2 is used. Use the same -oneline parameter there instead
of counting the lines twice.

Fixes: b964641e9925 ("selftests: pmtu: Make list_flush_ipv6_exception test more demanding")
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@canonical.com>
Acked-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/pmtu.sh | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index ab367e75f095..d697815d2785 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -1249,8 +1249,7 @@ test_list_flush_ipv4_exception() {
 	done
 	run_cmd ${ns_a} ping -q -M want -i 0.1 -c 2 -s 1800 "${dst2}"
 
-	# Each exception is printed as two lines
-	if [ "$(${ns_a} ip route list cache | wc -l)" -ne 202 ]; then
+	if [ "$(${ns_a} ip -oneline route list cache | wc -l)" -ne 101 ]; then
 		err "  can't list cached exceptions"
 		fail=1
 	fi
@@ -1300,7 +1299,7 @@ test_list_flush_ipv6_exception() {
 		run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s 1800 "${dst_prefix1}${i}"
 	done
 	run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s 1800 "${dst2}"
-	if [ "$(${ns_a} ip -6 route list cache | wc -l)" -ne 101 ]; then
+	if [ "$(${ns_a} ip -oneline -6 route list cache | wc -l)" -ne 101 ]; then
 		err "  can't list cached exceptions"
 		fail=1
 	fi
-- 
2.20.1


[-- Attachment #3: net_54.mbox --]
[-- Type: Application/Octet-Stream, Size: 64428 bytes --]

From b8db717ffa55a38cf52b13a7a2d8535cad3fc051 Mon Sep 17 00:00:00 2001
From: Jeroen de Borst <jeroendb@google.com>
Date: Tue, 26 Nov 2019 15:36:19 -0800
Subject: [PATCH 01/25] gve: Fix the queue page list allocated pages count

[ Upstream commit a95069ecb7092d03b2ea1c39ee04514fe9627540 ]

In gve_alloc_queue_page_list(), when a page allocation fails,
qpl->num_entries will be wrong.  In this case priv->num_registered_pages
can underflow in gve_free_queue_page_list(), causing subsequent calls
to gve_alloc_queue_page_list() to fail.

Fixes: f5cedc84a30d ("gve: Add transmit and receive support")
Signed-off-by: Jeroen de Borst <jeroendb@google.com>
Reviewed-by: Catherine Sullivan <csully@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/google/gve/gve_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index aca95f64bde8..9b7a8db9860f 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -544,7 +544,7 @@ static int gve_alloc_queue_page_list(struct gve_priv *priv, u32 id,
 	}
 
 	qpl->id = id;
-	qpl->num_entries = pages;
+	qpl->num_entries = 0;
 	qpl->pages = kvzalloc(pages * sizeof(*qpl->pages), GFP_KERNEL);
 	/* caller handles clean up */
 	if (!qpl->pages)
@@ -562,6 +562,7 @@ static int gve_alloc_queue_page_list(struct gve_priv *priv, u32 id,
 		/* caller handles clean up */
 		if (err)
 			return -ENOMEM;
+		qpl->num_entries++;
 	}
 	priv->num_registered_pages += pages;
 
-- 
2.20.1


From 5c6f2744a7046690ba28d041798d2993056e8568 Mon Sep 17 00:00:00 2001
From: Menglong Dong <dong.menglong@zte.com.cn>
Date: Mon, 25 Nov 2019 16:58:09 +0800
Subject: [PATCH 02/25] macvlan: schedule bc_work even if error

[ Upstream commit 1d7ea55668878bb350979c377fc72509dd6f5b21 ]

While enqueueing a broadcast skb to port->bc_queue, schedule_work()
is called to add port->bc_work, which processes the skbs in
bc_queue, to "events" work queue. If port->bc_queue is full, the
skb will be discarded and schedule_work(&port->bc_work) won't be
called. However, if port->bc_queue is full and port->bc_work is not
running or pending, port->bc_queue will keep full and schedule_work()
won't be called any more, and all broadcast skbs to macvlan will be
discarded. This case can happen:

macvlan_process_broadcast() is the pending function of port->bc_work,
it moves all the skbs in port->bc_queue to the queue "list", and
processes the skbs in "list". During this, new skbs will keep being
added to port->bc_queue in macvlan_broadcast_enqueue(), and
port->bc_queue may already full when macvlan_process_broadcast()
return. This may happen, especially when there are a lot of real-time
threads and the process is preempted.

Fix this by calling schedule_work(&port->bc_work) even if
port->bc_work is full in macvlan_broadcast_enqueue().

Fixes: 412ca1550cbe ("macvlan: Move broadcasts into a work queue")
Signed-off-by: Menglong Dong <dong.menglong@zte.com.cn>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macvlan.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 34fc59bd1e20..05631d97eeb4 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -359,10 +359,11 @@ static void macvlan_broadcast_enqueue(struct macvlan_port *port,
 	}
 	spin_unlock(&port->bc_queue.lock);
 
+	schedule_work(&port->bc_work);
+
 	if (err)
 		goto free_nskb;
 
-	schedule_work(&port->bc_work);
 	return;
 
 free_nskb:
-- 
2.20.1


From 7e87210a4afa01301dee68b3e71c7bef073fea4a Mon Sep 17 00:00:00 2001
From: David Bauer <mail@david-bauer.net>
Date: Fri, 22 Nov 2019 22:44:51 +0100
Subject: [PATCH 03/25] mdio_bus: don't use managed reset-controller

[ Upstream commit 32085f25d7b68404055f3525c780142fc72e543f ]

Geert Uytterhoeven reported that using devm_reset_controller_get leads
to a WARNING when probing a reset-controlled PHY. This is because the
device devm_reset_controller_get gets supplied is not actually the
one being probed.

Acquire an unmanaged reset-control as well as free the reset_control on
unregister to fix this.

Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
CC: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David Bauer <mail@david-bauer.net>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mdio_bus.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index dbacb0031877..229e480179ff 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -62,8 +62,8 @@ static int mdiobus_register_reset(struct mdio_device *mdiodev)
 	struct reset_control *reset = NULL;
 
 	if (mdiodev->dev.of_node)
-		reset = devm_reset_control_get_exclusive(&mdiodev->dev,
-							 "phy");
+		reset = of_reset_control_get_exclusive(mdiodev->dev.of_node,
+						       "phy");
 	if (IS_ERR(reset)) {
 		if (PTR_ERR(reset) == -ENOENT || PTR_ERR(reset) == -ENOTSUPP)
 			reset = NULL;
@@ -107,6 +107,8 @@ int mdiobus_unregister_device(struct mdio_device *mdiodev)
 	if (mdiodev->bus->mdio_map[mdiodev->addr] != mdiodev)
 		return -EINVAL;
 
+	reset_control_put(mdiodev->reset_ctrl);
+
 	mdiodev->bus->mdio_map[mdiodev->addr] = NULL;
 
 	return 0;
-- 
2.20.1


From 71d0385b833d16f018ba82e445f74119d84b6b3e Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Mon, 25 Nov 2019 12:43:51 +0100
Subject: [PATCH 04/25] net: dsa: sja1105: fix sja1105_parse_rgmii_delays()

[ Upstream commit 9bca3a0a923fc3f0fb9e41391be1d0f291e86858 ]

This function was using configuration of port 0 in devicetree for all ports.
In case CPU port was not 0, the delay settings was ignored. This resulted not
working communication between CPU and the switch.

Fixes: f5b8631c293b ("net: dsa: sja1105: Error out if RGMII delays are requested in DT")
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/sja1105/sja1105_main.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index 7687ddcae159..aa140662c7c2 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -594,15 +594,15 @@ static int sja1105_parse_rgmii_delays(struct sja1105_private *priv,
 	int i;
 
 	for (i = 0; i < SJA1105_NUM_PORTS; i++) {
-		if (ports->role == XMII_MAC)
+		if (ports[i].role == XMII_MAC)
 			continue;
 
-		if (ports->phy_mode == PHY_INTERFACE_MODE_RGMII_RXID ||
-		    ports->phy_mode == PHY_INTERFACE_MODE_RGMII_ID)
+		if (ports[i].phy_mode == PHY_INTERFACE_MODE_RGMII_RXID ||
+		    ports[i].phy_mode == PHY_INTERFACE_MODE_RGMII_ID)
 			priv->rgmii_rx_delay[i] = true;
 
-		if (ports->phy_mode == PHY_INTERFACE_MODE_RGMII_TXID ||
-		    ports->phy_mode == PHY_INTERFACE_MODE_RGMII_ID)
+		if (ports[i].phy_mode == PHY_INTERFACE_MODE_RGMII_TXID ||
+		    ports[i].phy_mode == PHY_INTERFACE_MODE_RGMII_ID)
 			priv->rgmii_tx_delay[i] = true;
 
 		if ((priv->rgmii_rx_delay[i] || priv->rgmii_tx_delay[i]) &&
-- 
2.20.1


From bf823c6ba227a79ed653f1310d01886c559c7e0b Mon Sep 17 00:00:00 2001
From: Chuhong Yuan <hslester96@gmail.com>
Date: Thu, 28 Nov 2019 10:00:21 +0800
Subject: [PATCH 05/25] net: macb: add missed tasklet_kill

[ Upstream commit 61183b056b49e2937ff92a1424291ba36a6f6d05 ]

This driver forgets to kill tasklet in remove.
Add the call to fix it.

Fixes: 032dc41ba6e2 ("net: macb: Handle HRESP error")
Signed-off-by: Chuhong Yuan <hslester96@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 1e1b774e1953..0f10a272827c 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -4392,6 +4392,7 @@ static int macb_remove(struct platform_device *pdev)
 		mdiobus_free(bp->mii_bus);
 
 		unregister_netdev(dev);
+		tasklet_kill(&bp->hresp_err_tasklet);
 		pm_runtime_disable(&pdev->dev);
 		pm_runtime_dont_use_autosuspend(&pdev->dev);
 		if (!pm_runtime_suspended(&pdev->dev)) {
-- 
2.20.1


From d2547fdfaaf8bf8c4b1ce2622966d26725b3c126 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Wed, 27 Nov 2019 00:16:44 +0200
Subject: [PATCH 06/25] net: psample: fix skb_over_panic

[ Upstream commit 7eb9d7675c08937cd11d32b0b40442d4d731c5ee ]

We need to calculate the skb size correctly otherwise we risk triggering
skb_over_panic[1]. The issue is that data_len is added to the skb in a
nl attribute, but we don't account for its header size (nlattr 4 bytes)
and alignment. We account for it when calculating the total size in
the > PSAMPLE_MAX_PACKET_SIZE comparison correctly, but not when
allocating after that. The fix is simple - use nla_total_size() for
data_len when allocating.

To reproduce:
 $ tc qdisc add dev eth1 clsact
 $ tc filter add dev eth1 egress matchall action sample rate 1 group 1 trunc 129
 $ mausezahn eth1 -b bcast -a rand -c 1 -p 129
 < skb_over_panic BUG(), tail is 4 bytes past skb->end >

[1] Trace:
 [   50.459526][ T3480] skbuff: skb_over_panic: text:(____ptrval____) len:196 put:136 head:(____ptrval____) data:(____ptrval____) tail:0xc4 end:0xc0 dev:<NULL>
 [   50.474339][ T3480] ------------[ cut here ]------------
 [   50.481132][ T3480] kernel BUG at net/core/skbuff.c:108!
 [   50.486059][ T3480] invalid opcode: 0000 [#1] PREEMPT SMP
 [   50.489463][ T3480] CPU: 3 PID: 3480 Comm: mausezahn Not tainted 5.4.0-rc7 #108
 [   50.492844][ T3480] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-2.fc30 04/01/2014
 [   50.496551][ T3480] RIP: 0010:skb_panic+0x79/0x7b
 [   50.498261][ T3480] Code: bc 00 00 00 41 57 4c 89 e6 48 c7 c7 90 29 9a 83 4c 8b 8b c0 00 00 00 50 8b 83 b8 00 00 00 50 ff b3 c8 00 00 00 e8 ae ef c0 fe <0f> 0b e8 2f df c8 fe 48 8b 55 08 44 89 f6 4c 89 e7 48 c7 c1 a0 22
 [   50.504111][ T3480] RSP: 0018:ffffc90000447a10 EFLAGS: 00010282
 [   50.505835][ T3480] RAX: 0000000000000087 RBX: ffff888039317d00 RCX: 0000000000000000
 [   50.507900][ T3480] RDX: 0000000000000000 RSI: ffffffff812716e1 RDI: 00000000ffffffff
 [   50.509820][ T3480] RBP: ffffc90000447a60 R08: 0000000000000001 R09: 0000000000000000
 [   50.511735][ T3480] R10: ffffffff81d4f940 R11: 0000000000000000 R12: ffffffff834a22b0
 [   50.513494][ T3480] R13: ffffffff82c10433 R14: 0000000000000088 R15: ffffffff838a8084
 [   50.515222][ T3480] FS:  00007f3536462700(0000) GS:ffff88803eac0000(0000) knlGS:0000000000000000
 [   50.517135][ T3480] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 [   50.518583][ T3480] CR2: 0000000000442008 CR3: 000000003b222000 CR4: 00000000000006e0
 [   50.520723][ T3480] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
 [   50.522709][ T3480] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
 [   50.524450][ T3480] Call Trace:
 [   50.525214][ T3480]  skb_put.cold+0x1b/0x1b
 [   50.526171][ T3480]  psample_sample_packet+0x1d3/0x340
 [   50.527307][ T3480]  tcf_sample_act+0x178/0x250
 [   50.528339][ T3480]  tcf_action_exec+0xb1/0x190
 [   50.529354][ T3480]  mall_classify+0x67/0x90
 [   50.530332][ T3480]  tcf_classify+0x72/0x160
 [   50.531286][ T3480]  __dev_queue_xmit+0x3db/0xd50
 [   50.532327][ T3480]  dev_queue_xmit+0x18/0x20
 [   50.533299][ T3480]  packet_sendmsg+0xee7/0x2090
 [   50.534331][ T3480]  sock_sendmsg+0x54/0x70
 [   50.535271][ T3480]  __sys_sendto+0x148/0x1f0
 [   50.536252][ T3480]  ? tomoyo_file_ioctl+0x23/0x30
 [   50.537334][ T3480]  ? ksys_ioctl+0x5e/0xb0
 [   50.540068][ T3480]  __x64_sys_sendto+0x2a/0x30
 [   50.542810][ T3480]  do_syscall_64+0x73/0x1f0
 [   50.545383][ T3480]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
 [   50.548477][ T3480] RIP: 0033:0x7f35357d6fb3
 [   50.551020][ T3480] Code: 48 8b 0d 18 90 20 00 f7 d8 64 89 01 48 83 c8 ff c3 66 0f 1f 44 00 00 83 3d f9 d3 20 00 00 75 13 49 89 ca b8 2c 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 34 c3 48 83 ec 08 e8 eb f6 ff ff 48 89 04 24
 [   50.558547][ T3480] RSP: 002b:00007ffe0c7212c8 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
 [   50.561870][ T3480] RAX: ffffffffffffffda RBX: 0000000001dac010 RCX: 00007f35357d6fb3
 [   50.565142][ T3480] RDX: 0000000000000082 RSI: 0000000001dac2a2 RDI: 0000000000000003
 [   50.568469][ T3480] RBP: 00007ffe0c7212f0 R08: 00007ffe0c7212d0 R09: 0000000000000014
 [   50.571731][ T3480] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000082
 [   50.574961][ T3480] R13: 0000000001dac2a2 R14: 0000000000000001 R15: 0000000000000003
 [   50.578170][ T3480] Modules linked in: sch_ingress virtio_net
 [   50.580976][ T3480] ---[ end trace 61a515626a595af6 ]---

CC: Yotam Gigi <yotamg@mellanox.com>
CC: Jiri Pirko <jiri@mellanox.com>
CC: Jamal Hadi Salim <jhs@mojatatu.com>
CC: Simon Horman <simon.horman@netronome.com>
CC: Roopa Prabhu <roopa@cumulusnetworks.com>
Fixes: 6ae0a6286171 ("net: Introduce psample, a new genetlink channel for packet sampling")
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/psample/psample.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/psample/psample.c b/net/psample/psample.c
index a6ceb0533b5b..6f2fbc6b9eb2 100644
--- a/net/psample/psample.c
+++ b/net/psample/psample.c
@@ -229,7 +229,7 @@ void psample_sample_packet(struct psample_group *group, struct sk_buff *skb,
 		data_len = PSAMPLE_MAX_PACKET_SIZE - meta_len - NLA_HDRLEN
 			    - NLA_ALIGNTO;
 
-	nl_skb = genlmsg_new(meta_len + data_len, GFP_ATOMIC);
+	nl_skb = genlmsg_new(meta_len + nla_total_size(data_len), GFP_ATOMIC);
 	if (unlikely(!nl_skb))
 		return;
 
-- 
2.20.1


From 68707bf91d20c1a706ceadec715fb4fbe5fa3ca8 Mon Sep 17 00:00:00 2001
From: Dust Li <dust.li@linux.alibaba.com>
Date: Thu, 28 Nov 2019 14:29:09 +0800
Subject: [PATCH 07/25] net: sched: fix `tc -s class show` no bstats on class
 with nolock subqueues

[ Upstream commit 14e54ab9143fa60794d13ea0a66c792a2046a8f3 ]

When a classful qdisc's child qdisc has set the flag
TCQ_F_CPUSTATS (pfifo_fast for example), the child qdisc's
cpu_bstats should be passed to gnet_stats_copy_basic(),
but many classful qdisc didn't do that. As a result,
`tc -s class show dev DEV` always return 0 for bytes and
packets in this case.

Pass the child qdisc's cpu_bstats to gnet_stats_copy_basic()
to fix this issue.

The qstats also has this problem, but it has been fixed
in 5dd431b6b9 ("net: sched: introduce and use qstats read...")
and bstats still remains buggy.

Fixes: 22e0f8b9322c ("net: sched: make bstats per cpu and estimator RCU safe")
Signed-off-by: Dust Li <dust.li@linux.alibaba.com>
Signed-off-by: Tony Lu <tonylu@linux.alibaba.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_mq.c     | 3 ++-
 net/sched/sch_mqprio.c | 4 ++--
 net/sched/sch_multiq.c | 2 +-
 net/sched/sch_prio.c   | 2 +-
 4 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
index 0d578333e967..278c0b2dc523 100644
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -245,7 +245,8 @@ static int mq_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 	struct netdev_queue *dev_queue = mq_queue_get(sch, cl);
 
 	sch = dev_queue->qdisc_sleeping;
-	if (gnet_stats_copy_basic(&sch->running, d, NULL, &sch->bstats) < 0 ||
+	if (gnet_stats_copy_basic(&sch->running, d, sch->cpu_bstats,
+				  &sch->bstats) < 0 ||
 	    qdisc_qstats_copy(d, sch) < 0)
 		return -1;
 	return 0;
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index 46980b8d66c5..0d0113a24962 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -557,8 +557,8 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 		struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl);
 
 		sch = dev_queue->qdisc_sleeping;
-		if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
-					  d, NULL, &sch->bstats) < 0 ||
+		if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), d,
+					  sch->cpu_bstats, &sch->bstats) < 0 ||
 		    qdisc_qstats_copy(d, sch) < 0)
 			return -1;
 	}
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index b2b7fdb06fc6..1330ad224931 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -339,7 +339,7 @@ static int multiq_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 
 	cl_q = q->queues[cl - 1];
 	if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
-				  d, NULL, &cl_q->bstats) < 0 ||
+				  d, cl_q->cpu_bstats, &cl_q->bstats) < 0 ||
 	    qdisc_qstats_copy(d, cl_q) < 0)
 		return -1;
 
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index 0f8fedb8809a..18b884cfdfe8 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -356,7 +356,7 @@ static int prio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 
 	cl_q = q->queues[cl - 1];
 	if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
-				  d, NULL, &cl_q->bstats) < 0 ||
+				  d, cl_q->cpu_bstats, &cl_q->bstats) < 0 ||
 	    qdisc_qstats_copy(d, cl_q) < 0)
 		return -1;
 
-- 
2.20.1


From e127117e90a8f31e57ca18eb5b30420a4117232b Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 26 Nov 2019 12:55:50 +0100
Subject: [PATCH 08/25] openvswitch: fix flow command message size

[ Upstream commit 4e81c0b3fa93d07653e2415fa71656b080a112fd ]

When user-space sets the OVS_UFID_F_OMIT_* flags, and the relevant
flow has no UFID, we can exceed the computed size, as
ovs_nla_put_identifier() will always dump an OVS_FLOW_ATTR_KEY
attribute.
Take the above in account when computing the flow command message
size.

Fixes: 74ed7ab9264c ("openvswitch: Add support for unique flow IDs.")
Reported-by: Qi Jun Ding <qding@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/datapath.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index d8c364d637b1..ce386331964f 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -704,9 +704,13 @@ static size_t ovs_flow_cmd_msg_size(const struct sw_flow_actions *acts,
 {
 	size_t len = NLMSG_ALIGN(sizeof(struct ovs_header));
 
-	/* OVS_FLOW_ATTR_UFID */
+	/* OVS_FLOW_ATTR_UFID, or unmasked flow key as fallback
+	 * see ovs_nla_put_identifier()
+	 */
 	if (sfid && ovs_identifier_is_ufid(sfid))
 		len += nla_total_size(sfid->ufid_len);
+	else
+		len += nla_total_size(ovs_key_attr_size());
 
 	/* OVS_FLOW_ATTR_KEY */
 	if (!sfid || should_fill_key(sfid, ufid_flags))
-- 
2.20.1


From 3097ae45be3cf240b0719dbf7dfd8ba2898996ab Mon Sep 17 00:00:00 2001
From: Navid Emamdoost <navid.emamdoost@gmail.com>
Date: Fri, 22 Nov 2019 16:17:56 -0600
Subject: [PATCH 09/25] sctp: Fix memory leak in sctp_sf_do_5_2_4_dupcook

[ Upstream commit b6631c6031c746ed004c4221ec0616d7a520f441 ]

In the implementation of sctp_sf_do_5_2_4_dupcook() the allocated
new_asoc is leaked if security_sctp_assoc_request() fails. Release it
via sctp_association_free().

Fixes: 2277c7cd75e3 ("sctp: Add LSM hooks")
Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/sctp/sm_statefuns.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 0c21c52fc408..4ab8208a2dd4 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -2160,8 +2160,10 @@ enum sctp_disposition sctp_sf_do_5_2_4_dupcook(
 
 	/* Update socket peer label if first association. */
 	if (security_sctp_assoc_request((struct sctp_endpoint *)ep,
-					chunk->skb))
+					chunk->skb)) {
+		sctp_association_free(new_asoc);
 		return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+	}
 
 	/* Set temp so that it won't be added into hashtable */
 	new_asoc->temp = 1;
-- 
2.20.1


From b8e44b462bb620153fc384a5d01ba82286f8ab4f Mon Sep 17 00:00:00 2001
From: Jouni Hogander <jouni.hogander@unikie.com>
Date: Mon, 25 Nov 2019 14:23:43 +0200
Subject: [PATCH 10/25] slip: Fix use-after-free Read in slip_open

[ Upstream commit e58c1912418980f57ba2060017583067f5f71e52 ]

Slip_open doesn't clean-up device which registration failed from the
slip_devs device list. On next open after failure this list is iterated
and freed device is accessed. Fix this by calling sl_free_netdev in error
path.

Here is the trace from the Syzbot:

__dump_stack lib/dump_stack.c:77 [inline]
dump_stack+0x197/0x210 lib/dump_stack.c:118
print_address_description.constprop.0.cold+0xd4/0x30b mm/kasan/report.c:374
__kasan_report.cold+0x1b/0x41 mm/kasan/report.c:506
kasan_report+0x12/0x20 mm/kasan/common.c:634
__asan_report_load8_noabort+0x14/0x20 mm/kasan/generic_report.c:132
sl_sync drivers/net/slip/slip.c:725 [inline]
slip_open+0xecd/0x11b7 drivers/net/slip/slip.c:801
tty_ldisc_open.isra.0+0xa3/0x110 drivers/tty/tty_ldisc.c:469
tty_set_ldisc+0x30e/0x6b0 drivers/tty/tty_ldisc.c:596
tiocsetd drivers/tty/tty_io.c:2334 [inline]
tty_ioctl+0xe8d/0x14f0 drivers/tty/tty_io.c:2594
vfs_ioctl fs/ioctl.c:46 [inline]
file_ioctl fs/ioctl.c:509 [inline]
do_vfs_ioctl+0xdb6/0x13e0 fs/ioctl.c:696
ksys_ioctl+0xab/0xd0 fs/ioctl.c:713
__do_sys_ioctl fs/ioctl.c:720 [inline]
__se_sys_ioctl fs/ioctl.c:718 [inline]
__x64_sys_ioctl+0x73/0xb0 fs/ioctl.c:718
do_syscall_64+0xfa/0x760 arch/x86/entry/common.c:290
entry_SYSCALL_64_after_hwframe+0x49/0xbe

Fixes: 3b5a39979daf ("slip: Fix memory leak in slip_open error path")
Reported-by: syzbot+4d5170758f3762109542@syzkaller.appspotmail.com
Cc: David Miller <davem@davemloft.net>
Cc: Oliver Hartkopp <socketcan@hartkopp.net>
Cc: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Signed-off-by: Jouni Hogander <jouni.hogander@unikie.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/slip/slip.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c
index 4d479e3c817d..2a91c192659f 100644
--- a/drivers/net/slip/slip.c
+++ b/drivers/net/slip/slip.c
@@ -855,6 +855,7 @@ static int slip_open(struct tty_struct *tty)
 	sl->tty = NULL;
 	tty->disc_data = NULL;
 	clear_bit(SLF_INUSE, &sl->flags);
+	sl_free_netdev(sl->dev);
 	free_netdev(sl->dev);
 
 err_exit:
-- 
2.20.1


From d27a2bd501670f6d6af9264e548dc0a90b8928f9 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sat, 23 Nov 2019 11:56:49 +0800
Subject: [PATCH 11/25] sctp: cache netns in sctp_ep_common

[ Upstream commit 312434617cb16be5166316cf9d08ba760b1042a1 ]

This patch is to fix a data-race reported by syzbot:

  BUG: KCSAN: data-race in sctp_assoc_migrate / sctp_hash_obj

  write to 0xffff8880b67c0020 of 8 bytes by task 18908 on cpu 1:
    sctp_assoc_migrate+0x1a6/0x290 net/sctp/associola.c:1091
    sctp_sock_migrate+0x8aa/0x9b0 net/sctp/socket.c:9465
    sctp_accept+0x3c8/0x470 net/sctp/socket.c:4916
    inet_accept+0x7f/0x360 net/ipv4/af_inet.c:734
    __sys_accept4+0x224/0x430 net/socket.c:1754
    __do_sys_accept net/socket.c:1795 [inline]
    __se_sys_accept net/socket.c:1792 [inline]
    __x64_sys_accept+0x4e/0x60 net/socket.c:1792
    do_syscall_64+0xcc/0x370 arch/x86/entry/common.c:290
    entry_SYSCALL_64_after_hwframe+0x44/0xa9

  read to 0xffff8880b67c0020 of 8 bytes by task 12003 on cpu 0:
    sctp_hash_obj+0x4f/0x2d0 net/sctp/input.c:894
    rht_key_get_hash include/linux/rhashtable.h:133 [inline]
    rht_key_hashfn include/linux/rhashtable.h:159 [inline]
    rht_head_hashfn include/linux/rhashtable.h:174 [inline]
    head_hashfn lib/rhashtable.c:41 [inline]
    rhashtable_rehash_one lib/rhashtable.c:245 [inline]
    rhashtable_rehash_chain lib/rhashtable.c:276 [inline]
    rhashtable_rehash_table lib/rhashtable.c:316 [inline]
    rht_deferred_worker+0x468/0xab0 lib/rhashtable.c:420
    process_one_work+0x3d4/0x890 kernel/workqueue.c:2269
    worker_thread+0xa0/0x800 kernel/workqueue.c:2415
    kthread+0x1d4/0x200 drivers/block/aoe/aoecmd.c:1253
    ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:352

It was caused by rhashtable access asoc->base.sk when sctp_assoc_migrate
is changing its value. However, what rhashtable wants is netns from asoc
base.sk, and for an asoc, its netns won't change once set. So we can
simply fix it by caching netns since created.

Fixes: d6c0256a60e6 ("sctp: add the rhashtable apis for sctp global transport hashtable")
Reported-by: syzbot+e3b35fe7918ff0ee474e@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 include/net/sctp/structs.h | 3 +++
 net/sctp/associola.c       | 1 +
 net/sctp/endpointola.c     | 1 +
 net/sctp/input.c           | 4 ++--
 4 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 503fbc3cd819..2b6f3f13d5bc 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1239,6 +1239,9 @@ struct sctp_ep_common {
 	/* What socket does this endpoint belong to?  */
 	struct sock *sk;
 
+	/* Cache netns and it won't change once set */
+	struct net *net;
+
 	/* This is where we receive inbound chunks.  */
 	struct sctp_inq	  inqueue;
 
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index d2ffc9a0ba3a..41839b85c268 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -64,6 +64,7 @@ static struct sctp_association *sctp_association_init(
 	/* Discarding const is appropriate here.  */
 	asoc->ep = (struct sctp_endpoint *)ep;
 	asoc->base.sk = (struct sock *)sk;
+	asoc->base.net = sock_net(sk);
 
 	sctp_endpoint_hold(asoc->ep);
 	sock_hold(asoc->base.sk);
diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c
index ea53049d1db6..3067deb0fbec 100644
--- a/net/sctp/endpointola.c
+++ b/net/sctp/endpointola.c
@@ -110,6 +110,7 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep,
 
 	/* Remember who we are attached to.  */
 	ep->base.sk = sk;
+	ep->base.net = sock_net(sk);
 	sock_hold(ep->base.sk);
 
 	return ep;
diff --git a/net/sctp/input.c b/net/sctp/input.c
index 2277981559d0..4d2bcfc9d7f8 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -882,7 +882,7 @@ static inline int sctp_hash_cmp(struct rhashtable_compare_arg *arg,
 	if (!sctp_transport_hold(t))
 		return err;
 
-	if (!net_eq(sock_net(t->asoc->base.sk), x->net))
+	if (!net_eq(t->asoc->base.net, x->net))
 		goto out;
 	if (x->lport != htons(t->asoc->base.bind_addr.port))
 		goto out;
@@ -897,7 +897,7 @@ static inline __u32 sctp_hash_obj(const void *data, u32 len, u32 seed)
 {
 	const struct sctp_transport *t = data;
 
-	return sctp_hashfn(sock_net(t->asoc->base.sk),
+	return sctp_hashfn(t->asoc->base.net,
 			   htons(t->asoc->base.bind_addr.port),
 			   &t->ipaddr, seed);
 }
-- 
2.20.1


From bc220855149432427e158dc5d96cdf40c2cea17c Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Sun, 1 Dec 2019 18:41:24 +0100
Subject: [PATCH 12/25] openvswitch: drop unneeded BUG_ON() in
 ovs_flow_cmd_build_info()

[ Upstream commit 8ffeb03fbba3b599690b361467bfd2373e8c450f ]

All the callers of ovs_flow_cmd_build_info() already deal with
error return code correctly, so we can handle the error condition
in a more gracefull way. Still dump a warning to preserve
debuggability.

v1 -> v2:
 - clarify the commit message
 - clean the skb and report the error (DaveM)

Fixes: ccb1352e76cf ("net: Add Open vSwitch kernel components.")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/datapath.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index ce386331964f..230e36406976 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -886,7 +886,10 @@ static struct sk_buff *ovs_flow_cmd_build_info(const struct sw_flow *flow,
 	retval = ovs_flow_cmd_fill_info(flow, dp_ifindex, skb,
 					info->snd_portid, info->snd_seq, 0,
 					cmd, ufid_flags);
-	BUG_ON(retval < 0);
+	if (WARN_ON_ONCE(retval < 0)) {
+		kfree_skb(skb);
+		skb = ERR_PTR(retval);
+	}
 	return skb;
 }
 
-- 
2.20.1


From 918f3187ad8fc6b7472d092be13d0485f952d9a9 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Sun, 1 Dec 2019 18:41:25 +0100
Subject: [PATCH 13/25] openvswitch: remove another BUG_ON()

[ Upstream commit 8a574f86652a4540a2433946ba826ccb87f398cc ]

If we can't build the flow del notification, we can simply delete
the flow, no need to crash the kernel. Still keep a WARN_ON to
preserve debuggability.

Note: the BUG_ON() predates the Fixes tag, but this change
can be applied only after the mentioned commit.

v1 -> v2:
 - do not leak an skb on error

Fixes: aed067783e50 ("openvswitch: Minimize ovs_flow_cmd_del critical section.")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/datapath.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 230e36406976..23f67b8fdeaa 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -1353,7 +1353,10 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info)
 						     OVS_FLOW_CMD_DEL,
 						     ufid_flags);
 			rcu_read_unlock();
-			BUG_ON(err < 0);
+			if (WARN_ON_ONCE(err < 0)) {
+				kfree_skb(reply);
+				goto out_free;
+			}
 
 			ovs_notify(&dp_flow_genl_family, reply, info);
 		} else {
@@ -1361,6 +1364,7 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
+out_free:
 	ovs_flow_free(flow, true);
 	return 0;
 unlock:
-- 
2.20.1


From fd6ddd9653137eb75438ae23a6b3d8154007c27c Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 27 Nov 2019 12:16:39 -0800
Subject: [PATCH 14/25] net/tls: take into account that bpf_exec_tx_verdict()
 may free the record

[ Upstream commit c329ef9684de9517d82af5b4758c9e1b64a8a11a ]

bpf_exec_tx_verdict() may free the record if tls_push_record()
fails, or if the entire record got consumed by BPF. Re-check
ctx->open_rec before touching the data.

Fixes: d3b18ad31f93 ("tls: add bpf support to sk_msg handling")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 319735d5c084..cf715e124805 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -979,7 +979,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 					num_async++;
 				else if (ret == -ENOMEM)
 					goto wait_for_memory;
-				else if (ret == -ENOSPC)
+				else if (ctx->open_rec && ret == -ENOSPC)
 					goto rollback_iter;
 				else if (ret != -EAGAIN)
 					goto send_end;
@@ -1048,11 +1048,12 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 		ret = sk_stream_wait_memory(sk, &timeo);
 		if (ret) {
 trim_sgl:
-			tls_trim_both_msgs(sk, orig_size);
+			if (ctx->open_rec)
+				tls_trim_both_msgs(sk, orig_size);
 			goto send_end;
 		}
 
-		if (msg_en->sg.size < required_size)
+		if (ctx->open_rec && msg_en->sg.size < required_size)
 			goto alloc_encrypted;
 	}
 
@@ -1185,11 +1186,13 @@ static int tls_sw_do_sendpage(struct sock *sk, struct page *page,
 wait_for_memory:
 		ret = sk_stream_wait_memory(sk, &timeo);
 		if (ret) {
-			tls_trim_both_msgs(sk, msg_pl->sg.size);
+			if (ctx->open_rec)
+				tls_trim_both_msgs(sk, msg_pl->sg.size);
 			goto sendpage_end;
 		}
 
-		goto alloc_payload;
+		if (ctx->open_rec)
+			goto alloc_payload;
 	}
 
 	if (num_async) {
-- 
2.20.1


From a1e1f82d7564095a062fdf6bfbad39fb7301deed Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 27 Nov 2019 12:16:40 -0800
Subject: [PATCH 15/25] net/tls: free the record on encryption error

[ Upstream commit d10523d0b3d78153ee58d19853ced26c9004c8c4 ]

When tls_do_encryption() fails the SG lists are left with the
SG_END and SG_CHAIN marks in place. One could hope that once
encryption fails we will never see the record again, but that
is in fact not true. Commit d3b18ad31f93 ("tls: add bpf support
to sk_msg handling") added special handling to ENOMEM and ENOSPC
errors which mean we may see the same record re-submitted.

As suggested by John free the record, the BPF code is already
doing just that.

Reported-by: syzbot+df0d4ec12332661dd1f9@syzkaller.appspotmail.com
Fixes: d3b18ad31f93 ("tls: add bpf support to sk_msg handling")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index cf715e124805..6ef70447f58d 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -766,8 +766,14 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk,
 
 	policy = !(flags & MSG_SENDPAGE_NOPOLICY);
 	psock = sk_psock_get(sk);
-	if (!psock || !policy)
-		return tls_push_record(sk, flags, record_type);
+	if (!psock || !policy) {
+		err = tls_push_record(sk, flags, record_type);
+		if (err) {
+			*copied -= sk_msg_free(sk, msg);
+			tls_free_open_rec(sk);
+		}
+		return err;
+	}
 more_data:
 	enospc = sk_msg_full(msg);
 	if (psock->eval == __SK_NONE) {
-- 
2.20.1


From 529f0fb2cb66e1dda78d0442eb1eedc5f9c59146 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 27 Nov 2019 12:16:41 -0800
Subject: [PATCH 16/25] net: skmsg: fix TLS 1.3 crash with full sk_msg

[ Upstream commit 031097d9e079e40dce401031d1012e83d80eaf01 ]

TLS 1.3 started using the entry at the end of the SG array
for chaining-in the single byte content type entry. This mostly
works:

[ E E E E E E . . ]
  ^           ^
   start       end

                 E < content type
               /
[ E E E E E E C . ]
  ^           ^
   start       end

(Where E denotes a populated SG entry; C denotes a chaining entry.)

If the array is full, however, the end will point to the start:

[ E E E E E E E E ]
  ^
   start
   end

And we end up overwriting the start:

    E < content type
   /
[ C E E E E E E E ]
  ^
   start
   end

The sg array is supposed to be a circular buffer with start and
end markers pointing anywhere. In case where start > end
(i.e. the circular buffer has "wrapped") there is an extra entry
reserved at the end to chain the two halves together.

[ E E E E E E . . l ]

(Where l is the reserved entry for "looping" back to front.

As suggested by John, let's reserve another entry for chaining
SG entries after the main circular buffer. Note that this entry
has to be pointed to by the end entry so its position is not fixed.

Examples of full messages:

[ E E E E E E E E . l ]
  ^               ^
   start           end

   <---------------.
[ E E . E E E E E E l ]
      ^ ^
   end   start

Now the end will always point to an unused entry, so TLS 1.3
can always use it.

Fixes: 130b392c6cd6 ("net: tls: Add tls 1.3 support")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skmsg.h | 26 +++++++++++++-------------
 net/core/filter.c     |  8 ++++----
 net/core/skmsg.c      |  2 +-
 net/ipv4/tcp_bpf.c    |  2 +-
 4 files changed, 19 insertions(+), 19 deletions(-)

diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index ce7055259877..da4caff7efa4 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -14,6 +14,7 @@
 #include <net/strparser.h>
 
 #define MAX_MSG_FRAGS			MAX_SKB_FRAGS
+#define NR_MSG_FRAG_IDS			(MAX_MSG_FRAGS + 1)
 
 enum __sk_action {
 	__SK_DROP = 0,
@@ -29,11 +30,13 @@ struct sk_msg_sg {
 	u32				size;
 	u32				copybreak;
 	bool				copy[MAX_MSG_FRAGS];
-	/* The extra element is used for chaining the front and sections when
-	 * the list becomes partitioned (e.g. end < start). The crypto APIs
-	 * require the chaining.
+	/* The extra two elements:
+	 * 1) used for chaining the front and sections when the list becomes
+	 *    partitioned (e.g. end < start). The crypto APIs require the
+	 *    chaining;
+	 * 2) to chain tailer SG entries after the message.
 	 */
-	struct scatterlist		data[MAX_MSG_FRAGS + 1];
+	struct scatterlist		data[MAX_MSG_FRAGS + 2];
 };
 
 /* UAPI in filter.c depends on struct sk_msg_sg being first element. */
@@ -141,13 +144,13 @@ static inline void sk_msg_apply_bytes(struct sk_psock *psock, u32 bytes)
 
 static inline u32 sk_msg_iter_dist(u32 start, u32 end)
 {
-	return end >= start ? end - start : end + (MAX_MSG_FRAGS - start);
+	return end >= start ? end - start : end + (NR_MSG_FRAG_IDS - start);
 }
 
 #define sk_msg_iter_var_prev(var)			\
 	do {						\
 		if (var == 0)				\
-			var = MAX_MSG_FRAGS - 1;	\
+			var = NR_MSG_FRAG_IDS - 1;	\
 		else					\
 			var--;				\
 	} while (0)
@@ -155,7 +158,7 @@ static inline u32 sk_msg_iter_dist(u32 start, u32 end)
 #define sk_msg_iter_var_next(var)			\
 	do {						\
 		var++;					\
-		if (var == MAX_MSG_FRAGS)		\
+		if (var == NR_MSG_FRAG_IDS)		\
 			var = 0;			\
 	} while (0)
 
@@ -172,9 +175,9 @@ static inline void sk_msg_clear_meta(struct sk_msg *msg)
 
 static inline void sk_msg_init(struct sk_msg *msg)
 {
-	BUILD_BUG_ON(ARRAY_SIZE(msg->sg.data) - 1 != MAX_MSG_FRAGS);
+	BUILD_BUG_ON(ARRAY_SIZE(msg->sg.data) - 1 != NR_MSG_FRAG_IDS);
 	memset(msg, 0, sizeof(*msg));
-	sg_init_marker(msg->sg.data, MAX_MSG_FRAGS);
+	sg_init_marker(msg->sg.data, NR_MSG_FRAG_IDS);
 }
 
 static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src,
@@ -195,14 +198,11 @@ static inline void sk_msg_xfer_full(struct sk_msg *dst, struct sk_msg *src)
 
 static inline bool sk_msg_full(const struct sk_msg *msg)
 {
-	return (msg->sg.end == msg->sg.start) && msg->sg.size;
+	return sk_msg_iter_dist(msg->sg.start, msg->sg.end) == MAX_MSG_FRAGS;
 }
 
 static inline u32 sk_msg_elem_used(const struct sk_msg *msg)
 {
-	if (sk_msg_full(msg))
-		return MAX_MSG_FRAGS;
-
 	return sk_msg_iter_dist(msg->sg.start, msg->sg.end);
 }
 
diff --git a/net/core/filter.c b/net/core/filter.c
index 3fed5755494b..6d0111bfdb4a 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2299,7 +2299,7 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start,
 	WARN_ON_ONCE(last_sge == first_sge);
 	shift = last_sge > first_sge ?
 		last_sge - first_sge - 1 :
-		MAX_SKB_FRAGS - first_sge + last_sge - 1;
+		NR_MSG_FRAG_IDS - first_sge + last_sge - 1;
 	if (!shift)
 		goto out;
 
@@ -2308,8 +2308,8 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start,
 	do {
 		u32 move_from;
 
-		if (i + shift >= MAX_MSG_FRAGS)
-			move_from = i + shift - MAX_MSG_FRAGS;
+		if (i + shift >= NR_MSG_FRAG_IDS)
+			move_from = i + shift - NR_MSG_FRAG_IDS;
 		else
 			move_from = i + shift;
 		if (move_from == msg->sg.end)
@@ -2323,7 +2323,7 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start,
 	} while (1);
 
 	msg->sg.end = msg->sg.end - shift > msg->sg.end ?
-		      msg->sg.end - shift + MAX_MSG_FRAGS :
+		      msg->sg.end - shift + NR_MSG_FRAG_IDS :
 		      msg->sg.end - shift;
 out:
 	msg->data = sg_virt(&msg->sg.data[first_sge]) + start - offset;
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index ad31e4e53d0a..0675d022584e 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -421,7 +421,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb)
 	copied = skb->len;
 	msg->sg.start = 0;
 	msg->sg.size = copied;
-	msg->sg.end = num_sge == MAX_MSG_FRAGS ? 0 : num_sge;
+	msg->sg.end = num_sge;
 	msg->skb = skb;
 
 	sk_psock_queue_msg(psock, msg);
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 8a56e09cfb0e..e38705165ac9 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -301,7 +301,7 @@ EXPORT_SYMBOL_GPL(tcp_bpf_sendmsg_redir);
 static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,
 				struct sk_msg *msg, int *copied, int flags)
 {
-	bool cork = false, enospc = msg->sg.start == msg->sg.end;
+	bool cork = false, enospc = sk_msg_full(msg);
 	struct sock *sk_redir;
 	u32 tosend, delta = 0;
 	int ret;
-- 
2.20.1


From 85238972a788efb62282f9e35db249528505d7b3 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 27 Nov 2019 12:16:42 -0800
Subject: [PATCH 17/25] selftests/tls: add a test for fragmented messages

[ Upstream commit 65190f77424d7b82c4aad7326c9cce6bd91a2fcc ]

Add a sendmsg test with very fragmented messages. This should
fill up sk_msg and test the boundary conditions.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/tls.c | 60 +++++++++++++++++++++++++++++++
 1 file changed, 60 insertions(+)

diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 1c8f194d6556..46abcae47dee 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -268,6 +268,38 @@ TEST_F(tls, sendmsg_single)
 	EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
 }
 
+#define MAX_FRAGS	64
+#define SEND_LEN	13
+TEST_F(tls, sendmsg_fragmented)
+{
+	char const *test_str = "test_sendmsg";
+	char buf[SEND_LEN * MAX_FRAGS];
+	struct iovec vec[MAX_FRAGS];
+	struct msghdr msg;
+	int i, frags;
+
+	for (frags = 1; frags <= MAX_FRAGS; frags++) {
+		for (i = 0; i < frags; i++) {
+			vec[i].iov_base = (char *)test_str;
+			vec[i].iov_len = SEND_LEN;
+		}
+
+		memset(&msg, 0, sizeof(struct msghdr));
+		msg.msg_iov = vec;
+		msg.msg_iovlen = frags;
+
+		EXPECT_EQ(sendmsg(self->fd, &msg, 0), SEND_LEN * frags);
+		EXPECT_EQ(recv(self->cfd, buf, SEND_LEN * frags, MSG_WAITALL),
+			  SEND_LEN * frags);
+
+		for (i = 0; i < frags; i++)
+			EXPECT_EQ(memcmp(buf + SEND_LEN * i,
+					 test_str, SEND_LEN), 0);
+	}
+}
+#undef MAX_FRAGS
+#undef SEND_LEN
+
 TEST_F(tls, sendmsg_large)
 {
 	void *mem = malloc(16384);
@@ -694,6 +726,34 @@ TEST_F(tls, recv_lowat)
 	EXPECT_EQ(memcmp(send_mem, recv_mem + 10, 5), 0);
 }
 
+TEST_F(tls, recv_rcvbuf)
+{
+	char send_mem[4096];
+	char recv_mem[4096];
+	int rcv_buf = 1024;
+
+	memset(send_mem, 0x1c, sizeof(send_mem));
+
+	EXPECT_EQ(setsockopt(self->cfd, SOL_SOCKET, SO_RCVBUF,
+			     &rcv_buf, sizeof(rcv_buf)), 0);
+
+	EXPECT_EQ(send(self->fd, send_mem, 512, 0), 512);
+	memset(recv_mem, 0, sizeof(recv_mem));
+	EXPECT_EQ(recv(self->cfd, recv_mem, sizeof(recv_mem), 0), 512);
+	EXPECT_EQ(memcmp(send_mem, recv_mem, 512), 0);
+
+	if (self->notls)
+		return;
+
+	EXPECT_EQ(send(self->fd, send_mem, 4096, 0), 4096);
+	memset(recv_mem, 0, sizeof(recv_mem));
+	EXPECT_EQ(recv(self->cfd, recv_mem, sizeof(recv_mem), 0), -1);
+	EXPECT_EQ(errno, EMSGSIZE);
+
+	EXPECT_EQ(recv(self->cfd, recv_mem, sizeof(recv_mem), 0), -1);
+	EXPECT_EQ(errno, EMSGSIZE);
+}
+
 TEST_F(tls, bidir)
 {
 	char const *test_str = "test_read";
-- 
2.20.1


From 13613b1754619cef781ce352a10f6055418837ad Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 27 Nov 2019 12:16:43 -0800
Subject: [PATCH 18/25] net/tls: remove the dead inplace_crypto code

[ Upstream commit 9e5ffed37df68d0ccfb2fdc528609e23a1e70ebe ]

Looks like when BPF support was added by commit d3b18ad31f93
("tls: add bpf support to sk_msg handling") and
commit d829e9c4112b ("tls: convert to generic sk_msg interface")
it broke/removed the support for in-place crypto as added by
commit 4e6d47206c32 ("tls: Add support for inplace records
encryption").

The inplace_crypto member of struct tls_rec is dead, inited
to zero, and sometimes set to zero again. It used to be
set to 1 when record was allocated, but the skmsg code doesn't
seem to have been written with the idea of in-place crypto
in mind.

Since non trivial effort is required to bring the feature back
and we don't really have the HW to measure the benefit just
remove the left over support for now to avoid confusing readers.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h | 1 -
 net/tls/tls_sw.c  | 6 +-----
 2 files changed, 1 insertion(+), 6 deletions(-)

diff --git a/include/net/tls.h b/include/net/tls.h
index f4ad831eaa02..b3d57c4d0916 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -122,7 +122,6 @@ struct tls_rec {
 	struct list_head list;
 	int tx_ready;
 	int tx_flags;
-	int inplace_crypto;
 
 	struct sk_msg msg_plaintext;
 	struct sk_msg msg_encrypted;
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 6ef70447f58d..8343f30bb96d 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -705,8 +705,7 @@ static int tls_push_record(struct sock *sk, int flags,
 	}
 
 	i = msg_pl->sg.start;
-	sg_chain(rec->sg_aead_in, 2, rec->inplace_crypto ?
-		 &msg_en->sg.data[i] : &msg_pl->sg.data[i]);
+	sg_chain(rec->sg_aead_in, 2, &msg_pl->sg.data[i]);
 
 	i = msg_en->sg.end;
 	sk_msg_iter_var_prev(i);
@@ -971,8 +970,6 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 			if (ret)
 				goto fallback_to_reg_send;
 
-			rec->inplace_crypto = 0;
-
 			num_zc++;
 			copied += try_to_copy;
 
@@ -1171,7 +1168,6 @@ static int tls_sw_do_sendpage(struct sock *sk, struct page *page,
 
 		tls_ctx->pending_open_record_frags = true;
 		if (full_record || eor || sk_msg_full(msg_pl)) {
-			rec->inplace_crypto = 0;
 			ret = bpf_exec_tx_verdict(msg_pl, sk, full_record,
 						  record_type, &copied, flags);
 			if (ret) {
-- 
2.20.1


From b5c5f02cb6838031543e4cef1a874ab96b4f53a9 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 27 Nov 2019 12:16:44 -0800
Subject: [PATCH 19/25] net/tls: use sg_next() to walk sg entries

[ Upstream commit c5daa6cccdc2f94aca2c9b3fa5f94e4469997293 ]

Partially sent record cleanup path increments an SG entry
directly instead of using sg_next(). This should not be a
problem today, as encrypted messages should be always
allocated as arrays. But given this is a cleanup path it's
easy to miss was this ever to change. Use sg_next(), and
simplify the code.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h  |  2 +-
 net/tls/tls_main.c | 13 ++-----------
 net/tls/tls_sw.c   |  3 ++-
 3 files changed, 5 insertions(+), 13 deletions(-)

diff --git a/include/net/tls.h b/include/net/tls.h
index b3d57c4d0916..093abb5a3dff 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -395,7 +395,7 @@ int tls_push_sg(struct sock *sk, struct tls_context *ctx,
 		int flags);
 int tls_push_partial_record(struct sock *sk, struct tls_context *ctx,
 			    int flags);
-bool tls_free_partial_record(struct sock *sk, struct tls_context *ctx);
+void tls_free_partial_record(struct sock *sk, struct tls_context *ctx);
 
 static inline struct tls_msg *tls_msg(struct sk_buff *skb)
 {
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index f874cc0da45d..eff444293594 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -209,24 +209,15 @@ int tls_push_partial_record(struct sock *sk, struct tls_context *ctx,
 	return tls_push_sg(sk, ctx, sg, offset, flags);
 }
 
-bool tls_free_partial_record(struct sock *sk, struct tls_context *ctx)
+void tls_free_partial_record(struct sock *sk, struct tls_context *ctx)
 {
 	struct scatterlist *sg;
 
-	sg = ctx->partially_sent_record;
-	if (!sg)
-		return false;
-
-	while (1) {
+	for (sg = ctx->partially_sent_record; sg; sg = sg_next(sg)) {
 		put_page(sg_page(sg));
 		sk_mem_uncharge(sk, sg->length);
-
-		if (sg_is_last(sg))
-			break;
-		sg++;
 	}
 	ctx->partially_sent_record = NULL;
-	return true;
 }
 
 static void tls_write_space(struct sock *sk)
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 8343f30bb96d..5dd0f01913c0 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -2084,7 +2084,8 @@ void tls_sw_release_resources_tx(struct sock *sk)
 	/* Free up un-sent records in tx_list. First, free
 	 * the partially sent record if any at head of tx_list.
 	 */
-	if (tls_free_partial_record(sk, tls_ctx)) {
+	if (tls_ctx->partially_sent_record) {
+		tls_free_partial_record(sk, tls_ctx);
 		rec = list_first_entry(&ctx->tx_list,
 				       struct tls_rec, list);
 		list_del(&rec->list);
-- 
2.20.1


From eeb364fc4c63c096202a5c9901b72d217a99ed9a Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 27 Nov 2019 12:16:45 -0800
Subject: [PATCH 20/25] selftests: bpf: test_sockmap: handle file creation
 failures gracefully

[ Upstream commit 4b67c515036313f3c3ecba3cb2babb9cbddb3f85 ]

test_sockmap creates a temporary file to use for sendpage.
this may fail for various reasons. Handle the error rather
than segfault.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/bpf/test_sockmap.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 3845144e2c91..8b838e91cfe5 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -332,6 +332,10 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt,
 	int i, fp;
 
 	file = fopen(".sendpage_tst.tmp", "w+");
+	if (!file) {
+		perror("create file for sendpage");
+		return 1;
+	}
 	for (i = 0; i < iov_length * cnt; i++, k++)
 		fwrite(&k, sizeof(char), 1, file);
 	fflush(file);
@@ -339,6 +343,11 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt,
 	fclose(file);
 
 	fp = open(".sendpage_tst.tmp", O_RDONLY);
+	if (fp < 0) {
+		perror("reopen file for sendpage");
+		return 1;
+	}
+
 	clock_gettime(CLOCK_MONOTONIC, &s->start);
 	for (i = 0; i < cnt; i++) {
 		int sent = sendfile(fd, fp, NULL, iov_length);
-- 
2.20.1


From f2a9e1fe2939194410b60f48d4d1eb5cfe5d4808 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 27 Nov 2019 12:16:46 -0800
Subject: [PATCH 21/25] selftests: bpf: correct perror strings

[ Upstream commit e5dc9dd3258098bf8b5ceb75fc3433b41eff618a ]

perror(str) is basically equivalent to
print("%s: %s\n", str, strerror(errno)).
New line or colon at the end of str is
a mistake/breaks formatting.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/bpf/test_sockmap.c | 38 +++++++++++-----------
 tools/testing/selftests/bpf/xdping.c       |  2 +-
 2 files changed, 20 insertions(+), 20 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 8b838e91cfe5..4a851513c842 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -240,14 +240,14 @@ static int sockmap_init_sockets(int verbose)
 	addr.sin_port = htons(S1_PORT);
 	err = bind(s1, (struct sockaddr *)&addr, sizeof(addr));
 	if (err < 0) {
-		perror("bind s1 failed()\n");
+		perror("bind s1 failed()");
 		return errno;
 	}
 
 	addr.sin_port = htons(S2_PORT);
 	err = bind(s2, (struct sockaddr *)&addr, sizeof(addr));
 	if (err < 0) {
-		perror("bind s2 failed()\n");
+		perror("bind s2 failed()");
 		return errno;
 	}
 
@@ -255,14 +255,14 @@ static int sockmap_init_sockets(int verbose)
 	addr.sin_port = htons(S1_PORT);
 	err = listen(s1, 32);
 	if (err < 0) {
-		perror("listen s1 failed()\n");
+		perror("listen s1 failed()");
 		return errno;
 	}
 
 	addr.sin_port = htons(S2_PORT);
 	err = listen(s2, 32);
 	if (err < 0) {
-		perror("listen s1 failed()\n");
+		perror("listen s1 failed()");
 		return errno;
 	}
 
@@ -270,14 +270,14 @@ static int sockmap_init_sockets(int verbose)
 	addr.sin_port = htons(S1_PORT);
 	err = connect(c1, (struct sockaddr *)&addr, sizeof(addr));
 	if (err < 0 && errno != EINPROGRESS) {
-		perror("connect c1 failed()\n");
+		perror("connect c1 failed()");
 		return errno;
 	}
 
 	addr.sin_port = htons(S2_PORT);
 	err = connect(c2, (struct sockaddr *)&addr, sizeof(addr));
 	if (err < 0 && errno != EINPROGRESS) {
-		perror("connect c2 failed()\n");
+		perror("connect c2 failed()");
 		return errno;
 	} else if (err < 0) {
 		err = 0;
@@ -286,13 +286,13 @@ static int sockmap_init_sockets(int verbose)
 	/* Accept Connecrtions */
 	p1 = accept(s1, NULL, NULL);
 	if (p1 < 0) {
-		perror("accept s1 failed()\n");
+		perror("accept s1 failed()");
 		return errno;
 	}
 
 	p2 = accept(s2, NULL, NULL);
 	if (p2 < 0) {
-		perror("accept s1 failed()\n");
+		perror("accept s1 failed()");
 		return errno;
 	}
 
@@ -353,7 +353,7 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt,
 		int sent = sendfile(fd, fp, NULL, iov_length);
 
 		if (!drop && sent < 0) {
-			perror("send loop error:");
+			perror("send loop error");
 			close(fp);
 			return sent;
 		} else if (drop && sent >= 0) {
@@ -472,7 +472,7 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 			int sent = sendmsg(fd, &msg, flags);
 
 			if (!drop && sent < 0) {
-				perror("send loop error:");
+				perror("send loop error");
 				goto out_errno;
 			} else if (drop && sent >= 0) {
 				printf("send loop error expected: %i\n", sent);
@@ -508,7 +508,7 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 		total_bytes -= txmsg_pop_total;
 		err = clock_gettime(CLOCK_MONOTONIC, &s->start);
 		if (err < 0)
-			perror("recv start time: ");
+			perror("recv start time");
 		while (s->bytes_recvd < total_bytes) {
 			if (txmsg_cork) {
 				timeout.tv_sec = 0;
@@ -552,7 +552,7 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 			if (recv < 0) {
 				if (errno != EWOULDBLOCK) {
 					clock_gettime(CLOCK_MONOTONIC, &s->end);
-					perror("recv failed()\n");
+					perror("recv failed()");
 					goto out_errno;
 				}
 			}
@@ -566,7 +566,7 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 
 				errno = msg_verify_data(&msg, recv, chunk_sz);
 				if (errno) {
-					perror("data verify msg failed\n");
+					perror("data verify msg failed");
 					goto out_errno;
 				}
 				if (recvp) {
@@ -574,7 +574,7 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 								recvp,
 								chunk_sz);
 					if (errno) {
-						perror("data verify msg_peek failed\n");
+						perror("data verify msg_peek failed");
 						goto out_errno;
 					}
 				}
@@ -663,7 +663,7 @@ static int sendmsg_test(struct sockmap_options *opt)
 			err = 0;
 		exit(err ? 1 : 0);
 	} else if (rxpid == -1) {
-		perror("msg_loop_rx: ");
+		perror("msg_loop_rx");
 		return errno;
 	}
 
@@ -690,7 +690,7 @@ static int sendmsg_test(struct sockmap_options *opt)
 				s.bytes_recvd, recvd_Bps, recvd_Bps/giga);
 		exit(err ? 1 : 0);
 	} else if (txpid == -1) {
-		perror("msg_loop_tx: ");
+		perror("msg_loop_tx");
 		return errno;
 	}
 
@@ -724,7 +724,7 @@ static int forever_ping_pong(int rate, struct sockmap_options *opt)
 	/* Ping/Pong data from client to server */
 	sc = send(c1, buf, sizeof(buf), 0);
 	if (sc < 0) {
-		perror("send failed()\n");
+		perror("send failed()");
 		return sc;
 	}
 
@@ -757,7 +757,7 @@ static int forever_ping_pong(int rate, struct sockmap_options *opt)
 			rc = recv(i, buf, sizeof(buf), 0);
 			if (rc < 0) {
 				if (errno != EWOULDBLOCK) {
-					perror("recv failed()\n");
+					perror("recv failed()");
 					return rc;
 				}
 			}
@@ -769,7 +769,7 @@ static int forever_ping_pong(int rate, struct sockmap_options *opt)
 
 			sc = send(i, buf, rc, 0);
 			if (sc < 0) {
-				perror("send failed()\n");
+				perror("send failed()");
 				return sc;
 			}
 		}
diff --git a/tools/testing/selftests/bpf/xdping.c b/tools/testing/selftests/bpf/xdping.c
index d60a343b1371..842d9155d36c 100644
--- a/tools/testing/selftests/bpf/xdping.c
+++ b/tools/testing/selftests/bpf/xdping.c
@@ -45,7 +45,7 @@ static int get_stats(int fd, __u16 count, __u32 raddr)
 	printf("\nXDP RTT data:\n");
 
 	if (bpf_map_lookup_elem(fd, &raddr, &pinginfo)) {
-		perror("bpf_map_lookup elem: ");
+		perror("bpf_map_lookup elem");
 		return 1;
 	}
 
-- 
2.20.1


From 6356802f139fdd7b16f37488c86c8fb1fc047aa0 Mon Sep 17 00:00:00 2001
From: John Rutherford <john.rutherford@dektech.com.au>
Date: Tue, 26 Nov 2019 13:52:55 +1100
Subject: [PATCH 22/25] tipc: fix link name length check

[ Upstream commit fd567ac20cb0377ff466d3337e6e9ac5d0cb15e4 ]

In commit 4f07b80c9733 ("tipc: check msg->req data len in
tipc_nl_compat_bearer_disable") the same patch code was copied into
routines: tipc_nl_compat_bearer_disable(),
tipc_nl_compat_link_stat_dump() and tipc_nl_compat_link_reset_stats().
The two link routine occurrences should have been modified to check
the maximum link name length and not bearer name length.

Fixes: 4f07b80c9733 ("tipc: check msg->reg data len in tipc_nl_compat_bearer_disable")
Signed-off-by: John Rutherford <john.rutherford@dektech.com.au>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/netlink_compat.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index e135d4e11231..d4d2928424e2 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -550,7 +550,7 @@ static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg,
 	if (len <= 0)
 		return -EINVAL;
 
-	len = min_t(int, len, TIPC_MAX_BEARER_NAME);
+	len = min_t(int, len, TIPC_MAX_LINK_NAME);
 	if (!string_is_valid(name, len))
 		return -EINVAL;
 
@@ -822,7 +822,7 @@ static int tipc_nl_compat_link_reset_stats(struct tipc_nl_compat_cmd_doit *cmd,
 	if (len <= 0)
 		return -EINVAL;
 
-	len = min_t(int, len, TIPC_MAX_BEARER_NAME);
+	len = min_t(int, len, TIPC_MAX_LINK_NAME);
 	if (!string_is_valid(name, len))
 		return -EINVAL;
 
-- 
2.20.1


From 1d590dd7111364f9b3d1ef99bc2900994ed32c6f Mon Sep 17 00:00:00 2001
From: Thadeu Lima de Souza Cascardo <cascardo@canonical.com>
Date: Thu, 28 Nov 2019 15:58:06 -0300
Subject: [PATCH 23/25] selftests: pmtu: use -oneline for ip route list cache

[ Upstream commit 2745aea6750ff0d2c48285d25bdb00e5b636ec8b ]

Some versions of iproute2 will output more than one line per entry, which
will cause the test to fail, like:

TEST: ipv6: list and flush cached exceptions                        [FAIL]
  can't list cached exceptions

That happens, for example, with iproute2 4.15.0. When using the -oneline
option, this will work just fine:

TEST: ipv6: list and flush cached exceptions                        [ OK ]

This also works just fine with a more recent version of iproute2, like
5.4.0.

For some reason, two lines are printed for the IPv4 test no matter what
version of iproute2 is used. Use the same -oneline parameter there instead
of counting the lines twice.

Fixes: b964641e9925 ("selftests: pmtu: Make list_flush_ipv6_exception test more demanding")
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@canonical.com>
Acked-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/pmtu.sh | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index ab367e75f095..d697815d2785 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -1249,8 +1249,7 @@ test_list_flush_ipv4_exception() {
 	done
 	run_cmd ${ns_a} ping -q -M want -i 0.1 -c 2 -s 1800 "${dst2}"
 
-	# Each exception is printed as two lines
-	if [ "$(${ns_a} ip route list cache | wc -l)" -ne 202 ]; then
+	if [ "$(${ns_a} ip -oneline route list cache | wc -l)" -ne 101 ]; then
 		err "  can't list cached exceptions"
 		fail=1
 	fi
@@ -1300,7 +1299,7 @@ test_list_flush_ipv6_exception() {
 		run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s 1800 "${dst_prefix1}${i}"
 	done
 	run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s 1800 "${dst2}"
-	if [ "$(${ns_a} ip -6 route list cache | wc -l)" -ne 101 ]; then
+	if [ "$(${ns_a} ip -oneline -6 route list cache | wc -l)" -ne 101 ]; then
 		err "  can't list cached exceptions"
 		fail=1
 	fi
-- 
2.20.1


From b967bf39cc7853d76df03c52b71f68eb4999f38a Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 1 Dec 2019 10:27:14 +0100
Subject: [PATCH 24/25] r8169: fix jumbo configuration for RTL8168evl

[ Upstream commit 14012c9f3bb922b9e0751ba43d15cc580a6049bf ]

Alan reported [0] that network is broken since the referenced commit
when using jumbo frames. This commit isn't wrong, it just revealed
another issue that has been existing before. According to the vendor
driver the RTL8168e-specific jumbo config doesn't apply for RTL8168evl.

[0] https://lkml.org/lkml/2019/11/30/119

Fixes: 4ebcb113edcc ("r8169: fix jumbo packet handling on resume from suspend")
Reported-by: Alan J. Wylie <alan@wylie.me.uk>
Tested-by: Alan J. Wylie <alan@wylie.me.uk>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index c33c438850cc..97993655ad87 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -4118,7 +4118,7 @@ static void rtl_hw_jumbo_enable(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_27 ... RTL_GIGA_MAC_VER_28:
 		r8168dp_hw_jumbo_enable(tp);
 		break;
-	case RTL_GIGA_MAC_VER_31 ... RTL_GIGA_MAC_VER_34:
+	case RTL_GIGA_MAC_VER_31 ... RTL_GIGA_MAC_VER_33:
 		r8168e_hw_jumbo_enable(tp);
 		break;
 	default:
-- 
2.20.1


From 5021347d23c4e31e4aa26278ce8446ec44b7c36c Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 1 Dec 2019 10:39:56 +0100
Subject: [PATCH 25/25] r8169: fix resume on cable plug-in

[ Upstream commit 398fd408ccfb5e44b1cbe73a209d2281d3efa83c ]

It was reported [0] that network doesn't wake up on cable plug-in with
certain chip versions. Reason is that on these chip versions the PHY
doesn't detect cable plug-in when being in power-down mode. So prevent
the PHY from powering down if WoL is enabled.

[0] https://bugzilla.kernel.org/show_bug.cgi?id=202103

Fixes: 95fb8bb3181b ("net: phy: force phy suspend when calling phy_stop")
Reported-by: jhdskag3 <jhdskag3@tutanota.com>
Tested-by: jhdskag3 <jhdskag3@tutanota.com>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 97993655ad87..1d67eeeab79d 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -1516,6 +1516,7 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts)
 	rtl_lock_config_regs(tp);
 
 	device_set_wakeup_enable(tp_to_dev(tp), wolopts);
+	tp->dev->wol_enabled = wolopts ? 1 : 0;
 }
 
 static int rtl8169_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Mon, Dec 02, 2019 at 07:21:47PM -0800, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v5.3 and v5.4
> -stable, respectively.
> 
> Thank you!


All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 102 bytes --]


Please queue up the following networking bug fixes for v5.3 and
v5.4 -stable, respectively.

Thanks!

[-- Attachment #2: net_53.mbox --]
[-- Type: Application/Octet-Stream, Size: 114605 bytes --]

From ac9dffd361dff90a9b74ced72ec9181b8b13384f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 5 Dec 2019 20:43:46 -0800
Subject: [PATCH 01/26] inet: protect against too small mtu values.

[ Upstream commit 501a90c945103e8627406763dac418f20f3837b2 ]

syzbot was once again able to crash a host by setting a very small mtu
on loopback device.

Let's make inetdev_valid_mtu() available in include/net/ip.h,
and use it in ip_setup_cork(), so that we protect both ip_append_page()
and __ip_append_data()

Also add a READ_ONCE() when the device mtu is read.

Pairs this lockless read with one WRITE_ONCE() in __dev_set_mtu(),
even if other code paths might write over this field.

Add a big comment in include/linux/netdevice.h about dev->mtu
needing READ_ONCE()/WRITE_ONCE() annotations.

Hopefully we will add the missing ones in followup patches.

[1]

refcount_t: saturated; leaking memory.
WARNING: CPU: 0 PID: 9464 at lib/refcount.c:22 refcount_warn_saturate+0x138/0x1f0 lib/refcount.c:22
Kernel panic - not syncing: panic_on_warn set ...
CPU: 0 PID: 9464 Comm: syz-executor850 Not tainted 5.4.0-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x197/0x210 lib/dump_stack.c:118
 panic+0x2e3/0x75c kernel/panic.c:221
 __warn.cold+0x2f/0x3e kernel/panic.c:582
 report_bug+0x289/0x300 lib/bug.c:195
 fixup_bug arch/x86/kernel/traps.c:174 [inline]
 fixup_bug arch/x86/kernel/traps.c:169 [inline]
 do_error_trap+0x11b/0x200 arch/x86/kernel/traps.c:267
 do_invalid_op+0x37/0x50 arch/x86/kernel/traps.c:286
 invalid_op+0x23/0x30 arch/x86/entry/entry_64.S:1027
RIP: 0010:refcount_warn_saturate+0x138/0x1f0 lib/refcount.c:22
Code: 06 31 ff 89 de e8 c8 f5 e6 fd 84 db 0f 85 6f ff ff ff e8 7b f4 e6 fd 48 c7 c7 e0 71 4f 88 c6 05 56 a6 a4 06 01 e8 c7 a8 b7 fd <0f> 0b e9 50 ff ff ff e8 5c f4 e6 fd 0f b6 1d 3d a6 a4 06 31 ff 89
RSP: 0018:ffff88809689f550 EFLAGS: 00010286
RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000
RDX: 0000000000000000 RSI: ffffffff815e4336 RDI: ffffed1012d13e9c
RBP: ffff88809689f560 R08: ffff88809c50a3c0 R09: fffffbfff15d31b1
R10: fffffbfff15d31b0 R11: ffffffff8ae98d87 R12: 0000000000000001
R13: 0000000000040100 R14: ffff888099041104 R15: ffff888218d96e40
 refcount_add include/linux/refcount.h:193 [inline]
 skb_set_owner_w+0x2b6/0x410 net/core/sock.c:1999
 sock_wmalloc+0xf1/0x120 net/core/sock.c:2096
 ip_append_page+0x7ef/0x1190 net/ipv4/ip_output.c:1383
 udp_sendpage+0x1c7/0x480 net/ipv4/udp.c:1276
 inet_sendpage+0xdb/0x150 net/ipv4/af_inet.c:821
 kernel_sendpage+0x92/0xf0 net/socket.c:3794
 sock_sendpage+0x8b/0xc0 net/socket.c:936
 pipe_to_sendpage+0x2da/0x3c0 fs/splice.c:458
 splice_from_pipe_feed fs/splice.c:512 [inline]
 __splice_from_pipe+0x3ee/0x7c0 fs/splice.c:636
 splice_from_pipe+0x108/0x170 fs/splice.c:671
 generic_splice_sendpage+0x3c/0x50 fs/splice.c:842
 do_splice_from fs/splice.c:861 [inline]
 direct_splice_actor+0x123/0x190 fs/splice.c:1035
 splice_direct_to_actor+0x3b4/0xa30 fs/splice.c:990
 do_splice_direct+0x1da/0x2a0 fs/splice.c:1078
 do_sendfile+0x597/0xd00 fs/read_write.c:1464
 __do_sys_sendfile64 fs/read_write.c:1525 [inline]
 __se_sys_sendfile64 fs/read_write.c:1511 [inline]
 __x64_sys_sendfile64+0x1dd/0x220 fs/read_write.c:1511
 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x441409
Code: e8 ac e8 ff ff 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 eb 08 fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007fffb64c4f78 EFLAGS: 00000246 ORIG_RAX: 0000000000000028
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 0000000000441409
RDX: 0000000000000000 RSI: 0000000000000006 RDI: 0000000000000005
RBP: 0000000000073b8a R08: 0000000000000010 R09: 0000000000000010
R10: 0000000000010001 R11: 0000000000000246 R12: 0000000000402180
R13: 0000000000402210 R14: 0000000000000000 R15: 0000000000000000
Kernel Offset: disabled
Rebooting in 86400 seconds..

Fixes: 1470ddf7f8ce ("inet: Remove explicit write references to sk/inet in ip_append_data")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  5 +++++
 include/net/ip.h          |  5 +++++
 net/core/dev.c            |  3 ++-
 net/ipv4/devinet.c        |  5 -----
 net/ipv4/ip_output.c      | 13 ++++++++-----
 5 files changed, 20 insertions(+), 11 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 88292953aa6f..9d639ea51acd 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1848,6 +1848,11 @@ struct net_device {
 	unsigned char		if_port;
 	unsigned char		dma;
 
+	/* Note : dev->mtu is often read without holding a lock.
+	 * Writers usually hold RTNL.
+	 * It is recommended to use READ_ONCE() to annotate the reads,
+	 * and to use WRITE_ONCE() to annotate the writes.
+	 */
 	unsigned int		mtu;
 	unsigned int		min_mtu;
 	unsigned int		max_mtu;
diff --git a/include/net/ip.h b/include/net/ip.h
index e6609ab69161..df712087320a 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -759,4 +759,9 @@ int ip_misc_proc_init(void);
 int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto, u8 family,
 				struct netlink_ext_ack *extack);
 
+static inline bool inetdev_valid_mtu(unsigned int mtu)
+{
+	return likely(mtu >= IPV4_MIN_MTU);
+}
+
 #endif	/* _IP_H */
diff --git a/net/core/dev.c b/net/core/dev.c
index 33b278b826b5..ae83b3059d67 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7662,7 +7662,8 @@ int __dev_set_mtu(struct net_device *dev, int new_mtu)
 	if (ops->ndo_change_mtu)
 		return ops->ndo_change_mtu(dev, new_mtu);
 
-	dev->mtu = new_mtu;
+	/* Pairs with all the lockless reads of dev->mtu in the stack */
+	WRITE_ONCE(dev->mtu, new_mtu);
 	return 0;
 }
 EXPORT_SYMBOL(__dev_set_mtu);
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index a4b5bd4d2c89..e4632bd2026d 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1496,11 +1496,6 @@ static void inetdev_changename(struct net_device *dev, struct in_device *in_dev)
 	}
 }
 
-static bool inetdev_valid_mtu(unsigned int mtu)
-{
-	return mtu >= IPV4_MIN_MTU;
-}
-
 static void inetdev_send_gratuitous_arp(struct net_device *dev,
 					struct in_device *in_dev)
 
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index e780ceab16e1..cd664655806e 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1258,15 +1258,18 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 		cork->addr = ipc->addr;
 	}
 
-	/*
-	 * We steal reference to this route, caller should not release it
-	 */
-	*rtp = NULL;
 	cork->fragsize = ip_sk_use_pmtu(sk) ?
-			 dst_mtu(&rt->dst) : rt->dst.dev->mtu;
+			 dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu);
+
+	if (!inetdev_valid_mtu(cork->fragsize))
+		return -ENETUNREACH;
 
 	cork->gso_size = ipc->gso_size;
+
 	cork->dst = &rt->dst;
+	/* We stole this route, caller should not release it. */
+	*rtp = NULL;
+
 	cork->length = 0;
 	cork->ttl = ipc->ttl;
 	cork->tos = ipc->tos;
-- 
2.20.1


From 73f238543980a341efe455922ee8f6c45b724caf Mon Sep 17 00:00:00 2001
From: Vladyslav Tarasiuk <vladyslavt@mellanox.com>
Date: Fri, 6 Dec 2019 13:51:05 +0000
Subject: [PATCH 02/26] mqprio: Fix out-of-bounds access in mqprio_dump

[ Upstream commit 9f104c7736904ac72385bbb48669e0c923ca879b ]

When user runs a command like
tc qdisc add dev eth1 root mqprio
KASAN stack-out-of-bounds warning is emitted.
Currently, NLA_ALIGN macro used in mqprio_dump provides too large
buffer size as argument for nla_put and memcpy down the call stack.
The flow looks like this:
1. nla_put expects exact object size as an argument;
2. Later it provides this size to memcpy;
3. To calculate correct padding for SKB, nla_put applies NLA_ALIGN
   macro itself.

Therefore, NLA_ALIGN should not be applied to the nla_put parameter.
Otherwise it will lead to out-of-bounds memory access in memcpy.

Fixes: 4e8b86c06269 ("mqprio: Introduce new hardware offload mode and shaper in mqprio")
Signed-off-by: Vladyslav Tarasiuk <vladyslavt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_mqprio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index 0d0113a24962..7b67e4d8e448 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -433,7 +433,7 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb)
 		opt.offset[tc] = dev->tc_to_txq[tc].offset;
 	}
 
-	if (nla_put(skb, TCA_OPTIONS, NLA_ALIGN(sizeof(opt)), &opt))
+	if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt))
 		goto nla_put_failure;
 
 	if ((priv->flags & TC_MQPRIO_F_MODE) &&
-- 
2.20.1


From 88c49b274861c263fe77835bde1a52d7830b7a93 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Tue, 3 Dec 2019 16:48:06 +0200
Subject: [PATCH 03/26] net: bridge: deny dev_set_mac_address() when
 unregistering

[ Upstream commit c4b4c421857dc7b1cf0dccbd738472360ff2cd70 ]

We have an interesting memory leak in the bridge when it is being
unregistered and is a slave to a master device which would change the
mac of its slaves on unregister (e.g. bond, team). This is a very
unusual setup but we do end up leaking 1 fdb entry because
dev_set_mac_address() would cause the bridge to insert the new mac address
into its table after all fdbs are flushed, i.e. after dellink() on the
bridge has finished and we call NETDEV_UNREGISTER the bond/team would
release it and will call dev_set_mac_address() to restore its original
address and that in turn will add an fdb in the bridge.
One fix is to check for the bridge dev's reg_state in its
ndo_set_mac_address callback and return an error if the bridge is not in
NETREG_REGISTERED.

Easy steps to reproduce:
 1. add bond in mode != A/B
 2. add any slave to the bond
 3. add bridge dev as a slave to the bond
 4. destroy the bridge device

Trace:
 unreferenced object 0xffff888035c4d080 (size 128):
   comm "ip", pid 4068, jiffies 4296209429 (age 1413.753s)
   hex dump (first 32 bytes):
     41 1d c9 36 80 88 ff ff 00 00 00 00 00 00 00 00  A..6............
     d2 19 c9 5e 3f d7 00 00 00 00 00 00 00 00 00 00  ...^?...........
   backtrace:
     [<00000000ddb525dc>] kmem_cache_alloc+0x155/0x26f
     [<00000000633ff1e0>] fdb_create+0x21/0x486 [bridge]
     [<0000000092b17e9c>] fdb_insert+0x91/0xdc [bridge]
     [<00000000f2a0f0ff>] br_fdb_change_mac_address+0xb3/0x175 [bridge]
     [<000000001de02dbd>] br_stp_change_bridge_id+0xf/0xff [bridge]
     [<00000000ac0e32b1>] br_set_mac_address+0x76/0x99 [bridge]
     [<000000006846a77f>] dev_set_mac_address+0x63/0x9b
     [<00000000d30738fc>] __bond_release_one+0x3f6/0x455 [bonding]
     [<00000000fc7ec01d>] bond_netdev_event+0x2f2/0x400 [bonding]
     [<00000000305d7795>] notifier_call_chain+0x38/0x56
     [<0000000028885d4a>] call_netdevice_notifiers+0x1e/0x23
     [<000000008279477b>] rollback_registered_many+0x353/0x6a4
     [<0000000018ef753a>] unregister_netdevice_many+0x17/0x6f
     [<00000000ba854b7a>] rtnl_delete_link+0x3c/0x43
     [<00000000adf8618d>] rtnl_dellink+0x1dc/0x20a
     [<000000009b6395fd>] rtnetlink_rcv_msg+0x23d/0x268

Fixes: 43598813386f ("bridge: add local MAC address to forwarding table (v2)")
Reported-by: syzbot+2add91c08eb181fea1bf@syzkaller.appspotmail.com
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_device.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 681b72862c16..750e8dba38ec 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -253,6 +253,12 @@ static int br_set_mac_address(struct net_device *dev, void *p)
 	if (!is_valid_ether_addr(addr->sa_data))
 		return -EADDRNOTAVAIL;
 
+	/* dev_set_mac_addr() can be called by a master device on bridge's
+	 * NETDEV_UNREGISTER, but since it's being destroyed do nothing
+	 */
+	if (dev->reg_state != NETREG_REGISTERED)
+		return -EBUSY;
+
 	spin_lock_bh(&br->lock);
 	if (!ether_addr_equal(dev->dev_addr, addr->sa_data)) {
 		/* Mac address will be changed in br_stp_change_bridge_id(). */
-- 
2.20.1


From a29765f274f1439960f5af055ae6313f669c795b Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <alobakin@dlink.ru>
Date: Thu, 5 Dec 2019 13:02:35 +0300
Subject: [PATCH 04/26] net: dsa: fix flow dissection on Tx path

[ Upstream commit 8bef0af09a5415df761b04fa487a6c34acae74bc ]

Commit 43e665287f93 ("net-next: dsa: fix flow dissection") added an
ability to override protocol and network offset during flow dissection
for DSA-enabled devices (i.e. controllers shipped as switch CPU ports)
in order to fix skb hashing for RPS on Rx path.

However, skb_hash() and added part of code can be invoked not only on
Rx, but also on Tx path if we have a multi-queued device and:
 - kernel is running on UP system or
 - XPS is not configured.

The call stack in this two cases will be like: dev_queue_xmit() ->
__dev_queue_xmit() -> netdev_core_pick_tx() -> netdev_pick_tx() ->
skb_tx_hash() -> skb_get_hash().

The problem is that skbs queued for Tx have both network offset and
correct protocol already set up even after inserting a CPU tag by DSA
tagger, so calling tag_ops->flow_dissect() on this path actually only
breaks flow dissection and hashing.

This can be observed by adding debug prints just before and right after
tag_ops->flow_dissect() call to the related block of code:

Before the patch:

Rx path (RPS):

[   19.240001] Rx: proto: 0x00f8, nhoff: 0	/* ETH_P_XDSA */
[   19.244271] tag_ops->flow_dissect()
[   19.247811] Rx: proto: 0x0800, nhoff: 8	/* ETH_P_IP */

[   19.215435] Rx: proto: 0x00f8, nhoff: 0	/* ETH_P_XDSA */
[   19.219746] tag_ops->flow_dissect()
[   19.223241] Rx: proto: 0x0806, nhoff: 8	/* ETH_P_ARP */

[   18.654057] Rx: proto: 0x00f8, nhoff: 0	/* ETH_P_XDSA */
[   18.658332] tag_ops->flow_dissect()
[   18.661826] Rx: proto: 0x8100, nhoff: 8	/* ETH_P_8021Q */

Tx path (UP system):

[   18.759560] Tx: proto: 0x0800, nhoff: 26	/* ETH_P_IP */
[   18.763933] tag_ops->flow_dissect()
[   18.767485] Tx: proto: 0x920b, nhoff: 34	/* junk */

[   22.800020] Tx: proto: 0x0806, nhoff: 26	/* ETH_P_ARP */
[   22.804392] tag_ops->flow_dissect()
[   22.807921] Tx: proto: 0x920b, nhoff: 34	/* junk */

[   16.898342] Tx: proto: 0x86dd, nhoff: 26	/* ETH_P_IPV6 */
[   16.902705] tag_ops->flow_dissect()
[   16.906227] Tx: proto: 0x920b, nhoff: 34	/* junk */

After:

Rx path (RPS):

[   16.520993] Rx: proto: 0x00f8, nhoff: 0	/* ETH_P_XDSA */
[   16.525260] tag_ops->flow_dissect()
[   16.528808] Rx: proto: 0x0800, nhoff: 8	/* ETH_P_IP */

[   15.484807] Rx: proto: 0x00f8, nhoff: 0	/* ETH_P_XDSA */
[   15.490417] tag_ops->flow_dissect()
[   15.495223] Rx: proto: 0x0806, nhoff: 8	/* ETH_P_ARP */

[   17.134621] Rx: proto: 0x00f8, nhoff: 0	/* ETH_P_XDSA */
[   17.138895] tag_ops->flow_dissect()
[   17.142388] Rx: proto: 0x8100, nhoff: 8	/* ETH_P_8021Q */

Tx path (UP system):

[   15.499558] Tx: proto: 0x0800, nhoff: 26	/* ETH_P_IP */

[   20.664689] Tx: proto: 0x0806, nhoff: 26	/* ETH_P_ARP */

[   18.565782] Tx: proto: 0x86dd, nhoff: 26	/* ETH_P_IPV6 */

In order to fix that we can add the check 'proto == htons(ETH_P_XDSA)'
to prevent code from calling tag_ops->flow_dissect() on Tx.
I also decided to initialize 'offset' variable so tagger callbacks can
now safely leave it untouched without provoking a chaos.

Fixes: 43e665287f93 ("net-next: dsa: fix flow dissection")
Signed-off-by: Alexander Lobakin <alobakin@dlink.ru>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/flow_dissector.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 2f5326a82465..fdcce7ab0cc3 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -853,9 +853,10 @@ bool __skb_flow_dissect(const struct net *net,
 		nhoff = skb_network_offset(skb);
 		hlen = skb_headlen(skb);
 #if IS_ENABLED(CONFIG_NET_DSA)
-		if (unlikely(skb->dev && netdev_uses_dsa(skb->dev))) {
+		if (unlikely(skb->dev && netdev_uses_dsa(skb->dev) &&
+			     proto == htons(ETH_P_XDSA))) {
 			const struct dsa_device_ops *ops;
-			int offset;
+			int offset = 0;
 
 			ops = skb->dev->dsa_ptr->tag_ops;
 			if (ops->flow_dissect &&
-- 
2.20.1


From 234e405c3e38b6b57f53915be35875e2a5564c88 Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Fri, 6 Dec 2019 14:28:20 +0200
Subject: [PATCH 05/26] net: ethernet: ti: cpsw: fix extra rx interrupt

[ Upstream commit 51302f77bedab8768b761ed1899c08f89af9e4e2 ]

Now RX interrupt is triggered twice every time, because in
cpsw_rx_interrupt() it is asked first and then disabled. So there will be
pending interrupt always, when RX interrupt is enabled again in NAPI
handler.

Fix it by first disabling IRQ and then do ask.

Fixes: 870915feabdc ("drivers: net: cpsw: remove disable_irq/enable_irq as irq can be masked from cpsw itself")
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index a46b8b2e44e1..1840fa1f8f3c 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -890,8 +890,8 @@ static irqreturn_t cpsw_rx_interrupt(int irq, void *dev_id)
 {
 	struct cpsw_common *cpsw = dev_id;
 
-	cpdma_ctlr_eoi(cpsw->dma, CPDMA_EOI_RX);
 	writel(0, &cpsw->wr_regs->rx_en);
+	cpdma_ctlr_eoi(cpsw->dma, CPDMA_EOI_RX);
 
 	if (cpsw->quirk_irq) {
 		disable_irq_nosync(cpsw->irqs_table[0]);
-- 
2.20.1


From e0325b65a9d20efbee07d15c4e5d925bbcfabdde Mon Sep 17 00:00:00 2001
From: Dust Li <dust.li@linux.alibaba.com>
Date: Tue, 3 Dec 2019 11:17:40 +0800
Subject: [PATCH 06/26] net: sched: fix dump qlen for sch_mq/sch_mqprio with
 NOLOCK subqueues

[ Upstream commit 2f23cd42e19c22c24ff0e221089b7b6123b117c5 ]

sch->q.len hasn't been set if the subqueue is a NOLOCK qdisc
 in mq_dump() and mqprio_dump().

Fixes: ce679e8df7ed ("net: sched: add support for TCQ_F_NOLOCK subqueues to sch_mqprio")
Signed-off-by: Dust Li <dust.li@linux.alibaba.com>
Signed-off-by: Tony Lu <tonylu@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_mq.c     | 1 +
 net/sched/sch_mqprio.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
index 278c0b2dc523..e79f1afe0cfd 100644
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -153,6 +153,7 @@ static int mq_dump(struct Qdisc *sch, struct sk_buff *skb)
 			__gnet_stats_copy_queue(&sch->qstats,
 						qdisc->cpu_qstats,
 						&qdisc->qstats, qlen);
+			sch->q.qlen		+= qlen;
 		} else {
 			sch->q.qlen		+= qdisc->q.qlen;
 			sch->bstats.bytes	+= qdisc->bstats.bytes;
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index 7b67e4d8e448..8766ab5b8788 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -411,6 +411,7 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb)
 			__gnet_stats_copy_queue(&sch->qstats,
 						qdisc->cpu_qstats,
 						&qdisc->qstats, qlen);
+			sch->q.qlen		+= qlen;
 		} else {
 			sch->q.qlen		+= qdisc->q.qlen;
 			sch->bstats.bytes	+= qdisc->bstats.bytes;
-- 
2.20.1


From f263977baa147aad631a8757e5a009825151baec Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 7 Dec 2019 11:34:45 -0800
Subject: [PATCH 07/26] net_sched: validate TCA_KIND attribute in
 tc_chain_tmplt_add()

[ Upstream commit 2dd5616ecdcebdf5a8d007af64e040d4e9214efe ]

Use the new tcf_proto_check_kind() helper to make sure user
provided value is well formed.

BUG: KMSAN: uninit-value in string_nocheck lib/vsprintf.c:606 [inline]
BUG: KMSAN: uninit-value in string+0x4be/0x600 lib/vsprintf.c:668
CPU: 0 PID: 12358 Comm: syz-executor.1 Not tainted 5.4.0-rc8-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c9/0x220 lib/dump_stack.c:118
 kmsan_report+0x128/0x220 mm/kmsan/kmsan_report.c:108
 __msan_warning+0x64/0xc0 mm/kmsan/kmsan_instr.c:245
 string_nocheck lib/vsprintf.c:606 [inline]
 string+0x4be/0x600 lib/vsprintf.c:668
 vsnprintf+0x218f/0x3210 lib/vsprintf.c:2510
 __request_module+0x2b1/0x11c0 kernel/kmod.c:143
 tcf_proto_lookup_ops+0x171/0x700 net/sched/cls_api.c:139
 tc_chain_tmplt_add net/sched/cls_api.c:2730 [inline]
 tc_ctl_chain+0x1904/0x38a0 net/sched/cls_api.c:2850
 rtnetlink_rcv_msg+0x115a/0x1580 net/core/rtnetlink.c:5224
 netlink_rcv_skb+0x431/0x620 net/netlink/af_netlink.c:2477
 rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:5242
 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
 netlink_unicast+0xf3e/0x1020 net/netlink/af_netlink.c:1328
 netlink_sendmsg+0x110f/0x1330 net/netlink/af_netlink.c:1917
 sock_sendmsg_nosec net/socket.c:637 [inline]
 sock_sendmsg net/socket.c:657 [inline]
 ___sys_sendmsg+0x14ff/0x1590 net/socket.c:2311
 __sys_sendmsg net/socket.c:2356 [inline]
 __do_sys_sendmsg net/socket.c:2365 [inline]
 __se_sys_sendmsg+0x305/0x460 net/socket.c:2363
 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2363
 do_syscall_64+0xb6/0x160 arch/x86/entry/common.c:291
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x45a649
Code: ad b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f0790795c78 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 000000000045a649
RDX: 0000000000000000 RSI: 0000000020000300 RDI: 0000000000000006
RBP: 000000000075bfc8 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00007f07907966d4
R13: 00000000004c8db5 R14: 00000000004df630 R15: 00000000ffffffff

Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:149 [inline]
 kmsan_internal_poison_shadow+0x5c/0x110 mm/kmsan/kmsan.c:132
 kmsan_slab_alloc+0x97/0x100 mm/kmsan/kmsan_hooks.c:86
 slab_alloc_node mm/slub.c:2773 [inline]
 __kmalloc_node_track_caller+0xe27/0x11a0 mm/slub.c:4381
 __kmalloc_reserve net/core/skbuff.c:141 [inline]
 __alloc_skb+0x306/0xa10 net/core/skbuff.c:209
 alloc_skb include/linux/skbuff.h:1049 [inline]
 netlink_alloc_large_skb net/netlink/af_netlink.c:1174 [inline]
 netlink_sendmsg+0x783/0x1330 net/netlink/af_netlink.c:1892
 sock_sendmsg_nosec net/socket.c:637 [inline]
 sock_sendmsg net/socket.c:657 [inline]
 ___sys_sendmsg+0x14ff/0x1590 net/socket.c:2311
 __sys_sendmsg net/socket.c:2356 [inline]
 __do_sys_sendmsg net/socket.c:2365 [inline]
 __se_sys_sendmsg+0x305/0x460 net/socket.c:2363
 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2363
 do_syscall_64+0xb6/0x160 arch/x86/entry/common.c:291
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 6f96c3c6904c ("net_sched: fix backward compatibility for TCA_KIND")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 5c1769999a92..758ca7e5304c 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -2854,13 +2854,19 @@ static int tc_chain_tmplt_add(struct tcf_chain *chain, struct net *net,
 			      struct netlink_ext_ack *extack)
 {
 	const struct tcf_proto_ops *ops;
+	char name[IFNAMSIZ];
 	void *tmplt_priv;
 
 	/* If kind is not set, user did not specify template. */
 	if (!tca[TCA_KIND])
 		return 0;
 
-	ops = tcf_proto_lookup_ops(nla_data(tca[TCA_KIND]), true, extack);
+	if (tcf_proto_check_kind(tca[TCA_KIND], name)) {
+		NL_SET_ERR_MSG(extack, "Specified TC chain template name too long");
+		return -EINVAL;
+	}
+
+	ops = tcf_proto_lookup_ops(name, true, extack);
 	if (IS_ERR(ops))
 		return PTR_ERR(ops);
 	if (!ops->tmplt_create || !ops->tmplt_destroy || !ops->tmplt_dump) {
-- 
2.20.1


From dfd7a8e6ac6c0b31767590c171d186040a46ca8f Mon Sep 17 00:00:00 2001
From: Jouni Hogander <jouni.hogander@unikie.com>
Date: Thu, 5 Dec 2019 15:57:07 +0200
Subject: [PATCH 08/26] net-sysfs: Call dev_hold always in
 netdev_queue_add_kobject

[ Upstream commit e0b60903b434a7ee21ba8d8659f207ed84101e89 ]

Dev_hold has to be called always in netdev_queue_add_kobject.
Otherwise usage count drops below 0 in case of failure in
kobject_init_and_add.

Fixes: b8eb718348b8 ("net-sysfs: Fix reference count leak in rx|netdev_queue_add_kobject")
Reported-by: Hulk Robot <hulkci@huawei.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: David Miller <davem@davemloft.net>
Cc: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/net-sysfs.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 865ba6ca16eb..8ddd72ca2452 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1457,14 +1457,17 @@ static int netdev_queue_add_kobject(struct net_device *dev, int index)
 	struct kobject *kobj = &queue->kobj;
 	int error = 0;
 
+	/* Kobject_put later will trigger netdev_queue_release call
+	 * which decreases dev refcount: Take that reference here
+	 */
+	dev_hold(queue->dev);
+
 	kobj->kset = dev->queues_kset;
 	error = kobject_init_and_add(kobj, &netdev_queue_ktype, NULL,
 				     "tx-%u", index);
 	if (error)
 		return error;
 
-	dev_hold(queue->dev);
-
 #ifdef CONFIG_BQL
 	error = sysfs_create_group(kobj, &dql_group);
 	if (error) {
-- 
2.20.1


From 2414c7a6eafaeca38ffc28100cf5e240ac759795 Mon Sep 17 00:00:00 2001
From: Mian Yousaf Kaukab <ykaukab@suse.de>
Date: Thu, 5 Dec 2019 10:41:16 +0100
Subject: [PATCH 09/26] net: thunderx: start phy before starting
 autonegotiation

[ Upstream commit a350d2e7adbb57181d33e3aa6f0565632747feaa ]

Since commit 2b3e88ea6528 ("net: phy: improve phy state checking")
phy_start_aneg() expects phy state to be >= PHY_UP. Call phy_start()
before calling phy_start_aneg() during probe so that autonegotiation
is initiated.

As phy_start() takes care of calling phy_start_aneg(), drop the explicit
call to phy_start_aneg().

Network fails without this patch on Octeon TX.

Fixes: 2b3e88ea6528 ("net: phy: improve phy state checking")
Signed-off-by: Mian Yousaf Kaukab <ykaukab@suse.de>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/thunder/thunder_bgx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index acb016834f04..6cc100e7d5c0 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -1115,7 +1115,7 @@ static int bgx_lmac_enable(struct bgx *bgx, u8 lmacid)
 				       phy_interface_mode(lmac->lmac_type)))
 			return -ENODEV;
 
-		phy_start_aneg(lmac->phydev);
+		phy_start(lmac->phydev);
 		return 0;
 	}
 
-- 
2.20.1


From 6a8610d2affbcfcf5e4b8eabd1da1cdace4f1641 Mon Sep 17 00:00:00 2001
From: Valentin Vidic <vvidic@valentin-vidic.from.hr>
Date: Thu, 5 Dec 2019 07:41:18 +0100
Subject: [PATCH 10/26] net/tls: Fix return values to avoid ENOTSUPP

[ Upstream commit 4a5cdc604b9cf645e6fa24d8d9f055955c3c8516 ]

ENOTSUPP is not available in userspace, for example:

  setsockopt failed, 524, Unknown error 524

Signed-off-by: Valentin Vidic <vvidic@valentin-vidic.from.hr>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_device.c              | 8 ++++----
 net/tls/tls_main.c                | 4 ++--
 net/tls/tls_sw.c                  | 8 ++++----
 tools/testing/selftests/net/tls.c | 8 ++------
 4 files changed, 12 insertions(+), 16 deletions(-)

diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 6b0c9b798d9c..d12793e541a4 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -385,7 +385,7 @@ static int tls_push_data(struct sock *sk,
 
 	if (flags &
 	    ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SENDPAGE_NOTLAST))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	if (sk->sk_err)
 		return -sk->sk_err;
@@ -519,7 +519,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page,
 	lock_sock(sk);
 
 	if (flags & MSG_OOB) {
-		rc = -ENOTSUPP;
+		rc = -EOPNOTSUPP;
 		goto out;
 	}
 
@@ -961,7 +961,7 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx)
 	}
 
 	if (!(netdev->features & NETIF_F_HW_TLS_TX)) {
-		rc = -ENOTSUPP;
+		rc = -EOPNOTSUPP;
 		goto release_netdev;
 	}
 
@@ -1034,7 +1034,7 @@ int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx)
 	}
 
 	if (!(netdev->features & NETIF_F_HW_TLS_RX)) {
-		rc = -ENOTSUPP;
+		rc = -EOPNOTSUPP;
 		goto release_netdev;
 	}
 
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index c7ecd053d4e7..07476df4b13f 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -473,7 +473,7 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval,
 	/* check version */
 	if (crypto_info->version != TLS_1_2_VERSION &&
 	    crypto_info->version != TLS_1_3_VERSION) {
-		rc = -ENOTSUPP;
+		rc = -EINVAL;
 		goto err_crypto_info;
 	}
 
@@ -782,7 +782,7 @@ static int tls_init(struct sock *sk)
 	 * share the ulp context.
 	 */
 	if (sk->sk_state != TCP_ESTABLISHED)
-		return -ENOTSUPP;
+		return -ENOTCONN;
 
 	tls_build_proto(sk);
 
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 45e993c4e8f6..8e031926efb4 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -900,7 +900,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 	int ret = 0;
 
 	if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	mutex_lock(&tls_ctx->tx_lock);
 	lock_sock(sk);
@@ -1215,7 +1215,7 @@ int tls_sw_sendpage_locked(struct sock *sk, struct page *page,
 	if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
 		      MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY |
 		      MSG_NO_SHARED_FRAGS))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	return tls_sw_do_sendpage(sk, page, offset, size, flags);
 }
@@ -1228,7 +1228,7 @@ int tls_sw_sendpage(struct sock *sk, struct page *page,
 
 	if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
 		      MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	mutex_lock(&tls_ctx->tx_lock);
 	lock_sock(sk);
@@ -1928,7 +1928,7 @@ ssize_t tls_sw_splice_read(struct socket *sock,  loff_t *ppos,
 
 		/* splice does not support reading control messages */
 		if (ctx->control != TLS_RECORD_TYPE_DATA) {
-			err = -ENOTSUPP;
+			err = -EINVAL;
 			goto splice_read_end;
 		}
 
diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 46abcae47dee..13e5ef615026 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -25,10 +25,6 @@
 #define TLS_PAYLOAD_MAX_LEN 16384
 #define SOL_TLS 282
 
-#ifndef ENOTSUPP
-#define ENOTSUPP 524
-#endif
-
 FIXTURE(tls_basic)
 {
 	int fd, cfd;
@@ -1205,11 +1201,11 @@ TEST(non_established) {
 	/* TLS ULP not supported */
 	if (errno == ENOENT)
 		return;
-	EXPECT_EQ(errno, ENOTSUPP);
+	EXPECT_EQ(errno, ENOTCONN);
 
 	ret = setsockopt(sfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
 	EXPECT_EQ(ret, -1);
-	EXPECT_EQ(errno, ENOTSUPP);
+	EXPECT_EQ(errno, ENOTCONN);
 
 	ret = getsockname(sfd, &addr, &len);
 	ASSERT_EQ(ret, 0);
-- 
2.20.1


From c6f221f5e6dfd210b06873adec624a45d3dc0601 Mon Sep 17 00:00:00 2001
From: Aaron Conole <aconole@redhat.com>
Date: Tue, 3 Dec 2019 16:34:13 -0500
Subject: [PATCH 11/26] openvswitch: support asymmetric conntrack

[ Upstream commit 5d50aa83e2c8e91ced2cca77c198b468ca9210f4 ]

The openvswitch module shares a common conntrack and NAT infrastructure
exposed via netfilter.  It's possible that a packet needs both SNAT and
DNAT manipulation, due to e.g. tuple collision.  Netfilter can support
this because it runs through the NAT table twice - once on ingress and
again after egress.  The openvswitch module doesn't have such capability.

Like netfilter hook infrastructure, we should run through NAT twice to
keep the symmetry.

Fixes: 05752523e565 ("openvswitch: Interface with NAT.")
Signed-off-by: Aaron Conole <aconole@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/conntrack.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 05249eb45082..283e8f9a5fd2 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -903,6 +903,17 @@ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
 	}
 	err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, maniptype);
 
+	if (err == NF_ACCEPT &&
+	    ct->status & IPS_SRC_NAT && ct->status & IPS_DST_NAT) {
+		if (maniptype == NF_NAT_MANIP_SRC)
+			maniptype = NF_NAT_MANIP_DST;
+		else
+			maniptype = NF_NAT_MANIP_SRC;
+
+		err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range,
+					 maniptype);
+	}
+
 	/* Mark NAT done if successful and update the flow key. */
 	if (err == NF_ACCEPT)
 		ovs_nat_update_key(key, skb, maniptype);
-- 
2.20.1


From 3f91c1ecb6b2ed7f72455f245172a9446aa3fd92 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 5 Dec 2019 10:10:15 -0800
Subject: [PATCH 12/26] tcp: md5: fix potential overestimation of TCP option
 space

[ Upstream commit 9424e2e7ad93ffffa88f882c9bc5023570904b55 ]

Back in 2008, Adam Langley fixed the corner case of packets for flows
having all of the following options : MD5 TS SACK

Since MD5 needs 20 bytes, and TS needs 12 bytes, no sack block
can be cooked from the remaining 8 bytes.

tcp_established_options() correctly sets opts->num_sack_blocks
to zero, but returns 36 instead of 32.

This means TCP cooks packets with 4 extra bytes at the end
of options, containing unitialized bytes.

Fixes: 33ad798c924b ("tcp: options clean up")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 8a645f304e6c..606e17e1aca3 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -755,8 +755,9 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
 			min_t(unsigned int, eff_sacks,
 			      (remaining - TCPOLEN_SACK_BASE_ALIGNED) /
 			      TCPOLEN_SACK_PERBLOCK);
-		size += TCPOLEN_SACK_BASE_ALIGNED +
-			opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK;
+		if (likely(opts->num_sack_blocks))
+			size += TCPOLEN_SACK_BASE_ALIGNED +
+				opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK;
 	}
 
 	return size;
-- 
2.20.1


From e41c980af0ebba34f8276255ec888cb9aad68f70 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Fri, 6 Dec 2019 05:25:48 +0000
Subject: [PATCH 13/26] tipc: fix ordering of tipc module init and exit routine

[ Upstream commit 9cf1cd8ee3ee09ef2859017df2058e2f53c5347f ]

In order to set/get/dump, the tipc uses the generic netlink
infrastructure. So, when tipc module is inserted, init function
calls genl_register_family().
After genl_register_family(), set/get/dump commands are immediately
allowed and these callbacks internally use the net_generic.
net_generic is allocated by register_pernet_device() but this
is called after genl_register_family() in the __init function.
So, these callbacks would use un-initialized net_generic.

Test commands:
    #SHELL1
    while :
    do
        modprobe tipc
        modprobe -rv tipc
    done

    #SHELL2
    while :
    do
        tipc link list
    done

Splat looks like:
[   59.616322][ T2788] kasan: CONFIG_KASAN_INLINE enabled
[   59.617234][ T2788] kasan: GPF could be caused by NULL-ptr deref or user memory access
[   59.618398][ T2788] general protection fault: 0000 [#1] SMP DEBUG_PAGEALLOC KASAN PTI
[   59.619389][ T2788] CPU: 3 PID: 2788 Comm: tipc Not tainted 5.4.0+ #194
[   59.620231][ T2788] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[   59.621428][ T2788] RIP: 0010:tipc_bcast_get_broadcast_mode+0x131/0x310 [tipc]
[   59.622379][ T2788] Code: c7 c6 ef 8b 38 c0 65 ff 0d 84 83 c9 3f e8 d7 a5 f2 e3 48 8d bb 38 11 00 00 48 b8 00 00 00 00
[   59.622550][ T2780] NET: Registered protocol family 30
[   59.624627][ T2788] RSP: 0018:ffff88804b09f578 EFLAGS: 00010202
[   59.624630][ T2788] RAX: dffffc0000000000 RBX: 0000000000000011 RCX: 000000008bc66907
[   59.624631][ T2788] RDX: 0000000000000229 RSI: 000000004b3cf4cc RDI: 0000000000001149
[   59.624633][ T2788] RBP: ffff88804b09f588 R08: 0000000000000003 R09: fffffbfff4fb3df1
[   59.624635][ T2788] R10: fffffbfff50318f8 R11: ffff888066cadc18 R12: ffffffffa6cc2f40
[   59.624637][ T2788] R13: 1ffff11009613eba R14: ffff8880662e9328 R15: ffff8880662e9328
[   59.624639][ T2788] FS:  00007f57d8f7b740(0000) GS:ffff88806cc00000(0000) knlGS:0000000000000000
[   59.624645][ T2788] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   59.625875][ T2780] tipc: Started in single node mode
[   59.626128][ T2788] CR2: 00007f57d887a8c0 CR3: 000000004b140002 CR4: 00000000000606e0
[   59.633991][ T2788] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[   59.635195][ T2788] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[   59.636478][ T2788] Call Trace:
[   59.637025][ T2788]  tipc_nl_add_bc_link+0x179/0x1470 [tipc]
[   59.638219][ T2788]  ? lock_downgrade+0x6e0/0x6e0
[   59.638923][ T2788]  ? __tipc_nl_add_link+0xf90/0xf90 [tipc]
[   59.639533][ T2788]  ? tipc_nl_node_dump_link+0x318/0xa50 [tipc]
[   59.640160][ T2788]  ? mutex_lock_io_nested+0x1380/0x1380
[   59.640746][ T2788]  tipc_nl_node_dump_link+0x4fd/0xa50 [tipc]
[   59.641356][ T2788]  ? tipc_nl_node_reset_link_stats+0x340/0x340 [tipc]
[   59.642088][ T2788]  ? __skb_ext_del+0x270/0x270
[   59.642594][ T2788]  genl_lock_dumpit+0x85/0xb0
[   59.643050][ T2788]  netlink_dump+0x49c/0xed0
[   59.643529][ T2788]  ? __netlink_sendskb+0xc0/0xc0
[   59.644044][ T2788]  ? __netlink_dump_start+0x190/0x800
[   59.644617][ T2788]  ? __mutex_unlock_slowpath+0xd0/0x670
[   59.645177][ T2788]  __netlink_dump_start+0x5a0/0x800
[   59.645692][ T2788]  genl_rcv_msg+0xa75/0xe90
[   59.646144][ T2788]  ? __lock_acquire+0xdfe/0x3de0
[   59.646692][ T2788]  ? genl_family_rcv_msg_attrs_parse+0x320/0x320
[   59.647340][ T2788]  ? genl_lock_dumpit+0xb0/0xb0
[   59.647821][ T2788]  ? genl_unlock+0x20/0x20
[   59.648290][ T2788]  ? genl_parallel_done+0xe0/0xe0
[   59.648787][ T2788]  ? find_held_lock+0x39/0x1d0
[   59.649276][ T2788]  ? genl_rcv+0x15/0x40
[   59.649722][ T2788]  ? lock_contended+0xcd0/0xcd0
[   59.650296][ T2788]  netlink_rcv_skb+0x121/0x350
[   59.650828][ T2788]  ? genl_family_rcv_msg_attrs_parse+0x320/0x320
[   59.651491][ T2788]  ? netlink_ack+0x940/0x940
[   59.651953][ T2788]  ? lock_acquire+0x164/0x3b0
[   59.652449][ T2788]  genl_rcv+0x24/0x40
[   59.652841][ T2788]  netlink_unicast+0x421/0x600
[ ... ]

Fixes: 7e4369057806 ("tipc: fix a slab object leak")
Fixes: a62fbccecd62 ("tipc: make subscriber server support net namespace")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/core.c | 29 +++++++++++++++--------------
 1 file changed, 15 insertions(+), 14 deletions(-)

diff --git a/net/tipc/core.c b/net/tipc/core.c
index c8370722f0bb..10d5b888a9c1 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -122,14 +122,6 @@ static int __init tipc_init(void)
 	sysctl_tipc_rmem[1] = RCVBUF_DEF;
 	sysctl_tipc_rmem[2] = RCVBUF_MAX;
 
-	err = tipc_netlink_start();
-	if (err)
-		goto out_netlink;
-
-	err = tipc_netlink_compat_start();
-	if (err)
-		goto out_netlink_compat;
-
 	err = tipc_register_sysctl();
 	if (err)
 		goto out_sysctl;
@@ -150,8 +142,21 @@ static int __init tipc_init(void)
 	if (err)
 		goto out_bearer;
 
+	err = tipc_netlink_start();
+	if (err)
+		goto out_netlink;
+
+	err = tipc_netlink_compat_start();
+	if (err)
+		goto out_netlink_compat;
+
 	pr_info("Started in single node mode\n");
 	return 0;
+
+out_netlink_compat:
+	tipc_netlink_stop();
+out_netlink:
+	tipc_bearer_cleanup();
 out_bearer:
 	unregister_pernet_device(&tipc_topsrv_net_ops);
 out_pernet_topsrv:
@@ -161,22 +166,18 @@ static int __init tipc_init(void)
 out_pernet:
 	tipc_unregister_sysctl();
 out_sysctl:
-	tipc_netlink_compat_stop();
-out_netlink_compat:
-	tipc_netlink_stop();
-out_netlink:
 	pr_err("Unable to start in single node mode\n");
 	return err;
 }
 
 static void __exit tipc_exit(void)
 {
+	tipc_netlink_compat_stop();
+	tipc_netlink_stop();
 	tipc_bearer_cleanup();
 	unregister_pernet_device(&tipc_topsrv_net_ops);
 	tipc_socket_stop();
 	unregister_pernet_device(&tipc_net_ops);
-	tipc_netlink_stop();
-	tipc_netlink_compat_stop();
 	tipc_unregister_sysctl();
 
 	pr_info("Deactivated\n");
-- 
2.20.1


From 9453bdbc4c698d3fae3f3189ec088bb7f9f8f31e Mon Sep 17 00:00:00 2001
From: Huy Nguyen <huyn@mellanox.com>
Date: Fri, 6 Sep 2019 09:28:46 -0500
Subject: [PATCH 14/26] net/mlx5e: Query global pause state before setting
 prio2buffer

[ Upstream commit 73e6551699a32fac703ceea09214d6580edcf2d5 ]

When the user changes prio2buffer mapping while global pause is
enabled, mlx5 driver incorrectly sets all active buffers
(buffer that has at least one priority mapped) to lossy.

Solution:
If global pause is enabled, set all the active buffers to lossless
in prio2buffer command.
Also, add error message when buffer size is not enough to meet
xoff threshold.

Fixes: 0696d60853d5 ("net/mlx5e: Receive buffer configuration")
Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../mellanox/mlx5/core/en/port_buffer.c       | 27 +++++++++++++++++--
 1 file changed, 25 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
index 633b117eb13e..99c7cdd0404a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
@@ -155,8 +155,11 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer,
 		}
 
 		if (port_buffer->buffer[i].size <
-		    (xoff + max_mtu + (1 << MLX5E_BUFFER_CELL_SHIFT)))
+		    (xoff + max_mtu + (1 << MLX5E_BUFFER_CELL_SHIFT))) {
+			pr_err("buffer_size[%d]=%d is not enough for lossless buffer\n",
+			       i, port_buffer->buffer[i].size);
 			return -ENOMEM;
+		}
 
 		port_buffer->buffer[i].xoff = port_buffer->buffer[i].size - xoff;
 		port_buffer->buffer[i].xon  =
@@ -232,6 +235,26 @@ static int update_buffer_lossy(unsigned int max_mtu,
 	return 0;
 }
 
+static int fill_pfc_en(struct mlx5_core_dev *mdev, u8 *pfc_en)
+{
+	u32 g_rx_pause, g_tx_pause;
+	int err;
+
+	err = mlx5_query_port_pause(mdev, &g_rx_pause, &g_tx_pause);
+	if (err)
+		return err;
+
+	/* If global pause enabled, set all active buffers to lossless.
+	 * Otherwise, check PFC setting.
+	 */
+	if (g_rx_pause || g_tx_pause)
+		*pfc_en = 0xff;
+	else
+		err = mlx5_query_port_pfc(mdev, pfc_en, NULL);
+
+	return err;
+}
+
 #define MINIMUM_MAX_MTU 9216
 int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 				    u32 change, unsigned int mtu,
@@ -277,7 +300,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 
 	if (change & MLX5E_PORT_BUFFER_PRIO2BUFFER) {
 		update_prio2buffer = true;
-		err = mlx5_query_port_pfc(priv->mdev, &curr_pfc_en, NULL);
+		err = fill_pfc_en(priv->mdev, &curr_pfc_en);
 		if (err)
 			return err;
 
-- 
2.20.1


From 9249a1ab38f88d81e368ea6891b657971a7de0b7 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Wed, 4 Dec 2019 15:35:52 +0100
Subject: [PATCH 15/26] net: ipv6: add net argument to ip6_dst_lookup_flow

[ Upstream commit c4e85f73afb6384123e5ef1bba3315b2e3ad031e ]

This will be used in the conversion of ipv6_stub to ip6_dst_lookup_flow,
as some modules currently pass a net argument without a socket to
ip6_dst_lookup. This is equivalent to commit 343d60aada5a ("ipv6: change
ipv6_stub_impl.ipv6_dst_lookup to take net argument").

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h               | 2 +-
 net/dccp/ipv6.c                  | 6 +++---
 net/ipv6/af_inet6.c              | 2 +-
 net/ipv6/datagram.c              | 2 +-
 net/ipv6/inet6_connection_sock.c | 4 ++--
 net/ipv6/ip6_output.c            | 8 ++++----
 net/ipv6/raw.c                   | 2 +-
 net/ipv6/syncookies.c            | 2 +-
 net/ipv6/tcp_ipv6.c              | 4 ++--
 net/l2tp/l2tp_ip6.c              | 2 +-
 net/sctp/ipv6.c                  | 4 ++--
 11 files changed, 19 insertions(+), 19 deletions(-)

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 8dfc65639aa4..6a939a7cc988 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -1017,7 +1017,7 @@ static inline struct sk_buff *ip6_finish_skb(struct sock *sk)
 
 int ip6_dst_lookup(struct net *net, struct sock *sk, struct dst_entry **dst,
 		   struct flowi6 *fl6);
-struct dst_entry *ip6_dst_lookup_flow(const struct sock *sk, struct flowi6 *fl6,
+struct dst_entry *ip6_dst_lookup_flow(struct net *net, const struct sock *sk, struct flowi6 *fl6,
 				      const struct in6_addr *final_dst);
 struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
 					 const struct in6_addr *final_dst,
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 1b7381ff787b..e81869b7875f 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -210,7 +210,7 @@ static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req
 	final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final);
 	rcu_read_unlock();
 
-	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
+	dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
 		dst = NULL;
@@ -281,7 +281,7 @@ static void dccp_v6_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb)
 	security_skb_classify_flow(rxskb, flowi6_to_flowi(&fl6));
 
 	/* sk = NULL, but it is safe for now. RST socket required. */
-	dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL);
+	dst = ip6_dst_lookup_flow(sock_net(ctl_sk), ctl_sk, &fl6, NULL);
 	if (!IS_ERR(dst)) {
 		skb_dst_set(skb, dst);
 		ip6_xmit(ctl_sk, skb, &fl6, 0, NULL, 0);
@@ -911,7 +911,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk));
 	final_p = fl6_update_dst(&fl6, opt, &final);
 
-	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
+	dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
 		goto failure;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index ef37e0574f54..9e05b7276022 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -765,7 +765,7 @@ int inet6_sk_rebuild_header(struct sock *sk)
 					 &final);
 		rcu_read_unlock();
 
-		dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
+		dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p);
 		if (IS_ERR(dst)) {
 			sk->sk_route_caps = 0;
 			sk->sk_err_soft = -PTR_ERR(dst);
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 96f939248d2f..390bedde21a5 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -85,7 +85,7 @@ int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr)
 	final_p = fl6_update_dst(&fl6, opt, &final);
 	rcu_read_unlock();
 
-	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
+	dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
 		goto out;
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 4da24aa6c696..9f3ef6e02568 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -48,7 +48,7 @@ struct dst_entry *inet6_csk_route_req(const struct sock *sk,
 	fl6->flowi6_uid = sk->sk_uid;
 	security_req_classify_flow(req, flowi6_to_flowi(fl6));
 
-	dst = ip6_dst_lookup_flow(sk, fl6, final_p);
+	dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p);
 	if (IS_ERR(dst))
 		return NULL;
 
@@ -103,7 +103,7 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk,
 
 	dst = __inet6_csk_dst_check(sk, np->dst_cookie);
 	if (!dst) {
-		dst = ip6_dst_lookup_flow(sk, fl6, final_p);
+		dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p);
 
 		if (!IS_ERR(dst))
 			ip6_dst_store(sk, dst, NULL, NULL);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index e71568f730f9..43c7389922b1 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1144,19 +1144,19 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup);
  *	It returns a valid dst pointer on success, or a pointer encoded
  *	error code.
  */
-struct dst_entry *ip6_dst_lookup_flow(const struct sock *sk, struct flowi6 *fl6,
+struct dst_entry *ip6_dst_lookup_flow(struct net *net, const struct sock *sk, struct flowi6 *fl6,
 				      const struct in6_addr *final_dst)
 {
 	struct dst_entry *dst = NULL;
 	int err;
 
-	err = ip6_dst_lookup_tail(sock_net(sk), sk, &dst, fl6);
+	err = ip6_dst_lookup_tail(net, sk, &dst, fl6);
 	if (err)
 		return ERR_PTR(err);
 	if (final_dst)
 		fl6->daddr = *final_dst;
 
-	return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
+	return xfrm_lookup_route(net, dst, flowi6_to_flowi(fl6), sk, 0);
 }
 EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow);
 
@@ -1188,7 +1188,7 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
 	if (dst)
 		return dst;
 
-	dst = ip6_dst_lookup_flow(sk, fl6, final_dst);
+	dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_dst);
 	if (connected && !IS_ERR(dst))
 		ip6_sk_dst_store_flow(sk, dst_clone(dst), fl6);
 
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 8a6131991e38..6889716bf989 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -923,7 +923,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
 
-	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
+	dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
 		goto out;
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 16632e02e9b0..30915f6f31e3 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -235,7 +235,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 		fl6.flowi6_uid = sk->sk_uid;
 		security_req_classify_flow(req, flowi6_to_flowi(&fl6));
 
-		dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
+		dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p);
 		if (IS_ERR(dst))
 			goto out_free;
 	}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 5da069e91cac..84497e0342bc 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -275,7 +275,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
-	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
+	dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
 		goto failure;
@@ -904,7 +904,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
 	 * Underlying function will use this to retrieve the network
 	 * namespace
 	 */
-	dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL);
+	dst = ip6_dst_lookup_flow(sock_net(ctl_sk), ctl_sk, &fl6, NULL);
 	if (!IS_ERR(dst)) {
 		skb_dst_set(buff, dst);
 		ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL, tclass);
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 687e23a8b326..ad371606cba5 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -615,7 +615,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
 
-	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
+	dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
 		goto out;
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index e5f2fc726a98..e9c2b4dfb542 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -275,7 +275,7 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 	final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
 	rcu_read_unlock();
 
-	dst = ip6_dst_lookup_flow(sk, fl6, final_p);
+	dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p);
 	if (!asoc || saddr)
 		goto out;
 
@@ -328,7 +328,7 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 		fl6->saddr = laddr->a.v6.sin6_addr;
 		fl6->fl6_sport = laddr->a.v6.sin6_port;
 		final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
-		bdst = ip6_dst_lookup_flow(sk, fl6, final_p);
+		bdst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p);
 
 		if (IS_ERR(bdst))
 			continue;
-- 
2.20.1


From fef3ed096184498ffb8d2e7338f466f79caba4e0 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Wed, 4 Dec 2019 15:35:53 +0100
Subject: [PATCH 16/26] net: ipv6_stub: use ip6_dst_lookup_flow instead of
 ip6_dst_lookup

[ Upstream commit 6c8991f41546c3c472503dff1ea9daaddf9331c2 ]

ipv6_stub uses the ip6_dst_lookup function to allow other modules to
perform IPv6 lookups. However, this function skips the XFRM layer
entirely.

All users of ipv6_stub->ip6_dst_lookup use ip_route_output_flow (via the
ip_route_output_key and ip_route_output helpers) for their IPv4 lookups,
which calls xfrm_lookup_route(). This patch fixes this inconsistent
behavior by switching the stub to ip6_dst_lookup_flow, which also calls
xfrm_lookup_route().

This requires some changes in all the callers, as these two functions
take different arguments and have different return types.

Fixes: 5f81bd2e5d80 ("ipv6: export a stub for IPv6 symbols used by vxlan")
Reported-by: Xiumei Mu <xmu@redhat.com>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/core/addr.c                      |  7 +++----
 drivers/infiniband/sw/rxe/rxe_net.c                 |  8 +++++---
 drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c |  8 ++++----
 drivers/net/geneve.c                                |  4 +++-
 drivers/net/vxlan.c                                 |  8 +++-----
 include/net/ipv6_stubs.h                            |  6 ++++--
 net/core/lwt_bpf.c                                  |  4 +---
 net/ipv6/addrconf_core.c                            | 11 ++++++-----
 net/ipv6/af_inet6.c                                 |  2 +-
 net/mpls/af_mpls.c                                  |  7 +++----
 net/tipc/udp_media.c                                |  9 ++++++---
 11 files changed, 39 insertions(+), 35 deletions(-)

diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index bf539c34ccd3..fca5025d5a1a 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -421,16 +421,15 @@ static int addr6_resolve(struct sockaddr *src_sock,
 				(const struct sockaddr_in6 *)dst_sock;
 	struct flowi6 fl6;
 	struct dst_entry *dst;
-	int ret;
 
 	memset(&fl6, 0, sizeof fl6);
 	fl6.daddr = dst_in->sin6_addr;
 	fl6.saddr = src_in->sin6_addr;
 	fl6.flowi6_oif = addr->bound_dev_if;
 
-	ret = ipv6_stub->ipv6_dst_lookup(addr->net, NULL, &dst, &fl6);
-	if (ret < 0)
-		return ret;
+	dst = ipv6_stub->ipv6_dst_lookup_flow(addr->net, NULL, &fl6, NULL);
+	if (IS_ERR(dst))
+		return PTR_ERR(dst);
 
 	if (ipv6_addr_any(&src_in->sin6_addr))
 		src_in->sin6_addr = fl6.saddr;
diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c
index 5a3474f9351b..312c2fc961c0 100644
--- a/drivers/infiniband/sw/rxe/rxe_net.c
+++ b/drivers/infiniband/sw/rxe/rxe_net.c
@@ -117,10 +117,12 @@ static struct dst_entry *rxe_find_route6(struct net_device *ndev,
 	memcpy(&fl6.daddr, daddr, sizeof(*daddr));
 	fl6.flowi6_proto = IPPROTO_UDP;
 
-	if (unlikely(ipv6_stub->ipv6_dst_lookup(sock_net(recv_sockets.sk6->sk),
-						recv_sockets.sk6->sk, &ndst, &fl6))) {
+	ndst = ipv6_stub->ipv6_dst_lookup_flow(sock_net(recv_sockets.sk6->sk),
+					       recv_sockets.sk6->sk, &fl6,
+					       NULL);
+	if (unlikely(IS_ERR(ndst))) {
 		pr_err_ratelimited("no route to %pI6\n", daddr);
-		goto put;
+		return NULL;
 	}
 
 	if (unlikely(ndst->error)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index d41c520ce0a8..0d520c93c9ba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -137,10 +137,10 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
 #if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6)
 	int ret;
 
-	ret = ipv6_stub->ipv6_dst_lookup(dev_net(mirred_dev), NULL, &dst,
-					 fl6);
-	if (ret < 0)
-		return ret;
+	dst = ipv6_stub->ipv6_dst_lookup_flow(dev_net(mirred_dev), NULL, fl6,
+					      NULL);
+	if (IS_ERR(dst))
+		return PTR_ERR(dst);
 
 	if (!(*out_ttl))
 		*out_ttl = ip6_dst_hoplimit(dst);
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index cb2ea8facd8d..ac1470a6c64f 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -853,7 +853,9 @@ static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb,
 		if (dst)
 			return dst;
 	}
-	if (ipv6_stub->ipv6_dst_lookup(geneve->net, gs6->sock->sk, &dst, fl6)) {
+	dst = ipv6_stub->ipv6_dst_lookup_flow(geneve->net, gs6->sock->sk, fl6,
+					      NULL);
+	if (IS_ERR(dst)) {
 		netdev_dbg(dev, "no route to %pI6\n", &fl6->daddr);
 		return ERR_PTR(-ENETUNREACH);
 	}
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index e07872869266..838d0390b2f4 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2276,7 +2276,6 @@ static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan,
 	bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
 	struct dst_entry *ndst;
 	struct flowi6 fl6;
-	int err;
 
 	if (!sock6)
 		return ERR_PTR(-EIO);
@@ -2299,10 +2298,9 @@ static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan,
 	fl6.fl6_dport = dport;
 	fl6.fl6_sport = sport;
 
-	err = ipv6_stub->ipv6_dst_lookup(vxlan->net,
-					 sock6->sock->sk,
-					 &ndst, &fl6);
-	if (unlikely(err < 0)) {
+	ndst = ipv6_stub->ipv6_dst_lookup_flow(vxlan->net, sock6->sock->sk,
+					       &fl6, NULL);
+	if (unlikely(IS_ERR(ndst))) {
 		netdev_dbg(dev, "no route to %pI6\n", daddr);
 		return ERR_PTR(-ENETUNREACH);
 	}
diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h
index 5c93e942c50b..3e7d2c0e79ca 100644
--- a/include/net/ipv6_stubs.h
+++ b/include/net/ipv6_stubs.h
@@ -24,8 +24,10 @@ struct ipv6_stub {
 				 const struct in6_addr *addr);
 	int (*ipv6_sock_mc_drop)(struct sock *sk, int ifindex,
 				 const struct in6_addr *addr);
-	int (*ipv6_dst_lookup)(struct net *net, struct sock *sk,
-			       struct dst_entry **dst, struct flowi6 *fl6);
+	struct dst_entry *(*ipv6_dst_lookup_flow)(struct net *net,
+						  const struct sock *sk,
+						  struct flowi6 *fl6,
+						  const struct in6_addr *final_dst);
 	int (*ipv6_route_input)(struct sk_buff *skb);
 
 	struct fib6_table *(*fib6_get_table)(struct net *net, u32 id);
diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index 74cfb8b5ab33..99a6de52b21d 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -230,9 +230,7 @@ static int bpf_lwt_xmit_reroute(struct sk_buff *skb)
 		fl6.daddr = iph6->daddr;
 		fl6.saddr = iph6->saddr;
 
-		err = ipv6_stub->ipv6_dst_lookup(net, skb->sk, &dst, &fl6);
-		if (unlikely(err))
-			goto err;
+		dst = ipv6_stub->ipv6_dst_lookup_flow(net, skb->sk, &fl6, NULL);
 		if (IS_ERR(dst)) {
 			err = PTR_ERR(dst);
 			goto err;
diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index 783f3c1466da..748a4253650f 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -128,11 +128,12 @@ int inet6addr_validator_notifier_call_chain(unsigned long val, void *v)
 }
 EXPORT_SYMBOL(inet6addr_validator_notifier_call_chain);
 
-static int eafnosupport_ipv6_dst_lookup(struct net *net, struct sock *u1,
-					struct dst_entry **u2,
-					struct flowi6 *u3)
+static struct dst_entry *eafnosupport_ipv6_dst_lookup_flow(struct net *net,
+							   const struct sock *sk,
+							   struct flowi6 *fl6,
+							   const struct in6_addr *final_dst)
 {
-	return -EAFNOSUPPORT;
+	return ERR_PTR(-EAFNOSUPPORT);
 }
 
 static int eafnosupport_ipv6_route_input(struct sk_buff *skb)
@@ -189,7 +190,7 @@ static int eafnosupport_ip6_del_rt(struct net *net, struct fib6_info *rt)
 }
 
 const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) {
-	.ipv6_dst_lookup   = eafnosupport_ipv6_dst_lookup,
+	.ipv6_dst_lookup_flow = eafnosupport_ipv6_dst_lookup_flow,
 	.ipv6_route_input  = eafnosupport_ipv6_route_input,
 	.fib6_get_table    = eafnosupport_fib6_get_table,
 	.fib6_table_lookup = eafnosupport_fib6_table_lookup,
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 9e05b7276022..14ac1d911287 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -946,7 +946,7 @@ static int ipv6_route_input(struct sk_buff *skb)
 static const struct ipv6_stub ipv6_stub_impl = {
 	.ipv6_sock_mc_join = ipv6_sock_mc_join,
 	.ipv6_sock_mc_drop = ipv6_sock_mc_drop,
-	.ipv6_dst_lookup   = ip6_dst_lookup,
+	.ipv6_dst_lookup_flow = ip6_dst_lookup_flow,
 	.ipv6_route_input  = ipv6_route_input,
 	.fib6_get_table	   = fib6_get_table,
 	.fib6_table_lookup = fib6_table_lookup,
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index c312741df2ce..4701edffb1f7 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -617,16 +617,15 @@ static struct net_device *inet6_fib_lookup_dev(struct net *net,
 	struct net_device *dev;
 	struct dst_entry *dst;
 	struct flowi6 fl6;
-	int err;
 
 	if (!ipv6_stub)
 		return ERR_PTR(-EAFNOSUPPORT);
 
 	memset(&fl6, 0, sizeof(fl6));
 	memcpy(&fl6.daddr, addr, sizeof(struct in6_addr));
-	err = ipv6_stub->ipv6_dst_lookup(net, NULL, &dst, &fl6);
-	if (err)
-		return ERR_PTR(err);
+	dst = ipv6_stub->ipv6_dst_lookup_flow(net, NULL, &fl6, NULL);
+	if (IS_ERR(dst))
+		return ERR_CAST(dst);
 
 	dev = dst->dev;
 	dev_hold(dev);
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index 287df68721df..186c78431217 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -195,10 +195,13 @@ static int tipc_udp_xmit(struct net *net, struct sk_buff *skb,
 				.saddr = src->ipv6,
 				.flowi6_proto = IPPROTO_UDP
 			};
-			err = ipv6_stub->ipv6_dst_lookup(net, ub->ubsock->sk,
-							 &ndst, &fl6);
-			if (err)
+			ndst = ipv6_stub->ipv6_dst_lookup_flow(net,
+							       ub->ubsock->sk,
+							       &fl6, NULL);
+			if (IS_ERR(ndst)) {
+				err = PTR_ERR(ndst);
 				goto tx_error;
+			}
 			dst_cache_set_ip6(cache, ndst, &fl6.saddr);
 		}
 		ttl = ip6_dst_hoplimit(ndst);
-- 
2.20.1


From f456953fc1580fed4d20f3c822b6367473925109 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Fri, 6 Dec 2019 12:38:36 +0100
Subject: [PATCH 17/26] tcp: fix rejected syncookies due to stale timestamps

[ Upstream commit 04d26e7b159a396372646a480f4caa166d1b6720 ]

If no synflood happens for a long enough period of time, then the
synflood timestamp isn't refreshed and jiffies can advance so much
that time_after32() can't accurately compare them any more.

Therefore, we can end up in a situation where time_after32(now,
last_overflow + HZ) returns false, just because these two values are
too far apart. In that case, the synflood timestamp isn't updated as
it should be, which can trick tcp_synq_no_recent_overflow() into
rejecting valid syncookies.

For example, let's consider the following scenario on a system
with HZ=1000:

  * The synflood timestamp is 0, either because that's the timestamp
    of the last synflood or, more commonly, because we're working with
    a freshly created socket.

  * We receive a new SYN, which triggers synflood protection. Let's say
    that this happens when jiffies == 2147484649 (that is,
    'synflood timestamp' + HZ + 2^31 + 1).

  * Then tcp_synq_overflow() doesn't update the synflood timestamp,
    because time_after32(2147484649, 1000) returns false.
    With:
      - 2147484649: the value of jiffies, aka. 'now'.
      - 1000: the value of 'last_overflow' + HZ.

  * A bit later, we receive the ACK completing the 3WHS. But
    cookie_v[46]_check() rejects it because tcp_synq_no_recent_overflow()
    says that we're not under synflood. That's because
    time_after32(2147484649, 120000) returns false.
    With:
      - 2147484649: the value of jiffies, aka. 'now'.
      - 120000: the value of 'last_overflow' + TCP_SYNCOOKIE_VALID.

    Of course, in reality jiffies would have increased a bit, but this
    condition will last for the next 119 seconds, which is far enough
    to accommodate for jiffie's growth.

Fix this by updating the overflow timestamp whenever jiffies isn't
within the [last_overflow, last_overflow + HZ] range. That shouldn't
have any performance impact since the update still happens at most once
per second.

Now we're guaranteed to have fresh timestamps while under synflood, so
tcp_synq_no_recent_overflow() can safely use it with time_after32() in
such situations.

Stale timestamps can still make tcp_synq_no_recent_overflow() return
the wrong verdict when not under synflood. This will be handled in the
next patch.

For 64 bits architectures, the problem was introduced with the
conversion of ->tw_ts_recent_stamp to 32 bits integer by commit
cca9bab1b72c ("tcp: use monotonic timestamps for PAWS").
The problem has always been there on 32 bits architectures.

Fixes: cca9bab1b72c ("tcp: use monotonic timestamps for PAWS")
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/time.h | 13 +++++++++++++
 include/net/tcp.h    |  5 +++--
 2 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/include/linux/time.h b/include/linux/time.h
index 27d83fd2ae61..5f3e49978837 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -96,4 +96,17 @@ static inline bool itimerspec64_valid(const struct itimerspec64 *its)
  */
 #define time_after32(a, b)	((s32)((u32)(b) - (u32)(a)) < 0)
 #define time_before32(b, a)	time_after32(a, b)
+
+/**
+ * time_between32 - check if a 32-bit timestamp is within a given time range
+ * @t:	the time which may be within [l,h]
+ * @l:	the lower bound of the range
+ * @h:	the higher bound of the range
+ *
+ * time_before32(t, l, h) returns true if @l <= @t <= @h. All operands are
+ * treated as 32-bit integers.
+ *
+ * Equivalent to !(time_before32(@t, @l) || time_after32(@t, @h)).
+ */
+#define time_between32(t, l, h) ((u32)(h) - (u32)(l) >= (u32)(t) - (u32)(l))
 #endif
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 81e8ade1e6e4..4fb34c42bb66 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -484,14 +484,15 @@ static inline void tcp_synq_overflow(const struct sock *sk)
 		reuse = rcu_dereference(sk->sk_reuseport_cb);
 		if (likely(reuse)) {
 			last_overflow = READ_ONCE(reuse->synq_overflow_ts);
-			if (time_after32(now, last_overflow + HZ))
+			if (!time_between32(now, last_overflow,
+					    last_overflow + HZ))
 				WRITE_ONCE(reuse->synq_overflow_ts, now);
 			return;
 		}
 	}
 
 	last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
-	if (time_after32(now, last_overflow + HZ))
+	if (!time_between32(now, last_overflow, last_overflow + HZ))
 		tcp_sk(sk)->rx_opt.ts_recent_stamp = now;
 }
 
-- 
2.20.1


From 9f78d50b31a3496119f513a3cdeb2101ff1a4a6d Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Fri, 6 Dec 2019 12:38:43 +0100
Subject: [PATCH 18/26] tcp: tighten acceptance of ACKs not matching a child
 socket

[ Upstream commit cb44a08f8647fd2e8db5cc9ac27cd8355fa392d8 ]

When no synflood occurs, the synflood timestamp isn't updated.
Therefore it can be so old that time_after32() can consider it to be
in the future.

That's a problem for tcp_synq_no_recent_overflow() as it may report
that a recent overflow occurred while, in fact, it's just that jiffies
has grown past 'last_overflow' + TCP_SYNCOOKIE_VALID + 2^31.

Spurious detection of recent overflows lead to extra syncookie
verification in cookie_v[46]_check(). At that point, the verification
should fail and the packet dropped. But we should have dropped the
packet earlier as we didn't even send a syncookie.

Let's refine tcp_synq_no_recent_overflow() to report a recent overflow
only if jiffies is within the
[last_overflow, last_overflow + TCP_SYNCOOKIE_VALID] interval. This
way, no spurious recent overflow is reported when jiffies wraps and
'last_overflow' becomes in the future from the point of view of
time_after32().

However, if jiffies wraps and enters the
[last_overflow, last_overflow + TCP_SYNCOOKIE_VALID] interval (with
'last_overflow' being a stale synflood timestamp), then
tcp_synq_no_recent_overflow() still erroneously reports an
overflow. In such cases, we have to rely on syncookie verification
to drop the packet. We unfortunately have no way to differentiate
between a fresh and a stale syncookie timestamp.

In practice, using last_overflow as lower bound is problematic.
If the synflood timestamp is concurrently updated between the time
we read jiffies and the moment we store the timestamp in
'last_overflow', then 'now' becomes smaller than 'last_overflow' and
tcp_synq_no_recent_overflow() returns true, potentially dropping a
valid syncookie.

Reading jiffies after loading the timestamp could fix the problem,
but that'd require a memory barrier. Let's just accommodate for
potential timestamp growth instead and extend the interval using
'last_overflow - HZ' as lower bound.

Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 4fb34c42bb66..c1fad1b4c91b 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -508,13 +508,23 @@ static inline bool tcp_synq_no_recent_overflow(const struct sock *sk)
 		reuse = rcu_dereference(sk->sk_reuseport_cb);
 		if (likely(reuse)) {
 			last_overflow = READ_ONCE(reuse->synq_overflow_ts);
-			return time_after32(now, last_overflow +
-					    TCP_SYNCOOKIE_VALID);
+			return !time_between32(now, last_overflow - HZ,
+					       last_overflow +
+					       TCP_SYNCOOKIE_VALID);
 		}
 	}
 
 	last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
-	return time_after32(now, last_overflow + TCP_SYNCOOKIE_VALID);
+
+	/* If last_overflow <= jiffies <= last_overflow + TCP_SYNCOOKIE_VALID,
+	 * then we're under synflood. However, we have to use
+	 * 'last_overflow - HZ' as lower bound. That's because a concurrent
+	 * tcp_synq_overflow() could update .ts_recent_stamp after we read
+	 * jiffies but before we store .ts_recent_stamp into last_overflow,
+	 * which could lead to rejecting a valid syncookie.
+	 */
+	return !time_between32(now, last_overflow - HZ,
+			       last_overflow + TCP_SYNCOOKIE_VALID);
 }
 
 static inline u32 tcp_cookie_time(void)
-- 
2.20.1


From cc85a9586a820c8e1033b909e7f0022f9433f39f Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Fri, 6 Dec 2019 12:38:49 +0100
Subject: [PATCH 19/26] tcp: Protect accesses to .ts_recent_stamp with
 {READ,WRITE}_ONCE()

[ Upstream commit 721c8dafad26ccfa90ff659ee19755e3377b829d ]

Syncookies borrow the ->rx_opt.ts_recent_stamp field to store the
timestamp of the last synflood. Protect them with READ_ONCE() and
WRITE_ONCE() since reads and writes aren't serialised.

Use of .rx_opt.ts_recent_stamp for storing the synflood timestamp was
introduced by a0f82f64e269 ("syncookies: remove last_synq_overflow from
struct tcp_sock"). But unprotected accesses were already there when
timestamp was stored in .last_synq_overflow.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index c1fad1b4c91b..09910641fcc3 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -491,9 +491,9 @@ static inline void tcp_synq_overflow(const struct sock *sk)
 		}
 	}
 
-	last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
+	last_overflow = READ_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp);
 	if (!time_between32(now, last_overflow, last_overflow + HZ))
-		tcp_sk(sk)->rx_opt.ts_recent_stamp = now;
+		WRITE_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp, now);
 }
 
 /* syncookies: no recent synqueue overflow on this listening socket? */
@@ -514,7 +514,7 @@ static inline bool tcp_synq_no_recent_overflow(const struct sock *sk)
 		}
 	}
 
-	last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
+	last_overflow = READ_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp);
 
 	/* If last_overflow <= jiffies <= last_overflow + TCP_SYNCOOKIE_VALID,
 	 * then we're under synflood. However, we have to use
-- 
2.20.1


From 0df468dc55aa2cbd9f3ce8282fe9ac531688d325 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 5 Dec 2019 19:39:02 -0800
Subject: [PATCH 20/26] gre: refetch erspan header from skb->data after
 pskb_may_pull()

[ Upstream commit 0e4940928c26527ce8f97237fef4c8a91cd34207 ]

After pskb_may_pull() we should always refetch the header
pointers from the skb->data in case it got reallocated.

In gre_parse_header(), the erspan header is still fetched
from the 'options' pointer which is fetched before
pskb_may_pull().

Found this during code review of a KMSAN bug report.

Fixes: cb73ee40b1b3 ("net: ip_gre: use erspan key field for tunnel lookup")
Cc: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Acked-by: William Tu <u9012063@gmail.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/gre_demux.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c
index 44bfeecac33e..5fd6e8ed02b5 100644
--- a/net/ipv4/gre_demux.c
+++ b/net/ipv4/gre_demux.c
@@ -127,7 +127,7 @@ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 		if (!pskb_may_pull(skb, nhs + hdr_len + sizeof(*ershdr)))
 			return -EINVAL;
 
-		ershdr = (struct erspan_base_hdr *)options;
+		ershdr = (struct erspan_base_hdr *)(skb->data + nhs + hdr_len);
 		tpi->key = cpu_to_be32(get_session_id(ershdr));
 	}
 
-- 
2.20.1


From e2afdefb4f994ecdbb5d3fd165e9286890fd523c Mon Sep 17 00:00:00 2001
From: Martin Varghese <martin.varghese@nokia.com>
Date: Mon, 2 Dec 2019 10:49:51 +0530
Subject: [PATCH 21/26] Fixed updating of ethertype in function skb_mpls_pop

[ Upstream commit 040b5cfbcefa263ccf2c118c4938308606bb7ed8 ]

The skb_mpls_pop was not updating ethertype of an ethernet packet if the
packet was originally received from a non ARPHRD_ETHER device.

In the below OVS data path flow, since the device corresponding to port 7
is an l3 device (ARPHRD_NONE) the skb_mpls_pop function does not update
the ethertype of the packet even though the previous push_eth action had
added an ethernet header to the packet.

recirc_id(0),in_port(7),eth_type(0x8847),
mpls(label=12/0xfffff,tc=0/0,ttl=0/0x0,bos=1/1),
actions:push_eth(src=00:00:00:00:00:00,dst=00:00:00:00:00:00),
pop_mpls(eth_type=0x800),4

Fixes: ed246cee09b9 ("net: core: move pop MPLS functionality from OvS to core helper")
Signed-off-by: Martin Varghese <martin.varghese@nokia.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h    | 3 ++-
 net/core/skbuff.c         | 6 ++++--
 net/openvswitch/actions.c | 3 ++-
 net/sched/act_mpls.c      | 4 +++-
 4 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 7647beaac2d2..38ab5ef0a29b 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3483,7 +3483,8 @@ int skb_vlan_pop(struct sk_buff *skb);
 int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci);
 int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto,
 		  int mac_len);
-int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len);
+int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len,
+		 bool ethernet);
 int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse);
 int skb_mpls_dec_ttl(struct sk_buff *skb);
 struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy,
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index d4a47c44daf0..ebfa55d934d1 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5517,12 +5517,14 @@ EXPORT_SYMBOL_GPL(skb_mpls_push);
  * @skb: buffer
  * @next_proto: ethertype of header after popped MPLS header
  * @mac_len: length of the MAC header
+ * @ethernet: flag to indicate if ethernet header is present in packet
  *
  * Expects skb->data at mac header.
  *
  * Returns 0 on success, -errno otherwise.
  */
-int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len)
+int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len,
+		 bool ethernet)
 {
 	int err;
 
@@ -5541,7 +5543,7 @@ int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len)
 	skb_reset_mac_header(skb);
 	skb_set_network_header(skb, mac_len);
 
-	if (skb->dev && skb->dev->type == ARPHRD_ETHER) {
+	if (ethernet) {
 		struct ethhdr *hdr;
 
 		/* use mpls_hdr() to get ethertype to account for VLANs. */
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 1c77f520f474..fd54a2eb833b 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -179,7 +179,8 @@ static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key,
 {
 	int err;
 
-	err = skb_mpls_pop(skb, ethertype, skb->mac_len);
+	err = skb_mpls_pop(skb, ethertype, skb->mac_len,
+			   ovs_key_mac_proto(key) == MAC_PROTO_ETHERNET);
 	if (err)
 		return err;
 
diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c
index 4cf6c553bb0b..bf74a6c4990c 100644
--- a/net/sched/act_mpls.c
+++ b/net/sched/act_mpls.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 /* Copyright (C) 2019 Netronome Systems, Inc. */
 
+#include <linux/if_arp.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -76,7 +77,8 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a,
 
 	switch (p->tcfm_action) {
 	case TCA_MPLS_ACT_POP:
-		if (skb_mpls_pop(skb, p->tcfm_proto, mac_len))
+		if (skb_mpls_pop(skb, p->tcfm_proto, mac_len,
+				 skb->dev && skb->dev->type == ARPHRD_ETHER))
 			goto drop;
 		break;
 	case TCA_MPLS_ACT_PUSH:
-- 
2.20.1


From 4f965107d20b7be1dc19be81e070c300f40ca924 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Thu, 5 Dec 2019 07:23:39 +0000
Subject: [PATCH 22/26] hsr: fix a NULL pointer dereference in hsr_dev_xmit()

[ Upstream commit df95467b6d2bfce49667ee4b71c67249b01957f7 ]

hsr_dev_xmit() calls hsr_port_get_hsr() to find master node and that would
return NULL if master node is not existing in the list.
But hsr_dev_xmit() doesn't check return pointer so a NULL dereference
could occur.

Test commands:
    ip netns add nst
    ip link add veth0 type veth peer name veth1
    ip link add veth2 type veth peer name veth3
    ip link set veth1 netns nst
    ip link set veth3 netns nst
    ip link set veth0 up
    ip link set veth2 up
    ip link add hsr0 type hsr slave1 veth0 slave2 veth2
    ip a a 192.168.100.1/24 dev hsr0
    ip link set hsr0 up
    ip netns exec nst ip link set veth1 up
    ip netns exec nst ip link set veth3 up
    ip netns exec nst ip link add hsr1 type hsr slave1 veth1 slave2 veth3
    ip netns exec nst ip a a 192.168.100.2/24 dev hsr1
    ip netns exec nst ip link set hsr1 up
    hping3 192.168.100.2 -2 --flood &
    modprobe -rv hsr

Splat looks like:
[  217.351122][ T1635] kasan: CONFIG_KASAN_INLINE enabled
[  217.352969][ T1635] kasan: GPF could be caused by NULL-ptr deref or user memory access
[  217.354297][ T1635] general protection fault: 0000 [#1] SMP DEBUG_PAGEALLOC KASAN PTI
[  217.355507][ T1635] CPU: 1 PID: 1635 Comm: hping3 Not tainted 5.4.0+ #192
[  217.356472][ T1635] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[  217.357804][ T1635] RIP: 0010:hsr_dev_xmit+0x34/0x90 [hsr]
[  217.373010][ T1635] Code: 48 8d be 00 0c 00 00 be 04 00 00 00 48 83 ec 08 e8 21 be ff ff 48 8d 78 10 48 ba 00 b
[  217.376919][ T1635] RSP: 0018:ffff8880cd8af058 EFLAGS: 00010202
[  217.377571][ T1635] RAX: 0000000000000000 RBX: ffff8880acde6840 RCX: 0000000000000002
[  217.379465][ T1635] RDX: dffffc0000000000 RSI: 0000000000000004 RDI: 0000000000000010
[  217.380274][ T1635] RBP: ffff8880acde6840 R08: ffffed101b440d5d R09: 0000000000000001
[  217.381078][ T1635] R10: 0000000000000001 R11: ffffed101b440d5c R12: ffff8880bffcc000
[  217.382023][ T1635] R13: ffff8880bffcc088 R14: 0000000000000000 R15: ffff8880ca675c00
[  217.383094][ T1635] FS:  00007f060d9d1740(0000) GS:ffff8880da000000(0000) knlGS:0000000000000000
[  217.384289][ T1635] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  217.385009][ T1635] CR2: 00007faf15381dd0 CR3: 00000000d523c001 CR4: 00000000000606e0
[  217.385940][ T1635] Call Trace:
[  217.386544][ T1635]  dev_hard_start_xmit+0x160/0x740
[  217.387114][ T1635]  __dev_queue_xmit+0x1961/0x2e10
[  217.388118][ T1635]  ? check_object+0xaf/0x260
[  217.391466][ T1635]  ? __alloc_skb+0xb9/0x500
[  217.392017][ T1635]  ? init_object+0x6b/0x80
[  217.392629][ T1635]  ? netdev_core_pick_tx+0x2e0/0x2e0
[  217.393175][ T1635]  ? __alloc_skb+0xb9/0x500
[  217.393727][ T1635]  ? rcu_read_lock_sched_held+0x90/0xc0
[  217.394331][ T1635]  ? rcu_read_lock_bh_held+0xa0/0xa0
[  217.395013][ T1635]  ? kasan_unpoison_shadow+0x30/0x40
[  217.395668][ T1635]  ? __kasan_kmalloc.constprop.4+0xa0/0xd0
[  217.396280][ T1635]  ? __kmalloc_node_track_caller+0x3a8/0x3f0
[  217.399007][ T1635]  ? __kasan_kmalloc.constprop.4+0xa0/0xd0
[  217.400093][ T1635]  ? __kmalloc_reserve.isra.46+0x2e/0xb0
[  217.401118][ T1635]  ? memset+0x1f/0x40
[  217.402529][ T1635]  ? __alloc_skb+0x317/0x500
[  217.404915][ T1635]  ? arp_xmit+0xca/0x2c0
[ ... ]

Fixes: 311633b60406 ("hsr: switch ->dellink() to ->ndo_uninit()")
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/hsr/hsr_device.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index f509b495451a..b01e1bae4ddc 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -227,8 +227,13 @@ static int hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct hsr_port *master;
 
 	master = hsr_port_get_hsr(hsr, HSR_PT_MASTER);
-	skb->dev = master->dev;
-	hsr_forward_skb(skb, master);
+	if (master) {
+		skb->dev = master->dev;
+		hsr_forward_skb(skb, master);
+	} else {
+		atomic_long_inc(&dev->tx_dropped);
+		dev_kfree_skb_any(skb);
+	}
 	return NETDEV_TX_OK;
 }
 
-- 
2.20.1


From 6e8d9ae41057ca03ece5f0844fef9d3650969e56 Mon Sep 17 00:00:00 2001
From: Martin Varghese <martin.varghese@nokia.com>
Date: Thu, 5 Dec 2019 05:57:22 +0530
Subject: [PATCH 23/26] net: Fixed updating of ethertype in skb_mpls_push()

[ Upstream commit d04ac224b1688f005a84f764cfe29844f8e9da08 ]

The skb_mpls_push was not updating ethertype of an ethernet packet if
the packet was originally received from a non ARPHRD_ETHER device.

In the below OVS data path flow, since the device corresponding to
port 7 is an l3 device (ARPHRD_NONE) the skb_mpls_push function does
not update the ethertype of the packet even though the previous
push_eth action had added an ethernet header to the packet.

recirc_id(0),in_port(7),eth_type(0x0800),ipv4(tos=0/0xfc,ttl=64,frag=no),
actions:push_eth(src=00:00:00:00:00:00,dst=00:00:00:00:00:00),
push_mpls(label=13,tc=0,ttl=64,bos=1,eth_type=0x8847),4

Fixes: 8822e270d697 ("net: core: move push MPLS functionality from OvS to core helper")
Signed-off-by: Martin Varghese <martin.varghese@nokia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h    | 2 +-
 net/core/skbuff.c         | 4 ++--
 net/openvswitch/actions.c | 3 ++-
 net/sched/act_mpls.c      | 3 ++-
 4 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 38ab5ef0a29b..451b4ef1c0b7 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3482,7 +3482,7 @@ int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci);
 int skb_vlan_pop(struct sk_buff *skb);
 int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci);
 int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto,
-		  int mac_len);
+		  int mac_len, bool ethernet);
 int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len,
 		 bool ethernet);
 int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index ebfa55d934d1..7b62f1bd04a0 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5472,7 +5472,7 @@ static void skb_mod_eth_type(struct sk_buff *skb, struct ethhdr *hdr,
  * Returns 0 on success, -errno otherwise.
  */
 int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto,
-		  int mac_len)
+		  int mac_len, bool ethernet)
 {
 	struct mpls_shim_hdr *lse;
 	int err;
@@ -5503,7 +5503,7 @@ int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto,
 	lse->label_stack_entry = mpls_lse;
 	skb_postpush_rcsum(skb, lse, MPLS_HLEN);
 
-	if (skb->dev && skb->dev->type == ARPHRD_ETHER)
+	if (ethernet)
 		skb_mod_eth_type(skb, eth_hdr(skb), mpls_proto);
 	skb->protocol = mpls_proto;
 
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index fd54a2eb833b..99352f09deaa 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -166,7 +166,8 @@ static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key,
 	int err;
 
 	err = skb_mpls_push(skb, mpls->mpls_lse, mpls->mpls_ethertype,
-			    skb->mac_len);
+			    skb->mac_len,
+			    ovs_key_mac_proto(key) == MAC_PROTO_ETHERNET);
 	if (err)
 		return err;
 
diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c
index bf74a6c4990c..db570d2bd0e0 100644
--- a/net/sched/act_mpls.c
+++ b/net/sched/act_mpls.c
@@ -83,7 +83,8 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a,
 		break;
 	case TCA_MPLS_ACT_PUSH:
 		new_lse = tcf_mpls_get_lse(NULL, p, !eth_p_mpls(skb->protocol));
-		if (skb_mpls_push(skb, new_lse, p->tcfm_proto, mac_len))
+		if (skb_mpls_push(skb, new_lse, p->tcfm_proto, mac_len,
+				  skb->dev && skb->dev->type == ARPHRD_ETHER))
 			goto drop;
 		break;
 	case TCA_MPLS_ACT_MODIFY:
-- 
2.20.1


From 2da3817e47e4219854d9429c0d6e910ba6b1c72f Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Mon, 25 Nov 2019 12:11:49 +0200
Subject: [PATCH 24/26] net/mlx5e: Fix TXQ indices to be sequential

[ Upstream commit c55d8b108caa2ec1ae8dddd02cb9d3a740f7c838 ]

Cited patch changed (channel index, tc) => (TXQ index) mapping to be a
static one, in order to keep indices consistent when changing number of
channels or TCs.

For 32 channels (OOB) and 8 TCs, real num of TXQs is 256.
When reducing the amount of channels to 8, the real num of TXQs will be
changed to 64.
This indices method is buggy:
- Channel #0, TC 3, the TXQ index is 96.
- Index 8 is not valid, as there is no such TXQ from driver perspective
  (As it represents channel #8, TC 0, which is not valid with the above
  configuration).

As part of driver's select queue, it calls netdev_pick_tx which returns an
index in the range of real number of TXQs. Depends on the return value,
with the examples above, driver could have returned index larger than the
real number of tx queues, or crash the kernel as it tries to read invalid
address of SQ which was not allocated.

Fix that by allocating sequential TXQ indices, and hold a new mapping
between (channel index, tc) => (real TXQ index). This mapping will be
updated as part of priv channels activation, and is used in
mlx5e_select_queue to find the selected queue index.

The existing indices mapping (channel_tc2txq) is no longer needed, as it
is used only for statistics structures and can be calculated on run time.
Delete its definintion and updates.

Fixes: 8bfaf07f7806 ("net/mlx5e: Present SW stats when state is not opened")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h  |  2 +-
 .../net/ethernet/mellanox/mlx5/core/en_main.c | 31 +++++++------------
 .../ethernet/mellanox/mlx5/core/en_stats.c    |  2 +-
 .../net/ethernet/mellanox/mlx5/core/en_tx.c   |  2 +-
 4 files changed, 15 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 65bec19a438f..2120300aa70e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -792,7 +792,7 @@ struct mlx5e_xsk {
 struct mlx5e_priv {
 	/* priv data path fields - start */
 	struct mlx5e_txqsq *txq2sq[MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC];
-	int channel_tc2txq[MLX5E_MAX_NUM_CHANNELS][MLX5E_MAX_NUM_TC];
+	int channel_tc2realtxq[MLX5E_MAX_NUM_CHANNELS][MLX5E_MAX_NUM_TC];
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 	struct mlx5e_dcbx_dp       dcbx_dp;
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index f3a2970c3fcf..fdf515ca5cf5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1678,11 +1678,10 @@ static int mlx5e_open_sqs(struct mlx5e_channel *c,
 			  struct mlx5e_params *params,
 			  struct mlx5e_channel_param *cparam)
 {
-	struct mlx5e_priv *priv = c->priv;
 	int err, tc;
 
 	for (tc = 0; tc < params->num_tc; tc++) {
-		int txq_ix = c->ix + tc * priv->max_nch;
+		int txq_ix = c->ix + tc * params->num_channels;
 
 		err = mlx5e_open_txqsq(c, c->priv->tisn[tc], txq_ix,
 				       params, &cparam->sq, &c->sq[tc], tc);
@@ -2856,26 +2855,21 @@ static void mlx5e_netdev_set_tcs(struct net_device *netdev)
 		netdev_set_tc_queue(netdev, tc, nch, 0);
 }
 
-static void mlx5e_build_tc2txq_maps(struct mlx5e_priv *priv)
+static void mlx5e_build_txq_maps(struct mlx5e_priv *priv)
 {
-	int i, tc;
+	int i, ch;
 
-	for (i = 0; i < priv->max_nch; i++)
-		for (tc = 0; tc < priv->profile->max_tc; tc++)
-			priv->channel_tc2txq[i][tc] = i + tc * priv->max_nch;
-}
+	ch = priv->channels.num;
 
-static void mlx5e_build_tx2sq_maps(struct mlx5e_priv *priv)
-{
-	struct mlx5e_channel *c;
-	struct mlx5e_txqsq *sq;
-	int i, tc;
+	for (i = 0; i < ch; i++) {
+		int tc;
+
+		for (tc = 0; tc < priv->channels.params.num_tc; tc++) {
+			struct mlx5e_channel *c = priv->channels.c[i];
+			struct mlx5e_txqsq *sq = &c->sq[tc];
 
-	for (i = 0; i < priv->channels.num; i++) {
-		c = priv->channels.c[i];
-		for (tc = 0; tc < c->num_tc; tc++) {
-			sq = &c->sq[tc];
 			priv->txq2sq[sq->txq_ix] = sq;
+			priv->channel_tc2realtxq[i][tc] = i + tc * ch;
 		}
 	}
 }
@@ -2890,7 +2884,7 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv)
 	netif_set_real_num_tx_queues(netdev, num_txqs);
 	netif_set_real_num_rx_queues(netdev, num_rxqs);
 
-	mlx5e_build_tx2sq_maps(priv);
+	mlx5e_build_txq_maps(priv);
 	mlx5e_activate_channels(&priv->channels);
 	mlx5e_xdp_tx_enable(priv);
 	netif_tx_start_all_queues(priv->netdev);
@@ -4968,7 +4962,6 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev,
 	if (err)
 		mlx5_core_err(mdev, "TLS initialization failed, %d\n", err);
 	mlx5e_build_nic_netdev(netdev);
-	mlx5e_build_tc2txq_maps(priv);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 57f9f346d213..0b394d6d730f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -1435,7 +1435,7 @@ static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data,
 			for (j = 0; j < NUM_SQ_STATS; j++)
 				sprintf(data + (idx++) * ETH_GSTRING_LEN,
 					sq_stats_desc[j].format,
-					priv->channel_tc2txq[i][tc]);
+					i + tc * max_nch);
 
 	for (i = 0; i < max_nch; i++) {
 		for (j = 0; j < NUM_XSKSQ_STATS * is_xsk; j++)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index d5d2b1af3dbc..565ac6347fa9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -93,7 +93,7 @@ u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
 	if (txq_ix >= num_channels)
 		txq_ix = priv->txq2sq[txq_ix]->ch_ix;
 
-	return priv->channel_tc2txq[txq_ix][up];
+	return priv->channel_tc2realtxq[txq_ix][up];
 }
 
 static inline int mlx5e_skb_l2_header_offset(struct sk_buff *skb)
-- 
2.20.1


From aada3e7cbb4155118657686a86ff5e7c34249b36 Mon Sep 17 00:00:00 2001
From: Jonathan Lemon <jonathan.lemon@gmail.com>
Date: Thu, 14 Nov 2019 14:13:00 -0800
Subject: [PATCH 25/26] page_pool: do not release pool until inflight == 0.

[ Upstream commit c3f812cea0d7006469d1cf33a4a9f0a12bb4b3a3 ]

The page pool keeps track of the number of pages in flight, and
it isn't safe to remove the pool until all pages are returned.

Disallow removing the pool until all pages are back, so the pool
is always available for page producers.

Make the page pool responsible for its own delayed destruction
instead of relying on XDP, so the page pool can be used without
the xdp memory model.

When all pages are returned, free the pool and notify xdp if the
pool is registered with the xdp memory system.  Have the callback
perform a table walk since some drivers (cpsw) may share the pool
among multiple xdp_rxq_info.

Note that the increment of pages_state_release_cnt may result in
inflight == 0, resulting in the pool being released.

Fixes: d956a048cd3f ("xdp: force mem allocator removal and periodic warning")
Signed-off-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/stmicro/stmmac/stmmac_main.c |   4 +-
 include/net/page_pool.h                       |  52 ++------
 include/net/xdp_priv.h                        |   4 -
 include/trace/events/xdp.h                    |  19 +--
 net/core/page_pool.c                          | 122 +++++++++++-------
 net/core/xdp.c                                | 121 +++++++----------
 6 files changed, 139 insertions(+), 183 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index ed0e694a0855..d8dd4265d89d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1477,10 +1477,8 @@ static void free_dma_rx_desc_resources(struct stmmac_priv *priv)
 					  rx_q->dma_erx, rx_q->dma_rx_phy);
 
 		kfree(rx_q->buf_pool);
-		if (rx_q->page_pool) {
-			page_pool_request_shutdown(rx_q->page_pool);
+		if (rx_q->page_pool)
 			page_pool_destroy(rx_q->page_pool);
-		}
 	}
 }
 
diff --git a/include/net/page_pool.h b/include/net/page_pool.h
index 2cbcdbdec254..1121faa99c12 100644
--- a/include/net/page_pool.h
+++ b/include/net/page_pool.h
@@ -70,7 +70,12 @@ struct page_pool_params {
 struct page_pool {
 	struct page_pool_params p;
 
-        u32 pages_state_hold_cnt;
+	struct delayed_work release_dw;
+	void (*disconnect)(void *);
+	unsigned long defer_start;
+	unsigned long defer_warn;
+
+	u32 pages_state_hold_cnt;
 
 	/*
 	 * Data structure for allocation side
@@ -129,25 +134,19 @@ inline enum dma_data_direction page_pool_get_dma_dir(struct page_pool *pool)
 
 struct page_pool *page_pool_create(const struct page_pool_params *params);
 
-void __page_pool_free(struct page_pool *pool);
-static inline void page_pool_free(struct page_pool *pool)
-{
-	/* When page_pool isn't compiled-in, net/core/xdp.c doesn't
-	 * allow registering MEM_TYPE_PAGE_POOL, but shield linker.
-	 */
 #ifdef CONFIG_PAGE_POOL
-	__page_pool_free(pool);
-#endif
-}
-
-/* Drivers use this instead of page_pool_free */
+void page_pool_destroy(struct page_pool *pool);
+void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *));
+#else
 static inline void page_pool_destroy(struct page_pool *pool)
 {
-	if (!pool)
-		return;
+}
 
-	page_pool_free(pool);
+static inline void page_pool_use_xdp_mem(struct page_pool *pool,
+					 void (*disconnect)(void *))
+{
 }
+#endif
 
 /* Never call this directly, use helpers below */
 void __page_pool_put_page(struct page_pool *pool,
@@ -170,24 +169,6 @@ static inline void page_pool_recycle_direct(struct page_pool *pool,
 	__page_pool_put_page(pool, page, true);
 }
 
-/* API user MUST have disconnected alloc-side (not allowed to call
- * page_pool_alloc_pages()) before calling this.  The free-side can
- * still run concurrently, to handle in-flight packet-pages.
- *
- * A request to shutdown can fail (with false) if there are still
- * in-flight packet-pages.
- */
-bool __page_pool_request_shutdown(struct page_pool *pool);
-static inline bool page_pool_request_shutdown(struct page_pool *pool)
-{
-	bool safe_to_remove = false;
-
-#ifdef CONFIG_PAGE_POOL
-	safe_to_remove = __page_pool_request_shutdown(pool);
-#endif
-	return safe_to_remove;
-}
-
 /* Disconnects a page (from a page_pool).  API users can have a need
  * to disconnect a page (from a page_pool), to allow it to be used as
  * a regular page (that will eventually be returned to the normal
@@ -216,11 +197,6 @@ static inline bool is_page_pool_compiled_in(void)
 #endif
 }
 
-static inline void page_pool_get(struct page_pool *pool)
-{
-	refcount_inc(&pool->user_cnt);
-}
-
 static inline bool page_pool_put(struct page_pool *pool)
 {
 	return refcount_dec_and_test(&pool->user_cnt);
diff --git a/include/net/xdp_priv.h b/include/net/xdp_priv.h
index 6a8cba6ea79a..a9d5b7603b89 100644
--- a/include/net/xdp_priv.h
+++ b/include/net/xdp_priv.h
@@ -12,12 +12,8 @@ struct xdp_mem_allocator {
 		struct page_pool *page_pool;
 		struct zero_copy_allocator *zc_alloc;
 	};
-	int disconnect_cnt;
-	unsigned long defer_start;
 	struct rhash_head node;
 	struct rcu_head rcu;
-	struct delayed_work defer_wq;
-	unsigned long defer_warn;
 };
 
 #endif /* __LINUX_NET_XDP_PRIV_H__ */
diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h
index 68899fdc985b..eabc60f1d129 100644
--- a/include/trace/events/xdp.h
+++ b/include/trace/events/xdp.h
@@ -316,19 +316,15 @@ __MEM_TYPE_MAP(__MEM_TYPE_TP_FN)
 
 TRACE_EVENT(mem_disconnect,
 
-	TP_PROTO(const struct xdp_mem_allocator *xa,
-		 bool safe_to_remove, bool force),
+	TP_PROTO(const struct xdp_mem_allocator *xa),
 
-	TP_ARGS(xa, safe_to_remove, force),
+	TP_ARGS(xa),
 
 	TP_STRUCT__entry(
 		__field(const struct xdp_mem_allocator *,	xa)
 		__field(u32,		mem_id)
 		__field(u32,		mem_type)
 		__field(const void *,	allocator)
-		__field(bool,		safe_to_remove)
-		__field(bool,		force)
-		__field(int,		disconnect_cnt)
 	),
 
 	TP_fast_assign(
@@ -336,19 +332,12 @@ TRACE_EVENT(mem_disconnect,
 		__entry->mem_id		= xa->mem.id;
 		__entry->mem_type	= xa->mem.type;
 		__entry->allocator	= xa->allocator;
-		__entry->safe_to_remove	= safe_to_remove;
-		__entry->force		= force;
-		__entry->disconnect_cnt	= xa->disconnect_cnt;
 	),
 
-	TP_printk("mem_id=%d mem_type=%s allocator=%p"
-		  " safe_to_remove=%s force=%s disconnect_cnt=%d",
+	TP_printk("mem_id=%d mem_type=%s allocator=%p",
 		  __entry->mem_id,
 		  __print_symbolic(__entry->mem_type, __MEM_TYPE_SYM_TAB),
-		  __entry->allocator,
-		  __entry->safe_to_remove ? "true" : "false",
-		  __entry->force ? "true" : "false",
-		  __entry->disconnect_cnt
+		  __entry->allocator
 	)
 );
 
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 3272dc7a8c81..6e7715243dda 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -18,6 +18,9 @@
 
 #include <trace/events/page_pool.h>
 
+#define DEFER_TIME (msecs_to_jiffies(1000))
+#define DEFER_WARN_INTERVAL (60 * HZ)
+
 static int page_pool_init(struct page_pool *pool,
 			  const struct page_pool_params *params)
 {
@@ -200,22 +203,14 @@ static s32 page_pool_inflight(struct page_pool *pool)
 {
 	u32 release_cnt = atomic_read(&pool->pages_state_release_cnt);
 	u32 hold_cnt = READ_ONCE(pool->pages_state_hold_cnt);
-	s32 distance;
-
-	distance = _distance(hold_cnt, release_cnt);
-
-	trace_page_pool_inflight(pool, distance, hold_cnt, release_cnt);
-	return distance;
-}
+	s32 inflight;
 
-static bool __page_pool_safe_to_destroy(struct page_pool *pool)
-{
-	s32 inflight = page_pool_inflight(pool);
+	inflight = _distance(hold_cnt, release_cnt);
 
-	/* The distance should not be able to become negative */
+	trace_page_pool_inflight(pool, inflight, hold_cnt, release_cnt);
 	WARN(inflight < 0, "Negative(%d) inflight packet-pages", inflight);
 
-	return (inflight == 0);
+	return inflight;
 }
 
 /* Cleanup page_pool state from page */
@@ -223,6 +218,7 @@ static void __page_pool_clean_page(struct page_pool *pool,
 				   struct page *page)
 {
 	dma_addr_t dma;
+	int count;
 
 	if (!(pool->p.flags & PP_FLAG_DMA_MAP))
 		goto skip_dma_unmap;
@@ -234,9 +230,11 @@ static void __page_pool_clean_page(struct page_pool *pool,
 			     DMA_ATTR_SKIP_CPU_SYNC);
 	page->dma_addr = 0;
 skip_dma_unmap:
-	atomic_inc(&pool->pages_state_release_cnt);
-	trace_page_pool_state_release(pool, page,
-			      atomic_read(&pool->pages_state_release_cnt));
+	/* This may be the last page returned, releasing the pool, so
+	 * it is not safe to reference pool afterwards.
+	 */
+	count = atomic_inc_return(&pool->pages_state_release_cnt);
+	trace_page_pool_state_release(pool, page, count);
 }
 
 /* unmap the page and clean our state */
@@ -345,31 +343,10 @@ static void __page_pool_empty_ring(struct page_pool *pool)
 	}
 }
 
-static void __warn_in_flight(struct page_pool *pool)
+static void page_pool_free(struct page_pool *pool)
 {
-	u32 release_cnt = atomic_read(&pool->pages_state_release_cnt);
-	u32 hold_cnt = READ_ONCE(pool->pages_state_hold_cnt);
-	s32 distance;
-
-	distance = _distance(hold_cnt, release_cnt);
-
-	/* Drivers should fix this, but only problematic when DMA is used */
-	WARN(1, "Still in-flight pages:%d hold:%u released:%u",
-	     distance, hold_cnt, release_cnt);
-}
-
-void __page_pool_free(struct page_pool *pool)
-{
-	/* Only last user actually free/release resources */
-	if (!page_pool_put(pool))
-		return;
-
-	WARN(pool->alloc.count, "API usage violation");
-	WARN(!ptr_ring_empty(&pool->ring), "ptr_ring is not empty");
-
-	/* Can happen due to forced shutdown */
-	if (!__page_pool_safe_to_destroy(pool))
-		__warn_in_flight(pool);
+	if (pool->disconnect)
+		pool->disconnect(pool);
 
 	ptr_ring_cleanup(&pool->ring, NULL);
 
@@ -378,12 +355,8 @@ void __page_pool_free(struct page_pool *pool)
 
 	kfree(pool);
 }
-EXPORT_SYMBOL(__page_pool_free);
 
-/* Request to shutdown: release pages cached by page_pool, and check
- * for in-flight pages
- */
-bool __page_pool_request_shutdown(struct page_pool *pool)
+static void page_pool_scrub(struct page_pool *pool)
 {
 	struct page *page;
 
@@ -400,7 +373,64 @@ bool __page_pool_request_shutdown(struct page_pool *pool)
 	 * be in-flight.
 	 */
 	__page_pool_empty_ring(pool);
+}
+
+static int page_pool_release(struct page_pool *pool)
+{
+	int inflight;
+
+	page_pool_scrub(pool);
+	inflight = page_pool_inflight(pool);
+	if (!inflight)
+		page_pool_free(pool);
+
+	return inflight;
+}
+
+static void page_pool_release_retry(struct work_struct *wq)
+{
+	struct delayed_work *dwq = to_delayed_work(wq);
+	struct page_pool *pool = container_of(dwq, typeof(*pool), release_dw);
+	int inflight;
+
+	inflight = page_pool_release(pool);
+	if (!inflight)
+		return;
+
+	/* Periodic warning */
+	if (time_after_eq(jiffies, pool->defer_warn)) {
+		int sec = (s32)((u32)jiffies - (u32)pool->defer_start) / HZ;
+
+		pr_warn("%s() stalled pool shutdown %d inflight %d sec\n",
+			__func__, inflight, sec);
+		pool->defer_warn = jiffies + DEFER_WARN_INTERVAL;
+	}
+
+	/* Still not ready to be disconnected, retry later */
+	schedule_delayed_work(&pool->release_dw, DEFER_TIME);
+}
+
+void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *))
+{
+	refcount_inc(&pool->user_cnt);
+	pool->disconnect = disconnect;
+}
+
+void page_pool_destroy(struct page_pool *pool)
+{
+	if (!pool)
+		return;
+
+	if (!page_pool_put(pool))
+		return;
+
+	if (!page_pool_release(pool))
+		return;
+
+	pool->defer_start = jiffies;
+	pool->defer_warn  = jiffies + DEFER_WARN_INTERVAL;
 
-	return __page_pool_safe_to_destroy(pool);
+	INIT_DELAYED_WORK(&pool->release_dw, page_pool_release_retry);
+	schedule_delayed_work(&pool->release_dw, DEFER_TIME);
 }
-EXPORT_SYMBOL(__page_pool_request_shutdown);
+EXPORT_SYMBOL(page_pool_destroy);
diff --git a/net/core/xdp.c b/net/core/xdp.c
index d7bf62ffbb5e..ac866ac65f2b 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -70,10 +70,6 @@ static void __xdp_mem_allocator_rcu_free(struct rcu_head *rcu)
 
 	xa = container_of(rcu, struct xdp_mem_allocator, rcu);
 
-	/* Allocator have indicated safe to remove before this is called */
-	if (xa->mem.type == MEM_TYPE_PAGE_POOL)
-		page_pool_free(xa->page_pool);
-
 	/* Allow this ID to be reused */
 	ida_simple_remove(&mem_id_pool, xa->mem.id);
 
@@ -85,62 +81,57 @@ static void __xdp_mem_allocator_rcu_free(struct rcu_head *rcu)
 	kfree(xa);
 }
 
-static bool __mem_id_disconnect(int id, bool force)
+static void mem_xa_remove(struct xdp_mem_allocator *xa)
 {
-	struct xdp_mem_allocator *xa;
-	bool safe_to_remove = true;
+	trace_mem_disconnect(xa);
 
 	mutex_lock(&mem_id_lock);
 
-	xa = rhashtable_lookup_fast(mem_id_ht, &id, mem_id_rht_params);
-	if (!xa) {
-		mutex_unlock(&mem_id_lock);
-		WARN(1, "Request remove non-existing id(%d), driver bug?", id);
-		return true;
-	}
-	xa->disconnect_cnt++;
-
-	/* Detects in-flight packet-pages for page_pool */
-	if (xa->mem.type == MEM_TYPE_PAGE_POOL)
-		safe_to_remove = page_pool_request_shutdown(xa->page_pool);
-
-	trace_mem_disconnect(xa, safe_to_remove, force);
-
-	if ((safe_to_remove || force) &&
-	    !rhashtable_remove_fast(mem_id_ht, &xa->node, mem_id_rht_params))
+	if (!rhashtable_remove_fast(mem_id_ht, &xa->node, mem_id_rht_params))
 		call_rcu(&xa->rcu, __xdp_mem_allocator_rcu_free);
 
 	mutex_unlock(&mem_id_lock);
-	return (safe_to_remove|force);
 }
 
-#define DEFER_TIME (msecs_to_jiffies(1000))
-#define DEFER_WARN_INTERVAL (30 * HZ)
-#define DEFER_MAX_RETRIES 120
+static void mem_allocator_disconnect(void *allocator)
+{
+	struct xdp_mem_allocator *xa;
+	struct rhashtable_iter iter;
+
+	rhashtable_walk_enter(mem_id_ht, &iter);
+	do {
+		rhashtable_walk_start(&iter);
+
+		while ((xa = rhashtable_walk_next(&iter)) && !IS_ERR(xa)) {
+			if (xa->allocator == allocator)
+				mem_xa_remove(xa);
+		}
+
+		rhashtable_walk_stop(&iter);
 
-static void mem_id_disconnect_defer_retry(struct work_struct *wq)
+	} while (xa == ERR_PTR(-EAGAIN));
+	rhashtable_walk_exit(&iter);
+}
+
+static void mem_id_disconnect(int id)
 {
-	struct delayed_work *dwq = to_delayed_work(wq);
-	struct xdp_mem_allocator *xa = container_of(dwq, typeof(*xa), defer_wq);
-	bool force = false;
+	struct xdp_mem_allocator *xa;
 
-	if (xa->disconnect_cnt > DEFER_MAX_RETRIES)
-		force = true;
+	mutex_lock(&mem_id_lock);
 
-	if (__mem_id_disconnect(xa->mem.id, force))
+	xa = rhashtable_lookup_fast(mem_id_ht, &id, mem_id_rht_params);
+	if (!xa) {
+		mutex_unlock(&mem_id_lock);
+		WARN(1, "Request remove non-existing id(%d), driver bug?", id);
 		return;
+	}
 
-	/* Periodic warning */
-	if (time_after_eq(jiffies, xa->defer_warn)) {
-		int sec = (s32)((u32)jiffies - (u32)xa->defer_start) / HZ;
+	trace_mem_disconnect(xa);
 
-		pr_warn("%s() stalled mem.id=%u shutdown %d attempts %d sec\n",
-			__func__, xa->mem.id, xa->disconnect_cnt, sec);
-		xa->defer_warn = jiffies + DEFER_WARN_INTERVAL;
-	}
+	if (!rhashtable_remove_fast(mem_id_ht, &xa->node, mem_id_rht_params))
+		call_rcu(&xa->rcu, __xdp_mem_allocator_rcu_free);
 
-	/* Still not ready to be disconnected, retry later */
-	schedule_delayed_work(&xa->defer_wq, DEFER_TIME);
+	mutex_unlock(&mem_id_lock);
 }
 
 void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq)
@@ -153,38 +144,21 @@ void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq)
 		return;
 	}
 
-	if (xdp_rxq->mem.type != MEM_TYPE_PAGE_POOL &&
-	    xdp_rxq->mem.type != MEM_TYPE_ZERO_COPY) {
-		return;
-	}
-
 	if (id == 0)
 		return;
 
-	if (__mem_id_disconnect(id, false))
-		return;
-
-	/* Could not disconnect, defer new disconnect attempt to later */
-	mutex_lock(&mem_id_lock);
+	if (xdp_rxq->mem.type == MEM_TYPE_ZERO_COPY)
+		return mem_id_disconnect(id);
 
-	xa = rhashtable_lookup_fast(mem_id_ht, &id, mem_id_rht_params);
-	if (!xa) {
-		mutex_unlock(&mem_id_lock);
-		return;
+	if (xdp_rxq->mem.type == MEM_TYPE_PAGE_POOL) {
+		rcu_read_lock();
+		xa = rhashtable_lookup(mem_id_ht, &id, mem_id_rht_params);
+		page_pool_destroy(xa->page_pool);
+		rcu_read_unlock();
 	}
-	xa->defer_start = jiffies;
-	xa->defer_warn  = jiffies + DEFER_WARN_INTERVAL;
-
-	INIT_DELAYED_WORK(&xa->defer_wq, mem_id_disconnect_defer_retry);
-	mutex_unlock(&mem_id_lock);
-	schedule_delayed_work(&xa->defer_wq, DEFER_TIME);
 }
 EXPORT_SYMBOL_GPL(xdp_rxq_info_unreg_mem_model);
 
-/* This unregister operation will also cleanup and destroy the
- * allocator. The page_pool_free() operation is first called when it's
- * safe to remove, possibly deferred to a workqueue.
- */
 void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq)
 {
 	/* Simplify driver cleanup code paths, allow unreg "unused" */
@@ -371,7 +345,7 @@ int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq,
 	}
 
 	if (type == MEM_TYPE_PAGE_POOL)
-		page_pool_get(xdp_alloc->page_pool);
+		page_pool_use_xdp_mem(allocator, mem_allocator_disconnect);
 
 	mutex_unlock(&mem_id_lock);
 
@@ -402,15 +376,8 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct,
 		/* mem->id is valid, checked in xdp_rxq_info_reg_mem_model() */
 		xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
 		page = virt_to_head_page(data);
-		if (likely(xa)) {
-			napi_direct &= !xdp_return_frame_no_direct();
-			page_pool_put_page(xa->page_pool, page, napi_direct);
-		} else {
-			/* Hopefully stack show who to blame for late return */
-			WARN_ONCE(1, "page_pool gone mem.id=%d", mem->id);
-			trace_mem_return_failed(mem, page);
-			put_page(page);
-		}
+		napi_direct &= !xdp_return_frame_no_direct();
+		page_pool_put_page(xa->page_pool, page, napi_direct);
 		rcu_read_unlock();
 		break;
 	case MEM_TYPE_PAGE_SHARED:
-- 
2.20.1


From f4e532c391bd96c72f2004838d63c3b3d213f711 Mon Sep 17 00:00:00 2001
From: Jonathan Lemon <jonathan.lemon@gmail.com>
Date: Tue, 3 Dec 2019 14:01:14 -0800
Subject: [PATCH 26/26] xdp: obtain the mem_id mutex before trying to remove an
 entry.

[ Upstream commit 86c76c09898332143be365c702cf8d586ed4ed21 ]

A lockdep splat was observed when trying to remove an xdp memory
model from the table since the mutex was obtained when trying to
remove the entry, but not before the table walk started:

Fix the splat by obtaining the lock before starting the table walk.

Fixes: c3f812cea0d7 ("page_pool: do not release pool until inflight == 0.")
Reported-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Tested-by: Grygorii Strashko <grygorii.strashko@ti.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/xdp.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/core/xdp.c b/net/core/xdp.c
index ac866ac65f2b..b3f463c6543f 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -85,12 +85,8 @@ static void mem_xa_remove(struct xdp_mem_allocator *xa)
 {
 	trace_mem_disconnect(xa);
 
-	mutex_lock(&mem_id_lock);
-
 	if (!rhashtable_remove_fast(mem_id_ht, &xa->node, mem_id_rht_params))
 		call_rcu(&xa->rcu, __xdp_mem_allocator_rcu_free);
-
-	mutex_unlock(&mem_id_lock);
 }
 
 static void mem_allocator_disconnect(void *allocator)
@@ -98,6 +94,8 @@ static void mem_allocator_disconnect(void *allocator)
 	struct xdp_mem_allocator *xa;
 	struct rhashtable_iter iter;
 
+	mutex_lock(&mem_id_lock);
+
 	rhashtable_walk_enter(mem_id_ht, &iter);
 	do {
 		rhashtable_walk_start(&iter);
@@ -111,6 +109,8 @@ static void mem_allocator_disconnect(void *allocator)
 
 	} while (xa == ERR_PTR(-EAGAIN));
 	rhashtable_walk_exit(&iter);
+
+	mutex_unlock(&mem_id_lock);
 }
 
 static void mem_id_disconnect(int id)
-- 
2.20.1


[-- Attachment #3: net_54.mbox --]
[-- Type: Application/Octet-Stream, Size: 159851 bytes --]

From 52142b1b0d6fd35ceb3a2fc590f92ba470a29411 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 5 Dec 2019 20:43:46 -0800
Subject: [PATCH 01/38] inet: protect against too small mtu values.

[ Upstream commit 501a90c945103e8627406763dac418f20f3837b2 ]

syzbot was once again able to crash a host by setting a very small mtu
on loopback device.

Let's make inetdev_valid_mtu() available in include/net/ip.h,
and use it in ip_setup_cork(), so that we protect both ip_append_page()
and __ip_append_data()

Also add a READ_ONCE() when the device mtu is read.

Pairs this lockless read with one WRITE_ONCE() in __dev_set_mtu(),
even if other code paths might write over this field.

Add a big comment in include/linux/netdevice.h about dev->mtu
needing READ_ONCE()/WRITE_ONCE() annotations.

Hopefully we will add the missing ones in followup patches.

[1]

refcount_t: saturated; leaking memory.
WARNING: CPU: 0 PID: 9464 at lib/refcount.c:22 refcount_warn_saturate+0x138/0x1f0 lib/refcount.c:22
Kernel panic - not syncing: panic_on_warn set ...
CPU: 0 PID: 9464 Comm: syz-executor850 Not tainted 5.4.0-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x197/0x210 lib/dump_stack.c:118
 panic+0x2e3/0x75c kernel/panic.c:221
 __warn.cold+0x2f/0x3e kernel/panic.c:582
 report_bug+0x289/0x300 lib/bug.c:195
 fixup_bug arch/x86/kernel/traps.c:174 [inline]
 fixup_bug arch/x86/kernel/traps.c:169 [inline]
 do_error_trap+0x11b/0x200 arch/x86/kernel/traps.c:267
 do_invalid_op+0x37/0x50 arch/x86/kernel/traps.c:286
 invalid_op+0x23/0x30 arch/x86/entry/entry_64.S:1027
RIP: 0010:refcount_warn_saturate+0x138/0x1f0 lib/refcount.c:22
Code: 06 31 ff 89 de e8 c8 f5 e6 fd 84 db 0f 85 6f ff ff ff e8 7b f4 e6 fd 48 c7 c7 e0 71 4f 88 c6 05 56 a6 a4 06 01 e8 c7 a8 b7 fd <0f> 0b e9 50 ff ff ff e8 5c f4 e6 fd 0f b6 1d 3d a6 a4 06 31 ff 89
RSP: 0018:ffff88809689f550 EFLAGS: 00010286
RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000
RDX: 0000000000000000 RSI: ffffffff815e4336 RDI: ffffed1012d13e9c
RBP: ffff88809689f560 R08: ffff88809c50a3c0 R09: fffffbfff15d31b1
R10: fffffbfff15d31b0 R11: ffffffff8ae98d87 R12: 0000000000000001
R13: 0000000000040100 R14: ffff888099041104 R15: ffff888218d96e40
 refcount_add include/linux/refcount.h:193 [inline]
 skb_set_owner_w+0x2b6/0x410 net/core/sock.c:1999
 sock_wmalloc+0xf1/0x120 net/core/sock.c:2096
 ip_append_page+0x7ef/0x1190 net/ipv4/ip_output.c:1383
 udp_sendpage+0x1c7/0x480 net/ipv4/udp.c:1276
 inet_sendpage+0xdb/0x150 net/ipv4/af_inet.c:821
 kernel_sendpage+0x92/0xf0 net/socket.c:3794
 sock_sendpage+0x8b/0xc0 net/socket.c:936
 pipe_to_sendpage+0x2da/0x3c0 fs/splice.c:458
 splice_from_pipe_feed fs/splice.c:512 [inline]
 __splice_from_pipe+0x3ee/0x7c0 fs/splice.c:636
 splice_from_pipe+0x108/0x170 fs/splice.c:671
 generic_splice_sendpage+0x3c/0x50 fs/splice.c:842
 do_splice_from fs/splice.c:861 [inline]
 direct_splice_actor+0x123/0x190 fs/splice.c:1035
 splice_direct_to_actor+0x3b4/0xa30 fs/splice.c:990
 do_splice_direct+0x1da/0x2a0 fs/splice.c:1078
 do_sendfile+0x597/0xd00 fs/read_write.c:1464
 __do_sys_sendfile64 fs/read_write.c:1525 [inline]
 __se_sys_sendfile64 fs/read_write.c:1511 [inline]
 __x64_sys_sendfile64+0x1dd/0x220 fs/read_write.c:1511
 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x441409
Code: e8 ac e8 ff ff 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 eb 08 fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007fffb64c4f78 EFLAGS: 00000246 ORIG_RAX: 0000000000000028
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 0000000000441409
RDX: 0000000000000000 RSI: 0000000000000006 RDI: 0000000000000005
RBP: 0000000000073b8a R08: 0000000000000010 R09: 0000000000000010
R10: 0000000000010001 R11: 0000000000000246 R12: 0000000000402180
R13: 0000000000402210 R14: 0000000000000000 R15: 0000000000000000
Kernel Offset: disabled
Rebooting in 86400 seconds..

Fixes: 1470ddf7f8ce ("inet: Remove explicit write references to sk/inet in ip_append_data")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  5 +++++
 include/net/ip.h          |  5 +++++
 net/core/dev.c            |  3 ++-
 net/ipv4/devinet.c        |  5 -----
 net/ipv4/ip_output.c      | 13 ++++++++-----
 5 files changed, 20 insertions(+), 11 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index c20f190b4c18..76d952aeb0fc 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1867,6 +1867,11 @@ struct net_device {
 	unsigned char		if_port;
 	unsigned char		dma;
 
+	/* Note : dev->mtu is often read without holding a lock.
+	 * Writers usually hold RTNL.
+	 * It is recommended to use READ_ONCE() to annotate the reads,
+	 * and to use WRITE_ONCE() to annotate the writes.
+	 */
 	unsigned int		mtu;
 	unsigned int		min_mtu;
 	unsigned int		max_mtu;
diff --git a/include/net/ip.h b/include/net/ip.h
index a2c61c36dc4a..4b15cc1c224c 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -760,4 +760,9 @@ int ip_misc_proc_init(void);
 int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto, u8 family,
 				struct netlink_ext_ack *extack);
 
+static inline bool inetdev_valid_mtu(unsigned int mtu)
+{
+	return likely(mtu >= IPV4_MIN_MTU);
+}
+
 #endif	/* _IP_H */
diff --git a/net/core/dev.c b/net/core/dev.c
index 99ac84ff398f..046307445ece 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7967,7 +7967,8 @@ int __dev_set_mtu(struct net_device *dev, int new_mtu)
 	if (ops->ndo_change_mtu)
 		return ops->ndo_change_mtu(dev, new_mtu);
 
-	dev->mtu = new_mtu;
+	/* Pairs with all the lockless reads of dev->mtu in the stack */
+	WRITE_ONCE(dev->mtu, new_mtu);
 	return 0;
 }
 EXPORT_SYMBOL(__dev_set_mtu);
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index a4b5bd4d2c89..e4632bd2026d 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1496,11 +1496,6 @@ static void inetdev_changename(struct net_device *dev, struct in_device *in_dev)
 	}
 }
 
-static bool inetdev_valid_mtu(unsigned int mtu)
-{
-	return mtu >= IPV4_MIN_MTU;
-}
-
 static void inetdev_send_gratuitous_arp(struct net_device *dev,
 					struct in_device *in_dev)
 
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 3d8baaaf7086..b268ee1c1b44 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1258,15 +1258,18 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 		cork->addr = ipc->addr;
 	}
 
-	/*
-	 * We steal reference to this route, caller should not release it
-	 */
-	*rtp = NULL;
 	cork->fragsize = ip_sk_use_pmtu(sk) ?
-			 dst_mtu(&rt->dst) : rt->dst.dev->mtu;
+			 dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu);
+
+	if (!inetdev_valid_mtu(cork->fragsize))
+		return -ENETUNREACH;
 
 	cork->gso_size = ipc->gso_size;
+
 	cork->dst = &rt->dst;
+	/* We stole this route, caller should not release it. */
+	*rtp = NULL;
+
 	cork->length = 0;
 	cork->ttl = ipc->ttl;
 	cork->tos = ipc->tos;
-- 
2.20.1


From 2058b886be0bea87c601f3c2192157936c93dd35 Mon Sep 17 00:00:00 2001
From: Vladyslav Tarasiuk <vladyslavt@mellanox.com>
Date: Fri, 6 Dec 2019 13:51:05 +0000
Subject: [PATCH 02/38] mqprio: Fix out-of-bounds access in mqprio_dump

[ Upstream commit 9f104c7736904ac72385bbb48669e0c923ca879b ]

When user runs a command like
tc qdisc add dev eth1 root mqprio
KASAN stack-out-of-bounds warning is emitted.
Currently, NLA_ALIGN macro used in mqprio_dump provides too large
buffer size as argument for nla_put and memcpy down the call stack.
The flow looks like this:
1. nla_put expects exact object size as an argument;
2. Later it provides this size to memcpy;
3. To calculate correct padding for SKB, nla_put applies NLA_ALIGN
   macro itself.

Therefore, NLA_ALIGN should not be applied to the nla_put parameter.
Otherwise it will lead to out-of-bounds memory access in memcpy.

Fixes: 4e8b86c06269 ("mqprio: Introduce new hardware offload mode and shaper in mqprio")
Signed-off-by: Vladyslav Tarasiuk <vladyslavt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_mqprio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index 0d0113a24962..7b67e4d8e448 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -433,7 +433,7 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb)
 		opt.offset[tc] = dev->tc_to_txq[tc].offset;
 	}
 
-	if (nla_put(skb, TCA_OPTIONS, NLA_ALIGN(sizeof(opt)), &opt))
+	if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt))
 		goto nla_put_failure;
 
 	if ((priv->flags & TC_MQPRIO_F_MODE) &&
-- 
2.20.1


From 541c060b85a7dfeea8864578c1310a639d549eea Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Tue, 3 Dec 2019 16:48:06 +0200
Subject: [PATCH 03/38] net: bridge: deny dev_set_mac_address() when
 unregistering

[ Upstream commit c4b4c421857dc7b1cf0dccbd738472360ff2cd70 ]

We have an interesting memory leak in the bridge when it is being
unregistered and is a slave to a master device which would change the
mac of its slaves on unregister (e.g. bond, team). This is a very
unusual setup but we do end up leaking 1 fdb entry because
dev_set_mac_address() would cause the bridge to insert the new mac address
into its table after all fdbs are flushed, i.e. after dellink() on the
bridge has finished and we call NETDEV_UNREGISTER the bond/team would
release it and will call dev_set_mac_address() to restore its original
address and that in turn will add an fdb in the bridge.
One fix is to check for the bridge dev's reg_state in its
ndo_set_mac_address callback and return an error if the bridge is not in
NETREG_REGISTERED.

Easy steps to reproduce:
 1. add bond in mode != A/B
 2. add any slave to the bond
 3. add bridge dev as a slave to the bond
 4. destroy the bridge device

Trace:
 unreferenced object 0xffff888035c4d080 (size 128):
   comm "ip", pid 4068, jiffies 4296209429 (age 1413.753s)
   hex dump (first 32 bytes):
     41 1d c9 36 80 88 ff ff 00 00 00 00 00 00 00 00  A..6............
     d2 19 c9 5e 3f d7 00 00 00 00 00 00 00 00 00 00  ...^?...........
   backtrace:
     [<00000000ddb525dc>] kmem_cache_alloc+0x155/0x26f
     [<00000000633ff1e0>] fdb_create+0x21/0x486 [bridge]
     [<0000000092b17e9c>] fdb_insert+0x91/0xdc [bridge]
     [<00000000f2a0f0ff>] br_fdb_change_mac_address+0xb3/0x175 [bridge]
     [<000000001de02dbd>] br_stp_change_bridge_id+0xf/0xff [bridge]
     [<00000000ac0e32b1>] br_set_mac_address+0x76/0x99 [bridge]
     [<000000006846a77f>] dev_set_mac_address+0x63/0x9b
     [<00000000d30738fc>] __bond_release_one+0x3f6/0x455 [bonding]
     [<00000000fc7ec01d>] bond_netdev_event+0x2f2/0x400 [bonding]
     [<00000000305d7795>] notifier_call_chain+0x38/0x56
     [<0000000028885d4a>] call_netdevice_notifiers+0x1e/0x23
     [<000000008279477b>] rollback_registered_many+0x353/0x6a4
     [<0000000018ef753a>] unregister_netdevice_many+0x17/0x6f
     [<00000000ba854b7a>] rtnl_delete_link+0x3c/0x43
     [<00000000adf8618d>] rtnl_dellink+0x1dc/0x20a
     [<000000009b6395fd>] rtnetlink_rcv_msg+0x23d/0x268

Fixes: 43598813386f ("bridge: add local MAC address to forwarding table (v2)")
Reported-by: syzbot+2add91c08eb181fea1bf@syzkaller.appspotmail.com
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_device.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index e804a3016902..022dc6e504c4 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -245,6 +245,12 @@ static int br_set_mac_address(struct net_device *dev, void *p)
 	if (!is_valid_ether_addr(addr->sa_data))
 		return -EADDRNOTAVAIL;
 
+	/* dev_set_mac_addr() can be called by a master device on bridge's
+	 * NETDEV_UNREGISTER, but since it's being destroyed do nothing
+	 */
+	if (dev->reg_state != NETREG_REGISTERED)
+		return -EBUSY;
+
 	spin_lock_bh(&br->lock);
 	if (!ether_addr_equal(dev->dev_addr, addr->sa_data)) {
 		/* Mac address will be changed in br_stp_change_bridge_id(). */
-- 
2.20.1


From 51697474082ce471d4f4eafb20dc58693e284d6a Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <alobakin@dlink.ru>
Date: Thu, 5 Dec 2019 13:02:35 +0300
Subject: [PATCH 04/38] net: dsa: fix flow dissection on Tx path

[ Upstream commit 8bef0af09a5415df761b04fa487a6c34acae74bc ]

Commit 43e665287f93 ("net-next: dsa: fix flow dissection") added an
ability to override protocol and network offset during flow dissection
for DSA-enabled devices (i.e. controllers shipped as switch CPU ports)
in order to fix skb hashing for RPS on Rx path.

However, skb_hash() and added part of code can be invoked not only on
Rx, but also on Tx path if we have a multi-queued device and:
 - kernel is running on UP system or
 - XPS is not configured.

The call stack in this two cases will be like: dev_queue_xmit() ->
__dev_queue_xmit() -> netdev_core_pick_tx() -> netdev_pick_tx() ->
skb_tx_hash() -> skb_get_hash().

The problem is that skbs queued for Tx have both network offset and
correct protocol already set up even after inserting a CPU tag by DSA
tagger, so calling tag_ops->flow_dissect() on this path actually only
breaks flow dissection and hashing.

This can be observed by adding debug prints just before and right after
tag_ops->flow_dissect() call to the related block of code:

Before the patch:

Rx path (RPS):

[   19.240001] Rx: proto: 0x00f8, nhoff: 0	/* ETH_P_XDSA */
[   19.244271] tag_ops->flow_dissect()
[   19.247811] Rx: proto: 0x0800, nhoff: 8	/* ETH_P_IP */

[   19.215435] Rx: proto: 0x00f8, nhoff: 0	/* ETH_P_XDSA */
[   19.219746] tag_ops->flow_dissect()
[   19.223241] Rx: proto: 0x0806, nhoff: 8	/* ETH_P_ARP */

[   18.654057] Rx: proto: 0x00f8, nhoff: 0	/* ETH_P_XDSA */
[   18.658332] tag_ops->flow_dissect()
[   18.661826] Rx: proto: 0x8100, nhoff: 8	/* ETH_P_8021Q */

Tx path (UP system):

[   18.759560] Tx: proto: 0x0800, nhoff: 26	/* ETH_P_IP */
[   18.763933] tag_ops->flow_dissect()
[   18.767485] Tx: proto: 0x920b, nhoff: 34	/* junk */

[   22.800020] Tx: proto: 0x0806, nhoff: 26	/* ETH_P_ARP */
[   22.804392] tag_ops->flow_dissect()
[   22.807921] Tx: proto: 0x920b, nhoff: 34	/* junk */

[   16.898342] Tx: proto: 0x86dd, nhoff: 26	/* ETH_P_IPV6 */
[   16.902705] tag_ops->flow_dissect()
[   16.906227] Tx: proto: 0x920b, nhoff: 34	/* junk */

After:

Rx path (RPS):

[   16.520993] Rx: proto: 0x00f8, nhoff: 0	/* ETH_P_XDSA */
[   16.525260] tag_ops->flow_dissect()
[   16.528808] Rx: proto: 0x0800, nhoff: 8	/* ETH_P_IP */

[   15.484807] Rx: proto: 0x00f8, nhoff: 0	/* ETH_P_XDSA */
[   15.490417] tag_ops->flow_dissect()
[   15.495223] Rx: proto: 0x0806, nhoff: 8	/* ETH_P_ARP */

[   17.134621] Rx: proto: 0x00f8, nhoff: 0	/* ETH_P_XDSA */
[   17.138895] tag_ops->flow_dissect()
[   17.142388] Rx: proto: 0x8100, nhoff: 8	/* ETH_P_8021Q */

Tx path (UP system):

[   15.499558] Tx: proto: 0x0800, nhoff: 26	/* ETH_P_IP */

[   20.664689] Tx: proto: 0x0806, nhoff: 26	/* ETH_P_ARP */

[   18.565782] Tx: proto: 0x86dd, nhoff: 26	/* ETH_P_IPV6 */

In order to fix that we can add the check 'proto == htons(ETH_P_XDSA)'
to prevent code from calling tag_ops->flow_dissect() on Tx.
I also decided to initialize 'offset' variable so tagger callbacks can
now safely leave it untouched without provoking a chaos.

Fixes: 43e665287f93 ("net-next: dsa: fix flow dissection")
Signed-off-by: Alexander Lobakin <alobakin@dlink.ru>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/flow_dissector.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 68eda10d0680..c206d1cb6ec1 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -870,9 +870,10 @@ bool __skb_flow_dissect(const struct net *net,
 		nhoff = skb_network_offset(skb);
 		hlen = skb_headlen(skb);
 #if IS_ENABLED(CONFIG_NET_DSA)
-		if (unlikely(skb->dev && netdev_uses_dsa(skb->dev))) {
+		if (unlikely(skb->dev && netdev_uses_dsa(skb->dev) &&
+			     proto == htons(ETH_P_XDSA))) {
 			const struct dsa_device_ops *ops;
-			int offset;
+			int offset = 0;
 
 			ops = skb->dev->dsa_ptr->tag_ops;
 			if (ops->flow_dissect &&
-- 
2.20.1


From a8537d3dc28744c5f41a934aa3af493c167d029d Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Fri, 6 Dec 2019 14:28:20 +0200
Subject: [PATCH 05/38] net: ethernet: ti: cpsw: fix extra rx interrupt

[ Upstream commit 51302f77bedab8768b761ed1899c08f89af9e4e2 ]

Now RX interrupt is triggered twice every time, because in
cpsw_rx_interrupt() it is asked first and then disabled. So there will be
pending interrupt always, when RX interrupt is enabled again in NAPI
handler.

Fix it by first disabling IRQ and then do ask.

Fixes: 870915feabdc ("drivers: net: cpsw: remove disable_irq/enable_irq as irq can be masked from cpsw itself")
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index f298d714efd6..d7a953c647b4 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -890,8 +890,8 @@ static irqreturn_t cpsw_rx_interrupt(int irq, void *dev_id)
 {
 	struct cpsw_common *cpsw = dev_id;
 
-	cpdma_ctlr_eoi(cpsw->dma, CPDMA_EOI_RX);
 	writel(0, &cpsw->wr_regs->rx_en);
+	cpdma_ctlr_eoi(cpsw->dma, CPDMA_EOI_RX);
 
 	if (cpsw->quirk_irq) {
 		disable_irq_nosync(cpsw->irqs_table[0]);
-- 
2.20.1


From 9e04735b8fd1bc9de73ca2e806e7dc5dff374614 Mon Sep 17 00:00:00 2001
From: Dust Li <dust.li@linux.alibaba.com>
Date: Tue, 3 Dec 2019 11:17:40 +0800
Subject: [PATCH 06/38] net: sched: fix dump qlen for sch_mq/sch_mqprio with
 NOLOCK subqueues

[ Upstream commit 2f23cd42e19c22c24ff0e221089b7b6123b117c5 ]

sch->q.len hasn't been set if the subqueue is a NOLOCK qdisc
 in mq_dump() and mqprio_dump().

Fixes: ce679e8df7ed ("net: sched: add support for TCQ_F_NOLOCK subqueues to sch_mqprio")
Signed-off-by: Dust Li <dust.li@linux.alibaba.com>
Signed-off-by: Tony Lu <tonylu@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_mq.c     | 1 +
 net/sched/sch_mqprio.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
index 278c0b2dc523..e79f1afe0cfd 100644
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -153,6 +153,7 @@ static int mq_dump(struct Qdisc *sch, struct sk_buff *skb)
 			__gnet_stats_copy_queue(&sch->qstats,
 						qdisc->cpu_qstats,
 						&qdisc->qstats, qlen);
+			sch->q.qlen		+= qlen;
 		} else {
 			sch->q.qlen		+= qdisc->q.qlen;
 			sch->bstats.bytes	+= qdisc->bstats.bytes;
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index 7b67e4d8e448..8766ab5b8788 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -411,6 +411,7 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb)
 			__gnet_stats_copy_queue(&sch->qstats,
 						qdisc->cpu_qstats,
 						&qdisc->qstats, qlen);
+			sch->q.qlen		+= qlen;
 		} else {
 			sch->q.qlen		+= qdisc->q.qlen;
 			sch->bstats.bytes	+= qdisc->bstats.bytes;
-- 
2.20.1


From fafd0c74f600ffcf2786bcd038029692f6c162f7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 7 Dec 2019 11:34:45 -0800
Subject: [PATCH 07/38] net_sched: validate TCA_KIND attribute in
 tc_chain_tmplt_add()

[ Upstream commit 2dd5616ecdcebdf5a8d007af64e040d4e9214efe ]

Use the new tcf_proto_check_kind() helper to make sure user
provided value is well formed.

BUG: KMSAN: uninit-value in string_nocheck lib/vsprintf.c:606 [inline]
BUG: KMSAN: uninit-value in string+0x4be/0x600 lib/vsprintf.c:668
CPU: 0 PID: 12358 Comm: syz-executor.1 Not tainted 5.4.0-rc8-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c9/0x220 lib/dump_stack.c:118
 kmsan_report+0x128/0x220 mm/kmsan/kmsan_report.c:108
 __msan_warning+0x64/0xc0 mm/kmsan/kmsan_instr.c:245
 string_nocheck lib/vsprintf.c:606 [inline]
 string+0x4be/0x600 lib/vsprintf.c:668
 vsnprintf+0x218f/0x3210 lib/vsprintf.c:2510
 __request_module+0x2b1/0x11c0 kernel/kmod.c:143
 tcf_proto_lookup_ops+0x171/0x700 net/sched/cls_api.c:139
 tc_chain_tmplt_add net/sched/cls_api.c:2730 [inline]
 tc_ctl_chain+0x1904/0x38a0 net/sched/cls_api.c:2850
 rtnetlink_rcv_msg+0x115a/0x1580 net/core/rtnetlink.c:5224
 netlink_rcv_skb+0x431/0x620 net/netlink/af_netlink.c:2477
 rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:5242
 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
 netlink_unicast+0xf3e/0x1020 net/netlink/af_netlink.c:1328
 netlink_sendmsg+0x110f/0x1330 net/netlink/af_netlink.c:1917
 sock_sendmsg_nosec net/socket.c:637 [inline]
 sock_sendmsg net/socket.c:657 [inline]
 ___sys_sendmsg+0x14ff/0x1590 net/socket.c:2311
 __sys_sendmsg net/socket.c:2356 [inline]
 __do_sys_sendmsg net/socket.c:2365 [inline]
 __se_sys_sendmsg+0x305/0x460 net/socket.c:2363
 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2363
 do_syscall_64+0xb6/0x160 arch/x86/entry/common.c:291
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x45a649
Code: ad b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f0790795c78 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 000000000045a649
RDX: 0000000000000000 RSI: 0000000020000300 RDI: 0000000000000006
RBP: 000000000075bfc8 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00007f07907966d4
R13: 00000000004c8db5 R14: 00000000004df630 R15: 00000000ffffffff

Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:149 [inline]
 kmsan_internal_poison_shadow+0x5c/0x110 mm/kmsan/kmsan.c:132
 kmsan_slab_alloc+0x97/0x100 mm/kmsan/kmsan_hooks.c:86
 slab_alloc_node mm/slub.c:2773 [inline]
 __kmalloc_node_track_caller+0xe27/0x11a0 mm/slub.c:4381
 __kmalloc_reserve net/core/skbuff.c:141 [inline]
 __alloc_skb+0x306/0xa10 net/core/skbuff.c:209
 alloc_skb include/linux/skbuff.h:1049 [inline]
 netlink_alloc_large_skb net/netlink/af_netlink.c:1174 [inline]
 netlink_sendmsg+0x783/0x1330 net/netlink/af_netlink.c:1892
 sock_sendmsg_nosec net/socket.c:637 [inline]
 sock_sendmsg net/socket.c:657 [inline]
 ___sys_sendmsg+0x14ff/0x1590 net/socket.c:2311
 __sys_sendmsg net/socket.c:2356 [inline]
 __do_sys_sendmsg net/socket.c:2365 [inline]
 __se_sys_sendmsg+0x305/0x460 net/socket.c:2363
 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2363
 do_syscall_64+0xb6/0x160 arch/x86/entry/common.c:291
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 6f96c3c6904c ("net_sched: fix backward compatibility for TCA_KIND")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 20d60b8fcb70..37c95cefb7de 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -2721,13 +2721,19 @@ static int tc_chain_tmplt_add(struct tcf_chain *chain, struct net *net,
 			      struct netlink_ext_ack *extack)
 {
 	const struct tcf_proto_ops *ops;
+	char name[IFNAMSIZ];
 	void *tmplt_priv;
 
 	/* If kind is not set, user did not specify template. */
 	if (!tca[TCA_KIND])
 		return 0;
 
-	ops = tcf_proto_lookup_ops(nla_data(tca[TCA_KIND]), true, extack);
+	if (tcf_proto_check_kind(tca[TCA_KIND], name)) {
+		NL_SET_ERR_MSG(extack, "Specified TC chain template name too long");
+		return -EINVAL;
+	}
+
+	ops = tcf_proto_lookup_ops(name, true, extack);
 	if (IS_ERR(ops))
 		return PTR_ERR(ops);
 	if (!ops->tmplt_create || !ops->tmplt_destroy || !ops->tmplt_dump) {
-- 
2.20.1


From 24322fe2bb542082a72412be47b3cd34743c0fe0 Mon Sep 17 00:00:00 2001
From: Jouni Hogander <jouni.hogander@unikie.com>
Date: Thu, 5 Dec 2019 15:57:07 +0200
Subject: [PATCH 08/38] net-sysfs: Call dev_hold always in
 netdev_queue_add_kobject

[ Upstream commit e0b60903b434a7ee21ba8d8659f207ed84101e89 ]

Dev_hold has to be called always in netdev_queue_add_kobject.
Otherwise usage count drops below 0 in case of failure in
kobject_init_and_add.

Fixes: b8eb718348b8 ("net-sysfs: Fix reference count leak in rx|netdev_queue_add_kobject")
Reported-by: Hulk Robot <hulkci@huawei.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: David Miller <davem@davemloft.net>
Cc: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/net-sysfs.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index ae3bcb1540ec..5c4624298996 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1459,14 +1459,17 @@ static int netdev_queue_add_kobject(struct net_device *dev, int index)
 	struct kobject *kobj = &queue->kobj;
 	int error = 0;
 
+	/* Kobject_put later will trigger netdev_queue_release call
+	 * which decreases dev refcount: Take that reference here
+	 */
+	dev_hold(queue->dev);
+
 	kobj->kset = dev->queues_kset;
 	error = kobject_init_and_add(kobj, &netdev_queue_ktype, NULL,
 				     "tx-%u", index);
 	if (error)
 		goto err;
 
-	dev_hold(queue->dev);
-
 #ifdef CONFIG_BQL
 	error = sysfs_create_group(kobj, &dql_group);
 	if (error)
-- 
2.20.1


From d6e25cacabf2ff39fe1f8d4a967941e68ac7a60a Mon Sep 17 00:00:00 2001
From: Mian Yousaf Kaukab <ykaukab@suse.de>
Date: Thu, 5 Dec 2019 10:41:16 +0100
Subject: [PATCH 09/38] net: thunderx: start phy before starting
 autonegotiation

[ Upstream commit a350d2e7adbb57181d33e3aa6f0565632747feaa ]

Since commit 2b3e88ea6528 ("net: phy: improve phy state checking")
phy_start_aneg() expects phy state to be >= PHY_UP. Call phy_start()
before calling phy_start_aneg() during probe so that autonegotiation
is initiated.

As phy_start() takes care of calling phy_start_aneg(), drop the explicit
call to phy_start_aneg().

Network fails without this patch on Octeon TX.

Fixes: 2b3e88ea6528 ("net: phy: improve phy state checking")
Signed-off-by: Mian Yousaf Kaukab <ykaukab@suse.de>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/thunder/thunder_bgx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index acb016834f04..6cc100e7d5c0 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -1115,7 +1115,7 @@ static int bgx_lmac_enable(struct bgx *bgx, u8 lmacid)
 				       phy_interface_mode(lmac->lmac_type)))
 			return -ENODEV;
 
-		phy_start_aneg(lmac->phydev);
+		phy_start(lmac->phydev);
 		return 0;
 	}
 
-- 
2.20.1


From 547807bd01bdd929ee29828013224353b2ea5d5d Mon Sep 17 00:00:00 2001
From: Valentin Vidic <vvidic@valentin-vidic.from.hr>
Date: Thu, 5 Dec 2019 07:41:18 +0100
Subject: [PATCH 10/38] net/tls: Fix return values to avoid ENOTSUPP

[ Upstream commit 4a5cdc604b9cf645e6fa24d8d9f055955c3c8516 ]

ENOTSUPP is not available in userspace, for example:

  setsockopt failed, 524, Unknown error 524

Signed-off-by: Valentin Vidic <vvidic@valentin-vidic.from.hr>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_device.c              | 8 ++++----
 net/tls/tls_main.c                | 4 ++--
 net/tls/tls_sw.c                  | 8 ++++----
 tools/testing/selftests/net/tls.c | 8 ++------
 4 files changed, 12 insertions(+), 16 deletions(-)

diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 683d00837693..3f5209e2d4ee 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -417,7 +417,7 @@ static int tls_push_data(struct sock *sk,
 
 	if (flags &
 	    ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SENDPAGE_NOTLAST))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	if (sk->sk_err)
 		return -sk->sk_err;
@@ -560,7 +560,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page,
 	lock_sock(sk);
 
 	if (flags & MSG_OOB) {
-		rc = -ENOTSUPP;
+		rc = -EOPNOTSUPP;
 		goto out;
 	}
 
@@ -999,7 +999,7 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx)
 	}
 
 	if (!(netdev->features & NETIF_F_HW_TLS_TX)) {
-		rc = -ENOTSUPP;
+		rc = -EOPNOTSUPP;
 		goto release_netdev;
 	}
 
@@ -1071,7 +1071,7 @@ int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx)
 	}
 
 	if (!(netdev->features & NETIF_F_HW_TLS_RX)) {
-		rc = -ENOTSUPP;
+		rc = -EOPNOTSUPP;
 		goto release_netdev;
 	}
 
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index eff444293594..82d0beed8f07 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -482,7 +482,7 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval,
 	/* check version */
 	if (crypto_info->version != TLS_1_2_VERSION &&
 	    crypto_info->version != TLS_1_3_VERSION) {
-		rc = -ENOTSUPP;
+		rc = -EINVAL;
 		goto err_crypto_info;
 	}
 
@@ -778,7 +778,7 @@ static int tls_init(struct sock *sk)
 	 * share the ulp context.
 	 */
 	if (sk->sk_state != TCP_ESTABLISHED)
-		return -ENOTSUPP;
+		return -ENOTCONN;
 
 	tls_build_proto(sk);
 
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 5dd0f01913c0..c70cf30c5492 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -900,7 +900,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 	int ret = 0;
 
 	if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	mutex_lock(&tls_ctx->tx_lock);
 	lock_sock(sk);
@@ -1215,7 +1215,7 @@ int tls_sw_sendpage_locked(struct sock *sk, struct page *page,
 	if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
 		      MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY |
 		      MSG_NO_SHARED_FRAGS))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	return tls_sw_do_sendpage(sk, page, offset, size, flags);
 }
@@ -1228,7 +1228,7 @@ int tls_sw_sendpage(struct sock *sk, struct page *page,
 
 	if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
 		      MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	mutex_lock(&tls_ctx->tx_lock);
 	lock_sock(sk);
@@ -1927,7 +1927,7 @@ ssize_t tls_sw_splice_read(struct socket *sock,  loff_t *ppos,
 
 		/* splice does not support reading control messages */
 		if (ctx->control != TLS_RECORD_TYPE_DATA) {
-			err = -ENOTSUPP;
+			err = -EINVAL;
 			goto splice_read_end;
 		}
 
diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 46abcae47dee..13e5ef615026 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -25,10 +25,6 @@
 #define TLS_PAYLOAD_MAX_LEN 16384
 #define SOL_TLS 282
 
-#ifndef ENOTSUPP
-#define ENOTSUPP 524
-#endif
-
 FIXTURE(tls_basic)
 {
 	int fd, cfd;
@@ -1205,11 +1201,11 @@ TEST(non_established) {
 	/* TLS ULP not supported */
 	if (errno == ENOENT)
 		return;
-	EXPECT_EQ(errno, ENOTSUPP);
+	EXPECT_EQ(errno, ENOTCONN);
 
 	ret = setsockopt(sfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
 	EXPECT_EQ(ret, -1);
-	EXPECT_EQ(errno, ENOTSUPP);
+	EXPECT_EQ(errno, ENOTCONN);
 
 	ret = getsockname(sfd, &addr, &len);
 	ASSERT_EQ(ret, 0);
-- 
2.20.1


From 1e72642795a4b910740e7984dcf897595bba21ad Mon Sep 17 00:00:00 2001
From: Aaron Conole <aconole@redhat.com>
Date: Tue, 3 Dec 2019 16:34:13 -0500
Subject: [PATCH 11/38] openvswitch: support asymmetric conntrack

[ Upstream commit 5d50aa83e2c8e91ced2cca77c198b468ca9210f4 ]

The openvswitch module shares a common conntrack and NAT infrastructure
exposed via netfilter.  It's possible that a packet needs both SNAT and
DNAT manipulation, due to e.g. tuple collision.  Netfilter can support
this because it runs through the NAT table twice - once on ingress and
again after egress.  The openvswitch module doesn't have such capability.

Like netfilter hook infrastructure, we should run through NAT twice to
keep the symmetry.

Fixes: 05752523e565 ("openvswitch: Interface with NAT.")
Signed-off-by: Aaron Conole <aconole@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/conntrack.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 05249eb45082..283e8f9a5fd2 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -903,6 +903,17 @@ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
 	}
 	err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, maniptype);
 
+	if (err == NF_ACCEPT &&
+	    ct->status & IPS_SRC_NAT && ct->status & IPS_DST_NAT) {
+		if (maniptype == NF_NAT_MANIP_SRC)
+			maniptype = NF_NAT_MANIP_DST;
+		else
+			maniptype = NF_NAT_MANIP_SRC;
+
+		err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range,
+					 maniptype);
+	}
+
 	/* Mark NAT done if successful and update the flow key. */
 	if (err == NF_ACCEPT)
 		ovs_nat_update_key(key, skb, maniptype);
-- 
2.20.1


From 141bd0587c0f19f64c17bb2a88ae968b331d8494 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 5 Dec 2019 10:10:15 -0800
Subject: [PATCH 12/38] tcp: md5: fix potential overestimation of TCP option
 space

[ Upstream commit 9424e2e7ad93ffffa88f882c9bc5023570904b55 ]

Back in 2008, Adam Langley fixed the corner case of packets for flows
having all of the following options : MD5 TS SACK

Since MD5 needs 20 bytes, and TS needs 12 bytes, no sack block
can be cooked from the remaining 8 bytes.

tcp_established_options() correctly sets opts->num_sack_blocks
to zero, but returns 36 instead of 32.

This means TCP cooks packets with 4 extra bytes at the end
of options, containing unitialized bytes.

Fixes: 33ad798c924b ("tcp: options clean up")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 0488607c5cd3..762edd800d78 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -755,8 +755,9 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
 			min_t(unsigned int, eff_sacks,
 			      (remaining - TCPOLEN_SACK_BASE_ALIGNED) /
 			      TCPOLEN_SACK_PERBLOCK);
-		size += TCPOLEN_SACK_BASE_ALIGNED +
-			opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK;
+		if (likely(opts->num_sack_blocks))
+			size += TCPOLEN_SACK_BASE_ALIGNED +
+				opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK;
 	}
 
 	return size;
-- 
2.20.1


From b50875371a9172d8aa064963d13ca6b93cb3cd4f Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Fri, 6 Dec 2019 05:25:48 +0000
Subject: [PATCH 13/38] tipc: fix ordering of tipc module init and exit routine

[ Upstream commit 9cf1cd8ee3ee09ef2859017df2058e2f53c5347f ]

In order to set/get/dump, the tipc uses the generic netlink
infrastructure. So, when tipc module is inserted, init function
calls genl_register_family().
After genl_register_family(), set/get/dump commands are immediately
allowed and these callbacks internally use the net_generic.
net_generic is allocated by register_pernet_device() but this
is called after genl_register_family() in the __init function.
So, these callbacks would use un-initialized net_generic.

Test commands:
    #SHELL1
    while :
    do
        modprobe tipc
        modprobe -rv tipc
    done

    #SHELL2
    while :
    do
        tipc link list
    done

Splat looks like:
[   59.616322][ T2788] kasan: CONFIG_KASAN_INLINE enabled
[   59.617234][ T2788] kasan: GPF could be caused by NULL-ptr deref or user memory access
[   59.618398][ T2788] general protection fault: 0000 [#1] SMP DEBUG_PAGEALLOC KASAN PTI
[   59.619389][ T2788] CPU: 3 PID: 2788 Comm: tipc Not tainted 5.4.0+ #194
[   59.620231][ T2788] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[   59.621428][ T2788] RIP: 0010:tipc_bcast_get_broadcast_mode+0x131/0x310 [tipc]
[   59.622379][ T2788] Code: c7 c6 ef 8b 38 c0 65 ff 0d 84 83 c9 3f e8 d7 a5 f2 e3 48 8d bb 38 11 00 00 48 b8 00 00 00 00
[   59.622550][ T2780] NET: Registered protocol family 30
[   59.624627][ T2788] RSP: 0018:ffff88804b09f578 EFLAGS: 00010202
[   59.624630][ T2788] RAX: dffffc0000000000 RBX: 0000000000000011 RCX: 000000008bc66907
[   59.624631][ T2788] RDX: 0000000000000229 RSI: 000000004b3cf4cc RDI: 0000000000001149
[   59.624633][ T2788] RBP: ffff88804b09f588 R08: 0000000000000003 R09: fffffbfff4fb3df1
[   59.624635][ T2788] R10: fffffbfff50318f8 R11: ffff888066cadc18 R12: ffffffffa6cc2f40
[   59.624637][ T2788] R13: 1ffff11009613eba R14: ffff8880662e9328 R15: ffff8880662e9328
[   59.624639][ T2788] FS:  00007f57d8f7b740(0000) GS:ffff88806cc00000(0000) knlGS:0000000000000000
[   59.624645][ T2788] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   59.625875][ T2780] tipc: Started in single node mode
[   59.626128][ T2788] CR2: 00007f57d887a8c0 CR3: 000000004b140002 CR4: 00000000000606e0
[   59.633991][ T2788] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[   59.635195][ T2788] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[   59.636478][ T2788] Call Trace:
[   59.637025][ T2788]  tipc_nl_add_bc_link+0x179/0x1470 [tipc]
[   59.638219][ T2788]  ? lock_downgrade+0x6e0/0x6e0
[   59.638923][ T2788]  ? __tipc_nl_add_link+0xf90/0xf90 [tipc]
[   59.639533][ T2788]  ? tipc_nl_node_dump_link+0x318/0xa50 [tipc]
[   59.640160][ T2788]  ? mutex_lock_io_nested+0x1380/0x1380
[   59.640746][ T2788]  tipc_nl_node_dump_link+0x4fd/0xa50 [tipc]
[   59.641356][ T2788]  ? tipc_nl_node_reset_link_stats+0x340/0x340 [tipc]
[   59.642088][ T2788]  ? __skb_ext_del+0x270/0x270
[   59.642594][ T2788]  genl_lock_dumpit+0x85/0xb0
[   59.643050][ T2788]  netlink_dump+0x49c/0xed0
[   59.643529][ T2788]  ? __netlink_sendskb+0xc0/0xc0
[   59.644044][ T2788]  ? __netlink_dump_start+0x190/0x800
[   59.644617][ T2788]  ? __mutex_unlock_slowpath+0xd0/0x670
[   59.645177][ T2788]  __netlink_dump_start+0x5a0/0x800
[   59.645692][ T2788]  genl_rcv_msg+0xa75/0xe90
[   59.646144][ T2788]  ? __lock_acquire+0xdfe/0x3de0
[   59.646692][ T2788]  ? genl_family_rcv_msg_attrs_parse+0x320/0x320
[   59.647340][ T2788]  ? genl_lock_dumpit+0xb0/0xb0
[   59.647821][ T2788]  ? genl_unlock+0x20/0x20
[   59.648290][ T2788]  ? genl_parallel_done+0xe0/0xe0
[   59.648787][ T2788]  ? find_held_lock+0x39/0x1d0
[   59.649276][ T2788]  ? genl_rcv+0x15/0x40
[   59.649722][ T2788]  ? lock_contended+0xcd0/0xcd0
[   59.650296][ T2788]  netlink_rcv_skb+0x121/0x350
[   59.650828][ T2788]  ? genl_family_rcv_msg_attrs_parse+0x320/0x320
[   59.651491][ T2788]  ? netlink_ack+0x940/0x940
[   59.651953][ T2788]  ? lock_acquire+0x164/0x3b0
[   59.652449][ T2788]  genl_rcv+0x24/0x40
[   59.652841][ T2788]  netlink_unicast+0x421/0x600
[ ... ]

Fixes: 7e4369057806 ("tipc: fix a slab object leak")
Fixes: a62fbccecd62 ("tipc: make subscriber server support net namespace")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/core.c | 29 +++++++++++++++--------------
 1 file changed, 15 insertions(+), 14 deletions(-)

diff --git a/net/tipc/core.c b/net/tipc/core.c
index 8f35060a24e1..12192e7f4050 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -125,14 +125,6 @@ static int __init tipc_init(void)
 	sysctl_tipc_rmem[1] = RCVBUF_DEF;
 	sysctl_tipc_rmem[2] = RCVBUF_MAX;
 
-	err = tipc_netlink_start();
-	if (err)
-		goto out_netlink;
-
-	err = tipc_netlink_compat_start();
-	if (err)
-		goto out_netlink_compat;
-
 	err = tipc_register_sysctl();
 	if (err)
 		goto out_sysctl;
@@ -153,8 +145,21 @@ static int __init tipc_init(void)
 	if (err)
 		goto out_bearer;
 
+	err = tipc_netlink_start();
+	if (err)
+		goto out_netlink;
+
+	err = tipc_netlink_compat_start();
+	if (err)
+		goto out_netlink_compat;
+
 	pr_info("Started in single node mode\n");
 	return 0;
+
+out_netlink_compat:
+	tipc_netlink_stop();
+out_netlink:
+	tipc_bearer_cleanup();
 out_bearer:
 	unregister_pernet_device(&tipc_topsrv_net_ops);
 out_pernet_topsrv:
@@ -164,22 +169,18 @@ static int __init tipc_init(void)
 out_pernet:
 	tipc_unregister_sysctl();
 out_sysctl:
-	tipc_netlink_compat_stop();
-out_netlink_compat:
-	tipc_netlink_stop();
-out_netlink:
 	pr_err("Unable to start in single node mode\n");
 	return err;
 }
 
 static void __exit tipc_exit(void)
 {
+	tipc_netlink_compat_stop();
+	tipc_netlink_stop();
 	tipc_bearer_cleanup();
 	unregister_pernet_device(&tipc_topsrv_net_ops);
 	tipc_socket_stop();
 	unregister_pernet_device(&tipc_net_ops);
-	tipc_netlink_stop();
-	tipc_netlink_compat_stop();
 	tipc_unregister_sysctl();
 
 	pr_info("Deactivated\n");
-- 
2.20.1


From ecaecf08d9378e996155ed09536f682d2f68501a Mon Sep 17 00:00:00 2001
From: Huy Nguyen <huyn@mellanox.com>
Date: Fri, 6 Sep 2019 09:28:46 -0500
Subject: [PATCH 14/38] net/mlx5e: Query global pause state before setting
 prio2buffer

[ Upstream commit 73e6551699a32fac703ceea09214d6580edcf2d5 ]

When the user changes prio2buffer mapping while global pause is
enabled, mlx5 driver incorrectly sets all active buffers
(buffer that has at least one priority mapped) to lossy.

Solution:
If global pause is enabled, set all the active buffers to lossless
in prio2buffer command.
Also, add error message when buffer size is not enough to meet
xoff threshold.

Fixes: 0696d60853d5 ("net/mlx5e: Receive buffer configuration")
Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../mellanox/mlx5/core/en/port_buffer.c       | 27 +++++++++++++++++--
 1 file changed, 25 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
index 633b117eb13e..99c7cdd0404a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
@@ -155,8 +155,11 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer,
 		}
 
 		if (port_buffer->buffer[i].size <
-		    (xoff + max_mtu + (1 << MLX5E_BUFFER_CELL_SHIFT)))
+		    (xoff + max_mtu + (1 << MLX5E_BUFFER_CELL_SHIFT))) {
+			pr_err("buffer_size[%d]=%d is not enough for lossless buffer\n",
+			       i, port_buffer->buffer[i].size);
 			return -ENOMEM;
+		}
 
 		port_buffer->buffer[i].xoff = port_buffer->buffer[i].size - xoff;
 		port_buffer->buffer[i].xon  =
@@ -232,6 +235,26 @@ static int update_buffer_lossy(unsigned int max_mtu,
 	return 0;
 }
 
+static int fill_pfc_en(struct mlx5_core_dev *mdev, u8 *pfc_en)
+{
+	u32 g_rx_pause, g_tx_pause;
+	int err;
+
+	err = mlx5_query_port_pause(mdev, &g_rx_pause, &g_tx_pause);
+	if (err)
+		return err;
+
+	/* If global pause enabled, set all active buffers to lossless.
+	 * Otherwise, check PFC setting.
+	 */
+	if (g_rx_pause || g_tx_pause)
+		*pfc_en = 0xff;
+	else
+		err = mlx5_query_port_pfc(mdev, pfc_en, NULL);
+
+	return err;
+}
+
 #define MINIMUM_MAX_MTU 9216
 int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 				    u32 change, unsigned int mtu,
@@ -277,7 +300,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 
 	if (change & MLX5E_PORT_BUFFER_PRIO2BUFFER) {
 		update_prio2buffer = true;
-		err = mlx5_query_port_pfc(priv->mdev, &curr_pfc_en, NULL);
+		err = fill_pfc_en(priv->mdev, &curr_pfc_en);
 		if (err)
 			return err;
 
-- 
2.20.1


From 517ee670ad00578210fe11773a145cc3dd102b24 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Wed, 4 Dec 2019 15:35:52 +0100
Subject: [PATCH 15/38] net: ipv6: add net argument to ip6_dst_lookup_flow

[ Upstream commit c4e85f73afb6384123e5ef1bba3315b2e3ad031e ]

This will be used in the conversion of ipv6_stub to ip6_dst_lookup_flow,
as some modules currently pass a net argument without a socket to
ip6_dst_lookup. This is equivalent to commit 343d60aada5a ("ipv6: change
ipv6_stub_impl.ipv6_dst_lookup to take net argument").

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h               | 2 +-
 net/dccp/ipv6.c                  | 6 +++---
 net/ipv6/af_inet6.c              | 2 +-
 net/ipv6/datagram.c              | 2 +-
 net/ipv6/inet6_connection_sock.c | 4 ++--
 net/ipv6/ip6_output.c            | 8 ++++----
 net/ipv6/raw.c                   | 2 +-
 net/ipv6/syncookies.c            | 2 +-
 net/ipv6/tcp_ipv6.c              | 4 ++--
 net/l2tp/l2tp_ip6.c              | 2 +-
 net/sctp/ipv6.c                  | 4 ++--
 11 files changed, 19 insertions(+), 19 deletions(-)

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 009605c56f20..b59b3dae0f71 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -1017,7 +1017,7 @@ static inline struct sk_buff *ip6_finish_skb(struct sock *sk)
 
 int ip6_dst_lookup(struct net *net, struct sock *sk, struct dst_entry **dst,
 		   struct flowi6 *fl6);
-struct dst_entry *ip6_dst_lookup_flow(const struct sock *sk, struct flowi6 *fl6,
+struct dst_entry *ip6_dst_lookup_flow(struct net *net, const struct sock *sk, struct flowi6 *fl6,
 				      const struct in6_addr *final_dst);
 struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
 					 const struct in6_addr *final_dst,
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 25aab672fc99..1e5e08cc0bfc 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -210,7 +210,7 @@ static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req
 	final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final);
 	rcu_read_unlock();
 
-	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
+	dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
 		dst = NULL;
@@ -282,7 +282,7 @@ static void dccp_v6_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb)
 	security_skb_classify_flow(rxskb, flowi6_to_flowi(&fl6));
 
 	/* sk = NULL, but it is safe for now. RST socket required. */
-	dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL);
+	dst = ip6_dst_lookup_flow(sock_net(ctl_sk), ctl_sk, &fl6, NULL);
 	if (!IS_ERR(dst)) {
 		skb_dst_set(skb, dst);
 		ip6_xmit(ctl_sk, skb, &fl6, 0, NULL, 0, 0);
@@ -912,7 +912,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk));
 	final_p = fl6_update_dst(&fl6, opt, &final);
 
-	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
+	dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
 		goto failure;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index ef37e0574f54..9e05b7276022 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -765,7 +765,7 @@ int inet6_sk_rebuild_header(struct sock *sk)
 					 &final);
 		rcu_read_unlock();
 
-		dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
+		dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p);
 		if (IS_ERR(dst)) {
 			sk->sk_route_caps = 0;
 			sk->sk_err_soft = -PTR_ERR(dst);
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 96f939248d2f..390bedde21a5 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -85,7 +85,7 @@ int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr)
 	final_p = fl6_update_dst(&fl6, opt, &final);
 	rcu_read_unlock();
 
-	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
+	dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
 		goto out;
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 0a0945a5b30d..fe9cb8d1adca 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -48,7 +48,7 @@ struct dst_entry *inet6_csk_route_req(const struct sock *sk,
 	fl6->flowi6_uid = sk->sk_uid;
 	security_req_classify_flow(req, flowi6_to_flowi(fl6));
 
-	dst = ip6_dst_lookup_flow(sk, fl6, final_p);
+	dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p);
 	if (IS_ERR(dst))
 		return NULL;
 
@@ -103,7 +103,7 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk,
 
 	dst = __inet6_csk_dst_check(sk, np->dst_cookie);
 	if (!dst) {
-		dst = ip6_dst_lookup_flow(sk, fl6, final_p);
+		dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p);
 
 		if (!IS_ERR(dst))
 			ip6_dst_store(sk, dst, NULL, NULL);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 71827b56c006..78d495581d69 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1144,19 +1144,19 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup);
  *	It returns a valid dst pointer on success, or a pointer encoded
  *	error code.
  */
-struct dst_entry *ip6_dst_lookup_flow(const struct sock *sk, struct flowi6 *fl6,
+struct dst_entry *ip6_dst_lookup_flow(struct net *net, const struct sock *sk, struct flowi6 *fl6,
 				      const struct in6_addr *final_dst)
 {
 	struct dst_entry *dst = NULL;
 	int err;
 
-	err = ip6_dst_lookup_tail(sock_net(sk), sk, &dst, fl6);
+	err = ip6_dst_lookup_tail(net, sk, &dst, fl6);
 	if (err)
 		return ERR_PTR(err);
 	if (final_dst)
 		fl6->daddr = *final_dst;
 
-	return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
+	return xfrm_lookup_route(net, dst, flowi6_to_flowi(fl6), sk, 0);
 }
 EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow);
 
@@ -1188,7 +1188,7 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
 	if (dst)
 		return dst;
 
-	dst = ip6_dst_lookup_flow(sk, fl6, final_dst);
+	dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_dst);
 	if (connected && !IS_ERR(dst))
 		ip6_sk_dst_store_flow(sk, dst_clone(dst), fl6);
 
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index a77f6b7d3a7c..dfe5e603ffe1 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -925,7 +925,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
 
-	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
+	dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
 		goto out;
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 16632e02e9b0..30915f6f31e3 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -235,7 +235,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 		fl6.flowi6_uid = sk->sk_uid;
 		security_req_classify_flow(req, flowi6_to_flowi(&fl6));
 
-		dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
+		dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p);
 		if (IS_ERR(dst))
 			goto out_free;
 	}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 4804b6dc5e65..b42fa41cfceb 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -275,7 +275,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
-	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
+	dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
 		goto failure;
@@ -906,7 +906,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
 	 * Underlying function will use this to retrieve the network
 	 * namespace
 	 */
-	dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL);
+	dst = ip6_dst_lookup_flow(sock_net(ctl_sk), ctl_sk, &fl6, NULL);
 	if (!IS_ERR(dst)) {
 		skb_dst_set(buff, dst);
 		ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL, tclass,
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 802f19aba7e3..d148766f40d1 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -615,7 +615,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
 
-	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
+	dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
 		goto out;
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index dd860fea0148..bc734cfaa29e 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -275,7 +275,7 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 	final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
 	rcu_read_unlock();
 
-	dst = ip6_dst_lookup_flow(sk, fl6, final_p);
+	dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p);
 	if (!asoc || saddr)
 		goto out;
 
@@ -328,7 +328,7 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 		fl6->saddr = laddr->a.v6.sin6_addr;
 		fl6->fl6_sport = laddr->a.v6.sin6_port;
 		final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
-		bdst = ip6_dst_lookup_flow(sk, fl6, final_p);
+		bdst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p);
 
 		if (IS_ERR(bdst))
 			continue;
-- 
2.20.1


From 79cfa1ab6792b5637aae2f78bae2fce8b3ba5676 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Wed, 4 Dec 2019 15:35:53 +0100
Subject: [PATCH 16/38] net: ipv6_stub: use ip6_dst_lookup_flow instead of
 ip6_dst_lookup

[ Upstream commit 6c8991f41546c3c472503dff1ea9daaddf9331c2 ]

ipv6_stub uses the ip6_dst_lookup function to allow other modules to
perform IPv6 lookups. However, this function skips the XFRM layer
entirely.

All users of ipv6_stub->ip6_dst_lookup use ip_route_output_flow (via the
ip_route_output_key and ip_route_output helpers) for their IPv4 lookups,
which calls xfrm_lookup_route(). This patch fixes this inconsistent
behavior by switching the stub to ip6_dst_lookup_flow, which also calls
xfrm_lookup_route().

This requires some changes in all the callers, as these two functions
take different arguments and have different return types.

Fixes: 5f81bd2e5d80 ("ipv6: export a stub for IPv6 symbols used by vxlan")
Reported-by: Xiumei Mu <xmu@redhat.com>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/core/addr.c                      |  7 +++----
 drivers/infiniband/sw/rxe/rxe_net.c                 |  8 +++++---
 drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c |  8 ++++----
 drivers/net/geneve.c                                |  4 +++-
 drivers/net/vxlan.c                                 |  8 +++-----
 include/net/ipv6_stubs.h                            |  6 ++++--
 net/core/lwt_bpf.c                                  |  4 +---
 net/ipv6/addrconf_core.c                            | 11 ++++++-----
 net/ipv6/af_inet6.c                                 |  2 +-
 net/mpls/af_mpls.c                                  |  7 +++----
 net/tipc/udp_media.c                                |  9 ++++++---
 11 files changed, 39 insertions(+), 35 deletions(-)

diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 6d7ec371e7b2..606fa6d86685 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -421,16 +421,15 @@ static int addr6_resolve(struct sockaddr *src_sock,
 				(const struct sockaddr_in6 *)dst_sock;
 	struct flowi6 fl6;
 	struct dst_entry *dst;
-	int ret;
 
 	memset(&fl6, 0, sizeof fl6);
 	fl6.daddr = dst_in->sin6_addr;
 	fl6.saddr = src_in->sin6_addr;
 	fl6.flowi6_oif = addr->bound_dev_if;
 
-	ret = ipv6_stub->ipv6_dst_lookup(addr->net, NULL, &dst, &fl6);
-	if (ret < 0)
-		return ret;
+	dst = ipv6_stub->ipv6_dst_lookup_flow(addr->net, NULL, &fl6, NULL);
+	if (IS_ERR(dst))
+		return PTR_ERR(dst);
 
 	if (ipv6_addr_any(&src_in->sin6_addr))
 		src_in->sin6_addr = fl6.saddr;
diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c
index 5a3474f9351b..312c2fc961c0 100644
--- a/drivers/infiniband/sw/rxe/rxe_net.c
+++ b/drivers/infiniband/sw/rxe/rxe_net.c
@@ -117,10 +117,12 @@ static struct dst_entry *rxe_find_route6(struct net_device *ndev,
 	memcpy(&fl6.daddr, daddr, sizeof(*daddr));
 	fl6.flowi6_proto = IPPROTO_UDP;
 
-	if (unlikely(ipv6_stub->ipv6_dst_lookup(sock_net(recv_sockets.sk6->sk),
-						recv_sockets.sk6->sk, &ndst, &fl6))) {
+	ndst = ipv6_stub->ipv6_dst_lookup_flow(sock_net(recv_sockets.sk6->sk),
+					       recv_sockets.sk6->sk, &fl6,
+					       NULL);
+	if (unlikely(IS_ERR(ndst))) {
 		pr_err_ratelimited("no route to %pI6\n", daddr);
-		goto put;
+		return NULL;
 	}
 
 	if (unlikely(ndst->error)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index 745ab6cd7c30..362f01bc8372 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -144,10 +144,10 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
 #if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6)
 	int ret;
 
-	ret = ipv6_stub->ipv6_dst_lookup(dev_net(mirred_dev), NULL, &dst,
-					 fl6);
-	if (ret < 0)
-		return ret;
+	dst = ipv6_stub->ipv6_dst_lookup_flow(dev_net(mirred_dev), NULL, fl6,
+					      NULL);
+	if (IS_ERR(dst))
+		return PTR_ERR(dst);
 
 	if (!(*out_ttl))
 		*out_ttl = ip6_dst_hoplimit(dst);
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 3ab24fdccd3b..5c6b7fc04ea6 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -853,7 +853,9 @@ static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb,
 		if (dst)
 			return dst;
 	}
-	if (ipv6_stub->ipv6_dst_lookup(geneve->net, gs6->sock->sk, &dst, fl6)) {
+	dst = ipv6_stub->ipv6_dst_lookup_flow(geneve->net, gs6->sock->sk, fl6,
+					      NULL);
+	if (IS_ERR(dst)) {
 		netdev_dbg(dev, "no route to %pI6\n", &fl6->daddr);
 		return ERR_PTR(-ENETUNREACH);
 	}
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 8869154fad88..404ac3a0d1c3 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2276,7 +2276,6 @@ static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan,
 	bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
 	struct dst_entry *ndst;
 	struct flowi6 fl6;
-	int err;
 
 	if (!sock6)
 		return ERR_PTR(-EIO);
@@ -2299,10 +2298,9 @@ static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan,
 	fl6.fl6_dport = dport;
 	fl6.fl6_sport = sport;
 
-	err = ipv6_stub->ipv6_dst_lookup(vxlan->net,
-					 sock6->sock->sk,
-					 &ndst, &fl6);
-	if (unlikely(err < 0)) {
+	ndst = ipv6_stub->ipv6_dst_lookup_flow(vxlan->net, sock6->sock->sk,
+					       &fl6, NULL);
+	if (unlikely(IS_ERR(ndst))) {
 		netdev_dbg(dev, "no route to %pI6\n", daddr);
 		return ERR_PTR(-ENETUNREACH);
 	}
diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h
index 5c93e942c50b..3e7d2c0e79ca 100644
--- a/include/net/ipv6_stubs.h
+++ b/include/net/ipv6_stubs.h
@@ -24,8 +24,10 @@ struct ipv6_stub {
 				 const struct in6_addr *addr);
 	int (*ipv6_sock_mc_drop)(struct sock *sk, int ifindex,
 				 const struct in6_addr *addr);
-	int (*ipv6_dst_lookup)(struct net *net, struct sock *sk,
-			       struct dst_entry **dst, struct flowi6 *fl6);
+	struct dst_entry *(*ipv6_dst_lookup_flow)(struct net *net,
+						  const struct sock *sk,
+						  struct flowi6 *fl6,
+						  const struct in6_addr *final_dst);
 	int (*ipv6_route_input)(struct sk_buff *skb);
 
 	struct fib6_table *(*fib6_get_table)(struct net *net, u32 id);
diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index 74cfb8b5ab33..99a6de52b21d 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -230,9 +230,7 @@ static int bpf_lwt_xmit_reroute(struct sk_buff *skb)
 		fl6.daddr = iph6->daddr;
 		fl6.saddr = iph6->saddr;
 
-		err = ipv6_stub->ipv6_dst_lookup(net, skb->sk, &dst, &fl6);
-		if (unlikely(err))
-			goto err;
+		dst = ipv6_stub->ipv6_dst_lookup_flow(net, skb->sk, &fl6, NULL);
 		if (IS_ERR(dst)) {
 			err = PTR_ERR(dst);
 			goto err;
diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index 2fc079284ca4..ea00ce3d4117 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -129,11 +129,12 @@ int inet6addr_validator_notifier_call_chain(unsigned long val, void *v)
 }
 EXPORT_SYMBOL(inet6addr_validator_notifier_call_chain);
 
-static int eafnosupport_ipv6_dst_lookup(struct net *net, struct sock *u1,
-					struct dst_entry **u2,
-					struct flowi6 *u3)
+static struct dst_entry *eafnosupport_ipv6_dst_lookup_flow(struct net *net,
+							   const struct sock *sk,
+							   struct flowi6 *fl6,
+							   const struct in6_addr *final_dst)
 {
-	return -EAFNOSUPPORT;
+	return ERR_PTR(-EAFNOSUPPORT);
 }
 
 static int eafnosupport_ipv6_route_input(struct sk_buff *skb)
@@ -190,7 +191,7 @@ static int eafnosupport_ip6_del_rt(struct net *net, struct fib6_info *rt)
 }
 
 const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) {
-	.ipv6_dst_lookup   = eafnosupport_ipv6_dst_lookup,
+	.ipv6_dst_lookup_flow = eafnosupport_ipv6_dst_lookup_flow,
 	.ipv6_route_input  = eafnosupport_ipv6_route_input,
 	.fib6_get_table    = eafnosupport_fib6_get_table,
 	.fib6_table_lookup = eafnosupport_fib6_table_lookup,
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 9e05b7276022..14ac1d911287 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -946,7 +946,7 @@ static int ipv6_route_input(struct sk_buff *skb)
 static const struct ipv6_stub ipv6_stub_impl = {
 	.ipv6_sock_mc_join = ipv6_sock_mc_join,
 	.ipv6_sock_mc_drop = ipv6_sock_mc_drop,
-	.ipv6_dst_lookup   = ip6_dst_lookup,
+	.ipv6_dst_lookup_flow = ip6_dst_lookup_flow,
 	.ipv6_route_input  = ipv6_route_input,
 	.fib6_get_table	   = fib6_get_table,
 	.fib6_table_lookup = fib6_table_lookup,
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index c312741df2ce..4701edffb1f7 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -617,16 +617,15 @@ static struct net_device *inet6_fib_lookup_dev(struct net *net,
 	struct net_device *dev;
 	struct dst_entry *dst;
 	struct flowi6 fl6;
-	int err;
 
 	if (!ipv6_stub)
 		return ERR_PTR(-EAFNOSUPPORT);
 
 	memset(&fl6, 0, sizeof(fl6));
 	memcpy(&fl6.daddr, addr, sizeof(struct in6_addr));
-	err = ipv6_stub->ipv6_dst_lookup(net, NULL, &dst, &fl6);
-	if (err)
-		return ERR_PTR(err);
+	dst = ipv6_stub->ipv6_dst_lookup_flow(net, NULL, &fl6, NULL);
+	if (IS_ERR(dst))
+		return ERR_CAST(dst);
 
 	dev = dst->dev;
 	dev_hold(dev);
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index 287df68721df..186c78431217 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -195,10 +195,13 @@ static int tipc_udp_xmit(struct net *net, struct sk_buff *skb,
 				.saddr = src->ipv6,
 				.flowi6_proto = IPPROTO_UDP
 			};
-			err = ipv6_stub->ipv6_dst_lookup(net, ub->ubsock->sk,
-							 &ndst, &fl6);
-			if (err)
+			ndst = ipv6_stub->ipv6_dst_lookup_flow(net,
+							       ub->ubsock->sk,
+							       &fl6, NULL);
+			if (IS_ERR(ndst)) {
+				err = PTR_ERR(ndst);
 				goto tx_error;
+			}
 			dst_cache_set_ip6(cache, ndst, &fl6.saddr);
 		}
 		ttl = ip6_dst_hoplimit(ndst);
-- 
2.20.1


From 422e3df074653fc0153bbc5927b20b377df9038b Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Fri, 6 Dec 2019 12:38:36 +0100
Subject: [PATCH 17/38] tcp: fix rejected syncookies due to stale timestamps

[ Upstream commit 04d26e7b159a396372646a480f4caa166d1b6720 ]

If no synflood happens for a long enough period of time, then the
synflood timestamp isn't refreshed and jiffies can advance so much
that time_after32() can't accurately compare them any more.

Therefore, we can end up in a situation where time_after32(now,
last_overflow + HZ) returns false, just because these two values are
too far apart. In that case, the synflood timestamp isn't updated as
it should be, which can trick tcp_synq_no_recent_overflow() into
rejecting valid syncookies.

For example, let's consider the following scenario on a system
with HZ=1000:

  * The synflood timestamp is 0, either because that's the timestamp
    of the last synflood or, more commonly, because we're working with
    a freshly created socket.

  * We receive a new SYN, which triggers synflood protection. Let's say
    that this happens when jiffies == 2147484649 (that is,
    'synflood timestamp' + HZ + 2^31 + 1).

  * Then tcp_synq_overflow() doesn't update the synflood timestamp,
    because time_after32(2147484649, 1000) returns false.
    With:
      - 2147484649: the value of jiffies, aka. 'now'.
      - 1000: the value of 'last_overflow' + HZ.

  * A bit later, we receive the ACK completing the 3WHS. But
    cookie_v[46]_check() rejects it because tcp_synq_no_recent_overflow()
    says that we're not under synflood. That's because
    time_after32(2147484649, 120000) returns false.
    With:
      - 2147484649: the value of jiffies, aka. 'now'.
      - 120000: the value of 'last_overflow' + TCP_SYNCOOKIE_VALID.

    Of course, in reality jiffies would have increased a bit, but this
    condition will last for the next 119 seconds, which is far enough
    to accommodate for jiffie's growth.

Fix this by updating the overflow timestamp whenever jiffies isn't
within the [last_overflow, last_overflow + HZ] range. That shouldn't
have any performance impact since the update still happens at most once
per second.

Now we're guaranteed to have fresh timestamps while under synflood, so
tcp_synq_no_recent_overflow() can safely use it with time_after32() in
such situations.

Stale timestamps can still make tcp_synq_no_recent_overflow() return
the wrong verdict when not under synflood. This will be handled in the
next patch.

For 64 bits architectures, the problem was introduced with the
conversion of ->tw_ts_recent_stamp to 32 bits integer by commit
cca9bab1b72c ("tcp: use monotonic timestamps for PAWS").
The problem has always been there on 32 bits architectures.

Fixes: cca9bab1b72c ("tcp: use monotonic timestamps for PAWS")
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/time.h | 13 +++++++++++++
 include/net/tcp.h    |  5 +++--
 2 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/include/linux/time.h b/include/linux/time.h
index 27d83fd2ae61..5f3e49978837 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -96,4 +96,17 @@ static inline bool itimerspec64_valid(const struct itimerspec64 *its)
  */
 #define time_after32(a, b)	((s32)((u32)(b) - (u32)(a)) < 0)
 #define time_before32(b, a)	time_after32(a, b)
+
+/**
+ * time_between32 - check if a 32-bit timestamp is within a given time range
+ * @t:	the time which may be within [l,h]
+ * @l:	the lower bound of the range
+ * @h:	the higher bound of the range
+ *
+ * time_before32(t, l, h) returns true if @l <= @t <= @h. All operands are
+ * treated as 32-bit integers.
+ *
+ * Equivalent to !(time_before32(@t, @l) || time_after32(@t, @h)).
+ */
+#define time_between32(t, l, h) ((u32)(h) - (u32)(l) >= (u32)(t) - (u32)(l))
 #endif
diff --git a/include/net/tcp.h b/include/net/tcp.h
index ab4eb5eb5d07..3276a181a66d 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -494,14 +494,15 @@ static inline void tcp_synq_overflow(const struct sock *sk)
 		reuse = rcu_dereference(sk->sk_reuseport_cb);
 		if (likely(reuse)) {
 			last_overflow = READ_ONCE(reuse->synq_overflow_ts);
-			if (time_after32(now, last_overflow + HZ))
+			if (!time_between32(now, last_overflow,
+					    last_overflow + HZ))
 				WRITE_ONCE(reuse->synq_overflow_ts, now);
 			return;
 		}
 	}
 
 	last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
-	if (time_after32(now, last_overflow + HZ))
+	if (!time_between32(now, last_overflow, last_overflow + HZ))
 		tcp_sk(sk)->rx_opt.ts_recent_stamp = now;
 }
 
-- 
2.20.1


From a0708676f8779be8adab5e9bb6563cbba4fc6a55 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Fri, 6 Dec 2019 12:38:43 +0100
Subject: [PATCH 18/38] tcp: tighten acceptance of ACKs not matching a child
 socket

[ Upstream commit cb44a08f8647fd2e8db5cc9ac27cd8355fa392d8 ]

When no synflood occurs, the synflood timestamp isn't updated.
Therefore it can be so old that time_after32() can consider it to be
in the future.

That's a problem for tcp_synq_no_recent_overflow() as it may report
that a recent overflow occurred while, in fact, it's just that jiffies
has grown past 'last_overflow' + TCP_SYNCOOKIE_VALID + 2^31.

Spurious detection of recent overflows lead to extra syncookie
verification in cookie_v[46]_check(). At that point, the verification
should fail and the packet dropped. But we should have dropped the
packet earlier as we didn't even send a syncookie.

Let's refine tcp_synq_no_recent_overflow() to report a recent overflow
only if jiffies is within the
[last_overflow, last_overflow + TCP_SYNCOOKIE_VALID] interval. This
way, no spurious recent overflow is reported when jiffies wraps and
'last_overflow' becomes in the future from the point of view of
time_after32().

However, if jiffies wraps and enters the
[last_overflow, last_overflow + TCP_SYNCOOKIE_VALID] interval (with
'last_overflow' being a stale synflood timestamp), then
tcp_synq_no_recent_overflow() still erroneously reports an
overflow. In such cases, we have to rely on syncookie verification
to drop the packet. We unfortunately have no way to differentiate
between a fresh and a stale syncookie timestamp.

In practice, using last_overflow as lower bound is problematic.
If the synflood timestamp is concurrently updated between the time
we read jiffies and the moment we store the timestamp in
'last_overflow', then 'now' becomes smaller than 'last_overflow' and
tcp_synq_no_recent_overflow() returns true, potentially dropping a
valid syncookie.

Reading jiffies after loading the timestamp could fix the problem,
but that'd require a memory barrier. Let's just accommodate for
potential timestamp growth instead and extend the interval using
'last_overflow - HZ' as lower bound.

Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 3276a181a66d..be7ae98cc7e7 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -518,13 +518,23 @@ static inline bool tcp_synq_no_recent_overflow(const struct sock *sk)
 		reuse = rcu_dereference(sk->sk_reuseport_cb);
 		if (likely(reuse)) {
 			last_overflow = READ_ONCE(reuse->synq_overflow_ts);
-			return time_after32(now, last_overflow +
-					    TCP_SYNCOOKIE_VALID);
+			return !time_between32(now, last_overflow - HZ,
+					       last_overflow +
+					       TCP_SYNCOOKIE_VALID);
 		}
 	}
 
 	last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
-	return time_after32(now, last_overflow + TCP_SYNCOOKIE_VALID);
+
+	/* If last_overflow <= jiffies <= last_overflow + TCP_SYNCOOKIE_VALID,
+	 * then we're under synflood. However, we have to use
+	 * 'last_overflow - HZ' as lower bound. That's because a concurrent
+	 * tcp_synq_overflow() could update .ts_recent_stamp after we read
+	 * jiffies but before we store .ts_recent_stamp into last_overflow,
+	 * which could lead to rejecting a valid syncookie.
+	 */
+	return !time_between32(now, last_overflow - HZ,
+			       last_overflow + TCP_SYNCOOKIE_VALID);
 }
 
 static inline u32 tcp_cookie_time(void)
-- 
2.20.1


From 4a561ddd691d176e83c52519f29f81f9667ab4e4 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Fri, 6 Dec 2019 12:38:49 +0100
Subject: [PATCH 19/38] tcp: Protect accesses to .ts_recent_stamp with
 {READ,WRITE}_ONCE()

[ Upstream commit 721c8dafad26ccfa90ff659ee19755e3377b829d ]

Syncookies borrow the ->rx_opt.ts_recent_stamp field to store the
timestamp of the last synflood. Protect them with READ_ONCE() and
WRITE_ONCE() since reads and writes aren't serialised.

Use of .rx_opt.ts_recent_stamp for storing the synflood timestamp was
introduced by a0f82f64e269 ("syncookies: remove last_synq_overflow from
struct tcp_sock"). But unprotected accesses were already there when
timestamp was stored in .last_synq_overflow.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index be7ae98cc7e7..b2367cfe0bda 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -501,9 +501,9 @@ static inline void tcp_synq_overflow(const struct sock *sk)
 		}
 	}
 
-	last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
+	last_overflow = READ_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp);
 	if (!time_between32(now, last_overflow, last_overflow + HZ))
-		tcp_sk(sk)->rx_opt.ts_recent_stamp = now;
+		WRITE_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp, now);
 }
 
 /* syncookies: no recent synqueue overflow on this listening socket? */
@@ -524,7 +524,7 @@ static inline bool tcp_synq_no_recent_overflow(const struct sock *sk)
 		}
 	}
 
-	last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
+	last_overflow = READ_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp);
 
 	/* If last_overflow <= jiffies <= last_overflow + TCP_SYNCOOKIE_VALID,
 	 * then we're under synflood. However, we have to use
-- 
2.20.1


From 15031116db5661460a29369d7451630cd66485aa Mon Sep 17 00:00:00 2001
From: John Hurley <john.hurley@netronome.com>
Date: Thu, 5 Dec 2019 17:03:34 +0000
Subject: [PATCH 20/38] net: core: rename indirect block ingress cb function

[ Upstream commit dbad3408896c3c5722ec9cda065468b3df16c5bf ]

With indirect blocks, a driver can register for callbacks from a device
that is does not 'own', for example, a tunnel device. When registering to
or unregistering from a new device, a callback is triggered to generate
a bind/unbind event. This, in turn, allows the driver to receive any
existing rules or to properly clean up installed rules.

When first added, it was assumed that all indirect block registrations
would be for ingress offloads. However, the NFP driver can, in some
instances, support clsact qdisc binds for egress offload.

Change the name of the indirect block callback command in flow_offload to
remove the 'ingress' identifier from it. While this does not change
functionality, a follow up patch will implement a more more generic
callback than just those currently just supporting ingress offload.

Fixes: 4d12ba42787b ("nfp: flower: allow offloading of matches on 'internal' ports")
Signed-off-by: John Hurley <john.hurley@netronome.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow_offload.h        | 15 +++++------
 net/core/flow_offload.c           | 45 +++++++++++++++----------------
 net/netfilter/nf_tables_offload.c |  6 ++---
 net/sched/cls_api.c               |  4 +--
 4 files changed, 34 insertions(+), 36 deletions(-)

diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h
index 86c567f531f3..c6f7bd22db60 100644
--- a/include/net/flow_offload.h
+++ b/include/net/flow_offload.h
@@ -380,19 +380,18 @@ static inline void flow_block_init(struct flow_block *flow_block)
 typedef int flow_indr_block_bind_cb_t(struct net_device *dev, void *cb_priv,
 				      enum tc_setup_type type, void *type_data);
 
-typedef void flow_indr_block_ing_cmd_t(struct net_device *dev,
-					flow_indr_block_bind_cb_t *cb,
-					void *cb_priv,
-					enum flow_block_command command);
+typedef void flow_indr_block_cmd_t(struct net_device *dev,
+				   flow_indr_block_bind_cb_t *cb, void *cb_priv,
+				   enum flow_block_command command);
 
-struct flow_indr_block_ing_entry {
-	flow_indr_block_ing_cmd_t *cb;
+struct flow_indr_block_entry {
+	flow_indr_block_cmd_t *cb;
 	struct list_head	list;
 };
 
-void flow_indr_add_block_ing_cb(struct flow_indr_block_ing_entry *entry);
+void flow_indr_add_block_cb(struct flow_indr_block_entry *entry);
 
-void flow_indr_del_block_ing_cb(struct flow_indr_block_ing_entry *entry);
+void flow_indr_del_block_cb(struct flow_indr_block_entry *entry);
 
 int __flow_indr_block_cb_register(struct net_device *dev, void *cb_priv,
 				  flow_indr_block_bind_cb_t *cb,
diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c
index cf52d9c422fa..45b6a59ac124 100644
--- a/net/core/flow_offload.c
+++ b/net/core/flow_offload.c
@@ -283,7 +283,7 @@ int flow_block_cb_setup_simple(struct flow_block_offload *f,
 }
 EXPORT_SYMBOL(flow_block_cb_setup_simple);
 
-static LIST_HEAD(block_ing_cb_list);
+static LIST_HEAD(block_cb_list);
 
 static struct rhashtable indr_setup_block_ht;
 
@@ -391,20 +391,19 @@ static void flow_indr_block_cb_del(struct flow_indr_block_cb *indr_block_cb)
 	kfree(indr_block_cb);
 }
 
-static DEFINE_MUTEX(flow_indr_block_ing_cb_lock);
+static DEFINE_MUTEX(flow_indr_block_cb_lock);
 
-static void flow_block_ing_cmd(struct net_device *dev,
-			       flow_indr_block_bind_cb_t *cb,
-			       void *cb_priv,
-			       enum flow_block_command command)
+static void flow_block_cmd(struct net_device *dev,
+			   flow_indr_block_bind_cb_t *cb, void *cb_priv,
+			   enum flow_block_command command)
 {
-	struct flow_indr_block_ing_entry *entry;
+	struct flow_indr_block_entry *entry;
 
-	mutex_lock(&flow_indr_block_ing_cb_lock);
-	list_for_each_entry(entry, &block_ing_cb_list, list) {
+	mutex_lock(&flow_indr_block_cb_lock);
+	list_for_each_entry(entry, &block_cb_list, list) {
 		entry->cb(dev, cb, cb_priv, command);
 	}
-	mutex_unlock(&flow_indr_block_ing_cb_lock);
+	mutex_unlock(&flow_indr_block_cb_lock);
 }
 
 int __flow_indr_block_cb_register(struct net_device *dev, void *cb_priv,
@@ -424,8 +423,8 @@ int __flow_indr_block_cb_register(struct net_device *dev, void *cb_priv,
 	if (err)
 		goto err_dev_put;
 
-	flow_block_ing_cmd(dev, indr_block_cb->cb, indr_block_cb->cb_priv,
-			   FLOW_BLOCK_BIND);
+	flow_block_cmd(dev, indr_block_cb->cb, indr_block_cb->cb_priv,
+		       FLOW_BLOCK_BIND);
 
 	return 0;
 
@@ -464,8 +463,8 @@ void __flow_indr_block_cb_unregister(struct net_device *dev,
 	if (!indr_block_cb)
 		return;
 
-	flow_block_ing_cmd(dev, indr_block_cb->cb, indr_block_cb->cb_priv,
-			   FLOW_BLOCK_UNBIND);
+	flow_block_cmd(dev, indr_block_cb->cb, indr_block_cb->cb_priv,
+		       FLOW_BLOCK_UNBIND);
 
 	flow_indr_block_cb_del(indr_block_cb);
 	flow_indr_block_dev_put(indr_dev);
@@ -499,21 +498,21 @@ void flow_indr_block_call(struct net_device *dev,
 }
 EXPORT_SYMBOL_GPL(flow_indr_block_call);
 
-void flow_indr_add_block_ing_cb(struct flow_indr_block_ing_entry *entry)
+void flow_indr_add_block_cb(struct flow_indr_block_entry *entry)
 {
-	mutex_lock(&flow_indr_block_ing_cb_lock);
-	list_add_tail(&entry->list, &block_ing_cb_list);
-	mutex_unlock(&flow_indr_block_ing_cb_lock);
+	mutex_lock(&flow_indr_block_cb_lock);
+	list_add_tail(&entry->list, &block_cb_list);
+	mutex_unlock(&flow_indr_block_cb_lock);
 }
-EXPORT_SYMBOL_GPL(flow_indr_add_block_ing_cb);
+EXPORT_SYMBOL_GPL(flow_indr_add_block_cb);
 
-void flow_indr_del_block_ing_cb(struct flow_indr_block_ing_entry *entry)
+void flow_indr_del_block_cb(struct flow_indr_block_entry *entry)
 {
-	mutex_lock(&flow_indr_block_ing_cb_lock);
+	mutex_lock(&flow_indr_block_cb_lock);
 	list_del(&entry->list);
-	mutex_unlock(&flow_indr_block_ing_cb_lock);
+	mutex_unlock(&flow_indr_block_cb_lock);
 }
-EXPORT_SYMBOL_GPL(flow_indr_del_block_ing_cb);
+EXPORT_SYMBOL_GPL(flow_indr_del_block_cb);
 
 static int __init init_flow_indr_rhashtable(void)
 {
diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c
index e25dab8128db..5f6037695dee 100644
--- a/net/netfilter/nf_tables_offload.c
+++ b/net/netfilter/nf_tables_offload.c
@@ -455,7 +455,7 @@ static int nft_offload_netdev_event(struct notifier_block *this,
 	return NOTIFY_DONE;
 }
 
-static struct flow_indr_block_ing_entry block_ing_entry = {
+static struct flow_indr_block_entry block_ing_entry = {
 	.cb	= nft_indr_block_cb,
 	.list	= LIST_HEAD_INIT(block_ing_entry.list),
 };
@@ -472,13 +472,13 @@ int nft_offload_init(void)
 	if (err < 0)
 		return err;
 
-	flow_indr_add_block_ing_cb(&block_ing_entry);
+	flow_indr_add_block_cb(&block_ing_entry);
 
 	return 0;
 }
 
 void nft_offload_exit(void)
 {
-	flow_indr_del_block_ing_cb(&block_ing_entry);
+	flow_indr_del_block_cb(&block_ing_entry);
 	unregister_netdevice_notifier(&nft_offload_netdev_notifier);
 }
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 37c95cefb7de..57045f2490e8 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -3632,7 +3632,7 @@ static struct pernet_operations tcf_net_ops = {
 	.size = sizeof(struct tcf_net),
 };
 
-static struct flow_indr_block_ing_entry block_ing_entry = {
+static struct flow_indr_block_entry block_ing_entry = {
 	.cb = tc_indr_block_get_and_ing_cmd,
 	.list = LIST_HEAD_INIT(block_ing_entry.list),
 };
@@ -3649,7 +3649,7 @@ static int __init tc_filter_init(void)
 	if (err)
 		goto err_register_pernet_subsys;
 
-	flow_indr_add_block_ing_cb(&block_ing_entry);
+	flow_indr_add_block_cb(&block_ing_entry);
 
 	rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_new_tfilter, NULL,
 		      RTNL_FLAG_DOIT_UNLOCKED);
-- 
2.20.1


From 07bcb193ac2d36e31d9f9858038231b996f8e870 Mon Sep 17 00:00:00 2001
From: John Hurley <john.hurley@netronome.com>
Date: Thu, 5 Dec 2019 17:03:35 +0000
Subject: [PATCH 21/38] net: sched: allow indirect blocks to bind to clsact in
 TC

[ Upstream commit 25a443f74bcff2c4d506a39eae62fc15ad7c618a ]

When a device is bound to a clsact qdisc, bind events are triggered to
registered drivers for both ingress and egress. However, if a driver
registers to such a device using the indirect block routines then it is
assumed that it is only interested in ingress offload and so only replays
ingress bind/unbind messages.

The NFP driver supports the offload of some egress filters when
registering to a block with qdisc of type clsact. However, on unregister,
if the block is still active, it will not receive an unbind egress
notification which can prevent proper cleanup of other registered
callbacks.

Modify the indirect block callback command in TC to send messages of
ingress and/or egress bind depending on the qdisc in use. NFP currently
supports egress offload for TC flower offload so the changes are only
added to TC.

Fixes: 4d12ba42787b ("nfp: flower: allow offloading of matches on 'internal' ports")
Signed-off-by: John Hurley <john.hurley@netronome.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 52 ++++++++++++++++++++++++++++-----------------
 1 file changed, 33 insertions(+), 19 deletions(-)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 57045f2490e8..6a0eacafdb19 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -626,15 +626,15 @@ static void tcf_chain_flush(struct tcf_chain *chain, bool rtnl_held)
 static int tcf_block_setup(struct tcf_block *block,
 			   struct flow_block_offload *bo);
 
-static void tc_indr_block_ing_cmd(struct net_device *dev,
-				  struct tcf_block *block,
-				  flow_indr_block_bind_cb_t *cb,
-				  void *cb_priv,
-				  enum flow_block_command command)
+static void tc_indr_block_cmd(struct net_device *dev, struct tcf_block *block,
+			      flow_indr_block_bind_cb_t *cb, void *cb_priv,
+			      enum flow_block_command command, bool ingress)
 {
 	struct flow_block_offload bo = {
 		.command	= command,
-		.binder_type	= FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS,
+		.binder_type	= ingress ?
+				  FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS :
+				  FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS,
 		.net		= dev_net(dev),
 		.block_shared	= tcf_block_non_null_shared(block),
 	};
@@ -652,9 +652,10 @@ static void tc_indr_block_ing_cmd(struct net_device *dev,
 	up_write(&block->cb_lock);
 }
 
-static struct tcf_block *tc_dev_ingress_block(struct net_device *dev)
+static struct tcf_block *tc_dev_block(struct net_device *dev, bool ingress)
 {
 	const struct Qdisc_class_ops *cops;
+	const struct Qdisc_ops *ops;
 	struct Qdisc *qdisc;
 
 	if (!dev_ingress_queue(dev))
@@ -664,24 +665,37 @@ static struct tcf_block *tc_dev_ingress_block(struct net_device *dev)
 	if (!qdisc)
 		return NULL;
 
-	cops = qdisc->ops->cl_ops;
+	ops = qdisc->ops;
+	if (!ops)
+		return NULL;
+
+	if (!ingress && !strcmp("ingress", ops->id))
+		return NULL;
+
+	cops = ops->cl_ops;
 	if (!cops)
 		return NULL;
 
 	if (!cops->tcf_block)
 		return NULL;
 
-	return cops->tcf_block(qdisc, TC_H_MIN_INGRESS, NULL);
+	return cops->tcf_block(qdisc,
+			       ingress ? TC_H_MIN_INGRESS : TC_H_MIN_EGRESS,
+			       NULL);
 }
 
-static void tc_indr_block_get_and_ing_cmd(struct net_device *dev,
-					  flow_indr_block_bind_cb_t *cb,
-					  void *cb_priv,
-					  enum flow_block_command command)
+static void tc_indr_block_get_and_cmd(struct net_device *dev,
+				      flow_indr_block_bind_cb_t *cb,
+				      void *cb_priv,
+				      enum flow_block_command command)
 {
-	struct tcf_block *block = tc_dev_ingress_block(dev);
+	struct tcf_block *block;
+
+	block = tc_dev_block(dev, true);
+	tc_indr_block_cmd(dev, block, cb, cb_priv, command, true);
 
-	tc_indr_block_ing_cmd(dev, block, cb, cb_priv, command);
+	block = tc_dev_block(dev, false);
+	tc_indr_block_cmd(dev, block, cb, cb_priv, command, false);
 }
 
 static void tc_indr_block_call(struct tcf_block *block,
@@ -3632,9 +3646,9 @@ static struct pernet_operations tcf_net_ops = {
 	.size = sizeof(struct tcf_net),
 };
 
-static struct flow_indr_block_entry block_ing_entry = {
-	.cb = tc_indr_block_get_and_ing_cmd,
-	.list = LIST_HEAD_INIT(block_ing_entry.list),
+static struct flow_indr_block_entry block_entry = {
+	.cb = tc_indr_block_get_and_cmd,
+	.list = LIST_HEAD_INIT(block_entry.list),
 };
 
 static int __init tc_filter_init(void)
@@ -3649,7 +3663,7 @@ static int __init tc_filter_init(void)
 	if (err)
 		goto err_register_pernet_subsys;
 
-	flow_indr_add_block_cb(&block_ing_entry);
+	flow_indr_add_block_cb(&block_entry);
 
 	rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_new_tfilter, NULL,
 		      RTNL_FLAG_DOIT_UNLOCKED);
-- 
2.20.1


From 94c4ebe3c31c0a85e33ae21ce4c782aa526662e7 Mon Sep 17 00:00:00 2001
From: Yoshiki Komachi <komachi.yoshiki@gmail.com>
Date: Tue, 3 Dec 2019 19:40:12 +0900
Subject: [PATCH 22/38] cls_flower: Fix the behavior using port ranges with
 hw-offload

[ Upstream commit 8ffb055beae58574d3e77b4bf9d4d15eace1ca27 ]

The recent commit 5c72299fba9d ("net: sched: cls_flower: Classify
packets using port ranges") had added filtering based on port ranges
to tc flower. However the commit missed necessary changes in hw-offload
code, so the feature gave rise to generating incorrect offloaded flow
keys in NIC.

One more detailed example is below:

$ tc qdisc add dev eth0 ingress
$ tc filter add dev eth0 ingress protocol ip flower ip_proto tcp \
  dst_port 100-200 action drop

With the setup above, an exact match filter with dst_port == 0 will be
installed in NIC by hw-offload. IOW, the NIC will have a rule which is
equivalent to the following one.

$ tc qdisc add dev eth0 ingress
$ tc filter add dev eth0 ingress protocol ip flower ip_proto tcp \
  dst_port 0 action drop

The behavior was caused by the flow dissector which extracts packet
data into the flow key in the tc flower. More specifically, regardless
of exact match or specified port ranges, fl_init_dissector() set the
FLOW_DISSECTOR_KEY_PORTS flag in struct flow_dissector to extract port
numbers from skb in skb_flow_dissect() called by fl_classify(). Note
that device drivers received the same struct flow_dissector object as
used in skb_flow_dissect(). Thus, offloaded drivers could not identify
which of these is used because the FLOW_DISSECTOR_KEY_PORTS flag was
set to struct flow_dissector in either case.

This patch adds the new FLOW_DISSECTOR_KEY_PORTS_RANGE flag and the new
tp_range field in struct fl_flow_key to recognize which filters are applied
to offloaded drivers. At this point, when filters based on port ranges
passed to drivers, drivers return the EOPNOTSUPP error because they do
not support the feature (the newly created FLOW_DISSECTOR_KEY_PORTS_RANGE
flag).

Fixes: 5c72299fba9d ("net: sched: cls_flower: Classify packets using port ranges")
Signed-off-by: Yoshiki Komachi <komachi.yoshiki@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow_dissector.h |   1 +
 net/core/flow_dissector.c    |  37 ++++++++---
 net/sched/cls_flower.c       | 118 ++++++++++++++++++++---------------
 3 files changed, 95 insertions(+), 61 deletions(-)

diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index 5cd12276ae21..e5fc8db1f783 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -229,6 +229,7 @@ enum flow_dissector_key_id {
 	FLOW_DISSECTOR_KEY_IPV4_ADDRS, /* struct flow_dissector_key_ipv4_addrs */
 	FLOW_DISSECTOR_KEY_IPV6_ADDRS, /* struct flow_dissector_key_ipv6_addrs */
 	FLOW_DISSECTOR_KEY_PORTS, /* struct flow_dissector_key_ports */
+	FLOW_DISSECTOR_KEY_PORTS_RANGE, /* struct flow_dissector_key_ports */
 	FLOW_DISSECTOR_KEY_ICMP, /* struct flow_dissector_key_icmp */
 	FLOW_DISSECTOR_KEY_ETH_ADDRS, /* struct flow_dissector_key_eth_addrs */
 	FLOW_DISSECTOR_KEY_TIPC, /* struct flow_dissector_key_tipc */
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index c206d1cb6ec1..1292f3f0f93f 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -683,6 +683,31 @@ __skb_flow_dissect_tcp(const struct sk_buff *skb,
 	key_tcp->flags = (*(__be16 *) &tcp_flag_word(th) & htons(0x0FFF));
 }
 
+static void
+__skb_flow_dissect_ports(const struct sk_buff *skb,
+			 struct flow_dissector *flow_dissector,
+			 void *target_container, void *data, int nhoff,
+			 u8 ip_proto, int hlen)
+{
+	enum flow_dissector_key_id dissector_ports = FLOW_DISSECTOR_KEY_MAX;
+	struct flow_dissector_key_ports *key_ports;
+
+	if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS))
+		dissector_ports = FLOW_DISSECTOR_KEY_PORTS;
+	else if (dissector_uses_key(flow_dissector,
+				    FLOW_DISSECTOR_KEY_PORTS_RANGE))
+		dissector_ports = FLOW_DISSECTOR_KEY_PORTS_RANGE;
+
+	if (dissector_ports == FLOW_DISSECTOR_KEY_MAX)
+		return;
+
+	key_ports = skb_flow_dissector_target(flow_dissector,
+					      dissector_ports,
+					      target_container);
+	key_ports->ports = __skb_flow_get_ports(skb, nhoff, ip_proto,
+						data, hlen);
+}
+
 static void
 __skb_flow_dissect_ipv4(const struct sk_buff *skb,
 			struct flow_dissector *flow_dissector,
@@ -852,7 +877,6 @@ bool __skb_flow_dissect(const struct net *net,
 	struct flow_dissector_key_control *key_control;
 	struct flow_dissector_key_basic *key_basic;
 	struct flow_dissector_key_addrs *key_addrs;
-	struct flow_dissector_key_ports *key_ports;
 	struct flow_dissector_key_icmp *key_icmp;
 	struct flow_dissector_key_tags *key_tags;
 	struct flow_dissector_key_vlan *key_vlan;
@@ -1300,14 +1324,9 @@ bool __skb_flow_dissect(const struct net *net,
 		break;
 	}
 
-	if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS) &&
-	    !(key_control->flags & FLOW_DIS_IS_FRAGMENT)) {
-		key_ports = skb_flow_dissector_target(flow_dissector,
-						      FLOW_DISSECTOR_KEY_PORTS,
-						      target_container);
-		key_ports->ports = __skb_flow_get_ports(skb, nhoff, ip_proto,
-							data, hlen);
-	}
+	if (!(key_control->flags & FLOW_DIS_IS_FRAGMENT))
+		__skb_flow_dissect_ports(skb, flow_dissector, target_container,
+					 data, nhoff, ip_proto, hlen);
 
 	if (dissector_uses_key(flow_dissector,
 			       FLOW_DISSECTOR_KEY_ICMP)) {
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 74221e3351c3..4ac110bf19c5 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -54,8 +54,13 @@ struct fl_flow_key {
 	struct flow_dissector_key_ip ip;
 	struct flow_dissector_key_ip enc_ip;
 	struct flow_dissector_key_enc_opts enc_opts;
-	struct flow_dissector_key_ports tp_min;
-	struct flow_dissector_key_ports tp_max;
+	union {
+		struct flow_dissector_key_ports tp;
+		struct {
+			struct flow_dissector_key_ports tp_min;
+			struct flow_dissector_key_ports tp_max;
+		};
+	} tp_range;
 	struct flow_dissector_key_ct ct;
 } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */
 
@@ -198,19 +203,19 @@ static bool fl_range_port_dst_cmp(struct cls_fl_filter *filter,
 {
 	__be16 min_mask, max_mask, min_val, max_val;
 
-	min_mask = htons(filter->mask->key.tp_min.dst);
-	max_mask = htons(filter->mask->key.tp_max.dst);
-	min_val = htons(filter->key.tp_min.dst);
-	max_val = htons(filter->key.tp_max.dst);
+	min_mask = htons(filter->mask->key.tp_range.tp_min.dst);
+	max_mask = htons(filter->mask->key.tp_range.tp_max.dst);
+	min_val = htons(filter->key.tp_range.tp_min.dst);
+	max_val = htons(filter->key.tp_range.tp_max.dst);
 
 	if (min_mask && max_mask) {
-		if (htons(key->tp.dst) < min_val ||
-		    htons(key->tp.dst) > max_val)
+		if (htons(key->tp_range.tp.dst) < min_val ||
+		    htons(key->tp_range.tp.dst) > max_val)
 			return false;
 
 		/* skb does not have min and max values */
-		mkey->tp_min.dst = filter->mkey.tp_min.dst;
-		mkey->tp_max.dst = filter->mkey.tp_max.dst;
+		mkey->tp_range.tp_min.dst = filter->mkey.tp_range.tp_min.dst;
+		mkey->tp_range.tp_max.dst = filter->mkey.tp_range.tp_max.dst;
 	}
 	return true;
 }
@@ -221,19 +226,19 @@ static bool fl_range_port_src_cmp(struct cls_fl_filter *filter,
 {
 	__be16 min_mask, max_mask, min_val, max_val;
 
-	min_mask = htons(filter->mask->key.tp_min.src);
-	max_mask = htons(filter->mask->key.tp_max.src);
-	min_val = htons(filter->key.tp_min.src);
-	max_val = htons(filter->key.tp_max.src);
+	min_mask = htons(filter->mask->key.tp_range.tp_min.src);
+	max_mask = htons(filter->mask->key.tp_range.tp_max.src);
+	min_val = htons(filter->key.tp_range.tp_min.src);
+	max_val = htons(filter->key.tp_range.tp_max.src);
 
 	if (min_mask && max_mask) {
-		if (htons(key->tp.src) < min_val ||
-		    htons(key->tp.src) > max_val)
+		if (htons(key->tp_range.tp.src) < min_val ||
+		    htons(key->tp_range.tp.src) > max_val)
 			return false;
 
 		/* skb does not have min and max values */
-		mkey->tp_min.src = filter->mkey.tp_min.src;
-		mkey->tp_max.src = filter->mkey.tp_max.src;
+		mkey->tp_range.tp_min.src = filter->mkey.tp_range.tp_min.src;
+		mkey->tp_range.tp_max.src = filter->mkey.tp_range.tp_max.src;
 	}
 	return true;
 }
@@ -715,23 +720,25 @@ static void fl_set_key_val(struct nlattr **tb,
 static int fl_set_key_port_range(struct nlattr **tb, struct fl_flow_key *key,
 				 struct fl_flow_key *mask)
 {
-	fl_set_key_val(tb, &key->tp_min.dst,
-		       TCA_FLOWER_KEY_PORT_DST_MIN, &mask->tp_min.dst,
-		       TCA_FLOWER_UNSPEC, sizeof(key->tp_min.dst));
-	fl_set_key_val(tb, &key->tp_max.dst,
-		       TCA_FLOWER_KEY_PORT_DST_MAX, &mask->tp_max.dst,
-		       TCA_FLOWER_UNSPEC, sizeof(key->tp_max.dst));
-	fl_set_key_val(tb, &key->tp_min.src,
-		       TCA_FLOWER_KEY_PORT_SRC_MIN, &mask->tp_min.src,
-		       TCA_FLOWER_UNSPEC, sizeof(key->tp_min.src));
-	fl_set_key_val(tb, &key->tp_max.src,
-		       TCA_FLOWER_KEY_PORT_SRC_MAX, &mask->tp_max.src,
-		       TCA_FLOWER_UNSPEC, sizeof(key->tp_max.src));
-
-	if ((mask->tp_min.dst && mask->tp_max.dst &&
-	     htons(key->tp_max.dst) <= htons(key->tp_min.dst)) ||
-	     (mask->tp_min.src && mask->tp_max.src &&
-	      htons(key->tp_max.src) <= htons(key->tp_min.src)))
+	fl_set_key_val(tb, &key->tp_range.tp_min.dst,
+		       TCA_FLOWER_KEY_PORT_DST_MIN, &mask->tp_range.tp_min.dst,
+		       TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_min.dst));
+	fl_set_key_val(tb, &key->tp_range.tp_max.dst,
+		       TCA_FLOWER_KEY_PORT_DST_MAX, &mask->tp_range.tp_max.dst,
+		       TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_max.dst));
+	fl_set_key_val(tb, &key->tp_range.tp_min.src,
+		       TCA_FLOWER_KEY_PORT_SRC_MIN, &mask->tp_range.tp_min.src,
+		       TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_min.src));
+	fl_set_key_val(tb, &key->tp_range.tp_max.src,
+		       TCA_FLOWER_KEY_PORT_SRC_MAX, &mask->tp_range.tp_max.src,
+		       TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_max.src));
+
+	if ((mask->tp_range.tp_min.dst && mask->tp_range.tp_max.dst &&
+	     htons(key->tp_range.tp_max.dst) <=
+		 htons(key->tp_range.tp_min.dst)) ||
+	    (mask->tp_range.tp_min.src && mask->tp_range.tp_max.src &&
+	     htons(key->tp_range.tp_max.src) <=
+		 htons(key->tp_range.tp_min.src)))
 		return -EINVAL;
 
 	return 0;
@@ -1320,9 +1327,10 @@ static void fl_init_dissector(struct flow_dissector *dissector,
 			     FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4);
 	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
 			     FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6);
-	if (FL_KEY_IS_MASKED(mask, tp) ||
-	    FL_KEY_IS_MASKED(mask, tp_min) || FL_KEY_IS_MASKED(mask, tp_max))
-		FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_PORTS, tp);
+	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
+			     FLOW_DISSECTOR_KEY_PORTS, tp);
+	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
+			     FLOW_DISSECTOR_KEY_PORTS_RANGE, tp_range);
 	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
 			     FLOW_DISSECTOR_KEY_IP, ip);
 	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
@@ -1371,8 +1379,10 @@ static struct fl_flow_mask *fl_create_new_mask(struct cls_fl_head *head,
 
 	fl_mask_copy(newmask, mask);
 
-	if ((newmask->key.tp_min.dst && newmask->key.tp_max.dst) ||
-	    (newmask->key.tp_min.src && newmask->key.tp_max.src))
+	if ((newmask->key.tp_range.tp_min.dst &&
+	     newmask->key.tp_range.tp_max.dst) ||
+	    (newmask->key.tp_range.tp_min.src &&
+	     newmask->key.tp_range.tp_max.src))
 		newmask->flags |= TCA_FLOWER_MASK_FLAGS_RANGE;
 
 	err = fl_init_mask_hashtable(newmask);
@@ -1970,18 +1980,22 @@ static int fl_dump_key_val(struct sk_buff *skb,
 static int fl_dump_key_port_range(struct sk_buff *skb, struct fl_flow_key *key,
 				  struct fl_flow_key *mask)
 {
-	if (fl_dump_key_val(skb, &key->tp_min.dst, TCA_FLOWER_KEY_PORT_DST_MIN,
-			    &mask->tp_min.dst, TCA_FLOWER_UNSPEC,
-			    sizeof(key->tp_min.dst)) ||
-	    fl_dump_key_val(skb, &key->tp_max.dst, TCA_FLOWER_KEY_PORT_DST_MAX,
-			    &mask->tp_max.dst, TCA_FLOWER_UNSPEC,
-			    sizeof(key->tp_max.dst)) ||
-	    fl_dump_key_val(skb, &key->tp_min.src, TCA_FLOWER_KEY_PORT_SRC_MIN,
-			    &mask->tp_min.src, TCA_FLOWER_UNSPEC,
-			    sizeof(key->tp_min.src)) ||
-	    fl_dump_key_val(skb, &key->tp_max.src, TCA_FLOWER_KEY_PORT_SRC_MAX,
-			    &mask->tp_max.src, TCA_FLOWER_UNSPEC,
-			    sizeof(key->tp_max.src)))
+	if (fl_dump_key_val(skb, &key->tp_range.tp_min.dst,
+			    TCA_FLOWER_KEY_PORT_DST_MIN,
+			    &mask->tp_range.tp_min.dst, TCA_FLOWER_UNSPEC,
+			    sizeof(key->tp_range.tp_min.dst)) ||
+	    fl_dump_key_val(skb, &key->tp_range.tp_max.dst,
+			    TCA_FLOWER_KEY_PORT_DST_MAX,
+			    &mask->tp_range.tp_max.dst, TCA_FLOWER_UNSPEC,
+			    sizeof(key->tp_range.tp_max.dst)) ||
+	    fl_dump_key_val(skb, &key->tp_range.tp_min.src,
+			    TCA_FLOWER_KEY_PORT_SRC_MIN,
+			    &mask->tp_range.tp_min.src, TCA_FLOWER_UNSPEC,
+			    sizeof(key->tp_range.tp_min.src)) ||
+	    fl_dump_key_val(skb, &key->tp_range.tp_max.src,
+			    TCA_FLOWER_KEY_PORT_SRC_MAX,
+			    &mask->tp_range.tp_max.src, TCA_FLOWER_UNSPEC,
+			    sizeof(key->tp_range.tp_max.src)))
 		return -1;
 
 	return 0;
-- 
2.20.1


From fb806a3e9e5dd4d56df3f26a6d733b3b0ce74adc Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 5 Dec 2019 19:39:02 -0800
Subject: [PATCH 23/38] gre: refetch erspan header from skb->data after
 pskb_may_pull()

[ Upstream commit 0e4940928c26527ce8f97237fef4c8a91cd34207 ]

After pskb_may_pull() we should always refetch the header
pointers from the skb->data in case it got reallocated.

In gre_parse_header(), the erspan header is still fetched
from the 'options' pointer which is fetched before
pskb_may_pull().

Found this during code review of a KMSAN bug report.

Fixes: cb73ee40b1b3 ("net: ip_gre: use erspan key field for tunnel lookup")
Cc: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Acked-by: William Tu <u9012063@gmail.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/gre_demux.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c
index 44bfeecac33e..5fd6e8ed02b5 100644
--- a/net/ipv4/gre_demux.c
+++ b/net/ipv4/gre_demux.c
@@ -127,7 +127,7 @@ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 		if (!pskb_may_pull(skb, nhs + hdr_len + sizeof(*ershdr)))
 			return -EINVAL;
 
-		ershdr = (struct erspan_base_hdr *)options;
+		ershdr = (struct erspan_base_hdr *)(skb->data + nhs + hdr_len);
 		tpi->key = cpu_to_be32(get_session_id(ershdr));
 	}
 
-- 
2.20.1


From 924b00d75026b17dcb9794296cd77d2a8cbcd430 Mon Sep 17 00:00:00 2001
From: Martin Varghese <martin.varghese@nokia.com>
Date: Mon, 2 Dec 2019 10:49:51 +0530
Subject: [PATCH 24/38] Fixed updating of ethertype in function skb_mpls_pop

[ Upstream commit 040b5cfbcefa263ccf2c118c4938308606bb7ed8 ]

The skb_mpls_pop was not updating ethertype of an ethernet packet if the
packet was originally received from a non ARPHRD_ETHER device.

In the below OVS data path flow, since the device corresponding to port 7
is an l3 device (ARPHRD_NONE) the skb_mpls_pop function does not update
the ethertype of the packet even though the previous push_eth action had
added an ethernet header to the packet.

recirc_id(0),in_port(7),eth_type(0x8847),
mpls(label=12/0xfffff,tc=0/0,ttl=0/0x0,bos=1/1),
actions:push_eth(src=00:00:00:00:00:00,dst=00:00:00:00:00:00),
pop_mpls(eth_type=0x800),4

Fixes: ed246cee09b9 ("net: core: move pop MPLS functionality from OvS to core helper")
Signed-off-by: Martin Varghese <martin.varghese@nokia.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h    | 3 ++-
 net/core/skbuff.c         | 6 ++++--
 net/openvswitch/actions.c | 3 ++-
 net/sched/act_mpls.c      | 4 +++-
 4 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 8688f7adfda7..026d48df12f8 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3528,7 +3528,8 @@ int skb_vlan_pop(struct sk_buff *skb);
 int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci);
 int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto,
 		  int mac_len);
-int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len);
+int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len,
+		 bool ethernet);
 int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse);
 int skb_mpls_dec_ttl(struct sk_buff *skb);
 struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy,
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 867e61df00db..312e80e86898 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5529,12 +5529,14 @@ EXPORT_SYMBOL_GPL(skb_mpls_push);
  * @skb: buffer
  * @next_proto: ethertype of header after popped MPLS header
  * @mac_len: length of the MAC header
+ * @ethernet: flag to indicate if ethernet header is present in packet
  *
  * Expects skb->data at mac header.
  *
  * Returns 0 on success, -errno otherwise.
  */
-int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len)
+int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len,
+		 bool ethernet)
 {
 	int err;
 
@@ -5553,7 +5555,7 @@ int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len)
 	skb_reset_mac_header(skb);
 	skb_set_network_header(skb, mac_len);
 
-	if (skb->dev && skb->dev->type == ARPHRD_ETHER) {
+	if (ethernet) {
 		struct ethhdr *hdr;
 
 		/* use mpls_hdr() to get ethertype to account for VLANs. */
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 1c77f520f474..fd54a2eb833b 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -179,7 +179,8 @@ static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key,
 {
 	int err;
 
-	err = skb_mpls_pop(skb, ethertype, skb->mac_len);
+	err = skb_mpls_pop(skb, ethertype, skb->mac_len,
+			   ovs_key_mac_proto(key) == MAC_PROTO_ETHERNET);
 	if (err)
 		return err;
 
diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c
index 4cf6c553bb0b..bf74a6c4990c 100644
--- a/net/sched/act_mpls.c
+++ b/net/sched/act_mpls.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 /* Copyright (C) 2019 Netronome Systems, Inc. */
 
+#include <linux/if_arp.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -76,7 +77,8 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a,
 
 	switch (p->tcfm_action) {
 	case TCA_MPLS_ACT_POP:
-		if (skb_mpls_pop(skb, p->tcfm_proto, mac_len))
+		if (skb_mpls_pop(skb, p->tcfm_proto, mac_len,
+				 skb->dev && skb->dev->type == ARPHRD_ETHER))
 			goto drop;
 		break;
 	case TCA_MPLS_ACT_PUSH:
-- 
2.20.1


From 0f9ee542a89ea7a405923893065db6cda6d2a675 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Thu, 5 Dec 2019 07:23:39 +0000
Subject: [PATCH 25/38] hsr: fix a NULL pointer dereference in hsr_dev_xmit()

[ Upstream commit df95467b6d2bfce49667ee4b71c67249b01957f7 ]

hsr_dev_xmit() calls hsr_port_get_hsr() to find master node and that would
return NULL if master node is not existing in the list.
But hsr_dev_xmit() doesn't check return pointer so a NULL dereference
could occur.

Test commands:
    ip netns add nst
    ip link add veth0 type veth peer name veth1
    ip link add veth2 type veth peer name veth3
    ip link set veth1 netns nst
    ip link set veth3 netns nst
    ip link set veth0 up
    ip link set veth2 up
    ip link add hsr0 type hsr slave1 veth0 slave2 veth2
    ip a a 192.168.100.1/24 dev hsr0
    ip link set hsr0 up
    ip netns exec nst ip link set veth1 up
    ip netns exec nst ip link set veth3 up
    ip netns exec nst ip link add hsr1 type hsr slave1 veth1 slave2 veth3
    ip netns exec nst ip a a 192.168.100.2/24 dev hsr1
    ip netns exec nst ip link set hsr1 up
    hping3 192.168.100.2 -2 --flood &
    modprobe -rv hsr

Splat looks like:
[  217.351122][ T1635] kasan: CONFIG_KASAN_INLINE enabled
[  217.352969][ T1635] kasan: GPF could be caused by NULL-ptr deref or user memory access
[  217.354297][ T1635] general protection fault: 0000 [#1] SMP DEBUG_PAGEALLOC KASAN PTI
[  217.355507][ T1635] CPU: 1 PID: 1635 Comm: hping3 Not tainted 5.4.0+ #192
[  217.356472][ T1635] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[  217.357804][ T1635] RIP: 0010:hsr_dev_xmit+0x34/0x90 [hsr]
[  217.373010][ T1635] Code: 48 8d be 00 0c 00 00 be 04 00 00 00 48 83 ec 08 e8 21 be ff ff 48 8d 78 10 48 ba 00 b
[  217.376919][ T1635] RSP: 0018:ffff8880cd8af058 EFLAGS: 00010202
[  217.377571][ T1635] RAX: 0000000000000000 RBX: ffff8880acde6840 RCX: 0000000000000002
[  217.379465][ T1635] RDX: dffffc0000000000 RSI: 0000000000000004 RDI: 0000000000000010
[  217.380274][ T1635] RBP: ffff8880acde6840 R08: ffffed101b440d5d R09: 0000000000000001
[  217.381078][ T1635] R10: 0000000000000001 R11: ffffed101b440d5c R12: ffff8880bffcc000
[  217.382023][ T1635] R13: ffff8880bffcc088 R14: 0000000000000000 R15: ffff8880ca675c00
[  217.383094][ T1635] FS:  00007f060d9d1740(0000) GS:ffff8880da000000(0000) knlGS:0000000000000000
[  217.384289][ T1635] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  217.385009][ T1635] CR2: 00007faf15381dd0 CR3: 00000000d523c001 CR4: 00000000000606e0
[  217.385940][ T1635] Call Trace:
[  217.386544][ T1635]  dev_hard_start_xmit+0x160/0x740
[  217.387114][ T1635]  __dev_queue_xmit+0x1961/0x2e10
[  217.388118][ T1635]  ? check_object+0xaf/0x260
[  217.391466][ T1635]  ? __alloc_skb+0xb9/0x500
[  217.392017][ T1635]  ? init_object+0x6b/0x80
[  217.392629][ T1635]  ? netdev_core_pick_tx+0x2e0/0x2e0
[  217.393175][ T1635]  ? __alloc_skb+0xb9/0x500
[  217.393727][ T1635]  ? rcu_read_lock_sched_held+0x90/0xc0
[  217.394331][ T1635]  ? rcu_read_lock_bh_held+0xa0/0xa0
[  217.395013][ T1635]  ? kasan_unpoison_shadow+0x30/0x40
[  217.395668][ T1635]  ? __kasan_kmalloc.constprop.4+0xa0/0xd0
[  217.396280][ T1635]  ? __kmalloc_node_track_caller+0x3a8/0x3f0
[  217.399007][ T1635]  ? __kasan_kmalloc.constprop.4+0xa0/0xd0
[  217.400093][ T1635]  ? __kmalloc_reserve.isra.46+0x2e/0xb0
[  217.401118][ T1635]  ? memset+0x1f/0x40
[  217.402529][ T1635]  ? __alloc_skb+0x317/0x500
[  217.404915][ T1635]  ? arp_xmit+0xca/0x2c0
[ ... ]

Fixes: 311633b60406 ("hsr: switch ->dellink() to ->ndo_uninit()")
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/hsr/hsr_device.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index f509b495451a..b01e1bae4ddc 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -227,8 +227,13 @@ static int hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct hsr_port *master;
 
 	master = hsr_port_get_hsr(hsr, HSR_PT_MASTER);
-	skb->dev = master->dev;
-	hsr_forward_skb(skb, master);
+	if (master) {
+		skb->dev = master->dev;
+		hsr_forward_skb(skb, master);
+	} else {
+		atomic_long_inc(&dev->tx_dropped);
+		dev_kfree_skb_any(skb);
+	}
 	return NETDEV_TX_OK;
 }
 
-- 
2.20.1


From 71188bed6f98ce64fa3bb236a9de5f78ed0025e7 Mon Sep 17 00:00:00 2001
From: Martin Varghese <martin.varghese@nokia.com>
Date: Thu, 5 Dec 2019 05:57:22 +0530
Subject: [PATCH 26/38] net: Fixed updating of ethertype in skb_mpls_push()

[ Upstream commit d04ac224b1688f005a84f764cfe29844f8e9da08 ]

The skb_mpls_push was not updating ethertype of an ethernet packet if
the packet was originally received from a non ARPHRD_ETHER device.

In the below OVS data path flow, since the device corresponding to
port 7 is an l3 device (ARPHRD_NONE) the skb_mpls_push function does
not update the ethertype of the packet even though the previous
push_eth action had added an ethernet header to the packet.

recirc_id(0),in_port(7),eth_type(0x0800),ipv4(tos=0/0xfc,ttl=64,frag=no),
actions:push_eth(src=00:00:00:00:00:00,dst=00:00:00:00:00:00),
push_mpls(label=13,tc=0,ttl=64,bos=1,eth_type=0x8847),4

Fixes: 8822e270d697 ("net: core: move push MPLS functionality from OvS to core helper")
Signed-off-by: Martin Varghese <martin.varghese@nokia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h    | 2 +-
 net/core/skbuff.c         | 4 ++--
 net/openvswitch/actions.c | 3 ++-
 net/sched/act_mpls.c      | 3 ++-
 4 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 026d48df12f8..1ba6e2cc2725 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3527,7 +3527,7 @@ int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci);
 int skb_vlan_pop(struct sk_buff *skb);
 int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci);
 int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto,
-		  int mac_len);
+		  int mac_len, bool ethernet);
 int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len,
 		 bool ethernet);
 int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 312e80e86898..973a71f4bc89 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5484,7 +5484,7 @@ static void skb_mod_eth_type(struct sk_buff *skb, struct ethhdr *hdr,
  * Returns 0 on success, -errno otherwise.
  */
 int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto,
-		  int mac_len)
+		  int mac_len, bool ethernet)
 {
 	struct mpls_shim_hdr *lse;
 	int err;
@@ -5515,7 +5515,7 @@ int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto,
 	lse->label_stack_entry = mpls_lse;
 	skb_postpush_rcsum(skb, lse, MPLS_HLEN);
 
-	if (skb->dev && skb->dev->type == ARPHRD_ETHER)
+	if (ethernet)
 		skb_mod_eth_type(skb, eth_hdr(skb), mpls_proto);
 	skb->protocol = mpls_proto;
 
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index fd54a2eb833b..99352f09deaa 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -166,7 +166,8 @@ static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key,
 	int err;
 
 	err = skb_mpls_push(skb, mpls->mpls_lse, mpls->mpls_ethertype,
-			    skb->mac_len);
+			    skb->mac_len,
+			    ovs_key_mac_proto(key) == MAC_PROTO_ETHERNET);
 	if (err)
 		return err;
 
diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c
index bf74a6c4990c..db570d2bd0e0 100644
--- a/net/sched/act_mpls.c
+++ b/net/sched/act_mpls.c
@@ -83,7 +83,8 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a,
 		break;
 	case TCA_MPLS_ACT_PUSH:
 		new_lse = tcf_mpls_get_lse(NULL, p, !eth_p_mpls(skb->protocol));
-		if (skb_mpls_push(skb, new_lse, p->tcfm_proto, mac_len))
+		if (skb_mpls_push(skb, new_lse, p->tcfm_proto, mac_len,
+				  skb->dev && skb->dev->type == ARPHRD_ETHER))
 			goto drop;
 		break;
 	case TCA_MPLS_ACT_MODIFY:
-- 
2.20.1


From 66d2608fcd6ed0c83d8a9b6dc14c12589062af3c Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Mon, 25 Nov 2019 12:11:49 +0200
Subject: [PATCH 27/38] net/mlx5e: Fix TXQ indices to be sequential

[ Upstream commit c55d8b108caa2ec1ae8dddd02cb9d3a740f7c838 ]

Cited patch changed (channel index, tc) => (TXQ index) mapping to be a
static one, in order to keep indices consistent when changing number of
channels or TCs.

For 32 channels (OOB) and 8 TCs, real num of TXQs is 256.
When reducing the amount of channels to 8, the real num of TXQs will be
changed to 64.
This indices method is buggy:
- Channel #0, TC 3, the TXQ index is 96.
- Index 8 is not valid, as there is no such TXQ from driver perspective
  (As it represents channel #8, TC 0, which is not valid with the above
  configuration).

As part of driver's select queue, it calls netdev_pick_tx which returns an
index in the range of real number of TXQs. Depends on the return value,
with the examples above, driver could have returned index larger than the
real number of tx queues, or crash the kernel as it tries to read invalid
address of SQ which was not allocated.

Fix that by allocating sequential TXQ indices, and hold a new mapping
between (channel index, tc) => (real TXQ index). This mapping will be
updated as part of priv channels activation, and is used in
mlx5e_select_queue to find the selected queue index.

The existing indices mapping (channel_tc2txq) is no longer needed, as it
is used only for statistics structures and can be calculated on run time.
Delete its definintion and updates.

Fixes: 8bfaf07f7806 ("net/mlx5e: Present SW stats when state is not opened")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h  |  2 +-
 .../net/ethernet/mellanox/mlx5/core/en_main.c | 31 +++++++------------
 .../ethernet/mellanox/mlx5/core/en_stats.c    |  2 +-
 .../net/ethernet/mellanox/mlx5/core/en_tx.c   |  2 +-
 4 files changed, 15 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index f1a7bc46f1c0..2c16add0b642 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -816,7 +816,7 @@ struct mlx5e_xsk {
 struct mlx5e_priv {
 	/* priv data path fields - start */
 	struct mlx5e_txqsq *txq2sq[MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC];
-	int channel_tc2txq[MLX5E_MAX_NUM_CHANNELS][MLX5E_MAX_NUM_TC];
+	int channel_tc2realtxq[MLX5E_MAX_NUM_CHANNELS][MLX5E_MAX_NUM_TC];
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 	struct mlx5e_dcbx_dp       dcbx_dp;
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 2a56e66f58d8..6abd4ed5b69b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1693,11 +1693,10 @@ static int mlx5e_open_sqs(struct mlx5e_channel *c,
 			  struct mlx5e_params *params,
 			  struct mlx5e_channel_param *cparam)
 {
-	struct mlx5e_priv *priv = c->priv;
 	int err, tc;
 
 	for (tc = 0; tc < params->num_tc; tc++) {
-		int txq_ix = c->ix + tc * priv->max_nch;
+		int txq_ix = c->ix + tc * params->num_channels;
 
 		err = mlx5e_open_txqsq(c, c->priv->tisn[c->lag_port][tc], txq_ix,
 				       params, &cparam->sq, &c->sq[tc], tc);
@@ -2878,26 +2877,21 @@ static void mlx5e_netdev_set_tcs(struct net_device *netdev)
 		netdev_set_tc_queue(netdev, tc, nch, 0);
 }
 
-static void mlx5e_build_tc2txq_maps(struct mlx5e_priv *priv)
+static void mlx5e_build_txq_maps(struct mlx5e_priv *priv)
 {
-	int i, tc;
+	int i, ch;
 
-	for (i = 0; i < priv->max_nch; i++)
-		for (tc = 0; tc < priv->profile->max_tc; tc++)
-			priv->channel_tc2txq[i][tc] = i + tc * priv->max_nch;
-}
+	ch = priv->channels.num;
 
-static void mlx5e_build_tx2sq_maps(struct mlx5e_priv *priv)
-{
-	struct mlx5e_channel *c;
-	struct mlx5e_txqsq *sq;
-	int i, tc;
+	for (i = 0; i < ch; i++) {
+		int tc;
+
+		for (tc = 0; tc < priv->channels.params.num_tc; tc++) {
+			struct mlx5e_channel *c = priv->channels.c[i];
+			struct mlx5e_txqsq *sq = &c->sq[tc];
 
-	for (i = 0; i < priv->channels.num; i++) {
-		c = priv->channels.c[i];
-		for (tc = 0; tc < c->num_tc; tc++) {
-			sq = &c->sq[tc];
 			priv->txq2sq[sq->txq_ix] = sq;
+			priv->channel_tc2realtxq[i][tc] = i + tc * ch;
 		}
 	}
 }
@@ -2912,7 +2906,7 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv)
 	netif_set_real_num_tx_queues(netdev, num_txqs);
 	netif_set_real_num_rx_queues(netdev, num_rxqs);
 
-	mlx5e_build_tx2sq_maps(priv);
+	mlx5e_build_txq_maps(priv);
 	mlx5e_activate_channels(&priv->channels);
 	mlx5e_xdp_tx_enable(priv);
 	netif_tx_start_all_queues(priv->netdev);
@@ -5028,7 +5022,6 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev,
 	if (err)
 		mlx5_core_err(mdev, "TLS initialization failed, %d\n", err);
 	mlx5e_build_nic_netdev(netdev);
-	mlx5e_build_tc2txq_maps(priv);
 	mlx5e_health_create_reporters(priv);
 
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 7e6ebd0505cc..9f09253f9f46 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -1601,7 +1601,7 @@ static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data,
 			for (j = 0; j < NUM_SQ_STATS; j++)
 				sprintf(data + (idx++) * ETH_GSTRING_LEN,
 					sq_stats_desc[j].format,
-					priv->channel_tc2txq[i][tc]);
+					i + tc * max_nch);
 
 	for (i = 0; i < max_nch; i++) {
 		for (j = 0; j < NUM_XSKSQ_STATS * is_xsk; j++)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 67dc4f0921b6..dee12f17f9c2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -93,7 +93,7 @@ u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
 	if (txq_ix >= num_channels)
 		txq_ix = priv->txq2sq[txq_ix]->ch_ix;
 
-	return priv->channel_tc2txq[txq_ix][up];
+	return priv->channel_tc2realtxq[txq_ix][up];
 }
 
 static inline int mlx5e_skb_l2_header_offset(struct sk_buff *skb)
-- 
2.20.1


From 22480eb36d379c2879a4091cc81661124ce9f24e Mon Sep 17 00:00:00 2001
From: Aaron Conole <aconole@redhat.com>
Date: Tue, 3 Dec 2019 16:34:14 -0500
Subject: [PATCH 28/38] act_ct: support asymmetric conntrack

[ Upstream commit 95219afbb980f10934de9f23a3e199be69c5ed09 ]

The act_ct TC module shares a common conntrack and NAT infrastructure
exposed via netfilter.  It's possible that a packet needs both SNAT and
DNAT manipulation, due to e.g. tuple collision.  Netfilter can support
this because it runs through the NAT table twice - once on ingress and
again after egress.  The act_ct action doesn't have such capability.

Like netfilter hook infrastructure, we should run through NAT twice to
keep the symmetry.

Fixes: b57dc7c13ea9 ("net/sched: Introduce action ct")
Signed-off-by: Aaron Conole <aconole@redhat.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ct.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index fcc46025e790..f3232a00970f 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -329,6 +329,7 @@ static int tcf_ct_act_nat(struct sk_buff *skb,
 			  bool commit)
 {
 #if IS_ENABLED(CONFIG_NF_NAT)
+	int err;
 	enum nf_nat_manip_type maniptype;
 
 	if (!(ct_action & TCA_CT_ACT_NAT))
@@ -359,7 +360,17 @@ static int tcf_ct_act_nat(struct sk_buff *skb,
 		return NF_ACCEPT;
 	}
 
-	return ct_nat_execute(skb, ct, ctinfo, range, maniptype);
+	err = ct_nat_execute(skb, ct, ctinfo, range, maniptype);
+	if (err == NF_ACCEPT &&
+	    ct->status & IPS_SRC_NAT && ct->status & IPS_DST_NAT) {
+		if (maniptype == NF_NAT_MANIP_SRC)
+			maniptype = NF_NAT_MANIP_DST;
+		else
+			maniptype = NF_NAT_MANIP_SRC;
+
+		err = ct_nat_execute(skb, ct, ctinfo, range, maniptype);
+	}
+	return err;
 #else
 	return NF_ACCEPT;
 #endif
-- 
2.20.1


From 4615e64963afb0bc6570e614dae2b4e85936b499 Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Thu, 5 Dec 2019 10:30:22 +0200
Subject: [PATCH 29/38] net/mlx5e: Fix SFF 8472 eeprom length

[ Upstream commit c431f8597863a91eea6024926e0c1b179cfa4852 ]

SFF 8472 eeprom length is 512 bytes. Fix module info return value to
support 512 bytes read.

Fixes: ace329f4ab3b ("net/mlx5e: ethtool, Remove unsupported SFP EEPROM high pages query")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Reviewed-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 95601269fa2e..d5d80be1a6c7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1643,7 +1643,7 @@ static int mlx5e_get_module_info(struct net_device *netdev,
 		break;
 	case MLX5_MODULE_ID_SFP:
 		modinfo->type       = ETH_MODULE_SFF_8472;
-		modinfo->eeprom_len = MLX5_EEPROM_PAGE_LENGTH;
+		modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN;
 		break;
 	default:
 		netdev_err(priv->netdev, "%s: cable type not recognized:0x%x\n",
-- 
2.20.1


From 43ec125d951673e2c8da9fc24f70876d79f2b4f2 Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@mellanox.com>
Date: Wed, 4 Dec 2019 11:25:43 +0200
Subject: [PATCH 30/38] net/mlx5e: Fix freeing flow with kfree() and not
 kvfree()

[ Upstream commit a23dae79fb6555c808528707c6389345d0b0c189 ]

Flows are allocated with kzalloc() so free with kfree().

Fixes: 04de7dda7394 ("net/mlx5e: Infrastructure for duplicated offloading of TC flows")
Signed-off-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Eli Britstein <elibr@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index f90a9f8e0fc6..c2c7f214a56a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1616,7 +1616,7 @@ static void __mlx5e_tc_del_fdb_peer_flow(struct mlx5e_tc_flow *flow)
 	flow_flag_clear(flow, DUP);
 
 	mlx5e_tc_del_fdb_flow(flow->peer_flow->priv, flow->peer_flow);
-	kvfree(flow->peer_flow);
+	kfree(flow->peer_flow);
 	flow->peer_flow = NULL;
 }
 
-- 
2.20.1


From f4458f56652ba08572129c62d57b48f345374c91 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Sun, 1 Dec 2019 14:45:25 +0200
Subject: [PATCH 31/38] net/mlx5e: Fix translation of link mode into speed

[ Upstream commit 6d485e5e555436d2c13accdb10807328c4158a17 ]

Add a missing value in translation of PTYS ext_eth_proto_oper to its
corresponding speed. When ext_eth_proto_oper bit 10 is set, ethtool
shows unknown speed. With this fix, ethtool shows speed is 100G as
expected.

Fixes: a08b4ed1373d ("net/mlx5: Add support to ext_* fields introduced in Port Type and Speed register")
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/port.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
index f777994f3005..fce6eccdcf8b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
@@ -73,6 +73,7 @@ static const u32 mlx5e_ext_link_speed[MLX5E_EXT_LINK_MODES_NUMBER] = {
 	[MLX5E_50GAUI_2_LAUI_2_50GBASE_CR2_KR2]	= 50000,
 	[MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR]	= 50000,
 	[MLX5E_CAUI_4_100GBASE_CR4_KR4]		= 100000,
+	[MLX5E_100GAUI_2_100GBASE_CR2_KR2]	= 100000,
 	[MLX5E_200GAUI_4_200GBASE_CR4_KR4]	= 200000,
 	[MLX5E_400GAUI_8]			= 400000,
 };
-- 
2.20.1


From 5e342ad143d61303c735bd11913d96fc25558146 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Sun, 1 Dec 2019 16:33:55 +0200
Subject: [PATCH 32/38] net/mlx5e: ethtool, Fix analysis of speed setting

[ Upstream commit 3d7cadae51f1b7f28358e36d0a1ce3f0ae2eee60 ]

When setting speed to 100G via ethtool (AN is set to off), only 25G*4 is
configured while the user, who has an advanced HW which supports
extended PTYS, expects also 50G*2 to be configured.
With this patch, when extended PTYS mode is available, configure
PTYS via extended fields.

Fixes: 4b95840a6ced ("net/mlx5e: Fix matching of speed to PRM link modes")
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en_ethtool.c    | 13 +++----------
 1 file changed, 3 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index d5d80be1a6c7..c6776f308d5e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1027,18 +1027,11 @@ static bool ext_link_mode_requested(const unsigned long *adver)
 	return bitmap_intersects(modes, adver, __ETHTOOL_LINK_MODE_MASK_NBITS);
 }
 
-static bool ext_speed_requested(u32 speed)
-{
-#define MLX5E_MAX_PTYS_LEGACY_SPEED 100000
-	return !!(speed > MLX5E_MAX_PTYS_LEGACY_SPEED);
-}
-
-static bool ext_requested(u8 autoneg, const unsigned long *adver, u32 speed)
+static bool ext_requested(u8 autoneg, const unsigned long *adver, bool ext_supported)
 {
 	bool ext_link_mode = ext_link_mode_requested(adver);
-	bool ext_speed = ext_speed_requested(speed);
 
-	return  autoneg == AUTONEG_ENABLE ? ext_link_mode : ext_speed;
+	return  autoneg == AUTONEG_ENABLE ? ext_link_mode : ext_supported;
 }
 
 int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
@@ -1065,8 +1058,8 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 	autoneg = link_ksettings->base.autoneg;
 	speed = link_ksettings->base.speed;
 
-	ext = ext_requested(autoneg, adver, speed),
 	ext_supported = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+	ext = ext_requested(autoneg, adver, ext_supported);
 	if (!ext_supported && ext)
 		return -EOPNOTSUPP;
 
-- 
2.20.1


From 5f40ddc95cb0f238003e2a34a75e44a82eb0bbfb Mon Sep 17 00:00:00 2001
From: Jonathan Lemon <jonathan.lemon@gmail.com>
Date: Thu, 14 Nov 2019 14:13:00 -0800
Subject: [PATCH 33/38] page_pool: do not release pool until inflight == 0.

[ Upstream commit c3f812cea0d7006469d1cf33a4a9f0a12bb4b3a3 ]

The page pool keeps track of the number of pages in flight, and
it isn't safe to remove the pool until all pages are returned.

Disallow removing the pool until all pages are back, so the pool
is always available for page producers.

Make the page pool responsible for its own delayed destruction
instead of relying on XDP, so the page pool can be used without
the xdp memory model.

When all pages are returned, free the pool and notify xdp if the
pool is registered with the xdp memory system.  Have the callback
perform a table walk since some drivers (cpsw) may share the pool
among multiple xdp_rxq_info.

Note that the increment of pages_state_release_cnt may result in
inflight == 0, resulting in the pool being released.

Fixes: d956a048cd3f ("xdp: force mem allocator removal and periodic warning")
Signed-off-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/stmicro/stmmac/stmmac_main.c |   4 +-
 include/net/page_pool.h                       |  52 ++------
 include/net/xdp_priv.h                        |   4 -
 include/trace/events/xdp.h                    |  19 +--
 net/core/page_pool.c                          | 122 +++++++++++-------
 net/core/xdp.c                                | 121 +++++++----------
 6 files changed, 139 insertions(+), 183 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index f826365c979d..271a00f24f45 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1502,10 +1502,8 @@ static void free_dma_rx_desc_resources(struct stmmac_priv *priv)
 					  rx_q->dma_erx, rx_q->dma_rx_phy);
 
 		kfree(rx_q->buf_pool);
-		if (rx_q->page_pool) {
-			page_pool_request_shutdown(rx_q->page_pool);
+		if (rx_q->page_pool)
 			page_pool_destroy(rx_q->page_pool);
-		}
 	}
 }
 
diff --git a/include/net/page_pool.h b/include/net/page_pool.h
index 2cbcdbdec254..1121faa99c12 100644
--- a/include/net/page_pool.h
+++ b/include/net/page_pool.h
@@ -70,7 +70,12 @@ struct page_pool_params {
 struct page_pool {
 	struct page_pool_params p;
 
-        u32 pages_state_hold_cnt;
+	struct delayed_work release_dw;
+	void (*disconnect)(void *);
+	unsigned long defer_start;
+	unsigned long defer_warn;
+
+	u32 pages_state_hold_cnt;
 
 	/*
 	 * Data structure for allocation side
@@ -129,25 +134,19 @@ inline enum dma_data_direction page_pool_get_dma_dir(struct page_pool *pool)
 
 struct page_pool *page_pool_create(const struct page_pool_params *params);
 
-void __page_pool_free(struct page_pool *pool);
-static inline void page_pool_free(struct page_pool *pool)
-{
-	/* When page_pool isn't compiled-in, net/core/xdp.c doesn't
-	 * allow registering MEM_TYPE_PAGE_POOL, but shield linker.
-	 */
 #ifdef CONFIG_PAGE_POOL
-	__page_pool_free(pool);
-#endif
-}
-
-/* Drivers use this instead of page_pool_free */
+void page_pool_destroy(struct page_pool *pool);
+void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *));
+#else
 static inline void page_pool_destroy(struct page_pool *pool)
 {
-	if (!pool)
-		return;
+}
 
-	page_pool_free(pool);
+static inline void page_pool_use_xdp_mem(struct page_pool *pool,
+					 void (*disconnect)(void *))
+{
 }
+#endif
 
 /* Never call this directly, use helpers below */
 void __page_pool_put_page(struct page_pool *pool,
@@ -170,24 +169,6 @@ static inline void page_pool_recycle_direct(struct page_pool *pool,
 	__page_pool_put_page(pool, page, true);
 }
 
-/* API user MUST have disconnected alloc-side (not allowed to call
- * page_pool_alloc_pages()) before calling this.  The free-side can
- * still run concurrently, to handle in-flight packet-pages.
- *
- * A request to shutdown can fail (with false) if there are still
- * in-flight packet-pages.
- */
-bool __page_pool_request_shutdown(struct page_pool *pool);
-static inline bool page_pool_request_shutdown(struct page_pool *pool)
-{
-	bool safe_to_remove = false;
-
-#ifdef CONFIG_PAGE_POOL
-	safe_to_remove = __page_pool_request_shutdown(pool);
-#endif
-	return safe_to_remove;
-}
-
 /* Disconnects a page (from a page_pool).  API users can have a need
  * to disconnect a page (from a page_pool), to allow it to be used as
  * a regular page (that will eventually be returned to the normal
@@ -216,11 +197,6 @@ static inline bool is_page_pool_compiled_in(void)
 #endif
 }
 
-static inline void page_pool_get(struct page_pool *pool)
-{
-	refcount_inc(&pool->user_cnt);
-}
-
 static inline bool page_pool_put(struct page_pool *pool)
 {
 	return refcount_dec_and_test(&pool->user_cnt);
diff --git a/include/net/xdp_priv.h b/include/net/xdp_priv.h
index 6a8cba6ea79a..a9d5b7603b89 100644
--- a/include/net/xdp_priv.h
+++ b/include/net/xdp_priv.h
@@ -12,12 +12,8 @@ struct xdp_mem_allocator {
 		struct page_pool *page_pool;
 		struct zero_copy_allocator *zc_alloc;
 	};
-	int disconnect_cnt;
-	unsigned long defer_start;
 	struct rhash_head node;
 	struct rcu_head rcu;
-	struct delayed_work defer_wq;
-	unsigned long defer_warn;
 };
 
 #endif /* __LINUX_NET_XDP_PRIV_H__ */
diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h
index 8c8420230a10..c79943e82a54 100644
--- a/include/trace/events/xdp.h
+++ b/include/trace/events/xdp.h
@@ -317,19 +317,15 @@ __MEM_TYPE_MAP(__MEM_TYPE_TP_FN)
 
 TRACE_EVENT(mem_disconnect,
 
-	TP_PROTO(const struct xdp_mem_allocator *xa,
-		 bool safe_to_remove, bool force),
+	TP_PROTO(const struct xdp_mem_allocator *xa),
 
-	TP_ARGS(xa, safe_to_remove, force),
+	TP_ARGS(xa),
 
 	TP_STRUCT__entry(
 		__field(const struct xdp_mem_allocator *,	xa)
 		__field(u32,		mem_id)
 		__field(u32,		mem_type)
 		__field(const void *,	allocator)
-		__field(bool,		safe_to_remove)
-		__field(bool,		force)
-		__field(int,		disconnect_cnt)
 	),
 
 	TP_fast_assign(
@@ -337,19 +333,12 @@ TRACE_EVENT(mem_disconnect,
 		__entry->mem_id		= xa->mem.id;
 		__entry->mem_type	= xa->mem.type;
 		__entry->allocator	= xa->allocator;
-		__entry->safe_to_remove	= safe_to_remove;
-		__entry->force		= force;
-		__entry->disconnect_cnt	= xa->disconnect_cnt;
 	),
 
-	TP_printk("mem_id=%d mem_type=%s allocator=%p"
-		  " safe_to_remove=%s force=%s disconnect_cnt=%d",
+	TP_printk("mem_id=%d mem_type=%s allocator=%p",
 		  __entry->mem_id,
 		  __print_symbolic(__entry->mem_type, __MEM_TYPE_SYM_TAB),
-		  __entry->allocator,
-		  __entry->safe_to_remove ? "true" : "false",
-		  __entry->force ? "true" : "false",
-		  __entry->disconnect_cnt
+		  __entry->allocator
 	)
 );
 
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 5bc65587f1c4..dfc2501c35d9 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -18,6 +18,9 @@
 
 #include <trace/events/page_pool.h>
 
+#define DEFER_TIME (msecs_to_jiffies(1000))
+#define DEFER_WARN_INTERVAL (60 * HZ)
+
 static int page_pool_init(struct page_pool *pool,
 			  const struct page_pool_params *params)
 {
@@ -193,22 +196,14 @@ static s32 page_pool_inflight(struct page_pool *pool)
 {
 	u32 release_cnt = atomic_read(&pool->pages_state_release_cnt);
 	u32 hold_cnt = READ_ONCE(pool->pages_state_hold_cnt);
-	s32 distance;
-
-	distance = _distance(hold_cnt, release_cnt);
-
-	trace_page_pool_inflight(pool, distance, hold_cnt, release_cnt);
-	return distance;
-}
+	s32 inflight;
 
-static bool __page_pool_safe_to_destroy(struct page_pool *pool)
-{
-	s32 inflight = page_pool_inflight(pool);
+	inflight = _distance(hold_cnt, release_cnt);
 
-	/* The distance should not be able to become negative */
+	trace_page_pool_inflight(pool, inflight, hold_cnt, release_cnt);
 	WARN(inflight < 0, "Negative(%d) inflight packet-pages", inflight);
 
-	return (inflight == 0);
+	return inflight;
 }
 
 /* Cleanup page_pool state from page */
@@ -216,6 +211,7 @@ static void __page_pool_clean_page(struct page_pool *pool,
 				   struct page *page)
 {
 	dma_addr_t dma;
+	int count;
 
 	if (!(pool->p.flags & PP_FLAG_DMA_MAP))
 		goto skip_dma_unmap;
@@ -227,9 +223,11 @@ static void __page_pool_clean_page(struct page_pool *pool,
 			     DMA_ATTR_SKIP_CPU_SYNC);
 	page->dma_addr = 0;
 skip_dma_unmap:
-	atomic_inc(&pool->pages_state_release_cnt);
-	trace_page_pool_state_release(pool, page,
-			      atomic_read(&pool->pages_state_release_cnt));
+	/* This may be the last page returned, releasing the pool, so
+	 * it is not safe to reference pool afterwards.
+	 */
+	count = atomic_inc_return(&pool->pages_state_release_cnt);
+	trace_page_pool_state_release(pool, page, count);
 }
 
 /* unmap the page and clean our state */
@@ -338,31 +336,10 @@ static void __page_pool_empty_ring(struct page_pool *pool)
 	}
 }
 
-static void __warn_in_flight(struct page_pool *pool)
+static void page_pool_free(struct page_pool *pool)
 {
-	u32 release_cnt = atomic_read(&pool->pages_state_release_cnt);
-	u32 hold_cnt = READ_ONCE(pool->pages_state_hold_cnt);
-	s32 distance;
-
-	distance = _distance(hold_cnt, release_cnt);
-
-	/* Drivers should fix this, but only problematic when DMA is used */
-	WARN(1, "Still in-flight pages:%d hold:%u released:%u",
-	     distance, hold_cnt, release_cnt);
-}
-
-void __page_pool_free(struct page_pool *pool)
-{
-	/* Only last user actually free/release resources */
-	if (!page_pool_put(pool))
-		return;
-
-	WARN(pool->alloc.count, "API usage violation");
-	WARN(!ptr_ring_empty(&pool->ring), "ptr_ring is not empty");
-
-	/* Can happen due to forced shutdown */
-	if (!__page_pool_safe_to_destroy(pool))
-		__warn_in_flight(pool);
+	if (pool->disconnect)
+		pool->disconnect(pool);
 
 	ptr_ring_cleanup(&pool->ring, NULL);
 
@@ -371,12 +348,8 @@ void __page_pool_free(struct page_pool *pool)
 
 	kfree(pool);
 }
-EXPORT_SYMBOL(__page_pool_free);
 
-/* Request to shutdown: release pages cached by page_pool, and check
- * for in-flight pages
- */
-bool __page_pool_request_shutdown(struct page_pool *pool)
+static void page_pool_scrub(struct page_pool *pool)
 {
 	struct page *page;
 
@@ -393,7 +366,64 @@ bool __page_pool_request_shutdown(struct page_pool *pool)
 	 * be in-flight.
 	 */
 	__page_pool_empty_ring(pool);
+}
+
+static int page_pool_release(struct page_pool *pool)
+{
+	int inflight;
+
+	page_pool_scrub(pool);
+	inflight = page_pool_inflight(pool);
+	if (!inflight)
+		page_pool_free(pool);
+
+	return inflight;
+}
+
+static void page_pool_release_retry(struct work_struct *wq)
+{
+	struct delayed_work *dwq = to_delayed_work(wq);
+	struct page_pool *pool = container_of(dwq, typeof(*pool), release_dw);
+	int inflight;
+
+	inflight = page_pool_release(pool);
+	if (!inflight)
+		return;
+
+	/* Periodic warning */
+	if (time_after_eq(jiffies, pool->defer_warn)) {
+		int sec = (s32)((u32)jiffies - (u32)pool->defer_start) / HZ;
+
+		pr_warn("%s() stalled pool shutdown %d inflight %d sec\n",
+			__func__, inflight, sec);
+		pool->defer_warn = jiffies + DEFER_WARN_INTERVAL;
+	}
+
+	/* Still not ready to be disconnected, retry later */
+	schedule_delayed_work(&pool->release_dw, DEFER_TIME);
+}
+
+void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *))
+{
+	refcount_inc(&pool->user_cnt);
+	pool->disconnect = disconnect;
+}
+
+void page_pool_destroy(struct page_pool *pool)
+{
+	if (!pool)
+		return;
+
+	if (!page_pool_put(pool))
+		return;
+
+	if (!page_pool_release(pool))
+		return;
+
+	pool->defer_start = jiffies;
+	pool->defer_warn  = jiffies + DEFER_WARN_INTERVAL;
 
-	return __page_pool_safe_to_destroy(pool);
+	INIT_DELAYED_WORK(&pool->release_dw, page_pool_release_retry);
+	schedule_delayed_work(&pool->release_dw, DEFER_TIME);
 }
-EXPORT_SYMBOL(__page_pool_request_shutdown);
+EXPORT_SYMBOL(page_pool_destroy);
diff --git a/net/core/xdp.c b/net/core/xdp.c
index d7bf62ffbb5e..ac866ac65f2b 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -70,10 +70,6 @@ static void __xdp_mem_allocator_rcu_free(struct rcu_head *rcu)
 
 	xa = container_of(rcu, struct xdp_mem_allocator, rcu);
 
-	/* Allocator have indicated safe to remove before this is called */
-	if (xa->mem.type == MEM_TYPE_PAGE_POOL)
-		page_pool_free(xa->page_pool);
-
 	/* Allow this ID to be reused */
 	ida_simple_remove(&mem_id_pool, xa->mem.id);
 
@@ -85,62 +81,57 @@ static void __xdp_mem_allocator_rcu_free(struct rcu_head *rcu)
 	kfree(xa);
 }
 
-static bool __mem_id_disconnect(int id, bool force)
+static void mem_xa_remove(struct xdp_mem_allocator *xa)
 {
-	struct xdp_mem_allocator *xa;
-	bool safe_to_remove = true;
+	trace_mem_disconnect(xa);
 
 	mutex_lock(&mem_id_lock);
 
-	xa = rhashtable_lookup_fast(mem_id_ht, &id, mem_id_rht_params);
-	if (!xa) {
-		mutex_unlock(&mem_id_lock);
-		WARN(1, "Request remove non-existing id(%d), driver bug?", id);
-		return true;
-	}
-	xa->disconnect_cnt++;
-
-	/* Detects in-flight packet-pages for page_pool */
-	if (xa->mem.type == MEM_TYPE_PAGE_POOL)
-		safe_to_remove = page_pool_request_shutdown(xa->page_pool);
-
-	trace_mem_disconnect(xa, safe_to_remove, force);
-
-	if ((safe_to_remove || force) &&
-	    !rhashtable_remove_fast(mem_id_ht, &xa->node, mem_id_rht_params))
+	if (!rhashtable_remove_fast(mem_id_ht, &xa->node, mem_id_rht_params))
 		call_rcu(&xa->rcu, __xdp_mem_allocator_rcu_free);
 
 	mutex_unlock(&mem_id_lock);
-	return (safe_to_remove|force);
 }
 
-#define DEFER_TIME (msecs_to_jiffies(1000))
-#define DEFER_WARN_INTERVAL (30 * HZ)
-#define DEFER_MAX_RETRIES 120
+static void mem_allocator_disconnect(void *allocator)
+{
+	struct xdp_mem_allocator *xa;
+	struct rhashtable_iter iter;
+
+	rhashtable_walk_enter(mem_id_ht, &iter);
+	do {
+		rhashtable_walk_start(&iter);
+
+		while ((xa = rhashtable_walk_next(&iter)) && !IS_ERR(xa)) {
+			if (xa->allocator == allocator)
+				mem_xa_remove(xa);
+		}
+
+		rhashtable_walk_stop(&iter);
 
-static void mem_id_disconnect_defer_retry(struct work_struct *wq)
+	} while (xa == ERR_PTR(-EAGAIN));
+	rhashtable_walk_exit(&iter);
+}
+
+static void mem_id_disconnect(int id)
 {
-	struct delayed_work *dwq = to_delayed_work(wq);
-	struct xdp_mem_allocator *xa = container_of(dwq, typeof(*xa), defer_wq);
-	bool force = false;
+	struct xdp_mem_allocator *xa;
 
-	if (xa->disconnect_cnt > DEFER_MAX_RETRIES)
-		force = true;
+	mutex_lock(&mem_id_lock);
 
-	if (__mem_id_disconnect(xa->mem.id, force))
+	xa = rhashtable_lookup_fast(mem_id_ht, &id, mem_id_rht_params);
+	if (!xa) {
+		mutex_unlock(&mem_id_lock);
+		WARN(1, "Request remove non-existing id(%d), driver bug?", id);
 		return;
+	}
 
-	/* Periodic warning */
-	if (time_after_eq(jiffies, xa->defer_warn)) {
-		int sec = (s32)((u32)jiffies - (u32)xa->defer_start) / HZ;
+	trace_mem_disconnect(xa);
 
-		pr_warn("%s() stalled mem.id=%u shutdown %d attempts %d sec\n",
-			__func__, xa->mem.id, xa->disconnect_cnt, sec);
-		xa->defer_warn = jiffies + DEFER_WARN_INTERVAL;
-	}
+	if (!rhashtable_remove_fast(mem_id_ht, &xa->node, mem_id_rht_params))
+		call_rcu(&xa->rcu, __xdp_mem_allocator_rcu_free);
 
-	/* Still not ready to be disconnected, retry later */
-	schedule_delayed_work(&xa->defer_wq, DEFER_TIME);
+	mutex_unlock(&mem_id_lock);
 }
 
 void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq)
@@ -153,38 +144,21 @@ void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq)
 		return;
 	}
 
-	if (xdp_rxq->mem.type != MEM_TYPE_PAGE_POOL &&
-	    xdp_rxq->mem.type != MEM_TYPE_ZERO_COPY) {
-		return;
-	}
-
 	if (id == 0)
 		return;
 
-	if (__mem_id_disconnect(id, false))
-		return;
-
-	/* Could not disconnect, defer new disconnect attempt to later */
-	mutex_lock(&mem_id_lock);
+	if (xdp_rxq->mem.type == MEM_TYPE_ZERO_COPY)
+		return mem_id_disconnect(id);
 
-	xa = rhashtable_lookup_fast(mem_id_ht, &id, mem_id_rht_params);
-	if (!xa) {
-		mutex_unlock(&mem_id_lock);
-		return;
+	if (xdp_rxq->mem.type == MEM_TYPE_PAGE_POOL) {
+		rcu_read_lock();
+		xa = rhashtable_lookup(mem_id_ht, &id, mem_id_rht_params);
+		page_pool_destroy(xa->page_pool);
+		rcu_read_unlock();
 	}
-	xa->defer_start = jiffies;
-	xa->defer_warn  = jiffies + DEFER_WARN_INTERVAL;
-
-	INIT_DELAYED_WORK(&xa->defer_wq, mem_id_disconnect_defer_retry);
-	mutex_unlock(&mem_id_lock);
-	schedule_delayed_work(&xa->defer_wq, DEFER_TIME);
 }
 EXPORT_SYMBOL_GPL(xdp_rxq_info_unreg_mem_model);
 
-/* This unregister operation will also cleanup and destroy the
- * allocator. The page_pool_free() operation is first called when it's
- * safe to remove, possibly deferred to a workqueue.
- */
 void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq)
 {
 	/* Simplify driver cleanup code paths, allow unreg "unused" */
@@ -371,7 +345,7 @@ int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq,
 	}
 
 	if (type == MEM_TYPE_PAGE_POOL)
-		page_pool_get(xdp_alloc->page_pool);
+		page_pool_use_xdp_mem(allocator, mem_allocator_disconnect);
 
 	mutex_unlock(&mem_id_lock);
 
@@ -402,15 +376,8 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct,
 		/* mem->id is valid, checked in xdp_rxq_info_reg_mem_model() */
 		xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
 		page = virt_to_head_page(data);
-		if (likely(xa)) {
-			napi_direct &= !xdp_return_frame_no_direct();
-			page_pool_put_page(xa->page_pool, page, napi_direct);
-		} else {
-			/* Hopefully stack show who to blame for late return */
-			WARN_ONCE(1, "page_pool gone mem.id=%d", mem->id);
-			trace_mem_return_failed(mem, page);
-			put_page(page);
-		}
+		napi_direct &= !xdp_return_frame_no_direct();
+		page_pool_put_page(xa->page_pool, page, napi_direct);
 		rcu_read_unlock();
 		break;
 	case MEM_TYPE_PAGE_SHARED:
-- 
2.20.1


From a32d0dbc0f645809634c7b1804661b10ba5745db Mon Sep 17 00:00:00 2001
From: Jonathan Lemon <jonathan.lemon@gmail.com>
Date: Tue, 3 Dec 2019 14:01:14 -0800
Subject: [PATCH 34/38] xdp: obtain the mem_id mutex before trying to remove an
 entry.

[ Upstream commit 86c76c09898332143be365c702cf8d586ed4ed21 ]

A lockdep splat was observed when trying to remove an xdp memory
model from the table since the mutex was obtained when trying to
remove the entry, but not before the table walk started:

Fix the splat by obtaining the lock before starting the table walk.

Fixes: c3f812cea0d7 ("page_pool: do not release pool until inflight == 0.")
Reported-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Tested-by: Grygorii Strashko <grygorii.strashko@ti.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/xdp.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/core/xdp.c b/net/core/xdp.c
index ac866ac65f2b..b3f463c6543f 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -85,12 +85,8 @@ static void mem_xa_remove(struct xdp_mem_allocator *xa)
 {
 	trace_mem_disconnect(xa);
 
-	mutex_lock(&mem_id_lock);
-
 	if (!rhashtable_remove_fast(mem_id_ht, &xa->node, mem_id_rht_params))
 		call_rcu(&xa->rcu, __xdp_mem_allocator_rcu_free);
-
-	mutex_unlock(&mem_id_lock);
 }
 
 static void mem_allocator_disconnect(void *allocator)
@@ -98,6 +94,8 @@ static void mem_allocator_disconnect(void *allocator)
 	struct xdp_mem_allocator *xa;
 	struct rhashtable_iter iter;
 
+	mutex_lock(&mem_id_lock);
+
 	rhashtable_walk_enter(mem_id_ht, &iter);
 	do {
 		rhashtable_walk_start(&iter);
@@ -111,6 +109,8 @@ static void mem_allocator_disconnect(void *allocator)
 
 	} while (xa == ERR_PTR(-EAGAIN));
 	rhashtable_walk_exit(&iter);
+
+	mutex_unlock(&mem_id_lock);
 }
 
 static void mem_id_disconnect(int id)
-- 
2.20.1


From bfcb7418b0c2195fe39a8f24629c5af6c6292fca Mon Sep 17 00:00:00 2001
From: Shannon Nelson <snelson@pensando.io>
Date: Tue, 3 Dec 2019 14:17:34 -0800
Subject: [PATCH 35/38] ionic: keep users rss hash across lif reset

[ Upstream commit ffac2027e18f006f42630f2e01a8a9bd8dc664b5 ]

If the user has specified their own RSS hash key, don't
lose it across queue resets such as DOWN/UP, MTU change,
and number of channels change.  This is fixed by moving
the key initialization to a little earlier in the lif
creation.

Also, let's clean up the RSS config a little better on
the way down by setting it all to 0.

Fixes: aa3198819bea ("ionic: Add RSS support")
Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/pensando/ionic/ionic_lif.c | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index 20faa8d24c9f..134640412d7b 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -1364,12 +1364,9 @@ int ionic_lif_rss_config(struct ionic_lif *lif, const u16 types,
 
 static int ionic_lif_rss_init(struct ionic_lif *lif)
 {
-	u8 rss_key[IONIC_RSS_HASH_KEY_SIZE];
 	unsigned int tbl_sz;
 	unsigned int i;
 
-	netdev_rss_key_fill(rss_key, IONIC_RSS_HASH_KEY_SIZE);
-
 	lif->rss_types = IONIC_RSS_TYPE_IPV4     |
 			 IONIC_RSS_TYPE_IPV4_TCP |
 			 IONIC_RSS_TYPE_IPV4_UDP |
@@ -1382,12 +1379,18 @@ static int ionic_lif_rss_init(struct ionic_lif *lif)
 	for (i = 0; i < tbl_sz; i++)
 		lif->rss_ind_tbl[i] = ethtool_rxfh_indir_default(i, lif->nxqs);
 
-	return ionic_lif_rss_config(lif, lif->rss_types, rss_key, NULL);
+	return ionic_lif_rss_config(lif, lif->rss_types, NULL, NULL);
 }
 
-static int ionic_lif_rss_deinit(struct ionic_lif *lif)
+static void ionic_lif_rss_deinit(struct ionic_lif *lif)
 {
-	return ionic_lif_rss_config(lif, 0x0, NULL, NULL);
+	int tbl_sz;
+
+	tbl_sz = le16_to_cpu(lif->ionic->ident.lif.eth.rss_ind_tbl_sz);
+	memset(lif->rss_ind_tbl, 0, tbl_sz);
+	memset(lif->rss_hash_key, 0, IONIC_RSS_HASH_KEY_SIZE);
+
+	ionic_lif_rss_config(lif, 0x0, NULL, NULL);
 }
 
 static void ionic_txrx_disable(struct ionic_lif *lif)
@@ -1710,6 +1713,7 @@ static struct ionic_lif *ionic_lif_alloc(struct ionic *ionic, unsigned int index
 		dev_err(dev, "Failed to allocate rss indirection table, aborting\n");
 		goto err_out_free_qcqs;
 	}
+	netdev_rss_key_fill(lif->rss_hash_key, IONIC_RSS_HASH_KEY_SIZE);
 
 	list_add_tail(&lif->list, &ionic->lifs);
 
-- 
2.20.1


From 97e7d0a30aafaf72a06bba8723c0d2f536689cc0 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Tue, 3 Dec 2019 17:45:35 +0200
Subject: [PATCH 36/38] net: mscc: ocelot: unregister the PTP clock on deinit

[ Upstream commit 9385973fe8db9743fa93bf17245635be4eb8c4a6 ]

Currently a switch driver deinit frees the regmaps, but the PTP clock is
still out there, available to user space via /dev/ptpN. Any PTP
operation is a ticking time bomb, since it will attempt to use the freed
regmaps and thus trigger kernel panics:

[    4.291746] fsl_enetc 0000:00:00.2 eth1: error -22 setting up slave phy
[    4.291871] mscc_felix 0000:00:00.5: Failed to register DSA switch: -22
[    4.308666] mscc_felix: probe of 0000:00:00.5 failed with error -22
[    6.358270] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000088
[    6.367090] Mem abort info:
[    6.369888]   ESR = 0x96000046
[    6.369891]   EC = 0x25: DABT (current EL), IL = 32 bits
[    6.369892]   SET = 0, FnV = 0
[    6.369894]   EA = 0, S1PTW = 0
[    6.369895] Data abort info:
[    6.369897]   ISV = 0, ISS = 0x00000046
[    6.369899]   CM = 0, WnR = 1
[    6.369902] user pgtable: 4k pages, 48-bit VAs, pgdp=00000020d58c7000
[    6.369904] [0000000000000088] pgd=00000020d5912003, pud=00000020d5915003, pmd=0000000000000000
[    6.369914] Internal error: Oops: 96000046 [#1] PREEMPT SMP
[    6.420443] Modules linked in:
[    6.423506] CPU: 1 PID: 262 Comm: phc_ctl Not tainted 5.4.0-03625-gb7b2a5dadd7f #204
[    6.431273] Hardware name: LS1028A RDB Board (DT)
[    6.435989] pstate: 40000085 (nZcv daIf -PAN -UAO)
[    6.440802] pc : css_release+0x24/0x58
[    6.444561] lr : regmap_read+0x40/0x78
[    6.448316] sp : ffff800010513cc0
[    6.451636] x29: ffff800010513cc0 x28: ffff002055873040
[    6.456963] x27: 0000000000000000 x26: 0000000000000000
[    6.462289] x25: 0000000000000000 x24: 0000000000000000
[    6.467617] x23: 0000000000000000 x22: 0000000000000080
[    6.472944] x21: ffff800010513d44 x20: 0000000000000080
[    6.478270] x19: 0000000000000000 x18: 0000000000000000
[    6.483596] x17: 0000000000000000 x16: 0000000000000000
[    6.488921] x15: 0000000000000000 x14: 0000000000000000
[    6.494247] x13: 0000000000000000 x12: 0000000000000000
[    6.499573] x11: 0000000000000000 x10: 0000000000000000
[    6.504899] x9 : 0000000000000000 x8 : 0000000000000000
[    6.510225] x7 : 0000000000000000 x6 : ffff800010513cf0
[    6.515550] x5 : 0000000000000000 x4 : 0000000fffffffe0
[    6.520876] x3 : 0000000000000088 x2 : ffff800010513d44
[    6.526202] x1 : ffffcada668ea000 x0 : ffffcada64d8b0c0
[    6.531528] Call trace:
[    6.533977]  css_release+0x24/0x58
[    6.537385]  regmap_read+0x40/0x78
[    6.540795]  __ocelot_read_ix+0x6c/0xa0
[    6.544641]  ocelot_ptp_gettime64+0x4c/0x110
[    6.548921]  ptp_clock_gettime+0x4c/0x58
[    6.552853]  pc_clock_gettime+0x5c/0xa8
[    6.556699]  __arm64_sys_clock_gettime+0x68/0xc8
[    6.561331]  el0_svc_common.constprop.2+0x7c/0x178
[    6.566133]  el0_svc_handler+0x34/0xa0
[    6.569891]  el0_sync_handler+0x114/0x1d0
[    6.573908]  el0_sync+0x140/0x180
[    6.577232] Code: d503201f b00119a1 91022263 b27b7be4 (f9004663)
[    6.583349] ---[ end trace d196b9b14cdae2da ]---
[    6.587977] Kernel panic - not syncing: Fatal exception
[    6.593216] SMP: stopping secondary CPUs
[    6.597151] Kernel Offset: 0x4ada54400000 from 0xffff800010000000
[    6.603261] PHYS_OFFSET: 0xffffd0a7c0000000
[    6.607454] CPU features: 0x10002,21806008
[    6.611558] Memory Limit: none

And now that ocelot->ptp_clock is checked at exit, prevent a potential
error where ptp_clock_register returned a pointer-encoded error, which
we are keeping in the ocelot private data structure. So now,
ocelot->ptp_clock is now either NULL or a valid pointer.

Fixes: 4e3b0468e6d7 ("net: mscc: PTP Hardware Clock (PHC) support")
Cc: Antoine Tenart <antoine.tenart@bootlin.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 672ea1342add..da1fd0e08c36 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -1979,14 +1979,18 @@ static struct ptp_clock_info ocelot_ptp_clock_info = {
 
 static int ocelot_init_timestamp(struct ocelot *ocelot)
 {
+	struct ptp_clock *ptp_clock;
+
 	ocelot->ptp_info = ocelot_ptp_clock_info;
-	ocelot->ptp_clock = ptp_clock_register(&ocelot->ptp_info, ocelot->dev);
-	if (IS_ERR(ocelot->ptp_clock))
-		return PTR_ERR(ocelot->ptp_clock);
+	ptp_clock = ptp_clock_register(&ocelot->ptp_info, ocelot->dev);
+	if (IS_ERR(ptp_clock))
+		return PTR_ERR(ptp_clock);
 	/* Check if PHC support is missing at the configuration level */
-	if (!ocelot->ptp_clock)
+	if (!ptp_clock)
 		return 0;
 
+	ocelot->ptp_clock = ptp_clock;
+
 	ocelot_write(ocelot, SYS_PTP_CFG_PTP_STAMP_WID(30), SYS_PTP_CFG);
 	ocelot_write(ocelot, 0xffffffff, ANA_TABLES_PTP_ID_LOW);
 	ocelot_write(ocelot, 0xffffffff, ANA_TABLES_PTP_ID_HIGH);
@@ -2213,6 +2217,8 @@ void ocelot_deinit(struct ocelot *ocelot)
 	destroy_workqueue(ocelot->stats_queue);
 	mutex_destroy(&ocelot->stats_lock);
 	ocelot_ace_deinit();
+	if (ocelot->ptp_clock)
+		ptp_clock_unregister(ocelot->ptp_clock);
 
 	for (i = 0; i < ocelot->num_phys_ports; i++) {
 		port = ocelot->ports[i];
-- 
2.20.1


From b1215d7b63184ccde438c190b7b329647351443e Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 6 Dec 2019 23:27:15 +0100
Subject: [PATCH 37/38] r8169: add missing RX enabling for WoL on RTL8125

[ Upstream commit 00222d1394104f0fd6c01ca9f578afec9e0f148b ]

RTL8125 also requires to enable RX for WoL.

v2: add missing Fixes tag

Fixes: f1bce4ad2f1c ("r8169: add support for RTL8125")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 1d67eeeab79d..7a9c86854c03 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -3920,7 +3920,7 @@ static void rtl_wol_suspend_quirk(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_32:
 	case RTL_GIGA_MAC_VER_33:
 	case RTL_GIGA_MAC_VER_34:
-	case RTL_GIGA_MAC_VER_37 ... RTL_GIGA_MAC_VER_51:
+	case RTL_GIGA_MAC_VER_37 ... RTL_GIGA_MAC_VER_61:
 		RTL_W32(tp, RxConfig, RTL_R32(tp, RxConfig) |
 			AcceptBroadcast | AcceptMulticast | AcceptMyPhys);
 		break;
-- 
2.20.1


From b65ed4c28e298c456b462527a4218864fe9c0f55 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 7 Dec 2019 22:21:52 +0100
Subject: [PATCH 38/38] r8169: fix rtl_hw_jumbo_disable for RTL8168evl

[ Upstream commit 0fc75219fe9a3c90631453e9870e4f6d956f0ebc ]

In referenced fix we removed the RTL8168e-specific jumbo config for
RTL8168evl in rtl_hw_jumbo_enable(). We have to do the same in
rtl_hw_jumbo_disable().

v2: fix referenced commit id

Fixes: 14012c9f3bb9 ("r8169: fix jumbo configuration for RTL8168evl")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 7a9c86854c03..4fe0977d01fa 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -4145,7 +4145,7 @@ static void rtl_hw_jumbo_disable(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_27 ... RTL_GIGA_MAC_VER_28:
 		r8168dp_hw_jumbo_disable(tp);
 		break;
-	case RTL_GIGA_MAC_VER_31 ... RTL_GIGA_MAC_VER_34:
+	case RTL_GIGA_MAC_VER_31 ... RTL_GIGA_MAC_VER_33:
 		r8168e_hw_jumbo_disable(tp);
 		break;
 	default:
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Mon, Dec 16, 2019 at 02:10:09PM -0800, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v5.3 and
> v5.4 -stable, respectively.

Many thanks for these, I'll queue them up after this next round of
stable kernels are out.

No need to do anything for 5.3 after this, it will be end-of-life.

thanks,

greg k-h

Re: [PATCHES] Networking

[Greg KH]

On Mon, Dec 16, 2019 at 02:10:09PM -0800, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v5.3 and
> v5.4 -stable, respectively.

All now queued up.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 103 bytes --]


Please queue up the following networking bug fixes for v4.19 and
v5.4 -stable, respectively.

Thanks!

[-- Attachment #2: net_419.mbox --]
[-- Type: Application/Octet-Stream, Size: 28817 bytes --]

From e5ef85b637df0bac0fe6e38dacceaaa205cc915b Mon Sep 17 00:00:00 2001
From: Mao Wenan <maowenan@huawei.com>
Date: Mon, 9 Dec 2019 21:31:25 +0800
Subject: [PATCH 01/13] af_packet: set defaule value for tmo

[ Upstream commit b43d1f9f7067c6759b1051e8ecb84e82cef569fe ]

There is softlockup when using TPACKET_V3:
...
NMI watchdog: BUG: soft lockup - CPU#2 stuck for 60010ms!
(__irq_svc) from [<c0558a0c>] (_raw_spin_unlock_irqrestore+0x44/0x54)
(_raw_spin_unlock_irqrestore) from [<c027b7e8>] (mod_timer+0x210/0x25c)
(mod_timer) from [<c0549c30>]
(prb_retire_rx_blk_timer_expired+0x68/0x11c)
(prb_retire_rx_blk_timer_expired) from [<c027a7ac>]
(call_timer_fn+0x90/0x17c)
(call_timer_fn) from [<c027ab6c>] (run_timer_softirq+0x2d4/0x2fc)
(run_timer_softirq) from [<c021eaf4>] (__do_softirq+0x218/0x318)
(__do_softirq) from [<c021eea0>] (irq_exit+0x88/0xac)
(irq_exit) from [<c0240130>] (msa_irq_exit+0x11c/0x1d4)
(msa_irq_exit) from [<c0209cf0>] (handle_IPI+0x650/0x7f4)
(handle_IPI) from [<c02015bc>] (gic_handle_irq+0x108/0x118)
(gic_handle_irq) from [<c0558ee4>] (__irq_usr+0x44/0x5c)
...

If __ethtool_get_link_ksettings() is failed in
prb_calc_retire_blk_tmo(), msec and tmo will be zero, so tov_in_jiffies
is zero and the timer expire for retire_blk_timer is turn to
mod_timer(&pkc->retire_blk_timer, jiffies + 0),
which will trigger cpu usage of softirq is 100%.

Fixes: f6fb8f100b80 ("af-packet: TPACKET_V3 flexible buffer implementation.")
Tested-by: Xiao Jiangfeng <xiaojiangfeng@huawei.com>
Signed-off-by: Mao Wenan <maowenan@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 7204e7bbebb0..ac65e66d1d72 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -552,7 +552,8 @@ static int prb_calc_retire_blk_tmo(struct packet_sock *po,
 			msec = 1;
 			div = ecmd.base.speed / 1000;
 		}
-	}
+	} else
+		return DEFAULT_PRB_RETIRE_TOV;
 
 	mbits = (blk_size_in_bytes * 8) / (1024 * 1024);
 
-- 
2.20.1


From a18e32a12560d2ed3a7ca8dda2a68d4bdbb3bef8 Mon Sep 17 00:00:00 2001
From: Chuhong Yuan <hslester96@gmail.com>
Date: Tue, 10 Dec 2019 00:22:07 +0800
Subject: [PATCH 02/13] fjes: fix missed check in fjes_acpi_add

[ Upstream commit a288f105a03a7e0e629a8da2b31f34ebf0343ee2 ]

fjes_acpi_add() misses a check for platform_device_register_simple().
Add a check to fix it.

Fixes: 658d439b2292 ("fjes: Introduce FUJITSU Extended Socket Network Device driver")
Signed-off-by: Chuhong Yuan <hslester96@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/fjes/fjes_main.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/fjes/fjes_main.c b/drivers/net/fjes/fjes_main.c
index 61a9843346ad..1979f8f8dac7 100644
--- a/drivers/net/fjes/fjes_main.c
+++ b/drivers/net/fjes/fjes_main.c
@@ -181,6 +181,9 @@ static int fjes_acpi_add(struct acpi_device *device)
 	/* create platform_device */
 	plat_dev = platform_device_register_simple(DRV_NAME, 0, fjes_resource,
 						   ARRAY_SIZE(fjes_resource));
+	if (IS_ERR(plat_dev))
+		return PTR_ERR(plat_dev);
+
 	device->driver_data = plat_dev;
 
 	return 0;
-- 
2.20.1


From 092d15faeb9ad21131435d197d5537122f738d22 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Thu, 19 Dec 2019 23:24:47 +0000
Subject: [PATCH 03/13] mod_devicetable: fix PHY module format

[ Upstream commit d2ed49cf6c13e379c5819aa5ac20e1f9674ebc89 ]

When a PHY is probed, if the top bit is set, we end up requesting a
module with the string "mdio:-10101110000000100101000101010001" -
the top bit is printed to a signed -1 value. This leads to the module
not being loaded.

Fix the module format string and the macro generating the values for
it to ensure that we only print unsigned types and the top bit is
always 0/1. We correctly end up with
"mdio:10101110000000100101000101010001".

Fixes: 8626d3b43280 ("phylib: Support phy module autoloading")
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/mod_devicetable.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index 01797cb4587e..867db9b9384c 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -551,9 +551,9 @@ struct platform_device_id {
 #define MDIO_NAME_SIZE		32
 #define MDIO_MODULE_PREFIX	"mdio:"
 
-#define MDIO_ID_FMT "%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d"
+#define MDIO_ID_FMT "%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u"
 #define MDIO_ID_ARGS(_id) \
-	(_id)>>31, ((_id)>>30) & 1, ((_id)>>29) & 1, ((_id)>>28) & 1,	\
+	((_id)>>31) & 1, ((_id)>>30) & 1, ((_id)>>29) & 1, ((_id)>>28) & 1, \
 	((_id)>>27) & 1, ((_id)>>26) & 1, ((_id)>>25) & 1, ((_id)>>24) & 1, \
 	((_id)>>23) & 1, ((_id)>>22) & 1, ((_id)>>21) & 1, ((_id)>>20) & 1, \
 	((_id)>>19) & 1, ((_id)>>18) & 1, ((_id)>>17) & 1, ((_id)>>16) & 1, \
-- 
2.20.1


From 41de174cea2c876d90f701828594b1ec9ede935a Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Fri, 20 Dec 2019 14:31:40 +0100
Subject: [PATCH 04/13] net: dst: Force 4-byte alignment of dst_metrics

[ Upstream commit 258a980d1ec23e2c786e9536a7dd260bea74bae6 ]

When storing a pointer to a dst_metrics structure in dst_entry._metrics,
two flags are added in the least significant bits of the pointer value.
Hence this assumes all pointers to dst_metrics structures have at least
4-byte alignment.

However, on m68k, the minimum alignment of 32-bit values is 2 bytes, not
4 bytes.  Hence in some kernel builds, dst_default_metrics may be only
2-byte aligned, leading to obscure boot warnings like:

    WARNING: CPU: 0 PID: 7 at lib/refcount.c:28 refcount_warn_saturate+0x44/0x9a
    refcount_t: underflow; use-after-free.
    Modules linked in:
    CPU: 0 PID: 7 Comm: ksoftirqd/0 Tainted: G        W         5.5.0-rc2-atari-01448-g114a1a1038af891d-dirty #261
    Stack from 10835e6c:
	    10835e6c 0038134f 00023fa6 00394b0f 0000001c 00000009 00321560 00023fea
	    00394b0f 0000001c 001a70f8 00000009 00000000 10835eb4 00000001 00000000
	    04208040 0000000a 00394b4a 10835ed4 00043aa8 001a70f8 00394b0f 0000001c
	    00000009 00394b4a 0026aba8 003215a4 00000003 00000000 0026d5a8 00000001
	    003215a4 003a4361 003238d6 000001f0 00000000 003215a4 10aa3b00 00025e84
	    003ddb00 10834000 002416a8 10aa3b00 00000000 00000080 000aa038 0004854a
    Call Trace: [<00023fa6>] __warn+0xb2/0xb4
     [<00023fea>] warn_slowpath_fmt+0x42/0x64
     [<001a70f8>] refcount_warn_saturate+0x44/0x9a
     [<00043aa8>] printk+0x0/0x18
     [<001a70f8>] refcount_warn_saturate+0x44/0x9a
     [<0026aba8>] refcount_sub_and_test.constprop.73+0x38/0x3e
     [<0026d5a8>] ipv4_dst_destroy+0x5e/0x7e
     [<00025e84>] __local_bh_enable_ip+0x0/0x8e
     [<002416a8>] dst_destroy+0x40/0xae

Fix this by forcing 4-byte alignment of all dst_metrics structures.

Fixes: e5fd387ad5b30ca3 ("ipv6: do not overwrite inetpeer metrics prematurely")
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/dst.h b/include/net/dst.h
index ffc8ee0ea5e5..851cf1124240 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -93,7 +93,7 @@ struct dst_entry {
 struct dst_metrics {
 	u32		metrics[RTAX_MAX];
 	refcount_t	refcnt;
-};
+} __aligned(4);		/* Low pointer bits contain DST_METRICS_FLAGS */
 extern const struct dst_metrics dst_default_metrics;
 
 u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old);
-- 
2.20.1


From 3c985881ecb1e4daac126d88af57353923f8c393 Mon Sep 17 00:00:00 2001
From: Navid Emamdoost <navid.emamdoost@gmail.com>
Date: Sat, 14 Dec 2019 19:10:44 -0600
Subject: [PATCH 05/13] net: gemini: Fix memory leak in gmac_setup_txqs

[ Upstream commit f37f710353677639bc5d37ee785335994adf2529 ]

In the implementation of gmac_setup_txqs() the allocated desc_ring is
leaked if TX queue base is not aligned. Release it via
dma_free_coherent.

Fixes: 4d5ae32f5e1e ("net: ethernet: Add a driver for Gemini gigabit ethernet")
Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cortina/gemini.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index 4af78de0e077..01a212097836 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -577,6 +577,8 @@ static int gmac_setup_txqs(struct net_device *netdev)
 
 	if (port->txq_dma_base & ~DMA_Q_BASE_MASK) {
 		dev_warn(geth->dev, "TX queue base is not aligned\n");
+		dma_free_coherent(geth->dev, len * sizeof(*desc_ring),
+				  desc_ring, port->txq_dma_base);
 		kfree(skb_tab);
 		return -ENOMEM;
 	}
-- 
2.20.1


From 0c488991a9595e787721fbab149c7aa7791dd0b6 Mon Sep 17 00:00:00 2001
From: Jiangfeng Xiao <xiaojiangfeng@huawei.com>
Date: Thu, 19 Dec 2019 10:08:07 +0800
Subject: [PATCH 06/13] net: hisilicon: Fix a BUG trigered by wrong bytes_compl

[ Upstream commit 90b3b339364c76baa2436445401ea9ade040c216 ]

When doing stress test, we get the following trace:
kernel BUG at lib/dynamic_queue_limits.c:26!
Internal error: Oops - BUG: 0 [#1] SMP ARM
Modules linked in: hip04_eth
CPU: 0 PID: 2003 Comm: tDblStackPcap0 Tainted: G           O L  4.4.197 #1
Hardware name: Hisilicon A15
task: c3637668 task.stack: de3bc000
PC is at dql_completed+0x18/0x154
LR is at hip04_tx_reclaim+0x110/0x174 [hip04_eth]
pc : [<c041abfc>]    lr : [<bf0003a8>]    psr: 800f0313
sp : de3bdc2c  ip : 00000000  fp : c020fb10
r10: 00000000  r9 : c39b4224  r8 : 00000001
r7 : 00000046  r6 : c39b4000  r5 : 0078f392  r4 : 0078f392
r3 : 00000047  r2 : 00000000  r1 : 00000046  r0 : df5d5c80
Flags: Nzcv  IRQs on  FIQs on  Mode SVC_32  ISA ARM  Segment user
Control: 32c5387d  Table: 1e189b80  DAC: 55555555
Process tDblStackPcap0 (pid: 2003, stack limit = 0xde3bc190)
Stack: (0xde3bdc2c to 0xde3be000)
[<c041abfc>] (dql_completed) from [<bf0003a8>] (hip04_tx_reclaim+0x110/0x174 [hip04_eth])
[<bf0003a8>] (hip04_tx_reclaim [hip04_eth]) from [<bf0012c0>] (hip04_rx_poll+0x20/0x388 [hip04_eth])
[<bf0012c0>] (hip04_rx_poll [hip04_eth]) from [<c04c8d9c>] (net_rx_action+0x120/0x374)
[<c04c8d9c>] (net_rx_action) from [<c021eaf4>] (__do_softirq+0x218/0x318)
[<c021eaf4>] (__do_softirq) from [<c021eea0>] (irq_exit+0x88/0xac)
[<c021eea0>] (irq_exit) from [<c0240130>] (msa_irq_exit+0x11c/0x1d4)
[<c0240130>] (msa_irq_exit) from [<c0267ba8>] (__handle_domain_irq+0x110/0x148)
[<c0267ba8>] (__handle_domain_irq) from [<c0201588>] (gic_handle_irq+0xd4/0x118)
[<c0201588>] (gic_handle_irq) from [<c0558360>] (__irq_svc+0x40/0x58)
Exception stack(0xde3bdde0 to 0xde3bde28)
dde0: 00000000 00008001 c3637668 00000000 00000000 a00f0213 dd3627a0 c0af6380
de00: c086d380 a00f0213 c0a22a50 de3bde6c 00000002 de3bde30 c0558138 c055813c
de20: 600f0213 ffffffff
[<c0558360>] (__irq_svc) from [<c055813c>] (_raw_spin_unlock_irqrestore+0x44/0x54)
Kernel panic - not syncing: Fatal exception in interrupt

Pre-modification code:
int hip04_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
{
[...]
[1]	priv->tx_head = TX_NEXT(tx_head);
[2]	count++;
[3]	netdev_sent_queue(ndev, skb->len);
[...]
}
An rx interrupt occurs if hip04_mac_start_xmit just executes to the line 2,
tx_head has been updated, but corresponding 'skb->len' has not been
added to dql_queue.

And then
hip04_mac_interrupt->__napi_schedule->hip04_rx_poll->hip04_tx_reclaim

In hip04_tx_reclaim, because tx_head has been updated,
bytes_compl will plus an additional "skb-> len"
which has not been added to dql_queue. And then
trigger the BUG_ON(bytes_compl > num_queued - dql->num_completed).

To solve the problem described above, we put
"netdev_sent_queue(ndev, skb->len);"
before
"priv->tx_head = TX_NEXT(tx_head);"

Fixes: a41ea46a9a12 ("net: hisilicon: new hip04 ethernet driver")
Signed-off-by: Jiangfeng Xiao <xiaojiangfeng@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hip04_eth.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c
index e8936ae46add..718afa4be2a0 100644
--- a/drivers/net/ethernet/hisilicon/hip04_eth.c
+++ b/drivers/net/ethernet/hisilicon/hip04_eth.c
@@ -456,9 +456,9 @@ hip04_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	skb_tx_timestamp(skb);
 
 	hip04_set_xmit_desc(priv, phys);
-	priv->tx_head = TX_NEXT(tx_head);
 	count++;
 	netdev_sent_queue(ndev, skb->len);
+	priv->tx_head = TX_NEXT(tx_head);
 
 	stats->tx_bytes += skb->len;
 	stats->tx_packets++;
-- 
2.20.1


From 4040f6a359ecbb96d6d68042823a5eb1292075a4 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Wed, 18 Dec 2019 17:21:55 +0800
Subject: [PATCH 07/13] net: nfc: nci: fix a possible sleep-in-atomic-context
 bug in nci_uart_tty_receive()

[ Upstream commit b7ac893652cafadcf669f78452329727e4e255cc ]

The kernel may sleep while holding a spinlock.
The function call path (from bottom to top) in Linux 4.19 is:

net/nfc/nci/uart.c, 349:
	nci_skb_alloc in nci_uart_default_recv_buf
net/nfc/nci/uart.c, 255:
	(FUNC_PTR)nci_uart_default_recv_buf in nci_uart_tty_receive
net/nfc/nci/uart.c, 254:
	spin_lock in nci_uart_tty_receive

nci_skb_alloc(GFP_KERNEL) can sleep at runtime.
(FUNC_PTR) means a function pointer is called.

To fix this bug, GFP_KERNEL is replaced with GFP_ATOMIC for
nci_skb_alloc().

This bug is found by a static analysis tool STCheck written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/nfc/nci/uart.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/nfc/nci/uart.c b/net/nfc/nci/uart.c
index a66f102c6c01..040576dd73bb 100644
--- a/net/nfc/nci/uart.c
+++ b/net/nfc/nci/uart.c
@@ -348,7 +348,7 @@ static int nci_uart_default_recv_buf(struct nci_uart *nu, const u8 *data,
 			nu->rx_packet_len = -1;
 			nu->rx_skb = nci_skb_alloc(nu->ndev,
 						   NCI_MAX_PACKET_SIZE,
-						   GFP_KERNEL);
+						   GFP_ATOMIC);
 			if (!nu->rx_skb)
 				return -ENOMEM;
 		}
-- 
2.20.1


From 411a5d09b9d846500c5485819e1c9d17ad6cc7a7 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben@decadent.org.uk>
Date: Tue, 17 Dec 2019 01:57:40 +0000
Subject: [PATCH 08/13] net: qlogic: Fix error paths in
 ql_alloc_large_buffers()

[ Upstream commit cad46039e4c99812db067c8ac22a864960e7acc4 ]

ql_alloc_large_buffers() has the usual RX buffer allocation
loop where it allocates skbs and maps them for DMA.  It also
treats failure as a fatal error.

There are (at least) three bugs in the error paths:

1. ql_free_large_buffers() assumes that the lrg_buf[] entry for the
first buffer that couldn't be allocated will have .skb == NULL.
But the qla_buf[] array is not zero-initialised.

2. ql_free_large_buffers() DMA-unmaps all skbs in lrg_buf[].  This is
incorrect for the last allocated skb, if DMA mapping failed.

3. Commit 1acb8f2a7a9f ("net: qlogic: Fix memory leak in
ql_alloc_large_buffers") added a direct call to dev_kfree_skb_any()
after the skb is recorded in lrg_buf[], so ql_free_large_buffers()
will double-free it.

The bugs are somewhat inter-twined, so fix them all at once:

* Clear each entry in qla_buf[] before attempting to allocate
  an skb for it.  This goes half-way to fixing bug 1.
* Set the .skb field only after the skb is DMA-mapped.  This
  fixes the rest.

Fixes: 1357bfcf7106 ("qla3xxx: Dynamically size the rx buffer queue ...")
Fixes: 0f8ab89e825f ("qla3xxx: Check return code from pci_map_single() ...")
Fixes: 1acb8f2a7a9f ("net: qlogic: Fix memory leak in ql_alloc_large_buffers")
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qla3xxx.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c
index 783ee6a32b5d..1b5e098b2367 100644
--- a/drivers/net/ethernet/qlogic/qla3xxx.c
+++ b/drivers/net/ethernet/qlogic/qla3xxx.c
@@ -2757,6 +2757,9 @@ static int ql_alloc_large_buffers(struct ql3_adapter *qdev)
 	int err;
 
 	for (i = 0; i < qdev->num_large_buffers; i++) {
+		lrg_buf_cb = &qdev->lrg_buf[i];
+		memset(lrg_buf_cb, 0, sizeof(struct ql_rcv_buf_cb));
+
 		skb = netdev_alloc_skb(qdev->ndev,
 				       qdev->lrg_buffer_len);
 		if (unlikely(!skb)) {
@@ -2767,11 +2770,7 @@ static int ql_alloc_large_buffers(struct ql3_adapter *qdev)
 			ql_free_large_buffers(qdev);
 			return -ENOMEM;
 		} else {
-
-			lrg_buf_cb = &qdev->lrg_buf[i];
-			memset(lrg_buf_cb, 0, sizeof(struct ql_rcv_buf_cb));
 			lrg_buf_cb->index = i;
-			lrg_buf_cb->skb = skb;
 			/*
 			 * We save some space to copy the ethhdr from first
 			 * buffer
@@ -2793,6 +2792,7 @@ static int ql_alloc_large_buffers(struct ql3_adapter *qdev)
 				return -ENOMEM;
 			}
 
+			lrg_buf_cb->skb = skb;
 			dma_unmap_addr_set(lrg_buf_cb, mapaddr, map);
 			dma_unmap_len_set(lrg_buf_cb, maplen,
 					  qdev->lrg_buffer_len -
-- 
2.20.1


From f52e6c933d79286b4ba1cb0f14d95680992359d2 Mon Sep 17 00:00:00 2001
From: Cristian Birsan <cristian.birsan@microchip.com>
Date: Thu, 12 Dec 2019 13:52:47 +0200
Subject: [PATCH 09/13] net: usb: lan78xx: Fix suspend/resume PHY register
 access error

[ Upstream commit 20032b63586ac6c28c936dff696981159913a13f ]

Lan78xx driver accesses the PHY registers through MDIO bus over USB
connection. When performing a suspend/resume, the PHY registers can be
accessed before the USB connection is resumed. This will generate an
error and will prevent the device to resume correctly.
This patch adds the dependency between the MDIO bus and USB device to
allow correct handling of suspend/resume.

Fixes: ce85e13ad6ef ("lan78xx: Update to use phylib instead of mii_if_info.")
Signed-off-by: Cristian Birsan <cristian.birsan@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/lan78xx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 50bf4b2080d5..6dd24a1ca10d 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -1823,6 +1823,7 @@ static int lan78xx_mdio_init(struct lan78xx_net *dev)
 	dev->mdiobus->read = lan78xx_mdiobus_read;
 	dev->mdiobus->write = lan78xx_mdiobus_write;
 	dev->mdiobus->name = "lan78xx-mdiobus";
+	dev->mdiobus->parent = &dev->udev->dev;
 
 	snprintf(dev->mdiobus->id, MII_BUS_ID_SIZE, "usb-%03d:%03d",
 		 dev->udev->bus->busnum, dev->udev->devnum);
-- 
2.20.1


From 62ad03642ee0e1bba29afb88049bcdc144d9ecf3 Mon Sep 17 00:00:00 2001
From: Manish Chopra <manishc@marvell.com>
Date: Thu, 19 Dec 2019 10:35:16 -0800
Subject: [PATCH 10/13] qede: Disable hardware gro when xdp prog is installed

[ Upstream commit 4c8dc00503db24deaf0b89dddfa84b7cba7cd4ce ]

commit 18c602dee472 ("qede: Use NETIF_F_GRO_HW.") introduced
a regression in driver that when xdp program is installed on
qede device, device's aggregation feature (hardware GRO) is not
getting disabled, which is unexpected with xdp.

Fixes: 18c602dee472 ("qede: Use NETIF_F_GRO_HW.")
Signed-off-by: Manish Chopra <manishc@marvell.com>
Signed-off-by: Ariel Elior <aelior@marvell.com>
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qede/qede_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 630b13a9c3d5..0d8e39ffbcd1 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -1362,6 +1362,7 @@ static int qede_alloc_mem_rxq(struct qede_dev *edev, struct qede_rx_queue *rxq)
 		rxq->rx_buf_seg_size = roundup_pow_of_two(size);
 	} else {
 		rxq->rx_buf_seg_size = PAGE_SIZE;
+		edev->ndev->features &= ~NETIF_F_GRO_HW;
 	}
 
 	/* Allocate the parallel driver ring for Rx buffers */
@@ -1406,6 +1407,7 @@ static int qede_alloc_mem_rxq(struct qede_dev *edev, struct qede_rx_queue *rxq)
 		}
 	}
 
+	edev->gro_disable = !(edev->ndev->features & NETIF_F_GRO_HW);
 	if (!edev->gro_disable)
 		qede_set_tpa_param(rxq);
 err:
@@ -1606,8 +1608,6 @@ static void qede_init_fp(struct qede_dev *edev)
 		snprintf(fp->name, sizeof(fp->name), "%s-fp-%d",
 			 edev->ndev->name, queue_id);
 	}
-
-	edev->gro_disable = !(edev->ndev->features & NETIF_F_GRO_HW);
 }
 
 static int qede_set_real_num_queues(struct qede_dev *edev)
-- 
2.20.1


From ecb8749fbe29f1d187e9d86396171138e86a3237 Mon Sep 17 00:00:00 2001
From: Manish Chopra <manishc@marvell.com>
Date: Thu, 12 Dec 2019 06:49:28 -0800
Subject: [PATCH 11/13] qede: Fix multicast mac configuration

[ Upstream commit 0af67e49b018e7280a4227bfe7b6005bc9d3e442 ]

Driver doesn't accommodate the configuration for max number
of multicast mac addresses, in such particular case it leaves
the device with improper/invalid multicast configuration state,
causing connectivity issues (in lacp bonding like scenarios).

Signed-off-by: Manish Chopra <manishc@marvell.com>
Signed-off-by: Ariel Elior <aelior@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qede/qede_filter.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c
index b16ce7d93caf..c3d5d40afec0 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_filter.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c
@@ -1230,7 +1230,7 @@ qede_configure_mcast_filtering(struct net_device *ndev,
 	netif_addr_lock_bh(ndev);
 
 	mc_count = netdev_mc_count(ndev);
-	if (mc_count < 64) {
+	if (mc_count <= 64) {
 		netdev_for_each_mc_addr(ha, ndev) {
 			ether_addr_copy(temp, ha->addr);
 			temp += ETH_ALEN;
-- 
2.20.1


From f0085c325b0e66092c4ec98758b94a449dbd2283 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 9 Dec 2019 13:45:54 +0800
Subject: [PATCH 12/13] sctp: fully initialize v4 addr in some functions

[ Upstream commit b6f3320b1d5267e7b583a6d0c88dda518101740c ]

Syzbot found a crash:

  BUG: KMSAN: uninit-value in crc32_body lib/crc32.c:112 [inline]
  BUG: KMSAN: uninit-value in crc32_le_generic lib/crc32.c:179 [inline]
  BUG: KMSAN: uninit-value in __crc32c_le_base+0x4fa/0xd30 lib/crc32.c:202
  Call Trace:
    crc32_body lib/crc32.c:112 [inline]
    crc32_le_generic lib/crc32.c:179 [inline]
    __crc32c_le_base+0x4fa/0xd30 lib/crc32.c:202
    chksum_update+0xb2/0x110 crypto/crc32c_generic.c:90
    crypto_shash_update+0x4c5/0x530 crypto/shash.c:107
    crc32c+0x150/0x220 lib/libcrc32c.c:47
    sctp_csum_update+0x89/0xa0 include/net/sctp/checksum.h:36
    __skb_checksum+0x1297/0x12a0 net/core/skbuff.c:2640
    sctp_compute_cksum include/net/sctp/checksum.h:59 [inline]
    sctp_packet_pack net/sctp/output.c:528 [inline]
    sctp_packet_transmit+0x40fb/0x4250 net/sctp/output.c:597
    sctp_outq_flush_transports net/sctp/outqueue.c:1146 [inline]
    sctp_outq_flush+0x1823/0x5d80 net/sctp/outqueue.c:1194
    sctp_outq_uncork+0xd0/0xf0 net/sctp/outqueue.c:757
    sctp_cmd_interpreter net/sctp/sm_sideeffect.c:1781 [inline]
    sctp_side_effects net/sctp/sm_sideeffect.c:1184 [inline]
    sctp_do_sm+0x8fe1/0x9720 net/sctp/sm_sideeffect.c:1155
    sctp_primitive_REQUESTHEARTBEAT+0x175/0x1a0 net/sctp/primitive.c:185
    sctp_apply_peer_addr_params+0x212/0x1d40 net/sctp/socket.c:2433
    sctp_setsockopt_peer_addr_params net/sctp/socket.c:2686 [inline]
    sctp_setsockopt+0x189bb/0x19090 net/sctp/socket.c:4672

The issue was caused by transport->ipaddr set with uninit addr param, which
was passed by:

  sctp_transport_init net/sctp/transport.c:47 [inline]
  sctp_transport_new+0x248/0xa00 net/sctp/transport.c:100
  sctp_assoc_add_peer+0x5ba/0x2030 net/sctp/associola.c:611
  sctp_process_param net/sctp/sm_make_chunk.c:2524 [inline]

where 'addr' is set by sctp_v4_from_addr_param(), and it doesn't initialize
the padding of addr->v4.

Later when calling sctp_make_heartbeat(), hbinfo.daddr(=transport->ipaddr)
will become the part of skb, and the issue occurs.

This patch is to fix it by initializing the padding of addr->v4 in
sctp_v4_from_addr_param(), as well as other functions that do the similar
thing, and these functions shouldn't trust that the caller initializes the
memory, as Marcelo suggested.

Reported-by: syzbot+6dcbfea81cd3d4dd0b02@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/protocol.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 6d36f74ad295..269b528e50b9 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -242,6 +242,7 @@ static void sctp_v4_from_skb(union sctp_addr *addr, struct sk_buff *skb,
 		sa->sin_port = sh->dest;
 		sa->sin_addr.s_addr = ip_hdr(skb)->daddr;
 	}
+	memset(sa->sin_zero, 0, sizeof(sa->sin_zero));
 }
 
 /* Initialize an sctp_addr from a socket. */
@@ -250,6 +251,7 @@ static void sctp_v4_from_sk(union sctp_addr *addr, struct sock *sk)
 	addr->v4.sin_family = AF_INET;
 	addr->v4.sin_port = 0;
 	addr->v4.sin_addr.s_addr = inet_sk(sk)->inet_rcv_saddr;
+	memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
 }
 
 /* Initialize sk->sk_rcv_saddr from sctp_addr. */
@@ -272,6 +274,7 @@ static void sctp_v4_from_addr_param(union sctp_addr *addr,
 	addr->v4.sin_family = AF_INET;
 	addr->v4.sin_port = port;
 	addr->v4.sin_addr.s_addr = param->v4.addr.s_addr;
+	memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
 }
 
 /* Initialize an address parameter from a sctp_addr and return the length
@@ -296,6 +299,7 @@ static void sctp_v4_dst_saddr(union sctp_addr *saddr, struct flowi4 *fl4,
 	saddr->v4.sin_family = AF_INET;
 	saddr->v4.sin_port = port;
 	saddr->v4.sin_addr.s_addr = fl4->saddr;
+	memset(saddr->v4.sin_zero, 0, sizeof(saddr->v4.sin_zero));
 }
 
 /* Compare two addresses exactly. */
@@ -318,6 +322,7 @@ static void sctp_v4_inaddr_any(union sctp_addr *addr, __be16 port)
 	addr->v4.sin_family = AF_INET;
 	addr->v4.sin_addr.s_addr = htonl(INADDR_ANY);
 	addr->v4.sin_port = port;
+	memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
 }
 
 /* Is this a wildcard address? */
-- 
2.20.1


From 7abdada2c8f07a898cf218f201e5c422cc3dfd53 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Mon, 9 Dec 2019 08:56:34 +0200
Subject: [PATCH 13/13] selftests: forwarding: Delete IPv6 address at the end

[ Upstream commit 65cb13986229cec02635a1ecbcd1e2dd18353201 ]

When creating the second host in h2_create(), two addresses are assigned
to the interface, but only one is deleted. When running the test twice
in a row the following error is observed:

$ ./router_bridge_vlan.sh
TEST: ping                                                          [ OK ]
TEST: ping6                                                         [ OK ]
TEST: vlan                                                          [ OK ]
$ ./router_bridge_vlan.sh
RTNETLINK answers: File exists
TEST: ping                                                          [ OK ]
TEST: ping6                                                         [ OK ]
TEST: vlan                                                          [ OK ]

Fix this by deleting the address during cleanup.

Fixes: 5b1e7f9ebd56 ("selftests: forwarding: Test routed bridge interface")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/router_bridge_vlan.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh b/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh
index fef88eb4b873..fa6a88c50750 100755
--- a/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh
+++ b/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh
@@ -36,7 +36,7 @@ h2_destroy()
 {
 	ip -6 route del 2001:db8:1::/64 vrf v$h2
 	ip -4 route del 192.0.2.0/28 vrf v$h2
-	simple_if_fini $h2 192.0.2.130/28
+	simple_if_fini $h2 192.0.2.130/28 2001:db8:2::2/64
 }
 
 router_create()
-- 
2.20.1


[-- Attachment #3: net_54.mbox --]
[-- Type: Application/Octet-Stream, Size: 68926 bytes --]

From 835f499c31cc419fa1e5e0ab09708b151b774173 Mon Sep 17 00:00:00 2001
From: Mao Wenan <maowenan@huawei.com>
Date: Mon, 9 Dec 2019 21:31:25 +0800
Subject: [PATCH 01/27] af_packet: set defaule value for tmo

[ Upstream commit b43d1f9f7067c6759b1051e8ecb84e82cef569fe ]

There is softlockup when using TPACKET_V3:
...
NMI watchdog: BUG: soft lockup - CPU#2 stuck for 60010ms!
(__irq_svc) from [<c0558a0c>] (_raw_spin_unlock_irqrestore+0x44/0x54)
(_raw_spin_unlock_irqrestore) from [<c027b7e8>] (mod_timer+0x210/0x25c)
(mod_timer) from [<c0549c30>]
(prb_retire_rx_blk_timer_expired+0x68/0x11c)
(prb_retire_rx_blk_timer_expired) from [<c027a7ac>]
(call_timer_fn+0x90/0x17c)
(call_timer_fn) from [<c027ab6c>] (run_timer_softirq+0x2d4/0x2fc)
(run_timer_softirq) from [<c021eaf4>] (__do_softirq+0x218/0x318)
(__do_softirq) from [<c021eea0>] (irq_exit+0x88/0xac)
(irq_exit) from [<c0240130>] (msa_irq_exit+0x11c/0x1d4)
(msa_irq_exit) from [<c0209cf0>] (handle_IPI+0x650/0x7f4)
(handle_IPI) from [<c02015bc>] (gic_handle_irq+0x108/0x118)
(gic_handle_irq) from [<c0558ee4>] (__irq_usr+0x44/0x5c)
...

If __ethtool_get_link_ksettings() is failed in
prb_calc_retire_blk_tmo(), msec and tmo will be zero, so tov_in_jiffies
is zero and the timer expire for retire_blk_timer is turn to
mod_timer(&pkc->retire_blk_timer, jiffies + 0),
which will trigger cpu usage of softirq is 100%.

Fixes: f6fb8f100b80 ("af-packet: TPACKET_V3 flexible buffer implementation.")
Tested-by: Xiao Jiangfeng <xiaojiangfeng@huawei.com>
Signed-off-by: Mao Wenan <maowenan@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 82a50e850245..529d4ce945db 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -544,7 +544,8 @@ static int prb_calc_retire_blk_tmo(struct packet_sock *po,
 			msec = 1;
 			div = ecmd.base.speed / 1000;
 		}
-	}
+	} else
+		return DEFAULT_PRB_RETIRE_TOV;
 
 	mbits = (blk_size_in_bytes * 8) / (1024 * 1024);
 
-- 
2.20.1


From 08a918863bedb23994fa37520968eb9996fbdcb6 Mon Sep 17 00:00:00 2001
From: Chuhong Yuan <hslester96@gmail.com>
Date: Tue, 10 Dec 2019 00:22:07 +0800
Subject: [PATCH 02/27] fjes: fix missed check in fjes_acpi_add

[ Upstream commit a288f105a03a7e0e629a8da2b31f34ebf0343ee2 ]

fjes_acpi_add() misses a check for platform_device_register_simple().
Add a check to fix it.

Fixes: 658d439b2292 ("fjes: Introduce FUJITSU Extended Socket Network Device driver")
Signed-off-by: Chuhong Yuan <hslester96@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/fjes/fjes_main.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/fjes/fjes_main.c b/drivers/net/fjes/fjes_main.c
index b517c1af9de0..91a1059517f5 100644
--- a/drivers/net/fjes/fjes_main.c
+++ b/drivers/net/fjes/fjes_main.c
@@ -166,6 +166,9 @@ static int fjes_acpi_add(struct acpi_device *device)
 	/* create platform_device */
 	plat_dev = platform_device_register_simple(DRV_NAME, 0, fjes_resource,
 						   ARRAY_SIZE(fjes_resource));
+	if (IS_ERR(plat_dev))
+		return PTR_ERR(plat_dev);
+
 	device->driver_data = plat_dev;
 
 	return 0;
-- 
2.20.1


From 8c93098d7f0b956a99789734dcb0ba8093f4cc5c Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Thu, 19 Dec 2019 23:24:47 +0000
Subject: [PATCH 03/27] mod_devicetable: fix PHY module format

[ Upstream commit d2ed49cf6c13e379c5819aa5ac20e1f9674ebc89 ]

When a PHY is probed, if the top bit is set, we end up requesting a
module with the string "mdio:-10101110000000100101000101010001" -
the top bit is printed to a signed -1 value. This leads to the module
not being loaded.

Fix the module format string and the macro generating the values for
it to ensure that we only print unsigned types and the top bit is
always 0/1. We correctly end up with
"mdio:10101110000000100101000101010001".

Fixes: 8626d3b43280 ("phylib: Support phy module autoloading")
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/mod_devicetable.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index 5714fd35a83c..e3596db077dc 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -587,9 +587,9 @@ struct platform_device_id {
 #define MDIO_NAME_SIZE		32
 #define MDIO_MODULE_PREFIX	"mdio:"
 
-#define MDIO_ID_FMT "%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d"
+#define MDIO_ID_FMT "%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u"
 #define MDIO_ID_ARGS(_id) \
-	(_id)>>31, ((_id)>>30) & 1, ((_id)>>29) & 1, ((_id)>>28) & 1,	\
+	((_id)>>31) & 1, ((_id)>>30) & 1, ((_id)>>29) & 1, ((_id)>>28) & 1, \
 	((_id)>>27) & 1, ((_id)>>26) & 1, ((_id)>>25) & 1, ((_id)>>24) & 1, \
 	((_id)>>23) & 1, ((_id)>>22) & 1, ((_id)>>21) & 1, ((_id)>>20) & 1, \
 	((_id)>>19) & 1, ((_id)>>18) & 1, ((_id)>>17) & 1, ((_id)>>16) & 1, \
-- 
2.20.1


From fafa170e6ab802d1b6e974c9e73d9215fddeb9fa Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Fri, 20 Dec 2019 14:31:40 +0100
Subject: [PATCH 04/27] net: dst: Force 4-byte alignment of dst_metrics

[ Upstream commit 258a980d1ec23e2c786e9536a7dd260bea74bae6 ]

When storing a pointer to a dst_metrics structure in dst_entry._metrics,
two flags are added in the least significant bits of the pointer value.
Hence this assumes all pointers to dst_metrics structures have at least
4-byte alignment.

However, on m68k, the minimum alignment of 32-bit values is 2 bytes, not
4 bytes.  Hence in some kernel builds, dst_default_metrics may be only
2-byte aligned, leading to obscure boot warnings like:

    WARNING: CPU: 0 PID: 7 at lib/refcount.c:28 refcount_warn_saturate+0x44/0x9a
    refcount_t: underflow; use-after-free.
    Modules linked in:
    CPU: 0 PID: 7 Comm: ksoftirqd/0 Tainted: G        W         5.5.0-rc2-atari-01448-g114a1a1038af891d-dirty #261
    Stack from 10835e6c:
	    10835e6c 0038134f 00023fa6 00394b0f 0000001c 00000009 00321560 00023fea
	    00394b0f 0000001c 001a70f8 00000009 00000000 10835eb4 00000001 00000000
	    04208040 0000000a 00394b4a 10835ed4 00043aa8 001a70f8 00394b0f 0000001c
	    00000009 00394b4a 0026aba8 003215a4 00000003 00000000 0026d5a8 00000001
	    003215a4 003a4361 003238d6 000001f0 00000000 003215a4 10aa3b00 00025e84
	    003ddb00 10834000 002416a8 10aa3b00 00000000 00000080 000aa038 0004854a
    Call Trace: [<00023fa6>] __warn+0xb2/0xb4
     [<00023fea>] warn_slowpath_fmt+0x42/0x64
     [<001a70f8>] refcount_warn_saturate+0x44/0x9a
     [<00043aa8>] printk+0x0/0x18
     [<001a70f8>] refcount_warn_saturate+0x44/0x9a
     [<0026aba8>] refcount_sub_and_test.constprop.73+0x38/0x3e
     [<0026d5a8>] ipv4_dst_destroy+0x5e/0x7e
     [<00025e84>] __local_bh_enable_ip+0x0/0x8e
     [<002416a8>] dst_destroy+0x40/0xae

Fix this by forcing 4-byte alignment of all dst_metrics structures.

Fixes: e5fd387ad5b30ca3 ("ipv6: do not overwrite inetpeer metrics prematurely")
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/dst.h b/include/net/dst.h
index fe62fe2eb781..8224dad2ae94 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -82,7 +82,7 @@ struct dst_entry {
 struct dst_metrics {
 	u32		metrics[RTAX_MAX];
 	refcount_t	refcnt;
-};
+} __aligned(4);		/* Low pointer bits contain DST_METRICS_FLAGS */
 extern const struct dst_metrics dst_default_metrics;
 
 u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old);
-- 
2.20.1


From 37853f13b6afeac2dcfb4df4c4f001385cd26fd8 Mon Sep 17 00:00:00 2001
From: Navid Emamdoost <navid.emamdoost@gmail.com>
Date: Sat, 14 Dec 2019 19:10:44 -0600
Subject: [PATCH 05/27] net: gemini: Fix memory leak in gmac_setup_txqs

[ Upstream commit f37f710353677639bc5d37ee785335994adf2529 ]

In the implementation of gmac_setup_txqs() the allocated desc_ring is
leaked if TX queue base is not aligned. Release it via
dma_free_coherent.

Fixes: 4d5ae32f5e1e ("net: ethernet: Add a driver for Gemini gigabit ethernet")
Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cortina/gemini.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index a8f4c69252ff..2814b96751b4 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -576,6 +576,8 @@ static int gmac_setup_txqs(struct net_device *netdev)
 
 	if (port->txq_dma_base & ~DMA_Q_BASE_MASK) {
 		dev_warn(geth->dev, "TX queue base is not aligned\n");
+		dma_free_coherent(geth->dev, len * sizeof(*desc_ring),
+				  desc_ring, port->txq_dma_base);
 		kfree(skb_tab);
 		return -ENOMEM;
 	}
-- 
2.20.1


From f347912afacf576d0acf604403cd88405da3ad38 Mon Sep 17 00:00:00 2001
From: Jiangfeng Xiao <xiaojiangfeng@huawei.com>
Date: Thu, 19 Dec 2019 10:08:07 +0800
Subject: [PATCH 06/27] net: hisilicon: Fix a BUG trigered by wrong bytes_compl

[ Upstream commit 90b3b339364c76baa2436445401ea9ade040c216 ]

When doing stress test, we get the following trace:
kernel BUG at lib/dynamic_queue_limits.c:26!
Internal error: Oops - BUG: 0 [#1] SMP ARM
Modules linked in: hip04_eth
CPU: 0 PID: 2003 Comm: tDblStackPcap0 Tainted: G           O L  4.4.197 #1
Hardware name: Hisilicon A15
task: c3637668 task.stack: de3bc000
PC is at dql_completed+0x18/0x154
LR is at hip04_tx_reclaim+0x110/0x174 [hip04_eth]
pc : [<c041abfc>]    lr : [<bf0003a8>]    psr: 800f0313
sp : de3bdc2c  ip : 00000000  fp : c020fb10
r10: 00000000  r9 : c39b4224  r8 : 00000001
r7 : 00000046  r6 : c39b4000  r5 : 0078f392  r4 : 0078f392
r3 : 00000047  r2 : 00000000  r1 : 00000046  r0 : df5d5c80
Flags: Nzcv  IRQs on  FIQs on  Mode SVC_32  ISA ARM  Segment user
Control: 32c5387d  Table: 1e189b80  DAC: 55555555
Process tDblStackPcap0 (pid: 2003, stack limit = 0xde3bc190)
Stack: (0xde3bdc2c to 0xde3be000)
[<c041abfc>] (dql_completed) from [<bf0003a8>] (hip04_tx_reclaim+0x110/0x174 [hip04_eth])
[<bf0003a8>] (hip04_tx_reclaim [hip04_eth]) from [<bf0012c0>] (hip04_rx_poll+0x20/0x388 [hip04_eth])
[<bf0012c0>] (hip04_rx_poll [hip04_eth]) from [<c04c8d9c>] (net_rx_action+0x120/0x374)
[<c04c8d9c>] (net_rx_action) from [<c021eaf4>] (__do_softirq+0x218/0x318)
[<c021eaf4>] (__do_softirq) from [<c021eea0>] (irq_exit+0x88/0xac)
[<c021eea0>] (irq_exit) from [<c0240130>] (msa_irq_exit+0x11c/0x1d4)
[<c0240130>] (msa_irq_exit) from [<c0267ba8>] (__handle_domain_irq+0x110/0x148)
[<c0267ba8>] (__handle_domain_irq) from [<c0201588>] (gic_handle_irq+0xd4/0x118)
[<c0201588>] (gic_handle_irq) from [<c0558360>] (__irq_svc+0x40/0x58)
Exception stack(0xde3bdde0 to 0xde3bde28)
dde0: 00000000 00008001 c3637668 00000000 00000000 a00f0213 dd3627a0 c0af6380
de00: c086d380 a00f0213 c0a22a50 de3bde6c 00000002 de3bde30 c0558138 c055813c
de20: 600f0213 ffffffff
[<c0558360>] (__irq_svc) from [<c055813c>] (_raw_spin_unlock_irqrestore+0x44/0x54)
Kernel panic - not syncing: Fatal exception in interrupt

Pre-modification code:
int hip04_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
{
[...]
[1]	priv->tx_head = TX_NEXT(tx_head);
[2]	count++;
[3]	netdev_sent_queue(ndev, skb->len);
[...]
}
An rx interrupt occurs if hip04_mac_start_xmit just executes to the line 2,
tx_head has been updated, but corresponding 'skb->len' has not been
added to dql_queue.

And then
hip04_mac_interrupt->__napi_schedule->hip04_rx_poll->hip04_tx_reclaim

In hip04_tx_reclaim, because tx_head has been updated,
bytes_compl will plus an additional "skb-> len"
which has not been added to dql_queue. And then
trigger the BUG_ON(bytes_compl > num_queued - dql->num_completed).

To solve the problem described above, we put
"netdev_sent_queue(ndev, skb->len);"
before
"priv->tx_head = TX_NEXT(tx_head);"

Fixes: a41ea46a9a12 ("net: hisilicon: new hip04 ethernet driver")
Signed-off-by: Jiangfeng Xiao <xiaojiangfeng@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hip04_eth.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c
index 4606a7e4a6d1..2ffe035e96d6 100644
--- a/drivers/net/ethernet/hisilicon/hip04_eth.c
+++ b/drivers/net/ethernet/hisilicon/hip04_eth.c
@@ -543,9 +543,9 @@ hip04_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	skb_tx_timestamp(skb);
 
 	hip04_set_xmit_desc(priv, phys);
-	priv->tx_head = TX_NEXT(tx_head);
 	count++;
 	netdev_sent_queue(ndev, skb->len);
+	priv->tx_head = TX_NEXT(tx_head);
 
 	stats->tx_bytes += skb->len;
 	stats->tx_packets++;
-- 
2.20.1


From 351a8b581159df6228636206e755165206b00923 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Wed, 18 Dec 2019 17:21:55 +0800
Subject: [PATCH 07/27] net: nfc: nci: fix a possible sleep-in-atomic-context
 bug in nci_uart_tty_receive()

[ Upstream commit b7ac893652cafadcf669f78452329727e4e255cc ]

The kernel may sleep while holding a spinlock.
The function call path (from bottom to top) in Linux 4.19 is:

net/nfc/nci/uart.c, 349:
	nci_skb_alloc in nci_uart_default_recv_buf
net/nfc/nci/uart.c, 255:
	(FUNC_PTR)nci_uart_default_recv_buf in nci_uart_tty_receive
net/nfc/nci/uart.c, 254:
	spin_lock in nci_uart_tty_receive

nci_skb_alloc(GFP_KERNEL) can sleep at runtime.
(FUNC_PTR) means a function pointer is called.

To fix this bug, GFP_KERNEL is replaced with GFP_ATOMIC for
nci_skb_alloc().

This bug is found by a static analysis tool STCheck written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/nfc/nci/uart.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/nfc/nci/uart.c b/net/nfc/nci/uart.c
index 78fe622eba65..11b554ce07ff 100644
--- a/net/nfc/nci/uart.c
+++ b/net/nfc/nci/uart.c
@@ -346,7 +346,7 @@ static int nci_uart_default_recv_buf(struct nci_uart *nu, const u8 *data,
 			nu->rx_packet_len = -1;
 			nu->rx_skb = nci_skb_alloc(nu->ndev,
 						   NCI_MAX_PACKET_SIZE,
-						   GFP_KERNEL);
+						   GFP_ATOMIC);
 			if (!nu->rx_skb)
 				return -ENOMEM;
 		}
-- 
2.20.1


From 9a409c9800f157ace2ca62474769e0770815adc6 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Thu, 19 Dec 2019 23:24:52 +0000
Subject: [PATCH 08/27] net: phy: ensure that phy IDs are correctly typed

[ Upstream commit 7d49a32a66d2215c5b3bf9bc67c9036ea9904111 ]

PHY IDs are 32-bit unsigned quantities. Ensure that they are always
treated as such, and not passed around as "int"s.

Fixes: 13d0ab6750b2 ("net: phy: check return code when requesting PHY driver module")
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 8 ++++----
 include/linux/phy.h          | 2 +-
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index adb66a2fae18..1f24083007b9 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -552,7 +552,7 @@ static const struct device_type mdio_bus_phy_type = {
 	.pm = MDIO_BUS_PHY_PM_OPS,
 };
 
-static int phy_request_driver_module(struct phy_device *dev, int phy_id)
+static int phy_request_driver_module(struct phy_device *dev, u32 phy_id)
 {
 	int ret;
 
@@ -564,15 +564,15 @@ static int phy_request_driver_module(struct phy_device *dev, int phy_id)
 	 * then modprobe isn't available.
 	 */
 	if (IS_ENABLED(CONFIG_MODULES) && ret < 0 && ret != -ENOENT) {
-		phydev_err(dev, "error %d loading PHY driver module for ID 0x%08x\n",
-			   ret, phy_id);
+		phydev_err(dev, "error %d loading PHY driver module for ID 0x%08lx\n",
+			   ret, (unsigned long)phy_id);
 		return ret;
 	}
 
 	return 0;
 }
 
-struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id,
+struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id,
 				     bool is_c45,
 				     struct phy_c45_device_ids *c45_ids)
 {
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 9a0e981df502..3d5d53313e6c 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -993,7 +993,7 @@ int phy_modify_paged_changed(struct phy_device *phydev, int page, u32 regnum,
 int phy_modify_paged(struct phy_device *phydev, int page, u32 regnum,
 		     u16 mask, u16 set);
 
-struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id,
+struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id,
 				     bool is_c45,
 				     struct phy_c45_device_ids *c45_ids);
 #if IS_ENABLED(CONFIG_PHYLIB)
-- 
2.20.1


From 6267d795b438d8b700895999822d354d7063e578 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben@decadent.org.uk>
Date: Tue, 17 Dec 2019 01:57:40 +0000
Subject: [PATCH 09/27] net: qlogic: Fix error paths in
 ql_alloc_large_buffers()

[ Upstream commit cad46039e4c99812db067c8ac22a864960e7acc4 ]

ql_alloc_large_buffers() has the usual RX buffer allocation
loop where it allocates skbs and maps them for DMA.  It also
treats failure as a fatal error.

There are (at least) three bugs in the error paths:

1. ql_free_large_buffers() assumes that the lrg_buf[] entry for the
first buffer that couldn't be allocated will have .skb == NULL.
But the qla_buf[] array is not zero-initialised.

2. ql_free_large_buffers() DMA-unmaps all skbs in lrg_buf[].  This is
incorrect for the last allocated skb, if DMA mapping failed.

3. Commit 1acb8f2a7a9f ("net: qlogic: Fix memory leak in
ql_alloc_large_buffers") added a direct call to dev_kfree_skb_any()
after the skb is recorded in lrg_buf[], so ql_free_large_buffers()
will double-free it.

The bugs are somewhat inter-twined, so fix them all at once:

* Clear each entry in qla_buf[] before attempting to allocate
  an skb for it.  This goes half-way to fixing bug 1.
* Set the .skb field only after the skb is DMA-mapped.  This
  fixes the rest.

Fixes: 1357bfcf7106 ("qla3xxx: Dynamically size the rx buffer queue ...")
Fixes: 0f8ab89e825f ("qla3xxx: Check return code from pci_map_single() ...")
Fixes: 1acb8f2a7a9f ("net: qlogic: Fix memory leak in ql_alloc_large_buffers")
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qla3xxx.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c
index b4b8ba00ee01..986f26578d34 100644
--- a/drivers/net/ethernet/qlogic/qla3xxx.c
+++ b/drivers/net/ethernet/qlogic/qla3xxx.c
@@ -2756,6 +2756,9 @@ static int ql_alloc_large_buffers(struct ql3_adapter *qdev)
 	int err;
 
 	for (i = 0; i < qdev->num_large_buffers; i++) {
+		lrg_buf_cb = &qdev->lrg_buf[i];
+		memset(lrg_buf_cb, 0, sizeof(struct ql_rcv_buf_cb));
+
 		skb = netdev_alloc_skb(qdev->ndev,
 				       qdev->lrg_buffer_len);
 		if (unlikely(!skb)) {
@@ -2766,11 +2769,7 @@ static int ql_alloc_large_buffers(struct ql3_adapter *qdev)
 			ql_free_large_buffers(qdev);
 			return -ENOMEM;
 		} else {
-
-			lrg_buf_cb = &qdev->lrg_buf[i];
-			memset(lrg_buf_cb, 0, sizeof(struct ql_rcv_buf_cb));
 			lrg_buf_cb->index = i;
-			lrg_buf_cb->skb = skb;
 			/*
 			 * We save some space to copy the ethhdr from first
 			 * buffer
@@ -2792,6 +2791,7 @@ static int ql_alloc_large_buffers(struct ql3_adapter *qdev)
 				return -ENOMEM;
 			}
 
+			lrg_buf_cb->skb = skb;
 			dma_unmap_addr_set(lrg_buf_cb, mapaddr, map);
 			dma_unmap_len_set(lrg_buf_cb, maplen,
 					  qdev->lrg_buffer_len -
-- 
2.20.1


From 3fa2424bcddb384fc153da6b47a2673decd97d33 Mon Sep 17 00:00:00 2001
From: Jouni Hogander <jouni.hogander@unikie.com>
Date: Tue, 17 Dec 2019 13:46:34 +0200
Subject: [PATCH 10/27] net-sysfs: Call dev_hold always in rx_queue_add_kobject

[ Upstream commit ddd9b5e3e765d8ed5a35786a6cb00111713fe161 ]

Dev_hold has to be called always in rx_queue_add_kobject.
Otherwise usage count drops below 0 in case of failure in
kobject_init_and_add.

Fixes: b8eb718348b8 ("net-sysfs: Fix reference count leak in rx|netdev_queue_add_kobject")
Reported-by: syzbot <syzbot+30209ea299c09d8785c9@syzkaller.appspotmail.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: David Miller <davem@davemloft.net>
Cc: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Signed-off-by: Jouni Hogander <jouni.hogander@unikie.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/net-sysfs.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index ae3bcb1540ec..b4db68e5caa9 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -919,14 +919,17 @@ static int rx_queue_add_kobject(struct net_device *dev, int index)
 	struct kobject *kobj = &queue->kobj;
 	int error = 0;
 
+	/* Kobject_put later will trigger rx_queue_release call which
+	 * decreases dev refcount: Take that reference here
+	 */
+	dev_hold(queue->dev);
+
 	kobj->kset = dev->queues_kset;
 	error = kobject_init_and_add(kobj, &rx_queue_ktype, NULL,
 				     "rx-%u", index);
 	if (error)
 		goto err;
 
-	dev_hold(queue->dev);
-
 	if (dev->sysfs_rx_queue_group) {
 		error = sysfs_create_group(kobj, dev->sysfs_rx_queue_group);
 		if (error)
-- 
2.20.1


From a75c8582e6d0dd68ba34f13df7217d0638aa53bb Mon Sep 17 00:00:00 2001
From: Cristian Birsan <cristian.birsan@microchip.com>
Date: Thu, 12 Dec 2019 13:52:47 +0200
Subject: [PATCH 11/27] net: usb: lan78xx: Fix suspend/resume PHY register
 access error

[ Upstream commit 20032b63586ac6c28c936dff696981159913a13f ]

Lan78xx driver accesses the PHY registers through MDIO bus over USB
connection. When performing a suspend/resume, the PHY registers can be
accessed before the USB connection is resumed. This will generate an
error and will prevent the device to resume correctly.
This patch adds the dependency between the MDIO bus and USB device to
allow correct handling of suspend/resume.

Fixes: ce85e13ad6ef ("lan78xx: Update to use phylib instead of mii_if_info.")
Signed-off-by: Cristian Birsan <cristian.birsan@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/lan78xx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index f24a1b0b801f..0becc79fd431 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -1808,6 +1808,7 @@ static int lan78xx_mdio_init(struct lan78xx_net *dev)
 	dev->mdiobus->read = lan78xx_mdiobus_read;
 	dev->mdiobus->write = lan78xx_mdiobus_write;
 	dev->mdiobus->name = "lan78xx-mdiobus";
+	dev->mdiobus->parent = &dev->udev->dev;
 
 	snprintf(dev->mdiobus->id, MII_BUS_ID_SIZE, "usb-%03d:%03d",
 		 dev->udev->bus->busnum, dev->udev->devnum);
-- 
2.20.1


From e73738787b50b0e0f50eb0791a1c2ff2d55c1166 Mon Sep 17 00:00:00 2001
From: John Hurley <john.hurley@netronome.com>
Date: Tue, 17 Dec 2019 11:28:56 +0000
Subject: [PATCH 12/27] nfp: flower: fix stats id allocation

[ Upstream commit 39f14c00b13c47186739a4cbc7a16e04d7fdbb60 ]

As flower rules are added, they are given a stats ID based on the number
of rules that can be supported in firmware. Only after the initial
allocation of all available IDs does the driver begin to reuse those that
have been released.

The initial allocation of IDs was modified to account for multiple memory
units on the offloaded device. However, this introduced a bug whereby the
counter that controls the IDs could be decremented before the ID was
assigned (where it is further decremented). This means that the stats ID
could be assigned as -1/0xfffffff which is out of range.

Fix this by only decrementing the main counter after the current ID has
been assigned.

Fixes: 467322e2627f ("nfp: flower: support multiple memory units for filter offloads")
Signed-off-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/metadata.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/metadata.c b/drivers/net/ethernet/netronome/nfp/flower/metadata.c
index 7c4a15e967df..5defd31d481c 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/metadata.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/metadata.c
@@ -65,17 +65,17 @@ static int nfp_get_stats_entry(struct nfp_app *app, u32 *stats_context_id)
 	freed_stats_id = priv->stats_ring_size;
 	/* Check for unallocated entries first. */
 	if (priv->stats_ids.init_unalloc > 0) {
-		if (priv->active_mem_unit == priv->total_mem_units) {
-			priv->stats_ids.init_unalloc--;
-			priv->active_mem_unit = 0;
-		}
-
 		*stats_context_id =
 			FIELD_PREP(NFP_FL_STAT_ID_STAT,
 				   priv->stats_ids.init_unalloc - 1) |
 			FIELD_PREP(NFP_FL_STAT_ID_MU_NUM,
 				   priv->active_mem_unit);
-		priv->active_mem_unit++;
+
+		if (++priv->active_mem_unit == priv->total_mem_units) {
+			priv->stats_ids.init_unalloc--;
+			priv->active_mem_unit = 0;
+		}
+
 		return 0;
 	}
 
-- 
2.20.1


From 2adc93c3072266511c6b1d6e750c56d718eb2257 Mon Sep 17 00:00:00 2001
From: Manish Chopra <manishc@marvell.com>
Date: Thu, 19 Dec 2019 10:35:16 -0800
Subject: [PATCH 13/27] qede: Disable hardware gro when xdp prog is installed

[ Upstream commit 4c8dc00503db24deaf0b89dddfa84b7cba7cd4ce ]

commit 18c602dee472 ("qede: Use NETIF_F_GRO_HW.") introduced
a regression in driver that when xdp program is installed on
qede device, device's aggregation feature (hardware GRO) is not
getting disabled, which is unexpected with xdp.

Fixes: 18c602dee472 ("qede: Use NETIF_F_GRO_HW.")
Signed-off-by: Manish Chopra <manishc@marvell.com>
Signed-off-by: Ariel Elior <aelior@marvell.com>
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qede/qede_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index a220cc7c947a..ba53612ae0df 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -1406,6 +1406,7 @@ static int qede_alloc_mem_rxq(struct qede_dev *edev, struct qede_rx_queue *rxq)
 		rxq->rx_buf_seg_size = roundup_pow_of_two(size);
 	} else {
 		rxq->rx_buf_seg_size = PAGE_SIZE;
+		edev->ndev->features &= ~NETIF_F_GRO_HW;
 	}
 
 	/* Allocate the parallel driver ring for Rx buffers */
@@ -1450,6 +1451,7 @@ static int qede_alloc_mem_rxq(struct qede_dev *edev, struct qede_rx_queue *rxq)
 		}
 	}
 
+	edev->gro_disable = !(edev->ndev->features & NETIF_F_GRO_HW);
 	if (!edev->gro_disable)
 		qede_set_tpa_param(rxq);
 err:
@@ -1702,8 +1704,6 @@ static void qede_init_fp(struct qede_dev *edev)
 		snprintf(fp->name, sizeof(fp->name), "%s-fp-%d",
 			 edev->ndev->name, queue_id);
 	}
-
-	edev->gro_disable = !(edev->ndev->features & NETIF_F_GRO_HW);
 }
 
 static int qede_set_real_num_queues(struct qede_dev *edev)
-- 
2.20.1


From 5e3c16e668da9cb65e276d2d293dd882cde33414 Mon Sep 17 00:00:00 2001
From: Manish Chopra <manishc@marvell.com>
Date: Thu, 12 Dec 2019 06:49:28 -0800
Subject: [PATCH 14/27] qede: Fix multicast mac configuration

[ Upstream commit 0af67e49b018e7280a4227bfe7b6005bc9d3e442 ]

Driver doesn't accommodate the configuration for max number
of multicast mac addresses, in such particular case it leaves
the device with improper/invalid multicast configuration state,
causing connectivity issues (in lacp bonding like scenarios).

Signed-off-by: Manish Chopra <manishc@marvell.com>
Signed-off-by: Ariel Elior <aelior@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qede/qede_filter.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c
index 9a6a9a008714..c8bdbf057d5a 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_filter.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c
@@ -1230,7 +1230,7 @@ qede_configure_mcast_filtering(struct net_device *ndev,
 	netif_addr_lock_bh(ndev);
 
 	mc_count = netdev_mc_count(ndev);
-	if (mc_count < 64) {
+	if (mc_count <= 64) {
 		netdev_for_each_mc_addr(ha, ndev) {
 			ether_addr_copy(temp, ha->addr);
 			temp += ETH_ALEN;
-- 
2.20.1


From 5a7b173f110920e16e429d4dc0b1e56f09bb85cc Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Mon, 16 Dec 2019 22:01:16 -0300
Subject: [PATCH 15/27] sctp: fix memleak on err handling of stream
 initialization

[ Upstream commit 951c6db954a1adefab492f6da805decacabbd1a7 ]

syzbot reported a memory leak when an allocation fails within
genradix_prealloc() for output streams. That's because
genradix_prealloc() leaves initialized members initialized when the
issue happens and SCTP stack will abort the current initialization but
without cleaning up such members.

The fix here is to always call genradix_free() when genradix_prealloc()
fails, for output and also input streams, as it suffers from the same
issue.

Reported-by: syzbot+772d9e36c490b18d51d1@syzkaller.appspotmail.com
Fixes: 2075e50caf5e ("sctp: convert to genradix")
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Tested-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/stream.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index e83cdaa2ab76..6a30392068a0 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -84,8 +84,10 @@ static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt,
 		return 0;
 
 	ret = genradix_prealloc(&stream->out, outcnt, gfp);
-	if (ret)
+	if (ret) {
+		genradix_free(&stream->out);
 		return ret;
+	}
 
 	stream->outcnt = outcnt;
 	return 0;
@@ -100,8 +102,10 @@ static int sctp_stream_alloc_in(struct sctp_stream *stream, __u16 incnt,
 		return 0;
 
 	ret = genradix_prealloc(&stream->in, incnt, gfp);
-	if (ret)
+	if (ret) {
+		genradix_free(&stream->in);
 		return ret;
+	}
 
 	stream->incnt = incnt;
 	return 0;
-- 
2.20.1


From 73132beb2dcfc20009a1d386230af4724fbae110 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 9 Dec 2019 13:45:54 +0800
Subject: [PATCH 16/27] sctp: fully initialize v4 addr in some functions

[ Upstream commit b6f3320b1d5267e7b583a6d0c88dda518101740c ]

Syzbot found a crash:

  BUG: KMSAN: uninit-value in crc32_body lib/crc32.c:112 [inline]
  BUG: KMSAN: uninit-value in crc32_le_generic lib/crc32.c:179 [inline]
  BUG: KMSAN: uninit-value in __crc32c_le_base+0x4fa/0xd30 lib/crc32.c:202
  Call Trace:
    crc32_body lib/crc32.c:112 [inline]
    crc32_le_generic lib/crc32.c:179 [inline]
    __crc32c_le_base+0x4fa/0xd30 lib/crc32.c:202
    chksum_update+0xb2/0x110 crypto/crc32c_generic.c:90
    crypto_shash_update+0x4c5/0x530 crypto/shash.c:107
    crc32c+0x150/0x220 lib/libcrc32c.c:47
    sctp_csum_update+0x89/0xa0 include/net/sctp/checksum.h:36
    __skb_checksum+0x1297/0x12a0 net/core/skbuff.c:2640
    sctp_compute_cksum include/net/sctp/checksum.h:59 [inline]
    sctp_packet_pack net/sctp/output.c:528 [inline]
    sctp_packet_transmit+0x40fb/0x4250 net/sctp/output.c:597
    sctp_outq_flush_transports net/sctp/outqueue.c:1146 [inline]
    sctp_outq_flush+0x1823/0x5d80 net/sctp/outqueue.c:1194
    sctp_outq_uncork+0xd0/0xf0 net/sctp/outqueue.c:757
    sctp_cmd_interpreter net/sctp/sm_sideeffect.c:1781 [inline]
    sctp_side_effects net/sctp/sm_sideeffect.c:1184 [inline]
    sctp_do_sm+0x8fe1/0x9720 net/sctp/sm_sideeffect.c:1155
    sctp_primitive_REQUESTHEARTBEAT+0x175/0x1a0 net/sctp/primitive.c:185
    sctp_apply_peer_addr_params+0x212/0x1d40 net/sctp/socket.c:2433
    sctp_setsockopt_peer_addr_params net/sctp/socket.c:2686 [inline]
    sctp_setsockopt+0x189bb/0x19090 net/sctp/socket.c:4672

The issue was caused by transport->ipaddr set with uninit addr param, which
was passed by:

  sctp_transport_init net/sctp/transport.c:47 [inline]
  sctp_transport_new+0x248/0xa00 net/sctp/transport.c:100
  sctp_assoc_add_peer+0x5ba/0x2030 net/sctp/associola.c:611
  sctp_process_param net/sctp/sm_make_chunk.c:2524 [inline]

where 'addr' is set by sctp_v4_from_addr_param(), and it doesn't initialize
the padding of addr->v4.

Later when calling sctp_make_heartbeat(), hbinfo.daddr(=transport->ipaddr)
will become the part of skb, and the issue occurs.

This patch is to fix it by initializing the padding of addr->v4 in
sctp_v4_from_addr_param(), as well as other functions that do the similar
thing, and these functions shouldn't trust that the caller initializes the
memory, as Marcelo suggested.

Reported-by: syzbot+6dcbfea81cd3d4dd0b02@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/protocol.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 08d14d86ecfb..681ffb3545db 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -227,6 +227,7 @@ static void sctp_v4_from_skb(union sctp_addr *addr, struct sk_buff *skb,
 		sa->sin_port = sh->dest;
 		sa->sin_addr.s_addr = ip_hdr(skb)->daddr;
 	}
+	memset(sa->sin_zero, 0, sizeof(sa->sin_zero));
 }
 
 /* Initialize an sctp_addr from a socket. */
@@ -235,6 +236,7 @@ static void sctp_v4_from_sk(union sctp_addr *addr, struct sock *sk)
 	addr->v4.sin_family = AF_INET;
 	addr->v4.sin_port = 0;
 	addr->v4.sin_addr.s_addr = inet_sk(sk)->inet_rcv_saddr;
+	memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
 }
 
 /* Initialize sk->sk_rcv_saddr from sctp_addr. */
@@ -257,6 +259,7 @@ static void sctp_v4_from_addr_param(union sctp_addr *addr,
 	addr->v4.sin_family = AF_INET;
 	addr->v4.sin_port = port;
 	addr->v4.sin_addr.s_addr = param->v4.addr.s_addr;
+	memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
 }
 
 /* Initialize an address parameter from a sctp_addr and return the length
@@ -281,6 +284,7 @@ static void sctp_v4_dst_saddr(union sctp_addr *saddr, struct flowi4 *fl4,
 	saddr->v4.sin_family = AF_INET;
 	saddr->v4.sin_port = port;
 	saddr->v4.sin_addr.s_addr = fl4->saddr;
+	memset(saddr->v4.sin_zero, 0, sizeof(saddr->v4.sin_zero));
 }
 
 /* Compare two addresses exactly. */
@@ -303,6 +307,7 @@ static void sctp_v4_inaddr_any(union sctp_addr *addr, __be16 port)
 	addr->v4.sin_family = AF_INET;
 	addr->v4.sin_addr.s_addr = htonl(INADDR_ANY);
 	addr->v4.sin_port = port;
+	memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
 }
 
 /* Is this a wildcard address? */
-- 
2.20.1


From f1569507f7e22e6fadaabcb2085f0bdbd9f18fc0 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Mon, 9 Dec 2019 08:56:34 +0200
Subject: [PATCH 17/27] selftests: forwarding: Delete IPv6 address at the end

[ Upstream commit 65cb13986229cec02635a1ecbcd1e2dd18353201 ]

When creating the second host in h2_create(), two addresses are assigned
to the interface, but only one is deleted. When running the test twice
in a row the following error is observed:

$ ./router_bridge_vlan.sh
TEST: ping                                                          [ OK ]
TEST: ping6                                                         [ OK ]
TEST: vlan                                                          [ OK ]
$ ./router_bridge_vlan.sh
RTNETLINK answers: File exists
TEST: ping                                                          [ OK ]
TEST: ping6                                                         [ OK ]
TEST: vlan                                                          [ OK ]

Fix this by deleting the address during cleanup.

Fixes: 5b1e7f9ebd56 ("selftests: forwarding: Test routed bridge interface")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/router_bridge_vlan.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh b/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh
index fef88eb4b873..fa6a88c50750 100755
--- a/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh
+++ b/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh
@@ -36,7 +36,7 @@ h2_destroy()
 {
 	ip -6 route del 2001:db8:1::/64 vrf v$h2
 	ip -4 route del 192.0.2.0/28 vrf v$h2
-	simple_if_fini $h2 192.0.2.130/28
+	simple_if_fini $h2 192.0.2.130/28 2001:db8:2::2/64
 }
 
 router_create()
-- 
2.20.1


From 40ed775c82810cb806588de8850ef3ae2cb647d9 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 7 Dec 2019 12:23:21 -0800
Subject: [PATCH 18/27] neighbour: remove neigh_cleanup() method

[ Upstream commit f394722fb0d0f701119368959d7cd0ecbc46363a ]

neigh_cleanup() has not been used for seven years, and was a wrong design.

Messing with shared pointer in bond_neigh_init() without proper
memory barriers would at least trigger syzbot complains eventually.

It is time to remove this stuff.

Fixes: b63b70d87741 ("IPoIB: Use a private hash table for path lookup in xmit path")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 8 --------
 include/net/neighbour.h         | 1 -
 net/core/neighbour.c            | 3 ---
 3 files changed, 12 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 62f65573eb04..3a63a4e4f62b 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3622,18 +3622,10 @@ static int bond_neigh_init(struct neighbour *n)
 		return 0;
 
 	parms.neigh_setup = NULL;
-	parms.neigh_cleanup = NULL;
 	ret = slave_ops->ndo_neigh_setup(slave->dev, &parms);
 	if (ret)
 		return ret;
 
-	/* Assign slave's neigh_cleanup to neighbour in case cleanup is called
-	 * after the last slave has been detached.  Assumes that all slaves
-	 * utilize the same neigh_cleanup (true at this writing as only user
-	 * is ipoib).
-	 */
-	n->parms->neigh_cleanup = parms.neigh_cleanup;
-
 	if (!parms.neigh_setup)
 		return 0;
 
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index b8452cc0e059..5e679c8dae0b 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -72,7 +72,6 @@ struct neigh_parms {
 	struct net_device *dev;
 	struct list_head list;
 	int	(*neigh_setup)(struct neighbour *);
-	void	(*neigh_cleanup)(struct neighbour *);
 	struct neigh_table *tbl;
 
 	void	*sysctl_table;
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 5480edff0c86..08ebc3ac5343 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -98,9 +98,6 @@ static int neigh_blackhole(struct neighbour *neigh, struct sk_buff *skb)
 
 static void neigh_cleanup_and_release(struct neighbour *neigh)
 {
-	if (neigh->parms->neigh_cleanup)
-		neigh->parms->neigh_cleanup(neigh);
-
 	trace_neigh_cleanup_and_release(neigh, 0);
 	__neigh_notify(neigh, RTM_DELNEIGH, 0, 0);
 	call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh);
-- 
2.20.1


From 05ff499ba070e586d5b0bef337b54c74cb8f8947 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 7 Dec 2019 14:10:34 -0800
Subject: [PATCH 19/27] bonding: fix bond_neigh_init()

[ Upstream commit 9e99bfefdbce2e23ef37487a3bcb4adf90a791d1 ]

1) syzbot reported an uninit-value in bond_neigh_setup() [1]

 bond_neigh_setup() uses a temporary on-stack 'struct neigh_parms parms',
 but only clears parms.neigh_setup field.

 A stacked bonding device would then enter bond_neigh_setup()
 and read garbage from parms->dev.

 If we get really unlucky and garbage is matching @dev, then we
 could recurse and eventually crash.

 Let's make sure the whole structure is cleared to avoid surprises.

2) bond_neigh_setup() can be called while another cpu manipulates
 the master device, removing or adding a slave.
 We need at least rcu protection to prevent use-after-free.

Note: Prior code does not support a stack of bonding devices,
      this patch does not attempt to fix this, and leave a comment instead.

[1]

BUG: KMSAN: uninit-value in bond_neigh_setup+0xa4/0x110 drivers/net/bonding/bond_main.c:3655
CPU: 0 PID: 11256 Comm: syz-executor.0 Not tainted 5.4.0-rc8-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c9/0x220 lib/dump_stack.c:118
 kmsan_report+0x128/0x220 mm/kmsan/kmsan_report.c:108
 __msan_warning+0x57/0xa0 mm/kmsan/kmsan_instr.c:245
 bond_neigh_setup+0xa4/0x110 drivers/net/bonding/bond_main.c:3655
 bond_neigh_init+0x216/0x4b0 drivers/net/bonding/bond_main.c:3626
 ___neigh_create+0x169e/0x2c40 net/core/neighbour.c:613
 __neigh_create+0xbd/0xd0 net/core/neighbour.c:674
 ip6_finish_output2+0x149a/0x2670 net/ipv6/ip6_output.c:113
 __ip6_finish_output+0x83d/0x8f0 net/ipv6/ip6_output.c:142
 ip6_finish_output+0x2db/0x420 net/ipv6/ip6_output.c:152
 NF_HOOK_COND include/linux/netfilter.h:294 [inline]
 ip6_output+0x5d3/0x720 net/ipv6/ip6_output.c:175
 dst_output include/net/dst.h:436 [inline]
 NF_HOOK include/linux/netfilter.h:305 [inline]
 mld_sendpack+0xebd/0x13d0 net/ipv6/mcast.c:1682
 mld_send_cr net/ipv6/mcast.c:1978 [inline]
 mld_ifc_timer_expire+0x116b/0x1680 net/ipv6/mcast.c:2477
 call_timer_fn+0x232/0x530 kernel/time/timer.c:1404
 expire_timers kernel/time/timer.c:1449 [inline]
 __run_timers+0xd60/0x1270 kernel/time/timer.c:1773
 run_timer_softirq+0x2d/0x50 kernel/time/timer.c:1786
 __do_softirq+0x4a1/0x83a kernel/softirq.c:293
 invoke_softirq kernel/softirq.c:375 [inline]
 irq_exit+0x230/0x280 kernel/softirq.c:416
 exiting_irq+0xe/0x10 arch/x86/include/asm/apic.h:536
 smp_apic_timer_interrupt+0x48/0x70 arch/x86/kernel/apic/apic.c:1138
 apic_timer_interrupt+0x2e/0x40 arch/x86/entry/entry_64.S:835
 </IRQ>
RIP: 0010:kmsan_free_page+0x18d/0x1c0 mm/kmsan/kmsan_shadow.c:439
Code: 4c 89 ff 44 89 f6 e8 82 0d ee ff 65 ff 0d 9f 26 3b 60 65 8b 05 98 26 3b 60 85 c0 75 24 e8 5b f6 35 ff 4c 89 6d d0 ff 75 d0 9d <48> 83 c4 10 5b 41 5c 41 5d 41 5e 41 5f 5d c3 0f 0b 0f 0b 0f 0b 0f
RSP: 0018:ffffb328034af818 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13
RAX: 0000000000000000 RBX: ffffe2d7471f8360 RCX: 0000000000000000
RDX: ffffffffadea7000 RSI: 0000000000000004 RDI: ffff93496fcda104
RBP: ffffb328034af850 R08: ffff934a47e86d00 R09: ffff93496fc41900
R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000001
R13: 0000000000000246 R14: 0000000000000000 R15: ffffe2d7472225c0
 free_pages_prepare mm/page_alloc.c:1138 [inline]
 free_pcp_prepare mm/page_alloc.c:1230 [inline]
 free_unref_page_prepare+0x1d9/0x770 mm/page_alloc.c:3025
 free_unref_page mm/page_alloc.c:3074 [inline]
 free_the_page mm/page_alloc.c:4832 [inline]
 __free_pages+0x154/0x230 mm/page_alloc.c:4840
 __vunmap+0xdac/0xf20 mm/vmalloc.c:2277
 __vfree mm/vmalloc.c:2325 [inline]
 vfree+0x7c/0x170 mm/vmalloc.c:2355
 copy_entries_to_user net/ipv6/netfilter/ip6_tables.c:883 [inline]
 get_entries net/ipv6/netfilter/ip6_tables.c:1041 [inline]
 do_ip6t_get_ctl+0xfa4/0x1030 net/ipv6/netfilter/ip6_tables.c:1709
 nf_sockopt net/netfilter/nf_sockopt.c:104 [inline]
 nf_getsockopt+0x481/0x4e0 net/netfilter/nf_sockopt.c:122
 ipv6_getsockopt+0x264/0x510 net/ipv6/ipv6_sockglue.c:1400
 tcp_getsockopt+0x1c6/0x1f0 net/ipv4/tcp.c:3688
 sock_common_getsockopt+0x13f/0x180 net/core/sock.c:3110
 __sys_getsockopt+0x533/0x7b0 net/socket.c:2129
 __do_sys_getsockopt net/socket.c:2144 [inline]
 __se_sys_getsockopt+0xe1/0x100 net/socket.c:2141
 __x64_sys_getsockopt+0x62/0x80 net/socket.c:2141
 do_syscall_64+0xb6/0x160 arch/x86/entry/common.c:291
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x45d20a
Code: b8 34 01 00 00 0f 05 48 3d 01 f0 ff ff 0f 83 8d 8b fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 49 89 ca b8 37 00 00 00 0f 05 <48> 3d 01 f0 ff ff 0f 83 6a 8b fb ff c3 66 0f 1f 84 00 00 00 00 00
RSP: 002b:0000000000a6f618 EFLAGS: 00000212 ORIG_RAX: 0000000000000037
RAX: ffffffffffffffda RBX: 0000000000a6f640 RCX: 000000000045d20a
RDX: 0000000000000041 RSI: 0000000000000029 RDI: 0000000000000003
RBP: 0000000000717cc0 R08: 0000000000a6f63c R09: 0000000000004000
R10: 0000000000a6f740 R11: 0000000000000212 R12: 0000000000000003
R13: 0000000000000000 R14: 0000000000000029 R15: 0000000000715b00

Local variable description: ----parms@bond_neigh_init
Variable was created at:
 bond_neigh_init+0x8c/0x4b0 drivers/net/bonding/bond_main.c:3617
 bond_neigh_init+0x8c/0x4b0 drivers/net/bonding/bond_main.c:3617

Fixes: 9918d5bf329d ("bonding: modify only neigh_parms owned by us")
Fixes: 234bcf8a499e ("net/bonding: correctly proxy slave neigh param setup ndo function")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Cc: Veaceslav Falico <vfalico@gmail.com>
Cc: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 31 +++++++++++++++++++++----------
 1 file changed, 21 insertions(+), 10 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 3a63a4e4f62b..face00c622ed 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3612,24 +3612,35 @@ static int bond_neigh_init(struct neighbour *n)
 	const struct net_device_ops *slave_ops;
 	struct neigh_parms parms;
 	struct slave *slave;
-	int ret;
+	int ret = 0;
 
-	slave = bond_first_slave(bond);
+	rcu_read_lock();
+	slave = bond_first_slave_rcu(bond);
 	if (!slave)
-		return 0;
+		goto out;
 	slave_ops = slave->dev->netdev_ops;
 	if (!slave_ops->ndo_neigh_setup)
-		return 0;
+		goto out;
 
-	parms.neigh_setup = NULL;
+	/* TODO: find another way [1] to implement this.
+	 * Passing a zeroed structure is fragile,
+	 * but at least we do not pass garbage.
+	 *
+	 * [1] One way would be that ndo_neigh_setup() never touch
+	 *     struct neigh_parms, but propagate the new neigh_setup()
+	 *     back to ___neigh_create() / neigh_parms_alloc()
+	 */
+	memset(&parms, 0, sizeof(parms));
 	ret = slave_ops->ndo_neigh_setup(slave->dev, &parms);
-	if (ret)
-		return ret;
 
-	if (!parms.neigh_setup)
-		return 0;
+	if (ret)
+		goto out;
 
-	return parms.neigh_setup(n);
+	if (parms.neigh_setup)
+		ret = parms.neigh_setup(n);
+out:
+	rcu_read_unlock();
+	return ret;
 }
 
 /* The bonding ndo_neigh_setup is called at init time beofre any
-- 
2.20.1


From dad09c939e5b97a68613b2710f965ee12adf4f01 Mon Sep 17 00:00:00 2001
From: Arthur Kiyanovski <akiyano@amazon.com>
Date: Thu, 19 Dec 2019 17:40:55 +0200
Subject: [PATCH 20/27] net: ena: fix default tx interrupt moderation interval

[ Upstream commit 05785adf6e570a068adf0502b61fe2b521d7f0ca ]

Current default non-adaptive tx interrupt moderation interval is 196 us.
This value is too high and might cause the tx queue to fill up.

In this commit we set the default non-adaptive tx interrupt moderation
interval to 64 us in order to:
1. Reduce the probability of the queue filling-up (when compared to the
   current default value of 196 us).
2. Reduce unnecessary tx interrupt overhead (which happens if we set the
   default tx interval to 0).
   We determined experimentally that 64 us is an optimal value that
   reduces interrupt rate by more than 20% without affecting performance.

Fixes: 1738cd3ed342 ("net: ena: Add a driver for Amazon Elastic Network Adapters (ENA)")
Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_com.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_com.h b/drivers/net/ethernet/amazon/ena/ena_com.h
index 7c941eba0bc9..0ce37d54ed10 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.h
+++ b/drivers/net/ethernet/amazon/ena/ena_com.h
@@ -72,7 +72,7 @@
 /*****************************************************************************/
 /* ENA adaptive interrupt moderation settings */
 
-#define ENA_INTR_INITIAL_TX_INTERVAL_USECS		196
+#define ENA_INTR_INITIAL_TX_INTERVAL_USECS		64
 #define ENA_INTR_INITIAL_RX_INTERVAL_USECS		0
 #define ENA_DEFAULT_INTR_DELAY_RESOLUTION		1
 
-- 
2.20.1


From 821fed671847ed2117c20eff90e8d70fc91dec84 Mon Sep 17 00:00:00 2001
From: Arthur Kiyanovski <akiyano@amazon.com>
Date: Thu, 19 Dec 2019 17:40:56 +0200
Subject: [PATCH 21/27] net: ena: fix issues in setting interrupt moderation
 params in ethtool

[ Upstream commit 41c53caa5a61ebc9221b71cc37f4a90549f1121d ]

Issue 1:
--------
Reproduction steps:
1. sudo ethtool -C eth0 rx-usecs 128
2. sudo ethtool -C eth0 adaptive-rx on
3. sudo ethtool -C eth0 adaptive-rx off
4. ethtool -c eth0

expected output: rx-usecs 128
actual output: rx-usecs 0

Reason for issue:
In stage 3, ethtool userspace calls first the ena_get_coalesce() handler
to get the current value of all properties, and then the ena_set_coalesce()
handler. When ena_get_coalesce() is called the adaptive interrupt
moderation is still on. There is an if in the code that returns the
rx_coalesce_usecs only if the adaptive interrupt moderation is off.
And since it is still on, rx_coalesce_usecs is not set, meaning it
stays 0.

Solution to issue:
Remove this if static interrupt moderation intervals have nothing to do
with dynamic ones.

Issue 2:
--------
Reproduction steps:
1. sudo ethtool -C eth0 adaptive-rx on
2. sudo ethtool -C eth0 rx-usecs 128
3. ethtool -c eth0

expected output: rx-usecs 128
actual output: rx-usecs 0

Reason for issue:
In stage 2, when ena_set_coalesce() is called, the handler tests if
rx adaptive interrupt moderation is on, and if it is, it returns before
getting to the part in the function that sets the rx non-adaptive
interrupt moderation interval.

Solution to issue:
Remove the return from the function when rx adaptive interrupt moderation
is on.

Also cleaned up the fixed code in ena_set_coalesce by grouping together
adaptive interrupt moderation toggling, and using && instead of nested
ifs.

Fixes: b3db86dc4b82 ("net: ena: reimplement set/get_coalesce()")
Fixes: 0eda847953d8 ("net: ena: fix retrieval of nonadaptive interrupt moderation intervals")
Fixes: 1738cd3ed342 ("net: ena: Add a driver for Amazon Elastic Network Adapters (ENA)")
Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_ethtool.c | 24 ++++++++-----------
 1 file changed, 10 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
index 16553d92fad2..8c1c73b0ced7 100644
--- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c
+++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
@@ -315,10 +315,9 @@ static int ena_get_coalesce(struct net_device *net_dev,
 		ena_com_get_nonadaptive_moderation_interval_tx(ena_dev) *
 			ena_dev->intr_delay_resolution;
 
-	if (!ena_com_get_adaptive_moderation_enabled(ena_dev))
-		coalesce->rx_coalesce_usecs =
-			ena_com_get_nonadaptive_moderation_interval_rx(ena_dev)
-			* ena_dev->intr_delay_resolution;
+	coalesce->rx_coalesce_usecs =
+		ena_com_get_nonadaptive_moderation_interval_rx(ena_dev)
+		* ena_dev->intr_delay_resolution;
 
 	coalesce->use_adaptive_rx_coalesce =
 		ena_com_get_adaptive_moderation_enabled(ena_dev);
@@ -367,12 +366,6 @@ static int ena_set_coalesce(struct net_device *net_dev,
 
 	ena_update_tx_rings_intr_moderation(adapter);
 
-	if (coalesce->use_adaptive_rx_coalesce) {
-		if (!ena_com_get_adaptive_moderation_enabled(ena_dev))
-			ena_com_enable_adaptive_moderation(ena_dev);
-		return 0;
-	}
-
 	rc = ena_com_update_nonadaptive_moderation_interval_rx(ena_dev,
 							       coalesce->rx_coalesce_usecs);
 	if (rc)
@@ -380,10 +373,13 @@ static int ena_set_coalesce(struct net_device *net_dev,
 
 	ena_update_rx_rings_intr_moderation(adapter);
 
-	if (!coalesce->use_adaptive_rx_coalesce) {
-		if (ena_com_get_adaptive_moderation_enabled(ena_dev))
-			ena_com_disable_adaptive_moderation(ena_dev);
-	}
+	if (coalesce->use_adaptive_rx_coalesce &&
+	    !ena_com_get_adaptive_moderation_enabled(ena_dev))
+		ena_com_enable_adaptive_moderation(ena_dev);
+
+	if (!coalesce->use_adaptive_rx_coalesce &&
+	    ena_com_get_adaptive_moderation_enabled(ena_dev))
+		ena_com_disable_adaptive_moderation(ena_dev);
 
 	return 0;
 }
-- 
2.20.1


From f8aeeab71f4878b0b8580db7393723f3c2b94010 Mon Sep 17 00:00:00 2001
From: Ioana Ciornei <ioana.ciornei@nxp.com>
Date: Mon, 16 Dec 2019 17:32:30 +0200
Subject: [PATCH 22/27] dpaa2-ptp: fix double free of the ptp_qoriq IRQ

[ Upstream commit daa6eb5a149519583c8a8cb31945f06417d21902 ]

Upon reusing the ptp_qoriq driver, the ptp_qoriq_free() function was
used on the remove path to free any allocated resources.
The ptp_qoriq IRQ is among these resources that are freed in
ptp_qoriq_free() even though it is also a managed one (allocated using
devm_request_threaded_irq).

Drop the resource managed version of requesting the IRQ in order to not
trigger a double free of the interrupt as below:

[  226.731005] Trying to free already-free IRQ 126
[  226.735533] WARNING: CPU: 6 PID: 749 at kernel/irq/manage.c:1707
__free_irq+0x9c/0x2b8
[  226.743435] Modules linked in:
[  226.746480] CPU: 6 PID: 749 Comm: bash Tainted: G        W
5.4.0-03629-gfd7102c32b2c-dirty #912
[  226.755857] Hardware name: NXP Layerscape LX2160ARDB (DT)
[  226.761244] pstate: 40000085 (nZcv daIf -PAN -UAO)
[  226.766022] pc : __free_irq+0x9c/0x2b8
[  226.769758] lr : __free_irq+0x9c/0x2b8
[  226.773493] sp : ffff8000125039f0
(...)
[  226.856275] Call trace:
[  226.858710]  __free_irq+0x9c/0x2b8
[  226.862098]  free_irq+0x30/0x70
[  226.865229]  devm_irq_release+0x14/0x20
[  226.869054]  release_nodes+0x1b0/0x220
[  226.872790]  devres_release_all+0x34/0x50
[  226.876790]  device_release_driver_internal+0x100/0x1c0

Fixes: d346c9e86d86 ("dpaa2-ptp: reuse ptp_qoriq driver")
Cc: Yangbo Lu <yangbo.lu@nxp.com>
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Reviewed-by: Yangbo Lu <yangbo.lu@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c
index a9503aea527f..6437fe6b9abf 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c
@@ -160,10 +160,10 @@ static int dpaa2_ptp_probe(struct fsl_mc_device *mc_dev)
 	irq = mc_dev->irqs[0];
 	ptp_qoriq->irq = irq->msi_desc->irq;
 
-	err = devm_request_threaded_irq(dev, ptp_qoriq->irq, NULL,
-					dpaa2_ptp_irq_handler_thread,
-					IRQF_NO_SUSPEND | IRQF_ONESHOT,
-					dev_name(dev), ptp_qoriq);
+	err = request_threaded_irq(ptp_qoriq->irq, NULL,
+				   dpaa2_ptp_irq_handler_thread,
+				   IRQF_NO_SUSPEND | IRQF_ONESHOT,
+				   dev_name(dev), ptp_qoriq);
 	if (err < 0) {
 		dev_err(dev, "devm_request_threaded_irq(): %d\n", err);
 		goto err_free_mc_irq;
@@ -173,18 +173,20 @@ static int dpaa2_ptp_probe(struct fsl_mc_device *mc_dev)
 				   DPRTC_IRQ_INDEX, 1);
 	if (err < 0) {
 		dev_err(dev, "dprtc_set_irq_enable(): %d\n", err);
-		goto err_free_mc_irq;
+		goto err_free_threaded_irq;
 	}
 
 	err = ptp_qoriq_init(ptp_qoriq, base, &dpaa2_ptp_caps);
 	if (err)
-		goto err_free_mc_irq;
+		goto err_free_threaded_irq;
 
 	dpaa2_phc_index = ptp_qoriq->phc_index;
 	dev_set_drvdata(dev, ptp_qoriq);
 
 	return 0;
 
+err_free_threaded_irq:
+	free_irq(ptp_qoriq->irq, ptp_qoriq);
 err_free_mc_irq:
 	fsl_mc_free_irqs(mc_dev);
 err_unmap:
-- 
2.20.1


From b433658e4b44ccea8d1c36458dbf8c789335908e Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Mon, 9 Dec 2019 08:55:20 +0200
Subject: [PATCH 23/27] mlxsw: spectrum_router: Remove unlikely
 user-triggerable warning

[ Upstream commit 62201c00c4679ad8f0730d6d925a5d23651dfad2 ]

In case the driver vetoes the addition of an IPv6 multipath route, the
IPv6 stack will emit delete notifications for the sibling routes that
were already added to the FIB trie. Since these siblings are not present
in hardware, a warning will be generated.

Have the driver ignore notifications for routes it does not have.

Fixes: ebee3cad835f ("ipv6: Add IPv6 multipath notifications for add / replace")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 39d600c8b92d..210ebc91d3d6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -5637,8 +5637,13 @@ static void mlxsw_sp_router_fib6_del(struct mlxsw_sp *mlxsw_sp,
 	if (mlxsw_sp_fib6_rt_should_ignore(rt))
 		return;
 
+	/* Multipath routes are first added to the FIB trie and only then
+	 * notified. If we vetoed the addition, we will get a delete
+	 * notification for a route we do not have. Therefore, do not warn if
+	 * route was not found.
+	 */
 	fib6_entry = mlxsw_sp_fib6_entry_lookup(mlxsw_sp, rt);
-	if (WARN_ON(!fib6_entry))
+	if (!fib6_entry)
 		return;
 
 	/* If not all the nexthops are deleted, then only reduce the nexthop
-- 
2.20.1


From 95b533fb2b8c4bd2bc63b755d9677d42190640cf Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Mon, 9 Dec 2019 13:19:24 +0200
Subject: [PATCH 24/27] net: ethernet: ti: davinci_cpdma: fix warning "device
 driver frees DMA memory with different size"

[ Upstream commit 8a2b22203f8596729c54eba221b4044351bfe167 ]

The TI CPSW(s) driver produces warning with DMA API debug options enabled:

WARNING: CPU: 0 PID: 1033 at kernel/dma/debug.c:1025 check_unmap+0x4a8/0x968
DMA-API: cpsw 48484000.ethernet: device driver frees DMA memory with different size
 [device address=0x00000000abc6aa02] [map size=64 bytes] [unmap size=42 bytes]
CPU: 0 PID: 1033 Comm: ping Not tainted 5.3.0-dirty #41
Hardware name: Generic DRA72X (Flattened Device Tree)
[<c0112c60>] (unwind_backtrace) from [<c010d270>] (show_stack+0x10/0x14)
[<c010d270>] (show_stack) from [<c09bc564>] (dump_stack+0xd8/0x110)
[<c09bc564>] (dump_stack) from [<c013b93c>] (__warn+0xe0/0x10c)
[<c013b93c>] (__warn) from [<c013b9ac>] (warn_slowpath_fmt+0x44/0x6c)
[<c013b9ac>] (warn_slowpath_fmt) from [<c01e0368>] (check_unmap+0x4a8/0x968)
[<c01e0368>] (check_unmap) from [<c01e08a8>] (debug_dma_unmap_page+0x80/0x90)
[<c01e08a8>] (debug_dma_unmap_page) from [<c0752414>] (__cpdma_chan_free+0x114/0x16c)
[<c0752414>] (__cpdma_chan_free) from [<c07525c4>] (__cpdma_chan_process+0x158/0x17c)
[<c07525c4>] (__cpdma_chan_process) from [<c0753690>] (cpdma_chan_process+0x3c/0x5c)
[<c0753690>] (cpdma_chan_process) from [<c0758660>] (cpsw_tx_mq_poll+0x48/0x94)
[<c0758660>] (cpsw_tx_mq_poll) from [<c0803018>] (net_rx_action+0x108/0x4e4)
[<c0803018>] (net_rx_action) from [<c010230c>] (__do_softirq+0xec/0x598)
[<c010230c>] (__do_softirq) from [<c0143914>] (do_softirq.part.4+0x68/0x74)
[<c0143914>] (do_softirq.part.4) from [<c0143a44>] (__local_bh_enable_ip+0x124/0x17c)
[<c0143a44>] (__local_bh_enable_ip) from [<c0871590>] (ip_finish_output2+0x294/0xb7c)
[<c0871590>] (ip_finish_output2) from [<c0875440>] (ip_output+0x210/0x364)
[<c0875440>] (ip_output) from [<c0875e2c>] (ip_send_skb+0x1c/0xf8)
[<c0875e2c>] (ip_send_skb) from [<c08a7fd4>] (raw_sendmsg+0x9a8/0xc74)
[<c08a7fd4>] (raw_sendmsg) from [<c07d6b90>] (sock_sendmsg+0x14/0x24)
[<c07d6b90>] (sock_sendmsg) from [<c07d8260>] (__sys_sendto+0xbc/0x100)
[<c07d8260>] (__sys_sendto) from [<c01011ac>] (__sys_trace_return+0x0/0x14)
Exception stack(0xea9a7fa8 to 0xea9a7ff0)
...

The reason is that cpdma_chan_submit_si() now stores original buffer length
(sw_len) in CPDMA descriptor instead of adjusted buffer length (hw_len)
used to map the buffer.

Hence, fix an issue by passing correct buffer length in CPDMA descriptor.

Cc: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Fixes: 6670acacd59e ("net: ethernet: ti: davinci_cpdma: add dma mapped submit")
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Reviewed-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/davinci_cpdma.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/ti/davinci_cpdma.c b/drivers/net/ethernet/ti/davinci_cpdma.c
index 37ba708ac781..6614fa3089b2 100644
--- a/drivers/net/ethernet/ti/davinci_cpdma.c
+++ b/drivers/net/ethernet/ti/davinci_cpdma.c
@@ -1018,7 +1018,6 @@ static int cpdma_chan_submit_si(struct submit_info *si)
 	struct cpdma_chan		*chan = si->chan;
 	struct cpdma_ctlr		*ctlr = chan->ctlr;
 	int				len = si->len;
-	int				swlen = len;
 	struct cpdma_desc __iomem	*desc;
 	dma_addr_t			buffer;
 	u32				mode;
@@ -1046,7 +1045,6 @@ static int cpdma_chan_submit_si(struct submit_info *si)
 	if (si->data_dma) {
 		buffer = si->data_dma;
 		dma_sync_single_for_device(ctlr->dev, buffer, len, chan->dir);
-		swlen |= CPDMA_DMA_EXT_MAP;
 	} else {
 		buffer = dma_map_single(ctlr->dev, si->data_virt, len, chan->dir);
 		ret = dma_mapping_error(ctlr->dev, buffer);
@@ -1065,7 +1063,8 @@ static int cpdma_chan_submit_si(struct submit_info *si)
 	writel_relaxed(mode | len, &desc->hw_mode);
 	writel_relaxed((uintptr_t)si->token, &desc->sw_token);
 	writel_relaxed(buffer, &desc->sw_buffer);
-	writel_relaxed(swlen, &desc->sw_len);
+	writel_relaxed(si->data_dma ? len | CPDMA_DMA_EXT_MAP : len,
+		       &desc->sw_len);
 	desc_read(desc, sw_len);
 
 	__cpdma_chan_submit(chan, desc);
-- 
2.20.1


From cbf4e4d3db01aa5ab27d1eb4101c8ae2f726c1d3 Mon Sep 17 00:00:00 2001
From: Padmanabhan Rajanbabu <p.rajanbabu@samsung.com>
Date: Thu, 19 Dec 2019 15:47:01 +0530
Subject: [PATCH 25/27] net: stmmac: platform: Fix MDIO init for platforms
 without PHY

[ Upstream commit d3e014ec7d5ebe9644b5486bc530b91e62bbf624 ]

The current implementation of "stmmac_dt_phy" function initializes
the MDIO platform bus data, even in the absence of PHY. This fix
will skip MDIO initialization if there is no PHY present.

Fixes: 7437127 ("net: stmmac: Convert to phylink and remove phylib logic")
Acked-by: Jayati Sahu <jayati.sahu@samsung.com>
Signed-off-by: Sriram Dash <sriram.dash@samsung.com>
Signed-off-by: Padmanabhan Rajanbabu <p.rajanbabu@samsung.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 170c3a052b14..1f230bd854c4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -320,7 +320,7 @@ static int stmmac_mtl_setup(struct platform_device *pdev,
 static int stmmac_dt_phy(struct plat_stmmacenet_data *plat,
 			 struct device_node *np, struct device *dev)
 {
-	bool mdio = true;
+	bool mdio = false;
 	static const struct of_device_id need_mdio_ids[] = {
 		{ .compatible = "snps,dwc-qos-ethernet-4.10" },
 		{},
-- 
2.20.1


From 83382f532c2316f8d1a6ce97d8e98a63ffd26853 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 13 Dec 2019 12:00:27 -0800
Subject: [PATCH 26/27] net: dsa: b53: Fix egress flooding settings

[ Upstream commit 63cc54a6f0736a432b04308a74677ab0ba8a58ee ]

There were several issues with 53568438e381 ("net: dsa: b53: Add support for port_egress_floods callback") that resulted in breaking connectivity for standalone ports:

- both user and CPU ports must allow unicast and multicast forwarding by
  default otherwise this just flat out breaks connectivity for
  standalone DSA ports
- IP multicast is treated similarly as multicast, but has separate
  control registers
- the UC, MC and IPMC lookup failure register offsets were wrong, and
  instead used bit values that are meaningful for the
  B53_IP_MULTICAST_CTRL register

Fixes: 53568438e381 ("net: dsa: b53: Add support for port_egress_floods callback")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Vivien Didelot <vivien.didelot@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/b53/b53_common.c | 21 ++++++++++++++++-----
 1 file changed, 16 insertions(+), 5 deletions(-)

diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index cc3536315eff..a7132c1593c3 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -347,7 +347,7 @@ static void b53_set_forwarding(struct b53_device *dev, int enable)
 	 * frames should be flooded or not.
 	 */
 	b53_read8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, &mgmt);
-	mgmt |= B53_UC_FWD_EN | B53_MC_FWD_EN;
+	mgmt |= B53_UC_FWD_EN | B53_MC_FWD_EN | B53_IPMC_FWD_EN;
 	b53_write8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, mgmt);
 }
 
@@ -526,6 +526,8 @@ int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy)
 
 	cpu_port = ds->ports[port].cpu_dp->index;
 
+	b53_br_egress_floods(ds, port, true, true);
+
 	if (dev->ops->irq_enable)
 		ret = dev->ops->irq_enable(dev, port);
 	if (ret)
@@ -641,6 +643,8 @@ static void b53_enable_cpu_port(struct b53_device *dev, int port)
 	b53_write8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), port_ctrl);
 
 	b53_brcm_hdr_setup(dev->ds, port);
+
+	b53_br_egress_floods(dev->ds, port, true, true);
 }
 
 static void b53_enable_mib(struct b53_device *dev)
@@ -1766,19 +1770,26 @@ int b53_br_egress_floods(struct dsa_switch *ds, int port,
 	struct b53_device *dev = ds->priv;
 	u16 uc, mc;
 
-	b53_read16(dev, B53_CTRL_PAGE, B53_UC_FWD_EN, &uc);
+	b53_read16(dev, B53_CTRL_PAGE, B53_UC_FLOOD_MASK, &uc);
 	if (unicast)
 		uc |= BIT(port);
 	else
 		uc &= ~BIT(port);
-	b53_write16(dev, B53_CTRL_PAGE, B53_UC_FWD_EN, uc);
+	b53_write16(dev, B53_CTRL_PAGE, B53_UC_FLOOD_MASK, uc);
+
+	b53_read16(dev, B53_CTRL_PAGE, B53_MC_FLOOD_MASK, &mc);
+	if (multicast)
+		mc |= BIT(port);
+	else
+		mc &= ~BIT(port);
+	b53_write16(dev, B53_CTRL_PAGE, B53_MC_FLOOD_MASK, mc);
 
-	b53_read16(dev, B53_CTRL_PAGE, B53_MC_FWD_EN, &mc);
+	b53_read16(dev, B53_CTRL_PAGE, B53_IPMC_FLOOD_MASK, &mc);
 	if (multicast)
 		mc |= BIT(port);
 	else
 		mc &= ~BIT(port);
-	b53_write16(dev, B53_CTRL_PAGE, B53_MC_FWD_EN, mc);
+	b53_write16(dev, B53_CTRL_PAGE, B53_IPMC_FLOOD_MASK, mc);
 
 	return 0;
 
-- 
2.20.1


From 716b49e9b90f3a3b014aa90b039b507f2df8a56e Mon Sep 17 00:00:00 2001
From: Stephan Gerhold <stephan@gerhold.net>
Date: Mon, 9 Dec 2019 19:53:43 +0100
Subject: [PATCH 27/27] NFC: nxp-nci: Fix probing without ACPI

[ Upstream commit 868afbaca1e2a7923e48b5e8c07be34660525db5 ]

devm_acpi_dev_add_driver_gpios() returns -ENXIO if CONFIG_ACPI
is disabled (e.g. on device tree platforms).
In this case, nxp-nci will silently fail to probe.

The other NFC drivers only log a debug message if
devm_acpi_dev_add_driver_gpios() fails.
Do the same in nxp-nci to fix this problem.

Fixes: ad0acfd69add ("NFC: nxp-nci: Get rid of code duplication in ->probe()")
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Stephan Gerhold <stephan@gerhold.net>
Acked-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/nfc/nxp-nci/i2c.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nfc/nxp-nci/i2c.c b/drivers/nfc/nxp-nci/i2c.c
index 4d1909aecd6c..9f60e4dc5a90 100644
--- a/drivers/nfc/nxp-nci/i2c.c
+++ b/drivers/nfc/nxp-nci/i2c.c
@@ -278,7 +278,7 @@ static int nxp_nci_i2c_probe(struct i2c_client *client,
 
 	r = devm_acpi_dev_add_driver_gpios(dev, acpi_nxp_nci_gpios);
 	if (r)
-		return r;
+		dev_dbg(dev, "Unable to add GPIO mapping table\n");
 
 	phy->gpiod_en = devm_gpiod_get(dev, "enable", GPIOD_OUT_LOW);
 	if (IS_ERR(phy->gpiod_en)) {
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Sat, Dec 28, 2019 at 12:14:42AM -0800, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.19 and
> v5.4 -stable, respectively.

All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 106 bytes --]


Please queue up the following networking bug fixes for v4.19 and v5.4
-stable, respectively.

Thank you!

[-- Attachment #2: net_419.mbox --]
[-- Type: Application/Octet-Stream, Size: 85141 bytes --]

From 4c5162e82e49a24a539e889427eeae03847e43c4 Mon Sep 17 00:00:00 2001
From: Netanel Belgazal <netanel@amazon.com>
Date: Tue, 10 Dec 2019 11:27:44 +0000
Subject: [PATCH 01/23] net: ena: fix napi handler misbehavior when the napi
 budget is zero

[ Upstream commit 24dee0c7478d1a1e00abdf5625b7f921467325dc ]

In netpoll the napi handler could be called with budget equal to zero.
Current ENA napi handler doesn't take that into consideration.

The napi handler handles Rx packets in a do-while loop.
Currently, the budget check happens only after decrementing the
budget, therefore the napi handler, in rare cases, could run over
MAX_INT packets.

In addition to that, this moves all budget related variables to int
calculation and stop mixing u32 to avoid ambiguity

Fixes: 1738cd3ed342 ("net: ena: Add a driver for Amazon Elastic Network Adapters (ENA)")
Signed-off-by: Netanel Belgazal <netanel@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index b5d72815776c..e26c195fec83 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -1197,8 +1197,8 @@ static int ena_io_poll(struct napi_struct *napi, int budget)
 	struct ena_napi *ena_napi = container_of(napi, struct ena_napi, napi);
 	struct ena_ring *tx_ring, *rx_ring;
 
-	u32 tx_work_done;
-	u32 rx_work_done;
+	int tx_work_done;
+	int rx_work_done = 0;
 	int tx_budget;
 	int napi_comp_call = 0;
 	int ret;
@@ -1215,7 +1215,11 @@ static int ena_io_poll(struct napi_struct *napi, int budget)
 	}
 
 	tx_work_done = ena_clean_tx_irq(tx_ring, tx_budget);
-	rx_work_done = ena_clean_rx_irq(rx_ring, napi, budget);
+	/* On netpoll the budget is zero and the handler should only clean the
+	 * tx completions.
+	 */
+	if (likely(budget))
+		rx_work_done = ena_clean_rx_irq(rx_ring, napi, budget);
 
 	/* If the device is about to reset or down, avoid unmask
 	 * the interrupt and return 0 so NAPI won't reschedule
-- 
2.20.1


From 2becf9e3e86ab929097fefb0c4f624ba25701341 Mon Sep 17 00:00:00 2001
From: Vladyslav Tarasiuk <vladyslavt@mellanox.com>
Date: Thu, 26 Dec 2019 10:41:56 +0200
Subject: [PATCH 02/23] net/mlxfw: Fix out-of-memory error in mfa2 flash
 burning

[ Upstream commit a5bcd72e054aabb93ddc51ed8cde36a5bfc50271 ]

The burning process requires to perform internal allocations of large
chunks of memory. This memory doesn't need to be contiguous and can be
safely allocated by vzalloc() instead of kzalloc(). This patch changes
such allocation to avoid possible out-of-memory failure.

Fixes: 410ed13cae39 ("Add the mlxfw module for Mellanox firmware flash process")
Signed-off-by: Vladyslav Tarasiuk <vladyslavt@mellanox.com>
Reviewed-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Tested-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.c b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.c
index 993cb5ba934e..b99169a386eb 100644
--- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.c
+++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.c
@@ -37,6 +37,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/netlink.h>
+#include <linux/vmalloc.h>
 #include <linux/xz.h>
 #include "mlxfw_mfa2.h"
 #include "mlxfw_mfa2_file.h"
@@ -579,7 +580,7 @@ mlxfw_mfa2_file_component_get(const struct mlxfw_mfa2_file *mfa2_file,
 	comp_size = be32_to_cpu(comp->size);
 	comp_buf_size = comp_size + mlxfw_mfa2_comp_magic_len;
 
-	comp_data = kmalloc(sizeof(*comp_data) + comp_buf_size, GFP_KERNEL);
+	comp_data = vzalloc(sizeof(*comp_data) + comp_buf_size);
 	if (!comp_data)
 		return ERR_PTR(-ENOMEM);
 	comp_data->comp.data_size = comp_size;
@@ -601,7 +602,7 @@ mlxfw_mfa2_file_component_get(const struct mlxfw_mfa2_file *mfa2_file,
 	comp_data->comp.data = comp_data->buff + mlxfw_mfa2_comp_magic_len;
 	return &comp_data->comp;
 err_out:
-	kfree(comp_data);
+	vfree(comp_data);
 	return ERR_PTR(err);
 }
 
@@ -610,7 +611,7 @@ void mlxfw_mfa2_file_component_put(struct mlxfw_mfa2_component *comp)
 	const struct mlxfw_mfa2_comp_data *comp_data;
 
 	comp_data = container_of(comp, struct mlxfw_mfa2_comp_data, comp);
-	kfree(comp_data);
+	vfree(comp_data);
 }
 
 void mlxfw_mfa2_file_fini(struct mlxfw_mfa2_file *mfa2_file)
-- 
2.20.1


From 2fc284ea24294bb4b88cf72451722c8bcde1e65c Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Thu, 26 Dec 2019 20:01:01 +0100
Subject: [PATCH 03/23] net: stmmac: dwmac-meson8b: Fix the RGMII TX delay on
 Meson8b/8m2 SoCs

[ Upstream commit bd6f48546b9cb7a785344fc78058c420923d7ed8 ]

GXBB and newer SoCs use the fixed FCLK_DIV2 (1GHz) clock as input for
the m250_sel clock. Meson8b and Meson8m2 use MPLL2 instead, whose rate
can be adjusted at runtime.

So far we have been running MPLL2 with ~250MHz (and the internal
m250_div with value 1), which worked enough that we could transfer data
with an TX delay of 4ns. Unfortunately there is high packet loss with
an RGMII PHY when transferring data (receiving data works fine though).
Odroid-C1's u-boot is running with a TX delay of only 2ns as well as
the internal m250_div set to 2 - no lost (TX) packets can be observed
with that setting in u-boot.

Manual testing has shown that the TX packet loss goes away when using
the following settings in Linux (the vendor kernel uses the same
settings):
- MPLL2 clock set to ~500MHz
- m250_div set to 2
- TX delay set to 2ns on the MAC side

Update the m250_div divider settings to only accept dividers greater or
equal 2 to fix the TX delay generated by the MAC.

iperf3 results before the change:
[ ID] Interval           Transfer     Bitrate         Retr
[  5]   0.00-10.00  sec   182 MBytes   153 Mbits/sec  514      sender
[  5]   0.00-10.00  sec   182 MBytes   152 Mbits/sec           receiver

iperf3 results after the change (including an updated TX delay of 2ns):
[ ID] Interval           Transfer     Bitrate         Retr  Cwnd
[  5]   0.00-10.00  sec   927 MBytes   778 Mbits/sec    0      sender
[  5]   0.00-10.01  sec   927 MBytes   777 Mbits/sec           receiver

Fixes: 4f6a71b84e1afd ("net: stmmac: dwmac-meson8b: fix internal RGMII clock configuration")
Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/stmicro/stmmac/dwmac-meson8b.c    | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
index c5979569fd60..94b46258e8ff 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
@@ -118,6 +118,14 @@ static int meson8b_init_rgmii_tx_clk(struct meson8b_dwmac *dwmac)
 	struct device *dev = dwmac->dev;
 	const char *parent_name, *mux_parent_names[MUX_CLK_NUM_PARENTS];
 	struct meson8b_dwmac_clk_configs *clk_configs;
+	static const struct clk_div_table div_table[] = {
+		{ .div = 2, .val = 2, },
+		{ .div = 3, .val = 3, },
+		{ .div = 4, .val = 4, },
+		{ .div = 5, .val = 5, },
+		{ .div = 6, .val = 6, },
+		{ .div = 7, .val = 7, },
+	};
 
 	clk_configs = devm_kzalloc(dev, sizeof(*clk_configs), GFP_KERNEL);
 	if (!clk_configs)
@@ -152,9 +160,9 @@ static int meson8b_init_rgmii_tx_clk(struct meson8b_dwmac *dwmac)
 	clk_configs->m250_div.reg = dwmac->regs + PRG_ETH0;
 	clk_configs->m250_div.shift = PRG_ETH0_CLK_M250_DIV_SHIFT;
 	clk_configs->m250_div.width = PRG_ETH0_CLK_M250_DIV_WIDTH;
-	clk_configs->m250_div.flags = CLK_DIVIDER_ONE_BASED |
-				CLK_DIVIDER_ALLOW_ZERO |
-				CLK_DIVIDER_ROUND_CLOSEST;
+	clk_configs->m250_div.table = div_table;
+	clk_configs->m250_div.flags = CLK_DIVIDER_ALLOW_ZERO |
+				      CLK_DIVIDER_ROUND_CLOSEST;
 	clk = meson8b_dwmac_register_clk(dwmac, "m250_div", &parent_name, 1,
 					 &clk_divider_ops,
 					 &clk_configs->m250_div.hw);
-- 
2.20.1


From 2e02e7a04973f2d59854b1f025e27c97b7b7ced2 Mon Sep 17 00:00:00 2001
From: Vladis Dronov <vdronov@redhat.com>
Date: Fri, 27 Dec 2019 03:26:27 +0100
Subject: [PATCH 04/23] ptp: fix the race between the release of ptp_clock and
 cdev

[ Upstream commit a33121e5487b424339636b25c35d3a180eaa5f5e ]

In a case when a ptp chardev (like /dev/ptp0) is open but an underlying
device is removed, closing this file leads to a race. This reproduces
easily in a kvm virtual machine:

ts# cat openptp0.c
int main() { ... fp = fopen("/dev/ptp0", "r"); ... sleep(10); }
ts# uname -r
5.5.0-rc3-46cf053e
ts# cat /proc/cmdline
... slub_debug=FZP
ts# modprobe ptp_kvm
ts# ./openptp0 &
[1] 670
opened /dev/ptp0, sleeping 10s...
ts# rmmod ptp_kvm
ts# ls /dev/ptp*
ls: cannot access '/dev/ptp*': No such file or directory
ts# ...woken up
[   48.010809] general protection fault: 0000 [#1] SMP
[   48.012502] CPU: 6 PID: 658 Comm: openptp0 Not tainted 5.5.0-rc3-46cf053e #25
[   48.014624] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), ...
[   48.016270] RIP: 0010:module_put.part.0+0x7/0x80
[   48.017939] RSP: 0018:ffffb3850073be00 EFLAGS: 00010202
[   48.018339] RAX: 000000006b6b6b6b RBX: 6b6b6b6b6b6b6b6b RCX: ffff89a476c00ad0
[   48.018936] RDX: fffff65a08d3ea08 RSI: 0000000000000247 RDI: 6b6b6b6b6b6b6b6b
[   48.019470] ...                                              ^^^ a slub poison
[   48.023854] Call Trace:
[   48.024050]  __fput+0x21f/0x240
[   48.024288]  task_work_run+0x79/0x90
[   48.024555]  do_exit+0x2af/0xab0
[   48.024799]  ? vfs_write+0x16a/0x190
[   48.025082]  do_group_exit+0x35/0x90
[   48.025387]  __x64_sys_exit_group+0xf/0x10
[   48.025737]  do_syscall_64+0x3d/0x130
[   48.026056]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[   48.026479] RIP: 0033:0x7f53b12082f6
[   48.026792] ...
[   48.030945] Modules linked in: ptp i6300esb watchdog [last unloaded: ptp_kvm]
[   48.045001] Fixing recursive fault but reboot is needed!

This happens in:

static void __fput(struct file *file)
{   ...
    if (file->f_op->release)
        file->f_op->release(inode, file); <<< cdev is kfree'd here
    if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL &&
             !(mode & FMODE_PATH))) {
        cdev_put(inode->i_cdev); <<< cdev fields are accessed here

Namely:

__fput()
  posix_clock_release()
    kref_put(&clk->kref, delete_clock) <<< the last reference
      delete_clock()
        delete_ptp_clock()
          kfree(ptp) <<< cdev is embedded in ptp
  cdev_put
    module_put(p->owner) <<< *p is kfree'd, bang!

Here cdev is embedded in posix_clock which is embedded in ptp_clock.
The race happens because ptp_clock's lifetime is controlled by two
refcounts: kref and cdev.kobj in posix_clock. This is wrong.

Make ptp_clock's sysfs device a parent of cdev with cdev_device_add()
created especially for such cases. This way the parent device with its
ptp_clock is not released until all references to the cdev are released.
This adds a requirement that an initialized but not exposed struct
device should be provided to posix_clock_register() by a caller instead
of a simple dev_t.

This approach was adopted from the commit 72139dfa2464 ("watchdog: Fix
the race between the release of watchdog_core_data and cdev"). See
details of the implementation in the commit 233ed09d7fda ("chardev: add
helper function to register char devs with a struct device").

Link: https://lore.kernel.org/linux-fsdevel/20191125125342.6189-1-vdronov@redhat.com/T/#u
Analyzed-by: Stephen Johnston <sjohnsto@redhat.com>
Analyzed-by: Vern Lovejoy <vlovejoy@redhat.com>
Signed-off-by: Vladis Dronov <vdronov@redhat.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/ptp/ptp_clock.c     | 31 ++++++++++++++-----------------
 drivers/ptp/ptp_private.h   |  2 +-
 include/linux/posix-clock.h | 19 +++++++++++--------
 kernel/time/posix-clock.c   | 31 +++++++++++++------------------
 4 files changed, 39 insertions(+), 44 deletions(-)

diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c
index c64903a5978f..b818f65480c1 100644
--- a/drivers/ptp/ptp_clock.c
+++ b/drivers/ptp/ptp_clock.c
@@ -175,9 +175,9 @@ static struct posix_clock_operations ptp_clock_ops = {
 	.read		= ptp_read,
 };
 
-static void delete_ptp_clock(struct posix_clock *pc)
+static void ptp_clock_release(struct device *dev)
 {
-	struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock);
+	struct ptp_clock *ptp = container_of(dev, struct ptp_clock, dev);
 
 	mutex_destroy(&ptp->tsevq_mux);
 	mutex_destroy(&ptp->pincfg_mux);
@@ -222,7 +222,6 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info,
 	}
 
 	ptp->clock.ops = ptp_clock_ops;
-	ptp->clock.release = delete_ptp_clock;
 	ptp->info = info;
 	ptp->devid = MKDEV(major, index);
 	ptp->index = index;
@@ -249,15 +248,6 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info,
 	if (err)
 		goto no_pin_groups;
 
-	/* Create a new device in our class. */
-	ptp->dev = device_create_with_groups(ptp_class, parent, ptp->devid,
-					     ptp, ptp->pin_attr_groups,
-					     "ptp%d", ptp->index);
-	if (IS_ERR(ptp->dev)) {
-		err = PTR_ERR(ptp->dev);
-		goto no_device;
-	}
-
 	/* Register a new PPS source. */
 	if (info->pps) {
 		struct pps_source_info pps;
@@ -273,8 +263,18 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info,
 		}
 	}
 
-	/* Create a posix clock. */
-	err = posix_clock_register(&ptp->clock, ptp->devid);
+	/* Initialize a new device of our class in our clock structure. */
+	device_initialize(&ptp->dev);
+	ptp->dev.devt = ptp->devid;
+	ptp->dev.class = ptp_class;
+	ptp->dev.parent = parent;
+	ptp->dev.groups = ptp->pin_attr_groups;
+	ptp->dev.release = ptp_clock_release;
+	dev_set_drvdata(&ptp->dev, ptp);
+	dev_set_name(&ptp->dev, "ptp%d", ptp->index);
+
+	/* Create a posix clock and link it to the device. */
+	err = posix_clock_register(&ptp->clock, &ptp->dev);
 	if (err) {
 		pr_err("failed to create posix clock\n");
 		goto no_clock;
@@ -286,8 +286,6 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info,
 	if (ptp->pps_source)
 		pps_unregister_source(ptp->pps_source);
 no_pps:
-	device_destroy(ptp_class, ptp->devid);
-no_device:
 	ptp_cleanup_pin_groups(ptp);
 no_pin_groups:
 	if (ptp->kworker)
@@ -317,7 +315,6 @@ int ptp_clock_unregister(struct ptp_clock *ptp)
 	if (ptp->pps_source)
 		pps_unregister_source(ptp->pps_source);
 
-	device_destroy(ptp_class, ptp->devid);
 	ptp_cleanup_pin_groups(ptp);
 
 	posix_clock_unregister(&ptp->clock);
diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h
index c7c62b782cb9..05f6b6a9bbd5 100644
--- a/drivers/ptp/ptp_private.h
+++ b/drivers/ptp/ptp_private.h
@@ -41,7 +41,7 @@ struct timestamp_event_queue {
 
 struct ptp_clock {
 	struct posix_clock clock;
-	struct device *dev;
+	struct device dev;
 	struct ptp_clock_info *info;
 	dev_t devid;
 	int index; /* index into clocks.map */
diff --git a/include/linux/posix-clock.h b/include/linux/posix-clock.h
index 3a3bc71017d5..03cb1f21b0e0 100644
--- a/include/linux/posix-clock.h
+++ b/include/linux/posix-clock.h
@@ -82,29 +82,32 @@ struct posix_clock_operations {
  *
  * @ops:     Functional interface to the clock
  * @cdev:    Character device instance for this clock
- * @kref:    Reference count.
+ * @dev:     Pointer to the clock's device.
  * @rwsem:   Protects the 'zombie' field from concurrent access.
  * @zombie:  If 'zombie' is true, then the hardware has disappeared.
- * @release: A function to free the structure when the reference count reaches
- *           zero. May be NULL if structure is statically allocated.
  *
  * Drivers should embed their struct posix_clock within a private
  * structure, obtaining a reference to it during callbacks using
  * container_of().
+ *
+ * Drivers should supply an initialized but not exposed struct device
+ * to posix_clock_register(). It is used to manage lifetime of the
+ * driver's private structure. It's 'release' field should be set to
+ * a release function for this private structure.
  */
 struct posix_clock {
 	struct posix_clock_operations ops;
 	struct cdev cdev;
-	struct kref kref;
+	struct device *dev;
 	struct rw_semaphore rwsem;
 	bool zombie;
-	void (*release)(struct posix_clock *clk);
 };
 
 /**
  * posix_clock_register() - register a new clock
- * @clk:   Pointer to the clock. Caller must provide 'ops' and 'release'
- * @devid: Allocated device id
+ * @clk:   Pointer to the clock. Caller must provide 'ops' field
+ * @dev:   Pointer to the initialized device. Caller must provide
+ *         'release' field
  *
  * A clock driver calls this function to register itself with the
  * clock device subsystem. If 'clk' points to dynamically allocated
@@ -113,7 +116,7 @@ struct posix_clock {
  *
  * Returns zero on success, non-zero otherwise.
  */
-int posix_clock_register(struct posix_clock *clk, dev_t devid);
+int posix_clock_register(struct posix_clock *clk, struct device *dev);
 
 /**
  * posix_clock_unregister() - unregister a clock
diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c
index fe56c4e06c51..c8a8501fae5b 100644
--- a/kernel/time/posix-clock.c
+++ b/kernel/time/posix-clock.c
@@ -27,8 +27,6 @@
 
 #include "posix-timers.h"
 
-static void delete_clock(struct kref *kref);
-
 /*
  * Returns NULL if the posix_clock instance attached to 'fp' is old and stale.
  */
@@ -138,7 +136,7 @@ static int posix_clock_open(struct inode *inode, struct file *fp)
 		err = 0;
 
 	if (!err) {
-		kref_get(&clk->kref);
+		get_device(clk->dev);
 		fp->private_data = clk;
 	}
 out:
@@ -154,7 +152,7 @@ static int posix_clock_release(struct inode *inode, struct file *fp)
 	if (clk->ops.release)
 		err = clk->ops.release(clk);
 
-	kref_put(&clk->kref, delete_clock);
+	put_device(clk->dev);
 
 	fp->private_data = NULL;
 
@@ -174,38 +172,35 @@ static const struct file_operations posix_clock_file_operations = {
 #endif
 };
 
-int posix_clock_register(struct posix_clock *clk, dev_t devid)
+int posix_clock_register(struct posix_clock *clk, struct device *dev)
 {
 	int err;
 
-	kref_init(&clk->kref);
 	init_rwsem(&clk->rwsem);
 
 	cdev_init(&clk->cdev, &posix_clock_file_operations);
+	err = cdev_device_add(&clk->cdev, dev);
+	if (err) {
+		pr_err("%s unable to add device %d:%d\n",
+			dev_name(dev), MAJOR(dev->devt), MINOR(dev->devt));
+		return err;
+	}
 	clk->cdev.owner = clk->ops.owner;
-	err = cdev_add(&clk->cdev, devid, 1);
+	clk->dev = dev;
 
-	return err;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(posix_clock_register);
 
-static void delete_clock(struct kref *kref)
-{
-	struct posix_clock *clk = container_of(kref, struct posix_clock, kref);
-
-	if (clk->release)
-		clk->release(clk);
-}
-
 void posix_clock_unregister(struct posix_clock *clk)
 {
-	cdev_del(&clk->cdev);
+	cdev_device_del(&clk->cdev, clk->dev);
 
 	down_write(&clk->rwsem);
 	clk->zombie = true;
 	up_write(&clk->rwsem);
 
-	kref_put(&clk->kref, delete_clock);
+	put_device(clk->dev);
 }
 EXPORT_SYMBOL_GPL(posix_clock_unregister);
 
-- 
2.20.1


From b4c73728758707b9f1ac9ee1d0df8e8daf14485e Mon Sep 17 00:00:00 2001
From: Cambda Zhu <cambda@linux.alibaba.com>
Date: Fri, 27 Dec 2019 16:52:37 +0800
Subject: [PATCH 05/23] tcp: Fix highest_sack and highest_sack_seq

[ Upstream commit 853697504de043ff0bfd815bd3a64de1dce73dc7 ]

>From commit 50895b9de1d3 ("tcp: highest_sack fix"), the logic about
setting tp->highest_sack to the head of the send queue was removed.
Of course the logic is error prone, but it is logical. Before we
remove the pointer to the highest sack skb and use the seq instead,
we need to set tp->highest_sack to NULL when there is no skb after
the last sack, and then replace NULL with the real skb when new skb
inserted into the rtx queue, because the NULL means the highest sack
seq is tp->snd_nxt. If tp->highest_sack is NULL and new data sent,
the next ACK with sack option will increase tp->reordering unexpectedly.

This patch sets tp->highest_sack to the tail of the rtx queue if
it's NULL and new data is sent. The patch keeps the rule that the
highest_sack can only be maintained by sack processing, except for
this only case.

Fixes: 50895b9de1d3 ("tcp: highest_sack fix")
Signed-off-by: Cambda Zhu <cambda@linux.alibaba.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index ad787e7882f7..e3ce1f56f845 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -60,6 +60,9 @@ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb)
 	__skb_unlink(skb, &sk->sk_write_queue);
 	tcp_rbtree_insert(&sk->tcp_rtx_queue, skb);
 
+	if (tp->highest_sack == NULL)
+		tp->highest_sack = skb;
+
 	tp->packets_out += tcp_skb_pcount(skb);
 	if (!prior_packets || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)
 		tcp_rearm_rto(sk);
-- 
2.20.1


From a447c982cef37e2b7f1a18f8b68b89ce0f9d2a73 Mon Sep 17 00:00:00 2001
From: Antonio Messina <amessina@google.com>
Date: Thu, 19 Dec 2019 15:08:03 +0100
Subject: [PATCH 06/23] udp: fix integer overflow while computing available
 space in sk_rcvbuf

[ Upstream commit feed8a4fc9d46c3126fb9fcae0e9248270c6321a ]

When the size of the receive buffer for a socket is close to 2^31 when
computing if we have enough space in the buffer to copy a packet from
the queue to the buffer we might hit an integer overflow.

When an user set net.core.rmem_default to a value close to 2^31 UDP
packets are dropped because of this overflow. This can be visible, for
instance, with failure to resolve hostnames.

This can be fixed by casting sk_rcvbuf (which is an int) to unsigned
int, similarly to how it is done in TCP.

Signed-off-by: Antonio Messina <amessina@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 8877bd140a0d..2eeae0455b14 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1412,7 +1412,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb)
 	 * queue contains some other skb
 	 */
 	rmem = atomic_add_return(size, &sk->sk_rmem_alloc);
-	if (rmem > (size + sk->sk_rcvbuf))
+	if (rmem > (size + (unsigned int)sk->sk_rcvbuf))
 		goto uncharge_drop;
 
 	spin_lock(&list->lock);
-- 
2.20.1


From f8e093f5f40e7e8aaa9b82c42e40066c8a72a2dd Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Fri, 6 Dec 2019 15:39:12 +0100
Subject: [PATCH 07/23] vhost/vsock: accept only packets with the right dst_cid

[ Upstream commit 8a3cc29c316c17de590e3ff8b59f3d6cbfd37b0a ]

When we receive a new packet from the guest, we check if the
src_cid is correct, but we forgot to check the dst_cid.

The host should accept only packets where dst_cid is
equal to the host CID.

Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/vsock.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 8dcee4faf701..5f5c5de31f10 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -436,7 +436,9 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work)
 		virtio_transport_deliver_tap_pkt(pkt);
 
 		/* Only accept correctly addressed packets */
-		if (le64_to_cpu(pkt->hdr.src_cid) == vsock->guest_cid)
+		if (le64_to_cpu(pkt->hdr.src_cid) == vsock->guest_cid &&
+		    le64_to_cpu(pkt->hdr.dst_cid) ==
+		    vhost_transport_get_local_cid())
 			virtio_transport_recv_pkt(pkt);
 		else
 			virtio_transport_free_pkt(pkt);
-- 
2.20.1


From 8cf0c38071dc364db6a9a3e7e24b8f07fbd28c5c Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Sun, 22 Dec 2019 10:51:09 +0800
Subject: [PATCH 08/23] net: add bool confirm_neigh parameter for
 dst_ops.update_pmtu

[ Upstream commit bd085ef678b2cc8c38c105673dfe8ff8f5ec0c57 ]

The MTU update code is supposed to be invoked in response to real
networking events that update the PMTU. In IPv6 PMTU update function
__ip6_rt_update_pmtu() we called dst_confirm_neigh() to update neighbor
confirmed time.

But for tunnel code, it will call pmtu before xmit, like:
  - tnl_update_pmtu()
    - skb_dst_update_pmtu()
      - ip6_rt_update_pmtu()
        - __ip6_rt_update_pmtu()
          - dst_confirm_neigh()

If the tunnel remote dst mac address changed and we still do the neigh
confirm, we will not be able to update neigh cache and ping6 remote
will failed.

So for this ip_tunnel_xmit() case, _EVEN_ if the MTU is changed, we
should not be invoking dst_confirm_neigh() as we have no evidence
of successful two-way communication at this point.

On the other hand it is also important to keep the neigh reachability fresh
for TCP flows, so we cannot remove this dst_confirm_neigh() call.

To fix the issue, we have to add a new bool parameter for dst_ops.update_pmtu
to choose whether we should do neigh update or not. I will add the parameter
in this patch and set all the callers to true to comply with the previous
way, and fix the tunnel code one by one on later patches.

v5: No change.
v4: No change.
v3: Do not remove dst_confirm_neigh, but add a new bool parameter in
    dst_ops.update_pmtu to control whether we should do neighbor confirm.
    Also split the big patch to small ones for each area.
v2: Remove dst_confirm_neigh in __ip6_rt_update_pmtu.

Suggested-by: David Miller <davem@davemloft.net>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/gtp.c                |  2 +-
 include/net/dst.h                |  2 +-
 include/net/dst_ops.h            |  3 ++-
 net/bridge/br_nf_core.c          |  3 ++-
 net/decnet/dn_route.c            |  6 ++++--
 net/ipv4/inet_connection_sock.c  |  2 +-
 net/ipv4/route.c                 |  9 ++++++---
 net/ipv4/xfrm4_policy.c          |  5 +++--
 net/ipv6/inet6_connection_sock.c |  2 +-
 net/ipv6/ip6_gre.c               |  2 +-
 net/ipv6/route.c                 | 22 +++++++++++++++-------
 net/ipv6/xfrm6_policy.c          |  5 +++--
 net/netfilter/ipvs/ip_vs_xmit.c  |  2 +-
 net/sctp/transport.c             |  2 +-
 14 files changed, 42 insertions(+), 25 deletions(-)

diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index d178d5bad7e4..9e3963f46458 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -545,7 +545,7 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev,
 		mtu = dst_mtu(&rt->dst);
 	}
 
-	rt->dst.ops->update_pmtu(&rt->dst, NULL, skb, mtu);
+	rt->dst.ops->update_pmtu(&rt->dst, NULL, skb, mtu, true);
 
 	if (!skb_is_gso(skb) && (iph->frag_off & htons(IP_DF)) &&
 	    mtu < ntohs(iph->tot_len)) {
diff --git a/include/net/dst.h b/include/net/dst.h
index 851cf1124240..aac3f5b4c7b5 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -527,7 +527,7 @@ static inline void skb_dst_update_pmtu(struct sk_buff *skb, u32 mtu)
 	struct dst_entry *dst = skb_dst(skb);
 
 	if (dst && dst->ops->update_pmtu)
-		dst->ops->update_pmtu(dst, NULL, skb, mtu);
+		dst->ops->update_pmtu(dst, NULL, skb, mtu, true);
 }
 
 static inline void skb_tunnel_check_pmtu(struct sk_buff *skb,
diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h
index 5ec645f27ee3..443863c7b8da 100644
--- a/include/net/dst_ops.h
+++ b/include/net/dst_ops.h
@@ -27,7 +27,8 @@ struct dst_ops {
 	struct dst_entry *	(*negative_advice)(struct dst_entry *);
 	void			(*link_failure)(struct sk_buff *);
 	void			(*update_pmtu)(struct dst_entry *dst, struct sock *sk,
-					       struct sk_buff *skb, u32 mtu);
+					       struct sk_buff *skb, u32 mtu,
+					       bool confirm_neigh);
 	void			(*redirect)(struct dst_entry *dst, struct sock *sk,
 					    struct sk_buff *skb);
 	int			(*local_out)(struct net *net, struct sock *sk, struct sk_buff *skb);
diff --git a/net/bridge/br_nf_core.c b/net/bridge/br_nf_core.c
index 8e2d7cfa4e16..d88e724d5755 100644
--- a/net/bridge/br_nf_core.c
+++ b/net/bridge/br_nf_core.c
@@ -26,7 +26,8 @@
 #endif
 
 static void fake_update_pmtu(struct dst_entry *dst, struct sock *sk,
-			     struct sk_buff *skb, u32 mtu)
+			     struct sk_buff *skb, u32 mtu,
+			     bool confirm_neigh)
 {
 }
 
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index 1c002c0fb712..658191fba94e 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -118,7 +118,8 @@ static void dn_dst_ifdown(struct dst_entry *, struct net_device *dev, int how);
 static struct dst_entry *dn_dst_negative_advice(struct dst_entry *);
 static void dn_dst_link_failure(struct sk_buff *);
 static void dn_dst_update_pmtu(struct dst_entry *dst, struct sock *sk,
-			       struct sk_buff *skb , u32 mtu);
+			       struct sk_buff *skb , u32 mtu,
+			       bool confirm_neigh);
 static void dn_dst_redirect(struct dst_entry *dst, struct sock *sk,
 			    struct sk_buff *skb);
 static struct neighbour *dn_dst_neigh_lookup(const struct dst_entry *dst,
@@ -259,7 +260,8 @@ static int dn_dst_gc(struct dst_ops *ops)
  * advertise to the other end).
  */
 static void dn_dst_update_pmtu(struct dst_entry *dst, struct sock *sk,
-			       struct sk_buff *skb, u32 mtu)
+			       struct sk_buff *skb, u32 mtu,
+			       bool confirm_neigh)
 {
 	struct dn_route *rt = (struct dn_route *) dst;
 	struct neighbour *n = rt->n;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 15e7f7915a21..636a11c56cf5 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -1089,7 +1089,7 @@ struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu)
 		if (!dst)
 			goto out;
 	}
-	dst->ops->update_pmtu(dst, sk, NULL, mtu);
+	dst->ops->update_pmtu(dst, sk, NULL, mtu, true);
 
 	dst = __sk_dst_check(sk, 0);
 	if (!dst)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 69127f6039b2..4590af506244 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -142,7 +142,8 @@ static unsigned int	 ipv4_mtu(const struct dst_entry *dst);
 static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst);
 static void		 ipv4_link_failure(struct sk_buff *skb);
 static void		 ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
-					   struct sk_buff *skb, u32 mtu);
+					   struct sk_buff *skb, u32 mtu,
+					   bool confirm_neigh);
 static void		 ip_do_redirect(struct dst_entry *dst, struct sock *sk,
 					struct sk_buff *skb);
 static void		ipv4_dst_destroy(struct dst_entry *dst);
@@ -1035,7 +1036,8 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
 }
 
 static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
-			      struct sk_buff *skb, u32 mtu)
+			      struct sk_buff *skb, u32 mtu,
+			      bool confirm_neigh)
 {
 	struct rtable *rt = (struct rtable *) dst;
 	struct flowi4 fl4;
@@ -2559,7 +2561,8 @@ static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst)
 }
 
 static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
-					  struct sk_buff *skb, u32 mtu)
+					  struct sk_buff *skb, u32 mtu,
+					  bool confirm_neigh)
 {
 }
 
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 2b144b92ae46..1e5e2e4be0b2 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -222,12 +222,13 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 }
 
 static void xfrm4_update_pmtu(struct dst_entry *dst, struct sock *sk,
-			      struct sk_buff *skb, u32 mtu)
+			      struct sk_buff *skb, u32 mtu,
+			      bool confirm_neigh)
 {
 	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
 	struct dst_entry *path = xdst->route;
 
-	path->ops->update_pmtu(path, sk, skb, mtu);
+	path->ops->update_pmtu(path, sk, skb, mtu, confirm_neigh);
 }
 
 static void xfrm4_redirect(struct dst_entry *dst, struct sock *sk,
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 9a31d13bf180..890adadcda16 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -150,7 +150,7 @@ struct dst_entry *inet6_csk_update_pmtu(struct sock *sk, u32 mtu)
 
 	if (IS_ERR(dst))
 		return NULL;
-	dst->ops->update_pmtu(dst, sk, NULL, mtu);
+	dst->ops->update_pmtu(dst, sk, NULL, mtu, true);
 
 	dst = inet6_csk_route_socket(sk, &fl6);
 	return IS_ERR(dst) ? NULL : dst;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 8fd28edd6ac5..9853fa47641e 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1060,7 +1060,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 
 	/* TooBig packet may have updated dst->dev's mtu */
 	if (!t->parms.collect_md && dst && dst_mtu(dst) > dst->dev->mtu)
-		dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu);
+		dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu, true);
 
 	err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu,
 			   NEXTHDR_GRE);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 076c21f6a645..f8fe4c9ead4d 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -99,7 +99,8 @@ static int		ip6_pkt_prohibit(struct sk_buff *skb);
 static int		ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff *skb);
 static void		ip6_link_failure(struct sk_buff *skb);
 static void		ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
-					   struct sk_buff *skb, u32 mtu);
+					   struct sk_buff *skb, u32 mtu,
+					   bool confirm_neigh);
 static void		rt6_do_redirect(struct dst_entry *dst, struct sock *sk,
 					struct sk_buff *skb);
 static int rt6_score_route(struct fib6_info *rt, int oif, int strict);
@@ -266,7 +267,8 @@ static unsigned int ip6_blackhole_mtu(const struct dst_entry *dst)
 }
 
 static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
-					 struct sk_buff *skb, u32 mtu)
+					 struct sk_buff *skb, u32 mtu,
+					 bool confirm_neigh)
 {
 }
 
@@ -2352,7 +2354,8 @@ static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt)
 }
 
 static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
-				 const struct ipv6hdr *iph, u32 mtu)
+				 const struct ipv6hdr *iph, u32 mtu,
+				 bool confirm_neigh)
 {
 	const struct in6_addr *daddr, *saddr;
 	struct rt6_info *rt6 = (struct rt6_info *)dst;
@@ -2370,7 +2373,10 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
 		daddr = NULL;
 		saddr = NULL;
 	}
-	dst_confirm_neigh(dst, daddr);
+
+	if (confirm_neigh)
+		dst_confirm_neigh(dst, daddr);
+
 	mtu = max_t(u32, mtu, IPV6_MIN_MTU);
 	if (mtu >= dst_mtu(dst))
 		return;
@@ -2401,9 +2407,11 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
 }
 
 static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
-			       struct sk_buff *skb, u32 mtu)
+			       struct sk_buff *skb, u32 mtu,
+			       bool confirm_neigh)
 {
-	__ip6_rt_update_pmtu(dst, sk, skb ? ipv6_hdr(skb) : NULL, mtu);
+	__ip6_rt_update_pmtu(dst, sk, skb ? ipv6_hdr(skb) : NULL, mtu,
+			     confirm_neigh);
 }
 
 void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
@@ -2423,7 +2431,7 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
 
 	dst = ip6_route_output(net, NULL, &fl6);
 	if (!dst->error)
-		__ip6_rt_update_pmtu(dst, NULL, iph, ntohl(mtu));
+		__ip6_rt_update_pmtu(dst, NULL, iph, ntohl(mtu), true);
 	dst_release(dst);
 }
 EXPORT_SYMBOL_GPL(ip6_update_pmtu);
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index d35bcf92969c..30232591cf2b 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -221,12 +221,13 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
 }
 
 static void xfrm6_update_pmtu(struct dst_entry *dst, struct sock *sk,
-			      struct sk_buff *skb, u32 mtu)
+			      struct sk_buff *skb, u32 mtu,
+			      bool confirm_neigh)
 {
 	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
 	struct dst_entry *path = xdst->route;
 
-	path->ops->update_pmtu(path, sk, skb, mtu);
+	path->ops->update_pmtu(path, sk, skb, mtu, confirm_neigh);
 }
 
 static void xfrm6_redirect(struct dst_entry *dst, struct sock *sk,
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 473cce2a5231..3f75cd947045 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -209,7 +209,7 @@ static inline void maybe_update_pmtu(int skb_af, struct sk_buff *skb, int mtu)
 	struct rtable *ort = skb_rtable(skb);
 
 	if (!skb->dev && sk && sk_fullsock(sk))
-		ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu);
+		ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu, true);
 }
 
 static inline bool ensure_mtu_is_adequate(struct netns_ipvs *ipvs, int skb_af,
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index ad158d311ffa..c0d55ed62d2e 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -278,7 +278,7 @@ bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu)
 
 		pf->af->from_sk(&addr, sk);
 		pf->to_sk_daddr(&t->ipaddr, sk);
-		dst->ops->update_pmtu(dst, sk, NULL, pmtu);
+		dst->ops->update_pmtu(dst, sk, NULL, pmtu, true);
 		pf->to_sk_daddr(&addr, sk);
 
 		dst = sctp_transport_dst_check(t);
-- 
2.20.1


From 79b5d5c17f8691b092ab41bcc7afeea8441d7249 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Sun, 22 Dec 2019 10:51:10 +0800
Subject: [PATCH 09/23] ip6_gre: do not confirm neighbor when do pmtu update

[ Upstream commit 675d76ad0ad5bf41c9a129772ef0aba8f57ea9a7 ]

When we do ipv6 gre pmtu update, we will also do neigh confirm currently.
This will cause the neigh cache be refreshed and set to REACHABLE before
xmit.

But if the remote mac address changed, e.g. device is deleted and recreated,
we will not able to notice this and still use the old mac address as the neigh
cache is REACHABLE.

Fix this by disable neigh confirm when do pmtu update

v5: No change.
v4: No change.
v3: Do not remove dst_confirm_neigh, but add a new bool parameter in
    dst_ops.update_pmtu to control whether we should do neighbor confirm.
    Also split the big patch to small ones for each area.
v2: Remove dst_confirm_neigh in __ip6_rt_update_pmtu.

Reported-by: Jianlin Shi <jishi@redhat.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 9853fa47641e..b3515a4f1303 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1060,7 +1060,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 
 	/* TooBig packet may have updated dst->dev's mtu */
 	if (!t->parms.collect_md && dst && dst_mtu(dst) > dst->dev->mtu)
-		dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu, true);
+		dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu, false);
 
 	err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu,
 			   NEXTHDR_GRE);
-- 
2.20.1


From 9aa6c4b069f0102aa2c39f7ba3b1a900a7ae8220 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Sun, 22 Dec 2019 10:51:11 +0800
Subject: [PATCH 10/23] gtp: do not confirm neighbor when do pmtu update

[ Upstream commit 6e9105c73f8d2163d12d5dfd762fd75483ed30f5 ]

When do IPv6 tunnel PMTU update and calls __ip6_rt_update_pmtu() in the end,
we should not call dst_confirm_neigh() as there is no two-way communication.

Although GTP only support ipv4 right now, and __ip_rt_update_pmtu() does not
call dst_confirm_neigh(), we still set it to false to keep consistency with
IPv6 code.

v5: No change.
v4: No change.
v3: Do not remove dst_confirm_neigh, but add a new bool parameter in
    dst_ops.update_pmtu to control whether we should do neighbor confirm.
    Also split the big patch to small ones for each area.
v2: Remove dst_confirm_neigh in __ip6_rt_update_pmtu.

Reviewed-by: Guillaume Nault <gnault@redhat.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/gtp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 9e3963f46458..d957ffdfec0f 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -545,7 +545,7 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev,
 		mtu = dst_mtu(&rt->dst);
 	}
 
-	rt->dst.ops->update_pmtu(&rt->dst, NULL, skb, mtu, true);
+	rt->dst.ops->update_pmtu(&rt->dst, NULL, skb, mtu, false);
 
 	if (!skb_is_gso(skb) && (iph->frag_off & htons(IP_DF)) &&
 	    mtu < ntohs(iph->tot_len)) {
-- 
2.20.1


From dc690082bbfd54797b86523a8108bb0afebd2ad7 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Sun, 22 Dec 2019 10:51:12 +0800
Subject: [PATCH 11/23] net/dst: add new function
 skb_dst_update_pmtu_no_confirm

[ Upstream commit 07dc35c6e3cc3c001915d05f5bf21f80a39a0970 ]

Add a new function skb_dst_update_pmtu_no_confirm() for callers who need
update pmtu but should not do neighbor confirm.

v5: No change.
v4: No change.
v3: Do not remove dst_confirm_neigh, but add a new bool parameter in
    dst_ops.update_pmtu to control whether we should do neighbor confirm.
    Also split the big patch to small ones for each area.
v2: Remove dst_confirm_neigh in __ip6_rt_update_pmtu.

Reviewed-by: Guillaume Nault <gnault@redhat.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst.h | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/include/net/dst.h b/include/net/dst.h
index aac3f5b4c7b5..c886c45ba286 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -530,6 +530,15 @@ static inline void skb_dst_update_pmtu(struct sk_buff *skb, u32 mtu)
 		dst->ops->update_pmtu(dst, NULL, skb, mtu, true);
 }
 
+/* update dst pmtu but not do neighbor confirm */
+static inline void skb_dst_update_pmtu_no_confirm(struct sk_buff *skb, u32 mtu)
+{
+	struct dst_entry *dst = skb_dst(skb);
+
+	if (dst && dst->ops->update_pmtu)
+		dst->ops->update_pmtu(dst, NULL, skb, mtu, false);
+}
+
 static inline void skb_tunnel_check_pmtu(struct sk_buff *skb,
 					 struct dst_entry *encap_dst,
 					 int headroom)
-- 
2.20.1


From 3650478934a67296964764fbe9fb998d64dff5de Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Sun, 22 Dec 2019 10:51:13 +0800
Subject: [PATCH 12/23] tunnel: do not confirm neighbor when do pmtu update

[ Upstream commit 7a1592bcb15d71400a98632727791d1e68ea0ee8 ]

When do tunnel PMTU update and calls __ip6_rt_update_pmtu() in the end,
we should not call dst_confirm_neigh() as there is no two-way communication.

v5: No Change.
v4: Update commit description
v3: Do not remove dst_confirm_neigh, but add a new bool parameter in
    dst_ops.update_pmtu to control whether we should do neighbor confirm.
    Also split the big patch to small ones for each area.
v2: Remove dst_confirm_neigh in __ip6_rt_update_pmtu.

Fixes: 0dec879f636f ("net: use dst_confirm_neigh for UDP, RAW, ICMP, L2TP")
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Tested-by: Guillaume Nault <gnault@redhat.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_tunnel.c  | 2 +-
 net/ipv6/ip6_tunnel.c | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 054d01c16dc6..420e891ac59d 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -513,7 +513,7 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
 	else
 		mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
 
-	skb_dst_update_pmtu(skb, mtu);
+	skb_dst_update_pmtu_no_confirm(skb, mtu);
 
 	if (skb->protocol == htons(ETH_P_IP)) {
 		if (!skb_is_gso(skb) &&
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index d0ad85b8650d..e3b4237b2832 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -645,7 +645,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		if (rel_info > dst_mtu(skb_dst(skb2)))
 			goto out;
 
-		skb_dst_update_pmtu(skb2, rel_info);
+		skb_dst_update_pmtu_no_confirm(skb2, rel_info);
 	}
 
 	icmp_send(skb2, rel_type, rel_code, htonl(rel_info));
@@ -1137,7 +1137,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 	mtu = max(mtu, skb->protocol == htons(ETH_P_IPV6) ?
 		       IPV6_MIN_MTU : IPV4_MIN_MTU);
 
-	skb_dst_update_pmtu(skb, mtu);
+	skb_dst_update_pmtu_no_confirm(skb, mtu);
 	if (skb->len - t->tun_hlen - eth_hlen > mtu && !skb_is_gso(skb)) {
 		*pmtu = mtu;
 		err = -EMSGSIZE;
-- 
2.20.1


From 4789b816b9e1496f4f2f2b42e015760e4ca8027e Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Sun, 22 Dec 2019 10:51:14 +0800
Subject: [PATCH 13/23] vti: do not confirm neighbor when do pmtu update

[ Upstream commit 8247a79efa2f28b44329f363272550c1738377de ]

When do IPv6 tunnel PMTU update and calls __ip6_rt_update_pmtu() in the end,
we should not call dst_confirm_neigh() as there is no two-way communication.

Although vti and vti6 are immune to this problem because they are IFF_NOARP
interfaces, as Guillaume pointed. There is still no sense to confirm neighbour
here.

v5: Update commit description.
v4: No change.
v3: Do not remove dst_confirm_neigh, but add a new bool parameter in
    dst_ops.update_pmtu to control whether we should do neighbor confirm.
    Also split the big patch to small ones for each area.
v2: Remove dst_confirm_neigh in __ip6_rt_update_pmtu.

Reviewed-by: Guillaume Nault <gnault@redhat.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_vti.c  | 2 +-
 net/ipv6/ip6_vti.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 808f8d15c519..960f4faaf294 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -235,7 +235,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
 
 	mtu = dst_mtu(dst);
 	if (skb->len > mtu) {
-		skb_dst_update_pmtu(skb, mtu);
+		skb_dst_update_pmtu_no_confirm(skb, mtu);
 		if (skb->protocol == htons(ETH_P_IP)) {
 			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
 				  htonl(mtu));
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 8b6eefff2f7e..bfd39db3398a 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -483,7 +483,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 
 	mtu = dst_mtu(dst);
 	if (skb->len > mtu) {
-		skb_dst_update_pmtu(skb, mtu);
+		skb_dst_update_pmtu_no_confirm(skb, mtu);
 
 		if (skb->protocol == htons(ETH_P_IPV6)) {
 			if (mtu < IPV6_MIN_MTU)
-- 
2.20.1


From f848d38a2552e476dd4325fab86201c0ffe0d5e3 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Sun, 22 Dec 2019 10:51:15 +0800
Subject: [PATCH 14/23] sit: do not confirm neighbor when do pmtu update

[ Upstream commit 4d42df46d6372ece4cb4279870b46c2ea7304a47 ]

When do IPv6 tunnel PMTU update and calls __ip6_rt_update_pmtu() in the end,
we should not call dst_confirm_neigh() as there is no two-way communication.

v5: No change.
v4: No change.
v3: Do not remove dst_confirm_neigh, but add a new bool parameter in
    dst_ops.update_pmtu to control whether we should do neighbor confirm.
    Also split the big patch to small ones for each area.
v2: Remove dst_confirm_neigh in __ip6_rt_update_pmtu.

Reviewed-by: Guillaume Nault <gnault@redhat.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 41b3fe8ac3bc..bfed7508ba19 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -943,7 +943,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 		}
 
 		if (tunnel->parms.iph.daddr)
-			skb_dst_update_pmtu(skb, mtu);
+			skb_dst_update_pmtu_no_confirm(skb, mtu);
 
 		if (skb->len > mtu && !skb_is_gso(skb)) {
 			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
-- 
2.20.1


From 1f0782deaa6f952fd27356c9e92e5841641c6c17 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Sun, 22 Dec 2019 10:51:16 +0800
Subject: [PATCH 15/23] net/dst: do not confirm neighbor for vxlan and geneve
 pmtu update

[ Upstream commit f081042d128a0c7acbd67611def62e1b52e2d294 ]

When do IPv6 tunnel PMTU update and calls __ip6_rt_update_pmtu() in the end,
we should not call dst_confirm_neigh() as there is no two-way communication.

So disable the neigh confirm for vxlan and geneve pmtu update.

v5: No change.
v4: No change.
v3: Do not remove dst_confirm_neigh, but add a new bool parameter in
    dst_ops.update_pmtu to control whether we should do neighbor confirm.
    Also split the big patch to small ones for each area.
v2: Remove dst_confirm_neigh in __ip6_rt_update_pmtu.

Fixes: a93bf0ff4490 ("vxlan: update skb dst pmtu on tx path")
Fixes: 52a589d51f10 ("geneve: update skb dst pmtu on tx path")
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Tested-by: Guillaume Nault <gnault@redhat.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/dst.h b/include/net/dst.h
index c886c45ba286..35ae45fa0758 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -546,7 +546,7 @@ static inline void skb_tunnel_check_pmtu(struct sk_buff *skb,
 	u32 encap_mtu = dst_mtu(encap_dst);
 
 	if (skb->len > encap_mtu - headroom)
-		skb_dst_update_pmtu(skb, encap_mtu - headroom);
+		skb_dst_update_pmtu_no_confirm(skb, encap_mtu - headroom);
 }
 
 #endif /* _NET_DST_H */
-- 
2.20.1


From 755a3a00daaa4b853a22f72a6de630556cdbc876 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 12 Dec 2019 10:32:13 -0800
Subject: [PATCH 16/23] 6pack,mkiss: fix possible deadlock

[ Upstream commit 5c9934b6767b16ba60be22ec3cbd4379ad64170d ]

We got another syzbot report [1] that tells us we must use
write_lock_irq()/write_unlock_irq() to avoid possible deadlock.

[1]

WARNING: inconsistent lock state
5.5.0-rc1-syzkaller #0 Not tainted
--------------------------------
inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-R} usage.
syz-executor826/9605 [HC1[1]:SC0[0]:HE0:SE1] takes:
ffffffff8a128718 (disc_data_lock){+-..}, at: sp_get.isra.0+0x1d/0xf0 drivers/net/ppp/ppp_synctty.c:138
{HARDIRQ-ON-W} state was registered at:
  lock_acquire+0x190/0x410 kernel/locking/lockdep.c:4485
  __raw_write_lock_bh include/linux/rwlock_api_smp.h:203 [inline]
  _raw_write_lock_bh+0x33/0x50 kernel/locking/spinlock.c:319
  sixpack_close+0x1d/0x250 drivers/net/hamradio/6pack.c:657
  tty_ldisc_close.isra.0+0x119/0x1a0 drivers/tty/tty_ldisc.c:489
  tty_set_ldisc+0x230/0x6b0 drivers/tty/tty_ldisc.c:585
  tiocsetd drivers/tty/tty_io.c:2337 [inline]
  tty_ioctl+0xe8d/0x14f0 drivers/tty/tty_io.c:2597
  vfs_ioctl fs/ioctl.c:47 [inline]
  file_ioctl fs/ioctl.c:545 [inline]
  do_vfs_ioctl+0x977/0x14e0 fs/ioctl.c:732
  ksys_ioctl+0xab/0xd0 fs/ioctl.c:749
  __do_sys_ioctl fs/ioctl.c:756 [inline]
  __se_sys_ioctl fs/ioctl.c:754 [inline]
  __x64_sys_ioctl+0x73/0xb0 fs/ioctl.c:754
  do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294
  entry_SYSCALL_64_after_hwframe+0x49/0xbe
irq event stamp: 3946
hardirqs last  enabled at (3945): [<ffffffff87c86e43>] __raw_spin_unlock_irq include/linux/spinlock_api_smp.h:168 [inline]
hardirqs last  enabled at (3945): [<ffffffff87c86e43>] _raw_spin_unlock_irq+0x23/0x80 kernel/locking/spinlock.c:199
hardirqs last disabled at (3946): [<ffffffff8100675f>] trace_hardirqs_off_thunk+0x1a/0x1c arch/x86/entry/thunk_64.S:42
softirqs last  enabled at (2658): [<ffffffff86a8b4df>] spin_unlock_bh include/linux/spinlock.h:383 [inline]
softirqs last  enabled at (2658): [<ffffffff86a8b4df>] clusterip_netdev_event+0x46f/0x670 net/ipv4/netfilter/ipt_CLUSTERIP.c:222
softirqs last disabled at (2656): [<ffffffff86a8b22b>] spin_lock_bh include/linux/spinlock.h:343 [inline]
softirqs last disabled at (2656): [<ffffffff86a8b22b>] clusterip_netdev_event+0x1bb/0x670 net/ipv4/netfilter/ipt_CLUSTERIP.c:196

other info that might help us debug this:
 Possible unsafe locking scenario:

       CPU0
       ----
  lock(disc_data_lock);
  <Interrupt>
    lock(disc_data_lock);

 *** DEADLOCK ***

5 locks held by syz-executor826/9605:
 #0: ffff8880a905e198 (&tty->legacy_mutex){+.+.}, at: tty_lock+0xc7/0x130 drivers/tty/tty_mutex.c:19
 #1: ffffffff899a56c0 (rcu_read_lock){....}, at: mutex_spin_on_owner+0x0/0x330 kernel/locking/mutex.c:413
 #2: ffff8880a496a2b0 (&(&i->lock)->rlock){-.-.}, at: spin_lock include/linux/spinlock.h:338 [inline]
 #2: ffff8880a496a2b0 (&(&i->lock)->rlock){-.-.}, at: serial8250_interrupt+0x2d/0x1a0 drivers/tty/serial/8250/8250_core.c:116
 #3: ffffffff8c104048 (&port_lock_key){-.-.}, at: serial8250_handle_irq.part.0+0x24/0x330 drivers/tty/serial/8250/8250_port.c:1823
 #4: ffff8880a905e090 (&tty->ldisc_sem){++++}, at: tty_ldisc_ref+0x22/0x90 drivers/tty/tty_ldisc.c:288

stack backtrace:
CPU: 1 PID: 9605 Comm: syz-executor826 Not tainted 5.5.0-rc1-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x197/0x210 lib/dump_stack.c:118
 print_usage_bug.cold+0x327/0x378 kernel/locking/lockdep.c:3101
 valid_state kernel/locking/lockdep.c:3112 [inline]
 mark_lock_irq kernel/locking/lockdep.c:3309 [inline]
 mark_lock+0xbb4/0x1220 kernel/locking/lockdep.c:3666
 mark_usage kernel/locking/lockdep.c:3554 [inline]
 __lock_acquire+0x1e55/0x4a00 kernel/locking/lockdep.c:3909
 lock_acquire+0x190/0x410 kernel/locking/lockdep.c:4485
 __raw_read_lock include/linux/rwlock_api_smp.h:149 [inline]
 _raw_read_lock+0x32/0x50 kernel/locking/spinlock.c:223
 sp_get.isra.0+0x1d/0xf0 drivers/net/ppp/ppp_synctty.c:138
 sixpack_write_wakeup+0x25/0x340 drivers/net/hamradio/6pack.c:402
 tty_wakeup+0xe9/0x120 drivers/tty/tty_io.c:536
 tty_port_default_wakeup+0x2b/0x40 drivers/tty/tty_port.c:50
 tty_port_tty_wakeup+0x57/0x70 drivers/tty/tty_port.c:387
 uart_write_wakeup+0x46/0x70 drivers/tty/serial/serial_core.c:104
 serial8250_tx_chars+0x495/0xaf0 drivers/tty/serial/8250/8250_port.c:1761
 serial8250_handle_irq.part.0+0x2a2/0x330 drivers/tty/serial/8250/8250_port.c:1834
 serial8250_handle_irq drivers/tty/serial/8250/8250_port.c:1820 [inline]
 serial8250_default_handle_irq+0xc0/0x150 drivers/tty/serial/8250/8250_port.c:1850
 serial8250_interrupt+0xf1/0x1a0 drivers/tty/serial/8250/8250_core.c:126
 __handle_irq_event_percpu+0x15d/0x970 kernel/irq/handle.c:149
 handle_irq_event_percpu+0x74/0x160 kernel/irq/handle.c:189
 handle_irq_event+0xa7/0x134 kernel/irq/handle.c:206
 handle_edge_irq+0x25e/0x8d0 kernel/irq/chip.c:830
 generic_handle_irq_desc include/linux/irqdesc.h:156 [inline]
 do_IRQ+0xde/0x280 arch/x86/kernel/irq.c:250
 common_interrupt+0xf/0xf arch/x86/entry/entry_64.S:607
 </IRQ>
RIP: 0010:cpu_relax arch/x86/include/asm/processor.h:685 [inline]
RIP: 0010:mutex_spin_on_owner+0x247/0x330 kernel/locking/mutex.c:579
Code: c3 be 08 00 00 00 4c 89 e7 e8 e5 06 59 00 4c 89 e0 48 c1 e8 03 42 80 3c 38 00 0f 85 e1 00 00 00 49 8b 04 24 a8 01 75 96 f3 90 <e9> 2f fe ff ff 0f 0b e8 0d 19 09 00 84 c0 0f 85 ff fd ff ff 48 c7
RSP: 0018:ffffc90001eafa20 EFLAGS: 00000246 ORIG_RAX: ffffffffffffffd7
RAX: 0000000000000000 RBX: ffff88809fd9e0c0 RCX: 1ffffffff13266dd
RDX: 0000000000000000 RSI: 0000000000000008 RDI: 0000000000000000
RBP: ffffc90001eafa60 R08: 1ffff11013d22898 R09: ffffed1013d22899
R10: ffffed1013d22898 R11: ffff88809e9144c7 R12: ffff8880a905e138
R13: ffff88809e9144c0 R14: 0000000000000000 R15: dffffc0000000000
 mutex_optimistic_spin kernel/locking/mutex.c:673 [inline]
 __mutex_lock_common kernel/locking/mutex.c:962 [inline]
 __mutex_lock+0x32b/0x13c0 kernel/locking/mutex.c:1106
 mutex_lock_nested+0x16/0x20 kernel/locking/mutex.c:1121
 tty_lock+0xc7/0x130 drivers/tty/tty_mutex.c:19
 tty_release+0xb5/0xe90 drivers/tty/tty_io.c:1665
 __fput+0x2ff/0x890 fs/file_table.c:280
 ____fput+0x16/0x20 fs/file_table.c:313
 task_work_run+0x145/0x1c0 kernel/task_work.c:113
 exit_task_work include/linux/task_work.h:22 [inline]
 do_exit+0x8e7/0x2ef0 kernel/exit.c:797
 do_group_exit+0x135/0x360 kernel/exit.c:895
 __do_sys_exit_group kernel/exit.c:906 [inline]
 __se_sys_exit_group kernel/exit.c:904 [inline]
 __x64_sys_exit_group+0x44/0x50 kernel/exit.c:904
 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x43fef8
Code: Bad RIP value.
RSP: 002b:00007ffdb07d2338 EFLAGS: 00000246 ORIG_RAX: 00000000000000e7
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 000000000043fef8
RDX: 0000000000000000 RSI: 000000000000003c RDI: 0000000000000000
RBP: 00000000004bf730 R08: 00000000000000e7 R09: ffffffffffffffd0
R10: 00000000004002c8 R11: 0000000000000246 R12: 0000000000000001
R13: 00000000006d1180 R14: 0000000000000000 R15: 0000000000000000

Fixes: 6e4e2f811bad ("6pack,mkiss: fix lock inconsistency")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/hamradio/6pack.c | 4 ++--
 drivers/net/hamradio/mkiss.c | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c
index 54e63ec04907..8c636c493227 100644
--- a/drivers/net/hamradio/6pack.c
+++ b/drivers/net/hamradio/6pack.c
@@ -654,10 +654,10 @@ static void sixpack_close(struct tty_struct *tty)
 {
 	struct sixpack *sp;
 
-	write_lock_bh(&disc_data_lock);
+	write_lock_irq(&disc_data_lock);
 	sp = tty->disc_data;
 	tty->disc_data = NULL;
-	write_unlock_bh(&disc_data_lock);
+	write_unlock_irq(&disc_data_lock);
 	if (!sp)
 		return;
 
diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c
index 13e4c1eff353..3b14e6e281d4 100644
--- a/drivers/net/hamradio/mkiss.c
+++ b/drivers/net/hamradio/mkiss.c
@@ -783,10 +783,10 @@ static void mkiss_close(struct tty_struct *tty)
 {
 	struct mkiss *ax;
 
-	write_lock_bh(&disc_data_lock);
+	write_lock_irq(&disc_data_lock);
 	ax = tty->disc_data;
 	tty->disc_data = NULL;
-	write_unlock_bh(&disc_data_lock);
+	write_unlock_irq(&disc_data_lock);
 
 	if (!ax)
 		return;
-- 
2.20.1


From 6effd72d795f022cfb6123f9c500e55da28bb59a Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Wed, 11 Dec 2019 08:23:00 +0000
Subject: [PATCH 17/23] gtp: do not allow adding duplicate tid and ms_addr pdp
 context

[ Upstream commit 6b01b1d9b2d38dc84ac398bfe9f00baff06a31e5 ]

GTP RX packet path lookups pdp context with TID. If duplicate TID pdp
contexts are existing in the list, it couldn't select correct pdp context.
So, TID value  should be unique.
GTP TX packet path lookups pdp context with ms_addr. If duplicate ms_addr pdp
contexts are existing in the list, it couldn't select correct pdp context.
So, ms_addr value should be unique.

Fixes: 459aa660eb1d ("gtp: add initial driver for datapath of GPRS Tunneling Protocol (GTP-U)")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/gtp.c | 32 ++++++++++++++++++++++----------
 1 file changed, 22 insertions(+), 10 deletions(-)

diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index d957ffdfec0f..5a50f8842b5a 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -931,24 +931,31 @@ static void ipv4_pdp_fill(struct pdp_ctx *pctx, struct genl_info *info)
 	}
 }
 
-static int ipv4_pdp_add(struct gtp_dev *gtp, struct sock *sk,
-			struct genl_info *info)
+static int gtp_pdp_add(struct gtp_dev *gtp, struct sock *sk,
+		       struct genl_info *info)
 {
+	struct pdp_ctx *pctx, *pctx_tid = NULL;
 	struct net_device *dev = gtp->dev;
 	u32 hash_ms, hash_tid = 0;
-	struct pdp_ctx *pctx;
+	unsigned int version;
 	bool found = false;
 	__be32 ms_addr;
 
 	ms_addr = nla_get_be32(info->attrs[GTPA_MS_ADDRESS]);
 	hash_ms = ipv4_hashfn(ms_addr) % gtp->hash_size;
+	version = nla_get_u32(info->attrs[GTPA_VERSION]);
 
-	hlist_for_each_entry_rcu(pctx, &gtp->addr_hash[hash_ms], hlist_addr) {
-		if (pctx->ms_addr_ip4.s_addr == ms_addr) {
-			found = true;
-			break;
-		}
-	}
+	pctx = ipv4_pdp_find(gtp, ms_addr);
+	if (pctx)
+		found = true;
+	if (version == GTP_V0)
+		pctx_tid = gtp0_pdp_find(gtp,
+					 nla_get_u64(info->attrs[GTPA_TID]));
+	else if (version == GTP_V1)
+		pctx_tid = gtp1_pdp_find(gtp,
+					 nla_get_u32(info->attrs[GTPA_I_TEI]));
+	if (pctx_tid)
+		found = true;
 
 	if (found) {
 		if (info->nlhdr->nlmsg_flags & NLM_F_EXCL)
@@ -956,6 +963,11 @@ static int ipv4_pdp_add(struct gtp_dev *gtp, struct sock *sk,
 		if (info->nlhdr->nlmsg_flags & NLM_F_REPLACE)
 			return -EOPNOTSUPP;
 
+		if (pctx && pctx_tid)
+			return -EEXIST;
+		if (!pctx)
+			pctx = pctx_tid;
+
 		ipv4_pdp_fill(pctx, info);
 
 		if (pctx->gtp_version == GTP_V0)
@@ -1079,7 +1091,7 @@ static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info)
 		goto out_unlock;
 	}
 
-	err = ipv4_pdp_add(gtp, sk, info);
+	err = gtp_pdp_add(gtp, sk, info);
 
 out_unlock:
 	rcu_read_unlock();
-- 
2.20.1


From 57cb8e2881ac7cb444a73a58224b7573f2ba9dbc Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Tue, 10 Dec 2019 22:33:05 +0000
Subject: [PATCH 18/23] net: marvell: mvpp2: phylink requires the link
 interrupt

[ Upstream commit f3f2364ea14d1cf6bf966542f31eadcf178f1577 ]

phylink requires the MAC to report when its link status changes when
operating in inband modes.  Failure to report link status changes
means that phylink has no idea when the link events happen, which
results in either the network interface's carrier remaining up or
remaining permanently down.

For example, with a fiber module, if the interface is brought up and
link is initially established, taking the link down at the far end
will cut the optical power.  The SFP module's LOS asserts, we
deactivate the link, and the network interface reports no carrier.

When the far end is brought back up, the SFP module's LOS deasserts,
but the MAC may be slower to establish link.  If this happens (which
in my tests is a certainty) then phylink never hears that the MAC
has established link with the far end, and the network interface is
stuck reporting no carrier.  This means the interface is
non-functional.

Avoiding the link interrupt when we have phylink is basically not
an option, so remove the !port->phylink from the test.

Fixes: 4bb043262878 ("net: mvpp2: phylink support")
Tested-by: Sven Auhagen <sven.auhagen@voleatech.de>
Tested-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index a50977ce4076..04bee450eb3d 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -3341,7 +3341,7 @@ static int mvpp2_open(struct net_device *dev)
 		valid = true;
 	}
 
-	if (priv->hw_version == MVPP22 && port->link_irq && !port->phylink) {
+	if (priv->hw_version == MVPP22 && port->link_irq) {
 		err = request_irq(port->link_irq, mvpp2_link_status_isr, 0,
 				  dev->name, port);
 		if (err) {
-- 
2.20.1


From fc88c276ddfdf7923a6ef650f5da3cef4db776ca Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 13 Dec 2019 18:20:41 -0800
Subject: [PATCH 19/23] tcp/dccp: fix possible race __inet_lookup_established()

[ Upstream commit 8dbd76e79a16b45b2ccb01d2f2e08dbf64e71e40 ]

Michal Kubecek and Firo Yang did a very nice analysis of crashes
happening in __inet_lookup_established().

Since a TCP socket can go from TCP_ESTABLISH to TCP_LISTEN
(via a close()/socket()/listen() cycle) without a RCU grace period,
I should not have changed listeners linkage in their hash table.

They must use the nulls protocol (Documentation/RCU/rculist_nulls.txt),
so that a lookup can detect a socket in a hash list was moved in
another one.

Since we added code in commit d296ba60d8e2 ("soreuseport: Resolve
merge conflict for v4/v6 ordering fix"), we have to add
hlist_nulls_add_tail_rcu() helper.

Fixes: 3b24d854cb35 ("tcp/dccp: do not touch listener sk_refcnt under synflood")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Michal Kubecek <mkubecek@suse.cz>
Reported-by: Firo Yang <firo.yang@suse.com>
Reviewed-by: Michal Kubecek <mkubecek@suse.cz>
Link: https://lore.kernel.org/netdev/20191120083919.GH27852@unicorn.suse.cz/
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 include/linux/rculist_nulls.h | 37 +++++++++++++++++++++++++++++++++++
 include/net/inet_hashtables.h | 12 +++++++++---
 include/net/sock.h            |  5 +++++
 net/ipv4/inet_diag.c          |  3 ++-
 net/ipv4/inet_hashtables.c    | 16 +++++++--------
 net/ipv4/tcp_ipv4.c           |  7 ++++---
 6 files changed, 65 insertions(+), 15 deletions(-)

diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h
index bc8206a8f30e..61974c4c566b 100644
--- a/include/linux/rculist_nulls.h
+++ b/include/linux/rculist_nulls.h
@@ -100,6 +100,43 @@ static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n,
 		first->pprev = &n->next;
 }
 
+/**
+ * hlist_nulls_add_tail_rcu
+ * @n: the element to add to the hash list.
+ * @h: the list to add to.
+ *
+ * Description:
+ * Adds the specified element to the specified hlist_nulls,
+ * while permitting racing traversals.
+ *
+ * The caller must take whatever precautions are necessary
+ * (such as holding appropriate locks) to avoid racing
+ * with another list-mutation primitive, such as hlist_nulls_add_head_rcu()
+ * or hlist_nulls_del_rcu(), running on this same list.
+ * However, it is perfectly legal to run concurrently with
+ * the _rcu list-traversal primitives, such as
+ * hlist_nulls_for_each_entry_rcu(), used to prevent memory-consistency
+ * problems on Alpha CPUs.  Regardless of the type of CPU, the
+ * list-traversal primitive must be guarded by rcu_read_lock().
+ */
+static inline void hlist_nulls_add_tail_rcu(struct hlist_nulls_node *n,
+					    struct hlist_nulls_head *h)
+{
+	struct hlist_nulls_node *i, *last = NULL;
+
+	/* Note: write side code, so rcu accessors are not needed. */
+	for (i = h->first; !is_a_nulls(i); i = i->next)
+		last = i;
+
+	if (last) {
+		n->next = last->next;
+		n->pprev = &last->next;
+		rcu_assign_pointer(hlist_next_rcu(last), n);
+	} else {
+		hlist_nulls_add_head_rcu(n, h);
+	}
+}
+
 /**
  * hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type
  * @tpos:	the type * to use as a loop cursor.
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 9141e95529e7..b875dcef173c 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -106,13 +106,19 @@ struct inet_bind_hashbucket {
 	struct hlist_head	chain;
 };
 
-/*
- * Sockets can be hashed in established or listening table
+/* Sockets can be hashed in established or listening table.
+ * We must use different 'nulls' end-of-chain value for all hash buckets :
+ * A socket might transition from ESTABLISH to LISTEN state without
+ * RCU grace period. A lookup in ehash table needs to handle this case.
  */
+#define LISTENING_NULLS_BASE (1U << 29)
 struct inet_listen_hashbucket {
 	spinlock_t		lock;
 	unsigned int		count;
-	struct hlist_head	head;
+	union {
+		struct hlist_head	head;
+		struct hlist_nulls_head	nulls_head;
+	};
 };
 
 /* This is for listening sockets, thus all sockets which possess wildcards. */
diff --git a/include/net/sock.h b/include/net/sock.h
index 4545a9ecc219..f359e5c94762 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -721,6 +721,11 @@ static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_h
 	hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list);
 }
 
+static inline void __sk_nulls_add_node_tail_rcu(struct sock *sk, struct hlist_nulls_head *list)
+{
+	hlist_nulls_add_tail_rcu(&sk->sk_nulls_node, list);
+}
+
 static inline void sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
 {
 	sock_hold(sk);
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 5731670c560b..9742b37afe1d 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -918,11 +918,12 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb,
 
 		for (i = s_i; i < INET_LHTABLE_SIZE; i++) {
 			struct inet_listen_hashbucket *ilb;
+			struct hlist_nulls_node *node;
 
 			num = 0;
 			ilb = &hashinfo->listening_hash[i];
 			spin_lock(&ilb->lock);
-			sk_for_each(sk, &ilb->head) {
+			sk_nulls_for_each(sk, node, &ilb->nulls_head) {
 				struct inet_sock *inet = inet_sk(sk);
 
 				if (!net_eq(sock_net(sk), net))
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 7be966a60801..900756b3defb 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -560,10 +560,11 @@ static int inet_reuseport_add_sock(struct sock *sk,
 				   struct inet_listen_hashbucket *ilb)
 {
 	struct inet_bind_bucket *tb = inet_csk(sk)->icsk_bind_hash;
+	const struct hlist_nulls_node *node;
 	struct sock *sk2;
 	kuid_t uid = sock_i_uid(sk);
 
-	sk_for_each_rcu(sk2, &ilb->head) {
+	sk_nulls_for_each_rcu(sk2, node, &ilb->nulls_head) {
 		if (sk2 != sk &&
 		    sk2->sk_family == sk->sk_family &&
 		    ipv6_only_sock(sk2) == ipv6_only_sock(sk) &&
@@ -599,9 +600,9 @@ int __inet_hash(struct sock *sk, struct sock *osk)
 	}
 	if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport &&
 		sk->sk_family == AF_INET6)
-		hlist_add_tail_rcu(&sk->sk_node, &ilb->head);
+		__sk_nulls_add_node_tail_rcu(sk, &ilb->nulls_head);
 	else
-		hlist_add_head_rcu(&sk->sk_node, &ilb->head);
+		__sk_nulls_add_node_rcu(sk, &ilb->nulls_head);
 	inet_hash2(hashinfo, sk);
 	ilb->count++;
 	sock_set_flag(sk, SOCK_RCU_FREE);
@@ -650,11 +651,9 @@ void inet_unhash(struct sock *sk)
 		reuseport_detach_sock(sk);
 	if (ilb) {
 		inet_unhash2(hashinfo, sk);
-		 __sk_del_node_init(sk);
-		 ilb->count--;
-	} else {
-		__sk_nulls_del_node_init_rcu(sk);
+		ilb->count--;
 	}
+	__sk_nulls_del_node_init_rcu(sk);
 	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
 unlock:
 	spin_unlock_bh(lock);
@@ -790,7 +789,8 @@ void inet_hashinfo_init(struct inet_hashinfo *h)
 
 	for (i = 0; i < INET_LHTABLE_SIZE; i++) {
 		spin_lock_init(&h->listening_hash[i].lock);
-		INIT_HLIST_HEAD(&h->listening_hash[i].head);
+		INIT_HLIST_NULLS_HEAD(&h->listening_hash[i].nulls_head,
+				      i + LISTENING_NULLS_BASE);
 		h->listening_hash[i].count = 0;
 	}
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index bfec48849735..5553f6a833f3 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2020,13 +2020,14 @@ static void *listening_get_next(struct seq_file *seq, void *cur)
 	struct tcp_iter_state *st = seq->private;
 	struct net *net = seq_file_net(seq);
 	struct inet_listen_hashbucket *ilb;
+	struct hlist_nulls_node *node;
 	struct sock *sk = cur;
 
 	if (!sk) {
 get_head:
 		ilb = &tcp_hashinfo.listening_hash[st->bucket];
 		spin_lock(&ilb->lock);
-		sk = sk_head(&ilb->head);
+		sk = sk_nulls_head(&ilb->nulls_head);
 		st->offset = 0;
 		goto get_sk;
 	}
@@ -2034,9 +2035,9 @@ static void *listening_get_next(struct seq_file *seq, void *cur)
 	++st->num;
 	++st->offset;
 
-	sk = sk_next(sk);
+	sk = sk_nulls_next(sk);
 get_sk:
-	sk_for_each_from(sk) {
+	sk_nulls_for_each_from(sk, node) {
 		if (!net_eq(sock_net(sk), net))
 			continue;
 		if (sk->sk_family == afinfo->family)
-- 
2.20.1


From b9cee4f926c1b6101a4ca0e8206f92c845ad73e0 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 12 Dec 2019 12:55:29 -0800
Subject: [PATCH 20/23] tcp: do not send empty skb from tcp_write_xmit()

[ Upstream commit 1f85e6267caca44b30c54711652b0726fadbb131 ]

Backport of commit fdfc5c8594c2 ("tcp: remove empty skb from
write queue in error cases") in linux-4.14 stable triggered
various bugs. One of them has been fixed in commit ba2ddb43f270
("tcp: Don't dequeue SYN/FIN-segments from write-queue"), but
we still have crashes in some occasions.

Root-cause is that when tcp_sendmsg() has allocated a fresh
skb and could not append a fragment before being blocked
in sk_stream_wait_memory(), tcp_write_xmit() might be called
and decide to send this fresh and empty skb.

Sending an empty packet is not only silly, it might have caused
many issues we had in the past with tp->packets_out being
out of sync.

Fixes: c65f7f00c587 ("[TCP]: Simplify SKB data portion allocation with NETIF_F_SG.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Christoph Paasch <cpaasch@apple.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Cc: Jason Baron <jbaron@akamai.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/ipv4/tcp_output.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index e3ce1f56f845..1cc20edf4762 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2376,6 +2376,14 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 		if (tcp_small_queue_check(sk, skb, 0))
 			break;
 
+		/* Argh, we hit an empty skb(), presumably a thread
+		 * is sleeping in sendmsg()/sk_stream_wait_memory().
+		 * We do not want to send a pure-ack packet and have
+		 * a strange looking rtx queue with empty packet(s).
+		 */
+		if (TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq)
+			break;
+
 		if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp)))
 			break;
 
-- 
2.20.1


From 2c87784120add794b5da3d2207de4fe99a6d8ef7 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Wed, 11 Dec 2019 08:23:17 +0000
Subject: [PATCH 21/23] gtp: fix wrong condition in gtp_genl_dump_pdp()

[ Upstream commit 94a6d9fb88df43f92d943c32b84ce398d50bf49f ]

gtp_genl_dump_pdp() is ->dumpit() callback of GTP module and it is used
to dump pdp contexts. it would be re-executed because of dump packet size.

If dump packet size is too big, it saves current dump pointer
(gtp interface pointer, bucket, TID value) then it restarts dump from
last pointer.
Current GTP code allows adding zero TID pdp context but dump code
ignores zero TID value. So, last dump pointer will not be found.

In addition, this patch adds missing rcu_read_lock() in
gtp_genl_dump_pdp().

Fixes: 459aa660eb1d ("gtp: add initial driver for datapath of GPRS Tunneling Protocol (GTP-U)")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/gtp.c | 36 +++++++++++++++++++-----------------
 1 file changed, 19 insertions(+), 17 deletions(-)

diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 5a50f8842b5a..502df75bb916 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -42,7 +42,6 @@ struct pdp_ctx {
 	struct hlist_node	hlist_addr;
 
 	union {
-		u64		tid;
 		struct {
 			u64	tid;
 			u16	flow;
@@ -1249,43 +1248,46 @@ static int gtp_genl_dump_pdp(struct sk_buff *skb,
 				struct netlink_callback *cb)
 {
 	struct gtp_dev *last_gtp = (struct gtp_dev *)cb->args[2], *gtp;
+	int i, j, bucket = cb->args[0], skip = cb->args[1];
 	struct net *net = sock_net(skb->sk);
-	struct gtp_net *gn = net_generic(net, gtp_net_id);
-	unsigned long tid = cb->args[1];
-	int i, k = cb->args[0], ret;
 	struct pdp_ctx *pctx;
+	struct gtp_net *gn;
+
+	gn = net_generic(net, gtp_net_id);
 
 	if (cb->args[4])
 		return 0;
 
+	rcu_read_lock();
 	list_for_each_entry_rcu(gtp, &gn->gtp_dev_list, list) {
 		if (last_gtp && last_gtp != gtp)
 			continue;
 		else
 			last_gtp = NULL;
 
-		for (i = k; i < gtp->hash_size; i++) {
-			hlist_for_each_entry_rcu(pctx, &gtp->tid_hash[i], hlist_tid) {
-				if (tid && tid != pctx->u.tid)
-					continue;
-				else
-					tid = 0;
-
-				ret = gtp_genl_fill_info(skb,
-							 NETLINK_CB(cb->skb).portid,
-							 cb->nlh->nlmsg_seq,
-							 cb->nlh->nlmsg_type, pctx);
-				if (ret < 0) {
+		for (i = bucket; i < gtp->hash_size; i++) {
+			j = 0;
+			hlist_for_each_entry_rcu(pctx, &gtp->tid_hash[i],
+						 hlist_tid) {
+				if (j >= skip &&
+				    gtp_genl_fill_info(skb,
+					    NETLINK_CB(cb->skb).portid,
+					    cb->nlh->nlmsg_seq,
+					    cb->nlh->nlmsg_type, pctx)) {
 					cb->args[0] = i;
-					cb->args[1] = pctx->u.tid;
+					cb->args[1] = j;
 					cb->args[2] = (unsigned long)gtp;
 					goto out;
 				}
+				j++;
 			}
+			skip = 0;
 		}
+		bucket = 0;
 	}
 	cb->args[4] = 1;
 out:
+	rcu_read_unlock();
 	return skb->len;
 }
 
-- 
2.20.1


From 7f9515920026f35991eb65de47d524ad5dce74dc Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Wed, 11 Dec 2019 08:23:34 +0000
Subject: [PATCH 22/23] gtp: fix an use-after-free in ipv4_pdp_find()

[ Upstream commit 94dc550a5062030569d4aa76e10e50c8fc001930 ]

ipv4_pdp_find() is called in TX packet path of GTP.
ipv4_pdp_find() internally uses gtp->tid_hash to lookup pdp context.
In the current code, gtp->tid_hash and gtp->addr_hash are freed by
->dellink(), which is gtp_dellink().
But gtp_dellink() would be called while packets are processing.
So, gtp_dellink() should not free gtp->tid_hash and gtp->addr_hash.
Instead, dev->priv_destructor() would be used because this callback
is called after all packet processing safely.

Test commands:
    ip link add veth1 type veth peer name veth2
    ip a a 172.0.0.1/24 dev veth1
    ip link set veth1 up
    ip a a 172.99.0.1/32 dev lo

    gtp-link add gtp1 &

    gtp-tunnel add gtp1 v1 200 100 172.99.0.2 172.0.0.2
    ip r a  172.99.0.2/32 dev gtp1
    ip link set gtp1 mtu 1500

    ip netns add ns2
    ip link set veth2 netns ns2
    ip netns exec ns2 ip a a 172.0.0.2/24 dev veth2
    ip netns exec ns2 ip link set veth2 up
    ip netns exec ns2 ip a a 172.99.0.2/32 dev lo
    ip netns exec ns2 ip link set lo up

    ip netns exec ns2 gtp-link add gtp2 &
    ip netns exec ns2 gtp-tunnel add gtp2 v1 100 200 172.99.0.1 172.0.0.1
    ip netns exec ns2 ip r a 172.99.0.1/32 dev gtp2
    ip netns exec ns2 ip link set gtp2 mtu 1500

    hping3 172.99.0.2 -2 --flood &
    ip link del gtp1

Splat looks like:
[   72.568081][ T1195] BUG: KASAN: use-after-free in ipv4_pdp_find.isra.12+0x130/0x170 [gtp]
[   72.568916][ T1195] Read of size 8 at addr ffff8880b9a35d28 by task hping3/1195
[   72.569631][ T1195]
[   72.569861][ T1195] CPU: 2 PID: 1195 Comm: hping3 Not tainted 5.5.0-rc1 #199
[   72.570547][ T1195] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[   72.571438][ T1195] Call Trace:
[   72.571764][ T1195]  dump_stack+0x96/0xdb
[   72.572171][ T1195]  ? ipv4_pdp_find.isra.12+0x130/0x170 [gtp]
[   72.572761][ T1195]  print_address_description.constprop.5+0x1be/0x360
[   72.573400][ T1195]  ? ipv4_pdp_find.isra.12+0x130/0x170 [gtp]
[   72.573971][ T1195]  ? ipv4_pdp_find.isra.12+0x130/0x170 [gtp]
[   72.574544][ T1195]  __kasan_report+0x12a/0x16f
[   72.575014][ T1195]  ? ipv4_pdp_find.isra.12+0x130/0x170 [gtp]
[   72.575593][ T1195]  kasan_report+0xe/0x20
[   72.576004][ T1195]  ipv4_pdp_find.isra.12+0x130/0x170 [gtp]
[   72.576577][ T1195]  gtp_build_skb_ip4+0x199/0x1420 [gtp]
[ ... ]
[   72.647671][ T1195] BUG: unable to handle page fault for address: ffff8880b9a35d28
[   72.648512][ T1195] #PF: supervisor read access in kernel mode
[   72.649158][ T1195] #PF: error_code(0x0000) - not-present page
[   72.649849][ T1195] PGD a6c01067 P4D a6c01067 PUD 11fb07067 PMD 11f939067 PTE 800fffff465ca060
[   72.652958][ T1195] Oops: 0000 [#1] SMP DEBUG_PAGEALLOC KASAN PTI
[   72.653834][ T1195] CPU: 2 PID: 1195 Comm: hping3 Tainted: G    B             5.5.0-rc1 #199
[   72.668062][ T1195] RIP: 0010:ipv4_pdp_find.isra.12+0x86/0x170 [gtp]
[ ... ]
[   72.679168][ T1195] Call Trace:
[   72.679603][ T1195]  gtp_build_skb_ip4+0x199/0x1420 [gtp]
[   72.681915][ T1195]  ? ipv4_pdp_find.isra.12+0x170/0x170 [gtp]
[   72.682513][ T1195]  ? lock_acquire+0x164/0x3b0
[   72.682966][ T1195]  ? gtp_dev_xmit+0x35e/0x890 [gtp]
[   72.683481][ T1195]  gtp_dev_xmit+0x3c2/0x890 [gtp]
[ ... ]

Fixes: 459aa660eb1d ("gtp: add initial driver for datapath of GPRS Tunneling Protocol (GTP-U)")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/gtp.c | 34 +++++++++++++++++-----------------
 1 file changed, 17 insertions(+), 17 deletions(-)

diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 502df75bb916..8c32abad162f 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -644,9 +644,16 @@ static void gtp_link_setup(struct net_device *dev)
 }
 
 static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize);
-static void gtp_hashtable_free(struct gtp_dev *gtp);
 static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[]);
 
+static void gtp_destructor(struct net_device *dev)
+{
+	struct gtp_dev *gtp = netdev_priv(dev);
+
+	kfree(gtp->addr_hash);
+	kfree(gtp->tid_hash);
+}
+
 static int gtp_newlink(struct net *src_net, struct net_device *dev,
 		       struct nlattr *tb[], struct nlattr *data[],
 		       struct netlink_ext_ack *extack)
@@ -681,13 +688,15 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev,
 
 	gn = net_generic(dev_net(dev), gtp_net_id);
 	list_add_rcu(&gtp->list, &gn->gtp_dev_list);
+	dev->priv_destructor = gtp_destructor;
 
 	netdev_dbg(dev, "registered new GTP interface\n");
 
 	return 0;
 
 out_hashtable:
-	gtp_hashtable_free(gtp);
+	kfree(gtp->addr_hash);
+	kfree(gtp->tid_hash);
 out_encap:
 	gtp_encap_disable(gtp);
 	return err;
@@ -696,9 +705,14 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev,
 static void gtp_dellink(struct net_device *dev, struct list_head *head)
 {
 	struct gtp_dev *gtp = netdev_priv(dev);
+	struct pdp_ctx *pctx;
+	int i;
+
+	for (i = 0; i < gtp->hash_size; i++)
+		hlist_for_each_entry_rcu(pctx, &gtp->tid_hash[i], hlist_tid)
+			pdp_context_delete(pctx);
 
 	gtp_encap_disable(gtp);
-	gtp_hashtable_free(gtp);
 	list_del_rcu(&gtp->list);
 	unregister_netdevice_queue(dev, head);
 }
@@ -776,20 +790,6 @@ static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize)
 	return -ENOMEM;
 }
 
-static void gtp_hashtable_free(struct gtp_dev *gtp)
-{
-	struct pdp_ctx *pctx;
-	int i;
-
-	for (i = 0; i < gtp->hash_size; i++)
-		hlist_for_each_entry_rcu(pctx, &gtp->tid_hash[i], hlist_tid)
-			pdp_context_delete(pctx);
-
-	synchronize_rcu();
-	kfree(gtp->addr_hash);
-	kfree(gtp->tid_hash);
-}
-
 static struct sock *gtp_encap_enable_socket(int fd, int type,
 					    struct gtp_dev *gtp)
 {
-- 
2.20.1


From eac3bbeba3988b72cfda063ecba621029151a9f3 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Wed, 11 Dec 2019 08:23:48 +0000
Subject: [PATCH 23/23] gtp: avoid zero size hashtable

[ Upstream commit 6a902c0f31993ab02e1b6ea7085002b9c9083b6a ]

GTP default hashtable size is 1024 and userspace could set specific
hashtable size with IFLA_GTP_PDP_HASHSIZE. If hashtable size is set to 0
from userspace,  hashtable will not work and panic will occur.

Fixes: 459aa660eb1d ("gtp: add initial driver for datapath of GPRS Tunneling Protocol (GTP-U)")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/gtp.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 8c32abad162f..494f00b9c5ef 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -671,10 +671,13 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev,
 	if (err < 0)
 		return err;
 
-	if (!data[IFLA_GTP_PDP_HASHSIZE])
+	if (!data[IFLA_GTP_PDP_HASHSIZE]) {
 		hashsize = 1024;
-	else
+	} else {
 		hashsize = nla_get_u32(data[IFLA_GTP_PDP_HASHSIZE]);
+		if (!hashsize)
+			hashsize = 1024;
+	}
 
 	err = gtp_hashtable_new(gtp, hashsize);
 	if (err < 0)
-- 
2.20.1


[-- Attachment #3: net_54.mbox --]
[-- Type: Application/Octet-Stream, Size: 160591 bytes --]

From 585008517f68d731ff3a811a00328fe3cbe0578e Mon Sep 17 00:00:00 2001
From: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Date: Mon, 30 Dec 2019 18:14:08 +0530
Subject: [PATCH 01/46] cxgb4/cxgb4vf: fix flow control display for auto
 negotiation

[ Upstream commit 0caeaf6ad532f9be5a768a158627cb31921cc8b7 ]

As per 802.3-2005, Section Two, Annex 28B, Table 28B-2 [1], when
_only_ Rx pause is enabled, both symmetric and asymmetric pause
towards local device must be enabled. Also, firmware returns the local
device's flow control pause params as part of advertised capabilities
and negotiated params as part of current link attributes. So, fix up
ethtool's flow control pause params fetch logic to read from acaps,
instead of linkattr.

[1] https://standards.ieee.org/standard/802_3-2005.html

Fixes: c3168cabe1af ("cxgb4/cxgbvf: Handle 32-bit fw port capabilities")
Signed-off-by: Surendra Mobiya <surendra@chelsio.com>
Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4.h    |  1 +
 .../ethernet/chelsio/cxgb4/cxgb4_ethtool.c    |  4 ++--
 drivers/net/ethernet/chelsio/cxgb4/t4_hw.c    | 21 ++++++++++++-------
 .../ethernet/chelsio/cxgb4vf/cxgb4vf_main.c   |  4 ++--
 .../ethernet/chelsio/cxgb4vf/t4vf_common.h    |  1 +
 .../net/ethernet/chelsio/cxgb4vf/t4vf_hw.c    | 18 +++++++++-------
 6 files changed, 30 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index 1fbb640e896a..4025a683fa7d 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -503,6 +503,7 @@ struct link_config {
 
 	enum cc_pause  requested_fc;     /* flow control user has requested */
 	enum cc_pause  fc;               /* actual link flow control */
+	enum cc_pause  advertised_fc;    /* actual advertised flow control */
 
 	enum cc_fec    requested_fec;	 /* Forward Error Correction: */
 	enum cc_fec    fec;		 /* requested and actual in use */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
index 76538f4cd595..f537be9cb315 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
@@ -793,8 +793,8 @@ static void get_pauseparam(struct net_device *dev,
 	struct port_info *p = netdev_priv(dev);
 
 	epause->autoneg = (p->link_cfg.requested_fc & PAUSE_AUTONEG) != 0;
-	epause->rx_pause = (p->link_cfg.fc & PAUSE_RX) != 0;
-	epause->tx_pause = (p->link_cfg.fc & PAUSE_TX) != 0;
+	epause->rx_pause = (p->link_cfg.advertised_fc & PAUSE_RX) != 0;
+	epause->tx_pause = (p->link_cfg.advertised_fc & PAUSE_TX) != 0;
 }
 
 static int set_pauseparam(struct net_device *dev,
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index f2a7824da42b..3f6813daf3c1 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -4089,7 +4089,8 @@ static inline fw_port_cap32_t cc_to_fwcap_pause(enum cc_pause cc_pause)
 		if (cc_pause & PAUSE_TX)
 			fw_pause |= FW_PORT_CAP32_802_3_PAUSE;
 		else
-			fw_pause |= FW_PORT_CAP32_802_3_ASM_DIR;
+			fw_pause |= FW_PORT_CAP32_802_3_ASM_DIR |
+				    FW_PORT_CAP32_802_3_PAUSE;
 	} else if (cc_pause & PAUSE_TX) {
 		fw_pause |= FW_PORT_CAP32_802_3_ASM_DIR;
 	}
@@ -8563,17 +8564,17 @@ static fw_port_cap32_t lstatus_to_fwcap(u32 lstatus)
 void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl)
 {
 	const struct fw_port_cmd *cmd = (const void *)rpl;
-	int action = FW_PORT_CMD_ACTION_G(be32_to_cpu(cmd->action_to_len16));
-	struct adapter *adapter = pi->adapter;
+	fw_port_cap32_t pcaps, acaps, lpacaps, linkattr;
 	struct link_config *lc = &pi->link_cfg;
-	int link_ok, linkdnrc;
-	enum fw_port_type port_type;
+	struct adapter *adapter = pi->adapter;
+	unsigned int speed, fc, fec, adv_fc;
 	enum fw_port_module_type mod_type;
-	unsigned int speed, fc, fec;
-	fw_port_cap32_t pcaps, acaps, lpacaps, linkattr;
+	int action, link_ok, linkdnrc;
+	enum fw_port_type port_type;
 
 	/* Extract the various fields from the Port Information message.
 	 */
+	action = FW_PORT_CMD_ACTION_G(be32_to_cpu(cmd->action_to_len16));
 	switch (action) {
 	case FW_PORT_ACTION_GET_PORT_INFO: {
 		u32 lstatus = be32_to_cpu(cmd->u.info.lstatus_to_modtype);
@@ -8611,6 +8612,7 @@ void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl)
 	}
 
 	fec = fwcap_to_cc_fec(acaps);
+	adv_fc = fwcap_to_cc_pause(acaps);
 	fc = fwcap_to_cc_pause(linkattr);
 	speed = fwcap_to_speed(linkattr);
 
@@ -8667,7 +8669,9 @@ void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl)
 	}
 
 	if (link_ok != lc->link_ok || speed != lc->speed ||
-	    fc != lc->fc || fec != lc->fec) {	/* something changed */
+	    fc != lc->fc || adv_fc != lc->advertised_fc ||
+	    fec != lc->fec) {
+		/* something changed */
 		if (!link_ok && lc->link_ok) {
 			lc->link_down_rc = linkdnrc;
 			dev_warn_ratelimited(adapter->pdev_dev,
@@ -8677,6 +8681,7 @@ void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl)
 		}
 		lc->link_ok = link_ok;
 		lc->speed = speed;
+		lc->advertised_fc = adv_fc;
 		lc->fc = fc;
 		lc->fec = fec;
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
index f6fc0875d5b0..f4d41f968afa 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
@@ -1690,8 +1690,8 @@ static void cxgb4vf_get_pauseparam(struct net_device *dev,
 	struct port_info *pi = netdev_priv(dev);
 
 	pauseparam->autoneg = (pi->link_cfg.requested_fc & PAUSE_AUTONEG) != 0;
-	pauseparam->rx_pause = (pi->link_cfg.fc & PAUSE_RX) != 0;
-	pauseparam->tx_pause = (pi->link_cfg.fc & PAUSE_TX) != 0;
+	pauseparam->rx_pause = (pi->link_cfg.advertised_fc & PAUSE_RX) != 0;
+	pauseparam->tx_pause = (pi->link_cfg.advertised_fc & PAUSE_TX) != 0;
 }
 
 /*
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h
index ccca67cf4487..57cfd10a99ec 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h
@@ -135,6 +135,7 @@ struct link_config {
 
 	enum cc_pause	requested_fc;	/* flow control user has requested */
 	enum cc_pause	fc;		/* actual link flow control */
+	enum cc_pause   advertised_fc;  /* actual advertised flow control */
 
 	enum cc_fec	auto_fec;	/* Forward Error Correction: */
 	enum cc_fec	requested_fec;	/*   "automatic" (IEEE 802.3), */
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
index 8a389d617a23..9d49ff211cc1 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
@@ -1913,16 +1913,16 @@ static const char *t4vf_link_down_rc_str(unsigned char link_down_rc)
 static void t4vf_handle_get_port_info(struct port_info *pi,
 				      const struct fw_port_cmd *cmd)
 {
-	int action = FW_PORT_CMD_ACTION_G(be32_to_cpu(cmd->action_to_len16));
-	struct adapter *adapter = pi->adapter;
+	fw_port_cap32_t pcaps, acaps, lpacaps, linkattr;
 	struct link_config *lc = &pi->link_cfg;
-	int link_ok, linkdnrc;
-	enum fw_port_type port_type;
+	struct adapter *adapter = pi->adapter;
+	unsigned int speed, fc, fec, adv_fc;
 	enum fw_port_module_type mod_type;
-	unsigned int speed, fc, fec;
-	fw_port_cap32_t pcaps, acaps, lpacaps, linkattr;
+	int action, link_ok, linkdnrc;
+	enum fw_port_type port_type;
 
 	/* Extract the various fields from the Port Information message. */
+	action = FW_PORT_CMD_ACTION_G(be32_to_cpu(cmd->action_to_len16));
 	switch (action) {
 	case FW_PORT_ACTION_GET_PORT_INFO: {
 		u32 lstatus = be32_to_cpu(cmd->u.info.lstatus_to_modtype);
@@ -1982,6 +1982,7 @@ static void t4vf_handle_get_port_info(struct port_info *pi,
 	}
 
 	fec = fwcap_to_cc_fec(acaps);
+	adv_fc = fwcap_to_cc_pause(acaps);
 	fc = fwcap_to_cc_pause(linkattr);
 	speed = fwcap_to_speed(linkattr);
 
@@ -2012,7 +2013,9 @@ static void t4vf_handle_get_port_info(struct port_info *pi,
 	}
 
 	if (link_ok != lc->link_ok || speed != lc->speed ||
-	    fc != lc->fc || fec != lc->fec) {	/* something changed */
+	    fc != lc->fc || adv_fc != lc->advertised_fc ||
+	    fec != lc->fec) {
+		/* something changed */
 		if (!link_ok && lc->link_ok) {
 			lc->link_down_rc = linkdnrc;
 			dev_warn_ratelimited(adapter->pdev_dev,
@@ -2022,6 +2025,7 @@ static void t4vf_handle_get_port_info(struct port_info *pi,
 		}
 		lc->link_ok = link_ok;
 		lc->speed = speed;
+		lc->advertised_fc = adv_fc;
 		lc->fc = fc;
 		lc->fec = fec;
 
-- 
2.20.1


From 12db9259e104374c74adb1278b57e8eef4f288fe Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 20 Dec 2019 11:24:21 -0800
Subject: [PATCH 02/46] net: dsa: bcm_sf2: Fix IP fragment location and
 behavior

[ Upstream commit 7c3125f0a6ebc17846c5908ad7d6056d66c1c426 ]

The IP fragment is specified through user-defined field as the first
bit of the first user-defined word. We were previously trying to extract
it from the user-defined mask which could not possibly work. The ip_frag
is also supposed to be a boolean, if we do not cast it as such, we risk
overwriting the next fields in CFP_DATA(6) which would render the rule
inoperative.

Fixes: 7318166cacad ("net: dsa: bcm_sf2: Add support for ethtool::rxnfc")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2_cfp.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c
index d264776a95a3..471837cf0b21 100644
--- a/drivers/net/dsa/bcm_sf2_cfp.c
+++ b/drivers/net/dsa/bcm_sf2_cfp.c
@@ -358,7 +358,7 @@ static int bcm_sf2_cfp_ipv4_rule_set(struct bcm_sf2_priv *priv, int port,
 		return -EINVAL;
 	}
 
-	ip_frag = be32_to_cpu(fs->m_ext.data[0]);
+	ip_frag = !!(be32_to_cpu(fs->h_ext.data[0]) & 1);
 
 	/* Locate the first rule available */
 	if (fs->location == RX_CLS_LOC_ANY)
@@ -569,7 +569,7 @@ static int bcm_sf2_cfp_rule_cmp(struct bcm_sf2_priv *priv, int port,
 
 		if (rule->fs.flow_type != fs->flow_type ||
 		    rule->fs.ring_cookie != fs->ring_cookie ||
-		    rule->fs.m_ext.data[0] != fs->m_ext.data[0])
+		    rule->fs.h_ext.data[0] != fs->h_ext.data[0])
 			continue;
 
 		switch (fs->flow_type & ~FLOW_EXT) {
@@ -621,7 +621,7 @@ static int bcm_sf2_cfp_ipv6_rule_set(struct bcm_sf2_priv *priv, int port,
 		return -EINVAL;
 	}
 
-	ip_frag = be32_to_cpu(fs->m_ext.data[0]);
+	ip_frag = !!(be32_to_cpu(fs->h_ext.data[0]) & 1);
 
 	layout = &udf_tcpip6_layout;
 	slice_num = bcm_sf2_get_slice_number(layout, 0);
-- 
2.20.1


From 6cb31129062c490f09b305c417ceb78bf5d51749 Mon Sep 17 00:00:00 2001
From: Vladyslav Tarasiuk <vladyslavt@mellanox.com>
Date: Thu, 26 Dec 2019 10:41:56 +0200
Subject: [PATCH 03/46] net/mlxfw: Fix out-of-memory error in mfa2 flash
 burning

[ Upstream commit a5bcd72e054aabb93ddc51ed8cde36a5bfc50271 ]

The burning process requires to perform internal allocations of large
chunks of memory. This memory doesn't need to be contiguous and can be
safely allocated by vzalloc() instead of kzalloc(). This patch changes
such allocation to avoid possible out-of-memory failure.

Fixes: 410ed13cae39 ("Add the mlxfw module for Mellanox firmware flash process")
Signed-off-by: Vladyslav Tarasiuk <vladyslavt@mellanox.com>
Reviewed-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Tested-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.c b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.c
index 544344ac4894..79057af4fe99 100644
--- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.c
+++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.c
@@ -6,6 +6,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/netlink.h>
+#include <linux/vmalloc.h>
 #include <linux/xz.h>
 #include "mlxfw_mfa2.h"
 #include "mlxfw_mfa2_file.h"
@@ -548,7 +549,7 @@ mlxfw_mfa2_file_component_get(const struct mlxfw_mfa2_file *mfa2_file,
 	comp_size = be32_to_cpu(comp->size);
 	comp_buf_size = comp_size + mlxfw_mfa2_comp_magic_len;
 
-	comp_data = kmalloc(sizeof(*comp_data) + comp_buf_size, GFP_KERNEL);
+	comp_data = vzalloc(sizeof(*comp_data) + comp_buf_size);
 	if (!comp_data)
 		return ERR_PTR(-ENOMEM);
 	comp_data->comp.data_size = comp_size;
@@ -570,7 +571,7 @@ mlxfw_mfa2_file_component_get(const struct mlxfw_mfa2_file *mfa2_file,
 	comp_data->comp.data = comp_data->buff + mlxfw_mfa2_comp_magic_len;
 	return &comp_data->comp;
 err_out:
-	kfree(comp_data);
+	vfree(comp_data);
 	return ERR_PTR(err);
 }
 
@@ -579,7 +580,7 @@ void mlxfw_mfa2_file_component_put(struct mlxfw_mfa2_component *comp)
 	const struct mlxfw_mfa2_comp_data *comp_data;
 
 	comp_data = container_of(comp, struct mlxfw_mfa2_comp_data, comp);
-	kfree(comp_data);
+	vfree(comp_data);
 }
 
 void mlxfw_mfa2_file_fini(struct mlxfw_mfa2_file *mfa2_file)
-- 
2.20.1


From 374e72bd556901ee928df14c49434626020c9e5f Mon Sep 17 00:00:00 2001
From: Madalin Bucur <madalin.bucur@oss.nxp.com>
Date: Mon, 23 Dec 2019 10:06:10 +0200
Subject: [PATCH 04/46] net: phy: aquantia: add suspend / resume ops for AQR105

[ Upstream commit 1c93fb45761e79b3c00080e71523886cefaf351c ]

The suspend/resume code for AQR107 works on AQR105 too.
This patch fixes issues with the partner not seeing the link down
when the interface using AQR105 is brought down.

Fixes: bee8259dd31f ("net: phy: add driver for aquantia phy")
Signed-off-by: Madalin Bucur <madalin.bucur@oss.nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/aquantia_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/phy/aquantia_main.c b/drivers/net/phy/aquantia_main.c
index 3b29d381116f..975789d9349d 100644
--- a/drivers/net/phy/aquantia_main.c
+++ b/drivers/net/phy/aquantia_main.c
@@ -627,6 +627,8 @@ static struct phy_driver aqr_driver[] = {
 	.config_intr	= aqr_config_intr,
 	.ack_interrupt	= aqr_ack_interrupt,
 	.read_status	= aqr_read_status,
+	.suspend	= aqr107_suspend,
+	.resume		= aqr107_resume,
 },
 {
 	PHY_ID_MATCH_MODEL(PHY_ID_AQR106),
-- 
2.20.1


From b30593349bb0361ddccc18546e892067a81f8670 Mon Sep 17 00:00:00 2001
From: Shmulik Ladkani <sladkani@proofpoint.com>
Date: Wed, 25 Dec 2019 10:51:01 +0200
Subject: [PATCH 05/46] net/sched: act_mirred: Pull mac prior redir to non
 mac_header_xmit device

[ Upstream commit 70cf3dc7313207816255b9acb0dffb19dae78144 ]

There's no skb_pull performed when a mirred action is set at egress of a
mac device, with a target device/action that expects skb->data to point
at the network header.

As a result, either the target device is errornously given an skb with
data pointing to the mac (egress case), or the net stack receives the
skb with data pointing to the mac (ingress case).

E.g:
 # tc qdisc add dev eth9 root handle 1: prio
 # tc filter add dev eth9 parent 1: prio 9 protocol ip handle 9 basic \
   action mirred egress redirect dev tun0

 (tun0 is a tun device. result: tun0 errornously gets the eth header
  instead of the iph)

Revise the push/pull logic of tcf_mirred_act() to not rely on the
skb_at_tc_ingress() vs tcf_mirred_act_wants_ingress() comparison, as it
does not cover all "pull" cases.

Instead, calculate whether the required action on the target device
requires the data to point at the network header, and compare this to
whether skb->data points to network header - and make the push/pull
adjustments as necessary.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Shmulik Ladkani <sladkani@proofpoint.com>
Tested-by: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_mirred.c | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 08923b21e566..f0df0d90b8bd 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -219,8 +219,10 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a,
 	bool use_reinsert;
 	bool want_ingress;
 	bool is_redirect;
+	bool expects_nh;
 	int m_eaction;
 	int mac_len;
+	bool at_nh;
 
 	rec_level = __this_cpu_inc_return(mirred_rec_level);
 	if (unlikely(rec_level > MIRRED_RECURSION_LIMIT)) {
@@ -261,19 +263,19 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a,
 			goto out;
 	}
 
-	/* If action's target direction differs than filter's direction,
-	 * and devices expect a mac header on xmit, then mac push/pull is
-	 * needed.
-	 */
 	want_ingress = tcf_mirred_act_wants_ingress(m_eaction);
-	if (skb_at_tc_ingress(skb) != want_ingress && m_mac_header_xmit) {
-		if (!skb_at_tc_ingress(skb)) {
-			/* caught at egress, act ingress: pull mac */
-			mac_len = skb_network_header(skb) - skb_mac_header(skb);
+
+	expects_nh = want_ingress || !m_mac_header_xmit;
+	at_nh = skb->data == skb_network_header(skb);
+	if (at_nh != expects_nh) {
+		mac_len = skb_at_tc_ingress(skb) ? skb->mac_len :
+			  skb_network_header(skb) - skb_mac_header(skb);
+		if (expects_nh) {
+			/* target device/action expect data at nh */
 			skb_pull_rcsum(skb2, mac_len);
 		} else {
-			/* caught at ingress, act egress: push mac */
-			skb_push_rcsum(skb2, skb->mac_len);
+			/* target device/action expect data at mac */
+			skb_push_rcsum(skb2, mac_len);
 		}
 	}
 
-- 
2.20.1


From c23aec7725ff41faee2b94ab7cd3e3b96c89a047 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Sat, 28 Dec 2019 16:36:58 +0100
Subject: [PATCH 06/46] net/sched: add delete_empty() to filters and use it in
 cls_flower

[ Upstream commit a5b72a083da197b493c7ed1e5730d62d3199f7d6 ]

Revert "net/sched: cls_u32: fix refcount leak in the error path of
u32_change()", and fix the u32 refcount leak in a more generic way that
preserves the semantic of rule dumping.
On tc filters that don't support lockless insertion/removal, there is no
need to guard against concurrent insertion when a removal is in progress.
Therefore, for most of them we can avoid a full walk() when deleting, and
just decrease the refcount, like it was done on older Linux kernels.
This fixes situations where walk() was wrongly detecting a non-empty
filter, like it happened with cls_u32 in the error path of change(), thus
leading to failures in the following tdc selftests:

 6aa7: (filter, u32) Add/Replace u32 with source match and invalid indev
 6658: (filter, u32) Add/Replace u32 with custom hash table and invalid handle
 74c2: (filter, u32) Add/Replace u32 filter with invalid hash table id

On cls_flower, and on (future) lockless filters, this check is necessary:
move all the check_empty() logic in a callback so that each filter
can have its own implementation. For cls_flower, it's sufficient to check
if no IDRs have been allocated.

This reverts commit 275c44aa194b7159d1191817b20e076f55f0e620.

Changes since v1:
 - document the need for delete_empty() when TCF_PROTO_OPS_DOIT_UNLOCKED
   is used, thanks to Vlad Buslov
 - implement delete_empty() without doing fl_walk(), thanks to Vlad Buslov
 - squash revert and new fix in a single patch, to be nice with bisect
   tests that run tdc on u32 filter, thanks to Dave Miller

Fixes: 275c44aa194b ("net/sched: cls_u32: fix refcount leak in the error path of u32_change()")
Fixes: 6676d5e416ee ("net: sched: set dedicated tcf_walker flag when tp is empty")
Suggested-by: Jamal Hadi Salim <jhs@mojatatu.com>
Suggested-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Reviewed-by: Vlad Buslov <vladbu@mellanox.com>
Tested-by: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h |  5 +++++
 net/sched/cls_api.c       | 31 +++++--------------------------
 net/sched/cls_flower.c    | 12 ++++++++++++
 3 files changed, 22 insertions(+), 26 deletions(-)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index d80acda231ae..47e61956168d 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -308,6 +308,7 @@ struct tcf_proto_ops {
 	int			(*delete)(struct tcf_proto *tp, void *arg,
 					  bool *last, bool rtnl_held,
 					  struct netlink_ext_ack *);
+	bool			(*delete_empty)(struct tcf_proto *tp);
 	void			(*walk)(struct tcf_proto *tp,
 					struct tcf_walker *arg, bool rtnl_held);
 	int			(*reoffload)(struct tcf_proto *tp, bool add,
@@ -336,6 +337,10 @@ struct tcf_proto_ops {
 	int			flags;
 };
 
+/* Classifiers setting TCF_PROTO_OPS_DOIT_UNLOCKED in tcf_proto_ops->flags
+ * are expected to implement tcf_proto_ops->delete_empty(), otherwise race
+ * conditions can occur when filters are inserted/deleted simultaneously.
+ */
 enum tcf_proto_ops_flags {
 	TCF_PROTO_OPS_DOIT_UNLOCKED = 1,
 };
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 6a0eacafdb19..76e0d122616a 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -308,33 +308,12 @@ static void tcf_proto_put(struct tcf_proto *tp, bool rtnl_held,
 		tcf_proto_destroy(tp, rtnl_held, true, extack);
 }
 
-static int walker_check_empty(struct tcf_proto *tp, void *fh,
-			      struct tcf_walker *arg)
+static bool tcf_proto_check_delete(struct tcf_proto *tp)
 {
-	if (fh) {
-		arg->nonempty = true;
-		return -1;
-	}
-	return 0;
-}
-
-static bool tcf_proto_is_empty(struct tcf_proto *tp, bool rtnl_held)
-{
-	struct tcf_walker walker = { .fn = walker_check_empty, };
-
-	if (tp->ops->walk) {
-		tp->ops->walk(tp, &walker, rtnl_held);
-		return !walker.nonempty;
-	}
-	return true;
-}
+	if (tp->ops->delete_empty)
+		return tp->ops->delete_empty(tp);
 
-static bool tcf_proto_check_delete(struct tcf_proto *tp, bool rtnl_held)
-{
-	spin_lock(&tp->lock);
-	if (tcf_proto_is_empty(tp, rtnl_held))
-		tp->deleting = true;
-	spin_unlock(&tp->lock);
+	tp->deleting = true;
 	return tp->deleting;
 }
 
@@ -1751,7 +1730,7 @@ static void tcf_chain_tp_delete_empty(struct tcf_chain *chain,
 	 * concurrently.
 	 * Mark tp for deletion if it is empty.
 	 */
-	if (!tp_iter || !tcf_proto_check_delete(tp, rtnl_held)) {
+	if (!tp_iter || !tcf_proto_check_delete(tp)) {
 		mutex_unlock(&chain->filter_chain_lock);
 		return;
 	}
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 4ac110bf19c5..5cf8163710c8 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -2519,6 +2519,17 @@ static void fl_bind_class(void *fh, u32 classid, unsigned long cl)
 		f->res.class = cl;
 }
 
+static bool fl_delete_empty(struct tcf_proto *tp)
+{
+	struct cls_fl_head *head = fl_head_dereference(tp);
+
+	spin_lock(&tp->lock);
+	tp->deleting = idr_is_empty(&head->handle_idr);
+	spin_unlock(&tp->lock);
+
+	return tp->deleting;
+}
+
 static struct tcf_proto_ops cls_fl_ops __read_mostly = {
 	.kind		= "flower",
 	.classify	= fl_classify,
@@ -2528,6 +2539,7 @@ static struct tcf_proto_ops cls_fl_ops __read_mostly = {
 	.put		= fl_put,
 	.change		= fl_change,
 	.delete		= fl_delete,
+	.delete_empty	= fl_delete_empty,
 	.walk		= fl_walk,
 	.reoffload	= fl_reoffload,
 	.hw_add		= fl_hw_add,
-- 
2.20.1


From 9c9c1e7081320b3a2cfe5b181f7dec9a4f4d8ce5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 23 Dec 2019 11:13:24 -0800
Subject: [PATCH 07/46] net_sched: sch_fq: properly set sk->sk_pacing_status

[ Upstream commit bb3d0b8bf5be61ab1d6f472c43cbf34de17e796b ]

If fq_classify() recycles a struct fq_flow because
a socket structure has been reallocated, we do not
set sk->sk_pacing_status immediately, but later if the
flow becomes detached.

This means that any flow requiring pacing (BBR, or SO_MAX_PACING_RATE)
might fallback to TCP internal pacing, which requires a per-socket
high resolution timer, and therefore more cpu cycles.

Fixes: 218af599fa63 ("tcp: internal implementation for pacing")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_fq.c | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 98dd87ce1510..78ecdf146882 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -301,6 +301,9 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q)
 				     f->socket_hash != sk->sk_hash)) {
 				f->credit = q->initial_quantum;
 				f->socket_hash = sk->sk_hash;
+				if (q->rate_enable)
+					smp_store_release(&sk->sk_pacing_status,
+							  SK_PACING_FQ);
 				if (fq_flow_is_throttled(f))
 					fq_flow_unset_throttled(q, f);
 				f->time_next_packet = 0ULL;
@@ -322,8 +325,12 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q)
 
 	fq_flow_set_detached(f);
 	f->sk = sk;
-	if (skb->sk == sk)
+	if (skb->sk == sk) {
 		f->socket_hash = sk->sk_hash;
+		if (q->rate_enable)
+			smp_store_release(&sk->sk_pacing_status,
+					  SK_PACING_FQ);
+	}
 	f->credit = q->initial_quantum;
 
 	rb_link_node(&f->fq_node, parent, p);
@@ -428,17 +435,9 @@ static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	f->qlen++;
 	qdisc_qstats_backlog_inc(sch, skb);
 	if (fq_flow_is_detached(f)) {
-		struct sock *sk = skb->sk;
-
 		fq_flow_add_tail(&q->new_flows, f);
 		if (time_after(jiffies, f->age + q->flow_refill_delay))
 			f->credit = max_t(u32, f->credit, q->quantum);
-		if (sk && q->rate_enable) {
-			if (unlikely(smp_load_acquire(&sk->sk_pacing_status) !=
-				     SK_PACING_FQ))
-				smp_store_release(&sk->sk_pacing_status,
-						  SK_PACING_FQ);
-		}
 		q->inactive_flows--;
 	}
 
-- 
2.20.1


From 3eeed18ce1879d0540b1549a59aedfe24c7b66e2 Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Thu, 26 Dec 2019 20:01:01 +0100
Subject: [PATCH 08/46] net: stmmac: dwmac-meson8b: Fix the RGMII TX delay on
 Meson8b/8m2 SoCs

[ Upstream commit bd6f48546b9cb7a785344fc78058c420923d7ed8 ]

GXBB and newer SoCs use the fixed FCLK_DIV2 (1GHz) clock as input for
the m250_sel clock. Meson8b and Meson8m2 use MPLL2 instead, whose rate
can be adjusted at runtime.

So far we have been running MPLL2 with ~250MHz (and the internal
m250_div with value 1), which worked enough that we could transfer data
with an TX delay of 4ns. Unfortunately there is high packet loss with
an RGMII PHY when transferring data (receiving data works fine though).
Odroid-C1's u-boot is running with a TX delay of only 2ns as well as
the internal m250_div set to 2 - no lost (TX) packets can be observed
with that setting in u-boot.

Manual testing has shown that the TX packet loss goes away when using
the following settings in Linux (the vendor kernel uses the same
settings):
- MPLL2 clock set to ~500MHz
- m250_div set to 2
- TX delay set to 2ns on the MAC side

Update the m250_div divider settings to only accept dividers greater or
equal 2 to fix the TX delay generated by the MAC.

iperf3 results before the change:
[ ID] Interval           Transfer     Bitrate         Retr
[  5]   0.00-10.00  sec   182 MBytes   153 Mbits/sec  514      sender
[  5]   0.00-10.00  sec   182 MBytes   152 Mbits/sec           receiver

iperf3 results after the change (including an updated TX delay of 2ns):
[ ID] Interval           Transfer     Bitrate         Retr  Cwnd
[  5]   0.00-10.00  sec   927 MBytes   778 Mbits/sec    0      sender
[  5]   0.00-10.01  sec   927 MBytes   777 Mbits/sec           receiver

Fixes: 4f6a71b84e1afd ("net: stmmac: dwmac-meson8b: fix internal RGMII clock configuration")
Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/stmicro/stmmac/dwmac-meson8b.c    | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
index 306da8f6b7d5..33ce139f090f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
@@ -112,6 +112,14 @@ static int meson8b_init_rgmii_tx_clk(struct meson8b_dwmac *dwmac)
 	struct device *dev = dwmac->dev;
 	const char *parent_name, *mux_parent_names[MUX_CLK_NUM_PARENTS];
 	struct meson8b_dwmac_clk_configs *clk_configs;
+	static const struct clk_div_table div_table[] = {
+		{ .div = 2, .val = 2, },
+		{ .div = 3, .val = 3, },
+		{ .div = 4, .val = 4, },
+		{ .div = 5, .val = 5, },
+		{ .div = 6, .val = 6, },
+		{ .div = 7, .val = 7, },
+	};
 
 	clk_configs = devm_kzalloc(dev, sizeof(*clk_configs), GFP_KERNEL);
 	if (!clk_configs)
@@ -146,9 +154,9 @@ static int meson8b_init_rgmii_tx_clk(struct meson8b_dwmac *dwmac)
 	clk_configs->m250_div.reg = dwmac->regs + PRG_ETH0;
 	clk_configs->m250_div.shift = PRG_ETH0_CLK_M250_DIV_SHIFT;
 	clk_configs->m250_div.width = PRG_ETH0_CLK_M250_DIV_WIDTH;
-	clk_configs->m250_div.flags = CLK_DIVIDER_ONE_BASED |
-				CLK_DIVIDER_ALLOW_ZERO |
-				CLK_DIVIDER_ROUND_CLOSEST;
+	clk_configs->m250_div.table = div_table;
+	clk_configs->m250_div.flags = CLK_DIVIDER_ALLOW_ZERO |
+				      CLK_DIVIDER_ROUND_CLOSEST;
 	clk = meson8b_dwmac_register_clk(dwmac, "m250_div", &parent_name, 1,
 					 &clk_divider_ops,
 					 &clk_configs->m250_div.hw);
-- 
2.20.1


From 32b88ce94820c6d0e45d7fae9b759fa75f5682f7 Mon Sep 17 00:00:00 2001
From: Vladis Dronov <vdronov@redhat.com>
Date: Fri, 27 Dec 2019 03:26:27 +0100
Subject: [PATCH 09/46] ptp: fix the race between the release of ptp_clock and
 cdev

[ Upstream commit a33121e5487b424339636b25c35d3a180eaa5f5e ]

In a case when a ptp chardev (like /dev/ptp0) is open but an underlying
device is removed, closing this file leads to a race. This reproduces
easily in a kvm virtual machine:

ts# cat openptp0.c
int main() { ... fp = fopen("/dev/ptp0", "r"); ... sleep(10); }
ts# uname -r
5.5.0-rc3-46cf053e
ts# cat /proc/cmdline
... slub_debug=FZP
ts# modprobe ptp_kvm
ts# ./openptp0 &
[1] 670
opened /dev/ptp0, sleeping 10s...
ts# rmmod ptp_kvm
ts# ls /dev/ptp*
ls: cannot access '/dev/ptp*': No such file or directory
ts# ...woken up
[   48.010809] general protection fault: 0000 [#1] SMP
[   48.012502] CPU: 6 PID: 658 Comm: openptp0 Not tainted 5.5.0-rc3-46cf053e #25
[   48.014624] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), ...
[   48.016270] RIP: 0010:module_put.part.0+0x7/0x80
[   48.017939] RSP: 0018:ffffb3850073be00 EFLAGS: 00010202
[   48.018339] RAX: 000000006b6b6b6b RBX: 6b6b6b6b6b6b6b6b RCX: ffff89a476c00ad0
[   48.018936] RDX: fffff65a08d3ea08 RSI: 0000000000000247 RDI: 6b6b6b6b6b6b6b6b
[   48.019470] ...                                              ^^^ a slub poison
[   48.023854] Call Trace:
[   48.024050]  __fput+0x21f/0x240
[   48.024288]  task_work_run+0x79/0x90
[   48.024555]  do_exit+0x2af/0xab0
[   48.024799]  ? vfs_write+0x16a/0x190
[   48.025082]  do_group_exit+0x35/0x90
[   48.025387]  __x64_sys_exit_group+0xf/0x10
[   48.025737]  do_syscall_64+0x3d/0x130
[   48.026056]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[   48.026479] RIP: 0033:0x7f53b12082f6
[   48.026792] ...
[   48.030945] Modules linked in: ptp i6300esb watchdog [last unloaded: ptp_kvm]
[   48.045001] Fixing recursive fault but reboot is needed!

This happens in:

static void __fput(struct file *file)
{   ...
    if (file->f_op->release)
        file->f_op->release(inode, file); <<< cdev is kfree'd here
    if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL &&
             !(mode & FMODE_PATH))) {
        cdev_put(inode->i_cdev); <<< cdev fields are accessed here

Namely:

__fput()
  posix_clock_release()
    kref_put(&clk->kref, delete_clock) <<< the last reference
      delete_clock()
        delete_ptp_clock()
          kfree(ptp) <<< cdev is embedded in ptp
  cdev_put
    module_put(p->owner) <<< *p is kfree'd, bang!

Here cdev is embedded in posix_clock which is embedded in ptp_clock.
The race happens because ptp_clock's lifetime is controlled by two
refcounts: kref and cdev.kobj in posix_clock. This is wrong.

Make ptp_clock's sysfs device a parent of cdev with cdev_device_add()
created especially for such cases. This way the parent device with its
ptp_clock is not released until all references to the cdev are released.
This adds a requirement that an initialized but not exposed struct
device should be provided to posix_clock_register() by a caller instead
of a simple dev_t.

This approach was adopted from the commit 72139dfa2464 ("watchdog: Fix
the race between the release of watchdog_core_data and cdev"). See
details of the implementation in the commit 233ed09d7fda ("chardev: add
helper function to register char devs with a struct device").

Link: https://lore.kernel.org/linux-fsdevel/20191125125342.6189-1-vdronov@redhat.com/T/#u
Analyzed-by: Stephen Johnston <sjohnsto@redhat.com>
Analyzed-by: Vern Lovejoy <vlovejoy@redhat.com>
Signed-off-by: Vladis Dronov <vdronov@redhat.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/ptp/ptp_clock.c     | 31 ++++++++++++++-----------------
 drivers/ptp/ptp_private.h   |  2 +-
 include/linux/posix-clock.h | 19 +++++++++++--------
 kernel/time/posix-clock.c   | 31 +++++++++++++------------------
 4 files changed, 39 insertions(+), 44 deletions(-)

diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c
index e60eab7f8a61..61fafe0374ce 100644
--- a/drivers/ptp/ptp_clock.c
+++ b/drivers/ptp/ptp_clock.c
@@ -166,9 +166,9 @@ static struct posix_clock_operations ptp_clock_ops = {
 	.read		= ptp_read,
 };
 
-static void delete_ptp_clock(struct posix_clock *pc)
+static void ptp_clock_release(struct device *dev)
 {
-	struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock);
+	struct ptp_clock *ptp = container_of(dev, struct ptp_clock, dev);
 
 	mutex_destroy(&ptp->tsevq_mux);
 	mutex_destroy(&ptp->pincfg_mux);
@@ -213,7 +213,6 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info,
 	}
 
 	ptp->clock.ops = ptp_clock_ops;
-	ptp->clock.release = delete_ptp_clock;
 	ptp->info = info;
 	ptp->devid = MKDEV(major, index);
 	ptp->index = index;
@@ -236,15 +235,6 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info,
 	if (err)
 		goto no_pin_groups;
 
-	/* Create a new device in our class. */
-	ptp->dev = device_create_with_groups(ptp_class, parent, ptp->devid,
-					     ptp, ptp->pin_attr_groups,
-					     "ptp%d", ptp->index);
-	if (IS_ERR(ptp->dev)) {
-		err = PTR_ERR(ptp->dev);
-		goto no_device;
-	}
-
 	/* Register a new PPS source. */
 	if (info->pps) {
 		struct pps_source_info pps;
@@ -260,8 +250,18 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info,
 		}
 	}
 
-	/* Create a posix clock. */
-	err = posix_clock_register(&ptp->clock, ptp->devid);
+	/* Initialize a new device of our class in our clock structure. */
+	device_initialize(&ptp->dev);
+	ptp->dev.devt = ptp->devid;
+	ptp->dev.class = ptp_class;
+	ptp->dev.parent = parent;
+	ptp->dev.groups = ptp->pin_attr_groups;
+	ptp->dev.release = ptp_clock_release;
+	dev_set_drvdata(&ptp->dev, ptp);
+	dev_set_name(&ptp->dev, "ptp%d", ptp->index);
+
+	/* Create a posix clock and link it to the device. */
+	err = posix_clock_register(&ptp->clock, &ptp->dev);
 	if (err) {
 		pr_err("failed to create posix clock\n");
 		goto no_clock;
@@ -273,8 +273,6 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info,
 	if (ptp->pps_source)
 		pps_unregister_source(ptp->pps_source);
 no_pps:
-	device_destroy(ptp_class, ptp->devid);
-no_device:
 	ptp_cleanup_pin_groups(ptp);
 no_pin_groups:
 	if (ptp->kworker)
@@ -304,7 +302,6 @@ int ptp_clock_unregister(struct ptp_clock *ptp)
 	if (ptp->pps_source)
 		pps_unregister_source(ptp->pps_source);
 
-	device_destroy(ptp_class, ptp->devid);
 	ptp_cleanup_pin_groups(ptp);
 
 	posix_clock_unregister(&ptp->clock);
diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h
index 9171d42468fd..6b97155148f1 100644
--- a/drivers/ptp/ptp_private.h
+++ b/drivers/ptp/ptp_private.h
@@ -28,7 +28,7 @@ struct timestamp_event_queue {
 
 struct ptp_clock {
 	struct posix_clock clock;
-	struct device *dev;
+	struct device dev;
 	struct ptp_clock_info *info;
 	dev_t devid;
 	int index; /* index into clocks.map */
diff --git a/include/linux/posix-clock.h b/include/linux/posix-clock.h
index fe6cfdcfbc26..468328b1e1dd 100644
--- a/include/linux/posix-clock.h
+++ b/include/linux/posix-clock.h
@@ -69,29 +69,32 @@ struct posix_clock_operations {
  *
  * @ops:     Functional interface to the clock
  * @cdev:    Character device instance for this clock
- * @kref:    Reference count.
+ * @dev:     Pointer to the clock's device.
  * @rwsem:   Protects the 'zombie' field from concurrent access.
  * @zombie:  If 'zombie' is true, then the hardware has disappeared.
- * @release: A function to free the structure when the reference count reaches
- *           zero. May be NULL if structure is statically allocated.
  *
  * Drivers should embed their struct posix_clock within a private
  * structure, obtaining a reference to it during callbacks using
  * container_of().
+ *
+ * Drivers should supply an initialized but not exposed struct device
+ * to posix_clock_register(). It is used to manage lifetime of the
+ * driver's private structure. It's 'release' field should be set to
+ * a release function for this private structure.
  */
 struct posix_clock {
 	struct posix_clock_operations ops;
 	struct cdev cdev;
-	struct kref kref;
+	struct device *dev;
 	struct rw_semaphore rwsem;
 	bool zombie;
-	void (*release)(struct posix_clock *clk);
 };
 
 /**
  * posix_clock_register() - register a new clock
- * @clk:   Pointer to the clock. Caller must provide 'ops' and 'release'
- * @devid: Allocated device id
+ * @clk:   Pointer to the clock. Caller must provide 'ops' field
+ * @dev:   Pointer to the initialized device. Caller must provide
+ *         'release' field
  *
  * A clock driver calls this function to register itself with the
  * clock device subsystem. If 'clk' points to dynamically allocated
@@ -100,7 +103,7 @@ struct posix_clock {
  *
  * Returns zero on success, non-zero otherwise.
  */
-int posix_clock_register(struct posix_clock *clk, dev_t devid);
+int posix_clock_register(struct posix_clock *clk, struct device *dev);
 
 /**
  * posix_clock_unregister() - unregister a clock
diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c
index ec960bb939fd..200fb2d3be99 100644
--- a/kernel/time/posix-clock.c
+++ b/kernel/time/posix-clock.c
@@ -14,8 +14,6 @@
 
 #include "posix-timers.h"
 
-static void delete_clock(struct kref *kref);
-
 /*
  * Returns NULL if the posix_clock instance attached to 'fp' is old and stale.
  */
@@ -125,7 +123,7 @@ static int posix_clock_open(struct inode *inode, struct file *fp)
 		err = 0;
 
 	if (!err) {
-		kref_get(&clk->kref);
+		get_device(clk->dev);
 		fp->private_data = clk;
 	}
 out:
@@ -141,7 +139,7 @@ static int posix_clock_release(struct inode *inode, struct file *fp)
 	if (clk->ops.release)
 		err = clk->ops.release(clk);
 
-	kref_put(&clk->kref, delete_clock);
+	put_device(clk->dev);
 
 	fp->private_data = NULL;
 
@@ -161,38 +159,35 @@ static const struct file_operations posix_clock_file_operations = {
 #endif
 };
 
-int posix_clock_register(struct posix_clock *clk, dev_t devid)
+int posix_clock_register(struct posix_clock *clk, struct device *dev)
 {
 	int err;
 
-	kref_init(&clk->kref);
 	init_rwsem(&clk->rwsem);
 
 	cdev_init(&clk->cdev, &posix_clock_file_operations);
+	err = cdev_device_add(&clk->cdev, dev);
+	if (err) {
+		pr_err("%s unable to add device %d:%d\n",
+			dev_name(dev), MAJOR(dev->devt), MINOR(dev->devt));
+		return err;
+	}
 	clk->cdev.owner = clk->ops.owner;
-	err = cdev_add(&clk->cdev, devid, 1);
+	clk->dev = dev;
 
-	return err;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(posix_clock_register);
 
-static void delete_clock(struct kref *kref)
-{
-	struct posix_clock *clk = container_of(kref, struct posix_clock, kref);
-
-	if (clk->release)
-		clk->release(clk);
-}
-
 void posix_clock_unregister(struct posix_clock *clk)
 {
-	cdev_del(&clk->cdev);
+	cdev_device_del(&clk->cdev, clk->dev);
 
 	down_write(&clk->rwsem);
 	clk->zombie = true;
 	up_write(&clk->rwsem);
 
-	kref_put(&clk->kref, delete_clock);
+	put_device(clk->dev);
 }
 EXPORT_SYMBOL_GPL(posix_clock_unregister);
 
-- 
2.20.1


From 07bb2de5f491eb3be17fc4d538e6b20b54fd9180 Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Fri, 20 Dec 2019 15:03:44 -0300
Subject: [PATCH 10/46] sctp: fix err handling of stream initialization

[ Upstream commit 61d5d4062876e21331c3d0ba4b02dbd50c06a658 ]

The fix on 951c6db954a1 fixed the issued reported there but introduced
another. When the allocation fails within sctp_stream_init() it is
okay/necessary to free the genradix. But it is also called when adding
new streams, from sctp_send_add_streams() and
sctp_process_strreset_addstrm_in() and in those situations it cannot
just free the genradix because by then it is a fully operational
association.

The fix here then is to only free the genradix in sctp_stream_init()
and on those other call sites  move on with what it already had and let
the subsequent error handling to handle it.

Tested with the reproducers from this report and the previous one,
with lksctp-tools and sctp-tests.

Reported-by: syzbot+9a1bc632e78a1a98488b@syzkaller.appspotmail.com
Fixes: 951c6db954a1 ("sctp: fix memleak on err handling of stream initialization")
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/stream.c | 30 +++++++++++++++---------------
 1 file changed, 15 insertions(+), 15 deletions(-)

diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index 6a30392068a0..c1a100d2fed3 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -84,10 +84,8 @@ static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt,
 		return 0;
 
 	ret = genradix_prealloc(&stream->out, outcnt, gfp);
-	if (ret) {
-		genradix_free(&stream->out);
+	if (ret)
 		return ret;
-	}
 
 	stream->outcnt = outcnt;
 	return 0;
@@ -102,10 +100,8 @@ static int sctp_stream_alloc_in(struct sctp_stream *stream, __u16 incnt,
 		return 0;
 
 	ret = genradix_prealloc(&stream->in, incnt, gfp);
-	if (ret) {
-		genradix_free(&stream->in);
+	if (ret)
 		return ret;
-	}
 
 	stream->incnt = incnt;
 	return 0;
@@ -123,7 +119,7 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt,
 	 * a new one with new outcnt to save memory if needed.
 	 */
 	if (outcnt == stream->outcnt)
-		goto in;
+		goto handle_in;
 
 	/* Filter out chunks queued on streams that won't exist anymore */
 	sched->unsched_all(stream);
@@ -132,24 +128,28 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt,
 
 	ret = sctp_stream_alloc_out(stream, outcnt, gfp);
 	if (ret)
-		goto out;
+		goto out_err;
 
 	for (i = 0; i < stream->outcnt; i++)
 		SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN;
 
-in:
+handle_in:
 	sctp_stream_interleave_init(stream);
 	if (!incnt)
 		goto out;
 
 	ret = sctp_stream_alloc_in(stream, incnt, gfp);
-	if (ret) {
-		sched->free(stream);
-		genradix_free(&stream->out);
-		stream->outcnt = 0;
-		goto out;
-	}
+	if (ret)
+		goto in_err;
+
+	goto out;
 
+in_err:
+	sched->free(stream);
+	genradix_free(&stream->in);
+out_err:
+	genradix_free(&stream->out);
+	stream->outcnt = 0;
 out:
 	return ret;
 }
-- 
2.20.1


From 1c3132977d685d019bd5e777e499c6394a0cd4a4 Mon Sep 17 00:00:00 2001
From: Cambda Zhu <cambda@linux.alibaba.com>
Date: Fri, 27 Dec 2019 16:52:37 +0800
Subject: [PATCH 11/46] tcp: Fix highest_sack and highest_sack_seq

[ Upstream commit 853697504de043ff0bfd815bd3a64de1dce73dc7 ]

>From commit 50895b9de1d3 ("tcp: highest_sack fix"), the logic about
setting tp->highest_sack to the head of the send queue was removed.
Of course the logic is error prone, but it is logical. Before we
remove the pointer to the highest sack skb and use the seq instead,
we need to set tp->highest_sack to NULL when there is no skb after
the last sack, and then replace NULL with the real skb when new skb
inserted into the rtx queue, because the NULL means the highest sack
seq is tp->snd_nxt. If tp->highest_sack is NULL and new data sent,
the next ACK with sack option will increase tp->reordering unexpectedly.

This patch sets tp->highest_sack to the tail of the rtx queue if
it's NULL and new data is sent. The patch keeps the rule that the
highest_sack can only be maintained by sack processing, except for
this only case.

Fixes: 50895b9de1d3 ("tcp: highest_sack fix")
Signed-off-by: Cambda Zhu <cambda@linux.alibaba.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 762edd800d78..b89167fc14a3 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -72,6 +72,9 @@ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb)
 	__skb_unlink(skb, &sk->sk_write_queue);
 	tcp_rbtree_insert(&sk->tcp_rtx_queue, skb);
 
+	if (tp->highest_sack == NULL)
+		tp->highest_sack = skb;
+
 	tp->packets_out += tcp_skb_pcount(skb);
 	if (!prior_packets || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)
 		tcp_rearm_rto(sk);
-- 
2.20.1


From 05aff0cb449b1b5434871bc004b52aaec90f124d Mon Sep 17 00:00:00 2001
From: Antonio Messina <amessina@google.com>
Date: Thu, 19 Dec 2019 15:08:03 +0100
Subject: [PATCH 12/46] udp: fix integer overflow while computing available
 space in sk_rcvbuf

[ Upstream commit feed8a4fc9d46c3126fb9fcae0e9248270c6321a ]

When the size of the receive buffer for a socket is close to 2^31 when
computing if we have enough space in the buffer to copy a packet from
the queue to the buffer we might hit an integer overflow.

When an user set net.core.rmem_default to a value close to 2^31 UDP
packets are dropped because of this overflow. This can be visible, for
instance, with failure to resolve hostnames.

This can be fixed by casting sk_rcvbuf (which is an int) to unsigned
int, similarly to how it is done in TCP.

Signed-off-by: Antonio Messina <amessina@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 447defbfccdd..7aa4e77161f6 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1475,7 +1475,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb)
 	 * queue contains some other skb
 	 */
 	rmem = atomic_add_return(size, &sk->sk_rmem_alloc);
-	if (rmem > (size + sk->sk_rcvbuf))
+	if (rmem > (size + (unsigned int)sk->sk_rcvbuf))
 		goto uncharge_drop;
 
 	spin_lock(&list->lock);
-- 
2.20.1


From 2fe30e9f1e5b0ef0dac357885eb1ce4956871f62 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Tue, 10 Dec 2019 02:49:07 -0500
Subject: [PATCH 13/46] bnxt_en: Fix MSIX request logic for RDMA driver.

[ Upstream commit 0c722ec0a289c7f6b53f89bad1cfb7c4db3f7a62 ]

The logic needs to check both bp->total_irqs and the reserved IRQs in
hw_resc->resv_irqs if applicable and see if both are enough to cover
the L2 and RDMA requested vectors.  The current code is only checking
bp->total_irqs and can fail in some code paths, such as the TX timeout
code path with the RDMA driver requesting vectors after recovery.  In
this code path, we have not reserved enough MSIX resources for the
RDMA driver yet.

Fixes: 75720e6323a1 ("bnxt_en: Keep track of reserved IRQs.")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index b2c160947fc8..30816ec4fa91 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -113,8 +113,10 @@ static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, int ulp_id,
 {
 	struct net_device *dev = edev->net;
 	struct bnxt *bp = netdev_priv(dev);
+	struct bnxt_hw_resc *hw_resc;
 	int max_idx, max_cp_rings;
 	int avail_msix, idx;
+	int total_vecs;
 	int rc = 0;
 
 	ASSERT_RTNL();
@@ -142,7 +144,10 @@ static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, int ulp_id,
 	}
 	edev->ulp_tbl[ulp_id].msix_base = idx;
 	edev->ulp_tbl[ulp_id].msix_requested = avail_msix;
-	if (bp->total_irqs < (idx + avail_msix)) {
+	hw_resc = &bp->hw_resc;
+	total_vecs = idx + avail_msix;
+	if (bp->total_irqs < total_vecs ||
+	    (BNXT_NEW_RM(bp) && hw_resc->resv_irqs < total_vecs)) {
 		if (netif_running(dev)) {
 			bnxt_close_nic(bp, true, false);
 			rc = bnxt_open_nic(bp, true, false);
@@ -156,7 +161,6 @@ static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, int ulp_id,
 	}
 
 	if (BNXT_NEW_RM(bp)) {
-		struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
 		int resv_msix;
 
 		resv_msix = hw_resc->resv_irqs - bp->cp_nr_rings;
-- 
2.20.1


From bc24a751d6798421e4465b6222b713eeeffd4bfa Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Tue, 10 Dec 2019 02:49:08 -0500
Subject: [PATCH 14/46] bnxt_en: Free context memory in the open path if
 firmware has been reset.

[ Upstream commit 325f85f37e5b35807d86185bdf2c64d2980c44ba ]

This will trigger new context memory to be rediscovered and allocated
during the re-probe process after a firmware reset.  Without this, the
newly reset firmware does not have valid context memory and the driver
will eventually fail to allocate some resources.

Fixes: ec5d31e3c15d ("bnxt_en: Handle firmware reset status during IF_UP.")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 527e1bf93116..a23f582442e0 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -8766,6 +8766,9 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up)
 	}
 	if (resc_reinit || fw_reset) {
 		if (fw_reset) {
+			bnxt_free_ctx_mem(bp);
+			kfree(bp->ctx);
+			bp->ctx = NULL;
 			rc = bnxt_fw_init_one(bp);
 			if (rc) {
 				set_bit(BNXT_STATE_ABORT_ERR, &bp->state);
-- 
2.20.1


From 152f91eb33a3c42a5e719b8ff013e15ddee0b2d8 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Tue, 10 Dec 2019 02:49:09 -0500
Subject: [PATCH 15/46] bnxt_en: Return error if FW returns more data than dump
 length

[ Upstream commit c74751f4c39232c31214ec6a3bc1c7e62f5c728b ]

If any change happened in the configuration of VF in VM while
collecting live dump, there could be a race and firmware can return
more data than allocated dump length. Fix it by keeping track of
the accumulated core dump length copied so far and abort the copy
with error code if the next chunk of core dump will exceed the
original dump length.

Fixes: 6c5657d085ae ("bnxt_en: Add support for ethtool get dump.")
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 38 +++++++++++++++----
 .../net/ethernet/broadcom/bnxt/bnxt_ethtool.h |  4 ++
 2 files changed, 34 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 89f95428556e..ece70f61c89a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -3064,8 +3064,15 @@ static int bnxt_hwrm_dbg_dma_data(struct bnxt *bp, void *msg, int msg_len,
 			}
 		}
 
-		if (info->dest_buf)
-			memcpy(info->dest_buf + off, dma_buf, len);
+		if (info->dest_buf) {
+			if ((info->seg_start + off + len) <=
+			    BNXT_COREDUMP_BUF_LEN(info->buf_len)) {
+				memcpy(info->dest_buf + off, dma_buf, len);
+			} else {
+				rc = -ENOBUFS;
+				break;
+			}
+		}
 
 		if (cmn_req->req_type ==
 				cpu_to_le16(HWRM_DBG_COREDUMP_RETRIEVE))
@@ -3119,7 +3126,7 @@ static int bnxt_hwrm_dbg_coredump_initiate(struct bnxt *bp, u16 component_id,
 
 static int bnxt_hwrm_dbg_coredump_retrieve(struct bnxt *bp, u16 component_id,
 					   u16 segment_id, u32 *seg_len,
-					   void *buf, u32 offset)
+					   void *buf, u32 buf_len, u32 offset)
 {
 	struct hwrm_dbg_coredump_retrieve_input req = {0};
 	struct bnxt_hwrm_dbg_dma_info info = {NULL};
@@ -3134,8 +3141,11 @@ static int bnxt_hwrm_dbg_coredump_retrieve(struct bnxt *bp, u16 component_id,
 				seq_no);
 	info.data_len_off = offsetof(struct hwrm_dbg_coredump_retrieve_output,
 				     data_len);
-	if (buf)
+	if (buf) {
 		info.dest_buf = buf + offset;
+		info.buf_len = buf_len;
+		info.seg_start = offset;
+	}
 
 	rc = bnxt_hwrm_dbg_dma_data(bp, &req, sizeof(req), &info);
 	if (!rc)
@@ -3225,14 +3235,17 @@ bnxt_fill_coredump_record(struct bnxt *bp, struct bnxt_coredump_record *record,
 static int bnxt_get_coredump(struct bnxt *bp, void *buf, u32 *dump_len)
 {
 	u32 ver_get_resp_len = sizeof(struct hwrm_ver_get_output);
+	u32 offset = 0, seg_hdr_len, seg_record_len, buf_len = 0;
 	struct coredump_segment_record *seg_record = NULL;
-	u32 offset = 0, seg_hdr_len, seg_record_len;
 	struct bnxt_coredump_segment_hdr seg_hdr;
 	struct bnxt_coredump coredump = {NULL};
 	time64_t start_time;
 	u16 start_utc;
 	int rc = 0, i;
 
+	if (buf)
+		buf_len = *dump_len;
+
 	start_time = ktime_get_real_seconds();
 	start_utc = sys_tz.tz_minuteswest * 60;
 	seg_hdr_len = sizeof(seg_hdr);
@@ -3265,6 +3278,12 @@ static int bnxt_get_coredump(struct bnxt *bp, void *buf, u32 *dump_len)
 		u32 duration = 0, seg_len = 0;
 		unsigned long start, end;
 
+		if (buf && ((offset + seg_hdr_len) >
+			    BNXT_COREDUMP_BUF_LEN(buf_len))) {
+			rc = -ENOBUFS;
+			goto err;
+		}
+
 		start = jiffies;
 
 		rc = bnxt_hwrm_dbg_coredump_initiate(bp, comp_id, seg_id);
@@ -3277,9 +3296,11 @@ static int bnxt_get_coredump(struct bnxt *bp, void *buf, u32 *dump_len)
 
 		/* Write segment data into the buffer */
 		rc = bnxt_hwrm_dbg_coredump_retrieve(bp, comp_id, seg_id,
-						     &seg_len, buf,
+						     &seg_len, buf, buf_len,
 						     offset + seg_hdr_len);
-		if (rc)
+		if (rc && rc == -ENOBUFS)
+			goto err;
+		else if (rc)
 			netdev_err(bp->dev,
 				   "Failed to retrieve coredump for seg = %d\n",
 				   seg_record->segment_id);
@@ -3309,7 +3330,8 @@ static int bnxt_get_coredump(struct bnxt *bp, void *buf, u32 *dump_len)
 					  rc);
 	kfree(coredump.data);
 	*dump_len += sizeof(struct bnxt_coredump_record);
-
+	if (rc == -ENOBUFS)
+		netdev_err(bp->dev, "Firmware returned large coredump buffer");
 	return rc;
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h
index b5b65b3f8534..3998f6e809a9 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h
@@ -31,6 +31,8 @@ struct bnxt_coredump {
 	u16		total_segs;
 };
 
+#define BNXT_COREDUMP_BUF_LEN(len) ((len) - sizeof(struct bnxt_coredump_record))
+
 struct bnxt_hwrm_dbg_dma_info {
 	void *dest_buf;
 	int dest_buf_size;
@@ -38,6 +40,8 @@ struct bnxt_hwrm_dbg_dma_info {
 	u16 seq_off;
 	u16 data_len_off;
 	u16 segs;
+	u32 seg_start;
+	u32 buf_len;
 };
 
 struct hwrm_dbg_cmn_input {
-- 
2.20.1


From 7a7cf0b2d0db750b51e96a58efb4e1c36b148425 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Tue, 10 Dec 2019 02:49:10 -0500
Subject: [PATCH 16/46] bnxt_en: Fix bp->fw_health allocation and free logic.

[ Upstream commit 8280b38e01f71e0f89389ccad3fa43b79e57c604 ]

bp->fw_health needs to be allocated for either the firmware initiated
reset feature or the driver initiated error recovery feature.  The
current code is not allocating bp->fw_health for all the necessary cases.
This patch corrects the logic to allocate bp->fw_health correctly when
needed.  If allocation fails, we clear the feature flags.

We also add the the missing kfree(bp->fw_health) when the driver is
unloaded.  If we get an async reset message from the firmware, we also
need to make sure that we have a valid bp->fw_health before proceeding.

Fixes: 07f83d72d238 ("bnxt_en: Discover firmware error recovery capabilities.")
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 36 ++++++++++++++++-------
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |  1 +
 2 files changed, 27 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index a23f582442e0..a5e47b6e6142 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1995,6 +1995,9 @@ static int bnxt_async_event_process(struct bnxt *bp,
 	case ASYNC_EVENT_CMPL_EVENT_ID_RESET_NOTIFY: {
 		u32 data1 = le32_to_cpu(cmpl->event_data1);
 
+		if (!bp->fw_health)
+			goto async_event_process_exit;
+
 		bp->fw_reset_timestamp = jiffies;
 		bp->fw_reset_min_dsecs = cmpl->timestamp_lo;
 		if (!bp->fw_reset_min_dsecs)
@@ -4438,8 +4441,9 @@ static int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp)
 			    FUNC_DRV_RGTR_REQ_ENABLES_VER);
 
 	req.os_type = cpu_to_le16(FUNC_DRV_RGTR_REQ_OS_TYPE_LINUX);
-	flags = FUNC_DRV_RGTR_REQ_FLAGS_16BIT_VER_MODE |
-		FUNC_DRV_RGTR_REQ_FLAGS_HOT_RESET_SUPPORT;
+	flags = FUNC_DRV_RGTR_REQ_FLAGS_16BIT_VER_MODE;
+	if (bp->fw_cap & BNXT_FW_CAP_HOT_RESET)
+		flags |= FUNC_DRV_RGTR_REQ_FLAGS_HOT_RESET_SUPPORT;
 	if (bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY)
 		flags |= FUNC_DRV_RGTR_REQ_FLAGS_ERROR_RECOVERY_SUPPORT;
 	req.flags = cpu_to_le32(flags);
@@ -7096,14 +7100,6 @@ static int bnxt_hwrm_error_recovery_qcfg(struct bnxt *bp)
 	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 	if (rc)
 		goto err_recovery_out;
-	if (!fw_health) {
-		fw_health = kzalloc(sizeof(*fw_health), GFP_KERNEL);
-		bp->fw_health = fw_health;
-		if (!fw_health) {
-			rc = -ENOMEM;
-			goto err_recovery_out;
-		}
-	}
 	fw_health->flags = le32_to_cpu(resp->flags);
 	if ((fw_health->flags & ERROR_RECOVERY_QCFG_RESP_FLAGS_CO_CPU) &&
 	    !(bp->fw_cap & BNXT_FW_CAP_KONG_MB_CHNL)) {
@@ -10419,6 +10415,23 @@ static void bnxt_init_dflt_coal(struct bnxt *bp)
 	bp->stats_coal_ticks = BNXT_DEF_STATS_COAL_TICKS;
 }
 
+static void bnxt_alloc_fw_health(struct bnxt *bp)
+{
+	if (bp->fw_health)
+		return;
+
+	if (!(bp->fw_cap & BNXT_FW_CAP_HOT_RESET) &&
+	    !(bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY))
+		return;
+
+	bp->fw_health = kzalloc(sizeof(*bp->fw_health), GFP_KERNEL);
+	if (!bp->fw_health) {
+		netdev_warn(bp->dev, "Failed to allocate fw_health\n");
+		bp->fw_cap &= ~BNXT_FW_CAP_HOT_RESET;
+		bp->fw_cap &= ~BNXT_FW_CAP_ERROR_RECOVERY;
+	}
+}
+
 static int bnxt_fw_init_one_p1(struct bnxt *bp)
 {
 	int rc;
@@ -10465,6 +10478,7 @@ static int bnxt_fw_init_one_p2(struct bnxt *bp)
 		netdev_warn(bp->dev, "hwrm query adv flow mgnt failure rc: %d\n",
 			    rc);
 
+	bnxt_alloc_fw_health(bp);
 	rc = bnxt_hwrm_error_recovery_qcfg(bp);
 	if (rc)
 		netdev_warn(bp->dev, "hwrm query error recovery failure rc: %d\n",
@@ -11344,6 +11358,8 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 	bnxt_dcb_free(bp);
 	kfree(bp->edev);
 	bp->edev = NULL;
+	kfree(bp->fw_health);
+	bp->fw_health = NULL;
 	bnxt_cleanup_pci(bp);
 	bnxt_free_ctx_mem(bp);
 	kfree(bp->ctx);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 5163bb848618..dc26e3ace43f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1658,6 +1658,7 @@ struct bnxt {
 	#define BNXT_FW_CAP_PCIE_STATS_SUPPORTED	0x00020000
 	#define BNXT_FW_CAP_EXT_STATS_SUPPORTED		0x00040000
 	#define BNXT_FW_CAP_ERR_RECOVER_RELOAD		0x00100000
+	#define BNXT_FW_CAP_HOT_RESET			0x00200000
 
 #define BNXT_NEW_RM(bp)		((bp)->fw_cap & BNXT_FW_CAP_NEW_RM)
 	u32			hwrm_spec_code;
-- 
2.20.1


From b5277a50cb6773981eea63df5282acc4bdf76a73 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Tue, 10 Dec 2019 02:49:11 -0500
Subject: [PATCH 17/46] bnxt_en: Remove unnecessary NULL checks for fw_health

[ Upstream commit 0797c10d2d1fa0d6f14612404781b348fc757c3e ]

After fixing the allocation of bp->fw_health in the previous patch,
the driver will not go through the fw reset and recovery code paths
if bp->fw_health allocation fails.  So we can now remove the
unnecessary NULL checks.

Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c         | 6 ++----
 drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c | 6 +-----
 2 files changed, 3 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index a5e47b6e6142..6ee08f2ba909 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -9953,8 +9953,7 @@ static void bnxt_fw_health_check(struct bnxt *bp)
 	struct bnxt_fw_health *fw_health = bp->fw_health;
 	u32 val;
 
-	if (!fw_health || !fw_health->enabled ||
-	    test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))
+	if (!fw_health->enabled || test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))
 		return;
 
 	if (fw_health->tmr_counter) {
@@ -10697,8 +10696,7 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 		bnxt_queue_fw_reset_work(bp, bp->fw_reset_min_dsecs * HZ / 10);
 		return;
 	case BNXT_FW_RESET_STATE_ENABLE_DEV:
-		if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state) &&
-		    bp->fw_health) {
+		if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state)) {
 			u32 val;
 
 			val = bnxt_fw_health_readl(bp,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index 7d2cfea05737..ffc36d6df304 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -19,11 +19,10 @@ static int bnxt_fw_reporter_diagnose(struct devlink_health_reporter *reporter,
 				     struct devlink_fmsg *fmsg)
 {
 	struct bnxt *bp = devlink_health_reporter_priv(reporter);
-	struct bnxt_fw_health *health = bp->fw_health;
 	u32 val, health_status;
 	int rc;
 
-	if (!health || test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))
+	if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))
 		return 0;
 
 	val = bnxt_fw_health_readl(bp, BNXT_FW_HEALTH_REG);
@@ -162,9 +161,6 @@ void bnxt_devlink_health_report(struct bnxt *bp, unsigned long event)
 	struct bnxt_fw_health *fw_health = bp->fw_health;
 	struct bnxt_fw_reporter_ctx fw_reporter_ctx;
 
-	if (!fw_health)
-		return;
-
 	fw_reporter_ctx.sp_event = event;
 	switch (event) {
 	case BNXT_FW_RESET_NOTIFY_SP_EVENT:
-- 
2.20.1


From 2e8cbc0c0569609c7be10a1d6d3ec61b3d97d70e Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Tue, 10 Dec 2019 02:49:12 -0500
Subject: [PATCH 18/46] bnxt_en: Fix the logic that creates the health
 reporters.

[ Upstream commit 937f188c1f4f89b3fa93ba31fc8587dc1fb14a22 ]

Fix the logic to properly check the fw capabilities and create the
devlink health reporters only when needed.  The current code creates
the reporters unconditionally as long as bp->fw_health is valid, and
that's not correct.

Call bnxt_dl_fw_reporters_create() directly from the init and reset
code path instead of from bnxt_dl_register().  This allows the
reporters to be adjusted when capabilities change.  The same
applies to bnxt_dl_fw_reporters_destroy().

Fixes: 6763c779c2d8 ("bnxt_en: Add new FW devlink_health_reporter")
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c     | 11 +++-
 .../net/ethernet/broadcom/bnxt/bnxt_devlink.c | 64 +++++++++++++------
 .../net/ethernet/broadcom/bnxt/bnxt_devlink.h |  2 +
 3 files changed, 56 insertions(+), 21 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 6ee08f2ba909..07fa6dba3242 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -10563,6 +10563,12 @@ static int bnxt_fw_init_one(struct bnxt *bp)
 	rc = bnxt_approve_mac(bp, bp->dev->dev_addr, false);
 	if (rc)
 		return rc;
+
+	/* In case fw capabilities have changed, destroy the unneeded
+	 * reporters and create newly capable ones.
+	 */
+	bnxt_dl_fw_reporters_destroy(bp, false);
+	bnxt_dl_fw_reporters_create(bp);
 	bnxt_fw_init_one_p3(bp);
 	return 0;
 }
@@ -11339,6 +11345,7 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 
 	if (BNXT_PF(bp)) {
 		bnxt_sriov_disable(bp);
+		bnxt_dl_fw_reporters_destroy(bp, true);
 		bnxt_dl_unregister(bp);
 	}
 
@@ -11837,8 +11844,10 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (rc)
 		goto init_err_cleanup_tc;
 
-	if (BNXT_PF(bp))
+	if (BNXT_PF(bp)) {
 		bnxt_dl_register(bp);
+		bnxt_dl_fw_reporters_create(bp);
+	}
 
 	netdev_info(dev, "%s found at mem %lx, node addr %pM\n",
 		    board_info[ent->driver_data].name,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index ffc36d6df304..adb87638e330 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -102,21 +102,15 @@ struct devlink_health_reporter_ops bnxt_dl_fw_fatal_reporter_ops = {
 	.recover = bnxt_fw_fatal_recover,
 };
 
-static void bnxt_dl_fw_reporters_create(struct bnxt *bp)
+void bnxt_dl_fw_reporters_create(struct bnxt *bp)
 {
 	struct bnxt_fw_health *health = bp->fw_health;
 
-	if (!health)
+	if (!bp->dl || !health)
 		return;
 
-	health->fw_reporter =
-		devlink_health_reporter_create(bp->dl, &bnxt_dl_fw_reporter_ops,
-					       0, false, bp);
-	if (IS_ERR(health->fw_reporter)) {
-		netdev_warn(bp->dev, "Failed to create FW health reporter, rc = %ld\n",
-			    PTR_ERR(health->fw_reporter));
-		health->fw_reporter = NULL;
-	}
+	if (!(bp->fw_cap & BNXT_FW_CAP_HOT_RESET) || health->fw_reset_reporter)
+		goto err_recovery;
 
 	health->fw_reset_reporter =
 		devlink_health_reporter_create(bp->dl,
@@ -126,8 +120,30 @@ static void bnxt_dl_fw_reporters_create(struct bnxt *bp)
 		netdev_warn(bp->dev, "Failed to create FW fatal health reporter, rc = %ld\n",
 			    PTR_ERR(health->fw_reset_reporter));
 		health->fw_reset_reporter = NULL;
+		bp->fw_cap &= ~BNXT_FW_CAP_HOT_RESET;
 	}
 
+err_recovery:
+	if (!(bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY))
+		return;
+
+	if (!health->fw_reporter) {
+		health->fw_reporter =
+			devlink_health_reporter_create(bp->dl,
+						       &bnxt_dl_fw_reporter_ops,
+						       0, false, bp);
+		if (IS_ERR(health->fw_reporter)) {
+			netdev_warn(bp->dev, "Failed to create FW health reporter, rc = %ld\n",
+				    PTR_ERR(health->fw_reporter));
+			health->fw_reporter = NULL;
+			bp->fw_cap &= ~BNXT_FW_CAP_ERROR_RECOVERY;
+			return;
+		}
+	}
+
+	if (health->fw_fatal_reporter)
+		return;
+
 	health->fw_fatal_reporter =
 		devlink_health_reporter_create(bp->dl,
 					       &bnxt_dl_fw_fatal_reporter_ops,
@@ -136,24 +152,35 @@ static void bnxt_dl_fw_reporters_create(struct bnxt *bp)
 		netdev_warn(bp->dev, "Failed to create FW fatal health reporter, rc = %ld\n",
 			    PTR_ERR(health->fw_fatal_reporter));
 		health->fw_fatal_reporter = NULL;
+		bp->fw_cap &= ~BNXT_FW_CAP_ERROR_RECOVERY;
 	}
 }
 
-static void bnxt_dl_fw_reporters_destroy(struct bnxt *bp)
+void bnxt_dl_fw_reporters_destroy(struct bnxt *bp, bool all)
 {
 	struct bnxt_fw_health *health = bp->fw_health;
 
-	if (!health)
+	if (!bp->dl || !health)
 		return;
 
-	if (health->fw_reporter)
-		devlink_health_reporter_destroy(health->fw_reporter);
-
-	if (health->fw_reset_reporter)
+	if ((all || !(bp->fw_cap & BNXT_FW_CAP_HOT_RESET)) &&
+	    health->fw_reset_reporter) {
 		devlink_health_reporter_destroy(health->fw_reset_reporter);
+		health->fw_reset_reporter = NULL;
+	}
 
-	if (health->fw_fatal_reporter)
+	if ((bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY) && !all)
+		return;
+
+	if (health->fw_reporter) {
+		devlink_health_reporter_destroy(health->fw_reporter);
+		health->fw_reporter = NULL;
+	}
+
+	if (health->fw_fatal_reporter) {
 		devlink_health_reporter_destroy(health->fw_fatal_reporter);
+		health->fw_fatal_reporter = NULL;
+	}
 }
 
 void bnxt_devlink_health_report(struct bnxt *bp, unsigned long event)
@@ -458,8 +485,6 @@ int bnxt_dl_register(struct bnxt *bp)
 
 	devlink_params_publish(dl);
 
-	bnxt_dl_fw_reporters_create(bp);
-
 	return 0;
 
 err_dl_port_unreg:
@@ -482,7 +507,6 @@ void bnxt_dl_unregister(struct bnxt *bp)
 	if (!dl)
 		return;
 
-	bnxt_dl_fw_reporters_destroy(bp);
 	devlink_port_params_unregister(&bp->dl_port, bnxt_dl_port_params,
 				       ARRAY_SIZE(bnxt_dl_port_params));
 	devlink_port_unregister(&bp->dl_port);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
index 2f4fd0a7d04b..689c47ab2155 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
@@ -57,6 +57,8 @@ struct bnxt_dl_nvm_param {
 };
 
 void bnxt_devlink_health_report(struct bnxt *bp, unsigned long event);
+void bnxt_dl_fw_reporters_create(struct bnxt *bp);
+void bnxt_dl_fw_reporters_destroy(struct bnxt *bp, bool all);
 int bnxt_dl_register(struct bnxt *bp);
 void bnxt_dl_unregister(struct bnxt *bp);
 
-- 
2.20.1


From b4e9ed66dc69432ca84bfbf4fbcfd9bf374ad4f8 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Tue, 10 Dec 2019 02:49:13 -0500
Subject: [PATCH 19/46] bnxt_en: Add missing devlink health reporters for VFs.

[ Upstream commit 7e334fc8003c7a38372cc98e7be6082670a47d29 ]

The VF driver also needs to create the health reporters since
VFs are also involved in firmware reset and recovery.  Modify
bnxt_dl_register() and bnxt_dl_unregister() so that they can
be called by the VFs to register/unregister devlink.  Only the PF
will register the devlink parameters.  With devlink registered,
we can now create the health reporters on the VFs.

Fixes: 6763c779c2d8 ("bnxt_en: Add new FW devlink_health_reporter")
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c     | 13 ++++-------
 .../net/ethernet/broadcom/bnxt/bnxt_devlink.c | 23 ++++++++++++++-----
 2 files changed, 22 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 07fa6dba3242..c0df947ed9f9 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -11343,12 +11343,11 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 	struct net_device *dev = pci_get_drvdata(pdev);
 	struct bnxt *bp = netdev_priv(dev);
 
-	if (BNXT_PF(bp)) {
+	if (BNXT_PF(bp))
 		bnxt_sriov_disable(bp);
-		bnxt_dl_fw_reporters_destroy(bp, true);
-		bnxt_dl_unregister(bp);
-	}
 
+	bnxt_dl_fw_reporters_destroy(bp, true);
+	bnxt_dl_unregister(bp);
 	pci_disable_pcie_error_reporting(pdev);
 	unregister_netdev(dev);
 	bnxt_shutdown_tc(bp);
@@ -11844,10 +11843,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (rc)
 		goto init_err_cleanup_tc;
 
-	if (BNXT_PF(bp)) {
-		bnxt_dl_register(bp);
-		bnxt_dl_fw_reporters_create(bp);
-	}
+	bnxt_dl_register(bp);
+	bnxt_dl_fw_reporters_create(bp);
 
 	netdev_info(dev, "%s found at mem %lx, node addr %pM\n",
 		    board_info[ent->driver_data].name,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index adb87638e330..1e236e74ff2f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -226,6 +226,8 @@ static const struct devlink_ops bnxt_dl_ops = {
 #endif /* CONFIG_BNXT_SRIOV */
 };
 
+static const struct devlink_ops bnxt_vf_dl_ops;
+
 enum bnxt_dl_param_id {
 	BNXT_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
 	BNXT_DEVLINK_PARAM_ID_GRE_VER_CHECK,
@@ -439,7 +441,10 @@ int bnxt_dl_register(struct bnxt *bp)
 		return -ENOTSUPP;
 	}
 
-	dl = devlink_alloc(&bnxt_dl_ops, sizeof(struct bnxt_dl));
+	if (BNXT_PF(bp))
+		dl = devlink_alloc(&bnxt_dl_ops, sizeof(struct bnxt_dl));
+	else
+		dl = devlink_alloc(&bnxt_vf_dl_ops, sizeof(struct bnxt_dl));
 	if (!dl) {
 		netdev_warn(bp->dev, "devlink_alloc failed");
 		return -ENOMEM;
@@ -458,6 +463,9 @@ int bnxt_dl_register(struct bnxt *bp)
 		goto err_dl_free;
 	}
 
+	if (!BNXT_PF(bp))
+		return 0;
+
 	rc = devlink_params_register(dl, bnxt_dl_params,
 				     ARRAY_SIZE(bnxt_dl_params));
 	if (rc) {
@@ -507,11 +515,14 @@ void bnxt_dl_unregister(struct bnxt *bp)
 	if (!dl)
 		return;
 
-	devlink_port_params_unregister(&bp->dl_port, bnxt_dl_port_params,
-				       ARRAY_SIZE(bnxt_dl_port_params));
-	devlink_port_unregister(&bp->dl_port);
-	devlink_params_unregister(dl, bnxt_dl_params,
-				  ARRAY_SIZE(bnxt_dl_params));
+	if (BNXT_PF(bp)) {
+		devlink_port_params_unregister(&bp->dl_port,
+					       bnxt_dl_port_params,
+					       ARRAY_SIZE(bnxt_dl_port_params));
+		devlink_port_unregister(&bp->dl_port);
+		devlink_params_unregister(dl, bnxt_dl_params,
+					  ARRAY_SIZE(bnxt_dl_params));
+	}
 	devlink_unregister(dl);
 	devlink_free(dl);
 }
-- 
2.20.1


From 6fe7fd28786536142fe16a44af7c690e610d6fe8 Mon Sep 17 00:00:00 2001
From: Amit Cohen <amitc@mellanox.com>
Date: Sun, 29 Dec 2019 13:40:22 +0200
Subject: [PATCH 20/46] mlxsw: spectrum_router: Skip loopback RIFs during MAC
 validation

[ Upstream commit 314bd842d98e1035cc40b671a71e07f48420e58f ]

When a router interface (RIF) is created the MAC address of the backing
netdev is verified to have the same MSBs as existing RIFs. This is
required in order to avoid changing existing RIF MAC addresses that all
share the same MSBs.

Loopback RIFs are special in this regard as they do not have a MAC
address, given they are only used to loop packets from the overlay to
the underlay.

Without this change, an error is returned when trying to create a RIF
after the creation of a GRE tunnel that is represented by a loopback
RIF. 'rif->dev->dev_addr' points to the GRE device's local IP, which
does not share the same MSBs as physical interfaces. Adding an IP
address to any physical interface results in:

Error: mlxsw_spectrum: All router interface MAC addresses must have the
same prefix.

Fix this by skipping loopback RIFs during MAC validation.

Fixes: 74bc99397438 ("mlxsw: spectrum_router: Veto unsupported RIF MAC addresses")
Signed-off-by: Amit Cohen <amitc@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 210ebc91d3d6..efdf8cb5114c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -6985,6 +6985,9 @@ static int mlxsw_sp_router_port_check_rif_addr(struct mlxsw_sp *mlxsw_sp,
 
 	for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) {
 		rif = mlxsw_sp->router->rifs[i];
+		if (rif && rif->ops &&
+		    rif->ops->type == MLXSW_SP_RIF_TYPE_IPIP_LB)
+			continue;
 		if (rif && rif->dev && rif->dev != dev &&
 		    !ether_addr_equal_masked(rif->dev->dev_addr, dev_addr,
 					     mlxsw_sp->mac_mask)) {
-- 
2.20.1


From 8a5fb00966da45646e07478c50b775bb2673b313 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Sun, 29 Dec 2019 13:40:23 +0200
Subject: [PATCH 21/46] mlxsw: spectrum: Use dedicated policer for VRRP packets

[ Upstream commit acca789a358cc960be3937851d7de6591c79d6c2 ]

Currently, VRRP packets and packets that hit exceptions during routing
(e.g., MTU error) are policed using the same policer towards the CPU.
This means, for example, that misconfiguration of the MTU on a routed
interface can prevent VRRP packets from reaching the CPU, which in turn
can cause the VRRP daemon to assume it is the Master router.

Fix this by using a dedicated policer for VRRP packets.

Fixes: 11566d34f895 ("mlxsw: spectrum: Add VRRP traps")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Alex Veber <alexve@mellanox.com>
Tested-by: Alex Veber <alexve@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h      | 1 +
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 9 +++++++--
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 5494cf93f34c..8e42ebdbd487 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -5421,6 +5421,7 @@ enum mlxsw_reg_htgt_trap_group {
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_LBERROR,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP0,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP1,
+	MLXSW_REG_HTGT_TRAP_GROUP_SP_VRRP,
 
 	__MLXSW_REG_HTGT_TRAP_GROUP_MAX,
 	MLXSW_REG_HTGT_TRAP_GROUP_MAX = __MLXSW_REG_HTGT_TRAP_GROUP_MAX - 1
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index dcf9562bce8a..3ec18fb0d479 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4398,8 +4398,8 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 	MLXSW_SP_RXL_MARK(ROUTER_ALERT_IPV6, TRAP_TO_CPU, ROUTER_EXP, false),
 	MLXSW_SP_RXL_MARK(IPIP_DECAP_ERROR, TRAP_TO_CPU, ROUTER_EXP, false),
 	MLXSW_SP_RXL_MARK(DECAP_ECN0, TRAP_TO_CPU, ROUTER_EXP, false),
-	MLXSW_SP_RXL_MARK(IPV4_VRRP, TRAP_TO_CPU, ROUTER_EXP, false),
-	MLXSW_SP_RXL_MARK(IPV6_VRRP, TRAP_TO_CPU, ROUTER_EXP, false),
+	MLXSW_SP_RXL_MARK(IPV4_VRRP, TRAP_TO_CPU, VRRP, false),
+	MLXSW_SP_RXL_MARK(IPV6_VRRP, TRAP_TO_CPU, VRRP, false),
 	/* PKT Sample trap */
 	MLXSW_RXL(mlxsw_sp_rx_listener_sample_func, PKT_SAMPLE, MIRROR_TO_CPU,
 		  false, SP_IP2ME, DISCARD),
@@ -4483,6 +4483,10 @@ static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core)
 			rate = 19 * 1024;
 			burst_size = 12;
 			break;
+		case MLXSW_REG_HTGT_TRAP_GROUP_SP_VRRP:
+			rate = 360;
+			burst_size = 7;
+			break;
 		default:
 			continue;
 		}
@@ -4522,6 +4526,7 @@ static int mlxsw_sp_trap_groups_set(struct mlxsw_core *mlxsw_core)
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_OSPF:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_PIM:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP0:
+		case MLXSW_REG_HTGT_TRAP_GROUP_SP_VRRP:
 			priority = 5;
 			tc = 5;
 			break;
-- 
2.20.1


From 8fd2d0594038364858550185e36f372e76d6404f Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Sun, 22 Dec 2019 10:51:09 +0800
Subject: [PATCH 22/46] net: add bool confirm_neigh parameter for
 dst_ops.update_pmtu

[ Upstream commit bd085ef678b2cc8c38c105673dfe8ff8f5ec0c57 ]

The MTU update code is supposed to be invoked in response to real
networking events that update the PMTU. In IPv6 PMTU update function
__ip6_rt_update_pmtu() we called dst_confirm_neigh() to update neighbor
confirmed time.

But for tunnel code, it will call pmtu before xmit, like:
  - tnl_update_pmtu()
    - skb_dst_update_pmtu()
      - ip6_rt_update_pmtu()
        - __ip6_rt_update_pmtu()
          - dst_confirm_neigh()

If the tunnel remote dst mac address changed and we still do the neigh
confirm, we will not be able to update neigh cache and ping6 remote
will failed.

So for this ip_tunnel_xmit() case, _EVEN_ if the MTU is changed, we
should not be invoking dst_confirm_neigh() as we have no evidence
of successful two-way communication at this point.

On the other hand it is also important to keep the neigh reachability fresh
for TCP flows, so we cannot remove this dst_confirm_neigh() call.

To fix the issue, we have to add a new bool parameter for dst_ops.update_pmtu
to choose whether we should do neigh update or not. I will add the parameter
in this patch and set all the callers to true to comply with the previous
way, and fix the tunnel code one by one on later patches.

v5: No change.
v4: No change.
v3: Do not remove dst_confirm_neigh, but add a new bool parameter in
    dst_ops.update_pmtu to control whether we should do neighbor confirm.
    Also split the big patch to small ones for each area.
v2: Remove dst_confirm_neigh in __ip6_rt_update_pmtu.

Suggested-by: David Miller <davem@davemloft.net>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/gtp.c                |  2 +-
 include/net/dst.h                |  2 +-
 include/net/dst_ops.h            |  3 ++-
 net/bridge/br_nf_core.c          |  3 ++-
 net/decnet/dn_route.c            |  6 ++++--
 net/ipv4/inet_connection_sock.c  |  2 +-
 net/ipv4/route.c                 |  9 ++++++---
 net/ipv4/xfrm4_policy.c          |  5 +++--
 net/ipv6/inet6_connection_sock.c |  2 +-
 net/ipv6/ip6_gre.c               |  2 +-
 net/ipv6/route.c                 | 22 +++++++++++++++-------
 net/ipv6/xfrm6_policy.c          |  5 +++--
 net/netfilter/ipvs/ip_vs_xmit.c  |  2 +-
 net/sctp/transport.c             |  2 +-
 14 files changed, 42 insertions(+), 25 deletions(-)

diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index ecfe26215935..9cac0accba7a 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -541,7 +541,7 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev,
 		mtu = dst_mtu(&rt->dst);
 	}
 
-	rt->dst.ops->update_pmtu(&rt->dst, NULL, skb, mtu);
+	rt->dst.ops->update_pmtu(&rt->dst, NULL, skb, mtu, true);
 
 	if (!skb_is_gso(skb) && (iph->frag_off & htons(IP_DF)) &&
 	    mtu < ntohs(iph->tot_len)) {
diff --git a/include/net/dst.h b/include/net/dst.h
index 8224dad2ae94..593630e0e076 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -516,7 +516,7 @@ static inline void skb_dst_update_pmtu(struct sk_buff *skb, u32 mtu)
 	struct dst_entry *dst = skb_dst(skb);
 
 	if (dst && dst->ops->update_pmtu)
-		dst->ops->update_pmtu(dst, NULL, skb, mtu);
+		dst->ops->update_pmtu(dst, NULL, skb, mtu, true);
 }
 
 static inline void skb_tunnel_check_pmtu(struct sk_buff *skb,
diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h
index 5ec645f27ee3..443863c7b8da 100644
--- a/include/net/dst_ops.h
+++ b/include/net/dst_ops.h
@@ -27,7 +27,8 @@ struct dst_ops {
 	struct dst_entry *	(*negative_advice)(struct dst_entry *);
 	void			(*link_failure)(struct sk_buff *);
 	void			(*update_pmtu)(struct dst_entry *dst, struct sock *sk,
-					       struct sk_buff *skb, u32 mtu);
+					       struct sk_buff *skb, u32 mtu,
+					       bool confirm_neigh);
 	void			(*redirect)(struct dst_entry *dst, struct sock *sk,
 					    struct sk_buff *skb);
 	int			(*local_out)(struct net *net, struct sock *sk, struct sk_buff *skb);
diff --git a/net/bridge/br_nf_core.c b/net/bridge/br_nf_core.c
index 2cdfc5d6c25d..8c69f0c95a8e 100644
--- a/net/bridge/br_nf_core.c
+++ b/net/bridge/br_nf_core.c
@@ -22,7 +22,8 @@
 #endif
 
 static void fake_update_pmtu(struct dst_entry *dst, struct sock *sk,
-			     struct sk_buff *skb, u32 mtu)
+			     struct sk_buff *skb, u32 mtu,
+			     bool confirm_neigh)
 {
 }
 
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index aea918135ec3..08c3dc45f1a4 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -110,7 +110,8 @@ static void dn_dst_ifdown(struct dst_entry *, struct net_device *dev, int how);
 static struct dst_entry *dn_dst_negative_advice(struct dst_entry *);
 static void dn_dst_link_failure(struct sk_buff *);
 static void dn_dst_update_pmtu(struct dst_entry *dst, struct sock *sk,
-			       struct sk_buff *skb , u32 mtu);
+			       struct sk_buff *skb , u32 mtu,
+			       bool confirm_neigh);
 static void dn_dst_redirect(struct dst_entry *dst, struct sock *sk,
 			    struct sk_buff *skb);
 static struct neighbour *dn_dst_neigh_lookup(const struct dst_entry *dst,
@@ -251,7 +252,8 @@ static int dn_dst_gc(struct dst_ops *ops)
  * advertise to the other end).
  */
 static void dn_dst_update_pmtu(struct dst_entry *dst, struct sock *sk,
-			       struct sk_buff *skb, u32 mtu)
+			       struct sk_buff *skb, u32 mtu,
+			       bool confirm_neigh)
 {
 	struct dn_route *rt = (struct dn_route *) dst;
 	struct neighbour *n = rt->n;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index eb30fc1770de..ac05e273bc66 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -1086,7 +1086,7 @@ struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu)
 		if (!dst)
 			goto out;
 	}
-	dst->ops->update_pmtu(dst, sk, NULL, mtu);
+	dst->ops->update_pmtu(dst, sk, NULL, mtu, true);
 
 	dst = __sk_dst_check(sk, 0);
 	if (!dst)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 621f83434b24..fe34e9e0912a 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -139,7 +139,8 @@ static unsigned int	 ipv4_mtu(const struct dst_entry *dst);
 static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst);
 static void		 ipv4_link_failure(struct sk_buff *skb);
 static void		 ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
-					   struct sk_buff *skb, u32 mtu);
+					   struct sk_buff *skb, u32 mtu,
+					   bool confirm_neigh);
 static void		 ip_do_redirect(struct dst_entry *dst, struct sock *sk,
 					struct sk_buff *skb);
 static void		ipv4_dst_destroy(struct dst_entry *dst);
@@ -1043,7 +1044,8 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
 }
 
 static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
-			      struct sk_buff *skb, u32 mtu)
+			      struct sk_buff *skb, u32 mtu,
+			      bool confirm_neigh)
 {
 	struct rtable *rt = (struct rtable *) dst;
 	struct flowi4 fl4;
@@ -2648,7 +2650,8 @@ static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst)
 }
 
 static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
-					  struct sk_buff *skb, u32 mtu)
+					  struct sk_buff *skb, u32 mtu,
+					  bool confirm_neigh)
 {
 }
 
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 35b84b52b702..9ebd54752e03 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -100,12 +100,13 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
 }
 
 static void xfrm4_update_pmtu(struct dst_entry *dst, struct sock *sk,
-			      struct sk_buff *skb, u32 mtu)
+			      struct sk_buff *skb, u32 mtu,
+			      bool confirm_neigh)
 {
 	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
 	struct dst_entry *path = xdst->route;
 
-	path->ops->update_pmtu(path, sk, skb, mtu);
+	path->ops->update_pmtu(path, sk, skb, mtu, confirm_neigh);
 }
 
 static void xfrm4_redirect(struct dst_entry *dst, struct sock *sk,
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index fe9cb8d1adca..e315526fa244 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -146,7 +146,7 @@ struct dst_entry *inet6_csk_update_pmtu(struct sock *sk, u32 mtu)
 
 	if (IS_ERR(dst))
 		return NULL;
-	dst->ops->update_pmtu(dst, sk, NULL, mtu);
+	dst->ops->update_pmtu(dst, sk, NULL, mtu, true);
 
 	dst = inet6_csk_route_socket(sk, &fl6);
 	return IS_ERR(dst) ? NULL : dst;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 923034c52ce4..071cb237f00b 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1040,7 +1040,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 
 	/* TooBig packet may have updated dst->dev's mtu */
 	if (!t->parms.collect_md && dst && dst_mtu(dst) > dst->dev->mtu)
-		dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu);
+		dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu, true);
 
 	err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu,
 			   NEXTHDR_GRE);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 3f83ea851ebf..e4ed9c7b43b0 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -95,7 +95,8 @@ static int		ip6_pkt_prohibit(struct sk_buff *skb);
 static int		ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff *skb);
 static void		ip6_link_failure(struct sk_buff *skb);
 static void		ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
-					   struct sk_buff *skb, u32 mtu);
+					   struct sk_buff *skb, u32 mtu,
+					   bool confirm_neigh);
 static void		rt6_do_redirect(struct dst_entry *dst, struct sock *sk,
 					struct sk_buff *skb);
 static int rt6_score_route(const struct fib6_nh *nh, u32 fib6_flags, int oif,
@@ -264,7 +265,8 @@ static unsigned int ip6_blackhole_mtu(const struct dst_entry *dst)
 }
 
 static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
-					 struct sk_buff *skb, u32 mtu)
+					 struct sk_buff *skb, u32 mtu,
+					 bool confirm_neigh)
 {
 }
 
@@ -2695,7 +2697,8 @@ static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt)
 }
 
 static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
-				 const struct ipv6hdr *iph, u32 mtu)
+				 const struct ipv6hdr *iph, u32 mtu,
+				 bool confirm_neigh)
 {
 	const struct in6_addr *daddr, *saddr;
 	struct rt6_info *rt6 = (struct rt6_info *)dst;
@@ -2713,7 +2716,10 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
 		daddr = NULL;
 		saddr = NULL;
 	}
-	dst_confirm_neigh(dst, daddr);
+
+	if (confirm_neigh)
+		dst_confirm_neigh(dst, daddr);
+
 	mtu = max_t(u32, mtu, IPV6_MIN_MTU);
 	if (mtu >= dst_mtu(dst))
 		return;
@@ -2767,9 +2773,11 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
 }
 
 static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
-			       struct sk_buff *skb, u32 mtu)
+			       struct sk_buff *skb, u32 mtu,
+			       bool confirm_neigh)
 {
-	__ip6_rt_update_pmtu(dst, sk, skb ? ipv6_hdr(skb) : NULL, mtu);
+	__ip6_rt_update_pmtu(dst, sk, skb ? ipv6_hdr(skb) : NULL, mtu,
+			     confirm_neigh);
 }
 
 void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
@@ -2788,7 +2796,7 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
 
 	dst = ip6_route_output(net, NULL, &fl6);
 	if (!dst->error)
-		__ip6_rt_update_pmtu(dst, NULL, iph, ntohl(mtu));
+		__ip6_rt_update_pmtu(dst, NULL, iph, ntohl(mtu), true);
 	dst_release(dst);
 }
 EXPORT_SYMBOL_GPL(ip6_update_pmtu);
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 699e0730ce8e..af7a4b8b1e9c 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -98,12 +98,13 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
 }
 
 static void xfrm6_update_pmtu(struct dst_entry *dst, struct sock *sk,
-			      struct sk_buff *skb, u32 mtu)
+			      struct sk_buff *skb, u32 mtu,
+			      bool confirm_neigh)
 {
 	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
 	struct dst_entry *path = xdst->route;
 
-	path->ops->update_pmtu(path, sk, skb, mtu);
+	path->ops->update_pmtu(path, sk, skb, mtu, confirm_neigh);
 }
 
 static void xfrm6_redirect(struct dst_entry *dst, struct sock *sk,
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 888d3068a492..c62a131a6094 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -208,7 +208,7 @@ static inline void maybe_update_pmtu(int skb_af, struct sk_buff *skb, int mtu)
 	struct rtable *ort = skb_rtable(skb);
 
 	if (!skb->dev && sk && sk_fullsock(sk))
-		ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu);
+		ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu, true);
 }
 
 static inline bool ensure_mtu_is_adequate(struct netns_ipvs *ipvs, int skb_af,
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index 7235a6032671..3bbe1a58ec87 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -263,7 +263,7 @@ bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu)
 
 		pf->af->from_sk(&addr, sk);
 		pf->to_sk_daddr(&t->ipaddr, sk);
-		dst->ops->update_pmtu(dst, sk, NULL, pmtu);
+		dst->ops->update_pmtu(dst, sk, NULL, pmtu, true);
 		pf->to_sk_daddr(&addr, sk);
 
 		dst = sctp_transport_dst_check(t);
-- 
2.20.1


From bcb5d346947e0add0e276b8587d829b22bfc72eb Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Sun, 22 Dec 2019 10:51:10 +0800
Subject: [PATCH 23/46] ip6_gre: do not confirm neighbor when do pmtu update

[ Upstream commit 675d76ad0ad5bf41c9a129772ef0aba8f57ea9a7 ]

When we do ipv6 gre pmtu update, we will also do neigh confirm currently.
This will cause the neigh cache be refreshed and set to REACHABLE before
xmit.

But if the remote mac address changed, e.g. device is deleted and recreated,
we will not able to notice this and still use the old mac address as the neigh
cache is REACHABLE.

Fix this by disable neigh confirm when do pmtu update

v5: No change.
v4: No change.
v3: Do not remove dst_confirm_neigh, but add a new bool parameter in
    dst_ops.update_pmtu to control whether we should do neighbor confirm.
    Also split the big patch to small ones for each area.
v2: Remove dst_confirm_neigh in __ip6_rt_update_pmtu.

Reported-by: Jianlin Shi <jishi@redhat.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 071cb237f00b..189de56f5e36 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1040,7 +1040,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 
 	/* TooBig packet may have updated dst->dev's mtu */
 	if (!t->parms.collect_md && dst && dst_mtu(dst) > dst->dev->mtu)
-		dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu, true);
+		dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu, false);
 
 	err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu,
 			   NEXTHDR_GRE);
-- 
2.20.1


From dcf507a5b54c9d62dac837c533dac2eea6f3815c Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Sun, 22 Dec 2019 10:51:11 +0800
Subject: [PATCH 24/46] gtp: do not confirm neighbor when do pmtu update

[ Upstream commit 6e9105c73f8d2163d12d5dfd762fd75483ed30f5 ]

When do IPv6 tunnel PMTU update and calls __ip6_rt_update_pmtu() in the end,
we should not call dst_confirm_neigh() as there is no two-way communication.

Although GTP only support ipv4 right now, and __ip_rt_update_pmtu() does not
call dst_confirm_neigh(), we still set it to false to keep consistency with
IPv6 code.

v5: No change.
v4: No change.
v3: Do not remove dst_confirm_neigh, but add a new bool parameter in
    dst_ops.update_pmtu to control whether we should do neighbor confirm.
    Also split the big patch to small ones for each area.
v2: Remove dst_confirm_neigh in __ip6_rt_update_pmtu.

Reviewed-by: Guillaume Nault <gnault@redhat.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/gtp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 9cac0accba7a..71b34ff8e7eb 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -541,7 +541,7 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev,
 		mtu = dst_mtu(&rt->dst);
 	}
 
-	rt->dst.ops->update_pmtu(&rt->dst, NULL, skb, mtu, true);
+	rt->dst.ops->update_pmtu(&rt->dst, NULL, skb, mtu, false);
 
 	if (!skb_is_gso(skb) && (iph->frag_off & htons(IP_DF)) &&
 	    mtu < ntohs(iph->tot_len)) {
-- 
2.20.1


From e42e01994b64b307c296e508ee1beeffc8603168 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Sun, 22 Dec 2019 10:51:12 +0800
Subject: [PATCH 25/46] net/dst: add new function
 skb_dst_update_pmtu_no_confirm

[ Upstream commit 07dc35c6e3cc3c001915d05f5bf21f80a39a0970 ]

Add a new function skb_dst_update_pmtu_no_confirm() for callers who need
update pmtu but should not do neighbor confirm.

v5: No change.
v4: No change.
v3: Do not remove dst_confirm_neigh, but add a new bool parameter in
    dst_ops.update_pmtu to control whether we should do neighbor confirm.
    Also split the big patch to small ones for each area.
v2: Remove dst_confirm_neigh in __ip6_rt_update_pmtu.

Reviewed-by: Guillaume Nault <gnault@redhat.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst.h | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/include/net/dst.h b/include/net/dst.h
index 593630e0e076..dc7cc1f1051c 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -519,6 +519,15 @@ static inline void skb_dst_update_pmtu(struct sk_buff *skb, u32 mtu)
 		dst->ops->update_pmtu(dst, NULL, skb, mtu, true);
 }
 
+/* update dst pmtu but not do neighbor confirm */
+static inline void skb_dst_update_pmtu_no_confirm(struct sk_buff *skb, u32 mtu)
+{
+	struct dst_entry *dst = skb_dst(skb);
+
+	if (dst && dst->ops->update_pmtu)
+		dst->ops->update_pmtu(dst, NULL, skb, mtu, false);
+}
+
 static inline void skb_tunnel_check_pmtu(struct sk_buff *skb,
 					 struct dst_entry *encap_dst,
 					 int headroom)
-- 
2.20.1


From fb5c7dd9db39c7fc981b386b7f46233d68e4ba44 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Sun, 22 Dec 2019 10:51:13 +0800
Subject: [PATCH 26/46] tunnel: do not confirm neighbor when do pmtu update

[ Upstream commit 7a1592bcb15d71400a98632727791d1e68ea0ee8 ]

When do tunnel PMTU update and calls __ip6_rt_update_pmtu() in the end,
we should not call dst_confirm_neigh() as there is no two-way communication.

v5: No Change.
v4: Update commit description
v3: Do not remove dst_confirm_neigh, but add a new bool parameter in
    dst_ops.update_pmtu to control whether we should do neighbor confirm.
    Also split the big patch to small ones for each area.
v2: Remove dst_confirm_neigh in __ip6_rt_update_pmtu.

Fixes: 0dec879f636f ("net: use dst_confirm_neigh for UDP, RAW, ICMP, L2TP")
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Tested-by: Guillaume Nault <gnault@redhat.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_tunnel.c  | 2 +-
 net/ipv6/ip6_tunnel.c | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 38c02bb62e2c..0fe2a5d3e258 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -505,7 +505,7 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
 		mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
 
 	if (skb_valid_dst(skb))
-		skb_dst_update_pmtu(skb, mtu);
+		skb_dst_update_pmtu_no_confirm(skb, mtu);
 
 	if (skb->protocol == htons(ETH_P_IP)) {
 		if (!skb_is_gso(skb) &&
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 754a484d35df..2f376dbc37d5 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -640,7 +640,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		if (rel_info > dst_mtu(skb_dst(skb2)))
 			goto out;
 
-		skb_dst_update_pmtu(skb2, rel_info);
+		skb_dst_update_pmtu_no_confirm(skb2, rel_info);
 	}
 
 	icmp_send(skb2, rel_type, rel_code, htonl(rel_info));
@@ -1132,7 +1132,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 	mtu = max(mtu, skb->protocol == htons(ETH_P_IPV6) ?
 		       IPV6_MIN_MTU : IPV4_MIN_MTU);
 
-	skb_dst_update_pmtu(skb, mtu);
+	skb_dst_update_pmtu_no_confirm(skb, mtu);
 	if (skb->len - t->tun_hlen - eth_hlen > mtu && !skb_is_gso(skb)) {
 		*pmtu = mtu;
 		err = -EMSGSIZE;
-- 
2.20.1


From 7bc3c70df610e6933127e27bb910dacee2dda370 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Sun, 22 Dec 2019 10:51:14 +0800
Subject: [PATCH 27/46] vti: do not confirm neighbor when do pmtu update

[ Upstream commit 8247a79efa2f28b44329f363272550c1738377de ]

When do IPv6 tunnel PMTU update and calls __ip6_rt_update_pmtu() in the end,
we should not call dst_confirm_neigh() as there is no two-way communication.

Although vti and vti6 are immune to this problem because they are IFF_NOARP
interfaces, as Guillaume pointed. There is still no sense to confirm neighbour
here.

v5: Update commit description.
v4: No change.
v3: Do not remove dst_confirm_neigh, but add a new bool parameter in
    dst_ops.update_pmtu to control whether we should do neighbor confirm.
    Also split the big patch to small ones for each area.
v2: Remove dst_confirm_neigh in __ip6_rt_update_pmtu.

Reviewed-by: Guillaume Nault <gnault@redhat.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_vti.c  | 2 +-
 net/ipv6/ip6_vti.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index cfb025606793..fb9f6d60c27c 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -214,7 +214,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
 
 	mtu = dst_mtu(dst);
 	if (skb->len > mtu) {
-		skb_dst_update_pmtu(skb, mtu);
+		skb_dst_update_pmtu_no_confirm(skb, mtu);
 		if (skb->protocol == htons(ETH_P_IP)) {
 			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
 				  htonl(mtu));
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 024db17386d2..6f08b760c2a7 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -479,7 +479,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 
 	mtu = dst_mtu(dst);
 	if (skb->len > mtu) {
-		skb_dst_update_pmtu(skb, mtu);
+		skb_dst_update_pmtu_no_confirm(skb, mtu);
 
 		if (skb->protocol == htons(ETH_P_IPV6)) {
 			if (mtu < IPV6_MIN_MTU)
-- 
2.20.1


From 64cc371e5ca8727135cc36b5630c7b6a41dfd4a3 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Sun, 22 Dec 2019 10:51:15 +0800
Subject: [PATCH 28/46] sit: do not confirm neighbor when do pmtu update

[ Upstream commit 4d42df46d6372ece4cb4279870b46c2ea7304a47 ]

When do IPv6 tunnel PMTU update and calls __ip6_rt_update_pmtu() in the end,
we should not call dst_confirm_neigh() as there is no two-way communication.

v5: No change.
v4: No change.
v3: Do not remove dst_confirm_neigh, but add a new bool parameter in
    dst_ops.update_pmtu to control whether we should do neighbor confirm.
    Also split the big patch to small ones for each area.
v2: Remove dst_confirm_neigh in __ip6_rt_update_pmtu.

Reviewed-by: Guillaume Nault <gnault@redhat.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index b2ccbc473127..98954830c40b 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -944,7 +944,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 		}
 
 		if (tunnel->parms.iph.daddr)
-			skb_dst_update_pmtu(skb, mtu);
+			skb_dst_update_pmtu_no_confirm(skb, mtu);
 
 		if (skb->len > mtu && !skb_is_gso(skb)) {
 			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
-- 
2.20.1


From 604eea988dc00a2614ba1e614cf0ad81ad307468 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Sun, 22 Dec 2019 10:51:16 +0800
Subject: [PATCH 29/46] net/dst: do not confirm neighbor for vxlan and geneve
 pmtu update

[ Upstream commit f081042d128a0c7acbd67611def62e1b52e2d294 ]

When do IPv6 tunnel PMTU update and calls __ip6_rt_update_pmtu() in the end,
we should not call dst_confirm_neigh() as there is no two-way communication.

So disable the neigh confirm for vxlan and geneve pmtu update.

v5: No change.
v4: No change.
v3: Do not remove dst_confirm_neigh, but add a new bool parameter in
    dst_ops.update_pmtu to control whether we should do neighbor confirm.
    Also split the big patch to small ones for each area.
v2: Remove dst_confirm_neigh in __ip6_rt_update_pmtu.

Fixes: a93bf0ff4490 ("vxlan: update skb dst pmtu on tx path")
Fixes: 52a589d51f10 ("geneve: update skb dst pmtu on tx path")
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Tested-by: Guillaume Nault <gnault@redhat.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/dst.h b/include/net/dst.h
index dc7cc1f1051c..3448cf865ede 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -535,7 +535,7 @@ static inline void skb_tunnel_check_pmtu(struct sk_buff *skb,
 	u32 encap_mtu = dst_mtu(encap_dst);
 
 	if (skb->len > encap_mtu - headroom)
-		skb_dst_update_pmtu(skb, encap_mtu - headroom);
+		skb_dst_update_pmtu_no_confirm(skb, encap_mtu - headroom);
 }
 
 #endif /* _NET_DST_H */
-- 
2.20.1


From 09889c7fc7700e299b0fa18116d797c1fc4d5025 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Fri, 27 Dec 2019 03:11:13 +0200
Subject: [PATCH 30/46] net: dsa: sja1105: Reconcile the meaning of TPID and
 TPID2 for E/T and P/Q/R/S

[ Upstream commit 54fa49ee88138756df0fcf867cb1849904710a8c ]

For first-generation switches (SJA1105E and SJA1105T):
- TPID means C-Tag (typically 0x8100)
- TPID2 means S-Tag (typically 0x88A8)

While for the second generation switches (SJA1105P, SJA1105Q, SJA1105R,
SJA1105S) it is the other way around:
- TPID means S-Tag (typically 0x88A8)
- TPID2 means C-Tag (typically 0x8100)

In other words, E/T tags untagged traffic with TPID, and P/Q/R/S with
TPID2.

So the patch mentioned below fixed VLAN filtering for P/Q/R/S, but broke
it for E/T.

We strive for a common code path for all switches in the family, so just
lie in the static config packing functions that TPID and TPID2 are at
swapped bit offsets than they actually are, for P/Q/R/S. This will make
both switches understand TPID to be ETH_P_8021Q and TPID2 to be
ETH_P_8021AD. The meaning from the original E/T was chosen over P/Q/R/S
because E/T is actually the one with public documentation available
(UM10944.pdf).

Fixes: f9a1a7646c0d ("net: dsa: sja1105: Reverse TPID and TPID2")
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/sja1105/sja1105_main.c          | 8 ++++----
 drivers/net/dsa/sja1105/sja1105_static_config.c | 7 +++++--
 2 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index 4e5a428ab1a4..7763221286d4 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -1560,8 +1560,8 @@ static int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled)
 
 	if (enabled) {
 		/* Enable VLAN filtering. */
-		tpid  = ETH_P_8021AD;
-		tpid2 = ETH_P_8021Q;
+		tpid  = ETH_P_8021Q;
+		tpid2 = ETH_P_8021AD;
 	} else {
 		/* Disable VLAN filtering. */
 		tpid  = ETH_P_SJA1105;
@@ -1570,9 +1570,9 @@ static int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled)
 
 	table = &priv->static_config.tables[BLK_IDX_GENERAL_PARAMS];
 	general_params = table->entries;
-	/* EtherType used to identify outer tagged (S-tag) VLAN traffic */
-	general_params->tpid = tpid;
 	/* EtherType used to identify inner tagged (C-tag) VLAN traffic */
+	general_params->tpid = tpid;
+	/* EtherType used to identify outer tagged (S-tag) VLAN traffic */
 	general_params->tpid2 = tpid2;
 	/* When VLAN filtering is on, we need to at least be able to
 	 * decode management traffic through the "backup plan".
diff --git a/drivers/net/dsa/sja1105/sja1105_static_config.c b/drivers/net/dsa/sja1105/sja1105_static_config.c
index 0d03e13e9909..63d2311817c4 100644
--- a/drivers/net/dsa/sja1105/sja1105_static_config.c
+++ b/drivers/net/dsa/sja1105/sja1105_static_config.c
@@ -142,6 +142,9 @@ static size_t sja1105et_general_params_entry_packing(void *buf, void *entry_ptr,
 	return size;
 }
 
+/* TPID and TPID2 are intentionally reversed so that semantic
+ * compatibility with E/T is kept.
+ */
 static size_t
 sja1105pqrs_general_params_entry_packing(void *buf, void *entry_ptr,
 					 enum packing_op op)
@@ -166,9 +169,9 @@ sja1105pqrs_general_params_entry_packing(void *buf, void *entry_ptr,
 	sja1105_packing(buf, &entry->mirr_port,   141, 139, size, op);
 	sja1105_packing(buf, &entry->vlmarker,    138, 107, size, op);
 	sja1105_packing(buf, &entry->vlmask,      106,  75, size, op);
-	sja1105_packing(buf, &entry->tpid,         74,  59, size, op);
+	sja1105_packing(buf, &entry->tpid2,        74,  59, size, op);
 	sja1105_packing(buf, &entry->ignore2stf,   58,  58, size, op);
-	sja1105_packing(buf, &entry->tpid2,        57,  42, size, op);
+	sja1105_packing(buf, &entry->tpid,         57,  42, size, op);
 	sja1105_packing(buf, &entry->queue_ts,     41,  41, size, op);
 	sja1105_packing(buf, &entry->egrmirrvid,   40,  29, size, op);
 	sja1105_packing(buf, &entry->egrmirrpcp,   28,  26, size, op);
-- 
2.20.1


From 8fd6946a193f6804f4bde7e71db019682f8e5868 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Tue, 10 Dec 2019 22:33:05 +0000
Subject: [PATCH 31/46] net: marvell: mvpp2: phylink requires the link
 interrupt

[ Upstream commit f3f2364ea14d1cf6bf966542f31eadcf178f1577 ]

phylink requires the MAC to report when its link status changes when
operating in inband modes.  Failure to report link status changes
means that phylink has no idea when the link events happen, which
results in either the network interface's carrier remaining up or
remaining permanently down.

For example, with a fiber module, if the interface is brought up and
link is initially established, taking the link down at the far end
will cut the optical power.  The SFP module's LOS asserts, we
deactivate the link, and the network interface reports no carrier.

When the far end is brought back up, the SFP module's LOS deasserts,
but the MAC may be slower to establish link.  If this happens (which
in my tests is a certainty) then phylink never hears that the MAC
has established link with the far end, and the network interface is
stuck reporting no carrier.  This means the interface is
non-functional.

Avoiding the link interrupt when we have phylink is basically not
an option, so remove the !port->phylink from the test.

Fixes: 4bb043262878 ("net: mvpp2: phylink support")
Tested-by: Sven Auhagen <sven.auhagen@voleatech.de>
Tested-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 111b3b8239e1..ef44c6979a31 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -3674,7 +3674,7 @@ static int mvpp2_open(struct net_device *dev)
 		valid = true;
 	}
 
-	if (priv->hw_version == MVPP22 && port->link_irq && !port->phylink) {
+	if (priv->hw_version == MVPP22 && port->link_irq) {
 		err = request_irq(port->link_irq, mvpp2_link_status_isr, 0,
 				  dev->name, port);
 		if (err) {
-- 
2.20.1


From 28db4d9f80ddeb83db018e07309ff202bdc75dcc Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Wed, 11 Dec 2019 08:23:17 +0000
Subject: [PATCH 32/46] gtp: fix wrong condition in gtp_genl_dump_pdp()

[ Upstream commit 94a6d9fb88df43f92d943c32b84ce398d50bf49f ]

gtp_genl_dump_pdp() is ->dumpit() callback of GTP module and it is used
to dump pdp contexts. it would be re-executed because of dump packet size.

If dump packet size is too big, it saves current dump pointer
(gtp interface pointer, bucket, TID value) then it restarts dump from
last pointer.
Current GTP code allows adding zero TID pdp context but dump code
ignores zero TID value. So, last dump pointer will not be found.

In addition, this patch adds missing rcu_read_lock() in
gtp_genl_dump_pdp().

Fixes: 459aa660eb1d ("gtp: add initial driver for datapath of GPRS Tunneling Protocol (GTP-U)")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/gtp.c | 36 +++++++++++++++++++-----------------
 1 file changed, 19 insertions(+), 17 deletions(-)

diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 71b34ff8e7eb..7bbc1be3490d 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -38,7 +38,6 @@ struct pdp_ctx {
 	struct hlist_node	hlist_addr;
 
 	union {
-		u64		tid;
 		struct {
 			u64	tid;
 			u16	flow;
@@ -1232,43 +1231,46 @@ static int gtp_genl_dump_pdp(struct sk_buff *skb,
 				struct netlink_callback *cb)
 {
 	struct gtp_dev *last_gtp = (struct gtp_dev *)cb->args[2], *gtp;
+	int i, j, bucket = cb->args[0], skip = cb->args[1];
 	struct net *net = sock_net(skb->sk);
-	struct gtp_net *gn = net_generic(net, gtp_net_id);
-	unsigned long tid = cb->args[1];
-	int i, k = cb->args[0], ret;
 	struct pdp_ctx *pctx;
+	struct gtp_net *gn;
+
+	gn = net_generic(net, gtp_net_id);
 
 	if (cb->args[4])
 		return 0;
 
+	rcu_read_lock();
 	list_for_each_entry_rcu(gtp, &gn->gtp_dev_list, list) {
 		if (last_gtp && last_gtp != gtp)
 			continue;
 		else
 			last_gtp = NULL;
 
-		for (i = k; i < gtp->hash_size; i++) {
-			hlist_for_each_entry_rcu(pctx, &gtp->tid_hash[i], hlist_tid) {
-				if (tid && tid != pctx->u.tid)
-					continue;
-				else
-					tid = 0;
-
-				ret = gtp_genl_fill_info(skb,
-							 NETLINK_CB(cb->skb).portid,
-							 cb->nlh->nlmsg_seq,
-							 cb->nlh->nlmsg_type, pctx);
-				if (ret < 0) {
+		for (i = bucket; i < gtp->hash_size; i++) {
+			j = 0;
+			hlist_for_each_entry_rcu(pctx, &gtp->tid_hash[i],
+						 hlist_tid) {
+				if (j >= skip &&
+				    gtp_genl_fill_info(skb,
+					    NETLINK_CB(cb->skb).portid,
+					    cb->nlh->nlmsg_seq,
+					    cb->nlh->nlmsg_type, pctx)) {
 					cb->args[0] = i;
-					cb->args[1] = pctx->u.tid;
+					cb->args[1] = j;
 					cb->args[2] = (unsigned long)gtp;
 					goto out;
 				}
+				j++;
 			}
+			skip = 0;
 		}
+		bucket = 0;
 	}
 	cb->args[4] = 1;
 out:
+	rcu_read_unlock();
 	return skb->len;
 }
 
-- 
2.20.1


From 1d2d865317d532e7fb1ea13e67868bb55769afc6 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Wed, 11 Dec 2019 08:23:48 +0000
Subject: [PATCH 33/46] gtp: avoid zero size hashtable

[ Upstream commit 6a902c0f31993ab02e1b6ea7085002b9c9083b6a ]

GTP default hashtable size is 1024 and userspace could set specific
hashtable size with IFLA_GTP_PDP_HASHSIZE. If hashtable size is set to 0
from userspace,  hashtable will not work and panic will occur.

Fixes: 459aa660eb1d ("gtp: add initial driver for datapath of GPRS Tunneling Protocol (GTP-U)")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/gtp.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 7bbc1be3490d..522802961712 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -660,10 +660,13 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev,
 	if (err < 0)
 		return err;
 
-	if (!data[IFLA_GTP_PDP_HASHSIZE])
+	if (!data[IFLA_GTP_PDP_HASHSIZE]) {
 		hashsize = 1024;
-	else
+	} else {
 		hashsize = nla_get_u32(data[IFLA_GTP_PDP_HASHSIZE]);
+		if (!hashsize)
+			hashsize = 1024;
+	}
 
 	err = gtp_hashtable_new(gtp, hashsize);
 	if (err < 0)
-- 
2.20.1


From 630c4dfca26bdf6bb03adddc926077fb177eeb03 Mon Sep 17 00:00:00 2001
From: Mahesh Bandewar <maheshb@google.com>
Date: Fri, 6 Dec 2019 15:44:55 -0800
Subject: [PATCH 34/46] bonding: fix active-backup transition after link
 failure

[ Upstream commit 5d485ed88d48f8101a2067348e267c0aaf4ed486 ]

After the recent fix in commit 1899bb325149 ("bonding: fix state
transition issue in link monitoring"), the active-backup mode with
miimon initially come-up fine but after a link-failure, both members
transition into backup state.

Following steps to reproduce the scenario (eth1 and eth2 are the
slaves of the bond):

    ip link set eth1 up
    ip link set eth2 down
    sleep 1
    ip link set eth2 up
    ip link set eth1 down
    cat /sys/class/net/eth1/bonding_slave/state
    cat /sys/class/net/eth2/bonding_slave/state

Fixes: 1899bb325149 ("bonding: fix state transition issue in link monitoring")
CC: Jay Vosburgh <jay.vosburgh@canonical.com>
Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Acked-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/bonding/bond_main.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index face00c622ed..7dcd709f4ac3 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2225,9 +2225,6 @@ static void bond_miimon_commit(struct bonding *bond)
 			} else if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
 				/* make it immediately active */
 				bond_set_active_slave(slave);
-			} else if (slave != primary) {
-				/* prevent it from being the active one */
-				bond_set_backup_slave(slave);
 			}
 
 			slave_info(bond->dev, slave->dev, "link status definitely up, %u Mbps %s duplex\n",
-- 
2.20.1


From d48203819f0f8f0b43f128d8aa08fc6d830e4cee Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 12 Dec 2019 10:32:13 -0800
Subject: [PATCH 35/46] 6pack,mkiss: fix possible deadlock

[ Upstream commit 5c9934b6767b16ba60be22ec3cbd4379ad64170d ]

We got another syzbot report [1] that tells us we must use
write_lock_irq()/write_unlock_irq() to avoid possible deadlock.

[1]

WARNING: inconsistent lock state
5.5.0-rc1-syzkaller #0 Not tainted
--------------------------------
inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-R} usage.
syz-executor826/9605 [HC1[1]:SC0[0]:HE0:SE1] takes:
ffffffff8a128718 (disc_data_lock){+-..}, at: sp_get.isra.0+0x1d/0xf0 drivers/net/ppp/ppp_synctty.c:138
{HARDIRQ-ON-W} state was registered at:
  lock_acquire+0x190/0x410 kernel/locking/lockdep.c:4485
  __raw_write_lock_bh include/linux/rwlock_api_smp.h:203 [inline]
  _raw_write_lock_bh+0x33/0x50 kernel/locking/spinlock.c:319
  sixpack_close+0x1d/0x250 drivers/net/hamradio/6pack.c:657
  tty_ldisc_close.isra.0+0x119/0x1a0 drivers/tty/tty_ldisc.c:489
  tty_set_ldisc+0x230/0x6b0 drivers/tty/tty_ldisc.c:585
  tiocsetd drivers/tty/tty_io.c:2337 [inline]
  tty_ioctl+0xe8d/0x14f0 drivers/tty/tty_io.c:2597
  vfs_ioctl fs/ioctl.c:47 [inline]
  file_ioctl fs/ioctl.c:545 [inline]
  do_vfs_ioctl+0x977/0x14e0 fs/ioctl.c:732
  ksys_ioctl+0xab/0xd0 fs/ioctl.c:749
  __do_sys_ioctl fs/ioctl.c:756 [inline]
  __se_sys_ioctl fs/ioctl.c:754 [inline]
  __x64_sys_ioctl+0x73/0xb0 fs/ioctl.c:754
  do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294
  entry_SYSCALL_64_after_hwframe+0x49/0xbe
irq event stamp: 3946
hardirqs last  enabled at (3945): [<ffffffff87c86e43>] __raw_spin_unlock_irq include/linux/spinlock_api_smp.h:168 [inline]
hardirqs last  enabled at (3945): [<ffffffff87c86e43>] _raw_spin_unlock_irq+0x23/0x80 kernel/locking/spinlock.c:199
hardirqs last disabled at (3946): [<ffffffff8100675f>] trace_hardirqs_off_thunk+0x1a/0x1c arch/x86/entry/thunk_64.S:42
softirqs last  enabled at (2658): [<ffffffff86a8b4df>] spin_unlock_bh include/linux/spinlock.h:383 [inline]
softirqs last  enabled at (2658): [<ffffffff86a8b4df>] clusterip_netdev_event+0x46f/0x670 net/ipv4/netfilter/ipt_CLUSTERIP.c:222
softirqs last disabled at (2656): [<ffffffff86a8b22b>] spin_lock_bh include/linux/spinlock.h:343 [inline]
softirqs last disabled at (2656): [<ffffffff86a8b22b>] clusterip_netdev_event+0x1bb/0x670 net/ipv4/netfilter/ipt_CLUSTERIP.c:196

other info that might help us debug this:
 Possible unsafe locking scenario:

       CPU0
       ----
  lock(disc_data_lock);
  <Interrupt>
    lock(disc_data_lock);

 *** DEADLOCK ***

5 locks held by syz-executor826/9605:
 #0: ffff8880a905e198 (&tty->legacy_mutex){+.+.}, at: tty_lock+0xc7/0x130 drivers/tty/tty_mutex.c:19
 #1: ffffffff899a56c0 (rcu_read_lock){....}, at: mutex_spin_on_owner+0x0/0x330 kernel/locking/mutex.c:413
 #2: ffff8880a496a2b0 (&(&i->lock)->rlock){-.-.}, at: spin_lock include/linux/spinlock.h:338 [inline]
 #2: ffff8880a496a2b0 (&(&i->lock)->rlock){-.-.}, at: serial8250_interrupt+0x2d/0x1a0 drivers/tty/serial/8250/8250_core.c:116
 #3: ffffffff8c104048 (&port_lock_key){-.-.}, at: serial8250_handle_irq.part.0+0x24/0x330 drivers/tty/serial/8250/8250_port.c:1823
 #4: ffff8880a905e090 (&tty->ldisc_sem){++++}, at: tty_ldisc_ref+0x22/0x90 drivers/tty/tty_ldisc.c:288

stack backtrace:
CPU: 1 PID: 9605 Comm: syz-executor826 Not tainted 5.5.0-rc1-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x197/0x210 lib/dump_stack.c:118
 print_usage_bug.cold+0x327/0x378 kernel/locking/lockdep.c:3101
 valid_state kernel/locking/lockdep.c:3112 [inline]
 mark_lock_irq kernel/locking/lockdep.c:3309 [inline]
 mark_lock+0xbb4/0x1220 kernel/locking/lockdep.c:3666
 mark_usage kernel/locking/lockdep.c:3554 [inline]
 __lock_acquire+0x1e55/0x4a00 kernel/locking/lockdep.c:3909
 lock_acquire+0x190/0x410 kernel/locking/lockdep.c:4485
 __raw_read_lock include/linux/rwlock_api_smp.h:149 [inline]
 _raw_read_lock+0x32/0x50 kernel/locking/spinlock.c:223
 sp_get.isra.0+0x1d/0xf0 drivers/net/ppp/ppp_synctty.c:138
 sixpack_write_wakeup+0x25/0x340 drivers/net/hamradio/6pack.c:402
 tty_wakeup+0xe9/0x120 drivers/tty/tty_io.c:536
 tty_port_default_wakeup+0x2b/0x40 drivers/tty/tty_port.c:50
 tty_port_tty_wakeup+0x57/0x70 drivers/tty/tty_port.c:387
 uart_write_wakeup+0x46/0x70 drivers/tty/serial/serial_core.c:104
 serial8250_tx_chars+0x495/0xaf0 drivers/tty/serial/8250/8250_port.c:1761
 serial8250_handle_irq.part.0+0x2a2/0x330 drivers/tty/serial/8250/8250_port.c:1834
 serial8250_handle_irq drivers/tty/serial/8250/8250_port.c:1820 [inline]
 serial8250_default_handle_irq+0xc0/0x150 drivers/tty/serial/8250/8250_port.c:1850
 serial8250_interrupt+0xf1/0x1a0 drivers/tty/serial/8250/8250_core.c:126
 __handle_irq_event_percpu+0x15d/0x970 kernel/irq/handle.c:149
 handle_irq_event_percpu+0x74/0x160 kernel/irq/handle.c:189
 handle_irq_event+0xa7/0x134 kernel/irq/handle.c:206
 handle_edge_irq+0x25e/0x8d0 kernel/irq/chip.c:830
 generic_handle_irq_desc include/linux/irqdesc.h:156 [inline]
 do_IRQ+0xde/0x280 arch/x86/kernel/irq.c:250
 common_interrupt+0xf/0xf arch/x86/entry/entry_64.S:607
 </IRQ>
RIP: 0010:cpu_relax arch/x86/include/asm/processor.h:685 [inline]
RIP: 0010:mutex_spin_on_owner+0x247/0x330 kernel/locking/mutex.c:579
Code: c3 be 08 00 00 00 4c 89 e7 e8 e5 06 59 00 4c 89 e0 48 c1 e8 03 42 80 3c 38 00 0f 85 e1 00 00 00 49 8b 04 24 a8 01 75 96 f3 90 <e9> 2f fe ff ff 0f 0b e8 0d 19 09 00 84 c0 0f 85 ff fd ff ff 48 c7
RSP: 0018:ffffc90001eafa20 EFLAGS: 00000246 ORIG_RAX: ffffffffffffffd7
RAX: 0000000000000000 RBX: ffff88809fd9e0c0 RCX: 1ffffffff13266dd
RDX: 0000000000000000 RSI: 0000000000000008 RDI: 0000000000000000
RBP: ffffc90001eafa60 R08: 1ffff11013d22898 R09: ffffed1013d22899
R10: ffffed1013d22898 R11: ffff88809e9144c7 R12: ffff8880a905e138
R13: ffff88809e9144c0 R14: 0000000000000000 R15: dffffc0000000000
 mutex_optimistic_spin kernel/locking/mutex.c:673 [inline]
 __mutex_lock_common kernel/locking/mutex.c:962 [inline]
 __mutex_lock+0x32b/0x13c0 kernel/locking/mutex.c:1106
 mutex_lock_nested+0x16/0x20 kernel/locking/mutex.c:1121
 tty_lock+0xc7/0x130 drivers/tty/tty_mutex.c:19
 tty_release+0xb5/0xe90 drivers/tty/tty_io.c:1665
 __fput+0x2ff/0x890 fs/file_table.c:280
 ____fput+0x16/0x20 fs/file_table.c:313
 task_work_run+0x145/0x1c0 kernel/task_work.c:113
 exit_task_work include/linux/task_work.h:22 [inline]
 do_exit+0x8e7/0x2ef0 kernel/exit.c:797
 do_group_exit+0x135/0x360 kernel/exit.c:895
 __do_sys_exit_group kernel/exit.c:906 [inline]
 __se_sys_exit_group kernel/exit.c:904 [inline]
 __x64_sys_exit_group+0x44/0x50 kernel/exit.c:904
 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x43fef8
Code: Bad RIP value.
RSP: 002b:00007ffdb07d2338 EFLAGS: 00000246 ORIG_RAX: 00000000000000e7
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 000000000043fef8
RDX: 0000000000000000 RSI: 000000000000003c RDI: 0000000000000000
RBP: 00000000004bf730 R08: 00000000000000e7 R09: ffffffffffffffd0
R10: 00000000004002c8 R11: 0000000000000246 R12: 0000000000000001
R13: 00000000006d1180 R14: 0000000000000000 R15: 0000000000000000

Fixes: 6e4e2f811bad ("6pack,mkiss: fix lock inconsistency")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/hamradio/6pack.c | 4 ++--
 drivers/net/hamradio/mkiss.c | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c
index 23281aeeb222..71d6629e65c9 100644
--- a/drivers/net/hamradio/6pack.c
+++ b/drivers/net/hamradio/6pack.c
@@ -654,10 +654,10 @@ static void sixpack_close(struct tty_struct *tty)
 {
 	struct sixpack *sp;
 
-	write_lock_bh(&disc_data_lock);
+	write_lock_irq(&disc_data_lock);
 	sp = tty->disc_data;
 	tty->disc_data = NULL;
-	write_unlock_bh(&disc_data_lock);
+	write_unlock_irq(&disc_data_lock);
 	if (!sp)
 		return;
 
diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c
index c5bfa19ddb93..deef14215110 100644
--- a/drivers/net/hamradio/mkiss.c
+++ b/drivers/net/hamradio/mkiss.c
@@ -773,10 +773,10 @@ static void mkiss_close(struct tty_struct *tty)
 {
 	struct mkiss *ax;
 
-	write_lock_bh(&disc_data_lock);
+	write_lock_irq(&disc_data_lock);
 	ax = tty->disc_data;
 	tty->disc_data = NULL;
-	write_unlock_bh(&disc_data_lock);
+	write_unlock_irq(&disc_data_lock);
 
 	if (!ax)
 		return;
-- 
2.20.1


From b734cc36c61c04d7d175e2568572a0ea992258b7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 12 Dec 2019 12:55:29 -0800
Subject: [PATCH 36/46] tcp: do not send empty skb from tcp_write_xmit()

[ Upstream commit 1f85e6267caca44b30c54711652b0726fadbb131 ]

Backport of commit fdfc5c8594c2 ("tcp: remove empty skb from
write queue in error cases") in linux-4.14 stable triggered
various bugs. One of them has been fixed in commit ba2ddb43f270
("tcp: Don't dequeue SYN/FIN-segments from write-queue"), but
we still have crashes in some occasions.

Root-cause is that when tcp_sendmsg() has allocated a fresh
skb and could not append a fragment before being blocked
in sk_stream_wait_memory(), tcp_write_xmit() might be called
and decide to send this fresh and empty skb.

Sending an empty packet is not only silly, it might have caused
many issues we had in the past with tp->packets_out being
out of sync.

Fixes: c65f7f00c587 ("[TCP]: Simplify SKB data portion allocation with NETIF_F_SG.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Christoph Paasch <cpaasch@apple.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Cc: Jason Baron <jbaron@akamai.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/ipv4/tcp_output.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index b89167fc14a3..0269584e9cf7 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2441,6 +2441,14 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 		if (tcp_small_queue_check(sk, skb, 0))
 			break;
 
+		/* Argh, we hit an empty skb(), presumably a thread
+		 * is sleeping in sendmsg()/sk_stream_wait_memory().
+		 * We do not want to send a pure-ack packet and have
+		 * a strange looking rtx queue with empty packet(s).
+		 */
+		if (TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq)
+			break;
+
 		if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp)))
 			break;
 
-- 
2.20.1


From 2fc8c34ab7e22dff2502e2edcb3034907b774390 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 13 Dec 2019 18:20:41 -0800
Subject: [PATCH 37/46] tcp/dccp: fix possible race __inet_lookup_established()

[ Upstream commit 8dbd76e79a16b45b2ccb01d2f2e08dbf64e71e40 ]

Michal Kubecek and Firo Yang did a very nice analysis of crashes
happening in __inet_lookup_established().

Since a TCP socket can go from TCP_ESTABLISH to TCP_LISTEN
(via a close()/socket()/listen() cycle) without a RCU grace period,
I should not have changed listeners linkage in their hash table.

They must use the nulls protocol (Documentation/RCU/rculist_nulls.txt),
so that a lookup can detect a socket in a hash list was moved in
another one.

Since we added code in commit d296ba60d8e2 ("soreuseport: Resolve
merge conflict for v4/v6 ordering fix"), we have to add
hlist_nulls_add_tail_rcu() helper.

Fixes: 3b24d854cb35 ("tcp/dccp: do not touch listener sk_refcnt under synflood")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Michal Kubecek <mkubecek@suse.cz>
Reported-by: Firo Yang <firo.yang@suse.com>
Reviewed-by: Michal Kubecek <mkubecek@suse.cz>
Link: https://lore.kernel.org/netdev/20191120083919.GH27852@unicorn.suse.cz/
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 include/linux/rculist_nulls.h | 37 +++++++++++++++++++++++++++++++++++
 include/net/inet_hashtables.h | 12 +++++++++---
 include/net/sock.h            |  5 +++++
 net/ipv4/inet_diag.c          |  3 ++-
 net/ipv4/inet_hashtables.c    | 16 +++++++--------
 net/ipv4/tcp_ipv4.c           |  7 ++++---
 6 files changed, 65 insertions(+), 15 deletions(-)

diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h
index bc8206a8f30e..61974c4c566b 100644
--- a/include/linux/rculist_nulls.h
+++ b/include/linux/rculist_nulls.h
@@ -100,6 +100,43 @@ static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n,
 		first->pprev = &n->next;
 }
 
+/**
+ * hlist_nulls_add_tail_rcu
+ * @n: the element to add to the hash list.
+ * @h: the list to add to.
+ *
+ * Description:
+ * Adds the specified element to the specified hlist_nulls,
+ * while permitting racing traversals.
+ *
+ * The caller must take whatever precautions are necessary
+ * (such as holding appropriate locks) to avoid racing
+ * with another list-mutation primitive, such as hlist_nulls_add_head_rcu()
+ * or hlist_nulls_del_rcu(), running on this same list.
+ * However, it is perfectly legal to run concurrently with
+ * the _rcu list-traversal primitives, such as
+ * hlist_nulls_for_each_entry_rcu(), used to prevent memory-consistency
+ * problems on Alpha CPUs.  Regardless of the type of CPU, the
+ * list-traversal primitive must be guarded by rcu_read_lock().
+ */
+static inline void hlist_nulls_add_tail_rcu(struct hlist_nulls_node *n,
+					    struct hlist_nulls_head *h)
+{
+	struct hlist_nulls_node *i, *last = NULL;
+
+	/* Note: write side code, so rcu accessors are not needed. */
+	for (i = h->first; !is_a_nulls(i); i = i->next)
+		last = i;
+
+	if (last) {
+		n->next = last->next;
+		n->pprev = &last->next;
+		rcu_assign_pointer(hlist_next_rcu(last), n);
+	} else {
+		hlist_nulls_add_head_rcu(n, h);
+	}
+}
+
 /**
  * hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type
  * @tpos:	the type * to use as a loop cursor.
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index af2b4c065a04..d0019d3395cf 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -103,13 +103,19 @@ struct inet_bind_hashbucket {
 	struct hlist_head	chain;
 };
 
-/*
- * Sockets can be hashed in established or listening table
+/* Sockets can be hashed in established or listening table.
+ * We must use different 'nulls' end-of-chain value for all hash buckets :
+ * A socket might transition from ESTABLISH to LISTEN state without
+ * RCU grace period. A lookup in ehash table needs to handle this case.
  */
+#define LISTENING_NULLS_BASE (1U << 29)
 struct inet_listen_hashbucket {
 	spinlock_t		lock;
 	unsigned int		count;
-	struct hlist_head	head;
+	union {
+		struct hlist_head	head;
+		struct hlist_nulls_head	nulls_head;
+	};
 };
 
 /* This is for listening sockets, thus all sockets which possess wildcards. */
diff --git a/include/net/sock.h b/include/net/sock.h
index 013396e50b91..e09e2886a836 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -723,6 +723,11 @@ static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_h
 	hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list);
 }
 
+static inline void __sk_nulls_add_node_tail_rcu(struct sock *sk, struct hlist_nulls_head *list)
+{
+	hlist_nulls_add_tail_rcu(&sk->sk_nulls_node, list);
+}
+
 static inline void sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
 {
 	sock_hold(sk);
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 7dc79b973e6e..6a4c82f96e78 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -914,11 +914,12 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb,
 
 		for (i = s_i; i < INET_LHTABLE_SIZE; i++) {
 			struct inet_listen_hashbucket *ilb;
+			struct hlist_nulls_node *node;
 
 			num = 0;
 			ilb = &hashinfo->listening_hash[i];
 			spin_lock(&ilb->lock);
-			sk_for_each(sk, &ilb->head) {
+			sk_nulls_for_each(sk, node, &ilb->nulls_head) {
 				struct inet_sock *inet = inet_sk(sk);
 
 				if (!net_eq(sock_net(sk), net))
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 83fb00153018..2bbaaf0c7176 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -516,10 +516,11 @@ static int inet_reuseport_add_sock(struct sock *sk,
 				   struct inet_listen_hashbucket *ilb)
 {
 	struct inet_bind_bucket *tb = inet_csk(sk)->icsk_bind_hash;
+	const struct hlist_nulls_node *node;
 	struct sock *sk2;
 	kuid_t uid = sock_i_uid(sk);
 
-	sk_for_each_rcu(sk2, &ilb->head) {
+	sk_nulls_for_each_rcu(sk2, node, &ilb->nulls_head) {
 		if (sk2 != sk &&
 		    sk2->sk_family == sk->sk_family &&
 		    ipv6_only_sock(sk2) == ipv6_only_sock(sk) &&
@@ -555,9 +556,9 @@ int __inet_hash(struct sock *sk, struct sock *osk)
 	}
 	if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport &&
 		sk->sk_family == AF_INET6)
-		hlist_add_tail_rcu(&sk->sk_node, &ilb->head);
+		__sk_nulls_add_node_tail_rcu(sk, &ilb->nulls_head);
 	else
-		hlist_add_head_rcu(&sk->sk_node, &ilb->head);
+		__sk_nulls_add_node_rcu(sk, &ilb->nulls_head);
 	inet_hash2(hashinfo, sk);
 	ilb->count++;
 	sock_set_flag(sk, SOCK_RCU_FREE);
@@ -606,11 +607,9 @@ void inet_unhash(struct sock *sk)
 		reuseport_detach_sock(sk);
 	if (ilb) {
 		inet_unhash2(hashinfo, sk);
-		 __sk_del_node_init(sk);
-		 ilb->count--;
-	} else {
-		__sk_nulls_del_node_init_rcu(sk);
+		ilb->count--;
 	}
+	__sk_nulls_del_node_init_rcu(sk);
 	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
 unlock:
 	spin_unlock_bh(lock);
@@ -750,7 +749,8 @@ void inet_hashinfo_init(struct inet_hashinfo *h)
 
 	for (i = 0; i < INET_LHTABLE_SIZE; i++) {
 		spin_lock_init(&h->listening_hash[i].lock);
-		INIT_HLIST_HEAD(&h->listening_hash[i].head);
+		INIT_HLIST_NULLS_HEAD(&h->listening_hash[i].nulls_head,
+				      i + LISTENING_NULLS_BASE);
 		h->listening_hash[i].count = 0;
 	}
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 67b2dc7a1727..eda64871f983 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2149,13 +2149,14 @@ static void *listening_get_next(struct seq_file *seq, void *cur)
 	struct tcp_iter_state *st = seq->private;
 	struct net *net = seq_file_net(seq);
 	struct inet_listen_hashbucket *ilb;
+	struct hlist_nulls_node *node;
 	struct sock *sk = cur;
 
 	if (!sk) {
 get_head:
 		ilb = &tcp_hashinfo.listening_hash[st->bucket];
 		spin_lock(&ilb->lock);
-		sk = sk_head(&ilb->head);
+		sk = sk_nulls_head(&ilb->nulls_head);
 		st->offset = 0;
 		goto get_sk;
 	}
@@ -2163,9 +2164,9 @@ static void *listening_get_next(struct seq_file *seq, void *cur)
 	++st->num;
 	++st->offset;
 
-	sk = sk_next(sk);
+	sk = sk_nulls_next(sk);
 get_sk:
-	sk_for_each_from(sk) {
+	sk_nulls_for_each_from(sk, node) {
 		if (!net_eq(sock_net(sk), net))
 			continue;
 		if (sk->sk_family == afinfo->family)
-- 
2.20.1


From 76c6981741152952c3155ed8d4d785d15b6ed831 Mon Sep 17 00:00:00 2001
From: Haiyang Zhang <haiyangz@microsoft.com>
Date: Wed, 11 Dec 2019 14:26:27 -0800
Subject: [PATCH 38/46] hv_netvsc: Fix tx_table init in rndis_set_subchannel()

[ Upstream commit c39ea5cba5a2e97fc01b78c85208bf31383b399c ]

Host can provide send indirection table messages anytime after RSS is
enabled by calling rndis_filter_set_rss_param(). So the host provided
table values may be overwritten by the initialization in
rndis_set_subchannel().

To prevent this problem, move the tx_table initialization before calling
rndis_filter_set_rss_param().

Fixes: a6fb6aa3cfa9 ("hv_netvsc: Set tx_table to equal weight after subchannels open")
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/hyperv/rndis_filter.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index abaf8156d19d..e3d3c9097ff1 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -1165,6 +1165,9 @@ int rndis_set_subchannel(struct net_device *ndev,
 	wait_event(nvdev->subchan_open,
 		   atomic_read(&nvdev->open_chn) == nvdev->num_chn);
 
+	for (i = 0; i < VRSS_SEND_TAB_SIZE; i++)
+		ndev_ctx->tx_table[i] = i % nvdev->num_chn;
+
 	/* ignore failures from setting rss parameters, still have channels */
 	if (dev_info)
 		rndis_filter_set_rss_param(rdev, dev_info->rss_key);
@@ -1174,9 +1177,6 @@ int rndis_set_subchannel(struct net_device *ndev,
 	netif_set_real_num_tx_queues(ndev, nvdev->num_chn);
 	netif_set_real_num_rx_queues(ndev, nvdev->num_chn);
 
-	for (i = 0; i < VRSS_SEND_TAB_SIZE; i++)
-		ndev_ctx->tx_table[i] = i % nvdev->num_chn;
-
 	return 0;
 }
 
-- 
2.20.1


From b2080136cf07210eebe53d9428fbe0fbefa6b0f6 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Wed, 11 Dec 2019 08:23:34 +0000
Subject: [PATCH 39/46] gtp: fix an use-after-free in ipv4_pdp_find()

[ Upstream commit 94dc550a5062030569d4aa76e10e50c8fc001930 ]

ipv4_pdp_find() is called in TX packet path of GTP.
ipv4_pdp_find() internally uses gtp->tid_hash to lookup pdp context.
In the current code, gtp->tid_hash and gtp->addr_hash are freed by
->dellink(), which is gtp_dellink().
But gtp_dellink() would be called while packets are processing.
So, gtp_dellink() should not free gtp->tid_hash and gtp->addr_hash.
Instead, dev->priv_destructor() would be used because this callback
is called after all packet processing safely.

Test commands:
    ip link add veth1 type veth peer name veth2
    ip a a 172.0.0.1/24 dev veth1
    ip link set veth1 up
    ip a a 172.99.0.1/32 dev lo

    gtp-link add gtp1 &

    gtp-tunnel add gtp1 v1 200 100 172.99.0.2 172.0.0.2
    ip r a  172.99.0.2/32 dev gtp1
    ip link set gtp1 mtu 1500

    ip netns add ns2
    ip link set veth2 netns ns2
    ip netns exec ns2 ip a a 172.0.0.2/24 dev veth2
    ip netns exec ns2 ip link set veth2 up
    ip netns exec ns2 ip a a 172.99.0.2/32 dev lo
    ip netns exec ns2 ip link set lo up

    ip netns exec ns2 gtp-link add gtp2 &
    ip netns exec ns2 gtp-tunnel add gtp2 v1 100 200 172.99.0.1 172.0.0.1
    ip netns exec ns2 ip r a 172.99.0.1/32 dev gtp2
    ip netns exec ns2 ip link set gtp2 mtu 1500

    hping3 172.99.0.2 -2 --flood &
    ip link del gtp1

Splat looks like:
[   72.568081][ T1195] BUG: KASAN: use-after-free in ipv4_pdp_find.isra.12+0x130/0x170 [gtp]
[   72.568916][ T1195] Read of size 8 at addr ffff8880b9a35d28 by task hping3/1195
[   72.569631][ T1195]
[   72.569861][ T1195] CPU: 2 PID: 1195 Comm: hping3 Not tainted 5.5.0-rc1 #199
[   72.570547][ T1195] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[   72.571438][ T1195] Call Trace:
[   72.571764][ T1195]  dump_stack+0x96/0xdb
[   72.572171][ T1195]  ? ipv4_pdp_find.isra.12+0x130/0x170 [gtp]
[   72.572761][ T1195]  print_address_description.constprop.5+0x1be/0x360
[   72.573400][ T1195]  ? ipv4_pdp_find.isra.12+0x130/0x170 [gtp]
[   72.573971][ T1195]  ? ipv4_pdp_find.isra.12+0x130/0x170 [gtp]
[   72.574544][ T1195]  __kasan_report+0x12a/0x16f
[   72.575014][ T1195]  ? ipv4_pdp_find.isra.12+0x130/0x170 [gtp]
[   72.575593][ T1195]  kasan_report+0xe/0x20
[   72.576004][ T1195]  ipv4_pdp_find.isra.12+0x130/0x170 [gtp]
[   72.576577][ T1195]  gtp_build_skb_ip4+0x199/0x1420 [gtp]
[ ... ]
[   72.647671][ T1195] BUG: unable to handle page fault for address: ffff8880b9a35d28
[   72.648512][ T1195] #PF: supervisor read access in kernel mode
[   72.649158][ T1195] #PF: error_code(0x0000) - not-present page
[   72.649849][ T1195] PGD a6c01067 P4D a6c01067 PUD 11fb07067 PMD 11f939067 PTE 800fffff465ca060
[   72.652958][ T1195] Oops: 0000 [#1] SMP DEBUG_PAGEALLOC KASAN PTI
[   72.653834][ T1195] CPU: 2 PID: 1195 Comm: hping3 Tainted: G    B             5.5.0-rc1 #199
[   72.668062][ T1195] RIP: 0010:ipv4_pdp_find.isra.12+0x86/0x170 [gtp]
[ ... ]
[   72.679168][ T1195] Call Trace:
[   72.679603][ T1195]  gtp_build_skb_ip4+0x199/0x1420 [gtp]
[   72.681915][ T1195]  ? ipv4_pdp_find.isra.12+0x170/0x170 [gtp]
[   72.682513][ T1195]  ? lock_acquire+0x164/0x3b0
[   72.682966][ T1195]  ? gtp_dev_xmit+0x35e/0x890 [gtp]
[   72.683481][ T1195]  gtp_dev_xmit+0x3c2/0x890 [gtp]
[ ... ]

Fixes: 459aa660eb1d ("gtp: add initial driver for datapath of GPRS Tunneling Protocol (GTP-U)")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/gtp.c | 34 +++++++++++++++++-----------------
 1 file changed, 17 insertions(+), 17 deletions(-)

diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 522802961712..f5aa5e1c7722 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -640,9 +640,16 @@ static void gtp_link_setup(struct net_device *dev)
 }
 
 static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize);
-static void gtp_hashtable_free(struct gtp_dev *gtp);
 static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[]);
 
+static void gtp_destructor(struct net_device *dev)
+{
+	struct gtp_dev *gtp = netdev_priv(dev);
+
+	kfree(gtp->addr_hash);
+	kfree(gtp->tid_hash);
+}
+
 static int gtp_newlink(struct net *src_net, struct net_device *dev,
 		       struct nlattr *tb[], struct nlattr *data[],
 		       struct netlink_ext_ack *extack)
@@ -680,13 +687,15 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev,
 
 	gn = net_generic(dev_net(dev), gtp_net_id);
 	list_add_rcu(&gtp->list, &gn->gtp_dev_list);
+	dev->priv_destructor = gtp_destructor;
 
 	netdev_dbg(dev, "registered new GTP interface\n");
 
 	return 0;
 
 out_hashtable:
-	gtp_hashtable_free(gtp);
+	kfree(gtp->addr_hash);
+	kfree(gtp->tid_hash);
 out_encap:
 	gtp_encap_disable(gtp);
 	return err;
@@ -695,8 +704,13 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev,
 static void gtp_dellink(struct net_device *dev, struct list_head *head)
 {
 	struct gtp_dev *gtp = netdev_priv(dev);
+	struct pdp_ctx *pctx;
+	int i;
+
+	for (i = 0; i < gtp->hash_size; i++)
+		hlist_for_each_entry_rcu(pctx, &gtp->tid_hash[i], hlist_tid)
+			pdp_context_delete(pctx);
 
-	gtp_hashtable_free(gtp);
 	list_del_rcu(&gtp->list);
 	unregister_netdevice_queue(dev, head);
 }
@@ -774,20 +788,6 @@ static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize)
 	return -ENOMEM;
 }
 
-static void gtp_hashtable_free(struct gtp_dev *gtp)
-{
-	struct pdp_ctx *pctx;
-	int i;
-
-	for (i = 0; i < gtp->hash_size; i++)
-		hlist_for_each_entry_rcu(pctx, &gtp->tid_hash[i], hlist_tid)
-			pdp_context_delete(pctx);
-
-	synchronize_rcu();
-	kfree(gtp->addr_hash);
-	kfree(gtp->tid_hash);
-}
-
 static struct sock *gtp_encap_enable_socket(int fd, int type,
 					    struct gtp_dev *gtp)
 {
-- 
2.20.1


From 27e38602d0ec9d503fde6489fc0e21bed4a032a2 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Wed, 11 Dec 2019 08:23:00 +0000
Subject: [PATCH 40/46] gtp: do not allow adding duplicate tid and ms_addr pdp
 context

[ Upstream commit 6b01b1d9b2d38dc84ac398bfe9f00baff06a31e5 ]

GTP RX packet path lookups pdp context with TID. If duplicate TID pdp
contexts are existing in the list, it couldn't select correct pdp context.
So, TID value  should be unique.
GTP TX packet path lookups pdp context with ms_addr. If duplicate ms_addr pdp
contexts are existing in the list, it couldn't select correct pdp context.
So, ms_addr value should be unique.

Fixes: 459aa660eb1d ("gtp: add initial driver for datapath of GPRS Tunneling Protocol (GTP-U)")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/gtp.c | 32 ++++++++++++++++++++++----------
 1 file changed, 22 insertions(+), 10 deletions(-)

diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index f5aa5e1c7722..fca471e27f39 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -928,24 +928,31 @@ static void ipv4_pdp_fill(struct pdp_ctx *pctx, struct genl_info *info)
 	}
 }
 
-static int ipv4_pdp_add(struct gtp_dev *gtp, struct sock *sk,
-			struct genl_info *info)
+static int gtp_pdp_add(struct gtp_dev *gtp, struct sock *sk,
+		       struct genl_info *info)
 {
+	struct pdp_ctx *pctx, *pctx_tid = NULL;
 	struct net_device *dev = gtp->dev;
 	u32 hash_ms, hash_tid = 0;
-	struct pdp_ctx *pctx;
+	unsigned int version;
 	bool found = false;
 	__be32 ms_addr;
 
 	ms_addr = nla_get_be32(info->attrs[GTPA_MS_ADDRESS]);
 	hash_ms = ipv4_hashfn(ms_addr) % gtp->hash_size;
+	version = nla_get_u32(info->attrs[GTPA_VERSION]);
 
-	hlist_for_each_entry_rcu(pctx, &gtp->addr_hash[hash_ms], hlist_addr) {
-		if (pctx->ms_addr_ip4.s_addr == ms_addr) {
-			found = true;
-			break;
-		}
-	}
+	pctx = ipv4_pdp_find(gtp, ms_addr);
+	if (pctx)
+		found = true;
+	if (version == GTP_V0)
+		pctx_tid = gtp0_pdp_find(gtp,
+					 nla_get_u64(info->attrs[GTPA_TID]));
+	else if (version == GTP_V1)
+		pctx_tid = gtp1_pdp_find(gtp,
+					 nla_get_u32(info->attrs[GTPA_I_TEI]));
+	if (pctx_tid)
+		found = true;
 
 	if (found) {
 		if (info->nlhdr->nlmsg_flags & NLM_F_EXCL)
@@ -953,6 +960,11 @@ static int ipv4_pdp_add(struct gtp_dev *gtp, struct sock *sk,
 		if (info->nlhdr->nlmsg_flags & NLM_F_REPLACE)
 			return -EOPNOTSUPP;
 
+		if (pctx && pctx_tid)
+			return -EEXIST;
+		if (!pctx)
+			pctx = pctx_tid;
+
 		ipv4_pdp_fill(pctx, info);
 
 		if (pctx->gtp_version == GTP_V0)
@@ -1076,7 +1088,7 @@ static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info)
 		goto out_unlock;
 	}
 
-	err = ipv4_pdp_add(gtp, sk, info);
+	err = gtp_pdp_add(gtp, sk, info);
 
 out_unlock:
 	rcu_read_unlock();
-- 
2.20.1


From 49e45bbb56082a01d248eec84a91122e14696a08 Mon Sep 17 00:00:00 2001
From: Jonathan Lemon <jonathan.lemon@gmail.com>
Date: Tue, 10 Dec 2019 08:39:46 -0800
Subject: [PATCH 41/46] bnxt: apply computed clamp value for coalece parameter

[ Upstream commit 6adc4601c2a1ac87b4ab8ed0cb55db6efd0264e8 ]

After executing "ethtool -C eth0 rx-usecs-irq 0", the box becomes
unresponsive, likely due to interrupt livelock.  It appears that
a minimum clamp value for the irq timer is computed, but is never
applied.

Fix by applying the corrected clamp value.

Fixes: 74706afa712d ("bnxt_en: Update interrupt coalescing logic.")
Signed-off-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index c0df947ed9f9..5c75b061243f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -6178,7 +6178,7 @@ static void bnxt_hwrm_set_coal_params(struct bnxt *bp,
 		tmr = bnxt_usec_to_coal_tmr(bp, hw_coal->coal_ticks_irq);
 		val = clamp_t(u16, tmr, 1,
 			      coal_cap->cmpl_aggr_dma_tmr_during_int_max);
-		req->cmpl_aggr_dma_tmr_during_int = cpu_to_le16(tmr);
+		req->cmpl_aggr_dma_tmr_during_int = cpu_to_le16(val);
 		req->enables |=
 			cpu_to_le16(BNXT_COAL_CMPL_AGGR_TMR_DURING_INT_ENABLE);
 	}
-- 
2.20.1


From eef58099a7d8d6930df46be0cb808256fa7c8e77 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Wed, 11 Dec 2019 22:20:16 +0800
Subject: [PATCH 42/46] ipv6/addrconf: only check invalid header values when
 NETLINK_F_STRICT_CHK is set

[ Upstream commit 2beb6d2901a3f73106485d560c49981144aeacb1 ]

In commit 4b1373de73a3 ("net: ipv6: addr: perform strict checks also for
doit handlers") we add strict check for inet6_rtm_getaddr(). But we did
the invalid header values check before checking if NETLINK_F_STRICT_CHK
is set. This may break backwards compatibility if user already set the
ifm->ifa_prefixlen, ifm->ifa_flags, ifm->ifa_scope in their netlink code.

I didn't move the nlmsg_len check because I thought it's a valid check.

Reported-by: Jianlin Shi <jishi@redhat.com>
Fixes: 4b1373de73a3 ("net: ipv6: addr: perform strict checks also for doit handlers")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/ipv6/addrconf.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 34ccef18b40e..f9b5690e94fd 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5231,16 +5231,16 @@ static int inet6_rtm_valid_getaddr_req(struct sk_buff *skb,
 		return -EINVAL;
 	}
 
+	if (!netlink_strict_get_check(skb))
+		return nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX,
+					      ifa_ipv6_policy, extack);
+
 	ifm = nlmsg_data(nlh);
 	if (ifm->ifa_prefixlen || ifm->ifa_flags || ifm->ifa_scope) {
 		NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for get address request");
 		return -EINVAL;
 	}
 
-	if (!netlink_strict_get_check(skb))
-		return nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX,
-					      ifa_ipv6_policy, extack);
-
 	err = nlmsg_parse_deprecated_strict(nlh, sizeof(*ifm), tb, IFA_MAX,
 					    ifa_ipv6_policy, extack);
 	if (err)
-- 
2.20.1


From 9d6ba83e5e4449f3c87b8d54766c4fb8edaeb514 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Fri, 13 Dec 2019 10:06:30 +0000
Subject: [PATCH 43/46] net: phylink: fix interface passed to mac_link_up

[ Upstream commit 9b2079c046a9d6c9c73a4ec33816678565ee01f3 ]

A mismerge between the following two commits:

c678726305b9 ("net: phylink: ensure consistent phy interface mode")
27755ff88c0e ("net: phylink: Add phylink_mac_link_{up, down} wrapper functions")

resulted in the wrong interface being passed to the mac_link_up()
function. Fix this up.

Fixes: b4b12b0d2f02 ("Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net")
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/phy/phylink.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 536236fdb232..bf5bbb565cf5 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -444,8 +444,7 @@ static void phylink_mac_link_up(struct phylink *pl,
 
 	pl->cur_interface = link_state.interface;
 	pl->ops->mac_link_up(pl->config, pl->link_an_mode,
-			     pl->phy_state.interface,
-			     pl->phydev);
+			     pl->cur_interface, pl->phydev);
 
 	if (ndev)
 		netif_carrier_on(ndev);
-- 
2.20.1


From a38aa44291a95bb6583a5aa157e9f1cbe096976a Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.ibm.com>
Date: Thu, 12 Dec 2019 22:35:58 +0100
Subject: [PATCH 44/46] net/smc: add fallback check to connect()

[ Upstream commit 86434744fedf0cfe07a9eee3f4632c0e25c1d136 ]

FASTOPEN setsockopt() or sendmsg() may switch the SMC socket to fallback
mode. Once fallback mode is active, the native TCP socket functions are
called. Nevertheless there is a small race window, when FASTOPEN
setsockopt/sendmsg runs in parallel to a connect(), and switch the
socket into fallback mode before connect() takes the sock lock.
Make sure the SMC-specific connect setup is omitted in this case.

This way a syzbot-reported refcount problem is fixed, triggered by
different threads running non-blocking connect() and FASTOPEN_KEY
setsockopt.

Reported-by: syzbot+96d3f9ff6a86d37e44c8@syzkaller.appspotmail.com
Fixes: 6d6dd528d5af ("net/smc: fix refcount non-blocking connect() -part 2")
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/smc/af_smc.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 737b49909a7a..6a6d3b2aa5a9 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -854,6 +854,8 @@ static int smc_connect(struct socket *sock, struct sockaddr *addr,
 		goto out;
 
 	sock_hold(&smc->sk); /* sock put in passive closing */
+	if (smc->use_fallback)
+		goto out;
 	if (flags & O_NONBLOCK) {
 		if (schedule_work(&smc->connect_work))
 			smc->connect_nonblock = 1;
@@ -1716,8 +1718,6 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
 		sk->sk_err = smc->clcsock->sk->sk_err;
 		sk->sk_error_report(sk);
 	}
-	if (rc)
-		return rc;
 
 	if (optlen < sizeof(int))
 		return -EINVAL;
@@ -1725,6 +1725,8 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
 		return -EFAULT;
 
 	lock_sock(sk);
+	if (rc || smc->use_fallback)
+		goto out;
 	switch (optname) {
 	case TCP_ULP:
 	case TCP_FASTOPEN:
@@ -1736,15 +1738,14 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
 			smc_switch_to_fallback(smc);
 			smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP;
 		} else {
-			if (!smc->use_fallback)
-				rc = -EINVAL;
+			rc = -EINVAL;
 		}
 		break;
 	case TCP_NODELAY:
 		if (sk->sk_state != SMC_INIT &&
 		    sk->sk_state != SMC_LISTEN &&
 		    sk->sk_state != SMC_CLOSED) {
-			if (val && !smc->use_fallback)
+			if (val)
 				mod_delayed_work(system_wq, &smc->conn.tx_work,
 						 0);
 		}
@@ -1753,7 +1754,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
 		if (sk->sk_state != SMC_INIT &&
 		    sk->sk_state != SMC_LISTEN &&
 		    sk->sk_state != SMC_CLOSED) {
-			if (!val && !smc->use_fallback)
+			if (!val)
 				mod_delayed_work(system_wq, &smc->conn.tx_work,
 						 0);
 		}
@@ -1764,6 +1765,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
 	default:
 		break;
 	}
+out:
 	release_sock(sk);
 
 	return rc;
-- 
2.20.1


From 371421039bf83e6af9d333df0a9a13e6d5f2353a Mon Sep 17 00:00:00 2001
From: Netanel Belgazal <netanel@amazon.com>
Date: Tue, 10 Dec 2019 11:27:44 +0000
Subject: [PATCH 45/46] net: ena: fix napi handler misbehavior when the napi
 budget is zero

[ Upstream commit 24dee0c7478d1a1e00abdf5625b7f921467325dc ]

In netpoll the napi handler could be called with budget equal to zero.
Current ENA napi handler doesn't take that into consideration.

The napi handler handles Rx packets in a do-while loop.
Currently, the budget check happens only after decrementing the
budget, therefore the napi handler, in rare cases, could run over
MAX_INT packets.

In addition to that, this moves all budget related variables to int
calculation and stop mixing u32 to avoid ambiguity

Fixes: 1738cd3ed342 ("net: ena: Add a driver for Amazon Elastic Network Adapters (ENA)")
Signed-off-by: Netanel Belgazal <netanel@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index c487d2a7d6dd..b4a145220aba 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -1238,8 +1238,8 @@ static int ena_io_poll(struct napi_struct *napi, int budget)
 	struct ena_napi *ena_napi = container_of(napi, struct ena_napi, napi);
 	struct ena_ring *tx_ring, *rx_ring;
 
-	u32 tx_work_done;
-	u32 rx_work_done;
+	int tx_work_done;
+	int rx_work_done = 0;
 	int tx_budget;
 	int napi_comp_call = 0;
 	int ret;
@@ -1256,7 +1256,11 @@ static int ena_io_poll(struct napi_struct *napi, int budget)
 	}
 
 	tx_work_done = ena_clean_tx_irq(tx_ring, tx_budget);
-	rx_work_done = ena_clean_rx_irq(rx_ring, napi, budget);
+	/* On netpoll the budget is zero and the handler should only clean the
+	 * tx completions.
+	 */
+	if (likely(budget))
+		rx_work_done = ena_clean_rx_irq(rx_ring, napi, budget);
 
 	/* If the device is about to reset or down, avoid unmask
 	 * the interrupt and return 0 so NAPI won't reschedule
-- 
2.20.1


From 10d7851a82dd0260dba73389138a1e8a7aa18aa8 Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Fri, 6 Dec 2019 15:39:12 +0100
Subject: [PATCH 46/46] vhost/vsock: accept only packets with the right dst_cid

[ Upstream commit 8a3cc29c316c17de590e3ff8b59f3d6cbfd37b0a ]

When we receive a new packet from the guest, we check if the
src_cid is correct, but we forgot to check the dst_cid.

The host should accept only packets where dst_cid is
equal to the host CID.

Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/vsock.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 9f57736fe15e..88a5aa6624b4 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -437,7 +437,9 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work)
 		virtio_transport_deliver_tap_pkt(pkt);
 
 		/* Only accept correctly addressed packets */
-		if (le64_to_cpu(pkt->hdr.src_cid) == vsock->guest_cid)
+		if (le64_to_cpu(pkt->hdr.src_cid) == vsock->guest_cid &&
+		    le64_to_cpu(pkt->hdr.dst_cid) ==
+		    vhost_transport_get_local_cid())
 			virtio_transport_recv_pkt(pkt);
 		else
 			virtio_transport_free_pkt(pkt);
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Wed, Jan 01, 2020 at 12:13:37PM -0800, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.19 and v5.4
> -stable, respectively.
> 
> Thank you!


all now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 106 bytes --]


Please queue up the following networking bug fixes for v4.19
and v5.4 -stable, respectively.

Thank you.

[-- Attachment #2: net_419.mbox --]
[-- Type: Application/Octet-Stream, Size: 38864 bytes --]

From 8565844b139379303389936a82d4dfa50a00aa5b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 6 Jan 2020 06:45:37 -0800
Subject: [PATCH 01/15] gtp: fix bad unlock balance in gtp_encap_enable_socket

[ Upstream commit 90d72256addff9e5f8ad645e8f632750dd1f8935 ]

WARNING: bad unlock balance detected!
5.5.0-rc5-syzkaller #0 Not tainted
-------------------------------------
syz-executor921/9688 is trying to release lock (sk_lock-AF_INET6) at:
[<ffffffff84bf8506>] gtp_encap_enable_socket+0x146/0x400 drivers/net/gtp.c:830
but there are no more locks to release!

other info that might help us debug this:
2 locks held by syz-executor921/9688:
 #0: ffffffff8a4d8840 (rtnl_mutex){+.+.}, at: rtnl_lock net/core/rtnetlink.c:72 [inline]
 #0: ffffffff8a4d8840 (rtnl_mutex){+.+.}, at: rtnetlink_rcv_msg+0x405/0xaf0 net/core/rtnetlink.c:5421
 #1: ffff88809304b560 (slock-AF_INET6){+...}, at: spin_lock_bh include/linux/spinlock.h:343 [inline]
 #1: ffff88809304b560 (slock-AF_INET6){+...}, at: release_sock+0x20/0x1c0 net/core/sock.c:2951

stack backtrace:
CPU: 0 PID: 9688 Comm: syz-executor921 Not tainted 5.5.0-rc5-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x197/0x210 lib/dump_stack.c:118
 print_unlock_imbalance_bug kernel/locking/lockdep.c:4008 [inline]
 print_unlock_imbalance_bug.cold+0x114/0x123 kernel/locking/lockdep.c:3984
 __lock_release kernel/locking/lockdep.c:4242 [inline]
 lock_release+0x5f2/0x960 kernel/locking/lockdep.c:4503
 sock_release_ownership include/net/sock.h:1496 [inline]
 release_sock+0x17c/0x1c0 net/core/sock.c:2961
 gtp_encap_enable_socket+0x146/0x400 drivers/net/gtp.c:830
 gtp_encap_enable drivers/net/gtp.c:852 [inline]
 gtp_newlink+0x9fc/0xc60 drivers/net/gtp.c:666
 __rtnl_newlink+0x109e/0x1790 net/core/rtnetlink.c:3305
 rtnl_newlink+0x69/0xa0 net/core/rtnetlink.c:3363
 rtnetlink_rcv_msg+0x45e/0xaf0 net/core/rtnetlink.c:5424
 netlink_rcv_skb+0x177/0x450 net/netlink/af_netlink.c:2477
 rtnetlink_rcv+0x1d/0x30 net/core/rtnetlink.c:5442
 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
 netlink_unicast+0x58c/0x7d0 net/netlink/af_netlink.c:1328
 netlink_sendmsg+0x91c/0xea0 net/netlink/af_netlink.c:1917
 sock_sendmsg_nosec net/socket.c:639 [inline]
 sock_sendmsg+0xd7/0x130 net/socket.c:659
 ____sys_sendmsg+0x753/0x880 net/socket.c:2330
 ___sys_sendmsg+0x100/0x170 net/socket.c:2384
 __sys_sendmsg+0x105/0x1d0 net/socket.c:2417
 __do_sys_sendmsg net/socket.c:2426 [inline]
 __se_sys_sendmsg net/socket.c:2424 [inline]
 __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2424
 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x445d49
Code: e8 bc b7 02 00 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 2b 12 fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f8019074db8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 00000000006dac38 RCX: 0000000000445d49
RDX: 0000000000000000 RSI: 0000000020000180 RDI: 0000000000000003
RBP: 00000000006dac30 R08: 0000000000000004 R09: 0000000000000000
R10: 0000000000000008 R11: 0000000000000246 R12: 00000000006dac3c
R13: 00007ffea687f6bf R14: 00007f80190759c0 R15: 20c49ba5e353f7cf

Fixes: e198987e7dd7 ("gtp: fix suspicious RCU usage")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/gtp.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 494f00b9c5ef..6571cac6e786 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -818,7 +818,7 @@ static struct sock *gtp_encap_enable_socket(int fd, int type,
 	lock_sock(sock->sk);
 	if (sock->sk->sk_user_data) {
 		sk = ERR_PTR(-EBUSY);
-		goto out_sock;
+		goto out_rel_sock;
 	}
 
 	sk = sock->sk;
@@ -831,8 +831,9 @@ static struct sock *gtp_encap_enable_socket(int fd, int type,
 
 	setup_udp_tunnel_sock(sock_net(sock->sk), sock, &tuncfg);
 
-out_sock:
+out_rel_sock:
 	release_sock(sock->sk);
+out_sock:
 	sockfd_put(sock);
 	return sk;
 }
-- 
2.20.1


From c91bf334d50e69c6a1e3928c596ce300271bd44e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 6 Jan 2020 12:30:48 -0800
Subject: [PATCH 02/15] macvlan: do not assume mac_header is set in
 macvlan_broadcast()

[ Upstream commit 96cc4b69581db68efc9749ef32e9cf8e0160c509 ]

Use of eth_hdr() in tx path is error prone.

Many drivers call skb_reset_mac_header() before using it,
but others do not.

Commit 6d1ccff62780 ("net: reset mac header in dev_start_xmit()")
attempted to fix this generically, but commit d346a3fae3ff
("packet: introduce PACKET_QDISC_BYPASS socket option") brought
back the macvlan bug.

Lets add a new helper, so that tx paths no longer have
to call skb_reset_mac_header() only to get a pointer
to skb->data.

Hopefully we will be able to revert 6d1ccff62780
("net: reset mac header in dev_start_xmit()") and save few cycles
in transmit fast path.

BUG: KASAN: use-after-free in __get_unaligned_cpu32 include/linux/unaligned/packed_struct.h:19 [inline]
BUG: KASAN: use-after-free in mc_hash drivers/net/macvlan.c:251 [inline]
BUG: KASAN: use-after-free in macvlan_broadcast+0x547/0x620 drivers/net/macvlan.c:277
Read of size 4 at addr ffff8880a4932401 by task syz-executor947/9579

CPU: 0 PID: 9579 Comm: syz-executor947 Not tainted 5.5.0-rc4-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x197/0x210 lib/dump_stack.c:118
 print_address_description.constprop.0.cold+0xd4/0x30b mm/kasan/report.c:374
 __kasan_report.cold+0x1b/0x41 mm/kasan/report.c:506
 kasan_report+0x12/0x20 mm/kasan/common.c:639
 __asan_report_load_n_noabort+0xf/0x20 mm/kasan/generic_report.c:145
 __get_unaligned_cpu32 include/linux/unaligned/packed_struct.h:19 [inline]
 mc_hash drivers/net/macvlan.c:251 [inline]
 macvlan_broadcast+0x547/0x620 drivers/net/macvlan.c:277
 macvlan_queue_xmit drivers/net/macvlan.c:520 [inline]
 macvlan_start_xmit+0x402/0x77f drivers/net/macvlan.c:559
 __netdev_start_xmit include/linux/netdevice.h:4447 [inline]
 netdev_start_xmit include/linux/netdevice.h:4461 [inline]
 dev_direct_xmit+0x419/0x630 net/core/dev.c:4079
 packet_direct_xmit+0x1a9/0x250 net/packet/af_packet.c:240
 packet_snd net/packet/af_packet.c:2966 [inline]
 packet_sendmsg+0x260d/0x6220 net/packet/af_packet.c:2991
 sock_sendmsg_nosec net/socket.c:639 [inline]
 sock_sendmsg+0xd7/0x130 net/socket.c:659
 __sys_sendto+0x262/0x380 net/socket.c:1985
 __do_sys_sendto net/socket.c:1997 [inline]
 __se_sys_sendto net/socket.c:1993 [inline]
 __x64_sys_sendto+0xe1/0x1a0 net/socket.c:1993
 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x442639
Code: 18 89 d0 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 5b 10 fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007ffc13549e08 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000442639
RDX: 000000000000000e RSI: 0000000020000080 RDI: 0000000000000003
RBP: 0000000000000004 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 0000000000403bb0 R14: 0000000000000000 R15: 0000000000000000

Allocated by task 9389:
 save_stack+0x23/0x90 mm/kasan/common.c:72
 set_track mm/kasan/common.c:80 [inline]
 __kasan_kmalloc mm/kasan/common.c:513 [inline]
 __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:486
 kasan_kmalloc+0x9/0x10 mm/kasan/common.c:527
 __do_kmalloc mm/slab.c:3656 [inline]
 __kmalloc+0x163/0x770 mm/slab.c:3665
 kmalloc include/linux/slab.h:561 [inline]
 tomoyo_realpath_from_path+0xc5/0x660 security/tomoyo/realpath.c:252
 tomoyo_get_realpath security/tomoyo/file.c:151 [inline]
 tomoyo_path_perm+0x230/0x430 security/tomoyo/file.c:822
 tomoyo_inode_getattr+0x1d/0x30 security/tomoyo/tomoyo.c:129
 security_inode_getattr+0xf2/0x150 security/security.c:1222
 vfs_getattr+0x25/0x70 fs/stat.c:115
 vfs_statx_fd+0x71/0xc0 fs/stat.c:145
 vfs_fstat include/linux/fs.h:3265 [inline]
 __do_sys_newfstat+0x9b/0x120 fs/stat.c:378
 __se_sys_newfstat fs/stat.c:375 [inline]
 __x64_sys_newfstat+0x54/0x80 fs/stat.c:375
 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Freed by task 9389:
 save_stack+0x23/0x90 mm/kasan/common.c:72
 set_track mm/kasan/common.c:80 [inline]
 kasan_set_free_info mm/kasan/common.c:335 [inline]
 __kasan_slab_free+0x102/0x150 mm/kasan/common.c:474
 kasan_slab_free+0xe/0x10 mm/kasan/common.c:483
 __cache_free mm/slab.c:3426 [inline]
 kfree+0x10a/0x2c0 mm/slab.c:3757
 tomoyo_realpath_from_path+0x1a7/0x660 security/tomoyo/realpath.c:289
 tomoyo_get_realpath security/tomoyo/file.c:151 [inline]
 tomoyo_path_perm+0x230/0x430 security/tomoyo/file.c:822
 tomoyo_inode_getattr+0x1d/0x30 security/tomoyo/tomoyo.c:129
 security_inode_getattr+0xf2/0x150 security/security.c:1222
 vfs_getattr+0x25/0x70 fs/stat.c:115
 vfs_statx_fd+0x71/0xc0 fs/stat.c:145
 vfs_fstat include/linux/fs.h:3265 [inline]
 __do_sys_newfstat+0x9b/0x120 fs/stat.c:378
 __se_sys_newfstat fs/stat.c:375 [inline]
 __x64_sys_newfstat+0x54/0x80 fs/stat.c:375
 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

The buggy address belongs to the object at ffff8880a4932000
 which belongs to the cache kmalloc-4k of size 4096
The buggy address is located 1025 bytes inside of
 4096-byte region [ffff8880a4932000, ffff8880a4933000)
The buggy address belongs to the page:
page:ffffea0002924c80 refcount:1 mapcount:0 mapping:ffff8880aa402000 index:0x0 compound_mapcount: 0
raw: 00fffe0000010200 ffffea0002846208 ffffea00028f3888 ffff8880aa402000
raw: 0000000000000000 ffff8880a4932000 0000000100000001 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff8880a4932300: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff8880a4932380: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff8880a4932400: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                   ^
 ffff8880a4932480: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff8880a4932500: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb

Fixes: b863ceb7ddce ("[NET]: Add macvlan driver")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macvlan.c    | 2 +-
 include/linux/if_ether.h | 8 ++++++++
 2 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 78789dfbe29e..41c0a3b55bfb 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -263,7 +263,7 @@ static void macvlan_broadcast(struct sk_buff *skb,
 			      struct net_device *src,
 			      enum macvlan_mode mode)
 {
-	const struct ethhdr *eth = eth_hdr(skb);
+	const struct ethhdr *eth = skb_eth_hdr(skb);
 	const struct macvlan_dev *vlan;
 	struct sk_buff *nskb;
 	unsigned int i;
diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h
index 548fd535fd02..d433f5e292c9 100644
--- a/include/linux/if_ether.h
+++ b/include/linux/if_ether.h
@@ -28,6 +28,14 @@ static inline struct ethhdr *eth_hdr(const struct sk_buff *skb)
 	return (struct ethhdr *)skb_mac_header(skb);
 }
 
+/* Prefer this version in TX path, instead of
+ * skb_reset_mac_header() + eth_hdr()
+ */
+static inline struct ethhdr *skb_eth_hdr(const struct sk_buff *skb)
+{
+	return (struct ethhdr *)skb->data;
+}
+
 static inline struct ethhdr *inner_eth_hdr(const struct sk_buff *skb)
 {
 	return (struct ethhdr *)skb_inner_mac_header(skb);
-- 
2.20.1


From 881bcf6e3db0282be3e0b21f8a3dbace2e2932ac Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sat, 4 Jan 2020 23:14:51 +0100
Subject: [PATCH 03/15] net: dsa: mv88e6xxx: Preserve priority when setting CPU
 port.

[ Upstream commit d8dc2c9676e614ef62f54a155b50076888c8a29a ]

The 6390 family uses an extended register to set the port connected to
the CPU. The lower 5 bits indicate the port, the upper three bits are
the priority of the frames as they pass through the switch, what
egress queue they should use, etc. Since frames being set to the CPU
are typically management frames, BPDU, IGMP, ARP, etc set the priority
to 7, the reset default, and the highest.

Fixes: 33641994a676 ("net: dsa: mv88e6xxx: Monitor and Management tables")
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Tested-by: Chris Healy <cphealy@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/global1.c | 5 +++++
 drivers/net/dsa/mv88e6xxx/global1.h | 1 +
 2 files changed, 6 insertions(+)

diff --git a/drivers/net/dsa/mv88e6xxx/global1.c b/drivers/net/dsa/mv88e6xxx/global1.c
index 38e399e0f30e..8298d6743c57 100644
--- a/drivers/net/dsa/mv88e6xxx/global1.c
+++ b/drivers/net/dsa/mv88e6xxx/global1.c
@@ -371,6 +371,11 @@ int mv88e6390_g1_set_cpu_port(struct mv88e6xxx_chip *chip, int port)
 {
 	u16 ptr = MV88E6390_G1_MONITOR_MGMT_CTL_PTR_CPU_DEST;
 
+	/* Use the default high priority for management frames sent to
+	 * the CPU.
+	 */
+	port |= MV88E6390_G1_MONITOR_MGMT_CTL_PTR_CPU_DEST_MGMTPRI;
+
 	return mv88e6390_g1_monitor_write(chip, ptr, port);
 }
 
diff --git a/drivers/net/dsa/mv88e6xxx/global1.h b/drivers/net/dsa/mv88e6xxx/global1.h
index bef01331266f..70b870c7cf1d 100644
--- a/drivers/net/dsa/mv88e6xxx/global1.h
+++ b/drivers/net/dsa/mv88e6xxx/global1.h
@@ -197,6 +197,7 @@
 #define MV88E6390_G1_MONITOR_MGMT_CTL_PTR_INGRESS_DEST		0x2000
 #define MV88E6390_G1_MONITOR_MGMT_CTL_PTR_EGRESS_DEST		0x2100
 #define MV88E6390_G1_MONITOR_MGMT_CTL_PTR_CPU_DEST		0x3000
+#define MV88E6390_G1_MONITOR_MGMT_CTL_PTR_CPU_DEST_MGMTPRI	0x00e0
 #define MV88E6390_G1_MONITOR_MGMT_CTL_DATA_MASK			0x00ff
 
 /* Offset 0x1C: Global Control 2 */
-- 
2.20.1


From 4f0702705091ac9315b34eda2227f3b2c3ceec16 Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wens@csie.org>
Date: Mon, 6 Jan 2020 11:09:45 +0800
Subject: [PATCH 04/15] net: stmmac: dwmac-sun8i: Allow all RGMII modes

[ Upstream commit f1239d8aa84dad8fe4b6cc1356f40fc8e842db47 ]

Allow all the RGMII modes to be used. This would allow us to represent
the hardware better in the device tree with RGMII_ID where in most
cases the PHY's internal delay for both RX and TX are used.

Fixes: 9f93ac8d4085 ("net-next: stmmac: Add dwmac-sun8i")
Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index fea286e14add..ef13a462c36d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -946,6 +946,9 @@ static int sun8i_dwmac_set_syscon(struct stmmac_priv *priv)
 		/* default */
 		break;
 	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
 		reg |= SYSCON_EPIT | SYSCON_ETCS_INT_GMII;
 		break;
 	case PHY_INTERFACE_MODE_RMII:
-- 
2.20.1


From 76616e743125e98ed3ae87cdc66a2ff150c09fc5 Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wens@csie.org>
Date: Mon, 6 Jan 2020 11:09:22 +0800
Subject: [PATCH 05/15] net: stmmac: dwmac-sunxi: Allow all RGMII modes

[ Upstream commit 52cc73e5404c7ba0cbfc50cb4c265108c84b3d5a ]

Allow all the RGMII modes to be used. This would allow us to represent
the hardware better in the device tree with RGMII_ID where in most
cases the PHY's internal delay for both RX and TX are used.

Fixes: af0bd4e9ba80 ("net: stmmac: sunxi platform extensions for GMAC in Allwinner A20 SoC's")
Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
index 62ccbd47c1db..fc1fa0f9f338 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
@@ -53,7 +53,7 @@ static int sun7i_gmac_init(struct platform_device *pdev, void *priv)
 	 * rate, which then uses the auto-reparenting feature of the
 	 * clock driver, and enabling/disabling the clock.
 	 */
-	if (gmac->interface == PHY_INTERFACE_MODE_RGMII) {
+	if (phy_interface_mode_is_rgmii(gmac->interface)) {
 		clk_set_rate(gmac->tx_clk, SUN7I_GMAC_GMII_RGMII_RATE);
 		clk_prepare_enable(gmac->tx_clk);
 		gmac->clk_enabled = 1;
-- 
2.20.1


From 1ed0940b259f12d85e2a393821069ef766277cdd Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 7 Jan 2020 10:57:01 -0800
Subject: [PATCH 06/15] net: usb: lan78xx: fix possible skb leak

[ Upstream commit 47240ba0cd09bb6fe6db9889582048324999dfa4 ]

If skb_linearize() fails, we need to free the skb.

TSO makes skb bigger, and this bug might be the reason
Raspberry Pi 3B+ users had to disable TSO.

Fixes: 55d7de9de6c3 ("Microchip's LAN7800 family USB 2/3 to 10/100/1000 Ethernet device driver")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: RENARD Pierre-Francois <pfrenard@gmail.com>
Cc: Stefan Wahren <stefan.wahren@i2se.com>
Cc: Woojung Huh <woojung.huh@microchip.com>
Cc: Microchip Linux Driver Support <UNGLinuxDriver@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/lan78xx.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 6dd24a1ca10d..8e2657626ca0 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -2736,11 +2736,6 @@ static int lan78xx_stop(struct net_device *net)
 	return 0;
 }
 
-static int lan78xx_linearize(struct sk_buff *skb)
-{
-	return skb_linearize(skb);
-}
-
 static struct sk_buff *lan78xx_tx_prep(struct lan78xx_net *dev,
 				       struct sk_buff *skb, gfp_t flags)
 {
@@ -2751,8 +2746,10 @@ static struct sk_buff *lan78xx_tx_prep(struct lan78xx_net *dev,
 		return NULL;
 	}
 
-	if (lan78xx_linearize(skb) < 0)
+	if (skb_linearize(skb)) {
+		dev_kfree_skb_any(skb);
 		return NULL;
+	}
 
 	tx_cmd_a = (u32)(skb->len & TX_CMD_A_LEN_MASK_) | TX_CMD_A_FCS_;
 
-- 
2.20.1


From 955807145716b4474cd8da08b5ff3f4cd3f2163b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 6 Jan 2020 06:10:39 -0800
Subject: [PATCH 07/15] pkt_sched: fq: do not accept silly TCA_FQ_QUANTUM

[ Upstream commit d9e15a2733067c9328fb56d98fe8e574fa19ec31 ]

As diagnosed by Florian :

If TCA_FQ_QUANTUM is set to 0x80000000, fq_deueue()
can loop forever in :

if (f->credit <= 0) {
  f->credit += q->quantum;
  goto begin;
}

... because f->credit is either 0 or -2147483648.

Let's limit TCA_FQ_QUANTUM to no more than 1 << 20 :
This max value should limit risks of breaking user setups
while fixing this bug.

Fixes: afe4fd062416 ("pkt_sched: fq: Fair Queue packet scheduler")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Diagnosed-by: Florian Westphal <fw@strlen.de>
Reported-by: syzbot+dc9071cc5a85950bdfce@syzkaller.appspotmail.com
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_fq.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 4808713c73b9..1ee2b77f607b 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -735,10 +735,12 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt,
 	if (tb[TCA_FQ_QUANTUM]) {
 		u32 quantum = nla_get_u32(tb[TCA_FQ_QUANTUM]);
 
-		if (quantum > 0)
+		if (quantum > 0 && quantum <= (1 << 20)) {
 			q->quantum = quantum;
-		else
+		} else {
+			NL_SET_ERR_MSG_MOD(extack, "invalid quantum");
 			err = -EINVAL;
+		}
 	}
 
 	if (tb[TCA_FQ_INITIAL_QUANTUM])
-- 
2.20.1


From fb4c1d93ecf1143033f348e4d88d506bb9e31a32 Mon Sep 17 00:00:00 2001
From: Wen Yang <wenyang@linux.alibaba.com>
Date: Thu, 2 Jan 2020 17:21:43 +0800
Subject: [PATCH 08/15] sch_cake: avoid possible divide by zero in
 cake_enqueue()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 68aab823c223646fab311f8a6581994facee66a0 ]

The variables 'window_interval' is u64 and do_div()
truncates it to 32 bits, which means it can test
non-zero and be truncated to zero for division.
The unit of window_interval is nanoseconds,
so its lower 32-bit is relatively easy to exceed.
Fix this issue by using div64_u64() instead.

Fixes: 7298de9cd725 ("sch_cake: Add ingress mode")
Signed-off-by: Wen Yang <wenyang@linux.alibaba.com>
Cc: Kevin Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk>
Cc: Toke Høiland-Jørgensen <toke@redhat.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: cake@lists.bufferbloat.net
Cc: netdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Acked-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_cake.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index e4cf72b0675e..824e3c37e5dd 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -1758,7 +1758,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 						      q->avg_window_begin));
 			u64 b = q->avg_window_bytes * (u64)NSEC_PER_SEC;
 
-			do_div(b, window_interval);
+			b = div64_u64(b, window_interval);
 			q->avg_peak_bandwidth =
 				cake_ewma(q->avg_peak_bandwidth, b,
 					  b > q->avg_peak_bandwidth ? 2 : 8);
-- 
2.20.1


From 8b72241617f33beb58008fe748492e66f4d2d4de Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sat, 4 Jan 2020 14:15:02 +0800
Subject: [PATCH 09/15] sctp: free cmd->obj.chunk for the unprocessed
 SCTP_CMD_REPLY

[ Upstream commit be7a7729207797476b6666f046d765bdf9630407 ]

This patch is to fix a memleak caused by no place to free cmd->obj.chunk
for the unprocessed SCTP_CMD_REPLY. This issue occurs when failing to
process a cmd while there're still SCTP_CMD_REPLY cmds on the cmd seq
with an allocated chunk in cmd->obj.chunk.

So fix it by freeing cmd->obj.chunk for each SCTP_CMD_REPLY cmd left on
the cmd seq when any cmd returns error. While at it, also remove 'nomem'
label.

Reported-by: syzbot+107c4aff5f392bf1517f@syzkaller.appspotmail.com
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sm_sideeffect.c | 28 ++++++++++++++++++----------
 1 file changed, 18 insertions(+), 10 deletions(-)

diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index de8a82bc6b42..0234a64b3b19 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -1373,8 +1373,10 @@ static int sctp_cmd_interpreter(enum sctp_event event_type,
 			/* Generate an INIT ACK chunk.  */
 			new_obj = sctp_make_init_ack(asoc, chunk, GFP_ATOMIC,
 						     0);
-			if (!new_obj)
-				goto nomem;
+			if (!new_obj) {
+				error = -ENOMEM;
+				break;
+			}
 
 			sctp_add_cmd_sf(commands, SCTP_CMD_REPLY,
 					SCTP_CHUNK(new_obj));
@@ -1396,7 +1398,8 @@ static int sctp_cmd_interpreter(enum sctp_event event_type,
 			if (!new_obj) {
 				if (cmd->obj.chunk)
 					sctp_chunk_free(cmd->obj.chunk);
-				goto nomem;
+				error = -ENOMEM;
+				break;
 			}
 			sctp_add_cmd_sf(commands, SCTP_CMD_REPLY,
 					SCTP_CHUNK(new_obj));
@@ -1443,8 +1446,10 @@ static int sctp_cmd_interpreter(enum sctp_event event_type,
 
 			/* Generate a SHUTDOWN chunk.  */
 			new_obj = sctp_make_shutdown(asoc, chunk);
-			if (!new_obj)
-				goto nomem;
+			if (!new_obj) {
+				error = -ENOMEM;
+				break;
+			}
 			sctp_add_cmd_sf(commands, SCTP_CMD_REPLY,
 					SCTP_CHUNK(new_obj));
 			break;
@@ -1780,11 +1785,17 @@ static int sctp_cmd_interpreter(enum sctp_event event_type,
 			break;
 		}
 
-		if (error)
+		if (error) {
+			cmd = sctp_next_cmd(commands);
+			while (cmd) {
+				if (cmd->verb == SCTP_CMD_REPLY)
+					sctp_chunk_free(cmd->obj.chunk);
+				cmd = sctp_next_cmd(commands);
+			}
 			break;
+		}
 	}
 
-out:
 	/* If this is in response to a received chunk, wait until
 	 * we are done with the packet to open the queue so that we don't
 	 * send multiple packets in response to a single request.
@@ -1799,7 +1810,4 @@ static int sctp_cmd_interpreter(enum sctp_event event_type,
 		sp->data_ready_signalled = 0;
 
 	return error;
-nomem:
-	error = -ENOMEM;
-	goto out;
 }
-- 
2.20.1


From 74b6d419f9128b3f6c75fdffaf8d2be0f0398c50 Mon Sep 17 00:00:00 2001
From: Pengcheng Yang <yangpc@wangsu.com>
Date: Mon, 30 Dec 2019 17:54:41 +0800
Subject: [PATCH 10/15] tcp: fix "old stuff" D-SACK causing SACK to be treated
 as D-SACK

[ Upstream commit c9655008e7845bcfdaac10a1ed8554ec167aea88 ]

When we receive a D-SACK, where the sequence number satisfies:
	undo_marker <= start_seq < end_seq <= prior_snd_una
we consider this is a valid D-SACK and tcp_is_sackblock_valid()
returns true, then this D-SACK is discarded as "old stuff",
but the variable first_sack_index is not marked as negative
in tcp_sacktag_write_queue().

If this D-SACK also carries a SACK that needs to be processed
(for example, the previous SACK segment was lost), this SACK
will be treated as a D-SACK in the following processing of
tcp_sacktag_write_queue(), which will eventually lead to
incorrect updates of undo_retrans and reordering.

Fixes: fd6dad616d4f ("[TCP]: Earlier SACK block verification & simplify access to them")
Signed-off-by: Pengcheng Yang <yangpc@wangsu.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 3a08ee81cbc3..578b65e6e65b 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1716,8 +1716,11 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb,
 		}
 
 		/* Ignore very old stuff early */
-		if (!after(sp[used_sacks].end_seq, prior_snd_una))
+		if (!after(sp[used_sacks].end_seq, prior_snd_una)) {
+			if (i == 0)
+				first_sack_index = -1;
 			continue;
+		}
 
 		used_sacks++;
 	}
-- 
2.20.1


From aed07a7ab6cd54d427deed80de07f6782cb58b6c Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Thu, 2 Jan 2020 17:23:45 +0800
Subject: [PATCH 11/15] vxlan: fix tos value before xmit

[ Upstream commit 71130f29979c7c7956b040673e6b9d5643003176 ]

Before ip_tunnel_ecn_encap() and udp_tunnel_xmit_skb() we should filter
tos value by RT_TOS() instead of using config tos directly.

vxlan_get_route() would filter the tos to fl4.flowi4_tos but we didn't
return it back, as geneve_get_v4_rt() did. So we have to use RT_TOS()
directly in function ip_tunnel_ecn_encap().

Fixes: 206aaafcd279 ("VXLAN: Use IP Tunnels tunnel ENC encap API")
Fixes: 1400615d64cf ("vxlan: allow setting ipv6 traffic class")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index d8a56df3933f..613f36681853 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2217,7 +2217,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		ndst = &rt->dst;
 		skb_tunnel_check_pmtu(skb, ndst, VXLAN_HEADROOM);
 
-		tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
+		tos = ip_tunnel_ecn_encap(RT_TOS(tos), old_iph, skb);
 		ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
 		err = vxlan_build_skb(skb, ndst, sizeof(struct iphdr),
 				      vni, md, flags, udp_sum);
@@ -2254,7 +2254,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 
 		skb_tunnel_check_pmtu(skb, ndst, VXLAN6_HEADROOM);
 
-		tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
+		tos = ip_tunnel_ecn_encap(RT_TOS(tos), old_iph, skb);
 		ttl = ttl ? : ip6_dst_hoplimit(ndst);
 		skb_scrub_packet(skb, xnet);
 		err = vxlan_build_skb(skb, ndst, sizeof(struct ipv6hdr),
-- 
2.20.1


From ee279dabd04e96c6401e130d2c5d690796407240 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 7 Jan 2020 01:42:24 -0800
Subject: [PATCH 12/15] vlan: fix memory leak in vlan_dev_set_egress_priority

[ Upstream commit 9bbd917e0bec9aebdbd0c8dbc966caec15eb33e9 ]

There are few cases where the ndo_uninit() handler might be not
called if an error happens while device is initialized.

Since vlan_newlink() calls vlan_changelink() before
trying to register the netdevice, we need to make sure
vlan_dev_uninit() has been called at least once,
or we might leak allocated memory.

BUG: memory leak
unreferenced object 0xffff888122a206c0 (size 32):
  comm "syz-executor511", pid 7124, jiffies 4294950399 (age 32.240s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 61 73 00 00 00 00 00 00 00 00  ......as........
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<000000000eb3bb85>] kmemleak_alloc_recursive include/linux/kmemleak.h:43 [inline]
    [<000000000eb3bb85>] slab_post_alloc_hook mm/slab.h:586 [inline]
    [<000000000eb3bb85>] slab_alloc mm/slab.c:3320 [inline]
    [<000000000eb3bb85>] kmem_cache_alloc_trace+0x145/0x2c0 mm/slab.c:3549
    [<000000007b99f620>] kmalloc include/linux/slab.h:556 [inline]
    [<000000007b99f620>] vlan_dev_set_egress_priority+0xcc/0x150 net/8021q/vlan_dev.c:194
    [<000000007b0cb745>] vlan_changelink+0xd6/0x140 net/8021q/vlan_netlink.c:126
    [<0000000065aba83a>] vlan_newlink+0x135/0x200 net/8021q/vlan_netlink.c:181
    [<00000000fb5dd7a2>] __rtnl_newlink+0x89a/0xb80 net/core/rtnetlink.c:3305
    [<00000000ae4273a1>] rtnl_newlink+0x4e/0x80 net/core/rtnetlink.c:3363
    [<00000000decab39f>] rtnetlink_rcv_msg+0x178/0x4b0 net/core/rtnetlink.c:5424
    [<00000000accba4ee>] netlink_rcv_skb+0x61/0x170 net/netlink/af_netlink.c:2477
    [<00000000319fe20f>] rtnetlink_rcv+0x1d/0x30 net/core/rtnetlink.c:5442
    [<00000000d51938dc>] netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
    [<00000000d51938dc>] netlink_unicast+0x223/0x310 net/netlink/af_netlink.c:1328
    [<00000000e539ac79>] netlink_sendmsg+0x2c0/0x570 net/netlink/af_netlink.c:1917
    [<000000006250c27e>] sock_sendmsg_nosec net/socket.c:639 [inline]
    [<000000006250c27e>] sock_sendmsg+0x54/0x70 net/socket.c:659
    [<00000000e2a156d1>] ____sys_sendmsg+0x2d0/0x300 net/socket.c:2330
    [<000000008c87466e>] ___sys_sendmsg+0x8a/0xd0 net/socket.c:2384
    [<00000000110e3054>] __sys_sendmsg+0x80/0xf0 net/socket.c:2417
    [<00000000d71077c8>] __do_sys_sendmsg net/socket.c:2426 [inline]
    [<00000000d71077c8>] __se_sys_sendmsg net/socket.c:2424 [inline]
    [<00000000d71077c8>] __x64_sys_sendmsg+0x23/0x30 net/socket.c:2424

Fixe: 07b5b17e157b ("[VLAN]: Use rtnl_link API")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/8021q/vlan.h         | 1 +
 net/8021q/vlan_dev.c     | 3 ++-
 net/8021q/vlan_netlink.c | 9 +++++----
 3 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h
index 44df1c3df02d..e9cd8ef2a245 100644
--- a/net/8021q/vlan.h
+++ b/net/8021q/vlan.h
@@ -114,6 +114,7 @@ int vlan_check_real_dev(struct net_device *real_dev,
 void vlan_setup(struct net_device *dev);
 int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack);
 void unregister_vlan_dev(struct net_device *dev, struct list_head *head);
+void vlan_dev_uninit(struct net_device *dev);
 bool vlan_dev_inherit_address(struct net_device *dev,
 			      struct net_device *real_dev);
 
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index fce3b7eebffb..84ef83772114 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -612,7 +612,8 @@ static int vlan_dev_init(struct net_device *dev)
 	return 0;
 }
 
-static void vlan_dev_uninit(struct net_device *dev)
+/* Note: this function might be called multiple times for the same device. */
+void vlan_dev_uninit(struct net_device *dev)
 {
 	struct vlan_priority_tci_mapping *pm;
 	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c
index 9b60c1e399e2..6e19aeb888fb 100644
--- a/net/8021q/vlan_netlink.c
+++ b/net/8021q/vlan_netlink.c
@@ -181,10 +181,11 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev,
 		return -EINVAL;
 
 	err = vlan_changelink(dev, tb, data, extack);
-	if (err < 0)
-		return err;
-
-	return register_vlan_dev(dev, extack);
+	if (!err)
+		err = register_vlan_dev(dev, extack);
+	if (err)
+		vlan_dev_uninit(dev);
+	return err;
 }
 
 static inline size_t vlan_qos_map_size(unsigned int n)
-- 
2.20.1


From 2ebf55695be0676334cd2627d483318cf65730dd Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 7 Jan 2020 01:42:25 -0800
Subject: [PATCH 13/15] vlan: vlan_changelink() should propagate errors

[ Upstream commit eb8ef2a3c50092bb018077c047b8dba1ce0e78e3 ]

Both vlan_dev_change_flags() and vlan_dev_set_egress_priority()
can return an error. vlan_changelink() should not ignore them.

Fixes: 07b5b17e157b ("[VLAN]: Use rtnl_link API")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/8021q/vlan_netlink.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c
index 6e19aeb888fb..74042b9d7f73 100644
--- a/net/8021q/vlan_netlink.c
+++ b/net/8021q/vlan_netlink.c
@@ -110,11 +110,13 @@ static int vlan_changelink(struct net_device *dev, struct nlattr *tb[],
 	struct ifla_vlan_flags *flags;
 	struct ifla_vlan_qos_mapping *m;
 	struct nlattr *attr;
-	int rem;
+	int rem, err;
 
 	if (data[IFLA_VLAN_FLAGS]) {
 		flags = nla_data(data[IFLA_VLAN_FLAGS]);
-		vlan_dev_change_flags(dev, flags->flags, flags->mask);
+		err = vlan_dev_change_flags(dev, flags->flags, flags->mask);
+		if (err)
+			return err;
 	}
 	if (data[IFLA_VLAN_INGRESS_QOS]) {
 		nla_for_each_nested(attr, data[IFLA_VLAN_INGRESS_QOS], rem) {
@@ -125,7 +127,9 @@ static int vlan_changelink(struct net_device *dev, struct nlattr *tb[],
 	if (data[IFLA_VLAN_EGRESS_QOS]) {
 		nla_for_each_nested(attr, data[IFLA_VLAN_EGRESS_QOS], rem) {
 			m = nla_data(attr);
-			vlan_dev_set_egress_priority(dev, m->from, m->to);
+			err = vlan_dev_set_egress_priority(dev, m->from, m->to);
+			if (err)
+				return err;
 		}
 	}
 	return 0;
-- 
2.20.1


From aac9ed532228f36550e5a82da59813f1e3fa107a Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 6 Jan 2020 18:01:55 +0000
Subject: [PATCH 14/15] mlxsw: spectrum_qdisc: Ignore grafting of invisible
 FIFO

[ Upstream commit 3971a535b839489e4ea31796cc086e6ce616318c ]

The following patch will change PRIO to replace a removed Qdisc with an
invisible FIFO, instead of NOOP. mlxsw will see this replacement due to the
graft message that is generated. But because FIFO does not issue its own
REPLACE message, when the graft operation takes place, the Qdisc that mlxsw
tracks under the indicated band is still the old one. The child
handle (0:0) therefore does not match, and mlxsw rejects the graft
operation, which leads to an extack message:

    Warning: Offloading graft operation failed.

Fix by ignoring the invisible children in the PRIO graft handler. The
DESTROY message of the removed Qdisc is going to follow shortly and handle
the removal.

Fixes: 32dc5efc6cb4 ("mlxsw: spectrum: qdiscs: prio: Handle graft command")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c
index bdf53cf350f6..720514b5c006 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c
@@ -650,6 +650,13 @@ mlxsw_sp_qdisc_prio_graft(struct mlxsw_sp_port *mlxsw_sp_port,
 	    mlxsw_sp_port->tclass_qdiscs[tclass_num].handle == p->child_handle)
 		return 0;
 
+	if (!p->child_handle) {
+		/* This is an invisible FIFO replacing the original Qdisc.
+		 * Ignore it--the original Qdisc's destroy will follow.
+		 */
+		return 0;
+	}
+
 	/* See if the grafted qdisc is already offloaded on any tclass. If so,
 	 * unoffload it.
 	 */
-- 
2.20.1


From 6e42852229a0b51ec4210e0a0c0adf62546a60c3 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 6 Jan 2020 18:01:56 +0000
Subject: [PATCH 15/15] net: sch_prio: When ungrafting, replace with FIFO

[ Upstream commit 240ce7f6428ff5188b9eedc066e1e4d645b8635f ]

When a child Qdisc is removed from one of the PRIO Qdisc's bands, it is
replaced unconditionally by a NOOP qdisc. As a result, any traffic hitting
that band gets dropped. That is incorrect--no Qdisc was explicitly added
when PRIO was created, and after removal, none should have to be added
either.

Fix PRIO by first attempting to create a default Qdisc and only falling
back to noop when that fails. This pattern of attempting to create an
invisible FIFO, using NOOP only as a fallback, is also seen in other
Qdiscs.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_prio.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index 5672abede0cc..1cbbd8c31405 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -314,8 +314,14 @@ static int prio_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 	bool any_qdisc_is_offloaded;
 	int err;
 
-	if (new == NULL)
-		new = &noop_qdisc;
+	if (!new) {
+		new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops,
+					TC_H_MAKE(sch->handle, arg), extack);
+		if (!new)
+			new = &noop_qdisc;
+		else
+			qdisc_hash_add(new, true);
+	}
 
 	*old = qdisc_replace(sch, new, &q->queues[band]);
 
-- 
2.20.1


[-- Attachment #3: net_54.mbox --]
[-- Type: Application/Octet-Stream, Size: 62576 bytes --]

From 11a8ecf778e9d69a522530f1ec348d1840558810 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 6 Jan 2020 06:45:37 -0800
Subject: [PATCH 01/24] gtp: fix bad unlock balance in gtp_encap_enable_socket

[ Upstream commit 90d72256addff9e5f8ad645e8f632750dd1f8935 ]

WARNING: bad unlock balance detected!
5.5.0-rc5-syzkaller #0 Not tainted
-------------------------------------
syz-executor921/9688 is trying to release lock (sk_lock-AF_INET6) at:
[<ffffffff84bf8506>] gtp_encap_enable_socket+0x146/0x400 drivers/net/gtp.c:830
but there are no more locks to release!

other info that might help us debug this:
2 locks held by syz-executor921/9688:
 #0: ffffffff8a4d8840 (rtnl_mutex){+.+.}, at: rtnl_lock net/core/rtnetlink.c:72 [inline]
 #0: ffffffff8a4d8840 (rtnl_mutex){+.+.}, at: rtnetlink_rcv_msg+0x405/0xaf0 net/core/rtnetlink.c:5421
 #1: ffff88809304b560 (slock-AF_INET6){+...}, at: spin_lock_bh include/linux/spinlock.h:343 [inline]
 #1: ffff88809304b560 (slock-AF_INET6){+...}, at: release_sock+0x20/0x1c0 net/core/sock.c:2951

stack backtrace:
CPU: 0 PID: 9688 Comm: syz-executor921 Not tainted 5.5.0-rc5-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x197/0x210 lib/dump_stack.c:118
 print_unlock_imbalance_bug kernel/locking/lockdep.c:4008 [inline]
 print_unlock_imbalance_bug.cold+0x114/0x123 kernel/locking/lockdep.c:3984
 __lock_release kernel/locking/lockdep.c:4242 [inline]
 lock_release+0x5f2/0x960 kernel/locking/lockdep.c:4503
 sock_release_ownership include/net/sock.h:1496 [inline]
 release_sock+0x17c/0x1c0 net/core/sock.c:2961
 gtp_encap_enable_socket+0x146/0x400 drivers/net/gtp.c:830
 gtp_encap_enable drivers/net/gtp.c:852 [inline]
 gtp_newlink+0x9fc/0xc60 drivers/net/gtp.c:666
 __rtnl_newlink+0x109e/0x1790 net/core/rtnetlink.c:3305
 rtnl_newlink+0x69/0xa0 net/core/rtnetlink.c:3363
 rtnetlink_rcv_msg+0x45e/0xaf0 net/core/rtnetlink.c:5424
 netlink_rcv_skb+0x177/0x450 net/netlink/af_netlink.c:2477
 rtnetlink_rcv+0x1d/0x30 net/core/rtnetlink.c:5442
 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
 netlink_unicast+0x58c/0x7d0 net/netlink/af_netlink.c:1328
 netlink_sendmsg+0x91c/0xea0 net/netlink/af_netlink.c:1917
 sock_sendmsg_nosec net/socket.c:639 [inline]
 sock_sendmsg+0xd7/0x130 net/socket.c:659
 ____sys_sendmsg+0x753/0x880 net/socket.c:2330
 ___sys_sendmsg+0x100/0x170 net/socket.c:2384
 __sys_sendmsg+0x105/0x1d0 net/socket.c:2417
 __do_sys_sendmsg net/socket.c:2426 [inline]
 __se_sys_sendmsg net/socket.c:2424 [inline]
 __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2424
 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x445d49
Code: e8 bc b7 02 00 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 2b 12 fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f8019074db8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 00000000006dac38 RCX: 0000000000445d49
RDX: 0000000000000000 RSI: 0000000020000180 RDI: 0000000000000003
RBP: 00000000006dac30 R08: 0000000000000004 R09: 0000000000000000
R10: 0000000000000008 R11: 0000000000000246 R12: 00000000006dac3c
R13: 00007ffea687f6bf R14: 00007f80190759c0 R15: 20c49ba5e353f7cf

Fixes: e198987e7dd7 ("gtp: fix suspicious RCU usage")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/gtp.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index fca471e27f39..f6222ada6818 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -813,7 +813,7 @@ static struct sock *gtp_encap_enable_socket(int fd, int type,
 	lock_sock(sock->sk);
 	if (sock->sk->sk_user_data) {
 		sk = ERR_PTR(-EBUSY);
-		goto out_sock;
+		goto out_rel_sock;
 	}
 
 	sk = sock->sk;
@@ -826,8 +826,9 @@ static struct sock *gtp_encap_enable_socket(int fd, int type,
 
 	setup_udp_tunnel_sock(sock_net(sock->sk), sock, &tuncfg);
 
-out_sock:
+out_rel_sock:
 	release_sock(sock->sk);
+out_sock:
 	sockfd_put(sock);
 	return sk;
 }
-- 
2.20.1


From 25b274924a259aea5d8d86417f762cca8f2b91e5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 6 Jan 2020 12:30:48 -0800
Subject: [PATCH 02/24] macvlan: do not assume mac_header is set in
 macvlan_broadcast()

[ Upstream commit 96cc4b69581db68efc9749ef32e9cf8e0160c509 ]

Use of eth_hdr() in tx path is error prone.

Many drivers call skb_reset_mac_header() before using it,
but others do not.

Commit 6d1ccff62780 ("net: reset mac header in dev_start_xmit()")
attempted to fix this generically, but commit d346a3fae3ff
("packet: introduce PACKET_QDISC_BYPASS socket option") brought
back the macvlan bug.

Lets add a new helper, so that tx paths no longer have
to call skb_reset_mac_header() only to get a pointer
to skb->data.

Hopefully we will be able to revert 6d1ccff62780
("net: reset mac header in dev_start_xmit()") and save few cycles
in transmit fast path.

BUG: KASAN: use-after-free in __get_unaligned_cpu32 include/linux/unaligned/packed_struct.h:19 [inline]
BUG: KASAN: use-after-free in mc_hash drivers/net/macvlan.c:251 [inline]
BUG: KASAN: use-after-free in macvlan_broadcast+0x547/0x620 drivers/net/macvlan.c:277
Read of size 4 at addr ffff8880a4932401 by task syz-executor947/9579

CPU: 0 PID: 9579 Comm: syz-executor947 Not tainted 5.5.0-rc4-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x197/0x210 lib/dump_stack.c:118
 print_address_description.constprop.0.cold+0xd4/0x30b mm/kasan/report.c:374
 __kasan_report.cold+0x1b/0x41 mm/kasan/report.c:506
 kasan_report+0x12/0x20 mm/kasan/common.c:639
 __asan_report_load_n_noabort+0xf/0x20 mm/kasan/generic_report.c:145
 __get_unaligned_cpu32 include/linux/unaligned/packed_struct.h:19 [inline]
 mc_hash drivers/net/macvlan.c:251 [inline]
 macvlan_broadcast+0x547/0x620 drivers/net/macvlan.c:277
 macvlan_queue_xmit drivers/net/macvlan.c:520 [inline]
 macvlan_start_xmit+0x402/0x77f drivers/net/macvlan.c:559
 __netdev_start_xmit include/linux/netdevice.h:4447 [inline]
 netdev_start_xmit include/linux/netdevice.h:4461 [inline]
 dev_direct_xmit+0x419/0x630 net/core/dev.c:4079
 packet_direct_xmit+0x1a9/0x250 net/packet/af_packet.c:240
 packet_snd net/packet/af_packet.c:2966 [inline]
 packet_sendmsg+0x260d/0x6220 net/packet/af_packet.c:2991
 sock_sendmsg_nosec net/socket.c:639 [inline]
 sock_sendmsg+0xd7/0x130 net/socket.c:659
 __sys_sendto+0x262/0x380 net/socket.c:1985
 __do_sys_sendto net/socket.c:1997 [inline]
 __se_sys_sendto net/socket.c:1993 [inline]
 __x64_sys_sendto+0xe1/0x1a0 net/socket.c:1993
 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x442639
Code: 18 89 d0 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 5b 10 fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007ffc13549e08 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000442639
RDX: 000000000000000e RSI: 0000000020000080 RDI: 0000000000000003
RBP: 0000000000000004 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 0000000000403bb0 R14: 0000000000000000 R15: 0000000000000000

Allocated by task 9389:
 save_stack+0x23/0x90 mm/kasan/common.c:72
 set_track mm/kasan/common.c:80 [inline]
 __kasan_kmalloc mm/kasan/common.c:513 [inline]
 __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:486
 kasan_kmalloc+0x9/0x10 mm/kasan/common.c:527
 __do_kmalloc mm/slab.c:3656 [inline]
 __kmalloc+0x163/0x770 mm/slab.c:3665
 kmalloc include/linux/slab.h:561 [inline]
 tomoyo_realpath_from_path+0xc5/0x660 security/tomoyo/realpath.c:252
 tomoyo_get_realpath security/tomoyo/file.c:151 [inline]
 tomoyo_path_perm+0x230/0x430 security/tomoyo/file.c:822
 tomoyo_inode_getattr+0x1d/0x30 security/tomoyo/tomoyo.c:129
 security_inode_getattr+0xf2/0x150 security/security.c:1222
 vfs_getattr+0x25/0x70 fs/stat.c:115
 vfs_statx_fd+0x71/0xc0 fs/stat.c:145
 vfs_fstat include/linux/fs.h:3265 [inline]
 __do_sys_newfstat+0x9b/0x120 fs/stat.c:378
 __se_sys_newfstat fs/stat.c:375 [inline]
 __x64_sys_newfstat+0x54/0x80 fs/stat.c:375
 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Freed by task 9389:
 save_stack+0x23/0x90 mm/kasan/common.c:72
 set_track mm/kasan/common.c:80 [inline]
 kasan_set_free_info mm/kasan/common.c:335 [inline]
 __kasan_slab_free+0x102/0x150 mm/kasan/common.c:474
 kasan_slab_free+0xe/0x10 mm/kasan/common.c:483
 __cache_free mm/slab.c:3426 [inline]
 kfree+0x10a/0x2c0 mm/slab.c:3757
 tomoyo_realpath_from_path+0x1a7/0x660 security/tomoyo/realpath.c:289
 tomoyo_get_realpath security/tomoyo/file.c:151 [inline]
 tomoyo_path_perm+0x230/0x430 security/tomoyo/file.c:822
 tomoyo_inode_getattr+0x1d/0x30 security/tomoyo/tomoyo.c:129
 security_inode_getattr+0xf2/0x150 security/security.c:1222
 vfs_getattr+0x25/0x70 fs/stat.c:115
 vfs_statx_fd+0x71/0xc0 fs/stat.c:145
 vfs_fstat include/linux/fs.h:3265 [inline]
 __do_sys_newfstat+0x9b/0x120 fs/stat.c:378
 __se_sys_newfstat fs/stat.c:375 [inline]
 __x64_sys_newfstat+0x54/0x80 fs/stat.c:375
 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

The buggy address belongs to the object at ffff8880a4932000
 which belongs to the cache kmalloc-4k of size 4096
The buggy address is located 1025 bytes inside of
 4096-byte region [ffff8880a4932000, ffff8880a4933000)
The buggy address belongs to the page:
page:ffffea0002924c80 refcount:1 mapcount:0 mapping:ffff8880aa402000 index:0x0 compound_mapcount: 0
raw: 00fffe0000010200 ffffea0002846208 ffffea00028f3888 ffff8880aa402000
raw: 0000000000000000 ffff8880a4932000 0000000100000001 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff8880a4932300: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff8880a4932380: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff8880a4932400: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                   ^
 ffff8880a4932480: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff8880a4932500: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb

Fixes: b863ceb7ddce ("[NET]: Add macvlan driver")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macvlan.c    | 2 +-
 include/linux/if_ether.h | 8 ++++++++
 2 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 05631d97eeb4..747c0542a53c 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -259,7 +259,7 @@ static void macvlan_broadcast(struct sk_buff *skb,
 			      struct net_device *src,
 			      enum macvlan_mode mode)
 {
-	const struct ethhdr *eth = eth_hdr(skb);
+	const struct ethhdr *eth = skb_eth_hdr(skb);
 	const struct macvlan_dev *vlan;
 	struct sk_buff *nskb;
 	unsigned int i;
diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h
index 76cf11e905e1..8a9792a6427a 100644
--- a/include/linux/if_ether.h
+++ b/include/linux/if_ether.h
@@ -24,6 +24,14 @@ static inline struct ethhdr *eth_hdr(const struct sk_buff *skb)
 	return (struct ethhdr *)skb_mac_header(skb);
 }
 
+/* Prefer this version in TX path, instead of
+ * skb_reset_mac_header() + eth_hdr()
+ */
+static inline struct ethhdr *skb_eth_hdr(const struct sk_buff *skb)
+{
+	return (struct ethhdr *)skb->data;
+}
+
 static inline struct ethhdr *inner_eth_hdr(const struct sk_buff *skb)
 {
 	return (struct ethhdr *)skb_inner_mac_header(skb);
-- 
2.20.1


From 19a1a2c41db1210f86058cad827dfb18124b30f7 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sat, 4 Jan 2020 23:14:51 +0100
Subject: [PATCH 03/24] net: dsa: mv88e6xxx: Preserve priority when setting CPU
 port.

[ Upstream commit d8dc2c9676e614ef62f54a155b50076888c8a29a ]

The 6390 family uses an extended register to set the port connected to
the CPU. The lower 5 bits indicate the port, the upper three bits are
the priority of the frames as they pass through the switch, what
egress queue they should use, etc. Since frames being set to the CPU
are typically management frames, BPDU, IGMP, ARP, etc set the priority
to 7, the reset default, and the highest.

Fixes: 33641994a676 ("net: dsa: mv88e6xxx: Monitor and Management tables")
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Tested-by: Chris Healy <cphealy@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/global1.c | 5 +++++
 drivers/net/dsa/mv88e6xxx/global1.h | 1 +
 2 files changed, 6 insertions(+)

diff --git a/drivers/net/dsa/mv88e6xxx/global1.c b/drivers/net/dsa/mv88e6xxx/global1.c
index 25ec4c0ac589..8a903624fdd7 100644
--- a/drivers/net/dsa/mv88e6xxx/global1.c
+++ b/drivers/net/dsa/mv88e6xxx/global1.c
@@ -332,6 +332,11 @@ int mv88e6390_g1_set_cpu_port(struct mv88e6xxx_chip *chip, int port)
 {
 	u16 ptr = MV88E6390_G1_MONITOR_MGMT_CTL_PTR_CPU_DEST;
 
+	/* Use the default high priority for management frames sent to
+	 * the CPU.
+	 */
+	port |= MV88E6390_G1_MONITOR_MGMT_CTL_PTR_CPU_DEST_MGMTPRI;
+
 	return mv88e6390_g1_monitor_write(chip, ptr, port);
 }
 
diff --git a/drivers/net/dsa/mv88e6xxx/global1.h b/drivers/net/dsa/mv88e6xxx/global1.h
index 0870fcc8bfc8..0ae96a1e919b 100644
--- a/drivers/net/dsa/mv88e6xxx/global1.h
+++ b/drivers/net/dsa/mv88e6xxx/global1.h
@@ -210,6 +210,7 @@
 #define MV88E6390_G1_MONITOR_MGMT_CTL_PTR_INGRESS_DEST		0x2000
 #define MV88E6390_G1_MONITOR_MGMT_CTL_PTR_EGRESS_DEST		0x2100
 #define MV88E6390_G1_MONITOR_MGMT_CTL_PTR_CPU_DEST		0x3000
+#define MV88E6390_G1_MONITOR_MGMT_CTL_PTR_CPU_DEST_MGMTPRI	0x00e0
 #define MV88E6390_G1_MONITOR_MGMT_CTL_DATA_MASK			0x00ff
 
 /* Offset 0x1C: Global Control 2 */
-- 
2.20.1


From 3686c2944301bc2f513389693f11b72f45dc2f23 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Thu, 2 Jan 2020 15:33:34 +0100
Subject: [PATCH 04/24] net: freescale: fec: Fix ethtool -d runtime PM

[ Upstream commit c72a0bc0aa19f49160330a65ab77184b5b7d131b ]

In order to dump the FECs registers the clocks have to be ticking,
otherwise a data abort occurs.  Add calls to runtime PM so they are
enabled and later disabled.

Fixes: e8fcfcd5684a ("net: fec: optimize the clock management to save power")
Reported-by: Chris Healy <Chris.Healy@zii.aero>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_main.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 4bb30761abfc..8336f4cbaf95 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -2199,8 +2199,14 @@ static void fec_enet_get_regs(struct net_device *ndev,
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
 	u32 __iomem *theregs = (u32 __iomem *)fep->hwp;
+	struct device *dev = &fep->pdev->dev;
 	u32 *buf = (u32 *)regbuf;
 	u32 i, off;
+	int ret;
+
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0)
+		return;
 
 	regs->version = fec_enet_register_version;
 
@@ -2216,6 +2222,9 @@ static void fec_enet_get_regs(struct net_device *ndev,
 		off >>= 2;
 		buf[off] = readl(&theregs[off]);
 	}
+
+	pm_runtime_mark_last_busy(dev);
+	pm_runtime_put_autosuspend(dev);
 }
 
 static int fec_enet_get_ts_info(struct net_device *ndev,
-- 
2.20.1


From 313cae5ffe05e38c90d1e0ea847c3c4df7c4fbc9 Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wens@csie.org>
Date: Mon, 6 Jan 2020 11:09:45 +0800
Subject: [PATCH 05/24] net: stmmac: dwmac-sun8i: Allow all RGMII modes

[ Upstream commit f1239d8aa84dad8fe4b6cc1356f40fc8e842db47 ]

Allow all the RGMII modes to be used. This would allow us to represent
the hardware better in the device tree with RGMII_ID where in most
cases the PHY's internal delay for both RX and TX are used.

Fixes: 9f93ac8d4085 ("net-next: stmmac: Add dwmac-sun8i")
Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index 6e47be63a43c..e9e0867ec139 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -957,6 +957,9 @@ static int sun8i_dwmac_set_syscon(struct stmmac_priv *priv)
 		/* default */
 		break;
 	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
 		reg |= SYSCON_EPIT | SYSCON_ETCS_INT_GMII;
 		break;
 	case PHY_INTERFACE_MODE_RMII:
-- 
2.20.1


From a0886872e02b505f529b6c2a04cc65ab463627d6 Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wens@csie.org>
Date: Mon, 6 Jan 2020 11:09:22 +0800
Subject: [PATCH 06/24] net: stmmac: dwmac-sunxi: Allow all RGMII modes

[ Upstream commit 52cc73e5404c7ba0cbfc50cb4c265108c84b3d5a ]

Allow all the RGMII modes to be used. This would allow us to represent
the hardware better in the device tree with RGMII_ID where in most
cases the PHY's internal delay for both RX and TX are used.

Fixes: af0bd4e9ba80 ("net: stmmac: sunxi platform extensions for GMAC in Allwinner A20 SoC's")
Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
index a299da3971b4..102d637bc84a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
@@ -44,7 +44,7 @@ static int sun7i_gmac_init(struct platform_device *pdev, void *priv)
 	 * rate, which then uses the auto-reparenting feature of the
 	 * clock driver, and enabling/disabling the clock.
 	 */
-	if (gmac->interface == PHY_INTERFACE_MODE_RGMII) {
+	if (phy_interface_mode_is_rgmii(gmac->interface)) {
 		clk_set_rate(gmac->tx_clk, SUN7I_GMAC_GMII_RGMII_RATE);
 		clk_prepare_enable(gmac->tx_clk);
 		gmac->clk_enabled = 1;
-- 
2.20.1


From 4ea9aa47e1eeca5f5fb91fbfc8ca105642185d92 Mon Sep 17 00:00:00 2001
From: Jose Abreu <Jose.Abreu@synopsys.com>
Date: Tue, 7 Jan 2020 13:35:42 +0100
Subject: [PATCH 07/24] net: stmmac: Fixed link does not need MDIO Bus

[ Upstream commit da29f2d84bd10234df570b7f07cbd0166e738230 ]

When using fixed link we don't need the MDIO bus support.

Reported-by: Heiko Stuebner <heiko@sntech.de>
Reported-by: kernelci.org bot <bot@kernelci.org>
Fixes: d3e014ec7d5e ("net: stmmac: platform: Fix MDIO init for platforms without PHY")
Signed-off-by: Jose Abreu <Jose.Abreu@synopsys.com>
Acked-by: Sriram Dash <Sriram.dash@samsung.com>
Tested-by: Patrice Chotard <patrice.chotard@st.com>
Tested-by: Heiko Stuebner <heiko@sntech.de>
Acked-by: Neil Armstrong <narmstrong@baylibre.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Tested-by: Florian Fainelli <f.fainelli@gmail> # Lamobo R1 (fixed-link + MDIO sub node for roboswitch).
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 1f230bd854c4..5150551c28be 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -320,7 +320,7 @@ static int stmmac_mtl_setup(struct platform_device *pdev,
 static int stmmac_dt_phy(struct plat_stmmacenet_data *plat,
 			 struct device_node *np, struct device *dev)
 {
-	bool mdio = false;
+	bool mdio = !of_phy_is_fixed_link(np);
 	static const struct of_device_id need_mdio_ids[] = {
 		{ .compatible = "snps,dwc-qos-ethernet-4.10" },
 		{},
-- 
2.20.1


From 11ca45d44e72658335dd92131cc12f80014c16a6 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 7 Jan 2020 10:57:01 -0800
Subject: [PATCH 08/24] net: usb: lan78xx: fix possible skb leak

[ Upstream commit 47240ba0cd09bb6fe6db9889582048324999dfa4 ]

If skb_linearize() fails, we need to free the skb.

TSO makes skb bigger, and this bug might be the reason
Raspberry Pi 3B+ users had to disable TSO.

Fixes: 55d7de9de6c3 ("Microchip's LAN7800 family USB 2/3 to 10/100/1000 Ethernet device driver")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: RENARD Pierre-Francois <pfrenard@gmail.com>
Cc: Stefan Wahren <stefan.wahren@i2se.com>
Cc: Woojung Huh <woojung.huh@microchip.com>
Cc: Microchip Linux Driver Support <UNGLinuxDriver@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/lan78xx.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 0becc79fd431..05141027dda8 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -2724,11 +2724,6 @@ static int lan78xx_stop(struct net_device *net)
 	return 0;
 }
 
-static int lan78xx_linearize(struct sk_buff *skb)
-{
-	return skb_linearize(skb);
-}
-
 static struct sk_buff *lan78xx_tx_prep(struct lan78xx_net *dev,
 				       struct sk_buff *skb, gfp_t flags)
 {
@@ -2740,8 +2735,10 @@ static struct sk_buff *lan78xx_tx_prep(struct lan78xx_net *dev,
 		return NULL;
 	}
 
-	if (lan78xx_linearize(skb) < 0)
+	if (skb_linearize(skb)) {
+		dev_kfree_skb_any(skb);
 		return NULL;
+	}
 
 	tx_cmd_a = (u32)(skb->len & TX_CMD_A_LEN_MASK_) | TX_CMD_A_FCS_;
 
-- 
2.20.1


From 1633777f090e5bc3d6ef982cf13dfcd14f2bc2cb Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 6 Jan 2020 06:10:39 -0800
Subject: [PATCH 09/24] pkt_sched: fq: do not accept silly TCA_FQ_QUANTUM

[ Upstream commit d9e15a2733067c9328fb56d98fe8e574fa19ec31 ]

As diagnosed by Florian :

If TCA_FQ_QUANTUM is set to 0x80000000, fq_deueue()
can loop forever in :

if (f->credit <= 0) {
  f->credit += q->quantum;
  goto begin;
}

... because f->credit is either 0 or -2147483648.

Let's limit TCA_FQ_QUANTUM to no more than 1 << 20 :
This max value should limit risks of breaking user setups
while fixing this bug.

Fixes: afe4fd062416 ("pkt_sched: fq: Fair Queue packet scheduler")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Diagnosed-by: Florian Westphal <fw@strlen.de>
Reported-by: syzbot+dc9071cc5a85950bdfce@syzkaller.appspotmail.com
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_fq.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 78ecdf146882..712ad248d6a7 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -787,10 +787,12 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt,
 	if (tb[TCA_FQ_QUANTUM]) {
 		u32 quantum = nla_get_u32(tb[TCA_FQ_QUANTUM]);
 
-		if (quantum > 0)
+		if (quantum > 0 && quantum <= (1 << 20)) {
 			q->quantum = quantum;
-		else
+		} else {
+			NL_SET_ERR_MSG_MOD(extack, "invalid quantum");
 			err = -EINVAL;
+		}
 	}
 
 	if (tb[TCA_FQ_INITIAL_QUANTUM])
-- 
2.20.1


From eaa16df5cdf481c37277108b4785fce16bfa7668 Mon Sep 17 00:00:00 2001
From: Wen Yang <wenyang@linux.alibaba.com>
Date: Thu, 2 Jan 2020 17:21:43 +0800
Subject: [PATCH 10/24] sch_cake: avoid possible divide by zero in
 cake_enqueue()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 68aab823c223646fab311f8a6581994facee66a0 ]

The variables 'window_interval' is u64 and do_div()
truncates it to 32 bits, which means it can test
non-zero and be truncated to zero for division.
The unit of window_interval is nanoseconds,
so its lower 32-bit is relatively easy to exceed.
Fix this issue by using div64_u64() instead.

Fixes: 7298de9cd725 ("sch_cake: Add ingress mode")
Signed-off-by: Wen Yang <wenyang@linux.alibaba.com>
Cc: Kevin Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk>
Cc: Toke Høiland-Jørgensen <toke@redhat.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: cake@lists.bufferbloat.net
Cc: netdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Acked-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_cake.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 53a80bc6b13a..dd0e8680b030 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -1769,7 +1769,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 						      q->avg_window_begin));
 			u64 b = q->avg_window_bytes * (u64)NSEC_PER_SEC;
 
-			do_div(b, window_interval);
+			b = div64_u64(b, window_interval);
 			q->avg_peak_bandwidth =
 				cake_ewma(q->avg_peak_bandwidth, b,
 					  b > q->avg_peak_bandwidth ? 2 : 8);
-- 
2.20.1


From 173cd6dc91dc18d605f1464e9eccce116f50a16d Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sat, 4 Jan 2020 14:15:02 +0800
Subject: [PATCH 11/24] sctp: free cmd->obj.chunk for the unprocessed
 SCTP_CMD_REPLY

[ Upstream commit be7a7729207797476b6666f046d765bdf9630407 ]

This patch is to fix a memleak caused by no place to free cmd->obj.chunk
for the unprocessed SCTP_CMD_REPLY. This issue occurs when failing to
process a cmd while there're still SCTP_CMD_REPLY cmds on the cmd seq
with an allocated chunk in cmd->obj.chunk.

So fix it by freeing cmd->obj.chunk for each SCTP_CMD_REPLY cmd left on
the cmd seq when any cmd returns error. While at it, also remove 'nomem'
label.

Reported-by: syzbot+107c4aff5f392bf1517f@syzkaller.appspotmail.com
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sm_sideeffect.c | 28 ++++++++++++++++++----------
 1 file changed, 18 insertions(+), 10 deletions(-)

diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index e52b2128e43b..b06cae508158 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -1358,8 +1358,10 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type,
 			/* Generate an INIT ACK chunk.  */
 			new_obj = sctp_make_init_ack(asoc, chunk, GFP_ATOMIC,
 						     0);
-			if (!new_obj)
-				goto nomem;
+			if (!new_obj) {
+				error = -ENOMEM;
+				break;
+			}
 
 			sctp_add_cmd_sf(commands, SCTP_CMD_REPLY,
 					SCTP_CHUNK(new_obj));
@@ -1381,7 +1383,8 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type,
 			if (!new_obj) {
 				if (cmd->obj.chunk)
 					sctp_chunk_free(cmd->obj.chunk);
-				goto nomem;
+				error = -ENOMEM;
+				break;
 			}
 			sctp_add_cmd_sf(commands, SCTP_CMD_REPLY,
 					SCTP_CHUNK(new_obj));
@@ -1428,8 +1431,10 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type,
 
 			/* Generate a SHUTDOWN chunk.  */
 			new_obj = sctp_make_shutdown(asoc, chunk);
-			if (!new_obj)
-				goto nomem;
+			if (!new_obj) {
+				error = -ENOMEM;
+				break;
+			}
 			sctp_add_cmd_sf(commands, SCTP_CMD_REPLY,
 					SCTP_CHUNK(new_obj));
 			break;
@@ -1765,11 +1770,17 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type,
 			break;
 		}
 
-		if (error)
+		if (error) {
+			cmd = sctp_next_cmd(commands);
+			while (cmd) {
+				if (cmd->verb == SCTP_CMD_REPLY)
+					sctp_chunk_free(cmd->obj.chunk);
+				cmd = sctp_next_cmd(commands);
+			}
 			break;
+		}
 	}
 
-out:
 	/* If this is in response to a received chunk, wait until
 	 * we are done with the packet to open the queue so that we don't
 	 * send multiple packets in response to a single request.
@@ -1784,7 +1795,4 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type,
 		sp->data_ready_signalled = 0;
 
 	return error;
-nomem:
-	error = -ENOMEM;
-	goto out;
 }
-- 
2.20.1


From fa337c6931e66dbf747cf14daeaac39978aae69b Mon Sep 17 00:00:00 2001
From: Pengcheng Yang <yangpc@wangsu.com>
Date: Mon, 30 Dec 2019 17:54:41 +0800
Subject: [PATCH 12/24] tcp: fix "old stuff" D-SACK causing SACK to be treated
 as D-SACK

[ Upstream commit c9655008e7845bcfdaac10a1ed8554ec167aea88 ]

When we receive a D-SACK, where the sequence number satisfies:
	undo_marker <= start_seq < end_seq <= prior_snd_una
we consider this is a valid D-SACK and tcp_is_sackblock_valid()
returns true, then this D-SACK is discarded as "old stuff",
but the variable first_sack_index is not marked as negative
in tcp_sacktag_write_queue().

If this D-SACK also carries a SACK that needs to be processed
(for example, the previous SACK segment was lost), this SACK
will be treated as a D-SACK in the following processing of
tcp_sacktag_write_queue(), which will eventually lead to
incorrect updates of undo_retrans and reordering.

Fixes: fd6dad616d4f ("[TCP]: Earlier SACK block verification & simplify access to them")
Signed-off-by: Pengcheng Yang <yangpc@wangsu.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a2e52ad7cdab..67e44e6717b0 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1727,8 +1727,11 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb,
 		}
 
 		/* Ignore very old stuff early */
-		if (!after(sp[used_sacks].end_seq, prior_snd_una))
+		if (!after(sp[used_sacks].end_seq, prior_snd_una)) {
+			if (i == 0)
+				first_sack_index = -1;
 			continue;
+		}
 
 		used_sacks++;
 	}
-- 
2.20.1


From 305958f75ba47d615a2e5d1bb5513fe8f139070e Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Thu, 2 Jan 2020 17:23:45 +0800
Subject: [PATCH 13/24] vxlan: fix tos value before xmit

[ Upstream commit 71130f29979c7c7956b040673e6b9d5643003176 ]

Before ip_tunnel_ecn_encap() and udp_tunnel_xmit_skb() we should filter
tos value by RT_TOS() instead of using config tos directly.

vxlan_get_route() would filter the tos to fl4.flowi4_tos but we didn't
return it back, as geneve_get_v4_rt() did. So we have to use RT_TOS()
directly in function ip_tunnel_ecn_encap().

Fixes: 206aaafcd279 ("VXLAN: Use IP Tunnels tunnel ENC encap API")
Fixes: 1400615d64cf ("vxlan: allow setting ipv6 traffic class")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 404ac3a0d1c3..283dfeb406ad 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2542,7 +2542,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		ndst = &rt->dst;
 		skb_tunnel_check_pmtu(skb, ndst, VXLAN_HEADROOM);
 
-		tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
+		tos = ip_tunnel_ecn_encap(RT_TOS(tos), old_iph, skb);
 		ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
 		err = vxlan_build_skb(skb, ndst, sizeof(struct iphdr),
 				      vni, md, flags, udp_sum);
@@ -2582,7 +2582,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 
 		skb_tunnel_check_pmtu(skb, ndst, VXLAN6_HEADROOM);
 
-		tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
+		tos = ip_tunnel_ecn_encap(RT_TOS(tos), old_iph, skb);
 		ttl = ttl ? : ip6_dst_hoplimit(ndst);
 		skb_scrub_packet(skb, xnet);
 		err = vxlan_build_skb(skb, ndst, sizeof(struct ipv6hdr),
-- 
2.20.1


From 25ad8337a2c52967d56a1a3cfe761146a842eb05 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 6 Jan 2020 18:01:55 +0000
Subject: [PATCH 14/24] mlxsw: spectrum_qdisc: Ignore grafting of invisible
 FIFO

[ Upstream commit 3971a535b839489e4ea31796cc086e6ce616318c ]

The following patch will change PRIO to replace a removed Qdisc with an
invisible FIFO, instead of NOOP. mlxsw will see this replacement due to the
graft message that is generated. But because FIFO does not issue its own
REPLACE message, when the graft operation takes place, the Qdisc that mlxsw
tracks under the indicated band is still the old one. The child
handle (0:0) therefore does not match, and mlxsw rejects the graft
operation, which leads to an extack message:

    Warning: Offloading graft operation failed.

Fix by ignoring the invisible children in the PRIO graft handler. The
DESTROY message of the removed Qdisc is going to follow shortly and handle
the removal.

Fixes: 32dc5efc6cb4 ("mlxsw: spectrum: qdiscs: prio: Handle graft command")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c
index bdf53cf350f6..720514b5c006 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c
@@ -650,6 +650,13 @@ mlxsw_sp_qdisc_prio_graft(struct mlxsw_sp_port *mlxsw_sp_port,
 	    mlxsw_sp_port->tclass_qdiscs[tclass_num].handle == p->child_handle)
 		return 0;
 
+	if (!p->child_handle) {
+		/* This is an invisible FIFO replacing the original Qdisc.
+		 * Ignore it--the original Qdisc's destroy will follow.
+		 */
+		return 0;
+	}
+
 	/* See if the grafted qdisc is already offloaded on any tclass. If so,
 	 * unoffload it.
 	 */
-- 
2.20.1


From 0901127fcca72d0d6f04eef7d29a669d82093185 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 6 Jan 2020 18:01:56 +0000
Subject: [PATCH 15/24] net: sch_prio: When ungrafting, replace with FIFO

[ Upstream commit 240ce7f6428ff5188b9eedc066e1e4d645b8635f ]

When a child Qdisc is removed from one of the PRIO Qdisc's bands, it is
replaced unconditionally by a NOOP qdisc. As a result, any traffic hitting
that band gets dropped. That is incorrect--no Qdisc was explicitly added
when PRIO was created, and after removal, none should have to be added
either.

Fix PRIO by first attempting to create a default Qdisc and only falling
back to noop when that fails. This pattern of attempting to create an
invisible FIFO, using NOOP only as a fallback, is also seen in other
Qdiscs.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_prio.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index 18b884cfdfe8..647941702f9f 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -292,8 +292,14 @@ static int prio_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 	struct tc_prio_qopt_offload graft_offload;
 	unsigned long band = arg - 1;
 
-	if (new == NULL)
-		new = &noop_qdisc;
+	if (!new) {
+		new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops,
+					TC_H_MAKE(sch->handle, arg), extack);
+		if (!new)
+			new = &noop_qdisc;
+		else
+			qdisc_hash_add(new, true);
+	}
 
 	*old = qdisc_replace(sch, new, &q->queues[band]);
 
-- 
2.20.1


From 884bd2d8b952b880785567ece8751a10fe1146a9 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 7 Jan 2020 01:42:24 -0800
Subject: [PATCH 16/24] vlan: fix memory leak in vlan_dev_set_egress_priority

[ Upstream commit 9bbd917e0bec9aebdbd0c8dbc966caec15eb33e9 ]

There are few cases where the ndo_uninit() handler might be not
called if an error happens while device is initialized.

Since vlan_newlink() calls vlan_changelink() before
trying to register the netdevice, we need to make sure
vlan_dev_uninit() has been called at least once,
or we might leak allocated memory.

BUG: memory leak
unreferenced object 0xffff888122a206c0 (size 32):
  comm "syz-executor511", pid 7124, jiffies 4294950399 (age 32.240s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 61 73 00 00 00 00 00 00 00 00  ......as........
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<000000000eb3bb85>] kmemleak_alloc_recursive include/linux/kmemleak.h:43 [inline]
    [<000000000eb3bb85>] slab_post_alloc_hook mm/slab.h:586 [inline]
    [<000000000eb3bb85>] slab_alloc mm/slab.c:3320 [inline]
    [<000000000eb3bb85>] kmem_cache_alloc_trace+0x145/0x2c0 mm/slab.c:3549
    [<000000007b99f620>] kmalloc include/linux/slab.h:556 [inline]
    [<000000007b99f620>] vlan_dev_set_egress_priority+0xcc/0x150 net/8021q/vlan_dev.c:194
    [<000000007b0cb745>] vlan_changelink+0xd6/0x140 net/8021q/vlan_netlink.c:126
    [<0000000065aba83a>] vlan_newlink+0x135/0x200 net/8021q/vlan_netlink.c:181
    [<00000000fb5dd7a2>] __rtnl_newlink+0x89a/0xb80 net/core/rtnetlink.c:3305
    [<00000000ae4273a1>] rtnl_newlink+0x4e/0x80 net/core/rtnetlink.c:3363
    [<00000000decab39f>] rtnetlink_rcv_msg+0x178/0x4b0 net/core/rtnetlink.c:5424
    [<00000000accba4ee>] netlink_rcv_skb+0x61/0x170 net/netlink/af_netlink.c:2477
    [<00000000319fe20f>] rtnetlink_rcv+0x1d/0x30 net/core/rtnetlink.c:5442
    [<00000000d51938dc>] netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
    [<00000000d51938dc>] netlink_unicast+0x223/0x310 net/netlink/af_netlink.c:1328
    [<00000000e539ac79>] netlink_sendmsg+0x2c0/0x570 net/netlink/af_netlink.c:1917
    [<000000006250c27e>] sock_sendmsg_nosec net/socket.c:639 [inline]
    [<000000006250c27e>] sock_sendmsg+0x54/0x70 net/socket.c:659
    [<00000000e2a156d1>] ____sys_sendmsg+0x2d0/0x300 net/socket.c:2330
    [<000000008c87466e>] ___sys_sendmsg+0x8a/0xd0 net/socket.c:2384
    [<00000000110e3054>] __sys_sendmsg+0x80/0xf0 net/socket.c:2417
    [<00000000d71077c8>] __do_sys_sendmsg net/socket.c:2426 [inline]
    [<00000000d71077c8>] __se_sys_sendmsg net/socket.c:2424 [inline]
    [<00000000d71077c8>] __x64_sys_sendmsg+0x23/0x30 net/socket.c:2424

Fixe: 07b5b17e157b ("[VLAN]: Use rtnl_link API")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/8021q/vlan.h         | 1 +
 net/8021q/vlan_dev.c     | 3 ++-
 net/8021q/vlan_netlink.c | 9 +++++----
 3 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h
index c46daf09a501..bb7ec1a3915d 100644
--- a/net/8021q/vlan.h
+++ b/net/8021q/vlan.h
@@ -126,6 +126,7 @@ int vlan_check_real_dev(struct net_device *real_dev,
 void vlan_setup(struct net_device *dev);
 int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack);
 void unregister_vlan_dev(struct net_device *dev, struct list_head *head);
+void vlan_dev_uninit(struct net_device *dev);
 bool vlan_dev_inherit_address(struct net_device *dev,
 			      struct net_device *real_dev);
 
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index e5bff5cc6f97..2a78da4072de 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -586,7 +586,8 @@ static int vlan_dev_init(struct net_device *dev)
 	return 0;
 }
 
-static void vlan_dev_uninit(struct net_device *dev)
+/* Note: this function might be called multiple times for the same device. */
+void vlan_dev_uninit(struct net_device *dev)
 {
 	struct vlan_priority_tci_mapping *pm;
 	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c
index c482a6fe9393..b2a4b8b5a0cd 100644
--- a/net/8021q/vlan_netlink.c
+++ b/net/8021q/vlan_netlink.c
@@ -179,10 +179,11 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev,
 		return -EINVAL;
 
 	err = vlan_changelink(dev, tb, data, extack);
-	if (err < 0)
-		return err;
-
-	return register_vlan_dev(dev, extack);
+	if (!err)
+		err = register_vlan_dev(dev, extack);
+	if (err)
+		vlan_dev_uninit(dev);
+	return err;
 }
 
 static inline size_t vlan_qos_map_size(unsigned int n)
-- 
2.20.1


From 6b0eb009fa6daa4c325af5721e2c710ab70ad7ba Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 7 Jan 2020 01:42:25 -0800
Subject: [PATCH 17/24] vlan: vlan_changelink() should propagate errors

[ Upstream commit eb8ef2a3c50092bb018077c047b8dba1ce0e78e3 ]

Both vlan_dev_change_flags() and vlan_dev_set_egress_priority()
can return an error. vlan_changelink() should not ignore them.

Fixes: 07b5b17e157b ("[VLAN]: Use rtnl_link API")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/8021q/vlan_netlink.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c
index b2a4b8b5a0cd..0db85aeb119b 100644
--- a/net/8021q/vlan_netlink.c
+++ b/net/8021q/vlan_netlink.c
@@ -108,11 +108,13 @@ static int vlan_changelink(struct net_device *dev, struct nlattr *tb[],
 	struct ifla_vlan_flags *flags;
 	struct ifla_vlan_qos_mapping *m;
 	struct nlattr *attr;
-	int rem;
+	int rem, err;
 
 	if (data[IFLA_VLAN_FLAGS]) {
 		flags = nla_data(data[IFLA_VLAN_FLAGS]);
-		vlan_dev_change_flags(dev, flags->flags, flags->mask);
+		err = vlan_dev_change_flags(dev, flags->flags, flags->mask);
+		if (err)
+			return err;
 	}
 	if (data[IFLA_VLAN_INGRESS_QOS]) {
 		nla_for_each_nested(attr, data[IFLA_VLAN_INGRESS_QOS], rem) {
@@ -123,7 +125,9 @@ static int vlan_changelink(struct net_device *dev, struct nlattr *tb[],
 	if (data[IFLA_VLAN_EGRESS_QOS]) {
 		nla_for_each_nested(attr, data[IFLA_VLAN_EGRESS_QOS], rem) {
 			m = nla_data(attr);
-			vlan_dev_set_egress_priority(dev, m->from, m->to);
+			err = vlan_dev_set_egress_priority(dev, m->from, m->to);
+			if (err)
+				return err;
 		}
 	}
 	return 0;
-- 
2.20.1


From d1782407b88cf31e9277bb4a7e71077236ca1538 Mon Sep 17 00:00:00 2001
From: Stephen Boyd <sboyd@kernel.org>
Date: Fri, 3 Jan 2020 16:19:21 -0800
Subject: [PATCH 18/24] macb: Don't unregister clks unconditionally

[ Upstream commit d89091a4930ee0d80bee3e259a98513f3a2543ec ]

The only clk init function in this driver that register a clk is
fu540_c000_clk_init(), and thus we need to unregister the clk when this
driver is removed on that platform. Other init functions, for example
macb_clk_init(), don't register clks and therefore we shouldn't
unregister the clks when this driver is removed. Convert this
registration path to devm so it gets auto-unregistered when this driver
is removed and drop the clk_unregister() calls in driver remove (and
error paths) so that we don't erroneously remove a clk from the system
that isn't registered by this driver.

Otherwise we get strange crashes with a use-after-free when the
devm_clk_get() call in macb_clk_init() calls clk_put() on a clk pointer
that has become invalid because it is freed in clk_unregister().

Cc: Nicolas Ferre <nicolas.ferre@microchip.com>
Cc: Yash Shah <yash.shah@sifive.com>
Reported-by: Guenter Roeck <linux@roeck-us.net>
Fixes: c218ad559020 ("macb: Add support for SiFive FU540-C000")
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 0f10a272827c..f496b248bda3 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -4027,7 +4027,7 @@ static int fu540_c000_clk_init(struct platform_device *pdev, struct clk **pclk,
 	mgmt->rate = 0;
 	mgmt->hw.init = &init;
 
-	*tx_clk = clk_register(NULL, &mgmt->hw);
+	*tx_clk = devm_clk_register(&pdev->dev, &mgmt->hw);
 	if (IS_ERR(*tx_clk))
 		return PTR_ERR(*tx_clk);
 
@@ -4361,7 +4361,6 @@ static int macb_probe(struct platform_device *pdev)
 
 err_disable_clocks:
 	clk_disable_unprepare(tx_clk);
-	clk_unregister(tx_clk);
 	clk_disable_unprepare(hclk);
 	clk_disable_unprepare(pclk);
 	clk_disable_unprepare(rx_clk);
@@ -4397,7 +4396,6 @@ static int macb_remove(struct platform_device *pdev)
 		pm_runtime_dont_use_autosuspend(&pdev->dev);
 		if (!pm_runtime_suspended(&pdev->dev)) {
 			clk_disable_unprepare(bp->tx_clk);
-			clk_unregister(bp->tx_clk);
 			clk_disable_unprepare(bp->hclk);
 			clk_disable_unprepare(bp->pclk);
 			clk_disable_unprepare(bp->rx_clk);
-- 
2.20.1


From d2a1ccca3ae495b5b2237cb6a50960eb371b339b Mon Sep 17 00:00:00 2001
From: Michael Guralnik <michaelgur@mellanox.com>
Date: Wed, 20 Nov 2019 11:43:49 +0200
Subject: [PATCH 19/24] net/mlx5: Move devlink registration before interfaces
 load

[ Upstream commit a6f3b62386a02c1e94bfa22c543f82d63f5e631b ]

Register devlink before interfaces are added.
This will allow interfaces to use devlink while initalizing. For example,
call mlx5_is_roce_enabled.

Fixes: aba25279c100 ("net/mlx5e: Add TX reporter support")
Signed-off-by: Michael Guralnik <michaelgur@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 50ab88d80033..051ab845b501 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1197,6 +1197,12 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, bool boot)
 	if (err)
 		goto err_load;
 
+	if (boot) {
+		err = mlx5_devlink_register(priv_to_devlink(dev), dev->device);
+		if (err)
+			goto err_devlink_reg;
+	}
+
 	if (mlx5_device_registered(dev)) {
 		mlx5_attach_device(dev);
 	} else {
@@ -1214,6 +1220,9 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, bool boot)
 	return err;
 
 err_reg_dev:
+	if (boot)
+		mlx5_devlink_unregister(priv_to_devlink(dev));
+err_devlink_reg:
 	mlx5_unload(dev);
 err_load:
 	if (boot)
@@ -1353,10 +1362,6 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	request_module_nowait(MLX5_IB_MOD);
 
-	err = mlx5_devlink_register(devlink, &pdev->dev);
-	if (err)
-		goto clean_load;
-
 	err = mlx5_crdump_enable(dev);
 	if (err)
 		dev_err(&pdev->dev, "mlx5_crdump_enable failed with error code %d\n", err);
@@ -1364,9 +1369,6 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	pci_save_state(pdev);
 	return 0;
 
-clean_load:
-	mlx5_unload_one(dev, true);
-
 err_load_one:
 	mlx5_pci_close(dev);
 pci_init_err:
-- 
2.20.1


From 1402865befbff1ada1de6bf253bb8c93f8e6f831 Mon Sep 17 00:00:00 2001
From: Baruch Siach <baruch@tkos.co.il>
Date: Thu, 19 Dec 2019 11:48:22 +0200
Subject: [PATCH 20/24] net: dsa: mv88e6xxx: force cmode write on 6141/6341

[ Upstream commit f7a48b68abd9b20ce1ac6298aaaa3c4d158271dd ]

mv88e6xxx_port_set_cmode() relies on cmode stored in struct
mv88e6xxx_port to skip cmode update when the requested value matches the
cached value. It turns out that mv88e6xxx_port_hidden_write() might
change the port cmode setting as a side effect, so we can't rely on the
cached value to determine that cmode update in not necessary.

Force cmode update in mv88e6341_port_set_cmode(), to make
serdes configuration work again. Other mv88e6xxx_port_set_cmode()
callers keep the current behaviour.

This fixes serdes configuration of the 6141 switch on SolidRun Clearfog
GT-8K.

Fixes: 7a3007d22e8 ("net: dsa: mv88e6xxx: fully support SERDES on Topaz family")
Reported-by: Denis Odintsov <d.odintsov@traviangames.com>
Signed-off-by: Baruch Siach <baruch@tkos.co.il>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/port.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c
index 15ef81654b67..330c41e87171 100644
--- a/drivers/net/dsa/mv88e6xxx/port.c
+++ b/drivers/net/dsa/mv88e6xxx/port.c
@@ -393,7 +393,7 @@ phy_interface_t mv88e6390x_port_max_speed_mode(int port)
 }
 
 static int mv88e6xxx_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
-				    phy_interface_t mode)
+				    phy_interface_t mode, bool force)
 {
 	u8 lane;
 	u16 cmode;
@@ -427,8 +427,8 @@ static int mv88e6xxx_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 		cmode = 0;
 	}
 
-	/* cmode doesn't change, nothing to do for us */
-	if (cmode == chip->ports[port].cmode)
+	/* cmode doesn't change, nothing to do for us unless forced */
+	if (cmode == chip->ports[port].cmode && !force)
 		return 0;
 
 	lane = mv88e6xxx_serdes_get_lane(chip, port);
@@ -484,7 +484,7 @@ int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 	if (port != 9 && port != 10)
 		return -EOPNOTSUPP;
 
-	return mv88e6xxx_port_set_cmode(chip, port, mode);
+	return mv88e6xxx_port_set_cmode(chip, port, mode, false);
 }
 
 int mv88e6390_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
@@ -504,7 +504,7 @@ int mv88e6390_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 		break;
 	}
 
-	return mv88e6xxx_port_set_cmode(chip, port, mode);
+	return mv88e6xxx_port_set_cmode(chip, port, mode, false);
 }
 
 static int mv88e6341_port_set_cmode_writable(struct mv88e6xxx_chip *chip,
@@ -555,7 +555,7 @@ int mv88e6341_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 	if (err)
 		return err;
 
-	return mv88e6xxx_port_set_cmode(chip, port, mode);
+	return mv88e6xxx_port_set_cmode(chip, port, mode, true);
 }
 
 int mv88e6185_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode)
-- 
2.20.1


From dc146b792d5900d60d900d84a9df3da14f60575c Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Wed, 4 Dec 2019 14:34:18 +0200
Subject: [PATCH 21/24] net/mlx5e: Always print health reporter message to
 dmesg

[ Upstream commit 99cda45426c9a2c59bb2f7cb886a405440282455 ]

In case a reporter exists, error message is logged only to the devlink
tracer. The devlink tracer is a visibility utility only, which user can
choose not to monitor.
After cited patch, 3rd party monitoring tools that tracks these error
message will no longer find them in dmesg, causing a regression.

With this patch, error messages are also logged into the dmesg.

Fixes: c50de4af1d63 ("net/mlx5e: Generalize tx reporter's functionality")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/health.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
index 1d6b58860da6..3a975641f902 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c
@@ -197,9 +197,10 @@ int mlx5e_health_report(struct mlx5e_priv *priv,
 			struct devlink_health_reporter *reporter, char *err_str,
 			struct mlx5e_err_ctx *err_ctx)
 {
-	if (!reporter) {
-		netdev_err(priv->netdev, err_str);
+	netdev_err(priv->netdev, err_str);
+
+	if (!reporter)
 		return err_ctx->recover(&err_ctx->ctx);
-	}
+
 	return devlink_health_report(reporter, err_str, err_ctx);
 }
-- 
2.20.1


From 7ee157980edb16d64af62e1ce55a311d5e22ea66 Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@mellanox.com>
Date: Mon, 23 Dec 2019 16:16:31 +0200
Subject: [PATCH 22/24] net/mlx5: DR, No need for atomic refcount for internal
 SW steering resources

[ Upstream commit 4ce380ca477507e2f413584cdd99e1698d6682d6 ]

No need for an atomic refcounter for the STE and hashtables.
These are internal SW steering resources and they are always
under domain mutex.

This also fixes the following refcount error:
  refcount_t: addition on 0; use-after-free.
  WARNING: CPU: 9 PID: 3527 at lib/refcount.c:25 refcount_warn_saturate+0x81/0xe0
  Call Trace:
   dr_table_init_nic+0x10d/0x110 [mlx5_core]
   mlx5dr_table_create+0xb4/0x230 [mlx5_core]
   mlx5_cmd_dr_create_flow_table+0x39/0x120 [mlx5_core]
   __mlx5_create_flow_table+0x221/0x5f0 [mlx5_core]
   esw_create_offloads_fdb_tables+0x180/0x5a0 [mlx5_core]
   ...

Fixes: 26d688e33f88 ("net/mlx5: DR, Add Steering entry (STE) utilities")
Signed-off-by: Yevgeny Kliteynik <kliteyn@mellanox.com>
Reviewed-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../ethernet/mellanox/mlx5/core/steering/dr_rule.c |  2 +-
 .../ethernet/mellanox/mlx5/core/steering/dr_ste.c  | 10 +++++-----
 .../mellanox/mlx5/core/steering/dr_types.h         | 14 ++++++++------
 3 files changed, 14 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
index bd1699e62142..6d186e2d3e74 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
@@ -209,7 +209,7 @@ static void dr_rule_rehash_copy_ste_ctrl(struct mlx5dr_matcher *matcher,
 	/* We need to copy the refcount since this ste
 	 * may have been traversed several times
 	 */
-	refcount_set(&new_ste->refcount, refcount_read(&cur_ste->refcount));
+	new_ste->refcount = cur_ste->refcount;
 
 	/* Link old STEs rule_mem list to the new ste */
 	mlx5dr_rule_update_rule_member(cur_ste, new_ste);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
index 3cbf74b44d1f..2739ed2a2911 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
@@ -340,7 +340,7 @@ static void dr_ste_replace(struct mlx5dr_ste *dst, struct mlx5dr_ste *src)
 	if (dst->next_htbl)
 		dst->next_htbl->pointing_ste = dst;
 
-	refcount_set(&dst->refcount, refcount_read(&src->refcount));
+	dst->refcount = src->refcount;
 
 	INIT_LIST_HEAD(&dst->rule_list);
 	list_splice_tail_init(&src->rule_list, &dst->rule_list);
@@ -557,7 +557,7 @@ bool mlx5dr_ste_is_not_valid_entry(u8 *p_hw_ste)
 
 bool mlx5dr_ste_not_used_ste(struct mlx5dr_ste *ste)
 {
-	return !refcount_read(&ste->refcount);
+	return !ste->refcount;
 }
 
 /* Init one ste as a pattern for ste data array */
@@ -681,14 +681,14 @@ struct mlx5dr_ste_htbl *mlx5dr_ste_htbl_alloc(struct mlx5dr_icm_pool *pool,
 	htbl->ste_arr = chunk->ste_arr;
 	htbl->hw_ste_arr = chunk->hw_ste_arr;
 	htbl->miss_list = chunk->miss_list;
-	refcount_set(&htbl->refcount, 0);
+	htbl->refcount = 0;
 
 	for (i = 0; i < chunk->num_of_entries; i++) {
 		struct mlx5dr_ste *ste = &htbl->ste_arr[i];
 
 		ste->hw_ste = htbl->hw_ste_arr + i * DR_STE_SIZE_REDUCED;
 		ste->htbl = htbl;
-		refcount_set(&ste->refcount, 0);
+		ste->refcount = 0;
 		INIT_LIST_HEAD(&ste->miss_list_node);
 		INIT_LIST_HEAD(&htbl->miss_list[i]);
 		INIT_LIST_HEAD(&ste->rule_list);
@@ -705,7 +705,7 @@ struct mlx5dr_ste_htbl *mlx5dr_ste_htbl_alloc(struct mlx5dr_icm_pool *pool,
 
 int mlx5dr_ste_htbl_free(struct mlx5dr_ste_htbl *htbl)
 {
-	if (refcount_read(&htbl->refcount))
+	if (htbl->refcount)
 		return -EBUSY;
 
 	mlx5dr_icm_free_chunk(htbl->chunk);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
index 1cb3769d4e3c..31737dfca4ea 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
@@ -117,7 +117,7 @@ struct mlx5dr_matcher_rx_tx;
 struct mlx5dr_ste {
 	u8 *hw_ste;
 	/* refcount: indicates the num of rules that using this ste */
-	refcount_t refcount;
+	u32 refcount;
 
 	/* attached to the miss_list head at each htbl entry */
 	struct list_head miss_list_node;
@@ -149,7 +149,7 @@ struct mlx5dr_ste_htbl_ctrl {
 struct mlx5dr_ste_htbl {
 	u8 lu_type;
 	u16 byte_mask;
-	refcount_t refcount;
+	u32 refcount;
 	struct mlx5dr_icm_chunk *chunk;
 	struct mlx5dr_ste *ste_arr;
 	u8 *hw_ste_arr;
@@ -200,13 +200,14 @@ int mlx5dr_ste_htbl_free(struct mlx5dr_ste_htbl *htbl);
 
 static inline void mlx5dr_htbl_put(struct mlx5dr_ste_htbl *htbl)
 {
-	if (refcount_dec_and_test(&htbl->refcount))
+	htbl->refcount--;
+	if (!htbl->refcount)
 		mlx5dr_ste_htbl_free(htbl);
 }
 
 static inline void mlx5dr_htbl_get(struct mlx5dr_ste_htbl *htbl)
 {
-	refcount_inc(&htbl->refcount);
+	htbl->refcount++;
 }
 
 /* STE utils */
@@ -248,14 +249,15 @@ static inline void mlx5dr_ste_put(struct mlx5dr_ste *ste,
 				  struct mlx5dr_matcher *matcher,
 				  struct mlx5dr_matcher_rx_tx *nic_matcher)
 {
-	if (refcount_dec_and_test(&ste->refcount))
+	ste->refcount--;
+	if (!ste->refcount)
 		mlx5dr_ste_free(ste, matcher, nic_matcher);
 }
 
 /* initial as 0, increased only when ste appears in a new rule */
 static inline void mlx5dr_ste_get(struct mlx5dr_ste *ste)
 {
-	refcount_inc(&ste->refcount);
+	ste->refcount++;
 }
 
 void mlx5dr_ste_set_hit_addr_by_next_htbl(u8 *hw_ste,
-- 
2.20.1


From 14eaa3a22ceaaf14b00d38e34ec885ad146618ba Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.com>
Date: Wed, 11 Dec 2019 09:17:40 +0200
Subject: [PATCH 23/24] net/mlx5e: Fix hairpin RSS table size

[ Upstream commit 6412bb396a63f28de994b1480edf8e4caf4aa494 ]

Set hairpin table size to the corret size, based on the groups that
would be created in it. Groups are laid out on the table such that a
group occupies a range of entries in the table. This implies that the
group ranges should have correspondence to the table they are laid upon.

The patch cited below  made group 1's size to grow hence causing
overflow of group range laid on the table.

Fixes: a795d8db2a6d ("net/mlx5e: Support RSS for IP-in-IP and IPv6 tunneled packets")
Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/fs.h | 16 ++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/en_fs.c | 16 ----------------
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c |  2 +-
 3 files changed, 17 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
index 68d593074f6c..d48292ccda29 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
@@ -122,6 +122,22 @@ enum {
 #endif
 };
 
+#define MLX5E_TTC_NUM_GROUPS	3
+#define MLX5E_TTC_GROUP1_SIZE	(BIT(3) + MLX5E_NUM_TUNNEL_TT)
+#define MLX5E_TTC_GROUP2_SIZE	 BIT(1)
+#define MLX5E_TTC_GROUP3_SIZE	 BIT(0)
+#define MLX5E_TTC_TABLE_SIZE	(MLX5E_TTC_GROUP1_SIZE +\
+				 MLX5E_TTC_GROUP2_SIZE +\
+				 MLX5E_TTC_GROUP3_SIZE)
+
+#define MLX5E_INNER_TTC_NUM_GROUPS	3
+#define MLX5E_INNER_TTC_GROUP1_SIZE	BIT(3)
+#define MLX5E_INNER_TTC_GROUP2_SIZE	BIT(1)
+#define MLX5E_INNER_TTC_GROUP3_SIZE	BIT(0)
+#define MLX5E_INNER_TTC_TABLE_SIZE	(MLX5E_INNER_TTC_GROUP1_SIZE +\
+					 MLX5E_INNER_TTC_GROUP2_SIZE +\
+					 MLX5E_INNER_TTC_GROUP3_SIZE)
+
 #ifdef CONFIG_MLX5_EN_RXNFC
 
 struct mlx5e_ethtool_table {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
index 15b7f0f1427c..73d3dc07331f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
@@ -904,22 +904,6 @@ static int mlx5e_generate_ttc_table_rules(struct mlx5e_priv *priv,
 	return err;
 }
 
-#define MLX5E_TTC_NUM_GROUPS	3
-#define MLX5E_TTC_GROUP1_SIZE	(BIT(3) + MLX5E_NUM_TUNNEL_TT)
-#define MLX5E_TTC_GROUP2_SIZE	 BIT(1)
-#define MLX5E_TTC_GROUP3_SIZE	 BIT(0)
-#define MLX5E_TTC_TABLE_SIZE	(MLX5E_TTC_GROUP1_SIZE +\
-				 MLX5E_TTC_GROUP2_SIZE +\
-				 MLX5E_TTC_GROUP3_SIZE)
-
-#define MLX5E_INNER_TTC_NUM_GROUPS	3
-#define MLX5E_INNER_TTC_GROUP1_SIZE	BIT(3)
-#define MLX5E_INNER_TTC_GROUP2_SIZE	BIT(1)
-#define MLX5E_INNER_TTC_GROUP3_SIZE	BIT(0)
-#define MLX5E_INNER_TTC_TABLE_SIZE	(MLX5E_INNER_TTC_GROUP1_SIZE +\
-					 MLX5E_INNER_TTC_GROUP2_SIZE +\
-					 MLX5E_INNER_TTC_GROUP3_SIZE)
-
 static int mlx5e_create_ttc_table_groups(struct mlx5e_ttc_table *ttc,
 					 bool use_ipv)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 814a4ba4e7fa..947122c68493 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -586,7 +586,7 @@ static void mlx5e_hairpin_set_ttc_params(struct mlx5e_hairpin *hp,
 	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++)
 		ttc_params->indir_tirn[tt] = hp->indir_tirn[tt];
 
-	ft_attr->max_fte = MLX5E_NUM_TT;
+	ft_attr->max_fte = MLX5E_TTC_TABLE_SIZE;
 	ft_attr->level = MLX5E_TC_TTC_FT_LEVEL;
 	ft_attr->prio = MLX5E_TC_PRIO;
 }
-- 
2.20.1


From 7aad3f5a9a408f9cc0dfc8fb584b5588bd213160 Mon Sep 17 00:00:00 2001
From: Erez Shitrit <erezsh@mellanox.com>
Date: Mon, 25 Nov 2019 10:26:24 +0200
Subject: [PATCH 24/24] net/mlx5: DR, Init lists that are used in rule's member

[ Upstream commit df55c5586e5185f890192a6802dc5b46fddd3606 ]

Whenever adding new member of rule object we attach it to 2 lists,
These 2 lists should be initialized first.

Fixes: 41d07074154c ("net/mlx5: DR, Expose steering rule functionality")
Signed-off-by: Erez Shitrit <erezsh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
index 6d186e2d3e74..e1a647dde978 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
@@ -638,6 +638,9 @@ static int dr_rule_add_member(struct mlx5dr_rule_rx_tx *nic_rule,
 	if (!rule_mem)
 		return -ENOMEM;
 
+	INIT_LIST_HEAD(&rule_mem->list);
+	INIT_LIST_HEAD(&rule_mem->use_ste_list);
+
 	rule_mem->ste = ste;
 	list_add_tail(&rule_mem->list, &nic_rule->rule_members_list);
 
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Fri, Jan 10, 2020 at 04:33:16PM -0800, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.19
> and v5.4 -stable, respectively.

All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 106 bytes --]


Please queue up the following networking bug fixes for v4.19 and v5.4
-stable, respectively.

Thank you!

[-- Attachment #2: net_419.mbox --]
[-- Type: Application/Octet-Stream, Size: 21682 bytes --]

From b2a072aec34712363c340c558766b058a9d850a3 Mon Sep 17 00:00:00 2001
From: Mohammed Gamal <mgamal@redhat.com>
Date: Tue, 14 Jan 2020 15:09:50 +0200
Subject: [PATCH 01/12] hv_netvsc: Fix memory leak when removing rndis device

[ Upstream commit 536dc5df2808efbefc5acee334d3c4f701790ec0 ]

kmemleak detects the following memory leak when hot removing
a network device:

unreferenced object 0xffff888083f63600 (size 256):
  comm "kworker/0:1", pid 12, jiffies 4294831717 (age 1113.676s)
  hex dump (first 32 bytes):
    00 40 c7 33 80 88 ff ff 00 00 00 00 10 00 00 00  .@.3............
    00 00 00 00 ad 4e ad de ff ff ff ff 00 00 00 00  .....N..........
  backtrace:
    [<00000000d4a8f5be>] rndis_filter_device_add+0x117/0x11c0 [hv_netvsc]
    [<000000009c02d75b>] netvsc_probe+0x5e7/0xbf0 [hv_netvsc]
    [<00000000ddafce23>] vmbus_probe+0x74/0x170 [hv_vmbus]
    [<00000000046e64f1>] really_probe+0x22f/0xb50
    [<000000005cc35eb7>] driver_probe_device+0x25e/0x370
    [<0000000043c642b2>] bus_for_each_drv+0x11f/0x1b0
    [<000000005e3d09f0>] __device_attach+0x1c6/0x2f0
    [<00000000a72c362f>] bus_probe_device+0x1a6/0x260
    [<0000000008478399>] device_add+0x10a3/0x18e0
    [<00000000cf07b48c>] vmbus_device_register+0xe7/0x1e0 [hv_vmbus]
    [<00000000d46cf032>] vmbus_add_channel_work+0x8ab/0x1770 [hv_vmbus]
    [<000000002c94bb64>] process_one_work+0x919/0x17d0
    [<0000000096de6781>] worker_thread+0x87/0xb40
    [<00000000fbe7397e>] kthread+0x333/0x3f0
    [<000000004f844269>] ret_from_fork+0x3a/0x50

rndis_filter_device_add() allocates an instance of struct rndis_device
which never gets deallocated as rndis_filter_device_remove() sets
net_device->extension which points to the rndis_device struct to NULL,
leaving the rndis_device dangling.

Since net_device->extension is eventually freed in free_netvsc_device(),
we refrain from setting it to NULL inside rndis_filter_device_remove()

Signed-off-by: Mohammed Gamal <mgamal@redhat.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/rndis_filter.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index f47e36ac42a7..dd91834f841d 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -1375,8 +1375,6 @@ void rndis_filter_device_remove(struct hv_device *dev,
 	/* Halt and release the rndis device */
 	rndis_filter_halt_device(net_dev, rndis_dev);
 
-	net_dev->extension = NULL;
-
 	netvsc_device_remove(dev);
 }
 
-- 
2.21.1


From 93c47381b9f72d599b00680afc7a5e931cb2efb6 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 14 Jan 2020 13:00:35 -0800
Subject: [PATCH 02/12] macvlan: use skb_reset_mac_header() in
 macvlan_queue_xmit()

[ Upstream commit 1712b2fff8c682d145c7889d2290696647d82dab ]

I missed the fact that macvlan_broadcast() can be used both
in RX and TX.

skb_eth_hdr() makes only sense in TX paths, so we can not
use it blindly in macvlan_broadcast()

Fixes: 96cc4b69581d ("macvlan: do not assume mac_header is set in macvlan_broadcast()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Jurgen Van Ham <juvanham@gmail.com>
Tested-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macvlan.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 41c0a3b55bfb..277bbff53cff 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -263,7 +263,7 @@ static void macvlan_broadcast(struct sk_buff *skb,
 			      struct net_device *src,
 			      enum macvlan_mode mode)
 {
-	const struct ethhdr *eth = skb_eth_hdr(skb);
+	const struct ethhdr *eth = eth_hdr(skb);
 	const struct macvlan_dev *vlan;
 	struct sk_buff *nskb;
 	unsigned int i;
@@ -517,10 +517,11 @@ static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev)
 	const struct macvlan_dev *dest;
 
 	if (vlan->mode == MACVLAN_MODE_BRIDGE) {
-		const struct ethhdr *eth = (void *)skb->data;
+		const struct ethhdr *eth = skb_eth_hdr(skb);
 
 		/* send to other bridge ports directly */
 		if (is_multicast_ether_addr(eth->h_dest)) {
+			skb_reset_mac_header(skb);
 			macvlan_broadcast(skb, port, dev, MACVLAN_MODE_BRIDGE);
 			goto xmit_world;
 		}
-- 
2.21.1


From 19564a8dfa97b57c42309d59d5533dd1f7c3520a Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <alobakin@dlink.ru>
Date: Wed, 15 Jan 2020 11:56:52 +0300
Subject: [PATCH 03/12] net: dsa: tag_qca: fix doubled Tx statistics

[ Upstream commit bd5874da57edd001b35cf28ae737779498c16a56 ]

DSA subsystem takes care of netdev statistics since commit 4ed70ce9f01c
("net: dsa: Refactor transmit path to eliminate duplication"), so
any accounting inside tagger callbacks is redundant and can lead to
messing up the stats.
This bug is present in Qualcomm tagger since day 0.

Fixes: cafdc45c949b ("net-next: dsa: add Qualcomm tag RX/TX handler")
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Alexander Lobakin <alobakin@dlink.ru>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/tag_qca.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c
index 613f4ee97771..66a952118dfd 100644
--- a/net/dsa/tag_qca.c
+++ b/net/dsa/tag_qca.c
@@ -41,9 +41,6 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct dsa_port *dp = dsa_slave_to_port(dev);
 	u16 *phdr, hdr;
 
-	dev->stats.tx_packets++;
-	dev->stats.tx_bytes += skb->len;
-
 	if (skb_cow_head(skb, 0) < 0)
 		return NULL;
 
-- 
2.21.1


From 5fcc6911eaaeed98c37c721a25f88653e85a577a Mon Sep 17 00:00:00 2001
From: Yonglong Liu <liuyonglong@huawei.com>
Date: Thu, 16 Jan 2020 15:41:17 +0800
Subject: [PATCH 04/12] net: hns: fix soft lockup when there is not enough
 memory

[ Upstream commit 49edd6a2c456150870ddcef5b7ed11b21d849e13 ]

When there is not enough memory and napi_alloc_skb() return NULL,
the HNS driver will print error message, and than try again, if
the memory is not enough for a while, huge error message and the
retry operation will cause soft lockup.

When napi_alloc_skb() return NULL because of no memory, we can
get a warn_alloc() call trace, so this patch deletes the error
message. We already use polling mode to handle irq, but the
retry operation will render the polling weight inactive, this
patch just return budget when the rx is not completed to avoid
dead loop.

Fixes: 36eedfde1a36 ("net: hns: Optimize hns_nic_common_poll for better performance")
Fixes: b5996f11ea54 ("net: add Hisilicon Network Subsystem basic ethernet support")
Signed-off-by: Yonglong Liu <liuyonglong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns/hns_enet.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index 7f8cf809e02b..024b08fafd3b 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -569,7 +569,6 @@ static int hns_nic_poll_rx_skb(struct hns_nic_ring_data *ring_data,
 	skb = *out_skb = napi_alloc_skb(&ring_data->napi,
 					HNS_RX_HEAD_SIZE);
 	if (unlikely(!skb)) {
-		netdev_err(ndev, "alloc rx skb fail\n");
 		ring->stats.sw_err_cnt++;
 		return -ENOMEM;
 	}
@@ -1060,7 +1059,6 @@ static int hns_nic_common_poll(struct napi_struct *napi, int budget)
 		container_of(napi, struct hns_nic_ring_data, napi);
 	struct hnae_ring *ring = ring_data->ring;
 
-try_again:
 	clean_complete += ring_data->poll_one(
 				ring_data, budget - clean_complete,
 				ring_data->ex_process);
@@ -1070,7 +1068,7 @@ static int hns_nic_common_poll(struct napi_struct *napi, int budget)
 			napi_complete(napi);
 			ring->q->handle->dev->ops->toggle_ring_irq(ring, 0);
 		} else {
-			goto try_again;
+			return budget;
 		}
 	}
 
-- 
2.21.1


From 1f02d0c2f75b547c1a5f51a8b405cbfb974183f7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 13 Jan 2020 09:27:11 -0800
Subject: [PATCH 05/12] net: usb: lan78xx: limit size of local TSO packets

[ Upstream commit f8d7408a4d7f60f8b2df0f81decdc882dd9c20dc ]

lan78xx_tx_bh() makes sure to not exceed MAX_SINGLE_PACKET_SIZE
bytes in the aggregated packets it builds, but does
nothing to prevent large GSO packets being submitted.

Pierre-Francois reported various hangs when/if TSO is enabled.

For localy generated packets, we can use netif_set_gso_max_size()
to limit the size of TSO packets.

Note that forwarded packets could still hit the issue,
so a complete fix might require implementing .ndo_features_check
for this driver, forcing a software segmentation if the size
of the TSO packet exceeds MAX_SINGLE_PACKET_SIZE.

Fixes: 55d7de9de6c3 ("Microchip's LAN7800 family USB 2/3 to 10/100/1000 Ethernet device driver")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: RENARD Pierre-Francois <pfrenard@gmail.com>
Tested-by: RENARD Pierre-Francois <pfrenard@gmail.com>
Cc: Stefan Wahren <stefan.wahren@i2se.com>
Cc: Woojung Huh <woojung.huh@microchip.com>
Cc: Microchip Linux Driver Support <UNGLinuxDriver@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/lan78xx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 42715520c070..7d708aeb4576 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -3769,6 +3769,7 @@ static int lan78xx_probe(struct usb_interface *intf,
 
 	/* MTU range: 68 - 9000 */
 	netdev->max_mtu = MAX_SINGLE_PACKET_SIZE;
+	netif_set_gso_max_size(netdev, MAX_SINGLE_PACKET_SIZE - MAX_HEADER);
 
 	dev->ep_blkin = (intf->cur_altsetting)->endpoint + 0;
 	dev->ep_blkout = (intf->cur_altsetting)->endpoint + 1;
-- 
2.21.1


From 2c43bedd2e01df891fa123f6685217e588133186 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Tue, 14 Jan 2020 14:54:48 +0000
Subject: [PATCH 06/12] net/wan/fsl_ucc_hdlc: fix out of bounds write on array
 utdm_info

[ Upstream commit ddf420390526ede3b9ff559ac89f58cb59d9db2f ]

Array utdm_info is declared as an array of MAX_HDLC_NUM (4) elements
however up to UCC_MAX_NUM (8) elements are potentially being written
to it.  Currently we have an array out-of-bounds write error on the
last 4 elements. Fix this by making utdm_info UCC_MAX_NUM elements in
size.

Addresses-Coverity: ("Out-of-bounds write")
Fixes: c19b6d246a35 ("drivers/net: support hdlc function for QE-UCC")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wan/fsl_ucc_hdlc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c
index 0212f576a838..daeab33f623e 100644
--- a/drivers/net/wan/fsl_ucc_hdlc.c
+++ b/drivers/net/wan/fsl_ucc_hdlc.c
@@ -76,7 +76,7 @@ static struct ucc_tdm_info utdm_primary_info = {
 	},
 };
 
-static struct ucc_tdm_info utdm_info[MAX_HDLC_NUM];
+static struct ucc_tdm_info utdm_info[UCC_MAX_NUM];
 
 static int uhdlc_init(struct ucc_hdlc_private *priv)
 {
-- 
2.21.1


From f07152e2c5c6dbcb5ec0bf37527ba7e2e1d4f287 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 13 Jan 2020 18:23:58 +0100
Subject: [PATCH 07/12] NFC: pn533: fix bulk-message timeout

[ Upstream commit a112adafcb47760feff959ee1ecd10b74d2c5467 ]

The driver was doing a synchronous uninterruptible bulk-transfer without
using a timeout. This could lead to the driver hanging on probe due to a
malfunctioning (or malicious) device until the device is physically
disconnected. While sleeping in probe the driver prevents other devices
connected to the same hub from being added to (or removed from) the bus.

An arbitrary limit of five seconds should be more than enough.

Fixes: dbafc28955fa ("NFC: pn533: don't send USB data off of the stack")
Signed-off-by: Johan Hovold <johan@kernel.org>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/nfc/pn533/usb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nfc/pn533/usb.c b/drivers/nfc/pn533/usb.c
index fcb57d64d97e..a2c9b3f3bc23 100644
--- a/drivers/nfc/pn533/usb.c
+++ b/drivers/nfc/pn533/usb.c
@@ -403,7 +403,7 @@ static int pn533_acr122_poweron_rdr(struct pn533_usb_phy *phy)
 		       cmd, sizeof(cmd), false);
 
 	rc = usb_bulk_msg(phy->udev, phy->out_urb->pipe, buffer, sizeof(cmd),
-			  &transferred, 0);
+			  &transferred, 5000);
 	kfree(buffer);
 	if (rc || (transferred != sizeof(cmd))) {
 		nfc_err(&phy->udev->dev,
-- 
2.21.1


From 08e7f17c66dc3ab537e718c4b65a4d2e958e94e5 Mon Sep 17 00:00:00 2001
From: Vladis Dronov <vdronov@redhat.com>
Date: Mon, 13 Jan 2020 14:00:09 +0100
Subject: [PATCH 08/12] ptp: free ptp device pin descriptors properly

[ Upstream commit 75718584cb3c64e6269109d4d54f888ac5a5fd15 ]

There is a bug in ptp_clock_unregister(), where ptp_cleanup_pin_groups()
first frees ptp->pin_{,dev_}attr, but then posix_clock_unregister() needs
them to destroy a related sysfs device.

These functions can not be just swapped, as posix_clock_unregister() frees
ptp which is needed in the ptp_cleanup_pin_groups(). Fix this by calling
ptp_cleanup_pin_groups() in ptp_clock_release(), right before ptp is freed.

This makes this patch fix an UAF bug in a patch which fixes an UAF bug.

Reported-by: Antti Laakso <antti.laakso@intel.com>
Fixes: a33121e5487b ("ptp: fix the race between the release of ptp_clock and cdev")
Link: https://lore.kernel.org/netdev/3d2bd09735dbdaf003585ca376b7c1e5b69a19bd.camel@intel.com/
Signed-off-by: Vladis Dronov <vdronov@redhat.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/ptp/ptp_clock.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c
index b818f65480c1..e232233beb8f 100644
--- a/drivers/ptp/ptp_clock.c
+++ b/drivers/ptp/ptp_clock.c
@@ -179,6 +179,7 @@ static void ptp_clock_release(struct device *dev)
 {
 	struct ptp_clock *ptp = container_of(dev, struct ptp_clock, dev);
 
+	ptp_cleanup_pin_groups(ptp);
 	mutex_destroy(&ptp->tsevq_mux);
 	mutex_destroy(&ptp->pincfg_mux);
 	ida_simple_remove(&ptp_clocks_map, ptp->index);
@@ -315,9 +316,8 @@ int ptp_clock_unregister(struct ptp_clock *ptp)
 	if (ptp->pps_source)
 		pps_unregister_source(ptp->pps_source);
 
-	ptp_cleanup_pin_groups(ptp);
-
 	posix_clock_unregister(&ptp->clock);
+
 	return 0;
 }
 EXPORT_SYMBOL(ptp_clock_unregister);
-- 
2.21.1


From 26d2e033da1d51cd7c86ed3bb10b401edaf169b6 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Tue, 14 Jan 2020 09:27:29 +0100
Subject: [PATCH 09/12] r8152: add missing endpoint sanity check

[ Upstream commit 86f3f4cd53707ceeec079b83205c8d3c756eca93 ]

Add missing endpoint sanity check to probe in order to prevent a
NULL-pointer dereference (or slab out-of-bounds access) when retrieving
the interrupt-endpoint bInterval on ndo_open() in case a device lacks
the expected endpoints.

Fixes: 40a82917b1d3 ("net/usb/r8152: enable interrupt transfer")
Cc: hayeswang <hayeswang@realtek.com>
Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 91d47a714afd..db817d3c2bb8 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -5167,6 +5167,9 @@ static int rtl8152_probe(struct usb_interface *intf,
 		return -ENODEV;
 	}
 
+	if (intf->cur_altsetting->desc.bNumEndpoints < 3)
+		return -ENODEV;
+
 	usb_reset_device(udev);
 	netdev = alloc_etherdev(sizeof(struct r8152));
 	if (!netdev) {
-- 
2.21.1


From 936a3962a85b06dee8d9123fca5c5d28f41057ab Mon Sep 17 00:00:00 2001
From: Pengcheng Yang <yangpc@wangsu.com>
Date: Tue, 14 Jan 2020 17:23:40 +0800
Subject: [PATCH 10/12] tcp: fix marked lost packets not being retransmitted

[ Upstream commit e176b1ba476cf36f723cfcc7a9e57f3cb47dec70 ]

When the packet pointed to by retransmit_skb_hint is unlinked by ACK,
retransmit_skb_hint will be set to NULL in tcp_clean_rtx_queue().
If packet loss is detected at this time, retransmit_skb_hint will be set
to point to the current packet loss in tcp_verify_retransmit_hint(),
then the packets that were previously marked lost but not retransmitted
due to the restriction of cwnd will be skipped and cannot be
retransmitted.

To fix this, when retransmit_skb_hint is NULL, retransmit_skb_hint can
be reset only after all marked lost packets are retransmitted
(retrans_out >= lost_out), otherwise we need to traverse from
tcp_rtx_queue_head in tcp_xmit_retransmit_queue().

Packetdrill to demonstrate:

// Disable RACK and set max_reordering to keep things simple
    0 `sysctl -q net.ipv4.tcp_recovery=0`
   +0 `sysctl -q net.ipv4.tcp_max_reordering=3`

// Establish a connection
   +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
   +0 bind(3, ..., ...) = 0
   +0 listen(3, 1) = 0

  +.1 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
   +0 > S. 0:0(0) ack 1 <...>
 +.01 < . 1:1(0) ack 1 win 257
   +0 accept(3, ..., ...) = 4

// Send 8 data segments
   +0 write(4, ..., 8000) = 8000
   +0 > P. 1:8001(8000) ack 1

// Enter recovery and 1:3001 is marked lost
 +.01 < . 1:1(0) ack 1 win 257 <sack 3001:4001,nop,nop>
   +0 < . 1:1(0) ack 1 win 257 <sack 5001:6001 3001:4001,nop,nop>
   +0 < . 1:1(0) ack 1 win 257 <sack 5001:7001 3001:4001,nop,nop>

// Retransmit 1:1001, now retransmit_skb_hint points to 1001:2001
   +0 > . 1:1001(1000) ack 1

// 1001:2001 was ACKed causing retransmit_skb_hint to be set to NULL
 +.01 < . 1:1(0) ack 2001 win 257 <sack 5001:8001 3001:4001,nop,nop>
// Now retransmit_skb_hint points to 4001:5001 which is now marked lost

// BUG: 2001:3001 was not retransmitted
   +0 > . 2001:3001(1000) ack 1

Signed-off-by: Pengcheng Yang <yangpc@wangsu.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Tested-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 578b65e6e65b..e286a9647a73 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -901,9 +901,10 @@ static void tcp_check_sack_reordering(struct sock *sk, const u32 low_seq,
 /* This must be called before lost_out is incremented */
 static void tcp_verify_retransmit_hint(struct tcp_sock *tp, struct sk_buff *skb)
 {
-	if (!tp->retransmit_skb_hint ||
-	    before(TCP_SKB_CB(skb)->seq,
-		   TCP_SKB_CB(tp->retransmit_skb_hint)->seq))
+	if ((!tp->retransmit_skb_hint && tp->retrans_out >= tp->lost_out) ||
+	    (tp->retransmit_skb_hint &&
+	     before(TCP_SKB_CB(skb)->seq,
+		    TCP_SKB_CB(tp->retransmit_skb_hint)->seq)))
 		tp->retransmit_skb_hint = skb;
 }
 
-- 
2.21.1


From 8a2d3d423bb7d5ed103d735cc403b5b35deabe7a Mon Sep 17 00:00:00 2001
From: Navid Emamdoost <navid.emamdoost@gmail.com>
Date: Tue, 10 Sep 2019 18:01:40 -0500
Subject: [PATCH 11/12] wimax: i2400: fix memory leak

[ Upstream commit 2507e6ab7a9a440773be476141a255934468c5ef ]

In i2400m_op_rfkill_sw_toggle cmd buffer should be released along with
skb response.

Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wimax/i2400m/op-rfkill.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wimax/i2400m/op-rfkill.c b/drivers/net/wimax/i2400m/op-rfkill.c
index b0dba35a8ad2..7c92e8ace9c2 100644
--- a/drivers/net/wimax/i2400m/op-rfkill.c
+++ b/drivers/net/wimax/i2400m/op-rfkill.c
@@ -142,6 +142,7 @@ int i2400m_op_rfkill_sw_toggle(struct wimax_dev *wimax_dev,
 			"%d\n", result);
 	result = 0;
 error_cmd:
+	kfree(cmd);
 	kfree_skb(ack_skb);
 error_msg_to_dev:
 error_alloc:
-- 
2.21.1


From 9c46c1820dacebc4a157632a13b9716af3c6f648 Mon Sep 17 00:00:00 2001
From: Navid Emamdoost <navid.emamdoost@gmail.com>
Date: Fri, 25 Oct 2019 23:53:30 -0500
Subject: [PATCH 12/12] wimax: i2400: Fix memory leak in
 i2400m_op_rfkill_sw_toggle

[ Upstream commit 6f3ef5c25cc762687a7341c18cbea5af54461407 ]

In the implementation of i2400m_op_rfkill_sw_toggle() the allocated
buffer for cmd should be released before returning. The
documentation for i2400m_msg_to_dev() says when it returns the buffer
can be reused. Meaning cmd should be released in either case. Move
kfree(cmd) before return to be reached by all execution paths.

Fixes: 2507e6ab7a9a ("wimax: i2400: fix memory leak")
Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wimax/i2400m/op-rfkill.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wimax/i2400m/op-rfkill.c b/drivers/net/wimax/i2400m/op-rfkill.c
index 7c92e8ace9c2..dc6fe93ce71f 100644
--- a/drivers/net/wimax/i2400m/op-rfkill.c
+++ b/drivers/net/wimax/i2400m/op-rfkill.c
@@ -142,12 +142,12 @@ int i2400m_op_rfkill_sw_toggle(struct wimax_dev *wimax_dev,
 			"%d\n", result);
 	result = 0;
 error_cmd:
-	kfree(cmd);
 	kfree_skb(ack_skb);
 error_msg_to_dev:
 error_alloc:
 	d_fnend(4, dev, "(wimax_dev %p state %d) = %d\n",
 		wimax_dev, state, result);
+	kfree(cmd);
 	return result;
 }
 
-- 
2.21.1


[-- Attachment #3: net_54.mbox --]
[-- Type: Application/Octet-Stream, Size: 52985 bytes --]

From 59365bb9320cdcaee626def2434bafe5c8398cf4 Mon Sep 17 00:00:00 2001
From: Mohammed Gamal <mgamal@redhat.com>
Date: Tue, 14 Jan 2020 15:09:50 +0200
Subject: [PATCH 01/26] hv_netvsc: Fix memory leak when removing rndis device

[ Upstream commit 536dc5df2808efbefc5acee334d3c4f701790ec0 ]

kmemleak detects the following memory leak when hot removing
a network device:

unreferenced object 0xffff888083f63600 (size 256):
  comm "kworker/0:1", pid 12, jiffies 4294831717 (age 1113.676s)
  hex dump (first 32 bytes):
    00 40 c7 33 80 88 ff ff 00 00 00 00 10 00 00 00  .@.3............
    00 00 00 00 ad 4e ad de ff ff ff ff 00 00 00 00  .....N..........
  backtrace:
    [<00000000d4a8f5be>] rndis_filter_device_add+0x117/0x11c0 [hv_netvsc]
    [<000000009c02d75b>] netvsc_probe+0x5e7/0xbf0 [hv_netvsc]
    [<00000000ddafce23>] vmbus_probe+0x74/0x170 [hv_vmbus]
    [<00000000046e64f1>] really_probe+0x22f/0xb50
    [<000000005cc35eb7>] driver_probe_device+0x25e/0x370
    [<0000000043c642b2>] bus_for_each_drv+0x11f/0x1b0
    [<000000005e3d09f0>] __device_attach+0x1c6/0x2f0
    [<00000000a72c362f>] bus_probe_device+0x1a6/0x260
    [<0000000008478399>] device_add+0x10a3/0x18e0
    [<00000000cf07b48c>] vmbus_device_register+0xe7/0x1e0 [hv_vmbus]
    [<00000000d46cf032>] vmbus_add_channel_work+0x8ab/0x1770 [hv_vmbus]
    [<000000002c94bb64>] process_one_work+0x919/0x17d0
    [<0000000096de6781>] worker_thread+0x87/0xb40
    [<00000000fbe7397e>] kthread+0x333/0x3f0
    [<000000004f844269>] ret_from_fork+0x3a/0x50

rndis_filter_device_add() allocates an instance of struct rndis_device
which never gets deallocated as rndis_filter_device_remove() sets
net_device->extension which points to the rndis_device struct to NULL,
leaving the rndis_device dangling.

Since net_device->extension is eventually freed in free_netvsc_device(),
we refrain from setting it to NULL inside rndis_filter_device_remove()

Signed-off-by: Mohammed Gamal <mgamal@redhat.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/rndis_filter.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index f81e58267a6e..b9e44bb22289 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -1436,8 +1436,6 @@ void rndis_filter_device_remove(struct hv_device *dev,
 	/* Halt and release the rndis device */
 	rndis_filter_halt_device(net_dev, rndis_dev);
 
-	net_dev->extension = NULL;
-
 	netvsc_device_remove(dev);
 }
 
-- 
2.21.1


From 0dbceefbb214af5cd28e5be58270ab96b9a15dfa Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 14 Jan 2020 13:00:35 -0800
Subject: [PATCH 02/26] macvlan: use skb_reset_mac_header() in
 macvlan_queue_xmit()

[ Upstream commit 1712b2fff8c682d145c7889d2290696647d82dab ]

I missed the fact that macvlan_broadcast() can be used both
in RX and TX.

skb_eth_hdr() makes only sense in TX paths, so we can not
use it blindly in macvlan_broadcast()

Fixes: 96cc4b69581d ("macvlan: do not assume mac_header is set in macvlan_broadcast()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Jurgen Van Ham <juvanham@gmail.com>
Tested-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macvlan.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 747c0542a53c..c5bf61565726 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -259,7 +259,7 @@ static void macvlan_broadcast(struct sk_buff *skb,
 			      struct net_device *src,
 			      enum macvlan_mode mode)
 {
-	const struct ethhdr *eth = skb_eth_hdr(skb);
+	const struct ethhdr *eth = eth_hdr(skb);
 	const struct macvlan_dev *vlan;
 	struct sk_buff *nskb;
 	unsigned int i;
@@ -513,10 +513,11 @@ static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev)
 	const struct macvlan_dev *dest;
 
 	if (vlan->mode == MACVLAN_MODE_BRIDGE) {
-		const struct ethhdr *eth = (void *)skb->data;
+		const struct ethhdr *eth = skb_eth_hdr(skb);
 
 		/* send to other bridge ports directly */
 		if (is_multicast_ether_addr(eth->h_dest)) {
+			skb_reset_mac_header(skb);
 			macvlan_broadcast(skb, port, dev, MACVLAN_MODE_BRIDGE);
 			goto xmit_world;
 		}
-- 
2.21.1


From 36a0f384502eb2fa0b9cc1d9432e61bd8c392d16 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Wed, 15 Jan 2020 13:02:38 -0800
Subject: [PATCH 03/26] net: avoid updating qdisc_xmit_lock_key in
 netdev_update_lockdep_key()

[ Upstream commit 53d374979ef147ab51f5d632dfe20b14aebeccd0 ]

syzbot reported some bogus lockdep warnings, for example bad unlock
balance in sch_direct_xmit(). They are due to a race condition between
slow path and fast path, that is qdisc_xmit_lock_key gets re-registered
in netdev_update_lockdep_key() on slow path, while we could still
acquire the queue->_xmit_lock on fast path in this small window:

CPU A						CPU B
						__netif_tx_lock();
lockdep_unregister_key(qdisc_xmit_lock_key);
						__netif_tx_unlock();
lockdep_register_key(qdisc_xmit_lock_key);

In fact, unlike the addr_list_lock which has to be reordered when
the master/slave device relationship changes, queue->_xmit_lock is
only acquired on fast path and only when NETIF_F_LLTX is not set,
so there is likely no nested locking for it.

Therefore, we can just get rid of re-registration of
qdisc_xmit_lock_key.

Reported-by: syzbot+4ec99438ed7450da6272@syzkaller.appspotmail.com
Fixes: ab92d68fc22f ("net: core: add generic lockdep keys")
Cc: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 3e11c6bb4dd6..3098c90d60e2 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8953,22 +8953,10 @@ static void netdev_unregister_lockdep_key(struct net_device *dev)
 
 void netdev_update_lockdep_key(struct net_device *dev)
 {
-	struct netdev_queue *queue;
-	int i;
-
-	lockdep_unregister_key(&dev->qdisc_xmit_lock_key);
 	lockdep_unregister_key(&dev->addr_list_lock_key);
-
-	lockdep_register_key(&dev->qdisc_xmit_lock_key);
 	lockdep_register_key(&dev->addr_list_lock_key);
 
 	lockdep_set_class(&dev->addr_list_lock, &dev->addr_list_lock_key);
-	for (i = 0; i < dev->num_tx_queues; i++) {
-		queue = netdev_get_tx_queue(dev, i);
-
-		lockdep_set_class(&queue->_xmit_lock,
-				  &dev->qdisc_xmit_lock_key);
-	}
 }
 EXPORT_SYMBOL(netdev_update_lockdep_key);
 
-- 
2.21.1


From 2b0272d2d23b2751fcb47b7942dc82a8d34328e3 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <alobakin@dlink.ru>
Date: Wed, 15 Jan 2020 11:56:52 +0300
Subject: [PATCH 04/26] net: dsa: tag_qca: fix doubled Tx statistics

[ Upstream commit bd5874da57edd001b35cf28ae737779498c16a56 ]

DSA subsystem takes care of netdev statistics since commit 4ed70ce9f01c
("net: dsa: Refactor transmit path to eliminate duplication"), so
any accounting inside tagger callbacks is redundant and can lead to
messing up the stats.
This bug is present in Qualcomm tagger since day 0.

Fixes: cafdc45c949b ("net-next: dsa: add Qualcomm tag RX/TX handler")
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Alexander Lobakin <alobakin@dlink.ru>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/tag_qca.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c
index c95885215525..c8a128c9e5e0 100644
--- a/net/dsa/tag_qca.c
+++ b/net/dsa/tag_qca.c
@@ -33,9 +33,6 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct dsa_port *dp = dsa_slave_to_port(dev);
 	u16 *phdr, hdr;
 
-	dev->stats.tx_packets++;
-	dev->stats.tx_bytes += skb->len;
-
 	if (skb_cow_head(skb, 0) < 0)
 		return NULL;
 
-- 
2.21.1


From 6e77b6d9443bba3bb1e44a4463050bab8fae24ec Mon Sep 17 00:00:00 2001
From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Wed, 15 Jan 2020 10:46:45 +0800
Subject: [PATCH 05/26] net: hns3: pad the short frame before sending to the
 hardware

[ Upstream commit 36c67349a1a1c88b9cf11d7ca7762ababdb38867 ]

The hardware can not handle short frames below or equal to 32
bytes according to the hardware user manual, and it will trigger
a RAS error when the frame's length is below 33 bytes.

This patch pads the SKB when skb->len is below 33 bytes before
sending it to hardware.

Fixes: 76ad4f0ee747 ("net: hns3: Add support of HNS3 Ethernet Driver for hip08 SoC")
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 84d8816c8681..0c8d2269bc46 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -54,6 +54,8 @@ MODULE_PARM_DESC(debug, " Network interface message level setting");
 #define HNS3_INNER_VLAN_TAG	1
 #define HNS3_OUTER_VLAN_TAG	2
 
+#define HNS3_MIN_TX_LEN		33U
+
 /* hns3_pci_tbl - PCI Device ID Table
  *
  * Last entry must be all 0s
@@ -1329,6 +1331,10 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev)
 	int ret;
 	int i;
 
+	/* Hardware can only handle short frames above 32 bytes */
+	if (skb_put_padto(skb, HNS3_MIN_TX_LEN))
+		return NETDEV_TX_OK;
+
 	/* Prefetch the data used later */
 	prefetch(skb->data);
 
-- 
2.21.1


From 685807cd1060dcf1cf719d3897d7efe25d045b44 Mon Sep 17 00:00:00 2001
From: Yonglong Liu <liuyonglong@huawei.com>
Date: Thu, 16 Jan 2020 15:41:17 +0800
Subject: [PATCH 06/26] net: hns: fix soft lockup when there is not enough
 memory

[ Upstream commit 49edd6a2c456150870ddcef5b7ed11b21d849e13 ]

When there is not enough memory and napi_alloc_skb() return NULL,
the HNS driver will print error message, and than try again, if
the memory is not enough for a while, huge error message and the
retry operation will cause soft lockup.

When napi_alloc_skb() return NULL because of no memory, we can
get a warn_alloc() call trace, so this patch deletes the error
message. We already use polling mode to handle irq, but the
retry operation will render the polling weight inactive, this
patch just return budget when the rx is not completed to avoid
dead loop.

Fixes: 36eedfde1a36 ("net: hns: Optimize hns_nic_common_poll for better performance")
Fixes: b5996f11ea54 ("net: add Hisilicon Network Subsystem basic ethernet support")
Signed-off-by: Yonglong Liu <liuyonglong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns/hns_enet.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index 14ab20491fd0..eb69e5c81a4d 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -565,7 +565,6 @@ static int hns_nic_poll_rx_skb(struct hns_nic_ring_data *ring_data,
 	skb = *out_skb = napi_alloc_skb(&ring_data->napi,
 					HNS_RX_HEAD_SIZE);
 	if (unlikely(!skb)) {
-		netdev_err(ndev, "alloc rx skb fail\n");
 		ring->stats.sw_err_cnt++;
 		return -ENOMEM;
 	}
@@ -1056,7 +1055,6 @@ static int hns_nic_common_poll(struct napi_struct *napi, int budget)
 		container_of(napi, struct hns_nic_ring_data, napi);
 	struct hnae_ring *ring = ring_data->ring;
 
-try_again:
 	clean_complete += ring_data->poll_one(
 				ring_data, budget - clean_complete,
 				ring_data->ex_process);
@@ -1066,7 +1064,7 @@ static int hns_nic_common_poll(struct napi_struct *napi, int budget)
 			napi_complete(napi);
 			ring->q->handle->dev->ops->toggle_ring_irq(ring, 0);
 		} else {
-			goto try_again;
+			return budget;
 		}
 	}
 
-- 
2.21.1


From 9213b800e659e1c698e6ba9af436f9079dcc7c69 Mon Sep 17 00:00:00 2001
From: Michael Grzeschik <m.grzeschik@pengutronix.de>
Date: Thu, 16 Jan 2020 14:16:31 +0100
Subject: [PATCH 07/26] net: phy: dp83867: Set FORCE_LINK_GOOD to default after
 reset

[ Upstream commit 86ffe920e669ec73035e84553e18edf17d16317c ]

According to the Datasheet this bit should be 0 (Normal operation) in
default. With the FORCE_LINK_GOOD bit set, it is not possible to get a
link. This patch sets FORCE_LINK_GOOD to the default value after
resetting the phy.

Signed-off-by: Michael Grzeschik <m.grzeschik@pengutronix.de>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/dp83867.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c
index cf4455bbf888..52e80434e45e 100644
--- a/drivers/net/phy/dp83867.c
+++ b/drivers/net/phy/dp83867.c
@@ -80,6 +80,7 @@
 #define DP83867_PHYCR_FIFO_DEPTH_MAX		0x03
 #define DP83867_PHYCR_FIFO_DEPTH_MASK		GENMASK(15, 14)
 #define DP83867_PHYCR_RESERVED_MASK		BIT(11)
+#define DP83867_PHYCR_FORCE_LINK_GOOD		BIT(10)
 
 /* RGMIIDCTL bits */
 #define DP83867_RGMII_TX_CLK_DELAY_MAX		0xf
@@ -454,7 +455,12 @@ static int dp83867_phy_reset(struct phy_device *phydev)
 
 	usleep_range(10, 20);
 
-	return 0;
+	/* After reset FORCE_LINK_GOOD bit is set. Although the
+	 * default value should be unset. Disable FORCE_LINK_GOOD
+	 * for the phy to work properly.
+	 */
+	return phy_modify(phydev, MII_DP83867_PHYCTRL,
+			 DP83867_PHYCR_FORCE_LINK_GOOD, 0);
 }
 
 static struct phy_driver dp83867_driver[] = {
-- 
2.21.1


From d2e590dd88737a90ffa7e2cb70141047597c60f3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 15 Jan 2020 08:20:39 -0800
Subject: [PATCH 08/26] net/sched: act_ife: initalize ife->metalist earlier

[ Upstream commit 44c23d71599f81a1c7fe8389e0319822dd50c37c ]

It seems better to init ife->metalist earlier in tcf_ife_init()
to avoid the following crash :

kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] PREEMPT SMP KASAN
CPU: 0 PID: 10483 Comm: syz-executor216 Not tainted 5.5.0-rc5-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:_tcf_ife_cleanup net/sched/act_ife.c:412 [inline]
RIP: 0010:tcf_ife_cleanup+0x6e/0x400 net/sched/act_ife.c:431
Code: 48 c1 ea 03 80 3c 02 00 0f 85 94 03 00 00 49 8b bd f8 00 00 00 48 b8 00 00 00 00 00 fc ff df 4c 8d 67 e8 48 89 fa 48 c1 ea 03 <80> 3c 02 00 0f 85 5c 03 00 00 48 bb 00 00 00 00 00 fc ff df 48 8b
RSP: 0018:ffffc90001dc6d00 EFLAGS: 00010246
RAX: dffffc0000000000 RBX: ffffffff864619c0 RCX: ffffffff815bfa09
RDX: 0000000000000000 RSI: 0000000000000004 RDI: 0000000000000000
RBP: ffffc90001dc6d50 R08: 0000000000000004 R09: fffff520003b8d8e
R10: fffff520003b8d8d R11: 0000000000000003 R12: ffffffffffffffe8
R13: ffff8880a79fc000 R14: ffff88809aba0e00 R15: 0000000000000000
FS:  0000000001b51880(0000) GS:ffff8880ae800000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000563f52cce140 CR3: 0000000093541000 CR4: 00000000001406f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 tcf_action_cleanup+0x62/0x1b0 net/sched/act_api.c:119
 __tcf_action_put+0xfa/0x130 net/sched/act_api.c:135
 __tcf_idr_release net/sched/act_api.c:165 [inline]
 __tcf_idr_release+0x59/0xf0 net/sched/act_api.c:145
 tcf_idr_release include/net/act_api.h:171 [inline]
 tcf_ife_init+0x97c/0x1870 net/sched/act_ife.c:616
 tcf_action_init_1+0x6b6/0xa40 net/sched/act_api.c:944
 tcf_action_init+0x21a/0x330 net/sched/act_api.c:1000
 tcf_action_add+0xf5/0x3b0 net/sched/act_api.c:1410
 tc_ctl_action+0x390/0x488 net/sched/act_api.c:1465
 rtnetlink_rcv_msg+0x45e/0xaf0 net/core/rtnetlink.c:5424
 netlink_rcv_skb+0x177/0x450 net/netlink/af_netlink.c:2477
 rtnetlink_rcv+0x1d/0x30 net/core/rtnetlink.c:5442
 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
 netlink_unicast+0x58c/0x7d0 net/netlink/af_netlink.c:1328
 netlink_sendmsg+0x91c/0xea0 net/netlink/af_netlink.c:1917
 sock_sendmsg_nosec net/socket.c:639 [inline]
 sock_sendmsg+0xd7/0x130 net/socket.c:659
 ____sys_sendmsg+0x753/0x880 net/socket.c:2330
 ___sys_sendmsg+0x100/0x170 net/socket.c:2384
 __sys_sendmsg+0x105/0x1d0 net/socket.c:2417
 __do_sys_sendmsg net/socket.c:2426 [inline]
 __se_sys_sendmsg net/socket.c:2424 [inline]
 __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2424
 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Fixes: 11a94d7fd80f ("net/sched: act_ife: validate the control action inside init()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Davide Caratti <dcaratti@redhat.com>
Reviewed-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ife.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 3a31e241c647..a0cfb4793c93 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -536,6 +536,9 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	}
 
 	ife = to_ife(*a);
+	if (ret == ACT_P_CREATED)
+		INIT_LIST_HEAD(&ife->metalist);
+
 	err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
 	if (err < 0)
 		goto release_idr;
@@ -565,10 +568,6 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 		p->eth_type = ife_type;
 	}
 
-
-	if (ret == ACT_P_CREATED)
-		INIT_LIST_HEAD(&ife->metalist);
-
 	if (tb[TCA_IFE_METALST]) {
 		err = nla_parse_nested_deprecated(tb2, IFE_META_MAX,
 						  tb[TCA_IFE_METALST], NULL,
-- 
2.21.1


From a5a452c482236478c87aa4ce2226ba7fe4c84c26 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 13 Jan 2020 09:27:11 -0800
Subject: [PATCH 09/26] net: usb: lan78xx: limit size of local TSO packets

[ Upstream commit f8d7408a4d7f60f8b2df0f81decdc882dd9c20dc ]

lan78xx_tx_bh() makes sure to not exceed MAX_SINGLE_PACKET_SIZE
bytes in the aggregated packets it builds, but does
nothing to prevent large GSO packets being submitted.

Pierre-Francois reported various hangs when/if TSO is enabled.

For localy generated packets, we can use netif_set_gso_max_size()
to limit the size of TSO packets.

Note that forwarded packets could still hit the issue,
so a complete fix might require implementing .ndo_features_check
for this driver, forcing a software segmentation if the size
of the TSO packet exceeds MAX_SINGLE_PACKET_SIZE.

Fixes: 55d7de9de6c3 ("Microchip's LAN7800 family USB 2/3 to 10/100/1000 Ethernet device driver")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: RENARD Pierre-Francois <pfrenard@gmail.com>
Tested-by: RENARD Pierre-Francois <pfrenard@gmail.com>
Cc: Stefan Wahren <stefan.wahren@i2se.com>
Cc: Woojung Huh <woojung.huh@microchip.com>
Cc: Microchip Linux Driver Support <UNGLinuxDriver@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/lan78xx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 3e5f2f7a155e..c232f1612083 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -3750,6 +3750,7 @@ static int lan78xx_probe(struct usb_interface *intf,
 
 	/* MTU range: 68 - 9000 */
 	netdev->max_mtu = MAX_SINGLE_PACKET_SIZE;
+	netif_set_gso_max_size(netdev, MAX_SINGLE_PACKET_SIZE - MAX_HEADER);
 
 	dev->ep_blkin = (intf->cur_altsetting)->endpoint + 0;
 	dev->ep_blkout = (intf->cur_altsetting)->endpoint + 1;
-- 
2.21.1


From 81530079a7ea2978ee5e5361a25e19ec56d26ba1 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Tue, 14 Jan 2020 14:54:48 +0000
Subject: [PATCH 10/26] net/wan/fsl_ucc_hdlc: fix out of bounds write on array
 utdm_info

[ Upstream commit ddf420390526ede3b9ff559ac89f58cb59d9db2f ]

Array utdm_info is declared as an array of MAX_HDLC_NUM (4) elements
however up to UCC_MAX_NUM (8) elements are potentially being written
to it.  Currently we have an array out-of-bounds write error on the
last 4 elements. Fix this by making utdm_info UCC_MAX_NUM elements in
size.

Addresses-Coverity: ("Out-of-bounds write")
Fixes: c19b6d246a35 ("drivers/net: support hdlc function for QE-UCC")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wan/fsl_ucc_hdlc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c
index ca0f3be2b6bf..aef7de225783 100644
--- a/drivers/net/wan/fsl_ucc_hdlc.c
+++ b/drivers/net/wan/fsl_ucc_hdlc.c
@@ -73,7 +73,7 @@ static struct ucc_tdm_info utdm_primary_info = {
 	},
 };
 
-static struct ucc_tdm_info utdm_info[MAX_HDLC_NUM];
+static struct ucc_tdm_info utdm_info[UCC_MAX_NUM];
 
 static int uhdlc_init(struct ucc_hdlc_private *priv)
 {
-- 
2.21.1


From f9ff864a5c16e4ed2b9a5e336bb02b790f049709 Mon Sep 17 00:00:00 2001
From: Vladis Dronov <vdronov@redhat.com>
Date: Mon, 13 Jan 2020 14:00:09 +0100
Subject: [PATCH 11/26] ptp: free ptp device pin descriptors properly

[ Upstream commit 75718584cb3c64e6269109d4d54f888ac5a5fd15 ]

There is a bug in ptp_clock_unregister(), where ptp_cleanup_pin_groups()
first frees ptp->pin_{,dev_}attr, but then posix_clock_unregister() needs
them to destroy a related sysfs device.

These functions can not be just swapped, as posix_clock_unregister() frees
ptp which is needed in the ptp_cleanup_pin_groups(). Fix this by calling
ptp_cleanup_pin_groups() in ptp_clock_release(), right before ptp is freed.

This makes this patch fix an UAF bug in a patch which fixes an UAF bug.

Reported-by: Antti Laakso <antti.laakso@intel.com>
Fixes: a33121e5487b ("ptp: fix the race between the release of ptp_clock and cdev")
Link: https://lore.kernel.org/netdev/3d2bd09735dbdaf003585ca376b7c1e5b69a19bd.camel@intel.com/
Signed-off-by: Vladis Dronov <vdronov@redhat.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/ptp/ptp_clock.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c
index 61fafe0374ce..b84f16bbd6f2 100644
--- a/drivers/ptp/ptp_clock.c
+++ b/drivers/ptp/ptp_clock.c
@@ -170,6 +170,7 @@ static void ptp_clock_release(struct device *dev)
 {
 	struct ptp_clock *ptp = container_of(dev, struct ptp_clock, dev);
 
+	ptp_cleanup_pin_groups(ptp);
 	mutex_destroy(&ptp->tsevq_mux);
 	mutex_destroy(&ptp->pincfg_mux);
 	ida_simple_remove(&ptp_clocks_map, ptp->index);
@@ -302,9 +303,8 @@ int ptp_clock_unregister(struct ptp_clock *ptp)
 	if (ptp->pps_source)
 		pps_unregister_source(ptp->pps_source);
 
-	ptp_cleanup_pin_groups(ptp);
-
 	posix_clock_unregister(&ptp->clock);
+
 	return 0;
 }
 EXPORT_SYMBOL(ptp_clock_unregister);
-- 
2.21.1


From 2c6922e953bab130410a10b4e91a37d33ad52a47 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Tue, 14 Jan 2020 09:27:29 +0100
Subject: [PATCH 12/26] r8152: add missing endpoint sanity check

[ Upstream commit 86f3f4cd53707ceeec079b83205c8d3c756eca93 ]

Add missing endpoint sanity check to probe in order to prevent a
NULL-pointer dereference (or slab out-of-bounds access) when retrieving
the interrupt-endpoint bInterval on ndo_open() in case a device lacks
the expected endpoints.

Fixes: 40a82917b1d3 ("net/usb/r8152: enable interrupt transfer")
Cc: hayeswang <hayeswang@realtek.com>
Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index b2507c59ba8b..9e4b7a400284 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -5587,6 +5587,9 @@ static int rtl8152_probe(struct usb_interface *intf,
 		return -ENODEV;
 	}
 
+	if (intf->cur_altsetting->desc.bNumEndpoints < 3)
+		return -ENODEV;
+
 	usb_reset_device(udev);
 	netdev = alloc_etherdev(sizeof(struct r8152));
 	if (!netdev) {
-- 
2.21.1


From fb76d1aeeaefd1d93070e351fd465af2c6c34024 Mon Sep 17 00:00:00 2001
From: Pengcheng Yang <yangpc@wangsu.com>
Date: Tue, 14 Jan 2020 17:23:40 +0800
Subject: [PATCH 13/26] tcp: fix marked lost packets not being retransmitted

[ Upstream commit e176b1ba476cf36f723cfcc7a9e57f3cb47dec70 ]

When the packet pointed to by retransmit_skb_hint is unlinked by ACK,
retransmit_skb_hint will be set to NULL in tcp_clean_rtx_queue().
If packet loss is detected at this time, retransmit_skb_hint will be set
to point to the current packet loss in tcp_verify_retransmit_hint(),
then the packets that were previously marked lost but not retransmitted
due to the restriction of cwnd will be skipped and cannot be
retransmitted.

To fix this, when retransmit_skb_hint is NULL, retransmit_skb_hint can
be reset only after all marked lost packets are retransmitted
(retrans_out >= lost_out), otherwise we need to traverse from
tcp_rtx_queue_head in tcp_xmit_retransmit_queue().

Packetdrill to demonstrate:

// Disable RACK and set max_reordering to keep things simple
    0 `sysctl -q net.ipv4.tcp_recovery=0`
   +0 `sysctl -q net.ipv4.tcp_max_reordering=3`

// Establish a connection
   +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
   +0 bind(3, ..., ...) = 0
   +0 listen(3, 1) = 0

  +.1 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
   +0 > S. 0:0(0) ack 1 <...>
 +.01 < . 1:1(0) ack 1 win 257
   +0 accept(3, ..., ...) = 4

// Send 8 data segments
   +0 write(4, ..., 8000) = 8000
   +0 > P. 1:8001(8000) ack 1

// Enter recovery and 1:3001 is marked lost
 +.01 < . 1:1(0) ack 1 win 257 <sack 3001:4001,nop,nop>
   +0 < . 1:1(0) ack 1 win 257 <sack 5001:6001 3001:4001,nop,nop>
   +0 < . 1:1(0) ack 1 win 257 <sack 5001:7001 3001:4001,nop,nop>

// Retransmit 1:1001, now retransmit_skb_hint points to 1001:2001
   +0 > . 1:1001(1000) ack 1

// 1001:2001 was ACKed causing retransmit_skb_hint to be set to NULL
 +.01 < . 1:1(0) ack 2001 win 257 <sack 5001:8001 3001:4001,nop,nop>
// Now retransmit_skb_hint points to 4001:5001 which is now marked lost

// BUG: 2001:3001 was not retransmitted
   +0 > . 2001:3001(1000) ack 1

Signed-off-by: Pengcheng Yang <yangpc@wangsu.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Tested-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 67e44e6717b0..59b78ce2ce2e 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -915,9 +915,10 @@ static void tcp_check_sack_reordering(struct sock *sk, const u32 low_seq,
 /* This must be called before lost_out is incremented */
 static void tcp_verify_retransmit_hint(struct tcp_sock *tp, struct sk_buff *skb)
 {
-	if (!tp->retransmit_skb_hint ||
-	    before(TCP_SKB_CB(skb)->seq,
-		   TCP_SKB_CB(tp->retransmit_skb_hint)->seq))
+	if ((!tp->retransmit_skb_hint && tp->retrans_out >= tp->lost_out) ||
+	    (tp->retransmit_skb_hint &&
+	     before(TCP_SKB_CB(skb)->seq,
+		    TCP_SKB_CB(tp->retransmit_skb_hint)->seq)))
 		tp->retransmit_skb_hint = skb;
 }
 
-- 
2.21.1


From e72587e491b5d69fa4ce399adb000109306e054b Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Fri, 17 Jan 2020 00:32:45 -0500
Subject: [PATCH 14/26] bnxt_en: Fix NTUPLE firmware command failures.

[ Upstream commit ceb3284c588eee5ea256c70e4d8d7cf399b8134e ]

The NTUPLE related firmware commands are sent to the wrong firmware
channel, causing all these commands to fail on new firmware that
supports the new firmware channel.  Fix it by excluding the 3
NTUPLE firmware commands from the list for the new firmware channel.

Fixes: 760b6d33410c ("bnxt_en: Add support for 2nd firmware message channel.")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.h | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index dc26e3ace43f..3c7ccb2f55a0 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1904,9 +1904,6 @@ static inline bool bnxt_cfa_hwrm_message(u16 req_type)
 	case HWRM_CFA_ENCAP_RECORD_FREE:
 	case HWRM_CFA_DECAP_FILTER_ALLOC:
 	case HWRM_CFA_DECAP_FILTER_FREE:
-	case HWRM_CFA_NTUPLE_FILTER_ALLOC:
-	case HWRM_CFA_NTUPLE_FILTER_FREE:
-	case HWRM_CFA_NTUPLE_FILTER_CFG:
 	case HWRM_CFA_EM_FLOW_ALLOC:
 	case HWRM_CFA_EM_FLOW_FREE:
 	case HWRM_CFA_EM_FLOW_CFG:
-- 
2.21.1


From a7c19e915f767d006829de33cdbb9b33e0f2eced Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Fri, 17 Jan 2020 00:32:46 -0500
Subject: [PATCH 15/26] bnxt_en: Fix ipv6 RFS filter matching logic.

[ Upstream commit 6fc7caa84e713f7627e171ab1e7c4b5be0dc9b3d ]

Fix bnxt_fltr_match() to match ipv6 source and destination addresses.
The function currently only checks ipv4 addresses and will not work
corrently on ipv6 filters.

Fixes: c0c050c58d84 ("bnxt_en: New Broadcom ethernet driver.")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 22 +++++++++++++++++-----
 1 file changed, 17 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 5c75b061243f..2179f4ea8936 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -10991,11 +10991,23 @@ static bool bnxt_fltr_match(struct bnxt_ntuple_filter *f1,
 	struct flow_keys *keys1 = &f1->fkeys;
 	struct flow_keys *keys2 = &f2->fkeys;
 
-	if (keys1->addrs.v4addrs.src == keys2->addrs.v4addrs.src &&
-	    keys1->addrs.v4addrs.dst == keys2->addrs.v4addrs.dst &&
-	    keys1->ports.ports == keys2->ports.ports &&
-	    keys1->basic.ip_proto == keys2->basic.ip_proto &&
-	    keys1->basic.n_proto == keys2->basic.n_proto &&
+	if (keys1->basic.n_proto != keys2->basic.n_proto ||
+	    keys1->basic.ip_proto != keys2->basic.ip_proto)
+		return false;
+
+	if (keys1->basic.n_proto == htons(ETH_P_IP)) {
+		if (keys1->addrs.v4addrs.src != keys2->addrs.v4addrs.src ||
+		    keys1->addrs.v4addrs.dst != keys2->addrs.v4addrs.dst)
+			return false;
+	} else {
+		if (memcmp(&keys1->addrs.v6addrs.src, &keys2->addrs.v6addrs.src,
+			   sizeof(keys1->addrs.v6addrs.src)) ||
+		    memcmp(&keys1->addrs.v6addrs.dst, &keys2->addrs.v6addrs.dst,
+			   sizeof(keys1->addrs.v6addrs.dst)))
+			return false;
+	}
+
+	if (keys1->ports.ports == keys2->ports.ports &&
 	    keys1->control.flags == keys2->control.flags &&
 	    ether_addr_equal(f1->src_mac_addr, f2->src_mac_addr) &&
 	    ether_addr_equal(f1->dst_mac_addr, f2->dst_mac_addr))
-- 
2.21.1


From e688234063100895d8fc356842bb2347fa2219de Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Fri, 17 Jan 2020 00:32:47 -0500
Subject: [PATCH 16/26] bnxt_en: Do not treat DSN (Digital Serial Number) read
 failure as fatal.

[ Upstream commit d061b2411d5f3d6272187ab734ce0640827fca13 ]

DSN read can fail, for example on a kdump kernel without PCIe extended
config space support.  If DSN read fails, don't set the
BNXT_FLAG_DSN_VALID flag and continue loading.  Check the flag
to see if the stored DSN is valid before using it.  Only VF reps
creation should fail without valid DSN.

Fixes: 03213a996531 ("bnxt: move bp->switch_id initialization to PF probe")
Reported-by: Marc Smith <msmith626@gmail.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c     | 7 +++----
 drivers/net/ethernet/broadcom/bnxt/bnxt.h     | 1 +
 drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c | 3 +++
 3 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 2179f4ea8936..cf292f7c3d3c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -11299,7 +11299,7 @@ int bnxt_get_port_parent_id(struct net_device *dev,
 		return -EOPNOTSUPP;
 
 	/* The PF and it's VF-reps only support the switchdev framework */
-	if (!BNXT_PF(bp))
+	if (!BNXT_PF(bp) || !(bp->flags & BNXT_FLAG_DSN_VALID))
 		return -EOPNOTSUPP;
 
 	ppid->id_len = sizeof(bp->switch_id);
@@ -11691,6 +11691,7 @@ static int bnxt_pcie_dsn_get(struct bnxt *bp, u8 dsn[])
 	put_unaligned_le32(dw, &dsn[0]);
 	pci_read_config_dword(pdev, pos + 4, &dw);
 	put_unaligned_le32(dw, &dsn[4]);
+	bp->flags |= BNXT_FLAG_DSN_VALID;
 	return 0;
 }
 
@@ -11802,9 +11803,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	if (BNXT_PF(bp)) {
 		/* Read the adapter's DSN to use as the eswitch switch_id */
-		rc = bnxt_pcie_dsn_get(bp, bp->switch_id);
-		if (rc)
-			goto init_err_pci_clean;
+		bnxt_pcie_dsn_get(bp, bp->switch_id);
 	}
 
 	/* MTU range: 60 - FW defined max */
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 3c7ccb2f55a0..2e6ad53fdc75 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1510,6 +1510,7 @@ struct bnxt {
 	#define BNXT_FLAG_NO_AGG_RINGS	0x20000
 	#define BNXT_FLAG_RX_PAGE_MODE	0x40000
 	#define BNXT_FLAG_MULTI_HOST	0x100000
+	#define BNXT_FLAG_DSN_VALID	0x200000
 	#define BNXT_FLAG_DOUBLE_DB	0x400000
 	#define BNXT_FLAG_CHIP_NITRO_A0	0x1000000
 	#define BNXT_FLAG_DIM		0x2000000
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
index f9bf7d7250ab..b010b34cdaf8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
@@ -398,6 +398,9 @@ static int bnxt_vf_reps_create(struct bnxt *bp)
 	struct net_device *dev;
 	int rc, i;
 
+	if (!(bp->flags & BNXT_FLAG_DSN_VALID))
+		return -ENODEV;
+
 	bp->vf_reps = kcalloc(num_vfs, sizeof(vf_rep), GFP_KERNEL);
 	if (!bp->vf_reps)
 		return -ENOMEM;
-- 
2.21.1


From ad8637da6ee09f2a10df4943fc73de78b90475f1 Mon Sep 17 00:00:00 2001
From: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Date: Wed, 15 Jan 2020 13:02:42 +0900
Subject: [PATCH 17/26] net: ethernet: ave: Avoid lockdep warning

[ Upstream commit 82d5d6a638cbd12b7dfe8acafd9efd87a656cc06 ]

When building with PROVE_LOCKING=y, lockdep shows the following
dump message.

    INFO: trying to register non-static key.
    the code is fine but needs lockdep annotation.
    turning off the locking correctness validator.
     ...

Calling device_set_wakeup_enable() directly occurs this issue,
and it isn't necessary for initialization, so this patch creates
internal function __ave_ethtool_set_wol() and replaces with this
in ave_init() and ave_resume().

Fixes: 7200f2e3c9e2 ("net: ethernet: ave: Set initial wol state to disabled")
Signed-off-by: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/socionext/sni_ave.c | 20 +++++++++++++-------
 1 file changed, 13 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c
index 6e984d5a729f..38d39c4b5ac8 100644
--- a/drivers/net/ethernet/socionext/sni_ave.c
+++ b/drivers/net/ethernet/socionext/sni_ave.c
@@ -424,16 +424,22 @@ static void ave_ethtool_get_wol(struct net_device *ndev,
 		phy_ethtool_get_wol(ndev->phydev, wol);
 }
 
-static int ave_ethtool_set_wol(struct net_device *ndev,
-			       struct ethtool_wolinfo *wol)
+static int __ave_ethtool_set_wol(struct net_device *ndev,
+				 struct ethtool_wolinfo *wol)
 {
-	int ret;
-
 	if (!ndev->phydev ||
 	    (wol->wolopts & (WAKE_ARP | WAKE_MAGICSECURE)))
 		return -EOPNOTSUPP;
 
-	ret = phy_ethtool_set_wol(ndev->phydev, wol);
+	return phy_ethtool_set_wol(ndev->phydev, wol);
+}
+
+static int ave_ethtool_set_wol(struct net_device *ndev,
+			       struct ethtool_wolinfo *wol)
+{
+	int ret;
+
+	ret = __ave_ethtool_set_wol(ndev, wol);
 	if (!ret)
 		device_set_wakeup_enable(&ndev->dev, !!wol->wolopts);
 
@@ -1216,7 +1222,7 @@ static int ave_init(struct net_device *ndev)
 
 	/* set wol initial state disabled */
 	wol.wolopts = 0;
-	ave_ethtool_set_wol(ndev, &wol);
+	__ave_ethtool_set_wol(ndev, &wol);
 
 	if (!phy_interface_is_rgmii(phydev))
 		phy_set_max_speed(phydev, SPEED_100);
@@ -1768,7 +1774,7 @@ static int ave_resume(struct device *dev)
 
 	ave_ethtool_get_wol(ndev, &wol);
 	wol.wolopts = priv->wolopts;
-	ave_ethtool_set_wol(ndev, &wol);
+	__ave_ethtool_set_wol(ndev, &wol);
 
 	if (ndev->phydev) {
 		ret = phy_resume(ndev->phydev);
-- 
2.21.1


From ae9240d40524c9b361dce503c89d68a38aab6d65 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 16 Jan 2020 13:08:58 -0800
Subject: [PATCH 18/26] net: systemport: Fixed queue mapping in internal ring
 map

[ Upstream commit 5a9ef19454cd5daec8041bc7c3c11deb7456d9a0 ]

We would not be transmitting using the correct SYSTEMPORT transmit queue
during ndo_select_queue() which looks up the internal TX ring map
because while establishing the mapping we would be off by 4, so for
instance, when we populate switch port mappings we would be doing:

switch port 0, queue 0 -> ring index #0
switch port 0, queue 1 -> ring index #1
...
switch port 0, queue 3 -> ring index #3
switch port 1, queue 0 -> ring index #8 (4 + 4 * 1)
...

instead of using ring index #4. This would cause our ndo_select_queue()
to use the fallback queue mechanism which would pick up an incorrect
ring for that switch port. Fix this by using the correct switch queue
number instead of SYSTEMPORT queue number.

Fixes: 25c440704661 ("net: systemport: Simplify queue mapping logic")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bcmsysport.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index a977a459bd20..b4c664957266 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -2323,7 +2323,7 @@ static int bcm_sysport_map_queues(struct notifier_block *nb,
 		ring->switch_queue = qp;
 		ring->switch_port = port;
 		ring->inspect = true;
-		priv->ring_map[q + port * num_tx_queues] = ring;
+		priv->ring_map[qp + port * num_tx_queues] = ring;
 		qp++;
 	}
 
@@ -2338,7 +2338,7 @@ static int bcm_sysport_unmap_queues(struct notifier_block *nb,
 	struct net_device *slave_dev;
 	unsigned int num_tx_queues;
 	struct net_device *dev;
-	unsigned int q, port;
+	unsigned int q, qp, port;
 
 	priv = container_of(nb, struct bcm_sysport_priv, dsa_notifier);
 	if (priv->netdev != info->master)
@@ -2364,7 +2364,8 @@ static int bcm_sysport_unmap_queues(struct notifier_block *nb,
 			continue;
 
 		ring->inspect = false;
-		priv->ring_map[q + port * num_tx_queues] = NULL;
+		qp = ring->switch_queue;
+		priv->ring_map[qp + port * num_tx_queues] = NULL;
 	}
 
 	return 0;
-- 
2.21.1


From 7f83fbd356ee103da789dd805822fd64e2bc70e3 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 16 Jan 2020 20:43:27 +0200
Subject: [PATCH 19/26] net: dsa: sja1105: Don't error out on disabled ports
 with no phy-mode

[ Upstream commit 27afe0d34e9121a3d61cc0af9b17c2542dadde24 ]

The sja1105_parse_ports_node function was tested only on device trees
where all ports were enabled. Fix this check so that the driver
continues to probe only with the ports where status is not "disabled",
as expected.

Fixes: 8aa9ebccae87 ("net: dsa: Introduce driver for NXP SJA1105 5-port L2 switch")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/sja1105/sja1105_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index 7763221286d4..3b51e87a3714 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -619,7 +619,7 @@ static int sja1105_parse_ports_node(struct sja1105_private *priv,
 	struct device *dev = &priv->spidev->dev;
 	struct device_node *child;
 
-	for_each_child_of_node(ports_node, child) {
+	for_each_available_child_of_node(ports_node, child) {
 		struct device_node *phy_node;
 		int phy_mode;
 		u32 index;
-- 
2.21.1


From 44db7da23e1b6f58817e35fbd8813acdd8acef18 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <alobakin@dlink.ru>
Date: Wed, 15 Jan 2020 11:54:38 +0300
Subject: [PATCH 20/26] net: dsa: tag_gswip: fix typo in tagger name

[ Upstream commit ad32205470919c8e04cdd33e0613bdba50c2376d ]

The correct name is GSWIP (Gigabit Switch IP). Typo was introduced in
875138f81d71a ("dsa: Move tagger name into its ops structure") while
moving tagger names to their structures.

Fixes: 875138f81d71a ("dsa: Move tagger name into its ops structure")
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Alexander Lobakin <alobakin@dlink.ru>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Acked-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/tag_gswip.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/dsa/tag_gswip.c b/net/dsa/tag_gswip.c
index b678160bbd66..408d4af390a0 100644
--- a/net/dsa/tag_gswip.c
+++ b/net/dsa/tag_gswip.c
@@ -104,7 +104,7 @@ static struct sk_buff *gswip_tag_rcv(struct sk_buff *skb,
 }
 
 static const struct dsa_device_ops gswip_netdev_ops = {
-	.name = "gwsip",
+	.name = "gswip",
 	.proto	= DSA_TAG_PROTO_GSWIP,
 	.xmit = gswip_tag_xmit,
 	.rcv = gswip_tag_rcv,
-- 
2.21.1


From fe5a4ce3b1ba76c09f26320d0690bc15f5254a6b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 18 Jan 2020 20:45:06 -0800
Subject: [PATCH 21/26] net: sched: act_ctinfo: fix memory leak
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 09d4f10a5e78d76a53e3e584f1e6a701b6d24108 ]

Implement a cleanup method to properly free ci->params

BUG: memory leak
unreferenced object 0xffff88811746e2c0 (size 64):
  comm "syz-executor617", pid 7106, jiffies 4294943055 (age 14.250s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
    c0 34 60 84 ff ff ff ff 00 00 00 00 00 00 00 00  .4`.............
  backtrace:
    [<0000000015aa236f>] kmemleak_alloc_recursive include/linux/kmemleak.h:43 [inline]
    [<0000000015aa236f>] slab_post_alloc_hook mm/slab.h:586 [inline]
    [<0000000015aa236f>] slab_alloc mm/slab.c:3320 [inline]
    [<0000000015aa236f>] kmem_cache_alloc_trace+0x145/0x2c0 mm/slab.c:3549
    [<000000002c946bd1>] kmalloc include/linux/slab.h:556 [inline]
    [<000000002c946bd1>] kzalloc include/linux/slab.h:670 [inline]
    [<000000002c946bd1>] tcf_ctinfo_init+0x21a/0x530 net/sched/act_ctinfo.c:236
    [<0000000086952cca>] tcf_action_init_1+0x400/0x5b0 net/sched/act_api.c:944
    [<000000005ab29bf8>] tcf_action_init+0x135/0x1c0 net/sched/act_api.c:1000
    [<00000000392f56f9>] tcf_action_add+0x9a/0x200 net/sched/act_api.c:1410
    [<0000000088f3c5dd>] tc_ctl_action+0x14d/0x1bb net/sched/act_api.c:1465
    [<000000006b39d986>] rtnetlink_rcv_msg+0x178/0x4b0 net/core/rtnetlink.c:5424
    [<00000000fd6ecace>] netlink_rcv_skb+0x61/0x170 net/netlink/af_netlink.c:2477
    [<0000000047493d02>] rtnetlink_rcv+0x1d/0x30 net/core/rtnetlink.c:5442
    [<00000000bdcf8286>] netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
    [<00000000bdcf8286>] netlink_unicast+0x223/0x310 net/netlink/af_netlink.c:1328
    [<00000000fc5b92d9>] netlink_sendmsg+0x2c0/0x570 net/netlink/af_netlink.c:1917
    [<00000000da84d076>] sock_sendmsg_nosec net/socket.c:639 [inline]
    [<00000000da84d076>] sock_sendmsg+0x54/0x70 net/socket.c:659
    [<0000000042fb2eee>] ____sys_sendmsg+0x2d0/0x300 net/socket.c:2330
    [<000000008f23f67e>] ___sys_sendmsg+0x8a/0xd0 net/socket.c:2384
    [<00000000d838e4f6>] __sys_sendmsg+0x80/0xf0 net/socket.c:2417
    [<00000000289a9cb1>] __do_sys_sendmsg net/socket.c:2426 [inline]
    [<00000000289a9cb1>] __se_sys_sendmsg net/socket.c:2424 [inline]
    [<00000000289a9cb1>] __x64_sys_sendmsg+0x23/0x30 net/socket.c:2424

Fixes: 24ec483cec98 ("net: sched: Introduce act_ctinfo action")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Kevin 'ldir' Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Kevin 'ldir' Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ctinfo.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c
index 0dbcfd1dca7b..f45995a6237a 100644
--- a/net/sched/act_ctinfo.c
+++ b/net/sched/act_ctinfo.c
@@ -360,6 +360,16 @@ static int tcf_ctinfo_search(struct net *net, struct tc_action **a, u32 index)
 	return tcf_idr_search(tn, a, index);
 }
 
+static void tcf_ctinfo_cleanup(struct tc_action *a)
+{
+	struct tcf_ctinfo *ci = to_ctinfo(a);
+	struct tcf_ctinfo_params *cp;
+
+	cp = rcu_dereference_protected(ci->params, 1);
+	if (cp)
+		kfree_rcu(cp, rcu);
+}
+
 static struct tc_action_ops act_ctinfo_ops = {
 	.kind	= "ctinfo",
 	.id	= TCA_ID_CTINFO,
@@ -367,6 +377,7 @@ static struct tc_action_ops act_ctinfo_ops = {
 	.act	= tcf_ctinfo_act,
 	.dump	= tcf_ctinfo_dump,
 	.init	= tcf_ctinfo_init,
+	.cleanup= tcf_ctinfo_cleanup,
 	.walk	= tcf_ctinfo_walker,
 	.lookup	= tcf_ctinfo_search,
 	.size	= sizeof(struct tcf_ctinfo),
-- 
2.21.1


From e345a20103d14d62cb44c1bb790a4809de057d7e Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 16 Jan 2020 12:55:48 -0800
Subject: [PATCH 22/26] net: dsa: bcm_sf2: Configure IMP port for 2Gb/sec

[ Upstream commit 8f1880cbe8d0d49ebb7e9ae409b3b96676e5aa97 ]

With the implementation of the system reset controller we lost a setting
that is currently applied by the bootloader and which configures the IMP
port for 2Gb/sec, the default is 1Gb/sec. This is needed given the
number of ports and applications we expect to run so bring back that
setting.

Fixes: 01b0ac07589e ("net: dsa: bcm_sf2: Add support for optional reset controller line")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 69fc13046ac7..47b21096b577 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -68,7 +68,7 @@ static void bcm_sf2_imp_setup(struct dsa_switch *ds, int port)
 
 		/* Force link status for IMP port */
 		reg = core_readl(priv, offset);
-		reg |= (MII_SW_OR | LINK_STS);
+		reg |= (MII_SW_OR | LINK_STS | GMII_SPEED_UP_2G);
 		core_writel(priv, reg, offset);
 
 		/* Enable Broadcast, Multicast, Unicast forwarding to IMP port */
-- 
2.21.1


From d61e795136ef62252a055840365943f711a0c773 Mon Sep 17 00:00:00 2001
From: Navid Emamdoost <navid.emamdoost@gmail.com>
Date: Tue, 10 Sep 2019 18:01:40 -0500
Subject: [PATCH 23/26] wimax: i2400: fix memory leak

[ Upstream commit 2507e6ab7a9a440773be476141a255934468c5ef ]

In i2400m_op_rfkill_sw_toggle cmd buffer should be released along with
skb response.

Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wimax/i2400m/op-rfkill.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wimax/i2400m/op-rfkill.c b/drivers/net/wimax/i2400m/op-rfkill.c
index 5c79f052cad2..edd51c061eaf 100644
--- a/drivers/net/wimax/i2400m/op-rfkill.c
+++ b/drivers/net/wimax/i2400m/op-rfkill.c
@@ -127,6 +127,7 @@ int i2400m_op_rfkill_sw_toggle(struct wimax_dev *wimax_dev,
 			"%d\n", result);
 	result = 0;
 error_cmd:
+	kfree(cmd);
 	kfree_skb(ack_skb);
 error_msg_to_dev:
 error_alloc:
-- 
2.21.1


From f5bda3bdf475ad283bec8d487c039665d9e333ea Mon Sep 17 00:00:00 2001
From: Navid Emamdoost <navid.emamdoost@gmail.com>
Date: Fri, 25 Oct 2019 23:53:30 -0500
Subject: [PATCH 24/26] wimax: i2400: Fix memory leak in
 i2400m_op_rfkill_sw_toggle

[ Upstream commit 6f3ef5c25cc762687a7341c18cbea5af54461407 ]

In the implementation of i2400m_op_rfkill_sw_toggle() the allocated
buffer for cmd should be released before returning. The
documentation for i2400m_msg_to_dev() says when it returns the buffer
can be reused. Meaning cmd should be released in either case. Move
kfree(cmd) before return to be reached by all execution paths.

Fixes: 2507e6ab7a9a ("wimax: i2400: fix memory leak")
Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wimax/i2400m/op-rfkill.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/wimax/i2400m/op-rfkill.c b/drivers/net/wimax/i2400m/op-rfkill.c
index edd51c061eaf..5c79f052cad2 100644
--- a/drivers/net/wimax/i2400m/op-rfkill.c
+++ b/drivers/net/wimax/i2400m/op-rfkill.c
@@ -127,7 +127,6 @@ int i2400m_op_rfkill_sw_toggle(struct wimax_dev *wimax_dev,
 			"%d\n", result);
 	result = 0;
 error_cmd:
-	kfree(cmd);
 	kfree_skb(ack_skb);
 error_msg_to_dev:
 error_alloc:
-- 
2.21.1


From c10bc31ce65ef3c0dbc6c161c6a92b70108d4a48 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 13 Jan 2020 18:23:58 +0100
Subject: [PATCH 25/26] NFC: pn533: fix bulk-message timeout

[ Upstream commit a112adafcb47760feff959ee1ecd10b74d2c5467 ]

The driver was doing a synchronous uninterruptible bulk-transfer without
using a timeout. This could lead to the driver hanging on probe due to a
malfunctioning (or malicious) device until the device is physically
disconnected. While sleeping in probe the driver prevents other devices
connected to the same hub from being added to (or removed from) the bus.

An arbitrary limit of five seconds should be more than enough.

Fixes: dbafc28955fa ("NFC: pn533: don't send USB data off of the stack")
Signed-off-by: Johan Hovold <johan@kernel.org>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/nfc/pn533/usb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nfc/pn533/usb.c b/drivers/nfc/pn533/usb.c
index e897e4d768ef..d7a355d05368 100644
--- a/drivers/nfc/pn533/usb.c
+++ b/drivers/nfc/pn533/usb.c
@@ -391,7 +391,7 @@ static int pn533_acr122_poweron_rdr(struct pn533_usb_phy *phy)
 		       cmd, sizeof(cmd), false);
 
 	rc = usb_bulk_msg(phy->udev, phy->out_urb->pipe, buffer, sizeof(cmd),
-			  &transferred, 0);
+			  &transferred, 5000);
 	kfree(buffer);
 	if (rc || (transferred != sizeof(cmd))) {
 		nfc_err(&phy->udev->dev,
-- 
2.21.1


From 8842a7e858107fe8a66b2c4a033d540b26ded798 Mon Sep 17 00:00:00 2001
From: Navid Emamdoost <navid.emamdoost@gmail.com>
Date: Wed, 25 Sep 2019 10:48:30 -0500
Subject: [PATCH 26/26] i40e: prevent memory leak in i40e_setup_macvlans

[ Upstream commit 27d461333459d282ffa4a2bdb6b215a59d493a8f ]

In i40e_setup_macvlans if i40e_setup_channel fails the allocated memory
for ch should be released.

Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 4960c9c3e773..a8dd0228b678 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -7168,6 +7168,7 @@ static int i40e_setup_macvlans(struct i40e_vsi *vsi, u16 macvlan_cnt, u16 qcnt,
 		ch->num_queue_pairs = qcnt;
 		if (!i40e_setup_channel(pf, vsi, ch)) {
 			ret = -EINVAL;
+			kfree(ch);
 			goto err_free;
 		}
 		ch->parent_vsi = vsi;
-- 
2.21.1

Re: [PATCHES] Networking

[Greg KH]

On Mon, Jan 20, 2020 at 08:44:20PM +0100, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.19 and v5.4
> -stable, respectively.
> 
> Thank you!

All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 106 bytes --]


Please queue up the following networking bug fixes for v4.19
and v5.4 -stable, respectively.

Thank you.

[-- Attachment #2: net_419.mbox --]
[-- Type: Application/Octet-Stream, Size: 49057 bytes --]

From 0db2ea7d4ccb01abf1d4427c55d1dfcaa7312421 Mon Sep 17 00:00:00 2001
From: Richard Palethorpe <rpalethorpe@suse.com>
Date: Tue, 21 Jan 2020 14:42:58 +0100
Subject: [PATCH 01/17] can, slip: Protect tty->disc_data in write_wakeup and
 close with RCU

[ Upstream commit 0ace17d56824165c7f4c68785d6b58971db954dd ]

write_wakeup can happen in parallel with close/hangup where tty->disc_data
is set to NULL and the netdevice is freed thus also freeing
disc_data. write_wakeup accesses disc_data so we must prevent close from
freeing the netdev while write_wakeup has a non-NULL view of
tty->disc_data.

We also need to make sure that accesses to disc_data are atomic. Which can
all be done with RCU.

This problem was found by Syzkaller on SLCAN, but the same issue is
reproducible with the SLIP line discipline using an LTP test based on the
Syzkaller reproducer.

A fix which didn't use RCU was posted by Hillf Danton.

Fixes: 661f7fda21b1 ("slip: Fix deadlock in write_wakeup")
Fixes: a8e83b17536a ("slcan: Port write_wakeup deadlock fix from slip")
Reported-by: syzbot+017e491ae13c0068598a@syzkaller.appspotmail.com
Signed-off-by: Richard Palethorpe <rpalethorpe@suse.com>
Cc: Wolfgang Grandegger <wg@grandegger.com>
Cc: Marc Kleine-Budde <mkl@pengutronix.de>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Tyler Hall <tylerwhall@gmail.com>
Cc: linux-can@vger.kernel.org
Cc: netdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: syzkaller@googlegroups.com
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/can/slcan.c | 12 ++++++++++--
 drivers/net/slip/slip.c | 12 ++++++++++--
 2 files changed, 20 insertions(+), 4 deletions(-)

diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c
index cf0769ad39cd..b2e5bcae7fbe 100644
--- a/drivers/net/can/slcan.c
+++ b/drivers/net/can/slcan.c
@@ -343,9 +343,16 @@ static void slcan_transmit(struct work_struct *work)
  */
 static void slcan_write_wakeup(struct tty_struct *tty)
 {
-	struct slcan *sl = tty->disc_data;
+	struct slcan *sl;
+
+	rcu_read_lock();
+	sl = rcu_dereference(tty->disc_data);
+	if (!sl)
+		goto out;
 
 	schedule_work(&sl->tx_work);
+out:
+	rcu_read_unlock();
 }
 
 /* Send a can_frame to a TTY queue. */
@@ -640,10 +647,11 @@ static void slcan_close(struct tty_struct *tty)
 		return;
 
 	spin_lock_bh(&sl->lock);
-	tty->disc_data = NULL;
+	rcu_assign_pointer(tty->disc_data, NULL);
 	sl->tty = NULL;
 	spin_unlock_bh(&sl->lock);
 
+	synchronize_rcu();
 	flush_work(&sl->tx_work);
 
 	/* Flush network side */
diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c
index 77207f936871..93f303ec17e2 100644
--- a/drivers/net/slip/slip.c
+++ b/drivers/net/slip/slip.c
@@ -452,9 +452,16 @@ static void slip_transmit(struct work_struct *work)
  */
 static void slip_write_wakeup(struct tty_struct *tty)
 {
-	struct slip *sl = tty->disc_data;
+	struct slip *sl;
+
+	rcu_read_lock();
+	sl = rcu_dereference(tty->disc_data);
+	if (!sl)
+		goto out;
 
 	schedule_work(&sl->tx_work);
+out:
+	rcu_read_unlock();
 }
 
 static void sl_tx_timeout(struct net_device *dev)
@@ -882,10 +889,11 @@ static void slip_close(struct tty_struct *tty)
 		return;
 
 	spin_lock_bh(&sl->lock);
-	tty->disc_data = NULL;
+	rcu_assign_pointer(tty->disc_data, NULL);
 	sl->tty = NULL;
 	spin_unlock_bh(&sl->lock);
 
+	synchronize_rcu();
 	flush_work(&sl->tx_work);
 
 	/* VSV = very important to remove timers */
-- 
2.21.1


From c7d76bdeea940c7d134e20deb5de7b31c87af164 Mon Sep 17 00:00:00 2001
From: Wenwen Wang <wenwen@cs.uga.edu>
Date: Sat, 25 Jan 2020 14:33:29 +0000
Subject: [PATCH 02/17] firestream: fix memory leaks

[ Upstream commit fa865ba183d61c1ec8cbcab8573159c3b72b89a4 ]

In fs_open(), 'vcc' is allocated through kmalloc() and assigned to
'atm_vcc->dev_data.' In the following execution, if an error occurs, e.g.,
there is no more free channel, an error code EBUSY or ENOMEM will be
returned. However, 'vcc' is not deallocated, leading to memory leaks. Note
that, in normal cases where fs_open() returns 0, 'vcc' will be deallocated
in fs_close(). But, if fs_open() fails, there is no guarantee that
fs_close() will be invoked.

To fix this issue, deallocate 'vcc' before the error code is returned.

Signed-off-by: Wenwen Wang <wenwen@cs.uga.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/atm/firestream.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/atm/firestream.c b/drivers/atm/firestream.c
index 4e46dc9e41ad..112b1001c269 100644
--- a/drivers/atm/firestream.c
+++ b/drivers/atm/firestream.c
@@ -927,6 +927,7 @@ static int fs_open(struct atm_vcc *atm_vcc)
 			}
 			if (!to) {
 				printk ("No more free channels for FS50..\n");
+				kfree(vcc);
 				return -EBUSY;
 			}
 			vcc->channo = dev->channo;
@@ -937,6 +938,7 @@ static int fs_open(struct atm_vcc *atm_vcc)
 			if (((DO_DIRECTION(rxtp) && dev->atm_vccs[vcc->channo])) ||
 			    ( DO_DIRECTION(txtp) && test_bit (vcc->channo, dev->tx_inuse))) {
 				printk ("Channel is in use for FS155.\n");
+				kfree(vcc);
 				return -EBUSY;
 			}
 		}
@@ -950,6 +952,7 @@ static int fs_open(struct atm_vcc *atm_vcc)
 			    tc, sizeof (struct fs_transmit_config));
 		if (!tc) {
 			fs_dprintk (FS_DEBUG_OPEN, "fs: can't alloc transmit_config.\n");
+			kfree(vcc);
 			return -ENOMEM;
 		}
 
-- 
2.21.1


From b905b6cfc8c95236a60a6bf5266dcc347b2046c9 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 21 Jan 2020 23:17:14 -0800
Subject: [PATCH 03/17] gtp: make sure only SOCK_DGRAM UDP sockets are accepted

[ Upstream commit 940ba14986657a50c15f694efca1beba31fa568f ]

A malicious user could use RAW sockets and fool
GTP using them as standard SOCK_DGRAM UDP sockets.

BUG: KMSAN: uninit-value in udp_tunnel_encap_enable include/net/udp_tunnel.h:174 [inline]
BUG: KMSAN: uninit-value in setup_udp_tunnel_sock+0x45e/0x6f0 net/ipv4/udp_tunnel.c:85
CPU: 0 PID: 11262 Comm: syz-executor613 Not tainted 5.5.0-rc5-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c9/0x220 lib/dump_stack.c:118
 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:118
 __msan_warning+0x58/0xa0 mm/kmsan/kmsan_instr.c:215
 udp_tunnel_encap_enable include/net/udp_tunnel.h:174 [inline]
 setup_udp_tunnel_sock+0x45e/0x6f0 net/ipv4/udp_tunnel.c:85
 gtp_encap_enable_socket+0x37f/0x5a0 drivers/net/gtp.c:827
 gtp_encap_enable drivers/net/gtp.c:844 [inline]
 gtp_newlink+0xfb/0x1e50 drivers/net/gtp.c:666
 __rtnl_newlink net/core/rtnetlink.c:3305 [inline]
 rtnl_newlink+0x2973/0x3920 net/core/rtnetlink.c:3363
 rtnetlink_rcv_msg+0x1153/0x1570 net/core/rtnetlink.c:5424
 netlink_rcv_skb+0x451/0x650 net/netlink/af_netlink.c:2477
 rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:5442
 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
 netlink_unicast+0xf9e/0x1100 net/netlink/af_netlink.c:1328
 netlink_sendmsg+0x1248/0x14d0 net/netlink/af_netlink.c:1917
 sock_sendmsg_nosec net/socket.c:639 [inline]
 sock_sendmsg net/socket.c:659 [inline]
 ____sys_sendmsg+0x12b6/0x1350 net/socket.c:2330
 ___sys_sendmsg net/socket.c:2384 [inline]
 __sys_sendmsg+0x451/0x5f0 net/socket.c:2417
 __do_sys_sendmsg net/socket.c:2426 [inline]
 __se_sys_sendmsg+0x97/0xb0 net/socket.c:2424
 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2424
 do_syscall_64+0xb8/0x160 arch/x86/entry/common.c:296
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x441359
Code: e8 ac e8 ff ff 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 eb 08 fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007fff1cd0ac28 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 0000000000441359
RDX: 0000000000000000 RSI: 0000000020000100 RDI: 0000000000000003
RBP: 00000000006cb018 R08: 00000000004002c8 R09: 00000000004002c8
R10: 00000000004002c8 R11: 0000000000000246 R12: 00000000004020d0
R13: 0000000000402160 R14: 0000000000000000 R15: 0000000000000000

Uninit was created at:
 kmsan_save_stack_with_flags+0x3c/0x90 mm/kmsan/kmsan.c:144
 kmsan_internal_alloc_meta_for_pages mm/kmsan/kmsan_shadow.c:307 [inline]
 kmsan_alloc_page+0x12a/0x310 mm/kmsan/kmsan_shadow.c:336
 __alloc_pages_nodemask+0x57f2/0x5f60 mm/page_alloc.c:4800
 alloc_pages_current+0x67d/0x990 mm/mempolicy.c:2207
 alloc_pages include/linux/gfp.h:534 [inline]
 alloc_slab_page+0x111/0x12f0 mm/slub.c:1511
 allocate_slab mm/slub.c:1656 [inline]
 new_slab+0x2bc/0x1130 mm/slub.c:1722
 new_slab_objects mm/slub.c:2473 [inline]
 ___slab_alloc+0x1533/0x1f30 mm/slub.c:2624
 __slab_alloc mm/slub.c:2664 [inline]
 slab_alloc_node mm/slub.c:2738 [inline]
 slab_alloc mm/slub.c:2783 [inline]
 kmem_cache_alloc+0xb23/0xd70 mm/slub.c:2788
 sk_prot_alloc+0xf2/0x620 net/core/sock.c:1597
 sk_alloc+0xf0/0xbe0 net/core/sock.c:1657
 inet_create+0x7c7/0x1370 net/ipv4/af_inet.c:321
 __sock_create+0x8eb/0xf00 net/socket.c:1420
 sock_create net/socket.c:1471 [inline]
 __sys_socket+0x1a1/0x600 net/socket.c:1513
 __do_sys_socket net/socket.c:1522 [inline]
 __se_sys_socket+0x8d/0xb0 net/socket.c:1520
 __x64_sys_socket+0x4a/0x70 net/socket.c:1520
 do_syscall_64+0xb8/0x160 arch/x86/entry/common.c:296
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 459aa660eb1d ("gtp: add initial driver for datapath of GPRS Tunneling Protocol (GTP-U)")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Pablo Neira <pablo@netfilter.org>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/gtp.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 6571cac6e786..ee086441dcbe 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -809,19 +809,21 @@ static struct sock *gtp_encap_enable_socket(int fd, int type,
 		return NULL;
 	}
 
-	if (sock->sk->sk_protocol != IPPROTO_UDP) {
+	sk = sock->sk;
+	if (sk->sk_protocol != IPPROTO_UDP ||
+	    sk->sk_type != SOCK_DGRAM ||
+	    (sk->sk_family != AF_INET && sk->sk_family != AF_INET6)) {
 		pr_debug("socket fd=%d not UDP\n", fd);
 		sk = ERR_PTR(-EINVAL);
 		goto out_sock;
 	}
 
-	lock_sock(sock->sk);
-	if (sock->sk->sk_user_data) {
+	lock_sock(sk);
+	if (sk->sk_user_data) {
 		sk = ERR_PTR(-EBUSY);
 		goto out_rel_sock;
 	}
 
-	sk = sock->sk;
 	sock_hold(sk);
 
 	tuncfg.sk_user_data = gtp;
-- 
2.21.1


From e6d11f1dde29748e62d65a7b7cb765ad9e4d6558 Mon Sep 17 00:00:00 2001
From: Yuki Taguchi <tagyounit@gmail.com>
Date: Mon, 20 Jan 2020 13:48:37 +0900
Subject: [PATCH 04/17] ipv6: sr: remove SKB_GSO_IPXIP6 on End.D* actions

[ Upstream commit 62ebaeaedee7591c257543d040677a60e35c7aec ]

After LRO/GRO is applied, SRv6 encapsulated packets have
SKB_GSO_IPXIP6 feature flag, and this flag must be removed right after
decapulation procedure.

Currently, SKB_GSO_IPXIP6 flag is not removed on End.D* actions, which
creates inconsistent packet state, that is, a normal TCP/IP packets
have the SKB_GSO_IPXIP6 flag. This behavior can cause unexpected
fallback to GSO on routing to netdevices that do not support
SKB_GSO_IPXIP6. For example, on inter-VRF forwarding, decapsulated
packets separated into small packets by GSO because VRF devices do not
support TSO for packets with SKB_GSO_IPXIP6 flag, and this degrades
forwarding performance.

This patch removes encapsulation related GSO flags from the skb right
after the End.D* action is applied.

Fixes: d7a669dd2f8b ("ipv6: sr: add helper functions for seg6local")
Signed-off-by: Yuki Taguchi <tagyounit@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/seg6_local.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c
index 60325dbfe88b..607709a8847c 100644
--- a/net/ipv6/seg6_local.c
+++ b/net/ipv6/seg6_local.c
@@ -28,6 +28,7 @@
 #include <net/addrconf.h>
 #include <net/ip6_route.h>
 #include <net/dst_cache.h>
+#include <net/ip_tunnels.h>
 #ifdef CONFIG_IPV6_SEG6_HMAC
 #include <net/seg6_hmac.h>
 #endif
@@ -135,7 +136,8 @@ static bool decap_and_validate(struct sk_buff *skb, int proto)
 
 	skb_reset_network_header(skb);
 	skb_reset_transport_header(skb);
-	skb->encapsulation = 0;
+	if (iptunnel_pull_offloads(skb))
+		return false;
 
 	return true;
 }
-- 
2.21.1


From 8ac59e8cea9dd2d5f1063163e6ec498c44460c85 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 23 Jan 2020 09:49:34 -0800
Subject: [PATCH 05/17] net: bcmgenet: Use netif_tx_napi_add() for TX NAPI

[ Upstream commit 148965df1a990af98b2c84092c2a2274c7489284 ]

Before commit 7587935cfa11 ("net: bcmgenet: move NAPI initialization to
ring initialization") moved the code, this used to be
netif_tx_napi_add(), but we lost that small semantic change in the
process, restore that.

Fixes: 7587935cfa11 ("net: bcmgenet: move NAPI initialization to ring initialization")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Acked-by: Doug Berger <opendmb@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index b7d75011cede..736a6a5fbd98 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -2166,8 +2166,8 @@ static void bcmgenet_init_tx_ring(struct bcmgenet_priv *priv,
 				  DMA_END_ADDR);
 
 	/* Initialize Tx NAPI */
-	netif_napi_add(priv->dev, &ring->napi, bcmgenet_tx_poll,
-		       NAPI_POLL_WEIGHT);
+	netif_tx_napi_add(priv->dev, &ring->napi, bcmgenet_tx_poll,
+			  NAPI_POLL_WEIGHT);
 }
 
 /* Initialize a RDMA ring */
-- 
2.21.1


From 78a6b07991a41e0d0b49bddd783ea93a42983cc9 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Fri, 24 Jan 2020 20:41:44 +1100
Subject: [PATCH 06/17] net: cxgb3_main: Add CAP_NET_ADMIN check to
 CHELSIO_GET_MEM

[ Upstream commit 3546d8f1bbe992488ed91592cf6bf76e7114791a =

The cxgb3 driver for "Chelsio T3-based gigabit and 10Gb Ethernet
adapters" implements a custom ioctl as SIOCCHIOCTL/SIOCDEVPRIVATE in
cxgb_extension_ioctl().

One of the subcommands of the ioctl is CHELSIO_GET_MEM, which appears
to read memory directly out of the adapter and return it to userspace.
It's not entirely clear what the contents of the adapter memory
contains, but the assumption is that it shouldn't be accessible to all
users.

So add a CAP_NET_ADMIN check to the CHELSIO_GET_MEM case. Put it after
the is_offload() check, which matches two of the other subcommands in
the same function which also check for is_offload() and CAP_NET_ADMIN.

Found by Ilja by code inspection, not tested as I don't have the
required hardware.

Reported-by: Ilja Van Sprundel <ivansprundel@ioactive.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
index 6be6de0774b6..c82469ab7aba 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
@@ -2449,6 +2449,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr)
 
 		if (!is_offload(adapter))
 			return -EOPNOTSUPP;
+		if (!capable(CAP_NET_ADMIN))
+			return -EPERM;
 		if (!(adapter->flags & FULL_INIT_DONE))
 			return -EIO;	/* need the memory controllers */
 		if (copy_from_user(&t, useraddr, sizeof(t)))
-- 
2.21.1


From 0464f6bf67a52f312e9244e5d38763b6875ea637 Mon Sep 17 00:00:00 2001
From: Niko Kortstrom <niko.kortstrom@nokia.com>
Date: Thu, 16 Jan 2020 11:43:27 +0200
Subject: [PATCH 07/17] net: ip6_gre: fix moving ip6gre between namespaces

[ Upstream commit 690afc165bb314354667f67157c1a1aea7dc797a ]

Support for moving IPv4 GRE tunnels between namespaces was added in
commit b57708add314 ("gre: add x-netns support"). The respective change
for IPv6 tunnels, commit 22f08069e8b4 ("ip6gre: add x-netns support")
did not drop NETIF_F_NETNS_LOCAL flag so moving them from one netns to
another is still denied in IPv6 case. Drop NETIF_F_NETNS_LOCAL flag from
ip6gre tunnels to allow moving ip6gre tunnel endpoints between network
namespaces.

Signed-off-by: Niko Kortstrom <niko.kortstrom@nokia.com>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Acked-by: William Tu <u9012063@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index b3515a4f1303..fbc478b6daf1 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1486,7 +1486,6 @@ static int ip6gre_tunnel_init_common(struct net_device *dev)
 		dev->mtu -= 8;
 
 	if (tunnel->parms.collect_md) {
-		dev->features |= NETIF_F_NETNS_LOCAL;
 		netif_keep_dst(dev);
 	}
 	ip6gre_tnl_init_features(dev);
@@ -1914,7 +1913,6 @@ static void ip6gre_tap_setup(struct net_device *dev)
 	dev->needs_free_netdev = true;
 	dev->priv_destructor = ip6gre_dev_free;
 
-	dev->features |= NETIF_F_NETNS_LOCAL;
 	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 	netif_keep_dst(dev);
@@ -2222,7 +2220,6 @@ static void ip6erspan_tap_setup(struct net_device *dev)
 	dev->needs_free_netdev = true;
 	dev->priv_destructor = ip6gre_dev_free;
 
-	dev->features |= NETIF_F_NETNS_LOCAL;
 	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 	netif_keep_dst(dev);
-- 
2.21.1


From c7ec105456ae1f7371e4d7e865045265da30f1a8 Mon Sep 17 00:00:00 2001
From: William Dauchy <w.dauchy@criteo.com>
Date: Tue, 21 Jan 2020 21:49:54 +0100
Subject: [PATCH 08/17] net, ip6_tunnel: fix namespaces move

[ Upstream commit 5311a69aaca30fa849c3cc46fb25f75727fb72d0 ]

in the same manner as commit d0f418516022 ("net, ip_tunnel: fix
namespaces move"), fix namespace moving as it was broken since commit
8d79266bc48c ("ip6_tunnel: add collect_md mode to IPv6 tunnel"), but for
ipv6 this time; there is no reason to keep it for ip6_tunnel.

Fixes: 8d79266bc48c ("ip6_tunnel: add collect_md mode to IPv6 tunnel")
Signed-off-by: William Dauchy <w.dauchy@criteo.com>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index e3b4237b2832..8e70a015c792 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1882,10 +1882,8 @@ static int ip6_tnl_dev_init(struct net_device *dev)
 	if (err)
 		return err;
 	ip6_tnl_link_config(t);
-	if (t->parms.collect_md) {
-		dev->features |= NETIF_F_NETNS_LOCAL;
+	if (t->parms.collect_md)
 		netif_keep_dst(dev);
-	}
 	return 0;
 }
 
-- 
2.21.1


From 9514fd40366b228854aaf27d6570a5e7d97a555f Mon Sep 17 00:00:00 2001
From: William Dauchy <w.dauchy@criteo.com>
Date: Tue, 21 Jan 2020 15:26:24 +0100
Subject: [PATCH 09/17] net, ip_tunnel: fix namespaces move

[ Upstream commit d0f418516022c32ecceaf4275423e5bd3f8743a9 ]

in the same manner as commit 690afc165bb3 ("net: ip6_gre: fix moving
ip6gre between namespaces"), fix namespace moving as it was broken since
commit 2e15ea390e6f ("ip_gre: Add support to collect tunnel metadata.").
Indeed, the ip6_gre commit removed the local flag for collect_md
condition, so there is no reason to keep it for ip_gre/ip_tunnel.

this patch will fix both ip_tunnel and ip_gre modules.

Fixes: 2e15ea390e6f ("ip_gre: Add support to collect tunnel metadata.")
Signed-off-by: William Dauchy <w.dauchy@criteo.com>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_tunnel.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 420e891ac59d..3e0349307e48 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -1202,10 +1202,8 @@ int ip_tunnel_init(struct net_device *dev)
 	iph->version		= 4;
 	iph->ihl		= 5;
 
-	if (tunnel->collect_md) {
-		dev->features |= NETIF_F_NETNS_LOCAL;
+	if (tunnel->collect_md)
 		netif_keep_dst(dev);
-	}
 	return 0;
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_init);
-- 
2.21.1


From 91c3e2c8a3f6a11495da0831adbcf73374943398 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 21 Jan 2020 22:47:29 -0800
Subject: [PATCH 10/17] net: rtnetlink: validate IFLA_MTU attribute in
 rtnl_create_link()

[ Upstream commit d836f5c69d87473ff65c06a6123e5b2cf5e56f5b ]

rtnl_create_link() needs to apply dev->min_mtu and dev->max_mtu
checks that we apply in do_setlink()

Otherwise malicious users can crash the kernel, for example after
an integer overflow :

BUG: KASAN: use-after-free in memset include/linux/string.h:365 [inline]
BUG: KASAN: use-after-free in __alloc_skb+0x37b/0x5e0 net/core/skbuff.c:238
Write of size 32 at addr ffff88819f20b9c0 by task swapper/0/0

CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.5.0-rc1-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x197/0x210 lib/dump_stack.c:118
 print_address_description.constprop.0.cold+0xd4/0x30b mm/kasan/report.c:374
 __kasan_report.cold+0x1b/0x41 mm/kasan/report.c:506
 kasan_report+0x12/0x20 mm/kasan/common.c:639
 check_memory_region_inline mm/kasan/generic.c:185 [inline]
 check_memory_region+0x134/0x1a0 mm/kasan/generic.c:192
 memset+0x24/0x40 mm/kasan/common.c:108
 memset include/linux/string.h:365 [inline]
 __alloc_skb+0x37b/0x5e0 net/core/skbuff.c:238
 alloc_skb include/linux/skbuff.h:1049 [inline]
 alloc_skb_with_frags+0x93/0x590 net/core/skbuff.c:5664
 sock_alloc_send_pskb+0x7ad/0x920 net/core/sock.c:2242
 sock_alloc_send_skb+0x32/0x40 net/core/sock.c:2259
 mld_newpack+0x1d7/0x7f0 net/ipv6/mcast.c:1609
 add_grhead.isra.0+0x299/0x370 net/ipv6/mcast.c:1713
 add_grec+0x7db/0x10b0 net/ipv6/mcast.c:1844
 mld_send_cr net/ipv6/mcast.c:1970 [inline]
 mld_ifc_timer_expire+0x3d3/0x950 net/ipv6/mcast.c:2477
 call_timer_fn+0x1ac/0x780 kernel/time/timer.c:1404
 expire_timers kernel/time/timer.c:1449 [inline]
 __run_timers kernel/time/timer.c:1773 [inline]
 __run_timers kernel/time/timer.c:1740 [inline]
 run_timer_softirq+0x6c3/0x1790 kernel/time/timer.c:1786
 __do_softirq+0x262/0x98c kernel/softirq.c:292
 invoke_softirq kernel/softirq.c:373 [inline]
 irq_exit+0x19b/0x1e0 kernel/softirq.c:413
 exiting_irq arch/x86/include/asm/apic.h:536 [inline]
 smp_apic_timer_interrupt+0x1a3/0x610 arch/x86/kernel/apic/apic.c:1137
 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:829
 </IRQ>
RIP: 0010:native_safe_halt+0xe/0x10 arch/x86/include/asm/irqflags.h:61
Code: 98 6b ea f9 eb 8a cc cc cc cc cc cc e9 07 00 00 00 0f 00 2d 44 1c 60 00 f4 c3 66 90 e9 07 00 00 00 0f 00 2d 34 1c 60 00 fb f4 <c3> cc 55 48 89 e5 41 57 41 56 41 55 41 54 53 e8 4e 5d 9a f9 e8 79
RSP: 0018:ffffffff89807ce8 EFLAGS: 00000286 ORIG_RAX: ffffffffffffff13
RAX: 1ffffffff13266ae RBX: ffffffff8987a1c0 RCX: 0000000000000000
RDX: dffffc0000000000 RSI: 0000000000000006 RDI: ffffffff8987aa54
RBP: ffffffff89807d18 R08: ffffffff8987a1c0 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: dffffc0000000000
R13: ffffffff8a799980 R14: 0000000000000000 R15: 0000000000000000
 arch_cpu_idle+0xa/0x10 arch/x86/kernel/process.c:690
 default_idle_call+0x84/0xb0 kernel/sched/idle.c:94
 cpuidle_idle_call kernel/sched/idle.c:154 [inline]
 do_idle+0x3c8/0x6e0 kernel/sched/idle.c:269
 cpu_startup_entry+0x1b/0x20 kernel/sched/idle.c:361
 rest_init+0x23b/0x371 init/main.c:451
 arch_call_rest_init+0xe/0x1b
 start_kernel+0x904/0x943 init/main.c:784
 x86_64_start_reservations+0x29/0x2b arch/x86/kernel/head64.c:490
 x86_64_start_kernel+0x77/0x7b arch/x86/kernel/head64.c:471
 secondary_startup_64+0xa4/0xb0 arch/x86/kernel/head_64.S:242

The buggy address belongs to the page:
page:ffffea00067c82c0 refcount:0 mapcount:0 mapping:0000000000000000 index:0x0
raw: 057ffe0000000000 ffffea00067c82c8 ffffea00067c82c8 0000000000000000
raw: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff88819f20b880: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
 ffff88819f20b900: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
>ffff88819f20b980: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
                                           ^
 ffff88819f20ba00: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
 ffff88819f20ba80: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff

Fixes: 61e84623ace3 ("net: centralize net_device min/max MTU checking")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  2 ++
 net/core/dev.c            | 29 +++++++++++++++++++----------
 net/core/rtnetlink.c      | 13 +++++++++++--
 3 files changed, 32 insertions(+), 12 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d5527e3828d1..84bbdcbb199a 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3579,6 +3579,8 @@ int dev_set_alias(struct net_device *, const char *, size_t);
 int dev_get_alias(const struct net_device *, char *, size_t);
 int dev_change_net_namespace(struct net_device *, struct net *, const char *);
 int __dev_set_mtu(struct net_device *, int);
+int dev_validate_mtu(struct net_device *dev, int mtu,
+		     struct netlink_ext_ack *extack);
 int dev_set_mtu_ext(struct net_device *dev, int mtu,
 		    struct netlink_ext_ack *extack);
 int dev_set_mtu(struct net_device *, int);
diff --git a/net/core/dev.c b/net/core/dev.c
index a26d87073f71..3a28504fbe3b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7781,6 +7781,22 @@ int __dev_set_mtu(struct net_device *dev, int new_mtu)
 }
 EXPORT_SYMBOL(__dev_set_mtu);
 
+int dev_validate_mtu(struct net_device *dev, int new_mtu,
+		     struct netlink_ext_ack *extack)
+{
+	/* MTU must be positive, and in range */
+	if (new_mtu < 0 || new_mtu < dev->min_mtu) {
+		NL_SET_ERR_MSG(extack, "mtu less than device minimum");
+		return -EINVAL;
+	}
+
+	if (dev->max_mtu > 0 && new_mtu > dev->max_mtu) {
+		NL_SET_ERR_MSG(extack, "mtu greater than device maximum");
+		return -EINVAL;
+	}
+	return 0;
+}
+
 /**
  *	dev_set_mtu_ext - Change maximum transfer unit
  *	@dev: device
@@ -7797,16 +7813,9 @@ int dev_set_mtu_ext(struct net_device *dev, int new_mtu,
 	if (new_mtu == dev->mtu)
 		return 0;
 
-	/* MTU must be positive, and in range */
-	if (new_mtu < 0 || new_mtu < dev->min_mtu) {
-		NL_SET_ERR_MSG(extack, "mtu less than device minimum");
-		return -EINVAL;
-	}
-
-	if (dev->max_mtu > 0 && new_mtu > dev->max_mtu) {
-		NL_SET_ERR_MSG(extack, "mtu greater than device maximum");
-		return -EINVAL;
-	}
+	err = dev_validate_mtu(dev, new_mtu, extack);
+	if (err)
+		return err;
 
 	if (!netif_device_present(dev))
 		return -ENODEV;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index dbb3c0c7c132..f51973f458e4 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2875,8 +2875,17 @@ struct net_device *rtnl_create_link(struct net *net,
 	dev->rtnl_link_ops = ops;
 	dev->rtnl_link_state = RTNL_LINK_INITIALIZING;
 
-	if (tb[IFLA_MTU])
-		dev->mtu = nla_get_u32(tb[IFLA_MTU]);
+	if (tb[IFLA_MTU]) {
+		u32 mtu = nla_get_u32(tb[IFLA_MTU]);
+		int err;
+
+		err = dev_validate_mtu(dev, mtu, NULL);
+		if (err) {
+			free_netdev(dev);
+			return ERR_PTR(err);
+		}
+		dev->mtu = mtu;
+	}
 	if (tb[IFLA_ADDRESS]) {
 		memcpy(dev->dev_addr, nla_data(tb[IFLA_ADDRESS]),
 				nla_len(tb[IFLA_ADDRESS]));
-- 
2.21.1


From f50e239eaa32be415ac1e3e3127e49c8f0f8dfe0 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Wed, 22 Jan 2020 15:42:02 -0800
Subject: [PATCH 11/17] net_sched: fix datalen for ematch

[ Upstream commit 61678d28d4a45ef376f5d02a839cc37509ae9281 ]

syzbot reported an out-of-bound access in em_nbyte. As initially
analyzed by Eric, this is because em_nbyte sets its own em->datalen
in em_nbyte_change() other than the one specified by user, but this
value gets overwritten later by its caller tcf_em_validate().
We should leave em->datalen untouched to respect their choices.

I audit all the in-tree ematch users, all of those implement
->change() set em->datalen, so we can just avoid setting it twice
in this case.

Reported-and-tested-by: syzbot+5af9a90dad568aa9f611@syzkaller.appspotmail.com
Reported-by: syzbot+2f07903a5b05e7f36410@syzkaller.appspotmail.com
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/ematch.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/ematch.c b/net/sched/ematch.c
index 1331a4c2d8ff..750d88d0cfd9 100644
--- a/net/sched/ematch.c
+++ b/net/sched/ematch.c
@@ -267,12 +267,12 @@ static int tcf_em_validate(struct tcf_proto *tp,
 				}
 				em->data = (unsigned long) v;
 			}
+			em->datalen = data_len;
 		}
 	}
 
 	em->matchid = em_hdr->matchid;
 	em->flags = em_hdr->flags;
-	em->datalen = data_len;
 	em->net = net;
 
 	err = 0;
-- 
2.21.1


From 8304dffb3519371c496e4acb9a6c82160e9e2af3 Mon Sep 17 00:00:00 2001
From: Jouni Hogander <jouni.hogander@unikie.com>
Date: Mon, 20 Jan 2020 09:51:03 +0200
Subject: [PATCH 12/17] net-sysfs: Fix reference count leak

[ Upstream commit cb626bf566eb4433318d35681286c494f04fedcc ]

Netdev_register_kobject is calling device_initialize. In case of error
reference taken by device_initialize is not given up.

Drivers are supposed to call free_netdev in case of error. In non-error
case the last reference is given up there and device release sequence
is triggered. In error case this reference is kept and the release
sequence is never started.

Fix this by setting reg_state as NETREG_UNREGISTERED if registering
fails.

This is the rootcause for couple of memory leaks reported by Syzkaller:

BUG: memory leak unreferenced object 0xffff8880675ca008 (size 256):
  comm "netdev_register", pid 281, jiffies 4294696663 (age 6.808s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
  backtrace:
    [<0000000058ca4711>] kmem_cache_alloc_trace+0x167/0x280
    [<000000002340019b>] device_add+0x882/0x1750
    [<000000001d588c3a>] netdev_register_kobject+0x128/0x380
    [<0000000011ef5535>] register_netdevice+0xa1b/0xf00
    [<000000007fcf1c99>] __tun_chr_ioctl+0x20d5/0x3dd0
    [<000000006a5b7b2b>] tun_chr_ioctl+0x2f/0x40
    [<00000000f30f834a>] do_vfs_ioctl+0x1c7/0x1510
    [<00000000fba062ea>] ksys_ioctl+0x99/0xb0
    [<00000000b1c1b8d2>] __x64_sys_ioctl+0x78/0xb0
    [<00000000984cabb9>] do_syscall_64+0x16f/0x580
    [<000000000bde033d>] entry_SYSCALL_64_after_hwframe+0x44/0xa9
    [<00000000e6ca2d9f>] 0xffffffffffffffff

BUG: memory leak
unreferenced object 0xffff8880668ba588 (size 8):
  comm "kobject_set_nam", pid 286, jiffies 4294725297 (age 9.871s)
  hex dump (first 8 bytes):
    6e 72 30 00 cc be df 2b                          nr0....+
  backtrace:
    [<00000000a322332a>] __kmalloc_track_caller+0x16e/0x290
    [<00000000236fd26b>] kstrdup+0x3e/0x70
    [<00000000dd4a2815>] kstrdup_const+0x3e/0x50
    [<0000000049a377fc>] kvasprintf_const+0x10e/0x160
    [<00000000627fc711>] kobject_set_name_vargs+0x5b/0x140
    [<0000000019eeab06>] dev_set_name+0xc0/0xf0
    [<0000000069cb12bc>] netdev_register_kobject+0xc8/0x320
    [<00000000f2e83732>] register_netdevice+0xa1b/0xf00
    [<000000009e1f57cc>] __tun_chr_ioctl+0x20d5/0x3dd0
    [<000000009c560784>] tun_chr_ioctl+0x2f/0x40
    [<000000000d759e02>] do_vfs_ioctl+0x1c7/0x1510
    [<00000000351d7c31>] ksys_ioctl+0x99/0xb0
    [<000000008390040a>] __x64_sys_ioctl+0x78/0xb0
    [<0000000052d196b7>] do_syscall_64+0x16f/0x580
    [<0000000019af9236>] entry_SYSCALL_64_after_hwframe+0x44/0xa9
    [<00000000bc384531>] 0xffffffffffffffff

v3 -> v4:
  Set reg_state to NETREG_UNREGISTERED if registering fails

v2 -> v3:
* Replaced BUG_ON with WARN_ON in free_netdev and netdev_release

v1 -> v2:
* Relying on driver calling free_netdev rather than calling
  put_device directly in error path

Reported-by: syzbot+ad8ca40ecd77896d51e2@syzkaller.appspotmail.com
Cc: David Miller <davem@davemloft.net>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Signed-off-by: Jouni Hogander <jouni.hogander@unikie.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 3a28504fbe3b..1a48bdfc3810 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8734,8 +8734,10 @@ int register_netdevice(struct net_device *dev)
 		goto err_uninit;
 
 	ret = netdev_register_kobject(dev);
-	if (ret)
+	if (ret) {
+		dev->reg_state = NETREG_UNREGISTERED;
 		goto err_uninit;
+	}
 	dev->reg_state = NETREG_REGISTERED;
 
 	__netdev_update_features(dev);
-- 
2.21.1


From f299883b25c1513a688ecd8d4ede2922d9a08fad Mon Sep 17 00:00:00 2001
From: James Hughes <james.hughes@raspberrypi.org>
Date: Mon, 20 Jan 2020 11:12:40 +0000
Subject: [PATCH 13/17] net: usb: lan78xx: Add .ndo_features_check

[ Upstream commit ce896476c65d72b4b99fa09c2f33436b4198f034 ]

As reported by Eric Dumazet, there are still some outstanding
cases where the driver does not handle TSO correctly when skb's
are over a certain size. Most cases have been fixed, this patch
should ensure that forwarded SKB's that are greater than
MAX_SINGLE_PACKET_SIZE - TX_OVERHEAD are software segmented
and handled correctly.

Signed-off-by: James Hughes <james.hughes@raspberrypi.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/lan78xx.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 7d708aeb4576..92548887df2f 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -31,6 +31,7 @@
 #include <linux/mdio.h>
 #include <linux/phy.h>
 #include <net/ip6_checksum.h>
+#include <net/vxlan.h>
 #include <linux/interrupt.h>
 #include <linux/irqdomain.h>
 #include <linux/irq.h>
@@ -3686,6 +3687,19 @@ static void lan78xx_tx_timeout(struct net_device *net)
 	tasklet_schedule(&dev->bh);
 }
 
+static netdev_features_t lan78xx_features_check(struct sk_buff *skb,
+						struct net_device *netdev,
+						netdev_features_t features)
+{
+	if (skb->len + TX_OVERHEAD > MAX_SINGLE_PACKET_SIZE)
+		features &= ~NETIF_F_GSO_MASK;
+
+	features = vlan_features_check(skb, features);
+	features = vxlan_features_check(skb, features);
+
+	return features;
+}
+
 static const struct net_device_ops lan78xx_netdev_ops = {
 	.ndo_open		= lan78xx_open,
 	.ndo_stop		= lan78xx_stop,
@@ -3699,6 +3713,7 @@ static const struct net_device_ops lan78xx_netdev_ops = {
 	.ndo_set_features	= lan78xx_set_features,
 	.ndo_vlan_rx_add_vid	= lan78xx_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= lan78xx_vlan_rx_kill_vid,
+	.ndo_features_check	= lan78xx_features_check,
 };
 
 static void lan78xx_stat_monitor(struct timer_list *t)
-- 
2.21.1


From 6d529010e0474f05dbbd310d983ccbfcb98fa3f6 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 21 Jan 2020 16:50:49 +0100
Subject: [PATCH 14/17] Revert "udp: do rmem bulk free even if the rx sk queue
 is empty"

[ Upstream commit d39ca2590d10712f412add7a88e1dd467a7246f4 ]

This reverts commit 0d4a6608f68c7532dcbfec2ea1150c9761767d03.

Willem reported that after commit 0d4a6608f68c ("udp: do rmem bulk
free even if the rx sk queue is empty") the memory allocated by
an almost idle system with many UDP sockets can grow a lot.

For stable kernel keep the solution as simple as possible and revert
the offending commit.

Reported-by: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
Diagnosed-by: Eric Dumazet <eric.dumazet@gmail.com>
Fixes: 0d4a6608f68c ("udp: do rmem bulk free even if the rx sk queue is empty")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 2eeae0455b14..0ef04cda1b27 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1305,7 +1305,8 @@ static void udp_rmem_release(struct sock *sk, int size, int partial,
 	if (likely(partial)) {
 		up->forward_deficit += size;
 		size = up->forward_deficit;
-		if (size < (sk->sk_rcvbuf >> 2))
+		if (size < (sk->sk_rcvbuf >> 2) &&
+		    !skb_queue_empty(&up->reader_queue))
 			return;
 	} else {
 		size += up->forward_deficit;
-- 
2.21.1


From 95d400308916d09aa691389546796b95513a84e7 Mon Sep 17 00:00:00 2001
From: Wen Yang <wenyang@linux.alibaba.com>
Date: Mon, 20 Jan 2020 18:04:56 +0800
Subject: [PATCH 15/17] tcp_bbr: improve arithmetic division in bbr_update_bw()

[ Upstream commit 5b2f1f3070b6447b76174ea8bfb7390dc6253ebd ]

do_div() does a 64-by-32 division. Use div64_long() instead of it
if the divisor is long, to avoid truncation to 32-bit.
And as a nice side effect also cleans up the function a bit.

Signed-off-by: Wen Yang <wenyang@linux.alibaba.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
Cc: netdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_bbr.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 02ff2dde9609..b371e66502c3 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -680,8 +680,7 @@ static void bbr_update_bw(struct sock *sk, const struct rate_sample *rs)
 	 * bandwidth sample. Delivered is in packets and interval_us in uS and
 	 * ratio will be <<1 for most connections. So delivered is first scaled.
 	 */
-	bw = (u64)rs->delivered * BW_UNIT;
-	do_div(bw, rs->interval_us);
+	bw = div64_long((u64)rs->delivered * BW_UNIT, rs->interval_us);
 
 	/* If this sample is application-limited, it is likely to have a very
 	 * low delivered count that represents application behavior rather than
-- 
2.21.1


From cf22bebffd48afee62dd390a6e294d32db42b3b2 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 22 Jan 2020 21:03:00 -0800
Subject: [PATCH 16/17] tcp: do not leave dangling pointers in tp->highest_sack

[ Upstream commit 2bec445f9bf35e52e395b971df48d3e1e5dc704a ]

Latest commit 853697504de0 ("tcp: Fix highest_sack and highest_sack_seq")
apparently allowed syzbot to trigger various crashes in TCP stack [1]

I believe this commit only made things easier for syzbot to find
its way into triggering use-after-frees. But really the bugs
could lead to bad TCP behavior or even plain crashes even for
non malicious peers.

I have audited all calls to tcp_rtx_queue_unlink() and
tcp_rtx_queue_unlink_and_free() and made sure tp->highest_sack would be updated
if we are removing from rtx queue the skb that tp->highest_sack points to.

These updates were missing in three locations :

1) tcp_clean_rtx_queue() [This one seems quite serious,
                          I have no idea why this was not caught earlier]

2) tcp_rtx_queue_purge() [Probably not a big deal for normal operations]

3) tcp_send_synack()     [Probably not a big deal for normal operations]

[1]
BUG: KASAN: use-after-free in tcp_highest_sack_seq include/net/tcp.h:1864 [inline]
BUG: KASAN: use-after-free in tcp_highest_sack_seq include/net/tcp.h:1856 [inline]
BUG: KASAN: use-after-free in tcp_check_sack_reordering+0x33c/0x3a0 net/ipv4/tcp_input.c:891
Read of size 4 at addr ffff8880a488d068 by task ksoftirqd/1/16

CPU: 1 PID: 16 Comm: ksoftirqd/1 Not tainted 5.5.0-rc5-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x197/0x210 lib/dump_stack.c:118
 print_address_description.constprop.0.cold+0xd4/0x30b mm/kasan/report.c:374
 __kasan_report.cold+0x1b/0x41 mm/kasan/report.c:506
 kasan_report+0x12/0x20 mm/kasan/common.c:639
 __asan_report_load4_noabort+0x14/0x20 mm/kasan/generic_report.c:134
 tcp_highest_sack_seq include/net/tcp.h:1864 [inline]
 tcp_highest_sack_seq include/net/tcp.h:1856 [inline]
 tcp_check_sack_reordering+0x33c/0x3a0 net/ipv4/tcp_input.c:891
 tcp_try_undo_partial net/ipv4/tcp_input.c:2730 [inline]
 tcp_fastretrans_alert+0xf74/0x23f0 net/ipv4/tcp_input.c:2847
 tcp_ack+0x2577/0x5bf0 net/ipv4/tcp_input.c:3710
 tcp_rcv_established+0x6dd/0x1e90 net/ipv4/tcp_input.c:5706
 tcp_v4_do_rcv+0x619/0x8d0 net/ipv4/tcp_ipv4.c:1619
 tcp_v4_rcv+0x307f/0x3b40 net/ipv4/tcp_ipv4.c:2001
 ip_protocol_deliver_rcu+0x5a/0x880 net/ipv4/ip_input.c:204
 ip_local_deliver_finish+0x23b/0x380 net/ipv4/ip_input.c:231
 NF_HOOK include/linux/netfilter.h:307 [inline]
 NF_HOOK include/linux/netfilter.h:301 [inline]
 ip_local_deliver+0x1e9/0x520 net/ipv4/ip_input.c:252
 dst_input include/net/dst.h:442 [inline]
 ip_rcv_finish+0x1db/0x2f0 net/ipv4/ip_input.c:428
 NF_HOOK include/linux/netfilter.h:307 [inline]
 NF_HOOK include/linux/netfilter.h:301 [inline]
 ip_rcv+0xe8/0x3f0 net/ipv4/ip_input.c:538
 __netif_receive_skb_one_core+0x113/0x1a0 net/core/dev.c:5148
 __netif_receive_skb+0x2c/0x1d0 net/core/dev.c:5262
 process_backlog+0x206/0x750 net/core/dev.c:6093
 napi_poll net/core/dev.c:6530 [inline]
 net_rx_action+0x508/0x1120 net/core/dev.c:6598
 __do_softirq+0x262/0x98c kernel/softirq.c:292
 run_ksoftirqd kernel/softirq.c:603 [inline]
 run_ksoftirqd+0x8e/0x110 kernel/softirq.c:595
 smpboot_thread_fn+0x6a3/0xa40 kernel/smpboot.c:165
 kthread+0x361/0x430 kernel/kthread.c:255
 ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:352

Allocated by task 10091:
 save_stack+0x23/0x90 mm/kasan/common.c:72
 set_track mm/kasan/common.c:80 [inline]
 __kasan_kmalloc mm/kasan/common.c:513 [inline]
 __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:486
 kasan_slab_alloc+0xf/0x20 mm/kasan/common.c:521
 slab_post_alloc_hook mm/slab.h:584 [inline]
 slab_alloc_node mm/slab.c:3263 [inline]
 kmem_cache_alloc_node+0x138/0x740 mm/slab.c:3575
 __alloc_skb+0xd5/0x5e0 net/core/skbuff.c:198
 alloc_skb_fclone include/linux/skbuff.h:1099 [inline]
 sk_stream_alloc_skb net/ipv4/tcp.c:875 [inline]
 sk_stream_alloc_skb+0x113/0xc90 net/ipv4/tcp.c:852
 tcp_sendmsg_locked+0xcf9/0x3470 net/ipv4/tcp.c:1282
 tcp_sendmsg+0x30/0x50 net/ipv4/tcp.c:1432
 inet_sendmsg+0x9e/0xe0 net/ipv4/af_inet.c:807
 sock_sendmsg_nosec net/socket.c:652 [inline]
 sock_sendmsg+0xd7/0x130 net/socket.c:672
 __sys_sendto+0x262/0x380 net/socket.c:1998
 __do_sys_sendto net/socket.c:2010 [inline]
 __se_sys_sendto net/socket.c:2006 [inline]
 __x64_sys_sendto+0xe1/0x1a0 net/socket.c:2006
 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Freed by task 10095:
 save_stack+0x23/0x90 mm/kasan/common.c:72
 set_track mm/kasan/common.c:80 [inline]
 kasan_set_free_info mm/kasan/common.c:335 [inline]
 __kasan_slab_free+0x102/0x150 mm/kasan/common.c:474
 kasan_slab_free+0xe/0x10 mm/kasan/common.c:483
 __cache_free mm/slab.c:3426 [inline]
 kmem_cache_free+0x86/0x320 mm/slab.c:3694
 kfree_skbmem+0x178/0x1c0 net/core/skbuff.c:645
 __kfree_skb+0x1e/0x30 net/core/skbuff.c:681
 sk_eat_skb include/net/sock.h:2453 [inline]
 tcp_recvmsg+0x1252/0x2930 net/ipv4/tcp.c:2166
 inet_recvmsg+0x136/0x610 net/ipv4/af_inet.c:838
 sock_recvmsg_nosec net/socket.c:886 [inline]
 sock_recvmsg net/socket.c:904 [inline]
 sock_recvmsg+0xce/0x110 net/socket.c:900
 __sys_recvfrom+0x1ff/0x350 net/socket.c:2055
 __do_sys_recvfrom net/socket.c:2073 [inline]
 __se_sys_recvfrom net/socket.c:2069 [inline]
 __x64_sys_recvfrom+0xe1/0x1a0 net/socket.c:2069
 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

The buggy address belongs to the object at ffff8880a488d040
 which belongs to the cache skbuff_fclone_cache of size 456
The buggy address is located 40 bytes inside of
 456-byte region [ffff8880a488d040, ffff8880a488d208)
The buggy address belongs to the page:
page:ffffea0002922340 refcount:1 mapcount:0 mapping:ffff88821b057000 index:0x0
raw: 00fffe0000000200 ffffea00022a5788 ffffea0002624a48 ffff88821b057000
raw: 0000000000000000 ffff8880a488d040 0000000100000006 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff8880a488cf00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 ffff8880a488cf80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
>ffff8880a488d000: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb
                                                          ^
 ffff8880a488d080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff8880a488d100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb

Fixes: 853697504de0 ("tcp: Fix highest_sack and highest_sack_seq")
Fixes: 50895b9de1d3 ("tcp: highest_sack fix")
Fixes: 737ff314563c ("tcp: use sequence distance to detect reordering")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Cambda Zhu <cambda@linux.alibaba.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c        | 1 +
 net/ipv4/tcp_input.c  | 1 +
 net/ipv4/tcp_output.c | 1 +
 3 files changed, 3 insertions(+)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index cd8a92e7a39e..5d58a84978d7 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2507,6 +2507,7 @@ static void tcp_rtx_queue_purge(struct sock *sk)
 {
 	struct rb_node *p = rb_first(&sk->tcp_rtx_queue);
 
+	tcp_sk(sk)->highest_sack = NULL;
 	while (p) {
 		struct sk_buff *skb = rb_to_skb(p);
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e286a9647a73..38b6d8f90a44 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3149,6 +3149,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack,
 			tp->retransmit_skb_hint = NULL;
 		if (unlikely(skb == tp->lost_skb_hint))
 			tp->lost_skb_hint = NULL;
+		tcp_highest_sack_replace(sk, skb, next);
 		tcp_rtx_queue_unlink_and_free(skb, sk);
 	}
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 1cc20edf4762..cc4ba42052c2 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3165,6 +3165,7 @@ int tcp_send_synack(struct sock *sk)
 			if (!nskb)
 				return -ENOMEM;
 			INIT_LIST_HEAD(&nskb->tcp_tsorted_anchor);
+			tcp_highest_sack_replace(sk, skb, nskb);
 			tcp_rtx_queue_unlink_and_free(skb, sk);
 			__skb_header_release(nskb);
 			tcp_rbtree_insert(&sk->tcp_rtx_queue, nskb);
-- 
2.21.1


From edf528f84c4218c728035ec7ab73b02e6ad0c1f6 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 22 Jan 2020 09:07:35 -0800
Subject: [PATCH 17/17] tun: add mutex_unlock() call and napi.skb clearing in
 tun_get_user()

[ Upstream commit 1efba987c48629c0c64703bb4ea76ca1a3771d17 ]

If both IFF_NAPI_FRAGS mode and XDP are enabled, and the XDP program
consumes the skb, we need to clear the napi.skb (or risk
a use-after-free) and release the mutex (or risk a deadlock)

WARNING: lock held when returning to user space!
5.5.0-rc6-syzkaller #0 Not tainted
------------------------------------------------
syz-executor.0/455 is leaving the kernel with locks still held!
1 lock held by syz-executor.0/455:
 #0: ffff888098f6e748 (&tfile->napi_mutex){+.+.}, at: tun_get_user+0x1604/0x3fc0 drivers/net/tun.c:1835

Fixes: 90e33d459407 ("tun: enable napi_gro_frags() for TUN/TAP driver")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Petar Penkov <ppenkov@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index bbd92221c6ca..09c444d3b496 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1900,6 +1900,10 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 			if (ret != XDP_PASS) {
 				rcu_read_unlock();
 				local_bh_enable();
+				if (frags) {
+					tfile->napi.skb = NULL;
+					mutex_unlock(&tfile->napi_mutex);
+				}
 				return total_len;
 			}
 		}
-- 
2.21.1


[-- Attachment #3: net_54.mbox --]
[-- Type: Application/Octet-Stream, Size: 96616 bytes --]

From 375807cca7a423d535c83c3bcb1c7381cc5897e7 Mon Sep 17 00:00:00 2001
From: Richard Palethorpe <rpalethorpe@suse.com>
Date: Tue, 21 Jan 2020 14:42:58 +0100
Subject: [PATCH 01/32] can, slip: Protect tty->disc_data in write_wakeup and
 close with RCU

[ Upstream commit 0ace17d56824165c7f4c68785d6b58971db954dd ]

write_wakeup can happen in parallel with close/hangup where tty->disc_data
is set to NULL and the netdevice is freed thus also freeing
disc_data. write_wakeup accesses disc_data so we must prevent close from
freeing the netdev while write_wakeup has a non-NULL view of
tty->disc_data.

We also need to make sure that accesses to disc_data are atomic. Which can
all be done with RCU.

This problem was found by Syzkaller on SLCAN, but the same issue is
reproducible with the SLIP line discipline using an LTP test based on the
Syzkaller reproducer.

A fix which didn't use RCU was posted by Hillf Danton.

Fixes: 661f7fda21b1 ("slip: Fix deadlock in write_wakeup")
Fixes: a8e83b17536a ("slcan: Port write_wakeup deadlock fix from slip")
Reported-by: syzbot+017e491ae13c0068598a@syzkaller.appspotmail.com
Signed-off-by: Richard Palethorpe <rpalethorpe@suse.com>
Cc: Wolfgang Grandegger <wg@grandegger.com>
Cc: Marc Kleine-Budde <mkl@pengutronix.de>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Tyler Hall <tylerwhall@gmail.com>
Cc: linux-can@vger.kernel.org
Cc: netdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: syzkaller@googlegroups.com
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/can/slcan.c | 12 ++++++++++--
 drivers/net/slip/slip.c | 12 ++++++++++--
 2 files changed, 20 insertions(+), 4 deletions(-)

diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c
index 2e57122f02fb..2f5c287eac95 100644
--- a/drivers/net/can/slcan.c
+++ b/drivers/net/can/slcan.c
@@ -344,9 +344,16 @@ static void slcan_transmit(struct work_struct *work)
  */
 static void slcan_write_wakeup(struct tty_struct *tty)
 {
-	struct slcan *sl = tty->disc_data;
+	struct slcan *sl;
+
+	rcu_read_lock();
+	sl = rcu_dereference(tty->disc_data);
+	if (!sl)
+		goto out;
 
 	schedule_work(&sl->tx_work);
+out:
+	rcu_read_unlock();
 }
 
 /* Send a can_frame to a TTY queue. */
@@ -644,10 +651,11 @@ static void slcan_close(struct tty_struct *tty)
 		return;
 
 	spin_lock_bh(&sl->lock);
-	tty->disc_data = NULL;
+	rcu_assign_pointer(tty->disc_data, NULL);
 	sl->tty = NULL;
 	spin_unlock_bh(&sl->lock);
 
+	synchronize_rcu();
 	flush_work(&sl->tx_work);
 
 	/* Flush network side */
diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c
index 2a91c192659f..61d7e0d1d77d 100644
--- a/drivers/net/slip/slip.c
+++ b/drivers/net/slip/slip.c
@@ -452,9 +452,16 @@ static void slip_transmit(struct work_struct *work)
  */
 static void slip_write_wakeup(struct tty_struct *tty)
 {
-	struct slip *sl = tty->disc_data;
+	struct slip *sl;
+
+	rcu_read_lock();
+	sl = rcu_dereference(tty->disc_data);
+	if (!sl)
+		goto out;
 
 	schedule_work(&sl->tx_work);
+out:
+	rcu_read_unlock();
 }
 
 static void sl_tx_timeout(struct net_device *dev)
@@ -882,10 +889,11 @@ static void slip_close(struct tty_struct *tty)
 		return;
 
 	spin_lock_bh(&sl->lock);
-	tty->disc_data = NULL;
+	rcu_assign_pointer(tty->disc_data, NULL);
 	sl->tty = NULL;
 	spin_unlock_bh(&sl->lock);
 
+	synchronize_rcu();
 	flush_work(&sl->tx_work);
 
 	/* VSV = very important to remove timers */
-- 
2.21.1


From 063ab4522fc2d04c4fad781a9623fd6da9dc8940 Mon Sep 17 00:00:00 2001
From: Wenwen Wang <wenwen@cs.uga.edu>
Date: Sat, 25 Jan 2020 14:33:29 +0000
Subject: [PATCH 02/32] firestream: fix memory leaks

[ Upstream commit fa865ba183d61c1ec8cbcab8573159c3b72b89a4 ]

In fs_open(), 'vcc' is allocated through kmalloc() and assigned to
'atm_vcc->dev_data.' In the following execution, if an error occurs, e.g.,
there is no more free channel, an error code EBUSY or ENOMEM will be
returned. However, 'vcc' is not deallocated, leading to memory leaks. Note
that, in normal cases where fs_open() returns 0, 'vcc' will be deallocated
in fs_close(). But, if fs_open() fails, there is no guarantee that
fs_close() will be invoked.

To fix this issue, deallocate 'vcc' before the error code is returned.

Signed-off-by: Wenwen Wang <wenwen@cs.uga.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/atm/firestream.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/atm/firestream.c b/drivers/atm/firestream.c
index 2bbab0230aeb..d287837ed755 100644
--- a/drivers/atm/firestream.c
+++ b/drivers/atm/firestream.c
@@ -912,6 +912,7 @@ static int fs_open(struct atm_vcc *atm_vcc)
 			}
 			if (!to) {
 				printk ("No more free channels for FS50..\n");
+				kfree(vcc);
 				return -EBUSY;
 			}
 			vcc->channo = dev->channo;
@@ -922,6 +923,7 @@ static int fs_open(struct atm_vcc *atm_vcc)
 			if (((DO_DIRECTION(rxtp) && dev->atm_vccs[vcc->channo])) ||
 			    ( DO_DIRECTION(txtp) && test_bit (vcc->channo, dev->tx_inuse))) {
 				printk ("Channel is in use for FS155.\n");
+				kfree(vcc);
 				return -EBUSY;
 			}
 		}
@@ -935,6 +937,7 @@ static int fs_open(struct atm_vcc *atm_vcc)
 			    tc, sizeof (struct fs_transmit_config));
 		if (!tc) {
 			fs_dprintk (FS_DEBUG_OPEN, "fs: can't alloc transmit_config.\n");
+			kfree(vcc);
 			return -ENOMEM;
 		}
 
-- 
2.21.1


From 932e7d8f4be853509e8eee279fce0fbd9d93fd5a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 21 Jan 2020 23:17:14 -0800
Subject: [PATCH 03/32] gtp: make sure only SOCK_DGRAM UDP sockets are accepted

[ Upstream commit 940ba14986657a50c15f694efca1beba31fa568f ]

A malicious user could use RAW sockets and fool
GTP using them as standard SOCK_DGRAM UDP sockets.

BUG: KMSAN: uninit-value in udp_tunnel_encap_enable include/net/udp_tunnel.h:174 [inline]
BUG: KMSAN: uninit-value in setup_udp_tunnel_sock+0x45e/0x6f0 net/ipv4/udp_tunnel.c:85
CPU: 0 PID: 11262 Comm: syz-executor613 Not tainted 5.5.0-rc5-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c9/0x220 lib/dump_stack.c:118
 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:118
 __msan_warning+0x58/0xa0 mm/kmsan/kmsan_instr.c:215
 udp_tunnel_encap_enable include/net/udp_tunnel.h:174 [inline]
 setup_udp_tunnel_sock+0x45e/0x6f0 net/ipv4/udp_tunnel.c:85
 gtp_encap_enable_socket+0x37f/0x5a0 drivers/net/gtp.c:827
 gtp_encap_enable drivers/net/gtp.c:844 [inline]
 gtp_newlink+0xfb/0x1e50 drivers/net/gtp.c:666
 __rtnl_newlink net/core/rtnetlink.c:3305 [inline]
 rtnl_newlink+0x2973/0x3920 net/core/rtnetlink.c:3363
 rtnetlink_rcv_msg+0x1153/0x1570 net/core/rtnetlink.c:5424
 netlink_rcv_skb+0x451/0x650 net/netlink/af_netlink.c:2477
 rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:5442
 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
 netlink_unicast+0xf9e/0x1100 net/netlink/af_netlink.c:1328
 netlink_sendmsg+0x1248/0x14d0 net/netlink/af_netlink.c:1917
 sock_sendmsg_nosec net/socket.c:639 [inline]
 sock_sendmsg net/socket.c:659 [inline]
 ____sys_sendmsg+0x12b6/0x1350 net/socket.c:2330
 ___sys_sendmsg net/socket.c:2384 [inline]
 __sys_sendmsg+0x451/0x5f0 net/socket.c:2417
 __do_sys_sendmsg net/socket.c:2426 [inline]
 __se_sys_sendmsg+0x97/0xb0 net/socket.c:2424
 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2424
 do_syscall_64+0xb8/0x160 arch/x86/entry/common.c:296
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x441359
Code: e8 ac e8 ff ff 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 eb 08 fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007fff1cd0ac28 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 0000000000441359
RDX: 0000000000000000 RSI: 0000000020000100 RDI: 0000000000000003
RBP: 00000000006cb018 R08: 00000000004002c8 R09: 00000000004002c8
R10: 00000000004002c8 R11: 0000000000000246 R12: 00000000004020d0
R13: 0000000000402160 R14: 0000000000000000 R15: 0000000000000000

Uninit was created at:
 kmsan_save_stack_with_flags+0x3c/0x90 mm/kmsan/kmsan.c:144
 kmsan_internal_alloc_meta_for_pages mm/kmsan/kmsan_shadow.c:307 [inline]
 kmsan_alloc_page+0x12a/0x310 mm/kmsan/kmsan_shadow.c:336
 __alloc_pages_nodemask+0x57f2/0x5f60 mm/page_alloc.c:4800
 alloc_pages_current+0x67d/0x990 mm/mempolicy.c:2207
 alloc_pages include/linux/gfp.h:534 [inline]
 alloc_slab_page+0x111/0x12f0 mm/slub.c:1511
 allocate_slab mm/slub.c:1656 [inline]
 new_slab+0x2bc/0x1130 mm/slub.c:1722
 new_slab_objects mm/slub.c:2473 [inline]
 ___slab_alloc+0x1533/0x1f30 mm/slub.c:2624
 __slab_alloc mm/slub.c:2664 [inline]
 slab_alloc_node mm/slub.c:2738 [inline]
 slab_alloc mm/slub.c:2783 [inline]
 kmem_cache_alloc+0xb23/0xd70 mm/slub.c:2788
 sk_prot_alloc+0xf2/0x620 net/core/sock.c:1597
 sk_alloc+0xf0/0xbe0 net/core/sock.c:1657
 inet_create+0x7c7/0x1370 net/ipv4/af_inet.c:321
 __sock_create+0x8eb/0xf00 net/socket.c:1420
 sock_create net/socket.c:1471 [inline]
 __sys_socket+0x1a1/0x600 net/socket.c:1513
 __do_sys_socket net/socket.c:1522 [inline]
 __se_sys_socket+0x8d/0xb0 net/socket.c:1520
 __x64_sys_socket+0x4a/0x70 net/socket.c:1520
 do_syscall_64+0xb8/0x160 arch/x86/entry/common.c:296
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 459aa660eb1d ("gtp: add initial driver for datapath of GPRS Tunneling Protocol (GTP-U)")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Pablo Neira <pablo@netfilter.org>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/gtp.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index f6222ada6818..9b3ba98726d7 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -804,19 +804,21 @@ static struct sock *gtp_encap_enable_socket(int fd, int type,
 		return NULL;
 	}
 
-	if (sock->sk->sk_protocol != IPPROTO_UDP) {
+	sk = sock->sk;
+	if (sk->sk_protocol != IPPROTO_UDP ||
+	    sk->sk_type != SOCK_DGRAM ||
+	    (sk->sk_family != AF_INET && sk->sk_family != AF_INET6)) {
 		pr_debug("socket fd=%d not UDP\n", fd);
 		sk = ERR_PTR(-EINVAL);
 		goto out_sock;
 	}
 
-	lock_sock(sock->sk);
-	if (sock->sk->sk_user_data) {
+	lock_sock(sk);
+	if (sk->sk_user_data) {
 		sk = ERR_PTR(-EBUSY);
 		goto out_rel_sock;
 	}
 
-	sk = sock->sk;
 	sock_hold(sk);
 
 	tuncfg.sk_user_data = gtp;
-- 
2.21.1


From 0539f8d2509e2280604145f31ff24d951d75840e Mon Sep 17 00:00:00 2001
From: Yuki Taguchi <tagyounit@gmail.com>
Date: Mon, 20 Jan 2020 13:48:37 +0900
Subject: [PATCH 04/32] ipv6: sr: remove SKB_GSO_IPXIP6 on End.D* actions

[ Upstream commit 62ebaeaedee7591c257543d040677a60e35c7aec ]

After LRO/GRO is applied, SRv6 encapsulated packets have
SKB_GSO_IPXIP6 feature flag, and this flag must be removed right after
decapulation procedure.

Currently, SKB_GSO_IPXIP6 flag is not removed on End.D* actions, which
creates inconsistent packet state, that is, a normal TCP/IP packets
have the SKB_GSO_IPXIP6 flag. This behavior can cause unexpected
fallback to GSO on routing to netdevices that do not support
SKB_GSO_IPXIP6. For example, on inter-VRF forwarding, decapsulated
packets separated into small packets by GSO because VRF devices do not
support TSO for packets with SKB_GSO_IPXIP6 flag, and this degrades
forwarding performance.

This patch removes encapsulation related GSO flags from the skb right
after the End.D* action is applied.

Fixes: d7a669dd2f8b ("ipv6: sr: add helper functions for seg6local")
Signed-off-by: Yuki Taguchi <tagyounit@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/seg6_local.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c
index e70567446f28..802eebf8ac4b 100644
--- a/net/ipv6/seg6_local.c
+++ b/net/ipv6/seg6_local.c
@@ -23,6 +23,7 @@
 #include <net/addrconf.h>
 #include <net/ip6_route.h>
 #include <net/dst_cache.h>
+#include <net/ip_tunnels.h>
 #ifdef CONFIG_IPV6_SEG6_HMAC
 #include <net/seg6_hmac.h>
 #endif
@@ -135,7 +136,8 @@ static bool decap_and_validate(struct sk_buff *skb, int proto)
 
 	skb_reset_network_header(skb);
 	skb_reset_transport_header(skb);
-	skb->encapsulation = 0;
+	if (iptunnel_pull_offloads(skb))
+		return false;
 
 	return true;
 }
-- 
2.21.1


From dd13d0d9ffeb21fb9ca861d5592d930b9998bfd6 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 23 Jan 2020 09:49:34 -0800
Subject: [PATCH 05/32] net: bcmgenet: Use netif_tx_napi_add() for TX NAPI

[ Upstream commit 148965df1a990af98b2c84092c2a2274c7489284 ]

Before commit 7587935cfa11 ("net: bcmgenet: move NAPI initialization to
ring initialization") moved the code, this used to be
netif_tx_napi_add(), but we lost that small semantic change in the
process, restore that.

Fixes: 7587935cfa11 ("net: bcmgenet: move NAPI initialization to ring initialization")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Acked-by: Doug Berger <opendmb@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 1de51811fcb4..8f909d57501f 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -2164,8 +2164,8 @@ static void bcmgenet_init_tx_ring(struct bcmgenet_priv *priv,
 				  DMA_END_ADDR);
 
 	/* Initialize Tx NAPI */
-	netif_napi_add(priv->dev, &ring->napi, bcmgenet_tx_poll,
-		       NAPI_POLL_WEIGHT);
+	netif_tx_napi_add(priv->dev, &ring->napi, bcmgenet_tx_poll,
+			  NAPI_POLL_WEIGHT);
 }
 
 /* Initialize a RDMA ring */
-- 
2.21.1


From b81230fb8c3c5d2ba348f81f3e2dc27a2b5abc7c Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Fri, 24 Jan 2020 20:41:44 +1100
Subject: [PATCH 06/32] net: cxgb3_main: Add CAP_NET_ADMIN check to
 CHELSIO_GET_MEM

[ Upstream commit 3546d8f1bbe992488ed91592cf6bf76e7114791a =

The cxgb3 driver for "Chelsio T3-based gigabit and 10Gb Ethernet
adapters" implements a custom ioctl as SIOCCHIOCTL/SIOCDEVPRIVATE in
cxgb_extension_ioctl().

One of the subcommands of the ioctl is CHELSIO_GET_MEM, which appears
to read memory directly out of the adapter and return it to userspace.
It's not entirely clear what the contents of the adapter memory
contains, but the assumption is that it shouldn't be accessible to all
users.

So add a CAP_NET_ADMIN check to the CHELSIO_GET_MEM case. Put it after
the is_offload() check, which matches two of the other subcommands in
the same function which also check for is_offload() and CAP_NET_ADMIN.

Found by Ilja by code inspection, not tested as I don't have the
required hardware.

Reported-by: Ilja Van Sprundel <ivansprundel@ioactive.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
index 58f89f6a040f..97ff8608f0ab 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
@@ -2448,6 +2448,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr)
 
 		if (!is_offload(adapter))
 			return -EOPNOTSUPP;
+		if (!capable(CAP_NET_ADMIN))
+			return -EPERM;
 		if (!(adapter->flags & FULL_INIT_DONE))
 			return -EIO;	/* need the memory controllers */
 		if (copy_from_user(&t, useraddr, sizeof(t)))
-- 
2.21.1


From a1038fc9a04899413cad998785c09da1020071fe Mon Sep 17 00:00:00 2001
From: Niko Kortstrom <niko.kortstrom@nokia.com>
Date: Thu, 16 Jan 2020 11:43:27 +0200
Subject: [PATCH 07/32] net: ip6_gre: fix moving ip6gre between namespaces

[ Upstream commit 690afc165bb314354667f67157c1a1aea7dc797a ]

Support for moving IPv4 GRE tunnels between namespaces was added in
commit b57708add314 ("gre: add x-netns support"). The respective change
for IPv6 tunnels, commit 22f08069e8b4 ("ip6gre: add x-netns support")
did not drop NETIF_F_NETNS_LOCAL flag so moving them from one netns to
another is still denied in IPv6 case. Drop NETIF_F_NETNS_LOCAL flag from
ip6gre tunnels to allow moving ip6gre tunnel endpoints between network
namespaces.

Signed-off-by: Niko Kortstrom <niko.kortstrom@nokia.com>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Acked-by: William Tu <u9012063@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 189de56f5e36..9ec05a1df5e1 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1466,7 +1466,6 @@ static int ip6gre_tunnel_init_common(struct net_device *dev)
 		dev->mtu -= 8;
 
 	if (tunnel->parms.collect_md) {
-		dev->features |= NETIF_F_NETNS_LOCAL;
 		netif_keep_dst(dev);
 	}
 	ip6gre_tnl_init_features(dev);
@@ -1894,7 +1893,6 @@ static void ip6gre_tap_setup(struct net_device *dev)
 	dev->needs_free_netdev = true;
 	dev->priv_destructor = ip6gre_dev_free;
 
-	dev->features |= NETIF_F_NETNS_LOCAL;
 	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 	netif_keep_dst(dev);
@@ -2197,7 +2195,6 @@ static void ip6erspan_tap_setup(struct net_device *dev)
 	dev->needs_free_netdev = true;
 	dev->priv_destructor = ip6gre_dev_free;
 
-	dev->features |= NETIF_F_NETNS_LOCAL;
 	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 	netif_keep_dst(dev);
-- 
2.21.1


From 3ef2400bee719551dab135391c29d1b87c26a099 Mon Sep 17 00:00:00 2001
From: William Dauchy <w.dauchy@criteo.com>
Date: Tue, 21 Jan 2020 21:49:54 +0100
Subject: [PATCH 08/32] net, ip6_tunnel: fix namespaces move

[ Upstream commit 5311a69aaca30fa849c3cc46fb25f75727fb72d0 ]

in the same manner as commit d0f418516022 ("net, ip_tunnel: fix
namespaces move"), fix namespace moving as it was broken since commit
8d79266bc48c ("ip6_tunnel: add collect_md mode to IPv6 tunnel"), but for
ipv6 this time; there is no reason to keep it for ip6_tunnel.

Fixes: 8d79266bc48c ("ip6_tunnel: add collect_md mode to IPv6 tunnel")
Signed-off-by: William Dauchy <w.dauchy@criteo.com>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 2f376dbc37d5..b5dd20c4599b 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1877,10 +1877,8 @@ static int ip6_tnl_dev_init(struct net_device *dev)
 	if (err)
 		return err;
 	ip6_tnl_link_config(t);
-	if (t->parms.collect_md) {
-		dev->features |= NETIF_F_NETNS_LOCAL;
+	if (t->parms.collect_md)
 		netif_keep_dst(dev);
-	}
 	return 0;
 }
 
-- 
2.21.1


From 71796bf165fcda9fb36c886d7db5cfd8112ba284 Mon Sep 17 00:00:00 2001
From: William Dauchy <w.dauchy@criteo.com>
Date: Tue, 21 Jan 2020 15:26:24 +0100
Subject: [PATCH 09/32] net, ip_tunnel: fix namespaces move

[ Upstream commit d0f418516022c32ecceaf4275423e5bd3f8743a9 ]

in the same manner as commit 690afc165bb3 ("net: ip6_gre: fix moving
ip6gre between namespaces"), fix namespace moving as it was broken since
commit 2e15ea390e6f ("ip_gre: Add support to collect tunnel metadata.").
Indeed, the ip6_gre commit removed the local flag for collect_md
condition, so there is no reason to keep it for ip_gre/ip_tunnel.

this patch will fix both ip_tunnel and ip_gre modules.

Fixes: 2e15ea390e6f ("ip_gre: Add support to collect tunnel metadata.")
Signed-off-by: William Dauchy <w.dauchy@criteo.com>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_tunnel.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 0fe2a5d3e258..74e1d964a615 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -1236,10 +1236,8 @@ int ip_tunnel_init(struct net_device *dev)
 	iph->version		= 4;
 	iph->ihl		= 5;
 
-	if (tunnel->collect_md) {
-		dev->features |= NETIF_F_NETNS_LOCAL;
+	if (tunnel->collect_md)
 		netif_keep_dst(dev);
-	}
 	return 0;
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_init);
-- 
2.21.1


From bd0ffa38d067dee9a4fe80102a804dbbfab0af2f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 21 Jan 2020 22:47:29 -0800
Subject: [PATCH 10/32] net: rtnetlink: validate IFLA_MTU attribute in
 rtnl_create_link()

[ Upstream commit d836f5c69d87473ff65c06a6123e5b2cf5e56f5b ]

rtnl_create_link() needs to apply dev->min_mtu and dev->max_mtu
checks that we apply in do_setlink()

Otherwise malicious users can crash the kernel, for example after
an integer overflow :

BUG: KASAN: use-after-free in memset include/linux/string.h:365 [inline]
BUG: KASAN: use-after-free in __alloc_skb+0x37b/0x5e0 net/core/skbuff.c:238
Write of size 32 at addr ffff88819f20b9c0 by task swapper/0/0

CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.5.0-rc1-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x197/0x210 lib/dump_stack.c:118
 print_address_description.constprop.0.cold+0xd4/0x30b mm/kasan/report.c:374
 __kasan_report.cold+0x1b/0x41 mm/kasan/report.c:506
 kasan_report+0x12/0x20 mm/kasan/common.c:639
 check_memory_region_inline mm/kasan/generic.c:185 [inline]
 check_memory_region+0x134/0x1a0 mm/kasan/generic.c:192
 memset+0x24/0x40 mm/kasan/common.c:108
 memset include/linux/string.h:365 [inline]
 __alloc_skb+0x37b/0x5e0 net/core/skbuff.c:238
 alloc_skb include/linux/skbuff.h:1049 [inline]
 alloc_skb_with_frags+0x93/0x590 net/core/skbuff.c:5664
 sock_alloc_send_pskb+0x7ad/0x920 net/core/sock.c:2242
 sock_alloc_send_skb+0x32/0x40 net/core/sock.c:2259
 mld_newpack+0x1d7/0x7f0 net/ipv6/mcast.c:1609
 add_grhead.isra.0+0x299/0x370 net/ipv6/mcast.c:1713
 add_grec+0x7db/0x10b0 net/ipv6/mcast.c:1844
 mld_send_cr net/ipv6/mcast.c:1970 [inline]
 mld_ifc_timer_expire+0x3d3/0x950 net/ipv6/mcast.c:2477
 call_timer_fn+0x1ac/0x780 kernel/time/timer.c:1404
 expire_timers kernel/time/timer.c:1449 [inline]
 __run_timers kernel/time/timer.c:1773 [inline]
 __run_timers kernel/time/timer.c:1740 [inline]
 run_timer_softirq+0x6c3/0x1790 kernel/time/timer.c:1786
 __do_softirq+0x262/0x98c kernel/softirq.c:292
 invoke_softirq kernel/softirq.c:373 [inline]
 irq_exit+0x19b/0x1e0 kernel/softirq.c:413
 exiting_irq arch/x86/include/asm/apic.h:536 [inline]
 smp_apic_timer_interrupt+0x1a3/0x610 arch/x86/kernel/apic/apic.c:1137
 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:829
 </IRQ>
RIP: 0010:native_safe_halt+0xe/0x10 arch/x86/include/asm/irqflags.h:61
Code: 98 6b ea f9 eb 8a cc cc cc cc cc cc e9 07 00 00 00 0f 00 2d 44 1c 60 00 f4 c3 66 90 e9 07 00 00 00 0f 00 2d 34 1c 60 00 fb f4 <c3> cc 55 48 89 e5 41 57 41 56 41 55 41 54 53 e8 4e 5d 9a f9 e8 79
RSP: 0018:ffffffff89807ce8 EFLAGS: 00000286 ORIG_RAX: ffffffffffffff13
RAX: 1ffffffff13266ae RBX: ffffffff8987a1c0 RCX: 0000000000000000
RDX: dffffc0000000000 RSI: 0000000000000006 RDI: ffffffff8987aa54
RBP: ffffffff89807d18 R08: ffffffff8987a1c0 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: dffffc0000000000
R13: ffffffff8a799980 R14: 0000000000000000 R15: 0000000000000000
 arch_cpu_idle+0xa/0x10 arch/x86/kernel/process.c:690
 default_idle_call+0x84/0xb0 kernel/sched/idle.c:94
 cpuidle_idle_call kernel/sched/idle.c:154 [inline]
 do_idle+0x3c8/0x6e0 kernel/sched/idle.c:269
 cpu_startup_entry+0x1b/0x20 kernel/sched/idle.c:361
 rest_init+0x23b/0x371 init/main.c:451
 arch_call_rest_init+0xe/0x1b
 start_kernel+0x904/0x943 init/main.c:784
 x86_64_start_reservations+0x29/0x2b arch/x86/kernel/head64.c:490
 x86_64_start_kernel+0x77/0x7b arch/x86/kernel/head64.c:471
 secondary_startup_64+0xa4/0xb0 arch/x86/kernel/head_64.S:242

The buggy address belongs to the page:
page:ffffea00067c82c0 refcount:0 mapcount:0 mapping:0000000000000000 index:0x0
raw: 057ffe0000000000 ffffea00067c82c8 ffffea00067c82c8 0000000000000000
raw: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff88819f20b880: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
 ffff88819f20b900: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
>ffff88819f20b980: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
                                           ^
 ffff88819f20ba00: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
 ffff88819f20ba80: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff

Fixes: 61e84623ace3 ("net: centralize net_device min/max MTU checking")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  2 ++
 net/core/dev.c            | 29 +++++++++++++++++++----------
 net/core/rtnetlink.c      | 13 +++++++++++--
 3 files changed, 32 insertions(+), 12 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 13f09706033a..f8fde9fa479c 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3666,6 +3666,8 @@ int dev_set_alias(struct net_device *, const char *, size_t);
 int dev_get_alias(const struct net_device *, char *, size_t);
 int dev_change_net_namespace(struct net_device *, struct net *, const char *);
 int __dev_set_mtu(struct net_device *, int);
+int dev_validate_mtu(struct net_device *dev, int mtu,
+		     struct netlink_ext_ack *extack);
 int dev_set_mtu_ext(struct net_device *dev, int mtu,
 		    struct netlink_ext_ack *extack);
 int dev_set_mtu(struct net_device *, int);
diff --git a/net/core/dev.c b/net/core/dev.c
index 3098c90d60e2..3a94ec2610ea 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7973,6 +7973,22 @@ int __dev_set_mtu(struct net_device *dev, int new_mtu)
 }
 EXPORT_SYMBOL(__dev_set_mtu);
 
+int dev_validate_mtu(struct net_device *dev, int new_mtu,
+		     struct netlink_ext_ack *extack)
+{
+	/* MTU must be positive, and in range */
+	if (new_mtu < 0 || new_mtu < dev->min_mtu) {
+		NL_SET_ERR_MSG(extack, "mtu less than device minimum");
+		return -EINVAL;
+	}
+
+	if (dev->max_mtu > 0 && new_mtu > dev->max_mtu) {
+		NL_SET_ERR_MSG(extack, "mtu greater than device maximum");
+		return -EINVAL;
+	}
+	return 0;
+}
+
 /**
  *	dev_set_mtu_ext - Change maximum transfer unit
  *	@dev: device
@@ -7989,16 +8005,9 @@ int dev_set_mtu_ext(struct net_device *dev, int new_mtu,
 	if (new_mtu == dev->mtu)
 		return 0;
 
-	/* MTU must be positive, and in range */
-	if (new_mtu < 0 || new_mtu < dev->min_mtu) {
-		NL_SET_ERR_MSG(extack, "mtu less than device minimum");
-		return -EINVAL;
-	}
-
-	if (dev->max_mtu > 0 && new_mtu > dev->max_mtu) {
-		NL_SET_ERR_MSG(extack, "mtu greater than device maximum");
-		return -EINVAL;
-	}
+	err = dev_validate_mtu(dev, new_mtu, extack);
+	if (err)
+		return err;
 
 	if (!netif_device_present(dev))
 		return -ENODEV;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index e4ec575c1fba..944acb1a9f29 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2959,8 +2959,17 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname,
 	dev->rtnl_link_ops = ops;
 	dev->rtnl_link_state = RTNL_LINK_INITIALIZING;
 
-	if (tb[IFLA_MTU])
-		dev->mtu = nla_get_u32(tb[IFLA_MTU]);
+	if (tb[IFLA_MTU]) {
+		u32 mtu = nla_get_u32(tb[IFLA_MTU]);
+		int err;
+
+		err = dev_validate_mtu(dev, mtu, extack);
+		if (err) {
+			free_netdev(dev);
+			return ERR_PTR(err);
+		}
+		dev->mtu = mtu;
+	}
 	if (tb[IFLA_ADDRESS]) {
 		memcpy(dev->dev_addr, nla_data(tb[IFLA_ADDRESS]),
 				nla_len(tb[IFLA_ADDRESS]));
-- 
2.21.1


From 591e2ca35d55afd26c0a6064e3fcb9ac4361583a Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Wed, 22 Jan 2020 15:42:02 -0800
Subject: [PATCH 11/32] net_sched: fix datalen for ematch

[ Upstream commit 61678d28d4a45ef376f5d02a839cc37509ae9281 ]

syzbot reported an out-of-bound access in em_nbyte. As initially
analyzed by Eric, this is because em_nbyte sets its own em->datalen
in em_nbyte_change() other than the one specified by user, but this
value gets overwritten later by its caller tcf_em_validate().
We should leave em->datalen untouched to respect their choices.

I audit all the in-tree ematch users, all of those implement
->change() set em->datalen, so we can just avoid setting it twice
in this case.

Reported-and-tested-by: syzbot+5af9a90dad568aa9f611@syzkaller.appspotmail.com
Reported-by: syzbot+2f07903a5b05e7f36410@syzkaller.appspotmail.com
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/ematch.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/ematch.c b/net/sched/ematch.c
index 8f2ad706784d..d0140a92694a 100644
--- a/net/sched/ematch.c
+++ b/net/sched/ematch.c
@@ -263,12 +263,12 @@ static int tcf_em_validate(struct tcf_proto *tp,
 				}
 				em->data = (unsigned long) v;
 			}
+			em->datalen = data_len;
 		}
 	}
 
 	em->matchid = em_hdr->matchid;
 	em->flags = em_hdr->flags;
-	em->datalen = data_len;
 	em->net = net;
 
 	err = 0;
-- 
2.21.1


From c29885be6cc4eeab5cd2f13243e0a257d39a6c0b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 21 Jan 2020 11:02:20 -0800
Subject: [PATCH 12/32] net_sched: use validated TCA_KIND attribute in
 tc_new_tfilter()

[ Upstream commit 36d79af7fb59d6d9106feb9c1855eb93d6d53fe6 ]

sysbot found another issue in tc_new_tfilter().
We probably should use @name which contains the sanitized
version of TCA_KIND.

BUG: KMSAN: uninit-value in string_nocheck lib/vsprintf.c:608 [inline]
BUG: KMSAN: uninit-value in string+0x522/0x690 lib/vsprintf.c:689
CPU: 1 PID: 10753 Comm: syz-executor.1 Not tainted 5.5.0-rc5-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c9/0x220 lib/dump_stack.c:118
 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:118
 __msan_warning+0x58/0xa0 mm/kmsan/kmsan_instr.c:215
 string_nocheck lib/vsprintf.c:608 [inline]
 string+0x522/0x690 lib/vsprintf.c:689
 vsnprintf+0x207d/0x31b0 lib/vsprintf.c:2574
 __request_module+0x2ad/0x11c0 kernel/kmod.c:143
 tcf_proto_lookup_ops+0x241/0x720 net/sched/cls_api.c:139
 tcf_proto_create net/sched/cls_api.c:262 [inline]
 tc_new_tfilter+0x2a4e/0x5010 net/sched/cls_api.c:2058
 rtnetlink_rcv_msg+0xcb7/0x1570 net/core/rtnetlink.c:5415
 netlink_rcv_skb+0x451/0x650 net/netlink/af_netlink.c:2477
 rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:5442
 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
 netlink_unicast+0xf9e/0x1100 net/netlink/af_netlink.c:1328
 netlink_sendmsg+0x1248/0x14d0 net/netlink/af_netlink.c:1917
 sock_sendmsg_nosec net/socket.c:639 [inline]
 sock_sendmsg net/socket.c:659 [inline]
 ____sys_sendmsg+0x12b6/0x1350 net/socket.c:2330
 ___sys_sendmsg net/socket.c:2384 [inline]
 __sys_sendmsg+0x451/0x5f0 net/socket.c:2417
 __do_sys_sendmsg net/socket.c:2426 [inline]
 __se_sys_sendmsg+0x97/0xb0 net/socket.c:2424
 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2424
 do_syscall_64+0xb8/0x160 arch/x86/entry/common.c:296
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x45b349
Code: ad b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f88b3948c78 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 00007f88b39496d4 RCX: 000000000045b349
RDX: 0000000000000000 RSI: 00000000200001c0 RDI: 0000000000000003
RBP: 000000000075bfc8 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff
R13: 000000000000099f R14: 00000000004cb163 R15: 000000000075bfd4

Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:144 [inline]
 kmsan_internal_poison_shadow+0x66/0xd0 mm/kmsan/kmsan.c:127
 kmsan_slab_alloc+0x8a/0xe0 mm/kmsan/kmsan_hooks.c:82
 slab_alloc_node mm/slub.c:2774 [inline]
 __kmalloc_node_track_caller+0xb40/0x1200 mm/slub.c:4382
 __kmalloc_reserve net/core/skbuff.c:141 [inline]
 __alloc_skb+0x2fd/0xac0 net/core/skbuff.c:209
 alloc_skb include/linux/skbuff.h:1049 [inline]
 netlink_alloc_large_skb net/netlink/af_netlink.c:1174 [inline]
 netlink_sendmsg+0x7d3/0x14d0 net/netlink/af_netlink.c:1892
 sock_sendmsg_nosec net/socket.c:639 [inline]
 sock_sendmsg net/socket.c:659 [inline]
 ____sys_sendmsg+0x12b6/0x1350 net/socket.c:2330
 ___sys_sendmsg net/socket.c:2384 [inline]
 __sys_sendmsg+0x451/0x5f0 net/socket.c:2417
 __do_sys_sendmsg net/socket.c:2426 [inline]
 __se_sys_sendmsg+0x97/0xb0 net/socket.c:2424
 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2424
 do_syscall_64+0xb8/0x160 arch/x86/entry/common.c:296
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 6f96c3c6904c ("net_sched: fix backward compatibility for TCA_KIND")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 76e0d122616a..c2cdd0fc2e70 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -2055,9 +2055,8 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
 							       &chain_info));
 
 		mutex_unlock(&chain->filter_chain_lock);
-		tp_new = tcf_proto_create(nla_data(tca[TCA_KIND]),
-					  protocol, prio, chain, rtnl_held,
-					  extack);
+		tp_new = tcf_proto_create(name, protocol, prio, chain,
+					  rtnl_held, extack);
 		if (IS_ERR(tp_new)) {
 			err = PTR_ERR(tp_new);
 			goto errout_tp;
-- 
2.21.1


From d1dbbf3f91e8a422b4e71639fddfbdcdcaf58f5c Mon Sep 17 00:00:00 2001
From: Jouni Hogander <jouni.hogander@unikie.com>
Date: Mon, 20 Jan 2020 09:51:03 +0200
Subject: [PATCH 13/32] net-sysfs: Fix reference count leak

[ Upstream commit cb626bf566eb4433318d35681286c494f04fedcc ]

Netdev_register_kobject is calling device_initialize. In case of error
reference taken by device_initialize is not given up.

Drivers are supposed to call free_netdev in case of error. In non-error
case the last reference is given up there and device release sequence
is triggered. In error case this reference is kept and the release
sequence is never started.

Fix this by setting reg_state as NETREG_UNREGISTERED if registering
fails.

This is the rootcause for couple of memory leaks reported by Syzkaller:

BUG: memory leak unreferenced object 0xffff8880675ca008 (size 256):
  comm "netdev_register", pid 281, jiffies 4294696663 (age 6.808s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
  backtrace:
    [<0000000058ca4711>] kmem_cache_alloc_trace+0x167/0x280
    [<000000002340019b>] device_add+0x882/0x1750
    [<000000001d588c3a>] netdev_register_kobject+0x128/0x380
    [<0000000011ef5535>] register_netdevice+0xa1b/0xf00
    [<000000007fcf1c99>] __tun_chr_ioctl+0x20d5/0x3dd0
    [<000000006a5b7b2b>] tun_chr_ioctl+0x2f/0x40
    [<00000000f30f834a>] do_vfs_ioctl+0x1c7/0x1510
    [<00000000fba062ea>] ksys_ioctl+0x99/0xb0
    [<00000000b1c1b8d2>] __x64_sys_ioctl+0x78/0xb0
    [<00000000984cabb9>] do_syscall_64+0x16f/0x580
    [<000000000bde033d>] entry_SYSCALL_64_after_hwframe+0x44/0xa9
    [<00000000e6ca2d9f>] 0xffffffffffffffff

BUG: memory leak
unreferenced object 0xffff8880668ba588 (size 8):
  comm "kobject_set_nam", pid 286, jiffies 4294725297 (age 9.871s)
  hex dump (first 8 bytes):
    6e 72 30 00 cc be df 2b                          nr0....+
  backtrace:
    [<00000000a322332a>] __kmalloc_track_caller+0x16e/0x290
    [<00000000236fd26b>] kstrdup+0x3e/0x70
    [<00000000dd4a2815>] kstrdup_const+0x3e/0x50
    [<0000000049a377fc>] kvasprintf_const+0x10e/0x160
    [<00000000627fc711>] kobject_set_name_vargs+0x5b/0x140
    [<0000000019eeab06>] dev_set_name+0xc0/0xf0
    [<0000000069cb12bc>] netdev_register_kobject+0xc8/0x320
    [<00000000f2e83732>] register_netdevice+0xa1b/0xf00
    [<000000009e1f57cc>] __tun_chr_ioctl+0x20d5/0x3dd0
    [<000000009c560784>] tun_chr_ioctl+0x2f/0x40
    [<000000000d759e02>] do_vfs_ioctl+0x1c7/0x1510
    [<00000000351d7c31>] ksys_ioctl+0x99/0xb0
    [<000000008390040a>] __x64_sys_ioctl+0x78/0xb0
    [<0000000052d196b7>] do_syscall_64+0x16f/0x580
    [<0000000019af9236>] entry_SYSCALL_64_after_hwframe+0x44/0xa9
    [<00000000bc384531>] 0xffffffffffffffff

v3 -> v4:
  Set reg_state to NETREG_UNREGISTERED if registering fails

v2 -> v3:
* Replaced BUG_ON with WARN_ON in free_netdev and netdev_release

v1 -> v2:
* Relying on driver calling free_netdev rather than calling
  put_device directly in error path

Reported-by: syzbot+ad8ca40ecd77896d51e2@syzkaller.appspotmail.com
Cc: David Miller <davem@davemloft.net>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Signed-off-by: Jouni Hogander <jouni.hogander@unikie.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 3a94ec2610ea..af6ee5ff4fda 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -9082,8 +9082,10 @@ int register_netdevice(struct net_device *dev)
 		goto err_uninit;
 
 	ret = netdev_register_kobject(dev);
-	if (ret)
+	if (ret) {
+		dev->reg_state = NETREG_UNREGISTERED;
 		goto err_uninit;
+	}
 	dev->reg_state = NETREG_REGISTERED;
 
 	__netdev_update_features(dev);
-- 
2.21.1


From 35c3143f910a7efc87472180a7af58dbe5f4d09d Mon Sep 17 00:00:00 2001
From: James Hughes <james.hughes@raspberrypi.org>
Date: Mon, 20 Jan 2020 11:12:40 +0000
Subject: [PATCH 14/32] net: usb: lan78xx: Add .ndo_features_check

[ Upstream commit ce896476c65d72b4b99fa09c2f33436b4198f034 ]

As reported by Eric Dumazet, there are still some outstanding
cases where the driver does not handle TSO correctly when skb's
are over a certain size. Most cases have been fixed, this patch
should ensure that forwarded SKB's that are greater than
MAX_SINGLE_PACKET_SIZE - TX_OVERHEAD are software segmented
and handled correctly.

Signed-off-by: James Hughes <james.hughes@raspberrypi.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/lan78xx.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index c232f1612083..0170a441208a 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -20,6 +20,7 @@
 #include <linux/mdio.h>
 #include <linux/phy.h>
 #include <net/ip6_checksum.h>
+#include <net/vxlan.h>
 #include <linux/interrupt.h>
 #include <linux/irqdomain.h>
 #include <linux/irq.h>
@@ -3668,6 +3669,19 @@ static void lan78xx_tx_timeout(struct net_device *net)
 	tasklet_schedule(&dev->bh);
 }
 
+static netdev_features_t lan78xx_features_check(struct sk_buff *skb,
+						struct net_device *netdev,
+						netdev_features_t features)
+{
+	if (skb->len + TX_OVERHEAD > MAX_SINGLE_PACKET_SIZE)
+		features &= ~NETIF_F_GSO_MASK;
+
+	features = vlan_features_check(skb, features);
+	features = vxlan_features_check(skb, features);
+
+	return features;
+}
+
 static const struct net_device_ops lan78xx_netdev_ops = {
 	.ndo_open		= lan78xx_open,
 	.ndo_stop		= lan78xx_stop,
@@ -3681,6 +3695,7 @@ static const struct net_device_ops lan78xx_netdev_ops = {
 	.ndo_set_features	= lan78xx_set_features,
 	.ndo_vlan_rx_add_vid	= lan78xx_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= lan78xx_vlan_rx_kill_vid,
+	.ndo_features_check	= lan78xx_features_check,
 };
 
 static void lan78xx_stat_monitor(struct timer_list *t)
-- 
2.21.1


From b23566c0f6a56140d22aaa947cd7bf0c4c036c61 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 21 Jan 2020 16:50:49 +0100
Subject: [PATCH 15/32] Revert "udp: do rmem bulk free even if the rx sk queue
 is empty"

[ Upstream commit d39ca2590d10712f412add7a88e1dd467a7246f4 ]

This reverts commit 0d4a6608f68c7532dcbfec2ea1150c9761767d03.

Willem reported that after commit 0d4a6608f68c ("udp: do rmem bulk
free even if the rx sk queue is empty") the memory allocated by
an almost idle system with many UDP sockets can grow a lot.

For stable kernel keep the solution as simple as possible and revert
the offending commit.

Reported-by: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
Diagnosed-by: Eric Dumazet <eric.dumazet@gmail.com>
Fixes: 0d4a6608f68c ("udp: do rmem bulk free even if the rx sk queue is empty")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 7aa4e77161f6..7ae7065758bd 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1368,7 +1368,8 @@ static void udp_rmem_release(struct sock *sk, int size, int partial,
 	if (likely(partial)) {
 		up->forward_deficit += size;
 		size = up->forward_deficit;
-		if (size < (sk->sk_rcvbuf >> 2))
+		if (size < (sk->sk_rcvbuf >> 2) &&
+		    !skb_queue_empty(&up->reader_queue))
 			return;
 	} else {
 		size += up->forward_deficit;
-- 
2.21.1


From ffaa3f1b819e362f547001118611434a4b79ae85 Mon Sep 17 00:00:00 2001
From: Wen Yang <wenyang@linux.alibaba.com>
Date: Mon, 20 Jan 2020 18:04:56 +0800
Subject: [PATCH 16/32] tcp_bbr: improve arithmetic division in bbr_update_bw()

[ Upstream commit 5b2f1f3070b6447b76174ea8bfb7390dc6253ebd ]

do_div() does a 64-by-32 division. Use div64_long() instead of it
if the divisor is long, to avoid truncation to 32-bit.
And as a nice side effect also cleans up the function a bit.

Signed-off-by: Wen Yang <wenyang@linux.alibaba.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
Cc: netdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_bbr.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index a6545ef0d27b..6c4d79baff26 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -779,8 +779,7 @@ static void bbr_update_bw(struct sock *sk, const struct rate_sample *rs)
 	 * bandwidth sample. Delivered is in packets and interval_us in uS and
 	 * ratio will be <<1 for most connections. So delivered is first scaled.
 	 */
-	bw = (u64)rs->delivered * BW_UNIT;
-	do_div(bw, rs->interval_us);
+	bw = div64_long((u64)rs->delivered * BW_UNIT, rs->interval_us);
 
 	/* If this sample is application-limited, it is likely to have a very
 	 * low delivered count that represents application behavior rather than
-- 
2.21.1


From 91357051dfff74172ce1e12d1bf4874aca77be4d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 22 Jan 2020 21:03:00 -0800
Subject: [PATCH 17/32] tcp: do not leave dangling pointers in tp->highest_sack

[ Upstream commit 2bec445f9bf35e52e395b971df48d3e1e5dc704a ]

Latest commit 853697504de0 ("tcp: Fix highest_sack and highest_sack_seq")
apparently allowed syzbot to trigger various crashes in TCP stack [1]

I believe this commit only made things easier for syzbot to find
its way into triggering use-after-frees. But really the bugs
could lead to bad TCP behavior or even plain crashes even for
non malicious peers.

I have audited all calls to tcp_rtx_queue_unlink() and
tcp_rtx_queue_unlink_and_free() and made sure tp->highest_sack would be updated
if we are removing from rtx queue the skb that tp->highest_sack points to.

These updates were missing in three locations :

1) tcp_clean_rtx_queue() [This one seems quite serious,
                          I have no idea why this was not caught earlier]

2) tcp_rtx_queue_purge() [Probably not a big deal for normal operations]

3) tcp_send_synack()     [Probably not a big deal for normal operations]

[1]
BUG: KASAN: use-after-free in tcp_highest_sack_seq include/net/tcp.h:1864 [inline]
BUG: KASAN: use-after-free in tcp_highest_sack_seq include/net/tcp.h:1856 [inline]
BUG: KASAN: use-after-free in tcp_check_sack_reordering+0x33c/0x3a0 net/ipv4/tcp_input.c:891
Read of size 4 at addr ffff8880a488d068 by task ksoftirqd/1/16

CPU: 1 PID: 16 Comm: ksoftirqd/1 Not tainted 5.5.0-rc5-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x197/0x210 lib/dump_stack.c:118
 print_address_description.constprop.0.cold+0xd4/0x30b mm/kasan/report.c:374
 __kasan_report.cold+0x1b/0x41 mm/kasan/report.c:506
 kasan_report+0x12/0x20 mm/kasan/common.c:639
 __asan_report_load4_noabort+0x14/0x20 mm/kasan/generic_report.c:134
 tcp_highest_sack_seq include/net/tcp.h:1864 [inline]
 tcp_highest_sack_seq include/net/tcp.h:1856 [inline]
 tcp_check_sack_reordering+0x33c/0x3a0 net/ipv4/tcp_input.c:891
 tcp_try_undo_partial net/ipv4/tcp_input.c:2730 [inline]
 tcp_fastretrans_alert+0xf74/0x23f0 net/ipv4/tcp_input.c:2847
 tcp_ack+0x2577/0x5bf0 net/ipv4/tcp_input.c:3710
 tcp_rcv_established+0x6dd/0x1e90 net/ipv4/tcp_input.c:5706
 tcp_v4_do_rcv+0x619/0x8d0 net/ipv4/tcp_ipv4.c:1619
 tcp_v4_rcv+0x307f/0x3b40 net/ipv4/tcp_ipv4.c:2001
 ip_protocol_deliver_rcu+0x5a/0x880 net/ipv4/ip_input.c:204
 ip_local_deliver_finish+0x23b/0x380 net/ipv4/ip_input.c:231
 NF_HOOK include/linux/netfilter.h:307 [inline]
 NF_HOOK include/linux/netfilter.h:301 [inline]
 ip_local_deliver+0x1e9/0x520 net/ipv4/ip_input.c:252
 dst_input include/net/dst.h:442 [inline]
 ip_rcv_finish+0x1db/0x2f0 net/ipv4/ip_input.c:428
 NF_HOOK include/linux/netfilter.h:307 [inline]
 NF_HOOK include/linux/netfilter.h:301 [inline]
 ip_rcv+0xe8/0x3f0 net/ipv4/ip_input.c:538
 __netif_receive_skb_one_core+0x113/0x1a0 net/core/dev.c:5148
 __netif_receive_skb+0x2c/0x1d0 net/core/dev.c:5262
 process_backlog+0x206/0x750 net/core/dev.c:6093
 napi_poll net/core/dev.c:6530 [inline]
 net_rx_action+0x508/0x1120 net/core/dev.c:6598
 __do_softirq+0x262/0x98c kernel/softirq.c:292
 run_ksoftirqd kernel/softirq.c:603 [inline]
 run_ksoftirqd+0x8e/0x110 kernel/softirq.c:595
 smpboot_thread_fn+0x6a3/0xa40 kernel/smpboot.c:165
 kthread+0x361/0x430 kernel/kthread.c:255
 ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:352

Allocated by task 10091:
 save_stack+0x23/0x90 mm/kasan/common.c:72
 set_track mm/kasan/common.c:80 [inline]
 __kasan_kmalloc mm/kasan/common.c:513 [inline]
 __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:486
 kasan_slab_alloc+0xf/0x20 mm/kasan/common.c:521
 slab_post_alloc_hook mm/slab.h:584 [inline]
 slab_alloc_node mm/slab.c:3263 [inline]
 kmem_cache_alloc_node+0x138/0x740 mm/slab.c:3575
 __alloc_skb+0xd5/0x5e0 net/core/skbuff.c:198
 alloc_skb_fclone include/linux/skbuff.h:1099 [inline]
 sk_stream_alloc_skb net/ipv4/tcp.c:875 [inline]
 sk_stream_alloc_skb+0x113/0xc90 net/ipv4/tcp.c:852
 tcp_sendmsg_locked+0xcf9/0x3470 net/ipv4/tcp.c:1282
 tcp_sendmsg+0x30/0x50 net/ipv4/tcp.c:1432
 inet_sendmsg+0x9e/0xe0 net/ipv4/af_inet.c:807
 sock_sendmsg_nosec net/socket.c:652 [inline]
 sock_sendmsg+0xd7/0x130 net/socket.c:672
 __sys_sendto+0x262/0x380 net/socket.c:1998
 __do_sys_sendto net/socket.c:2010 [inline]
 __se_sys_sendto net/socket.c:2006 [inline]
 __x64_sys_sendto+0xe1/0x1a0 net/socket.c:2006
 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Freed by task 10095:
 save_stack+0x23/0x90 mm/kasan/common.c:72
 set_track mm/kasan/common.c:80 [inline]
 kasan_set_free_info mm/kasan/common.c:335 [inline]
 __kasan_slab_free+0x102/0x150 mm/kasan/common.c:474
 kasan_slab_free+0xe/0x10 mm/kasan/common.c:483
 __cache_free mm/slab.c:3426 [inline]
 kmem_cache_free+0x86/0x320 mm/slab.c:3694
 kfree_skbmem+0x178/0x1c0 net/core/skbuff.c:645
 __kfree_skb+0x1e/0x30 net/core/skbuff.c:681
 sk_eat_skb include/net/sock.h:2453 [inline]
 tcp_recvmsg+0x1252/0x2930 net/ipv4/tcp.c:2166
 inet_recvmsg+0x136/0x610 net/ipv4/af_inet.c:838
 sock_recvmsg_nosec net/socket.c:886 [inline]
 sock_recvmsg net/socket.c:904 [inline]
 sock_recvmsg+0xce/0x110 net/socket.c:900
 __sys_recvfrom+0x1ff/0x350 net/socket.c:2055
 __do_sys_recvfrom net/socket.c:2073 [inline]
 __se_sys_recvfrom net/socket.c:2069 [inline]
 __x64_sys_recvfrom+0xe1/0x1a0 net/socket.c:2069
 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

The buggy address belongs to the object at ffff8880a488d040
 which belongs to the cache skbuff_fclone_cache of size 456
The buggy address is located 40 bytes inside of
 456-byte region [ffff8880a488d040, ffff8880a488d208)
The buggy address belongs to the page:
page:ffffea0002922340 refcount:1 mapcount:0 mapping:ffff88821b057000 index:0x0
raw: 00fffe0000000200 ffffea00022a5788 ffffea0002624a48 ffff88821b057000
raw: 0000000000000000 ffff8880a488d040 0000000100000006 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff8880a488cf00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 ffff8880a488cf80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
>ffff8880a488d000: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb
                                                          ^
 ffff8880a488d080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff8880a488d100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb

Fixes: 853697504de0 ("tcp: Fix highest_sack and highest_sack_seq")
Fixes: 50895b9de1d3 ("tcp: highest_sack fix")
Fixes: 737ff314563c ("tcp: use sequence distance to detect reordering")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Cambda Zhu <cambda@linux.alibaba.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c        | 1 +
 net/ipv4/tcp_input.c  | 1 +
 net/ipv4/tcp_output.c | 1 +
 3 files changed, 3 insertions(+)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 84115577d3dc..3640e8563a10 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2520,6 +2520,7 @@ static void tcp_rtx_queue_purge(struct sock *sk)
 {
 	struct rb_node *p = rb_first(&sk->tcp_rtx_queue);
 
+	tcp_sk(sk)->highest_sack = NULL;
 	while (p) {
 		struct sk_buff *skb = rb_to_skb(p);
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 59b78ce2ce2e..6f7155d91313 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3164,6 +3164,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack,
 			tp->retransmit_skb_hint = NULL;
 		if (unlikely(skb == tp->lost_skb_hint))
 			tp->lost_skb_hint = NULL;
+		tcp_highest_sack_replace(sk, skb, next);
 		tcp_rtx_queue_unlink_and_free(skb, sk);
 	}
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index e4ba915c4bb5..660b24fe041e 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3231,6 +3231,7 @@ int tcp_send_synack(struct sock *sk)
 			if (!nskb)
 				return -ENOMEM;
 			INIT_LIST_HEAD(&nskb->tcp_tsorted_anchor);
+			tcp_highest_sack_replace(sk, skb, nskb);
 			tcp_rtx_queue_unlink_and_free(skb, sk);
 			__skb_header_release(nskb);
 			tcp_rbtree_insert(&sk->tcp_rtx_queue, nskb);
-- 
2.21.1


From 76ca0bb8fbb66bb0877a3f98073c7a1788741bee Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 22 Jan 2020 09:07:35 -0800
Subject: [PATCH 18/32] tun: add mutex_unlock() call and napi.skb clearing in
 tun_get_user()

[ Upstream commit 1efba987c48629c0c64703bb4ea76ca1a3771d17 ]

If both IFF_NAPI_FRAGS mode and XDP are enabled, and the XDP program
consumes the skb, we need to clear the napi.skb (or risk
a use-after-free) and release the mutex (or risk a deadlock)

WARNING: lock held when returning to user space!
5.5.0-rc6-syzkaller #0 Not tainted
------------------------------------------------
syz-executor.0/455 is leaving the kernel with locks still held!
1 lock held by syz-executor.0/455:
 #0: ffff888098f6e748 (&tfile->napi_mutex){+.+.}, at: tun_get_user+0x1604/0x3fc0 drivers/net/tun.c:1835

Fixes: 90e33d459407 ("tun: enable napi_gro_frags() for TUN/TAP driver")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Petar Penkov <ppenkov@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 16564ebcde50..69f553a028ee 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1936,6 +1936,10 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 			if (ret != XDP_PASS) {
 				rcu_read_unlock();
 				local_bh_enable();
+				if (frags) {
+					tfile->napi.skb = NULL;
+					mutex_unlock(&tfile->napi_mutex);
+				}
 				return total_len;
 			}
 		}
-- 
2.21.1


From ef92aea82c2dd6fdada254a414eadf9f20b38284 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Wed, 22 Jan 2020 15:07:27 +1100
Subject: [PATCH 19/32] airo: Fix possible info leak in
 AIROOLDIOCTL/SIOCDEVPRIVATE

[ Upstream commit d6bce2137f5d6bb1093e96d2f801479099b28094 ]

The driver for Cisco Aironet 4500 and 4800 series cards (airo.c),
implements AIROOLDIOCTL/SIOCDEVPRIVATE in airo_ioctl().

The ioctl handler copies an aironet_ioctl struct from userspace, which
includes a command and a length. Some of the commands are handled in
readrids(), which kmalloc()'s a buffer of RIDSIZE (2048) bytes.

That buffer is then passed to PC4500_readrid(), which has two cases.
The else case does some setup and then reads up to RIDSIZE bytes from
the hardware into the kmalloc()'ed buffer.

Here len == RIDSIZE, pBuf is the kmalloc()'ed buffer:

	// read the rid length field
	bap_read(ai, pBuf, 2, BAP1);
	// length for remaining part of rid
	len = min(len, (int)le16_to_cpu(*(__le16*)pBuf)) - 2;
	...
	// read remainder of the rid
	rc = bap_read(ai, ((__le16*)pBuf)+1, len, BAP1);

PC4500_readrid() then returns to readrids() which does:

	len = comp->len;
	if (copy_to_user(comp->data, iobuf, min(len, (int)RIDSIZE))) {

Where comp->len is the user controlled length field.

So if the "rid length field" returned by the hardware is < 2048, and
the user requests 2048 bytes in comp->len, we will leak the previous
contents of the kmalloc()'ed buffer to userspace.

Fix it by kzalloc()'ing the buffer.

Found by Ilja by code inspection, not tested as I don't have the
required hardware.

Reported-by: Ilja Van Sprundel <ivansprundel@ioactive.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wireless/cisco/airo.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/cisco/airo.c b/drivers/net/wireless/cisco/airo.c
index f43c06569ea1..d69c2ee7e206 100644
--- a/drivers/net/wireless/cisco/airo.c
+++ b/drivers/net/wireless/cisco/airo.c
@@ -7813,7 +7813,7 @@ static int readrids(struct net_device *dev, aironet_ioctl *comp) {
 		return -EINVAL;
 	}
 
-	if ((iobuf = kmalloc(RIDSIZE, GFP_KERNEL)) == NULL)
+	if ((iobuf = kzalloc(RIDSIZE, GFP_KERNEL)) == NULL)
 		return -ENOMEM;
 
 	PC4500_readrid(ai,ridcode,iobuf,RIDSIZE, 1);
-- 
2.21.1


From e5eed7882572d001f1a90e32280a428d96716f0a Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Wed, 22 Jan 2020 15:07:28 +1100
Subject: [PATCH 20/32] airo: Add missing CAP_NET_ADMIN check in
 AIROOLDIOCTL/SIOCDEVPRIVATE

[ Upstream commit 78f7a7566f5eb59321e99b55a6fdb16ea05b37d1 ]

The driver for Cisco Aironet 4500 and 4800 series cards (airo.c),
implements AIROOLDIOCTL/SIOCDEVPRIVATE in airo_ioctl().

The ioctl handler copies an aironet_ioctl struct from userspace, which
includes a command. Some of the commands are handled in readrids(),
where the user controlled command is converted into a driver-internal
value called "ridcode".

There are two command values, AIROGWEPKTMP and AIROGWEPKNV, which
correspond to ridcode values of RID_WEP_TEMP and RID_WEP_PERM
respectively. These commands both have checks that the user has
CAP_NET_ADMIN, with the comment that "Only super-user can read WEP
keys", otherwise they return -EPERM.

However there is another command value, AIRORRID, that lets the user
specify the ridcode value directly, with no other checks. This means
the user can bypass the CAP_NET_ADMIN check on AIROGWEPKTMP and
AIROGWEPKNV.

Fix it by moving the CAP_NET_ADMIN check out of the command handling
and instead do it later based on the ridcode. That way regardless of
whether the ridcode is set via AIROGWEPKTMP or AIROGWEPKNV, or passed
in using AIRORID, we always do the CAP_NET_ADMIN check.

Found by Ilja by code inspection, not tested as I don't have the
required hardware.

Reported-by: Ilja Van Sprundel <ivansprundel@ioactive.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wireless/cisco/airo.c | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/drivers/net/wireless/cisco/airo.c b/drivers/net/wireless/cisco/airo.c
index d69c2ee7e206..c4c8f1b62e1e 100644
--- a/drivers/net/wireless/cisco/airo.c
+++ b/drivers/net/wireless/cisco/airo.c
@@ -7790,16 +7790,8 @@ static int readrids(struct net_device *dev, aironet_ioctl *comp) {
 	case AIROGVLIST:    ridcode = RID_APLIST;       break;
 	case AIROGDRVNAM:   ridcode = RID_DRVNAME;      break;
 	case AIROGEHTENC:   ridcode = RID_ETHERENCAP;   break;
-	case AIROGWEPKTMP:  ridcode = RID_WEP_TEMP;
-		/* Only super-user can read WEP keys */
-		if (!capable(CAP_NET_ADMIN))
-			return -EPERM;
-		break;
-	case AIROGWEPKNV:   ridcode = RID_WEP_PERM;
-		/* Only super-user can read WEP keys */
-		if (!capable(CAP_NET_ADMIN))
-			return -EPERM;
-		break;
+	case AIROGWEPKTMP:  ridcode = RID_WEP_TEMP;	break;
+	case AIROGWEPKNV:   ridcode = RID_WEP_PERM;	break;
 	case AIROGSTAT:     ridcode = RID_STATUS;       break;
 	case AIROGSTATSD32: ridcode = RID_STATSDELTA;   break;
 	case AIROGSTATSC32: ridcode = RID_STATS;        break;
@@ -7813,6 +7805,12 @@ static int readrids(struct net_device *dev, aironet_ioctl *comp) {
 		return -EINVAL;
 	}
 
+	if (ridcode == RID_WEP_TEMP || ridcode == RID_WEP_PERM) {
+		/* Only super-user can read WEP keys */
+		if (!capable(CAP_NET_ADMIN))
+			return -EPERM;
+	}
+
 	if ((iobuf = kzalloc(RIDSIZE, GFP_KERNEL)) == NULL)
 		return -ENOMEM;
 
-- 
2.21.1


From 035200f52bf191bec439c669a0c0ccb888a663d2 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 22 Jan 2020 20:09:52 +0200
Subject: [PATCH 21/32] mlxsw: spectrum_acl: Fix use-after-free during reload

[ Upstream commit 971de2e572118c1128bff295341e37b6c8b8f108 ]

During reload (or module unload), the router block is de-initialized.
Among other things, this results in the removal of a default multicast
route from each active virtual router (VRF). These default routes are
configured during initialization to trap packets to the CPU. In
Spectrum-2, unlike Spectrum-1, multicast routes are implemented using
ACL rules.

Since the router block is de-initialized before the ACL block, it is
possible that the ACL rules corresponding to the default routes are
deleted while being accessed by the ACL delayed work that queries rules'
activity from the device. This can result in a rare use-after-free [1].

Fix this by protecting the rules list accessed by the delayed work with
a lock. We cannot use a spinlock as the activity read operation is
blocking.

[1]
[  123.331662] ==================================================================
[  123.339920] BUG: KASAN: use-after-free in mlxsw_sp_acl_rule_activity_update_work+0x330/0x3b0
[  123.349381] Read of size 8 at addr ffff8881f3bb4520 by task kworker/0:2/78
[  123.357080]
[  123.358773] CPU: 0 PID: 78 Comm: kworker/0:2 Not tainted 5.5.0-rc5-custom-33108-gf5df95d3ef41 #2209
[  123.368898] Hardware name: Mellanox Technologies Ltd. MSN3700C/VMOD0008, BIOS 5.11 10/10/2018
[  123.378456] Workqueue: mlxsw_core mlxsw_sp_acl_rule_activity_update_work
[  123.385970] Call Trace:
[  123.388734]  dump_stack+0xc6/0x11e
[  123.392568]  print_address_description.constprop.4+0x21/0x340
[  123.403236]  __kasan_report.cold.8+0x76/0xb1
[  123.414884]  kasan_report+0xe/0x20
[  123.418716]  mlxsw_sp_acl_rule_activity_update_work+0x330/0x3b0
[  123.444034]  process_one_work+0xb06/0x19a0
[  123.453731]  worker_thread+0x91/0xe90
[  123.467348]  kthread+0x348/0x410
[  123.476847]  ret_from_fork+0x24/0x30
[  123.480863]
[  123.482545] Allocated by task 73:
[  123.486273]  save_stack+0x19/0x80
[  123.490000]  __kasan_kmalloc.constprop.6+0xc1/0xd0
[  123.495379]  mlxsw_sp_acl_rule_create+0xa7/0x230
[  123.500566]  mlxsw_sp2_mr_tcam_route_create+0xf6/0x3e0
[  123.506334]  mlxsw_sp_mr_tcam_route_create+0x5b4/0x820
[  123.512102]  mlxsw_sp_mr_table_create+0x3b5/0x690
[  123.517389]  mlxsw_sp_vr_get+0x289/0x4d0
[  123.521797]  mlxsw_sp_fib_node_get+0xa2/0x990
[  123.526692]  mlxsw_sp_router_fib4_event_work+0x54c/0x2d60
[  123.532752]  process_one_work+0xb06/0x19a0
[  123.537352]  worker_thread+0x91/0xe90
[  123.541471]  kthread+0x348/0x410
[  123.545103]  ret_from_fork+0x24/0x30
[  123.549113]
[  123.550795] Freed by task 518:
[  123.554231]  save_stack+0x19/0x80
[  123.557958]  __kasan_slab_free+0x125/0x170
[  123.562556]  kfree+0xd7/0x3a0
[  123.565895]  mlxsw_sp_acl_rule_destroy+0x63/0xd0
[  123.571081]  mlxsw_sp2_mr_tcam_route_destroy+0xd5/0x130
[  123.576946]  mlxsw_sp_mr_tcam_route_destroy+0xba/0x260
[  123.582714]  mlxsw_sp_mr_table_destroy+0x1ab/0x290
[  123.588091]  mlxsw_sp_vr_put+0x1db/0x350
[  123.592496]  mlxsw_sp_fib_node_put+0x298/0x4c0
[  123.597486]  mlxsw_sp_vr_fib_flush+0x15b/0x360
[  123.602476]  mlxsw_sp_router_fib_flush+0xba/0x470
[  123.607756]  mlxsw_sp_vrs_fini+0xaa/0x120
[  123.612260]  mlxsw_sp_router_fini+0x137/0x384
[  123.617152]  mlxsw_sp_fini+0x30a/0x4a0
[  123.621374]  mlxsw_core_bus_device_unregister+0x159/0x600
[  123.627435]  mlxsw_devlink_core_bus_device_reload_down+0x7e/0xb0
[  123.634176]  devlink_reload+0xb4/0x380
[  123.638391]  devlink_nl_cmd_reload+0x610/0x700
[  123.643382]  genl_rcv_msg+0x6a8/0xdc0
[  123.647497]  netlink_rcv_skb+0x134/0x3a0
[  123.651904]  genl_rcv+0x29/0x40
[  123.655436]  netlink_unicast+0x4d4/0x700
[  123.659843]  netlink_sendmsg+0x7c0/0xc70
[  123.664251]  __sys_sendto+0x265/0x3c0
[  123.668367]  __x64_sys_sendto+0xe2/0x1b0
[  123.672773]  do_syscall_64+0xa0/0x530
[  123.676892]  entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  123.682552]
[  123.684238] The buggy address belongs to the object at ffff8881f3bb4500
[  123.684238]  which belongs to the cache kmalloc-128 of size 128
[  123.698261] The buggy address is located 32 bytes inside of
[  123.698261]  128-byte region [ffff8881f3bb4500, ffff8881f3bb4580)
[  123.711303] The buggy address belongs to the page:
[  123.716682] page:ffffea0007ceed00 refcount:1 mapcount:0 mapping:ffff888236403500 index:0x0
[  123.725958] raw: 0200000000000200 dead000000000100 dead000000000122 ffff888236403500
[  123.734646] raw: 0000000000000000 0000000000100010 00000001ffffffff 0000000000000000
[  123.743315] page dumped because: kasan: bad access detected
[  123.749562]
[  123.751241] Memory state around the buggy address:
[  123.756620]  ffff8881f3bb4400: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[  123.764716]  ffff8881f3bb4480: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[  123.772812] >ffff8881f3bb4500: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  123.780904]                                ^
[  123.785697]  ffff8881f3bb4580: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[  123.793793]  ffff8881f3bb4600: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[  123.801883] ==================================================================

Fixes: cf7221a4f5a5 ("mlxsw: spectrum_router: Add Multicast routing support for Spectrum-2")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_acl.c   | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index 150b3a144b83..3d3cca596116 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -8,6 +8,7 @@
 #include <linux/string.h>
 #include <linux/rhashtable.h>
 #include <linux/netdevice.h>
+#include <linux/mutex.h>
 #include <net/net_namespace.h>
 #include <net/tc_act/tc_vlan.h>
 
@@ -25,6 +26,7 @@ struct mlxsw_sp_acl {
 	struct mlxsw_sp_fid *dummy_fid;
 	struct rhashtable ruleset_ht;
 	struct list_head rules;
+	struct mutex rules_lock; /* Protects rules list */
 	struct {
 		struct delayed_work dw;
 		unsigned long interval;	/* ms */
@@ -701,7 +703,9 @@ int mlxsw_sp_acl_rule_add(struct mlxsw_sp *mlxsw_sp,
 			goto err_ruleset_block_bind;
 	}
 
+	mutex_lock(&mlxsw_sp->acl->rules_lock);
 	list_add_tail(&rule->list, &mlxsw_sp->acl->rules);
+	mutex_unlock(&mlxsw_sp->acl->rules_lock);
 	block->rule_count++;
 	block->egress_blocker_rule_count += rule->rulei->egress_bind_blocker;
 	return 0;
@@ -723,7 +727,9 @@ void mlxsw_sp_acl_rule_del(struct mlxsw_sp *mlxsw_sp,
 
 	block->egress_blocker_rule_count -= rule->rulei->egress_bind_blocker;
 	ruleset->ht_key.block->rule_count--;
+	mutex_lock(&mlxsw_sp->acl->rules_lock);
 	list_del(&rule->list);
+	mutex_unlock(&mlxsw_sp->acl->rules_lock);
 	if (!ruleset->ht_key.chain_index &&
 	    mlxsw_sp_acl_ruleset_is_singular(ruleset))
 		mlxsw_sp_acl_ruleset_block_unbind(mlxsw_sp, ruleset,
@@ -783,19 +789,18 @@ static int mlxsw_sp_acl_rules_activity_update(struct mlxsw_sp_acl *acl)
 	struct mlxsw_sp_acl_rule *rule;
 	int err;
 
-	/* Protect internal structures from changes */
-	rtnl_lock();
+	mutex_lock(&acl->rules_lock);
 	list_for_each_entry(rule, &acl->rules, list) {
 		err = mlxsw_sp_acl_rule_activity_update(acl->mlxsw_sp,
 							rule);
 		if (err)
 			goto err_rule_update;
 	}
-	rtnl_unlock();
+	mutex_unlock(&acl->rules_lock);
 	return 0;
 
 err_rule_update:
-	rtnl_unlock();
+	mutex_unlock(&acl->rules_lock);
 	return err;
 }
 
@@ -880,6 +885,7 @@ int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp)
 	acl->dummy_fid = fid;
 
 	INIT_LIST_HEAD(&acl->rules);
+	mutex_init(&acl->rules_lock);
 	err = mlxsw_sp_acl_tcam_init(mlxsw_sp, &acl->tcam);
 	if (err)
 		goto err_acl_ops_init;
@@ -892,6 +898,7 @@ int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp)
 	return 0;
 
 err_acl_ops_init:
+	mutex_destroy(&acl->rules_lock);
 	mlxsw_sp_fid_put(fid);
 err_fid_get:
 	rhashtable_destroy(&acl->ruleset_ht);
@@ -908,6 +915,7 @@ void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp)
 
 	cancel_delayed_work_sync(&mlxsw_sp->acl->rule_activity_update.dw);
 	mlxsw_sp_acl_tcam_fini(mlxsw_sp, &acl->tcam);
+	mutex_destroy(&acl->rules_lock);
 	WARN_ON(!list_empty(&acl->rules));
 	mlxsw_sp_fid_put(acl->dummy_fid);
 	rhashtable_destroy(&acl->ruleset_ht);
-- 
2.21.1


From a769900b3fd4c9ca557e002f5d0793b672037e45 Mon Sep 17 00:00:00 2001
From: Kristian Evensen <kristian.evensen@gmail.com>
Date: Thu, 23 Jan 2020 13:20:18 +0100
Subject: [PATCH 22/32] fou: Fix IPv6 netlink policy

[ Upstream commit bb48eb9b12a95db9d679025927269d4adda6dbd1 ]

When submitting v2 of "fou: Support binding FoU socket" (1713cb37bf67),
I accidentally sent the wrong version of the patch and one fix was
missing. In the initial version of the patch, as well as the version 2
that I submitted, I incorrectly used ".type" for the two V6-attributes.
The correct is to use ".len".

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Fixes: 1713cb37bf67 ("fou: Support binding FoU socket")
Signed-off-by: Kristian Evensen <kristian.evensen@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fou.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 30fa771d382a..dcc79ff54b41 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -662,8 +662,8 @@ static const struct nla_policy fou_nl_policy[FOU_ATTR_MAX + 1] = {
 	[FOU_ATTR_REMCSUM_NOPARTIAL]	= { .type = NLA_FLAG, },
 	[FOU_ATTR_LOCAL_V4]		= { .type = NLA_U32, },
 	[FOU_ATTR_PEER_V4]		= { .type = NLA_U32, },
-	[FOU_ATTR_LOCAL_V6]		= { .type = sizeof(struct in6_addr), },
-	[FOU_ATTR_PEER_V6]		= { .type = sizeof(struct in6_addr), },
+	[FOU_ATTR_LOCAL_V6]		= { .len = sizeof(struct in6_addr), },
+	[FOU_ATTR_PEER_V6]		= { .len = sizeof(struct in6_addr), },
 	[FOU_ATTR_PEER_PORT]		= { .type = NLA_U16, },
 	[FOU_ATTR_IFINDEX]		= { .type = NLA_S32, },
 };
-- 
2.21.1


From ef1f161a3f0dbe3c5209061e4240cd3515143194 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Tue, 21 Jan 2020 15:09:40 +0000
Subject: [PATCH 23/32] net: Fix packet reordering caused by GRO and listified
 RX cooperation

[ Upstream commit c80794323e82ac6ab45052ebba5757ce47b4b588 ]

Commit 323ebb61e32b ("net: use listified RX for handling GRO_NORMAL
skbs") introduces batching of GRO_NORMAL packets in napi_frags_finish,
and commit 6570bc79c0df ("net: core: use listified Rx for GRO_NORMAL in
napi_gro_receive()") adds the same to napi_skb_finish. However,
dev_gro_receive (that is called just before napi_{frags,skb}_finish) can
also pass skbs to the networking stack: e.g., when the GRO session is
flushed, napi_gro_complete is called, which passes pp directly to
netif_receive_skb_internal, skipping napi->rx_list. It means that the
packet stored in pp will be handled by the stack earlier than the
packets that arrived before, but are still waiting in napi->rx_list. It
leads to TCP reorderings that can be observed in the TCPOFOQueue counter
in netstat.

This commit fixes the reordering issue by making napi_gro_complete also
use napi->rx_list, so that all packets going through GRO will keep their
order. In order to keep napi_gro_flush working properly, gro_normal_list
calls are moved after the flush to clear napi->rx_list.

iwlwifi calls napi_gro_flush directly and does the same thing that is
done by gro_normal_list, so the same change is applied there:
napi_gro_flush is moved to be before the flush of napi->rx_list.

A few other drivers also use napi_gro_flush (brocade/bna/bnad.c,
cortina/gemini.c, hisilicon/hns3/hns3_enet.c). The first two also use
napi_complete_done afterwards, which performs the gro_normal_list flush,
so they are fine. The latter calls napi_gro_receive right after
napi_gro_flush, so it can end up with non-empty napi->rx_list anyway.

Fixes: 323ebb61e32b ("net: use listified RX for handling GRO_NORMAL skbs")
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Cc: Alexander Lobakin <alobakin@dlink.ru>
Cc: Edward Cree <ecree@solarflare.com>
Acked-by: Alexander Lobakin <alobakin@dlink.ru>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Acked-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wireless/intel/iwlwifi/pcie/rx.c |  4 +-
 net/core/dev.c                               | 64 ++++++++++----------
 2 files changed, 35 insertions(+), 33 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
index 041dd75ac72b..64c74acadb99 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
@@ -1537,13 +1537,13 @@ static void iwl_pcie_rx_handle(struct iwl_trans *trans, int queue)
 
 	napi = &rxq->napi;
 	if (napi->poll) {
+		napi_gro_flush(napi, false);
+
 		if (napi->rx_count) {
 			netif_receive_skb_list(&napi->rx_list);
 			INIT_LIST_HEAD(&napi->rx_list);
 			napi->rx_count = 0;
 		}
-
-		napi_gro_flush(napi, false);
 	}
 
 	iwl_pcie_rxq_restock(trans, rxq);
diff --git a/net/core/dev.c b/net/core/dev.c
index af6ee5ff4fda..82325d3d1371 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5270,9 +5270,29 @@ static void flush_all_backlogs(void)
 	put_online_cpus();
 }
 
+/* Pass the currently batched GRO_NORMAL SKBs up to the stack. */
+static void gro_normal_list(struct napi_struct *napi)
+{
+	if (!napi->rx_count)
+		return;
+	netif_receive_skb_list_internal(&napi->rx_list);
+	INIT_LIST_HEAD(&napi->rx_list);
+	napi->rx_count = 0;
+}
+
+/* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded,
+ * pass the whole batch up to the stack.
+ */
+static void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb)
+{
+	list_add_tail(&skb->list, &napi->rx_list);
+	if (++napi->rx_count >= gro_normal_batch)
+		gro_normal_list(napi);
+}
+
 INDIRECT_CALLABLE_DECLARE(int inet_gro_complete(struct sk_buff *, int));
 INDIRECT_CALLABLE_DECLARE(int ipv6_gro_complete(struct sk_buff *, int));
-static int napi_gro_complete(struct sk_buff *skb)
+static int napi_gro_complete(struct napi_struct *napi, struct sk_buff *skb)
 {
 	struct packet_offload *ptype;
 	__be16 type = skb->protocol;
@@ -5305,7 +5325,8 @@ static int napi_gro_complete(struct sk_buff *skb)
 	}
 
 out:
-	return netif_receive_skb_internal(skb);
+	gro_normal_one(napi, skb);
+	return NET_RX_SUCCESS;
 }
 
 static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index,
@@ -5318,7 +5339,7 @@ static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index,
 		if (flush_old && NAPI_GRO_CB(skb)->age == jiffies)
 			return;
 		skb_list_del_init(skb);
-		napi_gro_complete(skb);
+		napi_gro_complete(napi, skb);
 		napi->gro_hash[index].count--;
 	}
 
@@ -5421,7 +5442,7 @@ static void gro_pull_from_frag0(struct sk_buff *skb, int grow)
 	}
 }
 
-static void gro_flush_oldest(struct list_head *head)
+static void gro_flush_oldest(struct napi_struct *napi, struct list_head *head)
 {
 	struct sk_buff *oldest;
 
@@ -5437,7 +5458,7 @@ static void gro_flush_oldest(struct list_head *head)
 	 * SKB to the chain.
 	 */
 	skb_list_del_init(oldest);
-	napi_gro_complete(oldest);
+	napi_gro_complete(napi, oldest);
 }
 
 INDIRECT_CALLABLE_DECLARE(struct sk_buff *inet_gro_receive(struct list_head *,
@@ -5513,7 +5534,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 
 	if (pp) {
 		skb_list_del_init(pp);
-		napi_gro_complete(pp);
+		napi_gro_complete(napi, pp);
 		napi->gro_hash[hash].count--;
 	}
 
@@ -5524,7 +5545,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 		goto normal;
 
 	if (unlikely(napi->gro_hash[hash].count >= MAX_GRO_SKBS)) {
-		gro_flush_oldest(gro_head);
+		gro_flush_oldest(napi, gro_head);
 	} else {
 		napi->gro_hash[hash].count++;
 	}
@@ -5672,26 +5693,6 @@ struct sk_buff *napi_get_frags(struct napi_struct *napi)
 }
 EXPORT_SYMBOL(napi_get_frags);
 
-/* Pass the currently batched GRO_NORMAL SKBs up to the stack. */
-static void gro_normal_list(struct napi_struct *napi)
-{
-	if (!napi->rx_count)
-		return;
-	netif_receive_skb_list_internal(&napi->rx_list);
-	INIT_LIST_HEAD(&napi->rx_list);
-	napi->rx_count = 0;
-}
-
-/* Queue one GRO_NORMAL SKB up for list processing.  If batch size exceeded,
- * pass the whole batch up to the stack.
- */
-static void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb)
-{
-	list_add_tail(&skb->list, &napi->rx_list);
-	if (++napi->rx_count >= gro_normal_batch)
-		gro_normal_list(napi);
-}
-
 static gro_result_t napi_frags_finish(struct napi_struct *napi,
 				      struct sk_buff *skb,
 				      gro_result_t ret)
@@ -5979,8 +5980,6 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 				 NAPIF_STATE_IN_BUSY_POLL)))
 		return false;
 
-	gro_normal_list(n);
-
 	if (n->gro_bitmask) {
 		unsigned long timeout = 0;
 
@@ -5996,6 +5995,9 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 			hrtimer_start(&n->timer, ns_to_ktime(timeout),
 				      HRTIMER_MODE_REL_PINNED);
 	}
+
+	gro_normal_list(n);
+
 	if (unlikely(!list_empty(&n->poll_list))) {
 		/* If n->poll_list is not empty, we need to mask irqs */
 		local_irq_save(flags);
@@ -6327,8 +6329,6 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll)
 		goto out_unlock;
 	}
 
-	gro_normal_list(n);
-
 	if (n->gro_bitmask) {
 		/* flush too old packets
 		 * If HZ < 1000, flush all packets.
@@ -6336,6 +6336,8 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll)
 		napi_gro_flush(n, HZ >= 1000);
 	}
 
+	gro_normal_list(n);
+
 	/* Some drivers may have called napi_schedule
 	 * prior to exhausting their budget.
 	 */
-- 
2.21.1


From c5f4090334dc633c0aa6143fa1e3a81794056d56 Mon Sep 17 00:00:00 2001
From: Paul Blakey <paulb@mellanox.com>
Date: Tue, 31 Dec 2019 17:04:15 +0200
Subject: [PATCH 24/32] net/mlx5: Fix lowest FDB pool size

The pool sizes represent the pool sizes in the fw. when we request
a pool size from fw, it will return the next possible group.
We track how many pools the fw has left and start requesting groups
from the big to the small.
When we start request 4k group, which doesn't exists in fw, fw
wants to allocate the next possible size, 64k, but will fail since
its exhausted. The correct smallest pool size in fw is 128 and not 4k.

Fixes: e52c28024008 ("net/mlx5: E-Switch, Add chains and priorities")
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 9004a07e457a..5acfdea3a75a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -858,7 +858,7 @@ static int esw_add_fdb_miss_rule(struct mlx5_eswitch *esw)
  */
 #define ESW_SIZE (16 * 1024 * 1024)
 const unsigned int ESW_POOLS[4] = { 4 * 1024 * 1024, 1 * 1024 * 1024,
-				    64 * 1024, 4 * 1024 };
+				    64 * 1024, 128 };
 
 static int
 get_sz_from_pool(struct mlx5_eswitch *esw)
-- 
2.21.1


From 2eac4544256304c6aa99d85970996d1f9a452bd3 Mon Sep 17 00:00:00 2001
From: Meir Lichtinger <meirl@mellanox.com>
Date: Thu, 12 Dec 2019 16:09:33 +0200
Subject: [PATCH 25/32] net/mlx5: Update the list of the PCI supported devices

Add the upcoming ConnectX-7 device ID.

Fixes: 85327a9c4150 ("net/mlx5: Update the list of the PCI supported devices")
Signed-off-by: Meir Lichtinger <meirl@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 051ab845b501..c96a0e501007 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1569,6 +1569,7 @@ static const struct pci_device_id mlx5_core_pci_table[] = {
 	{ PCI_VDEVICE(MELLANOX, 0x101d) },			/* ConnectX-6 Dx */
 	{ PCI_VDEVICE(MELLANOX, 0x101e), MLX5_PCI_DEV_IS_VF},	/* ConnectX Family mlx5Gen Virtual Function */
 	{ PCI_VDEVICE(MELLANOX, 0x101f) },			/* ConnectX-6 LX */
+	{ PCI_VDEVICE(MELLANOX, 0x1021) },			/* ConnectX-7 */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d2) },			/* BlueField integrated ConnectX-5 network controller */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d3), MLX5_PCI_DEV_IS_VF},	/* BlueField integrated ConnectX-5 network controller VF */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d6) },			/* BlueField-2 integrated ConnectX-6 Dx network controller */
-- 
2.21.1


From a10cb0cdbf19fb28c08ad4194da5f2fb1fdfb6db Mon Sep 17 00:00:00 2001
From: Erez Shitrit <erezsh@mellanox.com>
Date: Wed, 8 Jan 2020 14:17:32 +0200
Subject: [PATCH 26/32] net/mlx5: DR, Enable counter on non-fwd-dest objects

The current code handles only counters that attached to dest, we still
have the cases where we have counter on non-dest, like over drop etc.

Fixes: 6a48faeeca10 ("net/mlx5: Add direct rule fs_cmd implementation")
Signed-off-by: Hamdan Igbaria <hamdani@mellanox.com>
Signed-off-by: Erez Shitrit <erezsh@mellanox.com>
Reviewed-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../mellanox/mlx5/core/steering/fs_dr.c       | 42 +++++++++++++------
 1 file changed, 29 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
index 3d587d0bdbbe..1e32e2443f73 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
@@ -352,26 +352,16 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
 	if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
 		list_for_each_entry(dst, &fte->node.children, node.list) {
 			enum mlx5_flow_destination_type type = dst->dest_attr.type;
-			u32 id;
 
 			if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) {
 				err = -ENOSPC;
 				goto free_actions;
 			}
 
-			switch (type) {
-			case MLX5_FLOW_DESTINATION_TYPE_COUNTER:
-				id = dst->dest_attr.counter_id;
+			if (type == MLX5_FLOW_DESTINATION_TYPE_COUNTER)
+				continue;
 
-				tmp_action =
-					mlx5dr_action_create_flow_counter(id);
-				if (!tmp_action) {
-					err = -ENOMEM;
-					goto free_actions;
-				}
-				fs_dr_actions[fs_dr_num_actions++] = tmp_action;
-				actions[num_actions++] = tmp_action;
-				break;
+			switch (type) {
 			case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE:
 				tmp_action = create_ft_action(dev, dst);
 				if (!tmp_action) {
@@ -397,6 +387,32 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
 		}
 	}
 
+	if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
+		list_for_each_entry(dst, &fte->node.children, node.list) {
+			u32 id;
+
+			if (dst->dest_attr.type !=
+			    MLX5_FLOW_DESTINATION_TYPE_COUNTER)
+				continue;
+
+			if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) {
+				err = -ENOSPC;
+				goto free_actions;
+			}
+
+			id = dst->dest_attr.counter_id;
+			tmp_action =
+				mlx5dr_action_create_flow_counter(id);
+			if (!tmp_action) {
+				err = -ENOMEM;
+				goto free_actions;
+			}
+
+			fs_dr_actions[fs_dr_num_actions++] = tmp_action;
+			actions[num_actions++] = tmp_action;
+		}
+	}
+
 	params.match_sz = match_sz;
 	params.match_buf = (u64 *)fte->val;
 
-- 
2.21.1


From ee1905a2ded1d59d4eaaec46f08ed5cbd85425a6 Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.com>
Date: Sun, 12 Jan 2020 13:43:37 +0200
Subject: [PATCH 27/32] net/mlx5: E-Switch, Prevent ingress rate configuration
 of uplink rep

Since the implementation relies on limiting the VF transmit rate to
simulate ingress rate limiting, and since either uplink representor or
ecpf are not associated with a VF, we limit the rate limit configuration
for those ports.

Fixes: fcb64c0f5640 ("net/mlx5: E-Switch, add ingress rate support")
Signed-off-by: Eli Cohen <eli@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 96711e34d248..1f9107d83848 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -3951,6 +3951,13 @@ static int apply_police_params(struct mlx5e_priv *priv, u32 rate,
 	u32 rate_mbps;
 	int err;
 
+	vport_num = rpriv->rep->vport;
+	if (vport_num >= MLX5_VPORT_ECPF) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Ingress rate limit is supported only for Eswitch ports connected to VFs");
+		return -EOPNOTSUPP;
+	}
+
 	esw = priv->mdev->priv.eswitch;
 	/* rate is given in bytes/sec.
 	 * First convert to bits/sec and then round to the nearest mbit/secs.
@@ -3959,8 +3966,6 @@ static int apply_police_params(struct mlx5e_priv *priv, u32 rate,
 	 * 1 mbit/sec.
 	 */
 	rate_mbps = rate ? max_t(u32, (rate * 8 + 500000) / 1000000, 1) : 0;
-	vport_num = rpriv->rep->vport;
-
 	err = mlx5_esw_modify_vport_rate(esw, vport_num, rate_mbps);
 	if (err)
 		NL_SET_ERR_MSG_MOD(extack, "failed applying action to hardware");
-- 
2.21.1


From f0f2720dc4b233c24417cd8db6d6c23522b71c89 Mon Sep 17 00:00:00 2001
From: Erez Shitrit <erezsh@mellanox.com>
Date: Sun, 12 Jan 2020 08:57:59 +0200
Subject: [PATCH 28/32] net/mlx5: DR, use non preemptible call to get the
 current cpu number

Use raw_smp_processor_id instead of smp_processor_id() otherwise we will
get the following trace in debug-kernel:
	BUG: using smp_processor_id() in preemptible [00000000] code: devlink
	caller is dr_create_cq.constprop.2+0x31d/0x970 [mlx5_core]
	Call Trace:
	dump_stack+0x9a/0xf0
	debug_smp_processor_id+0x1f3/0x200
	dr_create_cq.constprop.2+0x31d/0x970
	genl_family_rcv_msg+0x5fd/0x1170
	genl_rcv_msg+0xb8/0x160
	netlink_rcv_skb+0x11e/0x340

Fixes: 297cccebdc5a ("net/mlx5: DR, Expose an internal API to issue RDMA operations")
Signed-off-by: Erez Shitrit <erezsh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
index 51803eef13dd..c7f10d4f8f8d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
 /* Copyright (c) 2019 Mellanox Technologies. */
 
+#include <linux/smp.h>
 #include "dr_types.h"
 
 #define QUEUE_SIZE 128
@@ -729,7 +730,7 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev,
 	if (!in)
 		goto err_cqwq;
 
-	vector = smp_processor_id() % mlx5_comp_vectors_count(mdev);
+	vector = raw_smp_processor_id() % mlx5_comp_vectors_count(mdev);
 	err = mlx5_vector2eqn(mdev, vector, &eqn, &irqn);
 	if (err) {
 		kvfree(in);
-- 
2.21.1


From 68dbd2ddf643affe4372755d9a6b0989ca7c2646 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Sun, 12 Jan 2020 16:22:14 +0200
Subject: [PATCH 29/32] net/mlx5e: kTLS, Fix corner-case checks in TX resync
 flow

There are the following cases:

1. Packet ends before start marker: bypass offload.
2. Packet starts before start marker and ends after it: drop,
   not supported, breaks contract with kernel.
3. packet ends before tls record info starts: drop,
   this packet was already acknowledged and its record info
   was released.

Add the above as comment in code.

Mind possible wraparounds of the TCP seq, replace the simple comparison
with a call to the TCP before() method.

In addition, remove logic that handles negative sync_len values,
as it became impossible.

Fixes: d2ead1f360e8 ("net/mlx5e: Add kTLS TX HW offload support")
Fixes: 46a3ea98074e ("net/mlx5e: kTLS, Enhance TX resync flow")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Reviewed-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../mellanox/mlx5/core/en_accel/ktls_tx.c     | 33 +++++++++++--------
 1 file changed, 19 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
index 778dab1af8fc..8dbb92176bd7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
@@ -180,7 +180,7 @@ mlx5e_ktls_tx_post_param_wqes(struct mlx5e_txqsq *sq,
 
 struct tx_sync_info {
 	u64 rcd_sn;
-	s32 sync_len;
+	u32 sync_len;
 	int nr_frags;
 	skb_frag_t frags[MAX_SKB_FRAGS];
 };
@@ -193,13 +193,14 @@ enum mlx5e_ktls_sync_retval {
 
 static enum mlx5e_ktls_sync_retval
 tx_sync_info_get(struct mlx5e_ktls_offload_context_tx *priv_tx,
-		 u32 tcp_seq, struct tx_sync_info *info)
+		 u32 tcp_seq, int datalen, struct tx_sync_info *info)
 {
 	struct tls_offload_context_tx *tx_ctx = priv_tx->tx_ctx;
 	enum mlx5e_ktls_sync_retval ret = MLX5E_KTLS_SYNC_DONE;
 	struct tls_record_info *record;
 	int remaining, i = 0;
 	unsigned long flags;
+	bool ends_before;
 
 	spin_lock_irqsave(&tx_ctx->lock, flags);
 	record = tls_get_record(tx_ctx, tcp_seq, &info->rcd_sn);
@@ -209,9 +210,21 @@ tx_sync_info_get(struct mlx5e_ktls_offload_context_tx *priv_tx,
 		goto out;
 	}
 
-	if (unlikely(tcp_seq < tls_record_start_seq(record))) {
-		ret = tls_record_is_start_marker(record) ?
-			MLX5E_KTLS_SYNC_SKIP_NO_DATA : MLX5E_KTLS_SYNC_FAIL;
+	/* There are the following cases:
+	 * 1. packet ends before start marker: bypass offload.
+	 * 2. packet starts before start marker and ends after it: drop,
+	 *    not supported, breaks contract with kernel.
+	 * 3. packet ends before tls record info starts: drop,
+	 *    this packet was already acknowledged and its record info
+	 *    was released.
+	 */
+	ends_before = before(tcp_seq + datalen, tls_record_start_seq(record));
+
+	if (unlikely(tls_record_is_start_marker(record))) {
+		ret = ends_before ? MLX5E_KTLS_SYNC_SKIP_NO_DATA : MLX5E_KTLS_SYNC_FAIL;
+		goto out;
+	} else if (ends_before) {
+		ret = MLX5E_KTLS_SYNC_FAIL;
 		goto out;
 	}
 
@@ -337,7 +350,7 @@ mlx5e_ktls_tx_handle_ooo(struct mlx5e_ktls_offload_context_tx *priv_tx,
 	u8 num_wqebbs;
 	int i = 0;
 
-	ret = tx_sync_info_get(priv_tx, seq, &info);
+	ret = tx_sync_info_get(priv_tx, seq, datalen, &info);
 	if (unlikely(ret != MLX5E_KTLS_SYNC_DONE)) {
 		if (ret == MLX5E_KTLS_SYNC_SKIP_NO_DATA) {
 			stats->tls_skip_no_sync_data++;
@@ -351,14 +364,6 @@ mlx5e_ktls_tx_handle_ooo(struct mlx5e_ktls_offload_context_tx *priv_tx,
 		goto err_out;
 	}
 
-	if (unlikely(info.sync_len < 0)) {
-		if (likely(datalen <= -info.sync_len))
-			return MLX5E_KTLS_SYNC_DONE;
-
-		stats->tls_drop_bypass_req++;
-		goto err_out;
-	}
-
 	stats->tls_ooo++;
 
 	tx_post_resync_params(sq, priv_tx, info.rcd_sn);
-- 
2.21.1


From 177c2d8f9f3a196003f821bb8adf988af77ece6b Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Mon, 13 Jan 2020 14:46:09 +0200
Subject: [PATCH 30/32] net/mlx5e: kTLS, Remove redundant posts in TX resync
 flow

The call to tx_post_resync_params() is done earlier in the flow,
the post of the control WQEs is unnecessarily repeated. Remove it.

Fixes: 700ec4974240 ("net/mlx5e: kTLS, Fix missing SQ edge fill")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Reviewed-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
index 8dbb92176bd7..592e921aa167 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
@@ -383,8 +383,6 @@ mlx5e_ktls_tx_handle_ooo(struct mlx5e_ktls_offload_context_tx *priv_tx,
 	if (unlikely(contig_wqebbs_room < num_wqebbs))
 		mlx5e_fill_sq_frag_edge(sq, wq, pi, contig_wqebbs_room);
 
-	tx_post_resync_params(sq, priv_tx, info.rcd_sn);
-
 	for (; i < info.nr_frags; i++) {
 		unsigned int orig_fsz, frag_offset = 0, n = 0;
 		skb_frag_t *f = &info.frags[i];
-- 
2.21.1


From 9a0a9e585210bef20212ad99b852b963ffd1b4ca Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Mon, 20 Jan 2020 13:42:00 +0200
Subject: [PATCH 31/32] net/mlx5e: kTLS, Do not send decrypted-marked SKBs via
 non-accel path

When TCP out-of-order is identified (unexpected tcp seq mismatch), driver
analyzes the packet and decides what handling should it get:
1. go to accelerated path (to be encrypted in HW),
2. go to regular xmit path (send w/o encryption),
3. drop.

Packets marked with skb->decrypted by the TLS stack in the TX flow skips
SW encryption, and rely on the HW offload.
Verify that such packets are never sent un-encrypted on the wire.
Add a WARN to catch such bugs, and prefer dropping the packet in these cases.

Fixes: 46a3ea98074e ("net/mlx5e: kTLS, Enhance TX resync flow")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Reviewed-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
index 592e921aa167..f260dd96873b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
@@ -458,12 +458,18 @@ struct sk_buff *mlx5e_ktls_handle_tx_skb(struct net_device *netdev,
 		enum mlx5e_ktls_sync_retval ret =
 			mlx5e_ktls_tx_handle_ooo(priv_tx, sq, datalen, seq);
 
-		if (likely(ret == MLX5E_KTLS_SYNC_DONE))
+		switch (ret) {
+		case MLX5E_KTLS_SYNC_DONE:
 			*wqe = mlx5e_sq_fetch_wqe(sq, sizeof(**wqe), pi);
-		else if (ret == MLX5E_KTLS_SYNC_FAIL)
+			break;
+		case MLX5E_KTLS_SYNC_SKIP_NO_DATA:
+			if (likely(!skb->decrypted))
+				goto out;
+			WARN_ON_ONCE(1);
+			/* fall-through */
+		default: /* MLX5E_KTLS_SYNC_FAIL */
 			goto err_out;
-		else /* ret == MLX5E_KTLS_SYNC_SKIP_NO_DATA */
-			goto out;
+		}
 	}
 
 	priv_tx->expected_seq = seq + datalen;
-- 
2.21.1


From 1564b3be0a4445086751842a7bbc18ab403eb90a Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Fri, 10 Jan 2020 09:03:58 -0800
Subject: [PATCH 32/32] ipv4: Detect rollover in specific fib table dump

[ Upstream commit 9827c0634e461703abf81e8cc8b7adf5da5886d0 ]

Sven-Haegar reported looping on fib dumps when 255.255.255.255 route has
been added to a table. The looping is caused by the key rolling over from
FFFFFFFF to 0. When dumping a specific table only, we need a means to detect
when the table dump is done. The key and count saved to cb args are both 0
only at the start of the table dump. If key is 0 and count > 0, then we are
in the rollover case. Detect and return to avoid looping.

This only affects dumps of a specific table; for dumps of all tables
(the case prior to the change in the Fixes tag) inet_dump_fib moved
the entry counter to the next table and reset the cb args used by
fib_table_dump and fn_trie_dump_leaf, so the rollover ffffffff back
to 0 did not cause looping with the dumps.

Fixes: effe67926624 ("net: Enable kernel side filtering of route dumps")
Reported-by: Sven-Haegar Koch <haegar@sdinet.de>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_trie.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 1ab2fb6bb37d..f12fa8da6127 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -2175,6 +2175,12 @@ int fib_table_dump(struct fib_table *tb, struct sk_buff *skb,
 	int count = cb->args[2];
 	t_key key = cb->args[3];
 
+	/* First time here, count and key are both always 0. Count > 0
+	 * and key == 0 means the dump has wrapped around and we are done.
+	 */
+	if (count && !key)
+		return skb->len;
+
 	while ((l = leaf_walk_rcu(&tp, key)) != NULL) {
 		int err;
 
-- 
2.21.1

Re: [PATCHES] Networking

[Greg KH]

On Mon, Jan 27, 2020 at 12:16:17PM +0100, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v4.19
> and v5.4 -stable, respectively.

All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 105 bytes --]


Please queue up the following networking bug fixes for v5.4 and v5.5
-stable, respectively.

Thank you!

[-- Attachment #2: net_54.mbox --]
[-- Type: Application/Octet-Stream, Size: 32558 bytes --]

From e96c428e336cf2abef7c8ff64947c7a4a1d58140 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 24 Jan 2020 14:57:20 -0800
Subject: [PATCH 1/9] net_sched: ematch: reject invalid TCF_EM_SIMPLE

[ Upstream commit 55cd9f67f1e45de8517cdaab985fb8e56c0bc1d8 ]

It is possible for malicious userspace to set TCF_EM_SIMPLE bit
even for matches that should not have this bit set.

This can fool two places using tcf_em_is_simple()

1) tcf_em_tree_destroy() -> memory leak of em->data
   if ops->destroy() is NULL

2) tcf_em_tree_dump() wrongly report/leak 4 low-order bytes
   of a kernel pointer.

BUG: memory leak
unreferenced object 0xffff888121850a40 (size 32):
  comm "syz-executor927", pid 7193, jiffies 4294941655 (age 19.840s)
  hex dump (first 32 bytes):
    00 00 00 00 01 00 00 00 00 00 00 00 00 00 00 00  ................
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<00000000f67036ea>] kmemleak_alloc_recursive include/linux/kmemleak.h:43 [inline]
    [<00000000f67036ea>] slab_post_alloc_hook mm/slab.h:586 [inline]
    [<00000000f67036ea>] slab_alloc mm/slab.c:3320 [inline]
    [<00000000f67036ea>] __do_kmalloc mm/slab.c:3654 [inline]
    [<00000000f67036ea>] __kmalloc_track_caller+0x165/0x300 mm/slab.c:3671
    [<00000000fab0cc8e>] kmemdup+0x27/0x60 mm/util.c:127
    [<00000000d9992e0a>] kmemdup include/linux/string.h:453 [inline]
    [<00000000d9992e0a>] em_nbyte_change+0x5b/0x90 net/sched/em_nbyte.c:32
    [<000000007e04f711>] tcf_em_validate net/sched/ematch.c:241 [inline]
    [<000000007e04f711>] tcf_em_tree_validate net/sched/ematch.c:359 [inline]
    [<000000007e04f711>] tcf_em_tree_validate+0x332/0x46f net/sched/ematch.c:300
    [<000000007a769204>] basic_set_parms net/sched/cls_basic.c:157 [inline]
    [<000000007a769204>] basic_change+0x1d7/0x5f0 net/sched/cls_basic.c:219
    [<00000000e57a5997>] tc_new_tfilter+0x566/0xf70 net/sched/cls_api.c:2104
    [<0000000074b68559>] rtnetlink_rcv_msg+0x3b2/0x4b0 net/core/rtnetlink.c:5415
    [<00000000b7fe53fb>] netlink_rcv_skb+0x61/0x170 net/netlink/af_netlink.c:2477
    [<00000000e83a40d0>] rtnetlink_rcv+0x1d/0x30 net/core/rtnetlink.c:5442
    [<00000000d62ba933>] netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
    [<00000000d62ba933>] netlink_unicast+0x223/0x310 net/netlink/af_netlink.c:1328
    [<0000000088070f72>] netlink_sendmsg+0x2c0/0x570 net/netlink/af_netlink.c:1917
    [<00000000f70b15ea>] sock_sendmsg_nosec net/socket.c:639 [inline]
    [<00000000f70b15ea>] sock_sendmsg+0x54/0x70 net/socket.c:659
    [<00000000ef95a9be>] ____sys_sendmsg+0x2d0/0x300 net/socket.c:2330
    [<00000000b650f1ab>] ___sys_sendmsg+0x8a/0xd0 net/socket.c:2384
    [<0000000055bfa74a>] __sys_sendmsg+0x80/0xf0 net/socket.c:2417
    [<000000002abac183>] __do_sys_sendmsg net/socket.c:2426 [inline]
    [<000000002abac183>] __se_sys_sendmsg net/socket.c:2424 [inline]
    [<000000002abac183>] __x64_sys_sendmsg+0x23/0x30 net/socket.c:2424

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot+03c4738ed29d5d366ddf@syzkaller.appspotmail.com
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/ematch.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/sched/ematch.c b/net/sched/ematch.c
index d0140a92694a..dd3b8c11a2e0 100644
--- a/net/sched/ematch.c
+++ b/net/sched/ematch.c
@@ -238,6 +238,9 @@ static int tcf_em_validate(struct tcf_proto *tp,
 			goto errout;
 
 		if (em->ops->change) {
+			err = -EINVAL;
+			if (em_hdr->flags & TCF_EM_SIMPLE)
+				goto errout;
 			err = em->ops->change(net, data, data_len, em);
 			if (err < 0)
 				goto errout;
-- 
2.21.1


From 513b4a033ebc007223845dd7066e081a73601592 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 23 Jan 2020 16:26:18 -0800
Subject: [PATCH 2/9] net_sched: fix ops->bind_class() implementations

[ Upstream commit 2e24cd755552350b94a7617617c6877b8cbcb701 ]

The current implementations of ops->bind_class() are merely
searching for classid and updating class in the struct tcf_result,
without invoking either of cl_ops->bind_tcf() or
cl_ops->unbind_tcf(). This breaks the design of them as qdisc's
like cbq use them to count filters too. This is why syzbot triggered
the warning in cbq_destroy_class().

In order to fix this, we have to call cl_ops->bind_tcf() and
cl_ops->unbind_tcf() like the filter binding path. This patch does
so by refactoring out two helper functions __tcf_bind_filter()
and __tcf_unbind_filter(), which are lockless and accept a Qdisc
pointer, then teaching each implementation to call them correctly.

Note, we merely pass the Qdisc pointer as an opaque pointer to
each filter, they only need to pass it down to the helper
functions without understanding it at all.

Fixes: 07d79fc7d94e ("net_sched: add reverse binding for tc class")
Reported-and-tested-by: syzbot+0a0596220218fcb603a8@syzkaller.appspotmail.com
Reported-and-tested-by: syzbot+63bdb6006961d8c917c6@syzkaller.appspotmail.com
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/pkt_cls.h     | 33 +++++++++++++++++++--------------
 include/net/sch_generic.h |  3 ++-
 net/sched/cls_basic.c     | 11 ++++++++---
 net/sched/cls_bpf.c       | 11 ++++++++---
 net/sched/cls_flower.c    | 11 ++++++++---
 net/sched/cls_fw.c        | 11 ++++++++---
 net/sched/cls_matchall.c  | 11 ++++++++---
 net/sched/cls_route.c     | 11 ++++++++---
 net/sched/cls_rsvp.h      | 11 ++++++++---
 net/sched/cls_tcindex.c   | 11 ++++++++---
 net/sched/cls_u32.c       | 11 ++++++++---
 net/sched/sch_api.c       |  6 ++++--
 12 files changed, 97 insertions(+), 44 deletions(-)

diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index e553fc80eb23..9976ad2f54fd 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -141,31 +141,38 @@ __cls_set_class(unsigned long *clp, unsigned long cl)
 	return xchg(clp, cl);
 }
 
-static inline unsigned long
-cls_set_class(struct Qdisc *q, unsigned long *clp, unsigned long cl)
+static inline void
+__tcf_bind_filter(struct Qdisc *q, struct tcf_result *r, unsigned long base)
 {
-	unsigned long old_cl;
+	unsigned long cl;
 
-	sch_tree_lock(q);
-	old_cl = __cls_set_class(clp, cl);
-	sch_tree_unlock(q);
-	return old_cl;
+	cl = q->ops->cl_ops->bind_tcf(q, base, r->classid);
+	cl = __cls_set_class(&r->class, cl);
+	if (cl)
+		q->ops->cl_ops->unbind_tcf(q, cl);
 }
 
 static inline void
 tcf_bind_filter(struct tcf_proto *tp, struct tcf_result *r, unsigned long base)
 {
 	struct Qdisc *q = tp->chain->block->q;
-	unsigned long cl;
 
 	/* Check q as it is not set for shared blocks. In that case,
 	 * setting class is not supported.
 	 */
 	if (!q)
 		return;
-	cl = q->ops->cl_ops->bind_tcf(q, base, r->classid);
-	cl = cls_set_class(q, &r->class, cl);
-	if (cl)
+	sch_tree_lock(q);
+	__tcf_bind_filter(q, r, base);
+	sch_tree_unlock(q);
+}
+
+static inline void
+__tcf_unbind_filter(struct Qdisc *q, struct tcf_result *r)
+{
+	unsigned long cl;
+
+	if ((cl = __cls_set_class(&r->class, 0)) != 0)
 		q->ops->cl_ops->unbind_tcf(q, cl);
 }
 
@@ -173,12 +180,10 @@ static inline void
 tcf_unbind_filter(struct tcf_proto *tp, struct tcf_result *r)
 {
 	struct Qdisc *q = tp->chain->block->q;
-	unsigned long cl;
 
 	if (!q)
 		return;
-	if ((cl = __cls_set_class(&r->class, 0)) != 0)
-		q->ops->cl_ops->unbind_tcf(q, cl);
+	__tcf_unbind_filter(q, r);
 }
 
 struct tcf_exts {
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 32e418dba133..d334e4609dd4 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -318,7 +318,8 @@ struct tcf_proto_ops {
 					  void *type_data);
 	void			(*hw_del)(struct tcf_proto *tp,
 					  void *type_data);
-	void			(*bind_class)(void *, u32, unsigned long);
+	void			(*bind_class)(void *, u32, unsigned long,
+					      void *, unsigned long);
 	void *			(*tmplt_create)(struct net *net,
 						struct tcf_chain *chain,
 						struct nlattr **tca,
diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c
index 4aafbe3d435c..f256a7c69093 100644
--- a/net/sched/cls_basic.c
+++ b/net/sched/cls_basic.c
@@ -263,12 +263,17 @@ static void basic_walk(struct tcf_proto *tp, struct tcf_walker *arg,
 	}
 }
 
-static void basic_bind_class(void *fh, u32 classid, unsigned long cl)
+static void basic_bind_class(void *fh, u32 classid, unsigned long cl, void *q,
+			     unsigned long base)
 {
 	struct basic_filter *f = fh;
 
-	if (f && f->res.classid == classid)
-		f->res.class = cl;
+	if (f && f->res.classid == classid) {
+		if (cl)
+			__tcf_bind_filter(q, &f->res, base);
+		else
+			__tcf_unbind_filter(q, &f->res);
+	}
 }
 
 static int basic_dump(struct net *net, struct tcf_proto *tp, void *fh,
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 8229ed4a67be..6e3e63db0e01 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -631,12 +631,17 @@ static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, void *fh,
 	return -1;
 }
 
-static void cls_bpf_bind_class(void *fh, u32 classid, unsigned long cl)
+static void cls_bpf_bind_class(void *fh, u32 classid, unsigned long cl,
+			       void *q, unsigned long base)
 {
 	struct cls_bpf_prog *prog = fh;
 
-	if (prog && prog->res.classid == classid)
-		prog->res.class = cl;
+	if (prog && prog->res.classid == classid) {
+		if (cl)
+			__tcf_bind_filter(q, &prog->res, base);
+		else
+			__tcf_unbind_filter(q, &prog->res);
+	}
 }
 
 static void cls_bpf_walk(struct tcf_proto *tp, struct tcf_walker *arg,
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 5cf8163710c8..7394e01c0c9c 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -2511,12 +2511,17 @@ static int fl_tmplt_dump(struct sk_buff *skb, struct net *net, void *tmplt_priv)
 	return -EMSGSIZE;
 }
 
-static void fl_bind_class(void *fh, u32 classid, unsigned long cl)
+static void fl_bind_class(void *fh, u32 classid, unsigned long cl, void *q,
+			  unsigned long base)
 {
 	struct cls_fl_filter *f = fh;
 
-	if (f && f->res.classid == classid)
-		f->res.class = cl;
+	if (f && f->res.classid == classid) {
+		if (cl)
+			__tcf_bind_filter(q, &f->res, base);
+		else
+			__tcf_unbind_filter(q, &f->res);
+	}
 }
 
 static bool fl_delete_empty(struct tcf_proto *tp)
diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c
index c9496c920d6f..ec945294626a 100644
--- a/net/sched/cls_fw.c
+++ b/net/sched/cls_fw.c
@@ -419,12 +419,17 @@ static int fw_dump(struct net *net, struct tcf_proto *tp, void *fh,
 	return -1;
 }
 
-static void fw_bind_class(void *fh, u32 classid, unsigned long cl)
+static void fw_bind_class(void *fh, u32 classid, unsigned long cl, void *q,
+			  unsigned long base)
 {
 	struct fw_filter *f = fh;
 
-	if (f && f->res.classid == classid)
-		f->res.class = cl;
+	if (f && f->res.classid == classid) {
+		if (cl)
+			__tcf_bind_filter(q, &f->res, base);
+		else
+			__tcf_unbind_filter(q, &f->res);
+	}
 }
 
 static struct tcf_proto_ops cls_fw_ops __read_mostly = {
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index 7fc2eb62aa98..039cc86974f4 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -393,12 +393,17 @@ static int mall_dump(struct net *net, struct tcf_proto *tp, void *fh,
 	return -1;
 }
 
-static void mall_bind_class(void *fh, u32 classid, unsigned long cl)
+static void mall_bind_class(void *fh, u32 classid, unsigned long cl, void *q,
+			    unsigned long base)
 {
 	struct cls_mall_head *head = fh;
 
-	if (head && head->res.classid == classid)
-		head->res.class = cl;
+	if (head && head->res.classid == classid) {
+		if (cl)
+			__tcf_bind_filter(q, &head->res, base);
+		else
+			__tcf_unbind_filter(q, &head->res);
+	}
 }
 
 static struct tcf_proto_ops cls_mall_ops __read_mostly = {
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index 2d9e0b4484ea..6f8786b06bde 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -641,12 +641,17 @@ static int route4_dump(struct net *net, struct tcf_proto *tp, void *fh,
 	return -1;
 }
 
-static void route4_bind_class(void *fh, u32 classid, unsigned long cl)
+static void route4_bind_class(void *fh, u32 classid, unsigned long cl, void *q,
+			      unsigned long base)
 {
 	struct route4_filter *f = fh;
 
-	if (f && f->res.classid == classid)
-		f->res.class = cl;
+	if (f && f->res.classid == classid) {
+		if (cl)
+			__tcf_bind_filter(q, &f->res, base);
+		else
+			__tcf_unbind_filter(q, &f->res);
+	}
 }
 
 static struct tcf_proto_ops cls_route4_ops __read_mostly = {
diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h
index 2f3c03b25d5d..c22624131949 100644
--- a/net/sched/cls_rsvp.h
+++ b/net/sched/cls_rsvp.h
@@ -738,12 +738,17 @@ static int rsvp_dump(struct net *net, struct tcf_proto *tp, void *fh,
 	return -1;
 }
 
-static void rsvp_bind_class(void *fh, u32 classid, unsigned long cl)
+static void rsvp_bind_class(void *fh, u32 classid, unsigned long cl, void *q,
+			    unsigned long base)
 {
 	struct rsvp_filter *f = fh;
 
-	if (f && f->res.classid == classid)
-		f->res.class = cl;
+	if (f && f->res.classid == classid) {
+		if (cl)
+			__tcf_bind_filter(q, &f->res, base);
+		else
+			__tcf_unbind_filter(q, &f->res);
+	}
 }
 
 static struct tcf_proto_ops RSVP_OPS __read_mostly = {
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index e573e5a5c794..3d4a1280352f 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -654,12 +654,17 @@ static int tcindex_dump(struct net *net, struct tcf_proto *tp, void *fh,
 	return -1;
 }
 
-static void tcindex_bind_class(void *fh, u32 classid, unsigned long cl)
+static void tcindex_bind_class(void *fh, u32 classid, unsigned long cl,
+			       void *q, unsigned long base)
 {
 	struct tcindex_filter_result *r = fh;
 
-	if (r && r->res.classid == classid)
-		r->res.class = cl;
+	if (r && r->res.classid == classid) {
+		if (cl)
+			__tcf_bind_filter(q, &r->res, base);
+		else
+			__tcf_unbind_filter(q, &r->res);
+	}
 }
 
 static struct tcf_proto_ops cls_tcindex_ops __read_mostly = {
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index a0e6fac613de..e15ff335953d 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -1255,12 +1255,17 @@ static int u32_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb,
 	return 0;
 }
 
-static void u32_bind_class(void *fh, u32 classid, unsigned long cl)
+static void u32_bind_class(void *fh, u32 classid, unsigned long cl, void *q,
+			   unsigned long base)
 {
 	struct tc_u_knode *n = fh;
 
-	if (n && n->res.classid == classid)
-		n->res.class = cl;
+	if (n && n->res.classid == classid) {
+		if (cl)
+			__tcf_bind_filter(q, &n->res, base);
+		else
+			__tcf_unbind_filter(q, &n->res);
+	}
 }
 
 static int u32_dump(struct net *net, struct tcf_proto *tp, void *fh,
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 1047825d9f48..943ad3425380 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1891,8 +1891,9 @@ static int tclass_del_notify(struct net *net,
 
 struct tcf_bind_args {
 	struct tcf_walker w;
-	u32 classid;
+	unsigned long base;
 	unsigned long cl;
+	u32 classid;
 };
 
 static int tcf_node_bind(struct tcf_proto *tp, void *n, struct tcf_walker *arg)
@@ -1903,7 +1904,7 @@ static int tcf_node_bind(struct tcf_proto *tp, void *n, struct tcf_walker *arg)
 		struct Qdisc *q = tcf_block_q(tp->chain->block);
 
 		sch_tree_lock(q);
-		tp->ops->bind_class(n, a->classid, a->cl);
+		tp->ops->bind_class(n, a->classid, a->cl, q, a->base);
 		sch_tree_unlock(q);
 	}
 	return 0;
@@ -1936,6 +1937,7 @@ static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid,
 
 			arg.w.fn = tcf_node_bind;
 			arg.classid = clid;
+			arg.base = cl;
 			arg.cl = new_cl;
 			tp->ops->walk(tp, &arg.w, true);
 		}
-- 
2.21.1


From f9a3b5faf1b8d64357470921ee2e2268739c1cb5 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 23 Jan 2020 17:27:08 -0800
Subject: [PATCH 3/9] net_sched: walk through all child classes in
 tc_bind_tclass()

[ Upstream commit 760d228e322e99cdf6d81b4b60a268b8f13cf67a ]

In a complex TC class hierarchy like this:

tc qdisc add dev eth0 root handle 1:0 cbq bandwidth 100Mbit         \
  avpkt 1000 cell 8
tc class add dev eth0 parent 1:0 classid 1:1 cbq bandwidth 100Mbit  \
  rate 6Mbit weight 0.6Mbit prio 8 allot 1514 cell 8 maxburst 20      \
  avpkt 1000 bounded

tc filter add dev eth0 parent 1:0 protocol ip prio 1 u32 match ip \
  sport 80 0xffff flowid 1:3
tc filter add dev eth0 parent 1:0 protocol ip prio 1 u32 match ip \
  sport 25 0xffff flowid 1:4

tc class add dev eth0 parent 1:1 classid 1:3 cbq bandwidth 100Mbit  \
  rate 5Mbit weight 0.5Mbit prio 5 allot 1514 cell 8 maxburst 20      \
  avpkt 1000
tc class add dev eth0 parent 1:1 classid 1:4 cbq bandwidth 100Mbit  \
  rate 3Mbit weight 0.3Mbit prio 5 allot 1514 cell 8 maxburst 20      \
  avpkt 1000

where filters are installed on qdisc 1:0, so we can't merely
search from class 1:1 when creating class 1:3 and class 1:4. We have
to walk through all the child classes of the direct parent qdisc.
Otherwise we would miss filters those need reverse binding.

Fixes: 07d79fc7d94e ("net_sched: add reverse binding for tc class")
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_api.c | 41 ++++++++++++++++++++++++++++++-----------
 1 file changed, 30 insertions(+), 11 deletions(-)

diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 943ad3425380..50794125bf02 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1910,22 +1910,24 @@ static int tcf_node_bind(struct tcf_proto *tp, void *n, struct tcf_walker *arg)
 	return 0;
 }
 
-static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid,
-			   unsigned long new_cl)
+struct tc_bind_class_args {
+	struct qdisc_walker w;
+	unsigned long new_cl;
+	u32 portid;
+	u32 clid;
+};
+
+static int tc_bind_class_walker(struct Qdisc *q, unsigned long cl,
+				struct qdisc_walker *w)
 {
+	struct tc_bind_class_args *a = (struct tc_bind_class_args *)w;
 	const struct Qdisc_class_ops *cops = q->ops->cl_ops;
 	struct tcf_block *block;
 	struct tcf_chain *chain;
-	unsigned long cl;
 
-	cl = cops->find(q, portid);
-	if (!cl)
-		return;
-	if (!cops->tcf_block)
-		return;
 	block = cops->tcf_block(q, cl, NULL);
 	if (!block)
-		return;
+		return 0;
 	for (chain = tcf_get_next_chain(block, NULL);
 	     chain;
 	     chain = tcf_get_next_chain(block, chain)) {
@@ -1936,12 +1938,29 @@ static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid,
 			struct tcf_bind_args arg = {};
 
 			arg.w.fn = tcf_node_bind;
-			arg.classid = clid;
+			arg.classid = a->clid;
 			arg.base = cl;
-			arg.cl = new_cl;
+			arg.cl = a->new_cl;
 			tp->ops->walk(tp, &arg.w, true);
 		}
 	}
+
+	return 0;
+}
+
+static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid,
+			   unsigned long new_cl)
+{
+	const struct Qdisc_class_ops *cops = q->ops->cl_ops;
+	struct tc_bind_class_args args = {};
+
+	if (!cops->tcf_block)
+		return;
+	args.portid = portid;
+	args.clid = clid;
+	args.new_cl = new_cl;
+	args.w.fn = tc_bind_class_walker;
+	q->ops->cl_ops->walk(q, &args.w);
 }
 
 #else
-- 
2.21.1


From b3b68d848a47289922a9cdc701da159e24e39ae1 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Sat, 25 Jan 2020 12:48:50 +0100
Subject: [PATCH 4/9] net: socionext: fix possible user-after-free in
 netsec_process_rx

[ Upstream commit b5e82e3c89c78ee0407ea8e8087af5519b6c7bae ]

Fix possible use-after-free in in netsec_process_rx that can occurs if
the first packet is sent to the normal networking stack and the
following one is dropped by the bpf program attached to the xdp hook.
Fix the issue defining the skb pointer in the 'budget' loop

Fixes: ba2b232108d3c ("net: netsec: add XDP support")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/socionext/netsec.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index 41ddd8fff2a7..4600a2e04822 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -928,7 +928,6 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 	struct netsec_rx_pkt_info rx_info;
 	enum dma_data_direction dma_dir;
 	struct bpf_prog *xdp_prog;
-	struct sk_buff *skb = NULL;
 	u16 xdp_xmit = 0;
 	u32 xdp_act = 0;
 	int done = 0;
@@ -942,6 +941,7 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 		struct netsec_de *de = dring->vaddr + (DESC_SZ * idx);
 		struct netsec_desc *desc = &dring->desc[idx];
 		struct page *page = virt_to_page(desc->addr);
+		struct sk_buff *skb = NULL;
 		u32 xdp_result = XDP_PASS;
 		u16 pkt_len, desc_len;
 		dma_addr_t dma_handle;
-- 
2.21.1


From e8d8958b815601cfbf330b8c9d60f361f99036a4 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Sat, 25 Jan 2020 12:48:51 +0100
Subject: [PATCH 5/9] net: socionext: fix xdp_result initialization in
 netsec_process_rx

[ Upstream commit 02758cb6dac31a2b4bd9e535cffbe718acd46404 ]

Fix xdp_result initialization in netsec_process_rx in order to not
increase rx counters if there is no bpf program attached to the xdp hook
and napi_gro_receive returns GRO_DROP

Fixes: ba2b232108d3c ("net: netsec: add XDP support")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/socionext/netsec.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index 4600a2e04822..8bd2912bf713 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -941,8 +941,8 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 		struct netsec_de *de = dring->vaddr + (DESC_SZ * idx);
 		struct netsec_desc *desc = &dring->desc[idx];
 		struct page *page = virt_to_page(desc->addr);
+		u32 xdp_result = NETSEC_XDP_PASS;
 		struct sk_buff *skb = NULL;
-		u32 xdp_result = XDP_PASS;
 		u16 pkt_len, desc_len;
 		dma_addr_t dma_handle;
 		struct xdp_buff xdp;
-- 
2.21.1


From 1f84c060cfdc1d09cbbad6a82875ae9ce43f6a82 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Mon, 27 Jan 2020 15:40:31 -0500
Subject: [PATCH 6/9] udp: segment looped gso packets correctly

[ Upstream commit 6cd021a58c18a1731f7e47f83e172c0c302d65e5 ]

Multicast and broadcast packets can be looped from egress to ingress
pre segmentation with dev_loopback_xmit. That function unconditionally
sets ip_summed to CHECKSUM_UNNECESSARY.

udp_rcv_segment segments gso packets in the udp rx path. Segmentation
usually executes on egress, and does not expect packets of this type.
__udp_gso_segment interprets !CHECKSUM_PARTIAL as CHECKSUM_NONE. But
the offsets are not correct for gso_make_checksum.

UDP GSO packets are of type CHECKSUM_PARTIAL, with their uh->check set
to the correct pseudo header checksum. Reset ip_summed to this type.
(CHECKSUM_PARTIAL is allowed on ingress, see comments in skbuff.h)

Reported-by: syzbot <syzkaller@googlegroups.com>
Fixes: cf329aa42b66 ("udp: cope with UDP GRO packet misdirection")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/udp.h | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/include/net/udp.h b/include/net/udp.h
index bad74f780831..8f163d674f07 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -476,6 +476,9 @@ static inline struct sk_buff *udp_rcv_segment(struct sock *sk,
 	if (!inet_get_convert_csum(sk))
 		features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
 
+	if (skb->pkt_type == PACKET_LOOPBACK)
+		skb->ip_summed = CHECKSUM_PARTIAL;
+
 	/* the GSO CB lays after the UDP one, no need to save and restore any
 	 * CB fragment
 	 */
-- 
2.21.1


From 4faafd6d7d56d605f7e23945590072617881c0ca Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sat, 25 Jan 2020 22:18:47 +0100
Subject: [PATCH 7/9] mlxsw: minimal: Fix an error handling path in
 'mlxsw_m_port_create()'

[ Upstream commit 6dd4b4f3936e17fedea1308bc70e9716f68bf232 ]

An 'alloc_etherdev()' called is not ballanced by a corresponding
'free_netdev()' call in one error handling path.

Slighly reorder the error handling code to catch the missed case.

Fixes: c100e47caa8e ("mlxsw: minimal: Add ethtool support")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/minimal.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/minimal.c b/drivers/net/ethernet/mellanox/mlxsw/minimal.c
index 471b0ca6d69a..55dfba990e6e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/minimal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/minimal.c
@@ -204,8 +204,8 @@ mlxsw_m_port_create(struct mlxsw_m *mlxsw_m, u8 local_port, u8 module)
 
 err_register_netdev:
 	mlxsw_m->ports[local_port] = NULL;
-	free_netdev(dev);
 err_dev_addr_get:
+	free_netdev(dev);
 err_alloc_etherdev:
 	mlxsw_core_port_fini(mlxsw_m->core, local_port);
 	return err;
-- 
2.21.1


From 946a775b62ad8c4f41c0138efda4d983e19ef01f Mon Sep 17 00:00:00 2001
From: Stephen Worley <sworley@cumulusnetworks.com>
Date: Fri, 24 Jan 2020 16:53:27 -0500
Subject: [PATCH 8/9] net: include struct nhmsg size in nh nlmsg size

[ Upstream commit f9e95555757915fc194288862d2978e370fe316b ]

Include the size of struct nhmsg size when calculating
how much of a payload to allocate in a new netlink nexthop
notification message.

Without this, we will fail to fill the skbuff at certain nexthop
group sizes.

You can reproduce the failure with the following iproute2 commands:

ip link add dummy1 type dummy
ip link add dummy2 type dummy
ip link add dummy3 type dummy
ip link add dummy4 type dummy
ip link add dummy5 type dummy
ip link add dummy6 type dummy
ip link add dummy7 type dummy
ip link add dummy8 type dummy
ip link add dummy9 type dummy
ip link add dummy10 type dummy
ip link add dummy11 type dummy
ip link add dummy12 type dummy
ip link add dummy13 type dummy
ip link add dummy14 type dummy
ip link add dummy15 type dummy
ip link add dummy16 type dummy
ip link add dummy17 type dummy
ip link add dummy18 type dummy
ip link add dummy19 type dummy

ip ro add 1.1.1.1/32 dev dummy1
ip ro add 1.1.1.2/32 dev dummy2
ip ro add 1.1.1.3/32 dev dummy3
ip ro add 1.1.1.4/32 dev dummy4
ip ro add 1.1.1.5/32 dev dummy5
ip ro add 1.1.1.6/32 dev dummy6
ip ro add 1.1.1.7/32 dev dummy7
ip ro add 1.1.1.8/32 dev dummy8
ip ro add 1.1.1.9/32 dev dummy9
ip ro add 1.1.1.10/32 dev dummy10
ip ro add 1.1.1.11/32 dev dummy11
ip ro add 1.1.1.12/32 dev dummy12
ip ro add 1.1.1.13/32 dev dummy13
ip ro add 1.1.1.14/32 dev dummy14
ip ro add 1.1.1.15/32 dev dummy15
ip ro add 1.1.1.16/32 dev dummy16
ip ro add 1.1.1.17/32 dev dummy17
ip ro add 1.1.1.18/32 dev dummy18
ip ro add 1.1.1.19/32 dev dummy19

ip next add id 1 via 1.1.1.1 dev dummy1
ip next add id 2 via 1.1.1.2 dev dummy2
ip next add id 3 via 1.1.1.3 dev dummy3
ip next add id 4 via 1.1.1.4 dev dummy4
ip next add id 5 via 1.1.1.5 dev dummy5
ip next add id 6 via 1.1.1.6 dev dummy6
ip next add id 7 via 1.1.1.7 dev dummy7
ip next add id 8 via 1.1.1.8 dev dummy8
ip next add id 9 via 1.1.1.9 dev dummy9
ip next add id 10 via 1.1.1.10 dev dummy10
ip next add id 11 via 1.1.1.11 dev dummy11
ip next add id 12 via 1.1.1.12 dev dummy12
ip next add id 13 via 1.1.1.13 dev dummy13
ip next add id 14 via 1.1.1.14 dev dummy14
ip next add id 15 via 1.1.1.15 dev dummy15
ip next add id 16 via 1.1.1.16 dev dummy16
ip next add id 17 via 1.1.1.17 dev dummy17
ip next add id 18 via 1.1.1.18 dev dummy18
ip next add id 19 via 1.1.1.19 dev dummy19

ip next add id 1111 group 1/2/3/4/5/6/7/8/9/10/11/12/13/14/15/16/17/18/19
ip next del id 1111

Fixes: 430a049190de ("nexthop: Add support for nexthop groups")
Signed-off-by: Stephen Worley <sworley@cumulusnetworks.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/nexthop.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index fc34fd1668d6..3737d32ad11a 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -322,7 +322,9 @@ static size_t nh_nlmsg_size_single(struct nexthop *nh)
 
 static size_t nh_nlmsg_size(struct nexthop *nh)
 {
-	size_t sz = nla_total_size(4);    /* NHA_ID */
+	size_t sz = NLMSG_ALIGN(sizeof(struct nhmsg));
+
+	sz += nla_total_size(4); /* NHA_ID */
 
 	if (nh->is_group)
 		sz += nh_nlmsg_size_grp(nh);
-- 
2.21.1


From ee4cfa8c90bec65495e52195288e561aa45475b3 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 24 Jan 2020 23:08:04 +0000
Subject: [PATCH 9/9] rxrpc: Fix use-after-free in rxrpc_receive_data()

[ Upstream commit 122d74fac84204b9a98263636f6f9a3b2e665639 ]

The subpacket scanning loop in rxrpc_receive_data() references the
subpacket count in the private data part of the sk_buff in the loop
termination condition.  However, when the final subpacket is pasted into
the ring buffer, the function is no longer has a ref on the sk_buff and
should not be looking at sp->* any more.  This point is actually marked in
the code when skb is cleared (but sp is not - which is an error).

Fix this by caching sp->nr_subpackets in a local variable and using that
instead.

Also clear 'sp' to catch accesses after that point.

This can show up as an oops in rxrpc_get_skb() if sp->nr_subpackets gets
trashed by the sk_buff getting freed and reused in the meantime.

Fixes: e2de6c404898 ("rxrpc: Use info in skbuff instead of reparsing a jumbo packet")
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/input.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 86bd133b4fa0..96d54e5bf7bc 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -413,7 +413,7 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb)
 {
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
 	enum rxrpc_call_state state;
-	unsigned int j;
+	unsigned int j, nr_subpackets;
 	rxrpc_serial_t serial = sp->hdr.serial, ack_serial = 0;
 	rxrpc_seq_t seq0 = sp->hdr.seq, hard_ack;
 	bool immediate_ack = false, jumbo_bad = false;
@@ -457,7 +457,8 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb)
 	call->ackr_prev_seq = seq0;
 	hard_ack = READ_ONCE(call->rx_hard_ack);
 
-	if (sp->nr_subpackets > 1) {
+	nr_subpackets = sp->nr_subpackets;
+	if (nr_subpackets > 1) {
 		if (call->nr_jumbo_bad > 3) {
 			ack = RXRPC_ACK_NOSPACE;
 			ack_serial = serial;
@@ -465,11 +466,11 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb)
 		}
 	}
 
-	for (j = 0; j < sp->nr_subpackets; j++) {
+	for (j = 0; j < nr_subpackets; j++) {
 		rxrpc_serial_t serial = sp->hdr.serial + j;
 		rxrpc_seq_t seq = seq0 + j;
 		unsigned int ix = seq & RXRPC_RXTX_BUFF_MASK;
-		bool terminal = (j == sp->nr_subpackets - 1);
+		bool terminal = (j == nr_subpackets - 1);
 		bool last = terminal && (sp->rx_flags & RXRPC_SKB_INCL_LAST);
 		u8 flags, annotation = j;
 
@@ -506,7 +507,7 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb)
 		}
 
 		if (call->rxtx_buffer[ix]) {
-			rxrpc_input_dup_data(call, seq, sp->nr_subpackets > 1,
+			rxrpc_input_dup_data(call, seq, nr_subpackets > 1,
 					     &jumbo_bad);
 			if (ack != RXRPC_ACK_DUPLICATE) {
 				ack = RXRPC_ACK_DUPLICATE;
@@ -564,6 +565,7 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb)
 			 * ring.
 			 */
 			skb = NULL;
+			sp = NULL;
 		}
 
 		if (last) {
-- 
2.21.1


[-- Attachment #3: net_55.mbox --]
[-- Type: Application/Octet-Stream, Size: 34357 bytes --]

From 9a757f467ea267141459e1010bbd21b537d5dd8d Mon Sep 17 00:00:00 2001
From: Sven Auhagen <sven.auhagen@voleatech.de>
Date: Sat, 25 Jan 2020 08:07:03 +0000
Subject: [PATCH 01/10] mvneta driver disallow XDP program on hardware buffer
 management

[ Upstream commit 79572c98c554dcdb080bca547c871a51716dcdf8 ]

Recently XDP Support was added to the mvneta driver
for software buffer management only.
It is still possible to attach an XDP program if
hardware buffer management is used.
It is not doing anything at that point.

The patch disallows attaching XDP programs to mvneta
if hardware buffer management is used.

I am sorry about that. It is my first submission and I am having
some troubles with the format of my emails.

v4 -> v5:
- Remove extra tabs

v3 -> v4:
- Please ignore v3 I accidentally submitted
  my other patch with git-send-mail and v4 is correct

v2 -> v3:
- My mailserver corrupted the patch
  resubmission with git-send-email

v1 -> v2:
- Fixing the patches indentation

Signed-off-by: Sven Auhagen <sven.auhagen@voleatech.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 67ad8b8b127d..8bad5b864682 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -4226,6 +4226,12 @@ static int mvneta_xdp_setup(struct net_device *dev, struct bpf_prog *prog,
 		return -EOPNOTSUPP;
 	}
 
+	if (pp->bm_priv) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Hardware Buffer Management not supported on XDP");
+		return -EOPNOTSUPP;
+	}
+
 	need_update = !!pp->xdp_prog != !!prog;
 	if (running && need_update)
 		mvneta_stop(dev);
-- 
2.21.1


From bbe1ed733a0af324c7e854d31fd7c1042e25ae2f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 24 Jan 2020 14:57:20 -0800
Subject: [PATCH 02/10] net_sched: ematch: reject invalid TCF_EM_SIMPLE

[ Upstream commit 55cd9f67f1e45de8517cdaab985fb8e56c0bc1d8 ]

It is possible for malicious userspace to set TCF_EM_SIMPLE bit
even for matches that should not have this bit set.

This can fool two places using tcf_em_is_simple()

1) tcf_em_tree_destroy() -> memory leak of em->data
   if ops->destroy() is NULL

2) tcf_em_tree_dump() wrongly report/leak 4 low-order bytes
   of a kernel pointer.

BUG: memory leak
unreferenced object 0xffff888121850a40 (size 32):
  comm "syz-executor927", pid 7193, jiffies 4294941655 (age 19.840s)
  hex dump (first 32 bytes):
    00 00 00 00 01 00 00 00 00 00 00 00 00 00 00 00  ................
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<00000000f67036ea>] kmemleak_alloc_recursive include/linux/kmemleak.h:43 [inline]
    [<00000000f67036ea>] slab_post_alloc_hook mm/slab.h:586 [inline]
    [<00000000f67036ea>] slab_alloc mm/slab.c:3320 [inline]
    [<00000000f67036ea>] __do_kmalloc mm/slab.c:3654 [inline]
    [<00000000f67036ea>] __kmalloc_track_caller+0x165/0x300 mm/slab.c:3671
    [<00000000fab0cc8e>] kmemdup+0x27/0x60 mm/util.c:127
    [<00000000d9992e0a>] kmemdup include/linux/string.h:453 [inline]
    [<00000000d9992e0a>] em_nbyte_change+0x5b/0x90 net/sched/em_nbyte.c:32
    [<000000007e04f711>] tcf_em_validate net/sched/ematch.c:241 [inline]
    [<000000007e04f711>] tcf_em_tree_validate net/sched/ematch.c:359 [inline]
    [<000000007e04f711>] tcf_em_tree_validate+0x332/0x46f net/sched/ematch.c:300
    [<000000007a769204>] basic_set_parms net/sched/cls_basic.c:157 [inline]
    [<000000007a769204>] basic_change+0x1d7/0x5f0 net/sched/cls_basic.c:219
    [<00000000e57a5997>] tc_new_tfilter+0x566/0xf70 net/sched/cls_api.c:2104
    [<0000000074b68559>] rtnetlink_rcv_msg+0x3b2/0x4b0 net/core/rtnetlink.c:5415
    [<00000000b7fe53fb>] netlink_rcv_skb+0x61/0x170 net/netlink/af_netlink.c:2477
    [<00000000e83a40d0>] rtnetlink_rcv+0x1d/0x30 net/core/rtnetlink.c:5442
    [<00000000d62ba933>] netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
    [<00000000d62ba933>] netlink_unicast+0x223/0x310 net/netlink/af_netlink.c:1328
    [<0000000088070f72>] netlink_sendmsg+0x2c0/0x570 net/netlink/af_netlink.c:1917
    [<00000000f70b15ea>] sock_sendmsg_nosec net/socket.c:639 [inline]
    [<00000000f70b15ea>] sock_sendmsg+0x54/0x70 net/socket.c:659
    [<00000000ef95a9be>] ____sys_sendmsg+0x2d0/0x300 net/socket.c:2330
    [<00000000b650f1ab>] ___sys_sendmsg+0x8a/0xd0 net/socket.c:2384
    [<0000000055bfa74a>] __sys_sendmsg+0x80/0xf0 net/socket.c:2417
    [<000000002abac183>] __do_sys_sendmsg net/socket.c:2426 [inline]
    [<000000002abac183>] __se_sys_sendmsg net/socket.c:2424 [inline]
    [<000000002abac183>] __x64_sys_sendmsg+0x23/0x30 net/socket.c:2424

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot+03c4738ed29d5d366ddf@syzkaller.appspotmail.com
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/ematch.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/sched/ematch.c b/net/sched/ematch.c
index d0140a92694a..dd3b8c11a2e0 100644
--- a/net/sched/ematch.c
+++ b/net/sched/ematch.c
@@ -238,6 +238,9 @@ static int tcf_em_validate(struct tcf_proto *tp,
 			goto errout;
 
 		if (em->ops->change) {
+			err = -EINVAL;
+			if (em_hdr->flags & TCF_EM_SIMPLE)
+				goto errout;
 			err = em->ops->change(net, data, data_len, em);
 			if (err < 0)
 				goto errout;
-- 
2.21.1


From 9d216ce28a0a54a18f96cade4c3d820c6baf4b7c Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 23 Jan 2020 16:26:18 -0800
Subject: [PATCH 03/10] net_sched: fix ops->bind_class() implementations

[ Upstream commit 2e24cd755552350b94a7617617c6877b8cbcb701 ]

The current implementations of ops->bind_class() are merely
searching for classid and updating class in the struct tcf_result,
without invoking either of cl_ops->bind_tcf() or
cl_ops->unbind_tcf(). This breaks the design of them as qdisc's
like cbq use them to count filters too. This is why syzbot triggered
the warning in cbq_destroy_class().

In order to fix this, we have to call cl_ops->bind_tcf() and
cl_ops->unbind_tcf() like the filter binding path. This patch does
so by refactoring out two helper functions __tcf_bind_filter()
and __tcf_unbind_filter(), which are lockless and accept a Qdisc
pointer, then teaching each implementation to call them correctly.

Note, we merely pass the Qdisc pointer as an opaque pointer to
each filter, they only need to pass it down to the helper
functions without understanding it at all.

Fixes: 07d79fc7d94e ("net_sched: add reverse binding for tc class")
Reported-and-tested-by: syzbot+0a0596220218fcb603a8@syzkaller.appspotmail.com
Reported-and-tested-by: syzbot+63bdb6006961d8c917c6@syzkaller.appspotmail.com
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/pkt_cls.h     | 33 +++++++++++++++++++--------------
 include/net/sch_generic.h |  3 ++-
 net/sched/cls_basic.c     | 11 ++++++++---
 net/sched/cls_bpf.c       | 11 ++++++++---
 net/sched/cls_flower.c    | 11 ++++++++---
 net/sched/cls_fw.c        | 11 ++++++++---
 net/sched/cls_matchall.c  | 11 ++++++++---
 net/sched/cls_route.c     | 11 ++++++++---
 net/sched/cls_rsvp.h      | 11 ++++++++---
 net/sched/cls_tcindex.c   | 11 ++++++++---
 net/sched/cls_u32.c       | 11 ++++++++---
 net/sched/sch_api.c       |  6 ++++--
 12 files changed, 97 insertions(+), 44 deletions(-)

diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index e553fc80eb23..9976ad2f54fd 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -141,31 +141,38 @@ __cls_set_class(unsigned long *clp, unsigned long cl)
 	return xchg(clp, cl);
 }
 
-static inline unsigned long
-cls_set_class(struct Qdisc *q, unsigned long *clp, unsigned long cl)
+static inline void
+__tcf_bind_filter(struct Qdisc *q, struct tcf_result *r, unsigned long base)
 {
-	unsigned long old_cl;
+	unsigned long cl;
 
-	sch_tree_lock(q);
-	old_cl = __cls_set_class(clp, cl);
-	sch_tree_unlock(q);
-	return old_cl;
+	cl = q->ops->cl_ops->bind_tcf(q, base, r->classid);
+	cl = __cls_set_class(&r->class, cl);
+	if (cl)
+		q->ops->cl_ops->unbind_tcf(q, cl);
 }
 
 static inline void
 tcf_bind_filter(struct tcf_proto *tp, struct tcf_result *r, unsigned long base)
 {
 	struct Qdisc *q = tp->chain->block->q;
-	unsigned long cl;
 
 	/* Check q as it is not set for shared blocks. In that case,
 	 * setting class is not supported.
 	 */
 	if (!q)
 		return;
-	cl = q->ops->cl_ops->bind_tcf(q, base, r->classid);
-	cl = cls_set_class(q, &r->class, cl);
-	if (cl)
+	sch_tree_lock(q);
+	__tcf_bind_filter(q, r, base);
+	sch_tree_unlock(q);
+}
+
+static inline void
+__tcf_unbind_filter(struct Qdisc *q, struct tcf_result *r)
+{
+	unsigned long cl;
+
+	if ((cl = __cls_set_class(&r->class, 0)) != 0)
 		q->ops->cl_ops->unbind_tcf(q, cl);
 }
 
@@ -173,12 +180,10 @@ static inline void
 tcf_unbind_filter(struct tcf_proto *tp, struct tcf_result *r)
 {
 	struct Qdisc *q = tp->chain->block->q;
-	unsigned long cl;
 
 	if (!q)
 		return;
-	if ((cl = __cls_set_class(&r->class, 0)) != 0)
-		q->ops->cl_ops->unbind_tcf(q, cl);
+	__tcf_unbind_filter(q, r);
 }
 
 struct tcf_exts {
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index fceddf89592a..151208704ed2 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -318,7 +318,8 @@ struct tcf_proto_ops {
 					  void *type_data);
 	void			(*hw_del)(struct tcf_proto *tp,
 					  void *type_data);
-	void			(*bind_class)(void *, u32, unsigned long);
+	void			(*bind_class)(void *, u32, unsigned long,
+					      void *, unsigned long);
 	void *			(*tmplt_create)(struct net *net,
 						struct tcf_chain *chain,
 						struct nlattr **tca,
diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c
index 4aafbe3d435c..f256a7c69093 100644
--- a/net/sched/cls_basic.c
+++ b/net/sched/cls_basic.c
@@ -263,12 +263,17 @@ static void basic_walk(struct tcf_proto *tp, struct tcf_walker *arg,
 	}
 }
 
-static void basic_bind_class(void *fh, u32 classid, unsigned long cl)
+static void basic_bind_class(void *fh, u32 classid, unsigned long cl, void *q,
+			     unsigned long base)
 {
 	struct basic_filter *f = fh;
 
-	if (f && f->res.classid == classid)
-		f->res.class = cl;
+	if (f && f->res.classid == classid) {
+		if (cl)
+			__tcf_bind_filter(q, &f->res, base);
+		else
+			__tcf_unbind_filter(q, &f->res);
+	}
 }
 
 static int basic_dump(struct net *net, struct tcf_proto *tp, void *fh,
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 8229ed4a67be..6e3e63db0e01 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -631,12 +631,17 @@ static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, void *fh,
 	return -1;
 }
 
-static void cls_bpf_bind_class(void *fh, u32 classid, unsigned long cl)
+static void cls_bpf_bind_class(void *fh, u32 classid, unsigned long cl,
+			       void *q, unsigned long base)
 {
 	struct cls_bpf_prog *prog = fh;
 
-	if (prog && prog->res.classid == classid)
-		prog->res.class = cl;
+	if (prog && prog->res.classid == classid) {
+		if (cl)
+			__tcf_bind_filter(q, &prog->res, base);
+		else
+			__tcf_unbind_filter(q, &prog->res);
+	}
 }
 
 static void cls_bpf_walk(struct tcf_proto *tp, struct tcf_walker *arg,
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index b0f42e62dd76..f9c0d1e8d380 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -2765,12 +2765,17 @@ static int fl_tmplt_dump(struct sk_buff *skb, struct net *net, void *tmplt_priv)
 	return -EMSGSIZE;
 }
 
-static void fl_bind_class(void *fh, u32 classid, unsigned long cl)
+static void fl_bind_class(void *fh, u32 classid, unsigned long cl, void *q,
+			  unsigned long base)
 {
 	struct cls_fl_filter *f = fh;
 
-	if (f && f->res.classid == classid)
-		f->res.class = cl;
+	if (f && f->res.classid == classid) {
+		if (cl)
+			__tcf_bind_filter(q, &f->res, base);
+		else
+			__tcf_unbind_filter(q, &f->res);
+	}
 }
 
 static bool fl_delete_empty(struct tcf_proto *tp)
diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c
index c9496c920d6f..ec945294626a 100644
--- a/net/sched/cls_fw.c
+++ b/net/sched/cls_fw.c
@@ -419,12 +419,17 @@ static int fw_dump(struct net *net, struct tcf_proto *tp, void *fh,
 	return -1;
 }
 
-static void fw_bind_class(void *fh, u32 classid, unsigned long cl)
+static void fw_bind_class(void *fh, u32 classid, unsigned long cl, void *q,
+			  unsigned long base)
 {
 	struct fw_filter *f = fh;
 
-	if (f && f->res.classid == classid)
-		f->res.class = cl;
+	if (f && f->res.classid == classid) {
+		if (cl)
+			__tcf_bind_filter(q, &f->res, base);
+		else
+			__tcf_unbind_filter(q, &f->res);
+	}
 }
 
 static struct tcf_proto_ops cls_fw_ops __read_mostly = {
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index 7fc2eb62aa98..039cc86974f4 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -393,12 +393,17 @@ static int mall_dump(struct net *net, struct tcf_proto *tp, void *fh,
 	return -1;
 }
 
-static void mall_bind_class(void *fh, u32 classid, unsigned long cl)
+static void mall_bind_class(void *fh, u32 classid, unsigned long cl, void *q,
+			    unsigned long base)
 {
 	struct cls_mall_head *head = fh;
 
-	if (head && head->res.classid == classid)
-		head->res.class = cl;
+	if (head && head->res.classid == classid) {
+		if (cl)
+			__tcf_bind_filter(q, &head->res, base);
+		else
+			__tcf_unbind_filter(q, &head->res);
+	}
 }
 
 static struct tcf_proto_ops cls_mall_ops __read_mostly = {
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index 2d9e0b4484ea..6f8786b06bde 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -641,12 +641,17 @@ static int route4_dump(struct net *net, struct tcf_proto *tp, void *fh,
 	return -1;
 }
 
-static void route4_bind_class(void *fh, u32 classid, unsigned long cl)
+static void route4_bind_class(void *fh, u32 classid, unsigned long cl, void *q,
+			      unsigned long base)
 {
 	struct route4_filter *f = fh;
 
-	if (f && f->res.classid == classid)
-		f->res.class = cl;
+	if (f && f->res.classid == classid) {
+		if (cl)
+			__tcf_bind_filter(q, &f->res, base);
+		else
+			__tcf_unbind_filter(q, &f->res);
+	}
 }
 
 static struct tcf_proto_ops cls_route4_ops __read_mostly = {
diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h
index 2f3c03b25d5d..c22624131949 100644
--- a/net/sched/cls_rsvp.h
+++ b/net/sched/cls_rsvp.h
@@ -738,12 +738,17 @@ static int rsvp_dump(struct net *net, struct tcf_proto *tp, void *fh,
 	return -1;
 }
 
-static void rsvp_bind_class(void *fh, u32 classid, unsigned long cl)
+static void rsvp_bind_class(void *fh, u32 classid, unsigned long cl, void *q,
+			    unsigned long base)
 {
 	struct rsvp_filter *f = fh;
 
-	if (f && f->res.classid == classid)
-		f->res.class = cl;
+	if (f && f->res.classid == classid) {
+		if (cl)
+			__tcf_bind_filter(q, &f->res, base);
+		else
+			__tcf_unbind_filter(q, &f->res);
+	}
 }
 
 static struct tcf_proto_ops RSVP_OPS __read_mostly = {
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index e573e5a5c794..3d4a1280352f 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -654,12 +654,17 @@ static int tcindex_dump(struct net *net, struct tcf_proto *tp, void *fh,
 	return -1;
 }
 
-static void tcindex_bind_class(void *fh, u32 classid, unsigned long cl)
+static void tcindex_bind_class(void *fh, u32 classid, unsigned long cl,
+			       void *q, unsigned long base)
 {
 	struct tcindex_filter_result *r = fh;
 
-	if (r && r->res.classid == classid)
-		r->res.class = cl;
+	if (r && r->res.classid == classid) {
+		if (cl)
+			__tcf_bind_filter(q, &r->res, base);
+		else
+			__tcf_unbind_filter(q, &r->res);
+	}
 }
 
 static struct tcf_proto_ops cls_tcindex_ops __read_mostly = {
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index a0e6fac613de..e15ff335953d 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -1255,12 +1255,17 @@ static int u32_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb,
 	return 0;
 }
 
-static void u32_bind_class(void *fh, u32 classid, unsigned long cl)
+static void u32_bind_class(void *fh, u32 classid, unsigned long cl, void *q,
+			   unsigned long base)
 {
 	struct tc_u_knode *n = fh;
 
-	if (n && n->res.classid == classid)
-		n->res.class = cl;
+	if (n && n->res.classid == classid) {
+		if (cl)
+			__tcf_bind_filter(q, &n->res, base);
+		else
+			__tcf_unbind_filter(q, &n->res);
+	}
 }
 
 static int u32_dump(struct net *net, struct tcf_proto *tp, void *fh,
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 1047825d9f48..943ad3425380 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1891,8 +1891,9 @@ static int tclass_del_notify(struct net *net,
 
 struct tcf_bind_args {
 	struct tcf_walker w;
-	u32 classid;
+	unsigned long base;
 	unsigned long cl;
+	u32 classid;
 };
 
 static int tcf_node_bind(struct tcf_proto *tp, void *n, struct tcf_walker *arg)
@@ -1903,7 +1904,7 @@ static int tcf_node_bind(struct tcf_proto *tp, void *n, struct tcf_walker *arg)
 		struct Qdisc *q = tcf_block_q(tp->chain->block);
 
 		sch_tree_lock(q);
-		tp->ops->bind_class(n, a->classid, a->cl);
+		tp->ops->bind_class(n, a->classid, a->cl, q, a->base);
 		sch_tree_unlock(q);
 	}
 	return 0;
@@ -1936,6 +1937,7 @@ static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid,
 
 			arg.w.fn = tcf_node_bind;
 			arg.classid = clid;
+			arg.base = cl;
 			arg.cl = new_cl;
 			tp->ops->walk(tp, &arg.w, true);
 		}
-- 
2.21.1


From 038998814e98d7c1da1262b7e26f34db0f1d4d77 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 23 Jan 2020 17:27:08 -0800
Subject: [PATCH 04/10] net_sched: walk through all child classes in
 tc_bind_tclass()

[ Upstream commit 760d228e322e99cdf6d81b4b60a268b8f13cf67a ]

In a complex TC class hierarchy like this:

tc qdisc add dev eth0 root handle 1:0 cbq bandwidth 100Mbit         \
  avpkt 1000 cell 8
tc class add dev eth0 parent 1:0 classid 1:1 cbq bandwidth 100Mbit  \
  rate 6Mbit weight 0.6Mbit prio 8 allot 1514 cell 8 maxburst 20      \
  avpkt 1000 bounded

tc filter add dev eth0 parent 1:0 protocol ip prio 1 u32 match ip \
  sport 80 0xffff flowid 1:3
tc filter add dev eth0 parent 1:0 protocol ip prio 1 u32 match ip \
  sport 25 0xffff flowid 1:4

tc class add dev eth0 parent 1:1 classid 1:3 cbq bandwidth 100Mbit  \
  rate 5Mbit weight 0.5Mbit prio 5 allot 1514 cell 8 maxburst 20      \
  avpkt 1000
tc class add dev eth0 parent 1:1 classid 1:4 cbq bandwidth 100Mbit  \
  rate 3Mbit weight 0.3Mbit prio 5 allot 1514 cell 8 maxburst 20      \
  avpkt 1000

where filters are installed on qdisc 1:0, so we can't merely
search from class 1:1 when creating class 1:3 and class 1:4. We have
to walk through all the child classes of the direct parent qdisc.
Otherwise we would miss filters those need reverse binding.

Fixes: 07d79fc7d94e ("net_sched: add reverse binding for tc class")
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_api.c | 41 ++++++++++++++++++++++++++++++-----------
 1 file changed, 30 insertions(+), 11 deletions(-)

diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 943ad3425380..50794125bf02 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1910,22 +1910,24 @@ static int tcf_node_bind(struct tcf_proto *tp, void *n, struct tcf_walker *arg)
 	return 0;
 }
 
-static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid,
-			   unsigned long new_cl)
+struct tc_bind_class_args {
+	struct qdisc_walker w;
+	unsigned long new_cl;
+	u32 portid;
+	u32 clid;
+};
+
+static int tc_bind_class_walker(struct Qdisc *q, unsigned long cl,
+				struct qdisc_walker *w)
 {
+	struct tc_bind_class_args *a = (struct tc_bind_class_args *)w;
 	const struct Qdisc_class_ops *cops = q->ops->cl_ops;
 	struct tcf_block *block;
 	struct tcf_chain *chain;
-	unsigned long cl;
 
-	cl = cops->find(q, portid);
-	if (!cl)
-		return;
-	if (!cops->tcf_block)
-		return;
 	block = cops->tcf_block(q, cl, NULL);
 	if (!block)
-		return;
+		return 0;
 	for (chain = tcf_get_next_chain(block, NULL);
 	     chain;
 	     chain = tcf_get_next_chain(block, chain)) {
@@ -1936,12 +1938,29 @@ static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid,
 			struct tcf_bind_args arg = {};
 
 			arg.w.fn = tcf_node_bind;
-			arg.classid = clid;
+			arg.classid = a->clid;
 			arg.base = cl;
-			arg.cl = new_cl;
+			arg.cl = a->new_cl;
 			tp->ops->walk(tp, &arg.w, true);
 		}
 	}
+
+	return 0;
+}
+
+static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid,
+			   unsigned long new_cl)
+{
+	const struct Qdisc_class_ops *cops = q->ops->cl_ops;
+	struct tc_bind_class_args args = {};
+
+	if (!cops->tcf_block)
+		return;
+	args.portid = portid;
+	args.clid = clid;
+	args.new_cl = new_cl;
+	args.w.fn = tc_bind_class_walker;
+	q->ops->cl_ops->walk(q, &args.w);
 }
 
 #else
-- 
2.21.1


From 86ae5c190954da74942a7feafac0413a30a055eb Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Sat, 25 Jan 2020 12:48:50 +0100
Subject: [PATCH 05/10] net: socionext: fix possible user-after-free in
 netsec_process_rx

[ Upstream commit b5e82e3c89c78ee0407ea8e8087af5519b6c7bae ]

Fix possible use-after-free in in netsec_process_rx that can occurs if
the first packet is sent to the normal networking stack and the
following one is dropped by the bpf program attached to the xdp hook.
Fix the issue defining the skb pointer in the 'budget' loop

Fixes: ba2b232108d3c ("net: netsec: add XDP support")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/socionext/netsec.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index 869a498e3b5e..0e12a9856aea 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -929,7 +929,6 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 	struct netsec_rx_pkt_info rx_info;
 	enum dma_data_direction dma_dir;
 	struct bpf_prog *xdp_prog;
-	struct sk_buff *skb = NULL;
 	u16 xdp_xmit = 0;
 	u32 xdp_act = 0;
 	int done = 0;
@@ -943,6 +942,7 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 		struct netsec_de *de = dring->vaddr + (DESC_SZ * idx);
 		struct netsec_desc *desc = &dring->desc[idx];
 		struct page *page = virt_to_page(desc->addr);
+		struct sk_buff *skb = NULL;
 		u32 xdp_result = XDP_PASS;
 		u16 pkt_len, desc_len;
 		dma_addr_t dma_handle;
-- 
2.21.1


From 2bd726d7e32de3abc9cc197ff5b4756465a54601 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Sat, 25 Jan 2020 12:48:51 +0100
Subject: [PATCH 06/10] net: socionext: fix xdp_result initialization in
 netsec_process_rx

[ Upstream commit 02758cb6dac31a2b4bd9e535cffbe718acd46404 ]

Fix xdp_result initialization in netsec_process_rx in order to not
increase rx counters if there is no bpf program attached to the xdp hook
and napi_gro_receive returns GRO_DROP

Fixes: ba2b232108d3c ("net: netsec: add XDP support")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/socionext/netsec.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index 0e12a9856aea..56c0e643f430 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -942,8 +942,8 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 		struct netsec_de *de = dring->vaddr + (DESC_SZ * idx);
 		struct netsec_desc *desc = &dring->desc[idx];
 		struct page *page = virt_to_page(desc->addr);
+		u32 xdp_result = NETSEC_XDP_PASS;
 		struct sk_buff *skb = NULL;
-		u32 xdp_result = XDP_PASS;
 		u16 pkt_len, desc_len;
 		dma_addr_t dma_handle;
 		struct xdp_buff xdp;
-- 
2.21.1


From 4c6313e5c9eaa88ad4b0185c8cba59ef6832a4ea Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Mon, 27 Jan 2020 15:40:31 -0500
Subject: [PATCH 07/10] udp: segment looped gso packets correctly

[ Upstream commit 6cd021a58c18a1731f7e47f83e172c0c302d65e5 ]

Multicast and broadcast packets can be looped from egress to ingress
pre segmentation with dev_loopback_xmit. That function unconditionally
sets ip_summed to CHECKSUM_UNNECESSARY.

udp_rcv_segment segments gso packets in the udp rx path. Segmentation
usually executes on egress, and does not expect packets of this type.
__udp_gso_segment interprets !CHECKSUM_PARTIAL as CHECKSUM_NONE. But
the offsets are not correct for gso_make_checksum.

UDP GSO packets are of type CHECKSUM_PARTIAL, with their uh->check set
to the correct pseudo header checksum. Reset ip_summed to this type.
(CHECKSUM_PARTIAL is allowed on ingress, see comments in skbuff.h)

Reported-by: syzbot <syzkaller@googlegroups.com>
Fixes: cf329aa42b66 ("udp: cope with UDP GRO packet misdirection")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/udp.h | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/include/net/udp.h b/include/net/udp.h
index bad74f780831..8f163d674f07 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -476,6 +476,9 @@ static inline struct sk_buff *udp_rcv_segment(struct sock *sk,
 	if (!inet_get_convert_csum(sk))
 		features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
 
+	if (skb->pkt_type == PACKET_LOOPBACK)
+		skb->ip_summed = CHECKSUM_PARTIAL;
+
 	/* the GSO CB lays after the UDP one, no need to save and restore any
 	 * CB fragment
 	 */
-- 
2.21.1


From 9fbfb0a784583c7e0ff78f2d1cfbb21280d35b27 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sat, 25 Jan 2020 22:18:47 +0100
Subject: [PATCH 08/10] mlxsw: minimal: Fix an error handling path in
 'mlxsw_m_port_create()'

[ Upstream commit 6dd4b4f3936e17fedea1308bc70e9716f68bf232 ]

An 'alloc_etherdev()' called is not ballanced by a corresponding
'free_netdev()' call in one error handling path.

Slighly reorder the error handling code to catch the missed case.

Fixes: c100e47caa8e ("mlxsw: minimal: Add ethtool support")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/minimal.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/minimal.c b/drivers/net/ethernet/mellanox/mlxsw/minimal.c
index 2b543911ae00..c4caeeadcba9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/minimal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/minimal.c
@@ -213,8 +213,8 @@ mlxsw_m_port_create(struct mlxsw_m *mlxsw_m, u8 local_port, u8 module)
 
 err_register_netdev:
 	mlxsw_m->ports[local_port] = NULL;
-	free_netdev(dev);
 err_dev_addr_get:
+	free_netdev(dev);
 err_alloc_etherdev:
 	mlxsw_core_port_fini(mlxsw_m->core, local_port);
 	return err;
-- 
2.21.1


From 2126eb4941a357d57659005358261035f7da65ed Mon Sep 17 00:00:00 2001
From: Stephen Worley <sworley@cumulusnetworks.com>
Date: Fri, 24 Jan 2020 16:53:27 -0500
Subject: [PATCH 09/10] net: include struct nhmsg size in nh nlmsg size

[ Upstream commit f9e95555757915fc194288862d2978e370fe316b ]

Include the size of struct nhmsg size when calculating
how much of a payload to allocate in a new netlink nexthop
notification message.

Without this, we will fail to fill the skbuff at certain nexthop
group sizes.

You can reproduce the failure with the following iproute2 commands:

ip link add dummy1 type dummy
ip link add dummy2 type dummy
ip link add dummy3 type dummy
ip link add dummy4 type dummy
ip link add dummy5 type dummy
ip link add dummy6 type dummy
ip link add dummy7 type dummy
ip link add dummy8 type dummy
ip link add dummy9 type dummy
ip link add dummy10 type dummy
ip link add dummy11 type dummy
ip link add dummy12 type dummy
ip link add dummy13 type dummy
ip link add dummy14 type dummy
ip link add dummy15 type dummy
ip link add dummy16 type dummy
ip link add dummy17 type dummy
ip link add dummy18 type dummy
ip link add dummy19 type dummy

ip ro add 1.1.1.1/32 dev dummy1
ip ro add 1.1.1.2/32 dev dummy2
ip ro add 1.1.1.3/32 dev dummy3
ip ro add 1.1.1.4/32 dev dummy4
ip ro add 1.1.1.5/32 dev dummy5
ip ro add 1.1.1.6/32 dev dummy6
ip ro add 1.1.1.7/32 dev dummy7
ip ro add 1.1.1.8/32 dev dummy8
ip ro add 1.1.1.9/32 dev dummy9
ip ro add 1.1.1.10/32 dev dummy10
ip ro add 1.1.1.11/32 dev dummy11
ip ro add 1.1.1.12/32 dev dummy12
ip ro add 1.1.1.13/32 dev dummy13
ip ro add 1.1.1.14/32 dev dummy14
ip ro add 1.1.1.15/32 dev dummy15
ip ro add 1.1.1.16/32 dev dummy16
ip ro add 1.1.1.17/32 dev dummy17
ip ro add 1.1.1.18/32 dev dummy18
ip ro add 1.1.1.19/32 dev dummy19

ip next add id 1 via 1.1.1.1 dev dummy1
ip next add id 2 via 1.1.1.2 dev dummy2
ip next add id 3 via 1.1.1.3 dev dummy3
ip next add id 4 via 1.1.1.4 dev dummy4
ip next add id 5 via 1.1.1.5 dev dummy5
ip next add id 6 via 1.1.1.6 dev dummy6
ip next add id 7 via 1.1.1.7 dev dummy7
ip next add id 8 via 1.1.1.8 dev dummy8
ip next add id 9 via 1.1.1.9 dev dummy9
ip next add id 10 via 1.1.1.10 dev dummy10
ip next add id 11 via 1.1.1.11 dev dummy11
ip next add id 12 via 1.1.1.12 dev dummy12
ip next add id 13 via 1.1.1.13 dev dummy13
ip next add id 14 via 1.1.1.14 dev dummy14
ip next add id 15 via 1.1.1.15 dev dummy15
ip next add id 16 via 1.1.1.16 dev dummy16
ip next add id 17 via 1.1.1.17 dev dummy17
ip next add id 18 via 1.1.1.18 dev dummy18
ip next add id 19 via 1.1.1.19 dev dummy19

ip next add id 1111 group 1/2/3/4/5/6/7/8/9/10/11/12/13/14/15/16/17/18/19
ip next del id 1111

Fixes: 430a049190de ("nexthop: Add support for nexthop groups")
Signed-off-by: Stephen Worley <sworley@cumulusnetworks.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/nexthop.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 511eaa94e2d1..d072c326dd64 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -321,7 +321,9 @@ static size_t nh_nlmsg_size_single(struct nexthop *nh)
 
 static size_t nh_nlmsg_size(struct nexthop *nh)
 {
-	size_t sz = nla_total_size(4);    /* NHA_ID */
+	size_t sz = NLMSG_ALIGN(sizeof(struct nhmsg));
+
+	sz += nla_total_size(4); /* NHA_ID */
 
 	if (nh->is_group)
 		sz += nh_nlmsg_size_grp(nh);
-- 
2.21.1


From 7f7f04e7ffe9ed8746d8162aeef5950f843e6458 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 24 Jan 2020 23:08:04 +0000
Subject: [PATCH 10/10] rxrpc: Fix use-after-free in rxrpc_receive_data()

[ Upstream commit 122d74fac84204b9a98263636f6f9a3b2e665639 ]

The subpacket scanning loop in rxrpc_receive_data() references the
subpacket count in the private data part of the sk_buff in the loop
termination condition.  However, when the final subpacket is pasted into
the ring buffer, the function is no longer has a ref on the sk_buff and
should not be looking at sp->* any more.  This point is actually marked in
the code when skb is cleared (but sp is not - which is an error).

Fix this by caching sp->nr_subpackets in a local variable and using that
instead.

Also clear 'sp' to catch accesses after that point.

This can show up as an oops in rxrpc_get_skb() if sp->nr_subpackets gets
trashed by the sk_buff getting freed and reused in the meantime.

Fixes: e2de6c404898 ("rxrpc: Use info in skbuff instead of reparsing a jumbo packet")
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/input.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 86bd133b4fa0..96d54e5bf7bc 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -413,7 +413,7 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb)
 {
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
 	enum rxrpc_call_state state;
-	unsigned int j;
+	unsigned int j, nr_subpackets;
 	rxrpc_serial_t serial = sp->hdr.serial, ack_serial = 0;
 	rxrpc_seq_t seq0 = sp->hdr.seq, hard_ack;
 	bool immediate_ack = false, jumbo_bad = false;
@@ -457,7 +457,8 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb)
 	call->ackr_prev_seq = seq0;
 	hard_ack = READ_ONCE(call->rx_hard_ack);
 
-	if (sp->nr_subpackets > 1) {
+	nr_subpackets = sp->nr_subpackets;
+	if (nr_subpackets > 1) {
 		if (call->nr_jumbo_bad > 3) {
 			ack = RXRPC_ACK_NOSPACE;
 			ack_serial = serial;
@@ -465,11 +466,11 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb)
 		}
 	}
 
-	for (j = 0; j < sp->nr_subpackets; j++) {
+	for (j = 0; j < nr_subpackets; j++) {
 		rxrpc_serial_t serial = sp->hdr.serial + j;
 		rxrpc_seq_t seq = seq0 + j;
 		unsigned int ix = seq & RXRPC_RXTX_BUFF_MASK;
-		bool terminal = (j == sp->nr_subpackets - 1);
+		bool terminal = (j == nr_subpackets - 1);
 		bool last = terminal && (sp->rx_flags & RXRPC_SKB_INCL_LAST);
 		u8 flags, annotation = j;
 
@@ -506,7 +507,7 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb)
 		}
 
 		if (call->rxtx_buffer[ix]) {
-			rxrpc_input_dup_data(call, seq, sp->nr_subpackets > 1,
+			rxrpc_input_dup_data(call, seq, nr_subpackets > 1,
 					     &jumbo_bad);
 			if (ack != RXRPC_ACK_DUPLICATE) {
 				ack = RXRPC_ACK_DUPLICATE;
@@ -564,6 +565,7 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb)
 			 * ring.
 			 */
 			skb = NULL;
+			sp = NULL;
 		}
 
 		if (last) {
-- 
2.21.1

Re: [PATCHES] Networking

[Greg KH]

On Thu, Jan 30, 2020 at 11:12:27AM +0100, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v5.4 and v5.5
> -stable, respectively.

All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 105 bytes --]


Please queue up the following networking bug fixes for v5.4 and
v5.5 -stable, respectively.

Thank you!

[-- Attachment #2: net_54.mbox --]
[-- Type: Application/Octet-Stream, Size: 53380 bytes --]

From 829db68c89a475433e8dc8322de58c6b7ef63f33 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Mon, 27 Jan 2020 04:56:22 -0500
Subject: [PATCH 01/20] bnxt_en: Move devlink_register before registering
 netdev

[ Upstream commit cda2cab0771183932d6ba73c5ac63bb63decdadf ]

Latest kernels get the phys_port_name via devlink, if
ndo_get_phys_port_name is not defined. To provide the phys_port_name
correctly, register devlink before registering netdev.

Also call devlink_port_type_eth_set() after registering netdev as
devlink port updates the netdev structure and notifies user.

Cc: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c         | 12 ++++++++----
 drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c |  1 -
 2 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index cf292f7c3d3c..2d04a45945a7 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -11359,9 +11359,9 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 		bnxt_sriov_disable(bp);
 
 	bnxt_dl_fw_reporters_destroy(bp, true);
-	bnxt_dl_unregister(bp);
 	pci_disable_pcie_error_reporting(pdev);
 	unregister_netdev(dev);
+	bnxt_dl_unregister(bp);
 	bnxt_shutdown_tc(bp);
 	bnxt_cancel_sp_work(bp);
 	bp->sp_event = 0;
@@ -11850,11 +11850,14 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		bnxt_init_tc(bp);
 	}
 
+	bnxt_dl_register(bp);
+
 	rc = register_netdev(dev);
 	if (rc)
-		goto init_err_cleanup_tc;
+		goto init_err_cleanup;
 
-	bnxt_dl_register(bp);
+	if (BNXT_PF(bp))
+		devlink_port_type_eth_set(&bp->dl_port, bp->dev);
 	bnxt_dl_fw_reporters_create(bp);
 
 	netdev_info(dev, "%s found at mem %lx, node addr %pM\n",
@@ -11864,7 +11867,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	return 0;
 
-init_err_cleanup_tc:
+init_err_cleanup:
+	bnxt_dl_unregister(bp);
 	bnxt_shutdown_tc(bp);
 	bnxt_clear_int_mode(bp);
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index 1e236e74ff2f..2d817ba0602c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -482,7 +482,6 @@ int bnxt_dl_register(struct bnxt *bp)
 		netdev_err(bp->dev, "devlink_port_register failed");
 		goto err_dl_param_unreg;
 	}
-	devlink_port_type_eth_set(&bp->dl_port, bp->dev);
 
 	rc = devlink_port_params_register(&bp->dl_port, bnxt_dl_port_params,
 					  ARRAY_SIZE(bnxt_dl_port_params));
-- 
2.21.1


From 14a5bc37e9692866c6d51d313a456f03a41e1955 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 31 Jan 2020 15:27:04 -0800
Subject: [PATCH 02/20] cls_rsvp: fix rsvp_policy

[ Upstream commit cb3c0e6bdf64d0d124e94ce43cbe4ccbb9b37f51 ]

NLA_BINARY can be confusing, since .len value represents
the max size of the blob.

cls_rsvp really wants user space to provide long enough data
for TCA_RSVP_DST and TCA_RSVP_SRC attributes.

BUG: KMSAN: uninit-value in rsvp_get net/sched/cls_rsvp.h:258 [inline]
BUG: KMSAN: uninit-value in gen_handle net/sched/cls_rsvp.h:402 [inline]
BUG: KMSAN: uninit-value in rsvp_change+0x1ae9/0x4220 net/sched/cls_rsvp.h:572
CPU: 1 PID: 13228 Comm: syz-executor.1 Not tainted 5.5.0-rc5-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c9/0x220 lib/dump_stack.c:118
 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:118
 __msan_warning+0x58/0xa0 mm/kmsan/kmsan_instr.c:215
 rsvp_get net/sched/cls_rsvp.h:258 [inline]
 gen_handle net/sched/cls_rsvp.h:402 [inline]
 rsvp_change+0x1ae9/0x4220 net/sched/cls_rsvp.h:572
 tc_new_tfilter+0x31fe/0x5010 net/sched/cls_api.c:2104
 rtnetlink_rcv_msg+0xcb7/0x1570 net/core/rtnetlink.c:5415
 netlink_rcv_skb+0x451/0x650 net/netlink/af_netlink.c:2477
 rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:5442
 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
 netlink_unicast+0xf9e/0x1100 net/netlink/af_netlink.c:1328
 netlink_sendmsg+0x1248/0x14d0 net/netlink/af_netlink.c:1917
 sock_sendmsg_nosec net/socket.c:639 [inline]
 sock_sendmsg net/socket.c:659 [inline]
 ____sys_sendmsg+0x12b6/0x1350 net/socket.c:2330
 ___sys_sendmsg net/socket.c:2384 [inline]
 __sys_sendmsg+0x451/0x5f0 net/socket.c:2417
 __do_sys_sendmsg net/socket.c:2426 [inline]
 __se_sys_sendmsg+0x97/0xb0 net/socket.c:2424
 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2424
 do_syscall_64+0xb8/0x160 arch/x86/entry/common.c:296
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x45b349
Code: ad b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f269d43dc78 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 00007f269d43e6d4 RCX: 000000000045b349
RDX: 0000000000000000 RSI: 00000000200001c0 RDI: 0000000000000003
RBP: 000000000075bfc8 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff
R13: 00000000000009c2 R14: 00000000004cb338 R15: 000000000075bfd4

Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:144 [inline]
 kmsan_internal_poison_shadow+0x66/0xd0 mm/kmsan/kmsan.c:127
 kmsan_slab_alloc+0x8a/0xe0 mm/kmsan/kmsan_hooks.c:82
 slab_alloc_node mm/slub.c:2774 [inline]
 __kmalloc_node_track_caller+0xb40/0x1200 mm/slub.c:4382
 __kmalloc_reserve net/core/skbuff.c:141 [inline]
 __alloc_skb+0x2fd/0xac0 net/core/skbuff.c:209
 alloc_skb include/linux/skbuff.h:1049 [inline]
 netlink_alloc_large_skb net/netlink/af_netlink.c:1174 [inline]
 netlink_sendmsg+0x7d3/0x14d0 net/netlink/af_netlink.c:1892
 sock_sendmsg_nosec net/socket.c:639 [inline]
 sock_sendmsg net/socket.c:659 [inline]
 ____sys_sendmsg+0x12b6/0x1350 net/socket.c:2330
 ___sys_sendmsg net/socket.c:2384 [inline]
 __sys_sendmsg+0x451/0x5f0 net/socket.c:2417
 __do_sys_sendmsg net/socket.c:2426 [inline]
 __se_sys_sendmsg+0x97/0xb0 net/socket.c:2424
 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2424
 do_syscall_64+0xb8/0x160 arch/x86/entry/common.c:296
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 6fa8c0144b77 ("[NET_SCHED]: Use nla_policy for attribute validation in classifiers")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/cls_rsvp.h | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h
index c22624131949..d36949d9382c 100644
--- a/net/sched/cls_rsvp.h
+++ b/net/sched/cls_rsvp.h
@@ -463,10 +463,8 @@ static u32 gen_tunnel(struct rsvp_head *data)
 
 static const struct nla_policy rsvp_policy[TCA_RSVP_MAX + 1] = {
 	[TCA_RSVP_CLASSID]	= { .type = NLA_U32 },
-	[TCA_RSVP_DST]		= { .type = NLA_BINARY,
-				    .len = RSVP_DST_LEN * sizeof(u32) },
-	[TCA_RSVP_SRC]		= { .type = NLA_BINARY,
-				    .len = RSVP_DST_LEN * sizeof(u32) },
+	[TCA_RSVP_DST]		= { .len = RSVP_DST_LEN * sizeof(u32) },
+	[TCA_RSVP_SRC]		= { .len = RSVP_DST_LEN * sizeof(u32) },
 	[TCA_RSVP_PINFO]	= { .len = sizeof(struct tc_rsvp_pinfo) },
 };
 
-- 
2.21.1


From 724b3e34f789057547b6c1eac2353ed2c40e5307 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Tue, 4 Feb 2020 03:24:59 +0000
Subject: [PATCH 03/20] gtp: use __GFP_NOWARN to avoid memalloc warning

[ Upstream commit bd5cd35b782abf5437fbd01dfaee12437d20e832 ]

gtp hashtable size is received by user-space.
So, this hashtable size could be too large. If so, kmalloc will internally
print a warning message.
This warning message is actually not necessary for the gtp module.
So, this patch adds __GFP_NOWARN to avoid this message.

Splat looks like:
[ 2171.200049][ T1860] WARNING: CPU: 1 PID: 1860 at mm/page_alloc.c:4713 __alloc_pages_nodemask+0x2f3/0x740
[ 2171.238885][ T1860] Modules linked in: gtp veth openvswitch nsh nf_conncount nf_nat nf_conntrack nf_defrag_ipv]
[ 2171.262680][ T1860] CPU: 1 PID: 1860 Comm: gtp-link Not tainted 5.5.0+ #321
[ 2171.263567][ T1860] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[ 2171.264681][ T1860] RIP: 0010:__alloc_pages_nodemask+0x2f3/0x740
[ 2171.265332][ T1860] Code: 64 fe ff ff 65 48 8b 04 25 c0 0f 02 00 48 05 f0 12 00 00 41 be 01 00 00 00 49 89 47 0
[ 2171.267301][ T1860] RSP: 0018:ffff8880b51af1f0 EFLAGS: 00010246
[ 2171.268320][ T1860] RAX: ffffed1016a35e43 RBX: 0000000000000000 RCX: 0000000000000000
[ 2171.269517][ T1860] RDX: 0000000000000000 RSI: 000000000000000b RDI: 0000000000000000
[ 2171.270305][ T1860] RBP: 0000000000040cc0 R08: ffffed1018893109 R09: dffffc0000000000
[ 2171.275973][ T1860] R10: 0000000000000001 R11: ffffed1018893108 R12: 1ffff11016a35e43
[ 2171.291039][ T1860] R13: 000000000000000b R14: 000000000000000b R15: 00000000000f4240
[ 2171.292328][ T1860] FS:  00007f53cbc83740(0000) GS:ffff8880da000000(0000) knlGS:0000000000000000
[ 2171.293409][ T1860] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 2171.294586][ T1860] CR2: 000055f540014508 CR3: 00000000b49f2004 CR4: 00000000000606e0
[ 2171.295424][ T1860] Call Trace:
[ 2171.295756][ T1860]  ? mark_held_locks+0xa5/0xe0
[ 2171.296659][ T1860]  ? __alloc_pages_slowpath+0x21b0/0x21b0
[ 2171.298283][ T1860]  ? gtp_encap_enable_socket+0x13e/0x400 [gtp]
[ 2171.298962][ T1860]  ? alloc_pages_current+0xc1/0x1a0
[ 2171.299475][ T1860]  kmalloc_order+0x22/0x80
[ 2171.299936][ T1860]  kmalloc_order_trace+0x1d/0x140
[ 2171.300437][ T1860]  __kmalloc+0x302/0x3a0
[ 2171.300896][ T1860]  gtp_newlink+0x293/0xba0 [gtp]
[ ... ]

Fixes: 459aa660eb1d ("gtp: add initial driver for datapath of GPRS Tunneling Protocol (GTP-U)")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/gtp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 9b3ba98726d7..3a53d222bfcc 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -767,12 +767,12 @@ static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize)
 	int i;
 
 	gtp->addr_hash = kmalloc_array(hsize, sizeof(struct hlist_head),
-				       GFP_KERNEL);
+				       GFP_KERNEL | __GFP_NOWARN);
 	if (gtp->addr_hash == NULL)
 		return -ENOMEM;
 
 	gtp->tid_hash = kmalloc_array(hsize, sizeof(struct hlist_head),
-				      GFP_KERNEL);
+				      GFP_KERNEL | __GFP_NOWARN);
 	if (gtp->tid_hash == NULL)
 		goto err1;
 
-- 
2.21.1


From 6aaa459a110ebdad6ebc598b277a1a54eb8c456a Mon Sep 17 00:00:00 2001
From: Ridge Kennedy <ridge.kennedy@alliedtelesis.co.nz>
Date: Tue, 4 Feb 2020 12:24:00 +1300
Subject: [PATCH 04/20] l2tp: Allow duplicate session creation with UDP

[ Upstream commit 0d0d9a388a858e271bb70e71e99e7fe2a6fd6f64 ]

In the past it was possible to create multiple L2TPv3 sessions with the
same session id as long as the sessions belonged to different tunnels.
The resulting sessions had issues when used with IP encapsulated tunnels,
but worked fine with UDP encapsulated ones. Some applications began to
rely on this behaviour to avoid having to negotiate unique session ids.

Some time ago a change was made to require session ids to be unique across
all tunnels, breaking the applications making use of this "feature".

This change relaxes the duplicate session id check to allow duplicates
if both of the colliding sessions belong to UDP encapsulated tunnels.

Fixes: dbdbc73b4478 ("l2tp: fix duplicate session creation")
Signed-off-by: Ridge Kennedy <ridge.kennedy@alliedtelesis.co.nz>
Acked-by: James Chapman <jchapman@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index f82ea12bac37..425b95eb7e87 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -322,8 +322,13 @@ int l2tp_session_register(struct l2tp_session *session,
 
 		spin_lock_bh(&pn->l2tp_session_hlist_lock);
 
+		/* IP encap expects session IDs to be globally unique, while
+		 * UDP encap doesn't.
+		 */
 		hlist_for_each_entry(session_walk, g_head, global_hlist)
-			if (session_walk->session_id == session->session_id) {
+			if (session_walk->session_id == session->session_id &&
+			    (session_walk->tunnel->encap == L2TP_ENCAPTYPE_IP ||
+			     tunnel->encap == L2TP_ENCAPTYPE_IP)) {
 				err = -EEXIST;
 				goto err_tlock_pnlock;
 			}
-- 
2.21.1


From 5df617b51551dffda0409e601e2eacc846fb3a9e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 3 Feb 2020 10:15:07 -0800
Subject: [PATCH 05/20] net: hsr: fix possible NULL deref in hsr_handle_frame()

[ Upstream commit 2b5b8251bc9fe2f9118411f037862ee17cf81e97 ]

hsr_port_get_rcu() can return NULL, so we need to be careful.

general protection fault, probably for non-canonical address 0xdffffc0000000006: 0000 [#1] PREEMPT SMP KASAN
KASAN: null-ptr-deref in range [0x0000000000000030-0x0000000000000037]
CPU: 1 PID: 10249 Comm: syz-executor.5 Not tainted 5.5.0-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:__read_once_size include/linux/compiler.h:199 [inline]
RIP: 0010:hsr_addr_is_self+0x86/0x330 net/hsr/hsr_framereg.c:44
Code: 04 00 f3 f3 f3 65 48 8b 04 25 28 00 00 00 48 89 45 d0 31 c0 e8 6b ff 94 f9 4c 89 f2 48 b8 00 00 00 00 00 fc ff df 48 c1 ea 03 <80> 3c 02 00 0f 85 75 02 00 00 48 8b 43 30 49 39 c6 49 89 47 c0 0f
RSP: 0018:ffffc90000da8a90 EFLAGS: 00010206
RAX: dffffc0000000000 RBX: 0000000000000000 RCX: ffffffff87e0cc33
RDX: 0000000000000006 RSI: ffffffff87e035d5 RDI: 0000000000000000
RBP: ffffc90000da8b20 R08: ffff88808e7de040 R09: ffffed1015d2707c
R10: ffffed1015d2707b R11: ffff8880ae9383db R12: ffff8880a689bc5e
R13: 1ffff920001b5153 R14: 0000000000000030 R15: ffffc90000da8af8
FS:  00007fd7a42be700(0000) GS:ffff8880ae900000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000001b32338000 CR3: 00000000a928c000 CR4: 00000000001406e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 <IRQ>
 hsr_handle_frame+0x1c5/0x630 net/hsr/hsr_slave.c:31
 __netif_receive_skb_core+0xfbc/0x30b0 net/core/dev.c:5099
 __netif_receive_skb_one_core+0xa8/0x1a0 net/core/dev.c:5196
 __netif_receive_skb+0x2c/0x1d0 net/core/dev.c:5312
 process_backlog+0x206/0x750 net/core/dev.c:6144
 napi_poll net/core/dev.c:6582 [inline]
 net_rx_action+0x508/0x1120 net/core/dev.c:6650
 __do_softirq+0x262/0x98c kernel/softirq.c:292
 do_softirq_own_stack+0x2a/0x40 arch/x86/entry/entry_64.S:1082
 </IRQ>

Fixes: c5a759117210 ("net/hsr: Use list_head (and rcu) instead of array for slave devices.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/hsr/hsr_slave.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c
index ee561297d8a7..fbfd0db182b7 100644
--- a/net/hsr/hsr_slave.c
+++ b/net/hsr/hsr_slave.c
@@ -27,6 +27,8 @@ static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb)
 
 	rcu_read_lock(); /* hsr->node_db, hsr->ports */
 	port = hsr_port_get_rcu(skb->dev);
+	if (!port)
+		goto finish_pass;
 
 	if (hsr_addr_is_self(port->hsr, eth_hdr(skb)->h_source)) {
 		/* Directly kill frames sent by ourselves */
-- 
2.21.1


From f77c4aee5f9759076ddd1b57462e21fe887d6895 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sun, 2 Feb 2020 21:14:35 -0800
Subject: [PATCH 06/20] net_sched: fix an OOB access in cls_tcindex

[ Upstream commit 599be01ee567b61f4471ee8078870847d0a11e8e ]

As Eric noticed, tcindex_alloc_perfect_hash() uses cp->hash
to compute the size of memory allocation, but cp->hash is
set again after the allocation, this caused an out-of-bound
access.

So we have to move all cp->hash initialization and computation
before the memory allocation. Move cp->mask and cp->shift together
as cp->hash may need them for computation too.

Reported-and-tested-by: syzbot+35d4dea36c387813ed31@syzkaller.appspotmail.com
Fixes: 331b72922c5f ("net: sched: RCU cls_tcindex")
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Cc: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_tcindex.c | 40 ++++++++++++++++++++--------------------
 1 file changed, 20 insertions(+), 20 deletions(-)

diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 3d4a1280352f..0323aee03de7 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -333,12 +333,31 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	cp->fall_through = p->fall_through;
 	cp->tp = tp;
 
+	if (tb[TCA_TCINDEX_HASH])
+		cp->hash = nla_get_u32(tb[TCA_TCINDEX_HASH]);
+
+	if (tb[TCA_TCINDEX_MASK])
+		cp->mask = nla_get_u16(tb[TCA_TCINDEX_MASK]);
+
+	if (tb[TCA_TCINDEX_SHIFT])
+		cp->shift = nla_get_u32(tb[TCA_TCINDEX_SHIFT]);
+
+	if (!cp->hash) {
+		/* Hash not specified, use perfect hash if the upper limit
+		 * of the hashing index is below the threshold.
+		 */
+		if ((cp->mask >> cp->shift) < PERFECT_HASH_THRESHOLD)
+			cp->hash = (cp->mask >> cp->shift) + 1;
+		else
+			cp->hash = DEFAULT_HASH_SIZE;
+	}
+
 	if (p->perfect) {
 		int i;
 
 		if (tcindex_alloc_perfect_hash(net, cp) < 0)
 			goto errout;
-		for (i = 0; i < cp->hash; i++)
+		for (i = 0; i < min(cp->hash, p->hash); i++)
 			cp->perfect[i].res = p->perfect[i].res;
 		balloc = 1;
 	}
@@ -350,15 +369,6 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	if (old_r)
 		cr = r->res;
 
-	if (tb[TCA_TCINDEX_HASH])
-		cp->hash = nla_get_u32(tb[TCA_TCINDEX_HASH]);
-
-	if (tb[TCA_TCINDEX_MASK])
-		cp->mask = nla_get_u16(tb[TCA_TCINDEX_MASK]);
-
-	if (tb[TCA_TCINDEX_SHIFT])
-		cp->shift = nla_get_u32(tb[TCA_TCINDEX_SHIFT]);
-
 	err = -EBUSY;
 
 	/* Hash already allocated, make sure that we still meet the
@@ -376,16 +386,6 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	if (tb[TCA_TCINDEX_FALL_THROUGH])
 		cp->fall_through = nla_get_u32(tb[TCA_TCINDEX_FALL_THROUGH]);
 
-	if (!cp->hash) {
-		/* Hash not specified, use perfect hash if the upper limit
-		 * of the hashing index is below the threshold.
-		 */
-		if ((cp->mask >> cp->shift) < PERFECT_HASH_THRESHOLD)
-			cp->hash = (cp->mask >> cp->shift) + 1;
-		else
-			cp->hash = DEFAULT_HASH_SIZE;
-	}
-
 	if (!cp->perfect && !cp->h)
 		cp->alloc_hash = cp->hash;
 
-- 
2.21.1


From ededc0223e4fd2f613a0df3f6e496875c3d30b15 Mon Sep 17 00:00:00 2001
From: Nicolin Chen <nicoleotsuka@gmail.com>
Date: Fri, 31 Jan 2020 18:01:24 -0800
Subject: [PATCH 07/20] net: stmmac: Delete txtimer in suspend()

[ Upstream commit 14b41a2959fbaa50932699d32ceefd6643abacc6 ]

When running v5.5 with a rootfs on NFS, memory abort may happen in
the system resume stage:
 Unable to handle kernel paging request at virtual address dead00000000012a
 [dead00000000012a] address between user and kernel address ranges
 pc : run_timer_softirq+0x334/0x3d8
 lr : run_timer_softirq+0x244/0x3d8
 x1 : ffff800011cafe80 x0 : dead000000000122
 Call trace:
  run_timer_softirq+0x334/0x3d8
  efi_header_end+0x114/0x234
  irq_exit+0xd0/0xd8
  __handle_domain_irq+0x60/0xb0
  gic_handle_irq+0x58/0xa8
  el1_irq+0xb8/0x180
  arch_cpu_idle+0x10/0x18
  do_idle+0x1d8/0x2b0
  cpu_startup_entry+0x24/0x40
  secondary_start_kernel+0x1b4/0x208
 Code: f9000693 a9400660 f9000020 b4000040 (f9000401)
 ---[ end trace bb83ceeb4c482071 ]---
 Kernel panic - not syncing: Fatal exception in interrupt
 SMP: stopping secondary CPUs
 SMP: failed to stop secondary CPUs 2-3
 Kernel Offset: disabled
 CPU features: 0x00002,2300aa30
 Memory Limit: none
 ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]---

It's found that stmmac_xmit() and stmmac_resume() sometimes might
run concurrently, possibly resulting in a race condition between
mod_timer() and setup_timer(), being called by stmmac_xmit() and
stmmac_resume() respectively.

Since the resume() runs setup_timer() every time, it'd be safer to
have del_timer_sync() in the suspend() as the counterpart.

Signed-off-by: Nicolin Chen <nicoleotsuka@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 06dd65c419c4..582176d869c3 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -4763,6 +4763,7 @@ int stmmac_suspend(struct device *dev)
 {
 	struct net_device *ndev = dev_get_drvdata(dev);
 	struct stmmac_priv *priv = netdev_priv(ndev);
+	u32 chan;
 
 	if (!ndev || !netif_running(ndev))
 		return 0;
@@ -4776,6 +4777,9 @@ int stmmac_suspend(struct device *dev)
 
 	stmmac_disable_all_queues(priv);
 
+	for (chan = 0; chan < priv->plat->tx_queues_to_use; chan++)
+		del_timer_sync(&priv->tx_queue[chan].txtimer);
+
 	/* Stop TX/RX DMA */
 	stmmac_stop_all_dma(priv);
 
-- 
2.21.1


From c2c17ccc6a7378865acadd24a8a7a0cbb41f1453 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 2 Feb 2020 02:41:38 -0500
Subject: [PATCH 08/20] bnxt_en: Fix TC queue mapping.

[ Upstream commit 18e4960c18f484ac288f41b43d0e6c4c88e6ea78 ]

The driver currently only calls netdev_set_tc_queue when the number of
TCs is greater than 1.  Instead, the comparison should be greater than
or equal to 1.  Even with 1 TC, we need to set the queue mapping.

This bug can cause warnings when the number of TCs is changed back to 1.

Fixes: 7809592d3e2e ("bnxt_en: Enable MSIX early in bnxt_init_one().")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 2d04a45945a7..e7496b56e4c6 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -7873,7 +7873,7 @@ static void bnxt_setup_msix(struct bnxt *bp)
 	int tcs, i;
 
 	tcs = netdev_get_num_tc(dev);
-	if (tcs > 1) {
+	if (tcs) {
 		int i, off, count;
 
 		for (i = 0; i < tcs; i++) {
-- 
2.21.1


From 8e3ddcf4bc38cbc89285370a8304e1fa109b2377 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 30 Jan 2020 21:50:35 +0000
Subject: [PATCH 09/20] rxrpc: Fix use-after-free in rxrpc_put_local()

[ Upstream commit fac20b9e738523fc884ee3ea5be360a321cd8bad ]

Fix rxrpc_put_local() to not access local->debug_id after calling
atomic_dec_return() as, unless that returned n==0, we no longer have the
right to access the object.

Fixes: 06d9532fa6b3 ("rxrpc: Fix read-after-free in rxrpc_queue_local()")
Signed-off-by: David Howells <dhowells@redhat.com>
---
 net/rxrpc/local_object.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index 36587260cabd..3aa179efcda4 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -364,11 +364,14 @@ void rxrpc_queue_local(struct rxrpc_local *local)
 void rxrpc_put_local(struct rxrpc_local *local)
 {
 	const void *here = __builtin_return_address(0);
+	unsigned int debug_id;
 	int n;
 
 	if (local) {
+		debug_id = local->debug_id;
+
 		n = atomic_dec_return(&local->usage);
-		trace_rxrpc_local(local->debug_id, rxrpc_local_put, n, here);
+		trace_rxrpc_local(debug_id, rxrpc_local_put, n, here);
 
 		if (n == 0)
 			call_rcu(&local->rcu, rxrpc_local_rcu);
-- 
2.21.1


From 39abd0cf1d7f3d2a0d264e08d5ae9b0059927ba0 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 30 Jan 2020 21:50:36 +0000
Subject: [PATCH 10/20] rxrpc: Fix insufficient receive notification generation

[ Upstream commit f71dbf2fb28489a79bde0dca1c8adfb9cdb20a6b ]

In rxrpc_input_data(), rxrpc_notify_socket() is called if the base sequence
number of the packet is immediately following the hard-ack point at the end
of the function.  However, this isn't sufficient, since the recvmsg side
may have been advancing the window and then overrun the position in which
we're adding - at which point rx_hard_ack >= seq0 and no notification is
generated.

Fix this by always generating a notification at the end of the input
function.

Without this, a long call may stall, possibly indefinitely.

Fixes: 248f219cb8bc ("rxrpc: Rewrite the data and ack handling code")
Signed-off-by: David Howells <dhowells@redhat.com>
---
 net/rxrpc/input.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 96d54e5bf7bc..ef10fbf71b15 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -599,10 +599,8 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb)
 				  false, true,
 				  rxrpc_propose_ack_input_data);
 
-	if (seq0 == READ_ONCE(call->rx_hard_ack) + 1) {
-		trace_rxrpc_notify_socket(call->debug_id, serial);
-		rxrpc_notify_socket(call);
-	}
+	trace_rxrpc_notify_socket(call->debug_id, serial);
+	rxrpc_notify_socket(call);
 
 unlock:
 	spin_unlock(&call->input_lock);
-- 
2.21.1


From a1af1d026188eac0611972f2fbfc1360a4c6ac86 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 30 Jan 2020 21:50:36 +0000
Subject: [PATCH 11/20] rxrpc: Fix missing active use pinning of rxrpc_local
 object

[ Upstream commit 04d36d748fac349b068ef621611f454010054c58 ]

The introduction of a split between the reference count on rxrpc_local
objects and the usage count didn't quite go far enough.  A number of kernel
work items need to make use of the socket to perform transmission.  These
also need to get an active count on the local object to prevent the socket
from being closed.

Fix this by getting the active count in those places.

Also split out the raw active count get/put functions as these places tend
to hold refs on the rxrpc_local object already, so getting and putting an
extra object ref is just a waste of time.

The problem can lead to symptoms like:

    BUG: kernel NULL pointer dereference, address: 0000000000000018
    ..
    CPU: 2 PID: 818 Comm: kworker/u9:0 Not tainted 5.5.0-fscache+ #51
    ...
    RIP: 0010:selinux_socket_sendmsg+0x5/0x13
    ...
    Call Trace:
     security_socket_sendmsg+0x2c/0x3e
     sock_sendmsg+0x1a/0x46
     rxrpc_send_keepalive+0x131/0x1ae
     rxrpc_peer_keepalive_worker+0x219/0x34b
     process_one_work+0x18e/0x271
     worker_thread+0x1a3/0x247
     kthread+0xe6/0xeb
     ret_from_fork+0x1f/0x30

Fixes: 730c5fd42c1e ("rxrpc: Fix local endpoint refcounting")
Signed-off-by: David Howells <dhowells@redhat.com>
---
 net/rxrpc/af_rxrpc.c     |  2 ++
 net/rxrpc/ar-internal.h  | 10 ++++++++++
 net/rxrpc/conn_event.c   | 30 ++++++++++++++++++----------
 net/rxrpc/local_object.c | 18 +++++++----------
 net/rxrpc/peer_event.c   | 42 ++++++++++++++++++++++------------------
 5 files changed, 62 insertions(+), 40 deletions(-)

diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index d72ddb67bb74..4a6ca9723a12 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -194,6 +194,7 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len)
 service_in_use:
 	write_unlock(&local->services_lock);
 	rxrpc_unuse_local(local);
+	rxrpc_put_local(local);
 	ret = -EADDRINUSE;
 error_unlock:
 	release_sock(&rx->sk);
@@ -899,6 +900,7 @@ static int rxrpc_release_sock(struct sock *sk)
 	rxrpc_purge_queue(&sk->sk_receive_queue);
 
 	rxrpc_unuse_local(rx->local);
+	rxrpc_put_local(rx->local);
 	rx->local = NULL;
 	key_put(rx->key);
 	rx->key = NULL;
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 5e99df80e80a..94441fee85bc 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -1021,6 +1021,16 @@ void rxrpc_unuse_local(struct rxrpc_local *);
 void rxrpc_queue_local(struct rxrpc_local *);
 void rxrpc_destroy_all_locals(struct rxrpc_net *);
 
+static inline bool __rxrpc_unuse_local(struct rxrpc_local *local)
+{
+	return atomic_dec_return(&local->active_users) == 0;
+}
+
+static inline bool __rxrpc_use_local(struct rxrpc_local *local)
+{
+	return atomic_fetch_add_unless(&local->active_users, 1, 0) != 0;
+}
+
 /*
  * misc.c
  */
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index 808a4723f868..06fcff2ebbba 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -438,16 +438,12 @@ static void rxrpc_process_delayed_final_acks(struct rxrpc_connection *conn)
 /*
  * connection-level event processor
  */
-void rxrpc_process_connection(struct work_struct *work)
+static void rxrpc_do_process_connection(struct rxrpc_connection *conn)
 {
-	struct rxrpc_connection *conn =
-		container_of(work, struct rxrpc_connection, processor);
 	struct sk_buff *skb;
 	u32 abort_code = RX_PROTOCOL_ERROR;
 	int ret;
 
-	rxrpc_see_connection(conn);
-
 	if (test_and_clear_bit(RXRPC_CONN_EV_CHALLENGE, &conn->events))
 		rxrpc_secure_connection(conn);
 
@@ -475,18 +471,32 @@ void rxrpc_process_connection(struct work_struct *work)
 		}
 	}
 
-out:
-	rxrpc_put_connection(conn);
-	_leave("");
 	return;
 
 requeue_and_leave:
 	skb_queue_head(&conn->rx_queue, skb);
-	goto out;
+	return;
 
 protocol_error:
 	if (rxrpc_abort_connection(conn, ret, abort_code) < 0)
 		goto requeue_and_leave;
 	rxrpc_free_skb(skb, rxrpc_skb_freed);
-	goto out;
+	return;
+}
+
+void rxrpc_process_connection(struct work_struct *work)
+{
+	struct rxrpc_connection *conn =
+		container_of(work, struct rxrpc_connection, processor);
+
+	rxrpc_see_connection(conn);
+
+	if (__rxrpc_use_local(conn->params.local)) {
+		rxrpc_do_process_connection(conn);
+		rxrpc_unuse_local(conn->params.local);
+	}
+
+	rxrpc_put_connection(conn);
+	_leave("");
+	return;
 }
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index 3aa179efcda4..a6c1349e965d 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -383,14 +383,11 @@ void rxrpc_put_local(struct rxrpc_local *local)
  */
 struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *local)
 {
-	unsigned int au;
-
 	local = rxrpc_get_local_maybe(local);
 	if (!local)
 		return NULL;
 
-	au = atomic_fetch_add_unless(&local->active_users, 1, 0);
-	if (au == 0) {
+	if (!__rxrpc_use_local(local)) {
 		rxrpc_put_local(local);
 		return NULL;
 	}
@@ -404,14 +401,11 @@ struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *local)
  */
 void rxrpc_unuse_local(struct rxrpc_local *local)
 {
-	unsigned int au;
-
 	if (local) {
-		au = atomic_dec_return(&local->active_users);
-		if (au == 0)
+		if (__rxrpc_unuse_local(local)) {
+			rxrpc_get_local(local);
 			rxrpc_queue_local(local);
-		else
-			rxrpc_put_local(local);
+		}
 	}
 }
 
@@ -468,7 +462,7 @@ static void rxrpc_local_processor(struct work_struct *work)
 
 	do {
 		again = false;
-		if (atomic_read(&local->active_users) == 0) {
+		if (!__rxrpc_use_local(local)) {
 			rxrpc_local_destroyer(local);
 			break;
 		}
@@ -482,6 +476,8 @@ static void rxrpc_local_processor(struct work_struct *work)
 			rxrpc_process_local_events(local);
 			again = true;
 		}
+
+		__rxrpc_unuse_local(local);
 	} while (again);
 
 	rxrpc_put_local(local);
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index 48f67a9b1037..923b263c401b 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -364,27 +364,31 @@ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet,
 		if (!rxrpc_get_peer_maybe(peer))
 			continue;
 
-		spin_unlock_bh(&rxnet->peer_hash_lock);
-
-		keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME;
-		slot = keepalive_at - base;
-		_debug("%02x peer %u t=%d {%pISp}",
-		       cursor, peer->debug_id, slot, &peer->srx.transport);
+		if (__rxrpc_use_local(peer->local)) {
+			spin_unlock_bh(&rxnet->peer_hash_lock);
+
+			keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME;
+			slot = keepalive_at - base;
+			_debug("%02x peer %u t=%d {%pISp}",
+			       cursor, peer->debug_id, slot, &peer->srx.transport);
+
+			if (keepalive_at <= base ||
+			    keepalive_at > base + RXRPC_KEEPALIVE_TIME) {
+				rxrpc_send_keepalive(peer);
+				slot = RXRPC_KEEPALIVE_TIME;
+			}
 
-		if (keepalive_at <= base ||
-		    keepalive_at > base + RXRPC_KEEPALIVE_TIME) {
-			rxrpc_send_keepalive(peer);
-			slot = RXRPC_KEEPALIVE_TIME;
+			/* A transmission to this peer occurred since last we
+			 * examined it so put it into the appropriate future
+			 * bucket.
+			 */
+			slot += cursor;
+			slot &= mask;
+			spin_lock_bh(&rxnet->peer_hash_lock);
+			list_add_tail(&peer->keepalive_link,
+				      &rxnet->peer_keepalive[slot & mask]);
+			rxrpc_unuse_local(peer->local);
 		}
-
-		/* A transmission to this peer occurred since last we examined
-		 * it so put it into the appropriate future bucket.
-		 */
-		slot += cursor;
-		slot &= mask;
-		spin_lock_bh(&rxnet->peer_hash_lock);
-		list_add_tail(&peer->keepalive_link,
-			      &rxnet->peer_keepalive[slot & mask]);
 		rxrpc_put_peer_locked(peer);
 	}
 
-- 
2.21.1


From a9591f4c9d7e6cf877ac3fa84763041ad55fbd00 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 30 Jan 2020 21:50:36 +0000
Subject: [PATCH 12/20] rxrpc: Fix NULL pointer deref due to call->conn being
 cleared on disconnect

[ Upstream commit 5273a191dca65a675dc0bcf3909e59c6933e2831 ]

When a call is disconnected, the connection pointer from the call is
cleared to make sure it isn't used again and to prevent further attempted
transmission for the call.  Unfortunately, there might be a daemon trying
to use it at the same time to transmit a packet.

Fix this by keeping call->conn set, but setting a flag on the call to
indicate disconnection instead.

Remove also the bits in the transmission functions where the conn pointer is
checked and a ref taken under spinlock as this is now redundant.

Fixes: 8d94aa381dab ("rxrpc: Calls shouldn't hold socket refs")
Signed-off-by: David Howells <dhowells@redhat.com>
---
 net/rxrpc/ar-internal.h |  1 +
 net/rxrpc/call_object.c |  4 ++--
 net/rxrpc/conn_client.c |  3 +--
 net/rxrpc/conn_object.c |  4 ++--
 net/rxrpc/output.c      | 27 +++++++++------------------
 5 files changed, 15 insertions(+), 24 deletions(-)

diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 94441fee85bc..7d730c438404 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -490,6 +490,7 @@ enum rxrpc_call_flag {
 	RXRPC_CALL_RX_HEARD,		/* The peer responded at least once to this call */
 	RXRPC_CALL_RX_UNDERRUN,		/* Got data underrun */
 	RXRPC_CALL_IS_INTR,		/* The call is interruptible */
+	RXRPC_CALL_DISCONNECTED,	/* The call has been disconnected */
 };
 
 /*
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index a31c18c09894..dbdbc4f18b5e 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -493,7 +493,7 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call)
 
 	_debug("RELEASE CALL %p (%d CONN %p)", call, call->debug_id, conn);
 
-	if (conn)
+	if (conn && !test_bit(RXRPC_CALL_DISCONNECTED, &call->flags))
 		rxrpc_disconnect_call(call);
 	if (call->security)
 		call->security->free_call_crypto(call);
@@ -569,6 +569,7 @@ static void rxrpc_rcu_destroy_call(struct rcu_head *rcu)
 	struct rxrpc_call *call = container_of(rcu, struct rxrpc_call, rcu);
 	struct rxrpc_net *rxnet = call->rxnet;
 
+	rxrpc_put_connection(call->conn);
 	rxrpc_put_peer(call->peer);
 	kfree(call->rxtx_buffer);
 	kfree(call->rxtx_annotations);
@@ -590,7 +591,6 @@ void rxrpc_cleanup_call(struct rxrpc_call *call)
 
 	ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE);
 	ASSERT(test_bit(RXRPC_CALL_RELEASED, &call->flags));
-	ASSERTCMP(call->conn, ==, NULL);
 
 	rxrpc_cleanup_ring(call);
 	rxrpc_free_skb(call->tx_pending, rxrpc_skb_cleaned);
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index 376370cd9285..ea7d4c21f889 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -785,6 +785,7 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *call)
 	u32 cid;
 
 	spin_lock(&conn->channel_lock);
+	set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
 
 	cid = call->cid;
 	if (cid) {
@@ -792,7 +793,6 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *call)
 		chan = &conn->channels[channel];
 	}
 	trace_rxrpc_client(conn, channel, rxrpc_client_chan_disconnect);
-	call->conn = NULL;
 
 	/* Calls that have never actually been assigned a channel can simply be
 	 * discarded.  If the conn didn't get used either, it will follow
@@ -908,7 +908,6 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *call)
 	spin_unlock(&rxnet->client_conn_cache_lock);
 out_2:
 	spin_unlock(&conn->channel_lock);
-	rxrpc_put_connection(conn);
 	_leave("");
 	return;
 
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index 38d718e90dc6..c0b3154f7a7e 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -171,6 +171,8 @@ void __rxrpc_disconnect_call(struct rxrpc_connection *conn,
 
 	_enter("%d,%x", conn->debug_id, call->cid);
 
+	set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
+
 	if (rcu_access_pointer(chan->call) == call) {
 		/* Save the result of the call so that we can repeat it if necessary
 		 * through the channel, whilst disposing of the actual call record.
@@ -223,9 +225,7 @@ void rxrpc_disconnect_call(struct rxrpc_call *call)
 	__rxrpc_disconnect_call(conn, call);
 	spin_unlock(&conn->channel_lock);
 
-	call->conn = NULL;
 	conn->idle_timestamp = jiffies;
-	rxrpc_put_connection(conn);
 }
 
 /*
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index 935bb60fff56..bad3d2420344 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -129,7 +129,7 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn,
 int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
 			  rxrpc_serial_t *_serial)
 {
-	struct rxrpc_connection *conn = NULL;
+	struct rxrpc_connection *conn;
 	struct rxrpc_ack_buffer *pkt;
 	struct msghdr msg;
 	struct kvec iov[2];
@@ -139,18 +139,14 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
 	int ret;
 	u8 reason;
 
-	spin_lock_bh(&call->lock);
-	if (call->conn)
-		conn = rxrpc_get_connection_maybe(call->conn);
-	spin_unlock_bh(&call->lock);
-	if (!conn)
+	if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags))
 		return -ECONNRESET;
 
 	pkt = kzalloc(sizeof(*pkt), GFP_KERNEL);
-	if (!pkt) {
-		rxrpc_put_connection(conn);
+	if (!pkt)
 		return -ENOMEM;
-	}
+
+	conn = call->conn;
 
 	msg.msg_name	= &call->peer->srx.transport;
 	msg.msg_namelen	= call->peer->srx.transport_len;
@@ -244,7 +240,6 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
 	}
 
 out:
-	rxrpc_put_connection(conn);
 	kfree(pkt);
 	return ret;
 }
@@ -254,7 +249,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
  */
 int rxrpc_send_abort_packet(struct rxrpc_call *call)
 {
-	struct rxrpc_connection *conn = NULL;
+	struct rxrpc_connection *conn;
 	struct rxrpc_abort_buffer pkt;
 	struct msghdr msg;
 	struct kvec iov[1];
@@ -271,13 +266,11 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call)
 	    test_bit(RXRPC_CALL_TX_LAST, &call->flags))
 		return 0;
 
-	spin_lock_bh(&call->lock);
-	if (call->conn)
-		conn = rxrpc_get_connection_maybe(call->conn);
-	spin_unlock_bh(&call->lock);
-	if (!conn)
+	if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags))
 		return -ECONNRESET;
 
+	conn = call->conn;
+
 	msg.msg_name	= &call->peer->srx.transport;
 	msg.msg_namelen	= call->peer->srx.transport_len;
 	msg.msg_control	= NULL;
@@ -312,8 +305,6 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call)
 		trace_rxrpc_tx_packet(call->debug_id, &pkt.whdr,
 				      rxrpc_tx_point_call_abort);
 	rxrpc_tx_backoff(call, ret);
-
-	rxrpc_put_connection(conn);
 	return ret;
 }
 
-- 
2.21.1


From dd99e9d1097f95dac9794764bf9fd3ec21a4b02d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 31 Jan 2020 09:14:47 -0800
Subject: [PATCH 13/20] tcp: clear tp->total_retrans in tcp_disconnect()

[ Upstream commit c13c48c00a6bc1febc73902505bdec0967bd7095 ]

total_retrans needs to be cleared in tcp_disconnect().

tcp_disconnect() is rarely used, but it is worth fixing it.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: SeongJae Park <sjpark@amazon.de>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 3640e8563a10..554ec2f92792 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2622,6 +2622,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tcp_set_ca_state(sk, TCP_CA_Open);
 	tp->is_sack_reneg = 0;
 	tcp_clear_retrans(tp);
+	tp->total_retrans = 0;
 	inet_csk_delack_init(sk);
 	/* Initialize rcv_mss to TCP_MIN_MSS to avoid division by 0
 	 * issue in __tcp_select_window()
-- 
2.21.1


From 5e6a44dae91055fa8d9d8a61c5a2f5ed5eb1079e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 31 Jan 2020 10:22:47 -0800
Subject: [PATCH 14/20] tcp: clear tp->delivered in tcp_disconnect()

[ Upstream commit 2fbdd56251b5c62f96589f39eded277260de7267 ]

tp->delivered needs to be cleared in tcp_disconnect().

tcp_disconnect() is rarely used, but it is worth fixing it.

Fixes: ddf1af6fa00e ("tcp: new delivery accounting")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 554ec2f92792..5b251643c514 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2618,6 +2618,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tp->snd_cwnd = TCP_INIT_CWND;
 	tp->snd_cwnd_cnt = 0;
 	tp->window_clamp = 0;
+	tp->delivered = 0;
 	tp->delivered_ce = 0;
 	tcp_set_ca_state(sk, TCP_CA_Open);
 	tp->is_sack_reneg = 0;
-- 
2.21.1


From e88edcb59b114b6275d9407fbda98c40bedabf77 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 31 Jan 2020 10:32:41 -0800
Subject: [PATCH 15/20] tcp: clear tp->data_segs{in|out} in tcp_disconnect()

[ Upstream commit db7ffee6f3eb3683cdcaeddecc0a630a14546fe3 ]

tp->data_segs_in and tp->data_segs_out need to be cleared
in tcp_disconnect().

tcp_disconnect() is rarely used, but it is worth fixing it.

Fixes: a44d6eacdaf5 ("tcp: Add RFC4898 tcpEStatsPerfDataSegsOut/In")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Martin KaFai Lau <kafai@fb.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 5b251643c514..79e10d26e2ba 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2639,6 +2639,8 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tp->bytes_acked = 0;
 	tp->bytes_received = 0;
 	tp->bytes_retrans = 0;
+	tp->data_segs_in = 0;
+	tp->data_segs_out = 0;
 	tp->duplicate_sack[0].start_seq = 0;
 	tp->duplicate_sack[0].end_seq = 0;
 	tp->dsack_dups = 0;
-- 
2.21.1


From ca3b8a46171d3a1a34b5b29af90917b0ca0fb6cc Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 31 Jan 2020 10:44:50 -0800
Subject: [PATCH 16/20] tcp: clear tp->segs_{in|out} in tcp_disconnect()

[ Upstream commit 784f8344de750a41344f4bbbebb8507a730fc99c ]

tp->segs_in and tp->segs_out need to be cleared in tcp_disconnect().

tcp_disconnect() is rarely used, but it is worth fixing it.

Fixes: 2efd055c53c0 ("tcp: add tcpi_segs_in and tcpi_segs_out to tcp_info")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Marcelo Ricardo Leitner <mleitner@redhat.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 79e10d26e2ba..deb466fc3d1f 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2635,6 +2635,8 @@ int tcp_disconnect(struct sock *sk, int flags)
 	sk->sk_rx_dst = NULL;
 	tcp_saved_syn_free(tp);
 	tp->compressed_ack = 0;
+	tp->segs_in = 0;
+	tp->segs_out = 0;
 	tp->bytes_sent = 0;
 	tp->bytes_acked = 0;
 	tp->bytes_received = 0;
-- 
2.21.1


From 494ee482e00d8f3d99c5b1c0ed9e08f3c2496252 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <snelson@pensando.io>
Date: Thu, 30 Jan 2020 10:07:06 -0800
Subject: [PATCH 17/20] ionic: fix rxq comp packet type mask

[ Upstream commit b5ce31b5e11b768b7d685b2bab7db09ad5549493 ]

Be sure to include all the packet type bits in the mask.

Fixes: fbfb8031533c ("ionic: Add hardware init and device commands")
Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/pensando/ionic/ionic_if.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_if.h b/drivers/net/ethernet/pensando/ionic/ionic_if.h
index 5bfdda19f64d..d8745f87f065 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_if.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_if.h
@@ -862,7 +862,7 @@ struct ionic_rxq_comp {
 #define IONIC_RXQ_COMP_CSUM_F_VLAN	0x40
 #define IONIC_RXQ_COMP_CSUM_F_CALC	0x80
 	u8     pkt_type_color;
-#define IONIC_RXQ_COMP_PKT_TYPE_MASK	0x0f
+#define IONIC_RXQ_COMP_PKT_TYPE_MASK	0x7f
 };
 
 enum ionic_pkt_type {
-- 
2.21.1


From c4a6118a59362752e5b8192ce8b9486bbd6c7846 Mon Sep 17 00:00:00 2001
From: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Date: Sat, 1 Feb 2020 13:43:01 +0100
Subject: [PATCH 18/20] MAINTAINERS: correct entries for ISDN/mISDN section

[ Upstream commit dff6bc1bfd462b76dc13ec19dedc2c134a62ac59 ]

Commit 6d97985072dc ("isdn: move capi drivers to staging") cleaned up the
isdn drivers and split the MAINTAINERS section for ISDN, but missed to add
the terminal slash for the two directories mISDN and hardware. Hence, all
files in those directories were not part of the new ISDN/mISDN SUBSYSTEM,
but were considered to be part of "THE REST".

Rectify the situation, and while at it, also complete the section with two
further build files that belong to that subsystem.

This was identified with a small script that finds all files belonging to
"THE REST" according to the current MAINTAINERS file, and I investigated
upon its output.

Fixes: 6d97985072dc ("isdn: move capi drivers to staging")
Signed-off-by: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 4f7ac27d8651..d1aeebb59e6a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8704,8 +8704,10 @@ L:	isdn4linux@listserv.isdn4linux.de (subscribers-only)
 L:	netdev@vger.kernel.org
 W:	http://www.isdn4linux.de
 S:	Maintained
-F:	drivers/isdn/mISDN
-F:	drivers/isdn/hardware
+F:	drivers/isdn/mISDN/
+F:	drivers/isdn/hardware/
+F:	drivers/isdn/Kconfig
+F:	drivers/isdn/Makefile
 
 ISDN/CAPI SUBSYSTEM
 M:	Karsten Keil <isdn@linux-pingi.de>
-- 
2.21.1


From e3a9d6ef9e584831b9f9ce0cc40ac46ba85ca08d Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Sat, 1 Feb 2020 16:43:22 +0000
Subject: [PATCH 19/20] netdevsim: fix stack-out-of-bounds in
 nsim_dev_debugfs_init()

[ Upstream commit 6fb8852b1298200da39bd85788bc5755d1d56f32 ]

When netdevsim dev is being created, a debugfs directory is created.
The variable "dev_ddir_name" is 16bytes device name pointer and device
name is "netdevsim<dev id>".
The maximum dev id length is 10.
So, 16bytes for device name isn't enough.

Test commands:
    modprobe netdevsim
    echo "1000000000 0" > /sys/bus/netdevsim/new_device

Splat looks like:
[  249.622710][  T900] BUG: KASAN: stack-out-of-bounds in number+0x824/0x880
[  249.623658][  T900] Write of size 1 at addr ffff88804c527988 by task bash/900
[  249.624521][  T900]
[  249.624830][  T900] CPU: 1 PID: 900 Comm: bash Not tainted 5.5.0+ #322
[  249.625691][  T900] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[  249.626712][  T900] Call Trace:
[  249.627103][  T900]  dump_stack+0x96/0xdb
[  249.627639][  T900]  ? number+0x824/0x880
[  249.628173][  T900]  print_address_description.constprop.5+0x1be/0x360
[  249.629022][  T900]  ? number+0x824/0x880
[  249.629569][  T900]  ? number+0x824/0x880
[  249.630105][  T900]  __kasan_report+0x12a/0x170
[  249.630717][  T900]  ? number+0x824/0x880
[  249.631201][  T900]  kasan_report+0xe/0x20
[  249.631723][  T900]  number+0x824/0x880
[  249.632235][  T900]  ? put_dec+0xa0/0xa0
[  249.632716][  T900]  ? rcu_read_lock_sched_held+0x90/0xc0
[  249.633392][  T900]  vsnprintf+0x63c/0x10b0
[  249.633983][  T900]  ? pointer+0x5b0/0x5b0
[  249.634543][  T900]  ? mark_lock+0x11d/0xc40
[  249.635200][  T900]  sprintf+0x9b/0xd0
[  249.635750][  T900]  ? scnprintf+0xe0/0xe0
[  249.636370][  T900]  nsim_dev_probe+0x63c/0xbf0 [netdevsim]
[ ... ]

Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Fixes: ab1d0cc004d7 ("netdevsim: change debugfs tree topology")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/netdevsim/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index 44c2d857a7fa..91b302f0192f 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -73,7 +73,7 @@ static const struct file_operations nsim_dev_take_snapshot_fops = {
 
 static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev)
 {
-	char dev_ddir_name[16];
+	char dev_ddir_name[sizeof(DRV_NAME) + 10];
 
 	sprintf(dev_ddir_name, DRV_NAME "%u", nsim_dev->nsim_bus_dev->dev.id);
 	nsim_dev->ddir = debugfs_create_dir(dev_ddir_name, nsim_dev_ddir);
-- 
2.21.1


From c967e0a0d51f0d4bab2db4d39273e9ad02846e6f Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Sun, 2 Feb 2020 02:41:37 -0500
Subject: [PATCH 20/20] bnxt_en: Fix logic that disables Bus Master during
 firmware reset.

[ Upstream commit d407302895d3f3ca3a333c711744a95e0b1b0150 ]

The current logic that calls pci_disable_device() in __bnxt_close_nic()
during firmware reset is flawed.  If firmware is still alive, we're
disabling the device too early, causing some firmware commands to
not reach the firmware.

Fix it by moving the logic to bnxt_reset_close().  If firmware is
in fatal condition, we call pci_disable_device() before we free
any of the rings to prevent DMA corruption of the freed rings.  If
firmware is still alive, we call pci_disable_device() after the
last firmware message has been sent.

Fixes: 3bc7d4a352ef ("bnxt_en: Add BNXT_STATE_IN_FW_RESET state.")
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index e7496b56e4c6..41297533b4a8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -9273,10 +9273,6 @@ static void __bnxt_close_nic(struct bnxt *bp, bool irq_re_init,
 	bnxt_debug_dev_exit(bp);
 	bnxt_disable_napi(bp);
 	del_timer_sync(&bp->timer);
-	if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state) &&
-	    pci_is_enabled(bp->pdev))
-		pci_disable_device(bp->pdev);
-
 	bnxt_free_skbs(bp);
 
 	/* Save ring stats before shutdown */
@@ -10052,8 +10048,15 @@ static void bnxt_fw_reset_close(struct bnxt *bp)
 {
 	__bnxt_close_nic(bp, true, false);
 	bnxt_ulp_irq_stop(bp);
+	/* When firmware is fatal state, disable PCI device to prevent
+	 * any potential bad DMAs before freeing kernel memory.
+	 */
+	if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state))
+		pci_disable_device(bp->pdev);
 	bnxt_clear_int_mode(bp);
 	bnxt_hwrm_func_drv_unrgtr(bp);
+	if (pci_is_enabled(bp->pdev))
+		pci_disable_device(bp->pdev);
 	bnxt_free_ctx_mem(bp);
 	kfree(bp->ctx);
 	bp->ctx = NULL;
-- 
2.21.1


[-- Attachment #3: net_55.mbox --]
[-- Type: Application/Octet-Stream, Size: 64154 bytes --]

From f9512376bc5003545c8e1e2760301b30458c0745 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Mon, 27 Jan 2020 04:56:22 -0500
Subject: [PATCH 01/25] bnxt_en: Move devlink_register before registering
 netdev

[ Upstream commit cda2cab0771183932d6ba73c5ac63bb63decdadf ]

Latest kernels get the phys_port_name via devlink, if
ndo_get_phys_port_name is not defined. To provide the phys_port_name
correctly, register devlink before registering netdev.

Also call devlink_port_type_eth_set() after registering netdev as
devlink port updates the netdev structure and notifies user.

Cc: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c         | 12 ++++++++----
 drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c |  1 -
 2 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index e6f18f6070ef..d45b662123c0 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -11433,9 +11433,9 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 		bnxt_sriov_disable(bp);
 
 	bnxt_dl_fw_reporters_destroy(bp, true);
-	bnxt_dl_unregister(bp);
 	pci_disable_pcie_error_reporting(pdev);
 	unregister_netdev(dev);
+	bnxt_dl_unregister(bp);
 	bnxt_shutdown_tc(bp);
 	bnxt_cancel_sp_work(bp);
 	bp->sp_event = 0;
@@ -11905,11 +11905,14 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		bnxt_init_tc(bp);
 	}
 
+	bnxt_dl_register(bp);
+
 	rc = register_netdev(dev);
 	if (rc)
-		goto init_err_cleanup_tc;
+		goto init_err_cleanup;
 
-	bnxt_dl_register(bp);
+	if (BNXT_PF(bp))
+		devlink_port_type_eth_set(&bp->dl_port, bp->dev);
 	bnxt_dl_fw_reporters_create(bp);
 
 	netdev_info(dev, "%s found at mem %lx, node addr %pM\n",
@@ -11919,7 +11922,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	return 0;
 
-init_err_cleanup_tc:
+init_err_cleanup:
+	bnxt_dl_unregister(bp);
 	bnxt_shutdown_tc(bp);
 	bnxt_clear_int_mode(bp);
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index 3eedd4477218..8fcaa2398344 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -526,7 +526,6 @@ int bnxt_dl_register(struct bnxt *bp)
 		netdev_err(bp->dev, "devlink_port_register failed");
 		goto err_dl_param_unreg;
 	}
-	devlink_port_type_eth_set(&bp->dl_port, bp->dev);
 
 	rc = devlink_port_params_register(&bp->dl_port, bnxt_dl_port_params,
 					  ARRAY_SIZE(bnxt_dl_port_params));
-- 
2.21.1


From 9b3ae34eb8ad8e41373c85c8b3ebb65d4a46ee0a Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Tue, 4 Feb 2020 03:24:59 +0000
Subject: [PATCH 02/25] gtp: use __GFP_NOWARN to avoid memalloc warning

[ Upstream commit bd5cd35b782abf5437fbd01dfaee12437d20e832 ]

gtp hashtable size is received by user-space.
So, this hashtable size could be too large. If so, kmalloc will internally
print a warning message.
This warning message is actually not necessary for the gtp module.
So, this patch adds __GFP_NOWARN to avoid this message.

Splat looks like:
[ 2171.200049][ T1860] WARNING: CPU: 1 PID: 1860 at mm/page_alloc.c:4713 __alloc_pages_nodemask+0x2f3/0x740
[ 2171.238885][ T1860] Modules linked in: gtp veth openvswitch nsh nf_conncount nf_nat nf_conntrack nf_defrag_ipv]
[ 2171.262680][ T1860] CPU: 1 PID: 1860 Comm: gtp-link Not tainted 5.5.0+ #321
[ 2171.263567][ T1860] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[ 2171.264681][ T1860] RIP: 0010:__alloc_pages_nodemask+0x2f3/0x740
[ 2171.265332][ T1860] Code: 64 fe ff ff 65 48 8b 04 25 c0 0f 02 00 48 05 f0 12 00 00 41 be 01 00 00 00 49 89 47 0
[ 2171.267301][ T1860] RSP: 0018:ffff8880b51af1f0 EFLAGS: 00010246
[ 2171.268320][ T1860] RAX: ffffed1016a35e43 RBX: 0000000000000000 RCX: 0000000000000000
[ 2171.269517][ T1860] RDX: 0000000000000000 RSI: 000000000000000b RDI: 0000000000000000
[ 2171.270305][ T1860] RBP: 0000000000040cc0 R08: ffffed1018893109 R09: dffffc0000000000
[ 2171.275973][ T1860] R10: 0000000000000001 R11: ffffed1018893108 R12: 1ffff11016a35e43
[ 2171.291039][ T1860] R13: 000000000000000b R14: 000000000000000b R15: 00000000000f4240
[ 2171.292328][ T1860] FS:  00007f53cbc83740(0000) GS:ffff8880da000000(0000) knlGS:0000000000000000
[ 2171.293409][ T1860] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 2171.294586][ T1860] CR2: 000055f540014508 CR3: 00000000b49f2004 CR4: 00000000000606e0
[ 2171.295424][ T1860] Call Trace:
[ 2171.295756][ T1860]  ? mark_held_locks+0xa5/0xe0
[ 2171.296659][ T1860]  ? __alloc_pages_slowpath+0x21b0/0x21b0
[ 2171.298283][ T1860]  ? gtp_encap_enable_socket+0x13e/0x400 [gtp]
[ 2171.298962][ T1860]  ? alloc_pages_current+0xc1/0x1a0
[ 2171.299475][ T1860]  kmalloc_order+0x22/0x80
[ 2171.299936][ T1860]  kmalloc_order_trace+0x1d/0x140
[ 2171.300437][ T1860]  __kmalloc+0x302/0x3a0
[ 2171.300896][ T1860]  gtp_newlink+0x293/0xba0 [gtp]
[ ... ]

Fixes: 459aa660eb1d ("gtp: add initial driver for datapath of GPRS Tunneling Protocol (GTP-U)")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/gtp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 9b3ba98726d7..3a53d222bfcc 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -767,12 +767,12 @@ static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize)
 	int i;
 
 	gtp->addr_hash = kmalloc_array(hsize, sizeof(struct hlist_head),
-				       GFP_KERNEL);
+				       GFP_KERNEL | __GFP_NOWARN);
 	if (gtp->addr_hash == NULL)
 		return -ENOMEM;
 
 	gtp->tid_hash = kmalloc_array(hsize, sizeof(struct hlist_head),
-				      GFP_KERNEL);
+				      GFP_KERNEL | __GFP_NOWARN);
 	if (gtp->tid_hash == NULL)
 		goto err1;
 
-- 
2.21.1


From 11e75f7fa1e073883539acbd7537638cd7159b0f Mon Sep 17 00:00:00 2001
From: Ridge Kennedy <ridge.kennedy@alliedtelesis.co.nz>
Date: Tue, 4 Feb 2020 12:24:00 +1300
Subject: [PATCH 03/25] l2tp: Allow duplicate session creation with UDP

[ Upstream commit 0d0d9a388a858e271bb70e71e99e7fe2a6fd6f64 ]

In the past it was possible to create multiple L2TPv3 sessions with the
same session id as long as the sessions belonged to different tunnels.
The resulting sessions had issues when used with IP encapsulated tunnels,
but worked fine with UDP encapsulated ones. Some applications began to
rely on this behaviour to avoid having to negotiate unique session ids.

Some time ago a change was made to require session ids to be unique across
all tunnels, breaking the applications making use of this "feature".

This change relaxes the duplicate session id check to allow duplicates
if both of the colliding sessions belong to UDP encapsulated tunnels.

Fixes: dbdbc73b4478 ("l2tp: fix duplicate session creation")
Signed-off-by: Ridge Kennedy <ridge.kennedy@alliedtelesis.co.nz>
Acked-by: James Chapman <jchapman@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index f82ea12bac37..425b95eb7e87 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -322,8 +322,13 @@ int l2tp_session_register(struct l2tp_session *session,
 
 		spin_lock_bh(&pn->l2tp_session_hlist_lock);
 
+		/* IP encap expects session IDs to be globally unique, while
+		 * UDP encap doesn't.
+		 */
 		hlist_for_each_entry(session_walk, g_head, global_hlist)
-			if (session_walk->session_id == session->session_id) {
+			if (session_walk->session_id == session->session_id &&
+			    (session_walk->tunnel->encap == L2TP_ENCAPTYPE_IP ||
+			     tunnel->encap == L2TP_ENCAPTYPE_IP)) {
 				err = -EEXIST;
 				goto err_tlock_pnlock;
 			}
-- 
2.21.1


From 7fb90526fda11e7888249f2f017852b6475d17aa Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 3 Feb 2020 10:15:07 -0800
Subject: [PATCH 04/25] net: hsr: fix possible NULL deref in hsr_handle_frame()

[ Upstream commit 2b5b8251bc9fe2f9118411f037862ee17cf81e97 ]

hsr_port_get_rcu() can return NULL, so we need to be careful.

general protection fault, probably for non-canonical address 0xdffffc0000000006: 0000 [#1] PREEMPT SMP KASAN
KASAN: null-ptr-deref in range [0x0000000000000030-0x0000000000000037]
CPU: 1 PID: 10249 Comm: syz-executor.5 Not tainted 5.5.0-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:__read_once_size include/linux/compiler.h:199 [inline]
RIP: 0010:hsr_addr_is_self+0x86/0x330 net/hsr/hsr_framereg.c:44
Code: 04 00 f3 f3 f3 65 48 8b 04 25 28 00 00 00 48 89 45 d0 31 c0 e8 6b ff 94 f9 4c 89 f2 48 b8 00 00 00 00 00 fc ff df 48 c1 ea 03 <80> 3c 02 00 0f 85 75 02 00 00 48 8b 43 30 49 39 c6 49 89 47 c0 0f
RSP: 0018:ffffc90000da8a90 EFLAGS: 00010206
RAX: dffffc0000000000 RBX: 0000000000000000 RCX: ffffffff87e0cc33
RDX: 0000000000000006 RSI: ffffffff87e035d5 RDI: 0000000000000000
RBP: ffffc90000da8b20 R08: ffff88808e7de040 R09: ffffed1015d2707c
R10: ffffed1015d2707b R11: ffff8880ae9383db R12: ffff8880a689bc5e
R13: 1ffff920001b5153 R14: 0000000000000030 R15: ffffc90000da8af8
FS:  00007fd7a42be700(0000) GS:ffff8880ae900000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000001b32338000 CR3: 00000000a928c000 CR4: 00000000001406e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 <IRQ>
 hsr_handle_frame+0x1c5/0x630 net/hsr/hsr_slave.c:31
 __netif_receive_skb_core+0xfbc/0x30b0 net/core/dev.c:5099
 __netif_receive_skb_one_core+0xa8/0x1a0 net/core/dev.c:5196
 __netif_receive_skb+0x2c/0x1d0 net/core/dev.c:5312
 process_backlog+0x206/0x750 net/core/dev.c:6144
 napi_poll net/core/dev.c:6582 [inline]
 net_rx_action+0x508/0x1120 net/core/dev.c:6650
 __do_softirq+0x262/0x98c kernel/softirq.c:292
 do_softirq_own_stack+0x2a/0x40 arch/x86/entry/entry_64.S:1082
 </IRQ>

Fixes: c5a759117210 ("net/hsr: Use list_head (and rcu) instead of array for slave devices.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/hsr/hsr_slave.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c
index ee561297d8a7..fbfd0db182b7 100644
--- a/net/hsr/hsr_slave.c
+++ b/net/hsr/hsr_slave.c
@@ -27,6 +27,8 @@ static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb)
 
 	rcu_read_lock(); /* hsr->node_db, hsr->ports */
 	port = hsr_port_get_rcu(skb->dev);
+	if (!port)
+		goto finish_pass;
 
 	if (hsr_addr_is_self(port->hsr, eth_hdr(skb)->h_source)) {
 		/* Directly kill frames sent by ourselves */
-- 
2.21.1


From 2278143620ba9e4ff60feb1f3a074f5cc965d088 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sun, 2 Feb 2020 21:14:35 -0800
Subject: [PATCH 05/25] net_sched: fix an OOB access in cls_tcindex

[ Upstream commit 599be01ee567b61f4471ee8078870847d0a11e8e ]

As Eric noticed, tcindex_alloc_perfect_hash() uses cp->hash
to compute the size of memory allocation, but cp->hash is
set again after the allocation, this caused an out-of-bound
access.

So we have to move all cp->hash initialization and computation
before the memory allocation. Move cp->mask and cp->shift together
as cp->hash may need them for computation too.

Reported-and-tested-by: syzbot+35d4dea36c387813ed31@syzkaller.appspotmail.com
Fixes: 331b72922c5f ("net: sched: RCU cls_tcindex")
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Cc: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_tcindex.c | 40 ++++++++++++++++++++--------------------
 1 file changed, 20 insertions(+), 20 deletions(-)

diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 3d4a1280352f..0323aee03de7 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -333,12 +333,31 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	cp->fall_through = p->fall_through;
 	cp->tp = tp;
 
+	if (tb[TCA_TCINDEX_HASH])
+		cp->hash = nla_get_u32(tb[TCA_TCINDEX_HASH]);
+
+	if (tb[TCA_TCINDEX_MASK])
+		cp->mask = nla_get_u16(tb[TCA_TCINDEX_MASK]);
+
+	if (tb[TCA_TCINDEX_SHIFT])
+		cp->shift = nla_get_u32(tb[TCA_TCINDEX_SHIFT]);
+
+	if (!cp->hash) {
+		/* Hash not specified, use perfect hash if the upper limit
+		 * of the hashing index is below the threshold.
+		 */
+		if ((cp->mask >> cp->shift) < PERFECT_HASH_THRESHOLD)
+			cp->hash = (cp->mask >> cp->shift) + 1;
+		else
+			cp->hash = DEFAULT_HASH_SIZE;
+	}
+
 	if (p->perfect) {
 		int i;
 
 		if (tcindex_alloc_perfect_hash(net, cp) < 0)
 			goto errout;
-		for (i = 0; i < cp->hash; i++)
+		for (i = 0; i < min(cp->hash, p->hash); i++)
 			cp->perfect[i].res = p->perfect[i].res;
 		balloc = 1;
 	}
@@ -350,15 +369,6 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	if (old_r)
 		cr = r->res;
 
-	if (tb[TCA_TCINDEX_HASH])
-		cp->hash = nla_get_u32(tb[TCA_TCINDEX_HASH]);
-
-	if (tb[TCA_TCINDEX_MASK])
-		cp->mask = nla_get_u16(tb[TCA_TCINDEX_MASK]);
-
-	if (tb[TCA_TCINDEX_SHIFT])
-		cp->shift = nla_get_u32(tb[TCA_TCINDEX_SHIFT]);
-
 	err = -EBUSY;
 
 	/* Hash already allocated, make sure that we still meet the
@@ -376,16 +386,6 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	if (tb[TCA_TCINDEX_FALL_THROUGH])
 		cp->fall_through = nla_get_u32(tb[TCA_TCINDEX_FALL_THROUGH]);
 
-	if (!cp->hash) {
-		/* Hash not specified, use perfect hash if the upper limit
-		 * of the hashing index is below the threshold.
-		 */
-		if ((cp->mask >> cp->shift) < PERFECT_HASH_THRESHOLD)
-			cp->hash = (cp->mask >> cp->shift) + 1;
-		else
-			cp->hash = DEFAULT_HASH_SIZE;
-	}
-
 	if (!cp->perfect && !cp->h)
 		cp->alloc_hash = cp->hash;
 
-- 
2.21.1


From 404b5455964d98a2e53e70a01063dfdb794eb62c Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 30 Jan 2020 14:59:49 +0200
Subject: [PATCH 06/25] net/core: Do not clear VF index for node/port GUIDs
 query

[ Upstream commit 9fbf082f569980ddd7cab348e0a118678db0e47e ]

VF numbers were assigned to node_guid and port_guid, but cleared
right before such query calls were issued. It caused to return
node/port GUIDs of VF index 0 for all VFs.

Fixes: 30aad41721e0 ("net/core: Add support for getting VF GUIDs")
Reported-by: Adrian Chiris <adrianc@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index d9001b5c48eb..f02705ff0e5e 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1241,6 +1241,8 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb,
 		return 0;
 
 	memset(&vf_vlan_info, 0, sizeof(vf_vlan_info));
+	memset(&node_guid, 0, sizeof(node_guid));
+	memset(&port_guid, 0, sizeof(port_guid));
 
 	vf_mac.vf =
 		vf_vlan.vf =
@@ -1289,8 +1291,6 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb,
 		    sizeof(vf_trust), &vf_trust))
 		goto nla_put_vf_failure;
 
-	memset(&node_guid, 0, sizeof(node_guid));
-	memset(&port_guid, 0, sizeof(port_guid));
 	if (dev->netdev_ops->ndo_get_vf_guid &&
 	    !dev->netdev_ops->ndo_get_vf_guid(dev, vfs_num, &node_guid,
 					      &port_guid)) {
-- 
2.21.1


From 6cfce1094c8ada18b614e26c2d73b4aa12eb3dc3 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 29 Jan 2020 12:50:53 +0100
Subject: [PATCH 07/25] net: mvneta: fix XDP support if sw bm is used as
 fallback

[ Upstream commit 44efc78d0e464ce70b45b165c005f8bedc17952e ]

In order to fix XDP support if sw buffer management is used as fallback
for hw bm devices, define MVNETA_SKB_HEADROOM as maximum between
XDP_PACKET_HEADROOM and NET_SKB_PAD and let the hw aligns the IP header
to 4-byte boundary.
Fix rx_offset_correction initialization if mvneta_bm_port_init fails in
mvneta_resume routine

Fixes: 0db51da7a8e9 ("net: mvneta: add basic XDP support")
Tested-by: Sven Auhagen <sven.auhagen@voleatech.de>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 8bad5b864682..c66eeed10938 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -324,8 +324,7 @@
 	      ETH_HLEN + ETH_FCS_LEN,			     \
 	      cache_line_size())
 
-#define MVNETA_SKB_HEADROOM	(max(XDP_PACKET_HEADROOM, NET_SKB_PAD) + \
-				 NET_IP_ALIGN)
+#define MVNETA_SKB_HEADROOM	max(XDP_PACKET_HEADROOM, NET_SKB_PAD)
 #define MVNETA_SKB_PAD	(SKB_DATA_ALIGN(sizeof(struct skb_shared_info) + \
 			 MVNETA_SKB_HEADROOM))
 #define MVNETA_SKB_SIZE(len)	(SKB_DATA_ALIGN(len) + MVNETA_SKB_PAD)
@@ -1167,6 +1166,7 @@ static void mvneta_bm_update_mtu(struct mvneta_port *pp, int mtu)
 	mvneta_bm_pool_destroy(pp->bm_priv, pp->pool_short, 1 << pp->id);
 
 	pp->bm_priv = NULL;
+	pp->rx_offset_correction = MVNETA_SKB_HEADROOM;
 	mvreg_write(pp, MVNETA_ACC_MODE, MVNETA_ACC_MODE_EXT1);
 	netdev_info(pp->dev, "fail to update MTU, fall back to software BM\n");
 }
@@ -4948,7 +4948,6 @@ static int mvneta_probe(struct platform_device *pdev)
 	SET_NETDEV_DEV(dev, &pdev->dev);
 
 	pp->id = global_port_id++;
-	pp->rx_offset_correction = MVNETA_SKB_HEADROOM;
 
 	/* Obtain access to BM resources if enabled and already initialized */
 	bm_node = of_parse_phandle(dn, "buffer-manager", 0);
@@ -4973,6 +4972,10 @@ static int mvneta_probe(struct platform_device *pdev)
 	}
 	of_node_put(bm_node);
 
+	/* sw buffer management */
+	if (!pp->bm_priv)
+		pp->rx_offset_correction = MVNETA_SKB_HEADROOM;
+
 	err = mvneta_init(&pdev->dev, pp);
 	if (err < 0)
 		goto err_netdev;
@@ -5130,6 +5133,7 @@ static int mvneta_resume(struct device *device)
 		err = mvneta_bm_port_init(pdev, pp);
 		if (err < 0) {
 			dev_info(&pdev->dev, "use SW buffer management\n");
+			pp->rx_offset_correction = MVNETA_SKB_HEADROOM;
 			pp->bm_priv = NULL;
 		}
 	}
-- 
2.21.1


From b707698937f65de5d990084b3c5befe0dd5491c6 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 2 Feb 2020 02:41:38 -0500
Subject: [PATCH 08/25] bnxt_en: Fix TC queue mapping.

[ Upstream commit 18e4960c18f484ac288f41b43d0e6c4c88e6ea78 ]

The driver currently only calls netdev_set_tc_queue when the number of
TCs is greater than 1.  Instead, the comparison should be greater than
or equal to 1.  Even with 1 TC, we need to set the queue mapping.

This bug can cause warnings when the number of TCs is changed back to 1.

Fixes: 7809592d3e2e ("bnxt_en: Enable MSIX early in bnxt_init_one().")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index d45b662123c0..0625357d3152 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -7892,7 +7892,7 @@ static void bnxt_setup_msix(struct bnxt *bp)
 	int tcs, i;
 
 	tcs = netdev_get_num_tc(dev);
-	if (tcs > 1) {
+	if (tcs) {
 		int i, off, count;
 
 		for (i = 0; i < tcs; i++) {
-- 
2.21.1


From 55d37a79b9cf344a1b3ab583e63bbdade1a8b68b Mon Sep 17 00:00:00 2001
From: Nicolin Chen <nicoleotsuka@gmail.com>
Date: Fri, 31 Jan 2020 18:01:24 -0800
Subject: [PATCH 09/25] net: stmmac: Delete txtimer in suspend()

[ Upstream commit 14b41a2959fbaa50932699d32ceefd6643abacc6 ]

When running v5.5 with a rootfs on NFS, memory abort may happen in
the system resume stage:
 Unable to handle kernel paging request at virtual address dead00000000012a
 [dead00000000012a] address between user and kernel address ranges
 pc : run_timer_softirq+0x334/0x3d8
 lr : run_timer_softirq+0x244/0x3d8
 x1 : ffff800011cafe80 x0 : dead000000000122
 Call trace:
  run_timer_softirq+0x334/0x3d8
  efi_header_end+0x114/0x234
  irq_exit+0xd0/0xd8
  __handle_domain_irq+0x60/0xb0
  gic_handle_irq+0x58/0xa8
  el1_irq+0xb8/0x180
  arch_cpu_idle+0x10/0x18
  do_idle+0x1d8/0x2b0
  cpu_startup_entry+0x24/0x40
  secondary_start_kernel+0x1b4/0x208
 Code: f9000693 a9400660 f9000020 b4000040 (f9000401)
 ---[ end trace bb83ceeb4c482071 ]---
 Kernel panic - not syncing: Fatal exception in interrupt
 SMP: stopping secondary CPUs
 SMP: failed to stop secondary CPUs 2-3
 Kernel Offset: disabled
 CPU features: 0x00002,2300aa30
 Memory Limit: none
 ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]---

It's found that stmmac_xmit() and stmmac_resume() sometimes might
run concurrently, possibly resulting in a race condition between
mod_timer() and setup_timer(), being called by stmmac_xmit() and
stmmac_resume() respectively.

Since the resume() runs setup_timer() every time, it'd be safer to
have del_timer_sync() in the suspend() as the counterpart.

Signed-off-by: Nicolin Chen <nicoleotsuka@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 80d59b775907..6bc1bdb137ae 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -4860,6 +4860,7 @@ int stmmac_suspend(struct device *dev)
 {
 	struct net_device *ndev = dev_get_drvdata(dev);
 	struct stmmac_priv *priv = netdev_priv(ndev);
+	u32 chan;
 
 	if (!ndev || !netif_running(ndev))
 		return 0;
@@ -4873,6 +4874,9 @@ int stmmac_suspend(struct device *dev)
 
 	stmmac_disable_all_queues(priv);
 
+	for (chan = 0; chan < priv->plat->tx_queues_to_use; chan++)
+		del_timer_sync(&priv->tx_queue[chan].txtimer);
+
 	/* Stop TX/RX DMA */
 	stmmac_stop_all_dma(priv);
 
-- 
2.21.1


From 632b1d195e3089949546ee83c735ff293b156174 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 31 Jan 2020 09:14:47 -0800
Subject: [PATCH 10/25] tcp: clear tp->total_retrans in tcp_disconnect()

[ Upstream commit c13c48c00a6bc1febc73902505bdec0967bd7095 ]

total_retrans needs to be cleared in tcp_disconnect().

tcp_disconnect() is rarely used, but it is worth fixing it.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: SeongJae Park <sjpark@amazon.de>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index a7d766e6390e..4f1f7ec46ffc 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2625,6 +2625,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tcp_set_ca_state(sk, TCP_CA_Open);
 	tp->is_sack_reneg = 0;
 	tcp_clear_retrans(tp);
+	tp->total_retrans = 0;
 	inet_csk_delack_init(sk);
 	/* Initialize rcv_mss to TCP_MIN_MSS to avoid division by 0
 	 * issue in __tcp_select_window()
-- 
2.21.1


From d79205cbb146f4c85b6e31b68c0e2de216a4209c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 31 Jan 2020 10:22:47 -0800
Subject: [PATCH 11/25] tcp: clear tp->delivered in tcp_disconnect()

[ Upstream commit 2fbdd56251b5c62f96589f39eded277260de7267 ]

tp->delivered needs to be cleared in tcp_disconnect().

tcp_disconnect() is rarely used, but it is worth fixing it.

Fixes: ddf1af6fa00e ("tcp: new delivery accounting")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 4f1f7ec46ffc..3cca00d78b3e 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2621,6 +2621,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tp->snd_cwnd = TCP_INIT_CWND;
 	tp->snd_cwnd_cnt = 0;
 	tp->window_clamp = 0;
+	tp->delivered = 0;
 	tp->delivered_ce = 0;
 	tcp_set_ca_state(sk, TCP_CA_Open);
 	tp->is_sack_reneg = 0;
-- 
2.21.1


From 688dafea0376834bd84462680d931d44ad96ef7e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 31 Jan 2020 10:32:41 -0800
Subject: [PATCH 12/25] tcp: clear tp->data_segs{in|out} in tcp_disconnect()

[ Upstream commit db7ffee6f3eb3683cdcaeddecc0a630a14546fe3 ]

tp->data_segs_in and tp->data_segs_out need to be cleared
in tcp_disconnect().

tcp_disconnect() is rarely used, but it is worth fixing it.

Fixes: a44d6eacdaf5 ("tcp: Add RFC4898 tcpEStatsPerfDataSegsOut/In")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Martin KaFai Lau <kafai@fb.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 3cca00d78b3e..788e1ec249c6 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2642,6 +2642,8 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tp->bytes_acked = 0;
 	tp->bytes_received = 0;
 	tp->bytes_retrans = 0;
+	tp->data_segs_in = 0;
+	tp->data_segs_out = 0;
 	tp->duplicate_sack[0].start_seq = 0;
 	tp->duplicate_sack[0].end_seq = 0;
 	tp->dsack_dups = 0;
-- 
2.21.1


From 4a36c372eb1a4bd38773ff5cfe332f71d1e35ded Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 31 Jan 2020 10:44:50 -0800
Subject: [PATCH 13/25] tcp: clear tp->segs_{in|out} in tcp_disconnect()

[ Upstream commit 784f8344de750a41344f4bbbebb8507a730fc99c ]

tp->segs_in and tp->segs_out need to be cleared in tcp_disconnect().

tcp_disconnect() is rarely used, but it is worth fixing it.

Fixes: 2efd055c53c0 ("tcp: add tcpi_segs_in and tcpi_segs_out to tcp_info")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Marcelo Ricardo Leitner <mleitner@redhat.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 788e1ec249c6..94e137f7aa9f 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2638,6 +2638,8 @@ int tcp_disconnect(struct sock *sk, int flags)
 	sk->sk_rx_dst = NULL;
 	tcp_saved_syn_free(tp);
 	tp->compressed_ack = 0;
+	tp->segs_in = 0;
+	tp->segs_out = 0;
 	tp->bytes_sent = 0;
 	tp->bytes_acked = 0;
 	tp->bytes_received = 0;
-- 
2.21.1


From 12012dd9c5304a31720d4817531c4dbfbf20826b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 31 Jan 2020 15:27:04 -0800
Subject: [PATCH 14/25] cls_rsvp: fix rsvp_policy

[ Upstream commit cb3c0e6bdf64d0d124e94ce43cbe4ccbb9b37f51 ]

NLA_BINARY can be confusing, since .len value represents
the max size of the blob.

cls_rsvp really wants user space to provide long enough data
for TCA_RSVP_DST and TCA_RSVP_SRC attributes.

BUG: KMSAN: uninit-value in rsvp_get net/sched/cls_rsvp.h:258 [inline]
BUG: KMSAN: uninit-value in gen_handle net/sched/cls_rsvp.h:402 [inline]
BUG: KMSAN: uninit-value in rsvp_change+0x1ae9/0x4220 net/sched/cls_rsvp.h:572
CPU: 1 PID: 13228 Comm: syz-executor.1 Not tainted 5.5.0-rc5-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c9/0x220 lib/dump_stack.c:118
 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:118
 __msan_warning+0x58/0xa0 mm/kmsan/kmsan_instr.c:215
 rsvp_get net/sched/cls_rsvp.h:258 [inline]
 gen_handle net/sched/cls_rsvp.h:402 [inline]
 rsvp_change+0x1ae9/0x4220 net/sched/cls_rsvp.h:572
 tc_new_tfilter+0x31fe/0x5010 net/sched/cls_api.c:2104
 rtnetlink_rcv_msg+0xcb7/0x1570 net/core/rtnetlink.c:5415
 netlink_rcv_skb+0x451/0x650 net/netlink/af_netlink.c:2477
 rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:5442
 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
 netlink_unicast+0xf9e/0x1100 net/netlink/af_netlink.c:1328
 netlink_sendmsg+0x1248/0x14d0 net/netlink/af_netlink.c:1917
 sock_sendmsg_nosec net/socket.c:639 [inline]
 sock_sendmsg net/socket.c:659 [inline]
 ____sys_sendmsg+0x12b6/0x1350 net/socket.c:2330
 ___sys_sendmsg net/socket.c:2384 [inline]
 __sys_sendmsg+0x451/0x5f0 net/socket.c:2417
 __do_sys_sendmsg net/socket.c:2426 [inline]
 __se_sys_sendmsg+0x97/0xb0 net/socket.c:2424
 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2424
 do_syscall_64+0xb8/0x160 arch/x86/entry/common.c:296
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x45b349
Code: ad b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f269d43dc78 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 00007f269d43e6d4 RCX: 000000000045b349
RDX: 0000000000000000 RSI: 00000000200001c0 RDI: 0000000000000003
RBP: 000000000075bfc8 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff
R13: 00000000000009c2 R14: 00000000004cb338 R15: 000000000075bfd4

Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:144 [inline]
 kmsan_internal_poison_shadow+0x66/0xd0 mm/kmsan/kmsan.c:127
 kmsan_slab_alloc+0x8a/0xe0 mm/kmsan/kmsan_hooks.c:82
 slab_alloc_node mm/slub.c:2774 [inline]
 __kmalloc_node_track_caller+0xb40/0x1200 mm/slub.c:4382
 __kmalloc_reserve net/core/skbuff.c:141 [inline]
 __alloc_skb+0x2fd/0xac0 net/core/skbuff.c:209
 alloc_skb include/linux/skbuff.h:1049 [inline]
 netlink_alloc_large_skb net/netlink/af_netlink.c:1174 [inline]
 netlink_sendmsg+0x7d3/0x14d0 net/netlink/af_netlink.c:1892
 sock_sendmsg_nosec net/socket.c:639 [inline]
 sock_sendmsg net/socket.c:659 [inline]
 ____sys_sendmsg+0x12b6/0x1350 net/socket.c:2330
 ___sys_sendmsg net/socket.c:2384 [inline]
 __sys_sendmsg+0x451/0x5f0 net/socket.c:2417
 __do_sys_sendmsg net/socket.c:2426 [inline]
 __se_sys_sendmsg+0x97/0xb0 net/socket.c:2424
 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2424
 do_syscall_64+0xb8/0x160 arch/x86/entry/common.c:296
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 6fa8c0144b77 ("[NET_SCHED]: Use nla_policy for attribute validation in classifiers")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/cls_rsvp.h | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h
index c22624131949..d36949d9382c 100644
--- a/net/sched/cls_rsvp.h
+++ b/net/sched/cls_rsvp.h
@@ -463,10 +463,8 @@ static u32 gen_tunnel(struct rsvp_head *data)
 
 static const struct nla_policy rsvp_policy[TCA_RSVP_MAX + 1] = {
 	[TCA_RSVP_CLASSID]	= { .type = NLA_U32 },
-	[TCA_RSVP_DST]		= { .type = NLA_BINARY,
-				    .len = RSVP_DST_LEN * sizeof(u32) },
-	[TCA_RSVP_SRC]		= { .type = NLA_BINARY,
-				    .len = RSVP_DST_LEN * sizeof(u32) },
+	[TCA_RSVP_DST]		= { .len = RSVP_DST_LEN * sizeof(u32) },
+	[TCA_RSVP_SRC]		= { .len = RSVP_DST_LEN * sizeof(u32) },
 	[TCA_RSVP_PINFO]	= { .len = sizeof(struct tc_rsvp_pinfo) },
 };
 
-- 
2.21.1


From c46eec72859768333ac4467d9b6ef6bcdcc47e23 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 30 Jan 2020 21:50:35 +0000
Subject: [PATCH 15/25] rxrpc: Fix use-after-free in rxrpc_put_local()

[ Upstream commit fac20b9e738523fc884ee3ea5be360a321cd8bad ]

Fix rxrpc_put_local() to not access local->debug_id after calling
atomic_dec_return() as, unless that returned n==0, we no longer have the
right to access the object.

Fixes: 06d9532fa6b3 ("rxrpc: Fix read-after-free in rxrpc_queue_local()")
Signed-off-by: David Howells <dhowells@redhat.com>
---
 net/rxrpc/local_object.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index 36587260cabd..3aa179efcda4 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -364,11 +364,14 @@ void rxrpc_queue_local(struct rxrpc_local *local)
 void rxrpc_put_local(struct rxrpc_local *local)
 {
 	const void *here = __builtin_return_address(0);
+	unsigned int debug_id;
 	int n;
 
 	if (local) {
+		debug_id = local->debug_id;
+
 		n = atomic_dec_return(&local->usage);
-		trace_rxrpc_local(local->debug_id, rxrpc_local_put, n, here);
+		trace_rxrpc_local(debug_id, rxrpc_local_put, n, here);
 
 		if (n == 0)
 			call_rcu(&local->rcu, rxrpc_local_rcu);
-- 
2.21.1


From ac10d3060865ceba097533f826745dd8436a85bf Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 30 Jan 2020 21:50:36 +0000
Subject: [PATCH 16/25] rxrpc: Fix insufficient receive notification generation

[ Upstream commit f71dbf2fb28489a79bde0dca1c8adfb9cdb20a6b ]

In rxrpc_input_data(), rxrpc_notify_socket() is called if the base sequence
number of the packet is immediately following the hard-ack point at the end
of the function.  However, this isn't sufficient, since the recvmsg side
may have been advancing the window and then overrun the position in which
we're adding - at which point rx_hard_ack >= seq0 and no notification is
generated.

Fix this by always generating a notification at the end of the input
function.

Without this, a long call may stall, possibly indefinitely.

Fixes: 248f219cb8bc ("rxrpc: Rewrite the data and ack handling code")
Signed-off-by: David Howells <dhowells@redhat.com>
---
 net/rxrpc/input.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 96d54e5bf7bc..ef10fbf71b15 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -599,10 +599,8 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb)
 				  false, true,
 				  rxrpc_propose_ack_input_data);
 
-	if (seq0 == READ_ONCE(call->rx_hard_ack) + 1) {
-		trace_rxrpc_notify_socket(call->debug_id, serial);
-		rxrpc_notify_socket(call);
-	}
+	trace_rxrpc_notify_socket(call->debug_id, serial);
+	rxrpc_notify_socket(call);
 
 unlock:
 	spin_unlock(&call->input_lock);
-- 
2.21.1


From 5b395e15b59b5cd21f1312c6e8bd531d1f55863c Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 30 Jan 2020 21:50:36 +0000
Subject: [PATCH 17/25] rxrpc: Fix missing active use pinning of rxrpc_local
 object

[ Upstream commit 04d36d748fac349b068ef621611f454010054c58 ]

The introduction of a split between the reference count on rxrpc_local
objects and the usage count didn't quite go far enough.  A number of kernel
work items need to make use of the socket to perform transmission.  These
also need to get an active count on the local object to prevent the socket
from being closed.

Fix this by getting the active count in those places.

Also split out the raw active count get/put functions as these places tend
to hold refs on the rxrpc_local object already, so getting and putting an
extra object ref is just a waste of time.

The problem can lead to symptoms like:

    BUG: kernel NULL pointer dereference, address: 0000000000000018
    ..
    CPU: 2 PID: 818 Comm: kworker/u9:0 Not tainted 5.5.0-fscache+ #51
    ...
    RIP: 0010:selinux_socket_sendmsg+0x5/0x13
    ...
    Call Trace:
     security_socket_sendmsg+0x2c/0x3e
     sock_sendmsg+0x1a/0x46
     rxrpc_send_keepalive+0x131/0x1ae
     rxrpc_peer_keepalive_worker+0x219/0x34b
     process_one_work+0x18e/0x271
     worker_thread+0x1a3/0x247
     kthread+0xe6/0xeb
     ret_from_fork+0x1f/0x30

Fixes: 730c5fd42c1e ("rxrpc: Fix local endpoint refcounting")
Signed-off-by: David Howells <dhowells@redhat.com>
---
 net/rxrpc/af_rxrpc.c     |  2 ++
 net/rxrpc/ar-internal.h  | 10 ++++++++++
 net/rxrpc/conn_event.c   | 30 ++++++++++++++++++----------
 net/rxrpc/local_object.c | 18 +++++++----------
 net/rxrpc/peer_event.c   | 42 ++++++++++++++++++++++------------------
 5 files changed, 62 insertions(+), 40 deletions(-)

diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 9d3c4d2d893a..fe42f986cd94 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -194,6 +194,7 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len)
 service_in_use:
 	write_unlock(&local->services_lock);
 	rxrpc_unuse_local(local);
+	rxrpc_put_local(local);
 	ret = -EADDRINUSE;
 error_unlock:
 	release_sock(&rx->sk);
@@ -899,6 +900,7 @@ static int rxrpc_release_sock(struct sock *sk)
 	rxrpc_purge_queue(&sk->sk_receive_queue);
 
 	rxrpc_unuse_local(rx->local);
+	rxrpc_put_local(rx->local);
 	rx->local = NULL;
 	key_put(rx->key);
 	rx->key = NULL;
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 5e99df80e80a..94441fee85bc 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -1021,6 +1021,16 @@ void rxrpc_unuse_local(struct rxrpc_local *);
 void rxrpc_queue_local(struct rxrpc_local *);
 void rxrpc_destroy_all_locals(struct rxrpc_net *);
 
+static inline bool __rxrpc_unuse_local(struct rxrpc_local *local)
+{
+	return atomic_dec_return(&local->active_users) == 0;
+}
+
+static inline bool __rxrpc_use_local(struct rxrpc_local *local)
+{
+	return atomic_fetch_add_unless(&local->active_users, 1, 0) != 0;
+}
+
 /*
  * misc.c
  */
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index 808a4723f868..06fcff2ebbba 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -438,16 +438,12 @@ static void rxrpc_process_delayed_final_acks(struct rxrpc_connection *conn)
 /*
  * connection-level event processor
  */
-void rxrpc_process_connection(struct work_struct *work)
+static void rxrpc_do_process_connection(struct rxrpc_connection *conn)
 {
-	struct rxrpc_connection *conn =
-		container_of(work, struct rxrpc_connection, processor);
 	struct sk_buff *skb;
 	u32 abort_code = RX_PROTOCOL_ERROR;
 	int ret;
 
-	rxrpc_see_connection(conn);
-
 	if (test_and_clear_bit(RXRPC_CONN_EV_CHALLENGE, &conn->events))
 		rxrpc_secure_connection(conn);
 
@@ -475,18 +471,32 @@ void rxrpc_process_connection(struct work_struct *work)
 		}
 	}
 
-out:
-	rxrpc_put_connection(conn);
-	_leave("");
 	return;
 
 requeue_and_leave:
 	skb_queue_head(&conn->rx_queue, skb);
-	goto out;
+	return;
 
 protocol_error:
 	if (rxrpc_abort_connection(conn, ret, abort_code) < 0)
 		goto requeue_and_leave;
 	rxrpc_free_skb(skb, rxrpc_skb_freed);
-	goto out;
+	return;
+}
+
+void rxrpc_process_connection(struct work_struct *work)
+{
+	struct rxrpc_connection *conn =
+		container_of(work, struct rxrpc_connection, processor);
+
+	rxrpc_see_connection(conn);
+
+	if (__rxrpc_use_local(conn->params.local)) {
+		rxrpc_do_process_connection(conn);
+		rxrpc_unuse_local(conn->params.local);
+	}
+
+	rxrpc_put_connection(conn);
+	_leave("");
+	return;
 }
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index 3aa179efcda4..a6c1349e965d 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -383,14 +383,11 @@ void rxrpc_put_local(struct rxrpc_local *local)
  */
 struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *local)
 {
-	unsigned int au;
-
 	local = rxrpc_get_local_maybe(local);
 	if (!local)
 		return NULL;
 
-	au = atomic_fetch_add_unless(&local->active_users, 1, 0);
-	if (au == 0) {
+	if (!__rxrpc_use_local(local)) {
 		rxrpc_put_local(local);
 		return NULL;
 	}
@@ -404,14 +401,11 @@ struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *local)
  */
 void rxrpc_unuse_local(struct rxrpc_local *local)
 {
-	unsigned int au;
-
 	if (local) {
-		au = atomic_dec_return(&local->active_users);
-		if (au == 0)
+		if (__rxrpc_unuse_local(local)) {
+			rxrpc_get_local(local);
 			rxrpc_queue_local(local);
-		else
-			rxrpc_put_local(local);
+		}
 	}
 }
 
@@ -468,7 +462,7 @@ static void rxrpc_local_processor(struct work_struct *work)
 
 	do {
 		again = false;
-		if (atomic_read(&local->active_users) == 0) {
+		if (!__rxrpc_use_local(local)) {
 			rxrpc_local_destroyer(local);
 			break;
 		}
@@ -482,6 +476,8 @@ static void rxrpc_local_processor(struct work_struct *work)
 			rxrpc_process_local_events(local);
 			again = true;
 		}
+
+		__rxrpc_unuse_local(local);
 	} while (again);
 
 	rxrpc_put_local(local);
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index 48f67a9b1037..923b263c401b 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -364,27 +364,31 @@ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet,
 		if (!rxrpc_get_peer_maybe(peer))
 			continue;
 
-		spin_unlock_bh(&rxnet->peer_hash_lock);
-
-		keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME;
-		slot = keepalive_at - base;
-		_debug("%02x peer %u t=%d {%pISp}",
-		       cursor, peer->debug_id, slot, &peer->srx.transport);
+		if (__rxrpc_use_local(peer->local)) {
+			spin_unlock_bh(&rxnet->peer_hash_lock);
+
+			keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME;
+			slot = keepalive_at - base;
+			_debug("%02x peer %u t=%d {%pISp}",
+			       cursor, peer->debug_id, slot, &peer->srx.transport);
+
+			if (keepalive_at <= base ||
+			    keepalive_at > base + RXRPC_KEEPALIVE_TIME) {
+				rxrpc_send_keepalive(peer);
+				slot = RXRPC_KEEPALIVE_TIME;
+			}
 
-		if (keepalive_at <= base ||
-		    keepalive_at > base + RXRPC_KEEPALIVE_TIME) {
-			rxrpc_send_keepalive(peer);
-			slot = RXRPC_KEEPALIVE_TIME;
+			/* A transmission to this peer occurred since last we
+			 * examined it so put it into the appropriate future
+			 * bucket.
+			 */
+			slot += cursor;
+			slot &= mask;
+			spin_lock_bh(&rxnet->peer_hash_lock);
+			list_add_tail(&peer->keepalive_link,
+				      &rxnet->peer_keepalive[slot & mask]);
+			rxrpc_unuse_local(peer->local);
 		}
-
-		/* A transmission to this peer occurred since last we examined
-		 * it so put it into the appropriate future bucket.
-		 */
-		slot += cursor;
-		slot &= mask;
-		spin_lock_bh(&rxnet->peer_hash_lock);
-		list_add_tail(&peer->keepalive_link,
-			      &rxnet->peer_keepalive[slot & mask]);
 		rxrpc_put_peer_locked(peer);
 	}
 
-- 
2.21.1


From 66fc7f8f5479ee7510abb37c1fc57031f1374443 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 30 Jan 2020 21:50:36 +0000
Subject: [PATCH 18/25] rxrpc: Fix NULL pointer deref due to call->conn being
 cleared on disconnect

[ Upstream commit 5273a191dca65a675dc0bcf3909e59c6933e2831 ]

When a call is disconnected, the connection pointer from the call is
cleared to make sure it isn't used again and to prevent further attempted
transmission for the call.  Unfortunately, there might be a daemon trying
to use it at the same time to transmit a packet.

Fix this by keeping call->conn set, but setting a flag on the call to
indicate disconnection instead.

Remove also the bits in the transmission functions where the conn pointer is
checked and a ref taken under spinlock as this is now redundant.

Fixes: 8d94aa381dab ("rxrpc: Calls shouldn't hold socket refs")
Signed-off-by: David Howells <dhowells@redhat.com>
---
 net/rxrpc/ar-internal.h |  1 +
 net/rxrpc/call_object.c |  4 ++--
 net/rxrpc/conn_client.c |  3 +--
 net/rxrpc/conn_object.c |  4 ++--
 net/rxrpc/output.c      | 27 +++++++++------------------
 5 files changed, 15 insertions(+), 24 deletions(-)

diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 94441fee85bc..7d730c438404 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -490,6 +490,7 @@ enum rxrpc_call_flag {
 	RXRPC_CALL_RX_HEARD,		/* The peer responded at least once to this call */
 	RXRPC_CALL_RX_UNDERRUN,		/* Got data underrun */
 	RXRPC_CALL_IS_INTR,		/* The call is interruptible */
+	RXRPC_CALL_DISCONNECTED,	/* The call has been disconnected */
 };
 
 /*
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index a31c18c09894..dbdbc4f18b5e 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -493,7 +493,7 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call)
 
 	_debug("RELEASE CALL %p (%d CONN %p)", call, call->debug_id, conn);
 
-	if (conn)
+	if (conn && !test_bit(RXRPC_CALL_DISCONNECTED, &call->flags))
 		rxrpc_disconnect_call(call);
 	if (call->security)
 		call->security->free_call_crypto(call);
@@ -569,6 +569,7 @@ static void rxrpc_rcu_destroy_call(struct rcu_head *rcu)
 	struct rxrpc_call *call = container_of(rcu, struct rxrpc_call, rcu);
 	struct rxrpc_net *rxnet = call->rxnet;
 
+	rxrpc_put_connection(call->conn);
 	rxrpc_put_peer(call->peer);
 	kfree(call->rxtx_buffer);
 	kfree(call->rxtx_annotations);
@@ -590,7 +591,6 @@ void rxrpc_cleanup_call(struct rxrpc_call *call)
 
 	ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE);
 	ASSERT(test_bit(RXRPC_CALL_RELEASED, &call->flags));
-	ASSERTCMP(call->conn, ==, NULL);
 
 	rxrpc_cleanup_ring(call);
 	rxrpc_free_skb(call->tx_pending, rxrpc_skb_cleaned);
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index 376370cd9285..ea7d4c21f889 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -785,6 +785,7 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *call)
 	u32 cid;
 
 	spin_lock(&conn->channel_lock);
+	set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
 
 	cid = call->cid;
 	if (cid) {
@@ -792,7 +793,6 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *call)
 		chan = &conn->channels[channel];
 	}
 	trace_rxrpc_client(conn, channel, rxrpc_client_chan_disconnect);
-	call->conn = NULL;
 
 	/* Calls that have never actually been assigned a channel can simply be
 	 * discarded.  If the conn didn't get used either, it will follow
@@ -908,7 +908,6 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *call)
 	spin_unlock(&rxnet->client_conn_cache_lock);
 out_2:
 	spin_unlock(&conn->channel_lock);
-	rxrpc_put_connection(conn);
 	_leave("");
 	return;
 
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index 38d718e90dc6..c0b3154f7a7e 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -171,6 +171,8 @@ void __rxrpc_disconnect_call(struct rxrpc_connection *conn,
 
 	_enter("%d,%x", conn->debug_id, call->cid);
 
+	set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
+
 	if (rcu_access_pointer(chan->call) == call) {
 		/* Save the result of the call so that we can repeat it if necessary
 		 * through the channel, whilst disposing of the actual call record.
@@ -223,9 +225,7 @@ void rxrpc_disconnect_call(struct rxrpc_call *call)
 	__rxrpc_disconnect_call(conn, call);
 	spin_unlock(&conn->channel_lock);
 
-	call->conn = NULL;
 	conn->idle_timestamp = jiffies;
-	rxrpc_put_connection(conn);
 }
 
 /*
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index 935bb60fff56..bad3d2420344 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -129,7 +129,7 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn,
 int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
 			  rxrpc_serial_t *_serial)
 {
-	struct rxrpc_connection *conn = NULL;
+	struct rxrpc_connection *conn;
 	struct rxrpc_ack_buffer *pkt;
 	struct msghdr msg;
 	struct kvec iov[2];
@@ -139,18 +139,14 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
 	int ret;
 	u8 reason;
 
-	spin_lock_bh(&call->lock);
-	if (call->conn)
-		conn = rxrpc_get_connection_maybe(call->conn);
-	spin_unlock_bh(&call->lock);
-	if (!conn)
+	if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags))
 		return -ECONNRESET;
 
 	pkt = kzalloc(sizeof(*pkt), GFP_KERNEL);
-	if (!pkt) {
-		rxrpc_put_connection(conn);
+	if (!pkt)
 		return -ENOMEM;
-	}
+
+	conn = call->conn;
 
 	msg.msg_name	= &call->peer->srx.transport;
 	msg.msg_namelen	= call->peer->srx.transport_len;
@@ -244,7 +240,6 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
 	}
 
 out:
-	rxrpc_put_connection(conn);
 	kfree(pkt);
 	return ret;
 }
@@ -254,7 +249,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
  */
 int rxrpc_send_abort_packet(struct rxrpc_call *call)
 {
-	struct rxrpc_connection *conn = NULL;
+	struct rxrpc_connection *conn;
 	struct rxrpc_abort_buffer pkt;
 	struct msghdr msg;
 	struct kvec iov[1];
@@ -271,13 +266,11 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call)
 	    test_bit(RXRPC_CALL_TX_LAST, &call->flags))
 		return 0;
 
-	spin_lock_bh(&call->lock);
-	if (call->conn)
-		conn = rxrpc_get_connection_maybe(call->conn);
-	spin_unlock_bh(&call->lock);
-	if (!conn)
+	if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags))
 		return -ECONNRESET;
 
+	conn = call->conn;
+
 	msg.msg_name	= &call->peer->srx.transport;
 	msg.msg_namelen	= call->peer->srx.transport_len;
 	msg.msg_control	= NULL;
@@ -312,8 +305,6 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call)
 		trace_rxrpc_tx_packet(call->debug_id, &pkt.whdr,
 				      rxrpc_tx_point_call_abort);
 	rxrpc_tx_backoff(call, ret);
-
-	rxrpc_put_connection(conn);
 	return ret;
 }
 
-- 
2.21.1


From 4c2be7a487a0f5535590eaa44578dc27fe487225 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 2 Feb 2020 02:41:35 -0500
Subject: [PATCH 19/25] bnxt_en: Refactor logic to re-enable SRIOV after
 firmware reset detected.

[ Upstream commit c16d4ee0e397163fe7ceac281eaa952e63fadec7 ]

Put the current logic in bnxt_open() to re-enable SRIOV after detecting
firmware reset into a new function bnxt_reenable_sriov().  This call
needs to be invoked in the firmware reset path also in the next patch.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 0625357d3152..6c5825475a73 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -9240,6 +9240,17 @@ void bnxt_half_close_nic(struct bnxt *bp)
 	bnxt_free_mem(bp, false);
 }
 
+static void bnxt_reenable_sriov(struct bnxt *bp)
+{
+	if (BNXT_PF(bp)) {
+		struct bnxt_pf_info *pf = &bp->pf;
+		int n = pf->active_vfs;
+
+		if (n)
+			bnxt_cfg_hw_sriov(bp, &n, true);
+	}
+}
+
 static int bnxt_open(struct net_device *dev)
 {
 	struct bnxt *bp = netdev_priv(dev);
@@ -9258,13 +9269,7 @@ static int bnxt_open(struct net_device *dev)
 		bnxt_hwrm_if_change(bp, false);
 	} else {
 		if (test_and_clear_bit(BNXT_STATE_FW_RESET_DET, &bp->state)) {
-			if (BNXT_PF(bp)) {
-				struct bnxt_pf_info *pf = &bp->pf;
-				int n = pf->active_vfs;
-
-				if (n)
-					bnxt_cfg_hw_sriov(bp, &n, true);
-			}
+			bnxt_reenable_sriov(bp);
 			if (!test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))
 				bnxt_ulp_start(bp, 0);
 		}
-- 
2.21.1


From cc66cf74aee03c91b5455035222c4e2af71c8627 Mon Sep 17 00:00:00 2001
From: Michael Walle <michael@walle.cc>
Date: Thu, 30 Jan 2020 18:54:02 +0100
Subject: [PATCH 20/25] net: phy: at803x: disable vddio regulator

[ Upstream commit 2318ca8aef3877da2b16b92edce47a497370a86e ]

The probe() might enable a VDDIO regulator, which needs to be disabled
again before calling regulator_put(). Add a remove() function.

Fixes: 2f664823a470 ("net: phy: at803x: add device tree binding")
Signed-off-by: Michael Walle <michael@walle.cc>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/at803x.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c
index aee62610bade..481cf48c9b9e 100644
--- a/drivers/net/phy/at803x.c
+++ b/drivers/net/phy/at803x.c
@@ -489,6 +489,14 @@ static int at803x_probe(struct phy_device *phydev)
 	return at803x_parse_dt(phydev);
 }
 
+static void at803x_remove(struct phy_device *phydev)
+{
+	struct at803x_priv *priv = phydev->priv;
+
+	if (priv->vddio)
+		regulator_disable(priv->vddio);
+}
+
 static int at803x_clk_out_config(struct phy_device *phydev)
 {
 	struct at803x_priv *priv = phydev->priv;
@@ -711,6 +719,7 @@ static struct phy_driver at803x_driver[] = {
 	.name			= "Qualcomm Atheros AR8035",
 	.phy_id_mask		= AT803X_PHY_ID_MASK,
 	.probe			= at803x_probe,
+	.remove			= at803x_remove,
 	.config_init		= at803x_config_init,
 	.set_wol		= at803x_set_wol,
 	.get_wol		= at803x_get_wol,
@@ -726,6 +735,7 @@ static struct phy_driver at803x_driver[] = {
 	.name			= "Qualcomm Atheros AR8030",
 	.phy_id_mask		= AT803X_PHY_ID_MASK,
 	.probe			= at803x_probe,
+	.remove			= at803x_remove,
 	.config_init		= at803x_config_init,
 	.link_change_notify	= at803x_link_change_notify,
 	.set_wol		= at803x_set_wol,
@@ -741,6 +751,7 @@ static struct phy_driver at803x_driver[] = {
 	.name			= "Qualcomm Atheros AR8031/AR8033",
 	.phy_id_mask		= AT803X_PHY_ID_MASK,
 	.probe			= at803x_probe,
+	.remove			= at803x_remove,
 	.config_init		= at803x_config_init,
 	.set_wol		= at803x_set_wol,
 	.get_wol		= at803x_get_wol,
-- 
2.21.1


From 218d96e0692553fb51151bdc4ebf545b7f3166e4 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 2 Feb 2020 02:41:36 -0500
Subject: [PATCH 21/25] bnxt_en: Fix RDMA driver failure with SRIOV after
 firmware reset.

[ Upstream commit 12de2eadf87825c3990c1aa68b5e93101ca2f043 ]

bnxt_ulp_start() needs to be called before SRIOV is re-enabled after
firmware reset.  Re-enabling SRIOV may consume all the resources and
may cause the RDMA driver to fail to get MSIX and other resources.
Fix it by calling bnxt_ulp_start() first before calling
bnxt_reenable_sriov().

We re-arrange the logic so that we call bnxt_ulp_start() and
bnxt_reenable_sriov() in proper sequence in bnxt_fw_reset_task() and
bnxt_open().  The former is the normal coordinated firmware reset sequence
and the latter is firmware reset while the function is down.  This new
logic is now more straight forward and will now fix both scenarios.

Fixes: f3a6d206c25a ("bnxt_en: Call bnxt_ulp_stop()/bnxt_ulp_start() during error recovery.")
Reported-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 6c5825475a73..5a779d949716 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -9269,9 +9269,10 @@ static int bnxt_open(struct net_device *dev)
 		bnxt_hwrm_if_change(bp, false);
 	} else {
 		if (test_and_clear_bit(BNXT_STATE_FW_RESET_DET, &bp->state)) {
-			bnxt_reenable_sriov(bp);
-			if (!test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))
+			if (!test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
 				bnxt_ulp_start(bp, 0);
+				bnxt_reenable_sriov(bp);
+			}
 		}
 		bnxt_hwmon_open(bp);
 	}
@@ -10827,6 +10828,8 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 		smp_mb__before_atomic();
 		clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
 		bnxt_ulp_start(bp, rc);
+		if (!rc)
+			bnxt_reenable_sriov(bp);
 		bnxt_dl_health_status_update(bp, true);
 		rtnl_unlock();
 		break;
-- 
2.21.1


From 696f69cbbbe8048485a256ab4919d91489669485 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <snelson@pensando.io>
Date: Thu, 30 Jan 2020 10:07:06 -0800
Subject: [PATCH 22/25] ionic: fix rxq comp packet type mask

[ Upstream commit b5ce31b5e11b768b7d685b2bab7db09ad5549493 ]

Be sure to include all the packet type bits in the mask.

Fixes: fbfb8031533c ("ionic: Add hardware init and device commands")
Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/pensando/ionic/ionic_if.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_if.h b/drivers/net/ethernet/pensando/ionic/ionic_if.h
index 39317cdfa6cf..ed23a05f2642 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_if.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_if.h
@@ -862,7 +862,7 @@ struct ionic_rxq_comp {
 #define IONIC_RXQ_COMP_CSUM_F_VLAN	0x40
 #define IONIC_RXQ_COMP_CSUM_F_CALC	0x80
 	u8     pkt_type_color;
-#define IONIC_RXQ_COMP_PKT_TYPE_MASK	0x0f
+#define IONIC_RXQ_COMP_PKT_TYPE_MASK	0x7f
 };
 
 enum ionic_pkt_type {
-- 
2.21.1


From ca63442c9681c5bf58a7f4c4b8cc4e7422913239 Mon Sep 17 00:00:00 2001
From: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Date: Sat, 1 Feb 2020 13:43:01 +0100
Subject: [PATCH 23/25] MAINTAINERS: correct entries for ISDN/mISDN section

[ Upstream commit dff6bc1bfd462b76dc13ec19dedc2c134a62ac59 ]

Commit 6d97985072dc ("isdn: move capi drivers to staging") cleaned up the
isdn drivers and split the MAINTAINERS section for ISDN, but missed to add
the terminal slash for the two directories mISDN and hardware. Hence, all
files in those directories were not part of the new ISDN/mISDN SUBSYSTEM,
but were considered to be part of "THE REST".

Rectify the situation, and while at it, also complete the section with two
further build files that belong to that subsystem.

This was identified with a small script that finds all files belonging to
"THE REST" according to the current MAINTAINERS file, and I investigated
upon its output.

Fixes: 6d97985072dc ("isdn: move capi drivers to staging")
Signed-off-by: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 56765f542244..44bc9d7f04a4 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8808,8 +8808,10 @@ L:	isdn4linux@listserv.isdn4linux.de (subscribers-only)
 L:	netdev@vger.kernel.org
 W:	http://www.isdn4linux.de
 S:	Maintained
-F:	drivers/isdn/mISDN
-F:	drivers/isdn/hardware
+F:	drivers/isdn/mISDN/
+F:	drivers/isdn/hardware/
+F:	drivers/isdn/Kconfig
+F:	drivers/isdn/Makefile
 
 ISDN/CAPI SUBSYSTEM
 M:	Karsten Keil <isdn@linux-pingi.de>
-- 
2.21.1


From 3f1e42cd0cbf36af2978ca50de3c7733e3965a10 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Sat, 1 Feb 2020 16:43:22 +0000
Subject: [PATCH 24/25] netdevsim: fix stack-out-of-bounds in
 nsim_dev_debugfs_init()

[ Upstream commit 6fb8852b1298200da39bd85788bc5755d1d56f32 ]

When netdevsim dev is being created, a debugfs directory is created.
The variable "dev_ddir_name" is 16bytes device name pointer and device
name is "netdevsim<dev id>".
The maximum dev id length is 10.
So, 16bytes for device name isn't enough.

Test commands:
    modprobe netdevsim
    echo "1000000000 0" > /sys/bus/netdevsim/new_device

Splat looks like:
[  249.622710][  T900] BUG: KASAN: stack-out-of-bounds in number+0x824/0x880
[  249.623658][  T900] Write of size 1 at addr ffff88804c527988 by task bash/900
[  249.624521][  T900]
[  249.624830][  T900] CPU: 1 PID: 900 Comm: bash Not tainted 5.5.0+ #322
[  249.625691][  T900] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[  249.626712][  T900] Call Trace:
[  249.627103][  T900]  dump_stack+0x96/0xdb
[  249.627639][  T900]  ? number+0x824/0x880
[  249.628173][  T900]  print_address_description.constprop.5+0x1be/0x360
[  249.629022][  T900]  ? number+0x824/0x880
[  249.629569][  T900]  ? number+0x824/0x880
[  249.630105][  T900]  __kasan_report+0x12a/0x170
[  249.630717][  T900]  ? number+0x824/0x880
[  249.631201][  T900]  kasan_report+0xe/0x20
[  249.631723][  T900]  number+0x824/0x880
[  249.632235][  T900]  ? put_dec+0xa0/0xa0
[  249.632716][  T900]  ? rcu_read_lock_sched_held+0x90/0xc0
[  249.633392][  T900]  vsnprintf+0x63c/0x10b0
[  249.633983][  T900]  ? pointer+0x5b0/0x5b0
[  249.634543][  T900]  ? mark_lock+0x11d/0xc40
[  249.635200][  T900]  sprintf+0x9b/0xd0
[  249.635750][  T900]  ? scnprintf+0xe0/0xe0
[  249.636370][  T900]  nsim_dev_probe+0x63c/0xbf0 [netdevsim]
[ ... ]

Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Fixes: ab1d0cc004d7 ("netdevsim: change debugfs tree topology")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/netdevsim/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index 4b39aba2e9c4..2a945b3c7c76 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -73,7 +73,7 @@ static const struct file_operations nsim_dev_take_snapshot_fops = {
 
 static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev)
 {
-	char dev_ddir_name[16];
+	char dev_ddir_name[sizeof(DRV_NAME) + 10];
 
 	sprintf(dev_ddir_name, DRV_NAME "%u", nsim_dev->nsim_bus_dev->dev.id);
 	nsim_dev->ddir = debugfs_create_dir(dev_ddir_name, nsim_dev_ddir);
-- 
2.21.1


From b29ca01b5a6dfb6ff963ecc407e66dfcac42ef83 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Sun, 2 Feb 2020 02:41:37 -0500
Subject: [PATCH 25/25] bnxt_en: Fix logic that disables Bus Master during
 firmware reset.

[ Upstream commit d407302895d3f3ca3a333c711744a95e0b1b0150 ]

The current logic that calls pci_disable_device() in __bnxt_close_nic()
during firmware reset is flawed.  If firmware is still alive, we're
disabling the device too early, causing some firmware commands to
not reach the firmware.

Fix it by moving the logic to bnxt_reset_close().  If firmware is
in fatal condition, we call pci_disable_device() before we free
any of the rings to prevent DMA corruption of the freed rings.  If
firmware is still alive, we call pci_disable_device() after the
last firmware message has been sent.

Fixes: 3bc7d4a352ef ("bnxt_en: Add BNXT_STATE_IN_FW_RESET state.")
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 5a779d949716..01b603c5e76a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -9312,10 +9312,6 @@ static void __bnxt_close_nic(struct bnxt *bp, bool irq_re_init,
 	bnxt_debug_dev_exit(bp);
 	bnxt_disable_napi(bp);
 	del_timer_sync(&bp->timer);
-	if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state) &&
-	    pci_is_enabled(bp->pdev))
-		pci_disable_device(bp->pdev);
-
 	bnxt_free_skbs(bp);
 
 	/* Save ring stats before shutdown */
@@ -10093,9 +10089,16 @@ static void bnxt_reset(struct bnxt *bp, bool silent)
 static void bnxt_fw_reset_close(struct bnxt *bp)
 {
 	bnxt_ulp_stop(bp);
+	/* When firmware is fatal state, disable PCI device to prevent
+	 * any potential bad DMAs before freeing kernel memory.
+	 */
+	if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state))
+		pci_disable_device(bp->pdev);
 	__bnxt_close_nic(bp, true, false);
 	bnxt_clear_int_mode(bp);
 	bnxt_hwrm_func_drv_unrgtr(bp);
+	if (pci_is_enabled(bp->pdev))
+		pci_disable_device(bp->pdev);
 	bnxt_free_ctx_mem(bp);
 	kfree(bp->ctx);
 	bp->ctx = NULL;
-- 
2.21.1

Re: [PATCHES] Networking

[Greg KH]

On Wed, Feb 05, 2020 at 03:07:49PM +0100, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v5.4 and
> v5.5 -stable, respectively.

All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 105 bytes --]


Please queue up the following networking bug fixes for v5.4 and
v5.5 -stable, respectively.

Thank you.

[-- Attachment #2: net_54.mbox --]
[-- Type: Application/Octet-Stream, Size: 70928 bytes --]

From 1feb04008d8291a923bb372529342b84acd1c41e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 4 Feb 2020 19:26:05 -0800
Subject: [PATCH 01/24] bonding/alb: properly access headers in bond_alb_xmit()

[ Upstream commit 38f88c45404293bbc027b956def6c10cbd45c616 ]

syzbot managed to send an IPX packet through bond_alb_xmit()
and af_packet and triggered a use-after-free.

First, bond_alb_xmit() was using ipx_hdr() helper to reach
the IPX header, but ipx_hdr() was using the transport offset
instead of the network offset. In the particular syzbot
report transport offset was 0xFFFF

This patch removes ipx_hdr() since it was only (mis)used from bonding.

Then we need to make sure IPv4/IPv6/IPX headers are pulled
in skb->head before dereferencing anything.

BUG: KASAN: use-after-free in bond_alb_xmit+0x153a/0x1590 drivers/net/bonding/bond_alb.c:1452
Read of size 2 at addr ffff8801ce56dfff by task syz-executor.2/18108
 (if (ipx_hdr(skb)->ipx_checksum != IPX_NO_CHECKSUM) ...)

Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 [<ffffffff8441fc42>] __dump_stack lib/dump_stack.c:17 [inline]
 [<ffffffff8441fc42>] dump_stack+0x14d/0x20b lib/dump_stack.c:53
 [<ffffffff81a7dec4>] print_address_description+0x6f/0x20b mm/kasan/report.c:282
 [<ffffffff81a7e0ec>] kasan_report_error mm/kasan/report.c:380 [inline]
 [<ffffffff81a7e0ec>] kasan_report mm/kasan/report.c:438 [inline]
 [<ffffffff81a7e0ec>] kasan_report.cold+0x8c/0x2a0 mm/kasan/report.c:422
 [<ffffffff81a7dc4f>] __asan_report_load_n_noabort+0xf/0x20 mm/kasan/report.c:469
 [<ffffffff82c8c00a>] bond_alb_xmit+0x153a/0x1590 drivers/net/bonding/bond_alb.c:1452
 [<ffffffff82c60c74>] __bond_start_xmit drivers/net/bonding/bond_main.c:4199 [inline]
 [<ffffffff82c60c74>] bond_start_xmit+0x4f4/0x1570 drivers/net/bonding/bond_main.c:4224
 [<ffffffff83baa558>] __netdev_start_xmit include/linux/netdevice.h:4525 [inline]
 [<ffffffff83baa558>] netdev_start_xmit include/linux/netdevice.h:4539 [inline]
 [<ffffffff83baa558>] xmit_one net/core/dev.c:3611 [inline]
 [<ffffffff83baa558>] dev_hard_start_xmit+0x168/0x910 net/core/dev.c:3627
 [<ffffffff83bacf35>] __dev_queue_xmit+0x1f55/0x33b0 net/core/dev.c:4238
 [<ffffffff83bae3a8>] dev_queue_xmit+0x18/0x20 net/core/dev.c:4278
 [<ffffffff84339189>] packet_snd net/packet/af_packet.c:3226 [inline]
 [<ffffffff84339189>] packet_sendmsg+0x4919/0x70b0 net/packet/af_packet.c:3252
 [<ffffffff83b1ac0c>] sock_sendmsg_nosec net/socket.c:673 [inline]
 [<ffffffff83b1ac0c>] sock_sendmsg+0x12c/0x160 net/socket.c:684
 [<ffffffff83b1f5a2>] __sys_sendto+0x262/0x380 net/socket.c:1996
 [<ffffffff83b1f700>] SYSC_sendto net/socket.c:2008 [inline]
 [<ffffffff83b1f700>] SyS_sendto+0x40/0x60 net/socket.c:2004

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Cc: Veaceslav Falico <vfalico@gmail.com>
Cc: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_alb.c | 44 ++++++++++++++++++++++++----------
 include/net/ipx.h              |  5 ----
 2 files changed, 32 insertions(+), 17 deletions(-)

diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 4f2e6910c623..1cc2cd894f87 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -1383,26 +1383,31 @@ netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 	bool do_tx_balance = true;
 	u32 hash_index = 0;
 	const u8 *hash_start = NULL;
-	struct ipv6hdr *ip6hdr;
 
 	skb_reset_mac_header(skb);
 	eth_data = eth_hdr(skb);
 
 	switch (ntohs(skb->protocol)) {
 	case ETH_P_IP: {
-		const struct iphdr *iph = ip_hdr(skb);
+		const struct iphdr *iph;
 
 		if (is_broadcast_ether_addr(eth_data->h_dest) ||
-		    iph->daddr == ip_bcast ||
-		    iph->protocol == IPPROTO_IGMP) {
+		    !pskb_network_may_pull(skb, sizeof(*iph))) {
+			do_tx_balance = false;
+			break;
+		}
+		iph = ip_hdr(skb);
+		if (iph->daddr == ip_bcast || iph->protocol == IPPROTO_IGMP) {
 			do_tx_balance = false;
 			break;
 		}
 		hash_start = (char *)&(iph->daddr);
 		hash_size = sizeof(iph->daddr);
-	}
 		break;
-	case ETH_P_IPV6:
+	}
+	case ETH_P_IPV6: {
+		const struct ipv6hdr *ip6hdr;
+
 		/* IPv6 doesn't really use broadcast mac address, but leave
 		 * that here just in case.
 		 */
@@ -1419,7 +1424,11 @@ netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 			break;
 		}
 
-		/* Additianally, DAD probes should not be tx-balanced as that
+		if (!pskb_network_may_pull(skb, sizeof(*ip6hdr))) {
+			do_tx_balance = false;
+			break;
+		}
+		/* Additionally, DAD probes should not be tx-balanced as that
 		 * will lead to false positives for duplicate addresses and
 		 * prevent address configuration from working.
 		 */
@@ -1429,17 +1438,26 @@ netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 			break;
 		}
 
-		hash_start = (char *)&(ipv6_hdr(skb)->daddr);
-		hash_size = sizeof(ipv6_hdr(skb)->daddr);
+		hash_start = (char *)&ip6hdr->daddr;
+		hash_size = sizeof(ip6hdr->daddr);
 		break;
-	case ETH_P_IPX:
-		if (ipx_hdr(skb)->ipx_checksum != IPX_NO_CHECKSUM) {
+	}
+	case ETH_P_IPX: {
+		const struct ipxhdr *ipxhdr;
+
+		if (pskb_network_may_pull(skb, sizeof(*ipxhdr))) {
+			do_tx_balance = false;
+			break;
+		}
+		ipxhdr = (struct ipxhdr *)skb_network_header(skb);
+
+		if (ipxhdr->ipx_checksum != IPX_NO_CHECKSUM) {
 			/* something is wrong with this packet */
 			do_tx_balance = false;
 			break;
 		}
 
-		if (ipx_hdr(skb)->ipx_type != IPX_TYPE_NCP) {
+		if (ipxhdr->ipx_type != IPX_TYPE_NCP) {
 			/* The only protocol worth balancing in
 			 * this family since it has an "ARP" like
 			 * mechanism
@@ -1448,9 +1466,11 @@ netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 			break;
 		}
 
+		eth_data = eth_hdr(skb);
 		hash_start = (char *)eth_data->h_dest;
 		hash_size = ETH_ALEN;
 		break;
+	}
 	case ETH_P_ARP:
 		do_tx_balance = false;
 		if (bond_info->rlb_enabled)
diff --git a/include/net/ipx.h b/include/net/ipx.h
index baf090390998..9d1342807b59 100644
--- a/include/net/ipx.h
+++ b/include/net/ipx.h
@@ -47,11 +47,6 @@ struct ipxhdr {
 /* From af_ipx.c */
 extern int sysctl_ipx_pprop_broadcasting;
 
-static __inline__ struct ipxhdr *ipx_hdr(struct sk_buff *skb)
-{
-	return (struct ipxhdr *)skb_transport_header(skb);
-}
-
 struct ipx_interface {
 	/* IPX address */
 	__be32			if_netnum;
-- 
2.21.1


From ecc3ee57424c98466274e0241c881fa330f1cddb Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Tue, 4 Feb 2020 15:59:50 -0800
Subject: [PATCH 02/24] devlink: report 0 after hitting end in region read

[ Upstream commit d5b90e99e1d51b7b5d2b74fbc4c2db236a510913 ]

commit fdd41ec21e15 ("devlink: Return right error code in case of errors
for region read") modified the region read code to report errors
properly in unexpected cases.

In the case where the start_offset and ret_offset match, it unilaterally
converted this into an error. This causes an issue for the "dump"
version of the command. In this case, the devlink region dump will
always report an invalid argument:

000000000000ffd0 ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
000000000000ffe0 ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
devlink answers: Invalid argument
000000000000fff0 ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff

This occurs because the expected flow for the dump is to return 0 after
there is no further data.

The simplest fix would be to stop converting the error code to -EINVAL
if start_offset == ret_offset. However, avoid unnecessary work by
checking for when start_offset is larger than the region size and
returning 0 upfront.

Fixes: fdd41ec21e15 ("devlink: Return right error code in case of errors for region read")
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/devlink.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/core/devlink.c b/net/core/devlink.c
index ae614965c8c2..61bc67047f56 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -3863,6 +3863,12 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
 		goto out_unlock;
 	}
 
+	/* return 0 if there is no further data to read */
+	if (start_offset >= region->size) {
+		err = 0;
+		goto out_unlock;
+	}
+
 	hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
 			  &devlink_nl_family, NLM_F_ACK | NLM_F_MULTI,
 			  DEVLINK_CMD_REGION_READ);
-- 
2.21.1


From f075b33f54613ff07400936603ace5344dae214b Mon Sep 17 00:00:00 2001
From: Madalin Bucur <madalin.bucur@oss.nxp.com>
Date: Tue, 4 Feb 2020 12:08:58 +0200
Subject: [PATCH 03/24] dpaa_eth: support all modes with rate adapting PHYs

[ Upstream commit 73a21fa817f0cc8022dc6226250a86bca727a56d ]

Stop removing modes that are not supported on the system interface
when the connected PHY is capable of rate adaptation. This addresses
an issue with the LS1046ARDB board 10G interface no longer working
with an 1G link partner after autonegotiation support was added
for the Aquantia PHY on board in

commit 09c4c57f7bc4 ("net: phy: aquantia: add support for auto-negotiation configuration")

Before this commit the values advertised by the PHY were not
influenced by the dpaa_eth driver removal of system-side unsupported
modes as the aqr_config_aneg() was basically a no-op. After this
commit, the modes removed by the dpaa_eth driver were no longer
advertised thus autonegotiation with 1G link partners failed.

Reported-by: Mian Yousaf Kaukab <ykaukab@suse.de>
Signed-off-by: Madalin Bucur <madalin.bucur@oss.nxp.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index fcbe01f61aa4..e130233b5085 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -2483,6 +2483,9 @@ static void dpaa_adjust_link(struct net_device *net_dev)
 	mac_dev->adjust_link(mac_dev);
 }
 
+/* The Aquantia PHYs are capable of performing rate adaptation */
+#define PHY_VEND_AQUANTIA	0x03a1b400
+
 static int dpaa_phy_init(struct net_device *net_dev)
 {
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
@@ -2501,9 +2504,14 @@ static int dpaa_phy_init(struct net_device *net_dev)
 		return -ENODEV;
 	}
 
-	/* Remove any features not supported by the controller */
-	ethtool_convert_legacy_u32_to_link_mode(mask, mac_dev->if_support);
-	linkmode_and(phy_dev->supported, phy_dev->supported, mask);
+	/* Unless the PHY is capable of rate adaptation */
+	if (mac_dev->phy_if != PHY_INTERFACE_MODE_XGMII ||
+	    ((phy_dev->drv->phy_id & GENMASK(31, 10)) != PHY_VEND_AQUANTIA)) {
+		/* remove any features not supported by the controller */
+		ethtool_convert_legacy_u32_to_link_mode(mask,
+							mac_dev->if_support);
+		linkmode_and(phy_dev->supported, phy_dev->supported, mask);
+	}
 
 	phy_support_asym_pause(phy_dev);
 
-- 
2.21.1


From 4defed9c1f2016382bdad782b6ef812468164e82 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 6 Feb 2020 11:07:45 -0800
Subject: [PATCH 04/24] net: dsa: b53: Always use dev->vlan_enabled in
 b53_configure_vlan()

[ Upstream commit df373702bc0f8f2d83980ea441e71639fc1efcf8 ]

b53_configure_vlan() is called by the bcm_sf2 driver upon setup and
indirectly through resume as well. During the initial setup, we are
guaranteed that dev->vlan_enabled is false, so there is no change in
behavior, however during suspend, we may have enabled VLANs before, so we
do want to restore that setting.

Fixes: dad8d7c6452b ("net: dsa: b53: Properly account for VLAN filtering")
Fixes: 967dd82ffc52 ("net: dsa: b53: Add support for Broadcom RoboSwitch")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/b53/b53_common.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index a7132c1593c3..7ed667b304d1 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -680,7 +680,7 @@ int b53_configure_vlan(struct dsa_switch *ds)
 		b53_do_vlan_op(dev, VTA_CMD_CLEAR);
 	}
 
-	b53_enable_vlan(dev, false, ds->vlan_filtering);
+	b53_enable_vlan(dev, dev->vlan_enabled, ds->vlan_filtering);
 
 	b53_for_each_port(dev, i)
 		b53_write16(dev, B53_VLAN_PAGE,
-- 
2.21.1


From b649b77aba406df204a2784e3494d7ef2d950bad Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 6 Feb 2020 11:23:52 -0800
Subject: [PATCH 05/24] net: dsa: bcm_sf2: Only 7278 supports 2Gb/sec IMP port

[ Upstream commit de34d7084edd069dac5aa010cfe32bd8c4619fa6 ]

The 7445 switch clocking profiles do not allow us to run the IMP port at
2Gb/sec in a way that it is reliable and consistent. Make sure that the
setting is only applied to the 7278 family.

Fixes: 8f1880cbe8d0 ("net: dsa: bcm_sf2: Configure IMP port for 2Gb/sec")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 47b21096b577..fecd5e674e04 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -68,7 +68,9 @@ static void bcm_sf2_imp_setup(struct dsa_switch *ds, int port)
 
 		/* Force link status for IMP port */
 		reg = core_readl(priv, offset);
-		reg |= (MII_SW_OR | LINK_STS | GMII_SPEED_UP_2G);
+		reg |= (MII_SW_OR | LINK_STS);
+		if (priv->type == BCM7278_DEVICE_ID)
+			reg |= GMII_SPEED_UP_2G;
 		core_writel(priv, reg, offset);
 
 		/* Enable Broadcast, Multicast, Unicast forwarding to IMP port */
-- 
2.21.1


From 044cda24d4b430541ae5bda406c936b96fe6ce44 Mon Sep 17 00:00:00 2001
From: Razvan Stefanescu <razvan.stefanescu@microchip.com>
Date: Fri, 7 Feb 2020 17:44:04 +0200
Subject: [PATCH 06/24] net: dsa: microchip: enable module autoprobe

[ Upstream commit f8c2afa66d5397b0b9293c4347dac6dabb327685 ]

This matches /sys/devices/.../spi1.0/modalias content.

Fixes: 9b2d9f05cddf ("net: dsa: microchip: add ksz9567 to ksz9477 driver")
Fixes: d9033ae95cf4 ("net: dsa: microchip: add KSZ8563 compatibility string")
Fixes: 8c29bebb1f8a ("net: dsa: microchip: add KSZ9893 switch support")
Fixes: 45316818371d ("net: dsa: add support for ksz9897 ethernet switch")
Fixes: b987e98e50ab ("dsa: add DSA switch driver for Microchip KSZ9477")
Signed-off-by: Razvan Stefanescu <razvan.stefanescu@microchip.com>
Signed-off-by: Codrin Ciubotariu <codrin.ciubotariu@microchip.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/microchip/ksz9477_spi.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/dsa/microchip/ksz9477_spi.c b/drivers/net/dsa/microchip/ksz9477_spi.c
index c5f64959a184..1142768969c2 100644
--- a/drivers/net/dsa/microchip/ksz9477_spi.c
+++ b/drivers/net/dsa/microchip/ksz9477_spi.c
@@ -101,6 +101,12 @@ static struct spi_driver ksz9477_spi_driver = {
 
 module_spi_driver(ksz9477_spi_driver);
 
+MODULE_ALIAS("spi:ksz9477");
+MODULE_ALIAS("spi:ksz9897");
+MODULE_ALIAS("spi:ksz9893");
+MODULE_ALIAS("spi:ksz9563");
+MODULE_ALIAS("spi:ksz8563");
+MODULE_ALIAS("spi:ksz9567");
 MODULE_AUTHOR("Woojung Huh <Woojung.Huh@microchip.com>");
 MODULE_DESCRIPTION("Microchip KSZ9477 Series Switch SPI access Driver");
 MODULE_LICENSE("GPL");
-- 
2.21.1


From f7c12bef90ece69b46c56e4b379da5a1f653bdbe Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 6 Feb 2020 10:14:39 +0100
Subject: [PATCH 07/24] net: mvneta: move rx_dropped and rx_errors in per-cpu
 stats

[ Upstream commit c35947b8ff8acca33134ee39c31708233765c31a ]

Move rx_dropped and rx_errors counters in mvneta_pcpu_stats in order to
avoid possible races updating statistics

Fixes: 562e2f467e71 ("net: mvneta: Improve the buffer allocation method for SWBM")
Fixes: dc35a10f68d3 ("net: mvneta: bm: add support for hardware buffer management")
Fixes: c5aff18204da ("net: mvneta: driver for Marvell Armada 370/XP network unit")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 27 +++++++++++++++++++++------
 1 file changed, 21 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index e49820675c8c..6b1a81df1465 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -388,6 +388,8 @@ struct mvneta_pcpu_stats {
 	struct	u64_stats_sync syncp;
 	u64	rx_packets;
 	u64	rx_bytes;
+	u64	rx_dropped;
+	u64	rx_errors;
 	u64	tx_packets;
 	u64	tx_bytes;
 };
@@ -706,6 +708,8 @@ mvneta_get_stats64(struct net_device *dev,
 		struct mvneta_pcpu_stats *cpu_stats;
 		u64 rx_packets;
 		u64 rx_bytes;
+		u64 rx_dropped;
+		u64 rx_errors;
 		u64 tx_packets;
 		u64 tx_bytes;
 
@@ -714,19 +718,20 @@ mvneta_get_stats64(struct net_device *dev,
 			start = u64_stats_fetch_begin_irq(&cpu_stats->syncp);
 			rx_packets = cpu_stats->rx_packets;
 			rx_bytes   = cpu_stats->rx_bytes;
+			rx_dropped = cpu_stats->rx_dropped;
+			rx_errors  = cpu_stats->rx_errors;
 			tx_packets = cpu_stats->tx_packets;
 			tx_bytes   = cpu_stats->tx_bytes;
 		} while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start));
 
 		stats->rx_packets += rx_packets;
 		stats->rx_bytes   += rx_bytes;
+		stats->rx_dropped += rx_dropped;
+		stats->rx_errors  += rx_errors;
 		stats->tx_packets += tx_packets;
 		stats->tx_bytes   += tx_bytes;
 	}
 
-	stats->rx_errors	= dev->stats.rx_errors;
-	stats->rx_dropped	= dev->stats.rx_dropped;
-
 	stats->tx_dropped	= dev->stats.tx_dropped;
 }
 
@@ -1703,8 +1708,14 @@ static u32 mvneta_txq_desc_csum(int l3_offs, int l3_proto,
 static void mvneta_rx_error(struct mvneta_port *pp,
 			    struct mvneta_rx_desc *rx_desc)
 {
+	struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats);
 	u32 status = rx_desc->status;
 
+	/* update per-cpu counter */
+	u64_stats_update_begin(&stats->syncp);
+	stats->rx_errors++;
+	u64_stats_update_end(&stats->syncp);
+
 	switch (status & MVNETA_RXD_ERR_CODE_MASK) {
 	case MVNETA_RXD_ERR_CRC:
 		netdev_err(pp->dev, "bad rx status %08x (crc error), size=%d\n",
@@ -1965,7 +1976,6 @@ static int mvneta_rx_swbm(struct napi_struct *napi,
 			/* Check errors only for FIRST descriptor */
 			if (rx_status & MVNETA_RXD_ERR_SUMMARY) {
 				mvneta_rx_error(pp, rx_desc);
-				dev->stats.rx_errors++;
 				/* leave the descriptor untouched */
 				continue;
 			}
@@ -1976,11 +1986,17 @@ static int mvneta_rx_swbm(struct napi_struct *napi,
 			skb_size = max(rx_copybreak, rx_header_size);
 			rxq->skb = netdev_alloc_skb_ip_align(dev, skb_size);
 			if (unlikely(!rxq->skb)) {
+				struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats);
+
 				netdev_err(dev,
 					   "Can't allocate skb on queue %d\n",
 					   rxq->id);
-				dev->stats.rx_dropped++;
+
 				rxq->skb_alloc_err++;
+
+				u64_stats_update_begin(&stats->syncp);
+				stats->rx_dropped++;
+				u64_stats_update_end(&stats->syncp);
 				continue;
 			}
 			copy_size = min(skb_size, rx_bytes);
@@ -2137,7 +2153,6 @@ static int mvneta_rx_hwbm(struct napi_struct *napi,
 			mvneta_bm_pool_put_bp(pp->bm_priv, bm_pool,
 					      rx_desc->buf_phys_addr);
 err_drop_frame:
-			dev->stats.rx_errors++;
 			mvneta_rx_error(pp, rx_desc);
 			/* leave the descriptor untouched */
 			continue;
-- 
2.21.1


From 08dc2c211ae6856d29d6f4363a1c8de849d29284 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Tue, 4 Feb 2020 11:10:12 -0800
Subject: [PATCH 08/24] net_sched: fix a resource leak in tcindex_set_parms()

[ Upstream commit 52b5ae501c045010aeeb1d5ac0373ff161a88291 ]

Jakub noticed there is a potential resource leak in
tcindex_set_parms(): when tcindex_filter_result_init() fails
and it jumps to 'errout1' which doesn't release the memory
and resources allocated by tcindex_alloc_perfect_hash().

We should just jump to 'errout_alloc' which calls
tcindex_free_perfect_hash().

Fixes: b9a24bb76bf6 ("net_sched: properly handle failure case of tcf_exts_init()")
Reported-by: Jakub Kicinski <kuba@kernel.org>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_tcindex.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 3d4a1280352f..e53834c35447 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -346,7 +346,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 
 	err = tcindex_filter_result_init(&new_filter_result, net);
 	if (err < 0)
-		goto errout1;
+		goto errout_alloc;
 	if (old_r)
 		cr = r->res;
 
@@ -484,7 +484,6 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 		tcindex_free_perfect_hash(cp);
 	else if (balloc == 2)
 		kfree(cp->h);
-errout1:
 	tcf_exts_destroy(&new_filter_result.exts);
 errout:
 	kfree(cp);
-- 
2.21.1


From 5c3c7abf1ff928d92260f5fb8b451b597eb86f20 Mon Sep 17 00:00:00 2001
From: Dejin Zheng <zhengdejin5@gmail.com>
Date: Thu, 6 Feb 2020 23:29:17 +0800
Subject: [PATCH 09/24] net: stmmac: fix a possible endless loop

[ Upstream commit 7d10f0774f9e32aa2f2e012f7fcb312a2ce422b9 ]

It forgot to reduce the value of the variable retry in a while loop
in the ethqos_configure() function. It may cause an endless loop and
without timeout.

Fixes: a7c30e62d4b8 ("net: stmmac: Add driver for Qualcomm ethqos")
Signed-off-by: Dejin Zheng <zhengdejin5@gmail.com>
Acked-by: Vinod Koul <vkoul@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
index 7ec895407d23..e0a5fe83d8e0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
@@ -413,6 +413,7 @@ static int ethqos_configure(struct qcom_ethqos *ethqos)
 			dll_lock = rgmii_readl(ethqos, SDC4_STATUS);
 			if (dll_lock & SDC4_STATUS_DLL_LOCK)
 				break;
+			retry--;
 		} while (retry > 0);
 		if (!retry)
 			dev_err(&ethqos->pdev->dev,
-- 
2.21.1


From fb67f708de861269bc205c1b86dbfc93baecae2b Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 5 Feb 2020 12:32:04 -0800
Subject: [PATCH 10/24] net: systemport: Avoid RBUF stuck in Wake-on-LAN mode

[ Upstream commit 263a425a482fc495d6d3f9a29b9103a664c38b69 ]

After a number of suspend and resume cycles, it is possible for the RBUF
to be stuck in Wake-on-LAN mode, despite the MPD enable bit being
cleared which instructed the RBUF to exit that mode.

Avoid creating that problematic condition by clearing the RX_EN and
TX_EN bits in the UniMAC prior to disable the Magic Packet Detector
logic which is guaranteed to make the RBUF exit Wake-on-LAN mode.

Fixes: 83e82f4c706b ("net: systemport: add Wake-on-LAN support")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bcmsysport.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index b4c664957266..4a27577e137b 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -2728,6 +2728,9 @@ static int __maybe_unused bcm_sysport_resume(struct device *d)
 
 	umac_reset(priv);
 
+	/* Disable the UniMAC RX/TX */
+	umac_enable_set(priv, CMD_RX_EN | CMD_TX_EN, 0);
+
 	/* We may have been suspended and never received a WOL event that
 	 * would turn off MPD detection, take care of that now
 	 */
-- 
2.21.1


From 55b98880a803f84c26d19c8e6cc5c41be31a01e3 Mon Sep 17 00:00:00 2001
From: Raed Salem <raeds@mellanox.com>
Date: Tue, 24 Dec 2019 09:54:45 +0200
Subject: [PATCH 11/24] net/mlx5: IPsec, Fix esp modify function attribute

[ Upstream commit 0dc2c534f17c05bed0622b37a744bc38b48ca88a ]

The function mlx5_fpga_esp_validate_xfrm_attrs is wrongly used
with negative negation as zero value indicates success but it
used as failure return value instead.

Fix by remove the unary not negation operator.

Fixes: 05564d0ae075 ("net/mlx5: Add flow-steering commands for FPGA IPSec implementation")
Signed-off-by: Raed Salem <raeds@mellanox.com>
Reviewed-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
index c76da309506b..e62a9b1aa060 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
@@ -1478,7 +1478,7 @@ int mlx5_fpga_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm,
 	if (!memcmp(&xfrm->attrs, attrs, sizeof(xfrm->attrs)))
 		return 0;
 
-	if (!mlx5_fpga_esp_validate_xfrm_attrs(mdev, attrs)) {
+	if (mlx5_fpga_esp_validate_xfrm_attrs(mdev, attrs)) {
 		mlx5_core_warn(mdev, "Tried to create an esp with unsupported attrs\n");
 		return -EOPNOTSUPP;
 	}
-- 
2.21.1


From c509221ad810416029fdbb96cc152c5d6a07f390 Mon Sep 17 00:00:00 2001
From: Raed Salem <raeds@mellanox.com>
Date: Wed, 23 Oct 2019 16:41:21 +0300
Subject: [PATCH 12/24] net/mlx5: IPsec, fix memory leak at
 mlx5_fpga_ipsec_delete_sa_ctx

[ Upstream commit 08db2cf577487f5123aebcc2f913e0b8a2c14b43 ]

SA context is allocated at mlx5_fpga_ipsec_create_sa_ctx,
however the counterpart mlx5_fpga_ipsec_delete_sa_ctx function
nullifies sa_ctx pointer without freeing the memory allocated,
hence the memory leak.

Fix by free SA context when the SA is released.

Fixes: d6c4f0298cec ("net/mlx5: Refactor accel IPSec code")
Signed-off-by: Raed Salem <raeds@mellanox.com>
Reviewed-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
index e62a9b1aa060..72232e570af7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
@@ -850,6 +850,7 @@ void mlx5_fpga_ipsec_delete_sa_ctx(void *context)
 	mutex_lock(&fpga_xfrm->lock);
 	if (!--fpga_xfrm->num_rules) {
 		mlx5_fpga_ipsec_release_sa_ctx(fpga_xfrm->sa_ctx);
+		kfree(fpga_xfrm->sa_ctx);
 		fpga_xfrm->sa_ctx = NULL;
 	}
 	mutex_unlock(&fpga_xfrm->lock);
-- 
2.21.1


From b4f7ccf966413561764fdf7734094655fb881711 Mon Sep 17 00:00:00 2001
From: Harini Katakam <harini.katakam@xilinx.com>
Date: Wed, 5 Feb 2020 18:08:11 +0530
Subject: [PATCH 13/24] net: macb: Remove unnecessary alignment check for TSO

[ Upstream commit 41c1ef978c8d0259c6636e6d2d854777e92650eb ]

The IP TSO implementation does NOT require the length to be a
multiple of 8. That is only a requirement for UFO as per IP
documentation. Hence, exit macb_features_check function in the
beginning if the protocol is not UDP. Only when it is UDP,
proceed further to the alignment checks. Update comments to
reflect the same. Also remove dead code checking for protocol
TCP when calculating header length.

Fixes: 1629dd4f763c ("cadence: Add LSO support.")
Signed-off-by: Harini Katakam <harini.katakam@xilinx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index f496b248bda3..081f17cf6752 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -1664,16 +1664,14 @@ static netdev_features_t macb_features_check(struct sk_buff *skb,
 
 	/* Validate LSO compatibility */
 
-	/* there is only one buffer */
-	if (!skb_is_nonlinear(skb))
+	/* there is only one buffer or protocol is not UDP */
+	if (!skb_is_nonlinear(skb) || (ip_hdr(skb)->protocol != IPPROTO_UDP))
 		return features;
 
 	/* length of header */
 	hdrlen = skb_transport_offset(skb);
-	if (ip_hdr(skb)->protocol == IPPROTO_TCP)
-		hdrlen += tcp_hdrlen(skb);
 
-	/* For LSO:
+	/* For UFO only:
 	 * When software supplies two or more payload buffers all payload buffers
 	 * apart from the last must be a multiple of 8 bytes in size.
 	 */
-- 
2.21.1


From a56f32d58725fdeeb1c28f9f95d2923b8d9fa39f Mon Sep 17 00:00:00 2001
From: Harini Katakam <harini.katakam@xilinx.com>
Date: Wed, 5 Feb 2020 18:08:12 +0530
Subject: [PATCH 14/24] net: macb: Limit maximum GEM TX length in TSO

[ Upstream commit f822e9c4ffa511a5c681cf866287d9383a3b6f1b ]

GEM_MAX_TX_LEN currently resolves to 0x3FF8 for any IP version supporting
TSO with full 14bits of length field in payload descriptor. But an IP
errata causes false amba_error (bit 6 of ISR) when length in payload
descriptors is specified above 16387. The error occurs because the DMA
falsely concludes that there is not enough space in SRAM for incoming
payload. These errors were observed continuously under stress of large
packets using iperf on a version where SRAM was 16K for each queue. This
errata will be documented shortly and affects all versions since TSO
functionality was added. Hence limit the max length to 0x3FC0 (rounded).

Signed-off-by: Harini Katakam <harini.katakam@xilinx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 081f17cf6752..95a94507cec1 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -73,7 +73,11 @@ struct sifive_fu540_macb_mgmt {
 /* Max length of transmit frame must be a multiple of 8 bytes */
 #define MACB_TX_LEN_ALIGN	8
 #define MACB_MAX_TX_LEN		((unsigned int)((1 << MACB_TX_FRMLEN_SIZE) - 1) & ~((unsigned int)(MACB_TX_LEN_ALIGN - 1)))
-#define GEM_MAX_TX_LEN		((unsigned int)((1 << GEM_TX_FRMLEN_SIZE) - 1) & ~((unsigned int)(MACB_TX_LEN_ALIGN - 1)))
+/* Limit maximum TX length as per Cadence TSO errata. This is to avoid a
+ * false amba_error in TX path from the DMA assuming there is not enough
+ * space in the SRAM (16KB) even when there is.
+ */
+#define GEM_MAX_TX_LEN		(unsigned int)(0x3FC0)
 
 #define GEM_MTU_MIN_SIZE	ETH_MIN_MTU
 #define MACB_NETIF_LSO		NETIF_F_TSO
-- 
2.21.1


From cef3b1384195100e84bc07bdb40a647e999f6d01 Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Thu, 6 Feb 2020 13:46:06 -0800
Subject: [PATCH 15/24] taprio: Fix enabling offload with wrong number of
 traffic classes

[ Upstream commit 5652e63df3303c2a702bac25fbf710b9cb64dfba ]

If the driver implementing taprio offloading depends on the value of
the network device number of traffic classes (dev->num_tc) for
whatever reason, it was going to receive the value zero. The value was
only set after the offloading function is called.

So, moving setting the number of traffic classes to before the
offloading function is called fixes this issue. This is safe because
this only happens when taprio is instantiated (we don't allow this
configuration to be changed without first removing taprio).

Fixes: 9c66d1564676 ("taprio: Add support for hardware offloading")
Reported-by: Po Liu <po.liu@nxp.com>
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Acked-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_taprio.c | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index c609373c8661..ad0dadcfcdba 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -1444,6 +1444,19 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 
 	taprio_set_picos_per_byte(dev, q);
 
+	if (mqprio) {
+		netdev_set_num_tc(dev, mqprio->num_tc);
+		for (i = 0; i < mqprio->num_tc; i++)
+			netdev_set_tc_queue(dev, i,
+					    mqprio->count[i],
+					    mqprio->offset[i]);
+
+		/* Always use supplied priority mappings */
+		for (i = 0; i <= TC_BITMASK; i++)
+			netdev_set_prio_tc_map(dev, i,
+					       mqprio->prio_tc_map[i]);
+	}
+
 	if (FULL_OFFLOAD_IS_ENABLED(taprio_flags))
 		err = taprio_enable_offload(dev, mqprio, q, new_admin, extack);
 	else
@@ -1471,19 +1484,6 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 		q->advance_timer.function = advance_sched;
 	}
 
-	if (mqprio) {
-		netdev_set_num_tc(dev, mqprio->num_tc);
-		for (i = 0; i < mqprio->num_tc; i++)
-			netdev_set_tc_queue(dev, i,
-					    mqprio->count[i],
-					    mqprio->offset[i]);
-
-		/* Always use supplied priority mappings */
-		for (i = 0; i <= TC_BITMASK; i++)
-			netdev_set_prio_tc_map(dev, i,
-					       mqprio->prio_tc_map[i]);
-	}
-
 	if (FULL_OFFLOAD_IS_ENABLED(taprio_flags)) {
 		q->dequeue = taprio_dequeue_offload;
 		q->peek = taprio_peek_offload;
-- 
2.21.1


From d9126f697382704e5353192be2439ea2f55c9d64 Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Thu, 6 Feb 2020 13:46:07 -0800
Subject: [PATCH 16/24] taprio: Fix still allowing changing the flags during
 runtime

[ Upstream commit a9d6227436f32142209f4428f2dc616761485112 ]

Because 'q->flags' starts as zero, and zero is a valid value, we
aren't able to detect the transition from zero to something else
during "runtime".

The solution is to initialize 'q->flags' with an invalid value, so we
can detect if 'q->flags' was set by the user or not.

To better solidify the behavior, 'flags' handling is moved to a
separate function. The behavior is:
 - 'flags' if unspecified by the user, is assumed to be zero;
 - 'flags' cannot change during "runtime" (i.e. a change() request
 cannot modify it);

With this new function we can remove taprio_flags, which should reduce
the risk of future accidents.

Allowing flags to be changed was causing the following RCU stall:

[ 1730.558249] rcu: INFO: rcu_preempt detected stalls on CPUs/tasks:
[ 1730.558258] rcu: 	  6-...0: (190 ticks this GP) idle=922/0/0x1 softirq=25580/25582 fqs=16250
[ 1730.558264] 		  (detected by 2, t=65002 jiffies, g=33017, q=81)
[ 1730.558269] Sending NMI from CPU 2 to CPUs 6:
[ 1730.559277] NMI backtrace for cpu 6
[ 1730.559277] CPU: 6 PID: 0 Comm: swapper/6 Tainted: G            E     5.5.0-rc6+ #35
[ 1730.559278] Hardware name: Gigabyte Technology Co., Ltd. Z390 AORUS ULTRA/Z390 AORUS ULTRA-CF, BIOS F7 03/14/2019
[ 1730.559278] RIP: 0010:__hrtimer_run_queues+0xe2/0x440
[ 1730.559278] Code: 48 8b 43 28 4c 89 ff 48 8b 75 c0 48 89 45 c8 e8 f4 bb 7c 00 0f 1f 44 00 00 65 8b 05 40 31 f0 68 89 c0 48 0f a3 05 3e 5c 25 01 <0f> 82 fc 01 00 00 48 8b 45 c8 48 89 df ff d0 89 45 c8 0f 1f 44 00
[ 1730.559279] RSP: 0018:ffff9970802d8f10 EFLAGS: 00000083
[ 1730.559279] RAX: 0000000000000006 RBX: ffff8b31645bff38 RCX: 0000000000000000
[ 1730.559280] RDX: 0000000000000000 RSI: ffffffff9710f2ec RDI: ffffffff978daf0e
[ 1730.559280] RBP: ffff9970802d8f68 R08: 0000000000000000 R09: 0000000000000000
[ 1730.559280] R10: 0000018336d7944e R11: 0000000000000001 R12: ffff8b316e39f9c0
[ 1730.559281] R13: ffff8b316e39f940 R14: ffff8b316e39f998 R15: ffff8b316e39f7c0
[ 1730.559281] FS:  0000000000000000(0000) GS:ffff8b316e380000(0000) knlGS:0000000000000000
[ 1730.559281] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 1730.559281] CR2: 00007f1105303760 CR3: 0000000227210005 CR4: 00000000003606e0
[ 1730.559282] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 1730.559282] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ 1730.559282] Call Trace:
[ 1730.559282]  <IRQ>
[ 1730.559283]  ? taprio_dequeue_soft+0x2d0/0x2d0 [sch_taprio]
[ 1730.559283]  hrtimer_interrupt+0x104/0x220
[ 1730.559283]  ? irqtime_account_irq+0x34/0xa0
[ 1730.559283]  smp_apic_timer_interrupt+0x6d/0x230
[ 1730.559284]  apic_timer_interrupt+0xf/0x20
[ 1730.559284]  </IRQ>
[ 1730.559284] RIP: 0010:cpu_idle_poll+0x35/0x1a0
[ 1730.559285] Code: 88 82 ff 65 44 8b 25 12 7d 73 68 0f 1f 44 00 00 e8 90 c3 89 ff fb 65 48 8b 1c 25 c0 7e 01 00 48 8b 03 a8 08 74 0b eb 1c f3 90 <48> 8b 03 a8 08 75 13 8b 05 be a8 a8 00 85 c0 75 ed e8 75 48 84 ff
[ 1730.559285] RSP: 0018:ffff997080137ea8 EFLAGS: 00000202 ORIG_RAX: ffffffffffffff13
[ 1730.559285] RAX: 0000000000000001 RBX: ffff8b316bc3c580 RCX: 0000000000000000
[ 1730.559286] RDX: 0000000000000001 RSI: 000000002819aad9 RDI: ffffffff978da730
[ 1730.559286] RBP: ffff997080137ec0 R08: 0000018324a6d387 R09: 0000000000000000
[ 1730.559286] R10: 0000000000000400 R11: 0000000000000001 R12: 0000000000000006
[ 1730.559286] R13: ffff8b316bc3c580 R14: 0000000000000000 R15: 0000000000000000
[ 1730.559287]  ? cpu_idle_poll+0x20/0x1a0
[ 1730.559287]  ? cpu_idle_poll+0x20/0x1a0
[ 1730.559287]  do_idle+0x4d/0x1f0
[ 1730.559287]  ? complete+0x44/0x50
[ 1730.559288]  cpu_startup_entry+0x1b/0x20
[ 1730.559288]  start_secondary+0x142/0x180
[ 1730.559288]  secondary_startup_64+0xb6/0xc0
[ 1776.686313] nvme nvme0: I/O 96 QID 1 timeout, completion polled

Fixes: 4cfd5779bd6e ("taprio: Add support for txtime-assist mode")
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_taprio.c | 61 ++++++++++++++++++++++++++++--------------
 1 file changed, 41 insertions(+), 20 deletions(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index ad0dadcfcdba..e2d4283bea6d 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -31,6 +31,7 @@ static DEFINE_SPINLOCK(taprio_list_lock);
 
 #define TXTIME_ASSIST_IS_ENABLED(flags) ((flags) & TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST)
 #define FULL_OFFLOAD_IS_ENABLED(flags) ((flags) & TCA_TAPRIO_ATTR_FLAG_FULL_OFFLOAD)
+#define TAPRIO_FLAGS_INVALID U32_MAX
 
 struct sched_entry {
 	struct list_head list;
@@ -1367,6 +1368,33 @@ static int taprio_mqprio_cmp(const struct net_device *dev,
 	return 0;
 }
 
+/* The semantics of the 'flags' argument in relation to 'change()'
+ * requests, are interpreted following two rules (which are applied in
+ * this order): (1) an omitted 'flags' argument is interpreted as
+ * zero; (2) the 'flags' of a "running" taprio instance cannot be
+ * changed.
+ */
+static int taprio_new_flags(const struct nlattr *attr, u32 old,
+			    struct netlink_ext_ack *extack)
+{
+	u32 new = 0;
+
+	if (attr)
+		new = nla_get_u32(attr);
+
+	if (old != TAPRIO_FLAGS_INVALID && old != new) {
+		NL_SET_ERR_MSG_MOD(extack, "Changing 'flags' of a running schedule is not supported");
+		return -EOPNOTSUPP;
+	}
+
+	if (!taprio_flags_valid(new)) {
+		NL_SET_ERR_MSG_MOD(extack, "Specified 'flags' are not valid");
+		return -EINVAL;
+	}
+
+	return new;
+}
+
 static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 			 struct netlink_ext_ack *extack)
 {
@@ -1375,7 +1403,6 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 	struct taprio_sched *q = qdisc_priv(sch);
 	struct net_device *dev = qdisc_dev(sch);
 	struct tc_mqprio_qopt *mqprio = NULL;
-	u32 taprio_flags = 0;
 	unsigned long flags;
 	ktime_t start;
 	int i, err;
@@ -1388,21 +1415,14 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 	if (tb[TCA_TAPRIO_ATTR_PRIOMAP])
 		mqprio = nla_data(tb[TCA_TAPRIO_ATTR_PRIOMAP]);
 
-	if (tb[TCA_TAPRIO_ATTR_FLAGS]) {
-		taprio_flags = nla_get_u32(tb[TCA_TAPRIO_ATTR_FLAGS]);
-
-		if (q->flags != 0 && q->flags != taprio_flags) {
-			NL_SET_ERR_MSG_MOD(extack, "Changing 'flags' of a running schedule is not supported");
-			return -EOPNOTSUPP;
-		} else if (!taprio_flags_valid(taprio_flags)) {
-			NL_SET_ERR_MSG_MOD(extack, "Specified 'flags' are not valid");
-			return -EINVAL;
-		}
+	err = taprio_new_flags(tb[TCA_TAPRIO_ATTR_FLAGS],
+			       q->flags, extack);
+	if (err < 0)
+		return err;
 
-		q->flags = taprio_flags;
-	}
+	q->flags = err;
 
-	err = taprio_parse_mqprio_opt(dev, mqprio, extack, taprio_flags);
+	err = taprio_parse_mqprio_opt(dev, mqprio, extack, q->flags);
 	if (err < 0)
 		return err;
 
@@ -1457,7 +1477,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 					       mqprio->prio_tc_map[i]);
 	}
 
-	if (FULL_OFFLOAD_IS_ENABLED(taprio_flags))
+	if (FULL_OFFLOAD_IS_ENABLED(q->flags))
 		err = taprio_enable_offload(dev, mqprio, q, new_admin, extack);
 	else
 		err = taprio_disable_offload(dev, q, extack);
@@ -1477,14 +1497,14 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 		q->txtime_delay = nla_get_u32(tb[TCA_TAPRIO_ATTR_TXTIME_DELAY]);
 	}
 
-	if (!TXTIME_ASSIST_IS_ENABLED(taprio_flags) &&
-	    !FULL_OFFLOAD_IS_ENABLED(taprio_flags) &&
+	if (!TXTIME_ASSIST_IS_ENABLED(q->flags) &&
+	    !FULL_OFFLOAD_IS_ENABLED(q->flags) &&
 	    !hrtimer_active(&q->advance_timer)) {
 		hrtimer_init(&q->advance_timer, q->clockid, HRTIMER_MODE_ABS);
 		q->advance_timer.function = advance_sched;
 	}
 
-	if (FULL_OFFLOAD_IS_ENABLED(taprio_flags)) {
+	if (FULL_OFFLOAD_IS_ENABLED(q->flags)) {
 		q->dequeue = taprio_dequeue_offload;
 		q->peek = taprio_peek_offload;
 	} else {
@@ -1501,7 +1521,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 		goto unlock;
 	}
 
-	if (TXTIME_ASSIST_IS_ENABLED(taprio_flags)) {
+	if (TXTIME_ASSIST_IS_ENABLED(q->flags)) {
 		setup_txtime(q, new_admin, start);
 
 		if (!oper) {
@@ -1528,7 +1548,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 
 		spin_unlock_irqrestore(&q->current_entry_lock, flags);
 
-		if (FULL_OFFLOAD_IS_ENABLED(taprio_flags))
+		if (FULL_OFFLOAD_IS_ENABLED(q->flags))
 			taprio_offload_config_changed(q);
 	}
 
@@ -1597,6 +1617,7 @@ static int taprio_init(struct Qdisc *sch, struct nlattr *opt,
 	 * and get the valid one on taprio_change().
 	 */
 	q->clockid = -1;
+	q->flags = TAPRIO_FLAGS_INVALID;
 
 	spin_lock(&taprio_list_lock);
 	list_add(&q->taprio_list, &taprio_list);
-- 
2.21.1


From 2756eaadec34f7e6e625fe8d16750921f59cf2e3 Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Thu, 6 Feb 2020 13:46:08 -0800
Subject: [PATCH 17/24] taprio: Add missing policy validation for flags

[ Upstream commit 49c684d79cfdc3032344bf6f3deeea81c4efedbf ]

netlink policy validation for the 'flags' argument was missing.

Fixes: 4cfd5779bd6e ("taprio: Add support for txtime-assist mode")
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_taprio.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index e2d4283bea6d..b82a9769ab40 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -767,6 +767,7 @@ static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = {
 	[TCA_TAPRIO_ATTR_SCHED_CLOCKID]              = { .type = NLA_S32 },
 	[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME]           = { .type = NLA_S64 },
 	[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION] = { .type = NLA_S64 },
+	[TCA_TAPRIO_ATTR_FLAGS]                      = { .type = NLA_U32 },
 };
 
 static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry,
-- 
2.21.1


From d369f325a0760c53fd92666c3f45c3196a0c1b34 Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Thu, 6 Feb 2020 13:46:09 -0800
Subject: [PATCH 18/24] taprio: Use taprio_reset_tc() to reset Traffic Classes
 configuration

[ Upstream commit 7c16680a08ee1e444a67d232c679ccf5b30fad16 ]

When destroying the current taprio instance, which can happen when the
creation of one fails, we should reset the traffic class configuration
back to the default state.

netdev_reset_tc() is a better way because in addition to setting the
number of traffic classes to zero, it also resets the priority to
traffic classes mapping to the default value.

Fixes: 5a781ccbd19e ("tc: Add support for configuring the taprio scheduler")
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_taprio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index b82a9769ab40..21df69071df2 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -1588,7 +1588,7 @@ static void taprio_destroy(struct Qdisc *sch)
 	}
 	q->qdiscs = NULL;
 
-	netdev_set_num_tc(dev, 0);
+	netdev_reset_tc(dev);
 
 	if (q->oper_sched)
 		call_rcu(&q->oper_sched->rcu, taprio_free_sched_cb);
-- 
2.21.1


From 0241b0f0c681039dcaec71476d05e8d3fbf2e24a Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Thu, 6 Feb 2020 13:46:10 -0800
Subject: [PATCH 19/24] taprio: Fix dropping packets when using taprio + ETF
 offloading

[ Upstream commit bfabd41da34180d05382312533a3adc2e012dee0 ]

When using taprio offloading together with ETF offloading, configured
like this, for example:

$ tc qdisc replace dev $IFACE parent root handle 100 taprio \
  	num_tc 4 \
        map 2 2 1 0 3 2 2 2 2 2 2 2 2 2 2 2 \
	queues 1@0 1@1 1@2 1@3 \
	base-time $BASE_TIME \
	sched-entry S 01 1000000 \
	sched-entry S 0e 1000000 \
	flags 0x2

$ tc qdisc replace dev $IFACE parent 100:1 etf \
     	offload delta 300000 clockid CLOCK_TAI

During enqueue, it works out that the verification added for the
"txtime" assisted mode is run when using taprio + ETF offloading, the
only thing missing is initializing the 'next_txtime' of all the cycle
entries. (if we don't set 'next_txtime' all packets from SO_TXTIME
sockets are dropped)

Fixes: 4cfd5779bd6e ("taprio: Add support for txtime-assist mode")
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_taprio.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 21df69071df2..660fc45ee40f 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -1522,9 +1522,9 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 		goto unlock;
 	}
 
-	if (TXTIME_ASSIST_IS_ENABLED(q->flags)) {
-		setup_txtime(q, new_admin, start);
+	setup_txtime(q, new_admin, start);
 
+	if (TXTIME_ASSIST_IS_ENABLED(q->flags)) {
 		if (!oper) {
 			rcu_assign_pointer(q->oper_sched, new_admin);
 			err = 0;
-- 
2.21.1


From 99b1915ac88871770cbad621ab2d323501a0338f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 7 Feb 2020 07:16:37 -0800
Subject: [PATCH 20/24] ipv6/addrconf: fix potential NULL deref in
 inet6_set_link_af()

[ Upstream commit db3fa271022dacb9f741b96ea4714461a8911bb9 ]

__in6_dev_get(dev) called from inet6_set_link_af() can return NULL.

The needed check has been recently removed, let's add it back.

While do_setlink() does call validate_linkmsg() :
...
err = validate_linkmsg(dev, tb); /* OK at this point */
...

It is possible that the following call happening before the
->set_link_af() removes IPv6 if MTU is less than 1280 :

if (tb[IFLA_MTU]) {
    err = dev_set_mtu_ext(dev, nla_get_u32(tb[IFLA_MTU]), extack);
    if (err < 0)
          goto errout;
    status |= DO_SETLINK_MODIFIED;
}
...

if (tb[IFLA_AF_SPEC]) {
   ...
   err = af_ops->set_link_af(dev, af);
      ->inet6_set_link_af() // CRASH because idev is NULL

Please note that IPv4 is immune to the bug since inet_set_link_af() does :

struct in_device *in_dev = __in_dev_get_rcu(dev);
if (!in_dev)
    return -EAFNOSUPPORT;

This problem has been mentioned in commit cf7afbfeb8ce ("rtnl: make
link af-specific updates atomic") changelog :

    This method is not fail proof, while it is currently sufficient
    to make set_link_af() inerrable and thus 100% atomic, the
    validation function method will not be able to detect all error
    scenarios in the future, there will likely always be errors
    depending on states which are f.e. not protected by rtnl_mutex
    and thus may change between validation and setting.

IPv6: ADDRCONF(NETDEV_CHANGE): lo: link becomes ready
general protection fault, probably for non-canonical address 0xdffffc0000000056: 0000 [#1] PREEMPT SMP KASAN
KASAN: null-ptr-deref in range [0x00000000000002b0-0x00000000000002b7]
CPU: 0 PID: 9698 Comm: syz-executor712 Not tainted 5.5.0-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:inet6_set_link_af+0x66e/0xae0 net/ipv6/addrconf.c:5733
Code: 38 d0 7f 08 84 c0 0f 85 20 03 00 00 48 8d bb b0 02 00 00 45 0f b6 64 24 04 48 b8 00 00 00 00 00 fc ff df 48 89 fa 48 c1 ea 03 <0f> b6 04 02 84 c0 74 08 3c 03 0f 8e 1a 03 00 00 44 89 a3 b0 02 00
RSP: 0018:ffffc90005b06d40 EFLAGS: 00010206
RAX: dffffc0000000000 RBX: 0000000000000000 RCX: ffffffff86df39a6
RDX: 0000000000000056 RSI: ffffffff86df3e74 RDI: 00000000000002b0
RBP: ffffc90005b06e70 R08: ffff8880a2ac0380 R09: ffffc90005b06db0
R10: fffff52000b60dbe R11: ffffc90005b06df7 R12: 0000000000000000
R13: 0000000000000000 R14: ffff8880a1fcc424 R15: dffffc0000000000
FS:  0000000000c46880(0000) GS:ffff8880ae800000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000055f0494ca0d0 CR3: 000000009e4ac000 CR4: 00000000001406f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 do_setlink+0x2a9f/0x3720 net/core/rtnetlink.c:2754
 rtnl_group_changelink net/core/rtnetlink.c:3103 [inline]
 __rtnl_newlink+0xdd1/0x1790 net/core/rtnetlink.c:3257
 rtnl_newlink+0x69/0xa0 net/core/rtnetlink.c:3377
 rtnetlink_rcv_msg+0x45e/0xaf0 net/core/rtnetlink.c:5438
 netlink_rcv_skb+0x177/0x450 net/netlink/af_netlink.c:2477
 rtnetlink_rcv+0x1d/0x30 net/core/rtnetlink.c:5456
 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
 netlink_unicast+0x59e/0x7e0 net/netlink/af_netlink.c:1328
 netlink_sendmsg+0x91c/0xea0 net/netlink/af_netlink.c:1917
 sock_sendmsg_nosec net/socket.c:652 [inline]
 sock_sendmsg+0xd7/0x130 net/socket.c:672
 ____sys_sendmsg+0x753/0x880 net/socket.c:2343
 ___sys_sendmsg+0x100/0x170 net/socket.c:2397
 __sys_sendmsg+0x105/0x1d0 net/socket.c:2430
 __do_sys_sendmsg net/socket.c:2439 [inline]
 __se_sys_sendmsg net/socket.c:2437 [inline]
 __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2437
 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x4402e9
Code: 18 89 d0 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 fb 13 fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007fffd62fbcf8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 00000000004402e9
RDX: 0000000000000000 RSI: 0000000020000080 RDI: 0000000000000003
RBP: 00000000006ca018 R08: 0000000000000008 R09: 00000000004002c8
R10: 0000000000000005 R11: 0000000000000246 R12: 0000000000401b70
R13: 0000000000401c00 R14: 0000000000000000 R15: 0000000000000000
Modules linked in:
---[ end trace cfa7664b8fdcdff3 ]---
RIP: 0010:inet6_set_link_af+0x66e/0xae0 net/ipv6/addrconf.c:5733
Code: 38 d0 7f 08 84 c0 0f 85 20 03 00 00 48 8d bb b0 02 00 00 45 0f b6 64 24 04 48 b8 00 00 00 00 00 fc ff df 48 89 fa 48 c1 ea 03 <0f> b6 04 02 84 c0 74 08 3c 03 0f 8e 1a 03 00 00 44 89 a3 b0 02 00
RSP: 0018:ffffc90005b06d40 EFLAGS: 00010206
RAX: dffffc0000000000 RBX: 0000000000000000 RCX: ffffffff86df39a6
RDX: 0000000000000056 RSI: ffffffff86df3e74 RDI: 00000000000002b0
RBP: ffffc90005b06e70 R08: ffff8880a2ac0380 R09: ffffc90005b06db0
R10: fffff52000b60dbe R11: ffffc90005b06df7 R12: 0000000000000000
R13: 0000000000000000 R14: ffff8880a1fcc424 R15: dffffc0000000000
FS:  0000000000c46880(0000) GS:ffff8880ae900000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000020000004 CR3: 000000009e4ac000 CR4: 00000000001406e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400

Fixes: 7dc2bccab0ee ("Validate required parameters in inet6_validate_link_af")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Bisected-and-reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index f9b5690e94fd..b11ccb53c7e0 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5719,6 +5719,9 @@ static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla)
 	struct nlattr *tb[IFLA_INET6_MAX + 1];
 	int err;
 
+	if (!idev)
+		return -EAFNOSUPPORT;
+
 	if (nla_parse_nested_deprecated(tb, IFLA_INET6_MAX, nla, NULL, NULL) < 0)
 		BUG();
 
-- 
2.21.1


From 809d63d6323a07df388d469bb4744c665a6d335e Mon Sep 17 00:00:00 2001
From: Sudarsana Reddy Kalluru <skalluru@marvell.com>
Date: Wed, 5 Feb 2020 05:10:55 -0800
Subject: [PATCH 21/24] qed: Fix timestamping issue for L2 unicast ptp packets.

[ Upstream commit 0202d293c2faecba791ba4afc5aec086249c393d ]

commit cedeac9df4b8 ("qed: Add support for Timestamping the unicast
PTP packets.") handles the timestamping of L4 ptp packets only.
This patch adds driver changes to detect/timestamp both L2/L4 unicast
PTP packets.

Fixes: cedeac9df4b8 ("qed: Add support for Timestamping the unicast PTP packets.")
Signed-off-by: Sudarsana Reddy Kalluru <skalluru@marvell.com>
Signed-off-by: Ariel Elior <aelior@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_ptp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_ptp.c b/drivers/net/ethernet/qlogic/qed/qed_ptp.c
index 0dacf2c18c09..3e613058e225 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ptp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ptp.c
@@ -44,8 +44,8 @@
 /* Add/subtract the Adjustment_Value when making a Drift adjustment */
 #define QED_DRIFT_CNTR_DIRECTION_SHIFT		31
 #define QED_TIMESTAMP_MASK			BIT(16)
-/* Param mask for Hardware to detect/timestamp the unicast PTP packets */
-#define QED_PTP_UCAST_PARAM_MASK		0xF
+/* Param mask for Hardware to detect/timestamp the L2/L4 unicast PTP packets */
+#define QED_PTP_UCAST_PARAM_MASK              0x70F
 
 static enum qed_resc_lock qed_ptcdev_to_resc(struct qed_hwfn *p_hwfn)
 {
-- 
2.21.1


From a4642ff21b821c93b6c9ab65109d8c2cf6c8c160 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Fri, 7 Feb 2020 19:29:28 +0200
Subject: [PATCH 22/24] drop_monitor: Do not cancel uninitialized work item

[ Upstream commit dfa7f709596be5ca46c070d4f8acbb344322056a ]

Drop monitor uses a work item that takes care of constructing and
sending netlink notifications to user space. In case drop monitor never
started to monitor, then the work item is uninitialized and not
associated with a function.

Therefore, a stop command from user space results in canceling an
uninitialized work item which leads to the following warning [1].

Fix this by not processing a stop command if drop monitor is not
currently monitoring.

[1]
[   31.735402] ------------[ cut here ]------------
[   31.736470] WARNING: CPU: 0 PID: 143 at kernel/workqueue.c:3032 __flush_work+0x89f/0x9f0
...
[   31.738120] CPU: 0 PID: 143 Comm: dwdump Not tainted 5.5.0-custom-09491-g16d4077796b8 #727
[   31.741968] RIP: 0010:__flush_work+0x89f/0x9f0
...
[   31.760526] Call Trace:
[   31.771689]  __cancel_work_timer+0x2a6/0x3b0
[   31.776809]  net_dm_cmd_trace+0x300/0xef0
[   31.777549]  genl_rcv_msg+0x5c6/0xd50
[   31.781005]  netlink_rcv_skb+0x13b/0x3a0
[   31.784114]  genl_rcv+0x29/0x40
[   31.784720]  netlink_unicast+0x49f/0x6a0
[   31.787148]  netlink_sendmsg+0x7cf/0xc80
[   31.790426]  ____sys_sendmsg+0x620/0x770
[   31.793458]  ___sys_sendmsg+0xfd/0x170
[   31.802216]  __sys_sendmsg+0xdf/0x1a0
[   31.806195]  do_syscall_64+0xa0/0x540
[   31.806885]  entry_SYSCALL_64_after_hwframe+0x49/0xbe

Fixes: 8e94c3bc922e ("drop_monitor: Allow user to start monitoring hardware drops")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/drop_monitor.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 536e032d95c8..246a258b1fac 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -1004,8 +1004,10 @@ static void net_dm_hw_monitor_stop(struct netlink_ext_ack *extack)
 {
 	int cpu;
 
-	if (!monitor_hw)
+	if (!monitor_hw) {
 		NL_SET_ERR_MSG_MOD(extack, "Hardware monitoring already disabled");
+		return;
+	}
 
 	monitor_hw = false;
 
-- 
2.21.1


From 7ad40b444d35878c6f1e0653b7ca0ce12c360c3e Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@mellanox.com>
Date: Mon, 27 Jan 2020 09:27:51 +0200
Subject: [PATCH 23/24] net/mlx5: Fix deadlock in fs_core

[ Upstream commit c1948390d78b5183ee9b7dd831efd7f6ac496ab0 ]

free_match_list could be called when the flow table is already
locked. We need to pass this notation to tree_put_node.

It fixes the following lockdep warnning:

[ 1797.268537] ============================================
[ 1797.276837] WARNING: possible recursive locking detected
[ 1797.285101] 5.5.0-rc5+ #10 Not tainted
[ 1797.291641] --------------------------------------------
[ 1797.299917] handler10/9296 is trying to acquire lock:
[ 1797.307885] ffff889ad399a0a0 (&node->lock){++++}, at:
tree_put_node+0x1d5/0x210 [mlx5_core]
[ 1797.319694]
[ 1797.319694] but task is already holding lock:
[ 1797.330904] ffff889ad399a0a0 (&node->lock){++++}, at:
nested_down_write_ref_node.part.33+0x1a/0x60 [mlx5_core]
[ 1797.344707]
[ 1797.344707] other info that might help us debug this:
[ 1797.356952]  Possible unsafe locking scenario:
[ 1797.356952]
[ 1797.368333]        CPU0
[ 1797.373357]        ----
[ 1797.378364]   lock(&node->lock);
[ 1797.384222]   lock(&node->lock);
[ 1797.390031]
[ 1797.390031]  *** DEADLOCK ***
[ 1797.390031]
[ 1797.403003]  May be due to missing lock nesting notation
[ 1797.403003]
[ 1797.414691] 3 locks held by handler10/9296:
[ 1797.421465]  #0: ffff889cf2c5a110 (&block->cb_lock){++++}, at:
tc_setup_cb_add+0x70/0x250
[ 1797.432810]  #1: ffff88a030081490 (&comp->sem){++++}, at:
mlx5_devcom_get_peer_data+0x4c/0xb0 [mlx5_core]
[ 1797.445829]  #2: ffff889ad399a0a0 (&node->lock){++++}, at:
nested_down_write_ref_node.part.33+0x1a/0x60 [mlx5_core]
[ 1797.459913]
[ 1797.459913] stack backtrace:
[ 1797.469436] CPU: 1 PID: 9296 Comm: handler10 Kdump: loaded Not
tainted 5.5.0-rc5+ #10
[ 1797.480643] Hardware name: Dell Inc. PowerEdge R730/072T6D, BIOS
2.4.3 01/17/2017
[ 1797.491480] Call Trace:
[ 1797.496701]  dump_stack+0x96/0xe0
[ 1797.502864]  __lock_acquire.cold.63+0xf8/0x212
[ 1797.510301]  ? lockdep_hardirqs_on+0x250/0x250
[ 1797.517701]  ? mark_held_locks+0x55/0xa0
[ 1797.524547]  ? quarantine_put+0xb7/0x160
[ 1797.531422]  ? lockdep_hardirqs_on+0x17d/0x250
[ 1797.538913]  lock_acquire+0xd6/0x1f0
[ 1797.545529]  ? tree_put_node+0x1d5/0x210 [mlx5_core]
[ 1797.553701]  down_write+0x94/0x140
[ 1797.560206]  ? tree_put_node+0x1d5/0x210 [mlx5_core]
[ 1797.568464]  ? down_write_killable_nested+0x170/0x170
[ 1797.576925]  ? del_hw_flow_group+0xde/0x1f0 [mlx5_core]
[ 1797.585629]  tree_put_node+0x1d5/0x210 [mlx5_core]
[ 1797.593891]  ? free_match_list.part.25+0x147/0x170 [mlx5_core]
[ 1797.603389]  free_match_list.part.25+0xe0/0x170 [mlx5_core]
[ 1797.612654]  _mlx5_add_flow_rules+0x17e2/0x20b0 [mlx5_core]
[ 1797.621838]  ? lock_acquire+0xd6/0x1f0
[ 1797.629028]  ? esw_get_prio_table+0xb0/0x3e0 [mlx5_core]
[ 1797.637981]  ? alloc_insert_flow_group+0x420/0x420 [mlx5_core]
[ 1797.647459]  ? try_to_wake_up+0x4c7/0xc70
[ 1797.654881]  ? lock_downgrade+0x350/0x350
[ 1797.662271]  ? __mutex_unlock_slowpath+0xb1/0x3f0
[ 1797.670396]  ? find_held_lock+0xac/0xd0
[ 1797.677540]  ? mlx5_add_flow_rules+0xdc/0x360 [mlx5_core]
[ 1797.686467]  mlx5_add_flow_rules+0xdc/0x360 [mlx5_core]
[ 1797.695134]  ? _mlx5_add_flow_rules+0x20b0/0x20b0 [mlx5_core]
[ 1797.704270]  ? irq_exit+0xa5/0x170
[ 1797.710764]  ? retint_kernel+0x10/0x10
[ 1797.717698]  ? mlx5_eswitch_set_rule_source_port.isra.9+0x122/0x230
[mlx5_core]
[ 1797.728708]  mlx5_eswitch_add_offloaded_rule+0x465/0x6d0 [mlx5_core]
[ 1797.738713]  ? mlx5_eswitch_get_prio_range+0x30/0x30 [mlx5_core]
[ 1797.748384]  ? mlx5_fc_stats_work+0x670/0x670 [mlx5_core]
[ 1797.757400]  mlx5e_tc_offload_fdb_rules.isra.27+0x24/0x90 [mlx5_core]
[ 1797.767665]  mlx5e_tc_add_fdb_flow+0xaf8/0xd40 [mlx5_core]
[ 1797.776886]  ? mlx5e_encap_put+0xd0/0xd0 [mlx5_core]
[ 1797.785562]  ? mlx5e_alloc_flow.isra.43+0x18c/0x1c0 [mlx5_core]
[ 1797.795353]  __mlx5e_add_fdb_flow+0x2e2/0x440 [mlx5_core]
[ 1797.804558]  ? mlx5e_tc_update_neigh_used_value+0x8c0/0x8c0
[mlx5_core]
[ 1797.815093]  ? wait_for_completion+0x260/0x260
[ 1797.823272]  mlx5e_configure_flower+0xe94/0x1620 [mlx5_core]
[ 1797.832792]  ? __mlx5e_add_fdb_flow+0x440/0x440 [mlx5_core]
[ 1797.842096]  ? down_read+0x11a/0x2e0
[ 1797.849090]  ? down_write+0x140/0x140
[ 1797.856142]  ? mlx5e_rep_indr_setup_block_cb+0xc0/0xc0 [mlx5_core]
[ 1797.866027]  tc_setup_cb_add+0x11a/0x250
[ 1797.873339]  fl_hw_replace_filter+0x25e/0x320 [cls_flower]
[ 1797.882385]  ? fl_hw_destroy_filter+0x1c0/0x1c0 [cls_flower]
[ 1797.891607]  fl_change+0x1d54/0x1fb6 [cls_flower]
[ 1797.899772]  ? __rhashtable_insert_fast.constprop.50+0x9f0/0x9f0
[cls_flower]
[ 1797.910728]  ? lock_downgrade+0x350/0x350
[ 1797.918187]  ? __radix_tree_lookup+0xa5/0x130
[ 1797.926046]  ? fl_set_key+0x1590/0x1590 [cls_flower]
[ 1797.934611]  ? __rhashtable_insert_fast.constprop.50+0x9f0/0x9f0
[cls_flower]
[ 1797.945673]  tc_new_tfilter+0xcd1/0x1240
[ 1797.953138]  ? tc_del_tfilter+0xb10/0xb10
[ 1797.960688]  ? avc_has_perm_noaudit+0x92/0x320
[ 1797.968721]  ? avc_has_perm_noaudit+0x1df/0x320
[ 1797.976816]  ? avc_has_extended_perms+0x990/0x990
[ 1797.985090]  ? mark_lock+0xaa/0x9e0
[ 1797.991988]  ? match_held_lock+0x1b/0x240
[ 1797.999457]  ? match_held_lock+0x1b/0x240
[ 1798.006859]  ? find_held_lock+0xac/0xd0
[ 1798.014045]  ? symbol_put_addr+0x40/0x40
[ 1798.021317]  ? rcu_read_lock_sched_held+0xd0/0xd0
[ 1798.029460]  ? tc_del_tfilter+0xb10/0xb10
[ 1798.036810]  rtnetlink_rcv_msg+0x4d5/0x620
[ 1798.044236]  ? rtnl_bridge_getlink+0x460/0x460
[ 1798.052034]  ? lockdep_hardirqs_on+0x250/0x250
[ 1798.059837]  ? match_held_lock+0x1b/0x240
[ 1798.067146]  ? find_held_lock+0xac/0xd0
[ 1798.074246]  netlink_rcv_skb+0xc6/0x1f0
[ 1798.081339]  ? rtnl_bridge_getlink+0x460/0x460
[ 1798.089104]  ? netlink_ack+0x440/0x440
[ 1798.096061]  netlink_unicast+0x2d4/0x3b0
[ 1798.103189]  ? netlink_attachskb+0x3f0/0x3f0
[ 1798.110724]  ? _copy_from_iter_full+0xda/0x370
[ 1798.118415]  netlink_sendmsg+0x3ba/0x6a0
[ 1798.125478]  ? netlink_unicast+0x3b0/0x3b0
[ 1798.132705]  ? netlink_unicast+0x3b0/0x3b0
[ 1798.139880]  sock_sendmsg+0x94/0xa0
[ 1798.146332]  ____sys_sendmsg+0x36c/0x3f0
[ 1798.153251]  ? copy_msghdr_from_user+0x165/0x230
[ 1798.160941]  ? kernel_sendmsg+0x30/0x30
[ 1798.167738]  ___sys_sendmsg+0xeb/0x150
[ 1798.174411]  ? sendmsg_copy_msghdr+0x30/0x30
[ 1798.181649]  ? lock_downgrade+0x350/0x350
[ 1798.188559]  ? rcu_read_lock_sched_held+0xd0/0xd0
[ 1798.196239]  ? __fget+0x21d/0x320
[ 1798.202335]  ? do_dup2+0x2a0/0x2a0
[ 1798.208499]  ? lock_downgrade+0x350/0x350
[ 1798.215366]  ? __fget_light+0xd6/0xf0
[ 1798.221808]  ? syscall_trace_enter+0x369/0x5d0
[ 1798.229112]  __sys_sendmsg+0xd3/0x160
[ 1798.235511]  ? __sys_sendmsg_sock+0x60/0x60
[ 1798.242478]  ? syscall_trace_enter+0x233/0x5d0
[ 1798.249721]  ? syscall_slow_exit_work+0x280/0x280
[ 1798.257211]  ? do_syscall_64+0x1e/0x2e0
[ 1798.263680]  do_syscall_64+0x72/0x2e0
[ 1798.269950]  entry_SYSCALL_64_after_hwframe+0x49/0xbe

Fixes: bd71b08ec2ee ("net/mlx5: Support multiple updates of steering rules in parallel")
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Alaa Hleihel <alaa@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 791e14ac26f4..86e6bbb57482 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -1555,16 +1555,16 @@ struct match_list_head {
 	struct match_list first;
 };
 
-static void free_match_list(struct match_list_head *head)
+static void free_match_list(struct match_list_head *head, bool ft_locked)
 {
 	if (!list_empty(&head->list)) {
 		struct match_list *iter, *match_tmp;
 
 		list_del(&head->first.list);
-		tree_put_node(&head->first.g->node, false);
+		tree_put_node(&head->first.g->node, ft_locked);
 		list_for_each_entry_safe(iter, match_tmp, &head->list,
 					 list) {
-			tree_put_node(&iter->g->node, false);
+			tree_put_node(&iter->g->node, ft_locked);
 			list_del(&iter->list);
 			kfree(iter);
 		}
@@ -1573,7 +1573,8 @@ static void free_match_list(struct match_list_head *head)
 
 static int build_match_list(struct match_list_head *match_head,
 			    struct mlx5_flow_table *ft,
-			    const struct mlx5_flow_spec *spec)
+			    const struct mlx5_flow_spec *spec,
+			    bool ft_locked)
 {
 	struct rhlist_head *tmp, *list;
 	struct mlx5_flow_group *g;
@@ -1598,7 +1599,7 @@ static int build_match_list(struct match_list_head *match_head,
 
 		curr_match = kmalloc(sizeof(*curr_match), GFP_ATOMIC);
 		if (!curr_match) {
-			free_match_list(match_head);
+			free_match_list(match_head, ft_locked);
 			err = -ENOMEM;
 			goto out;
 		}
@@ -1778,7 +1779,7 @@ _mlx5_add_flow_rules(struct mlx5_flow_table *ft,
 	version = atomic_read(&ft->node.version);
 
 	/* Collect all fgs which has a matching match_criteria */
-	err = build_match_list(&match_head, ft, spec);
+	err = build_match_list(&match_head, ft, spec, take_write);
 	if (err) {
 		if (take_write)
 			up_write_ref_node(&ft->node, false);
@@ -1792,7 +1793,7 @@ _mlx5_add_flow_rules(struct mlx5_flow_table *ft,
 
 	rule = try_add_to_existing_fg(ft, &match_head.list, spec, flow_act, dest,
 				      dest_num, version);
-	free_match_list(&match_head);
+	free_match_list(&match_head, take_write);
 	if (!IS_ERR(rule) ||
 	    (PTR_ERR(rule) != -ENOENT && PTR_ERR(rule) != -EAGAIN)) {
 		if (take_write)
-- 
2.21.1


From 64cf0bdcc3d164fdeeef00eef550e593b121a73e Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Mon, 27 Jan 2020 14:18:14 +0200
Subject: [PATCH 24/24] net/mlx5: Deprecate usage of generic TLS HW capability
 bit

[ Upstream commit 61c00cca41aeeaa8e5263c2f81f28534bc1efafb ]

Deprecate the generic TLS cap bit, use the new TX-specific
TLS cap bit instead.

Fixes: a12ff35e0fb7 ("net/mlx5: Introduce TLS TX offload hardware bits and structures")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h        | 2 +-
 .../net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c    | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/fw.c               | 2 +-
 include/linux/mlx5/mlx5_ifc.h                              | 7 ++++---
 4 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h
index d787bc0a4155..e09bc3858d57 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h
@@ -45,7 +45,7 @@ void mlx5_ktls_destroy_key(struct mlx5_core_dev *mdev, u32 key_id);
 
 static inline bool mlx5_accel_is_ktls_device(struct mlx5_core_dev *mdev)
 {
-	if (!MLX5_CAP_GEN(mdev, tls))
+	if (!MLX5_CAP_GEN(mdev, tls_tx))
 		return false;
 
 	if (!MLX5_CAP_GEN(mdev, log_max_dek))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
index 71384ad1a443..ef1ed15a53b4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
@@ -269,7 +269,7 @@ struct sk_buff *mlx5e_tls_handle_tx_skb(struct net_device *netdev,
 	int datalen;
 	u32 skb_seq;
 
-	if (MLX5_CAP_GEN(sq->channel->mdev, tls)) {
+	if (MLX5_CAP_GEN(sq->channel->mdev, tls_tx)) {
 		skb = mlx5e_ktls_handle_tx_skb(netdev, sq, skb, wqe, pi);
 		goto out;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index a19790dee7b2..13e86f0b42f5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -239,7 +239,7 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev)
 			return err;
 	}
 
-	if (MLX5_CAP_GEN(dev, tls)) {
+	if (MLX5_CAP_GEN(dev, tls_tx)) {
 		err = mlx5_core_get_caps(dev, MLX5_CAP_TLS);
 		if (err)
 			return err;
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 0836fe232f97..0cdc8d12785a 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1417,14 +1417,15 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 	u8         reserved_at_440[0x20];
 
-	u8         tls[0x1];
-	u8         reserved_at_461[0x2];
+	u8         reserved_at_460[0x3];
 	u8         log_max_uctx[0x5];
 	u8         reserved_at_468[0x3];
 	u8         log_max_umem[0x5];
 	u8         max_num_eqs[0x10];
 
-	u8         reserved_at_480[0x3];
+	u8         reserved_at_480[0x1];
+	u8         tls_tx[0x1];
+	u8         reserved_at_482[0x1];
 	u8         log_max_l2_table[0x5];
 	u8         reserved_at_488[0x8];
 	u8         log_uar_page_sz[0x10];
-- 
2.21.1


[-- Attachment #3: net_55.mbox --]
[-- Type: Application/Octet-Stream, Size: 86931 bytes --]

From 5968633032fa56015647ac450763717b1fc63731 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 4 Feb 2020 19:26:05 -0800
Subject: [PATCH 01/31] bonding/alb: properly access headers in bond_alb_xmit()

[ Upstream commit 38f88c45404293bbc027b956def6c10cbd45c616 ]

syzbot managed to send an IPX packet through bond_alb_xmit()
and af_packet and triggered a use-after-free.

First, bond_alb_xmit() was using ipx_hdr() helper to reach
the IPX header, but ipx_hdr() was using the transport offset
instead of the network offset. In the particular syzbot
report transport offset was 0xFFFF

This patch removes ipx_hdr() since it was only (mis)used from bonding.

Then we need to make sure IPv4/IPv6/IPX headers are pulled
in skb->head before dereferencing anything.

BUG: KASAN: use-after-free in bond_alb_xmit+0x153a/0x1590 drivers/net/bonding/bond_alb.c:1452
Read of size 2 at addr ffff8801ce56dfff by task syz-executor.2/18108
 (if (ipx_hdr(skb)->ipx_checksum != IPX_NO_CHECKSUM) ...)

Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 [<ffffffff8441fc42>] __dump_stack lib/dump_stack.c:17 [inline]
 [<ffffffff8441fc42>] dump_stack+0x14d/0x20b lib/dump_stack.c:53
 [<ffffffff81a7dec4>] print_address_description+0x6f/0x20b mm/kasan/report.c:282
 [<ffffffff81a7e0ec>] kasan_report_error mm/kasan/report.c:380 [inline]
 [<ffffffff81a7e0ec>] kasan_report mm/kasan/report.c:438 [inline]
 [<ffffffff81a7e0ec>] kasan_report.cold+0x8c/0x2a0 mm/kasan/report.c:422
 [<ffffffff81a7dc4f>] __asan_report_load_n_noabort+0xf/0x20 mm/kasan/report.c:469
 [<ffffffff82c8c00a>] bond_alb_xmit+0x153a/0x1590 drivers/net/bonding/bond_alb.c:1452
 [<ffffffff82c60c74>] __bond_start_xmit drivers/net/bonding/bond_main.c:4199 [inline]
 [<ffffffff82c60c74>] bond_start_xmit+0x4f4/0x1570 drivers/net/bonding/bond_main.c:4224
 [<ffffffff83baa558>] __netdev_start_xmit include/linux/netdevice.h:4525 [inline]
 [<ffffffff83baa558>] netdev_start_xmit include/linux/netdevice.h:4539 [inline]
 [<ffffffff83baa558>] xmit_one net/core/dev.c:3611 [inline]
 [<ffffffff83baa558>] dev_hard_start_xmit+0x168/0x910 net/core/dev.c:3627
 [<ffffffff83bacf35>] __dev_queue_xmit+0x1f55/0x33b0 net/core/dev.c:4238
 [<ffffffff83bae3a8>] dev_queue_xmit+0x18/0x20 net/core/dev.c:4278
 [<ffffffff84339189>] packet_snd net/packet/af_packet.c:3226 [inline]
 [<ffffffff84339189>] packet_sendmsg+0x4919/0x70b0 net/packet/af_packet.c:3252
 [<ffffffff83b1ac0c>] sock_sendmsg_nosec net/socket.c:673 [inline]
 [<ffffffff83b1ac0c>] sock_sendmsg+0x12c/0x160 net/socket.c:684
 [<ffffffff83b1f5a2>] __sys_sendto+0x262/0x380 net/socket.c:1996
 [<ffffffff83b1f700>] SYSC_sendto net/socket.c:2008 [inline]
 [<ffffffff83b1f700>] SyS_sendto+0x40/0x60 net/socket.c:2004

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Cc: Veaceslav Falico <vfalico@gmail.com>
Cc: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_alb.c | 44 ++++++++++++++++++++++++----------
 include/net/ipx.h              |  5 ----
 2 files changed, 32 insertions(+), 17 deletions(-)

diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 4f2e6910c623..1cc2cd894f87 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -1383,26 +1383,31 @@ netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 	bool do_tx_balance = true;
 	u32 hash_index = 0;
 	const u8 *hash_start = NULL;
-	struct ipv6hdr *ip6hdr;
 
 	skb_reset_mac_header(skb);
 	eth_data = eth_hdr(skb);
 
 	switch (ntohs(skb->protocol)) {
 	case ETH_P_IP: {
-		const struct iphdr *iph = ip_hdr(skb);
+		const struct iphdr *iph;
 
 		if (is_broadcast_ether_addr(eth_data->h_dest) ||
-		    iph->daddr == ip_bcast ||
-		    iph->protocol == IPPROTO_IGMP) {
+		    !pskb_network_may_pull(skb, sizeof(*iph))) {
+			do_tx_balance = false;
+			break;
+		}
+		iph = ip_hdr(skb);
+		if (iph->daddr == ip_bcast || iph->protocol == IPPROTO_IGMP) {
 			do_tx_balance = false;
 			break;
 		}
 		hash_start = (char *)&(iph->daddr);
 		hash_size = sizeof(iph->daddr);
-	}
 		break;
-	case ETH_P_IPV6:
+	}
+	case ETH_P_IPV6: {
+		const struct ipv6hdr *ip6hdr;
+
 		/* IPv6 doesn't really use broadcast mac address, but leave
 		 * that here just in case.
 		 */
@@ -1419,7 +1424,11 @@ netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 			break;
 		}
 
-		/* Additianally, DAD probes should not be tx-balanced as that
+		if (!pskb_network_may_pull(skb, sizeof(*ip6hdr))) {
+			do_tx_balance = false;
+			break;
+		}
+		/* Additionally, DAD probes should not be tx-balanced as that
 		 * will lead to false positives for duplicate addresses and
 		 * prevent address configuration from working.
 		 */
@@ -1429,17 +1438,26 @@ netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 			break;
 		}
 
-		hash_start = (char *)&(ipv6_hdr(skb)->daddr);
-		hash_size = sizeof(ipv6_hdr(skb)->daddr);
+		hash_start = (char *)&ip6hdr->daddr;
+		hash_size = sizeof(ip6hdr->daddr);
 		break;
-	case ETH_P_IPX:
-		if (ipx_hdr(skb)->ipx_checksum != IPX_NO_CHECKSUM) {
+	}
+	case ETH_P_IPX: {
+		const struct ipxhdr *ipxhdr;
+
+		if (pskb_network_may_pull(skb, sizeof(*ipxhdr))) {
+			do_tx_balance = false;
+			break;
+		}
+		ipxhdr = (struct ipxhdr *)skb_network_header(skb);
+
+		if (ipxhdr->ipx_checksum != IPX_NO_CHECKSUM) {
 			/* something is wrong with this packet */
 			do_tx_balance = false;
 			break;
 		}
 
-		if (ipx_hdr(skb)->ipx_type != IPX_TYPE_NCP) {
+		if (ipxhdr->ipx_type != IPX_TYPE_NCP) {
 			/* The only protocol worth balancing in
 			 * this family since it has an "ARP" like
 			 * mechanism
@@ -1448,9 +1466,11 @@ netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 			break;
 		}
 
+		eth_data = eth_hdr(skb);
 		hash_start = (char *)eth_data->h_dest;
 		hash_size = ETH_ALEN;
 		break;
+	}
 	case ETH_P_ARP:
 		do_tx_balance = false;
 		if (bond_info->rlb_enabled)
diff --git a/include/net/ipx.h b/include/net/ipx.h
index baf090390998..9d1342807b59 100644
--- a/include/net/ipx.h
+++ b/include/net/ipx.h
@@ -47,11 +47,6 @@ struct ipxhdr {
 /* From af_ipx.c */
 extern int sysctl_ipx_pprop_broadcasting;
 
-static __inline__ struct ipxhdr *ipx_hdr(struct sk_buff *skb)
-{
-	return (struct ipxhdr *)skb_transport_header(skb);
-}
-
 struct ipx_interface {
 	/* IPX address */
 	__be32			if_netnum;
-- 
2.21.1


From ac2b4c7ca5334326d0f69c9fcb13d1f91540dbff Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Tue, 4 Feb 2020 15:59:50 -0800
Subject: [PATCH 02/31] devlink: report 0 after hitting end in region read

[ Upstream commit d5b90e99e1d51b7b5d2b74fbc4c2db236a510913 ]

commit fdd41ec21e15 ("devlink: Return right error code in case of errors
for region read") modified the region read code to report errors
properly in unexpected cases.

In the case where the start_offset and ret_offset match, it unilaterally
converted this into an error. This causes an issue for the "dump"
version of the command. In this case, the devlink region dump will
always report an invalid argument:

000000000000ffd0 ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
000000000000ffe0 ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
devlink answers: Invalid argument
000000000000fff0 ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff

This occurs because the expected flow for the dump is to return 0 after
there is no further data.

The simplest fix would be to stop converting the error code to -EINVAL
if start_offset == ret_offset. However, avoid unnecessary work by
checking for when start_offset is larger than the region size and
returning 0 upfront.

Fixes: fdd41ec21e15 ("devlink: Return right error code in case of errors for region read")
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/devlink.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/core/devlink.c b/net/core/devlink.c
index f76219bf0c21..42370702d0e0 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -3986,6 +3986,12 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
 		goto out_unlock;
 	}
 
+	/* return 0 if there is no further data to read */
+	if (start_offset >= region->size) {
+		err = 0;
+		goto out_unlock;
+	}
+
 	hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
 			  &devlink_nl_family, NLM_F_ACK | NLM_F_MULTI,
 			  DEVLINK_CMD_REGION_READ);
-- 
2.21.1


From 3121b50d0ea02a12ed9b01c95781fed0dc03fa50 Mon Sep 17 00:00:00 2001
From: Madalin Bucur <madalin.bucur@oss.nxp.com>
Date: Tue, 4 Feb 2020 12:08:58 +0200
Subject: [PATCH 03/31] dpaa_eth: support all modes with rate adapting PHYs

[ Upstream commit 73a21fa817f0cc8022dc6226250a86bca727a56d ]

Stop removing modes that are not supported on the system interface
when the connected PHY is capable of rate adaptation. This addresses
an issue with the LS1046ARDB board 10G interface no longer working
with an 1G link partner after autonegotiation support was added
for the Aquantia PHY on board in

commit 09c4c57f7bc4 ("net: phy: aquantia: add support for auto-negotiation configuration")

Before this commit the values advertised by the PHY were not
influenced by the dpaa_eth driver removal of system-side unsupported
modes as the aqr_config_aneg() was basically a no-op. After this
commit, the modes removed by the dpaa_eth driver were no longer
advertised thus autonegotiation with 1G link partners failed.

Reported-by: Mian Yousaf Kaukab <ykaukab@suse.de>
Signed-off-by: Madalin Bucur <madalin.bucur@oss.nxp.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index a301f0095223..f827daf09b72 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -2453,6 +2453,9 @@ static void dpaa_adjust_link(struct net_device *net_dev)
 	mac_dev->adjust_link(mac_dev);
 }
 
+/* The Aquantia PHYs are capable of performing rate adaptation */
+#define PHY_VEND_AQUANTIA	0x03a1b400
+
 static int dpaa_phy_init(struct net_device *net_dev)
 {
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
@@ -2471,9 +2474,14 @@ static int dpaa_phy_init(struct net_device *net_dev)
 		return -ENODEV;
 	}
 
-	/* Remove any features not supported by the controller */
-	ethtool_convert_legacy_u32_to_link_mode(mask, mac_dev->if_support);
-	linkmode_and(phy_dev->supported, phy_dev->supported, mask);
+	/* Unless the PHY is capable of rate adaptation */
+	if (mac_dev->phy_if != PHY_INTERFACE_MODE_XGMII ||
+	    ((phy_dev->drv->phy_id & GENMASK(31, 10)) != PHY_VEND_AQUANTIA)) {
+		/* remove any features not supported by the controller */
+		ethtool_convert_legacy_u32_to_link_mode(mask,
+							mac_dev->if_support);
+		linkmode_and(phy_dev->supported, phy_dev->supported, mask);
+	}
 
 	phy_support_asym_pause(phy_dev);
 
-- 
2.21.1


From 7803322b9c177a9e40045a785cda6fd9c5ce547b Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 6 Feb 2020 11:07:45 -0800
Subject: [PATCH 04/31] net: dsa: b53: Always use dev->vlan_enabled in
 b53_configure_vlan()

[ Upstream commit df373702bc0f8f2d83980ea441e71639fc1efcf8 ]

b53_configure_vlan() is called by the bcm_sf2 driver upon setup and
indirectly through resume as well. During the initial setup, we are
guaranteed that dev->vlan_enabled is false, so there is no change in
behavior, however during suspend, we may have enabled VLANs before, so we
do want to restore that setting.

Fixes: dad8d7c6452b ("net: dsa: b53: Properly account for VLAN filtering")
Fixes: 967dd82ffc52 ("net: dsa: b53: Add support for Broadcom RoboSwitch")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/b53/b53_common.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index edacacfc9365..6a1ff4d43e3a 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -680,7 +680,7 @@ int b53_configure_vlan(struct dsa_switch *ds)
 		b53_do_vlan_op(dev, VTA_CMD_CLEAR);
 	}
 
-	b53_enable_vlan(dev, false, ds->vlan_filtering);
+	b53_enable_vlan(dev, dev->vlan_enabled, ds->vlan_filtering);
 
 	b53_for_each_port(dev, i)
 		b53_write16(dev, B53_VLAN_PAGE,
-- 
2.21.1


From 0e818ac51a9ee785046f0c6538bea9aa8206be96 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 6 Feb 2020 11:23:52 -0800
Subject: [PATCH 05/31] net: dsa: bcm_sf2: Only 7278 supports 2Gb/sec IMP port

[ Upstream commit de34d7084edd069dac5aa010cfe32bd8c4619fa6 ]

The 7445 switch clocking profiles do not allow us to run the IMP port at
2Gb/sec in a way that it is reliable and consistent. Make sure that the
setting is only applied to the 7278 family.

Fixes: 8f1880cbe8d0 ("net: dsa: bcm_sf2: Configure IMP port for 2Gb/sec")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 3e8635311d0d..d1955543acd1 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -68,7 +68,9 @@ static void bcm_sf2_imp_setup(struct dsa_switch *ds, int port)
 
 		/* Force link status for IMP port */
 		reg = core_readl(priv, offset);
-		reg |= (MII_SW_OR | LINK_STS | GMII_SPEED_UP_2G);
+		reg |= (MII_SW_OR | LINK_STS);
+		if (priv->type == BCM7278_DEVICE_ID)
+			reg |= GMII_SPEED_UP_2G;
 		core_writel(priv, reg, offset);
 
 		/* Enable Broadcast, Multicast, Unicast forwarding to IMP port */
-- 
2.21.1


From a2edd0c9bb99e6c5082e0127cc51d71e3fa8cb4f Mon Sep 17 00:00:00 2001
From: Razvan Stefanescu <razvan.stefanescu@microchip.com>
Date: Fri, 7 Feb 2020 17:44:04 +0200
Subject: [PATCH 06/31] net: dsa: microchip: enable module autoprobe

[ Upstream commit f8c2afa66d5397b0b9293c4347dac6dabb327685 ]

This matches /sys/devices/.../spi1.0/modalias content.

Fixes: 9b2d9f05cddf ("net: dsa: microchip: add ksz9567 to ksz9477 driver")
Fixes: d9033ae95cf4 ("net: dsa: microchip: add KSZ8563 compatibility string")
Fixes: 8c29bebb1f8a ("net: dsa: microchip: add KSZ9893 switch support")
Fixes: 45316818371d ("net: dsa: add support for ksz9897 ethernet switch")
Fixes: b987e98e50ab ("dsa: add DSA switch driver for Microchip KSZ9477")
Signed-off-by: Razvan Stefanescu <razvan.stefanescu@microchip.com>
Signed-off-by: Codrin Ciubotariu <codrin.ciubotariu@microchip.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/microchip/ksz9477_spi.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/dsa/microchip/ksz9477_spi.c b/drivers/net/dsa/microchip/ksz9477_spi.c
index c5f64959a184..1142768969c2 100644
--- a/drivers/net/dsa/microchip/ksz9477_spi.c
+++ b/drivers/net/dsa/microchip/ksz9477_spi.c
@@ -101,6 +101,12 @@ static struct spi_driver ksz9477_spi_driver = {
 
 module_spi_driver(ksz9477_spi_driver);
 
+MODULE_ALIAS("spi:ksz9477");
+MODULE_ALIAS("spi:ksz9897");
+MODULE_ALIAS("spi:ksz9893");
+MODULE_ALIAS("spi:ksz9563");
+MODULE_ALIAS("spi:ksz8563");
+MODULE_ALIAS("spi:ksz9567");
 MODULE_AUTHOR("Woojung Huh <Woojung.Huh@microchip.com>");
 MODULE_DESCRIPTION("Microchip KSZ9477 Series Switch SPI access Driver");
 MODULE_LICENSE("GPL");
-- 
2.21.1


From 1ca2e99d9c7cc809420f9f4bdb78e2c7ca954488 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 6 Feb 2020 10:14:39 +0100
Subject: [PATCH 07/31] net: mvneta: move rx_dropped and rx_errors in per-cpu
 stats

[ Upstream commit c35947b8ff8acca33134ee39c31708233765c31a ]

Move rx_dropped and rx_errors counters in mvneta_pcpu_stats in order to
avoid possible races updating statistics

Fixes: 562e2f467e71 ("net: mvneta: Improve the buffer allocation method for SWBM")
Fixes: dc35a10f68d3 ("net: mvneta: bm: add support for hardware buffer management")
Fixes: c5aff18204da ("net: mvneta: driver for Marvell Armada 370/XP network unit")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 31 +++++++++++++++++++--------
 1 file changed, 22 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 8bad5b864682..d031f800bba5 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -402,6 +402,8 @@ struct mvneta_pcpu_stats {
 	struct	u64_stats_sync syncp;
 	u64	rx_packets;
 	u64	rx_bytes;
+	u64	rx_dropped;
+	u64	rx_errors;
 	u64	tx_packets;
 	u64	tx_bytes;
 };
@@ -739,6 +741,8 @@ mvneta_get_stats64(struct net_device *dev,
 		struct mvneta_pcpu_stats *cpu_stats;
 		u64 rx_packets;
 		u64 rx_bytes;
+		u64 rx_dropped;
+		u64 rx_errors;
 		u64 tx_packets;
 		u64 tx_bytes;
 
@@ -747,19 +751,20 @@ mvneta_get_stats64(struct net_device *dev,
 			start = u64_stats_fetch_begin_irq(&cpu_stats->syncp);
 			rx_packets = cpu_stats->rx_packets;
 			rx_bytes   = cpu_stats->rx_bytes;
+			rx_dropped = cpu_stats->rx_dropped;
+			rx_errors  = cpu_stats->rx_errors;
 			tx_packets = cpu_stats->tx_packets;
 			tx_bytes   = cpu_stats->tx_bytes;
 		} while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start));
 
 		stats->rx_packets += rx_packets;
 		stats->rx_bytes   += rx_bytes;
+		stats->rx_dropped += rx_dropped;
+		stats->rx_errors  += rx_errors;
 		stats->tx_packets += tx_packets;
 		stats->tx_bytes   += tx_bytes;
 	}
 
-	stats->rx_errors	= dev->stats.rx_errors;
-	stats->rx_dropped	= dev->stats.rx_dropped;
-
 	stats->tx_dropped	= dev->stats.tx_dropped;
 }
 
@@ -1736,8 +1741,14 @@ static u32 mvneta_txq_desc_csum(int l3_offs, int l3_proto,
 static void mvneta_rx_error(struct mvneta_port *pp,
 			    struct mvneta_rx_desc *rx_desc)
 {
+	struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats);
 	u32 status = rx_desc->status;
 
+	/* update per-cpu counter */
+	u64_stats_update_begin(&stats->syncp);
+	stats->rx_errors++;
+	u64_stats_update_end(&stats->syncp);
+
 	switch (status & MVNETA_RXD_ERR_CODE_MASK) {
 	case MVNETA_RXD_ERR_CRC:
 		netdev_err(pp->dev, "bad rx status %08x (crc error), size=%d\n",
@@ -2179,11 +2190,15 @@ mvneta_swbm_rx_frame(struct mvneta_port *pp,
 
 	rxq->skb = build_skb(xdp->data_hard_start, PAGE_SIZE);
 	if (unlikely(!rxq->skb)) {
-		netdev_err(dev,
-			   "Can't allocate skb on queue %d\n",
-			   rxq->id);
-		dev->stats.rx_dropped++;
+		struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats);
+
+		netdev_err(dev, "Can't allocate skb on queue %d\n", rxq->id);
 		rxq->skb_alloc_err++;
+
+		u64_stats_update_begin(&stats->syncp);
+		stats->rx_dropped++;
+		u64_stats_update_end(&stats->syncp);
+
 		return -ENOMEM;
 	}
 	page_pool_release_page(rxq->page_pool, page);
@@ -2270,7 +2285,6 @@ static int mvneta_rx_swbm(struct napi_struct *napi,
 			/* Check errors only for FIRST descriptor */
 			if (rx_status & MVNETA_RXD_ERR_SUMMARY) {
 				mvneta_rx_error(pp, rx_desc);
-				dev->stats.rx_errors++;
 				/* leave the descriptor untouched */
 				continue;
 			}
@@ -2372,7 +2386,6 @@ static int mvneta_rx_hwbm(struct napi_struct *napi,
 			mvneta_bm_pool_put_bp(pp->bm_priv, bm_pool,
 					      rx_desc->buf_phys_addr);
 err_drop_frame:
-			dev->stats.rx_errors++;
 			mvneta_rx_error(pp, rx_desc);
 			/* leave the descriptor untouched */
 			continue;
-- 
2.21.1


From 7eff7969805cad3aa62bca55d975e66f6ef5e3e9 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Tue, 4 Feb 2020 11:10:12 -0800
Subject: [PATCH 08/31] net_sched: fix a resource leak in tcindex_set_parms()

[ Upstream commit 52b5ae501c045010aeeb1d5ac0373ff161a88291 ]

Jakub noticed there is a potential resource leak in
tcindex_set_parms(): when tcindex_filter_result_init() fails
and it jumps to 'errout1' which doesn't release the memory
and resources allocated by tcindex_alloc_perfect_hash().

We should just jump to 'errout_alloc' which calls
tcindex_free_perfect_hash().

Fixes: b9a24bb76bf6 ("net_sched: properly handle failure case of tcf_exts_init()")
Reported-by: Jakub Kicinski <kuba@kernel.org>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_tcindex.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 3d4a1280352f..e53834c35447 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -346,7 +346,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 
 	err = tcindex_filter_result_init(&new_filter_result, net);
 	if (err < 0)
-		goto errout1;
+		goto errout_alloc;
 	if (old_r)
 		cr = r->res;
 
@@ -484,7 +484,6 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 		tcindex_free_perfect_hash(cp);
 	else if (balloc == 2)
 		kfree(cp->h);
-errout1:
 	tcf_exts_destroy(&new_filter_result.exts);
 errout:
 	kfree(cp);
-- 
2.21.1


From 6efacdba91027b38f28e9e081c3243b59e0edeed Mon Sep 17 00:00:00 2001
From: Dejin Zheng <zhengdejin5@gmail.com>
Date: Thu, 6 Feb 2020 23:29:17 +0800
Subject: [PATCH 09/31] net: stmmac: fix a possible endless loop

[ Upstream commit 7d10f0774f9e32aa2f2e012f7fcb312a2ce422b9 ]

It forgot to reduce the value of the variable retry in a while loop
in the ethqos_configure() function. It may cause an endless loop and
without timeout.

Fixes: a7c30e62d4b8 ("net: stmmac: Add driver for Qualcomm ethqos")
Signed-off-by: Dejin Zheng <zhengdejin5@gmail.com>
Acked-by: Vinod Koul <vkoul@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
index 7ec895407d23..e0a5fe83d8e0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
@@ -413,6 +413,7 @@ static int ethqos_configure(struct qcom_ethqos *ethqos)
 			dll_lock = rgmii_readl(ethqos, SDC4_STATUS);
 			if (dll_lock & SDC4_STATUS_DLL_LOCK)
 				break;
+			retry--;
 		} while (retry > 0);
 		if (!retry)
 			dev_err(&ethqos->pdev->dev,
-- 
2.21.1


From db655b2888dd1ffa2b8fed7614068c457b6f1a98 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 5 Feb 2020 12:32:04 -0800
Subject: [PATCH 10/31] net: systemport: Avoid RBUF stuck in Wake-on-LAN mode

[ Upstream commit 263a425a482fc495d6d3f9a29b9103a664c38b69 ]

After a number of suspend and resume cycles, it is possible for the RBUF
to be stuck in Wake-on-LAN mode, despite the MPD enable bit being
cleared which instructed the RBUF to exit that mode.

Avoid creating that problematic condition by clearing the RX_EN and
TX_EN bits in the UniMAC prior to disable the Magic Packet Detector
logic which is guaranteed to make the RBUF exit Wake-on-LAN mode.

Fixes: 83e82f4c706b ("net: systemport: add Wake-on-LAN support")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bcmsysport.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index d6b1a153f9df..c1ae42244f02 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -2728,6 +2728,9 @@ static int __maybe_unused bcm_sysport_resume(struct device *d)
 
 	umac_reset(priv);
 
+	/* Disable the UniMAC RX/TX */
+	umac_enable_set(priv, CMD_RX_EN | CMD_TX_EN, 0);
+
 	/* We may have been suspended and never received a WOL event that
 	 * would turn off MPD detection, take care of that now
 	 */
-- 
2.21.1


From 9485ef84a90e168ca6f32a8f676a62305370802d Mon Sep 17 00:00:00 2001
From: Raed Salem <raeds@mellanox.com>
Date: Tue, 24 Dec 2019 09:54:45 +0200
Subject: [PATCH 11/31] net/mlx5: IPsec, Fix esp modify function attribute

[ Upstream commit 0dc2c534f17c05bed0622b37a744bc38b48ca88a ]

The function mlx5_fpga_esp_validate_xfrm_attrs is wrongly used
with negative negation as zero value indicates success but it
used as failure return value instead.

Fix by remove the unary not negation operator.

Fixes: 05564d0ae075 ("net/mlx5: Add flow-steering commands for FPGA IPSec implementation")
Signed-off-by: Raed Salem <raeds@mellanox.com>
Reviewed-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
index e4ec0e03c289..4ed4d4d8e073 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
@@ -1478,7 +1478,7 @@ int mlx5_fpga_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm,
 	if (!memcmp(&xfrm->attrs, attrs, sizeof(xfrm->attrs)))
 		return 0;
 
-	if (!mlx5_fpga_esp_validate_xfrm_attrs(mdev, attrs)) {
+	if (mlx5_fpga_esp_validate_xfrm_attrs(mdev, attrs)) {
 		mlx5_core_warn(mdev, "Tried to create an esp with unsupported attrs\n");
 		return -EOPNOTSUPP;
 	}
-- 
2.21.1


From 19e048364529b5428d0442e3e5c8580eaed7e7c2 Mon Sep 17 00:00:00 2001
From: Raed Salem <raeds@mellanox.com>
Date: Wed, 23 Oct 2019 16:41:21 +0300
Subject: [PATCH 12/31] net/mlx5: IPsec, fix memory leak at
 mlx5_fpga_ipsec_delete_sa_ctx

[ Upstream commit 08db2cf577487f5123aebcc2f913e0b8a2c14b43 ]

SA context is allocated at mlx5_fpga_ipsec_create_sa_ctx,
however the counterpart mlx5_fpga_ipsec_delete_sa_ctx function
nullifies sa_ctx pointer without freeing the memory allocated,
hence the memory leak.

Fix by free SA context when the SA is released.

Fixes: d6c4f0298cec ("net/mlx5: Refactor accel IPSec code")
Signed-off-by: Raed Salem <raeds@mellanox.com>
Reviewed-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
index 4ed4d4d8e073..4c61d25d2e88 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
@@ -850,6 +850,7 @@ void mlx5_fpga_ipsec_delete_sa_ctx(void *context)
 	mutex_lock(&fpga_xfrm->lock);
 	if (!--fpga_xfrm->num_rules) {
 		mlx5_fpga_ipsec_release_sa_ctx(fpga_xfrm->sa_ctx);
+		kfree(fpga_xfrm->sa_ctx);
 		fpga_xfrm->sa_ctx = NULL;
 	}
 	mutex_unlock(&fpga_xfrm->lock);
-- 
2.21.1


From 7cb6c7e7e7dc2661e7e46260d9038f7e7b03be55 Mon Sep 17 00:00:00 2001
From: Harini Katakam <harini.katakam@xilinx.com>
Date: Wed, 5 Feb 2020 18:08:11 +0530
Subject: [PATCH 13/31] net: macb: Remove unnecessary alignment check for TSO

[ Upstream commit 41c1ef978c8d0259c6636e6d2d854777e92650eb ]

The IP TSO implementation does NOT require the length to be a
multiple of 8. That is only a requirement for UFO as per IP
documentation. Hence, exit macb_features_check function in the
beginning if the protocol is not UDP. Only when it is UDP,
proceed further to the alignment checks. Update comments to
reflect the same. Also remove dead code checking for protocol
TCP when calculating header length.

Fixes: 1629dd4f763c ("cadence: Add LSO support.")
Signed-off-by: Harini Katakam <harini.katakam@xilinx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index f7d87c71aaa9..f14196ceb8ba 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -1752,16 +1752,14 @@ static netdev_features_t macb_features_check(struct sk_buff *skb,
 
 	/* Validate LSO compatibility */
 
-	/* there is only one buffer */
-	if (!skb_is_nonlinear(skb))
+	/* there is only one buffer or protocol is not UDP */
+	if (!skb_is_nonlinear(skb) || (ip_hdr(skb)->protocol != IPPROTO_UDP))
 		return features;
 
 	/* length of header */
 	hdrlen = skb_transport_offset(skb);
-	if (ip_hdr(skb)->protocol == IPPROTO_TCP)
-		hdrlen += tcp_hdrlen(skb);
 
-	/* For LSO:
+	/* For UFO only:
 	 * When software supplies two or more payload buffers all payload buffers
 	 * apart from the last must be a multiple of 8 bytes in size.
 	 */
-- 
2.21.1


From b21f0b0a761f5e879333c50dbc7ed9dea40a8b87 Mon Sep 17 00:00:00 2001
From: Harini Katakam <harini.katakam@xilinx.com>
Date: Wed, 5 Feb 2020 18:08:12 +0530
Subject: [PATCH 14/31] net: macb: Limit maximum GEM TX length in TSO

[ Upstream commit f822e9c4ffa511a5c681cf866287d9383a3b6f1b ]

GEM_MAX_TX_LEN currently resolves to 0x3FF8 for any IP version supporting
TSO with full 14bits of length field in payload descriptor. But an IP
errata causes false amba_error (bit 6 of ISR) when length in payload
descriptors is specified above 16387. The error occurs because the DMA
falsely concludes that there is not enough space in SRAM for incoming
payload. These errors were observed continuously under stress of large
packets using iperf on a version where SRAM was 16K for each queue. This
errata will be documented shortly and affects all versions since TSO
functionality was added. Hence limit the max length to 0x3FC0 (rounded).

Signed-off-by: Harini Katakam <harini.katakam@xilinx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index f14196ceb8ba..71bb0d56533a 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -73,7 +73,11 @@ struct sifive_fu540_macb_mgmt {
 /* Max length of transmit frame must be a multiple of 8 bytes */
 #define MACB_TX_LEN_ALIGN	8
 #define MACB_MAX_TX_LEN		((unsigned int)((1 << MACB_TX_FRMLEN_SIZE) - 1) & ~((unsigned int)(MACB_TX_LEN_ALIGN - 1)))
-#define GEM_MAX_TX_LEN		((unsigned int)((1 << GEM_TX_FRMLEN_SIZE) - 1) & ~((unsigned int)(MACB_TX_LEN_ALIGN - 1)))
+/* Limit maximum TX length as per Cadence TSO errata. This is to avoid a
+ * false amba_error in TX path from the DMA assuming there is not enough
+ * space in the SRAM (16KB) even when there is.
+ */
+#define GEM_MAX_TX_LEN		(unsigned int)(0x3FC0)
 
 #define GEM_MTU_MIN_SIZE	ETH_MIN_MTU
 #define MACB_NETIF_LSO		NETIF_F_TSO
-- 
2.21.1


From b88ea6483706c664be49698282d45783664f9fcd Mon Sep 17 00:00:00 2001
From: "Tan, Tee Min" <tee.min.tan@intel.com>
Date: Fri, 7 Feb 2020 15:33:20 +0800
Subject: [PATCH 15/31] net: stmmac: fix incorrect GMAC_VLAN_TAG register
 writting in GMAC4+

[ Upstream commit 9eeeb3c9de4e3aeaa2bec097162f09305dd9f4c3 ]

It should always do a read of current value of GMAC_VLAN_TAG instead of
directly overwriting the register value.

Fixes: c1be0022df0d ("net: stmmac: Add VLAN HASH filtering support in GMAC4+")
Signed-off-by: Tan, Tee Min <tee.min.tan@intel.com>
Signed-off-by: Ong Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index 40ca00e596dd..6e3d0ab0ecd6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -736,11 +736,14 @@ static void dwmac4_update_vlan_hash(struct mac_device_info *hw, u32 hash,
 				    __le16 perfect_match, bool is_double)
 {
 	void __iomem *ioaddr = hw->pcsr;
+	u32 value;
 
 	writel(hash, ioaddr + GMAC_VLAN_HASH_TABLE);
 
+	value = readl(ioaddr + GMAC_VLAN_TAG);
+
 	if (hash) {
-		u32 value = GMAC_VLAN_VTHM | GMAC_VLAN_ETV;
+		value |= GMAC_VLAN_VTHM | GMAC_VLAN_ETV;
 		if (is_double) {
 			value |= GMAC_VLAN_EDVLP;
 			value |= GMAC_VLAN_ESVL;
@@ -759,8 +762,6 @@ static void dwmac4_update_vlan_hash(struct mac_device_info *hw, u32 hash,
 
 		writel(value | perfect_match, ioaddr + GMAC_VLAN_TAG);
 	} else {
-		u32 value = readl(ioaddr + GMAC_VLAN_TAG);
-
 		value &= ~(GMAC_VLAN_VTHM | GMAC_VLAN_ETV);
 		value &= ~(GMAC_VLAN_EDVLP | GMAC_VLAN_ESVL);
 		value &= ~GMAC_VLAN_DOVLTC;
-- 
2.21.1


From c615ede85dcc594176a36008c10641a7f99b58ab Mon Sep 17 00:00:00 2001
From: Ong Boon Leong <boon.leong.ong@intel.com>
Date: Fri, 7 Feb 2020 15:33:40 +0800
Subject: [PATCH 16/31] net: stmmac: xgmac: fix incorrect XGMAC_VLAN_TAG
 register writting

[ Upstream commit 907a076881f171254219faad05f46ac5baabedfb ]

We should always do a read of current value of XGMAC_VLAN_TAG instead of
directly overwriting the register value.

Fixes: 3cd1cfcba26e2 ("net: stmmac: Implement VLAN Hash Filtering in XGMAC")
Signed-off-by: Ong Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index 082f5ee9e525..9fb85faa8ed2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -569,7 +569,9 @@ static void dwxgmac2_update_vlan_hash(struct mac_device_info *hw, u32 hash,
 
 		writel(value, ioaddr + XGMAC_PACKET_FILTER);
 
-		value = XGMAC_VLAN_VTHM | XGMAC_VLAN_ETV;
+		value = readl(ioaddr + XGMAC_VLAN_TAG);
+
+		value |= XGMAC_VLAN_VTHM | XGMAC_VLAN_ETV;
 		if (is_double) {
 			value |= XGMAC_VLAN_EDVLP;
 			value |= XGMAC_VLAN_ESVL;
@@ -584,7 +586,9 @@ static void dwxgmac2_update_vlan_hash(struct mac_device_info *hw, u32 hash,
 
 		writel(value, ioaddr + XGMAC_PACKET_FILTER);
 
-		value = XGMAC_VLAN_ETV;
+		value = readl(ioaddr + XGMAC_VLAN_TAG);
+
+		value |= XGMAC_VLAN_ETV;
 		if (is_double) {
 			value |= XGMAC_VLAN_EDVLP;
 			value |= XGMAC_VLAN_ESVL;
-- 
2.21.1


From 350492d74c8e628f2674a62dadff34bf06f87b8d Mon Sep 17 00:00:00 2001
From: "Verma, Aashish" <aashishx.verma@intel.com>
Date: Fri, 7 Feb 2020 15:33:54 +0800
Subject: [PATCH 17/31] net: stmmac: fix missing IFF_MULTICAST check in
 dwmac4_set_filter

[ Upstream commit 2ba31cd93784b61813226d259fd94a221ecd9d61 ]

Without checking for IFF_MULTICAST flag, it is wrong to assume multicast
filtering is always enabled. By checking against IFF_MULTICAST, now
the driver behaves correctly when the multicast support is toggled by below
command:-
  ip link set <devname> multicast off|on

Fixes: 477286b53f55 ("stmmac: add GMAC4 core support")
Signed-off-by: Verma, Aashish <aashishx.verma@intel.com>
Tested-by: Tan, Tee Min <tee.min.tan@intel.com>
Signed-off-by: Ong Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index 6e3d0ab0ecd6..53be936137d0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -420,7 +420,7 @@ static void dwmac4_set_filter(struct mac_device_info *hw,
 		value |= GMAC_PACKET_FILTER_PM;
 		/* Set all the bits of the HASH tab */
 		memset(mc_filter, 0xff, sizeof(mc_filter));
-	} else if (!netdev_mc_empty(dev)) {
+	} else if (!netdev_mc_empty(dev) && (dev->flags & IFF_MULTICAST)) {
 		struct netdev_hw_addr *ha;
 
 		/* Hash filter for multicast */
-- 
2.21.1


From ac80529a3d86cdea546307e7883c5f7c6cceb18a Mon Sep 17 00:00:00 2001
From: "Tan, Tee Min" <tee.min.tan@intel.com>
Date: Fri, 7 Feb 2020 15:34:15 +0800
Subject: [PATCH 18/31] net: stmmac: xgmac: fix missing IFF_MULTICAST checki in
 dwxgmac2_set_filter

[ Upstream commit 2f633d5820e4ed870f408957322acb9263bce2f4 ]

Without checking for IFF_MULTICAST flag, it is wrong to assume multicast
filtering is always enabled. By checking against IFF_MULTICAST, now
the driver behaves correctly when the multicast support is toggled by below
command:-
  ip link set <devname> multicast off|on

Fixes: 0efedbf11f07a ("net: stmmac: xgmac: Fix XGMAC selftests")
Signed-off-by: Tan, Tee Min <tee.min.tan@intel.com>
Signed-off-by: Ong Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index 9fb85faa8ed2..e9bf54a579df 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -458,7 +458,7 @@ static void dwxgmac2_set_filter(struct mac_device_info *hw,
 
 		for (i = 0; i < XGMAC_MAX_HASH_TABLE; i++)
 			writel(~0x0, ioaddr + XGMAC_HASH_TABLE(i));
-	} else if (!netdev_mc_empty(dev)) {
+	} else if (!netdev_mc_empty(dev) && (dev->flags & IFF_MULTICAST)) {
 		struct netdev_hw_addr *ha;
 
 		value |= XGMAC_FILTER_HMC;
-- 
2.21.1


From df3345d8cd614d03ca7385b911220afdfa0f9130 Mon Sep 17 00:00:00 2001
From: Voon Weifeng <weifeng.voon@intel.com>
Date: Fri, 7 Feb 2020 15:34:28 +0800
Subject: [PATCH 19/31] net: stmmac: update pci platform data to use
 phy_interface

[ Upstream commit 909c1dde67c433f1e4122f2619cbd8ac370fcf0a ]

The recent patch to support passive mode converter did not take care the
phy interface configuration in PCI platform data. Hence, converting all
the PCI platform data from plat->interface to plat->phy_interface as the
default mode is meant for PHY.

Fixes: 0060c8783330 ("net: stmmac: implement support for passive mode converters via dt")
Signed-off-by: Voon Weifeng <weifeng.voon@intel.com>
Tested-by: Tan, Tee Min <tee.min.tan@intel.com>
Signed-off-by: Ong Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
index 8237dbc3e991..d2bc04dedd7c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
@@ -96,7 +96,7 @@ static int stmmac_default_data(struct pci_dev *pdev,
 
 	plat->bus_id = 1;
 	plat->phy_addr = 0;
-	plat->interface = PHY_INTERFACE_MODE_GMII;
+	plat->phy_interface = PHY_INTERFACE_MODE_GMII;
 
 	plat->dma_cfg->pbl = 32;
 	plat->dma_cfg->pblx8 = true;
@@ -220,7 +220,8 @@ static int ehl_sgmii_data(struct pci_dev *pdev,
 {
 	plat->bus_id = 1;
 	plat->phy_addr = 0;
-	plat->interface = PHY_INTERFACE_MODE_SGMII;
+	plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
+
 	return ehl_common_data(pdev, plat);
 }
 
@@ -233,7 +234,8 @@ static int ehl_rgmii_data(struct pci_dev *pdev,
 {
 	plat->bus_id = 1;
 	plat->phy_addr = 0;
-	plat->interface = PHY_INTERFACE_MODE_RGMII;
+	plat->phy_interface = PHY_INTERFACE_MODE_RGMII;
+
 	return ehl_common_data(pdev, plat);
 }
 
@@ -261,7 +263,7 @@ static int tgl_sgmii_data(struct pci_dev *pdev,
 {
 	plat->bus_id = 1;
 	plat->phy_addr = 0;
-	plat->interface = PHY_INTERFACE_MODE_SGMII;
+	plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
 	return tgl_common_data(pdev, plat);
 }
 
@@ -361,7 +363,7 @@ static int quark_default_data(struct pci_dev *pdev,
 
 	plat->bus_id = pci_dev_id(pdev);
 	plat->phy_addr = ret;
-	plat->interface = PHY_INTERFACE_MODE_RMII;
+	plat->phy_interface = PHY_INTERFACE_MODE_RMII;
 
 	plat->dma_cfg->pbl = 16;
 	plat->dma_cfg->pblx8 = true;
@@ -418,7 +420,7 @@ static int snps_gmac5_default_data(struct pci_dev *pdev,
 
 	plat->bus_id = 1;
 	plat->phy_addr = -1;
-	plat->interface = PHY_INTERFACE_MODE_GMII;
+	plat->phy_interface = PHY_INTERFACE_MODE_GMII;
 
 	plat->dma_cfg->pbl = 32;
 	plat->dma_cfg->pblx8 = true;
-- 
2.21.1


From 1fce048eb3e7453bc7ba57de3a99d7293da2b25e Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Thu, 6 Feb 2020 13:46:06 -0800
Subject: [PATCH 20/31] taprio: Fix enabling offload with wrong number of
 traffic classes

[ Upstream commit 5652e63df3303c2a702bac25fbf710b9cb64dfba ]

If the driver implementing taprio offloading depends on the value of
the network device number of traffic classes (dev->num_tc) for
whatever reason, it was going to receive the value zero. The value was
only set after the offloading function is called.

So, moving setting the number of traffic classes to before the
offloading function is called fixes this issue. This is safe because
this only happens when taprio is instantiated (we don't allow this
configuration to be changed without first removing taprio).

Fixes: 9c66d1564676 ("taprio: Add support for hardware offloading")
Reported-by: Po Liu <po.liu@nxp.com>
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Acked-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_taprio.c | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index c609373c8661..ad0dadcfcdba 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -1444,6 +1444,19 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 
 	taprio_set_picos_per_byte(dev, q);
 
+	if (mqprio) {
+		netdev_set_num_tc(dev, mqprio->num_tc);
+		for (i = 0; i < mqprio->num_tc; i++)
+			netdev_set_tc_queue(dev, i,
+					    mqprio->count[i],
+					    mqprio->offset[i]);
+
+		/* Always use supplied priority mappings */
+		for (i = 0; i <= TC_BITMASK; i++)
+			netdev_set_prio_tc_map(dev, i,
+					       mqprio->prio_tc_map[i]);
+	}
+
 	if (FULL_OFFLOAD_IS_ENABLED(taprio_flags))
 		err = taprio_enable_offload(dev, mqprio, q, new_admin, extack);
 	else
@@ -1471,19 +1484,6 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 		q->advance_timer.function = advance_sched;
 	}
 
-	if (mqprio) {
-		netdev_set_num_tc(dev, mqprio->num_tc);
-		for (i = 0; i < mqprio->num_tc; i++)
-			netdev_set_tc_queue(dev, i,
-					    mqprio->count[i],
-					    mqprio->offset[i]);
-
-		/* Always use supplied priority mappings */
-		for (i = 0; i <= TC_BITMASK; i++)
-			netdev_set_prio_tc_map(dev, i,
-					       mqprio->prio_tc_map[i]);
-	}
-
 	if (FULL_OFFLOAD_IS_ENABLED(taprio_flags)) {
 		q->dequeue = taprio_dequeue_offload;
 		q->peek = taprio_peek_offload;
-- 
2.21.1


From 0788bddd892d3e1581e041824060eb81663471df Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Thu, 6 Feb 2020 13:46:07 -0800
Subject: [PATCH 21/31] taprio: Fix still allowing changing the flags during
 runtime

[ Upstream commit a9d6227436f32142209f4428f2dc616761485112 ]

Because 'q->flags' starts as zero, and zero is a valid value, we
aren't able to detect the transition from zero to something else
during "runtime".

The solution is to initialize 'q->flags' with an invalid value, so we
can detect if 'q->flags' was set by the user or not.

To better solidify the behavior, 'flags' handling is moved to a
separate function. The behavior is:
 - 'flags' if unspecified by the user, is assumed to be zero;
 - 'flags' cannot change during "runtime" (i.e. a change() request
 cannot modify it);

With this new function we can remove taprio_flags, which should reduce
the risk of future accidents.

Allowing flags to be changed was causing the following RCU stall:

[ 1730.558249] rcu: INFO: rcu_preempt detected stalls on CPUs/tasks:
[ 1730.558258] rcu: 	  6-...0: (190 ticks this GP) idle=922/0/0x1 softirq=25580/25582 fqs=16250
[ 1730.558264] 		  (detected by 2, t=65002 jiffies, g=33017, q=81)
[ 1730.558269] Sending NMI from CPU 2 to CPUs 6:
[ 1730.559277] NMI backtrace for cpu 6
[ 1730.559277] CPU: 6 PID: 0 Comm: swapper/6 Tainted: G            E     5.5.0-rc6+ #35
[ 1730.559278] Hardware name: Gigabyte Technology Co., Ltd. Z390 AORUS ULTRA/Z390 AORUS ULTRA-CF, BIOS F7 03/14/2019
[ 1730.559278] RIP: 0010:__hrtimer_run_queues+0xe2/0x440
[ 1730.559278] Code: 48 8b 43 28 4c 89 ff 48 8b 75 c0 48 89 45 c8 e8 f4 bb 7c 00 0f 1f 44 00 00 65 8b 05 40 31 f0 68 89 c0 48 0f a3 05 3e 5c 25 01 <0f> 82 fc 01 00 00 48 8b 45 c8 48 89 df ff d0 89 45 c8 0f 1f 44 00
[ 1730.559279] RSP: 0018:ffff9970802d8f10 EFLAGS: 00000083
[ 1730.559279] RAX: 0000000000000006 RBX: ffff8b31645bff38 RCX: 0000000000000000
[ 1730.559280] RDX: 0000000000000000 RSI: ffffffff9710f2ec RDI: ffffffff978daf0e
[ 1730.559280] RBP: ffff9970802d8f68 R08: 0000000000000000 R09: 0000000000000000
[ 1730.559280] R10: 0000018336d7944e R11: 0000000000000001 R12: ffff8b316e39f9c0
[ 1730.559281] R13: ffff8b316e39f940 R14: ffff8b316e39f998 R15: ffff8b316e39f7c0
[ 1730.559281] FS:  0000000000000000(0000) GS:ffff8b316e380000(0000) knlGS:0000000000000000
[ 1730.559281] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 1730.559281] CR2: 00007f1105303760 CR3: 0000000227210005 CR4: 00000000003606e0
[ 1730.559282] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 1730.559282] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ 1730.559282] Call Trace:
[ 1730.559282]  <IRQ>
[ 1730.559283]  ? taprio_dequeue_soft+0x2d0/0x2d0 [sch_taprio]
[ 1730.559283]  hrtimer_interrupt+0x104/0x220
[ 1730.559283]  ? irqtime_account_irq+0x34/0xa0
[ 1730.559283]  smp_apic_timer_interrupt+0x6d/0x230
[ 1730.559284]  apic_timer_interrupt+0xf/0x20
[ 1730.559284]  </IRQ>
[ 1730.559284] RIP: 0010:cpu_idle_poll+0x35/0x1a0
[ 1730.559285] Code: 88 82 ff 65 44 8b 25 12 7d 73 68 0f 1f 44 00 00 e8 90 c3 89 ff fb 65 48 8b 1c 25 c0 7e 01 00 48 8b 03 a8 08 74 0b eb 1c f3 90 <48> 8b 03 a8 08 75 13 8b 05 be a8 a8 00 85 c0 75 ed e8 75 48 84 ff
[ 1730.559285] RSP: 0018:ffff997080137ea8 EFLAGS: 00000202 ORIG_RAX: ffffffffffffff13
[ 1730.559285] RAX: 0000000000000001 RBX: ffff8b316bc3c580 RCX: 0000000000000000
[ 1730.559286] RDX: 0000000000000001 RSI: 000000002819aad9 RDI: ffffffff978da730
[ 1730.559286] RBP: ffff997080137ec0 R08: 0000018324a6d387 R09: 0000000000000000
[ 1730.559286] R10: 0000000000000400 R11: 0000000000000001 R12: 0000000000000006
[ 1730.559286] R13: ffff8b316bc3c580 R14: 0000000000000000 R15: 0000000000000000
[ 1730.559287]  ? cpu_idle_poll+0x20/0x1a0
[ 1730.559287]  ? cpu_idle_poll+0x20/0x1a0
[ 1730.559287]  do_idle+0x4d/0x1f0
[ 1730.559287]  ? complete+0x44/0x50
[ 1730.559288]  cpu_startup_entry+0x1b/0x20
[ 1730.559288]  start_secondary+0x142/0x180
[ 1730.559288]  secondary_startup_64+0xb6/0xc0
[ 1776.686313] nvme nvme0: I/O 96 QID 1 timeout, completion polled

Fixes: 4cfd5779bd6e ("taprio: Add support for txtime-assist mode")
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_taprio.c | 61 ++++++++++++++++++++++++++++--------------
 1 file changed, 41 insertions(+), 20 deletions(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index ad0dadcfcdba..e2d4283bea6d 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -31,6 +31,7 @@ static DEFINE_SPINLOCK(taprio_list_lock);
 
 #define TXTIME_ASSIST_IS_ENABLED(flags) ((flags) & TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST)
 #define FULL_OFFLOAD_IS_ENABLED(flags) ((flags) & TCA_TAPRIO_ATTR_FLAG_FULL_OFFLOAD)
+#define TAPRIO_FLAGS_INVALID U32_MAX
 
 struct sched_entry {
 	struct list_head list;
@@ -1367,6 +1368,33 @@ static int taprio_mqprio_cmp(const struct net_device *dev,
 	return 0;
 }
 
+/* The semantics of the 'flags' argument in relation to 'change()'
+ * requests, are interpreted following two rules (which are applied in
+ * this order): (1) an omitted 'flags' argument is interpreted as
+ * zero; (2) the 'flags' of a "running" taprio instance cannot be
+ * changed.
+ */
+static int taprio_new_flags(const struct nlattr *attr, u32 old,
+			    struct netlink_ext_ack *extack)
+{
+	u32 new = 0;
+
+	if (attr)
+		new = nla_get_u32(attr);
+
+	if (old != TAPRIO_FLAGS_INVALID && old != new) {
+		NL_SET_ERR_MSG_MOD(extack, "Changing 'flags' of a running schedule is not supported");
+		return -EOPNOTSUPP;
+	}
+
+	if (!taprio_flags_valid(new)) {
+		NL_SET_ERR_MSG_MOD(extack, "Specified 'flags' are not valid");
+		return -EINVAL;
+	}
+
+	return new;
+}
+
 static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 			 struct netlink_ext_ack *extack)
 {
@@ -1375,7 +1403,6 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 	struct taprio_sched *q = qdisc_priv(sch);
 	struct net_device *dev = qdisc_dev(sch);
 	struct tc_mqprio_qopt *mqprio = NULL;
-	u32 taprio_flags = 0;
 	unsigned long flags;
 	ktime_t start;
 	int i, err;
@@ -1388,21 +1415,14 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 	if (tb[TCA_TAPRIO_ATTR_PRIOMAP])
 		mqprio = nla_data(tb[TCA_TAPRIO_ATTR_PRIOMAP]);
 
-	if (tb[TCA_TAPRIO_ATTR_FLAGS]) {
-		taprio_flags = nla_get_u32(tb[TCA_TAPRIO_ATTR_FLAGS]);
-
-		if (q->flags != 0 && q->flags != taprio_flags) {
-			NL_SET_ERR_MSG_MOD(extack, "Changing 'flags' of a running schedule is not supported");
-			return -EOPNOTSUPP;
-		} else if (!taprio_flags_valid(taprio_flags)) {
-			NL_SET_ERR_MSG_MOD(extack, "Specified 'flags' are not valid");
-			return -EINVAL;
-		}
+	err = taprio_new_flags(tb[TCA_TAPRIO_ATTR_FLAGS],
+			       q->flags, extack);
+	if (err < 0)
+		return err;
 
-		q->flags = taprio_flags;
-	}
+	q->flags = err;
 
-	err = taprio_parse_mqprio_opt(dev, mqprio, extack, taprio_flags);
+	err = taprio_parse_mqprio_opt(dev, mqprio, extack, q->flags);
 	if (err < 0)
 		return err;
 
@@ -1457,7 +1477,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 					       mqprio->prio_tc_map[i]);
 	}
 
-	if (FULL_OFFLOAD_IS_ENABLED(taprio_flags))
+	if (FULL_OFFLOAD_IS_ENABLED(q->flags))
 		err = taprio_enable_offload(dev, mqprio, q, new_admin, extack);
 	else
 		err = taprio_disable_offload(dev, q, extack);
@@ -1477,14 +1497,14 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 		q->txtime_delay = nla_get_u32(tb[TCA_TAPRIO_ATTR_TXTIME_DELAY]);
 	}
 
-	if (!TXTIME_ASSIST_IS_ENABLED(taprio_flags) &&
-	    !FULL_OFFLOAD_IS_ENABLED(taprio_flags) &&
+	if (!TXTIME_ASSIST_IS_ENABLED(q->flags) &&
+	    !FULL_OFFLOAD_IS_ENABLED(q->flags) &&
 	    !hrtimer_active(&q->advance_timer)) {
 		hrtimer_init(&q->advance_timer, q->clockid, HRTIMER_MODE_ABS);
 		q->advance_timer.function = advance_sched;
 	}
 
-	if (FULL_OFFLOAD_IS_ENABLED(taprio_flags)) {
+	if (FULL_OFFLOAD_IS_ENABLED(q->flags)) {
 		q->dequeue = taprio_dequeue_offload;
 		q->peek = taprio_peek_offload;
 	} else {
@@ -1501,7 +1521,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 		goto unlock;
 	}
 
-	if (TXTIME_ASSIST_IS_ENABLED(taprio_flags)) {
+	if (TXTIME_ASSIST_IS_ENABLED(q->flags)) {
 		setup_txtime(q, new_admin, start);
 
 		if (!oper) {
@@ -1528,7 +1548,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 
 		spin_unlock_irqrestore(&q->current_entry_lock, flags);
 
-		if (FULL_OFFLOAD_IS_ENABLED(taprio_flags))
+		if (FULL_OFFLOAD_IS_ENABLED(q->flags))
 			taprio_offload_config_changed(q);
 	}
 
@@ -1597,6 +1617,7 @@ static int taprio_init(struct Qdisc *sch, struct nlattr *opt,
 	 * and get the valid one on taprio_change().
 	 */
 	q->clockid = -1;
+	q->flags = TAPRIO_FLAGS_INVALID;
 
 	spin_lock(&taprio_list_lock);
 	list_add(&q->taprio_list, &taprio_list);
-- 
2.21.1


From 441c4f70b3041a520277f0179386d663ad1070c4 Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Thu, 6 Feb 2020 13:46:08 -0800
Subject: [PATCH 22/31] taprio: Add missing policy validation for flags

[ Upstream commit 49c684d79cfdc3032344bf6f3deeea81c4efedbf ]

netlink policy validation for the 'flags' argument was missing.

Fixes: 4cfd5779bd6e ("taprio: Add support for txtime-assist mode")
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_taprio.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index e2d4283bea6d..b82a9769ab40 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -767,6 +767,7 @@ static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = {
 	[TCA_TAPRIO_ATTR_SCHED_CLOCKID]              = { .type = NLA_S32 },
 	[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME]           = { .type = NLA_S64 },
 	[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION] = { .type = NLA_S64 },
+	[TCA_TAPRIO_ATTR_FLAGS]                      = { .type = NLA_U32 },
 };
 
 static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry,
-- 
2.21.1


From 62a1516d8ed02dce73f46752657bf2a0080e45cd Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Thu, 6 Feb 2020 13:46:09 -0800
Subject: [PATCH 23/31] taprio: Use taprio_reset_tc() to reset Traffic Classes
 configuration

[ Upstream commit 7c16680a08ee1e444a67d232c679ccf5b30fad16 ]

When destroying the current taprio instance, which can happen when the
creation of one fails, we should reset the traffic class configuration
back to the default state.

netdev_reset_tc() is a better way because in addition to setting the
number of traffic classes to zero, it also resets the priority to
traffic classes mapping to the default value.

Fixes: 5a781ccbd19e ("tc: Add support for configuring the taprio scheduler")
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_taprio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index b82a9769ab40..21df69071df2 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -1588,7 +1588,7 @@ static void taprio_destroy(struct Qdisc *sch)
 	}
 	q->qdiscs = NULL;
 
-	netdev_set_num_tc(dev, 0);
+	netdev_reset_tc(dev);
 
 	if (q->oper_sched)
 		call_rcu(&q->oper_sched->rcu, taprio_free_sched_cb);
-- 
2.21.1


From 7bd47694bf71aef2563eed595318e665e96e3cf9 Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Thu, 6 Feb 2020 13:46:10 -0800
Subject: [PATCH 24/31] taprio: Fix dropping packets when using taprio + ETF
 offloading

[ Upstream commit bfabd41da34180d05382312533a3adc2e012dee0 ]

When using taprio offloading together with ETF offloading, configured
like this, for example:

$ tc qdisc replace dev $IFACE parent root handle 100 taprio \
  	num_tc 4 \
        map 2 2 1 0 3 2 2 2 2 2 2 2 2 2 2 2 \
	queues 1@0 1@1 1@2 1@3 \
	base-time $BASE_TIME \
	sched-entry S 01 1000000 \
	sched-entry S 0e 1000000 \
	flags 0x2

$ tc qdisc replace dev $IFACE parent 100:1 etf \
     	offload delta 300000 clockid CLOCK_TAI

During enqueue, it works out that the verification added for the
"txtime" assisted mode is run when using taprio + ETF offloading, the
only thing missing is initializing the 'next_txtime' of all the cycle
entries. (if we don't set 'next_txtime' all packets from SO_TXTIME
sockets are dropped)

Fixes: 4cfd5779bd6e ("taprio: Add support for txtime-assist mode")
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_taprio.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 21df69071df2..660fc45ee40f 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -1522,9 +1522,9 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 		goto unlock;
 	}
 
-	if (TXTIME_ASSIST_IS_ENABLED(q->flags)) {
-		setup_txtime(q, new_admin, start);
+	setup_txtime(q, new_admin, start);
 
+	if (TXTIME_ASSIST_IS_ENABLED(q->flags)) {
 		if (!oper) {
 			rcu_assign_pointer(q->oper_sched, new_admin);
 			err = 0;
-- 
2.21.1


From 71d9d533a231a0e883e636f53ef95a94ab4d1ab2 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 7 Feb 2020 07:16:37 -0800
Subject: [PATCH 25/31] ipv6/addrconf: fix potential NULL deref in
 inet6_set_link_af()

[ Upstream commit db3fa271022dacb9f741b96ea4714461a8911bb9 ]

__in6_dev_get(dev) called from inet6_set_link_af() can return NULL.

The needed check has been recently removed, let's add it back.

While do_setlink() does call validate_linkmsg() :
...
err = validate_linkmsg(dev, tb); /* OK at this point */
...

It is possible that the following call happening before the
->set_link_af() removes IPv6 if MTU is less than 1280 :

if (tb[IFLA_MTU]) {
    err = dev_set_mtu_ext(dev, nla_get_u32(tb[IFLA_MTU]), extack);
    if (err < 0)
          goto errout;
    status |= DO_SETLINK_MODIFIED;
}
...

if (tb[IFLA_AF_SPEC]) {
   ...
   err = af_ops->set_link_af(dev, af);
      ->inet6_set_link_af() // CRASH because idev is NULL

Please note that IPv4 is immune to the bug since inet_set_link_af() does :

struct in_device *in_dev = __in_dev_get_rcu(dev);
if (!in_dev)
    return -EAFNOSUPPORT;

This problem has been mentioned in commit cf7afbfeb8ce ("rtnl: make
link af-specific updates atomic") changelog :

    This method is not fail proof, while it is currently sufficient
    to make set_link_af() inerrable and thus 100% atomic, the
    validation function method will not be able to detect all error
    scenarios in the future, there will likely always be errors
    depending on states which are f.e. not protected by rtnl_mutex
    and thus may change between validation and setting.

IPv6: ADDRCONF(NETDEV_CHANGE): lo: link becomes ready
general protection fault, probably for non-canonical address 0xdffffc0000000056: 0000 [#1] PREEMPT SMP KASAN
KASAN: null-ptr-deref in range [0x00000000000002b0-0x00000000000002b7]
CPU: 0 PID: 9698 Comm: syz-executor712 Not tainted 5.5.0-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:inet6_set_link_af+0x66e/0xae0 net/ipv6/addrconf.c:5733
Code: 38 d0 7f 08 84 c0 0f 85 20 03 00 00 48 8d bb b0 02 00 00 45 0f b6 64 24 04 48 b8 00 00 00 00 00 fc ff df 48 89 fa 48 c1 ea 03 <0f> b6 04 02 84 c0 74 08 3c 03 0f 8e 1a 03 00 00 44 89 a3 b0 02 00
RSP: 0018:ffffc90005b06d40 EFLAGS: 00010206
RAX: dffffc0000000000 RBX: 0000000000000000 RCX: ffffffff86df39a6
RDX: 0000000000000056 RSI: ffffffff86df3e74 RDI: 00000000000002b0
RBP: ffffc90005b06e70 R08: ffff8880a2ac0380 R09: ffffc90005b06db0
R10: fffff52000b60dbe R11: ffffc90005b06df7 R12: 0000000000000000
R13: 0000000000000000 R14: ffff8880a1fcc424 R15: dffffc0000000000
FS:  0000000000c46880(0000) GS:ffff8880ae800000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000055f0494ca0d0 CR3: 000000009e4ac000 CR4: 00000000001406f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 do_setlink+0x2a9f/0x3720 net/core/rtnetlink.c:2754
 rtnl_group_changelink net/core/rtnetlink.c:3103 [inline]
 __rtnl_newlink+0xdd1/0x1790 net/core/rtnetlink.c:3257
 rtnl_newlink+0x69/0xa0 net/core/rtnetlink.c:3377
 rtnetlink_rcv_msg+0x45e/0xaf0 net/core/rtnetlink.c:5438
 netlink_rcv_skb+0x177/0x450 net/netlink/af_netlink.c:2477
 rtnetlink_rcv+0x1d/0x30 net/core/rtnetlink.c:5456
 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
 netlink_unicast+0x59e/0x7e0 net/netlink/af_netlink.c:1328
 netlink_sendmsg+0x91c/0xea0 net/netlink/af_netlink.c:1917
 sock_sendmsg_nosec net/socket.c:652 [inline]
 sock_sendmsg+0xd7/0x130 net/socket.c:672
 ____sys_sendmsg+0x753/0x880 net/socket.c:2343
 ___sys_sendmsg+0x100/0x170 net/socket.c:2397
 __sys_sendmsg+0x105/0x1d0 net/socket.c:2430
 __do_sys_sendmsg net/socket.c:2439 [inline]
 __se_sys_sendmsg net/socket.c:2437 [inline]
 __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2437
 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x4402e9
Code: 18 89 d0 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 fb 13 fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007fffd62fbcf8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 00000000004402e9
RDX: 0000000000000000 RSI: 0000000020000080 RDI: 0000000000000003
RBP: 00000000006ca018 R08: 0000000000000008 R09: 00000000004002c8
R10: 0000000000000005 R11: 0000000000000246 R12: 0000000000401b70
R13: 0000000000401c00 R14: 0000000000000000 R15: 0000000000000000
Modules linked in:
---[ end trace cfa7664b8fdcdff3 ]---
RIP: 0010:inet6_set_link_af+0x66e/0xae0 net/ipv6/addrconf.c:5733
Code: 38 d0 7f 08 84 c0 0f 85 20 03 00 00 48 8d bb b0 02 00 00 45 0f b6 64 24 04 48 b8 00 00 00 00 00 fc ff df 48 89 fa 48 c1 ea 03 <0f> b6 04 02 84 c0 74 08 3c 03 0f 8e 1a 03 00 00 44 89 a3 b0 02 00
RSP: 0018:ffffc90005b06d40 EFLAGS: 00010206
RAX: dffffc0000000000 RBX: 0000000000000000 RCX: ffffffff86df39a6
RDX: 0000000000000056 RSI: ffffffff86df3e74 RDI: 00000000000002b0
RBP: ffffc90005b06e70 R08: ffff8880a2ac0380 R09: ffffc90005b06db0
R10: fffff52000b60dbe R11: ffffc90005b06df7 R12: 0000000000000000
R13: 0000000000000000 R14: ffff8880a1fcc424 R15: dffffc0000000000
FS:  0000000000c46880(0000) GS:ffff8880ae900000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000020000004 CR3: 000000009e4ac000 CR4: 00000000001406e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400

Fixes: 7dc2bccab0ee ("Validate required parameters in inet6_validate_link_af")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Bisected-and-reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 39d861d00377..cb493e15959c 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5718,6 +5718,9 @@ static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla)
 	struct nlattr *tb[IFLA_INET6_MAX + 1];
 	int err;
 
+	if (!idev)
+		return -EAFNOSUPPORT;
+
 	if (nla_parse_nested_deprecated(tb, IFLA_INET6_MAX, nla, NULL, NULL) < 0)
 		BUG();
 
-- 
2.21.1


From ade2332243457e1c9b5eac7511b63f9e0bdfdc16 Mon Sep 17 00:00:00 2001
From: Sudarsana Reddy Kalluru <skalluru@marvell.com>
Date: Wed, 5 Feb 2020 05:10:55 -0800
Subject: [PATCH 26/31] qed: Fix timestamping issue for L2 unicast ptp packets.

[ Upstream commit 0202d293c2faecba791ba4afc5aec086249c393d ]

commit cedeac9df4b8 ("qed: Add support for Timestamping the unicast
PTP packets.") handles the timestamping of L4 ptp packets only.
This patch adds driver changes to detect/timestamp both L2/L4 unicast
PTP packets.

Fixes: cedeac9df4b8 ("qed: Add support for Timestamping the unicast PTP packets.")
Signed-off-by: Sudarsana Reddy Kalluru <skalluru@marvell.com>
Signed-off-by: Ariel Elior <aelior@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_ptp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_ptp.c b/drivers/net/ethernet/qlogic/qed/qed_ptp.c
index 0dacf2c18c09..3e613058e225 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ptp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ptp.c
@@ -44,8 +44,8 @@
 /* Add/subtract the Adjustment_Value when making a Drift adjustment */
 #define QED_DRIFT_CNTR_DIRECTION_SHIFT		31
 #define QED_TIMESTAMP_MASK			BIT(16)
-/* Param mask for Hardware to detect/timestamp the unicast PTP packets */
-#define QED_PTP_UCAST_PARAM_MASK		0xF
+/* Param mask for Hardware to detect/timestamp the L2/L4 unicast PTP packets */
+#define QED_PTP_UCAST_PARAM_MASK              0x70F
 
 static enum qed_resc_lock qed_ptcdev_to_resc(struct qed_hwfn *p_hwfn)
 {
-- 
2.21.1


From af857a99e3274762b1046eb87cae53e3d60ff35c Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Fri, 7 Feb 2020 19:29:28 +0200
Subject: [PATCH 27/31] drop_monitor: Do not cancel uninitialized work item

[ Upstream commit dfa7f709596be5ca46c070d4f8acbb344322056a ]

Drop monitor uses a work item that takes care of constructing and
sending netlink notifications to user space. In case drop monitor never
started to monitor, then the work item is uninitialized and not
associated with a function.

Therefore, a stop command from user space results in canceling an
uninitialized work item which leads to the following warning [1].

Fix this by not processing a stop command if drop monitor is not
currently monitoring.

[1]
[   31.735402] ------------[ cut here ]------------
[   31.736470] WARNING: CPU: 0 PID: 143 at kernel/workqueue.c:3032 __flush_work+0x89f/0x9f0
...
[   31.738120] CPU: 0 PID: 143 Comm: dwdump Not tainted 5.5.0-custom-09491-g16d4077796b8 #727
[   31.741968] RIP: 0010:__flush_work+0x89f/0x9f0
...
[   31.760526] Call Trace:
[   31.771689]  __cancel_work_timer+0x2a6/0x3b0
[   31.776809]  net_dm_cmd_trace+0x300/0xef0
[   31.777549]  genl_rcv_msg+0x5c6/0xd50
[   31.781005]  netlink_rcv_skb+0x13b/0x3a0
[   31.784114]  genl_rcv+0x29/0x40
[   31.784720]  netlink_unicast+0x49f/0x6a0
[   31.787148]  netlink_sendmsg+0x7cf/0xc80
[   31.790426]  ____sys_sendmsg+0x620/0x770
[   31.793458]  ___sys_sendmsg+0xfd/0x170
[   31.802216]  __sys_sendmsg+0xdf/0x1a0
[   31.806195]  do_syscall_64+0xa0/0x540
[   31.806885]  entry_SYSCALL_64_after_hwframe+0x49/0xbe

Fixes: 8e94c3bc922e ("drop_monitor: Allow user to start monitoring hardware drops")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/drop_monitor.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 536e032d95c8..246a258b1fac 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -1004,8 +1004,10 @@ static void net_dm_hw_monitor_stop(struct netlink_ext_ack *extack)
 {
 	int cpu;
 
-	if (!monitor_hw)
+	if (!monitor_hw) {
 		NL_SET_ERR_MSG_MOD(extack, "Hardware monitoring already disabled");
+		return;
+	}
 
 	monitor_hw = false;
 
-- 
2.21.1


From fb81c8e99f1b6ed3381741d74fc170328b111f3c Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@mellanox.com>
Date: Mon, 27 Jan 2020 09:27:51 +0200
Subject: [PATCH 28/31] net/mlx5: Fix deadlock in fs_core

[ Upstream commit c1948390d78b5183ee9b7dd831efd7f6ac496ab0 ]

free_match_list could be called when the flow table is already
locked. We need to pass this notation to tree_put_node.

It fixes the following lockdep warnning:

[ 1797.268537] ============================================
[ 1797.276837] WARNING: possible recursive locking detected
[ 1797.285101] 5.5.0-rc5+ #10 Not tainted
[ 1797.291641] --------------------------------------------
[ 1797.299917] handler10/9296 is trying to acquire lock:
[ 1797.307885] ffff889ad399a0a0 (&node->lock){++++}, at:
tree_put_node+0x1d5/0x210 [mlx5_core]
[ 1797.319694]
[ 1797.319694] but task is already holding lock:
[ 1797.330904] ffff889ad399a0a0 (&node->lock){++++}, at:
nested_down_write_ref_node.part.33+0x1a/0x60 [mlx5_core]
[ 1797.344707]
[ 1797.344707] other info that might help us debug this:
[ 1797.356952]  Possible unsafe locking scenario:
[ 1797.356952]
[ 1797.368333]        CPU0
[ 1797.373357]        ----
[ 1797.378364]   lock(&node->lock);
[ 1797.384222]   lock(&node->lock);
[ 1797.390031]
[ 1797.390031]  *** DEADLOCK ***
[ 1797.390031]
[ 1797.403003]  May be due to missing lock nesting notation
[ 1797.403003]
[ 1797.414691] 3 locks held by handler10/9296:
[ 1797.421465]  #0: ffff889cf2c5a110 (&block->cb_lock){++++}, at:
tc_setup_cb_add+0x70/0x250
[ 1797.432810]  #1: ffff88a030081490 (&comp->sem){++++}, at:
mlx5_devcom_get_peer_data+0x4c/0xb0 [mlx5_core]
[ 1797.445829]  #2: ffff889ad399a0a0 (&node->lock){++++}, at:
nested_down_write_ref_node.part.33+0x1a/0x60 [mlx5_core]
[ 1797.459913]
[ 1797.459913] stack backtrace:
[ 1797.469436] CPU: 1 PID: 9296 Comm: handler10 Kdump: loaded Not
tainted 5.5.0-rc5+ #10
[ 1797.480643] Hardware name: Dell Inc. PowerEdge R730/072T6D, BIOS
2.4.3 01/17/2017
[ 1797.491480] Call Trace:
[ 1797.496701]  dump_stack+0x96/0xe0
[ 1797.502864]  __lock_acquire.cold.63+0xf8/0x212
[ 1797.510301]  ? lockdep_hardirqs_on+0x250/0x250
[ 1797.517701]  ? mark_held_locks+0x55/0xa0
[ 1797.524547]  ? quarantine_put+0xb7/0x160
[ 1797.531422]  ? lockdep_hardirqs_on+0x17d/0x250
[ 1797.538913]  lock_acquire+0xd6/0x1f0
[ 1797.545529]  ? tree_put_node+0x1d5/0x210 [mlx5_core]
[ 1797.553701]  down_write+0x94/0x140
[ 1797.560206]  ? tree_put_node+0x1d5/0x210 [mlx5_core]
[ 1797.568464]  ? down_write_killable_nested+0x170/0x170
[ 1797.576925]  ? del_hw_flow_group+0xde/0x1f0 [mlx5_core]
[ 1797.585629]  tree_put_node+0x1d5/0x210 [mlx5_core]
[ 1797.593891]  ? free_match_list.part.25+0x147/0x170 [mlx5_core]
[ 1797.603389]  free_match_list.part.25+0xe0/0x170 [mlx5_core]
[ 1797.612654]  _mlx5_add_flow_rules+0x17e2/0x20b0 [mlx5_core]
[ 1797.621838]  ? lock_acquire+0xd6/0x1f0
[ 1797.629028]  ? esw_get_prio_table+0xb0/0x3e0 [mlx5_core]
[ 1797.637981]  ? alloc_insert_flow_group+0x420/0x420 [mlx5_core]
[ 1797.647459]  ? try_to_wake_up+0x4c7/0xc70
[ 1797.654881]  ? lock_downgrade+0x350/0x350
[ 1797.662271]  ? __mutex_unlock_slowpath+0xb1/0x3f0
[ 1797.670396]  ? find_held_lock+0xac/0xd0
[ 1797.677540]  ? mlx5_add_flow_rules+0xdc/0x360 [mlx5_core]
[ 1797.686467]  mlx5_add_flow_rules+0xdc/0x360 [mlx5_core]
[ 1797.695134]  ? _mlx5_add_flow_rules+0x20b0/0x20b0 [mlx5_core]
[ 1797.704270]  ? irq_exit+0xa5/0x170
[ 1797.710764]  ? retint_kernel+0x10/0x10
[ 1797.717698]  ? mlx5_eswitch_set_rule_source_port.isra.9+0x122/0x230
[mlx5_core]
[ 1797.728708]  mlx5_eswitch_add_offloaded_rule+0x465/0x6d0 [mlx5_core]
[ 1797.738713]  ? mlx5_eswitch_get_prio_range+0x30/0x30 [mlx5_core]
[ 1797.748384]  ? mlx5_fc_stats_work+0x670/0x670 [mlx5_core]
[ 1797.757400]  mlx5e_tc_offload_fdb_rules.isra.27+0x24/0x90 [mlx5_core]
[ 1797.767665]  mlx5e_tc_add_fdb_flow+0xaf8/0xd40 [mlx5_core]
[ 1797.776886]  ? mlx5e_encap_put+0xd0/0xd0 [mlx5_core]
[ 1797.785562]  ? mlx5e_alloc_flow.isra.43+0x18c/0x1c0 [mlx5_core]
[ 1797.795353]  __mlx5e_add_fdb_flow+0x2e2/0x440 [mlx5_core]
[ 1797.804558]  ? mlx5e_tc_update_neigh_used_value+0x8c0/0x8c0
[mlx5_core]
[ 1797.815093]  ? wait_for_completion+0x260/0x260
[ 1797.823272]  mlx5e_configure_flower+0xe94/0x1620 [mlx5_core]
[ 1797.832792]  ? __mlx5e_add_fdb_flow+0x440/0x440 [mlx5_core]
[ 1797.842096]  ? down_read+0x11a/0x2e0
[ 1797.849090]  ? down_write+0x140/0x140
[ 1797.856142]  ? mlx5e_rep_indr_setup_block_cb+0xc0/0xc0 [mlx5_core]
[ 1797.866027]  tc_setup_cb_add+0x11a/0x250
[ 1797.873339]  fl_hw_replace_filter+0x25e/0x320 [cls_flower]
[ 1797.882385]  ? fl_hw_destroy_filter+0x1c0/0x1c0 [cls_flower]
[ 1797.891607]  fl_change+0x1d54/0x1fb6 [cls_flower]
[ 1797.899772]  ? __rhashtable_insert_fast.constprop.50+0x9f0/0x9f0
[cls_flower]
[ 1797.910728]  ? lock_downgrade+0x350/0x350
[ 1797.918187]  ? __radix_tree_lookup+0xa5/0x130
[ 1797.926046]  ? fl_set_key+0x1590/0x1590 [cls_flower]
[ 1797.934611]  ? __rhashtable_insert_fast.constprop.50+0x9f0/0x9f0
[cls_flower]
[ 1797.945673]  tc_new_tfilter+0xcd1/0x1240
[ 1797.953138]  ? tc_del_tfilter+0xb10/0xb10
[ 1797.960688]  ? avc_has_perm_noaudit+0x92/0x320
[ 1797.968721]  ? avc_has_perm_noaudit+0x1df/0x320
[ 1797.976816]  ? avc_has_extended_perms+0x990/0x990
[ 1797.985090]  ? mark_lock+0xaa/0x9e0
[ 1797.991988]  ? match_held_lock+0x1b/0x240
[ 1797.999457]  ? match_held_lock+0x1b/0x240
[ 1798.006859]  ? find_held_lock+0xac/0xd0
[ 1798.014045]  ? symbol_put_addr+0x40/0x40
[ 1798.021317]  ? rcu_read_lock_sched_held+0xd0/0xd0
[ 1798.029460]  ? tc_del_tfilter+0xb10/0xb10
[ 1798.036810]  rtnetlink_rcv_msg+0x4d5/0x620
[ 1798.044236]  ? rtnl_bridge_getlink+0x460/0x460
[ 1798.052034]  ? lockdep_hardirqs_on+0x250/0x250
[ 1798.059837]  ? match_held_lock+0x1b/0x240
[ 1798.067146]  ? find_held_lock+0xac/0xd0
[ 1798.074246]  netlink_rcv_skb+0xc6/0x1f0
[ 1798.081339]  ? rtnl_bridge_getlink+0x460/0x460
[ 1798.089104]  ? netlink_ack+0x440/0x440
[ 1798.096061]  netlink_unicast+0x2d4/0x3b0
[ 1798.103189]  ? netlink_attachskb+0x3f0/0x3f0
[ 1798.110724]  ? _copy_from_iter_full+0xda/0x370
[ 1798.118415]  netlink_sendmsg+0x3ba/0x6a0
[ 1798.125478]  ? netlink_unicast+0x3b0/0x3b0
[ 1798.132705]  ? netlink_unicast+0x3b0/0x3b0
[ 1798.139880]  sock_sendmsg+0x94/0xa0
[ 1798.146332]  ____sys_sendmsg+0x36c/0x3f0
[ 1798.153251]  ? copy_msghdr_from_user+0x165/0x230
[ 1798.160941]  ? kernel_sendmsg+0x30/0x30
[ 1798.167738]  ___sys_sendmsg+0xeb/0x150
[ 1798.174411]  ? sendmsg_copy_msghdr+0x30/0x30
[ 1798.181649]  ? lock_downgrade+0x350/0x350
[ 1798.188559]  ? rcu_read_lock_sched_held+0xd0/0xd0
[ 1798.196239]  ? __fget+0x21d/0x320
[ 1798.202335]  ? do_dup2+0x2a0/0x2a0
[ 1798.208499]  ? lock_downgrade+0x350/0x350
[ 1798.215366]  ? __fget_light+0xd6/0xf0
[ 1798.221808]  ? syscall_trace_enter+0x369/0x5d0
[ 1798.229112]  __sys_sendmsg+0xd3/0x160
[ 1798.235511]  ? __sys_sendmsg_sock+0x60/0x60
[ 1798.242478]  ? syscall_trace_enter+0x233/0x5d0
[ 1798.249721]  ? syscall_slow_exit_work+0x280/0x280
[ 1798.257211]  ? do_syscall_64+0x1e/0x2e0
[ 1798.263680]  do_syscall_64+0x72/0x2e0
[ 1798.269950]  entry_SYSCALL_64_after_hwframe+0x49/0xbe

Fixes: bd71b08ec2ee ("net/mlx5: Support multiple updates of steering rules in parallel")
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Alaa Hleihel <alaa@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 8c5df6c7d7b6..8af87f922fb6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -1555,16 +1555,16 @@ struct match_list_head {
 	struct match_list first;
 };
 
-static void free_match_list(struct match_list_head *head)
+static void free_match_list(struct match_list_head *head, bool ft_locked)
 {
 	if (!list_empty(&head->list)) {
 		struct match_list *iter, *match_tmp;
 
 		list_del(&head->first.list);
-		tree_put_node(&head->first.g->node, false);
+		tree_put_node(&head->first.g->node, ft_locked);
 		list_for_each_entry_safe(iter, match_tmp, &head->list,
 					 list) {
-			tree_put_node(&iter->g->node, false);
+			tree_put_node(&iter->g->node, ft_locked);
 			list_del(&iter->list);
 			kfree(iter);
 		}
@@ -1573,7 +1573,8 @@ static void free_match_list(struct match_list_head *head)
 
 static int build_match_list(struct match_list_head *match_head,
 			    struct mlx5_flow_table *ft,
-			    const struct mlx5_flow_spec *spec)
+			    const struct mlx5_flow_spec *spec,
+			    bool ft_locked)
 {
 	struct rhlist_head *tmp, *list;
 	struct mlx5_flow_group *g;
@@ -1598,7 +1599,7 @@ static int build_match_list(struct match_list_head *match_head,
 
 		curr_match = kmalloc(sizeof(*curr_match), GFP_ATOMIC);
 		if (!curr_match) {
-			free_match_list(match_head);
+			free_match_list(match_head, ft_locked);
 			err = -ENOMEM;
 			goto out;
 		}
@@ -1778,7 +1779,7 @@ _mlx5_add_flow_rules(struct mlx5_flow_table *ft,
 	version = atomic_read(&ft->node.version);
 
 	/* Collect all fgs which has a matching match_criteria */
-	err = build_match_list(&match_head, ft, spec);
+	err = build_match_list(&match_head, ft, spec, take_write);
 	if (err) {
 		if (take_write)
 			up_write_ref_node(&ft->node, false);
@@ -1792,7 +1793,7 @@ _mlx5_add_flow_rules(struct mlx5_flow_table *ft,
 
 	rule = try_add_to_existing_fg(ft, &match_head.list, spec, flow_act, dest,
 				      dest_num, version);
-	free_match_list(&match_head);
+	free_match_list(&match_head, take_write);
 	if (!IS_ERR(rule) ||
 	    (PTR_ERR(rule) != -ENOENT && PTR_ERR(rule) != -EAGAIN)) {
 		if (take_write)
-- 
2.21.1


From a8435c513c1c1cca174f4bc6fd69bcd2e3fd6b53 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Mon, 27 Jan 2020 14:18:14 +0200
Subject: [PATCH 29/31] net/mlx5: Deprecate usage of generic TLS HW capability
 bit

[ Upstream commit 61c00cca41aeeaa8e5263c2f81f28534bc1efafb ]

Deprecate the generic TLS cap bit, use the new TX-specific
TLS cap bit instead.

Fixes: a12ff35e0fb7 ("net/mlx5: Introduce TLS TX offload hardware bits and structures")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h        | 2 +-
 .../net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c    | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/fw.c               | 2 +-
 include/linux/mlx5/mlx5_ifc.h                              | 7 ++++---
 4 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h
index d787bc0a4155..e09bc3858d57 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h
@@ -45,7 +45,7 @@ void mlx5_ktls_destroy_key(struct mlx5_core_dev *mdev, u32 key_id);
 
 static inline bool mlx5_accel_is_ktls_device(struct mlx5_core_dev *mdev)
 {
-	if (!MLX5_CAP_GEN(mdev, tls))
+	if (!MLX5_CAP_GEN(mdev, tls_tx))
 		return false;
 
 	if (!MLX5_CAP_GEN(mdev, log_max_dek))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
index 71384ad1a443..ef1ed15a53b4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
@@ -269,7 +269,7 @@ struct sk_buff *mlx5e_tls_handle_tx_skb(struct net_device *netdev,
 	int datalen;
 	u32 skb_seq;
 
-	if (MLX5_CAP_GEN(sq->channel->mdev, tls)) {
+	if (MLX5_CAP_GEN(sq->channel->mdev, tls_tx)) {
 		skb = mlx5e_ktls_handle_tx_skb(netdev, sq, skb, wqe, pi);
 		goto out;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index a19790dee7b2..13e86f0b42f5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -239,7 +239,7 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev)
 			return err;
 	}
 
-	if (MLX5_CAP_GEN(dev, tls)) {
+	if (MLX5_CAP_GEN(dev, tls_tx)) {
 		err = mlx5_core_get_caps(dev, MLX5_CAP_TLS);
 		if (err)
 			return err;
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 5d54fccf87fc..56f124a6eccb 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1418,14 +1418,15 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 	u8         reserved_at_440[0x20];
 
-	u8         tls[0x1];
-	u8         reserved_at_461[0x2];
+	u8         reserved_at_460[0x3];
 	u8         log_max_uctx[0x5];
 	u8         reserved_at_468[0x3];
 	u8         log_max_umem[0x5];
 	u8         max_num_eqs[0x10];
 
-	u8         reserved_at_480[0x3];
+	u8         reserved_at_480[0x1];
+	u8         tls_tx[0x1];
+	u8         reserved_at_482[0x1];
 	u8         log_max_l2_table[0x5];
 	u8         reserved_at_488[0x8];
 	u8         log_uar_page_sz[0x10];
-- 
2.21.1


From 119d18f450ab94e6daff822381a430fd02197a04 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Wed, 5 Feb 2020 21:22:46 +0100
Subject: [PATCH 30/31] r8169: fix performance regression related to PCIe max
 read request size

[ Upstream commit 21b5f672fb2eb1366dedc4ac9d32431146b378d3 ]

It turned out that on low performance systems the original change can
cause lower tx performance. On a N3450-based mini-PC tx performance
in iperf3 was reduced from 950Mbps to ~900Mbps. Therefore effectively
revert the original change, just use pcie_set_readrq() now instead of
changing the PCIe capability register directly.

Fixes: 2df49d365498 ("r8169: remove fiddling with the PCIe max read request size")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 67a4d5d45e3a..92a590154bb9 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -3865,15 +3865,18 @@ static void rtl_hw_jumbo_enable(struct rtl8169_private *tp)
 	switch (tp->mac_version) {
 	case RTL_GIGA_MAC_VER_12:
 	case RTL_GIGA_MAC_VER_17:
+		pcie_set_readrq(tp->pci_dev, 512);
 		r8168b_1_hw_jumbo_enable(tp);
 		break;
 	case RTL_GIGA_MAC_VER_18 ... RTL_GIGA_MAC_VER_26:
+		pcie_set_readrq(tp->pci_dev, 512);
 		r8168c_hw_jumbo_enable(tp);
 		break;
 	case RTL_GIGA_MAC_VER_27 ... RTL_GIGA_MAC_VER_28:
 		r8168dp_hw_jumbo_enable(tp);
 		break;
 	case RTL_GIGA_MAC_VER_31 ... RTL_GIGA_MAC_VER_33:
+		pcie_set_readrq(tp->pci_dev, 512);
 		r8168e_hw_jumbo_enable(tp);
 		break;
 	default:
@@ -3903,6 +3906,9 @@ static void rtl_hw_jumbo_disable(struct rtl8169_private *tp)
 		break;
 	}
 	rtl_lock_config_regs(tp);
+
+	if (pci_is_pcie(tp->pci_dev) && tp->supports_gmii)
+		pcie_set_readrq(tp->pci_dev, 4096);
 }
 
 static void rtl_jumbo_config(struct rtl8169_private *tp, int mtu)
-- 
2.21.1


From 7ea65cb7346232717ea19ff5aaa810c150e3f075 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Thu, 9 Jan 2020 15:53:37 +0200
Subject: [PATCH 31/31] net/mlx5e: TX, Error completion is for last WQE in
 batch

[ Upstream commit b57e66ad42d051ed31319c28ed1b62b191299a29 ]

For a cyclic work queue, when not requesting a completion per WQE,
a single CQE might indicate the completion of several WQEs.
However, in case some WQE in the batch causes an error, then an error
completion is issued, breaking the batch, and pointing to the offending
WQE in the wqe_counter field.

Hence, WQE-specific error CQE handling (like printing, breaking, etc...)
should be performed only for the last WQE in batch.

Fixes: 130c7b46c93d ("net/mlx5e: TX, Dump WQs wqe descriptors on CQE with error events")
Fixes: fd9b4be8002c ("net/mlx5e: RX, Support multiple outstanding UMR posts")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en_rx.c   | 16 +++++----
 .../net/ethernet/mellanox/mlx5/core/en_tx.c   | 33 ++++++++-----------
 2 files changed, 23 insertions(+), 26 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 9e9960146e5b..1c3ab69cbd96 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -613,13 +613,6 @@ void mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
 
 		wqe_counter = be16_to_cpu(cqe->wqe_counter);
 
-		if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_REQ)) {
-			netdev_WARN_ONCE(cq->channel->netdev,
-					 "Bad OP in ICOSQ CQE: 0x%x\n", get_cqe_opcode(cqe));
-			if (!test_and_set_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state))
-				queue_work(cq->channel->priv->wq, &sq->recover_work);
-			break;
-		}
 		do {
 			struct mlx5e_sq_wqe_info *wi;
 			u16 ci;
@@ -629,6 +622,15 @@ void mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
 			ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc);
 			wi = &sq->db.ico_wqe[ci];
 
+			if (last_wqe && unlikely(get_cqe_opcode(cqe) != MLX5_CQE_REQ)) {
+				netdev_WARN_ONCE(cq->channel->netdev,
+						 "Bad OP in ICOSQ CQE: 0x%x\n",
+						 get_cqe_opcode(cqe));
+				if (!test_and_set_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state))
+					queue_work(cq->channel->priv->wq, &sq->recover_work);
+				break;
+			}
+
 			if (likely(wi->opcode == MLX5_OPCODE_UMR)) {
 				sqcc += MLX5E_UMR_WQEBBS;
 				wi->umr.rq->mpwqe.umr_completed++;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 2565ba8692d9..ee60383adc5b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -451,34 +451,17 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 
 	i = 0;
 	do {
+		struct mlx5e_tx_wqe_info *wi;
 		u16 wqe_counter;
 		bool last_wqe;
+		u16 ci;
 
 		mlx5_cqwq_pop(&cq->wq);
 
 		wqe_counter = be16_to_cpu(cqe->wqe_counter);
 
-		if (unlikely(get_cqe_opcode(cqe) == MLX5_CQE_REQ_ERR)) {
-			if (!test_and_set_bit(MLX5E_SQ_STATE_RECOVERING,
-					      &sq->state)) {
-				struct mlx5e_tx_wqe_info *wi;
-				u16 ci;
-
-				ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc);
-				wi = &sq->db.wqe_info[ci];
-				mlx5e_dump_error_cqe(sq,
-						     (struct mlx5_err_cqe *)cqe);
-				mlx5_wq_cyc_wqe_dump(&sq->wq, ci, wi->num_wqebbs);
-				queue_work(cq->channel->priv->wq,
-					   &sq->recover_work);
-			}
-			stats->cqe_err++;
-		}
-
 		do {
-			struct mlx5e_tx_wqe_info *wi;
 			struct sk_buff *skb;
-			u16 ci;
 			int j;
 
 			last_wqe = (sqcc == wqe_counter);
@@ -516,6 +499,18 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 			napi_consume_skb(skb, napi_budget);
 		} while (!last_wqe);
 
+		if (unlikely(get_cqe_opcode(cqe) == MLX5_CQE_REQ_ERR)) {
+			if (!test_and_set_bit(MLX5E_SQ_STATE_RECOVERING,
+					      &sq->state)) {
+				mlx5e_dump_error_cqe(sq,
+						     (struct mlx5_err_cqe *)cqe);
+				mlx5_wq_cyc_wqe_dump(&sq->wq, ci, wi->num_wqebbs);
+				queue_work(cq->channel->priv->wq,
+					   &sq->recover_work);
+			}
+			stats->cqe_err++;
+		}
+
 	} while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
 
 	stats->cqes += i;
-- 
2.21.1

Re: [PATCHES] Networking

[Greg KH]

On Sun, Feb 09, 2020 at 10:21:28PM +0100, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v5.4 and
> v5.5 -stable, respectively.
> 
> Thank you.

THanks for these, all now queued up.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 105 bytes --]


Please queue up the following networking bug fixes for v5.4 and
v5.5 -stable, respectively.

Thank you.

[-- Attachment #2: net_54.mbox --]
[-- Type: Application/Octet-Stream, Size: 16804 bytes --]

From a480eaea3735fcd24b131ef4de7f0059966802dc Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
Date: Mon, 10 Feb 2020 17:10:46 +0100
Subject: [PATCH 1/6] core: Don't skip generic XDP program execution for cloned
 SKBs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit ad1e03b2b3d4430baaa109b77bc308dc73050de3 ]

The current generic XDP handler skips execution of XDP programs entirely if
an SKB is marked as cloned. This leads to some surprising behaviour, as
packets can end up being cloned in various ways, which will make an XDP
program not see all the traffic on an interface.

This was discovered by a simple test case where an XDP program that always
returns XDP_DROP is installed on a veth device. When combining this with
the Scapy packet sniffer (which uses an AF_PACKET) socket on the sending
side, SKBs reliably end up in the cloned state, causing them to be passed
through to the receiving interface instead of being dropped. A minimal
reproducer script for this is included below.

This patch fixed the issue by simply triggering the existing linearisation
code for cloned SKBs instead of skipping the XDP program execution. This
behaviour is in line with the behaviour of the native XDP implementation
for the veth driver, which will reallocate and copy the SKB data if the SKB
is marked as shared.

Reproducer Python script (requires BCC and Scapy):

from scapy.all import TCP, IP, Ether, sendp, sniff, AsyncSniffer, Raw, UDP
from bcc import BPF
import time, sys, subprocess, shlex

SKB_MODE = (1 << 1)
DRV_MODE = (1 << 2)
PYTHON=sys.executable

def client():
    time.sleep(2)
    # Sniffing on the sender causes skb_cloned() to be set
    s = AsyncSniffer()
    s.start()

    for p in range(10):
        sendp(Ether(dst="aa:aa:aa:aa:aa:aa", src="cc:cc:cc:cc:cc:cc")/IP()/UDP()/Raw("Test"),
              verbose=False)
        time.sleep(0.1)

    s.stop()
    return 0

def server(mode):
    prog = BPF(text="int dummy_drop(struct xdp_md *ctx) {return XDP_DROP;}")
    func = prog.load_func("dummy_drop", BPF.XDP)
    prog.attach_xdp("a_to_b", func, mode)

    time.sleep(1)

    s = sniff(iface="a_to_b", count=10, timeout=15)
    if len(s):
        print(f"Got {len(s)} packets - should have gotten 0")
        return 1
    else:
        print("Got no packets - as expected")
        return 0

if len(sys.argv) < 2:
    print(f"Usage: {sys.argv[0]} <skb|drv>")
    sys.exit(1)

if sys.argv[1] == "client":
    sys.exit(client())
elif sys.argv[1] == "server":
    mode = SKB_MODE if sys.argv[2] == 'skb' else DRV_MODE
    sys.exit(server(mode))
else:
    try:
        mode = sys.argv[1]
        if mode not in ('skb', 'drv'):
            print(f"Usage: {sys.argv[0]} <skb|drv>")
            sys.exit(1)
        print(f"Running in {mode} mode")

        for cmd in [
                'ip netns add netns_a',
                'ip netns add netns_b',
                'ip -n netns_a link add a_to_b type veth peer name b_to_a netns netns_b',
                # Disable ipv6 to make sure there's no address autoconf traffic
                'ip netns exec netns_a sysctl -qw net.ipv6.conf.a_to_b.disable_ipv6=1',
                'ip netns exec netns_b sysctl -qw net.ipv6.conf.b_to_a.disable_ipv6=1',
                'ip -n netns_a link set dev a_to_b address aa:aa:aa:aa:aa:aa',
                'ip -n netns_b link set dev b_to_a address cc:cc:cc:cc:cc:cc',
                'ip -n netns_a link set dev a_to_b up',
                'ip -n netns_b link set dev b_to_a up']:
            subprocess.check_call(shlex.split(cmd))

        server = subprocess.Popen(shlex.split(f"ip netns exec netns_a {PYTHON} {sys.argv[0]} server {mode}"))
        client = subprocess.Popen(shlex.split(f"ip netns exec netns_b {PYTHON} {sys.argv[0]} client"))

        client.wait()
        server.wait()
        sys.exit(server.returncode)

    finally:
        subprocess.run(shlex.split("ip netns delete netns_a"))
        subprocess.run(shlex.split("ip netns delete netns_b"))

Fixes: d445516966dc ("net: xdp: support xdp generic on virtual devices")
Reported-by: Stepan Horacek <shoracek@redhat.com>
Suggested-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 82325d3d1371..a7e2e57af63a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4256,14 +4256,14 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 	/* Reinjected packets coming from act_mirred or similar should
 	 * not get XDP generic processing.
 	 */
-	if (skb_cloned(skb) || skb_is_tc_redirected(skb))
+	if (skb_is_tc_redirected(skb))
 		return XDP_PASS;
 
 	/* XDP packets must be linear and must have sufficient headroom
 	 * of XDP_PACKET_HEADROOM bytes. This is the guarantee that also
 	 * native XDP provides, thus we need to do it here as well.
 	 */
-	if (skb_is_nonlinear(skb) ||
+	if (skb_cloned(skb) || skb_is_nonlinear(skb) ||
 	    skb_headroom(skb) < XDP_PACKET_HEADROOM) {
 		int hroom = XDP_PACKET_HEADROOM - skb_headroom(skb);
 		int troom = skb->tail + skb->data_len - skb->end;
-- 
2.20.1


From 5719a648054c9f3b705a5291cb52786bb981c429 Mon Sep 17 00:00:00 2001
From: Firo Yang <firo.yang@suse.com>
Date: Wed, 12 Feb 2020 06:09:17 +0100
Subject: [PATCH 2/6] enic: prevent waking up stopped tx queues over watchdog
 reset

[ Upstream commit 0f90522591fd09dd201065c53ebefdfe3c6b55cb ]

Recent months, our customer reported several kernel crashes all
preceding with following message:
NETDEV WATCHDOG: eth2 (enic): transmit queue 0 timed out
Error message of one of those crashes:
BUG: unable to handle kernel paging request at ffffffffa007e090

After analyzing severl vmcores, I found that most of crashes are
caused by memory corruption. And all the corrupted memory areas
are overwritten by data of network packets. Moreover, I also found
that the tx queues were enabled over watchdog reset.

After going through the source code, I found that in enic_stop(),
the tx queues stopped by netif_tx_disable() could be woken up over
a small time window between netif_tx_disable() and the
napi_disable() by the following code path:
napi_poll->
  enic_poll_msix_wq->
     vnic_cq_service->
        enic_wq_service->
           netif_wake_subqueue(enic->netdev, q_number)->
              test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &txq->state)
In turn, upper netowrk stack could queue skb to ENIC NIC though
enic_hard_start_xmit(). And this might introduce some race condition.

Our customer comfirmed that this kind of kernel crash doesn't occur over
90 days since they applied this patch.

Signed-off-by: Firo Yang <firo.yang@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cisco/enic/enic_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index acb2856936d2..6e2ab10ad2e6 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -2013,10 +2013,10 @@ static int enic_stop(struct net_device *netdev)
 		napi_disable(&enic->napi[i]);
 
 	netif_carrier_off(netdev);
-	netif_tx_disable(netdev);
 	if (vnic_dev_get_intr_mode(enic->vdev) == VNIC_DEV_INTR_MODE_MSIX)
 		for (i = 0; i < enic->wq_count; i++)
 			napi_disable(&enic->napi[enic_cq_wq(enic, i)]);
+	netif_tx_disable(netdev);
 
 	if (!enic_is_dynamic(enic) && !enic_is_sriov_vf(enic))
 		enic_dev_del_station_addr(enic);
-- 
2.20.1


From b4d22c53a8209bac76af833a50ff87b7f93761a7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 10 Feb 2020 11:36:13 -0800
Subject: [PATCH 3/6] net/smc: fix leak of kernel memory to user space

[ Upstream commit 457fed775c97ac2c0cd1672aaf2ff2c8a6235e87 ]

As nlmsg_put() does not clear the memory that is reserved,
it this the caller responsability to make sure all of this
memory will be written, in order to not reveal prior content.

While we are at it, we can provide the socket cookie even
if clsock is not set.

syzbot reported :

BUG: KMSAN: uninit-value in __arch_swab32 arch/x86/include/uapi/asm/swab.h:10 [inline]
BUG: KMSAN: uninit-value in __fswab32 include/uapi/linux/swab.h:59 [inline]
BUG: KMSAN: uninit-value in __swab32p include/uapi/linux/swab.h:179 [inline]
BUG: KMSAN: uninit-value in __be32_to_cpup include/uapi/linux/byteorder/little_endian.h:82 [inline]
BUG: KMSAN: uninit-value in get_unaligned_be32 include/linux/unaligned/access_ok.h:30 [inline]
BUG: KMSAN: uninit-value in ____bpf_skb_load_helper_32 net/core/filter.c:240 [inline]
BUG: KMSAN: uninit-value in ____bpf_skb_load_helper_32_no_cache net/core/filter.c:255 [inline]
BUG: KMSAN: uninit-value in bpf_skb_load_helper_32_no_cache+0x14a/0x390 net/core/filter.c:252
CPU: 1 PID: 5262 Comm: syz-executor.5 Not tainted 5.5.0-rc5-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c9/0x220 lib/dump_stack.c:118
 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:118
 __msan_warning+0x58/0xa0 mm/kmsan/kmsan_instr.c:215
 __arch_swab32 arch/x86/include/uapi/asm/swab.h:10 [inline]
 __fswab32 include/uapi/linux/swab.h:59 [inline]
 __swab32p include/uapi/linux/swab.h:179 [inline]
 __be32_to_cpup include/uapi/linux/byteorder/little_endian.h:82 [inline]
 get_unaligned_be32 include/linux/unaligned/access_ok.h:30 [inline]
 ____bpf_skb_load_helper_32 net/core/filter.c:240 [inline]
 ____bpf_skb_load_helper_32_no_cache net/core/filter.c:255 [inline]
 bpf_skb_load_helper_32_no_cache+0x14a/0x390 net/core/filter.c:252

Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:144 [inline]
 kmsan_internal_poison_shadow+0x66/0xd0 mm/kmsan/kmsan.c:127
 kmsan_kmalloc_large+0x73/0xc0 mm/kmsan/kmsan_hooks.c:128
 kmalloc_large_node_hook mm/slub.c:1406 [inline]
 kmalloc_large_node+0x282/0x2c0 mm/slub.c:3841
 __kmalloc_node_track_caller+0x44b/0x1200 mm/slub.c:4368
 __kmalloc_reserve net/core/skbuff.c:141 [inline]
 __alloc_skb+0x2fd/0xac0 net/core/skbuff.c:209
 alloc_skb include/linux/skbuff.h:1049 [inline]
 netlink_dump+0x44b/0x1ab0 net/netlink/af_netlink.c:2224
 __netlink_dump_start+0xbb2/0xcf0 net/netlink/af_netlink.c:2352
 netlink_dump_start include/linux/netlink.h:233 [inline]
 smc_diag_handler_dump+0x2ba/0x300 net/smc/smc_diag.c:242
 sock_diag_rcv_msg+0x211/0x610 net/core/sock_diag.c:256
 netlink_rcv_skb+0x451/0x650 net/netlink/af_netlink.c:2477
 sock_diag_rcv+0x63/0x80 net/core/sock_diag.c:275
 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
 netlink_unicast+0xf9e/0x1100 net/netlink/af_netlink.c:1328
 netlink_sendmsg+0x1248/0x14d0 net/netlink/af_netlink.c:1917
 sock_sendmsg_nosec net/socket.c:639 [inline]
 sock_sendmsg net/socket.c:659 [inline]
 kernel_sendmsg+0x433/0x440 net/socket.c:679
 sock_no_sendpage+0x235/0x300 net/core/sock.c:2740
 kernel_sendpage net/socket.c:3776 [inline]
 sock_sendpage+0x1e1/0x2c0 net/socket.c:937
 pipe_to_sendpage+0x38c/0x4c0 fs/splice.c:458
 splice_from_pipe_feed fs/splice.c:512 [inline]
 __splice_from_pipe+0x539/0xed0 fs/splice.c:636
 splice_from_pipe fs/splice.c:671 [inline]
 generic_splice_sendpage+0x1d5/0x2d0 fs/splice.c:844
 do_splice_from fs/splice.c:863 [inline]
 do_splice fs/splice.c:1170 [inline]
 __do_sys_splice fs/splice.c:1447 [inline]
 __se_sys_splice+0x2380/0x3350 fs/splice.c:1427
 __x64_sys_splice+0x6e/0x90 fs/splice.c:1427
 do_syscall_64+0xb8/0x160 arch/x86/entry/common.c:296
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: f16a7dd5cf27 ("smc: netlink interface for SMC sockets")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Ursula Braun <ubraun@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/smc_diag.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c
index f38727ecf8b2..e1f64f4ba236 100644
--- a/net/smc/smc_diag.c
+++ b/net/smc/smc_diag.c
@@ -39,16 +39,15 @@ static void smc_diag_msg_common_fill(struct smc_diag_msg *r, struct sock *sk)
 {
 	struct smc_sock *smc = smc_sk(sk);
 
+	memset(r, 0, sizeof(*r));
 	r->diag_family = sk->sk_family;
+	sock_diag_save_cookie(sk, r->id.idiag_cookie);
 	if (!smc->clcsock)
 		return;
 	r->id.idiag_sport = htons(smc->clcsock->sk->sk_num);
 	r->id.idiag_dport = smc->clcsock->sk->sk_dport;
 	r->id.idiag_if = smc->clcsock->sk->sk_bound_dev_if;
-	sock_diag_save_cookie(sk, r->id.idiag_cookie);
 	if (sk->sk_protocol == SMCPROTO_SMC) {
-		memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src));
-		memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst));
 		r->id.idiag_src[0] = smc->clcsock->sk->sk_rcv_saddr;
 		r->id.idiag_dst[0] = smc->clcsock->sk->sk_daddr;
 #if IS_ENABLED(CONFIG_IPV6)
-- 
2.20.1


From cc2e87b3d8e0ce75da29e47c382a84f7ad76807c Mon Sep 17 00:00:00 2001
From: Per Forlin <per.forlin@axis.com>
Date: Thu, 13 Feb 2020 15:37:09 +0100
Subject: [PATCH 4/6] net: dsa: tag_qca: Make sure there is headroom for tag

[ Upstream commit 04fb91243a853dbde216d829c79d9632e52aa8d9 ]

Passing tag size to skb_cow_head will make sure
there is enough headroom for the tag data.
This change does not introduce any overhead in case there
is already available headroom for tag.

Signed-off-by: Per Forlin <perfn@axis.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/tag_qca.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c
index c8a128c9e5e0..70db7c909f74 100644
--- a/net/dsa/tag_qca.c
+++ b/net/dsa/tag_qca.c
@@ -33,7 +33,7 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct dsa_port *dp = dsa_slave_to_port(dev);
 	u16 *phdr, hdr;
 
-	if (skb_cow_head(skb, 0) < 0)
+	if (skb_cow_head(skb, QCA_HDR_LEN) < 0)
 		return NULL;
 
 	skb_push(skb, QCA_HDR_LEN);
-- 
2.20.1


From f90909cb7527c8072e8351b5d38b82c6bb16b9f9 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Tue, 11 Feb 2020 19:33:39 +0100
Subject: [PATCH 5/6] net/sched: matchall: add missing validation of
 TCA_MATCHALL_FLAGS

[ Upstream commit 1afa3cc90f8fb745c777884d79eaa1001d6927a6 ]

unlike other classifiers that can be offloaded (i.e. users can set flags
like 'skip_hw' and 'skip_sw'), 'cls_matchall' doesn't validate the size
of netlink attribute 'TCA_MATCHALL_FLAGS' provided by user: add a proper
entry to mall_policy.

Fixes: b87f7936a932 ("net/sched: Add match-all classifier hw offloading.")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_matchall.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index 039cc86974f4..610a0b728161 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -157,6 +157,7 @@ static void *mall_get(struct tcf_proto *tp, u32 handle)
 static const struct nla_policy mall_policy[TCA_MATCHALL_MAX + 1] = {
 	[TCA_MATCHALL_UNSPEC]		= { .type = NLA_UNSPEC },
 	[TCA_MATCHALL_CLASSID]		= { .type = NLA_U32 },
+	[TCA_MATCHALL_FLAGS]		= { .type = NLA_U32 },
 };
 
 static int mall_set_parms(struct net *net, struct tcf_proto *tp,
-- 
2.20.1


From f3df89cf772ff3b69195a10297b3d97568ca9f58 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Tue, 11 Feb 2020 19:33:40 +0100
Subject: [PATCH 6/6] net/sched: flower: add missing validation of
 TCA_FLOWER_FLAGS

[ Upstream commit e2debf0852c4d66ba1a8bde12869b196094c70a7 ]

unlike other classifiers that can be offloaded (i.e. users can set flags
like 'skip_hw' and 'skip_sw'), 'cls_flower' doesn't validate the size of
netlink attribute 'TCA_FLOWER_FLAGS' provided by user: add a proper entry
to fl_policy.

Fixes: 5b33f48842fa ("net/flower: Introduce hardware offload support")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_flower.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 7394e01c0c9c..5eceeee593cf 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -689,6 +689,7 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = {
 					    .len = 128 / BITS_PER_BYTE },
 	[TCA_FLOWER_KEY_CT_LABELS_MASK]	= { .type = NLA_BINARY,
 					    .len = 128 / BITS_PER_BYTE },
+	[TCA_FLOWER_FLAGS]		= { .type = NLA_U32 },
 };
 
 static const struct nla_policy
-- 
2.20.1


[-- Attachment #3: net_55.mbox --]
[-- Type: Application/Octet-Stream, Size: 16804 bytes --]

From ca7440e7341dad6f36054294777178cdcfbba84c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
Date: Mon, 10 Feb 2020 17:10:46 +0100
Subject: [PATCH 1/6] core: Don't skip generic XDP program execution for cloned
 SKBs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit ad1e03b2b3d4430baaa109b77bc308dc73050de3 ]

The current generic XDP handler skips execution of XDP programs entirely if
an SKB is marked as cloned. This leads to some surprising behaviour, as
packets can end up being cloned in various ways, which will make an XDP
program not see all the traffic on an interface.

This was discovered by a simple test case where an XDP program that always
returns XDP_DROP is installed on a veth device. When combining this with
the Scapy packet sniffer (which uses an AF_PACKET) socket on the sending
side, SKBs reliably end up in the cloned state, causing them to be passed
through to the receiving interface instead of being dropped. A minimal
reproducer script for this is included below.

This patch fixed the issue by simply triggering the existing linearisation
code for cloned SKBs instead of skipping the XDP program execution. This
behaviour is in line with the behaviour of the native XDP implementation
for the veth driver, which will reallocate and copy the SKB data if the SKB
is marked as shared.

Reproducer Python script (requires BCC and Scapy):

from scapy.all import TCP, IP, Ether, sendp, sniff, AsyncSniffer, Raw, UDP
from bcc import BPF
import time, sys, subprocess, shlex

SKB_MODE = (1 << 1)
DRV_MODE = (1 << 2)
PYTHON=sys.executable

def client():
    time.sleep(2)
    # Sniffing on the sender causes skb_cloned() to be set
    s = AsyncSniffer()
    s.start()

    for p in range(10):
        sendp(Ether(dst="aa:aa:aa:aa:aa:aa", src="cc:cc:cc:cc:cc:cc")/IP()/UDP()/Raw("Test"),
              verbose=False)
        time.sleep(0.1)

    s.stop()
    return 0

def server(mode):
    prog = BPF(text="int dummy_drop(struct xdp_md *ctx) {return XDP_DROP;}")
    func = prog.load_func("dummy_drop", BPF.XDP)
    prog.attach_xdp("a_to_b", func, mode)

    time.sleep(1)

    s = sniff(iface="a_to_b", count=10, timeout=15)
    if len(s):
        print(f"Got {len(s)} packets - should have gotten 0")
        return 1
    else:
        print("Got no packets - as expected")
        return 0

if len(sys.argv) < 2:
    print(f"Usage: {sys.argv[0]} <skb|drv>")
    sys.exit(1)

if sys.argv[1] == "client":
    sys.exit(client())
elif sys.argv[1] == "server":
    mode = SKB_MODE if sys.argv[2] == 'skb' else DRV_MODE
    sys.exit(server(mode))
else:
    try:
        mode = sys.argv[1]
        if mode not in ('skb', 'drv'):
            print(f"Usage: {sys.argv[0]} <skb|drv>")
            sys.exit(1)
        print(f"Running in {mode} mode")

        for cmd in [
                'ip netns add netns_a',
                'ip netns add netns_b',
                'ip -n netns_a link add a_to_b type veth peer name b_to_a netns netns_b',
                # Disable ipv6 to make sure there's no address autoconf traffic
                'ip netns exec netns_a sysctl -qw net.ipv6.conf.a_to_b.disable_ipv6=1',
                'ip netns exec netns_b sysctl -qw net.ipv6.conf.b_to_a.disable_ipv6=1',
                'ip -n netns_a link set dev a_to_b address aa:aa:aa:aa:aa:aa',
                'ip -n netns_b link set dev b_to_a address cc:cc:cc:cc:cc:cc',
                'ip -n netns_a link set dev a_to_b up',
                'ip -n netns_b link set dev b_to_a up']:
            subprocess.check_call(shlex.split(cmd))

        server = subprocess.Popen(shlex.split(f"ip netns exec netns_a {PYTHON} {sys.argv[0]} server {mode}"))
        client = subprocess.Popen(shlex.split(f"ip netns exec netns_b {PYTHON} {sys.argv[0]} client"))

        client.wait()
        server.wait()
        sys.exit(server.returncode)

    finally:
        subprocess.run(shlex.split("ip netns delete netns_a"))
        subprocess.run(shlex.split("ip netns delete netns_b"))

Fixes: d445516966dc ("net: xdp: support xdp generic on virtual devices")
Reported-by: Stepan Horacek <shoracek@redhat.com>
Suggested-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 81befd0c2510..466f2e4144b0 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4477,14 +4477,14 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 	/* Reinjected packets coming from act_mirred or similar should
 	 * not get XDP generic processing.
 	 */
-	if (skb_cloned(skb) || skb_is_tc_redirected(skb))
+	if (skb_is_tc_redirected(skb))
 		return XDP_PASS;
 
 	/* XDP packets must be linear and must have sufficient headroom
 	 * of XDP_PACKET_HEADROOM bytes. This is the guarantee that also
 	 * native XDP provides, thus we need to do it here as well.
 	 */
-	if (skb_is_nonlinear(skb) ||
+	if (skb_cloned(skb) || skb_is_nonlinear(skb) ||
 	    skb_headroom(skb) < XDP_PACKET_HEADROOM) {
 		int hroom = XDP_PACKET_HEADROOM - skb_headroom(skb);
 		int troom = skb->tail + skb->data_len - skb->end;
-- 
2.20.1


From 3ed05912fa4fa261c813f81b30b5e684ed43c7bf Mon Sep 17 00:00:00 2001
From: Firo Yang <firo.yang@suse.com>
Date: Wed, 12 Feb 2020 06:09:17 +0100
Subject: [PATCH 2/6] enic: prevent waking up stopped tx queues over watchdog
 reset

[ Upstream commit 0f90522591fd09dd201065c53ebefdfe3c6b55cb ]

Recent months, our customer reported several kernel crashes all
preceding with following message:
NETDEV WATCHDOG: eth2 (enic): transmit queue 0 timed out
Error message of one of those crashes:
BUG: unable to handle kernel paging request at ffffffffa007e090

After analyzing severl vmcores, I found that most of crashes are
caused by memory corruption. And all the corrupted memory areas
are overwritten by data of network packets. Moreover, I also found
that the tx queues were enabled over watchdog reset.

After going through the source code, I found that in enic_stop(),
the tx queues stopped by netif_tx_disable() could be woken up over
a small time window between netif_tx_disable() and the
napi_disable() by the following code path:
napi_poll->
  enic_poll_msix_wq->
     vnic_cq_service->
        enic_wq_service->
           netif_wake_subqueue(enic->netdev, q_number)->
              test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &txq->state)
In turn, upper netowrk stack could queue skb to ENIC NIC though
enic_hard_start_xmit(). And this might introduce some race condition.

Our customer comfirmed that this kind of kernel crash doesn't occur over
90 days since they applied this patch.

Signed-off-by: Firo Yang <firo.yang@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cisco/enic/enic_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index acb2856936d2..6e2ab10ad2e6 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -2013,10 +2013,10 @@ static int enic_stop(struct net_device *netdev)
 		napi_disable(&enic->napi[i]);
 
 	netif_carrier_off(netdev);
-	netif_tx_disable(netdev);
 	if (vnic_dev_get_intr_mode(enic->vdev) == VNIC_DEV_INTR_MODE_MSIX)
 		for (i = 0; i < enic->wq_count; i++)
 			napi_disable(&enic->napi[enic_cq_wq(enic, i)]);
+	netif_tx_disable(netdev);
 
 	if (!enic_is_dynamic(enic) && !enic_is_sriov_vf(enic))
 		enic_dev_del_station_addr(enic);
-- 
2.20.1


From 7397652d2dbace75939313d92b656204531954a0 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 10 Feb 2020 11:36:13 -0800
Subject: [PATCH 3/6] net/smc: fix leak of kernel memory to user space

[ Upstream commit 457fed775c97ac2c0cd1672aaf2ff2c8a6235e87 ]

As nlmsg_put() does not clear the memory that is reserved,
it this the caller responsability to make sure all of this
memory will be written, in order to not reveal prior content.

While we are at it, we can provide the socket cookie even
if clsock is not set.

syzbot reported :

BUG: KMSAN: uninit-value in __arch_swab32 arch/x86/include/uapi/asm/swab.h:10 [inline]
BUG: KMSAN: uninit-value in __fswab32 include/uapi/linux/swab.h:59 [inline]
BUG: KMSAN: uninit-value in __swab32p include/uapi/linux/swab.h:179 [inline]
BUG: KMSAN: uninit-value in __be32_to_cpup include/uapi/linux/byteorder/little_endian.h:82 [inline]
BUG: KMSAN: uninit-value in get_unaligned_be32 include/linux/unaligned/access_ok.h:30 [inline]
BUG: KMSAN: uninit-value in ____bpf_skb_load_helper_32 net/core/filter.c:240 [inline]
BUG: KMSAN: uninit-value in ____bpf_skb_load_helper_32_no_cache net/core/filter.c:255 [inline]
BUG: KMSAN: uninit-value in bpf_skb_load_helper_32_no_cache+0x14a/0x390 net/core/filter.c:252
CPU: 1 PID: 5262 Comm: syz-executor.5 Not tainted 5.5.0-rc5-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c9/0x220 lib/dump_stack.c:118
 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:118
 __msan_warning+0x58/0xa0 mm/kmsan/kmsan_instr.c:215
 __arch_swab32 arch/x86/include/uapi/asm/swab.h:10 [inline]
 __fswab32 include/uapi/linux/swab.h:59 [inline]
 __swab32p include/uapi/linux/swab.h:179 [inline]
 __be32_to_cpup include/uapi/linux/byteorder/little_endian.h:82 [inline]
 get_unaligned_be32 include/linux/unaligned/access_ok.h:30 [inline]
 ____bpf_skb_load_helper_32 net/core/filter.c:240 [inline]
 ____bpf_skb_load_helper_32_no_cache net/core/filter.c:255 [inline]
 bpf_skb_load_helper_32_no_cache+0x14a/0x390 net/core/filter.c:252

Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:144 [inline]
 kmsan_internal_poison_shadow+0x66/0xd0 mm/kmsan/kmsan.c:127
 kmsan_kmalloc_large+0x73/0xc0 mm/kmsan/kmsan_hooks.c:128
 kmalloc_large_node_hook mm/slub.c:1406 [inline]
 kmalloc_large_node+0x282/0x2c0 mm/slub.c:3841
 __kmalloc_node_track_caller+0x44b/0x1200 mm/slub.c:4368
 __kmalloc_reserve net/core/skbuff.c:141 [inline]
 __alloc_skb+0x2fd/0xac0 net/core/skbuff.c:209
 alloc_skb include/linux/skbuff.h:1049 [inline]
 netlink_dump+0x44b/0x1ab0 net/netlink/af_netlink.c:2224
 __netlink_dump_start+0xbb2/0xcf0 net/netlink/af_netlink.c:2352
 netlink_dump_start include/linux/netlink.h:233 [inline]
 smc_diag_handler_dump+0x2ba/0x300 net/smc/smc_diag.c:242
 sock_diag_rcv_msg+0x211/0x610 net/core/sock_diag.c:256
 netlink_rcv_skb+0x451/0x650 net/netlink/af_netlink.c:2477
 sock_diag_rcv+0x63/0x80 net/core/sock_diag.c:275
 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
 netlink_unicast+0xf9e/0x1100 net/netlink/af_netlink.c:1328
 netlink_sendmsg+0x1248/0x14d0 net/netlink/af_netlink.c:1917
 sock_sendmsg_nosec net/socket.c:639 [inline]
 sock_sendmsg net/socket.c:659 [inline]
 kernel_sendmsg+0x433/0x440 net/socket.c:679
 sock_no_sendpage+0x235/0x300 net/core/sock.c:2740
 kernel_sendpage net/socket.c:3776 [inline]
 sock_sendpage+0x1e1/0x2c0 net/socket.c:937
 pipe_to_sendpage+0x38c/0x4c0 fs/splice.c:458
 splice_from_pipe_feed fs/splice.c:512 [inline]
 __splice_from_pipe+0x539/0xed0 fs/splice.c:636
 splice_from_pipe fs/splice.c:671 [inline]
 generic_splice_sendpage+0x1d5/0x2d0 fs/splice.c:844
 do_splice_from fs/splice.c:863 [inline]
 do_splice fs/splice.c:1170 [inline]
 __do_sys_splice fs/splice.c:1447 [inline]
 __se_sys_splice+0x2380/0x3350 fs/splice.c:1427
 __x64_sys_splice+0x6e/0x90 fs/splice.c:1427
 do_syscall_64+0xb8/0x160 arch/x86/entry/common.c:296
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: f16a7dd5cf27 ("smc: netlink interface for SMC sockets")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Ursula Braun <ubraun@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/smc_diag.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c
index f38727ecf8b2..e1f64f4ba236 100644
--- a/net/smc/smc_diag.c
+++ b/net/smc/smc_diag.c
@@ -39,16 +39,15 @@ static void smc_diag_msg_common_fill(struct smc_diag_msg *r, struct sock *sk)
 {
 	struct smc_sock *smc = smc_sk(sk);
 
+	memset(r, 0, sizeof(*r));
 	r->diag_family = sk->sk_family;
+	sock_diag_save_cookie(sk, r->id.idiag_cookie);
 	if (!smc->clcsock)
 		return;
 	r->id.idiag_sport = htons(smc->clcsock->sk->sk_num);
 	r->id.idiag_dport = smc->clcsock->sk->sk_dport;
 	r->id.idiag_if = smc->clcsock->sk->sk_bound_dev_if;
-	sock_diag_save_cookie(sk, r->id.idiag_cookie);
 	if (sk->sk_protocol == SMCPROTO_SMC) {
-		memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src));
-		memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst));
 		r->id.idiag_src[0] = smc->clcsock->sk->sk_rcv_saddr;
 		r->id.idiag_dst[0] = smc->clcsock->sk->sk_daddr;
 #if IS_ENABLED(CONFIG_IPV6)
-- 
2.20.1


From 9abe31bc7faa463b971f161f7f4b141b7a06b7ee Mon Sep 17 00:00:00 2001
From: Per Forlin <per.forlin@axis.com>
Date: Thu, 13 Feb 2020 15:37:09 +0100
Subject: [PATCH 4/6] net: dsa: tag_qca: Make sure there is headroom for tag

[ Upstream commit 04fb91243a853dbde216d829c79d9632e52aa8d9 ]

Passing tag size to skb_cow_head will make sure
there is enough headroom for the tag data.
This change does not introduce any overhead in case there
is already available headroom for tag.

Signed-off-by: Per Forlin <perfn@axis.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/tag_qca.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c
index c8a128c9e5e0..70db7c909f74 100644
--- a/net/dsa/tag_qca.c
+++ b/net/dsa/tag_qca.c
@@ -33,7 +33,7 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct dsa_port *dp = dsa_slave_to_port(dev);
 	u16 *phdr, hdr;
 
-	if (skb_cow_head(skb, 0) < 0)
+	if (skb_cow_head(skb, QCA_HDR_LEN) < 0)
 		return NULL;
 
 	skb_push(skb, QCA_HDR_LEN);
-- 
2.20.1


From 3e423df4d9ccd3d1afa3e111627740aaba0bc3ec Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Tue, 11 Feb 2020 19:33:39 +0100
Subject: [PATCH 5/6] net/sched: matchall: add missing validation of
 TCA_MATCHALL_FLAGS

[ Upstream commit 1afa3cc90f8fb745c777884d79eaa1001d6927a6 ]

unlike other classifiers that can be offloaded (i.e. users can set flags
like 'skip_hw' and 'skip_sw'), 'cls_matchall' doesn't validate the size
of netlink attribute 'TCA_MATCHALL_FLAGS' provided by user: add a proper
entry to mall_policy.

Fixes: b87f7936a932 ("net/sched: Add match-all classifier hw offloading.")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_matchall.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index 039cc86974f4..610a0b728161 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -157,6 +157,7 @@ static void *mall_get(struct tcf_proto *tp, u32 handle)
 static const struct nla_policy mall_policy[TCA_MATCHALL_MAX + 1] = {
 	[TCA_MATCHALL_UNSPEC]		= { .type = NLA_UNSPEC },
 	[TCA_MATCHALL_CLASSID]		= { .type = NLA_U32 },
+	[TCA_MATCHALL_FLAGS]		= { .type = NLA_U32 },
 };
 
 static int mall_set_parms(struct net *net, struct tcf_proto *tp,
-- 
2.20.1


From bf0f66d5f8e2dac8fa1ddad63b239cce60dbb447 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Tue, 11 Feb 2020 19:33:40 +0100
Subject: [PATCH 6/6] net/sched: flower: add missing validation of
 TCA_FLOWER_FLAGS

[ Upstream commit e2debf0852c4d66ba1a8bde12869b196094c70a7 ]

unlike other classifiers that can be offloaded (i.e. users can set flags
like 'skip_hw' and 'skip_sw'), 'cls_flower' doesn't validate the size of
netlink attribute 'TCA_FLOWER_FLAGS' provided by user: add a proper entry
to fl_policy.

Fixes: 5b33f48842fa ("net/flower: Introduce hardware offload support")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_flower.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index f9c0d1e8d380..7e54d2ab5254 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -691,6 +691,7 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = {
 					    .len = 128 / BITS_PER_BYTE },
 	[TCA_FLOWER_KEY_CT_LABELS_MASK]	= { .type = NLA_BINARY,
 					    .len = 128 / BITS_PER_BYTE },
+	[TCA_FLOWER_FLAGS]		= { .type = NLA_U32 },
 };
 
 static const struct nla_policy
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Tue, Feb 18, 2020 at 03:41:07PM -0800, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v5.4 and
> v5.5 -stable, respectively.

Now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 105 bytes --]


Please queue up the following networking bug fixes for
v5.4 and v5.5 -stable, respectively.

Thank you.

[-- Attachment #2: net_54.mbox --]
[-- Type: Application/Octet-Stream, Size: 57162 bytes --]

From 2ac3f2f8811b5232d8c65eef8d1276c0c285bbf8 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 14 Feb 2020 15:26:19 -0800
Subject: [PATCH 01/19] net: dsa: b53: Ensure the default VID is untagged

[ Upstream commit d965a5432d4c3e6b9c3d2bc1d4a800013bbf76f6 ]

We need to ensure that the default VID is untagged otherwise the switch
will be sending tagged frames and the results can be problematic. This
is especially true with b53 switches that use VID 0 as their default
VLAN since VID 0 has a special meaning.

Fixes: fea83353177a ("net: dsa: b53: Fix default VLAN ID")
Fixes: 061f6a505ac3 ("net: dsa: Add ndo_vlan_rx_{add, kill}_vid implementation")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/b53/b53_common.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 7ed667b304d1..d618650533b6 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -1353,6 +1353,9 @@ void b53_vlan_add(struct dsa_switch *ds, int port,
 
 		b53_get_vlan_entry(dev, vid, vl);
 
+		if (vid == 0 && vid == b53_default_pvid(dev))
+			untagged = true;
+
 		vl->members |= BIT(port);
 		if (untagged && !dsa_is_cpu_port(ds, port))
 			vl->untag |= BIT(port);
-- 
2.20.1


From f66826bb432b05cc3fbe823f42f38346aab4a4a2 Mon Sep 17 00:00:00 2001
From: Jethro Beekman <jethro@fortanix.com>
Date: Wed, 12 Feb 2020 16:43:41 +0100
Subject: [PATCH 02/19] net: fib_rules: Correctly set table field when table
 number exceeds 8 bits

[ Upstream commit 540e585a79e9d643ede077b73bcc7aa2d7b4d919 ]

In 709772e6e06564ed94ba740de70185ac3d792773, RT_TABLE_COMPAT was added to
allow legacy software to deal with routing table numbers >= 256, but the
same change to FIB rule queries was overlooked.

Signed-off-by: Jethro Beekman <jethro@fortanix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/fib_rules.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index dd220ce7ca7a..bb11fc87bbae 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -967,7 +967,7 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule,
 
 	frh = nlmsg_data(nlh);
 	frh->family = ops->family;
-	frh->table = rule->table;
+	frh->table = rule->table < 256 ? rule->table : RT_TABLE_COMPAT;
 	if (nla_put_u32(skb, FRA_TABLE, rule->table))
 		goto nla_put_failure;
 	if (nla_put_u32(skb, FRA_SUPPRESS_PREFIXLEN, rule->suppress_prefixlen))
-- 
2.20.1


From 0cea651b9f8e374e03c237d6976d6382c95a4eeb Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Wed, 12 Feb 2020 17:45:38 +0100
Subject: [PATCH 03/19] net: macb: ensure interface is not suspended on
 at91rm9200

[ Upstream commit e6a41c23df0d5da01540d2abef41591589c0b4be ]

Because of autosuspend, at91ether_start is called with clocks disabled.
Ensure that pm_runtime doesn't suspend the interface as soon as it is
opened as there is no pm_runtime support is the other relevant parts of the
platform support for at91rm9200.

Fixes: d54f89af6cc4 ("net: macb: Add pm runtime support")
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Reviewed-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Acked-by: Nicolas Ferre <nicolas.ferre@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 95a94507cec1..234c13ebbc41 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -3690,6 +3690,10 @@ static int at91ether_open(struct net_device *dev)
 	u32 ctl;
 	int ret;
 
+	ret = pm_runtime_get_sync(&lp->pdev->dev);
+	if (ret < 0)
+		return ret;
+
 	/* Clear internal statistics */
 	ctl = macb_readl(lp, NCR);
 	macb_writel(lp, NCR, ctl | MACB_BIT(CLRSTAT));
@@ -3750,7 +3754,7 @@ static int at91ether_close(struct net_device *dev)
 			  q->rx_buffers, q->rx_buffers_dma);
 	q->rx_buffers = NULL;
 
-	return 0;
+	return pm_runtime_put(&lp->pdev->dev);
 }
 
 /* Transmit packet */
-- 
2.20.1


From 266a414cf4343f4c430559f5c465109bc6103cd9 Mon Sep 17 00:00:00 2001
From: Horatiu Vultur <horatiu.vultur@microchip.com>
Date: Mon, 17 Feb 2020 09:31:33 +0100
Subject: [PATCH 04/19] net: mscc: fix in frame extraction

[ Upstream commit a81541041ceb55bcec9a8bb8ad3482263f0a205a ]

Each extracted frame on Ocelot has an IFH. The frame and IFH are extracted
by reading chuncks of 4 bytes from a register.

In case the IFH and frames were read corretly it would try to read the next
frame. In case there are no more frames in the queue, it checks if there
were any previous errors and in that case clear the queue. But this check
will always succeed also when there are no errors. Because when extracting
the IFH the error is checked against 4(number of bytes read) and then the
error is set only if the extraction of the frame failed. So in a happy case
where there are no errors the err variable is still 4. So it could be
a case where after the check that there are no more frames in the queue, a
frame will arrive in the queue but because the error is not reseted, it
would try to flush the queue. So the frame will be lost.

The fix consist in resetting the error after reading the IFH.

Signed-off-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Acked-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot_board.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c
index aac115136720..337156232501 100644
--- a/drivers/net/ethernet/mscc/ocelot_board.c
+++ b/drivers/net/ethernet/mscc/ocelot_board.c
@@ -112,6 +112,14 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg)
 		if (err != 4)
 			break;
 
+		/* At this point the IFH was read correctly, so it is safe to
+		 * presume that there is no error. The err needs to be reset
+		 * otherwise a frame could come in CPU queue between the while
+		 * condition and the check for error later on. And in that case
+		 * the new frame is just removed and not processed.
+		 */
+		err = 0;
+
 		ocelot_parse_ifh(ifh, &info);
 
 		dev = ocelot->ports[info.port]->dev;
-- 
2.20.1


From 400724e93c8bb62e46d61674b3e3500c1e1f338a Mon Sep 17 00:00:00 2001
From: Arun Parameswaran <arun.parameswaran@broadcom.com>
Date: Fri, 14 Feb 2020 13:47:46 -0800
Subject: [PATCH 05/19] net: phy: restore mdio regs in the iproc mdio driver

The mii management register in iproc mdio block
does not have a retention register so it is lost on suspend.
Save and restore value of register while resuming from suspend.

Fixes: bb1a619735b4 ("net: phy: Initialize mdio clock at probe function")
Signed-off-by: Arun Parameswaran <arun.parameswaran@broadcom.com>
Signed-off-by: Scott Branden <scott.branden@broadcom.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mdio-bcm-iproc.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/drivers/net/phy/mdio-bcm-iproc.c b/drivers/net/phy/mdio-bcm-iproc.c
index 7e9975d25066..f1ded03f0229 100644
--- a/drivers/net/phy/mdio-bcm-iproc.c
+++ b/drivers/net/phy/mdio-bcm-iproc.c
@@ -178,6 +178,23 @@ static int iproc_mdio_remove(struct platform_device *pdev)
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
+int iproc_mdio_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct iproc_mdio_priv *priv = platform_get_drvdata(pdev);
+
+	/* restore the mii clock configuration */
+	iproc_mdio_config_clk(priv->base);
+
+	return 0;
+}
+
+static const struct dev_pm_ops iproc_mdio_pm_ops = {
+	.resume = iproc_mdio_resume
+};
+#endif /* CONFIG_PM_SLEEP */
+
 static const struct of_device_id iproc_mdio_of_match[] = {
 	{ .compatible = "brcm,iproc-mdio", },
 	{ /* sentinel */ },
@@ -188,6 +205,9 @@ static struct platform_driver iproc_mdio_driver = {
 	.driver = {
 		.name = "iproc-mdio",
 		.of_match_table = iproc_mdio_of_match,
+#ifdef CONFIG_PM_SLEEP
+		.pm = &iproc_mdio_pm_ops,
+#endif
 	},
 	.probe = iproc_mdio_probe,
 	.remove = iproc_mdio_remove,
-- 
2.20.1


From cb46917323c336cfab21ca9a820986d054b676ca Mon Sep 17 00:00:00 2001
From: Jason Baron <jbaron@akamai.com>
Date: Mon, 17 Feb 2020 15:38:09 -0500
Subject: [PATCH 06/19] net: sched: correct flower port blocking

[ Upstream commit 8a9093c79863b58cc2f9874d7ae788f0d622a596 ]

tc flower rules that are based on src or dst port blocking are sometimes
ineffective due to uninitialized stack data. __skb_flow_dissect() extracts
ports from the skb for tc flower to match against. However, the port
dissection is not done when when the FLOW_DIS_IS_FRAGMENT bit is set in
key_control->flags. All callers of __skb_flow_dissect(), zero-out the
key_control field except for fl_classify() as used by the flower
classifier. Thus, the FLOW_DIS_IS_FRAGMENT may be set on entry to
__skb_flow_dissect(), since key_control is allocated on the stack
and may not be initialized.

Since key_basic and key_control are present for all flow keys, let's
make sure they are initialized.

Fixes: 62230715fd24 ("flow_dissector: do not dissect l4 ports for fragments")
Co-developed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Jason Baron <jbaron@akamai.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow_dissector.h | 9 +++++++++
 net/sched/cls_flower.c       | 1 +
 2 files changed, 10 insertions(+)

diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index e5fc8db1f783..78f6437cbc3a 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -5,6 +5,7 @@
 #include <linux/types.h>
 #include <linux/in6.h>
 #include <linux/siphash.h>
+#include <linux/string.h>
 #include <uapi/linux/if_ether.h>
 
 /**
@@ -338,4 +339,12 @@ struct bpf_flow_dissector {
 	void			*data_end;
 };
 
+static inline void
+flow_dissector_init_keys(struct flow_dissector_key_control *key_control,
+			 struct flow_dissector_key_basic *key_basic)
+{
+	memset(key_control, 0, sizeof(*key_control));
+	memset(key_basic, 0, sizeof(*key_basic));
+}
+
 #endif
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 5eceeee593cf..1d270540e74d 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -303,6 +303,7 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 	struct cls_fl_filter *f;
 
 	list_for_each_entry_rcu(mask, &head->masks, list) {
+		flow_dissector_init_keys(&skb_key.control, &skb_key.basic);
 		fl_clear_masked_range(&skb_key, mask);
 
 		skb_flow_dissect_meta(skb, &mask->dissector, &skb_key);
-- 
2.20.1


From 671090f053b5efebb121aee1210a0b4ca6dd9343 Mon Sep 17 00:00:00 2001
From: Rohit Maheshwari <rohitm@chelsio.com>
Date: Wed, 19 Feb 2020 09:40:22 +0530
Subject: [PATCH 07/19] net/tls: Fix to avoid gettig invalid tls record

[ Upstream commit 06f5201c6392f998a49ca9c9173e2930c8eb51d8 ]

Current code doesn't check if tcp sequence number is starting from (/after)
1st record's start sequnce number. It only checks if seq number is before
1st record's end sequnce number. This problem will always be a possibility
in re-transmit case. If a record which belongs to a requested seq number is
already deleted, tls_get_record will start looking into list and as per the
check it will look if seq number is before the end seq of 1st record, which
will always be true and will return 1st record always, it should in fact
return NULL.
As part of the fix, start looking each record only if the sequence number
lies in the list else return NULL.
There is one more check added, driver look for the start marker record to
handle tcp packets which are before the tls offload start sequence number,
hence return 1st record if the record is tls start marker and seq number is
before the 1st record's starting sequence number.

Fixes: e8f69799810c ("net/tls: Add generic NIC offload infrastructure")
Signed-off-by: Rohit Maheshwari <rohitm@chelsio.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_device.c | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 3f5209e2d4ee..1adeb1c0473b 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -581,7 +581,7 @@ struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context,
 				       u32 seq, u64 *p_record_sn)
 {
 	u64 record_sn = context->hint_record_sn;
-	struct tls_record_info *info;
+	struct tls_record_info *info, *last;
 
 	info = context->retransmit_hint;
 	if (!info ||
@@ -593,6 +593,24 @@ struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context,
 						struct tls_record_info, list);
 		if (!info)
 			return NULL;
+		/* send the start_marker record if seq number is before the
+		 * tls offload start marker sequence number. This record is
+		 * required to handle TCP packets which are before TLS offload
+		 * started.
+		 *  And if it's not start marker, look if this seq number
+		 * belongs to the list.
+		 */
+		if (likely(!tls_record_is_start_marker(info))) {
+			/* we have the first record, get the last record to see
+			 * if this seq number belongs to the list.
+			 */
+			last = list_last_entry(&context->records_list,
+					       struct tls_record_info, list);
+
+			if (!between(seq, tls_record_start_seq(info),
+				     last->end_seq))
+				return NULL;
+		}
 		record_sn = context->unacked_record_sn;
 	}
 
-- 
2.20.1


From 3129cc92a4bad81c12abd812fbedb2b5bee731c4 Mon Sep 17 00:00:00 2001
From: Dmitry Osipenko <digetx@gmail.com>
Date: Wed, 19 Feb 2020 18:01:22 +0300
Subject: [PATCH 08/19] nfc: pn544: Fix occasional HW initialization failure

[ Upstream commit c3331d2fe3fd4d5e321f2467d01f72de7edfb5d0 ]

The PN544 driver checks the "enable" polarity during of driver's probe and
it's doing that by turning ON and OFF NFC with different polarities until
enabling succeeds. It takes some time for the hardware to power-down, and
thus, to deassert the IRQ that is raised by turning ON the hardware.
Since the delay after last power-down of the polarity-checking process is
missed in the code, the interrupt may trigger immediately after installing
the IRQ handler (right after the checking is done), which results in IRQ
handler trying to touch the disabled HW and ends with marking NFC as
'DEAD' during of the driver's probe:

  pn544_hci_i2c 1-002a: NFC: nfc_en polarity : active high
  pn544_hci_i2c 1-002a: NFC: invalid len byte
  shdlc: llc_shdlc_recv_frame: NULL Frame -> link is dead

This patch fixes the occasional NFC initialization failure on Nexus 7
device.

Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/nfc/pn544/i2c.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/nfc/pn544/i2c.c b/drivers/nfc/pn544/i2c.c
index 720c89d6066e..4ac8cb262559 100644
--- a/drivers/nfc/pn544/i2c.c
+++ b/drivers/nfc/pn544/i2c.c
@@ -225,6 +225,7 @@ static void pn544_hci_i2c_platform_init(struct pn544_i2c_phy *phy)
 
 out:
 	gpiod_set_value_cansleep(phy->gpiod_en, !phy->en_polarity);
+	usleep_range(10000, 15000);
 }
 
 static void pn544_hci_i2c_enable_mode(struct pn544_i2c_phy *phy, int run_mode)
-- 
2.20.1


From 4087fa456bf2a1eca7dd47240a3c54ea7f82eec8 Mon Sep 17 00:00:00 2001
From: Michal Kalderon <michal.kalderon@marvell.com>
Date: Mon, 17 Feb 2020 13:37:18 +0200
Subject: [PATCH 09/19] qede: Fix race between rdma destroy workqueue and link
 change event

[ Upstream commit af6565adb02d3129d3fae4d9d5da945abaf4417a ]

If an event is added while the rdma workqueue is being destroyed
it could lead to several races, list corruption, null pointer
dereference during queue_work or init_queue.
This fixes the race between the two flows which can occur during
shutdown.

A kref object and a completion object are added to the rdma_dev
structure, these are initialized before the workqueue is created.
The refcnt is used to indicate work is being added to the
workqueue and ensures the cleanup flow won't start while we're in
the middle of adding the event.
Once the work is added, the refcnt is decreased and the cleanup flow
is safe to run.

Fixes: cee9fbd8e2e ("qede: Add qedr framework")
Signed-off-by: Ariel Elior <ariel.elior@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qede/qede.h      |  2 ++
 drivers/net/ethernet/qlogic/qede/qede_rdma.c | 29 +++++++++++++++++++-
 2 files changed, 30 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index c303a92d5b06..1f27f9866b80 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -163,6 +163,8 @@ struct qede_rdma_dev {
 	struct list_head entry;
 	struct list_head rdma_event_list;
 	struct workqueue_struct *rdma_wq;
+	struct kref refcnt;
+	struct completion event_comp;
 	bool exp_recovery;
 };
 
diff --git a/drivers/net/ethernet/qlogic/qede/qede_rdma.c b/drivers/net/ethernet/qlogic/qede/qede_rdma.c
index ffabc2d2f082..2d873ae8a234 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_rdma.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_rdma.c
@@ -59,6 +59,9 @@ static void _qede_rdma_dev_add(struct qede_dev *edev)
 static int qede_rdma_create_wq(struct qede_dev *edev)
 {
 	INIT_LIST_HEAD(&edev->rdma_info.rdma_event_list);
+	kref_init(&edev->rdma_info.refcnt);
+	init_completion(&edev->rdma_info.event_comp);
+
 	edev->rdma_info.rdma_wq = create_singlethread_workqueue("rdma_wq");
 	if (!edev->rdma_info.rdma_wq) {
 		DP_NOTICE(edev, "qedr: Could not create workqueue\n");
@@ -83,8 +86,23 @@ static void qede_rdma_cleanup_event(struct qede_dev *edev)
 	}
 }
 
+static void qede_rdma_complete_event(struct kref *ref)
+{
+	struct qede_rdma_dev *rdma_dev =
+		container_of(ref, struct qede_rdma_dev, refcnt);
+
+	/* no more events will be added after this */
+	complete(&rdma_dev->event_comp);
+}
+
 static void qede_rdma_destroy_wq(struct qede_dev *edev)
 {
+	/* Avoid race with add_event flow, make sure it finishes before
+	 * we start accessing the list and cleaning up the work
+	 */
+	kref_put(&edev->rdma_info.refcnt, qede_rdma_complete_event);
+	wait_for_completion(&edev->rdma_info.event_comp);
+
 	qede_rdma_cleanup_event(edev);
 	destroy_workqueue(edev->rdma_info.rdma_wq);
 }
@@ -310,15 +328,24 @@ static void qede_rdma_add_event(struct qede_dev *edev,
 	if (!edev->rdma_info.qedr_dev)
 		return;
 
+	/* We don't want the cleanup flow to start while we're allocating and
+	 * scheduling the work
+	 */
+	if (!kref_get_unless_zero(&edev->rdma_info.refcnt))
+		return; /* already being destroyed */
+
 	event_node = qede_rdma_get_free_event_node(edev);
 	if (!event_node)
-		return;
+		goto out;
 
 	event_node->event = event;
 	event_node->ptr = edev;
 
 	INIT_WORK(&event_node->work, qede_rdma_handle_event);
 	queue_work(edev->rdma_info.rdma_wq, &event_node->work);
+
+out:
+	kref_put(&edev->rdma_info.refcnt, qede_rdma_complete_event);
 }
 
 void qede_rdma_dev_event_open(struct qede_dev *edev)
-- 
2.20.1


From 931376d5d0aef6af1c1b8e05caa6d734968ab768 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 18 Feb 2020 18:15:44 +0100
Subject: [PATCH 10/19] Revert "net: dev: introduce support for sch BYPASS for
 lockless qdisc"

[ Upstream commit 379349e9bc3b42b8b2f8f7a03f64a97623fff323 ]

This reverts commit ba27b4cdaaa66561aaedb2101876e563738d36fe

Ahmed reported ouf-of-order issues bisected to commit ba27b4cdaaa6
("net: dev: introduce support for sch BYPASS for lockless qdisc").
I can't find any working solution other than a plain revert.

This will introduce some minor performance regressions for
pfifo_fast qdisc. I plan to address them in net-next with more
indirect call wrapper boilerplate for qdiscs.

Reported-by: Ahmad Fatoum <a.fatoum@pengutronix.de>
Fixes: ba27b4cdaaa6 ("net: dev: introduce support for sch BYPASS for lockless qdisc")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 22 ++--------------------
 1 file changed, 2 insertions(+), 20 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index a7e2e57af63a..c5db02fb1665 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3386,26 +3386,8 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 	qdisc_calculate_pkt_len(skb, q);
 
 	if (q->flags & TCQ_F_NOLOCK) {
-		if ((q->flags & TCQ_F_CAN_BYPASS) && READ_ONCE(q->empty) &&
-		    qdisc_run_begin(q)) {
-			if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED,
-					      &q->state))) {
-				__qdisc_drop(skb, &to_free);
-				rc = NET_XMIT_DROP;
-				goto end_run;
-			}
-			qdisc_bstats_cpu_update(q, skb);
-
-			rc = NET_XMIT_SUCCESS;
-			if (sch_direct_xmit(skb, q, dev, txq, NULL, true))
-				__qdisc_run(q);
-
-end_run:
-			qdisc_run_end(q);
-		} else {
-			rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
-			qdisc_run(q);
-		}
+		rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
+		qdisc_run(q);
 
 		if (unlikely(to_free))
 			kfree_skb_list(to_free);
-- 
2.20.1


From 0fda5a7657c8ae54bf1abdcc964142fa28d84f89 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 19 Feb 2020 14:16:32 -0500
Subject: [PATCH 11/19] udp: rehash on disconnect

[ Upstream commit 303d0403b8c25e994e4a6e45389e173cf8706fb5 ]

As of the below commit, udp sockets bound to a specific address can
coexist with one bound to the any addr for the same port.

The commit also phased out the use of socket hashing based only on
port (hslot), in favor of always hashing on {addr, port} (hslot2).

The change broke the following behavior with disconnect (AF_UNSPEC):

    server binds to 0.0.0.0:1337
    server connects to 127.0.0.1:80
    server disconnects
    client connects to 127.0.0.1:1337
    client sends "hello"
    server reads "hello"	// times out, packet did not find sk

On connect the server acquires a specific source addr suitable for
routing to its destination. On disconnect it reverts to the any addr.

The connect call triggers a rehash to a different hslot2. On
disconnect, add the same to return to the original hslot2.

Skip this step if the socket is going to be unhashed completely.

Fixes: 4cdeeee9252a ("net: udp: prefer listeners bound to an address")
Reported-by: Pavel Roskin <plroskin@gmail.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 7ae7065758bd..f3b7cb725c1b 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1856,8 +1856,12 @@ int __udp_disconnect(struct sock *sk, int flags)
 	inet->inet_dport = 0;
 	sock_rps_reset_rxhash(sk);
 	sk->sk_bound_dev_if = 0;
-	if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
+	if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) {
 		inet_reset_saddr(sk);
+		if (sk->sk_prot->rehash &&
+		    (sk->sk_userlocks & SOCK_BINDPORT_LOCK))
+			sk->sk_prot->rehash(sk);
+	}
 
 	if (!(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) {
 		sk->sk_prot->unhash(sk);
-- 
2.20.1


From 5ff23812d40ba37dcb7e0dd6a9650fc68ffdc714 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 18 Feb 2020 12:07:53 +0800
Subject: [PATCH 12/19] sctp: move the format error check out of
 __sctp_sf_do_9_1_abort

[ Upstream commit 245709ec8be89af46ea7ef0444c9c80913999d99 ]

When T2 timer is to be stopped, the asoc should also be deleted,
otherwise, there will be no chance to call sctp_association_free
and the asoc could last in memory forever.

However, in sctp_sf_shutdown_sent_abort(), after adding the cmd
SCTP_CMD_TIMER_STOP for T2 timer, it may return error due to the
format error from __sctp_sf_do_9_1_abort() and miss adding
SCTP_CMD_ASSOC_FAILED where the asoc will be deleted.

This patch is to fix it by moving the format error check out of
__sctp_sf_do_9_1_abort(), and do it before adding the cmd
SCTP_CMD_TIMER_STOP for T2 timer.

Thanks Hangbin for reporting this issue by the fuzz testing.

v1->v2:
  - improve the comment in the code as Marcelo's suggestion.

Fixes: 96ca468b86b0 ("sctp: check invalid value of length parameter in error cause")
Reported-by: Hangbin Liu <liuhangbin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sm_statefuns.c | 29 ++++++++++++++++++++---------
 1 file changed, 20 insertions(+), 9 deletions(-)

diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 4ab8208a2dd4..c6d83a64eac3 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -170,6 +170,16 @@ static inline bool sctp_chunk_length_valid(struct sctp_chunk *chunk,
 	return true;
 }
 
+/* Check for format error in an ABORT chunk */
+static inline bool sctp_err_chunk_valid(struct sctp_chunk *chunk)
+{
+	struct sctp_errhdr *err;
+
+	sctp_walk_errors(err, chunk->chunk_hdr);
+
+	return (void *)err == (void *)chunk->chunk_end;
+}
+
 /**********************************************************
  * These are the state functions for handling chunk events.
  **********************************************************/
@@ -2255,6 +2265,9 @@ enum sctp_disposition sctp_sf_shutdown_pending_abort(
 		    sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest))
 		return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands);
 
+	if (!sctp_err_chunk_valid(chunk))
+		return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
 	return __sctp_sf_do_9_1_abort(net, ep, asoc, type, arg, commands);
 }
 
@@ -2298,6 +2311,9 @@ enum sctp_disposition sctp_sf_shutdown_sent_abort(
 		    sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest))
 		return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands);
 
+	if (!sctp_err_chunk_valid(chunk))
+		return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
 	/* Stop the T2-shutdown timer. */
 	sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP,
 			SCTP_TO(SCTP_EVENT_TIMEOUT_T2_SHUTDOWN));
@@ -2565,6 +2581,9 @@ enum sctp_disposition sctp_sf_do_9_1_abort(
 		    sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest))
 		return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands);
 
+	if (!sctp_err_chunk_valid(chunk))
+		return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
 	return __sctp_sf_do_9_1_abort(net, ep, asoc, type, arg, commands);
 }
 
@@ -2582,16 +2601,8 @@ static enum sctp_disposition __sctp_sf_do_9_1_abort(
 
 	/* See if we have an error cause code in the chunk.  */
 	len = ntohs(chunk->chunk_hdr->length);
-	if (len >= sizeof(struct sctp_chunkhdr) + sizeof(struct sctp_errhdr)) {
-		struct sctp_errhdr *err;
-
-		sctp_walk_errors(err, chunk->chunk_hdr);
-		if ((void *)err != (void *)chunk->chunk_end)
-			return sctp_sf_pdiscard(net, ep, asoc, type, arg,
-						commands);
-
+	if (len >= sizeof(struct sctp_chunkhdr) + sizeof(struct sctp_errhdr))
 		error = ((struct sctp_errhdr *)chunk->skb->data)->cause;
-	}
 
 	sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ECONNRESET));
 	/* ASSOC_FAILED will DELETE_TCB. */
-- 
2.20.1


From 83fc9917f9932b081afd3a39bf5fb5f5af64c283 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Thu, 20 Feb 2020 17:26:34 -0500
Subject: [PATCH 13/19] bnxt_en: Improve device shutdown method.

[ Upstream commit 5567ae4a8d569d996d0d88d0eceb76205e4c7ce5 ]

Especially when bnxt_shutdown() is called during kexec, we need to
disable MSIX and disable Bus Master to completely quiesce the device.
Make these 2 calls unconditionally in the shutdown method.

Fixes: c20dc142dd7b ("bnxt_en: Disable bus master during PCI shutdown and driver unload.")
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 68618891b0e4..e03e610dd183 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -11908,10 +11908,10 @@ static void bnxt_shutdown(struct pci_dev *pdev)
 		dev_close(dev);
 
 	bnxt_ulp_shutdown(bp);
+	bnxt_clear_int_mode(bp);
+	pci_disable_device(pdev);
 
 	if (system_state == SYSTEM_POWER_OFF) {
-		bnxt_clear_int_mode(bp);
-		pci_disable_device(pdev);
 		pci_wake_from_d3(pdev, bp->wol);
 		pci_set_power_state(pdev, PCI_D3hot);
 	}
-- 
2.20.1


From 66d067a39734767bb9ca99536cdf78df3bd53fce Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Thu, 20 Feb 2020 17:26:35 -0500
Subject: [PATCH 14/19] bnxt_en: Issue PCIe FLR in kdump kernel to cleanup
 pending DMAs.

[ Upstream commit 8743db4a9acfd51f805ac0c87bcaae92c42d1061 ]

If crashed kernel does not shutdown the NIC properly, PCIe FLR
is required in the kdump kernel in order to initialize all the
functions properly.

Fixes: d629522e1d66 ("bnxt_en: Reduce memory usage when running in kdump kernel.")
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index e03e610dd183..374e11a91790 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -11712,6 +11712,14 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (version_printed++ == 0)
 		pr_info("%s", version);
 
+	/* Clear any pending DMA transactions from crash kernel
+	 * while loading driver in capture kernel.
+	 */
+	if (is_kdump_kernel()) {
+		pci_clear_master(pdev);
+		pcie_flr(pdev);
+	}
+
 	max_irqs = bnxt_get_max_irq(pdev);
 	dev = alloc_etherdev_mq(sizeof(*bp), max_irqs);
 	if (!dev)
-- 
2.20.1


From bd06f561e910c21a5846dd69a1ad421d58ed0bad Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Sat, 15 Feb 2020 10:50:08 +0000
Subject: [PATCH 15/19] bonding: add missing netdev_update_lockdep_key()

[ Upstream commit 064ff66e2bef84f1153087612032b5b9eab005bd ]

After bond_release(), netdev_update_lockdep_key() should be called.
But both ioctl path and attribute path don't call
netdev_update_lockdep_key().
This patch adds missing netdev_update_lockdep_key().

Test commands:
    ip link add bond0 type bond
    ip link add bond1 type bond
    ifenslave bond0 bond1
    ifenslave -d bond0 bond1
    ifenslave bond1 bond0

Splat looks like:
[   29.501182][ T1046] WARNING: possible circular locking dependency detected
[   29.501945][ T1039] hardirqs last disabled at (1962): [<ffffffffac6c807f>] handle_mm_fault+0x13f/0x700
[   29.503442][ T1046] 5.5.0+ #322 Not tainted
[   29.503447][ T1046] ------------------------------------------------------
[   29.504277][ T1039] softirqs last  enabled at (1180): [<ffffffffade00678>] __do_softirq+0x678/0x981
[   29.505443][ T1046] ifenslave/1046 is trying to acquire lock:
[   29.505886][ T1039] softirqs last disabled at (1169): [<ffffffffac19c18a>] irq_exit+0x17a/0x1a0
[   29.509997][ T1046] ffff88805d5da280 (&dev->addr_list_lock_key#3){+...}, at: dev_mc_sync_multiple+0x95/0x120
[   29.511243][ T1046]
[   29.511243][ T1046] but task is already holding lock:
[   29.512192][ T1046] ffff8880460f2280 (&dev->addr_list_lock_key#4){+...}, at: bond_enslave+0x4482/0x47b0 [bonding]
[   29.514124][ T1046]
[   29.514124][ T1046] which lock already depends on the new lock.
[   29.514124][ T1046]
[   29.517297][ T1046]
[   29.517297][ T1046] the existing dependency chain (in reverse order) is:
[   29.518231][ T1046]
[   29.518231][ T1046] -> #1 (&dev->addr_list_lock_key#4){+...}:
[   29.519076][ T1046]        _raw_spin_lock+0x30/0x70
[   29.519588][ T1046]        dev_mc_sync_multiple+0x95/0x120
[   29.520208][ T1046]        bond_enslave+0x448d/0x47b0 [bonding]
[   29.520862][ T1046]        bond_option_slaves_set+0x1a3/0x370 [bonding]
[   29.521640][ T1046]        __bond_opt_set+0x1ff/0xbb0 [bonding]
[   29.522438][ T1046]        __bond_opt_set_notify+0x2b/0xf0 [bonding]
[   29.523251][ T1046]        bond_opt_tryset_rtnl+0x92/0xf0 [bonding]
[   29.524082][ T1046]        bonding_sysfs_store_option+0x8a/0xf0 [bonding]
[   29.524959][ T1046]        kernfs_fop_write+0x276/0x410
[   29.525620][ T1046]        vfs_write+0x197/0x4a0
[   29.526218][ T1046]        ksys_write+0x141/0x1d0
[   29.526818][ T1046]        do_syscall_64+0x99/0x4f0
[   29.527430][ T1046]        entry_SYSCALL_64_after_hwframe+0x49/0xbe
[   29.528265][ T1046]
[   29.528265][ T1046] -> #0 (&dev->addr_list_lock_key#3){+...}:
[   29.529272][ T1046]        __lock_acquire+0x2d8d/0x3de0
[   29.529935][ T1046]        lock_acquire+0x164/0x3b0
[   29.530638][ T1046]        _raw_spin_lock+0x30/0x70
[   29.531187][ T1046]        dev_mc_sync_multiple+0x95/0x120
[   29.531790][ T1046]        bond_enslave+0x448d/0x47b0 [bonding]
[   29.532451][ T1046]        bond_option_slaves_set+0x1a3/0x370 [bonding]
[   29.533163][ T1046]        __bond_opt_set+0x1ff/0xbb0 [bonding]
[   29.533789][ T1046]        __bond_opt_set_notify+0x2b/0xf0 [bonding]
[   29.534595][ T1046]        bond_opt_tryset_rtnl+0x92/0xf0 [bonding]
[   29.535500][ T1046]        bonding_sysfs_store_option+0x8a/0xf0 [bonding]
[   29.536379][ T1046]        kernfs_fop_write+0x276/0x410
[   29.537057][ T1046]        vfs_write+0x197/0x4a0
[   29.537640][ T1046]        ksys_write+0x141/0x1d0
[   29.538251][ T1046]        do_syscall_64+0x99/0x4f0
[   29.538870][ T1046]        entry_SYSCALL_64_after_hwframe+0x49/0xbe
[   29.539659][ T1046]
[   29.539659][ T1046] other info that might help us debug this:
[   29.539659][ T1046]
[   29.540953][ T1046]  Possible unsafe locking scenario:
[   29.540953][ T1046]
[   29.541883][ T1046]        CPU0                    CPU1
[   29.542540][ T1046]        ----                    ----
[   29.543209][ T1046]   lock(&dev->addr_list_lock_key#4);
[   29.543880][ T1046]                                lock(&dev->addr_list_lock_key#3);
[   29.544873][ T1046]                                lock(&dev->addr_list_lock_key#4);
[   29.545863][ T1046]   lock(&dev->addr_list_lock_key#3);
[   29.546525][ T1046]
[   29.546525][ T1046]  *** DEADLOCK ***
[   29.546525][ T1046]
[   29.547542][ T1046] 5 locks held by ifenslave/1046:
[   29.548196][ T1046]  #0: ffff88806044c478 (sb_writers#5){.+.+}, at: vfs_write+0x3bb/0x4a0
[   29.549248][ T1046]  #1: ffff88805af00890 (&of->mutex){+.+.}, at: kernfs_fop_write+0x1cf/0x410
[   29.550343][ T1046]  #2: ffff88805b8b54b0 (kn->count#157){.+.+}, at: kernfs_fop_write+0x1f2/0x410
[   29.551575][ T1046]  #3: ffffffffaecf4cf0 (rtnl_mutex){+.+.}, at: bond_opt_tryset_rtnl+0x5f/0xf0 [bonding]
[   29.552819][ T1046]  #4: ffff8880460f2280 (&dev->addr_list_lock_key#4){+...}, at: bond_enslave+0x4482/0x47b0 [bonding]
[   29.554175][ T1046]
[   29.554175][ T1046] stack backtrace:
[   29.554907][ T1046] CPU: 0 PID: 1046 Comm: ifenslave Not tainted 5.5.0+ #322
[   29.555854][ T1046] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[   29.557064][ T1046] Call Trace:
[   29.557504][ T1046]  dump_stack+0x96/0xdb
[   29.558054][ T1046]  check_noncircular+0x371/0x450
[   29.558723][ T1046]  ? print_circular_bug.isra.35+0x310/0x310
[   29.559486][ T1046]  ? hlock_class+0x130/0x130
[   29.560100][ T1046]  ? __lock_acquire+0x2d8d/0x3de0
[   29.560761][ T1046]  __lock_acquire+0x2d8d/0x3de0
[   29.561366][ T1046]  ? register_lock_class+0x14d0/0x14d0
[   29.562045][ T1046]  ? find_held_lock+0x39/0x1d0
[   29.562641][ T1046]  lock_acquire+0x164/0x3b0
[   29.563199][ T1046]  ? dev_mc_sync_multiple+0x95/0x120
[   29.563872][ T1046]  _raw_spin_lock+0x30/0x70
[   29.564464][ T1046]  ? dev_mc_sync_multiple+0x95/0x120
[   29.565146][ T1046]  dev_mc_sync_multiple+0x95/0x120
[   29.565793][ T1046]  bond_enslave+0x448d/0x47b0 [bonding]
[   29.566487][ T1046]  ? bond_update_slave_arr+0x940/0x940 [bonding]
[   29.567279][ T1046]  ? bstr_printf+0xc20/0xc20
[   29.567857][ T1046]  ? stack_trace_consume_entry+0x160/0x160
[   29.568614][ T1046]  ? deactivate_slab.isra.77+0x2c5/0x800
[   29.569320][ T1046]  ? check_chain_key+0x236/0x5d0
[   29.569939][ T1046]  ? sscanf+0x93/0xc0
[   29.570442][ T1046]  ? vsscanf+0x1e20/0x1e20
[   29.571003][ T1046]  bond_option_slaves_set+0x1a3/0x370 [bonding]
[ ... ]

Fixes: ab92d68fc22f ("net: core: add generic lockdep keys")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c    | 2 ++
 drivers/net/bonding/bond_options.c | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 7dcd709f4ac3..f65e5bb35c28 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3550,6 +3550,8 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd
 	case BOND_RELEASE_OLD:
 	case SIOCBONDRELEASE:
 		res = bond_release(bond_dev, slave_dev);
+		if (!res)
+			netdev_update_lockdep_key(slave_dev);
 		break;
 	case BOND_SETHWADDR_OLD:
 	case SIOCBONDSETHWADDR:
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index ddb3916d3506..215c10923289 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -1398,6 +1398,8 @@ static int bond_option_slaves_set(struct bonding *bond,
 	case '-':
 		slave_dbg(bond->dev, dev, "Releasing interface\n");
 		ret = bond_release(bond->dev, dev);
+		if (!ret)
+			netdev_update_lockdep_key(dev);
 		break;
 
 	default:
-- 
2.20.1


From ef454c40ab85d248e968ce7c709b37ced7b2615b Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Sat, 15 Feb 2020 10:50:21 +0000
Subject: [PATCH 16/19] net: export netdev_next_lower_dev_rcu()

[ Upstream commit 7151affeef8d527f50b4b68a871fd28bd660023f ]

netdev_next_lower_dev_rcu() will be used to implement a function,
which is to walk all lower interfaces.
There are already functions that they walk their lower interface.
(netdev_walk_all_lower_dev_rcu, netdev_walk_all_lower_dev()).
But, there would be cases that couldn't be covered by given
netdev_walk_all_lower_dev_{rcu}() function.
So, some modules would want to implement own function,
which is to walk all lower interfaces.

In the next patch, netdev_next_lower_dev_rcu() will be used.
In addition, this patch removes two unused prototypes in netdevice.h.

Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 7 +++----
 net/core/dev.c            | 6 +++---
 2 files changed, 6 insertions(+), 7 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index f8fde9fa479c..b580a35f50ea 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -72,6 +72,8 @@ void netdev_set_default_ethtool_ops(struct net_device *dev,
 #define NET_RX_SUCCESS		0	/* keep 'em coming, baby */
 #define NET_RX_DROP		1	/* packet dropped */
 
+#define MAX_NEST_DEV 8
+
 /*
  * Transmit return codes: transmit return codes originate from three different
  * namespaces:
@@ -4294,11 +4296,8 @@ void *netdev_lower_get_next(struct net_device *dev,
 	     ldev; \
 	     ldev = netdev_lower_get_next(dev, &(iter)))
 
-struct net_device *netdev_all_lower_get_next(struct net_device *dev,
+struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
 					     struct list_head **iter);
-struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev,
-						 struct list_head **iter);
-
 int netdev_walk_all_lower_dev(struct net_device *dev,
 			      int (*fn)(struct net_device *lower_dev,
 					void *data),
diff --git a/net/core/dev.c b/net/core/dev.c
index c5db02fb1665..db8c229e0f4a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -146,7 +146,6 @@
 #include "net-sysfs.h"
 
 #define MAX_GRO_SKBS 8
-#define MAX_NEST_DEV 8
 
 /* This should be increased if a protocol with a bigger head is added. */
 #define GRO_MAX_HEAD (MAX_HEADER + 128)
@@ -6914,8 +6913,8 @@ static int __netdev_walk_all_lower_dev(struct net_device *dev,
 	return 0;
 }
 
-static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
-						    struct list_head **iter)
+struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
+					     struct list_head **iter)
 {
 	struct netdev_adjacent *lower;
 
@@ -6927,6 +6926,7 @@ static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
 
 	return lower->dev;
 }
+EXPORT_SYMBOL(netdev_next_lower_dev_rcu);
 
 static u8 __netdev_upper_depth(struct net_device *dev)
 {
-- 
2.20.1


From 2f6e08310bd0e13cd238441e792b76503f525c71 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Sat, 15 Feb 2020 10:50:40 +0000
Subject: [PATCH 17/19] bonding: fix lockdep warning in bond_get_stats()

[ Upstream commit b3e80d44f5b1b470dd9e2dbc6816e63a5c519709 ]

In the "struct bonding", there is stats_lock.
This lock protects "bond_stats" in the "struct bonding".
bond_stats is updated in the bond_get_stats() and this function would be
executed concurrently. So, the lock is needed.

Bonding interfaces would be nested.
So, either stats_lock should use dynamic lockdep class key or stats_lock
should be used by spin_lock_nested(). In the current code, stats_lock is
using a dynamic lockdep class key.
But there is no updating stats_lock_key routine So, lockdep warning
will occur.

Test commands:
    ip link add bond0 type bond
    ip link add bond1 type bond
    ip link set bond0 master bond1
    ip link set bond0 nomaster
    ip link set bond1 master bond0

Splat looks like:
[   38.420603][  T957] 5.5.0+ #394 Not tainted
[   38.421074][  T957] ------------------------------------------------------
[   38.421837][  T957] ip/957 is trying to acquire lock:
[   38.422399][  T957] ffff888063262cd8 (&bond->stats_lock_key#2){+.+.}, at: bond_get_stats+0x90/0x4d0 [bonding]
[   38.423528][  T957]
[   38.423528][  T957] but task is already holding lock:
[   38.424526][  T957] ffff888065fd2cd8 (&bond->stats_lock_key){+.+.}, at: bond_get_stats+0x90/0x4d0 [bonding]
[   38.426075][  T957]
[   38.426075][  T957] which lock already depends on the new lock.
[   38.426075][  T957]
[   38.428536][  T957]
[   38.428536][  T957] the existing dependency chain (in reverse order) is:
[   38.429475][  T957]
[   38.429475][  T957] -> #1 (&bond->stats_lock_key){+.+.}:
[   38.430273][  T957]        _raw_spin_lock+0x30/0x70
[   38.430812][  T957]        bond_get_stats+0x90/0x4d0 [bonding]
[   38.431451][  T957]        dev_get_stats+0x1ec/0x270
[   38.432088][  T957]        bond_get_stats+0x1a5/0x4d0 [bonding]
[   38.432767][  T957]        dev_get_stats+0x1ec/0x270
[   38.433322][  T957]        rtnl_fill_stats+0x44/0xbe0
[   38.433866][  T957]        rtnl_fill_ifinfo+0xeb2/0x3720
[   38.434474][  T957]        rtmsg_ifinfo_build_skb+0xca/0x170
[   38.435081][  T957]        rtmsg_ifinfo_event.part.33+0x1b/0xb0
[   38.436848][  T957]        rtnetlink_event+0xcd/0x120
[   38.437455][  T957]        notifier_call_chain+0x90/0x160
[   38.438067][  T957]        netdev_change_features+0x74/0xa0
[   38.438708][  T957]        bond_compute_features.isra.45+0x4e6/0x6f0 [bonding]
[   38.439522][  T957]        bond_enslave+0x3639/0x47b0 [bonding]
[   38.440225][  T957]        do_setlink+0xaab/0x2ef0
[   38.440786][  T957]        __rtnl_newlink+0x9c5/0x1270
[   38.441463][  T957]        rtnl_newlink+0x65/0x90
[   38.442075][  T957]        rtnetlink_rcv_msg+0x4a8/0x890
[   38.442774][  T957]        netlink_rcv_skb+0x121/0x350
[   38.443451][  T957]        netlink_unicast+0x42e/0x610
[   38.444282][  T957]        netlink_sendmsg+0x65a/0xb90
[   38.444992][  T957]        ____sys_sendmsg+0x5ce/0x7a0
[   38.445679][  T957]        ___sys_sendmsg+0x10f/0x1b0
[   38.446365][  T957]        __sys_sendmsg+0xc6/0x150
[   38.447007][  T957]        do_syscall_64+0x99/0x4f0
[   38.447668][  T957]        entry_SYSCALL_64_after_hwframe+0x49/0xbe
[   38.448538][  T957]
[   38.448538][  T957] -> #0 (&bond->stats_lock_key#2){+.+.}:
[   38.449554][  T957]        __lock_acquire+0x2d8d/0x3de0
[   38.450148][  T957]        lock_acquire+0x164/0x3b0
[   38.450711][  T957]        _raw_spin_lock+0x30/0x70
[   38.451292][  T957]        bond_get_stats+0x90/0x4d0 [bonding]
[   38.451950][  T957]        dev_get_stats+0x1ec/0x270
[   38.452425][  T957]        bond_get_stats+0x1a5/0x4d0 [bonding]
[   38.453362][  T957]        dev_get_stats+0x1ec/0x270
[   38.453825][  T957]        rtnl_fill_stats+0x44/0xbe0
[   38.454390][  T957]        rtnl_fill_ifinfo+0xeb2/0x3720
[   38.456257][  T957]        rtmsg_ifinfo_build_skb+0xca/0x170
[   38.456998][  T957]        rtmsg_ifinfo_event.part.33+0x1b/0xb0
[   38.459351][  T957]        rtnetlink_event+0xcd/0x120
[   38.460086][  T957]        notifier_call_chain+0x90/0x160
[   38.460829][  T957]        netdev_change_features+0x74/0xa0
[   38.461752][  T957]        bond_compute_features.isra.45+0x4e6/0x6f0 [bonding]
[   38.462705][  T957]        bond_enslave+0x3639/0x47b0 [bonding]
[   38.463476][  T957]        do_setlink+0xaab/0x2ef0
[   38.464141][  T957]        __rtnl_newlink+0x9c5/0x1270
[   38.464897][  T957]        rtnl_newlink+0x65/0x90
[   38.465522][  T957]        rtnetlink_rcv_msg+0x4a8/0x890
[   38.466215][  T957]        netlink_rcv_skb+0x121/0x350
[   38.466895][  T957]        netlink_unicast+0x42e/0x610
[   38.467583][  T957]        netlink_sendmsg+0x65a/0xb90
[   38.468285][  T957]        ____sys_sendmsg+0x5ce/0x7a0
[   38.469202][  T957]        ___sys_sendmsg+0x10f/0x1b0
[   38.469884][  T957]        __sys_sendmsg+0xc6/0x150
[   38.470587][  T957]        do_syscall_64+0x99/0x4f0
[   38.471245][  T957]        entry_SYSCALL_64_after_hwframe+0x49/0xbe
[   38.472093][  T957]
[   38.472093][  T957] other info that might help us debug this:
[   38.472093][  T957]
[   38.473438][  T957]  Possible unsafe locking scenario:
[   38.473438][  T957]
[   38.474898][  T957]        CPU0                    CPU1
[   38.476234][  T957]        ----                    ----
[   38.480171][  T957]   lock(&bond->stats_lock_key);
[   38.480808][  T957]                                lock(&bond->stats_lock_key#2);
[   38.481791][  T957]                                lock(&bond->stats_lock_key);
[   38.482754][  T957]   lock(&bond->stats_lock_key#2);
[   38.483416][  T957]
[   38.483416][  T957]  *** DEADLOCK ***
[   38.483416][  T957]
[   38.484505][  T957] 3 locks held by ip/957:
[   38.485048][  T957]  #0: ffffffffbccf6230 (rtnl_mutex){+.+.}, at: rtnetlink_rcv_msg+0x457/0x890
[   38.486198][  T957]  #1: ffff888065fd2cd8 (&bond->stats_lock_key){+.+.}, at: bond_get_stats+0x90/0x4d0 [bonding]
[   38.487625][  T957]  #2: ffffffffbc9254c0 (rcu_read_lock){....}, at: bond_get_stats+0x5/0x4d0 [bonding]
[   38.488897][  T957]
[   38.488897][  T957] stack backtrace:
[   38.489646][  T957] CPU: 1 PID: 957 Comm: ip Not tainted 5.5.0+ #394
[   38.490497][  T957] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[   38.492810][  T957] Call Trace:
[   38.493219][  T957]  dump_stack+0x96/0xdb
[   38.493709][  T957]  check_noncircular+0x371/0x450
[   38.494344][  T957]  ? lookup_address+0x60/0x60
[   38.494923][  T957]  ? print_circular_bug.isra.35+0x310/0x310
[   38.495699][  T957]  ? hlock_class+0x130/0x130
[   38.496334][  T957]  ? __lock_acquire+0x2d8d/0x3de0
[   38.496979][  T957]  __lock_acquire+0x2d8d/0x3de0
[   38.497607][  T957]  ? register_lock_class+0x14d0/0x14d0
[   38.498333][  T957]  ? check_chain_key+0x236/0x5d0
[   38.499003][  T957]  lock_acquire+0x164/0x3b0
[   38.499800][  T957]  ? bond_get_stats+0x90/0x4d0 [bonding]
[   38.500706][  T957]  _raw_spin_lock+0x30/0x70
[   38.501435][  T957]  ? bond_get_stats+0x90/0x4d0 [bonding]
[   38.502311][  T957]  bond_get_stats+0x90/0x4d0 [bonding]
[ ... ]

But, there is another problem.
The dynamic lockdep class key is protected by RTNL, but bond_get_stats()
would be called outside of RTNL.
So, it would use an invalid dynamic lockdep class key.

In order to fix this issue, stats_lock uses spin_lock_nested() instead of
a dynamic lockdep key.
The bond_get_stats() calls bond_get_lowest_level_rcu() to get the correct
nest level value, which will be used by spin_lock_nested().
The "dev->lower_level" indicates lower nest level value, but this value
is invalid outside of RTNL.
So, bond_get_lowest_level_rcu() returns valid lower nest level value in
the RCU critical section.
bond_get_lowest_level_rcu() will be work only when LOCKDEP is enabled.

Fixes: 089bca2caed0 ("bonding: use dynamic lockdep key instead of subclass")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 53 +++++++++++++++++++++++++++++++--
 1 file changed, 50 insertions(+), 3 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index f65e5bb35c28..703c5c2c80e5 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3436,6 +3436,47 @@ static void bond_fold_stats(struct rtnl_link_stats64 *_res,
 	}
 }
 
+#ifdef CONFIG_LOCKDEP
+static int bond_get_lowest_level_rcu(struct net_device *dev)
+{
+	struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
+	struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
+	int cur = 0, max = 0;
+
+	now = dev;
+	iter = &dev->adj_list.lower;
+
+	while (1) {
+		next = NULL;
+		while (1) {
+			ldev = netdev_next_lower_dev_rcu(now, &iter);
+			if (!ldev)
+				break;
+
+			next = ldev;
+			niter = &ldev->adj_list.lower;
+			dev_stack[cur] = now;
+			iter_stack[cur++] = iter;
+			if (max <= cur)
+				max = cur;
+			break;
+		}
+
+		if (!next) {
+			if (!cur)
+				return max;
+			next = dev_stack[--cur];
+			niter = iter_stack[cur];
+		}
+
+		now = next;
+		iter = niter;
+	}
+
+	return max;
+}
+#endif
+
 static void bond_get_stats(struct net_device *bond_dev,
 			   struct rtnl_link_stats64 *stats)
 {
@@ -3443,11 +3484,17 @@ static void bond_get_stats(struct net_device *bond_dev,
 	struct rtnl_link_stats64 temp;
 	struct list_head *iter;
 	struct slave *slave;
+	int nest_level = 0;
 
-	spin_lock(&bond->stats_lock);
-	memcpy(stats, &bond->bond_stats, sizeof(*stats));
 
 	rcu_read_lock();
+#ifdef CONFIG_LOCKDEP
+	nest_level = bond_get_lowest_level_rcu(bond_dev);
+#endif
+
+	spin_lock_nested(&bond->stats_lock, nest_level);
+	memcpy(stats, &bond->bond_stats, sizeof(*stats));
+
 	bond_for_each_slave_rcu(bond, slave, iter) {
 		const struct rtnl_link_stats64 *new =
 			dev_get_stats(slave->dev, &temp);
@@ -3457,10 +3504,10 @@ static void bond_get_stats(struct net_device *bond_dev,
 		/* save off the slave stats for the next run */
 		memcpy(&slave->slave_stats, new, sizeof(*new));
 	}
-	rcu_read_unlock();
 
 	memcpy(&bond->bond_stats, stats, sizeof(*stats));
 	spin_unlock(&bond->stats_lock);
+	rcu_read_unlock();
 }
 
 static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd)
-- 
2.20.1


From f15b6f4e1ba9cc496b296fb87b39cc38737bc394 Mon Sep 17 00:00:00 2001
From: Benjamin Poirier <bpoirier@cumulusnetworks.com>
Date: Wed, 12 Feb 2020 10:41:06 +0900
Subject: [PATCH 18/19] ipv6: Fix route replacement with dev-only route

[ Upstream commit e404b8c7cfb31654c9024d497cec58a501501692 ]

After commit 27596472473a ("ipv6: fix ECMP route replacement") it is no
longer possible to replace an ECMP-able route by a non ECMP-able route.
For example,
	ip route add 2001:db8::1/128 via fe80::1 dev dummy0
	ip route replace 2001:db8::1/128 dev dummy0
does not work as expected.

Tweak the replacement logic so that point 3 in the log of the above commit
becomes:
3. If the new route is not ECMP-able, and no matching non-ECMP-able route
exists, replace matching ECMP-able route (if any) or add the new route.

We can now summarize the entire replace semantics to:
When doing a replace, prefer replacing a matching route of the same
"ECMP-able-ness" as the replace argument. If there is no such candidate,
fallback to the first route found.

Fixes: 27596472473a ("ipv6: fix ECMP route replacement")
Signed-off-by: Benjamin Poirier <bpoirier@cumulusnetworks.com>
Reviewed-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_fib.c                       | 7 ++++---
 tools/testing/selftests/net/fib_tests.sh | 6 ++++++
 2 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 6e2af411cd9c..c75274e0745c 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1050,8 +1050,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
 					found++;
 					break;
 				}
-				if (rt_can_ecmp)
-					fallback_ins = fallback_ins ?: ins;
+				fallback_ins = fallback_ins ?: ins;
 				goto next_iter;
 			}
 
@@ -1094,7 +1093,9 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
 	}
 
 	if (fallback_ins && !found) {
-		/* No ECMP-able route found, replace first non-ECMP one */
+		/* No matching route with same ecmp-able-ness found, replace
+		 * first matching route
+		 */
 		ins = fallback_ins;
 		iter = rcu_dereference_protected(*ins,
 				    lockdep_is_held(&rt->fib6_table->tb6_lock));
diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 76c1897e6352..474638ef2697 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -910,6 +910,12 @@ ipv6_rt_replace_mpath()
 	check_route6 "2001:db8:104::/64 via 2001:db8:101::3 dev veth1 metric 1024"
 	log_test $? 0 "Multipath with single path via multipath attribute"
 
+	# multipath with dev-only
+	add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
+	run_cmd "$IP -6 ro replace 2001:db8:104::/64 dev veth1"
+	check_route6 "2001:db8:104::/64 dev veth1 metric 1024"
+	log_test $? 0 "Multipath with dev-only"
+
 	# route replace fails - invalid nexthop 1
 	add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
 	run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:111::3 nexthop via 2001:db8:103::3"
-- 
2.20.1


From be3db5735fe6c1d7b1a29ec7c0749764fc50dee2 Mon Sep 17 00:00:00 2001
From: Benjamin Poirier <bpoirier@cumulusnetworks.com>
Date: Wed, 12 Feb 2020 10:41:07 +0900
Subject: [PATCH 19/19] ipv6: Fix nlmsg_flags when splitting a multipath route

[ Upstream commit afecdb376bd81d7e16578f0cfe82a1aec7ae18f3 ]

When splitting an RTA_MULTIPATH request into multiple routes and adding the
second and later components, we must not simply remove NLM_F_REPLACE but
instead replace it by NLM_F_CREATE. Otherwise, it may look like the netlink
message was malformed.

For example,
	ip route add 2001:db8::1/128 dev dummy0
	ip route change 2001:db8::1/128 nexthop via fe80::30:1 dev dummy0 \
		nexthop via fe80::30:2 dev dummy0
results in the following warnings:
[ 1035.057019] IPv6: RTM_NEWROUTE with no NLM_F_CREATE or NLM_F_REPLACE
[ 1035.057517] IPv6: NLM_F_CREATE should be set when creating new route

This patch makes the nlmsg sequence look equivalent for __ip6_ins_rt() to
what it would get if the multipath route had been added in multiple netlink
operations:
	ip route add 2001:db8::1/128 dev dummy0
	ip route change 2001:db8::1/128 nexthop via fe80::30:1 dev dummy0
	ip route append 2001:db8::1/128 nexthop via fe80::30:2 dev dummy0

Fixes: 27596472473a ("ipv6: fix ECMP route replacement")
Signed-off-by: Benjamin Poirier <bpoirier@cumulusnetworks.com>
Reviewed-by: Michal Kubecek <mkubecek@suse.cz>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index e4ed9c7b43b0..894c7370c1bd 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -5155,6 +5155,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 		 */
 		cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL |
 						     NLM_F_REPLACE);
+		cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_CREATE;
 		nhn++;
 	}
 
-- 
2.20.1


[-- Attachment #3: net_55.mbox --]
[-- Type: Application/Octet-Stream, Size: 79117 bytes --]

From fb298d77c2eb35a45038e7ff5e0ed0ac5e8dcc81 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 14 Feb 2020 15:26:19 -0800
Subject: [PATCH 01/23] net: dsa: b53: Ensure the default VID is untagged

[ Upstream commit d965a5432d4c3e6b9c3d2bc1d4a800013bbf76f6 ]

We need to ensure that the default VID is untagged otherwise the switch
will be sending tagged frames and the results can be problematic. This
is especially true with b53 switches that use VID 0 as their default
VLAN since VID 0 has a special meaning.

Fixes: fea83353177a ("net: dsa: b53: Fix default VLAN ID")
Fixes: 061f6a505ac3 ("net: dsa: Add ndo_vlan_rx_{add, kill}_vid implementation")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/b53/b53_common.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 6a1ff4d43e3a..38b16efda4a9 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -1353,6 +1353,9 @@ void b53_vlan_add(struct dsa_switch *ds, int port,
 
 		b53_get_vlan_entry(dev, vid, vl);
 
+		if (vid == 0 && vid == b53_default_pvid(dev))
+			untagged = true;
+
 		vl->members |= BIT(port);
 		if (untagged && !dsa_is_cpu_port(ds, port))
 			vl->untag |= BIT(port);
-- 
2.20.1


From 9f4f6e14046637a07d5f44f99565c2ea3f16e399 Mon Sep 17 00:00:00 2001
From: Jethro Beekman <jethro@fortanix.com>
Date: Wed, 12 Feb 2020 16:43:41 +0100
Subject: [PATCH 02/23] net: fib_rules: Correctly set table field when table
 number exceeds 8 bits

[ Upstream commit 540e585a79e9d643ede077b73bcc7aa2d7b4d919 ]

In 709772e6e06564ed94ba740de70185ac3d792773, RT_TABLE_COMPAT was added to
allow legacy software to deal with routing table numbers >= 256, but the
same change to FIB rule queries was overlooked.

Signed-off-by: Jethro Beekman <jethro@fortanix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/fib_rules.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 3e7e15278c46..bd7eba9066f8 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -974,7 +974,7 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule,
 
 	frh = nlmsg_data(nlh);
 	frh->family = ops->family;
-	frh->table = rule->table;
+	frh->table = rule->table < 256 ? rule->table : RT_TABLE_COMPAT;
 	if (nla_put_u32(skb, FRA_TABLE, rule->table))
 		goto nla_put_failure;
 	if (nla_put_u32(skb, FRA_SUPPRESS_PREFIXLEN, rule->suppress_prefixlen))
-- 
2.20.1


From cd474772d567353a164a2ceb3245712e7c3be492 Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Wed, 12 Feb 2020 17:45:38 +0100
Subject: [PATCH 03/23] net: macb: ensure interface is not suspended on
 at91rm9200

[ Upstream commit e6a41c23df0d5da01540d2abef41591589c0b4be ]

Because of autosuspend, at91ether_start is called with clocks disabled.
Ensure that pm_runtime doesn't suspend the interface as soon as it is
opened as there is no pm_runtime support is the other relevant parts of the
platform support for at91rm9200.

Fixes: d54f89af6cc4 ("net: macb: Add pm runtime support")
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Reviewed-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Acked-by: Nicolas Ferre <nicolas.ferre@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 71bb0d56533a..e916fc223621 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -3751,6 +3751,10 @@ static int at91ether_open(struct net_device *dev)
 	u32 ctl;
 	int ret;
 
+	ret = pm_runtime_get_sync(&lp->pdev->dev);
+	if (ret < 0)
+		return ret;
+
 	/* Clear internal statistics */
 	ctl = macb_readl(lp, NCR);
 	macb_writel(lp, NCR, ctl | MACB_BIT(CLRSTAT));
@@ -3815,7 +3819,7 @@ static int at91ether_close(struct net_device *dev)
 			  q->rx_buffers, q->rx_buffers_dma);
 	q->rx_buffers = NULL;
 
-	return 0;
+	return pm_runtime_put(&lp->pdev->dev);
 }
 
 /* Transmit packet */
-- 
2.20.1


From c62e9e69f95be43e29b65d140615822eaff03b10 Mon Sep 17 00:00:00 2001
From: Horatiu Vultur <horatiu.vultur@microchip.com>
Date: Mon, 17 Feb 2020 09:31:33 +0100
Subject: [PATCH 04/23] net: mscc: fix in frame extraction

[ Upstream commit a81541041ceb55bcec9a8bb8ad3482263f0a205a ]

Each extracted frame on Ocelot has an IFH. The frame and IFH are extracted
by reading chuncks of 4 bytes from a register.

In case the IFH and frames were read corretly it would try to read the next
frame. In case there are no more frames in the queue, it checks if there
were any previous errors and in that case clear the queue. But this check
will always succeed also when there are no errors. Because when extracting
the IFH the error is checked against 4(number of bytes read) and then the
error is set only if the extraction of the frame failed. So in a happy case
where there are no errors the err variable is still 4. So it could be
a case where after the check that there are no more frames in the queue, a
frame will arrive in the queue but because the error is not reseted, it
would try to flush the queue. So the frame will be lost.

The fix consist in resetting the error after reading the IFH.

Signed-off-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Acked-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot_board.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c
index 2da8eee27e98..ecbd4be145b8 100644
--- a/drivers/net/ethernet/mscc/ocelot_board.c
+++ b/drivers/net/ethernet/mscc/ocelot_board.c
@@ -114,6 +114,14 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg)
 		if (err != 4)
 			break;
 
+		/* At this point the IFH was read correctly, so it is safe to
+		 * presume that there is no error. The err needs to be reset
+		 * otherwise a frame could come in CPU queue between the while
+		 * condition and the check for error later on. And in that case
+		 * the new frame is just removed and not processed.
+		 */
+		err = 0;
+
 		ocelot_parse_ifh(ifh, &info);
 
 		ocelot_port = ocelot->ports[info.port];
-- 
2.20.1


From ee49026972f5d7293f41f1f381e26b021ed5021b Mon Sep 17 00:00:00 2001
From: Arun Parameswaran <arun.parameswaran@broadcom.com>
Date: Fri, 14 Feb 2020 13:47:46 -0800
Subject: [PATCH 05/23] net: phy: restore mdio regs in the iproc mdio driver

The mii management register in iproc mdio block
does not have a retention register so it is lost on suspend.
Save and restore value of register while resuming from suspend.

Fixes: bb1a619735b4 ("net: phy: Initialize mdio clock at probe function")
Signed-off-by: Arun Parameswaran <arun.parameswaran@broadcom.com>
Signed-off-by: Scott Branden <scott.branden@broadcom.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mdio-bcm-iproc.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/drivers/net/phy/mdio-bcm-iproc.c b/drivers/net/phy/mdio-bcm-iproc.c
index 7e9975d25066..f1ded03f0229 100644
--- a/drivers/net/phy/mdio-bcm-iproc.c
+++ b/drivers/net/phy/mdio-bcm-iproc.c
@@ -178,6 +178,23 @@ static int iproc_mdio_remove(struct platform_device *pdev)
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
+int iproc_mdio_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct iproc_mdio_priv *priv = platform_get_drvdata(pdev);
+
+	/* restore the mii clock configuration */
+	iproc_mdio_config_clk(priv->base);
+
+	return 0;
+}
+
+static const struct dev_pm_ops iproc_mdio_pm_ops = {
+	.resume = iproc_mdio_resume
+};
+#endif /* CONFIG_PM_SLEEP */
+
 static const struct of_device_id iproc_mdio_of_match[] = {
 	{ .compatible = "brcm,iproc-mdio", },
 	{ /* sentinel */ },
@@ -188,6 +205,9 @@ static struct platform_driver iproc_mdio_driver = {
 	.driver = {
 		.name = "iproc-mdio",
 		.of_match_table = iproc_mdio_of_match,
+#ifdef CONFIG_PM_SLEEP
+		.pm = &iproc_mdio_pm_ops,
+#endif
 	},
 	.probe = iproc_mdio_probe,
 	.remove = iproc_mdio_remove,
-- 
2.20.1


From 6db9c2b007bd0983aa5d9212c961fec8f3e3608f Mon Sep 17 00:00:00 2001
From: Jason Baron <jbaron@akamai.com>
Date: Mon, 17 Feb 2020 15:38:09 -0500
Subject: [PATCH 06/23] net: sched: correct flower port blocking

[ Upstream commit 8a9093c79863b58cc2f9874d7ae788f0d622a596 ]

tc flower rules that are based on src or dst port blocking are sometimes
ineffective due to uninitialized stack data. __skb_flow_dissect() extracts
ports from the skb for tc flower to match against. However, the port
dissection is not done when when the FLOW_DIS_IS_FRAGMENT bit is set in
key_control->flags. All callers of __skb_flow_dissect(), zero-out the
key_control field except for fl_classify() as used by the flower
classifier. Thus, the FLOW_DIS_IS_FRAGMENT may be set on entry to
__skb_flow_dissect(), since key_control is allocated on the stack
and may not be initialized.

Since key_basic and key_control are present for all flow keys, let's
make sure they are initialized.

Fixes: 62230715fd24 ("flow_dissector: do not dissect l4 ports for fragments")
Co-developed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Jason Baron <jbaron@akamai.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow_dissector.h | 9 +++++++++
 net/sched/cls_flower.c       | 1 +
 2 files changed, 10 insertions(+)

diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index d93017a7ce5c..e03827f702f3 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -5,6 +5,7 @@
 #include <linux/types.h>
 #include <linux/in6.h>
 #include <linux/siphash.h>
+#include <linux/string.h>
 #include <uapi/linux/if_ether.h>
 
 struct sk_buff;
@@ -349,4 +350,12 @@ struct bpf_flow_dissector {
 	void			*data_end;
 };
 
+static inline void
+flow_dissector_init_keys(struct flow_dissector_key_control *key_control,
+			 struct flow_dissector_key_basic *key_basic)
+{
+	memset(key_control, 0, sizeof(*key_control));
+	memset(key_basic, 0, sizeof(*key_basic));
+}
+
 #endif
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 7e54d2ab5254..d32d4233d337 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -305,6 +305,7 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 	struct cls_fl_filter *f;
 
 	list_for_each_entry_rcu(mask, &head->masks, list) {
+		flow_dissector_init_keys(&skb_key.control, &skb_key.basic);
 		fl_clear_masked_range(&skb_key, mask);
 
 		skb_flow_dissect_meta(skb, &mask->dissector, &skb_key);
-- 
2.20.1


From f4c971b08e0a9c9cc84f87e16a5f350c907c3a2d Mon Sep 17 00:00:00 2001
From: Rohit Maheshwari <rohitm@chelsio.com>
Date: Wed, 19 Feb 2020 09:40:22 +0530
Subject: [PATCH 07/23] net/tls: Fix to avoid gettig invalid tls record

[ Upstream commit 06f5201c6392f998a49ca9c9173e2930c8eb51d8 ]

Current code doesn't check if tcp sequence number is starting from (/after)
1st record's start sequnce number. It only checks if seq number is before
1st record's end sequnce number. This problem will always be a possibility
in re-transmit case. If a record which belongs to a requested seq number is
already deleted, tls_get_record will start looking into list and as per the
check it will look if seq number is before the end seq of 1st record, which
will always be true and will return 1st record always, it should in fact
return NULL.
As part of the fix, start looking each record only if the sequence number
lies in the list else return NULL.
There is one more check added, driver look for the start marker record to
handle tcp packets which are before the tls offload start sequence number,
hence return 1st record if the record is tls start marker and seq number is
before the 1st record's starting sequence number.

Fixes: e8f69799810c ("net/tls: Add generic NIC offload infrastructure")
Signed-off-by: Rohit Maheshwari <rohitm@chelsio.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_device.c | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index cd91ad812291..e72d7d787935 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -592,7 +592,7 @@ struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context,
 				       u32 seq, u64 *p_record_sn)
 {
 	u64 record_sn = context->hint_record_sn;
-	struct tls_record_info *info;
+	struct tls_record_info *info, *last;
 
 	info = context->retransmit_hint;
 	if (!info ||
@@ -604,6 +604,24 @@ struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context,
 						struct tls_record_info, list);
 		if (!info)
 			return NULL;
+		/* send the start_marker record if seq number is before the
+		 * tls offload start marker sequence number. This record is
+		 * required to handle TCP packets which are before TLS offload
+		 * started.
+		 *  And if it's not start marker, look if this seq number
+		 * belongs to the list.
+		 */
+		if (likely(!tls_record_is_start_marker(info))) {
+			/* we have the first record, get the last record to see
+			 * if this seq number belongs to the list.
+			 */
+			last = list_last_entry(&context->records_list,
+					       struct tls_record_info, list);
+
+			if (!between(seq, tls_record_start_seq(info),
+				     last->end_seq))
+				return NULL;
+		}
 		record_sn = context->unacked_record_sn;
 	}
 
-- 
2.20.1


From 542cb93033f243af1cb623cc024c1415de1bbf08 Mon Sep 17 00:00:00 2001
From: Dmitry Osipenko <digetx@gmail.com>
Date: Wed, 19 Feb 2020 18:01:22 +0300
Subject: [PATCH 08/23] nfc: pn544: Fix occasional HW initialization failure

[ Upstream commit c3331d2fe3fd4d5e321f2467d01f72de7edfb5d0 ]

The PN544 driver checks the "enable" polarity during of driver's probe and
it's doing that by turning ON and OFF NFC with different polarities until
enabling succeeds. It takes some time for the hardware to power-down, and
thus, to deassert the IRQ that is raised by turning ON the hardware.
Since the delay after last power-down of the polarity-checking process is
missed in the code, the interrupt may trigger immediately after installing
the IRQ handler (right after the checking is done), which results in IRQ
handler trying to touch the disabled HW and ends with marking NFC as
'DEAD' during of the driver's probe:

  pn544_hci_i2c 1-002a: NFC: nfc_en polarity : active high
  pn544_hci_i2c 1-002a: NFC: invalid len byte
  shdlc: llc_shdlc_recv_frame: NULL Frame -> link is dead

This patch fixes the occasional NFC initialization failure on Nexus 7
device.

Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/nfc/pn544/i2c.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/nfc/pn544/i2c.c b/drivers/nfc/pn544/i2c.c
index 720c89d6066e..4ac8cb262559 100644
--- a/drivers/nfc/pn544/i2c.c
+++ b/drivers/nfc/pn544/i2c.c
@@ -225,6 +225,7 @@ static void pn544_hci_i2c_platform_init(struct pn544_i2c_phy *phy)
 
 out:
 	gpiod_set_value_cansleep(phy->gpiod_en, !phy->en_polarity);
+	usleep_range(10000, 15000);
 }
 
 static void pn544_hci_i2c_enable_mode(struct pn544_i2c_phy *phy, int run_mode)
-- 
2.20.1


From ba888b9d15bff6005ff104de4687d288e600c45b Mon Sep 17 00:00:00 2001
From: Michal Kalderon <michal.kalderon@marvell.com>
Date: Mon, 17 Feb 2020 13:37:18 +0200
Subject: [PATCH 09/23] qede: Fix race between rdma destroy workqueue and link
 change event

[ Upstream commit af6565adb02d3129d3fae4d9d5da945abaf4417a ]

If an event is added while the rdma workqueue is being destroyed
it could lead to several races, list corruption, null pointer
dereference during queue_work or init_queue.
This fixes the race between the two flows which can occur during
shutdown.

A kref object and a completion object are added to the rdma_dev
structure, these are initialized before the workqueue is created.
The refcnt is used to indicate work is being added to the
workqueue and ensures the cleanup flow won't start while we're in
the middle of adding the event.
Once the work is added, the refcnt is decreased and the cleanup flow
is safe to run.

Fixes: cee9fbd8e2e ("qede: Add qedr framework")
Signed-off-by: Ariel Elior <ariel.elior@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qede/qede.h      |  2 ++
 drivers/net/ethernet/qlogic/qede/qede_rdma.c | 29 +++++++++++++++++++-
 2 files changed, 30 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index e8a1b27db84d..234c6f30effb 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -163,6 +163,8 @@ struct qede_rdma_dev {
 	struct list_head entry;
 	struct list_head rdma_event_list;
 	struct workqueue_struct *rdma_wq;
+	struct kref refcnt;
+	struct completion event_comp;
 	bool exp_recovery;
 };
 
diff --git a/drivers/net/ethernet/qlogic/qede/qede_rdma.c b/drivers/net/ethernet/qlogic/qede/qede_rdma.c
index ffabc2d2f082..2d873ae8a234 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_rdma.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_rdma.c
@@ -59,6 +59,9 @@ static void _qede_rdma_dev_add(struct qede_dev *edev)
 static int qede_rdma_create_wq(struct qede_dev *edev)
 {
 	INIT_LIST_HEAD(&edev->rdma_info.rdma_event_list);
+	kref_init(&edev->rdma_info.refcnt);
+	init_completion(&edev->rdma_info.event_comp);
+
 	edev->rdma_info.rdma_wq = create_singlethread_workqueue("rdma_wq");
 	if (!edev->rdma_info.rdma_wq) {
 		DP_NOTICE(edev, "qedr: Could not create workqueue\n");
@@ -83,8 +86,23 @@ static void qede_rdma_cleanup_event(struct qede_dev *edev)
 	}
 }
 
+static void qede_rdma_complete_event(struct kref *ref)
+{
+	struct qede_rdma_dev *rdma_dev =
+		container_of(ref, struct qede_rdma_dev, refcnt);
+
+	/* no more events will be added after this */
+	complete(&rdma_dev->event_comp);
+}
+
 static void qede_rdma_destroy_wq(struct qede_dev *edev)
 {
+	/* Avoid race with add_event flow, make sure it finishes before
+	 * we start accessing the list and cleaning up the work
+	 */
+	kref_put(&edev->rdma_info.refcnt, qede_rdma_complete_event);
+	wait_for_completion(&edev->rdma_info.event_comp);
+
 	qede_rdma_cleanup_event(edev);
 	destroy_workqueue(edev->rdma_info.rdma_wq);
 }
@@ -310,15 +328,24 @@ static void qede_rdma_add_event(struct qede_dev *edev,
 	if (!edev->rdma_info.qedr_dev)
 		return;
 
+	/* We don't want the cleanup flow to start while we're allocating and
+	 * scheduling the work
+	 */
+	if (!kref_get_unless_zero(&edev->rdma_info.refcnt))
+		return; /* already being destroyed */
+
 	event_node = qede_rdma_get_free_event_node(edev);
 	if (!event_node)
-		return;
+		goto out;
 
 	event_node->event = event;
 	event_node->ptr = edev;
 
 	INIT_WORK(&event_node->work, qede_rdma_handle_event);
 	queue_work(edev->rdma_info.rdma_wq, &event_node->work);
+
+out:
+	kref_put(&edev->rdma_info.refcnt, qede_rdma_complete_event);
 }
 
 void qede_rdma_dev_event_open(struct qede_dev *edev)
-- 
2.20.1


From ffa21b68858ba591a88850e5ba60352f90ed4052 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 18 Feb 2020 18:15:44 +0100
Subject: [PATCH 10/23] Revert "net: dev: introduce support for sch BYPASS for
 lockless qdisc"

[ Upstream commit 379349e9bc3b42b8b2f8f7a03f64a97623fff323 ]

This reverts commit ba27b4cdaaa66561aaedb2101876e563738d36fe

Ahmed reported ouf-of-order issues bisected to commit ba27b4cdaaa6
("net: dev: introduce support for sch BYPASS for lockless qdisc").
I can't find any working solution other than a plain revert.

This will introduce some minor performance regressions for
pfifo_fast qdisc. I plan to address them in net-next with more
indirect call wrapper boilerplate for qdiscs.

Reported-by: Ahmad Fatoum <a.fatoum@pengutronix.de>
Fixes: ba27b4cdaaa6 ("net: dev: introduce support for sch BYPASS for lockless qdisc")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 22 ++--------------------
 1 file changed, 2 insertions(+), 20 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 466f2e4144b0..8461f4eba716 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3607,26 +3607,8 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 	qdisc_calculate_pkt_len(skb, q);
 
 	if (q->flags & TCQ_F_NOLOCK) {
-		if ((q->flags & TCQ_F_CAN_BYPASS) && READ_ONCE(q->empty) &&
-		    qdisc_run_begin(q)) {
-			if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED,
-					      &q->state))) {
-				__qdisc_drop(skb, &to_free);
-				rc = NET_XMIT_DROP;
-				goto end_run;
-			}
-			qdisc_bstats_cpu_update(q, skb);
-
-			rc = NET_XMIT_SUCCESS;
-			if (sch_direct_xmit(skb, q, dev, txq, NULL, true))
-				__qdisc_run(q);
-
-end_run:
-			qdisc_run_end(q);
-		} else {
-			rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
-			qdisc_run(q);
-		}
+		rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
+		qdisc_run(q);
 
 		if (unlikely(to_free))
 			kfree_skb_list(to_free);
-- 
2.20.1


From ae2d22ded11e6203312a32a11929a02309f7d806 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 19 Feb 2020 14:16:32 -0500
Subject: [PATCH 11/23] udp: rehash on disconnect

[ Upstream commit 303d0403b8c25e994e4a6e45389e173cf8706fb5 ]

As of the below commit, udp sockets bound to a specific address can
coexist with one bound to the any addr for the same port.

The commit also phased out the use of socket hashing based only on
port (hslot), in favor of always hashing on {addr, port} (hslot2).

The change broke the following behavior with disconnect (AF_UNSPEC):

    server binds to 0.0.0.0:1337
    server connects to 127.0.0.1:80
    server disconnects
    client connects to 127.0.0.1:1337
    client sends "hello"
    server reads "hello"	// times out, packet did not find sk

On connect the server acquires a specific source addr suitable for
routing to its destination. On disconnect it reverts to the any addr.

The connect call triggers a rehash to a different hslot2. On
disconnect, add the same to return to the original hslot2.

Skip this step if the socket is going to be unhashed completely.

Fixes: 4cdeeee9252a ("net: udp: prefer listeners bound to an address")
Reported-by: Pavel Roskin <plroskin@gmail.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 030d43c7c957..be5c5903cfe1 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1856,8 +1856,12 @@ int __udp_disconnect(struct sock *sk, int flags)
 	inet->inet_dport = 0;
 	sock_rps_reset_rxhash(sk);
 	sk->sk_bound_dev_if = 0;
-	if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
+	if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) {
 		inet_reset_saddr(sk);
+		if (sk->sk_prot->rehash &&
+		    (sk->sk_userlocks & SOCK_BINDPORT_LOCK))
+			sk->sk_prot->rehash(sk);
+	}
 
 	if (!(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) {
 		sk->sk_prot->unhash(sk);
-- 
2.20.1


From 5df9821e9f6aa65bfd01f9c0f2c9b05d6b803d51 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 18 Feb 2020 12:07:53 +0800
Subject: [PATCH 12/23] sctp: move the format error check out of
 __sctp_sf_do_9_1_abort

[ Upstream commit 245709ec8be89af46ea7ef0444c9c80913999d99 ]

When T2 timer is to be stopped, the asoc should also be deleted,
otherwise, there will be no chance to call sctp_association_free
and the asoc could last in memory forever.

However, in sctp_sf_shutdown_sent_abort(), after adding the cmd
SCTP_CMD_TIMER_STOP for T2 timer, it may return error due to the
format error from __sctp_sf_do_9_1_abort() and miss adding
SCTP_CMD_ASSOC_FAILED where the asoc will be deleted.

This patch is to fix it by moving the format error check out of
__sctp_sf_do_9_1_abort(), and do it before adding the cmd
SCTP_CMD_TIMER_STOP for T2 timer.

Thanks Hangbin for reporting this issue by the fuzz testing.

v1->v2:
  - improve the comment in the code as Marcelo's suggestion.

Fixes: 96ca468b86b0 ("sctp: check invalid value of length parameter in error cause")
Reported-by: Hangbin Liu <liuhangbin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sm_statefuns.c | 29 ++++++++++++++++++++---------
 1 file changed, 20 insertions(+), 9 deletions(-)

diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 4ab8208a2dd4..c6d83a64eac3 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -170,6 +170,16 @@ static inline bool sctp_chunk_length_valid(struct sctp_chunk *chunk,
 	return true;
 }
 
+/* Check for format error in an ABORT chunk */
+static inline bool sctp_err_chunk_valid(struct sctp_chunk *chunk)
+{
+	struct sctp_errhdr *err;
+
+	sctp_walk_errors(err, chunk->chunk_hdr);
+
+	return (void *)err == (void *)chunk->chunk_end;
+}
+
 /**********************************************************
  * These are the state functions for handling chunk events.
  **********************************************************/
@@ -2255,6 +2265,9 @@ enum sctp_disposition sctp_sf_shutdown_pending_abort(
 		    sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest))
 		return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands);
 
+	if (!sctp_err_chunk_valid(chunk))
+		return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
 	return __sctp_sf_do_9_1_abort(net, ep, asoc, type, arg, commands);
 }
 
@@ -2298,6 +2311,9 @@ enum sctp_disposition sctp_sf_shutdown_sent_abort(
 		    sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest))
 		return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands);
 
+	if (!sctp_err_chunk_valid(chunk))
+		return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
 	/* Stop the T2-shutdown timer. */
 	sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP,
 			SCTP_TO(SCTP_EVENT_TIMEOUT_T2_SHUTDOWN));
@@ -2565,6 +2581,9 @@ enum sctp_disposition sctp_sf_do_9_1_abort(
 		    sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest))
 		return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands);
 
+	if (!sctp_err_chunk_valid(chunk))
+		return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
 	return __sctp_sf_do_9_1_abort(net, ep, asoc, type, arg, commands);
 }
 
@@ -2582,16 +2601,8 @@ static enum sctp_disposition __sctp_sf_do_9_1_abort(
 
 	/* See if we have an error cause code in the chunk.  */
 	len = ntohs(chunk->chunk_hdr->length);
-	if (len >= sizeof(struct sctp_chunkhdr) + sizeof(struct sctp_errhdr)) {
-		struct sctp_errhdr *err;
-
-		sctp_walk_errors(err, chunk->chunk_hdr);
-		if ((void *)err != (void *)chunk->chunk_end)
-			return sctp_sf_pdiscard(net, ep, asoc, type, arg,
-						commands);
-
+	if (len >= sizeof(struct sctp_chunkhdr) + sizeof(struct sctp_errhdr))
 		error = ((struct sctp_errhdr *)chunk->skb->data)->cause;
-	}
 
 	sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ECONNRESET));
 	/* ASSOC_FAILED will DELETE_TCB. */
-- 
2.20.1


From c0ad62d198130c6507ee3cea535bb2672104a4e7 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Thu, 20 Feb 2020 17:26:34 -0500
Subject: [PATCH 13/23] bnxt_en: Improve device shutdown method.

[ Upstream commit 5567ae4a8d569d996d0d88d0eceb76205e4c7ce5 ]

Especially when bnxt_shutdown() is called during kexec, we need to
disable MSIX and disable Bus Master to completely quiesce the device.
Make these 2 calls unconditionally in the shutdown method.

Fixes: c20dc142dd7b ("bnxt_en: Disable bus master during PCI shutdown and driver unload.")
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 9d62200b6c33..1a90118370ea 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -11972,10 +11972,10 @@ static void bnxt_shutdown(struct pci_dev *pdev)
 		dev_close(dev);
 
 	bnxt_ulp_shutdown(bp);
+	bnxt_clear_int_mode(bp);
+	pci_disable_device(pdev);
 
 	if (system_state == SYSTEM_POWER_OFF) {
-		bnxt_clear_int_mode(bp);
-		pci_disable_device(pdev);
 		pci_wake_from_d3(pdev, bp->wol);
 		pci_set_power_state(pdev, PCI_D3hot);
 	}
-- 
2.20.1


From 07f1ce164660d588ed15251137a7758667165370 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Thu, 20 Feb 2020 17:26:35 -0500
Subject: [PATCH 14/23] bnxt_en: Issue PCIe FLR in kdump kernel to cleanup
 pending DMAs.

[ Upstream commit 8743db4a9acfd51f805ac0c87bcaae92c42d1061 ]

If crashed kernel does not shutdown the NIC properly, PCIe FLR
is required in the kdump kernel in order to initialize all the
functions properly.

Fixes: d629522e1d66 ("bnxt_en: Reduce memory usage when running in kdump kernel.")
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 1a90118370ea..cc86038b1d96 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -11775,6 +11775,14 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (version_printed++ == 0)
 		pr_info("%s", version);
 
+	/* Clear any pending DMA transactions from crash kernel
+	 * while loading driver in capture kernel.
+	 */
+	if (is_kdump_kernel()) {
+		pci_clear_master(pdev);
+		pcie_flr(pdev);
+	}
+
 	max_irqs = bnxt_get_max_irq(pdev);
 	dev = alloc_etherdev_mq(sizeof(*bp), max_irqs);
 	if (!dev)
-- 
2.20.1


From 5e6f39e4cd1631dc83d781fbce07d2b69a5a1b94 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Sat, 15 Feb 2020 10:50:08 +0000
Subject: [PATCH 15/23] bonding: add missing netdev_update_lockdep_key()

[ Upstream commit 064ff66e2bef84f1153087612032b5b9eab005bd ]

After bond_release(), netdev_update_lockdep_key() should be called.
But both ioctl path and attribute path don't call
netdev_update_lockdep_key().
This patch adds missing netdev_update_lockdep_key().

Test commands:
    ip link add bond0 type bond
    ip link add bond1 type bond
    ifenslave bond0 bond1
    ifenslave -d bond0 bond1
    ifenslave bond1 bond0

Splat looks like:
[   29.501182][ T1046] WARNING: possible circular locking dependency detected
[   29.501945][ T1039] hardirqs last disabled at (1962): [<ffffffffac6c807f>] handle_mm_fault+0x13f/0x700
[   29.503442][ T1046] 5.5.0+ #322 Not tainted
[   29.503447][ T1046] ------------------------------------------------------
[   29.504277][ T1039] softirqs last  enabled at (1180): [<ffffffffade00678>] __do_softirq+0x678/0x981
[   29.505443][ T1046] ifenslave/1046 is trying to acquire lock:
[   29.505886][ T1039] softirqs last disabled at (1169): [<ffffffffac19c18a>] irq_exit+0x17a/0x1a0
[   29.509997][ T1046] ffff88805d5da280 (&dev->addr_list_lock_key#3){+...}, at: dev_mc_sync_multiple+0x95/0x120
[   29.511243][ T1046]
[   29.511243][ T1046] but task is already holding lock:
[   29.512192][ T1046] ffff8880460f2280 (&dev->addr_list_lock_key#4){+...}, at: bond_enslave+0x4482/0x47b0 [bonding]
[   29.514124][ T1046]
[   29.514124][ T1046] which lock already depends on the new lock.
[   29.514124][ T1046]
[   29.517297][ T1046]
[   29.517297][ T1046] the existing dependency chain (in reverse order) is:
[   29.518231][ T1046]
[   29.518231][ T1046] -> #1 (&dev->addr_list_lock_key#4){+...}:
[   29.519076][ T1046]        _raw_spin_lock+0x30/0x70
[   29.519588][ T1046]        dev_mc_sync_multiple+0x95/0x120
[   29.520208][ T1046]        bond_enslave+0x448d/0x47b0 [bonding]
[   29.520862][ T1046]        bond_option_slaves_set+0x1a3/0x370 [bonding]
[   29.521640][ T1046]        __bond_opt_set+0x1ff/0xbb0 [bonding]
[   29.522438][ T1046]        __bond_opt_set_notify+0x2b/0xf0 [bonding]
[   29.523251][ T1046]        bond_opt_tryset_rtnl+0x92/0xf0 [bonding]
[   29.524082][ T1046]        bonding_sysfs_store_option+0x8a/0xf0 [bonding]
[   29.524959][ T1046]        kernfs_fop_write+0x276/0x410
[   29.525620][ T1046]        vfs_write+0x197/0x4a0
[   29.526218][ T1046]        ksys_write+0x141/0x1d0
[   29.526818][ T1046]        do_syscall_64+0x99/0x4f0
[   29.527430][ T1046]        entry_SYSCALL_64_after_hwframe+0x49/0xbe
[   29.528265][ T1046]
[   29.528265][ T1046] -> #0 (&dev->addr_list_lock_key#3){+...}:
[   29.529272][ T1046]        __lock_acquire+0x2d8d/0x3de0
[   29.529935][ T1046]        lock_acquire+0x164/0x3b0
[   29.530638][ T1046]        _raw_spin_lock+0x30/0x70
[   29.531187][ T1046]        dev_mc_sync_multiple+0x95/0x120
[   29.531790][ T1046]        bond_enslave+0x448d/0x47b0 [bonding]
[   29.532451][ T1046]        bond_option_slaves_set+0x1a3/0x370 [bonding]
[   29.533163][ T1046]        __bond_opt_set+0x1ff/0xbb0 [bonding]
[   29.533789][ T1046]        __bond_opt_set_notify+0x2b/0xf0 [bonding]
[   29.534595][ T1046]        bond_opt_tryset_rtnl+0x92/0xf0 [bonding]
[   29.535500][ T1046]        bonding_sysfs_store_option+0x8a/0xf0 [bonding]
[   29.536379][ T1046]        kernfs_fop_write+0x276/0x410
[   29.537057][ T1046]        vfs_write+0x197/0x4a0
[   29.537640][ T1046]        ksys_write+0x141/0x1d0
[   29.538251][ T1046]        do_syscall_64+0x99/0x4f0
[   29.538870][ T1046]        entry_SYSCALL_64_after_hwframe+0x49/0xbe
[   29.539659][ T1046]
[   29.539659][ T1046] other info that might help us debug this:
[   29.539659][ T1046]
[   29.540953][ T1046]  Possible unsafe locking scenario:
[   29.540953][ T1046]
[   29.541883][ T1046]        CPU0                    CPU1
[   29.542540][ T1046]        ----                    ----
[   29.543209][ T1046]   lock(&dev->addr_list_lock_key#4);
[   29.543880][ T1046]                                lock(&dev->addr_list_lock_key#3);
[   29.544873][ T1046]                                lock(&dev->addr_list_lock_key#4);
[   29.545863][ T1046]   lock(&dev->addr_list_lock_key#3);
[   29.546525][ T1046]
[   29.546525][ T1046]  *** DEADLOCK ***
[   29.546525][ T1046]
[   29.547542][ T1046] 5 locks held by ifenslave/1046:
[   29.548196][ T1046]  #0: ffff88806044c478 (sb_writers#5){.+.+}, at: vfs_write+0x3bb/0x4a0
[   29.549248][ T1046]  #1: ffff88805af00890 (&of->mutex){+.+.}, at: kernfs_fop_write+0x1cf/0x410
[   29.550343][ T1046]  #2: ffff88805b8b54b0 (kn->count#157){.+.+}, at: kernfs_fop_write+0x1f2/0x410
[   29.551575][ T1046]  #3: ffffffffaecf4cf0 (rtnl_mutex){+.+.}, at: bond_opt_tryset_rtnl+0x5f/0xf0 [bonding]
[   29.552819][ T1046]  #4: ffff8880460f2280 (&dev->addr_list_lock_key#4){+...}, at: bond_enslave+0x4482/0x47b0 [bonding]
[   29.554175][ T1046]
[   29.554175][ T1046] stack backtrace:
[   29.554907][ T1046] CPU: 0 PID: 1046 Comm: ifenslave Not tainted 5.5.0+ #322
[   29.555854][ T1046] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[   29.557064][ T1046] Call Trace:
[   29.557504][ T1046]  dump_stack+0x96/0xdb
[   29.558054][ T1046]  check_noncircular+0x371/0x450
[   29.558723][ T1046]  ? print_circular_bug.isra.35+0x310/0x310
[   29.559486][ T1046]  ? hlock_class+0x130/0x130
[   29.560100][ T1046]  ? __lock_acquire+0x2d8d/0x3de0
[   29.560761][ T1046]  __lock_acquire+0x2d8d/0x3de0
[   29.561366][ T1046]  ? register_lock_class+0x14d0/0x14d0
[   29.562045][ T1046]  ? find_held_lock+0x39/0x1d0
[   29.562641][ T1046]  lock_acquire+0x164/0x3b0
[   29.563199][ T1046]  ? dev_mc_sync_multiple+0x95/0x120
[   29.563872][ T1046]  _raw_spin_lock+0x30/0x70
[   29.564464][ T1046]  ? dev_mc_sync_multiple+0x95/0x120
[   29.565146][ T1046]  dev_mc_sync_multiple+0x95/0x120
[   29.565793][ T1046]  bond_enslave+0x448d/0x47b0 [bonding]
[   29.566487][ T1046]  ? bond_update_slave_arr+0x940/0x940 [bonding]
[   29.567279][ T1046]  ? bstr_printf+0xc20/0xc20
[   29.567857][ T1046]  ? stack_trace_consume_entry+0x160/0x160
[   29.568614][ T1046]  ? deactivate_slab.isra.77+0x2c5/0x800
[   29.569320][ T1046]  ? check_chain_key+0x236/0x5d0
[   29.569939][ T1046]  ? sscanf+0x93/0xc0
[   29.570442][ T1046]  ? vsscanf+0x1e20/0x1e20
[   29.571003][ T1046]  bond_option_slaves_set+0x1a3/0x370 [bonding]
[ ... ]

Fixes: ab92d68fc22f ("net: core: add generic lockdep keys")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c    | 2 ++
 drivers/net/bonding/bond_options.c | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 48d5ec770b94..1e9d5d35fc78 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3640,6 +3640,8 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd
 	case BOND_RELEASE_OLD:
 	case SIOCBONDRELEASE:
 		res = bond_release(bond_dev, slave_dev);
+		if (!res)
+			netdev_update_lockdep_key(slave_dev);
 		break;
 	case BOND_SETHWADDR_OLD:
 	case SIOCBONDSETHWADDR:
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index ddb3916d3506..215c10923289 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -1398,6 +1398,8 @@ static int bond_option_slaves_set(struct bonding *bond,
 	case '-':
 		slave_dbg(bond->dev, dev, "Releasing interface\n");
 		ret = bond_release(bond->dev, dev);
+		if (!ret)
+			netdev_update_lockdep_key(dev);
 		break;
 
 	default:
-- 
2.20.1


From 1f8991edd52b9f6c07ea5660c2736970b4fac171 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Sat, 15 Feb 2020 10:50:21 +0000
Subject: [PATCH 16/23] net: export netdev_next_lower_dev_rcu()

[ Upstream commit 7151affeef8d527f50b4b68a871fd28bd660023f ]

netdev_next_lower_dev_rcu() will be used to implement a function,
which is to walk all lower interfaces.
There are already functions that they walk their lower interface.
(netdev_walk_all_lower_dev_rcu, netdev_walk_all_lower_dev()).
But, there would be cases that couldn't be covered by given
netdev_walk_all_lower_dev_{rcu}() function.
So, some modules would want to implement own function,
which is to walk all lower interfaces.

In the next patch, netdev_next_lower_dev_rcu() will be used.
In addition, this patch removes two unused prototypes in netdevice.h.

Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 7 +++----
 net/core/dev.c            | 6 +++---
 2 files changed, 6 insertions(+), 7 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index cac56fb59af8..1dabd86b232a 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -72,6 +72,8 @@ void netdev_set_default_ethtool_ops(struct net_device *dev,
 #define NET_RX_SUCCESS		0	/* keep 'em coming, baby */
 #define NET_RX_DROP		1	/* packet dropped */
 
+#define MAX_NEST_DEV 8
+
 /*
  * Transmit return codes: transmit return codes originate from three different
  * namespaces:
@@ -4323,11 +4325,8 @@ void *netdev_lower_get_next(struct net_device *dev,
 	     ldev; \
 	     ldev = netdev_lower_get_next(dev, &(iter)))
 
-struct net_device *netdev_all_lower_get_next(struct net_device *dev,
+struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
 					     struct list_head **iter);
-struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev,
-						 struct list_head **iter);
-
 int netdev_walk_all_lower_dev(struct net_device *dev,
 			      int (*fn)(struct net_device *lower_dev,
 					void *data),
diff --git a/net/core/dev.c b/net/core/dev.c
index 8461f4eba716..dabed5337a9d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -146,7 +146,6 @@
 #include "net-sysfs.h"
 
 #define MAX_GRO_SKBS 8
-#define MAX_NEST_DEV 8
 
 /* This should be increased if a protocol with a bigger head is added. */
 #define GRO_MAX_HEAD (MAX_HEADER + 128)
@@ -7135,8 +7134,8 @@ static int __netdev_walk_all_lower_dev(struct net_device *dev,
 	return 0;
 }
 
-static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
-						    struct list_head **iter)
+struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
+					     struct list_head **iter)
 {
 	struct netdev_adjacent *lower;
 
@@ -7148,6 +7147,7 @@ static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
 
 	return lower->dev;
 }
+EXPORT_SYMBOL(netdev_next_lower_dev_rcu);
 
 static u8 __netdev_upper_depth(struct net_device *dev)
 {
-- 
2.20.1


From 9131b2de9fecfa6e4041b67de59fa7b7931b4f74 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Sat, 15 Feb 2020 10:50:40 +0000
Subject: [PATCH 17/23] bonding: fix lockdep warning in bond_get_stats()

[ Upstream commit b3e80d44f5b1b470dd9e2dbc6816e63a5c519709 ]

In the "struct bonding", there is stats_lock.
This lock protects "bond_stats" in the "struct bonding".
bond_stats is updated in the bond_get_stats() and this function would be
executed concurrently. So, the lock is needed.

Bonding interfaces would be nested.
So, either stats_lock should use dynamic lockdep class key or stats_lock
should be used by spin_lock_nested(). In the current code, stats_lock is
using a dynamic lockdep class key.
But there is no updating stats_lock_key routine So, lockdep warning
will occur.

Test commands:
    ip link add bond0 type bond
    ip link add bond1 type bond
    ip link set bond0 master bond1
    ip link set bond0 nomaster
    ip link set bond1 master bond0

Splat looks like:
[   38.420603][  T957] 5.5.0+ #394 Not tainted
[   38.421074][  T957] ------------------------------------------------------
[   38.421837][  T957] ip/957 is trying to acquire lock:
[   38.422399][  T957] ffff888063262cd8 (&bond->stats_lock_key#2){+.+.}, at: bond_get_stats+0x90/0x4d0 [bonding]
[   38.423528][  T957]
[   38.423528][  T957] but task is already holding lock:
[   38.424526][  T957] ffff888065fd2cd8 (&bond->stats_lock_key){+.+.}, at: bond_get_stats+0x90/0x4d0 [bonding]
[   38.426075][  T957]
[   38.426075][  T957] which lock already depends on the new lock.
[   38.426075][  T957]
[   38.428536][  T957]
[   38.428536][  T957] the existing dependency chain (in reverse order) is:
[   38.429475][  T957]
[   38.429475][  T957] -> #1 (&bond->stats_lock_key){+.+.}:
[   38.430273][  T957]        _raw_spin_lock+0x30/0x70
[   38.430812][  T957]        bond_get_stats+0x90/0x4d0 [bonding]
[   38.431451][  T957]        dev_get_stats+0x1ec/0x270
[   38.432088][  T957]        bond_get_stats+0x1a5/0x4d0 [bonding]
[   38.432767][  T957]        dev_get_stats+0x1ec/0x270
[   38.433322][  T957]        rtnl_fill_stats+0x44/0xbe0
[   38.433866][  T957]        rtnl_fill_ifinfo+0xeb2/0x3720
[   38.434474][  T957]        rtmsg_ifinfo_build_skb+0xca/0x170
[   38.435081][  T957]        rtmsg_ifinfo_event.part.33+0x1b/0xb0
[   38.436848][  T957]        rtnetlink_event+0xcd/0x120
[   38.437455][  T957]        notifier_call_chain+0x90/0x160
[   38.438067][  T957]        netdev_change_features+0x74/0xa0
[   38.438708][  T957]        bond_compute_features.isra.45+0x4e6/0x6f0 [bonding]
[   38.439522][  T957]        bond_enslave+0x3639/0x47b0 [bonding]
[   38.440225][  T957]        do_setlink+0xaab/0x2ef0
[   38.440786][  T957]        __rtnl_newlink+0x9c5/0x1270
[   38.441463][  T957]        rtnl_newlink+0x65/0x90
[   38.442075][  T957]        rtnetlink_rcv_msg+0x4a8/0x890
[   38.442774][  T957]        netlink_rcv_skb+0x121/0x350
[   38.443451][  T957]        netlink_unicast+0x42e/0x610
[   38.444282][  T957]        netlink_sendmsg+0x65a/0xb90
[   38.444992][  T957]        ____sys_sendmsg+0x5ce/0x7a0
[   38.445679][  T957]        ___sys_sendmsg+0x10f/0x1b0
[   38.446365][  T957]        __sys_sendmsg+0xc6/0x150
[   38.447007][  T957]        do_syscall_64+0x99/0x4f0
[   38.447668][  T957]        entry_SYSCALL_64_after_hwframe+0x49/0xbe
[   38.448538][  T957]
[   38.448538][  T957] -> #0 (&bond->stats_lock_key#2){+.+.}:
[   38.449554][  T957]        __lock_acquire+0x2d8d/0x3de0
[   38.450148][  T957]        lock_acquire+0x164/0x3b0
[   38.450711][  T957]        _raw_spin_lock+0x30/0x70
[   38.451292][  T957]        bond_get_stats+0x90/0x4d0 [bonding]
[   38.451950][  T957]        dev_get_stats+0x1ec/0x270
[   38.452425][  T957]        bond_get_stats+0x1a5/0x4d0 [bonding]
[   38.453362][  T957]        dev_get_stats+0x1ec/0x270
[   38.453825][  T957]        rtnl_fill_stats+0x44/0xbe0
[   38.454390][  T957]        rtnl_fill_ifinfo+0xeb2/0x3720
[   38.456257][  T957]        rtmsg_ifinfo_build_skb+0xca/0x170
[   38.456998][  T957]        rtmsg_ifinfo_event.part.33+0x1b/0xb0
[   38.459351][  T957]        rtnetlink_event+0xcd/0x120
[   38.460086][  T957]        notifier_call_chain+0x90/0x160
[   38.460829][  T957]        netdev_change_features+0x74/0xa0
[   38.461752][  T957]        bond_compute_features.isra.45+0x4e6/0x6f0 [bonding]
[   38.462705][  T957]        bond_enslave+0x3639/0x47b0 [bonding]
[   38.463476][  T957]        do_setlink+0xaab/0x2ef0
[   38.464141][  T957]        __rtnl_newlink+0x9c5/0x1270
[   38.464897][  T957]        rtnl_newlink+0x65/0x90
[   38.465522][  T957]        rtnetlink_rcv_msg+0x4a8/0x890
[   38.466215][  T957]        netlink_rcv_skb+0x121/0x350
[   38.466895][  T957]        netlink_unicast+0x42e/0x610
[   38.467583][  T957]        netlink_sendmsg+0x65a/0xb90
[   38.468285][  T957]        ____sys_sendmsg+0x5ce/0x7a0
[   38.469202][  T957]        ___sys_sendmsg+0x10f/0x1b0
[   38.469884][  T957]        __sys_sendmsg+0xc6/0x150
[   38.470587][  T957]        do_syscall_64+0x99/0x4f0
[   38.471245][  T957]        entry_SYSCALL_64_after_hwframe+0x49/0xbe
[   38.472093][  T957]
[   38.472093][  T957] other info that might help us debug this:
[   38.472093][  T957]
[   38.473438][  T957]  Possible unsafe locking scenario:
[   38.473438][  T957]
[   38.474898][  T957]        CPU0                    CPU1
[   38.476234][  T957]        ----                    ----
[   38.480171][  T957]   lock(&bond->stats_lock_key);
[   38.480808][  T957]                                lock(&bond->stats_lock_key#2);
[   38.481791][  T957]                                lock(&bond->stats_lock_key);
[   38.482754][  T957]   lock(&bond->stats_lock_key#2);
[   38.483416][  T957]
[   38.483416][  T957]  *** DEADLOCK ***
[   38.483416][  T957]
[   38.484505][  T957] 3 locks held by ip/957:
[   38.485048][  T957]  #0: ffffffffbccf6230 (rtnl_mutex){+.+.}, at: rtnetlink_rcv_msg+0x457/0x890
[   38.486198][  T957]  #1: ffff888065fd2cd8 (&bond->stats_lock_key){+.+.}, at: bond_get_stats+0x90/0x4d0 [bonding]
[   38.487625][  T957]  #2: ffffffffbc9254c0 (rcu_read_lock){....}, at: bond_get_stats+0x5/0x4d0 [bonding]
[   38.488897][  T957]
[   38.488897][  T957] stack backtrace:
[   38.489646][  T957] CPU: 1 PID: 957 Comm: ip Not tainted 5.5.0+ #394
[   38.490497][  T957] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[   38.492810][  T957] Call Trace:
[   38.493219][  T957]  dump_stack+0x96/0xdb
[   38.493709][  T957]  check_noncircular+0x371/0x450
[   38.494344][  T957]  ? lookup_address+0x60/0x60
[   38.494923][  T957]  ? print_circular_bug.isra.35+0x310/0x310
[   38.495699][  T957]  ? hlock_class+0x130/0x130
[   38.496334][  T957]  ? __lock_acquire+0x2d8d/0x3de0
[   38.496979][  T957]  __lock_acquire+0x2d8d/0x3de0
[   38.497607][  T957]  ? register_lock_class+0x14d0/0x14d0
[   38.498333][  T957]  ? check_chain_key+0x236/0x5d0
[   38.499003][  T957]  lock_acquire+0x164/0x3b0
[   38.499800][  T957]  ? bond_get_stats+0x90/0x4d0 [bonding]
[   38.500706][  T957]  _raw_spin_lock+0x30/0x70
[   38.501435][  T957]  ? bond_get_stats+0x90/0x4d0 [bonding]
[   38.502311][  T957]  bond_get_stats+0x90/0x4d0 [bonding]
[ ... ]

But, there is another problem.
The dynamic lockdep class key is protected by RTNL, but bond_get_stats()
would be called outside of RTNL.
So, it would use an invalid dynamic lockdep class key.

In order to fix this issue, stats_lock uses spin_lock_nested() instead of
a dynamic lockdep key.
The bond_get_stats() calls bond_get_lowest_level_rcu() to get the correct
nest level value, which will be used by spin_lock_nested().
The "dev->lower_level" indicates lower nest level value, but this value
is invalid outside of RTNL.
So, bond_get_lowest_level_rcu() returns valid lower nest level value in
the RCU critical section.
bond_get_lowest_level_rcu() will be work only when LOCKDEP is enabled.

Fixes: 089bca2caed0 ("bonding: use dynamic lockdep key instead of subclass")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 53 +++++++++++++++++++++++++++++++--
 1 file changed, 50 insertions(+), 3 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 1e9d5d35fc78..d10805e5e623 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3526,6 +3526,47 @@ static void bond_fold_stats(struct rtnl_link_stats64 *_res,
 	}
 }
 
+#ifdef CONFIG_LOCKDEP
+static int bond_get_lowest_level_rcu(struct net_device *dev)
+{
+	struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
+	struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
+	int cur = 0, max = 0;
+
+	now = dev;
+	iter = &dev->adj_list.lower;
+
+	while (1) {
+		next = NULL;
+		while (1) {
+			ldev = netdev_next_lower_dev_rcu(now, &iter);
+			if (!ldev)
+				break;
+
+			next = ldev;
+			niter = &ldev->adj_list.lower;
+			dev_stack[cur] = now;
+			iter_stack[cur++] = iter;
+			if (max <= cur)
+				max = cur;
+			break;
+		}
+
+		if (!next) {
+			if (!cur)
+				return max;
+			next = dev_stack[--cur];
+			niter = iter_stack[cur];
+		}
+
+		now = next;
+		iter = niter;
+	}
+
+	return max;
+}
+#endif
+
 static void bond_get_stats(struct net_device *bond_dev,
 			   struct rtnl_link_stats64 *stats)
 {
@@ -3533,11 +3574,17 @@ static void bond_get_stats(struct net_device *bond_dev,
 	struct rtnl_link_stats64 temp;
 	struct list_head *iter;
 	struct slave *slave;
+	int nest_level = 0;
 
-	spin_lock(&bond->stats_lock);
-	memcpy(stats, &bond->bond_stats, sizeof(*stats));
 
 	rcu_read_lock();
+#ifdef CONFIG_LOCKDEP
+	nest_level = bond_get_lowest_level_rcu(bond_dev);
+#endif
+
+	spin_lock_nested(&bond->stats_lock, nest_level);
+	memcpy(stats, &bond->bond_stats, sizeof(*stats));
+
 	bond_for_each_slave_rcu(bond, slave, iter) {
 		const struct rtnl_link_stats64 *new =
 			dev_get_stats(slave->dev, &temp);
@@ -3547,10 +3594,10 @@ static void bond_get_stats(struct net_device *bond_dev,
 		/* save off the slave stats for the next run */
 		memcpy(&slave->slave_stats, new, sizeof(*new));
 	}
-	rcu_read_unlock();
 
 	memcpy(&bond->bond_stats, stats, sizeof(*stats));
 	spin_unlock(&bond->stats_lock);
+	rcu_read_unlock();
 }
 
 static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd)
-- 
2.20.1


From c75dd5a4fe5b56d9356b57f54b676be7071fb462 Mon Sep 17 00:00:00 2001
From: Benjamin Poirier <bpoirier@cumulusnetworks.com>
Date: Wed, 12 Feb 2020 10:41:06 +0900
Subject: [PATCH 18/23] ipv6: Fix route replacement with dev-only route

[ Upstream commit e404b8c7cfb31654c9024d497cec58a501501692 ]

After commit 27596472473a ("ipv6: fix ECMP route replacement") it is no
longer possible to replace an ECMP-able route by a non ECMP-able route.
For example,
	ip route add 2001:db8::1/128 via fe80::1 dev dummy0
	ip route replace 2001:db8::1/128 dev dummy0
does not work as expected.

Tweak the replacement logic so that point 3 in the log of the above commit
becomes:
3. If the new route is not ECMP-able, and no matching non-ECMP-able route
exists, replace matching ECMP-able route (if any) or add the new route.

We can now summarize the entire replace semantics to:
When doing a replace, prefer replacing a matching route of the same
"ECMP-able-ness" as the replace argument. If there is no such candidate,
fallback to the first route found.

Fixes: 27596472473a ("ipv6: fix ECMP route replacement")
Signed-off-by: Benjamin Poirier <bpoirier@cumulusnetworks.com>
Reviewed-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_fib.c                       | 7 ++++---
 tools/testing/selftests/net/fib_tests.sh | 6 ++++++
 2 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index cfae0a1529a1..bde3bf180871 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1068,8 +1068,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
 					found++;
 					break;
 				}
-				if (rt_can_ecmp)
-					fallback_ins = fallback_ins ?: ins;
+				fallback_ins = fallback_ins ?: ins;
 				goto next_iter;
 			}
 
@@ -1112,7 +1111,9 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
 	}
 
 	if (fallback_ins && !found) {
-		/* No ECMP-able route found, replace first non-ECMP one */
+		/* No matching route with same ecmp-able-ness found, replace
+		 * first matching route
+		 */
 		ins = fallback_ins;
 		iter = rcu_dereference_protected(*ins,
 				    lockdep_is_held(&rt->fib6_table->tb6_lock));
diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 6dd403103800..60273f1bc7d9 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -910,6 +910,12 @@ ipv6_rt_replace_mpath()
 	check_route6 "2001:db8:104::/64 via 2001:db8:101::3 dev veth1 metric 1024"
 	log_test $? 0 "Multipath with single path via multipath attribute"
 
+	# multipath with dev-only
+	add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
+	run_cmd "$IP -6 ro replace 2001:db8:104::/64 dev veth1"
+	check_route6 "2001:db8:104::/64 dev veth1 metric 1024"
+	log_test $? 0 "Multipath with dev-only"
+
 	# route replace fails - invalid nexthop 1
 	add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
 	run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:111::3 nexthop via 2001:db8:103::3"
-- 
2.20.1


From 565282ea257fc391bdd002d86dfd7ec73b68fee6 Mon Sep 17 00:00:00 2001
From: Benjamin Poirier <bpoirier@cumulusnetworks.com>
Date: Wed, 12 Feb 2020 10:41:07 +0900
Subject: [PATCH 19/23] ipv6: Fix nlmsg_flags when splitting a multipath route

[ Upstream commit afecdb376bd81d7e16578f0cfe82a1aec7ae18f3 ]

When splitting an RTA_MULTIPATH request into multiple routes and adding the
second and later components, we must not simply remove NLM_F_REPLACE but
instead replace it by NLM_F_CREATE. Otherwise, it may look like the netlink
message was malformed.

For example,
	ip route add 2001:db8::1/128 dev dummy0
	ip route change 2001:db8::1/128 nexthop via fe80::30:1 dev dummy0 \
		nexthop via fe80::30:2 dev dummy0
results in the following warnings:
[ 1035.057019] IPv6: RTM_NEWROUTE with no NLM_F_CREATE or NLM_F_REPLACE
[ 1035.057517] IPv6: NLM_F_CREATE should be set when creating new route

This patch makes the nlmsg sequence look equivalent for __ip6_ins_rt() to
what it would get if the multipath route had been added in multiple netlink
operations:
	ip route add 2001:db8::1/128 dev dummy0
	ip route change 2001:db8::1/128 nexthop via fe80::30:1 dev dummy0
	ip route append 2001:db8::1/128 nexthop via fe80::30:2 dev dummy0

Fixes: 27596472473a ("ipv6: fix ECMP route replacement")
Signed-off-by: Benjamin Poirier <bpoirier@cumulusnetworks.com>
Reviewed-by: Michal Kubecek <mkubecek@suse.cz>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index affb51c11a25..119c7226c4be 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -5152,6 +5152,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 		 */
 		cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL |
 						     NLM_F_REPLACE);
+		cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_CREATE;
 		nhn++;
 	}
 
-- 
2.20.1


From 2b1a5d75958ebf4029de67ad11c3cdb3a866568a Mon Sep 17 00:00:00 2001
From: Shannon Nelson <snelson@pensando.io>
Date: Wed, 19 Feb 2020 14:59:42 -0800
Subject: [PATCH 20/23] ionic: fix fw_status read

[ Upstream commit 68b759a75d6257759d1e37ff13f2d0659baf1112 ]

The fw_status field is only 8 bits, so fix the read.  Also,
we only want to look at the one status bit, to allow for future
use of the other bits, and watch for a bad PCI read.

Fixes: 97ca486592c0 ("ionic: add heartbeat check")
Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/pensando/ionic/ionic_dev.c | 11 +++++++----
 drivers/net/ethernet/pensando/ionic/ionic_if.h  |  1 +
 2 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c
index 5f9d2ec70446..61c06fbe10db 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c
@@ -103,7 +103,7 @@ int ionic_heartbeat_check(struct ionic *ionic)
 {
 	struct ionic_dev *idev = &ionic->idev;
 	unsigned long hb_time;
-	u32 fw_status;
+	u8 fw_status;
 	u32 hb;
 
 	/* wait a little more than one second before testing again */
@@ -111,9 +111,12 @@ int ionic_heartbeat_check(struct ionic *ionic)
 	if (time_before(hb_time, (idev->last_hb_time + ionic->watchdog_period)))
 		return 0;
 
-	/* firmware is useful only if fw_status is non-zero */
-	fw_status = ioread32(&idev->dev_info_regs->fw_status);
-	if (!fw_status)
+	/* firmware is useful only if the running bit is set and
+	 * fw_status != 0xff (bad PCI read)
+	 */
+	fw_status = ioread8(&idev->dev_info_regs->fw_status);
+	if (fw_status == 0xff ||
+	    !(fw_status & IONIC_FW_STS_F_RUNNING))
 		return -ENXIO;
 
 	/* early FW has no heartbeat, else FW will return non-zero */
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_if.h b/drivers/net/ethernet/pensando/ionic/ionic_if.h
index ed23a05f2642..d5e8b4e2a96e 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_if.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_if.h
@@ -2348,6 +2348,7 @@ union ionic_dev_info_regs {
 		u8     version;
 		u8     asic_type;
 		u8     asic_rev;
+#define IONIC_FW_STS_F_RUNNING	0x1
 		u8     fw_status;
 		u32    fw_heartbeat;
 		char   fw_version[IONIC_DEVINFO_FWVERS_BUFLEN];
-- 
2.20.1


From a221c1f27ded6d1aa8fbba1e117ccfa444f5d940 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 14 Feb 2020 07:53:53 -0800
Subject: [PATCH 21/23] net: add strict checks in
 netdev_name_node_alt_destroy()

[ Upstream commit e08ad80551b4b33c02f2fce1522f6c227d3976cf ]

netdev_name_node_alt_destroy() does a lookup over all
device names of a namespace.

We need to make sure the name belongs to the device
of interest, and that we do not destroy its primary
name, since we rely on it being not deleted :
dev->name_node would indeed point to freed memory.

syzbot report was the following :

BUG: KASAN: use-after-free in dev_net include/linux/netdevice.h:2206 [inline]
BUG: KASAN: use-after-free in mld_force_mld_version net/ipv6/mcast.c:1172 [inline]
BUG: KASAN: use-after-free in mld_in_v2_mode_only net/ipv6/mcast.c:1180 [inline]
BUG: KASAN: use-after-free in mld_in_v1_mode+0x203/0x230 net/ipv6/mcast.c:1190
Read of size 8 at addr ffff88809886c588 by task swapper/1/0

CPU: 1 PID: 0 Comm: swapper/1 Not tainted 5.6.0-rc1-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x197/0x210 lib/dump_stack.c:118
 print_address_description.constprop.0.cold+0xd4/0x30b mm/kasan/report.c:374
 __kasan_report.cold+0x1b/0x32 mm/kasan/report.c:506
 kasan_report+0x12/0x20 mm/kasan/common.c:641
 __asan_report_load8_noabort+0x14/0x20 mm/kasan/generic_report.c:135
 dev_net include/linux/netdevice.h:2206 [inline]
 mld_force_mld_version net/ipv6/mcast.c:1172 [inline]
 mld_in_v2_mode_only net/ipv6/mcast.c:1180 [inline]
 mld_in_v1_mode+0x203/0x230 net/ipv6/mcast.c:1190
 mld_send_initial_cr net/ipv6/mcast.c:2083 [inline]
 mld_dad_timer_expire+0x24/0x230 net/ipv6/mcast.c:2118
 call_timer_fn+0x1ac/0x780 kernel/time/timer.c:1404
 expire_timers kernel/time/timer.c:1449 [inline]
 __run_timers kernel/time/timer.c:1773 [inline]
 __run_timers kernel/time/timer.c:1740 [inline]
 run_timer_softirq+0x6c3/0x1790 kernel/time/timer.c:1786
 __do_softirq+0x262/0x98c kernel/softirq.c:292
 invoke_softirq kernel/softirq.c:373 [inline]
 irq_exit+0x19b/0x1e0 kernel/softirq.c:413
 exiting_irq arch/x86/include/asm/apic.h:546 [inline]
 smp_apic_timer_interrupt+0x1a3/0x610 arch/x86/kernel/apic/apic.c:1146
 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:829
 </IRQ>
RIP: 0010:native_safe_halt+0xe/0x10 arch/x86/include/asm/irqflags.h:61
Code: 68 73 c5 f9 eb 8a cc cc cc cc cc cc e9 07 00 00 00 0f 00 2d 94 be 59 00 f4 c3 66 90 e9 07 00 00 00 0f 00 2d 84 be 59 00 fb f4 <c3> cc 55 48 89 e5 41 57 41 56 41 55 41 54 53 e8 de 2a 74 f9 e8 09
RSP: 0018:ffffc90000d3fd68 EFLAGS: 00000282 ORIG_RAX: ffffffffffffff13
RAX: 1ffffffff136761a RBX: ffff8880a99fc340 RCX: 0000000000000000
RDX: dffffc0000000000 RSI: 0000000000000006 RDI: ffff8880a99fcbd4
RBP: ffffc90000d3fd98 R08: ffff8880a99fc340 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: dffffc0000000000
R13: ffffffff8aa5a1c0 R14: 0000000000000000 R15: 0000000000000001
 arch_cpu_idle+0xa/0x10 arch/x86/kernel/process.c:686
 default_idle_call+0x84/0xb0 kernel/sched/idle.c:94
 cpuidle_idle_call kernel/sched/idle.c:154 [inline]
 do_idle+0x3c8/0x6e0 kernel/sched/idle.c:269
 cpu_startup_entry+0x1b/0x20 kernel/sched/idle.c:361
 start_secondary+0x2f4/0x410 arch/x86/kernel/smpboot.c:264
 secondary_startup_64+0xa4/0xb0 arch/x86/kernel/head_64.S:242

Allocated by task 10229:
 save_stack+0x23/0x90 mm/kasan/common.c:72
 set_track mm/kasan/common.c:80 [inline]
 __kasan_kmalloc mm/kasan/common.c:515 [inline]
 __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:488
 kasan_kmalloc+0x9/0x10 mm/kasan/common.c:529
 __do_kmalloc_node mm/slab.c:3616 [inline]
 __kmalloc_node+0x4e/0x70 mm/slab.c:3623
 kmalloc_node include/linux/slab.h:578 [inline]
 kvmalloc_node+0x68/0x100 mm/util.c:574
 kvmalloc include/linux/mm.h:645 [inline]
 kvzalloc include/linux/mm.h:653 [inline]
 alloc_netdev_mqs+0x98/0xe40 net/core/dev.c:9797
 rtnl_create_link+0x22d/0xaf0 net/core/rtnetlink.c:3047
 __rtnl_newlink+0xf9f/0x1790 net/core/rtnetlink.c:3309
 rtnl_newlink+0x69/0xa0 net/core/rtnetlink.c:3377
 rtnetlink_rcv_msg+0x45e/0xaf0 net/core/rtnetlink.c:5438
 netlink_rcv_skb+0x177/0x450 net/netlink/af_netlink.c:2477
 rtnetlink_rcv+0x1d/0x30 net/core/rtnetlink.c:5456
 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
 netlink_unicast+0x59e/0x7e0 net/netlink/af_netlink.c:1328
 netlink_sendmsg+0x91c/0xea0 net/netlink/af_netlink.c:1917
 sock_sendmsg_nosec net/socket.c:652 [inline]
 sock_sendmsg+0xd7/0x130 net/socket.c:672
 __sys_sendto+0x262/0x380 net/socket.c:1998
 __do_compat_sys_socketcall net/compat.c:771 [inline]
 __se_compat_sys_socketcall net/compat.c:719 [inline]
 __ia32_compat_sys_socketcall+0x530/0x710 net/compat.c:719
 do_syscall_32_irqs_on arch/x86/entry/common.c:337 [inline]
 do_fast_syscall_32+0x27b/0xe16 arch/x86/entry/common.c:408
 entry_SYSENTER_compat+0x70/0x7f arch/x86/entry/entry_64_compat.S:139

Freed by task 10229:
 save_stack+0x23/0x90 mm/kasan/common.c:72
 set_track mm/kasan/common.c:80 [inline]
 kasan_set_free_info mm/kasan/common.c:337 [inline]
 __kasan_slab_free+0x102/0x150 mm/kasan/common.c:476
 kasan_slab_free+0xe/0x10 mm/kasan/common.c:485
 __cache_free mm/slab.c:3426 [inline]
 kfree+0x10a/0x2c0 mm/slab.c:3757
 __netdev_name_node_alt_destroy+0x1ff/0x2a0 net/core/dev.c:322
 netdev_name_node_alt_destroy+0x57/0x80 net/core/dev.c:334
 rtnl_alt_ifname net/core/rtnetlink.c:3518 [inline]
 rtnl_linkprop.isra.0+0x575/0x6f0 net/core/rtnetlink.c:3567
 rtnl_dellinkprop+0x46/0x60 net/core/rtnetlink.c:3588
 rtnetlink_rcv_msg+0x45e/0xaf0 net/core/rtnetlink.c:5438
 netlink_rcv_skb+0x177/0x450 net/netlink/af_netlink.c:2477
 rtnetlink_rcv+0x1d/0x30 net/core/rtnetlink.c:5456
 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
 netlink_unicast+0x59e/0x7e0 net/netlink/af_netlink.c:1328
 netlink_sendmsg+0x91c/0xea0 net/netlink/af_netlink.c:1917
 sock_sendmsg_nosec net/socket.c:652 [inline]
 sock_sendmsg+0xd7/0x130 net/socket.c:672
 ____sys_sendmsg+0x753/0x880 net/socket.c:2343
 ___sys_sendmsg+0x100/0x170 net/socket.c:2397
 __sys_sendmsg+0x105/0x1d0 net/socket.c:2430
 __compat_sys_sendmsg net/compat.c:642 [inline]
 __do_compat_sys_sendmsg net/compat.c:649 [inline]
 __se_compat_sys_sendmsg net/compat.c:646 [inline]
 __ia32_compat_sys_sendmsg+0x7a/0xb0 net/compat.c:646
 do_syscall_32_irqs_on arch/x86/entry/common.c:337 [inline]
 do_fast_syscall_32+0x27b/0xe16 arch/x86/entry/common.c:408
 entry_SYSENTER_compat+0x70/0x7f arch/x86/entry/entry_64_compat.S:139

The buggy address belongs to the object at ffff88809886c000
 which belongs to the cache kmalloc-4k of size 4096
The buggy address is located 1416 bytes inside of
 4096-byte region [ffff88809886c000, ffff88809886d000)
The buggy address belongs to the page:
page:ffffea0002621b00 refcount:1 mapcount:0 mapping:ffff8880aa402000 index:0x0 compound_mapcount: 0
flags: 0xfffe0000010200(slab|head)
raw: 00fffe0000010200 ffffea0002610d08 ffffea0002607608 ffff8880aa402000
raw: 0000000000000000 ffff88809886c000 0000000100000001 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff88809886c480: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff88809886c500: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff88809886c580: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                      ^
 ffff88809886c600: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff88809886c680: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb

Fixes: 36fbf1e52bd3 ("net: rtnetlink: add linkprop commands to add and delete alternative ifnames")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Jiri Pirko <jiri@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/core/dev.c b/net/core/dev.c
index dabed5337a9d..c3da35f3c7e4 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -330,6 +330,12 @@ int netdev_name_node_alt_destroy(struct net_device *dev, const char *name)
 	name_node = netdev_name_node_lookup(net, name);
 	if (!name_node)
 		return -ENOENT;
+	/* lookup might have found our primary name or a name belonging
+	 * to another device.
+	 */
+	if (name_node == dev->name_node || name_node->dev != dev)
+		return -EINVAL;
+
 	__netdev_name_node_alt_destroy(name_node);
 
 	return 0;
-- 
2.20.1


From 260e3b53dcdf9cebaa2f4eb5c268d820dee682cd Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Wed, 19 Feb 2020 15:15:51 +0100
Subject: [PATCH 22/23] net: macb: Properly handle phylink on at91rm9200

[ Upstream commit ac2fcfa9fd26db67d7000677c05629c34cc94564 ]

at91ether_init was handling the phy mode and speed but since the switch to
phylink, the NCFGR register got overwritten by macb_mac_config(). The issue
is that the RM9200_RMII bit and the MACB_CLK_DIV32 field are cleared
but never restored as they conflict with the PAE, GBE and PCSSEL bits.

Add new capability to differentiate between EMAC and the other versions of
the IP and use it to set and avoid clearing the relevant bits.

Also, this fixes a NULL pointer dereference in macb_mac_link_up as the EMAC
doesn't use any rings/bufffers/queues.

Fixes: 7897b071ac3b ("net: macb: convert to phylink")
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb.h      |  1 +
 drivers/net/ethernet/cadence/macb_main.c | 60 +++++++++++++-----------
 2 files changed, 33 insertions(+), 28 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index 19fe4f4867c7..c16cc1cb5874 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -645,6 +645,7 @@
 #define MACB_CAPS_GEM_HAS_PTP			0x00000040
 #define MACB_CAPS_BD_RD_PREFETCH		0x00000080
 #define MACB_CAPS_NEEDS_RSTONUBR		0x00000100
+#define MACB_CAPS_MACB_IS_EMAC			0x08000000
 #define MACB_CAPS_FIFO_MODE			0x10000000
 #define MACB_CAPS_GIGABIT_MODE_AVAILABLE	0x20000000
 #define MACB_CAPS_SG_DISABLED			0x40000000
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index e916fc223621..20db44d7cda8 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -533,8 +533,21 @@ static void macb_mac_config(struct phylink_config *config, unsigned int mode,
 	old_ctrl = ctrl = macb_or_gem_readl(bp, NCFGR);
 
 	/* Clear all the bits we might set later */
-	ctrl &= ~(GEM_BIT(GBE) | MACB_BIT(SPD) | MACB_BIT(FD) | MACB_BIT(PAE) |
-		  GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL));
+	ctrl &= ~(MACB_BIT(SPD) | MACB_BIT(FD) | MACB_BIT(PAE));
+
+	if (bp->caps & MACB_CAPS_MACB_IS_EMAC) {
+		if (state->interface == PHY_INTERFACE_MODE_RMII)
+			ctrl |= MACB_BIT(RM9200_RMII);
+	} else {
+		ctrl &= ~(GEM_BIT(GBE) | GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL));
+
+		/* We do not support MLO_PAUSE_RX yet */
+		if (state->pause & MLO_PAUSE_TX)
+			ctrl |= MACB_BIT(PAE);
+
+		if (state->interface == PHY_INTERFACE_MODE_SGMII)
+			ctrl |= GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL);
+	}
 
 	if (state->speed == SPEED_1000)
 		ctrl |= GEM_BIT(GBE);
@@ -544,13 +557,6 @@ static void macb_mac_config(struct phylink_config *config, unsigned int mode,
 	if (state->duplex)
 		ctrl |= MACB_BIT(FD);
 
-	/* We do not support MLO_PAUSE_RX yet */
-	if (state->pause & MLO_PAUSE_TX)
-		ctrl |= MACB_BIT(PAE);
-
-	if (state->interface == PHY_INTERFACE_MODE_SGMII)
-		ctrl |= GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL);
-
 	/* Apply the new configuration, if any */
 	if (old_ctrl ^ ctrl)
 		macb_or_gem_writel(bp, NCFGR, ctrl);
@@ -569,9 +575,10 @@ static void macb_mac_link_down(struct phylink_config *config, unsigned int mode,
 	unsigned int q;
 	u32 ctrl;
 
-	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
-		queue_writel(queue, IDR,
-			     bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP));
+	if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC))
+		for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
+			queue_writel(queue, IDR,
+				     bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP));
 
 	/* Disable Rx and Tx */
 	ctrl = macb_readl(bp, NCR) & ~(MACB_BIT(RE) | MACB_BIT(TE));
@@ -588,17 +595,19 @@ static void macb_mac_link_up(struct phylink_config *config, unsigned int mode,
 	struct macb_queue *queue;
 	unsigned int q;
 
-	macb_set_tx_clk(bp->tx_clk, bp->speed, ndev);
+	if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC)) {
+		macb_set_tx_clk(bp->tx_clk, bp->speed, ndev);
 
-	/* Initialize rings & buffers as clearing MACB_BIT(TE) in link down
-	 * cleared the pipeline and control registers.
-	 */
-	bp->macbgem_ops.mog_init_rings(bp);
-	macb_init_buffers(bp);
+		/* Initialize rings & buffers as clearing MACB_BIT(TE) in link down
+		 * cleared the pipeline and control registers.
+		 */
+		bp->macbgem_ops.mog_init_rings(bp);
+		macb_init_buffers(bp);
 
-	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
-		queue_writel(queue, IER,
-			     bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP));
+		for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
+			queue_writel(queue, IER,
+				     bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP));
+	}
 
 	/* Enable Rx and Tx */
 	macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(RE) | MACB_BIT(TE));
@@ -4002,7 +4011,6 @@ static int at91ether_init(struct platform_device *pdev)
 	struct net_device *dev = platform_get_drvdata(pdev);
 	struct macb *bp = netdev_priv(dev);
 	int err;
-	u32 reg;
 
 	bp->queues[0].bp = bp;
 
@@ -4016,11 +4024,7 @@ static int at91ether_init(struct platform_device *pdev)
 
 	macb_writel(bp, NCR, 0);
 
-	reg = MACB_BF(CLK, MACB_CLK_DIV32) | MACB_BIT(BIG);
-	if (bp->phy_interface == PHY_INTERFACE_MODE_RMII)
-		reg |= MACB_BIT(RM9200_RMII);
-
-	macb_writel(bp, NCFGR, reg);
+	macb_writel(bp, NCFGR, MACB_BF(CLK, MACB_CLK_DIV32) | MACB_BIT(BIG));
 
 	return 0;
 }
@@ -4179,7 +4183,7 @@ static const struct macb_config sama5d4_config = {
 };
 
 static const struct macb_config emac_config = {
-	.caps = MACB_CAPS_NEEDS_RSTONUBR,
+	.caps = MACB_CAPS_NEEDS_RSTONUBR | MACB_CAPS_MACB_IS_EMAC,
 	.clk_init = at91ether_clk_init,
 	.init = at91ether_init,
 };
-- 
2.20.1


From ff0fa2e0b31a3aebf25b6688ced17e19dae48b98 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 12 Feb 2020 20:58:26 -0800
Subject: [PATCH 23/23] net: rtnetlink: fix bugs in rtnl_alt_ifname()

[ Upstream commit 44bfa9c5e5f06c72540273813e4c66beb5a8c213 ]

Since IFLA_ALT_IFNAME is an NLA_STRING, we have no
guarantee it is nul terminated.

We should use nla_strdup() instead of kstrdup(), since this
helper will make sure not accessing out-of-bounds data.

BUG: KMSAN: uninit-value in strlen+0x5e/0xa0 lib/string.c:535
CPU: 1 PID: 19157 Comm: syz-executor.5 Not tainted 5.5.0-rc5-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c9/0x220 lib/dump_stack.c:118
 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:118
 __msan_warning+0x58/0xa0 mm/kmsan/kmsan_instr.c:215
 strlen+0x5e/0xa0 lib/string.c:535
 kstrdup+0x7f/0x1a0 mm/util.c:59
 rtnl_alt_ifname net/core/rtnetlink.c:3495 [inline]
 rtnl_linkprop+0x85d/0xc00 net/core/rtnetlink.c:3553
 rtnl_newlinkprop+0x9d/0xb0 net/core/rtnetlink.c:3568
 rtnetlink_rcv_msg+0x1153/0x1570 net/core/rtnetlink.c:5424
 netlink_rcv_skb+0x451/0x650 net/netlink/af_netlink.c:2477
 rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:5442
 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
 netlink_unicast+0xf9e/0x1100 net/netlink/af_netlink.c:1328
 netlink_sendmsg+0x1248/0x14d0 net/netlink/af_netlink.c:1917
 sock_sendmsg_nosec net/socket.c:639 [inline]
 sock_sendmsg net/socket.c:659 [inline]
 ____sys_sendmsg+0x12b6/0x1350 net/socket.c:2330
 ___sys_sendmsg net/socket.c:2384 [inline]
 __sys_sendmsg+0x451/0x5f0 net/socket.c:2417
 __do_sys_sendmsg net/socket.c:2426 [inline]
 __se_sys_sendmsg+0x97/0xb0 net/socket.c:2424
 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2424
 do_syscall_64+0xb8/0x160 arch/x86/entry/common.c:296
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x45b3b9
Code: ad b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007ff1c7b1ac78 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 00007ff1c7b1b6d4 RCX: 000000000045b3b9
RDX: 0000000000000000 RSI: 0000000020000040 RDI: 0000000000000003
RBP: 000000000075bf20 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff
R13: 00000000000009cb R14: 00000000004cb3dd R15: 000000000075bf2c

Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:144 [inline]
 kmsan_internal_poison_shadow+0x66/0xd0 mm/kmsan/kmsan.c:127
 kmsan_slab_alloc+0x8a/0xe0 mm/kmsan/kmsan_hooks.c:82
 slab_alloc_node mm/slub.c:2774 [inline]
 __kmalloc_node_track_caller+0xb40/0x1200 mm/slub.c:4382
 __kmalloc_reserve net/core/skbuff.c:141 [inline]
 __alloc_skb+0x2fd/0xac0 net/core/skbuff.c:209
 alloc_skb include/linux/skbuff.h:1049 [inline]
 netlink_alloc_large_skb net/netlink/af_netlink.c:1174 [inline]
 netlink_sendmsg+0x7d3/0x14d0 net/netlink/af_netlink.c:1892
 sock_sendmsg_nosec net/socket.c:639 [inline]
 sock_sendmsg net/socket.c:659 [inline]
 ____sys_sendmsg+0x12b6/0x1350 net/socket.c:2330
 ___sys_sendmsg net/socket.c:2384 [inline]
 __sys_sendmsg+0x451/0x5f0 net/socket.c:2417
 __do_sys_sendmsg net/socket.c:2426 [inline]
 __se_sys_sendmsg+0x97/0xb0 net/socket.c:2424
 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2424
 do_syscall_64+0xb8/0x160 arch/x86/entry/common.c:296
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 36fbf1e52bd3 ("net: rtnetlink: add linkprop commands to add and delete alternative ifnames")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jiri Pirko <jiri@mellanox.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 26 ++++++++++++--------------
 1 file changed, 12 insertions(+), 14 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index f02705ff0e5e..1737bac74c45 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3499,27 +3499,25 @@ static int rtnl_alt_ifname(int cmd, struct net_device *dev, struct nlattr *attr,
 	if (err)
 		return err;
 
-	alt_ifname = nla_data(attr);
+	alt_ifname = nla_strdup(attr, GFP_KERNEL);
+	if (!alt_ifname)
+		return -ENOMEM;
+
 	if (cmd == RTM_NEWLINKPROP) {
-		alt_ifname = kstrdup(alt_ifname, GFP_KERNEL);
-		if (!alt_ifname)
-			return -ENOMEM;
 		err = netdev_name_node_alt_create(dev, alt_ifname);
-		if (err) {
-			kfree(alt_ifname);
-			return err;
-		}
+		if (!err)
+			alt_ifname = NULL;
 	} else if (cmd == RTM_DELLINKPROP) {
 		err = netdev_name_node_alt_destroy(dev, alt_ifname);
-		if (err)
-			return err;
 	} else {
-		WARN_ON(1);
-		return 0;
+		WARN_ON_ONCE(1);
+		err = -EINVAL;
 	}
 
-	*changed = true;
-	return 0;
+	kfree(alt_ifname);
+	if (!err)
+		*changed = true;
+	return err;
 }
 
 static int rtnl_linkprop(int cmd, struct sk_buff *skb, struct nlmsghdr *nlh,
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Sat, Feb 29, 2020 at 09:11:36PM -0800, David Miller wrote:
> 
> Please queue up the following networking bug fixes for
> v5.4 and v5.5 -stable, respectively.

All now queued up, thanks.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 105 bytes --]


Please queue up the following networking bug fixes for v5.4 and
v5.5 -stable, respectively.

Thank you.

[-- Attachment #2: net_54.mbox --]
[-- Type: Application/Octet-Stream, Size: 142059 bytes --]

From 455e351ce04676928cc9229042102845bd4c59bc Mon Sep 17 00:00:00 2001
From: Dmitry Yakunin <zeil@yandex-team.ru>
Date: Thu, 5 Mar 2020 17:45:57 +0300
Subject: [PATCH 01/52] cgroup, netclassid: periodically release file_lock on
 classid updating
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 018d26fcd12a75fb9b5fe233762aa3f2f0854b88 ]

In our production environment we have faced with problem that updating
classid in cgroup with heavy tasks cause long freeze of the file tables
in this tasks. By heavy tasks we understand tasks with many threads and
opened sockets (e.g. balancers). This freeze leads to an increase number
of client timeouts.

This patch implements following logic to fix this issue:
аfter iterating 1000 file descriptors file table lock will be released
thus providing a time gap for socket creation/deletion.

Now update is non atomic and socket may be skipped using calls:

dup2(oldfd, newfd);
close(oldfd);

But this case is not typical. Moreover before this patch skip is possible
too by hiding socket fd in unix socket buffer.

New sockets will be allocated with updated classid because cgroup state
is updated before start of the file descriptors iteration.

So in common cases this patch has no side effects.

Signed-off-by: Dmitry Yakunin <zeil@yandex-team.ru>
Reviewed-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/netclassid_cgroup.c | 47 ++++++++++++++++++++++++++++--------
 1 file changed, 37 insertions(+), 10 deletions(-)

diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c
index 0642f91c4038..b4c87fe31be2 100644
--- a/net/core/netclassid_cgroup.c
+++ b/net/core/netclassid_cgroup.c
@@ -53,30 +53,60 @@ static void cgrp_css_free(struct cgroup_subsys_state *css)
 	kfree(css_cls_state(css));
 }
 
+/*
+ * To avoid freezing of sockets creation for tasks with big number of threads
+ * and opened sockets lets release file_lock every 1000 iterated descriptors.
+ * New sockets will already have been created with new classid.
+ */
+
+struct update_classid_context {
+	u32 classid;
+	unsigned int batch;
+};
+
+#define UPDATE_CLASSID_BATCH 1000
+
 static int update_classid_sock(const void *v, struct file *file, unsigned n)
 {
 	int err;
+	struct update_classid_context *ctx = (void *)v;
 	struct socket *sock = sock_from_file(file, &err);
 
 	if (sock) {
 		spin_lock(&cgroup_sk_update_lock);
-		sock_cgroup_set_classid(&sock->sk->sk_cgrp_data,
-					(unsigned long)v);
+		sock_cgroup_set_classid(&sock->sk->sk_cgrp_data, ctx->classid);
 		spin_unlock(&cgroup_sk_update_lock);
 	}
+	if (--ctx->batch == 0) {
+		ctx->batch = UPDATE_CLASSID_BATCH;
+		return n + 1;
+	}
 	return 0;
 }
 
+static void update_classid_task(struct task_struct *p, u32 classid)
+{
+	struct update_classid_context ctx = {
+		.classid = classid,
+		.batch = UPDATE_CLASSID_BATCH
+	};
+	unsigned int fd = 0;
+
+	do {
+		task_lock(p);
+		fd = iterate_fd(p->files, fd, update_classid_sock, &ctx);
+		task_unlock(p);
+		cond_resched();
+	} while (fd);
+}
+
 static void cgrp_attach(struct cgroup_taskset *tset)
 {
 	struct cgroup_subsys_state *css;
 	struct task_struct *p;
 
 	cgroup_taskset_for_each(p, css, tset) {
-		task_lock(p);
-		iterate_fd(p->files, 0, update_classid_sock,
-			   (void *)(unsigned long)css_cls_state(css)->classid);
-		task_unlock(p);
+		update_classid_task(p, css_cls_state(css)->classid);
 	}
 }
 
@@ -98,10 +128,7 @@ static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft,
 
 	css_task_iter_start(css, 0, &it);
 	while ((p = css_task_iter_next(&it))) {
-		task_lock(p);
-		iterate_fd(p->files, 0, update_classid_sock,
-			   (void *)(unsigned long)cs->classid);
-		task_unlock(p);
+		update_classid_task(p, cs->classid);
 		cond_resched();
 	}
 	css_task_iter_end(&it);
-- 
2.20.1


From c5fa083c348ef9be91d869c579d8d8039a63e1e3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 7 Mar 2020 22:05:14 -0800
Subject: [PATCH 02/52] gre: fix uninit-value in __iptunnel_pull_header

[ Upstream commit 17c25cafd4d3e74c83dce56b158843b19c40b414 ]

syzbot found an interesting case of the kernel reading
an uninit-value [1]

Problem is in the handling of ETH_P_WCCP in gre_parse_header()

We look at the byte following GRE options to eventually decide
if the options are four bytes longer.

Use skb_header_pointer() to not pull bytes if we found
that no more bytes were needed.

All callers of gre_parse_header() are properly using pskb_may_pull()
anyway before proceeding to next header.

[1]
BUG: KMSAN: uninit-value in pskb_may_pull include/linux/skbuff.h:2303 [inline]
BUG: KMSAN: uninit-value in __iptunnel_pull_header+0x30c/0xbd0 net/ipv4/ip_tunnel_core.c:94
CPU: 1 PID: 11784 Comm: syz-executor940 Not tainted 5.6.0-rc2-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c9/0x220 lib/dump_stack.c:118
 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:118
 __msan_warning+0x58/0xa0 mm/kmsan/kmsan_instr.c:215
 pskb_may_pull include/linux/skbuff.h:2303 [inline]
 __iptunnel_pull_header+0x30c/0xbd0 net/ipv4/ip_tunnel_core.c:94
 iptunnel_pull_header include/net/ip_tunnels.h:411 [inline]
 gre_rcv+0x15e/0x19c0 net/ipv6/ip6_gre.c:606
 ip6_protocol_deliver_rcu+0x181b/0x22c0 net/ipv6/ip6_input.c:432
 ip6_input_finish net/ipv6/ip6_input.c:473 [inline]
 NF_HOOK include/linux/netfilter.h:307 [inline]
 ip6_input net/ipv6/ip6_input.c:482 [inline]
 ip6_mc_input+0xdf2/0x1460 net/ipv6/ip6_input.c:576
 dst_input include/net/dst.h:442 [inline]
 ip6_rcv_finish net/ipv6/ip6_input.c:76 [inline]
 NF_HOOK include/linux/netfilter.h:307 [inline]
 ipv6_rcv+0x683/0x710 net/ipv6/ip6_input.c:306
 __netif_receive_skb_one_core net/core/dev.c:5198 [inline]
 __netif_receive_skb net/core/dev.c:5312 [inline]
 netif_receive_skb_internal net/core/dev.c:5402 [inline]
 netif_receive_skb+0x66b/0xf20 net/core/dev.c:5461
 tun_rx_batched include/linux/skbuff.h:4321 [inline]
 tun_get_user+0x6aef/0x6f60 drivers/net/tun.c:1997
 tun_chr_write_iter+0x1f2/0x360 drivers/net/tun.c:2026
 call_write_iter include/linux/fs.h:1901 [inline]
 new_sync_write fs/read_write.c:483 [inline]
 __vfs_write+0xa5a/0xca0 fs/read_write.c:496
 vfs_write+0x44a/0x8f0 fs/read_write.c:558
 ksys_write+0x267/0x450 fs/read_write.c:611
 __do_sys_write fs/read_write.c:623 [inline]
 __se_sys_write fs/read_write.c:620 [inline]
 __ia32_sys_write+0xdb/0x120 fs/read_write.c:620
 do_syscall_32_irqs_on arch/x86/entry/common.c:339 [inline]
 do_fast_syscall_32+0x3c7/0x6e0 arch/x86/entry/common.c:410
 entry_SYSENTER_compat+0x68/0x77 arch/x86/entry/entry_64_compat.S:139
RIP: 0023:0xf7f62d99
Code: 90 e8 0b 00 00 00 f3 90 0f ae e8 eb f9 8d 74 26 00 89 3c 24 c3 90 90 90 90 90 90 90 90 90 90 90 90 51 52 55 89 e5 0f 34 cd 80 <5d> 5a 59 c3 90 90 90 90 eb 0d 90 90 90 90 90 90 90 90 90 90 90 90
RSP: 002b:00000000fffedb2c EFLAGS: 00000217 ORIG_RAX: 0000000000000004
RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000020002580
RDX: 0000000000000fca RSI: 0000000000000036 RDI: 0000000000000004
RBP: 0000000000008914 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000

Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:144 [inline]
 kmsan_internal_poison_shadow+0x66/0xd0 mm/kmsan/kmsan.c:127
 kmsan_slab_alloc+0x8a/0xe0 mm/kmsan/kmsan_hooks.c:82
 slab_alloc_node mm/slub.c:2793 [inline]
 __kmalloc_node_track_caller+0xb40/0x1200 mm/slub.c:4401
 __kmalloc_reserve net/core/skbuff.c:142 [inline]
 __alloc_skb+0x2fd/0xac0 net/core/skbuff.c:210
 alloc_skb include/linux/skbuff.h:1051 [inline]
 alloc_skb_with_frags+0x18c/0xa70 net/core/skbuff.c:5766
 sock_alloc_send_pskb+0xada/0xc60 net/core/sock.c:2242
 tun_alloc_skb drivers/net/tun.c:1529 [inline]
 tun_get_user+0x10ae/0x6f60 drivers/net/tun.c:1843
 tun_chr_write_iter+0x1f2/0x360 drivers/net/tun.c:2026
 call_write_iter include/linux/fs.h:1901 [inline]
 new_sync_write fs/read_write.c:483 [inline]
 __vfs_write+0xa5a/0xca0 fs/read_write.c:496
 vfs_write+0x44a/0x8f0 fs/read_write.c:558
 ksys_write+0x267/0x450 fs/read_write.c:611
 __do_sys_write fs/read_write.c:623 [inline]
 __se_sys_write fs/read_write.c:620 [inline]
 __ia32_sys_write+0xdb/0x120 fs/read_write.c:620
 do_syscall_32_irqs_on arch/x86/entry/common.c:339 [inline]
 do_fast_syscall_32+0x3c7/0x6e0 arch/x86/entry/common.c:410
 entry_SYSENTER_compat+0x68/0x77 arch/x86/entry/entry_64_compat.S:139

Fixes: 95f5c64c3c13 ("gre: Move utility functions to common headers")
Fixes: c54419321455 ("GRE: Refactor GRE tunneling code.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/gre_demux.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c
index 5fd6e8ed02b5..66fdbfe5447c 100644
--- a/net/ipv4/gre_demux.c
+++ b/net/ipv4/gre_demux.c
@@ -56,7 +56,9 @@ int gre_del_protocol(const struct gre_protocol *proto, u8 version)
 }
 EXPORT_SYMBOL_GPL(gre_del_protocol);
 
-/* Fills in tpi and returns header length to be pulled. */
+/* Fills in tpi and returns header length to be pulled.
+ * Note that caller must use pskb_may_pull() before pulling GRE header.
+ */
 int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 		     bool *csum_err, __be16 proto, int nhs)
 {
@@ -110,8 +112,14 @@ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 	 * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header
 	 */
 	if (greh->flags == 0 && tpi->proto == htons(ETH_P_WCCP)) {
+		u8 _val, *val;
+
+		val = skb_header_pointer(skb, nhs + hdr_len,
+					 sizeof(_val), &_val);
+		if (!val)
+			return -EINVAL;
 		tpi->proto = proto;
-		if ((*(u8 *)options & 0xF0) != 0x40)
+		if ((*val & 0xF0) != 0x40)
 			hdr_len += 4;
 	}
 	tpi->hdr_len = hdr_len;
-- 
2.20.1


From 2231d725d2f611171ea3dabe76a4cc9f753fc36d Mon Sep 17 00:00:00 2001
From: Dmitry Yakunin <zeil@yandex-team.ru>
Date: Thu, 5 Mar 2020 15:33:12 +0300
Subject: [PATCH 03/52] inet_diag: return classid for all socket types

[ Upstream commit 83f73c5bb7b9a9135173f0ba2b1aa00c06664ff9 ]

In commit 1ec17dbd90f8 ("inet_diag: fix reporting cgroup classid and
fallback to priority") croup classid reporting was fixed. But this works
only for TCP sockets because for other socket types icsk parameter can
be NULL and classid code path is skipped. This change moves classid
handling to inet_diag_msg_attrs_fill() function.

Also inet_diag_msg_attrs_size() helper was added and addends in
nlmsg_new() were reordered to save order from inet_sk_diag_fill().

Fixes: 1ec17dbd90f8 ("inet_diag: fix reporting cgroup classid and fallback to priority")
Signed-off-by: Dmitry Yakunin <zeil@yandex-team.ru>
Reviewed-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/inet_diag.h | 18 ++++++++++------
 net/ipv4/inet_diag.c      | 44 ++++++++++++++++++---------------------
 net/ipv4/raw_diag.c       |  5 +++--
 net/ipv4/udp_diag.c       |  5 +++--
 net/sctp/diag.c           |  8 ++-----
 5 files changed, 40 insertions(+), 40 deletions(-)

diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h
index 39faaaf843e1..c91cf2dee12a 100644
--- a/include/linux/inet_diag.h
+++ b/include/linux/inet_diag.h
@@ -2,15 +2,10 @@
 #ifndef _INET_DIAG_H_
 #define _INET_DIAG_H_ 1
 
+#include <net/netlink.h>
 #include <uapi/linux/inet_diag.h>
 
-struct net;
-struct sock;
 struct inet_hashinfo;
-struct nlattr;
-struct nlmsghdr;
-struct sk_buff;
-struct netlink_callback;
 
 struct inet_diag_handler {
 	void		(*dump)(struct sk_buff *skb,
@@ -62,6 +57,17 @@ int inet_diag_bc_sk(const struct nlattr *_bc, struct sock *sk);
 
 void inet_diag_msg_common_fill(struct inet_diag_msg *r, struct sock *sk);
 
+static inline size_t inet_diag_msg_attrs_size(void)
+{
+	return	  nla_total_size(1)  /* INET_DIAG_SHUTDOWN */
+		+ nla_total_size(1)  /* INET_DIAG_TOS */
+#if IS_ENABLED(CONFIG_IPV6)
+		+ nla_total_size(1)  /* INET_DIAG_TCLASS */
+		+ nla_total_size(1)  /* INET_DIAG_SKV6ONLY */
+#endif
+		+ nla_total_size(4)  /* INET_DIAG_MARK */
+		+ nla_total_size(4); /* INET_DIAG_CLASS_ID */
+}
 int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
 			     struct inet_diag_msg *r, int ext,
 			     struct user_namespace *user_ns, bool net_admin);
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 6a4c82f96e78..5b68bdaa8bff 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -100,13 +100,9 @@ static size_t inet_sk_attr_size(struct sock *sk,
 		aux = handler->idiag_get_aux_size(sk, net_admin);
 
 	return	  nla_total_size(sizeof(struct tcp_info))
-		+ nla_total_size(1) /* INET_DIAG_SHUTDOWN */
-		+ nla_total_size(1) /* INET_DIAG_TOS */
-		+ nla_total_size(1) /* INET_DIAG_TCLASS */
-		+ nla_total_size(4) /* INET_DIAG_MARK */
-		+ nla_total_size(4) /* INET_DIAG_CLASS_ID */
-		+ nla_total_size(sizeof(struct inet_diag_meminfo))
 		+ nla_total_size(sizeof(struct inet_diag_msg))
+		+ inet_diag_msg_attrs_size()
+		+ nla_total_size(sizeof(struct inet_diag_meminfo))
 		+ nla_total_size(SK_MEMINFO_VARS * sizeof(u32))
 		+ nla_total_size(TCP_CA_NAME_MAX)
 		+ nla_total_size(sizeof(struct tcpvegas_info))
@@ -147,6 +143,24 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
 	if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, sk->sk_mark))
 		goto errout;
 
+	if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) ||
+	    ext & (1 << (INET_DIAG_TCLASS - 1))) {
+		u32 classid = 0;
+
+#ifdef CONFIG_SOCK_CGROUP_DATA
+		classid = sock_cgroup_classid(&sk->sk_cgrp_data);
+#endif
+		/* Fallback to socket priority if class id isn't set.
+		 * Classful qdiscs use it as direct reference to class.
+		 * For cgroup2 classid is always zero.
+		 */
+		if (!classid)
+			classid = sk->sk_priority;
+
+		if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid))
+			goto errout;
+	}
+
 	r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk));
 	r->idiag_inode = sock_i_ino(sk);
 
@@ -284,24 +298,6 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 			goto errout;
 	}
 
-	if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) ||
-	    ext & (1 << (INET_DIAG_TCLASS - 1))) {
-		u32 classid = 0;
-
-#ifdef CONFIG_SOCK_CGROUP_DATA
-		classid = sock_cgroup_classid(&sk->sk_cgrp_data);
-#endif
-		/* Fallback to socket priority if class id isn't set.
-		 * Classful qdiscs use it as direct reference to class.
-		 * For cgroup2 classid is always zero.
-		 */
-		if (!classid)
-			classid = sk->sk_priority;
-
-		if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid))
-			goto errout;
-	}
-
 out:
 	nlmsg_end(skb, nlh);
 	return 0;
diff --git a/net/ipv4/raw_diag.c b/net/ipv4/raw_diag.c
index e35736b99300..a93e7d1e1251 100644
--- a/net/ipv4/raw_diag.c
+++ b/net/ipv4/raw_diag.c
@@ -100,8 +100,9 @@ static int raw_diag_dump_one(struct sk_buff *in_skb,
 	if (IS_ERR(sk))
 		return PTR_ERR(sk);
 
-	rep = nlmsg_new(sizeof(struct inet_diag_msg) +
-			sizeof(struct inet_diag_meminfo) + 64,
+	rep = nlmsg_new(nla_total_size(sizeof(struct inet_diag_msg)) +
+			inet_diag_msg_attrs_size() +
+			nla_total_size(sizeof(struct inet_diag_meminfo)) + 64,
 			GFP_KERNEL);
 	if (!rep) {
 		sock_put(sk);
diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c
index 910555a4d9fe..dccd2286bc28 100644
--- a/net/ipv4/udp_diag.c
+++ b/net/ipv4/udp_diag.c
@@ -64,8 +64,9 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb,
 		goto out;
 
 	err = -ENOMEM;
-	rep = nlmsg_new(sizeof(struct inet_diag_msg) +
-			sizeof(struct inet_diag_meminfo) + 64,
+	rep = nlmsg_new(nla_total_size(sizeof(struct inet_diag_msg)) +
+			inet_diag_msg_attrs_size() +
+			nla_total_size(sizeof(struct inet_diag_meminfo)) + 64,
 			GFP_KERNEL);
 	if (!rep)
 		goto out;
diff --git a/net/sctp/diag.c b/net/sctp/diag.c
index 0851166b9175..ba9f64fdfd23 100644
--- a/net/sctp/diag.c
+++ b/net/sctp/diag.c
@@ -237,15 +237,11 @@ static size_t inet_assoc_attr_size(struct sctp_association *asoc)
 		addrcnt++;
 
 	return	  nla_total_size(sizeof(struct sctp_info))
-		+ nla_total_size(1) /* INET_DIAG_SHUTDOWN */
-		+ nla_total_size(1) /* INET_DIAG_TOS */
-		+ nla_total_size(1) /* INET_DIAG_TCLASS */
-		+ nla_total_size(4) /* INET_DIAG_MARK */
-		+ nla_total_size(4) /* INET_DIAG_CLASS_ID */
 		+ nla_total_size(addrlen * asoc->peer.transport_count)
 		+ nla_total_size(addrlen * addrcnt)
-		+ nla_total_size(sizeof(struct inet_diag_meminfo))
 		+ nla_total_size(sizeof(struct inet_diag_msg))
+		+ inet_diag_msg_attrs_size()
+		+ nla_total_size(sizeof(struct inet_diag_meminfo))
 		+ 64;
 }
 
-- 
2.20.1


From ca72ab2b131156deccdcd70f399059a9d90e5a18 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Tue, 10 Mar 2020 15:27:37 +0800
Subject: [PATCH 04/52] ipv6/addrconf: call ipv6_mc_up() for non-Ethernet
 interface
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 60380488e4e0b95e9e82aa68aa9705baa86de84c ]

Rafał found an issue that for non-Ethernet interface, if we down and up
frequently, the memory will be consumed slowly.

The reason is we add allnodes/allrouters addressed in multicast list in
ipv6_add_dev(). When link down, we call ipv6_mc_down(), store all multicast
addresses via mld_add_delrec(). But when link up, we don't call ipv6_mc_up()
for non-Ethernet interface to remove the addresses. This makes idev->mc_tomb
getting bigger and bigger. The call stack looks like:

addrconf_notify(NETDEV_REGISTER)
	ipv6_add_dev
		ipv6_dev_mc_inc(ff01::1)
		ipv6_dev_mc_inc(ff02::1)
		ipv6_dev_mc_inc(ff02::2)

addrconf_notify(NETDEV_UP)
	addrconf_dev_config
		/* Alas, we support only Ethernet autoconfiguration. */
		return;

addrconf_notify(NETDEV_DOWN)
	addrconf_ifdown
		ipv6_mc_down
			igmp6_group_dropped(ff02::2)
				mld_add_delrec(ff02::2)
			igmp6_group_dropped(ff02::1)
			igmp6_group_dropped(ff01::1)

After investigating, I can't found a rule to disable multicast on
non-Ethernet interface. In RFC2460, the link could be Ethernet, PPP, ATM,
tunnels, etc. In IPv4, it doesn't check the dev type when calls ip_mc_up()
in inetdev_event(). Even for IPv6, we don't check the dev type and call
ipv6_add_dev(), ipv6_dev_mc_inc() after register device.

So I think it's OK to fix this memory consumer by calling ipv6_mc_up() for
non-Ethernet interface.

v2: Also check IFF_MULTICAST flag to make sure the interface supports
    multicast

Reported-by: Rafał Miłecki <zajec5@gmail.com>
Tested-by: Rafał Miłecki <zajec5@gmail.com>
Fixes: 74235a25c673 ("[IPV6] addrconf: Fix IPv6 on tuntap tunnels")
Fixes: 1666d49e1d41 ("mld: do not remove mld souce list info when set link down")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index b11ccb53c7e0..69e89baba183 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3345,6 +3345,10 @@ static void addrconf_dev_config(struct net_device *dev)
 	    (dev->type != ARPHRD_NONE) &&
 	    (dev->type != ARPHRD_RAWIP)) {
 		/* Alas, we support only Ethernet autoconfiguration. */
+		idev = __in6_dev_get(dev);
+		if (!IS_ERR_OR_NULL(idev) && dev->flags & IFF_UP &&
+		    dev->flags & IFF_MULTICAST)
+			ipv6_mc_up(idev);
 		return;
 	}
 
-- 
2.20.1


From 504255341178b92393950393d2577440945f30f7 Mon Sep 17 00:00:00 2001
From: Mahesh Bandewar <maheshb@google.com>
Date: Mon, 9 Mar 2020 15:57:02 -0700
Subject: [PATCH 05/52] ipvlan: add cond_resched_rcu() while processing
 muticast backlog
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit e18b353f102e371580f3f01dd47567a25acc3c1d ]

If there are substantial number of slaves created as simulated by
Syzbot, the backlog processing could take much longer and result
into the issue found in the Syzbot report.

INFO: rcu_sched detected stalls on CPUs/tasks:
        (detected by 1, t=10502 jiffies, g=5049, c=5048, q=752)
All QSes seen, last rcu_sched kthread activity 10502 (4294965563-4294955061), jiffies_till_next_fqs=1, root ->qsmask 0x0
syz-executor.1  R  running task on cpu   1  10984 11210   3866 0x30020008 179034491270
Call Trace:
 <IRQ>
 [<ffffffff81497163>] _sched_show_task kernel/sched/core.c:8063 [inline]
 [<ffffffff81497163>] _sched_show_task.cold+0x2fd/0x392 kernel/sched/core.c:8030
 [<ffffffff8146a91b>] sched_show_task+0xb/0x10 kernel/sched/core.c:8073
 [<ffffffff815c931b>] print_other_cpu_stall kernel/rcu/tree.c:1577 [inline]
 [<ffffffff815c931b>] check_cpu_stall kernel/rcu/tree.c:1695 [inline]
 [<ffffffff815c931b>] __rcu_pending kernel/rcu/tree.c:3478 [inline]
 [<ffffffff815c931b>] rcu_pending kernel/rcu/tree.c:3540 [inline]
 [<ffffffff815c931b>] rcu_check_callbacks.cold+0xbb4/0xc29 kernel/rcu/tree.c:2876
 [<ffffffff815e3962>] update_process_times+0x32/0x80 kernel/time/timer.c:1635
 [<ffffffff816164f0>] tick_sched_handle+0xa0/0x180 kernel/time/tick-sched.c:161
 [<ffffffff81616ae4>] tick_sched_timer+0x44/0x130 kernel/time/tick-sched.c:1193
 [<ffffffff815e75f7>] __run_hrtimer kernel/time/hrtimer.c:1393 [inline]
 [<ffffffff815e75f7>] __hrtimer_run_queues+0x307/0xd90 kernel/time/hrtimer.c:1455
 [<ffffffff815e90ea>] hrtimer_interrupt+0x2ea/0x730 kernel/time/hrtimer.c:1513
 [<ffffffff844050f4>] local_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1031 [inline]
 [<ffffffff844050f4>] smp_apic_timer_interrupt+0x144/0x5e0 arch/x86/kernel/apic/apic.c:1056
 [<ffffffff84401cbe>] apic_timer_interrupt+0x8e/0xa0 arch/x86/entry/entry_64.S:778
RIP: 0010:do_raw_read_lock+0x22/0x80 kernel/locking/spinlock_debug.c:153
RSP: 0018:ffff8801dad07ab8 EFLAGS: 00000a02 ORIG_RAX: ffffffffffffff12
RAX: 0000000000000000 RBX: ffff8801c4135680 RCX: 0000000000000000
RDX: 1ffff10038826afe RSI: ffff88019d816bb8 RDI: ffff8801c41357f0
RBP: ffff8801dad07ac0 R08: 0000000000004b15 R09: 0000000000310273
R10: ffff88019d816bb8 R11: 0000000000000001 R12: ffff8801c41357e8
R13: 0000000000000000 R14: ffff8801cfb19850 R15: ffff8801cfb198b0
 [<ffffffff8101460e>] __raw_read_lock_bh include/linux/rwlock_api_smp.h:177 [inline]
 [<ffffffff8101460e>] _raw_read_lock_bh+0x3e/0x50 kernel/locking/spinlock.c:240
 [<ffffffff840d78ca>] ipv6_chk_mcast_addr+0x11a/0x6f0 net/ipv6/mcast.c:1006
 [<ffffffff84023439>] ip6_mc_input+0x319/0x8e0 net/ipv6/ip6_input.c:482
 [<ffffffff840211c8>] dst_input include/net/dst.h:449 [inline]
 [<ffffffff840211c8>] ip6_rcv_finish+0x408/0x610 net/ipv6/ip6_input.c:78
 [<ffffffff840214de>] NF_HOOK include/linux/netfilter.h:292 [inline]
 [<ffffffff840214de>] NF_HOOK include/linux/netfilter.h:286 [inline]
 [<ffffffff840214de>] ipv6_rcv+0x10e/0x420 net/ipv6/ip6_input.c:278
 [<ffffffff83a29efa>] __netif_receive_skb_one_core+0x12a/0x1f0 net/core/dev.c:5303
 [<ffffffff83a2a15c>] __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:5417
 [<ffffffff83a2f536>] process_backlog+0x216/0x6c0 net/core/dev.c:6243
 [<ffffffff83a30d1b>] napi_poll net/core/dev.c:6680 [inline]
 [<ffffffff83a30d1b>] net_rx_action+0x47b/0xfb0 net/core/dev.c:6748
 [<ffffffff846002c8>] __do_softirq+0x2c8/0x99a kernel/softirq.c:317
 [<ffffffff813e656a>] invoke_softirq kernel/softirq.c:399 [inline]
 [<ffffffff813e656a>] irq_exit+0x16a/0x1a0 kernel/softirq.c:439
 [<ffffffff84405115>] exiting_irq arch/x86/include/asm/apic.h:561 [inline]
 [<ffffffff84405115>] smp_apic_timer_interrupt+0x165/0x5e0 arch/x86/kernel/apic/apic.c:1058
 [<ffffffff84401cbe>] apic_timer_interrupt+0x8e/0xa0 arch/x86/entry/entry_64.S:778
 </IRQ>
RIP: 0010:__sanitizer_cov_trace_pc+0x26/0x50 kernel/kcov.c:102
RSP: 0018:ffff880196033bd8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff12
RAX: ffff88019d8161c0 RBX: 00000000ffffffff RCX: ffffc90003501000
RDX: 0000000000000002 RSI: ffffffff816236d1 RDI: 0000000000000005
RBP: ffff880196033bd8 R08: ffff88019d8161c0 R09: 0000000000000000
R10: 1ffff10032c067f0 R11: 0000000000000000 R12: 0000000000000000
R13: 0000000000000080 R14: 0000000000000000 R15: 0000000000000000
 [<ffffffff816236d1>] do_futex+0x151/0x1d50 kernel/futex.c:3548
 [<ffffffff816260f0>] C_SYSC_futex kernel/futex_compat.c:201 [inline]
 [<ffffffff816260f0>] compat_SyS_futex+0x270/0x3b0 kernel/futex_compat.c:175
 [<ffffffff8101da17>] do_syscall_32_irqs_on arch/x86/entry/common.c:353 [inline]
 [<ffffffff8101da17>] do_fast_syscall_32+0x357/0xe1c arch/x86/entry/common.c:415
 [<ffffffff84401a9b>] entry_SYSENTER_compat+0x8b/0x9d arch/x86/entry/entry_64_compat.S:139
RIP: 0023:0xf7f23c69
RSP: 002b:00000000f5d1f12c EFLAGS: 00000282 ORIG_RAX: 00000000000000f0
RAX: ffffffffffffffda RBX: 000000000816af88 RCX: 0000000000000080
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 000000000816af8c
RBP: 00000000f5d1f228 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
rcu_sched kthread starved for 10502 jiffies! g5049 c5048 f0x2 RCU_GP_WAIT_FQS(3) ->state=0x0 ->cpu=1
rcu_sched       R  running task on cpu   1  13048     8      2 0x90000000 179099587640
Call Trace:
 [<ffffffff8147321f>] context_switch+0x60f/0xa60 kernel/sched/core.c:3209
 [<ffffffff8100095a>] __schedule+0x5aa/0x1da0 kernel/sched/core.c:3934
 [<ffffffff810021df>] schedule+0x8f/0x1b0 kernel/sched/core.c:4011
 [<ffffffff8101116d>] schedule_timeout+0x50d/0xee0 kernel/time/timer.c:1803
 [<ffffffff815c13f1>] rcu_gp_kthread+0xda1/0x3b50 kernel/rcu/tree.c:2327
 [<ffffffff8144b318>] kthread+0x348/0x420 kernel/kthread.c:246
 [<ffffffff84400266>] ret_from_fork+0x56/0x70 arch/x86/entry/entry_64.S:393

Fixes: ba35f8588f47 (“ipvlan: Defer multicast / broadcast processing to a work-queue”)
Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ipvlan/ipvlan_core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index 30cd0c4f0be0..514e497d9ff5 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -277,6 +277,7 @@ void ipvlan_process_multicast(struct work_struct *work)
 			}
 			ipvlan_count_rx(ipvlan, len, ret == NET_RX_SUCCESS, true);
 			local_bh_enable();
+			cond_resched_rcu();
 		}
 		rcu_read_unlock();
 
-- 
2.20.1


From c465c54865f96e0374b40eee47a03f2923b6e9bb Mon Sep 17 00:00:00 2001
From: Jiri Wiesner <jwiesner@suse.com>
Date: Sat, 7 Mar 2020 13:31:57 +0100
Subject: [PATCH 06/52] ipvlan: do not add hardware address of master to its
 unicast filter list

[ Upstream commit 63aae7b17344d4b08a7d05cb07044de4c0f9dcc6 ]

There is a problem when ipvlan slaves are created on a master device that
is a vmxnet3 device (ipvlan in VMware guests). The vmxnet3 driver does not
support unicast address filtering. When an ipvlan device is brought up in
ipvlan_open(), the ipvlan driver calls dev_uc_add() to add the hardware
address of the vmxnet3 master device to the unicast address list of the
master device, phy_dev->uc. This inevitably leads to the vmxnet3 master
device being forced into promiscuous mode by __dev_set_rx_mode().

Promiscuous mode is switched on the master despite the fact that there is
still only one hardware address that the master device should use for
filtering in order for the ipvlan device to be able to receive packets.
The comment above struct net_device describes the uc_promisc member as a
"counter, that indicates, that promiscuous mode has been enabled due to
the need to listen to additional unicast addresses in a device that does
not implement ndo_set_rx_mode()". Moreover, the design of ipvlan
guarantees that only the hardware address of a master device,
phy_dev->dev_addr, will be used to transmit and receive all packets from
its ipvlan slaves. Thus, the unicast address list of the master device
should not be modified by ipvlan_open() and ipvlan_stop() in order to make
ipvlan a workable option on masters that do not support unicast address
filtering.

Fixes: 2ad7bf3638411 ("ipvlan: Initial check-in of the IPVLAN driver")
Reported-by: Per Sundstrom <per.sundstrom@redqube.se>
Signed-off-by: Jiri Wiesner <jwiesner@suse.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ipvlan/ipvlan_main.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index ba3dfac1d904..b805abc9ec3b 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -164,7 +164,6 @@ static void ipvlan_uninit(struct net_device *dev)
 static int ipvlan_open(struct net_device *dev)
 {
 	struct ipvl_dev *ipvlan = netdev_priv(dev);
-	struct net_device *phy_dev = ipvlan->phy_dev;
 	struct ipvl_addr *addr;
 
 	if (ipvlan->port->mode == IPVLAN_MODE_L3 ||
@@ -178,7 +177,7 @@ static int ipvlan_open(struct net_device *dev)
 		ipvlan_ht_addr_add(ipvlan, addr);
 	rcu_read_unlock();
 
-	return dev_uc_add(phy_dev, phy_dev->dev_addr);
+	return 0;
 }
 
 static int ipvlan_stop(struct net_device *dev)
@@ -190,8 +189,6 @@ static int ipvlan_stop(struct net_device *dev)
 	dev_uc_unsync(phy_dev, dev);
 	dev_mc_unsync(phy_dev, dev);
 
-	dev_uc_del(phy_dev, phy_dev->dev_addr);
-
 	rcu_read_lock();
 	list_for_each_entry_rcu(addr, &ipvlan->addrs, anode)
 		ipvlan_ht_addr_del(addr);
-- 
2.20.1


From bed5fafe8adbefa56cb4995e037dd406a4fd0075 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 9 Mar 2020 18:22:58 -0700
Subject: [PATCH 07/52] ipvlan: do not use cond_resched_rcu() in
 ipvlan_process_multicast()

[ Upstream commit afe207d80a61e4d6e7cfa0611a4af46d0ba95628 ]

Commit e18b353f102e ("ipvlan: add cond_resched_rcu() while
processing muticast backlog") added a cond_resched_rcu() in a loop
using rcu protection to iterate over slaves.

This is breaking rcu rules, so lets instead use cond_resched()
at a point we can reschedule

Fixes: e18b353f102e ("ipvlan: add cond_resched_rcu() while processing muticast backlog")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ipvlan/ipvlan_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index 514e497d9ff5..57617ff5565f 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -277,7 +277,6 @@ void ipvlan_process_multicast(struct work_struct *work)
 			}
 			ipvlan_count_rx(ipvlan, len, ret == NET_RX_SUCCESS, true);
 			local_bh_enable();
-			cond_resched_rcu();
 		}
 		rcu_read_unlock();
 
@@ -294,6 +293,7 @@ void ipvlan_process_multicast(struct work_struct *work)
 		}
 		if (dev)
 			dev_put(dev);
+		cond_resched();
 	}
 }
 
-- 
2.20.1


From 925b3ad4696a8e523ebb56c5f8663a50c68d8a28 Mon Sep 17 00:00:00 2001
From: Mahesh Bandewar <maheshb@google.com>
Date: Mon, 9 Mar 2020 15:56:56 -0700
Subject: [PATCH 08/52] ipvlan: don't deref eth hdr before checking it's set
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit ad8192767c9f9cf97da57b9ffcea70fb100febef ]

IPvlan in L3 mode discards outbound multicast packets but performs
the check before ensuring the ether-header is set or not. This is
an error that Eric found through code browsing.

Fixes: 2ad7bf363841 (“ipvlan: Initial check-in of the IPVLAN driver.”)
Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ipvlan/ipvlan_core.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index 57617ff5565f..8801d093135c 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -499,19 +499,21 @@ static int ipvlan_process_outbound(struct sk_buff *skb)
 	struct ethhdr *ethh = eth_hdr(skb);
 	int ret = NET_XMIT_DROP;
 
-	/* In this mode we dont care about multicast and broadcast traffic */
-	if (is_multicast_ether_addr(ethh->h_dest)) {
-		pr_debug_ratelimited("Dropped {multi|broad}cast of type=[%x]\n",
-				     ntohs(skb->protocol));
-		kfree_skb(skb);
-		goto out;
-	}
-
 	/* The ipvlan is a pseudo-L2 device, so the packets that we receive
 	 * will have L2; which need to discarded and processed further
 	 * in the net-ns of the main-device.
 	 */
 	if (skb_mac_header_was_set(skb)) {
+		/* In this mode we dont care about
+		 * multicast and broadcast traffic */
+		if (is_multicast_ether_addr(ethh->h_dest)) {
+			pr_debug_ratelimited(
+				"Dropped {multi|broad}cast of type=[%x]\n",
+				ntohs(skb->protocol));
+			kfree_skb(skb);
+			goto out;
+		}
+
 		skb_pull(skb, sizeof(*ethh));
 		skb->mac_header = (typeof(skb->mac_header))~0U;
 		skb_reset_network_header(skb);
-- 
2.20.1


From a649a7655febe6b89c705ac7d8dd1f9d72994020 Mon Sep 17 00:00:00 2001
From: Mahesh Bandewar <maheshb@google.com>
Date: Mon, 9 Mar 2020 15:57:07 -0700
Subject: [PATCH 09/52] macvlan: add cond_resched() during multicast processing

[ Upstream commit ce9a4186f9ac475c415ffd20348176a4ea366670 ]

The Rx bound multicast packets are deferred to a workqueue and
macvlan can also suffer from the same attack that was discovered
by Syzbot for IPvlan. This solution is not as effective as in
IPvlan. IPvlan defers all (Tx and Rx) multicast packet processing
to a workqueue while macvlan does this way only for the Rx. This
fix should address the Rx codition to certain extent.

Tx is still suseptible. Tx multicast processing happens when
.ndo_start_xmit is called, hence we cannot add cond_resched().
However, it's not that severe since the user which is generating
 / flooding will be affected the most.

Fixes: 412ca1550cbe ("macvlan: Move broadcasts into a work queue")
Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macvlan.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index c5bf61565726..26f6be4796c7 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -334,6 +334,8 @@ static void macvlan_process_broadcast(struct work_struct *w)
 		if (src)
 			dev_put(src->dev);
 		consume_skb(skb);
+
+		cond_resched();
 	}
 }
 
-- 
2.20.1


From 9c225380a503798c7dcd91785515c5c300f03e1b Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Tue, 3 Mar 2020 15:01:46 +0000
Subject: [PATCH 10/52] net: dsa: fix phylink_start()/phylink_stop() calls

[ Upstream commit 8640f8dc6d657ebfb4e67c202ad32c5457858a13 ]

Place phylink_start()/phylink_stop() inside dsa_port_enable() and
dsa_port_disable(), which ensures that we call phylink_stop() before
tearing down phylink - which is a documented requirement.  Failure
to do so can cause use-after-free bugs.

Fixes: 0e27921816ad ("net: dsa: Use PHYLINK for the CPU/DSA ports")
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/dsa_priv.h |  2 ++
 net/dsa/port.c     | 32 ++++++++++++++++++++++++++------
 net/dsa/slave.c    |  8 ++------
 3 files changed, 30 insertions(+), 12 deletions(-)

diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index 12f8c7ee4dd8..bf9947c577b6 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -128,7 +128,9 @@ static inline struct net_device *dsa_master_find_slave(struct net_device *dev,
 /* port.c */
 int dsa_port_set_state(struct dsa_port *dp, u8 state,
 		       struct switchdev_trans *trans);
+int dsa_port_enable_rt(struct dsa_port *dp, struct phy_device *phy);
 int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy);
+void dsa_port_disable_rt(struct dsa_port *dp);
 void dsa_port_disable(struct dsa_port *dp);
 int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br);
 void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br);
diff --git a/net/dsa/port.c b/net/dsa/port.c
index 9b54e5a76297..2a1aa1a50254 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -63,7 +63,7 @@ static void dsa_port_set_state_now(struct dsa_port *dp, u8 state)
 		pr_err("DSA: failed to set STP state %u (%d)\n", state, err);
 }
 
-int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy)
+int dsa_port_enable_rt(struct dsa_port *dp, struct phy_device *phy)
 {
 	struct dsa_switch *ds = dp->ds;
 	int port = dp->index;
@@ -78,14 +78,31 @@ int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy)
 	if (!dp->bridge_dev)
 		dsa_port_set_state_now(dp, BR_STATE_FORWARDING);
 
+	if (dp->pl)
+		phylink_start(dp->pl);
+
 	return 0;
 }
 
-void dsa_port_disable(struct dsa_port *dp)
+int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy)
+{
+	int err;
+
+	rtnl_lock();
+	err = dsa_port_enable_rt(dp, phy);
+	rtnl_unlock();
+
+	return err;
+}
+
+void dsa_port_disable_rt(struct dsa_port *dp)
 {
 	struct dsa_switch *ds = dp->ds;
 	int port = dp->index;
 
+	if (dp->pl)
+		phylink_stop(dp->pl);
+
 	if (!dp->bridge_dev)
 		dsa_port_set_state_now(dp, BR_STATE_DISABLED);
 
@@ -93,6 +110,13 @@ void dsa_port_disable(struct dsa_port *dp)
 		ds->ops->port_disable(ds, port);
 }
 
+void dsa_port_disable(struct dsa_port *dp)
+{
+	rtnl_lock();
+	dsa_port_disable_rt(dp);
+	rtnl_unlock();
+}
+
 int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br)
 {
 	struct dsa_notifier_bridge_info info = {
@@ -615,10 +639,6 @@ static int dsa_port_phylink_register(struct dsa_port *dp)
 		goto err_phy_connect;
 	}
 
-	rtnl_lock();
-	phylink_start(dp->pl);
-	rtnl_unlock();
-
 	return 0;
 
 err_phy_connect:
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 028e65f4b5ba..23c2210fa7ec 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -90,12 +90,10 @@ static int dsa_slave_open(struct net_device *dev)
 			goto clear_allmulti;
 	}
 
-	err = dsa_port_enable(dp, dev->phydev);
+	err = dsa_port_enable_rt(dp, dev->phydev);
 	if (err)
 		goto clear_promisc;
 
-	phylink_start(dp->pl);
-
 	return 0;
 
 clear_promisc:
@@ -119,9 +117,7 @@ static int dsa_slave_close(struct net_device *dev)
 	cancel_work_sync(&dp->xmit_work);
 	skb_queue_purge(&dp->xmit_queue);
 
-	phylink_stop(dp->pl);
-
-	dsa_port_disable(dp);
+	dsa_port_disable_rt(dp);
 
 	dev_mc_unsync(master, dev);
 	dev_uc_unsync(master, dev);
-- 
2.20.1


From e6090cabb698206684c9db48506f9ad2c863fbc7 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Fri, 28 Feb 2020 19:39:41 +0000
Subject: [PATCH 11/52] net: dsa: mv88e6xxx: fix lockup on warm boot

[ Upstream commit 0395823b8d9a4d87bd1bf74359123461c2ae801b ]

If the switch is not hardware reset on a warm boot, interrupts can be
left enabled, and possibly pending. This will cause us to enter an
infinite loop trying to service an interrupt we are unable to handle,
thereby preventing the kernel from booting.

Ensure that the global 2 interrupt sources are disabled before we claim
the parent interrupt.

Observed on the ZII development revision B and C platforms with
reworked serdes support, and using reboot -f to reboot the platform.

Fixes: dc30c35be720 ("net: dsa: mv88e6xxx: Implement interrupt support.")
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/global2.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/dsa/mv88e6xxx/global2.c b/drivers/net/dsa/mv88e6xxx/global2.c
index bdbb72fc20ed..6240976679e1 100644
--- a/drivers/net/dsa/mv88e6xxx/global2.c
+++ b/drivers/net/dsa/mv88e6xxx/global2.c
@@ -1083,6 +1083,13 @@ int mv88e6xxx_g2_irq_setup(struct mv88e6xxx_chip *chip)
 {
 	int err, irq, virq;
 
+	chip->g2_irq.masked = ~0;
+	mv88e6xxx_reg_lock(chip);
+	err = mv88e6xxx_g2_int_mask(chip, ~chip->g2_irq.masked);
+	mv88e6xxx_reg_unlock(chip);
+	if (err)
+		return err;
+
 	chip->g2_irq.domain = irq_domain_add_simple(
 		chip->dev->of_node, 16, 0, &mv88e6xxx_g2_irq_domain_ops, chip);
 	if (!chip->g2_irq.domain)
@@ -1092,7 +1099,6 @@ int mv88e6xxx_g2_irq_setup(struct mv88e6xxx_chip *chip)
 		irq_create_mapping(chip->g2_irq.domain, irq);
 
 	chip->g2_irq.chip = mv88e6xxx_g2_irq_chip;
-	chip->g2_irq.masked = ~0;
 
 	chip->device_irq = irq_find_mapping(chip->g1_irq.domain,
 					    MV88E6XXX_G1_STS_IRQ_DEVICE);
-- 
2.20.1


From 49e6f8dbe7e2f5e67209b008136ad9328f9070fa Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 10 Mar 2020 20:36:16 -0700
Subject: [PATCH 12/52] net: fec: validate the new settings in
 fec_enet_set_coalesce()

[ Upstream commit ab14961d10d02d20767612c78ce148f6eb85bd58 ]

fec_enet_set_coalesce() validates the previously set params
and if they are within range proceeds to apply the new ones.
The new ones, however, are not validated. This seems backwards,
probably a copy-paste error?

Compile tested only.

Fixes: d851b47b22fc ("net: fec: add interrupt coalescence feature support")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Fugang Duan <fugang.duan@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_main.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 8336f4cbaf95..3fc8a66e4f41 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -2529,15 +2529,15 @@ fec_enet_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *ec)
 		return -EINVAL;
 	}
 
-	cycle = fec_enet_us_to_itr_clock(ndev, fep->rx_time_itr);
+	cycle = fec_enet_us_to_itr_clock(ndev, ec->rx_coalesce_usecs);
 	if (cycle > 0xFFFF) {
 		dev_err(dev, "Rx coalesced usec exceed hardware limitation\n");
 		return -EINVAL;
 	}
 
-	cycle = fec_enet_us_to_itr_clock(ndev, fep->tx_time_itr);
+	cycle = fec_enet_us_to_itr_clock(ndev, ec->tx_coalesce_usecs);
 	if (cycle > 0xFFFF) {
-		dev_err(dev, "Rx coalesced usec exceed hardware limitation\n");
+		dev_err(dev, "Tx coalesced usec exceed hardware limitation\n");
 		return -EINVAL;
 	}
 
-- 
2.20.1


From b320517cc140491d7479380fce2e98e935c54922 Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Thu, 5 Mar 2020 09:47:53 +0800
Subject: [PATCH 13/52] net: hns3: fix a not link up issue when fibre port
 supports autoneg

[ Upstream commit 68e1006f618e509fc7869259fe83ceec4a95dac3 ]

When fibre port supports auto-negotiation, the IMP(Intelligent
Management Process) processes the speed of auto-negotiation
and the  user's speed separately.
For below case, the port will get a not link up problem.
step 1: disables auto-negotiation and sets speed to A, then
the driver's MAC speed will be updated to A.
step 2: enables auto-negotiation and MAC gets negotiated
speed B, then the driver's MAC speed will be updated to B
through querying in periodical task.
step 3: MAC gets new negotiated speed A.
step 4: disables auto-negotiation and sets speed to B before
periodical task query new MAC speed A, the driver will  ignore
the speed configuration.

This patch fixes it by skipping speed and duplex checking when
fibre port supports auto-negotiation.

Fixes: 22f48e24a23d ("net: hns3: add autoneg and change speed support for fibre port")
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index c01cf8ef69df..d4652dea4569 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2417,10 +2417,12 @@ static int hclge_cfg_mac_speed_dup_hw(struct hclge_dev *hdev, int speed,
 
 int hclge_cfg_mac_speed_dup(struct hclge_dev *hdev, int speed, u8 duplex)
 {
+	struct hclge_mac *mac = &hdev->hw.mac;
 	int ret;
 
 	duplex = hclge_check_speed_dup(duplex, speed);
-	if (hdev->hw.mac.speed == speed && hdev->hw.mac.duplex == duplex)
+	if (!mac->support_autoneg && mac->speed == speed &&
+	    mac->duplex == duplex)
 		return 0;
 
 	ret = hclge_cfg_mac_speed_dup_hw(hdev, speed, duplex);
-- 
2.20.1


From c29aeedc5eec6c0abfc3c45e9770a8823dd3f113 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Sat, 29 Feb 2020 17:27:13 +0800
Subject: [PATCH 14/52] net/ipv6: use configured metric when add peer route

[ Upstream commit 07758eb9ff52794fba15d03aa88d92dbd1b7d125 ]

When we add peer address with metric configured, IPv4 could set the dest
metric correctly, but IPv6 do not. e.g.

]# ip addr add 192.0.2.1 peer 192.0.2.2/32 dev eth1 metric 20
]# ip route show dev eth1
192.0.2.2 proto kernel scope link src 192.0.2.1 metric 20
]# ip addr add 2001:db8::1 peer 2001:db8::2/128 dev eth1 metric 20
]# ip -6 route show dev eth1
2001:db8::1 proto kernel metric 20 pref medium
2001:db8::2 proto kernel metric 256 pref medium

Fix this by using configured metric instead of default one.

Reported-by: Jianlin Shi <jishi@redhat.com>
Fixes: 8308f3ff1753 ("net/ipv6: Add support for specifying metric of connected routes")
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 69e89baba183..68d713ba9136 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5988,9 +5988,9 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
 		if (ifp->idev->cnf.forwarding)
 			addrconf_join_anycast(ifp);
 		if (!ipv6_addr_any(&ifp->peer_addr))
-			addrconf_prefix_route(&ifp->peer_addr, 128, 0,
-					      ifp->idev->dev, 0, 0,
-					      GFP_ATOMIC);
+			addrconf_prefix_route(&ifp->peer_addr, 128,
+					      ifp->rt_priority, ifp->idev->dev,
+					      0, 0, GFP_ATOMIC);
 		break;
 	case RTM_DELADDR:
 		if (ifp->idev->cnf.forwarding)
-- 
2.20.1


From 1ddcf2705ac60d0da19cffec8462c95dfc58dd90 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 26 Feb 2020 19:47:34 +0100
Subject: [PATCH 15/52] netlink: Use netlink header as base to calculate bad
 attribute offset

[ Upstream commit 84b3268027641401bb8ad4427a90a3cce2eb86f5 ]

Userspace might send a batch that is composed of several netlink
messages. The netlink_ack() function must use the pointer to the netlink
header as base to calculate the bad attribute offset.

Fixes: 2d4bc93368f5 ("netlink: extended ACK reporting")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index e64b8784d487..c2a5174387ff 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2434,7 +2434,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err,
 							       in_skb->len))
 				WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_OFFS,
 						    (u8 *)extack->bad_attr -
-						    in_skb->data));
+						    (u8 *)nlh));
 		} else {
 			if (extack->cookie_len)
 				WARN_ON(nla_put(skb, NLMSGERR_ATTR_COOKIE,
-- 
2.20.1


From 23f1661adffae5581877961ff909684d252f31dc Mon Sep 17 00:00:00 2001
From: Dmitry Bogdanov <dbogdanov@marvell.com>
Date: Tue, 10 Mar 2020 18:22:24 +0300
Subject: [PATCH 16/52] net: macsec: update SCI upon MAC address change.

[ Upstream commit 6fc498bc82929ee23aa2f35a828c6178dfd3f823 ]

SCI should be updated, because it contains MAC in its first 6 octets.

Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver")
Signed-off-by: Dmitry Bogdanov <dbogdanov@marvell.com>
Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macsec.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index afd8b2a08245..3221c3b4efb1 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -2882,6 +2882,11 @@ static void macsec_dev_set_rx_mode(struct net_device *dev)
 	dev_uc_sync(real_dev, dev);
 }
 
+static sci_t dev_to_sci(struct net_device *dev, __be16 port)
+{
+	return make_sci(dev->dev_addr, port);
+}
+
 static int macsec_set_mac_address(struct net_device *dev, void *p)
 {
 	struct macsec_dev *macsec = macsec_priv(dev);
@@ -2903,6 +2908,7 @@ static int macsec_set_mac_address(struct net_device *dev, void *p)
 
 out:
 	ether_addr_copy(dev->dev_addr, addr->sa_data);
+	macsec->secy.sci = dev_to_sci(dev, MACSEC_PORT_ES);
 	return 0;
 }
 
@@ -3176,11 +3182,6 @@ static bool sci_exists(struct net_device *dev, sci_t sci)
 	return false;
 }
 
-static sci_t dev_to_sci(struct net_device *dev, __be16 port)
-{
-	return make_sci(dev->dev_addr, port);
-}
-
 static int macsec_add_dev(struct net_device *dev, sci_t sci, u8 icv_len)
 {
 	struct macsec_dev *macsec = macsec_priv(dev);
-- 
2.20.1


From 64c7a53ae4a4969f7a21ce4073dd4da595d39155 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 4 Mar 2020 17:24:31 +0300
Subject: [PATCH 17/52] net: nfc: fix bounds checking bugs on "pipe"

[ Upstream commit a3aefbfe45751bf7b338c181b97608e276b5bb73 ]

This is similar to commit 674d9de02aa7 ("NFC: Fix possible memory
corruption when handling SHDLC I-Frame commands") and commit d7ee81ad09f0
("NFC: nci: Add some bounds checking in nci_hci_cmd_received()") which
added range checks on "pipe".

The "pipe" variable comes skb->data[0] in nfc_hci_msg_rx_work().
It's in the 0-255 range.  We're using it as the array index into the
hdev->pipes[] array which has NFC_HCI_MAX_PIPES (128) members.

Fixes: 118278f20aa8 ("NFC: hci: Add pipes table to reference them with a tuple {gate, host}")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/nfc/hci/core.c | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c
index 6f1b096e601c..43811b5219b5 100644
--- a/net/nfc/hci/core.c
+++ b/net/nfc/hci/core.c
@@ -181,13 +181,20 @@ void nfc_hci_resp_received(struct nfc_hci_dev *hdev, u8 result,
 void nfc_hci_cmd_received(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd,
 			  struct sk_buff *skb)
 {
-	u8 gate = hdev->pipes[pipe].gate;
 	u8 status = NFC_HCI_ANY_OK;
 	struct hci_create_pipe_resp *create_info;
 	struct hci_delete_pipe_noti *delete_info;
 	struct hci_all_pipe_cleared_noti *cleared_info;
+	u8 gate;
 
-	pr_debug("from gate %x pipe %x cmd %x\n", gate, pipe, cmd);
+	pr_debug("from pipe %x cmd %x\n", pipe, cmd);
+
+	if (pipe >= NFC_HCI_MAX_PIPES) {
+		status = NFC_HCI_ANY_E_NOK;
+		goto exit;
+	}
+
+	gate = hdev->pipes[pipe].gate;
 
 	switch (cmd) {
 	case NFC_HCI_ADM_NOTIFY_PIPE_CREATED:
@@ -375,8 +382,14 @@ void nfc_hci_event_received(struct nfc_hci_dev *hdev, u8 pipe, u8 event,
 			    struct sk_buff *skb)
 {
 	int r = 0;
-	u8 gate = hdev->pipes[pipe].gate;
+	u8 gate;
+
+	if (pipe >= NFC_HCI_MAX_PIPES) {
+		pr_err("Discarded event %x to invalid pipe %x\n", event, pipe);
+		goto exit;
+	}
 
+	gate = hdev->pipes[pipe].gate;
 	if (gate == NFC_HCI_INVALID_GATE) {
 		pr_err("Discarded event %x to unopened pipe %x\n", event, pipe);
 		goto exit;
-- 
2.20.1


From c19f9e4927cbdfaaaf1fa1d550ee52ee7fbb10b4 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Mon, 9 Mar 2020 11:34:35 -0400
Subject: [PATCH 18/52] net/packet: tpacket_rcv: do not increment ring index on
 drop

[ Upstream commit 46e4c421a053c36bf7a33dda2272481bcaf3eed3 ]

In one error case, tpacket_rcv drops packets after incrementing the
ring producer index.

If this happens, it does not update tp_status to TP_STATUS_USER and
thus the reader is stalled for an iteration of the ring, causing out
of order arrival.

The only such error path is when virtio_net_hdr_from_skb fails due
to encountering an unknown GSO type.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 118cd66b7516..20edb7c25e22 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2273,6 +2273,13 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 					TP_STATUS_KERNEL, (macoff+snaplen));
 	if (!h.raw)
 		goto drop_n_account;
+
+	if (do_vnet &&
+	    virtio_net_hdr_from_skb(skb, h.raw + macoff -
+				    sizeof(struct virtio_net_hdr),
+				    vio_le(), true, 0))
+		goto drop_n_account;
+
 	if (po->tp_version <= TPACKET_V2) {
 		packet_increment_rx_head(po, &po->rx_ring);
 	/*
@@ -2285,12 +2292,6 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 			status |= TP_STATUS_LOSING;
 	}
 
-	if (do_vnet &&
-	    virtio_net_hdr_from_skb(skb, h.raw + macoff -
-				    sizeof(struct virtio_net_hdr),
-				    vio_le(), true, 0))
-		goto drop_n_account;
-
 	po->stats.stats1.tp_packets++;
 	if (copy_skb) {
 		status |= TP_STATUS_COPY;
-- 
2.20.1


From 921f8956095912e49c1ee34ecc505371b34f6d3a Mon Sep 17 00:00:00 2001
From: Jonas Gorski <jonas.gorski@gmail.com>
Date: Mon, 2 Mar 2020 20:46:57 +0100
Subject: [PATCH 19/52] net: phy: bcm63xx: fix OOPS due to missing driver name

[ Upstream commit 43de81b0601df7d7988d3f5617ee0987df65c883 ]

719655a14971 ("net: phy: Replace phy driver features u32 with link_mode
bitmap") was a bit over-eager and also removed the second phy driver's
name, resulting in a nasty OOPS on registration:

[    1.319854] CPU 0 Unable to handle kernel paging request at virtual address 00000000, epc == 804dd50c, ra == 804dd4f0
[    1.330859] Oops[#1]:
[    1.333138] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.4.22 #0
[    1.339217] $ 0   : 00000000 00000001 87ca7f00 805c1874
[    1.344590] $ 4   : 00000000 00000047 00585000 8701f800
[    1.349965] $ 8   : 8701f800 804f4a5c 00000003 64726976
[    1.355341] $12   : 00000001 00000000 00000000 00000114
[    1.360718] $16   : 87ca7f80 00000000 00000000 80639fe4
[    1.366093] $20   : 00000002 00000000 806441d0 80b90000
[    1.371470] $24   : 00000000 00000000
[    1.376847] $28   : 87c1e000 87c1fda0 80b90000 804dd4f0
[    1.382224] Hi    : d1c8f8da
[    1.385180] Lo    : 5518a480
[    1.388182] epc   : 804dd50c kset_find_obj+0x3c/0x114
[    1.393345] ra    : 804dd4f0 kset_find_obj+0x20/0x114
[    1.398530] Status: 10008703 KERNEL EXL IE
[    1.402833] Cause : 00800008 (ExcCode 02)
[    1.406952] BadVA : 00000000
[    1.409913] PrId  : 0002a075 (Broadcom BMIPS4350)
[    1.414745] Modules linked in:
[    1.417895] Process swapper/0 (pid: 1, threadinfo=(ptrval), task=(ptrval), tls=00000000)
[    1.426214] Stack : 87cec000 80630000 80639370 80640658 80640000 80049af4 80639fe4 8063a0d8
[    1.434816]         8063a0d8 802ef078 00000002 00000000 806441d0 80b90000 8063a0d8 802ef114
[    1.443417]         87cea0de 87c1fde0 00000000 804de488 87cea000 8063a0d8 8063a0d8 80334e48
[    1.452018]         80640000 8063984c 80639bf4 00000000 8065de48 00000001 8063a0d8 80334ed0
[    1.460620]         806441d0 80b90000 80b90000 802ef164 8065dd70 80620000 80b90000 8065de58
[    1.469222]         ...
[    1.471734] Call Trace:
[    1.474255] [<804dd50c>] kset_find_obj+0x3c/0x114
[    1.479141] [<802ef078>] driver_find+0x1c/0x44
[    1.483665] [<802ef114>] driver_register+0x74/0x148
[    1.488719] [<80334e48>] phy_driver_register+0x9c/0xd0
[    1.493968] [<80334ed0>] phy_drivers_register+0x54/0xe8
[    1.499345] [<8001061c>] do_one_initcall+0x7c/0x1f4
[    1.504374] [<80644ed8>] kernel_init_freeable+0x1d4/0x2b4
[    1.509940] [<804f4e24>] kernel_init+0x10/0xf8
[    1.514502] [<80018e68>] ret_from_kernel_thread+0x14/0x1c
[    1.520040] Code: 1060000c  02202025  90650000 <90810000> 24630001  14250004  24840001  14a0fffb  90650000
[    1.530061]
[    1.531698] ---[ end trace d52f1717cd29bdc8 ]---

Fix it by readding the name.

Fixes: 719655a14971 ("net: phy: Replace phy driver features u32 with link_mode bitmap")
Signed-off-by: Jonas Gorski <jonas.gorski@gmail.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/bcm63xx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/phy/bcm63xx.c b/drivers/net/phy/bcm63xx.c
index 23f1958ba6ad..459fb2069c7e 100644
--- a/drivers/net/phy/bcm63xx.c
+++ b/drivers/net/phy/bcm63xx.c
@@ -73,6 +73,7 @@ static struct phy_driver bcm63xx_driver[] = {
 	/* same phy as above, with just a different OUI */
 	.phy_id		= 0x002bdc00,
 	.phy_id_mask	= 0xfffffc00,
+	.name		= "Broadcom BCM63XX (2)",
 	/* PHY_BASIC_FEATURES */
 	.flags		= PHY_IS_INTERNAL,
 	.config_init	= bcm63xx_config_init,
-- 
2.20.1


From bef2eeaf5e58491587a538c247298b36a922f1c2 Mon Sep 17 00:00:00 2001
From: Remi Pommarel <repk@triplefau.lt>
Date: Sun, 8 Mar 2020 10:25:56 +0100
Subject: [PATCH 20/52] net: stmmac: dwmac1000: Disable ACS if enhanced descs
 are not used

[ Upstream commit b723bd933980f4956dabc8a8d84b3e83be8d094c ]

ACS (auto PAD/FCS stripping) removes FCS off 802.3 packets (LLC) so that
there is no need to manually strip it for such packets. The enhanced DMA
descriptors allow to flag LLC packets so that the receiving callback can
use that to strip FCS manually or not. On the other hand, normal
descriptors do not support that.

Thus in order to not truncate LLC packet ACS should be disabled when
using normal DMA descriptors.

Fixes: 47dd7a540b8a0 ("net: add support for STMicroelectronics Ethernet controllers.")
Signed-off-by: Remi Pommarel <repk@triplefau.lt>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
index 3d69da112625..43a785f86c69 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
@@ -24,6 +24,7 @@
 static void dwmac1000_core_init(struct mac_device_info *hw,
 				struct net_device *dev)
 {
+	struct stmmac_priv *priv = netdev_priv(dev);
 	void __iomem *ioaddr = hw->pcsr;
 	u32 value = readl(ioaddr + GMAC_CONTROL);
 	int mtu = dev->mtu;
@@ -35,7 +36,7 @@ static void dwmac1000_core_init(struct mac_device_info *hw,
 	 * Broadcom tags can look like invalid LLC/SNAP packets and cause the
 	 * hardware to truncate packets on reception.
 	 */
-	if (netdev_uses_dsa(dev))
+	if (netdev_uses_dsa(dev) || !priv->plat->enh_desc)
 		value &= ~GMAC_CONTROL_ACS;
 
 	if (mtu > 1500)
-- 
2.20.1


From 558834b67fcaf188fb132d3fcb07f3140ffc353d Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Thu, 12 Mar 2020 15:04:30 +0000
Subject: [PATCH 21/52] net: systemport: fix index check to avoid an array out
 of bounds access

[ Upstream commit c0368595c1639947839c0db8294ee96aca0b3b86 ]

Currently the bounds check on index is off by one and can lead to
an out of bounds access on array priv->filters_loc when index is
RXCHK_BRCM_TAG_MAX.

Fixes: bb9051a2b230 ("net: systemport: Add support for WAKE_FILTER")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bcmsysport.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 4a27577e137b..ad86a186ddc5 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -2135,7 +2135,7 @@ static int bcm_sysport_rule_set(struct bcm_sysport_priv *priv,
 		return -ENOSPC;
 
 	index = find_first_zero_bit(priv->filters, RXCHK_BRCM_TAG_MAX);
-	if (index > RXCHK_BRCM_TAG_MAX)
+	if (index >= RXCHK_BRCM_TAG_MAX)
 		return -ENOSPC;
 
 	/* Location is the classification ID, and index is the position
-- 
2.20.1


From d0f2f298410cdbe1a687153547787152f60d9708 Mon Sep 17 00:00:00 2001
From: You-Sheng Yang <vicamo.yang@canonical.com>
Date: Wed, 26 Feb 2020 23:37:10 +0800
Subject: [PATCH 22/52] r8152: check disconnect status after long sleep

[ Upstream commit d64c7a08034b32c285e576208ae44fc3ba3fa7df ]

Dell USB Type C docking WD19/WD19DC attaches additional peripherals as:

  /: Bus 02.Port 1: Dev 1, Class=root_hub, Driver=xhci_hcd/6p, 5000M
      |__ Port 1: Dev 11, If 0, Class=Hub, Driver=hub/4p, 5000M
          |__ Port 3: Dev 12, If 0, Class=Hub, Driver=hub/4p, 5000M
          |__ Port 4: Dev 13, If 0, Class=Vendor Specific Class,
              Driver=r8152, 5000M

where usb 2-1-3 is a hub connecting all USB Type-A/C ports on the dock.

When hotplugging such dock with additional usb devices already attached on
it, the probing process may reset usb 2.1 port, therefore r8152 ethernet
device is also reset. However, during r8152 device init there are several
for-loops that, when it's unable to retrieve hardware registers due to
being disconnected from USB, may take up to 14 seconds each in practice,
and that has to be completed before USB may re-enumerate devices on the
bus. As a result, devices attached to the dock will only be available
after nearly 1 minute after the dock was plugged in:

  [ 216.388290] [250] r8152 2-1.4:1.0: usb_probe_interface
  [ 216.388292] [250] r8152 2-1.4:1.0: usb_probe_interface - got id
  [ 258.830410] r8152 2-1.4:1.0 (unnamed net_device) (uninitialized): PHY not ready
  [ 258.830460] r8152 2-1.4:1.0 (unnamed net_device) (uninitialized): Invalid header when reading pass-thru MAC addr
  [ 258.830464] r8152 2-1.4:1.0 (unnamed net_device) (uninitialized): Get ether addr fail

This happens in, for example, r8153_init:

  static int generic_ocp_read(struct r8152 *tp, u16 index, u16 size,
			    void *data, u16 type)
  {
    if (test_bit(RTL8152_UNPLUG, &tp->flags))
      return -ENODEV;
    ...
  }

  static u16 ocp_read_word(struct r8152 *tp, u16 type, u16 index)
  {
    u32 data;
    ...
    generic_ocp_read(tp, index, sizeof(tmp), &tmp, type | byen);

    data = __le32_to_cpu(tmp);
    ...
    return (u16)data;
  }

  static void r8153_init(struct r8152 *tp)
  {
    ...
    if (test_bit(RTL8152_UNPLUG, &tp->flags))
      return;

    for (i = 0; i < 500; i++) {
      if (ocp_read_word(tp, MCU_TYPE_PLA, PLA_BOOT_CTRL) &
          AUTOLOAD_DONE)
        break;
      msleep(20);
    }
    ...
  }

Since ocp_read_word() doesn't check the return status of
generic_ocp_read(), and the only exit condition for the loop is to have
a match in the returned value, such loops will only ends after exceeding
its maximum runs when the device has been marked as disconnected, which
takes 500 * 20ms = 10 seconds in theory, 14 in practice.

To solve this long latency another test to RTL8152_UNPLUG flag should be
added after those 20ms sleep to skip unnecessary loops, so that the device
probe can complete early and proceed to parent port reset/reprobe process.

This can be reproduced on all kernel versions up to latest v5.6-rc2, but
after v5.5-rc7 the reproduce rate is dramatically lowered to 1/30 or less
while it was around 1/2.

Signed-off-by: You-Sheng Yang <vicamo.yang@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 6912624eed4a..44ea5dcc43fd 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -3006,6 +3006,8 @@ static u16 r8153_phy_status(struct r8152 *tp, u16 desired)
 		}
 
 		msleep(20);
+		if (test_bit(RTL8152_UNPLUG, &tp->flags))
+			break;
 	}
 
 	return data;
@@ -4419,7 +4421,10 @@ static void r8153_init(struct r8152 *tp)
 		if (ocp_read_word(tp, MCU_TYPE_PLA, PLA_BOOT_CTRL) &
 		    AUTOLOAD_DONE)
 			break;
+
 		msleep(20);
+		if (test_bit(RTL8152_UNPLUG, &tp->flags))
+			break;
 	}
 
 	data = r8153_phy_status(tp, 0);
@@ -4545,7 +4550,10 @@ static void r8153b_init(struct r8152 *tp)
 		if (ocp_read_word(tp, MCU_TYPE_PLA, PLA_BOOT_CTRL) &
 		    AUTOLOAD_DONE)
 			break;
+
 		msleep(20);
+		if (test_bit(RTL8152_UNPLUG, &tp->flags))
+			break;
 	}
 
 	data = r8153_phy_status(tp, 0);
-- 
2.20.1


From 6a03ea06d9b03d9d8feec55f813fb98d7028788b Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Mon, 9 Mar 2020 18:16:24 +0000
Subject: [PATCH 23/52] sfc: detach from cb_page in efx_copy_channel()

[ Upstream commit 4b1bd9db078f7d5332c8601a2f5bd43cf0458fd4 ]

It's a resource, not a parameter, so we can't copy it into the new
 channel's TX queues, otherwise aliasing will lead to resource-
 management bugs if the channel is subsequently torn down without
 being initialised.

Before the Fixes:-tagged commit there was a similar bug with
 tsoh_page, but I'm not sure it's worth doing another fix for such
 old kernels.

Fixes: e9117e5099ea ("sfc: Firmware-Assisted TSO version 2")
Suggested-by: Derek Shute <Derek.Shute@stratus.com>
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/efx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 2fef7402233e..82391abbd42b 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -519,6 +519,7 @@ efx_copy_channel(const struct efx_channel *old_channel)
 		if (tx_queue->channel)
 			tx_queue->channel = channel;
 		tx_queue->buffer = NULL;
+		tx_queue->cb_page = NULL;
 		memset(&tx_queue->txd, 0, sizeof(tx_queue->txd));
 	}
 
-- 
2.20.1


From 7e8be1f08ae162be9ba3d13b02a46ca1b8660fb8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 4 Mar 2020 15:51:43 -0800
Subject: [PATCH 24/52] slip: make slhc_compress() more robust against
 malicious packets

[ Upstream commit 110a40dfb708fe940a3f3704d470e431c368d256 ]

Before accessing various fields in IPV4 network header
and TCP header, make sure the packet :

- Has IP version 4 (ip->version == 4)
- Has not a silly network length (ip->ihl >= 5)
- Is big enough to hold network and transport headers
- Has not a silly TCP header size (th->doff >= sizeof(struct tcphdr) / 4)

syzbot reported :

BUG: KMSAN: uninit-value in slhc_compress+0x5b9/0x2e60 drivers/net/slip/slhc.c:270
CPU: 0 PID: 11728 Comm: syz-executor231 Not tainted 5.6.0-rc2-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c9/0x220 lib/dump_stack.c:118
 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:118
 __msan_warning+0x58/0xa0 mm/kmsan/kmsan_instr.c:215
 slhc_compress+0x5b9/0x2e60 drivers/net/slip/slhc.c:270
 ppp_send_frame drivers/net/ppp/ppp_generic.c:1637 [inline]
 __ppp_xmit_process+0x1902/0x2970 drivers/net/ppp/ppp_generic.c:1495
 ppp_xmit_process+0x147/0x2f0 drivers/net/ppp/ppp_generic.c:1516
 ppp_write+0x6bb/0x790 drivers/net/ppp/ppp_generic.c:512
 do_loop_readv_writev fs/read_write.c:717 [inline]
 do_iter_write+0x812/0xdc0 fs/read_write.c:1000
 compat_writev+0x2df/0x5a0 fs/read_write.c:1351
 do_compat_pwritev64 fs/read_write.c:1400 [inline]
 __do_compat_sys_pwritev fs/read_write.c:1420 [inline]
 __se_compat_sys_pwritev fs/read_write.c:1414 [inline]
 __ia32_compat_sys_pwritev+0x349/0x3f0 fs/read_write.c:1414
 do_syscall_32_irqs_on arch/x86/entry/common.c:339 [inline]
 do_fast_syscall_32+0x3c7/0x6e0 arch/x86/entry/common.c:410
 entry_SYSENTER_compat+0x68/0x77 arch/x86/entry/entry_64_compat.S:139
RIP: 0023:0xf7f7cd99
Code: 90 e8 0b 00 00 00 f3 90 0f ae e8 eb f9 8d 74 26 00 89 3c 24 c3 90 90 90 90 90 90 90 90 90 90 90 90 51 52 55 89 e5 0f 34 cd 80 <5d> 5a 59 c3 90 90 90 90 eb 0d 90 90 90 90 90 90 90 90 90 90 90 90
RSP: 002b:00000000ffdb84ac EFLAGS: 00000217 ORIG_RAX: 000000000000014e
RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00000000200001c0
RDX: 0000000000000001 RSI: 0000000000000000 RDI: 0000000000000003
RBP: 0000000040047459 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000

Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:144 [inline]
 kmsan_internal_poison_shadow+0x66/0xd0 mm/kmsan/kmsan.c:127
 kmsan_slab_alloc+0x8a/0xe0 mm/kmsan/kmsan_hooks.c:82
 slab_alloc_node mm/slub.c:2793 [inline]
 __kmalloc_node_track_caller+0xb40/0x1200 mm/slub.c:4401
 __kmalloc_reserve net/core/skbuff.c:142 [inline]
 __alloc_skb+0x2fd/0xac0 net/core/skbuff.c:210
 alloc_skb include/linux/skbuff.h:1051 [inline]
 ppp_write+0x115/0x790 drivers/net/ppp/ppp_generic.c:500
 do_loop_readv_writev fs/read_write.c:717 [inline]
 do_iter_write+0x812/0xdc0 fs/read_write.c:1000
 compat_writev+0x2df/0x5a0 fs/read_write.c:1351
 do_compat_pwritev64 fs/read_write.c:1400 [inline]
 __do_compat_sys_pwritev fs/read_write.c:1420 [inline]
 __se_compat_sys_pwritev fs/read_write.c:1414 [inline]
 __ia32_compat_sys_pwritev+0x349/0x3f0 fs/read_write.c:1414
 do_syscall_32_irqs_on arch/x86/entry/common.c:339 [inline]
 do_fast_syscall_32+0x3c7/0x6e0 arch/x86/entry/common.c:410
 entry_SYSENTER_compat+0x68/0x77 arch/x86/entry/entry_64_compat.S:139

Fixes: b5451d783ade ("slip: Move the SLIP drivers")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/slip/slhc.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/net/slip/slhc.c b/drivers/net/slip/slhc.c
index 58a69f830d29..f78ceba42e57 100644
--- a/drivers/net/slip/slhc.c
+++ b/drivers/net/slip/slhc.c
@@ -232,7 +232,7 @@ slhc_compress(struct slcompress *comp, unsigned char *icp, int isize,
 	struct cstate *cs = lcs->next;
 	unsigned long deltaS, deltaA;
 	short changes = 0;
-	int hlen;
+	int nlen, hlen;
 	unsigned char new_seq[16];
 	unsigned char *cp = new_seq;
 	struct iphdr *ip;
@@ -248,6 +248,8 @@ slhc_compress(struct slcompress *comp, unsigned char *icp, int isize,
 		return isize;
 
 	ip = (struct iphdr *) icp;
+	if (ip->version != 4 || ip->ihl < 5)
+		return isize;
 
 	/* Bail if this packet isn't TCP, or is an IP fragment */
 	if (ip->protocol != IPPROTO_TCP || (ntohs(ip->frag_off) & 0x3fff)) {
@@ -258,10 +260,14 @@ slhc_compress(struct slcompress *comp, unsigned char *icp, int isize,
 			comp->sls_o_tcp++;
 		return isize;
 	}
-	/* Extract TCP header */
+	nlen = ip->ihl * 4;
+	if (isize < nlen + sizeof(*th))
+		return isize;
 
-	th = (struct tcphdr *)(((unsigned char *)ip) + ip->ihl*4);
-	hlen = ip->ihl*4 + th->doff*4;
+	th = (struct tcphdr *)(icp + nlen);
+	if (th->doff < sizeof(struct tcphdr) / 4)
+		return isize;
+	hlen = nlen + th->doff * 4;
 
 	/*  Bail if the TCP packet isn't `compressible' (i.e., ACK isn't set or
 	 *  some other control bit is set). Also uncompressible if
-- 
2.20.1


From 24f754bb836cd43db0e275e3e1b2af5b262cffe7 Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Mon, 9 Mar 2020 10:39:53 -0700
Subject: [PATCH 25/52] taprio: Fix sending packets without dequeueing them

[ Upstream commit b09fe70ef520e011ba4a64f4b93f948a8f14717b ]

There was a bug that was causing packets to be sent to the driver
without first calling dequeue() on the "child" qdisc. And the KASAN
report below shows that sending a packet without calling dequeue()
leads to bad results.

The problem is that when checking the last qdisc "child" we do not set
the returned skb to NULL, which can cause it to be sent to the driver,
and so after the skb is sent, it may be freed, and in some situations a
reference to it may still be in the child qdisc, because it was never
dequeued.

The crash log looks like this:

[   19.937538] ==================================================================
[   19.938300] BUG: KASAN: use-after-free in taprio_dequeue_soft+0x620/0x780
[   19.938968] Read of size 4 at addr ffff8881128628cc by task swapper/1/0
[   19.939612]
[   19.939772] CPU: 1 PID: 0 Comm: swapper/1 Not tainted 5.6.0-rc3+ #97
[   19.940397] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qe4
[   19.941523] Call Trace:
[   19.941774]  <IRQ>
[   19.941985]  dump_stack+0x97/0xe0
[   19.942323]  print_address_description.constprop.0+0x3b/0x60
[   19.942884]  ? taprio_dequeue_soft+0x620/0x780
[   19.943325]  ? taprio_dequeue_soft+0x620/0x780
[   19.943767]  __kasan_report.cold+0x1a/0x32
[   19.944173]  ? taprio_dequeue_soft+0x620/0x780
[   19.944612]  kasan_report+0xe/0x20
[   19.944954]  taprio_dequeue_soft+0x620/0x780
[   19.945380]  __qdisc_run+0x164/0x18d0
[   19.945749]  net_tx_action+0x2c4/0x730
[   19.946124]  __do_softirq+0x268/0x7bc
[   19.946491]  irq_exit+0x17d/0x1b0
[   19.946824]  smp_apic_timer_interrupt+0xeb/0x380
[   19.947280]  apic_timer_interrupt+0xf/0x20
[   19.947687]  </IRQ>
[   19.947912] RIP: 0010:default_idle+0x2d/0x2d0
[   19.948345] Code: 00 00 41 56 41 55 65 44 8b 2d 3f 8d 7c 7c 41 54 55 53 0f 1f 44 00 00 e8 b1 b2 c5 fd e9 07 00 3
[   19.950166] RSP: 0018:ffff88811a3efda0 EFLAGS: 00000282 ORIG_RAX: ffffffffffffff13
[   19.950909] RAX: 0000000080000000 RBX: ffff88811a3a9600 RCX: ffffffff8385327e
[   19.951608] RDX: 1ffff110234752c0 RSI: 0000000000000000 RDI: ffffffff8385262f
[   19.952309] RBP: ffffed10234752c0 R08: 0000000000000001 R09: ffffed10234752c1
[   19.953009] R10: ffffed10234752c0 R11: ffff88811a3a9607 R12: 0000000000000001
[   19.953709] R13: 0000000000000001 R14: 0000000000000000 R15: 0000000000000000
[   19.954408]  ? default_idle_call+0x2e/0x70
[   19.954816]  ? default_idle+0x1f/0x2d0
[   19.955192]  default_idle_call+0x5e/0x70
[   19.955584]  do_idle+0x3d4/0x500
[   19.955909]  ? arch_cpu_idle_exit+0x40/0x40
[   19.956325]  ? _raw_spin_unlock_irqrestore+0x23/0x30
[   19.956829]  ? trace_hardirqs_on+0x30/0x160
[   19.957242]  cpu_startup_entry+0x19/0x20
[   19.957633]  start_secondary+0x2a6/0x380
[   19.958026]  ? set_cpu_sibling_map+0x18b0/0x18b0
[   19.958486]  secondary_startup_64+0xa4/0xb0
[   19.958921]
[   19.959078] Allocated by task 33:
[   19.959412]  save_stack+0x1b/0x80
[   19.959747]  __kasan_kmalloc.constprop.0+0xc2/0xd0
[   19.960222]  kmem_cache_alloc+0xe4/0x230
[   19.960617]  __alloc_skb+0x91/0x510
[   19.960967]  ndisc_alloc_skb+0x133/0x330
[   19.961358]  ndisc_send_ns+0x134/0x810
[   19.961735]  addrconf_dad_work+0xad5/0xf80
[   19.962144]  process_one_work+0x78e/0x13a0
[   19.962551]  worker_thread+0x8f/0xfa0
[   19.962919]  kthread+0x2ba/0x3b0
[   19.963242]  ret_from_fork+0x3a/0x50
[   19.963596]
[   19.963753] Freed by task 33:
[   19.964055]  save_stack+0x1b/0x80
[   19.964386]  __kasan_slab_free+0x12f/0x180
[   19.964830]  kmem_cache_free+0x80/0x290
[   19.965231]  ip6_mc_input+0x38a/0x4d0
[   19.965617]  ipv6_rcv+0x1a4/0x1d0
[   19.965948]  __netif_receive_skb_one_core+0xf2/0x180
[   19.966437]  netif_receive_skb+0x8c/0x3c0
[   19.966846]  br_handle_frame_finish+0x779/0x1310
[   19.967302]  br_handle_frame+0x42a/0x830
[   19.967694]  __netif_receive_skb_core+0xf0e/0x2a90
[   19.968167]  __netif_receive_skb_one_core+0x96/0x180
[   19.968658]  process_backlog+0x198/0x650
[   19.969047]  net_rx_action+0x2fa/0xaa0
[   19.969420]  __do_softirq+0x268/0x7bc
[   19.969785]
[   19.969940] The buggy address belongs to the object at ffff888112862840
[   19.969940]  which belongs to the cache skbuff_head_cache of size 224
[   19.971202] The buggy address is located 140 bytes inside of
[   19.971202]  224-byte region [ffff888112862840, ffff888112862920)
[   19.972344] The buggy address belongs to the page:
[   19.972820] page:ffffea00044a1800 refcount:1 mapcount:0 mapping:ffff88811a2bd1c0 index:0xffff8881128625c0 compo0
[   19.973930] flags: 0x8000000000010200(slab|head)
[   19.974388] raw: 8000000000010200 ffff88811a2ed650 ffff88811a2ed650 ffff88811a2bd1c0
[   19.975151] raw: ffff8881128625c0 0000000000190013 00000001ffffffff 0000000000000000
[   19.975915] page dumped because: kasan: bad access detected
[   19.976461] page_owner tracks the page as allocated
[   19.976946] page last allocated via order 2, migratetype Unmovable, gfp_mask 0xd20c0(__GFP_IO|__GFP_FS|__GFP_NO)
[   19.978332]  prep_new_page+0x24b/0x330
[   19.978707]  get_page_from_freelist+0x2057/0x2c90
[   19.979170]  __alloc_pages_nodemask+0x218/0x590
[   19.979619]  new_slab+0x9d/0x300
[   19.979948]  ___slab_alloc.constprop.0+0x2f9/0x6f0
[   19.980421]  __slab_alloc.constprop.0+0x30/0x60
[   19.980870]  kmem_cache_alloc+0x201/0x230
[   19.981269]  __alloc_skb+0x91/0x510
[   19.981620]  alloc_skb_with_frags+0x78/0x4a0
[   19.982043]  sock_alloc_send_pskb+0x5eb/0x750
[   19.982476]  unix_stream_sendmsg+0x399/0x7f0
[   19.982904]  sock_sendmsg+0xe2/0x110
[   19.983262]  ____sys_sendmsg+0x4de/0x6d0
[   19.983660]  ___sys_sendmsg+0xe4/0x160
[   19.984032]  __sys_sendmsg+0xab/0x130
[   19.984396]  do_syscall_64+0xe7/0xae0
[   19.984761] page last free stack trace:
[   19.985142]  __free_pages_ok+0x432/0xbc0
[   19.985533]  qlist_free_all+0x56/0xc0
[   19.985907]  quarantine_reduce+0x149/0x170
[   19.986315]  __kasan_kmalloc.constprop.0+0x9e/0xd0
[   19.986791]  kmem_cache_alloc+0xe4/0x230
[   19.987182]  prepare_creds+0x24/0x440
[   19.987548]  do_faccessat+0x80/0x590
[   19.987906]  do_syscall_64+0xe7/0xae0
[   19.988276]  entry_SYSCALL_64_after_hwframe+0x49/0xbe
[   19.988775]
[   19.988930] Memory state around the buggy address:
[   19.989402]  ffff888112862780: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[   19.990111]  ffff888112862800: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb
[   19.990822] >ffff888112862880: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[   19.991529]                                               ^
[   19.992081]  ffff888112862900: fb fb fb fb fc fc fc fc fc fc fc fc fc fc fc fc
[   19.992796]  ffff888112862980: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc

Fixes: 5a781ccbd19e ("tc: Add support for configuring the taprio scheduler")
Reported-by: Michael Schmidt <michael.schmidt@eti.uni-siegen.de>
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Acked-by: Andre Guedes <andre.guedes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_taprio.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 660fc45ee40f..437e333a4a33 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -564,8 +564,10 @@ static struct sk_buff *taprio_dequeue_soft(struct Qdisc *sch)
 		prio = skb->priority;
 		tc = netdev_get_prio_tc_map(dev, prio);
 
-		if (!(gate_mask & BIT(tc)))
+		if (!(gate_mask & BIT(tc))) {
+			skb = NULL;
 			continue;
+		}
 
 		len = qdisc_pkt_len(skb);
 		guard = ktime_add_ns(taprio_get_time(q),
@@ -575,13 +577,17 @@ static struct sk_buff *taprio_dequeue_soft(struct Qdisc *sch)
 		 * guard band ...
 		 */
 		if (gate_mask != TAPRIO_ALL_GATES_OPEN &&
-		    ktime_after(guard, entry->close_time))
+		    ktime_after(guard, entry->close_time)) {
+			skb = NULL;
 			continue;
+		}
 
 		/* ... and no budget. */
 		if (gate_mask != TAPRIO_ALL_GATES_OPEN &&
-		    atomic_sub_return(len, &entry->budget) < 0)
+		    atomic_sub_return(len, &entry->budget) < 0) {
+			skb = NULL;
 			continue;
+		}
 
 		skb = child->ops->dequeue(child);
 		if (unlikely(!skb))
-- 
2.20.1


From 4d75f90a83efd53b971a35b900ac97443bbf0e3b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 4 Mar 2020 09:32:16 -0800
Subject: [PATCH 26/52] bonding/alb: make sure arp header is pulled before
 accessing it

Similar to commit 38f88c454042 ("bonding/alb: properly access headers
in bond_alb_xmit()"), we need to make sure arp header was pulled
in skb->head before blindly accessing it in rlb_arp_xmit().

Remove arp_pkt() private helper, since it is more readable/obvious
to have the following construct back to back :

	if (!pskb_network_may_pull(skb, sizeof(*arp)))
		return NULL;
	arp = (struct arp_pkt *)skb_network_header(skb);

syzbot reported :

BUG: KMSAN: uninit-value in bond_slave_has_mac_rx include/net/bonding.h:704 [inline]
BUG: KMSAN: uninit-value in rlb_arp_xmit drivers/net/bonding/bond_alb.c:662 [inline]
BUG: KMSAN: uninit-value in bond_alb_xmit+0x575/0x25e0 drivers/net/bonding/bond_alb.c:1477
CPU: 0 PID: 12743 Comm: syz-executor.4 Not tainted 5.6.0-rc2-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c9/0x220 lib/dump_stack.c:118
 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:118
 __msan_warning+0x58/0xa0 mm/kmsan/kmsan_instr.c:215
 bond_slave_has_mac_rx include/net/bonding.h:704 [inline]
 rlb_arp_xmit drivers/net/bonding/bond_alb.c:662 [inline]
 bond_alb_xmit+0x575/0x25e0 drivers/net/bonding/bond_alb.c:1477
 __bond_start_xmit drivers/net/bonding/bond_main.c:4257 [inline]
 bond_start_xmit+0x85d/0x2f70 drivers/net/bonding/bond_main.c:4282
 __netdev_start_xmit include/linux/netdevice.h:4524 [inline]
 netdev_start_xmit include/linux/netdevice.h:4538 [inline]
 xmit_one net/core/dev.c:3470 [inline]
 dev_hard_start_xmit+0x531/0xab0 net/core/dev.c:3486
 __dev_queue_xmit+0x37de/0x4220 net/core/dev.c:4063
 dev_queue_xmit+0x4b/0x60 net/core/dev.c:4096
 packet_snd net/packet/af_packet.c:2967 [inline]
 packet_sendmsg+0x8347/0x93b0 net/packet/af_packet.c:2992
 sock_sendmsg_nosec net/socket.c:652 [inline]
 sock_sendmsg net/socket.c:672 [inline]
 __sys_sendto+0xc1b/0xc50 net/socket.c:1998
 __do_sys_sendto net/socket.c:2010 [inline]
 __se_sys_sendto+0x107/0x130 net/socket.c:2006
 __x64_sys_sendto+0x6e/0x90 net/socket.c:2006
 do_syscall_64+0xb8/0x160 arch/x86/entry/common.c:296
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x45c479
Code: ad b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007fc77ffbbc78 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 00007fc77ffbc6d4 RCX: 000000000045c479
RDX: 000000000000000e RSI: 00000000200004c0 RDI: 0000000000000003
RBP: 000000000076bf20 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff
R13: 0000000000000a04 R14: 00000000004cc7b0 R15: 000000000076bf2c

Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:144 [inline]
 kmsan_internal_poison_shadow+0x66/0xd0 mm/kmsan/kmsan.c:127
 kmsan_slab_alloc+0x8a/0xe0 mm/kmsan/kmsan_hooks.c:82
 slab_alloc_node mm/slub.c:2793 [inline]
 __kmalloc_node_track_caller+0xb40/0x1200 mm/slub.c:4401
 __kmalloc_reserve net/core/skbuff.c:142 [inline]
 __alloc_skb+0x2fd/0xac0 net/core/skbuff.c:210
 alloc_skb include/linux/skbuff.h:1051 [inline]
 alloc_skb_with_frags+0x18c/0xa70 net/core/skbuff.c:5766
 sock_alloc_send_pskb+0xada/0xc60 net/core/sock.c:2242
 packet_alloc_skb net/packet/af_packet.c:2815 [inline]
 packet_snd net/packet/af_packet.c:2910 [inline]
 packet_sendmsg+0x66a0/0x93b0 net/packet/af_packet.c:2992
 sock_sendmsg_nosec net/socket.c:652 [inline]
 sock_sendmsg net/socket.c:672 [inline]
 __sys_sendto+0xc1b/0xc50 net/socket.c:1998
 __do_sys_sendto net/socket.c:2010 [inline]
 __se_sys_sendto+0x107/0x130 net/socket.c:2006
 __x64_sys_sendto+0x6e/0x90 net/socket.c:2006
 do_syscall_64+0xb8/0x160 arch/x86/entry/common.c:296
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Cc: Veaceslav Falico <vfalico@gmail.com>
Cc: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_alb.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 1cc2cd894f87..c81698550e5a 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -50,11 +50,6 @@ struct arp_pkt {
 };
 #pragma pack()
 
-static inline struct arp_pkt *arp_pkt(const struct sk_buff *skb)
-{
-	return (struct arp_pkt *)skb_network_header(skb);
-}
-
 /* Forward declaration */
 static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[],
 				      bool strict_match);
@@ -553,10 +548,11 @@ static void rlb_req_update_subnet_clients(struct bonding *bond, __be32 src_ip)
 	spin_unlock(&bond->mode_lock);
 }
 
-static struct slave *rlb_choose_channel(struct sk_buff *skb, struct bonding *bond)
+static struct slave *rlb_choose_channel(struct sk_buff *skb,
+					struct bonding *bond,
+					const struct arp_pkt *arp)
 {
 	struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond));
-	struct arp_pkt *arp = arp_pkt(skb);
 	struct slave *assigned_slave, *curr_active_slave;
 	struct rlb_client_info *client_info;
 	u32 hash_index = 0;
@@ -653,8 +649,12 @@ static struct slave *rlb_choose_channel(struct sk_buff *skb, struct bonding *bon
  */
 static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond)
 {
-	struct arp_pkt *arp = arp_pkt(skb);
 	struct slave *tx_slave = NULL;
+	struct arp_pkt *arp;
+
+	if (!pskb_network_may_pull(skb, sizeof(*arp)))
+		return NULL;
+	arp = (struct arp_pkt *)skb_network_header(skb);
 
 	/* Don't modify or load balance ARPs that do not originate locally
 	 * (e.g.,arrive via a bridge).
@@ -664,7 +664,7 @@ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond)
 
 	if (arp->op_code == htons(ARPOP_REPLY)) {
 		/* the arp must be sent on the selected rx channel */
-		tx_slave = rlb_choose_channel(skb, bond);
+		tx_slave = rlb_choose_channel(skb, bond, arp);
 		if (tx_slave)
 			bond_hw_addr_copy(arp->mac_src, tx_slave->dev->dev_addr,
 					  tx_slave->dev->addr_len);
@@ -676,7 +676,7 @@ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond)
 		 * When the arp reply is received the entry will be updated
 		 * with the correct unicast address of the client.
 		 */
-		tx_slave = rlb_choose_channel(skb, bond);
+		tx_slave = rlb_choose_channel(skb, bond, arp);
 
 		/* The ARP reply packets must be delayed so that
 		 * they can cancel out the influence of the ARP request.
-- 
2.20.1


From 707e9dea1fd75b4ee73e2a134ac781f384b84398 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Sun, 1 Mar 2020 22:07:17 -0500
Subject: [PATCH 27/52] bnxt_en: reinitialize IRQs when MTU is modified

[ Upstream commit a9b952d267e59a3b405e644930f46d252cea7122 ]

MTU changes may affect the number of IRQs so we must call
bnxt_close_nic()/bnxt_open_nic() with the irq_re_init parameter
set to true.  The reason is that a larger MTU may require
aggregation rings not needed with smaller MTU.  We may not be
able to allocate the required number of aggregation rings and
so we reduce the number of channels which will change the number
of IRQs.  Without this patch, it may crash eventually in
pci_disable_msix() when the IRQs are not properly unwound.

Fixes: c0c050c58d84 ("bnxt_en: New Broadcom ethernet driver.")
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 374e11a91790..57c88e157f86 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -10891,13 +10891,13 @@ static int bnxt_change_mtu(struct net_device *dev, int new_mtu)
 	struct bnxt *bp = netdev_priv(dev);
 
 	if (netif_running(dev))
-		bnxt_close_nic(bp, false, false);
+		bnxt_close_nic(bp, true, false);
 
 	dev->mtu = new_mtu;
 	bnxt_set_ring_params(bp);
 
 	if (netif_running(dev))
-		return bnxt_open_nic(bp, false, false);
+		return bnxt_open_nic(bp, true, false);
 
 	return 0;
 }
-- 
2.20.1


From 13abda9c8c964cc7ae8a5be122b2abdc536eafa2 Mon Sep 17 00:00:00 2001
From: Edwin Peer <edwin.peer@broadcom.com>
Date: Sun, 1 Mar 2020 22:07:18 -0500
Subject: [PATCH 28/52] bnxt_en: fix error handling when flashing from file

[ Upstream commit 22630e28f9c2b55abd217869cc0696def89f2284 ]

After bnxt_hwrm_do_send_message() was updated to return standard error
codes in a recent commit, a regression in bnxt_flash_package_from_file()
was introduced.  The return value does not properly reflect all
possible firmware errors when calling firmware to flash the package.

Fix it by consolidating all errors in one local variable rc instead
of having 2 variables for different errors.

Fixes: d4f1420d3656 ("bnxt_en: Convert error code in firmware message response to standard code.")
Signed-off-by: Edwin Peer <edwin.peer@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 24 +++++++++----------
 1 file changed, 11 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index ece70f61c89a..cfa647d5b44d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -2005,8 +2005,8 @@ static int bnxt_flash_package_from_file(struct net_device *dev,
 	struct hwrm_nvm_install_update_output *resp = bp->hwrm_cmd_resp_addr;
 	struct hwrm_nvm_install_update_input install = {0};
 	const struct firmware *fw;
-	int rc, hwrm_err = 0;
 	u32 item_len;
+	int rc = 0;
 	u16 index;
 
 	bnxt_hwrm_fw_set_time(bp);
@@ -2050,15 +2050,14 @@ static int bnxt_flash_package_from_file(struct net_device *dev,
 			memcpy(kmem, fw->data, fw->size);
 			modify.host_src_addr = cpu_to_le64(dma_handle);
 
-			hwrm_err = hwrm_send_message(bp, &modify,
-						     sizeof(modify),
-						     FLASH_PACKAGE_TIMEOUT);
+			rc = hwrm_send_message(bp, &modify, sizeof(modify),
+					       FLASH_PACKAGE_TIMEOUT);
 			dma_free_coherent(&bp->pdev->dev, fw->size, kmem,
 					  dma_handle);
 		}
 	}
 	release_firmware(fw);
-	if (rc || hwrm_err)
+	if (rc)
 		goto err_exit;
 
 	if ((install_type & 0xffff) == 0)
@@ -2067,20 +2066,19 @@ static int bnxt_flash_package_from_file(struct net_device *dev,
 	install.install_type = cpu_to_le32(install_type);
 
 	mutex_lock(&bp->hwrm_cmd_lock);
-	hwrm_err = _hwrm_send_message(bp, &install, sizeof(install),
-				      INSTALL_PACKAGE_TIMEOUT);
-	if (hwrm_err) {
+	rc = _hwrm_send_message(bp, &install, sizeof(install),
+				INSTALL_PACKAGE_TIMEOUT);
+	if (rc) {
 		u8 error_code = ((struct hwrm_err_output *)resp)->cmd_err;
 
 		if (resp->error_code && error_code ==
 		    NVM_INSTALL_UPDATE_CMD_ERR_CODE_FRAG_ERR) {
 			install.flags |= cpu_to_le16(
 			       NVM_INSTALL_UPDATE_REQ_FLAGS_ALLOWED_TO_DEFRAG);
-			hwrm_err = _hwrm_send_message(bp, &install,
-						      sizeof(install),
-						      INSTALL_PACKAGE_TIMEOUT);
+			rc = _hwrm_send_message(bp, &install, sizeof(install),
+						INSTALL_PACKAGE_TIMEOUT);
 		}
-		if (hwrm_err)
+		if (rc)
 			goto flash_pkg_exit;
 	}
 
@@ -2092,7 +2090,7 @@ static int bnxt_flash_package_from_file(struct net_device *dev,
 flash_pkg_exit:
 	mutex_unlock(&bp->hwrm_cmd_lock);
 err_exit:
-	if (hwrm_err == -EACCES)
+	if (rc == -EACCES)
 		bnxt_print_admin_err(bp);
 	return rc;
 }
-- 
2.20.1


From a9fb326ec2936d2aa72faa5cd18b16823692606c Mon Sep 17 00:00:00 2001
From: Shakeel Butt <shakeelb@google.com>
Date: Mon, 9 Mar 2020 22:16:05 -0700
Subject: [PATCH 29/52] cgroup: memcg: net: do not associate sock with
 unrelated cgroup

[ Upstream commit e876ecc67db80dfdb8e237f71e5b43bb88ae549c ]

We are testing network memory accounting in our setup and noticed
inconsistent network memory usage and often unrelated cgroups network
usage correlates with testing workload. On further inspection, it
seems like mem_cgroup_sk_alloc() and cgroup_sk_alloc() are broken in
irq context specially for cgroup v1.

mem_cgroup_sk_alloc() and cgroup_sk_alloc() can be called in irq context
and kind of assumes that this can only happen from sk_clone_lock()
and the source sock object has already associated cgroup. However in
cgroup v1, where network memory accounting is opt-in, the source sock
can be unassociated with any cgroup and the new cloned sock can get
associated with unrelated interrupted cgroup.

Cgroup v2 can also suffer if the source sock object was created by
process in the root cgroup or if sk_alloc() is called in irq context.
The fix is to just do nothing in interrupt.

WARNING: Please note that about half of the TCP sockets are allocated
from the IRQ context, so, memory used by such sockets will not be
accouted by the memcg.

The stack trace of mem_cgroup_sk_alloc() from IRQ-context:

CPU: 70 PID: 12720 Comm: ssh Tainted:  5.6.0-smp-DEV #1
Hardware name: ...
Call Trace:
 <IRQ>
 dump_stack+0x57/0x75
 mem_cgroup_sk_alloc+0xe9/0xf0
 sk_clone_lock+0x2a7/0x420
 inet_csk_clone_lock+0x1b/0x110
 tcp_create_openreq_child+0x23/0x3b0
 tcp_v6_syn_recv_sock+0x88/0x730
 tcp_check_req+0x429/0x560
 tcp_v6_rcv+0x72d/0xa40
 ip6_protocol_deliver_rcu+0xc9/0x400
 ip6_input+0x44/0xd0
 ? ip6_protocol_deliver_rcu+0x400/0x400
 ip6_rcv_finish+0x71/0x80
 ipv6_rcv+0x5b/0xe0
 ? ip6_sublist_rcv+0x2e0/0x2e0
 process_backlog+0x108/0x1e0
 net_rx_action+0x26b/0x460
 __do_softirq+0x104/0x2a6
 do_softirq_own_stack+0x2a/0x40
 </IRQ>
 do_softirq.part.19+0x40/0x50
 __local_bh_enable_ip+0x51/0x60
 ip6_finish_output2+0x23d/0x520
 ? ip6table_mangle_hook+0x55/0x160
 __ip6_finish_output+0xa1/0x100
 ip6_finish_output+0x30/0xd0
 ip6_output+0x73/0x120
 ? __ip6_finish_output+0x100/0x100
 ip6_xmit+0x2e3/0x600
 ? ipv6_anycast_cleanup+0x50/0x50
 ? inet6_csk_route_socket+0x136/0x1e0
 ? skb_free_head+0x1e/0x30
 inet6_csk_xmit+0x95/0xf0
 __tcp_transmit_skb+0x5b4/0xb20
 __tcp_send_ack.part.60+0xa3/0x110
 tcp_send_ack+0x1d/0x20
 tcp_rcv_state_process+0xe64/0xe80
 ? tcp_v6_connect+0x5d1/0x5f0
 tcp_v6_do_rcv+0x1b1/0x3f0
 ? tcp_v6_do_rcv+0x1b1/0x3f0
 __release_sock+0x7f/0xd0
 release_sock+0x30/0xa0
 __inet_stream_connect+0x1c3/0x3b0
 ? prepare_to_wait+0xb0/0xb0
 inet_stream_connect+0x3b/0x60
 __sys_connect+0x101/0x120
 ? __sys_getsockopt+0x11b/0x140
 __x64_sys_connect+0x1a/0x20
 do_syscall_64+0x51/0x200
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

The stack trace of mem_cgroup_sk_alloc() from IRQ-context:
Fixes: 2d7580738345 ("mm: memcontrol: consolidate cgroup socket tracking")
Fixes: d979a39d7242 ("cgroup: duplicate cgroup reference when cloning sockets")
Signed-off-by: Shakeel Butt <shakeelb@google.com>
Reviewed-by: Roman Gushchin <guro@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/cgroup/cgroup.c | 4 ++++
 mm/memcontrol.c        | 4 ++++
 2 files changed, 8 insertions(+)

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 595c52d59f31..974631f68d40 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -6381,6 +6381,10 @@ void cgroup_sk_alloc(struct sock_cgroup_data *skcd)
 		return;
 	}
 
+	/* Don't associate the sock with unrelated interrupted task's cgroup. */
+	if (in_interrupt())
+		return;
+
 	rcu_read_lock();
 
 	while (true) {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ae9044bc9f80..549b08224455 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -6806,6 +6806,10 @@ void mem_cgroup_sk_alloc(struct sock *sk)
 		return;
 	}
 
+	/* Do not associate the sock with unrelated interrupted task's memcg. */
+	if (in_interrupt())
+		return;
+
 	rcu_read_lock();
 	memcg = mem_cgroup_from_task(current);
 	if (memcg == root_mem_cgroup)
-- 
2.20.1


From 22e6948b42da84285b64c5a42f8adc736e937c5b Mon Sep 17 00:00:00 2001
From: Shakeel Butt <shakeelb@google.com>
Date: Mon, 9 Mar 2020 22:16:06 -0700
Subject: [PATCH 30/52] net: memcg: late association of sock to memcg

[ Upstream commit d752a4986532cb6305dfd5290a614cde8072769d ]

If a TCP socket is allocated in IRQ context or cloned from unassociated
(i.e. not associated to a memcg) in IRQ context then it will remain
unassociated for its whole life. Almost half of the TCPs created on the
system are created in IRQ context, so, memory used by such sockets will
not be accounted by the memcg.

This issue is more widespread in cgroup v1 where network memory
accounting is opt-in but it can happen in cgroup v2 if the source socket
for the cloning was created in root memcg.

To fix the issue, just do the association of the sockets at the accept()
time in the process context and then force charge the memory buffer
already used and reserved by the socket.

Signed-off-by: Shakeel Butt <shakeelb@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 mm/memcontrol.c                 | 14 --------------
 net/core/sock.c                 |  5 ++++-
 net/ipv4/inet_connection_sock.c | 20 ++++++++++++++++++++
 3 files changed, 24 insertions(+), 15 deletions(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 549b08224455..23c99c6778d3 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -6792,20 +6792,6 @@ void mem_cgroup_sk_alloc(struct sock *sk)
 	if (!mem_cgroup_sockets_enabled)
 		return;
 
-	/*
-	 * Socket cloning can throw us here with sk_memcg already
-	 * filled. It won't however, necessarily happen from
-	 * process context. So the test for root memcg given
-	 * the current task's memcg won't help us in this case.
-	 *
-	 * Respecting the original socket's memcg is a better
-	 * decision in this case.
-	 */
-	if (sk->sk_memcg) {
-		css_get(&sk->sk_memcg->css);
-		return;
-	}
-
 	/* Do not associate the sock with unrelated interrupted task's memcg. */
 	if (in_interrupt())
 		return;
diff --git a/net/core/sock.c b/net/core/sock.c
index b4d1112174c1..0adf7a9e5a90 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1832,7 +1832,10 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		atomic_set(&newsk->sk_zckey, 0);
 
 		sock_reset_flag(newsk, SOCK_DONE);
-		mem_cgroup_sk_alloc(newsk);
+
+		/* sk->sk_memcg will be populated at accept() time */
+		newsk->sk_memcg = NULL;
+
 		cgroup_sk_alloc(&newsk->sk_cgrp_data);
 
 		rcu_read_lock();
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index ac05e273bc66..7ae7ece3997d 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -482,6 +482,26 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern)
 		}
 		spin_unlock_bh(&queue->fastopenq.lock);
 	}
+
+	if (mem_cgroup_sockets_enabled) {
+		int amt;
+
+		/* atomically get the memory usage, set and charge the
+		 * sk->sk_memcg.
+		 */
+		lock_sock(newsk);
+
+		/* The sk has not been accepted yet, no need to look at
+		 * sk->sk_wmem_queued.
+		 */
+		amt = sk_mem_pages(newsk->sk_forward_alloc +
+				   atomic_read(&sk->sk_rmem_alloc));
+		mem_cgroup_sk_alloc(newsk);
+		if (newsk->sk_memcg && amt)
+			mem_cgroup_charge_skmem(newsk->sk_memcg, amt);
+
+		release_sock(newsk);
+	}
 out:
 	release_sock(sk);
 	if (req)
-- 
2.20.1


From 133b2019c9518541d5bb98581e68f4e475936af8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 11 Mar 2020 11:44:26 -0700
Subject: [PATCH 31/52] net: memcg: fix lockdep splat in inet_csk_accept()

Locking newsk while still holding the listener lock triggered
a lockdep splat [1]

We can simply move the memcg code after we release the listener lock,
as this can also help if multiple threads are sharing a common listener.

Also fix a typo while reading socket sk_rmem_alloc.

[1]
WARNING: possible recursive locking detected
5.6.0-rc3-syzkaller #0 Not tainted
--------------------------------------------
syz-executor598/9524 is trying to acquire lock:
ffff88808b5b8b90 (sk_lock-AF_INET6){+.+.}, at: lock_sock include/net/sock.h:1541 [inline]
ffff88808b5b8b90 (sk_lock-AF_INET6){+.+.}, at: inet_csk_accept+0x69f/0xd30 net/ipv4/inet_connection_sock.c:492

but task is already holding lock:
ffff88808b5b9590 (sk_lock-AF_INET6){+.+.}, at: lock_sock include/net/sock.h:1541 [inline]
ffff88808b5b9590 (sk_lock-AF_INET6){+.+.}, at: inet_csk_accept+0x8d/0xd30 net/ipv4/inet_connection_sock.c:445

other info that might help us debug this:
 Possible unsafe locking scenario:

       CPU0
       ----
  lock(sk_lock-AF_INET6);
  lock(sk_lock-AF_INET6);

 *** DEADLOCK ***

 May be due to missing lock nesting notation

1 lock held by syz-executor598/9524:
 #0: ffff88808b5b9590 (sk_lock-AF_INET6){+.+.}, at: lock_sock include/net/sock.h:1541 [inline]
 #0: ffff88808b5b9590 (sk_lock-AF_INET6){+.+.}, at: inet_csk_accept+0x8d/0xd30 net/ipv4/inet_connection_sock.c:445

stack backtrace:
CPU: 0 PID: 9524 Comm: syz-executor598 Not tainted 5.6.0-rc3-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x188/0x20d lib/dump_stack.c:118
 print_deadlock_bug kernel/locking/lockdep.c:2370 [inline]
 check_deadlock kernel/locking/lockdep.c:2411 [inline]
 validate_chain kernel/locking/lockdep.c:2954 [inline]
 __lock_acquire.cold+0x114/0x288 kernel/locking/lockdep.c:3954
 lock_acquire+0x197/0x420 kernel/locking/lockdep.c:4484
 lock_sock_nested+0xc5/0x110 net/core/sock.c:2947
 lock_sock include/net/sock.h:1541 [inline]
 inet_csk_accept+0x69f/0xd30 net/ipv4/inet_connection_sock.c:492
 inet_accept+0xe9/0x7c0 net/ipv4/af_inet.c:734
 __sys_accept4_file+0x3ac/0x5b0 net/socket.c:1758
 __sys_accept4+0x53/0x90 net/socket.c:1809
 __do_sys_accept4 net/socket.c:1821 [inline]
 __se_sys_accept4 net/socket.c:1818 [inline]
 __x64_sys_accept4+0x93/0xf0 net/socket.c:1818
 do_syscall_64+0xf6/0x790 arch/x86/entry/common.c:294
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x4445c9
Code: e8 0c 0d 03 00 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 eb 08 fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007ffc35b37608 EFLAGS: 00000246 ORIG_RAX: 0000000000000120
RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00000000004445c9
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000003
RBP: 0000000000000000 R08: 0000000000306777 R09: 0000000000306777
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 00000000004053d0 R14: 0000000000000000 R15: 0000000000000000

Fixes: d752a4986532 ("net: memcg: late association of sock to memcg")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Shakeel Butt <shakeelb@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/inet_connection_sock.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 7ae7ece3997d..b0010c710802 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -483,27 +483,27 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern)
 		spin_unlock_bh(&queue->fastopenq.lock);
 	}
 
-	if (mem_cgroup_sockets_enabled) {
+out:
+	release_sock(sk);
+	if (newsk && mem_cgroup_sockets_enabled) {
 		int amt;
 
 		/* atomically get the memory usage, set and charge the
-		 * sk->sk_memcg.
+		 * newsk->sk_memcg.
 		 */
 		lock_sock(newsk);
 
-		/* The sk has not been accepted yet, no need to look at
-		 * sk->sk_wmem_queued.
+		/* The socket has not been accepted yet, no need to look at
+		 * newsk->sk_wmem_queued.
 		 */
 		amt = sk_mem_pages(newsk->sk_forward_alloc +
-				   atomic_read(&sk->sk_rmem_alloc));
+				   atomic_read(&newsk->sk_rmem_alloc));
 		mem_cgroup_sk_alloc(newsk);
 		if (newsk->sk_memcg && amt)
 			mem_cgroup_charge_skmem(newsk->sk_memcg, amt);
 
 		release_sock(newsk);
 	}
-out:
-	release_sock(sk);
 	if (req)
 		reqsk_put(req);
 	return newsk;
-- 
2.20.1


From 04caa24cf436b4bbe07c80e55987070bc1eb757d Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 2 Mar 2020 21:05:11 -0800
Subject: [PATCH 32/52] devlink: validate length of param values

[ Upstream commit 8750939b6ad86abc3f53ec8a9683a1cded4a5654 ]

DEVLINK_ATTR_PARAM_VALUE_DATA may have different types
so it's not checked by the normal netlink policy. Make
sure the attribute length is what we expect.

Fixes: e3b7ca18ad7b ("devlink: Add param set command")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/devlink.c | 31 +++++++++++++++++++------------
 1 file changed, 19 insertions(+), 12 deletions(-)

diff --git a/net/core/devlink.c b/net/core/devlink.c
index 61bc67047f56..c46726c5dcd6 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -3222,34 +3222,41 @@ devlink_param_value_get_from_info(const struct devlink_param *param,
 				  struct genl_info *info,
 				  union devlink_param_value *value)
 {
+	struct nlattr *param_data;
 	int len;
 
-	if (param->type != DEVLINK_PARAM_TYPE_BOOL &&
-	    !info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA])
+	param_data = info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA];
+
+	if (param->type != DEVLINK_PARAM_TYPE_BOOL && !param_data)
 		return -EINVAL;
 
 	switch (param->type) {
 	case DEVLINK_PARAM_TYPE_U8:
-		value->vu8 = nla_get_u8(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]);
+		if (nla_len(param_data) != sizeof(u8))
+			return -EINVAL;
+		value->vu8 = nla_get_u8(param_data);
 		break;
 	case DEVLINK_PARAM_TYPE_U16:
-		value->vu16 = nla_get_u16(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]);
+		if (nla_len(param_data) != sizeof(u16))
+			return -EINVAL;
+		value->vu16 = nla_get_u16(param_data);
 		break;
 	case DEVLINK_PARAM_TYPE_U32:
-		value->vu32 = nla_get_u32(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]);
+		if (nla_len(param_data) != sizeof(u32))
+			return -EINVAL;
+		value->vu32 = nla_get_u32(param_data);
 		break;
 	case DEVLINK_PARAM_TYPE_STRING:
-		len = strnlen(nla_data(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]),
-			      nla_len(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]));
-		if (len == nla_len(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]) ||
+		len = strnlen(nla_data(param_data), nla_len(param_data));
+		if (len == nla_len(param_data) ||
 		    len >= __DEVLINK_PARAM_MAX_STRING_VALUE)
 			return -EINVAL;
-		strcpy(value->vstr,
-		       nla_data(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]));
+		strcpy(value->vstr, nla_data(param_data));
 		break;
 	case DEVLINK_PARAM_TYPE_BOOL:
-		value->vbool = info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA] ?
-			       true : false;
+		if (param_data && nla_len(param_data))
+			return -EINVAL;
+		value->vbool = nla_get_flag(param_data);
 		break;
 	}
 	return 0;
-- 
2.20.1


From 460cf9cb02963bce5b8c134d9c4f58d2bc821189 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 2 Mar 2020 21:05:12 -0800
Subject: [PATCH 33/52] devlink: validate length of region addr/len

[ Upstream commit ff3b63b8c299b73ac599b120653b47e275407656 ]

DEVLINK_ATTR_REGION_CHUNK_ADDR and DEVLINK_ATTR_REGION_CHUNK_LEN
lack entries in the netlink policy. Corresponding nla_get_u64()s
may read beyond the end of the message.

Fixes: 4e54795a27f5 ("devlink: Add support for region snapshot read command")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/devlink.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/core/devlink.c b/net/core/devlink.c
index c46726c5dcd6..4c25f1aa2d37 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -5804,6 +5804,8 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_PARAM_VALUE_CMODE] = { .type = NLA_U8 },
 	[DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING },
 	[DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .type = NLA_U32 },
+	[DEVLINK_ATTR_REGION_CHUNK_ADDR] = { .type = NLA_U64 },
+	[DEVLINK_ATTR_REGION_CHUNK_LEN] = { .type = NLA_U64 },
 	[DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING },
 	[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] = { .type = NLA_U64 },
 	[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = { .type = NLA_U8 },
-- 
2.20.1


From 4ee581a252d86f3ad10d549b34d46b05ea55eec3 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 2 Mar 2020 21:05:13 -0800
Subject: [PATCH 34/52] fib: add missing attribute validation for tun_id

[ Upstream commit 4c16d64ea04056f1b1b324ab6916019f6a064114 ]

Add missing netlink policy entry for FRA_TUN_ID.

Fixes: e7030878fc84 ("fib: Add fib rule match on tunnel id")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/fib_rules.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index 20dcadd8eed9..7fed3193f81d 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -108,6 +108,7 @@ struct fib_rule_notifier_info {
 	[FRA_OIFNAME]	= { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, \
 	[FRA_PRIORITY]	= { .type = NLA_U32 }, \
 	[FRA_FWMARK]	= { .type = NLA_U32 }, \
+	[FRA_TUN_ID]	= { .type = NLA_U64 }, \
 	[FRA_FWMASK]	= { .type = NLA_U32 }, \
 	[FRA_TABLE]     = { .type = NLA_U32 }, \
 	[FRA_SUPPRESS_PREFIXLEN] = { .type = NLA_U32 }, \
-- 
2.20.1


From 918817ed7c65a7022de6b19314aba2d8f9c17ef2 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 2 Mar 2020 21:05:14 -0800
Subject: [PATCH 35/52] nl802154: add missing attribute validation

[ Upstream commit 9322cd7c4af2ccc7fe7c5f01adb53f4f77949e92 ]

Add missing attribute validation for several u8 types.

Fixes: 2c21d11518b6 ("net: add NL802154 interface for configuration of 802.15.4 devices")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Stefan Schmidt <stefan@datenfreihafen.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ieee802154/nl_policy.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/ieee802154/nl_policy.c b/net/ieee802154/nl_policy.c
index 2c7a38d76a3a..824e7e84014c 100644
--- a/net/ieee802154/nl_policy.c
+++ b/net/ieee802154/nl_policy.c
@@ -21,6 +21,11 @@ const struct nla_policy ieee802154_policy[IEEE802154_ATTR_MAX + 1] = {
 	[IEEE802154_ATTR_HW_ADDR] = { .type = NLA_HW_ADDR, },
 	[IEEE802154_ATTR_PAN_ID] = { .type = NLA_U16, },
 	[IEEE802154_ATTR_CHANNEL] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_BCN_ORD] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_SF_ORD] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_PAN_COORD] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_BAT_EXT] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_COORD_REALIGN] = { .type = NLA_U8, },
 	[IEEE802154_ATTR_PAGE] = { .type = NLA_U8, },
 	[IEEE802154_ATTR_COORD_SHORT_ADDR] = { .type = NLA_U16, },
 	[IEEE802154_ATTR_COORD_HW_ADDR] = { .type = NLA_HW_ADDR, },
-- 
2.20.1


From b02e5466b23730fa313674a09a2cf6a0ff1406e5 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 2 Mar 2020 21:05:15 -0800
Subject: [PATCH 36/52] nl802154: add missing attribute validation for dev_type

[ Upstream commit b60673c4c418bef7550d02faf53c34fbfeb366bf ]

Add missing attribute type validation for IEEE802154_ATTR_DEV_TYPE
to the netlink policy.

Fixes: 90c049b2c6ae ("ieee802154: interface type to be added")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Stefan Schmidt <stefan@datenfreihafen.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ieee802154/nl_policy.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ieee802154/nl_policy.c b/net/ieee802154/nl_policy.c
index 824e7e84014c..0672b2f01586 100644
--- a/net/ieee802154/nl_policy.c
+++ b/net/ieee802154/nl_policy.c
@@ -27,6 +27,7 @@ const struct nla_policy ieee802154_policy[IEEE802154_ATTR_MAX + 1] = {
 	[IEEE802154_ATTR_BAT_EXT] = { .type = NLA_U8, },
 	[IEEE802154_ATTR_COORD_REALIGN] = { .type = NLA_U8, },
 	[IEEE802154_ATTR_PAGE] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_DEV_TYPE] = { .type = NLA_U8, },
 	[IEEE802154_ATTR_COORD_SHORT_ADDR] = { .type = NLA_U16, },
 	[IEEE802154_ATTR_COORD_HW_ADDR] = { .type = NLA_HW_ADDR, },
 	[IEEE802154_ATTR_COORD_PAN_ID] = { .type = NLA_U16, },
-- 
2.20.1


From ff0c08b38d0dc3b0cffcf8fedb490ad6e3c52f47 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 2 Mar 2020 21:05:16 -0800
Subject: [PATCH 37/52] can: add missing attribute validation for termination

[ Upstream commit ab02ad660586b94f5d08912a3952b939cf4c4430 ]

Add missing attribute validation for IFLA_CAN_TERMINATION
to the netlink policy.

Fixes: 12a6075cabc0 ("can: dev: add CAN interface termination API")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/can/dev.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index 1c88c361938c..3a33fb503400 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -884,6 +884,7 @@ static const struct nla_policy can_policy[IFLA_CAN_MAX + 1] = {
 				= { .len = sizeof(struct can_bittiming) },
 	[IFLA_CAN_DATA_BITTIMING_CONST]
 				= { .len = sizeof(struct can_bittiming_const) },
+	[IFLA_CAN_TERMINATION]	= { .type = NLA_U16 },
 };
 
 static int can_validate(struct nlattr *tb[], struct nlattr *data[],
-- 
2.20.1


From 045eaa3c60594a88e0bde525a33a7bc4793af3ba Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 2 Mar 2020 21:05:17 -0800
Subject: [PATCH 38/52] macsec: add missing attribute validation for port

[ Upstream commit 31d9a1c524964bac77b7f9d0a1ac140dc6b57461 ]

Add missing attribute validation for IFLA_MACSEC_PORT
to the netlink policy.

Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macsec.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 3221c3b4efb1..6497a5c45220 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -2983,6 +2983,7 @@ static const struct device_type macsec_type = {
 
 static const struct nla_policy macsec_rtnl_policy[IFLA_MACSEC_MAX + 1] = {
 	[IFLA_MACSEC_SCI] = { .type = NLA_U64 },
+	[IFLA_MACSEC_PORT] = { .type = NLA_U16 },
 	[IFLA_MACSEC_ICV_LEN] = { .type = NLA_U8 },
 	[IFLA_MACSEC_CIPHER_SUITE] = { .type = NLA_U64 },
 	[IFLA_MACSEC_WINDOW] = { .type = NLA_U32 },
-- 
2.20.1


From fec5e4a08807241aee8367c2cd0140b84989ef51 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 2 Mar 2020 21:05:19 -0800
Subject: [PATCH 39/52] net: fq: add missing attribute validation for orphan
 mask

[ Upstream commit 7e6dc03eeb023e18427a373522f1d247b916a641 ]

Add missing attribute validation for TCA_FQ_ORPHAN_MASK
to the netlink policy.

Fixes: 06eb395fa985 ("pkt_sched: fq: better control of DDOS traffic")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_fq.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 712ad248d6a7..f757ea90aba6 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -745,6 +745,7 @@ static const struct nla_policy fq_policy[TCA_FQ_MAX + 1] = {
 	[TCA_FQ_FLOW_MAX_RATE]		= { .type = NLA_U32 },
 	[TCA_FQ_BUCKETS_LOG]		= { .type = NLA_U32 },
 	[TCA_FQ_FLOW_REFILL_DELAY]	= { .type = NLA_U32 },
+	[TCA_FQ_ORPHAN_MASK]		= { .type = NLA_U32 },
 	[TCA_FQ_LOW_RATE_THRESHOLD]	= { .type = NLA_U32 },
 	[TCA_FQ_CE_THRESHOLD]		= { .type = NLA_U32 },
 };
-- 
2.20.1


From b0988898d23232a89efb1f4d20dca6e858f13511 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 2 Mar 2020 21:05:20 -0800
Subject: [PATCH 40/52] net: taprio: add missing attribute validation for
 txtime delay

[ Upstream commit e13aaa0643da10006ec35715954e7f92a62899a5 ]

Add missing attribute validation for TCA_TAPRIO_ATTR_TXTIME_DELAY
to the netlink policy.

Fixes: 4cfd5779bd6e ("taprio: Add support for txtime-assist mode")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_taprio.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 437e333a4a33..b1eb12d33b9a 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -774,6 +774,7 @@ static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = {
 	[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME]           = { .type = NLA_S64 },
 	[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION] = { .type = NLA_S64 },
 	[TCA_TAPRIO_ATTR_FLAGS]                      = { .type = NLA_U32 },
+	[TCA_TAPRIO_ATTR_TXTIME_DELAY]		     = { .type = NLA_U32 },
 };
 
 static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry,
-- 
2.20.1


From f1ce21a8c35a5fe664d8270bcb78d1857b35a4a9 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 2 Mar 2020 21:05:21 -0800
Subject: [PATCH 41/52] team: add missing attribute validation for port ifindex

[ Upstream commit dd25cb272ccce4db67dc8509278229099e4f5e99 ]

Add missing attribute validation for TEAM_ATTR_OPTION_PORT_IFINDEX
to the netlink policy.

Fixes: 80f7c6683fe0 ("team: add support for per-port options")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index ca70a1d840eb..44dd26a62a6d 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -2240,6 +2240,7 @@ team_nl_option_policy[TEAM_ATTR_OPTION_MAX + 1] = {
 	[TEAM_ATTR_OPTION_CHANGED]		= { .type = NLA_FLAG },
 	[TEAM_ATTR_OPTION_TYPE]			= { .type = NLA_U8 },
 	[TEAM_ATTR_OPTION_DATA]			= { .type = NLA_BINARY },
+	[TEAM_ATTR_OPTION_PORT_IFINDEX]		= { .type = NLA_U32 },
 };
 
 static int team_nl_cmd_noop(struct sk_buff *skb, struct genl_info *info)
-- 
2.20.1


From 61924ee746ee178e3337ea78565a6827306d126e Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 2 Mar 2020 21:05:22 -0800
Subject: [PATCH 42/52] team: add missing attribute validation for array index

[ Upstream commit 669fcd7795900cd1880237cbbb57a7db66cb9ac8 ]

Add missing attribute validation for TEAM_ATTR_OPTION_ARRAY_INDEX
to the netlink policy.

Fixes: b13033262d24 ("team: introduce array options")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 44dd26a62a6d..4004f98e50d9 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -2241,6 +2241,7 @@ team_nl_option_policy[TEAM_ATTR_OPTION_MAX + 1] = {
 	[TEAM_ATTR_OPTION_TYPE]			= { .type = NLA_U8 },
 	[TEAM_ATTR_OPTION_DATA]			= { .type = NLA_BINARY },
 	[TEAM_ATTR_OPTION_PORT_IFINDEX]		= { .type = NLA_U32 },
+	[TEAM_ATTR_OPTION_ARRAY_INDEX]		= { .type = NLA_U32 },
 };
 
 static int team_nl_cmd_noop(struct sk_buff *skb, struct genl_info *info)
-- 
2.20.1


From b62aca15a1a7e4e5bfcb0cace0ed9a5ba673890f Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 2 Mar 2020 21:05:23 -0800
Subject: [PATCH 43/52] tipc: add missing attribute validation for MTU property

[ Upstream commit 213320a67962ff6e7b83b704d55cbebc341426db ]

Add missing attribute validation for TIPC_NLA_PROP_MTU
to the netlink policy.

Fixes: 901271e0403a ("tipc: implement configuration of UDP media MTU")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/netlink.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index d6165ad384c0..e9bbf4a00881 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -111,6 +111,7 @@ const struct nla_policy tipc_nl_prop_policy[TIPC_NLA_PROP_MAX + 1] = {
 	[TIPC_NLA_PROP_PRIO]		= { .type = NLA_U32 },
 	[TIPC_NLA_PROP_TOL]		= { .type = NLA_U32 },
 	[TIPC_NLA_PROP_WIN]		= { .type = NLA_U32 },
+	[TIPC_NLA_PROP_MTU]		= { .type = NLA_U32 },
 	[TIPC_NLA_PROP_BROADCAST]	= { .type = NLA_U32 },
 	[TIPC_NLA_PROP_BROADCAST_RATIO]	= { .type = NLA_U32 }
 };
-- 
2.20.1


From 9f080825327d8fdd135d54cbb71ab1efa9ad397b Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 2 Mar 2020 21:05:24 -0800
Subject: [PATCH 44/52] nfc: add missing attribute validation for SE API

[ Upstream commit 361d23e41ca6e504033f7e66a03b95788377caae ]

Add missing attribute validation for NFC_ATTR_SE_INDEX
to the netlink policy.

Fixes: 5ce3f32b5264 ("NFC: netlink: SE API implementation")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/nfc/netlink.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index afde0d763039..ab4acfa3c2e4 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -43,6 +43,7 @@ static const struct nla_policy nfc_genl_policy[NFC_ATTR_MAX + 1] = {
 	[NFC_ATTR_LLC_SDP] = { .type = NLA_NESTED },
 	[NFC_ATTR_FIRMWARE_NAME] = { .type = NLA_STRING,
 				     .len = NFC_FIRMWARE_NAME_MAXSIZE },
+	[NFC_ATTR_SE_INDEX] = { .type = NLA_U32 },
 	[NFC_ATTR_SE_APDU] = { .type = NLA_BINARY },
 	[NFC_ATTR_VENDOR_DATA] = { .type = NLA_BINARY },
 
-- 
2.20.1


From 5238a214e10da1eb3bf4479ae53ce56c0d458ec9 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 2 Mar 2020 21:05:25 -0800
Subject: [PATCH 45/52] nfc: add missing attribute validation for deactivate
 target

[ Upstream commit 88e706d5168b07df4792dbc3d1bc37b83e4bd74d ]

Add missing attribute validation for NFC_ATTR_TARGET_INDEX
to the netlink policy.

Fixes: 4d63adfe12dd ("NFC: Add NFC_CMD_DEACTIVATE_TARGET support")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/nfc/netlink.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index ab4acfa3c2e4..e97ff3777472 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -32,6 +32,7 @@ static const struct nla_policy nfc_genl_policy[NFC_ATTR_MAX + 1] = {
 	[NFC_ATTR_DEVICE_NAME] = { .type = NLA_STRING,
 				.len = NFC_DEVICE_NAME_MAXSIZE },
 	[NFC_ATTR_PROTOCOLS] = { .type = NLA_U32 },
+	[NFC_ATTR_TARGET_INDEX] = { .type = NLA_U32 },
 	[NFC_ATTR_COMM_MODE] = { .type = NLA_U8 },
 	[NFC_ATTR_RF_MODE] = { .type = NLA_U8 },
 	[NFC_ATTR_DEVICE_POWERED] = { .type = NLA_U8 },
-- 
2.20.1


From 78cca5b06cddd8f0f16c81ad6b1dc60a1ff6f7ce Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 2 Mar 2020 21:05:26 -0800
Subject: [PATCH 46/52] nfc: add missing attribute validation for vendor
 subcommand

[ Upstream commit 6ba3da446551f2150fadbf8c7788edcb977683d3 ]

Add missing attribute validation for vendor subcommand attributes
to the netlink policy.

Fixes: 9e58095f9660 ("NFC: netlink: Implement vendor command support")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/nfc/netlink.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index e97ff3777472..1b261375722e 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -46,6 +46,8 @@ static const struct nla_policy nfc_genl_policy[NFC_ATTR_MAX + 1] = {
 				     .len = NFC_FIRMWARE_NAME_MAXSIZE },
 	[NFC_ATTR_SE_INDEX] = { .type = NLA_U32 },
 	[NFC_ATTR_SE_APDU] = { .type = NLA_BINARY },
+	[NFC_ATTR_VENDOR_ID] = { .type = NLA_U32 },
+	[NFC_ATTR_VENDOR_SUBCMD] = { .type = NLA_U32 },
 	[NFC_ATTR_VENDOR_DATA] = { .type = NLA_BINARY },
 
 };
-- 
2.20.1


From 7577da942f72a925b9916c6b7b272230158a43df Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 1 Mar 2020 21:36:09 +0100
Subject: [PATCH 47/52] net: phy: avoid clearing PHY interrupts twice in irq
 handler

[ Upstream commit 249bc9744e165abe74ae326f43e9d70bad54c3b7 ]

On all PHY drivers that implement did_interrupt() reading the interrupt
status bits clears them. This means we may loose an interrupt that
is triggered between calling did_interrupt() and phy_clear_interrupt().
As part of the fix make it a requirement that did_interrupt() clears
the interrupt.

The Fixes tag refers to the first commit where the patch applies
cleanly.

Fixes: 49644e68f472 ("net: phy: add callback for custom interrupt handler to struct phy_driver")
Reported-by: Michael Walle <michael@walle.cc>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 3 ++-
 include/linux/phy.h   | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 105d389b58e7..ea890d802ffe 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -761,7 +761,8 @@ static irqreturn_t phy_interrupt(int irq, void *phy_dat)
 		phy_trigger_machine(phydev);
 	}
 
-	if (phy_clear_interrupt(phydev))
+	/* did_interrupt() may have cleared the interrupt already */
+	if (!phydev->drv->did_interrupt && phy_clear_interrupt(phydev))
 		goto phy_err;
 	return IRQ_HANDLED;
 
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 3d5d53313e6c..bf87c59a98bb 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -524,6 +524,7 @@ struct phy_driver {
 	/*
 	 * Checks if the PHY generated an interrupt.
 	 * For multi-PHY devices with shared PHY interrupt pin
+	 * Set interrupt bits have to be cleared.
 	 */
 	int (*did_interrupt)(struct phy_device *phydev);
 
-- 
2.20.1


From 25676f9d1f3664d587075c47f886612f0faaa7a3 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 12 Mar 2020 22:25:20 +0100
Subject: [PATCH 48/52] net: phy: fix MDIO bus PM PHY resuming

[ Upstream commit 611d779af7cad2b87487ff58e4931a90c20b113c ]

So far we have the unfortunate situation that mdio_bus_phy_may_suspend()
is called in suspend AND resume path, assuming that function result is
the same. After the original change this is no longer the case,
resulting in broken resume as reported by Geert.

To fix this call mdio_bus_phy_may_suspend() in the suspend path only,
and let the phy_device store the info whether it was suspended by
MDIO bus PM.

Fixes: 503ba7c69610 ("net: phy: Avoid multiple suspends")
Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Tested-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 6 +++++-
 include/linux/phy.h          | 2 ++
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 2bf0fda209a8..4300b31678b3 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -284,6 +284,8 @@ static int mdio_bus_phy_suspend(struct device *dev)
 	if (!mdio_bus_phy_may_suspend(phydev))
 		return 0;
 
+	phydev->suspended_by_mdio_bus = 1;
+
 	return phy_suspend(phydev);
 }
 
@@ -292,9 +294,11 @@ static int mdio_bus_phy_resume(struct device *dev)
 	struct phy_device *phydev = to_phy_device(dev);
 	int ret;
 
-	if (!mdio_bus_phy_may_suspend(phydev))
+	if (!phydev->suspended_by_mdio_bus)
 		goto no_resume;
 
+	phydev->suspended_by_mdio_bus = 0;
+
 	ret = phy_resume(phydev);
 	if (ret < 0)
 		return ret;
diff --git a/include/linux/phy.h b/include/linux/phy.h
index bf87c59a98bb..80750783b5b0 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -336,6 +336,7 @@ struct phy_c45_device_ids {
  * is_gigabit_capable: Set to true if PHY supports 1000Mbps
  * has_fixups: Set to true if this phy has fixups/quirks.
  * suspended: Set to true if this phy has been suspended successfully.
+ * suspended_by_mdio_bus: Set to true if this phy was suspended by MDIO bus.
  * sysfs_links: Internal boolean tracking sysfs symbolic links setup/removal.
  * loopback_enabled: Set true if this phy has been loopbacked successfully.
  * state: state of the PHY for management purposes
@@ -372,6 +373,7 @@ struct phy_device {
 	unsigned is_gigabit_capable:1;
 	unsigned has_fixups:1;
 	unsigned suspended:1;
+	unsigned suspended_by_mdio_bus:1;
 	unsigned sysfs_links:1;
 	unsigned loopback_enabled:1;
 
-- 
2.20.1


From 86ef50e59923715493b1d0f5a853f7ea23ef17e4 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Tue, 3 Mar 2020 14:37:34 +0800
Subject: [PATCH 49/52] net/ipv6: need update peer route when modify metric

[ Upstream commit 617940123e0140521f3080d2befc2bf55bcda094 ]

When we modify the route metric, the peer address's route need also
be updated. Before the fix:

+ ip addr add dev dummy1 2001:db8::1 peer 2001:db8::2 metric 60
+ ip -6 route show dev dummy1
2001:db8::1 proto kernel metric 60 pref medium
2001:db8::2 proto kernel metric 60 pref medium
+ ip addr change dev dummy1 2001:db8::1 peer 2001:db8::2 metric 61
+ ip -6 route show dev dummy1
2001:db8::1 proto kernel metric 61 pref medium
2001:db8::2 proto kernel metric 60 pref medium

After the fix:
+ ip addr change dev dummy1 2001:db8::1 peer 2001:db8::2 metric 61
+ ip -6 route show dev dummy1
2001:db8::1 proto kernel metric 61 pref medium
2001:db8::2 proto kernel metric 61 pref medium

Fixes: 8308f3ff1753 ("net/ipv6: Add support for specifying metric of connected routes")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 68d713ba9136..0999738ed4a5 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -4590,12 +4590,14 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
 }
 
 static int modify_prefix_route(struct inet6_ifaddr *ifp,
-			       unsigned long expires, u32 flags)
+			       unsigned long expires, u32 flags,
+			       bool modify_peer)
 {
 	struct fib6_info *f6i;
 	u32 prio;
 
-	f6i = addrconf_get_prefix_route(&ifp->addr, ifp->prefix_len,
+	f6i = addrconf_get_prefix_route(modify_peer ? &ifp->peer_addr : &ifp->addr,
+					ifp->prefix_len,
 					ifp->idev->dev, 0, RTF_DEFAULT, true);
 	if (!f6i)
 		return -ENOENT;
@@ -4606,7 +4608,8 @@ static int modify_prefix_route(struct inet6_ifaddr *ifp,
 		ip6_del_rt(dev_net(ifp->idev->dev), f6i);
 
 		/* add new one */
-		addrconf_prefix_route(&ifp->addr, ifp->prefix_len,
+		addrconf_prefix_route(modify_peer ? &ifp->peer_addr : &ifp->addr,
+				      ifp->prefix_len,
 				      ifp->rt_priority, ifp->idev->dev,
 				      expires, flags, GFP_KERNEL);
 	} else {
@@ -4682,7 +4685,7 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg)
 		int rc = -ENOENT;
 
 		if (had_prefixroute)
-			rc = modify_prefix_route(ifp, expires, flags);
+			rc = modify_prefix_route(ifp, expires, flags, false);
 
 		/* prefix route could have been deleted; if so restore it */
 		if (rc == -ENOENT) {
@@ -4690,6 +4693,15 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg)
 					      ifp->rt_priority, ifp->idev->dev,
 					      expires, flags, GFP_KERNEL);
 		}
+
+		if (had_prefixroute && !ipv6_addr_any(&ifp->peer_addr))
+			rc = modify_prefix_route(ifp, expires, flags, true);
+
+		if (rc == -ENOENT && !ipv6_addr_any(&ifp->peer_addr)) {
+			addrconf_prefix_route(&ifp->peer_addr, ifp->prefix_len,
+					      ifp->rt_priority, ifp->idev->dev,
+					      expires, flags, GFP_KERNEL);
+		}
 	} else if (had_prefixroute) {
 		enum cleanup_prefix_rt_t action;
 		unsigned long rt_expires;
-- 
2.20.1


From d0d0489e880dbc2f2b657ac795401118a598deb3 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Tue, 3 Mar 2020 14:37:35 +0800
Subject: [PATCH 50/52] net/ipv6: remove the old peer route if change it to a
 new one

[ Upstream commit d0098e4c6b83e502cc1cd96d67ca86bc79a6c559 ]

When we modify the peer route and changed it to a new one, we should
remove the old route first. Before the fix:

+ ip addr add dev dummy1 2001:db8::1 peer 2001:db8::2
+ ip -6 route show dev dummy1
2001:db8::1 proto kernel metric 256 pref medium
2001:db8::2 proto kernel metric 256 pref medium
+ ip addr change dev dummy1 2001:db8::1 peer 2001:db8::3
+ ip -6 route show dev dummy1
2001:db8::1 proto kernel metric 256 pref medium
2001:db8::2 proto kernel metric 256 pref medium

After the fix:
+ ip addr change dev dummy1 2001:db8::1 peer 2001:db8::3
+ ip -6 route show dev dummy1
2001:db8::1 proto kernel metric 256 pref medium
2001:db8::3 proto kernel metric 256 pref medium

This patch depend on the previous patch "net/ipv6: need update peer route
when modify metric" to update new peer route after delete old one.

Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 21 +++++++++++++++++----
 1 file changed, 17 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 0999738ed4a5..d02ccd749a60 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1226,11 +1226,13 @@ check_cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long *expires)
 }
 
 static void
-cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires, bool del_rt)
+cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires,
+		     bool del_rt, bool del_peer)
 {
 	struct fib6_info *f6i;
 
-	f6i = addrconf_get_prefix_route(&ifp->addr, ifp->prefix_len,
+	f6i = addrconf_get_prefix_route(del_peer ? &ifp->peer_addr : &ifp->addr,
+					ifp->prefix_len,
 					ifp->idev->dev, 0, RTF_DEFAULT, true);
 	if (f6i) {
 		if (del_rt)
@@ -1293,7 +1295,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
 
 	if (action != CLEANUP_PREFIX_RT_NOP) {
 		cleanup_prefix_route(ifp, expires,
-			action == CLEANUP_PREFIX_RT_DEL);
+			action == CLEANUP_PREFIX_RT_DEL, false);
 	}
 
 	/* clean up prefsrc entries */
@@ -4631,6 +4633,7 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg)
 	unsigned long timeout;
 	bool was_managetempaddr;
 	bool had_prefixroute;
+	bool new_peer = false;
 
 	ASSERT_RTNL();
 
@@ -4662,6 +4665,13 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg)
 		cfg->preferred_lft = timeout;
 	}
 
+	if (cfg->peer_pfx &&
+	    memcmp(&ifp->peer_addr, cfg->peer_pfx, sizeof(struct in6_addr))) {
+		if (!ipv6_addr_any(&ifp->peer_addr))
+			cleanup_prefix_route(ifp, expires, true, true);
+		new_peer = true;
+	}
+
 	spin_lock_bh(&ifp->lock);
 	was_managetempaddr = ifp->flags & IFA_F_MANAGETEMPADDR;
 	had_prefixroute = ifp->flags & IFA_F_PERMANENT &&
@@ -4677,6 +4687,9 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg)
 	if (cfg->rt_priority && cfg->rt_priority != ifp->rt_priority)
 		ifp->rt_priority = cfg->rt_priority;
 
+	if (new_peer)
+		ifp->peer_addr = *cfg->peer_pfx;
+
 	spin_unlock_bh(&ifp->lock);
 	if (!(ifp->flags&IFA_F_TENTATIVE))
 		ipv6_ifa_notify(0, ifp);
@@ -4712,7 +4725,7 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg)
 
 		if (action != CLEANUP_PREFIX_RT_NOP) {
 			cleanup_prefix_route(ifp, rt_expires,
-				action == CLEANUP_PREFIX_RT_DEL);
+				action == CLEANUP_PREFIX_RT_DEL, false);
 		}
 	}
 
-- 
2.20.1


From 0ccbc82a0b65bd78568eb2dab71b7ecd38e7adec Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Tue, 3 Mar 2020 14:37:36 +0800
Subject: [PATCH 51/52] selftests/net/fib_tests: update addr_metric_test for
 peer route testing

[ Upstream commit 0d29169a708bf730ede287248e429d579f432d1d ]

This patch update {ipv4, ipv6}_addr_metric_test with
1. Set metric of address with peer route and see if the route added
correctly.
2. Modify metric and peer address for peer route and see if the route
changed correctly.

Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/fib_tests.sh | 34 +++++++++++++++++++++---
 1 file changed, 31 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 474638ef2697..09854f8a0b57 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -1041,6 +1041,27 @@ ipv6_addr_metric_test()
 	fi
 	log_test $rc 0 "Prefix route with metric on link up"
 
+	# verify peer metric added correctly
+	set -e
+	run_cmd "$IP -6 addr flush dev dummy2"
+	run_cmd "$IP -6 addr add dev dummy2 2001:db8:104::1 peer 2001:db8:104::2 metric 260"
+	set +e
+
+	check_route6 "2001:db8:104::1 dev dummy2 proto kernel metric 260"
+	log_test $? 0 "Set metric with peer route on local side"
+	log_test $? 0 "User specified metric on local address"
+	check_route6 "2001:db8:104::2 dev dummy2 proto kernel metric 260"
+	log_test $? 0 "Set metric with peer route on peer side"
+
+	set -e
+	run_cmd "$IP -6 addr change dev dummy2 2001:db8:104::1 peer 2001:db8:104::3 metric 261"
+	set +e
+
+	check_route6 "2001:db8:104::1 dev dummy2 proto kernel metric 261"
+	log_test $? 0 "Modify metric and peer address on local side"
+	check_route6 "2001:db8:104::3 dev dummy2 proto kernel metric 261"
+	log_test $? 0 "Modify metric and peer address on peer side"
+
 	$IP li del dummy1
 	$IP li del dummy2
 	cleanup
@@ -1457,13 +1478,20 @@ ipv4_addr_metric_test()
 
 	run_cmd "$IP addr flush dev dummy2"
 	run_cmd "$IP addr add dev dummy2 172.16.104.1/32 peer 172.16.104.2 metric 260"
-	run_cmd "$IP addr change dev dummy2 172.16.104.1/32 peer 172.16.104.2 metric 261"
 	rc=$?
 	if [ $rc -eq 0 ]; then
-		check_route "172.16.104.2 dev dummy2 proto kernel scope link src 172.16.104.1 metric 261"
+		check_route "172.16.104.2 dev dummy2 proto kernel scope link src 172.16.104.1 metric 260"
+		rc=$?
+	fi
+	log_test $rc 0 "Set metric of address with peer route"
+
+	run_cmd "$IP addr change dev dummy2 172.16.104.1/32 peer 172.16.104.3 metric 261"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		check_route "172.16.104.3 dev dummy2 proto kernel scope link src 172.16.104.1 metric 261"
 		rc=$?
 	fi
-	log_test $rc 0 "Modify metric of address with peer route"
+	log_test $rc 0 "Modify metric and peer address for peer route"
 
 	$IP li del dummy1
 	$IP li del dummy2
-- 
2.20.1


From 4f42e544d707c688d108014b79259b9072618ef6 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Wed, 11 Mar 2020 16:24:24 +0100
Subject: [PATCH 52/52] net: dsa: Don't instantiate phylink for CPU/DSA ports
 unless needed

[ Upstream commit a20f997010c4ec76eaa55b8cc047d76dcac69f70 ]

By default, DSA drivers should configure CPU and DSA ports to their
maximum speed. In many configurations this is sufficient to make the
link work.

In some cases it is necessary to configure the link to run slower,
e.g. because of limitations of the SoC it is connected to. Or back to
back PHYs are used and the PHY needs to be driven in order to
establish link. In this case, phylink is used.

Only instantiate phylink if it is required. If there is no PHY, or no
fixed link properties, phylink can upset a link which works in the
default configuration.

Fixes: 0e27921816ad ("net: dsa: Use PHYLINK for the CPU/DSA ports")
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/port.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/net/dsa/port.c b/net/dsa/port.c
index 2a1aa1a50254..fa023af69bc4 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -649,9 +649,14 @@ static int dsa_port_phylink_register(struct dsa_port *dp)
 int dsa_port_link_register_of(struct dsa_port *dp)
 {
 	struct dsa_switch *ds = dp->ds;
+	struct device_node *phy_np;
 
-	if (!ds->ops->adjust_link)
-		return dsa_port_phylink_register(dp);
+	if (!ds->ops->adjust_link) {
+		phy_np = of_parse_phandle(dp->dn, "phy-handle", 0);
+		if (of_phy_is_fixed_link(dp->dn) || phy_np)
+			return dsa_port_phylink_register(dp);
+		return 0;
+	}
 
 	dev_warn(ds->dev,
 		 "Using legacy PHYLIB callbacks. Please migrate to PHYLINK!\n");
@@ -666,11 +671,12 @@ void dsa_port_link_unregister_of(struct dsa_port *dp)
 {
 	struct dsa_switch *ds = dp->ds;
 
-	if (!ds->ops->adjust_link) {
+	if (!ds->ops->adjust_link && dp->pl) {
 		rtnl_lock();
 		phylink_disconnect_phy(dp->pl);
 		rtnl_unlock();
 		phylink_destroy(dp->pl);
+		dp->pl = NULL;
 		return;
 	}
 
-- 
2.20.1


[-- Attachment #3: net_55.mbox --]
[-- Type: Application/Octet-Stream, Size: 183194 bytes --]

From a015a48d31e4670a98a566d7d07b959029727c7a Mon Sep 17 00:00:00 2001
From: Dmitry Yakunin <zeil@yandex-team.ru>
Date: Thu, 5 Mar 2020 17:45:57 +0300
Subject: [PATCH 01/66] cgroup, netclassid: periodically release file_lock on
 classid updating
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 018d26fcd12a75fb9b5fe233762aa3f2f0854b88 ]

In our production environment we have faced with problem that updating
classid in cgroup with heavy tasks cause long freeze of the file tables
in this tasks. By heavy tasks we understand tasks with many threads and
opened sockets (e.g. balancers). This freeze leads to an increase number
of client timeouts.

This patch implements following logic to fix this issue:
аfter iterating 1000 file descriptors file table lock will be released
thus providing a time gap for socket creation/deletion.

Now update is non atomic and socket may be skipped using calls:

dup2(oldfd, newfd);
close(oldfd);

But this case is not typical. Moreover before this patch skip is possible
too by hiding socket fd in unix socket buffer.

New sockets will be allocated with updated classid because cgroup state
is updated before start of the file descriptors iteration.

So in common cases this patch has no side effects.

Signed-off-by: Dmitry Yakunin <zeil@yandex-team.ru>
Reviewed-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/netclassid_cgroup.c | 47 ++++++++++++++++++++++++++++--------
 1 file changed, 37 insertions(+), 10 deletions(-)

diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c
index 0642f91c4038..b4c87fe31be2 100644
--- a/net/core/netclassid_cgroup.c
+++ b/net/core/netclassid_cgroup.c
@@ -53,30 +53,60 @@ static void cgrp_css_free(struct cgroup_subsys_state *css)
 	kfree(css_cls_state(css));
 }
 
+/*
+ * To avoid freezing of sockets creation for tasks with big number of threads
+ * and opened sockets lets release file_lock every 1000 iterated descriptors.
+ * New sockets will already have been created with new classid.
+ */
+
+struct update_classid_context {
+	u32 classid;
+	unsigned int batch;
+};
+
+#define UPDATE_CLASSID_BATCH 1000
+
 static int update_classid_sock(const void *v, struct file *file, unsigned n)
 {
 	int err;
+	struct update_classid_context *ctx = (void *)v;
 	struct socket *sock = sock_from_file(file, &err);
 
 	if (sock) {
 		spin_lock(&cgroup_sk_update_lock);
-		sock_cgroup_set_classid(&sock->sk->sk_cgrp_data,
-					(unsigned long)v);
+		sock_cgroup_set_classid(&sock->sk->sk_cgrp_data, ctx->classid);
 		spin_unlock(&cgroup_sk_update_lock);
 	}
+	if (--ctx->batch == 0) {
+		ctx->batch = UPDATE_CLASSID_BATCH;
+		return n + 1;
+	}
 	return 0;
 }
 
+static void update_classid_task(struct task_struct *p, u32 classid)
+{
+	struct update_classid_context ctx = {
+		.classid = classid,
+		.batch = UPDATE_CLASSID_BATCH
+	};
+	unsigned int fd = 0;
+
+	do {
+		task_lock(p);
+		fd = iterate_fd(p->files, fd, update_classid_sock, &ctx);
+		task_unlock(p);
+		cond_resched();
+	} while (fd);
+}
+
 static void cgrp_attach(struct cgroup_taskset *tset)
 {
 	struct cgroup_subsys_state *css;
 	struct task_struct *p;
 
 	cgroup_taskset_for_each(p, css, tset) {
-		task_lock(p);
-		iterate_fd(p->files, 0, update_classid_sock,
-			   (void *)(unsigned long)css_cls_state(css)->classid);
-		task_unlock(p);
+		update_classid_task(p, css_cls_state(css)->classid);
 	}
 }
 
@@ -98,10 +128,7 @@ static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft,
 
 	css_task_iter_start(css, 0, &it);
 	while ((p = css_task_iter_next(&it))) {
-		task_lock(p);
-		iterate_fd(p->files, 0, update_classid_sock,
-			   (void *)(unsigned long)cs->classid);
-		task_unlock(p);
+		update_classid_task(p, cs->classid);
 		cond_resched();
 	}
 	css_task_iter_end(&it);
-- 
2.20.1


From f1ece29412c418c13186bf5e3c3baa751d0be432 Mon Sep 17 00:00:00 2001
From: Vishal Kulkarni <vishal@chelsio.com>
Date: Mon, 2 Mar 2020 10:54:13 +0530
Subject: [PATCH 02/66] cxgb4: fix checks for max queues to allocate

[ Upstream commit 116ca924aea664141afa86a1425edc3fcda0d06f ]

Hardware can support more than 8 queues currently limited by
netif_get_num_default_rss_queues(). So, rework and fix checks for max
number of queues to allocate. The checks should be based on how many are
actually supported by hardware, OR the number of online cpus; whichever
is lower.

Fixes: 5952dde72307 ("cxgb4: set maximal number of default RSS queues")
Signed-off-by: Vishal Kulkarni <vishal@chelsio.com>"
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/chelsio/cxgb4/cxgb4_main.c   | 49 ++++++++++---------
 1 file changed, 27 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 0dedd3e9c31e..b11ba4565c20 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -5351,12 +5351,11 @@ static inline bool is_x_10g_port(const struct link_config *lc)
 static int cfg_queues(struct adapter *adap)
 {
 	u32 avail_qsets, avail_eth_qsets, avail_uld_qsets;
+	u32 i, n10g = 0, qidx = 0, n1g = 0;
+	u32 ncpus = num_online_cpus();
 	u32 niqflint, neq, num_ulds;
 	struct sge *s = &adap->sge;
-	u32 i, n10g = 0, qidx = 0;
-#ifndef CONFIG_CHELSIO_T4_DCB
-	int q10g = 0;
-#endif
+	u32 q10g = 0, q1g;
 
 	/* Reduce memory usage in kdump environment, disable all offload. */
 	if (is_kdump_kernel() || (is_uld(adap) && t4_uld_mem_alloc(adap))) {
@@ -5394,44 +5393,50 @@ static int cfg_queues(struct adapter *adap)
 		n10g += is_x_10g_port(&adap2pinfo(adap, i)->link_cfg);
 
 	avail_eth_qsets = min_t(u32, avail_qsets, MAX_ETH_QSETS);
+
+	/* We default to 1 queue per non-10G port and up to # of cores queues
+	 * per 10G port.
+	 */
+	if (n10g)
+		q10g = (avail_eth_qsets - (adap->params.nports - n10g)) / n10g;
+
+	n1g = adap->params.nports - n10g;
 #ifdef CONFIG_CHELSIO_T4_DCB
 	/* For Data Center Bridging support we need to be able to support up
 	 * to 8 Traffic Priorities; each of which will be assigned to its
 	 * own TX Queue in order to prevent Head-Of-Line Blocking.
 	 */
+	q1g = 8;
 	if (adap->params.nports * 8 > avail_eth_qsets) {
 		dev_err(adap->pdev_dev, "DCB avail_eth_qsets=%d < %d!\n",
 			avail_eth_qsets, adap->params.nports * 8);
 		return -ENOMEM;
 	}
 
-	for_each_port(adap, i) {
-		struct port_info *pi = adap2pinfo(adap, i);
+	if (adap->params.nports * ncpus < avail_eth_qsets)
+		q10g = max(8U, ncpus);
+	else
+		q10g = max(8U, q10g);
 
-		pi->first_qset = qidx;
-		pi->nqsets = is_kdump_kernel() ? 1 : 8;
-		qidx += pi->nqsets;
-	}
-#else /* !CONFIG_CHELSIO_T4_DCB */
-	/* We default to 1 queue per non-10G port and up to # of cores queues
-	 * per 10G port.
-	 */
-	if (n10g)
-		q10g = (avail_eth_qsets - (adap->params.nports - n10g)) / n10g;
-	if (q10g > netif_get_num_default_rss_queues())
-		q10g = netif_get_num_default_rss_queues();
+	while ((q10g * n10g) > (avail_eth_qsets - n1g * q1g))
+		q10g--;
 
-	if (is_kdump_kernel())
+#else /* !CONFIG_CHELSIO_T4_DCB */
+	q1g = 1;
+	q10g = min(q10g, ncpus);
+#endif /* !CONFIG_CHELSIO_T4_DCB */
+	if (is_kdump_kernel()) {
 		q10g = 1;
+		q1g = 1;
+	}
 
 	for_each_port(adap, i) {
 		struct port_info *pi = adap2pinfo(adap, i);
 
 		pi->first_qset = qidx;
-		pi->nqsets = is_x_10g_port(&pi->link_cfg) ? q10g : 1;
+		pi->nqsets = is_x_10g_port(&pi->link_cfg) ? q10g : q1g;
 		qidx += pi->nqsets;
 	}
-#endif /* !CONFIG_CHELSIO_T4_DCB */
 
 	s->ethqsets = qidx;
 	s->max_ethqsets = qidx;   /* MSI-X may lower it later */
@@ -5443,7 +5448,7 @@ static int cfg_queues(struct adapter *adap)
 		 * capped by the number of available cores.
 		 */
 		num_ulds = adap->num_uld + adap->num_ofld_uld;
-		i = min_t(u32, MAX_OFLD_QSETS, num_online_cpus());
+		i = min_t(u32, MAX_OFLD_QSETS, ncpus);
 		avail_uld_qsets = roundup(i, adap->params.nports);
 		if (avail_qsets < num_ulds * adap->params.nports) {
 			adap->params.offload = 0;
-- 
2.20.1


From 19235b95d00f84b425b40ce9fa86e0cfcad7c5d2 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 7 Mar 2020 22:05:14 -0800
Subject: [PATCH 03/66] gre: fix uninit-value in __iptunnel_pull_header

[ Upstream commit 17c25cafd4d3e74c83dce56b158843b19c40b414 ]

syzbot found an interesting case of the kernel reading
an uninit-value [1]

Problem is in the handling of ETH_P_WCCP in gre_parse_header()

We look at the byte following GRE options to eventually decide
if the options are four bytes longer.

Use skb_header_pointer() to not pull bytes if we found
that no more bytes were needed.

All callers of gre_parse_header() are properly using pskb_may_pull()
anyway before proceeding to next header.

[1]
BUG: KMSAN: uninit-value in pskb_may_pull include/linux/skbuff.h:2303 [inline]
BUG: KMSAN: uninit-value in __iptunnel_pull_header+0x30c/0xbd0 net/ipv4/ip_tunnel_core.c:94
CPU: 1 PID: 11784 Comm: syz-executor940 Not tainted 5.6.0-rc2-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c9/0x220 lib/dump_stack.c:118
 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:118
 __msan_warning+0x58/0xa0 mm/kmsan/kmsan_instr.c:215
 pskb_may_pull include/linux/skbuff.h:2303 [inline]
 __iptunnel_pull_header+0x30c/0xbd0 net/ipv4/ip_tunnel_core.c:94
 iptunnel_pull_header include/net/ip_tunnels.h:411 [inline]
 gre_rcv+0x15e/0x19c0 net/ipv6/ip6_gre.c:606
 ip6_protocol_deliver_rcu+0x181b/0x22c0 net/ipv6/ip6_input.c:432
 ip6_input_finish net/ipv6/ip6_input.c:473 [inline]
 NF_HOOK include/linux/netfilter.h:307 [inline]
 ip6_input net/ipv6/ip6_input.c:482 [inline]
 ip6_mc_input+0xdf2/0x1460 net/ipv6/ip6_input.c:576
 dst_input include/net/dst.h:442 [inline]
 ip6_rcv_finish net/ipv6/ip6_input.c:76 [inline]
 NF_HOOK include/linux/netfilter.h:307 [inline]
 ipv6_rcv+0x683/0x710 net/ipv6/ip6_input.c:306
 __netif_receive_skb_one_core net/core/dev.c:5198 [inline]
 __netif_receive_skb net/core/dev.c:5312 [inline]
 netif_receive_skb_internal net/core/dev.c:5402 [inline]
 netif_receive_skb+0x66b/0xf20 net/core/dev.c:5461
 tun_rx_batched include/linux/skbuff.h:4321 [inline]
 tun_get_user+0x6aef/0x6f60 drivers/net/tun.c:1997
 tun_chr_write_iter+0x1f2/0x360 drivers/net/tun.c:2026
 call_write_iter include/linux/fs.h:1901 [inline]
 new_sync_write fs/read_write.c:483 [inline]
 __vfs_write+0xa5a/0xca0 fs/read_write.c:496
 vfs_write+0x44a/0x8f0 fs/read_write.c:558
 ksys_write+0x267/0x450 fs/read_write.c:611
 __do_sys_write fs/read_write.c:623 [inline]
 __se_sys_write fs/read_write.c:620 [inline]
 __ia32_sys_write+0xdb/0x120 fs/read_write.c:620
 do_syscall_32_irqs_on arch/x86/entry/common.c:339 [inline]
 do_fast_syscall_32+0x3c7/0x6e0 arch/x86/entry/common.c:410
 entry_SYSENTER_compat+0x68/0x77 arch/x86/entry/entry_64_compat.S:139
RIP: 0023:0xf7f62d99
Code: 90 e8 0b 00 00 00 f3 90 0f ae e8 eb f9 8d 74 26 00 89 3c 24 c3 90 90 90 90 90 90 90 90 90 90 90 90 51 52 55 89 e5 0f 34 cd 80 <5d> 5a 59 c3 90 90 90 90 eb 0d 90 90 90 90 90 90 90 90 90 90 90 90
RSP: 002b:00000000fffedb2c EFLAGS: 00000217 ORIG_RAX: 0000000000000004
RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000020002580
RDX: 0000000000000fca RSI: 0000000000000036 RDI: 0000000000000004
RBP: 0000000000008914 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000

Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:144 [inline]
 kmsan_internal_poison_shadow+0x66/0xd0 mm/kmsan/kmsan.c:127
 kmsan_slab_alloc+0x8a/0xe0 mm/kmsan/kmsan_hooks.c:82
 slab_alloc_node mm/slub.c:2793 [inline]
 __kmalloc_node_track_caller+0xb40/0x1200 mm/slub.c:4401
 __kmalloc_reserve net/core/skbuff.c:142 [inline]
 __alloc_skb+0x2fd/0xac0 net/core/skbuff.c:210
 alloc_skb include/linux/skbuff.h:1051 [inline]
 alloc_skb_with_frags+0x18c/0xa70 net/core/skbuff.c:5766
 sock_alloc_send_pskb+0xada/0xc60 net/core/sock.c:2242
 tun_alloc_skb drivers/net/tun.c:1529 [inline]
 tun_get_user+0x10ae/0x6f60 drivers/net/tun.c:1843
 tun_chr_write_iter+0x1f2/0x360 drivers/net/tun.c:2026
 call_write_iter include/linux/fs.h:1901 [inline]
 new_sync_write fs/read_write.c:483 [inline]
 __vfs_write+0xa5a/0xca0 fs/read_write.c:496
 vfs_write+0x44a/0x8f0 fs/read_write.c:558
 ksys_write+0x267/0x450 fs/read_write.c:611
 __do_sys_write fs/read_write.c:623 [inline]
 __se_sys_write fs/read_write.c:620 [inline]
 __ia32_sys_write+0xdb/0x120 fs/read_write.c:620
 do_syscall_32_irqs_on arch/x86/entry/common.c:339 [inline]
 do_fast_syscall_32+0x3c7/0x6e0 arch/x86/entry/common.c:410
 entry_SYSENTER_compat+0x68/0x77 arch/x86/entry/entry_64_compat.S:139

Fixes: 95f5c64c3c13 ("gre: Move utility functions to common headers")
Fixes: c54419321455 ("GRE: Refactor GRE tunneling code.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/gre_demux.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c
index 5fd6e8ed02b5..66fdbfe5447c 100644
--- a/net/ipv4/gre_demux.c
+++ b/net/ipv4/gre_demux.c
@@ -56,7 +56,9 @@ int gre_del_protocol(const struct gre_protocol *proto, u8 version)
 }
 EXPORT_SYMBOL_GPL(gre_del_protocol);
 
-/* Fills in tpi and returns header length to be pulled. */
+/* Fills in tpi and returns header length to be pulled.
+ * Note that caller must use pskb_may_pull() before pulling GRE header.
+ */
 int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 		     bool *csum_err, __be16 proto, int nhs)
 {
@@ -110,8 +112,14 @@ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 	 * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header
 	 */
 	if (greh->flags == 0 && tpi->proto == htons(ETH_P_WCCP)) {
+		u8 _val, *val;
+
+		val = skb_header_pointer(skb, nhs + hdr_len,
+					 sizeof(_val), &_val);
+		if (!val)
+			return -EINVAL;
 		tpi->proto = proto;
-		if ((*(u8 *)options & 0xF0) != 0x40)
+		if ((*val & 0xF0) != 0x40)
 			hdr_len += 4;
 	}
 	tpi->hdr_len = hdr_len;
-- 
2.20.1


From 922fd97520dd2743e1aa8e3aa1a53ce6cbadb9f1 Mon Sep 17 00:00:00 2001
From: Dmitry Yakunin <zeil@yandex-team.ru>
Date: Thu, 5 Mar 2020 15:33:12 +0300
Subject: [PATCH 04/66] inet_diag: return classid for all socket types

[ Upstream commit 83f73c5bb7b9a9135173f0ba2b1aa00c06664ff9 ]

In commit 1ec17dbd90f8 ("inet_diag: fix reporting cgroup classid and
fallback to priority") croup classid reporting was fixed. But this works
only for TCP sockets because for other socket types icsk parameter can
be NULL and classid code path is skipped. This change moves classid
handling to inet_diag_msg_attrs_fill() function.

Also inet_diag_msg_attrs_size() helper was added and addends in
nlmsg_new() were reordered to save order from inet_sk_diag_fill().

Fixes: 1ec17dbd90f8 ("inet_diag: fix reporting cgroup classid and fallback to priority")
Signed-off-by: Dmitry Yakunin <zeil@yandex-team.ru>
Reviewed-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/inet_diag.h | 18 ++++++++++------
 net/ipv4/inet_diag.c      | 44 ++++++++++++++++++---------------------
 net/ipv4/raw_diag.c       |  5 +++--
 net/ipv4/udp_diag.c       |  5 +++--
 net/sctp/diag.c           |  8 ++-----
 5 files changed, 40 insertions(+), 40 deletions(-)

diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h
index 39faaaf843e1..c91cf2dee12a 100644
--- a/include/linux/inet_diag.h
+++ b/include/linux/inet_diag.h
@@ -2,15 +2,10 @@
 #ifndef _INET_DIAG_H_
 #define _INET_DIAG_H_ 1
 
+#include <net/netlink.h>
 #include <uapi/linux/inet_diag.h>
 
-struct net;
-struct sock;
 struct inet_hashinfo;
-struct nlattr;
-struct nlmsghdr;
-struct sk_buff;
-struct netlink_callback;
 
 struct inet_diag_handler {
 	void		(*dump)(struct sk_buff *skb,
@@ -62,6 +57,17 @@ int inet_diag_bc_sk(const struct nlattr *_bc, struct sock *sk);
 
 void inet_diag_msg_common_fill(struct inet_diag_msg *r, struct sock *sk);
 
+static inline size_t inet_diag_msg_attrs_size(void)
+{
+	return	  nla_total_size(1)  /* INET_DIAG_SHUTDOWN */
+		+ nla_total_size(1)  /* INET_DIAG_TOS */
+#if IS_ENABLED(CONFIG_IPV6)
+		+ nla_total_size(1)  /* INET_DIAG_TCLASS */
+		+ nla_total_size(1)  /* INET_DIAG_SKV6ONLY */
+#endif
+		+ nla_total_size(4)  /* INET_DIAG_MARK */
+		+ nla_total_size(4); /* INET_DIAG_CLASS_ID */
+}
 int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
 			     struct inet_diag_msg *r, int ext,
 			     struct user_namespace *user_ns, bool net_admin);
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index f11e997e517b..8c8377568a78 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -100,13 +100,9 @@ static size_t inet_sk_attr_size(struct sock *sk,
 		aux = handler->idiag_get_aux_size(sk, net_admin);
 
 	return	  nla_total_size(sizeof(struct tcp_info))
-		+ nla_total_size(1) /* INET_DIAG_SHUTDOWN */
-		+ nla_total_size(1) /* INET_DIAG_TOS */
-		+ nla_total_size(1) /* INET_DIAG_TCLASS */
-		+ nla_total_size(4) /* INET_DIAG_MARK */
-		+ nla_total_size(4) /* INET_DIAG_CLASS_ID */
-		+ nla_total_size(sizeof(struct inet_diag_meminfo))
 		+ nla_total_size(sizeof(struct inet_diag_msg))
+		+ inet_diag_msg_attrs_size()
+		+ nla_total_size(sizeof(struct inet_diag_meminfo))
 		+ nla_total_size(SK_MEMINFO_VARS * sizeof(u32))
 		+ nla_total_size(TCP_CA_NAME_MAX)
 		+ nla_total_size(sizeof(struct tcpvegas_info))
@@ -147,6 +143,24 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
 	if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, sk->sk_mark))
 		goto errout;
 
+	if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) ||
+	    ext & (1 << (INET_DIAG_TCLASS - 1))) {
+		u32 classid = 0;
+
+#ifdef CONFIG_SOCK_CGROUP_DATA
+		classid = sock_cgroup_classid(&sk->sk_cgrp_data);
+#endif
+		/* Fallback to socket priority if class id isn't set.
+		 * Classful qdiscs use it as direct reference to class.
+		 * For cgroup2 classid is always zero.
+		 */
+		if (!classid)
+			classid = sk->sk_priority;
+
+		if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid))
+			goto errout;
+	}
+
 	r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk));
 	r->idiag_inode = sock_i_ino(sk);
 
@@ -284,24 +298,6 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 			goto errout;
 	}
 
-	if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) ||
-	    ext & (1 << (INET_DIAG_TCLASS - 1))) {
-		u32 classid = 0;
-
-#ifdef CONFIG_SOCK_CGROUP_DATA
-		classid = sock_cgroup_classid(&sk->sk_cgrp_data);
-#endif
-		/* Fallback to socket priority if class id isn't set.
-		 * Classful qdiscs use it as direct reference to class.
-		 * For cgroup2 classid is always zero.
-		 */
-		if (!classid)
-			classid = sk->sk_priority;
-
-		if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid))
-			goto errout;
-	}
-
 out:
 	nlmsg_end(skb, nlh);
 	return 0;
diff --git a/net/ipv4/raw_diag.c b/net/ipv4/raw_diag.c
index e35736b99300..a93e7d1e1251 100644
--- a/net/ipv4/raw_diag.c
+++ b/net/ipv4/raw_diag.c
@@ -100,8 +100,9 @@ static int raw_diag_dump_one(struct sk_buff *in_skb,
 	if (IS_ERR(sk))
 		return PTR_ERR(sk);
 
-	rep = nlmsg_new(sizeof(struct inet_diag_msg) +
-			sizeof(struct inet_diag_meminfo) + 64,
+	rep = nlmsg_new(nla_total_size(sizeof(struct inet_diag_msg)) +
+			inet_diag_msg_attrs_size() +
+			nla_total_size(sizeof(struct inet_diag_meminfo)) + 64,
 			GFP_KERNEL);
 	if (!rep) {
 		sock_put(sk);
diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c
index 910555a4d9fe..dccd2286bc28 100644
--- a/net/ipv4/udp_diag.c
+++ b/net/ipv4/udp_diag.c
@@ -64,8 +64,9 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb,
 		goto out;
 
 	err = -ENOMEM;
-	rep = nlmsg_new(sizeof(struct inet_diag_msg) +
-			sizeof(struct inet_diag_meminfo) + 64,
+	rep = nlmsg_new(nla_total_size(sizeof(struct inet_diag_msg)) +
+			inet_diag_msg_attrs_size() +
+			nla_total_size(sizeof(struct inet_diag_meminfo)) + 64,
 			GFP_KERNEL);
 	if (!rep)
 		goto out;
diff --git a/net/sctp/diag.c b/net/sctp/diag.c
index 8a15146faaeb..1069d7af3672 100644
--- a/net/sctp/diag.c
+++ b/net/sctp/diag.c
@@ -237,15 +237,11 @@ static size_t inet_assoc_attr_size(struct sctp_association *asoc)
 		addrcnt++;
 
 	return	  nla_total_size(sizeof(struct sctp_info))
-		+ nla_total_size(1) /* INET_DIAG_SHUTDOWN */
-		+ nla_total_size(1) /* INET_DIAG_TOS */
-		+ nla_total_size(1) /* INET_DIAG_TCLASS */
-		+ nla_total_size(4) /* INET_DIAG_MARK */
-		+ nla_total_size(4) /* INET_DIAG_CLASS_ID */
 		+ nla_total_size(addrlen * asoc->peer.transport_count)
 		+ nla_total_size(addrlen * addrcnt)
-		+ nla_total_size(sizeof(struct inet_diag_meminfo))
 		+ nla_total_size(sizeof(struct inet_diag_msg))
+		+ inet_diag_msg_attrs_size()
+		+ nla_total_size(sizeof(struct inet_diag_meminfo))
 		+ 64;
 }
 
-- 
2.20.1


From 552f151b6ecf31c4f57e731bd7c022d153ffe623 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Tue, 10 Mar 2020 15:27:37 +0800
Subject: [PATCH 05/66] ipv6/addrconf: call ipv6_mc_up() for non-Ethernet
 interface
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 60380488e4e0b95e9e82aa68aa9705baa86de84c ]

Rafał found an issue that for non-Ethernet interface, if we down and up
frequently, the memory will be consumed slowly.

The reason is we add allnodes/allrouters addressed in multicast list in
ipv6_add_dev(). When link down, we call ipv6_mc_down(), store all multicast
addresses via mld_add_delrec(). But when link up, we don't call ipv6_mc_up()
for non-Ethernet interface to remove the addresses. This makes idev->mc_tomb
getting bigger and bigger. The call stack looks like:

addrconf_notify(NETDEV_REGISTER)
	ipv6_add_dev
		ipv6_dev_mc_inc(ff01::1)
		ipv6_dev_mc_inc(ff02::1)
		ipv6_dev_mc_inc(ff02::2)

addrconf_notify(NETDEV_UP)
	addrconf_dev_config
		/* Alas, we support only Ethernet autoconfiguration. */
		return;

addrconf_notify(NETDEV_DOWN)
	addrconf_ifdown
		ipv6_mc_down
			igmp6_group_dropped(ff02::2)
				mld_add_delrec(ff02::2)
			igmp6_group_dropped(ff02::1)
			igmp6_group_dropped(ff01::1)

After investigating, I can't found a rule to disable multicast on
non-Ethernet interface. In RFC2460, the link could be Ethernet, PPP, ATM,
tunnels, etc. In IPv4, it doesn't check the dev type when calls ip_mc_up()
in inetdev_event(). Even for IPv6, we don't check the dev type and call
ipv6_add_dev(), ipv6_dev_mc_inc() after register device.

So I think it's OK to fix this memory consumer by calling ipv6_mc_up() for
non-Ethernet interface.

v2: Also check IFF_MULTICAST flag to make sure the interface supports
    multicast

Reported-by: Rafał Miłecki <zajec5@gmail.com>
Tested-by: Rafał Miłecki <zajec5@gmail.com>
Fixes: 74235a25c673 ("[IPV6] addrconf: Fix IPv6 on tuntap tunnels")
Fixes: 1666d49e1d41 ("mld: do not remove mld souce list info when set link down")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index cb493e15959c..49367ec8a08d 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3345,6 +3345,10 @@ static void addrconf_dev_config(struct net_device *dev)
 	    (dev->type != ARPHRD_NONE) &&
 	    (dev->type != ARPHRD_RAWIP)) {
 		/* Alas, we support only Ethernet autoconfiguration. */
+		idev = __in6_dev_get(dev);
+		if (!IS_ERR_OR_NULL(idev) && dev->flags & IFF_UP &&
+		    dev->flags & IFF_MULTICAST)
+			ipv6_mc_up(idev);
 		return;
 	}
 
-- 
2.20.1


From 13bbb3b453a4f60ebfbc0f421704e463ebdca894 Mon Sep 17 00:00:00 2001
From: Mahesh Bandewar <maheshb@google.com>
Date: Mon, 9 Mar 2020 15:57:02 -0700
Subject: [PATCH 06/66] ipvlan: add cond_resched_rcu() while processing
 muticast backlog
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit e18b353f102e371580f3f01dd47567a25acc3c1d ]

If there are substantial number of slaves created as simulated by
Syzbot, the backlog processing could take much longer and result
into the issue found in the Syzbot report.

INFO: rcu_sched detected stalls on CPUs/tasks:
        (detected by 1, t=10502 jiffies, g=5049, c=5048, q=752)
All QSes seen, last rcu_sched kthread activity 10502 (4294965563-4294955061), jiffies_till_next_fqs=1, root ->qsmask 0x0
syz-executor.1  R  running task on cpu   1  10984 11210   3866 0x30020008 179034491270
Call Trace:
 <IRQ>
 [<ffffffff81497163>] _sched_show_task kernel/sched/core.c:8063 [inline]
 [<ffffffff81497163>] _sched_show_task.cold+0x2fd/0x392 kernel/sched/core.c:8030
 [<ffffffff8146a91b>] sched_show_task+0xb/0x10 kernel/sched/core.c:8073
 [<ffffffff815c931b>] print_other_cpu_stall kernel/rcu/tree.c:1577 [inline]
 [<ffffffff815c931b>] check_cpu_stall kernel/rcu/tree.c:1695 [inline]
 [<ffffffff815c931b>] __rcu_pending kernel/rcu/tree.c:3478 [inline]
 [<ffffffff815c931b>] rcu_pending kernel/rcu/tree.c:3540 [inline]
 [<ffffffff815c931b>] rcu_check_callbacks.cold+0xbb4/0xc29 kernel/rcu/tree.c:2876
 [<ffffffff815e3962>] update_process_times+0x32/0x80 kernel/time/timer.c:1635
 [<ffffffff816164f0>] tick_sched_handle+0xa0/0x180 kernel/time/tick-sched.c:161
 [<ffffffff81616ae4>] tick_sched_timer+0x44/0x130 kernel/time/tick-sched.c:1193
 [<ffffffff815e75f7>] __run_hrtimer kernel/time/hrtimer.c:1393 [inline]
 [<ffffffff815e75f7>] __hrtimer_run_queues+0x307/0xd90 kernel/time/hrtimer.c:1455
 [<ffffffff815e90ea>] hrtimer_interrupt+0x2ea/0x730 kernel/time/hrtimer.c:1513
 [<ffffffff844050f4>] local_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1031 [inline]
 [<ffffffff844050f4>] smp_apic_timer_interrupt+0x144/0x5e0 arch/x86/kernel/apic/apic.c:1056
 [<ffffffff84401cbe>] apic_timer_interrupt+0x8e/0xa0 arch/x86/entry/entry_64.S:778
RIP: 0010:do_raw_read_lock+0x22/0x80 kernel/locking/spinlock_debug.c:153
RSP: 0018:ffff8801dad07ab8 EFLAGS: 00000a02 ORIG_RAX: ffffffffffffff12
RAX: 0000000000000000 RBX: ffff8801c4135680 RCX: 0000000000000000
RDX: 1ffff10038826afe RSI: ffff88019d816bb8 RDI: ffff8801c41357f0
RBP: ffff8801dad07ac0 R08: 0000000000004b15 R09: 0000000000310273
R10: ffff88019d816bb8 R11: 0000000000000001 R12: ffff8801c41357e8
R13: 0000000000000000 R14: ffff8801cfb19850 R15: ffff8801cfb198b0
 [<ffffffff8101460e>] __raw_read_lock_bh include/linux/rwlock_api_smp.h:177 [inline]
 [<ffffffff8101460e>] _raw_read_lock_bh+0x3e/0x50 kernel/locking/spinlock.c:240
 [<ffffffff840d78ca>] ipv6_chk_mcast_addr+0x11a/0x6f0 net/ipv6/mcast.c:1006
 [<ffffffff84023439>] ip6_mc_input+0x319/0x8e0 net/ipv6/ip6_input.c:482
 [<ffffffff840211c8>] dst_input include/net/dst.h:449 [inline]
 [<ffffffff840211c8>] ip6_rcv_finish+0x408/0x610 net/ipv6/ip6_input.c:78
 [<ffffffff840214de>] NF_HOOK include/linux/netfilter.h:292 [inline]
 [<ffffffff840214de>] NF_HOOK include/linux/netfilter.h:286 [inline]
 [<ffffffff840214de>] ipv6_rcv+0x10e/0x420 net/ipv6/ip6_input.c:278
 [<ffffffff83a29efa>] __netif_receive_skb_one_core+0x12a/0x1f0 net/core/dev.c:5303
 [<ffffffff83a2a15c>] __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:5417
 [<ffffffff83a2f536>] process_backlog+0x216/0x6c0 net/core/dev.c:6243
 [<ffffffff83a30d1b>] napi_poll net/core/dev.c:6680 [inline]
 [<ffffffff83a30d1b>] net_rx_action+0x47b/0xfb0 net/core/dev.c:6748
 [<ffffffff846002c8>] __do_softirq+0x2c8/0x99a kernel/softirq.c:317
 [<ffffffff813e656a>] invoke_softirq kernel/softirq.c:399 [inline]
 [<ffffffff813e656a>] irq_exit+0x16a/0x1a0 kernel/softirq.c:439
 [<ffffffff84405115>] exiting_irq arch/x86/include/asm/apic.h:561 [inline]
 [<ffffffff84405115>] smp_apic_timer_interrupt+0x165/0x5e0 arch/x86/kernel/apic/apic.c:1058
 [<ffffffff84401cbe>] apic_timer_interrupt+0x8e/0xa0 arch/x86/entry/entry_64.S:778
 </IRQ>
RIP: 0010:__sanitizer_cov_trace_pc+0x26/0x50 kernel/kcov.c:102
RSP: 0018:ffff880196033bd8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff12
RAX: ffff88019d8161c0 RBX: 00000000ffffffff RCX: ffffc90003501000
RDX: 0000000000000002 RSI: ffffffff816236d1 RDI: 0000000000000005
RBP: ffff880196033bd8 R08: ffff88019d8161c0 R09: 0000000000000000
R10: 1ffff10032c067f0 R11: 0000000000000000 R12: 0000000000000000
R13: 0000000000000080 R14: 0000000000000000 R15: 0000000000000000
 [<ffffffff816236d1>] do_futex+0x151/0x1d50 kernel/futex.c:3548
 [<ffffffff816260f0>] C_SYSC_futex kernel/futex_compat.c:201 [inline]
 [<ffffffff816260f0>] compat_SyS_futex+0x270/0x3b0 kernel/futex_compat.c:175
 [<ffffffff8101da17>] do_syscall_32_irqs_on arch/x86/entry/common.c:353 [inline]
 [<ffffffff8101da17>] do_fast_syscall_32+0x357/0xe1c arch/x86/entry/common.c:415
 [<ffffffff84401a9b>] entry_SYSENTER_compat+0x8b/0x9d arch/x86/entry/entry_64_compat.S:139
RIP: 0023:0xf7f23c69
RSP: 002b:00000000f5d1f12c EFLAGS: 00000282 ORIG_RAX: 00000000000000f0
RAX: ffffffffffffffda RBX: 000000000816af88 RCX: 0000000000000080
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 000000000816af8c
RBP: 00000000f5d1f228 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
rcu_sched kthread starved for 10502 jiffies! g5049 c5048 f0x2 RCU_GP_WAIT_FQS(3) ->state=0x0 ->cpu=1
rcu_sched       R  running task on cpu   1  13048     8      2 0x90000000 179099587640
Call Trace:
 [<ffffffff8147321f>] context_switch+0x60f/0xa60 kernel/sched/core.c:3209
 [<ffffffff8100095a>] __schedule+0x5aa/0x1da0 kernel/sched/core.c:3934
 [<ffffffff810021df>] schedule+0x8f/0x1b0 kernel/sched/core.c:4011
 [<ffffffff8101116d>] schedule_timeout+0x50d/0xee0 kernel/time/timer.c:1803
 [<ffffffff815c13f1>] rcu_gp_kthread+0xda1/0x3b50 kernel/rcu/tree.c:2327
 [<ffffffff8144b318>] kthread+0x348/0x420 kernel/kthread.c:246
 [<ffffffff84400266>] ret_from_fork+0x56/0x70 arch/x86/entry/entry_64.S:393

Fixes: ba35f8588f47 (“ipvlan: Defer multicast / broadcast processing to a work-queue”)
Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ipvlan/ipvlan_core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index 30cd0c4f0be0..514e497d9ff5 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -277,6 +277,7 @@ void ipvlan_process_multicast(struct work_struct *work)
 			}
 			ipvlan_count_rx(ipvlan, len, ret == NET_RX_SUCCESS, true);
 			local_bh_enable();
+			cond_resched_rcu();
 		}
 		rcu_read_unlock();
 
-- 
2.20.1


From 56a0221eab2b88b51d9d43f6922cdc451540f30b Mon Sep 17 00:00:00 2001
From: Jiri Wiesner <jwiesner@suse.com>
Date: Sat, 7 Mar 2020 13:31:57 +0100
Subject: [PATCH 07/66] ipvlan: do not add hardware address of master to its
 unicast filter list

[ Upstream commit 63aae7b17344d4b08a7d05cb07044de4c0f9dcc6 ]

There is a problem when ipvlan slaves are created on a master device that
is a vmxnet3 device (ipvlan in VMware guests). The vmxnet3 driver does not
support unicast address filtering. When an ipvlan device is brought up in
ipvlan_open(), the ipvlan driver calls dev_uc_add() to add the hardware
address of the vmxnet3 master device to the unicast address list of the
master device, phy_dev->uc. This inevitably leads to the vmxnet3 master
device being forced into promiscuous mode by __dev_set_rx_mode().

Promiscuous mode is switched on the master despite the fact that there is
still only one hardware address that the master device should use for
filtering in order for the ipvlan device to be able to receive packets.
The comment above struct net_device describes the uc_promisc member as a
"counter, that indicates, that promiscuous mode has been enabled due to
the need to listen to additional unicast addresses in a device that does
not implement ndo_set_rx_mode()". Moreover, the design of ipvlan
guarantees that only the hardware address of a master device,
phy_dev->dev_addr, will be used to transmit and receive all packets from
its ipvlan slaves. Thus, the unicast address list of the master device
should not be modified by ipvlan_open() and ipvlan_stop() in order to make
ipvlan a workable option on masters that do not support unicast address
filtering.

Fixes: 2ad7bf3638411 ("ipvlan: Initial check-in of the IPVLAN driver")
Reported-by: Per Sundstrom <per.sundstrom@redqube.se>
Signed-off-by: Jiri Wiesner <jwiesner@suse.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ipvlan/ipvlan_main.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index a70662261a5a..f195f278a83a 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -164,7 +164,6 @@ static void ipvlan_uninit(struct net_device *dev)
 static int ipvlan_open(struct net_device *dev)
 {
 	struct ipvl_dev *ipvlan = netdev_priv(dev);
-	struct net_device *phy_dev = ipvlan->phy_dev;
 	struct ipvl_addr *addr;
 
 	if (ipvlan->port->mode == IPVLAN_MODE_L3 ||
@@ -178,7 +177,7 @@ static int ipvlan_open(struct net_device *dev)
 		ipvlan_ht_addr_add(ipvlan, addr);
 	rcu_read_unlock();
 
-	return dev_uc_add(phy_dev, phy_dev->dev_addr);
+	return 0;
 }
 
 static int ipvlan_stop(struct net_device *dev)
@@ -190,8 +189,6 @@ static int ipvlan_stop(struct net_device *dev)
 	dev_uc_unsync(phy_dev, dev);
 	dev_mc_unsync(phy_dev, dev);
 
-	dev_uc_del(phy_dev, phy_dev->dev_addr);
-
 	rcu_read_lock();
 	list_for_each_entry_rcu(addr, &ipvlan->addrs, anode)
 		ipvlan_ht_addr_del(addr);
-- 
2.20.1


From ea9569211ee419e49e0a8d6f0a4d5d91dbb971f6 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 9 Mar 2020 18:22:58 -0700
Subject: [PATCH 08/66] ipvlan: do not use cond_resched_rcu() in
 ipvlan_process_multicast()

[ Upstream commit afe207d80a61e4d6e7cfa0611a4af46d0ba95628 ]

Commit e18b353f102e ("ipvlan: add cond_resched_rcu() while
processing muticast backlog") added a cond_resched_rcu() in a loop
using rcu protection to iterate over slaves.

This is breaking rcu rules, so lets instead use cond_resched()
at a point we can reschedule

Fixes: e18b353f102e ("ipvlan: add cond_resched_rcu() while processing muticast backlog")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ipvlan/ipvlan_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index 514e497d9ff5..57617ff5565f 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -277,7 +277,6 @@ void ipvlan_process_multicast(struct work_struct *work)
 			}
 			ipvlan_count_rx(ipvlan, len, ret == NET_RX_SUCCESS, true);
 			local_bh_enable();
-			cond_resched_rcu();
 		}
 		rcu_read_unlock();
 
@@ -294,6 +293,7 @@ void ipvlan_process_multicast(struct work_struct *work)
 		}
 		if (dev)
 			dev_put(dev);
+		cond_resched();
 	}
 }
 
-- 
2.20.1


From 7b62a54e52ef17032e0337d7f89352652f9a57cd Mon Sep 17 00:00:00 2001
From: Mahesh Bandewar <maheshb@google.com>
Date: Mon, 9 Mar 2020 15:56:56 -0700
Subject: [PATCH 09/66] ipvlan: don't deref eth hdr before checking it's set
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit ad8192767c9f9cf97da57b9ffcea70fb100febef ]

IPvlan in L3 mode discards outbound multicast packets but performs
the check before ensuring the ether-header is set or not. This is
an error that Eric found through code browsing.

Fixes: 2ad7bf363841 (“ipvlan: Initial check-in of the IPVLAN driver.”)
Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ipvlan/ipvlan_core.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index 57617ff5565f..8801d093135c 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -499,19 +499,21 @@ static int ipvlan_process_outbound(struct sk_buff *skb)
 	struct ethhdr *ethh = eth_hdr(skb);
 	int ret = NET_XMIT_DROP;
 
-	/* In this mode we dont care about multicast and broadcast traffic */
-	if (is_multicast_ether_addr(ethh->h_dest)) {
-		pr_debug_ratelimited("Dropped {multi|broad}cast of type=[%x]\n",
-				     ntohs(skb->protocol));
-		kfree_skb(skb);
-		goto out;
-	}
-
 	/* The ipvlan is a pseudo-L2 device, so the packets that we receive
 	 * will have L2; which need to discarded and processed further
 	 * in the net-ns of the main-device.
 	 */
 	if (skb_mac_header_was_set(skb)) {
+		/* In this mode we dont care about
+		 * multicast and broadcast traffic */
+		if (is_multicast_ether_addr(ethh->h_dest)) {
+			pr_debug_ratelimited(
+				"Dropped {multi|broad}cast of type=[%x]\n",
+				ntohs(skb->protocol));
+			kfree_skb(skb);
+			goto out;
+		}
+
 		skb_pull(skb, sizeof(*ethh));
 		skb->mac_header = (typeof(skb->mac_header))~0U;
 		skb_reset_network_header(skb);
-- 
2.20.1


From 978f7a38a479a54beee4156643bf4e74fa07fba2 Mon Sep 17 00:00:00 2001
From: Mahesh Bandewar <maheshb@google.com>
Date: Mon, 9 Mar 2020 15:57:07 -0700
Subject: [PATCH 10/66] macvlan: add cond_resched() during multicast processing

[ Upstream commit ce9a4186f9ac475c415ffd20348176a4ea366670 ]

The Rx bound multicast packets are deferred to a workqueue and
macvlan can also suffer from the same attack that was discovered
by Syzbot for IPvlan. This solution is not as effective as in
IPvlan. IPvlan defers all (Tx and Rx) multicast packet processing
to a workqueue while macvlan does this way only for the Rx. This
fix should address the Rx codition to certain extent.

Tx is still suseptible. Tx multicast processing happens when
.ndo_start_xmit is called, hence we cannot add cond_resched().
However, it's not that severe since the user which is generating
 / flooding will be affected the most.

Fixes: 412ca1550cbe ("macvlan: Move broadcasts into a work queue")
Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macvlan.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index c5bf61565726..26f6be4796c7 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -334,6 +334,8 @@ static void macvlan_process_broadcast(struct work_struct *w)
 		if (src)
 			dev_put(src->dev);
 		consume_skb(skb);
+
+		cond_resched();
 	}
 }
 
-- 
2.20.1


From b9caea30f66b025af102db17b97f37d18ab81049 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Tue, 3 Mar 2020 15:01:46 +0000
Subject: [PATCH 11/66] net: dsa: fix phylink_start()/phylink_stop() calls

[ Upstream commit 8640f8dc6d657ebfb4e67c202ad32c5457858a13 ]

Place phylink_start()/phylink_stop() inside dsa_port_enable() and
dsa_port_disable(), which ensures that we call phylink_stop() before
tearing down phylink - which is a documented requirement.  Failure
to do so can cause use-after-free bugs.

Fixes: 0e27921816ad ("net: dsa: Use PHYLINK for the CPU/DSA ports")
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/dsa_priv.h |  2 ++
 net/dsa/port.c     | 32 ++++++++++++++++++++++++++------
 net/dsa/slave.c    |  8 ++------
 3 files changed, 30 insertions(+), 12 deletions(-)

diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index 2dd86d9bcda9..a0bdd6011c9f 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -117,7 +117,9 @@ static inline struct net_device *dsa_master_find_slave(struct net_device *dev,
 /* port.c */
 int dsa_port_set_state(struct dsa_port *dp, u8 state,
 		       struct switchdev_trans *trans);
+int dsa_port_enable_rt(struct dsa_port *dp, struct phy_device *phy);
 int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy);
+void dsa_port_disable_rt(struct dsa_port *dp);
 void dsa_port_disable(struct dsa_port *dp);
 int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br);
 void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br);
diff --git a/net/dsa/port.c b/net/dsa/port.c
index 46ac9ba21987..a26756d1dd39 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -63,7 +63,7 @@ static void dsa_port_set_state_now(struct dsa_port *dp, u8 state)
 		pr_err("DSA: failed to set STP state %u (%d)\n", state, err);
 }
 
-int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy)
+int dsa_port_enable_rt(struct dsa_port *dp, struct phy_device *phy)
 {
 	struct dsa_switch *ds = dp->ds;
 	int port = dp->index;
@@ -78,14 +78,31 @@ int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy)
 	if (!dp->bridge_dev)
 		dsa_port_set_state_now(dp, BR_STATE_FORWARDING);
 
+	if (dp->pl)
+		phylink_start(dp->pl);
+
 	return 0;
 }
 
-void dsa_port_disable(struct dsa_port *dp)
+int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy)
+{
+	int err;
+
+	rtnl_lock();
+	err = dsa_port_enable_rt(dp, phy);
+	rtnl_unlock();
+
+	return err;
+}
+
+void dsa_port_disable_rt(struct dsa_port *dp)
 {
 	struct dsa_switch *ds = dp->ds;
 	int port = dp->index;
 
+	if (dp->pl)
+		phylink_stop(dp->pl);
+
 	if (!dp->bridge_dev)
 		dsa_port_set_state_now(dp, BR_STATE_DISABLED);
 
@@ -93,6 +110,13 @@ void dsa_port_disable(struct dsa_port *dp)
 		ds->ops->port_disable(ds, port);
 }
 
+void dsa_port_disable(struct dsa_port *dp)
+{
+	rtnl_lock();
+	dsa_port_disable_rt(dp);
+	rtnl_unlock();
+}
+
 int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br)
 {
 	struct dsa_notifier_bridge_info info = {
@@ -619,10 +643,6 @@ static int dsa_port_phylink_register(struct dsa_port *dp)
 		goto err_phy_connect;
 	}
 
-	rtnl_lock();
-	phylink_start(dp->pl);
-	rtnl_unlock();
-
 	return 0;
 
 err_phy_connect:
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 78ffc87dc25e..0b882de5483c 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -90,12 +90,10 @@ static int dsa_slave_open(struct net_device *dev)
 			goto clear_allmulti;
 	}
 
-	err = dsa_port_enable(dp, dev->phydev);
+	err = dsa_port_enable_rt(dp, dev->phydev);
 	if (err)
 		goto clear_promisc;
 
-	phylink_start(dp->pl);
-
 	return 0;
 
 clear_promisc:
@@ -119,9 +117,7 @@ static int dsa_slave_close(struct net_device *dev)
 	cancel_work_sync(&dp->xmit_work);
 	skb_queue_purge(&dp->xmit_queue);
 
-	phylink_stop(dp->pl);
-
-	dsa_port_disable(dp);
+	dsa_port_disable_rt(dp);
 
 	dev_mc_unsync(master, dev);
 	dev_uc_unsync(master, dev);
-- 
2.20.1


From fabbc3390438a9c07473973b93679f80106f7026 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Fri, 28 Feb 2020 19:39:41 +0000
Subject: [PATCH 12/66] net: dsa: mv88e6xxx: fix lockup on warm boot

[ Upstream commit 0395823b8d9a4d87bd1bf74359123461c2ae801b ]

If the switch is not hardware reset on a warm boot, interrupts can be
left enabled, and possibly pending. This will cause us to enter an
infinite loop trying to service an interrupt we are unable to handle,
thereby preventing the kernel from booting.

Ensure that the global 2 interrupt sources are disabled before we claim
the parent interrupt.

Observed on the ZII development revision B and C platforms with
reworked serdes support, and using reboot -f to reboot the platform.

Fixes: dc30c35be720 ("net: dsa: mv88e6xxx: Implement interrupt support.")
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/global2.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/dsa/mv88e6xxx/global2.c b/drivers/net/dsa/mv88e6xxx/global2.c
index 87bfe7c8c9cd..246751b4f3b5 100644
--- a/drivers/net/dsa/mv88e6xxx/global2.c
+++ b/drivers/net/dsa/mv88e6xxx/global2.c
@@ -1096,6 +1096,13 @@ int mv88e6xxx_g2_irq_setup(struct mv88e6xxx_chip *chip)
 {
 	int err, irq, virq;
 
+	chip->g2_irq.masked = ~0;
+	mv88e6xxx_reg_lock(chip);
+	err = mv88e6xxx_g2_int_mask(chip, ~chip->g2_irq.masked);
+	mv88e6xxx_reg_unlock(chip);
+	if (err)
+		return err;
+
 	chip->g2_irq.domain = irq_domain_add_simple(
 		chip->dev->of_node, 16, 0, &mv88e6xxx_g2_irq_domain_ops, chip);
 	if (!chip->g2_irq.domain)
@@ -1105,7 +1112,6 @@ int mv88e6xxx_g2_irq_setup(struct mv88e6xxx_chip *chip)
 		irq_create_mapping(chip->g2_irq.domain, irq);
 
 	chip->g2_irq.chip = mv88e6xxx_g2_irq_chip;
-	chip->g2_irq.masked = ~0;
 
 	chip->device_irq = irq_find_mapping(chip->g1_irq.domain,
 					    MV88E6XXX_G1_STS_IRQ_DEVICE);
-- 
2.20.1


From 196e8edf3a8ff250c667bb7af6f39338606e85bb Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 10 Mar 2020 20:36:16 -0700
Subject: [PATCH 13/66] net: fec: validate the new settings in
 fec_enet_set_coalesce()

[ Upstream commit ab14961d10d02d20767612c78ce148f6eb85bd58 ]

fec_enet_set_coalesce() validates the previously set params
and if they are within range proceeds to apply the new ones.
The new ones, however, are not validated. This seems backwards,
probably a copy-paste error?

Compile tested only.

Fixes: d851b47b22fc ("net: fec: add interrupt coalescence feature support")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Fugang Duan <fugang.duan@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_main.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 9294027e9d90..ab028f954ac5 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -2529,15 +2529,15 @@ fec_enet_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *ec)
 		return -EINVAL;
 	}
 
-	cycle = fec_enet_us_to_itr_clock(ndev, fep->rx_time_itr);
+	cycle = fec_enet_us_to_itr_clock(ndev, ec->rx_coalesce_usecs);
 	if (cycle > 0xFFFF) {
 		dev_err(dev, "Rx coalesced usec exceed hardware limitation\n");
 		return -EINVAL;
 	}
 
-	cycle = fec_enet_us_to_itr_clock(ndev, fep->tx_time_itr);
+	cycle = fec_enet_us_to_itr_clock(ndev, ec->tx_coalesce_usecs);
 	if (cycle > 0xFFFF) {
-		dev_err(dev, "Rx coalesced usec exceed hardware limitation\n");
+		dev_err(dev, "Tx coalesced usec exceed hardware limitation\n");
 		return -EINVAL;
 	}
 
-- 
2.20.1


From c6d0cda304256ab4cdeb7fc96984e18eba13bbcc Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Thu, 5 Mar 2020 09:47:53 +0800
Subject: [PATCH 14/66] net: hns3: fix a not link up issue when fibre port
 supports autoneg

[ Upstream commit 68e1006f618e509fc7869259fe83ceec4a95dac3 ]

When fibre port supports auto-negotiation, the IMP(Intelligent
Management Process) processes the speed of auto-negotiation
and the  user's speed separately.
For below case, the port will get a not link up problem.
step 1: disables auto-negotiation and sets speed to A, then
the driver's MAC speed will be updated to A.
step 2: enables auto-negotiation and MAC gets negotiated
speed B, then the driver's MAC speed will be updated to B
through querying in periodical task.
step 3: MAC gets new negotiated speed A.
step 4: disables auto-negotiation and sets speed to B before
periodical task query new MAC speed A, the driver will  ignore
the speed configuration.

This patch fixes it by skipping speed and duplex checking when
fibre port supports auto-negotiation.

Fixes: 22f48e24a23d ("net: hns3: add autoneg and change speed support for fibre port")
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 5d74f5a60102..02f0e1e6b6f9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2450,10 +2450,12 @@ static int hclge_cfg_mac_speed_dup_hw(struct hclge_dev *hdev, int speed,
 
 int hclge_cfg_mac_speed_dup(struct hclge_dev *hdev, int speed, u8 duplex)
 {
+	struct hclge_mac *mac = &hdev->hw.mac;
 	int ret;
 
 	duplex = hclge_check_speed_dup(duplex, speed);
-	if (hdev->hw.mac.speed == speed && hdev->hw.mac.duplex == duplex)
+	if (!mac->support_autoneg && mac->speed == speed &&
+	    mac->duplex == duplex)
 		return 0;
 
 	ret = hclge_cfg_mac_speed_dup_hw(hdev, speed, duplex);
-- 
2.20.1


From 6d000b73db5430fffb4d458d0f6f8c3b02df2879 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Sat, 29 Feb 2020 17:27:13 +0800
Subject: [PATCH 15/66] net/ipv6: use configured metric when add peer route

[ Upstream commit 07758eb9ff52794fba15d03aa88d92dbd1b7d125 ]

When we add peer address with metric configured, IPv4 could set the dest
metric correctly, but IPv6 do not. e.g.

]# ip addr add 192.0.2.1 peer 192.0.2.2/32 dev eth1 metric 20
]# ip route show dev eth1
192.0.2.2 proto kernel scope link src 192.0.2.1 metric 20
]# ip addr add 2001:db8::1 peer 2001:db8::2/128 dev eth1 metric 20
]# ip -6 route show dev eth1
2001:db8::1 proto kernel metric 20 pref medium
2001:db8::2 proto kernel metric 256 pref medium

Fix this by using configured metric instead of default one.

Reported-by: Jianlin Shi <jishi@redhat.com>
Fixes: 8308f3ff1753 ("net/ipv6: Add support for specifying metric of connected routes")
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 49367ec8a08d..2d758a39dd29 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5987,9 +5987,9 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
 		if (ifp->idev->cnf.forwarding)
 			addrconf_join_anycast(ifp);
 		if (!ipv6_addr_any(&ifp->peer_addr))
-			addrconf_prefix_route(&ifp->peer_addr, 128, 0,
-					      ifp->idev->dev, 0, 0,
-					      GFP_ATOMIC);
+			addrconf_prefix_route(&ifp->peer_addr, 128,
+					      ifp->rt_priority, ifp->idev->dev,
+					      0, 0, GFP_ATOMIC);
 		break;
 	case RTM_DELADDR:
 		if (ifp->idev->cnf.forwarding)
-- 
2.20.1


From e430074f85fb794b6a48564d21278de11c5230c8 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 26 Feb 2020 19:47:34 +0100
Subject: [PATCH 16/66] netlink: Use netlink header as base to calculate bad
 attribute offset

[ Upstream commit 84b3268027641401bb8ad4427a90a3cce2eb86f5 ]

Userspace might send a batch that is composed of several netlink
messages. The netlink_ack() function must use the pointer to the netlink
header as base to calculate the bad attribute offset.

Fixes: 2d4bc93368f5 ("netlink: extended ACK reporting")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index edf3e285e242..5313f1cec170 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2434,7 +2434,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err,
 							       in_skb->len))
 				WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_OFFS,
 						    (u8 *)extack->bad_attr -
-						    in_skb->data));
+						    (u8 *)nlh));
 		} else {
 			if (extack->cookie_len)
 				WARN_ON(nla_put(skb, NLMSGERR_ATTR_COOKIE,
-- 
2.20.1


From bd9f3e602f0906838fb6ce4970af9ed3b2a0c726 Mon Sep 17 00:00:00 2001
From: Dmitry Bogdanov <dbogdanov@marvell.com>
Date: Tue, 10 Mar 2020 18:22:24 +0300
Subject: [PATCH 17/66] net: macsec: update SCI upon MAC address change.

[ Upstream commit 6fc498bc82929ee23aa2f35a828c6178dfd3f823 ]

SCI should be updated, because it contains MAC in its first 6 octets.

Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver")
Signed-off-by: Dmitry Bogdanov <dbogdanov@marvell.com>
Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macsec.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index afd8b2a08245..88b7544910d9 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -532,6 +532,11 @@ static struct macsec_eth_header *macsec_ethhdr(struct sk_buff *skb)
 	return (struct macsec_eth_header *)skb_mac_header(skb);
 }
 
+static sci_t dev_to_sci(struct net_device *dev, __be16 port)
+{
+	return make_sci(dev->dev_addr, port);
+}
+
 static u32 tx_sa_update_pn(struct macsec_tx_sa *tx_sa, struct macsec_secy *secy)
 {
 	u32 pn;
@@ -2903,6 +2908,7 @@ static int macsec_set_mac_address(struct net_device *dev, void *p)
 
 out:
 	ether_addr_copy(dev->dev_addr, addr->sa_data);
+	macsec->secy.sci = dev_to_sci(dev, MACSEC_PORT_ES);
 	return 0;
 }
 
@@ -3176,11 +3182,6 @@ static bool sci_exists(struct net_device *dev, sci_t sci)
 	return false;
 }
 
-static sci_t dev_to_sci(struct net_device *dev, __be16 port)
-{
-	return make_sci(dev->dev_addr, port);
-}
-
 static int macsec_add_dev(struct net_device *dev, sci_t sci, u8 icv_len)
 {
 	struct macsec_dev *macsec = macsec_priv(dev);
-- 
2.20.1


From 415a12fe4a9c17d3bcb29203496137c4ad0689ab Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Tue, 10 Mar 2020 03:28:18 +0200
Subject: [PATCH 18/66] net: mscc: ocelot: properly account for VLAN header
 length when setting MRU

[ Upstream commit a8015ded89ad740d21355470d41879c5bd82aab7 ]

What the driver writes into MAC_MAXLEN_CFG does not actually represent
VLAN_ETH_FRAME_LEN but instead ETH_FRAME_LEN + ETH_FCS_LEN. Yes they are
numerically equal, but the difference is important, as the switch treats
VLAN-tagged traffic specially and knows to increase the maximum accepted
frame size automatically. So it is always wrong to account for VLAN in
the MAC_MAXLEN_CFG register.

Unconditionally increase the maximum allowed frame size for
double-tagged traffic. Accounting for the additional length does not
mean that the other VLAN membership checks aren't performed, so there's
no harm done.

Also, stop abusing the MTU name for configuring the MRU. There is no
support for configuring the MRU on an interface at the moment.

Fixes: a556c76adc05 ("net: mscc: Add initial Ocelot switch support")
Fixes: fa914e9c4d94 ("net: mscc: ocelot: create a helper for changing the port MTU")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot.c     | 28 ++++++++++++++++----------
 drivers/net/ethernet/mscc/ocelot_dev.h |  2 +-
 2 files changed, 18 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 985b46d7e3d1..88c0464a54e2 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -2175,24 +2175,29 @@ static int ocelot_init_timestamp(struct ocelot *ocelot)
 	return 0;
 }
 
-static void ocelot_port_set_mtu(struct ocelot *ocelot, int port, size_t mtu)
+/* Configure the maximum SDU (L2 payload) on RX to the value specified in @sdu.
+ * The length of VLAN tags is accounted for automatically via DEV_MAC_TAGS_CFG.
+ */
+static void ocelot_port_set_maxlen(struct ocelot *ocelot, int port, size_t sdu)
 {
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
+	int maxlen = sdu + ETH_HLEN + ETH_FCS_LEN;
 	int atop_wm;
 
-	ocelot_port_writel(ocelot_port, mtu, DEV_MAC_MAXLEN_CFG);
+	ocelot_port_writel(ocelot_port, maxlen, DEV_MAC_MAXLEN_CFG);
 
 	/* Set Pause WM hysteresis
-	 * 152 = 6 * mtu / OCELOT_BUFFER_CELL_SZ
-	 * 101 = 4 * mtu / OCELOT_BUFFER_CELL_SZ
+	 * 152 = 6 * maxlen / OCELOT_BUFFER_CELL_SZ
+	 * 101 = 4 * maxlen / OCELOT_BUFFER_CELL_SZ
 	 */
 	ocelot_write_rix(ocelot, SYS_PAUSE_CFG_PAUSE_ENA |
 			 SYS_PAUSE_CFG_PAUSE_STOP(101) |
 			 SYS_PAUSE_CFG_PAUSE_START(152), SYS_PAUSE_CFG, port);
 
 	/* Tail dropping watermark */
-	atop_wm = (ocelot->shared_queue_sz - 9 * mtu) / OCELOT_BUFFER_CELL_SZ;
-	ocelot_write_rix(ocelot, ocelot_wm_enc(9 * mtu),
+	atop_wm = (ocelot->shared_queue_sz - 9 * maxlen) /
+		   OCELOT_BUFFER_CELL_SZ;
+	ocelot_write_rix(ocelot, ocelot_wm_enc(9 * maxlen),
 			 SYS_ATOP, port);
 	ocelot_write(ocelot, ocelot_wm_enc(atop_wm), SYS_ATOP_TOT_CFG);
 }
@@ -2221,9 +2226,10 @@ void ocelot_init_port(struct ocelot *ocelot, int port)
 			   DEV_MAC_HDX_CFG);
 
 	/* Set Max Length and maximum tags allowed */
-	ocelot_port_set_mtu(ocelot, port, VLAN_ETH_FRAME_LEN);
+	ocelot_port_set_maxlen(ocelot, port, ETH_DATA_LEN);
 	ocelot_port_writel(ocelot_port, DEV_MAC_TAGS_CFG_TAG_ID(ETH_P_8021AD) |
 			   DEV_MAC_TAGS_CFG_VLAN_AWR_ENA |
+			   DEV_MAC_TAGS_CFG_VLAN_DBL_AWR_ENA |
 			   DEV_MAC_TAGS_CFG_VLAN_LEN_AWR_ENA,
 			   DEV_MAC_TAGS_CFG);
 
@@ -2309,18 +2315,18 @@ void ocelot_set_cpu_port(struct ocelot *ocelot, int cpu,
 	 * Only one port can be an NPI at the same time.
 	 */
 	if (cpu < ocelot->num_phys_ports) {
-		int mtu = VLAN_ETH_FRAME_LEN + OCELOT_TAG_LEN;
+		int sdu = ETH_DATA_LEN + OCELOT_TAG_LEN;
 
 		ocelot_write(ocelot, QSYS_EXT_CPU_CFG_EXT_CPUQ_MSK_M |
 			     QSYS_EXT_CPU_CFG_EXT_CPU_PORT(cpu),
 			     QSYS_EXT_CPU_CFG);
 
 		if (injection == OCELOT_TAG_PREFIX_SHORT)
-			mtu += OCELOT_SHORT_PREFIX_LEN;
+			sdu += OCELOT_SHORT_PREFIX_LEN;
 		else if (injection == OCELOT_TAG_PREFIX_LONG)
-			mtu += OCELOT_LONG_PREFIX_LEN;
+			sdu += OCELOT_LONG_PREFIX_LEN;
 
-		ocelot_port_set_mtu(ocelot, cpu, mtu);
+		ocelot_port_set_maxlen(ocelot, cpu, sdu);
 	}
 
 	/* CPU port Injection/Extraction configuration */
diff --git a/drivers/net/ethernet/mscc/ocelot_dev.h b/drivers/net/ethernet/mscc/ocelot_dev.h
index 0a50d53bbd3f..7c08437061fc 100644
--- a/drivers/net/ethernet/mscc/ocelot_dev.h
+++ b/drivers/net/ethernet/mscc/ocelot_dev.h
@@ -74,7 +74,7 @@
 #define DEV_MAC_TAGS_CFG_TAG_ID_M                         GENMASK(31, 16)
 #define DEV_MAC_TAGS_CFG_TAG_ID_X(x)                      (((x) & GENMASK(31, 16)) >> 16)
 #define DEV_MAC_TAGS_CFG_VLAN_LEN_AWR_ENA                 BIT(2)
-#define DEV_MAC_TAGS_CFG_PB_ENA                           BIT(1)
+#define DEV_MAC_TAGS_CFG_VLAN_DBL_AWR_ENA                 BIT(1)
 #define DEV_MAC_TAGS_CFG_VLAN_AWR_ENA                     BIT(0)
 
 #define DEV_MAC_ADV_CHK_CFG                               0x2c
-- 
2.20.1


From 955bad111b40ff3c90841a39ffc1f7b7ab63a1b1 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 4 Mar 2020 17:24:31 +0300
Subject: [PATCH 19/66] net: nfc: fix bounds checking bugs on "pipe"

[ Upstream commit a3aefbfe45751bf7b338c181b97608e276b5bb73 ]

This is similar to commit 674d9de02aa7 ("NFC: Fix possible memory
corruption when handling SHDLC I-Frame commands") and commit d7ee81ad09f0
("NFC: nci: Add some bounds checking in nci_hci_cmd_received()") which
added range checks on "pipe".

The "pipe" variable comes skb->data[0] in nfc_hci_msg_rx_work().
It's in the 0-255 range.  We're using it as the array index into the
hdev->pipes[] array which has NFC_HCI_MAX_PIPES (128) members.

Fixes: 118278f20aa8 ("NFC: hci: Add pipes table to reference them with a tuple {gate, host}")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/nfc/hci/core.c | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c
index 6f1b096e601c..43811b5219b5 100644
--- a/net/nfc/hci/core.c
+++ b/net/nfc/hci/core.c
@@ -181,13 +181,20 @@ void nfc_hci_resp_received(struct nfc_hci_dev *hdev, u8 result,
 void nfc_hci_cmd_received(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd,
 			  struct sk_buff *skb)
 {
-	u8 gate = hdev->pipes[pipe].gate;
 	u8 status = NFC_HCI_ANY_OK;
 	struct hci_create_pipe_resp *create_info;
 	struct hci_delete_pipe_noti *delete_info;
 	struct hci_all_pipe_cleared_noti *cleared_info;
+	u8 gate;
 
-	pr_debug("from gate %x pipe %x cmd %x\n", gate, pipe, cmd);
+	pr_debug("from pipe %x cmd %x\n", pipe, cmd);
+
+	if (pipe >= NFC_HCI_MAX_PIPES) {
+		status = NFC_HCI_ANY_E_NOK;
+		goto exit;
+	}
+
+	gate = hdev->pipes[pipe].gate;
 
 	switch (cmd) {
 	case NFC_HCI_ADM_NOTIFY_PIPE_CREATED:
@@ -375,8 +382,14 @@ void nfc_hci_event_received(struct nfc_hci_dev *hdev, u8 pipe, u8 event,
 			    struct sk_buff *skb)
 {
 	int r = 0;
-	u8 gate = hdev->pipes[pipe].gate;
+	u8 gate;
+
+	if (pipe >= NFC_HCI_MAX_PIPES) {
+		pr_err("Discarded event %x to invalid pipe %x\n", event, pipe);
+		goto exit;
+	}
 
+	gate = hdev->pipes[pipe].gate;
 	if (gate == NFC_HCI_INVALID_GATE) {
 		pr_err("Discarded event %x to unopened pipe %x\n", event, pipe);
 		goto exit;
-- 
2.20.1


From 0ef326c8f0f0aedafbadfd4320dbfa1f929013fd Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Mon, 9 Mar 2020 11:34:35 -0400
Subject: [PATCH 20/66] net/packet: tpacket_rcv: do not increment ring index on
 drop

[ Upstream commit 46e4c421a053c36bf7a33dda2272481bcaf3eed3 ]

In one error case, tpacket_rcv drops packets after incrementing the
ring producer index.

If this happens, it does not update tp_status to TP_STATUS_USER and
thus the reader is stalled for an iteration of the ring, causing out
of order arrival.

The only such error path is when virtio_net_hdr_from_skb fails due
to encountering an unknown GSO type.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 118cd66b7516..20edb7c25e22 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2273,6 +2273,13 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 					TP_STATUS_KERNEL, (macoff+snaplen));
 	if (!h.raw)
 		goto drop_n_account;
+
+	if (do_vnet &&
+	    virtio_net_hdr_from_skb(skb, h.raw + macoff -
+				    sizeof(struct virtio_net_hdr),
+				    vio_le(), true, 0))
+		goto drop_n_account;
+
 	if (po->tp_version <= TPACKET_V2) {
 		packet_increment_rx_head(po, &po->rx_ring);
 	/*
@@ -2285,12 +2292,6 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 			status |= TP_STATUS_LOSING;
 	}
 
-	if (do_vnet &&
-	    virtio_net_hdr_from_skb(skb, h.raw + macoff -
-				    sizeof(struct virtio_net_hdr),
-				    vio_le(), true, 0))
-		goto drop_n_account;
-
 	po->stats.stats1.tp_packets++;
 	if (copy_skb) {
 		status |= TP_STATUS_COPY;
-- 
2.20.1


From 5e64727a6b461a08e454a986c5bd5a5b70cd9e07 Mon Sep 17 00:00:00 2001
From: Jonas Gorski <jonas.gorski@gmail.com>
Date: Mon, 2 Mar 2020 20:46:57 +0100
Subject: [PATCH 21/66] net: phy: bcm63xx: fix OOPS due to missing driver name

[ Upstream commit 43de81b0601df7d7988d3f5617ee0987df65c883 ]

719655a14971 ("net: phy: Replace phy driver features u32 with link_mode
bitmap") was a bit over-eager and also removed the second phy driver's
name, resulting in a nasty OOPS on registration:

[    1.319854] CPU 0 Unable to handle kernel paging request at virtual address 00000000, epc == 804dd50c, ra == 804dd4f0
[    1.330859] Oops[#1]:
[    1.333138] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.4.22 #0
[    1.339217] $ 0   : 00000000 00000001 87ca7f00 805c1874
[    1.344590] $ 4   : 00000000 00000047 00585000 8701f800
[    1.349965] $ 8   : 8701f800 804f4a5c 00000003 64726976
[    1.355341] $12   : 00000001 00000000 00000000 00000114
[    1.360718] $16   : 87ca7f80 00000000 00000000 80639fe4
[    1.366093] $20   : 00000002 00000000 806441d0 80b90000
[    1.371470] $24   : 00000000 00000000
[    1.376847] $28   : 87c1e000 87c1fda0 80b90000 804dd4f0
[    1.382224] Hi    : d1c8f8da
[    1.385180] Lo    : 5518a480
[    1.388182] epc   : 804dd50c kset_find_obj+0x3c/0x114
[    1.393345] ra    : 804dd4f0 kset_find_obj+0x20/0x114
[    1.398530] Status: 10008703 KERNEL EXL IE
[    1.402833] Cause : 00800008 (ExcCode 02)
[    1.406952] BadVA : 00000000
[    1.409913] PrId  : 0002a075 (Broadcom BMIPS4350)
[    1.414745] Modules linked in:
[    1.417895] Process swapper/0 (pid: 1, threadinfo=(ptrval), task=(ptrval), tls=00000000)
[    1.426214] Stack : 87cec000 80630000 80639370 80640658 80640000 80049af4 80639fe4 8063a0d8
[    1.434816]         8063a0d8 802ef078 00000002 00000000 806441d0 80b90000 8063a0d8 802ef114
[    1.443417]         87cea0de 87c1fde0 00000000 804de488 87cea000 8063a0d8 8063a0d8 80334e48
[    1.452018]         80640000 8063984c 80639bf4 00000000 8065de48 00000001 8063a0d8 80334ed0
[    1.460620]         806441d0 80b90000 80b90000 802ef164 8065dd70 80620000 80b90000 8065de58
[    1.469222]         ...
[    1.471734] Call Trace:
[    1.474255] [<804dd50c>] kset_find_obj+0x3c/0x114
[    1.479141] [<802ef078>] driver_find+0x1c/0x44
[    1.483665] [<802ef114>] driver_register+0x74/0x148
[    1.488719] [<80334e48>] phy_driver_register+0x9c/0xd0
[    1.493968] [<80334ed0>] phy_drivers_register+0x54/0xe8
[    1.499345] [<8001061c>] do_one_initcall+0x7c/0x1f4
[    1.504374] [<80644ed8>] kernel_init_freeable+0x1d4/0x2b4
[    1.509940] [<804f4e24>] kernel_init+0x10/0xf8
[    1.514502] [<80018e68>] ret_from_kernel_thread+0x14/0x1c
[    1.520040] Code: 1060000c  02202025  90650000 <90810000> 24630001  14250004  24840001  14a0fffb  90650000
[    1.530061]
[    1.531698] ---[ end trace d52f1717cd29bdc8 ]---

Fix it by readding the name.

Fixes: 719655a14971 ("net: phy: Replace phy driver features u32 with link_mode bitmap")
Signed-off-by: Jonas Gorski <jonas.gorski@gmail.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/bcm63xx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/phy/bcm63xx.c b/drivers/net/phy/bcm63xx.c
index 23f1958ba6ad..459fb2069c7e 100644
--- a/drivers/net/phy/bcm63xx.c
+++ b/drivers/net/phy/bcm63xx.c
@@ -73,6 +73,7 @@ static struct phy_driver bcm63xx_driver[] = {
 	/* same phy as above, with just a different OUI */
 	.phy_id		= 0x002bdc00,
 	.phy_id_mask	= 0xfffffc00,
+	.name		= "Broadcom BCM63XX (2)",
 	/* PHY_BASIC_FEATURES */
 	.flags		= PHY_IS_INTERNAL,
 	.config_init	= bcm63xx_config_init,
-- 
2.20.1


From 2e3d191ac9d344cb301d891da35c16c966ab7133 Mon Sep 17 00:00:00 2001
From: Karsten Graul <kgraul@linux.ibm.com>
Date: Tue, 10 Mar 2020 09:33:30 +0100
Subject: [PATCH 22/66] net/smc: cancel event worker during device removal

[ Upstream commit ece0d7bd74615773268475b6b64d6f1ebbd4b4c6 ]

During IB device removal, cancel the event worker before the device
structure is freed.

Fixes: a4cf0443c414 ("smc: introduce SMC as an IB-client")
Reported-by: syzbot+b297c6825752e7a07272@syzkaller.appspotmail.com
Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Reviewed-by: Ursula Braun <ubraun@linux.ibm.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/smc_ib.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index 548632621f4b..32fee2ca7c4c 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -580,6 +580,7 @@ static void smc_ib_remove_dev(struct ib_device *ibdev, void *client_data)
 	smc_smcr_terminate_all(smcibdev);
 	smc_ib_cleanup_per_ibdev(smcibdev);
 	ib_unregister_event_handler(&smcibdev->event_handler);
+	cancel_work_sync(&smcibdev->port_event_work);
 	kfree(smcibdev);
 }
 
-- 
2.20.1


From c0e5d3a6b4593f0d90f9614defd73ab8cf283ee0 Mon Sep 17 00:00:00 2001
From: Remi Pommarel <repk@triplefau.lt>
Date: Sun, 8 Mar 2020 10:25:56 +0100
Subject: [PATCH 23/66] net: stmmac: dwmac1000: Disable ACS if enhanced descs
 are not used

[ Upstream commit b723bd933980f4956dabc8a8d84b3e83be8d094c ]

ACS (auto PAD/FCS stripping) removes FCS off 802.3 packets (LLC) so that
there is no need to manually strip it for such packets. The enhanced DMA
descriptors allow to flag LLC packets so that the receiving callback can
use that to strip FCS manually or not. On the other hand, normal
descriptors do not support that.

Thus in order to not truncate LLC packet ACS should be disabled when
using normal DMA descriptors.

Fixes: 47dd7a540b8a0 ("net: add support for STMicroelectronics Ethernet controllers.")
Signed-off-by: Remi Pommarel <repk@triplefau.lt>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
index d0356fbd1e43..542784300620 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
@@ -24,6 +24,7 @@
 static void dwmac1000_core_init(struct mac_device_info *hw,
 				struct net_device *dev)
 {
+	struct stmmac_priv *priv = netdev_priv(dev);
 	void __iomem *ioaddr = hw->pcsr;
 	u32 value = readl(ioaddr + GMAC_CONTROL);
 	int mtu = dev->mtu;
@@ -35,7 +36,7 @@ static void dwmac1000_core_init(struct mac_device_info *hw,
 	 * Broadcom tags can look like invalid LLC/SNAP packets and cause the
 	 * hardware to truncate packets on reception.
 	 */
-	if (netdev_uses_dsa(dev))
+	if (netdev_uses_dsa(dev) || !priv->plat->enh_desc)
 		value &= ~GMAC_CONTROL_ACS;
 
 	if (mtu > 1500)
-- 
2.20.1


From 5dc4d40348ec95f3d6060399fb3555391f3d4cc3 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Thu, 12 Mar 2020 15:04:30 +0000
Subject: [PATCH 24/66] net: systemport: fix index check to avoid an array out
 of bounds access

[ Upstream commit c0368595c1639947839c0db8294ee96aca0b3b86 ]

Currently the bounds check on index is off by one and can lead to
an out of bounds access on array priv->filters_loc when index is
RXCHK_BRCM_TAG_MAX.

Fixes: bb9051a2b230 ("net: systemport: Add support for WAKE_FILTER")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bcmsysport.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index c1ae42244f02..5e322fe30b1d 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -2135,7 +2135,7 @@ static int bcm_sysport_rule_set(struct bcm_sysport_priv *priv,
 		return -ENOSPC;
 
 	index = find_first_zero_bit(priv->filters, RXCHK_BRCM_TAG_MAX);
-	if (index > RXCHK_BRCM_TAG_MAX)
+	if (index >= RXCHK_BRCM_TAG_MAX)
 		return -ENOSPC;
 
 	/* Location is the classification ID, and index is the position
-- 
2.20.1


From 61e64fa516edca6ba046de11c4b0f1cfb79963f3 Mon Sep 17 00:00:00 2001
From: You-Sheng Yang <vicamo.yang@canonical.com>
Date: Wed, 26 Feb 2020 23:37:10 +0800
Subject: [PATCH 25/66] r8152: check disconnect status after long sleep

[ Upstream commit d64c7a08034b32c285e576208ae44fc3ba3fa7df ]

Dell USB Type C docking WD19/WD19DC attaches additional peripherals as:

  /: Bus 02.Port 1: Dev 1, Class=root_hub, Driver=xhci_hcd/6p, 5000M
      |__ Port 1: Dev 11, If 0, Class=Hub, Driver=hub/4p, 5000M
          |__ Port 3: Dev 12, If 0, Class=Hub, Driver=hub/4p, 5000M
          |__ Port 4: Dev 13, If 0, Class=Vendor Specific Class,
              Driver=r8152, 5000M

where usb 2-1-3 is a hub connecting all USB Type-A/C ports on the dock.

When hotplugging such dock with additional usb devices already attached on
it, the probing process may reset usb 2.1 port, therefore r8152 ethernet
device is also reset. However, during r8152 device init there are several
for-loops that, when it's unable to retrieve hardware registers due to
being disconnected from USB, may take up to 14 seconds each in practice,
and that has to be completed before USB may re-enumerate devices on the
bus. As a result, devices attached to the dock will only be available
after nearly 1 minute after the dock was plugged in:

  [ 216.388290] [250] r8152 2-1.4:1.0: usb_probe_interface
  [ 216.388292] [250] r8152 2-1.4:1.0: usb_probe_interface - got id
  [ 258.830410] r8152 2-1.4:1.0 (unnamed net_device) (uninitialized): PHY not ready
  [ 258.830460] r8152 2-1.4:1.0 (unnamed net_device) (uninitialized): Invalid header when reading pass-thru MAC addr
  [ 258.830464] r8152 2-1.4:1.0 (unnamed net_device) (uninitialized): Get ether addr fail

This happens in, for example, r8153_init:

  static int generic_ocp_read(struct r8152 *tp, u16 index, u16 size,
			    void *data, u16 type)
  {
    if (test_bit(RTL8152_UNPLUG, &tp->flags))
      return -ENODEV;
    ...
  }

  static u16 ocp_read_word(struct r8152 *tp, u16 type, u16 index)
  {
    u32 data;
    ...
    generic_ocp_read(tp, index, sizeof(tmp), &tmp, type | byen);

    data = __le32_to_cpu(tmp);
    ...
    return (u16)data;
  }

  static void r8153_init(struct r8152 *tp)
  {
    ...
    if (test_bit(RTL8152_UNPLUG, &tp->flags))
      return;

    for (i = 0; i < 500; i++) {
      if (ocp_read_word(tp, MCU_TYPE_PLA, PLA_BOOT_CTRL) &
          AUTOLOAD_DONE)
        break;
      msleep(20);
    }
    ...
  }

Since ocp_read_word() doesn't check the return status of
generic_ocp_read(), and the only exit condition for the loop is to have
a match in the returned value, such loops will only ends after exceeding
its maximum runs when the device has been marked as disconnected, which
takes 500 * 20ms = 10 seconds in theory, 14 in practice.

To solve this long latency another test to RTL8152_UNPLUG flag should be
added after those 20ms sleep to skip unnecessary loops, so that the device
probe can complete early and proceed to parent port reset/reprobe process.

This can be reproduced on all kernel versions up to latest v5.6-rc2, but
after v5.5-rc7 the reproduce rate is dramatically lowered to 1/30 or less
while it was around 1/2.

Signed-off-by: You-Sheng Yang <vicamo.yang@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 3f425f974d03..e8e35c35fa96 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -3220,6 +3220,8 @@ static u16 r8153_phy_status(struct r8152 *tp, u16 desired)
 		}
 
 		msleep(20);
+		if (test_bit(RTL8152_UNPLUG, &tp->flags))
+			break;
 	}
 
 	return data;
@@ -5401,7 +5403,10 @@ static void r8153_init(struct r8152 *tp)
 		if (ocp_read_word(tp, MCU_TYPE_PLA, PLA_BOOT_CTRL) &
 		    AUTOLOAD_DONE)
 			break;
+
 		msleep(20);
+		if (test_bit(RTL8152_UNPLUG, &tp->flags))
+			break;
 	}
 
 	data = r8153_phy_status(tp, 0);
@@ -5538,7 +5543,10 @@ static void r8153b_init(struct r8152 *tp)
 		if (ocp_read_word(tp, MCU_TYPE_PLA, PLA_BOOT_CTRL) &
 		    AUTOLOAD_DONE)
 			break;
+
 		msleep(20);
+		if (test_bit(RTL8152_UNPLUG, &tp->flags))
+			break;
 	}
 
 	data = r8153_phy_status(tp, 0);
-- 
2.20.1


From 9995073eb57a72bbf104e897435838d9c47d0b90 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Mon, 9 Mar 2020 18:16:24 +0000
Subject: [PATCH 26/66] sfc: detach from cb_page in efx_copy_channel()

[ Upstream commit 4b1bd9db078f7d5332c8601a2f5bd43cf0458fd4 ]

It's a resource, not a parameter, so we can't copy it into the new
 channel's TX queues, otherwise aliasing will lead to resource-
 management bugs if the channel is subsequently torn down without
 being initialised.

Before the Fixes:-tagged commit there was a similar bug with
 tsoh_page, but I'm not sure it's worth doing another fix for such
 old kernels.

Fixes: e9117e5099ea ("sfc: Firmware-Assisted TSO version 2")
Suggested-by: Derek Shute <Derek.Shute@stratus.com>
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/efx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 7a38d7f282a1..bc6c7f3f804d 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -525,6 +525,7 @@ efx_copy_channel(const struct efx_channel *old_channel)
 		if (tx_queue->channel)
 			tx_queue->channel = channel;
 		tx_queue->buffer = NULL;
+		tx_queue->cb_page = NULL;
 		memset(&tx_queue->txd, 0, sizeof(tx_queue->txd));
 	}
 
-- 
2.20.1


From 8f01de27f43726d6a1482a345ec68dcb134058d5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 4 Mar 2020 15:51:43 -0800
Subject: [PATCH 27/66] slip: make slhc_compress() more robust against
 malicious packets

[ Upstream commit 110a40dfb708fe940a3f3704d470e431c368d256 ]

Before accessing various fields in IPV4 network header
and TCP header, make sure the packet :

- Has IP version 4 (ip->version == 4)
- Has not a silly network length (ip->ihl >= 5)
- Is big enough to hold network and transport headers
- Has not a silly TCP header size (th->doff >= sizeof(struct tcphdr) / 4)

syzbot reported :

BUG: KMSAN: uninit-value in slhc_compress+0x5b9/0x2e60 drivers/net/slip/slhc.c:270
CPU: 0 PID: 11728 Comm: syz-executor231 Not tainted 5.6.0-rc2-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c9/0x220 lib/dump_stack.c:118
 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:118
 __msan_warning+0x58/0xa0 mm/kmsan/kmsan_instr.c:215
 slhc_compress+0x5b9/0x2e60 drivers/net/slip/slhc.c:270
 ppp_send_frame drivers/net/ppp/ppp_generic.c:1637 [inline]
 __ppp_xmit_process+0x1902/0x2970 drivers/net/ppp/ppp_generic.c:1495
 ppp_xmit_process+0x147/0x2f0 drivers/net/ppp/ppp_generic.c:1516
 ppp_write+0x6bb/0x790 drivers/net/ppp/ppp_generic.c:512
 do_loop_readv_writev fs/read_write.c:717 [inline]
 do_iter_write+0x812/0xdc0 fs/read_write.c:1000
 compat_writev+0x2df/0x5a0 fs/read_write.c:1351
 do_compat_pwritev64 fs/read_write.c:1400 [inline]
 __do_compat_sys_pwritev fs/read_write.c:1420 [inline]
 __se_compat_sys_pwritev fs/read_write.c:1414 [inline]
 __ia32_compat_sys_pwritev+0x349/0x3f0 fs/read_write.c:1414
 do_syscall_32_irqs_on arch/x86/entry/common.c:339 [inline]
 do_fast_syscall_32+0x3c7/0x6e0 arch/x86/entry/common.c:410
 entry_SYSENTER_compat+0x68/0x77 arch/x86/entry/entry_64_compat.S:139
RIP: 0023:0xf7f7cd99
Code: 90 e8 0b 00 00 00 f3 90 0f ae e8 eb f9 8d 74 26 00 89 3c 24 c3 90 90 90 90 90 90 90 90 90 90 90 90 51 52 55 89 e5 0f 34 cd 80 <5d> 5a 59 c3 90 90 90 90 eb 0d 90 90 90 90 90 90 90 90 90 90 90 90
RSP: 002b:00000000ffdb84ac EFLAGS: 00000217 ORIG_RAX: 000000000000014e
RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00000000200001c0
RDX: 0000000000000001 RSI: 0000000000000000 RDI: 0000000000000003
RBP: 0000000040047459 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000

Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:144 [inline]
 kmsan_internal_poison_shadow+0x66/0xd0 mm/kmsan/kmsan.c:127
 kmsan_slab_alloc+0x8a/0xe0 mm/kmsan/kmsan_hooks.c:82
 slab_alloc_node mm/slub.c:2793 [inline]
 __kmalloc_node_track_caller+0xb40/0x1200 mm/slub.c:4401
 __kmalloc_reserve net/core/skbuff.c:142 [inline]
 __alloc_skb+0x2fd/0xac0 net/core/skbuff.c:210
 alloc_skb include/linux/skbuff.h:1051 [inline]
 ppp_write+0x115/0x790 drivers/net/ppp/ppp_generic.c:500
 do_loop_readv_writev fs/read_write.c:717 [inline]
 do_iter_write+0x812/0xdc0 fs/read_write.c:1000
 compat_writev+0x2df/0x5a0 fs/read_write.c:1351
 do_compat_pwritev64 fs/read_write.c:1400 [inline]
 __do_compat_sys_pwritev fs/read_write.c:1420 [inline]
 __se_compat_sys_pwritev fs/read_write.c:1414 [inline]
 __ia32_compat_sys_pwritev+0x349/0x3f0 fs/read_write.c:1414
 do_syscall_32_irqs_on arch/x86/entry/common.c:339 [inline]
 do_fast_syscall_32+0x3c7/0x6e0 arch/x86/entry/common.c:410
 entry_SYSENTER_compat+0x68/0x77 arch/x86/entry/entry_64_compat.S:139

Fixes: b5451d783ade ("slip: Move the SLIP drivers")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/slip/slhc.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/net/slip/slhc.c b/drivers/net/slip/slhc.c
index 58a69f830d29..f78ceba42e57 100644
--- a/drivers/net/slip/slhc.c
+++ b/drivers/net/slip/slhc.c
@@ -232,7 +232,7 @@ slhc_compress(struct slcompress *comp, unsigned char *icp, int isize,
 	struct cstate *cs = lcs->next;
 	unsigned long deltaS, deltaA;
 	short changes = 0;
-	int hlen;
+	int nlen, hlen;
 	unsigned char new_seq[16];
 	unsigned char *cp = new_seq;
 	struct iphdr *ip;
@@ -248,6 +248,8 @@ slhc_compress(struct slcompress *comp, unsigned char *icp, int isize,
 		return isize;
 
 	ip = (struct iphdr *) icp;
+	if (ip->version != 4 || ip->ihl < 5)
+		return isize;
 
 	/* Bail if this packet isn't TCP, or is an IP fragment */
 	if (ip->protocol != IPPROTO_TCP || (ntohs(ip->frag_off) & 0x3fff)) {
@@ -258,10 +260,14 @@ slhc_compress(struct slcompress *comp, unsigned char *icp, int isize,
 			comp->sls_o_tcp++;
 		return isize;
 	}
-	/* Extract TCP header */
+	nlen = ip->ihl * 4;
+	if (isize < nlen + sizeof(*th))
+		return isize;
 
-	th = (struct tcphdr *)(((unsigned char *)ip) + ip->ihl*4);
-	hlen = ip->ihl*4 + th->doff*4;
+	th = (struct tcphdr *)(icp + nlen);
+	if (th->doff < sizeof(struct tcphdr) / 4)
+		return isize;
+	hlen = nlen + th->doff * 4;
 
 	/*  Bail if the TCP packet isn't `compressible' (i.e., ACK isn't set or
 	 *  some other control bit is set). Also uncompressible if
-- 
2.20.1


From 59cd5d09c898d861a1c91be1869e6927da3dd2bd Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Mon, 9 Mar 2020 10:39:53 -0700
Subject: [PATCH 28/66] taprio: Fix sending packets without dequeueing them

[ Upstream commit b09fe70ef520e011ba4a64f4b93f948a8f14717b ]

There was a bug that was causing packets to be sent to the driver
without first calling dequeue() on the "child" qdisc. And the KASAN
report below shows that sending a packet without calling dequeue()
leads to bad results.

The problem is that when checking the last qdisc "child" we do not set
the returned skb to NULL, which can cause it to be sent to the driver,
and so after the skb is sent, it may be freed, and in some situations a
reference to it may still be in the child qdisc, because it was never
dequeued.

The crash log looks like this:

[   19.937538] ==================================================================
[   19.938300] BUG: KASAN: use-after-free in taprio_dequeue_soft+0x620/0x780
[   19.938968] Read of size 4 at addr ffff8881128628cc by task swapper/1/0
[   19.939612]
[   19.939772] CPU: 1 PID: 0 Comm: swapper/1 Not tainted 5.6.0-rc3+ #97
[   19.940397] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qe4
[   19.941523] Call Trace:
[   19.941774]  <IRQ>
[   19.941985]  dump_stack+0x97/0xe0
[   19.942323]  print_address_description.constprop.0+0x3b/0x60
[   19.942884]  ? taprio_dequeue_soft+0x620/0x780
[   19.943325]  ? taprio_dequeue_soft+0x620/0x780
[   19.943767]  __kasan_report.cold+0x1a/0x32
[   19.944173]  ? taprio_dequeue_soft+0x620/0x780
[   19.944612]  kasan_report+0xe/0x20
[   19.944954]  taprio_dequeue_soft+0x620/0x780
[   19.945380]  __qdisc_run+0x164/0x18d0
[   19.945749]  net_tx_action+0x2c4/0x730
[   19.946124]  __do_softirq+0x268/0x7bc
[   19.946491]  irq_exit+0x17d/0x1b0
[   19.946824]  smp_apic_timer_interrupt+0xeb/0x380
[   19.947280]  apic_timer_interrupt+0xf/0x20
[   19.947687]  </IRQ>
[   19.947912] RIP: 0010:default_idle+0x2d/0x2d0
[   19.948345] Code: 00 00 41 56 41 55 65 44 8b 2d 3f 8d 7c 7c 41 54 55 53 0f 1f 44 00 00 e8 b1 b2 c5 fd e9 07 00 3
[   19.950166] RSP: 0018:ffff88811a3efda0 EFLAGS: 00000282 ORIG_RAX: ffffffffffffff13
[   19.950909] RAX: 0000000080000000 RBX: ffff88811a3a9600 RCX: ffffffff8385327e
[   19.951608] RDX: 1ffff110234752c0 RSI: 0000000000000000 RDI: ffffffff8385262f
[   19.952309] RBP: ffffed10234752c0 R08: 0000000000000001 R09: ffffed10234752c1
[   19.953009] R10: ffffed10234752c0 R11: ffff88811a3a9607 R12: 0000000000000001
[   19.953709] R13: 0000000000000001 R14: 0000000000000000 R15: 0000000000000000
[   19.954408]  ? default_idle_call+0x2e/0x70
[   19.954816]  ? default_idle+0x1f/0x2d0
[   19.955192]  default_idle_call+0x5e/0x70
[   19.955584]  do_idle+0x3d4/0x500
[   19.955909]  ? arch_cpu_idle_exit+0x40/0x40
[   19.956325]  ? _raw_spin_unlock_irqrestore+0x23/0x30
[   19.956829]  ? trace_hardirqs_on+0x30/0x160
[   19.957242]  cpu_startup_entry+0x19/0x20
[   19.957633]  start_secondary+0x2a6/0x380
[   19.958026]  ? set_cpu_sibling_map+0x18b0/0x18b0
[   19.958486]  secondary_startup_64+0xa4/0xb0
[   19.958921]
[   19.959078] Allocated by task 33:
[   19.959412]  save_stack+0x1b/0x80
[   19.959747]  __kasan_kmalloc.constprop.0+0xc2/0xd0
[   19.960222]  kmem_cache_alloc+0xe4/0x230
[   19.960617]  __alloc_skb+0x91/0x510
[   19.960967]  ndisc_alloc_skb+0x133/0x330
[   19.961358]  ndisc_send_ns+0x134/0x810
[   19.961735]  addrconf_dad_work+0xad5/0xf80
[   19.962144]  process_one_work+0x78e/0x13a0
[   19.962551]  worker_thread+0x8f/0xfa0
[   19.962919]  kthread+0x2ba/0x3b0
[   19.963242]  ret_from_fork+0x3a/0x50
[   19.963596]
[   19.963753] Freed by task 33:
[   19.964055]  save_stack+0x1b/0x80
[   19.964386]  __kasan_slab_free+0x12f/0x180
[   19.964830]  kmem_cache_free+0x80/0x290
[   19.965231]  ip6_mc_input+0x38a/0x4d0
[   19.965617]  ipv6_rcv+0x1a4/0x1d0
[   19.965948]  __netif_receive_skb_one_core+0xf2/0x180
[   19.966437]  netif_receive_skb+0x8c/0x3c0
[   19.966846]  br_handle_frame_finish+0x779/0x1310
[   19.967302]  br_handle_frame+0x42a/0x830
[   19.967694]  __netif_receive_skb_core+0xf0e/0x2a90
[   19.968167]  __netif_receive_skb_one_core+0x96/0x180
[   19.968658]  process_backlog+0x198/0x650
[   19.969047]  net_rx_action+0x2fa/0xaa0
[   19.969420]  __do_softirq+0x268/0x7bc
[   19.969785]
[   19.969940] The buggy address belongs to the object at ffff888112862840
[   19.969940]  which belongs to the cache skbuff_head_cache of size 224
[   19.971202] The buggy address is located 140 bytes inside of
[   19.971202]  224-byte region [ffff888112862840, ffff888112862920)
[   19.972344] The buggy address belongs to the page:
[   19.972820] page:ffffea00044a1800 refcount:1 mapcount:0 mapping:ffff88811a2bd1c0 index:0xffff8881128625c0 compo0
[   19.973930] flags: 0x8000000000010200(slab|head)
[   19.974388] raw: 8000000000010200 ffff88811a2ed650 ffff88811a2ed650 ffff88811a2bd1c0
[   19.975151] raw: ffff8881128625c0 0000000000190013 00000001ffffffff 0000000000000000
[   19.975915] page dumped because: kasan: bad access detected
[   19.976461] page_owner tracks the page as allocated
[   19.976946] page last allocated via order 2, migratetype Unmovable, gfp_mask 0xd20c0(__GFP_IO|__GFP_FS|__GFP_NO)
[   19.978332]  prep_new_page+0x24b/0x330
[   19.978707]  get_page_from_freelist+0x2057/0x2c90
[   19.979170]  __alloc_pages_nodemask+0x218/0x590
[   19.979619]  new_slab+0x9d/0x300
[   19.979948]  ___slab_alloc.constprop.0+0x2f9/0x6f0
[   19.980421]  __slab_alloc.constprop.0+0x30/0x60
[   19.980870]  kmem_cache_alloc+0x201/0x230
[   19.981269]  __alloc_skb+0x91/0x510
[   19.981620]  alloc_skb_with_frags+0x78/0x4a0
[   19.982043]  sock_alloc_send_pskb+0x5eb/0x750
[   19.982476]  unix_stream_sendmsg+0x399/0x7f0
[   19.982904]  sock_sendmsg+0xe2/0x110
[   19.983262]  ____sys_sendmsg+0x4de/0x6d0
[   19.983660]  ___sys_sendmsg+0xe4/0x160
[   19.984032]  __sys_sendmsg+0xab/0x130
[   19.984396]  do_syscall_64+0xe7/0xae0
[   19.984761] page last free stack trace:
[   19.985142]  __free_pages_ok+0x432/0xbc0
[   19.985533]  qlist_free_all+0x56/0xc0
[   19.985907]  quarantine_reduce+0x149/0x170
[   19.986315]  __kasan_kmalloc.constprop.0+0x9e/0xd0
[   19.986791]  kmem_cache_alloc+0xe4/0x230
[   19.987182]  prepare_creds+0x24/0x440
[   19.987548]  do_faccessat+0x80/0x590
[   19.987906]  do_syscall_64+0xe7/0xae0
[   19.988276]  entry_SYSCALL_64_after_hwframe+0x49/0xbe
[   19.988775]
[   19.988930] Memory state around the buggy address:
[   19.989402]  ffff888112862780: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[   19.990111]  ffff888112862800: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb
[   19.990822] >ffff888112862880: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[   19.991529]                                               ^
[   19.992081]  ffff888112862900: fb fb fb fb fc fc fc fc fc fc fc fc fc fc fc fc
[   19.992796]  ffff888112862980: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc

Fixes: 5a781ccbd19e ("tc: Add support for configuring the taprio scheduler")
Reported-by: Michael Schmidt <michael.schmidt@eti.uni-siegen.de>
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Acked-by: Andre Guedes <andre.guedes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_taprio.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 660fc45ee40f..437e333a4a33 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -564,8 +564,10 @@ static struct sk_buff *taprio_dequeue_soft(struct Qdisc *sch)
 		prio = skb->priority;
 		tc = netdev_get_prio_tc_map(dev, prio);
 
-		if (!(gate_mask & BIT(tc)))
+		if (!(gate_mask & BIT(tc))) {
+			skb = NULL;
 			continue;
+		}
 
 		len = qdisc_pkt_len(skb);
 		guard = ktime_add_ns(taprio_get_time(q),
@@ -575,13 +577,17 @@ static struct sk_buff *taprio_dequeue_soft(struct Qdisc *sch)
 		 * guard band ...
 		 */
 		if (gate_mask != TAPRIO_ALL_GATES_OPEN &&
-		    ktime_after(guard, entry->close_time))
+		    ktime_after(guard, entry->close_time)) {
+			skb = NULL;
 			continue;
+		}
 
 		/* ... and no budget. */
 		if (gate_mask != TAPRIO_ALL_GATES_OPEN &&
-		    atomic_sub_return(len, &entry->budget) < 0)
+		    atomic_sub_return(len, &entry->budget) < 0) {
+			skb = NULL;
 			continue;
+		}
 
 		skb = child->ops->dequeue(child);
 		if (unlikely(!skb))
-- 
2.20.1


From 5aa7562ef0332414da9549c1931a4bad5b5ddc70 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 4 Mar 2020 09:32:16 -0800
Subject: [PATCH 29/66] bonding/alb: make sure arp header is pulled before
 accessing it

Similar to commit 38f88c454042 ("bonding/alb: properly access headers
in bond_alb_xmit()"), we need to make sure arp header was pulled
in skb->head before blindly accessing it in rlb_arp_xmit().

Remove arp_pkt() private helper, since it is more readable/obvious
to have the following construct back to back :

	if (!pskb_network_may_pull(skb, sizeof(*arp)))
		return NULL;
	arp = (struct arp_pkt *)skb_network_header(skb);

syzbot reported :

BUG: KMSAN: uninit-value in bond_slave_has_mac_rx include/net/bonding.h:704 [inline]
BUG: KMSAN: uninit-value in rlb_arp_xmit drivers/net/bonding/bond_alb.c:662 [inline]
BUG: KMSAN: uninit-value in bond_alb_xmit+0x575/0x25e0 drivers/net/bonding/bond_alb.c:1477
CPU: 0 PID: 12743 Comm: syz-executor.4 Not tainted 5.6.0-rc2-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c9/0x220 lib/dump_stack.c:118
 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:118
 __msan_warning+0x58/0xa0 mm/kmsan/kmsan_instr.c:215
 bond_slave_has_mac_rx include/net/bonding.h:704 [inline]
 rlb_arp_xmit drivers/net/bonding/bond_alb.c:662 [inline]
 bond_alb_xmit+0x575/0x25e0 drivers/net/bonding/bond_alb.c:1477
 __bond_start_xmit drivers/net/bonding/bond_main.c:4257 [inline]
 bond_start_xmit+0x85d/0x2f70 drivers/net/bonding/bond_main.c:4282
 __netdev_start_xmit include/linux/netdevice.h:4524 [inline]
 netdev_start_xmit include/linux/netdevice.h:4538 [inline]
 xmit_one net/core/dev.c:3470 [inline]
 dev_hard_start_xmit+0x531/0xab0 net/core/dev.c:3486
 __dev_queue_xmit+0x37de/0x4220 net/core/dev.c:4063
 dev_queue_xmit+0x4b/0x60 net/core/dev.c:4096
 packet_snd net/packet/af_packet.c:2967 [inline]
 packet_sendmsg+0x8347/0x93b0 net/packet/af_packet.c:2992
 sock_sendmsg_nosec net/socket.c:652 [inline]
 sock_sendmsg net/socket.c:672 [inline]
 __sys_sendto+0xc1b/0xc50 net/socket.c:1998
 __do_sys_sendto net/socket.c:2010 [inline]
 __se_sys_sendto+0x107/0x130 net/socket.c:2006
 __x64_sys_sendto+0x6e/0x90 net/socket.c:2006
 do_syscall_64+0xb8/0x160 arch/x86/entry/common.c:296
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x45c479
Code: ad b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007fc77ffbbc78 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 00007fc77ffbc6d4 RCX: 000000000045c479
RDX: 000000000000000e RSI: 00000000200004c0 RDI: 0000000000000003
RBP: 000000000076bf20 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff
R13: 0000000000000a04 R14: 00000000004cc7b0 R15: 000000000076bf2c

Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:144 [inline]
 kmsan_internal_poison_shadow+0x66/0xd0 mm/kmsan/kmsan.c:127
 kmsan_slab_alloc+0x8a/0xe0 mm/kmsan/kmsan_hooks.c:82
 slab_alloc_node mm/slub.c:2793 [inline]
 __kmalloc_node_track_caller+0xb40/0x1200 mm/slub.c:4401
 __kmalloc_reserve net/core/skbuff.c:142 [inline]
 __alloc_skb+0x2fd/0xac0 net/core/skbuff.c:210
 alloc_skb include/linux/skbuff.h:1051 [inline]
 alloc_skb_with_frags+0x18c/0xa70 net/core/skbuff.c:5766
 sock_alloc_send_pskb+0xada/0xc60 net/core/sock.c:2242
 packet_alloc_skb net/packet/af_packet.c:2815 [inline]
 packet_snd net/packet/af_packet.c:2910 [inline]
 packet_sendmsg+0x66a0/0x93b0 net/packet/af_packet.c:2992
 sock_sendmsg_nosec net/socket.c:652 [inline]
 sock_sendmsg net/socket.c:672 [inline]
 __sys_sendto+0xc1b/0xc50 net/socket.c:1998
 __do_sys_sendto net/socket.c:2010 [inline]
 __se_sys_sendto+0x107/0x130 net/socket.c:2006
 __x64_sys_sendto+0x6e/0x90 net/socket.c:2006
 do_syscall_64+0xb8/0x160 arch/x86/entry/common.c:296
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Cc: Veaceslav Falico <vfalico@gmail.com>
Cc: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_alb.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 1cc2cd894f87..c81698550e5a 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -50,11 +50,6 @@ struct arp_pkt {
 };
 #pragma pack()
 
-static inline struct arp_pkt *arp_pkt(const struct sk_buff *skb)
-{
-	return (struct arp_pkt *)skb_network_header(skb);
-}
-
 /* Forward declaration */
 static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[],
 				      bool strict_match);
@@ -553,10 +548,11 @@ static void rlb_req_update_subnet_clients(struct bonding *bond, __be32 src_ip)
 	spin_unlock(&bond->mode_lock);
 }
 
-static struct slave *rlb_choose_channel(struct sk_buff *skb, struct bonding *bond)
+static struct slave *rlb_choose_channel(struct sk_buff *skb,
+					struct bonding *bond,
+					const struct arp_pkt *arp)
 {
 	struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond));
-	struct arp_pkt *arp = arp_pkt(skb);
 	struct slave *assigned_slave, *curr_active_slave;
 	struct rlb_client_info *client_info;
 	u32 hash_index = 0;
@@ -653,8 +649,12 @@ static struct slave *rlb_choose_channel(struct sk_buff *skb, struct bonding *bon
  */
 static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond)
 {
-	struct arp_pkt *arp = arp_pkt(skb);
 	struct slave *tx_slave = NULL;
+	struct arp_pkt *arp;
+
+	if (!pskb_network_may_pull(skb, sizeof(*arp)))
+		return NULL;
+	arp = (struct arp_pkt *)skb_network_header(skb);
 
 	/* Don't modify or load balance ARPs that do not originate locally
 	 * (e.g.,arrive via a bridge).
@@ -664,7 +664,7 @@ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond)
 
 	if (arp->op_code == htons(ARPOP_REPLY)) {
 		/* the arp must be sent on the selected rx channel */
-		tx_slave = rlb_choose_channel(skb, bond);
+		tx_slave = rlb_choose_channel(skb, bond, arp);
 		if (tx_slave)
 			bond_hw_addr_copy(arp->mac_src, tx_slave->dev->dev_addr,
 					  tx_slave->dev->addr_len);
@@ -676,7 +676,7 @@ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond)
 		 * When the arp reply is received the entry will be updated
 		 * with the correct unicast address of the client.
 		 */
-		tx_slave = rlb_choose_channel(skb, bond);
+		tx_slave = rlb_choose_channel(skb, bond, arp);
 
 		/* The ARP reply packets must be delayed so that
 		 * they can cancel out the influence of the ARP request.
-- 
2.20.1


From ffc946c9e02bc54d5c4fd1ee0320f29805544792 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Sun, 1 Mar 2020 22:07:17 -0500
Subject: [PATCH 30/66] bnxt_en: reinitialize IRQs when MTU is modified

[ Upstream commit a9b952d267e59a3b405e644930f46d252cea7122 ]

MTU changes may affect the number of IRQs so we must call
bnxt_close_nic()/bnxt_open_nic() with the irq_re_init parameter
set to true.  The reason is that a larger MTU may require
aggregation rings not needed with smaller MTU.  We may not be
able to allocate the required number of aggregation rings and
so we reduce the number of channels which will change the number
of IRQs.  Without this patch, it may crash eventually in
pci_disable_msix() when the IRQs are not properly unwound.

Fixes: c0c050c58d84 ("bnxt_en: New Broadcom ethernet driver.")
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index cc86038b1d96..05da27a64d55 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -10973,13 +10973,13 @@ static int bnxt_change_mtu(struct net_device *dev, int new_mtu)
 	struct bnxt *bp = netdev_priv(dev);
 
 	if (netif_running(dev))
-		bnxt_close_nic(bp, false, false);
+		bnxt_close_nic(bp, true, false);
 
 	dev->mtu = new_mtu;
 	bnxt_set_ring_params(bp);
 
 	if (netif_running(dev))
-		return bnxt_open_nic(bp, false, false);
+		return bnxt_open_nic(bp, true, false);
 
 	return 0;
 }
-- 
2.20.1


From 9ea6dab4aa91fc0c79dfa85f3d2e293279b0851a Mon Sep 17 00:00:00 2001
From: Edwin Peer <edwin.peer@broadcom.com>
Date: Sun, 1 Mar 2020 22:07:18 -0500
Subject: [PATCH 31/66] bnxt_en: fix error handling when flashing from file

[ Upstream commit 22630e28f9c2b55abd217869cc0696def89f2284 ]

After bnxt_hwrm_do_send_message() was updated to return standard error
codes in a recent commit, a regression in bnxt_flash_package_from_file()
was introduced.  The return value does not properly reflect all
possible firmware errors when calling firmware to flash the package.

Fix it by consolidating all errors in one local variable rc instead
of having 2 variables for different errors.

Fixes: d4f1420d3656 ("bnxt_en: Convert error code in firmware message response to standard code.")
Signed-off-by: Edwin Peer <edwin.peer@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 24 +++++++++----------
 1 file changed, 11 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 08d56ec7b68a..972383aefc2b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -2007,8 +2007,8 @@ int bnxt_flash_package_from_file(struct net_device *dev, const char *filename,
 	struct hwrm_nvm_install_update_output *resp = bp->hwrm_cmd_resp_addr;
 	struct hwrm_nvm_install_update_input install = {0};
 	const struct firmware *fw;
-	int rc, hwrm_err = 0;
 	u32 item_len;
+	int rc = 0;
 	u16 index;
 
 	bnxt_hwrm_fw_set_time(bp);
@@ -2052,15 +2052,14 @@ int bnxt_flash_package_from_file(struct net_device *dev, const char *filename,
 			memcpy(kmem, fw->data, fw->size);
 			modify.host_src_addr = cpu_to_le64(dma_handle);
 
-			hwrm_err = hwrm_send_message(bp, &modify,
-						     sizeof(modify),
-						     FLASH_PACKAGE_TIMEOUT);
+			rc = hwrm_send_message(bp, &modify, sizeof(modify),
+					       FLASH_PACKAGE_TIMEOUT);
 			dma_free_coherent(&bp->pdev->dev, fw->size, kmem,
 					  dma_handle);
 		}
 	}
 	release_firmware(fw);
-	if (rc || hwrm_err)
+	if (rc)
 		goto err_exit;
 
 	if ((install_type & 0xffff) == 0)
@@ -2069,20 +2068,19 @@ int bnxt_flash_package_from_file(struct net_device *dev, const char *filename,
 	install.install_type = cpu_to_le32(install_type);
 
 	mutex_lock(&bp->hwrm_cmd_lock);
-	hwrm_err = _hwrm_send_message(bp, &install, sizeof(install),
-				      INSTALL_PACKAGE_TIMEOUT);
-	if (hwrm_err) {
+	rc = _hwrm_send_message(bp, &install, sizeof(install),
+				INSTALL_PACKAGE_TIMEOUT);
+	if (rc) {
 		u8 error_code = ((struct hwrm_err_output *)resp)->cmd_err;
 
 		if (resp->error_code && error_code ==
 		    NVM_INSTALL_UPDATE_CMD_ERR_CODE_FRAG_ERR) {
 			install.flags |= cpu_to_le16(
 			       NVM_INSTALL_UPDATE_REQ_FLAGS_ALLOWED_TO_DEFRAG);
-			hwrm_err = _hwrm_send_message(bp, &install,
-						      sizeof(install),
-						      INSTALL_PACKAGE_TIMEOUT);
+			rc = _hwrm_send_message(bp, &install, sizeof(install),
+						INSTALL_PACKAGE_TIMEOUT);
 		}
-		if (hwrm_err)
+		if (rc)
 			goto flash_pkg_exit;
 	}
 
@@ -2094,7 +2092,7 @@ int bnxt_flash_package_from_file(struct net_device *dev, const char *filename,
 flash_pkg_exit:
 	mutex_unlock(&bp->hwrm_cmd_lock);
 err_exit:
-	if (hwrm_err == -EACCES)
+	if (rc == -EACCES)
 		bnxt_print_admin_err(bp);
 	return rc;
 }
-- 
2.20.1


From 40181a49b443f3355027e186cd40e5c2bf079f80 Mon Sep 17 00:00:00 2001
From: Shakeel Butt <shakeelb@google.com>
Date: Mon, 9 Mar 2020 22:16:05 -0700
Subject: [PATCH 32/66] cgroup: memcg: net: do not associate sock with
 unrelated cgroup

[ Upstream commit e876ecc67db80dfdb8e237f71e5b43bb88ae549c ]

We are testing network memory accounting in our setup and noticed
inconsistent network memory usage and often unrelated cgroups network
usage correlates with testing workload. On further inspection, it
seems like mem_cgroup_sk_alloc() and cgroup_sk_alloc() are broken in
irq context specially for cgroup v1.

mem_cgroup_sk_alloc() and cgroup_sk_alloc() can be called in irq context
and kind of assumes that this can only happen from sk_clone_lock()
and the source sock object has already associated cgroup. However in
cgroup v1, where network memory accounting is opt-in, the source sock
can be unassociated with any cgroup and the new cloned sock can get
associated with unrelated interrupted cgroup.

Cgroup v2 can also suffer if the source sock object was created by
process in the root cgroup or if sk_alloc() is called in irq context.
The fix is to just do nothing in interrupt.

WARNING: Please note that about half of the TCP sockets are allocated
from the IRQ context, so, memory used by such sockets will not be
accouted by the memcg.

The stack trace of mem_cgroup_sk_alloc() from IRQ-context:

CPU: 70 PID: 12720 Comm: ssh Tainted:  5.6.0-smp-DEV #1
Hardware name: ...
Call Trace:
 <IRQ>
 dump_stack+0x57/0x75
 mem_cgroup_sk_alloc+0xe9/0xf0
 sk_clone_lock+0x2a7/0x420
 inet_csk_clone_lock+0x1b/0x110
 tcp_create_openreq_child+0x23/0x3b0
 tcp_v6_syn_recv_sock+0x88/0x730
 tcp_check_req+0x429/0x560
 tcp_v6_rcv+0x72d/0xa40
 ip6_protocol_deliver_rcu+0xc9/0x400
 ip6_input+0x44/0xd0
 ? ip6_protocol_deliver_rcu+0x400/0x400
 ip6_rcv_finish+0x71/0x80
 ipv6_rcv+0x5b/0xe0
 ? ip6_sublist_rcv+0x2e0/0x2e0
 process_backlog+0x108/0x1e0
 net_rx_action+0x26b/0x460
 __do_softirq+0x104/0x2a6
 do_softirq_own_stack+0x2a/0x40
 </IRQ>
 do_softirq.part.19+0x40/0x50
 __local_bh_enable_ip+0x51/0x60
 ip6_finish_output2+0x23d/0x520
 ? ip6table_mangle_hook+0x55/0x160
 __ip6_finish_output+0xa1/0x100
 ip6_finish_output+0x30/0xd0
 ip6_output+0x73/0x120
 ? __ip6_finish_output+0x100/0x100
 ip6_xmit+0x2e3/0x600
 ? ipv6_anycast_cleanup+0x50/0x50
 ? inet6_csk_route_socket+0x136/0x1e0
 ? skb_free_head+0x1e/0x30
 inet6_csk_xmit+0x95/0xf0
 __tcp_transmit_skb+0x5b4/0xb20
 __tcp_send_ack.part.60+0xa3/0x110
 tcp_send_ack+0x1d/0x20
 tcp_rcv_state_process+0xe64/0xe80
 ? tcp_v6_connect+0x5d1/0x5f0
 tcp_v6_do_rcv+0x1b1/0x3f0
 ? tcp_v6_do_rcv+0x1b1/0x3f0
 __release_sock+0x7f/0xd0
 release_sock+0x30/0xa0
 __inet_stream_connect+0x1c3/0x3b0
 ? prepare_to_wait+0xb0/0xb0
 inet_stream_connect+0x3b/0x60
 __sys_connect+0x101/0x120
 ? __sys_getsockopt+0x11b/0x140
 __x64_sys_connect+0x1a/0x20
 do_syscall_64+0x51/0x200
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

The stack trace of mem_cgroup_sk_alloc() from IRQ-context:
Fixes: 2d7580738345 ("mm: memcontrol: consolidate cgroup socket tracking")
Fixes: d979a39d7242 ("cgroup: duplicate cgroup reference when cloning sockets")
Signed-off-by: Shakeel Butt <shakeelb@google.com>
Reviewed-by: Roman Gushchin <guro@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 kernel/cgroup/cgroup.c | 4 ++++
 mm/memcontrol.c        | 4 ++++
 2 files changed, 8 insertions(+)

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 30892c4759b4..0afe325982c7 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -6263,6 +6263,10 @@ void cgroup_sk_alloc(struct sock_cgroup_data *skcd)
 		return;
 	}
 
+	/* Don't associate the sock with unrelated interrupted task's cgroup. */
+	if (in_interrupt())
+		return;
+
 	rcu_read_lock();
 
 	while (true) {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index eda490113372..f89598436dec 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -6697,6 +6697,10 @@ void mem_cgroup_sk_alloc(struct sock *sk)
 		return;
 	}
 
+	/* Do not associate the sock with unrelated interrupted task's memcg. */
+	if (in_interrupt())
+		return;
+
 	rcu_read_lock();
 	memcg = mem_cgroup_from_task(current);
 	if (memcg == root_mem_cgroup)
-- 
2.20.1


From afe74643dcd7ae01670583ccb221f01ff99595bd Mon Sep 17 00:00:00 2001
From: Shakeel Butt <shakeelb@google.com>
Date: Mon, 9 Mar 2020 22:16:06 -0700
Subject: [PATCH 33/66] net: memcg: late association of sock to memcg

[ Upstream commit d752a4986532cb6305dfd5290a614cde8072769d ]

If a TCP socket is allocated in IRQ context or cloned from unassociated
(i.e. not associated to a memcg) in IRQ context then it will remain
unassociated for its whole life. Almost half of the TCPs created on the
system are created in IRQ context, so, memory used by such sockets will
not be accounted by the memcg.

This issue is more widespread in cgroup v1 where network memory
accounting is opt-in but it can happen in cgroup v2 if the source socket
for the cloning was created in root memcg.

To fix the issue, just do the association of the sockets at the accept()
time in the process context and then force charge the memory buffer
already used and reserved by the socket.

Signed-off-by: Shakeel Butt <shakeelb@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 mm/memcontrol.c                 | 14 --------------
 net/core/sock.c                 |  5 ++++-
 net/ipv4/inet_connection_sock.c | 20 ++++++++++++++++++++
 3 files changed, 24 insertions(+), 15 deletions(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index f89598436dec..ea1bcd21fefd 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -6683,20 +6683,6 @@ void mem_cgroup_sk_alloc(struct sock *sk)
 	if (!mem_cgroup_sockets_enabled)
 		return;
 
-	/*
-	 * Socket cloning can throw us here with sk_memcg already
-	 * filled. It won't however, necessarily happen from
-	 * process context. So the test for root memcg given
-	 * the current task's memcg won't help us in this case.
-	 *
-	 * Respecting the original socket's memcg is a better
-	 * decision in this case.
-	 */
-	if (sk->sk_memcg) {
-		css_get(&sk->sk_memcg->css);
-		return;
-	}
-
 	/* Do not associate the sock with unrelated interrupted task's memcg. */
 	if (in_interrupt())
 		return;
diff --git a/net/core/sock.c b/net/core/sock.c
index 8459ad579f73..a2f8a34c1e69 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1830,7 +1830,10 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		atomic_set(&newsk->sk_zckey, 0);
 
 		sock_reset_flag(newsk, SOCK_DONE);
-		mem_cgroup_sk_alloc(newsk);
+
+		/* sk->sk_memcg will be populated at accept() time */
+		newsk->sk_memcg = NULL;
+
 		cgroup_sk_alloc(&newsk->sk_cgrp_data);
 
 		rcu_read_lock();
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 18c0d5bffe12..1be9048e5c6b 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -482,6 +482,26 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern)
 		}
 		spin_unlock_bh(&queue->fastopenq.lock);
 	}
+
+	if (mem_cgroup_sockets_enabled) {
+		int amt;
+
+		/* atomically get the memory usage, set and charge the
+		 * sk->sk_memcg.
+		 */
+		lock_sock(newsk);
+
+		/* The sk has not been accepted yet, no need to look at
+		 * sk->sk_wmem_queued.
+		 */
+		amt = sk_mem_pages(newsk->sk_forward_alloc +
+				   atomic_read(&sk->sk_rmem_alloc));
+		mem_cgroup_sk_alloc(newsk);
+		if (newsk->sk_memcg && amt)
+			mem_cgroup_charge_skmem(newsk->sk_memcg, amt);
+
+		release_sock(newsk);
+	}
 out:
 	release_sock(sk);
 	if (req)
-- 
2.20.1


From 6a771997ab2224e5a1b77d0a61c57359fe4e7868 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 11 Mar 2020 11:44:26 -0700
Subject: [PATCH 34/66] net: memcg: fix lockdep splat in inet_csk_accept()

Locking newsk while still holding the listener lock triggered
a lockdep splat [1]

We can simply move the memcg code after we release the listener lock,
as this can also help if multiple threads are sharing a common listener.

Also fix a typo while reading socket sk_rmem_alloc.

[1]
WARNING: possible recursive locking detected
5.6.0-rc3-syzkaller #0 Not tainted
--------------------------------------------
syz-executor598/9524 is trying to acquire lock:
ffff88808b5b8b90 (sk_lock-AF_INET6){+.+.}, at: lock_sock include/net/sock.h:1541 [inline]
ffff88808b5b8b90 (sk_lock-AF_INET6){+.+.}, at: inet_csk_accept+0x69f/0xd30 net/ipv4/inet_connection_sock.c:492

but task is already holding lock:
ffff88808b5b9590 (sk_lock-AF_INET6){+.+.}, at: lock_sock include/net/sock.h:1541 [inline]
ffff88808b5b9590 (sk_lock-AF_INET6){+.+.}, at: inet_csk_accept+0x8d/0xd30 net/ipv4/inet_connection_sock.c:445

other info that might help us debug this:
 Possible unsafe locking scenario:

       CPU0
       ----
  lock(sk_lock-AF_INET6);
  lock(sk_lock-AF_INET6);

 *** DEADLOCK ***

 May be due to missing lock nesting notation

1 lock held by syz-executor598/9524:
 #0: ffff88808b5b9590 (sk_lock-AF_INET6){+.+.}, at: lock_sock include/net/sock.h:1541 [inline]
 #0: ffff88808b5b9590 (sk_lock-AF_INET6){+.+.}, at: inet_csk_accept+0x8d/0xd30 net/ipv4/inet_connection_sock.c:445

stack backtrace:
CPU: 0 PID: 9524 Comm: syz-executor598 Not tainted 5.6.0-rc3-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x188/0x20d lib/dump_stack.c:118
 print_deadlock_bug kernel/locking/lockdep.c:2370 [inline]
 check_deadlock kernel/locking/lockdep.c:2411 [inline]
 validate_chain kernel/locking/lockdep.c:2954 [inline]
 __lock_acquire.cold+0x114/0x288 kernel/locking/lockdep.c:3954
 lock_acquire+0x197/0x420 kernel/locking/lockdep.c:4484
 lock_sock_nested+0xc5/0x110 net/core/sock.c:2947
 lock_sock include/net/sock.h:1541 [inline]
 inet_csk_accept+0x69f/0xd30 net/ipv4/inet_connection_sock.c:492
 inet_accept+0xe9/0x7c0 net/ipv4/af_inet.c:734
 __sys_accept4_file+0x3ac/0x5b0 net/socket.c:1758
 __sys_accept4+0x53/0x90 net/socket.c:1809
 __do_sys_accept4 net/socket.c:1821 [inline]
 __se_sys_accept4 net/socket.c:1818 [inline]
 __x64_sys_accept4+0x93/0xf0 net/socket.c:1818
 do_syscall_64+0xf6/0x790 arch/x86/entry/common.c:294
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x4445c9
Code: e8 0c 0d 03 00 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 eb 08 fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007ffc35b37608 EFLAGS: 00000246 ORIG_RAX: 0000000000000120
RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00000000004445c9
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000003
RBP: 0000000000000000 R08: 0000000000306777 R09: 0000000000306777
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 00000000004053d0 R14: 0000000000000000 R15: 0000000000000000

Fixes: d752a4986532 ("net: memcg: late association of sock to memcg")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Shakeel Butt <shakeelb@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/inet_connection_sock.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 1be9048e5c6b..159513ce8511 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -483,27 +483,27 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern)
 		spin_unlock_bh(&queue->fastopenq.lock);
 	}
 
-	if (mem_cgroup_sockets_enabled) {
+out:
+	release_sock(sk);
+	if (newsk && mem_cgroup_sockets_enabled) {
 		int amt;
 
 		/* atomically get the memory usage, set and charge the
-		 * sk->sk_memcg.
+		 * newsk->sk_memcg.
 		 */
 		lock_sock(newsk);
 
-		/* The sk has not been accepted yet, no need to look at
-		 * sk->sk_wmem_queued.
+		/* The socket has not been accepted yet, no need to look at
+		 * newsk->sk_wmem_queued.
 		 */
 		amt = sk_mem_pages(newsk->sk_forward_alloc +
-				   atomic_read(&sk->sk_rmem_alloc));
+				   atomic_read(&newsk->sk_rmem_alloc));
 		mem_cgroup_sk_alloc(newsk);
 		if (newsk->sk_memcg && amt)
 			mem_cgroup_charge_skmem(newsk->sk_memcg, amt);
 
 		release_sock(newsk);
 	}
-out:
-	release_sock(sk);
 	if (req)
 		reqsk_put(req);
 	return newsk;
-- 
2.20.1


From ab506f808846f2e18a981465b6b4932018f8f70f Mon Sep 17 00:00:00 2001
From: Madalin Bucur <madalin.bucur@nxp.com>
Date: Wed, 4 Mar 2020 18:04:25 +0200
Subject: [PATCH 35/66] dt-bindings: net: FMan erratum A050385

FMAN DMA read or writes under heavy traffic load may cause FMAN
internal resource leak; thus stopping further packet processing.

The FMAN internal queue can overflow when FMAN splits single
read or write transactions into multiple smaller transactions
such that more than 17 AXI transactions are in flight from FMAN
to interconnect. When the FMAN internal queue overflows, it can
stall further packet processing. The issue can occur with any one
of the following three conditions:

  1. FMAN AXI transaction crosses 4K address boundary (Errata
     A010022)
  2. FMAN DMA address for an AXI transaction is not 16 byte
     aligned, i.e. the last 4 bits of an address are non-zero
  3. Scatter Gather (SG) frames have more than one SG buffer in
     the SG list and any one of the buffers, except the last
     buffer in the SG list has data size that is not a multiple
     of 16 bytes, i.e., other than 16, 32, 48, 64, etc.

With any one of the above three conditions present, there is
likelihood of stalled FMAN packet processing, especially under
stress with multiple ports injecting line-rate traffic.

To avoid situations that stall FMAN packet processing, all of the
above three conditions must be avoided; therefore, configure the
system with the following rules:

  1. Frame buffers must not span a 4KB address boundary, unless
     the frame start address is 256 byte aligned
  2. All FMAN DMA start addresses (for example, BMAN buffer
     address, FD[address] + FD[offset]) are 16B aligned
  3. SG table and buffer addresses are 16B aligned and the size
     of SG buffers are multiple of 16 bytes, except for the last
     SG buffer that can be of any size.

Additional workaround notes:
- Address alignment of 64 bytes is recommended for maximally
efficient system bus transactions (although 16 byte alignment is
sufficient to avoid the stall condition)
- To support frame sizes that are larger than 4K bytes, there are
two options:
  1. Large single buffer frames that span a 4KB page boundary can
     be converted into SG frames to avoid transaction splits at
     the 4KB boundary,
  2. Align the large single buffer to 256B address boundaries,
     ensure that the frame address plus offset is 256B aligned.
- If software generated SG frames have buffers that are unaligned
and with random non-multiple of 16 byte lengths, before
transmitting such frames via FMAN, frames will need to be copied
into a new single buffer or multiple buffer SG frame that is
compliant with the three rules listed above.

Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/devicetree/bindings/net/fsl-fman.txt | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/fsl-fman.txt b/Documentation/devicetree/bindings/net/fsl-fman.txt
index 250f8d8cdce4..c00fb0d22c7b 100644
--- a/Documentation/devicetree/bindings/net/fsl-fman.txt
+++ b/Documentation/devicetree/bindings/net/fsl-fman.txt
@@ -110,6 +110,13 @@ PROPERTIES
 		Usage: required
 		Definition: See soc/fsl/qman.txt and soc/fsl/bman.txt
 
+- fsl,erratum-a050385
+		Usage: optional
+		Value type: boolean
+		Definition: A boolean property. Indicates the presence of the
+		erratum A050385 which indicates that DMA transactions that are
+		split can result in a FMan lock.
+
 =============================================================================
 FMan MURAM Node
 
-- 
2.20.1


From 58523ea732eb9dafc430d3e0aa3b66f9ac14b541 Mon Sep 17 00:00:00 2001
From: Madalin Bucur <madalin.bucur@nxp.com>
Date: Wed, 4 Mar 2020 18:04:26 +0200
Subject: [PATCH 36/66] arm64: dts: ls1043a: FMan erratum A050385

The LS1043A SoC is affected by the A050385 erratum stating that
FMAN DMA read or writes under heavy traffic load may cause FMAN
internal resource leak thus stopping further packet processing.

Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/arm64/boot/dts/freescale/fsl-ls1043-post.dtsi | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043-post.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1043-post.dtsi
index 6082ae022136..d237162a8744 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1043-post.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1043-post.dtsi
@@ -20,6 +20,8 @@
 };
 
 &fman0 {
+	fsl,erratum-a050385;
+
 	/* these aliases provide the FMan ports mapping */
 	enet0: ethernet@e0000 {
 	};
-- 
2.20.1


From dbf28ea0455c171eb8805d7e3abb18f0b17127e4 Mon Sep 17 00:00:00 2001
From: Madalin Bucur <madalin.bucur@nxp.com>
Date: Wed, 4 Mar 2020 18:04:27 +0200
Subject: [PATCH 37/66] fsl/fman: detect FMan erratum A050385

Detect the presence of the A050385 erratum.

Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fman/Kconfig | 28 +++++++++++++++++++++
 drivers/net/ethernet/freescale/fman/fman.c  | 18 +++++++++++++
 drivers/net/ethernet/freescale/fman/fman.h  |  5 ++++
 3 files changed, 51 insertions(+)

diff --git a/drivers/net/ethernet/freescale/fman/Kconfig b/drivers/net/ethernet/freescale/fman/Kconfig
index 0139cb9042ec..34150182cc35 100644
--- a/drivers/net/ethernet/freescale/fman/Kconfig
+++ b/drivers/net/ethernet/freescale/fman/Kconfig
@@ -8,3 +8,31 @@ config FSL_FMAN
 	help
 		Freescale Data-Path Acceleration Architecture Frame Manager
 		(FMan) support
+
+config DPAA_ERRATUM_A050385
+	bool
+	depends on ARM64 && FSL_DPAA
+	default y
+	help
+		DPAA FMan erratum A050385 software workaround implementation:
+		align buffers, data start, SG fragment length to avoid FMan DMA
+		splits.
+		FMAN DMA read or writes under heavy traffic load may cause FMAN
+		internal resource leak thus stopping further packet processing.
+		The FMAN internal queue can overflow when FMAN splits single
+		read or write transactions into multiple smaller transactions
+		such that more than 17 AXI transactions are in flight from FMAN
+		to interconnect. When the FMAN internal queue overflows, it can
+		stall further packet processing. The issue can occur with any
+		one of the following three conditions:
+		1. FMAN AXI transaction crosses 4K address boundary (Errata
+		A010022)
+		2. FMAN DMA address for an AXI transaction is not 16 byte
+		aligned, i.e. the last 4 bits of an address are non-zero
+		3. Scatter Gather (SG) frames have more than one SG buffer in
+		the SG list and any one of the buffers, except the last
+		buffer in the SG list has data size that is not a multiple
+		of 16 bytes, i.e., other than 16, 32, 48, 64, etc.
+		With any one of the above three conditions present, there is
+		likelihood of stalled FMAN packet processing, especially under
+		stress with multiple ports injecting line-rate traffic.
diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c
index 934111def0be..f151d6e111dd 100644
--- a/drivers/net/ethernet/freescale/fman/fman.c
+++ b/drivers/net/ethernet/freescale/fman/fman.c
@@ -1,5 +1,6 @@
 /*
  * Copyright 2008-2015 Freescale Semiconductor Inc.
+ * Copyright 2020 NXP
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions are met:
@@ -566,6 +567,10 @@ struct fman_cfg {
 	u32 qmi_def_tnums_thresh;
 };
 
+#ifdef CONFIG_DPAA_ERRATUM_A050385
+static bool fman_has_err_a050385;
+#endif
+
 static irqreturn_t fman_exceptions(struct fman *fman,
 				   enum fman_exceptions exception)
 {
@@ -2518,6 +2523,14 @@ struct fman *fman_bind(struct device *fm_dev)
 }
 EXPORT_SYMBOL(fman_bind);
 
+#ifdef CONFIG_DPAA_ERRATUM_A050385
+bool fman_has_errata_a050385(void)
+{
+	return fman_has_err_a050385;
+}
+EXPORT_SYMBOL(fman_has_errata_a050385);
+#endif
+
 static irqreturn_t fman_err_irq(int irq, void *handle)
 {
 	struct fman *fman = (struct fman *)handle;
@@ -2845,6 +2858,11 @@ static struct fman *read_dts_node(struct platform_device *of_dev)
 		goto fman_free;
 	}
 
+#ifdef CONFIG_DPAA_ERRATUM_A050385
+	fman_has_err_a050385 =
+		of_property_read_bool(fm_node, "fsl,erratum-a050385");
+#endif
+
 	return fman;
 
 fman_node_put:
diff --git a/drivers/net/ethernet/freescale/fman/fman.h b/drivers/net/ethernet/freescale/fman/fman.h
index 935c317fa696..f2ede1360f03 100644
--- a/drivers/net/ethernet/freescale/fman/fman.h
+++ b/drivers/net/ethernet/freescale/fman/fman.h
@@ -1,5 +1,6 @@
 /*
  * Copyright 2008-2015 Freescale Semiconductor Inc.
+ * Copyright 2020 NXP
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions are met:
@@ -398,6 +399,10 @@ u16 fman_get_max_frm(void);
 
 int fman_get_rx_extra_headroom(void);
 
+#ifdef CONFIG_DPAA_ERRATUM_A050385
+bool fman_has_errata_a050385(void);
+#endif
+
 struct fman *fman_bind(struct device *dev);
 
 #endif /* __FM_H */
-- 
2.20.1


From d0b92a1b4bfacd87879c0c4e13a8b25555654963 Mon Sep 17 00:00:00 2001
From: Madalin Bucur <madalin.bucur@nxp.com>
Date: Wed, 4 Mar 2020 18:04:28 +0200
Subject: [PATCH 38/66] dpaa_eth: FMan erratum A050385 workaround

Align buffers, data start, SG fragment length to avoid DMA splits.
These changes prevent the A050385 erratum to manifest itself:

FMAN DMA read or writes under heavy traffic load may cause FMAN
internal resource leak; thus stopping further packet processing.

The FMAN internal queue can overflow when FMAN splits single
read or write transactions into multiple smaller transactions
such that more than 17 AXI transactions are in flight from FMAN
to interconnect. When the FMAN internal queue overflows, it can
stall further packet processing. The issue can occur with any one
of the following three conditions:

  1. FMAN AXI transaction crosses 4K address boundary (Errata
	 A010022)
  2. FMAN DMA address for an AXI transaction is not 16 byte
	 aligned, i.e. the last 4 bits of an address are non-zero
  3. Scatter Gather (SG) frames have more than one SG buffer in
	 the SG list and any one of the buffers, except the last
	 buffer in the SG list has data size that is not a multiple
	 of 16 bytes, i.e., other than 16, 32, 48, 64, etc.

With any one of the above three conditions present, there is
likelihood of stalled FMAN packet processing, especially under
stress with multiple ports injecting line-rate traffic.

To avoid situations that stall FMAN packet processing, all of the
above three conditions must be avoided; therefore, configure the
system with the following rules:

  1. Frame buffers must not span a 4KB address boundary, unless
	 the frame start address is 256 byte aligned
  2. All FMAN DMA start addresses (for example, BMAN buffer
	 address, FD[address] + FD[offset]) are 16B aligned
  3. SG table and buffer addresses are 16B aligned and the size
	 of SG buffers are multiple of 16 bytes, except for the last
	 SG buffer that can be of any size.

Additional workaround notes:
- Address alignment of 64 bytes is recommended for maximally
efficient system bus transactions (although 16 byte alignment is
sufficient to avoid the stall condition)
- To support frame sizes that are larger than 4K bytes, there are
two options:
  1. Large single buffer frames that span a 4KB page boundary can
	 be converted into SG frames to avoid transaction splits at
	 the 4KB boundary,
  2. Align the large single buffer to 256B address boundaries,
	 ensure that the frame address plus offset is 256B aligned.
- If software generated SG frames have buffers that are unaligned
and with random non-multiple of 16 byte lengths, before
transmitting such frames via FMAN, frames will need to be copied
into a new single buffer or multiple buffer SG frame that is
compliant with the three rules listed above.

Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/freescale/dpaa/dpaa_eth.c    | 110 +++++++++++++++++-
 1 file changed, 107 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index f827daf09b72..36e2e28fa6e3 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -1,4 +1,5 @@
 /* Copyright 2008 - 2016 Freescale Semiconductor Inc.
+ * Copyright 2020 NXP
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions are met:
@@ -123,7 +124,22 @@ MODULE_PARM_DESC(tx_timeout, "The Tx timeout in ms");
 #define FSL_QMAN_MAX_OAL	127
 
 /* Default alignment for start of data in an Rx FD */
+#ifdef CONFIG_DPAA_ERRATUM_A050385
+/* aligning data start to 64 avoids DMA transaction splits, unless the buffer
+ * is crossing a 4k page boundary
+ */
+#define DPAA_FD_DATA_ALIGNMENT  (fman_has_errata_a050385() ? 64 : 16)
+/* aligning to 256 avoids DMA transaction splits caused by 4k page boundary
+ * crossings; also, all SG fragments except the last must have a size multiple
+ * of 256 to avoid DMA transaction splits
+ */
+#define DPAA_A050385_ALIGN 256
+#define DPAA_FD_RX_DATA_ALIGNMENT (fman_has_errata_a050385() ? \
+				   DPAA_A050385_ALIGN : 16)
+#else
 #define DPAA_FD_DATA_ALIGNMENT  16
+#define DPAA_FD_RX_DATA_ALIGNMENT DPAA_FD_DATA_ALIGNMENT
+#endif
 
 /* The DPAA requires 256 bytes reserved and mapped for the SGT */
 #define DPAA_SGT_SIZE 256
@@ -158,8 +174,13 @@ MODULE_PARM_DESC(tx_timeout, "The Tx timeout in ms");
 #define DPAA_PARSE_RESULTS_SIZE sizeof(struct fman_prs_result)
 #define DPAA_TIME_STAMP_SIZE 8
 #define DPAA_HASH_RESULTS_SIZE 8
+#ifdef CONFIG_DPAA_ERRATUM_A050385
+#define DPAA_RX_PRIV_DATA_SIZE (DPAA_A050385_ALIGN - (DPAA_PARSE_RESULTS_SIZE\
+	 + DPAA_TIME_STAMP_SIZE + DPAA_HASH_RESULTS_SIZE))
+#else
 #define DPAA_RX_PRIV_DATA_SIZE	(u16)(DPAA_TX_PRIV_DATA_SIZE + \
 					dpaa_rx_extra_headroom)
+#endif
 
 #define DPAA_ETH_PCD_RXQ_NUM	128
 
@@ -180,7 +201,12 @@ static struct dpaa_bp *dpaa_bp_array[BM_MAX_NUM_OF_POOLS];
 
 #define DPAA_BP_RAW_SIZE 4096
 
+#ifdef CONFIG_DPAA_ERRATUM_A050385
+#define dpaa_bp_size(raw_size) (SKB_WITH_OVERHEAD(raw_size) & \
+				~(DPAA_A050385_ALIGN - 1))
+#else
 #define dpaa_bp_size(raw_size) SKB_WITH_OVERHEAD(raw_size)
+#endif
 
 static int dpaa_max_frm;
 
@@ -1192,7 +1218,7 @@ static int dpaa_eth_init_rx_port(struct fman_port *port, struct dpaa_bp *bp,
 	buf_prefix_content.pass_prs_result = true;
 	buf_prefix_content.pass_hash_result = true;
 	buf_prefix_content.pass_time_stamp = true;
-	buf_prefix_content.data_align = DPAA_FD_DATA_ALIGNMENT;
+	buf_prefix_content.data_align = DPAA_FD_RX_DATA_ALIGNMENT;
 
 	rx_p = &params.specific_params.rx_params;
 	rx_p->err_fqid = errq->fqid;
@@ -1662,6 +1688,8 @@ static u8 rx_csum_offload(const struct dpaa_priv *priv, const struct qm_fd *fd)
 	return CHECKSUM_NONE;
 }
 
+#define PTR_IS_ALIGNED(x, a) (IS_ALIGNED((unsigned long)(x), (a)))
+
 /* Build a linear skb around the received buffer.
  * We are guaranteed there is enough room at the end of the data buffer to
  * accommodate the shared info area of the skb.
@@ -1733,8 +1761,7 @@ static struct sk_buff *sg_fd_to_skb(const struct dpaa_priv *priv,
 
 		sg_addr = qm_sg_addr(&sgt[i]);
 		sg_vaddr = phys_to_virt(sg_addr);
-		WARN_ON(!IS_ALIGNED((unsigned long)sg_vaddr,
-				    SMP_CACHE_BYTES));
+		WARN_ON(!PTR_IS_ALIGNED(sg_vaddr, SMP_CACHE_BYTES));
 
 		dma_unmap_page(priv->rx_dma_dev, sg_addr,
 			       DPAA_BP_RAW_SIZE, DMA_FROM_DEVICE);
@@ -2022,6 +2049,75 @@ static inline int dpaa_xmit(struct dpaa_priv *priv,
 	return 0;
 }
 
+#ifdef CONFIG_DPAA_ERRATUM_A050385
+int dpaa_a050385_wa(struct net_device *net_dev, struct sk_buff **s)
+{
+	struct dpaa_priv *priv = netdev_priv(net_dev);
+	struct sk_buff *new_skb, *skb = *s;
+	unsigned char *start, i;
+
+	/* check linear buffer alignment */
+	if (!PTR_IS_ALIGNED(skb->data, DPAA_A050385_ALIGN))
+		goto workaround;
+
+	/* linear buffers just need to have an aligned start */
+	if (!skb_is_nonlinear(skb))
+		return 0;
+
+	/* linear data size for nonlinear skbs needs to be aligned */
+	if (!IS_ALIGNED(skb_headlen(skb), DPAA_A050385_ALIGN))
+		goto workaround;
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+		/* all fragments need to have aligned start addresses */
+		if (!IS_ALIGNED(skb_frag_off(frag), DPAA_A050385_ALIGN))
+			goto workaround;
+
+		/* all but last fragment need to have aligned sizes */
+		if (!IS_ALIGNED(skb_frag_size(frag), DPAA_A050385_ALIGN) &&
+		    (i < skb_shinfo(skb)->nr_frags - 1))
+			goto workaround;
+	}
+
+	return 0;
+
+workaround:
+	/* copy all the skb content into a new linear buffer */
+	new_skb = netdev_alloc_skb(net_dev, skb->len + DPAA_A050385_ALIGN - 1 +
+						priv->tx_headroom);
+	if (!new_skb)
+		return -ENOMEM;
+
+	/* NET_SKB_PAD bytes already reserved, adding up to tx_headroom */
+	skb_reserve(new_skb, priv->tx_headroom - NET_SKB_PAD);
+
+	/* Workaround for DPAA_A050385 requires data start to be aligned */
+	start = PTR_ALIGN(new_skb->data, DPAA_A050385_ALIGN);
+	if (start - new_skb->data != 0)
+		skb_reserve(new_skb, start - new_skb->data);
+
+	skb_put(new_skb, skb->len);
+	skb_copy_bits(skb, 0, new_skb->data, skb->len);
+	skb_copy_header(new_skb, skb);
+	new_skb->dev = skb->dev;
+
+	/* We move the headroom when we align it so we have to reset the
+	 * network and transport header offsets relative to the new data
+	 * pointer. The checksum offload relies on these offsets.
+	 */
+	skb_set_network_header(new_skb, skb_network_offset(skb));
+	skb_set_transport_header(new_skb, skb_transport_offset(skb));
+
+	/* TODO: does timestamping need the result in the old skb? */
+	dev_kfree_skb(skb);
+	*s = new_skb;
+
+	return 0;
+}
+#endif
+
 static netdev_tx_t
 dpaa_start_xmit(struct sk_buff *skb, struct net_device *net_dev)
 {
@@ -2068,6 +2164,14 @@ dpaa_start_xmit(struct sk_buff *skb, struct net_device *net_dev)
 		nonlinear = skb_is_nonlinear(skb);
 	}
 
+#ifdef CONFIG_DPAA_ERRATUM_A050385
+	if (unlikely(fman_has_errata_a050385())) {
+		if (dpaa_a050385_wa(net_dev, &skb))
+			goto enomem;
+		nonlinear = skb_is_nonlinear(skb);
+	}
+#endif
+
 	if (nonlinear) {
 		/* Just create a S/G fd based on the skb */
 		err = skb_to_sg_fd(priv, skb, &fd);
-- 
2.20.1


From ddd90396bbeed98b74dcadb645857ff80440c4e8 Mon Sep 17 00:00:00 2001
From: Yonglong Liu <liuyonglong@huawei.com>
Date: Thu, 12 Mar 2020 15:11:03 +0800
Subject: [PATCH 39/66] net: hns3: fix "tc qdisc del" failed issue

[ Upstream commit 5eb01ddfcfb25e6ebc404a41deae946bde776731 ]

The HNS3 driver supports to configure TC numbers and TC to priority
map via "tc" tool. But when delete the rule, will fail, because
the HNS3 driver needs at least one TC, but the "tc" tool sets TC
number to zero when delete.

This patch makes sure that the TC number is at least one.

Fixes: 30d240dfa2e8 ("net: hns3: Add mqprio hardware offload support in hns3 driver")
Signed-off-by: Yonglong Liu <liuyonglong@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index b3deb5e5ce29..d3161af9f8c0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -1675,7 +1675,7 @@ static int hns3_setup_tc(struct net_device *netdev, void *type_data)
 	netif_dbg(h, drv, netdev, "setup tc: num_tc=%u\n", tc);
 
 	return (kinfo->dcb_ops && kinfo->dcb_ops->setup_tc) ?
-		kinfo->dcb_ops->setup_tc(h, tc, prio_tc) : -EOPNOTSUPP;
+		kinfo->dcb_ops->setup_tc(h, tc ? tc : 1, prio_tc) : -EOPNOTSUPP;
 }
 
 static int hns3_nic_setup_tc(struct net_device *dev, enum tc_setup_type type,
-- 
2.20.1


From 3d9431cd53ba8faba28b733a8a344d16c542e032 Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Thu, 12 Mar 2020 15:11:05 +0800
Subject: [PATCH 40/66] net: hns3: fix RMW issue for VLAN filter switch

[ Upstream commit 903b85d3adce99a5301d5959c4d3c9d14a7974d4 ]

According to the user manual, the ingress and egress VLAN filter
are configured at the same time. Currently, hclge_init_vlan_config()
and hclge_set_vlan_spoofchk() will both change the VLAN filter
switch. So it's necessary to read the old configuration before
modifying it.

Fixes: 22044f95faa0 ("net: hns3: add support for spoof check setting")
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../hisilicon/hns3/hns3pf/hclge_main.c        | 19 +++++++++++++++----
 1 file changed, 15 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 02f0e1e6b6f9..7dbc930a9e84 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -7727,16 +7727,27 @@ static int hclge_set_vlan_filter_ctrl(struct hclge_dev *hdev, u8 vlan_type,
 	struct hclge_desc desc;
 	int ret;
 
-	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_VLAN_FILTER_CTRL, false);
-
+	/* read current vlan filter parameter */
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_VLAN_FILTER_CTRL, true);
 	req = (struct hclge_vlan_filter_ctrl_cmd *)desc.data;
 	req->vlan_type = vlan_type;
-	req->vlan_fe = filter_en ? fe_type : 0;
 	req->vf_id = vf_id;
 
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"failed to get vlan filter config, ret = %d.\n", ret);
+		return ret;
+	}
+
+	/* modify and write new config parameter */
+	hclge_cmd_reuse_desc(&desc, false);
+	req->vlan_fe = filter_en ?
+			(req->vlan_fe | fe_type) : (req->vlan_fe & ~fe_type);
+
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret)
-		dev_err(&hdev->pdev->dev, "set vlan filter fail, ret =%d.\n",
+		dev_err(&hdev->pdev->dev, "failed to set vlan filter, ret = %d.\n",
 			ret);
 
 	return ret;
-- 
2.20.1


From 9586a8decd5eb9dc9a3a991df995e85373b7d1a9 Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Thu, 12 Mar 2020 15:11:06 +0800
Subject: [PATCH 41/66] net: hns3: clear port base VLAN when unload PF

[ Upstream commit 59359fc8a2f7af062777692e6a7aae73483729ec ]

Currently, PF missed to clear the port base VLAN for VF when
unload. In this case, the VLAN id will remain in the VLAN
table. This patch fixes it.

Fixes: 92f11ea177cd ("net: hns3: fix set port based VLAN issue for VF")
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../hisilicon/hns3/hns3pf/hclge_main.c        | 23 +++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 7dbc930a9e84..b5e0ace648c0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -8486,6 +8486,28 @@ static int hclge_set_vf_vlan_filter(struct hnae3_handle *handle, int vfid,
 	}
 }
 
+static void hclge_clear_vf_vlan(struct hclge_dev *hdev)
+{
+	struct hclge_vlan_info *vlan_info;
+	struct hclge_vport *vport;
+	int ret;
+	int vf;
+
+	/* clear port base vlan for all vf */
+	for (vf = HCLGE_VF_VPORT_START_NUM; vf < hdev->num_alloc_vport; vf++) {
+		vport = &hdev->vport[vf];
+		vlan_info = &vport->port_base_vlan_cfg.vlan_info;
+
+		ret = hclge_set_vlan_filter_hw(hdev, htons(ETH_P_8021Q),
+					       vport->vport_id,
+					       vlan_info->vlan_tag, true);
+		if (ret)
+			dev_err(&hdev->pdev->dev,
+				"failed to clear vf vlan for vf%d, ret = %d\n",
+				vf - HCLGE_VF_VPORT_START_NUM, ret);
+	}
+}
+
 int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto,
 			  u16 vlan_id, bool is_kill)
 {
@@ -9895,6 +9917,7 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev)
 	struct hclge_mac *mac = &hdev->hw.mac;
 
 	hclge_reset_vf_rate(hdev);
+	hclge_clear_vf_vlan(hdev);
 	hclge_misc_affinity_teardown(hdev);
 	hclge_state_uninit(hdev);
 
-- 
2.20.1


From 51023d09401a73db229efbbeb6f28b23c1b23a9a Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 2 Mar 2020 21:05:11 -0800
Subject: [PATCH 42/66] devlink: validate length of param values

[ Upstream commit 8750939b6ad86abc3f53ec8a9683a1cded4a5654 ]

DEVLINK_ATTR_PARAM_VALUE_DATA may have different types
so it's not checked by the normal netlink policy. Make
sure the attribute length is what we expect.

Fixes: e3b7ca18ad7b ("devlink: Add param set command")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/devlink.c | 31 +++++++++++++++++++------------
 1 file changed, 19 insertions(+), 12 deletions(-)

diff --git a/net/core/devlink.c b/net/core/devlink.c
index 42370702d0e0..06013c006644 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -3352,34 +3352,41 @@ devlink_param_value_get_from_info(const struct devlink_param *param,
 				  struct genl_info *info,
 				  union devlink_param_value *value)
 {
+	struct nlattr *param_data;
 	int len;
 
-	if (param->type != DEVLINK_PARAM_TYPE_BOOL &&
-	    !info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA])
+	param_data = info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA];
+
+	if (param->type != DEVLINK_PARAM_TYPE_BOOL && !param_data)
 		return -EINVAL;
 
 	switch (param->type) {
 	case DEVLINK_PARAM_TYPE_U8:
-		value->vu8 = nla_get_u8(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]);
+		if (nla_len(param_data) != sizeof(u8))
+			return -EINVAL;
+		value->vu8 = nla_get_u8(param_data);
 		break;
 	case DEVLINK_PARAM_TYPE_U16:
-		value->vu16 = nla_get_u16(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]);
+		if (nla_len(param_data) != sizeof(u16))
+			return -EINVAL;
+		value->vu16 = nla_get_u16(param_data);
 		break;
 	case DEVLINK_PARAM_TYPE_U32:
-		value->vu32 = nla_get_u32(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]);
+		if (nla_len(param_data) != sizeof(u32))
+			return -EINVAL;
+		value->vu32 = nla_get_u32(param_data);
 		break;
 	case DEVLINK_PARAM_TYPE_STRING:
-		len = strnlen(nla_data(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]),
-			      nla_len(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]));
-		if (len == nla_len(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]) ||
+		len = strnlen(nla_data(param_data), nla_len(param_data));
+		if (len == nla_len(param_data) ||
 		    len >= __DEVLINK_PARAM_MAX_STRING_VALUE)
 			return -EINVAL;
-		strcpy(value->vstr,
-		       nla_data(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]));
+		strcpy(value->vstr, nla_data(param_data));
 		break;
 	case DEVLINK_PARAM_TYPE_BOOL:
-		value->vbool = info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA] ?
-			       true : false;
+		if (param_data && nla_len(param_data))
+			return -EINVAL;
+		value->vbool = nla_get_flag(param_data);
 		break;
 	}
 	return 0;
-- 
2.20.1


From f3b5e47e4293ad7809fad334cabe3c72d99125e5 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 2 Mar 2020 21:05:12 -0800
Subject: [PATCH 43/66] devlink: validate length of region addr/len

[ Upstream commit ff3b63b8c299b73ac599b120653b47e275407656 ]

DEVLINK_ATTR_REGION_CHUNK_ADDR and DEVLINK_ATTR_REGION_CHUNK_LEN
lack entries in the netlink policy. Corresponding nla_get_u64()s
may read beyond the end of the message.

Fixes: 4e54795a27f5 ("devlink: Add support for region snapshot read command")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/devlink.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/core/devlink.c b/net/core/devlink.c
index 06013c006644..b10c7a83badb 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -5924,6 +5924,8 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_PARAM_VALUE_CMODE] = { .type = NLA_U8 },
 	[DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING },
 	[DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .type = NLA_U32 },
+	[DEVLINK_ATTR_REGION_CHUNK_ADDR] = { .type = NLA_U64 },
+	[DEVLINK_ATTR_REGION_CHUNK_LEN] = { .type = NLA_U64 },
 	[DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING },
 	[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] = { .type = NLA_U64 },
 	[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = { .type = NLA_U8 },
-- 
2.20.1


From 8cc3723a1edf3dd41fe1d6926dd0d9d826a0a32f Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 2 Mar 2020 21:05:13 -0800
Subject: [PATCH 44/66] fib: add missing attribute validation for tun_id

[ Upstream commit 4c16d64ea04056f1b1b324ab6916019f6a064114 ]

Add missing netlink policy entry for FRA_TUN_ID.

Fixes: e7030878fc84 ("fib: Add fib rule match on tunnel id")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/fib_rules.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index 54e227e6b06a..a259050f84af 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -108,6 +108,7 @@ struct fib_rule_notifier_info {
 	[FRA_OIFNAME]	= { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, \
 	[FRA_PRIORITY]	= { .type = NLA_U32 }, \
 	[FRA_FWMARK]	= { .type = NLA_U32 }, \
+	[FRA_TUN_ID]	= { .type = NLA_U64 }, \
 	[FRA_FWMASK]	= { .type = NLA_U32 }, \
 	[FRA_TABLE]     = { .type = NLA_U32 }, \
 	[FRA_SUPPRESS_PREFIXLEN] = { .type = NLA_U32 }, \
-- 
2.20.1


From c8a22e37ecf5c6459b04b0c47e069615300536a6 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 2 Mar 2020 21:05:14 -0800
Subject: [PATCH 45/66] nl802154: add missing attribute validation

[ Upstream commit 9322cd7c4af2ccc7fe7c5f01adb53f4f77949e92 ]

Add missing attribute validation for several u8 types.

Fixes: 2c21d11518b6 ("net: add NL802154 interface for configuration of 802.15.4 devices")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Stefan Schmidt <stefan@datenfreihafen.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ieee802154/nl_policy.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/ieee802154/nl_policy.c b/net/ieee802154/nl_policy.c
index 2c7a38d76a3a..824e7e84014c 100644
--- a/net/ieee802154/nl_policy.c
+++ b/net/ieee802154/nl_policy.c
@@ -21,6 +21,11 @@ const struct nla_policy ieee802154_policy[IEEE802154_ATTR_MAX + 1] = {
 	[IEEE802154_ATTR_HW_ADDR] = { .type = NLA_HW_ADDR, },
 	[IEEE802154_ATTR_PAN_ID] = { .type = NLA_U16, },
 	[IEEE802154_ATTR_CHANNEL] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_BCN_ORD] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_SF_ORD] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_PAN_COORD] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_BAT_EXT] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_COORD_REALIGN] = { .type = NLA_U8, },
 	[IEEE802154_ATTR_PAGE] = { .type = NLA_U8, },
 	[IEEE802154_ATTR_COORD_SHORT_ADDR] = { .type = NLA_U16, },
 	[IEEE802154_ATTR_COORD_HW_ADDR] = { .type = NLA_HW_ADDR, },
-- 
2.20.1


From abbd25ba8ed94aa528b4c464b51bb94cab55335d Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 2 Mar 2020 21:05:15 -0800
Subject: [PATCH 46/66] nl802154: add missing attribute validation for dev_type

[ Upstream commit b60673c4c418bef7550d02faf53c34fbfeb366bf ]

Add missing attribute type validation for IEEE802154_ATTR_DEV_TYPE
to the netlink policy.

Fixes: 90c049b2c6ae ("ieee802154: interface type to be added")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Stefan Schmidt <stefan@datenfreihafen.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ieee802154/nl_policy.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ieee802154/nl_policy.c b/net/ieee802154/nl_policy.c
index 824e7e84014c..0672b2f01586 100644
--- a/net/ieee802154/nl_policy.c
+++ b/net/ieee802154/nl_policy.c
@@ -27,6 +27,7 @@ const struct nla_policy ieee802154_policy[IEEE802154_ATTR_MAX + 1] = {
 	[IEEE802154_ATTR_BAT_EXT] = { .type = NLA_U8, },
 	[IEEE802154_ATTR_COORD_REALIGN] = { .type = NLA_U8, },
 	[IEEE802154_ATTR_PAGE] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_DEV_TYPE] = { .type = NLA_U8, },
 	[IEEE802154_ATTR_COORD_SHORT_ADDR] = { .type = NLA_U16, },
 	[IEEE802154_ATTR_COORD_HW_ADDR] = { .type = NLA_HW_ADDR, },
 	[IEEE802154_ATTR_COORD_PAN_ID] = { .type = NLA_U16, },
-- 
2.20.1


From 0c8a858ef2c7bfc8bcbf9087ef4067b09b38c730 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 2 Mar 2020 21:05:16 -0800
Subject: [PATCH 47/66] can: add missing attribute validation for termination

[ Upstream commit ab02ad660586b94f5d08912a3952b939cf4c4430 ]

Add missing attribute validation for IFLA_CAN_TERMINATION
to the netlink policy.

Fixes: 12a6075cabc0 ("can: dev: add CAN interface termination API")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/can/dev.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index 6ee06a49fb4c..68834a2853c9 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -883,6 +883,7 @@ static const struct nla_policy can_policy[IFLA_CAN_MAX + 1] = {
 				= { .len = sizeof(struct can_bittiming) },
 	[IFLA_CAN_DATA_BITTIMING_CONST]
 				= { .len = sizeof(struct can_bittiming_const) },
+	[IFLA_CAN_TERMINATION]	= { .type = NLA_U16 },
 };
 
 static int can_validate(struct nlattr *tb[], struct nlattr *data[],
-- 
2.20.1


From cc7504e3ecae9fda05d99bd88afd64917272016b Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 2 Mar 2020 21:05:17 -0800
Subject: [PATCH 48/66] macsec: add missing attribute validation for port

[ Upstream commit 31d9a1c524964bac77b7f9d0a1ac140dc6b57461 ]

Add missing attribute validation for IFLA_MACSEC_PORT
to the netlink policy.

Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macsec.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 88b7544910d9..57ef24546e96 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -2983,6 +2983,7 @@ static const struct device_type macsec_type = {
 
 static const struct nla_policy macsec_rtnl_policy[IFLA_MACSEC_MAX + 1] = {
 	[IFLA_MACSEC_SCI] = { .type = NLA_U64 },
+	[IFLA_MACSEC_PORT] = { .type = NLA_U16 },
 	[IFLA_MACSEC_ICV_LEN] = { .type = NLA_U8 },
 	[IFLA_MACSEC_CIPHER_SUITE] = { .type = NLA_U64 },
 	[IFLA_MACSEC_WINDOW] = { .type = NLA_U32 },
-- 
2.20.1


From 9f4462464ed7277ad93cf822b0e1c3a09df7c1e2 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 2 Mar 2020 21:05:18 -0800
Subject: [PATCH 49/66] openvswitch: add missing attribute validation for hash

[ Upstream commit b5ab1f1be6180a2e975eede18731804b5164a05d ]

Add missing attribute validation for OVS_PACKET_ATTR_HASH
to the netlink policy.

Fixes: bd1903b7c459 ("net: openvswitch: add hash info to upcall")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Greg Rose <gvrose8192@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/datapath.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index e3a37d22539c..c82b88693fe2 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -647,6 +647,7 @@ static const struct nla_policy packet_policy[OVS_PACKET_ATTR_MAX + 1] = {
 	[OVS_PACKET_ATTR_ACTIONS] = { .type = NLA_NESTED },
 	[OVS_PACKET_ATTR_PROBE] = { .type = NLA_FLAG },
 	[OVS_PACKET_ATTR_MRU] = { .type = NLA_U16 },
+	[OVS_PACKET_ATTR_HASH] = { .type = NLA_U64 },
 };
 
 static const struct genl_ops dp_packet_genl_ops[] = {
-- 
2.20.1


From e15b49ef678bcd22cdcbb027431155950f761713 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 2 Mar 2020 21:05:19 -0800
Subject: [PATCH 50/66] net: fq: add missing attribute validation for orphan
 mask

[ Upstream commit 7e6dc03eeb023e18427a373522f1d247b916a641 ]

Add missing attribute validation for TCA_FQ_ORPHAN_MASK
to the netlink policy.

Fixes: 06eb395fa985 ("pkt_sched: fq: better control of DDOS traffic")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_fq.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index a5a295477ecc..371ad84def3b 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -744,6 +744,7 @@ static const struct nla_policy fq_policy[TCA_FQ_MAX + 1] = {
 	[TCA_FQ_FLOW_MAX_RATE]		= { .type = NLA_U32 },
 	[TCA_FQ_BUCKETS_LOG]		= { .type = NLA_U32 },
 	[TCA_FQ_FLOW_REFILL_DELAY]	= { .type = NLA_U32 },
+	[TCA_FQ_ORPHAN_MASK]		= { .type = NLA_U32 },
 	[TCA_FQ_LOW_RATE_THRESHOLD]	= { .type = NLA_U32 },
 	[TCA_FQ_CE_THRESHOLD]		= { .type = NLA_U32 },
 };
-- 
2.20.1


From 68f2f0f37ef586c726f14d30af91d699888a963d Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 2 Mar 2020 21:05:20 -0800
Subject: [PATCH 51/66] net: taprio: add missing attribute validation for
 txtime delay

[ Upstream commit e13aaa0643da10006ec35715954e7f92a62899a5 ]

Add missing attribute validation for TCA_TAPRIO_ATTR_TXTIME_DELAY
to the netlink policy.

Fixes: 4cfd5779bd6e ("taprio: Add support for txtime-assist mode")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_taprio.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 437e333a4a33..b1eb12d33b9a 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -774,6 +774,7 @@ static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = {
 	[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME]           = { .type = NLA_S64 },
 	[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION] = { .type = NLA_S64 },
 	[TCA_TAPRIO_ATTR_FLAGS]                      = { .type = NLA_U32 },
+	[TCA_TAPRIO_ATTR_TXTIME_DELAY]		     = { .type = NLA_U32 },
 };
 
 static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry,
-- 
2.20.1


From 3f20a4bca700e674d652dc35f02475d844efdf84 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 2 Mar 2020 21:05:21 -0800
Subject: [PATCH 52/66] team: add missing attribute validation for port ifindex

[ Upstream commit dd25cb272ccce4db67dc8509278229099e4f5e99 ]

Add missing attribute validation for TEAM_ATTR_OPTION_PORT_IFINDEX
to the netlink policy.

Fixes: 80f7c6683fe0 ("team: add support for per-port options")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index ca70a1d840eb..44dd26a62a6d 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -2240,6 +2240,7 @@ team_nl_option_policy[TEAM_ATTR_OPTION_MAX + 1] = {
 	[TEAM_ATTR_OPTION_CHANGED]		= { .type = NLA_FLAG },
 	[TEAM_ATTR_OPTION_TYPE]			= { .type = NLA_U8 },
 	[TEAM_ATTR_OPTION_DATA]			= { .type = NLA_BINARY },
+	[TEAM_ATTR_OPTION_PORT_IFINDEX]		= { .type = NLA_U32 },
 };
 
 static int team_nl_cmd_noop(struct sk_buff *skb, struct genl_info *info)
-- 
2.20.1


From a2ab38b61da897d3b48cdc863216282f82a6d621 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 2 Mar 2020 21:05:22 -0800
Subject: [PATCH 53/66] team: add missing attribute validation for array index

[ Upstream commit 669fcd7795900cd1880237cbbb57a7db66cb9ac8 ]

Add missing attribute validation for TEAM_ATTR_OPTION_ARRAY_INDEX
to the netlink policy.

Fixes: b13033262d24 ("team: introduce array options")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 44dd26a62a6d..4004f98e50d9 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -2241,6 +2241,7 @@ team_nl_option_policy[TEAM_ATTR_OPTION_MAX + 1] = {
 	[TEAM_ATTR_OPTION_TYPE]			= { .type = NLA_U8 },
 	[TEAM_ATTR_OPTION_DATA]			= { .type = NLA_BINARY },
 	[TEAM_ATTR_OPTION_PORT_IFINDEX]		= { .type = NLA_U32 },
+	[TEAM_ATTR_OPTION_ARRAY_INDEX]		= { .type = NLA_U32 },
 };
 
 static int team_nl_cmd_noop(struct sk_buff *skb, struct genl_info *info)
-- 
2.20.1


From d77bff8c376150961fb163a3809f702ecef7d1bd Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 2 Mar 2020 21:05:23 -0800
Subject: [PATCH 54/66] tipc: add missing attribute validation for MTU property

[ Upstream commit 213320a67962ff6e7b83b704d55cbebc341426db ]

Add missing attribute validation for TIPC_NLA_PROP_MTU
to the netlink policy.

Fixes: 901271e0403a ("tipc: implement configuration of UDP media MTU")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/netlink.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index e53231bd23b4..85f957689d32 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -115,6 +115,7 @@ const struct nla_policy tipc_nl_prop_policy[TIPC_NLA_PROP_MAX + 1] = {
 	[TIPC_NLA_PROP_PRIO]		= { .type = NLA_U32 },
 	[TIPC_NLA_PROP_TOL]		= { .type = NLA_U32 },
 	[TIPC_NLA_PROP_WIN]		= { .type = NLA_U32 },
+	[TIPC_NLA_PROP_MTU]		= { .type = NLA_U32 },
 	[TIPC_NLA_PROP_BROADCAST]	= { .type = NLA_U32 },
 	[TIPC_NLA_PROP_BROADCAST_RATIO]	= { .type = NLA_U32 }
 };
-- 
2.20.1


From a0e316efd01d78d797506a6cc6c4d24c47da6e9e Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 2 Mar 2020 21:05:24 -0800
Subject: [PATCH 55/66] nfc: add missing attribute validation for SE API

[ Upstream commit 361d23e41ca6e504033f7e66a03b95788377caae ]

Add missing attribute validation for NFC_ATTR_SE_INDEX
to the netlink policy.

Fixes: 5ce3f32b5264 ("NFC: netlink: SE API implementation")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/nfc/netlink.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index eee0dddb7749..842407a48f96 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -43,6 +43,7 @@ static const struct nla_policy nfc_genl_policy[NFC_ATTR_MAX + 1] = {
 	[NFC_ATTR_LLC_SDP] = { .type = NLA_NESTED },
 	[NFC_ATTR_FIRMWARE_NAME] = { .type = NLA_STRING,
 				     .len = NFC_FIRMWARE_NAME_MAXSIZE },
+	[NFC_ATTR_SE_INDEX] = { .type = NLA_U32 },
 	[NFC_ATTR_SE_APDU] = { .type = NLA_BINARY },
 	[NFC_ATTR_VENDOR_DATA] = { .type = NLA_BINARY },
 
-- 
2.20.1


From 707cc0d207850eb67dd5d73666b5724c1dba024d Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 2 Mar 2020 21:05:25 -0800
Subject: [PATCH 56/66] nfc: add missing attribute validation for deactivate
 target

[ Upstream commit 88e706d5168b07df4792dbc3d1bc37b83e4bd74d ]

Add missing attribute validation for NFC_ATTR_TARGET_INDEX
to the netlink policy.

Fixes: 4d63adfe12dd ("NFC: Add NFC_CMD_DEACTIVATE_TARGET support")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/nfc/netlink.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index 842407a48f96..e988ca486d66 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -32,6 +32,7 @@ static const struct nla_policy nfc_genl_policy[NFC_ATTR_MAX + 1] = {
 	[NFC_ATTR_DEVICE_NAME] = { .type = NLA_STRING,
 				.len = NFC_DEVICE_NAME_MAXSIZE },
 	[NFC_ATTR_PROTOCOLS] = { .type = NLA_U32 },
+	[NFC_ATTR_TARGET_INDEX] = { .type = NLA_U32 },
 	[NFC_ATTR_COMM_MODE] = { .type = NLA_U8 },
 	[NFC_ATTR_RF_MODE] = { .type = NLA_U8 },
 	[NFC_ATTR_DEVICE_POWERED] = { .type = NLA_U8 },
-- 
2.20.1


From 8d459ddf3f86ef7b0f60d4da18fbfa323ac8ec9e Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 2 Mar 2020 21:05:26 -0800
Subject: [PATCH 57/66] nfc: add missing attribute validation for vendor
 subcommand

[ Upstream commit 6ba3da446551f2150fadbf8c7788edcb977683d3 ]

Add missing attribute validation for vendor subcommand attributes
to the netlink policy.

Fixes: 9e58095f9660 ("NFC: netlink: Implement vendor command support")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/nfc/netlink.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index e988ca486d66..e894254c17d4 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -46,6 +46,8 @@ static const struct nla_policy nfc_genl_policy[NFC_ATTR_MAX + 1] = {
 				     .len = NFC_FIRMWARE_NAME_MAXSIZE },
 	[NFC_ATTR_SE_INDEX] = { .type = NLA_U32 },
 	[NFC_ATTR_SE_APDU] = { .type = NLA_BINARY },
+	[NFC_ATTR_VENDOR_ID] = { .type = NLA_U32 },
+	[NFC_ATTR_VENDOR_SUBCMD] = { .type = NLA_U32 },
 	[NFC_ATTR_VENDOR_DATA] = { .type = NLA_BINARY },
 
 };
-- 
2.20.1


From 3bbeafca22c0b1997165d62f3997ace4606d8cc6 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 1 Mar 2020 21:36:09 +0100
Subject: [PATCH 58/66] net: phy: avoid clearing PHY interrupts twice in irq
 handler

[ Upstream commit 249bc9744e165abe74ae326f43e9d70bad54c3b7 ]

On all PHY drivers that implement did_interrupt() reading the interrupt
status bits clears them. This means we may loose an interrupt that
is triggered between calling did_interrupt() and phy_clear_interrupt().
As part of the fix make it a requirement that did_interrupt() clears
the interrupt.

The Fixes tag refers to the first commit where the patch applies
cleanly.

Fixes: 49644e68f472 ("net: phy: add callback for custom interrupt handler to struct phy_driver")
Reported-by: Michael Walle <michael@walle.cc>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 3 ++-
 include/linux/phy.h   | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 80be4d691e5b..6f6ebe908ed8 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -702,7 +702,8 @@ static irqreturn_t phy_interrupt(int irq, void *phy_dat)
 		phy_trigger_machine(phydev);
 	}
 
-	if (phy_clear_interrupt(phydev))
+	/* did_interrupt() may have cleared the interrupt already */
+	if (!phydev->drv->did_interrupt && phy_clear_interrupt(phydev))
 		goto phy_err;
 	return IRQ_HANDLED;
 
diff --git a/include/linux/phy.h b/include/linux/phy.h
index dd4a91f1feaa..74356e8bbe71 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -531,6 +531,7 @@ struct phy_driver {
 	/*
 	 * Checks if the PHY generated an interrupt.
 	 * For multi-PHY devices with shared PHY interrupt pin
+	 * Set interrupt bits have to be cleared.
 	 */
 	int (*did_interrupt)(struct phy_device *phydev);
 
-- 
2.20.1


From ab17de4d91f24742a25d8b197bb482088950c47f Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 12 Mar 2020 22:25:20 +0100
Subject: [PATCH 59/66] net: phy: fix MDIO bus PM PHY resuming

[ Upstream commit 611d779af7cad2b87487ff58e4931a90c20b113c ]

So far we have the unfortunate situation that mdio_bus_phy_may_suspend()
is called in suspend AND resume path, assuming that function result is
the same. After the original change this is no longer the case,
resulting in broken resume as reported by Geert.

To fix this call mdio_bus_phy_may_suspend() in the suspend path only,
and let the phy_device store the info whether it was suspended by
MDIO bus PM.

Fixes: 503ba7c69610 ("net: phy: Avoid multiple suspends")
Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Tested-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 6 +++++-
 include/linux/phy.h          | 2 ++
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index b13c52873ef5..11712e3802ba 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -285,6 +285,8 @@ static int mdio_bus_phy_suspend(struct device *dev)
 	if (!mdio_bus_phy_may_suspend(phydev))
 		return 0;
 
+	phydev->suspended_by_mdio_bus = 1;
+
 	return phy_suspend(phydev);
 }
 
@@ -293,9 +295,11 @@ static int mdio_bus_phy_resume(struct device *dev)
 	struct phy_device *phydev = to_phy_device(dev);
 	int ret;
 
-	if (!mdio_bus_phy_may_suspend(phydev))
+	if (!phydev->suspended_by_mdio_bus)
 		goto no_resume;
 
+	phydev->suspended_by_mdio_bus = 0;
+
 	ret = phy_resume(phydev);
 	if (ret < 0)
 		return ret;
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 74356e8bbe71..b5e21c3a22d0 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -338,6 +338,7 @@ struct phy_c45_device_ids {
  * is_gigabit_capable: Set to true if PHY supports 1000Mbps
  * has_fixups: Set to true if this phy has fixups/quirks.
  * suspended: Set to true if this phy has been suspended successfully.
+ * suspended_by_mdio_bus: Set to true if this phy was suspended by MDIO bus.
  * sysfs_links: Internal boolean tracking sysfs symbolic links setup/removal.
  * loopback_enabled: Set true if this phy has been loopbacked successfully.
  * state: state of the PHY for management purposes
@@ -376,6 +377,7 @@ struct phy_device {
 	unsigned is_gigabit_capable:1;
 	unsigned has_fixups:1;
 	unsigned suspended:1;
+	unsigned suspended_by_mdio_bus:1;
 	unsigned sysfs_links:1;
 	unsigned loopback_enabled:1;
 
-- 
2.20.1


From 54666447063712ffb6e01609fb3d00aa0fc69c2c Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Tue, 3 Mar 2020 14:37:34 +0800
Subject: [PATCH 60/66] net/ipv6: need update peer route when modify metric

[ Upstream commit 617940123e0140521f3080d2befc2bf55bcda094 ]

When we modify the route metric, the peer address's route need also
be updated. Before the fix:

+ ip addr add dev dummy1 2001:db8::1 peer 2001:db8::2 metric 60
+ ip -6 route show dev dummy1
2001:db8::1 proto kernel metric 60 pref medium
2001:db8::2 proto kernel metric 60 pref medium
+ ip addr change dev dummy1 2001:db8::1 peer 2001:db8::2 metric 61
+ ip -6 route show dev dummy1
2001:db8::1 proto kernel metric 61 pref medium
2001:db8::2 proto kernel metric 60 pref medium

After the fix:
+ ip addr change dev dummy1 2001:db8::1 peer 2001:db8::2 metric 61
+ ip -6 route show dev dummy1
2001:db8::1 proto kernel metric 61 pref medium
2001:db8::2 proto kernel metric 61 pref medium

Fixes: 8308f3ff1753 ("net/ipv6: Add support for specifying metric of connected routes")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 2d758a39dd29..cabaff4b9760 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -4590,12 +4590,14 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
 }
 
 static int modify_prefix_route(struct inet6_ifaddr *ifp,
-			       unsigned long expires, u32 flags)
+			       unsigned long expires, u32 flags,
+			       bool modify_peer)
 {
 	struct fib6_info *f6i;
 	u32 prio;
 
-	f6i = addrconf_get_prefix_route(&ifp->addr, ifp->prefix_len,
+	f6i = addrconf_get_prefix_route(modify_peer ? &ifp->peer_addr : &ifp->addr,
+					ifp->prefix_len,
 					ifp->idev->dev, 0, RTF_DEFAULT, true);
 	if (!f6i)
 		return -ENOENT;
@@ -4606,7 +4608,8 @@ static int modify_prefix_route(struct inet6_ifaddr *ifp,
 		ip6_del_rt(dev_net(ifp->idev->dev), f6i);
 
 		/* add new one */
-		addrconf_prefix_route(&ifp->addr, ifp->prefix_len,
+		addrconf_prefix_route(modify_peer ? &ifp->peer_addr : &ifp->addr,
+				      ifp->prefix_len,
 				      ifp->rt_priority, ifp->idev->dev,
 				      expires, flags, GFP_KERNEL);
 	} else {
@@ -4682,7 +4685,7 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg)
 		int rc = -ENOENT;
 
 		if (had_prefixroute)
-			rc = modify_prefix_route(ifp, expires, flags);
+			rc = modify_prefix_route(ifp, expires, flags, false);
 
 		/* prefix route could have been deleted; if so restore it */
 		if (rc == -ENOENT) {
@@ -4690,6 +4693,15 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg)
 					      ifp->rt_priority, ifp->idev->dev,
 					      expires, flags, GFP_KERNEL);
 		}
+
+		if (had_prefixroute && !ipv6_addr_any(&ifp->peer_addr))
+			rc = modify_prefix_route(ifp, expires, flags, true);
+
+		if (rc == -ENOENT && !ipv6_addr_any(&ifp->peer_addr)) {
+			addrconf_prefix_route(&ifp->peer_addr, ifp->prefix_len,
+					      ifp->rt_priority, ifp->idev->dev,
+					      expires, flags, GFP_KERNEL);
+		}
 	} else if (had_prefixroute) {
 		enum cleanup_prefix_rt_t action;
 		unsigned long rt_expires;
-- 
2.20.1


From f2e53de4886f0d8c1fad13b60a2ad4c82d725130 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Tue, 3 Mar 2020 14:37:35 +0800
Subject: [PATCH 61/66] net/ipv6: remove the old peer route if change it to a
 new one

[ Upstream commit d0098e4c6b83e502cc1cd96d67ca86bc79a6c559 ]

When we modify the peer route and changed it to a new one, we should
remove the old route first. Before the fix:

+ ip addr add dev dummy1 2001:db8::1 peer 2001:db8::2
+ ip -6 route show dev dummy1
2001:db8::1 proto kernel metric 256 pref medium
2001:db8::2 proto kernel metric 256 pref medium
+ ip addr change dev dummy1 2001:db8::1 peer 2001:db8::3
+ ip -6 route show dev dummy1
2001:db8::1 proto kernel metric 256 pref medium
2001:db8::2 proto kernel metric 256 pref medium

After the fix:
+ ip addr change dev dummy1 2001:db8::1 peer 2001:db8::3
+ ip -6 route show dev dummy1
2001:db8::1 proto kernel metric 256 pref medium
2001:db8::3 proto kernel metric 256 pref medium

This patch depend on the previous patch "net/ipv6: need update peer route
when modify metric" to update new peer route after delete old one.

Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 21 +++++++++++++++++----
 1 file changed, 17 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index cabaff4b9760..46d614b611db 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1226,11 +1226,13 @@ check_cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long *expires)
 }
 
 static void
-cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires, bool del_rt)
+cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires,
+		     bool del_rt, bool del_peer)
 {
 	struct fib6_info *f6i;
 
-	f6i = addrconf_get_prefix_route(&ifp->addr, ifp->prefix_len,
+	f6i = addrconf_get_prefix_route(del_peer ? &ifp->peer_addr : &ifp->addr,
+					ifp->prefix_len,
 					ifp->idev->dev, 0, RTF_DEFAULT, true);
 	if (f6i) {
 		if (del_rt)
@@ -1293,7 +1295,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
 
 	if (action != CLEANUP_PREFIX_RT_NOP) {
 		cleanup_prefix_route(ifp, expires,
-			action == CLEANUP_PREFIX_RT_DEL);
+			action == CLEANUP_PREFIX_RT_DEL, false);
 	}
 
 	/* clean up prefsrc entries */
@@ -4631,6 +4633,7 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg)
 	unsigned long timeout;
 	bool was_managetempaddr;
 	bool had_prefixroute;
+	bool new_peer = false;
 
 	ASSERT_RTNL();
 
@@ -4662,6 +4665,13 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg)
 		cfg->preferred_lft = timeout;
 	}
 
+	if (cfg->peer_pfx &&
+	    memcmp(&ifp->peer_addr, cfg->peer_pfx, sizeof(struct in6_addr))) {
+		if (!ipv6_addr_any(&ifp->peer_addr))
+			cleanup_prefix_route(ifp, expires, true, true);
+		new_peer = true;
+	}
+
 	spin_lock_bh(&ifp->lock);
 	was_managetempaddr = ifp->flags & IFA_F_MANAGETEMPADDR;
 	had_prefixroute = ifp->flags & IFA_F_PERMANENT &&
@@ -4677,6 +4687,9 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg)
 	if (cfg->rt_priority && cfg->rt_priority != ifp->rt_priority)
 		ifp->rt_priority = cfg->rt_priority;
 
+	if (new_peer)
+		ifp->peer_addr = *cfg->peer_pfx;
+
 	spin_unlock_bh(&ifp->lock);
 	if (!(ifp->flags&IFA_F_TENTATIVE))
 		ipv6_ifa_notify(0, ifp);
@@ -4712,7 +4725,7 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg)
 
 		if (action != CLEANUP_PREFIX_RT_NOP) {
 			cleanup_prefix_route(ifp, rt_expires,
-				action == CLEANUP_PREFIX_RT_DEL);
+				action == CLEANUP_PREFIX_RT_DEL, false);
 		}
 	}
 
-- 
2.20.1


From 2499e03bf20a407c73429dc8967e1af67f4973d3 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Tue, 3 Mar 2020 14:37:36 +0800
Subject: [PATCH 62/66] selftests/net/fib_tests: update addr_metric_test for
 peer route testing

[ Upstream commit 0d29169a708bf730ede287248e429d579f432d1d ]

This patch update {ipv4, ipv6}_addr_metric_test with
1. Set metric of address with peer route and see if the route added
correctly.
2. Modify metric and peer address for peer route and see if the route
changed correctly.

Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/fib_tests.sh | 34 +++++++++++++++++++++---
 1 file changed, 31 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 60273f1bc7d9..b7616704b55e 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -1041,6 +1041,27 @@ ipv6_addr_metric_test()
 	fi
 	log_test $rc 0 "Prefix route with metric on link up"
 
+	# verify peer metric added correctly
+	set -e
+	run_cmd "$IP -6 addr flush dev dummy2"
+	run_cmd "$IP -6 addr add dev dummy2 2001:db8:104::1 peer 2001:db8:104::2 metric 260"
+	set +e
+
+	check_route6 "2001:db8:104::1 dev dummy2 proto kernel metric 260"
+	log_test $? 0 "Set metric with peer route on local side"
+	log_test $? 0 "User specified metric on local address"
+	check_route6 "2001:db8:104::2 dev dummy2 proto kernel metric 260"
+	log_test $? 0 "Set metric with peer route on peer side"
+
+	set -e
+	run_cmd "$IP -6 addr change dev dummy2 2001:db8:104::1 peer 2001:db8:104::3 metric 261"
+	set +e
+
+	check_route6 "2001:db8:104::1 dev dummy2 proto kernel metric 261"
+	log_test $? 0 "Modify metric and peer address on local side"
+	check_route6 "2001:db8:104::3 dev dummy2 proto kernel metric 261"
+	log_test $? 0 "Modify metric and peer address on peer side"
+
 	$IP li del dummy1
 	$IP li del dummy2
 	cleanup
@@ -1457,13 +1478,20 @@ ipv4_addr_metric_test()
 
 	run_cmd "$IP addr flush dev dummy2"
 	run_cmd "$IP addr add dev dummy2 172.16.104.1/32 peer 172.16.104.2 metric 260"
-	run_cmd "$IP addr change dev dummy2 172.16.104.1/32 peer 172.16.104.2 metric 261"
 	rc=$?
 	if [ $rc -eq 0 ]; then
-		check_route "172.16.104.2 dev dummy2 proto kernel scope link src 172.16.104.1 metric 261"
+		check_route "172.16.104.2 dev dummy2 proto kernel scope link src 172.16.104.1 metric 260"
+		rc=$?
+	fi
+	log_test $rc 0 "Set metric of address with peer route"
+
+	run_cmd "$IP addr change dev dummy2 172.16.104.1/32 peer 172.16.104.3 metric 261"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		check_route "172.16.104.3 dev dummy2 proto kernel scope link src 172.16.104.1 metric 261"
 		rc=$?
 	fi
-	log_test $rc 0 "Modify metric of address with peer route"
+	log_test $rc 0 "Modify metric and peer address for peer route"
 
 	$IP li del dummy1
 	$IP li del dummy2
-- 
2.20.1


From 99df02c86300d4c62c6a4584e0aaf501e37ca3bf Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Tue, 10 Mar 2020 18:38:01 +0100
Subject: [PATCH 63/66] s390/qeth: don't reset default_out_queue

[ Upstream commit 240c1948491b81cfe40f84ea040a8f2a4966f101 ]

When an OSA device in prio-queue setup is reduced to 1 TX queue due to
HW restrictions, we reset its the default_out_queue to 0.

In the old code this was needed so that qeth_get_priority_queue() gets
the queue selection right. But with proper multiqueue support we already
reduced dev->real_num_tx_queues to 1, and so the stack puts all traffic
on txq 0 without even calling .ndo_select_queue.

Thus we can preserve the user's configuration, and apply it if the OSA
device later re-gains support for multiple TX queues.

Fixes: 73dc2daf110f ("s390/qeth: add TX multiqueue support for OSA devices")
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 4fd7b0ceb4ff..42326867e7af 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -1244,7 +1244,6 @@ static int qeth_osa_set_output_queues(struct qeth_card *card, bool single)
 	if (count == 1)
 		dev_info(&card->gdev->dev, "Priority Queueing not supported\n");
 
-	card->qdio.default_out_queue = single ? 0 : QETH_DEFAULT_QUEUE;
 	card->qdio.no_out_queues = count;
 	return 0;
 }
-- 
2.20.1


From c2e1d6dba173a0c6524f388c9fe48ab63f3f0274 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Tue, 10 Mar 2020 18:38:02 +0100
Subject: [PATCH 64/66] s390/qeth: handle error when backing RX buffer

[ Upstream commit 17413852804d7e86e6f0576cca32c1541817800e ]

qeth_init_qdio_queues() fills the RX ring with an initial set of
RX buffers. If qeth_init_input_buffer() fails to back one of the RX
buffers with memory, we need to bail out and report the error.

Fixes: 4a71df50047f ("qeth: new qeth device driver")
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 42326867e7af..d2420707518c 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -2633,12 +2633,12 @@ static int qeth_init_input_buffer(struct qeth_card *card,
 		buf->rx_skb = netdev_alloc_skb(card->dev,
 					       QETH_RX_PULL_LEN + ETH_HLEN);
 		if (!buf->rx_skb)
-			return 1;
+			return -ENOMEM;
 	}
 
 	pool_entry = qeth_find_free_buffer_pool_entry(card);
 	if (!pool_entry)
-		return 1;
+		return -ENOBUFS;
 
 	/*
 	 * since the buffer is accessed only from the input_tasklet
@@ -2682,10 +2682,15 @@ int qeth_init_qdio_queues(struct qeth_card *card)
 	/* inbound queue */
 	qdio_reset_buffers(card->qdio.in_q->qdio_bufs, QDIO_MAX_BUFFERS_PER_Q);
 	memset(&card->rx, 0, sizeof(struct qeth_rx));
+
 	qeth_initialize_working_pool_list(card);
 	/*give only as many buffers to hardware as we have buffer pool entries*/
-	for (i = 0; i < card->qdio.in_buf_pool.buf_count - 1; ++i)
-		qeth_init_input_buffer(card, &card->qdio.in_q->bufs[i]);
+	for (i = 0; i < card->qdio.in_buf_pool.buf_count - 1; i++) {
+		rc = qeth_init_input_buffer(card, &card->qdio.in_q->bufs[i]);
+		if (rc)
+			return rc;
+	}
+
 	card->qdio.in_q->next_buf_to_init =
 		card->qdio.in_buf_pool.buf_count - 1;
 	rc = do_QDIO(CARD_DDEV(card), QDIO_FLAG_SYNC_INPUT, 0, 0,
-- 
2.20.1


From 0073d8283e748bb040325d52bbc532d5b75ea5c0 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Wed, 11 Mar 2020 16:24:24 +0100
Subject: [PATCH 65/66] net: dsa: Don't instantiate phylink for CPU/DSA ports
 unless needed

[ Upstream commit a20f997010c4ec76eaa55b8cc047d76dcac69f70 ]

By default, DSA drivers should configure CPU and DSA ports to their
maximum speed. In many configurations this is sufficient to make the
link work.

In some cases it is necessary to configure the link to run slower,
e.g. because of limitations of the SoC it is connected to. Or back to
back PHYs are used and the PHY needs to be driven in order to
establish link. In this case, phylink is used.

Only instantiate phylink if it is required. If there is no PHY, or no
fixed link properties, phylink can upset a link which works in the
default configuration.

Fixes: 0e27921816ad ("net: dsa: Use PHYLINK for the CPU/DSA ports")
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/port.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/net/dsa/port.c b/net/dsa/port.c
index a26756d1dd39..f190b129260e 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -653,9 +653,14 @@ static int dsa_port_phylink_register(struct dsa_port *dp)
 int dsa_port_link_register_of(struct dsa_port *dp)
 {
 	struct dsa_switch *ds = dp->ds;
+	struct device_node *phy_np;
 
-	if (!ds->ops->adjust_link)
-		return dsa_port_phylink_register(dp);
+	if (!ds->ops->adjust_link) {
+		phy_np = of_parse_phandle(dp->dn, "phy-handle", 0);
+		if (of_phy_is_fixed_link(dp->dn) || phy_np)
+			return dsa_port_phylink_register(dp);
+		return 0;
+	}
 
 	dev_warn(ds->dev,
 		 "Using legacy PHYLIB callbacks. Please migrate to PHYLINK!\n");
@@ -670,11 +675,12 @@ void dsa_port_link_unregister_of(struct dsa_port *dp)
 {
 	struct dsa_switch *ds = dp->ds;
 
-	if (!ds->ops->adjust_link) {
+	if (!ds->ops->adjust_link && dp->pl) {
 		rtnl_lock();
 		phylink_disconnect_phy(dp->pl);
 		rtnl_unlock();
 		phylink_destroy(dp->pl);
+		dp->pl = NULL;
 		return;
 	}
 
-- 
2.20.1


From cb0a025eddc78b09afeb84fe8a7489eb53a86872 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Wed, 11 Mar 2020 21:02:31 +0100
Subject: [PATCH 66/66] net: dsa: mv88e6xxx: Add missing mask of ATU occupancy
 register

[ Upstream commit 012fc74517b25177dfede2ed45cd108258564e4a ]

Only the bottom 12 bits contain the ATU bin occupancy statistics. The
upper bits need masking off.

Fixes: e0c69ca7dfbb ("net: dsa: mv88e6xxx: Add ATU occupancy via devlink resources")
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 3bd988529178..5f88effeb17a 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -2762,6 +2762,8 @@ static u64 mv88e6xxx_devlink_atu_bin_get(struct mv88e6xxx_chip *chip,
 		goto unlock;
 	}
 
+	occupancy &= MV88E6XXX_G2_ATU_STATS_MASK;
+
 unlock:
 	mv88e6xxx_reg_unlock(chip);
 
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Fri, Mar 13, 2020 at 09:52:04PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v5.4 and
> v5.5 -stable, respectively.

Lots of patches this time, thanks!  All now queued up.

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 105 bytes --]


Please queue up the following networking bug fixes for v5.4
and v5.5 -stable, respectively.

Thank you.

[-- Attachment #2: net_54.mbox --]
[-- Type: Application/Octet-Stream, Size: 116225 bytes --]

From a320e96bb8ccc0474449b24a48255ab30d376019 Mon Sep 17 00:00:00 2001
From: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Date: Thu, 19 Mar 2020 23:08:09 +0530
Subject: [PATCH 01/47] cxgb4: fix throughput drop during Tx backpressure

[ Upstream commit 7affd80802afb6ca92dba47d768632fbde365241 ]

commit 7c3bebc3d868 ("cxgb4: request the TX CIDX updates to status page")
reverted back to getting Tx CIDX updates via DMA, instead of interrupts,
introduced by commit d429005fdf2c ("cxgb4/cxgb4vf: Add support for SGE
doorbell queue timer")

However, it missed reverting back several code changes where Tx CIDX
updates are not explicitly requested during backpressure when using
interrupt mode. These missed changes cause slow recovery during
backpressure because the corresponding interrupt no longer comes and
hence results in Tx throughput drop.

So, revert back these missed code changes, as well, which will allow
explicitly requesting Tx CIDX updates when backpressure happens.
This enables the corresponding interrupt with Tx CIDX update message
to get generated and hence speed up recovery and restore back
throughput.

Fixes: 7c3bebc3d868 ("cxgb4: request the TX CIDX updates to status page")
Fixes: d429005fdf2c ("cxgb4/cxgb4vf: Add support for SGE doorbell queue timer")
Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/sge.c | 42 ++----------------------
 1 file changed, 2 insertions(+), 40 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index 928bfea5457b..3af6d8376a66 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -1469,16 +1469,7 @@ out_free:	dev_kfree_skb_any(skb);
 		 * has opened up.
 		 */
 		eth_txq_stop(q);
-
-		/* If we're using the SGE Doorbell Queue Timer facility, we
-		 * don't need to ask the Firmware to send us Egress Queue CIDX
-		 * Updates: the Hardware will do this automatically.  And
-		 * since we send the Ingress Queue CIDX Updates to the
-		 * corresponding Ethernet Response Queue, we'll get them very
-		 * quickly.
-		 */
-		if (!q->dbqt)
-			wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F;
+		wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F;
 	}
 
 	wr = (void *)&q->q.desc[q->q.pidx];
@@ -1792,16 +1783,7 @@ static netdev_tx_t cxgb4_vf_eth_xmit(struct sk_buff *skb,
 		 * has opened up.
 		 */
 		eth_txq_stop(txq);
-
-		/* If we're using the SGE Doorbell Queue Timer facility, we
-		 * don't need to ask the Firmware to send us Egress Queue CIDX
-		 * Updates: the Hardware will do this automatically.  And
-		 * since we send the Ingress Queue CIDX Updates to the
-		 * corresponding Ethernet Response Queue, we'll get them very
-		 * quickly.
-		 */
-		if (!txq->dbqt)
-			wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F;
+		wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F;
 	}
 
 	/* Start filling in our Work Request.  Note that we do _not_ handle
@@ -2924,26 +2906,6 @@ static void t4_tx_completion_handler(struct sge_rspq *rspq,
 	}
 
 	txq = &s->ethtxq[pi->first_qset + rspq->idx];
-
-	/* We've got the Hardware Consumer Index Update in the Egress Update
-	 * message.  If we're using the SGE Doorbell Queue Timer mechanism,
-	 * these Egress Update messages will be our sole CIDX Updates we get
-	 * since we don't want to chew up PCIe bandwidth for both Ingress
-	 * Messages and Status Page writes.  However, The code which manages
-	 * reclaiming successfully DMA'ed TX Work Requests uses the CIDX value
-	 * stored in the Status Page at the end of the TX Queue.  It's easiest
-	 * to simply copy the CIDX Update value from the Egress Update message
-	 * to the Status Page.  Also note that no Endian issues need to be
-	 * considered here since both are Big Endian and we're just copying
-	 * bytes consistently ...
-	 */
-	if (txq->dbqt) {
-		struct cpl_sge_egr_update *egr;
-
-		egr = (struct cpl_sge_egr_update *)rsp;
-		WRITE_ONCE(txq->q.stat->cidx, egr->cidx);
-	}
-
 	t4_sge_eth_txq_egress_update(adapter, txq, -1);
 }
 
-- 
2.20.1


From 724d4fe578c490f509fa46212b994ddf3f44f616 Mon Sep 17 00:00:00 2001
From: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Date: Thu, 19 Mar 2020 23:08:10 +0530
Subject: [PATCH 02/47] cxgb4: fix Txq restart check during backpressure

[ Upstream commit f1f20a8666c55cb534b8f3fc1130eebf01a06155 ]

Driver reclaims descriptors in much smaller batches, even if hardware
indicates more to reclaim, during backpressure. So, fix the check to
restart the Txq during backpressure, by looking at how many
descriptors hardware had indicated to reclaim, and not on how many
descriptors that driver had actually reclaimed. Once the Txq is
restarted, driver will reclaim even more descriptors when Tx path
is entered again.

Fixes: d429005fdf2c ("cxgb4/cxgb4vf: Add support for SGE doorbell queue timer")
Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/sge.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index 3af6d8376a66..3a45ac8f0e01 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -1324,8 +1324,9 @@ static inline void t6_fill_tnl_lso(struct sk_buff *skb,
 int t4_sge_eth_txq_egress_update(struct adapter *adap, struct sge_eth_txq *eq,
 				 int maxreclaim)
 {
+	unsigned int reclaimed, hw_cidx;
 	struct sge_txq *q = &eq->q;
-	unsigned int reclaimed;
+	int hw_in_use;
 
 	if (!q->in_use || !__netif_tx_trylock(eq->txq))
 		return 0;
@@ -1333,12 +1334,17 @@ int t4_sge_eth_txq_egress_update(struct adapter *adap, struct sge_eth_txq *eq,
 	/* Reclaim pending completed TX Descriptors. */
 	reclaimed = reclaim_completed_tx(adap, &eq->q, maxreclaim, true);
 
+	hw_cidx = ntohs(READ_ONCE(q->stat->cidx));
+	hw_in_use = q->pidx - hw_cidx;
+	if (hw_in_use < 0)
+		hw_in_use += q->size;
+
 	/* If the TX Queue is currently stopped and there's now more than half
 	 * the queue available, restart it.  Otherwise bail out since the rest
 	 * of what we want do here is with the possibility of shipping any
 	 * currently buffered Coalesced TX Work Request.
 	 */
-	if (netif_tx_queue_stopped(eq->txq) && txq_avail(q) > (q->size / 2)) {
+	if (netif_tx_queue_stopped(eq->txq) && hw_in_use < (q->size / 2)) {
 		netif_tx_wake_queue(eq->txq);
 		eq->q.restarts++;
 	}
-- 
2.20.1


From b70a3e7a3f1f3d012804ffb4c974111bf1d07a5d Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Sat, 14 Mar 2020 08:18:42 +0100
Subject: [PATCH 03/47] geneve: move debug check after netdev unregister

[ Upstream commit 0fda7600c2e174fe27e9cf02e78e345226e441fa ]

The debug check must be done after unregister_netdevice_many() call --
the list_del() for this is done inside .ndo_stop.

Fixes: 2843a25348f8 ("geneve: speedup geneve tunnels dismantle")
Reported-and-tested-by: <syzbot+68a8ed58e3d17c700de5@syzkaller.appspotmail.com>
Cc: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 5c6b7fc04ea6..730ab57201bd 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1845,8 +1845,6 @@ static void geneve_destroy_tunnels(struct net *net, struct list_head *head)
 		if (!net_eq(dev_net(geneve->dev), net))
 			unregister_netdevice_queue(geneve->dev, head);
 	}
-
-	WARN_ON_ONCE(!list_empty(&gn->sock_list));
 }
 
 static void __net_exit geneve_exit_batch_net(struct list_head *net_list)
@@ -1861,6 +1859,12 @@ static void __net_exit geneve_exit_batch_net(struct list_head *net_list)
 	/* unregister the devices gathered above */
 	unregister_netdevice_many(&list);
 	rtnl_unlock();
+
+	list_for_each_entry(net, net_list, exit_list) {
+		const struct geneve_net *gn = net_generic(net, geneve_net_id);
+
+		WARN_ON_ONCE(!list_empty(&gn->sock_list));
+	}
 }
 
 static struct pernet_operations geneve_net_ops = {
-- 
2.20.1


From 061312896d69ef8e6c460f0200e9226e797e5916 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Sat, 21 Mar 2020 06:46:50 +0000
Subject: [PATCH 04/47] hsr: fix general protection fault in hsr_addr_is_self()

[ Upstream commit 3a303cfdd28d5f930a307c82e8a9d996394d5ebd ]

The port->hsr is used in the hsr_handle_frame(), which is a
callback of rx_handler.
hsr master and slaves are initialized in hsr_add_port().
This function initializes several pointers, which includes port->hsr after
registering rx_handler.
So, in the rx_handler routine, un-initialized pointer would be used.
In order to fix this, pointers should be initialized before
registering rx_handler.

Test commands:
    ip netns del left
    ip netns del right
    modprobe -rv veth
    modprobe -rv hsr
    killall ping
    modprobe hsr
    ip netns add left
    ip netns add right
    ip link add veth0 type veth peer name veth1
    ip link add veth2 type veth peer name veth3
    ip link add veth4 type veth peer name veth5
    ip link set veth1 netns left
    ip link set veth3 netns right
    ip link set veth4 netns left
    ip link set veth5 netns right
    ip link set veth0 up
    ip link set veth2 up
    ip link set veth0 address fc:00:00:00:00:01
    ip link set veth2 address fc:00:00:00:00:02
    ip netns exec left ip link set veth1 up
    ip netns exec left ip link set veth4 up
    ip netns exec right ip link set veth3 up
    ip netns exec right ip link set veth5 up
    ip link add hsr0 type hsr slave1 veth0 slave2 veth2
    ip a a 192.168.100.1/24 dev hsr0
    ip link set hsr0 up
    ip netns exec left ip link add hsr1 type hsr slave1 veth1 slave2 veth4
    ip netns exec left ip a a 192.168.100.2/24 dev hsr1
    ip netns exec left ip link set hsr1 up
    ip netns exec left ip n a 192.168.100.1 dev hsr1 lladdr \
	    fc:00:00:00:00:01 nud permanent
    ip netns exec left ip n r 192.168.100.1 dev hsr1 lladdr \
	    fc:00:00:00:00:01 nud permanent
    for i in {1..100}
    do
        ip netns exec left ping 192.168.100.1 &
    done
    ip netns exec left hping3 192.168.100.1 -2 --flood &
    ip netns exec right ip link add hsr2 type hsr slave1 veth3 slave2 veth5
    ip netns exec right ip a a 192.168.100.3/24 dev hsr2
    ip netns exec right ip link set hsr2 up
    ip netns exec right ip n a 192.168.100.1 dev hsr2 lladdr \
	    fc:00:00:00:00:02 nud permanent
    ip netns exec right ip n r 192.168.100.1 dev hsr2 lladdr \
	    fc:00:00:00:00:02 nud permanent
    for i in {1..100}
    do
        ip netns exec right ping 192.168.100.1 &
    done
    ip netns exec right hping3 192.168.100.1 -2 --flood &
    while :
    do
        ip link add hsr0 type hsr slave1 veth0 slave2 veth2
	ip a a 192.168.100.1/24 dev hsr0
	ip link set hsr0 up
	ip link del hsr0
    done

Splat looks like:
[  120.954938][    C0] general protection fault, probably for non-canonical address 0xdffffc0000000006: 0000 [#1]I
[  120.957761][    C0] KASAN: null-ptr-deref in range [0x0000000000000030-0x0000000000000037]
[  120.959064][    C0] CPU: 0 PID: 1511 Comm: hping3 Not tainted 5.6.0-rc5+ #460
[  120.960054][    C0] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[  120.962261][    C0] RIP: 0010:hsr_addr_is_self+0x65/0x2a0 [hsr]
[  120.963149][    C0] Code: 44 24 18 70 73 2f c0 48 c1 eb 03 48 8d 04 13 c7 00 f1 f1 f1 f1 c7 40 04 00 f2 f2 f2 4
[  120.966277][    C0] RSP: 0018:ffff8880d9c09af0 EFLAGS: 00010206
[  120.967293][    C0] RAX: 0000000000000006 RBX: 1ffff1101b38135f RCX: 0000000000000000
[  120.968516][    C0] RDX: dffffc0000000000 RSI: ffff8880d17cb208 RDI: 0000000000000000
[  120.969718][    C0] RBP: 0000000000000030 R08: ffffed101b3c0e3c R09: 0000000000000001
[  120.972203][    C0] R10: 0000000000000001 R11: ffffed101b3c0e3b R12: 0000000000000000
[  120.973379][    C0] R13: ffff8880aaf80100 R14: ffff8880aaf800f2 R15: ffff8880aaf80040
[  120.974410][    C0] FS:  00007f58e693f740(0000) GS:ffff8880d9c00000(0000) knlGS:0000000000000000
[  120.979794][    C0] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  120.980773][    C0] CR2: 00007ffcb8b38f29 CR3: 00000000afe8e001 CR4: 00000000000606f0
[  120.981945][    C0] Call Trace:
[  120.982411][    C0]  <IRQ>
[  120.982848][    C0]  ? hsr_add_node+0x8c0/0x8c0 [hsr]
[  120.983522][    C0]  ? rcu_read_lock_held+0x90/0xa0
[  120.984159][    C0]  ? rcu_read_lock_sched_held+0xc0/0xc0
[  120.984944][    C0]  hsr_handle_frame+0x1db/0x4e0 [hsr]
[  120.985597][    C0]  ? hsr_nl_nodedown+0x2b0/0x2b0 [hsr]
[  120.986289][    C0]  __netif_receive_skb_core+0x6bf/0x3170
[  120.992513][    C0]  ? check_chain_key+0x236/0x5d0
[  120.993223][    C0]  ? do_xdp_generic+0x1460/0x1460
[  120.993875][    C0]  ? register_lock_class+0x14d0/0x14d0
[  120.994609][    C0]  ? __netif_receive_skb_one_core+0x8d/0x160
[  120.995377][    C0]  __netif_receive_skb_one_core+0x8d/0x160
[  120.996204][    C0]  ? __netif_receive_skb_core+0x3170/0x3170
[ ... ]

Reported-by: syzbot+fcf5dd39282ceb27108d@syzkaller.appspotmail.com
Fixes: c5a759117210 ("net/hsr: Use list_head (and rcu) instead of array for slave devices.")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/hsr/hsr_slave.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c
index fbfd0db182b7..a9104d42aafb 100644
--- a/net/hsr/hsr_slave.c
+++ b/net/hsr/hsr_slave.c
@@ -145,16 +145,16 @@ int hsr_add_port(struct hsr_priv *hsr, struct net_device *dev,
 	if (!port)
 		return -ENOMEM;
 
+	port->hsr = hsr;
+	port->dev = dev;
+	port->type = type;
+
 	if (type != HSR_PT_MASTER) {
 		res = hsr_portdev_setup(dev, port);
 		if (res)
 			goto fail_dev_setup;
 	}
 
-	port->hsr = hsr;
-	port->dev = dev;
-	port->type = type;
-
 	list_add_tail_rcu(&port->port_list, &hsr->ports);
 	synchronize_rcu();
 
-- 
2.20.1


From 79a6209f2100cbfd7952adc9d2822bfe16c48251 Mon Sep 17 00:00:00 2001
From: Qian Cai <cai@lca.pw>
Date: Thu, 19 Mar 2020 22:54:21 -0400
Subject: [PATCH 05/47] ipv4: fix a RCU-list lock in inet_dump_fib()

[ Upstream commit dddeb30bfc43926620f954266fd12c65a7206f07 ]

There is a place,

inet_dump_fib()
  fib_table_dump
    fn_trie_dump_leaf()
      hlist_for_each_entry_rcu()

without rcu_read_lock() will trigger a warning,

 WARNING: suspicious RCU usage
 -----------------------------
 net/ipv4/fib_trie.c:2216 RCU-list traversed in non-reader section!!

 other info that might help us debug this:

 rcu_scheduler_active = 2, debug_locks = 1
 1 lock held by ip/1923:
  #0: ffffffff8ce76e40 (rtnl_mutex){+.+.}, at: netlink_dump+0xd6/0x840

 Call Trace:
  dump_stack+0xa1/0xea
  lockdep_rcu_suspicious+0x103/0x10d
  fn_trie_dump_leaf+0x581/0x590
  fib_table_dump+0x15f/0x220
  inet_dump_fib+0x4ad/0x5d0
  netlink_dump+0x350/0x840
  __netlink_dump_start+0x315/0x3e0
  rtnetlink_rcv_msg+0x4d1/0x720
  netlink_rcv_skb+0xf0/0x220
  rtnetlink_rcv+0x15/0x20
  netlink_unicast+0x306/0x460
  netlink_sendmsg+0x44b/0x770
  __sys_sendto+0x259/0x270
  __x64_sys_sendto+0x80/0xa0
  do_syscall_64+0x69/0xf4
  entry_SYSCALL_64_after_hwframe+0x49/0xb3

Fixes: 18a8021a7be3 ("net/ipv4: Plumb support for filtering route dumps")
Signed-off-by: Qian Cai <cai@lca.pw>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_frontend.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 71c78d223dfd..48bf3b9be475 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1007,7 +1007,9 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 			return -ENOENT;
 		}
 
+		rcu_read_lock();
 		err = fib_table_dump(tb, skb, cb, &filter);
+		rcu_read_unlock();
 		return skb->len ? : err;
 	}
 
-- 
2.20.1


From c16333bec01d98bacce447466381d96cd06851f8 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Sun, 22 Mar 2020 13:51:13 -0400
Subject: [PATCH 06/47] macsec: restrict to ethernet devices

[ Upstream commit b06d072ccc4b1acd0147b17914b7ad1caa1818bb ]

Only attach macsec to ethernet devices.

Syzbot was able to trigger a KMSAN warning in macsec_handle_frame
by attaching to a phonet device.

Macvlan has a similar check in macvlan_port_create.

v1->v2
  - fix commit message typo

Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macsec.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 6497a5c45220..32c627702ac5 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -16,6 +16,7 @@
 #include <net/genetlink.h>
 #include <net/sock.h>
 #include <net/gro_cells.h>
+#include <linux/if_arp.h>
 
 #include <uapi/linux/if_macsec.h>
 
@@ -3236,6 +3237,8 @@ static int macsec_newlink(struct net *net, struct net_device *dev,
 	real_dev = __dev_get_by_index(net, nla_get_u32(tb[IFLA_LINK]));
 	if (!real_dev)
 		return -ENODEV;
+	if (real_dev->type != ARPHRD_ETHER)
+		return -EINVAL;
 
 	dev->priv_flags |= IFF_MACSEC;
 
-- 
2.20.1


From 11ad822a6f3e201de2f4fe286ea5c9c009574874 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Thu, 19 Mar 2020 13:25:39 +0200
Subject: [PATCH 07/47] mlxsw: pci: Only issue reset when system is ready

[ Upstream commit 6002059d7882c3512e6ac52fa82424272ddfcd5c ]

During initialization the driver issues a software reset command and
then waits for the system status to change back to "ready" state.

However, before issuing the reset command the driver does not check that
the system is actually in "ready" state. On Spectrum-{1,2} systems this
was always the case as the hardware initialization time is very short.
On Spectrum-3 systems this is no longer the case. This results in the
software reset command timing-out and the driver failing to load:

[ 6.347591] mlxsw_spectrum3 0000:06:00.0: Cmd exec timed-out (opcode=40(ACCESS_REG),opcode_mod=0,in_mod=0)
[ 6.358382] mlxsw_spectrum3 0000:06:00.0: Reg cmd access failed (reg_id=9023(mrsr),type=write)
[ 6.368028] mlxsw_spectrum3 0000:06:00.0: cannot register bus device
[ 6.375274] mlxsw_spectrum3: probe of 0000:06:00.0 failed with error -110

Fix this by waiting for the system to become ready both before issuing
the reset command and afterwards. In case of failure, print the last
system status to aid in debugging.

Fixes: da382875c616 ("mlxsw: spectrum: Extend to support Spectrum-3 ASIC")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/pci.c | 50 ++++++++++++++++++-----
 1 file changed, 39 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index 615455a21567..f3d1f9411d10 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -1318,36 +1318,64 @@ static void mlxsw_pci_mbox_free(struct mlxsw_pci *mlxsw_pci,
 			    mbox->mapaddr);
 }
 
-static int mlxsw_pci_sw_reset(struct mlxsw_pci *mlxsw_pci,
-			      const struct pci_device_id *id)
+static int mlxsw_pci_sys_ready_wait(struct mlxsw_pci *mlxsw_pci,
+				    const struct pci_device_id *id,
+				    u32 *p_sys_status)
 {
 	unsigned long end;
-	char mrsr_pl[MLXSW_REG_MRSR_LEN];
-	int err;
+	u32 val;
 
-	mlxsw_reg_mrsr_pack(mrsr_pl);
-	err = mlxsw_reg_write(mlxsw_pci->core, MLXSW_REG(mrsr), mrsr_pl);
-	if (err)
-		return err;
 	if (id->device == PCI_DEVICE_ID_MELLANOX_SWITCHX2) {
 		msleep(MLXSW_PCI_SW_RESET_TIMEOUT_MSECS);
 		return 0;
 	}
 
-	/* We must wait for the HW to become responsive once again. */
+	/* We must wait for the HW to become responsive. */
 	msleep(MLXSW_PCI_SW_RESET_WAIT_MSECS);
 
 	end = jiffies + msecs_to_jiffies(MLXSW_PCI_SW_RESET_TIMEOUT_MSECS);
 	do {
-		u32 val = mlxsw_pci_read32(mlxsw_pci, FW_READY);
-
+		val = mlxsw_pci_read32(mlxsw_pci, FW_READY);
 		if ((val & MLXSW_PCI_FW_READY_MASK) == MLXSW_PCI_FW_READY_MAGIC)
 			return 0;
 		cond_resched();
 	} while (time_before(jiffies, end));
+
+	*p_sys_status = val & MLXSW_PCI_FW_READY_MASK;
+
 	return -EBUSY;
 }
 
+static int mlxsw_pci_sw_reset(struct mlxsw_pci *mlxsw_pci,
+			      const struct pci_device_id *id)
+{
+	struct pci_dev *pdev = mlxsw_pci->pdev;
+	char mrsr_pl[MLXSW_REG_MRSR_LEN];
+	u32 sys_status;
+	int err;
+
+	err = mlxsw_pci_sys_ready_wait(mlxsw_pci, id, &sys_status);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to reach system ready status before reset. Status is 0x%x\n",
+			sys_status);
+		return err;
+	}
+
+	mlxsw_reg_mrsr_pack(mrsr_pl);
+	err = mlxsw_reg_write(mlxsw_pci->core, MLXSW_REG(mrsr), mrsr_pl);
+	if (err)
+		return err;
+
+	err = mlxsw_pci_sys_ready_wait(mlxsw_pci, id, &sys_status);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to reach system ready status after reset. Status is 0x%x\n",
+			sys_status);
+		return err;
+	}
+
+	return 0;
+}
+
 static int mlxsw_pci_alloc_irq_vectors(struct mlxsw_pci *mlxsw_pci)
 {
 	int err;
-- 
2.20.1


From e8f810cf83beaf245170bf6d9d92da972fe4ae82 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Thu, 26 Mar 2020 16:17:33 +0200
Subject: [PATCH 08/47] mlxsw: spectrum_mr: Fix list iteration in error path

[ Upstream commit f6bf1bafdc2152bb22aff3a4e947f2441a1d49e2 ]

list_for_each_entry_from_reverse() iterates backwards over the list from
the current position, but in the error path we should start from the
previous position.

Fix this by using list_for_each_entry_continue_reverse() instead.

This suppresses the following error from coccinelle:

drivers/net/ethernet/mellanox/mlxsw//spectrum_mr.c:655:34-38: ERROR:
invalid reference to the index variable of the iterator on line 636

Fixes: c011ec1bbfd6 ("mlxsw: spectrum: Add the multicast routing offloading logic")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
index 54275624718b..336e5ecc68f8 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
@@ -637,12 +637,12 @@ static int mlxsw_sp_mr_vif_resolve(struct mlxsw_sp_mr_table *mr_table,
 	return 0;
 
 err_erif_unresolve:
-	list_for_each_entry_from_reverse(erve, &mr_vif->route_evif_list,
-					 vif_node)
+	list_for_each_entry_continue_reverse(erve, &mr_vif->route_evif_list,
+					     vif_node)
 		mlxsw_sp_mr_route_evif_unresolve(mr_table, erve);
 err_irif_unresolve:
-	list_for_each_entry_from_reverse(irve, &mr_vif->route_ivif_list,
-					 vif_node)
+	list_for_each_entry_continue_reverse(irve, &mr_vif->route_ivif_list,
+					     vif_node)
 		mlxsw_sp_mr_route_ivif_unresolve(mr_table, irve);
 	mr_vif->rif = NULL;
 	return err;
-- 
2.20.1


From 823d6e12fd32165111a66379aa181755b7733bc3 Mon Sep 17 00:00:00 2001
From: Bruno Meneguele <bmeneg@redhat.com>
Date: Thu, 12 Mar 2020 20:08:20 -0300
Subject: [PATCH 09/47] net/bpfilter: fix dprintf usage for /dev/kmsg

[ Upstream commit 13d0f7b814d9b4c67e60d8c2820c86ea181e7d99 ]

The bpfilter UMH code was recently changed to log its informative messages to
/dev/kmsg, however this interface doesn't support SEEK_CUR yet, used by
dprintf(). As result dprintf() returns -EINVAL and doesn't log anything.

However there already had some discussions about supporting SEEK_CUR into
/dev/kmsg interface in the past it wasn't concluded. Since the only user of
that from userspace perspective inside the kernel is the bpfilter UMH
(userspace) module it's better to correct it here instead waiting a conclusion
on the interface.

Fixes: 36c4357c63f3 ("net: bpfilter: print umh messages to /dev/kmsg")
Signed-off-by: Bruno Meneguele <bmeneg@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bpfilter/main.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/net/bpfilter/main.c b/net/bpfilter/main.c
index 77396a098fbe..efea4874743e 100644
--- a/net/bpfilter/main.c
+++ b/net/bpfilter/main.c
@@ -10,7 +10,7 @@
 #include <asm/unistd.h>
 #include "msgfmt.h"
 
-int debug_fd;
+FILE *debug_f;
 
 static int handle_get_cmd(struct mbox_request *cmd)
 {
@@ -35,9 +35,10 @@ static void loop(void)
 		struct mbox_reply reply;
 		int n;
 
+		fprintf(debug_f, "testing the buffer\n");
 		n = read(0, &req, sizeof(req));
 		if (n != sizeof(req)) {
-			dprintf(debug_fd, "invalid request %d\n", n);
+			fprintf(debug_f, "invalid request %d\n", n);
 			return;
 		}
 
@@ -47,7 +48,7 @@ static void loop(void)
 
 		n = write(1, &reply, sizeof(reply));
 		if (n != sizeof(reply)) {
-			dprintf(debug_fd, "reply failed %d\n", n);
+			fprintf(debug_f, "reply failed %d\n", n);
 			return;
 		}
 	}
@@ -55,9 +56,10 @@ static void loop(void)
 
 int main(void)
 {
-	debug_fd = open("/dev/kmsg", 00000002);
-	dprintf(debug_fd, "Started bpfilter\n");
+	debug_f = fopen("/dev/kmsg", "w");
+	setvbuf(debug_f, 0, _IOLBF, 0);
+	fprintf(debug_f, "Started bpfilter\n");
 	loop();
-	close(debug_fd);
+	fclose(debug_f);
 	return 0;
 }
-- 
2.20.1


From 87cb59df634528b346ef4fb80aff10f4c9068a62 Mon Sep 17 00:00:00 2001
From: Zh-yuan Ye <ye.zh-yuan@socionext.com>
Date: Tue, 24 Mar 2020 17:28:25 +0900
Subject: [PATCH 10/47] net: cbs: Fix software cbs to consider packet sending
 time

[ Upstream commit 961d0e5b32946703125964f9f5b6321d60f4d706 ]

Currently the software CBS does not consider the packet sending time
when depleting the credits. It caused the throughput to be
Idleslope[kbps] * (Port transmit rate[kbps] / |Sendslope[kbps]|) where
Idleslope * (Port transmit rate / (Idleslope + |Sendslope|)) = Idleslope
is expected. In order to fix the issue above, this patch takes the time
when the packet sending completes into account by moving the anchor time
variable "last" ahead to the send completion time upon transmission and
adding wait when the next dequeue request comes before the send
completion time of the previous packet.

changelog:
V2->V3:
 - remove unnecessary whitespace cleanup
 - add the checks if port_rate is 0 before division

V1->V2:
 - combine variable "send_completed" into "last"
 - add the comment for estimate of the packet sending

Fixes: 585d763af09c ("net/sched: Introduce Credit Based Shaper (CBS) qdisc")
Signed-off-by: Zh-yuan Ye <ye.zh-yuan@socionext.com>
Reviewed-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_cbs.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c
index b2905b03a432..2eaac2ff380f 100644
--- a/net/sched/sch_cbs.c
+++ b/net/sched/sch_cbs.c
@@ -181,6 +181,11 @@ static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch)
 	s64 credits;
 	int len;
 
+	/* The previous packet is still being sent */
+	if (now < q->last) {
+		qdisc_watchdog_schedule_ns(&q->watchdog, q->last);
+		return NULL;
+	}
 	if (q->credits < 0) {
 		credits = timediff_to_credits(now - q->last, q->idleslope);
 
@@ -212,7 +217,12 @@ static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch)
 	credits += q->credits;
 
 	q->credits = max_t(s64, credits, q->locredit);
-	q->last = now;
+	/* Estimate of the transmission of the last byte of the packet in ns */
+	if (unlikely(atomic64_read(&q->port_rate) == 0))
+		q->last = now;
+	else
+		q->last = now + div64_s64(len * NSEC_PER_SEC,
+					  atomic64_read(&q->port_rate));
 
 	return skb;
 }
-- 
2.20.1


From 5d009705db11f28c9176d63ad74ada6f9aab1928 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Sun, 22 Mar 2020 13:58:50 -0700
Subject: [PATCH 11/47] net: dsa: Fix duplicate frames flooded by learning

[ Upstream commit 0e62f543bed03a64495bd2651d4fe1aa4bcb7fe5 ]

When both the switch and the bridge are learning about new addresses,
switch ports attached to the bridge would see duplicate ARP frames
because both entities would attempt to send them.

Fixes: 5037d532b83d ("net: dsa: add Broadcom tag RX/TX handler")
Reported-by: Maxime Bizon <mbizon@freebox.fr>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Vivien Didelot <vivien.didelot@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/tag_brcm.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c
index 9c3114179690..9169b63a89e3 100644
--- a/net/dsa/tag_brcm.c
+++ b/net/dsa/tag_brcm.c
@@ -140,6 +140,8 @@ static struct sk_buff *brcm_tag_rcv_ll(struct sk_buff *skb,
 	/* Remove Broadcom tag and update checksum */
 	skb_pull_rcsum(skb, BRCM_TAG_LEN);
 
+	skb->offload_fwd_mark = 1;
+
 	return skb;
 }
 #endif
-- 
2.20.1


From 276cda0e4186205faca83615f7bc0818302cc44b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ren=C3=A9=20van=20Dorst?= <opensource@vdorst.com>
Date: Thu, 19 Mar 2020 14:47:56 +0100
Subject: [PATCH 12/47] net: dsa: mt7530: Change the LINK bit to reflect the
 link status
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 22259471b51925353bd7b16f864c79fdd76e425e ]

Andrew reported:

After a number of network port link up/down changes, sometimes the switch
port gets stuck in a state where it thinks it is still transmitting packets
but the cpu port is not actually transmitting anymore. In this state you
will see a message on the console
"mtk_soc_eth 1e100000.ethernet eth0: transmit timed out" and the Tx counter
in ifconfig will be incrementing on virtual port, but not incrementing on
cpu port.

The issue is that MAC TX/RX status has no impact on the link status or
queue manager of the switch. So the queue manager just queues up packets
of a disabled port and sends out pause frames when the queue is full.

Change the LINK bit to reflect the link status.

Fixes: b8f126a8d543 ("net-next: dsa: add dsa support for Mediatek MT7530 switch")
Reported-by: Andrew Smith <andrew.smith@digi.com>
Signed-off-by: René van Dorst <opensource@vdorst.com>
Reviewed-by: Vivien Didelot <vivien.didelot@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mt7530.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index 1d8d36de4d20..e0e932f0aed1 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -566,7 +566,7 @@ mt7530_mib_reset(struct dsa_switch *ds)
 static void
 mt7530_port_set_status(struct mt7530_priv *priv, int port, int enable)
 {
-	u32 mask = PMCR_TX_EN | PMCR_RX_EN;
+	u32 mask = PMCR_TX_EN | PMCR_RX_EN | PMCR_FORCE_LNK;
 
 	if (enable)
 		mt7530_set(priv, MT7530_PMCR_P(port), mask);
@@ -1439,7 +1439,7 @@ static void mt7530_phylink_mac_config(struct dsa_switch *ds, int port,
 	mcr_new &= ~(PMCR_FORCE_SPEED_1000 | PMCR_FORCE_SPEED_100 |
 		     PMCR_FORCE_FDX | PMCR_TX_FC_EN | PMCR_RX_FC_EN);
 	mcr_new |= PMCR_IFG_XMIT(1) | PMCR_MAC_MODE | PMCR_BACKOFF_EN |
-		   PMCR_BACKPR_EN | PMCR_FORCE_MODE | PMCR_FORCE_LNK;
+		   PMCR_BACKPR_EN | PMCR_FORCE_MODE;
 
 	/* Are we connected to external phy */
 	if (port == 5 && dsa_is_user_port(ds, 5))
-- 
2.20.1


From e0280a77332ef71f51df3371cec00b166d90971a Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Tue, 24 Mar 2020 11:45:34 +0200
Subject: [PATCH 13/47] net: dsa: tag_8021q: replace dsa_8021q_remove_header
 with __skb_vlan_pop

[ Upstream commit e80f40cbe4dd51371818e967d40da8fe305db5e4 ]

Not only did this wheel did not need reinventing, but there is also
an issue with it: It doesn't remove the VLAN header in a way that
preserves the L2 payload checksum when that is being provided by the DSA
master hw.  It should recalculate checksum both for the push, before
removing the header, and for the pull afterwards. But the current
implementation is quite dizzying, with pulls followed immediately
afterwards by pushes, the memmove is done before the push, etc.  This
makes a DSA master with RX checksumming offload to print stack traces
with the infamous 'hw csum failure' message.

So remove the dsa_8021q_remove_header function and replace it with
something that actually works with inet checksumming.

Fixes: d461933638ae ("net: dsa: tag_8021q: Create helper function for removing VLAN header")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/dsa/8021q.h |  7 -------
 net/dsa/tag_8021q.c       | 43 ---------------------------------------
 net/dsa/tag_sja1105.c     | 19 ++++++++---------
 3 files changed, 9 insertions(+), 60 deletions(-)

diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h
index 0aa803c451a3..c620d9139c28 100644
--- a/include/linux/dsa/8021q.h
+++ b/include/linux/dsa/8021q.h
@@ -28,8 +28,6 @@ int dsa_8021q_rx_switch_id(u16 vid);
 
 int dsa_8021q_rx_source_port(u16 vid);
 
-struct sk_buff *dsa_8021q_remove_header(struct sk_buff *skb);
-
 #else
 
 int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index,
@@ -64,11 +62,6 @@ int dsa_8021q_rx_source_port(u16 vid)
 	return 0;
 }
 
-struct sk_buff *dsa_8021q_remove_header(struct sk_buff *skb)
-{
-	return NULL;
-}
-
 #endif /* IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q) */
 
 #endif /* _NET_DSA_8021Q_H */
diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c
index 9e5a883a9f0c..ebe73848d1cf 100644
--- a/net/dsa/tag_8021q.c
+++ b/net/dsa/tag_8021q.c
@@ -299,49 +299,6 @@ struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev,
 }
 EXPORT_SYMBOL_GPL(dsa_8021q_xmit);
 
-/* In the DSA packet_type handler, skb->data points in the middle of the VLAN
- * tag, after tpid and before tci. This is because so far, ETH_HLEN
- * (DMAC, SMAC, EtherType) bytes were pulled.
- * There are 2 bytes of VLAN tag left in skb->data, and upper
- * layers expect the 'real' EtherType to be consumed as well.
- * Coincidentally, a VLAN header is also of the same size as
- * the number of bytes that need to be pulled.
- *
- * skb_mac_header                                      skb->data
- * |                                                       |
- * v                                                       v
- * |   |   |   |   |   |   |   |   |   |   |   |   |   |   |   |   |   |   |
- * +-----------------------+-----------------------+-------+-------+-------+
- * |    Destination MAC    |      Source MAC       |  TPID |  TCI  | EType |
- * +-----------------------+-----------------------+-------+-------+-------+
- * ^                                               |               |
- * |<--VLAN_HLEN-->to                              <---VLAN_HLEN--->
- * from            |
- *       >>>>>>>   v
- *       >>>>>>>   |   |   |   |   |   |   |   |   |   |   |   |   |   |   |
- *       >>>>>>>   +-----------------------+-----------------------+-------+
- *       >>>>>>>   |    Destination MAC    |      Source MAC       | EType |
- *                 +-----------------------+-----------------------+-------+
- *                 ^                                                       ^
- * (now part of    |                                                       |
- *  skb->head)     skb_mac_header                                  skb->data
- */
-struct sk_buff *dsa_8021q_remove_header(struct sk_buff *skb)
-{
-	u8 *from = skb_mac_header(skb);
-	u8 *dest = from + VLAN_HLEN;
-
-	memmove(dest, from, ETH_HLEN - VLAN_HLEN);
-	skb_pull(skb, VLAN_HLEN);
-	skb_push(skb, ETH_HLEN);
-	skb_reset_mac_header(skb);
-	skb_reset_mac_len(skb);
-	skb_pull_rcsum(skb, ETH_HLEN);
-
-	return skb;
-}
-EXPORT_SYMBOL_GPL(dsa_8021q_remove_header);
-
 static const struct dsa_device_ops dsa_8021q_netdev_ops = {
 	.name		= "8021q",
 	.proto		= DSA_TAG_PROTO_8021Q,
diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c
index 63ef2a14c934..12f3ce52e62e 100644
--- a/net/dsa/tag_sja1105.c
+++ b/net/dsa/tag_sja1105.c
@@ -238,14 +238,14 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb,
 {
 	struct sja1105_meta meta = {0};
 	int source_port, switch_id;
-	struct vlan_ethhdr *hdr;
+	struct ethhdr *hdr;
 	u16 tpid, vid, tci;
 	bool is_link_local;
 	bool is_tagged;
 	bool is_meta;
 
-	hdr = vlan_eth_hdr(skb);
-	tpid = ntohs(hdr->h_vlan_proto);
+	hdr = eth_hdr(skb);
+	tpid = ntohs(hdr->h_proto);
 	is_tagged = (tpid == ETH_P_SJA1105);
 	is_link_local = sja1105_is_link_local(skb);
 	is_meta = sja1105_is_meta_frame(skb);
@@ -254,7 +254,12 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb,
 
 	if (is_tagged) {
 		/* Normal traffic path. */
-		tci = ntohs(hdr->h_vlan_TCI);
+		skb_push_rcsum(skb, ETH_HLEN);
+		__skb_vlan_pop(skb, &tci);
+		skb_pull_rcsum(skb, ETH_HLEN);
+		skb_reset_network_header(skb);
+		skb_reset_transport_header(skb);
+
 		vid = tci & VLAN_VID_MASK;
 		source_port = dsa_8021q_rx_source_port(vid);
 		switch_id = dsa_8021q_rx_switch_id(vid);
@@ -283,12 +288,6 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb,
 		return NULL;
 	}
 
-	/* Delete/overwrite fake VLAN header, DSA expects to not find
-	 * it there, see dsa_switch_rcv: skb_push(skb, ETH_HLEN).
-	 */
-	if (is_tagged)
-		skb = dsa_8021q_remove_header(skb);
-
 	return sja1105_rcv_meta_state_machine(skb, &meta, is_link_local,
 					      is_meta);
 }
-- 
2.20.1


From c8bb33ec4ec54cdd4084ca85e6be3431c4241487 Mon Sep 17 00:00:00 2001
From: "Guilherme G. Piccoli" <gpiccoli@canonical.com>
Date: Fri, 20 Mar 2020 09:55:34 -0300
Subject: [PATCH 14/47] net: ena: Add PCI shutdown handler to allow safe kexec

[ Upstream commit 428c491332bca498c8eb2127669af51506c346c7 ]

Currently ENA only provides the PCI remove() handler, used during rmmod
for example. This is not called on shutdown/kexec path; we are potentially
creating a failure scenario on kexec:

(a) Kexec is triggered, no shutdown() / remove() handler is called for ENA;
instead pci_device_shutdown() clears the master bit of the PCI device,
stopping all DMA transactions;

(b) Kexec reboot happens and the device gets enabled again, likely having
its FW with that DMA transaction buffered; then it may trigger the (now
invalid) memory operation in the new kernel, corrupting kernel memory area.

This patch aims to prevent this, by implementing a shutdown() handler
quite similar to the remove() one - the difference being the handling
of the netdev, which is unregistered on remove(), but following the
convention observed in other drivers, it's only detached on shutdown().

This prevents an odd issue in AWS Nitro instances, in which after the 2nd
kexec the next one will fail with an initrd corruption, caused by a wild
DMA write to invalid kernel memory. The lspci output for the adapter
present in my instance is:

00:05.0 Ethernet controller [0200]: Amazon.com, Inc. Elastic Network
Adapter (ENA) [1d0f:ec20]

Suggested-by: Gavin Shan <gshan@redhat.com>
Signed-off-by: Guilherme G. Piccoli <gpiccoli@canonical.com>
Acked-by: Sameeh Jubran <sameehj@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 51 ++++++++++++++++----
 1 file changed, 41 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index f0cddf250cfd..26325f7b3c1f 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -3652,13 +3652,15 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 /*****************************************************************************/
 
-/* ena_remove - Device Removal Routine
+/* __ena_shutoff - Helper used in both PCI remove/shutdown routines
  * @pdev: PCI device information struct
+ * @shutdown: Is it a shutdown operation? If false, means it is a removal
  *
- * ena_remove is called by the PCI subsystem to alert the driver
- * that it should release a PCI device.
+ * __ena_shutoff is a helper routine that does the real work on shutdown and
+ * removal paths; the difference between those paths is with regards to whether
+ * dettach or unregister the netdevice.
  */
-static void ena_remove(struct pci_dev *pdev)
+static void __ena_shutoff(struct pci_dev *pdev, bool shutdown)
 {
 	struct ena_adapter *adapter = pci_get_drvdata(pdev);
 	struct ena_com_dev *ena_dev;
@@ -3677,13 +3679,17 @@ static void ena_remove(struct pci_dev *pdev)
 
 	cancel_work_sync(&adapter->reset_task);
 
-	rtnl_lock();
+	rtnl_lock(); /* lock released inside the below if-else block */
 	ena_destroy_device(adapter, true);
-	rtnl_unlock();
-
-	unregister_netdev(netdev);
-
-	free_netdev(netdev);
+	if (shutdown) {
+		netif_device_detach(netdev);
+		dev_close(netdev);
+		rtnl_unlock();
+	} else {
+		rtnl_unlock();
+		unregister_netdev(netdev);
+		free_netdev(netdev);
+	}
 
 	ena_com_rss_destroy(ena_dev);
 
@@ -3698,6 +3704,30 @@ static void ena_remove(struct pci_dev *pdev)
 	vfree(ena_dev);
 }
 
+/* ena_remove - Device Removal Routine
+ * @pdev: PCI device information struct
+ *
+ * ena_remove is called by the PCI subsystem to alert the driver
+ * that it should release a PCI device.
+ */
+
+static void ena_remove(struct pci_dev *pdev)
+{
+	__ena_shutoff(pdev, false);
+}
+
+/* ena_shutdown - Device Shutdown Routine
+ * @pdev: PCI device information struct
+ *
+ * ena_shutdown is called by the PCI subsystem to alert the driver that
+ * a shutdown/reboot (or kexec) is happening and device must be disabled.
+ */
+
+static void ena_shutdown(struct pci_dev *pdev)
+{
+	__ena_shutoff(pdev, true);
+}
+
 #ifdef CONFIG_PM
 /* ena_suspend - PM suspend callback
  * @pdev: PCI device information struct
@@ -3747,6 +3777,7 @@ static struct pci_driver ena_pci_driver = {
 	.id_table	= ena_pci_tbl,
 	.probe		= ena_probe,
 	.remove		= ena_remove,
+	.shutdown	= ena_shutdown,
 #ifdef CONFIG_PM
 	.suspend    = ena_suspend,
 	.resume     = ena_resume,
-- 
2.20.1


From aac1ae4ea65e111adf318d5be5ec30629beb4061 Mon Sep 17 00:00:00 2001
From: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
Date: Mon, 16 Mar 2020 22:56:36 +0800
Subject: [PATCH 15/47] net: mvneta: Fix the case where the last poll did not
 process all rx

[ Upstream commit 065fd83e1be2e1ba0d446a257fd86a3cc7bddb51 ]

For the case where the last mvneta_poll did not process all
RX packets, we need to xor the pp->cause_rx_tx or port->cause_rx_tx
before claculating the rx_queue.

Fixes: 2dcf75e2793c ("net: mvneta: Associate RX queues with each CPU")
Signed-off-by: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 6b1a81df1465..a10ae28ebc8a 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -2804,11 +2804,10 @@ static int mvneta_poll(struct napi_struct *napi, int budget)
 	/* For the case where the last mvneta_poll did not process all
 	 * RX packets
 	 */
-	rx_queue = fls(((cause_rx_tx >> 8) & 0xff));
-
 	cause_rx_tx |= pp->neta_armada3700 ? pp->cause_rx_tx :
 		port->cause_rx_tx;
 
+	rx_queue = fls(((cause_rx_tx >> 8) & 0xff));
 	if (rx_queue) {
 		rx_queue = rx_queue - 1;
 		if (pp->bm_priv)
-- 
2.20.1


From 1b7e09328528c7c16a2a82e7166bb2d6c7b52844 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 13 Mar 2020 12:18:09 -0400
Subject: [PATCH 16/47] net/packet: tpacket_rcv: avoid a producer race
 condition

[ Upstream commit 61fad6816fc10fb8793a925d5c1256d1c3db0cd2 ]

PACKET_RX_RING can cause multiple writers to access the same slot if a
fast writer wraps the ring while a slow writer is still copying. This
is particularly likely with few, large, slots (e.g., GSO packets).

Synchronize kernel thread ownership of rx ring slots with a bitmap.

Writers acquire a slot race-free by testing tp_status TP_STATUS_KERNEL
while holding the sk receive queue lock. They release this lock before
copying and set tp_status to TP_STATUS_USER to release to userspace
when done. During copying, another writer may take the lock, also see
TP_STATUS_KERNEL, and start writing to the same slot.

Introduce a new rx_owner_map bitmap with a bit per slot. To acquire a
slot, test and set with the lock held. To release race-free, update
tp_status and owner bit as a transaction, so take the lock again.

This is the one of a variety of discussed options (see Link below):

* instead of a shadow ring, embed the data in the slot itself, such as
in tp_padding. But any test for this field may match a value left by
userspace, causing deadlock.

* avoid the lock on release. This leaves a small race if releasing the
shadow slot before setting TP_STATUS_USER. The below reproducer showed
that this race is not academic. If releasing the slot after tp_status,
the race is more subtle. See the first link for details.

* add a new tp_status TP_KERNEL_OWNED to avoid the transactional store
of two fields. But, legacy applications may interpret all non-zero
tp_status as owned by the user. As libpcap does. So this is possible
only opt-in by newer processes. It can be added as an optional mode.

* embed the struct at the tail of pg_vec to avoid extra allocation.
The implementation proved no less complex than a separate field.

The additional locking cost on release adds contention, no different
than scaling on multicore or multiqueue h/w. In practice, below
reproducer nor small packet tcpdump showed a noticeable change in
perf report in cycles spent in spinlock. Where contention is
problematic, packet sockets support mitigation through PACKET_FANOUT.
And we can consider adding opt-in state TP_KERNEL_OWNED.

Easy to reproduce by running multiple netperf or similar TCP_STREAM
flows concurrently with `tcpdump -B 129 -n greater 60000`.

Based on an earlier patchset by Jon Rosen. See links below.

I believe this issue goes back to the introduction of tpacket_rcv,
which predates git history.

Link: https://www.mail-archive.com/netdev@vger.kernel.org/msg237222.html
Suggested-by: Jon Rosen <jrosen@cisco.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Jon Rosen <jrosen@cisco.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 21 +++++++++++++++++++++
 net/packet/internal.h  |  5 ++++-
 2 files changed, 25 insertions(+), 1 deletion(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 20edb7c25e22..1d63ab3a878a 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2172,6 +2172,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	struct timespec ts;
 	__u32 ts_status;
 	bool is_drop_n_account = false;
+	unsigned int slot_id = 0;
 	bool do_vnet = false;
 
 	/* struct tpacket{2,3}_hdr is aligned to a multiple of TPACKET_ALIGNMENT.
@@ -2274,6 +2275,13 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	if (!h.raw)
 		goto drop_n_account;
 
+	if (po->tp_version <= TPACKET_V2) {
+		slot_id = po->rx_ring.head;
+		if (test_bit(slot_id, po->rx_ring.rx_owner_map))
+			goto drop_n_account;
+		__set_bit(slot_id, po->rx_ring.rx_owner_map);
+	}
+
 	if (do_vnet &&
 	    virtio_net_hdr_from_skb(skb, h.raw + macoff -
 				    sizeof(struct virtio_net_hdr),
@@ -2379,7 +2387,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 #endif
 
 	if (po->tp_version <= TPACKET_V2) {
+		spin_lock(&sk->sk_receive_queue.lock);
 		__packet_set_status(po, h.raw, status);
+		__clear_bit(slot_id, po->rx_ring.rx_owner_map);
+		spin_unlock(&sk->sk_receive_queue.lock);
 		sk->sk_data_ready(sk);
 	} else {
 		prb_clear_blk_fill_status(&po->rx_ring);
@@ -4276,6 +4287,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 {
 	struct pgv *pg_vec = NULL;
 	struct packet_sock *po = pkt_sk(sk);
+	unsigned long *rx_owner_map = NULL;
 	int was_running, order = 0;
 	struct packet_ring_buffer *rb;
 	struct sk_buff_head *rb_queue;
@@ -4361,6 +4373,12 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 			}
 			break;
 		default:
+			if (!tx_ring) {
+				rx_owner_map = bitmap_alloc(req->tp_frame_nr,
+					GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO);
+				if (!rx_owner_map)
+					goto out_free_pg_vec;
+			}
 			break;
 		}
 	}
@@ -4390,6 +4408,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 		err = 0;
 		spin_lock_bh(&rb_queue->lock);
 		swap(rb->pg_vec, pg_vec);
+		if (po->tp_version <= TPACKET_V2)
+			swap(rb->rx_owner_map, rx_owner_map);
 		rb->frame_max = (req->tp_frame_nr - 1);
 		rb->head = 0;
 		rb->frame_size = req->tp_frame_size;
@@ -4421,6 +4441,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 	}
 
 out_free_pg_vec:
+	bitmap_free(rx_owner_map);
 	if (pg_vec)
 		free_pg_vec(pg_vec, order, req->tp_block_nr);
 out:
diff --git a/net/packet/internal.h b/net/packet/internal.h
index 82fb2b10f790..907f4cd2a718 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -70,7 +70,10 @@ struct packet_ring_buffer {
 
 	unsigned int __percpu	*pending_refcnt;
 
-	struct tpacket_kbdq_core	prb_bdqc;
+	union {
+		unsigned long			*rx_owner_map;
+		struct tpacket_kbdq_core	prb_bdqc;
+	};
 };
 
 extern struct mutex fanout_mutex;
-- 
2.20.1


From 98154b850acf63792622120668434dce7f54f922 Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Tue, 17 Mar 2020 20:04:54 +0200
Subject: [PATCH 17/47] net: phy: dp83867: w/a for fld detect threshold
 bootstrapping issue

[ Upstream commit 749f6f6843115b424680f1aada3c0dd613ad807c ]

When the DP83867 PHY is strapped to enable Fast Link Drop (FLD) feature
STRAP_STS2.STRAP_ FLD (reg 0x006F bit 10), the Energy Lost Threshold for
FLD Energy Lost Mode FLD_THR_CFG.ENERGY_LOST_FLD_THR (reg 0x002e bits 2:0)
will be defaulted to 0x2. This may cause the phy link to be unstable. The
new DP83867 DM recommends to always restore ENERGY_LOST_FLD_THR to 0x1.

Hence, restore default value of FLD_THR_CFG.ENERGY_LOST_FLD_THR to 0x1 when
FLD is enabled by bootstrapping as recommended by DM.

Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/dp83867.c | 21 ++++++++++++++++++++-
 1 file changed, 20 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c
index 52e80434e45e..31a559513362 100644
--- a/drivers/net/phy/dp83867.c
+++ b/drivers/net/phy/dp83867.c
@@ -25,7 +25,8 @@
 #define DP83867_CFG3		0x1e
 
 /* Extended Registers */
-#define DP83867_CFG4            0x0031
+#define DP83867_FLD_THR_CFG	0x002e
+#define DP83867_CFG4		0x0031
 #define DP83867_CFG4_SGMII_ANEG_MASK (BIT(5) | BIT(6))
 #define DP83867_CFG4_SGMII_ANEG_TIMER_11MS   (3 << 5)
 #define DP83867_CFG4_SGMII_ANEG_TIMER_800US  (2 << 5)
@@ -74,6 +75,7 @@
 #define DP83867_STRAP_STS2_CLK_SKEW_RX_MASK	GENMASK(2, 0)
 #define DP83867_STRAP_STS2_CLK_SKEW_RX_SHIFT	0
 #define DP83867_STRAP_STS2_CLK_SKEW_NONE	BIT(2)
+#define DP83867_STRAP_STS2_STRAP_FLD		BIT(10)
 
 /* PHY CTRL bits */
 #define DP83867_PHYCR_FIFO_DEPTH_SHIFT		14
@@ -103,6 +105,9 @@
 /* CFG4 bits */
 #define DP83867_CFG4_PORT_MIRROR_EN              BIT(0)
 
+/* FLD_THR_CFG */
+#define DP83867_FLD_THR_CFG_ENERGY_LOST_THR_MASK	0x7
+
 enum {
 	DP83867_PORT_MIRROING_KEEP,
 	DP83867_PORT_MIRROING_EN,
@@ -318,6 +323,20 @@ static int dp83867_config_init(struct phy_device *phydev)
 		phy_clear_bits_mmd(phydev, DP83867_DEVADDR, DP83867_CFG4,
 				   BIT(7));
 
+	bs = phy_read_mmd(phydev, DP83867_DEVADDR, DP83867_STRAP_STS2);
+	if (bs & DP83867_STRAP_STS2_STRAP_FLD) {
+		/* When using strap to enable FLD, the ENERGY_LOST_FLD_THR will
+		 * be set to 0x2. This may causes the PHY link to be unstable -
+		 * the default value 0x1 need to be restored.
+		 */
+		ret = phy_modify_mmd(phydev, DP83867_DEVADDR,
+				     DP83867_FLD_THR_CFG,
+				     DP83867_FLD_THR_CFG_ENERGY_LOST_THR_MASK,
+				     0x1);
+		if (ret)
+			return ret;
+	}
+
 	if (phy_interface_is_rgmii(phydev)) {
 		val = phy_read(phydev, MII_DP83867_PHYCTRL);
 		if (val < 0)
-- 
2.20.1


From 291a247666b26853333b8e749bdbd59d92bec378 Mon Sep 17 00:00:00 2001
From: Andre Przywara <andre.przywara@arm.com>
Date: Tue, 24 Mar 2020 16:10:10 +0000
Subject: [PATCH 18/47] net: phy: mdio-bcm-unimac: Fix clock handling

[ Upstream commit c312c7818b86b663d32ec5d4b512abf06b23899a ]

The DT binding for this PHY describes an *optional* clock property.
Due to a bug in the error handling logic, we are actually ignoring this
clock *all* of the time so far.

Fix this by using devm_clk_get_optional() to handle this clock properly.

Fixes: b78ac6ecd1b6b ("net: phy: mdio-bcm-unimac: Allow configuring MDIO clock divider")
Signed-off-by: Andre Przywara <andre.przywara@arm.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mdio-bcm-unimac.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/mdio-bcm-unimac.c b/drivers/net/phy/mdio-bcm-unimac.c
index 4a28fb29adaa..fbd36891ee64 100644
--- a/drivers/net/phy/mdio-bcm-unimac.c
+++ b/drivers/net/phy/mdio-bcm-unimac.c
@@ -242,11 +242,9 @@ static int unimac_mdio_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 
-	priv->clk = devm_clk_get(&pdev->dev, NULL);
-	if (PTR_ERR(priv->clk) == -EPROBE_DEFER)
+	priv->clk = devm_clk_get_optional(&pdev->dev, NULL);
+	if (IS_ERR(priv->clk))
 		return PTR_ERR(priv->clk);
-	else
-		priv->clk = NULL;
 
 	ret = clk_prepare_enable(priv->clk);
 	if (ret)
-- 
2.20.1


From 98e128fff4f43d59cdb4ab4dfca103edb513027f Mon Sep 17 00:00:00 2001
From: Rayagonda Kokatanur <rayagonda.kokatanur@broadcom.com>
Date: Tue, 17 Mar 2020 10:24:35 +0530
Subject: [PATCH 19/47] net: phy: mdio-mux-bcm-iproc: check
 clk_prepare_enable() return value

[ Upstream commit 872307abbd0d9afd72171929806c2fa33dc34179 ]

Check clk_prepare_enable() return value.

Fixes: 2c7230446bc9 ("net: phy: Add pm support to Broadcom iProc mdio mux driver")
Signed-off-by: Rayagonda Kokatanur <rayagonda.kokatanur@broadcom.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mdio-mux-bcm-iproc.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/mdio-mux-bcm-iproc.c b/drivers/net/phy/mdio-mux-bcm-iproc.c
index 88d409e48c1f..aad6809ebe39 100644
--- a/drivers/net/phy/mdio-mux-bcm-iproc.c
+++ b/drivers/net/phy/mdio-mux-bcm-iproc.c
@@ -288,8 +288,13 @@ static int mdio_mux_iproc_suspend(struct device *dev)
 static int mdio_mux_iproc_resume(struct device *dev)
 {
 	struct iproc_mdiomux_desc *md = dev_get_drvdata(dev);
+	int rc;
 
-	clk_prepare_enable(md->core_clk);
+	rc = clk_prepare_enable(md->core_clk);
+	if (rc) {
+		dev_err(md->dev, "failed to enable core clk\n");
+		return rc;
+	}
 	mdio_mux_iproc_config(md);
 
 	return 0;
-- 
2.20.1


From dff2608f69f12fdbefaa1439c1714baba731ad57 Mon Sep 17 00:00:00 2001
From: Pawel Dembicki <paweldembicki@gmail.com>
Date: Fri, 20 Mar 2020 21:46:14 +0100
Subject: [PATCH 20/47] net: qmi_wwan: add support for ASKEY WWHC050
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 12a5ba5a1994568d4ceaff9e78c6b0329d953386 ]

ASKEY WWHC050 is a mcie LTE modem.
The oem configuration states:

T:  Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#=  2 Spd=480  MxCh= 0
D:  Ver= 2.10 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1690 ProdID=7588 Rev=ff.ff
S:  Manufacturer=Android
S:  Product=Android
S:  SerialNumber=813f0eef6e6e
C:* #Ifs= 6 Cfg#= 1 Atr=80 MxPwr=500mA
I:* If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 1 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=(none)
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E:  Ad=84(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E:  Ad=86(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
E:  Ad=88(I) Atr=03(Int.) MxPS=   8 Ivl=32ms
E:  Ad=87(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 5 Alt= 0 #EPs= 2 Cls=08(stor.) Sub=06 Prot=50 Driver=(none)
E:  Ad=89(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=06(O) Atr=02(Bulk) MxPS= 512 Ivl=125us

Tested on openwrt distribution.

Signed-off-by: Cezary Jackiewicz <cezary@eko.one.pl>
Signed-off-by: Pawel Dembicki <paweldembicki@gmail.com>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 5754bb6ca0ee..6c738a271257 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1210,6 +1210,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1435, 0xd182, 5)},	/* Wistron NeWeb D18 */
 	{QMI_FIXED_INTF(0x1435, 0xd191, 4)},	/* Wistron NeWeb D19Q1 */
 	{QMI_QUIRK_SET_DTR(0x1508, 0x1001, 4)},	/* Fibocom NL668 series */
+	{QMI_FIXED_INTF(0x1690, 0x7588, 4)},    /* ASKEY WWHC050 */
 	{QMI_FIXED_INTF(0x16d8, 0x6003, 0)},	/* CMOTech 6003 */
 	{QMI_FIXED_INTF(0x16d8, 0x6007, 0)},	/* CMOTech CHE-628S */
 	{QMI_FIXED_INTF(0x16d8, 0x6008, 0)},	/* CMOTech CMU-301 */
-- 
2.20.1


From 56fbef57992e4ce1ec866cb1aa32c1631e0ccbb8 Mon Sep 17 00:00:00 2001
From: Paul Blakey <paulb@mellanox.com>
Date: Wed, 18 Mar 2020 12:50:33 +0200
Subject: [PATCH 21/47] net/sched: act_ct: Fix leak of ct zone template on
 replace

[ Upstream commit dd2af10402684cb5840a127caec9e7cdcff6d167 ]

Currently, on replace, the previous action instance params
is swapped with a newly allocated params. The old params is
only freed (via kfree_rcu), without releasing the allocated
ct zone template related to it.

Call tcf_ct_params_free (via call_rcu) for the old params,
so it will release it.

Fixes: b57dc7c13ea9 ("net/sched: Introduce action ct")
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ct.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index f3232a00970f..0586546c20d7 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -739,7 +739,7 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla,
 	if (goto_ch)
 		tcf_chain_put_by_act(goto_ch);
 	if (params)
-		kfree_rcu(params, rcu);
+		call_rcu(&params->rcu, tcf_ct_params_free);
 	if (res == ACT_P_CREATED)
 		tcf_idr_insert(tn, *a);
 
-- 
2.20.1


From 04091c19830ef53a2f5c5498ffbc9a85b6b3f5b5 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Fri, 13 Mar 2020 22:29:54 -0700
Subject: [PATCH 22/47] net_sched: cls_route: remove the right filter from
 hashtable

[ Upstream commit ef299cc3fa1a9e1288665a9fdc8bff55629fd359 ]

route4_change() allocates a new filter and copies values from
the old one. After the new filter is inserted into the hash
table, the old filter should be removed and freed, as the final
step of the update.

However, the current code mistakenly removes the new one. This
looks apparently wrong to me, and it causes double "free" and
use-after-free too, as reported by syzbot.

Reported-and-tested-by: syzbot+f9b32aaacd60305d9687@syzkaller.appspotmail.com
Reported-and-tested-by: syzbot+2f8c233f131943d6056d@syzkaller.appspotmail.com
Reported-and-tested-by: syzbot+9c2df9fd5e9445b74e01@syzkaller.appspotmail.com
Fixes: 1109c00547fc ("net: sched: RCU cls_route")
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Cc: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_route.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index 6f8786b06bde..5efa3e7ace15 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -534,8 +534,8 @@ static int route4_change(struct net *net, struct sk_buff *in_skb,
 			fp = &b->ht[h];
 			for (pfp = rtnl_dereference(*fp); pfp;
 			     fp = &pfp->next, pfp = rtnl_dereference(*fp)) {
-				if (pfp == f) {
-					*fp = f->next;
+				if (pfp == fold) {
+					rcu_assign_pointer(*fp, fold->next);
 					break;
 				}
 			}
-- 
2.20.1


From d6754bc691de6fe3cc1f07906a7e4b3f9fbe369b Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Wed, 11 Mar 2020 22:42:27 -0700
Subject: [PATCH 23/47] net_sched: hold rtnl lock in
 tcindex_partial_destroy_work()

[ Upstream commit b1be2e8cd290f620777bfdb8aa00890cd2fa02b5 ]

syzbot reported a use-after-free in tcindex_dump(). This is due to
the lack of RTNL in the deferred rcu work. We queue this work with
RTNL in tcindex_change(), later, tcindex_dump() is called:

        fh = tp->ops->get(tp, t->tcm_handle);
	...
        err = tp->ops->change(..., &fh, ...);
        tfilter_notify(..., fh, ...);

but there is nothing to serialize the pending
tcindex_partial_destroy_work() with tcindex_dump().

Fix this by simply holding RTNL in tcindex_partial_destroy_work(),
so that it won't be called until RTNL is released after
tc_new_tfilter() is completed.

Reported-and-tested-by: syzbot+653090db2562495901dc@syzkaller.appspotmail.com
Fixes: 3d210534cc93 ("net_sched: fix a race condition in tcindex_destroy()")
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_tcindex.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 09b7dc5fe7e0..f2cb24b6f0cf 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -261,8 +261,10 @@ static void tcindex_partial_destroy_work(struct work_struct *work)
 					      struct tcindex_data,
 					      rwork);
 
+	rtnl_lock();
 	kfree(p->perfect);
 	kfree(p);
+	rtnl_unlock();
 }
 
 static void tcindex_free_perfect_hash(struct tcindex_data *cp)
-- 
2.20.1


From 82aeae946fc1131976cbc1f335186168fe15cbf4 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Wed, 11 Mar 2020 22:42:28 -0700
Subject: [PATCH 24/47] net_sched: keep alloc_hash updated after hash
 allocation

[ Upstream commit 0d1c3530e1bd38382edef72591b78e877e0edcd3 ]

In commit 599be01ee567 ("net_sched: fix an OOB access in cls_tcindex")
I moved cp->hash calculation before the first
tcindex_alloc_perfect_hash(), but cp->alloc_hash is left untouched.
This difference could lead to another out of bound access.

cp->alloc_hash should always be the size allocated, we should
update it after this tcindex_alloc_perfect_hash().

Reported-and-tested-by: syzbot+dcc34d54d68ef7d2d53d@syzkaller.appspotmail.com
Reported-and-tested-by: syzbot+c72da7b9ed57cde6fca2@syzkaller.appspotmail.com
Fixes: 599be01ee567 ("net_sched: fix an OOB access in cls_tcindex")
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_tcindex.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index f2cb24b6f0cf..9904299424a1 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -359,6 +359,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 
 		if (tcindex_alloc_perfect_hash(net, cp) < 0)
 			goto errout;
+		cp->alloc_hash = cp->hash;
 		for (i = 0; i < min(cp->hash, p->hash); i++)
 			cp->perfect[i].res = p->perfect[i].res;
 		balloc = 1;
-- 
2.20.1


From 0358c5945d282179e4ef75d64962217908fe1c8b Mon Sep 17 00:00:00 2001
From: Emil Renner Berthing <kernel@esmil.dk>
Date: Sat, 21 Mar 2020 15:36:19 +0100
Subject: [PATCH 25/47] net: stmmac: dwmac-rk: fix error path in rk_gmac_probe

[ Upstream commit 9de9aa487daff7a5c73434c24269b44ed6a428e6 ]

Make sure we clean up devicetree related configuration
also when clock init fails.

Fixes: fecd4d7eef8b ("net: stmmac: dwmac-rk: Add integrated PHY support")
Signed-off-by: Emil Renner Berthing <kernel@esmil.dk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index e2e469c37a4d..9f9aaa47a8dc 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -1411,7 +1411,7 @@ static int rk_gmac_probe(struct platform_device *pdev)
 
 	ret = rk_gmac_clk_init(plat_dat);
 	if (ret)
-		return ret;
+		goto err_remove_config_dt;
 
 	ret = rk_gmac_powerup(plat_dat->bsp_priv);
 	if (ret)
-- 
2.20.1


From 871a0193a43f6b757e17a7ab38d3e31b2cd0996e Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Fri, 20 Mar 2020 16:21:17 +0300
Subject: [PATCH 26/47] NFC: fdp: Fix a signedness bug in fdp_nci_send_patch()

[ Upstream commit 0dcdf9f64028ec3b75db6b691560f8286f3898bf ]

The nci_conn_max_data_pkt_payload_size() function sometimes returns
-EPROTO so "max_size" needs to be signed for the error handling to
work.  We can make "payload_size" an int as well.

Fixes: a06347c04c13 ("NFC: Add Intel Fields Peak NFC solution driver")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/nfc/fdp/fdp.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/nfc/fdp/fdp.c b/drivers/nfc/fdp/fdp.c
index 0cc9ac856fe2..ed2123129e0e 100644
--- a/drivers/nfc/fdp/fdp.c
+++ b/drivers/nfc/fdp/fdp.c
@@ -184,7 +184,7 @@ static int fdp_nci_send_patch(struct nci_dev *ndev, u8 conn_id, u8 type)
 	const struct firmware *fw;
 	struct sk_buff *skb;
 	unsigned long len;
-	u8 max_size, payload_size;
+	int max_size, payload_size;
 	int rc = 0;
 
 	if ((type == NCI_PATCH_TYPE_OTP && !info->otp_patch) ||
@@ -207,8 +207,7 @@ static int fdp_nci_send_patch(struct nci_dev *ndev, u8 conn_id, u8 type)
 
 	while (len) {
 
-		payload_size = min_t(unsigned long, (unsigned long) max_size,
-				     len);
+		payload_size = min_t(unsigned long, max_size, len);
 
 		skb = nci_skb_alloc(ndev, (NCI_CTRL_HDR_SIZE + payload_size),
 				    GFP_KERNEL);
-- 
2.20.1


From 696aa6b461b4e11bfa9d62f410c364886bb62073 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Tue, 24 Mar 2020 20:58:29 +0100
Subject: [PATCH 27/47] r8169: re-enable MSI on RTL8168c

[ Upstream commit f13bc68131b0c0d67a77fb43444e109828a983bf ]

The original change fixed an issue on RTL8168b by mimicking the vendor
driver behavior to disable MSI on chip versions before RTL8168d.
This however now caused an issue on a system with RTL8168c, see [0].
Therefore leave MSI disabled on RTL8168b, but re-enable it on RTL8168c.

[0] https://bugzilla.redhat.com/show_bug.cgi?id=1792839

Fixes: 003bd5b4a7b4 ("r8169: don't use MSI before RTL8168d")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index a2cef6a004e7..238c5456bc09 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -6812,7 +6812,7 @@ static int rtl_alloc_irq(struct rtl8169_private *tp)
 		RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~MSIEnable);
 		rtl_lock_config_regs(tp);
 		/* fall through */
-	case RTL_GIGA_MAC_VER_07 ... RTL_GIGA_MAC_VER_24:
+	case RTL_GIGA_MAC_VER_07 ... RTL_GIGA_MAC_VER_17:
 		flags = PCI_IRQ_LEGACY;
 		break;
 	default:
-- 
2.20.1


From eacee49f48b10632cadc788dcdcd6c0af5ab50d5 Mon Sep 17 00:00:00 2001
From: Oliver Hartkopp <socketcan@hartkopp.net>
Date: Sat, 21 Mar 2020 14:08:29 +0100
Subject: [PATCH 28/47] slcan: not call free_netdev before rtnl_unlock in
 slcan_open

[ Upstream commit 2091a3d42b4f339eaeed11228e0cbe9d4f92f558 ]

As the description before netdev_run_todo, we cannot call free_netdev
before rtnl_unlock, fix it by reorder the code.

This patch is a 1:1 copy of upstream slip.c commit f596c87005f7
("slip: not call free_netdev before rtnl_unlock in slip_open").

Reported-by: yangerkun <yangerkun@huawei.com>
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/can/slcan.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c
index 2f5c287eac95..a3664281a33f 100644
--- a/drivers/net/can/slcan.c
+++ b/drivers/net/can/slcan.c
@@ -625,7 +625,10 @@ static int slcan_open(struct tty_struct *tty)
 	tty->disc_data = NULL;
 	clear_bit(SLF_INUSE, &sl->flags);
 	slc_free_netdev(sl->dev);
+	/* do not call free_netdev before rtnl_unlock */
+	rtnl_unlock();
 	free_netdev(sl->dev);
+	return err;
 
 err_exit:
 	rtnl_unlock();
-- 
2.20.1


From 82ac47253d29ca240796479d4176eeb791fb4901 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 20 Mar 2020 16:52:02 +0100
Subject: [PATCH 29/47] tcp: also NULL skb->dev when copy was needed

[ Upstream commit 07f8e4d0fddbf2f87e4cefb551278abc38db8cdd ]

In rare cases retransmit logic will make a full skb copy, which will not
trigger the zeroing added in recent change
b738a185beaa ("tcp: ensure skb->dev is NULL before leaving TCP stack").

Cc: Eric Dumazet <edumazet@google.com>
Fixes: 75c119afe14f ("tcp: implement rb-tree based retransmit queue")
Fixes: 28f8bfd1ac94 ("netfilter: Support iif matches in POSTROUTING")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 660b24fe041e..196425f6d0ba 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2976,8 +2976,12 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 
 		tcp_skb_tsorted_save(skb) {
 			nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC);
-			err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
-				     -ENOBUFS;
+			if (nskb) {
+				nskb->dev = NULL;
+				err = tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC);
+			} else {
+				err = -ENOBUFS;
+			}
 		} tcp_skb_tsorted_restore(skb);
 
 		if (!err) {
-- 
2.20.1


From 94f77ffc36430607288ba759033375f8e623e4b7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 19 Mar 2020 12:49:55 -0700
Subject: [PATCH 30/47] tcp: ensure skb->dev is NULL before leaving TCP stack

[ Upstream commit b738a185beaab8728943acdb3e67371b8a88185e ]

skb->rbnode is sharing three skb fields : next, prev, dev

When a packet is sent, TCP keeps the original skb (master)
in a rtx queue, which was converted to rbtree a while back.

__tcp_transmit_skb() is responsible to clone the master skb,
and add the TCP header to the clone before sending it
to network layer.

skb_clone() already clears skb->next and skb->prev, but copies
the master oskb->dev into the clone.

We need to clear skb->dev, otherwise lower layers could interpret
the value as a pointer to a netdev.

This old bug surfaced recently when commit 28f8bfd1ac94
("netfilter: Support iif matches in POSTROUTING") was merged.

Before this netfilter commit, skb->dev value was ignored and
changed before reaching dev_queue_xmit()

Fixes: 75c119afe14f ("tcp: implement rb-tree based retransmit queue")
Fixes: 28f8bfd1ac94 ("netfilter: Support iif matches in POSTROUTING")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Martin Zaharinov <micron10@gmail.com>
Cc: Florian Westphal <fw@strlen.de>
Cc: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 196425f6d0ba..c8d03c1b4c6b 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1048,6 +1048,10 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 
 		if (unlikely(!skb))
 			return -ENOBUFS;
+		/* retransmit skbs might have a non zero value in skb->dev
+		 * because skb->dev is aliased with skb->rbnode.rb_left
+		 */
+		skb->dev = NULL;
 	}
 
 	inet = inet_sk(sk);
-- 
2.20.1


From b0375305e83196957f29b6417ddfc53cd4738bca Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 18 Mar 2020 19:21:02 -0700
Subject: [PATCH 31/47] tcp: repair: fix TCP_QUEUE_SEQ implementation

[ Upstream commit 6cd6cbf593bfa3ae6fc3ed34ac21da4d35045425 ]

When application uses TCP_QUEUE_SEQ socket option to
change tp->rcv_next, we must also update tp->copied_seq.

Otherwise, stuff relying on tcp_inq() being precise can
eventually be confused.

For example, tcp_zerocopy_receive() might crash because
it does not expect tcp_recv_skb() to return NULL.

We could add tests in various places to fix the issue,
or simply make sure tcp_inq() wont return a random value,
and leave fast path as it is.

Note that this fixes ioctl(fd, SIOCINQ, &val) at the same
time.

Fixes: ee9952831cfd ("tcp: Initial repair mode")
Fixes: 05255b823a61 ("tcp: add TCP_ZEROCOPY_RECEIVE support for zerocopy receive")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index deb466fc3d1f..e378ff17f8c6 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2943,8 +2943,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 			err = -EPERM;
 		else if (tp->repair_queue == TCP_SEND_QUEUE)
 			WRITE_ONCE(tp->write_seq, val);
-		else if (tp->repair_queue == TCP_RECV_QUEUE)
+		else if (tp->repair_queue == TCP_RECV_QUEUE) {
 			WRITE_ONCE(tp->rcv_nxt, val);
+			WRITE_ONCE(tp->copied_seq, val);
+		}
 		else
 			err = -EINVAL;
 		break;
-- 
2.20.1


From b58de0b5771d5906d81953c731bcfd5c69f6451d Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Wed, 18 Mar 2020 13:28:09 +0000
Subject: [PATCH 32/47] vxlan: check return value of gro_cells_init()

[ Upstream commit 384d91c267e621e0926062cfb3f20cb72dc16928 ]

gro_cells_init() returns error if memory allocation is failed.
But the vxlan module doesn't check the return value of gro_cells_init().

Fixes: 58ce31cca1ff ("vxlan: GRO support at tunnel layer")`
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 283dfeb406ad..93690f77ec9c 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2779,10 +2779,19 @@ static void vxlan_vs_add_dev(struct vxlan_sock *vs, struct vxlan_dev *vxlan,
 /* Setup stats when device is created */
 static int vxlan_init(struct net_device *dev)
 {
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	int err;
+
 	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
 	if (!dev->tstats)
 		return -ENOMEM;
 
+	err = gro_cells_init(&vxlan->gro_cells, dev);
+	if (err) {
+		free_percpu(dev->tstats);
+		return err;
+	}
+
 	return 0;
 }
 
@@ -3043,8 +3052,6 @@ static void vxlan_setup(struct net_device *dev)
 
 	vxlan->dev = dev;
 
-	gro_cells_init(&vxlan->gro_cells, dev);
-
 	for (h = 0; h < FDB_HASH_SIZE; ++h) {
 		spin_lock_init(&vxlan->hash_lock[h]);
 		INIT_HLIST_HEAD(&vxlan->fdb_head[h]);
-- 
2.20.1


From defd2727ccbfd99361298a3f4ebce50a46b10f42 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 22 Mar 2020 16:40:01 -0400
Subject: [PATCH 33/47] bnxt_en: Fix Priority Bytes and Packets counters in
 ethtool -S.

[ Upstream commit a24ec3220f369aa0b94c863b6b310685a727151c ]

There is an indexing bug in determining these ethtool priority
counters.  Instead of using the queue ID to index, we need to
normalize by modulo 10 to get the index.  This index is then used
to obtain the proper CoS queue counter.  Rename bp->pri2cos to
bp->pri2cos_idx to make this more clear.

Fixes: e37fed790335 ("bnxt_en: Add ethtool -S priority counters.")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c         | 10 +++++++++-
 drivers/net/ethernet/broadcom/bnxt/bnxt.h         |  2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c |  8 ++++----
 3 files changed, 14 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 57c88e157f86..1e78ea0df26b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -7387,14 +7387,22 @@ static int bnxt_hwrm_port_qstats_ext(struct bnxt *bp)
 		pri2cos = &resp2->pri0_cos_queue_id;
 		for (i = 0; i < 8; i++) {
 			u8 queue_id = pri2cos[i];
+			u8 queue_idx;
 
+			/* Per port queue IDs start from 0, 10, 20, etc */
+			queue_idx = queue_id % 10;
+			if (queue_idx > BNXT_MAX_QUEUE) {
+				bp->pri2cos_valid = false;
+				goto qstats_done;
+			}
 			for (j = 0; j < bp->max_q; j++) {
 				if (bp->q_ids[j] == queue_id)
-					bp->pri2cos[i] = j;
+					bp->pri2cos_idx[i] = queue_idx;
 			}
 		}
 		bp->pri2cos_valid = 1;
 	}
+qstats_done:
 	mutex_unlock(&bp->hwrm_cmd_lock);
 	return rc;
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 2e6ad53fdc75..cda7ba31095a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1688,7 +1688,7 @@ struct bnxt {
 	u16			fw_rx_stats_ext_size;
 	u16			fw_tx_stats_ext_size;
 	u16			hw_ring_stats_size;
-	u8			pri2cos[8];
+	u8			pri2cos_idx[8];
 	u8			pri2cos_valid;
 
 	u16			hwrm_max_req_len;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index cfa647d5b44d..fb1ab58da9fa 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -589,25 +589,25 @@ static void bnxt_get_ethtool_stats(struct net_device *dev,
 		if (bp->pri2cos_valid) {
 			for (i = 0; i < 8; i++, j++) {
 				long n = bnxt_rx_bytes_pri_arr[i].base_off +
-					 bp->pri2cos[i];
+					 bp->pri2cos_idx[i];
 
 				buf[j] = le64_to_cpu(*(rx_port_stats_ext + n));
 			}
 			for (i = 0; i < 8; i++, j++) {
 				long n = bnxt_rx_pkts_pri_arr[i].base_off +
-					 bp->pri2cos[i];
+					 bp->pri2cos_idx[i];
 
 				buf[j] = le64_to_cpu(*(rx_port_stats_ext + n));
 			}
 			for (i = 0; i < 8; i++, j++) {
 				long n = bnxt_tx_bytes_pri_arr[i].base_off +
-					 bp->pri2cos[i];
+					 bp->pri2cos_idx[i];
 
 				buf[j] = le64_to_cpu(*(tx_port_stats_ext + n));
 			}
 			for (i = 0; i < 8; i++, j++) {
 				long n = bnxt_tx_pkts_pri_arr[i].base_off +
-					 bp->pri2cos[i];
+					 bp->pri2cos_idx[i];
 
 				buf[j] = le64_to_cpu(*(tx_port_stats_ext + n));
 			}
-- 
2.20.1


From 9a268eb1d35a1cdaf8e4256c7ef69d4e9a172de3 Mon Sep 17 00:00:00 2001
From: Edwin Peer <edwin.peer@broadcom.com>
Date: Sun, 22 Mar 2020 16:40:02 -0400
Subject: [PATCH 34/47] bnxt_en: fix memory leaks in bnxt_dcbnl_ieee_getets()

[ Upstream commit 62d4073e86e62e316bea2c53e77db10418fd5dd7 ]

The allocated ieee_ets structure goes out of scope without being freed,
leaking memory. Appropriate result codes should be returned so that
callers do not rely on invalid data passed by reference.

Also cache the ETS config retrieved from the device so that it doesn't
need to be freed. The balance of the code was clearly written with the
intent of having the results of querying the hardware cached in the
device structure. The commensurate store was evidently missed though.

Fixes: 7df4ae9fe855 ("bnxt_en: Implement DCBNL to support host-based DCBX.")
Signed-off-by: Edwin Peer <edwin.peer@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
index fb6f30d0d1d0..b1511bcffb1b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
@@ -479,24 +479,26 @@ static int bnxt_dcbnl_ieee_getets(struct net_device *dev, struct ieee_ets *ets)
 {
 	struct bnxt *bp = netdev_priv(dev);
 	struct ieee_ets *my_ets = bp->ieee_ets;
+	int rc;
 
 	ets->ets_cap = bp->max_tc;
 
 	if (!my_ets) {
-		int rc;
-
 		if (bp->dcbx_cap & DCB_CAP_DCBX_HOST)
 			return 0;
 
 		my_ets = kzalloc(sizeof(*my_ets), GFP_KERNEL);
 		if (!my_ets)
-			return 0;
+			return -ENOMEM;
 		rc = bnxt_hwrm_queue_cos2bw_qcfg(bp, my_ets);
 		if (rc)
-			return 0;
+			goto error;
 		rc = bnxt_hwrm_queue_pri2cos_qcfg(bp, my_ets);
 		if (rc)
-			return 0;
+			goto error;
+
+		/* cache result */
+		bp->ieee_ets = my_ets;
 	}
 
 	ets->cbs = my_ets->cbs;
@@ -505,6 +507,9 @@ static int bnxt_dcbnl_ieee_getets(struct net_device *dev, struct ieee_ets *ets)
 	memcpy(ets->tc_tsa, my_ets->tc_tsa, sizeof(ets->tc_tsa));
 	memcpy(ets->prio_tc, my_ets->prio_tc, sizeof(ets->prio_tc));
 	return 0;
+error:
+	kfree(my_ets);
+	return rc;
 }
 
 static int bnxt_dcbnl_ieee_setets(struct net_device *dev, struct ieee_ets *ets)
-- 
2.20.1


From 8a3dd59af221369d8883f7de3d6e44a90386ce88 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 22 Mar 2020 16:40:03 -0400
Subject: [PATCH 35/47] bnxt_en: Return error if bnxt_alloc_ctx_mem() fails.

[ Upstream commit 0b5b561cea32d5bb1e0a82d65b755a3cb5212141 ]

The current code ignores the return value from
bnxt_hwrm_func_backing_store_cfg(), causing the driver to proceed in
the init path even when this vital firmware call has failed.  Fix it
by propagating the error code to the caller.

Fixes: 1b9394e5a2ad ("bnxt_en: Configure context memory on new devices.")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 1e78ea0df26b..ff6694ca0d3f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -6863,12 +6863,12 @@ static int bnxt_alloc_ctx_mem(struct bnxt *bp)
 	}
 	ena |= FUNC_BACKING_STORE_CFG_REQ_DFLT_ENABLES;
 	rc = bnxt_hwrm_func_backing_store_cfg(bp, ena);
-	if (rc)
+	if (rc) {
 		netdev_err(bp->dev, "Failed configuring context mem, rc = %d.\n",
 			   rc);
-	else
-		ctx->flags |= BNXT_CTX_FLAG_INITED;
-
+		return rc;
+	}
+	ctx->flags |= BNXT_CTX_FLAG_INITED;
 	return 0;
 }
 
-- 
2.20.1


From fb0ced5d9e4d425378a14af54b7a9f19e9caa81b Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 22 Mar 2020 16:40:04 -0400
Subject: [PATCH 36/47] bnxt_en: Free context memory after disabling PCI in
 probe error path.

[ Upstream commit 62bfb932a51f6d08eb409248e69f8d6428c2cabd ]

Other shutdown code paths will always disable PCI first to shutdown DMA
before freeing context memory.  Do the same sequence in the error path
of probe to be safe and consistent.

Fixes: c20dc142dd7b ("bnxt_en: Disable bus master during PCI shutdown and driver unload.")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index ff6694ca0d3f..ae5416e84b88 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -11895,12 +11895,12 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 init_err_pci_clean:
 	bnxt_free_hwrm_short_cmd_req(bp);
 	bnxt_free_hwrm_resources(bp);
-	bnxt_free_ctx_mem(bp);
-	kfree(bp->ctx);
-	bp->ctx = NULL;
 	kfree(bp->fw_health);
 	bp->fw_health = NULL;
 	bnxt_cleanup_pci(bp);
+	bnxt_free_ctx_mem(bp);
+	kfree(bp->ctx);
+	bp->ctx = NULL;
 
 init_err_free:
 	free_netdev(dev);
-- 
2.20.1


From f5891ff49dbdac1ca08b61e60847bf80cda14dce Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Sun, 22 Mar 2020 16:40:05 -0400
Subject: [PATCH 37/47] bnxt_en: Reset rings if ring reservation fails during
 open()

[ Upstream commit 5d765a5e4bd7c368e564e11402bba74cf7f03ac1 ]

If ring counts are not reset when ring reservation fails,
bnxt_init_dflt_ring_mode() will not be called again to reinitialise
IRQs when open() is called and results in system crash as napi will
also be not initialised. This patch fixes it by resetting the ring
counts.

Fixes: 47558acd56a7 ("bnxt_en: Reserve rings at driver open if none was reserved at probe time.")
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index ae5416e84b88..6862594b49ab 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -11603,6 +11603,10 @@ static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh)
 		bp->rx_nr_rings++;
 		bp->cp_nr_rings++;
 	}
+	if (rc) {
+		bp->tx_nr_rings = 0;
+		bp->rx_nr_rings = 0;
+	}
 	return rc;
 }
 
-- 
2.20.1


From d813c0ba2e1b66a833069ca2a4a9367bf3c49ad0 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Fri, 13 Mar 2020 13:39:36 +0200
Subject: [PATCH 38/47] net: ip_gre: Separate ERSPAN newlink / changelink
 callbacks

[ Upstream commit e1f8f78ffe9854308b9e12a73ebe4e909074fc33 ]

ERSPAN shares most of the code path with GRE and gretap code. While that
helps keep the code compact, it is also error prone. Currently a broken
userspace can turn a gretap tunnel into a de facto ERSPAN one by passing
IFLA_GRE_ERSPAN_VER. There has been a similar issue in ip6gretap in the
past.

To prevent these problems in future, split the newlink and changelink code
paths. Split the ERSPAN code out of ipgre_netlink_parms() into a new
function erspan_netlink_parms(). Extract a piece of common logic from
ipgre_newlink() and ipgre_changelink() into ipgre_newlink_encap_setup().
Add erspan_newlink() and erspan_changelink().

Fixes: 84e54fe0a5ea ("gre: introduce native tunnel support for ERSPAN")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_gre.c | 103 ++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 85 insertions(+), 18 deletions(-)

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 10636fb6093e..765d3e75be1b 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1149,6 +1149,22 @@ static int ipgre_netlink_parms(struct net_device *dev,
 	if (data[IFLA_GRE_FWMARK])
 		*fwmark = nla_get_u32(data[IFLA_GRE_FWMARK]);
 
+	return 0;
+}
+
+static int erspan_netlink_parms(struct net_device *dev,
+				struct nlattr *data[],
+				struct nlattr *tb[],
+				struct ip_tunnel_parm *parms,
+				__u32 *fwmark)
+{
+	struct ip_tunnel *t = netdev_priv(dev);
+	int err;
+
+	err = ipgre_netlink_parms(dev, data, tb, parms, fwmark);
+	if (err)
+		return err;
+
 	if (data[IFLA_GRE_ERSPAN_VER]) {
 		t->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]);
 
@@ -1272,45 +1288,70 @@ static void ipgre_tap_setup(struct net_device *dev)
 	ip_tunnel_setup(dev, gre_tap_net_id);
 }
 
-static int ipgre_newlink(struct net *src_net, struct net_device *dev,
-			 struct nlattr *tb[], struct nlattr *data[],
-			 struct netlink_ext_ack *extack)
+static int
+ipgre_newlink_encap_setup(struct net_device *dev, struct nlattr *data[])
 {
-	struct ip_tunnel_parm p;
 	struct ip_tunnel_encap ipencap;
-	__u32 fwmark = 0;
-	int err;
 
 	if (ipgre_netlink_encap_parms(data, &ipencap)) {
 		struct ip_tunnel *t = netdev_priv(dev);
-		err = ip_tunnel_encap_setup(t, &ipencap);
+		int err = ip_tunnel_encap_setup(t, &ipencap);
 
 		if (err < 0)
 			return err;
 	}
 
+	return 0;
+}
+
+static int ipgre_newlink(struct net *src_net, struct net_device *dev,
+			 struct nlattr *tb[], struct nlattr *data[],
+			 struct netlink_ext_ack *extack)
+{
+	struct ip_tunnel_parm p;
+	__u32 fwmark = 0;
+	int err;
+
+	err = ipgre_newlink_encap_setup(dev, data);
+	if (err)
+		return err;
+
 	err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark);
 	if (err < 0)
 		return err;
 	return ip_tunnel_newlink(dev, tb, &p, fwmark);
 }
 
+static int erspan_newlink(struct net *src_net, struct net_device *dev,
+			  struct nlattr *tb[], struct nlattr *data[],
+			  struct netlink_ext_ack *extack)
+{
+	struct ip_tunnel_parm p;
+	__u32 fwmark = 0;
+	int err;
+
+	err = ipgre_newlink_encap_setup(dev, data);
+	if (err)
+		return err;
+
+	err = erspan_netlink_parms(dev, data, tb, &p, &fwmark);
+	if (err)
+		return err;
+	return ip_tunnel_newlink(dev, tb, &p, fwmark);
+}
+
 static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[],
 			    struct nlattr *data[],
 			    struct netlink_ext_ack *extack)
 {
 	struct ip_tunnel *t = netdev_priv(dev);
-	struct ip_tunnel_encap ipencap;
 	__u32 fwmark = t->fwmark;
 	struct ip_tunnel_parm p;
 	int err;
 
-	if (ipgre_netlink_encap_parms(data, &ipencap)) {
-		err = ip_tunnel_encap_setup(t, &ipencap);
-
-		if (err < 0)
-			return err;
-	}
+	err = ipgre_newlink_encap_setup(dev, data);
+	if (err)
+		return err;
 
 	err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark);
 	if (err < 0)
@@ -1323,8 +1364,34 @@ static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[],
 	t->parms.i_flags = p.i_flags;
 	t->parms.o_flags = p.o_flags;
 
-	if (strcmp(dev->rtnl_link_ops->kind, "erspan"))
-		ipgre_link_update(dev, !tb[IFLA_MTU]);
+	ipgre_link_update(dev, !tb[IFLA_MTU]);
+
+	return 0;
+}
+
+static int erspan_changelink(struct net_device *dev, struct nlattr *tb[],
+			     struct nlattr *data[],
+			     struct netlink_ext_ack *extack)
+{
+	struct ip_tunnel *t = netdev_priv(dev);
+	__u32 fwmark = t->fwmark;
+	struct ip_tunnel_parm p;
+	int err;
+
+	err = ipgre_newlink_encap_setup(dev, data);
+	if (err)
+		return err;
+
+	err = erspan_netlink_parms(dev, data, tb, &p, &fwmark);
+	if (err < 0)
+		return err;
+
+	err = ip_tunnel_changelink(dev, tb, &p, fwmark);
+	if (err < 0)
+		return err;
+
+	t->parms.i_flags = p.i_flags;
+	t->parms.o_flags = p.o_flags;
 
 	return 0;
 }
@@ -1515,8 +1582,8 @@ static struct rtnl_link_ops erspan_link_ops __read_mostly = {
 	.priv_size	= sizeof(struct ip_tunnel),
 	.setup		= erspan_setup,
 	.validate	= erspan_validate,
-	.newlink	= ipgre_newlink,
-	.changelink	= ipgre_changelink,
+	.newlink	= erspan_newlink,
+	.changelink	= erspan_changelink,
 	.dellink	= ip_tunnel_dellink,
 	.get_size	= ipgre_get_size,
 	.fill_info	= ipgre_fill_info,
-- 
2.20.1


From bc526dabe9483034b198ae54e411c32c5629fae2 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 16 Mar 2020 19:53:00 +0200
Subject: [PATCH 39/47] net: ip_gre: Accept IFLA_INFO_DATA-less configuration

[ Upstream commit 32ca98feab8c9076c89c0697c5a85e46fece809d ]

The fix referenced below causes a crash when an ERSPAN tunnel is created
without passing IFLA_INFO_DATA. Fix by validating passed-in data in the
same way as ipgre does.

Fixes: e1f8f78ffe98 ("net: ip_gre: Separate ERSPAN newlink / changelink callbacks")
Reported-by: syzbot+1b4ebf4dae4e510dd219@syzkaller.appspotmail.com
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_gre.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 765d3e75be1b..85ba1453ba5c 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1164,6 +1164,8 @@ static int erspan_netlink_parms(struct net_device *dev,
 	err = ipgre_netlink_parms(dev, data, tb, parms, fwmark);
 	if (err)
 		return err;
+	if (!data)
+		return 0;
 
 	if (data[IFLA_GRE_ERSPAN_VER]) {
 		t->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]);
-- 
2.20.1


From 5894ccd274944f90154ac0a60d77cd9ffff43f94 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Fri, 13 Mar 2020 06:50:14 +0000
Subject: [PATCH 40/47] hsr: use rcu_read_lock() in
 hsr_get_node_{list/status}()

[ Upstream commit 173756b86803655d70af7732079b3aa935e6ab68 ]

hsr_get_node_{list/status}() are not under rtnl_lock() because
they are callback functions of generic netlink.
But they use __dev_get_by_index() without rtnl_lock().
So, it would use unsafe data.
In order to fix it, rcu_read_lock() and dev_get_by_index_rcu()
are used instead of __dev_get_by_index().

Fixes: f421436a591d ("net/hsr: Add support for the High-availability Seamless Redundancy protocol (HSRv0)")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/hsr/hsr_framereg.c |  9 ++-------
 net/hsr/hsr_netlink.c  | 39 +++++++++++++++++++++------------------
 2 files changed, 23 insertions(+), 25 deletions(-)

diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c
index 27dc65d7de67..002f341f3564 100644
--- a/net/hsr/hsr_framereg.c
+++ b/net/hsr/hsr_framereg.c
@@ -482,12 +482,9 @@ int hsr_get_node_data(struct hsr_priv *hsr,
 	struct hsr_port *port;
 	unsigned long tdiff;
 
-	rcu_read_lock();
 	node = find_node_by_addr_A(&hsr->node_db, addr);
-	if (!node) {
-		rcu_read_unlock();
-		return -ENOENT;	/* No such entry */
-	}
+	if (!node)
+		return -ENOENT;
 
 	ether_addr_copy(addr_b, node->macaddress_B);
 
@@ -522,7 +519,5 @@ int hsr_get_node_data(struct hsr_priv *hsr,
 		*addr_b_ifindex = -1;
 	}
 
-	rcu_read_unlock();
-
 	return 0;
 }
diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c
index 8dc0547f01d0..d6760df2ad1f 100644
--- a/net/hsr/hsr_netlink.c
+++ b/net/hsr/hsr_netlink.c
@@ -251,15 +251,16 @@ static int hsr_get_node_status(struct sk_buff *skb_in, struct genl_info *info)
 	if (!na)
 		goto invalid;
 
-	hsr_dev = __dev_get_by_index(genl_info_net(info),
-				     nla_get_u32(info->attrs[HSR_A_IFINDEX]));
+	rcu_read_lock();
+	hsr_dev = dev_get_by_index_rcu(genl_info_net(info),
+				       nla_get_u32(info->attrs[HSR_A_IFINDEX]));
 	if (!hsr_dev)
-		goto invalid;
+		goto rcu_unlock;
 	if (!is_hsr_master(hsr_dev))
-		goto invalid;
+		goto rcu_unlock;
 
 	/* Send reply */
-	skb_out = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	skb_out = genlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC);
 	if (!skb_out) {
 		res = -ENOMEM;
 		goto fail;
@@ -313,12 +314,10 @@ static int hsr_get_node_status(struct sk_buff *skb_in, struct genl_info *info)
 	res = nla_put_u16(skb_out, HSR_A_IF1_SEQ, hsr_node_if1_seq);
 	if (res < 0)
 		goto nla_put_failure;
-	rcu_read_lock();
 	port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_A);
 	if (port)
 		res = nla_put_u32(skb_out, HSR_A_IF1_IFINDEX,
 				  port->dev->ifindex);
-	rcu_read_unlock();
 	if (res < 0)
 		goto nla_put_failure;
 
@@ -328,20 +327,22 @@ static int hsr_get_node_status(struct sk_buff *skb_in, struct genl_info *info)
 	res = nla_put_u16(skb_out, HSR_A_IF2_SEQ, hsr_node_if2_seq);
 	if (res < 0)
 		goto nla_put_failure;
-	rcu_read_lock();
 	port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B);
 	if (port)
 		res = nla_put_u32(skb_out, HSR_A_IF2_IFINDEX,
 				  port->dev->ifindex);
-	rcu_read_unlock();
 	if (res < 0)
 		goto nla_put_failure;
 
+	rcu_read_unlock();
+
 	genlmsg_end(skb_out, msg_head);
 	genlmsg_unicast(genl_info_net(info), skb_out, info->snd_portid);
 
 	return 0;
 
+rcu_unlock:
+	rcu_read_unlock();
 invalid:
 	netlink_ack(skb_in, nlmsg_hdr(skb_in), -EINVAL, NULL);
 	return 0;
@@ -351,6 +352,7 @@ static int hsr_get_node_status(struct sk_buff *skb_in, struct genl_info *info)
 	/* Fall through */
 
 fail:
+	rcu_read_unlock();
 	return res;
 }
 
@@ -377,15 +379,16 @@ static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info)
 	if (!na)
 		goto invalid;
 
-	hsr_dev = __dev_get_by_index(genl_info_net(info),
-				     nla_get_u32(info->attrs[HSR_A_IFINDEX]));
+	rcu_read_lock();
+	hsr_dev = dev_get_by_index_rcu(genl_info_net(info),
+				       nla_get_u32(info->attrs[HSR_A_IFINDEX]));
 	if (!hsr_dev)
-		goto invalid;
+		goto rcu_unlock;
 	if (!is_hsr_master(hsr_dev))
-		goto invalid;
+		goto rcu_unlock;
 
 	/* Send reply */
-	skb_out = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	skb_out = genlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC);
 	if (!skb_out) {
 		res = -ENOMEM;
 		goto fail;
@@ -405,14 +408,11 @@ static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info)
 
 	hsr = netdev_priv(hsr_dev);
 
-	rcu_read_lock();
 	pos = hsr_get_next_node(hsr, NULL, addr);
 	while (pos) {
 		res = nla_put(skb_out, HSR_A_NODE_ADDR, ETH_ALEN, addr);
-		if (res < 0) {
-			rcu_read_unlock();
+		if (res < 0)
 			goto nla_put_failure;
-		}
 		pos = hsr_get_next_node(hsr, pos, addr);
 	}
 	rcu_read_unlock();
@@ -422,6 +422,8 @@ static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info)
 
 	return 0;
 
+rcu_unlock:
+	rcu_read_unlock();
 invalid:
 	netlink_ack(skb_in, nlmsg_hdr(skb_in), -EINVAL, NULL);
 	return 0;
@@ -431,6 +433,7 @@ static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info)
 	/* Fall through */
 
 fail:
+	rcu_read_unlock();
 	return res;
 }
 
-- 
2.20.1


From a0c66bcfa1ea069d8528e065778f5e2779edeccd Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Fri, 13 Mar 2020 06:50:24 +0000
Subject: [PATCH 41/47] hsr: add restart routine into hsr_get_node_list()

[ Upstream commit ca19c70f5225771c05bcdcb832b4eb84d7271c5e ]

The hsr_get_node_list() is to send node addresses to the userspace.
If there are so many nodes, it could fail because of buffer size.
In order to avoid this failure, the restart routine is added.

Fixes: f421436a591d ("net/hsr: Add support for the High-availability Seamless Redundancy protocol (HSRv0)")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/hsr/hsr_netlink.c | 38 ++++++++++++++++++++++++--------------
 1 file changed, 24 insertions(+), 14 deletions(-)

diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c
index d6760df2ad1f..726bfe923999 100644
--- a/net/hsr/hsr_netlink.c
+++ b/net/hsr/hsr_netlink.c
@@ -360,16 +360,14 @@ static int hsr_get_node_status(struct sk_buff *skb_in, struct genl_info *info)
  */
 static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info)
 {
-	/* For receiving */
-	struct nlattr *na;
+	unsigned char addr[ETH_ALEN];
 	struct net_device *hsr_dev;
-
-	/* For sending */
 	struct sk_buff *skb_out;
-	void *msg_head;
 	struct hsr_priv *hsr;
-	void *pos;
-	unsigned char addr[ETH_ALEN];
+	bool restart = false;
+	struct nlattr *na;
+	void *pos = NULL;
+	void *msg_head;
 	int res;
 
 	if (!info)
@@ -387,8 +385,9 @@ static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info)
 	if (!is_hsr_master(hsr_dev))
 		goto rcu_unlock;
 
+restart:
 	/* Send reply */
-	skb_out = genlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC);
+	skb_out = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_ATOMIC);
 	if (!skb_out) {
 		res = -ENOMEM;
 		goto fail;
@@ -402,17 +401,28 @@ static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info)
 		goto nla_put_failure;
 	}
 
-	res = nla_put_u32(skb_out, HSR_A_IFINDEX, hsr_dev->ifindex);
-	if (res < 0)
-		goto nla_put_failure;
+	if (!restart) {
+		res = nla_put_u32(skb_out, HSR_A_IFINDEX, hsr_dev->ifindex);
+		if (res < 0)
+			goto nla_put_failure;
+	}
 
 	hsr = netdev_priv(hsr_dev);
 
-	pos = hsr_get_next_node(hsr, NULL, addr);
+	if (!pos)
+		pos = hsr_get_next_node(hsr, NULL, addr);
 	while (pos) {
 		res = nla_put(skb_out, HSR_A_NODE_ADDR, ETH_ALEN, addr);
-		if (res < 0)
+		if (res < 0) {
+			if (res == -EMSGSIZE) {
+				genlmsg_end(skb_out, msg_head);
+				genlmsg_unicast(genl_info_net(info), skb_out,
+						info->snd_portid);
+				restart = true;
+				goto restart;
+			}
 			goto nla_put_failure;
+		}
 		pos = hsr_get_next_node(hsr, pos, addr);
 	}
 	rcu_read_unlock();
@@ -429,7 +439,7 @@ static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info)
 	return 0;
 
 nla_put_failure:
-	kfree_skb(skb_out);
+	nlmsg_free(skb_out);
 	/* Fall through */
 
 fail:
-- 
2.20.1


From 3bb9a8669ff087fa85fc978877db7688295b0cce Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Fri, 13 Mar 2020 06:50:33 +0000
Subject: [PATCH 42/47] hsr: set .netnsok flag

[ Upstream commit 09e91dbea0aa32be02d8877bd50490813de56b9a ]

The hsr module has been supporting the list and status command.
(HSR_C_GET_NODE_LIST and HSR_C_GET_NODE_STATUS)
These commands send node information to the user-space via generic netlink.
But, in the non-init_net namespace, these commands are not allowed
because .netnsok flag is false.
So, there is no way to get node information in the non-init_net namespace.

Fixes: f421436a591d ("net/hsr: Add support for the High-availability Seamless Redundancy protocol (HSRv0)")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/hsr/hsr_netlink.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c
index 726bfe923999..fae21c863b1f 100644
--- a/net/hsr/hsr_netlink.c
+++ b/net/hsr/hsr_netlink.c
@@ -470,6 +470,7 @@ static struct genl_family hsr_genl_family __ro_after_init = {
 	.version = 1,
 	.maxattr = HSR_A_MAX,
 	.policy = hsr_genl_policy,
+	.netnsok = true,
 	.module = THIS_MODULE,
 	.ops = hsr_ops,
 	.n_ops = ARRAY_SIZE(hsr_ops),
-- 
2.20.1


From e2fb5edfb09586e54bdc9d6d68b89bbdbbc267b2 Mon Sep 17 00:00:00 2001
From: Hamdan Igbaria <hamdani@mellanox.com>
Date: Mon, 24 Feb 2020 14:41:29 +0200
Subject: [PATCH 43/47] net/mlx5: DR, Fix postsend actions write length

[ Upstream commit 692b0399a22530b2de8490bea75a7d20d59391d0 ]

Fix the send info write length to be (actions x action) size in bytes.

Fixes: 297cccebdc5a ("net/mlx5: DR, Expose an internal API to issue RDMA operations")
Signed-off-by: Hamdan Igbaria <hamdani@mellanox.com>
Reviewed-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c | 1 -
 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c   | 3 ++-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
index 004c56c2fc0c..b2dfa2b5366f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
@@ -930,7 +930,6 @@ static int dr_actions_l2_rewrite(struct mlx5dr_domain *dmn,
 
 	action->rewrite.data = (void *)ops;
 	action->rewrite.num_of_actions = i;
-	action->rewrite.chunk->byte_size = i * sizeof(*ops);
 
 	ret = mlx5dr_send_postsend_action(dmn, action);
 	if (ret) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
index c7f10d4f8f8d..095ec7b1399d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
@@ -558,7 +558,8 @@ int mlx5dr_send_postsend_action(struct mlx5dr_domain *dmn,
 	int ret;
 
 	send_info.write.addr = (uintptr_t)action->rewrite.data;
-	send_info.write.length = action->rewrite.chunk->byte_size;
+	send_info.write.length = action->rewrite.num_of_actions *
+				 DR_MODIFY_ACTION_SIZE;
 	send_info.write.lkey = 0;
 	send_info.remote_addr = action->rewrite.chunk->mr_addr;
 	send_info.rkey = action->rewrite.chunk->rkey;
-- 
2.20.1


From 22cc4ecf56fe788d553ba483826a33d089e0247f Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Mon, 9 Mar 2020 09:44:18 +0200
Subject: [PATCH 44/47] net/mlx5e: Enhance ICOSQ WQE info fields

[ Upstream commit 1de0306c3a05d305e45b1f1fabe2f4e94222eb6b ]

Add number of WQEBBs (WQE's Basic Block) to WQE info struct. Set the
number of WQEBBs on WQE post, and increment the consumer counter (cc)
on completion.

In case of error completions, the cc was mistakenly not incremented,
keeping a gap between cc and pc (producer counter). This failed the
recovery flow on the ICOSQ from a CQE error which timed-out waiting for
the cc and pc to meet.

Fixes: be5323c8379f ("net/mlx5e: Report and recover from CQE error on ICOSQ")
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      |  1 +
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c   | 11 +++++------
 drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c |  1 +
 3 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 9c8427698238..24e8dc9e6db5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -371,6 +371,7 @@ enum {
 
 struct mlx5e_sq_wqe_info {
 	u8  opcode;
+	u8 num_wqebbs;
 
 	/* Auxiliary data for different opcodes. */
 	union {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 82cffb3a9964..1d295a7afc8c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -477,6 +477,7 @@ static inline void mlx5e_fill_icosq_frag_edge(struct mlx5e_icosq *sq,
 	/* fill sq frag edge with nops to avoid wqe wrapping two pages */
 	for (; wi < edge_wi; wi++) {
 		wi->opcode = MLX5_OPCODE_NOP;
+		wi->num_wqebbs = 1;
 		mlx5e_post_nop(wq, sq->sqn, &sq->pc);
 	}
 }
@@ -525,6 +526,7 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 	umr_wqe->uctrl.xlt_offset = cpu_to_be16(xlt_offset);
 
 	sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_UMR;
+	sq->db.ico_wqe[pi].num_wqebbs = MLX5E_UMR_WQEBBS;
 	sq->db.ico_wqe[pi].umr.rq = rq;
 	sq->pc += MLX5E_UMR_WQEBBS;
 
@@ -628,17 +630,14 @@ void mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
 
 			ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc);
 			wi = &sq->db.ico_wqe[ci];
+			sqcc += wi->num_wqebbs;
 
-			if (likely(wi->opcode == MLX5_OPCODE_UMR)) {
-				sqcc += MLX5E_UMR_WQEBBS;
+			if (likely(wi->opcode == MLX5_OPCODE_UMR))
 				wi->umr.rq->mpwqe.umr_completed++;
-			} else if (likely(wi->opcode == MLX5_OPCODE_NOP)) {
-				sqcc++;
-			} else {
+			else if (unlikely(wi->opcode != MLX5_OPCODE_NOP))
 				netdev_WARN_ONCE(cq->channel->netdev,
 						 "Bad OPCODE in ICOSQ WQE info: 0x%x\n",
 						 wi->opcode);
-			}
 
 		} while (!last_wqe);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
index 257a7c9f7a14..800d34ed8a96 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
@@ -78,6 +78,7 @@ void mlx5e_trigger_irq(struct mlx5e_icosq *sq)
 	u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
 
 	sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_NOP;
+	sq->db.ico_wqe[pi].num_wqebbs = 1;
 	nopwqe = mlx5e_post_nop(wq, sq->sqn, &sq->pc);
 	mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &nopwqe->ctrl);
 }
-- 
2.20.1


From a1cff49963d4cbd8945779f9834f96d9c98d2066 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Thu, 12 Mar 2020 12:35:32 +0200
Subject: [PATCH 45/47] net/mlx5e: Fix missing reset of SW metadata in Striding
 RQ reset

[ Upstream commit 39369fd536d485a99a59d8e357c0d4d3ce19a3b8 ]

When resetting the RQ (moving RQ state from RST to RDY), the driver
resets the WQ's SW metadata.
In striding RQ mode, we maintain a field that reflects the actual
expected WQ head (including in progress WQEs posted to the ICOSQ).
It was mistakenly not reset together with the WQ. Fix this here.

Fixes: 8276ea1353a4 ("net/mlx5e: Report and recover from CQE with error on RQ")
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index a226277b0980..f07b1399744e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -181,10 +181,12 @@ mlx5e_tx_dma_unmap(struct device *pdev, struct mlx5e_sq_dma *dma)
 
 static inline void mlx5e_rqwq_reset(struct mlx5e_rq *rq)
 {
-	if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
+	if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
 		mlx5_wq_ll_reset(&rq->mpwqe.wq);
-	else
+		rq->mpwqe.actual_wq_head = 0;
+	} else {
 		mlx5_wq_cyc_reset(&rq->wqe.wq);
+	}
 }
 
 /* SW parser related functions */
-- 
2.20.1


From 7f3f8d1e5e084e7794e8605435aa6a426805b32f Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Mon, 16 Mar 2020 16:53:10 +0200
Subject: [PATCH 46/47] net/mlx5e: Fix ICOSQ recovery flow with Striding RQ

[ Upstream commit e239c6d686e1c37fb2ab143162dfb57471a8643f ]

In striding RQ mode, the buffers of an RX WQE are first
prepared and posted to the HW using a UMR WQEs via the ICOSQ.
We maintain the state of these in-progress WQEs in the RQ
SW struct.

In the flow of ICOSQ recovery, the corresponding RQ is not
in error state, hence:

- The buffers of the in-progress WQEs must be released
  and the RQ metadata should reflect it.
- Existing RX WQEs in the RQ should not be affected.

For this, wrap the dealloc of the in-progress WQEs in
a function, and use it in the ICOSQ recovery flow
instead of mlx5e_free_rx_descs().

Fixes: be5323c8379f ("net/mlx5e: Report and recover from CQE error on ICOSQ")
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h  |  1 +
 .../mellanox/mlx5/core/en/reporter_rx.c       |  2 +-
 .../net/ethernet/mellanox/mlx5/core/en_main.c | 31 ++++++++++++++-----
 3 files changed, 26 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 24e8dc9e6db5..55ceabf077b2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -1059,6 +1059,7 @@ int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state, int next_state);
 void mlx5e_activate_rq(struct mlx5e_rq *rq);
 void mlx5e_deactivate_rq(struct mlx5e_rq *rq);
 void mlx5e_free_rx_descs(struct mlx5e_rq *rq);
+void mlx5e_free_rx_in_progress_descs(struct mlx5e_rq *rq);
 void mlx5e_activate_icosq(struct mlx5e_icosq *icosq);
 void mlx5e_deactivate_icosq(struct mlx5e_icosq *icosq);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
index b860569d4247..9fa4b98001d5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
@@ -90,7 +90,7 @@ static int mlx5e_rx_reporter_err_icosq_cqe_recover(void *ctx)
 		goto out;
 
 	mlx5e_reset_icosq_cc_pc(icosq);
-	mlx5e_free_rx_descs(rq);
+	mlx5e_free_rx_in_progress_descs(rq);
 	clear_bit(MLX5E_SQ_STATE_RECOVERING, &icosq->state);
 	mlx5e_activate_icosq(icosq);
 	mlx5e_activate_rq(rq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index e5e91cbcbc31..ee7c753e9ea0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -824,6 +824,29 @@ int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time)
 	return -ETIMEDOUT;
 }
 
+void mlx5e_free_rx_in_progress_descs(struct mlx5e_rq *rq)
+{
+	struct mlx5_wq_ll *wq;
+	u16 head;
+	int i;
+
+	if (rq->wq_type != MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
+		return;
+
+	wq = &rq->mpwqe.wq;
+	head = wq->head;
+
+	/* Outstanding UMR WQEs (in progress) start at wq->head */
+	for (i = 0; i < rq->mpwqe.umr_in_progress; i++) {
+		rq->dealloc_wqe(rq, head);
+		head = mlx5_wq_ll_get_wqe_next_ix(wq, head);
+	}
+
+	rq->mpwqe.actual_wq_head = wq->head;
+	rq->mpwqe.umr_in_progress = 0;
+	rq->mpwqe.umr_completed = 0;
+}
+
 void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
 {
 	__be16 wqe_ix_be;
@@ -831,14 +854,8 @@ void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
 
 	if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
 		struct mlx5_wq_ll *wq = &rq->mpwqe.wq;
-		u16 head = wq->head;
-		int i;
 
-		/* Outstanding UMR WQEs (in progress) start at wq->head */
-		for (i = 0; i < rq->mpwqe.umr_in_progress; i++) {
-			rq->dealloc_wqe(rq, head);
-			head = mlx5_wq_ll_get_wqe_next_ix(wq, head);
-		}
+		mlx5e_free_rx_in_progress_descs(rq);
 
 		while (!mlx5_wq_ll_is_empty(wq)) {
 			struct mlx5e_rx_wqe_ll *wqe;
-- 
2.20.1


From 441f7d39b2c3e0e69eba75079b03fef408d6b792 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Thu, 19 Mar 2020 13:25:17 +0200
Subject: [PATCH 47/47] net/mlx5e: Do not recover from a non-fatal syndrome

[ Upstream commit 187a9830c921d92c4a9a8e2921ecc4b35a97532c ]

For non-fatal syndromes like LOCAL_LENGTH_ERR, recovery shouldn't be
triggered. In these scenarios, the RQ is not actually in ERR state.
This misleads the recovery flow which assumes that the RQ is really in
error state and no more completions arrive, causing crashes on bad page
state.

Fixes: 8276ea1353a4 ("net/mlx5e: Report and recover from CQE with error on RQ")
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/health.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
index d3693fa547ac..e54f70d9af22 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
@@ -10,8 +10,7 @@
 
 static inline bool cqe_syndrome_needs_recover(u8 syndrome)
 {
-	return syndrome == MLX5_CQE_SYNDROME_LOCAL_LENGTH_ERR ||
-	       syndrome == MLX5_CQE_SYNDROME_LOCAL_QP_OP_ERR ||
+	return syndrome == MLX5_CQE_SYNDROME_LOCAL_QP_OP_ERR ||
 	       syndrome == MLX5_CQE_SYNDROME_LOCAL_PROT_ERR ||
 	       syndrome == MLX5_CQE_SYNDROME_WR_FLUSH_ERR;
 }
-- 
2.20.1


[-- Attachment #3: net_55.mbox --]
[-- Type: Application/Octet-Stream, Size: 140349 bytes --]

From 02275b673c7c97e9bfe60903ae6bb76e19aee132 Mon Sep 17 00:00:00 2001
From: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Date: Thu, 19 Mar 2020 23:08:09 +0530
Subject: [PATCH 01/56] cxgb4: fix throughput drop during Tx backpressure

[ Upstream commit 7affd80802afb6ca92dba47d768632fbde365241 ]

commit 7c3bebc3d868 ("cxgb4: request the TX CIDX updates to status page")
reverted back to getting Tx CIDX updates via DMA, instead of interrupts,
introduced by commit d429005fdf2c ("cxgb4/cxgb4vf: Add support for SGE
doorbell queue timer")

However, it missed reverting back several code changes where Tx CIDX
updates are not explicitly requested during backpressure when using
interrupt mode. These missed changes cause slow recovery during
backpressure because the corresponding interrupt no longer comes and
hence results in Tx throughput drop.

So, revert back these missed code changes, as well, which will allow
explicitly requesting Tx CIDX updates when backpressure happens.
This enables the corresponding interrupt with Tx CIDX update message
to get generated and hence speed up recovery and restore back
throughput.

Fixes: 7c3bebc3d868 ("cxgb4: request the TX CIDX updates to status page")
Fixes: d429005fdf2c ("cxgb4/cxgb4vf: Add support for SGE doorbell queue timer")
Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/sge.c | 42 ++----------------------
 1 file changed, 2 insertions(+), 40 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index 97cda501e7e8..c816837fbd85 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -1486,16 +1486,7 @@ static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 		 * has opened up.
 		 */
 		eth_txq_stop(q);
-
-		/* If we're using the SGE Doorbell Queue Timer facility, we
-		 * don't need to ask the Firmware to send us Egress Queue CIDX
-		 * Updates: the Hardware will do this automatically.  And
-		 * since we send the Ingress Queue CIDX Updates to the
-		 * corresponding Ethernet Response Queue, we'll get them very
-		 * quickly.
-		 */
-		if (!q->dbqt)
-			wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F;
+		wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F;
 	}
 
 	wr = (void *)&q->q.desc[q->q.pidx];
@@ -1805,16 +1796,7 @@ static netdev_tx_t cxgb4_vf_eth_xmit(struct sk_buff *skb,
 		 * has opened up.
 		 */
 		eth_txq_stop(txq);
-
-		/* If we're using the SGE Doorbell Queue Timer facility, we
-		 * don't need to ask the Firmware to send us Egress Queue CIDX
-		 * Updates: the Hardware will do this automatically.  And
-		 * since we send the Ingress Queue CIDX Updates to the
-		 * corresponding Ethernet Response Queue, we'll get them very
-		 * quickly.
-		 */
-		if (!txq->dbqt)
-			wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F;
+		wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F;
 	}
 
 	/* Start filling in our Work Request.  Note that we do _not_ handle
@@ -3370,26 +3352,6 @@ static void t4_tx_completion_handler(struct sge_rspq *rspq,
 	}
 
 	txq = &s->ethtxq[pi->first_qset + rspq->idx];
-
-	/* We've got the Hardware Consumer Index Update in the Egress Update
-	 * message.  If we're using the SGE Doorbell Queue Timer mechanism,
-	 * these Egress Update messages will be our sole CIDX Updates we get
-	 * since we don't want to chew up PCIe bandwidth for both Ingress
-	 * Messages and Status Page writes.  However, The code which manages
-	 * reclaiming successfully DMA'ed TX Work Requests uses the CIDX value
-	 * stored in the Status Page at the end of the TX Queue.  It's easiest
-	 * to simply copy the CIDX Update value from the Egress Update message
-	 * to the Status Page.  Also note that no Endian issues need to be
-	 * considered here since both are Big Endian and we're just copying
-	 * bytes consistently ...
-	 */
-	if (txq->dbqt) {
-		struct cpl_sge_egr_update *egr;
-
-		egr = (struct cpl_sge_egr_update *)rsp;
-		WRITE_ONCE(txq->q.stat->cidx, egr->cidx);
-	}
-
 	t4_sge_eth_txq_egress_update(adapter, txq, -1);
 }
 
-- 
2.20.1


From 4a38f543686d8acdb74f3684f6a2da2ab39ccef3 Mon Sep 17 00:00:00 2001
From: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Date: Thu, 19 Mar 2020 23:08:10 +0530
Subject: [PATCH 02/56] cxgb4: fix Txq restart check during backpressure

[ Upstream commit f1f20a8666c55cb534b8f3fc1130eebf01a06155 ]

Driver reclaims descriptors in much smaller batches, even if hardware
indicates more to reclaim, during backpressure. So, fix the check to
restart the Txq during backpressure, by looking at how many
descriptors hardware had indicated to reclaim, and not on how many
descriptors that driver had actually reclaimed. Once the Txq is
restarted, driver will reclaim even more descriptors when Tx path
is entered again.

Fixes: d429005fdf2c ("cxgb4/cxgb4vf: Add support for SGE doorbell queue timer")
Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/sge.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index c816837fbd85..cab3d17e0e1a 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -1307,8 +1307,9 @@ static inline void *write_tso_wr(struct adapter *adap, struct sk_buff *skb,
 int t4_sge_eth_txq_egress_update(struct adapter *adap, struct sge_eth_txq *eq,
 				 int maxreclaim)
 {
+	unsigned int reclaimed, hw_cidx;
 	struct sge_txq *q = &eq->q;
-	unsigned int reclaimed;
+	int hw_in_use;
 
 	if (!q->in_use || !__netif_tx_trylock(eq->txq))
 		return 0;
@@ -1316,12 +1317,17 @@ int t4_sge_eth_txq_egress_update(struct adapter *adap, struct sge_eth_txq *eq,
 	/* Reclaim pending completed TX Descriptors. */
 	reclaimed = reclaim_completed_tx(adap, &eq->q, maxreclaim, true);
 
+	hw_cidx = ntohs(READ_ONCE(q->stat->cidx));
+	hw_in_use = q->pidx - hw_cidx;
+	if (hw_in_use < 0)
+		hw_in_use += q->size;
+
 	/* If the TX Queue is currently stopped and there's now more than half
 	 * the queue available, restart it.  Otherwise bail out since the rest
 	 * of what we want do here is with the possibility of shipping any
 	 * currently buffered Coalesced TX Work Request.
 	 */
-	if (netif_tx_queue_stopped(eq->txq) && txq_avail(q) > (q->size / 2)) {
+	if (netif_tx_queue_stopped(eq->txq) && hw_in_use < (q->size / 2)) {
 		netif_tx_wake_queue(eq->txq);
 		eq->q.restarts++;
 	}
-- 
2.20.1


From 7299b227c70b97a2b15bb6d73bd4f70916d40aa8 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Sat, 14 Mar 2020 08:18:42 +0100
Subject: [PATCH 03/56] geneve: move debug check after netdev unregister

[ Upstream commit 0fda7600c2e174fe27e9cf02e78e345226e441fa ]

The debug check must be done after unregister_netdevice_many() call --
the list_del() for this is done inside .ndo_stop.

Fixes: 2843a25348f8 ("geneve: speedup geneve tunnels dismantle")
Reported-and-tested-by: <syzbot+68a8ed58e3d17c700de5@syzkaller.appspotmail.com>
Cc: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 75757e9954ba..09f279c0182b 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1845,8 +1845,6 @@ static void geneve_destroy_tunnels(struct net *net, struct list_head *head)
 		if (!net_eq(dev_net(geneve->dev), net))
 			unregister_netdevice_queue(geneve->dev, head);
 	}
-
-	WARN_ON_ONCE(!list_empty(&gn->sock_list));
 }
 
 static void __net_exit geneve_exit_batch_net(struct list_head *net_list)
@@ -1861,6 +1859,12 @@ static void __net_exit geneve_exit_batch_net(struct list_head *net_list)
 	/* unregister the devices gathered above */
 	unregister_netdevice_many(&list);
 	rtnl_unlock();
+
+	list_for_each_entry(net, net_list, exit_list) {
+		const struct geneve_net *gn = net_generic(net, geneve_net_id);
+
+		WARN_ON_ONCE(!list_empty(&gn->sock_list));
+	}
 }
 
 static struct pernet_operations geneve_net_ops = {
-- 
2.20.1


From 95c256c21147dfa18d52f5a07bcee44178986705 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Sat, 21 Mar 2020 06:46:50 +0000
Subject: [PATCH 04/56] hsr: fix general protection fault in hsr_addr_is_self()

[ Upstream commit 3a303cfdd28d5f930a307c82e8a9d996394d5ebd ]

The port->hsr is used in the hsr_handle_frame(), which is a
callback of rx_handler.
hsr master and slaves are initialized in hsr_add_port().
This function initializes several pointers, which includes port->hsr after
registering rx_handler.
So, in the rx_handler routine, un-initialized pointer would be used.
In order to fix this, pointers should be initialized before
registering rx_handler.

Test commands:
    ip netns del left
    ip netns del right
    modprobe -rv veth
    modprobe -rv hsr
    killall ping
    modprobe hsr
    ip netns add left
    ip netns add right
    ip link add veth0 type veth peer name veth1
    ip link add veth2 type veth peer name veth3
    ip link add veth4 type veth peer name veth5
    ip link set veth1 netns left
    ip link set veth3 netns right
    ip link set veth4 netns left
    ip link set veth5 netns right
    ip link set veth0 up
    ip link set veth2 up
    ip link set veth0 address fc:00:00:00:00:01
    ip link set veth2 address fc:00:00:00:00:02
    ip netns exec left ip link set veth1 up
    ip netns exec left ip link set veth4 up
    ip netns exec right ip link set veth3 up
    ip netns exec right ip link set veth5 up
    ip link add hsr0 type hsr slave1 veth0 slave2 veth2
    ip a a 192.168.100.1/24 dev hsr0
    ip link set hsr0 up
    ip netns exec left ip link add hsr1 type hsr slave1 veth1 slave2 veth4
    ip netns exec left ip a a 192.168.100.2/24 dev hsr1
    ip netns exec left ip link set hsr1 up
    ip netns exec left ip n a 192.168.100.1 dev hsr1 lladdr \
	    fc:00:00:00:00:01 nud permanent
    ip netns exec left ip n r 192.168.100.1 dev hsr1 lladdr \
	    fc:00:00:00:00:01 nud permanent
    for i in {1..100}
    do
        ip netns exec left ping 192.168.100.1 &
    done
    ip netns exec left hping3 192.168.100.1 -2 --flood &
    ip netns exec right ip link add hsr2 type hsr slave1 veth3 slave2 veth5
    ip netns exec right ip a a 192.168.100.3/24 dev hsr2
    ip netns exec right ip link set hsr2 up
    ip netns exec right ip n a 192.168.100.1 dev hsr2 lladdr \
	    fc:00:00:00:00:02 nud permanent
    ip netns exec right ip n r 192.168.100.1 dev hsr2 lladdr \
	    fc:00:00:00:00:02 nud permanent
    for i in {1..100}
    do
        ip netns exec right ping 192.168.100.1 &
    done
    ip netns exec right hping3 192.168.100.1 -2 --flood &
    while :
    do
        ip link add hsr0 type hsr slave1 veth0 slave2 veth2
	ip a a 192.168.100.1/24 dev hsr0
	ip link set hsr0 up
	ip link del hsr0
    done

Splat looks like:
[  120.954938][    C0] general protection fault, probably for non-canonical address 0xdffffc0000000006: 0000 [#1]I
[  120.957761][    C0] KASAN: null-ptr-deref in range [0x0000000000000030-0x0000000000000037]
[  120.959064][    C0] CPU: 0 PID: 1511 Comm: hping3 Not tainted 5.6.0-rc5+ #460
[  120.960054][    C0] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[  120.962261][    C0] RIP: 0010:hsr_addr_is_self+0x65/0x2a0 [hsr]
[  120.963149][    C0] Code: 44 24 18 70 73 2f c0 48 c1 eb 03 48 8d 04 13 c7 00 f1 f1 f1 f1 c7 40 04 00 f2 f2 f2 4
[  120.966277][    C0] RSP: 0018:ffff8880d9c09af0 EFLAGS: 00010206
[  120.967293][    C0] RAX: 0000000000000006 RBX: 1ffff1101b38135f RCX: 0000000000000000
[  120.968516][    C0] RDX: dffffc0000000000 RSI: ffff8880d17cb208 RDI: 0000000000000000
[  120.969718][    C0] RBP: 0000000000000030 R08: ffffed101b3c0e3c R09: 0000000000000001
[  120.972203][    C0] R10: 0000000000000001 R11: ffffed101b3c0e3b R12: 0000000000000000
[  120.973379][    C0] R13: ffff8880aaf80100 R14: ffff8880aaf800f2 R15: ffff8880aaf80040
[  120.974410][    C0] FS:  00007f58e693f740(0000) GS:ffff8880d9c00000(0000) knlGS:0000000000000000
[  120.979794][    C0] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  120.980773][    C0] CR2: 00007ffcb8b38f29 CR3: 00000000afe8e001 CR4: 00000000000606f0
[  120.981945][    C0] Call Trace:
[  120.982411][    C0]  <IRQ>
[  120.982848][    C0]  ? hsr_add_node+0x8c0/0x8c0 [hsr]
[  120.983522][    C0]  ? rcu_read_lock_held+0x90/0xa0
[  120.984159][    C0]  ? rcu_read_lock_sched_held+0xc0/0xc0
[  120.984944][    C0]  hsr_handle_frame+0x1db/0x4e0 [hsr]
[  120.985597][    C0]  ? hsr_nl_nodedown+0x2b0/0x2b0 [hsr]
[  120.986289][    C0]  __netif_receive_skb_core+0x6bf/0x3170
[  120.992513][    C0]  ? check_chain_key+0x236/0x5d0
[  120.993223][    C0]  ? do_xdp_generic+0x1460/0x1460
[  120.993875][    C0]  ? register_lock_class+0x14d0/0x14d0
[  120.994609][    C0]  ? __netif_receive_skb_one_core+0x8d/0x160
[  120.995377][    C0]  __netif_receive_skb_one_core+0x8d/0x160
[  120.996204][    C0]  ? __netif_receive_skb_core+0x3170/0x3170
[ ... ]

Reported-by: syzbot+fcf5dd39282ceb27108d@syzkaller.appspotmail.com
Fixes: c5a759117210 ("net/hsr: Use list_head (and rcu) instead of array for slave devices.")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/hsr/hsr_slave.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c
index fbfd0db182b7..a9104d42aafb 100644
--- a/net/hsr/hsr_slave.c
+++ b/net/hsr/hsr_slave.c
@@ -145,16 +145,16 @@ int hsr_add_port(struct hsr_priv *hsr, struct net_device *dev,
 	if (!port)
 		return -ENOMEM;
 
+	port->hsr = hsr;
+	port->dev = dev;
+	port->type = type;
+
 	if (type != HSR_PT_MASTER) {
 		res = hsr_portdev_setup(dev, port);
 		if (res)
 			goto fail_dev_setup;
 	}
 
-	port->hsr = hsr;
-	port->dev = dev;
-	port->type = type;
-
 	list_add_tail_rcu(&port->port_list, &hsr->ports);
 	synchronize_rcu();
 
-- 
2.20.1


From f392b95c8808c5d3f65ed7fd6de67fb37fd31df3 Mon Sep 17 00:00:00 2001
From: Qian Cai <cai@lca.pw>
Date: Thu, 19 Mar 2020 22:54:21 -0400
Subject: [PATCH 05/56] ipv4: fix a RCU-list lock in inet_dump_fib()

[ Upstream commit dddeb30bfc43926620f954266fd12c65a7206f07 ]

There is a place,

inet_dump_fib()
  fib_table_dump
    fn_trie_dump_leaf()
      hlist_for_each_entry_rcu()

without rcu_read_lock() will trigger a warning,

 WARNING: suspicious RCU usage
 -----------------------------
 net/ipv4/fib_trie.c:2216 RCU-list traversed in non-reader section!!

 other info that might help us debug this:

 rcu_scheduler_active = 2, debug_locks = 1
 1 lock held by ip/1923:
  #0: ffffffff8ce76e40 (rtnl_mutex){+.+.}, at: netlink_dump+0xd6/0x840

 Call Trace:
  dump_stack+0xa1/0xea
  lockdep_rcu_suspicious+0x103/0x10d
  fn_trie_dump_leaf+0x581/0x590
  fib_table_dump+0x15f/0x220
  inet_dump_fib+0x4ad/0x5d0
  netlink_dump+0x350/0x840
  __netlink_dump_start+0x315/0x3e0
  rtnetlink_rcv_msg+0x4d1/0x720
  netlink_rcv_skb+0xf0/0x220
  rtnetlink_rcv+0x15/0x20
  netlink_unicast+0x306/0x460
  netlink_sendmsg+0x44b/0x770
  __sys_sendto+0x259/0x270
  __x64_sys_sendto+0x80/0xa0
  do_syscall_64+0x69/0xf4
  entry_SYSCALL_64_after_hwframe+0x49/0xb3

Fixes: 18a8021a7be3 ("net/ipv4: Plumb support for filtering route dumps")
Signed-off-by: Qian Cai <cai@lca.pw>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_frontend.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 577db1d50a24..213be9c050ad 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -997,7 +997,9 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 			return -ENOENT;
 		}
 
+		rcu_read_lock();
 		err = fib_table_dump(tb, skb, cb, &filter);
+		rcu_read_unlock();
 		return skb->len ? : err;
 	}
 
-- 
2.20.1


From 3ba7c881394a1df8869196f80e062694ff56b5ad Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Sun, 22 Mar 2020 13:51:13 -0400
Subject: [PATCH 06/56] macsec: restrict to ethernet devices

[ Upstream commit b06d072ccc4b1acd0147b17914b7ad1caa1818bb ]

Only attach macsec to ethernet devices.

Syzbot was able to trigger a KMSAN warning in macsec_handle_frame
by attaching to a phonet device.

Macvlan has a similar check in macvlan_port_create.

v1->v2
  - fix commit message typo

Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macsec.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 57ef24546e96..7644aaa68489 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -16,6 +16,7 @@
 #include <net/genetlink.h>
 #include <net/sock.h>
 #include <net/gro_cells.h>
+#include <linux/if_arp.h>
 
 #include <uapi/linux/if_macsec.h>
 
@@ -3236,6 +3237,8 @@ static int macsec_newlink(struct net *net, struct net_device *dev,
 	real_dev = __dev_get_by_index(net, nla_get_u32(tb[IFLA_LINK]));
 	if (!real_dev)
 		return -ENODEV;
+	if (real_dev->type != ARPHRD_ETHER)
+		return -EINVAL;
 
 	dev->priv_flags |= IFF_MACSEC;
 
-- 
2.20.1


From a6c19bc4c78c61ca2f2a52597fceec7b462cb0e2 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Thu, 19 Mar 2020 13:25:39 +0200
Subject: [PATCH 07/56] mlxsw: pci: Only issue reset when system is ready

[ Upstream commit 6002059d7882c3512e6ac52fa82424272ddfcd5c ]

During initialization the driver issues a software reset command and
then waits for the system status to change back to "ready" state.

However, before issuing the reset command the driver does not check that
the system is actually in "ready" state. On Spectrum-{1,2} systems this
was always the case as the hardware initialization time is very short.
On Spectrum-3 systems this is no longer the case. This results in the
software reset command timing-out and the driver failing to load:

[ 6.347591] mlxsw_spectrum3 0000:06:00.0: Cmd exec timed-out (opcode=40(ACCESS_REG),opcode_mod=0,in_mod=0)
[ 6.358382] mlxsw_spectrum3 0000:06:00.0: Reg cmd access failed (reg_id=9023(mrsr),type=write)
[ 6.368028] mlxsw_spectrum3 0000:06:00.0: cannot register bus device
[ 6.375274] mlxsw_spectrum3: probe of 0000:06:00.0 failed with error -110

Fix this by waiting for the system to become ready both before issuing
the reset command and afterwards. In case of failure, print the last
system status to aid in debugging.

Fixes: da382875c616 ("mlxsw: spectrum: Extend to support Spectrum-3 ASIC")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/pci.c | 50 ++++++++++++++++++-----
 1 file changed, 39 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index 914c33e46fb4..e9ded1a6e131 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -1322,36 +1322,64 @@ static void mlxsw_pci_mbox_free(struct mlxsw_pci *mlxsw_pci,
 			    mbox->mapaddr);
 }
 
-static int mlxsw_pci_sw_reset(struct mlxsw_pci *mlxsw_pci,
-			      const struct pci_device_id *id)
+static int mlxsw_pci_sys_ready_wait(struct mlxsw_pci *mlxsw_pci,
+				    const struct pci_device_id *id,
+				    u32 *p_sys_status)
 {
 	unsigned long end;
-	char mrsr_pl[MLXSW_REG_MRSR_LEN];
-	int err;
+	u32 val;
 
-	mlxsw_reg_mrsr_pack(mrsr_pl);
-	err = mlxsw_reg_write(mlxsw_pci->core, MLXSW_REG(mrsr), mrsr_pl);
-	if (err)
-		return err;
 	if (id->device == PCI_DEVICE_ID_MELLANOX_SWITCHX2) {
 		msleep(MLXSW_PCI_SW_RESET_TIMEOUT_MSECS);
 		return 0;
 	}
 
-	/* We must wait for the HW to become responsive once again. */
+	/* We must wait for the HW to become responsive. */
 	msleep(MLXSW_PCI_SW_RESET_WAIT_MSECS);
 
 	end = jiffies + msecs_to_jiffies(MLXSW_PCI_SW_RESET_TIMEOUT_MSECS);
 	do {
-		u32 val = mlxsw_pci_read32(mlxsw_pci, FW_READY);
-
+		val = mlxsw_pci_read32(mlxsw_pci, FW_READY);
 		if ((val & MLXSW_PCI_FW_READY_MASK) == MLXSW_PCI_FW_READY_MAGIC)
 			return 0;
 		cond_resched();
 	} while (time_before(jiffies, end));
+
+	*p_sys_status = val & MLXSW_PCI_FW_READY_MASK;
+
 	return -EBUSY;
 }
 
+static int mlxsw_pci_sw_reset(struct mlxsw_pci *mlxsw_pci,
+			      const struct pci_device_id *id)
+{
+	struct pci_dev *pdev = mlxsw_pci->pdev;
+	char mrsr_pl[MLXSW_REG_MRSR_LEN];
+	u32 sys_status;
+	int err;
+
+	err = mlxsw_pci_sys_ready_wait(mlxsw_pci, id, &sys_status);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to reach system ready status before reset. Status is 0x%x\n",
+			sys_status);
+		return err;
+	}
+
+	mlxsw_reg_mrsr_pack(mrsr_pl);
+	err = mlxsw_reg_write(mlxsw_pci->core, MLXSW_REG(mrsr), mrsr_pl);
+	if (err)
+		return err;
+
+	err = mlxsw_pci_sys_ready_wait(mlxsw_pci, id, &sys_status);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to reach system ready status after reset. Status is 0x%x\n",
+			sys_status);
+		return err;
+	}
+
+	return 0;
+}
+
 static int mlxsw_pci_alloc_irq_vectors(struct mlxsw_pci *mlxsw_pci)
 {
 	int err;
-- 
2.20.1


From 07c8b1d9dbc97e8e0a5a274aff57ebd9fa86073b Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Thu, 26 Mar 2020 16:17:33 +0200
Subject: [PATCH 08/56] mlxsw: spectrum_mr: Fix list iteration in error path

[ Upstream commit f6bf1bafdc2152bb22aff3a4e947f2441a1d49e2 ]

list_for_each_entry_from_reverse() iterates backwards over the list from
the current position, but in the error path we should start from the
previous position.

Fix this by using list_for_each_entry_continue_reverse() instead.

This suppresses the following error from coccinelle:

drivers/net/ethernet/mellanox/mlxsw//spectrum_mr.c:655:34-38: ERROR:
invalid reference to the index variable of the iterator on line 636

Fixes: c011ec1bbfd6 ("mlxsw: spectrum: Add the multicast routing offloading logic")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
index 54275624718b..336e5ecc68f8 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
@@ -637,12 +637,12 @@ static int mlxsw_sp_mr_vif_resolve(struct mlxsw_sp_mr_table *mr_table,
 	return 0;
 
 err_erif_unresolve:
-	list_for_each_entry_from_reverse(erve, &mr_vif->route_evif_list,
-					 vif_node)
+	list_for_each_entry_continue_reverse(erve, &mr_vif->route_evif_list,
+					     vif_node)
 		mlxsw_sp_mr_route_evif_unresolve(mr_table, erve);
 err_irif_unresolve:
-	list_for_each_entry_from_reverse(irve, &mr_vif->route_ivif_list,
-					 vif_node)
+	list_for_each_entry_continue_reverse(irve, &mr_vif->route_ivif_list,
+					     vif_node)
 		mlxsw_sp_mr_route_ivif_unresolve(mr_table, irve);
 	mr_vif->rif = NULL;
 	return err;
-- 
2.20.1


From 0b998f14fb1b25adf2095f76a8a6c7fa029f0dbc Mon Sep 17 00:00:00 2001
From: Bruno Meneguele <bmeneg@redhat.com>
Date: Thu, 12 Mar 2020 20:08:20 -0300
Subject: [PATCH 09/56] net/bpfilter: fix dprintf usage for /dev/kmsg

[ Upstream commit 13d0f7b814d9b4c67e60d8c2820c86ea181e7d99 ]

The bpfilter UMH code was recently changed to log its informative messages to
/dev/kmsg, however this interface doesn't support SEEK_CUR yet, used by
dprintf(). As result dprintf() returns -EINVAL and doesn't log anything.

However there already had some discussions about supporting SEEK_CUR into
/dev/kmsg interface in the past it wasn't concluded. Since the only user of
that from userspace perspective inside the kernel is the bpfilter UMH
(userspace) module it's better to correct it here instead waiting a conclusion
on the interface.

Fixes: 36c4357c63f3 ("net: bpfilter: print umh messages to /dev/kmsg")
Signed-off-by: Bruno Meneguele <bmeneg@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bpfilter/main.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/net/bpfilter/main.c b/net/bpfilter/main.c
index 77396a098fbe..efea4874743e 100644
--- a/net/bpfilter/main.c
+++ b/net/bpfilter/main.c
@@ -10,7 +10,7 @@
 #include <asm/unistd.h>
 #include "msgfmt.h"
 
-int debug_fd;
+FILE *debug_f;
 
 static int handle_get_cmd(struct mbox_request *cmd)
 {
@@ -35,9 +35,10 @@ static void loop(void)
 		struct mbox_reply reply;
 		int n;
 
+		fprintf(debug_f, "testing the buffer\n");
 		n = read(0, &req, sizeof(req));
 		if (n != sizeof(req)) {
-			dprintf(debug_fd, "invalid request %d\n", n);
+			fprintf(debug_f, "invalid request %d\n", n);
 			return;
 		}
 
@@ -47,7 +48,7 @@ static void loop(void)
 
 		n = write(1, &reply, sizeof(reply));
 		if (n != sizeof(reply)) {
-			dprintf(debug_fd, "reply failed %d\n", n);
+			fprintf(debug_f, "reply failed %d\n", n);
 			return;
 		}
 	}
@@ -55,9 +56,10 @@ static void loop(void)
 
 int main(void)
 {
-	debug_fd = open("/dev/kmsg", 00000002);
-	dprintf(debug_fd, "Started bpfilter\n");
+	debug_f = fopen("/dev/kmsg", "w");
+	setvbuf(debug_f, 0, _IOLBF, 0);
+	fprintf(debug_f, "Started bpfilter\n");
 	loop();
-	close(debug_fd);
+	fclose(debug_f);
 	return 0;
 }
-- 
2.20.1


From 5860d46316edc827a4e44ad70f9588cae97fc186 Mon Sep 17 00:00:00 2001
From: Zh-yuan Ye <ye.zh-yuan@socionext.com>
Date: Tue, 24 Mar 2020 17:28:25 +0900
Subject: [PATCH 10/56] net: cbs: Fix software cbs to consider packet sending
 time

[ Upstream commit 961d0e5b32946703125964f9f5b6321d60f4d706 ]

Currently the software CBS does not consider the packet sending time
when depleting the credits. It caused the throughput to be
Idleslope[kbps] * (Port transmit rate[kbps] / |Sendslope[kbps]|) where
Idleslope * (Port transmit rate / (Idleslope + |Sendslope|)) = Idleslope
is expected. In order to fix the issue above, this patch takes the time
when the packet sending completes into account by moving the anchor time
variable "last" ahead to the send completion time upon transmission and
adding wait when the next dequeue request comes before the send
completion time of the previous packet.

changelog:
V2->V3:
 - remove unnecessary whitespace cleanup
 - add the checks if port_rate is 0 before division

V1->V2:
 - combine variable "send_completed" into "last"
 - add the comment for estimate of the packet sending

Fixes: 585d763af09c ("net/sched: Introduce Credit Based Shaper (CBS) qdisc")
Signed-off-by: Zh-yuan Ye <ye.zh-yuan@socionext.com>
Reviewed-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_cbs.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c
index b2905b03a432..2eaac2ff380f 100644
--- a/net/sched/sch_cbs.c
+++ b/net/sched/sch_cbs.c
@@ -181,6 +181,11 @@ static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch)
 	s64 credits;
 	int len;
 
+	/* The previous packet is still being sent */
+	if (now < q->last) {
+		qdisc_watchdog_schedule_ns(&q->watchdog, q->last);
+		return NULL;
+	}
 	if (q->credits < 0) {
 		credits = timediff_to_credits(now - q->last, q->idleslope);
 
@@ -212,7 +217,12 @@ static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch)
 	credits += q->credits;
 
 	q->credits = max_t(s64, credits, q->locredit);
-	q->last = now;
+	/* Estimate of the transmission of the last byte of the packet in ns */
+	if (unlikely(atomic64_read(&q->port_rate) == 0))
+		q->last = now;
+	else
+		q->last = now + div64_s64(len * NSEC_PER_SEC,
+					  atomic64_read(&q->port_rate));
 
 	return skb;
 }
-- 
2.20.1


From a41e149a86e8da4a48ef2bde5d80e278b379f4bb Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Sun, 22 Mar 2020 13:58:50 -0700
Subject: [PATCH 11/56] net: dsa: Fix duplicate frames flooded by learning

[ Upstream commit 0e62f543bed03a64495bd2651d4fe1aa4bcb7fe5 ]

When both the switch and the bridge are learning about new addresses,
switch ports attached to the bridge would see duplicate ARP frames
because both entities would attempt to send them.

Fixes: 5037d532b83d ("net: dsa: add Broadcom tag RX/TX handler")
Reported-by: Maxime Bizon <mbizon@freebox.fr>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Vivien Didelot <vivien.didelot@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/tag_brcm.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c
index 9c3114179690..9169b63a89e3 100644
--- a/net/dsa/tag_brcm.c
+++ b/net/dsa/tag_brcm.c
@@ -140,6 +140,8 @@ static struct sk_buff *brcm_tag_rcv_ll(struct sk_buff *skb,
 	/* Remove Broadcom tag and update checksum */
 	skb_pull_rcsum(skb, BRCM_TAG_LEN);
 
+	skb->offload_fwd_mark = 1;
+
 	return skb;
 }
 #endif
-- 
2.20.1


From e90670005a3c617e9ee3591b1b691e303e0a2411 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ren=C3=A9=20van=20Dorst?= <opensource@vdorst.com>
Date: Thu, 19 Mar 2020 14:47:56 +0100
Subject: [PATCH 12/56] net: dsa: mt7530: Change the LINK bit to reflect the
 link status
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 22259471b51925353bd7b16f864c79fdd76e425e ]

Andrew reported:

After a number of network port link up/down changes, sometimes the switch
port gets stuck in a state where it thinks it is still transmitting packets
but the cpu port is not actually transmitting anymore. In this state you
will see a message on the console
"mtk_soc_eth 1e100000.ethernet eth0: transmit timed out" and the Tx counter
in ifconfig will be incrementing on virtual port, but not incrementing on
cpu port.

The issue is that MAC TX/RX status has no impact on the link status or
queue manager of the switch. So the queue manager just queues up packets
of a disabled port and sends out pause frames when the queue is full.

Change the LINK bit to reflect the link status.

Fixes: b8f126a8d543 ("net-next: dsa: add dsa support for Mediatek MT7530 switch")
Reported-by: Andrew Smith <andrew.smith@digi.com>
Signed-off-by: René van Dorst <opensource@vdorst.com>
Reviewed-by: Vivien Didelot <vivien.didelot@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mt7530.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index ed1ec10ec62b..60a8a68567ba 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -566,7 +566,7 @@ mt7530_mib_reset(struct dsa_switch *ds)
 static void
 mt7530_port_set_status(struct mt7530_priv *priv, int port, int enable)
 {
-	u32 mask = PMCR_TX_EN | PMCR_RX_EN;
+	u32 mask = PMCR_TX_EN | PMCR_RX_EN | PMCR_FORCE_LNK;
 
 	if (enable)
 		mt7530_set(priv, MT7530_PMCR_P(port), mask);
@@ -1443,7 +1443,7 @@ static void mt7530_phylink_mac_config(struct dsa_switch *ds, int port,
 	mcr_new &= ~(PMCR_FORCE_SPEED_1000 | PMCR_FORCE_SPEED_100 |
 		     PMCR_FORCE_FDX | PMCR_TX_FC_EN | PMCR_RX_FC_EN);
 	mcr_new |= PMCR_IFG_XMIT(1) | PMCR_MAC_MODE | PMCR_BACKOFF_EN |
-		   PMCR_BACKPR_EN | PMCR_FORCE_MODE | PMCR_FORCE_LNK;
+		   PMCR_BACKPR_EN | PMCR_FORCE_MODE;
 
 	/* Are we connected to external phy */
 	if (port == 5 && dsa_is_user_port(ds, 5))
-- 
2.20.1


From e3d59634e4d0bdf80347cc101d9a5b284850f201 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Tue, 24 Mar 2020 11:45:34 +0200
Subject: [PATCH 13/56] net: dsa: tag_8021q: replace dsa_8021q_remove_header
 with __skb_vlan_pop

[ Upstream commit e80f40cbe4dd51371818e967d40da8fe305db5e4 ]

Not only did this wheel did not need reinventing, but there is also
an issue with it: It doesn't remove the VLAN header in a way that
preserves the L2 payload checksum when that is being provided by the DSA
master hw.  It should recalculate checksum both for the push, before
removing the header, and for the pull afterwards. But the current
implementation is quite dizzying, with pulls followed immediately
afterwards by pushes, the memmove is done before the push, etc.  This
makes a DSA master with RX checksumming offload to print stack traces
with the infamous 'hw csum failure' message.

So remove the dsa_8021q_remove_header function and replace it with
something that actually works with inet checksumming.

Fixes: d461933638ae ("net: dsa: tag_8021q: Create helper function for removing VLAN header")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/dsa/8021q.h |  7 -------
 net/dsa/tag_8021q.c       | 43 ---------------------------------------
 net/dsa/tag_sja1105.c     | 19 ++++++++---------
 3 files changed, 9 insertions(+), 60 deletions(-)

diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h
index 0aa803c451a3..c620d9139c28 100644
--- a/include/linux/dsa/8021q.h
+++ b/include/linux/dsa/8021q.h
@@ -28,8 +28,6 @@ int dsa_8021q_rx_switch_id(u16 vid);
 
 int dsa_8021q_rx_source_port(u16 vid);
 
-struct sk_buff *dsa_8021q_remove_header(struct sk_buff *skb);
-
 #else
 
 int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index,
@@ -64,11 +62,6 @@ int dsa_8021q_rx_source_port(u16 vid)
 	return 0;
 }
 
-struct sk_buff *dsa_8021q_remove_header(struct sk_buff *skb)
-{
-	return NULL;
-}
-
 #endif /* IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q) */
 
 #endif /* _NET_DSA_8021Q_H */
diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c
index 2fb6c26294b5..b97ad93d1c1a 100644
--- a/net/dsa/tag_8021q.c
+++ b/net/dsa/tag_8021q.c
@@ -298,47 +298,4 @@ struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev,
 }
 EXPORT_SYMBOL_GPL(dsa_8021q_xmit);
 
-/* In the DSA packet_type handler, skb->data points in the middle of the VLAN
- * tag, after tpid and before tci. This is because so far, ETH_HLEN
- * (DMAC, SMAC, EtherType) bytes were pulled.
- * There are 2 bytes of VLAN tag left in skb->data, and upper
- * layers expect the 'real' EtherType to be consumed as well.
- * Coincidentally, a VLAN header is also of the same size as
- * the number of bytes that need to be pulled.
- *
- * skb_mac_header                                      skb->data
- * |                                                       |
- * v                                                       v
- * |   |   |   |   |   |   |   |   |   |   |   |   |   |   |   |   |   |   |
- * +-----------------------+-----------------------+-------+-------+-------+
- * |    Destination MAC    |      Source MAC       |  TPID |  TCI  | EType |
- * +-----------------------+-----------------------+-------+-------+-------+
- * ^                                               |               |
- * |<--VLAN_HLEN-->to                              <---VLAN_HLEN--->
- * from            |
- *       >>>>>>>   v
- *       >>>>>>>   |   |   |   |   |   |   |   |   |   |   |   |   |   |   |
- *       >>>>>>>   +-----------------------+-----------------------+-------+
- *       >>>>>>>   |    Destination MAC    |      Source MAC       | EType |
- *                 +-----------------------+-----------------------+-------+
- *                 ^                                                       ^
- * (now part of    |                                                       |
- *  skb->head)     skb_mac_header                                  skb->data
- */
-struct sk_buff *dsa_8021q_remove_header(struct sk_buff *skb)
-{
-	u8 *from = skb_mac_header(skb);
-	u8 *dest = from + VLAN_HLEN;
-
-	memmove(dest, from, ETH_HLEN - VLAN_HLEN);
-	skb_pull(skb, VLAN_HLEN);
-	skb_push(skb, ETH_HLEN);
-	skb_reset_mac_header(skb);
-	skb_reset_mac_len(skb);
-	skb_pull_rcsum(skb, ETH_HLEN);
-
-	return skb;
-}
-EXPORT_SYMBOL_GPL(dsa_8021q_remove_header);
-
 MODULE_LICENSE("GPL v2");
diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c
index 63ef2a14c934..12f3ce52e62e 100644
--- a/net/dsa/tag_sja1105.c
+++ b/net/dsa/tag_sja1105.c
@@ -238,14 +238,14 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb,
 {
 	struct sja1105_meta meta = {0};
 	int source_port, switch_id;
-	struct vlan_ethhdr *hdr;
+	struct ethhdr *hdr;
 	u16 tpid, vid, tci;
 	bool is_link_local;
 	bool is_tagged;
 	bool is_meta;
 
-	hdr = vlan_eth_hdr(skb);
-	tpid = ntohs(hdr->h_vlan_proto);
+	hdr = eth_hdr(skb);
+	tpid = ntohs(hdr->h_proto);
 	is_tagged = (tpid == ETH_P_SJA1105);
 	is_link_local = sja1105_is_link_local(skb);
 	is_meta = sja1105_is_meta_frame(skb);
@@ -254,7 +254,12 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb,
 
 	if (is_tagged) {
 		/* Normal traffic path. */
-		tci = ntohs(hdr->h_vlan_TCI);
+		skb_push_rcsum(skb, ETH_HLEN);
+		__skb_vlan_pop(skb, &tci);
+		skb_pull_rcsum(skb, ETH_HLEN);
+		skb_reset_network_header(skb);
+		skb_reset_transport_header(skb);
+
 		vid = tci & VLAN_VID_MASK;
 		source_port = dsa_8021q_rx_source_port(vid);
 		switch_id = dsa_8021q_rx_switch_id(vid);
@@ -283,12 +288,6 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb,
 		return NULL;
 	}
 
-	/* Delete/overwrite fake VLAN header, DSA expects to not find
-	 * it there, see dsa_switch_rcv: skb_push(skb, ETH_HLEN).
-	 */
-	if (is_tagged)
-		skb = dsa_8021q_remove_header(skb);
-
 	return sja1105_rcv_meta_state_machine(skb, &meta, is_link_local,
 					      is_meta);
 }
-- 
2.20.1


From 20fed1d813bf388da435eb2a0a7699b4555e2281 Mon Sep 17 00:00:00 2001
From: "Guilherme G. Piccoli" <gpiccoli@canonical.com>
Date: Fri, 20 Mar 2020 09:55:34 -0300
Subject: [PATCH 14/56] net: ena: Add PCI shutdown handler to allow safe kexec

[ Upstream commit 428c491332bca498c8eb2127669af51506c346c7 ]

Currently ENA only provides the PCI remove() handler, used during rmmod
for example. This is not called on shutdown/kexec path; we are potentially
creating a failure scenario on kexec:

(a) Kexec is triggered, no shutdown() / remove() handler is called for ENA;
instead pci_device_shutdown() clears the master bit of the PCI device,
stopping all DMA transactions;

(b) Kexec reboot happens and the device gets enabled again, likely having
its FW with that DMA transaction buffered; then it may trigger the (now
invalid) memory operation in the new kernel, corrupting kernel memory area.

This patch aims to prevent this, by implementing a shutdown() handler
quite similar to the remove() one - the difference being the handling
of the netdev, which is unregistered on remove(), but following the
convention observed in other drivers, it's only detached on shutdown().

This prevents an odd issue in AWS Nitro instances, in which after the 2nd
kexec the next one will fail with an initrd corruption, caused by a wild
DMA write to invalid kernel memory. The lspci output for the adapter
present in my instance is:

00:05.0 Ethernet controller [0200]: Amazon.com, Inc. Elastic Network
Adapter (ENA) [1d0f:ec20]

Suggested-by: Gavin Shan <gshan@redhat.com>
Signed-off-by: Guilherme G. Piccoli <gpiccoli@canonical.com>
Acked-by: Sameeh Jubran <sameehj@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 51 ++++++++++++++++----
 1 file changed, 41 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 1c1a41bd11da..e91271866ad8 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -3662,13 +3662,15 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 /*****************************************************************************/
 
-/* ena_remove - Device Removal Routine
+/* __ena_shutoff - Helper used in both PCI remove/shutdown routines
  * @pdev: PCI device information struct
+ * @shutdown: Is it a shutdown operation? If false, means it is a removal
  *
- * ena_remove is called by the PCI subsystem to alert the driver
- * that it should release a PCI device.
+ * __ena_shutoff is a helper routine that does the real work on shutdown and
+ * removal paths; the difference between those paths is with regards to whether
+ * dettach or unregister the netdevice.
  */
-static void ena_remove(struct pci_dev *pdev)
+static void __ena_shutoff(struct pci_dev *pdev, bool shutdown)
 {
 	struct ena_adapter *adapter = pci_get_drvdata(pdev);
 	struct ena_com_dev *ena_dev;
@@ -3687,13 +3689,17 @@ static void ena_remove(struct pci_dev *pdev)
 
 	cancel_work_sync(&adapter->reset_task);
 
-	rtnl_lock();
+	rtnl_lock(); /* lock released inside the below if-else block */
 	ena_destroy_device(adapter, true);
-	rtnl_unlock();
-
-	unregister_netdev(netdev);
-
-	free_netdev(netdev);
+	if (shutdown) {
+		netif_device_detach(netdev);
+		dev_close(netdev);
+		rtnl_unlock();
+	} else {
+		rtnl_unlock();
+		unregister_netdev(netdev);
+		free_netdev(netdev);
+	}
 
 	ena_com_rss_destroy(ena_dev);
 
@@ -3708,6 +3714,30 @@ static void ena_remove(struct pci_dev *pdev)
 	vfree(ena_dev);
 }
 
+/* ena_remove - Device Removal Routine
+ * @pdev: PCI device information struct
+ *
+ * ena_remove is called by the PCI subsystem to alert the driver
+ * that it should release a PCI device.
+ */
+
+static void ena_remove(struct pci_dev *pdev)
+{
+	__ena_shutoff(pdev, false);
+}
+
+/* ena_shutdown - Device Shutdown Routine
+ * @pdev: PCI device information struct
+ *
+ * ena_shutdown is called by the PCI subsystem to alert the driver that
+ * a shutdown/reboot (or kexec) is happening and device must be disabled.
+ */
+
+static void ena_shutdown(struct pci_dev *pdev)
+{
+	__ena_shutoff(pdev, true);
+}
+
 #ifdef CONFIG_PM
 /* ena_suspend - PM suspend callback
  * @pdev: PCI device information struct
@@ -3757,6 +3787,7 @@ static struct pci_driver ena_pci_driver = {
 	.id_table	= ena_pci_tbl,
 	.probe		= ena_probe,
 	.remove		= ena_remove,
+	.shutdown	= ena_shutdown,
 #ifdef CONFIG_PM
 	.suspend    = ena_suspend,
 	.resume     = ena_resume,
-- 
2.20.1


From d1875b5b6f5603d080df6ab7b5fbda6f7c9d860b Mon Sep 17 00:00:00 2001
From: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
Date: Mon, 16 Mar 2020 22:56:36 +0800
Subject: [PATCH 15/56] net: mvneta: Fix the case where the last poll did not
 process all rx

[ Upstream commit 065fd83e1be2e1ba0d446a257fd86a3cc7bddb51 ]

For the case where the last mvneta_poll did not process all
RX packets, we need to xor the pp->cause_rx_tx or port->cause_rx_tx
before claculating the rx_queue.

Fixes: 2dcf75e2793c ("net: mvneta: Associate RX queues with each CPU")
Signed-off-by: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index e540f78e38a3..29d715945b3a 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -3036,11 +3036,10 @@ static int mvneta_poll(struct napi_struct *napi, int budget)
 	/* For the case where the last mvneta_poll did not process all
 	 * RX packets
 	 */
-	rx_queue = fls(((cause_rx_tx >> 8) & 0xff));
-
 	cause_rx_tx |= pp->neta_armada3700 ? pp->cause_rx_tx :
 		port->cause_rx_tx;
 
+	rx_queue = fls(((cause_rx_tx >> 8) & 0xff));
 	if (rx_queue) {
 		rx_queue = rx_queue - 1;
 		if (pp->bm_priv)
-- 
2.20.1


From e75eee120b8272b281ab48705e9e4bb995af4b25 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 13 Mar 2020 12:18:09 -0400
Subject: [PATCH 16/56] net/packet: tpacket_rcv: avoid a producer race
 condition

[ Upstream commit 61fad6816fc10fb8793a925d5c1256d1c3db0cd2 ]

PACKET_RX_RING can cause multiple writers to access the same slot if a
fast writer wraps the ring while a slow writer is still copying. This
is particularly likely with few, large, slots (e.g., GSO packets).

Synchronize kernel thread ownership of rx ring slots with a bitmap.

Writers acquire a slot race-free by testing tp_status TP_STATUS_KERNEL
while holding the sk receive queue lock. They release this lock before
copying and set tp_status to TP_STATUS_USER to release to userspace
when done. During copying, another writer may take the lock, also see
TP_STATUS_KERNEL, and start writing to the same slot.

Introduce a new rx_owner_map bitmap with a bit per slot. To acquire a
slot, test and set with the lock held. To release race-free, update
tp_status and owner bit as a transaction, so take the lock again.

This is the one of a variety of discussed options (see Link below):

* instead of a shadow ring, embed the data in the slot itself, such as
in tp_padding. But any test for this field may match a value left by
userspace, causing deadlock.

* avoid the lock on release. This leaves a small race if releasing the
shadow slot before setting TP_STATUS_USER. The below reproducer showed
that this race is not academic. If releasing the slot after tp_status,
the race is more subtle. See the first link for details.

* add a new tp_status TP_KERNEL_OWNED to avoid the transactional store
of two fields. But, legacy applications may interpret all non-zero
tp_status as owned by the user. As libpcap does. So this is possible
only opt-in by newer processes. It can be added as an optional mode.

* embed the struct at the tail of pg_vec to avoid extra allocation.
The implementation proved no less complex than a separate field.

The additional locking cost on release adds contention, no different
than scaling on multicore or multiqueue h/w. In practice, below
reproducer nor small packet tcpdump showed a noticeable change in
perf report in cycles spent in spinlock. Where contention is
problematic, packet sockets support mitigation through PACKET_FANOUT.
And we can consider adding opt-in state TP_KERNEL_OWNED.

Easy to reproduce by running multiple netperf or similar TCP_STREAM
flows concurrently with `tcpdump -B 129 -n greater 60000`.

Based on an earlier patchset by Jon Rosen. See links below.

I believe this issue goes back to the introduction of tpacket_rcv,
which predates git history.

Link: https://www.mail-archive.com/netdev@vger.kernel.org/msg237222.html
Suggested-by: Jon Rosen <jrosen@cisco.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Jon Rosen <jrosen@cisco.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 21 +++++++++++++++++++++
 net/packet/internal.h  |  5 ++++-
 2 files changed, 25 insertions(+), 1 deletion(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 20edb7c25e22..1d63ab3a878a 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2172,6 +2172,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	struct timespec ts;
 	__u32 ts_status;
 	bool is_drop_n_account = false;
+	unsigned int slot_id = 0;
 	bool do_vnet = false;
 
 	/* struct tpacket{2,3}_hdr is aligned to a multiple of TPACKET_ALIGNMENT.
@@ -2274,6 +2275,13 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	if (!h.raw)
 		goto drop_n_account;
 
+	if (po->tp_version <= TPACKET_V2) {
+		slot_id = po->rx_ring.head;
+		if (test_bit(slot_id, po->rx_ring.rx_owner_map))
+			goto drop_n_account;
+		__set_bit(slot_id, po->rx_ring.rx_owner_map);
+	}
+
 	if (do_vnet &&
 	    virtio_net_hdr_from_skb(skb, h.raw + macoff -
 				    sizeof(struct virtio_net_hdr),
@@ -2379,7 +2387,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 #endif
 
 	if (po->tp_version <= TPACKET_V2) {
+		spin_lock(&sk->sk_receive_queue.lock);
 		__packet_set_status(po, h.raw, status);
+		__clear_bit(slot_id, po->rx_ring.rx_owner_map);
+		spin_unlock(&sk->sk_receive_queue.lock);
 		sk->sk_data_ready(sk);
 	} else {
 		prb_clear_blk_fill_status(&po->rx_ring);
@@ -4276,6 +4287,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 {
 	struct pgv *pg_vec = NULL;
 	struct packet_sock *po = pkt_sk(sk);
+	unsigned long *rx_owner_map = NULL;
 	int was_running, order = 0;
 	struct packet_ring_buffer *rb;
 	struct sk_buff_head *rb_queue;
@@ -4361,6 +4373,12 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 			}
 			break;
 		default:
+			if (!tx_ring) {
+				rx_owner_map = bitmap_alloc(req->tp_frame_nr,
+					GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO);
+				if (!rx_owner_map)
+					goto out_free_pg_vec;
+			}
 			break;
 		}
 	}
@@ -4390,6 +4408,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 		err = 0;
 		spin_lock_bh(&rb_queue->lock);
 		swap(rb->pg_vec, pg_vec);
+		if (po->tp_version <= TPACKET_V2)
+			swap(rb->rx_owner_map, rx_owner_map);
 		rb->frame_max = (req->tp_frame_nr - 1);
 		rb->head = 0;
 		rb->frame_size = req->tp_frame_size;
@@ -4421,6 +4441,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 	}
 
 out_free_pg_vec:
+	bitmap_free(rx_owner_map);
 	if (pg_vec)
 		free_pg_vec(pg_vec, order, req->tp_block_nr);
 out:
diff --git a/net/packet/internal.h b/net/packet/internal.h
index 82fb2b10f790..907f4cd2a718 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -70,7 +70,10 @@ struct packet_ring_buffer {
 
 	unsigned int __percpu	*pending_refcnt;
 
-	struct tpacket_kbdq_core	prb_bdqc;
+	union {
+		unsigned long			*rx_owner_map;
+		struct tpacket_kbdq_core	prb_bdqc;
+	};
 };
 
 extern struct mutex fanout_mutex;
-- 
2.20.1


From 48754006a8ec8fdfecfb00c6d6f7a6e99460f2fd Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Tue, 17 Mar 2020 20:04:54 +0200
Subject: [PATCH 17/56] net: phy: dp83867: w/a for fld detect threshold
 bootstrapping issue

[ Upstream commit 749f6f6843115b424680f1aada3c0dd613ad807c ]

When the DP83867 PHY is strapped to enable Fast Link Drop (FLD) feature
STRAP_STS2.STRAP_ FLD (reg 0x006F bit 10), the Energy Lost Threshold for
FLD Energy Lost Mode FLD_THR_CFG.ENERGY_LOST_FLD_THR (reg 0x002e bits 2:0)
will be defaulted to 0x2. This may cause the phy link to be unstable. The
new DP83867 DM recommends to always restore ENERGY_LOST_FLD_THR to 0x1.

Hence, restore default value of FLD_THR_CFG.ENERGY_LOST_FLD_THR to 0x1 when
FLD is enabled by bootstrapping as recommended by DM.

Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/dp83867.c | 21 ++++++++++++++++++++-
 1 file changed, 20 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c
index 01cf71358359..84621a58fa56 100644
--- a/drivers/net/phy/dp83867.c
+++ b/drivers/net/phy/dp83867.c
@@ -28,7 +28,8 @@
 #define DP83867_CTRL		0x1f
 
 /* Extended Registers */
-#define DP83867_CFG4            0x0031
+#define DP83867_FLD_THR_CFG	0x002e
+#define DP83867_CFG4		0x0031
 #define DP83867_CFG4_SGMII_ANEG_MASK (BIT(5) | BIT(6))
 #define DP83867_CFG4_SGMII_ANEG_TIMER_11MS   (3 << 5)
 #define DP83867_CFG4_SGMII_ANEG_TIMER_800US  (2 << 5)
@@ -91,6 +92,7 @@
 #define DP83867_STRAP_STS2_CLK_SKEW_RX_MASK	GENMASK(2, 0)
 #define DP83867_STRAP_STS2_CLK_SKEW_RX_SHIFT	0
 #define DP83867_STRAP_STS2_CLK_SKEW_NONE	BIT(2)
+#define DP83867_STRAP_STS2_STRAP_FLD		BIT(10)
 
 /* PHY CTRL bits */
 #define DP83867_PHYCR_FIFO_DEPTH_SHIFT		14
@@ -123,6 +125,9 @@
 /* CFG4 bits */
 #define DP83867_CFG4_PORT_MIRROR_EN              BIT(0)
 
+/* FLD_THR_CFG */
+#define DP83867_FLD_THR_CFG_ENERGY_LOST_THR_MASK	0x7
+
 enum {
 	DP83867_PORT_MIRROING_KEEP,
 	DP83867_PORT_MIRROING_EN,
@@ -459,6 +464,20 @@ static int dp83867_config_init(struct phy_device *phydev)
 		phy_clear_bits_mmd(phydev, DP83867_DEVADDR, DP83867_CFG4,
 				   BIT(7));
 
+	bs = phy_read_mmd(phydev, DP83867_DEVADDR, DP83867_STRAP_STS2);
+	if (bs & DP83867_STRAP_STS2_STRAP_FLD) {
+		/* When using strap to enable FLD, the ENERGY_LOST_FLD_THR will
+		 * be set to 0x2. This may causes the PHY link to be unstable -
+		 * the default value 0x1 need to be restored.
+		 */
+		ret = phy_modify_mmd(phydev, DP83867_DEVADDR,
+				     DP83867_FLD_THR_CFG,
+				     DP83867_FLD_THR_CFG_ENERGY_LOST_THR_MASK,
+				     0x1);
+		if (ret)
+			return ret;
+	}
+
 	if (phy_interface_is_rgmii(phydev)) {
 		val = phy_read(phydev, MII_DP83867_PHYCTRL);
 		if (val < 0)
-- 
2.20.1


From 919493bfb3e0a994e836048b80aadea1f0cad902 Mon Sep 17 00:00:00 2001
From: Andre Przywara <andre.przywara@arm.com>
Date: Tue, 24 Mar 2020 16:10:10 +0000
Subject: [PATCH 18/56] net: phy: mdio-bcm-unimac: Fix clock handling

[ Upstream commit c312c7818b86b663d32ec5d4b512abf06b23899a ]

The DT binding for this PHY describes an *optional* clock property.
Due to a bug in the error handling logic, we are actually ignoring this
clock *all* of the time so far.

Fix this by using devm_clk_get_optional() to handle this clock properly.

Fixes: b78ac6ecd1b6b ("net: phy: mdio-bcm-unimac: Allow configuring MDIO clock divider")
Signed-off-by: Andre Przywara <andre.przywara@arm.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mdio-bcm-unimac.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/mdio-bcm-unimac.c b/drivers/net/phy/mdio-bcm-unimac.c
index 4a28fb29adaa..fbd36891ee64 100644
--- a/drivers/net/phy/mdio-bcm-unimac.c
+++ b/drivers/net/phy/mdio-bcm-unimac.c
@@ -242,11 +242,9 @@ static int unimac_mdio_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 
-	priv->clk = devm_clk_get(&pdev->dev, NULL);
-	if (PTR_ERR(priv->clk) == -EPROBE_DEFER)
+	priv->clk = devm_clk_get_optional(&pdev->dev, NULL);
+	if (IS_ERR(priv->clk))
 		return PTR_ERR(priv->clk);
-	else
-		priv->clk = NULL;
 
 	ret = clk_prepare_enable(priv->clk);
 	if (ret)
-- 
2.20.1


From 81af8ce5a5edce74f642854de3ec5175ba2ba154 Mon Sep 17 00:00:00 2001
From: Rayagonda Kokatanur <rayagonda.kokatanur@broadcom.com>
Date: Tue, 17 Mar 2020 10:24:35 +0530
Subject: [PATCH 19/56] net: phy: mdio-mux-bcm-iproc: check
 clk_prepare_enable() return value

[ Upstream commit 872307abbd0d9afd72171929806c2fa33dc34179 ]

Check clk_prepare_enable() return value.

Fixes: 2c7230446bc9 ("net: phy: Add pm support to Broadcom iProc mdio mux driver")
Signed-off-by: Rayagonda Kokatanur <rayagonda.kokatanur@broadcom.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mdio-mux-bcm-iproc.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/mdio-mux-bcm-iproc.c b/drivers/net/phy/mdio-mux-bcm-iproc.c
index 88d409e48c1f..aad6809ebe39 100644
--- a/drivers/net/phy/mdio-mux-bcm-iproc.c
+++ b/drivers/net/phy/mdio-mux-bcm-iproc.c
@@ -288,8 +288,13 @@ static int mdio_mux_iproc_suspend(struct device *dev)
 static int mdio_mux_iproc_resume(struct device *dev)
 {
 	struct iproc_mdiomux_desc *md = dev_get_drvdata(dev);
+	int rc;
 
-	clk_prepare_enable(md->core_clk);
+	rc = clk_prepare_enable(md->core_clk);
+	if (rc) {
+		dev_err(md->dev, "failed to enable core clk\n");
+		return rc;
+	}
 	mdio_mux_iproc_config(md);
 
 	return 0;
-- 
2.20.1


From b65c6bd2fc592f1ee2c5648444d8d8694ca9cd29 Mon Sep 17 00:00:00 2001
From: Pawel Dembicki <paweldembicki@gmail.com>
Date: Fri, 20 Mar 2020 21:46:14 +0100
Subject: [PATCH 20/56] net: qmi_wwan: add support for ASKEY WWHC050
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 12a5ba5a1994568d4ceaff9e78c6b0329d953386 ]

ASKEY WWHC050 is a mcie LTE modem.
The oem configuration states:

T:  Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#=  2 Spd=480  MxCh= 0
D:  Ver= 2.10 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1690 ProdID=7588 Rev=ff.ff
S:  Manufacturer=Android
S:  Product=Android
S:  SerialNumber=813f0eef6e6e
C:* #Ifs= 6 Cfg#= 1 Atr=80 MxPwr=500mA
I:* If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 1 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=(none)
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E:  Ad=84(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E:  Ad=86(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
E:  Ad=88(I) Atr=03(Int.) MxPS=   8 Ivl=32ms
E:  Ad=87(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 5 Alt= 0 #EPs= 2 Cls=08(stor.) Sub=06 Prot=50 Driver=(none)
E:  Ad=89(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=06(O) Atr=02(Bulk) MxPS= 512 Ivl=125us

Tested on openwrt distribution.

Signed-off-by: Cezary Jackiewicz <cezary@eko.one.pl>
Signed-off-by: Pawel Dembicki <paweldembicki@gmail.com>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 5754bb6ca0ee..6c738a271257 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1210,6 +1210,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1435, 0xd182, 5)},	/* Wistron NeWeb D18 */
 	{QMI_FIXED_INTF(0x1435, 0xd191, 4)},	/* Wistron NeWeb D19Q1 */
 	{QMI_QUIRK_SET_DTR(0x1508, 0x1001, 4)},	/* Fibocom NL668 series */
+	{QMI_FIXED_INTF(0x1690, 0x7588, 4)},    /* ASKEY WWHC050 */
 	{QMI_FIXED_INTF(0x16d8, 0x6003, 0)},	/* CMOTech 6003 */
 	{QMI_FIXED_INTF(0x16d8, 0x6007, 0)},	/* CMOTech CHE-628S */
 	{QMI_FIXED_INTF(0x16d8, 0x6008, 0)},	/* CMOTech CMU-301 */
-- 
2.20.1


From 4e668cb695a48f822169b2aac67766773f85050f Mon Sep 17 00:00:00 2001
From: Paul Blakey <paulb@mellanox.com>
Date: Wed, 18 Mar 2020 12:50:33 +0200
Subject: [PATCH 21/56] net/sched: act_ct: Fix leak of ct zone template on
 replace

[ Upstream commit dd2af10402684cb5840a127caec9e7cdcff6d167 ]

Currently, on replace, the previous action instance params
is swapped with a newly allocated params. The old params is
only freed (via kfree_rcu), without releasing the allocated
ct zone template related to it.

Call tcf_ct_params_free (via call_rcu) for the old params,
so it will release it.

Fixes: b57dc7c13ea9 ("net/sched: Introduce action ct")
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ct.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index f685c0d73708..41114b463161 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -739,7 +739,7 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla,
 	if (goto_ch)
 		tcf_chain_put_by_act(goto_ch);
 	if (params)
-		kfree_rcu(params, rcu);
+		call_rcu(&params->rcu, tcf_ct_params_free);
 	if (res == ACT_P_CREATED)
 		tcf_idr_insert(tn, *a);
 
-- 
2.20.1


From 00bdb96cd6e1d74ed217a890cb016f782e92d108 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Fri, 13 Mar 2020 22:29:54 -0700
Subject: [PATCH 22/56] net_sched: cls_route: remove the right filter from
 hashtable

[ Upstream commit ef299cc3fa1a9e1288665a9fdc8bff55629fd359 ]

route4_change() allocates a new filter and copies values from
the old one. After the new filter is inserted into the hash
table, the old filter should be removed and freed, as the final
step of the update.

However, the current code mistakenly removes the new one. This
looks apparently wrong to me, and it causes double "free" and
use-after-free too, as reported by syzbot.

Reported-and-tested-by: syzbot+f9b32aaacd60305d9687@syzkaller.appspotmail.com
Reported-and-tested-by: syzbot+2f8c233f131943d6056d@syzkaller.appspotmail.com
Reported-and-tested-by: syzbot+9c2df9fd5e9445b74e01@syzkaller.appspotmail.com
Fixes: 1109c00547fc ("net: sched: RCU cls_route")
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Cc: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_route.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index 6f8786b06bde..5efa3e7ace15 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -534,8 +534,8 @@ static int route4_change(struct net *net, struct sk_buff *in_skb,
 			fp = &b->ht[h];
 			for (pfp = rtnl_dereference(*fp); pfp;
 			     fp = &pfp->next, pfp = rtnl_dereference(*fp)) {
-				if (pfp == f) {
-					*fp = f->next;
+				if (pfp == fold) {
+					rcu_assign_pointer(*fp, fold->next);
 					break;
 				}
 			}
-- 
2.20.1


From 578e900119aa05d87331b9d02bb1f9297a6ce35b Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Wed, 11 Mar 2020 22:42:27 -0700
Subject: [PATCH 23/56] net_sched: hold rtnl lock in
 tcindex_partial_destroy_work()

[ Upstream commit b1be2e8cd290f620777bfdb8aa00890cd2fa02b5 ]

syzbot reported a use-after-free in tcindex_dump(). This is due to
the lack of RTNL in the deferred rcu work. We queue this work with
RTNL in tcindex_change(), later, tcindex_dump() is called:

        fh = tp->ops->get(tp, t->tcm_handle);
	...
        err = tp->ops->change(..., &fh, ...);
        tfilter_notify(..., fh, ...);

but there is nothing to serialize the pending
tcindex_partial_destroy_work() with tcindex_dump().

Fix this by simply holding RTNL in tcindex_partial_destroy_work(),
so that it won't be called until RTNL is released after
tc_new_tfilter() is completed.

Reported-and-tested-by: syzbot+653090db2562495901dc@syzkaller.appspotmail.com
Fixes: 3d210534cc93 ("net_sched: fix a race condition in tcindex_destroy()")
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_tcindex.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 09b7dc5fe7e0..f2cb24b6f0cf 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -261,8 +261,10 @@ static void tcindex_partial_destroy_work(struct work_struct *work)
 					      struct tcindex_data,
 					      rwork);
 
+	rtnl_lock();
 	kfree(p->perfect);
 	kfree(p);
+	rtnl_unlock();
 }
 
 static void tcindex_free_perfect_hash(struct tcindex_data *cp)
-- 
2.20.1


From e98bfda68385561fdedf96007f26029eadd99bc2 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Wed, 11 Mar 2020 22:42:28 -0700
Subject: [PATCH 24/56] net_sched: keep alloc_hash updated after hash
 allocation

[ Upstream commit 0d1c3530e1bd38382edef72591b78e877e0edcd3 ]

In commit 599be01ee567 ("net_sched: fix an OOB access in cls_tcindex")
I moved cp->hash calculation before the first
tcindex_alloc_perfect_hash(), but cp->alloc_hash is left untouched.
This difference could lead to another out of bound access.

cp->alloc_hash should always be the size allocated, we should
update it after this tcindex_alloc_perfect_hash().

Reported-and-tested-by: syzbot+dcc34d54d68ef7d2d53d@syzkaller.appspotmail.com
Reported-and-tested-by: syzbot+c72da7b9ed57cde6fca2@syzkaller.appspotmail.com
Fixes: 599be01ee567 ("net_sched: fix an OOB access in cls_tcindex")
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_tcindex.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index f2cb24b6f0cf..9904299424a1 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -359,6 +359,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 
 		if (tcindex_alloc_perfect_hash(net, cp) < 0)
 			goto errout;
+		cp->alloc_hash = cp->hash;
 		for (i = 0; i < min(cp->hash, p->hash); i++)
 			cp->perfect[i].res = p->perfect[i].res;
 		balloc = 1;
-- 
2.20.1


From 7b8becaab3b4420869d0a49ebc3b80f7f20096ee Mon Sep 17 00:00:00 2001
From: Emil Renner Berthing <kernel@esmil.dk>
Date: Sat, 21 Mar 2020 15:36:19 +0100
Subject: [PATCH 25/56] net: stmmac: dwmac-rk: fix error path in rk_gmac_probe

[ Upstream commit 9de9aa487daff7a5c73434c24269b44ed6a428e6 ]

Make sure we clean up devicetree related configuration
also when clock init fails.

Fixes: fecd4d7eef8b ("net: stmmac: dwmac-rk: Add integrated PHY support")
Signed-off-by: Emil Renner Berthing <kernel@esmil.dk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index dc50ba13a746..2d5573b3dee1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -1411,7 +1411,7 @@ static int rk_gmac_probe(struct platform_device *pdev)
 
 	ret = rk_gmac_clk_init(plat_dat);
 	if (ret)
-		return ret;
+		goto err_remove_config_dt;
 
 	ret = rk_gmac_powerup(plat_dat->bsp_priv);
 	if (ret)
-- 
2.20.1


From 16899c769d173f1d0b15b4af8194ff79fbc0d71a Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Fri, 20 Mar 2020 16:21:17 +0300
Subject: [PATCH 26/56] NFC: fdp: Fix a signedness bug in fdp_nci_send_patch()

[ Upstream commit 0dcdf9f64028ec3b75db6b691560f8286f3898bf ]

The nci_conn_max_data_pkt_payload_size() function sometimes returns
-EPROTO so "max_size" needs to be signed for the error handling to
work.  We can make "payload_size" an int as well.

Fixes: a06347c04c13 ("NFC: Add Intel Fields Peak NFC solution driver")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/nfc/fdp/fdp.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/nfc/fdp/fdp.c b/drivers/nfc/fdp/fdp.c
index 0cc9ac856fe2..ed2123129e0e 100644
--- a/drivers/nfc/fdp/fdp.c
+++ b/drivers/nfc/fdp/fdp.c
@@ -184,7 +184,7 @@ static int fdp_nci_send_patch(struct nci_dev *ndev, u8 conn_id, u8 type)
 	const struct firmware *fw;
 	struct sk_buff *skb;
 	unsigned long len;
-	u8 max_size, payload_size;
+	int max_size, payload_size;
 	int rc = 0;
 
 	if ((type == NCI_PATCH_TYPE_OTP && !info->otp_patch) ||
@@ -207,8 +207,7 @@ static int fdp_nci_send_patch(struct nci_dev *ndev, u8 conn_id, u8 type)
 
 	while (len) {
 
-		payload_size = min_t(unsigned long, (unsigned long) max_size,
-				     len);
+		payload_size = min_t(unsigned long, max_size, len);
 
 		skb = nci_skb_alloc(ndev, (NCI_CTRL_HDR_SIZE + payload_size),
 				    GFP_KERNEL);
-- 
2.20.1


From 378da7969dd073a46df5e6f590c2db3daa5e8bc9 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Tue, 24 Mar 2020 20:58:29 +0100
Subject: [PATCH 27/56] r8169: re-enable MSI on RTL8168c

[ Upstream commit f13bc68131b0c0d67a77fb43444e109828a983bf ]

The original change fixed an issue on RTL8168b by mimicking the vendor
driver behavior to disable MSI on chip versions before RTL8168d.
This however now caused an issue on a system with RTL8168c, see [0].
Therefore leave MSI disabled on RTL8168b, but re-enable it on RTL8168c.

[0] https://bugzilla.redhat.com/show_bug.cgi?id=1792839

Fixes: 003bd5b4a7b4 ("r8169: don't use MSI before RTL8168d")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 2d2d22f86dc6..27d963a366d4 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -6579,7 +6579,7 @@ static int rtl_alloc_irq(struct rtl8169_private *tp)
 		RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~MSIEnable);
 		rtl_lock_config_regs(tp);
 		/* fall through */
-	case RTL_GIGA_MAC_VER_07 ... RTL_GIGA_MAC_VER_24:
+	case RTL_GIGA_MAC_VER_07 ... RTL_GIGA_MAC_VER_17:
 		flags = PCI_IRQ_LEGACY;
 		break;
 	default:
-- 
2.20.1


From 0c3323f81b17a80510b438a0ab17c050b06da976 Mon Sep 17 00:00:00 2001
From: Oliver Hartkopp <socketcan@hartkopp.net>
Date: Sat, 21 Mar 2020 14:08:29 +0100
Subject: [PATCH 28/56] slcan: not call free_netdev before rtnl_unlock in
 slcan_open

[ Upstream commit 2091a3d42b4f339eaeed11228e0cbe9d4f92f558 ]

As the description before netdev_run_todo, we cannot call free_netdev
before rtnl_unlock, fix it by reorder the code.

This patch is a 1:1 copy of upstream slip.c commit f596c87005f7
("slip: not call free_netdev before rtnl_unlock in slip_open").

Reported-by: yangerkun <yangerkun@huawei.com>
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/can/slcan.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c
index 2f5c287eac95..a3664281a33f 100644
--- a/drivers/net/can/slcan.c
+++ b/drivers/net/can/slcan.c
@@ -625,7 +625,10 @@ static int slcan_open(struct tty_struct *tty)
 	tty->disc_data = NULL;
 	clear_bit(SLF_INUSE, &sl->flags);
 	slc_free_netdev(sl->dev);
+	/* do not call free_netdev before rtnl_unlock */
+	rtnl_unlock();
 	free_netdev(sl->dev);
+	return err;
 
 err_exit:
 	rtnl_unlock();
-- 
2.20.1


From 0ac10c227eb5f4141633adcf1c604a7a77859759 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 20 Mar 2020 16:52:02 +0100
Subject: [PATCH 29/56] tcp: also NULL skb->dev when copy was needed

[ Upstream commit 07f8e4d0fddbf2f87e4cefb551278abc38db8cdd ]

In rare cases retransmit logic will make a full skb copy, which will not
trigger the zeroing added in recent change
b738a185beaa ("tcp: ensure skb->dev is NULL before leaving TCP stack").

Cc: Eric Dumazet <edumazet@google.com>
Fixes: 75c119afe14f ("tcp: implement rb-tree based retransmit queue")
Fixes: 28f8bfd1ac94 ("netfilter: Support iif matches in POSTROUTING")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index b62b59b18db9..74d32739eaaa 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2976,8 +2976,12 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 
 		tcp_skb_tsorted_save(skb) {
 			nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC);
-			err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
-				     -ENOBUFS;
+			if (nskb) {
+				nskb->dev = NULL;
+				err = tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC);
+			} else {
+				err = -ENOBUFS;
+			}
 		} tcp_skb_tsorted_restore(skb);
 
 		if (!err) {
-- 
2.20.1


From fdf2065b5b28e6527de9b8ea55e64babcffd5211 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 19 Mar 2020 12:49:55 -0700
Subject: [PATCH 30/56] tcp: ensure skb->dev is NULL before leaving TCP stack

[ Upstream commit b738a185beaab8728943acdb3e67371b8a88185e ]

skb->rbnode is sharing three skb fields : next, prev, dev

When a packet is sent, TCP keeps the original skb (master)
in a rtx queue, which was converted to rbtree a while back.

__tcp_transmit_skb() is responsible to clone the master skb,
and add the TCP header to the clone before sending it
to network layer.

skb_clone() already clears skb->next and skb->prev, but copies
the master oskb->dev into the clone.

We need to clear skb->dev, otherwise lower layers could interpret
the value as a pointer to a netdev.

This old bug surfaced recently when commit 28f8bfd1ac94
("netfilter: Support iif matches in POSTROUTING") was merged.

Before this netfilter commit, skb->dev value was ignored and
changed before reaching dev_queue_xmit()

Fixes: 75c119afe14f ("tcp: implement rb-tree based retransmit queue")
Fixes: 28f8bfd1ac94 ("netfilter: Support iif matches in POSTROUTING")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Martin Zaharinov <micron10@gmail.com>
Cc: Florian Westphal <fw@strlen.de>
Cc: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 74d32739eaaa..32c200e7cd19 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1048,6 +1048,10 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 
 		if (unlikely(!skb))
 			return -ENOBUFS;
+		/* retransmit skbs might have a non zero value in skb->dev
+		 * because skb->dev is aliased with skb->rbnode.rb_left
+		 */
+		skb->dev = NULL;
 	}
 
 	inet = inet_sk(sk);
-- 
2.20.1


From 425c6a417cce5f42c59fd045f33ad105032b54f6 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 18 Mar 2020 19:21:02 -0700
Subject: [PATCH 31/56] tcp: repair: fix TCP_QUEUE_SEQ implementation

[ Upstream commit 6cd6cbf593bfa3ae6fc3ed34ac21da4d35045425 ]

When application uses TCP_QUEUE_SEQ socket option to
change tp->rcv_next, we must also update tp->copied_seq.

Otherwise, stuff relying on tcp_inq() being precise can
eventually be confused.

For example, tcp_zerocopy_receive() might crash because
it does not expect tcp_recv_skb() to return NULL.

We could add tests in various places to fix the issue,
or simply make sure tcp_inq() wont return a random value,
and leave fast path as it is.

Note that this fixes ioctl(fd, SIOCINQ, &val) at the same
time.

Fixes: ee9952831cfd ("tcp: Initial repair mode")
Fixes: 05255b823a61 ("tcp: add TCP_ZEROCOPY_RECEIVE support for zerocopy receive")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 94e137f7aa9f..4a4af955e467 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2947,8 +2947,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 			err = -EPERM;
 		else if (tp->repair_queue == TCP_SEND_QUEUE)
 			WRITE_ONCE(tp->write_seq, val);
-		else if (tp->repair_queue == TCP_RECV_QUEUE)
+		else if (tp->repair_queue == TCP_RECV_QUEUE) {
 			WRITE_ONCE(tp->rcv_nxt, val);
+			WRITE_ONCE(tp->copied_seq, val);
+		}
 		else
 			err = -EINVAL;
 		break;
-- 
2.20.1


From ce5c17a4ecc29c7475ee4d82c625d4d388a75859 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Wed, 18 Mar 2020 13:28:09 +0000
Subject: [PATCH 32/56] vxlan: check return value of gro_cells_init()

[ Upstream commit 384d91c267e621e0926062cfb3f20cb72dc16928 ]

gro_cells_init() returns error if memory allocation is failed.
But the vxlan module doesn't check the return value of gro_cells_init().

Fixes: 58ce31cca1ff ("vxlan: GRO support at tunnel layer")`
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 1c5159dcc720..8b986079d650 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2778,10 +2778,19 @@ static void vxlan_vs_add_dev(struct vxlan_sock *vs, struct vxlan_dev *vxlan,
 /* Setup stats when device is created */
 static int vxlan_init(struct net_device *dev)
 {
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	int err;
+
 	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
 	if (!dev->tstats)
 		return -ENOMEM;
 
+	err = gro_cells_init(&vxlan->gro_cells, dev);
+	if (err) {
+		free_percpu(dev->tstats);
+		return err;
+	}
+
 	return 0;
 }
 
@@ -3042,8 +3051,6 @@ static void vxlan_setup(struct net_device *dev)
 
 	vxlan->dev = dev;
 
-	gro_cells_init(&vxlan->gro_cells, dev);
-
 	for (h = 0; h < FDB_HASH_SIZE; ++h) {
 		spin_lock_init(&vxlan->hash_lock[h]);
 		INIT_HLIST_HEAD(&vxlan->fdb_head[h]);
-- 
2.20.1


From 640611bb8ef59af89652e33e507911607fa2bbbc Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Mon, 16 Mar 2020 14:44:55 -0700
Subject: [PATCH 33/56] Revert "net: bcmgenet: use RGMII loopback for MAC
 reset"

[ Upstream commit 612eb1c3b9e504de24136c947ed7c07bc342f3aa ]

This reverts commit 3a55402c93877d291b0a612d25edb03d1b4b93ac.

This is not a good solution when connecting to an external switch
that may not support the isolation of the TXC signal resulting in
output driver contention on the pin.

A different solution is necessary.

Signed-off-by: Doug Berger <opendmb@gmail.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/broadcom/genet/bcmgenet.c    |  2 ++
 drivers/net/ethernet/broadcom/genet/bcmmii.c  | 34 -------------------
 2 files changed, 2 insertions(+), 34 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 0a8624be44a9..1c7bedd8442e 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -1996,6 +1996,8 @@ static void reset_umac(struct bcmgenet_priv *priv)
 
 	/* issue soft reset with (rg)mii loopback to ensure a stable rxclk */
 	bcmgenet_umac_writel(priv, CMD_SW_RESET | CMD_LCL_LOOP_EN, UMAC_CMD);
+	udelay(2);
+	bcmgenet_umac_writel(priv, 0, UMAC_CMD);
 }
 
 static void bcmgenet_intr_disable(struct bcmgenet_priv *priv)
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index 10244941a7a6..69e80fb6e039 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -181,38 +181,8 @@ int bcmgenet_mii_config(struct net_device *dev, bool init)
 	const char *phy_name = NULL;
 	u32 id_mode_dis = 0;
 	u32 port_ctrl;
-	int bmcr = -1;
-	int ret;
 	u32 reg;
 
-	/* MAC clocking workaround during reset of umac state machines */
-	reg = bcmgenet_umac_readl(priv, UMAC_CMD);
-	if (reg & CMD_SW_RESET) {
-		/* An MII PHY must be isolated to prevent TXC contention */
-		if (priv->phy_interface == PHY_INTERFACE_MODE_MII) {
-			ret = phy_read(phydev, MII_BMCR);
-			if (ret >= 0) {
-				bmcr = ret;
-				ret = phy_write(phydev, MII_BMCR,
-						bmcr | BMCR_ISOLATE);
-			}
-			if (ret) {
-				netdev_err(dev, "failed to isolate PHY\n");
-				return ret;
-			}
-		}
-		/* Switch MAC clocking to RGMII generated clock */
-		bcmgenet_sys_writel(priv, PORT_MODE_EXT_GPHY, SYS_PORT_CTRL);
-		/* Ensure 5 clks with Rx disabled
-		 * followed by 5 clks with Reset asserted
-		 */
-		udelay(4);
-		reg &= ~(CMD_SW_RESET | CMD_LCL_LOOP_EN);
-		bcmgenet_umac_writel(priv, reg, UMAC_CMD);
-		/* Ensure 5 more clocks before Rx is enabled */
-		udelay(2);
-	}
-
 	switch (priv->phy_interface) {
 	case PHY_INTERFACE_MODE_INTERNAL:
 		phy_name = "internal PHY";
@@ -282,10 +252,6 @@ int bcmgenet_mii_config(struct net_device *dev, bool init)
 
 	bcmgenet_sys_writel(priv, port_ctrl, SYS_PORT_CTRL);
 
-	/* Restore the MII PHY after isolation */
-	if (bmcr >= 0)
-		phy_write(phydev, MII_BMCR, bmcr);
-
 	priv->ext_phy = !priv->internal_phy &&
 			(priv->phy_interface != PHY_INTERFACE_MODE_MOCA);
 
-- 
2.20.1


From 17eab56442403a5376a22ea2eb8c9e0787c1283d Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Mon, 16 Mar 2020 14:44:56 -0700
Subject: [PATCH 34/56] net: bcmgenet: keep MAC in reset until PHY is up

[ Upstream commit 88f6c8bf1aaed5039923fb4c701cab4d42176275 ]

As noted in commit 28c2d1a7a0bf ("net: bcmgenet: enable loopback
during UniMAC sw_reset") the UniMAC must be clocked at least 5
cycles while the sw_reset is asserted to ensure a clean reset.

That commit enabled local loopback to provide an Rx clock from the
GENET sourced Tx clk. However, when connected in MII mode the Tx
clk is sourced by the PHY so if an EPHY is not supplying clocks
(e.g. when the link is down) the UniMAC does not receive the
necessary clocks.

This commit extends the sw_reset window until the PHY reports that
the link is up thereby ensuring that the clocks are being provided
to the MAC to produce a clean reset.

One consequence is that if the system attempts to enter a Wake on
LAN suspend state when the PHY link has not been active the MAC
may not have had a chance to initialize cleanly. In this case, we
remove the sw_reset and enable the WoL reception path as normal
with the hope that the PHY will provide the necessary clocks to
drive the WoL blocks if the link becomes active after the system
has entered suspend.

Fixes: 1c1008c793fa ("net: bcmgenet: add main driver file")
Signed-off-by: Doug Berger <opendmb@gmail.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c     | 10 ++++------
 drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c |  6 +++++-
 drivers/net/ethernet/broadcom/genet/bcmmii.c       |  6 ++++++
 3 files changed, 15 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 1c7bedd8442e..98cb15d85ee8 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -1972,6 +1972,8 @@ static void umac_enable_set(struct bcmgenet_priv *priv, u32 mask, bool enable)
 	u32 reg;
 
 	reg = bcmgenet_umac_readl(priv, UMAC_CMD);
+	if (reg & CMD_SW_RESET)
+		return;
 	if (enable)
 		reg |= mask;
 	else
@@ -1991,13 +1993,9 @@ static void reset_umac(struct bcmgenet_priv *priv)
 	bcmgenet_rbuf_ctrl_set(priv, 0);
 	udelay(10);
 
-	/* disable MAC while updating its registers */
-	bcmgenet_umac_writel(priv, 0, UMAC_CMD);
-
-	/* issue soft reset with (rg)mii loopback to ensure a stable rxclk */
-	bcmgenet_umac_writel(priv, CMD_SW_RESET | CMD_LCL_LOOP_EN, UMAC_CMD);
+	/* issue soft reset and disable MAC while updating its registers */
+	bcmgenet_umac_writel(priv, CMD_SW_RESET, UMAC_CMD);
 	udelay(2);
-	bcmgenet_umac_writel(priv, 0, UMAC_CMD);
 }
 
 static void bcmgenet_intr_disable(struct bcmgenet_priv *priv)
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
index ea20d94bd050..c9a43695b182 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
@@ -132,8 +132,12 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 		return -EINVAL;
 	}
 
-	/* disable RX */
+	/* Can't suspend with WoL if MAC is still in reset */
 	reg = bcmgenet_umac_readl(priv, UMAC_CMD);
+	if (reg & CMD_SW_RESET)
+		reg &= ~CMD_SW_RESET;
+
+	/* disable RX */
 	reg &= ~CMD_RX_EN;
 	bcmgenet_umac_writel(priv, reg, UMAC_CMD);
 	mdelay(10);
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index 69e80fb6e039..b5930f80039d 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -95,6 +95,12 @@ void bcmgenet_mii_setup(struct net_device *dev)
 			       CMD_HD_EN |
 			       CMD_RX_PAUSE_IGNORE | CMD_TX_PAUSE_IGNORE);
 		reg |= cmd_bits;
+		if (reg & CMD_SW_RESET) {
+			reg &= ~CMD_SW_RESET;
+			bcmgenet_umac_writel(priv, reg, UMAC_CMD);
+			udelay(2);
+			reg |= CMD_TX_EN | CMD_RX_EN;
+		}
 		bcmgenet_umac_writel(priv, reg, UMAC_CMD);
 	} else {
 		/* done if nothing has changed */
-- 
2.20.1


From ac6ae879d36484c17d4f3441e09fde6558d914a9 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 22 Mar 2020 16:40:01 -0400
Subject: [PATCH 35/56] bnxt_en: Fix Priority Bytes and Packets counters in
 ethtool -S.

[ Upstream commit a24ec3220f369aa0b94c863b6b310685a727151c ]

There is an indexing bug in determining these ethtool priority
counters.  Instead of using the queue ID to index, we need to
normalize by modulo 10 to get the index.  This index is then used
to obtain the proper CoS queue counter.  Rename bp->pri2cos to
bp->pri2cos_idx to make this more clear.

Fixes: e37fed790335 ("bnxt_en: Add ethtool -S priority counters.")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c         | 10 +++++++++-
 drivers/net/ethernet/broadcom/bnxt/bnxt.h         |  2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c |  8 ++++----
 3 files changed, 14 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 05da27a64d55..582cf1807d0b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -7406,14 +7406,22 @@ static int bnxt_hwrm_port_qstats_ext(struct bnxt *bp)
 		pri2cos = &resp2->pri0_cos_queue_id;
 		for (i = 0; i < 8; i++) {
 			u8 queue_id = pri2cos[i];
+			u8 queue_idx;
 
+			/* Per port queue IDs start from 0, 10, 20, etc */
+			queue_idx = queue_id % 10;
+			if (queue_idx > BNXT_MAX_QUEUE) {
+				bp->pri2cos_valid = false;
+				goto qstats_done;
+			}
 			for (j = 0; j < bp->max_q; j++) {
 				if (bp->q_ids[j] == queue_id)
-					bp->pri2cos[i] = j;
+					bp->pri2cos_idx[i] = queue_idx;
 			}
 		}
 		bp->pri2cos_valid = 1;
 	}
+qstats_done:
 	mutex_unlock(&bp->hwrm_cmd_lock);
 	return rc;
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index f14335433a64..c67707c1a969 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1714,7 +1714,7 @@ struct bnxt {
 	u16			fw_rx_stats_ext_size;
 	u16			fw_tx_stats_ext_size;
 	u16			hw_ring_stats_size;
-	u8			pri2cos[8];
+	u8			pri2cos_idx[8];
 	u8			pri2cos_valid;
 
 	u16			hwrm_max_req_len;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 972383aefc2b..7946807c99b8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -589,25 +589,25 @@ static void bnxt_get_ethtool_stats(struct net_device *dev,
 		if (bp->pri2cos_valid) {
 			for (i = 0; i < 8; i++, j++) {
 				long n = bnxt_rx_bytes_pri_arr[i].base_off +
-					 bp->pri2cos[i];
+					 bp->pri2cos_idx[i];
 
 				buf[j] = le64_to_cpu(*(rx_port_stats_ext + n));
 			}
 			for (i = 0; i < 8; i++, j++) {
 				long n = bnxt_rx_pkts_pri_arr[i].base_off +
-					 bp->pri2cos[i];
+					 bp->pri2cos_idx[i];
 
 				buf[j] = le64_to_cpu(*(rx_port_stats_ext + n));
 			}
 			for (i = 0; i < 8; i++, j++) {
 				long n = bnxt_tx_bytes_pri_arr[i].base_off +
-					 bp->pri2cos[i];
+					 bp->pri2cos_idx[i];
 
 				buf[j] = le64_to_cpu(*(tx_port_stats_ext + n));
 			}
 			for (i = 0; i < 8; i++, j++) {
 				long n = bnxt_tx_pkts_pri_arr[i].base_off +
-					 bp->pri2cos[i];
+					 bp->pri2cos_idx[i];
 
 				buf[j] = le64_to_cpu(*(tx_port_stats_ext + n));
 			}
-- 
2.20.1


From 3edf6168c795d5b450ecec18b79a7b5edae6f4c4 Mon Sep 17 00:00:00 2001
From: Edwin Peer <edwin.peer@broadcom.com>
Date: Sun, 22 Mar 2020 16:40:02 -0400
Subject: [PATCH 36/56] bnxt_en: fix memory leaks in bnxt_dcbnl_ieee_getets()

[ Upstream commit 62d4073e86e62e316bea2c53e77db10418fd5dd7 ]

The allocated ieee_ets structure goes out of scope without being freed,
leaking memory. Appropriate result codes should be returned so that
callers do not rely on invalid data passed by reference.

Also cache the ETS config retrieved from the device so that it doesn't
need to be freed. The balance of the code was clearly written with the
intent of having the results of querying the hardware cached in the
device structure. The commensurate store was evidently missed though.

Fixes: 7df4ae9fe855 ("bnxt_en: Implement DCBNL to support host-based DCBX.")
Signed-off-by: Edwin Peer <edwin.peer@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
index fb6f30d0d1d0..b1511bcffb1b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
@@ -479,24 +479,26 @@ static int bnxt_dcbnl_ieee_getets(struct net_device *dev, struct ieee_ets *ets)
 {
 	struct bnxt *bp = netdev_priv(dev);
 	struct ieee_ets *my_ets = bp->ieee_ets;
+	int rc;
 
 	ets->ets_cap = bp->max_tc;
 
 	if (!my_ets) {
-		int rc;
-
 		if (bp->dcbx_cap & DCB_CAP_DCBX_HOST)
 			return 0;
 
 		my_ets = kzalloc(sizeof(*my_ets), GFP_KERNEL);
 		if (!my_ets)
-			return 0;
+			return -ENOMEM;
 		rc = bnxt_hwrm_queue_cos2bw_qcfg(bp, my_ets);
 		if (rc)
-			return 0;
+			goto error;
 		rc = bnxt_hwrm_queue_pri2cos_qcfg(bp, my_ets);
 		if (rc)
-			return 0;
+			goto error;
+
+		/* cache result */
+		bp->ieee_ets = my_ets;
 	}
 
 	ets->cbs = my_ets->cbs;
@@ -505,6 +507,9 @@ static int bnxt_dcbnl_ieee_getets(struct net_device *dev, struct ieee_ets *ets)
 	memcpy(ets->tc_tsa, my_ets->tc_tsa, sizeof(ets->tc_tsa));
 	memcpy(ets->prio_tc, my_ets->prio_tc, sizeof(ets->prio_tc));
 	return 0;
+error:
+	kfree(my_ets);
+	return rc;
 }
 
 static int bnxt_dcbnl_ieee_setets(struct net_device *dev, struct ieee_ets *ets)
-- 
2.20.1


From 3bc0b10da9da938002a40a432fda742d3a906758 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 22 Mar 2020 16:40:03 -0400
Subject: [PATCH 37/56] bnxt_en: Return error if bnxt_alloc_ctx_mem() fails.

[ Upstream commit 0b5b561cea32d5bb1e0a82d65b755a3cb5212141 ]

The current code ignores the return value from
bnxt_hwrm_func_backing_store_cfg(), causing the driver to proceed in
the init path even when this vital firmware call has failed.  Fix it
by propagating the error code to the caller.

Fixes: 1b9394e5a2ad ("bnxt_en: Configure context memory on new devices.")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 582cf1807d0b..53c210121923 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -6880,12 +6880,12 @@ static int bnxt_alloc_ctx_mem(struct bnxt *bp)
 	}
 	ena |= FUNC_BACKING_STORE_CFG_REQ_DFLT_ENABLES;
 	rc = bnxt_hwrm_func_backing_store_cfg(bp, ena);
-	if (rc)
+	if (rc) {
 		netdev_err(bp->dev, "Failed configuring context mem, rc = %d.\n",
 			   rc);
-	else
-		ctx->flags |= BNXT_CTX_FLAG_INITED;
-
+		return rc;
+	}
+	ctx->flags |= BNXT_CTX_FLAG_INITED;
 	return 0;
 }
 
-- 
2.20.1


From 22e40347e29982a42b769b8845b51ddf6dbd4721 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 22 Mar 2020 16:40:04 -0400
Subject: [PATCH 38/56] bnxt_en: Free context memory after disabling PCI in
 probe error path.

[ Upstream commit 62bfb932a51f6d08eb409248e69f8d6428c2cabd ]

Other shutdown code paths will always disable PCI first to shutdown DMA
before freeing context memory.  Do the same sequence in the error path
of probe to be safe and consistent.

Fixes: c20dc142dd7b ("bnxt_en: Disable bus master during PCI shutdown and driver unload.")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 53c210121923..9ad40bfdfd4f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -11959,12 +11959,12 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	bnxt_hwrm_func_drv_unrgtr(bp);
 	bnxt_free_hwrm_short_cmd_req(bp);
 	bnxt_free_hwrm_resources(bp);
-	bnxt_free_ctx_mem(bp);
-	kfree(bp->ctx);
-	bp->ctx = NULL;
 	kfree(bp->fw_health);
 	bp->fw_health = NULL;
 	bnxt_cleanup_pci(bp);
+	bnxt_free_ctx_mem(bp);
+	kfree(bp->ctx);
+	bp->ctx = NULL;
 
 init_err_free:
 	free_netdev(dev);
-- 
2.20.1


From 61e093df952ef0d6b7661ac33f0ccd2c557c1ad8 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Sun, 22 Mar 2020 16:40:05 -0400
Subject: [PATCH 39/56] bnxt_en: Reset rings if ring reservation fails during
 open()

[ Upstream commit 5d765a5e4bd7c368e564e11402bba74cf7f03ac1 ]

If ring counts are not reset when ring reservation fails,
bnxt_init_dflt_ring_mode() will not be called again to reinitialise
IRQs when open() is called and results in system crash as napi will
also be not initialised. This patch fixes it by resetting the ring
counts.

Fixes: 47558acd56a7 ("bnxt_en: Reserve rings at driver open if none was reserved at probe time.")
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 9ad40bfdfd4f..b92c47518665 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -11666,6 +11666,10 @@ static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh)
 		bp->rx_nr_rings++;
 		bp->cp_nr_rings++;
 	}
+	if (rc) {
+		bp->tx_nr_rings = 0;
+		bp->rx_nr_rings = 0;
+	}
 	return rc;
 }
 
-- 
2.20.1


From 178ed6f1c9c05fa50807439db58fdef5378e8608 Mon Sep 17 00:00:00 2001
From: Arthur Kiyanovski <akiyano@amazon.com>
Date: Tue, 17 Mar 2020 09:06:39 +0200
Subject: [PATCH 40/56] net: ena: fix incorrect setting of the number of msix
 vectors

[ Upstream commit ce1f352162828ba07470328828a32f47aa759020 ]

Overview:
We don't frequently change the msix vectors throughout the life cycle of
the driver. We do so in two functions: ena_probe() and ena_restore().
ena_probe() is only called when the driver is loaded. ena_restore() on the
other hand is called during device reset / resume operations.

We use num_io_queues for calculating and allocating the number of msix
vectors. At ena_probe() this value is equal to max_num_io_queues and thus
this is not an issue, however ena_restore() might be called after the
number of io queues has changed.

A possible bug scenario is as follows:

* Change number of queues from 8 to 4.
  (num_io_queues = 4, max_num_io_queues = 8, msix_vecs = 9,)
* Trigger reset occurs -> ena_restore is called.
  (num_io_queues = 4, max_num_io_queues =8 , msix_vecs = 5)
* Change number of queues from 4 to 6.
  (num_io_queues = 6, max_num_io_queues = 8, msix_vecs = 5)
* The driver will reset due to failure of check_for_rx_interrupt_queue()

Fix:
This can be easily fixed by always using max_num_io_queues to init the
msix_vecs, since this number won't change as opposed to num_io_queues.

Fixes: 4d19266022ec ("net: ena: multiple queue creation related cleanups")
Signed-off-by: Sameeh Jubran <sameehj@amazon.com>
Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index e91271866ad8..597f2498a152 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -1346,7 +1346,7 @@ static int ena_enable_msix(struct ena_adapter *adapter)
 	}
 
 	/* Reserved the max msix vectors we might need */
-	msix_vecs = ENA_MAX_MSIX_VEC(adapter->num_io_queues);
+	msix_vecs = ENA_MAX_MSIX_VEC(adapter->max_num_io_queues);
 	netif_dbg(adapter, probe, adapter->netdev,
 		  "trying to enable MSI-X, vectors %d\n", msix_vecs);
 
-- 
2.20.1


From 4c79a7b2427271cd5966efbd32f3614c50e699ed Mon Sep 17 00:00:00 2001
From: Arthur Kiyanovski <akiyano@amazon.com>
Date: Tue, 17 Mar 2020 09:06:40 +0200
Subject: [PATCH 41/56] net: ena: fix request of incorrect number of IRQ
 vectors

[ Upstream commit e02ae6ed51be3d28923bfd318ae57000f5643da5 ]

Bug:
In short the main issue is caused by the fact that the number of queues
is changed using ethtool after ena_probe() has been called and before
ena_up() was executed. Here is the full scenario in detail:

* ena_probe() is called when the driver is loaded, the driver is not up
  yet at the end of ena_probe().
* The number of queues is changed -> io_queue_count is changed as well -
  ena_up() is not called since the "dev_was_up" boolean in
  ena_update_queue_count() is false.
* ena_up() is called by the kernel (it's called asynchronously some
  time after ena_probe()). ena_setup_io_intr() is called by ena_up() and
  it uses io_queue_count to get the suitable irq lines for each msix
  vector. The function ena_request_io_irq() is called right after that
  and it uses msix_vecs - This value only changes during ena_probe() and
  ena_restore() - to request the irq vectors. This results in "Failed to
  request I/O IRQ" error for i > io_queue_count.

Numeric example:
* After ena_probe() io_queue_count = 8, msix_vecs = 9.
* The number of queues changes to 4 -> io_queue_count = 4, msix_vecs = 9.
* ena_up() is executed for the first time:
  ** ena_setup_io_intr() inits the vectors only up to io_queue_count.
  ** ena_request_io_irq() calls request_irq() and fails for i = 5.

How to reproduce:
simply run the following commands:
    sudo rmmod ena && sudo insmod ena.ko;
    sudo ethtool -L eth1 combined 3;

Fix:
Use ENA_MAX_MSIX_VEC(adapter->num_io_queues + adapter->xdp_num_queues)
instead of adapter->msix_vecs. We need to take XDP queues into
consideration as they need to have msix vectors assigned to them as well.
Note that the XDP cannot be attached before the driver is up and running
but in XDP mode the issue might occur when the number of queues changes
right after a reset trigger.
The ENA_MAX_MSIX_VEC simply adds one to the argument since the first msix
vector is reserved for management queue.

Fixes: 1738cd3ed342 ("net: ena: Add a driver for Amazon Elastic Network Adapters (ENA)")
Signed-off-by: Sameeh Jubran <sameehj@amazon.com>
Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 597f2498a152..91d4f8c91263 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -1444,6 +1444,7 @@ static int ena_request_mgmnt_irq(struct ena_adapter *adapter)
 
 static int ena_request_io_irq(struct ena_adapter *adapter)
 {
+	u32 io_queue_count = adapter->num_io_queues;
 	unsigned long flags = 0;
 	struct ena_irq *irq;
 	int rc = 0, i, k;
@@ -1454,7 +1455,7 @@ static int ena_request_io_irq(struct ena_adapter *adapter)
 		return -EINVAL;
 	}
 
-	for (i = ENA_IO_IRQ_FIRST_IDX; i < adapter->msix_vecs; i++) {
+	for (i = ENA_IO_IRQ_FIRST_IDX; i < ENA_MAX_MSIX_VEC(io_queue_count); i++) {
 		irq = &adapter->irq_tbl[i];
 		rc = request_irq(irq->vector, irq->handler, flags, irq->name,
 				 irq->data);
@@ -1495,6 +1496,7 @@ static void ena_free_mgmnt_irq(struct ena_adapter *adapter)
 
 static void ena_free_io_irq(struct ena_adapter *adapter)
 {
+	u32 io_queue_count = adapter->num_io_queues;
 	struct ena_irq *irq;
 	int i;
 
@@ -1505,7 +1507,7 @@ static void ena_free_io_irq(struct ena_adapter *adapter)
 	}
 #endif /* CONFIG_RFS_ACCEL */
 
-	for (i = ENA_IO_IRQ_FIRST_IDX; i < adapter->msix_vecs; i++) {
+	for (i = ENA_IO_IRQ_FIRST_IDX; i < ENA_MAX_MSIX_VEC(io_queue_count); i++) {
 		irq = &adapter->irq_tbl[i];
 		irq_set_affinity_hint(irq->vector, NULL);
 		free_irq(irq->vector, irq->data);
@@ -1520,12 +1522,13 @@ static void ena_disable_msix(struct ena_adapter *adapter)
 
 static void ena_disable_io_intr_sync(struct ena_adapter *adapter)
 {
+	u32 io_queue_count = adapter->num_io_queues;
 	int i;
 
 	if (!netif_running(adapter->netdev))
 		return;
 
-	for (i = ENA_IO_IRQ_FIRST_IDX; i < adapter->msix_vecs; i++)
+	for (i = ENA_IO_IRQ_FIRST_IDX; i < ENA_MAX_MSIX_VEC(io_queue_count); i++)
 		synchronize_irq(adapter->irq_tbl[i].vector);
 }
 
-- 
2.20.1


From d2abc1b0c7be119d89b60d8bb6939ed39468c0ef Mon Sep 17 00:00:00 2001
From: Arthur Kiyanovski <akiyano@amazon.com>
Date: Tue, 17 Mar 2020 09:06:41 +0200
Subject: [PATCH 42/56] net: ena: avoid memory access violation by validating
 req_id properly

[ Upstream commit 30623e1ed116bcd1785217d0a98eec643687e091 ]

Rx req_id is an index in struct ena_eth_io_rx_cdesc_base.
The driver should validate that the Rx req_id it received from
the device is in range [0, ring_size -1].  Failure to do so could
yield to potential memory access violoation.
The validation was mistakenly done when refilling
the Rx submission queue and not in Rx completion queue.

Fixes: ad974baef2a1 ("net: ena: add support for out of order rx buffers refill")
Signed-off-by: Noam Dagan <ndagan@amazon.com>
Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 91d4f8c91263..ba832e49a458 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -532,13 +532,9 @@ static int ena_refill_rx_bufs(struct ena_ring *rx_ring, u32 num)
 		struct ena_rx_buffer *rx_info;
 
 		req_id = rx_ring->free_ids[next_to_use];
-		rc = validate_rx_req_id(rx_ring, req_id);
-		if (unlikely(rc < 0))
-			break;
 
 		rx_info = &rx_ring->rx_buffer_info[req_id];
 
-
 		rc = ena_alloc_rx_page(rx_ring, rx_info,
 				       GFP_ATOMIC | __GFP_COMP);
 		if (unlikely(rc < 0)) {
@@ -868,9 +864,15 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring,
 	struct ena_rx_buffer *rx_info;
 	u16 len, req_id, buf = 0;
 	void *va;
+	int rc;
 
 	len = ena_bufs[buf].len;
 	req_id = ena_bufs[buf].req_id;
+
+	rc = validate_rx_req_id(rx_ring, req_id);
+	if (unlikely(rc < 0))
+		return NULL;
+
 	rx_info = &rx_ring->rx_buffer_info[req_id];
 
 	if (unlikely(!rx_info->page)) {
@@ -943,6 +945,11 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring,
 		buf++;
 		len = ena_bufs[buf].len;
 		req_id = ena_bufs[buf].req_id;
+
+		rc = validate_rx_req_id(rx_ring, req_id);
+		if (unlikely(rc < 0))
+			return NULL;
+
 		rx_info = &rx_ring->rx_buffer_info[req_id];
 	} while (1);
 
-- 
2.20.1


From 8373d4fa2c43b712a272f23589e183077fb17028 Mon Sep 17 00:00:00 2001
From: Arthur Kiyanovski <akiyano@amazon.com>
Date: Tue, 17 Mar 2020 09:06:42 +0200
Subject: [PATCH 43/56] net: ena: fix continuous keep-alive resets

[ Upstream commit dfdde1345bc124816f0fd42fa91b8748051e758e ]

last_keep_alive_jiffies is updated in probe and when a keep-alive
event is received.  In case the driver times-out on a keep-alive event,
it has high chances of continuously timing-out on keep-alive events.
This is because when the driver recovers from the keep-alive-timeout reset
the value of last_keep_alive_jiffies is very old, and if a keep-alive
event is not received before the next timer expires, the value of
last_keep_alive_jiffies will cause another keep-alive-timeout reset
and so forth in a loop.

Solution:
Update last_keep_alive_jiffies whenever the device is restored after
reset.

Fixes: 1738cd3ed342 ("net: ena: Add a driver for Amazon Elastic Network Adapters (ENA)")
Signed-off-by: Noam Dagan <ndagan@amazon.com>
Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index ba832e49a458..7646f98f6a64 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -2832,6 +2832,7 @@ static int ena_restore_device(struct ena_adapter *adapter)
 		netif_carrier_on(adapter->netdev);
 
 	mod_timer(&adapter->timer_service, round_jiffies(jiffies + HZ));
+	adapter->last_keep_alive_jiffies = jiffies;
 	dev_err(&pdev->dev,
 		"Device reset completed successfully, Driver info: %s\n",
 		version);
-- 
2.20.1


From c95182aa79da551db7e1690de702c6f04b3bb9b8 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Fri, 13 Mar 2020 13:39:36 +0200
Subject: [PATCH 44/56] net: ip_gre: Separate ERSPAN newlink / changelink
 callbacks

[ Upstream commit e1f8f78ffe9854308b9e12a73ebe4e909074fc33 ]

ERSPAN shares most of the code path with GRE and gretap code. While that
helps keep the code compact, it is also error prone. Currently a broken
userspace can turn a gretap tunnel into a de facto ERSPAN one by passing
IFLA_GRE_ERSPAN_VER. There has been a similar issue in ip6gretap in the
past.

To prevent these problems in future, split the newlink and changelink code
paths. Split the ERSPAN code out of ipgre_netlink_parms() into a new
function erspan_netlink_parms(). Extract a piece of common logic from
ipgre_newlink() and ipgre_changelink() into ipgre_newlink_encap_setup().
Add erspan_newlink() and erspan_changelink().

Fixes: 84e54fe0a5ea ("gre: introduce native tunnel support for ERSPAN")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_gre.c | 103 ++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 85 insertions(+), 18 deletions(-)

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 8274f98c511c..7765c65fc7d2 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1153,6 +1153,22 @@ static int ipgre_netlink_parms(struct net_device *dev,
 	if (data[IFLA_GRE_FWMARK])
 		*fwmark = nla_get_u32(data[IFLA_GRE_FWMARK]);
 
+	return 0;
+}
+
+static int erspan_netlink_parms(struct net_device *dev,
+				struct nlattr *data[],
+				struct nlattr *tb[],
+				struct ip_tunnel_parm *parms,
+				__u32 *fwmark)
+{
+	struct ip_tunnel *t = netdev_priv(dev);
+	int err;
+
+	err = ipgre_netlink_parms(dev, data, tb, parms, fwmark);
+	if (err)
+		return err;
+
 	if (data[IFLA_GRE_ERSPAN_VER]) {
 		t->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]);
 
@@ -1276,45 +1292,70 @@ static void ipgre_tap_setup(struct net_device *dev)
 	ip_tunnel_setup(dev, gre_tap_net_id);
 }
 
-static int ipgre_newlink(struct net *src_net, struct net_device *dev,
-			 struct nlattr *tb[], struct nlattr *data[],
-			 struct netlink_ext_ack *extack)
+static int
+ipgre_newlink_encap_setup(struct net_device *dev, struct nlattr *data[])
 {
-	struct ip_tunnel_parm p;
 	struct ip_tunnel_encap ipencap;
-	__u32 fwmark = 0;
-	int err;
 
 	if (ipgre_netlink_encap_parms(data, &ipencap)) {
 		struct ip_tunnel *t = netdev_priv(dev);
-		err = ip_tunnel_encap_setup(t, &ipencap);
+		int err = ip_tunnel_encap_setup(t, &ipencap);
 
 		if (err < 0)
 			return err;
 	}
 
+	return 0;
+}
+
+static int ipgre_newlink(struct net *src_net, struct net_device *dev,
+			 struct nlattr *tb[], struct nlattr *data[],
+			 struct netlink_ext_ack *extack)
+{
+	struct ip_tunnel_parm p;
+	__u32 fwmark = 0;
+	int err;
+
+	err = ipgre_newlink_encap_setup(dev, data);
+	if (err)
+		return err;
+
 	err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark);
 	if (err < 0)
 		return err;
 	return ip_tunnel_newlink(dev, tb, &p, fwmark);
 }
 
+static int erspan_newlink(struct net *src_net, struct net_device *dev,
+			  struct nlattr *tb[], struct nlattr *data[],
+			  struct netlink_ext_ack *extack)
+{
+	struct ip_tunnel_parm p;
+	__u32 fwmark = 0;
+	int err;
+
+	err = ipgre_newlink_encap_setup(dev, data);
+	if (err)
+		return err;
+
+	err = erspan_netlink_parms(dev, data, tb, &p, &fwmark);
+	if (err)
+		return err;
+	return ip_tunnel_newlink(dev, tb, &p, fwmark);
+}
+
 static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[],
 			    struct nlattr *data[],
 			    struct netlink_ext_ack *extack)
 {
 	struct ip_tunnel *t = netdev_priv(dev);
-	struct ip_tunnel_encap ipencap;
 	__u32 fwmark = t->fwmark;
 	struct ip_tunnel_parm p;
 	int err;
 
-	if (ipgre_netlink_encap_parms(data, &ipencap)) {
-		err = ip_tunnel_encap_setup(t, &ipencap);
-
-		if (err < 0)
-			return err;
-	}
+	err = ipgre_newlink_encap_setup(dev, data);
+	if (err)
+		return err;
 
 	err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark);
 	if (err < 0)
@@ -1327,8 +1368,34 @@ static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[],
 	t->parms.i_flags = p.i_flags;
 	t->parms.o_flags = p.o_flags;
 
-	if (strcmp(dev->rtnl_link_ops->kind, "erspan"))
-		ipgre_link_update(dev, !tb[IFLA_MTU]);
+	ipgre_link_update(dev, !tb[IFLA_MTU]);
+
+	return 0;
+}
+
+static int erspan_changelink(struct net_device *dev, struct nlattr *tb[],
+			     struct nlattr *data[],
+			     struct netlink_ext_ack *extack)
+{
+	struct ip_tunnel *t = netdev_priv(dev);
+	__u32 fwmark = t->fwmark;
+	struct ip_tunnel_parm p;
+	int err;
+
+	err = ipgre_newlink_encap_setup(dev, data);
+	if (err)
+		return err;
+
+	err = erspan_netlink_parms(dev, data, tb, &p, &fwmark);
+	if (err < 0)
+		return err;
+
+	err = ip_tunnel_changelink(dev, tb, &p, fwmark);
+	if (err < 0)
+		return err;
+
+	t->parms.i_flags = p.i_flags;
+	t->parms.o_flags = p.o_flags;
 
 	return 0;
 }
@@ -1519,8 +1586,8 @@ static struct rtnl_link_ops erspan_link_ops __read_mostly = {
 	.priv_size	= sizeof(struct ip_tunnel),
 	.setup		= erspan_setup,
 	.validate	= erspan_validate,
-	.newlink	= ipgre_newlink,
-	.changelink	= ipgre_changelink,
+	.newlink	= erspan_newlink,
+	.changelink	= erspan_changelink,
 	.dellink	= ip_tunnel_dellink,
 	.get_size	= ipgre_get_size,
 	.fill_info	= ipgre_fill_info,
-- 
2.20.1


From c5d026485b90656f2f0978766760a2b0961dccf8 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 16 Mar 2020 19:53:00 +0200
Subject: [PATCH 45/56] net: ip_gre: Accept IFLA_INFO_DATA-less configuration

[ Upstream commit 32ca98feab8c9076c89c0697c5a85e46fece809d ]

The fix referenced below causes a crash when an ERSPAN tunnel is created
without passing IFLA_INFO_DATA. Fix by validating passed-in data in the
same way as ipgre does.

Fixes: e1f8f78ffe98 ("net: ip_gre: Separate ERSPAN newlink / changelink callbacks")
Reported-by: syzbot+1b4ebf4dae4e510dd219@syzkaller.appspotmail.com
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_gre.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 7765c65fc7d2..029b24eeafba 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1168,6 +1168,8 @@ static int erspan_netlink_parms(struct net_device *dev,
 	err = ipgre_netlink_parms(dev, data, tb, parms, fwmark);
 	if (err)
 		return err;
+	if (!data)
+		return 0;
 
 	if (data[IFLA_GRE_ERSPAN_VER]) {
 		t->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]);
-- 
2.20.1


From cb545f5d9248f065379cc8a8f8779986df99f6cb Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Fri, 13 Mar 2020 06:50:14 +0000
Subject: [PATCH 46/56] hsr: use rcu_read_lock() in
 hsr_get_node_{list/status}()

[ Upstream commit 173756b86803655d70af7732079b3aa935e6ab68 ]

hsr_get_node_{list/status}() are not under rtnl_lock() because
they are callback functions of generic netlink.
But they use __dev_get_by_index() without rtnl_lock().
So, it would use unsafe data.
In order to fix it, rcu_read_lock() and dev_get_by_index_rcu()
are used instead of __dev_get_by_index().

Fixes: f421436a591d ("net/hsr: Add support for the High-availability Seamless Redundancy protocol (HSRv0)")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/hsr/hsr_framereg.c |  9 ++-------
 net/hsr/hsr_netlink.c  | 39 +++++++++++++++++++++------------------
 2 files changed, 23 insertions(+), 25 deletions(-)

diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c
index 27dc65d7de67..002f341f3564 100644
--- a/net/hsr/hsr_framereg.c
+++ b/net/hsr/hsr_framereg.c
@@ -482,12 +482,9 @@ int hsr_get_node_data(struct hsr_priv *hsr,
 	struct hsr_port *port;
 	unsigned long tdiff;
 
-	rcu_read_lock();
 	node = find_node_by_addr_A(&hsr->node_db, addr);
-	if (!node) {
-		rcu_read_unlock();
-		return -ENOENT;	/* No such entry */
-	}
+	if (!node)
+		return -ENOENT;
 
 	ether_addr_copy(addr_b, node->macaddress_B);
 
@@ -522,7 +519,5 @@ int hsr_get_node_data(struct hsr_priv *hsr,
 		*addr_b_ifindex = -1;
 	}
 
-	rcu_read_unlock();
-
 	return 0;
 }
diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c
index 8dc0547f01d0..d6760df2ad1f 100644
--- a/net/hsr/hsr_netlink.c
+++ b/net/hsr/hsr_netlink.c
@@ -251,15 +251,16 @@ static int hsr_get_node_status(struct sk_buff *skb_in, struct genl_info *info)
 	if (!na)
 		goto invalid;
 
-	hsr_dev = __dev_get_by_index(genl_info_net(info),
-				     nla_get_u32(info->attrs[HSR_A_IFINDEX]));
+	rcu_read_lock();
+	hsr_dev = dev_get_by_index_rcu(genl_info_net(info),
+				       nla_get_u32(info->attrs[HSR_A_IFINDEX]));
 	if (!hsr_dev)
-		goto invalid;
+		goto rcu_unlock;
 	if (!is_hsr_master(hsr_dev))
-		goto invalid;
+		goto rcu_unlock;
 
 	/* Send reply */
-	skb_out = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	skb_out = genlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC);
 	if (!skb_out) {
 		res = -ENOMEM;
 		goto fail;
@@ -313,12 +314,10 @@ static int hsr_get_node_status(struct sk_buff *skb_in, struct genl_info *info)
 	res = nla_put_u16(skb_out, HSR_A_IF1_SEQ, hsr_node_if1_seq);
 	if (res < 0)
 		goto nla_put_failure;
-	rcu_read_lock();
 	port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_A);
 	if (port)
 		res = nla_put_u32(skb_out, HSR_A_IF1_IFINDEX,
 				  port->dev->ifindex);
-	rcu_read_unlock();
 	if (res < 0)
 		goto nla_put_failure;
 
@@ -328,20 +327,22 @@ static int hsr_get_node_status(struct sk_buff *skb_in, struct genl_info *info)
 	res = nla_put_u16(skb_out, HSR_A_IF2_SEQ, hsr_node_if2_seq);
 	if (res < 0)
 		goto nla_put_failure;
-	rcu_read_lock();
 	port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B);
 	if (port)
 		res = nla_put_u32(skb_out, HSR_A_IF2_IFINDEX,
 				  port->dev->ifindex);
-	rcu_read_unlock();
 	if (res < 0)
 		goto nla_put_failure;
 
+	rcu_read_unlock();
+
 	genlmsg_end(skb_out, msg_head);
 	genlmsg_unicast(genl_info_net(info), skb_out, info->snd_portid);
 
 	return 0;
 
+rcu_unlock:
+	rcu_read_unlock();
 invalid:
 	netlink_ack(skb_in, nlmsg_hdr(skb_in), -EINVAL, NULL);
 	return 0;
@@ -351,6 +352,7 @@ static int hsr_get_node_status(struct sk_buff *skb_in, struct genl_info *info)
 	/* Fall through */
 
 fail:
+	rcu_read_unlock();
 	return res;
 }
 
@@ -377,15 +379,16 @@ static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info)
 	if (!na)
 		goto invalid;
 
-	hsr_dev = __dev_get_by_index(genl_info_net(info),
-				     nla_get_u32(info->attrs[HSR_A_IFINDEX]));
+	rcu_read_lock();
+	hsr_dev = dev_get_by_index_rcu(genl_info_net(info),
+				       nla_get_u32(info->attrs[HSR_A_IFINDEX]));
 	if (!hsr_dev)
-		goto invalid;
+		goto rcu_unlock;
 	if (!is_hsr_master(hsr_dev))
-		goto invalid;
+		goto rcu_unlock;
 
 	/* Send reply */
-	skb_out = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	skb_out = genlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC);
 	if (!skb_out) {
 		res = -ENOMEM;
 		goto fail;
@@ -405,14 +408,11 @@ static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info)
 
 	hsr = netdev_priv(hsr_dev);
 
-	rcu_read_lock();
 	pos = hsr_get_next_node(hsr, NULL, addr);
 	while (pos) {
 		res = nla_put(skb_out, HSR_A_NODE_ADDR, ETH_ALEN, addr);
-		if (res < 0) {
-			rcu_read_unlock();
+		if (res < 0)
 			goto nla_put_failure;
-		}
 		pos = hsr_get_next_node(hsr, pos, addr);
 	}
 	rcu_read_unlock();
@@ -422,6 +422,8 @@ static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info)
 
 	return 0;
 
+rcu_unlock:
+	rcu_read_unlock();
 invalid:
 	netlink_ack(skb_in, nlmsg_hdr(skb_in), -EINVAL, NULL);
 	return 0;
@@ -431,6 +433,7 @@ static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info)
 	/* Fall through */
 
 fail:
+	rcu_read_unlock();
 	return res;
 }
 
-- 
2.20.1


From 62bebb8496caa083c243e7689bbf9e70a94e25d7 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Fri, 13 Mar 2020 06:50:24 +0000
Subject: [PATCH 47/56] hsr: add restart routine into hsr_get_node_list()

[ Upstream commit ca19c70f5225771c05bcdcb832b4eb84d7271c5e ]

The hsr_get_node_list() is to send node addresses to the userspace.
If there are so many nodes, it could fail because of buffer size.
In order to avoid this failure, the restart routine is added.

Fixes: f421436a591d ("net/hsr: Add support for the High-availability Seamless Redundancy protocol (HSRv0)")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/hsr/hsr_netlink.c | 38 ++++++++++++++++++++++++--------------
 1 file changed, 24 insertions(+), 14 deletions(-)

diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c
index d6760df2ad1f..726bfe923999 100644
--- a/net/hsr/hsr_netlink.c
+++ b/net/hsr/hsr_netlink.c
@@ -360,16 +360,14 @@ static int hsr_get_node_status(struct sk_buff *skb_in, struct genl_info *info)
  */
 static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info)
 {
-	/* For receiving */
-	struct nlattr *na;
+	unsigned char addr[ETH_ALEN];
 	struct net_device *hsr_dev;
-
-	/* For sending */
 	struct sk_buff *skb_out;
-	void *msg_head;
 	struct hsr_priv *hsr;
-	void *pos;
-	unsigned char addr[ETH_ALEN];
+	bool restart = false;
+	struct nlattr *na;
+	void *pos = NULL;
+	void *msg_head;
 	int res;
 
 	if (!info)
@@ -387,8 +385,9 @@ static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info)
 	if (!is_hsr_master(hsr_dev))
 		goto rcu_unlock;
 
+restart:
 	/* Send reply */
-	skb_out = genlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC);
+	skb_out = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_ATOMIC);
 	if (!skb_out) {
 		res = -ENOMEM;
 		goto fail;
@@ -402,17 +401,28 @@ static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info)
 		goto nla_put_failure;
 	}
 
-	res = nla_put_u32(skb_out, HSR_A_IFINDEX, hsr_dev->ifindex);
-	if (res < 0)
-		goto nla_put_failure;
+	if (!restart) {
+		res = nla_put_u32(skb_out, HSR_A_IFINDEX, hsr_dev->ifindex);
+		if (res < 0)
+			goto nla_put_failure;
+	}
 
 	hsr = netdev_priv(hsr_dev);
 
-	pos = hsr_get_next_node(hsr, NULL, addr);
+	if (!pos)
+		pos = hsr_get_next_node(hsr, NULL, addr);
 	while (pos) {
 		res = nla_put(skb_out, HSR_A_NODE_ADDR, ETH_ALEN, addr);
-		if (res < 0)
+		if (res < 0) {
+			if (res == -EMSGSIZE) {
+				genlmsg_end(skb_out, msg_head);
+				genlmsg_unicast(genl_info_net(info), skb_out,
+						info->snd_portid);
+				restart = true;
+				goto restart;
+			}
 			goto nla_put_failure;
+		}
 		pos = hsr_get_next_node(hsr, pos, addr);
 	}
 	rcu_read_unlock();
@@ -429,7 +439,7 @@ static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info)
 	return 0;
 
 nla_put_failure:
-	kfree_skb(skb_out);
+	nlmsg_free(skb_out);
 	/* Fall through */
 
 fail:
-- 
2.20.1


From 7614b12905d6070997f3eb6b7f29fa2727c69286 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Fri, 13 Mar 2020 06:50:33 +0000
Subject: [PATCH 48/56] hsr: set .netnsok flag

[ Upstream commit 09e91dbea0aa32be02d8877bd50490813de56b9a ]

The hsr module has been supporting the list and status command.
(HSR_C_GET_NODE_LIST and HSR_C_GET_NODE_STATUS)
These commands send node information to the user-space via generic netlink.
But, in the non-init_net namespace, these commands are not allowed
because .netnsok flag is false.
So, there is no way to get node information in the non-init_net namespace.

Fixes: f421436a591d ("net/hsr: Add support for the High-availability Seamless Redundancy protocol (HSRv0)")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/hsr/hsr_netlink.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c
index 726bfe923999..fae21c863b1f 100644
--- a/net/hsr/hsr_netlink.c
+++ b/net/hsr/hsr_netlink.c
@@ -470,6 +470,7 @@ static struct genl_family hsr_genl_family __ro_after_init = {
 	.version = 1,
 	.maxattr = HSR_A_MAX,
 	.policy = hsr_genl_policy,
+	.netnsok = true,
 	.module = THIS_MODULE,
 	.ops = hsr_ops,
 	.n_ops = ARRAY_SIZE(hsr_ops),
-- 
2.20.1


From 28757a236aeb8ca8dc38d995bc33f5cc5006acb6 Mon Sep 17 00:00:00 2001
From: Hamdan Igbaria <hamdani@mellanox.com>
Date: Mon, 24 Feb 2020 14:41:29 +0200
Subject: [PATCH 49/56] net/mlx5: DR, Fix postsend actions write length

[ Upstream commit 692b0399a22530b2de8490bea75a7d20d59391d0 ]

Fix the send info write length to be (actions x action) size in bytes.

Fixes: 297cccebdc5a ("net/mlx5: DR, Expose an internal API to issue RDMA operations")
Signed-off-by: Hamdan Igbaria <hamdani@mellanox.com>
Reviewed-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c | 1 -
 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c   | 3 ++-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
index 004c56c2fc0c..b2dfa2b5366f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
@@ -930,7 +930,6 @@ static int dr_actions_l2_rewrite(struct mlx5dr_domain *dmn,
 
 	action->rewrite.data = (void *)ops;
 	action->rewrite.num_of_actions = i;
-	action->rewrite.chunk->byte_size = i * sizeof(*ops);
 
 	ret = mlx5dr_send_postsend_action(dmn, action);
 	if (ret) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
index c7f10d4f8f8d..095ec7b1399d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
@@ -558,7 +558,8 @@ int mlx5dr_send_postsend_action(struct mlx5dr_domain *dmn,
 	int ret;
 
 	send_info.write.addr = (uintptr_t)action->rewrite.data;
-	send_info.write.length = action->rewrite.chunk->byte_size;
+	send_info.write.length = action->rewrite.num_of_actions *
+				 DR_MODIFY_ACTION_SIZE;
 	send_info.write.lkey = 0;
 	send_info.remote_addr = action->rewrite.chunk->mr_addr;
 	send_info.rkey = action->rewrite.chunk->rkey;
-- 
2.20.1


From 4d480529d531811010a8becec4c5a029daf2b354 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Mon, 9 Mar 2020 09:44:18 +0200
Subject: [PATCH 50/56] net/mlx5e: Enhance ICOSQ WQE info fields

[ Upstream commit 1de0306c3a05d305e45b1f1fabe2f4e94222eb6b ]

Add number of WQEBBs (WQE's Basic Block) to WQE info struct. Set the
number of WQEBBs on WQE post, and increment the consumer counter (cc)
on completion.

In case of error completions, the cc was mistakenly not incremented,
keeping a gap between cc and pc (producer counter). This failed the
recovery flow on the ICOSQ from a CQE error which timed-out waiting for
the cc and pc to meet.

Fixes: be5323c8379f ("net/mlx5e: Report and recover from CQE error on ICOSQ")
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      |  1 +
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c   | 11 +++++------
 drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c |  1 +
 3 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 9c8427698238..24e8dc9e6db5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -371,6 +371,7 @@ enum {
 
 struct mlx5e_sq_wqe_info {
 	u8  opcode;
+	u8 num_wqebbs;
 
 	/* Auxiliary data for different opcodes. */
 	union {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 1c3ab69cbd96..312d4692425b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -477,6 +477,7 @@ static inline void mlx5e_fill_icosq_frag_edge(struct mlx5e_icosq *sq,
 	/* fill sq frag edge with nops to avoid wqe wrapping two pages */
 	for (; wi < edge_wi; wi++) {
 		wi->opcode = MLX5_OPCODE_NOP;
+		wi->num_wqebbs = 1;
 		mlx5e_post_nop(wq, sq->sqn, &sq->pc);
 	}
 }
@@ -525,6 +526,7 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 	umr_wqe->uctrl.xlt_offset = cpu_to_be16(xlt_offset);
 
 	sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_UMR;
+	sq->db.ico_wqe[pi].num_wqebbs = MLX5E_UMR_WQEBBS;
 	sq->db.ico_wqe[pi].umr.rq = rq;
 	sq->pc += MLX5E_UMR_WQEBBS;
 
@@ -621,6 +623,7 @@ void mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
 
 			ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc);
 			wi = &sq->db.ico_wqe[ci];
+			sqcc += wi->num_wqebbs;
 
 			if (last_wqe && unlikely(get_cqe_opcode(cqe) != MLX5_CQE_REQ)) {
 				netdev_WARN_ONCE(cq->channel->netdev,
@@ -631,16 +634,12 @@ void mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
 				break;
 			}
 
-			if (likely(wi->opcode == MLX5_OPCODE_UMR)) {
-				sqcc += MLX5E_UMR_WQEBBS;
+			if (likely(wi->opcode == MLX5_OPCODE_UMR))
 				wi->umr.rq->mpwqe.umr_completed++;
-			} else if (likely(wi->opcode == MLX5_OPCODE_NOP)) {
-				sqcc++;
-			} else {
+			else if (unlikely(wi->opcode != MLX5_OPCODE_NOP))
 				netdev_WARN_ONCE(cq->channel->netdev,
 						 "Bad OPCODE in ICOSQ WQE info: 0x%x\n",
 						 wi->opcode);
-			}
 
 		} while (!last_wqe);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
index 257a7c9f7a14..800d34ed8a96 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
@@ -78,6 +78,7 @@ void mlx5e_trigger_irq(struct mlx5e_icosq *sq)
 	u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
 
 	sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_NOP;
+	sq->db.ico_wqe[pi].num_wqebbs = 1;
 	nopwqe = mlx5e_post_nop(wq, sq->sqn, &sq->pc);
 	mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &nopwqe->ctrl);
 }
-- 
2.20.1


From 2dbc7b1ffcaea42aa296e6e9b58e9c904eaf83d6 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Thu, 12 Mar 2020 12:35:32 +0200
Subject: [PATCH 51/56] net/mlx5e: Fix missing reset of SW metadata in Striding
 RQ reset

[ Upstream commit 39369fd536d485a99a59d8e357c0d4d3ce19a3b8 ]

When resetting the RQ (moving RQ state from RST to RDY), the driver
resets the WQ's SW metadata.
In striding RQ mode, we maintain a field that reflects the actual
expected WQ head (including in progress WQEs posted to the ICOSQ).
It was mistakenly not reset together with the WQ. Fix this here.

Fixes: 8276ea1353a4 ("net/mlx5e: Report and recover from CQE with error on RQ")
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index a226277b0980..f07b1399744e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -181,10 +181,12 @@ mlx5e_tx_dma_unmap(struct device *pdev, struct mlx5e_sq_dma *dma)
 
 static inline void mlx5e_rqwq_reset(struct mlx5e_rq *rq)
 {
-	if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
+	if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
 		mlx5_wq_ll_reset(&rq->mpwqe.wq);
-	else
+		rq->mpwqe.actual_wq_head = 0;
+	} else {
 		mlx5_wq_cyc_reset(&rq->wqe.wq);
+	}
 }
 
 /* SW parser related functions */
-- 
2.20.1


From 745be32558cda860ea00870e861ce59b343fa825 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Mon, 16 Mar 2020 16:53:10 +0200
Subject: [PATCH 52/56] net/mlx5e: Fix ICOSQ recovery flow with Striding RQ

[ Upstream commit e239c6d686e1c37fb2ab143162dfb57471a8643f ]

In striding RQ mode, the buffers of an RX WQE are first
prepared and posted to the HW using a UMR WQEs via the ICOSQ.
We maintain the state of these in-progress WQEs in the RQ
SW struct.

In the flow of ICOSQ recovery, the corresponding RQ is not
in error state, hence:

- The buffers of the in-progress WQEs must be released
  and the RQ metadata should reflect it.
- Existing RX WQEs in the RQ should not be affected.

For this, wrap the dealloc of the in-progress WQEs in
a function, and use it in the ICOSQ recovery flow
instead of mlx5e_free_rx_descs().

Fixes: be5323c8379f ("net/mlx5e: Report and recover from CQE error on ICOSQ")
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h  |  1 +
 .../mellanox/mlx5/core/en/reporter_rx.c       |  2 +-
 .../net/ethernet/mellanox/mlx5/core/en_main.c | 31 ++++++++++++++-----
 3 files changed, 26 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 24e8dc9e6db5..55ceabf077b2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -1059,6 +1059,7 @@ int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state, int next_state);
 void mlx5e_activate_rq(struct mlx5e_rq *rq);
 void mlx5e_deactivate_rq(struct mlx5e_rq *rq);
 void mlx5e_free_rx_descs(struct mlx5e_rq *rq);
+void mlx5e_free_rx_in_progress_descs(struct mlx5e_rq *rq);
 void mlx5e_activate_icosq(struct mlx5e_icosq *icosq);
 void mlx5e_deactivate_icosq(struct mlx5e_icosq *icosq);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
index 6c72b592315b..a01e2de2488f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
@@ -90,7 +90,7 @@ static int mlx5e_rx_reporter_err_icosq_cqe_recover(void *ctx)
 		goto out;
 
 	mlx5e_reset_icosq_cc_pc(icosq);
-	mlx5e_free_rx_descs(rq);
+	mlx5e_free_rx_in_progress_descs(rq);
 	clear_bit(MLX5E_SQ_STATE_RECOVERING, &icosq->state);
 	mlx5e_activate_icosq(icosq);
 	mlx5e_activate_rq(rq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 5d9cfac67236..67fe002dfade 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -822,6 +822,29 @@ int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time)
 	return -ETIMEDOUT;
 }
 
+void mlx5e_free_rx_in_progress_descs(struct mlx5e_rq *rq)
+{
+	struct mlx5_wq_ll *wq;
+	u16 head;
+	int i;
+
+	if (rq->wq_type != MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
+		return;
+
+	wq = &rq->mpwqe.wq;
+	head = wq->head;
+
+	/* Outstanding UMR WQEs (in progress) start at wq->head */
+	for (i = 0; i < rq->mpwqe.umr_in_progress; i++) {
+		rq->dealloc_wqe(rq, head);
+		head = mlx5_wq_ll_get_wqe_next_ix(wq, head);
+	}
+
+	rq->mpwqe.actual_wq_head = wq->head;
+	rq->mpwqe.umr_in_progress = 0;
+	rq->mpwqe.umr_completed = 0;
+}
+
 void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
 {
 	__be16 wqe_ix_be;
@@ -829,14 +852,8 @@ void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
 
 	if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
 		struct mlx5_wq_ll *wq = &rq->mpwqe.wq;
-		u16 head = wq->head;
-		int i;
 
-		/* Outstanding UMR WQEs (in progress) start at wq->head */
-		for (i = 0; i < rq->mpwqe.umr_in_progress; i++) {
-			rq->dealloc_wqe(rq, head);
-			head = mlx5_wq_ll_get_wqe_next_ix(wq, head);
-		}
+		mlx5e_free_rx_in_progress_descs(rq);
 
 		while (!mlx5_wq_ll_is_empty(wq)) {
 			struct mlx5e_rx_wqe_ll *wqe;
-- 
2.20.1


From c1959c3bbffb273194f981d291700fa12e8eb70e Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Thu, 19 Mar 2020 13:25:17 +0200
Subject: [PATCH 53/56] net/mlx5e: Do not recover from a non-fatal syndrome

[ Upstream commit 187a9830c921d92c4a9a8e2921ecc4b35a97532c ]

For non-fatal syndromes like LOCAL_LENGTH_ERR, recovery shouldn't be
triggered. In these scenarios, the RQ is not actually in ERR state.
This misleads the recovery flow which assumes that the RQ is really in
error state and no more completions arrive, causing crashes on bad page
state.

Fixes: 8276ea1353a4 ("net/mlx5e: Report and recover from CQE with error on RQ")
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/health.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
index d3693fa547ac..e54f70d9af22 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
@@ -10,8 +10,7 @@
 
 static inline bool cqe_syndrome_needs_recover(u8 syndrome)
 {
-	return syndrome == MLX5_CQE_SYNDROME_LOCAL_LENGTH_ERR ||
-	       syndrome == MLX5_CQE_SYNDROME_LOCAL_QP_OP_ERR ||
+	return syndrome == MLX5_CQE_SYNDROME_LOCAL_QP_OP_ERR ||
 	       syndrome == MLX5_CQE_SYNDROME_LOCAL_PROT_ERR ||
 	       syndrome == MLX5_CQE_SYNDROME_WR_FLUSH_ERR;
 }
-- 
2.20.1


From 8919ef3da6f2e1e7c33e91d0eb5dd0af99903957 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Mon, 16 Mar 2020 09:31:03 +0200
Subject: [PATCH 54/56] net/mlx5_core: Set IB capability mask1 to fix ib_srpt
 connection failure

[ Upstream commit 306f354c67397b3138300cde875c5cab45b857f7 ]

The cap_mask1 isn't protected by field_select and not listed among RW
fields, but it is required to be written to properly initialize ports
in IB virtualization mode.

Link: https://lore.kernel.org/linux-rdma/88bab94d2fd72f3145835b4518bc63dda587add6.camel@redhat.com
Fixes: ab118da4c10a ("net/mlx5: Don't write read-only fields in MODIFY_HCA_VPORT_CONTEXT command")
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/vport.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index 1faac31f74d0..23f879da9104 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -1071,6 +1071,9 @@ int mlx5_core_modify_hca_vport_context(struct mlx5_core_dev *dev,
 		MLX5_SET64(hca_vport_context, ctx, port_guid, req->port_guid);
 	if (req->field_select & MLX5_HCA_VPORT_SEL_NODE_GUID)
 		MLX5_SET64(hca_vport_context, ctx, node_guid, req->node_guid);
+	MLX5_SET(hca_vport_context, ctx, cap_mask1, req->cap_mask1);
+	MLX5_SET(hca_vport_context, ctx, cap_mask1_field_select,
+		 req->cap_mask1_perm);
 	err = mlx5_cmd_exec(dev, in, in_sz, out, sizeof(out));
 ex:
 	kfree(in);
-- 
2.20.1


From 9660c0b8cac85d3c66e81fc0002cb56a1815d6d3 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Thu, 20 Feb 2020 13:40:24 +0200
Subject: [PATCH 55/56] net/mlx5e: kTLS, Fix TCP seq off-by-1 issue in TX
 resync flow

[ Upstream commit 56917766def72f5afdf4235adb91b6897ff26d9d ]

We have an off-by-1 issue in the TCP seq comparison.
The last sequence number that belongs to the TCP packet's payload
is not "start_seq + len", but one byte before it.
Fix it so the 'ends_before' is evaluated properly.

This fixes a bug that results in error completions in the
kTLS HW offload flows.

Fixes: ffbd9ca94e2e ("net/mlx5e: kTLS, Fix corner-case checks in TX resync flow")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
index f260dd96873b..52a56622034a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
@@ -218,7 +218,7 @@ tx_sync_info_get(struct mlx5e_ktls_offload_context_tx *priv_tx,
 	 *    this packet was already acknowledged and its record info
 	 *    was released.
 	 */
-	ends_before = before(tcp_seq + datalen, tls_record_start_seq(record));
+	ends_before = before(tcp_seq + datalen - 1, tls_record_start_seq(record));
 
 	if (unlikely(tls_record_is_start_marker(record))) {
 		ret = ends_before ? MLX5E_KTLS_SYNC_SKIP_NO_DATA : MLX5E_KTLS_SYNC_FAIL;
-- 
2.20.1


From ded5b6ffa61827d9f9b76449a8912e4393dbe262 Mon Sep 17 00:00:00 2001
From: Sebastian Hense <sebastian.hense1@ibm.com>
Date: Thu, 20 Feb 2020 08:11:36 +0100
Subject: [PATCH 56/56] net/mlx5e: Fix endianness handling in pedit mask

[ Upstream commit 404402abd5f90aa90a134eb9604b1750c1941529 ]

The mask value is provided as 64 bit and has to be casted in
either 32 or 16 bit. On big endian systems the wrong half was
casted which resulted in an all zero mask.

Fixes: 2b64beba0251 ("net/mlx5e: Support header re-write of partial fields in TC pedit offload")
Signed-off-by: Sebastian Hense <sebastian.hense1@ibm.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 7e32b9e3667c..d4bad2a444e2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2432,10 +2432,11 @@ static int offload_pedit_fields(struct pedit_headers_action *hdrs,
 			continue;
 
 		if (f->field_bsize == 32) {
-			mask_be32 = *(__be32 *)&mask;
+			mask_be32 = (__be32)mask;
 			mask = (__force unsigned long)cpu_to_le32(be32_to_cpu(mask_be32));
 		} else if (f->field_bsize == 16) {
-			mask_be16 = *(__be16 *)&mask;
+			mask_be32 = (__be32)mask;
+			mask_be16 = *(__be16 *)&mask_be32;
 			mask = (__force unsigned long)cpu_to_le16(be16_to_cpu(mask_be16));
 		}
 
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Fri, Mar 27, 2020 at 04:51:04PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v5.4
> and v5.5 -stable, respectively.

All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 105 bytes --]


Please queue up the following networking bug fixes for v5.5 and v5.6
-stable, respectively.

Thank you!

[-- Attachment #2: net_55.mbox --]
[-- Type: Application/Octet-Stream, Size: 16305 bytes --]

From 3bc1d7a301323fcc1eb4146ec99fbb6b5d68c3b0 Mon Sep 17 00:00:00 2001
From: Qian Cai <cai@lca.pw>
Date: Wed, 25 Mar 2020 18:01:00 -0400
Subject: [PATCH 1/6] ipv4: fix a RCU-list lock in fib_triestat_seq_show

[ Upstream commit fbe4e0c1b298b4665ee6915266c9d6c5b934ef4a ]

fib_triestat_seq_show() calls hlist_for_each_entry_rcu(tb, head,
tb_hlist) without rcu_read_lock() will trigger a warning,

 net/ipv4/fib_trie.c:2579 RCU-list traversed in non-reader section!!

 other info that might help us debug this:

 rcu_scheduler_active = 2, debug_locks = 1
 1 lock held by proc01/115277:
  #0: c0000014507acf00 (&p->lock){+.+.}-{3:3}, at: seq_read+0x58/0x670

 Call Trace:
  dump_stack+0xf4/0x164 (unreliable)
  lockdep_rcu_suspicious+0x140/0x164
  fib_triestat_seq_show+0x750/0x880
  seq_read+0x1a0/0x670
  proc_reg_read+0x10c/0x1b0
  __vfs_read+0x3c/0x70
  vfs_read+0xac/0x170
  ksys_read+0x7c/0x140
  system_call+0x5c/0x68

Fix it by adding a pair of rcu_read_lock/unlock() and use
cond_resched_rcu() to avoid the situation where walking of a large
number of items  may prevent scheduling for a long time.

Signed-off-by: Qian Cai <cai@lca.pw>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_trie.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 195469a13371..85a44099b7c3 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -2473,6 +2473,7 @@ static int fib_triestat_seq_show(struct seq_file *seq, void *v)
 		   " %zd bytes, size of tnode: %zd bytes.\n",
 		   LEAF_SIZE, TNODE_SIZE(0));
 
+	rcu_read_lock();
 	for (h = 0; h < FIB_TABLE_HASHSZ; h++) {
 		struct hlist_head *head = &net->ipv4.fib_table_hash[h];
 		struct fib_table *tb;
@@ -2492,7 +2493,9 @@ static int fib_triestat_seq_show(struct seq_file *seq, void *v)
 			trie_show_usage(seq, t->stats);
 #endif
 		}
+		cond_resched_rcu();
 	}
+	rcu_read_unlock();
 
 	return 0;
 }
-- 
2.20.1


From 15716b6588d692a6bc9f4a7e2a1efd0f7451353b Mon Sep 17 00:00:00 2001
From: Codrin Ciubotariu <codrin.ciubotariu@microchip.com>
Date: Tue, 31 Mar 2020 12:36:51 +0300
Subject: [PATCH 2/6] net: dsa: ksz: Select KSZ protocol tag

[ Upstream commit f772148eb757b0823fbfdc2fe592d5e06c7f19b0 ]

KSZ protocol tag is needed by the KSZ DSA drivers.

Fixes: 0b9f9dfbfab4 ("dsa: Allow tag drivers to be built as modules")
Tested-by: Cristian Birsan <cristian.birsan@microchip.com>
Signed-off-by: Codrin Ciubotariu <codrin.ciubotariu@microchip.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/microchip/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/dsa/microchip/Kconfig b/drivers/net/dsa/microchip/Kconfig
index 1d7870c6df3c..4ec6a47b7f72 100644
--- a/drivers/net/dsa/microchip/Kconfig
+++ b/drivers/net/dsa/microchip/Kconfig
@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config NET_DSA_MICROCHIP_KSZ_COMMON
+	select NET_DSA_TAG_KSZ
 	tristate
 
 menuconfig NET_DSA_MICROCHIP_KSZ9477
-- 
2.20.1


From d9e4d3f34d1f55a5e9fddf408e1209ed8f9c6de0 Mon Sep 17 00:00:00 2001
From: William Dauchy <w.dauchy@criteo.com>
Date: Fri, 27 Mar 2020 19:56:39 +0100
Subject: [PATCH 3/6] net, ip_tunnel: fix interface lookup with no key

[ Upstream commit 25629fdaff2ff509dd0b3f5ff93d70a75e79e0a1 ]

when creating a new ipip interface with no local/remote configuration,
the lookup is done with TUNNEL_NO_KEY flag, making it impossible to
match the new interface (only possible match being fallback or metada
case interface); e.g: `ip link add tunl1 type ipip dev eth0`

To fix this case, adding a flag check before the key comparison so we
permit to match an interface with no local/remote config; it also avoids
breaking possible userland tools relying on TUNNEL_NO_KEY flag and
uninitialised key.

context being on my side, I'm creating an extra ipip interface attached
to the physical one, and moving it to a dedicated namespace.

Fixes: c54419321455 ("GRE: Refactor GRE tunneling code.")
Signed-off-by: William Dauchy <w.dauchy@criteo.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_tunnel.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 74e1d964a615..cd4b84310d92 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -142,11 +142,8 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 			cand = t;
 	}
 
-	if (flags & TUNNEL_NO_KEY)
-		goto skip_key_lookup;
-
 	hlist_for_each_entry_rcu(t, head, hash_node) {
-		if (t->parms.i_key != key ||
+		if ((!(flags & TUNNEL_NO_KEY) && t->parms.i_key != key) ||
 		    t->parms.iph.saddr != 0 ||
 		    t->parms.iph.daddr != 0 ||
 		    !(t->dev->flags & IFF_UP))
@@ -158,7 +155,6 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 			cand = t;
 	}
 
-skip_key_lookup:
 	if (cand)
 		return cand;
 
-- 
2.20.1


From 18dddc1a554ad0ca33b72b016f8bd65c17f81b45 Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Thu, 26 Mar 2020 20:47:46 -0300
Subject: [PATCH 4/6] sctp: fix possibly using a bad saddr with a given dst

[ Upstream commit 582eea230536a6f104097dd46205822005d5fe3a ]

Under certain circumstances, depending on the order of addresses on the
interfaces, it could be that sctp_v[46]_get_dst() would return a dst
with a mismatched struct flowi.

For example, if when walking through the bind addresses and the first
one is not a match, it saves the dst as a fallback (added in
410f03831c07), but not the flowi. Then if the next one is also not a
match, the previous dst will be returned but with the flowi information
for the 2nd address, which is wrong.

The fix is to use a locally stored flowi that can be used for such
attempts, and copy it to the parameter only in case it is a possible
match, together with the corresponding dst entry.

The patch updates IPv6 code mostly just to be in sync. Even though the issue
is also present there, it fallback is not expected to work with IPv6.

Fixes: 410f03831c07 ("sctp: add routing output fallback")
Reported-by: Jin Meng <meng.a.jin@nokia-sbell.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Tested-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ipv6.c     | 20 ++++++++++++++------
 net/sctp/protocol.c | 28 +++++++++++++++++++---------
 2 files changed, 33 insertions(+), 15 deletions(-)

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index bc734cfaa29e..c87af430107a 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -228,7 +228,8 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 {
 	struct sctp_association *asoc = t->asoc;
 	struct dst_entry *dst = NULL;
-	struct flowi6 *fl6 = &fl->u.ip6;
+	struct flowi _fl;
+	struct flowi6 *fl6 = &_fl.u.ip6;
 	struct sctp_bind_addr *bp;
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct sctp_sockaddr_entry *laddr;
@@ -238,7 +239,7 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 	enum sctp_scope scope;
 	__u8 matchlen = 0;
 
-	memset(fl6, 0, sizeof(struct flowi6));
+	memset(&_fl, 0, sizeof(_fl));
 	fl6->daddr = daddr->v6.sin6_addr;
 	fl6->fl6_dport = daddr->v6.sin6_port;
 	fl6->flowi6_proto = IPPROTO_SCTP;
@@ -276,8 +277,11 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 	rcu_read_unlock();
 
 	dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p);
-	if (!asoc || saddr)
+	if (!asoc || saddr) {
+		t->dst = dst;
+		memcpy(fl, &_fl, sizeof(_fl));
 		goto out;
+	}
 
 	bp = &asoc->base.bind_addr;
 	scope = sctp_scope(daddr);
@@ -300,6 +304,8 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 			if ((laddr->a.sa.sa_family == AF_INET6) &&
 			    (sctp_v6_cmp_addr(&dst_saddr, &laddr->a))) {
 				rcu_read_unlock();
+				t->dst = dst;
+				memcpy(fl, &_fl, sizeof(_fl));
 				goto out;
 			}
 		}
@@ -338,6 +344,8 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 			if (!IS_ERR_OR_NULL(dst))
 				dst_release(dst);
 			dst = bdst;
+			t->dst = dst;
+			memcpy(fl, &_fl, sizeof(_fl));
 			break;
 		}
 
@@ -351,6 +359,8 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 			dst_release(dst);
 		dst = bdst;
 		matchlen = bmatchlen;
+		t->dst = dst;
+		memcpy(fl, &_fl, sizeof(_fl));
 	}
 	rcu_read_unlock();
 
@@ -359,14 +369,12 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 		struct rt6_info *rt;
 
 		rt = (struct rt6_info *)dst;
-		t->dst = dst;
 		t->dst_cookie = rt6_get_cookie(rt);
 		pr_debug("rt6_dst:%pI6/%d rt6_src:%pI6\n",
 			 &rt->rt6i_dst.addr, rt->rt6i_dst.plen,
-			 &fl6->saddr);
+			 &fl->u.ip6.saddr);
 	} else {
 		t->dst = NULL;
-
 		pr_debug("no route\n");
 	}
 }
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 78af2fcf90cc..092d1afdee0d 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -409,7 +409,8 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 {
 	struct sctp_association *asoc = t->asoc;
 	struct rtable *rt;
-	struct flowi4 *fl4 = &fl->u.ip4;
+	struct flowi _fl;
+	struct flowi4 *fl4 = &_fl.u.ip4;
 	struct sctp_bind_addr *bp;
 	struct sctp_sockaddr_entry *laddr;
 	struct dst_entry *dst = NULL;
@@ -419,7 +420,7 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 
 	if (t->dscp & SCTP_DSCP_SET_MASK)
 		tos = t->dscp & SCTP_DSCP_VAL_MASK;
-	memset(fl4, 0x0, sizeof(struct flowi4));
+	memset(&_fl, 0x0, sizeof(_fl));
 	fl4->daddr  = daddr->v4.sin_addr.s_addr;
 	fl4->fl4_dport = daddr->v4.sin_port;
 	fl4->flowi4_proto = IPPROTO_SCTP;
@@ -438,8 +439,11 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 		 &fl4->saddr);
 
 	rt = ip_route_output_key(sock_net(sk), fl4);
-	if (!IS_ERR(rt))
+	if (!IS_ERR(rt)) {
 		dst = &rt->dst;
+		t->dst = dst;
+		memcpy(fl, &_fl, sizeof(_fl));
+	}
 
 	/* If there is no association or if a source address is passed, no
 	 * more validation is required.
@@ -502,27 +506,33 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 		odev = __ip_dev_find(sock_net(sk), laddr->a.v4.sin_addr.s_addr,
 				     false);
 		if (!odev || odev->ifindex != fl4->flowi4_oif) {
-			if (!dst)
+			if (!dst) {
 				dst = &rt->dst;
-			else
+				t->dst = dst;
+				memcpy(fl, &_fl, sizeof(_fl));
+			} else {
 				dst_release(&rt->dst);
+			}
 			continue;
 		}
 
 		dst_release(dst);
 		dst = &rt->dst;
+		t->dst = dst;
+		memcpy(fl, &_fl, sizeof(_fl));
 		break;
 	}
 
 out_unlock:
 	rcu_read_unlock();
 out:
-	t->dst = dst;
-	if (dst)
+	if (dst) {
 		pr_debug("rt_dst:%pI4, rt_src:%pI4\n",
-			 &fl4->daddr, &fl4->saddr);
-	else
+			 &fl->u.ip4.daddr, &fl->u.ip4.saddr);
+	} else {
+		t->dst = NULL;
 		pr_debug("no route\n");
+	}
 }
 
 /* For v4, the source address is cached in the route entry(dst). So no need
-- 
2.20.1


From 773d32462cacf2392d85fa714d24abc2b33474ee Mon Sep 17 00:00:00 2001
From: Qiujun Huang <hqjagain@gmail.com>
Date: Fri, 27 Mar 2020 11:07:51 +0800
Subject: [PATCH 5/6] sctp: fix refcount bug in sctp_wfree

[ Upstream commit 5c3e82fe159622e46e91458c1a6509c321a62820 ]

We should iterate over the datamsgs to move
all chunks(skbs) to newsk.

The following case cause the bug:
for the trouble SKB, it was in outq->transmitted list

sctp_outq_sack
        sctp_check_transmitted
                SKB was moved to outq->sacked list
        then throw away the sack queue
                SKB was deleted from outq->sacked
(but it was held by datamsg at sctp_datamsg_to_asoc
So, sctp_wfree was not called here)

then migrate happened

        sctp_for_each_tx_datachunk(
        sctp_clear_owner_w);
        sctp_assoc_migrate();
        sctp_for_each_tx_datachunk(
        sctp_set_owner_w);
SKB was not in the outq, and was not changed to newsk

finally

__sctp_outq_teardown
        sctp_chunk_put (for another skb)
                sctp_datamsg_put
                        __kfree_skb(msg->frag_list)
                                sctp_wfree (for SKB)
	SKB->sk was still oldsk (skb->sk != asoc->base.sk).

Reported-and-tested-by: syzbot+cea71eec5d6de256d54d@syzkaller.appspotmail.com
Signed-off-by: Qiujun Huang <hqjagain@gmail.com>
Acked-by: Marcelo Ricardo Leitner <mleitner@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 31 +++++++++++++++++++++++--------
 1 file changed, 23 insertions(+), 8 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 0b485952a71c..ec84ae04a862 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -147,29 +147,44 @@ static void sctp_clear_owner_w(struct sctp_chunk *chunk)
 	skb_orphan(chunk->skb);
 }
 
+#define traverse_and_process()	\
+do {				\
+	msg = chunk->msg;	\
+	if (msg == prev_msg)	\
+		continue;	\
+	list_for_each_entry(c, &msg->chunks, frag_list) {	\
+		if ((clear && asoc->base.sk == c->skb->sk) ||	\
+		    (!clear && asoc->base.sk != c->skb->sk))	\
+			cb(c);	\
+	}			\
+	prev_msg = msg;		\
+} while (0)
+
 static void sctp_for_each_tx_datachunk(struct sctp_association *asoc,
+				       bool clear,
 				       void (*cb)(struct sctp_chunk *))
 
 {
+	struct sctp_datamsg *msg, *prev_msg = NULL;
 	struct sctp_outq *q = &asoc->outqueue;
+	struct sctp_chunk *chunk, *c;
 	struct sctp_transport *t;
-	struct sctp_chunk *chunk;
 
 	list_for_each_entry(t, &asoc->peer.transport_addr_list, transports)
 		list_for_each_entry(chunk, &t->transmitted, transmitted_list)
-			cb(chunk);
+			traverse_and_process();
 
 	list_for_each_entry(chunk, &q->retransmit, transmitted_list)
-		cb(chunk);
+		traverse_and_process();
 
 	list_for_each_entry(chunk, &q->sacked, transmitted_list)
-		cb(chunk);
+		traverse_and_process();
 
 	list_for_each_entry(chunk, &q->abandoned, transmitted_list)
-		cb(chunk);
+		traverse_and_process();
 
 	list_for_each_entry(chunk, &q->out_chunk_list, list)
-		cb(chunk);
+		traverse_and_process();
 }
 
 static void sctp_for_each_rx_skb(struct sctp_association *asoc, struct sock *sk,
@@ -9576,9 +9591,9 @@ static int sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
 	 * paths won't try to lock it and then oldsk.
 	 */
 	lock_sock_nested(newsk, SINGLE_DEPTH_NESTING);
-	sctp_for_each_tx_datachunk(assoc, sctp_clear_owner_w);
+	sctp_for_each_tx_datachunk(assoc, true, sctp_clear_owner_w);
 	sctp_assoc_migrate(assoc, newsk);
-	sctp_for_each_tx_datachunk(assoc, sctp_set_owner_w);
+	sctp_for_each_tx_datachunk(assoc, false, sctp_set_owner_w);
 
 	/* If the association on the newsk is already closed before accept()
 	 * is called, set RCV_SHUTDOWN flag.
-- 
2.20.1


From e1a64f66b9acead4a3bda0fe940075cdc73997b3 Mon Sep 17 00:00:00 2001
From: Codrin Ciubotariu <codrin.ciubotariu@microchip.com>
Date: Tue, 31 Mar 2020 12:39:35 +0300
Subject: [PATCH 6/6] net: macb: Fix handling of fixed-link node

[ Upstream commit 79540d133ed6f65a37dacb54b7a704cc8a24c52d ]

fixed-link nodes are treated as PHY nodes by of_mdiobus_child_is_phy().
We must check if the interface is a fixed-link before looking up for PHY
nodes.

Fixes: 7897b071ac3b ("net: macb: convert to phylink")
Tested-by: Cristian Birsan <cristian.birsan@microchip.com>
Signed-off-by: Codrin Ciubotariu <codrin.ciubotariu@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 20db44d7cda8..104884133001 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -685,6 +685,9 @@ static int macb_mdiobus_register(struct macb *bp)
 {
 	struct device_node *child, *np = bp->pdev->dev.of_node;
 
+	if (of_phy_is_fixed_link(np))
+		return mdiobus_register(bp->mii_bus);
+
 	/* Only create the PHY from the device tree if at least one PHY is
 	 * described. Otherwise scan the entire MDIO bus. We do this to support
 	 * old device tree that did not follow the best practices and did not
-- 
2.20.1


[-- Attachment #3: net_56.mbox --]
[-- Type: Application/Octet-Stream, Size: 19175 bytes --]

From deedf66fc28c6fc819b859b8208c7e8957bd679e Mon Sep 17 00:00:00 2001
From: Qian Cai <cai@lca.pw>
Date: Wed, 25 Mar 2020 18:01:00 -0400
Subject: [PATCH 1/8] ipv4: fix a RCU-list lock in fib_triestat_seq_show

[ Upstream commit fbe4e0c1b298b4665ee6915266c9d6c5b934ef4a ]

fib_triestat_seq_show() calls hlist_for_each_entry_rcu(tb, head,
tb_hlist) without rcu_read_lock() will trigger a warning,

 net/ipv4/fib_trie.c:2579 RCU-list traversed in non-reader section!!

 other info that might help us debug this:

 rcu_scheduler_active = 2, debug_locks = 1
 1 lock held by proc01/115277:
  #0: c0000014507acf00 (&p->lock){+.+.}-{3:3}, at: seq_read+0x58/0x670

 Call Trace:
  dump_stack+0xf4/0x164 (unreliable)
  lockdep_rcu_suspicious+0x140/0x164
  fib_triestat_seq_show+0x750/0x880
  seq_read+0x1a0/0x670
  proc_reg_read+0x10c/0x1b0
  __vfs_read+0x3c/0x70
  vfs_read+0xac/0x170
  ksys_read+0x7c/0x140
  system_call+0x5c/0x68

Fix it by adding a pair of rcu_read_lock/unlock() and use
cond_resched_rcu() to avoid the situation where walking of a large
number of items  may prevent scheduling for a long time.

Signed-off-by: Qian Cai <cai@lca.pw>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_trie.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index ff0c24371e33..3be0affbabd3 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -2577,6 +2577,7 @@ static int fib_triestat_seq_show(struct seq_file *seq, void *v)
 		   " %zd bytes, size of tnode: %zd bytes.\n",
 		   LEAF_SIZE, TNODE_SIZE(0));
 
+	rcu_read_lock();
 	for (h = 0; h < FIB_TABLE_HASHSZ; h++) {
 		struct hlist_head *head = &net->ipv4.fib_table_hash[h];
 		struct fib_table *tb;
@@ -2596,7 +2597,9 @@ static int fib_triestat_seq_show(struct seq_file *seq, void *v)
 			trie_show_usage(seq, t->stats);
 #endif
 		}
+		cond_resched_rcu();
 	}
+	rcu_read_unlock();
 
 	return 0;
 }
-- 
2.20.1


From 18636a7c3af6b815a3e431d8095d4f5020c6dce3 Mon Sep 17 00:00:00 2001
From: Codrin Ciubotariu <codrin.ciubotariu@microchip.com>
Date: Tue, 31 Mar 2020 12:36:51 +0300
Subject: [PATCH 2/8] net: dsa: ksz: Select KSZ protocol tag

[ Upstream commit f772148eb757b0823fbfdc2fe592d5e06c7f19b0 ]

KSZ protocol tag is needed by the KSZ DSA drivers.

Fixes: 0b9f9dfbfab4 ("dsa: Allow tag drivers to be built as modules")
Tested-by: Cristian Birsan <cristian.birsan@microchip.com>
Signed-off-by: Codrin Ciubotariu <codrin.ciubotariu@microchip.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/microchip/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/dsa/microchip/Kconfig b/drivers/net/dsa/microchip/Kconfig
index 1d7870c6df3c..4ec6a47b7f72 100644
--- a/drivers/net/dsa/microchip/Kconfig
+++ b/drivers/net/dsa/microchip/Kconfig
@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config NET_DSA_MICROCHIP_KSZ_COMMON
+	select NET_DSA_TAG_KSZ
 	tristate
 
 menuconfig NET_DSA_MICROCHIP_KSZ9477
-- 
2.20.1


From 05956d2b74d0a9e298b0716d9c8c19a5de1ea983 Mon Sep 17 00:00:00 2001
From: William Dauchy <w.dauchy@criteo.com>
Date: Fri, 27 Mar 2020 19:56:39 +0100
Subject: [PATCH 3/8] net, ip_tunnel: fix interface lookup with no key

[ Upstream commit 25629fdaff2ff509dd0b3f5ff93d70a75e79e0a1 ]

when creating a new ipip interface with no local/remote configuration,
the lookup is done with TUNNEL_NO_KEY flag, making it impossible to
match the new interface (only possible match being fallback or metada
case interface); e.g: `ip link add tunl1 type ipip dev eth0`

To fix this case, adding a flag check before the key comparison so we
permit to match an interface with no local/remote config; it also avoids
breaking possible userland tools relying on TUNNEL_NO_KEY flag and
uninitialised key.

context being on my side, I'm creating an extra ipip interface attached
to the physical one, and moving it to a dedicated namespace.

Fixes: c54419321455 ("GRE: Refactor GRE tunneling code.")
Signed-off-by: William Dauchy <w.dauchy@criteo.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_tunnel.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 74e1d964a615..cd4b84310d92 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -142,11 +142,8 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 			cand = t;
 	}
 
-	if (flags & TUNNEL_NO_KEY)
-		goto skip_key_lookup;
-
 	hlist_for_each_entry_rcu(t, head, hash_node) {
-		if (t->parms.i_key != key ||
+		if ((!(flags & TUNNEL_NO_KEY) && t->parms.i_key != key) ||
 		    t->parms.iph.saddr != 0 ||
 		    t->parms.iph.daddr != 0 ||
 		    !(t->dev->flags & IFF_UP))
@@ -158,7 +155,6 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 			cand = t;
 	}
 
-skip_key_lookup:
 	if (cand)
 		return cand;
 
-- 
2.20.1


From d2c676d4e49da91079a9bd62d0a19e9a23e26b9d Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Thu, 26 Mar 2020 20:47:46 -0300
Subject: [PATCH 4/8] sctp: fix possibly using a bad saddr with a given dst

[ Upstream commit 582eea230536a6f104097dd46205822005d5fe3a ]

Under certain circumstances, depending on the order of addresses on the
interfaces, it could be that sctp_v[46]_get_dst() would return a dst
with a mismatched struct flowi.

For example, if when walking through the bind addresses and the first
one is not a match, it saves the dst as a fallback (added in
410f03831c07), but not the flowi. Then if the next one is also not a
match, the previous dst will be returned but with the flowi information
for the 2nd address, which is wrong.

The fix is to use a locally stored flowi that can be used for such
attempts, and copy it to the parameter only in case it is a possible
match, together with the corresponding dst entry.

The patch updates IPv6 code mostly just to be in sync. Even though the issue
is also present there, it fallback is not expected to work with IPv6.

Fixes: 410f03831c07 ("sctp: add routing output fallback")
Reported-by: Jin Meng <meng.a.jin@nokia-sbell.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Tested-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ipv6.c     | 20 ++++++++++++++------
 net/sctp/protocol.c | 28 +++++++++++++++++++---------
 2 files changed, 33 insertions(+), 15 deletions(-)

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index bc734cfaa29e..c87af430107a 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -228,7 +228,8 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 {
 	struct sctp_association *asoc = t->asoc;
 	struct dst_entry *dst = NULL;
-	struct flowi6 *fl6 = &fl->u.ip6;
+	struct flowi _fl;
+	struct flowi6 *fl6 = &_fl.u.ip6;
 	struct sctp_bind_addr *bp;
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct sctp_sockaddr_entry *laddr;
@@ -238,7 +239,7 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 	enum sctp_scope scope;
 	__u8 matchlen = 0;
 
-	memset(fl6, 0, sizeof(struct flowi6));
+	memset(&_fl, 0, sizeof(_fl));
 	fl6->daddr = daddr->v6.sin6_addr;
 	fl6->fl6_dport = daddr->v6.sin6_port;
 	fl6->flowi6_proto = IPPROTO_SCTP;
@@ -276,8 +277,11 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 	rcu_read_unlock();
 
 	dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p);
-	if (!asoc || saddr)
+	if (!asoc || saddr) {
+		t->dst = dst;
+		memcpy(fl, &_fl, sizeof(_fl));
 		goto out;
+	}
 
 	bp = &asoc->base.bind_addr;
 	scope = sctp_scope(daddr);
@@ -300,6 +304,8 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 			if ((laddr->a.sa.sa_family == AF_INET6) &&
 			    (sctp_v6_cmp_addr(&dst_saddr, &laddr->a))) {
 				rcu_read_unlock();
+				t->dst = dst;
+				memcpy(fl, &_fl, sizeof(_fl));
 				goto out;
 			}
 		}
@@ -338,6 +344,8 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 			if (!IS_ERR_OR_NULL(dst))
 				dst_release(dst);
 			dst = bdst;
+			t->dst = dst;
+			memcpy(fl, &_fl, sizeof(_fl));
 			break;
 		}
 
@@ -351,6 +359,8 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 			dst_release(dst);
 		dst = bdst;
 		matchlen = bmatchlen;
+		t->dst = dst;
+		memcpy(fl, &_fl, sizeof(_fl));
 	}
 	rcu_read_unlock();
 
@@ -359,14 +369,12 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 		struct rt6_info *rt;
 
 		rt = (struct rt6_info *)dst;
-		t->dst = dst;
 		t->dst_cookie = rt6_get_cookie(rt);
 		pr_debug("rt6_dst:%pI6/%d rt6_src:%pI6\n",
 			 &rt->rt6i_dst.addr, rt->rt6i_dst.plen,
-			 &fl6->saddr);
+			 &fl->u.ip6.saddr);
 	} else {
 		t->dst = NULL;
-
 		pr_debug("no route\n");
 	}
 }
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 78af2fcf90cc..092d1afdee0d 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -409,7 +409,8 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 {
 	struct sctp_association *asoc = t->asoc;
 	struct rtable *rt;
-	struct flowi4 *fl4 = &fl->u.ip4;
+	struct flowi _fl;
+	struct flowi4 *fl4 = &_fl.u.ip4;
 	struct sctp_bind_addr *bp;
 	struct sctp_sockaddr_entry *laddr;
 	struct dst_entry *dst = NULL;
@@ -419,7 +420,7 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 
 	if (t->dscp & SCTP_DSCP_SET_MASK)
 		tos = t->dscp & SCTP_DSCP_VAL_MASK;
-	memset(fl4, 0x0, sizeof(struct flowi4));
+	memset(&_fl, 0x0, sizeof(_fl));
 	fl4->daddr  = daddr->v4.sin_addr.s_addr;
 	fl4->fl4_dport = daddr->v4.sin_port;
 	fl4->flowi4_proto = IPPROTO_SCTP;
@@ -438,8 +439,11 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 		 &fl4->saddr);
 
 	rt = ip_route_output_key(sock_net(sk), fl4);
-	if (!IS_ERR(rt))
+	if (!IS_ERR(rt)) {
 		dst = &rt->dst;
+		t->dst = dst;
+		memcpy(fl, &_fl, sizeof(_fl));
+	}
 
 	/* If there is no association or if a source address is passed, no
 	 * more validation is required.
@@ -502,27 +506,33 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 		odev = __ip_dev_find(sock_net(sk), laddr->a.v4.sin_addr.s_addr,
 				     false);
 		if (!odev || odev->ifindex != fl4->flowi4_oif) {
-			if (!dst)
+			if (!dst) {
 				dst = &rt->dst;
-			else
+				t->dst = dst;
+				memcpy(fl, &_fl, sizeof(_fl));
+			} else {
 				dst_release(&rt->dst);
+			}
 			continue;
 		}
 
 		dst_release(dst);
 		dst = &rt->dst;
+		t->dst = dst;
+		memcpy(fl, &_fl, sizeof(_fl));
 		break;
 	}
 
 out_unlock:
 	rcu_read_unlock();
 out:
-	t->dst = dst;
-	if (dst)
+	if (dst) {
 		pr_debug("rt_dst:%pI4, rt_src:%pI4\n",
-			 &fl4->daddr, &fl4->saddr);
-	else
+			 &fl->u.ip4.daddr, &fl->u.ip4.saddr);
+	} else {
+		t->dst = NULL;
 		pr_debug("no route\n");
+	}
 }
 
 /* For v4, the source address is cached in the route entry(dst). So no need
-- 
2.20.1


From 7231672240639e0a66e87ad22f7fe4f0d800e5ea Mon Sep 17 00:00:00 2001
From: Qiujun Huang <hqjagain@gmail.com>
Date: Fri, 27 Mar 2020 11:07:51 +0800
Subject: [PATCH 5/8] sctp: fix refcount bug in sctp_wfree

[ Upstream commit 5c3e82fe159622e46e91458c1a6509c321a62820 ]

We should iterate over the datamsgs to move
all chunks(skbs) to newsk.

The following case cause the bug:
for the trouble SKB, it was in outq->transmitted list

sctp_outq_sack
        sctp_check_transmitted
                SKB was moved to outq->sacked list
        then throw away the sack queue
                SKB was deleted from outq->sacked
(but it was held by datamsg at sctp_datamsg_to_asoc
So, sctp_wfree was not called here)

then migrate happened

        sctp_for_each_tx_datachunk(
        sctp_clear_owner_w);
        sctp_assoc_migrate();
        sctp_for_each_tx_datachunk(
        sctp_set_owner_w);
SKB was not in the outq, and was not changed to newsk

finally

__sctp_outq_teardown
        sctp_chunk_put (for another skb)
                sctp_datamsg_put
                        __kfree_skb(msg->frag_list)
                                sctp_wfree (for SKB)
	SKB->sk was still oldsk (skb->sk != asoc->base.sk).

Reported-and-tested-by: syzbot+cea71eec5d6de256d54d@syzkaller.appspotmail.com
Signed-off-by: Qiujun Huang <hqjagain@gmail.com>
Acked-by: Marcelo Ricardo Leitner <mleitner@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 31 +++++++++++++++++++++++--------
 1 file changed, 23 insertions(+), 8 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 1b56fc440606..757740115e93 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -147,29 +147,44 @@ static void sctp_clear_owner_w(struct sctp_chunk *chunk)
 	skb_orphan(chunk->skb);
 }
 
+#define traverse_and_process()	\
+do {				\
+	msg = chunk->msg;	\
+	if (msg == prev_msg)	\
+		continue;	\
+	list_for_each_entry(c, &msg->chunks, frag_list) {	\
+		if ((clear && asoc->base.sk == c->skb->sk) ||	\
+		    (!clear && asoc->base.sk != c->skb->sk))	\
+			cb(c);	\
+	}			\
+	prev_msg = msg;		\
+} while (0)
+
 static void sctp_for_each_tx_datachunk(struct sctp_association *asoc,
+				       bool clear,
 				       void (*cb)(struct sctp_chunk *))
 
 {
+	struct sctp_datamsg *msg, *prev_msg = NULL;
 	struct sctp_outq *q = &asoc->outqueue;
+	struct sctp_chunk *chunk, *c;
 	struct sctp_transport *t;
-	struct sctp_chunk *chunk;
 
 	list_for_each_entry(t, &asoc->peer.transport_addr_list, transports)
 		list_for_each_entry(chunk, &t->transmitted, transmitted_list)
-			cb(chunk);
+			traverse_and_process();
 
 	list_for_each_entry(chunk, &q->retransmit, transmitted_list)
-		cb(chunk);
+		traverse_and_process();
 
 	list_for_each_entry(chunk, &q->sacked, transmitted_list)
-		cb(chunk);
+		traverse_and_process();
 
 	list_for_each_entry(chunk, &q->abandoned, transmitted_list)
-		cb(chunk);
+		traverse_and_process();
 
 	list_for_each_entry(chunk, &q->out_chunk_list, list)
-		cb(chunk);
+		traverse_and_process();
 }
 
 static void sctp_for_each_rx_skb(struct sctp_association *asoc, struct sock *sk,
@@ -9574,9 +9589,9 @@ static int sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
 	 * paths won't try to lock it and then oldsk.
 	 */
 	lock_sock_nested(newsk, SINGLE_DEPTH_NESTING);
-	sctp_for_each_tx_datachunk(assoc, sctp_clear_owner_w);
+	sctp_for_each_tx_datachunk(assoc, true, sctp_clear_owner_w);
 	sctp_assoc_migrate(assoc, newsk);
-	sctp_for_each_tx_datachunk(assoc, sctp_set_owner_w);
+	sctp_for_each_tx_datachunk(assoc, false, sctp_set_owner_w);
 
 	/* If the association on the newsk is already closed before accept()
 	 * is called, set RCV_SHUTDOWN flag.
-- 
2.20.1


From d054834bdb56965d15cd5f16868515dd7d7471bb Mon Sep 17 00:00:00 2001
From: Codrin Ciubotariu <codrin.ciubotariu@microchip.com>
Date: Tue, 31 Mar 2020 12:39:35 +0300
Subject: [PATCH 6/8] net: macb: Fix handling of fixed-link node

[ Upstream commit 79540d133ed6f65a37dacb54b7a704cc8a24c52d ]

fixed-link nodes are treated as PHY nodes by of_mdiobus_child_is_phy().
We must check if the interface is a fixed-link before looking up for PHY
nodes.

Fixes: 7897b071ac3b ("net: macb: convert to phylink")
Tested-by: Cristian Birsan <cristian.birsan@microchip.com>
Signed-off-by: Codrin Ciubotariu <codrin.ciubotariu@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 2c28da1737fe..b3a51935e8e0 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -724,6 +724,9 @@ static int macb_mdiobus_register(struct macb *bp)
 {
 	struct device_node *child, *np = bp->pdev->dev.of_node;
 
+	if (of_phy_is_fixed_link(np))
+		return mdiobus_register(bp->mii_bus);
+
 	/* Only create the PHY from the device tree if at least one PHY is
 	 * described. Otherwise scan the entire MDIO bus. We do this to support
 	 * old device tree that did not follow the best practices and did not
-- 
2.20.1


From 1691d06c57a565fe56b4787482d0bfef8dc94254 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 30 Mar 2020 18:51:29 +0200
Subject: [PATCH 7/8] net: fix fraglist segmentation reference count leak

[ Upstream commit cf673ed0e057a2dd68d930c6d7e30d53c70c5789 ]

Xin Long says:
 On udp rx path udp_rcv_segment() may do segment where the frag skbs
 will get the header copied from the head skb in skb_segment_list()
 by calling __copy_skb_header(), which could overwrite the frag skbs'
 extensions by __skb_ext_copy() and cause a leak.

 This issue was found after loading esp_offload where a sec path ext
 is set in the skb.

Fix this by discarding head state of the fraglist skb before replacing
its contents.

Fixes: 3a1296a38d0cf62 ("net: Support GRO/GSO fraglist chaining.")
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Reported-by: Xiumei Mu <xmu@redhat.com>
Tested-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index e1101a4f90a6..bea447f38dcc 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3668,6 +3668,7 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb,
 
 		skb_push(nskb, -skb_network_offset(nskb) + offset);
 
+		skb_release_head_state(nskb);
 		 __copy_skb_header(nskb, skb);
 
 		skb_headers_offset_update(nskb, skb_headroom(nskb) - skb_headroom(skb));
-- 
2.20.1


From 0a1e11a6b1db10cbb598c4ab1f9566e0762c4610 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 30 Mar 2020 23:31:45 +0800
Subject: [PATCH 8/8] udp: initialize is_flist with 0 in udp_gro_receive

[ Upstream commit bde1b56f898ca8112912d7b36e55e1543b3be0cf ]

Without NAPI_GRO_CB(skb)->is_flist initialized, when the dev doesn't
support NETIF_F_GRO_FRAGLIST, is_flist can still be set and fraglist
will be used in udp_gro_receive().

So fix it by initializing is_flist with 0 in udp_gro_receive.

Fixes: 9fd1ff5d2ac7 ("udp: Support UDP fraglist GRO/GSO.")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp_offload.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 1a98583a79f4..e67a66fbf27b 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -453,6 +453,7 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
 	unsigned int off = skb_gro_offset(skb);
 	int flush = 1;
 
+	NAPI_GRO_CB(skb)->is_flist = 0;
 	if (skb->dev->features & NETIF_F_GRO_FRAGLIST)
 		NAPI_GRO_CB(skb)->is_flist = sk ? !udp_sk(sk)->gro_enabled: 1;
 
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Thu, Apr 02, 2020 at 01:16:33PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v5.5 and v5.6
> -stable, respectively.

All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 186 bytes --]


Please queue up the following networking bug fixes for v5.5 and v5.6
-stable, respectively.

Also, there is a Realtek PHY patch attached which should be queued up
for v5.4.

Thank you.

[-- Attachment #2: net_55.mbox --]
[-- Type: Application/Octet-Stream, Size: 37012 bytes --]

From 9de294d5d0648431b632c292fb27e8c038e682cc Mon Sep 17 00:00:00 2001
From: Herat Ramani <herat@chelsio.com>
Date: Wed, 1 Apr 2020 01:16:09 +0530
Subject: [PATCH 01/15] cxgb4: fix MPS index overwrite when setting MAC address

[ Upstream commit 41aa8561ca3fc5748391f08cc5f3e561923da52c ]

cxgb4_update_mac_filt() earlier requests firmware to add a new MAC
address into MPS TCAM. The MPS TCAM index returned by firmware is
stored in pi->xact_addr_filt. However, the saved MPS TCAM index gets
overwritten again with the return value of cxgb4_update_mac_filt(),
which is wrong.

When trying to update to another MAC address later, the wrong MPS TCAM
index is sent to firmware, which causes firmware to return error,
because it's not the same MPS TCAM index that firmware had sent
earlier to driver.

So, fix by removing the wrong overwrite being done after call to
cxgb4_update_mac_filt().

Fixes: 3f8cfd0d95e6 ("cxgb4/cxgb4vf: Program hash region for {t4/t4vf}_change_mac()")
Signed-off-by: Herat Ramani <herat@chelsio.com>
Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index b11ba4565c20..9934c8b0f0b0 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -3110,7 +3110,6 @@ static int cxgb_set_mac_addr(struct net_device *dev, void *p)
 		return ret;
 
 	memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);
-	pi->xact_addr_filt = ret;
 	return 0;
 }
 
-- 
2.20.1


From 082881907b30c90e741130a683bd174122d21b9e Mon Sep 17 00:00:00 2001
From: Jarod Wilson <jarod@redhat.com>
Date: Mon, 30 Mar 2020 11:22:19 -0400
Subject: [PATCH 02/15] ipv6: don't auto-add link-local address to lag ports

[ Upstream commit 744fdc8233f6aa9582ce08a51ca06e59796a3196 ]

Bonding slave and team port devices should not have link-local addresses
automatically added to them, as it can interfere with openvswitch being
able to properly add tc ingress.

Basic reproducer, courtesy of Marcelo:

$ ip link add name bond0 type bond
$ ip link set dev ens2f0np0 master bond0
$ ip link set dev ens2f1np2 master bond0
$ ip link set dev bond0 up
$ ip a s
1: lo: <LOOPBACK,UP,LOWER_UP> mtu 65536 qdisc noqueue state UNKNOWN
group default qlen 1000
    link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00
    inet 127.0.0.1/8 scope host lo
       valid_lft forever preferred_lft forever
    inet6 ::1/128 scope host
       valid_lft forever preferred_lft forever
2: ens2f0np0: <BROADCAST,MULTICAST,SLAVE,UP,LOWER_UP> mtu 1500 qdisc
mq master bond0 state UP group default qlen 1000
    link/ether 00:0f:53:2f:ea:40 brd ff:ff:ff:ff:ff:ff
5: ens2f1np2: <NO-CARRIER,BROADCAST,MULTICAST,SLAVE,UP> mtu 1500 qdisc
mq master bond0 state DOWN group default qlen 1000
    link/ether 00:0f:53:2f:ea:40 brd ff:ff:ff:ff:ff:ff
11: bond0: <BROADCAST,MULTICAST,MASTER,UP,LOWER_UP> mtu 1500 qdisc
noqueue state UP group default qlen 1000
    link/ether 00:0f:53:2f:ea:40 brd ff:ff:ff:ff:ff:ff
    inet6 fe80::20f:53ff:fe2f:ea40/64 scope link
       valid_lft forever preferred_lft forever

(above trimmed to relevant entries, obviously)

$ sysctl net.ipv6.conf.ens2f0np0.addr_gen_mode=0
net.ipv6.conf.ens2f0np0.addr_gen_mode = 0
$ sysctl net.ipv6.conf.ens2f1np2.addr_gen_mode=0
net.ipv6.conf.ens2f1np2.addr_gen_mode = 0

$ ip a l ens2f0np0
2: ens2f0np0: <BROADCAST,MULTICAST,SLAVE,UP,LOWER_UP> mtu 1500 qdisc
mq master bond0 state UP group default qlen 1000
    link/ether 00:0f:53:2f:ea:40 brd ff:ff:ff:ff:ff:ff
    inet6 fe80::20f:53ff:fe2f:ea40/64 scope link tentative
       valid_lft forever preferred_lft forever
$ ip a l ens2f1np2
5: ens2f1np2: <NO-CARRIER,BROADCAST,MULTICAST,SLAVE,UP> mtu 1500 qdisc
mq master bond0 state DOWN group default qlen 1000
    link/ether 00:0f:53:2f:ea:40 brd ff:ff:ff:ff:ff:ff
    inet6 fe80::20f:53ff:fe2f:ea40/64 scope link tentative
       valid_lft forever preferred_lft forever

Looks like addrconf_sysctl_addr_gen_mode() bypasses the original "is
this a slave interface?" check added by commit c2edacf80e15, and
results in an address getting added, while w/the proposed patch added,
no address gets added. This simply adds the same gating check to another
code path, and thus should prevent the same devices from erroneously
obtaining an ipv6 link-local address.

Fixes: d35a00b8e33d ("net/ipv6: allow sysctl to change link-local address generation mode")
Reported-by: Moshe Levi <moshele@mellanox.com>
CC: Stephen Hemminger <stephen@networkplumber.org>
CC: Marcelo Ricardo Leitner <mleitner@redhat.com>
CC: netdev@vger.kernel.org
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 46d614b611db..2a8175de8578 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3296,6 +3296,10 @@ static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route)
 	if (netif_is_l3_master(idev->dev))
 		return;
 
+	/* no link local addresses on devices flagged as slaves */
+	if (idev->dev->flags & IFF_SLAVE)
+		return;
+
 	ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0);
 
 	switch (idev->cnf.addr_gen_mode) {
-- 
2.20.1


From ecc70a0475b97ac62884a79b8c7769c22367aa8c Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Sat, 4 Apr 2020 14:35:17 -0700
Subject: [PATCH 03/15] net: dsa: bcm_sf2: Do not register slave MDIO bus with
 OF

[ Upstream commit 536fab5bf5826404534a6c271f622ad2930d9119 ]

We were registering our slave MDIO bus with OF and doing so with
assigning the newly created slave_mii_bus of_node to the master MDIO bus
controller node. This is a bad thing to do for a number of reasons:

- we are completely lying about the slave MII bus is arranged and yet we
  still want to control which MDIO devices it probes. It was attempted
  before to play tricks with the bus_mask to perform that:
  https://www.spinics.net/lists/netdev/msg429420.html but the approach
  was rightfully rejected

- the device_node reference counting is messed up and we are effectively
  doing a double probe on the devices we already probed using the
  master, this messes up all resources reference counts (such as clocks)

The proper fix for this as indicated by David in his reply to the
thread above is to use a platform data style registration so as to
control exactly which devices we probe:
https://www.spinics.net/lists/netdev/msg430083.html

By using mdiobus_register(), our slave_mii_bus->phy_mask value is used
as intended, and all the PHY addresses that must be redirected towards
our slave MDIO bus is happening while other addresses get redirected
towards the master MDIO bus.

Fixes: 461cd1b03e32 ("net: dsa: bcm_sf2: Register our slave MDIO bus")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Vivien Didelot <vivien.didelot@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index b0f5280a83cb..4481afd323a9 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -472,7 +472,7 @@ static int bcm_sf2_mdio_register(struct dsa_switch *ds)
 	priv->slave_mii_bus->parent = ds->dev->parent;
 	priv->slave_mii_bus->phy_mask = ~priv->indir_phy_mask;
 
-	err = of_mdiobus_register(priv->slave_mii_bus, dn);
+	err = mdiobus_register(priv->slave_mii_bus);
 	if (err && dn)
 		of_node_put(dn);
 
-- 
2.20.1


From 28d6c0a6477a461eb9126423cee722e05beb9203 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Sun, 5 Apr 2020 13:00:30 -0700
Subject: [PATCH 04/15] net: dsa: bcm_sf2: Ensure correct sub-node is parsed

[ Upstream commit afa3b592953bfaecfb4f2f335ec5f935cff56804 ]

When the bcm_sf2 was converted into a proper platform device driver and
used the new dsa_register_switch() interface, we would still be parsing
the legacy DSA node that contained all the port information since the
platform firmware has intentionally maintained backward and forward
compatibility to client programs. Ensure that we do parse the correct
node, which is "ports" per the revised DSA binding.

Fixes: d9338023fb8e ("net: dsa: bcm_sf2: Make it a real platform device driver")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Vivien Didelot <vivien.didelot@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 4481afd323a9..e93c81c4062e 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -1069,6 +1069,7 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev)
 	const struct bcm_sf2_of_data *data;
 	struct b53_platform_data *pdata;
 	struct dsa_switch_ops *ops;
+	struct device_node *ports;
 	struct bcm_sf2_priv *priv;
 	struct b53_device *dev;
 	struct dsa_switch *ds;
@@ -1136,7 +1137,11 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev)
 	set_bit(0, priv->cfp.used);
 	set_bit(0, priv->cfp.unique);
 
-	bcm_sf2_identify_ports(priv, dn->child);
+	ports = of_find_node_by_name(dn, "ports");
+	if (ports) {
+		bcm_sf2_identify_ports(priv, ports);
+		of_node_put(ports);
+	}
 
 	priv->irq0 = irq_of_parse_and_map(dn, 0);
 	priv->irq1 = irq_of_parse_and_map(dn, 1);
-- 
2.20.1


From c1bade18f357027742330dcc48394671a9246015 Mon Sep 17 00:00:00 2001
From: Chuanhong Guo <gch981213@gmail.com>
Date: Fri, 3 Apr 2020 19:28:24 +0800
Subject: [PATCH 05/15] net: dsa: mt7530: fix null pointer dereferencing in
 port5 setup
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 0452800f6db4ed0a42ffb15867c0acfd68829f6a ]

The 2nd gmac of mediatek soc ethernet may not be connected to a PHY
and a phy-handle isn't always available.
Unfortunately, mt7530 dsa driver assumes that the 2nd gmac is always
connected to switch port 5 and setup mt7530 according to phy address
of 2nd gmac node, causing null pointer dereferencing when phy-handle
isn't defined in dts.
This commit fix this setup code by checking return value of
of_parse_phandle before using it.

Fixes: 38f790a80560 ("net: dsa: mt7530: Add support for port 5")
Signed-off-by: Chuanhong Guo <gch981213@gmail.com>
Reviewed-by: Vivien Didelot <vivien.didelot@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Tested-by: René van Dorst <opensource@vdorst.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mt7530.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index 60a8a68567ba..936b9b65acca 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -1355,6 +1355,9 @@ mt7530_setup(struct dsa_switch *ds)
 				continue;
 
 			phy_node = of_parse_phandle(mac_np, "phy-handle", 0);
+			if (!phy_node)
+				continue;
+
 			if (phy_node->parent == priv->dev->of_node->parent) {
 				ret = of_get_phy_mode(mac_np, &interface);
 				if (ret && ret != -ENODEV)
-- 
2.20.1


From caee5348373be2b4d1855c2088f7ab07e4075990 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Fri, 3 Apr 2020 09:53:25 +0200
Subject: [PATCH 06/15] net: phy: micrel: kszphy_resume(): add delay after
 genphy_resume() before accessing PHY registers

[ Upstream commit 6110dff776f7fa65c35850ef65b41d3b39e2fac2 ]

After the power-down bit is cleared, the chip internally triggers a
global reset. According to the KSZ9031 documentation, we have to wait at
least 1ms for the reset to finish.

If the chip is accessed during reset, read will return 0xffff, while
write will be ignored. Depending on the system performance and MDIO bus
speed, we may or may not run in to this issue.

This bug was discovered on an iMX6QP system with KSZ9031 PHY and
attached PHY interrupt line. If IRQ was used, the link status update was
lost. In polling mode, the link status update was always correct.

The investigation showed, that during a read-modify-write access, the
read returned 0xffff (while the chip was still in reset) and
corresponding write hit the chip _after_ reset and triggered (due to the
0xffff) another reset in an undocumented bit (register 0x1f, bit 1),
resulting in the next write being lost due to the new reset cycle.

This patch fixes the issue by adding a 1...2 ms sleep after the
genphy_resume().

Fixes: 836384d2501d ("net: phy: micrel: Add specific suspend")
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/micrel.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 63dedec0433d..51b64f087717 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -25,6 +25,7 @@
 #include <linux/micrel_phy.h>
 #include <linux/of.h>
 #include <linux/clk.h>
+#include <linux/delay.h>
 
 /* Operation Mode Strap Override */
 #define MII_KSZPHY_OMSO				0x16
@@ -902,6 +903,12 @@ static int kszphy_resume(struct phy_device *phydev)
 
 	genphy_resume(phydev);
 
+	/* After switching from power-down to normal mode, an internal global
+	 * reset is automatically generated. Wait a minimum of 1 ms before
+	 * read/write access to the PHY registers.
+	 */
+	usleep_range(1000, 2000);
+
 	ret = kszphy_config_reset(phydev);
 	if (ret)
 		return ret;
-- 
2.20.1


From ce51ffd4f34402f8e72646d829340dd0dcf93f23 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sat, 28 Mar 2020 12:12:59 -0700
Subject: [PATCH 07/15] net_sched: add a temporary refcnt for struct
 tcindex_data

[ Upstream commit 304e024216a802a7dc8ba75d36de82fa136bbf3e ]

Although we intentionally use an ordered workqueue for all tc
filter works, the ordering is not guaranteed by RCU work,
given that tcf_queue_work() is esstenially a call_rcu().

This problem is demostrated by Thomas:

  CPU 0:
    tcf_queue_work()
      tcf_queue_work(&r->rwork, tcindex_destroy_rexts_work);

  -> Migration to CPU 1

  CPU 1:
     tcf_queue_work(&p->rwork, tcindex_destroy_work);

so the 2nd work could be queued before the 1st one, which leads
to a free-after-free.

Enforcing this order in RCU work is hard as it requires to change
RCU code too. Fortunately we can workaround this problem in tcindex
filter by taking a temporary refcnt, we only refcnt it right before
we begin to destroy it. This simplifies the code a lot as a full
refcnt requires much more changes in tcindex_set_parms().

Reported-by: syzbot+46f513c3033d592409d2@syzkaller.appspotmail.com
Fixes: 3d210534cc93 ("net_sched: fix a race condition in tcindex_destroy()")
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Paul E. McKenney <paulmck@kernel.org>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Reviewed-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_tcindex.c | 44 +++++++++++++++++++++++++++++++++++------
 1 file changed, 38 insertions(+), 6 deletions(-)

diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 9904299424a1..065345832a69 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -11,6 +11,7 @@
 #include <linux/skbuff.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
+#include <linux/refcount.h>
 #include <net/act_api.h>
 #include <net/netlink.h>
 #include <net/pkt_cls.h>
@@ -26,9 +27,12 @@
 #define DEFAULT_HASH_SIZE	64	/* optimized for diffserv */
 
 
+struct tcindex_data;
+
 struct tcindex_filter_result {
 	struct tcf_exts		exts;
 	struct tcf_result	res;
+	struct tcindex_data	*p;
 	struct rcu_work		rwork;
 };
 
@@ -49,6 +53,7 @@ struct tcindex_data {
 	u32 hash;		/* hash table size; 0 if undefined */
 	u32 alloc_hash;		/* allocated size */
 	u32 fall_through;	/* 0: only classify if explicit match */
+	refcount_t refcnt;	/* a temporary refcnt for perfect hash */
 	struct rcu_work rwork;
 };
 
@@ -57,6 +62,20 @@ static inline int tcindex_filter_is_set(struct tcindex_filter_result *r)
 	return tcf_exts_has_actions(&r->exts) || r->res.classid;
 }
 
+static void tcindex_data_get(struct tcindex_data *p)
+{
+	refcount_inc(&p->refcnt);
+}
+
+static void tcindex_data_put(struct tcindex_data *p)
+{
+	if (refcount_dec_and_test(&p->refcnt)) {
+		kfree(p->perfect);
+		kfree(p->h);
+		kfree(p);
+	}
+}
+
 static struct tcindex_filter_result *tcindex_lookup(struct tcindex_data *p,
 						    u16 key)
 {
@@ -141,6 +160,7 @@ static void __tcindex_destroy_rexts(struct tcindex_filter_result *r)
 {
 	tcf_exts_destroy(&r->exts);
 	tcf_exts_put_net(&r->exts);
+	tcindex_data_put(r->p);
 }
 
 static void tcindex_destroy_rexts_work(struct work_struct *work)
@@ -212,6 +232,8 @@ static int tcindex_delete(struct tcf_proto *tp, void *arg, bool *last,
 		else
 			__tcindex_destroy_fexts(f);
 	} else {
+		tcindex_data_get(p);
+
 		if (tcf_exts_get_net(&r->exts))
 			tcf_queue_work(&r->rwork, tcindex_destroy_rexts_work);
 		else
@@ -228,9 +250,7 @@ static void tcindex_destroy_work(struct work_struct *work)
 					      struct tcindex_data,
 					      rwork);
 
-	kfree(p->perfect);
-	kfree(p->h);
-	kfree(p);
+	tcindex_data_put(p);
 }
 
 static inline int
@@ -248,9 +268,11 @@ static const struct nla_policy tcindex_policy[TCA_TCINDEX_MAX + 1] = {
 };
 
 static int tcindex_filter_result_init(struct tcindex_filter_result *r,
+				      struct tcindex_data *p,
 				      struct net *net)
 {
 	memset(r, 0, sizeof(*r));
+	r->p = p;
 	return tcf_exts_init(&r->exts, net, TCA_TCINDEX_ACT,
 			     TCA_TCINDEX_POLICE);
 }
@@ -290,6 +312,7 @@ static int tcindex_alloc_perfect_hash(struct net *net, struct tcindex_data *cp)
 				    TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
 		if (err < 0)
 			goto errout;
+		cp->perfect[i].p = cp;
 	}
 
 	return 0;
@@ -334,6 +357,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	cp->alloc_hash = p->alloc_hash;
 	cp->fall_through = p->fall_through;
 	cp->tp = tp;
+	refcount_set(&cp->refcnt, 1); /* Paired with tcindex_destroy_work() */
 
 	if (tb[TCA_TCINDEX_HASH])
 		cp->hash = nla_get_u32(tb[TCA_TCINDEX_HASH]);
@@ -366,7 +390,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	}
 	cp->h = p->h;
 
-	err = tcindex_filter_result_init(&new_filter_result, net);
+	err = tcindex_filter_result_init(&new_filter_result, cp, net);
 	if (err < 0)
 		goto errout_alloc;
 	if (old_r)
@@ -434,7 +458,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 			goto errout_alloc;
 		f->key = handle;
 		f->next = NULL;
-		err = tcindex_filter_result_init(&f->result, net);
+		err = tcindex_filter_result_init(&f->result, cp, net);
 		if (err < 0) {
 			kfree(f);
 			goto errout_alloc;
@@ -447,7 +471,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	}
 
 	if (old_r && old_r != r) {
-		err = tcindex_filter_result_init(old_r, net);
+		err = tcindex_filter_result_init(old_r, cp, net);
 		if (err < 0) {
 			kfree(f);
 			goto errout_alloc;
@@ -571,6 +595,14 @@ static void tcindex_destroy(struct tcf_proto *tp, bool rtnl_held,
 		for (i = 0; i < p->hash; i++) {
 			struct tcindex_filter_result *r = p->perfect + i;
 
+			/* tcf_queue_work() does not guarantee the ordering we
+			 * want, so we have to take this refcnt temporarily to
+			 * ensure 'p' is freed after all tcindex_filter_result
+			 * here. Imperfect hash does not need this, because it
+			 * uses linked lists rather than an array.
+			 */
+			tcindex_data_get(p);
+
 			tcf_unbind_filter(tp, &r->res);
 			if (tcf_exts_get_net(&r->exts))
 				tcf_queue_work(&r->rwork,
-- 
2.20.1


From 9fe5c827601b1ea3063b3b5d9f8fd052bb1cd076 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 2 Apr 2020 20:58:51 -0700
Subject: [PATCH 08/15] net_sched: fix a missing refcnt in tcindex_init()

[ Upstream commit a8eab6d35e22f4f21471f16147be79529cd6aaf7 ]

The initial refcnt of struct tcindex_data should be 1,
it is clear that I forgot to set it to 1 in tcindex_init().
This leads to a dec-after-zero warning.

Reported-by: syzbot+8325e509a1bf83ec741d@syzkaller.appspotmail.com
Fixes: 304e024216a8 ("net_sched: add a temporary refcnt for struct tcindex_data")
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Cc: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_tcindex.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 065345832a69..61e95029c18f 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -151,6 +151,7 @@ static int tcindex_init(struct tcf_proto *tp)
 	p->mask = 0xffff;
 	p->hash = DEFAULT_HASH_SIZE;
 	p->fall_through = 1;
+	refcount_set(&p->refcnt, 1); /* Paired with tcindex_destroy_work() */
 
 	rcu_assign_pointer(tp->root, p);
 	return 0;
-- 
2.20.1


From 15ae3f46b86cc3f6763cd2b180e67a6fec4e5726 Mon Sep 17 00:00:00 2001
From: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
Date: Fri, 3 Apr 2020 10:23:29 +0800
Subject: [PATCH 09/15] net: stmmac: dwmac1000: fix out-of-bounds mac address
 reg setting

[ Upstream commit 3e1221acf6a8f8595b5ce354bab4327a69d54d18 ]

Commit 9463c4455900 ("net: stmmac: dwmac1000: Clear unused address
entries") cleared the unused mac address entries, but introduced an
out-of bounds mac address register programming bug -- After setting
the secondary unicast mac addresses, the "reg" value has reached
netdev_uc_count() + 1, thus we should only clear address entries
if (addr < perfect_addr_number)

Fixes: 9463c4455900 ("net: stmmac: dwmac1000: Clear unused address entries")
Signed-off-by: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
index 542784300620..efc6ec1b8027 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
@@ -207,7 +207,7 @@ static void dwmac1000_set_filter(struct mac_device_info *hw,
 			reg++;
 		}
 
-		while (reg <= perfect_addr_number) {
+		while (reg < perfect_addr_number) {
 			writel(0, ioaddr + GMAC_ADDR_HIGH(reg));
 			writel(0, ioaddr + GMAC_ADDR_LOW(reg));
 			reg++;
-- 
2.20.1


From 5f2a8c93591c29e44ac07594dbe9556604de5a40 Mon Sep 17 00:00:00 2001
From: Richard Palethorpe <rpalethorpe@suse.com>
Date: Wed, 1 Apr 2020 12:06:39 +0200
Subject: [PATCH 10/15] slcan: Don't transmit uninitialized stack data in
 padding

[ Upstream commit b9258a2cece4ec1f020715fe3554bc2e360f6264 ]

struct can_frame contains some padding which is not explicitly zeroed in
slc_bump. This uninitialized data will then be transmitted if the stack
initialization hardening feature is not enabled (CONFIG_INIT_STACK_ALL).

This commit just zeroes the whole struct including the padding.

Signed-off-by: Richard Palethorpe <rpalethorpe@suse.com>
Fixes: a1044e36e457 ("can: add slcan driver for serial/USB-serial CAN adapters")
Reviewed-by: Kees Cook <keescook@chromium.org>
Cc: linux-can@vger.kernel.org
Cc: netdev@vger.kernel.org
Cc: security@kernel.org
Cc: wg@grandegger.com
Cc: mkl@pengutronix.de
Cc: davem@davemloft.net
Acked-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/can/slcan.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c
index a3664281a33f..4dfa459ef5c7 100644
--- a/drivers/net/can/slcan.c
+++ b/drivers/net/can/slcan.c
@@ -148,7 +148,7 @@ static void slc_bump(struct slcan *sl)
 	u32 tmpid;
 	char *cmd = sl->rbuff;
 
-	cf.can_id = 0;
+	memset(&cf, 0, sizeof(cf));
 
 	switch (*cmd) {
 	case 'r':
@@ -187,8 +187,6 @@ static void slc_bump(struct slcan *sl)
 	else
 		return;
 
-	*(u64 *) (&cf.data) = 0; /* clear payload */
-
 	/* RTR frames may have a dlc > 0 but they never have any data bytes */
 	if (!(cf.can_id & CAN_RTR_FLAG)) {
 		for (i = 0; i < cf.can_dlc; i++) {
-- 
2.20.1


From 7396d0504a2425d3787ebaef6a4562a593017e23 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Fri, 3 Apr 2020 16:13:21 +0100
Subject: [PATCH 11/15] tun: Don't put_page() for all negative return values
 from XDP program

[ Upstream commit bee348907d19d654e8524d3a946dcd25b693aa7e ]

When an XDP program is installed, tun_build_skb() grabs a reference to
the current page fragment page if the program returns XDP_REDIRECT or
XDP_TX. However, since tun_xdp_act() passes through negative return
values from the XDP program, it is possible to trigger the error path by
mistake and accidentally drop a reference to the fragments page without
taking one, leading to a spurious free. This is believed to be the cause
of some KASAN use-after-free reports from syzbot [1], although without a
reproducer it is not possible to confirm whether this patch fixes the
problem.

Ensure that we only drop a reference to the fragments page if the XDP
transmit or redirect operations actually fail.

[1] https://syzkaller.appspot.com/bug?id=e76a6af1be4acd727ff6bbca669833f98cbf5d95

Cc: "David S. Miller" <davem@davemloft.net>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
CC: Eric Dumazet <edumazet@google.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Fixes: 8ae1aff0b331 ("tuntap: split out XDP logic")
Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 35e884a8242d..6d3317d868d2 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1715,8 +1715,12 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 			alloc_frag->offset += buflen;
 		}
 		err = tun_xdp_act(tun, xdp_prog, &xdp, act);
-		if (err < 0)
-			goto err_xdp;
+		if (err < 0) {
+			if (act == XDP_REDIRECT || act == XDP_TX)
+				put_page(alloc_frag->page);
+			goto out;
+		}
+
 		if (err == XDP_REDIRECT)
 			xdp_do_flush_map();
 		if (err != XDP_PASS)
@@ -1730,8 +1734,6 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 
 	return __tun_build_skb(tfile, alloc_frag, buf, buflen, len, pad);
 
-err_xdp:
-	put_page(alloc_frag->page);
 out:
 	rcu_read_unlock();
 	local_bh_enable();
-- 
2.20.1


From 6977cdf1ec7060adef785104b582b64fdd11cfda Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Sun, 5 Apr 2020 09:50:22 +0300
Subject: [PATCH 12/15] mlxsw: spectrum_flower: Do not stop at
 FLOW_ACTION_VLAN_MANGLE

[ Upstream commit ccfc569347f870830e7c7cf854679a06cf9c45b5 ]

The handler for FLOW_ACTION_VLAN_MANGLE ends by returning whatever the
lower-level function that it calls returns. If there are more actions lined
up after this action, those are never offloaded. Fix by only bailing out
when the called function returns an error.

Fixes: a150201a70da ("mlxsw: spectrum: Add support for vlan modify TC action")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
index b607919c8ad0..498de6ef6870 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
@@ -123,9 +123,12 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 			u8 prio = act->vlan.prio;
 			u16 vid = act->vlan.vid;
 
-			return mlxsw_sp_acl_rulei_act_vlan(mlxsw_sp, rulei,
-							   act->id, vid,
-							   proto, prio, extack);
+			err = mlxsw_sp_acl_rulei_act_vlan(mlxsw_sp, rulei,
+							  act->id, vid,
+							  proto, prio, extack);
+			if (err)
+				return err;
+			break;
 			}
 		default:
 			NL_SET_ERR_MSG_MOD(extack, "Unsupported action");
-- 
2.20.1


From 8696c8fff778ecb150ea34c1894b6ee890398cc0 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 4 Apr 2020 23:48:45 +0200
Subject: [PATCH 13/15] r8169: change back SG and TSO to be disabled by default

[ Upstream commit 95099c569a9fdbe186a27447dfa8a5a0562d4b7f ]

There has been a number of reports that using SG/TSO on different chip
versions results in tx timeouts. However for a lot of people SG/TSO
works fine. Therefore disable both features by default, but allow users
to enable them. Use at own risk!

Fixes: 93681cd7d94f ("r8169: enable HW csum and TSO")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
---
 drivers/net/ethernet/realtek/r8169_main.c | 34 +++++++++++------------
 1 file changed, 16 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index cab63828643a..a002f54e0196 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -6934,12 +6934,10 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	netif_napi_add(dev, &tp->napi, rtl8169_poll, NAPI_POLL_WEIGHT);
 
-	dev->features |= NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO |
-		NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_TX |
-		NETIF_F_HW_VLAN_CTAG_RX;
-	dev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO |
-		NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_TX |
-		NETIF_F_HW_VLAN_CTAG_RX;
+	dev->features |= NETIF_F_IP_CSUM | NETIF_F_RXCSUM |
+			 NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX;
+	dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_RXCSUM |
+			   NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX;
 	dev->vlan_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO |
 		NETIF_F_HIGHDMA;
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
@@ -6957,25 +6955,25 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		dev->hw_features &= ~NETIF_F_HW_VLAN_CTAG_RX;
 
 	if (rtl_chip_supports_csum_v2(tp)) {
-		dev->hw_features |= NETIF_F_IPV6_CSUM | NETIF_F_TSO6;
-		dev->features |= NETIF_F_IPV6_CSUM | NETIF_F_TSO6;
+		dev->hw_features |= NETIF_F_IPV6_CSUM;
+		dev->features |= NETIF_F_IPV6_CSUM;
+	}
+
+	/* There has been a number of reports that using SG/TSO results in
+	 * tx timeouts. However for a lot of people SG/TSO works fine.
+	 * Therefore disable both features by default, but allow users to
+	 * enable them. Use at own risk!
+	 */
+	if (rtl_chip_supports_csum_v2(tp)) {
+		dev->hw_features |= NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6;
 		dev->gso_max_size = RTL_GSO_MAX_SIZE_V2;
 		dev->gso_max_segs = RTL_GSO_MAX_SEGS_V2;
 	} else {
+		dev->hw_features |= NETIF_F_SG | NETIF_F_TSO;
 		dev->gso_max_size = RTL_GSO_MAX_SIZE_V1;
 		dev->gso_max_segs = RTL_GSO_MAX_SEGS_V1;
 	}
 
-	/* RTL8168e-vl and one RTL8168c variant are known to have a
-	 * HW issue with TSO.
-	 */
-	if (tp->mac_version == RTL_GIGA_MAC_VER_34 ||
-	    tp->mac_version == RTL_GIGA_MAC_VER_22) {
-		dev->vlan_features &= ~(NETIF_F_ALL_TSO | NETIF_F_SG);
-		dev->hw_features &= ~(NETIF_F_ALL_TSO | NETIF_F_SG);
-		dev->features &= ~(NETIF_F_ALL_TSO | NETIF_F_SG);
-	}
-
 	dev->hw_features |= NETIF_F_RXALL;
 	dev->hw_features |= NETIF_F_RXFCS;
 
-- 
2.20.1


From d9c8f6c1439d774b5dcaac82d3c7a4fd5783b803 Mon Sep 17 00:00:00 2001
From: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Date: Wed, 1 Apr 2020 01:17:01 +0530
Subject: [PATCH 14/15] cxgb4: free MQPRIO resources in shutdown path

[ Upstream commit cef8dac96bc108633f5090bb3a9988d734dc1ee0 ]

Perform missing MQPRIO resource cleanup in PCI shutdown path. Also,
fix MQPRIO MSIX bitmap leak in resource cleanup.

Fixes: b1396c2bd675 ("cxgb4: parse and configure TC-MQPRIO offload")
Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/chelsio/cxgb4/cxgb4_main.c   |  4 ++++
 .../ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c  | 23 +++++++++++++++++++
 .../ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.h  |  1 +
 3 files changed, 28 insertions(+)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 9934c8b0f0b0..a2fa4b1fd443 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -6651,6 +6651,10 @@ static void shutdown_one(struct pci_dev *pdev)
 			if (adapter->port[i]->reg_state == NETREG_REGISTERED)
 				cxgb_close(adapter->port[i]);
 
+		rtnl_lock();
+		cxgb4_mqprio_stop_offload(adapter);
+		rtnl_unlock();
+
 		if (is_uld(adapter)) {
 			detach_ulds(adapter);
 			t4_uld_clean_up(adapter);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c
index ec3eb45ee3b4..e6af4906d674 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c
@@ -301,6 +301,7 @@ static void cxgb4_mqprio_free_hw_resources(struct net_device *dev)
 			cxgb4_clear_msix_aff(eorxq->msix->vec,
 					     eorxq->msix->aff_mask);
 			free_irq(eorxq->msix->vec, &eorxq->rspq);
+			cxgb4_free_msix_idx_in_bmap(adap, eorxq->msix->idx);
 		}
 
 		free_rspq_fl(adap, &eorxq->rspq, &eorxq->fl);
@@ -611,6 +612,28 @@ int cxgb4_setup_tc_mqprio(struct net_device *dev,
 	return ret;
 }
 
+void cxgb4_mqprio_stop_offload(struct adapter *adap)
+{
+	struct cxgb4_tc_port_mqprio *tc_port_mqprio;
+	struct net_device *dev;
+	u8 i;
+
+	if (!adap->tc_mqprio || !adap->tc_mqprio->port_mqprio)
+		return;
+
+	for_each_port(adap, i) {
+		dev = adap->port[i];
+		if (!dev)
+			continue;
+
+		tc_port_mqprio = &adap->tc_mqprio->port_mqprio[i];
+		if (!tc_port_mqprio->mqprio.qopt.num_tc)
+			continue;
+
+		cxgb4_mqprio_disable_offload(dev);
+	}
+}
+
 int cxgb4_init_tc_mqprio(struct adapter *adap)
 {
 	struct cxgb4_tc_port_mqprio *tc_port_mqprio, *port_mqprio;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.h
index c532f1ef8451..ff8794132b22 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.h
@@ -38,6 +38,7 @@ struct cxgb4_tc_mqprio {
 
 int cxgb4_setup_tc_mqprio(struct net_device *dev,
 			  struct tc_mqprio_qopt_offload *mqprio);
+void cxgb4_mqprio_stop_offload(struct adapter *adap);
 int cxgb4_init_tc_mqprio(struct adapter *adap);
 void cxgb4_cleanup_tc_mqprio(struct adapter *adap);
 #endif /* __CXGB4_TC_MQPRIO_H__ */
-- 
2.20.1


From 62c1bd5b50f32945850aed02f7bb980564382222 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Wed, 1 Apr 2020 11:57:32 +0200
Subject: [PATCH 15/15] net: phy: at803x: fix clock sink configuration on
 ATH8030 and ATH8035

[ Upstream commit b1f4c209d84057b6d40b939b6e4404854271d797 ]

The masks in priv->clk_25m_reg and priv->clk_25m_mask are one-bits-set
for the values that comprise the fields, not zero-bits-set.

This patch fixes the clock frequency configuration for ATH8030 and
ATH8035 Atheros PHYs by removing the erroneous "~".

To reproduce this bug, configure the PHY  with the device tree binding
"qca,clk-out-frequency" and remove the machine specific PHY fixups.

Fixes: 2f664823a47021 ("net: phy: at803x: add device tree binding")
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reported-by: Russell King <rmk+kernel@armlinux.org.uk>
Reviewed-by: Russell King <rmk+kernel@armlinux.org.uk>
Tested-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/at803x.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c
index 481cf48c9b9e..31f731e6df72 100644
--- a/drivers/net/phy/at803x.c
+++ b/drivers/net/phy/at803x.c
@@ -425,8 +425,8 @@ static int at803x_parse_dt(struct phy_device *phydev)
 		 */
 		if (at803x_match_phy_id(phydev, ATH8030_PHY_ID) ||
 		    at803x_match_phy_id(phydev, ATH8035_PHY_ID)) {
-			priv->clk_25m_reg &= ~AT8035_CLK_OUT_MASK;
-			priv->clk_25m_mask &= ~AT8035_CLK_OUT_MASK;
+			priv->clk_25m_reg &= AT8035_CLK_OUT_MASK;
+			priv->clk_25m_mask &= AT8035_CLK_OUT_MASK;
 		}
 	}
 
-- 
2.20.1


[-- Attachment #3: net_56.mbox --]
[-- Type: Application/Octet-Stream, Size: 37008 bytes --]

From d2d1525e72ba55483502f0ee415823de64724d12 Mon Sep 17 00:00:00 2001
From: Herat Ramani <herat@chelsio.com>
Date: Wed, 1 Apr 2020 01:16:09 +0530
Subject: [PATCH 01/15] cxgb4: fix MPS index overwrite when setting MAC address

[ Upstream commit 41aa8561ca3fc5748391f08cc5f3e561923da52c ]

cxgb4_update_mac_filt() earlier requests firmware to add a new MAC
address into MPS TCAM. The MPS TCAM index returned by firmware is
stored in pi->xact_addr_filt. However, the saved MPS TCAM index gets
overwritten again with the return value of cxgb4_update_mac_filt(),
which is wrong.

When trying to update to another MAC address later, the wrong MPS TCAM
index is sent to firmware, which causes firmware to return error,
because it's not the same MPS TCAM index that firmware had sent
earlier to driver.

So, fix by removing the wrong overwrite being done after call to
cxgb4_update_mac_filt().

Fixes: 3f8cfd0d95e6 ("cxgb4/cxgb4vf: Program hash region for {t4/t4vf}_change_mac()")
Signed-off-by: Herat Ramani <herat@chelsio.com>
Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 97f90edbc068..6767c73c87a1 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -3138,7 +3138,6 @@ static int cxgb_set_mac_addr(struct net_device *dev, void *p)
 		return ret;
 
 	memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);
-	pi->xact_addr_filt = ret;
 	return 0;
 }
 
-- 
2.20.1


From e60240bdfca2b07dfe3c96bad2ef392815125366 Mon Sep 17 00:00:00 2001
From: Jarod Wilson <jarod@redhat.com>
Date: Mon, 30 Mar 2020 11:22:19 -0400
Subject: [PATCH 02/15] ipv6: don't auto-add link-local address to lag ports

[ Upstream commit 744fdc8233f6aa9582ce08a51ca06e59796a3196 ]

Bonding slave and team port devices should not have link-local addresses
automatically added to them, as it can interfere with openvswitch being
able to properly add tc ingress.

Basic reproducer, courtesy of Marcelo:

$ ip link add name bond0 type bond
$ ip link set dev ens2f0np0 master bond0
$ ip link set dev ens2f1np2 master bond0
$ ip link set dev bond0 up
$ ip a s
1: lo: <LOOPBACK,UP,LOWER_UP> mtu 65536 qdisc noqueue state UNKNOWN
group default qlen 1000
    link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00
    inet 127.0.0.1/8 scope host lo
       valid_lft forever preferred_lft forever
    inet6 ::1/128 scope host
       valid_lft forever preferred_lft forever
2: ens2f0np0: <BROADCAST,MULTICAST,SLAVE,UP,LOWER_UP> mtu 1500 qdisc
mq master bond0 state UP group default qlen 1000
    link/ether 00:0f:53:2f:ea:40 brd ff:ff:ff:ff:ff:ff
5: ens2f1np2: <NO-CARRIER,BROADCAST,MULTICAST,SLAVE,UP> mtu 1500 qdisc
mq master bond0 state DOWN group default qlen 1000
    link/ether 00:0f:53:2f:ea:40 brd ff:ff:ff:ff:ff:ff
11: bond0: <BROADCAST,MULTICAST,MASTER,UP,LOWER_UP> mtu 1500 qdisc
noqueue state UP group default qlen 1000
    link/ether 00:0f:53:2f:ea:40 brd ff:ff:ff:ff:ff:ff
    inet6 fe80::20f:53ff:fe2f:ea40/64 scope link
       valid_lft forever preferred_lft forever

(above trimmed to relevant entries, obviously)

$ sysctl net.ipv6.conf.ens2f0np0.addr_gen_mode=0
net.ipv6.conf.ens2f0np0.addr_gen_mode = 0
$ sysctl net.ipv6.conf.ens2f1np2.addr_gen_mode=0
net.ipv6.conf.ens2f1np2.addr_gen_mode = 0

$ ip a l ens2f0np0
2: ens2f0np0: <BROADCAST,MULTICAST,SLAVE,UP,LOWER_UP> mtu 1500 qdisc
mq master bond0 state UP group default qlen 1000
    link/ether 00:0f:53:2f:ea:40 brd ff:ff:ff:ff:ff:ff
    inet6 fe80::20f:53ff:fe2f:ea40/64 scope link tentative
       valid_lft forever preferred_lft forever
$ ip a l ens2f1np2
5: ens2f1np2: <NO-CARRIER,BROADCAST,MULTICAST,SLAVE,UP> mtu 1500 qdisc
mq master bond0 state DOWN group default qlen 1000
    link/ether 00:0f:53:2f:ea:40 brd ff:ff:ff:ff:ff:ff
    inet6 fe80::20f:53ff:fe2f:ea40/64 scope link tentative
       valid_lft forever preferred_lft forever

Looks like addrconf_sysctl_addr_gen_mode() bypasses the original "is
this a slave interface?" check added by commit c2edacf80e15, and
results in an address getting added, while w/the proposed patch added,
no address gets added. This simply adds the same gating check to another
code path, and thus should prevent the same devices from erroneously
obtaining an ipv6 link-local address.

Fixes: d35a00b8e33d ("net/ipv6: allow sysctl to change link-local address generation mode")
Reported-by: Moshe Levi <moshele@mellanox.com>
CC: Stephen Hemminger <stephen@networkplumber.org>
CC: Marcelo Ricardo Leitner <mleitner@redhat.com>
CC: netdev@vger.kernel.org
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 46d614b611db..2a8175de8578 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3296,6 +3296,10 @@ static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route)
 	if (netif_is_l3_master(idev->dev))
 		return;
 
+	/* no link local addresses on devices flagged as slaves */
+	if (idev->dev->flags & IFF_SLAVE)
+		return;
+
 	ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0);
 
 	switch (idev->cnf.addr_gen_mode) {
-- 
2.20.1


From 57094bfd0cec89e18a3e2daacacdfab597aec05b Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Sat, 4 Apr 2020 14:35:17 -0700
Subject: [PATCH 03/15] net: dsa: bcm_sf2: Do not register slave MDIO bus with
 OF

[ Upstream commit 536fab5bf5826404534a6c271f622ad2930d9119 ]

We were registering our slave MDIO bus with OF and doing so with
assigning the newly created slave_mii_bus of_node to the master MDIO bus
controller node. This is a bad thing to do for a number of reasons:

- we are completely lying about the slave MII bus is arranged and yet we
  still want to control which MDIO devices it probes. It was attempted
  before to play tricks with the bus_mask to perform that:
  https://www.spinics.net/lists/netdev/msg429420.html but the approach
  was rightfully rejected

- the device_node reference counting is messed up and we are effectively
  doing a double probe on the devices we already probed using the
  master, this messes up all resources reference counts (such as clocks)

The proper fix for this as indicated by David in his reply to the
thread above is to use a platform data style registration so as to
control exactly which devices we probe:
https://www.spinics.net/lists/netdev/msg430083.html

By using mdiobus_register(), our slave_mii_bus->phy_mask value is used
as intended, and all the PHY addresses that must be redirected towards
our slave MDIO bus is happening while other addresses get redirected
towards the master MDIO bus.

Fixes: 461cd1b03e32 ("net: dsa: bcm_sf2: Register our slave MDIO bus")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Vivien Didelot <vivien.didelot@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index b0f5280a83cb..4481afd323a9 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -472,7 +472,7 @@ static int bcm_sf2_mdio_register(struct dsa_switch *ds)
 	priv->slave_mii_bus->parent = ds->dev->parent;
 	priv->slave_mii_bus->phy_mask = ~priv->indir_phy_mask;
 
-	err = of_mdiobus_register(priv->slave_mii_bus, dn);
+	err = mdiobus_register(priv->slave_mii_bus);
 	if (err && dn)
 		of_node_put(dn);
 
-- 
2.20.1


From cabf51a4928d267c27a36ee45dbe58acb6cbb165 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Sun, 5 Apr 2020 13:00:30 -0700
Subject: [PATCH 04/15] net: dsa: bcm_sf2: Ensure correct sub-node is parsed

[ Upstream commit afa3b592953bfaecfb4f2f335ec5f935cff56804 ]

When the bcm_sf2 was converted into a proper platform device driver and
used the new dsa_register_switch() interface, we would still be parsing
the legacy DSA node that contained all the port information since the
platform firmware has intentionally maintained backward and forward
compatibility to client programs. Ensure that we do parse the correct
node, which is "ports" per the revised DSA binding.

Fixes: d9338023fb8e ("net: dsa: bcm_sf2: Make it a real platform device driver")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Vivien Didelot <vivien.didelot@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 4481afd323a9..e93c81c4062e 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -1069,6 +1069,7 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev)
 	const struct bcm_sf2_of_data *data;
 	struct b53_platform_data *pdata;
 	struct dsa_switch_ops *ops;
+	struct device_node *ports;
 	struct bcm_sf2_priv *priv;
 	struct b53_device *dev;
 	struct dsa_switch *ds;
@@ -1136,7 +1137,11 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev)
 	set_bit(0, priv->cfp.used);
 	set_bit(0, priv->cfp.unique);
 
-	bcm_sf2_identify_ports(priv, dn->child);
+	ports = of_find_node_by_name(dn, "ports");
+	if (ports) {
+		bcm_sf2_identify_ports(priv, ports);
+		of_node_put(ports);
+	}
 
 	priv->irq0 = irq_of_parse_and_map(dn, 0);
 	priv->irq1 = irq_of_parse_and_map(dn, 1);
-- 
2.20.1


From 1276f0a60724f553e420bd1ba61ed437ee0fe8f8 Mon Sep 17 00:00:00 2001
From: Chuanhong Guo <gch981213@gmail.com>
Date: Fri, 3 Apr 2020 19:28:24 +0800
Subject: [PATCH 05/15] net: dsa: mt7530: fix null pointer dereferencing in
 port5 setup
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 0452800f6db4ed0a42ffb15867c0acfd68829f6a ]

The 2nd gmac of mediatek soc ethernet may not be connected to a PHY
and a phy-handle isn't always available.
Unfortunately, mt7530 dsa driver assumes that the 2nd gmac is always
connected to switch port 5 and setup mt7530 according to phy address
of 2nd gmac node, causing null pointer dereferencing when phy-handle
isn't defined in dts.
This commit fix this setup code by checking return value of
of_parse_phandle before using it.

Fixes: 38f790a80560 ("net: dsa: mt7530: Add support for port 5")
Signed-off-by: Chuanhong Guo <gch981213@gmail.com>
Reviewed-by: Vivien Didelot <vivien.didelot@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Tested-by: René van Dorst <opensource@vdorst.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mt7530.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index 7cbd1bd4c5a6..9b0de2852c69 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -1356,6 +1356,9 @@ mt7530_setup(struct dsa_switch *ds)
 				continue;
 
 			phy_node = of_parse_phandle(mac_np, "phy-handle", 0);
+			if (!phy_node)
+				continue;
+
 			if (phy_node->parent == priv->dev->of_node->parent) {
 				ret = of_get_phy_mode(mac_np, &interface);
 				if (ret && ret != -ENODEV)
-- 
2.20.1


From 2b5879dd78697a59995cf3fa1f66ca53957efd78 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Fri, 3 Apr 2020 09:53:25 +0200
Subject: [PATCH 06/15] net: phy: micrel: kszphy_resume(): add delay after
 genphy_resume() before accessing PHY registers

[ Upstream commit 6110dff776f7fa65c35850ef65b41d3b39e2fac2 ]

After the power-down bit is cleared, the chip internally triggers a
global reset. According to the KSZ9031 documentation, we have to wait at
least 1ms for the reset to finish.

If the chip is accessed during reset, read will return 0xffff, while
write will be ignored. Depending on the system performance and MDIO bus
speed, we may or may not run in to this issue.

This bug was discovered on an iMX6QP system with KSZ9031 PHY and
attached PHY interrupt line. If IRQ was used, the link status update was
lost. In polling mode, the link status update was always correct.

The investigation showed, that during a read-modify-write access, the
read returned 0xffff (while the chip was still in reset) and
corresponding write hit the chip _after_ reset and triggered (due to the
0xffff) another reset in an undocumented bit (register 0x1f, bit 1),
resulting in the next write being lost due to the new reset cycle.

This patch fixes the issue by adding a 1...2 ms sleep after the
genphy_resume().

Fixes: 836384d2501d ("net: phy: micrel: Add specific suspend")
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/micrel.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 63dedec0433d..51b64f087717 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -25,6 +25,7 @@
 #include <linux/micrel_phy.h>
 #include <linux/of.h>
 #include <linux/clk.h>
+#include <linux/delay.h>
 
 /* Operation Mode Strap Override */
 #define MII_KSZPHY_OMSO				0x16
@@ -902,6 +903,12 @@ static int kszphy_resume(struct phy_device *phydev)
 
 	genphy_resume(phydev);
 
+	/* After switching from power-down to normal mode, an internal global
+	 * reset is automatically generated. Wait a minimum of 1 ms before
+	 * read/write access to the PHY registers.
+	 */
+	usleep_range(1000, 2000);
+
 	ret = kszphy_config_reset(phydev);
 	if (ret)
 		return ret;
-- 
2.20.1


From 68ac52734deaac9d9bda3d721726995925effeaa Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sat, 28 Mar 2020 12:12:59 -0700
Subject: [PATCH 07/15] net_sched: add a temporary refcnt for struct
 tcindex_data

[ Upstream commit 304e024216a802a7dc8ba75d36de82fa136bbf3e ]

Although we intentionally use an ordered workqueue for all tc
filter works, the ordering is not guaranteed by RCU work,
given that tcf_queue_work() is esstenially a call_rcu().

This problem is demostrated by Thomas:

  CPU 0:
    tcf_queue_work()
      tcf_queue_work(&r->rwork, tcindex_destroy_rexts_work);

  -> Migration to CPU 1

  CPU 1:
     tcf_queue_work(&p->rwork, tcindex_destroy_work);

so the 2nd work could be queued before the 1st one, which leads
to a free-after-free.

Enforcing this order in RCU work is hard as it requires to change
RCU code too. Fortunately we can workaround this problem in tcindex
filter by taking a temporary refcnt, we only refcnt it right before
we begin to destroy it. This simplifies the code a lot as a full
refcnt requires much more changes in tcindex_set_parms().

Reported-by: syzbot+46f513c3033d592409d2@syzkaller.appspotmail.com
Fixes: 3d210534cc93 ("net_sched: fix a race condition in tcindex_destroy()")
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Paul E. McKenney <paulmck@kernel.org>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Reviewed-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_tcindex.c | 44 +++++++++++++++++++++++++++++++++++------
 1 file changed, 38 insertions(+), 6 deletions(-)

diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 9904299424a1..065345832a69 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -11,6 +11,7 @@
 #include <linux/skbuff.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
+#include <linux/refcount.h>
 #include <net/act_api.h>
 #include <net/netlink.h>
 #include <net/pkt_cls.h>
@@ -26,9 +27,12 @@
 #define DEFAULT_HASH_SIZE	64	/* optimized for diffserv */
 
 
+struct tcindex_data;
+
 struct tcindex_filter_result {
 	struct tcf_exts		exts;
 	struct tcf_result	res;
+	struct tcindex_data	*p;
 	struct rcu_work		rwork;
 };
 
@@ -49,6 +53,7 @@ struct tcindex_data {
 	u32 hash;		/* hash table size; 0 if undefined */
 	u32 alloc_hash;		/* allocated size */
 	u32 fall_through;	/* 0: only classify if explicit match */
+	refcount_t refcnt;	/* a temporary refcnt for perfect hash */
 	struct rcu_work rwork;
 };
 
@@ -57,6 +62,20 @@ static inline int tcindex_filter_is_set(struct tcindex_filter_result *r)
 	return tcf_exts_has_actions(&r->exts) || r->res.classid;
 }
 
+static void tcindex_data_get(struct tcindex_data *p)
+{
+	refcount_inc(&p->refcnt);
+}
+
+static void tcindex_data_put(struct tcindex_data *p)
+{
+	if (refcount_dec_and_test(&p->refcnt)) {
+		kfree(p->perfect);
+		kfree(p->h);
+		kfree(p);
+	}
+}
+
 static struct tcindex_filter_result *tcindex_lookup(struct tcindex_data *p,
 						    u16 key)
 {
@@ -141,6 +160,7 @@ static void __tcindex_destroy_rexts(struct tcindex_filter_result *r)
 {
 	tcf_exts_destroy(&r->exts);
 	tcf_exts_put_net(&r->exts);
+	tcindex_data_put(r->p);
 }
 
 static void tcindex_destroy_rexts_work(struct work_struct *work)
@@ -212,6 +232,8 @@ static int tcindex_delete(struct tcf_proto *tp, void *arg, bool *last,
 		else
 			__tcindex_destroy_fexts(f);
 	} else {
+		tcindex_data_get(p);
+
 		if (tcf_exts_get_net(&r->exts))
 			tcf_queue_work(&r->rwork, tcindex_destroy_rexts_work);
 		else
@@ -228,9 +250,7 @@ static void tcindex_destroy_work(struct work_struct *work)
 					      struct tcindex_data,
 					      rwork);
 
-	kfree(p->perfect);
-	kfree(p->h);
-	kfree(p);
+	tcindex_data_put(p);
 }
 
 static inline int
@@ -248,9 +268,11 @@ static const struct nla_policy tcindex_policy[TCA_TCINDEX_MAX + 1] = {
 };
 
 static int tcindex_filter_result_init(struct tcindex_filter_result *r,
+				      struct tcindex_data *p,
 				      struct net *net)
 {
 	memset(r, 0, sizeof(*r));
+	r->p = p;
 	return tcf_exts_init(&r->exts, net, TCA_TCINDEX_ACT,
 			     TCA_TCINDEX_POLICE);
 }
@@ -290,6 +312,7 @@ static int tcindex_alloc_perfect_hash(struct net *net, struct tcindex_data *cp)
 				    TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
 		if (err < 0)
 			goto errout;
+		cp->perfect[i].p = cp;
 	}
 
 	return 0;
@@ -334,6 +357,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	cp->alloc_hash = p->alloc_hash;
 	cp->fall_through = p->fall_through;
 	cp->tp = tp;
+	refcount_set(&cp->refcnt, 1); /* Paired with tcindex_destroy_work() */
 
 	if (tb[TCA_TCINDEX_HASH])
 		cp->hash = nla_get_u32(tb[TCA_TCINDEX_HASH]);
@@ -366,7 +390,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	}
 	cp->h = p->h;
 
-	err = tcindex_filter_result_init(&new_filter_result, net);
+	err = tcindex_filter_result_init(&new_filter_result, cp, net);
 	if (err < 0)
 		goto errout_alloc;
 	if (old_r)
@@ -434,7 +458,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 			goto errout_alloc;
 		f->key = handle;
 		f->next = NULL;
-		err = tcindex_filter_result_init(&f->result, net);
+		err = tcindex_filter_result_init(&f->result, cp, net);
 		if (err < 0) {
 			kfree(f);
 			goto errout_alloc;
@@ -447,7 +471,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	}
 
 	if (old_r && old_r != r) {
-		err = tcindex_filter_result_init(old_r, net);
+		err = tcindex_filter_result_init(old_r, cp, net);
 		if (err < 0) {
 			kfree(f);
 			goto errout_alloc;
@@ -571,6 +595,14 @@ static void tcindex_destroy(struct tcf_proto *tp, bool rtnl_held,
 		for (i = 0; i < p->hash; i++) {
 			struct tcindex_filter_result *r = p->perfect + i;
 
+			/* tcf_queue_work() does not guarantee the ordering we
+			 * want, so we have to take this refcnt temporarily to
+			 * ensure 'p' is freed after all tcindex_filter_result
+			 * here. Imperfect hash does not need this, because it
+			 * uses linked lists rather than an array.
+			 */
+			tcindex_data_get(p);
+
 			tcf_unbind_filter(tp, &r->res);
 			if (tcf_exts_get_net(&r->exts))
 				tcf_queue_work(&r->rwork,
-- 
2.20.1


From bdba718036e168f528b277e1c276b65341deae8e Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 2 Apr 2020 20:58:51 -0700
Subject: [PATCH 08/15] net_sched: fix a missing refcnt in tcindex_init()

[ Upstream commit a8eab6d35e22f4f21471f16147be79529cd6aaf7 ]

The initial refcnt of struct tcindex_data should be 1,
it is clear that I forgot to set it to 1 in tcindex_init().
This leads to a dec-after-zero warning.

Reported-by: syzbot+8325e509a1bf83ec741d@syzkaller.appspotmail.com
Fixes: 304e024216a8 ("net_sched: add a temporary refcnt for struct tcindex_data")
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Cc: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_tcindex.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 065345832a69..61e95029c18f 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -151,6 +151,7 @@ static int tcindex_init(struct tcf_proto *tp)
 	p->mask = 0xffff;
 	p->hash = DEFAULT_HASH_SIZE;
 	p->fall_through = 1;
+	refcount_set(&p->refcnt, 1); /* Paired with tcindex_destroy_work() */
 
 	rcu_assign_pointer(tp->root, p);
 	return 0;
-- 
2.20.1


From bc02770d6cf99106569945a53252084e8d90e680 Mon Sep 17 00:00:00 2001
From: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
Date: Fri, 3 Apr 2020 10:23:29 +0800
Subject: [PATCH 09/15] net: stmmac: dwmac1000: fix out-of-bounds mac address
 reg setting

[ Upstream commit 3e1221acf6a8f8595b5ce354bab4327a69d54d18 ]

Commit 9463c4455900 ("net: stmmac: dwmac1000: Clear unused address
entries") cleared the unused mac address entries, but introduced an
out-of bounds mac address register programming bug -- After setting
the secondary unicast mac addresses, the "reg" value has reached
netdev_uc_count() + 1, thus we should only clear address entries
if (addr < perfect_addr_number)

Fixes: 9463c4455900 ("net: stmmac: dwmac1000: Clear unused address entries")
Signed-off-by: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
index 542784300620..efc6ec1b8027 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
@@ -207,7 +207,7 @@ static void dwmac1000_set_filter(struct mac_device_info *hw,
 			reg++;
 		}
 
-		while (reg <= perfect_addr_number) {
+		while (reg < perfect_addr_number) {
 			writel(0, ioaddr + GMAC_ADDR_HIGH(reg));
 			writel(0, ioaddr + GMAC_ADDR_LOW(reg));
 			reg++;
-- 
2.20.1


From d09f80ef65b5bcb6d4ade373f36852c124175d26 Mon Sep 17 00:00:00 2001
From: Richard Palethorpe <rpalethorpe@suse.com>
Date: Wed, 1 Apr 2020 12:06:39 +0200
Subject: [PATCH 10/15] slcan: Don't transmit uninitialized stack data in
 padding

[ Upstream commit b9258a2cece4ec1f020715fe3554bc2e360f6264 ]

struct can_frame contains some padding which is not explicitly zeroed in
slc_bump. This uninitialized data will then be transmitted if the stack
initialization hardening feature is not enabled (CONFIG_INIT_STACK_ALL).

This commit just zeroes the whole struct including the padding.

Signed-off-by: Richard Palethorpe <rpalethorpe@suse.com>
Fixes: a1044e36e457 ("can: add slcan driver for serial/USB-serial CAN adapters")
Reviewed-by: Kees Cook <keescook@chromium.org>
Cc: linux-can@vger.kernel.org
Cc: netdev@vger.kernel.org
Cc: security@kernel.org
Cc: wg@grandegger.com
Cc: mkl@pengutronix.de
Cc: davem@davemloft.net
Acked-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/can/slcan.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c
index a3664281a33f..4dfa459ef5c7 100644
--- a/drivers/net/can/slcan.c
+++ b/drivers/net/can/slcan.c
@@ -148,7 +148,7 @@ static void slc_bump(struct slcan *sl)
 	u32 tmpid;
 	char *cmd = sl->rbuff;
 
-	cf.can_id = 0;
+	memset(&cf, 0, sizeof(cf));
 
 	switch (*cmd) {
 	case 'r':
@@ -187,8 +187,6 @@ static void slc_bump(struct slcan *sl)
 	else
 		return;
 
-	*(u64 *) (&cf.data) = 0; /* clear payload */
-
 	/* RTR frames may have a dlc > 0 but they never have any data bytes */
 	if (!(cf.can_id & CAN_RTR_FLAG)) {
 		for (i = 0; i < cf.can_dlc; i++) {
-- 
2.20.1


From 1db67a37f9227dfaab5461654977b9aaba3723d2 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Fri, 3 Apr 2020 16:13:21 +0100
Subject: [PATCH 11/15] tun: Don't put_page() for all negative return values
 from XDP program

[ Upstream commit bee348907d19d654e8524d3a946dcd25b693aa7e ]

When an XDP program is installed, tun_build_skb() grabs a reference to
the current page fragment page if the program returns XDP_REDIRECT or
XDP_TX. However, since tun_xdp_act() passes through negative return
values from the XDP program, it is possible to trigger the error path by
mistake and accidentally drop a reference to the fragments page without
taking one, leading to a spurious free. This is believed to be the cause
of some KASAN use-after-free reports from syzbot [1], although without a
reproducer it is not possible to confirm whether this patch fixes the
problem.

Ensure that we only drop a reference to the fragments page if the XDP
transmit or redirect operations actually fail.

[1] https://syzkaller.appspot.com/bug?id=e76a6af1be4acd727ff6bbca669833f98cbf5d95

Cc: "David S. Miller" <davem@davemloft.net>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
CC: Eric Dumazet <edumazet@google.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Fixes: 8ae1aff0b331 ("tuntap: split out XDP logic")
Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 650c937ed56b..9de9b7d8aedd 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1715,8 +1715,12 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 			alloc_frag->offset += buflen;
 		}
 		err = tun_xdp_act(tun, xdp_prog, &xdp, act);
-		if (err < 0)
-			goto err_xdp;
+		if (err < 0) {
+			if (act == XDP_REDIRECT || act == XDP_TX)
+				put_page(alloc_frag->page);
+			goto out;
+		}
+
 		if (err == XDP_REDIRECT)
 			xdp_do_flush();
 		if (err != XDP_PASS)
@@ -1730,8 +1734,6 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 
 	return __tun_build_skb(tfile, alloc_frag, buf, buflen, len, pad);
 
-err_xdp:
-	put_page(alloc_frag->page);
 out:
 	rcu_read_unlock();
 	local_bh_enable();
-- 
2.20.1


From 889f5192b2ae1b016e36e85d5d074652eb5944a5 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Sun, 5 Apr 2020 09:50:22 +0300
Subject: [PATCH 12/15] mlxsw: spectrum_flower: Do not stop at
 FLOW_ACTION_VLAN_MANGLE

[ Upstream commit ccfc569347f870830e7c7cf854679a06cf9c45b5 ]

The handler for FLOW_ACTION_VLAN_MANGLE ends by returning whatever the
lower-level function that it calls returns. If there are more actions lined
up after this action, those are never offloaded. Fix by only bailing out
when the called function returns an error.

Fixes: a150201a70da ("mlxsw: spectrum: Add support for vlan modify TC action")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
index b607919c8ad0..498de6ef6870 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
@@ -123,9 +123,12 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 			u8 prio = act->vlan.prio;
 			u16 vid = act->vlan.vid;
 
-			return mlxsw_sp_acl_rulei_act_vlan(mlxsw_sp, rulei,
-							   act->id, vid,
-							   proto, prio, extack);
+			err = mlxsw_sp_acl_rulei_act_vlan(mlxsw_sp, rulei,
+							  act->id, vid,
+							  proto, prio, extack);
+			if (err)
+				return err;
+			break;
 			}
 		default:
 			NL_SET_ERR_MSG_MOD(extack, "Unsupported action");
-- 
2.20.1


From d5e609d4b0bddc2ed7badb20373ded2f5bb41f17 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 4 Apr 2020 23:48:45 +0200
Subject: [PATCH 13/15] r8169: change back SG and TSO to be disabled by default

[ Upstream commit 95099c569a9fdbe186a27447dfa8a5a0562d4b7f ]

There has been a number of reports that using SG/TSO on different chip
versions results in tx timeouts. However for a lot of people SG/TSO
works fine. Therefore disable both features by default, but allow users
to enable them. Use at own risk!

Fixes: 93681cd7d94f ("r8169: enable HW csum and TSO")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
---
 drivers/net/ethernet/realtek/r8169_main.c | 34 +++++++++++------------
 1 file changed, 16 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 791d99b9e1cf..6b633e9d76da 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -5549,12 +5549,10 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	netif_napi_add(dev, &tp->napi, rtl8169_poll, NAPI_POLL_WEIGHT);
 
-	dev->features |= NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO |
-		NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_TX |
-		NETIF_F_HW_VLAN_CTAG_RX;
-	dev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO |
-		NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_TX |
-		NETIF_F_HW_VLAN_CTAG_RX;
+	dev->features |= NETIF_F_IP_CSUM | NETIF_F_RXCSUM |
+			 NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX;
+	dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_RXCSUM |
+			   NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX;
 	dev->vlan_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO |
 		NETIF_F_HIGHDMA;
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
@@ -5572,25 +5570,25 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		dev->hw_features &= ~NETIF_F_HW_VLAN_CTAG_RX;
 
 	if (rtl_chip_supports_csum_v2(tp)) {
-		dev->hw_features |= NETIF_F_IPV6_CSUM | NETIF_F_TSO6;
-		dev->features |= NETIF_F_IPV6_CSUM | NETIF_F_TSO6;
+		dev->hw_features |= NETIF_F_IPV6_CSUM;
+		dev->features |= NETIF_F_IPV6_CSUM;
+	}
+
+	/* There has been a number of reports that using SG/TSO results in
+	 * tx timeouts. However for a lot of people SG/TSO works fine.
+	 * Therefore disable both features by default, but allow users to
+	 * enable them. Use at own risk!
+	 */
+	if (rtl_chip_supports_csum_v2(tp)) {
+		dev->hw_features |= NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6;
 		dev->gso_max_size = RTL_GSO_MAX_SIZE_V2;
 		dev->gso_max_segs = RTL_GSO_MAX_SEGS_V2;
 	} else {
+		dev->hw_features |= NETIF_F_SG | NETIF_F_TSO;
 		dev->gso_max_size = RTL_GSO_MAX_SIZE_V1;
 		dev->gso_max_segs = RTL_GSO_MAX_SEGS_V1;
 	}
 
-	/* RTL8168e-vl and one RTL8168c variant are known to have a
-	 * HW issue with TSO.
-	 */
-	if (tp->mac_version == RTL_GIGA_MAC_VER_34 ||
-	    tp->mac_version == RTL_GIGA_MAC_VER_22) {
-		dev->vlan_features &= ~(NETIF_F_ALL_TSO | NETIF_F_SG);
-		dev->hw_features &= ~(NETIF_F_ALL_TSO | NETIF_F_SG);
-		dev->features &= ~(NETIF_F_ALL_TSO | NETIF_F_SG);
-	}
-
 	dev->hw_features |= NETIF_F_RXALL;
 	dev->hw_features |= NETIF_F_RXFCS;
 
-- 
2.20.1


From bfb82552fefbf7b99bb72845ac6236edf4852652 Mon Sep 17 00:00:00 2001
From: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Date: Wed, 1 Apr 2020 01:17:01 +0530
Subject: [PATCH 14/15] cxgb4: free MQPRIO resources in shutdown path

[ Upstream commit cef8dac96bc108633f5090bb3a9988d734dc1ee0 ]

Perform missing MQPRIO resource cleanup in PCI shutdown path. Also,
fix MQPRIO MSIX bitmap leak in resource cleanup.

Fixes: b1396c2bd675 ("cxgb4: parse and configure TC-MQPRIO offload")
Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/chelsio/cxgb4/cxgb4_main.c   |  4 ++++
 .../ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c  | 23 +++++++++++++++++++
 .../ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.h  |  1 +
 3 files changed, 28 insertions(+)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 6767c73c87a1..b0bdf7233f0c 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -6681,6 +6681,10 @@ static void shutdown_one(struct pci_dev *pdev)
 			if (adapter->port[i]->reg_state == NETREG_REGISTERED)
 				cxgb_close(adapter->port[i]);
 
+		rtnl_lock();
+		cxgb4_mqprio_stop_offload(adapter);
+		rtnl_unlock();
+
 		if (is_uld(adapter)) {
 			detach_ulds(adapter);
 			t4_uld_clean_up(adapter);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c
index ec3eb45ee3b4..e6af4906d674 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c
@@ -301,6 +301,7 @@ static void cxgb4_mqprio_free_hw_resources(struct net_device *dev)
 			cxgb4_clear_msix_aff(eorxq->msix->vec,
 					     eorxq->msix->aff_mask);
 			free_irq(eorxq->msix->vec, &eorxq->rspq);
+			cxgb4_free_msix_idx_in_bmap(adap, eorxq->msix->idx);
 		}
 
 		free_rspq_fl(adap, &eorxq->rspq, &eorxq->fl);
@@ -611,6 +612,28 @@ int cxgb4_setup_tc_mqprio(struct net_device *dev,
 	return ret;
 }
 
+void cxgb4_mqprio_stop_offload(struct adapter *adap)
+{
+	struct cxgb4_tc_port_mqprio *tc_port_mqprio;
+	struct net_device *dev;
+	u8 i;
+
+	if (!adap->tc_mqprio || !adap->tc_mqprio->port_mqprio)
+		return;
+
+	for_each_port(adap, i) {
+		dev = adap->port[i];
+		if (!dev)
+			continue;
+
+		tc_port_mqprio = &adap->tc_mqprio->port_mqprio[i];
+		if (!tc_port_mqprio->mqprio.qopt.num_tc)
+			continue;
+
+		cxgb4_mqprio_disable_offload(dev);
+	}
+}
+
 int cxgb4_init_tc_mqprio(struct adapter *adap)
 {
 	struct cxgb4_tc_port_mqprio *tc_port_mqprio, *port_mqprio;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.h
index c532f1ef8451..ff8794132b22 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.h
@@ -38,6 +38,7 @@ struct cxgb4_tc_mqprio {
 
 int cxgb4_setup_tc_mqprio(struct net_device *dev,
 			  struct tc_mqprio_qopt_offload *mqprio);
+void cxgb4_mqprio_stop_offload(struct adapter *adap);
 int cxgb4_init_tc_mqprio(struct adapter *adap);
 void cxgb4_cleanup_tc_mqprio(struct adapter *adap);
 #endif /* __CXGB4_TC_MQPRIO_H__ */
-- 
2.20.1


From ad2aade61bcee05f35d9e2d89da9359db2c2b7a4 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Wed, 1 Apr 2020 11:57:32 +0200
Subject: [PATCH 15/15] net: phy: at803x: fix clock sink configuration on
 ATH8030 and ATH8035

[ Upstream commit b1f4c209d84057b6d40b939b6e4404854271d797 ]

The masks in priv->clk_25m_reg and priv->clk_25m_mask are one-bits-set
for the values that comprise the fields, not zero-bits-set.

This patch fixes the clock frequency configuration for ATH8030 and
ATH8035 Atheros PHYs by removing the erroneous "~".

To reproduce this bug, configure the PHY  with the device tree binding
"qca,clk-out-frequency" and remove the machine specific PHY fixups.

Fixes: 2f664823a47021 ("net: phy: at803x: add device tree binding")
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reported-by: Russell King <rmk+kernel@armlinux.org.uk>
Reviewed-by: Russell King <rmk+kernel@armlinux.org.uk>
Tested-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/at803x.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c
index 481cf48c9b9e..31f731e6df72 100644
--- a/drivers/net/phy/at803x.c
+++ b/drivers/net/phy/at803x.c
@@ -425,8 +425,8 @@ static int at803x_parse_dt(struct phy_device *phydev)
 		 */
 		if (at803x_match_phy_id(phydev, ATH8030_PHY_ID) ||
 		    at803x_match_phy_id(phydev, ATH8035_PHY_ID)) {
-			priv->clk_25m_reg &= ~AT8035_CLK_OUT_MASK;
-			priv->clk_25m_mask &= ~AT8035_CLK_OUT_MASK;
+			priv->clk_25m_reg &= AT8035_CLK_OUT_MASK;
+			priv->clk_25m_mask &= AT8035_CLK_OUT_MASK;
 		}
 	}
 
-- 
2.20.1


[-- Attachment #4: 0001-net-phy-realtek-fix-handling-of-RTL8105e-integrated-PHY.patch --]
[-- Type: Text/X-Patch, Size: 1730 bytes --]

Subject: [PATCH 5.4 net] net: phy: realtek: fix handling of RTL8105e-integrated PHY
From: Heiner Kallweit <hkallweit1@gmail.com>
To: David Miller <davem@davemloft.net>,
 Realtek linux nic maintainers <nic_swsd@realtek.com>
Cc: "netdev@vger.kernel.org" <netdev@vger.kernel.org>
Date: Wed, 8 Apr 2020 00:01:42 +0200
User-Agent: Mozilla/5.0 (Windows NT 10.0; WOW64; rv:68.0) Gecko/20100101 Thunderbird/68.6.0

[ No applicable upstream commit ]

After the referenced fix it turned out that one particular RTL8168
chip version (RTL8105e) does not work on 5.4 because no dedicated PHY
driver exists. Adding this PHY driver was done for fixing a different
issue for versions from 5.5 already. I re-send the same change for 5.4
because the commit message differs.

Fixes: 2e8c339b4946 ("r8169: fix PHY driver check on platforms w/o module softdeps")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
---
Please apply on 5.4 only.
---
 drivers/net/phy/realtek.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c
index c76df51dd..879ca37c8 100644
--- a/drivers/net/phy/realtek.c
+++ b/drivers/net/phy/realtek.c
@@ -456,6 +456,15 @@ static struct phy_driver realtek_drvs[] = {
 		.resume		= genphy_resume,
 		.read_page	= rtl821x_read_page,
 		.write_page	= rtl821x_write_page,
+	}, {
+		PHY_ID_MATCH_MODEL(0x001cc880),
+		.name		= "RTL8208 Fast Ethernet",
+		.read_mmd	= genphy_read_mmd_unsupported,
+		.write_mmd	= genphy_write_mmd_unsupported,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+		.read_page	= rtl821x_read_page,
+		.write_page	= rtl821x_write_page,
 	}, {
 		PHY_ID_MATCH_EXACT(0x001cc910),
 		.name		= "RTL8211 Gigabit Ethernet",
-- 
2.26.0

Re: [PATCHES] Networking

[Greg KH]

On Wed, Apr 08, 2020 at 03:05:48PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v5.5 and v5.6
> -stable, respectively.
> 
> Also, there is a Realtek PHY patch attached which should be queued up
> for v5.4.

All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 105 bytes --]


Please queue up the following networking bug fixes for
v5.5 and v5.6 -stable, respectively.

Thank you!

[-- Attachment #2: net_55.mbox --]
[-- Type: Application/Octet-Stream, Size: 57080 bytes --]

From 822cff7af249a9beadaa56195188a7377f1e755b Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 16 Apr 2020 17:57:40 +0200
Subject: [PATCH 01/19] amd-xgbe: Use __napi_schedule() in BH context

[ Upstream commit d518691cbd3be3dae218e05cca3f3fc9b2f1aa77 ]

The driver uses __napi_schedule_irqoff() which is fine as long as it is
invoked with disabled interrupts by everybody. Since the commit
mentioned below the driver may invoke xgbe_isr_task() in tasklet/softirq
context. This may lead to list corruption if another driver uses
__napi_schedule_irqoff() in IRQ context.

Use __napi_schedule() which safe to use from IRQ and softirq context.

Fixes: 85b85c853401d ("amd-xgbe: Re-issue interrupt if interrupt status not cleared")
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Acked-by: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe-drv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 98f8f2033154..3bd20f765120 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -514,7 +514,7 @@ static void xgbe_isr_task(unsigned long data)
 				xgbe_disable_rx_tx_ints(pdata);
 
 				/* Turn on polling */
-				__napi_schedule_irqoff(&pdata->napi);
+				__napi_schedule(&pdata->napi);
 			}
 		} else {
 			/* Don't clear Rx/Tx status if doing per channel DMA
-- 
2.20.1


From 1e4e21a89058b21e7907bb8b691c2274ac1d2f80 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Tue, 7 Apr 2020 13:23:21 +0000
Subject: [PATCH 02/19] hsr: check protocol version in hsr_newlink()

[ Upstream commit 4faab8c446def7667adf1f722456c2f4c304069c ]

In the current hsr code, only 0 and 1 protocol versions are valid.
But current hsr code doesn't check the version, which is received by
userspace.

Test commands:
    ip link add dummy0 type dummy
    ip link add dummy1 type dummy
    ip link add hsr0 type hsr slave1 dummy0 slave2 dummy1 version 4

In the test commands, version 4 is invalid.
So, the command should be failed.

After this patch, following error will occur.
"Error: hsr: Only versions 0..1 are supported."

Fixes: ee1c27977284 ("net/hsr: Added support for HSR v1")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/hsr/hsr_netlink.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c
index fae21c863b1f..55c0b2e872a5 100644
--- a/net/hsr/hsr_netlink.c
+++ b/net/hsr/hsr_netlink.c
@@ -61,10 +61,16 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev,
 	else
 		multicast_spec = nla_get_u8(data[IFLA_HSR_MULTICAST_SPEC]);
 
-	if (!data[IFLA_HSR_VERSION])
+	if (!data[IFLA_HSR_VERSION]) {
 		hsr_version = 0;
-	else
+	} else {
 		hsr_version = nla_get_u8(data[IFLA_HSR_VERSION]);
+		if (hsr_version > 1) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Only versions 0..1 are supported");
+			return -EINVAL;
+		}
+	}
 
 	return hsr_dev_finalize(dev, link, multicast_spec, hsr_version);
 }
-- 
2.20.1


From 1f35b8db8f1ceeca3cae1095b3bb57ef06ef146d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Michael=20Wei=C3=9F?= <michael.weiss@aisec.fraunhofer.de>
Date: Tue, 7 Apr 2020 13:11:48 +0200
Subject: [PATCH 03/19] l2tp: Allow management of tunnels and session in user
 namespace
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 2abe05234f2e892728c388169631e4b99f354c86 ]

Creation and management of L2TPv3 tunnels and session through netlink
requires CAP_NET_ADMIN. However, a process with CAP_NET_ADMIN in a
non-initial user namespace gets an EPERM due to the use of the
genetlink GENL_ADMIN_PERM flag. Thus, management of L2TP VPNs inside
an unprivileged container won't work.

We replaced the GENL_ADMIN_PERM by the GENL_UNS_ADMIN_PERM flag
similar to other network modules which also had this problem, e.g.,
openvswitch (commit 4a92602aa1cd "openvswitch: allow management from
inside user namespaces") and nl80211 (commit 5617c6cd6f844 "nl80211:
Allow privileged operations from user namespaces").

I tested this in the container runtime trustm3 (trustm3.github.io)
and was able to create l2tp tunnels and sessions in unpriviliged
(user namespaced) containers using a private network namespace.
For other runtimes such as docker or lxc this should work, too.

Signed-off-by: Michael Weiß <michael.weiss@aisec.fraunhofer.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_netlink.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index f5a9bdc4980c..ebb381c3f1b9 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -920,51 +920,51 @@ static const struct genl_ops l2tp_nl_ops[] = {
 		.cmd = L2TP_CMD_TUNNEL_CREATE,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_tunnel_create,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_TUNNEL_DELETE,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_tunnel_delete,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_TUNNEL_MODIFY,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_tunnel_modify,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_TUNNEL_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_tunnel_get,
 		.dumpit = l2tp_nl_cmd_tunnel_dump,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_SESSION_CREATE,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_session_create,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_SESSION_DELETE,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_session_delete,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_SESSION_MODIFY,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_session_modify,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_SESSION_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_session_get,
 		.dumpit = l2tp_nl_cmd_session_dump,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 };
 
-- 
2.20.1


From 12076db0bf2822a3ca59c8d8e8767065b0b0fd2a Mon Sep 17 00:00:00 2001
From: DENG Qingfang <dqfext@gmail.com>
Date: Tue, 14 Apr 2020 14:34:08 +0800
Subject: [PATCH 04/19] net: dsa: mt7530: fix tagged frames pass-through in
 VLAN-unaware mode
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit e045124e93995fe01e42ed530003ddba5d55db4f ]

In VLAN-unaware mode, the Egress Tag (EG_TAG) field in Port VLAN
Control register must be set to Consistent to let tagged frames pass
through as is, otherwise their tags will be stripped.

Fixes: 83163f7dca56 ("net: dsa: mediatek: add VLAN support for MT7530")
Signed-off-by: DENG Qingfang <dqfext@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Tested-by: René van Dorst <opensource@vdorst.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mt7530.c | 18 ++++++++++++------
 drivers/net/dsa/mt7530.h |  7 +++++++
 2 files changed, 19 insertions(+), 6 deletions(-)

diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index 936b9b65acca..44dea65d8117 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -857,8 +857,9 @@ mt7530_port_set_vlan_unaware(struct dsa_switch *ds, int port)
 	 */
 	mt7530_rmw(priv, MT7530_PCR_P(port), PCR_PORT_VLAN_MASK,
 		   MT7530_PORT_MATRIX_MODE);
-	mt7530_rmw(priv, MT7530_PVC_P(port), VLAN_ATTR_MASK,
-		   VLAN_ATTR(MT7530_VLAN_TRANSPARENT));
+	mt7530_rmw(priv, MT7530_PVC_P(port), VLAN_ATTR_MASK | PVC_EG_TAG_MASK,
+		   VLAN_ATTR(MT7530_VLAN_TRANSPARENT) |
+		   PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT));
 
 	for (i = 0; i < MT7530_NUM_PORTS; i++) {
 		if (dsa_is_user_port(ds, i) &&
@@ -874,8 +875,8 @@ mt7530_port_set_vlan_unaware(struct dsa_switch *ds, int port)
 	if (all_user_ports_removed) {
 		mt7530_write(priv, MT7530_PCR_P(MT7530_CPU_PORT),
 			     PCR_MATRIX(dsa_user_ports(priv->ds)));
-		mt7530_write(priv, MT7530_PVC_P(MT7530_CPU_PORT),
-			     PORT_SPEC_TAG);
+		mt7530_write(priv, MT7530_PVC_P(MT7530_CPU_PORT), PORT_SPEC_TAG
+			     | PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT));
 	}
 }
 
@@ -901,8 +902,9 @@ mt7530_port_set_vlan_aware(struct dsa_switch *ds, int port)
 	/* Set the port as a user port which is to be able to recognize VID
 	 * from incoming packets before fetching entry within the VLAN table.
 	 */
-	mt7530_rmw(priv, MT7530_PVC_P(port), VLAN_ATTR_MASK,
-		   VLAN_ATTR(MT7530_VLAN_USER));
+	mt7530_rmw(priv, MT7530_PVC_P(port), VLAN_ATTR_MASK | PVC_EG_TAG_MASK,
+		   VLAN_ATTR(MT7530_VLAN_USER) |
+		   PVC_EG_TAG(MT7530_VLAN_EG_DISABLED));
 }
 
 static void
@@ -1332,6 +1334,10 @@ mt7530_setup(struct dsa_switch *ds)
 			mt7530_cpu_port_enable(priv, i);
 		else
 			mt7530_port_disable(ds, i);
+
+		/* Enable consistent egress tag */
+		mt7530_rmw(priv, MT7530_PVC_P(i), PVC_EG_TAG_MASK,
+			   PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT));
 	}
 
 	/* Setup port 5 */
diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h
index ccb9da8cad0d..9a769c6b7700 100644
--- a/drivers/net/dsa/mt7530.h
+++ b/drivers/net/dsa/mt7530.h
@@ -167,9 +167,16 @@ enum mt7530_port_mode {
 /* Register for port vlan control */
 #define MT7530_PVC_P(x)			(0x2010 + ((x) * 0x100))
 #define  PORT_SPEC_TAG			BIT(5)
+#define  PVC_EG_TAG(x)			(((x) & 0x7) << 8)
+#define  PVC_EG_TAG_MASK		PVC_EG_TAG(7)
 #define  VLAN_ATTR(x)			(((x) & 0x3) << 6)
 #define  VLAN_ATTR_MASK			VLAN_ATTR(3)
 
+enum mt7530_vlan_port_eg_tag {
+	MT7530_VLAN_EG_DISABLED = 0,
+	MT7530_VLAN_EG_CONSISTENT = 1,
+};
+
 enum mt7530_vlan_port_attr {
 	MT7530_VLAN_USER = 0,
 	MT7530_VLAN_TRANSPARENT = 3,
-- 
2.20.1


From 8ddf2bfa9cc6ae5039c619ea1bec89d70d6d4583 Mon Sep 17 00:00:00 2001
From: Taras Chornyi <taras.chornyi@plvision.eu>
Date: Thu, 9 Apr 2020 20:25:24 +0300
Subject: [PATCH 05/19] net: ipv4: devinet: Fix crash when add/del multicast IP
 with autojoin

[ Upstream commit 690cc86321eb9bcee371710252742fb16fe96824 ]

When CONFIG_IP_MULTICAST is not set and multicast ip is added to the device
with autojoin flag or when multicast ip is deleted kernel will crash.

steps to reproduce:

ip addr add 224.0.0.0/32 dev eth0
ip addr del 224.0.0.0/32 dev eth0

or

ip addr add 224.0.0.0/32 dev eth0 autojoin

Unable to handle kernel NULL pointer dereference at virtual address 0000000000000088
 pc : _raw_write_lock_irqsave+0x1e0/0x2ac
 lr : lock_sock_nested+0x1c/0x60
 Call trace:
  _raw_write_lock_irqsave+0x1e0/0x2ac
  lock_sock_nested+0x1c/0x60
  ip_mc_config.isra.28+0x50/0xe0
  inet_rtm_deladdr+0x1a8/0x1f0
  rtnetlink_rcv_msg+0x120/0x350
  netlink_rcv_skb+0x58/0x120
  rtnetlink_rcv+0x14/0x20
  netlink_unicast+0x1b8/0x270
  netlink_sendmsg+0x1a0/0x3b0
  ____sys_sendmsg+0x248/0x290
  ___sys_sendmsg+0x80/0xc0
  __sys_sendmsg+0x68/0xc0
  __arm64_sys_sendmsg+0x20/0x30
  el0_svc_common.constprop.2+0x88/0x150
  do_el0_svc+0x20/0x80
 el0_sync_handler+0x118/0x190
  el0_sync+0x140/0x180

Fixes: 93a714d6b53d ("multicast: Extend ip address command to enable multicast group join/leave on")
Signed-off-by: Taras Chornyi <taras.chornyi@plvision.eu>
Signed-off-by: Vadym Kochan <vadym.kochan@plvision.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/devinet.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index e4632bd2026d..458dc6eb5a68 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -614,12 +614,15 @@ struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix,
 	return NULL;
 }
 
-static int ip_mc_config(struct sock *sk, bool join, const struct in_ifaddr *ifa)
+static int ip_mc_autojoin_config(struct net *net, bool join,
+				 const struct in_ifaddr *ifa)
 {
+#if defined(CONFIG_IP_MULTICAST)
 	struct ip_mreqn mreq = {
 		.imr_multiaddr.s_addr = ifa->ifa_address,
 		.imr_ifindex = ifa->ifa_dev->dev->ifindex,
 	};
+	struct sock *sk = net->ipv4.mc_autojoin_sk;
 	int ret;
 
 	ASSERT_RTNL();
@@ -632,6 +635,9 @@ static int ip_mc_config(struct sock *sk, bool join, const struct in_ifaddr *ifa)
 	release_sock(sk);
 
 	return ret;
+#else
+	return -EOPNOTSUPP;
+#endif
 }
 
 static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -675,7 +681,7 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
 			continue;
 
 		if (ipv4_is_multicast(ifa->ifa_address))
-			ip_mc_config(net->ipv4.mc_autojoin_sk, false, ifa);
+			ip_mc_autojoin_config(net, false, ifa);
 		__inet_del_ifa(in_dev, ifap, 1, nlh, NETLINK_CB(skb).portid);
 		return 0;
 	}
@@ -940,8 +946,7 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
 		 */
 		set_ifa_lifetime(ifa, valid_lft, prefered_lft);
 		if (ifa->ifa_flags & IFA_F_MCAUTOJOIN) {
-			int ret = ip_mc_config(net->ipv4.mc_autojoin_sk,
-					       true, ifa);
+			int ret = ip_mc_autojoin_config(net, true, ifa);
 
 			if (ret < 0) {
 				inet_free_ifa(ifa);
-- 
2.20.1


From 283257951b4dbf6122bcaaea71910ed55cecf93e Mon Sep 17 00:00:00 2001
From: Tim Stallard <code@timstallard.me.uk>
Date: Fri, 3 Apr 2020 21:26:21 +0100
Subject: [PATCH 06/19] net: ipv6: do not consider routes via gateways for
 anycast address check

[ Upstream commit 03e2a984b6165621f287fadf5f4b5cd8b58dcaba ]

The behaviour for what is considered an anycast address changed in
commit 45e4fd26683c ("ipv6: Only create RTF_CACHE routes after
encountering pmtu exception"). This now considers the first
address in a subnet where there is a route via a gateway
to be an anycast address.

This breaks path MTU discovery and traceroutes when a host in a
remote network uses the address at the start of a prefix
(eg 2600:: advertised as 2600::/48 in the DFZ) as ICMP errors
will not be sent to anycast addresses.

This patch excludes any routes with a gateway, or via point to
point links, like the behaviour previously from
rt6_is_gw_or_nonexthop in net/ipv6/route.c.

This can be tested with:
ip link add v1 type veth peer name v2
ip netns add test
ip netns exec test ip link set lo up
ip link set v2 netns test
ip link set v1 up
ip netns exec test ip link set v2 up
ip addr add 2001:db8::1/64 dev v1 nodad
ip addr add 2001:db8:100:: dev lo nodad
ip netns exec test ip addr add 2001:db8::2/64 dev v2 nodad
ip netns exec test ip route add unreachable 2001:db8:1::1
ip netns exec test ip route add 2001:db8:100::/64 via 2001:db8::1
ip netns exec test sysctl net.ipv6.conf.all.forwarding=1
ip route add 2001:db8:1::1 via 2001:db8::2
ping -I 2001:db8::1 2001:db8:1::1 -c1
ping -I 2001:db8:100:: 2001:db8:1::1 -c1
ip addr delete 2001:db8:100:: dev lo
ip netns delete test

Currently the first ping will get back a destination unreachable ICMP
error, but the second will never get a response, with "icmp6_send:
acast source" logged. After this patch, both get destination
unreachable ICMP replies.

Fixes: 45e4fd26683c ("ipv6: Only create RTF_CACHE routes after encountering pmtu exception")
Signed-off-by: Tim Stallard <code@timstallard.me.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_route.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index b69c16cbbf71..2d0d91070268 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -254,6 +254,7 @@ static inline bool ipv6_anycast_destination(const struct dst_entry *dst,
 
 	return rt->rt6i_flags & RTF_ANYCAST ||
 		(rt->rt6i_dst.plen < 127 &&
+		 !(rt->rt6i_flags & (RTF_GATEWAY | RTF_NONEXTHOP)) &&
 		 ipv6_addr_equal(&rt->rt6i_dst.addr, daddr));
 }
 
-- 
2.20.1


From 169c6c91c79a4d09be8ea70da0ef38e3a680a11d Mon Sep 17 00:00:00 2001
From: Atsushi Nemoto <atsushi.nemoto@sord.co.jp>
Date: Fri, 10 Apr 2020 12:16:16 +0900
Subject: [PATCH 07/19] net: phy: micrel: use genphy_read_status for KSZ9131

[ Upstream commit 68dac3eb50be32957ae6e1e6da9281a3b7c6658b ]

KSZ9131 will not work with some switches due to workaround for KSZ9031
introduced in commit d2fd719bcb0e83cb39cfee22ee800f98a56eceb3
("net/phy: micrel: Add workaround for bad autoneg").
Use genphy_read_status instead of dedicated ksz9031_read_status.

Fixes: bff5b4b37372 ("net: phy: micrel: add Microchip KSZ9131 initial driver")
Signed-off-by: Atsushi Nemoto <atsushi.nemoto@sord.co.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/micrel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 51b64f087717..663c68ed6ef9 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -1154,7 +1154,7 @@ static struct phy_driver ksphy_driver[] = {
 	.driver_data	= &ksz9021_type,
 	.probe		= kszphy_probe,
 	.config_init	= ksz9131_config_init,
-	.read_status	= ksz9031_read_status,
+	.read_status	= genphy_read_status,
 	.ack_interrupt	= kszphy_ack_interrupt,
 	.config_intr	= kszphy_config_intr,
 	.get_sset_count = kszphy_get_sset_count,
-- 
2.20.1


From 214efc7d3af833a4a4005c035a46fd7907f3f0c1 Mon Sep 17 00:00:00 2001
From: Wang Wenhu <wenhu.wang@vivo.com>
Date: Wed, 8 Apr 2020 19:53:53 -0700
Subject: [PATCH 08/19] net: qrtr: send msgs from local of same id as broadcast

[ Upstream commit 6dbf02acef69b0742c238574583b3068afbd227c ]

If the local node id(qrtr_local_nid) is not modified after its
initialization, it equals to the broadcast node id(QRTR_NODE_BCAST).
So the messages from local node should not be taken as broadcast
and keep the process going to send them out anyway.

The definitions are as follow:
static unsigned int qrtr_local_nid = NUMA_NO_NODE;

Fixes: fdf5fd397566 ("net: qrtr: Broadcast messages only from control port")
Signed-off-by: Wang Wenhu <wenhu.wang@vivo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/qrtr/qrtr.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index 3d24d45be5f4..930f48a20546 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -763,20 +763,21 @@ static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 
 	node = NULL;
 	if (addr->sq_node == QRTR_NODE_BCAST) {
-		enqueue_fn = qrtr_bcast_enqueue;
-		if (addr->sq_port != QRTR_PORT_CTRL) {
+		if (addr->sq_port != QRTR_PORT_CTRL &&
+		    qrtr_local_nid != QRTR_NODE_BCAST) {
 			release_sock(sk);
 			return -ENOTCONN;
 		}
+		enqueue_fn = qrtr_bcast_enqueue;
 	} else if (addr->sq_node == ipc->us.sq_node) {
 		enqueue_fn = qrtr_local_enqueue;
 	} else {
-		enqueue_fn = qrtr_node_enqueue;
 		node = qrtr_node_lookup(addr->sq_node);
 		if (!node) {
 			release_sock(sk);
 			return -ECONNRESET;
 		}
+		enqueue_fn = qrtr_node_enqueue;
 	}
 
 	plen = (len + 3) & ~3;
-- 
2.20.1


From 36226d2cebc63663797214fb3406c26d30e3f126 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Date: Mon, 6 Apr 2020 14:39:32 +0300
Subject: [PATCH 09/19] net: revert default NAPI poll timeout to 2 jiffies

[ Upstream commit a4837980fd9fa4c70a821d11831698901baef56b ]

For HZ < 1000 timeout 2000us rounds up to 1 jiffy but expires randomly
because next timer interrupt could come shortly after starting softirq.

For commonly used CONFIG_HZ=1000 nothing changes.

Fixes: 7acf8a1e8a28 ("Replace 2 jiffies with sysctl netdev_budget_usecs to enable softirq tuning")
Reported-by: Dmitry Yakunin <zeil@yandex-team.ru>
Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 9d3fddbc7037..fc8459316c3d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4090,7 +4090,8 @@ EXPORT_SYMBOL(netdev_max_backlog);
 
 int netdev_tstamp_prequeue __read_mostly = 1;
 int netdev_budget __read_mostly = 300;
-unsigned int __read_mostly netdev_budget_usecs = 2000;
+/* Must be at least 2 jiffes to guarantee 1 jiffy timeout */
+unsigned int __read_mostly netdev_budget_usecs = 2 * USEC_PER_SEC / HZ;
 int weight_p __read_mostly = 64;           /* old backlog weight */
 int dev_weight_rx_bias __read_mostly = 1;  /* bias for backlog weight */
 int dev_weight_tx_bias __read_mostly = 1;  /* bias for output_queue quota */
-- 
2.20.1


From 0f88860545ec3f6805e6e9b7c17b448952384e7f Mon Sep 17 00:00:00 2001
From: Gilberto Bertin <me@jibi.io>
Date: Fri, 10 Apr 2020 18:20:59 +0200
Subject: [PATCH 10/19] net: tun: record RX queue in skb before
 do_xdp_generic()

[ Upstream commit 3fe260e00cd0bf0be853c48fcc1e19853df615bb ]

This allows netif_receive_generic_xdp() to correctly determine the RX
queue from which the skb is coming, so that the context passed to the
XDP program will contain the correct RX queue index.

Signed-off-by: Gilberto Bertin <me@jibi.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 6d3317d868d2..7874046a57dd 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1925,6 +1925,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 
 	skb_reset_network_header(skb);
 	skb_probe_transport_header(skb);
+	skb_record_rx_queue(skb, tfile->queue_index);
 
 	if (skb_xdp) {
 		struct bpf_prog *xdp_prog;
@@ -2498,6 +2499,7 @@ static int tun_xdp_one(struct tun_struct *tun,
 	skb->protocol = eth_type_trans(skb, tun->dev);
 	skb_reset_network_header(skb);
 	skb_probe_transport_header(skb);
+	skb_record_rx_queue(skb, tfile->queue_index);
 
 	if (skb_xdp) {
 		err = do_xdp_generic(xdp_prog, skb);
@@ -2509,7 +2511,6 @@ static int tun_xdp_one(struct tun_struct *tun,
 	    !tfile->detached)
 		rxhash = __skb_get_hash_symmetric(skb);
 
-	skb_record_rx_queue(skb, tfile->queue_index);
 	netif_receive_skb(skb);
 
 	/* No need for get_cpu_ptr() here since this function is
-- 
2.20.1


From 07c423969e3b94bf5cddafbd4fac3e46eb013553 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ren=C3=A9=20van=20Dorst?= <opensource@vdorst.com>
Date: Mon, 6 Apr 2020 05:42:53 +0800
Subject: [PATCH 11/19] net: dsa: mt7530: move mt7623 settings out off the
 mt7530
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 84d2f7b708c374a15a2abe092a74e0e47d018286 ]

Moving mt7623 logic out off mt7530, is required to make hardware setting
consistent after we introduce phylink to mtk driver.

Fixes: ca366d6c889b ("net: dsa: mt7530: Convert to PHYLINK API")
Reviewed-by: Sean Wang <sean.wang@mediatek.com>
Tested-by: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: René van Dorst <opensource@vdorst.com>
Tested-by: Frank Wunderlich <frank-w@public-files.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mt7530.c | 85 ----------------------------------------
 drivers/net/dsa/mt7530.h | 10 -----
 2 files changed, 95 deletions(-)

diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index 44dea65d8117..9cf5da89dbbb 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -66,58 +66,6 @@ static const struct mt7530_mib_desc mt7530_mib[] = {
 	MIB_DESC(1, 0xb8, "RxArlDrop"),
 };
 
-static int
-mt7623_trgmii_write(struct mt7530_priv *priv,  u32 reg, u32 val)
-{
-	int ret;
-
-	ret =  regmap_write(priv->ethernet, TRGMII_BASE(reg), val);
-	if (ret < 0)
-		dev_err(priv->dev,
-			"failed to priv write register\n");
-	return ret;
-}
-
-static u32
-mt7623_trgmii_read(struct mt7530_priv *priv, u32 reg)
-{
-	int ret;
-	u32 val;
-
-	ret = regmap_read(priv->ethernet, TRGMII_BASE(reg), &val);
-	if (ret < 0) {
-		dev_err(priv->dev,
-			"failed to priv read register\n");
-		return ret;
-	}
-
-	return val;
-}
-
-static void
-mt7623_trgmii_rmw(struct mt7530_priv *priv, u32 reg,
-		  u32 mask, u32 set)
-{
-	u32 val;
-
-	val = mt7623_trgmii_read(priv, reg);
-	val &= ~mask;
-	val |= set;
-	mt7623_trgmii_write(priv, reg, val);
-}
-
-static void
-mt7623_trgmii_set(struct mt7530_priv *priv, u32 reg, u32 val)
-{
-	mt7623_trgmii_rmw(priv, reg, 0, val);
-}
-
-static void
-mt7623_trgmii_clear(struct mt7530_priv *priv, u32 reg, u32 val)
-{
-	mt7623_trgmii_rmw(priv, reg, val, 0);
-}
-
 static int
 core_read_mmd_indirect(struct mt7530_priv *priv, int prtad, int devad)
 {
@@ -530,27 +478,6 @@ mt7530_pad_clk_setup(struct dsa_switch *ds, int mode)
 		for (i = 0 ; i < NUM_TRGMII_CTRL; i++)
 			mt7530_rmw(priv, MT7530_TRGMII_RD(i),
 				   RD_TAP_MASK, RD_TAP(16));
-	else
-		if (priv->id != ID_MT7621)
-			mt7623_trgmii_set(priv, GSW_INTF_MODE,
-					  INTF_MODE_TRGMII);
-
-	return 0;
-}
-
-static int
-mt7623_pad_clk_setup(struct dsa_switch *ds)
-{
-	struct mt7530_priv *priv = ds->priv;
-	int i;
-
-	for (i = 0 ; i < NUM_TRGMII_CTRL; i++)
-		mt7623_trgmii_write(priv, GSW_TRGMII_TD_ODT(i),
-				    TD_DM_DRVP(8) | TD_DM_DRVN(8));
-
-	mt7623_trgmii_set(priv, GSW_TRGMII_RCK_CTRL, RX_RST | RXC_DQSISEL);
-	mt7623_trgmii_clear(priv, GSW_TRGMII_RCK_CTRL, RX_RST);
-
 	return 0;
 }
 
@@ -1257,10 +1184,6 @@ mt7530_setup(struct dsa_switch *ds)
 	dn = dsa_to_port(ds, MT7530_CPU_PORT)->master->dev.of_node->parent;
 
 	if (priv->id == ID_MT7530) {
-		priv->ethernet = syscon_node_to_regmap(dn);
-		if (IS_ERR(priv->ethernet))
-			return PTR_ERR(priv->ethernet);
-
 		regulator_set_voltage(priv->core_pwr, 1000000, 1000000);
 		ret = regulator_enable(priv->core_pwr);
 		if (ret < 0) {
@@ -1426,14 +1349,6 @@ static void mt7530_phylink_mac_config(struct dsa_switch *ds, int port,
 		/* Setup TX circuit incluing relevant PAD and driving */
 		mt7530_pad_clk_setup(ds, state->interface);
 
-		if (priv->id == ID_MT7530) {
-			/* Setup RX circuit, relevant PAD and driving on the
-			 * host which must be placed after the setup on the
-			 * device side is all finished.
-			 */
-			mt7623_pad_clk_setup(ds);
-		}
-
 		priv->p6_interface = state->interface;
 		break;
 	default:
diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h
index 9a769c6b7700..756140b7dfd5 100644
--- a/drivers/net/dsa/mt7530.h
+++ b/drivers/net/dsa/mt7530.h
@@ -275,7 +275,6 @@ enum mt7530_vlan_port_attr {
 
 /* Registers for TRGMII on the both side */
 #define MT7530_TRGMII_RCK_CTRL		0x7a00
-#define GSW_TRGMII_RCK_CTRL		0x300
 #define  RX_RST				BIT(31)
 #define  RXC_DQSISEL			BIT(30)
 #define  DQSI1_TAP_MASK			(0x7f << 8)
@@ -284,31 +283,24 @@ enum mt7530_vlan_port_attr {
 #define  DQSI0_TAP(x)			((x) & 0x7f)
 
 #define MT7530_TRGMII_RCK_RTT		0x7a04
-#define GSW_TRGMII_RCK_RTT		0x304
 #define  DQS1_GATE			BIT(31)
 #define  DQS0_GATE			BIT(30)
 
 #define MT7530_TRGMII_RD(x)		(0x7a10 + (x) * 8)
-#define GSW_TRGMII_RD(x)		(0x310 + (x) * 8)
 #define  BSLIP_EN			BIT(31)
 #define  EDGE_CHK			BIT(30)
 #define  RD_TAP_MASK			0x7f
 #define  RD_TAP(x)			((x) & 0x7f)
 
-#define GSW_TRGMII_TXCTRL		0x340
 #define MT7530_TRGMII_TXCTRL		0x7a40
 #define  TRAIN_TXEN			BIT(31)
 #define  TXC_INV			BIT(30)
 #define  TX_RST				BIT(28)
 
 #define MT7530_TRGMII_TD_ODT(i)		(0x7a54 + 8 * (i))
-#define GSW_TRGMII_TD_ODT(i)		(0x354 + 8 * (i))
 #define  TD_DM_DRVP(x)			((x) & 0xf)
 #define  TD_DM_DRVN(x)			(((x) & 0xf) << 4)
 
-#define GSW_INTF_MODE			0x390
-#define  INTF_MODE_TRGMII		BIT(1)
-
 #define MT7530_TRGMII_TCK_CTRL		0x7a78
 #define  TCK_TAP(x)			(((x) & 0xf) << 8)
 
@@ -441,7 +433,6 @@ static const char *p5_intf_modes(unsigned int p5_interface)
  * @ds:			The pointer to the dsa core structure
  * @bus:		The bus used for the device and built-in PHY
  * @rstc:		The pointer to reset control used by MCM
- * @ethernet:		The regmap used for access TRGMII-based registers
  * @core_pwr:		The power supplied into the core
  * @io_pwr:		The power supplied into the I/O
  * @reset:		The descriptor for GPIO line tied to its reset pin
@@ -458,7 +449,6 @@ struct mt7530_priv {
 	struct dsa_switch	*ds;
 	struct mii_bus		*bus;
 	struct reset_control	*rstc;
-	struct regmap		*ethernet;
 	struct regulator	*core_pwr;
 	struct regulator	*io_pwr;
 	struct gpio_desc	*reset;
-- 
2.20.1


From c7413b37f4622d4366c25b47b82b97a8385ba595 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ren=C3=A9=20van=20Dorst?= <opensource@vdorst.com>
Date: Mon, 6 Apr 2020 05:42:54 +0800
Subject: [PATCH 12/19] net: ethernet: mediatek: move mt7623 settings out off
 the mt7530
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit a5d75538295b06bc6ade1b9da07b9bee57d1c677 ]

Moving mt7623 logic out off mt7530, is required to make hardware setting
consistent after we introduce phylink to mtk driver.

Fixes: b8fc9f30821e ("net: ethernet: mediatek: Add basic PHYLINK support")
Reviewed-by: Sean Wang <sean.wang@mediatek.com>
Tested-by: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: René van Dorst <opensource@vdorst.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c | 24 ++++++++++++++++++++-
 drivers/net/ethernet/mediatek/mtk_eth_soc.h |  8 +++++++
 2 files changed, 31 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 527ad2aadcca..ec035bef98b8 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -65,6 +65,17 @@ u32 mtk_r32(struct mtk_eth *eth, unsigned reg)
 	return __raw_readl(eth->base + reg);
 }
 
+u32 mtk_m32(struct mtk_eth *eth, u32 mask, u32 set, unsigned reg)
+{
+	u32 val;
+
+	val = mtk_r32(eth, reg);
+	val &= ~mask;
+	val |= set;
+	mtk_w32(eth, val, reg);
+	return reg;
+}
+
 static int mtk_mdio_busy_wait(struct mtk_eth *eth)
 {
 	unsigned long t_start = jiffies;
@@ -193,7 +204,7 @@ static void mtk_mac_config(struct phylink_config *config, unsigned int mode,
 	struct mtk_mac *mac = container_of(config, struct mtk_mac,
 					   phylink_config);
 	struct mtk_eth *eth = mac->hw;
-	u32 mcr_cur, mcr_new, sid;
+	u32 mcr_cur, mcr_new, sid, i;
 	int val, ge_mode, err;
 
 	/* MT76x8 has no hardware settings between for the MAC */
@@ -255,6 +266,17 @@ static void mtk_mac_config(struct phylink_config *config, unsigned int mode,
 				    PHY_INTERFACE_MODE_TRGMII)
 					mtk_gmac0_rgmii_adjust(mac->hw,
 							       state->speed);
+
+				/* mt7623_pad_clk_setup */
+				for (i = 0 ; i < NUM_TRGMII_CTRL; i++)
+					mtk_w32(mac->hw,
+						TD_DM_DRVP(8) | TD_DM_DRVN(8),
+						TRGMII_TD_ODT(i));
+
+				/* Assert/release MT7623 RXC reset */
+				mtk_m32(mac->hw, 0, RXC_RST | RXC_DQSISEL,
+					TRGMII_RCK_CTRL);
+				mtk_m32(mac->hw, RXC_RST, 0, TRGMII_RCK_CTRL);
 			}
 		}
 
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 85830fe14a1b..454cfcd465fd 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -352,10 +352,13 @@
 #define DQSI0(x)		((x << 0) & GENMASK(6, 0))
 #define DQSI1(x)		((x << 8) & GENMASK(14, 8))
 #define RXCTL_DMWTLAT(x)	((x << 16) & GENMASK(18, 16))
+#define RXC_RST			BIT(31)
 #define RXC_DQSISEL		BIT(30)
 #define RCK_CTRL_RGMII_1000	(RXC_DQSISEL | RXCTL_DMWTLAT(2) | DQSI1(16))
 #define RCK_CTRL_RGMII_10_100	RXCTL_DMWTLAT(2)
 
+#define NUM_TRGMII_CTRL		5
+
 /* TRGMII RXC control register */
 #define TRGMII_TCK_CTRL		0x10340
 #define TXCTL_DMWTLAT(x)	((x << 16) & GENMASK(18, 16))
@@ -363,6 +366,11 @@
 #define TCK_CTRL_RGMII_1000	TXCTL_DMWTLAT(2)
 #define TCK_CTRL_RGMII_10_100	(TXC_INV | TXCTL_DMWTLAT(2))
 
+/* TRGMII TX Drive Strength */
+#define TRGMII_TD_ODT(i)	(0x10354 + 8 * (i))
+#define  TD_DM_DRVP(x)		((x) & 0xf)
+#define  TD_DM_DRVN(x)		(((x) & 0xf) << 4)
+
 /* TRGMII Interface mode register */
 #define INTF_MODE		0x10390
 #define TRGMII_INTF_DIS		BIT(0)
-- 
2.20.1


From d112033f72c743bb310e01b08a2b9385e2c2b0c6 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Mon, 30 Mar 2020 10:21:49 +0300
Subject: [PATCH 13/19] net/mlx5: Fix frequent ioread PCI access during
 recovery

[ Upstream commit 8c702a53bb0a79bfa203ba21ef1caba43673c5b7 ]

High frequency of PCI ioread calls during recovery flow may cause the
following trace on powerpc:

[ 248.670288] EEH: 2100000 reads ignored for recovering device at
location=Slot1 driver=mlx5_core pci addr=0000:01:00.1
[ 248.670331] EEH: Might be infinite loop in mlx5_core driver
[ 248.670361] CPU: 2 PID: 35247 Comm: kworker/u192:11 Kdump: loaded
Tainted: G OE ------------ 4.14.0-115.14.1.el7a.ppc64le #1
[ 248.670425] Workqueue: mlx5_health0000:01:00.1 health_recover_work
[mlx5_core]
[ 248.670471] Call Trace:
[ 248.670492] [c00020391c11b960] [c000000000c217ac] dump_stack+0xb0/0xf4
(unreliable)
[ 248.670548] [c00020391c11b9a0] [c000000000045818]
eeh_check_failure+0x5c8/0x630
[ 248.670631] [c00020391c11ba50] [c00000000068fce4]
ioread32be+0x114/0x1c0
[ 248.670692] [c00020391c11bac0] [c00800000dd8b400]
mlx5_error_sw_reset+0x160/0x510 [mlx5_core]
[ 248.670752] [c00020391c11bb60] [c00800000dd75824]
mlx5_disable_device+0x34/0x1d0 [mlx5_core]
[ 248.670822] [c00020391c11bbe0] [c00800000dd8affc]
health_recover_work+0x11c/0x3c0 [mlx5_core]
[ 248.670891] [c00020391c11bc80] [c000000000164fcc]
process_one_work+0x1bc/0x5f0
[ 248.670955] [c00020391c11bd20] [c000000000167f8c]
worker_thread+0xac/0x6b0
[ 248.671015] [c00020391c11bdc0] [c000000000171618] kthread+0x168/0x1b0
[ 248.671067] [c00020391c11be30] [c00000000000b65c]
ret_from_kernel_thread+0x5c/0x80

Reduce the PCI ioread frequency during recovery by using msleep()
instead of cond_resched()

Fixes: 3e5b72ac2f29 ("net/mlx5: Issue SW reset on FW assert")
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Reviewed-by: Feras Daoud <ferasda@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/health.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index d9f4e8c59c1f..68e7ef7ca52d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -243,7 +243,7 @@ void mlx5_error_sw_reset(struct mlx5_core_dev *dev)
 		if (mlx5_get_nic_state(dev) == MLX5_NIC_IFC_DISABLED)
 			break;
 
-		cond_resched();
+		msleep(20);
 	} while (!time_after(jiffies, end));
 
 	if (mlx5_get_nic_state(dev) != MLX5_NIC_IFC_DISABLED) {
-- 
2.20.1


From bec74e58d1f519ee784f0aa66976508bbbfc67eb Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Tue, 24 Mar 2020 15:04:26 +0200
Subject: [PATCH 14/19] net/mlx5e: Add missing release firmware call

[ Upstream commit d19987ccf57501894fdd8fadc2e55e4a3dd57239 ]

Once driver finishes flashing the firmware image, it should release it.

Fixes: 9c8bca2637b8 ("mlx5: Move firmware flash implementation to devlink")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Reviewed-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/devlink.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index ac108f1e5bd6..184c3eaefbcb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -23,7 +23,10 @@ static int mlx5_devlink_flash_update(struct devlink *devlink,
 	if (err)
 		return err;
 
-	return mlx5_firmware_flash(dev, fw, extack);
+	err = mlx5_firmware_flash(dev, fw, extack);
+	release_firmware(fw);
+
+	return err;
 }
 
 static u8 mlx5_fw_ver_major(u32 version)
-- 
2.20.1


From 2d6d4ed832a0523a0e31c61f487769e8e618d3ee Mon Sep 17 00:00:00 2001
From: Dmytro Linkin <dmitrolin@mellanox.com>
Date: Wed, 1 Apr 2020 14:41:27 +0300
Subject: [PATCH 15/19] net/mlx5e: Fix nest_level for vlan pop action

[ Upstream commit 70f478ca085deec4d6c1f187f773f5827ddce7e8 ]

Current value of nest_level, assigned from net_device lower_level value,
does not reflect the actual number of vlan headers, needed to pop.
For ex., if we have untagged ingress traffic sended over vlan devices,
instead of one pop action, driver will perform two pop actions.
To fix that, calculate nest_level as difference between vlan device and
parent device lower_levels.

Fixes: f3b0a18bb6cb ("net: remove unnecessary variables and callback")
Signed-off-by: Dmytro Linkin <dmitrolin@mellanox.com>
Signed-off-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index d4bad2a444e2..f5bcaf7d5d9a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -3221,12 +3221,13 @@ static int add_vlan_pop_action(struct mlx5e_priv *priv,
 			       struct mlx5_esw_flow_attr *attr,
 			       u32 *action)
 {
-	int nest_level = attr->parse_attr->filter_dev->lower_level;
 	struct flow_action_entry vlan_act = {
 		.id = FLOW_ACTION_VLAN_POP,
 	};
-	int err = 0;
+	int nest_level, err = 0;
 
+	nest_level = attr->parse_attr->filter_dev->lower_level -
+						priv->netdev->lower_level;
 	while (nest_level--) {
 		err = parse_tc_vlan_action(priv, &vlan_act, attr, action);
 		if (err)
-- 
2.20.1


From 16c9d6e6afd0a6725a00bd86311ecb7c7fdfd234 Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@mellanox.com>
Date: Fri, 3 Apr 2020 03:57:30 -0500
Subject: [PATCH 16/19] net/mlx5e: Fix pfnum in devlink port attribute

[ Upstream commit 7482d9cb5b974b7ad1a58fa8714f7a8c05b5d278 ]

Cited patch missed to extract PCI pf number accurately for PF and VF
port flavour. It considered PCI device + function number.
Due to this, device having non zero device number shown large pfnum.

Hence, use only PCI function number; to avoid similar errors, derive
pfnum one time for all port flavours.

Fixes: f60f315d339e ("net/mlx5e: Register devlink ports for physical link, PCI PF, VFs")
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index f175cb24bb67..f4d96344022f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1854,29 +1854,30 @@ static int register_devlink_port(struct mlx5_core_dev *dev,
 	struct mlx5_eswitch_rep *rep = rpriv->rep;
 	struct netdev_phys_item_id ppid = {};
 	unsigned int dl_port_index = 0;
+	u16 pfnum;
 
 	if (!is_devlink_port_supported(dev, rpriv))
 		return 0;
 
 	mlx5e_rep_get_port_parent_id(rpriv->netdev, &ppid);
+	pfnum = PCI_FUNC(dev->pdev->devfn);
 
 	if (rep->vport == MLX5_VPORT_UPLINK) {
 		devlink_port_attrs_set(&rpriv->dl_port,
 				       DEVLINK_PORT_FLAVOUR_PHYSICAL,
-				       PCI_FUNC(dev->pdev->devfn), false, 0,
+				       pfnum, false, 0,
 				       &ppid.id[0], ppid.id_len);
 		dl_port_index = vport_to_devlink_port_index(dev, rep->vport);
 	} else if (rep->vport == MLX5_VPORT_PF) {
 		devlink_port_attrs_pci_pf_set(&rpriv->dl_port,
 					      &ppid.id[0], ppid.id_len,
-					      dev->pdev->devfn);
+					      pfnum);
 		dl_port_index = rep->vport;
 	} else if (mlx5_eswitch_is_vf_vport(dev->priv.eswitch,
 					    rpriv->rep->vport)) {
 		devlink_port_attrs_pci_vf_set(&rpriv->dl_port,
 					      &ppid.id[0], ppid.id_len,
-					      dev->pdev->devfn,
-					      rep->vport - 1);
+					      pfnum, rep->vport - 1);
 		dl_port_index = vport_to_devlink_port_index(dev, rep->vport);
 	}
 
-- 
2.20.1


From ea563ddbfd98b41c0f6866f8793ea82139fd9bbd Mon Sep 17 00:00:00 2001
From: Tim Stallard <code@timstallard.me.uk>
Date: Fri, 3 Apr 2020 21:22:57 +0100
Subject: [PATCH 17/19] net: icmp6: do not select saddr from iif when route has
 prefsrc set

[ Upstream commit b93cfb9cd3af3adc9ba4854f178d5300f7544d3e ]

Since commit fac6fce9bdb5 ("net: icmp6: provide input address for
traceroute6") ICMPv6 errors have source addresses from the ingress
interface. However, this overrides when source address selection is
influenced by setting preferred source addresses on routes.

This can result in ICMP errors being lost to upstream BCP38 filters
when the wrong source addresses are used, breaking path MTU discovery
and traceroute.

This patch sets the modified source address selection to only take place
when the route used has no prefsrc set.

It can be tested with:

ip link add v1 type veth peer name v2
ip netns add test
ip netns exec test ip link set lo up
ip link set v2 netns test
ip link set v1 up
ip netns exec test ip link set v2 up
ip addr add 2001:db8::1/64 dev v1 nodad
ip addr add 2001:db8::3 dev v1 nodad
ip netns exec test ip addr add 2001:db8::2/64 dev v2 nodad
ip netns exec test ip route add unreachable 2001:db8:1::1
ip netns exec test ip addr add 2001:db8:100::1 dev lo
ip netns exec test ip route add 2001:db8::1 dev v2 src 2001:db8:100::1
ip route add 2001:db8:1000::1 via 2001:db8::2
traceroute6 -s 2001:db8::1 2001:db8:1000::1
traceroute6 -s 2001:db8::3 2001:db8:1000::1
ip netns delete test

Output before:
$ traceroute6 -s 2001:db8::1 2001:db8:1000::1
traceroute to 2001:db8:1000::1 (2001:db8:1000::1), 30 hops max, 80 byte packets
 1  2001:db8::2 (2001:db8::2)  0.843 ms !N  0.396 ms !N  0.257 ms !N
$ traceroute6 -s 2001:db8::3 2001:db8:1000::1
traceroute to 2001:db8:1000::1 (2001:db8:1000::1), 30 hops max, 80 byte packets
 1  2001:db8::2 (2001:db8::2)  0.772 ms !N  0.257 ms !N  0.357 ms !N

After:
$ traceroute6 -s 2001:db8::1 2001:db8:1000::1
traceroute to 2001:db8:1000::1 (2001:db8:1000::1), 30 hops max, 80 byte packets
 1  2001:db8:100::1 (2001:db8:100::1)  8.885 ms !N  0.310 ms !N  0.174 ms !N
$ traceroute6 -s 2001:db8::3 2001:db8:1000::1
traceroute to 2001:db8:1000::1 (2001:db8:1000::1), 30 hops max, 80 byte packets
 1  2001:db8::2 (2001:db8::2)  1.403 ms !N  0.205 ms !N  0.313 ms !N

Fixes: fac6fce9bdb5 ("net: icmp6: provide input address for traceroute6")
Signed-off-by: Tim Stallard <code@timstallard.me.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/icmp.c | 21 ++++++++++++++++++++-
 1 file changed, 20 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index ef408a5090a2..c9504ec6a8d8 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -229,6 +229,25 @@ static bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
 	return res;
 }
 
+static bool icmpv6_rt_has_prefsrc(struct sock *sk, u8 type,
+				  struct flowi6 *fl6)
+{
+	struct net *net = sock_net(sk);
+	struct dst_entry *dst;
+	bool res = false;
+
+	dst = ip6_route_output(net, sk, fl6);
+	if (!dst->error) {
+		struct rt6_info *rt = (struct rt6_info *)dst;
+		struct in6_addr prefsrc;
+
+		rt6_get_prefsrc(rt, &prefsrc);
+		res = !ipv6_addr_any(&prefsrc);
+	}
+	dst_release(dst);
+	return res;
+}
+
 /*
  *	an inline helper for the "simple" if statement below
  *	checks if parameter problem report is caused by an
@@ -527,7 +546,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 		saddr = force_saddr;
 	if (saddr) {
 		fl6.saddr = *saddr;
-	} else {
+	} else if (!icmpv6_rt_has_prefsrc(sk, type, &fl6)) {
 		/* select a more meaningful saddr from input if */
 		struct net_device *in_netdev;
 
-- 
2.20.1


From f6b41eb6ed8e130f5422a497fa5fd382d140bed1 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Tue, 14 Apr 2020 22:36:15 +0300
Subject: [PATCH 18/19] net: mscc: ocelot: fix untagged packet drops when
 enslaving to vlan aware bridge

[ Upstream commit 87b0f983f66f23762921129fd35966eddc3f2dae ]

To rehash a previous explanation given in commit 1c44ce560b4d ("net:
mscc: ocelot: fix vlan_filtering when enslaving to bridge before link is
up"), the switch driver operates the in a mode where a single VLAN can
be transmitted as untagged on a particular egress port. That is the
"native VLAN on trunk port" use case.

The configuration for this native VLAN is driven in 2 ways:
 - Set the egress port rewriter to strip the VLAN tag for the native
   VID (as it is egress-untagged, after all).
 - Configure the ingress port to drop untagged and priority-tagged
   traffic, if there is no native VLAN. The intention of this setting is
   that a trunk port with no native VLAN should not accept untagged
   traffic.

Since both of the above configurations for the native VLAN should only
be done if VLAN awareness is requested, they are actually done from the
ocelot_port_vlan_filtering function, after the basic procedure of
toggling the VLAN awareness flag of the port.

But there's a problem with that simplistic approach: we are trying to
juggle with 2 independent variables from a single function:
 - Native VLAN of the port - its value is held in port->vid.
 - VLAN awareness state of the port - currently there are some issues
   here, more on that later*.
The actual problem can be seen when enslaving the switch ports to a VLAN
filtering bridge:
 0. The driver configures a pvid of zero for each port, when in
    standalone mode. While the bridge configures a default_pvid of 1 for
    each port that gets added as a slave to it.
 1. The bridge calls ocelot_port_vlan_filtering with vlan_aware=true.
    The VLAN-filtering-dependent portion of the native VLAN
    configuration is done, considering that the native VLAN is 0.
 2. The bridge calls ocelot_vlan_add with vid=1, pvid=true,
    untagged=true. The native VLAN changes to 1 (change which gets
    propagated to hardware).
 3. ??? - nobody calls ocelot_port_vlan_filtering again, to reapply the
    VLAN-filtering-dependent portion of the native VLAN configuration,
    for the new native VLAN of 1. One can notice that after toggling "ip
    link set dev br0 type bridge vlan_filtering 0 && ip link set dev br0
    type bridge vlan_filtering 1", the new native VLAN finally makes it
    through and untagged traffic finally starts flowing again. But
    obviously that shouldn't be needed.

So it is clear that 2 independent variables need to both re-trigger the
native VLAN configuration. So we introduce the second variable as
ocelot_port->vlan_aware.

*Actually both the DSA Felix driver and the Ocelot driver already had
each its own variable:
 - Ocelot: ocelot_port_private->vlan_aware
 - Felix: dsa_port->vlan_filtering
but the common Ocelot library needs to work with a single, common,
variable, so there is some refactoring done to move the vlan_aware
property from the private structure into the common ocelot_port
structure.

Fixes: 97bb69e1e36e ("net: mscc: ocelot: break apart ocelot_vlan_port_apply")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/ocelot/felix.c     |  5 +-
 drivers/net/ethernet/mscc/ocelot.c | 84 +++++++++++++++---------------
 drivers/net/ethernet/mscc/ocelot.h |  2 -
 include/soc/mscc/ocelot.h          |  4 +-
 4 files changed, 47 insertions(+), 48 deletions(-)

diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index b7f92464815d..07ba3eda3c6e 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -46,11 +46,8 @@ static int felix_fdb_add(struct dsa_switch *ds, int port,
 			 const unsigned char *addr, u16 vid)
 {
 	struct ocelot *ocelot = ds->priv;
-	bool vlan_aware;
 
-	vlan_aware = dsa_port_is_vlan_filtering(dsa_to_port(ds, port));
-
-	return ocelot_fdb_add(ocelot, port, addr, vid, vlan_aware);
+	return ocelot_fdb_add(ocelot, port, addr, vid);
 }
 
 static int felix_fdb_del(struct dsa_switch *ds, int port,
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 88c0464a54e2..9f6fe880b95f 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -183,44 +183,47 @@ static void ocelot_vlan_mode(struct ocelot *ocelot, int port,
 	ocelot_write(ocelot, val, ANA_VLANMASK);
 }
 
-void ocelot_port_vlan_filtering(struct ocelot *ocelot, int port,
-				bool vlan_aware)
+static int ocelot_port_set_native_vlan(struct ocelot *ocelot, int port,
+				       u16 vid)
 {
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
-	u32 val;
+	u32 val = 0;
 
-	if (vlan_aware)
-		val = ANA_PORT_VLAN_CFG_VLAN_AWARE_ENA |
-		      ANA_PORT_VLAN_CFG_VLAN_POP_CNT(1);
-	else
-		val = 0;
-	ocelot_rmw_gix(ocelot, val,
-		       ANA_PORT_VLAN_CFG_VLAN_AWARE_ENA |
-		       ANA_PORT_VLAN_CFG_VLAN_POP_CNT_M,
-		       ANA_PORT_VLAN_CFG, port);
+	if (ocelot_port->vid != vid) {
+		/* Always permit deleting the native VLAN (vid = 0) */
+		if (ocelot_port->vid && vid) {
+			dev_err(ocelot->dev,
+				"Port already has a native VLAN: %d\n",
+				ocelot_port->vid);
+			return -EBUSY;
+		}
+		ocelot_port->vid = vid;
+	}
+
+	ocelot_rmw_gix(ocelot, REW_PORT_VLAN_CFG_PORT_VID(vid),
+		       REW_PORT_VLAN_CFG_PORT_VID_M,
+		       REW_PORT_VLAN_CFG, port);
 
-	if (vlan_aware && !ocelot_port->vid)
+	if (ocelot_port->vlan_aware && !ocelot_port->vid)
 		/* If port is vlan-aware and tagged, drop untagged and priority
 		 * tagged frames.
 		 */
 		val = ANA_PORT_DROP_CFG_DROP_UNTAGGED_ENA |
 		      ANA_PORT_DROP_CFG_DROP_PRIO_S_TAGGED_ENA |
 		      ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA;
-	else
-		val = 0;
 	ocelot_rmw_gix(ocelot, val,
 		       ANA_PORT_DROP_CFG_DROP_UNTAGGED_ENA |
 		       ANA_PORT_DROP_CFG_DROP_PRIO_S_TAGGED_ENA |
 		       ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA,
 		       ANA_PORT_DROP_CFG, port);
 
-	if (vlan_aware) {
+	if (ocelot_port->vlan_aware) {
 		if (ocelot_port->vid)
 			/* Tag all frames except when VID == DEFAULT_VLAN */
-			val |= REW_TAG_CFG_TAG_CFG(1);
+			val = REW_TAG_CFG_TAG_CFG(1);
 		else
 			/* Tag all frames */
-			val |= REW_TAG_CFG_TAG_CFG(3);
+			val = REW_TAG_CFG_TAG_CFG(3);
 	} else {
 		/* Port tagging disabled. */
 		val = REW_TAG_CFG_TAG_CFG(0);
@@ -228,31 +231,31 @@ void ocelot_port_vlan_filtering(struct ocelot *ocelot, int port,
 	ocelot_rmw_gix(ocelot, val,
 		       REW_TAG_CFG_TAG_CFG_M,
 		       REW_TAG_CFG, port);
+
+	return 0;
 }
-EXPORT_SYMBOL(ocelot_port_vlan_filtering);
 
-static int ocelot_port_set_native_vlan(struct ocelot *ocelot, int port,
-				       u16 vid)
+void ocelot_port_vlan_filtering(struct ocelot *ocelot, int port,
+				bool vlan_aware)
 {
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
+	u32 val;
 
-	if (ocelot_port->vid != vid) {
-		/* Always permit deleting the native VLAN (vid = 0) */
-		if (ocelot_port->vid && vid) {
-			dev_err(ocelot->dev,
-				"Port already has a native VLAN: %d\n",
-				ocelot_port->vid);
-			return -EBUSY;
-		}
-		ocelot_port->vid = vid;
-	}
+	ocelot_port->vlan_aware = vlan_aware;
 
-	ocelot_rmw_gix(ocelot, REW_PORT_VLAN_CFG_PORT_VID(vid),
-		       REW_PORT_VLAN_CFG_PORT_VID_M,
-		       REW_PORT_VLAN_CFG, port);
+	if (vlan_aware)
+		val = ANA_PORT_VLAN_CFG_VLAN_AWARE_ENA |
+		      ANA_PORT_VLAN_CFG_VLAN_POP_CNT(1);
+	else
+		val = 0;
+	ocelot_rmw_gix(ocelot, val,
+		       ANA_PORT_VLAN_CFG_VLAN_AWARE_ENA |
+		       ANA_PORT_VLAN_CFG_VLAN_POP_CNT_M,
+		       ANA_PORT_VLAN_CFG, port);
 
-	return 0;
+	ocelot_port_set_native_vlan(ocelot, port, ocelot_port->vid);
 }
+EXPORT_SYMBOL(ocelot_port_vlan_filtering);
 
 /* Default vlan to clasify for untagged frames (may be zero) */
 static void ocelot_port_set_pvid(struct ocelot *ocelot, int port, u16 pvid)
@@ -857,12 +860,12 @@ static void ocelot_get_stats64(struct net_device *dev,
 }
 
 int ocelot_fdb_add(struct ocelot *ocelot, int port,
-		   const unsigned char *addr, u16 vid, bool vlan_aware)
+		   const unsigned char *addr, u16 vid)
 {
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
 
 	if (!vid) {
-		if (!vlan_aware)
+		if (!ocelot_port->vlan_aware)
 			/* If the bridge is not VLAN aware and no VID was
 			 * provided, set it to pvid to ensure the MAC entry
 			 * matches incoming untagged packets
@@ -889,7 +892,7 @@ static int ocelot_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 	struct ocelot *ocelot = priv->port.ocelot;
 	int port = priv->chip_port;
 
-	return ocelot_fdb_add(ocelot, port, addr, vid, priv->vlan_aware);
+	return ocelot_fdb_add(ocelot, port, addr, vid);
 }
 
 int ocelot_fdb_del(struct ocelot *ocelot, int port,
@@ -1488,8 +1491,8 @@ static int ocelot_port_attr_set(struct net_device *dev,
 		ocelot_port_attr_ageing_set(ocelot, port, attr->u.ageing_time);
 		break;
 	case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING:
-		priv->vlan_aware = attr->u.vlan_filtering;
-		ocelot_port_vlan_filtering(ocelot, port, priv->vlan_aware);
+		ocelot_port_vlan_filtering(ocelot, port,
+					   attr->u.vlan_filtering);
 		break;
 	case SWITCHDEV_ATTR_ID_BRIDGE_MC_DISABLED:
 		ocelot_port_attr_mc_set(ocelot, port, !attr->u.mc_disabled);
@@ -1860,7 +1863,6 @@ static int ocelot_netdevice_port_event(struct net_device *dev,
 			} else {
 				err = ocelot_port_bridge_leave(ocelot, port,
 							       info->upper_dev);
-				priv->vlan_aware = false;
 			}
 		}
 		if (netif_is_lag_master(info->upper_dev)) {
diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h
index c259114c48fd..2ff09de34b0d 100644
--- a/drivers/net/ethernet/mscc/ocelot.h
+++ b/drivers/net/ethernet/mscc/ocelot.h
@@ -66,8 +66,6 @@ struct ocelot_port_private {
 	struct phy_device *phy;
 	u8 chip_port;
 
-	u8 vlan_aware;
-
 	phy_interface_t phy_mode;
 	struct phy *serdes;
 
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index 64cbbbe74a36..a699b24b08de 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -411,6 +411,8 @@ struct ocelot_port {
 
 	void __iomem			*regs;
 
+	bool				vlan_aware;
+
 	/* Ingress default VLAN (pvid) */
 	u16				pvid;
 
@@ -527,7 +529,7 @@ int ocelot_port_bridge_leave(struct ocelot *ocelot, int port,
 int ocelot_fdb_dump(struct ocelot *ocelot, int port,
 		    dsa_fdb_dump_cb_t *cb, void *data);
 int ocelot_fdb_add(struct ocelot *ocelot, int port,
-		   const unsigned char *addr, u16 vid, bool vlan_aware);
+		   const unsigned char *addr, u16 vid);
 int ocelot_fdb_del(struct ocelot *ocelot, int port,
 		   const unsigned char *addr, u16 vid);
 int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid,
-- 
2.20.1


From 374fe08405a06343061e23222b30191289cb7a2b Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 14 Apr 2020 15:39:52 -0700
Subject: [PATCH 19/19] net: stmmac: dwmac-sunxi: Provide TX and RX fifo sizes

[ Upstream commit 806fd188ce2a4f8b587e83e73c478e6484fbfa55 ]

After commit bfcb813203e619a8960a819bf533ad2a108d8105 ("net: dsa:
configure the MTU for switch ports") my Lamobo R1 platform which uses
an allwinner,sun7i-a20-gmac compatible Ethernet MAC started to fail
by rejecting a MTU of 1536. The reason for that is that the DMA
capabilities are not readable on this version of the IP, and there
is also no 'tx-fifo-depth' property being provided in Device Tree. The
property is documented as optional, and is not provided.

Chen-Yu indicated that the FIFO sizes are 4KB for TX and 16KB for RX, so
provide these values through platform data as an immediate fix until
various Device Tree sources get updated accordingly.

Fixes: eaf4fac47807 ("net: stmmac: Do not accept invalid MTU values")
Suggested-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Acked-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
index 7d40760e9ba8..0e1ca2cba3c7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
@@ -150,6 +150,8 @@ static int sun7i_gmac_probe(struct platform_device *pdev)
 	plat_dat->init = sun7i_gmac_init;
 	plat_dat->exit = sun7i_gmac_exit;
 	plat_dat->fix_mac_speed = sun7i_fix_speed;
+	plat_dat->tx_fifo_size = 4096;
+	plat_dat->rx_fifo_size = 16384;
 
 	ret = sun7i_gmac_init(pdev, plat_dat->bsp_priv);
 	if (ret)
-- 
2.20.1


[-- Attachment #3: net_56.mbox --]
[-- Type: Application/Octet-Stream, Size: 63120 bytes --]

From e494875c39a38940980bd3ddd30b729a6512fc68 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 16 Apr 2020 17:57:40 +0200
Subject: [PATCH 01/21] amd-xgbe: Use __napi_schedule() in BH context

[ Upstream commit d518691cbd3be3dae218e05cca3f3fc9b2f1aa77 ]

The driver uses __napi_schedule_irqoff() which is fine as long as it is
invoked with disabled interrupts by everybody. Since the commit
mentioned below the driver may invoke xgbe_isr_task() in tasklet/softirq
context. This may lead to list corruption if another driver uses
__napi_schedule_irqoff() in IRQ context.

Use __napi_schedule() which safe to use from IRQ and softirq context.

Fixes: 85b85c853401d ("amd-xgbe: Re-issue interrupt if interrupt status not cleared")
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Acked-by: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe-drv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index b71f9b04a51e..a87264f95f1a 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -514,7 +514,7 @@ static void xgbe_isr_task(unsigned long data)
 				xgbe_disable_rx_tx_ints(pdata);
 
 				/* Turn on polling */
-				__napi_schedule_irqoff(&pdata->napi);
+				__napi_schedule(&pdata->napi);
 			}
 		} else {
 			/* Don't clear Rx/Tx status if doing per channel DMA
-- 
2.20.1


From b5c926579b5179427687578ddbd514e80ec73249 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Tue, 7 Apr 2020 13:23:21 +0000
Subject: [PATCH 02/21] hsr: check protocol version in hsr_newlink()

[ Upstream commit 4faab8c446def7667adf1f722456c2f4c304069c ]

In the current hsr code, only 0 and 1 protocol versions are valid.
But current hsr code doesn't check the version, which is received by
userspace.

Test commands:
    ip link add dummy0 type dummy
    ip link add dummy1 type dummy
    ip link add hsr0 type hsr slave1 dummy0 slave2 dummy1 version 4

In the test commands, version 4 is invalid.
So, the command should be failed.

After this patch, following error will occur.
"Error: hsr: Only versions 0..1 are supported."

Fixes: ee1c27977284 ("net/hsr: Added support for HSR v1")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/hsr/hsr_netlink.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c
index fae21c863b1f..55c0b2e872a5 100644
--- a/net/hsr/hsr_netlink.c
+++ b/net/hsr/hsr_netlink.c
@@ -61,10 +61,16 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev,
 	else
 		multicast_spec = nla_get_u8(data[IFLA_HSR_MULTICAST_SPEC]);
 
-	if (!data[IFLA_HSR_VERSION])
+	if (!data[IFLA_HSR_VERSION]) {
 		hsr_version = 0;
-	else
+	} else {
 		hsr_version = nla_get_u8(data[IFLA_HSR_VERSION]);
+		if (hsr_version > 1) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Only versions 0..1 are supported");
+			return -EINVAL;
+		}
+	}
 
 	return hsr_dev_finalize(dev, link, multicast_spec, hsr_version);
 }
-- 
2.20.1


From 918d22a29ecb62af02bddde7c0f1594c6f2488ec Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Michael=20Wei=C3=9F?= <michael.weiss@aisec.fraunhofer.de>
Date: Tue, 7 Apr 2020 13:11:48 +0200
Subject: [PATCH 03/21] l2tp: Allow management of tunnels and session in user
 namespace
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 2abe05234f2e892728c388169631e4b99f354c86 ]

Creation and management of L2TPv3 tunnels and session through netlink
requires CAP_NET_ADMIN. However, a process with CAP_NET_ADMIN in a
non-initial user namespace gets an EPERM due to the use of the
genetlink GENL_ADMIN_PERM flag. Thus, management of L2TP VPNs inside
an unprivileged container won't work.

We replaced the GENL_ADMIN_PERM by the GENL_UNS_ADMIN_PERM flag
similar to other network modules which also had this problem, e.g.,
openvswitch (commit 4a92602aa1cd "openvswitch: allow management from
inside user namespaces") and nl80211 (commit 5617c6cd6f844 "nl80211:
Allow privileged operations from user namespaces").

I tested this in the container runtime trustm3 (trustm3.github.io)
and was able to create l2tp tunnels and sessions in unpriviliged
(user namespaced) containers using a private network namespace.
For other runtimes such as docker or lxc this should work, too.

Signed-off-by: Michael Weiß <michael.weiss@aisec.fraunhofer.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_netlink.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index f5a9bdc4980c..ebb381c3f1b9 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -920,51 +920,51 @@ static const struct genl_ops l2tp_nl_ops[] = {
 		.cmd = L2TP_CMD_TUNNEL_CREATE,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_tunnel_create,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_TUNNEL_DELETE,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_tunnel_delete,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_TUNNEL_MODIFY,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_tunnel_modify,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_TUNNEL_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_tunnel_get,
 		.dumpit = l2tp_nl_cmd_tunnel_dump,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_SESSION_CREATE,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_session_create,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_SESSION_DELETE,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_session_delete,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_SESSION_MODIFY,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_session_modify,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_SESSION_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_session_get,
 		.dumpit = l2tp_nl_cmd_session_dump,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 };
 
-- 
2.20.1


From 22775fb95803665684ab0843a98a8306b586133e Mon Sep 17 00:00:00 2001
From: DENG Qingfang <dqfext@gmail.com>
Date: Tue, 14 Apr 2020 14:34:08 +0800
Subject: [PATCH 04/21] net: dsa: mt7530: fix tagged frames pass-through in
 VLAN-unaware mode
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit e045124e93995fe01e42ed530003ddba5d55db4f ]

In VLAN-unaware mode, the Egress Tag (EG_TAG) field in Port VLAN
Control register must be set to Consistent to let tagged frames pass
through as is, otherwise their tags will be stripped.

Fixes: 83163f7dca56 ("net: dsa: mediatek: add VLAN support for MT7530")
Signed-off-by: DENG Qingfang <dqfext@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Tested-by: René van Dorst <opensource@vdorst.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mt7530.c | 18 ++++++++++++------
 drivers/net/dsa/mt7530.h |  7 +++++++
 2 files changed, 19 insertions(+), 6 deletions(-)

diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index 9b0de2852c69..eab19fc1927d 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -857,8 +857,9 @@ mt7530_port_set_vlan_unaware(struct dsa_switch *ds, int port)
 	 */
 	mt7530_rmw(priv, MT7530_PCR_P(port), PCR_PORT_VLAN_MASK,
 		   MT7530_PORT_MATRIX_MODE);
-	mt7530_rmw(priv, MT7530_PVC_P(port), VLAN_ATTR_MASK,
-		   VLAN_ATTR(MT7530_VLAN_TRANSPARENT));
+	mt7530_rmw(priv, MT7530_PVC_P(port), VLAN_ATTR_MASK | PVC_EG_TAG_MASK,
+		   VLAN_ATTR(MT7530_VLAN_TRANSPARENT) |
+		   PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT));
 
 	for (i = 0; i < MT7530_NUM_PORTS; i++) {
 		if (dsa_is_user_port(ds, i) &&
@@ -874,8 +875,8 @@ mt7530_port_set_vlan_unaware(struct dsa_switch *ds, int port)
 	if (all_user_ports_removed) {
 		mt7530_write(priv, MT7530_PCR_P(MT7530_CPU_PORT),
 			     PCR_MATRIX(dsa_user_ports(priv->ds)));
-		mt7530_write(priv, MT7530_PVC_P(MT7530_CPU_PORT),
-			     PORT_SPEC_TAG);
+		mt7530_write(priv, MT7530_PVC_P(MT7530_CPU_PORT), PORT_SPEC_TAG
+			     | PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT));
 	}
 }
 
@@ -901,8 +902,9 @@ mt7530_port_set_vlan_aware(struct dsa_switch *ds, int port)
 	/* Set the port as a user port which is to be able to recognize VID
 	 * from incoming packets before fetching entry within the VLAN table.
 	 */
-	mt7530_rmw(priv, MT7530_PVC_P(port), VLAN_ATTR_MASK,
-		   VLAN_ATTR(MT7530_VLAN_USER));
+	mt7530_rmw(priv, MT7530_PVC_P(port), VLAN_ATTR_MASK | PVC_EG_TAG_MASK,
+		   VLAN_ATTR(MT7530_VLAN_USER) |
+		   PVC_EG_TAG(MT7530_VLAN_EG_DISABLED));
 }
 
 static void
@@ -1333,6 +1335,10 @@ mt7530_setup(struct dsa_switch *ds)
 			mt7530_cpu_port_enable(priv, i);
 		else
 			mt7530_port_disable(ds, i);
+
+		/* Enable consistent egress tag */
+		mt7530_rmw(priv, MT7530_PVC_P(i), PVC_EG_TAG_MASK,
+			   PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT));
 	}
 
 	/* Setup port 5 */
diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h
index ccb9da8cad0d..9a769c6b7700 100644
--- a/drivers/net/dsa/mt7530.h
+++ b/drivers/net/dsa/mt7530.h
@@ -167,9 +167,16 @@ enum mt7530_port_mode {
 /* Register for port vlan control */
 #define MT7530_PVC_P(x)			(0x2010 + ((x) * 0x100))
 #define  PORT_SPEC_TAG			BIT(5)
+#define  PVC_EG_TAG(x)			(((x) & 0x7) << 8)
+#define  PVC_EG_TAG_MASK		PVC_EG_TAG(7)
 #define  VLAN_ATTR(x)			(((x) & 0x3) << 6)
 #define  VLAN_ATTR_MASK			VLAN_ATTR(3)
 
+enum mt7530_vlan_port_eg_tag {
+	MT7530_VLAN_EG_DISABLED = 0,
+	MT7530_VLAN_EG_CONSISTENT = 1,
+};
+
 enum mt7530_vlan_port_attr {
 	MT7530_VLAN_USER = 0,
 	MT7530_VLAN_TRANSPARENT = 3,
-- 
2.20.1


From 201d7d9f7bfef8c796cd767f703fc8a2b3754afb Mon Sep 17 00:00:00 2001
From: Taras Chornyi <taras.chornyi@plvision.eu>
Date: Thu, 9 Apr 2020 20:25:24 +0300
Subject: [PATCH 05/21] net: ipv4: devinet: Fix crash when add/del multicast IP
 with autojoin

[ Upstream commit 690cc86321eb9bcee371710252742fb16fe96824 ]

When CONFIG_IP_MULTICAST is not set and multicast ip is added to the device
with autojoin flag or when multicast ip is deleted kernel will crash.

steps to reproduce:

ip addr add 224.0.0.0/32 dev eth0
ip addr del 224.0.0.0/32 dev eth0

or

ip addr add 224.0.0.0/32 dev eth0 autojoin

Unable to handle kernel NULL pointer dereference at virtual address 0000000000000088
 pc : _raw_write_lock_irqsave+0x1e0/0x2ac
 lr : lock_sock_nested+0x1c/0x60
 Call trace:
  _raw_write_lock_irqsave+0x1e0/0x2ac
  lock_sock_nested+0x1c/0x60
  ip_mc_config.isra.28+0x50/0xe0
  inet_rtm_deladdr+0x1a8/0x1f0
  rtnetlink_rcv_msg+0x120/0x350
  netlink_rcv_skb+0x58/0x120
  rtnetlink_rcv+0x14/0x20
  netlink_unicast+0x1b8/0x270
  netlink_sendmsg+0x1a0/0x3b0
  ____sys_sendmsg+0x248/0x290
  ___sys_sendmsg+0x80/0xc0
  __sys_sendmsg+0x68/0xc0
  __arm64_sys_sendmsg+0x20/0x30
  el0_svc_common.constprop.2+0x88/0x150
  do_el0_svc+0x20/0x80
 el0_sync_handler+0x118/0x190
  el0_sync+0x140/0x180

Fixes: 93a714d6b53d ("multicast: Extend ip address command to enable multicast group join/leave on")
Signed-off-by: Taras Chornyi <taras.chornyi@plvision.eu>
Signed-off-by: Vadym Kochan <vadym.kochan@plvision.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/devinet.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index e4632bd2026d..458dc6eb5a68 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -614,12 +614,15 @@ struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix,
 	return NULL;
 }
 
-static int ip_mc_config(struct sock *sk, bool join, const struct in_ifaddr *ifa)
+static int ip_mc_autojoin_config(struct net *net, bool join,
+				 const struct in_ifaddr *ifa)
 {
+#if defined(CONFIG_IP_MULTICAST)
 	struct ip_mreqn mreq = {
 		.imr_multiaddr.s_addr = ifa->ifa_address,
 		.imr_ifindex = ifa->ifa_dev->dev->ifindex,
 	};
+	struct sock *sk = net->ipv4.mc_autojoin_sk;
 	int ret;
 
 	ASSERT_RTNL();
@@ -632,6 +635,9 @@ static int ip_mc_config(struct sock *sk, bool join, const struct in_ifaddr *ifa)
 	release_sock(sk);
 
 	return ret;
+#else
+	return -EOPNOTSUPP;
+#endif
 }
 
 static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -675,7 +681,7 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
 			continue;
 
 		if (ipv4_is_multicast(ifa->ifa_address))
-			ip_mc_config(net->ipv4.mc_autojoin_sk, false, ifa);
+			ip_mc_autojoin_config(net, false, ifa);
 		__inet_del_ifa(in_dev, ifap, 1, nlh, NETLINK_CB(skb).portid);
 		return 0;
 	}
@@ -940,8 +946,7 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
 		 */
 		set_ifa_lifetime(ifa, valid_lft, prefered_lft);
 		if (ifa->ifa_flags & IFA_F_MCAUTOJOIN) {
-			int ret = ip_mc_config(net->ipv4.mc_autojoin_sk,
-					       true, ifa);
+			int ret = ip_mc_autojoin_config(net, true, ifa);
 
 			if (ret < 0) {
 				inet_free_ifa(ifa);
-- 
2.20.1


From ef823f8775cd18821d82d9c2071a2f74b22f4cfc Mon Sep 17 00:00:00 2001
From: Tim Stallard <code@timstallard.me.uk>
Date: Fri, 3 Apr 2020 21:26:21 +0100
Subject: [PATCH 06/21] net: ipv6: do not consider routes via gateways for
 anycast address check

[ Upstream commit 03e2a984b6165621f287fadf5f4b5cd8b58dcaba ]

The behaviour for what is considered an anycast address changed in
commit 45e4fd26683c ("ipv6: Only create RTF_CACHE routes after
encountering pmtu exception"). This now considers the first
address in a subnet where there is a route via a gateway
to be an anycast address.

This breaks path MTU discovery and traceroutes when a host in a
remote network uses the address at the start of a prefix
(eg 2600:: advertised as 2600::/48 in the DFZ) as ICMP errors
will not be sent to anycast addresses.

This patch excludes any routes with a gateway, or via point to
point links, like the behaviour previously from
rt6_is_gw_or_nonexthop in net/ipv6/route.c.

This can be tested with:
ip link add v1 type veth peer name v2
ip netns add test
ip netns exec test ip link set lo up
ip link set v2 netns test
ip link set v1 up
ip netns exec test ip link set v2 up
ip addr add 2001:db8::1/64 dev v1 nodad
ip addr add 2001:db8:100:: dev lo nodad
ip netns exec test ip addr add 2001:db8::2/64 dev v2 nodad
ip netns exec test ip route add unreachable 2001:db8:1::1
ip netns exec test ip route add 2001:db8:100::/64 via 2001:db8::1
ip netns exec test sysctl net.ipv6.conf.all.forwarding=1
ip route add 2001:db8:1::1 via 2001:db8::2
ping -I 2001:db8::1 2001:db8:1::1 -c1
ping -I 2001:db8:100:: 2001:db8:1::1 -c1
ip addr delete 2001:db8:100:: dev lo
ip netns delete test

Currently the first ping will get back a destination unreachable ICMP
error, but the second will never get a response, with "icmp6_send:
acast source" logged. After this patch, both get destination
unreachable ICMP replies.

Fixes: 45e4fd26683c ("ipv6: Only create RTF_CACHE routes after encountering pmtu exception")
Signed-off-by: Tim Stallard <code@timstallard.me.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_route.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index b69c16cbbf71..2d0d91070268 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -254,6 +254,7 @@ static inline bool ipv6_anycast_destination(const struct dst_entry *dst,
 
 	return rt->rt6i_flags & RTF_ANYCAST ||
 		(rt->rt6i_dst.plen < 127 &&
+		 !(rt->rt6i_flags & (RTF_GATEWAY | RTF_NONEXTHOP)) &&
 		 ipv6_addr_equal(&rt->rt6i_dst.addr, daddr));
 }
 
-- 
2.20.1


From 008505a87a1e1580dc2b781e7c602f34f53064e5 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Thu, 9 Apr 2020 14:08:08 +0000
Subject: [PATCH 07/21] net: macsec: fix using wrong structure in
 macsec_changelink()

[ Upstream commit 022e9d6090599c0593c78e87dc9ba98a290e6bc4 ]

In the macsec_changelink(), "struct macsec_tx_sa tx_sc" is used to
store "macsec_secy.tx_sc".
But, the struct type of tx_sc is macsec_tx_sc, not macsec_tx_sa.
So, the macsec_tx_sc should be used instead.

Test commands:
    ip link add dummy0 type dummy
    ip link add macsec0 link dummy0 type macsec
    ip link set macsec0 type macsec encrypt off

Splat looks like:
[61119.963483][ T9335] ==================================================================
[61119.964709][ T9335] BUG: KASAN: slab-out-of-bounds in macsec_changelink.part.34+0xb6/0x200 [macsec]
[61119.965787][ T9335] Read of size 160 at addr ffff888020d69c68 by task ip/9335
[61119.966699][ T9335]
[61119.966979][ T9335] CPU: 0 PID: 9335 Comm: ip Not tainted 5.6.0+ #503
[61119.967791][ T9335] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[61119.968914][ T9335] Call Trace:
[61119.969324][ T9335]  dump_stack+0x96/0xdb
[61119.969809][ T9335]  ? macsec_changelink.part.34+0xb6/0x200 [macsec]
[61119.970554][ T9335]  print_address_description.constprop.5+0x1be/0x360
[61119.971294][ T9335]  ? macsec_changelink.part.34+0xb6/0x200 [macsec]
[61119.971973][ T9335]  ? macsec_changelink.part.34+0xb6/0x200 [macsec]
[61119.972703][ T9335]  __kasan_report+0x12a/0x170
[61119.973323][ T9335]  ? macsec_changelink.part.34+0xb6/0x200 [macsec]
[61119.973942][ T9335]  kasan_report+0xe/0x20
[61119.974397][ T9335]  check_memory_region+0x149/0x1a0
[61119.974866][ T9335]  memcpy+0x1f/0x50
[61119.975209][ T9335]  macsec_changelink.part.34+0xb6/0x200 [macsec]
[61119.975825][ T9335]  ? macsec_get_stats64+0x3e0/0x3e0 [macsec]
[61119.976451][ T9335]  ? kernel_text_address+0x111/0x120
[61119.976990][ T9335]  ? pskb_expand_head+0x25f/0xe10
[61119.977503][ T9335]  ? stack_trace_save+0x82/0xb0
[61119.977986][ T9335]  ? memset+0x1f/0x40
[61119.978397][ T9335]  ? __nla_validate_parse+0x98/0x1ab0
[61119.978936][ T9335]  ? macsec_alloc_tfm+0x90/0x90 [macsec]
[61119.979511][ T9335]  ? __kasan_slab_free+0x111/0x150
[61119.980021][ T9335]  ? kfree+0xce/0x2f0
[61119.980700][ T9335]  ? netlink_trim+0x196/0x1f0
[61119.981420][ T9335]  ? nla_memcpy+0x90/0x90
[61119.982036][ T9335]  ? register_lock_class+0x19e0/0x19e0
[61119.982776][ T9335]  ? memcpy+0x34/0x50
[61119.983327][ T9335]  __rtnl_newlink+0x922/0x1270
[ ... ]

Fixes: 3cf3227a21d1 ("net: macsec: hardware offloading infrastructure")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macsec.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 92bc2b2df660..061aada4748a 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -3463,7 +3463,7 @@ static int macsec_changelink(struct net_device *dev, struct nlattr *tb[],
 			     struct netlink_ext_ack *extack)
 {
 	struct macsec_dev *macsec = macsec_priv(dev);
-	struct macsec_tx_sa tx_sc;
+	struct macsec_tx_sc tx_sc;
 	struct macsec_secy secy;
 	int ret;
 
-- 
2.20.1


From a7673bb8b5c1dc6105f5bcb3847ef34859fbfe73 Mon Sep 17 00:00:00 2001
From: Atsushi Nemoto <atsushi.nemoto@sord.co.jp>
Date: Fri, 10 Apr 2020 12:16:16 +0900
Subject: [PATCH 08/21] net: phy: micrel: use genphy_read_status for KSZ9131

[ Upstream commit 68dac3eb50be32957ae6e1e6da9281a3b7c6658b ]

KSZ9131 will not work with some switches due to workaround for KSZ9031
introduced in commit d2fd719bcb0e83cb39cfee22ee800f98a56eceb3
("net/phy: micrel: Add workaround for bad autoneg").
Use genphy_read_status instead of dedicated ksz9031_read_status.

Fixes: bff5b4b37372 ("net: phy: micrel: add Microchip KSZ9131 initial driver")
Signed-off-by: Atsushi Nemoto <atsushi.nemoto@sord.co.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/micrel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 51b64f087717..663c68ed6ef9 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -1154,7 +1154,7 @@ static struct phy_driver ksphy_driver[] = {
 	.driver_data	= &ksz9021_type,
 	.probe		= kszphy_probe,
 	.config_init	= ksz9131_config_init,
-	.read_status	= ksz9031_read_status,
+	.read_status	= genphy_read_status,
 	.ack_interrupt	= kszphy_ack_interrupt,
 	.config_intr	= kszphy_config_intr,
 	.get_sset_count = kszphy_get_sset_count,
-- 
2.20.1


From e8cb8a2b89f4aa23d0137f5b604e45cc43bb7e20 Mon Sep 17 00:00:00 2001
From: Wang Wenhu <wenhu.wang@vivo.com>
Date: Wed, 8 Apr 2020 19:53:53 -0700
Subject: [PATCH 09/21] net: qrtr: send msgs from local of same id as broadcast

[ Upstream commit 6dbf02acef69b0742c238574583b3068afbd227c ]

If the local node id(qrtr_local_nid) is not modified after its
initialization, it equals to the broadcast node id(QRTR_NODE_BCAST).
So the messages from local node should not be taken as broadcast
and keep the process going to send them out anyway.

The definitions are as follow:
static unsigned int qrtr_local_nid = NUMA_NO_NODE;

Fixes: fdf5fd397566 ("net: qrtr: Broadcast messages only from control port")
Signed-off-by: Wang Wenhu <wenhu.wang@vivo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/qrtr/qrtr.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index 5a8e42ad1504..b7b854621c26 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -907,20 +907,21 @@ static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 
 	node = NULL;
 	if (addr->sq_node == QRTR_NODE_BCAST) {
-		enqueue_fn = qrtr_bcast_enqueue;
-		if (addr->sq_port != QRTR_PORT_CTRL) {
+		if (addr->sq_port != QRTR_PORT_CTRL &&
+		    qrtr_local_nid != QRTR_NODE_BCAST) {
 			release_sock(sk);
 			return -ENOTCONN;
 		}
+		enqueue_fn = qrtr_bcast_enqueue;
 	} else if (addr->sq_node == ipc->us.sq_node) {
 		enqueue_fn = qrtr_local_enqueue;
 	} else {
-		enqueue_fn = qrtr_node_enqueue;
 		node = qrtr_node_lookup(addr->sq_node);
 		if (!node) {
 			release_sock(sk);
 			return -ECONNRESET;
 		}
+		enqueue_fn = qrtr_node_enqueue;
 	}
 
 	plen = (len + 3) & ~3;
-- 
2.20.1


From 75b088667aa8cfccc1a9a541655415dd8a4c4dc7 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Date: Mon, 6 Apr 2020 14:39:32 +0300
Subject: [PATCH 10/21] net: revert default NAPI poll timeout to 2 jiffies

[ Upstream commit a4837980fd9fa4c70a821d11831698901baef56b ]

For HZ < 1000 timeout 2000us rounds up to 1 jiffy but expires randomly
because next timer interrupt could come shortly after starting softirq.

For commonly used CONFIG_HZ=1000 nothing changes.

Fixes: 7acf8a1e8a28 ("Replace 2 jiffies with sysctl netdev_budget_usecs to enable softirq tuning")
Reported-by: Dmitry Yakunin <zeil@yandex-team.ru>
Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 500bba8874b0..77c154107b0d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4140,7 +4140,8 @@ EXPORT_SYMBOL(netdev_max_backlog);
 
 int netdev_tstamp_prequeue __read_mostly = 1;
 int netdev_budget __read_mostly = 300;
-unsigned int __read_mostly netdev_budget_usecs = 2000;
+/* Must be at least 2 jiffes to guarantee 1 jiffy timeout */
+unsigned int __read_mostly netdev_budget_usecs = 2 * USEC_PER_SEC / HZ;
 int weight_p __read_mostly = 64;           /* old backlog weight */
 int dev_weight_rx_bias __read_mostly = 1;  /* bias for backlog weight */
 int dev_weight_tx_bias __read_mostly = 1;  /* bias for output_queue quota */
-- 
2.20.1


From 96e749ea2e026109b65439f7a6272fa008fb6a65 Mon Sep 17 00:00:00 2001
From: Gilberto Bertin <me@jibi.io>
Date: Fri, 10 Apr 2020 18:20:59 +0200
Subject: [PATCH 11/21] net: tun: record RX queue in skb before
 do_xdp_generic()

[ Upstream commit 3fe260e00cd0bf0be853c48fcc1e19853df615bb ]

This allows netif_receive_generic_xdp() to correctly determine the RX
queue from which the skb is coming, so that the context passed to the
XDP program will contain the correct RX queue index.

Signed-off-by: Gilberto Bertin <me@jibi.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 9de9b7d8aedd..3063f2c9fa63 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1925,6 +1925,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 
 	skb_reset_network_header(skb);
 	skb_probe_transport_header(skb);
+	skb_record_rx_queue(skb, tfile->queue_index);
 
 	if (skb_xdp) {
 		struct bpf_prog *xdp_prog;
@@ -2498,6 +2499,7 @@ static int tun_xdp_one(struct tun_struct *tun,
 	skb->protocol = eth_type_trans(skb, tun->dev);
 	skb_reset_network_header(skb);
 	skb_probe_transport_header(skb);
+	skb_record_rx_queue(skb, tfile->queue_index);
 
 	if (skb_xdp) {
 		err = do_xdp_generic(xdp_prog, skb);
@@ -2509,7 +2511,6 @@ static int tun_xdp_one(struct tun_struct *tun,
 	    !tfile->detached)
 		rxhash = __skb_get_hash_symmetric(skb);
 
-	skb_record_rx_queue(skb, tfile->queue_index);
 	netif_receive_skb(skb);
 
 	/* No need for get_cpu_ptr() here since this function is
-- 
2.20.1


From c74253dbb298d2dc364908d4bbe87944b4b10220 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ren=C3=A9=20van=20Dorst?= <opensource@vdorst.com>
Date: Mon, 6 Apr 2020 05:42:53 +0800
Subject: [PATCH 12/21] net: dsa: mt7530: move mt7623 settings out off the
 mt7530
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 84d2f7b708c374a15a2abe092a74e0e47d018286 ]

Moving mt7623 logic out off mt7530, is required to make hardware setting
consistent after we introduce phylink to mtk driver.

Fixes: ca366d6c889b ("net: dsa: mt7530: Convert to PHYLINK API")
Reviewed-by: Sean Wang <sean.wang@mediatek.com>
Tested-by: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: René van Dorst <opensource@vdorst.com>
Tested-by: Frank Wunderlich <frank-w@public-files.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mt7530.c | 85 ----------------------------------------
 drivers/net/dsa/mt7530.h | 10 -----
 2 files changed, 95 deletions(-)

diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index eab19fc1927d..0123498242b9 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -66,58 +66,6 @@ static const struct mt7530_mib_desc mt7530_mib[] = {
 	MIB_DESC(1, 0xb8, "RxArlDrop"),
 };
 
-static int
-mt7623_trgmii_write(struct mt7530_priv *priv,  u32 reg, u32 val)
-{
-	int ret;
-
-	ret =  regmap_write(priv->ethernet, TRGMII_BASE(reg), val);
-	if (ret < 0)
-		dev_err(priv->dev,
-			"failed to priv write register\n");
-	return ret;
-}
-
-static u32
-mt7623_trgmii_read(struct mt7530_priv *priv, u32 reg)
-{
-	int ret;
-	u32 val;
-
-	ret = regmap_read(priv->ethernet, TRGMII_BASE(reg), &val);
-	if (ret < 0) {
-		dev_err(priv->dev,
-			"failed to priv read register\n");
-		return ret;
-	}
-
-	return val;
-}
-
-static void
-mt7623_trgmii_rmw(struct mt7530_priv *priv, u32 reg,
-		  u32 mask, u32 set)
-{
-	u32 val;
-
-	val = mt7623_trgmii_read(priv, reg);
-	val &= ~mask;
-	val |= set;
-	mt7623_trgmii_write(priv, reg, val);
-}
-
-static void
-mt7623_trgmii_set(struct mt7530_priv *priv, u32 reg, u32 val)
-{
-	mt7623_trgmii_rmw(priv, reg, 0, val);
-}
-
-static void
-mt7623_trgmii_clear(struct mt7530_priv *priv, u32 reg, u32 val)
-{
-	mt7623_trgmii_rmw(priv, reg, val, 0);
-}
-
 static int
 core_read_mmd_indirect(struct mt7530_priv *priv, int prtad, int devad)
 {
@@ -530,27 +478,6 @@ mt7530_pad_clk_setup(struct dsa_switch *ds, int mode)
 		for (i = 0 ; i < NUM_TRGMII_CTRL; i++)
 			mt7530_rmw(priv, MT7530_TRGMII_RD(i),
 				   RD_TAP_MASK, RD_TAP(16));
-	else
-		if (priv->id != ID_MT7621)
-			mt7623_trgmii_set(priv, GSW_INTF_MODE,
-					  INTF_MODE_TRGMII);
-
-	return 0;
-}
-
-static int
-mt7623_pad_clk_setup(struct dsa_switch *ds)
-{
-	struct mt7530_priv *priv = ds->priv;
-	int i;
-
-	for (i = 0 ; i < NUM_TRGMII_CTRL; i++)
-		mt7623_trgmii_write(priv, GSW_TRGMII_TD_ODT(i),
-				    TD_DM_DRVP(8) | TD_DM_DRVN(8));
-
-	mt7623_trgmii_set(priv, GSW_TRGMII_RCK_CTRL, RX_RST | RXC_DQSISEL);
-	mt7623_trgmii_clear(priv, GSW_TRGMII_RCK_CTRL, RX_RST);
-
 	return 0;
 }
 
@@ -1258,10 +1185,6 @@ mt7530_setup(struct dsa_switch *ds)
 	dn = dsa_to_port(ds, MT7530_CPU_PORT)->master->dev.of_node->parent;
 
 	if (priv->id == ID_MT7530) {
-		priv->ethernet = syscon_node_to_regmap(dn);
-		if (IS_ERR(priv->ethernet))
-			return PTR_ERR(priv->ethernet);
-
 		regulator_set_voltage(priv->core_pwr, 1000000, 1000000);
 		ret = regulator_enable(priv->core_pwr);
 		if (ret < 0) {
@@ -1427,14 +1350,6 @@ static void mt7530_phylink_mac_config(struct dsa_switch *ds, int port,
 		/* Setup TX circuit incluing relevant PAD and driving */
 		mt7530_pad_clk_setup(ds, state->interface);
 
-		if (priv->id == ID_MT7530) {
-			/* Setup RX circuit, relevant PAD and driving on the
-			 * host which must be placed after the setup on the
-			 * device side is all finished.
-			 */
-			mt7623_pad_clk_setup(ds);
-		}
-
 		priv->p6_interface = state->interface;
 		break;
 	default:
diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h
index 9a769c6b7700..756140b7dfd5 100644
--- a/drivers/net/dsa/mt7530.h
+++ b/drivers/net/dsa/mt7530.h
@@ -275,7 +275,6 @@ enum mt7530_vlan_port_attr {
 
 /* Registers for TRGMII on the both side */
 #define MT7530_TRGMII_RCK_CTRL		0x7a00
-#define GSW_TRGMII_RCK_CTRL		0x300
 #define  RX_RST				BIT(31)
 #define  RXC_DQSISEL			BIT(30)
 #define  DQSI1_TAP_MASK			(0x7f << 8)
@@ -284,31 +283,24 @@ enum mt7530_vlan_port_attr {
 #define  DQSI0_TAP(x)			((x) & 0x7f)
 
 #define MT7530_TRGMII_RCK_RTT		0x7a04
-#define GSW_TRGMII_RCK_RTT		0x304
 #define  DQS1_GATE			BIT(31)
 #define  DQS0_GATE			BIT(30)
 
 #define MT7530_TRGMII_RD(x)		(0x7a10 + (x) * 8)
-#define GSW_TRGMII_RD(x)		(0x310 + (x) * 8)
 #define  BSLIP_EN			BIT(31)
 #define  EDGE_CHK			BIT(30)
 #define  RD_TAP_MASK			0x7f
 #define  RD_TAP(x)			((x) & 0x7f)
 
-#define GSW_TRGMII_TXCTRL		0x340
 #define MT7530_TRGMII_TXCTRL		0x7a40
 #define  TRAIN_TXEN			BIT(31)
 #define  TXC_INV			BIT(30)
 #define  TX_RST				BIT(28)
 
 #define MT7530_TRGMII_TD_ODT(i)		(0x7a54 + 8 * (i))
-#define GSW_TRGMII_TD_ODT(i)		(0x354 + 8 * (i))
 #define  TD_DM_DRVP(x)			((x) & 0xf)
 #define  TD_DM_DRVN(x)			(((x) & 0xf) << 4)
 
-#define GSW_INTF_MODE			0x390
-#define  INTF_MODE_TRGMII		BIT(1)
-
 #define MT7530_TRGMII_TCK_CTRL		0x7a78
 #define  TCK_TAP(x)			(((x) & 0xf) << 8)
 
@@ -441,7 +433,6 @@ static const char *p5_intf_modes(unsigned int p5_interface)
  * @ds:			The pointer to the dsa core structure
  * @bus:		The bus used for the device and built-in PHY
  * @rstc:		The pointer to reset control used by MCM
- * @ethernet:		The regmap used for access TRGMII-based registers
  * @core_pwr:		The power supplied into the core
  * @io_pwr:		The power supplied into the I/O
  * @reset:		The descriptor for GPIO line tied to its reset pin
@@ -458,7 +449,6 @@ struct mt7530_priv {
 	struct dsa_switch	*ds;
 	struct mii_bus		*bus;
 	struct reset_control	*rstc;
-	struct regmap		*ethernet;
 	struct regulator	*core_pwr;
 	struct regulator	*io_pwr;
 	struct gpio_desc	*reset;
-- 
2.20.1


From 1ddb446a36edaa2b75b2c44c1439fd8c2bee5dae Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ren=C3=A9=20van=20Dorst?= <opensource@vdorst.com>
Date: Mon, 6 Apr 2020 05:42:54 +0800
Subject: [PATCH 13/21] net: ethernet: mediatek: move mt7623 settings out off
 the mt7530
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit a5d75538295b06bc6ade1b9da07b9bee57d1c677 ]

Moving mt7623 logic out off mt7530, is required to make hardware setting
consistent after we introduce phylink to mtk driver.

Fixes: b8fc9f30821e ("net: ethernet: mediatek: Add basic PHYLINK support")
Reviewed-by: Sean Wang <sean.wang@mediatek.com>
Tested-by: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: René van Dorst <opensource@vdorst.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c | 24 ++++++++++++++++++++-
 drivers/net/ethernet/mediatek/mtk_eth_soc.h |  8 +++++++
 2 files changed, 31 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 8c6cfd15481c..b5408c5b954a 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -65,6 +65,17 @@ u32 mtk_r32(struct mtk_eth *eth, unsigned reg)
 	return __raw_readl(eth->base + reg);
 }
 
+u32 mtk_m32(struct mtk_eth *eth, u32 mask, u32 set, unsigned reg)
+{
+	u32 val;
+
+	val = mtk_r32(eth, reg);
+	val &= ~mask;
+	val |= set;
+	mtk_w32(eth, val, reg);
+	return reg;
+}
+
 static int mtk_mdio_busy_wait(struct mtk_eth *eth)
 {
 	unsigned long t_start = jiffies;
@@ -193,7 +204,7 @@ static void mtk_mac_config(struct phylink_config *config, unsigned int mode,
 	struct mtk_mac *mac = container_of(config, struct mtk_mac,
 					   phylink_config);
 	struct mtk_eth *eth = mac->hw;
-	u32 mcr_cur, mcr_new, sid;
+	u32 mcr_cur, mcr_new, sid, i;
 	int val, ge_mode, err;
 
 	/* MT76x8 has no hardware settings between for the MAC */
@@ -255,6 +266,17 @@ static void mtk_mac_config(struct phylink_config *config, unsigned int mode,
 				    PHY_INTERFACE_MODE_TRGMII)
 					mtk_gmac0_rgmii_adjust(mac->hw,
 							       state->speed);
+
+				/* mt7623_pad_clk_setup */
+				for (i = 0 ; i < NUM_TRGMII_CTRL; i++)
+					mtk_w32(mac->hw,
+						TD_DM_DRVP(8) | TD_DM_DRVN(8),
+						TRGMII_TD_ODT(i));
+
+				/* Assert/release MT7623 RXC reset */
+				mtk_m32(mac->hw, 0, RXC_RST | RXC_DQSISEL,
+					TRGMII_RCK_CTRL);
+				mtk_m32(mac->hw, RXC_RST, 0, TRGMII_RCK_CTRL);
 			}
 		}
 
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 85830fe14a1b..454cfcd465fd 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -352,10 +352,13 @@
 #define DQSI0(x)		((x << 0) & GENMASK(6, 0))
 #define DQSI1(x)		((x << 8) & GENMASK(14, 8))
 #define RXCTL_DMWTLAT(x)	((x << 16) & GENMASK(18, 16))
+#define RXC_RST			BIT(31)
 #define RXC_DQSISEL		BIT(30)
 #define RCK_CTRL_RGMII_1000	(RXC_DQSISEL | RXCTL_DMWTLAT(2) | DQSI1(16))
 #define RCK_CTRL_RGMII_10_100	RXCTL_DMWTLAT(2)
 
+#define NUM_TRGMII_CTRL		5
+
 /* TRGMII RXC control register */
 #define TRGMII_TCK_CTRL		0x10340
 #define TXCTL_DMWTLAT(x)	((x << 16) & GENMASK(18, 16))
@@ -363,6 +366,11 @@
 #define TCK_CTRL_RGMII_1000	TXCTL_DMWTLAT(2)
 #define TCK_CTRL_RGMII_10_100	(TXC_INV | TXCTL_DMWTLAT(2))
 
+/* TRGMII TX Drive Strength */
+#define TRGMII_TD_ODT(i)	(0x10354 + 8 * (i))
+#define  TD_DM_DRVP(x)		((x) & 0xf)
+#define  TD_DM_DRVN(x)		(((x) & 0xf) << 4)
+
 /* TRGMII Interface mode register */
 #define INTF_MODE		0x10390
 #define TRGMII_INTF_DIS		BIT(0)
-- 
2.20.1


From 166f1effe4cc6688b76bd2109ef671e4b9c2f6b7 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Mon, 30 Mar 2020 10:21:49 +0300
Subject: [PATCH 14/21] net/mlx5: Fix frequent ioread PCI access during
 recovery

[ Upstream commit 8c702a53bb0a79bfa203ba21ef1caba43673c5b7 ]

High frequency of PCI ioread calls during recovery flow may cause the
following trace on powerpc:

[ 248.670288] EEH: 2100000 reads ignored for recovering device at
location=Slot1 driver=mlx5_core pci addr=0000:01:00.1
[ 248.670331] EEH: Might be infinite loop in mlx5_core driver
[ 248.670361] CPU: 2 PID: 35247 Comm: kworker/u192:11 Kdump: loaded
Tainted: G OE ------------ 4.14.0-115.14.1.el7a.ppc64le #1
[ 248.670425] Workqueue: mlx5_health0000:01:00.1 health_recover_work
[mlx5_core]
[ 248.670471] Call Trace:
[ 248.670492] [c00020391c11b960] [c000000000c217ac] dump_stack+0xb0/0xf4
(unreliable)
[ 248.670548] [c00020391c11b9a0] [c000000000045818]
eeh_check_failure+0x5c8/0x630
[ 248.670631] [c00020391c11ba50] [c00000000068fce4]
ioread32be+0x114/0x1c0
[ 248.670692] [c00020391c11bac0] [c00800000dd8b400]
mlx5_error_sw_reset+0x160/0x510 [mlx5_core]
[ 248.670752] [c00020391c11bb60] [c00800000dd75824]
mlx5_disable_device+0x34/0x1d0 [mlx5_core]
[ 248.670822] [c00020391c11bbe0] [c00800000dd8affc]
health_recover_work+0x11c/0x3c0 [mlx5_core]
[ 248.670891] [c00020391c11bc80] [c000000000164fcc]
process_one_work+0x1bc/0x5f0
[ 248.670955] [c00020391c11bd20] [c000000000167f8c]
worker_thread+0xac/0x6b0
[ 248.671015] [c00020391c11bdc0] [c000000000171618] kthread+0x168/0x1b0
[ 248.671067] [c00020391c11be30] [c00000000000b65c]
ret_from_kernel_thread+0x5c/0x80

Reduce the PCI ioread frequency during recovery by using msleep()
instead of cond_resched()

Fixes: 3e5b72ac2f29 ("net/mlx5: Issue SW reset on FW assert")
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Reviewed-by: Feras Daoud <ferasda@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/health.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index d9f4e8c59c1f..68e7ef7ca52d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -243,7 +243,7 @@ void mlx5_error_sw_reset(struct mlx5_core_dev *dev)
 		if (mlx5_get_nic_state(dev) == MLX5_NIC_IFC_DISABLED)
 			break;
 
-		cond_resched();
+		msleep(20);
 	} while (!time_after(jiffies, end));
 
 	if (mlx5_get_nic_state(dev) != MLX5_NIC_IFC_DISABLED) {
-- 
2.20.1


From f02714f0d856f4419932e063083edbb7ec3a07bf Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Tue, 24 Mar 2020 15:04:26 +0200
Subject: [PATCH 15/21] net/mlx5e: Add missing release firmware call

[ Upstream commit d19987ccf57501894fdd8fadc2e55e4a3dd57239 ]

Once driver finishes flashing the firmware image, it should release it.

Fixes: 9c8bca2637b8 ("mlx5: Move firmware flash implementation to devlink")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Reviewed-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/devlink.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index ac108f1e5bd6..184c3eaefbcb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -23,7 +23,10 @@ static int mlx5_devlink_flash_update(struct devlink *devlink,
 	if (err)
 		return err;
 
-	return mlx5_firmware_flash(dev, fw, extack);
+	err = mlx5_firmware_flash(dev, fw, extack);
+	release_firmware(fw);
+
+	return err;
 }
 
 static u8 mlx5_fw_ver_major(u32 version)
-- 
2.20.1


From 919a16df4c484c4f071cc93a089d71ac7e8ec115 Mon Sep 17 00:00:00 2001
From: Dmytro Linkin <dmitrolin@mellanox.com>
Date: Wed, 1 Apr 2020 14:41:27 +0300
Subject: [PATCH 16/21] net/mlx5e: Fix nest_level for vlan pop action

[ Upstream commit 70f478ca085deec4d6c1f187f773f5827ddce7e8 ]

Current value of nest_level, assigned from net_device lower_level value,
does not reflect the actual number of vlan headers, needed to pop.
For ex., if we have untagged ingress traffic sended over vlan devices,
instead of one pop action, driver will perform two pop actions.
To fix that, calculate nest_level as difference between vlan device and
parent device lower_levels.

Fixes: f3b0a18bb6cb ("net: remove unnecessary variables and callback")
Signed-off-by: Dmytro Linkin <dmitrolin@mellanox.com>
Signed-off-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index ec5fc52bf572..4659c205cc01 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -3269,12 +3269,13 @@ static int add_vlan_pop_action(struct mlx5e_priv *priv,
 			       struct mlx5_esw_flow_attr *attr,
 			       u32 *action)
 {
-	int nest_level = attr->parse_attr->filter_dev->lower_level;
 	struct flow_action_entry vlan_act = {
 		.id = FLOW_ACTION_VLAN_POP,
 	};
-	int err = 0;
+	int nest_level, err = 0;
 
+	nest_level = attr->parse_attr->filter_dev->lower_level -
+						priv->netdev->lower_level;
 	while (nest_level--) {
 		err = parse_tc_vlan_action(priv, &vlan_act, attr, action);
 		if (err)
-- 
2.20.1


From 4626357d620494ce1a6136e2380bada6fe5c29d8 Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@mellanox.com>
Date: Fri, 3 Apr 2020 03:57:30 -0500
Subject: [PATCH 17/21] net/mlx5e: Fix pfnum in devlink port attribute

[ Upstream commit 7482d9cb5b974b7ad1a58fa8714f7a8c05b5d278 ]

Cited patch missed to extract PCI pf number accurately for PF and VF
port flavour. It considered PCI device + function number.
Due to this, device having non zero device number shown large pfnum.

Hence, use only PCI function number; to avoid similar errors, derive
pfnum one time for all port flavours.

Fixes: f60f315d339e ("net/mlx5e: Register devlink ports for physical link, PCI PF, VFs")
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 6ed307d7f191..ffc193c4ad43 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1969,29 +1969,30 @@ static int register_devlink_port(struct mlx5_core_dev *dev,
 	struct mlx5_eswitch_rep *rep = rpriv->rep;
 	struct netdev_phys_item_id ppid = {};
 	unsigned int dl_port_index = 0;
+	u16 pfnum;
 
 	if (!is_devlink_port_supported(dev, rpriv))
 		return 0;
 
 	mlx5e_rep_get_port_parent_id(rpriv->netdev, &ppid);
+	pfnum = PCI_FUNC(dev->pdev->devfn);
 
 	if (rep->vport == MLX5_VPORT_UPLINK) {
 		devlink_port_attrs_set(&rpriv->dl_port,
 				       DEVLINK_PORT_FLAVOUR_PHYSICAL,
-				       PCI_FUNC(dev->pdev->devfn), false, 0,
+				       pfnum, false, 0,
 				       &ppid.id[0], ppid.id_len);
 		dl_port_index = vport_to_devlink_port_index(dev, rep->vport);
 	} else if (rep->vport == MLX5_VPORT_PF) {
 		devlink_port_attrs_pci_pf_set(&rpriv->dl_port,
 					      &ppid.id[0], ppid.id_len,
-					      dev->pdev->devfn);
+					      pfnum);
 		dl_port_index = rep->vport;
 	} else if (mlx5_eswitch_is_vf_vport(dev->priv.eswitch,
 					    rpriv->rep->vport)) {
 		devlink_port_attrs_pci_vf_set(&rpriv->dl_port,
 					      &ppid.id[0], ppid.id_len,
-					      dev->pdev->devfn,
-					      rep->vport - 1);
+					      pfnum, rep->vport - 1);
 		dl_port_index = vport_to_devlink_port_index(dev, rep->vport);
 	}
 
-- 
2.20.1


From c2b13a0d869d1ea760280fb7c59d85d1a7337b4a Mon Sep 17 00:00:00 2001
From: Tim Stallard <code@timstallard.me.uk>
Date: Fri, 3 Apr 2020 21:22:57 +0100
Subject: [PATCH 18/21] net: icmp6: do not select saddr from iif when route has
 prefsrc set

[ Upstream commit b93cfb9cd3af3adc9ba4854f178d5300f7544d3e ]

Since commit fac6fce9bdb5 ("net: icmp6: provide input address for
traceroute6") ICMPv6 errors have source addresses from the ingress
interface. However, this overrides when source address selection is
influenced by setting preferred source addresses on routes.

This can result in ICMP errors being lost to upstream BCP38 filters
when the wrong source addresses are used, breaking path MTU discovery
and traceroute.

This patch sets the modified source address selection to only take place
when the route used has no prefsrc set.

It can be tested with:

ip link add v1 type veth peer name v2
ip netns add test
ip netns exec test ip link set lo up
ip link set v2 netns test
ip link set v1 up
ip netns exec test ip link set v2 up
ip addr add 2001:db8::1/64 dev v1 nodad
ip addr add 2001:db8::3 dev v1 nodad
ip netns exec test ip addr add 2001:db8::2/64 dev v2 nodad
ip netns exec test ip route add unreachable 2001:db8:1::1
ip netns exec test ip addr add 2001:db8:100::1 dev lo
ip netns exec test ip route add 2001:db8::1 dev v2 src 2001:db8:100::1
ip route add 2001:db8:1000::1 via 2001:db8::2
traceroute6 -s 2001:db8::1 2001:db8:1000::1
traceroute6 -s 2001:db8::3 2001:db8:1000::1
ip netns delete test

Output before:
$ traceroute6 -s 2001:db8::1 2001:db8:1000::1
traceroute to 2001:db8:1000::1 (2001:db8:1000::1), 30 hops max, 80 byte packets
 1  2001:db8::2 (2001:db8::2)  0.843 ms !N  0.396 ms !N  0.257 ms !N
$ traceroute6 -s 2001:db8::3 2001:db8:1000::1
traceroute to 2001:db8:1000::1 (2001:db8:1000::1), 30 hops max, 80 byte packets
 1  2001:db8::2 (2001:db8::2)  0.772 ms !N  0.257 ms !N  0.357 ms !N

After:
$ traceroute6 -s 2001:db8::1 2001:db8:1000::1
traceroute to 2001:db8:1000::1 (2001:db8:1000::1), 30 hops max, 80 byte packets
 1  2001:db8:100::1 (2001:db8:100::1)  8.885 ms !N  0.310 ms !N  0.174 ms !N
$ traceroute6 -s 2001:db8::3 2001:db8:1000::1
traceroute to 2001:db8:1000::1 (2001:db8:1000::1), 30 hops max, 80 byte packets
 1  2001:db8::2 (2001:db8::2)  1.403 ms !N  0.205 ms !N  0.313 ms !N

Fixes: fac6fce9bdb5 ("net: icmp6: provide input address for traceroute6")
Signed-off-by: Tim Stallard <code@timstallard.me.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/icmp.c | 21 ++++++++++++++++++++-
 1 file changed, 20 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index ef408a5090a2..c9504ec6a8d8 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -229,6 +229,25 @@ static bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
 	return res;
 }
 
+static bool icmpv6_rt_has_prefsrc(struct sock *sk, u8 type,
+				  struct flowi6 *fl6)
+{
+	struct net *net = sock_net(sk);
+	struct dst_entry *dst;
+	bool res = false;
+
+	dst = ip6_route_output(net, sk, fl6);
+	if (!dst->error) {
+		struct rt6_info *rt = (struct rt6_info *)dst;
+		struct in6_addr prefsrc;
+
+		rt6_get_prefsrc(rt, &prefsrc);
+		res = !ipv6_addr_any(&prefsrc);
+	}
+	dst_release(dst);
+	return res;
+}
+
 /*
  *	an inline helper for the "simple" if statement below
  *	checks if parameter problem report is caused by an
@@ -527,7 +546,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 		saddr = force_saddr;
 	if (saddr) {
 		fl6.saddr = *saddr;
-	} else {
+	} else if (!icmpv6_rt_has_prefsrc(sk, type, &fl6)) {
 		/* select a more meaningful saddr from input if */
 		struct net_device *in_netdev;
 
-- 
2.20.1


From 7340b41f352711efebff9fbb4c6f4925400b5845 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Tue, 14 Apr 2020 22:36:15 +0300
Subject: [PATCH 19/21] net: mscc: ocelot: fix untagged packet drops when
 enslaving to vlan aware bridge

[ Upstream commit 87b0f983f66f23762921129fd35966eddc3f2dae ]

To rehash a previous explanation given in commit 1c44ce560b4d ("net:
mscc: ocelot: fix vlan_filtering when enslaving to bridge before link is
up"), the switch driver operates the in a mode where a single VLAN can
be transmitted as untagged on a particular egress port. That is the
"native VLAN on trunk port" use case.

The configuration for this native VLAN is driven in 2 ways:
 - Set the egress port rewriter to strip the VLAN tag for the native
   VID (as it is egress-untagged, after all).
 - Configure the ingress port to drop untagged and priority-tagged
   traffic, if there is no native VLAN. The intention of this setting is
   that a trunk port with no native VLAN should not accept untagged
   traffic.

Since both of the above configurations for the native VLAN should only
be done if VLAN awareness is requested, they are actually done from the
ocelot_port_vlan_filtering function, after the basic procedure of
toggling the VLAN awareness flag of the port.

But there's a problem with that simplistic approach: we are trying to
juggle with 2 independent variables from a single function:
 - Native VLAN of the port - its value is held in port->vid.
 - VLAN awareness state of the port - currently there are some issues
   here, more on that later*.
The actual problem can be seen when enslaving the switch ports to a VLAN
filtering bridge:
 0. The driver configures a pvid of zero for each port, when in
    standalone mode. While the bridge configures a default_pvid of 1 for
    each port that gets added as a slave to it.
 1. The bridge calls ocelot_port_vlan_filtering with vlan_aware=true.
    The VLAN-filtering-dependent portion of the native VLAN
    configuration is done, considering that the native VLAN is 0.
 2. The bridge calls ocelot_vlan_add with vid=1, pvid=true,
    untagged=true. The native VLAN changes to 1 (change which gets
    propagated to hardware).
 3. ??? - nobody calls ocelot_port_vlan_filtering again, to reapply the
    VLAN-filtering-dependent portion of the native VLAN configuration,
    for the new native VLAN of 1. One can notice that after toggling "ip
    link set dev br0 type bridge vlan_filtering 0 && ip link set dev br0
    type bridge vlan_filtering 1", the new native VLAN finally makes it
    through and untagged traffic finally starts flowing again. But
    obviously that shouldn't be needed.

So it is clear that 2 independent variables need to both re-trigger the
native VLAN configuration. So we introduce the second variable as
ocelot_port->vlan_aware.

*Actually both the DSA Felix driver and the Ocelot driver already had
each its own variable:
 - Ocelot: ocelot_port_private->vlan_aware
 - Felix: dsa_port->vlan_filtering
but the common Ocelot library needs to work with a single, common,
variable, so there is some refactoring done to move the vlan_aware
property from the private structure into the common ocelot_port
structure.

Fixes: 97bb69e1e36e ("net: mscc: ocelot: break apart ocelot_vlan_port_apply")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/ocelot/felix.c     |  5 +-
 drivers/net/ethernet/mscc/ocelot.c | 84 +++++++++++++++---------------
 drivers/net/ethernet/mscc/ocelot.h |  2 -
 include/soc/mscc/ocelot.h          |  4 +-
 4 files changed, 47 insertions(+), 48 deletions(-)

diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index 3257962c147e..9e895ab586d5 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -44,11 +44,8 @@ static int felix_fdb_add(struct dsa_switch *ds, int port,
 			 const unsigned char *addr, u16 vid)
 {
 	struct ocelot *ocelot = ds->priv;
-	bool vlan_aware;
 
-	vlan_aware = dsa_port_is_vlan_filtering(dsa_to_port(ds, port));
-
-	return ocelot_fdb_add(ocelot, port, addr, vid, vlan_aware);
+	return ocelot_fdb_add(ocelot, port, addr, vid);
 }
 
 static int felix_fdb_del(struct dsa_switch *ds, int port,
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index d3b7373c5961..b14286dc49fb 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -183,44 +183,47 @@ static void ocelot_vlan_mode(struct ocelot *ocelot, int port,
 	ocelot_write(ocelot, val, ANA_VLANMASK);
 }
 
-void ocelot_port_vlan_filtering(struct ocelot *ocelot, int port,
-				bool vlan_aware)
+static int ocelot_port_set_native_vlan(struct ocelot *ocelot, int port,
+				       u16 vid)
 {
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
-	u32 val;
+	u32 val = 0;
 
-	if (vlan_aware)
-		val = ANA_PORT_VLAN_CFG_VLAN_AWARE_ENA |
-		      ANA_PORT_VLAN_CFG_VLAN_POP_CNT(1);
-	else
-		val = 0;
-	ocelot_rmw_gix(ocelot, val,
-		       ANA_PORT_VLAN_CFG_VLAN_AWARE_ENA |
-		       ANA_PORT_VLAN_CFG_VLAN_POP_CNT_M,
-		       ANA_PORT_VLAN_CFG, port);
+	if (ocelot_port->vid != vid) {
+		/* Always permit deleting the native VLAN (vid = 0) */
+		if (ocelot_port->vid && vid) {
+			dev_err(ocelot->dev,
+				"Port already has a native VLAN: %d\n",
+				ocelot_port->vid);
+			return -EBUSY;
+		}
+		ocelot_port->vid = vid;
+	}
+
+	ocelot_rmw_gix(ocelot, REW_PORT_VLAN_CFG_PORT_VID(vid),
+		       REW_PORT_VLAN_CFG_PORT_VID_M,
+		       REW_PORT_VLAN_CFG, port);
 
-	if (vlan_aware && !ocelot_port->vid)
+	if (ocelot_port->vlan_aware && !ocelot_port->vid)
 		/* If port is vlan-aware and tagged, drop untagged and priority
 		 * tagged frames.
 		 */
 		val = ANA_PORT_DROP_CFG_DROP_UNTAGGED_ENA |
 		      ANA_PORT_DROP_CFG_DROP_PRIO_S_TAGGED_ENA |
 		      ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA;
-	else
-		val = 0;
 	ocelot_rmw_gix(ocelot, val,
 		       ANA_PORT_DROP_CFG_DROP_UNTAGGED_ENA |
 		       ANA_PORT_DROP_CFG_DROP_PRIO_S_TAGGED_ENA |
 		       ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA,
 		       ANA_PORT_DROP_CFG, port);
 
-	if (vlan_aware) {
+	if (ocelot_port->vlan_aware) {
 		if (ocelot_port->vid)
 			/* Tag all frames except when VID == DEFAULT_VLAN */
-			val |= REW_TAG_CFG_TAG_CFG(1);
+			val = REW_TAG_CFG_TAG_CFG(1);
 		else
 			/* Tag all frames */
-			val |= REW_TAG_CFG_TAG_CFG(3);
+			val = REW_TAG_CFG_TAG_CFG(3);
 	} else {
 		/* Port tagging disabled. */
 		val = REW_TAG_CFG_TAG_CFG(0);
@@ -228,31 +231,31 @@ void ocelot_port_vlan_filtering(struct ocelot *ocelot, int port,
 	ocelot_rmw_gix(ocelot, val,
 		       REW_TAG_CFG_TAG_CFG_M,
 		       REW_TAG_CFG, port);
+
+	return 0;
 }
-EXPORT_SYMBOL(ocelot_port_vlan_filtering);
 
-static int ocelot_port_set_native_vlan(struct ocelot *ocelot, int port,
-				       u16 vid)
+void ocelot_port_vlan_filtering(struct ocelot *ocelot, int port,
+				bool vlan_aware)
 {
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
+	u32 val;
 
-	if (ocelot_port->vid != vid) {
-		/* Always permit deleting the native VLAN (vid = 0) */
-		if (ocelot_port->vid && vid) {
-			dev_err(ocelot->dev,
-				"Port already has a native VLAN: %d\n",
-				ocelot_port->vid);
-			return -EBUSY;
-		}
-		ocelot_port->vid = vid;
-	}
+	ocelot_port->vlan_aware = vlan_aware;
 
-	ocelot_rmw_gix(ocelot, REW_PORT_VLAN_CFG_PORT_VID(vid),
-		       REW_PORT_VLAN_CFG_PORT_VID_M,
-		       REW_PORT_VLAN_CFG, port);
+	if (vlan_aware)
+		val = ANA_PORT_VLAN_CFG_VLAN_AWARE_ENA |
+		      ANA_PORT_VLAN_CFG_VLAN_POP_CNT(1);
+	else
+		val = 0;
+	ocelot_rmw_gix(ocelot, val,
+		       ANA_PORT_VLAN_CFG_VLAN_AWARE_ENA |
+		       ANA_PORT_VLAN_CFG_VLAN_POP_CNT_M,
+		       ANA_PORT_VLAN_CFG, port);
 
-	return 0;
+	ocelot_port_set_native_vlan(ocelot, port, ocelot_port->vid);
 }
+EXPORT_SYMBOL(ocelot_port_vlan_filtering);
 
 /* Default vlan to clasify for untagged frames (may be zero) */
 static void ocelot_port_set_pvid(struct ocelot *ocelot, int port, u16 pvid)
@@ -858,12 +861,12 @@ static void ocelot_get_stats64(struct net_device *dev,
 }
 
 int ocelot_fdb_add(struct ocelot *ocelot, int port,
-		   const unsigned char *addr, u16 vid, bool vlan_aware)
+		   const unsigned char *addr, u16 vid)
 {
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
 
 	if (!vid) {
-		if (!vlan_aware)
+		if (!ocelot_port->vlan_aware)
 			/* If the bridge is not VLAN aware and no VID was
 			 * provided, set it to pvid to ensure the MAC entry
 			 * matches incoming untagged packets
@@ -890,7 +893,7 @@ static int ocelot_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 	struct ocelot *ocelot = priv->port.ocelot;
 	int port = priv->chip_port;
 
-	return ocelot_fdb_add(ocelot, port, addr, vid, priv->vlan_aware);
+	return ocelot_fdb_add(ocelot, port, addr, vid);
 }
 
 int ocelot_fdb_del(struct ocelot *ocelot, int port,
@@ -1489,8 +1492,8 @@ static int ocelot_port_attr_set(struct net_device *dev,
 		ocelot_port_attr_ageing_set(ocelot, port, attr->u.ageing_time);
 		break;
 	case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING:
-		priv->vlan_aware = attr->u.vlan_filtering;
-		ocelot_port_vlan_filtering(ocelot, port, priv->vlan_aware);
+		ocelot_port_vlan_filtering(ocelot, port,
+					   attr->u.vlan_filtering);
 		break;
 	case SWITCHDEV_ATTR_ID_BRIDGE_MC_DISABLED:
 		ocelot_port_attr_mc_set(ocelot, port, !attr->u.mc_disabled);
@@ -1861,7 +1864,6 @@ static int ocelot_netdevice_port_event(struct net_device *dev,
 			} else {
 				err = ocelot_port_bridge_leave(ocelot, port,
 							       info->upper_dev);
-				priv->vlan_aware = false;
 			}
 		}
 		if (netif_is_lag_master(info->upper_dev)) {
diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h
index 04372ba72fec..8e67fc40db0d 100644
--- a/drivers/net/ethernet/mscc/ocelot.h
+++ b/drivers/net/ethernet/mscc/ocelot.h
@@ -66,8 +66,6 @@ struct ocelot_port_private {
 	struct phy_device *phy;
 	u8 chip_port;
 
-	u8 vlan_aware;
-
 	struct phy *serdes;
 
 	struct ocelot_port_tc tc;
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index 068f96b1a83e..f8e1955c86f1 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -411,6 +411,8 @@ struct ocelot_port {
 
 	void __iomem			*regs;
 
+	bool				vlan_aware;
+
 	/* Ingress default VLAN (pvid) */
 	u16				pvid;
 
@@ -529,7 +531,7 @@ int ocelot_port_bridge_leave(struct ocelot *ocelot, int port,
 int ocelot_fdb_dump(struct ocelot *ocelot, int port,
 		    dsa_fdb_dump_cb_t *cb, void *data);
 int ocelot_fdb_add(struct ocelot *ocelot, int port,
-		   const unsigned char *addr, u16 vid, bool vlan_aware);
+		   const unsigned char *addr, u16 vid);
 int ocelot_fdb_del(struct ocelot *ocelot, int port,
 		   const unsigned char *addr, u16 vid);
 int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid,
-- 
2.20.1


From fc1d005726ee4e7aa7d26f41eb54f460b1175ee8 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 14 Apr 2020 15:39:52 -0700
Subject: [PATCH 20/21] net: stmmac: dwmac-sunxi: Provide TX and RX fifo sizes

[ Upstream commit 806fd188ce2a4f8b587e83e73c478e6484fbfa55 ]

After commit bfcb813203e619a8960a819bf533ad2a108d8105 ("net: dsa:
configure the MTU for switch ports") my Lamobo R1 platform which uses
an allwinner,sun7i-a20-gmac compatible Ethernet MAC started to fail
by rejecting a MTU of 1536. The reason for that is that the DMA
capabilities are not readable on this version of the IP, and there
is also no 'tx-fifo-depth' property being provided in Device Tree. The
property is documented as optional, and is not provided.

Chen-Yu indicated that the FIFO sizes are 4KB for TX and 16KB for RX, so
provide these values through platform data as an immediate fix until
various Device Tree sources get updated accordingly.

Fixes: eaf4fac47807 ("net: stmmac: Do not accept invalid MTU values")
Suggested-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Acked-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
index 7d40760e9ba8..0e1ca2cba3c7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
@@ -150,6 +150,8 @@ static int sun7i_gmac_probe(struct platform_device *pdev)
 	plat_dat->init = sun7i_gmac_init;
 	plat_dat->exit = sun7i_gmac_exit;
 	plat_dat->fix_mac_speed = sun7i_fix_speed;
+	plat_dat->tx_fifo_size = 4096;
+	plat_dat->rx_fifo_size = 16384;
 
 	ret = sun7i_gmac_init(pdev, plat_dat->bsp_priv);
 	if (ret)
-- 
2.20.1


From 7b82b49a7eafa8c7b7ab30fabc1975bd0a2c2ad5 Mon Sep 17 00:00:00 2001
From: Clemens Gruber <clemens.gruber@pqgruber.com>
Date: Sat, 11 Apr 2020 18:51:25 +0200
Subject: [PATCH 21/21] net: phy: marvell: Fix pause frame negotiation

[ Upstream commit 3b72f84f8fb65e83e85e9be58eabcf95a40b8f46 ]

The negotiation of flow control / pause frame modes was broken since
commit fcf1f59afc67 ("net: phy: marvell: rearrange to use
genphy_read_lpa()") moved the setting of phydev->duplex below the
phy_resolve_aneg_pause call. Due to a check of DUPLEX_FULL in that
function, phydev->pause was no longer set.

Fix it by moving the parsing of the status variable before the blocks
dealing with the pause frames.

As the Marvell 88E1510 datasheet does not specify the timing between the
link status and the "Speed and Duplex Resolved" bit, we have to force
the link down as long as the resolved bit is not set, to avoid reporting
link up before we even have valid Speed/Duplex.

Tested with a Marvell 88E1510 (RGMII to Copper/1000Base-T)

Fixes: fcf1f59afc67 ("net: phy: marvell: rearrange to use genphy_read_lpa()")
Signed-off-by: Clemens Gruber <clemens.gruber@pqgruber.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/marvell.c | 46 ++++++++++++++++++++-------------------
 1 file changed, 24 insertions(+), 22 deletions(-)

diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index 9a8badafea8a..561df5e33f65 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -1278,6 +1278,30 @@ static int marvell_read_status_page_an(struct phy_device *phydev,
 	int lpa;
 	int err;
 
+	if (!(status & MII_M1011_PHY_STATUS_RESOLVED)) {
+		phydev->link = 0;
+		return 0;
+	}
+
+	if (status & MII_M1011_PHY_STATUS_FULLDUPLEX)
+		phydev->duplex = DUPLEX_FULL;
+	else
+		phydev->duplex = DUPLEX_HALF;
+
+	switch (status & MII_M1011_PHY_STATUS_SPD_MASK) {
+	case MII_M1011_PHY_STATUS_1000:
+		phydev->speed = SPEED_1000;
+		break;
+
+	case MII_M1011_PHY_STATUS_100:
+		phydev->speed = SPEED_100;
+		break;
+
+	default:
+		phydev->speed = SPEED_10;
+		break;
+	}
+
 	if (!fiber) {
 		err = genphy_read_lpa(phydev);
 		if (err < 0)
@@ -1306,28 +1330,6 @@ static int marvell_read_status_page_an(struct phy_device *phydev,
 		}
 	}
 
-	if (!(status & MII_M1011_PHY_STATUS_RESOLVED))
-		return 0;
-
-	if (status & MII_M1011_PHY_STATUS_FULLDUPLEX)
-		phydev->duplex = DUPLEX_FULL;
-	else
-		phydev->duplex = DUPLEX_HALF;
-
-	switch (status & MII_M1011_PHY_STATUS_SPD_MASK) {
-	case MII_M1011_PHY_STATUS_1000:
-		phydev->speed = SPEED_1000;
-		break;
-
-	case MII_M1011_PHY_STATUS_100:
-		phydev->speed = SPEED_100;
-		break;
-
-	default:
-		phydev->speed = SPEED_10;
-		break;
-	}
-
 	return 0;
 }
 
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Fri, Apr 17, 2020 at 10:51:00AM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for
> v5.5 and v5.6 -stable, respectively.

All now queued up, thanks!

No need to do v5.5 patches anymore, that kernel tree is now end-of-life
after this next release.

thanks,

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 105 bytes --]


Please queue up the following networking bug fixes for v5.4 and
v5.6 -stable, respectively.

Thank you!

[-- Attachment #2: net_54.mbox --]
[-- Type: Application/Octet-Stream, Size: 69158 bytes --]

From 94856827bfcb4590d2edf9517e3995e02ca7d89c Mon Sep 17 00:00:00 2001
From: Vishal Kulkarni <vishal@chelsio.com>
Date: Wed, 22 Apr 2020 21:20:07 +0530
Subject: [PATCH 01/27] cxgb4: fix adapter crash due to wrong MC size

[ Upstream commit ce222748078592afb51b810dc154531aeba4f512 ]

In the absence of MC1, the size calculation function
cudbg_mem_region_size() was returing wrong MC size and
resulted in adapter crash. This patch adds new argument
to cudbg_mem_region_size() which will have actual size
and returns error to caller in the absence of MC1.

Fixes: a1c69520f785 ("cxgb4: collect MC memory dump")
Signed-off-by: Vishal Kulkarni <vishal@chelsio.com>"
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/chelsio/cxgb4/cudbg_lib.c    | 27 ++++++++++++++-----
 1 file changed, 20 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
index c2e92786608b..7bcdce182ee5 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
@@ -1054,9 +1054,9 @@ static void cudbg_t4_fwcache(struct cudbg_init *pdbg_init,
 	}
 }
 
-static unsigned long cudbg_mem_region_size(struct cudbg_init *pdbg_init,
-					   struct cudbg_error *cudbg_err,
-					   u8 mem_type)
+static int cudbg_mem_region_size(struct cudbg_init *pdbg_init,
+				 struct cudbg_error *cudbg_err,
+				 u8 mem_type, unsigned long *region_size)
 {
 	struct adapter *padap = pdbg_init->adap;
 	struct cudbg_meminfo mem_info;
@@ -1065,15 +1065,23 @@ static unsigned long cudbg_mem_region_size(struct cudbg_init *pdbg_init,
 
 	memset(&mem_info, 0, sizeof(struct cudbg_meminfo));
 	rc = cudbg_fill_meminfo(padap, &mem_info);
-	if (rc)
+	if (rc) {
+		cudbg_err->sys_err = rc;
 		return rc;
+	}
 
 	cudbg_t4_fwcache(pdbg_init, cudbg_err);
 	rc = cudbg_meminfo_get_mem_index(padap, &mem_info, mem_type, &mc_idx);
-	if (rc)
+	if (rc) {
+		cudbg_err->sys_err = rc;
 		return rc;
+	}
+
+	if (region_size)
+		*region_size = mem_info.avail[mc_idx].limit -
+			       mem_info.avail[mc_idx].base;
 
-	return mem_info.avail[mc_idx].limit - mem_info.avail[mc_idx].base;
+	return 0;
 }
 
 static int cudbg_collect_mem_region(struct cudbg_init *pdbg_init,
@@ -1081,7 +1089,12 @@ static int cudbg_collect_mem_region(struct cudbg_init *pdbg_init,
 				    struct cudbg_error *cudbg_err,
 				    u8 mem_type)
 {
-	unsigned long size = cudbg_mem_region_size(pdbg_init, cudbg_err, mem_type);
+	unsigned long size = 0;
+	int rc;
+
+	rc = cudbg_mem_region_size(pdbg_init, cudbg_err, mem_type, &size);
+	if (rc)
+		return rc;
 
 	return cudbg_read_fw_mem(pdbg_init, dbg_buff, mem_type, size,
 				 cudbg_err);
-- 
2.20.1


From 95565c5da941febd293036216834f01fa0428181 Mon Sep 17 00:00:00 2001
From: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Date: Mon, 20 Apr 2020 15:26:54 +0530
Subject: [PATCH 02/27] cxgb4: fix large delays in PTP synchronization

[ Upstream commit bd019427bf3623ee3c7d2845cf921bbf4c14846c ]

Fetching PTP sync information from mailbox is slow and can take
up to 10 milliseconds. Reduce this unnecessary delay by directly
reading the information from the corresponding registers.

Fixes: 9c33e4208bce ("cxgb4: Add PTP Hardware Clock (PHC) support")
Signed-off-by: Manoj Malviya <manojmalviya@chelsio.com>
Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/chelsio/cxgb4/cxgb4_ptp.c    | 27 +++++--------------
 drivers/net/ethernet/chelsio/cxgb4/t4_regs.h  |  3 +++
 2 files changed, 9 insertions(+), 21 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c
index af1f40cbccc8..f5bc996ac77d 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c
@@ -311,32 +311,17 @@ static int cxgb4_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
  */
 static int cxgb4_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
 {
-	struct adapter *adapter = (struct adapter *)container_of(ptp,
-				   struct adapter, ptp_clock_info);
-	struct fw_ptp_cmd c;
+	struct adapter *adapter = container_of(ptp, struct adapter,
+					       ptp_clock_info);
 	u64 ns;
-	int err;
-
-	memset(&c, 0, sizeof(c));
-	c.op_to_portid = cpu_to_be32(FW_CMD_OP_V(FW_PTP_CMD) |
-				     FW_CMD_REQUEST_F |
-				     FW_CMD_READ_F |
-				     FW_PTP_CMD_PORTID_V(0));
-	c.retval_len16 = cpu_to_be32(FW_CMD_LEN16_V(sizeof(c) / 16));
-	c.u.ts.sc = FW_PTP_SC_GET_TIME;
 
-	err = t4_wr_mbox(adapter, adapter->mbox, &c, sizeof(c), &c);
-	if (err < 0) {
-		dev_err(adapter->pdev_dev,
-			"PTP: %s error %d\n", __func__, -err);
-		return err;
-	}
+	ns = t4_read_reg(adapter, T5_PORT_REG(0, MAC_PORT_PTP_SUM_LO_A));
+	ns |= (u64)t4_read_reg(adapter,
+			       T5_PORT_REG(0, MAC_PORT_PTP_SUM_HI_A)) << 32;
 
 	/* convert to timespec*/
-	ns = be64_to_cpu(c.u.ts.tm);
 	*ts = ns_to_timespec64(ns);
-
-	return err;
+	return 0;
 }
 
 /**
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
index a957a6e4d4c4..b0519c326692 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
@@ -1900,6 +1900,9 @@
 
 #define MAC_PORT_CFG2_A 0x818
 
+#define MAC_PORT_PTP_SUM_LO_A 0x990
+#define MAC_PORT_PTP_SUM_HI_A 0x994
+
 #define MPS_CMN_CTL_A	0x9000
 
 #define COUNTPAUSEMCRX_S    5
-- 
2.20.1


From 21fc30df2a834ca3eaf2dd730cfde39423fa7f78 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 22 Apr 2020 15:40:20 -0600
Subject: [PATCH 03/27] ipv4: Update fib_select_default to handle nexthop
 objects

[ Upstream commit 7c74b0bec918c1e0ca0b4208038c156eacf8f13f ]

A user reported [0] hitting the WARN_ON in fib_info_nh:

    [ 8633.839816] ------------[ cut here ]------------
    [ 8633.839819] WARNING: CPU: 0 PID: 1719 at include/net/nexthop.h:251 fib_select_path+0x303/0x381
    ...
    [ 8633.839846] RIP: 0010:fib_select_path+0x303/0x381
    ...
    [ 8633.839848] RSP: 0018:ffffb04d407f7d00 EFLAGS: 00010286
    [ 8633.839850] RAX: 0000000000000000 RBX: ffff9460b9897ee8 RCX: 00000000000000fe
    [ 8633.839851] RDX: 0000000000000000 RSI: 00000000ffffffff RDI: 0000000000000000
    [ 8633.839852] RBP: ffff946076049850 R08: 0000000059263a83 R09: ffff9460840e4000
    [ 8633.839853] R10: 0000000000000014 R11: 0000000000000000 R12: ffffb04d407f7dc0
    [ 8633.839854] R13: ffffffffa4ce3240 R14: 0000000000000000 R15: ffff9460b7681f60
    [ 8633.839857] FS:  00007fcac2e02700(0000) GS:ffff9460bdc00000(0000) knlGS:0000000000000000
    [ 8633.839858] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
    [ 8633.839859] CR2: 00007f27beb77e28 CR3: 0000000077734000 CR4: 00000000000006f0
    [ 8633.839867] Call Trace:
    [ 8633.839871]  ip_route_output_key_hash_rcu+0x421/0x890
    [ 8633.839873]  ip_route_output_key_hash+0x5e/0x80
    [ 8633.839876]  ip_route_output_flow+0x1a/0x50
    [ 8633.839878]  __ip4_datagram_connect+0x154/0x310
    [ 8633.839880]  ip4_datagram_connect+0x28/0x40
    [ 8633.839882]  __sys_connect+0xd6/0x100
    ...

The WARN_ON is triggered in fib_select_default which is invoked when
there are multiple default routes. Update the function to use
fib_info_nhc and convert the nexthop checks to use fib_nh_common.

Add test case that covers the affected code path.

[0] https://github.com/FRRouting/frr/issues/6089

Fixes: 493ced1ac47c ("ipv4: Allow routes to use nexthop objects")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_semantics.c                    |  6 +++---
 tools/testing/selftests/net/fib_nexthops.sh | 23 +++++++++++++++++++++
 2 files changed, 26 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index f1888c683426..01588eef0cee 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1999,7 +1999,7 @@ static void fib_select_default(const struct flowi4 *flp, struct fib_result *res)
 
 	hlist_for_each_entry_rcu(fa, fa_head, fa_list) {
 		struct fib_info *next_fi = fa->fa_info;
-		struct fib_nh *nh;
+		struct fib_nh_common *nhc;
 
 		if (fa->fa_slen != slen)
 			continue;
@@ -2022,8 +2022,8 @@ static void fib_select_default(const struct flowi4 *flp, struct fib_result *res)
 		    fa->fa_type != RTN_UNICAST)
 			continue;
 
-		nh = fib_info_nh(next_fi, 0);
-		if (!nh->fib_nh_gw4 || nh->fib_nh_scope != RT_SCOPE_LINK)
+		nhc = fib_info_nhc(next_fi, 0);
+		if (!nhc->nhc_gw_family || nhc->nhc_scope != RT_SCOPE_LINK)
 			continue;
 
 		fib_alias_accessed(fa);
diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh
index 796670ebc65b..6560ed796ac4 100755
--- a/tools/testing/selftests/net/fib_nexthops.sh
+++ b/tools/testing/selftests/net/fib_nexthops.sh
@@ -749,6 +749,29 @@ ipv4_fcnal_runtime()
 	run_cmd "ip netns exec me ping -c1 -w1 172.16.101.1"
 	log_test $? 0 "Ping - multipath"
 
+	run_cmd "$IP ro delete 172.16.101.1/32 nhid 122"
+
+	#
+	# multiple default routes
+	# - tests fib_select_default
+	run_cmd "$IP nexthop add id 501 via 172.16.1.2 dev veth1"
+	run_cmd "$IP ro add default nhid 501"
+	run_cmd "$IP ro add default via 172.16.1.3 dev veth1 metric 20"
+	run_cmd "ip netns exec me ping -c1 -w1 172.16.101.1"
+	log_test $? 0 "Ping - multiple default routes, nh first"
+
+	# flip the order
+	run_cmd "$IP ro del default nhid 501"
+	run_cmd "$IP ro del default via 172.16.1.3 dev veth1 metric 20"
+	run_cmd "$IP ro add default via 172.16.1.2 dev veth1 metric 20"
+	run_cmd "$IP nexthop replace id 501 via 172.16.1.3 dev veth1"
+	run_cmd "$IP ro add default nhid 501 metric 20"
+	run_cmd "ip netns exec me ping -c1 -w1 172.16.101.1"
+	log_test $? 0 "Ping - multiple default routes, nh second"
+
+	run_cmd "$IP nexthop delete nhid 501"
+	run_cmd "$IP ro del default"
+
 	#
 	# IPv4 with blackhole nexthops
 	#
-- 
2.20.1


From f7e2dbec238f52232c1eabbaa92807a08cb8b2c1 Mon Sep 17 00:00:00 2001
From: John Haxby <john.haxby@oracle.com>
Date: Sat, 18 Apr 2020 16:30:49 +0100
Subject: [PATCH 04/27] ipv6: fix restrict IPV6_ADDRFORM operation

[ Upstream commit 82c9ae440857840c56e05d4fb1427ee032531346 ]

Commit b6f6118901d1 ("ipv6: restrict IPV6_ADDRFORM operation") fixed a
problem found by syzbot an unfortunate logic error meant that it
also broke IPV6_ADDRFORM.

Rearrange the checks so that the earlier test is just one of the series
of checks made before moving the socket from IPv6 to IPv4.

Fixes: b6f6118901d1 ("ipv6: restrict IPV6_ADDRFORM operation")
Signed-off-by: John Haxby <john.haxby@oracle.com>
Cc: stable@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ipv6_sockglue.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index debdaeba5d8c..18d05403d3b5 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -183,15 +183,14 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 					retv = -EBUSY;
 					break;
 				}
-			} else if (sk->sk_protocol == IPPROTO_TCP) {
-				if (sk->sk_prot != &tcpv6_prot) {
-					retv = -EBUSY;
-					break;
-				}
-				break;
-			} else {
+			}
+			if (sk->sk_protocol == IPPROTO_TCP &&
+			    sk->sk_prot != &tcpv6_prot) {
+				retv = -EBUSY;
 				break;
 			}
+			if (sk->sk_protocol != IPPROTO_TCP)
+				break;
 			if (sk->sk_state != TCP_ESTABLISHED) {
 				retv = -ENOTCONN;
 				break;
-- 
2.20.1


From 58103450dce203771c078b3e644bbd7b41b35589 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Thu, 23 Apr 2020 13:40:47 +0000
Subject: [PATCH 05/27] macsec: avoid to set wrong mtu

[ Upstream commit 7f327080364abccf923fa5a5b24e038eb0ba1407 ]

When a macsec interface is created, the mtu is calculated with the lower
interface's mtu value.
If the mtu of lower interface is lower than the length, which is needed
by macsec interface, macsec's mtu value will be overflowed.
So, if the lower interface's mtu is too low, macsec interface's mtu
should be set to 0.

Test commands:
    ip link add dummy0 mtu 10 type dummy
    ip link add macsec0 link dummy0 type macsec
    ip link show macsec0

Before:
    11: macsec0@dummy0: <BROADCAST,MULTICAST,M-DOWN> mtu 4294967274
After:
    11: macsec0@dummy0: <BROADCAST,MULTICAST,M-DOWN> mtu 0

Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macsec.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 32c627702ac5..a0abc729f0ca 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -3226,11 +3226,11 @@ static int macsec_newlink(struct net *net, struct net_device *dev,
 			  struct netlink_ext_ack *extack)
 {
 	struct macsec_dev *macsec = macsec_priv(dev);
+	rx_handler_func_t *rx_handler;
+	u8 icv_len = DEFAULT_ICV_LEN;
 	struct net_device *real_dev;
-	int err;
+	int err, mtu;
 	sci_t sci;
-	u8 icv_len = DEFAULT_ICV_LEN;
-	rx_handler_func_t *rx_handler;
 
 	if (!tb[IFLA_LINK])
 		return -EINVAL;
@@ -3246,7 +3246,11 @@ static int macsec_newlink(struct net *net, struct net_device *dev,
 
 	if (data && data[IFLA_MACSEC_ICV_LEN])
 		icv_len = nla_get_u8(data[IFLA_MACSEC_ICV_LEN]);
-	dev->mtu = real_dev->mtu - icv_len - macsec_extra_len(true);
+	mtu = real_dev->mtu - icv_len - macsec_extra_len(true);
+	if (mtu < 0)
+		dev->mtu = 0;
+	else
+		dev->mtu = mtu;
 
 	rx_handler = rtnl_dereference(real_dev->rx_handler);
 	if (rx_handler && rx_handler != macsec_handle_frame)
-- 
2.20.1


From 2b3ca963663f71a3c8be4a81efaca0a4ab0eafe5 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Mon, 20 Apr 2020 13:29:40 +0000
Subject: [PATCH 06/27] macvlan: fix null dereference in macvlan_device_event()

[ Upstream commit 4dee15b4fd0d61ec6bbd179238191e959d34cf7a ]

In the macvlan_device_event(), the list_first_entry_or_null() is used.
This function could return null pointer if there is no node.
But, the macvlan module doesn't check the null pointer.
So, null-ptr-deref would occur.

      bond0
        |
   +----+-----+
   |          |
macvlan0   macvlan1
   |          |
 dummy0     dummy1

The problem scenario.
If dummy1 is removed,
1. ->dellink() of dummy1 is called.
2. NETDEV_UNREGISTER of dummy1 notification is sent to macvlan module.
3. ->dellink() of macvlan1 is called.
4. NETDEV_UNREGISTER of macvlan1 notification is sent to bond module.
5. __bond_release_one() is called and it internally calls
   dev_set_mac_address().
6. dev_set_mac_address() calls the ->ndo_set_mac_address() of macvlan1,
   which is macvlan_set_mac_address().
7. macvlan_set_mac_address() calls the dev_set_mac_address() with dummy1.
8. NETDEV_CHANGEADDR of dummy1 is sent to macvlan module.
9. In the macvlan_device_event(), it calls list_first_entry_or_null().
At this point, dummy1 and macvlan1 were removed.
So, list_first_entry_or_null() will return NULL.

Test commands:
    ip netns add nst
    ip netns exec nst ip link add bond0 type bond
    for i in {0..10}
    do
        ip netns exec nst ip link add dummy$i type dummy
	ip netns exec nst ip link add macvlan$i link dummy$i \
		type macvlan mode passthru
	ip netns exec nst ip link set macvlan$i master bond0
    done
    ip netns del nst

Splat looks like:
[   40.585687][  T146] general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] SMP DEI
[   40.587249][  T146] KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007]
[   40.588342][  T146] CPU: 1 PID: 146 Comm: kworker/u8:2 Not tainted 5.7.0-rc1+ #532
[   40.589299][  T146] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[   40.590469][  T146] Workqueue: netns cleanup_net
[   40.591045][  T146] RIP: 0010:macvlan_device_event+0x4e2/0x900 [macvlan]
[   40.591905][  T146] Code: 00 00 00 00 00 fc ff df 80 3c 06 00 0f 85 45 02 00 00 48 89 da 48 b8 00 00 00 00 00 fc ff d2
[   40.594126][  T146] RSP: 0018:ffff88806116f4a0 EFLAGS: 00010246
[   40.594783][  T146] RAX: dffffc0000000000 RBX: 0000000000000000 RCX: 0000000000000000
[   40.595653][  T146] RDX: 0000000000000000 RSI: ffff88806547ddd8 RDI: ffff8880540f1360
[   40.596495][  T146] RBP: ffff88804011a808 R08: fffffbfff4fb8421 R09: fffffbfff4fb8421
[   40.597377][  T146] R10: ffffffffa7dc2107 R11: 0000000000000000 R12: 0000000000000008
[   40.598186][  T146] R13: ffff88804011a000 R14: ffff8880540f1000 R15: 1ffff1100c22de9a
[   40.599012][  T146] FS:  0000000000000000(0000) GS:ffff888067800000(0000) knlGS:0000000000000000
[   40.600004][  T146] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   40.600665][  T146] CR2: 00005572d3a807b8 CR3: 000000005fcf4003 CR4: 00000000000606e0
[   40.601485][  T146] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[   40.602461][  T146] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[   40.603443][  T146] Call Trace:
[   40.603871][  T146]  ? nf_tables_dump_setelem+0xa0/0xa0 [nf_tables]
[   40.604587][  T146]  ? macvlan_uninit+0x100/0x100 [macvlan]
[   40.605212][  T146]  ? __module_text_address+0x13/0x140
[   40.605842][  T146]  notifier_call_chain+0x90/0x160
[   40.606477][  T146]  dev_set_mac_address+0x28e/0x3f0
[   40.607117][  T146]  ? netdev_notify_peers+0xc0/0xc0
[   40.607762][  T146]  ? __module_text_address+0x13/0x140
[   40.608440][  T146]  ? notifier_call_chain+0x90/0x160
[   40.609097][  T146]  ? dev_set_mac_address+0x1f0/0x3f0
[   40.609758][  T146]  dev_set_mac_address+0x1f0/0x3f0
[   40.610402][  T146]  ? __local_bh_enable_ip+0xe9/0x1b0
[   40.611071][  T146]  ? bond_hw_addr_flush+0x77/0x100 [bonding]
[   40.611823][  T146]  ? netdev_notify_peers+0xc0/0xc0
[   40.612461][  T146]  ? bond_hw_addr_flush+0x77/0x100 [bonding]
[   40.613213][  T146]  ? bond_hw_addr_flush+0x77/0x100 [bonding]
[   40.613963][  T146]  ? __local_bh_enable_ip+0xe9/0x1b0
[   40.614631][  T146]  ? bond_time_in_interval.isra.31+0x90/0x90 [bonding]
[   40.615484][  T146]  ? __bond_release_one+0x9f0/0x12c0 [bonding]
[   40.616230][  T146]  __bond_release_one+0x9f0/0x12c0 [bonding]
[   40.616949][  T146]  ? bond_enslave+0x47c0/0x47c0 [bonding]
[   40.617642][  T146]  ? lock_downgrade+0x730/0x730
[   40.618218][  T146]  ? check_flags.part.42+0x450/0x450
[   40.618850][  T146]  ? __mutex_unlock_slowpath+0xd0/0x670
[   40.619519][  T146]  ? trace_hardirqs_on+0x30/0x180
[   40.620117][  T146]  ? wait_for_completion+0x250/0x250
[   40.620754][  T146]  bond_netdev_event+0x822/0x970 [bonding]
[   40.621460][  T146]  ? __module_text_address+0x13/0x140
[   40.622097][  T146]  notifier_call_chain+0x90/0x160
[   40.622806][  T146]  rollback_registered_many+0x660/0xcf0
[   40.623522][  T146]  ? netif_set_real_num_tx_queues+0x780/0x780
[   40.624290][  T146]  ? notifier_call_chain+0x90/0x160
[   40.624957][  T146]  ? netdev_upper_dev_unlink+0x114/0x180
[   40.625686][  T146]  ? __netdev_adjacent_dev_unlink_neighbour+0x30/0x30
[   40.626421][  T146]  ? mutex_is_locked+0x13/0x50
[   40.627016][  T146]  ? unregister_netdevice_queue+0xf2/0x240
[   40.627663][  T146]  unregister_netdevice_many.part.134+0x13/0x1b0
[   40.628362][  T146]  default_device_exit_batch+0x2d9/0x390
[   40.628987][  T146]  ? unregister_netdevice_many+0x40/0x40
[   40.629615][  T146]  ? dev_change_net_namespace+0xcb0/0xcb0
[   40.630279][  T146]  ? prepare_to_wait_exclusive+0x2e0/0x2e0
[   40.630943][  T146]  ? ops_exit_list.isra.9+0x97/0x140
[   40.631554][  T146]  cleanup_net+0x441/0x890
[ ... ]

Fixes: e289fd28176b ("macvlan: fix the problem when mac address changes for passthru mode")
Reported-by: syzbot+5035b1f9dc7ea4558d5a@syzkaller.appspotmail.com
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macvlan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 26f6be4796c7..0ce1004a8d0d 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -1704,7 +1704,7 @@ static int macvlan_device_event(struct notifier_block *unused,
 						struct macvlan_dev,
 						list);
 
-		if (macvlan_sync_address(vlan->dev, dev->dev_addr))
+		if (vlan && macvlan_sync_address(vlan->dev, dev->dev_addr))
 			return NOTIFY_BAD;
 
 		break;
-- 
2.20.1


From 5647ccf84e64426502ac1941c97ce7e1cffafb41 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 22 Apr 2020 12:36:41 +0300
Subject: [PATCH 07/27] mlxsw: Fix some IS_ERR() vs NULL bugs

[ Upstream commit c391eb8366ae052d571bb2841f1ccb4d39f3ceb8 ]

The mlxsw_sp_acl_rulei_create() function is supposed to return an error
pointer from mlxsw_afa_block_create().  The problem is that these
functions both return NULL instead of error pointers.  Half the callers
expect NULL and half expect error pointers so it could lead to a NULL
dereference on failure.

This patch changes both of them to return error pointers and changes all
the callers which checked for NULL to check for IS_ERR() instead.

Fixes: 4cda7d8d7098 ("mlxsw: core: Introduce flexible actions support")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c | 4 ++--
 drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c    | 4 ++--
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c          | 2 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c      | 4 ++--
 4 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
index c51b2adfc1e1..2cbfa5cfefab 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
@@ -316,7 +316,7 @@ struct mlxsw_afa_block *mlxsw_afa_block_create(struct mlxsw_afa *mlxsw_afa)
 
 	block = kzalloc(sizeof(*block), GFP_KERNEL);
 	if (!block)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	INIT_LIST_HEAD(&block->resource_list);
 	block->afa = mlxsw_afa;
 
@@ -344,7 +344,7 @@ struct mlxsw_afa_block *mlxsw_afa_block_create(struct mlxsw_afa *mlxsw_afa)
 	mlxsw_afa_set_destroy(block->first_set);
 err_first_set_create:
 	kfree(block);
-	return NULL;
+	return ERR_PTR(-ENOMEM);
 }
 EXPORT_SYMBOL(mlxsw_afa_block_create);
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
index 6c66a0f1b79e..ad69913f19c1 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
@@ -88,8 +88,8 @@ static int mlxsw_sp2_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv,
 	 * to be written using PEFA register to all indexes for all regions.
 	 */
 	afa_block = mlxsw_afa_block_create(mlxsw_sp->afa);
-	if (!afa_block) {
-		err = -ENOMEM;
+	if (IS_ERR(afa_block)) {
+		err = PTR_ERR(afa_block);
 		goto err_afa_block;
 	}
 	err = mlxsw_afa_block_continue(afa_block);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index 3d3cca596116..d77cdcb5c642 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -444,7 +444,7 @@ mlxsw_sp_acl_rulei_create(struct mlxsw_sp_acl *acl,
 
 	rulei = kzalloc(sizeof(*rulei), GFP_KERNEL);
 	if (!rulei)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	if (afa_block) {
 		rulei->act_block = afa_block;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
index 346f4a5fe053..221aa6a474eb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
@@ -199,8 +199,8 @@ mlxsw_sp_mr_tcam_afa_block_create(struct mlxsw_sp *mlxsw_sp,
 	int err;
 
 	afa_block = mlxsw_afa_block_create(mlxsw_sp->afa);
-	if (!afa_block)
-		return ERR_PTR(-ENOMEM);
+	if (IS_ERR(afa_block))
+		return afa_block;
 
 	err = mlxsw_afa_block_append_allocated_counter(afa_block,
 						       counter_index);
-- 
2.20.1


From a9c65c0cdb1a4a31c4e088dd04ee4be4ba5e5ee8 Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Thu, 23 Apr 2020 15:44:17 -0700
Subject: [PATCH 08/27] net: bcmgenet: correct per TX/RX ring statistics

[ Upstream commit a6d0b83f25073bdf08b8547aeff961a62c6ab229 ]

The change to track net_device_stats per ring to better support SMP
missed updating the rx_dropped member.

The ndo_get_stats method is also needed to combine the results for
ethtool statistics (-S) before filling in the ethtool structure.

Fixes: 37a30b435b92 ("net: bcmgenet: Track per TX/RX rings statistics")
Signed-off-by: Doug Berger <opendmb@gmail.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 8f909d57501f..ff09ee777b2b 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -995,6 +995,8 @@ static void bcmgenet_get_ethtool_stats(struct net_device *dev,
 	if (netif_running(dev))
 		bcmgenet_update_mib_counters(priv);
 
+	dev->netdev_ops->ndo_get_stats(dev);
+
 	for (i = 0; i < BCMGENET_STATS_LEN; i++) {
 		const struct bcmgenet_stats *s;
 		char *p;
@@ -3204,6 +3206,7 @@ static struct net_device_stats *bcmgenet_get_stats(struct net_device *dev)
 	dev->stats.rx_packets = rx_packets;
 	dev->stats.rx_errors = rx_errors;
 	dev->stats.rx_missed_errors = rx_errors;
+	dev->stats.rx_dropped = rx_dropped;
 	return &dev->stats;
 }
 
-- 
2.20.1


From 14ab425e916bd655c19444a269acf824b9e5a086 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 15 Apr 2020 09:46:52 -0700
Subject: [PATCH 09/27] net/mlx4_en: avoid indirect call in TX completion

[ Upstream commit 310660a14b74c380b0ef5c12b66933d6a3d1b59f ]

Commit 9ecc2d86171a ("net/mlx4_en: add xdp forwarding and data write support")
brought another indirect call in fast path.

Use INDIRECT_CALL_2() helper to avoid the cost of the indirect call
when/if CONFIG_RETPOLINE=y

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Tariq Toukan <tariqt@mellanox.com>
Cc: Willem de Bruijn <willemb@google.com>
Reviewed-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_tx.c | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 4d5ca302c067..a30edb436f4a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -43,6 +43,7 @@
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/moduleparam.h>
+#include <linux/indirect_call_wrapper.h>
 
 #include "mlx4_en.h"
 
@@ -261,6 +262,10 @@ static void mlx4_en_stamp_wqe(struct mlx4_en_priv *priv,
 	}
 }
 
+INDIRECT_CALLABLE_DECLARE(u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
+						   struct mlx4_en_tx_ring *ring,
+						   int index, u64 timestamp,
+						   int napi_mode));
 
 u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
 			 struct mlx4_en_tx_ring *ring,
@@ -329,6 +334,11 @@ u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
 	return tx_info->nr_txbb;
 }
 
+INDIRECT_CALLABLE_DECLARE(u32 mlx4_en_recycle_tx_desc(struct mlx4_en_priv *priv,
+						      struct mlx4_en_tx_ring *ring,
+						      int index, u64 timestamp,
+						      int napi_mode));
+
 u32 mlx4_en_recycle_tx_desc(struct mlx4_en_priv *priv,
 			    struct mlx4_en_tx_ring *ring,
 			    int index, u64 timestamp,
@@ -449,7 +459,9 @@ bool mlx4_en_process_tx_cq(struct net_device *dev,
 				timestamp = mlx4_en_get_cqe_ts(cqe);
 
 			/* free next descriptor */
-			last_nr_txbb = ring->free_tx_desc(
+			last_nr_txbb = INDIRECT_CALL_2(ring->free_tx_desc,
+						       mlx4_en_free_tx_desc,
+						       mlx4_en_recycle_tx_desc,
 					priv, ring, ring_index,
 					timestamp, napi_budget);
 
-- 
2.20.1


From 98cb08e3234e3c1bd43f22ae3bee29f97e5d5094 Mon Sep 17 00:00:00 2001
From: Xiyu Yang <xiyuyang19@fudan.edu.cn>
Date: Wed, 15 Apr 2020 16:36:19 +0800
Subject: [PATCH 10/27] net: netrom: Fix potential nr_neigh refcnt leak in
 nr_add_node

[ Upstream commit d03f228470a8c0a22b774d1f8d47071e0de4f6dd ]

nr_add_node() invokes nr_neigh_get_dev(), which returns a local
reference of the nr_neigh object to "nr_neigh" with increased refcnt.

When nr_add_node() returns, "nr_neigh" becomes invalid, so the refcount
should be decreased to keep refcount balanced.

The issue happens in one normal path of nr_add_node(), which forgets to
decrease the refcnt increased by nr_neigh_get_dev() and causes a refcnt
leak. It should decrease the refcnt before the function returns like
other normal paths do.

Fix this issue by calling nr_neigh_put() before the nr_add_node()
returns.

Signed-off-by: Xiyu Yang <xiyuyang19@fudan.edu.cn>
Signed-off-by: Xin Tan <tanxin.ctf@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netrom/nr_route.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c
index d41335bad1f8..89cd9de21594 100644
--- a/net/netrom/nr_route.c
+++ b/net/netrom/nr_route.c
@@ -208,6 +208,7 @@ static int __must_check nr_add_node(ax25_address *nr, const char *mnemonic,
 		/* refcount initialized at 1 */
 		spin_unlock_bh(&nr_node_list_lock);
 
+		nr_neigh_put(nr_neigh);
 		return 0;
 	}
 	nr_node_lock(nr_node);
-- 
2.20.1


From 1a4175370d43bf988aa198ab4db7445d02d0e988 Mon Sep 17 00:00:00 2001
From: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Date: Fri, 17 Apr 2020 02:57:31 +0800
Subject: [PATCH 11/27] net: openvswitch: ovs_ct_exit to be done under ovs_lock

[ Upstream commit 27de77cec985233bdf6546437b9761853265c505 ]

syzbot wrote:
| =============================
| WARNING: suspicious RCU usage
| 5.7.0-rc1+ #45 Not tainted
| -----------------------------
| net/openvswitch/conntrack.c:1898 RCU-list traversed in non-reader section!!
|
| other info that might help us debug this:
| rcu_scheduler_active = 2, debug_locks = 1
| ...
|
| stack backtrace:
| Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-0-ga698c8995f-prebuilt.qemu.org 04/01/2014
| Workqueue: netns cleanup_net
| Call Trace:
| ...
| ovs_ct_exit
| ovs_exit_net
| ops_exit_list.isra.7
| cleanup_net
| process_one_work
| worker_thread

To avoid that warning, invoke the ovs_ct_exit under ovs_lock and add
lockdep_ovsl_is_held as optional lockdep expression.

Link: https://lore.kernel.org/lkml/000000000000e642a905a0cbee6e@google.com
Fixes: 11efd5cb04a1 ("openvswitch: Support conntrack zone limit")
Cc: Pravin B Shelar <pshelar@ovn.org>
Cc: Yi-Hung Wei <yihung.wei@gmail.com>
Reported-by: syzbot+7ef50afd3a211f879112@syzkaller.appspotmail.com
Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/conntrack.c | 3 ++-
 net/openvswitch/datapath.c  | 4 +++-
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 283e8f9a5fd2..8b70298857e3 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -1890,7 +1890,8 @@ static void ovs_ct_limit_exit(struct net *net, struct ovs_net *ovs_net)
 		struct hlist_head *head = &info->limits[i];
 		struct ovs_ct_limit *ct_limit;
 
-		hlist_for_each_entry_rcu(ct_limit, head, hlist_node)
+		hlist_for_each_entry_rcu(ct_limit, head, hlist_node,
+					 lockdep_ovsl_is_held())
 			kfree_rcu(ct_limit, rcu);
 	}
 	kfree(ovs_net->ct_limit_info->limits);
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 3eed90bfa2bf..4f097bd3339e 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -2430,8 +2430,10 @@ static void __net_exit ovs_exit_net(struct net *dnet)
 	struct net *net;
 	LIST_HEAD(head);
 
-	ovs_ct_exit(dnet);
 	ovs_lock();
+
+	ovs_ct_exit(dnet);
+
 	list_for_each_entry_safe(dp, dp_next, &ovs_net->dps, list_node)
 		__dp_destroy(dp);
 
-- 
2.20.1


From e4830f1411e8bd348e64628f81b5e3bf9891aae8 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sat, 18 Apr 2020 19:14:57 +0100
Subject: [PATCH 12/27] net: stmmac: dwmac-meson8b: Add missing boundary to
 RGMII TX clock array

[ Upstream commit f0212a5ebfa6cd789ab47666b9cc169e6e688732 ]

Running with KASAN on a VIM3L systems leads to the following splat
when probing the Ethernet device:

==================================================================
BUG: KASAN: global-out-of-bounds in _get_maxdiv+0x74/0xd8
Read of size 4 at addr ffffa000090615f4 by task systemd-udevd/139
CPU: 1 PID: 139 Comm: systemd-udevd Tainted: G            E     5.7.0-rc1-00101-g8624b7577b9c #781
Hardware name: amlogic w400/w400, BIOS 2020.01-rc5 03/12/2020
Call trace:
 dump_backtrace+0x0/0x2a0
 show_stack+0x20/0x30
 dump_stack+0xec/0x148
 print_address_description.isra.12+0x70/0x35c
 __kasan_report+0xfc/0x1d4
 kasan_report+0x4c/0x68
 __asan_load4+0x9c/0xd8
 _get_maxdiv+0x74/0xd8
 clk_divider_bestdiv+0x74/0x5e0
 clk_divider_round_rate+0x80/0x1a8
 clk_core_determine_round_nolock.part.9+0x9c/0xd0
 clk_core_round_rate_nolock+0xf0/0x108
 clk_hw_round_rate+0xac/0xf0
 clk_factor_round_rate+0xb8/0xd0
 clk_core_determine_round_nolock.part.9+0x9c/0xd0
 clk_core_round_rate_nolock+0xf0/0x108
 clk_core_round_rate_nolock+0xbc/0x108
 clk_core_set_rate_nolock+0xc4/0x2e8
 clk_set_rate+0x58/0xe0
 meson8b_dwmac_probe+0x588/0x72c [dwmac_meson8b]
 platform_drv_probe+0x78/0xd8
 really_probe+0x158/0x610
 driver_probe_device+0x140/0x1b0
 device_driver_attach+0xa4/0xb0
 __driver_attach+0xcc/0x1c8
 bus_for_each_dev+0xf4/0x168
 driver_attach+0x3c/0x50
 bus_add_driver+0x238/0x2e8
 driver_register+0xc8/0x1e8
 __platform_driver_register+0x88/0x98
 meson8b_dwmac_driver_init+0x28/0x1000 [dwmac_meson8b]
 do_one_initcall+0xa8/0x328
 do_init_module+0xe8/0x368
 load_module+0x3300/0x36b0
 __do_sys_finit_module+0x120/0x1a8
 __arm64_sys_finit_module+0x4c/0x60
 el0_svc_common.constprop.2+0xe4/0x268
 do_el0_svc+0x98/0xa8
 el0_svc+0x24/0x68
 el0_sync_handler+0x12c/0x318
 el0_sync+0x158/0x180

The buggy address belongs to the variable:
 div_table.63646+0x34/0xfffffffffffffa40 [dwmac_meson8b]

Memory state around the buggy address:
 ffffa00009061480: fa fa fa fa 00 00 00 01 fa fa fa fa 00 00 00 00
 ffffa00009061500: 05 fa fa fa fa fa fa fa 00 04 fa fa fa fa fa fa
>ffffa00009061580: 00 03 fa fa fa fa fa fa 00 00 00 00 00 00 fa fa
                                                             ^
 ffffa00009061600: fa fa fa fa 00 01 fa fa fa fa fa fa 01 fa fa fa
 ffffa00009061680: fa fa fa fa 00 01 fa fa fa fa fa fa 04 fa fa fa
==================================================================

Digging into this indeed shows that the clock divider array is
lacking a final fence, and that the clock subsystems goes in the
weeds. Oh well.

Let's add the empty structure that indicates the end of the array.

Fixes: bd6f48546b9c ("net: stmmac: dwmac-meson8b: Fix the RGMII TX delay on Meson8b/8m2 SoCs")
Signed-off-by: Marc Zyngier <maz@kernel.org>
Cc: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Reviewed-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
index 33ce139f090f..d1d6ba9cdccd 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
@@ -119,6 +119,7 @@ static int meson8b_init_rgmii_tx_clk(struct meson8b_dwmac *dwmac)
 		{ .div = 5, .val = 5, },
 		{ .div = 6, .val = 6, },
 		{ .div = 7, .val = 7, },
+		{ /* end of array */ }
 	};
 
 	clk_configs = devm_kzalloc(dev, sizeof(*clk_configs), GFP_KERNEL);
-- 
2.20.1


From 6b3dd8b7aab2eec8d08605283e8505116a9ea368 Mon Sep 17 00:00:00 2001
From: Xiyu Yang <xiyuyang19@fudan.edu.cn>
Date: Thu, 23 Apr 2020 13:13:03 +0800
Subject: [PATCH 13/27] net/x25: Fix x25_neigh refcnt leak when receiving frame

[ Upstream commit f35d12971b4d814cdb2f659d76b42f0c545270b6 ]

x25_lapb_receive_frame() invokes x25_get_neigh(), which returns a
reference of the specified x25_neigh object to "nb" with increased
refcnt.

When x25_lapb_receive_frame() returns, local variable "nb" becomes
invalid, so the refcount should be decreased to keep refcount balanced.

The reference counting issue happens in one path of
x25_lapb_receive_frame(). When pskb_may_pull() returns false, the
function forgets to decrease the refcnt increased by x25_get_neigh(),
causing a refcnt leak.

Fix this issue by calling x25_neigh_put() when pskb_may_pull() returns
false.

Fixes: cb101ed2c3c7 ("x25: Handle undersized/fragmented skbs")
Signed-off-by: Xiyu Yang <xiyuyang19@fudan.edu.cn>
Signed-off-by: Xin Tan <tanxin.ctf@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/x25/x25_dev.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/x25/x25_dev.c b/net/x25/x25_dev.c
index 00e782335cb0..25bf72ee6cad 100644
--- a/net/x25/x25_dev.c
+++ b/net/x25/x25_dev.c
@@ -115,8 +115,10 @@ int x25_lapb_receive_frame(struct sk_buff *skb, struct net_device *dev,
 		goto drop;
 	}
 
-	if (!pskb_may_pull(skb, 1))
+	if (!pskb_may_pull(skb, 1)) {
+		x25_neigh_put(nb);
 		return 0;
+	}
 
 	switch (skb->data[0]) {
 
-- 
2.20.1


From bf335ff54f9642d6cfd5cfc0d33f8d31519ab7f5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 21 Apr 2020 10:00:28 -0700
Subject: [PATCH 14/27] sched: etf: do not assume all sockets are full blown

[ Upstream commit a1211bf9a7774706722ba3b18c6157d980319f79 ]

skb->sk does not always point to a full blown socket,
we need to use sk_fullsock() before accessing fields which
only make sense on full socket.

BUG: KASAN: use-after-free in report_sock_error+0x286/0x300 net/sched/sch_etf.c:141
Read of size 1 at addr ffff88805eb9b245 by task syz-executor.5/9630

CPU: 1 PID: 9630 Comm: syz-executor.5 Not tainted 5.7.0-rc2-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x188/0x20d lib/dump_stack.c:118
 print_address_description.constprop.0.cold+0xd3/0x315 mm/kasan/report.c:382
 __kasan_report.cold+0x35/0x4d mm/kasan/report.c:511
 kasan_report+0x33/0x50 mm/kasan/common.c:625
 report_sock_error+0x286/0x300 net/sched/sch_etf.c:141
 etf_enqueue_timesortedlist+0x389/0x740 net/sched/sch_etf.c:170
 __dev_xmit_skb net/core/dev.c:3710 [inline]
 __dev_queue_xmit+0x154a/0x30a0 net/core/dev.c:4021
 neigh_hh_output include/net/neighbour.h:499 [inline]
 neigh_output include/net/neighbour.h:508 [inline]
 ip6_finish_output2+0xfb5/0x25b0 net/ipv6/ip6_output.c:117
 __ip6_finish_output+0x442/0xab0 net/ipv6/ip6_output.c:143
 ip6_finish_output+0x34/0x1f0 net/ipv6/ip6_output.c:153
 NF_HOOK_COND include/linux/netfilter.h:296 [inline]
 ip6_output+0x239/0x810 net/ipv6/ip6_output.c:176
 dst_output include/net/dst.h:435 [inline]
 NF_HOOK include/linux/netfilter.h:307 [inline]
 NF_HOOK include/linux/netfilter.h:301 [inline]
 ip6_xmit+0xe1a/0x2090 net/ipv6/ip6_output.c:280
 tcp_v6_send_synack+0x4e7/0x960 net/ipv6/tcp_ipv6.c:521
 tcp_rtx_synack+0x10d/0x1a0 net/ipv4/tcp_output.c:3916
 inet_rtx_syn_ack net/ipv4/inet_connection_sock.c:669 [inline]
 reqsk_timer_handler+0x4c2/0xb40 net/ipv4/inet_connection_sock.c:763
 call_timer_fn+0x1ac/0x780 kernel/time/timer.c:1405
 expire_timers kernel/time/timer.c:1450 [inline]
 __run_timers kernel/time/timer.c:1774 [inline]
 __run_timers kernel/time/timer.c:1741 [inline]
 run_timer_softirq+0x623/0x1600 kernel/time/timer.c:1787
 __do_softirq+0x26c/0x9f7 kernel/softirq.c:292
 invoke_softirq kernel/softirq.c:373 [inline]
 irq_exit+0x192/0x1d0 kernel/softirq.c:413
 exiting_irq arch/x86/include/asm/apic.h:546 [inline]
 smp_apic_timer_interrupt+0x19e/0x600 arch/x86/kernel/apic/apic.c:1140
 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:829
 </IRQ>
RIP: 0010:des_encrypt+0x157/0x9c0 lib/crypto/des.c:792
Code: 85 22 06 00 00 41 31 dc 41 8b 4d 04 44 89 e2 41 83 e4 3f 4a 8d 3c a5 60 72 72 88 81 e2 3f 3f 3f 3f 48 89 f8 48 c1 e8 03 31 d9 <0f> b6 34 28 48 89 f8 c1 c9 04 83 e0 07 83 c0 03 40 38 f0 7c 09 40
RSP: 0018:ffffc90003b5f6c0 EFLAGS: 00000282 ORIG_RAX: ffffffffffffff13
RAX: 1ffffffff10e4e55 RBX: 00000000d2f846d0 RCX: 00000000d2f846d0
RDX: 0000000012380612 RSI: ffffffff839863ca RDI: ffffffff887272a8
RBP: dffffc0000000000 R08: ffff888091d0a380 R09: 0000000000800081
R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000012
R13: ffff8880a8ae8078 R14: 00000000c545c93e R15: 0000000000000006
 cipher_crypt_one crypto/cipher.c:75 [inline]
 crypto_cipher_encrypt_one+0x124/0x210 crypto/cipher.c:82
 crypto_cbcmac_digest_update+0x1b5/0x250 crypto/ccm.c:830
 crypto_shash_update+0xc4/0x120 crypto/shash.c:119
 shash_ahash_update+0xa3/0x110 crypto/shash.c:246
 crypto_ahash_update include/crypto/hash.h:547 [inline]
 hash_sendmsg+0x518/0xad0 crypto/algif_hash.c:102
 sock_sendmsg_nosec net/socket.c:652 [inline]
 sock_sendmsg+0xcf/0x120 net/socket.c:672
 ____sys_sendmsg+0x308/0x7e0 net/socket.c:2362
 ___sys_sendmsg+0x100/0x170 net/socket.c:2416
 __sys_sendmmsg+0x195/0x480 net/socket.c:2506
 __do_sys_sendmmsg net/socket.c:2535 [inline]
 __se_sys_sendmmsg net/socket.c:2532 [inline]
 __x64_sys_sendmmsg+0x99/0x100 net/socket.c:2532
 do_syscall_64+0xf6/0x7d0 arch/x86/entry/common.c:295
 entry_SYSCALL_64_after_hwframe+0x49/0xb3
RIP: 0033:0x45c829
Code: 0d b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 db b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f6d9528ec78 EFLAGS: 00000246 ORIG_RAX: 0000000000000133
RAX: ffffffffffffffda RBX: 00000000004fc080 RCX: 000000000045c829
RDX: 0000000000000001 RSI: 0000000020002640 RDI: 0000000000000004
RBP: 000000000078bf00 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff
R13: 00000000000008d7 R14: 00000000004cb7aa R15: 00007f6d9528f6d4

Fixes: 4b15c7075352 ("net/sched: Make etf report drops on error_queue")
Fixes: 25db26a91364 ("net/sched: Introduce the ETF Qdisc")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Reviewed-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_etf.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c
index b1da5589a0c6..c48f91075b5c 100644
--- a/net/sched/sch_etf.c
+++ b/net/sched/sch_etf.c
@@ -82,7 +82,7 @@ static bool is_packet_valid(struct Qdisc *sch, struct sk_buff *nskb)
 	if (q->skip_sock_check)
 		goto skip;
 
-	if (!sk)
+	if (!sk || !sk_fullsock(sk))
 		return false;
 
 	if (!sock_flag(sk, SOCK_TXTIME))
@@ -137,8 +137,9 @@ static void report_sock_error(struct sk_buff *skb, u32 err, u8 code)
 	struct sock_exterr_skb *serr;
 	struct sk_buff *clone;
 	ktime_t txtime = skb->tstamp;
+	struct sock *sk = skb->sk;
 
-	if (!skb->sk || !(skb->sk->sk_txtime_report_errors))
+	if (!sk || !sk_fullsock(sk) || !(sk->sk_txtime_report_errors))
 		return;
 
 	clone = skb_clone(skb, GFP_ATOMIC);
@@ -154,7 +155,7 @@ static void report_sock_error(struct sk_buff *skb, u32 err, u8 code)
 	serr->ee.ee_data = (txtime >> 32); /* high part of tstamp */
 	serr->ee.ee_info = txtime; /* low part of tstamp */
 
-	if (sock_queue_err_skb(skb->sk, clone))
+	if (sock_queue_err_skb(sk, clone))
 		kfree_skb(clone);
 }
 
-- 
2.20.1


From c1da1ade7f7cbb5739c3979f129d0206acdee860 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 21 Apr 2020 08:47:24 -0600
Subject: [PATCH 15/27] selftests: Fix suppress test in fib_tests.sh

[ Upstream commit 2c1dd4c110627c2a4f006643f074119205cfcff4 ]

fib_tests is spewing errors:
    ...
    Cannot open network namespace "ns1": No such file or directory
    Cannot open network namespace "ns1": No such file or directory
    Cannot open network namespace "ns1": No such file or directory
    Cannot open network namespace "ns1": No such file or directory
    ping: connect: Network is unreachable
    Cannot open network namespace "ns1": No such file or directory
    Cannot open network namespace "ns1": No such file or directory
    ...

Each test entry in fib_tests is supposed to do its own setup and
cleanup. Right now the $IP commands in fib_suppress_test are
failing because there is no ns1. Add the setup/cleanup and logging
expected for each test.

Fixes: ca7a03c41753 ("ipv6: do not free rt if FIB_LOOKUP_NOREF is set on suppress rule")
Signed-off-by: David Ahern <dsahern@gmail.com>
Cc: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/fib_tests.sh | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 09854f8a0b57..4811067d9b05 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -618,16 +618,22 @@ fib_nexthop_test()
 
 fib_suppress_test()
 {
+	echo
+	echo "FIB rule with suppress_prefixlength"
+	setup
+
 	$IP link add dummy1 type dummy
 	$IP link set dummy1 up
 	$IP -6 route add default dev dummy1
 	$IP -6 rule add table main suppress_prefixlength 0
-	ping -f -c 1000 -W 1 1234::1 || true
+	ping -f -c 1000 -W 1 1234::1 >/dev/null 2>&1
 	$IP -6 rule del table main suppress_prefixlength 0
 	$IP link del dummy1
 
 	# If we got here without crashing, we're good.
-	return 0
+	log_test 0 0 "FIB rule suppress test"
+
+	cleanup
 }
 
 ################################################################################
-- 
2.20.1


From 24ff3d19a4290676890e2c6b4a58803578033ed4 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 17 Apr 2020 07:10:23 -0700
Subject: [PATCH 16/27] tcp: cache line align MAX_TCP_HEADER

[ Upstream commit 9bacd256f1354883d3c1402655153367982bba49 ]

TCP stack is dumb in how it cooks its output packets.

Depending on MAX_HEADER value, we might chose a bad ending point
for the headers.

If we align the end of TCP headers to cache line boundary, we
make sure to always use the smallest number of cache lines,
which always help.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 830c89db1245..cce285f70c8e 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -50,7 +50,7 @@ extern struct inet_hashinfo tcp_hashinfo;
 extern struct percpu_counter tcp_orphan_count;
 void tcp_time_wait(struct sock *sk, int state, int timeo);
 
-#define MAX_TCP_HEADER	(128 + MAX_HEADER)
+#define MAX_TCP_HEADER	L1_CACHE_ALIGN(128 + MAX_HEADER)
 #define MAX_TCP_OPTION_SPACE 40
 #define TCP_MIN_SND_MSS		48
 #define TCP_MIN_GSO_SIZE	(TCP_MIN_SND_MSS - MAX_TCP_OPTION_SPACE)
-- 
2.20.1


From 4bc5f69642afb4e616e7a67ba2217c9928c5129f Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Mon, 20 Apr 2020 15:01:33 +0000
Subject: [PATCH 17/27] team: fix hang in team_mode_get()

[ Upstream commit 1c30fbc76b8f0c07c92a8ca4cd7c456612e17eb5 ]

When team mode is changed or set, the team_mode_get() is called to check
whether the mode module is inserted or not. If the mode module is not
inserted, it calls the request_module().
In the request_module(), it creates a child process, which is
the "modprobe" process and waits for the done of the child process.
At this point, the following locks were used.
down_read(&cb_lock()); by genl_rcv()
    genl_lock(); by genl_rcv_msc()
        rtnl_lock(); by team_nl_cmd_options_set()
            mutex_lock(&team->lock); by team_nl_team_get()

Concurrently, the team module could be removed by rmmod or "modprobe -r"
The __exit function of team module is team_module_exit(), which calls
team_nl_fini() and it tries to acquire following locks.
down_write(&cb_lock);
    genl_lock();
Because of the genl_lock() and cb_lock, this process can't be finished
earlier than request_module() routine.

The problem secenario.
CPU0                                     CPU1
team_mode_get
    request_module()
                                         modprobe -r team_mode_roundrobin
                                                     team <--(B)
        modprobe team <--(A)
            team_mode_roundrobin

By request_module(), the "modprobe team_mode_roundrobin" command
will be executed. At this point, the modprobe process will decide
that the team module should be inserted before team_mode_roundrobin.
Because the team module is being removed.

By the module infrastructure, the same module insert/remove operations
can't be executed concurrently.
So, (A) waits for (B) but (B) also waits for (A) because of locks.
So that the hang occurs at this point.

Test commands:
    while :
    do
        teamd -d &
	killall teamd &
	modprobe -rv team_mode_roundrobin &
    done

The approach of this patch is to hold the reference count of the team
module if the team module is compiled as a module. If the reference count
of the team module is not zero while request_module() is being called,
the team module will not be removed at that moment.
So that the above scenario could not occur.

Fixes: 3d249d4ca7d0 ("net: introduce ethernet teaming device")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 4004f98e50d9..04845a4017f9 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -468,6 +468,9 @@ static const struct team_mode *team_mode_get(const char *kind)
 	struct team_mode_item *mitem;
 	const struct team_mode *mode = NULL;
 
+	if (!try_module_get(THIS_MODULE))
+		return NULL;
+
 	spin_lock(&mode_list_lock);
 	mitem = __find_mode(kind);
 	if (!mitem) {
@@ -483,6 +486,7 @@ static const struct team_mode *team_mode_get(const char *kind)
 	}
 
 	spin_unlock(&mode_list_lock);
+	module_put(THIS_MODULE);
 	return mode;
 }
 
-- 
2.20.1


From 72bac0be7b963cf84e645427a0e465ccac395228 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 21 Apr 2020 17:48:27 -0600
Subject: [PATCH 18/27] vrf: Fix IPv6 with qdisc and xfrm

[ Upstream commit a53c102872ad6e34e1518e25899dc9498c27f8b1 ]

When a qdisc is attached to the VRF device, the packet goes down the ndo
xmit function which is setup to send the packet back to the VRF driver
which does a lookup to send the packet out. The lookup in the VRF driver
is not considering xfrm policies. Change it to use ip6_dst_lookup_flow
rather than ip6_route_output.

Fixes: 35402e313663 ("net: Add IPv6 support to VRF device")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index b8228f50bc94..4285236b5f2e 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -188,8 +188,8 @@ static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
 	fl6.flowi6_proto = iph->nexthdr;
 	fl6.flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF;
 
-	dst = ip6_route_output(net, NULL, &fl6);
-	if (dst == dst_null)
+	dst = ip6_dst_lookup_flow(net, NULL, &fl6, NULL);
+	if (IS_ERR(dst) || dst == dst_null)
 		goto err;
 
 	skb_dst_drop(skb);
-- 
2.20.1


From 79e7a9d5c07416d975623d15ecdab7bcc68fbdb8 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Mon, 20 Apr 2020 20:26:51 -0700
Subject: [PATCH 19/27] net: dsa: b53: Lookup VID in ARL searches when VLAN is
 enabled

[ Upstream commit 2e97b0cd1651a270f3a3fcf42115c51f3284c049 ]

When VLAN is enabled, and an ARL search is issued, we also need to
compare the full {MAC,VID} tuple before returning a successful search
result.

Fixes: 1da6df85c6fb ("net: dsa: b53: Implement ARL add/del/dump operations")
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/b53/b53_common.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index d618650533b6..09fe33eab406 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -1472,6 +1472,9 @@ static int b53_arl_read(struct b53_device *dev, u64 mac,
 			continue;
 		if ((mac_vid & ARLTBL_MAC_MASK) != mac)
 			continue;
+		if (dev->vlan_enabled &&
+		    ((mac_vid >> ARLTBL_VID_S) & ARLTBL_VID_MASK) != vid)
+			continue;
 		*idx = i;
 	}
 
-- 
2.20.1


From 67ab83c157f7f2e3cf291d9baa4347f396de0c4a Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Mon, 20 Apr 2020 20:26:52 -0700
Subject: [PATCH 20/27] net: dsa: b53: Fix valid setting for MDB entries

[ Upstream commit eab167f4851a19c514469dfa81147f77e17b5b20 ]

When support for the MDB entries was added, the valid bit was correctly
changed to be assigned depending on the remaining port bitmask, that is,
if there were no more ports added to the entry's port bitmask, the entry
now becomes invalid. There was another assignment a few lines below that
would override this which would invalidate entries even when there were
still multiple ports left in the MDB entry.

Fixes: 5d65b64a3d97 ("net: dsa: b53: Add support for MDB")
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/b53/b53_common.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 09fe33eab406..ebbf03d3fe5a 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -1515,7 +1515,6 @@ static int b53_arl_op(struct b53_device *dev, int op, int port,
 
 	memset(&ent, 0, sizeof(ent));
 	ent.port = port;
-	ent.is_valid = is_valid;
 	ent.vid = vid;
 	ent.is_static = true;
 	memcpy(ent.mac, addr, ETH_ALEN);
-- 
2.20.1


From 333da92827dc67dcaf1f28e218b8c1545a1e397d Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Mon, 20 Apr 2020 20:26:53 -0700
Subject: [PATCH 21/27] net: dsa: b53: Fix ARL register definitions

[ Upstream commit c2e77a18a7ed65eb48f6e389b6a59a0fd753646a ]

The ARL {MAC,VID} tuple and the forward entry were off by 0x10 bytes,
which means that when we read/wrote from/to ARL bin index 0, we were
actually accessing the ARLA_RWCTRL register.

Fixes: 1da6df85c6fb ("net: dsa: b53: Implement ARL add/del/dump operations")
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/b53/b53_regs.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/b53/b53_regs.h b/drivers/net/dsa/b53/b53_regs.h
index 2a9f421680aa..d914e756cdab 100644
--- a/drivers/net/dsa/b53/b53_regs.h
+++ b/drivers/net/dsa/b53/b53_regs.h
@@ -304,7 +304,7 @@
  *
  * BCM5325 and BCM5365 share most definitions below
  */
-#define B53_ARLTBL_MAC_VID_ENTRY(n)	(0x10 * (n))
+#define B53_ARLTBL_MAC_VID_ENTRY(n)	((0x10 * (n)) + 0x10)
 #define   ARLTBL_MAC_MASK		0xffffffffffffULL
 #define   ARLTBL_VID_S			48
 #define   ARLTBL_VID_MASK_25		0xff
@@ -316,7 +316,7 @@
 #define   ARLTBL_VALID_25		BIT(63)
 
 /* ARL Table Data Entry N Registers (32 bit) */
-#define B53_ARLTBL_DATA_ENTRY(n)	((0x10 * (n)) + 0x08)
+#define B53_ARLTBL_DATA_ENTRY(n)	((0x10 * (n)) + 0x18)
 #define   ARLTBL_DATA_PORT_ID_MASK	0x1ff
 #define   ARLTBL_TC(tc)			((3 & tc) << 11)
 #define   ARLTBL_AGE			BIT(14)
-- 
2.20.1


From 38d2714387e066058cfd64fc7739e41196a17ab3 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Mon, 20 Apr 2020 20:26:54 -0700
Subject: [PATCH 22/27] net: dsa: b53: Rework ARL bin logic

[ Upstream commit 6344dbde6a27d10d16246d734b968f84887841e2 ]

When asking the ARL to read a MAC address, we will get a number of bins
returned in a single read. Out of those bins, there can essentially be 3
states:

- all bins are full, we have no space left, and we can either replace an
  existing address or return that full condition

- the MAC address was found, then we need to return its bin index and
  modify that one, and only that one

- the MAC address was not found and we have a least one bin free, we use
  that bin index location then

The code would unfortunately fail on all counts.

Fixes: 1da6df85c6fb ("net: dsa: b53: Implement ARL add/del/dump operations")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/b53/b53_common.c | 30 ++++++++++++++++++++++++++----
 drivers/net/dsa/b53/b53_regs.h   |  3 +++
 2 files changed, 29 insertions(+), 4 deletions(-)

diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index ebbf03d3fe5a..813f14a7792b 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -1450,6 +1450,7 @@ static int b53_arl_read(struct b53_device *dev, u64 mac,
 			u16 vid, struct b53_arl_entry *ent, u8 *idx,
 			bool is_valid)
 {
+	DECLARE_BITMAP(free_bins, B53_ARLTBL_MAX_BIN_ENTRIES);
 	unsigned int i;
 	int ret;
 
@@ -1457,6 +1458,8 @@ static int b53_arl_read(struct b53_device *dev, u64 mac,
 	if (ret)
 		return ret;
 
+	bitmap_zero(free_bins, dev->num_arl_entries);
+
 	/* Read the bins */
 	for (i = 0; i < dev->num_arl_entries; i++) {
 		u64 mac_vid;
@@ -1468,16 +1471,24 @@ static int b53_arl_read(struct b53_device *dev, u64 mac,
 			   B53_ARLTBL_DATA_ENTRY(i), &fwd_entry);
 		b53_arl_to_entry(ent, mac_vid, fwd_entry);
 
-		if (!(fwd_entry & ARLTBL_VALID))
+		if (!(fwd_entry & ARLTBL_VALID)) {
+			set_bit(i, free_bins);
 			continue;
+		}
 		if ((mac_vid & ARLTBL_MAC_MASK) != mac)
 			continue;
 		if (dev->vlan_enabled &&
 		    ((mac_vid >> ARLTBL_VID_S) & ARLTBL_VID_MASK) != vid)
 			continue;
 		*idx = i;
+		return 0;
 	}
 
+	if (bitmap_weight(free_bins, dev->num_arl_entries) == 0)
+		return -ENOSPC;
+
+	*idx = find_first_bit(free_bins, dev->num_arl_entries);
+
 	return -ENOENT;
 }
 
@@ -1507,10 +1518,21 @@ static int b53_arl_op(struct b53_device *dev, int op, int port,
 	if (op)
 		return ret;
 
-	/* We could not find a matching MAC, so reset to a new entry */
-	if (ret) {
+	switch (ret) {
+	case -ENOSPC:
+		dev_dbg(dev->dev, "{%pM,%.4d} no space left in ARL\n",
+			addr, vid);
+		return is_valid ? ret : 0;
+	case -ENOENT:
+		/* We could not find a matching MAC, so reset to a new entry */
+		dev_dbg(dev->dev, "{%pM,%.4d} not found, using idx: %d\n",
+			addr, vid, idx);
 		fwd_entry = 0;
-		idx = 1;
+		break;
+	default:
+		dev_dbg(dev->dev, "{%pM,%.4d} found, using idx: %d\n",
+			addr, vid, idx);
+		break;
 	}
 
 	memset(&ent, 0, sizeof(ent));
diff --git a/drivers/net/dsa/b53/b53_regs.h b/drivers/net/dsa/b53/b53_regs.h
index d914e756cdab..14f617e9173d 100644
--- a/drivers/net/dsa/b53/b53_regs.h
+++ b/drivers/net/dsa/b53/b53_regs.h
@@ -323,6 +323,9 @@
 #define   ARLTBL_STATIC			BIT(15)
 #define   ARLTBL_VALID			BIT(16)
 
+/* Maximum number of bin entries in the ARL for all switches */
+#define B53_ARLTBL_MAX_BIN_ENTRIES	4
+
 /* ARL Search Control Register (8 bit) */
 #define B53_ARL_SRCH_CTL		0x50
 #define B53_ARL_SRCH_CTL_25		0x20
-- 
2.20.1


From a4c3ff11647032b946f2c346643d613d5dfa1fcf Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Mon, 20 Apr 2020 20:26:55 -0700
Subject: [PATCH 23/27] net: dsa: b53: b53_arl_rw_op() needs to select IVL or
 SVL

[ Upstream commit 64fec9493f7dc9bdd7233bcfe98985c45bd0e3c1 ]

Flip the IVL_SVL_SELECT bit correctly based on the VLAN enable status,
the default is to perform Shared VLAN learning instead of Individual
learning.

Fixes: 1da6df85c6fb ("net: dsa: b53: Implement ARL add/del/dump operations")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/b53/b53_common.c | 4 ++++
 drivers/net/dsa/b53/b53_regs.h   | 1 +
 2 files changed, 5 insertions(+)

diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 813f14a7792b..14850b7fe6d7 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -1441,6 +1441,10 @@ static int b53_arl_rw_op(struct b53_device *dev, unsigned int op)
 		reg |= ARLTBL_RW;
 	else
 		reg &= ~ARLTBL_RW;
+	if (dev->vlan_enabled)
+		reg &= ~ARLTBL_IVL_SVL_SELECT;
+	else
+		reg |= ARLTBL_IVL_SVL_SELECT;
 	b53_write8(dev, B53_ARLIO_PAGE, B53_ARLTBL_RW_CTRL, reg);
 
 	return b53_arl_op_wait(dev);
diff --git a/drivers/net/dsa/b53/b53_regs.h b/drivers/net/dsa/b53/b53_regs.h
index 14f617e9173d..c90985c294a2 100644
--- a/drivers/net/dsa/b53/b53_regs.h
+++ b/drivers/net/dsa/b53/b53_regs.h
@@ -292,6 +292,7 @@
 /* ARL Table Read/Write Register (8 bit) */
 #define B53_ARLTBL_RW_CTRL		0x00
 #define    ARLTBL_RW			BIT(0)
+#define    ARLTBL_IVL_SVL_SELECT	BIT(6)
 #define    ARLTBL_START_DONE		BIT(7)
 
 /* MAC Address Index Register (48 bit) */
-- 
2.20.1


From d5b4d4d45af76b24e04c9021acd63d5a7adf960a Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Wed, 22 Apr 2020 17:29:50 +0200
Subject: [PATCH 24/27] vxlan: use the correct nlattr array in
 NL_SET_ERR_MSG_ATTR

[ Upstream commit cc8e7c69db4dcc565ed3020f97ddd6debab6cbe8 ]

IFLA_VXLAN_* attributes are in the data array, which is correctly
used when fetching the value, but not when setting the extended
ack. Because IFLA_VXLAN_MAX < IFLA_MAX, we avoid out of bounds
array accesses, but we don't provide a pointer to the invalid
attribute to userspace.

Fixes: 653ef6a3e4af ("vxlan: change vxlan_[config_]validate() to use netlink_ext_ack for error reporting")
Fixes: b4d3069783bc ("vxlan: Allow configuration of DF behaviour")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 93690f77ec9c..ae59fca96032 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -3144,7 +3144,7 @@ static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[],
 		u32 id = nla_get_u32(data[IFLA_VXLAN_ID]);
 
 		if (id >= VXLAN_N_VID) {
-			NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_ID],
+			NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_ID],
 					    "VXLAN ID must be lower than 16777216");
 			return -ERANGE;
 		}
@@ -3155,7 +3155,7 @@ static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[],
 			= nla_data(data[IFLA_VXLAN_PORT_RANGE]);
 
 		if (ntohs(p->high) < ntohs(p->low)) {
-			NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_PORT_RANGE],
+			NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_PORT_RANGE],
 					    "Invalid source port range");
 			return -EINVAL;
 		}
@@ -3165,7 +3165,7 @@ static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[],
 		enum ifla_vxlan_df df = nla_get_u8(data[IFLA_VXLAN_DF]);
 
 		if (df < 0 || df > VXLAN_DF_MAX) {
-			NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_DF],
+			NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_DF],
 					    "Invalid DF attribute");
 			return -EINVAL;
 		}
-- 
2.20.1


From 4f32d791423b44cd7323bb6325735d694863e490 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Wed, 22 Apr 2020 17:29:51 +0200
Subject: [PATCH 25/27] geneve: use the correct nlattr array in
 NL_SET_ERR_MSG_ATTR

[ Upstream commit 9a7b5b50de8a764671ba1800fe4c52d3b7013901 ]

IFLA_GENEVE_* attributes are in the data array, which is correctly
used when fetching the value, but not when setting the extended
ack. Because IFLA_GENEVE_MAX < IFLA_MAX, we avoid out of bounds
array accesses, but we don't provide a pointer to the invalid
attribute to userspace.

Fixes: a025fb5f49ad ("geneve: Allow configuration of DF behaviour")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 730ab57201bd..aa101f72d405 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1207,7 +1207,7 @@ static int geneve_validate(struct nlattr *tb[], struct nlattr *data[],
 		enum ifla_geneve_df df = nla_get_u8(data[IFLA_GENEVE_DF]);
 
 		if (df < 0 || df > GENEVE_DF_MAX) {
-			NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_GENEVE_DF],
+			NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_DF],
 					    "Invalid DF attribute");
 			return -EINVAL;
 		}
-- 
2.20.1


From 1d5a88528a4d0ba5ae5031f7f22b31c3ce2b3479 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Mon, 20 Apr 2020 17:13:51 -0600
Subject: [PATCH 26/27] xfrm: Always set XFRM_TRANSFORMED in
 xfrm{4,6}_output_finish

[ Upstream commit 0c922a4850eba2e668f73a3f1153196e09abb251 ]

IPSKB_XFRM_TRANSFORMED and IP6SKB_XFRM_TRANSFORMED are skb flags set by
xfrm code to tell other skb handlers that the packet has been passed
through the xfrm output functions. Simplify the code and just always
set them rather than conditionally based on netfilter enabled thus
making the flag available for other users.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/xfrm4_output.c | 2 --
 net/ipv6/xfrm6_output.c | 2 --
 2 files changed, 4 deletions(-)

diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
index ecff3fce9807..ab343ae686d4 100644
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -58,9 +58,7 @@ int xfrm4_output_finish(struct sock *sk, struct sk_buff *skb)
 {
 	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
 
-#ifdef CONFIG_NETFILTER
 	IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED;
-#endif
 
 	return xfrm_output(sk, skb);
 }
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index eecac1b7148e..cf2a0ce15c1c 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -111,9 +111,7 @@ int xfrm6_output_finish(struct sock *sk, struct sk_buff *skb)
 {
 	memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
 
-#ifdef CONFIG_NETFILTER
 	IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED;
-#endif
 
 	return xfrm_output(sk, skb);
 }
-- 
2.20.1


From bb53be1f6f4f3090f15b00c79d008b83e093f2d9 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Mon, 20 Apr 2020 17:13:52 -0600
Subject: [PATCH 27/27] vrf: Check skb for XFRM_TRANSFORMED flag

[ Upstream commit 16b9db1ce34ff00d6c18e82825125cfef0cdfb13 ]

To avoid a loop with qdiscs and xfrms, check if the skb has already gone
through the qdisc attached to the VRF device and then to the xfrm layer.
If so, no need for a second redirect.

Fixes: 193125dbd8eb ("net: Introduce VRF device driver")
Reported-by: Trev Larock <trev@larock.ca>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 4285236b5f2e..6716deeb35e3 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -474,7 +474,8 @@ static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev,
 	if (rt6_need_strict(&ipv6_hdr(skb)->daddr))
 		return skb;
 
-	if (qdisc_tx_is_default(vrf_dev))
+	if (qdisc_tx_is_default(vrf_dev) ||
+	    IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED)
 		return vrf_ip6_out_direct(vrf_dev, sk, skb);
 
 	return vrf_ip6_out_redirect(vrf_dev, skb);
@@ -686,7 +687,8 @@ static struct sk_buff *vrf_ip_out(struct net_device *vrf_dev,
 	    ipv4_is_lbcast(ip_hdr(skb)->daddr))
 		return skb;
 
-	if (qdisc_tx_is_default(vrf_dev))
+	if (qdisc_tx_is_default(vrf_dev) ||
+	    IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED)
 		return vrf_ip_out_direct(vrf_dev, sk, skb);
 
 	return vrf_ip_out_redirect(vrf_dev, skb);
-- 
2.20.1


[-- Attachment #3: net_56.mbox --]
[-- Type: Application/Octet-Stream, Size: 74127 bytes --]

From fc0ab917a915e81c49e8925194097cb9b63fb669 Mon Sep 17 00:00:00 2001
From: Vishal Kulkarni <vishal@chelsio.com>
Date: Wed, 22 Apr 2020 21:20:07 +0530
Subject: [PATCH 01/30] cxgb4: fix adapter crash due to wrong MC size

[ Upstream commit ce222748078592afb51b810dc154531aeba4f512 ]

In the absence of MC1, the size calculation function
cudbg_mem_region_size() was returing wrong MC size and
resulted in adapter crash. This patch adds new argument
to cudbg_mem_region_size() which will have actual size
and returns error to caller in the absence of MC1.

Fixes: a1c69520f785 ("cxgb4: collect MC memory dump")
Signed-off-by: Vishal Kulkarni <vishal@chelsio.com>"
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/chelsio/cxgb4/cudbg_lib.c    | 27 ++++++++++++++-----
 1 file changed, 20 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
index 19c11568113a..7b9cd69f9844 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
@@ -1049,9 +1049,9 @@ static void cudbg_t4_fwcache(struct cudbg_init *pdbg_init,
 	}
 }
 
-static unsigned long cudbg_mem_region_size(struct cudbg_init *pdbg_init,
-					   struct cudbg_error *cudbg_err,
-					   u8 mem_type)
+static int cudbg_mem_region_size(struct cudbg_init *pdbg_init,
+				 struct cudbg_error *cudbg_err,
+				 u8 mem_type, unsigned long *region_size)
 {
 	struct adapter *padap = pdbg_init->adap;
 	struct cudbg_meminfo mem_info;
@@ -1060,15 +1060,23 @@ static unsigned long cudbg_mem_region_size(struct cudbg_init *pdbg_init,
 
 	memset(&mem_info, 0, sizeof(struct cudbg_meminfo));
 	rc = cudbg_fill_meminfo(padap, &mem_info);
-	if (rc)
+	if (rc) {
+		cudbg_err->sys_err = rc;
 		return rc;
+	}
 
 	cudbg_t4_fwcache(pdbg_init, cudbg_err);
 	rc = cudbg_meminfo_get_mem_index(padap, &mem_info, mem_type, &mc_idx);
-	if (rc)
+	if (rc) {
+		cudbg_err->sys_err = rc;
 		return rc;
+	}
+
+	if (region_size)
+		*region_size = mem_info.avail[mc_idx].limit -
+			       mem_info.avail[mc_idx].base;
 
-	return mem_info.avail[mc_idx].limit - mem_info.avail[mc_idx].base;
+	return 0;
 }
 
 static int cudbg_collect_mem_region(struct cudbg_init *pdbg_init,
@@ -1076,7 +1084,12 @@ static int cudbg_collect_mem_region(struct cudbg_init *pdbg_init,
 				    struct cudbg_error *cudbg_err,
 				    u8 mem_type)
 {
-	unsigned long size = cudbg_mem_region_size(pdbg_init, cudbg_err, mem_type);
+	unsigned long size = 0;
+	int rc;
+
+	rc = cudbg_mem_region_size(pdbg_init, cudbg_err, mem_type, &size);
+	if (rc)
+		return rc;
 
 	return cudbg_read_fw_mem(pdbg_init, dbg_buff, mem_type, size,
 				 cudbg_err);
-- 
2.20.1


From fbf706b119f7f8656f1ac319f496f49cac294838 Mon Sep 17 00:00:00 2001
From: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Date: Mon, 20 Apr 2020 15:26:54 +0530
Subject: [PATCH 02/30] cxgb4: fix large delays in PTP synchronization

[ Upstream commit bd019427bf3623ee3c7d2845cf921bbf4c14846c ]

Fetching PTP sync information from mailbox is slow and can take
up to 10 milliseconds. Reduce this unnecessary delay by directly
reading the information from the corresponding registers.

Fixes: 9c33e4208bce ("cxgb4: Add PTP Hardware Clock (PHC) support")
Signed-off-by: Manoj Malviya <manojmalviya@chelsio.com>
Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/chelsio/cxgb4/cxgb4_ptp.c    | 27 +++++--------------
 drivers/net/ethernet/chelsio/cxgb4/t4_regs.h  |  3 +++
 2 files changed, 9 insertions(+), 21 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c
index af1f40cbccc8..f5bc996ac77d 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c
@@ -311,32 +311,17 @@ static int cxgb4_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
  */
 static int cxgb4_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
 {
-	struct adapter *adapter = (struct adapter *)container_of(ptp,
-				   struct adapter, ptp_clock_info);
-	struct fw_ptp_cmd c;
+	struct adapter *adapter = container_of(ptp, struct adapter,
+					       ptp_clock_info);
 	u64 ns;
-	int err;
-
-	memset(&c, 0, sizeof(c));
-	c.op_to_portid = cpu_to_be32(FW_CMD_OP_V(FW_PTP_CMD) |
-				     FW_CMD_REQUEST_F |
-				     FW_CMD_READ_F |
-				     FW_PTP_CMD_PORTID_V(0));
-	c.retval_len16 = cpu_to_be32(FW_CMD_LEN16_V(sizeof(c) / 16));
-	c.u.ts.sc = FW_PTP_SC_GET_TIME;
 
-	err = t4_wr_mbox(adapter, adapter->mbox, &c, sizeof(c), &c);
-	if (err < 0) {
-		dev_err(adapter->pdev_dev,
-			"PTP: %s error %d\n", __func__, -err);
-		return err;
-	}
+	ns = t4_read_reg(adapter, T5_PORT_REG(0, MAC_PORT_PTP_SUM_LO_A));
+	ns |= (u64)t4_read_reg(adapter,
+			       T5_PORT_REG(0, MAC_PORT_PTP_SUM_HI_A)) << 32;
 
 	/* convert to timespec*/
-	ns = be64_to_cpu(c.u.ts.tm);
 	*ts = ns_to_timespec64(ns);
-
-	return err;
+	return 0;
 }
 
 /**
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
index a957a6e4d4c4..b0519c326692 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
@@ -1900,6 +1900,9 @@
 
 #define MAC_PORT_CFG2_A 0x818
 
+#define MAC_PORT_PTP_SUM_LO_A 0x990
+#define MAC_PORT_PTP_SUM_HI_A 0x994
+
 #define MPS_CMN_CTL_A	0x9000
 
 #define COUNTPAUSEMCRX_S    5
-- 
2.20.1


From e595f7c2a20bebf8c7a09d1b669471f39134b575 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 22 Apr 2020 15:40:20 -0600
Subject: [PATCH 03/30] ipv4: Update fib_select_default to handle nexthop
 objects

[ Upstream commit 7c74b0bec918c1e0ca0b4208038c156eacf8f13f ]

A user reported [0] hitting the WARN_ON in fib_info_nh:

    [ 8633.839816] ------------[ cut here ]------------
    [ 8633.839819] WARNING: CPU: 0 PID: 1719 at include/net/nexthop.h:251 fib_select_path+0x303/0x381
    ...
    [ 8633.839846] RIP: 0010:fib_select_path+0x303/0x381
    ...
    [ 8633.839848] RSP: 0018:ffffb04d407f7d00 EFLAGS: 00010286
    [ 8633.839850] RAX: 0000000000000000 RBX: ffff9460b9897ee8 RCX: 00000000000000fe
    [ 8633.839851] RDX: 0000000000000000 RSI: 00000000ffffffff RDI: 0000000000000000
    [ 8633.839852] RBP: ffff946076049850 R08: 0000000059263a83 R09: ffff9460840e4000
    [ 8633.839853] R10: 0000000000000014 R11: 0000000000000000 R12: ffffb04d407f7dc0
    [ 8633.839854] R13: ffffffffa4ce3240 R14: 0000000000000000 R15: ffff9460b7681f60
    [ 8633.839857] FS:  00007fcac2e02700(0000) GS:ffff9460bdc00000(0000) knlGS:0000000000000000
    [ 8633.839858] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
    [ 8633.839859] CR2: 00007f27beb77e28 CR3: 0000000077734000 CR4: 00000000000006f0
    [ 8633.839867] Call Trace:
    [ 8633.839871]  ip_route_output_key_hash_rcu+0x421/0x890
    [ 8633.839873]  ip_route_output_key_hash+0x5e/0x80
    [ 8633.839876]  ip_route_output_flow+0x1a/0x50
    [ 8633.839878]  __ip4_datagram_connect+0x154/0x310
    [ 8633.839880]  ip4_datagram_connect+0x28/0x40
    [ 8633.839882]  __sys_connect+0xd6/0x100
    ...

The WARN_ON is triggered in fib_select_default which is invoked when
there are multiple default routes. Update the function to use
fib_info_nhc and convert the nexthop checks to use fib_nh_common.

Add test case that covers the affected code path.

[0] https://github.com/FRRouting/frr/issues/6089

Fixes: 493ced1ac47c ("ipv4: Allow routes to use nexthop objects")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_semantics.c                    |  6 +++---
 tools/testing/selftests/net/fib_nexthops.sh | 23 +++++++++++++++++++++
 2 files changed, 26 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index a803cdd9400a..ee0f3b2823e0 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -2012,7 +2012,7 @@ static void fib_select_default(const struct flowi4 *flp, struct fib_result *res)
 
 	hlist_for_each_entry_rcu(fa, fa_head, fa_list) {
 		struct fib_info *next_fi = fa->fa_info;
-		struct fib_nh *nh;
+		struct fib_nh_common *nhc;
 
 		if (fa->fa_slen != slen)
 			continue;
@@ -2035,8 +2035,8 @@ static void fib_select_default(const struct flowi4 *flp, struct fib_result *res)
 		    fa->fa_type != RTN_UNICAST)
 			continue;
 
-		nh = fib_info_nh(next_fi, 0);
-		if (!nh->fib_nh_gw4 || nh->fib_nh_scope != RT_SCOPE_LINK)
+		nhc = fib_info_nhc(next_fi, 0);
+		if (!nhc->nhc_gw_family || nhc->nhc_scope != RT_SCOPE_LINK)
 			continue;
 
 		fib_alias_accessed(fa);
diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh
index 796670ebc65b..6560ed796ac4 100755
--- a/tools/testing/selftests/net/fib_nexthops.sh
+++ b/tools/testing/selftests/net/fib_nexthops.sh
@@ -749,6 +749,29 @@ ipv4_fcnal_runtime()
 	run_cmd "ip netns exec me ping -c1 -w1 172.16.101.1"
 	log_test $? 0 "Ping - multipath"
 
+	run_cmd "$IP ro delete 172.16.101.1/32 nhid 122"
+
+	#
+	# multiple default routes
+	# - tests fib_select_default
+	run_cmd "$IP nexthop add id 501 via 172.16.1.2 dev veth1"
+	run_cmd "$IP ro add default nhid 501"
+	run_cmd "$IP ro add default via 172.16.1.3 dev veth1 metric 20"
+	run_cmd "ip netns exec me ping -c1 -w1 172.16.101.1"
+	log_test $? 0 "Ping - multiple default routes, nh first"
+
+	# flip the order
+	run_cmd "$IP ro del default nhid 501"
+	run_cmd "$IP ro del default via 172.16.1.3 dev veth1 metric 20"
+	run_cmd "$IP ro add default via 172.16.1.2 dev veth1 metric 20"
+	run_cmd "$IP nexthop replace id 501 via 172.16.1.3 dev veth1"
+	run_cmd "$IP ro add default nhid 501 metric 20"
+	run_cmd "ip netns exec me ping -c1 -w1 172.16.101.1"
+	log_test $? 0 "Ping - multiple default routes, nh second"
+
+	run_cmd "$IP nexthop delete nhid 501"
+	run_cmd "$IP ro del default"
+
 	#
 	# IPv4 with blackhole nexthops
 	#
-- 
2.20.1


From 9bec93e9c6bf81ce48c811cdd99e656552ca060c Mon Sep 17 00:00:00 2001
From: John Haxby <john.haxby@oracle.com>
Date: Sat, 18 Apr 2020 16:30:49 +0100
Subject: [PATCH 04/30] ipv6: fix restrict IPV6_ADDRFORM operation

[ Upstream commit 82c9ae440857840c56e05d4fb1427ee032531346 ]

Commit b6f6118901d1 ("ipv6: restrict IPV6_ADDRFORM operation") fixed a
problem found by syzbot an unfortunate logic error meant that it
also broke IPV6_ADDRFORM.

Rearrange the checks so that the earlier test is just one of the series
of checks made before moving the socket from IPv6 to IPv4.

Fixes: b6f6118901d1 ("ipv6: restrict IPV6_ADDRFORM operation")
Signed-off-by: John Haxby <john.haxby@oracle.com>
Cc: stable@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ipv6_sockglue.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index debdaeba5d8c..18d05403d3b5 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -183,15 +183,14 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 					retv = -EBUSY;
 					break;
 				}
-			} else if (sk->sk_protocol == IPPROTO_TCP) {
-				if (sk->sk_prot != &tcpv6_prot) {
-					retv = -EBUSY;
-					break;
-				}
-				break;
-			} else {
+			}
+			if (sk->sk_protocol == IPPROTO_TCP &&
+			    sk->sk_prot != &tcpv6_prot) {
+				retv = -EBUSY;
 				break;
 			}
+			if (sk->sk_protocol != IPPROTO_TCP)
+				break;
 			if (sk->sk_state != TCP_ESTABLISHED) {
 				retv = -ENOTCONN;
 				break;
-- 
2.20.1


From e2c91e62214546330c93832e76f2af70e3b92f89 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Thu, 23 Apr 2020 13:40:47 +0000
Subject: [PATCH 05/30] macsec: avoid to set wrong mtu

[ Upstream commit 7f327080364abccf923fa5a5b24e038eb0ba1407 ]

When a macsec interface is created, the mtu is calculated with the lower
interface's mtu value.
If the mtu of lower interface is lower than the length, which is needed
by macsec interface, macsec's mtu value will be overflowed.
So, if the lower interface's mtu is too low, macsec interface's mtu
should be set to 0.

Test commands:
    ip link add dummy0 mtu 10 type dummy
    ip link add macsec0 link dummy0 type macsec
    ip link show macsec0

Before:
    11: macsec0@dummy0: <BROADCAST,MULTICAST,M-DOWN> mtu 4294967274
After:
    11: macsec0@dummy0: <BROADCAST,MULTICAST,M-DOWN> mtu 0

Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macsec.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 9b4ae5c36da6..35aa7b0a2aeb 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -3658,11 +3658,11 @@ static int macsec_newlink(struct net *net, struct net_device *dev,
 			  struct netlink_ext_ack *extack)
 {
 	struct macsec_dev *macsec = macsec_priv(dev);
+	rx_handler_func_t *rx_handler;
+	u8 icv_len = DEFAULT_ICV_LEN;
 	struct net_device *real_dev;
-	int err;
+	int err, mtu;
 	sci_t sci;
-	u8 icv_len = DEFAULT_ICV_LEN;
-	rx_handler_func_t *rx_handler;
 
 	if (!tb[IFLA_LINK])
 		return -EINVAL;
@@ -3681,7 +3681,11 @@ static int macsec_newlink(struct net *net, struct net_device *dev,
 
 	if (data && data[IFLA_MACSEC_ICV_LEN])
 		icv_len = nla_get_u8(data[IFLA_MACSEC_ICV_LEN]);
-	dev->mtu = real_dev->mtu - icv_len - macsec_extra_len(true);
+	mtu = real_dev->mtu - icv_len - macsec_extra_len(true);
+	if (mtu < 0)
+		dev->mtu = 0;
+	else
+		dev->mtu = mtu;
 
 	rx_handler = rtnl_dereference(real_dev->rx_handler);
 	if (rx_handler && rx_handler != macsec_handle_frame)
-- 
2.20.1


From 27e2e8c3d83dd87ffade3118335108556e18b663 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Mon, 20 Apr 2020 13:29:40 +0000
Subject: [PATCH 06/30] macvlan: fix null dereference in macvlan_device_event()

[ Upstream commit 4dee15b4fd0d61ec6bbd179238191e959d34cf7a ]

In the macvlan_device_event(), the list_first_entry_or_null() is used.
This function could return null pointer if there is no node.
But, the macvlan module doesn't check the null pointer.
So, null-ptr-deref would occur.

      bond0
        |
   +----+-----+
   |          |
macvlan0   macvlan1
   |          |
 dummy0     dummy1

The problem scenario.
If dummy1 is removed,
1. ->dellink() of dummy1 is called.
2. NETDEV_UNREGISTER of dummy1 notification is sent to macvlan module.
3. ->dellink() of macvlan1 is called.
4. NETDEV_UNREGISTER of macvlan1 notification is sent to bond module.
5. __bond_release_one() is called and it internally calls
   dev_set_mac_address().
6. dev_set_mac_address() calls the ->ndo_set_mac_address() of macvlan1,
   which is macvlan_set_mac_address().
7. macvlan_set_mac_address() calls the dev_set_mac_address() with dummy1.
8. NETDEV_CHANGEADDR of dummy1 is sent to macvlan module.
9. In the macvlan_device_event(), it calls list_first_entry_or_null().
At this point, dummy1 and macvlan1 were removed.
So, list_first_entry_or_null() will return NULL.

Test commands:
    ip netns add nst
    ip netns exec nst ip link add bond0 type bond
    for i in {0..10}
    do
        ip netns exec nst ip link add dummy$i type dummy
	ip netns exec nst ip link add macvlan$i link dummy$i \
		type macvlan mode passthru
	ip netns exec nst ip link set macvlan$i master bond0
    done
    ip netns del nst

Splat looks like:
[   40.585687][  T146] general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] SMP DEI
[   40.587249][  T146] KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007]
[   40.588342][  T146] CPU: 1 PID: 146 Comm: kworker/u8:2 Not tainted 5.7.0-rc1+ #532
[   40.589299][  T146] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[   40.590469][  T146] Workqueue: netns cleanup_net
[   40.591045][  T146] RIP: 0010:macvlan_device_event+0x4e2/0x900 [macvlan]
[   40.591905][  T146] Code: 00 00 00 00 00 fc ff df 80 3c 06 00 0f 85 45 02 00 00 48 89 da 48 b8 00 00 00 00 00 fc ff d2
[   40.594126][  T146] RSP: 0018:ffff88806116f4a0 EFLAGS: 00010246
[   40.594783][  T146] RAX: dffffc0000000000 RBX: 0000000000000000 RCX: 0000000000000000
[   40.595653][  T146] RDX: 0000000000000000 RSI: ffff88806547ddd8 RDI: ffff8880540f1360
[   40.596495][  T146] RBP: ffff88804011a808 R08: fffffbfff4fb8421 R09: fffffbfff4fb8421
[   40.597377][  T146] R10: ffffffffa7dc2107 R11: 0000000000000000 R12: 0000000000000008
[   40.598186][  T146] R13: ffff88804011a000 R14: ffff8880540f1000 R15: 1ffff1100c22de9a
[   40.599012][  T146] FS:  0000000000000000(0000) GS:ffff888067800000(0000) knlGS:0000000000000000
[   40.600004][  T146] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   40.600665][  T146] CR2: 00005572d3a807b8 CR3: 000000005fcf4003 CR4: 00000000000606e0
[   40.601485][  T146] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[   40.602461][  T146] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[   40.603443][  T146] Call Trace:
[   40.603871][  T146]  ? nf_tables_dump_setelem+0xa0/0xa0 [nf_tables]
[   40.604587][  T146]  ? macvlan_uninit+0x100/0x100 [macvlan]
[   40.605212][  T146]  ? __module_text_address+0x13/0x140
[   40.605842][  T146]  notifier_call_chain+0x90/0x160
[   40.606477][  T146]  dev_set_mac_address+0x28e/0x3f0
[   40.607117][  T146]  ? netdev_notify_peers+0xc0/0xc0
[   40.607762][  T146]  ? __module_text_address+0x13/0x140
[   40.608440][  T146]  ? notifier_call_chain+0x90/0x160
[   40.609097][  T146]  ? dev_set_mac_address+0x1f0/0x3f0
[   40.609758][  T146]  dev_set_mac_address+0x1f0/0x3f0
[   40.610402][  T146]  ? __local_bh_enable_ip+0xe9/0x1b0
[   40.611071][  T146]  ? bond_hw_addr_flush+0x77/0x100 [bonding]
[   40.611823][  T146]  ? netdev_notify_peers+0xc0/0xc0
[   40.612461][  T146]  ? bond_hw_addr_flush+0x77/0x100 [bonding]
[   40.613213][  T146]  ? bond_hw_addr_flush+0x77/0x100 [bonding]
[   40.613963][  T146]  ? __local_bh_enable_ip+0xe9/0x1b0
[   40.614631][  T146]  ? bond_time_in_interval.isra.31+0x90/0x90 [bonding]
[   40.615484][  T146]  ? __bond_release_one+0x9f0/0x12c0 [bonding]
[   40.616230][  T146]  __bond_release_one+0x9f0/0x12c0 [bonding]
[   40.616949][  T146]  ? bond_enslave+0x47c0/0x47c0 [bonding]
[   40.617642][  T146]  ? lock_downgrade+0x730/0x730
[   40.618218][  T146]  ? check_flags.part.42+0x450/0x450
[   40.618850][  T146]  ? __mutex_unlock_slowpath+0xd0/0x670
[   40.619519][  T146]  ? trace_hardirqs_on+0x30/0x180
[   40.620117][  T146]  ? wait_for_completion+0x250/0x250
[   40.620754][  T146]  bond_netdev_event+0x822/0x970 [bonding]
[   40.621460][  T146]  ? __module_text_address+0x13/0x140
[   40.622097][  T146]  notifier_call_chain+0x90/0x160
[   40.622806][  T146]  rollback_registered_many+0x660/0xcf0
[   40.623522][  T146]  ? netif_set_real_num_tx_queues+0x780/0x780
[   40.624290][  T146]  ? notifier_call_chain+0x90/0x160
[   40.624957][  T146]  ? netdev_upper_dev_unlink+0x114/0x180
[   40.625686][  T146]  ? __netdev_adjacent_dev_unlink_neighbour+0x30/0x30
[   40.626421][  T146]  ? mutex_is_locked+0x13/0x50
[   40.627016][  T146]  ? unregister_netdevice_queue+0xf2/0x240
[   40.627663][  T146]  unregister_netdevice_many.part.134+0x13/0x1b0
[   40.628362][  T146]  default_device_exit_batch+0x2d9/0x390
[   40.628987][  T146]  ? unregister_netdevice_many+0x40/0x40
[   40.629615][  T146]  ? dev_change_net_namespace+0xcb0/0xcb0
[   40.630279][  T146]  ? prepare_to_wait_exclusive+0x2e0/0x2e0
[   40.630943][  T146]  ? ops_exit_list.isra.9+0x97/0x140
[   40.631554][  T146]  cleanup_net+0x441/0x890
[ ... ]

Fixes: e289fd28176b ("macvlan: fix the problem when mac address changes for passthru mode")
Reported-by: syzbot+5035b1f9dc7ea4558d5a@syzkaller.appspotmail.com
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macvlan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index e7289d67268f..0482adc9916b 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -1704,7 +1704,7 @@ static int macvlan_device_event(struct notifier_block *unused,
 						struct macvlan_dev,
 						list);
 
-		if (macvlan_sync_address(vlan->dev, dev->dev_addr))
+		if (vlan && macvlan_sync_address(vlan->dev, dev->dev_addr))
 			return NOTIFY_BAD;
 
 		break;
-- 
2.20.1


From 663544cc7a498c4313317d7e425d9c49897b81a5 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 22 Apr 2020 12:36:41 +0300
Subject: [PATCH 07/30] mlxsw: Fix some IS_ERR() vs NULL bugs

[ Upstream commit c391eb8366ae052d571bb2841f1ccb4d39f3ceb8 ]

The mlxsw_sp_acl_rulei_create() function is supposed to return an error
pointer from mlxsw_afa_block_create().  The problem is that these
functions both return NULL instead of error pointers.  Half the callers
expect NULL and half expect error pointers so it could lead to a NULL
dereference on failure.

This patch changes both of them to return error pointers and changes all
the callers which checked for NULL to check for IS_ERR() instead.

Fixes: 4cda7d8d7098 ("mlxsw: core: Introduce flexible actions support")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c | 4 ++--
 drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c    | 4 ++--
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c          | 2 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c      | 4 ++--
 4 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
index c51b2adfc1e1..2cbfa5cfefab 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
@@ -316,7 +316,7 @@ struct mlxsw_afa_block *mlxsw_afa_block_create(struct mlxsw_afa *mlxsw_afa)
 
 	block = kzalloc(sizeof(*block), GFP_KERNEL);
 	if (!block)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	INIT_LIST_HEAD(&block->resource_list);
 	block->afa = mlxsw_afa;
 
@@ -344,7 +344,7 @@ struct mlxsw_afa_block *mlxsw_afa_block_create(struct mlxsw_afa *mlxsw_afa)
 	mlxsw_afa_set_destroy(block->first_set);
 err_first_set_create:
 	kfree(block);
-	return NULL;
+	return ERR_PTR(-ENOMEM);
 }
 EXPORT_SYMBOL(mlxsw_afa_block_create);
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
index 6c66a0f1b79e..ad69913f19c1 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
@@ -88,8 +88,8 @@ static int mlxsw_sp2_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv,
 	 * to be written using PEFA register to all indexes for all regions.
 	 */
 	afa_block = mlxsw_afa_block_create(mlxsw_sp->afa);
-	if (!afa_block) {
-		err = -ENOMEM;
+	if (IS_ERR(afa_block)) {
+		err = PTR_ERR(afa_block);
 		goto err_afa_block;
 	}
 	err = mlxsw_afa_block_continue(afa_block);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index 3d3cca596116..d77cdcb5c642 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -444,7 +444,7 @@ mlxsw_sp_acl_rulei_create(struct mlxsw_sp_acl *acl,
 
 	rulei = kzalloc(sizeof(*rulei), GFP_KERNEL);
 	if (!rulei)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	if (afa_block) {
 		rulei->act_block = afa_block;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
index 346f4a5fe053..221aa6a474eb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
@@ -199,8 +199,8 @@ mlxsw_sp_mr_tcam_afa_block_create(struct mlxsw_sp *mlxsw_sp,
 	int err;
 
 	afa_block = mlxsw_afa_block_create(mlxsw_sp->afa);
-	if (!afa_block)
-		return ERR_PTR(-ENOMEM);
+	if (IS_ERR(afa_block))
+		return afa_block;
 
 	err = mlxsw_afa_block_append_allocated_counter(afa_block,
 						       counter_index);
-- 
2.20.1


From abb125a117c309944806eba8f092a7a7441ee8eb Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Thu, 23 Apr 2020 15:44:17 -0700
Subject: [PATCH 08/30] net: bcmgenet: correct per TX/RX ring statistics

[ Upstream commit a6d0b83f25073bdf08b8547aeff961a62c6ab229 ]

The change to track net_device_stats per ring to better support SMP
missed updating the rx_dropped member.

The ndo_get_stats method is also needed to combine the results for
ethtool statistics (-S) before filling in the ethtool structure.

Fixes: 37a30b435b92 ("net: bcmgenet: Track per TX/RX rings statistics")
Signed-off-by: Doug Berger <opendmb@gmail.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 1d678bee2cc9..b7c0c20e1325 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -938,6 +938,8 @@ static void bcmgenet_get_ethtool_stats(struct net_device *dev,
 	if (netif_running(dev))
 		bcmgenet_update_mib_counters(priv);
 
+	dev->netdev_ops->ndo_get_stats(dev);
+
 	for (i = 0; i < BCMGENET_STATS_LEN; i++) {
 		const struct bcmgenet_stats *s;
 		char *p;
@@ -3142,6 +3144,7 @@ static struct net_device_stats *bcmgenet_get_stats(struct net_device *dev)
 	dev->stats.rx_packets = rx_packets;
 	dev->stats.rx_errors = rx_errors;
 	dev->stats.rx_missed_errors = rx_errors;
+	dev->stats.rx_dropped = rx_dropped;
 	return &dev->stats;
 }
 
-- 
2.20.1


From b24e21f5f7bf973758c810a36c317bb48267f568 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 15 Apr 2020 09:46:52 -0700
Subject: [PATCH 09/30] net/mlx4_en: avoid indirect call in TX completion

[ Upstream commit 310660a14b74c380b0ef5c12b66933d6a3d1b59f ]

Commit 9ecc2d86171a ("net/mlx4_en: add xdp forwarding and data write support")
brought another indirect call in fast path.

Use INDIRECT_CALL_2() helper to avoid the cost of the indirect call
when/if CONFIG_RETPOLINE=y

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Tariq Toukan <tariqt@mellanox.com>
Cc: Willem de Bruijn <willemb@google.com>
Reviewed-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_tx.c | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 4d5ca302c067..a30edb436f4a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -43,6 +43,7 @@
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/moduleparam.h>
+#include <linux/indirect_call_wrapper.h>
 
 #include "mlx4_en.h"
 
@@ -261,6 +262,10 @@ static void mlx4_en_stamp_wqe(struct mlx4_en_priv *priv,
 	}
 }
 
+INDIRECT_CALLABLE_DECLARE(u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
+						   struct mlx4_en_tx_ring *ring,
+						   int index, u64 timestamp,
+						   int napi_mode));
 
 u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
 			 struct mlx4_en_tx_ring *ring,
@@ -329,6 +334,11 @@ u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
 	return tx_info->nr_txbb;
 }
 
+INDIRECT_CALLABLE_DECLARE(u32 mlx4_en_recycle_tx_desc(struct mlx4_en_priv *priv,
+						      struct mlx4_en_tx_ring *ring,
+						      int index, u64 timestamp,
+						      int napi_mode));
+
 u32 mlx4_en_recycle_tx_desc(struct mlx4_en_priv *priv,
 			    struct mlx4_en_tx_ring *ring,
 			    int index, u64 timestamp,
@@ -449,7 +459,9 @@ bool mlx4_en_process_tx_cq(struct net_device *dev,
 				timestamp = mlx4_en_get_cqe_ts(cqe);
 
 			/* free next descriptor */
-			last_nr_txbb = ring->free_tx_desc(
+			last_nr_txbb = INDIRECT_CALL_2(ring->free_tx_desc,
+						       mlx4_en_free_tx_desc,
+						       mlx4_en_recycle_tx_desc,
 					priv, ring, ring_index,
 					timestamp, napi_budget);
 
-- 
2.20.1


From 8824768eda29722fe70e649750ddbfd8beb7303f Mon Sep 17 00:00:00 2001
From: Xiyu Yang <xiyuyang19@fudan.edu.cn>
Date: Wed, 15 Apr 2020 16:36:19 +0800
Subject: [PATCH 10/30] net: netrom: Fix potential nr_neigh refcnt leak in
 nr_add_node

[ Upstream commit d03f228470a8c0a22b774d1f8d47071e0de4f6dd ]

nr_add_node() invokes nr_neigh_get_dev(), which returns a local
reference of the nr_neigh object to "nr_neigh" with increased refcnt.

When nr_add_node() returns, "nr_neigh" becomes invalid, so the refcount
should be decreased to keep refcount balanced.

The issue happens in one normal path of nr_add_node(), which forgets to
decrease the refcnt increased by nr_neigh_get_dev() and causes a refcnt
leak. It should decrease the refcnt before the function returns like
other normal paths do.

Fix this issue by calling nr_neigh_put() before the nr_add_node()
returns.

Signed-off-by: Xiyu Yang <xiyuyang19@fudan.edu.cn>
Signed-off-by: Xin Tan <tanxin.ctf@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netrom/nr_route.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c
index d41335bad1f8..89cd9de21594 100644
--- a/net/netrom/nr_route.c
+++ b/net/netrom/nr_route.c
@@ -208,6 +208,7 @@ static int __must_check nr_add_node(ax25_address *nr, const char *mnemonic,
 		/* refcount initialized at 1 */
 		spin_unlock_bh(&nr_node_list_lock);
 
+		nr_neigh_put(nr_neigh);
 		return 0;
 	}
 	nr_node_lock(nr_node);
-- 
2.20.1


From 4b4799870d04807ab909f98bcbea2750224779d3 Mon Sep 17 00:00:00 2001
From: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Date: Fri, 17 Apr 2020 02:57:31 +0800
Subject: [PATCH 11/30] net: openvswitch: ovs_ct_exit to be done under ovs_lock

[ Upstream commit 27de77cec985233bdf6546437b9761853265c505 ]

syzbot wrote:
| =============================
| WARNING: suspicious RCU usage
| 5.7.0-rc1+ #45 Not tainted
| -----------------------------
| net/openvswitch/conntrack.c:1898 RCU-list traversed in non-reader section!!
|
| other info that might help us debug this:
| rcu_scheduler_active = 2, debug_locks = 1
| ...
|
| stack backtrace:
| Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-0-ga698c8995f-prebuilt.qemu.org 04/01/2014
| Workqueue: netns cleanup_net
| Call Trace:
| ...
| ovs_ct_exit
| ovs_exit_net
| ops_exit_list.isra.7
| cleanup_net
| process_one_work
| worker_thread

To avoid that warning, invoke the ovs_ct_exit under ovs_lock and add
lockdep_ovsl_is_held as optional lockdep expression.

Link: https://lore.kernel.org/lkml/000000000000e642a905a0cbee6e@google.com
Fixes: 11efd5cb04a1 ("openvswitch: Support conntrack zone limit")
Cc: Pravin B Shelar <pshelar@ovn.org>
Cc: Yi-Hung Wei <yihung.wei@gmail.com>
Reported-by: syzbot+7ef50afd3a211f879112@syzkaller.appspotmail.com
Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/conntrack.c | 3 ++-
 net/openvswitch/datapath.c  | 4 +++-
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index e726159cfcfa..4340f25fe390 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -1895,7 +1895,8 @@ static void ovs_ct_limit_exit(struct net *net, struct ovs_net *ovs_net)
 		struct hlist_head *head = &info->limits[i];
 		struct ovs_ct_limit *ct_limit;
 
-		hlist_for_each_entry_rcu(ct_limit, head, hlist_node)
+		hlist_for_each_entry_rcu(ct_limit, head, hlist_node,
+					 lockdep_ovsl_is_held())
 			kfree_rcu(ct_limit, rcu);
 	}
 	kfree(ovs_net->ct_limit_info->limits);
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 07a7dd185995..c39f3c6c061d 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -2466,8 +2466,10 @@ static void __net_exit ovs_exit_net(struct net *dnet)
 	struct net *net;
 	LIST_HEAD(head);
 
-	ovs_ct_exit(dnet);
 	ovs_lock();
+
+	ovs_ct_exit(dnet);
+
 	list_for_each_entry_safe(dp, dp_next, &ovs_net->dps, list_node)
 		__dp_destroy(dp);
 
-- 
2.20.1


From e2b65e01b7bebf5a208d70a75e49848199e31a06 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sat, 18 Apr 2020 19:14:57 +0100
Subject: [PATCH 12/30] net: stmmac: dwmac-meson8b: Add missing boundary to
 RGMII TX clock array

[ Upstream commit f0212a5ebfa6cd789ab47666b9cc169e6e688732 ]

Running with KASAN on a VIM3L systems leads to the following splat
when probing the Ethernet device:

==================================================================
BUG: KASAN: global-out-of-bounds in _get_maxdiv+0x74/0xd8
Read of size 4 at addr ffffa000090615f4 by task systemd-udevd/139
CPU: 1 PID: 139 Comm: systemd-udevd Tainted: G            E     5.7.0-rc1-00101-g8624b7577b9c #781
Hardware name: amlogic w400/w400, BIOS 2020.01-rc5 03/12/2020
Call trace:
 dump_backtrace+0x0/0x2a0
 show_stack+0x20/0x30
 dump_stack+0xec/0x148
 print_address_description.isra.12+0x70/0x35c
 __kasan_report+0xfc/0x1d4
 kasan_report+0x4c/0x68
 __asan_load4+0x9c/0xd8
 _get_maxdiv+0x74/0xd8
 clk_divider_bestdiv+0x74/0x5e0
 clk_divider_round_rate+0x80/0x1a8
 clk_core_determine_round_nolock.part.9+0x9c/0xd0
 clk_core_round_rate_nolock+0xf0/0x108
 clk_hw_round_rate+0xac/0xf0
 clk_factor_round_rate+0xb8/0xd0
 clk_core_determine_round_nolock.part.9+0x9c/0xd0
 clk_core_round_rate_nolock+0xf0/0x108
 clk_core_round_rate_nolock+0xbc/0x108
 clk_core_set_rate_nolock+0xc4/0x2e8
 clk_set_rate+0x58/0xe0
 meson8b_dwmac_probe+0x588/0x72c [dwmac_meson8b]
 platform_drv_probe+0x78/0xd8
 really_probe+0x158/0x610
 driver_probe_device+0x140/0x1b0
 device_driver_attach+0xa4/0xb0
 __driver_attach+0xcc/0x1c8
 bus_for_each_dev+0xf4/0x168
 driver_attach+0x3c/0x50
 bus_add_driver+0x238/0x2e8
 driver_register+0xc8/0x1e8
 __platform_driver_register+0x88/0x98
 meson8b_dwmac_driver_init+0x28/0x1000 [dwmac_meson8b]
 do_one_initcall+0xa8/0x328
 do_init_module+0xe8/0x368
 load_module+0x3300/0x36b0
 __do_sys_finit_module+0x120/0x1a8
 __arm64_sys_finit_module+0x4c/0x60
 el0_svc_common.constprop.2+0xe4/0x268
 do_el0_svc+0x98/0xa8
 el0_svc+0x24/0x68
 el0_sync_handler+0x12c/0x318
 el0_sync+0x158/0x180

The buggy address belongs to the variable:
 div_table.63646+0x34/0xfffffffffffffa40 [dwmac_meson8b]

Memory state around the buggy address:
 ffffa00009061480: fa fa fa fa 00 00 00 01 fa fa fa fa 00 00 00 00
 ffffa00009061500: 05 fa fa fa fa fa fa fa 00 04 fa fa fa fa fa fa
>ffffa00009061580: 00 03 fa fa fa fa fa fa 00 00 00 00 00 00 fa fa
                                                             ^
 ffffa00009061600: fa fa fa fa 00 01 fa fa fa fa fa fa 01 fa fa fa
 ffffa00009061680: fa fa fa fa 00 01 fa fa fa fa fa fa 04 fa fa fa
==================================================================

Digging into this indeed shows that the clock divider array is
lacking a final fence, and that the clock subsystems goes in the
weeds. Oh well.

Let's add the empty structure that indicates the end of the array.

Fixes: bd6f48546b9c ("net: stmmac: dwmac-meson8b: Fix the RGMII TX delay on Meson8b/8m2 SoCs")
Signed-off-by: Marc Zyngier <maz@kernel.org>
Cc: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Reviewed-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
index 0e2fa14f1423..a3934ca6a043 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
@@ -119,6 +119,7 @@ static int meson8b_init_rgmii_tx_clk(struct meson8b_dwmac *dwmac)
 		{ .div = 5, .val = 5, },
 		{ .div = 6, .val = 6, },
 		{ .div = 7, .val = 7, },
+		{ /* end of array */ }
 	};
 
 	clk_configs = devm_kzalloc(dev, sizeof(*clk_configs), GFP_KERNEL);
-- 
2.20.1


From 0804f65abceed32744c72cf191cf10a8984c2376 Mon Sep 17 00:00:00 2001
From: Xiyu Yang <xiyuyang19@fudan.edu.cn>
Date: Thu, 23 Apr 2020 13:13:03 +0800
Subject: [PATCH 13/30] net/x25: Fix x25_neigh refcnt leak when receiving frame

[ Upstream commit f35d12971b4d814cdb2f659d76b42f0c545270b6 ]

x25_lapb_receive_frame() invokes x25_get_neigh(), which returns a
reference of the specified x25_neigh object to "nb" with increased
refcnt.

When x25_lapb_receive_frame() returns, local variable "nb" becomes
invalid, so the refcount should be decreased to keep refcount balanced.

The reference counting issue happens in one path of
x25_lapb_receive_frame(). When pskb_may_pull() returns false, the
function forgets to decrease the refcnt increased by x25_get_neigh(),
causing a refcnt leak.

Fix this issue by calling x25_neigh_put() when pskb_may_pull() returns
false.

Fixes: cb101ed2c3c7 ("x25: Handle undersized/fragmented skbs")
Signed-off-by: Xiyu Yang <xiyuyang19@fudan.edu.cn>
Signed-off-by: Xin Tan <tanxin.ctf@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/x25/x25_dev.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/x25/x25_dev.c b/net/x25/x25_dev.c
index 00e782335cb0..25bf72ee6cad 100644
--- a/net/x25/x25_dev.c
+++ b/net/x25/x25_dev.c
@@ -115,8 +115,10 @@ int x25_lapb_receive_frame(struct sk_buff *skb, struct net_device *dev,
 		goto drop;
 	}
 
-	if (!pskb_may_pull(skb, 1))
+	if (!pskb_may_pull(skb, 1)) {
+		x25_neigh_put(nb);
 		return 0;
+	}
 
 	switch (skb->data[0]) {
 
-- 
2.20.1


From 8c8b47354fd031fd58cd8899ac845da8179be4c8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 21 Apr 2020 10:00:28 -0700
Subject: [PATCH 14/30] sched: etf: do not assume all sockets are full blown

[ Upstream commit a1211bf9a7774706722ba3b18c6157d980319f79 ]

skb->sk does not always point to a full blown socket,
we need to use sk_fullsock() before accessing fields which
only make sense on full socket.

BUG: KASAN: use-after-free in report_sock_error+0x286/0x300 net/sched/sch_etf.c:141
Read of size 1 at addr ffff88805eb9b245 by task syz-executor.5/9630

CPU: 1 PID: 9630 Comm: syz-executor.5 Not tainted 5.7.0-rc2-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x188/0x20d lib/dump_stack.c:118
 print_address_description.constprop.0.cold+0xd3/0x315 mm/kasan/report.c:382
 __kasan_report.cold+0x35/0x4d mm/kasan/report.c:511
 kasan_report+0x33/0x50 mm/kasan/common.c:625
 report_sock_error+0x286/0x300 net/sched/sch_etf.c:141
 etf_enqueue_timesortedlist+0x389/0x740 net/sched/sch_etf.c:170
 __dev_xmit_skb net/core/dev.c:3710 [inline]
 __dev_queue_xmit+0x154a/0x30a0 net/core/dev.c:4021
 neigh_hh_output include/net/neighbour.h:499 [inline]
 neigh_output include/net/neighbour.h:508 [inline]
 ip6_finish_output2+0xfb5/0x25b0 net/ipv6/ip6_output.c:117
 __ip6_finish_output+0x442/0xab0 net/ipv6/ip6_output.c:143
 ip6_finish_output+0x34/0x1f0 net/ipv6/ip6_output.c:153
 NF_HOOK_COND include/linux/netfilter.h:296 [inline]
 ip6_output+0x239/0x810 net/ipv6/ip6_output.c:176
 dst_output include/net/dst.h:435 [inline]
 NF_HOOK include/linux/netfilter.h:307 [inline]
 NF_HOOK include/linux/netfilter.h:301 [inline]
 ip6_xmit+0xe1a/0x2090 net/ipv6/ip6_output.c:280
 tcp_v6_send_synack+0x4e7/0x960 net/ipv6/tcp_ipv6.c:521
 tcp_rtx_synack+0x10d/0x1a0 net/ipv4/tcp_output.c:3916
 inet_rtx_syn_ack net/ipv4/inet_connection_sock.c:669 [inline]
 reqsk_timer_handler+0x4c2/0xb40 net/ipv4/inet_connection_sock.c:763
 call_timer_fn+0x1ac/0x780 kernel/time/timer.c:1405
 expire_timers kernel/time/timer.c:1450 [inline]
 __run_timers kernel/time/timer.c:1774 [inline]
 __run_timers kernel/time/timer.c:1741 [inline]
 run_timer_softirq+0x623/0x1600 kernel/time/timer.c:1787
 __do_softirq+0x26c/0x9f7 kernel/softirq.c:292
 invoke_softirq kernel/softirq.c:373 [inline]
 irq_exit+0x192/0x1d0 kernel/softirq.c:413
 exiting_irq arch/x86/include/asm/apic.h:546 [inline]
 smp_apic_timer_interrupt+0x19e/0x600 arch/x86/kernel/apic/apic.c:1140
 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:829
 </IRQ>
RIP: 0010:des_encrypt+0x157/0x9c0 lib/crypto/des.c:792
Code: 85 22 06 00 00 41 31 dc 41 8b 4d 04 44 89 e2 41 83 e4 3f 4a 8d 3c a5 60 72 72 88 81 e2 3f 3f 3f 3f 48 89 f8 48 c1 e8 03 31 d9 <0f> b6 34 28 48 89 f8 c1 c9 04 83 e0 07 83 c0 03 40 38 f0 7c 09 40
RSP: 0018:ffffc90003b5f6c0 EFLAGS: 00000282 ORIG_RAX: ffffffffffffff13
RAX: 1ffffffff10e4e55 RBX: 00000000d2f846d0 RCX: 00000000d2f846d0
RDX: 0000000012380612 RSI: ffffffff839863ca RDI: ffffffff887272a8
RBP: dffffc0000000000 R08: ffff888091d0a380 R09: 0000000000800081
R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000012
R13: ffff8880a8ae8078 R14: 00000000c545c93e R15: 0000000000000006
 cipher_crypt_one crypto/cipher.c:75 [inline]
 crypto_cipher_encrypt_one+0x124/0x210 crypto/cipher.c:82
 crypto_cbcmac_digest_update+0x1b5/0x250 crypto/ccm.c:830
 crypto_shash_update+0xc4/0x120 crypto/shash.c:119
 shash_ahash_update+0xa3/0x110 crypto/shash.c:246
 crypto_ahash_update include/crypto/hash.h:547 [inline]
 hash_sendmsg+0x518/0xad0 crypto/algif_hash.c:102
 sock_sendmsg_nosec net/socket.c:652 [inline]
 sock_sendmsg+0xcf/0x120 net/socket.c:672
 ____sys_sendmsg+0x308/0x7e0 net/socket.c:2362
 ___sys_sendmsg+0x100/0x170 net/socket.c:2416
 __sys_sendmmsg+0x195/0x480 net/socket.c:2506
 __do_sys_sendmmsg net/socket.c:2535 [inline]
 __se_sys_sendmmsg net/socket.c:2532 [inline]
 __x64_sys_sendmmsg+0x99/0x100 net/socket.c:2532
 do_syscall_64+0xf6/0x7d0 arch/x86/entry/common.c:295
 entry_SYSCALL_64_after_hwframe+0x49/0xb3
RIP: 0033:0x45c829
Code: 0d b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 db b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f6d9528ec78 EFLAGS: 00000246 ORIG_RAX: 0000000000000133
RAX: ffffffffffffffda RBX: 00000000004fc080 RCX: 000000000045c829
RDX: 0000000000000001 RSI: 0000000020002640 RDI: 0000000000000004
RBP: 000000000078bf00 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff
R13: 00000000000008d7 R14: 00000000004cb7aa R15: 00007f6d9528f6d4

Fixes: 4b15c7075352 ("net/sched: Make etf report drops on error_queue")
Fixes: 25db26a91364 ("net/sched: Introduce the ETF Qdisc")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Reviewed-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_etf.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c
index b1da5589a0c6..c48f91075b5c 100644
--- a/net/sched/sch_etf.c
+++ b/net/sched/sch_etf.c
@@ -82,7 +82,7 @@ static bool is_packet_valid(struct Qdisc *sch, struct sk_buff *nskb)
 	if (q->skip_sock_check)
 		goto skip;
 
-	if (!sk)
+	if (!sk || !sk_fullsock(sk))
 		return false;
 
 	if (!sock_flag(sk, SOCK_TXTIME))
@@ -137,8 +137,9 @@ static void report_sock_error(struct sk_buff *skb, u32 err, u8 code)
 	struct sock_exterr_skb *serr;
 	struct sk_buff *clone;
 	ktime_t txtime = skb->tstamp;
+	struct sock *sk = skb->sk;
 
-	if (!skb->sk || !(skb->sk->sk_txtime_report_errors))
+	if (!sk || !sk_fullsock(sk) || !(sk->sk_txtime_report_errors))
 		return;
 
 	clone = skb_clone(skb, GFP_ATOMIC);
@@ -154,7 +155,7 @@ static void report_sock_error(struct sk_buff *skb, u32 err, u8 code)
 	serr->ee.ee_data = (txtime >> 32); /* high part of tstamp */
 	serr->ee.ee_info = txtime; /* low part of tstamp */
 
-	if (sock_queue_err_skb(skb->sk, clone))
+	if (sock_queue_err_skb(sk, clone))
 		kfree_skb(clone);
 }
 
-- 
2.20.1


From b9dff0baa2808dd0df596cffbd0e9876bc069350 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 21 Apr 2020 08:47:24 -0600
Subject: [PATCH 15/30] selftests: Fix suppress test in fib_tests.sh

[ Upstream commit 2c1dd4c110627c2a4f006643f074119205cfcff4 ]

fib_tests is spewing errors:
    ...
    Cannot open network namespace "ns1": No such file or directory
    Cannot open network namespace "ns1": No such file or directory
    Cannot open network namespace "ns1": No such file or directory
    Cannot open network namespace "ns1": No such file or directory
    ping: connect: Network is unreachable
    Cannot open network namespace "ns1": No such file or directory
    Cannot open network namespace "ns1": No such file or directory
    ...

Each test entry in fib_tests is supposed to do its own setup and
cleanup. Right now the $IP commands in fib_suppress_test are
failing because there is no ns1. Add the setup/cleanup and logging
expected for each test.

Fixes: ca7a03c41753 ("ipv6: do not free rt if FIB_LOOKUP_NOREF is set on suppress rule")
Signed-off-by: David Ahern <dsahern@gmail.com>
Cc: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/fib_tests.sh | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index b7616704b55e..84205c3a55eb 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -618,16 +618,22 @@ fib_nexthop_test()
 
 fib_suppress_test()
 {
+	echo
+	echo "FIB rule with suppress_prefixlength"
+	setup
+
 	$IP link add dummy1 type dummy
 	$IP link set dummy1 up
 	$IP -6 route add default dev dummy1
 	$IP -6 rule add table main suppress_prefixlength 0
-	ping -f -c 1000 -W 1 1234::1 || true
+	ping -f -c 1000 -W 1 1234::1 >/dev/null 2>&1
 	$IP -6 rule del table main suppress_prefixlength 0
 	$IP link del dummy1
 
 	# If we got here without crashing, we're good.
-	return 0
+	log_test 0 0 "FIB rule suppress test"
+
+	cleanup
 }
 
 ################################################################################
-- 
2.20.1


From 2eb0cba613f75e4a405100c2dce94098d0c72237 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 17 Apr 2020 07:10:23 -0700
Subject: [PATCH 16/30] tcp: cache line align MAX_TCP_HEADER

[ Upstream commit 9bacd256f1354883d3c1402655153367982bba49 ]

TCP stack is dumb in how it cooks its output packets.

Depending on MAX_HEADER value, we might chose a bad ending point
for the headers.

If we align the end of TCP headers to cache line boundary, we
make sure to always use the smallest number of cache lines,
which always help.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index a5ea27df3c2b..2edb73c27962 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -51,7 +51,7 @@ extern struct inet_hashinfo tcp_hashinfo;
 extern struct percpu_counter tcp_orphan_count;
 void tcp_time_wait(struct sock *sk, int state, int timeo);
 
-#define MAX_TCP_HEADER	(128 + MAX_HEADER)
+#define MAX_TCP_HEADER	L1_CACHE_ALIGN(128 + MAX_HEADER)
 #define MAX_TCP_OPTION_SPACE 40
 #define TCP_MIN_SND_MSS		48
 #define TCP_MIN_GSO_SIZE	(TCP_MIN_SND_MSS - MAX_TCP_OPTION_SPACE)
-- 
2.20.1


From 21fa70bd6b8e4b39890b88021a4f47a3187939fa Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Mon, 20 Apr 2020 15:01:33 +0000
Subject: [PATCH 17/30] team: fix hang in team_mode_get()

[ Upstream commit 1c30fbc76b8f0c07c92a8ca4cd7c456612e17eb5 ]

When team mode is changed or set, the team_mode_get() is called to check
whether the mode module is inserted or not. If the mode module is not
inserted, it calls the request_module().
In the request_module(), it creates a child process, which is
the "modprobe" process and waits for the done of the child process.
At this point, the following locks were used.
down_read(&cb_lock()); by genl_rcv()
    genl_lock(); by genl_rcv_msc()
        rtnl_lock(); by team_nl_cmd_options_set()
            mutex_lock(&team->lock); by team_nl_team_get()

Concurrently, the team module could be removed by rmmod or "modprobe -r"
The __exit function of team module is team_module_exit(), which calls
team_nl_fini() and it tries to acquire following locks.
down_write(&cb_lock);
    genl_lock();
Because of the genl_lock() and cb_lock, this process can't be finished
earlier than request_module() routine.

The problem secenario.
CPU0                                     CPU1
team_mode_get
    request_module()
                                         modprobe -r team_mode_roundrobin
                                                     team <--(B)
        modprobe team <--(A)
            team_mode_roundrobin

By request_module(), the "modprobe team_mode_roundrobin" command
will be executed. At this point, the modprobe process will decide
that the team module should be inserted before team_mode_roundrobin.
Because the team module is being removed.

By the module infrastructure, the same module insert/remove operations
can't be executed concurrently.
So, (A) waits for (B) but (B) also waits for (A) because of locks.
So that the hang occurs at this point.

Test commands:
    while :
    do
        teamd -d &
	killall teamd &
	modprobe -rv team_mode_roundrobin &
    done

The approach of this patch is to hold the reference count of the team
module if the team module is compiled as a module. If the reference count
of the team module is not zero while request_module() is being called,
the team module will not be removed at that moment.
So that the above scenario could not occur.

Fixes: 3d249d4ca7d0 ("net: introduce ethernet teaming device")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 4004f98e50d9..04845a4017f9 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -468,6 +468,9 @@ static const struct team_mode *team_mode_get(const char *kind)
 	struct team_mode_item *mitem;
 	const struct team_mode *mode = NULL;
 
+	if (!try_module_get(THIS_MODULE))
+		return NULL;
+
 	spin_lock(&mode_list_lock);
 	mitem = __find_mode(kind);
 	if (!mitem) {
@@ -483,6 +486,7 @@ static const struct team_mode *team_mode_get(const char *kind)
 	}
 
 	spin_unlock(&mode_list_lock);
+	module_put(THIS_MODULE);
 	return mode;
 }
 
-- 
2.20.1


From 4ceb2e2784c8474f0bfb5235ecc4fa9165366435 Mon Sep 17 00:00:00 2001
From: Xiyu Yang <xiyuyang19@fudan.edu.cn>
Date: Wed, 15 Apr 2020 16:39:56 +0800
Subject: [PATCH 18/30] tipc: Fix potential tipc_aead refcnt leak in
 tipc_crypto_rcv

[ Upstream commit 441870ee4240cf67b5d3ab8e16216a9ff42eb5d6 ]

tipc_crypto_rcv() invokes tipc_aead_get(), which returns a reference of
the tipc_aead object to "aead" with increased refcnt.

When tipc_crypto_rcv() returns, the original local reference of "aead"
becomes invalid, so the refcount should be decreased to keep refcount
balanced.

The issue happens in one error path of tipc_crypto_rcv(). When TIPC
message decryption status is EINPROGRESS or EBUSY, the function forgets
to decrease the refcnt increased by tipc_aead_get() and causes a refcnt
leak.

Fix this issue by calling tipc_aead_put() on the error path when TIPC
message decryption status is EINPROGRESS or EBUSY.

Signed-off-by: Xiyu Yang <xiyuyang19@fudan.edu.cn>
Signed-off-by: Xin Tan <tanxin.ctf@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/crypto.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c
index c8c47fc72653..8c47ded2edb6 100644
--- a/net/tipc/crypto.c
+++ b/net/tipc/crypto.c
@@ -1712,6 +1712,7 @@ int tipc_crypto_rcv(struct net *net, struct tipc_crypto *rx,
 	case -EBUSY:
 		this_cpu_inc(stats->stat[STAT_ASYNC]);
 		*skb = NULL;
+		tipc_aead_put(aead);
 		return rc;
 	default:
 		this_cpu_inc(stats->stat[STAT_NOK]);
-- 
2.20.1


From f45f658e1906d7e3392804d8c2176737e9edd551 Mon Sep 17 00:00:00 2001
From: Xiyu Yang <xiyuyang19@fudan.edu.cn>
Date: Wed, 15 Apr 2020 16:40:28 +0800
Subject: [PATCH 19/30] tipc: Fix potential tipc_node refcnt leak in tipc_rcv

[ Upstream commit de058420767df21e2b6b0f3bb36d1616fb962032 ]

tipc_rcv() invokes tipc_node_find() twice, which returns a reference of
the specified tipc_node object to "n" with increased refcnt.

When tipc_rcv() returns or a new object is assigned to "n", the original
local reference of "n" becomes invalid, so the refcount should be
decreased to keep refcount balanced.

The issue happens in some paths of tipc_rcv(), which forget to decrease
the refcnt increased by tipc_node_find() and will cause a refcnt leak.

Fix this issue by calling tipc_node_put() before the original object
pointed by "n" becomes invalid.

Signed-off-by: Xiyu Yang <xiyuyang19@fudan.edu.cn>
Signed-off-by: Xin Tan <tanxin.ctf@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/node.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/tipc/node.c b/net/tipc/node.c
index 0c88778c88b5..d50be9a3d479 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -2037,6 +2037,7 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b)
 		n = tipc_node_find_by_id(net, ehdr->id);
 	}
 	tipc_crypto_rcv(net, (n) ? n->crypto_rx : NULL, &skb, b);
+	tipc_node_put(n);
 	if (!skb)
 		return;
 
@@ -2089,7 +2090,7 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b)
 	/* Check/update node state before receiving */
 	if (unlikely(skb)) {
 		if (unlikely(skb_linearize(skb)))
-			goto discard;
+			goto out_node_put;
 		tipc_node_write_lock(n);
 		if (tipc_node_check_state(n, skb, bearer_id, &xmitq)) {
 			if (le->link) {
@@ -2118,6 +2119,7 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b)
 	if (!skb_queue_empty(&xmitq))
 		tipc_bearer_xmit(net, bearer_id, &xmitq, &le->maddr, n);
 
+out_node_put:
 	tipc_node_put(n);
 discard:
 	kfree_skb(skb);
-- 
2.20.1


From 83a2c2fa3d3c38ac3fcf0e00c28914a2da86b11e Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 21 Apr 2020 17:48:27 -0600
Subject: [PATCH 20/30] vrf: Fix IPv6 with qdisc and xfrm

[ Upstream commit a53c102872ad6e34e1518e25899dc9498c27f8b1 ]

When a qdisc is attached to the VRF device, the packet goes down the ndo
xmit function which is setup to send the packet back to the VRF driver
which does a lookup to send the packet out. The lookup in the VRF driver
is not considering xfrm policies. Change it to use ip6_dst_lookup_flow
rather than ip6_route_output.

Fixes: 35402e313663 ("net: Add IPv6 support to VRF device")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index b8228f50bc94..4285236b5f2e 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -188,8 +188,8 @@ static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
 	fl6.flowi6_proto = iph->nexthdr;
 	fl6.flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF;
 
-	dst = ip6_route_output(net, NULL, &fl6);
-	if (dst == dst_null)
+	dst = ip6_dst_lookup_flow(net, NULL, &fl6, NULL);
+	if (IS_ERR(dst) || dst == dst_null)
 		goto err;
 
 	skb_dst_drop(skb);
-- 
2.20.1


From d069af75c1d7010a98b23fb3790797ea97d4fdfa Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Mon, 20 Apr 2020 20:26:51 -0700
Subject: [PATCH 21/30] net: dsa: b53: Lookup VID in ARL searches when VLAN is
 enabled

[ Upstream commit 2e97b0cd1651a270f3a3fcf42115c51f3284c049 ]

When VLAN is enabled, and an ARL search is issued, we also need to
compare the full {MAC,VID} tuple before returning a successful search
result.

Fixes: 1da6df85c6fb ("net: dsa: b53: Implement ARL add/del/dump operations")
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/b53/b53_common.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 1a69286daa8d..ccf718dafe33 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -1485,6 +1485,9 @@ static int b53_arl_read(struct b53_device *dev, u64 mac,
 			continue;
 		if ((mac_vid & ARLTBL_MAC_MASK) != mac)
 			continue;
+		if (dev->vlan_enabled &&
+		    ((mac_vid >> ARLTBL_VID_S) & ARLTBL_VID_MASK) != vid)
+			continue;
 		*idx = i;
 	}
 
-- 
2.20.1


From 4265c0724efa6561322380f980fbc6a98dc19d2d Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Mon, 20 Apr 2020 20:26:52 -0700
Subject: [PATCH 22/30] net: dsa: b53: Fix valid setting for MDB entries

[ Upstream commit eab167f4851a19c514469dfa81147f77e17b5b20 ]

When support for the MDB entries was added, the valid bit was correctly
changed to be assigned depending on the remaining port bitmask, that is,
if there were no more ports added to the entry's port bitmask, the entry
now becomes invalid. There was another assignment a few lines below that
would override this which would invalidate entries even when there were
still multiple ports left in the MDB entry.

Fixes: 5d65b64a3d97 ("net: dsa: b53: Add support for MDB")
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/b53/b53_common.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index ccf718dafe33..1152331918bf 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -1541,7 +1541,6 @@ static int b53_arl_op(struct b53_device *dev, int op, int port,
 		ent.is_valid = !!(ent.port);
 	}
 
-	ent.is_valid = is_valid;
 	ent.vid = vid;
 	ent.is_static = true;
 	ent.is_age = false;
-- 
2.20.1


From 1eec0d69050cd1e8a31ede3e5517bd420e0182d7 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Mon, 20 Apr 2020 20:26:53 -0700
Subject: [PATCH 23/30] net: dsa: b53: Fix ARL register definitions

[ Upstream commit c2e77a18a7ed65eb48f6e389b6a59a0fd753646a ]

The ARL {MAC,VID} tuple and the forward entry were off by 0x10 bytes,
which means that when we read/wrote from/to ARL bin index 0, we were
actually accessing the ARLA_RWCTRL register.

Fixes: 1da6df85c6fb ("net: dsa: b53: Implement ARL add/del/dump operations")
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/b53/b53_regs.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/b53/b53_regs.h b/drivers/net/dsa/b53/b53_regs.h
index 2a9f421680aa..d914e756cdab 100644
--- a/drivers/net/dsa/b53/b53_regs.h
+++ b/drivers/net/dsa/b53/b53_regs.h
@@ -304,7 +304,7 @@
  *
  * BCM5325 and BCM5365 share most definitions below
  */
-#define B53_ARLTBL_MAC_VID_ENTRY(n)	(0x10 * (n))
+#define B53_ARLTBL_MAC_VID_ENTRY(n)	((0x10 * (n)) + 0x10)
 #define   ARLTBL_MAC_MASK		0xffffffffffffULL
 #define   ARLTBL_VID_S			48
 #define   ARLTBL_VID_MASK_25		0xff
@@ -316,7 +316,7 @@
 #define   ARLTBL_VALID_25		BIT(63)
 
 /* ARL Table Data Entry N Registers (32 bit) */
-#define B53_ARLTBL_DATA_ENTRY(n)	((0x10 * (n)) + 0x08)
+#define B53_ARLTBL_DATA_ENTRY(n)	((0x10 * (n)) + 0x18)
 #define   ARLTBL_DATA_PORT_ID_MASK	0x1ff
 #define   ARLTBL_TC(tc)			((3 & tc) << 11)
 #define   ARLTBL_AGE			BIT(14)
-- 
2.20.1


From cbea0a11a109cd6c8d193946aef1411c8bedc721 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Mon, 20 Apr 2020 20:26:54 -0700
Subject: [PATCH 24/30] net: dsa: b53: Rework ARL bin logic

[ Upstream commit 6344dbde6a27d10d16246d734b968f84887841e2 ]

When asking the ARL to read a MAC address, we will get a number of bins
returned in a single read. Out of those bins, there can essentially be 3
states:

- all bins are full, we have no space left, and we can either replace an
  existing address or return that full condition

- the MAC address was found, then we need to return its bin index and
  modify that one, and only that one

- the MAC address was not found and we have a least one bin free, we use
  that bin index location then

The code would unfortunately fail on all counts.

Fixes: 1da6df85c6fb ("net: dsa: b53: Implement ARL add/del/dump operations")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/b53/b53_common.c | 30 ++++++++++++++++++++++++++----
 drivers/net/dsa/b53/b53_regs.h   |  3 +++
 2 files changed, 29 insertions(+), 4 deletions(-)

diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 1152331918bf..69e430938f8c 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -1463,6 +1463,7 @@ static int b53_arl_read(struct b53_device *dev, u64 mac,
 			u16 vid, struct b53_arl_entry *ent, u8 *idx,
 			bool is_valid)
 {
+	DECLARE_BITMAP(free_bins, B53_ARLTBL_MAX_BIN_ENTRIES);
 	unsigned int i;
 	int ret;
 
@@ -1470,6 +1471,8 @@ static int b53_arl_read(struct b53_device *dev, u64 mac,
 	if (ret)
 		return ret;
 
+	bitmap_zero(free_bins, dev->num_arl_entries);
+
 	/* Read the bins */
 	for (i = 0; i < dev->num_arl_entries; i++) {
 		u64 mac_vid;
@@ -1481,16 +1484,24 @@ static int b53_arl_read(struct b53_device *dev, u64 mac,
 			   B53_ARLTBL_DATA_ENTRY(i), &fwd_entry);
 		b53_arl_to_entry(ent, mac_vid, fwd_entry);
 
-		if (!(fwd_entry & ARLTBL_VALID))
+		if (!(fwd_entry & ARLTBL_VALID)) {
+			set_bit(i, free_bins);
 			continue;
+		}
 		if ((mac_vid & ARLTBL_MAC_MASK) != mac)
 			continue;
 		if (dev->vlan_enabled &&
 		    ((mac_vid >> ARLTBL_VID_S) & ARLTBL_VID_MASK) != vid)
 			continue;
 		*idx = i;
+		return 0;
 	}
 
+	if (bitmap_weight(free_bins, dev->num_arl_entries) == 0)
+		return -ENOSPC;
+
+	*idx = find_first_bit(free_bins, dev->num_arl_entries);
+
 	return -ENOENT;
 }
 
@@ -1520,10 +1531,21 @@ static int b53_arl_op(struct b53_device *dev, int op, int port,
 	if (op)
 		return ret;
 
-	/* We could not find a matching MAC, so reset to a new entry */
-	if (ret) {
+	switch (ret) {
+	case -ENOSPC:
+		dev_dbg(dev->dev, "{%pM,%.4d} no space left in ARL\n",
+			addr, vid);
+		return is_valid ? ret : 0;
+	case -ENOENT:
+		/* We could not find a matching MAC, so reset to a new entry */
+		dev_dbg(dev->dev, "{%pM,%.4d} not found, using idx: %d\n",
+			addr, vid, idx);
 		fwd_entry = 0;
-		idx = 1;
+		break;
+	default:
+		dev_dbg(dev->dev, "{%pM,%.4d} found, using idx: %d\n",
+			addr, vid, idx);
+		break;
 	}
 
 	/* For multicast address, the port is a bitmask and the validity
diff --git a/drivers/net/dsa/b53/b53_regs.h b/drivers/net/dsa/b53/b53_regs.h
index d914e756cdab..14f617e9173d 100644
--- a/drivers/net/dsa/b53/b53_regs.h
+++ b/drivers/net/dsa/b53/b53_regs.h
@@ -323,6 +323,9 @@
 #define   ARLTBL_STATIC			BIT(15)
 #define   ARLTBL_VALID			BIT(16)
 
+/* Maximum number of bin entries in the ARL for all switches */
+#define B53_ARLTBL_MAX_BIN_ENTRIES	4
+
 /* ARL Search Control Register (8 bit) */
 #define B53_ARL_SRCH_CTL		0x50
 #define B53_ARL_SRCH_CTL_25		0x20
-- 
2.20.1


From 0efa15196e3bd520290313f925763ecb3ebbd472 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Mon, 20 Apr 2020 20:26:55 -0700
Subject: [PATCH 25/30] net: dsa: b53: b53_arl_rw_op() needs to select IVL or
 SVL

[ Upstream commit 64fec9493f7dc9bdd7233bcfe98985c45bd0e3c1 ]

Flip the IVL_SVL_SELECT bit correctly based on the VLAN enable status,
the default is to perform Shared VLAN learning instead of Individual
learning.

Fixes: 1da6df85c6fb ("net: dsa: b53: Implement ARL add/del/dump operations")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/b53/b53_common.c | 4 ++++
 drivers/net/dsa/b53/b53_regs.h   | 1 +
 2 files changed, 5 insertions(+)

diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 69e430938f8c..d93de7096ae0 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -1454,6 +1454,10 @@ static int b53_arl_rw_op(struct b53_device *dev, unsigned int op)
 		reg |= ARLTBL_RW;
 	else
 		reg &= ~ARLTBL_RW;
+	if (dev->vlan_enabled)
+		reg &= ~ARLTBL_IVL_SVL_SELECT;
+	else
+		reg |= ARLTBL_IVL_SVL_SELECT;
 	b53_write8(dev, B53_ARLIO_PAGE, B53_ARLTBL_RW_CTRL, reg);
 
 	return b53_arl_op_wait(dev);
diff --git a/drivers/net/dsa/b53/b53_regs.h b/drivers/net/dsa/b53/b53_regs.h
index 14f617e9173d..c90985c294a2 100644
--- a/drivers/net/dsa/b53/b53_regs.h
+++ b/drivers/net/dsa/b53/b53_regs.h
@@ -292,6 +292,7 @@
 /* ARL Table Read/Write Register (8 bit) */
 #define B53_ARLTBL_RW_CTRL		0x00
 #define    ARLTBL_RW			BIT(0)
+#define    ARLTBL_IVL_SVL_SELECT	BIT(6)
 #define    ARLTBL_START_DONE		BIT(7)
 
 /* MAC Address Index Register (48 bit) */
-- 
2.20.1


From f8326776b872ecfdbbbb062b409feea01adb09e0 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Wed, 22 Apr 2020 17:29:50 +0200
Subject: [PATCH 26/30] vxlan: use the correct nlattr array in
 NL_SET_ERR_MSG_ATTR

[ Upstream commit cc8e7c69db4dcc565ed3020f97ddd6debab6cbe8 ]

IFLA_VXLAN_* attributes are in the data array, which is correctly
used when fetching the value, but not when setting the extended
ack. Because IFLA_VXLAN_MAX < IFLA_MAX, we avoid out of bounds
array accesses, but we don't provide a pointer to the invalid
attribute to userspace.

Fixes: 653ef6a3e4af ("vxlan: change vxlan_[config_]validate() to use netlink_ext_ack for error reporting")
Fixes: b4d3069783bc ("vxlan: Allow configuration of DF behaviour")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 45308b3350cf..a5b415fed11e 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -3144,7 +3144,7 @@ static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[],
 		u32 id = nla_get_u32(data[IFLA_VXLAN_ID]);
 
 		if (id >= VXLAN_N_VID) {
-			NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_ID],
+			NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_ID],
 					    "VXLAN ID must be lower than 16777216");
 			return -ERANGE;
 		}
@@ -3155,7 +3155,7 @@ static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[],
 			= nla_data(data[IFLA_VXLAN_PORT_RANGE]);
 
 		if (ntohs(p->high) < ntohs(p->low)) {
-			NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_PORT_RANGE],
+			NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_PORT_RANGE],
 					    "Invalid source port range");
 			return -EINVAL;
 		}
@@ -3165,7 +3165,7 @@ static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[],
 		enum ifla_vxlan_df df = nla_get_u8(data[IFLA_VXLAN_DF]);
 
 		if (df < 0 || df > VXLAN_DF_MAX) {
-			NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_DF],
+			NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_DF],
 					    "Invalid DF attribute");
 			return -EINVAL;
 		}
-- 
2.20.1


From 07a6e014ff407c80550c2e1ad69d89515d55e882 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Wed, 22 Apr 2020 17:29:51 +0200
Subject: [PATCH 27/30] geneve: use the correct nlattr array in
 NL_SET_ERR_MSG_ATTR

[ Upstream commit 9a7b5b50de8a764671ba1800fe4c52d3b7013901 ]

IFLA_GENEVE_* attributes are in the data array, which is correctly
used when fetching the value, but not when setting the extended
ack. Because IFLA_GENEVE_MAX < IFLA_MAX, we avoid out of bounds
array accesses, but we don't provide a pointer to the invalid
attribute to userspace.

Fixes: a025fb5f49ad ("geneve: Allow configuration of DF behaviour")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 09f279c0182b..6b461be1820b 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1207,7 +1207,7 @@ static int geneve_validate(struct nlattr *tb[], struct nlattr *data[],
 		enum ifla_geneve_df df = nla_get_u8(data[IFLA_GENEVE_DF]);
 
 		if (df < 0 || df > GENEVE_DF_MAX) {
-			NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_GENEVE_DF],
+			NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_DF],
 					    "Invalid DF attribute");
 			return -EINVAL;
 		}
-- 
2.20.1


From 4d634e5a19ca4c0766958b159db074b763672d2f Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Mon, 20 Apr 2020 17:13:51 -0600
Subject: [PATCH 28/30] xfrm: Always set XFRM_TRANSFORMED in
 xfrm{4,6}_output_finish

[ Upstream commit 0c922a4850eba2e668f73a3f1153196e09abb251 ]

IPSKB_XFRM_TRANSFORMED and IP6SKB_XFRM_TRANSFORMED are skb flags set by
xfrm code to tell other skb handlers that the packet has been passed
through the xfrm output functions. Simplify the code and just always
set them rather than conditionally based on netfilter enabled thus
making the flag available for other users.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/xfrm4_output.c | 2 --
 net/ipv6/xfrm6_output.c | 2 --
 2 files changed, 4 deletions(-)

diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
index 89ba7c87de5d..30ddb9dc9398 100644
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -58,9 +58,7 @@ int xfrm4_output_finish(struct sock *sk, struct sk_buff *skb)
 {
 	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
 
-#ifdef CONFIG_NETFILTER
 	IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED;
-#endif
 
 	return xfrm_output(sk, skb);
 }
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index fbe51d40bd7e..e34167f790e6 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -111,9 +111,7 @@ int xfrm6_output_finish(struct sock *sk, struct sk_buff *skb)
 {
 	memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
 
-#ifdef CONFIG_NETFILTER
 	IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED;
-#endif
 
 	return xfrm_output(sk, skb);
 }
-- 
2.20.1


From 3d19ce558cbc036de6580d572f9fd915e1badbfa Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Mon, 20 Apr 2020 17:13:52 -0600
Subject: [PATCH 29/30] vrf: Check skb for XFRM_TRANSFORMED flag

[ Upstream commit 16b9db1ce34ff00d6c18e82825125cfef0cdfb13 ]

To avoid a loop with qdiscs and xfrms, check if the skb has already gone
through the qdisc attached to the VRF device and then to the xfrm layer.
If so, no need for a second redirect.

Fixes: 193125dbd8eb ("net: Introduce VRF device driver")
Reported-by: Trev Larock <trev@larock.ca>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 4285236b5f2e..6716deeb35e3 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -474,7 +474,8 @@ static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev,
 	if (rt6_need_strict(&ipv6_hdr(skb)->daddr))
 		return skb;
 
-	if (qdisc_tx_is_default(vrf_dev))
+	if (qdisc_tx_is_default(vrf_dev) ||
+	    IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED)
 		return vrf_ip6_out_direct(vrf_dev, sk, skb);
 
 	return vrf_ip6_out_redirect(vrf_dev, skb);
@@ -686,7 +687,8 @@ static struct sk_buff *vrf_ip_out(struct net_device *vrf_dev,
 	    ipv4_is_lbcast(ip_hdr(skb)->daddr))
 		return skb;
 
-	if (qdisc_tx_is_default(vrf_dev))
+	if (qdisc_tx_is_default(vrf_dev) ||
+	    IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED)
 		return vrf_ip_out_direct(vrf_dev, sk, skb);
 
 	return vrf_ip_out_redirect(vrf_dev, skb);
-- 
2.20.1


From 02b1e313adf45703800c5f36dd40e8f43f2582ea Mon Sep 17 00:00:00 2001
From: Tang Bin <tangbin@cmss.chinamobile.com>
Date: Thu, 23 Apr 2020 10:16:31 +0800
Subject: [PATCH 30/30] net: ethernet: ixp4xx: Add error handling in
 ixp4xx_eth_probe()

[ Upstream commit 6ed79cec3ced6e346a10a70120fcee5f03591bab ]

The function ixp4xx_eth_probe() does not perform sufficient error
checking after executing devm_ioremap_resource(), which can result
in crashes if a critical error path is encountered.

Fixes: f458ac479777 ("ARM/net: ixp4xx: Pass ethernet physical base as resource")
Signed-off-by: Zhang Shengju <zhangshengju@cmss.chinamobile.com>
Signed-off-by: Tang Bin <tangbin@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/xscale/ixp4xx_eth.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/xscale/ixp4xx_eth.c b/drivers/net/ethernet/xscale/ixp4xx_eth.c
index 269596c15133..2e5202923510 100644
--- a/drivers/net/ethernet/xscale/ixp4xx_eth.c
+++ b/drivers/net/ethernet/xscale/ixp4xx_eth.c
@@ -1387,6 +1387,8 @@ static int ixp4xx_eth_probe(struct platform_device *pdev)
 		return -ENODEV;
 	regs_phys = res->start;
 	port->regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(port->regs))
+		return PTR_ERR(port->regs);
 
 	switch (port->id) {
 	case IXP4XX_ETH_NPEA:
-- 
2.20.1

Re: [PATCHES] Networking

[Greg KH]

On Sun, Apr 26, 2020 at 06:10:46PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v5.4 and
> v5.6 -stable, respectively.

All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 105 bytes --]


Please queue up the following networking bug fixes for v5.4 and
v5.6 -stable, respectively.

Thank you.

[-- Attachment #2: net_54.mbox --]
[-- Type: Application/Octet-Stream, Size: 65437 bytes --]

From d72b4a36dd5a04701d8f5af53549283fa9c4a961 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 28 Apr 2020 19:01:58 -0700
Subject: [PATCH 01/31] devlink: fix return value after hitting end in region
 read

[ Upstream commit 610a9346c138b9c2c93d38bf5f3728e74ae9cbd5 ]

Commit d5b90e99e1d5 ("devlink: report 0 after hitting end in region read")
fixed region dump, but region read still returns a spurious error:

$ devlink region read netdevsim/netdevsim1/dummy snapshot 0 addr 0 len 128
0000000000000000 a6 f4 c4 1c 21 35 95 a6 9d 34 c3 5b 87 5b 35 79
0000000000000010 f3 a0 d7 ee 4f 2f 82 7f c6 dd c4 f6 a5 c3 1b ae
0000000000000020 a4 fd c8 62 07 59 48 03 70 3b c7 09 86 88 7f 68
0000000000000030 6f 45 5d 6d 7d 0e 16 38 a9 d0 7a 4b 1e 1e 2e a6
0000000000000040 e6 1d ae 06 d6 18 00 85 ca 62 e8 7e 11 7e f6 0f
0000000000000050 79 7e f7 0f f3 94 68 bd e6 40 22 85 b6 be 6f b1
0000000000000060 af db ef 5e 34 f0 98 4b 62 9a e3 1b 8b 93 fc 17
devlink answers: Invalid argument
0000000000000070 61 e8 11 11 66 10 a5 f7 b1 ea 8d 40 60 53 ed 12

This is a minimal fix, I'll follow up with a restructuring
so we don't have two checks for the same condition.

Fixes: fdd41ec21e15 ("devlink: Return right error code in case of errors for region read")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/devlink.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/core/devlink.c b/net/core/devlink.c
index 4c25f1aa2d37..5667cae57072 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -3907,6 +3907,11 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
 		end_offset = nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]);
 		end_offset += nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]);
 		dump = false;
+
+		if (start_offset == end_offset) {
+			err = 0;
+			goto nla_put_failure;
+		}
 	}
 
 	err = devlink_nl_region_read_snapshot_fill(skb, devlink,
-- 
2.26.2


From f743c91347eb8d3746f9af99e4884d82e9c7644d Mon Sep 17 00:00:00 2001
From: Julia Lawall <Julia.Lawall@inria.fr>
Date: Thu, 30 Apr 2020 21:51:32 +0200
Subject: [PATCH 02/31] dp83640: reverse arguments to list_add_tail

[ Upstream commit 865308373ed49c9fb05720d14cbf1315349b32a9 ]

In this code, it appears that phyter_clocks is a list head, based on
the previous list_for_each, and that clock->list is intended to be a
list element, given that it has just been initialized in
dp83640_clock_init.  Accordingly, switch the arguments to
list_add_tail, which takes the list head as the second argument.

Fixes: cb646e2b02b27 ("ptp: Added a clock driver for the National Semiconductor PHYTER.")
Signed-off-by: Julia Lawall <Julia.Lawall@inria.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/dp83640.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index 8f241b57fcf6..1c75b2627ca8 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -1119,7 +1119,7 @@ static struct dp83640_clock *dp83640_clock_get_bus(struct mii_bus *bus)
 		goto out;
 	}
 	dp83640_clock_init(clock, bus);
-	list_add_tail(&phyter_clocks, &clock->list);
+	list_add_tail(&clock->list, &phyter_clocks);
 out:
 	mutex_unlock(&phyter_clocks_lock);
 
-- 
2.26.2


From 1b22e3a6ed8cbb101476d0ec03865c7bece676c9 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 25 Apr 2020 12:40:25 -0700
Subject: [PATCH 03/31] fq_codel: fix TCA_FQ_CODEL_DROP_BATCH_SIZE sanity
 checks
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 14695212d4cd8b0c997f6121b6df8520038ce076 ]

My intent was to not let users set a zero drop_batch_size,
it seems I once again messed with min()/max().

Fixes: 9d18562a2278 ("fq_codel: add batch ability to fq_codel_drop()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_fq_codel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index c261c0a18868..76d72c3f52ed 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -417,7 +417,7 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt,
 		q->quantum = max(256U, nla_get_u32(tb[TCA_FQ_CODEL_QUANTUM]));
 
 	if (tb[TCA_FQ_CODEL_DROP_BATCH_SIZE])
-		q->drop_batch_size = min(1U, nla_get_u32(tb[TCA_FQ_CODEL_DROP_BATCH_SIZE]));
+		q->drop_batch_size = max(1U, nla_get_u32(tb[TCA_FQ_CODEL_DROP_BATCH_SIZE]));
 
 	if (tb[TCA_FQ_CODEL_MEMORY_LIMIT])
 		q->memory_limit = min(1U << 31, nla_get_u32(tb[TCA_FQ_CODEL_MEMORY_LIMIT]));
-- 
2.26.2


From 41efd49cd97abe7fe7fffe9497439d814921fa54 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@kernel.org>
Date: Fri, 1 May 2020 08:53:08 -0600
Subject: [PATCH 04/31] ipv6: Use global sernum for dst validation with nexthop
 objects

[ Upstream commit 8f34e53b60b337e559f1ea19e2780ff95ab2fa65 ]

Nik reported a bug with pcpu dst cache when nexthop objects are
used illustrated by the following:
    $ ip netns add foo
    $ ip -netns foo li set lo up
    $ ip -netns foo addr add 2001:db8:11::1/128 dev lo
    $ ip netns exec foo sysctl net.ipv6.conf.all.forwarding=1
    $ ip li add veth1 type veth peer name veth2
    $ ip li set veth1 up
    $ ip addr add 2001:db8:10::1/64 dev veth1
    $ ip li set dev veth2 netns foo
    $ ip -netns foo li set veth2 up
    $ ip -netns foo addr add 2001:db8:10::2/64 dev veth2
    $ ip -6 nexthop add id 100 via 2001:db8:10::2 dev veth1
    $ ip -6 route add 2001:db8:11::1/128 nhid 100

    Create a pcpu entry on cpu 0:
    $ taskset -a -c 0 ip -6 route get 2001:db8:11::1

    Re-add the route entry:
    $ ip -6 ro del 2001:db8:11::1
    $ ip -6 route add 2001:db8:11::1/128 nhid 100

    Route get on cpu 0 returns the stale pcpu:
    $ taskset -a -c 0 ip -6 route get 2001:db8:11::1
    RTNETLINK answers: Network is unreachable

    While cpu 1 works:
    $ taskset -a -c 1 ip -6 route get 2001:db8:11::1
    2001:db8:11::1 from :: via 2001:db8:10::2 dev veth1 src 2001:db8:10::1 metric 1024 pref medium

Conversion of FIB entries to work with external nexthop objects
missed an important difference between IPv4 and IPv6 - how dst
entries are invalidated when the FIB changes. IPv4 has a per-network
namespace generation id (rt_genid) that is bumped on changes to the FIB.
Checking if a dst_entry is still valid means comparing rt_genid in the
rtable to the current value of rt_genid for the namespace.

IPv6 also has a per network namespace counter, fib6_sernum, but the
count is saved per fib6_node. With the per-node counter only dst_entries
based on fib entries under the node are invalidated when changes are
made to the routes - limiting the scope of invalidations. IPv6 uses a
reference in the rt6_info, 'from', to track the corresponding fib entry
used to create the dst_entry. When validating a dst_entry, the 'from'
is used to backtrack to the fib6_node and check the sernum of it to the
cookie passed to the dst_check operation.

With the inline format (nexthop definition inline with the fib6_info),
dst_entries cached in the fib6_nh have a 1:1 correlation between fib
entries, nexthop data and dst_entries. With external nexthops, IPv6
looks more like IPv4 which means multiple fib entries across disparate
fib6_nodes can all reference the same fib6_nh. That means validation
of dst_entries based on external nexthops needs to use the IPv4 format
- the per-network namespace counter.

Add sernum to rt6_info and set it when creating a pcpu dst entry. Update
rt6_get_cookie to return sernum if it is set and update dst_check for
IPv6 to look for sernum set and based the check on it if so. Finally,
rt6_get_pcpu_route needs to validate the cached entry before returning
a pcpu entry (similar to the rt_cache_valid calls in __mkroute_input and
__mkroute_output for IPv4).

This problem only affects routes using the new, external nexthops.

Thanks to the kbuild test robot for catching the IS_ENABLED needed
around rt_genid_ipv6 before I sent this out.

Fixes: 5b98324ebe29 ("ipv6: Allow routes to use nexthop objects")
Reported-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Tested-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h       |  4 ++++
 include/net/net_namespace.h |  7 +++++++
 net/ipv6/route.c            | 25 +++++++++++++++++++++++++
 3 files changed, 36 insertions(+)

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 4b5656c71abc..bd0f1595bdc7 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -177,6 +177,7 @@ struct fib6_info {
 struct rt6_info {
 	struct dst_entry		dst;
 	struct fib6_info __rcu		*from;
+	int				sernum;
 
 	struct rt6key			rt6i_dst;
 	struct rt6key			rt6i_src;
@@ -260,6 +261,9 @@ static inline u32 rt6_get_cookie(const struct rt6_info *rt)
 	struct fib6_info *from;
 	u32 cookie = 0;
 
+	if (rt->sernum)
+		return rt->sernum;
+
 	rcu_read_lock();
 
 	from = rcu_dereference(rt->from);
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index c7e15a213ef2..0fca98a3d2d3 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -428,6 +428,13 @@ static inline int rt_genid_ipv4(struct net *net)
 	return atomic_read(&net->ipv4.rt_genid);
 }
 
+#if IS_ENABLED(CONFIG_IPV6)
+static inline int rt_genid_ipv6(const struct net *net)
+{
+	return atomic_read(&net->ipv6.fib6_sernum);
+}
+#endif
+
 static inline void rt_genid_bump_ipv4(struct net *net)
 {
 	atomic_inc(&net->ipv4.rt_genid);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 894c7370c1bd..c81d8e9e5169 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1388,9 +1388,18 @@ static struct rt6_info *ip6_rt_pcpu_alloc(const struct fib6_result *res)
 	}
 	ip6_rt_copy_init(pcpu_rt, res);
 	pcpu_rt->rt6i_flags |= RTF_PCPU;
+
+	if (f6i->nh)
+		pcpu_rt->sernum = rt_genid_ipv6(dev_net(dev));
+
 	return pcpu_rt;
 }
 
+static bool rt6_is_valid(const struct rt6_info *rt6)
+{
+	return rt6->sernum == rt_genid_ipv6(dev_net(rt6->dst.dev));
+}
+
 /* It should be called with rcu_read_lock() acquired */
 static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res)
 {
@@ -1398,6 +1407,19 @@ static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res)
 
 	pcpu_rt = this_cpu_read(*res->nh->rt6i_pcpu);
 
+	if (pcpu_rt && pcpu_rt->sernum && !rt6_is_valid(pcpu_rt)) {
+		struct rt6_info *prev, **p;
+
+		p = this_cpu_ptr(res->nh->rt6i_pcpu);
+		prev = xchg(p, NULL);
+		if (prev) {
+			dst_dev_put(&prev->dst);
+			dst_release(&prev->dst);
+		}
+
+		pcpu_rt = NULL;
+	}
+
 	return pcpu_rt;
 }
 
@@ -2599,6 +2621,9 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
 
 	rt = container_of(dst, struct rt6_info, dst);
 
+	if (rt->sernum)
+		return rt6_is_valid(rt) ? dst : NULL;
+
 	rcu_read_lock();
 
 	/* All IPV6 dsts are created with ->obsolete set to the value
-- 
2.26.2


From b614bd4dbac96c6ce8adbb5447ff650a4cb5e802 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Mon, 27 Apr 2020 18:05:47 +0300
Subject: [PATCH 05/31] mlxsw: spectrum_acl_tcam: Position vchunk in a vregion
 list properly

[ Upstream commit 6ef4889fc0b3aa6ab928e7565935ac6f762cee6e ]

Vregion helpers to get min and max priority depend on the correct
ordering of vchunks in the vregion list. However, the current code
always adds new chunk to the end of the list, no matter what the
priority is. Fix this by finding the correct place in the list and put
vchunk there.

Fixes: 22a677661f56 ("mlxsw: spectrum: Introduce ACL core with simple TCAM implementation")
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c  | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index e993159e8e4c..295b27112d36 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -986,8 +986,9 @@ mlxsw_sp_acl_tcam_vchunk_create(struct mlxsw_sp *mlxsw_sp,
 				unsigned int priority,
 				struct mlxsw_afk_element_usage *elusage)
 {
+	struct mlxsw_sp_acl_tcam_vchunk *vchunk, *vchunk2;
 	struct mlxsw_sp_acl_tcam_vregion *vregion;
-	struct mlxsw_sp_acl_tcam_vchunk *vchunk;
+	struct list_head *pos;
 	int err;
 
 	if (priority == MLXSW_SP_ACL_TCAM_CATCHALL_PRIO)
@@ -1025,7 +1026,14 @@ mlxsw_sp_acl_tcam_vchunk_create(struct mlxsw_sp *mlxsw_sp,
 	}
 
 	mlxsw_sp_acl_tcam_rehash_ctx_vregion_changed(vregion);
-	list_add_tail(&vchunk->list, &vregion->vchunk_list);
+
+	/* Position the vchunk inside the list according to priority */
+	list_for_each(pos, &vregion->vchunk_list) {
+		vchunk2 = list_entry(pos, typeof(*vchunk2), list);
+		if (vchunk2->priority > priority)
+			break;
+	}
+	list_add_tail(&vchunk->list, pos);
 	mutex_unlock(&vregion->lock);
 
 	return vchunk;
-- 
2.26.2


From 9f20b5d616db77de0b978e6e5d01d01e68e27491 Mon Sep 17 00:00:00 2001
From: Roman Mashak <mrv@mojatatu.com>
Date: Fri, 1 May 2020 21:34:18 -0400
Subject: [PATCH 06/31] neigh: send protocol value in neighbor create
 notification

[ Upstream commit 38212bb31fe923d0a2c6299bd2adfbb84cddef2a ]

When a new neighbor entry has been added, event is generated but it does not
include protocol, because its value is assigned after the event notification
routine has run, so move protocol assignment code earlier.

Fixes: df9b0e30d44c ("neighbor: Add protocol attribute")
Cc: David Ahern <dsahern@gmail.com>
Signed-off-by: Roman Mashak <mrv@mojatatu.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 920784a9b7ff..7b40d12f0c22 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1954,6 +1954,9 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 				   NEIGH_UPDATE_F_OVERRIDE_ISROUTER);
 	}
 
+	if (protocol)
+		neigh->protocol = protocol;
+
 	if (ndm->ndm_flags & NTF_EXT_LEARNED)
 		flags |= NEIGH_UPDATE_F_EXT_LEARNED;
 
@@ -1967,9 +1970,6 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 		err = __neigh_update(neigh, lladdr, ndm->ndm_state, flags,
 				     NETLINK_CB(skb).portid, extack);
 
-	if (protocol)
-		neigh->protocol = protocol;
-
 	neigh_release(neigh);
 
 out:
-- 
2.26.2


From c0ba8cb7c43ebffe7498d78cf5326d6170e0973e Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Mon, 4 May 2020 13:18:06 -0700
Subject: [PATCH 07/31] net: dsa: Do not leave DSA master with NULL netdev_ops

[ Upstream commit 050569fc8384c8056bacefcc246bcb2dfe574936 ]

When ndo_get_phys_port_name() for the CPU port was added we introduced
an early check for when the DSA master network device in
dsa_master_ndo_setup() already implements ndo_get_phys_port_name(). When
we perform the teardown operation in dsa_master_ndo_teardown() we would
not be checking that cpu_dp->orig_ndo_ops was successfully allocated and
non-NULL initialized.

With network device drivers such as virtio_net, this leads to a NPD as
soon as the DSA switch hanging off of it gets torn down because we are
now assigning the virtio_net device's netdev_ops a NULL pointer.

Fixes: da7b9e9b00d4 ("net: dsa: Add ndo_get_phys_port_name() for CPU port")
Reported-by: Allen Pais <allen.pais@oracle.com>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Tested-by: Allen Pais <allen.pais@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/master.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/dsa/master.c b/net/dsa/master.c
index 3255dfc97f86..be0b4ed3b7d8 100644
--- a/net/dsa/master.c
+++ b/net/dsa/master.c
@@ -259,7 +259,8 @@ static void dsa_master_ndo_teardown(struct net_device *dev)
 {
 	struct dsa_port *cpu_dp = dev->dsa_ptr;
 
-	dev->netdev_ops = cpu_dp->orig_ndo_ops;
+	if (cpu_dp->orig_ndo_ops)
+		dev->netdev_ops = cpu_dp->orig_ndo_ops;
 	cpu_dp->orig_ndo_ops = NULL;
 }
 
-- 
2.26.2


From 0572854bcf02a65951e6fdf01b4ea5faf8123b30 Mon Sep 17 00:00:00 2001
From: Dejin Zheng <zhengdejin5@gmail.com>
Date: Sun, 3 May 2020 20:32:26 +0800
Subject: [PATCH 08/31] net: macb: fix an issue about leak related system
 resources

[ Upstream commit b959c77dac09348955f344104c6a921ebe104753 ]

A call of the function macb_init() can fail in the function
fu540_c000_init. The related system resources were not released
then. use devm_platform_ioremap_resource() to replace ioremap()
to fix it.

Fixes: c218ad559020ff9 ("macb: Add support for SiFive FU540-C000")
Cc: Andy Shevchenko <andy.shevchenko@gmail.com>
Reviewed-by: Yash Shah <yash.shah@sifive.com>
Suggested-by: Nicolas Ferre <nicolas.ferre@microchip.com>
Suggested-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Dejin Zheng <zhengdejin5@gmail.com>
Acked-by: Nicolas Ferre <nicolas.ferre@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 234c13ebbc41..eae21fc68242 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -4048,15 +4048,9 @@ static int fu540_c000_clk_init(struct platform_device *pdev, struct clk **pclk,
 
 static int fu540_c000_init(struct platform_device *pdev)
 {
-	struct resource *res;
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-	if (!res)
-		return -ENODEV;
-
-	mgmt->reg = ioremap(res->start, resource_size(res));
-	if (!mgmt->reg)
-		return -ENOMEM;
+	mgmt->reg = devm_platform_ioremap_resource(pdev, 1);
+	if (IS_ERR(mgmt->reg))
+		return PTR_ERR(mgmt->reg);
 
 	return macb_init(pdev);
 }
-- 
2.26.2


From 8cb81fce1df86c4f947bb7c6ad90396c152822f4 Mon Sep 17 00:00:00 2001
From: Scott Dial <scott@scottdial.com>
Date: Fri, 24 Apr 2020 18:51:08 -0400
Subject: [PATCH 09/31] net: macsec: preserve ingress frame ordering

[ Upstream commit ab046a5d4be4c90a3952a0eae75617b49c0cb01b ]

MACsec decryption always occurs in a softirq context. Since
the FPU may not be usable in the softirq context, the call to
decrypt may be scheduled on the cryptd work queue. The cryptd
work queue does not provide ordering guarantees. Therefore,
preserving order requires masking out ASYNC implementations
of gcm(aes).

For instance, an Intel CPU with AES-NI makes available the
generic-gcm-aesni driver from the aesni_intel module to
implement gcm(aes). However, this implementation requires
the FPU, so it is not always available to use from a softirq
context, and will fallback to the cryptd work queue, which
does not preserve frame ordering. With this change, such a
system would select gcm_base(ctr(aes-aesni),ghash-generic).
While the aes-aesni implementation prefers to use the FPU, it
will fallback to the aes-asm implementation if unavailable.

By using a synchronous version of gcm(aes), the decryption
will complete before returning from crypto_aead_decrypt().
Therefore, the macsec_decrypt_done() callback will be called
before returning from macsec_decrypt(). Thus, the order of
calls to macsec_post_decrypt() for the frames is preserved.

While it's presumable that the pure AES-NI version of gcm(aes)
is more performant, the hybrid solution is capable of gigabit
speeds on modest hardware. Regardless, preserving the order
of frames is paramount for many network protocols (e.g.,
triggering TCP retries). Within the MACsec driver itself, the
replay protection is tripped by the out-of-order frames, and
can cause frames to be dropped.

This bug has been present in this code since it was added in
v4.6, however it may not have been noticed since not all CPUs
have FPU offload available. Additionally, the bug manifests
as occasional out-of-order packets that are easily
misattributed to other network phenomena.

When this code was added in v4.6, the crypto/gcm.c code did
not restrict selection of the ghash function based on the
ASYNC flag. For instance, x86 CPUs with PCLMULQDQ would
select the ghash-clmulni driver instead of ghash-generic,
which submits to the cryptd work queue if the FPU is busy.
However, this bug was was corrected in v4.8 by commit
b30bdfa86431afbafe15284a3ad5ac19b49b88e3, and was backported
all the way back to the v3.14 stable branch, so this patch
should be applicable back to the v4.6 stable branch.

Signed-off-by: Scott Dial <scott@scottdial.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macsec.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index a0abc729f0ca..4c86a73db475 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -1309,7 +1309,8 @@ static struct crypto_aead *macsec_alloc_tfm(char *key, int key_len, int icv_len)
 	struct crypto_aead *tfm;
 	int ret;
 
-	tfm = crypto_alloc_aead("gcm(aes)", 0, 0);
+	/* Pick a sync gcm(aes) cipher to ensure order is preserved. */
+	tfm = crypto_alloc_aead("gcm(aes)", 0, CRYPTO_ALG_ASYNC);
 
 	if (IS_ERR(tfm))
 		return tfm;
-- 
2.26.2


From 2ef95744e3a8772af7daaee47a7af2c552abb0f4 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Mon, 4 May 2020 11:36:02 +0300
Subject: [PATCH 10/31] net/mlx4_core: Fix use of ENOSPC around
 mlx4_counter_alloc()

[ Upstream commit 40e473071dbad04316ddc3613c3a3d1c75458299 ]

When ENOSPC is set the idx is still valid and gets set to the global
MLX4_SINK_COUNTER_INDEX.  However gcc's static analysis cannot tell that
ENOSPC is impossible from mlx4_cmd_imm() and gives this warning:

drivers/net/ethernet/mellanox/mlx4/main.c:2552:28: warning: 'idx' may be
used uninitialized in this function [-Wmaybe-uninitialized]
 2552 |    priv->def_counter[port] = idx;

Also, when ENOSPC is returned mlx4_allocate_default_counters should not
fail.

Fixes: 6de5f7f6a1fa ("net/mlx4_core: Allocate default counter per port")
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/main.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index d44ac666e730..87c2e8de6102 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -2550,6 +2550,7 @@ static int mlx4_allocate_default_counters(struct mlx4_dev *dev)
 
 		if (!err || err == -ENOSPC) {
 			priv->def_counter[port] = idx;
+			err = 0;
 		} else if (err == -ENOENT) {
 			err = 0;
 			continue;
@@ -2600,7 +2601,8 @@ int mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx, u8 usage)
 				   MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
 		if (!err)
 			*idx = get_param_l(&out_param);
-
+		if (WARN_ON(err == -ENOSPC))
+			err = -EINVAL;
 		return err;
 	}
 	return __mlx4_counter_alloc(dev, idx);
-- 
2.26.2


From 5fb60dbb496b31ebc122b42fd1294e1edc51051a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 2 May 2020 20:09:25 -0700
Subject: [PATCH 11/31] net_sched: sch_skbprio: add message validation to
 skbprio_change()

[ Upstream commit 2761121af87de45951989a0adada917837d8fa82 ]

Do not assume the attribute has the right size.

Fixes: aea5f654e6b7 ("net/sched: add skbprio scheduler")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_skbprio.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/sched/sch_skbprio.c b/net/sched/sch_skbprio.c
index 0fb10abf7579..7a5e4c454715 100644
--- a/net/sched/sch_skbprio.c
+++ b/net/sched/sch_skbprio.c
@@ -169,6 +169,9 @@ static int skbprio_change(struct Qdisc *sch, struct nlattr *opt,
 {
 	struct tc_skbprio_qopt *ctl = nla_data(opt);
 
+	if (opt->nla_len != nla_attr_size(sizeof(*ctl)))
+		return -EINVAL;
+
 	sch->limit = ctl->limit;
 	return 0;
 }
-- 
2.26.2


From 72b5aa801f7c8ac5d3c5ca5099b21363287b1589 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Mon, 4 May 2020 12:48:54 -0400
Subject: [PATCH 12/31] net: stricter validation of untrusted gso packets

[ Upstream commit 9274124f023b5c56dc4326637d4f787968b03607 ]

Syzkaller again found a path to a kernel crash through bad gso input:
a packet with transport header extending beyond skb_headlen(skb).

Tighten validation at kernel entry:

- Verify that the transport header lies within the linear section.

    To avoid pulling linux/tcp.h, verify just sizeof tcphdr.
    tcp_gso_segment will call pskb_may_pull (th->doff * 4) before use.

- Match the gso_type against the ip_proto found by the flow dissector.

Fixes: bfd5f4a3d605 ("packet: Add GSO/csum offload support.")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/virtio_net.h | 26 ++++++++++++++++++++++++--
 1 file changed, 24 insertions(+), 2 deletions(-)

diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 0d1fe9297ac6..6f6ade63b04c 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -3,6 +3,8 @@
 #define _LINUX_VIRTIO_NET_H
 
 #include <linux/if_vlan.h>
+#include <uapi/linux/tcp.h>
+#include <uapi/linux/udp.h>
 #include <uapi/linux/virtio_net.h>
 
 static inline int virtio_net_hdr_set_proto(struct sk_buff *skb,
@@ -28,17 +30,25 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 					bool little_endian)
 {
 	unsigned int gso_type = 0;
+	unsigned int thlen = 0;
+	unsigned int ip_proto;
 
 	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
 		switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
 		case VIRTIO_NET_HDR_GSO_TCPV4:
 			gso_type = SKB_GSO_TCPV4;
+			ip_proto = IPPROTO_TCP;
+			thlen = sizeof(struct tcphdr);
 			break;
 		case VIRTIO_NET_HDR_GSO_TCPV6:
 			gso_type = SKB_GSO_TCPV6;
+			ip_proto = IPPROTO_TCP;
+			thlen = sizeof(struct tcphdr);
 			break;
 		case VIRTIO_NET_HDR_GSO_UDP:
 			gso_type = SKB_GSO_UDP;
+			ip_proto = IPPROTO_UDP;
+			thlen = sizeof(struct udphdr);
 			break;
 		default:
 			return -EINVAL;
@@ -57,16 +67,22 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 
 		if (!skb_partial_csum_set(skb, start, off))
 			return -EINVAL;
+
+		if (skb_transport_offset(skb) + thlen > skb_headlen(skb))
+			return -EINVAL;
 	} else {
 		/* gso packets without NEEDS_CSUM do not set transport_offset.
 		 * probe and drop if does not match one of the above types.
 		 */
 		if (gso_type && skb->network_header) {
+			struct flow_keys_basic keys;
+
 			if (!skb->protocol)
 				virtio_net_hdr_set_proto(skb, hdr);
 retry:
-			skb_probe_transport_header(skb);
-			if (!skb_transport_header_was_set(skb)) {
+			if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys,
+							      NULL, 0, 0, 0,
+							      0)) {
 				/* UFO does not specify ipv4 or 6: try both */
 				if (gso_type & SKB_GSO_UDP &&
 				    skb->protocol == htons(ETH_P_IP)) {
@@ -75,6 +91,12 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 				}
 				return -EINVAL;
 			}
+
+			if (keys.control.thoff + thlen > skb_headlen(skb) ||
+			    keys.basic.ip_proto != ip_proto)
+				return -EINVAL;
+
+			skb_set_transport_header(skb, keys.control.thoff);
 		}
 	}
 
-- 
2.26.2


From ec44e4110b5ccc86c7e6d29b41881e9b16ddc3b7 Mon Sep 17 00:00:00 2001
From: Anthony Felice <tony.felice@timesys.com>
Date: Sun, 26 Apr 2020 22:00:59 -0400
Subject: [PATCH 13/31] net: tc35815: Fix phydev supported/advertising mask

[ Upstream commit 4b5b71f770e2edefbfe74203777264bfe6a9927c ]

Commit 3c1bcc8614db ("net: ethernet: Convert phydev advertize and
supported from u32 to link mode") updated ethernet drivers to use a
linkmode bitmap. It mistakenly dropped a bitwise negation in the
tc35815 ethernet driver on a bitmask to set the supported/advertising
flags.

Found by Anthony via code inspection, not tested as I do not have the
required hardware.

Fixes: 3c1bcc8614db ("net: ethernet: Convert phydev advertize and supported from u32 to link mode")
Signed-off-by: Anthony Felice <tony.felice@timesys.com>
Reviewed-by: Akshay Bhat <akshay.bhat@timesys.com>
Reviewed-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/toshiba/tc35815.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/toshiba/tc35815.c b/drivers/net/ethernet/toshiba/tc35815.c
index 12466a72cefc..aab0cf57c654 100644
--- a/drivers/net/ethernet/toshiba/tc35815.c
+++ b/drivers/net/ethernet/toshiba/tc35815.c
@@ -644,7 +644,7 @@ static int tc_mii_probe(struct net_device *dev)
 		linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, mask);
 		linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, mask);
 	}
-	linkmode_and(phydev->supported, phydev->supported, mask);
+	linkmode_andnot(phydev->supported, phydev->supported, mask);
 	linkmode_copy(phydev->advertising, phydev->supported);
 
 	lp->link = 0;
-- 
2.26.2


From b59727b7cc20259c988522d1e8d2d3ef5e7160ba Mon Sep 17 00:00:00 2001
From: Xiyu Yang <xiyuyang19@fudan.edu.cn>
Date: Sat, 25 Apr 2020 20:54:37 +0800
Subject: [PATCH 14/31] net/tls: Fix sk_psock refcnt leak in
 bpf_exec_tx_verdict()

[ Upstream commit 095f5614bfe16e5b3e191b34ea41b10d6fdd4ced ]

bpf_exec_tx_verdict() invokes sk_psock_get(), which returns a reference
of the specified sk_psock object to "psock" with increased refcnt.

When bpf_exec_tx_verdict() returns, local variable "psock" becomes
invalid, so the refcount should be decreased to keep refcount balanced.

The reference counting issue happens in one exception handling path of
bpf_exec_tx_verdict(). When "policy" equals to NULL but "psock" is not
NULL, the function forgets to decrease the refcnt increased by
sk_psock_get(), causing a refcnt leak.

Fix this issue by calling sk_psock_put() on this error path before
bpf_exec_tx_verdict() returns.

Signed-off-by: Xiyu Yang <xiyuyang19@fudan.edu.cn>
Signed-off-by: Xin Tan <tanxin.ctf@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 41e9c2932b34..7e646b2f04af 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -797,6 +797,8 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk,
 			*copied -= sk_msg_free(sk, msg);
 			tls_free_open_rec(sk);
 		}
+		if (psock)
+			sk_psock_put(sk, psock);
 		return err;
 	}
 more_data:
-- 
2.26.2


From b28850a19e61dd07a7c34cac90941f21bc827952 Mon Sep 17 00:00:00 2001
From: Xiyu Yang <xiyuyang19@fudan.edu.cn>
Date: Sat, 25 Apr 2020 21:10:23 +0800
Subject: [PATCH 15/31] net/tls: Fix sk_psock refcnt leak when in
 tls_data_ready()

[ Upstream commit 62b4011fa7bef9fa00a6aeec26e69685dc1cc21e ]

tls_data_ready() invokes sk_psock_get(), which returns a reference of
the specified sk_psock object to "psock" with increased refcnt.

When tls_data_ready() returns, local variable "psock" becomes invalid,
so the refcount should be decreased to keep refcount balanced.

The reference counting issue happens in one exception handling path of
tls_data_ready(). When "psock->ingress_msg" is empty but "psock" is not
NULL, the function forgets to decrease the refcnt increased by
sk_psock_get(), causing a refcnt leak.

Fix this issue by calling sk_psock_put() on all paths when "psock" is
not NULL.

Signed-off-by: Xiyu Yang <xiyuyang19@fudan.edu.cn>
Signed-off-by: Xin Tan <tanxin.ctf@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 7e646b2f04af..5513a08a4308 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -2078,8 +2078,9 @@ static void tls_data_ready(struct sock *sk)
 	strp_data_ready(&ctx->strp);
 
 	psock = sk_psock_get(sk);
-	if (psock && !list_empty(&psock->ingress_msg)) {
-		ctx->saved_data_ready(sk);
+	if (psock) {
+		if (!list_empty(&psock->ingress_msg))
+			ctx->saved_data_ready(sk);
 		sk_psock_put(sk, psock);
 	}
 }
-- 
2.26.2


From 4ee02c18aaf2af23ce3cbb8256aa635a801cda44 Mon Sep 17 00:00:00 2001
From: Matt Jolly <Kangie@footclan.ninja>
Date: Sun, 3 May 2020 01:52:28 +1000
Subject: [PATCH 16/31] net: usb: qmi_wwan: add support for DW5816e
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 57c7f2bd758eed867295c81d3527fff4fab1ed74 ]

Add support for Dell Wireless 5816e to drivers/net/usb/qmi_wwan.c

Signed-off-by: Matt Jolly <Kangie@footclan.ninja>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 6c738a271257..4bb8552a00d3 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1359,6 +1359,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x413c, 0x81b3, 8)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */
 	{QMI_FIXED_INTF(0x413c, 0x81b6, 8)},	/* Dell Wireless 5811e */
 	{QMI_FIXED_INTF(0x413c, 0x81b6, 10)},	/* Dell Wireless 5811e */
+	{QMI_FIXED_INTF(0x413c, 0x81cc, 8)},	/* Dell Wireless 5816e */
 	{QMI_FIXED_INTF(0x413c, 0x81d7, 0)},	/* Dell Wireless 5821e */
 	{QMI_FIXED_INTF(0x413c, 0x81d7, 1)},	/* Dell Wireless 5821e preproduction config */
 	{QMI_FIXED_INTF(0x413c, 0x81e0, 0)},	/* Dell Wireless 5821e with eSIM support*/
-- 
2.26.2


From d77c6851640ccea1340e4bf82d13159128aa22d8 Mon Sep 17 00:00:00 2001
From: Qiushi Wu <wu000273@umn.edu>
Date: Sat, 2 May 2020 17:42:59 -0500
Subject: [PATCH 17/31] nfp: abm: fix a memory leak bug

[ Upstream commit bd4af432cc71b5fbfe4833510359a6ad3ada250d ]

In function nfp_abm_vnic_set_mac, pointer nsp is allocated by nfp_nsp_open.
But when nfp_nsp_has_hwinfo_lookup fail, the pointer is not released,
which can lead to a memory leak bug. Fix this issue by adding
nfp_nsp_close(nsp) in the error path.

Fixes: f6e71efdf9fb1 ("nfp: abm: look up MAC addresses via management FW")
Signed-off-by: Qiushi Wu <wu000273@umn.edu>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/abm/main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.c b/drivers/net/ethernet/netronome/nfp/abm/main.c
index 9183b3e85d21..354efffac0f9 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.c
@@ -283,6 +283,7 @@ nfp_abm_vnic_set_mac(struct nfp_pf *pf, struct nfp_abm *abm, struct nfp_net *nn,
 	if (!nfp_nsp_has_hwinfo_lookup(nsp)) {
 		nfp_warn(pf->cpp, "NSP doesn't support PF MAC generation\n");
 		eth_hw_addr_random(nn->dp.netdev);
+		nfp_nsp_close(nsp);
 		return;
 	}
 
-- 
2.26.2


From 9d5e9c2a282b2a204b68be0d970d594800772a4e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 25 Apr 2020 15:19:51 -0700
Subject: [PATCH 18/31] sch_choke: avoid potential panic in choke_reset()

[ Upstream commit 8738c85c72b3108c9b9a369a39868ba5f8e10ae0 ]

If choke_init() could not allocate q->tab, we would crash later
in choke_reset().

BUG: KASAN: null-ptr-deref in memset include/linux/string.h:366 [inline]
BUG: KASAN: null-ptr-deref in choke_reset+0x208/0x340 net/sched/sch_choke.c:326
Write of size 8 at addr 0000000000000000 by task syz-executor822/7022

CPU: 1 PID: 7022 Comm: syz-executor822 Not tainted 5.7.0-rc1-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x188/0x20d lib/dump_stack.c:118
 __kasan_report.cold+0x5/0x4d mm/kasan/report.c:515
 kasan_report+0x33/0x50 mm/kasan/common.c:625
 check_memory_region_inline mm/kasan/generic.c:187 [inline]
 check_memory_region+0x141/0x190 mm/kasan/generic.c:193
 memset+0x20/0x40 mm/kasan/common.c:85
 memset include/linux/string.h:366 [inline]
 choke_reset+0x208/0x340 net/sched/sch_choke.c:326
 qdisc_reset+0x6b/0x520 net/sched/sch_generic.c:910
 dev_deactivate_queue.constprop.0+0x13c/0x240 net/sched/sch_generic.c:1138
 netdev_for_each_tx_queue include/linux/netdevice.h:2197 [inline]
 dev_deactivate_many+0xe2/0xba0 net/sched/sch_generic.c:1195
 dev_deactivate+0xf8/0x1c0 net/sched/sch_generic.c:1233
 qdisc_graft+0xd25/0x1120 net/sched/sch_api.c:1051
 tc_modify_qdisc+0xbab/0x1a00 net/sched/sch_api.c:1670
 rtnetlink_rcv_msg+0x44e/0xad0 net/core/rtnetlink.c:5454
 netlink_rcv_skb+0x15a/0x410 net/netlink/af_netlink.c:2469
 netlink_unicast_kernel net/netlink/af_netlink.c:1303 [inline]
 netlink_unicast+0x537/0x740 net/netlink/af_netlink.c:1329
 netlink_sendmsg+0x882/0xe10 net/netlink/af_netlink.c:1918
 sock_sendmsg_nosec net/socket.c:652 [inline]
 sock_sendmsg+0xcf/0x120 net/socket.c:672
 ____sys_sendmsg+0x6bf/0x7e0 net/socket.c:2362
 ___sys_sendmsg+0x100/0x170 net/socket.c:2416
 __sys_sendmsg+0xec/0x1b0 net/socket.c:2449
 do_syscall_64+0xf6/0x7d0 arch/x86/entry/common.c:295

Fixes: 77e62da6e60c ("sch_choke: drop all packets in queue during reset")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_choke.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index dba70377bbd9..4021f726b58f 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -323,7 +323,8 @@ static void choke_reset(struct Qdisc *sch)
 
 	sch->q.qlen = 0;
 	sch->qstats.backlog = 0;
-	memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *));
+	if (q->tab)
+		memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *));
 	q->head = q->tail = 0;
 	red_restart(&q->vars);
 }
-- 
2.26.2


From ec3aa723f46ac1c64bd997d6236c392a90058708 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 26 Apr 2020 18:19:07 -0700
Subject: [PATCH 19/31] sch_sfq: validate silly quantum values

[ Upstream commit df4953e4e997e273501339f607b77953772e3559 ]

syzbot managed to set up sfq so that q->scaled_quantum was zero,
triggering an infinite loop in sfq_dequeue()

More generally, we must only accept quantum between 1 and 2^18 - 7,
meaning scaled_quantum must be in [1, 0x7FFF] range.

Otherwise, we also could have a loop in sfq_dequeue()
if scaled_quantum happens to be 0x8000, since slot->allot
could indefinitely switch between 0 and 0x8000.

Fixes: eeaeb068f139 ("sch_sfq: allow big packets and be fair")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot+0251e883fe39e7a0cb0a@syzkaller.appspotmail.com
Cc: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_sfq.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index c787d4d46017..5a6def5e4e6d 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -637,6 +637,15 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt)
 	if (ctl->divisor &&
 	    (!is_power_of_2(ctl->divisor) || ctl->divisor > 65536))
 		return -EINVAL;
+
+	/* slot->allot is a short, make sure quantum is not too big. */
+	if (ctl->quantum) {
+		unsigned int scaled = SFQ_ALLOT_SIZE(ctl->quantum);
+
+		if (scaled <= 0 || scaled > SHRT_MAX)
+			return -EINVAL;
+	}
+
 	if (ctl_v1 && !red_check_params(ctl_v1->qth_min, ctl_v1->qth_max,
 					ctl_v1->Wlog))
 		return -EINVAL;
-- 
2.26.2


From e386360116275214310da8e0a4ea59ce6116a7f5 Mon Sep 17 00:00:00 2001
From: Tuong Lien <tuong.t.lien@dektech.com.au>
Date: Mon, 4 May 2020 11:15:54 +0700
Subject: [PATCH 20/31] tipc: fix partial topology connection closure

[ Upstream commit 980d69276f3048af43a045be2925dacfb898a7be ]

When an application connects to the TIPC topology server and subscribes
to some services, a new connection is created along with some objects -
'tipc_subscription' to store related data correspondingly...
However, there is one omission in the connection handling that when the
connection or application is orderly shutdown (e.g. via SIGQUIT, etc.),
the connection is not closed in kernel, the 'tipc_subscription' objects
are not freed too.
This results in:
- The maximum number of subscriptions (65535) will be reached soon, new
subscriptions will be rejected;
- TIPC module cannot be removed (unless the objects  are somehow forced
to release first);

The commit fixes the issue by closing the connection if the 'recvmsg()'
returns '0' i.e. when the peer is shutdown gracefully. It also includes
the other unexpected cases.

Acked-by: Jon Maloy <jmaloy@redhat.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Tuong Lien <tuong.t.lien@dektech.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/topsrv.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c
index 3a12fc18239b..73dbed0c4b6b 100644
--- a/net/tipc/topsrv.c
+++ b/net/tipc/topsrv.c
@@ -402,10 +402,11 @@ static int tipc_conn_rcv_from_sock(struct tipc_conn *con)
 		read_lock_bh(&sk->sk_callback_lock);
 		ret = tipc_conn_rcv_sub(srv, con, &s);
 		read_unlock_bh(&sk->sk_callback_lock);
+		if (!ret)
+			return 0;
 	}
-	if (ret < 0)
-		tipc_conn_close(con);
 
+	tipc_conn_close(con);
 	return ret;
 }
 
-- 
2.26.2


From d07edd1b9b017bf1acdc9cb4d23f994afb198e09 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
Date: Mon, 27 Apr 2020 16:11:05 +0200
Subject: [PATCH 21/31] tunnel: Propagate ECT(1) when decapsulating as
 recommended by RFC6040
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit b723748750ece7d844cdf2f52c01d37f83387208 ]

RFC 6040 recommends propagating an ECT(1) mark from an outer tunnel header
to the inner header if that inner header is already marked as ECT(0). When
RFC 6040 decapsulation was implemented, this case of propagation was not
added. This simply appears to be an oversight, so let's fix that.

Fixes: eccc1bb8d4b4 ("tunnel: drop packet if ECN present with not-ECT")
Reported-by: Bob Briscoe <ietf@bobbriscoe.net>
Reported-by: Olivier Tilmans <olivier.tilmans@nokia-bell-labs.com>
Cc: Dave Taht <dave.taht@gmail.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_ecn.h | 57 ++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 55 insertions(+), 2 deletions(-)

diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h
index c8e2bebd8d93..0f0d1efe06dd 100644
--- a/include/net/inet_ecn.h
+++ b/include/net/inet_ecn.h
@@ -99,6 +99,20 @@ static inline int IP_ECN_set_ce(struct iphdr *iph)
 	return 1;
 }
 
+static inline int IP_ECN_set_ect1(struct iphdr *iph)
+{
+	u32 check = (__force u32)iph->check;
+
+	if ((iph->tos & INET_ECN_MASK) != INET_ECN_ECT_0)
+		return 0;
+
+	check += (__force u16)htons(0x100);
+
+	iph->check = (__force __sum16)(check + (check>=0xFFFF));
+	iph->tos ^= INET_ECN_MASK;
+	return 1;
+}
+
 static inline void IP_ECN_clear(struct iphdr *iph)
 {
 	iph->tos &= ~INET_ECN_MASK;
@@ -134,6 +148,22 @@ static inline int IP6_ECN_set_ce(struct sk_buff *skb, struct ipv6hdr *iph)
 	return 1;
 }
 
+static inline int IP6_ECN_set_ect1(struct sk_buff *skb, struct ipv6hdr *iph)
+{
+	__be32 from, to;
+
+	if ((ipv6_get_dsfield(iph) & INET_ECN_MASK) != INET_ECN_ECT_0)
+		return 0;
+
+	from = *(__be32 *)iph;
+	to = from ^ htonl(INET_ECN_MASK << 20);
+	*(__be32 *)iph = to;
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		skb->csum = csum_add(csum_sub(skb->csum, (__force __wsum)from),
+				     (__force __wsum)to);
+	return 1;
+}
+
 static inline void ipv6_copy_dscp(unsigned int dscp, struct ipv6hdr *inner)
 {
 	dscp &= ~INET_ECN_MASK;
@@ -159,6 +189,25 @@ static inline int INET_ECN_set_ce(struct sk_buff *skb)
 	return 0;
 }
 
+static inline int INET_ECN_set_ect1(struct sk_buff *skb)
+{
+	switch (skb->protocol) {
+	case cpu_to_be16(ETH_P_IP):
+		if (skb_network_header(skb) + sizeof(struct iphdr) <=
+		    skb_tail_pointer(skb))
+			return IP_ECN_set_ect1(ip_hdr(skb));
+		break;
+
+	case cpu_to_be16(ETH_P_IPV6):
+		if (skb_network_header(skb) + sizeof(struct ipv6hdr) <=
+		    skb_tail_pointer(skb))
+			return IP6_ECN_set_ect1(skb, ipv6_hdr(skb));
+		break;
+	}
+
+	return 0;
+}
+
 /*
  * RFC 6040 4.2
  *  To decapsulate the inner header at the tunnel egress, a compliant
@@ -208,8 +257,12 @@ static inline int INET_ECN_decapsulate(struct sk_buff *skb,
 	int rc;
 
 	rc = __INET_ECN_decapsulate(outer, inner, &set_ce);
-	if (!rc && set_ce)
-		INET_ECN_set_ce(skb);
+	if (!rc) {
+		if (set_ce)
+			INET_ECN_set_ce(skb);
+		else if ((outer & INET_ECN_MASK) == INET_ECN_ECT_1)
+			INET_ECN_set_ect1(skb);
+	}
 
 	return rc;
 }
-- 
2.26.2


From 54183841bfe665828312ce7b290007aeb1dfd46c Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 26 Apr 2020 16:24:38 -0400
Subject: [PATCH 22/31] bnxt_en: Fix VF anti-spoof filter setup.

[ Upstream commit c71c4e49afe173823a2a85b0cabc9b3f1176ffa2 ]

Fix the logic that sets the enable/disable flag for the source MAC
filter according to firmware spec 1.7.1.

In the original firmware spec. before 1.7.1, the VF spoof check flags
were not latched after making the HWRM_FUNC_CFG call, so there was a
need to keep the func_flags so that subsequent calls would perserve
the VF spoof check setting.  A change was made in the 1.7.1 spec
so that the flags became latched.  So we now set or clear the anti-
spoof setting directly without retrieving the old settings in the
stored vf->func_flags which are no longer valid.  We also remove the
unneeded vf->func_flags.

Fixes: 8eb992e876a8 ("bnxt_en: Update firmware interface spec to 1.7.6.2.")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.h       |  1 -
 drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c | 10 ++--------
 2 files changed, 2 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index cda7ba31095a..a61a5873ab0a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1058,7 +1058,6 @@ struct bnxt_vf_info {
 #define BNXT_VF_LINK_FORCED	0x4
 #define BNXT_VF_LINK_UP		0x8
 #define BNXT_VF_TRUST		0x10
-	u32	func_flags; /* func cfg flags */
 	u32	min_tx_rate;
 	u32	max_tx_rate;
 	void	*hwrm_cmd_req_addr;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index f6f3454d6059..1046b22220a3 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -85,11 +85,10 @@ int bnxt_set_vf_spoofchk(struct net_device *dev, int vf_id, bool setting)
 	if (old_setting == setting)
 		return 0;
 
-	func_flags = vf->func_flags;
 	if (setting)
-		func_flags |= FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_ENABLE;
+		func_flags = FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_ENABLE;
 	else
-		func_flags |= FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_DISABLE;
+		func_flags = FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_DISABLE;
 	/*TODO: if the driver supports VLAN filter on guest VLAN,
 	 * the spoof check should also include vlan anti-spoofing
 	 */
@@ -98,7 +97,6 @@ int bnxt_set_vf_spoofchk(struct net_device *dev, int vf_id, bool setting)
 	req.flags = cpu_to_le32(func_flags);
 	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 	if (!rc) {
-		vf->func_flags = func_flags;
 		if (setting)
 			vf->flags |= BNXT_VF_SPOOFCHK;
 		else
@@ -230,7 +228,6 @@ int bnxt_set_vf_mac(struct net_device *dev, int vf_id, u8 *mac)
 	memcpy(vf->mac_addr, mac, ETH_ALEN);
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1);
 	req.fid = cpu_to_le16(vf->fw_fid);
-	req.flags = cpu_to_le32(vf->func_flags);
 	req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_MAC_ADDR);
 	memcpy(req.dflt_mac_addr, mac, ETH_ALEN);
 	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
@@ -268,7 +265,6 @@ int bnxt_set_vf_vlan(struct net_device *dev, int vf_id, u16 vlan_id, u8 qos,
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1);
 	req.fid = cpu_to_le16(vf->fw_fid);
-	req.flags = cpu_to_le32(vf->func_flags);
 	req.dflt_vlan = cpu_to_le16(vlan_tag);
 	req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_VLAN);
 	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
@@ -307,7 +303,6 @@ int bnxt_set_vf_bw(struct net_device *dev, int vf_id, int min_tx_rate,
 		return 0;
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1);
 	req.fid = cpu_to_le16(vf->fw_fid);
-	req.flags = cpu_to_le32(vf->func_flags);
 	req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_MAX_BW);
 	req.max_bw = cpu_to_le32(max_tx_rate);
 	req.enables |= cpu_to_le32(FUNC_CFG_REQ_ENABLES_MIN_BW);
@@ -479,7 +474,6 @@ static void __bnxt_set_vf_params(struct bnxt *bp, int vf_id)
 	vf = &bp->pf.vf[vf_id];
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1);
 	req.fid = cpu_to_le16(vf->fw_fid);
-	req.flags = cpu_to_le32(vf->func_flags);
 
 	if (is_valid_ether_addr(vf->mac_addr)) {
 		req.enables |= cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_MAC_ADDR);
-- 
2.26.2


From e45f97b05af21dc94adf8e0dbca338d37cdd4cf2 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Sun, 26 Apr 2020 16:24:39 -0400
Subject: [PATCH 23/31] bnxt_en: Reduce BNXT_MSIX_VEC_MAX value to supported
 CQs per PF.

[ Upstream commit 9e68cb0359b20f99c7b070f1d3305e5e0a9fae6d ]

Broadcom adapters support only maximum of 512 CQs per PF. If user sets
MSIx vectors more than supported CQs, firmware is setting incorrect value
for msix_vec_per_pf_max parameter. Fix it by reducing the BNXT_MSIX_VEC_MAX
value to 512, even though the maximum # of MSIx vectors supported by adapter
are 1280.

Fixes: f399e8497826 ("bnxt_en: Use msix_vec_per_pf_max and msix_vec_per_pf_min devlink params.")
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
index 689c47ab2155..ba94edec9fb8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
@@ -39,7 +39,7 @@ static inline void bnxt_link_bp_to_dl(struct bnxt *bp, struct devlink *dl)
 #define NVM_OFF_DIS_GRE_VER_CHECK	171
 #define NVM_OFF_ENABLE_SRIOV		401
 
-#define BNXT_MSIX_VEC_MAX	1280
+#define BNXT_MSIX_VEC_MAX	512
 #define BNXT_MSIX_VEC_MIN_MAX	128
 
 enum bnxt_nvm_dir_type {
-- 
2.26.2


From 643bea05a466c9156bbbad9f397a994d9fed069e Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 26 Apr 2020 16:24:40 -0400
Subject: [PATCH 24/31] bnxt_en: Improve AER slot reset.

[ Upstream commit bae361c54fb6ac6eba3b4762f49ce14beb73ef13 ]

Improve the slot reset sequence by disabling the device to prevent bad
DMAs if slot reset fails.  Return the proper result instead of always
PCI_ERS_RESULT_RECOVERED to the caller.

Fixes: 6316ea6db93d ("bnxt_en: Enable AER support.")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 6862594b49ab..cc49312744ed 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -12066,12 +12066,15 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev)
 		}
 	}
 
-	if (result != PCI_ERS_RESULT_RECOVERED && netif_running(netdev))
-		dev_close(netdev);
+	if (result != PCI_ERS_RESULT_RECOVERED) {
+		if (netif_running(netdev))
+			dev_close(netdev);
+		pci_disable_device(pdev);
+	}
 
 	rtnl_unlock();
 
-	return PCI_ERS_RESULT_RECOVERED;
+	return result;
 }
 
 /**
-- 
2.26.2


From 292aa3c88dc5d0d085b0b6ca63c6e0367af96efd Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 26 Apr 2020 16:24:41 -0400
Subject: [PATCH 25/31] bnxt_en: Return error when allocating zero size context
 memory.

[ Upstream commit bbf211b1ecb891c7e0cc7888834504183fc8b534 ]

bnxt_alloc_ctx_pg_tbls() should return error when the memory size of the
context memory to set up is zero.  By returning success (0), the caller
may proceed normally and may crash later when it tries to set up the
memory.

Fixes: 08fe9d181606 ("bnxt_en: Add Level 2 context memory paging support.")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index cc49312744ed..0c863773ae7f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -6649,7 +6649,7 @@ static int bnxt_alloc_ctx_pg_tbls(struct bnxt *bp,
 	int rc;
 
 	if (!mem_size)
-		return 0;
+		return -EINVAL;
 
 	ctx_pg->nr_pages = DIV_ROUND_UP(mem_size, BNXT_PAGE_SIZE);
 	if (ctx_pg->nr_pages > MAX_CTX_TOTAL_PAGES) {
-- 
2.26.2


From e5586c7eab2cd6c9ae038cd325293f10a3283f4f Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 26 Apr 2020 16:24:42 -0400
Subject: [PATCH 26/31] bnxt_en: Fix VLAN acceleration handling in
 bnxt_fix_features().

[ Upstream commit c72cb303aa6c2ae7e4184f0081c6d11bf03fb96b ]

The current logic in bnxt_fix_features() will inadvertently turn on both
CTAG and STAG VLAN offload if the user tries to disable both.  Fix it
by checking that the user is trying to enable CTAG or STAG before
enabling both.  The logic is supposed to enable or disable both CTAG and
STAG together.

Fixes: 5a9f6b238e59 ("bnxt_en: Enable and disable RX CTAG and RX STAG VLAN acceleration together.")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 0c863773ae7f..edf8452a2574 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -9755,6 +9755,7 @@ static netdev_features_t bnxt_fix_features(struct net_device *dev,
 					   netdev_features_t features)
 {
 	struct bnxt *bp = netdev_priv(dev);
+	netdev_features_t vlan_features;
 
 	if ((features & NETIF_F_NTUPLE) && !bnxt_rfs_capable(bp))
 		features &= ~NETIF_F_NTUPLE;
@@ -9771,12 +9772,14 @@ static netdev_features_t bnxt_fix_features(struct net_device *dev,
 	/* Both CTAG and STAG VLAN accelaration on the RX side have to be
 	 * turned on or off together.
 	 */
-	if ((features & (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX)) !=
-	    (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX)) {
+	vlan_features = features & (NETIF_F_HW_VLAN_CTAG_RX |
+				    NETIF_F_HW_VLAN_STAG_RX);
+	if (vlan_features != (NETIF_F_HW_VLAN_CTAG_RX |
+			      NETIF_F_HW_VLAN_STAG_RX)) {
 		if (dev->features & NETIF_F_HW_VLAN_CTAG_RX)
 			features &= ~(NETIF_F_HW_VLAN_CTAG_RX |
 				      NETIF_F_HW_VLAN_STAG_RX);
-		else
+		else if (vlan_features)
 			features |= NETIF_F_HW_VLAN_CTAG_RX |
 				    NETIF_F_HW_VLAN_STAG_RX;
 	}
-- 
2.26.2


From 07a4a1fdc5af8ef1c2d2abc0963fa449201f94a6 Mon Sep 17 00:00:00 2001
From: Erez Shitrit <erezsh@mellanox.com>
Date: Wed, 25 Mar 2020 17:19:43 +0200
Subject: [PATCH 27/31] net/mlx5: DR, On creation set CQ's arm_db member to
 right value

[ Upstream commit 8075411d93b6efe143d9f606f6531077795b7fbf ]

In polling mode, set arm_db member to a value that will avoid CQ
event recovery by the HW.
Otherwise we might get event without completion function.
In addition,empty completion function to was added to protect from
unexpected events.

Fixes: 297cccebdc5a ("net/mlx5: DR, Expose an internal API to issue RDMA operations")
Signed-off-by: Erez Shitrit <erezsh@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../ethernet/mellanox/mlx5/core/steering/dr_send.c | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
index 095ec7b1399d..7c77378accf0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
@@ -689,6 +689,12 @@ static void dr_cq_event(struct mlx5_core_cq *mcq,
 	pr_info("CQ event %u on CQ #%u\n", event, mcq->cqn);
 }
 
+static void dr_cq_complete(struct mlx5_core_cq *mcq,
+			   struct mlx5_eqe *eqe)
+{
+	pr_err("CQ completion CQ: #%u\n", mcq->cqn);
+}
+
 static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev,
 				      struct mlx5_uars_page *uar,
 				      size_t ncqe)
@@ -750,6 +756,7 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev,
 	mlx5_fill_page_frag_array(&cq->wq_ctrl.buf, pas);
 
 	cq->mcq.event = dr_cq_event;
+	cq->mcq.comp  = dr_cq_complete;
 
 	err = mlx5_core_create_cq(mdev, &cq->mcq, in, inlen, out, sizeof(out));
 	kvfree(in);
@@ -761,7 +768,12 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev,
 	cq->mcq.set_ci_db = cq->wq_ctrl.db.db;
 	cq->mcq.arm_db = cq->wq_ctrl.db.db + 1;
 	*cq->mcq.set_ci_db = 0;
-	*cq->mcq.arm_db = 0;
+
+	/* set no-zero value, in order to avoid the HW to run db-recovery on
+	 * CQ that used in polling mode.
+	 */
+	*cq->mcq.arm_db = cpu_to_be32(2 << 28);
+
 	cq->mcq.vector = 0;
 	cq->mcq.irqn = irqn;
 	cq->mcq.uar = uar;
-- 
2.26.2


From c65a5d24f8cd6f09f540beff85736942ea70d03c Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Sun, 21 Jul 2019 08:40:13 +0300
Subject: [PATCH 28/31] net/mlx5: Fix forced completion access non initialized
 command entry

[ Upstream commit f3cb3cebe26ed4c8036adbd9448b372129d3c371 ]

mlx5_cmd_flush() will trigger forced completions to all valid command
entries. Triggered by an asynch event such as fast teardown it can
happen at any stage of the command, including command initialization.
It will trigger forced completion and that can lead to completion on an
uninitialized command entry.

Setting MLX5_CMD_ENT_STATE_PENDING_COMP only after command entry is
initialized will ensure force completion is treated only if command
entry is initialized.

Fixes: 73dd3a4839c1 ("net/mlx5: Avoid using pending command interface slots")
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index ea934cd02448..88f04babd9ae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -888,7 +888,6 @@ static void cmd_work_handler(struct work_struct *work)
 	}
 
 	cmd->ent_arr[ent->idx] = ent;
-	set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state);
 	lay = get_inst(cmd, ent->idx);
 	ent->lay = lay;
 	memset(lay, 0, sizeof(*lay));
@@ -910,6 +909,7 @@ static void cmd_work_handler(struct work_struct *work)
 
 	if (ent->callback)
 		schedule_delayed_work(&ent->cb_timeout_work, cb_timeout);
+	set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state);
 
 	/* Skip sending command to fw if internal error */
 	if (pci_channel_offline(dev->pdev) ||
-- 
2.26.2


From 7616bb3540b178e81e13bde6bbb4a97c3fcc7f8a Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Sun, 23 Feb 2020 03:27:41 +0200
Subject: [PATCH 29/31] net/mlx5: Fix command entry leak in Internal Error
 State

[ Upstream commit cece6f432cca9f18900463ed01b97a152a03600a ]

Processing commands by cmd_work_handler() while already in Internal
Error State will result in entry leak, since the handler process force
completion without doorbell. Forced completion doesn't release the entry
and event completion will never arrive, so entry should be released.

Fixes: 73dd3a4839c1 ("net/mlx5: Avoid using pending command interface slots")
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 88f04babd9ae..08048a2d7259 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -922,6 +922,10 @@ static void cmd_work_handler(struct work_struct *work)
 		MLX5_SET(mbox_out, ent->out, syndrome, drv_synd);
 
 		mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
+		/* no doorbell, no need to keep the entry */
+		free_ent(cmd, ent->idx);
+		if (ent->callback)
+			free_cmd(ent);
 		return;
 	}
 
-- 
2.26.2


From 007aa1b60eaabc5e04ec9a1989db7f9260a66914 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 6 May 2020 13:16:22 +0300
Subject: [PATCH 30/31] net: mvpp2: prevent buffer overflow in mvpp22_rss_ctx()

[ Upstream commit 39bd16df7c31bb8cf5dfd0c88e42abd5ae10029d ]

The "rss_context" variable comes from the user via  ethtool_get_rxfh().
It can be any u32 value except zero.  Eventually it gets passed to
mvpp22_rss_ctx() and if it is over MVPP22_N_RSS_TABLES (8) then it
results in an array overflow.

Fixes: 895586d5dc32 ("net: mvpp2: cls: Use RSS contexts to handle RSS tables")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index ef44c6979a31..373b8c832850 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -4319,6 +4319,8 @@ static int mvpp2_ethtool_get_rxfh_context(struct net_device *dev, u32 *indir,
 
 	if (!mvpp22_rss_is_supported())
 		return -EOPNOTSUPP;
+	if (rss_context >= MVPP22_N_RSS_TABLES)
+		return -EINVAL;
 
 	if (hfunc)
 		*hfunc = ETH_RSS_HASH_CRC32;
-- 
2.26.2


From b80071993b4f20a86a0ece78390753246f0f8cf2 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 6 May 2020 13:16:56 +0300
Subject: [PATCH 31/31] net: mvpp2: cls: Prevent buffer overflow in
 mvpp2_ethtool_cls_rule_del()

[ Upstream commit 722c0f00d4feea77475a5dc943b53d60824a1e4e ]

The "info->fs.location" is a u32 that comes from the user via the
ethtool_set_rxnfc() function.  We need to check for invalid values to
prevent a buffer overflow.

I copy and pasted this check from the mvpp2_ethtool_cls_rule_ins()
function.

Fixes: 90b509b39ac9 ("net: mvpp2: cls: Add Classification offload support")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
index 35478cba2aa5..4344a59c823f 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
@@ -1422,6 +1422,9 @@ int mvpp2_ethtool_cls_rule_del(struct mvpp2_port *port,
 	struct mvpp2_ethtool_fs *efs;
 	int ret;
 
+	if (info->fs.location >= MVPP2_N_RFS_ENTRIES_PER_FLOW)
+		return -EINVAL;
+
 	efs = port->rfs_rules[info->fs.location];
 	if (!efs)
 		return -EINVAL;
-- 
2.26.2


[-- Attachment #3: net_56.mbox --]
[-- Type: Application/Octet-Stream, Size: 96044 bytes --]

From 940f04c53675ac5d089d08e9d6dfa763148eb9ce Mon Sep 17 00:00:00 2001
From: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Date: Thu, 30 Apr 2020 00:22:19 +0530
Subject: [PATCH 01/44] cxgb4: fix EOTID leak when disabling TC-MQPRIO offload

[ Upstream commit 69422a7e5d578aab277091f4ebb7c1b387f3e355 ]

Under heavy load, the EOTID termination FLOWC request fails to get
enqueued to the end of the Tx ring due to lack of credits. This
results in EOTID leak.

When disabling TC-MQPRIO offload, the link is already brought down
to cleanup EOTIDs. So, flush any pending enqueued skbs that can't be
sent outside the wire, to make room for FLOWC request. Also, move the
FLOWC descriptor consumption logic closer to when the FLOWC request is
actually posted to hardware.

Fixes: 0e395b3cb1fb ("cxgb4: add FLOWC based QoS offload")
Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/sge.c | 39 ++++++++++++++++++++++--
 1 file changed, 36 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index cab3d17e0e1a..d6eebd640753 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -2202,6 +2202,9 @@ static void ethofld_hard_xmit(struct net_device *dev,
 	if (unlikely(skip_eotx_wr)) {
 		start = (u64 *)wr;
 		eosw_txq->state = next_state;
+		eosw_txq->cred -= wrlen16;
+		eosw_txq->ncompl++;
+		eosw_txq->last_compl = 0;
 		goto write_wr_headers;
 	}
 
@@ -2360,6 +2363,34 @@ netdev_tx_t t4_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	return cxgb4_eth_xmit(skb, dev);
 }
 
+static void eosw_txq_flush_pending_skbs(struct sge_eosw_txq *eosw_txq)
+{
+	int pktcount = eosw_txq->pidx - eosw_txq->last_pidx;
+	int pidx = eosw_txq->pidx;
+	struct sk_buff *skb;
+
+	if (!pktcount)
+		return;
+
+	if (pktcount < 0)
+		pktcount += eosw_txq->ndesc;
+
+	while (pktcount--) {
+		pidx--;
+		if (pidx < 0)
+			pidx += eosw_txq->ndesc;
+
+		skb = eosw_txq->desc[pidx].skb;
+		if (skb) {
+			dev_consume_skb_any(skb);
+			eosw_txq->desc[pidx].skb = NULL;
+			eosw_txq->inuse--;
+		}
+	}
+
+	eosw_txq->pidx = eosw_txq->last_pidx + 1;
+}
+
 /**
  * cxgb4_ethofld_send_flowc - Send ETHOFLD flowc request to bind eotid to tc.
  * @dev - netdevice
@@ -2435,9 +2466,11 @@ int cxgb4_ethofld_send_flowc(struct net_device *dev, u32 eotid, u32 tc)
 					    FW_FLOWC_MNEM_EOSTATE_CLOSING :
 					    FW_FLOWC_MNEM_EOSTATE_ESTABLISHED);
 
-	eosw_txq->cred -= len16;
-	eosw_txq->ncompl++;
-	eosw_txq->last_compl = 0;
+	/* Free up any pending skbs to ensure there's room for
+	 * termination FLOWC.
+	 */
+	if (tc == FW_SCHED_CLS_NONE)
+		eosw_txq_flush_pending_skbs(eosw_txq);
 
 	ret = eosw_txq_enqueue(eosw_txq, skb);
 	if (ret) {
-- 
2.26.2


From 5718d1071b75a0a20bc7f31e3232667ec7545d77 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Mon, 4 May 2020 11:27:46 +0300
Subject: [PATCH 02/44] devlink: Fix reporter's recovery condition

[ Upstream commit bea0c5c942d3b4e9fb6ed45f6a7de74c6b112437 ]

Devlink health core conditions the reporter's recovery with the
expiration of the grace period. This is not relevant for the first
recovery. Explicitly demand that the grace period will only apply to
recoveries other than the first.

Fixes: c8e1da0bf923 ("devlink: Add health report functionality")
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/devlink.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/core/devlink.c b/net/core/devlink.c
index b831c5545d6a..fb0c17fdf525 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -5029,6 +5029,7 @@ int devlink_health_report(struct devlink_health_reporter *reporter,
 {
 	enum devlink_health_reporter_state prev_health_state;
 	struct devlink *devlink = reporter->devlink;
+	unsigned long recover_ts_threshold;
 
 	/* write a log message of the current error */
 	WARN_ON(!msg);
@@ -5039,10 +5040,12 @@ int devlink_health_report(struct devlink_health_reporter *reporter,
 	devlink_recover_notify(reporter, DEVLINK_CMD_HEALTH_REPORTER_RECOVER);
 
 	/* abort if the previous error wasn't recovered */
+	recover_ts_threshold = reporter->last_recovery_ts +
+			       msecs_to_jiffies(reporter->graceful_period);
 	if (reporter->auto_recover &&
 	    (prev_health_state != DEVLINK_HEALTH_REPORTER_STATE_HEALTHY ||
-	     jiffies - reporter->last_recovery_ts <
-	     msecs_to_jiffies(reporter->graceful_period))) {
+	     (reporter->last_recovery_ts && reporter->recovery_count &&
+	      time_is_after_jiffies(recover_ts_threshold)))) {
 		trace_devlink_health_recover_aborted(devlink,
 						     reporter->ops->name,
 						     reporter->health_state,
-- 
2.26.2


From 8ecd94af63c01b9626d19a46cb3263fded353ca3 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 28 Apr 2020 19:01:58 -0700
Subject: [PATCH 03/44] devlink: fix return value after hitting end in region
 read

[ Upstream commit 610a9346c138b9c2c93d38bf5f3728e74ae9cbd5 ]

Commit d5b90e99e1d5 ("devlink: report 0 after hitting end in region read")
fixed region dump, but region read still returns a spurious error:

$ devlink region read netdevsim/netdevsim1/dummy snapshot 0 addr 0 len 128
0000000000000000 a6 f4 c4 1c 21 35 95 a6 9d 34 c3 5b 87 5b 35 79
0000000000000010 f3 a0 d7 ee 4f 2f 82 7f c6 dd c4 f6 a5 c3 1b ae
0000000000000020 a4 fd c8 62 07 59 48 03 70 3b c7 09 86 88 7f 68
0000000000000030 6f 45 5d 6d 7d 0e 16 38 a9 d0 7a 4b 1e 1e 2e a6
0000000000000040 e6 1d ae 06 d6 18 00 85 ca 62 e8 7e 11 7e f6 0f
0000000000000050 79 7e f7 0f f3 94 68 bd e6 40 22 85 b6 be 6f b1
0000000000000060 af db ef 5e 34 f0 98 4b 62 9a e3 1b 8b 93 fc 17
devlink answers: Invalid argument
0000000000000070 61 e8 11 11 66 10 a5 f7 b1 ea 8d 40 60 53 ed 12

This is a minimal fix, I'll follow up with a restructuring
so we don't have two checks for the same condition.

Fixes: fdd41ec21e15 ("devlink: Return right error code in case of errors for region read")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/devlink.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/core/devlink.c b/net/core/devlink.c
index fb0c17fdf525..b4e26b702352 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -4030,6 +4030,11 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
 		end_offset = nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]);
 		end_offset += nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]);
 		dump = false;
+
+		if (start_offset == end_offset) {
+			err = 0;
+			goto nla_put_failure;
+		}
 	}
 
 	err = devlink_nl_region_read_snapshot_fill(skb, devlink,
-- 
2.26.2


From 231332be76b3e23d54e453e6cba2dc31a08a7e70 Mon Sep 17 00:00:00 2001
From: Julia Lawall <Julia.Lawall@inria.fr>
Date: Thu, 30 Apr 2020 21:51:32 +0200
Subject: [PATCH 04/44] dp83640: reverse arguments to list_add_tail

[ Upstream commit 865308373ed49c9fb05720d14cbf1315349b32a9 ]

In this code, it appears that phyter_clocks is a list head, based on
the previous list_for_each, and that clock->list is intended to be a
list element, given that it has just been initialized in
dp83640_clock_init.  Accordingly, switch the arguments to
list_add_tail, which takes the list head as the second argument.

Fixes: cb646e2b02b27 ("ptp: Added a clock driver for the National Semiconductor PHYTER.")
Signed-off-by: Julia Lawall <Julia.Lawall@inria.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/dp83640.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index ac72a324fcd1..b1d771325c57 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -1120,7 +1120,7 @@ static struct dp83640_clock *dp83640_clock_get_bus(struct mii_bus *bus)
 		goto out;
 	}
 	dp83640_clock_init(clock, bus);
-	list_add_tail(&phyter_clocks, &clock->list);
+	list_add_tail(&clock->list, &phyter_clocks);
 out:
 	mutex_unlock(&phyter_clocks_lock);
 
-- 
2.26.2


From 5d5e76431bcef068b84680d50262ae2b43a1788c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 25 Apr 2020 12:40:25 -0700
Subject: [PATCH 05/44] fq_codel: fix TCA_FQ_CODEL_DROP_BATCH_SIZE sanity
 checks
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 14695212d4cd8b0c997f6121b6df8520038ce076 ]

My intent was to not let users set a zero drop_batch_size,
it seems I once again messed with min()/max().

Fixes: 9d18562a2278 ("fq_codel: add batch ability to fq_codel_drop()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_fq_codel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 968519ff36e9..436160be9c18 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -416,7 +416,7 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt,
 		q->quantum = max(256U, nla_get_u32(tb[TCA_FQ_CODEL_QUANTUM]));
 
 	if (tb[TCA_FQ_CODEL_DROP_BATCH_SIZE])
-		q->drop_batch_size = min(1U, nla_get_u32(tb[TCA_FQ_CODEL_DROP_BATCH_SIZE]));
+		q->drop_batch_size = max(1U, nla_get_u32(tb[TCA_FQ_CODEL_DROP_BATCH_SIZE]));
 
 	if (tb[TCA_FQ_CODEL_MEMORY_LIMIT])
 		q->memory_limit = min(1U << 31, nla_get_u32(tb[TCA_FQ_CODEL_MEMORY_LIMIT]));
-- 
2.26.2


From 35f918d3066bb86d80eaa8d1756d81c25256dbff Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@kernel.org>
Date: Fri, 1 May 2020 08:53:08 -0600
Subject: [PATCH 06/44] ipv6: Use global sernum for dst validation with nexthop
 objects

[ Upstream commit 8f34e53b60b337e559f1ea19e2780ff95ab2fa65 ]

Nik reported a bug with pcpu dst cache when nexthop objects are
used illustrated by the following:
    $ ip netns add foo
    $ ip -netns foo li set lo up
    $ ip -netns foo addr add 2001:db8:11::1/128 dev lo
    $ ip netns exec foo sysctl net.ipv6.conf.all.forwarding=1
    $ ip li add veth1 type veth peer name veth2
    $ ip li set veth1 up
    $ ip addr add 2001:db8:10::1/64 dev veth1
    $ ip li set dev veth2 netns foo
    $ ip -netns foo li set veth2 up
    $ ip -netns foo addr add 2001:db8:10::2/64 dev veth2
    $ ip -6 nexthop add id 100 via 2001:db8:10::2 dev veth1
    $ ip -6 route add 2001:db8:11::1/128 nhid 100

    Create a pcpu entry on cpu 0:
    $ taskset -a -c 0 ip -6 route get 2001:db8:11::1

    Re-add the route entry:
    $ ip -6 ro del 2001:db8:11::1
    $ ip -6 route add 2001:db8:11::1/128 nhid 100

    Route get on cpu 0 returns the stale pcpu:
    $ taskset -a -c 0 ip -6 route get 2001:db8:11::1
    RTNETLINK answers: Network is unreachable

    While cpu 1 works:
    $ taskset -a -c 1 ip -6 route get 2001:db8:11::1
    2001:db8:11::1 from :: via 2001:db8:10::2 dev veth1 src 2001:db8:10::1 metric 1024 pref medium

Conversion of FIB entries to work with external nexthop objects
missed an important difference between IPv4 and IPv6 - how dst
entries are invalidated when the FIB changes. IPv4 has a per-network
namespace generation id (rt_genid) that is bumped on changes to the FIB.
Checking if a dst_entry is still valid means comparing rt_genid in the
rtable to the current value of rt_genid for the namespace.

IPv6 also has a per network namespace counter, fib6_sernum, but the
count is saved per fib6_node. With the per-node counter only dst_entries
based on fib entries under the node are invalidated when changes are
made to the routes - limiting the scope of invalidations. IPv6 uses a
reference in the rt6_info, 'from', to track the corresponding fib entry
used to create the dst_entry. When validating a dst_entry, the 'from'
is used to backtrack to the fib6_node and check the sernum of it to the
cookie passed to the dst_check operation.

With the inline format (nexthop definition inline with the fib6_info),
dst_entries cached in the fib6_nh have a 1:1 correlation between fib
entries, nexthop data and dst_entries. With external nexthops, IPv6
looks more like IPv4 which means multiple fib entries across disparate
fib6_nodes can all reference the same fib6_nh. That means validation
of dst_entries based on external nexthops needs to use the IPv4 format
- the per-network namespace counter.

Add sernum to rt6_info and set it when creating a pcpu dst entry. Update
rt6_get_cookie to return sernum if it is set and update dst_check for
IPv6 to look for sernum set and based the check on it if so. Finally,
rt6_get_pcpu_route needs to validate the cached entry before returning
a pcpu entry (similar to the rt_cache_valid calls in __mkroute_input and
__mkroute_output for IPv4).

This problem only affects routes using the new, external nexthops.

Thanks to the kbuild test robot for catching the IS_ENABLED needed
around rt_genid_ipv6 before I sent this out.

Fixes: 5b98324ebe29 ("ipv6: Allow routes to use nexthop objects")
Reported-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Tested-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h       |  4 ++++
 include/net/net_namespace.h |  7 +++++++
 net/ipv6/route.c            | 25 +++++++++++++++++++++++++
 3 files changed, 36 insertions(+)

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index fd60a8ac02ee..98ec56e2fae2 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -204,6 +204,7 @@ struct fib6_info {
 struct rt6_info {
 	struct dst_entry		dst;
 	struct fib6_info __rcu		*from;
+	int				sernum;
 
 	struct rt6key			rt6i_dst;
 	struct rt6key			rt6i_src;
@@ -292,6 +293,9 @@ static inline u32 rt6_get_cookie(const struct rt6_info *rt)
 	struct fib6_info *from;
 	u32 cookie = 0;
 
+	if (rt->sernum)
+		return rt->sernum;
+
 	rcu_read_lock();
 
 	from = rcu_dereference(rt->from);
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 854d39ef1ca3..9cdb67e3a553 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -432,6 +432,13 @@ static inline int rt_genid_ipv4(const struct net *net)
 	return atomic_read(&net->ipv4.rt_genid);
 }
 
+#if IS_ENABLED(CONFIG_IPV6)
+static inline int rt_genid_ipv6(const struct net *net)
+{
+	return atomic_read(&net->ipv6.fib6_sernum);
+}
+#endif
+
 static inline void rt_genid_bump_ipv4(struct net *net)
 {
 	atomic_inc(&net->ipv4.rt_genid);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 2931224b674e..42d0596dd398 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1388,9 +1388,18 @@ static struct rt6_info *ip6_rt_pcpu_alloc(const struct fib6_result *res)
 	}
 	ip6_rt_copy_init(pcpu_rt, res);
 	pcpu_rt->rt6i_flags |= RTF_PCPU;
+
+	if (f6i->nh)
+		pcpu_rt->sernum = rt_genid_ipv6(dev_net(dev));
+
 	return pcpu_rt;
 }
 
+static bool rt6_is_valid(const struct rt6_info *rt6)
+{
+	return rt6->sernum == rt_genid_ipv6(dev_net(rt6->dst.dev));
+}
+
 /* It should be called with rcu_read_lock() acquired */
 static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res)
 {
@@ -1398,6 +1407,19 @@ static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res)
 
 	pcpu_rt = this_cpu_read(*res->nh->rt6i_pcpu);
 
+	if (pcpu_rt && pcpu_rt->sernum && !rt6_is_valid(pcpu_rt)) {
+		struct rt6_info *prev, **p;
+
+		p = this_cpu_ptr(res->nh->rt6i_pcpu);
+		prev = xchg(p, NULL);
+		if (prev) {
+			dst_dev_put(&prev->dst);
+			dst_release(&prev->dst);
+		}
+
+		pcpu_rt = NULL;
+	}
+
 	return pcpu_rt;
 }
 
@@ -2596,6 +2618,9 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
 
 	rt = container_of(dst, struct rt6_info, dst);
 
+	if (rt->sernum)
+		return rt6_is_valid(rt) ? dst : NULL;
+
 	rcu_read_lock();
 
 	/* All IPV6 dsts are created with ->obsolete set to the value
-- 
2.26.2


From bfef034218d8191d9e1d633f3c1cfbdf029e71aa Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Mon, 27 Apr 2020 18:05:47 +0300
Subject: [PATCH 07/44] mlxsw: spectrum_acl_tcam: Position vchunk in a vregion
 list properly

[ Upstream commit 6ef4889fc0b3aa6ab928e7565935ac6f762cee6e ]

Vregion helpers to get min and max priority depend on the correct
ordering of vchunks in the vregion list. However, the current code
always adds new chunk to the end of the list, no matter what the
priority is. Fix this by finding the correct place in the list and put
vchunk there.

Fixes: 22a677661f56 ("mlxsw: spectrum: Introduce ACL core with simple TCAM implementation")
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c  | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index e993159e8e4c..295b27112d36 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -986,8 +986,9 @@ mlxsw_sp_acl_tcam_vchunk_create(struct mlxsw_sp *mlxsw_sp,
 				unsigned int priority,
 				struct mlxsw_afk_element_usage *elusage)
 {
+	struct mlxsw_sp_acl_tcam_vchunk *vchunk, *vchunk2;
 	struct mlxsw_sp_acl_tcam_vregion *vregion;
-	struct mlxsw_sp_acl_tcam_vchunk *vchunk;
+	struct list_head *pos;
 	int err;
 
 	if (priority == MLXSW_SP_ACL_TCAM_CATCHALL_PRIO)
@@ -1025,7 +1026,14 @@ mlxsw_sp_acl_tcam_vchunk_create(struct mlxsw_sp *mlxsw_sp,
 	}
 
 	mlxsw_sp_acl_tcam_rehash_ctx_vregion_changed(vregion);
-	list_add_tail(&vchunk->list, &vregion->vchunk_list);
+
+	/* Position the vchunk inside the list according to priority */
+	list_for_each(pos, &vregion->vchunk_list) {
+		vchunk2 = list_entry(pos, typeof(*vchunk2), list);
+		if (vchunk2->priority > priority)
+			break;
+	}
+	list_add_tail(&vchunk->list, pos);
 	mutex_unlock(&vregion->lock);
 
 	return vchunk;
-- 
2.26.2


From c10a451fcda4177220ea1f9893dc04ac18878a85 Mon Sep 17 00:00:00 2001
From: Roman Mashak <mrv@mojatatu.com>
Date: Fri, 1 May 2020 21:34:18 -0400
Subject: [PATCH 08/44] neigh: send protocol value in neighbor create
 notification

[ Upstream commit 38212bb31fe923d0a2c6299bd2adfbb84cddef2a ]

When a new neighbor entry has been added, event is generated but it does not
include protocol, because its value is assigned after the event notification
routine has run, so move protocol assignment code earlier.

Fixes: df9b0e30d44c ("neighbor: Add protocol attribute")
Cc: David Ahern <dsahern@gmail.com>
Signed-off-by: Roman Mashak <mrv@mojatatu.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 789a73aa7bd8..04953e5f2530 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1954,6 +1954,9 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 				   NEIGH_UPDATE_F_OVERRIDE_ISROUTER);
 	}
 
+	if (protocol)
+		neigh->protocol = protocol;
+
 	if (ndm->ndm_flags & NTF_EXT_LEARNED)
 		flags |= NEIGH_UPDATE_F_EXT_LEARNED;
 
@@ -1967,9 +1970,6 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 		err = __neigh_update(neigh, lladdr, ndm->ndm_state, flags,
 				     NETLINK_CB(skb).portid, extack);
 
-	if (protocol)
-		neigh->protocol = protocol;
-
 	neigh_release(neigh);
 
 out:
-- 
2.26.2


From 23cd56cb584e45c6427c3e9f2f63de2f15177c2d Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Thu, 30 Apr 2020 22:38:45 +0300
Subject: [PATCH 09/44] net: bridge: vlan: Add a schedule point during VLAN
 processing

[ Upstream commit 7979457b1d3a069cd857f5bd69e070e30223dd0c ]

User space can request to delete a range of VLANs from a bridge slave in
one netlink request. For each deleted VLAN the FDB needs to be traversed
in order to flush all the affected entries.

If a large range of VLANs is deleted and the number of FDB entries is
large or the FDB lock is contented, it is possible for the kernel to
loop through the deleted VLANs for a long time. In case preemption is
disabled, this can result in a soft lockup.

Fix this by adding a schedule point after each VLAN is deleted to yield
the CPU, if needed. This is safe because the VLANs are traversed in
process context.

Fixes: bdced7ef7838 ("bridge: support for multiple vlans and vlan ranges in setlink and dellink requests")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Stefan Priebe - Profihost AG <s.priebe@profihost.ag>
Tested-by: Stefan Priebe - Profihost AG <s.priebe@profihost.ag>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_netlink.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 43dab4066f91..a0f5dbee8f9c 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -612,6 +612,7 @@ int br_process_vlan_info(struct net_bridge *br,
 					       v - 1, rtm_cmd);
 				v_change_start = 0;
 			}
+			cond_resched();
 		}
 		/* v_change_start is set only if the last/whole range changed */
 		if (v_change_start)
-- 
2.26.2


From 54f918a24f7a4c29802f9a1463745a684ef944c9 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Mon, 4 May 2020 13:18:06 -0700
Subject: [PATCH 10/44] net: dsa: Do not leave DSA master with NULL netdev_ops

[ Upstream commit 050569fc8384c8056bacefcc246bcb2dfe574936 ]

When ndo_get_phys_port_name() for the CPU port was added we introduced
an early check for when the DSA master network device in
dsa_master_ndo_setup() already implements ndo_get_phys_port_name(). When
we perform the teardown operation in dsa_master_ndo_teardown() we would
not be checking that cpu_dp->orig_ndo_ops was successfully allocated and
non-NULL initialized.

With network device drivers such as virtio_net, this leads to a NPD as
soon as the DSA switch hanging off of it gets torn down because we are
now assigning the virtio_net device's netdev_ops a NULL pointer.

Fixes: da7b9e9b00d4 ("net: dsa: Add ndo_get_phys_port_name() for CPU port")
Reported-by: Allen Pais <allen.pais@oracle.com>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Tested-by: Allen Pais <allen.pais@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/master.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/dsa/master.c b/net/dsa/master.c
index bd44bde272f4..4f5219e2e63c 100644
--- a/net/dsa/master.c
+++ b/net/dsa/master.c
@@ -289,7 +289,8 @@ static void dsa_master_ndo_teardown(struct net_device *dev)
 {
 	struct dsa_port *cpu_dp = dev->dsa_ptr;
 
-	dev->netdev_ops = cpu_dp->orig_ndo_ops;
+	if (cpu_dp->orig_ndo_ops)
+		dev->netdev_ops = cpu_dp->orig_ndo_ops;
 	cpu_dp->orig_ndo_ops = NULL;
 }
 
-- 
2.26.2


From 8de14ad1913f0ca62b3c8990e6c017fc5c94dac8 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Sun, 3 May 2020 20:50:57 -0700
Subject: [PATCH 11/44] net: dsa: Do not make user port errors fatal

[ Upstream commit 86f8b1c01a0a537a73d2996615133be63cdf75db ]

Prior to 1d27732f411d ("net: dsa: setup and teardown ports"), we would
not treat failures to set-up an user port as fatal, but after this
commit we would, which is a regression for some systems where interfaces
may be declared in the Device Tree, but the underlying hardware may not
be present (pluggable daughter cards for instance).

Fixes: 1d27732f411d ("net: dsa: setup and teardown ports")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/dsa2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index e7c30b472034..154b639d27b8 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -459,7 +459,7 @@ static int dsa_tree_setup_switches(struct dsa_switch_tree *dst)
 	list_for_each_entry(dp, &dst->ports, list) {
 		err = dsa_port_setup(dp);
 		if (err)
-			goto teardown;
+			continue;
 	}
 
 	return 0;
-- 
2.26.2


From 5fc931b17894fefdd203373e46c4dc320f79991a Mon Sep 17 00:00:00 2001
From: Dejin Zheng <zhengdejin5@gmail.com>
Date: Sun, 3 May 2020 20:32:26 +0800
Subject: [PATCH 12/44] net: macb: fix an issue about leak related system
 resources

[ Upstream commit b959c77dac09348955f344104c6a921ebe104753 ]

A call of the function macb_init() can fail in the function
fu540_c000_init. The related system resources were not released
then. use devm_platform_ioremap_resource() to replace ioremap()
to fix it.

Fixes: c218ad559020ff9 ("macb: Add support for SiFive FU540-C000")
Cc: Andy Shevchenko <andy.shevchenko@gmail.com>
Reviewed-by: Yash Shah <yash.shah@sifive.com>
Suggested-by: Nicolas Ferre <nicolas.ferre@microchip.com>
Suggested-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Dejin Zheng <zhengdejin5@gmail.com>
Acked-by: Nicolas Ferre <nicolas.ferre@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index b3a51935e8e0..96dfb51de813 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -4159,15 +4159,9 @@ static int fu540_c000_clk_init(struct platform_device *pdev, struct clk **pclk,
 
 static int fu540_c000_init(struct platform_device *pdev)
 {
-	struct resource *res;
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-	if (!res)
-		return -ENODEV;
-
-	mgmt->reg = ioremap(res->start, resource_size(res));
-	if (!mgmt->reg)
-		return -ENOMEM;
+	mgmt->reg = devm_platform_ioremap_resource(pdev, 1);
+	if (IS_ERR(mgmt->reg))
+		return PTR_ERR(mgmt->reg);
 
 	return macb_init(pdev);
 }
-- 
2.26.2


From 48daedd3df13d588df3f46bdc1ede71ba2b8faef Mon Sep 17 00:00:00 2001
From: Scott Dial <scott@scottdial.com>
Date: Fri, 24 Apr 2020 18:51:08 -0400
Subject: [PATCH 13/44] net: macsec: preserve ingress frame ordering

[ Upstream commit ab046a5d4be4c90a3952a0eae75617b49c0cb01b ]

MACsec decryption always occurs in a softirq context. Since
the FPU may not be usable in the softirq context, the call to
decrypt may be scheduled on the cryptd work queue. The cryptd
work queue does not provide ordering guarantees. Therefore,
preserving order requires masking out ASYNC implementations
of gcm(aes).

For instance, an Intel CPU with AES-NI makes available the
generic-gcm-aesni driver from the aesni_intel module to
implement gcm(aes). However, this implementation requires
the FPU, so it is not always available to use from a softirq
context, and will fallback to the cryptd work queue, which
does not preserve frame ordering. With this change, such a
system would select gcm_base(ctr(aes-aesni),ghash-generic).
While the aes-aesni implementation prefers to use the FPU, it
will fallback to the aes-asm implementation if unavailable.

By using a synchronous version of gcm(aes), the decryption
will complete before returning from crypto_aead_decrypt().
Therefore, the macsec_decrypt_done() callback will be called
before returning from macsec_decrypt(). Thus, the order of
calls to macsec_post_decrypt() for the frames is preserved.

While it's presumable that the pure AES-NI version of gcm(aes)
is more performant, the hybrid solution is capable of gigabit
speeds on modest hardware. Regardless, preserving the order
of frames is paramount for many network protocols (e.g.,
triggering TCP retries). Within the MACsec driver itself, the
replay protection is tripped by the out-of-order frames, and
can cause frames to be dropped.

This bug has been present in this code since it was added in
v4.6, however it may not have been noticed since not all CPUs
have FPU offload available. Additionally, the bug manifests
as occasional out-of-order packets that are easily
misattributed to other network phenomena.

When this code was added in v4.6, the crypto/gcm.c code did
not restrict selection of the ghash function based on the
ASYNC flag. For instance, x86 CPUs with PCLMULQDQ would
select the ghash-clmulni driver instead of ghash-generic,
which submits to the cryptd work queue if the FPU is busy.
However, this bug was was corrected in v4.8 by commit
b30bdfa86431afbafe15284a3ad5ac19b49b88e3, and was backported
all the way back to the v3.14 stable branch, so this patch
should be applicable back to the v4.6 stable branch.

Signed-off-by: Scott Dial <scott@scottdial.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macsec.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 35aa7b0a2aeb..11028ef8be4e 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -1226,7 +1226,8 @@ static struct crypto_aead *macsec_alloc_tfm(char *key, int key_len, int icv_len)
 	struct crypto_aead *tfm;
 	int ret;
 
-	tfm = crypto_alloc_aead("gcm(aes)", 0, 0);
+	/* Pick a sync gcm(aes) cipher to ensure order is preserved. */
+	tfm = crypto_alloc_aead("gcm(aes)", 0, CRYPTO_ALG_ASYNC);
 
 	if (IS_ERR(tfm))
 		return tfm;
-- 
2.26.2


From 3a946e7208e34421be6fd572be83c736ff13666d Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Mon, 4 May 2020 11:36:02 +0300
Subject: [PATCH 14/44] net/mlx4_core: Fix use of ENOSPC around
 mlx4_counter_alloc()

[ Upstream commit 40e473071dbad04316ddc3613c3a3d1c75458299 ]

When ENOSPC is set the idx is still valid and gets set to the global
MLX4_SINK_COUNTER_INDEX.  However gcc's static analysis cannot tell that
ENOSPC is impossible from mlx4_cmd_imm() and gives this warning:

drivers/net/ethernet/mellanox/mlx4/main.c:2552:28: warning: 'idx' may be
used uninitialized in this function [-Wmaybe-uninitialized]
 2552 |    priv->def_counter[port] = idx;

Also, when ENOSPC is returned mlx4_allocate_default_counters should not
fail.

Fixes: 6de5f7f6a1fa ("net/mlx4_core: Allocate default counter per port")
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/main.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 5716c3d2bb86..c72c4e1ea383 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -2550,6 +2550,7 @@ static int mlx4_allocate_default_counters(struct mlx4_dev *dev)
 
 		if (!err || err == -ENOSPC) {
 			priv->def_counter[port] = idx;
+			err = 0;
 		} else if (err == -ENOENT) {
 			err = 0;
 			continue;
@@ -2600,7 +2601,8 @@ int mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx, u8 usage)
 				   MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
 		if (!err)
 			*idx = get_param_l(&out_param);
-
+		if (WARN_ON(err == -ENOSPC))
+			err = -EINVAL;
 		return err;
 	}
 	return __mlx4_counter_alloc(dev, idx);
-- 
2.26.2


From 75b6ecc4c05cff911c91d4fd2fed486302752e62 Mon Sep 17 00:00:00 2001
From: Baruch Siach <baruch@tkos.co.il>
Date: Sun, 26 Apr 2020 09:22:06 +0300
Subject: [PATCH 15/44] net: phy: marvell10g: fix temperature sensor on 2110

[ Upstream commit c3e302edca2457bbd0c958c445a7538fbf6a6ac8 ]

Read the temperature sensor register from the correct location for the
88E2110 PHY. There is no enable/disable bit on 2110, so make
mv3310_hwmon_config() run on 88X3310 only.

Fixes: 62d01535474b61 ("net: phy: marvell10g: add support for the 88x2110 PHY")
Cc: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Baruch Siach <baruch@tkos.co.il>
Reviewed-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/marvell10g.c | 27 ++++++++++++++++++++++++++-
 1 file changed, 26 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c
index 64c9f3bba2cd..e2658dace15d 100644
--- a/drivers/net/phy/marvell10g.c
+++ b/drivers/net/phy/marvell10g.c
@@ -44,6 +44,9 @@ enum {
 	MV_PCS_PAIRSWAP_AB	= 0x0002,
 	MV_PCS_PAIRSWAP_NONE	= 0x0003,
 
+	/* Temperature read register (88E2110 only) */
+	MV_PCS_TEMP		= 0x8042,
+
 	/* These registers appear at 0x800X and 0xa00X - the 0xa00X control
 	 * registers appear to set themselves to the 0x800X when AN is
 	 * restarted, but status registers appear readable from either.
@@ -54,6 +57,7 @@ enum {
 	/* Vendor2 MMD registers */
 	MV_V2_PORT_CTRL		= 0xf001,
 	MV_V2_PORT_CTRL_PWRDOWN = 0x0800,
+	/* Temperature control/read registers (88X3310 only) */
 	MV_V2_TEMP_CTRL		= 0xf08a,
 	MV_V2_TEMP_CTRL_MASK	= 0xc000,
 	MV_V2_TEMP_CTRL_SAMPLE	= 0x0000,
@@ -79,6 +83,24 @@ static umode_t mv3310_hwmon_is_visible(const void *data,
 	return 0;
 }
 
+static int mv3310_hwmon_read_temp_reg(struct phy_device *phydev)
+{
+	return phy_read_mmd(phydev, MDIO_MMD_VEND2, MV_V2_TEMP);
+}
+
+static int mv2110_hwmon_read_temp_reg(struct phy_device *phydev)
+{
+	return phy_read_mmd(phydev, MDIO_MMD_PCS, MV_PCS_TEMP);
+}
+
+static int mv10g_hwmon_read_temp_reg(struct phy_device *phydev)
+{
+	if (phydev->drv->phy_id == MARVELL_PHY_ID_88X3310)
+		return mv3310_hwmon_read_temp_reg(phydev);
+	else /* MARVELL_PHY_ID_88E2110 */
+		return mv2110_hwmon_read_temp_reg(phydev);
+}
+
 static int mv3310_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
 			     u32 attr, int channel, long *value)
 {
@@ -91,7 +113,7 @@ static int mv3310_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
 	}
 
 	if (type == hwmon_temp && attr == hwmon_temp_input) {
-		temp = phy_read_mmd(phydev, MDIO_MMD_VEND2, MV_V2_TEMP);
+		temp = mv10g_hwmon_read_temp_reg(phydev);
 		if (temp < 0)
 			return temp;
 
@@ -144,6 +166,9 @@ static int mv3310_hwmon_config(struct phy_device *phydev, bool enable)
 	u16 val;
 	int ret;
 
+	if (phydev->drv->phy_id != MARVELL_PHY_ID_88X3310)
+		return 0;
+
 	ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, MV_V2_TEMP,
 			    MV_V2_TEMP_UNKNOWN);
 	if (ret < 0)
-- 
2.26.2


From fa30765f917341017390436508368b6f4b60e54e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 2 May 2020 20:09:25 -0700
Subject: [PATCH 16/44] net_sched: sch_skbprio: add message validation to
 skbprio_change()

[ Upstream commit 2761121af87de45951989a0adada917837d8fa82 ]

Do not assume the attribute has the right size.

Fixes: aea5f654e6b7 ("net/sched: add skbprio scheduler")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_skbprio.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/sched/sch_skbprio.c b/net/sched/sch_skbprio.c
index 0fb10abf7579..7a5e4c454715 100644
--- a/net/sched/sch_skbprio.c
+++ b/net/sched/sch_skbprio.c
@@ -169,6 +169,9 @@ static int skbprio_change(struct Qdisc *sch, struct nlattr *opt,
 {
 	struct tc_skbprio_qopt *ctl = nla_data(opt);
 
+	if (opt->nla_len != nla_attr_size(sizeof(*ctl)))
+		return -EINVAL;
+
 	sch->limit = ctl->limit;
 	return 0;
 }
-- 
2.26.2


From 075cfd621e4e4b2ea925078a6870a5e5b551b559 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Mon, 4 May 2020 12:48:54 -0400
Subject: [PATCH 17/44] net: stricter validation of untrusted gso packets

[ Upstream commit 9274124f023b5c56dc4326637d4f787968b03607 ]

Syzkaller again found a path to a kernel crash through bad gso input:
a packet with transport header extending beyond skb_headlen(skb).

Tighten validation at kernel entry:

- Verify that the transport header lies within the linear section.

    To avoid pulling linux/tcp.h, verify just sizeof tcphdr.
    tcp_gso_segment will call pskb_may_pull (th->doff * 4) before use.

- Match the gso_type against the ip_proto found by the flow dissector.

Fixes: bfd5f4a3d605 ("packet: Add GSO/csum offload support.")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/virtio_net.h | 26 ++++++++++++++++++++++++--
 1 file changed, 24 insertions(+), 2 deletions(-)

diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 0d1fe9297ac6..6f6ade63b04c 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -3,6 +3,8 @@
 #define _LINUX_VIRTIO_NET_H
 
 #include <linux/if_vlan.h>
+#include <uapi/linux/tcp.h>
+#include <uapi/linux/udp.h>
 #include <uapi/linux/virtio_net.h>
 
 static inline int virtio_net_hdr_set_proto(struct sk_buff *skb,
@@ -28,17 +30,25 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 					bool little_endian)
 {
 	unsigned int gso_type = 0;
+	unsigned int thlen = 0;
+	unsigned int ip_proto;
 
 	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
 		switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
 		case VIRTIO_NET_HDR_GSO_TCPV4:
 			gso_type = SKB_GSO_TCPV4;
+			ip_proto = IPPROTO_TCP;
+			thlen = sizeof(struct tcphdr);
 			break;
 		case VIRTIO_NET_HDR_GSO_TCPV6:
 			gso_type = SKB_GSO_TCPV6;
+			ip_proto = IPPROTO_TCP;
+			thlen = sizeof(struct tcphdr);
 			break;
 		case VIRTIO_NET_HDR_GSO_UDP:
 			gso_type = SKB_GSO_UDP;
+			ip_proto = IPPROTO_UDP;
+			thlen = sizeof(struct udphdr);
 			break;
 		default:
 			return -EINVAL;
@@ -57,16 +67,22 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 
 		if (!skb_partial_csum_set(skb, start, off))
 			return -EINVAL;
+
+		if (skb_transport_offset(skb) + thlen > skb_headlen(skb))
+			return -EINVAL;
 	} else {
 		/* gso packets without NEEDS_CSUM do not set transport_offset.
 		 * probe and drop if does not match one of the above types.
 		 */
 		if (gso_type && skb->network_header) {
+			struct flow_keys_basic keys;
+
 			if (!skb->protocol)
 				virtio_net_hdr_set_proto(skb, hdr);
 retry:
-			skb_probe_transport_header(skb);
-			if (!skb_transport_header_was_set(skb)) {
+			if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys,
+							      NULL, 0, 0, 0,
+							      0)) {
 				/* UFO does not specify ipv4 or 6: try both */
 				if (gso_type & SKB_GSO_UDP &&
 				    skb->protocol == htons(ETH_P_IP)) {
@@ -75,6 +91,12 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 				}
 				return -EINVAL;
 			}
+
+			if (keys.control.thoff + thlen > skb_headlen(skb) ||
+			    keys.basic.ip_proto != ip_proto)
+				return -EINVAL;
+
+			skb_set_transport_header(skb, keys.control.thoff);
 		}
 	}
 
-- 
2.26.2


From 952ca14ab9402dd67c9bb3caa683f9fa0b8e31ce Mon Sep 17 00:00:00 2001
From: Anthony Felice <tony.felice@timesys.com>
Date: Sun, 26 Apr 2020 22:00:59 -0400
Subject: [PATCH 18/44] net: tc35815: Fix phydev supported/advertising mask

[ Upstream commit 4b5b71f770e2edefbfe74203777264bfe6a9927c ]

Commit 3c1bcc8614db ("net: ethernet: Convert phydev advertize and
supported from u32 to link mode") updated ethernet drivers to use a
linkmode bitmap. It mistakenly dropped a bitwise negation in the
tc35815 ethernet driver on a bitmask to set the supported/advertising
flags.

Found by Anthony via code inspection, not tested as I do not have the
required hardware.

Fixes: 3c1bcc8614db ("net: ethernet: Convert phydev advertize and supported from u32 to link mode")
Signed-off-by: Anthony Felice <tony.felice@timesys.com>
Reviewed-by: Akshay Bhat <akshay.bhat@timesys.com>
Reviewed-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/toshiba/tc35815.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/toshiba/tc35815.c b/drivers/net/ethernet/toshiba/tc35815.c
index 3fd43d30b20d..a1066fbb93b5 100644
--- a/drivers/net/ethernet/toshiba/tc35815.c
+++ b/drivers/net/ethernet/toshiba/tc35815.c
@@ -643,7 +643,7 @@ static int tc_mii_probe(struct net_device *dev)
 		linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, mask);
 		linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, mask);
 	}
-	linkmode_and(phydev->supported, phydev->supported, mask);
+	linkmode_andnot(phydev->supported, phydev->supported, mask);
 	linkmode_copy(phydev->advertising, phydev->supported);
 
 	lp->link = 0;
-- 
2.26.2


From 31c07905af5343e18f4f6c6cac0582f22fecb477 Mon Sep 17 00:00:00 2001
From: Xiyu Yang <xiyuyang19@fudan.edu.cn>
Date: Sat, 25 Apr 2020 20:54:37 +0800
Subject: [PATCH 19/44] net/tls: Fix sk_psock refcnt leak in
 bpf_exec_tx_verdict()

[ Upstream commit 095f5614bfe16e5b3e191b34ea41b10d6fdd4ced ]

bpf_exec_tx_verdict() invokes sk_psock_get(), which returns a reference
of the specified sk_psock object to "psock" with increased refcnt.

When bpf_exec_tx_verdict() returns, local variable "psock" becomes
invalid, so the refcount should be decreased to keep refcount balanced.

The reference counting issue happens in one exception handling path of
bpf_exec_tx_verdict(). When "policy" equals to NULL but "psock" is not
NULL, the function forgets to decrease the refcnt increased by
sk_psock_get(), causing a refcnt leak.

Fix this issue by calling sk_psock_put() on this error path before
bpf_exec_tx_verdict() returns.

Signed-off-by: Xiyu Yang <xiyuyang19@fudan.edu.cn>
Signed-off-by: Xin Tan <tanxin.ctf@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index c98e602a1a2d..704313dd082f 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -800,6 +800,8 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk,
 			*copied -= sk_msg_free(sk, msg);
 			tls_free_open_rec(sk);
 		}
+		if (psock)
+			sk_psock_put(sk, psock);
 		return err;
 	}
 more_data:
-- 
2.26.2


From e8fc68418140aa6b2c7eafbdddb2e43bdb561038 Mon Sep 17 00:00:00 2001
From: Xiyu Yang <xiyuyang19@fudan.edu.cn>
Date: Sat, 25 Apr 2020 21:10:23 +0800
Subject: [PATCH 20/44] net/tls: Fix sk_psock refcnt leak when in
 tls_data_ready()

[ Upstream commit 62b4011fa7bef9fa00a6aeec26e69685dc1cc21e ]

tls_data_ready() invokes sk_psock_get(), which returns a reference of
the specified sk_psock object to "psock" with increased refcnt.

When tls_data_ready() returns, local variable "psock" becomes invalid,
so the refcount should be decreased to keep refcount balanced.

The reference counting issue happens in one exception handling path of
tls_data_ready(). When "psock->ingress_msg" is empty but "psock" is not
NULL, the function forgets to decrease the refcnt increased by
sk_psock_get(), causing a refcnt leak.

Fix this issue by calling sk_psock_put() on all paths when "psock" is
not NULL.

Signed-off-by: Xiyu Yang <xiyuyang19@fudan.edu.cn>
Signed-off-by: Xin Tan <tanxin.ctf@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 704313dd082f..e23f94a5549b 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -2083,8 +2083,9 @@ static void tls_data_ready(struct sock *sk)
 	strp_data_ready(&ctx->strp);
 
 	psock = sk_psock_get(sk);
-	if (psock && !list_empty(&psock->ingress_msg)) {
-		ctx->saved_data_ready(sk);
+	if (psock) {
+		if (!list_empty(&psock->ingress_msg))
+			ctx->saved_data_ready(sk);
 		sk_psock_put(sk, psock);
 	}
 }
-- 
2.26.2


From 469f6a4abf1881c424e4f870897df526adcbd900 Mon Sep 17 00:00:00 2001
From: Matt Jolly <Kangie@footclan.ninja>
Date: Sun, 3 May 2020 01:52:28 +1000
Subject: [PATCH 21/44] net: usb: qmi_wwan: add support for DW5816e
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 57c7f2bd758eed867295c81d3527fff4fab1ed74 ]

Add support for Dell Wireless 5816e to drivers/net/usb/qmi_wwan.c

Signed-off-by: Matt Jolly <Kangie@footclan.ninja>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 6c738a271257..4bb8552a00d3 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1359,6 +1359,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x413c, 0x81b3, 8)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */
 	{QMI_FIXED_INTF(0x413c, 0x81b6, 8)},	/* Dell Wireless 5811e */
 	{QMI_FIXED_INTF(0x413c, 0x81b6, 10)},	/* Dell Wireless 5811e */
+	{QMI_FIXED_INTF(0x413c, 0x81cc, 8)},	/* Dell Wireless 5816e */
 	{QMI_FIXED_INTF(0x413c, 0x81d7, 0)},	/* Dell Wireless 5821e */
 	{QMI_FIXED_INTF(0x413c, 0x81d7, 1)},	/* Dell Wireless 5821e preproduction config */
 	{QMI_FIXED_INTF(0x413c, 0x81e0, 0)},	/* Dell Wireless 5821e with eSIM support*/
-- 
2.26.2


From 1ca2194f334b893684ca426d372f4f38c73ca961 Mon Sep 17 00:00:00 2001
From: Qiushi Wu <wu000273@umn.edu>
Date: Sat, 2 May 2020 17:42:59 -0500
Subject: [PATCH 22/44] nfp: abm: fix a memory leak bug

[ Upstream commit bd4af432cc71b5fbfe4833510359a6ad3ada250d ]

In function nfp_abm_vnic_set_mac, pointer nsp is allocated by nfp_nsp_open.
But when nfp_nsp_has_hwinfo_lookup fail, the pointer is not released,
which can lead to a memory leak bug. Fix this issue by adding
nfp_nsp_close(nsp) in the error path.

Fixes: f6e71efdf9fb1 ("nfp: abm: look up MAC addresses via management FW")
Signed-off-by: Qiushi Wu <wu000273@umn.edu>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/abm/main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.c b/drivers/net/ethernet/netronome/nfp/abm/main.c
index 9183b3e85d21..354efffac0f9 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.c
@@ -283,6 +283,7 @@ nfp_abm_vnic_set_mac(struct nfp_pf *pf, struct nfp_abm *abm, struct nfp_net *nn,
 	if (!nfp_nsp_has_hwinfo_lookup(nsp)) {
 		nfp_warn(pf->cpp, "NSP doesn't support PF MAC generation\n");
 		eth_hw_addr_random(nn->dp.netdev);
+		nfp_nsp_close(nsp);
 		return;
 	}
 
-- 
2.26.2


From 938c1edc90922fea23a9709e3e094002219a881c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 25 Apr 2020 15:19:51 -0700
Subject: [PATCH 23/44] sch_choke: avoid potential panic in choke_reset()

[ Upstream commit 8738c85c72b3108c9b9a369a39868ba5f8e10ae0 ]

If choke_init() could not allocate q->tab, we would crash later
in choke_reset().

BUG: KASAN: null-ptr-deref in memset include/linux/string.h:366 [inline]
BUG: KASAN: null-ptr-deref in choke_reset+0x208/0x340 net/sched/sch_choke.c:326
Write of size 8 at addr 0000000000000000 by task syz-executor822/7022

CPU: 1 PID: 7022 Comm: syz-executor822 Not tainted 5.7.0-rc1-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x188/0x20d lib/dump_stack.c:118
 __kasan_report.cold+0x5/0x4d mm/kasan/report.c:515
 kasan_report+0x33/0x50 mm/kasan/common.c:625
 check_memory_region_inline mm/kasan/generic.c:187 [inline]
 check_memory_region+0x141/0x190 mm/kasan/generic.c:193
 memset+0x20/0x40 mm/kasan/common.c:85
 memset include/linux/string.h:366 [inline]
 choke_reset+0x208/0x340 net/sched/sch_choke.c:326
 qdisc_reset+0x6b/0x520 net/sched/sch_generic.c:910
 dev_deactivate_queue.constprop.0+0x13c/0x240 net/sched/sch_generic.c:1138
 netdev_for_each_tx_queue include/linux/netdevice.h:2197 [inline]
 dev_deactivate_many+0xe2/0xba0 net/sched/sch_generic.c:1195
 dev_deactivate+0xf8/0x1c0 net/sched/sch_generic.c:1233
 qdisc_graft+0xd25/0x1120 net/sched/sch_api.c:1051
 tc_modify_qdisc+0xbab/0x1a00 net/sched/sch_api.c:1670
 rtnetlink_rcv_msg+0x44e/0xad0 net/core/rtnetlink.c:5454
 netlink_rcv_skb+0x15a/0x410 net/netlink/af_netlink.c:2469
 netlink_unicast_kernel net/netlink/af_netlink.c:1303 [inline]
 netlink_unicast+0x537/0x740 net/netlink/af_netlink.c:1329
 netlink_sendmsg+0x882/0xe10 net/netlink/af_netlink.c:1918
 sock_sendmsg_nosec net/socket.c:652 [inline]
 sock_sendmsg+0xcf/0x120 net/socket.c:672
 ____sys_sendmsg+0x6bf/0x7e0 net/socket.c:2362
 ___sys_sendmsg+0x100/0x170 net/socket.c:2416
 __sys_sendmsg+0xec/0x1b0 net/socket.c:2449
 do_syscall_64+0xf6/0x7d0 arch/x86/entry/common.c:295

Fixes: 77e62da6e60c ("sch_choke: drop all packets in queue during reset")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_choke.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index a36974e9c601..1bcf8fbfd40e 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -323,7 +323,8 @@ static void choke_reset(struct Qdisc *sch)
 
 	sch->q.qlen = 0;
 	sch->qstats.backlog = 0;
-	memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *));
+	if (q->tab)
+		memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *));
 	q->head = q->tail = 0;
 	red_restart(&q->vars);
 }
-- 
2.26.2


From adb99025a0a173bc5a17e6058a17986d2ae8465d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 26 Apr 2020 18:19:07 -0700
Subject: [PATCH 24/44] sch_sfq: validate silly quantum values

[ Upstream commit df4953e4e997e273501339f607b77953772e3559 ]

syzbot managed to set up sfq so that q->scaled_quantum was zero,
triggering an infinite loop in sfq_dequeue()

More generally, we must only accept quantum between 1 and 2^18 - 7,
meaning scaled_quantum must be in [1, 0x7FFF] range.

Otherwise, we also could have a loop in sfq_dequeue()
if scaled_quantum happens to be 0x8000, since slot->allot
could indefinitely switch between 0 and 0x8000.

Fixes: eeaeb068f139 ("sch_sfq: allow big packets and be fair")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot+0251e883fe39e7a0cb0a@syzkaller.appspotmail.com
Cc: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_sfq.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index c787d4d46017..5a6def5e4e6d 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -637,6 +637,15 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt)
 	if (ctl->divisor &&
 	    (!is_power_of_2(ctl->divisor) || ctl->divisor > 65536))
 		return -EINVAL;
+
+	/* slot->allot is a short, make sure quantum is not too big. */
+	if (ctl->quantum) {
+		unsigned int scaled = SFQ_ALLOT_SIZE(ctl->quantum);
+
+		if (scaled <= 0 || scaled > SHRT_MAX)
+			return -EINVAL;
+	}
+
 	if (ctl_v1 && !red_check_params(ctl_v1->qth_min, ctl_v1->qth_max,
 					ctl_v1->Wlog))
 		return -EINVAL;
-- 
2.26.2


From 33e883896d527957fbec1d41cb5c21c7bb3e47b7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 5 May 2020 20:51:06 -0700
Subject: [PATCH 25/44] selftests: net: tcp_mmap: clear whole
 tcp_zerocopy_receive struct

[ Upstream commit bf5525f3a8e3248be5aa5defe5aaadd60e1c1ba1 ]

We added fields in tcp_zerocopy_receive structure,
so make sure to clear all fields to not pass garbage to the kernel.

We were lucky because recent additions added 'out' parameters,
still we need to clean our reference implementation, before folks
copy/paste it.

Fixes: c8856c051454 ("tcp-zerocopy: Return inq along with tcp receive zerocopy.")
Fixes: 33946518d493 ("tcp-zerocopy: Return sk_err (if set) along with tcp receive zerocopy.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Arjun Roy <arjunroy@google.com>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/tcp_mmap.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c
index 35505b31e5cc..62171fd638c8 100644
--- a/tools/testing/selftests/net/tcp_mmap.c
+++ b/tools/testing/selftests/net/tcp_mmap.c
@@ -165,9 +165,10 @@ void *child_thread(void *arg)
 			socklen_t zc_len = sizeof(zc);
 			int res;
 
+			memset(&zc, 0, sizeof(zc));
 			zc.address = (__u64)((unsigned long)addr);
 			zc.length = chunk_size;
-			zc.recv_skip_hint = 0;
+
 			res = getsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE,
 					 &zc, &zc_len);
 			if (res == -1)
-- 
2.26.2


From 52d61542b0d5dafc6b0cd7125551ef38d9dd5fd3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 6 May 2020 09:21:15 -0700
Subject: [PATCH 26/44] selftests: net: tcp_mmap: fix SO_RCVLOWAT setting

[ Upstream commit a84724178bd7081cf3bd5b558616dd6a9a4ca63b ]

Since chunk_size is no longer an integer, we can not
use it directly as an argument of setsockopt().

This patch should fix tcp_mmap for Big Endian kernels.

Fixes: 597b01edafac ("selftests: net: avoid ptl lock contention in tcp_mmap")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Cc: Arjun Roy <arjunroy@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/tcp_mmap.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c
index 62171fd638c8..4555f88252ba 100644
--- a/tools/testing/selftests/net/tcp_mmap.c
+++ b/tools/testing/selftests/net/tcp_mmap.c
@@ -282,12 +282,14 @@ static void setup_sockaddr(int domain, const char *str_addr,
 static void do_accept(int fdlisten)
 {
 	pthread_attr_t attr;
+	int rcvlowat;
 
 	pthread_attr_init(&attr);
 	pthread_attr_setdetachstate(&attr, PTHREAD_CREATE_DETACHED);
 
+	rcvlowat = chunk_size;
 	if (setsockopt(fdlisten, SOL_SOCKET, SO_RCVLOWAT,
-		       &chunk_size, sizeof(chunk_size)) == -1) {
+		       &rcvlowat, sizeof(rcvlowat)) == -1) {
 		perror("setsockopt SO_RCVLOWAT");
 	}
 
-- 
2.26.2


From 2c507a994a0a73f084c5407ba3952af3df0d3a30 Mon Sep 17 00:00:00 2001
From: Tuong Lien <tuong.t.lien@dektech.com.au>
Date: Mon, 4 May 2020 11:15:54 +0700
Subject: [PATCH 27/44] tipc: fix partial topology connection closure

[ Upstream commit 980d69276f3048af43a045be2925dacfb898a7be ]

When an application connects to the TIPC topology server and subscribes
to some services, a new connection is created along with some objects -
'tipc_subscription' to store related data correspondingly...
However, there is one omission in the connection handling that when the
connection or application is orderly shutdown (e.g. via SIGQUIT, etc.),
the connection is not closed in kernel, the 'tipc_subscription' objects
are not freed too.
This results in:
- The maximum number of subscriptions (65535) will be reached soon, new
subscriptions will be rejected;
- TIPC module cannot be removed (unless the objects  are somehow forced
to release first);

The commit fixes the issue by closing the connection if the 'recvmsg()'
returns '0' i.e. when the peer is shutdown gracefully. It also includes
the other unexpected cases.

Acked-by: Jon Maloy <jmaloy@redhat.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Tuong Lien <tuong.t.lien@dektech.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/topsrv.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c
index 3a12fc18239b..73dbed0c4b6b 100644
--- a/net/tipc/topsrv.c
+++ b/net/tipc/topsrv.c
@@ -402,10 +402,11 @@ static int tipc_conn_rcv_from_sock(struct tipc_conn *con)
 		read_lock_bh(&sk->sk_callback_lock);
 		ret = tipc_conn_rcv_sub(srv, con, &s);
 		read_unlock_bh(&sk->sk_callback_lock);
+		if (!ret)
+			return 0;
 	}
-	if (ret < 0)
-		tipc_conn_close(con);
 
+	tipc_conn_close(con);
 	return ret;
 }
 
-- 
2.26.2


From fcdf5228682310f9fa9737a91d5d712ae309effa Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
Date: Mon, 27 Apr 2020 16:11:05 +0200
Subject: [PATCH 28/44] tunnel: Propagate ECT(1) when decapsulating as
 recommended by RFC6040
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit b723748750ece7d844cdf2f52c01d37f83387208 ]

RFC 6040 recommends propagating an ECT(1) mark from an outer tunnel header
to the inner header if that inner header is already marked as ECT(0). When
RFC 6040 decapsulation was implemented, this case of propagation was not
added. This simply appears to be an oversight, so let's fix that.

Fixes: eccc1bb8d4b4 ("tunnel: drop packet if ECN present with not-ECT")
Reported-by: Bob Briscoe <ietf@bobbriscoe.net>
Reported-by: Olivier Tilmans <olivier.tilmans@nokia-bell-labs.com>
Cc: Dave Taht <dave.taht@gmail.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_ecn.h | 57 ++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 55 insertions(+), 2 deletions(-)

diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h
index c8e2bebd8d93..0f0d1efe06dd 100644
--- a/include/net/inet_ecn.h
+++ b/include/net/inet_ecn.h
@@ -99,6 +99,20 @@ static inline int IP_ECN_set_ce(struct iphdr *iph)
 	return 1;
 }
 
+static inline int IP_ECN_set_ect1(struct iphdr *iph)
+{
+	u32 check = (__force u32)iph->check;
+
+	if ((iph->tos & INET_ECN_MASK) != INET_ECN_ECT_0)
+		return 0;
+
+	check += (__force u16)htons(0x100);
+
+	iph->check = (__force __sum16)(check + (check>=0xFFFF));
+	iph->tos ^= INET_ECN_MASK;
+	return 1;
+}
+
 static inline void IP_ECN_clear(struct iphdr *iph)
 {
 	iph->tos &= ~INET_ECN_MASK;
@@ -134,6 +148,22 @@ static inline int IP6_ECN_set_ce(struct sk_buff *skb, struct ipv6hdr *iph)
 	return 1;
 }
 
+static inline int IP6_ECN_set_ect1(struct sk_buff *skb, struct ipv6hdr *iph)
+{
+	__be32 from, to;
+
+	if ((ipv6_get_dsfield(iph) & INET_ECN_MASK) != INET_ECN_ECT_0)
+		return 0;
+
+	from = *(__be32 *)iph;
+	to = from ^ htonl(INET_ECN_MASK << 20);
+	*(__be32 *)iph = to;
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		skb->csum = csum_add(csum_sub(skb->csum, (__force __wsum)from),
+				     (__force __wsum)to);
+	return 1;
+}
+
 static inline void ipv6_copy_dscp(unsigned int dscp, struct ipv6hdr *inner)
 {
 	dscp &= ~INET_ECN_MASK;
@@ -159,6 +189,25 @@ static inline int INET_ECN_set_ce(struct sk_buff *skb)
 	return 0;
 }
 
+static inline int INET_ECN_set_ect1(struct sk_buff *skb)
+{
+	switch (skb->protocol) {
+	case cpu_to_be16(ETH_P_IP):
+		if (skb_network_header(skb) + sizeof(struct iphdr) <=
+		    skb_tail_pointer(skb))
+			return IP_ECN_set_ect1(ip_hdr(skb));
+		break;
+
+	case cpu_to_be16(ETH_P_IPV6):
+		if (skb_network_header(skb) + sizeof(struct ipv6hdr) <=
+		    skb_tail_pointer(skb))
+			return IP6_ECN_set_ect1(skb, ipv6_hdr(skb));
+		break;
+	}
+
+	return 0;
+}
+
 /*
  * RFC 6040 4.2
  *  To decapsulate the inner header at the tunnel egress, a compliant
@@ -208,8 +257,12 @@ static inline int INET_ECN_decapsulate(struct sk_buff *skb,
 	int rc;
 
 	rc = __INET_ECN_decapsulate(outer, inner, &set_ce);
-	if (!rc && set_ce)
-		INET_ECN_set_ce(skb);
+	if (!rc) {
+		if (set_ce)
+			INET_ECN_set_ce(skb);
+		else if ((outer & INET_ECN_MASK) == INET_ECN_ECT_1)
+			INET_ECN_set_ect1(skb);
+	}
 
 	return rc;
 }
-- 
2.26.2


From c19e980f7db6499db7102a863e2224236af41ddb Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 26 Apr 2020 16:24:38 -0400
Subject: [PATCH 29/44] bnxt_en: Fix VF anti-spoof filter setup.

[ Upstream commit c71c4e49afe173823a2a85b0cabc9b3f1176ffa2 ]

Fix the logic that sets the enable/disable flag for the source MAC
filter according to firmware spec 1.7.1.

In the original firmware spec. before 1.7.1, the VF spoof check flags
were not latched after making the HWRM_FUNC_CFG call, so there was a
need to keep the func_flags so that subsequent calls would perserve
the VF spoof check setting.  A change was made in the 1.7.1 spec
so that the flags became latched.  So we now set or clear the anti-
spoof setting directly without retrieving the old settings in the
stored vf->func_flags which are no longer valid.  We also remove the
unneeded vf->func_flags.

Fixes: 8eb992e876a8 ("bnxt_en: Update firmware interface spec to 1.7.6.2.")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.h       |  1 -
 drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c | 10 ++--------
 2 files changed, 2 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 63b170658532..ef0268649822 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1064,7 +1064,6 @@ struct bnxt_vf_info {
 #define BNXT_VF_LINK_FORCED	0x4
 #define BNXT_VF_LINK_UP		0x8
 #define BNXT_VF_TRUST		0x10
-	u32	func_flags; /* func cfg flags */
 	u32	min_tx_rate;
 	u32	max_tx_rate;
 	void	*hwrm_cmd_req_addr;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index 2aba1e02a8f4..1259d135c9cc 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -85,11 +85,10 @@ int bnxt_set_vf_spoofchk(struct net_device *dev, int vf_id, bool setting)
 	if (old_setting == setting)
 		return 0;
 
-	func_flags = vf->func_flags;
 	if (setting)
-		func_flags |= FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_ENABLE;
+		func_flags = FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_ENABLE;
 	else
-		func_flags |= FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_DISABLE;
+		func_flags = FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_DISABLE;
 	/*TODO: if the driver supports VLAN filter on guest VLAN,
 	 * the spoof check should also include vlan anti-spoofing
 	 */
@@ -98,7 +97,6 @@ int bnxt_set_vf_spoofchk(struct net_device *dev, int vf_id, bool setting)
 	req.flags = cpu_to_le32(func_flags);
 	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 	if (!rc) {
-		vf->func_flags = func_flags;
 		if (setting)
 			vf->flags |= BNXT_VF_SPOOFCHK;
 		else
@@ -230,7 +228,6 @@ int bnxt_set_vf_mac(struct net_device *dev, int vf_id, u8 *mac)
 	memcpy(vf->mac_addr, mac, ETH_ALEN);
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1);
 	req.fid = cpu_to_le16(vf->fw_fid);
-	req.flags = cpu_to_le32(vf->func_flags);
 	req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_MAC_ADDR);
 	memcpy(req.dflt_mac_addr, mac, ETH_ALEN);
 	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
@@ -268,7 +265,6 @@ int bnxt_set_vf_vlan(struct net_device *dev, int vf_id, u16 vlan_id, u8 qos,
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1);
 	req.fid = cpu_to_le16(vf->fw_fid);
-	req.flags = cpu_to_le32(vf->func_flags);
 	req.dflt_vlan = cpu_to_le16(vlan_tag);
 	req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_VLAN);
 	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
@@ -307,7 +303,6 @@ int bnxt_set_vf_bw(struct net_device *dev, int vf_id, int min_tx_rate,
 		return 0;
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1);
 	req.fid = cpu_to_le16(vf->fw_fid);
-	req.flags = cpu_to_le32(vf->func_flags);
 	req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_MAX_BW);
 	req.max_bw = cpu_to_le32(max_tx_rate);
 	req.enables |= cpu_to_le32(FUNC_CFG_REQ_ENABLES_MIN_BW);
@@ -479,7 +474,6 @@ static void __bnxt_set_vf_params(struct bnxt *bp, int vf_id)
 	vf = &bp->pf.vf[vf_id];
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1);
 	req.fid = cpu_to_le16(vf->fw_fid);
-	req.flags = cpu_to_le32(vf->func_flags);
 
 	if (is_valid_ether_addr(vf->mac_addr)) {
 		req.enables |= cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_MAC_ADDR);
-- 
2.26.2


From 91b810967b8987d144d50abe5314c5ec008654c4 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Sun, 26 Apr 2020 16:24:39 -0400
Subject: [PATCH 30/44] bnxt_en: Reduce BNXT_MSIX_VEC_MAX value to supported
 CQs per PF.

[ Upstream commit 9e68cb0359b20f99c7b070f1d3305e5e0a9fae6d ]

Broadcom adapters support only maximum of 512 CQs per PF. If user sets
MSIx vectors more than supported CQs, firmware is setting incorrect value
for msix_vec_per_pf_max parameter. Fix it by reducing the BNXT_MSIX_VEC_MAX
value to 512, even though the maximum # of MSIx vectors supported by adapter
are 1280.

Fixes: f399e8497826 ("bnxt_en: Use msix_vec_per_pf_max and msix_vec_per_pf_min devlink params.")
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
index 95f893f2a74d..d5c8bd49383a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
@@ -43,7 +43,7 @@ static inline void bnxt_link_bp_to_dl(struct bnxt *bp, struct devlink *dl)
 #define BNXT_NVM_CFG_VER_BITS		24
 #define BNXT_NVM_CFG_VER_BYTES		4
 
-#define BNXT_MSIX_VEC_MAX	1280
+#define BNXT_MSIX_VEC_MAX	512
 #define BNXT_MSIX_VEC_MIN_MAX	128
 
 enum bnxt_nvm_dir_type {
-- 
2.26.2


From f8570dff3e29686d5a205cdb3156b48ca0160598 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 26 Apr 2020 16:24:40 -0400
Subject: [PATCH 31/44] bnxt_en: Improve AER slot reset.

[ Upstream commit bae361c54fb6ac6eba3b4762f49ce14beb73ef13 ]

Improve the slot reset sequence by disabling the device to prevent bad
DMAs if slot reset fails.  Return the proper result instead of always
PCI_ERS_RESULT_RECOVERED to the caller.

Fixes: 6316ea6db93d ("bnxt_en: Enable AER support.")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index d28b406a26b1..cde586b96a17 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -12173,12 +12173,15 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev)
 		bnxt_ulp_start(bp, err);
 	}
 
-	if (result != PCI_ERS_RESULT_RECOVERED && netif_running(netdev))
-		dev_close(netdev);
+	if (result != PCI_ERS_RESULT_RECOVERED) {
+		if (netif_running(netdev))
+			dev_close(netdev);
+		pci_disable_device(pdev);
+	}
 
 	rtnl_unlock();
 
-	return PCI_ERS_RESULT_RECOVERED;
+	return result;
 }
 
 /**
-- 
2.26.2


From 5bd483436460868b25aaefb65f439b509e321f89 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 26 Apr 2020 16:24:41 -0400
Subject: [PATCH 32/44] bnxt_en: Return error when allocating zero size context
 memory.

[ Upstream commit bbf211b1ecb891c7e0cc7888834504183fc8b534 ]

bnxt_alloc_ctx_pg_tbls() should return error when the memory size of the
context memory to set up is zero.  By returning success (0), the caller
may proceed normally and may crash later when it tries to set up the
memory.

Fixes: 08fe9d181606 ("bnxt_en: Add Level 2 context memory paging support.")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index cde586b96a17..f06801edea7d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -6662,7 +6662,7 @@ static int bnxt_alloc_ctx_pg_tbls(struct bnxt *bp,
 	int rc;
 
 	if (!mem_size)
-		return 0;
+		return -EINVAL;
 
 	ctx_pg->nr_pages = DIV_ROUND_UP(mem_size, BNXT_PAGE_SIZE);
 	if (ctx_pg->nr_pages > MAX_CTX_TOTAL_PAGES) {
-- 
2.26.2


From 5c4ed5b16c49d0108d7e210d210be561bbf363d4 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 26 Apr 2020 16:24:42 -0400
Subject: [PATCH 33/44] bnxt_en: Fix VLAN acceleration handling in
 bnxt_fix_features().

[ Upstream commit c72cb303aa6c2ae7e4184f0081c6d11bf03fb96b ]

The current logic in bnxt_fix_features() will inadvertently turn on both
CTAG and STAG VLAN offload if the user tries to disable both.  Fix it
by checking that the user is trying to enable CTAG or STAG before
enabling both.  The logic is supposed to enable or disable both CTAG and
STAG together.

Fixes: 5a9f6b238e59 ("bnxt_en: Enable and disable RX CTAG and RX STAG VLAN acceleration together.")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index f06801edea7d..d0ddd08c4112 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -9794,6 +9794,7 @@ static netdev_features_t bnxt_fix_features(struct net_device *dev,
 					   netdev_features_t features)
 {
 	struct bnxt *bp = netdev_priv(dev);
+	netdev_features_t vlan_features;
 
 	if ((features & NETIF_F_NTUPLE) && !bnxt_rfs_capable(bp))
 		features &= ~NETIF_F_NTUPLE;
@@ -9810,12 +9811,14 @@ static netdev_features_t bnxt_fix_features(struct net_device *dev,
 	/* Both CTAG and STAG VLAN accelaration on the RX side have to be
 	 * turned on or off together.
 	 */
-	if ((features & (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX)) !=
-	    (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX)) {
+	vlan_features = features & (NETIF_F_HW_VLAN_CTAG_RX |
+				    NETIF_F_HW_VLAN_STAG_RX);
+	if (vlan_features != (NETIF_F_HW_VLAN_CTAG_RX |
+			      NETIF_F_HW_VLAN_STAG_RX)) {
 		if (dev->features & NETIF_F_HW_VLAN_CTAG_RX)
 			features &= ~(NETIF_F_HW_VLAN_CTAG_RX |
 				      NETIF_F_HW_VLAN_STAG_RX);
-		else
+		else if (vlan_features)
 			features |= NETIF_F_HW_VLAN_CTAG_RX |
 				    NETIF_F_HW_VLAN_STAG_RX;
 	}
-- 
2.26.2


From ad58eb8d7da2734f8786c3d7d20542f07397ae34 Mon Sep 17 00:00:00 2001
From: Erez Shitrit <erezsh@mellanox.com>
Date: Wed, 25 Mar 2020 17:19:43 +0200
Subject: [PATCH 34/44] net/mlx5: DR, On creation set CQ's arm_db member to
 right value

[ Upstream commit 8075411d93b6efe143d9f606f6531077795b7fbf ]

In polling mode, set arm_db member to a value that will avoid CQ
event recovery by the HW.
Otherwise we might get event without completion function.
In addition,empty completion function to was added to protect from
unexpected events.

Fixes: 297cccebdc5a ("net/mlx5: DR, Expose an internal API to issue RDMA operations")
Signed-off-by: Erez Shitrit <erezsh@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../ethernet/mellanox/mlx5/core/steering/dr_send.c | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
index 095ec7b1399d..7c77378accf0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
@@ -689,6 +689,12 @@ static void dr_cq_event(struct mlx5_core_cq *mcq,
 	pr_info("CQ event %u on CQ #%u\n", event, mcq->cqn);
 }
 
+static void dr_cq_complete(struct mlx5_core_cq *mcq,
+			   struct mlx5_eqe *eqe)
+{
+	pr_err("CQ completion CQ: #%u\n", mcq->cqn);
+}
+
 static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev,
 				      struct mlx5_uars_page *uar,
 				      size_t ncqe)
@@ -750,6 +756,7 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev,
 	mlx5_fill_page_frag_array(&cq->wq_ctrl.buf, pas);
 
 	cq->mcq.event = dr_cq_event;
+	cq->mcq.comp  = dr_cq_complete;
 
 	err = mlx5_core_create_cq(mdev, &cq->mcq, in, inlen, out, sizeof(out));
 	kvfree(in);
@@ -761,7 +768,12 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev,
 	cq->mcq.set_ci_db = cq->wq_ctrl.db.db;
 	cq->mcq.arm_db = cq->wq_ctrl.db.db + 1;
 	*cq->mcq.set_ci_db = 0;
-	*cq->mcq.arm_db = 0;
+
+	/* set no-zero value, in order to avoid the HW to run db-recovery on
+	 * CQ that used in polling mode.
+	 */
+	*cq->mcq.arm_db = cpu_to_be32(2 << 28);
+
 	cq->mcq.vector = 0;
 	cq->mcq.irqn = irqn;
 	cq->mcq.uar = uar;
-- 
2.26.2


From aa541fbe58664b9ff535186128891e98a5a36333 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Sun, 21 Jul 2019 08:40:13 +0300
Subject: [PATCH 35/44] net/mlx5: Fix forced completion access non initialized
 command entry

[ Upstream commit f3cb3cebe26ed4c8036adbd9448b372129d3c371 ]

mlx5_cmd_flush() will trigger forced completions to all valid command
entries. Triggered by an asynch event such as fast teardown it can
happen at any stage of the command, including command initialization.
It will trigger forced completion and that can lead to completion on an
uninitialized command entry.

Setting MLX5_CMD_ENT_STATE_PENDING_COMP only after command entry is
initialized will ensure force completion is treated only if command
entry is initialized.

Fixes: 73dd3a4839c1 ("net/mlx5: Avoid using pending command interface slots")
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 34cba97f7bf4..d7470f8d355e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -888,7 +888,6 @@ static void cmd_work_handler(struct work_struct *work)
 	}
 
 	cmd->ent_arr[ent->idx] = ent;
-	set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state);
 	lay = get_inst(cmd, ent->idx);
 	ent->lay = lay;
 	memset(lay, 0, sizeof(*lay));
@@ -910,6 +909,7 @@ static void cmd_work_handler(struct work_struct *work)
 
 	if (ent->callback)
 		schedule_delayed_work(&ent->cb_timeout_work, cb_timeout);
+	set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state);
 
 	/* Skip sending command to fw if internal error */
 	if (pci_channel_offline(dev->pdev) ||
-- 
2.26.2


From 9500a33194cd574d9172b96b45c44407767b647b Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Sun, 23 Feb 2020 03:27:41 +0200
Subject: [PATCH 36/44] net/mlx5: Fix command entry leak in Internal Error
 State

[ Upstream commit cece6f432cca9f18900463ed01b97a152a03600a ]

Processing commands by cmd_work_handler() while already in Internal
Error State will result in entry leak, since the handler process force
completion without doorbell. Forced completion doesn't release the entry
and event completion will never arrive, so entry should be released.

Fixes: 73dd3a4839c1 ("net/mlx5: Avoid using pending command interface slots")
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index d7470f8d355e..cede5bdfd598 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -922,6 +922,10 @@ static void cmd_work_handler(struct work_struct *work)
 		MLX5_SET(mbox_out, ent->out, syndrome, drv_synd);
 
 		mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
+		/* no doorbell, no need to keep the entry */
+		free_ent(cmd, ent->idx);
+		if (ent->callback)
+			free_cmd(ent);
 		return;
 	}
 
-- 
2.26.2


From 8cd2ad20f8849cf7fc9f1b960ea00ff4e87c797b Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@mellanox.com>
Date: Thu, 23 Apr 2020 12:37:21 +0300
Subject: [PATCH 37/44] net/mlx5e: Fix q counters on uplink representors

[ Upstream commit 67b38de646894c9a94fe4d6d17719e70cc6028eb ]

Need to allocate the q counters before init_rx which needs them
when creating the rq.

Fixes: 8520fa57a4e9 ("net/mlx5e: Create q counters on uplink representors")
Signed-off-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index ffc193c4ad43..2ad0d09cc9bd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1692,19 +1692,14 @@ static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv)
 
 static int mlx5e_init_ul_rep_rx(struct mlx5e_priv *priv)
 {
-	int err = mlx5e_init_rep_rx(priv);
-
-	if (err)
-		return err;
-
 	mlx5e_create_q_counters(priv);
-	return 0;
+	return mlx5e_init_rep_rx(priv);
 }
 
 static void mlx5e_cleanup_ul_rep_rx(struct mlx5e_priv *priv)
 {
-	mlx5e_destroy_q_counters(priv);
 	mlx5e_cleanup_rep_rx(priv);
+	mlx5e_destroy_q_counters(priv);
 }
 
 static int mlx5e_init_uplink_rep_tx(struct mlx5e_rep_priv *rpriv)
-- 
2.26.2


From af0f458a8cf611a323869fdfa9b5d4508e8ed244 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 6 May 2020 13:16:22 +0300
Subject: [PATCH 38/44] net: mvpp2: prevent buffer overflow in mvpp22_rss_ctx()

[ Upstream commit 39bd16df7c31bb8cf5dfd0c88e42abd5ae10029d ]

The "rss_context" variable comes from the user via  ethtool_get_rxfh().
It can be any u32 value except zero.  Eventually it gets passed to
mvpp22_rss_ctx() and if it is over MVPP22_N_RSS_TABLES (8) then it
results in an array overflow.

Fixes: 895586d5dc32 ("net: mvpp2: cls: Use RSS contexts to handle RSS tables")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 72133cbe55d4..eb78a948bee3 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -4325,6 +4325,8 @@ static int mvpp2_ethtool_get_rxfh_context(struct net_device *dev, u32 *indir,
 
 	if (!mvpp22_rss_is_supported())
 		return -EOPNOTSUPP;
+	if (rss_context >= MVPP22_N_RSS_TABLES)
+		return -EINVAL;
 
 	if (hfunc)
 		*hfunc = ETH_RSS_HASH_CRC32;
-- 
2.26.2


From be8f7149b17319ba1ee234d2669ad9e8fe28ce5d Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 6 May 2020 13:16:56 +0300
Subject: [PATCH 39/44] net: mvpp2: cls: Prevent buffer overflow in
 mvpp2_ethtool_cls_rule_del()

[ Upstream commit 722c0f00d4feea77475a5dc943b53d60824a1e4e ]

The "info->fs.location" is a u32 that comes from the user via the
ethtool_set_rxnfc() function.  We need to check for invalid values to
prevent a buffer overflow.

I copy and pasted this check from the mvpp2_ethtool_cls_rule_ins()
function.

Fixes: 90b509b39ac9 ("net: mvpp2: cls: Add Classification offload support")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
index 35478cba2aa5..4344a59c823f 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
@@ -1422,6 +1422,9 @@ int mvpp2_ethtool_cls_rule_del(struct mvpp2_port *port,
 	struct mvpp2_ethtool_fs *efs;
 	int ret;
 
+	if (info->fs.location >= MVPP2_N_RFS_ENTRIES_PER_FLOW)
+		return -EINVAL;
+
 	efs = port->rfs_rules[info->fs.location];
 	if (!efs)
 		return -EINVAL;
-- 
2.26.2


From c5a476dd26fc4bf65274684f15984bfeaf11d41b Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Wed, 29 Apr 2020 14:59:21 -0600
Subject: [PATCH 40/44] wireguard: queueing: cleanup ptr_ring in error path of
 packet_queue_init

[ Upstream commit 130c58606171326c81841a49cc913cd354113dd9 ]

Prior, if the alloc_percpu of packet_percpu_multicore_worker_alloc
failed, the previously allocated ptr_ring wouldn't be freed. This commit
adds the missing call to ptr_ring_cleanup in the error case.

Reported-by: Sultan Alsawaf <sultan@kerneltoast.com>
Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wireguard/queueing.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireguard/queueing.c b/drivers/net/wireguard/queueing.c
index 5c964fcb994e..71b8e80b58e1 100644
--- a/drivers/net/wireguard/queueing.c
+++ b/drivers/net/wireguard/queueing.c
@@ -35,8 +35,10 @@ int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function,
 		if (multicore) {
 			queue->worker = wg_packet_percpu_multicore_worker_alloc(
 				function, queue);
-			if (!queue->worker)
+			if (!queue->worker) {
+				ptr_ring_cleanup(&queue->ring, NULL);
 				return -ENOMEM;
+			}
 		} else {
 			INIT_WORK(&queue->work, function);
 		}
-- 
2.26.2


From 10e629aa7611bff2eb6685e0cd64108a8ed26531 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
Date: Wed, 29 Apr 2020 14:59:22 -0600
Subject: [PATCH 41/44] wireguard: receive: use tunnel helpers for
 decapsulating ECN markings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit eebabcb26ea1e3295704477c6cd4e772c96a9559 ]

WireGuard currently only propagates ECN markings on tunnel decap according
to the old RFC3168 specification. However, the spec has since been updated
in RFC6040 to recommend slightly different decapsulation semantics. This
was implemented in the kernel as a set of common helpers for ECN
decapsulation, so let's just switch over WireGuard to using those, so it
can benefit from this enhancement and any future tweaks. We do not drop
packets with invalid ECN marking combinations, because WireGuard is
frequently used to work around broken ISPs, which could be doing that.

Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
Reported-by: Olivier Tilmans <olivier.tilmans@nokia-bell-labs.com>
Cc: Dave Taht <dave.taht@gmail.com>
Cc: Rodney W. Grimes <ietf@gndrsh.dnsmgr.net>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wireguard/receive.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c
index da3b782ab7d3..267f202f1931 100644
--- a/drivers/net/wireguard/receive.c
+++ b/drivers/net/wireguard/receive.c
@@ -393,13 +393,11 @@ static void wg_packet_consume_data_done(struct wg_peer *peer,
 		len = ntohs(ip_hdr(skb)->tot_len);
 		if (unlikely(len < sizeof(struct iphdr)))
 			goto dishonest_packet_size;
-		if (INET_ECN_is_ce(PACKET_CB(skb)->ds))
-			IP_ECN_set_ce(ip_hdr(skb));
+		INET_ECN_decapsulate(skb, PACKET_CB(skb)->ds, ip_hdr(skb)->tos);
 	} else if (skb->protocol == htons(ETH_P_IPV6)) {
 		len = ntohs(ipv6_hdr(skb)->payload_len) +
 		      sizeof(struct ipv6hdr);
-		if (INET_ECN_is_ce(PACKET_CB(skb)->ds))
-			IP6_ECN_set_ce(skb, ipv6_hdr(skb));
+		INET_ECN_decapsulate(skb, PACKET_CB(skb)->ds, ipv6_get_dsfield(ipv6_hdr(skb)));
 	} else {
 		goto dishonest_packet_type;
 	}
-- 
2.26.2


From 7461aa0d1043eb9cd11afc41011861b032a11276 Mon Sep 17 00:00:00 2001
From: Dejin Zheng <zhengdejin5@gmail.com>
Date: Mon, 4 May 2020 20:01:27 +0800
Subject: [PATCH 42/44] net: enetc: fix an issue about leak system resources

[ Upstream commit d975cb7ea915e64a3ebcfef8a33051f3e6bf22a8 ]

the related system resources were not released when enetc_hw_alloc()
return error in the enetc_pci_mdio_probe(), add iounmap() for error
handling label "err_hw_alloc" to fix it.

Fixes: 6517798dd3432a ("enetc: Make MDIO accessors more generic and export to include/linux/fsl")
Cc: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Dejin Zheng <zhengdejin5@gmail.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c b/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c
index ebc635f8a4cc..15f37c5b8dc1 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c
@@ -74,8 +74,8 @@ static int enetc_pci_mdio_probe(struct pci_dev *pdev,
 	pci_disable_device(pdev);
 err_pci_enable:
 err_mdiobus_alloc:
-	iounmap(port_regs);
 err_hw_alloc:
+	iounmap(port_regs);
 err_ioremap:
 	return err;
 }
-- 
2.26.2


From 516939d23069531195b974ed0aec05b800f684af Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Wed, 6 May 2020 15:33:03 -0600
Subject: [PATCH 43/44] wireguard: socket: remove errant restriction on looping
 to self

[ Upstream commit b673e24aad36981f327a6570412ffa7754de8911 ]

It's already possible to create two different interfaces and loop
packets between them. This has always been possible with tunnels in the
kernel, and isn't specific to wireguard. Therefore, the networking stack
already needs to deal with that. At the very least, the packet winds up
exceeding the MTU and is discarded at that point. So, since this is
already something that happens, there's no need to forbid the not very
exceptional case of routing a packet back to the same interface; this
loop is no different than others, and we shouldn't special case it, but
rather rely on generic handling of loops in general. This also makes it
easier to do interesting things with wireguard such as onion routing.

At the same time, we add a selftest for this, ensuring that both onion
routing works and infinite routing loops do not crash the kernel. We
also add a test case for wireguard interfaces nesting packets and
sending traffic between each other, as well as the loop in this case
too. We make sure to send some throughput-heavy traffic for this use
case, to stress out any possible recursion issues with the locks around
workqueues.

Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wireguard/socket.c             | 12 -----
 tools/testing/selftests/wireguard/netns.sh | 54 ++++++++++++++++++++--
 2 files changed, 51 insertions(+), 15 deletions(-)

diff --git a/drivers/net/wireguard/socket.c b/drivers/net/wireguard/socket.c
index b0d6541582d3..f9018027fc13 100644
--- a/drivers/net/wireguard/socket.c
+++ b/drivers/net/wireguard/socket.c
@@ -76,12 +76,6 @@ static int send4(struct wg_device *wg, struct sk_buff *skb,
 			net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n",
 					    wg->dev->name, &endpoint->addr, ret);
 			goto err;
-		} else if (unlikely(rt->dst.dev == skb->dev)) {
-			ip_rt_put(rt);
-			ret = -ELOOP;
-			net_dbg_ratelimited("%s: Avoiding routing loop to %pISpfsc\n",
-					    wg->dev->name, &endpoint->addr);
-			goto err;
 		}
 		if (cache)
 			dst_cache_set_ip4(cache, &rt->dst, fl.saddr);
@@ -149,12 +143,6 @@ static int send6(struct wg_device *wg, struct sk_buff *skb,
 			net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n",
 					    wg->dev->name, &endpoint->addr, ret);
 			goto err;
-		} else if (unlikely(dst->dev == skb->dev)) {
-			dst_release(dst);
-			ret = -ELOOP;
-			net_dbg_ratelimited("%s: Avoiding routing loop to %pISpfsc\n",
-					    wg->dev->name, &endpoint->addr);
-			goto err;
 		}
 		if (cache)
 			dst_cache_set_ip6(cache, dst, &fl.saddr);
diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh
index 936e1ca9410e..17a1f53ceba0 100755
--- a/tools/testing/selftests/wireguard/netns.sh
+++ b/tools/testing/selftests/wireguard/netns.sh
@@ -48,8 +48,11 @@ cleanup() {
 	exec 2>/dev/null
 	printf "$orig_message_cost" > /proc/sys/net/core/message_cost
 	ip0 link del dev wg0
+	ip0 link del dev wg1
 	ip1 link del dev wg0
+	ip1 link del dev wg1
 	ip2 link del dev wg0
+	ip2 link del dev wg1
 	local to_kill="$(ip netns pids $netns0) $(ip netns pids $netns1) $(ip netns pids $netns2)"
 	[[ -n $to_kill ]] && kill $to_kill
 	pp ip netns del $netns1
@@ -77,18 +80,20 @@ ip0 link set wg0 netns $netns2
 key1="$(pp wg genkey)"
 key2="$(pp wg genkey)"
 key3="$(pp wg genkey)"
+key4="$(pp wg genkey)"
 pub1="$(pp wg pubkey <<<"$key1")"
 pub2="$(pp wg pubkey <<<"$key2")"
 pub3="$(pp wg pubkey <<<"$key3")"
+pub4="$(pp wg pubkey <<<"$key4")"
 psk="$(pp wg genpsk)"
 [[ -n $key1 && -n $key2 && -n $psk ]]
 
 configure_peers() {
 	ip1 addr add 192.168.241.1/24 dev wg0
-	ip1 addr add fd00::1/24 dev wg0
+	ip1 addr add fd00::1/112 dev wg0
 
 	ip2 addr add 192.168.241.2/24 dev wg0
-	ip2 addr add fd00::2/24 dev wg0
+	ip2 addr add fd00::2/112 dev wg0
 
 	n1 wg set wg0 \
 		private-key <(echo "$key1") \
@@ -230,9 +235,38 @@ n1 ping -W 1 -c 1 192.168.241.2
 n1 wg set wg0 private-key <(echo "$key3")
 n2 wg set wg0 peer "$pub3" preshared-key <(echo "$psk") allowed-ips 192.168.241.1/32 peer "$pub1" remove
 n1 ping -W 1 -c 1 192.168.241.2
+n2 wg set wg0 peer "$pub3" remove
+
+# Test that we can route wg through wg
+ip1 addr flush dev wg0
+ip2 addr flush dev wg0
+ip1 addr add fd00::5:1/112 dev wg0
+ip2 addr add fd00::5:2/112 dev wg0
+n1 wg set wg0 private-key <(echo "$key1") peer "$pub2" preshared-key <(echo "$psk") allowed-ips fd00::5:2/128 endpoint 127.0.0.1:2
+n2 wg set wg0 private-key <(echo "$key2") listen-port 2 peer "$pub1" preshared-key <(echo "$psk") allowed-ips fd00::5:1/128 endpoint 127.212.121.99:9998
+ip1 link add wg1 type wireguard
+ip2 link add wg1 type wireguard
+ip1 addr add 192.168.241.1/24 dev wg1
+ip1 addr add fd00::1/112 dev wg1
+ip2 addr add 192.168.241.2/24 dev wg1
+ip2 addr add fd00::2/112 dev wg1
+ip1 link set mtu 1340 up dev wg1
+ip2 link set mtu 1340 up dev wg1
+n1 wg set wg1 listen-port 5 private-key <(echo "$key3") peer "$pub4" allowed-ips 192.168.241.2/32,fd00::2/128 endpoint [fd00::5:2]:5
+n2 wg set wg1 listen-port 5 private-key <(echo "$key4") peer "$pub3" allowed-ips 192.168.241.1/32,fd00::1/128 endpoint [fd00::5:1]:5
+tests
+# Try to set up a routing loop between the two namespaces
+ip1 link set netns $netns0 dev wg1
+ip0 addr add 192.168.241.1/24 dev wg1
+ip0 link set up dev wg1
+n0 ping -W 1 -c 1 192.168.241.2
+n1 wg set wg0 peer "$pub2" endpoint 192.168.241.2:7
+ip2 link del wg0
+ip2 link del wg1
+! n0 ping -W 1 -c 10 -f 192.168.241.2 || false # Should not crash kernel
 
+ip0 link del wg1
 ip1 link del wg0
-ip2 link del wg0
 
 # Test using NAT. We now change the topology to this:
 # ┌────────────────────────────────────────┐    ┌────────────────────────────────────────────────┐     ┌────────────────────────────────────────┐
@@ -282,6 +316,20 @@ pp sleep 3
 n2 ping -W 1 -c 1 192.168.241.1
 n1 wg set wg0 peer "$pub2" persistent-keepalive 0
 
+# Test that onion routing works, even when it loops
+n1 wg set wg0 peer "$pub3" allowed-ips 192.168.242.2/32 endpoint 192.168.241.2:5
+ip1 addr add 192.168.242.1/24 dev wg0
+ip2 link add wg1 type wireguard
+ip2 addr add 192.168.242.2/24 dev wg1
+n2 wg set wg1 private-key <(echo "$key3") listen-port 5 peer "$pub1" allowed-ips 192.168.242.1/32
+ip2 link set wg1 up
+n1 ping -W 1 -c 1 192.168.242.2
+ip2 link del wg1
+n1 wg set wg0 peer "$pub3" endpoint 192.168.242.2:5
+! n1 ping -W 1 -c 1 192.168.242.2 || false # Should not crash kernel
+n1 wg set wg0 peer "$pub3" remove
+ip1 addr del 192.168.242.1/24 dev wg0
+
 # Do a wg-quick(8)-style policy routing for the default route, making sure vethc has a v6 address to tease out bugs.
 ip1 -6 addr add fc00::9/96 dev vethc
 ip1 -6 route add default via fc00::1
-- 
2.26.2


From 84a25ac29d96c1e689ccff357fa5bfabe591fceb Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Wed, 6 May 2020 15:33:04 -0600
Subject: [PATCH 44/44] wireguard: send/receive: cond_resched() when processing
 worker ringbuffers

[ Upstream commit 4005f5c3c9d006157ba716594e0d70c88a235c5e ]

Users with pathological hardware reported CPU stalls on CONFIG_
PREEMPT_VOLUNTARY=y, because the ringbuffers would stay full, meaning
these workers would never terminate. That turned out not to be okay on
systems without forced preemption, which Sultan observed. This commit
adds a cond_resched() to the bottom of each loop iteration, so that
these workers don't hog the core. Note that we don't need this on the
napi poll worker, since that terminates after its budget is expended.

Suggested-by: Sultan Alsawaf <sultan@kerneltoast.com>
Reported-by: Wang Jian <larkwang@gmail.com>
Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wireguard/receive.c | 2 ++
 drivers/net/wireguard/send.c    | 4 ++++
 2 files changed, 6 insertions(+)

diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c
index 267f202f1931..2566e13a292d 100644
--- a/drivers/net/wireguard/receive.c
+++ b/drivers/net/wireguard/receive.c
@@ -516,6 +516,8 @@ void wg_packet_decrypt_worker(struct work_struct *work)
 				&PACKET_CB(skb)->keypair->receiving)) ?
 				PACKET_STATE_CRYPTED : PACKET_STATE_DEAD;
 		wg_queue_enqueue_per_peer_napi(skb, state);
+		if (need_resched())
+			cond_resched();
 	}
 }
 
diff --git a/drivers/net/wireguard/send.c b/drivers/net/wireguard/send.c
index 7348c10cbae3..e8a7d0a0cb88 100644
--- a/drivers/net/wireguard/send.c
+++ b/drivers/net/wireguard/send.c
@@ -281,6 +281,8 @@ void wg_packet_tx_worker(struct work_struct *work)
 
 		wg_noise_keypair_put(keypair, false);
 		wg_peer_put(peer);
+		if (need_resched())
+			cond_resched();
 	}
 }
 
@@ -305,6 +307,8 @@ void wg_packet_encrypt_worker(struct work_struct *work)
 		wg_queue_enqueue_per_peer(&PACKET_PEER(first)->tx_queue, first,
 					  state);
 
+		if (need_resched())
+			cond_resched();
 	}
 }
 
-- 
2.26.2

Re: [PATCHES] Networking

[Greg KH]

On Mon, May 11, 2020 at 05:41:33PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v5.4 and
> v5.6 -stable, respectively.

Now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 105 bytes --]


Please queue up the following networking bug fixes for v5.4 and
v5.6 -stable, respectively.

Thank you.

[-- Attachment #2: net_54.mbox --]
[-- Type: Application/Octet-Stream, Size: 45736 bytes --]

From a41009f2a34f24d0726f5cfbb3100d972a9b3e12 Mon Sep 17 00:00:00 2001
From: Ioana Ciornei <ioana.ciornei@nxp.com>
Date: Fri, 15 May 2020 15:30:22 +0300
Subject: [PATCH 01/19] dpaa2-eth: properly handle buffer size restrictions

[ Upstream commit efa6a7d07523ffbbf6503c1a7eeb52201c15c0e3 ]

Depending on the WRIOP version, the buffer size on the RX path must by a
multiple of 64 or 256. Handle this restriction properly by aligning down
the buffer size to the necessary value. Also, use the new buffer size
dynamically computed instead of the compile time one.

Fixes: 27c874867c4e ("dpaa2-eth: Use a single page per Rx buffer")
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/freescale/dpaa2/dpaa2-eth.c  | 29 +++++++++++--------
 .../net/ethernet/freescale/dpaa2/dpaa2-eth.h  |  1 +
 2 files changed, 18 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index bf5add954181..a935b20effa3 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -86,7 +86,7 @@ static void free_rx_fd(struct dpaa2_eth_priv *priv,
 	for (i = 1; i < DPAA2_ETH_MAX_SG_ENTRIES; i++) {
 		addr = dpaa2_sg_get_addr(&sgt[i]);
 		sg_vaddr = dpaa2_iova_to_virt(priv->iommu_domain, addr);
-		dma_unmap_page(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
+		dma_unmap_page(dev, addr, priv->rx_buf_size,
 			       DMA_BIDIRECTIONAL);
 
 		free_pages((unsigned long)sg_vaddr, 0);
@@ -144,7 +144,7 @@ static struct sk_buff *build_frag_skb(struct dpaa2_eth_priv *priv,
 		/* Get the address and length from the S/G entry */
 		sg_addr = dpaa2_sg_get_addr(sge);
 		sg_vaddr = dpaa2_iova_to_virt(priv->iommu_domain, sg_addr);
-		dma_unmap_page(dev, sg_addr, DPAA2_ETH_RX_BUF_SIZE,
+		dma_unmap_page(dev, sg_addr, priv->rx_buf_size,
 			       DMA_BIDIRECTIONAL);
 
 		sg_length = dpaa2_sg_get_len(sge);
@@ -185,7 +185,7 @@ static struct sk_buff *build_frag_skb(struct dpaa2_eth_priv *priv,
 				(page_address(page) - page_address(head_page));
 
 			skb_add_rx_frag(skb, i - 1, head_page, page_offset,
-					sg_length, DPAA2_ETH_RX_BUF_SIZE);
+					sg_length, priv->rx_buf_size);
 		}
 
 		if (dpaa2_sg_is_final(sge))
@@ -211,7 +211,7 @@ static void free_bufs(struct dpaa2_eth_priv *priv, u64 *buf_array, int count)
 
 	for (i = 0; i < count; i++) {
 		vaddr = dpaa2_iova_to_virt(priv->iommu_domain, buf_array[i]);
-		dma_unmap_page(dev, buf_array[i], DPAA2_ETH_RX_BUF_SIZE,
+		dma_unmap_page(dev, buf_array[i], priv->rx_buf_size,
 			       DMA_BIDIRECTIONAL);
 		free_pages((unsigned long)vaddr, 0);
 	}
@@ -331,7 +331,7 @@ static u32 run_xdp(struct dpaa2_eth_priv *priv,
 		break;
 	case XDP_REDIRECT:
 		dma_unmap_page(priv->net_dev->dev.parent, addr,
-			       DPAA2_ETH_RX_BUF_SIZE, DMA_BIDIRECTIONAL);
+			       priv->rx_buf_size, DMA_BIDIRECTIONAL);
 		ch->buf_count--;
 		xdp.data_hard_start = vaddr;
 		err = xdp_do_redirect(priv->net_dev, &xdp, xdp_prog);
@@ -370,7 +370,7 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 	trace_dpaa2_rx_fd(priv->net_dev, fd);
 
 	vaddr = dpaa2_iova_to_virt(priv->iommu_domain, addr);
-	dma_sync_single_for_cpu(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
+	dma_sync_single_for_cpu(dev, addr, priv->rx_buf_size,
 				DMA_BIDIRECTIONAL);
 
 	fas = dpaa2_get_fas(vaddr, false);
@@ -389,13 +389,13 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 			return;
 		}
 
-		dma_unmap_page(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
+		dma_unmap_page(dev, addr, priv->rx_buf_size,
 			       DMA_BIDIRECTIONAL);
 		skb = build_linear_skb(ch, fd, vaddr);
 	} else if (fd_format == dpaa2_fd_sg) {
 		WARN_ON(priv->xdp_prog);
 
-		dma_unmap_page(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
+		dma_unmap_page(dev, addr, priv->rx_buf_size,
 			       DMA_BIDIRECTIONAL);
 		skb = build_frag_skb(priv, ch, buf_data);
 		free_pages((unsigned long)vaddr, 0);
@@ -963,7 +963,7 @@ static int add_bufs(struct dpaa2_eth_priv *priv,
 		if (!page)
 			goto err_alloc;
 
-		addr = dma_map_page(dev, page, 0, DPAA2_ETH_RX_BUF_SIZE,
+		addr = dma_map_page(dev, page, 0, priv->rx_buf_size,
 				    DMA_BIDIRECTIONAL);
 		if (unlikely(dma_mapping_error(dev, addr)))
 			goto err_map;
@@ -973,7 +973,7 @@ static int add_bufs(struct dpaa2_eth_priv *priv,
 		/* tracing point */
 		trace_dpaa2_eth_buf_seed(priv->net_dev,
 					 page, DPAA2_ETH_RX_BUF_RAW_SIZE,
-					 addr, DPAA2_ETH_RX_BUF_SIZE,
+					 addr, priv->rx_buf_size,
 					 bpid);
 	}
 
@@ -1680,7 +1680,7 @@ static bool xdp_mtu_valid(struct dpaa2_eth_priv *priv, int mtu)
 	int mfl, linear_mfl;
 
 	mfl = DPAA2_ETH_L2_MAX_FRM(mtu);
-	linear_mfl = DPAA2_ETH_RX_BUF_SIZE - DPAA2_ETH_RX_HWA_SIZE -
+	linear_mfl = priv->rx_buf_size - DPAA2_ETH_RX_HWA_SIZE -
 		     dpaa2_eth_rx_head_room(priv) - XDP_PACKET_HEADROOM;
 
 	if (mfl > linear_mfl) {
@@ -2432,6 +2432,11 @@ static int set_buffer_layout(struct dpaa2_eth_priv *priv)
 	else
 		rx_buf_align = DPAA2_ETH_RX_BUF_ALIGN;
 
+	/* We need to ensure that the buffer size seen by WRIOP is a multiple
+	 * of 64 or 256 bytes depending on the WRIOP version.
+	 */
+	priv->rx_buf_size = ALIGN_DOWN(DPAA2_ETH_RX_BUF_SIZE, rx_buf_align);
+
 	/* tx buffer */
 	buf_layout.private_data_size = DPAA2_ETH_SWA_SIZE;
 	buf_layout.pass_timestamp = true;
@@ -3096,7 +3101,7 @@ static int bind_dpni(struct dpaa2_eth_priv *priv)
 	pools_params.num_dpbp = 1;
 	pools_params.pools[0].dpbp_id = priv->dpbp_dev->obj_desc.id;
 	pools_params.pools[0].backup_pool = 0;
-	pools_params.pools[0].buffer_size = DPAA2_ETH_RX_BUF_SIZE;
+	pools_params.pools[0].buffer_size = priv->rx_buf_size;
 	err = dpni_set_pools(priv->mc_io, 0, priv->mc_token, &pools_params);
 	if (err) {
 		dev_err(dev, "dpni_set_pools() failed\n");
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index 8a0e65b3267f..4570ed53c6c7 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -373,6 +373,7 @@ struct dpaa2_eth_priv {
 	u16 tx_data_offset;
 
 	struct fsl_mc_device *dpbp_dev;
+	u16 rx_buf_size;
 	u16 bpid;
 	struct iommu_domain *iommu_domain;
 
-- 
2.26.2


From aa8a8b1741b91e06560be8637867d9300076d06e Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 7 May 2020 12:19:03 -0700
Subject: [PATCH 02/19] net: fix a potential recursive NETDEV_FEAT_CHANGE

[ Upstream commit dd912306ff008891c82cd9f63e8181e47a9cb2fb ]

syzbot managed to trigger a recursive NETDEV_FEAT_CHANGE event
between bonding master and slave. I managed to find a reproducer
for this:

  ip li set bond0 up
  ifenslave bond0 eth0
  brctl addbr br0
  ethtool -K eth0 lro off
  brctl addif br0 bond0
  ip li set br0 up

When a NETDEV_FEAT_CHANGE event is triggered on a bonding slave,
it captures this and calls bond_compute_features() to fixup its
master's and other slaves' features. However, when syncing with
its lower devices by netdev_sync_lower_features() this event is
triggered again on slaves when the LRO feature fails to change,
so it goes back and forth recursively until the kernel stack is
exhausted.

Commit 17b85d29e82c intentionally lets __netdev_update_features()
return -1 for such a failure case, so we have to just rely on
the existing check inside netdev_sync_lower_features() and skip
NETDEV_FEAT_CHANGE event only for this specific failure case.

Fixes: fd867d51f889 ("net/core: generic support for disabling netdev features down stack")
Reported-by: syzbot+e73ceacfd8560cc8a3ca@syzkaller.appspotmail.com
Reported-by: syzbot+c2fb6f9ddcea95ba49b5@syzkaller.appspotmail.com
Cc: Jarod Wilson <jarod@redhat.com>
Cc: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Jann Horn <jannh@google.com>
Reviewed-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 8ad1e8f00958..120b994af31c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8595,11 +8595,13 @@ static void netdev_sync_lower_features(struct net_device *upper,
 			netdev_dbg(upper, "Disabling feature %pNF on lower dev %s.\n",
 				   &feature, lower->name);
 			lower->wanted_features &= ~feature;
-			netdev_update_features(lower);
+			__netdev_update_features(lower);
 
 			if (unlikely(lower->features & feature))
 				netdev_WARN(upper, "failed to disable %pNF on %s!\n",
 					    &feature, lower->name);
+			else
+				netdev_features_change(lower);
 		}
 	}
 }
-- 
2.26.2


From ead98f27079e01ec4e30506ab0d2d944e4d4db28 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 12 May 2020 14:43:14 +0200
Subject: [PATCH 03/19] netlabel: cope with NULL catmap

[ Upstream commit eead1c2ea2509fd754c6da893a94f0e69e83ebe4 ]

The cipso and calipso code can set the MLS_CAT attribute on
successful parsing, even if the corresponding catmap has
not been allocated, as per current configuration and external
input.

Later, selinux code tries to access the catmap if the MLS_CAT flag
is present via netlbl_catmap_getlong(). That may cause null ptr
dereference while processing incoming network traffic.

Address the issue setting the MLS_CAT flag only if the catmap is
really allocated. Additionally let netlbl_catmap_getlong() cope
with NULL catmap.

Reported-by: Matthew Sheets <matthew.sheets@gd-ms.com>
Fixes: 4b8feff251da ("netlabel: fix the horribly broken catmap functions")
Fixes: ceba1832b1b2 ("calipso: Set the calipso socket label to match the secattr.")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Paul Moore <paul@paul-moore.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/cipso_ipv4.c        | 6 ++++--
 net/ipv6/calipso.c           | 3 ++-
 net/netlabel/netlabel_kapi.c | 6 ++++++
 3 files changed, 12 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 0bd10a1f477f..a23094b050f8 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -1258,7 +1258,8 @@ static int cipso_v4_parsetag_rbm(const struct cipso_v4_doi *doi_def,
 			return ret_val;
 		}
 
-		secattr->flags |= NETLBL_SECATTR_MLS_CAT;
+		if (secattr->attr.mls.cat)
+			secattr->flags |= NETLBL_SECATTR_MLS_CAT;
 	}
 
 	return 0;
@@ -1439,7 +1440,8 @@ static int cipso_v4_parsetag_rng(const struct cipso_v4_doi *doi_def,
 			return ret_val;
 		}
 
-		secattr->flags |= NETLBL_SECATTR_MLS_CAT;
+		if (secattr->attr.mls.cat)
+			secattr->flags |= NETLBL_SECATTR_MLS_CAT;
 	}
 
 	return 0;
diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c
index 221c81f85cbf..8d3f66c310db 100644
--- a/net/ipv6/calipso.c
+++ b/net/ipv6/calipso.c
@@ -1047,7 +1047,8 @@ static int calipso_opt_getattr(const unsigned char *calipso,
 			goto getattr_return;
 		}
 
-		secattr->flags |= NETLBL_SECATTR_MLS_CAT;
+		if (secattr->attr.mls.cat)
+			secattr->flags |= NETLBL_SECATTR_MLS_CAT;
 	}
 
 	secattr->type = NETLBL_NLTYPE_CALIPSO;
diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c
index 409a3ae47ce2..5e1239cef000 100644
--- a/net/netlabel/netlabel_kapi.c
+++ b/net/netlabel/netlabel_kapi.c
@@ -734,6 +734,12 @@ int netlbl_catmap_getlong(struct netlbl_lsm_catmap *catmap,
 	if ((off & (BITS_PER_LONG - 1)) != 0)
 		return -EINVAL;
 
+	/* a null catmap is equivalent to an empty one */
+	if (!catmap) {
+		*offset = (u32)-1;
+		return 0;
+	}
+
 	if (off < catmap->startbit) {
 		off = catmap->startbit;
 		*offset = off;
-- 
2.26.2


From 64106b15b36059e1bc60efe7a4d28a57a683cf22 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Tue, 12 May 2020 21:45:53 +0200
Subject: [PATCH 04/19] net: phy: fix aneg restart in phy_ethtool_set_eee

[ Upstream commit 9de5d235b60a7cdfcdd5461e70c5663e713fde87 ]

phy_restart_aneg() enables aneg in the PHY. That's not what we want
if phydev->autoneg is disabled. In this case still update EEE
advertisement register, but don't enable aneg and don't trigger an
aneg restart.

Fixes: f75abeb8338e ("net: phy: restart phy autonegotiation after EEE advertisment change")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index ea890d802ffe..54e5d4f9622c 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -1160,9 +1160,11 @@ int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data)
 		/* Restart autonegotiation so the new modes get sent to the
 		 * link partner.
 		 */
-		ret = phy_restart_aneg(phydev);
-		if (ret < 0)
-			return ret;
+		if (phydev->autoneg == AUTONEG_ENABLE) {
+			ret = phy_restart_aneg(phydev);
+			if (ret < 0)
+				return ret;
+		}
 	}
 
 	return 0;
-- 
2.26.2


From ad3d6f713c4ba61ac0a556c6bbb14e53463d784f Mon Sep 17 00:00:00 2001
From: Vinod Koul <vkoul@kernel.org>
Date: Thu, 14 May 2020 11:58:36 +0530
Subject: [PATCH 05/19] net: stmmac: fix num_por initialization

[ Upstream commit fd4a5177382230d39e0d95632d98103fb2938383 ]

Driver missed initializing num_por which is one of the por values that
driver configures to hardware. In order to get these values, add a new
structure ethqos_emac_driver_data which holds por and num_por values
and populate that in driver probe.

Fixes: a7c30e62d4b8 ("net: stmmac: Add driver for Qualcomm ethqos")
Reported-by: Rahul Ankushrao Kawadgave <rahulak@qti.qualcomm.com>
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Reviewed-by: Amit Kucheria <amit.kucheria@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
index e0a5fe83d8e0..bfc4a92f1d92 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
@@ -75,6 +75,11 @@ struct ethqos_emac_por {
 	unsigned int value;
 };
 
+struct ethqos_emac_driver_data {
+	const struct ethqos_emac_por *por;
+	unsigned int num_por;
+};
+
 struct qcom_ethqos {
 	struct platform_device *pdev;
 	void __iomem *rgmii_base;
@@ -171,6 +176,11 @@ static const struct ethqos_emac_por emac_v2_3_0_por[] = {
 	{ .offset = RGMII_IO_MACRO_CONFIG2,	.value = 0x00002060 },
 };
 
+static const struct ethqos_emac_driver_data emac_v2_3_0_data = {
+	.por = emac_v2_3_0_por,
+	.num_por = ARRAY_SIZE(emac_v2_3_0_por),
+};
+
 static int ethqos_dll_configure(struct qcom_ethqos *ethqos)
 {
 	unsigned int val;
@@ -442,6 +452,7 @@ static int qcom_ethqos_probe(struct platform_device *pdev)
 	struct device_node *np = pdev->dev.of_node;
 	struct plat_stmmacenet_data *plat_dat;
 	struct stmmac_resources stmmac_res;
+	const struct ethqos_emac_driver_data *data;
 	struct qcom_ethqos *ethqos;
 	struct resource *res;
 	int ret;
@@ -471,7 +482,9 @@ static int qcom_ethqos_probe(struct platform_device *pdev)
 		goto err_mem;
 	}
 
-	ethqos->por = of_device_get_match_data(&pdev->dev);
+	data = of_device_get_match_data(&pdev->dev);
+	ethqos->por = data->por;
+	ethqos->num_por = data->num_por;
 
 	ethqos->rgmii_clk = devm_clk_get(&pdev->dev, "rgmii");
 	if (IS_ERR(ethqos->rgmii_clk)) {
@@ -526,7 +539,7 @@ static int qcom_ethqos_remove(struct platform_device *pdev)
 }
 
 static const struct of_device_id qcom_ethqos_match[] = {
-	{ .compatible = "qcom,qcs404-ethqos", .data = &emac_v2_3_0_por},
+	{ .compatible = "qcom,qcs404-ethqos", .data = &emac_v2_3_0_data},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, qcom_ethqos_match);
-- 
2.26.2


From 6b5523b9f5305af848320963672aa8a9774136ef Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Thu, 14 May 2020 12:15:39 +0200
Subject: [PATCH 06/19] pppoe: only process PADT targeted at local interfaces
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit b8c158395119be62294da73646a3953c29ac974b ]

We don't want to disconnect a session because of a stray PADT arriving
while the interface is in promiscuous mode.
Furthermore, multicast and broadcast packets make no sense here, so
only PACKET_HOST is accepted.

Reported-by: David Balažic <xerces9@gmail.com>
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pppoe.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index a44dd3c8af63..087b01684135 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -492,6 +492,9 @@ static int pppoe_disc_rcv(struct sk_buff *skb, struct net_device *dev,
 	if (!skb)
 		goto out;
 
+	if (skb->pkt_type != PACKET_HOST)
+		goto abort;
+
 	if (!pskb_may_pull(skb, sizeof(struct pppoe_hdr)))
 		goto abort;
 
-- 
2.26.2


From c26e9ed0a58fdce2aff725a26123cff323fb4d42 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Maciej=20=C5=BBenczykowski?= <maze@google.com>
Date: Tue, 5 May 2020 11:57:23 -0700
Subject: [PATCH 07/19] Revert "ipv6: add mtu lock check in
 __ip6_rt_update_pmtu"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 09454fd0a4ce23cb3d8af65066c91a1bf27120dd ]

This reverts commit 19bda36c4299ce3d7e5bce10bebe01764a655a6d:

| ipv6: add mtu lock check in __ip6_rt_update_pmtu
|
| Prior to this patch, ipv6 didn't do mtu lock check in ip6_update_pmtu.
| It leaded to that mtu lock doesn't really work when receiving the pkt
| of ICMPV6_PKT_TOOBIG.
|
| This patch is to add mtu lock check in __ip6_rt_update_pmtu just as ipv4
| did in __ip_rt_update_pmtu.

The above reasoning is incorrect.  IPv6 *requires* icmp based pmtu to work.
There's already a comment to this effect elsewhere in the kernel:

  $ git grep -p -B1 -A3 'RTAX_MTU lock'
  net/ipv6/route.c=4813=

  static int rt6_mtu_change_route(struct fib6_info *f6i, void *p_arg)
  ...
    /* In IPv6 pmtu discovery is not optional,
       so that RTAX_MTU lock cannot disable it.
       We still use this lock to block changes
       caused by addrconf/ndisc.
    */

This reverts to the pre-4.9 behaviour.

Cc: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Xin Long <lucien.xin@gmail.com>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Maciej Żenczykowski <maze@google.com>
Fixes: 19bda36c4299 ("ipv6: add mtu lock check in __ip6_rt_update_pmtu")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index c81d8e9e5169..3b4af0a8bca6 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2728,8 +2728,10 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
 	const struct in6_addr *daddr, *saddr;
 	struct rt6_info *rt6 = (struct rt6_info *)dst;
 
-	if (dst_metric_locked(dst, RTAX_MTU))
-		return;
+	/* Note: do *NOT* check dst_metric_locked(dst, RTAX_MTU)
+	 * IPv6 pmtu discovery isn't optional, so 'mtu lock' cannot disable it.
+	 * [see also comment in rt6_mtu_change_route()]
+	 */
 
 	if (iph) {
 		daddr = &iph->daddr;
-- 
2.26.2


From a723b8a9976f37214a6384c47812ca877d7d43ef Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 14 May 2020 13:58:13 -0700
Subject: [PATCH 08/19] tcp: fix error recovery in tcp_zerocopy_receive()

[ Upstream commit e776af608f692a7a647455106295fa34469e7475 ]

If user provides wrong virtual address in TCP_ZEROCOPY_RECEIVE
operation we want to return -EINVAL error.

But depending on zc->recv_skip_hint content, we might return
-EIO error if the socket has SOCK_DONE set.

Make sure to return -EINVAL in this case.

BUG: KMSAN: uninit-value in tcp_zerocopy_receive net/ipv4/tcp.c:1833 [inline]
BUG: KMSAN: uninit-value in do_tcp_getsockopt+0x4494/0x6320 net/ipv4/tcp.c:3685
CPU: 1 PID: 625 Comm: syz-executor.0 Not tainted 5.7.0-rc4-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c9/0x220 lib/dump_stack.c:118
 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:121
 __msan_warning+0x58/0xa0 mm/kmsan/kmsan_instr.c:215
 tcp_zerocopy_receive net/ipv4/tcp.c:1833 [inline]
 do_tcp_getsockopt+0x4494/0x6320 net/ipv4/tcp.c:3685
 tcp_getsockopt+0xf8/0x1f0 net/ipv4/tcp.c:3728
 sock_common_getsockopt+0x13f/0x180 net/core/sock.c:3131
 __sys_getsockopt+0x533/0x7b0 net/socket.c:2177
 __do_sys_getsockopt net/socket.c:2192 [inline]
 __se_sys_getsockopt+0xe1/0x100 net/socket.c:2189
 __x64_sys_getsockopt+0x62/0x80 net/socket.c:2189
 do_syscall_64+0xb8/0x160 arch/x86/entry/common.c:297
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x45c829
Code: 0d b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 db b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f1deeb72c78 EFLAGS: 00000246 ORIG_RAX: 0000000000000037
RAX: ffffffffffffffda RBX: 00000000004e01e0 RCX: 000000000045c829
RDX: 0000000000000023 RSI: 0000000000000006 RDI: 0000000000000009
RBP: 000000000078bf00 R08: 0000000020000200 R09: 0000000000000000
R10: 00000000200001c0 R11: 0000000000000246 R12: 00000000ffffffff
R13: 00000000000001d8 R14: 00000000004d3038 R15: 00007f1deeb736d4

Local variable ----zc@do_tcp_getsockopt created at:
 do_tcp_getsockopt+0x1a74/0x6320 net/ipv4/tcp.c:3670
 do_tcp_getsockopt+0x1a74/0x6320 net/ipv4/tcp.c:3670

Fixes: 05255b823a61 ("tcp: add TCP_ZEROCOPY_RECEIVE support for zerocopy receive")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e378ff17f8c6..83829764773b 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1757,10 +1757,11 @@ static int tcp_zerocopy_receive(struct sock *sk,
 
 	down_read(&current->mm->mmap_sem);
 
-	ret = -EINVAL;
 	vma = find_vma(current->mm, address);
-	if (!vma || vma->vm_start > address || vma->vm_ops != &tcp_vm_ops)
-		goto out;
+	if (!vma || vma->vm_start > address || vma->vm_ops != &tcp_vm_ops) {
+		up_read(&current->mm->mmap_sem);
+		return -EINVAL;
+	}
 	zc->length = min_t(unsigned long, zc->length, vma->vm_end - address);
 
 	tp = tcp_sk(sk);
-- 
2.26.2


From c994348aa8a1a67c3d8146c799d29952c6ed0896 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 12 May 2020 06:54:30 -0700
Subject: [PATCH 09/19] tcp: fix SO_RCVLOWAT hangs with fat skbs

[ Upstream commit 24adbc1676af4e134e709ddc7f34cf2adc2131e4 ]

We autotune rcvbuf whenever SO_RCVLOWAT is set to account for 100%
overhead in tcp_set_rcvlowat()

This works well when skb->len/skb->truesize ratio is bigger than 0.5

But if we receive packets with small MSS, we can end up in a situation
where not enough bytes are available in the receive queue to satisfy
RCVLOWAT setting.
As our sk_rcvbuf limit is hit, we send zero windows in ACK packets,
preventing remote peer from sending more data.

Even autotuning does not help, because it only triggers at the time
user process drains the queue. If no EPOLLIN is generated, this
can not happen.

Note poll() has a similar issue, after commit
c7004482e8dc ("tcp: Respect SO_RCVLOWAT in tcp_poll().")

Fixes: 03f45c883c6f ("tcp: avoid extra wakeups for SO_RCVLOWAT users")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h    | 13 +++++++++++++
 net/ipv4/tcp.c       | 14 +++++++++++---
 net/ipv4/tcp_input.c |  3 ++-
 3 files changed, 26 insertions(+), 4 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index cce285f70c8e..7cf1b4972c66 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1401,6 +1401,19 @@ static inline int tcp_full_space(const struct sock *sk)
 	return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf));
 }
 
+/* We provision sk_rcvbuf around 200% of sk_rcvlowat.
+ * If 87.5 % (7/8) of the space has been consumed, we want to override
+ * SO_RCVLOWAT constraint, since we are receiving skbs with too small
+ * len/truesize ratio.
+ */
+static inline bool tcp_rmem_pressure(const struct sock *sk)
+{
+	int rcvbuf = READ_ONCE(sk->sk_rcvbuf);
+	int threshold = rcvbuf - (rcvbuf >> 3);
+
+	return atomic_read(&sk->sk_rmem_alloc) > threshold;
+}
+
 extern void tcp_openreq_init_rwin(struct request_sock *req,
 				  const struct sock *sk_listener,
 				  const struct dst_entry *dst);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 83829764773b..2a658c2c8903 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -477,9 +477,17 @@ static void tcp_tx_timestamp(struct sock *sk, u16 tsflags)
 static inline bool tcp_stream_is_readable(const struct tcp_sock *tp,
 					  int target, struct sock *sk)
 {
-	return (READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq) >= target) ||
-		(sk->sk_prot->stream_memory_read ?
-		sk->sk_prot->stream_memory_read(sk) : false);
+	int avail = READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq);
+
+	if (avail > 0) {
+		if (avail >= target)
+			return true;
+		if (tcp_rmem_pressure(sk))
+			return true;
+	}
+	if (sk->sk_prot->stream_memory_read)
+		return sk->sk_prot->stream_memory_read(sk);
+	return false;
 }
 
 /*
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 5af22c9712a6..677facbeed26 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4751,7 +4751,8 @@ void tcp_data_ready(struct sock *sk)
 	const struct tcp_sock *tp = tcp_sk(sk);
 	int avail = tp->rcv_nxt - tp->copied_seq;
 
-	if (avail < sk->sk_rcvlowat && !sock_flag(sk, SOCK_DONE))
+	if (avail < sk->sk_rcvlowat && !tcp_rmem_pressure(sk) &&
+	    !sock_flag(sk, SOCK_DONE))
 		return;
 
 	sk->sk_data_ready(sk);
-- 
2.26.2


From 72990d836130354988c33f3787e2b272709714ad Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Thu, 7 May 2020 03:25:56 -0400
Subject: [PATCH 10/19] virtio_net: fix lockdep warning on 32 bit

[ Upstream commit 01c3259818a11f3cc3cd767adbae6b45849c03c1 ]

When we fill up a receive VQ, try_fill_recv currently tries to count
kicks using a 64 bit stats counter. Turns out, on a 32 bit kernel that
uses a seqcount. sequence counts are "lock" constructs where you need to
make sure that writers are serialized.

In turn, this means that we mustn't run two try_fill_recv concurrently.
Which of course we don't. We do run try_fill_recv sometimes from a
softirq napi context, and sometimes from a fully preemptible context,
but the later always runs with napi disabled.

However, when it comes to the seqcount, lockdep is trying to enforce the
rule that the same lock isn't accessed from preemptible and softirq
context - it doesn't know about napi being enabled/disabled. This causes
a false-positive warning:

WARNING: inconsistent lock state
...
inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage.

As a work around, shut down the warning by switching
to u64_stats_update_begin_irqsave - that works by disabling
interrupts on 32 bit only, is a NOP on 64 bit.

Reported-by: Thomas Gleixner <tglx@linutronix.de>
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 5a635f028bdc..030d30603c29 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1231,9 +1231,11 @@ static bool try_fill_recv(struct virtnet_info *vi, struct receive_queue *rq,
 			break;
 	} while (rq->vq->num_free);
 	if (virtqueue_kick_prepare(rq->vq) && virtqueue_notify(rq->vq)) {
-		u64_stats_update_begin(&rq->stats.syncp);
+		unsigned long flags;
+
+		flags = u64_stats_update_begin_irqsave(&rq->stats.syncp);
 		rq->stats.kicks++;
-		u64_stats_update_end(&rq->stats.syncp);
+		u64_stats_update_end_irqrestore(&rq->stats.syncp, flags);
 	}
 
 	return !oom;
-- 
2.26.2


From 0d8c47fa56af7baec45d35c4e84aa5dac166ea43 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Fri, 8 May 2020 17:37:20 +0300
Subject: [PATCH 11/19] dpaa2-eth: prevent array underflow in update_cls_rule()

[ Upstream commit 6d32a5119811d2e9b5caa284181944c6f1f192ed ]

The "location" is controlled by the user via the ethtool_set_rxnfc()
function.  This update_cls_rule() function checks for array overflows
but it doesn't check if the value is negative.  I have changed the type
to unsigned to prevent array underflows.

Fixes: afb90dbb5f78 ("dpaa2-eth: Add ethtool support for flow classification")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
index dc9a6c36cac0..e4d9fb0e72bf 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
@@ -590,7 +590,7 @@ static int num_rules(struct dpaa2_eth_priv *priv)
 
 static int update_cls_rule(struct net_device *net_dev,
 			   struct ethtool_rx_flow_spec *new_fs,
-			   int location)
+			   unsigned int location)
 {
 	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
 	struct dpaa2_eth_cls_rule *rule;
-- 
2.26.2


From 9df0cf0be131b7a12789e1eb0a66238a6ccc5bb1 Mon Sep 17 00:00:00 2001
From: Luo bin <luobin9@huawei.com>
Date: Sun, 10 May 2020 19:01:08 +0000
Subject: [PATCH 12/19] hinic: fix a bug of ndo_stop

[ Upstream commit e8a1b0efd632d1c9db7d4e93da66377c7b524862 ]

if some function in ndo_stop interface returns failure because of
hardware fault, must go on excuting rest steps rather than return
failure directly, otherwise will cause memory leak.And bump the
timeout for SET_FUNC_STATE to ensure that cmd won't return failure
when hw is busy. Otherwise hw may stomp host memory if we free
memory regardless of the return value of SET_FUNC_STATE.

Fixes: 51ba902a16e6 ("net-next/hinic: Initialize hw interface")
Signed-off-by: Luo bin <luobin9@huawei.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/huawei/hinic/hinic_hw_mgmt.c    | 16 ++++++++++++----
 drivers/net/ethernet/huawei/hinic/hinic_main.c   | 16 ++--------------
 2 files changed, 14 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
index 8995e32dd1c0..992908e6eebf 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
@@ -45,6 +45,8 @@
 
 #define MGMT_MSG_TIMEOUT                5000
 
+#define SET_FUNC_PORT_MGMT_TIMEOUT	25000
+
 #define mgmt_to_pfhwdev(pf_mgmt)        \
 		container_of(pf_mgmt, struct hinic_pfhwdev, pf_to_mgmt)
 
@@ -238,12 +240,13 @@ static int msg_to_mgmt_sync(struct hinic_pf_to_mgmt *pf_to_mgmt,
 			    u8 *buf_in, u16 in_size,
 			    u8 *buf_out, u16 *out_size,
 			    enum mgmt_direction_type direction,
-			    u16 resp_msg_id)
+			    u16 resp_msg_id, u32 timeout)
 {
 	struct hinic_hwif *hwif = pf_to_mgmt->hwif;
 	struct pci_dev *pdev = hwif->pdev;
 	struct hinic_recv_msg *recv_msg;
 	struct completion *recv_done;
+	unsigned long timeo;
 	u16 msg_id;
 	int err;
 
@@ -267,8 +270,9 @@ static int msg_to_mgmt_sync(struct hinic_pf_to_mgmt *pf_to_mgmt,
 		goto unlock_sync_msg;
 	}
 
-	if (!wait_for_completion_timeout(recv_done,
-					 msecs_to_jiffies(MGMT_MSG_TIMEOUT))) {
+	timeo = msecs_to_jiffies(timeout ? timeout : MGMT_MSG_TIMEOUT);
+
+	if (!wait_for_completion_timeout(recv_done, timeo)) {
 		dev_err(&pdev->dev, "MGMT timeout, MSG id = %d\n", msg_id);
 		err = -ETIMEDOUT;
 		goto unlock_sync_msg;
@@ -342,6 +346,7 @@ int hinic_msg_to_mgmt(struct hinic_pf_to_mgmt *pf_to_mgmt,
 {
 	struct hinic_hwif *hwif = pf_to_mgmt->hwif;
 	struct pci_dev *pdev = hwif->pdev;
+	u32 timeout = 0;
 
 	if (sync != HINIC_MGMT_MSG_SYNC) {
 		dev_err(&pdev->dev, "Invalid MGMT msg type\n");
@@ -353,9 +358,12 @@ int hinic_msg_to_mgmt(struct hinic_pf_to_mgmt *pf_to_mgmt,
 		return -EINVAL;
 	}
 
+	if (cmd == HINIC_PORT_CMD_SET_FUNC_STATE)
+		timeout = SET_FUNC_PORT_MGMT_TIMEOUT;
+
 	return msg_to_mgmt_sync(pf_to_mgmt, mod, cmd, buf_in, in_size,
 				buf_out, out_size, MGMT_DIRECT_SEND,
-				MSG_NOT_RESP);
+				MSG_NOT_RESP, timeout);
 }
 
 /**
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c
index 42d00b049c6e..3f739ce40201 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_main.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c
@@ -483,7 +483,6 @@ static int hinic_close(struct net_device *netdev)
 {
 	struct hinic_dev *nic_dev = netdev_priv(netdev);
 	unsigned int flags;
-	int err;
 
 	down(&nic_dev->mgmt_lock);
 
@@ -497,20 +496,9 @@ static int hinic_close(struct net_device *netdev)
 
 	up(&nic_dev->mgmt_lock);
 
-	err = hinic_port_set_func_state(nic_dev, HINIC_FUNC_PORT_DISABLE);
-	if (err) {
-		netif_err(nic_dev, drv, netdev,
-			  "Failed to set func port state\n");
-		nic_dev->flags |= (flags & HINIC_INTF_UP);
-		return err;
-	}
+	hinic_port_set_state(nic_dev, HINIC_PORT_DISABLE);
 
-	err = hinic_port_set_state(nic_dev, HINIC_PORT_DISABLE);
-	if (err) {
-		netif_err(nic_dev, drv, netdev, "Failed to set port state\n");
-		nic_dev->flags |= (flags & HINIC_INTF_UP);
-		return err;
-	}
+	hinic_port_set_func_state(nic_dev, HINIC_FUNC_PORT_DISABLE);
 
 	if (nic_dev->flags & HINIC_RSS_ENABLE) {
 		hinic_rss_deinit(nic_dev);
-- 
2.26.2


From 8bd01eb849518d203c9b73d3280b3d9ef58ce04c Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Sat, 9 May 2020 16:45:44 -0700
Subject: [PATCH 13/19] net: dsa: loop: Add module soft dependency

[ Upstream commit 3047211ca11bf77b3ecbce045c0aa544d934b945 ]

There is a soft dependency against dsa_loop_bdinfo.ko which sets up the
MDIO device registration, since there are no symbols referenced by
dsa_loop.ko, there is no automatic loading of dsa_loop_bdinfo.ko which
is needed.

Fixes: 98cd1552ea27 ("net: dsa: Mock-up driver")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/dsa_loop.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c
index 925ed135a4d9..0df6c2b9484a 100644
--- a/drivers/net/dsa/dsa_loop.c
+++ b/drivers/net/dsa/dsa_loop.c
@@ -356,6 +356,7 @@ static void __exit dsa_loop_exit(void)
 }
 module_exit(dsa_loop_exit);
 
+MODULE_SOFTDEP("pre: dsa_loop_bdinfo");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Florian Fainelli");
 MODULE_DESCRIPTION("DSA loopback driver");
-- 
2.26.2


From 94fb04e8da1e4c3b68c7973613753518ba75cde5 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 8 May 2020 19:28:34 +0200
Subject: [PATCH 14/19] net: ipv4: really enforce backoff for redirects

[ Upstream commit 57644431a6c2faac5d754ebd35780cf43a531b1a ]

In commit b406472b5ad7 ("net: ipv4: avoid mixed n_redirects and
rate_tokens usage") I missed the fact that a 0 'rate_tokens' will
bypass the backoff algorithm.

Since rate_tokens is cleared after a redirect silence, and never
incremented on redirects, if the host keeps receiving packets
requiring redirect it will reply ignoring the backoff.

Additionally, the 'rate_last' field will be updated with the
cadence of the ingress packet requiring redirect. If that rate is
high enough, that will prevent the host from generating any
other kind of ICMP messages

The check for a zero 'rate_tokens' value was likely a shortcut
to avoid the more complex backoff algorithm after a redirect
silence period. Address the issue checking for 'n_redirects'
instead, which is incremented on successful redirect, and
does not interfere with other ICMP replies.

Fixes: b406472b5ad7 ("net: ipv4: avoid mixed n_redirects and rate_tokens usage")
Reported-and-tested-by: Colin Walters <walters@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/route.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index fe34e9e0912a..558ddf7ab395 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -914,7 +914,7 @@ void ip_rt_send_redirect(struct sk_buff *skb)
 	/* Check for load limit; set rate_last to the latest sent
 	 * redirect.
 	 */
-	if (peer->rate_tokens == 0 ||
+	if (peer->n_redirects == 0 ||
 	    time_after(jiffies,
 		       (peer->rate_last +
 			(ip_rt_redirect_load << peer->n_redirects)))) {
-- 
2.26.2


From b495d042f274cbf49f73afa5edb75a21464ec24f Mon Sep 17 00:00:00 2001
From: Zefan Li <lizefan@huawei.com>
Date: Sat, 9 May 2020 11:32:10 +0800
Subject: [PATCH 15/19] netprio_cgroup: Fix unlimited memory leak of v2 cgroups

[ Upstream commit 090e28b229af92dc5b40786ca673999d59e73056 ]

If systemd is configured to use hybrid mode which enables the use of
both cgroup v1 and v2, systemd will create new cgroup on both the default
root (v2) and netprio_cgroup hierarchy (v1) for a new session and attach
task to the two cgroups. If the task does some network thing then the v2
cgroup can never be freed after the session exited.

One of our machines ran into OOM due to this memory leak.

In the scenario described above when sk_alloc() is called
cgroup_sk_alloc() thought it's in v2 mode, so it stores
the cgroup pointer in sk->sk_cgrp_data and increments
the cgroup refcnt, but then sock_update_netprioidx()
thought it's in v1 mode, so it stores netprioidx value
in sk->sk_cgrp_data, so the cgroup refcnt will never be freed.

Currently we do the mode switch when someone writes to the ifpriomap
cgroup control file. The easiest fix is to also do the switch when
a task is attached to a new cgroup.

Fixes: bd1060a1d671 ("sock, cgroup: add sock->sk_cgroup")
Reported-by: Yang Yingliang <yangyingliang@huawei.com>
Tested-by: Yang Yingliang <yangyingliang@huawei.com>
Signed-off-by: Zefan Li <lizefan@huawei.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/netprio_cgroup.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index 256b7954b720..8618242c677a 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -236,6 +236,8 @@ static void net_prio_attach(struct cgroup_taskset *tset)
 	struct task_struct *p;
 	struct cgroup_subsys_state *css;
 
+	cgroup_sk_alloc_disable();
+
 	cgroup_taskset_for_each(p, css, tset) {
 		void *v = (void *)(unsigned long)css->cgroup->id;
 
-- 
2.26.2


From ca2a5ba453ad52881c3368e67302c3032e819011 Mon Sep 17 00:00:00 2001
From: Kelly Littlepage <kelly@onechronos.com>
Date: Fri, 8 May 2020 19:58:46 +0000
Subject: [PATCH 16/19] net: tcp: fix rx timestamp behavior for tcp_recvmsg

[ Upstream commit cc4de047b33be247f9c8150d3e496743a49642b8 ]

The stated intent of the original commit is to is to "return the timestamp
corresponding to the highest sequence number data returned." The current
implementation returns the timestamp for the last byte of the last fully
read skb, which is not necessarily the last byte in the recv buffer. This
patch converts behavior to the original definition, and to the behavior of
the previous draft versions of commit 98aaa913b4ed ("tcp: Extend
SOF_TIMESTAMPING_RX_SOFTWARE to TCP recvmsg") which also match this
behavior.

Fixes: 98aaa913b4ed ("tcp: Extend SOF_TIMESTAMPING_RX_SOFTWARE to TCP recvmsg")
Co-developed-by: Iris Liu <iris@onechronos.com>
Signed-off-by: Iris Liu <iris@onechronos.com>
Signed-off-by: Kelly Littlepage <kelly@onechronos.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 2a658c2c8903..fe3cdeddd097 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2158,13 +2158,15 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 			tp->urg_data = 0;
 			tcp_fast_path_check(sk);
 		}
-		if (used + offset < skb->len)
-			continue;
 
 		if (TCP_SKB_CB(skb)->has_rxtstamp) {
 			tcp_update_recv_tstamps(skb, &tss);
 			cmsg_flags |= 2;
 		}
+
+		if (used + offset < skb->len)
+			continue;
+
 		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
 			goto found_fin_ok;
 		if (!(flags & MSG_PEEK))
-- 
2.26.2


From 3c5595a2940b1fd073e40041f4e4b16990beb4cc Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Fri, 8 May 2020 07:27:35 +0000
Subject: [PATCH 17/19] nfp: abm: fix error return code in nfp_abm_vnic_alloc()

[ Upstream commit 5099dea0a59f1c89525bb0ceac36689178a4c125 ]

Fix to return negative error code -ENOMEM from the kzalloc() error
handling case instead of 0, as done elsewhere in this function.

Fixes: 174ab544e3bc ("nfp: abm: add cls_u32 offload for simple band classification")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/netronome/nfp/abm/main.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.c b/drivers/net/ethernet/netronome/nfp/abm/main.c
index 354efffac0f9..bdbf0726145e 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.c
@@ -333,8 +333,10 @@ nfp_abm_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, unsigned int id)
 		goto err_free_alink;
 
 	alink->prio_map = kzalloc(abm->prio_map_len, GFP_KERNEL);
-	if (!alink->prio_map)
+	if (!alink->prio_map) {
+		err = -ENOMEM;
 		goto err_free_alink;
+	}
 
 	/* This is a multi-host app, make sure MAC/PHY is up, but don't
 	 * make the MAC/PHY state follow the state of any of the ports.
-- 
2.26.2


From bb51ab73ce1362315df1d2a4f36c6e5547a533a4 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 8 May 2020 08:24:14 +0200
Subject: [PATCH 18/19] r8169: re-establish support for RTL8401 chip version
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 1f8492df081bd66255764f3ce82ba1b2c37def49 ]

r8169 never had native support for the RTL8401, however it reportedly
worked with the fallback to RTL8101e [0]. Therefore let's add this
as an explicit assignment.

[0] https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=956868

Fixes: b4cc2dcc9c7c ("r8169: remove default chip versions")
Reported-by: Camaleón <noelamac@gmail.com>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/r8169_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 3bc6d1ef29ec..6fa9852e3f97 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -2202,6 +2202,8 @@ static void rtl8169_get_mac_version(struct rtl8169_private *tp)
 		{ 0x7cf, 0x348,	RTL_GIGA_MAC_VER_07 },
 		{ 0x7cf, 0x248,	RTL_GIGA_MAC_VER_07 },
 		{ 0x7cf, 0x340,	RTL_GIGA_MAC_VER_13 },
+		/* RTL8401, reportedly works if treated as RTL8101e */
+		{ 0x7cf, 0x240,	RTL_GIGA_MAC_VER_13 },
 		{ 0x7cf, 0x343,	RTL_GIGA_MAC_VER_10 },
 		{ 0x7cf, 0x342,	RTL_GIGA_MAC_VER_16 },
 		{ 0x7c8, 0x348,	RTL_GIGA_MAC_VER_09 },
-- 
2.26.2


From bd30c2ccd63692e87559c8783086afa46ea0de9f Mon Sep 17 00:00:00 2001
From: Vincent Minet <v.minet@criteo.com>
Date: Fri, 8 May 2020 00:14:22 +0200
Subject: [PATCH 19/19] umh: fix memory leak on execve failure

[ Upstream commit db803036ada7d61d096783726f9771b3fc540370 ]

If a UMH process created by fork_usermode_blob() fails to execute,
a pair of struct file allocated by umh_pipe_setup() will leak.

Under normal conditions, the caller (like bpfilter) needs to manage the
lifetime of the UMH and its two pipes. But when fork_usermode_blob()
fails, the caller doesn't really have a way to know what needs to be
done. It seems better to do the cleanup ourselves in this case.

Fixes: 449325b52b7a ("umh: introduce fork_usermode_blob() helper")
Signed-off-by: Vincent Minet <v.minet@criteo.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 kernel/umh.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/kernel/umh.c b/kernel/umh.c
index 11bf5eea474c..3474d6aa55d8 100644
--- a/kernel/umh.c
+++ b/kernel/umh.c
@@ -475,6 +475,12 @@ static void umh_clean_and_save_pid(struct subprocess_info *info)
 {
 	struct umh_info *umh_info = info->data;
 
+	/* cleanup if umh_pipe_setup() was successful but exec failed */
+	if (info->pid && info->retval) {
+		fput(umh_info->pipe_to_umh);
+		fput(umh_info->pipe_from_umh);
+	}
+
 	argv_free(info->argv);
 	umh_info->pid = info->pid;
 }
-- 
2.26.2


[-- Attachment #3: net_56.mbox --]
[-- Type: Application/Octet-Stream, Size: 49148 bytes --]

From 3c46ae2ddb4a71a1ea580375e5fddad563adf068 Mon Sep 17 00:00:00 2001
From: Ioana Ciornei <ioana.ciornei@nxp.com>
Date: Fri, 15 May 2020 15:30:22 +0300
Subject: [PATCH 01/21] dpaa2-eth: properly handle buffer size restrictions

[ Upstream commit efa6a7d07523ffbbf6503c1a7eeb52201c15c0e3 ]

Depending on the WRIOP version, the buffer size on the RX path must by a
multiple of 64 or 256. Handle this restriction properly by aligning down
the buffer size to the necessary value. Also, use the new buffer size
dynamically computed instead of the compile time one.

Fixes: 27c874867c4e ("dpaa2-eth: Use a single page per Rx buffer")
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/freescale/dpaa2/dpaa2-eth.c  | 29 +++++++++++--------
 .../net/ethernet/freescale/dpaa2/dpaa2-eth.h  |  1 +
 2 files changed, 18 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 7ff147e89426..d9bbaa734d98 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -86,7 +86,7 @@ static void free_rx_fd(struct dpaa2_eth_priv *priv,
 	for (i = 1; i < DPAA2_ETH_MAX_SG_ENTRIES; i++) {
 		addr = dpaa2_sg_get_addr(&sgt[i]);
 		sg_vaddr = dpaa2_iova_to_virt(priv->iommu_domain, addr);
-		dma_unmap_page(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
+		dma_unmap_page(dev, addr, priv->rx_buf_size,
 			       DMA_BIDIRECTIONAL);
 
 		free_pages((unsigned long)sg_vaddr, 0);
@@ -144,7 +144,7 @@ static struct sk_buff *build_frag_skb(struct dpaa2_eth_priv *priv,
 		/* Get the address and length from the S/G entry */
 		sg_addr = dpaa2_sg_get_addr(sge);
 		sg_vaddr = dpaa2_iova_to_virt(priv->iommu_domain, sg_addr);
-		dma_unmap_page(dev, sg_addr, DPAA2_ETH_RX_BUF_SIZE,
+		dma_unmap_page(dev, sg_addr, priv->rx_buf_size,
 			       DMA_BIDIRECTIONAL);
 
 		sg_length = dpaa2_sg_get_len(sge);
@@ -185,7 +185,7 @@ static struct sk_buff *build_frag_skb(struct dpaa2_eth_priv *priv,
 				(page_address(page) - page_address(head_page));
 
 			skb_add_rx_frag(skb, i - 1, head_page, page_offset,
-					sg_length, DPAA2_ETH_RX_BUF_SIZE);
+					sg_length, priv->rx_buf_size);
 		}
 
 		if (dpaa2_sg_is_final(sge))
@@ -211,7 +211,7 @@ static void free_bufs(struct dpaa2_eth_priv *priv, u64 *buf_array, int count)
 
 	for (i = 0; i < count; i++) {
 		vaddr = dpaa2_iova_to_virt(priv->iommu_domain, buf_array[i]);
-		dma_unmap_page(dev, buf_array[i], DPAA2_ETH_RX_BUF_SIZE,
+		dma_unmap_page(dev, buf_array[i], priv->rx_buf_size,
 			       DMA_BIDIRECTIONAL);
 		free_pages((unsigned long)vaddr, 0);
 	}
@@ -335,7 +335,7 @@ static u32 run_xdp(struct dpaa2_eth_priv *priv,
 		break;
 	case XDP_REDIRECT:
 		dma_unmap_page(priv->net_dev->dev.parent, addr,
-			       DPAA2_ETH_RX_BUF_SIZE, DMA_BIDIRECTIONAL);
+			       priv->rx_buf_size, DMA_BIDIRECTIONAL);
 		ch->buf_count--;
 		xdp.data_hard_start = vaddr;
 		err = xdp_do_redirect(priv->net_dev, &xdp, xdp_prog);
@@ -374,7 +374,7 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 	trace_dpaa2_rx_fd(priv->net_dev, fd);
 
 	vaddr = dpaa2_iova_to_virt(priv->iommu_domain, addr);
-	dma_sync_single_for_cpu(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
+	dma_sync_single_for_cpu(dev, addr, priv->rx_buf_size,
 				DMA_BIDIRECTIONAL);
 
 	fas = dpaa2_get_fas(vaddr, false);
@@ -393,13 +393,13 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 			return;
 		}
 
-		dma_unmap_page(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
+		dma_unmap_page(dev, addr, priv->rx_buf_size,
 			       DMA_BIDIRECTIONAL);
 		skb = build_linear_skb(ch, fd, vaddr);
 	} else if (fd_format == dpaa2_fd_sg) {
 		WARN_ON(priv->xdp_prog);
 
-		dma_unmap_page(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
+		dma_unmap_page(dev, addr, priv->rx_buf_size,
 			       DMA_BIDIRECTIONAL);
 		skb = build_frag_skb(priv, ch, buf_data);
 		free_pages((unsigned long)vaddr, 0);
@@ -974,7 +974,7 @@ static int add_bufs(struct dpaa2_eth_priv *priv,
 		if (!page)
 			goto err_alloc;
 
-		addr = dma_map_page(dev, page, 0, DPAA2_ETH_RX_BUF_SIZE,
+		addr = dma_map_page(dev, page, 0, priv->rx_buf_size,
 				    DMA_BIDIRECTIONAL);
 		if (unlikely(dma_mapping_error(dev, addr)))
 			goto err_map;
@@ -984,7 +984,7 @@ static int add_bufs(struct dpaa2_eth_priv *priv,
 		/* tracing point */
 		trace_dpaa2_eth_buf_seed(priv->net_dev,
 					 page, DPAA2_ETH_RX_BUF_RAW_SIZE,
-					 addr, DPAA2_ETH_RX_BUF_SIZE,
+					 addr, priv->rx_buf_size,
 					 bpid);
 	}
 
@@ -1715,7 +1715,7 @@ static bool xdp_mtu_valid(struct dpaa2_eth_priv *priv, int mtu)
 	int mfl, linear_mfl;
 
 	mfl = DPAA2_ETH_L2_MAX_FRM(mtu);
-	linear_mfl = DPAA2_ETH_RX_BUF_SIZE - DPAA2_ETH_RX_HWA_SIZE -
+	linear_mfl = priv->rx_buf_size - DPAA2_ETH_RX_HWA_SIZE -
 		     dpaa2_eth_rx_head_room(priv) - XDP_PACKET_HEADROOM;
 
 	if (mfl > linear_mfl) {
@@ -2457,6 +2457,11 @@ static int set_buffer_layout(struct dpaa2_eth_priv *priv)
 	else
 		rx_buf_align = DPAA2_ETH_RX_BUF_ALIGN;
 
+	/* We need to ensure that the buffer size seen by WRIOP is a multiple
+	 * of 64 or 256 bytes depending on the WRIOP version.
+	 */
+	priv->rx_buf_size = ALIGN_DOWN(DPAA2_ETH_RX_BUF_SIZE, rx_buf_align);
+
 	/* tx buffer */
 	buf_layout.private_data_size = DPAA2_ETH_SWA_SIZE;
 	buf_layout.pass_timestamp = true;
@@ -3121,7 +3126,7 @@ static int bind_dpni(struct dpaa2_eth_priv *priv)
 	pools_params.num_dpbp = 1;
 	pools_params.pools[0].dpbp_id = priv->dpbp_dev->obj_desc.id;
 	pools_params.pools[0].backup_pool = 0;
-	pools_params.pools[0].buffer_size = DPAA2_ETH_RX_BUF_SIZE;
+	pools_params.pools[0].buffer_size = priv->rx_buf_size;
 	err = dpni_set_pools(priv->mc_io, 0, priv->mc_token, &pools_params);
 	if (err) {
 		dev_err(dev, "dpni_set_pools() failed\n");
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index 7635db3ef903..13242bf5b427 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -382,6 +382,7 @@ struct dpaa2_eth_priv {
 	u16 tx_data_offset;
 
 	struct fsl_mc_device *dpbp_dev;
+	u16 rx_buf_size;
 	u16 bpid;
 	struct iommu_domain *iommu_domain;
 
-- 
2.26.2


From 10b8ff0199994fcd52b7b3a4674a3c2b13a956ea Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 7 May 2020 18:53:24 +0200
Subject: [PATCH 02/21] mptcp: set correct vfs info for subflows

[ Upstream commit 7d14b0d2b9b317cfc14161143e2006b95a5da9b1 ]

When a subflow is created via mptcp_subflow_create_socket(),
a new 'struct socket' is allocated, with a new i_ino value.

When inspecting TCP sockets via the procfs and or the diag
interface, the above ones are not related to the process owning
the MPTCP master socket, even if they are a logical part of it
('ss -p' shows an empty process field)

Additionally, subflows created by the path manager get
the uid/gid from the running workqueue.

Subflows are part of the owning MPTCP master socket, let's
adjust the vfs info to reflect this.

After this patch, 'ss' correctly displays subflows as belonging
to the msk socket creator.

Fixes: 2303f994b3e1 ("mptcp: Associate MPTCP context with TCP socket")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/subflow.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 65122edf60aa..b89bd70f890a 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -633,6 +633,16 @@ int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock)
 	if (err)
 		return err;
 
+	/* the newly created socket really belongs to the owning MPTCP master
+	 * socket, even if for additional subflows the allocation is performed
+	 * by a kernel workqueue. Adjust inode references, so that the
+	 * procfs/diag interaces really show this one belonging to the correct
+	 * user.
+	 */
+	SOCK_INODE(sf)->i_ino = SOCK_INODE(sk->sk_socket)->i_ino;
+	SOCK_INODE(sf)->i_uid = SOCK_INODE(sk->sk_socket)->i_uid;
+	SOCK_INODE(sf)->i_gid = SOCK_INODE(sk->sk_socket)->i_gid;
+
 	subflow = mptcp_subflow_ctx(sf->sk);
 	pr_debug("subflow=%p", subflow);
 
-- 
2.26.2


From 30ff0b02b09916f501f6e105637cc204858111b8 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 7 May 2020 12:19:03 -0700
Subject: [PATCH 03/21] net: fix a potential recursive NETDEV_FEAT_CHANGE

[ Upstream commit dd912306ff008891c82cd9f63e8181e47a9cb2fb ]

syzbot managed to trigger a recursive NETDEV_FEAT_CHANGE event
between bonding master and slave. I managed to find a reproducer
for this:

  ip li set bond0 up
  ifenslave bond0 eth0
  brctl addbr br0
  ethtool -K eth0 lro off
  brctl addif br0 bond0
  ip li set br0 up

When a NETDEV_FEAT_CHANGE event is triggered on a bonding slave,
it captures this and calls bond_compute_features() to fixup its
master's and other slaves' features. However, when syncing with
its lower devices by netdev_sync_lower_features() this event is
triggered again on slaves when the LRO feature fails to change,
so it goes back and forth recursively until the kernel stack is
exhausted.

Commit 17b85d29e82c intentionally lets __netdev_update_features()
return -1 for such a failure case, so we have to just rely on
the existing check inside netdev_sync_lower_features() and skip
NETDEV_FEAT_CHANGE event only for this specific failure case.

Fixes: fd867d51f889 ("net/core: generic support for disabling netdev features down stack")
Reported-by: syzbot+e73ceacfd8560cc8a3ca@syzkaller.appspotmail.com
Reported-by: syzbot+c2fb6f9ddcea95ba49b5@syzkaller.appspotmail.com
Cc: Jarod Wilson <jarod@redhat.com>
Cc: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Jann Horn <jannh@google.com>
Reviewed-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 77c154107b0d..c7047b40f569 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8890,11 +8890,13 @@ static void netdev_sync_lower_features(struct net_device *upper,
 			netdev_dbg(upper, "Disabling feature %pNF on lower dev %s.\n",
 				   &feature, lower->name);
 			lower->wanted_features &= ~feature;
-			netdev_update_features(lower);
+			__netdev_update_features(lower);
 
 			if (unlikely(lower->features & feature))
 				netdev_WARN(upper, "failed to disable %pNF on %s!\n",
 					    &feature, lower->name);
+			else
+				netdev_features_change(lower);
 		}
 	}
 }
-- 
2.26.2


From 9b1ccb71c2f68b6e60049f0b60009341bf64cadb Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 12 May 2020 14:43:14 +0200
Subject: [PATCH 04/21] netlabel: cope with NULL catmap

[ Upstream commit eead1c2ea2509fd754c6da893a94f0e69e83ebe4 ]

The cipso and calipso code can set the MLS_CAT attribute on
successful parsing, even if the corresponding catmap has
not been allocated, as per current configuration and external
input.

Later, selinux code tries to access the catmap if the MLS_CAT flag
is present via netlbl_catmap_getlong(). That may cause null ptr
dereference while processing incoming network traffic.

Address the issue setting the MLS_CAT flag only if the catmap is
really allocated. Additionally let netlbl_catmap_getlong() cope
with NULL catmap.

Reported-by: Matthew Sheets <matthew.sheets@gd-ms.com>
Fixes: 4b8feff251da ("netlabel: fix the horribly broken catmap functions")
Fixes: ceba1832b1b2 ("calipso: Set the calipso socket label to match the secattr.")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Paul Moore <paul@paul-moore.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/cipso_ipv4.c        | 6 ++++--
 net/ipv6/calipso.c           | 3 ++-
 net/netlabel/netlabel_kapi.c | 6 ++++++
 3 files changed, 12 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 0bd10a1f477f..a23094b050f8 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -1258,7 +1258,8 @@ static int cipso_v4_parsetag_rbm(const struct cipso_v4_doi *doi_def,
 			return ret_val;
 		}
 
-		secattr->flags |= NETLBL_SECATTR_MLS_CAT;
+		if (secattr->attr.mls.cat)
+			secattr->flags |= NETLBL_SECATTR_MLS_CAT;
 	}
 
 	return 0;
@@ -1439,7 +1440,8 @@ static int cipso_v4_parsetag_rng(const struct cipso_v4_doi *doi_def,
 			return ret_val;
 		}
 
-		secattr->flags |= NETLBL_SECATTR_MLS_CAT;
+		if (secattr->attr.mls.cat)
+			secattr->flags |= NETLBL_SECATTR_MLS_CAT;
 	}
 
 	return 0;
diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c
index 221c81f85cbf..8d3f66c310db 100644
--- a/net/ipv6/calipso.c
+++ b/net/ipv6/calipso.c
@@ -1047,7 +1047,8 @@ static int calipso_opt_getattr(const unsigned char *calipso,
 			goto getattr_return;
 		}
 
-		secattr->flags |= NETLBL_SECATTR_MLS_CAT;
+		if (secattr->attr.mls.cat)
+			secattr->flags |= NETLBL_SECATTR_MLS_CAT;
 	}
 
 	secattr->type = NETLBL_NLTYPE_CALIPSO;
diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c
index 409a3ae47ce2..5e1239cef000 100644
--- a/net/netlabel/netlabel_kapi.c
+++ b/net/netlabel/netlabel_kapi.c
@@ -734,6 +734,12 @@ int netlbl_catmap_getlong(struct netlbl_lsm_catmap *catmap,
 	if ((off & (BITS_PER_LONG - 1)) != 0)
 		return -EINVAL;
 
+	/* a null catmap is equivalent to an empty one */
+	if (!catmap) {
+		*offset = (u32)-1;
+		return 0;
+	}
+
 	if (off < catmap->startbit) {
 		off = catmap->startbit;
 		*offset = off;
-- 
2.26.2


From 01c4d5031efb3d508f2c38559b107ede5c8c8651 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Tue, 12 May 2020 21:45:53 +0200
Subject: [PATCH 05/21] net: phy: fix aneg restart in phy_ethtool_set_eee

[ Upstream commit 9de5d235b60a7cdfcdd5461e70c5663e713fde87 ]

phy_restart_aneg() enables aneg in the PHY. That's not what we want
if phydev->autoneg is disabled. In this case still update EEE
advertisement register, but don't enable aneg and don't trigger an
aneg restart.

Fixes: f75abeb8338e ("net: phy: restart phy autonegotiation after EEE advertisment change")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 355bfdef48d2..594d97d3c8ab 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -1132,9 +1132,11 @@ int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data)
 		/* Restart autonegotiation so the new modes get sent to the
 		 * link partner.
 		 */
-		ret = phy_restart_aneg(phydev);
-		if (ret < 0)
-			return ret;
+		if (phydev->autoneg == AUTONEG_ENABLE) {
+			ret = phy_restart_aneg(phydev);
+			if (ret < 0)
+				return ret;
+		}
 	}
 
 	return 0;
-- 
2.26.2


From 94f7fd5a39ff2392c6d677c8f181a127bdb1c5d2 Mon Sep 17 00:00:00 2001
From: Vinod Koul <vkoul@kernel.org>
Date: Thu, 14 May 2020 11:58:36 +0530
Subject: [PATCH 06/21] net: stmmac: fix num_por initialization

[ Upstream commit fd4a5177382230d39e0d95632d98103fb2938383 ]

Driver missed initializing num_por which is one of the por values that
driver configures to hardware. In order to get these values, add a new
structure ethqos_emac_driver_data which holds por and num_por values
and populate that in driver probe.

Fixes: a7c30e62d4b8 ("net: stmmac: Add driver for Qualcomm ethqos")
Reported-by: Rahul Ankushrao Kawadgave <rahulak@qti.qualcomm.com>
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Reviewed-by: Amit Kucheria <amit.kucheria@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
index e0a5fe83d8e0..bfc4a92f1d92 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
@@ -75,6 +75,11 @@ struct ethqos_emac_por {
 	unsigned int value;
 };
 
+struct ethqos_emac_driver_data {
+	const struct ethqos_emac_por *por;
+	unsigned int num_por;
+};
+
 struct qcom_ethqos {
 	struct platform_device *pdev;
 	void __iomem *rgmii_base;
@@ -171,6 +176,11 @@ static const struct ethqos_emac_por emac_v2_3_0_por[] = {
 	{ .offset = RGMII_IO_MACRO_CONFIG2,	.value = 0x00002060 },
 };
 
+static const struct ethqos_emac_driver_data emac_v2_3_0_data = {
+	.por = emac_v2_3_0_por,
+	.num_por = ARRAY_SIZE(emac_v2_3_0_por),
+};
+
 static int ethqos_dll_configure(struct qcom_ethqos *ethqos)
 {
 	unsigned int val;
@@ -442,6 +452,7 @@ static int qcom_ethqos_probe(struct platform_device *pdev)
 	struct device_node *np = pdev->dev.of_node;
 	struct plat_stmmacenet_data *plat_dat;
 	struct stmmac_resources stmmac_res;
+	const struct ethqos_emac_driver_data *data;
 	struct qcom_ethqos *ethqos;
 	struct resource *res;
 	int ret;
@@ -471,7 +482,9 @@ static int qcom_ethqos_probe(struct platform_device *pdev)
 		goto err_mem;
 	}
 
-	ethqos->por = of_device_get_match_data(&pdev->dev);
+	data = of_device_get_match_data(&pdev->dev);
+	ethqos->por = data->por;
+	ethqos->num_por = data->num_por;
 
 	ethqos->rgmii_clk = devm_clk_get(&pdev->dev, "rgmii");
 	if (IS_ERR(ethqos->rgmii_clk)) {
@@ -526,7 +539,7 @@ static int qcom_ethqos_remove(struct platform_device *pdev)
 }
 
 static const struct of_device_id qcom_ethqos_match[] = {
-	{ .compatible = "qcom,qcs404-ethqos", .data = &emac_v2_3_0_por},
+	{ .compatible = "qcom,qcs404-ethqos", .data = &emac_v2_3_0_data},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, qcom_ethqos_match);
-- 
2.26.2


From d6ca573967598b2bd109482aeaac00cf81cfb6d5 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Thu, 14 May 2020 12:15:39 +0200
Subject: [PATCH 07/21] pppoe: only process PADT targeted at local interfaces
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit b8c158395119be62294da73646a3953c29ac974b ]

We don't want to disconnect a session because of a stray PADT arriving
while the interface is in promiscuous mode.
Furthermore, multicast and broadcast packets make no sense here, so
only PACKET_HOST is accepted.

Reported-by: David Balažic <xerces9@gmail.com>
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/pppoe.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index d760a36db28c..beedaad08255 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -490,6 +490,9 @@ static int pppoe_disc_rcv(struct sk_buff *skb, struct net_device *dev,
 	if (!skb)
 		goto out;
 
+	if (skb->pkt_type != PACKET_HOST)
+		goto abort;
+
 	if (!pskb_may_pull(skb, sizeof(struct pppoe_hdr)))
 		goto abort;
 
-- 
2.26.2


From 2756bbc3e38bd35a7a8af6936ff0d10cf3eadfe9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Maciej=20=C5=BBenczykowski?= <maze@google.com>
Date: Tue, 5 May 2020 11:57:23 -0700
Subject: [PATCH 08/21] Revert "ipv6: add mtu lock check in
 __ip6_rt_update_pmtu"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 09454fd0a4ce23cb3d8af65066c91a1bf27120dd ]

This reverts commit 19bda36c4299ce3d7e5bce10bebe01764a655a6d:

| ipv6: add mtu lock check in __ip6_rt_update_pmtu
|
| Prior to this patch, ipv6 didn't do mtu lock check in ip6_update_pmtu.
| It leaded to that mtu lock doesn't really work when receiving the pkt
| of ICMPV6_PKT_TOOBIG.
|
| This patch is to add mtu lock check in __ip6_rt_update_pmtu just as ipv4
| did in __ip_rt_update_pmtu.

The above reasoning is incorrect.  IPv6 *requires* icmp based pmtu to work.
There's already a comment to this effect elsewhere in the kernel:

  $ git grep -p -B1 -A3 'RTAX_MTU lock'
  net/ipv6/route.c=4813=

  static int rt6_mtu_change_route(struct fib6_info *f6i, void *p_arg)
  ...
    /* In IPv6 pmtu discovery is not optional,
       so that RTAX_MTU lock cannot disable it.
       We still use this lock to block changes
       caused by addrconf/ndisc.
    */

This reverts to the pre-4.9 behaviour.

Cc: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Xin Long <lucien.xin@gmail.com>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Maciej Żenczykowski <maze@google.com>
Fixes: 19bda36c4299 ("ipv6: add mtu lock check in __ip6_rt_update_pmtu")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 42d0596dd398..21ee5bcaeb91 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2725,8 +2725,10 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
 	const struct in6_addr *daddr, *saddr;
 	struct rt6_info *rt6 = (struct rt6_info *)dst;
 
-	if (dst_metric_locked(dst, RTAX_MTU))
-		return;
+	/* Note: do *NOT* check dst_metric_locked(dst, RTAX_MTU)
+	 * IPv6 pmtu discovery isn't optional, so 'mtu lock' cannot disable it.
+	 * [see also comment in rt6_mtu_change_route()]
+	 */
 
 	if (iph) {
 		daddr = &iph->daddr;
-- 
2.26.2


From ac808e8e4a856a46cb41ab93fa1cf3484c6270cc Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 14 May 2020 13:58:13 -0700
Subject: [PATCH 09/21] tcp: fix error recovery in tcp_zerocopy_receive()

[ Upstream commit e776af608f692a7a647455106295fa34469e7475 ]

If user provides wrong virtual address in TCP_ZEROCOPY_RECEIVE
operation we want to return -EINVAL error.

But depending on zc->recv_skip_hint content, we might return
-EIO error if the socket has SOCK_DONE set.

Make sure to return -EINVAL in this case.

BUG: KMSAN: uninit-value in tcp_zerocopy_receive net/ipv4/tcp.c:1833 [inline]
BUG: KMSAN: uninit-value in do_tcp_getsockopt+0x4494/0x6320 net/ipv4/tcp.c:3685
CPU: 1 PID: 625 Comm: syz-executor.0 Not tainted 5.7.0-rc4-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c9/0x220 lib/dump_stack.c:118
 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:121
 __msan_warning+0x58/0xa0 mm/kmsan/kmsan_instr.c:215
 tcp_zerocopy_receive net/ipv4/tcp.c:1833 [inline]
 do_tcp_getsockopt+0x4494/0x6320 net/ipv4/tcp.c:3685
 tcp_getsockopt+0xf8/0x1f0 net/ipv4/tcp.c:3728
 sock_common_getsockopt+0x13f/0x180 net/core/sock.c:3131
 __sys_getsockopt+0x533/0x7b0 net/socket.c:2177
 __do_sys_getsockopt net/socket.c:2192 [inline]
 __se_sys_getsockopt+0xe1/0x100 net/socket.c:2189
 __x64_sys_getsockopt+0x62/0x80 net/socket.c:2189
 do_syscall_64+0xb8/0x160 arch/x86/entry/common.c:297
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x45c829
Code: 0d b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 db b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f1deeb72c78 EFLAGS: 00000246 ORIG_RAX: 0000000000000037
RAX: ffffffffffffffda RBX: 00000000004e01e0 RCX: 000000000045c829
RDX: 0000000000000023 RSI: 0000000000000006 RDI: 0000000000000009
RBP: 000000000078bf00 R08: 0000000020000200 R09: 0000000000000000
R10: 00000000200001c0 R11: 0000000000000246 R12: 00000000ffffffff
R13: 00000000000001d8 R14: 00000000004d3038 R15: 00007f1deeb736d4

Local variable ----zc@do_tcp_getsockopt created at:
 do_tcp_getsockopt+0x1a74/0x6320 net/ipv4/tcp.c:3670
 do_tcp_getsockopt+0x1a74/0x6320 net/ipv4/tcp.c:3670

Fixes: 05255b823a61 ("tcp: add TCP_ZEROCOPY_RECEIVE support for zerocopy receive")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index dc77c303e6f7..f329109fc3c3 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1756,10 +1756,11 @@ static int tcp_zerocopy_receive(struct sock *sk,
 
 	down_read(&current->mm->mmap_sem);
 
-	ret = -EINVAL;
 	vma = find_vma(current->mm, address);
-	if (!vma || vma->vm_start > address || vma->vm_ops != &tcp_vm_ops)
-		goto out;
+	if (!vma || vma->vm_start > address || vma->vm_ops != &tcp_vm_ops) {
+		up_read(&current->mm->mmap_sem);
+		return -EINVAL;
+	}
 	zc->length = min_t(unsigned long, zc->length, vma->vm_end - address);
 
 	tp = tcp_sk(sk);
-- 
2.26.2


From 25f618aca8bc5cab410cd4a12d5bd8a1b12165ee Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 12 May 2020 06:54:30 -0700
Subject: [PATCH 10/21] tcp: fix SO_RCVLOWAT hangs with fat skbs

[ Upstream commit 24adbc1676af4e134e709ddc7f34cf2adc2131e4 ]

We autotune rcvbuf whenever SO_RCVLOWAT is set to account for 100%
overhead in tcp_set_rcvlowat()

This works well when skb->len/skb->truesize ratio is bigger than 0.5

But if we receive packets with small MSS, we can end up in a situation
where not enough bytes are available in the receive queue to satisfy
RCVLOWAT setting.
As our sk_rcvbuf limit is hit, we send zero windows in ACK packets,
preventing remote peer from sending more data.

Even autotuning does not help, because it only triggers at the time
user process drains the queue. If no EPOLLIN is generated, this
can not happen.

Note poll() has a similar issue, after commit
c7004482e8dc ("tcp: Respect SO_RCVLOWAT in tcp_poll().")

Fixes: 03f45c883c6f ("tcp: avoid extra wakeups for SO_RCVLOWAT users")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h    | 13 +++++++++++++
 net/ipv4/tcp.c       | 14 +++++++++++---
 net/ipv4/tcp_input.c |  3 ++-
 3 files changed, 26 insertions(+), 4 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 2edb73c27962..00a57766e16e 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1421,6 +1421,19 @@ static inline int tcp_full_space(const struct sock *sk)
 	return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf));
 }
 
+/* We provision sk_rcvbuf around 200% of sk_rcvlowat.
+ * If 87.5 % (7/8) of the space has been consumed, we want to override
+ * SO_RCVLOWAT constraint, since we are receiving skbs with too small
+ * len/truesize ratio.
+ */
+static inline bool tcp_rmem_pressure(const struct sock *sk)
+{
+	int rcvbuf = READ_ONCE(sk->sk_rcvbuf);
+	int threshold = rcvbuf - (rcvbuf >> 3);
+
+	return atomic_read(&sk->sk_rmem_alloc) > threshold;
+}
+
 extern void tcp_openreq_init_rwin(struct request_sock *req,
 				  const struct sock *sk_listener,
 				  const struct dst_entry *dst);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f329109fc3c3..f12f085028cb 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -476,9 +476,17 @@ static void tcp_tx_timestamp(struct sock *sk, u16 tsflags)
 static inline bool tcp_stream_is_readable(const struct tcp_sock *tp,
 					  int target, struct sock *sk)
 {
-	return (READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq) >= target) ||
-		(sk->sk_prot->stream_memory_read ?
-		sk->sk_prot->stream_memory_read(sk) : false);
+	int avail = READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq);
+
+	if (avail > 0) {
+		if (avail >= target)
+			return true;
+		if (tcp_rmem_pressure(sk))
+			return true;
+	}
+	if (sk->sk_prot->stream_memory_read)
+		return sk->sk_prot->stream_memory_read(sk);
+	return false;
 }
 
 /*
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 6b6b57000dad..e17d396102ce 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4761,7 +4761,8 @@ void tcp_data_ready(struct sock *sk)
 	const struct tcp_sock *tp = tcp_sk(sk);
 	int avail = tp->rcv_nxt - tp->copied_seq;
 
-	if (avail < sk->sk_rcvlowat && !sock_flag(sk, SOCK_DONE))
+	if (avail < sk->sk_rcvlowat && !tcp_rmem_pressure(sk) &&
+	    !sock_flag(sk, SOCK_DONE))
 		return;
 
 	sk->sk_data_ready(sk);
-- 
2.26.2


From 7cff32c77f372605c93afe08df161e0bd5bbc0b0 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Thu, 7 May 2020 03:25:56 -0400
Subject: [PATCH 11/21] virtio_net: fix lockdep warning on 32 bit

[ Upstream commit 01c3259818a11f3cc3cd767adbae6b45849c03c1 ]

When we fill up a receive VQ, try_fill_recv currently tries to count
kicks using a 64 bit stats counter. Turns out, on a 32 bit kernel that
uses a seqcount. sequence counts are "lock" constructs where you need to
make sure that writers are serialized.

In turn, this means that we mustn't run two try_fill_recv concurrently.
Which of course we don't. We do run try_fill_recv sometimes from a
softirq napi context, and sometimes from a fully preemptible context,
but the later always runs with napi disabled.

However, when it comes to the seqcount, lockdep is trying to enforce the
rule that the same lock isn't accessed from preemptible and softirq
context - it doesn't know about napi being enabled/disabled. This causes
a false-positive warning:

WARNING: inconsistent lock state
...
inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage.

As a work around, shut down the warning by switching
to u64_stats_update_begin_irqsave - that works by disabling
interrupts on 32 bit only, is a NOP on 64 bit.

Reported-by: Thomas Gleixner <tglx@linutronix.de>
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 2fe7a3188282..f7129bc898cc 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1231,9 +1231,11 @@ static bool try_fill_recv(struct virtnet_info *vi, struct receive_queue *rq,
 			break;
 	} while (rq->vq->num_free);
 	if (virtqueue_kick_prepare(rq->vq) && virtqueue_notify(rq->vq)) {
-		u64_stats_update_begin(&rq->stats.syncp);
+		unsigned long flags;
+
+		flags = u64_stats_update_begin_irqsave(&rq->stats.syncp);
 		rq->stats.kicks++;
-		u64_stats_update_end(&rq->stats.syncp);
+		u64_stats_update_end_irqrestore(&rq->stats.syncp, flags);
 	}
 
 	return !oom;
-- 
2.26.2


From 17a69201312f41ae7325bdefae730db040d01441 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Fri, 8 May 2020 17:37:20 +0300
Subject: [PATCH 12/21] dpaa2-eth: prevent array underflow in update_cls_rule()

[ Upstream commit 6d32a5119811d2e9b5caa284181944c6f1f192ed ]

The "location" is controlled by the user via the ethtool_set_rxnfc()
function.  This update_cls_rule() function checks for array overflows
but it doesn't check if the value is negative.  I have changed the type
to unsigned to prevent array underflows.

Fixes: afb90dbb5f78 ("dpaa2-eth: Add ethtool support for flow classification")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
index 96676abcebd5..c53f091af2cf 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
@@ -625,7 +625,7 @@ static int num_rules(struct dpaa2_eth_priv *priv)
 
 static int update_cls_rule(struct net_device *net_dev,
 			   struct ethtool_rx_flow_spec *new_fs,
-			   int location)
+			   unsigned int location)
 {
 	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
 	struct dpaa2_eth_cls_rule *rule;
-- 
2.26.2


From 40b2a1789ebae299f98554cffeafb824d1cdf18d Mon Sep 17 00:00:00 2001
From: Luo bin <luobin9@huawei.com>
Date: Sun, 10 May 2020 19:01:08 +0000
Subject: [PATCH 13/21] hinic: fix a bug of ndo_stop

[ Upstream commit e8a1b0efd632d1c9db7d4e93da66377c7b524862 ]

if some function in ndo_stop interface returns failure because of
hardware fault, must go on excuting rest steps rather than return
failure directly, otherwise will cause memory leak.And bump the
timeout for SET_FUNC_STATE to ensure that cmd won't return failure
when hw is busy. Otherwise hw may stomp host memory if we free
memory regardless of the return value of SET_FUNC_STATE.

Fixes: 51ba902a16e6 ("net-next/hinic: Initialize hw interface")
Signed-off-by: Luo bin <luobin9@huawei.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/huawei/hinic/hinic_hw_mgmt.c    | 16 ++++++++++++----
 drivers/net/ethernet/huawei/hinic/hinic_main.c   | 16 ++--------------
 2 files changed, 14 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
index 8995e32dd1c0..992908e6eebf 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
@@ -45,6 +45,8 @@
 
 #define MGMT_MSG_TIMEOUT                5000
 
+#define SET_FUNC_PORT_MGMT_TIMEOUT	25000
+
 #define mgmt_to_pfhwdev(pf_mgmt)        \
 		container_of(pf_mgmt, struct hinic_pfhwdev, pf_to_mgmt)
 
@@ -238,12 +240,13 @@ static int msg_to_mgmt_sync(struct hinic_pf_to_mgmt *pf_to_mgmt,
 			    u8 *buf_in, u16 in_size,
 			    u8 *buf_out, u16 *out_size,
 			    enum mgmt_direction_type direction,
-			    u16 resp_msg_id)
+			    u16 resp_msg_id, u32 timeout)
 {
 	struct hinic_hwif *hwif = pf_to_mgmt->hwif;
 	struct pci_dev *pdev = hwif->pdev;
 	struct hinic_recv_msg *recv_msg;
 	struct completion *recv_done;
+	unsigned long timeo;
 	u16 msg_id;
 	int err;
 
@@ -267,8 +270,9 @@ static int msg_to_mgmt_sync(struct hinic_pf_to_mgmt *pf_to_mgmt,
 		goto unlock_sync_msg;
 	}
 
-	if (!wait_for_completion_timeout(recv_done,
-					 msecs_to_jiffies(MGMT_MSG_TIMEOUT))) {
+	timeo = msecs_to_jiffies(timeout ? timeout : MGMT_MSG_TIMEOUT);
+
+	if (!wait_for_completion_timeout(recv_done, timeo)) {
 		dev_err(&pdev->dev, "MGMT timeout, MSG id = %d\n", msg_id);
 		err = -ETIMEDOUT;
 		goto unlock_sync_msg;
@@ -342,6 +346,7 @@ int hinic_msg_to_mgmt(struct hinic_pf_to_mgmt *pf_to_mgmt,
 {
 	struct hinic_hwif *hwif = pf_to_mgmt->hwif;
 	struct pci_dev *pdev = hwif->pdev;
+	u32 timeout = 0;
 
 	if (sync != HINIC_MGMT_MSG_SYNC) {
 		dev_err(&pdev->dev, "Invalid MGMT msg type\n");
@@ -353,9 +358,12 @@ int hinic_msg_to_mgmt(struct hinic_pf_to_mgmt *pf_to_mgmt,
 		return -EINVAL;
 	}
 
+	if (cmd == HINIC_PORT_CMD_SET_FUNC_STATE)
+		timeout = SET_FUNC_PORT_MGMT_TIMEOUT;
+
 	return msg_to_mgmt_sync(pf_to_mgmt, mod, cmd, buf_in, in_size,
 				buf_out, out_size, MGMT_DIRECT_SEND,
-				MSG_NOT_RESP);
+				MSG_NOT_RESP, timeout);
 }
 
 /**
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c
index 13560975c103..63b92f6cc856 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_main.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c
@@ -483,7 +483,6 @@ static int hinic_close(struct net_device *netdev)
 {
 	struct hinic_dev *nic_dev = netdev_priv(netdev);
 	unsigned int flags;
-	int err;
 
 	down(&nic_dev->mgmt_lock);
 
@@ -497,20 +496,9 @@ static int hinic_close(struct net_device *netdev)
 
 	up(&nic_dev->mgmt_lock);
 
-	err = hinic_port_set_func_state(nic_dev, HINIC_FUNC_PORT_DISABLE);
-	if (err) {
-		netif_err(nic_dev, drv, netdev,
-			  "Failed to set func port state\n");
-		nic_dev->flags |= (flags & HINIC_INTF_UP);
-		return err;
-	}
+	hinic_port_set_state(nic_dev, HINIC_PORT_DISABLE);
 
-	err = hinic_port_set_state(nic_dev, HINIC_PORT_DISABLE);
-	if (err) {
-		netif_err(nic_dev, drv, netdev, "Failed to set port state\n");
-		nic_dev->flags |= (flags & HINIC_INTF_UP);
-		return err;
-	}
+	hinic_port_set_func_state(nic_dev, HINIC_FUNC_PORT_DISABLE);
 
 	if (nic_dev->flags & HINIC_RSS_ENABLE) {
 		hinic_rss_deinit(nic_dev);
-- 
2.26.2


From ea18b8d3f5defdee380617d9a2e9efc04146da3d Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Sat, 9 May 2020 16:45:44 -0700
Subject: [PATCH 14/21] net: dsa: loop: Add module soft dependency

[ Upstream commit 3047211ca11bf77b3ecbce045c0aa544d934b945 ]

There is a soft dependency against dsa_loop_bdinfo.ko which sets up the
MDIO device registration, since there are no symbols referenced by
dsa_loop.ko, there is no automatic loading of dsa_loop_bdinfo.ko which
is needed.

Fixes: 98cd1552ea27 ("net: dsa: Mock-up driver")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/dsa_loop.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c
index fdcb70b9f0e4..400207c5c7de 100644
--- a/drivers/net/dsa/dsa_loop.c
+++ b/drivers/net/dsa/dsa_loop.c
@@ -360,6 +360,7 @@ static void __exit dsa_loop_exit(void)
 }
 module_exit(dsa_loop_exit);
 
+MODULE_SOFTDEP("pre: dsa_loop_bdinfo");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Florian Fainelli");
 MODULE_DESCRIPTION("DSA loopback driver");
-- 
2.26.2


From 19c9d9712ade769e37f2a257cceed48a8a3b7a79 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 8 May 2020 19:28:34 +0200
Subject: [PATCH 15/21] net: ipv4: really enforce backoff for redirects

[ Upstream commit 57644431a6c2faac5d754ebd35780cf43a531b1a ]

In commit b406472b5ad7 ("net: ipv4: avoid mixed n_redirects and
rate_tokens usage") I missed the fact that a 0 'rate_tokens' will
bypass the backoff algorithm.

Since rate_tokens is cleared after a redirect silence, and never
incremented on redirects, if the host keeps receiving packets
requiring redirect it will reply ignoring the backoff.

Additionally, the 'rate_last' field will be updated with the
cadence of the ingress packet requiring redirect. If that rate is
high enough, that will prevent the host from generating any
other kind of ICMP messages

The check for a zero 'rate_tokens' value was likely a shortcut
to avoid the more complex backoff algorithm after a redirect
silence period. Address the issue checking for 'n_redirects'
instead, which is incremented on successful redirect, and
does not interfere with other ICMP replies.

Fixes: b406472b5ad7 ("net: ipv4: avoid mixed n_redirects and rate_tokens usage")
Reported-and-tested-by: Colin Walters <walters@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/route.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index ebe7060d0fc9..ef6b70774fe1 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -915,7 +915,7 @@ void ip_rt_send_redirect(struct sk_buff *skb)
 	/* Check for load limit; set rate_last to the latest sent
 	 * redirect.
 	 */
-	if (peer->rate_tokens == 0 ||
+	if (peer->n_redirects == 0 ||
 	    time_after(jiffies,
 		       (peer->rate_last +
 			(ip_rt_redirect_load << peer->n_redirects)))) {
-- 
2.26.2


From 4b02d51ace71e067fa127859d7e8d28485a7d3e2 Mon Sep 17 00:00:00 2001
From: Zefan Li <lizefan@huawei.com>
Date: Sat, 9 May 2020 11:32:10 +0800
Subject: [PATCH 16/21] netprio_cgroup: Fix unlimited memory leak of v2 cgroups

[ Upstream commit 090e28b229af92dc5b40786ca673999d59e73056 ]

If systemd is configured to use hybrid mode which enables the use of
both cgroup v1 and v2, systemd will create new cgroup on both the default
root (v2) and netprio_cgroup hierarchy (v1) for a new session and attach
task to the two cgroups. If the task does some network thing then the v2
cgroup can never be freed after the session exited.

One of our machines ran into OOM due to this memory leak.

In the scenario described above when sk_alloc() is called
cgroup_sk_alloc() thought it's in v2 mode, so it stores
the cgroup pointer in sk->sk_cgrp_data and increments
the cgroup refcnt, but then sock_update_netprioidx()
thought it's in v1 mode, so it stores netprioidx value
in sk->sk_cgrp_data, so the cgroup refcnt will never be freed.

Currently we do the mode switch when someone writes to the ifpriomap
cgroup control file. The easiest fix is to also do the switch when
a task is attached to a new cgroup.

Fixes: bd1060a1d671 ("sock, cgroup: add sock->sk_cgroup")
Reported-by: Yang Yingliang <yangyingliang@huawei.com>
Tested-by: Yang Yingliang <yangyingliang@huawei.com>
Signed-off-by: Zefan Li <lizefan@huawei.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/netprio_cgroup.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index 8881dd943dd0..9bd4cab7d510 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -236,6 +236,8 @@ static void net_prio_attach(struct cgroup_taskset *tset)
 	struct task_struct *p;
 	struct cgroup_subsys_state *css;
 
+	cgroup_sk_alloc_disable();
+
 	cgroup_taskset_for_each(p, css, tset) {
 		void *v = (void *)(unsigned long)css->id;
 
-- 
2.26.2


From ffbe566a230818ad95aece1de07014acdf4e4079 Mon Sep 17 00:00:00 2001
From: Kelly Littlepage <kelly@onechronos.com>
Date: Fri, 8 May 2020 19:58:46 +0000
Subject: [PATCH 17/21] net: tcp: fix rx timestamp behavior for tcp_recvmsg

[ Upstream commit cc4de047b33be247f9c8150d3e496743a49642b8 ]

The stated intent of the original commit is to is to "return the timestamp
corresponding to the highest sequence number data returned." The current
implementation returns the timestamp for the last byte of the last fully
read skb, which is not necessarily the last byte in the recv buffer. This
patch converts behavior to the original definition, and to the behavior of
the previous draft versions of commit 98aaa913b4ed ("tcp: Extend
SOF_TIMESTAMPING_RX_SOFTWARE to TCP recvmsg") which also match this
behavior.

Fixes: 98aaa913b4ed ("tcp: Extend SOF_TIMESTAMPING_RX_SOFTWARE to TCP recvmsg")
Co-developed-by: Iris Liu <iris@onechronos.com>
Signed-off-by: Iris Liu <iris@onechronos.com>
Signed-off-by: Kelly Littlepage <kelly@onechronos.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f12f085028cb..06aad5e09459 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2163,13 +2163,15 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 			tp->urg_data = 0;
 			tcp_fast_path_check(sk);
 		}
-		if (used + offset < skb->len)
-			continue;
 
 		if (TCP_SKB_CB(skb)->has_rxtstamp) {
 			tcp_update_recv_tstamps(skb, &tss);
 			cmsg_flags |= 2;
 		}
+
+		if (used + offset < skb->len)
+			continue;
+
 		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
 			goto found_fin_ok;
 		if (!(flags & MSG_PEEK))
-- 
2.26.2


From 1b0bef58a37163c071f10803e2bd441a20b74181 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Fri, 8 May 2020 07:27:35 +0000
Subject: [PATCH 18/21] nfp: abm: fix error return code in nfp_abm_vnic_alloc()

[ Upstream commit 5099dea0a59f1c89525bb0ceac36689178a4c125 ]

Fix to return negative error code -ENOMEM from the kzalloc() error
handling case instead of 0, as done elsewhere in this function.

Fixes: 174ab544e3bc ("nfp: abm: add cls_u32 offload for simple band classification")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/netronome/nfp/abm/main.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.c b/drivers/net/ethernet/netronome/nfp/abm/main.c
index 354efffac0f9..bdbf0726145e 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.c
@@ -333,8 +333,10 @@ nfp_abm_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, unsigned int id)
 		goto err_free_alink;
 
 	alink->prio_map = kzalloc(abm->prio_map_len, GFP_KERNEL);
-	if (!alink->prio_map)
+	if (!alink->prio_map) {
+		err = -ENOMEM;
 		goto err_free_alink;
+	}
 
 	/* This is a multi-host app, make sure MAC/PHY is up, but don't
 	 * make the MAC/PHY state follow the state of any of the ports.
-- 
2.26.2


From 161f783c216d82f4a13eb2613d8139b4ca142237 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 8 May 2020 08:24:14 +0200
Subject: [PATCH 19/21] r8169: re-establish support for RTL8401 chip version
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 1f8492df081bd66255764f3ce82ba1b2c37def49 ]

r8169 never had native support for the RTL8401, however it reportedly
worked with the fallback to RTL8101e [0]. Therefore let's add this
as an explicit assignment.

[0] https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=956868

Fixes: b4cc2dcc9c7c ("r8169: remove default chip versions")
Reported-by: Camaleón <noelamac@gmail.com>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/r8169_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 6b633e9d76da..07a6b609f741 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -2127,6 +2127,8 @@ static void rtl8169_get_mac_version(struct rtl8169_private *tp)
 		{ 0x7cf, 0x348,	RTL_GIGA_MAC_VER_07 },
 		{ 0x7cf, 0x248,	RTL_GIGA_MAC_VER_07 },
 		{ 0x7cf, 0x340,	RTL_GIGA_MAC_VER_13 },
+		/* RTL8401, reportedly works if treated as RTL8101e */
+		{ 0x7cf, 0x240,	RTL_GIGA_MAC_VER_13 },
 		{ 0x7cf, 0x343,	RTL_GIGA_MAC_VER_10 },
 		{ 0x7cf, 0x342,	RTL_GIGA_MAC_VER_16 },
 		{ 0x7c8, 0x348,	RTL_GIGA_MAC_VER_09 },
-- 
2.26.2


From 024e073b3089e198f5ae2343857a9d0a5f27ebfe Mon Sep 17 00:00:00 2001
From: Vincent Minet <v.minet@criteo.com>
Date: Fri, 8 May 2020 00:14:22 +0200
Subject: [PATCH 20/21] umh: fix memory leak on execve failure

[ Upstream commit db803036ada7d61d096783726f9771b3fc540370 ]

If a UMH process created by fork_usermode_blob() fails to execute,
a pair of struct file allocated by umh_pipe_setup() will leak.

Under normal conditions, the caller (like bpfilter) needs to manage the
lifetime of the UMH and its two pipes. But when fork_usermode_blob()
fails, the caller doesn't really have a way to know what needs to be
done. It seems better to do the cleanup ourselves in this case.

Fixes: 449325b52b7a ("umh: introduce fork_usermode_blob() helper")
Signed-off-by: Vincent Minet <v.minet@criteo.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 kernel/umh.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/kernel/umh.c b/kernel/umh.c
index 11bf5eea474c..3474d6aa55d8 100644
--- a/kernel/umh.c
+++ b/kernel/umh.c
@@ -475,6 +475,12 @@ static void umh_clean_and_save_pid(struct subprocess_info *info)
 {
 	struct umh_info *umh_info = info->data;
 
+	/* cleanup if umh_pipe_setup() was successful but exec failed */
+	if (info->pid && info->retval) {
+		fput(umh_info->pipe_to_umh);
+		fput(umh_info->pipe_from_umh);
+	}
+
 	argv_free(info->argv);
 	umh_info->pid = info->pid;
 }
-- 
2.26.2


From c016d9a6594ec86951bfb68ed305e55b9427ef7d Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 13 May 2020 08:51:51 -0700
Subject: [PATCH 21/21] net: broadcom: Select BROADCOM_PHY for BCMGENET

[ Upstream commit 99addbe31f5524494f4d7077bcb3f6fa64c5d160 ]

The GENET controller on the Raspberry Pi 4 (2711) is typically
interfaced with an external Broadcom PHY via a RGMII electrical
interface. To make sure that delays are properly configured at the PHY
side, ensure that we the dedicated Broadcom PHY driver
(CONFIG_BROADCOM_PHY) is enabled for this to happen.

Fixes: 402482a6a78e ("net: bcmgenet: Clear ID_MODE_DIS in EXT_RGMII_OOB_CTRL when not needed")
Reported-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index 53055ce5dfd6..2a69c0d06f3c 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -69,6 +69,7 @@ config BCMGENET
 	select BCM7XXX_PHY
 	select MDIO_BCM_UNIMAC
 	select DIMLIB
+	select BROADCOM_PHY if ARCH_BCM2835
 	help
 	  This driver supports the built-in Ethernet MACs found in the
 	  Broadcom BCM7xxx Set Top Box family chipset.
-- 
2.26.2

Re: [PATCHES] Networking

[Greg KH]

On Fri, May 15, 2020 at 05:44:10PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v5.4 and
> v5.6 -stable, respectively.

All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 105 bytes --]


Please queue up the following networking bug fixes for v5.4 and
v5.6 -stable, respectively.

Thank you.

[-- Attachment #2: net_54.mbox --]
[-- Type: Application/Octet-Stream, Size: 84404 bytes --]

From ff63da534c7b09b7d2fc2733e14fd8b614fc22ba Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 19 May 2020 18:24:43 -0700
Subject: [PATCH 01/25] ax25: fix setsockopt(SO_BINDTODEVICE)

[ Upstream commit 687775cec056b38a4c8f3291e0dd7a9145f7b667 ]

syzbot was able to trigger this trace [1], probably by using
a zero optlen.

While we are at it, cap optlen to IFNAMSIZ - 1 instead of IFNAMSIZ.

[1]
BUG: KMSAN: uninit-value in strnlen+0xf9/0x170 lib/string.c:569
CPU: 0 PID: 8807 Comm: syz-executor483 Not tainted 5.7.0-rc4-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c9/0x220 lib/dump_stack.c:118
 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:121
 __msan_warning+0x58/0xa0 mm/kmsan/kmsan_instr.c:215
 strnlen+0xf9/0x170 lib/string.c:569
 dev_name_hash net/core/dev.c:207 [inline]
 netdev_name_node_lookup net/core/dev.c:277 [inline]
 __dev_get_by_name+0x75/0x2b0 net/core/dev.c:778
 ax25_setsockopt+0xfa3/0x1170 net/ax25/af_ax25.c:654
 __compat_sys_setsockopt+0x4ed/0x910 net/compat.c:403
 __do_compat_sys_setsockopt net/compat.c:413 [inline]
 __se_compat_sys_setsockopt+0xdd/0x100 net/compat.c:410
 __ia32_compat_sys_setsockopt+0x62/0x80 net/compat.c:410
 do_syscall_32_irqs_on arch/x86/entry/common.c:339 [inline]
 do_fast_syscall_32+0x3bf/0x6d0 arch/x86/entry/common.c:398
 entry_SYSENTER_compat+0x68/0x77 arch/x86/entry/entry_64_compat.S:139
RIP: 0023:0xf7f57dd9
Code: 90 e8 0b 00 00 00 f3 90 0f ae e8 eb f9 8d 74 26 00 89 3c 24 c3 90 90 90 90 90 90 90 90 90 90 90 90 51 52 55 89 e5 0f 34 cd 80 <5d> 5a 59 c3 90 90 90 90 eb 0d 90 90 90 90 90 90 90 90 90 90 90 90
RSP: 002b:00000000ffae8c1c EFLAGS: 00000217 ORIG_RAX: 000000000000016e
RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000000101
RDX: 0000000000000019 RSI: 0000000020000000 RDI: 0000000000000004
RBP: 0000000000000012 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000

Local variable ----devname@ax25_setsockopt created at:
 ax25_setsockopt+0xe6/0x1170 net/ax25/af_ax25.c:536
 ax25_setsockopt+0xe6/0x1170 net/ax25/af_ax25.c:536

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ax25/af_ax25.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index bb222b882b67..e5a3dc28116d 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -635,8 +635,10 @@ static int ax25_setsockopt(struct socket *sock, int level, int optname,
 		break;
 
 	case SO_BINDTODEVICE:
-		if (optlen > IFNAMSIZ)
-			optlen = IFNAMSIZ;
+		if (optlen > IFNAMSIZ - 1)
+			optlen = IFNAMSIZ - 1;
+
+		memset(devname, 0, sizeof(devname));
 
 		if (copy_from_user(devname, optval, optlen)) {
 			res = -EFAULT;
-- 
2.26.2


From 5672ce1e49e46c7f4d4e94c6a29868611a9152f9 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Mon, 25 May 2020 00:22:51 +0300
Subject: [PATCH 02/25] dpaa_eth: fix usage as DSA master, try 3

[ Upstream commit 5d14c304bfc14b4fd052dc83d5224376b48f52f0 ]

The dpaa-eth driver probes on compatible string for the MAC node, and
the fman/mac.c driver allocates a dpaa-ethernet platform device that
triggers the probing of the dpaa-eth net device driver.

All of this is fine, but the problem is that the struct device of the
dpaa_eth net_device is 2 parents away from the MAC which can be
referenced via of_node. So of_find_net_device_by_node can't find it, and
DSA switches won't be able to probe on top of FMan ports.

It would be a bit silly to modify a core function
(of_find_net_device_by_node) to look for dev->parent->parent->of_node
just for one driver. We're just 1 step away from implementing full
recursion.

Actually there have already been at least 2 previous attempts to make
this work:
- Commit a1a50c8e4c24 ("fsl/man: Inherit parent device and of_node")
- One or more of the patches in "[v3,0/6] adapt DPAA drivers for DSA":
  https://patchwork.ozlabs.org/project/netdev/cover/1508178970-28945-1-git-send-email-madalin.bucur@nxp.com/
  (I couldn't really figure out which one was supposed to solve the
  problem and how).

Point being, it looks like this is still pretty much a problem today.
On T1040, the /sys/class/net/eth0 symlink currently points to

../../devices/platform/ffe000000.soc/ffe400000.fman/ffe4e6000.ethernet/dpaa-ethernet.0/net/eth0

which pretty much illustrates the problem. The closest of_node we've got
is the "fsl,fman-memac" at /soc@ffe000000/fman@400000/ethernet@e6000,
which is what we'd like to be able to reference from DSA as host port.

For of_find_net_device_by_node to find the eth0 port, we would need the
parent of the eth0 net_device to not be the "dpaa-ethernet" platform
device, but to point 1 level higher, aka the "fsl,fman-memac" node
directly. The new sysfs path would look like this:

../../devices/platform/ffe000000.soc/ffe400000.fman/ffe4e6000.ethernet/net/eth0

And this is exactly what SET_NETDEV_DEV does. It sets the parent of the
net_device. The new parent has an of_node associated with it, and
of_dev_node_match already checks for the of_node of the device or of its
parent.

Fixes: a1a50c8e4c24 ("fsl/man: Inherit parent device and of_node")
Fixes: c6e26ea8c893 ("dpaa_eth: change device used")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 00c4beb760c3..cd9d08695cc1 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -2802,7 +2802,7 @@ static int dpaa_eth_probe(struct platform_device *pdev)
 	}
 
 	/* Do this here, so we can be verbose early */
-	SET_NETDEV_DEV(net_dev, dev);
+	SET_NETDEV_DEV(net_dev, dev->parent);
 	dev_set_drvdata(dev, net_dev);
 
 	priv = netdev_priv(net_dev);
-- 
2.26.2


From d6a28b2e1f8c7c5eac7f05a369c28828efa01aba Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Wed, 20 May 2020 11:15:46 +0200
Subject: [PATCH 03/25] net: don't return invalid table id error when we fall
 back to PF_UNSPEC

[ Upstream commit 41b4bd986f86331efc599b9a3f5fb86ad92e9af9 ]

In case we can't find a ->dumpit callback for the requested
(family,type) pair, we fall back to (PF_UNSPEC,type). In effect, we're
in the same situation as if userspace had requested a PF_UNSPEC
dump. For RTM_GETROUTE, that handler is rtnl_dump_all, which calls all
the registered RTM_GETROUTE handlers.

The requested table id may or may not exist for all of those
families. commit ae677bbb4441 ("net: Don't return invalid table id
error when dumping all families") fixed the problem when userspace
explicitly requests a PF_UNSPEC dump, but missed the fallback case.

For example, when we pass ipv6.disable=1 to a kernel with
CONFIG_IP_MROUTE=y and CONFIG_IP_MROUTE_MULTIPLE_TABLES=y,
the (PF_INET6, RTM_GETROUTE) handler isn't registered, so we end up in
rtnl_dump_all, and listing IPv6 routes will unexpectedly print:

  # ip -6 r
  Error: ipv4: MR table does not exist.
  Dump terminated

commit ae677bbb4441 introduced the dump_all_families variable, which
gets set when userspace requests a PF_UNSPEC dump. However, we can't
simply set the family to PF_UNSPEC in rtnetlink_rcv_msg in the
fallback case to get dump_all_families == true, because some messages
types (for example RTM_GETRULE and RTM_GETNEIGH) only register the
PF_UNSPEC handler and use the family to filter in the kernel what is
dumped to userspace. We would then export more entries, that userspace
would have to filter. iproute does that, but other programs may not.

Instead, this patch removes dump_all_families and updates the
RTM_GETROUTE handlers to check if the family that is being dumped is
their own. When it's not, which covers both the intentional PF_UNSPEC
dumps (as dump_all_families did) and the fallback case, ignore the
missing table id error.

Fixes: cb167893f41e ("net: Plumb support for filtering ipv4 and ipv6 multicast route dumps")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_fib.h    | 1 -
 net/ipv4/fib_frontend.c | 3 +--
 net/ipv4/ipmr.c         | 2 +-
 net/ipv6/ip6_fib.c      | 2 +-
 net/ipv6/ip6mr.c        | 2 +-
 5 files changed, 4 insertions(+), 6 deletions(-)

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index ab1ca9e238d2..72bcfdcb25e0 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -244,7 +244,6 @@ struct fib_dump_filter {
 	u32			table_id;
 	/* filter_set is an optimization that an entry is set */
 	bool			filter_set;
-	bool			dump_all_families;
 	bool			dump_routes;
 	bool			dump_exceptions;
 	unsigned char		protocol;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 48bf3b9be475..65adc5fb932f 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -928,7 +928,6 @@ int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh,
 	else
 		filter->dump_exceptions = false;
 
-	filter->dump_all_families = (rtm->rtm_family == AF_UNSPEC);
 	filter->flags    = rtm->rtm_flags;
 	filter->protocol = rtm->rtm_protocol;
 	filter->rt_type  = rtm->rtm_type;
@@ -1000,7 +999,7 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 	if (filter.table_id) {
 		tb = fib_get_table(net, filter.table_id);
 		if (!tb) {
-			if (filter.dump_all_families)
+			if (rtnl_msg_family(cb->nlh) != PF_INET)
 				return skb->len;
 
 			NL_SET_ERR_MSG(cb->extack, "ipv4: FIB table does not exist");
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 58007439cffd..d71935618871 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2609,7 +2609,7 @@ static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
 
 		mrt = ipmr_get_table(sock_net(skb->sk), filter.table_id);
 		if (!mrt) {
-			if (filter.dump_all_families)
+			if (rtnl_msg_family(cb->nlh) != RTNL_FAMILY_IPMR)
 				return skb->len;
 
 			NL_SET_ERR_MSG(cb->extack, "ipv4: MR table does not exist");
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index c75274e0745c..7a0c877ca306 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -613,7 +613,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 	if (arg.filter.table_id) {
 		tb = fib6_get_table(net, arg.filter.table_id);
 		if (!tb) {
-			if (arg.filter.dump_all_families)
+			if (rtnl_msg_family(cb->nlh) != PF_INET6)
 				goto out;
 
 			NL_SET_ERR_MSG_MOD(cb->extack, "FIB table does not exist");
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 857a89ad4d6c..dd41313d7fa5 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -2498,7 +2498,7 @@ static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
 
 		mrt = ip6mr_get_table(sock_net(skb->sk), filter.table_id);
 		if (!mrt) {
-			if (filter.dump_all_families)
+			if (rtnl_msg_family(cb->nlh) != RTNL_FAMILY_IP6MR)
 				return skb->len;
 
 			NL_SET_ERR_MSG_MOD(cb->extack, "MR table does not exist");
-- 
2.26.2


From a74b8e5c5ee39113b0be6590173d0732af17f65a Mon Sep 17 00:00:00 2001
From: DENG Qingfang <dqfext@gmail.com>
Date: Wed, 13 May 2020 23:10:16 +0800
Subject: [PATCH 04/25] net: dsa: mt7530: fix roaming from DSA user ports

[ Upstream commit 5e5502e012b8129e11be616acb0f9c34bc8f8adb ]

When a client moves from a DSA user port to a software port in a bridge,
it cannot reach any other clients that connected to the DSA user ports.
That is because SA learning on the CPU port is disabled, so the switch
ignores the client's frames from the CPU port and still thinks it is at
the user port.

Fix it by enabling SA learning on the CPU port.

To prevent the switch from learning from flooding frames from the CPU
port, set skb->offload_fwd_mark to 1 for unicast and broadcast frames,
and let the switch flood them instead of trapping to the CPU port.
Multicast frames still need to be trapped to the CPU port for snooping,
so set the SA_DIS bit of the MTK tag to 1 when transmitting those frames
to disable SA learning.

Fixes: b8f126a8d543 ("net-next: dsa: add dsa support for Mediatek MT7530 switch")
Signed-off-by: DENG Qingfang <dqfext@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mt7530.c |  9 ++-------
 drivers/net/dsa/mt7530.h |  1 +
 net/dsa/tag_mtk.c        | 15 +++++++++++++++
 3 files changed, 18 insertions(+), 7 deletions(-)

diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index cffaf4fdd772..6027bb65f7f6 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -639,11 +639,8 @@ mt7530_cpu_port_enable(struct mt7530_priv *priv,
 	mt7530_write(priv, MT7530_PVC_P(port),
 		     PORT_SPEC_TAG);
 
-	/* Disable auto learning on the cpu port */
-	mt7530_set(priv, MT7530_PSC_P(port), SA_DIS);
-
-	/* Unknown unicast frame fordwarding to the cpu port */
-	mt7530_set(priv, MT7530_MFC, UNU_FFP(BIT(port)));
+	/* Unknown multicast frame forwarding to the cpu port */
+	mt7530_rmw(priv, MT7530_MFC, UNM_FFP_MASK, UNM_FFP(BIT(port)));
 
 	/* Set CPU port number */
 	if (priv->id == ID_MT7621)
@@ -1246,8 +1243,6 @@ mt7530_setup(struct dsa_switch *ds)
 	/* Enable and reset MIB counters */
 	mt7530_mib_reset(ds);
 
-	mt7530_clear(priv, MT7530_MFC, UNU_FFP_MASK);
-
 	for (i = 0; i < MT7530_NUM_PORTS; i++) {
 		/* Disable forwarding by default on all ports */
 		mt7530_rmw(priv, MT7530_PCR_P(i), PCR_MATRIX_MASK,
diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h
index 756140b7dfd5..0e7e36d8f994 100644
--- a/drivers/net/dsa/mt7530.h
+++ b/drivers/net/dsa/mt7530.h
@@ -31,6 +31,7 @@ enum {
 #define MT7530_MFC			0x10
 #define  BC_FFP(x)			(((x) & 0xff) << 24)
 #define  UNM_FFP(x)			(((x) & 0xff) << 16)
+#define  UNM_FFP_MASK			UNM_FFP(~0)
 #define  UNU_FFP(x)			(((x) & 0xff) << 8)
 #define  UNU_FFP_MASK			UNU_FFP(~0)
 #define  CPU_EN				BIT(7)
diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c
index b5705cba8318..d6619edd53e5 100644
--- a/net/dsa/tag_mtk.c
+++ b/net/dsa/tag_mtk.c
@@ -15,6 +15,7 @@
 #define MTK_HDR_XMIT_TAGGED_TPID_8100	1
 #define MTK_HDR_RECV_SOURCE_PORT_MASK	GENMASK(2, 0)
 #define MTK_HDR_XMIT_DP_BIT_MASK	GENMASK(5, 0)
+#define MTK_HDR_XMIT_SA_DIS		BIT(6)
 
 static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb,
 				    struct net_device *dev)
@@ -22,6 +23,9 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb,
 	struct dsa_port *dp = dsa_slave_to_port(dev);
 	u8 *mtk_tag;
 	bool is_vlan_skb = true;
+	unsigned char *dest = eth_hdr(skb)->h_dest;
+	bool is_multicast_skb = is_multicast_ether_addr(dest) &&
+				!is_broadcast_ether_addr(dest);
 
 	/* Build the special tag after the MAC Source Address. If VLAN header
 	 * is present, it's required that VLAN header and special tag is
@@ -47,6 +51,10 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb,
 		     MTK_HDR_XMIT_UNTAGGED;
 	mtk_tag[1] = (1 << dp->index) & MTK_HDR_XMIT_DP_BIT_MASK;
 
+	/* Disable SA learning for multicast frames */
+	if (unlikely(is_multicast_skb))
+		mtk_tag[1] |= MTK_HDR_XMIT_SA_DIS;
+
 	/* Tag control information is kept for 802.1Q */
 	if (!is_vlan_skb) {
 		mtk_tag[2] = 0;
@@ -61,6 +69,9 @@ static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev,
 {
 	int port;
 	__be16 *phdr, hdr;
+	unsigned char *dest = eth_hdr(skb)->h_dest;
+	bool is_multicast_skb = is_multicast_ether_addr(dest) &&
+				!is_broadcast_ether_addr(dest);
 
 	if (unlikely(!pskb_may_pull(skb, MTK_HDR_LEN)))
 		return NULL;
@@ -86,6 +97,10 @@ static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev,
 	if (!skb->dev)
 		return NULL;
 
+	/* Only unicast or broadcast frames are offloaded */
+	if (likely(!is_multicast_skb))
+		skb->offload_fwd_mark = 1;
+
 	return skb;
 }
 
-- 
2.26.2


From dc3f1a0d36523ccc53637d17fb3de33999d35345 Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Fri, 22 May 2020 20:09:28 +0300
Subject: [PATCH 05/25] net: ethernet: ti: cpsw: fix ASSERT_RTNL() warning
 during suspend

[ Upstream commit 4c64b83d03f4aafcdf710caad994cbc855802e74 ]

vlan_for_each() are required to be called with rtnl_lock taken, otherwise
ASSERT_RTNL() warning will be triggered - which happens now during System
resume from suspend:
  cpsw_suspend()
  |- cpsw_ndo_stop()
    |- __hw_addr_ref_unsync_dev()
      |- cpsw_purge_all_mc()
         |- vlan_for_each()
            |- ASSERT_RTNL();

Hence, fix it by surrounding cpsw_ndo_stop() by rtnl_lock/unlock() calls.

Fixes: 15180eca569b ("net: ethernet: ti: cpsw: fix vlan mcast")
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index d7a953c647b4..39df8c8feb6c 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -2999,11 +2999,15 @@ static int cpsw_suspend(struct device *dev)
 	struct cpsw_common *cpsw = dev_get_drvdata(dev);
 	int i;
 
+	rtnl_lock();
+
 	for (i = 0; i < cpsw->data.slaves; i++)
 		if (cpsw->slaves[i].ndev)
 			if (netif_running(cpsw->slaves[i].ndev))
 				cpsw_ndo_stop(cpsw->slaves[i].ndev);
 
+	rtnl_unlock();
+
 	/* Select sleep pin state */
 	pinctrl_pm_select_sleep_state(dev);
 
-- 
2.26.2


From 3429eaa4d67403e66f953306bc871a2e8ec6fe40 Mon Sep 17 00:00:00 2001
From: Boris Sukholitko <boris.sukholitko@broadcom.com>
Date: Tue, 19 May 2020 10:32:37 +0300
Subject: [PATCH 06/25] __netif_receive_skb_core: pass skb by reference

[ Upstream commit c0bbbdc32febd4f034ecbf3ea17865785b2c0652 ]

__netif_receive_skb_core may change the skb pointer passed into it (e.g.
in rx_handler). The original skb may be freed as a result of this
operation.

The callers of __netif_receive_skb_core may further process original skb
by using pt_prev pointer returned by __netif_receive_skb_core thus
leading to unpleasant effects.

The solution is to pass skb by reference into __netif_receive_skb_core.

v2: Added Fixes tag and comment regarding ppt_prev and skb invariant.

Fixes: 88eb1944e18c ("net: core: propagate SKB lists through packet_type lookup")
Signed-off-by: Boris Sukholitko <boris.sukholitko@broadcom.com>
Acked-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 120b994af31c..8552874e5aac 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4713,11 +4713,12 @@ static inline int nf_ingress(struct sk_buff *skb, struct packet_type **pt_prev,
 	return 0;
 }
 
-static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc,
+static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc,
 				    struct packet_type **ppt_prev)
 {
 	struct packet_type *ptype, *pt_prev;
 	rx_handler_func_t *rx_handler;
+	struct sk_buff *skb = *pskb;
 	struct net_device *orig_dev;
 	bool deliver_exact = false;
 	int ret = NET_RX_DROP;
@@ -4748,8 +4749,10 @@ static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc,
 		ret2 = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog), skb);
 		preempt_enable();
 
-		if (ret2 != XDP_PASS)
-			return NET_RX_DROP;
+		if (ret2 != XDP_PASS) {
+			ret = NET_RX_DROP;
+			goto out;
+		}
 		skb_reset_mac_len(skb);
 	}
 
@@ -4899,6 +4902,13 @@ static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc,
 	}
 
 out:
+	/* The invariant here is that if *ppt_prev is not NULL
+	 * then skb should also be non-NULL.
+	 *
+	 * Apparently *ppt_prev assignment above holds this invariant due to
+	 * skb dereferencing near it.
+	 */
+	*pskb = skb;
 	return ret;
 }
 
@@ -4908,7 +4918,7 @@ static int __netif_receive_skb_one_core(struct sk_buff *skb, bool pfmemalloc)
 	struct packet_type *pt_prev = NULL;
 	int ret;
 
-	ret = __netif_receive_skb_core(skb, pfmemalloc, &pt_prev);
+	ret = __netif_receive_skb_core(&skb, pfmemalloc, &pt_prev);
 	if (pt_prev)
 		ret = INDIRECT_CALL_INET(pt_prev->func, ipv6_rcv, ip_rcv, skb,
 					 skb->dev, pt_prev, orig_dev);
@@ -4986,7 +4996,7 @@ static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemallo
 		struct packet_type *pt_prev = NULL;
 
 		skb_list_del_init(skb);
-		__netif_receive_skb_core(skb, pfmemalloc, &pt_prev);
+		__netif_receive_skb_core(&skb, pfmemalloc, &pt_prev);
 		if (!pt_prev)
 			continue;
 		if (pt_curr != pt_prev || od_curr != orig_dev) {
-- 
2.26.2


From 3ce434af3c81872ee49d373788b2b852f45ecd19 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Mon, 18 May 2020 17:13:34 -0700
Subject: [PATCH 07/25] net: inet_csk: Fix so_reuseport bind-address cache in
 tb->fast*

[ Upstream commit 88d7fcfa3b1fe670f0412b95be785aafca63352b ]

The commit 637bc8bbe6c0 ("inet: reset tb->fastreuseport when adding a reuseport sk")
added a bind-address cache in tb->fast*.  The tb->fast* caches the address
of a sk which has successfully been binded with SO_REUSEPORT ON.  The idea
is to avoid the expensive conflict search in inet_csk_bind_conflict().

There is an issue with wildcard matching where sk_reuseport_match() should
have returned false but it is currently returning true.  It ends up
hiding bind conflict.  For example,

bind("[::1]:443"); /* without SO_REUSEPORT. Succeed. */
bind("[::2]:443"); /* with    SO_REUSEPORT. Succeed. */
bind("[::]:443");  /* with    SO_REUSEPORT. Still Succeed where it shouldn't */

The last bind("[::]:443") with SO_REUSEPORT on should have failed because
it should have a conflict with the very first bind("[::1]:443") which
has SO_REUSEPORT off.  However, the address "[::2]" is cached in
tb->fast* in the second bind. In the last bind, the sk_reuseport_match()
returns true because the binding sk's wildcard addr "[::]" matches with
the "[::2]" cached in tb->fast*.

The correct bind conflict is reported by removing the second
bind such that tb->fast* cache is not involved and forces the
bind("[::]:443") to go through the inet_csk_bind_conflict():

bind("[::1]:443"); /* without SO_REUSEPORT. Succeed. */
bind("[::]:443");  /* with    SO_REUSEPORT. -EADDRINUSE */

The expected behavior for sk_reuseport_match() is, it should only allow
the "cached" tb->fast* address to be used as a wildcard match but not
the address of the binding sk.  To do that, the current
"bool match_wildcard" arg is split into
"bool match_sk1_wildcard" and "bool match_sk2_wildcard".

This change only affects the sk_reuseport_match() which is only
used by inet_csk (e.g. TCP).
The other use cases are calling inet_rcv_saddr_equal() and
this patch makes it pass the same "match_wildcard" arg twice to
the "ipv[46]_rcv_saddr_equal(..., match_wildcard, match_wildcard)".

Cc: Josef Bacik <jbacik@fb.com>
Fixes: 637bc8bbe6c0 ("inet: reset tb->fastreuseport when adding a reuseport sk")
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/inet_connection_sock.c | 43 ++++++++++++++++++---------------
 1 file changed, 24 insertions(+), 19 deletions(-)

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index b0010c710802..5e486895d67c 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -24,17 +24,19 @@
 #include <net/addrconf.h>
 
 #if IS_ENABLED(CONFIG_IPV6)
-/* match_wildcard == true:  IPV6_ADDR_ANY equals to any IPv6 addresses if IPv6
- *                          only, and any IPv4 addresses if not IPv6 only
- * match_wildcard == false: addresses must be exactly the same, i.e.
- *                          IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY,
- *                          and 0.0.0.0 equals to 0.0.0.0 only
+/* match_sk*_wildcard == true:  IPV6_ADDR_ANY equals to any IPv6 addresses
+ *				if IPv6 only, and any IPv4 addresses
+ *				if not IPv6 only
+ * match_sk*_wildcard == false: addresses must be exactly the same, i.e.
+ *				IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY,
+ *				and 0.0.0.0 equals to 0.0.0.0 only
  */
 static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
 				 const struct in6_addr *sk2_rcv_saddr6,
 				 __be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
 				 bool sk1_ipv6only, bool sk2_ipv6only,
-				 bool match_wildcard)
+				 bool match_sk1_wildcard,
+				 bool match_sk2_wildcard)
 {
 	int addr_type = ipv6_addr_type(sk1_rcv_saddr6);
 	int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED;
@@ -44,8 +46,8 @@ static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
 		if (!sk2_ipv6only) {
 			if (sk1_rcv_saddr == sk2_rcv_saddr)
 				return true;
-			if (!sk1_rcv_saddr || !sk2_rcv_saddr)
-				return match_wildcard;
+			return (match_sk1_wildcard && !sk1_rcv_saddr) ||
+				(match_sk2_wildcard && !sk2_rcv_saddr);
 		}
 		return false;
 	}
@@ -53,11 +55,11 @@ static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
 	if (addr_type == IPV6_ADDR_ANY && addr_type2 == IPV6_ADDR_ANY)
 		return true;
 
-	if (addr_type2 == IPV6_ADDR_ANY && match_wildcard &&
+	if (addr_type2 == IPV6_ADDR_ANY && match_sk2_wildcard &&
 	    !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED))
 		return true;
 
-	if (addr_type == IPV6_ADDR_ANY && match_wildcard &&
+	if (addr_type == IPV6_ADDR_ANY && match_sk1_wildcard &&
 	    !(sk1_ipv6only && addr_type2 == IPV6_ADDR_MAPPED))
 		return true;
 
@@ -69,18 +71,19 @@ static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
 }
 #endif
 
-/* match_wildcard == true:  0.0.0.0 equals to any IPv4 addresses
- * match_wildcard == false: addresses must be exactly the same, i.e.
- *                          0.0.0.0 only equals to 0.0.0.0
+/* match_sk*_wildcard == true:  0.0.0.0 equals to any IPv4 addresses
+ * match_sk*_wildcard == false: addresses must be exactly the same, i.e.
+ *				0.0.0.0 only equals to 0.0.0.0
  */
 static bool ipv4_rcv_saddr_equal(__be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
-				 bool sk2_ipv6only, bool match_wildcard)
+				 bool sk2_ipv6only, bool match_sk1_wildcard,
+				 bool match_sk2_wildcard)
 {
 	if (!sk2_ipv6only) {
 		if (sk1_rcv_saddr == sk2_rcv_saddr)
 			return true;
-		if (!sk1_rcv_saddr || !sk2_rcv_saddr)
-			return match_wildcard;
+		return (match_sk1_wildcard && !sk1_rcv_saddr) ||
+			(match_sk2_wildcard && !sk2_rcv_saddr);
 	}
 	return false;
 }
@@ -96,10 +99,12 @@ bool inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2,
 					    sk2->sk_rcv_saddr,
 					    ipv6_only_sock(sk),
 					    ipv6_only_sock(sk2),
+					    match_wildcard,
 					    match_wildcard);
 #endif
 	return ipv4_rcv_saddr_equal(sk->sk_rcv_saddr, sk2->sk_rcv_saddr,
-				    ipv6_only_sock(sk2), match_wildcard);
+				    ipv6_only_sock(sk2), match_wildcard,
+				    match_wildcard);
 }
 EXPORT_SYMBOL(inet_rcv_saddr_equal);
 
@@ -273,10 +278,10 @@ static inline int sk_reuseport_match(struct inet_bind_bucket *tb,
 					    tb->fast_rcv_saddr,
 					    sk->sk_rcv_saddr,
 					    tb->fast_ipv6_only,
-					    ipv6_only_sock(sk), true);
+					    ipv6_only_sock(sk), true, false);
 #endif
 	return ipv4_rcv_saddr_equal(tb->fast_rcv_saddr, sk->sk_rcv_saddr,
-				    ipv6_only_sock(sk), true);
+				    ipv6_only_sock(sk), true, false);
 }
 
 /* Obtain a reference to a local port for the given sock,
-- 
2.26.2


From 4bfa6e57c8a4b3cd85cee439c24db5dd7785800b Mon Sep 17 00:00:00 2001
From: Vadim Fedorenko <vfedorenko@novek.ru>
Date: Wed, 20 May 2020 11:50:48 +0300
Subject: [PATCH 08/25] net: ipip: fix wrong address family in init error path

[ Upstream commit 57ebc8f08504f176eb0f25b3e0fde517dec61a4f ]

In case of error with MPLS support the code is misusing AF_INET
instead of AF_MPLS.

Fixes: 1b69e7e6c4da ("ipip: support MPLS over IPv4")
Signed-off-by: Vadim Fedorenko <vfedorenko@novek.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ipip.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 2f01cf6fa0de..678575adaf3b 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -698,7 +698,7 @@ static int __init ipip_init(void)
 
 rtnl_link_failed:
 #if IS_ENABLED(CONFIG_MPLS)
-	xfrm4_tunnel_deregister(&mplsip_handler, AF_INET);
+	xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS);
 xfrm_tunnel_mplsip_failed:
 
 #endif
-- 
2.26.2


From 26306ccedd3998d9c661222c42383f2a8725b7cc Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Fri, 27 Dec 2019 07:01:53 +0200
Subject: [PATCH 09/25] net/mlx5: Add command entry handling completion

[ Upstream commit 17d00e839d3b592da9659c1977d45f85b77f986a ]

When FW response to commands is very slow and all command entries in
use are waiting for completion we can have a race where commands can get
timeout before they get out of the queue and handled. Timeout
completion on uninitialized command will cause releasing command's
buffers before accessing it for initialization and then we will get NULL
pointer exception while trying access it. It may also cause releasing
buffers of another command since we may have timeout completion before
even allocating entry index for this command.
Add entry handling completion to avoid this race.

Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters")
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 14 ++++++++++++++
 include/linux/mlx5/driver.h                   |  1 +
 2 files changed, 15 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 08048a2d7259..b6a3370068f1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -861,6 +861,7 @@ static void cmd_work_handler(struct work_struct *work)
 	int alloc_ret;
 	int cmd_mode;
 
+	complete(&ent->handling);
 	sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem;
 	down(sem);
 	if (!ent->page_queue) {
@@ -978,6 +979,11 @@ static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
 	struct mlx5_cmd *cmd = &dev->cmd;
 	int err;
 
+	if (!wait_for_completion_timeout(&ent->handling, timeout) &&
+	    cancel_work_sync(&ent->work)) {
+		ent->ret = -ECANCELED;
+		goto out_err;
+	}
 	if (cmd->mode == CMD_MODE_POLLING || ent->polling) {
 		wait_for_completion(&ent->done);
 	} else if (!wait_for_completion_timeout(&ent->done, timeout)) {
@@ -985,12 +991,17 @@ static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
 		mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
 	}
 
+out_err:
 	err = ent->ret;
 
 	if (err == -ETIMEDOUT) {
 		mlx5_core_warn(dev, "%s(0x%x) timeout. Will cause a leak of a command resource\n",
 			       mlx5_command_str(msg_to_opcode(ent->in)),
 			       msg_to_opcode(ent->in));
+	} else if (err == -ECANCELED) {
+		mlx5_core_warn(dev, "%s(0x%x) canceled on out of queue timeout.\n",
+			       mlx5_command_str(msg_to_opcode(ent->in)),
+			       msg_to_opcode(ent->in));
 	}
 	mlx5_core_dbg(dev, "err %d, delivery status %s(%d)\n",
 		      err, deliv_status_to_str(ent->status), ent->status);
@@ -1026,6 +1037,7 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 	ent->token = token;
 	ent->polling = force_polling;
 
+	init_completion(&ent->handling);
 	if (!callback)
 		init_completion(&ent->done);
 
@@ -1045,6 +1057,8 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 	err = wait_func(dev, ent);
 	if (err == -ETIMEDOUT)
 		goto out;
+	if (err == -ECANCELED)
+		goto out_free;
 
 	ds = ent->ts2 - ent->ts1;
 	op = MLX5_GET(mbox_in, in->first.data, opcode);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 3e80f03a387f..897829651204 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -756,6 +756,7 @@ struct mlx5_cmd_work_ent {
 	struct delayed_work	cb_timeout_work;
 	void		       *context;
 	int			idx;
+	struct completion	handling;
 	struct completion	done;
 	struct mlx5_cmd        *cmd;
 	struct work_struct	work;
-- 
2.26.2


From f662b2a639211dcc68aef489da332f51f0797dbb Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Wed, 20 May 2020 12:26:35 +0100
Subject: [PATCH 10/25] net: mvpp2: fix RX hashing for non-10G ports

[ Upstream commit 3138a07ce219acde4c0d7ea0b6d54ba64153328b ]

When rxhash is enabled on any ethernet port except the first in each CP
block, traffic flow is prevented.  The analysis is below:

I've been investigating this afternoon, and what I've found, comparing
a kernel without 895586d5dc32 and with 895586d5dc32 applied is:

- The table programmed into the hardware via mvpp22_rss_fill_table()
  appears to be identical with or without the commit.

- When rxhash is enabled on eth2, mvpp2_rss_port_c2_enable() reports
  that c2.attr[0] and c2.attr[2] are written back containing:

   - with 895586d5dc32, failing:    00200000 40000000
   - without 895586d5dc32, working: 04000000 40000000

- When disabling rxhash, c2.attr[0] and c2.attr[2] are written back as:

   04000000 00000000

The second value represents the MVPP22_CLS_C2_ATTR2_RSS_EN bit, the
first value is the queue number, which comprises two fields. The high
5 bits are 24:29 and the low three are 21:23 inclusive. This comes
from:

       c2.attr[0] = MVPP22_CLS_C2_ATTR0_QHIGH(qh) |
                     MVPP22_CLS_C2_ATTR0_QLOW(ql);

So, the working case gives eth2 a queue id of 4.0, or 32 as per
port->first_rxq, and the non-working case a queue id of 0.1, or 1.
The allocation of queue IDs seems to be in mvpp2_port_probe():

        if (priv->hw_version == MVPP21)
                port->first_rxq = port->id * port->nrxqs;
        else
                port->first_rxq = port->id * priv->max_port_rxqs;

Where:

        if (priv->hw_version == MVPP21)
                priv->max_port_rxqs = 8;
        else
                priv->max_port_rxqs = 32;

Making the port 0 (eth0 / eth1) have port->first_rxq = 0, and port 1
(eth2) be 32. It seems the idea is that the first 32 queues belong to
port 0, the second 32 queues belong to port 1, etc.

mvpp2_rss_port_c2_enable() gets the queue number from it's parameter,
'ctx', which comes from mvpp22_rss_ctx(port, 0). This returns
port->rss_ctx[0].

mvpp22_rss_context_create() is responsible for allocating that, which
it does by looking for an unallocated priv->rss_tables[] pointer. This
table is shared amongst all ports on the CP silicon.

When we write the tables in mvpp22_rss_fill_table(), the RSS table
entry is defined by:

                u32 sel = MVPP22_RSS_INDEX_TABLE(rss_ctx) |
                          MVPP22_RSS_INDEX_TABLE_ENTRY(i);

where rss_ctx is the context ID (queue number) and i is the index in
the table.

If we look at what is written:

- The first table to be written has "sel" values of 00000000..0000001f,
  containing values 0..3. This appears to be for eth1. This is table 0,
  RX queue number 0.
- The second table has "sel" values of 00000100..0000011f, and appears
  to be for eth2.  These contain values 0x20..0x23. This is table 1,
  RX queue number 0.
- The third table has "sel" values of 00000200..0000021f, and appears
  to be for eth3.  These contain values 0x40..0x43. This is table 2,
  RX queue number 0.

How do queue numbers translate to the RSS table?  There is another
table - the RXQ2RSS table, indexed by the MVPP22_RSS_INDEX_QUEUE field
of MVPP22_RSS_INDEX and accessed through the MVPP22_RXQ2RSS_TABLE
register. Before 895586d5dc32, it was:

       mvpp2_write(priv, MVPP22_RSS_INDEX,
                   MVPP22_RSS_INDEX_QUEUE(port->first_rxq));
       mvpp2_write(priv, MVPP22_RXQ2RSS_TABLE,
                   MVPP22_RSS_TABLE_POINTER(port->id));

and after:

       mvpp2_write(priv, MVPP22_RSS_INDEX, MVPP22_RSS_INDEX_QUEUE(ctx));
       mvpp2_write(priv, MVPP22_RXQ2RSS_TABLE, MVPP22_RSS_TABLE_POINTER(ctx));

Before the commit, for eth2, that would've contained '32' for the
index and '1' for the table pointer - mapping queue 32 to table 1.
Remember that this is queue-high.queue-low of 4.0.

After the commit, we appear to map queue 1 to table 1. That again
looks fine on the face of it.

Section 9.3.1 of the A8040 manual seems indicate the reason that the
queue number is separated. queue-low seems to always come from the
classifier, whereas queue-high can be from the ingress physical port
number or the classifier depending on the MVPP2_CLS_SWFWD_PCTRL_REG.

We set the port bit in MVPP2_CLS_SWFWD_PCTRL_REG, meaning that queue-high
comes from the MVPP2_CLS_SWFWD_P2HQ_REG() register... and this seems to
be where our bug comes from.

mvpp2_cls_oversize_rxq_set() sets this up as:

        mvpp2_write(port->priv, MVPP2_CLS_SWFWD_P2HQ_REG(port->id),
                    (port->first_rxq >> MVPP2_CLS_OVERSIZE_RXQ_LOW_BITS));

        val = mvpp2_read(port->priv, MVPP2_CLS_SWFWD_PCTRL_REG);
        val |= MVPP2_CLS_SWFWD_PCTRL_MASK(port->id);
        mvpp2_write(port->priv, MVPP2_CLS_SWFWD_PCTRL_REG, val);

Setting the MVPP2_CLS_SWFWD_PCTRL_MASK bit means that the queue-high
for eth2 is _always_ 4, so only queues 32 through 39 inclusive are
available to eth2. Yet, we're trying to tell the classifier to set
queue-high, which will be ignored, to zero. Hence, the queue-high
field (MVPP22_CLS_C2_ATTR0_QHIGH()) from the classifier will be
ignored.

This means we end up directing traffic from eth2 not to queue 1, but
to queue 33, and then we tell it to look up queue 33 in the RSS table.
However, RSS table has not been programmed for queue 33, and so it ends
up (presumably) dropping the packets.

It seems that mvpp22_rss_context_create() doesn't take account of the
fact that the upper 5 bits of the queue ID can't actually be changed
due to the settings in mvpp2_cls_oversize_rxq_set(), _or_ it seems that
mvpp2_cls_oversize_rxq_set() has been missed in this commit. Either
way, these two functions mutually disagree with what queue number
should be used.

Looking deeper into what mvpp2_cls_oversize_rxq_set() and the MTU
validation is doing, it seems that MVPP2_CLS_SWFWD_P2HQ_REG() is used
for over-sized packets attempting to egress through this port. With
the classifier having had RSS enabled and directing eth2 traffic to
queue 1, we may still have packets appearing on queue 32 for this port.

However, the only way we may end up with over-sized packets attempting
to egress through eth2 - is if the A8040 forwards frames between its
ports. From what I can see, we don't support that feature, and the
kernel restricts the egress packet size to the MTU. In any case, if we
were to attempt to transmit an oversized packet, we have no support in
the kernel to deal with that appearing in the port's receive queue.

So, this patch attempts to solve the issue by clearing the
MVPP2_CLS_SWFWD_PCTRL_MASK() bit, allowing MVPP22_CLS_C2_ATTR0_QHIGH()
from the classifier to define the queue-high field of the queue number.

My testing seems to confirm my findings above - clearing this bit
means that if I enable rxhash on eth2, the interface can then pass
traffic, as we are now directing traffic to RX queue 1 rather than
queue 33. Traffic still seems to work with rxhash off as well.

Reported-by: Matteo Croce <mcroce@redhat.com>
Tested-by: Matteo Croce <mcroce@redhat.com>
Fixes: 895586d5dc32 ("net: mvpp2: cls: Use RSS contexts to handle RSS tables")
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
index 4344a59c823f..6122057d60c0 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
@@ -1070,7 +1070,7 @@ void mvpp2_cls_oversize_rxq_set(struct mvpp2_port *port)
 		    (port->first_rxq >> MVPP2_CLS_OVERSIZE_RXQ_LOW_BITS));
 
 	val = mvpp2_read(port->priv, MVPP2_CLS_SWFWD_PCTRL_REG);
-	val |= MVPP2_CLS_SWFWD_PCTRL_MASK(port->id);
+	val &= ~MVPP2_CLS_SWFWD_PCTRL_MASK(port->id);
 	mvpp2_write(port->priv, MVPP2_CLS_SWFWD_PCTRL_REG, val);
 }
 
-- 
2.26.2


From 0a01569eaffb4cb7fb671c647cb7b333500bc2cc Mon Sep 17 00:00:00 2001
From: Stephen Worley <sworley@cumulusnetworks.com>
Date: Tue, 19 May 2020 21:57:12 -0400
Subject: [PATCH 11/25] net: nlmsg_cancel() if put fails for nhmsg

[ Upstream commit d69100b8eee27c2d60ee52df76e0b80a8d492d34 ]

Fixes data remnant seen when we fail to reserve space for a
nexthop group during a larger dump.

If we fail the reservation, we goto nla_put_failure and
cancel the message.

Reproduce with the following iproute2 commands:
=====================
ip link add dummy1 type dummy
ip link add dummy2 type dummy
ip link add dummy3 type dummy
ip link add dummy4 type dummy
ip link add dummy5 type dummy
ip link add dummy6 type dummy
ip link add dummy7 type dummy
ip link add dummy8 type dummy
ip link add dummy9 type dummy
ip link add dummy10 type dummy
ip link add dummy11 type dummy
ip link add dummy12 type dummy
ip link add dummy13 type dummy
ip link add dummy14 type dummy
ip link add dummy15 type dummy
ip link add dummy16 type dummy
ip link add dummy17 type dummy
ip link add dummy18 type dummy
ip link add dummy19 type dummy
ip link add dummy20 type dummy
ip link add dummy21 type dummy
ip link add dummy22 type dummy
ip link add dummy23 type dummy
ip link add dummy24 type dummy
ip link add dummy25 type dummy
ip link add dummy26 type dummy
ip link add dummy27 type dummy
ip link add dummy28 type dummy
ip link add dummy29 type dummy
ip link add dummy30 type dummy
ip link add dummy31 type dummy
ip link add dummy32 type dummy

ip link set dummy1 up
ip link set dummy2 up
ip link set dummy3 up
ip link set dummy4 up
ip link set dummy5 up
ip link set dummy6 up
ip link set dummy7 up
ip link set dummy8 up
ip link set dummy9 up
ip link set dummy10 up
ip link set dummy11 up
ip link set dummy12 up
ip link set dummy13 up
ip link set dummy14 up
ip link set dummy15 up
ip link set dummy16 up
ip link set dummy17 up
ip link set dummy18 up
ip link set dummy19 up
ip link set dummy20 up
ip link set dummy21 up
ip link set dummy22 up
ip link set dummy23 up
ip link set dummy24 up
ip link set dummy25 up
ip link set dummy26 up
ip link set dummy27 up
ip link set dummy28 up
ip link set dummy29 up
ip link set dummy30 up
ip link set dummy31 up
ip link set dummy32 up

ip link set dummy33 up
ip link set dummy34 up

ip link set vrf-red up
ip link set vrf-blue up

ip link set dummyVRFred up
ip link set dummyVRFblue up

ip ro add 1.1.1.1/32 dev dummy1
ip ro add 1.1.1.2/32 dev dummy2
ip ro add 1.1.1.3/32 dev dummy3
ip ro add 1.1.1.4/32 dev dummy4
ip ro add 1.1.1.5/32 dev dummy5
ip ro add 1.1.1.6/32 dev dummy6
ip ro add 1.1.1.7/32 dev dummy7
ip ro add 1.1.1.8/32 dev dummy8
ip ro add 1.1.1.9/32 dev dummy9
ip ro add 1.1.1.10/32 dev dummy10
ip ro add 1.1.1.11/32 dev dummy11
ip ro add 1.1.1.12/32 dev dummy12
ip ro add 1.1.1.13/32 dev dummy13
ip ro add 1.1.1.14/32 dev dummy14
ip ro add 1.1.1.15/32 dev dummy15
ip ro add 1.1.1.16/32 dev dummy16
ip ro add 1.1.1.17/32 dev dummy17
ip ro add 1.1.1.18/32 dev dummy18
ip ro add 1.1.1.19/32 dev dummy19
ip ro add 1.1.1.20/32 dev dummy20
ip ro add 1.1.1.21/32 dev dummy21
ip ro add 1.1.1.22/32 dev dummy22
ip ro add 1.1.1.23/32 dev dummy23
ip ro add 1.1.1.24/32 dev dummy24
ip ro add 1.1.1.25/32 dev dummy25
ip ro add 1.1.1.26/32 dev dummy26
ip ro add 1.1.1.27/32 dev dummy27
ip ro add 1.1.1.28/32 dev dummy28
ip ro add 1.1.1.29/32 dev dummy29
ip ro add 1.1.1.30/32 dev dummy30
ip ro add 1.1.1.31/32 dev dummy31
ip ro add 1.1.1.32/32 dev dummy32

ip next add id 1 via 1.1.1.1 dev dummy1
ip next add id 2 via 1.1.1.2 dev dummy2
ip next add id 3 via 1.1.1.3 dev dummy3
ip next add id 4 via 1.1.1.4 dev dummy4
ip next add id 5 via 1.1.1.5 dev dummy5
ip next add id 6 via 1.1.1.6 dev dummy6
ip next add id 7 via 1.1.1.7 dev dummy7
ip next add id 8 via 1.1.1.8 dev dummy8
ip next add id 9 via 1.1.1.9 dev dummy9
ip next add id 10 via 1.1.1.10 dev dummy10
ip next add id 11 via 1.1.1.11 dev dummy11
ip next add id 12 via 1.1.1.12 dev dummy12
ip next add id 13 via 1.1.1.13 dev dummy13
ip next add id 14 via 1.1.1.14 dev dummy14
ip next add id 15 via 1.1.1.15 dev dummy15
ip next add id 16 via 1.1.1.16 dev dummy16
ip next add id 17 via 1.1.1.17 dev dummy17
ip next add id 18 via 1.1.1.18 dev dummy18
ip next add id 19 via 1.1.1.19 dev dummy19
ip next add id 20 via 1.1.1.20 dev dummy20
ip next add id 21 via 1.1.1.21 dev dummy21
ip next add id 22 via 1.1.1.22 dev dummy22
ip next add id 23 via 1.1.1.23 dev dummy23
ip next add id 24 via 1.1.1.24 dev dummy24
ip next add id 25 via 1.1.1.25 dev dummy25
ip next add id 26 via 1.1.1.26 dev dummy26
ip next add id 27 via 1.1.1.27 dev dummy27
ip next add id 28 via 1.1.1.28 dev dummy28
ip next add id 29 via 1.1.1.29 dev dummy29
ip next add id 30 via 1.1.1.30 dev dummy30
ip next add id 31 via 1.1.1.31 dev dummy31
ip next add id 32 via 1.1.1.32 dev dummy32

i=100

while [ $i -le 200 ]
do
ip next add id $i group 1/2/3/4/5/6/7/8/9/10/11/12/13/14/15/16/17/18/19

	echo $i

	((i++))

done

ip next add id 999 group 1/2/3/4/5/6

ip next ls

========================

Fixes: ab84be7e54fc ("net: Initial nexthop code")
Signed-off-by: Stephen Worley <sworley@cumulusnetworks.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/nexthop.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 3737d32ad11a..d2369297910b 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -277,6 +277,7 @@ static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh,
 	return 0;
 
 nla_put_failure:
+	nlmsg_cancel(skb, nlh);
 	return -EMSGSIZE;
 }
 
-- 
2.26.2


From 6a5b21a23b3ba29b1cc601ceeb8e6fd558d2d0e6 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Tue, 19 May 2020 23:44:16 +0530
Subject: [PATCH 12/25] net: qrtr: Fix passing invalid reference to
 qrtr_local_enqueue()

[ Upstream commit d28ea1fbbf437054ef339afec241019f2c4e2bb6 ]

Once the traversal of the list is completed with list_for_each_entry(),
the iterator (node) will point to an invalid object. So passing this to
qrtr_local_enqueue() which is outside of the iterator block is erroneous
eventhough the object is not used.

So fix this by passing NULL to qrtr_local_enqueue().

Fixes: bdabad3e363d ("net: Add Qualcomm IPC router")
Reported-by: kbuild test robot <lkp@intel.com>
Reported-by: Julia Lawall <julia.lawall@lip6.fr>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/qrtr/qrtr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index 930f48a20546..2a4d50e04441 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -711,7 +711,7 @@ static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb,
 	}
 	mutex_unlock(&qrtr_node_lock);
 
-	qrtr_local_enqueue(node, skb, type, from, to);
+	qrtr_local_enqueue(NULL, skb, type, from, to);
 
 	return 0;
 }
-- 
2.26.2


From 33ce424a36ccc37bf7ff6d7898319a15701f77e6 Mon Sep 17 00:00:00 2001
From: Yuqi Jin <jinyuqi@huawei.com>
Date: Sat, 16 May 2020 11:46:49 +0800
Subject: [PATCH 13/25] net: revert "net: get rid of an signed integer overflow
 in ip_idents_reserve()"

[ Upstream commit a6211caa634da39d861a47437ffcda8b38ef421b ]

Commit adb03115f459 ("net: get rid of an signed integer overflow in ip_idents_reserve()")
used atomic_cmpxchg to replace "atomic_add_return" inside the function
"ip_idents_reserve". The reason was to avoid UBSAN warning.
However, this change has caused performance degrade and in GCC-8,
fno-strict-overflow is now mapped to -fwrapv -fwrapv-pointer
and signed integer overflow is now undefined by default at all
optimization levels[1]. Moreover, it was a bug in UBSAN vs -fwrapv
/-fno-strict-overflow, so Let's revert it safely.

[1] https://gcc.gnu.org/gcc-8/changes.html

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Suggested-by: Eric Dumazet <edumazet@google.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Jiri Pirko <jiri@resnulli.us>
Cc: Arvind Sankar <nivedita@alum.mit.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jiong Wang <jiongwang@huawei.com>
Signed-off-by: Yuqi Jin <jinyuqi@huawei.com>
Signed-off-by: Shaokun Zhang <zhangshaokun@hisilicon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 558ddf7ab395..b3a8d32f7d8d 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -490,18 +490,16 @@ u32 ip_idents_reserve(u32 hash, int segs)
 	atomic_t *p_id = ip_idents + hash % IP_IDENTS_SZ;
 	u32 old = READ_ONCE(*p_tstamp);
 	u32 now = (u32)jiffies;
-	u32 new, delta = 0;
+	u32 delta = 0;
 
 	if (old != now && cmpxchg(p_tstamp, old, now) == old)
 		delta = prandom_u32_max(now - old);
 
-	/* Do not use atomic_add_return() as it makes UBSAN unhappy */
-	do {
-		old = (u32)atomic_read(p_id);
-		new = old + delta + segs;
-	} while (atomic_cmpxchg(p_id, old, new) != old);
-
-	return new - segs;
+	/* If UBSAN reports an error there, please make sure your compiler
+	 * supports -fno-strict-overflow before reporting it that was a bug
+	 * in UBSAN, and it has been fixed in GCC-8.
+	 */
+	return atomic_add_return(segs + delta, p_id) - segs;
 }
 EXPORT_SYMBOL(ip_idents_reserve);
 
-- 
2.26.2


From c6c6525ed66047f74af6855553c4f8817b2c19d3 Mon Sep 17 00:00:00 2001
From: Roman Mashak <mrv@mojatatu.com>
Date: Sun, 17 May 2020 08:46:31 -0400
Subject: [PATCH 14/25] net sched: fix reporting the first-time use timestamp

[ Upstream commit b15e62631c5f19fea9895f7632dae9c1b27fe0cd ]

When a new action is installed, firstuse field of 'tcf_t' is explicitly set
to 0. Value of zero means "new action, not yet used"; as a packet hits the
action, 'firstuse' is stamped with the current jiffies value.

tcf_tm_dump() should return 0 for firstuse if action has not yet been hit.

Fixes: 48d8ee1694dd ("net sched actions: aggregate dumping of actions timeinfo")
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Roman Mashak <mrv@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/act_api.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/net/act_api.h b/include/net/act_api.h
index b18c699681ca..59d05feecfb8 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -69,7 +69,8 @@ static inline void tcf_tm_dump(struct tcf_t *dtm, const struct tcf_t *stm)
 {
 	dtm->install = jiffies_to_clock_t(jiffies - stm->install);
 	dtm->lastuse = jiffies_to_clock_t(jiffies - stm->lastuse);
-	dtm->firstuse = jiffies_to_clock_t(jiffies - stm->firstuse);
+	dtm->firstuse = stm->firstuse ?
+		jiffies_to_clock_t(jiffies - stm->firstuse) : 0;
 	dtm->expires = jiffies_to_clock_t(stm->expires);
 }
 
-- 
2.26.2


From d0cb016321c1743100f871b364e2bb882346c0ae Mon Sep 17 00:00:00 2001
From: Vinay Kumar Yadav <vinay.yadav@chelsio.com>
Date: Sat, 23 May 2020 01:40:31 +0530
Subject: [PATCH 15/25] net/tls: fix race condition causing kernel panic

[ Upstream commit 0cada33241d9de205522e3858b18e506ca5cce2c ]

tls_sw_recvmsg() and tls_decrypt_done() can be run concurrently.
// tls_sw_recvmsg()
	if (atomic_read(&ctx->decrypt_pending))
		crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
	else
		reinit_completion(&ctx->async_wait.completion);

//tls_decrypt_done()
  	pending = atomic_dec_return(&ctx->decrypt_pending);

  	if (!pending && READ_ONCE(ctx->async_notify))
  		complete(&ctx->async_wait.completion);

Consider the scenario tls_decrypt_done() is about to run complete()

	if (!pending && READ_ONCE(ctx->async_notify))

and tls_sw_recvmsg() reads decrypt_pending == 0, does reinit_completion(),
then tls_decrypt_done() runs complete(). This sequence of execution
results in wrong completion. Consequently, for next decrypt request,
it will not wait for completion, eventually on connection close, crypto
resources freed, there is no way to handle pending decrypt response.

This race condition can be avoided by having atomic_read() mutually
exclusive with atomic_dec_return(),complete().Intoduced spin lock to
ensure the mutual exclution.

Addressed similar problem in tx direction.

v1->v2:
- More readable commit message.
- Corrected the lock to fix new race scenario.
- Removed barrier which is not needed now.

Fixes: a42055e8d2c3 ("net/tls: Add support for async encryption of records for performance")
Signed-off-by: Vinay Kumar Yadav <vinay.yadav@chelsio.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h |  4 ++++
 net/tls/tls_sw.c  | 33 +++++++++++++++++++++++++++------
 2 files changed, 31 insertions(+), 6 deletions(-)

diff --git a/include/net/tls.h b/include/net/tls.h
index 093abb5a3dff..db26e3ec918f 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -157,6 +157,8 @@ struct tls_sw_context_tx {
 	struct tls_rec *open_rec;
 	struct list_head tx_list;
 	atomic_t encrypt_pending;
+	/* protect crypto_wait with encrypt_pending */
+	spinlock_t encrypt_compl_lock;
 	int async_notify;
 	int async_capable;
 
@@ -177,6 +179,8 @@ struct tls_sw_context_rx {
 	int async_capable;
 	bool decrypted;
 	atomic_t decrypt_pending;
+	/* protect crypto_wait with decrypt_pending*/
+	spinlock_t decrypt_compl_lock;
 	bool async_notify;
 };
 
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 5513a08a4308..6a2e94fd8cf2 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -203,10 +203,12 @@ static void tls_decrypt_done(struct crypto_async_request *req, int err)
 
 	kfree(aead_req);
 
+	spin_lock_bh(&ctx->decrypt_compl_lock);
 	pending = atomic_dec_return(&ctx->decrypt_pending);
 
-	if (!pending && READ_ONCE(ctx->async_notify))
+	if (!pending && ctx->async_notify)
 		complete(&ctx->async_wait.completion);
+	spin_unlock_bh(&ctx->decrypt_compl_lock);
 }
 
 static int tls_do_decryption(struct sock *sk,
@@ -464,10 +466,12 @@ static void tls_encrypt_done(struct crypto_async_request *req, int err)
 			ready = true;
 	}
 
+	spin_lock_bh(&ctx->encrypt_compl_lock);
 	pending = atomic_dec_return(&ctx->encrypt_pending);
 
-	if (!pending && READ_ONCE(ctx->async_notify))
+	if (!pending && ctx->async_notify)
 		complete(&ctx->async_wait.completion);
+	spin_unlock_bh(&ctx->encrypt_compl_lock);
 
 	if (!ready)
 		return;
@@ -923,6 +927,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 	int num_zc = 0;
 	int orig_size;
 	int ret = 0;
+	int pending;
 
 	if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL))
 		return -EOPNOTSUPP;
@@ -1089,13 +1094,19 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 		goto send_end;
 	} else if (num_zc) {
 		/* Wait for pending encryptions to get completed */
-		smp_store_mb(ctx->async_notify, true);
+		spin_lock_bh(&ctx->encrypt_compl_lock);
+		ctx->async_notify = true;
 
-		if (atomic_read(&ctx->encrypt_pending))
+		pending = atomic_read(&ctx->encrypt_pending);
+		spin_unlock_bh(&ctx->encrypt_compl_lock);
+		if (pending)
 			crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
 		else
 			reinit_completion(&ctx->async_wait.completion);
 
+		/* There can be no concurrent accesses, since we have no
+		 * pending encrypt operations
+		 */
 		WRITE_ONCE(ctx->async_notify, false);
 
 		if (ctx->async_wait.err) {
@@ -1724,6 +1735,7 @@ int tls_sw_recvmsg(struct sock *sk,
 	bool is_kvec = iov_iter_is_kvec(&msg->msg_iter);
 	bool is_peek = flags & MSG_PEEK;
 	int num_async = 0;
+	int pending;
 
 	flags |= nonblock;
 
@@ -1886,8 +1898,11 @@ int tls_sw_recvmsg(struct sock *sk,
 recv_end:
 	if (num_async) {
 		/* Wait for all previously submitted records to be decrypted */
-		smp_store_mb(ctx->async_notify, true);
-		if (atomic_read(&ctx->decrypt_pending)) {
+		spin_lock_bh(&ctx->decrypt_compl_lock);
+		ctx->async_notify = true;
+		pending = atomic_read(&ctx->decrypt_pending);
+		spin_unlock_bh(&ctx->decrypt_compl_lock);
+		if (pending) {
 			err = crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
 			if (err) {
 				/* one of async decrypt failed */
@@ -1899,6 +1914,10 @@ int tls_sw_recvmsg(struct sock *sk,
 		} else {
 			reinit_completion(&ctx->async_wait.completion);
 		}
+
+		/* There can be no concurrent accesses, since we have no
+		 * pending decrypt operations
+		 */
 		WRITE_ONCE(ctx->async_notify, false);
 
 		/* Drain records from the rx_list & copy if required */
@@ -2285,6 +2304,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 
 	if (tx) {
 		crypto_init_wait(&sw_ctx_tx->async_wait);
+		spin_lock_init(&sw_ctx_tx->encrypt_compl_lock);
 		crypto_info = &ctx->crypto_send.info;
 		cctx = &ctx->tx;
 		aead = &sw_ctx_tx->aead_send;
@@ -2293,6 +2313,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 		sw_ctx_tx->tx_work.sk = sk;
 	} else {
 		crypto_init_wait(&sw_ctx_rx->async_wait);
+		spin_lock_init(&sw_ctx_rx->decrypt_compl_lock);
 		crypto_info = &ctx->crypto_recv.info;
 		cctx = &ctx->rx;
 		skb_queue_head_init(&sw_ctx_rx->rx_list);
-- 
2.26.2


From 7e2b438d2467acca81383a00f44990be221afbac Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Sun, 17 May 2020 11:26:32 -0600
Subject: [PATCH 16/25] nexthop: Fix attribute checking for groups

[ Upstream commit 84be69b869a5a496a6cfde9b3c29509207a1f1fa ]

For nexthop groups, attributes after NHA_GROUP_TYPE are invalid, but
nh_check_attr_group starts checking at NHA_GROUP. The group type defaults
to multipath and the NHA_GROUP_TYPE is currently optional so this has
slipped through so far. Fix the attribute checking to handle support of
new group types.

Fixes: 430a049190de ("nexthop: Add support for nexthop groups")
Signed-off-by: ASSOGBA Emery <assogba.emery@gmail.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/nexthop.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index d2369297910b..4d1531c4780c 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -435,7 +435,7 @@ static int nh_check_attr_group(struct net *net, struct nlattr *tb[],
 		if (!valid_group_nh(nh, len, extack))
 			return -EINVAL;
 	}
-	for (i = NHA_GROUP + 1; i < __NHA_MAX; ++i) {
+	for (i = NHA_GROUP_TYPE + 1; i < __NHA_MAX; ++i) {
 		if (!tb[i])
 			continue;
 
-- 
2.26.2


From c52070a013c15f323ecbcf14a8a5bb5a787b9b4c Mon Sep 17 00:00:00 2001
From: Marc Payne <marc.payne@mdpsys.co.uk>
Date: Tue, 19 May 2020 19:01:46 +0100
Subject: [PATCH 17/25] r8152: support additional Microsoft Surface Ethernet
 Adapter variant

[ Upstream commit c27a204383616efba5a4194075e90819961ff66a ]

Device id 0927 is the RTL8153B-based component of the 'Surface USB-C to
Ethernet and USB Adapter' and may be used as a component of other devices
in future. Tested and working with the r8152 driver.

Update the cdc_ether blacklist due to the RTL8153 'network jam on suspend'
issue which this device will cause (personally confirmed).

Signed-off-by: Marc Payne <marc.payne@mdpsys.co.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ether.c | 11 +++++++++--
 drivers/net/usb/r8152.c     |  1 +
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index fe630438f67b..9bb37ac99a10 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -808,14 +808,21 @@ static const struct usb_device_id	products[] = {
 	.driver_info = 0,
 },
 
-/* Microsoft Surface 3 dock (based on Realtek RTL8153) */
+/* Microsoft Surface Ethernet Adapter (based on Realtek RTL8153) */
 {
 	USB_DEVICE_AND_INTERFACE_INFO(MICROSOFT_VENDOR_ID, 0x07c6, USB_CLASS_COMM,
 			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
 	.driver_info = 0,
 },
 
-	/* TP-LINK UE300 USB 3.0 Ethernet Adapters (based on Realtek RTL8153) */
+/* Microsoft Surface Ethernet Adapter (based on Realtek RTL8153B) */
+{
+	USB_DEVICE_AND_INTERFACE_INFO(MICROSOFT_VENDOR_ID, 0x0927, USB_CLASS_COMM,
+			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+	.driver_info = 0,
+},
+
+/* TP-LINK UE300 USB 3.0 Ethernet Adapters (based on Realtek RTL8153) */
 {
 	USB_DEVICE_AND_INTERFACE_INFO(TPLINK_VENDOR_ID, 0x0601, USB_CLASS_COMM,
 			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 44ea5dcc43fd..cd1a07175e11 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -5837,6 +5837,7 @@ static const struct usb_device_id rtl8152_table[] = {
 	{REALTEK_USB_DEVICE(VENDOR_ID_REALTEK, 0x8153)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07ab)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07c6)},
+	{REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x0927)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_SAMSUNG, 0xa101)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x304f)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x3062)},
-- 
2.26.2


From 9f985bc305a23d65542b1163fc8797604be22966 Mon Sep 17 00:00:00 2001
From: Neil Horman <nhorman@tuxdriver.com>
Date: Tue, 19 May 2020 16:04:05 -0400
Subject: [PATCH 18/25] sctp: Don't add the shutdown timer if its already been
 added

[ Upstream commit 20a785aa52c82246055a089e55df9dac47d67da1 ]

This BUG halt was reported a while back, but the patch somehow got
missed:

PID: 2879   TASK: c16adaa0  CPU: 1   COMMAND: "sctpn"
 #0 [f418dd28] crash_kexec at c04a7d8c
 #1 [f418dd7c] oops_end at c0863e02
 #2 [f418dd90] do_invalid_op at c040aaca
 #3 [f418de28] error_code (via invalid_op) at c08631a5
    EAX: f34baac0  EBX: 00000090  ECX: f418deb0  EDX: f5542950  EBP: 00000000
    DS:  007b      ESI: f34ba800  ES:  007b      EDI: f418dea0  GS:  00e0
    CS:  0060      EIP: c046fa5e  ERR: ffffffff  EFLAGS: 00010286
 #4 [f418de5c] add_timer at c046fa5e
 #5 [f418de68] sctp_do_sm at f8db8c77 [sctp]
 #6 [f418df30] sctp_primitive_SHUTDOWN at f8dcc1b5 [sctp]
 #7 [f418df48] inet_shutdown at c080baf9
 #8 [f418df5c] sys_shutdown at c079eedf
 #9 [f418df70] sys_socketcall at c079fe88
    EAX: ffffffda  EBX: 0000000d  ECX: bfceea90  EDX: 0937af98
    DS:  007b      ESI: 0000000c  ES:  007b      EDI: b7150ae4
    SS:  007b      ESP: bfceea7c  EBP: bfceeaa8  GS:  0033
    CS:  0073      EIP: b775c424  ERR: 00000066  EFLAGS: 00000282

It appears that the side effect that starts the shutdown timer was processed
multiple times, which can happen as multiple paths can trigger it.  This of
course leads to the BUG halt in add_timer getting called.

Fix seems pretty straightforward, just check before the timer is added if its
already been started.  If it has mod the timer instead to min(current
expiration, new expiration)

Its been tested but not confirmed to fix the problem, as the issue has only
occured in production environments where test kernels are enjoined from being
installed.  It appears to be a sane fix to me though.  Also, recentely,
Jere found a reproducer posted on list to confirm that this resolves the
issues

Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
CC: Vlad Yasevich <vyasevich@gmail.com>
CC: "David S. Miller" <davem@davemloft.net>
CC: jere.leppanen@nokia.com
CC: marcelo.leitner@gmail.com
CC: netdev@vger.kernel.org
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sm_sideeffect.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index b06cae508158..6927b658dad3 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -1522,9 +1522,17 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type,
 			timeout = asoc->timeouts[cmd->obj.to];
 			BUG_ON(!timeout);
 
-			timer->expires = jiffies + timeout;
-			sctp_association_hold(asoc);
-			add_timer(timer);
+			/*
+			 * SCTP has a hard time with timer starts.  Because we process
+			 * timer starts as side effects, it can be hard to tell if we
+			 * have already started a timer or not, which leads to BUG
+			 * halts when we call add_timer. So here, instead of just starting
+			 * a timer, if the timer is already started, and just mod
+			 * the timer with the shorter of the two expiration times
+			 */
+			if (!timer_pending(timer))
+				sctp_association_hold(asoc);
+			timer_reduce(timer, jiffies + timeout);
 			break;
 
 		case SCTP_CMD_TIMER_RESTART:
-- 
2.26.2


From 0c734b6007df2272a9009c5a47df6298234093cf Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jere=20Lepp=C3=A4nen?= <jere.leppanen@nokia.com>
Date: Wed, 20 May 2020 18:15:31 +0300
Subject: [PATCH 19/25] sctp: Start shutdown on association restart if in
 SHUTDOWN-SENT state and socket is closed
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit d3e8e4c11870413789f029a71e72ae6e971fe678 ]

Commit bdf6fa52f01b ("sctp: handle association restarts when the
socket is closed.") starts shutdown when an association is restarted,
if in SHUTDOWN-PENDING state and the socket is closed. However, the
rationale stated in that commit applies also when in SHUTDOWN-SENT
state - we don't want to move an association to ESTABLISHED state when
the socket has been closed, because that results in an association
that is unreachable from user space.

The problem scenario:

1.  Client crashes and/or restarts.

2.  Server (using one-to-one socket) calls close(). SHUTDOWN is lost.

3.  Client reconnects using the same addresses and ports.

4.  Server's association is restarted. The association and the socket
    move to ESTABLISHED state, even though the server process has
    closed its descriptor.

Also, after step 4 when the server process exits, some resources are
leaked in an attempt to release the underlying inet sock structure in
ESTABLISHED state:

    IPv4: Attempt to release TCP socket in state 1 00000000377288c7

Fix by acting the same way as in SHUTDOWN-PENDING state. That is, if
an association is restarted in SHUTDOWN-SENT state and the socket is
closed, then start shutdown and don't move the association or the
socket to ESTABLISHED state.

Fixes: bdf6fa52f01b ("sctp: handle association restarts when the socket is closed.")
Signed-off-by: Jere Leppänen <jere.leppanen@nokia.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sm_statefuns.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 5625a9500f21..84138a07e936 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -1856,12 +1856,13 @@ static enum sctp_disposition sctp_sf_do_dupcook_a(
 	/* Update the content of current association. */
 	sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc));
 	sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev));
-	if (sctp_state(asoc, SHUTDOWN_PENDING) &&
+	if ((sctp_state(asoc, SHUTDOWN_PENDING) ||
+	     sctp_state(asoc, SHUTDOWN_SENT)) &&
 	    (sctp_sstate(asoc->base.sk, CLOSING) ||
 	     sock_flag(asoc->base.sk, SOCK_DEAD))) {
-		/* if were currently in SHUTDOWN_PENDING, but the socket
-		 * has been closed by user, don't transition to ESTABLISHED.
-		 * Instead trigger SHUTDOWN bundled with COOKIE_ACK.
+		/* If the socket has been closed by user, don't
+		 * transition to ESTABLISHED. Instead trigger SHUTDOWN
+		 * bundled with COOKIE_ACK.
 		 */
 		sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl));
 		return sctp_sf_do_9_2_start_shutdown(net, ep, asoc,
-- 
2.26.2


From 5a3d220337ca3a093cd7a2caf436ecdc5fa6f120 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 21 May 2020 11:29:58 -0700
Subject: [PATCH 20/25] tipc: block BH before using dst_cache

[ Upstream commit 1378817486d6860f6a927f573491afe65287abf1 ]

dst_cache_get() documents it must be used with BH disabled.

sysbot reported :

BUG: using smp_processor_id() in preemptible [00000000] code: /21697
caller is dst_cache_get+0x3a/0xb0 net/core/dst_cache.c:68
CPU: 0 PID: 21697 Comm:  Not tainted 5.7.0-rc6-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x188/0x20d lib/dump_stack.c:118
 check_preemption_disabled lib/smp_processor_id.c:47 [inline]
 debug_smp_processor_id.cold+0x88/0x9b lib/smp_processor_id.c:57
 dst_cache_get+0x3a/0xb0 net/core/dst_cache.c:68
 tipc_udp_xmit.isra.0+0xb9/0xad0 net/tipc/udp_media.c:164
 tipc_udp_send_msg+0x3e6/0x490 net/tipc/udp_media.c:244
 tipc_bearer_xmit_skb+0x1de/0x3f0 net/tipc/bearer.c:526
 tipc_enable_bearer+0xb2f/0xd60 net/tipc/bearer.c:331
 __tipc_nl_bearer_enable+0x2bf/0x390 net/tipc/bearer.c:995
 tipc_nl_bearer_enable+0x1e/0x30 net/tipc/bearer.c:1003
 genl_family_rcv_msg_doit net/netlink/genetlink.c:673 [inline]
 genl_family_rcv_msg net/netlink/genetlink.c:718 [inline]
 genl_rcv_msg+0x627/0xdf0 net/netlink/genetlink.c:735
 netlink_rcv_skb+0x15a/0x410 net/netlink/af_netlink.c:2469
 genl_rcv+0x24/0x40 net/netlink/genetlink.c:746
 netlink_unicast_kernel net/netlink/af_netlink.c:1303 [inline]
 netlink_unicast+0x537/0x740 net/netlink/af_netlink.c:1329
 netlink_sendmsg+0x882/0xe10 net/netlink/af_netlink.c:1918
 sock_sendmsg_nosec net/socket.c:652 [inline]
 sock_sendmsg+0xcf/0x120 net/socket.c:672
 ____sys_sendmsg+0x6bf/0x7e0 net/socket.c:2362
 ___sys_sendmsg+0x100/0x170 net/socket.c:2416
 __sys_sendmsg+0xec/0x1b0 net/socket.c:2449
 do_syscall_64+0xf6/0x7d0 arch/x86/entry/common.c:295
 entry_SYSCALL_64_after_hwframe+0x49/0xb3
RIP: 0033:0x45ca29

Fixes: e9c1a793210f ("tipc: add dst_cache support for udp media")
Cc: Xin Long <lucien.xin@gmail.com>
Cc: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/udp_media.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index 186c78431217..8f0977a9d423 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -161,9 +161,11 @@ static int tipc_udp_xmit(struct net *net, struct sk_buff *skb,
 			 struct udp_bearer *ub, struct udp_media_addr *src,
 			 struct udp_media_addr *dst, struct dst_cache *cache)
 {
-	struct dst_entry *ndst = dst_cache_get(cache);
+	struct dst_entry *ndst;
 	int ttl, err = 0;
 
+	local_bh_disable();
+	ndst = dst_cache_get(cache);
 	if (dst->proto == htons(ETH_P_IP)) {
 		struct rtable *rt = (struct rtable *)ndst;
 
@@ -210,9 +212,11 @@ static int tipc_udp_xmit(struct net *net, struct sk_buff *skb,
 					   src->port, dst->port, false);
 #endif
 	}
+	local_bh_enable();
 	return err;
 
 tx_error:
+	local_bh_enable();
 	kfree_skb(skb);
 	return err;
 }
-- 
2.26.2


From 06e43a7389ab26b970ddc3955c4cceaa5262cab2 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Mon, 27 Apr 2020 16:56:59 +0300
Subject: [PATCH 21/25] net/mlx5e: kTLS, Destroy key object after destroying
 the TIS

[ Upstream commit 16736e11f43b80a38f98f6add54fab3b8c297df3 ]

The TLS TIS object contains the dek/key ID.
By destroying the key first, the TIS would contain an invalid
non-existing key ID.
Reverse the destroy order, this also acheives the desired assymetry
between the destroy and the create flows.

Fixes: d2ead1f360e8 ("net/mlx5e: Add kTLS TX HW offload support")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c
index 46725cd743a3..7d1985fa0d4f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c
@@ -69,8 +69,8 @@ static void mlx5e_ktls_del(struct net_device *netdev,
 	struct mlx5e_ktls_offload_context_tx *tx_priv =
 		mlx5e_get_ktls_tx_priv_ctx(tls_ctx);
 
-	mlx5_ktls_destroy_key(priv->mdev, tx_priv->key_id);
 	mlx5e_destroy_tis(priv->mdev, tx_priv->tisn);
+	mlx5_ktls_destroy_key(priv->mdev, tx_priv->key_id);
 	kvfree(tx_priv);
 }
 
-- 
2.26.2


From 93f4ef7f19b0ca6f663515718778bf694d765ce3 Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@mellanox.com>
Date: Thu, 30 Apr 2020 09:16:01 +0300
Subject: [PATCH 22/25] net/mlx5e: Fix inner tirs handling

[ Upstream commit a16b8e0dcf7043bee46174bed0553cc9e36b63a5 ]

In the cited commit inner_tirs argument was added to create and destroy
inner tirs, and no indication was added to mlx5e_modify_tirs_hash()
function. In order to have a consistent handling, use
inner_indir_tir[0].tirn in tirs destroy/modify function as an indication
to whether inner tirs are created.
Inner tirs are not created for representors and before this commit,
a call to mlx5e_modify_tirs_hash() was sending HW commands to
modify non-existent inner tirs.

Fixes: 46dc933cee82 ("net/mlx5e: Provide explicit directive if to create inner indirect tirs")
Signed-off-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h         |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c    | 12 +++++++-----
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c     |  4 ++--
 .../net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c    |  4 ++--
 4 files changed, 12 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 38aa55638bbe..98304c42e495 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -1103,7 +1103,7 @@ void mlx5e_close_drop_rq(struct mlx5e_rq *drop_rq);
 int mlx5e_create_indirect_rqt(struct mlx5e_priv *priv);
 
 int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc);
-void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc);
+void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv);
 
 int mlx5e_create_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs);
 void mlx5e_destroy_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 0e340893ca00..c133beb6a7a5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2758,7 +2758,8 @@ void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen)
 		mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in, inlen);
 	}
 
-	if (!mlx5e_tunnel_inner_ft_supported(priv->mdev))
+	/* Verify inner tirs resources allocated */
+	if (!priv->inner_indir_tir[0].tirn)
 		return;
 
 	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
@@ -3405,14 +3406,15 @@ int mlx5e_create_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs)
 	return err;
 }
 
-void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc)
+void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv)
 {
 	int i;
 
 	for (i = 0; i < MLX5E_NUM_INDIR_TIRS; i++)
 		mlx5e_destroy_tir(priv->mdev, &priv->indir_tir[i]);
 
-	if (!inner_ttc || !mlx5e_tunnel_inner_ft_supported(priv->mdev))
+	/* Verify inner tirs resources allocated */
+	if (!priv->inner_indir_tir[0].tirn)
 		return;
 
 	for (i = 0; i < MLX5E_NUM_INDIR_TIRS; i++)
@@ -5119,7 +5121,7 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv)
 err_destroy_direct_tirs:
 	mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
 err_destroy_indirect_tirs:
-	mlx5e_destroy_indirect_tirs(priv, true);
+	mlx5e_destroy_indirect_tirs(priv);
 err_destroy_direct_rqts:
 	mlx5e_destroy_direct_rqts(priv, priv->direct_tir);
 err_destroy_indirect_rqts:
@@ -5138,7 +5140,7 @@ static void mlx5e_cleanup_nic_rx(struct mlx5e_priv *priv)
 	mlx5e_destroy_direct_tirs(priv, priv->xsk_tir);
 	mlx5e_destroy_direct_rqts(priv, priv->xsk_tir);
 	mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
-	mlx5e_destroy_indirect_tirs(priv, true);
+	mlx5e_destroy_indirect_tirs(priv);
 	mlx5e_destroy_direct_rqts(priv, priv->direct_tir);
 	mlx5e_destroy_rqt(priv, &priv->indir_rqt);
 	mlx5e_close_drop_rq(&priv->drop_rq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index fddf644ba349..9b232ef36d53 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1597,7 +1597,7 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
 err_destroy_direct_tirs:
 	mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
 err_destroy_indirect_tirs:
-	mlx5e_destroy_indirect_tirs(priv, false);
+	mlx5e_destroy_indirect_tirs(priv);
 err_destroy_direct_rqts:
 	mlx5e_destroy_direct_rqts(priv, priv->direct_tir);
 err_destroy_indirect_rqts:
@@ -1614,7 +1614,7 @@ static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv)
 	mlx5_del_flow_rules(rpriv->vport_rx_rule);
 	mlx5e_destroy_ttc_table(priv, &priv->fs.ttc);
 	mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
-	mlx5e_destroy_indirect_tirs(priv, false);
+	mlx5e_destroy_indirect_tirs(priv);
 	mlx5e_destroy_direct_rqts(priv, priv->direct_tir);
 	mlx5e_destroy_rqt(priv, &priv->indir_rqt);
 	mlx5e_close_drop_rq(&priv->drop_rq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 3ed8ab2d703d..0fed2419623d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -396,7 +396,7 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv)
 err_destroy_direct_tirs:
 	mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
 err_destroy_indirect_tirs:
-	mlx5e_destroy_indirect_tirs(priv, true);
+	mlx5e_destroy_indirect_tirs(priv);
 err_destroy_direct_rqts:
 	mlx5e_destroy_direct_rqts(priv, priv->direct_tir);
 err_destroy_indirect_rqts:
@@ -412,7 +412,7 @@ static void mlx5i_cleanup_rx(struct mlx5e_priv *priv)
 {
 	mlx5i_destroy_flow_steering(priv);
 	mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
-	mlx5e_destroy_indirect_tirs(priv, true);
+	mlx5e_destroy_indirect_tirs(priv);
 	mlx5e_destroy_direct_rqts(priv, priv->direct_tir);
 	mlx5e_destroy_rqt(priv, &priv->indir_rqt);
 	mlx5e_close_drop_rq(&priv->drop_rq);
-- 
2.26.2


From 9eb4d50f0d1b676becc03d929d7a3388946aa324 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Wed, 29 Apr 2020 23:56:58 +0300
Subject: [PATCH 23/25] net/mlx5: Fix memory leak in mlx5_events_init

[ Upstream commit df14ad1eccb04a4a28c90389214dbacab085b244 ]

Fix memory leak in mlx5_events_init(), in case
create_single_thread_workqueue() fails, events
struct should be freed.

Fixes: 5d3c537f9070 ("net/mlx5: Handle event of power detection in the PCIE slot")
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/events.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c
index 8bcf3426b9c6..3ce17c3d7a00 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/events.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c
@@ -346,8 +346,10 @@ int mlx5_events_init(struct mlx5_core_dev *dev)
 	events->dev = dev;
 	dev->priv.events = events;
 	events->wq = create_singlethread_workqueue("mlx5_events");
-	if (!events->wq)
+	if (!events->wq) {
+		kfree(events);
 		return -ENOMEM;
+	}
 	INIT_WORK(&events->pcie_core_work, mlx5_pcie_event);
 
 	return 0;
-- 
2.26.2


From d101263a4b19c058273ecbc597e36747c25afb45 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Tue, 7 Apr 2020 17:38:28 +0300
Subject: [PATCH 24/25] net/mlx5e: Update netdev txq on completions during
 closure

[ Upstream commit 5e911e2c06bd8c17df29147a5e2d4b17fafda024 ]

On sq closure when we free its descriptors, we should also update netdev
txq on completions which would not arrive. Otherwise if we reopen sqs
and attach them back, for example on fw fatal recovery flow, we may get
tx timeout.

Fixes: 29429f3300a3 ("net/mlx5e: Timeout if SQ doesn't flush during close")
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index dee12f17f9c2..d9e0fc146741 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -537,10 +537,9 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq)
 {
 	struct mlx5e_tx_wqe_info *wi;
+	u32 dma_fifo_cc, nbytes = 0;
+	u16 ci, sqcc, npkts = 0;
 	struct sk_buff *skb;
-	u32 dma_fifo_cc;
-	u16 sqcc;
-	u16 ci;
 	int i;
 
 	sqcc = sq->cc;
@@ -565,11 +564,15 @@ void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq)
 		}
 
 		dev_kfree_skb_any(skb);
+		npkts++;
+		nbytes += wi->num_bytes;
 		sqcc += wi->num_wqebbs;
 	}
 
 	sq->dma_fifo_cc = dma_fifo_cc;
 	sq->cc = sqcc;
+
+	netdev_tx_completed_queue(sq->txq, npkts, nbytes);
 }
 
 #ifdef CONFIG_MLX5_CORE_IPOIB
-- 
2.26.2


From 5a8a2c9dca0069bec18330baa7ab261237c8bf0f Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@mellanox.com>
Date: Wed, 6 May 2020 14:52:04 +0300
Subject: [PATCH 25/25] net/mlx5: Fix error flow in case of function_setup
 failure

[ Upstream commit 4f7400d5cbaef676e00cdffb0565bf731c6bb09e ]

Currently, if an error occurred during mlx5_function_setup(), we
keep dev->state as DEVICE_STATE_UP.
Fixing it by adding a goto label.

Fixes: e161105e58da ("net/mlx5: Function setup/teardown procedures")
Signed-off-by: Shay Drory <shayd@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index c96a0e501007..7dcdda9ca351 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1183,7 +1183,7 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, bool boot)
 
 	err = mlx5_function_setup(dev, boot);
 	if (err)
-		goto out;
+		goto err_function;
 
 	if (boot) {
 		err = mlx5_init_once(dev);
@@ -1229,6 +1229,7 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, bool boot)
 		mlx5_cleanup_once(dev);
 function_teardown:
 	mlx5_function_teardown(dev, boot);
+err_function:
 	dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
 	mutex_unlock(&dev->intf_state_mutex);
 
-- 
2.26.2


[-- Attachment #3: net_56.mbox --]
[-- Type: Application/Octet-Stream, Size: 124417 bytes --]

From b09c8cccc1a4ab2064e532d90c104fc2a0f4a454 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 19 May 2020 18:24:43 -0700
Subject: [PATCH 01/33] ax25: fix setsockopt(SO_BINDTODEVICE)

[ Upstream commit 687775cec056b38a4c8f3291e0dd7a9145f7b667 ]

syzbot was able to trigger this trace [1], probably by using
a zero optlen.

While we are at it, cap optlen to IFNAMSIZ - 1 instead of IFNAMSIZ.

[1]
BUG: KMSAN: uninit-value in strnlen+0xf9/0x170 lib/string.c:569
CPU: 0 PID: 8807 Comm: syz-executor483 Not tainted 5.7.0-rc4-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c9/0x220 lib/dump_stack.c:118
 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:121
 __msan_warning+0x58/0xa0 mm/kmsan/kmsan_instr.c:215
 strnlen+0xf9/0x170 lib/string.c:569
 dev_name_hash net/core/dev.c:207 [inline]
 netdev_name_node_lookup net/core/dev.c:277 [inline]
 __dev_get_by_name+0x75/0x2b0 net/core/dev.c:778
 ax25_setsockopt+0xfa3/0x1170 net/ax25/af_ax25.c:654
 __compat_sys_setsockopt+0x4ed/0x910 net/compat.c:403
 __do_compat_sys_setsockopt net/compat.c:413 [inline]
 __se_compat_sys_setsockopt+0xdd/0x100 net/compat.c:410
 __ia32_compat_sys_setsockopt+0x62/0x80 net/compat.c:410
 do_syscall_32_irqs_on arch/x86/entry/common.c:339 [inline]
 do_fast_syscall_32+0x3bf/0x6d0 arch/x86/entry/common.c:398
 entry_SYSENTER_compat+0x68/0x77 arch/x86/entry/entry_64_compat.S:139
RIP: 0023:0xf7f57dd9
Code: 90 e8 0b 00 00 00 f3 90 0f ae e8 eb f9 8d 74 26 00 89 3c 24 c3 90 90 90 90 90 90 90 90 90 90 90 90 51 52 55 89 e5 0f 34 cd 80 <5d> 5a 59 c3 90 90 90 90 eb 0d 90 90 90 90 90 90 90 90 90 90 90 90
RSP: 002b:00000000ffae8c1c EFLAGS: 00000217 ORIG_RAX: 000000000000016e
RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000000101
RDX: 0000000000000019 RSI: 0000000020000000 RDI: 0000000000000004
RBP: 0000000000000012 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000

Local variable ----devname@ax25_setsockopt created at:
 ax25_setsockopt+0xe6/0x1170 net/ax25/af_ax25.c:536
 ax25_setsockopt+0xe6/0x1170 net/ax25/af_ax25.c:536

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ax25/af_ax25.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index ff57ea89c27e..fd91cd34f25e 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -635,8 +635,10 @@ static int ax25_setsockopt(struct socket *sock, int level, int optname,
 		break;
 
 	case SO_BINDTODEVICE:
-		if (optlen > IFNAMSIZ)
-			optlen = IFNAMSIZ;
+		if (optlen > IFNAMSIZ - 1)
+			optlen = IFNAMSIZ - 1;
+
+		memset(devname, 0, sizeof(devname));
 
 		if (copy_from_user(devname, optval, optlen)) {
 			res = -EFAULT;
-- 
2.26.2


From 3c27e235eb8a181d45d5b94b2f0cfb6a611c43ab Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Mon, 25 May 2020 00:22:51 +0300
Subject: [PATCH 02/33] dpaa_eth: fix usage as DSA master, try 3

[ Upstream commit 5d14c304bfc14b4fd052dc83d5224376b48f52f0 ]

The dpaa-eth driver probes on compatible string for the MAC node, and
the fman/mac.c driver allocates a dpaa-ethernet platform device that
triggers the probing of the dpaa-eth net device driver.

All of this is fine, but the problem is that the struct device of the
dpaa_eth net_device is 2 parents away from the MAC which can be
referenced via of_node. So of_find_net_device_by_node can't find it, and
DSA switches won't be able to probe on top of FMan ports.

It would be a bit silly to modify a core function
(of_find_net_device_by_node) to look for dev->parent->parent->of_node
just for one driver. We're just 1 step away from implementing full
recursion.

Actually there have already been at least 2 previous attempts to make
this work:
- Commit a1a50c8e4c24 ("fsl/man: Inherit parent device and of_node")
- One or more of the patches in "[v3,0/6] adapt DPAA drivers for DSA":
  https://patchwork.ozlabs.org/project/netdev/cover/1508178970-28945-1-git-send-email-madalin.bucur@nxp.com/
  (I couldn't really figure out which one was supposed to solve the
  problem and how).

Point being, it looks like this is still pretty much a problem today.
On T1040, the /sys/class/net/eth0 symlink currently points to

../../devices/platform/ffe000000.soc/ffe400000.fman/ffe4e6000.ethernet/dpaa-ethernet.0/net/eth0

which pretty much illustrates the problem. The closest of_node we've got
is the "fsl,fman-memac" at /soc@ffe000000/fman@400000/ethernet@e6000,
which is what we'd like to be able to reference from DSA as host port.

For of_find_net_device_by_node to find the eth0 port, we would need the
parent of the eth0 net_device to not be the "dpaa-ethernet" platform
device, but to point 1 level higher, aka the "fsl,fman-memac" node
directly. The new sysfs path would look like this:

../../devices/platform/ffe000000.soc/ffe400000.fman/ffe4e6000.ethernet/net/eth0

And this is exactly what SET_NETDEV_DEV does. It sets the parent of the
net_device. The new parent has an of_node associated with it, and
of_dev_node_match already checks for the of_node of the device or of its
parent.

Fixes: a1a50c8e4c24 ("fsl/man: Inherit parent device and of_node")
Fixes: c6e26ea8c893 ("dpaa_eth: change device used")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index ca74a684a904..ab337632793b 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -2902,7 +2902,7 @@ static int dpaa_eth_probe(struct platform_device *pdev)
 	}
 
 	/* Do this here, so we can be verbose early */
-	SET_NETDEV_DEV(net_dev, dev);
+	SET_NETDEV_DEV(net_dev, dev->parent);
 	dev_set_drvdata(dev, net_dev);
 
 	priv = netdev_priv(net_dev);
-- 
2.26.2


From 8269b58d04daf4ae4f5a8e27096b6aa64f67b172 Mon Sep 17 00:00:00 2001
From: Michal Kubecek <mkubecek@suse.cz>
Date: Sun, 10 May 2020 21:04:09 +0200
Subject: [PATCH 03/33] ethtool: count header size in reply size estimate

[ Upstream commit 7c87e32d2e380228ada79d20ac5b7674718ef097 ]

As ethnl_request_ops::reply_size handlers do not include common header
size into calculated/estimated reply size, it needs to be added in
ethnl_default_doit() and ethnl_default_notify() before allocating the
message. On the other hand, strset_reply_size() should not add common
header size.

Fixes: 728480f12442 ("ethtool: default handlers for GET requests")
Reported-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ethtool/netlink.c | 4 ++--
 net/ethtool/strset.c  | 1 -
 2 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index fc9e0b806889..d863dffbe53c 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -334,7 +334,7 @@ static int ethnl_default_doit(struct sk_buff *skb, struct genl_info *info)
 	ret = ops->reply_size(req_info, reply_data);
 	if (ret < 0)
 		goto err_cleanup;
-	reply_len = ret;
+	reply_len = ret + ethnl_reply_header_size();
 	ret = -ENOMEM;
 	rskb = ethnl_reply_init(reply_len, req_info->dev, ops->reply_cmd,
 				ops->hdr_attr, info, &reply_payload);
@@ -573,7 +573,7 @@ static void ethnl_default_notify(struct net_device *dev, unsigned int cmd,
 	ret = ops->reply_size(req_info, reply_data);
 	if (ret < 0)
 		goto err_cleanup;
-	reply_len = ret;
+	reply_len = ret + ethnl_reply_header_size();
 	ret = -ENOMEM;
 	skb = genlmsg_new(reply_len, GFP_KERNEL);
 	if (!skb)
diff --git a/net/ethtool/strset.c b/net/ethtool/strset.c
index 8e5911887b4c..fb7b3585458d 100644
--- a/net/ethtool/strset.c
+++ b/net/ethtool/strset.c
@@ -309,7 +309,6 @@ static int strset_reply_size(const struct ethnl_req_info *req_base,
 	int len = 0;
 	int ret;
 
-	len += ethnl_reply_header_size();
 	for (i = 0; i < ETH_SS_COUNT; i++) {
 		const struct strset_info *set_info = &data->sets[i];
 
-- 
2.26.2


From 5ea332ce05b20a0c80710d5ba5b2a73f8913a6f6 Mon Sep 17 00:00:00 2001
From: Claudiu Manoil <claudiu.manoil@nxp.com>
Date: Fri, 22 May 2020 11:54:34 +0300
Subject: [PATCH 04/33] felix: Fix initialization of ioremap resources

[ Upstream commit b4024c9e5c57902155d3b5e7de482e245f492bff ]

The caller of devm_ioremap_resource(), either accidentally
or by wrong assumption, is writing back derived resource data
to global static resource initialization tables that should
have been constant.  Meaning that after it computes the final
physical start address it saves the address for no reason
in the static tables.  This doesn't affect the first driver
probing after reboot, but it breaks consecutive driver reloads
(i.e. driver unbind & bind) because the initialization tables
no longer have the correct initial values.  So the next probe()
will map the device registers to wrong physical addresses,
causing ARM SError async exceptions.
This patch fixes all of the above.

Fixes: 56051948773e ("net: dsa: ocelot: add driver for Felix switch family")
Signed-off-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Tested-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/ocelot/felix.c         | 23 +++++++++++------------
 drivers/net/dsa/ocelot/felix.h         |  6 +++---
 drivers/net/dsa/ocelot/felix_vsc9959.c | 22 ++++++++++------------
 3 files changed, 24 insertions(+), 27 deletions(-)

diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index a7780c06fa65..b74580e87be8 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -385,6 +385,7 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports)
 	struct ocelot *ocelot = &felix->ocelot;
 	phy_interface_t *port_phy_modes;
 	resource_size_t switch_base;
+	struct resource res;
 	int port, i, err;
 
 	ocelot->num_phys_ports = num_phys_ports;
@@ -416,17 +417,16 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports)
 
 	for (i = 0; i < TARGET_MAX; i++) {
 		struct regmap *target;
-		struct resource *res;
 
 		if (!felix->info->target_io_res[i].name)
 			continue;
 
-		res = &felix->info->target_io_res[i];
-		res->flags = IORESOURCE_MEM;
-		res->start += switch_base;
-		res->end += switch_base;
+		memcpy(&res, &felix->info->target_io_res[i], sizeof(res));
+		res.flags = IORESOURCE_MEM;
+		res.start += switch_base;
+		res.end += switch_base;
 
-		target = ocelot_regmap_init(ocelot, res);
+		target = ocelot_regmap_init(ocelot, &res);
 		if (IS_ERR(target)) {
 			dev_err(ocelot->dev,
 				"Failed to map device memory space\n");
@@ -447,7 +447,6 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports)
 	for (port = 0; port < num_phys_ports; port++) {
 		struct ocelot_port *ocelot_port;
 		void __iomem *port_regs;
-		struct resource *res;
 
 		ocelot_port = devm_kzalloc(ocelot->dev,
 					   sizeof(struct ocelot_port),
@@ -459,12 +458,12 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports)
 			return -ENOMEM;
 		}
 
-		res = &felix->info->port_io_res[port];
-		res->flags = IORESOURCE_MEM;
-		res->start += switch_base;
-		res->end += switch_base;
+		memcpy(&res, &felix->info->port_io_res[port], sizeof(res));
+		res.flags = IORESOURCE_MEM;
+		res.start += switch_base;
+		res.end += switch_base;
 
-		port_regs = devm_ioremap_resource(ocelot->dev, res);
+		port_regs = devm_ioremap_resource(ocelot->dev, &res);
 		if (IS_ERR(port_regs)) {
 			dev_err(ocelot->dev,
 				"failed to map registers for port %d\n", port);
diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h
index 8771d40324f1..2c024cc901d4 100644
--- a/drivers/net/dsa/ocelot/felix.h
+++ b/drivers/net/dsa/ocelot/felix.h
@@ -8,9 +8,9 @@
 
 /* Platform-specific information */
 struct felix_info {
-	struct resource			*target_io_res;
-	struct resource			*port_io_res;
-	struct resource			*imdio_res;
+	const struct resource		*target_io_res;
+	const struct resource		*port_io_res;
+	const struct resource		*imdio_res;
 	const struct reg_field		*regfields;
 	const u32 *const		*map;
 	const struct ocelot_ops		*ops;
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index edc1a67c002b..50074da3a1a0 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -328,10 +328,8 @@ static const u32 *vsc9959_regmap[] = {
 	[GCB]	= vsc9959_gcb_regmap,
 };
 
-/* Addresses are relative to the PCI device's base address and
- * will be fixed up at ioremap time.
- */
-static struct resource vsc9959_target_io_res[] = {
+/* Addresses are relative to the PCI device's base address */
+static const struct resource vsc9959_target_io_res[] = {
 	[ANA] = {
 		.start	= 0x0280000,
 		.end	= 0x028ffff,
@@ -374,7 +372,7 @@ static struct resource vsc9959_target_io_res[] = {
 	},
 };
 
-static struct resource vsc9959_port_io_res[] = {
+static const struct resource vsc9959_port_io_res[] = {
 	{
 		.start	= 0x0100000,
 		.end	= 0x010ffff,
@@ -410,7 +408,7 @@ static struct resource vsc9959_port_io_res[] = {
 /* Port MAC 0 Internal MDIO bus through which the SerDes acting as an
  * SGMII/QSGMII MAC PCS can be found.
  */
-static struct resource vsc9959_imdio_res = {
+static const struct resource vsc9959_imdio_res = {
 	.start		= 0x8030,
 	.end		= 0x8040,
 	.name		= "imdio",
@@ -984,7 +982,7 @@ static int vsc9959_mdio_bus_alloc(struct ocelot *ocelot)
 	struct device *dev = ocelot->dev;
 	resource_size_t imdio_base;
 	void __iomem *imdio_regs;
-	struct resource *res;
+	struct resource res;
 	struct enetc_hw *hw;
 	struct mii_bus *bus;
 	int port;
@@ -1001,12 +999,12 @@ static int vsc9959_mdio_bus_alloc(struct ocelot *ocelot)
 	imdio_base = pci_resource_start(felix->pdev,
 					felix->info->imdio_pci_bar);
 
-	res = felix->info->imdio_res;
-	res->flags = IORESOURCE_MEM;
-	res->start += imdio_base;
-	res->end += imdio_base;
+	memcpy(&res, felix->info->imdio_res, sizeof(res));
+	res.flags = IORESOURCE_MEM;
+	res.start += imdio_base;
+	res.end += imdio_base;
 
-	imdio_regs = devm_ioremap_resource(dev, res);
+	imdio_regs = devm_ioremap_resource(dev, &res);
 	if (IS_ERR(imdio_regs)) {
 		dev_err(dev, "failed to map internal MDIO registers\n");
 		return PTR_ERR(imdio_regs);
-- 
2.26.2


From 9cc49797c789d88917ac552244a8adb684fa8770 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Wed, 20 May 2020 11:15:46 +0200
Subject: [PATCH 05/33] net: don't return invalid table id error when we fall
 back to PF_UNSPEC

[ Upstream commit 41b4bd986f86331efc599b9a3f5fb86ad92e9af9 ]

In case we can't find a ->dumpit callback for the requested
(family,type) pair, we fall back to (PF_UNSPEC,type). In effect, we're
in the same situation as if userspace had requested a PF_UNSPEC
dump. For RTM_GETROUTE, that handler is rtnl_dump_all, which calls all
the registered RTM_GETROUTE handlers.

The requested table id may or may not exist for all of those
families. commit ae677bbb4441 ("net: Don't return invalid table id
error when dumping all families") fixed the problem when userspace
explicitly requests a PF_UNSPEC dump, but missed the fallback case.

For example, when we pass ipv6.disable=1 to a kernel with
CONFIG_IP_MROUTE=y and CONFIG_IP_MROUTE_MULTIPLE_TABLES=y,
the (PF_INET6, RTM_GETROUTE) handler isn't registered, so we end up in
rtnl_dump_all, and listing IPv6 routes will unexpectedly print:

  # ip -6 r
  Error: ipv4: MR table does not exist.
  Dump terminated

commit ae677bbb4441 introduced the dump_all_families variable, which
gets set when userspace requests a PF_UNSPEC dump. However, we can't
simply set the family to PF_UNSPEC in rtnetlink_rcv_msg in the
fallback case to get dump_all_families == true, because some messages
types (for example RTM_GETRULE and RTM_GETNEIGH) only register the
PF_UNSPEC handler and use the family to filter in the kernel what is
dumped to userspace. We would then export more entries, that userspace
would have to filter. iproute does that, but other programs may not.

Instead, this patch removes dump_all_families and updates the
RTM_GETROUTE handlers to check if the family that is being dumped is
their own. When it's not, which covers both the intentional PF_UNSPEC
dumps (as dump_all_families did) and the fallback case, ignore the
missing table id error.

Fixes: cb167893f41e ("net: Plumb support for filtering ipv4 and ipv6 multicast route dumps")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_fib.h    | 1 -
 net/ipv4/fib_frontend.c | 3 +--
 net/ipv4/ipmr.c         | 2 +-
 net/ipv6/ip6_fib.c      | 2 +-
 net/ipv6/ip6mr.c        | 2 +-
 5 files changed, 4 insertions(+), 6 deletions(-)

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 6a1ae49809de..a89c0885fd2a 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -257,7 +257,6 @@ struct fib_dump_filter {
 	u32			table_id;
 	/* filter_set is an optimization that an entry is set */
 	bool			filter_set;
-	bool			dump_all_families;
 	bool			dump_routes;
 	bool			dump_exceptions;
 	unsigned char		protocol;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 213be9c050ad..1bf9da3a75f9 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -918,7 +918,6 @@ int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh,
 	else
 		filter->dump_exceptions = false;
 
-	filter->dump_all_families = (rtm->rtm_family == AF_UNSPEC);
 	filter->flags    = rtm->rtm_flags;
 	filter->protocol = rtm->rtm_protocol;
 	filter->rt_type  = rtm->rtm_type;
@@ -990,7 +989,7 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 	if (filter.table_id) {
 		tb = fib_get_table(net, filter.table_id);
 		if (!tb) {
-			if (filter.dump_all_families)
+			if (rtnl_msg_family(cb->nlh) != PF_INET)
 				return skb->len;
 
 			NL_SET_ERR_MSG(cb->extack, "ipv4: FIB table does not exist");
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 6e68def66822..2508b4c37af3 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2611,7 +2611,7 @@ static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
 
 		mrt = ipmr_get_table(sock_net(skb->sk), filter.table_id);
 		if (!mrt) {
-			if (filter.dump_all_families)
+			if (rtnl_msg_family(cb->nlh) != RTNL_FAMILY_IPMR)
 				return skb->len;
 
 			NL_SET_ERR_MSG(cb->extack, "ipv4: MR table does not exist");
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 72abf892302f..9a53590ef79c 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -664,7 +664,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 	if (arg.filter.table_id) {
 		tb = fib6_get_table(net, arg.filter.table_id);
 		if (!tb) {
-			if (arg.filter.dump_all_families)
+			if (rtnl_msg_family(cb->nlh) != PF_INET6)
 				goto out;
 
 			NL_SET_ERR_MSG_MOD(cb->extack, "FIB table does not exist");
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index bfa49ff70531..2ddb7c513e54 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -2501,7 +2501,7 @@ static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
 
 		mrt = ip6mr_get_table(sock_net(skb->sk), filter.table_id);
 		if (!mrt) {
-			if (filter.dump_all_families)
+			if (rtnl_msg_family(cb->nlh) != RTNL_FAMILY_IP6MR)
 				return skb->len;
 
 			NL_SET_ERR_MSG_MOD(cb->extack, "MR table does not exist");
-- 
2.26.2


From 398698a14a9a37d088abd36908959ba8fe7e5e80 Mon Sep 17 00:00:00 2001
From: DENG Qingfang <dqfext@gmail.com>
Date: Wed, 13 May 2020 23:10:16 +0800
Subject: [PATCH 06/33] net: dsa: mt7530: fix roaming from DSA user ports

[ Upstream commit 5e5502e012b8129e11be616acb0f9c34bc8f8adb ]

When a client moves from a DSA user port to a software port in a bridge,
it cannot reach any other clients that connected to the DSA user ports.
That is because SA learning on the CPU port is disabled, so the switch
ignores the client's frames from the CPU port and still thinks it is at
the user port.

Fix it by enabling SA learning on the CPU port.

To prevent the switch from learning from flooding frames from the CPU
port, set skb->offload_fwd_mark to 1 for unicast and broadcast frames,
and let the switch flood them instead of trapping to the CPU port.
Multicast frames still need to be trapped to the CPU port for snooping,
so set the SA_DIS bit of the MTK tag to 1 when transmitting those frames
to disable SA learning.

Fixes: b8f126a8d543 ("net-next: dsa: add dsa support for Mediatek MT7530 switch")
Signed-off-by: DENG Qingfang <dqfext@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mt7530.c |  9 ++-------
 drivers/net/dsa/mt7530.h |  1 +
 net/dsa/tag_mtk.c        | 15 +++++++++++++++
 3 files changed, 18 insertions(+), 7 deletions(-)

diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index 0123498242b9..b95425a63a13 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -639,11 +639,8 @@ mt7530_cpu_port_enable(struct mt7530_priv *priv,
 	mt7530_write(priv, MT7530_PVC_P(port),
 		     PORT_SPEC_TAG);
 
-	/* Disable auto learning on the cpu port */
-	mt7530_set(priv, MT7530_PSC_P(port), SA_DIS);
-
-	/* Unknown unicast frame fordwarding to the cpu port */
-	mt7530_set(priv, MT7530_MFC, UNU_FFP(BIT(port)));
+	/* Unknown multicast frame forwarding to the cpu port */
+	mt7530_rmw(priv, MT7530_MFC, UNM_FFP_MASK, UNM_FFP(BIT(port)));
 
 	/* Set CPU port number */
 	if (priv->id == ID_MT7621)
@@ -1247,8 +1244,6 @@ mt7530_setup(struct dsa_switch *ds)
 	/* Enable and reset MIB counters */
 	mt7530_mib_reset(ds);
 
-	mt7530_clear(priv, MT7530_MFC, UNU_FFP_MASK);
-
 	for (i = 0; i < MT7530_NUM_PORTS; i++) {
 		/* Disable forwarding by default on all ports */
 		mt7530_rmw(priv, MT7530_PCR_P(i), PCR_MATRIX_MASK,
diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h
index 756140b7dfd5..0e7e36d8f994 100644
--- a/drivers/net/dsa/mt7530.h
+++ b/drivers/net/dsa/mt7530.h
@@ -31,6 +31,7 @@ enum {
 #define MT7530_MFC			0x10
 #define  BC_FFP(x)			(((x) & 0xff) << 24)
 #define  UNM_FFP(x)			(((x) & 0xff) << 16)
+#define  UNM_FFP_MASK			UNM_FFP(~0)
 #define  UNU_FFP(x)			(((x) & 0xff) << 8)
 #define  UNU_FFP_MASK			UNU_FFP(~0)
 #define  CPU_EN				BIT(7)
diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c
index b5705cba8318..d6619edd53e5 100644
--- a/net/dsa/tag_mtk.c
+++ b/net/dsa/tag_mtk.c
@@ -15,6 +15,7 @@
 #define MTK_HDR_XMIT_TAGGED_TPID_8100	1
 #define MTK_HDR_RECV_SOURCE_PORT_MASK	GENMASK(2, 0)
 #define MTK_HDR_XMIT_DP_BIT_MASK	GENMASK(5, 0)
+#define MTK_HDR_XMIT_SA_DIS		BIT(6)
 
 static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb,
 				    struct net_device *dev)
@@ -22,6 +23,9 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb,
 	struct dsa_port *dp = dsa_slave_to_port(dev);
 	u8 *mtk_tag;
 	bool is_vlan_skb = true;
+	unsigned char *dest = eth_hdr(skb)->h_dest;
+	bool is_multicast_skb = is_multicast_ether_addr(dest) &&
+				!is_broadcast_ether_addr(dest);
 
 	/* Build the special tag after the MAC Source Address. If VLAN header
 	 * is present, it's required that VLAN header and special tag is
@@ -47,6 +51,10 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb,
 		     MTK_HDR_XMIT_UNTAGGED;
 	mtk_tag[1] = (1 << dp->index) & MTK_HDR_XMIT_DP_BIT_MASK;
 
+	/* Disable SA learning for multicast frames */
+	if (unlikely(is_multicast_skb))
+		mtk_tag[1] |= MTK_HDR_XMIT_SA_DIS;
+
 	/* Tag control information is kept for 802.1Q */
 	if (!is_vlan_skb) {
 		mtk_tag[2] = 0;
@@ -61,6 +69,9 @@ static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev,
 {
 	int port;
 	__be16 *phdr, hdr;
+	unsigned char *dest = eth_hdr(skb)->h_dest;
+	bool is_multicast_skb = is_multicast_ether_addr(dest) &&
+				!is_broadcast_ether_addr(dest);
 
 	if (unlikely(!pskb_may_pull(skb, MTK_HDR_LEN)))
 		return NULL;
@@ -86,6 +97,10 @@ static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev,
 	if (!skb->dev)
 		return NULL;
 
+	/* Only unicast or broadcast frames are offloaded */
+	if (likely(!is_multicast_skb))
+		skb->offload_fwd_mark = 1;
+
 	return skb;
 }
 
-- 
2.26.2


From ed89fc7509a4eb91bfdc400af346633bf6c97f85 Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Fri, 22 May 2020 20:09:28 +0300
Subject: [PATCH 07/33] net: ethernet: ti: cpsw: fix ASSERT_RTNL() warning
 during suspend

[ Upstream commit 4c64b83d03f4aafcdf710caad994cbc855802e74 ]

vlan_for_each() are required to be called with rtnl_lock taken, otherwise
ASSERT_RTNL() warning will be triggered - which happens now during System
resume from suspend:
  cpsw_suspend()
  |- cpsw_ndo_stop()
    |- __hw_addr_ref_unsync_dev()
      |- cpsw_purge_all_mc()
         |- vlan_for_each()
            |- ASSERT_RTNL();

Hence, fix it by surrounding cpsw_ndo_stop() by rtnl_lock/unlock() calls.

Fixes: 15180eca569b ("net: ethernet: ti: cpsw: fix vlan mcast")
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 6ae4a72e6f43..5577ff0b7663 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -1752,11 +1752,15 @@ static int cpsw_suspend(struct device *dev)
 	struct cpsw_common *cpsw = dev_get_drvdata(dev);
 	int i;
 
+	rtnl_lock();
+
 	for (i = 0; i < cpsw->data.slaves; i++)
 		if (cpsw->slaves[i].ndev)
 			if (netif_running(cpsw->slaves[i].ndev))
 				cpsw_ndo_stop(cpsw->slaves[i].ndev);
 
+	rtnl_unlock();
+
 	/* Select sleep pin state */
 	pinctrl_pm_select_sleep_state(dev);
 
-- 
2.26.2


From ade62ac8919bd437d5e719c8d429f1c7d298d58c Mon Sep 17 00:00:00 2001
From: Boris Sukholitko <boris.sukholitko@broadcom.com>
Date: Tue, 19 May 2020 10:32:37 +0300
Subject: [PATCH 08/33] __netif_receive_skb_core: pass skb by reference

[ Upstream commit c0bbbdc32febd4f034ecbf3ea17865785b2c0652 ]

__netif_receive_skb_core may change the skb pointer passed into it (e.g.
in rx_handler). The original skb may be freed as a result of this
operation.

The callers of __netif_receive_skb_core may further process original skb
by using pt_prev pointer returned by __netif_receive_skb_core thus
leading to unpleasant effects.

The solution is to pass skb by reference into __netif_receive_skb_core.

v2: Added Fixes tag and comment regarding ppt_prev and skb invariant.

Fixes: 88eb1944e18c ("net: core: propagate SKB lists through packet_type lookup")
Signed-off-by: Boris Sukholitko <boris.sukholitko@broadcom.com>
Acked-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index c7047b40f569..87fd5424e205 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4988,11 +4988,12 @@ static inline int nf_ingress(struct sk_buff *skb, struct packet_type **pt_prev,
 	return 0;
 }
 
-static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc,
+static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc,
 				    struct packet_type **ppt_prev)
 {
 	struct packet_type *ptype, *pt_prev;
 	rx_handler_func_t *rx_handler;
+	struct sk_buff *skb = *pskb;
 	struct net_device *orig_dev;
 	bool deliver_exact = false;
 	int ret = NET_RX_DROP;
@@ -5023,8 +5024,10 @@ static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc,
 		ret2 = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog), skb);
 		preempt_enable();
 
-		if (ret2 != XDP_PASS)
-			return NET_RX_DROP;
+		if (ret2 != XDP_PASS) {
+			ret = NET_RX_DROP;
+			goto out;
+		}
 		skb_reset_mac_len(skb);
 	}
 
@@ -5174,6 +5177,13 @@ static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc,
 	}
 
 out:
+	/* The invariant here is that if *ppt_prev is not NULL
+	 * then skb should also be non-NULL.
+	 *
+	 * Apparently *ppt_prev assignment above holds this invariant due to
+	 * skb dereferencing near it.
+	 */
+	*pskb = skb;
 	return ret;
 }
 
@@ -5183,7 +5193,7 @@ static int __netif_receive_skb_one_core(struct sk_buff *skb, bool pfmemalloc)
 	struct packet_type *pt_prev = NULL;
 	int ret;
 
-	ret = __netif_receive_skb_core(skb, pfmemalloc, &pt_prev);
+	ret = __netif_receive_skb_core(&skb, pfmemalloc, &pt_prev);
 	if (pt_prev)
 		ret = INDIRECT_CALL_INET(pt_prev->func, ipv6_rcv, ip_rcv, skb,
 					 skb->dev, pt_prev, orig_dev);
@@ -5261,7 +5271,7 @@ static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemallo
 		struct packet_type *pt_prev = NULL;
 
 		skb_list_del_init(skb);
-		__netif_receive_skb_core(skb, pfmemalloc, &pt_prev);
+		__netif_receive_skb_core(&skb, pfmemalloc, &pt_prev);
 		if (!pt_prev)
 			continue;
 		if (pt_curr != pt_prev || od_curr != orig_dev) {
-- 
2.26.2


From 9e200f297336888ee89e8513d21d88e848fedbb8 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Mon, 18 May 2020 17:13:34 -0700
Subject: [PATCH 09/33] net: inet_csk: Fix so_reuseport bind-address cache in
 tb->fast*

[ Upstream commit 88d7fcfa3b1fe670f0412b95be785aafca63352b ]

The commit 637bc8bbe6c0 ("inet: reset tb->fastreuseport when adding a reuseport sk")
added a bind-address cache in tb->fast*.  The tb->fast* caches the address
of a sk which has successfully been binded with SO_REUSEPORT ON.  The idea
is to avoid the expensive conflict search in inet_csk_bind_conflict().

There is an issue with wildcard matching where sk_reuseport_match() should
have returned false but it is currently returning true.  It ends up
hiding bind conflict.  For example,

bind("[::1]:443"); /* without SO_REUSEPORT. Succeed. */
bind("[::2]:443"); /* with    SO_REUSEPORT. Succeed. */
bind("[::]:443");  /* with    SO_REUSEPORT. Still Succeed where it shouldn't */

The last bind("[::]:443") with SO_REUSEPORT on should have failed because
it should have a conflict with the very first bind("[::1]:443") which
has SO_REUSEPORT off.  However, the address "[::2]" is cached in
tb->fast* in the second bind. In the last bind, the sk_reuseport_match()
returns true because the binding sk's wildcard addr "[::]" matches with
the "[::2]" cached in tb->fast*.

The correct bind conflict is reported by removing the second
bind such that tb->fast* cache is not involved and forces the
bind("[::]:443") to go through the inet_csk_bind_conflict():

bind("[::1]:443"); /* without SO_REUSEPORT. Succeed. */
bind("[::]:443");  /* with    SO_REUSEPORT. -EADDRINUSE */

The expected behavior for sk_reuseport_match() is, it should only allow
the "cached" tb->fast* address to be used as a wildcard match but not
the address of the binding sk.  To do that, the current
"bool match_wildcard" arg is split into
"bool match_sk1_wildcard" and "bool match_sk2_wildcard".

This change only affects the sk_reuseport_match() which is only
used by inet_csk (e.g. TCP).
The other use cases are calling inet_rcv_saddr_equal() and
this patch makes it pass the same "match_wildcard" arg twice to
the "ipv[46]_rcv_saddr_equal(..., match_wildcard, match_wildcard)".

Cc: Josef Bacik <jbacik@fb.com>
Fixes: 637bc8bbe6c0 ("inet: reset tb->fastreuseport when adding a reuseport sk")
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/inet_connection_sock.c | 43 ++++++++++++++++++---------------
 1 file changed, 24 insertions(+), 19 deletions(-)

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index d545fb99a8a1..76afe93904d5 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -24,17 +24,19 @@
 #include <net/addrconf.h>
 
 #if IS_ENABLED(CONFIG_IPV6)
-/* match_wildcard == true:  IPV6_ADDR_ANY equals to any IPv6 addresses if IPv6
- *                          only, and any IPv4 addresses if not IPv6 only
- * match_wildcard == false: addresses must be exactly the same, i.e.
- *                          IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY,
- *                          and 0.0.0.0 equals to 0.0.0.0 only
+/* match_sk*_wildcard == true:  IPV6_ADDR_ANY equals to any IPv6 addresses
+ *				if IPv6 only, and any IPv4 addresses
+ *				if not IPv6 only
+ * match_sk*_wildcard == false: addresses must be exactly the same, i.e.
+ *				IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY,
+ *				and 0.0.0.0 equals to 0.0.0.0 only
  */
 static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
 				 const struct in6_addr *sk2_rcv_saddr6,
 				 __be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
 				 bool sk1_ipv6only, bool sk2_ipv6only,
-				 bool match_wildcard)
+				 bool match_sk1_wildcard,
+				 bool match_sk2_wildcard)
 {
 	int addr_type = ipv6_addr_type(sk1_rcv_saddr6);
 	int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED;
@@ -44,8 +46,8 @@ static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
 		if (!sk2_ipv6only) {
 			if (sk1_rcv_saddr == sk2_rcv_saddr)
 				return true;
-			if (!sk1_rcv_saddr || !sk2_rcv_saddr)
-				return match_wildcard;
+			return (match_sk1_wildcard && !sk1_rcv_saddr) ||
+				(match_sk2_wildcard && !sk2_rcv_saddr);
 		}
 		return false;
 	}
@@ -53,11 +55,11 @@ static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
 	if (addr_type == IPV6_ADDR_ANY && addr_type2 == IPV6_ADDR_ANY)
 		return true;
 
-	if (addr_type2 == IPV6_ADDR_ANY && match_wildcard &&
+	if (addr_type2 == IPV6_ADDR_ANY && match_sk2_wildcard &&
 	    !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED))
 		return true;
 
-	if (addr_type == IPV6_ADDR_ANY && match_wildcard &&
+	if (addr_type == IPV6_ADDR_ANY && match_sk1_wildcard &&
 	    !(sk1_ipv6only && addr_type2 == IPV6_ADDR_MAPPED))
 		return true;
 
@@ -69,18 +71,19 @@ static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
 }
 #endif
 
-/* match_wildcard == true:  0.0.0.0 equals to any IPv4 addresses
- * match_wildcard == false: addresses must be exactly the same, i.e.
- *                          0.0.0.0 only equals to 0.0.0.0
+/* match_sk*_wildcard == true:  0.0.0.0 equals to any IPv4 addresses
+ * match_sk*_wildcard == false: addresses must be exactly the same, i.e.
+ *				0.0.0.0 only equals to 0.0.0.0
  */
 static bool ipv4_rcv_saddr_equal(__be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
-				 bool sk2_ipv6only, bool match_wildcard)
+				 bool sk2_ipv6only, bool match_sk1_wildcard,
+				 bool match_sk2_wildcard)
 {
 	if (!sk2_ipv6only) {
 		if (sk1_rcv_saddr == sk2_rcv_saddr)
 			return true;
-		if (!sk1_rcv_saddr || !sk2_rcv_saddr)
-			return match_wildcard;
+		return (match_sk1_wildcard && !sk1_rcv_saddr) ||
+			(match_sk2_wildcard && !sk2_rcv_saddr);
 	}
 	return false;
 }
@@ -96,10 +99,12 @@ bool inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2,
 					    sk2->sk_rcv_saddr,
 					    ipv6_only_sock(sk),
 					    ipv6_only_sock(sk2),
+					    match_wildcard,
 					    match_wildcard);
 #endif
 	return ipv4_rcv_saddr_equal(sk->sk_rcv_saddr, sk2->sk_rcv_saddr,
-				    ipv6_only_sock(sk2), match_wildcard);
+				    ipv6_only_sock(sk2), match_wildcard,
+				    match_wildcard);
 }
 EXPORT_SYMBOL(inet_rcv_saddr_equal);
 
@@ -273,10 +278,10 @@ static inline int sk_reuseport_match(struct inet_bind_bucket *tb,
 					    tb->fast_rcv_saddr,
 					    sk->sk_rcv_saddr,
 					    tb->fast_ipv6_only,
-					    ipv6_only_sock(sk), true);
+					    ipv6_only_sock(sk), true, false);
 #endif
 	return ipv4_rcv_saddr_equal(tb->fast_rcv_saddr, sk->sk_rcv_saddr,
-				    ipv6_only_sock(sk), true);
+				    ipv6_only_sock(sk), true, false);
 }
 
 /* Obtain a reference to a local port for the given sock,
-- 
2.26.2


From bfed4543b3579ce9df0df12fa9be2703aa118c5c Mon Sep 17 00:00:00 2001
From: Vadim Fedorenko <vfedorenko@novek.ru>
Date: Wed, 20 May 2020 11:50:48 +0300
Subject: [PATCH 10/33] net: ipip: fix wrong address family in init error path

[ Upstream commit 57ebc8f08504f176eb0f25b3e0fde517dec61a4f ]

In case of error with MPLS support the code is misusing AF_INET
instead of AF_MPLS.

Fixes: 1b69e7e6c4da ("ipip: support MPLS over IPv4")
Signed-off-by: Vadim Fedorenko <vfedorenko@novek.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ipip.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 2f01cf6fa0de..678575adaf3b 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -698,7 +698,7 @@ static int __init ipip_init(void)
 
 rtnl_link_failed:
 #if IS_ENABLED(CONFIG_MPLS)
-	xfrm4_tunnel_deregister(&mplsip_handler, AF_INET);
+	xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS);
 xfrm_tunnel_mplsip_failed:
 
 #endif
-- 
2.26.2


From afd8ab4b06070e2488797a1b1dba7cd3fdad88f1 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Fri, 27 Dec 2019 07:01:53 +0200
Subject: [PATCH 11/33] net/mlx5: Add command entry handling completion

[ Upstream commit 17d00e839d3b592da9659c1977d45f85b77f986a ]

When FW response to commands is very slow and all command entries in
use are waiting for completion we can have a race where commands can get
timeout before they get out of the queue and handled. Timeout
completion on uninitialized command will cause releasing command's
buffers before accessing it for initialization and then we will get NULL
pointer exception while trying access it. It may also cause releasing
buffers of another command since we may have timeout completion before
even allocating entry index for this command.
Add entry handling completion to avoid this race.

Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters")
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 14 ++++++++++++++
 include/linux/mlx5/driver.h                   |  1 +
 2 files changed, 15 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index cede5bdfd598..d695b75bc0af 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -861,6 +861,7 @@ static void cmd_work_handler(struct work_struct *work)
 	int alloc_ret;
 	int cmd_mode;
 
+	complete(&ent->handling);
 	sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem;
 	down(sem);
 	if (!ent->page_queue) {
@@ -978,6 +979,11 @@ static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
 	struct mlx5_cmd *cmd = &dev->cmd;
 	int err;
 
+	if (!wait_for_completion_timeout(&ent->handling, timeout) &&
+	    cancel_work_sync(&ent->work)) {
+		ent->ret = -ECANCELED;
+		goto out_err;
+	}
 	if (cmd->mode == CMD_MODE_POLLING || ent->polling) {
 		wait_for_completion(&ent->done);
 	} else if (!wait_for_completion_timeout(&ent->done, timeout)) {
@@ -985,12 +991,17 @@ static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
 		mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
 	}
 
+out_err:
 	err = ent->ret;
 
 	if (err == -ETIMEDOUT) {
 		mlx5_core_warn(dev, "%s(0x%x) timeout. Will cause a leak of a command resource\n",
 			       mlx5_command_str(msg_to_opcode(ent->in)),
 			       msg_to_opcode(ent->in));
+	} else if (err == -ECANCELED) {
+		mlx5_core_warn(dev, "%s(0x%x) canceled on out of queue timeout.\n",
+			       mlx5_command_str(msg_to_opcode(ent->in)),
+			       msg_to_opcode(ent->in));
 	}
 	mlx5_core_dbg(dev, "err %d, delivery status %s(%d)\n",
 		      err, deliv_status_to_str(ent->status), ent->status);
@@ -1026,6 +1037,7 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 	ent->token = token;
 	ent->polling = force_polling;
 
+	init_completion(&ent->handling);
 	if (!callback)
 		init_completion(&ent->done);
 
@@ -1045,6 +1057,8 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 	err = wait_func(dev, ent);
 	if (err == -ETIMEDOUT)
 		goto out;
+	if (err == -ECANCELED)
+		goto out_free;
 
 	ds = ent->ts2 - ent->ts1;
 	op = MLX5_GET(mbox_in, in->first.data, opcode);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 277a51d3ec40..b596353a3a12 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -761,6 +761,7 @@ struct mlx5_cmd_work_ent {
 	struct delayed_work	cb_timeout_work;
 	void		       *context;
 	int			idx;
+	struct completion	handling;
 	struct completion	done;
 	struct mlx5_cmd        *cmd;
 	struct work_struct	work;
-- 
2.26.2


From 33390d33194619be1a1cd3d1760da7ffb20f3c48 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Wed, 20 May 2020 12:26:35 +0100
Subject: [PATCH 12/33] net: mvpp2: fix RX hashing for non-10G ports

[ Upstream commit 3138a07ce219acde4c0d7ea0b6d54ba64153328b ]

When rxhash is enabled on any ethernet port except the first in each CP
block, traffic flow is prevented.  The analysis is below:

I've been investigating this afternoon, and what I've found, comparing
a kernel without 895586d5dc32 and with 895586d5dc32 applied is:

- The table programmed into the hardware via mvpp22_rss_fill_table()
  appears to be identical with or without the commit.

- When rxhash is enabled on eth2, mvpp2_rss_port_c2_enable() reports
  that c2.attr[0] and c2.attr[2] are written back containing:

   - with 895586d5dc32, failing:    00200000 40000000
   - without 895586d5dc32, working: 04000000 40000000

- When disabling rxhash, c2.attr[0] and c2.attr[2] are written back as:

   04000000 00000000

The second value represents the MVPP22_CLS_C2_ATTR2_RSS_EN bit, the
first value is the queue number, which comprises two fields. The high
5 bits are 24:29 and the low three are 21:23 inclusive. This comes
from:

       c2.attr[0] = MVPP22_CLS_C2_ATTR0_QHIGH(qh) |
                     MVPP22_CLS_C2_ATTR0_QLOW(ql);

So, the working case gives eth2 a queue id of 4.0, or 32 as per
port->first_rxq, and the non-working case a queue id of 0.1, or 1.
The allocation of queue IDs seems to be in mvpp2_port_probe():

        if (priv->hw_version == MVPP21)
                port->first_rxq = port->id * port->nrxqs;
        else
                port->first_rxq = port->id * priv->max_port_rxqs;

Where:

        if (priv->hw_version == MVPP21)
                priv->max_port_rxqs = 8;
        else
                priv->max_port_rxqs = 32;

Making the port 0 (eth0 / eth1) have port->first_rxq = 0, and port 1
(eth2) be 32. It seems the idea is that the first 32 queues belong to
port 0, the second 32 queues belong to port 1, etc.

mvpp2_rss_port_c2_enable() gets the queue number from it's parameter,
'ctx', which comes from mvpp22_rss_ctx(port, 0). This returns
port->rss_ctx[0].

mvpp22_rss_context_create() is responsible for allocating that, which
it does by looking for an unallocated priv->rss_tables[] pointer. This
table is shared amongst all ports on the CP silicon.

When we write the tables in mvpp22_rss_fill_table(), the RSS table
entry is defined by:

                u32 sel = MVPP22_RSS_INDEX_TABLE(rss_ctx) |
                          MVPP22_RSS_INDEX_TABLE_ENTRY(i);

where rss_ctx is the context ID (queue number) and i is the index in
the table.

If we look at what is written:

- The first table to be written has "sel" values of 00000000..0000001f,
  containing values 0..3. This appears to be for eth1. This is table 0,
  RX queue number 0.
- The second table has "sel" values of 00000100..0000011f, and appears
  to be for eth2.  These contain values 0x20..0x23. This is table 1,
  RX queue number 0.
- The third table has "sel" values of 00000200..0000021f, and appears
  to be for eth3.  These contain values 0x40..0x43. This is table 2,
  RX queue number 0.

How do queue numbers translate to the RSS table?  There is another
table - the RXQ2RSS table, indexed by the MVPP22_RSS_INDEX_QUEUE field
of MVPP22_RSS_INDEX and accessed through the MVPP22_RXQ2RSS_TABLE
register. Before 895586d5dc32, it was:

       mvpp2_write(priv, MVPP22_RSS_INDEX,
                   MVPP22_RSS_INDEX_QUEUE(port->first_rxq));
       mvpp2_write(priv, MVPP22_RXQ2RSS_TABLE,
                   MVPP22_RSS_TABLE_POINTER(port->id));

and after:

       mvpp2_write(priv, MVPP22_RSS_INDEX, MVPP22_RSS_INDEX_QUEUE(ctx));
       mvpp2_write(priv, MVPP22_RXQ2RSS_TABLE, MVPP22_RSS_TABLE_POINTER(ctx));

Before the commit, for eth2, that would've contained '32' for the
index and '1' for the table pointer - mapping queue 32 to table 1.
Remember that this is queue-high.queue-low of 4.0.

After the commit, we appear to map queue 1 to table 1. That again
looks fine on the face of it.

Section 9.3.1 of the A8040 manual seems indicate the reason that the
queue number is separated. queue-low seems to always come from the
classifier, whereas queue-high can be from the ingress physical port
number or the classifier depending on the MVPP2_CLS_SWFWD_PCTRL_REG.

We set the port bit in MVPP2_CLS_SWFWD_PCTRL_REG, meaning that queue-high
comes from the MVPP2_CLS_SWFWD_P2HQ_REG() register... and this seems to
be where our bug comes from.

mvpp2_cls_oversize_rxq_set() sets this up as:

        mvpp2_write(port->priv, MVPP2_CLS_SWFWD_P2HQ_REG(port->id),
                    (port->first_rxq >> MVPP2_CLS_OVERSIZE_RXQ_LOW_BITS));

        val = mvpp2_read(port->priv, MVPP2_CLS_SWFWD_PCTRL_REG);
        val |= MVPP2_CLS_SWFWD_PCTRL_MASK(port->id);
        mvpp2_write(port->priv, MVPP2_CLS_SWFWD_PCTRL_REG, val);

Setting the MVPP2_CLS_SWFWD_PCTRL_MASK bit means that the queue-high
for eth2 is _always_ 4, so only queues 32 through 39 inclusive are
available to eth2. Yet, we're trying to tell the classifier to set
queue-high, which will be ignored, to zero. Hence, the queue-high
field (MVPP22_CLS_C2_ATTR0_QHIGH()) from the classifier will be
ignored.

This means we end up directing traffic from eth2 not to queue 1, but
to queue 33, and then we tell it to look up queue 33 in the RSS table.
However, RSS table has not been programmed for queue 33, and so it ends
up (presumably) dropping the packets.

It seems that mvpp22_rss_context_create() doesn't take account of the
fact that the upper 5 bits of the queue ID can't actually be changed
due to the settings in mvpp2_cls_oversize_rxq_set(), _or_ it seems that
mvpp2_cls_oversize_rxq_set() has been missed in this commit. Either
way, these two functions mutually disagree with what queue number
should be used.

Looking deeper into what mvpp2_cls_oversize_rxq_set() and the MTU
validation is doing, it seems that MVPP2_CLS_SWFWD_P2HQ_REG() is used
for over-sized packets attempting to egress through this port. With
the classifier having had RSS enabled and directing eth2 traffic to
queue 1, we may still have packets appearing on queue 32 for this port.

However, the only way we may end up with over-sized packets attempting
to egress through eth2 - is if the A8040 forwards frames between its
ports. From what I can see, we don't support that feature, and the
kernel restricts the egress packet size to the MTU. In any case, if we
were to attempt to transmit an oversized packet, we have no support in
the kernel to deal with that appearing in the port's receive queue.

So, this patch attempts to solve the issue by clearing the
MVPP2_CLS_SWFWD_PCTRL_MASK() bit, allowing MVPP22_CLS_C2_ATTR0_QHIGH()
from the classifier to define the queue-high field of the queue number.

My testing seems to confirm my findings above - clearing this bit
means that if I enable rxhash on eth2, the interface can then pass
traffic, as we are now directing traffic to RX queue 1 rather than
queue 33. Traffic still seems to work with rxhash off as well.

Reported-by: Matteo Croce <mcroce@redhat.com>
Tested-by: Matteo Croce <mcroce@redhat.com>
Fixes: 895586d5dc32 ("net: mvpp2: cls: Use RSS contexts to handle RSS tables")
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
index 4344a59c823f..6122057d60c0 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
@@ -1070,7 +1070,7 @@ void mvpp2_cls_oversize_rxq_set(struct mvpp2_port *port)
 		    (port->first_rxq >> MVPP2_CLS_OVERSIZE_RXQ_LOW_BITS));
 
 	val = mvpp2_read(port->priv, MVPP2_CLS_SWFWD_PCTRL_REG);
-	val |= MVPP2_CLS_SWFWD_PCTRL_MASK(port->id);
+	val &= ~MVPP2_CLS_SWFWD_PCTRL_MASK(port->id);
 	mvpp2_write(port->priv, MVPP2_CLS_SWFWD_PCTRL_REG, val);
 }
 
-- 
2.26.2


From dc1d0782599dd7ba689612ffd73c53886119d1d0 Mon Sep 17 00:00:00 2001
From: Stephen Worley <sworley@cumulusnetworks.com>
Date: Tue, 19 May 2020 21:57:12 -0400
Subject: [PATCH 13/33] net: nlmsg_cancel() if put fails for nhmsg

[ Upstream commit d69100b8eee27c2d60ee52df76e0b80a8d492d34 ]

Fixes data remnant seen when we fail to reserve space for a
nexthop group during a larger dump.

If we fail the reservation, we goto nla_put_failure and
cancel the message.

Reproduce with the following iproute2 commands:
=====================
ip link add dummy1 type dummy
ip link add dummy2 type dummy
ip link add dummy3 type dummy
ip link add dummy4 type dummy
ip link add dummy5 type dummy
ip link add dummy6 type dummy
ip link add dummy7 type dummy
ip link add dummy8 type dummy
ip link add dummy9 type dummy
ip link add dummy10 type dummy
ip link add dummy11 type dummy
ip link add dummy12 type dummy
ip link add dummy13 type dummy
ip link add dummy14 type dummy
ip link add dummy15 type dummy
ip link add dummy16 type dummy
ip link add dummy17 type dummy
ip link add dummy18 type dummy
ip link add dummy19 type dummy
ip link add dummy20 type dummy
ip link add dummy21 type dummy
ip link add dummy22 type dummy
ip link add dummy23 type dummy
ip link add dummy24 type dummy
ip link add dummy25 type dummy
ip link add dummy26 type dummy
ip link add dummy27 type dummy
ip link add dummy28 type dummy
ip link add dummy29 type dummy
ip link add dummy30 type dummy
ip link add dummy31 type dummy
ip link add dummy32 type dummy

ip link set dummy1 up
ip link set dummy2 up
ip link set dummy3 up
ip link set dummy4 up
ip link set dummy5 up
ip link set dummy6 up
ip link set dummy7 up
ip link set dummy8 up
ip link set dummy9 up
ip link set dummy10 up
ip link set dummy11 up
ip link set dummy12 up
ip link set dummy13 up
ip link set dummy14 up
ip link set dummy15 up
ip link set dummy16 up
ip link set dummy17 up
ip link set dummy18 up
ip link set dummy19 up
ip link set dummy20 up
ip link set dummy21 up
ip link set dummy22 up
ip link set dummy23 up
ip link set dummy24 up
ip link set dummy25 up
ip link set dummy26 up
ip link set dummy27 up
ip link set dummy28 up
ip link set dummy29 up
ip link set dummy30 up
ip link set dummy31 up
ip link set dummy32 up

ip link set dummy33 up
ip link set dummy34 up

ip link set vrf-red up
ip link set vrf-blue up

ip link set dummyVRFred up
ip link set dummyVRFblue up

ip ro add 1.1.1.1/32 dev dummy1
ip ro add 1.1.1.2/32 dev dummy2
ip ro add 1.1.1.3/32 dev dummy3
ip ro add 1.1.1.4/32 dev dummy4
ip ro add 1.1.1.5/32 dev dummy5
ip ro add 1.1.1.6/32 dev dummy6
ip ro add 1.1.1.7/32 dev dummy7
ip ro add 1.1.1.8/32 dev dummy8
ip ro add 1.1.1.9/32 dev dummy9
ip ro add 1.1.1.10/32 dev dummy10
ip ro add 1.1.1.11/32 dev dummy11
ip ro add 1.1.1.12/32 dev dummy12
ip ro add 1.1.1.13/32 dev dummy13
ip ro add 1.1.1.14/32 dev dummy14
ip ro add 1.1.1.15/32 dev dummy15
ip ro add 1.1.1.16/32 dev dummy16
ip ro add 1.1.1.17/32 dev dummy17
ip ro add 1.1.1.18/32 dev dummy18
ip ro add 1.1.1.19/32 dev dummy19
ip ro add 1.1.1.20/32 dev dummy20
ip ro add 1.1.1.21/32 dev dummy21
ip ro add 1.1.1.22/32 dev dummy22
ip ro add 1.1.1.23/32 dev dummy23
ip ro add 1.1.1.24/32 dev dummy24
ip ro add 1.1.1.25/32 dev dummy25
ip ro add 1.1.1.26/32 dev dummy26
ip ro add 1.1.1.27/32 dev dummy27
ip ro add 1.1.1.28/32 dev dummy28
ip ro add 1.1.1.29/32 dev dummy29
ip ro add 1.1.1.30/32 dev dummy30
ip ro add 1.1.1.31/32 dev dummy31
ip ro add 1.1.1.32/32 dev dummy32

ip next add id 1 via 1.1.1.1 dev dummy1
ip next add id 2 via 1.1.1.2 dev dummy2
ip next add id 3 via 1.1.1.3 dev dummy3
ip next add id 4 via 1.1.1.4 dev dummy4
ip next add id 5 via 1.1.1.5 dev dummy5
ip next add id 6 via 1.1.1.6 dev dummy6
ip next add id 7 via 1.1.1.7 dev dummy7
ip next add id 8 via 1.1.1.8 dev dummy8
ip next add id 9 via 1.1.1.9 dev dummy9
ip next add id 10 via 1.1.1.10 dev dummy10
ip next add id 11 via 1.1.1.11 dev dummy11
ip next add id 12 via 1.1.1.12 dev dummy12
ip next add id 13 via 1.1.1.13 dev dummy13
ip next add id 14 via 1.1.1.14 dev dummy14
ip next add id 15 via 1.1.1.15 dev dummy15
ip next add id 16 via 1.1.1.16 dev dummy16
ip next add id 17 via 1.1.1.17 dev dummy17
ip next add id 18 via 1.1.1.18 dev dummy18
ip next add id 19 via 1.1.1.19 dev dummy19
ip next add id 20 via 1.1.1.20 dev dummy20
ip next add id 21 via 1.1.1.21 dev dummy21
ip next add id 22 via 1.1.1.22 dev dummy22
ip next add id 23 via 1.1.1.23 dev dummy23
ip next add id 24 via 1.1.1.24 dev dummy24
ip next add id 25 via 1.1.1.25 dev dummy25
ip next add id 26 via 1.1.1.26 dev dummy26
ip next add id 27 via 1.1.1.27 dev dummy27
ip next add id 28 via 1.1.1.28 dev dummy28
ip next add id 29 via 1.1.1.29 dev dummy29
ip next add id 30 via 1.1.1.30 dev dummy30
ip next add id 31 via 1.1.1.31 dev dummy31
ip next add id 32 via 1.1.1.32 dev dummy32

i=100

while [ $i -le 200 ]
do
ip next add id $i group 1/2/3/4/5/6/7/8/9/10/11/12/13/14/15/16/17/18/19

	echo $i

	((i++))

done

ip next add id 999 group 1/2/3/4/5/6

ip next ls

========================

Fixes: ab84be7e54fc ("net: Initial nexthop code")
Signed-off-by: Stephen Worley <sworley@cumulusnetworks.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/nexthop.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index d072c326dd64..489c27f894d7 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -276,6 +276,7 @@ static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh,
 	return 0;
 
 nla_put_failure:
+	nlmsg_cancel(skb, nlh);
 	return -EMSGSIZE;
 }
 
-- 
2.26.2


From 3c1361798ef89523eeed18d877dc298a11fd8bbe Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Tue, 19 May 2020 23:44:16 +0530
Subject: [PATCH 14/33] net: qrtr: Fix passing invalid reference to
 qrtr_local_enqueue()

[ Upstream commit d28ea1fbbf437054ef339afec241019f2c4e2bb6 ]

Once the traversal of the list is completed with list_for_each_entry(),
the iterator (node) will point to an invalid object. So passing this to
qrtr_local_enqueue() which is outside of the iterator block is erroneous
eventhough the object is not used.

So fix this by passing NULL to qrtr_local_enqueue().

Fixes: bdabad3e363d ("net: Add Qualcomm IPC router")
Reported-by: kbuild test robot <lkp@intel.com>
Reported-by: Julia Lawall <julia.lawall@lip6.fr>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/qrtr/qrtr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index b7b854621c26..9d38c14d251a 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -855,7 +855,7 @@ static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb,
 	}
 	mutex_unlock(&qrtr_node_lock);
 
-	qrtr_local_enqueue(node, skb, type, from, to);
+	qrtr_local_enqueue(NULL, skb, type, from, to);
 
 	return 0;
 }
-- 
2.26.2


From 6e3bfcd3d8c98a472338f52d306d0839e231bd18 Mon Sep 17 00:00:00 2001
From: Yuqi Jin <jinyuqi@huawei.com>
Date: Sat, 16 May 2020 11:46:49 +0800
Subject: [PATCH 15/33] net: revert "net: get rid of an signed integer overflow
 in ip_idents_reserve()"

[ Upstream commit a6211caa634da39d861a47437ffcda8b38ef421b ]

Commit adb03115f459 ("net: get rid of an signed integer overflow in ip_idents_reserve()")
used atomic_cmpxchg to replace "atomic_add_return" inside the function
"ip_idents_reserve". The reason was to avoid UBSAN warning.
However, this change has caused performance degrade and in GCC-8,
fno-strict-overflow is now mapped to -fwrapv -fwrapv-pointer
and signed integer overflow is now undefined by default at all
optimization levels[1]. Moreover, it was a bug in UBSAN vs -fwrapv
/-fno-strict-overflow, so Let's revert it safely.

[1] https://gcc.gnu.org/gcc-8/changes.html

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Suggested-by: Eric Dumazet <edumazet@google.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Jiri Pirko <jiri@resnulli.us>
Cc: Arvind Sankar <nivedita@alum.mit.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jiong Wang <jiongwang@huawei.com>
Signed-off-by: Yuqi Jin <jinyuqi@huawei.com>
Signed-off-by: Shaokun Zhang <zhangshaokun@hisilicon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index ef6b70774fe1..fea6a8a11183 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -491,18 +491,16 @@ u32 ip_idents_reserve(u32 hash, int segs)
 	atomic_t *p_id = ip_idents + hash % IP_IDENTS_SZ;
 	u32 old = READ_ONCE(*p_tstamp);
 	u32 now = (u32)jiffies;
-	u32 new, delta = 0;
+	u32 delta = 0;
 
 	if (old != now && cmpxchg(p_tstamp, old, now) == old)
 		delta = prandom_u32_max(now - old);
 
-	/* Do not use atomic_add_return() as it makes UBSAN unhappy */
-	do {
-		old = (u32)atomic_read(p_id);
-		new = old + delta + segs;
-	} while (atomic_cmpxchg(p_id, old, new) != old);
-
-	return new - segs;
+	/* If UBSAN reports an error there, please make sure your compiler
+	 * supports -fno-strict-overflow before reporting it that was a bug
+	 * in UBSAN, and it has been fixed in GCC-8.
+	 */
+	return atomic_add_return(segs + delta, p_id) - segs;
 }
 EXPORT_SYMBOL(ip_idents_reserve);
 
-- 
2.26.2


From f0b9476ad94c2cae5d00aefa17636839f1cffac0 Mon Sep 17 00:00:00 2001
From: Roman Mashak <mrv@mojatatu.com>
Date: Sun, 17 May 2020 08:46:31 -0400
Subject: [PATCH 16/33] net sched: fix reporting the first-time use timestamp

[ Upstream commit b15e62631c5f19fea9895f7632dae9c1b27fe0cd ]

When a new action is installed, firstuse field of 'tcf_t' is explicitly set
to 0. Value of zero means "new action, not yet used"; as a packet hits the
action, 'firstuse' is stamped with the current jiffies value.

tcf_tm_dump() should return 0 for firstuse if action has not yet been hit.

Fixes: 48d8ee1694dd ("net sched actions: aggregate dumping of actions timeinfo")
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Roman Mashak <mrv@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/act_api.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/net/act_api.h b/include/net/act_api.h
index 71347a90a9d1..050c0246dee8 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -69,7 +69,8 @@ static inline void tcf_tm_dump(struct tcf_t *dtm, const struct tcf_t *stm)
 {
 	dtm->install = jiffies_to_clock_t(jiffies - stm->install);
 	dtm->lastuse = jiffies_to_clock_t(jiffies - stm->lastuse);
-	dtm->firstuse = jiffies_to_clock_t(jiffies - stm->firstuse);
+	dtm->firstuse = stm->firstuse ?
+		jiffies_to_clock_t(jiffies - stm->firstuse) : 0;
 	dtm->expires = jiffies_to_clock_t(stm->expires);
 }
 
-- 
2.26.2


From c773e6679d5f4cee0ea8a94bb2bd562bb362ec40 Mon Sep 17 00:00:00 2001
From: Vinay Kumar Yadav <vinay.yadav@chelsio.com>
Date: Sat, 23 May 2020 01:40:31 +0530
Subject: [PATCH 17/33] net/tls: fix race condition causing kernel panic

[ Upstream commit 0cada33241d9de205522e3858b18e506ca5cce2c ]

tls_sw_recvmsg() and tls_decrypt_done() can be run concurrently.
// tls_sw_recvmsg()
	if (atomic_read(&ctx->decrypt_pending))
		crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
	else
		reinit_completion(&ctx->async_wait.completion);

//tls_decrypt_done()
  	pending = atomic_dec_return(&ctx->decrypt_pending);

  	if (!pending && READ_ONCE(ctx->async_notify))
  		complete(&ctx->async_wait.completion);

Consider the scenario tls_decrypt_done() is about to run complete()

	if (!pending && READ_ONCE(ctx->async_notify))

and tls_sw_recvmsg() reads decrypt_pending == 0, does reinit_completion(),
then tls_decrypt_done() runs complete(). This sequence of execution
results in wrong completion. Consequently, for next decrypt request,
it will not wait for completion, eventually on connection close, crypto
resources freed, there is no way to handle pending decrypt response.

This race condition can be avoided by having atomic_read() mutually
exclusive with atomic_dec_return(),complete().Intoduced spin lock to
ensure the mutual exclution.

Addressed similar problem in tx direction.

v1->v2:
- More readable commit message.
- Corrected the lock to fix new race scenario.
- Removed barrier which is not needed now.

Fixes: a42055e8d2c3 ("net/tls: Add support for async encryption of records for performance")
Signed-off-by: Vinay Kumar Yadav <vinay.yadav@chelsio.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h |  4 ++++
 net/tls/tls_sw.c  | 33 +++++++++++++++++++++++++++------
 2 files changed, 31 insertions(+), 6 deletions(-)

diff --git a/include/net/tls.h b/include/net/tls.h
index bf9eb4823933..18cd4f418464 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -135,6 +135,8 @@ struct tls_sw_context_tx {
 	struct tls_rec *open_rec;
 	struct list_head tx_list;
 	atomic_t encrypt_pending;
+	/* protect crypto_wait with encrypt_pending */
+	spinlock_t encrypt_compl_lock;
 	int async_notify;
 	u8 async_capable:1;
 
@@ -155,6 +157,8 @@ struct tls_sw_context_rx {
 	u8 async_capable:1;
 	u8 decrypted:1;
 	atomic_t decrypt_pending;
+	/* protect crypto_wait with decrypt_pending*/
+	spinlock_t decrypt_compl_lock;
 	bool async_notify;
 };
 
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index e23f94a5549b..ffa3cbc5449d 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -206,10 +206,12 @@ static void tls_decrypt_done(struct crypto_async_request *req, int err)
 
 	kfree(aead_req);
 
+	spin_lock_bh(&ctx->decrypt_compl_lock);
 	pending = atomic_dec_return(&ctx->decrypt_pending);
 
-	if (!pending && READ_ONCE(ctx->async_notify))
+	if (!pending && ctx->async_notify)
 		complete(&ctx->async_wait.completion);
+	spin_unlock_bh(&ctx->decrypt_compl_lock);
 }
 
 static int tls_do_decryption(struct sock *sk,
@@ -467,10 +469,12 @@ static void tls_encrypt_done(struct crypto_async_request *req, int err)
 			ready = true;
 	}
 
+	spin_lock_bh(&ctx->encrypt_compl_lock);
 	pending = atomic_dec_return(&ctx->encrypt_pending);
 
-	if (!pending && READ_ONCE(ctx->async_notify))
+	if (!pending && ctx->async_notify)
 		complete(&ctx->async_wait.completion);
+	spin_unlock_bh(&ctx->encrypt_compl_lock);
 
 	if (!ready)
 		return;
@@ -926,6 +930,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 	int num_zc = 0;
 	int orig_size;
 	int ret = 0;
+	int pending;
 
 	if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL))
 		return -EOPNOTSUPP;
@@ -1092,13 +1097,19 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 		goto send_end;
 	} else if (num_zc) {
 		/* Wait for pending encryptions to get completed */
-		smp_store_mb(ctx->async_notify, true);
+		spin_lock_bh(&ctx->encrypt_compl_lock);
+		ctx->async_notify = true;
 
-		if (atomic_read(&ctx->encrypt_pending))
+		pending = atomic_read(&ctx->encrypt_pending);
+		spin_unlock_bh(&ctx->encrypt_compl_lock);
+		if (pending)
 			crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
 		else
 			reinit_completion(&ctx->async_wait.completion);
 
+		/* There can be no concurrent accesses, since we have no
+		 * pending encrypt operations
+		 */
 		WRITE_ONCE(ctx->async_notify, false);
 
 		if (ctx->async_wait.err) {
@@ -1729,6 +1740,7 @@ int tls_sw_recvmsg(struct sock *sk,
 	bool is_kvec = iov_iter_is_kvec(&msg->msg_iter);
 	bool is_peek = flags & MSG_PEEK;
 	int num_async = 0;
+	int pending;
 
 	flags |= nonblock;
 
@@ -1891,8 +1903,11 @@ int tls_sw_recvmsg(struct sock *sk,
 recv_end:
 	if (num_async) {
 		/* Wait for all previously submitted records to be decrypted */
-		smp_store_mb(ctx->async_notify, true);
-		if (atomic_read(&ctx->decrypt_pending)) {
+		spin_lock_bh(&ctx->decrypt_compl_lock);
+		ctx->async_notify = true;
+		pending = atomic_read(&ctx->decrypt_pending);
+		spin_unlock_bh(&ctx->decrypt_compl_lock);
+		if (pending) {
 			err = crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
 			if (err) {
 				/* one of async decrypt failed */
@@ -1904,6 +1919,10 @@ int tls_sw_recvmsg(struct sock *sk,
 		} else {
 			reinit_completion(&ctx->async_wait.completion);
 		}
+
+		/* There can be no concurrent accesses, since we have no
+		 * pending decrypt operations
+		 */
 		WRITE_ONCE(ctx->async_notify, false);
 
 		/* Drain records from the rx_list & copy if required */
@@ -2290,6 +2309,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 
 	if (tx) {
 		crypto_init_wait(&sw_ctx_tx->async_wait);
+		spin_lock_init(&sw_ctx_tx->encrypt_compl_lock);
 		crypto_info = &ctx->crypto_send.info;
 		cctx = &ctx->tx;
 		aead = &sw_ctx_tx->aead_send;
@@ -2298,6 +2318,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 		sw_ctx_tx->tx_work.sk = sk;
 	} else {
 		crypto_init_wait(&sw_ctx_rx->async_wait);
+		spin_lock_init(&sw_ctx_rx->decrypt_compl_lock);
 		crypto_info = &ctx->crypto_recv.info;
 		cctx = &ctx->rx;
 		skb_queue_head_init(&sw_ctx_rx->rx_list);
-- 
2.26.2


From 43408103d43d4777493565f810adf0f551d164cf Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Sun, 17 May 2020 11:26:32 -0600
Subject: [PATCH 18/33] nexthop: Fix attribute checking for groups

[ Upstream commit 84be69b869a5a496a6cfde9b3c29509207a1f1fa ]

For nexthop groups, attributes after NHA_GROUP_TYPE are invalid, but
nh_check_attr_group starts checking at NHA_GROUP. The group type defaults
to multipath and the NHA_GROUP_TYPE is currently optional so this has
slipped through so far. Fix the attribute checking to handle support of
new group types.

Fixes: 430a049190de ("nexthop: Add support for nexthop groups")
Signed-off-by: ASSOGBA Emery <assogba.emery@gmail.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/nexthop.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 489c27f894d7..b03ea728d9a3 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -434,7 +434,7 @@ static int nh_check_attr_group(struct net *net, struct nlattr *tb[],
 		if (!valid_group_nh(nh, len, extack))
 			return -EINVAL;
 	}
-	for (i = NHA_GROUP + 1; i < __NHA_MAX; ++i) {
+	for (i = NHA_GROUP_TYPE + 1; i < __NHA_MAX; ++i) {
 		if (!tb[i])
 			continue;
 
-- 
2.26.2


From 570612b4e4e74303154719e9a5f786a6c692a2d5 Mon Sep 17 00:00:00 2001
From: Marc Payne <marc.payne@mdpsys.co.uk>
Date: Tue, 19 May 2020 19:01:46 +0100
Subject: [PATCH 19/33] r8152: support additional Microsoft Surface Ethernet
 Adapter variant

[ Upstream commit c27a204383616efba5a4194075e90819961ff66a ]

Device id 0927 is the RTL8153B-based component of the 'Surface USB-C to
Ethernet and USB Adapter' and may be used as a component of other devices
in future. Tested and working with the r8152 driver.

Update the cdc_ether blacklist due to the RTL8153 'network jam on suspend'
issue which this device will cause (personally confirmed).

Signed-off-by: Marc Payne <marc.payne@mdpsys.co.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ether.c | 11 +++++++++--
 drivers/net/usb/r8152.c     |  1 +
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index 0cdb2ce47645..a657943c9f01 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -815,14 +815,21 @@ static const struct usb_device_id	products[] = {
 	.driver_info = 0,
 },
 
-/* Microsoft Surface 3 dock (based on Realtek RTL8153) */
+/* Microsoft Surface Ethernet Adapter (based on Realtek RTL8153) */
 {
 	USB_DEVICE_AND_INTERFACE_INFO(MICROSOFT_VENDOR_ID, 0x07c6, USB_CLASS_COMM,
 			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
 	.driver_info = 0,
 },
 
-	/* TP-LINK UE300 USB 3.0 Ethernet Adapters (based on Realtek RTL8153) */
+/* Microsoft Surface Ethernet Adapter (based on Realtek RTL8153B) */
+{
+	USB_DEVICE_AND_INTERFACE_INFO(MICROSOFT_VENDOR_ID, 0x0927, USB_CLASS_COMM,
+			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+	.driver_info = 0,
+},
+
+/* TP-LINK UE300 USB 3.0 Ethernet Adapters (based on Realtek RTL8153) */
 {
 	USB_DEVICE_AND_INTERFACE_INFO(TPLINK_VENDOR_ID, 0x0601, USB_CLASS_COMM,
 			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 95b19ce96513..7c8c45984a5c 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -6901,6 +6901,7 @@ static const struct usb_device_id rtl8152_table[] = {
 	{REALTEK_USB_DEVICE(VENDOR_ID_REALTEK, 0x8153)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07ab)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07c6)},
+	{REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x0927)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_SAMSUNG, 0xa101)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x304f)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x3062)},
-- 
2.26.2


From 7ceb6dc65567e0ff85be245e7c316197593c7ff8 Mon Sep 17 00:00:00 2001
From: Neil Horman <nhorman@tuxdriver.com>
Date: Tue, 19 May 2020 16:04:05 -0400
Subject: [PATCH 20/33] sctp: Don't add the shutdown timer if its already been
 added

[ Upstream commit 20a785aa52c82246055a089e55df9dac47d67da1 ]

This BUG halt was reported a while back, but the patch somehow got
missed:

PID: 2879   TASK: c16adaa0  CPU: 1   COMMAND: "sctpn"
 #0 [f418dd28] crash_kexec at c04a7d8c
 #1 [f418dd7c] oops_end at c0863e02
 #2 [f418dd90] do_invalid_op at c040aaca
 #3 [f418de28] error_code (via invalid_op) at c08631a5
    EAX: f34baac0  EBX: 00000090  ECX: f418deb0  EDX: f5542950  EBP: 00000000
    DS:  007b      ESI: f34ba800  ES:  007b      EDI: f418dea0  GS:  00e0
    CS:  0060      EIP: c046fa5e  ERR: ffffffff  EFLAGS: 00010286
 #4 [f418de5c] add_timer at c046fa5e
 #5 [f418de68] sctp_do_sm at f8db8c77 [sctp]
 #6 [f418df30] sctp_primitive_SHUTDOWN at f8dcc1b5 [sctp]
 #7 [f418df48] inet_shutdown at c080baf9
 #8 [f418df5c] sys_shutdown at c079eedf
 #9 [f418df70] sys_socketcall at c079fe88
    EAX: ffffffda  EBX: 0000000d  ECX: bfceea90  EDX: 0937af98
    DS:  007b      ESI: 0000000c  ES:  007b      EDI: b7150ae4
    SS:  007b      ESP: bfceea7c  EBP: bfceeaa8  GS:  0033
    CS:  0073      EIP: b775c424  ERR: 00000066  EFLAGS: 00000282

It appears that the side effect that starts the shutdown timer was processed
multiple times, which can happen as multiple paths can trigger it.  This of
course leads to the BUG halt in add_timer getting called.

Fix seems pretty straightforward, just check before the timer is added if its
already been started.  If it has mod the timer instead to min(current
expiration, new expiration)

Its been tested but not confirmed to fix the problem, as the issue has only
occured in production environments where test kernels are enjoined from being
installed.  It appears to be a sane fix to me though.  Also, recentely,
Jere found a reproducer posted on list to confirm that this resolves the
issues

Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
CC: Vlad Yasevich <vyasevich@gmail.com>
CC: "David S. Miller" <davem@davemloft.net>
CC: jere.leppanen@nokia.com
CC: marcelo.leitner@gmail.com
CC: netdev@vger.kernel.org
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sm_sideeffect.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index 2bc29463e1dc..9f36fe911d08 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -1523,9 +1523,17 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type,
 			timeout = asoc->timeouts[cmd->obj.to];
 			BUG_ON(!timeout);
 
-			timer->expires = jiffies + timeout;
-			sctp_association_hold(asoc);
-			add_timer(timer);
+			/*
+			 * SCTP has a hard time with timer starts.  Because we process
+			 * timer starts as side effects, it can be hard to tell if we
+			 * have already started a timer or not, which leads to BUG
+			 * halts when we call add_timer. So here, instead of just starting
+			 * a timer, if the timer is already started, and just mod
+			 * the timer with the shorter of the two expiration times
+			 */
+			if (!timer_pending(timer))
+				sctp_association_hold(asoc);
+			timer_reduce(timer, jiffies + timeout);
 			break;
 
 		case SCTP_CMD_TIMER_RESTART:
-- 
2.26.2


From 6e4a5bd981e6dfeb3bd42f1d5038e217bdc56535 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jere=20Lepp=C3=A4nen?= <jere.leppanen@nokia.com>
Date: Wed, 20 May 2020 18:15:31 +0300
Subject: [PATCH 21/33] sctp: Start shutdown on association restart if in
 SHUTDOWN-SENT state and socket is closed
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit d3e8e4c11870413789f029a71e72ae6e971fe678 ]

Commit bdf6fa52f01b ("sctp: handle association restarts when the
socket is closed.") starts shutdown when an association is restarted,
if in SHUTDOWN-PENDING state and the socket is closed. However, the
rationale stated in that commit applies also when in SHUTDOWN-SENT
state - we don't want to move an association to ESTABLISHED state when
the socket has been closed, because that results in an association
that is unreachable from user space.

The problem scenario:

1.  Client crashes and/or restarts.

2.  Server (using one-to-one socket) calls close(). SHUTDOWN is lost.

3.  Client reconnects using the same addresses and ports.

4.  Server's association is restarted. The association and the socket
    move to ESTABLISHED state, even though the server process has
    closed its descriptor.

Also, after step 4 when the server process exits, some resources are
leaked in an attempt to release the underlying inet sock structure in
ESTABLISHED state:

    IPv4: Attempt to release TCP socket in state 1 00000000377288c7

Fix by acting the same way as in SHUTDOWN-PENDING state. That is, if
an association is restarted in SHUTDOWN-SENT state and the socket is
closed, then start shutdown and don't move the association or the
socket to ESTABLISHED state.

Fixes: bdf6fa52f01b ("sctp: handle association restarts when the socket is closed.")
Signed-off-by: Jere Leppänen <jere.leppanen@nokia.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/sm_statefuns.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 26788f4a3b9e..e86620fbd90f 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -1856,12 +1856,13 @@ static enum sctp_disposition sctp_sf_do_dupcook_a(
 	/* Update the content of current association. */
 	sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc));
 	sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev));
-	if (sctp_state(asoc, SHUTDOWN_PENDING) &&
+	if ((sctp_state(asoc, SHUTDOWN_PENDING) ||
+	     sctp_state(asoc, SHUTDOWN_SENT)) &&
 	    (sctp_sstate(asoc->base.sk, CLOSING) ||
 	     sock_flag(asoc->base.sk, SOCK_DEAD))) {
-		/* if were currently in SHUTDOWN_PENDING, but the socket
-		 * has been closed by user, don't transition to ESTABLISHED.
-		 * Instead trigger SHUTDOWN bundled with COOKIE_ACK.
+		/* If the socket has been closed by user, don't
+		 * transition to ESTABLISHED. Instead trigger SHUTDOWN
+		 * bundled with COOKIE_ACK.
 		 */
 		sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl));
 		return sctp_sf_do_9_2_start_shutdown(net, ep, asoc,
-- 
2.26.2


From 6ac82adf58daf81b42c65ec668c3018abf28cac0 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 21 May 2020 11:29:58 -0700
Subject: [PATCH 22/33] tipc: block BH before using dst_cache

[ Upstream commit 1378817486d6860f6a927f573491afe65287abf1 ]

dst_cache_get() documents it must be used with BH disabled.

sysbot reported :

BUG: using smp_processor_id() in preemptible [00000000] code: /21697
caller is dst_cache_get+0x3a/0xb0 net/core/dst_cache.c:68
CPU: 0 PID: 21697 Comm:  Not tainted 5.7.0-rc6-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x188/0x20d lib/dump_stack.c:118
 check_preemption_disabled lib/smp_processor_id.c:47 [inline]
 debug_smp_processor_id.cold+0x88/0x9b lib/smp_processor_id.c:57
 dst_cache_get+0x3a/0xb0 net/core/dst_cache.c:68
 tipc_udp_xmit.isra.0+0xb9/0xad0 net/tipc/udp_media.c:164
 tipc_udp_send_msg+0x3e6/0x490 net/tipc/udp_media.c:244
 tipc_bearer_xmit_skb+0x1de/0x3f0 net/tipc/bearer.c:526
 tipc_enable_bearer+0xb2f/0xd60 net/tipc/bearer.c:331
 __tipc_nl_bearer_enable+0x2bf/0x390 net/tipc/bearer.c:995
 tipc_nl_bearer_enable+0x1e/0x30 net/tipc/bearer.c:1003
 genl_family_rcv_msg_doit net/netlink/genetlink.c:673 [inline]
 genl_family_rcv_msg net/netlink/genetlink.c:718 [inline]
 genl_rcv_msg+0x627/0xdf0 net/netlink/genetlink.c:735
 netlink_rcv_skb+0x15a/0x410 net/netlink/af_netlink.c:2469
 genl_rcv+0x24/0x40 net/netlink/genetlink.c:746
 netlink_unicast_kernel net/netlink/af_netlink.c:1303 [inline]
 netlink_unicast+0x537/0x740 net/netlink/af_netlink.c:1329
 netlink_sendmsg+0x882/0xe10 net/netlink/af_netlink.c:1918
 sock_sendmsg_nosec net/socket.c:652 [inline]
 sock_sendmsg+0xcf/0x120 net/socket.c:672
 ____sys_sendmsg+0x6bf/0x7e0 net/socket.c:2362
 ___sys_sendmsg+0x100/0x170 net/socket.c:2416
 __sys_sendmsg+0xec/0x1b0 net/socket.c:2449
 do_syscall_64+0xf6/0x7d0 arch/x86/entry/common.c:295
 entry_SYSCALL_64_after_hwframe+0x49/0xb3
RIP: 0033:0x45ca29

Fixes: e9c1a793210f ("tipc: add dst_cache support for udp media")
Cc: Xin Long <lucien.xin@gmail.com>
Cc: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/udp_media.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index d6620ad53546..28a283f26a8d 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -161,9 +161,11 @@ static int tipc_udp_xmit(struct net *net, struct sk_buff *skb,
 			 struct udp_bearer *ub, struct udp_media_addr *src,
 			 struct udp_media_addr *dst, struct dst_cache *cache)
 {
-	struct dst_entry *ndst = dst_cache_get(cache);
+	struct dst_entry *ndst;
 	int ttl, err = 0;
 
+	local_bh_disable();
+	ndst = dst_cache_get(cache);
 	if (dst->proto == htons(ETH_P_IP)) {
 		struct rtable *rt = (struct rtable *)ndst;
 
@@ -210,9 +212,11 @@ static int tipc_udp_xmit(struct net *net, struct sk_buff *skb,
 					   src->port, dst->port, false);
 #endif
 	}
+	local_bh_enable();
 	return err;
 
 tx_error:
+	local_bh_enable();
 	kfree_skb(skb);
 	return err;
 }
-- 
2.26.2


From 68b562f9baf04840c4a8142cc475a02da7ef5972 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Mon, 27 Apr 2020 16:56:59 +0300
Subject: [PATCH 23/33] net/mlx5e: kTLS, Destroy key object after destroying
 the TIS

[ Upstream commit 16736e11f43b80a38f98f6add54fab3b8c297df3 ]

The TLS TIS object contains the dek/key ID.
By destroying the key first, the TIS would contain an invalid
non-existing key ID.
Reverse the destroy order, this also acheives the desired assymetry
between the destroy and the create flows.

Fixes: d2ead1f360e8 ("net/mlx5e: Add kTLS TX HW offload support")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c
index 46725cd743a3..7d1985fa0d4f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c
@@ -69,8 +69,8 @@ static void mlx5e_ktls_del(struct net_device *netdev,
 	struct mlx5e_ktls_offload_context_tx *tx_priv =
 		mlx5e_get_ktls_tx_priv_ctx(tls_ctx);
 
-	mlx5_ktls_destroy_key(priv->mdev, tx_priv->key_id);
 	mlx5e_destroy_tis(priv->mdev, tx_priv->tisn);
+	mlx5_ktls_destroy_key(priv->mdev, tx_priv->key_id);
 	kvfree(tx_priv);
 }
 
-- 
2.26.2


From 6f625e542e3090f8f2e40cdf729f2d7280763a81 Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@mellanox.com>
Date: Thu, 30 Apr 2020 09:16:01 +0300
Subject: [PATCH 24/33] net/mlx5e: Fix inner tirs handling

[ Upstream commit a16b8e0dcf7043bee46174bed0553cc9e36b63a5 ]

In the cited commit inner_tirs argument was added to create and destroy
inner tirs, and no indication was added to mlx5e_modify_tirs_hash()
function. In order to have a consistent handling, use
inner_indir_tir[0].tirn in tirs destroy/modify function as an indication
to whether inner tirs are created.
Inner tirs are not created for representors and before this commit,
a call to mlx5e_modify_tirs_hash() was sending HW commands to
modify non-existent inner tirs.

Fixes: 46dc933cee82 ("net/mlx5e: Provide explicit directive if to create inner indirect tirs")
Signed-off-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h         |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c    | 12 +++++++-----
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c     |  4 ++--
 .../net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c    |  4 ++--
 4 files changed, 12 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 5a5e6a21c6e1..80c579948152 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -1104,7 +1104,7 @@ void mlx5e_close_drop_rq(struct mlx5e_rq *drop_rq);
 int mlx5e_create_indirect_rqt(struct mlx5e_priv *priv);
 
 int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc);
-void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc);
+void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv);
 
 int mlx5e_create_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs);
 void mlx5e_destroy_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index d02db5aebac4..4fef7587165c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2747,7 +2747,8 @@ void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen)
 		mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in, inlen);
 	}
 
-	if (!mlx5e_tunnel_inner_ft_supported(priv->mdev))
+	/* Verify inner tirs resources allocated */
+	if (!priv->inner_indir_tir[0].tirn)
 		return;
 
 	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
@@ -3394,14 +3395,15 @@ int mlx5e_create_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs)
 	return err;
 }
 
-void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc)
+void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv)
 {
 	int i;
 
 	for (i = 0; i < MLX5E_NUM_INDIR_TIRS; i++)
 		mlx5e_destroy_tir(priv->mdev, &priv->indir_tir[i]);
 
-	if (!inner_ttc || !mlx5e_tunnel_inner_ft_supported(priv->mdev))
+	/* Verify inner tirs resources allocated */
+	if (!priv->inner_indir_tir[0].tirn)
 		return;
 
 	for (i = 0; i < MLX5E_NUM_INDIR_TIRS; i++)
@@ -5107,7 +5109,7 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv)
 err_destroy_direct_tirs:
 	mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
 err_destroy_indirect_tirs:
-	mlx5e_destroy_indirect_tirs(priv, true);
+	mlx5e_destroy_indirect_tirs(priv);
 err_destroy_direct_rqts:
 	mlx5e_destroy_direct_rqts(priv, priv->direct_tir);
 err_destroy_indirect_rqts:
@@ -5126,7 +5128,7 @@ static void mlx5e_cleanup_nic_rx(struct mlx5e_priv *priv)
 	mlx5e_destroy_direct_tirs(priv, priv->xsk_tir);
 	mlx5e_destroy_direct_rqts(priv, priv->xsk_tir);
 	mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
-	mlx5e_destroy_indirect_tirs(priv, true);
+	mlx5e_destroy_indirect_tirs(priv);
 	mlx5e_destroy_direct_rqts(priv, priv->direct_tir);
 	mlx5e_destroy_rqt(priv, &priv->indir_rqt);
 	mlx5e_close_drop_rq(&priv->drop_rq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 2ad0d09cc9bd..c3c3d89d9153 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1667,7 +1667,7 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
 err_destroy_direct_tirs:
 	mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
 err_destroy_indirect_tirs:
-	mlx5e_destroy_indirect_tirs(priv, false);
+	mlx5e_destroy_indirect_tirs(priv);
 err_destroy_direct_rqts:
 	mlx5e_destroy_direct_rqts(priv, priv->direct_tir);
 err_destroy_indirect_rqts:
@@ -1684,7 +1684,7 @@ static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv)
 	mlx5_del_flow_rules(rpriv->vport_rx_rule);
 	mlx5e_destroy_ttc_table(priv, &priv->fs.ttc);
 	mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
-	mlx5e_destroy_indirect_tirs(priv, false);
+	mlx5e_destroy_indirect_tirs(priv);
 	mlx5e_destroy_direct_rqts(priv, priv->direct_tir);
 	mlx5e_destroy_rqt(priv, &priv->indir_rqt);
 	mlx5e_close_drop_rq(&priv->drop_rq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 56078b23f1a0..0a334ceba7b1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -396,7 +396,7 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv)
 err_destroy_direct_tirs:
 	mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
 err_destroy_indirect_tirs:
-	mlx5e_destroy_indirect_tirs(priv, true);
+	mlx5e_destroy_indirect_tirs(priv);
 err_destroy_direct_rqts:
 	mlx5e_destroy_direct_rqts(priv, priv->direct_tir);
 err_destroy_indirect_rqts:
@@ -412,7 +412,7 @@ static void mlx5i_cleanup_rx(struct mlx5e_priv *priv)
 {
 	mlx5i_destroy_flow_steering(priv);
 	mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
-	mlx5e_destroy_indirect_tirs(priv, true);
+	mlx5e_destroy_indirect_tirs(priv);
 	mlx5e_destroy_direct_rqts(priv, priv->direct_tir);
 	mlx5e_destroy_rqt(priv, &priv->indir_rqt);
 	mlx5e_close_drop_rq(&priv->drop_rq);
-- 
2.26.2


From 313161f57061bf43e4511e791c458f955c1007c2 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Wed, 29 Apr 2020 23:56:58 +0300
Subject: [PATCH 25/33] net/mlx5: Fix memory leak in mlx5_events_init

[ Upstream commit df14ad1eccb04a4a28c90389214dbacab085b244 ]

Fix memory leak in mlx5_events_init(), in case
create_single_thread_workqueue() fails, events
struct should be freed.

Fixes: 5d3c537f9070 ("net/mlx5: Handle event of power detection in the PCIE slot")
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/events.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c
index 8bcf3426b9c6..3ce17c3d7a00 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/events.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c
@@ -346,8 +346,10 @@ int mlx5_events_init(struct mlx5_core_dev *dev)
 	events->dev = dev;
 	dev->priv.events = events;
 	events->wq = create_singlethread_workqueue("mlx5_events");
-	if (!events->wq)
+	if (!events->wq) {
+		kfree(events);
 		return -ENOMEM;
+	}
 	INIT_WORK(&events->pcie_core_work, mlx5_pcie_event);
 
 	return 0;
-- 
2.26.2


From b9a3439cf2e0997b7aede3235ffdc3674572719f Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Tue, 7 Apr 2020 17:38:28 +0300
Subject: [PATCH 26/33] net/mlx5e: Update netdev txq on completions during
 closure

[ Upstream commit 5e911e2c06bd8c17df29147a5e2d4b17fafda024 ]

On sq closure when we free its descriptors, we should also update netdev
txq on completions which would not arrive. Otherwise if we reopen sqs
and attach them back, for example on fw fatal recovery flow, we may get
tx timeout.

Fixes: 29429f3300a3 ("net/mlx5e: Timeout if SQ doesn't flush during close")
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index ee60383adc5b..c2b801b435cf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -538,10 +538,9 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq)
 {
 	struct mlx5e_tx_wqe_info *wi;
+	u32 dma_fifo_cc, nbytes = 0;
+	u16 ci, sqcc, npkts = 0;
 	struct sk_buff *skb;
-	u32 dma_fifo_cc;
-	u16 sqcc;
-	u16 ci;
 	int i;
 
 	sqcc = sq->cc;
@@ -566,11 +565,15 @@ void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq)
 		}
 
 		dev_kfree_skb_any(skb);
+		npkts++;
+		nbytes += wi->num_bytes;
 		sqcc += wi->num_wqebbs;
 	}
 
 	sq->dma_fifo_cc = dma_fifo_cc;
 	sq->cc = sqcc;
+
+	netdev_tx_completed_queue(sq->txq, npkts, nbytes);
 }
 
 #ifdef CONFIG_MLX5_CORE_IPOIB
-- 
2.26.2


From 750b0e055feb546fed5ffb7649f32cb254e72567 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@mellanox.com>
Date: Wed, 6 May 2020 14:52:04 +0300
Subject: [PATCH 27/33] net/mlx5: Fix error flow in case of function_setup
 failure

[ Upstream commit 4f7400d5cbaef676e00cdffb0565bf731c6bb09e ]

Currently, if an error occurred during mlx5_function_setup(), we
keep dev->state as DEVICE_STATE_UP.
Fixing it by adding a goto label.

Fixes: e161105e58da ("net/mlx5: Function setup/teardown procedures")
Signed-off-by: Shay Drory <shayd@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index f554cfddcf4e..7d67268ff686 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1179,7 +1179,7 @@ int mlx5_load_one(struct mlx5_core_dev *dev, bool boot)
 
 	err = mlx5_function_setup(dev, boot);
 	if (err)
-		goto out;
+		goto err_function;
 
 	if (boot) {
 		err = mlx5_init_once(dev);
@@ -1225,6 +1225,7 @@ int mlx5_load_one(struct mlx5_core_dev *dev, bool boot)
 		mlx5_cleanup_once(dev);
 function_teardown:
 	mlx5_function_teardown(dev, boot);
+err_function:
 	dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
 	mutex_unlock(&dev->intf_state_mutex);
 
-- 
2.26.2


From 3825969892fd39d05ffc7e970b2255b5e134c659 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Tue, 19 May 2020 22:49:28 -0600
Subject: [PATCH 28/33] wireguard: noise: read preshared key while taking lock

[ Upstream commit bc67d371256f5c47d824e2eec51e46c8d62d022e ]

Prior we read the preshared key after dropping the handshake lock, which
isn't an actual crypto issue if it races, but it's still not quite
correct. So copy that part of the state into a temporary like we do with
the rest of the handshake state variables. Then we can release the lock,
operate on the temporary, and zero it out at the end of the function. In
performance tests, the impact of this was entirely unnoticable, probably
because those bytes are coming from the same cacheline as other things
that are being copied out in the same manner.

Reported-by: Matt Dunwoodie <ncon@noconroy.net>
Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wireguard/noise.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireguard/noise.c b/drivers/net/wireguard/noise.c
index 708dc61c974f..07eb438a6dee 100644
--- a/drivers/net/wireguard/noise.c
+++ b/drivers/net/wireguard/noise.c
@@ -715,6 +715,7 @@ wg_noise_handshake_consume_response(struct message_handshake_response *src,
 	u8 e[NOISE_PUBLIC_KEY_LEN];
 	u8 ephemeral_private[NOISE_PUBLIC_KEY_LEN];
 	u8 static_private[NOISE_PUBLIC_KEY_LEN];
+	u8 preshared_key[NOISE_SYMMETRIC_KEY_LEN];
 
 	down_read(&wg->static_identity.lock);
 
@@ -733,6 +734,8 @@ wg_noise_handshake_consume_response(struct message_handshake_response *src,
 	memcpy(chaining_key, handshake->chaining_key, NOISE_HASH_LEN);
 	memcpy(ephemeral_private, handshake->ephemeral_private,
 	       NOISE_PUBLIC_KEY_LEN);
+	memcpy(preshared_key, handshake->preshared_key,
+	       NOISE_SYMMETRIC_KEY_LEN);
 	up_read(&handshake->lock);
 
 	if (state != HANDSHAKE_CREATED_INITIATION)
@@ -750,7 +753,7 @@ wg_noise_handshake_consume_response(struct message_handshake_response *src,
 		goto fail;
 
 	/* psk */
-	mix_psk(chaining_key, hash, key, handshake->preshared_key);
+	mix_psk(chaining_key, hash, key, preshared_key);
 
 	/* {} */
 	if (!message_decrypt(NULL, src->encrypted_nothing,
@@ -783,6 +786,7 @@ wg_noise_handshake_consume_response(struct message_handshake_response *src,
 	memzero_explicit(chaining_key, NOISE_HASH_LEN);
 	memzero_explicit(ephemeral_private, NOISE_PUBLIC_KEY_LEN);
 	memzero_explicit(static_private, NOISE_PUBLIC_KEY_LEN);
+	memzero_explicit(preshared_key, NOISE_SYMMETRIC_KEY_LEN);
 	up_read(&wg->static_identity.lock);
 	return ret_peer;
 }
-- 
2.26.2


From 1c6c17a3354d4fe8181416c61f19dbdff1aa2764 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Tue, 19 May 2020 22:49:29 -0600
Subject: [PATCH 29/33] wireguard: queueing: preserve flow hash across packet
 scrubbing
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit c78a0b4a78839d572d8a80f6a62221c0d7843135 ]

It's important that we clear most header fields during encapsulation and
decapsulation, because the packet is substantially changed, and we don't
want any info leak or logic bug due to an accidental correlation. But,
for encapsulation, it's wrong to clear skb->hash, since it's used by
fq_codel and flow dissection in general. Without it, classification does
not proceed as usual. This change might make it easier to estimate the
number of innerflows by examining clustering of out of order packets,
but this shouldn't open up anything that can't already be inferred
otherwise (e.g. syn packet size inference), and fq_codel can be disabled
anyway.

Furthermore, it might be the case that the hash isn't used or queried at
all until after wireguard transmits the encrypted UDP packet, which
means skb->hash might still be zero at this point, and thus no hash
taken over the inner packet data. In order to address this situation, we
force a calculation of skb->hash before encrypting packet data.

Of course this means that fq_codel might transmit packets slightly more
out of order than usual. Toke did some testing on beefy machines with
high quantities of parallel flows and found that increasing the
reply-attack counter to 8192 takes care of the most pathological cases
pretty well.

Reported-by: Dave Taht <dave.taht@gmail.com>
Reviewed-and-tested-by: Toke Høiland-Jørgensen <toke@toke.dk>
Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wireguard/messages.h |  2 +-
 drivers/net/wireguard/queueing.h | 10 +++++++++-
 drivers/net/wireguard/receive.c  |  2 +-
 drivers/net/wireguard/send.c     |  7 ++++++-
 4 files changed, 17 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireguard/messages.h b/drivers/net/wireguard/messages.h
index b8a7b9ce32ba..208da72673fc 100644
--- a/drivers/net/wireguard/messages.h
+++ b/drivers/net/wireguard/messages.h
@@ -32,7 +32,7 @@ enum cookie_values {
 };
 
 enum counter_values {
-	COUNTER_BITS_TOTAL = 2048,
+	COUNTER_BITS_TOTAL = 8192,
 	COUNTER_REDUNDANT_BITS = BITS_PER_LONG,
 	COUNTER_WINDOW_SIZE = COUNTER_BITS_TOTAL - COUNTER_REDUNDANT_BITS
 };
diff --git a/drivers/net/wireguard/queueing.h b/drivers/net/wireguard/queueing.h
index 3432232afe06..c58df439dbbe 100644
--- a/drivers/net/wireguard/queueing.h
+++ b/drivers/net/wireguard/queueing.h
@@ -87,12 +87,20 @@ static inline bool wg_check_packet_protocol(struct sk_buff *skb)
 	return real_protocol && skb->protocol == real_protocol;
 }
 
-static inline void wg_reset_packet(struct sk_buff *skb)
+static inline void wg_reset_packet(struct sk_buff *skb, bool encapsulating)
 {
+	u8 l4_hash = skb->l4_hash;
+	u8 sw_hash = skb->sw_hash;
+	u32 hash = skb->hash;
 	skb_scrub_packet(skb, true);
 	memset(&skb->headers_start, 0,
 	       offsetof(struct sk_buff, headers_end) -
 		       offsetof(struct sk_buff, headers_start));
+	if (encapsulating) {
+		skb->l4_hash = l4_hash;
+		skb->sw_hash = sw_hash;
+		skb->hash = hash;
+	}
 	skb->queue_mapping = 0;
 	skb->nohdr = 0;
 	skb->peeked = 0;
diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c
index 2566e13a292d..758d6a019184 100644
--- a/drivers/net/wireguard/receive.c
+++ b/drivers/net/wireguard/receive.c
@@ -485,7 +485,7 @@ int wg_packet_rx_poll(struct napi_struct *napi, int budget)
 		if (unlikely(wg_socket_endpoint_from_skb(&endpoint, skb)))
 			goto next;
 
-		wg_reset_packet(skb);
+		wg_reset_packet(skb, false);
 		wg_packet_consume_data_done(peer, skb, &endpoint);
 		free = false;
 
diff --git a/drivers/net/wireguard/send.c b/drivers/net/wireguard/send.c
index e8a7d0a0cb88..0d64a7531f64 100644
--- a/drivers/net/wireguard/send.c
+++ b/drivers/net/wireguard/send.c
@@ -170,6 +170,11 @@ static bool encrypt_packet(struct sk_buff *skb, struct noise_keypair *keypair)
 	struct sk_buff *trailer;
 	int num_frags;
 
+	/* Force hash calculation before encryption so that flow analysis is
+	 * consistent over the inner packet.
+	 */
+	skb_get_hash(skb);
+
 	/* Calculate lengths. */
 	padding_len = calculate_skb_padding(skb);
 	trailer_len = padding_len + noise_encrypted_len(0);
@@ -298,7 +303,7 @@ void wg_packet_encrypt_worker(struct work_struct *work)
 		skb_list_walk_safe(first, skb, next) {
 			if (likely(encrypt_packet(skb,
 					PACKET_CB(first)->keypair))) {
-				wg_reset_packet(skb);
+				wg_reset_packet(skb, true);
 			} else {
 				state = PACKET_STATE_DEAD;
 				break;
-- 
2.26.2


From ebae4148018ce6fb3145f1f6971869450d961dc8 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Tue, 19 May 2020 22:49:30 -0600
Subject: [PATCH 30/33] wireguard: noise: separate receive counter from send
 counter

[ Upstream commit a9e90d9931f3a474f04bab782ccd9d77904941e9 ]

In "wireguard: queueing: preserve flow hash across packet scrubbing", we
were required to slightly increase the size of the receive replay
counter to something still fairly small, but an increase nonetheless.
It turns out that we can recoup some of the additional memory overhead
by splitting up the prior union type into two distinct types. Before, we
used the same "noise_counter" union for both sending and receiving, with
sending just using a simple atomic64_t, while receiving used the full
replay counter checker. This meant that most of the memory being
allocated for the sending counter was being wasted. Since the old
"noise_counter" type increased in size in the prior commit, now is a
good time to split up that union type into a distinct "noise_replay_
counter" for receiving and a boring atomic64_t for sending, each using
neither more nor less memory than required.

Also, since sometimes the replay counter is accessed without
necessitating additional accesses to the bitmap, we can reduce cache
misses by hoisting the always-necessary lock above the bitmap in the
struct layout. We also change a "noise_replay_counter" stack allocation
to kmalloc in a -DDEBUG selftest so that KASAN doesn't trigger a stack
frame warning.

All and all, removing a bit of abstraction in this commit makes the code
simpler and smaller, in addition to the motivating memory usage
recuperation. For example, passing around raw "noise_symmetric_key"
structs is something that really only makes sense within noise.c, in the
one place where the sending and receiving keys can safely be thought of
as the same type of object; subsequent to that, it's important that we
uniformly access these through keypair->{sending,receiving}, where their
distinct roles are always made explicit. So this patch allows us to draw
that distinction clearly as well.

Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wireguard/noise.c            | 16 +++------
 drivers/net/wireguard/noise.h            | 14 ++++----
 drivers/net/wireguard/receive.c          | 42 ++++++++++++------------
 drivers/net/wireguard/selftest/counter.c | 17 +++++++---
 drivers/net/wireguard/send.c             | 12 +++----
 5 files changed, 48 insertions(+), 53 deletions(-)

diff --git a/drivers/net/wireguard/noise.c b/drivers/net/wireguard/noise.c
index 07eb438a6dee..626433690abb 100644
--- a/drivers/net/wireguard/noise.c
+++ b/drivers/net/wireguard/noise.c
@@ -104,6 +104,7 @@ static struct noise_keypair *keypair_create(struct wg_peer *peer)
 
 	if (unlikely(!keypair))
 		return NULL;
+	spin_lock_init(&keypair->receiving_counter.lock);
 	keypair->internal_id = atomic64_inc_return(&keypair_counter);
 	keypair->entry.type = INDEX_HASHTABLE_KEYPAIR;
 	keypair->entry.peer = peer;
@@ -358,25 +359,16 @@ static void kdf(u8 *first_dst, u8 *second_dst, u8 *third_dst, const u8 *data,
 	memzero_explicit(output, BLAKE2S_HASH_SIZE + 1);
 }
 
-static void symmetric_key_init(struct noise_symmetric_key *key)
-{
-	spin_lock_init(&key->counter.receive.lock);
-	atomic64_set(&key->counter.counter, 0);
-	memset(key->counter.receive.backtrack, 0,
-	       sizeof(key->counter.receive.backtrack));
-	key->birthdate = ktime_get_coarse_boottime_ns();
-	key->is_valid = true;
-}
-
 static void derive_keys(struct noise_symmetric_key *first_dst,
 			struct noise_symmetric_key *second_dst,
 			const u8 chaining_key[NOISE_HASH_LEN])
 {
+	u64 birthdate = ktime_get_coarse_boottime_ns();
 	kdf(first_dst->key, second_dst->key, NULL, NULL,
 	    NOISE_SYMMETRIC_KEY_LEN, NOISE_SYMMETRIC_KEY_LEN, 0, 0,
 	    chaining_key);
-	symmetric_key_init(first_dst);
-	symmetric_key_init(second_dst);
+	first_dst->birthdate = second_dst->birthdate = birthdate;
+	first_dst->is_valid = second_dst->is_valid = true;
 }
 
 static bool __must_check mix_dh(u8 chaining_key[NOISE_HASH_LEN],
diff --git a/drivers/net/wireguard/noise.h b/drivers/net/wireguard/noise.h
index f532d59d3f19..c527253dba80 100644
--- a/drivers/net/wireguard/noise.h
+++ b/drivers/net/wireguard/noise.h
@@ -15,18 +15,14 @@
 #include <linux/mutex.h>
 #include <linux/kref.h>
 
-union noise_counter {
-	struct {
-		u64 counter;
-		unsigned long backtrack[COUNTER_BITS_TOTAL / BITS_PER_LONG];
-		spinlock_t lock;
-	} receive;
-	atomic64_t counter;
+struct noise_replay_counter {
+	u64 counter;
+	spinlock_t lock;
+	unsigned long backtrack[COUNTER_BITS_TOTAL / BITS_PER_LONG];
 };
 
 struct noise_symmetric_key {
 	u8 key[NOISE_SYMMETRIC_KEY_LEN];
-	union noise_counter counter;
 	u64 birthdate;
 	bool is_valid;
 };
@@ -34,7 +30,9 @@ struct noise_symmetric_key {
 struct noise_keypair {
 	struct index_hashtable_entry entry;
 	struct noise_symmetric_key sending;
+	atomic64_t sending_counter;
 	struct noise_symmetric_key receiving;
+	struct noise_replay_counter receiving_counter;
 	__le32 remote_index;
 	bool i_am_the_initiator;
 	struct kref refcount;
diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c
index 758d6a019184..474bb69f0e1b 100644
--- a/drivers/net/wireguard/receive.c
+++ b/drivers/net/wireguard/receive.c
@@ -246,20 +246,20 @@ static void keep_key_fresh(struct wg_peer *peer)
 	}
 }
 
-static bool decrypt_packet(struct sk_buff *skb, struct noise_symmetric_key *key)
+static bool decrypt_packet(struct sk_buff *skb, struct noise_keypair *keypair)
 {
 	struct scatterlist sg[MAX_SKB_FRAGS + 8];
 	struct sk_buff *trailer;
 	unsigned int offset;
 	int num_frags;
 
-	if (unlikely(!key))
+	if (unlikely(!keypair))
 		return false;
 
-	if (unlikely(!READ_ONCE(key->is_valid) ||
-		  wg_birthdate_has_expired(key->birthdate, REJECT_AFTER_TIME) ||
-		  key->counter.receive.counter >= REJECT_AFTER_MESSAGES)) {
-		WRITE_ONCE(key->is_valid, false);
+	if (unlikely(!READ_ONCE(keypair->receiving.is_valid) ||
+		  wg_birthdate_has_expired(keypair->receiving.birthdate, REJECT_AFTER_TIME) ||
+		  keypair->receiving_counter.counter >= REJECT_AFTER_MESSAGES)) {
+		WRITE_ONCE(keypair->receiving.is_valid, false);
 		return false;
 	}
 
@@ -284,7 +284,7 @@ static bool decrypt_packet(struct sk_buff *skb, struct noise_symmetric_key *key)
 
 	if (!chacha20poly1305_decrypt_sg_inplace(sg, skb->len, NULL, 0,
 					         PACKET_CB(skb)->nonce,
-						 key->key))
+						 keypair->receiving.key))
 		return false;
 
 	/* Another ugly situation of pushing and pulling the header so as to
@@ -299,41 +299,41 @@ static bool decrypt_packet(struct sk_buff *skb, struct noise_symmetric_key *key)
 }
 
 /* This is RFC6479, a replay detection bitmap algorithm that avoids bitshifts */
-static bool counter_validate(union noise_counter *counter, u64 their_counter)
+static bool counter_validate(struct noise_replay_counter *counter, u64 their_counter)
 {
 	unsigned long index, index_current, top, i;
 	bool ret = false;
 
-	spin_lock_bh(&counter->receive.lock);
+	spin_lock_bh(&counter->lock);
 
-	if (unlikely(counter->receive.counter >= REJECT_AFTER_MESSAGES + 1 ||
+	if (unlikely(counter->counter >= REJECT_AFTER_MESSAGES + 1 ||
 		     their_counter >= REJECT_AFTER_MESSAGES))
 		goto out;
 
 	++their_counter;
 
 	if (unlikely((COUNTER_WINDOW_SIZE + their_counter) <
-		     counter->receive.counter))
+		     counter->counter))
 		goto out;
 
 	index = their_counter >> ilog2(BITS_PER_LONG);
 
-	if (likely(their_counter > counter->receive.counter)) {
-		index_current = counter->receive.counter >> ilog2(BITS_PER_LONG);
+	if (likely(their_counter > counter->counter)) {
+		index_current = counter->counter >> ilog2(BITS_PER_LONG);
 		top = min_t(unsigned long, index - index_current,
 			    COUNTER_BITS_TOTAL / BITS_PER_LONG);
 		for (i = 1; i <= top; ++i)
-			counter->receive.backtrack[(i + index_current) &
+			counter->backtrack[(i + index_current) &
 				((COUNTER_BITS_TOTAL / BITS_PER_LONG) - 1)] = 0;
-		counter->receive.counter = their_counter;
+		counter->counter = their_counter;
 	}
 
 	index &= (COUNTER_BITS_TOTAL / BITS_PER_LONG) - 1;
 	ret = !test_and_set_bit(their_counter & (BITS_PER_LONG - 1),
-				&counter->receive.backtrack[index]);
+				&counter->backtrack[index]);
 
 out:
-	spin_unlock_bh(&counter->receive.lock);
+	spin_unlock_bh(&counter->lock);
 	return ret;
 }
 
@@ -473,12 +473,12 @@ int wg_packet_rx_poll(struct napi_struct *napi, int budget)
 		if (unlikely(state != PACKET_STATE_CRYPTED))
 			goto next;
 
-		if (unlikely(!counter_validate(&keypair->receiving.counter,
+		if (unlikely(!counter_validate(&keypair->receiving_counter,
 					       PACKET_CB(skb)->nonce))) {
 			net_dbg_ratelimited("%s: Packet has invalid nonce %llu (max %llu)\n",
 					    peer->device->dev->name,
 					    PACKET_CB(skb)->nonce,
-					    keypair->receiving.counter.receive.counter);
+					    keypair->receiving_counter.counter);
 			goto next;
 		}
 
@@ -512,8 +512,8 @@ void wg_packet_decrypt_worker(struct work_struct *work)
 	struct sk_buff *skb;
 
 	while ((skb = ptr_ring_consume_bh(&queue->ring)) != NULL) {
-		enum packet_state state = likely(decrypt_packet(skb,
-				&PACKET_CB(skb)->keypair->receiving)) ?
+		enum packet_state state =
+			likely(decrypt_packet(skb, PACKET_CB(skb)->keypair)) ?
 				PACKET_STATE_CRYPTED : PACKET_STATE_DEAD;
 		wg_queue_enqueue_per_peer_napi(skb, state);
 		if (need_resched())
diff --git a/drivers/net/wireguard/selftest/counter.c b/drivers/net/wireguard/selftest/counter.c
index f4fbb9072ed7..ec3c156bf91b 100644
--- a/drivers/net/wireguard/selftest/counter.c
+++ b/drivers/net/wireguard/selftest/counter.c
@@ -6,18 +6,24 @@
 #ifdef DEBUG
 bool __init wg_packet_counter_selftest(void)
 {
+	struct noise_replay_counter *counter;
 	unsigned int test_num = 0, i;
-	union noise_counter counter;
 	bool success = true;
 
-#define T_INIT do {                                               \
-		memset(&counter, 0, sizeof(union noise_counter)); \
-		spin_lock_init(&counter.receive.lock);            \
+	counter = kmalloc(sizeof(*counter), GFP_KERNEL);
+	if (unlikely(!counter)) {
+		pr_err("nonce counter self-test malloc: FAIL\n");
+		return false;
+	}
+
+#define T_INIT do {                                    \
+		memset(counter, 0, sizeof(*counter));  \
+		spin_lock_init(&counter->lock);        \
 	} while (0)
 #define T_LIM (COUNTER_WINDOW_SIZE + 1)
 #define T(n, v) do {                                                  \
 		++test_num;                                           \
-		if (counter_validate(&counter, n) != (v)) {           \
+		if (counter_validate(counter, n) != (v)) {            \
 			pr_err("nonce counter self-test %u: FAIL\n",  \
 			       test_num);                             \
 			success = false;                              \
@@ -99,6 +105,7 @@ bool __init wg_packet_counter_selftest(void)
 
 	if (success)
 		pr_info("nonce counter self-tests: pass\n");
+	kfree(counter);
 	return success;
 }
 #endif
diff --git a/drivers/net/wireguard/send.c b/drivers/net/wireguard/send.c
index 0d64a7531f64..485d5d7a217b 100644
--- a/drivers/net/wireguard/send.c
+++ b/drivers/net/wireguard/send.c
@@ -129,7 +129,7 @@ static void keep_key_fresh(struct wg_peer *peer)
 	rcu_read_lock_bh();
 	keypair = rcu_dereference_bh(peer->keypairs.current_keypair);
 	if (likely(keypair && READ_ONCE(keypair->sending.is_valid)) &&
-	    (unlikely(atomic64_read(&keypair->sending.counter.counter) >
+	    (unlikely(atomic64_read(&keypair->sending_counter) >
 		      REKEY_AFTER_MESSAGES) ||
 	     (keypair->i_am_the_initiator &&
 	      unlikely(wg_birthdate_has_expired(keypair->sending.birthdate,
@@ -353,7 +353,6 @@ void wg_packet_purge_staged_packets(struct wg_peer *peer)
 
 void wg_packet_send_staged_packets(struct wg_peer *peer)
 {
-	struct noise_symmetric_key *key;
 	struct noise_keypair *keypair;
 	struct sk_buff_head packets;
 	struct sk_buff *skb;
@@ -373,10 +372,9 @@ void wg_packet_send_staged_packets(struct wg_peer *peer)
 	rcu_read_unlock_bh();
 	if (unlikely(!keypair))
 		goto out_nokey;
-	key = &keypair->sending;
-	if (unlikely(!READ_ONCE(key->is_valid)))
+	if (unlikely(!READ_ONCE(keypair->sending.is_valid)))
 		goto out_nokey;
-	if (unlikely(wg_birthdate_has_expired(key->birthdate,
+	if (unlikely(wg_birthdate_has_expired(keypair->sending.birthdate,
 					      REJECT_AFTER_TIME)))
 		goto out_invalid;
 
@@ -391,7 +389,7 @@ void wg_packet_send_staged_packets(struct wg_peer *peer)
 		 */
 		PACKET_CB(skb)->ds = ip_tunnel_ecn_encap(0, ip_hdr(skb), skb);
 		PACKET_CB(skb)->nonce =
-				atomic64_inc_return(&key->counter.counter) - 1;
+				atomic64_inc_return(&keypair->sending_counter) - 1;
 		if (unlikely(PACKET_CB(skb)->nonce >= REJECT_AFTER_MESSAGES))
 			goto out_invalid;
 	}
@@ -403,7 +401,7 @@ void wg_packet_send_staged_packets(struct wg_peer *peer)
 	return;
 
 out_invalid:
-	WRITE_ONCE(key->is_valid, false);
+	WRITE_ONCE(keypair->sending.is_valid, false);
 out_nokey:
 	wg_noise_keypair_put(keypair, false);
 
-- 
2.26.2


From f2cb901eebb80df3a5a811bc2d9cea3e8473983a Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 21 May 2020 22:03:08 +0200
Subject: [PATCH 31/33] r8169: fix OCP access on RTL8117

[ Upstream commit 561535b0f23961ced071b82575d5e83e6351a814 ]

According to r8168 vendor driver DASHv3 chips like RTL8168fp/RTL8117
need a special addressing for OCP access.
Fix is compile-tested only due to missing test hardware.

Fixes: 1287723aa139 ("r8169: add support for RTL8117")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 07a6b609f741..6e4fe2566f6b 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -1044,6 +1044,13 @@ static u16 rtl_ephy_read(struct rtl8169_private *tp, int reg_addr)
 		RTL_R32(tp, EPHYAR) & EPHYAR_DATA_MASK : ~0;
 }
 
+static void r8168fp_adjust_ocp_cmd(struct rtl8169_private *tp, u32 *cmd, int type)
+{
+	/* based on RTL8168FP_OOBMAC_BASE in vendor driver */
+	if (tp->mac_version == RTL_GIGA_MAC_VER_52 && type == ERIAR_OOB)
+		*cmd |= 0x7f0 << 18;
+}
+
 DECLARE_RTL_COND(rtl_eriar_cond)
 {
 	return RTL_R32(tp, ERIAR) & ERIAR_FLAG;
@@ -1052,9 +1059,12 @@ DECLARE_RTL_COND(rtl_eriar_cond)
 static void _rtl_eri_write(struct rtl8169_private *tp, int addr, u32 mask,
 			   u32 val, int type)
 {
+	u32 cmd = ERIAR_WRITE_CMD | type | mask | addr;
+
 	BUG_ON((addr & 3) || (mask == 0));
 	RTL_W32(tp, ERIDR, val);
-	RTL_W32(tp, ERIAR, ERIAR_WRITE_CMD | type | mask | addr);
+	r8168fp_adjust_ocp_cmd(tp, &cmd, type);
+	RTL_W32(tp, ERIAR, cmd);
 
 	rtl_udelay_loop_wait_low(tp, &rtl_eriar_cond, 100, 100);
 }
@@ -1067,7 +1077,10 @@ static void rtl_eri_write(struct rtl8169_private *tp, int addr, u32 mask,
 
 static u32 _rtl_eri_read(struct rtl8169_private *tp, int addr, int type)
 {
-	RTL_W32(tp, ERIAR, ERIAR_READ_CMD | type | ERIAR_MASK_1111 | addr);
+	u32 cmd = ERIAR_READ_CMD | type | ERIAR_MASK_1111 | addr;
+
+	r8168fp_adjust_ocp_cmd(tp, &cmd, type);
+	RTL_W32(tp, ERIAR, cmd);
 
 	return rtl_udelay_loop_wait_high(tp, &rtl_eriar_cond, 100, 100) ?
 		RTL_R32(tp, ERIDR) : ~0;
-- 
2.26.2


From 4f8774f3f1cd649fac899418b0315b5791e2aa3e Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Wed, 18 Mar 2020 21:44:32 +0200
Subject: [PATCH 32/33] net/mlx5: Fix a race when moving command interface to
 events mode

[ Upstream commit d43b7007dbd1195a5b6b83213e49b1516aaf6f5e ]

After driver creates (via FW command) an EQ for commands, the driver will
be informed on new commands completion by EQE. However, due to a race in
driver's internal command mode metadata update, some new commands will
still be miss-handled by driver as if we are in polling mode. Such commands
can get two non forced completion, leading to already freed command entry
access.

CREATE_EQ command, that maps EQ to the command queue must be posted to the
command queue while it is empty and no other command should be posted.

Add SW mechanism that once the CREATE_EQ command is about to be executed,
all other commands will return error without being sent to the FW. Allow
sending other commands only after successfully changing the driver's
internal command mode metadata.
We can safely return error to all other commands while creating the command
EQ, as all other commands might be sent from the user/application during
driver load. Application can rerun them later after driver's load was
finished.

Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 35 ++++++++++++++++---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c  |  3 ++
 include/linux/mlx5/driver.h                   |  6 ++++
 3 files changed, 40 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index d695b75bc0af..2f3cafdc3b1f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -848,6 +848,14 @@ static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg);
 static void mlx5_free_cmd_msg(struct mlx5_core_dev *dev,
 			      struct mlx5_cmd_msg *msg);
 
+static bool opcode_allowed(struct mlx5_cmd *cmd, u16 opcode)
+{
+	if (cmd->allowed_opcode == CMD_ALLOWED_OPCODE_ALL)
+		return true;
+
+	return cmd->allowed_opcode == opcode;
+}
+
 static void cmd_work_handler(struct work_struct *work)
 {
 	struct mlx5_cmd_work_ent *ent = container_of(work, struct mlx5_cmd_work_ent, work);
@@ -914,7 +922,8 @@ static void cmd_work_handler(struct work_struct *work)
 
 	/* Skip sending command to fw if internal error */
 	if (pci_channel_offline(dev->pdev) ||
-	    dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
+	    dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR ||
+	    !opcode_allowed(&dev->cmd, ent->op)) {
 		u8 status = 0;
 		u32 drv_synd;
 
@@ -1405,6 +1414,22 @@ static void create_debugfs_files(struct mlx5_core_dev *dev)
 	mlx5_cmdif_debugfs_init(dev);
 }
 
+void mlx5_cmd_allowed_opcode(struct mlx5_core_dev *dev, u16 opcode)
+{
+	struct mlx5_cmd *cmd = &dev->cmd;
+	int i;
+
+	for (i = 0; i < cmd->max_reg_cmds; i++)
+		down(&cmd->sem);
+	down(&cmd->pages_sem);
+
+	cmd->allowed_opcode = opcode;
+
+	up(&cmd->pages_sem);
+	for (i = 0; i < cmd->max_reg_cmds; i++)
+		up(&cmd->sem);
+}
+
 static void mlx5_cmd_change_mod(struct mlx5_core_dev *dev, int mode)
 {
 	struct mlx5_cmd *cmd = &dev->cmd;
@@ -1681,12 +1706,13 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 	int err;
 	u8 status = 0;
 	u32 drv_synd;
+	u16 opcode;
 	u8 token;
 
+	opcode = MLX5_GET(mbox_in, in, opcode);
 	if (pci_channel_offline(dev->pdev) ||
-	    dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
-		u16 opcode = MLX5_GET(mbox_in, in, opcode);
-
+	    dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR ||
+	    !opcode_allowed(&dev->cmd, opcode)) {
 		err = mlx5_internal_err_ret_value(dev, opcode, &drv_synd, &status);
 		MLX5_SET(mbox_out, out, status, status);
 		MLX5_SET(mbox_out, out, syndrome, drv_synd);
@@ -1988,6 +2014,7 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
 	mlx5_core_dbg(dev, "descriptor at dma 0x%llx\n", (unsigned long long)(cmd->dma));
 
 	cmd->mode = CMD_MODE_POLLING;
+	cmd->allowed_opcode = CMD_ALLOWED_OPCODE_ALL;
 
 	create_msg_cache(dev);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index cccea3a8eddd..ce6c621af043 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -611,11 +611,13 @@ static int create_async_eqs(struct mlx5_core_dev *dev)
 		.nent = MLX5_NUM_CMD_EQE,
 		.mask[0] = 1ull << MLX5_EVENT_TYPE_CMD,
 	};
+	mlx5_cmd_allowed_opcode(dev, MLX5_CMD_OP_CREATE_EQ);
 	err = setup_async_eq(dev, &table->cmd_eq, &param, "cmd");
 	if (err)
 		goto err1;
 
 	mlx5_cmd_use_events(dev);
+	mlx5_cmd_allowed_opcode(dev, CMD_ALLOWED_OPCODE_ALL);
 
 	param = (struct mlx5_eq_param) {
 		.irq_index = 0,
@@ -645,6 +647,7 @@ static int create_async_eqs(struct mlx5_core_dev *dev)
 	mlx5_cmd_use_polling(dev);
 	cleanup_async_eq(dev, &table->cmd_eq, "cmd");
 err1:
+	mlx5_cmd_allowed_opcode(dev, CMD_ALLOWED_OPCODE_ALL);
 	mlx5_eq_notifier_unregister(dev, &table->cq_err_nb);
 	return err;
 }
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index b596353a3a12..6050264ebde1 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -301,6 +301,7 @@ struct mlx5_cmd {
 	struct semaphore sem;
 	struct semaphore pages_sem;
 	int	mode;
+	u16     allowed_opcode;
 	struct mlx5_cmd_work_ent *ent_arr[MLX5_MAX_COMMANDS];
 	struct dma_pool *pool;
 	struct mlx5_cmd_debug dbg;
@@ -893,10 +894,15 @@ mlx5_frag_buf_get_idx_last_contig_stride(struct mlx5_frag_buf_ctrl *fbc, u32 ix)
 	return min_t(u32, last_frag_stride_idx - fbc->strides_offset, fbc->sz_m1);
 }
 
+enum {
+	CMD_ALLOWED_OPCODE_ALL,
+};
+
 int mlx5_cmd_init(struct mlx5_core_dev *dev);
 void mlx5_cmd_cleanup(struct mlx5_core_dev *dev);
 void mlx5_cmd_use_events(struct mlx5_core_dev *dev);
 void mlx5_cmd_use_polling(struct mlx5_core_dev *dev);
+void mlx5_cmd_allowed_opcode(struct mlx5_core_dev *dev, u16 opcode);
 
 struct mlx5_async_ctx {
 	struct mlx5_core_dev *dev;
-- 
2.26.2


From c92d9bbc82fb713262a39858154e242b54f8017c Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@mellanox.com>
Date: Mon, 11 May 2020 16:32:09 +0300
Subject: [PATCH 33/33] net/mlx5: Fix cleaning unmanaged flow tables

[ Upstream commit aee37f3d940ca732df71c3df49347bccaafc0b24 ]

Unmanaged flow tables doesn't have a parent and tree_put_node()
assume there is always a parent if cleaning is needed. fix that.

Fixes: 5281a0c90919 ("net/mlx5: fs_core: Introduce unmanaged flow tables")
Signed-off-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Reviewed-by: Paul Blakey <paulb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 9dc24241dc91..cdc566768a07 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -323,14 +323,13 @@ static void tree_put_node(struct fs_node *node, bool locked)
 		if (node->del_hw_func)
 			node->del_hw_func(node);
 		if (parent_node) {
-			/* Only root namespace doesn't have parent and we just
-			 * need to free its node.
-			 */
 			down_write_ref_node(parent_node, locked);
 			list_del_init(&node->list);
 			if (node->del_sw_func)
 				node->del_sw_func(node);
 			up_write_ref_node(parent_node, locked);
+		} else if (node->del_sw_func) {
+			node->del_sw_func(node);
 		} else {
 			kfree(node);
 		}
@@ -447,8 +446,10 @@ static void del_sw_flow_table(struct fs_node *node)
 	fs_get_obj(ft, node);
 
 	rhltable_destroy(&ft->fgs_hash);
-	fs_get_obj(prio, ft->node.parent);
-	prio->num_ft--;
+	if (ft->node.parent) {
+		fs_get_obj(prio, ft->node.parent);
+		prio->num_ft--;
+	}
 	kfree(ft);
 }
 
-- 
2.26.2

Re: [PATCHES] Networking

[Greg KH]

On Tue, May 26, 2020 at 11:16:52PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v5.4 and
> v5.6 -stable, respectively.

All queued up now, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 105 bytes --]


Please queue up the following networking bug fixes for v5.4 and
v5.6 -stable, respectively.

Thank you.

[-- Attachment #2: net_54.mbox --]
[-- Type: Application/Octet-Stream, Size: 30924 bytes --]

From 2fe4890ae9c724c2885808447d0405920a3959ab Mon Sep 17 00:00:00 2001
From: Yang Yingliang <yangyingliang@huawei.com>
Date: Sat, 30 May 2020 11:34:33 +0800
Subject: [PATCH 01/11] devinet: fix memleak in inetdev_init()

[ Upstream commit 1b49cd71b52403822731dc9f283185d1da355f97 ]

When devinet_sysctl_register() failed, the memory allocated
in neigh_parms_alloc() should be freed.

Fixes: 20e61da7ffcf ("ipv4: fail early when creating netdev named all or default")
Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/devinet.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 458dc6eb5a68..a27d034c85cc 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -276,6 +276,7 @@ static struct in_device *inetdev_init(struct net_device *dev)
 	err = devinet_sysctl_register(in_dev);
 	if (err) {
 		in_dev->dead = 1;
+		neigh_parms_release(&arp_tbl, in_dev->arp_parms);
 		in_dev_put(in_dev);
 		in_dev = NULL;
 		goto out;
-- 
2.26.2


From ab67fe8d0897ebbdddf6a14e9997aff8eb525dee Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 29 May 2020 11:32:25 -0700
Subject: [PATCH 02/11] l2tp: add sk_family checks to l2tp_validate_socket

[ Upstream commit d9a81a225277686eb629938986d97629ea102633 ]

syzbot was able to trigger a crash after using an ISDN socket
and fool l2tp.

Fix this by making sure the UDP socket is of the proper family.

BUG: KASAN: slab-out-of-bounds in setup_udp_tunnel_sock+0x465/0x540 net/ipv4/udp_tunnel.c:78
Write of size 1 at addr ffff88808ed0c590 by task syz-executor.5/3018

CPU: 0 PID: 3018 Comm: syz-executor.5 Not tainted 5.7.0-rc6-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x188/0x20d lib/dump_stack.c:118
 print_address_description.constprop.0.cold+0xd3/0x413 mm/kasan/report.c:382
 __kasan_report.cold+0x20/0x38 mm/kasan/report.c:511
 kasan_report+0x33/0x50 mm/kasan/common.c:625
 setup_udp_tunnel_sock+0x465/0x540 net/ipv4/udp_tunnel.c:78
 l2tp_tunnel_register+0xb15/0xdd0 net/l2tp/l2tp_core.c:1523
 l2tp_nl_cmd_tunnel_create+0x4b2/0xa60 net/l2tp/l2tp_netlink.c:249
 genl_family_rcv_msg_doit net/netlink/genetlink.c:673 [inline]
 genl_family_rcv_msg net/netlink/genetlink.c:718 [inline]
 genl_rcv_msg+0x627/0xdf0 net/netlink/genetlink.c:735
 netlink_rcv_skb+0x15a/0x410 net/netlink/af_netlink.c:2469
 genl_rcv+0x24/0x40 net/netlink/genetlink.c:746
 netlink_unicast_kernel net/netlink/af_netlink.c:1303 [inline]
 netlink_unicast+0x537/0x740 net/netlink/af_netlink.c:1329
 netlink_sendmsg+0x882/0xe10 net/netlink/af_netlink.c:1918
 sock_sendmsg_nosec net/socket.c:652 [inline]
 sock_sendmsg+0xcf/0x120 net/socket.c:672
 ____sys_sendmsg+0x6e6/0x810 net/socket.c:2352
 ___sys_sendmsg+0x100/0x170 net/socket.c:2406
 __sys_sendmsg+0xe5/0x1b0 net/socket.c:2439
 do_syscall_64+0xf6/0x7d0 arch/x86/entry/common.c:295
 entry_SYSCALL_64_after_hwframe+0x49/0xb3
RIP: 0033:0x45ca29
Code: 0d b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 db b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007effe76edc78 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 00000000004fe1c0 RCX: 000000000045ca29
RDX: 0000000000000000 RSI: 0000000020000240 RDI: 0000000000000005
RBP: 000000000078bf00 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff
R13: 000000000000094e R14: 00000000004d5d00 R15: 00007effe76ee6d4

Allocated by task 3018:
 save_stack+0x1b/0x40 mm/kasan/common.c:49
 set_track mm/kasan/common.c:57 [inline]
 __kasan_kmalloc mm/kasan/common.c:495 [inline]
 __kasan_kmalloc.constprop.0+0xbf/0xd0 mm/kasan/common.c:468
 __do_kmalloc mm/slab.c:3656 [inline]
 __kmalloc+0x161/0x7a0 mm/slab.c:3665
 kmalloc include/linux/slab.h:560 [inline]
 sk_prot_alloc+0x223/0x2f0 net/core/sock.c:1612
 sk_alloc+0x36/0x1100 net/core/sock.c:1666
 data_sock_create drivers/isdn/mISDN/socket.c:600 [inline]
 mISDN_sock_create+0x272/0x400 drivers/isdn/mISDN/socket.c:796
 __sock_create+0x3cb/0x730 net/socket.c:1428
 sock_create net/socket.c:1479 [inline]
 __sys_socket+0xef/0x200 net/socket.c:1521
 __do_sys_socket net/socket.c:1530 [inline]
 __se_sys_socket net/socket.c:1528 [inline]
 __x64_sys_socket+0x6f/0xb0 net/socket.c:1528
 do_syscall_64+0xf6/0x7d0 arch/x86/entry/common.c:295
 entry_SYSCALL_64_after_hwframe+0x49/0xb3

Freed by task 2484:
 save_stack+0x1b/0x40 mm/kasan/common.c:49
 set_track mm/kasan/common.c:57 [inline]
 kasan_set_free_info mm/kasan/common.c:317 [inline]
 __kasan_slab_free+0xf7/0x140 mm/kasan/common.c:456
 __cache_free mm/slab.c:3426 [inline]
 kfree+0x109/0x2b0 mm/slab.c:3757
 kvfree+0x42/0x50 mm/util.c:603
 __free_fdtable+0x2d/0x70 fs/file.c:31
 put_files_struct fs/file.c:420 [inline]
 put_files_struct+0x248/0x2e0 fs/file.c:413
 exit_files+0x7e/0xa0 fs/file.c:445
 do_exit+0xb04/0x2dd0 kernel/exit.c:791
 do_group_exit+0x125/0x340 kernel/exit.c:894
 get_signal+0x47b/0x24e0 kernel/signal.c:2739
 do_signal+0x81/0x2240 arch/x86/kernel/signal.c:784
 exit_to_usermode_loop+0x26c/0x360 arch/x86/entry/common.c:161
 prepare_exit_to_usermode arch/x86/entry/common.c:196 [inline]
 syscall_return_slowpath arch/x86/entry/common.c:279 [inline]
 do_syscall_64+0x6b1/0x7d0 arch/x86/entry/common.c:305
 entry_SYSCALL_64_after_hwframe+0x49/0xb3

The buggy address belongs to the object at ffff88808ed0c000
 which belongs to the cache kmalloc-2k of size 2048
The buggy address is located 1424 bytes inside of
 2048-byte region [ffff88808ed0c000, ffff88808ed0c800)
The buggy address belongs to the page:
page:ffffea00023b4300 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0
flags: 0xfffe0000000200(slab)
raw: 00fffe0000000200 ffffea0002838208 ffffea00015ba288 ffff8880aa000e00
raw: 0000000000000000 ffff88808ed0c000 0000000100000001 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff88808ed0c480: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
 ffff88808ed0c500: 00 00 00 fc fc fc fc fc fc fc fc fc fc fc fc fc
>ffff88808ed0c580: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
                         ^
 ffff88808ed0c600: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 ffff88808ed0c680: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc

Fixes: 6b9f34239b00 ("l2tp: fix races in tunnel creation")
Fixes: fd558d186df2 ("l2tp: Split pppol2tp patch into separate l2tp and ppp parts")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: James Chapman <jchapman@katalix.com>
Cc: Guillaume Nault <gnault@redhat.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 425b95eb7e87..6dc3bfa12b1e 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1460,6 +1460,9 @@ static int l2tp_validate_socket(const struct sock *sk, const struct net *net,
 	if (sk->sk_type != SOCK_DGRAM)
 		return -EPROTONOSUPPORT;
 
+	if (sk->sk_family != PF_INET && sk->sk_family != PF_INET6)
+		return -EPROTONOSUPPORT;
+
 	if ((encap == L2TP_ENCAPTYPE_UDP && sk->sk_protocol != IPPROTO_UDP) ||
 	    (encap == L2TP_ENCAPTYPE_IP && sk->sk_protocol != IPPROTO_L2TP))
 		return -EPROTONOSUPPORT;
-- 
2.26.2


From 76c1772f420d07cf35c333af347afa029cccd455 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 29 May 2020 11:20:53 -0700
Subject: [PATCH 03/11] l2tp: do not use inet_hash()/inet_unhash()

[ Upstream commit 02c71b144c811bcdd865e0a1226d0407d11357e8 ]

syzbot recently found a way to crash the kernel [1]

Issue here is that inet_hash() & inet_unhash() are currently
only meant to be used by TCP & DCCP, since only these protocols
provide the needed hashinfo pointer.

L2TP uses a single list (instead of a hash table)

This old bug became an issue after commit 610236587600
("bpf: Add new cgroup attach type to enable sock modifications")
since after this commit, sk_common_release() can be called
while the L2TP socket is still considered 'hashed'.

general protection fault, probably for non-canonical address 0xdffffc0000000001: 0000 [#1] PREEMPT SMP KASAN
KASAN: null-ptr-deref in range [0x0000000000000008-0x000000000000000f]
CPU: 0 PID: 7063 Comm: syz-executor654 Not tainted 5.7.0-rc6-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:inet_unhash+0x11f/0x770 net/ipv4/inet_hashtables.c:600
Code: 03 0f b6 04 02 84 c0 74 08 3c 03 0f 8e dd 04 00 00 48 8d 7d 08 44 8b 73 08 48 b8 00 00 00 00 00 fc ff df 48 89 fa 48 c1 ea 03 <80> 3c 02 00 0f 85 55 05 00 00 48 8d 7d 14 4c 8b 6d 08 48 b8 00 00
RSP: 0018:ffffc90001777d30 EFLAGS: 00010202
RAX: dffffc0000000000 RBX: ffff88809a6df940 RCX: ffffffff8697c242
RDX: 0000000000000001 RSI: ffffffff8697c251 RDI: 0000000000000008
RBP: 0000000000000000 R08: ffff88809f3ae1c0 R09: fffffbfff1514cc1
R10: ffffffff8a8a6607 R11: fffffbfff1514cc0 R12: ffff88809a6df9b0
R13: 0000000000000007 R14: 0000000000000000 R15: ffffffff873a4d00
FS:  0000000001d2b880(0000) GS:ffff8880ae600000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000006cd090 CR3: 000000009403a000 CR4: 00000000001406f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 sk_common_release+0xba/0x370 net/core/sock.c:3210
 inet_create net/ipv4/af_inet.c:390 [inline]
 inet_create+0x966/0xe00 net/ipv4/af_inet.c:248
 __sock_create+0x3cb/0x730 net/socket.c:1428
 sock_create net/socket.c:1479 [inline]
 __sys_socket+0xef/0x200 net/socket.c:1521
 __do_sys_socket net/socket.c:1530 [inline]
 __se_sys_socket net/socket.c:1528 [inline]
 __x64_sys_socket+0x6f/0xb0 net/socket.c:1528
 do_syscall_64+0xf6/0x7d0 arch/x86/entry/common.c:295
 entry_SYSCALL_64_after_hwframe+0x49/0xb3
RIP: 0033:0x441e29
Code: e8 fc b3 02 00 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 eb 08 fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007ffdce184148 EFLAGS: 00000246 ORIG_RAX: 0000000000000029
RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000441e29
RDX: 0000000000000073 RSI: 0000000000000002 RDI: 0000000000000002
RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 0000000000402c30 R14: 0000000000000000 R15: 0000000000000000
Modules linked in:
---[ end trace 23b6578228ce553e ]---
RIP: 0010:inet_unhash+0x11f/0x770 net/ipv4/inet_hashtables.c:600
Code: 03 0f b6 04 02 84 c0 74 08 3c 03 0f 8e dd 04 00 00 48 8d 7d 08 44 8b 73 08 48 b8 00 00 00 00 00 fc ff df 48 89 fa 48 c1 ea 03 <80> 3c 02 00 0f 85 55 05 00 00 48 8d 7d 14 4c 8b 6d 08 48 b8 00 00
RSP: 0018:ffffc90001777d30 EFLAGS: 00010202
RAX: dffffc0000000000 RBX: ffff88809a6df940 RCX: ffffffff8697c242
RDX: 0000000000000001 RSI: ffffffff8697c251 RDI: 0000000000000008
RBP: 0000000000000000 R08: ffff88809f3ae1c0 R09: fffffbfff1514cc1
R10: ffffffff8a8a6607 R11: fffffbfff1514cc0 R12: ffff88809a6df9b0
R13: 0000000000000007 R14: 0000000000000000 R15: ffffffff873a4d00
FS:  0000000001d2b880(0000) GS:ffff8880ae600000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000006cd090 CR3: 000000009403a000 CR4: 00000000001406f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400

Fixes: 0d76751fad77 ("l2tp: Add L2TPv3 IP encapsulation (no UDP) support")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: James Chapman <jchapman@katalix.com>
Cc: Andrii Nakryiko <andriin@fb.com>
Reported-by: syzbot+3610d489778b57cc8031@syzkaller.appspotmail.com
---
 net/l2tp/l2tp_ip.c  | 29 ++++++++++++++++++++++-------
 net/l2tp/l2tp_ip6.c | 30 ++++++++++++++++++++++--------
 2 files changed, 44 insertions(+), 15 deletions(-)

diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 0d7c887a2b75..955662a6dee7 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -20,7 +20,6 @@
 #include <net/icmp.h>
 #include <net/udp.h>
 #include <net/inet_common.h>
-#include <net/inet_hashtables.h>
 #include <net/tcp_states.h>
 #include <net/protocol.h>
 #include <net/xfrm.h>
@@ -209,15 +208,31 @@ static int l2tp_ip_recv(struct sk_buff *skb)
 	return 0;
 }
 
-static int l2tp_ip_open(struct sock *sk)
+static int l2tp_ip_hash(struct sock *sk)
 {
-	/* Prevent autobind. We don't have ports. */
-	inet_sk(sk)->inet_num = IPPROTO_L2TP;
+	if (sk_unhashed(sk)) {
+		write_lock_bh(&l2tp_ip_lock);
+		sk_add_node(sk, &l2tp_ip_table);
+		write_unlock_bh(&l2tp_ip_lock);
+	}
+	return 0;
+}
 
+static void l2tp_ip_unhash(struct sock *sk)
+{
+	if (sk_unhashed(sk))
+		return;
 	write_lock_bh(&l2tp_ip_lock);
-	sk_add_node(sk, &l2tp_ip_table);
+	sk_del_node_init(sk);
 	write_unlock_bh(&l2tp_ip_lock);
+}
+
+static int l2tp_ip_open(struct sock *sk)
+{
+	/* Prevent autobind. We don't have ports. */
+	inet_sk(sk)->inet_num = IPPROTO_L2TP;
 
+	l2tp_ip_hash(sk);
 	return 0;
 }
 
@@ -594,8 +609,8 @@ static struct proto l2tp_ip_prot = {
 	.sendmsg	   = l2tp_ip_sendmsg,
 	.recvmsg	   = l2tp_ip_recvmsg,
 	.backlog_rcv	   = l2tp_ip_backlog_recv,
-	.hash		   = inet_hash,
-	.unhash		   = inet_unhash,
+	.hash		   = l2tp_ip_hash,
+	.unhash		   = l2tp_ip_unhash,
 	.obj_size	   = sizeof(struct l2tp_ip_sock),
 #ifdef CONFIG_COMPAT
 	.compat_setsockopt = compat_ip_setsockopt,
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index d148766f40d1..0fa694bd3f6a 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -20,8 +20,6 @@
 #include <net/icmp.h>
 #include <net/udp.h>
 #include <net/inet_common.h>
-#include <net/inet_hashtables.h>
-#include <net/inet6_hashtables.h>
 #include <net/tcp_states.h>
 #include <net/protocol.h>
 #include <net/xfrm.h>
@@ -222,15 +220,31 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
 	return 0;
 }
 
-static int l2tp_ip6_open(struct sock *sk)
+static int l2tp_ip6_hash(struct sock *sk)
 {
-	/* Prevent autobind. We don't have ports. */
-	inet_sk(sk)->inet_num = IPPROTO_L2TP;
+	if (sk_unhashed(sk)) {
+		write_lock_bh(&l2tp_ip6_lock);
+		sk_add_node(sk, &l2tp_ip6_table);
+		write_unlock_bh(&l2tp_ip6_lock);
+	}
+	return 0;
+}
 
+static void l2tp_ip6_unhash(struct sock *sk)
+{
+	if (sk_unhashed(sk))
+		return;
 	write_lock_bh(&l2tp_ip6_lock);
-	sk_add_node(sk, &l2tp_ip6_table);
+	sk_del_node_init(sk);
 	write_unlock_bh(&l2tp_ip6_lock);
+}
+
+static int l2tp_ip6_open(struct sock *sk)
+{
+	/* Prevent autobind. We don't have ports. */
+	inet_sk(sk)->inet_num = IPPROTO_L2TP;
 
+	l2tp_ip6_hash(sk);
 	return 0;
 }
 
@@ -728,8 +742,8 @@ static struct proto l2tp_ip6_prot = {
 	.sendmsg	   = l2tp_ip6_sendmsg,
 	.recvmsg	   = l2tp_ip6_recvmsg,
 	.backlog_rcv	   = l2tp_ip6_backlog_recv,
-	.hash		   = inet6_hash,
-	.unhash		   = inet_unhash,
+	.hash		   = l2tp_ip6_hash,
+	.unhash		   = l2tp_ip6_unhash,
 	.obj_size	   = sizeof(struct l2tp_ip6_sock),
 #ifdef CONFIG_COMPAT
 	.compat_setsockopt = compat_ipv6_setsockopt,
-- 
2.26.2


From e919e629b45b0cd9f5ac77b4809d921e6987bf0c Mon Sep 17 00:00:00 2001
From: Mark Bloch <markb@mellanox.com>
Date: Wed, 20 May 2020 17:32:08 +0000
Subject: [PATCH 04/11] net/mlx5: Fix crash upon suspend/resume

[ Upstream commit 8fc3e29be9248048f449793502c15af329f35c6e ]

Currently a Linux system with the mlx5 NIC always crashes upon
hibernation - suspend/resume.

Add basic callbacks so the NIC could be suspended and resumed.

Fixes: 9603b61de1ee ("mlx5: Move pci device handling from mlx5_ib to mlx5_core")
Tested-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Mark Bloch <markb@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 7dcdda9ca351..e4a690128b3a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1554,6 +1554,22 @@ static void shutdown(struct pci_dev *pdev)
 	mlx5_pci_disable_device(dev);
 }
 
+static int mlx5_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+	struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
+
+	mlx5_unload_one(dev, false);
+
+	return 0;
+}
+
+static int mlx5_resume(struct pci_dev *pdev)
+{
+	struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
+
+	return mlx5_load_one(dev, false);
+}
+
 static const struct pci_device_id mlx5_core_pci_table[] = {
 	{ PCI_VDEVICE(MELLANOX, PCI_DEVICE_ID_MELLANOX_CONNECTIB) },
 	{ PCI_VDEVICE(MELLANOX, 0x1012), MLX5_PCI_DEV_IS_VF},	/* Connect-IB VF */
@@ -1597,6 +1613,8 @@ static struct pci_driver mlx5_core_driver = {
 	.id_table       = mlx5_core_pci_table,
 	.probe          = init_one,
 	.remove         = remove_one,
+	.suspend        = mlx5_suspend,
+	.resume         = mlx5_resume,
 	.shutdown	= shutdown,
 	.err_handler	= &mlx5_err_handler,
 	.sriov_configure   = mlx5_core_sriov_configure,
-- 
2.26.2


From adae8023389808855af8952843d05c4f5bd42c3c Mon Sep 17 00:00:00 2001
From: Fugang Duan <fugang.duan@nxp.com>
Date: Mon, 25 May 2020 16:18:14 +0800
Subject: [PATCH 05/11] net: stmmac: enable timestamp snapshot for required PTP
 packets in dwmac v5.10a
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit f2fb6b6275eba9d312957ca44c487bd780da6169 ]

For rx filter 'HWTSTAMP_FILTER_PTP_V2_EVENT', it should be
PTP v2/802.AS1, any layer, any kind of event packet, but HW only
take timestamp snapshot for below PTP message: sync, Pdelay_req,
Pdelay_resp.

Then it causes below issue when test E2E case:
ptp4l[2479.534]: port 1: received DELAY_REQ without timestamp
ptp4l[2481.423]: port 1: received DELAY_REQ without timestamp
ptp4l[2481.758]: port 1: received DELAY_REQ without timestamp
ptp4l[2483.524]: port 1: received DELAY_REQ without timestamp
ptp4l[2484.233]: port 1: received DELAY_REQ without timestamp
ptp4l[2485.750]: port 1: received DELAY_REQ without timestamp
ptp4l[2486.888]: port 1: received DELAY_REQ without timestamp
ptp4l[2487.265]: port 1: received DELAY_REQ without timestamp
ptp4l[2487.316]: port 1: received DELAY_REQ without timestamp

Timestamp snapshot dependency on register bits in received path:
SNAPTYPSEL TSMSTRENA TSEVNTENA 	PTP_Messages
01         x         0          SYNC, Follow_Up, Delay_Req,
                                Delay_Resp, Pdelay_Req, Pdelay_Resp,
                                Pdelay_Resp_Follow_Up
01         0         1          SYNC, Pdelay_Req, Pdelay_Resp

For dwmac v5.10a, enabling all events by setting register
DWC_EQOS_TIME_STAMPING[SNAPTYPSEL] to 2’b01, clearing bit [TSEVNTENA]
to 0’b0, which can support all required events.

Signed-off-by: Fugang Duan <fugang.duan@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 1623516efb17..982be75fde83 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -630,7 +630,8 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 			config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 			ptp_v2 = PTP_TCR_TSVER2ENA;
 			snap_type_sel = PTP_TCR_SNAPTYPSEL_1;
-			ts_event_en = PTP_TCR_TSEVNTENA;
+			if (priv->synopsys_id != DWMAC_CORE_5_10)
+				ts_event_en = PTP_TCR_TSEVNTENA;
 			ptp_over_ipv4_udp = PTP_TCR_TSIPV4ENA;
 			ptp_over_ipv6_udp = PTP_TCR_TSIPV6ENA;
 			ptp_over_ethernet = PTP_TCR_TSIPENA;
-- 
2.26.2


From 3abc6be62d464378d58f33e71f603ff302e1be55 Mon Sep 17 00:00:00 2001
From: Daniele Palmas <dnlplm@gmail.com>
Date: Mon, 25 May 2020 23:25:37 +0200
Subject: [PATCH 06/11] net: usb: qmi_wwan: add Telit LE910C1-EUX composition
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 591612aa578cd7148b7b9d74869ef40118978389 ]

Add support for Telit LE910C1-EUX composition

0x1031: tty, tty, tty, rmnet
Signed-off-by: Daniele Palmas <dnlplm@gmail.com>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 4bb8552a00d3..4a2c7355be63 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1324,6 +1324,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1bbb, 0x0203, 2)},	/* Alcatel L800MA */
 	{QMI_FIXED_INTF(0x2357, 0x0201, 4)},	/* TP-LINK HSUPA Modem MA180 */
 	{QMI_FIXED_INTF(0x2357, 0x9000, 4)},	/* TP-LINK MA260 */
+	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1031, 3)}, /* Telit LE910C1-EUX */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1040, 2)},	/* Telit LE922A */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1050, 2)},	/* Telit FN980 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1100, 3)},	/* Telit ME910 */
-- 
2.26.2


From 5d58280235d75169d32fe570696bb7bcceb2b425 Mon Sep 17 00:00:00 2001
From: Chuhong Yuan <hslester96@gmail.com>
Date: Thu, 28 May 2020 18:20:37 +0800
Subject: [PATCH 07/11] NFC: st21nfca: add missed kfree_skb() in an error path

[ Upstream commit 3decabdc714ca56c944f4669b4cdec5c2c1cea23 ]

st21nfca_tm_send_atr_res() misses to call kfree_skb() in an error path.
Add the missed function call to fix it.

Fixes: 1892bf844ea0 ("NFC: st21nfca: Adding P2P support to st21nfca in Initiator & Target mode")
Signed-off-by: Chuhong Yuan <hslester96@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/nfc/st21nfca/dep.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/nfc/st21nfca/dep.c b/drivers/nfc/st21nfca/dep.c
index 60acdfd1cb8c..856a10c293f8 100644
--- a/drivers/nfc/st21nfca/dep.c
+++ b/drivers/nfc/st21nfca/dep.c
@@ -173,8 +173,10 @@ static int st21nfca_tm_send_atr_res(struct nfc_hci_dev *hdev,
 		memcpy(atr_res->gbi, atr_req->gbi, gb_len);
 		r = nfc_set_remote_general_bytes(hdev->ndev, atr_res->gbi,
 						  gb_len);
-		if (r < 0)
+		if (r < 0) {
+			kfree_skb(skb);
 			return r;
+		}
 	}
 
 	info->dep_info.curr_nfc_dep_pni = 0;
-- 
2.26.2


From 20d6786fe599151a7fb5711ef8f8e07349b9d6bd Mon Sep 17 00:00:00 2001
From: Heinrich Kuhn <heinrich.kuhn@netronome.com>
Date: Wed, 27 May 2020 09:44:20 +0200
Subject: [PATCH 08/11] nfp: flower: fix used time of merge flow statistics

[ Upstream commit 5b186cd60f033110960a3db424ffbd6de4cee528 ]

Prior to this change the correct value for the used counter is calculated
but not stored nor, therefore, propagated to user-space. In use-cases such
as OVS use-case at least this results in active flows being removed from
the hardware datapath. Which results in both unnecessary flow tear-down
and setup, and packet processing on the host.

This patch addresses the problem by saving the calculated used value
which allows the value to propagate to user-space.

Found by inspection.

Fixes: aa6ce2ea0c93 ("nfp: flower: support stats update for merge flows")
Signed-off-by: Heinrich Kuhn <heinrich.kuhn@netronome.com>
Signed-off-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/offload.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index 987ae221f6be..4dd3f8a5a9b8 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -1368,7 +1368,8 @@ __nfp_flower_update_merge_stats(struct nfp_app *app,
 		ctx_id = be32_to_cpu(sub_flow->meta.host_ctx_id);
 		priv->stats[ctx_id].pkts += pkts;
 		priv->stats[ctx_id].bytes += bytes;
-		max_t(u64, priv->stats[ctx_id].used, used);
+		priv->stats[ctx_id].used = max_t(u64, used,
+						 priv->stats[ctx_id].used);
 	}
 }
 
-- 
2.26.2


From 964431946c391e2a6b3e32fea7e2f341451addf0 Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Wed, 27 May 2020 09:56:55 +0200
Subject: [PATCH 09/11] vsock: fix timeout in vsock_accept()

[ Upstream commit 7e0afbdfd13d1e708fe96e31c46c4897101a6a43 ]

The accept(2) is an "input" socket interface, so we should use
SO_RCVTIMEO instead of SO_SNDTIMEO to set the timeout.

So this patch replace sock_sndtimeo() with sock_rcvtimeo() to
use the right timeout in the vsock_accept().

Fixes: d021c344051a ("VSOCK: Introduce VM Sockets")
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Reviewed-by: Jorgen Hansen <jhansen@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/vmw_vsock/af_vsock.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 582a3e4dfce2..7bd6c8199ca6 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1275,7 +1275,7 @@ static int vsock_accept(struct socket *sock, struct socket *newsock, int flags,
 	/* Wait for children sockets to appear; these are the new sockets
 	 * created upon connection establishment.
 	 */
-	timeout = sock_sndtimeo(listener, flags & O_NONBLOCK);
+	timeout = sock_rcvtimeo(listener, flags & O_NONBLOCK);
 	prepare_to_wait(sk_sleep(listener), &wait, TASK_INTERRUPTIBLE);
 
 	while ((connected = vsock_dequeue_accept(listener)) == NULL &&
-- 
2.26.2


From 0074319ec8976143567c5de3d5b630b170d55515 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Mon, 25 May 2020 15:07:40 -0400
Subject: [PATCH 10/11] net: check untrusted gso_size at kernel entry

[ Upstream commit 6dd912f82680761d8fb6b1bb274a69d4c7010988 ]

Syzkaller again found a path to a kernel crash through bad gso input:
a packet with gso size exceeding len.

These packets are dropped in tcp_gso_segment and udp[46]_ufo_fragment.
But they may affect gso size calculations earlier in the path.

Now that we have thlen as of commit 9274124f023b ("net: stricter
validation of untrusted gso packets"), check gso_size at entry too.

Fixes: bfd5f4a3d605 ("packet: Add GSO/csum offload support.")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/virtio_net.h | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 6f6ade63b04c..88997022a4b5 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -31,6 +31,7 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 {
 	unsigned int gso_type = 0;
 	unsigned int thlen = 0;
+	unsigned int p_off = 0;
 	unsigned int ip_proto;
 
 	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
@@ -68,7 +69,8 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 		if (!skb_partial_csum_set(skb, start, off))
 			return -EINVAL;
 
-		if (skb_transport_offset(skb) + thlen > skb_headlen(skb))
+		p_off = skb_transport_offset(skb) + thlen;
+		if (p_off > skb_headlen(skb))
 			return -EINVAL;
 	} else {
 		/* gso packets without NEEDS_CSUM do not set transport_offset.
@@ -92,17 +94,25 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 				return -EINVAL;
 			}
 
-			if (keys.control.thoff + thlen > skb_headlen(skb) ||
+			p_off = keys.control.thoff + thlen;
+			if (p_off > skb_headlen(skb) ||
 			    keys.basic.ip_proto != ip_proto)
 				return -EINVAL;
 
 			skb_set_transport_header(skb, keys.control.thoff);
+		} else if (gso_type) {
+			p_off = thlen;
+			if (p_off > skb_headlen(skb))
+				return -EINVAL;
 		}
 	}
 
 	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
 		u16 gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size);
 
+		if (skb->len - p_off <= gso_size)
+			return -EINVAL;
+
 		skb_shinfo(skb)->gso_size = gso_size;
 		skb_shinfo(skb)->gso_type = gso_type;
 
-- 
2.26.2


From e95c9b7a667a6b6a4a4e212021387892e037adea Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 28 May 2020 14:57:47 -0700
Subject: [PATCH 11/11] net: be more gentle about silly gso requests coming
 from user

[ Upstream commit 7c6d2ecbda83150b2036a2b36b21381ad4667762 ]

Recent change in virtio_net_hdr_to_skb() broke some packetdrill tests.

When --mss=XXX option is set, packetdrill always provide gso_type & gso_size
for its inbound packets, regardless of packet size.

	if (packet->tcp && packet->mss) {
		if (packet->ipv4)
			gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
		else
			gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
		gso.gso_size = packet->mss;
	}

Since many other programs could do the same, relax virtio_net_hdr_to_skb()
to no longer return an error, but instead ignore gso settings.

This keeps Willem intent to make sure no malicious packet could
reach gso stack.

Note that TCP stack has a special logic in tcp_set_skb_tso_segs()
to clear gso_size for small packets.

Fixes: 6dd912f82680 ("net: check untrusted gso_size at kernel entry")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/virtio_net.h | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 88997022a4b5..e8a924eeea3d 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -109,16 +109,17 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 
 	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
 		u16 gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size);
+		struct skb_shared_info *shinfo = skb_shinfo(skb);
 
-		if (skb->len - p_off <= gso_size)
-			return -EINVAL;
-
-		skb_shinfo(skb)->gso_size = gso_size;
-		skb_shinfo(skb)->gso_type = gso_type;
+		/* Too small packets are not really GSO ones. */
+		if (skb->len - p_off > gso_size) {
+			shinfo->gso_size = gso_size;
+			shinfo->gso_type = gso_type;
 
-		/* Header must be checked, and gso_segs computed. */
-		skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
-		skb_shinfo(skb)->gso_segs = 0;
+			/* Header must be checked, and gso_segs computed. */
+			shinfo->gso_type |= SKB_GSO_DODGY;
+			shinfo->gso_segs = 0;
+		}
 	}
 
 	return 0;
-- 
2.26.2


[-- Attachment #3: net_56.mbox --]
[-- Type: Application/Octet-Stream, Size: 46749 bytes --]

From a90f4dba4c8d1fa3e8d6a44f5e01fa0d939d40fb Mon Sep 17 00:00:00 2001
From: Yang Yingliang <yangyingliang@huawei.com>
Date: Sat, 30 May 2020 11:34:33 +0800
Subject: [PATCH 01/17] devinet: fix memleak in inetdev_init()

[ Upstream commit 1b49cd71b52403822731dc9f283185d1da355f97 ]

When devinet_sysctl_register() failed, the memory allocated
in neigh_parms_alloc() should be freed.

Fixes: 20e61da7ffcf ("ipv4: fail early when creating netdev named all or default")
Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/devinet.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 458dc6eb5a68..a27d034c85cc 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -276,6 +276,7 @@ static struct in_device *inetdev_init(struct net_device *dev)
 	err = devinet_sysctl_register(in_dev);
 	if (err) {
 		in_dev->dead = 1;
+		neigh_parms_release(&arp_tbl, in_dev->arp_parms);
 		in_dev_put(in_dev);
 		in_dev = NULL;
 		goto out;
-- 
2.26.2


From db1c3de235ad0d5ff299ecac2dc94a9dbfb78f57 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 29 May 2020 11:32:25 -0700
Subject: [PATCH 02/17] l2tp: add sk_family checks to l2tp_validate_socket

[ Upstream commit d9a81a225277686eb629938986d97629ea102633 ]

syzbot was able to trigger a crash after using an ISDN socket
and fool l2tp.

Fix this by making sure the UDP socket is of the proper family.

BUG: KASAN: slab-out-of-bounds in setup_udp_tunnel_sock+0x465/0x540 net/ipv4/udp_tunnel.c:78
Write of size 1 at addr ffff88808ed0c590 by task syz-executor.5/3018

CPU: 0 PID: 3018 Comm: syz-executor.5 Not tainted 5.7.0-rc6-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x188/0x20d lib/dump_stack.c:118
 print_address_description.constprop.0.cold+0xd3/0x413 mm/kasan/report.c:382
 __kasan_report.cold+0x20/0x38 mm/kasan/report.c:511
 kasan_report+0x33/0x50 mm/kasan/common.c:625
 setup_udp_tunnel_sock+0x465/0x540 net/ipv4/udp_tunnel.c:78
 l2tp_tunnel_register+0xb15/0xdd0 net/l2tp/l2tp_core.c:1523
 l2tp_nl_cmd_tunnel_create+0x4b2/0xa60 net/l2tp/l2tp_netlink.c:249
 genl_family_rcv_msg_doit net/netlink/genetlink.c:673 [inline]
 genl_family_rcv_msg net/netlink/genetlink.c:718 [inline]
 genl_rcv_msg+0x627/0xdf0 net/netlink/genetlink.c:735
 netlink_rcv_skb+0x15a/0x410 net/netlink/af_netlink.c:2469
 genl_rcv+0x24/0x40 net/netlink/genetlink.c:746
 netlink_unicast_kernel net/netlink/af_netlink.c:1303 [inline]
 netlink_unicast+0x537/0x740 net/netlink/af_netlink.c:1329
 netlink_sendmsg+0x882/0xe10 net/netlink/af_netlink.c:1918
 sock_sendmsg_nosec net/socket.c:652 [inline]
 sock_sendmsg+0xcf/0x120 net/socket.c:672
 ____sys_sendmsg+0x6e6/0x810 net/socket.c:2352
 ___sys_sendmsg+0x100/0x170 net/socket.c:2406
 __sys_sendmsg+0xe5/0x1b0 net/socket.c:2439
 do_syscall_64+0xf6/0x7d0 arch/x86/entry/common.c:295
 entry_SYSCALL_64_after_hwframe+0x49/0xb3
RIP: 0033:0x45ca29
Code: 0d b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 db b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007effe76edc78 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 00000000004fe1c0 RCX: 000000000045ca29
RDX: 0000000000000000 RSI: 0000000020000240 RDI: 0000000000000005
RBP: 000000000078bf00 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff
R13: 000000000000094e R14: 00000000004d5d00 R15: 00007effe76ee6d4

Allocated by task 3018:
 save_stack+0x1b/0x40 mm/kasan/common.c:49
 set_track mm/kasan/common.c:57 [inline]
 __kasan_kmalloc mm/kasan/common.c:495 [inline]
 __kasan_kmalloc.constprop.0+0xbf/0xd0 mm/kasan/common.c:468
 __do_kmalloc mm/slab.c:3656 [inline]
 __kmalloc+0x161/0x7a0 mm/slab.c:3665
 kmalloc include/linux/slab.h:560 [inline]
 sk_prot_alloc+0x223/0x2f0 net/core/sock.c:1612
 sk_alloc+0x36/0x1100 net/core/sock.c:1666
 data_sock_create drivers/isdn/mISDN/socket.c:600 [inline]
 mISDN_sock_create+0x272/0x400 drivers/isdn/mISDN/socket.c:796
 __sock_create+0x3cb/0x730 net/socket.c:1428
 sock_create net/socket.c:1479 [inline]
 __sys_socket+0xef/0x200 net/socket.c:1521
 __do_sys_socket net/socket.c:1530 [inline]
 __se_sys_socket net/socket.c:1528 [inline]
 __x64_sys_socket+0x6f/0xb0 net/socket.c:1528
 do_syscall_64+0xf6/0x7d0 arch/x86/entry/common.c:295
 entry_SYSCALL_64_after_hwframe+0x49/0xb3

Freed by task 2484:
 save_stack+0x1b/0x40 mm/kasan/common.c:49
 set_track mm/kasan/common.c:57 [inline]
 kasan_set_free_info mm/kasan/common.c:317 [inline]
 __kasan_slab_free+0xf7/0x140 mm/kasan/common.c:456
 __cache_free mm/slab.c:3426 [inline]
 kfree+0x109/0x2b0 mm/slab.c:3757
 kvfree+0x42/0x50 mm/util.c:603
 __free_fdtable+0x2d/0x70 fs/file.c:31
 put_files_struct fs/file.c:420 [inline]
 put_files_struct+0x248/0x2e0 fs/file.c:413
 exit_files+0x7e/0xa0 fs/file.c:445
 do_exit+0xb04/0x2dd0 kernel/exit.c:791
 do_group_exit+0x125/0x340 kernel/exit.c:894
 get_signal+0x47b/0x24e0 kernel/signal.c:2739
 do_signal+0x81/0x2240 arch/x86/kernel/signal.c:784
 exit_to_usermode_loop+0x26c/0x360 arch/x86/entry/common.c:161
 prepare_exit_to_usermode arch/x86/entry/common.c:196 [inline]
 syscall_return_slowpath arch/x86/entry/common.c:279 [inline]
 do_syscall_64+0x6b1/0x7d0 arch/x86/entry/common.c:305
 entry_SYSCALL_64_after_hwframe+0x49/0xb3

The buggy address belongs to the object at ffff88808ed0c000
 which belongs to the cache kmalloc-2k of size 2048
The buggy address is located 1424 bytes inside of
 2048-byte region [ffff88808ed0c000, ffff88808ed0c800)
The buggy address belongs to the page:
page:ffffea00023b4300 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0
flags: 0xfffe0000000200(slab)
raw: 00fffe0000000200 ffffea0002838208 ffffea00015ba288 ffff8880aa000e00
raw: 0000000000000000 ffff88808ed0c000 0000000100000001 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff88808ed0c480: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
 ffff88808ed0c500: 00 00 00 fc fc fc fc fc fc fc fc fc fc fc fc fc
>ffff88808ed0c580: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
                         ^
 ffff88808ed0c600: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 ffff88808ed0c680: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc

Fixes: 6b9f34239b00 ("l2tp: fix races in tunnel creation")
Fixes: fd558d186df2 ("l2tp: Split pppol2tp patch into separate l2tp and ppp parts")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: James Chapman <jchapman@katalix.com>
Cc: Guillaume Nault <gnault@redhat.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index fcb53ed1c4fb..6d7ef78c88af 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1458,6 +1458,9 @@ static int l2tp_validate_socket(const struct sock *sk, const struct net *net,
 	if (sk->sk_type != SOCK_DGRAM)
 		return -EPROTONOSUPPORT;
 
+	if (sk->sk_family != PF_INET && sk->sk_family != PF_INET6)
+		return -EPROTONOSUPPORT;
+
 	if ((encap == L2TP_ENCAPTYPE_UDP && sk->sk_protocol != IPPROTO_UDP) ||
 	    (encap == L2TP_ENCAPTYPE_IP && sk->sk_protocol != IPPROTO_L2TP))
 		return -EPROTONOSUPPORT;
-- 
2.26.2


From c9a4edec5cd64adf9d2a914ef9e0b9485e3be6cf Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 29 May 2020 11:20:53 -0700
Subject: [PATCH 03/17] l2tp: do not use inet_hash()/inet_unhash()

[ Upstream commit 02c71b144c811bcdd865e0a1226d0407d11357e8 ]

syzbot recently found a way to crash the kernel [1]

Issue here is that inet_hash() & inet_unhash() are currently
only meant to be used by TCP & DCCP, since only these protocols
provide the needed hashinfo pointer.

L2TP uses a single list (instead of a hash table)

This old bug became an issue after commit 610236587600
("bpf: Add new cgroup attach type to enable sock modifications")
since after this commit, sk_common_release() can be called
while the L2TP socket is still considered 'hashed'.

general protection fault, probably for non-canonical address 0xdffffc0000000001: 0000 [#1] PREEMPT SMP KASAN
KASAN: null-ptr-deref in range [0x0000000000000008-0x000000000000000f]
CPU: 0 PID: 7063 Comm: syz-executor654 Not tainted 5.7.0-rc6-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:inet_unhash+0x11f/0x770 net/ipv4/inet_hashtables.c:600
Code: 03 0f b6 04 02 84 c0 74 08 3c 03 0f 8e dd 04 00 00 48 8d 7d 08 44 8b 73 08 48 b8 00 00 00 00 00 fc ff df 48 89 fa 48 c1 ea 03 <80> 3c 02 00 0f 85 55 05 00 00 48 8d 7d 14 4c 8b 6d 08 48 b8 00 00
RSP: 0018:ffffc90001777d30 EFLAGS: 00010202
RAX: dffffc0000000000 RBX: ffff88809a6df940 RCX: ffffffff8697c242
RDX: 0000000000000001 RSI: ffffffff8697c251 RDI: 0000000000000008
RBP: 0000000000000000 R08: ffff88809f3ae1c0 R09: fffffbfff1514cc1
R10: ffffffff8a8a6607 R11: fffffbfff1514cc0 R12: ffff88809a6df9b0
R13: 0000000000000007 R14: 0000000000000000 R15: ffffffff873a4d00
FS:  0000000001d2b880(0000) GS:ffff8880ae600000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000006cd090 CR3: 000000009403a000 CR4: 00000000001406f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 sk_common_release+0xba/0x370 net/core/sock.c:3210
 inet_create net/ipv4/af_inet.c:390 [inline]
 inet_create+0x966/0xe00 net/ipv4/af_inet.c:248
 __sock_create+0x3cb/0x730 net/socket.c:1428
 sock_create net/socket.c:1479 [inline]
 __sys_socket+0xef/0x200 net/socket.c:1521
 __do_sys_socket net/socket.c:1530 [inline]
 __se_sys_socket net/socket.c:1528 [inline]
 __x64_sys_socket+0x6f/0xb0 net/socket.c:1528
 do_syscall_64+0xf6/0x7d0 arch/x86/entry/common.c:295
 entry_SYSCALL_64_after_hwframe+0x49/0xb3
RIP: 0033:0x441e29
Code: e8 fc b3 02 00 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 eb 08 fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007ffdce184148 EFLAGS: 00000246 ORIG_RAX: 0000000000000029
RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000441e29
RDX: 0000000000000073 RSI: 0000000000000002 RDI: 0000000000000002
RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 0000000000402c30 R14: 0000000000000000 R15: 0000000000000000
Modules linked in:
---[ end trace 23b6578228ce553e ]---
RIP: 0010:inet_unhash+0x11f/0x770 net/ipv4/inet_hashtables.c:600
Code: 03 0f b6 04 02 84 c0 74 08 3c 03 0f 8e dd 04 00 00 48 8d 7d 08 44 8b 73 08 48 b8 00 00 00 00 00 fc ff df 48 89 fa 48 c1 ea 03 <80> 3c 02 00 0f 85 55 05 00 00 48 8d 7d 14 4c 8b 6d 08 48 b8 00 00
RSP: 0018:ffffc90001777d30 EFLAGS: 00010202
RAX: dffffc0000000000 RBX: ffff88809a6df940 RCX: ffffffff8697c242
RDX: 0000000000000001 RSI: ffffffff8697c251 RDI: 0000000000000008
RBP: 0000000000000000 R08: ffff88809f3ae1c0 R09: fffffbfff1514cc1
R10: ffffffff8a8a6607 R11: fffffbfff1514cc0 R12: ffff88809a6df9b0
R13: 0000000000000007 R14: 0000000000000000 R15: ffffffff873a4d00
FS:  0000000001d2b880(0000) GS:ffff8880ae600000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000006cd090 CR3: 000000009403a000 CR4: 00000000001406f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400

Fixes: 0d76751fad77 ("l2tp: Add L2TPv3 IP encapsulation (no UDP) support")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: James Chapman <jchapman@katalix.com>
Cc: Andrii Nakryiko <andriin@fb.com>
Reported-by: syzbot+3610d489778b57cc8031@syzkaller.appspotmail.com
---
 net/l2tp/l2tp_ip.c  | 29 ++++++++++++++++++++++-------
 net/l2tp/l2tp_ip6.c | 30 ++++++++++++++++++++++--------
 2 files changed, 44 insertions(+), 15 deletions(-)

diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 0d7c887a2b75..955662a6dee7 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -20,7 +20,6 @@
 #include <net/icmp.h>
 #include <net/udp.h>
 #include <net/inet_common.h>
-#include <net/inet_hashtables.h>
 #include <net/tcp_states.h>
 #include <net/protocol.h>
 #include <net/xfrm.h>
@@ -209,15 +208,31 @@ static int l2tp_ip_recv(struct sk_buff *skb)
 	return 0;
 }
 
-static int l2tp_ip_open(struct sock *sk)
+static int l2tp_ip_hash(struct sock *sk)
 {
-	/* Prevent autobind. We don't have ports. */
-	inet_sk(sk)->inet_num = IPPROTO_L2TP;
+	if (sk_unhashed(sk)) {
+		write_lock_bh(&l2tp_ip_lock);
+		sk_add_node(sk, &l2tp_ip_table);
+		write_unlock_bh(&l2tp_ip_lock);
+	}
+	return 0;
+}
 
+static void l2tp_ip_unhash(struct sock *sk)
+{
+	if (sk_unhashed(sk))
+		return;
 	write_lock_bh(&l2tp_ip_lock);
-	sk_add_node(sk, &l2tp_ip_table);
+	sk_del_node_init(sk);
 	write_unlock_bh(&l2tp_ip_lock);
+}
+
+static int l2tp_ip_open(struct sock *sk)
+{
+	/* Prevent autobind. We don't have ports. */
+	inet_sk(sk)->inet_num = IPPROTO_L2TP;
 
+	l2tp_ip_hash(sk);
 	return 0;
 }
 
@@ -594,8 +609,8 @@ static struct proto l2tp_ip_prot = {
 	.sendmsg	   = l2tp_ip_sendmsg,
 	.recvmsg	   = l2tp_ip_recvmsg,
 	.backlog_rcv	   = l2tp_ip_backlog_recv,
-	.hash		   = inet_hash,
-	.unhash		   = inet_unhash,
+	.hash		   = l2tp_ip_hash,
+	.unhash		   = l2tp_ip_unhash,
 	.obj_size	   = sizeof(struct l2tp_ip_sock),
 #ifdef CONFIG_COMPAT
 	.compat_setsockopt = compat_ip_setsockopt,
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index d148766f40d1..0fa694bd3f6a 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -20,8 +20,6 @@
 #include <net/icmp.h>
 #include <net/udp.h>
 #include <net/inet_common.h>
-#include <net/inet_hashtables.h>
-#include <net/inet6_hashtables.h>
 #include <net/tcp_states.h>
 #include <net/protocol.h>
 #include <net/xfrm.h>
@@ -222,15 +220,31 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
 	return 0;
 }
 
-static int l2tp_ip6_open(struct sock *sk)
+static int l2tp_ip6_hash(struct sock *sk)
 {
-	/* Prevent autobind. We don't have ports. */
-	inet_sk(sk)->inet_num = IPPROTO_L2TP;
+	if (sk_unhashed(sk)) {
+		write_lock_bh(&l2tp_ip6_lock);
+		sk_add_node(sk, &l2tp_ip6_table);
+		write_unlock_bh(&l2tp_ip6_lock);
+	}
+	return 0;
+}
 
+static void l2tp_ip6_unhash(struct sock *sk)
+{
+	if (sk_unhashed(sk))
+		return;
 	write_lock_bh(&l2tp_ip6_lock);
-	sk_add_node(sk, &l2tp_ip6_table);
+	sk_del_node_init(sk);
 	write_unlock_bh(&l2tp_ip6_lock);
+}
+
+static int l2tp_ip6_open(struct sock *sk)
+{
+	/* Prevent autobind. We don't have ports. */
+	inet_sk(sk)->inet_num = IPPROTO_L2TP;
 
+	l2tp_ip6_hash(sk);
 	return 0;
 }
 
@@ -728,8 +742,8 @@ static struct proto l2tp_ip6_prot = {
 	.sendmsg	   = l2tp_ip6_sendmsg,
 	.recvmsg	   = l2tp_ip6_recvmsg,
 	.backlog_rcv	   = l2tp_ip6_backlog_recv,
-	.hash		   = inet6_hash,
-	.unhash		   = inet_unhash,
+	.hash		   = l2tp_ip6_hash,
+	.unhash		   = l2tp_ip6_unhash,
 	.obj_size	   = sizeof(struct l2tp_ip6_sock),
 #ifdef CONFIG_COMPAT
 	.compat_setsockopt = compat_ipv6_setsockopt,
-- 
2.26.2


From 02ce069e83757932ee5dad00af99d06db44a91ee Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Mon, 25 May 2020 15:07:40 -0400
Subject: [PATCH 04/17] net: check untrusted gso_size at kernel entry

[ Upstream commit 6dd912f82680761d8fb6b1bb274a69d4c7010988 ]

Syzkaller again found a path to a kernel crash through bad gso input:
a packet with gso size exceeding len.

These packets are dropped in tcp_gso_segment and udp[46]_ufo_fragment.
But they may affect gso size calculations earlier in the path.

Now that we have thlen as of commit 9274124f023b ("net: stricter
validation of untrusted gso packets"), check gso_size at entry too.

Fixes: bfd5f4a3d605 ("packet: Add GSO/csum offload support.")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/virtio_net.h | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 6f6ade63b04c..88997022a4b5 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -31,6 +31,7 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 {
 	unsigned int gso_type = 0;
 	unsigned int thlen = 0;
+	unsigned int p_off = 0;
 	unsigned int ip_proto;
 
 	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
@@ -68,7 +69,8 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 		if (!skb_partial_csum_set(skb, start, off))
 			return -EINVAL;
 
-		if (skb_transport_offset(skb) + thlen > skb_headlen(skb))
+		p_off = skb_transport_offset(skb) + thlen;
+		if (p_off > skb_headlen(skb))
 			return -EINVAL;
 	} else {
 		/* gso packets without NEEDS_CSUM do not set transport_offset.
@@ -92,17 +94,25 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 				return -EINVAL;
 			}
 
-			if (keys.control.thoff + thlen > skb_headlen(skb) ||
+			p_off = keys.control.thoff + thlen;
+			if (p_off > skb_headlen(skb) ||
 			    keys.basic.ip_proto != ip_proto)
 				return -EINVAL;
 
 			skb_set_transport_header(skb, keys.control.thoff);
+		} else if (gso_type) {
+			p_off = thlen;
+			if (p_off > skb_headlen(skb))
+				return -EINVAL;
 		}
 	}
 
 	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
 		u16 gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size);
 
+		if (skb->len - p_off <= gso_size)
+			return -EINVAL;
+
 		skb_shinfo(skb)->gso_size = gso_size;
 		skb_shinfo(skb)->gso_type = gso_type;
 
-- 
2.26.2


From b051e443d830d84567e8ca05fd38dfb90220d251 Mon Sep 17 00:00:00 2001
From: Mark Bloch <markb@mellanox.com>
Date: Wed, 20 May 2020 17:32:08 +0000
Subject: [PATCH 05/17] net/mlx5: Fix crash upon suspend/resume

[ Upstream commit 8fc3e29be9248048f449793502c15af329f35c6e ]

Currently a Linux system with the mlx5 NIC always crashes upon
hibernation - suspend/resume.

Add basic callbacks so the NIC could be suspended and resumed.

Fixes: 9603b61de1ee ("mlx5: Move pci device handling from mlx5_ib to mlx5_core")
Tested-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Mark Bloch <markb@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 4a08e4eef283..20e12e14cfa8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1552,6 +1552,22 @@ static void shutdown(struct pci_dev *pdev)
 	mlx5_pci_disable_device(dev);
 }
 
+static int mlx5_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+	struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
+
+	mlx5_unload_one(dev, false);
+
+	return 0;
+}
+
+static int mlx5_resume(struct pci_dev *pdev)
+{
+	struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
+
+	return mlx5_load_one(dev, false);
+}
+
 static const struct pci_device_id mlx5_core_pci_table[] = {
 	{ PCI_VDEVICE(MELLANOX, PCI_DEVICE_ID_MELLANOX_CONNECTIB) },
 	{ PCI_VDEVICE(MELLANOX, 0x1012), MLX5_PCI_DEV_IS_VF},	/* Connect-IB VF */
@@ -1595,6 +1611,8 @@ static struct pci_driver mlx5_core_driver = {
 	.id_table       = mlx5_core_pci_table,
 	.probe          = init_one,
 	.remove         = remove_one,
+	.suspend        = mlx5_suspend,
+	.resume         = mlx5_resume,
 	.shutdown	= shutdown,
 	.err_handler	= &mlx5_err_handler,
 	.sriov_configure   = mlx5_core_sriov_configure,
-- 
2.26.2


From dcc1d2874570878901d16c7fd3e65371ec09e761 Mon Sep 17 00:00:00 2001
From: Fugang Duan <fugang.duan@nxp.com>
Date: Mon, 25 May 2020 16:18:14 +0800
Subject: [PATCH 06/17] net: stmmac: enable timestamp snapshot for required PTP
 packets in dwmac v5.10a
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit f2fb6b6275eba9d312957ca44c487bd780da6169 ]

For rx filter 'HWTSTAMP_FILTER_PTP_V2_EVENT', it should be
PTP v2/802.AS1, any layer, any kind of event packet, but HW only
take timestamp snapshot for below PTP message: sync, Pdelay_req,
Pdelay_resp.

Then it causes below issue when test E2E case:
ptp4l[2479.534]: port 1: received DELAY_REQ without timestamp
ptp4l[2481.423]: port 1: received DELAY_REQ without timestamp
ptp4l[2481.758]: port 1: received DELAY_REQ without timestamp
ptp4l[2483.524]: port 1: received DELAY_REQ without timestamp
ptp4l[2484.233]: port 1: received DELAY_REQ without timestamp
ptp4l[2485.750]: port 1: received DELAY_REQ without timestamp
ptp4l[2486.888]: port 1: received DELAY_REQ without timestamp
ptp4l[2487.265]: port 1: received DELAY_REQ without timestamp
ptp4l[2487.316]: port 1: received DELAY_REQ without timestamp

Timestamp snapshot dependency on register bits in received path:
SNAPTYPSEL TSMSTRENA TSEVNTENA 	PTP_Messages
01         x         0          SYNC, Follow_Up, Delay_Req,
                                Delay_Resp, Pdelay_Req, Pdelay_Resp,
                                Pdelay_Resp_Follow_Up
01         0         1          SYNC, Pdelay_Req, Pdelay_Resp

For dwmac v5.10a, enabling all events by setting register
DWC_EQOS_TIME_STAMPING[SNAPTYPSEL] to 2’b01, clearing bit [TSEVNTENA]
to 0’b0, which can support all required events.

Signed-off-by: Fugang Duan <fugang.duan@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index d564459290ce..bcb39012d34d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -630,7 +630,8 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 			config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 			ptp_v2 = PTP_TCR_TSVER2ENA;
 			snap_type_sel = PTP_TCR_SNAPTYPSEL_1;
-			ts_event_en = PTP_TCR_TSEVNTENA;
+			if (priv->synopsys_id != DWMAC_CORE_5_10)
+				ts_event_en = PTP_TCR_TSEVNTENA;
 			ptp_over_ipv4_udp = PTP_TCR_TSIPV4ENA;
 			ptp_over_ipv6_udp = PTP_TCR_TSIPV6ENA;
 			ptp_over_ethernet = PTP_TCR_TSIPENA;
-- 
2.26.2


From 0e34aae5896518bf33d7ea767bbfe0196015b86d Mon Sep 17 00:00:00 2001
From: Daniele Palmas <dnlplm@gmail.com>
Date: Mon, 25 May 2020 23:25:37 +0200
Subject: [PATCH 07/17] net: usb: qmi_wwan: add Telit LE910C1-EUX composition
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 591612aa578cd7148b7b9d74869ef40118978389 ]

Add support for Telit LE910C1-EUX composition

0x1031: tty, tty, tty, rmnet
Signed-off-by: Daniele Palmas <dnlplm@gmail.com>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 4bb8552a00d3..4a2c7355be63 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1324,6 +1324,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1bbb, 0x0203, 2)},	/* Alcatel L800MA */
 	{QMI_FIXED_INTF(0x2357, 0x0201, 4)},	/* TP-LINK HSUPA Modem MA180 */
 	{QMI_FIXED_INTF(0x2357, 0x9000, 4)},	/* TP-LINK MA260 */
+	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1031, 3)}, /* Telit LE910C1-EUX */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1040, 2)},	/* Telit LE922A */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1050, 2)},	/* Telit FN980 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1100, 3)},	/* Telit ME910 */
-- 
2.26.2


From fd4b20ea05f8c700ee1a50d741e9cfe9147f377d Mon Sep 17 00:00:00 2001
From: Chuhong Yuan <hslester96@gmail.com>
Date: Thu, 28 May 2020 18:20:37 +0800
Subject: [PATCH 08/17] NFC: st21nfca: add missed kfree_skb() in an error path

[ Upstream commit 3decabdc714ca56c944f4669b4cdec5c2c1cea23 ]

st21nfca_tm_send_atr_res() misses to call kfree_skb() in an error path.
Add the missed function call to fix it.

Fixes: 1892bf844ea0 ("NFC: st21nfca: Adding P2P support to st21nfca in Initiator & Target mode")
Signed-off-by: Chuhong Yuan <hslester96@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/nfc/st21nfca/dep.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/nfc/st21nfca/dep.c b/drivers/nfc/st21nfca/dep.c
index 60acdfd1cb8c..856a10c293f8 100644
--- a/drivers/nfc/st21nfca/dep.c
+++ b/drivers/nfc/st21nfca/dep.c
@@ -173,8 +173,10 @@ static int st21nfca_tm_send_atr_res(struct nfc_hci_dev *hdev,
 		memcpy(atr_res->gbi, atr_req->gbi, gb_len);
 		r = nfc_set_remote_general_bytes(hdev->ndev, atr_res->gbi,
 						  gb_len);
-		if (r < 0)
+		if (r < 0) {
+			kfree_skb(skb);
 			return r;
+		}
 	}
 
 	info->dep_info.curr_nfc_dep_pni = 0;
-- 
2.26.2


From 33ca7aee0bf03b953e57ad21d6fa80eaab1ea246 Mon Sep 17 00:00:00 2001
From: Heinrich Kuhn <heinrich.kuhn@netronome.com>
Date: Wed, 27 May 2020 09:44:20 +0200
Subject: [PATCH 09/17] nfp: flower: fix used time of merge flow statistics

[ Upstream commit 5b186cd60f033110960a3db424ffbd6de4cee528 ]

Prior to this change the correct value for the used counter is calculated
but not stored nor, therefore, propagated to user-space. In use-cases such
as OVS use-case at least this results in active flows being removed from
the hardware datapath. Which results in both unnecessary flow tear-down
and setup, and packet processing on the host.

This patch addresses the problem by saving the calculated used value
which allows the value to propagate to user-space.

Found by inspection.

Fixes: aa6ce2ea0c93 ("nfp: flower: support stats update for merge flows")
Signed-off-by: Heinrich Kuhn <heinrich.kuhn@netronome.com>
Signed-off-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/offload.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index 7ca5c1becfcf..c5dcfdd69773 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -1440,7 +1440,8 @@ __nfp_flower_update_merge_stats(struct nfp_app *app,
 		ctx_id = be32_to_cpu(sub_flow->meta.host_ctx_id);
 		priv->stats[ctx_id].pkts += pkts;
 		priv->stats[ctx_id].bytes += bytes;
-		max_t(u64, priv->stats[ctx_id].used, used);
+		priv->stats[ctx_id].used = max_t(u64, used,
+						 priv->stats[ctx_id].used);
 	}
 }
 
-- 
2.26.2


From 83f05b5645724ef94ea4c2c83414977e0c3c39ae Mon Sep 17 00:00:00 2001
From: Jonas Falkevik <jonas.falkevik@gmail.com>
Date: Wed, 27 May 2020 11:56:40 +0200
Subject: [PATCH 10/17] sctp: check assoc before SCTP_ADDR_{MADE_PRIM, ADDED}
 event

[ Upstream commit 45ebf73ebcec88a34a778f5feaa0b82b1c76069e ]

Make sure SCTP_ADDR_{MADE_PRIM,ADDED} are sent only for associations
that have been established.

These events are described in rfc6458#section-6.1
SCTP_PEER_ADDR_CHANGE:
This tag indicates that an address that is
part of an existing association has experienced a change of
state (e.g., a failure or return to service of the reachability
of an endpoint via a specific transport address).

Signed-off-by: Jonas Falkevik <jonas.falkevik@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ulpevent.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c
index c82dbdcf13f2..77d5c36a8991 100644
--- a/net/sctp/ulpevent.c
+++ b/net/sctp/ulpevent.c
@@ -343,6 +343,9 @@ void sctp_ulpevent_nofity_peer_addr_change(struct sctp_transport *transport,
 	struct sockaddr_storage addr;
 	struct sctp_ulpevent *event;
 
+	if (asoc->state < SCTP_STATE_ESTABLISHED)
+		return;
+
 	memset(&addr, 0, sizeof(struct sockaddr_storage));
 	memcpy(&addr, &transport->ipaddr, transport->af_specific->sockaddr_len);
 
-- 
2.26.2


From 7c3baf3ff9ef3781fe3fbaa671086a6ff4c8dadb Mon Sep 17 00:00:00 2001
From: Jia He <justin.he@arm.com>
Date: Sat, 30 May 2020 09:38:28 +0800
Subject: [PATCH 11/17] virtio_vsock: Fix race condition in
 virtio_transport_recv_pkt

[ Upstream commit 8692cefc433f282228fd44938dd4d26ed38254a2 ]

When client on the host tries to connect(SOCK_STREAM, O_NONBLOCK) to the
server on the guest, there will be a panic on a ThunderX2 (armv8a server):

[  463.718844] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000
[  463.718848] Mem abort info:
[  463.718849]   ESR = 0x96000044
[  463.718852]   EC = 0x25: DABT (current EL), IL = 32 bits
[  463.718853]   SET = 0, FnV = 0
[  463.718854]   EA = 0, S1PTW = 0
[  463.718855] Data abort info:
[  463.718856]   ISV = 0, ISS = 0x00000044
[  463.718857]   CM = 0, WnR = 1
[  463.718859] user pgtable: 4k pages, 48-bit VAs, pgdp=0000008f6f6e9000
[  463.718861] [0000000000000000] pgd=0000000000000000
[  463.718866] Internal error: Oops: 96000044 [#1] SMP
[...]
[  463.718977] CPU: 213 PID: 5040 Comm: vhost-5032 Tainted: G           O      5.7.0-rc7+ #139
[  463.718980] Hardware name: GIGABYTE R281-T91-00/MT91-FS1-00, BIOS F06 09/25/2018
[  463.718982] pstate: 60400009 (nZCv daif +PAN -UAO)
[  463.718995] pc : virtio_transport_recv_pkt+0x4c8/0xd40 [vmw_vsock_virtio_transport_common]
[  463.718999] lr : virtio_transport_recv_pkt+0x1fc/0xd40 [vmw_vsock_virtio_transport_common]
[  463.719000] sp : ffff80002dbe3c40
[...]
[  463.719025] Call trace:
[  463.719030]  virtio_transport_recv_pkt+0x4c8/0xd40 [vmw_vsock_virtio_transport_common]
[  463.719034]  vhost_vsock_handle_tx_kick+0x360/0x408 [vhost_vsock]
[  463.719041]  vhost_worker+0x100/0x1a0 [vhost]
[  463.719048]  kthread+0x128/0x130
[  463.719052]  ret_from_fork+0x10/0x18

The race condition is as follows:
Task1                                Task2
=====                                =====
__sock_release                       virtio_transport_recv_pkt
  __vsock_release                      vsock_find_bound_socket (found sk)
    lock_sock_nested
    vsock_remove_sock
    sock_orphan
      sk_set_socket(sk, NULL)
    sk->sk_shutdown = SHUTDOWN_MASK
    ...
    release_sock
                                    lock_sock
                                       virtio_transport_recv_connecting
                                         sk->sk_socket->state (panic!)

The root cause is that vsock_find_bound_socket can't hold the lock_sock,
so there is a small race window between vsock_find_bound_socket() and
lock_sock(). If __vsock_release() is running in another task,
sk->sk_socket will be set to NULL inadvertently.

This fixes it by checking sk->sk_shutdown(suggested by Stefano) after
lock_sock since sk->sk_shutdown is set to SHUTDOWN_MASK under the
protection of lock_sock_nested.

Signed-off-by: Jia He <justin.he@arm.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/vmw_vsock/virtio_transport_common.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index f3c4bab2f737..cfab9403a9c4 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -1128,6 +1128,14 @@ void virtio_transport_recv_pkt(struct virtio_transport *t,
 
 	lock_sock(sk);
 
+	/* Check if sk has been released before lock_sock */
+	if (sk->sk_shutdown == SHUTDOWN_MASK) {
+		(void)virtio_transport_reset_no_sock(t, pkt);
+		release_sock(sk);
+		sock_put(sk);
+		goto free_pkt;
+	}
+
 	/* Update CID in case it has changed after a transport reset event */
 	vsk->local_addr.svm_cid = dst.svm_cid;
 
-- 
2.26.2


From b101783bb0dcb7bb8c3ac3963d41dda3f6457768 Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Wed, 27 May 2020 09:56:55 +0200
Subject: [PATCH 12/17] vsock: fix timeout in vsock_accept()

[ Upstream commit 7e0afbdfd13d1e708fe96e31c46c4897101a6a43 ]

The accept(2) is an "input" socket interface, so we should use
SO_RCVTIMEO instead of SO_SNDTIMEO to set the timeout.

So this patch replace sock_sndtimeo() with sock_rcvtimeo() to
use the right timeout in the vsock_accept().

Fixes: d021c344051a ("VSOCK: Introduce VM Sockets")
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Reviewed-by: Jorgen Hansen <jhansen@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/vmw_vsock/af_vsock.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index a5f28708e0e7..626bf9044418 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1408,7 +1408,7 @@ static int vsock_accept(struct socket *sock, struct socket *newsock, int flags,
 	/* Wait for children sockets to appear; these are the new sockets
 	 * created upon connection establishment.
 	 */
-	timeout = sock_sndtimeo(listener, flags & O_NONBLOCK);
+	timeout = sock_rcvtimeo(listener, flags & O_NONBLOCK);
 	prepare_to_wait(sk_sleep(listener), &wait, TASK_INTERRUPTIBLE);
 
 	while ((connected = vsock_dequeue_accept(listener)) == NULL &&
-- 
2.26.2


From dc84627107107311c1c9aff246c873d86d093154 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 28 May 2020 14:57:47 -0700
Subject: [PATCH 13/17] net: be more gentle about silly gso requests coming
 from user

[ Upstream commit 7c6d2ecbda83150b2036a2b36b21381ad4667762 ]

Recent change in virtio_net_hdr_to_skb() broke some packetdrill tests.

When --mss=XXX option is set, packetdrill always provide gso_type & gso_size
for its inbound packets, regardless of packet size.

	if (packet->tcp && packet->mss) {
		if (packet->ipv4)
			gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
		else
			gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
		gso.gso_size = packet->mss;
	}

Since many other programs could do the same, relax virtio_net_hdr_to_skb()
to no longer return an error, but instead ignore gso settings.

This keeps Willem intent to make sure no malicious packet could
reach gso stack.

Note that TCP stack has a special logic in tcp_set_skb_tso_segs()
to clear gso_size for small packets.

Fixes: 6dd912f82680 ("net: check untrusted gso_size at kernel entry")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/virtio_net.h | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 88997022a4b5..e8a924eeea3d 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -109,16 +109,17 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 
 	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
 		u16 gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size);
+		struct skb_shared_info *shinfo = skb_shinfo(skb);
 
-		if (skb->len - p_off <= gso_size)
-			return -EINVAL;
-
-		skb_shinfo(skb)->gso_size = gso_size;
-		skb_shinfo(skb)->gso_type = gso_type;
+		/* Too small packets are not really GSO ones. */
+		if (skb->len - p_off > gso_size) {
+			shinfo->gso_size = gso_size;
+			shinfo->gso_type = gso_type;
 
-		/* Header must be checked, and gso_segs computed. */
-		skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
-		skb_shinfo(skb)->gso_segs = 0;
+			/* Header must be checked, and gso_segs computed. */
+			shinfo->gso_type |= SKB_GSO_DODGY;
+			shinfo->gso_segs = 0;
+		}
 	}
 
 	return 0;
-- 
2.26.2


From 02f09bb6b49ce0f7d84ddbee116a8f0daaeb744d Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Wed, 27 May 2020 19:48:03 +0300
Subject: [PATCH 14/17] net: dsa: felix: send VLANs on CPU port as
 egress-tagged

[ Upstream commit 183be6f967fe37c3154bfac39e913c3bafe89d1b ]

As explained in other commits before (b9cd75e66895 and 87b0f983f66f),
ocelot switches have a single egress-untagged VLAN per port, and the
driver would deny adding a second one while an egress-untagged VLAN
already exists.

But on the CPU port (where the VLAN configuration is implicit, because
there is no net device for the bridge to control), the DSA core attempts
to add a VLAN using the same flags as were used for the front-panel
port. This would make adding any untagged VLAN fail due to the CPU port
rejecting the configuration:

bridge vlan add dev swp0 vid 100 pvid untagged
[ 1865.854253] mscc_felix 0000:00:00.5: Port already has a native VLAN: 1
[ 1865.860824] mscc_felix 0000:00:00.5: Failed to add VLAN 100 to port 5: -16

(note that port 5 is the CPU port and not the front-panel swp0).

So this hardware will send all VLANs as tagged towards the CPU.

Fixes: 56051948773e ("net: dsa: ocelot: add driver for Felix switch family")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/ocelot/felix.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index b74580e87be8..5d9db8d042c1 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -100,13 +100,17 @@ static void felix_vlan_add(struct dsa_switch *ds, int port,
 			   const struct switchdev_obj_port_vlan *vlan)
 {
 	struct ocelot *ocelot = ds->priv;
+	u16 flags = vlan->flags;
 	u16 vid;
 	int err;
 
+	if (dsa_is_cpu_port(ds, port))
+		flags &= ~BRIDGE_VLAN_INFO_UNTAGGED;
+
 	for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) {
 		err = ocelot_vlan_add(ocelot, port, vid,
-				      vlan->flags & BRIDGE_VLAN_INFO_PVID,
-				      vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED);
+				      flags & BRIDGE_VLAN_INFO_PVID,
+				      flags & BRIDGE_VLAN_INFO_UNTAGGED);
 		if (err) {
 			dev_err(ds->dev, "Failed to add VLAN %d to port %d: %d\n",
 				vid, port, err);
-- 
2.26.2


From ae55fabbfccbfde3a63c3569501e42a6e4389ccd Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 29 May 2020 17:43:29 +0200
Subject: [PATCH 15/17] mptcp: fix unblocking connect()

[ Upstream commit 41be81a8d3d09acb9033799938306349328861f9 ]

Currently unblocking connect() on MPTCP sockets fails frequently.
If mptcp_stream_connect() is invoked to complete a previously
attempted unblocking connection, it will still try to create
the first subflow via __mptcp_socket_create(). If the 3whs is
completed and the 'can_ack' flag is already set, the latter
will fail with -EINVAL.

This change addresses the issue checking for pending connect and
delegating the completion to the first subflow. Additionally
do msk addresses and sk_state changes only when needed.

Fixes: 2303f994b3e1 ("mptcp: Associate MPTCP context with TCP socket")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/protocol.c | 20 ++++++++++++++++++--
 1 file changed, 18 insertions(+), 2 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 3c19a8efdcea..ddeb840acd29 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -920,6 +920,14 @@ static int mptcp_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 	int err;
 
 	lock_sock(sock->sk);
+	if (sock->state != SS_UNCONNECTED && msk->subflow) {
+		/* pending connection or invalid state, let existing subflow
+		 * cope with that
+		 */
+		ssock = msk->subflow;
+		goto do_connect;
+	}
+
 	ssock = __mptcp_socket_create(msk, TCP_SYN_SENT);
 	if (IS_ERR(ssock)) {
 		err = PTR_ERR(ssock);
@@ -934,9 +942,17 @@ static int mptcp_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 		mptcp_subflow_ctx(ssock->sk)->request_mptcp = 0;
 #endif
 
+do_connect:
 	err = ssock->ops->connect(ssock, uaddr, addr_len, flags);
-	inet_sk_state_store(sock->sk, inet_sk_state_load(ssock->sk));
-	mptcp_copy_inaddrs(sock->sk, ssock->sk);
+	sock->state = ssock->state;
+
+	/* on successful connect, the msk state will be moved to established by
+	 * subflow_finish_connect()
+	 */
+	if (!err || err == EINPROGRESS)
+		mptcp_copy_inaddrs(sock->sk, ssock->sk);
+	else
+		inet_sk_state_store(sock->sk, inet_sk_state_load(ssock->sk));
 
 unlock:
 	release_sock(sock->sk);
-- 
2.26.2


From 98b5c99113798f6bebfb844c308dcad383b63b4d Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Wed, 27 May 2020 02:04:26 +0200
Subject: [PATCH 16/17] net/sched: fix infinite loop in sch_fq_pie

[ Upstream commit bb2f930d6dd708469a587dc9ed1efe1ef969c0bf ]

this command hangs forever:

 # tc qdisc add dev eth0 root fq_pie flows 65536

 watchdog: BUG: soft lockup - CPU#1 stuck for 23s! [tc:1028]
 [...]
 CPU: 1 PID: 1028 Comm: tc Not tainted 5.7.0-rc6+ #167
 RIP: 0010:fq_pie_init+0x60e/0x8b7 [sch_fq_pie]
 Code: 4c 89 65 50 48 89 f8 48 c1 e8 03 42 80 3c 30 00 0f 85 2a 02 00 00 48 8d 7d 10 4c 89 65 58 48 89 f8 48 c1 e8 03 42 80 3c 30 00 <0f> 85 a7 01 00 00 48 8d 7d 18 48 c7 45 10 46 c3 23 00 48 89 f8 48
 RSP: 0018:ffff888138d67468 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13
 RAX: 1ffff9200018d2b2 RBX: ffff888139c1c400 RCX: ffffffffffffffff
 RDX: 000000000000c5e8 RSI: ffffc900000e5000 RDI: ffffc90000c69590
 RBP: ffffc90000c69580 R08: fffffbfff79a9699 R09: fffffbfff79a9699
 R10: 0000000000000700 R11: fffffbfff79a9698 R12: ffffc90000c695d0
 R13: 0000000000000000 R14: dffffc0000000000 R15: 000000002347c5e8
 FS:  00007f01e1850e40(0000) GS:ffff88814c880000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 000000000067c340 CR3: 000000013864c000 CR4: 0000000000340ee0
 Call Trace:
  qdisc_create+0x3fd/0xeb0
  tc_modify_qdisc+0x3be/0x14a0
  rtnetlink_rcv_msg+0x5f3/0x920
  netlink_rcv_skb+0x121/0x350
  netlink_unicast+0x439/0x630
  netlink_sendmsg+0x714/0xbf0
  sock_sendmsg+0xe2/0x110
  ____sys_sendmsg+0x5b4/0x890
  ___sys_sendmsg+0xe9/0x160
  __sys_sendmsg+0xd3/0x170
  do_syscall_64+0x9a/0x370
  entry_SYSCALL_64_after_hwframe+0x44/0xa9

we can't accept 65536 as a valid number for 'nflows', because the loop on
'idx' in fq_pie_init() will never end. The extack message is correct, but
it doesn't say that 0 is not a valid number for 'flows': while at it, fix
this also. Add a tdc selftest to check correct validation of 'flows'.

CC: Ivan Vecera <ivecera@redhat.com>
Fixes: ec97ecf1ebe4 ("net: sched: add Flow Queue PIE packet scheduler")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Reviewed-by: Ivan Vecera <ivecera@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_fq_pie.c                        |  4 ++--
 .../tc-testing/tc-tests/qdiscs/fq_pie.json    | 21 +++++++++++++++++++
 2 files changed, 23 insertions(+), 2 deletions(-)
 create mode 100644 tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json

diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c
index 214657eb3dfd..6675ec591356 100644
--- a/net/sched/sch_fq_pie.c
+++ b/net/sched/sch_fq_pie.c
@@ -298,9 +298,9 @@ static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt,
 			goto flow_error;
 		}
 		q->flows_cnt = nla_get_u32(tb[TCA_FQ_PIE_FLOWS]);
-		if (!q->flows_cnt || q->flows_cnt > 65536) {
+		if (!q->flows_cnt || q->flows_cnt >= 65536) {
 			NL_SET_ERR_MSG_MOD(extack,
-					   "Number of flows must be < 65536");
+					   "Number of flows must range in [1..65535]");
 			goto flow_error;
 		}
 	}
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json
new file mode 100644
index 000000000000..1cda2e11b3ad
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json
@@ -0,0 +1,21 @@
+[
+    {
+        "id": "83be",
+        "name": "Create FQ-PIE with invalid number of flows",
+        "category": [
+            "qdisc",
+            "fq_pie"
+        ],
+        "setup": [
+            "$IP link add dev $DUMMY type dummy || /bin/true"
+        ],
+        "cmdUnderTest": "$TC qdisc add dev $DUMMY root fq_pie flows 65536",
+        "expExitCode": "2",
+        "verifyCmd": "$TC qdisc show dev $DUMMY",
+        "matchPattern": "qdisc",
+        "matchCount": "0",
+        "teardown": [
+            "$IP link del dev $DUMMY"
+        ]
+    }
+]
-- 
2.26.2


From 25255e4426e862f0e8337c565260ddeb2e4e0f47 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Sun, 19 Apr 2020 14:12:35 +0200
Subject: [PATCH 17/17] net/mlx5e: replace EINVAL in mlx5e_flower_parse_meta()

[ Upstream commit a683012a8e77675a1947cc8f11f97cdc1d5bb769 ]

The drivers reports EINVAL to userspace through netlink on invalid meta
match. This is confusing since EINVAL is usually reserved for malformed
netlink messages. Replace it by more meaningful codes.

Fixes: 6d65bc64e232 ("net/mlx5e: Add mlx5e_flower_parse_meta support")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 4659c205cc01..46ff83408d05 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1824,7 +1824,7 @@ static int mlx5e_flower_parse_meta(struct net_device *filter_dev,
 	flow_rule_match_meta(rule, &match);
 	if (match.mask->ingress_ifindex != 0xFFFFFFFF) {
 		NL_SET_ERR_MSG_MOD(extack, "Unsupported ingress ifindex mask");
-		return -EINVAL;
+		return -EOPNOTSUPP;
 	}
 
 	ingress_dev = __dev_get_by_index(dev_net(filter_dev),
@@ -1832,13 +1832,13 @@ static int mlx5e_flower_parse_meta(struct net_device *filter_dev,
 	if (!ingress_dev) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Can't find the ingress port to match on");
-		return -EINVAL;
+		return -ENOENT;
 	}
 
 	if (ingress_dev != filter_dev) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Can't match on the ingress filter port");
-		return -EINVAL;
+		return -EOPNOTSUPP;
 	}
 
 	return 0;
-- 
2.26.2

Re: [PATCHES] Networking

[Greg KH]

On Sat, Jun 06, 2020 at 07:55:15PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v5.4 and
> v5.6 -stable, respectively.

All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 105 bytes --]


Please queue up the following networking bug fixes for v5.6 and v5.7
-stable, respectively.

Thank you!

[-- Attachment #2: net_56.mbox --]
[-- Type: Application/Octet-Stream, Size: 30235 bytes --]

From 91b5e68473b6046696e529ca7d21dbcd3d28c82f Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Mon, 1 Jun 2020 11:55:03 +0800
Subject: [PATCH 01/11] ipv6: fix IPV6_ADDRFORM operation logic

[ Upstream commit 79a1f0ccdbb4ad700590f61b00525b390cb53905 ]

Socket option IPV6_ADDRFORM supports UDP/UDPLITE and TCP at present.
Previously the checking logic looks like:
if (sk->sk_protocol == IPPROTO_UDP || sk->sk_protocol == IPPROTO_UDPLITE)
	do_some_check;
else if (sk->sk_protocol != IPPROTO_TCP)
	break;

After commit b6f6118901d1 ("ipv6: restrict IPV6_ADDRFORM operation"), TCP
was blocked as the logic changed to:
if (sk->sk_protocol == IPPROTO_UDP || sk->sk_protocol == IPPROTO_UDPLITE)
	do_some_check;
else if (sk->sk_protocol == IPPROTO_TCP)
	do_some_check;
	break;
else
	break;

Then after commit 82c9ae440857 ("ipv6: fix restrict IPV6_ADDRFORM operation")
UDP/UDPLITE were blocked as the logic changed to:
if (sk->sk_protocol == IPPROTO_UDP || sk->sk_protocol == IPPROTO_UDPLITE)
	do_some_check;
if (sk->sk_protocol == IPPROTO_TCP)
	do_some_check;

if (sk->sk_protocol != IPPROTO_TCP)
	break;

Fix it by using Eric's code and simply remove the break in TCP check, which
looks like:
if (sk->sk_protocol == IPPROTO_UDP || sk->sk_protocol == IPPROTO_UDPLITE)
	do_some_check;
else if (sk->sk_protocol == IPPROTO_TCP)
	do_some_check;
else
	break;

Fixes: 82c9ae440857 ("ipv6: fix restrict IPV6_ADDRFORM operation")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ipv6_sockglue.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 18d05403d3b5..5af97b4f5df3 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -183,14 +183,15 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 					retv = -EBUSY;
 					break;
 				}
-			}
-			if (sk->sk_protocol == IPPROTO_TCP &&
-			    sk->sk_prot != &tcpv6_prot) {
-				retv = -EBUSY;
+			} else if (sk->sk_protocol == IPPROTO_TCP) {
+				if (sk->sk_prot != &tcpv6_prot) {
+					retv = -EBUSY;
+					break;
+				}
+			} else {
 				break;
 			}
-			if (sk->sk_protocol != IPPROTO_TCP)
-				break;
+
 			if (sk->sk_state != TCP_ESTABLISHED) {
 				retv = -ENOTCONN;
 				break;
-- 
2.26.2


From 548993c29f849e00c35f3913307dc44d964f2450 Mon Sep 17 00:00:00 2001
From: Vadim Pasternak <vadimp@mellanox.com>
Date: Sun, 7 Jun 2020 11:10:27 +0300
Subject: [PATCH 02/11] mlxsw: core: Use different get_trend() callbacks for
 different thermal zones

[ Upstream commit 2dc2f760052da4925482ecdcdc5c94d4a599153c ]

The driver registers three different types of thermal zones: For the
ASIC itself, for port modules and for gearboxes.

Currently, all three types use the same get_trend() callback which does
not work correctly for the ASIC thermal zone. The callback assumes that
the device data is of type 'struct mlxsw_thermal_module', whereas for
the ASIC thermal zone 'struct mlxsw_thermal' is passed as device data.

Fix this by using one get_trend() callback for the ASIC thermal zone and
another for the other two types.

Fixes: 6f73862fabd9 ("mlxsw: core: Add the hottest thermal zone detection")
Signed-off-by: Vadim Pasternak <vadimp@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/core_thermal.c    | 23 +++++++++++++++----
 1 file changed, 19 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index ce0a6837daa3..05f8d5a92862 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -391,8 +391,7 @@ static int mlxsw_thermal_set_trip_hyst(struct thermal_zone_device *tzdev,
 static int mlxsw_thermal_trend_get(struct thermal_zone_device *tzdev,
 				   int trip, enum thermal_trend *trend)
 {
-	struct mlxsw_thermal_module *tz = tzdev->devdata;
-	struct mlxsw_thermal *thermal = tz->parent;
+	struct mlxsw_thermal *thermal = tzdev->devdata;
 
 	if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS)
 		return -EINVAL;
@@ -593,6 +592,22 @@ mlxsw_thermal_module_trip_hyst_set(struct thermal_zone_device *tzdev, int trip,
 	return 0;
 }
 
+static int mlxsw_thermal_module_trend_get(struct thermal_zone_device *tzdev,
+					  int trip, enum thermal_trend *trend)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+	struct mlxsw_thermal *thermal = tz->parent;
+
+	if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS)
+		return -EINVAL;
+
+	if (tzdev == thermal->tz_highest_dev)
+		return 1;
+
+	*trend = THERMAL_TREND_STABLE;
+	return 0;
+}
+
 static struct thermal_zone_device_ops mlxsw_thermal_module_ops = {
 	.bind		= mlxsw_thermal_module_bind,
 	.unbind		= mlxsw_thermal_module_unbind,
@@ -604,7 +619,7 @@ static struct thermal_zone_device_ops mlxsw_thermal_module_ops = {
 	.set_trip_temp	= mlxsw_thermal_module_trip_temp_set,
 	.get_trip_hyst	= mlxsw_thermal_module_trip_hyst_get,
 	.set_trip_hyst	= mlxsw_thermal_module_trip_hyst_set,
-	.get_trend	= mlxsw_thermal_trend_get,
+	.get_trend	= mlxsw_thermal_module_trend_get,
 };
 
 static int mlxsw_thermal_gearbox_temp_get(struct thermal_zone_device *tzdev,
@@ -643,7 +658,7 @@ static struct thermal_zone_device_ops mlxsw_thermal_gearbox_ops = {
 	.set_trip_temp	= mlxsw_thermal_module_trip_temp_set,
 	.get_trip_hyst	= mlxsw_thermal_module_trip_hyst_get,
 	.set_trip_hyst	= mlxsw_thermal_module_trip_hyst_set,
-	.get_trend	= mlxsw_thermal_trend_get,
+	.get_trend	= mlxsw_thermal_module_trend_get,
 };
 
 static int mlxsw_thermal_get_max_state(struct thermal_cooling_device *cdev,
-- 
2.26.2


From 4c4b4e95a3819758119a050695ce9f9f9de0fc9f Mon Sep 17 00:00:00 2001
From: Vasily Averin <vvs@virtuozzo.com>
Date: Tue, 2 Jun 2020 15:55:26 +0300
Subject: [PATCH 03/11] net_failover: fixed rollback in net_failover_open()

[ Upstream commit e8224bfe77293494626f6eec1884fee7b87d0ced ]

found by smatch:
drivers/net/net_failover.c:65 net_failover_open() error:
 we previously assumed 'primary_dev' could be null (see line 43)

Fixes: cfc80d9a1163 ("net: Introduce net_failover driver")
Signed-off-by: Vasily Averin <vvs@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/net_failover.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/net_failover.c b/drivers/net/net_failover.c
index b16a1221d19b..fb182bec8f06 100644
--- a/drivers/net/net_failover.c
+++ b/drivers/net/net_failover.c
@@ -61,7 +61,8 @@ static int net_failover_open(struct net_device *dev)
 	return 0;
 
 err_standby_open:
-	dev_close(primary_dev);
+	if (primary_dev)
+		dev_close(primary_dev);
 err_primary_open:
 	netif_tx_disable(dev);
 	return err;
-- 
2.26.2


From 2433d3a41363bb8ae8b34891ca20d3d956e710f6 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Sat, 30 May 2020 15:41:31 -0400
Subject: [PATCH 04/11] tun: correct header offsets in napi frags mode

[ Upstream commit 96aa1b22bd6bb9fccf62f6261f390ed6f3e7967f ]

Tun in IFF_NAPI_FRAGS mode calls napi_gro_frags. Unlike netif_rx and
netif_gro_receive, this expects skb->data to point to the mac layer.

But skb_probe_transport_header, __skb_get_hash_symmetric, and
xdp_do_generic in tun_get_user need skb->data to point to the network
header. Flow dissection also needs skb->protocol set, so
eth_type_trans has to be called.

Ensure the link layer header lies in linear as eth_type_trans pulls
ETH_HLEN. Then take the same code paths for frags as for not frags.
Push the link layer header back just before calling napi_gro_frags.

By pulling up to ETH_HLEN from frag0 into linear, this disables the
frag0 optimization in the special case when IFF_NAPI_FRAGS is used
with zero length iov[0] (and thus empty skb->linear).

Fixes: 90e33d459407 ("tun: enable napi_gro_frags() for TUN/TAP driver")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Petar Penkov <ppenkov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 3063f2c9fa63..d720f15cb1dc 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1908,8 +1908,11 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 		skb->dev = tun->dev;
 		break;
 	case IFF_TAP:
-		if (!frags)
-			skb->protocol = eth_type_trans(skb, tun->dev);
+		if (frags && !pskb_may_pull(skb, ETH_HLEN)) {
+			err = -ENOMEM;
+			goto drop;
+		}
+		skb->protocol = eth_type_trans(skb, tun->dev);
 		break;
 	}
 
@@ -1966,9 +1969,12 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	}
 
 	if (frags) {
+		u32 headlen;
+
 		/* Exercise flow dissector code path. */
-		u32 headlen = eth_get_headlen(tun->dev, skb->data,
-					      skb_headlen(skb));
+		skb_push(skb, ETH_HLEN);
+		headlen = eth_get_headlen(tun->dev, skb->data,
+					  skb_headlen(skb));
 
 		if (unlikely(headlen > skb_headlen(skb))) {
 			this_cpu_inc(tun->pcpu_stats->rx_dropped);
-- 
2.26.2


From 4293e4b955803573f7396e1b466b4b9b04ea9616 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Mon, 1 Jun 2020 15:58:54 +0300
Subject: [PATCH 05/11] bridge: Avoid infinite loop when suppressing NS
 messages with invalid options

[ Upstream commit 53fc685243bd6fb90d90305cea54598b78d3cbfc ]

When neighbor suppression is enabled the bridge device might reply to
Neighbor Solicitation (NS) messages on behalf of remote hosts.

In case the NS message includes the "Source link-layer address" option
[1], the bridge device will use the specified address as the link-layer
destination address in its reply.

To avoid an infinite loop, break out of the options parsing loop when
encountering an option with length zero and disregard the NS message.

This is consistent with the IPv6 ndisc code and RFC 4886 which states
that "Nodes MUST silently discard an ND packet that contains an option
with length zero" [2].

[1] https://tools.ietf.org/html/rfc4861#section-4.3
[2] https://tools.ietf.org/html/rfc4861#section-4.6

Fixes: ed842faeb2bd ("bridge: suppress nd pkts on BR_NEIGH_SUPPRESS ports")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Alla Segal <allas@mellanox.com>
Tested-by: Alla Segal <allas@mellanox.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_arp_nd_proxy.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/bridge/br_arp_nd_proxy.c b/net/bridge/br_arp_nd_proxy.c
index 37908561a64b..b18cdf03edb3 100644
--- a/net/bridge/br_arp_nd_proxy.c
+++ b/net/bridge/br_arp_nd_proxy.c
@@ -276,6 +276,10 @@ static void br_nd_send(struct net_bridge *br, struct net_bridge_port *p,
 	ns_olen = request->len - (skb_network_offset(request) +
 				  sizeof(struct ipv6hdr)) - sizeof(*ns);
 	for (i = 0; i < ns_olen - 1; i += (ns->opt[i + 1] << 3)) {
+		if (!ns->opt[i + 1]) {
+			kfree_skb(reply);
+			return;
+		}
 		if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) {
 			daddr = ns->opt + i + sizeof(struct nd_opt_hdr);
 			break;
-- 
2.26.2


From 57c2aab7ccf05c914f184dcb71311e1654b627d6 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Mon, 1 Jun 2020 15:58:55 +0300
Subject: [PATCH 06/11] vxlan: Avoid infinite loop when suppressing NS messages
 with invalid options

[ Upstream commit 8066e6b449e050675df48e7c4b16c29f00507ff0 ]

When proxy mode is enabled the vxlan device might reply to Neighbor
Solicitation (NS) messages on behalf of remote hosts.

In case the NS message includes the "Source link-layer address" option
[1], the vxlan device will use the specified address as the link-layer
destination address in its reply.

To avoid an infinite loop, break out of the options parsing loop when
encountering an option with length zero and disregard the NS message.

This is consistent with the IPv6 ndisc code and RFC 4886 which states
that "Nodes MUST silently discard an ND packet that contains an option
with length zero" [2].

[1] https://tools.ietf.org/html/rfc4861#section-4.3
[2] https://tools.ietf.org/html/rfc4861#section-4.6

Fixes: 4b29dba9c085 ("vxlan: fix nonfunctional neigh_reduce()")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index a5b415fed11e..779e56c43d27 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1924,6 +1924,10 @@ static struct sk_buff *vxlan_na_create(struct sk_buff *request,
 	ns_olen = request->len - skb_network_offset(request) -
 		sizeof(struct ipv6hdr) - sizeof(*ns);
 	for (i = 0; i < ns_olen-1; i += (ns->opt[i+1]<<3)) {
+		if (!ns->opt[i + 1]) {
+			kfree_skb(reply);
+			return NULL;
+		}
 		if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) {
 			daddr = ns->opt + i + sizeof(struct nd_opt_hdr);
 			break;
-- 
2.26.2


From 757ba378c253bfe313b3e305dbe36bffaebfcda1 Mon Sep 17 00:00:00 2001
From: Sameeh Jubran <sameehj@amazon.com>
Date: Wed, 3 Jun 2020 08:50:22 +0000
Subject: [PATCH 07/11] net: ena: xdp: XDP_TX: fix memory leak

[ Upstream commit cd07ecccba13b8bd5023ffe7be57363d07e3105f ]

When sending very high packet rate, the XDP tx queues can get full and
start dropping packets. In this case we don't free the pages which
results in ena driver draining the system memory.

Fix:
Simply free the pages when necessary.

Fixes: 548c4940b9f1 ("net: ena: Implement XDP_TX action")
Signed-off-by: Sameeh Jubran <sameehj@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index cada6e7e30f4..48449efb6039 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -358,7 +358,7 @@ static int ena_xdp_xmit_buff(struct net_device *dev,
 	ena_unmap_tx_buff(xdp_ring, tx_info);
 	tx_info->xdpf = NULL;
 error_drop_packet:
-
+	__free_page(tx_info->xdp_rx_page);
 	return NETDEV_TX_OK;
 }
 
-- 
2.26.2


From a4bd7d196f014a92d4c6d1a951df77e614959316 Mon Sep 17 00:00:00 2001
From: Sameeh Jubran <sameehj@amazon.com>
Date: Wed, 3 Jun 2020 08:50:23 +0000
Subject: [PATCH 08/11] net: ena: xdp: update napi budget for DROP and ABORTED

[ Upstream commit 3921a81c31df6057183aeb7f7d204003bf699d6f ]

This patch fixes two issues with XDP:

1. If the XDP verdict is XDP_ABORTED we break the loop, which results in
   us handling one buffer per napi cycle instead of the total budget
   (usually 64). To overcome this simply change the xdp_verdict check to
   != XDP_PASS. When the verdict is XDP_PASS, the skb is not expected to
   be NULL.

2. Update the residual budget for XDP_DROP and XDP_ABORTED, since
   packets are handled in these cases.

Fixes: 548c4940b9f1 ("net: ena: Implement XDP_TX action")
Signed-off-by: Sameeh Jubran <sameehj@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 48449efb6039..5f6892aa6588 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -1642,11 +1642,9 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi,
 					 &next_to_clean);
 
 		if (unlikely(!skb)) {
-			if (xdp_verdict == XDP_TX) {
+			if (xdp_verdict == XDP_TX)
 				ena_free_rx_page(rx_ring,
 						 &rx_ring->rx_buffer_info[rx_ring->ena_bufs[0].req_id]);
-				res_budget--;
-			}
 			for (i = 0; i < ena_rx_ctx.descs; i++) {
 				rx_ring->free_ids[next_to_clean] =
 					rx_ring->ena_bufs[i].req_id;
@@ -1654,8 +1652,10 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi,
 					ENA_RX_RING_IDX_NEXT(next_to_clean,
 							     rx_ring->ring_size);
 			}
-			if (xdp_verdict == XDP_TX || xdp_verdict == XDP_DROP)
+			if (xdp_verdict != XDP_PASS) {
+				res_budget--;
 				continue;
+			}
 			break;
 		}
 
-- 
2.26.2


From 3e75ead7546674473a2993f8c0cd9a92380665cf Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Tue, 2 Jun 2020 21:49:10 -0700
Subject: [PATCH 09/11] genetlink: fix memory leaks in
 genl_family_rcv_msg_dumpit()

[ Upstream commit c36f05559104b66bcd7f617e931e38c680227b74 ]

There are two kinds of memory leaks in genl_family_rcv_msg_dumpit():

1. Before we call ops->start(), whenever an error happens, we forget
   to free the memory allocated in genl_family_rcv_msg_dumpit().

2. When ops->start() fails, the 'info' has been already installed on
   the per socket control block, so we should not free it here. More
   importantly, nlk->cb_running is still false at this point, so
   netlink_sock_destruct() cannot free it either.

The first kind of memory leaks is easier to resolve, but the second
one requires some deeper thoughts.

After reviewing how netfilter handles this, the most elegant solution
I find is just to use a similar way to allocate the memory, that is,
moving memory allocations from caller into ops->start(). With this,
we can solve both kinds of memory leaks: for 1), no memory allocation
happens before ops->start(); for 2), ops->start() handles its own
failures and 'info' is installed to the socket control block only
when success. The only ugliness here is we have to pass all local
variables on stack via a struct, but this is not hard to understand.

Alternatively, we can introduce a ops->free() to solve this too,
but it is overkill as only genetlink has this problem so far.

Fixes: 1927f41a22a0 ("net: genetlink: introduce dump info struct to be available during dumpit op")
Reported-by: syzbot+21f04f481f449c8db840@syzkaller.appspotmail.com
Cc: "Jason A. Donenfeld" <Jason@zx2c4.com>
Cc: Florian Westphal <fw@strlen.de>
Cc: Pablo Neira Ayuso <pablo@netfilter.org>
Cc: Jiri Pirko <jiri@mellanox.com>
Cc: YueHaibing <yuehaibing@huawei.com>
Cc: Shaochun Chen <cscnull@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/genetlink.c | 94 +++++++++++++++++++++++++----------------
 1 file changed, 58 insertions(+), 36 deletions(-)

diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 9f357aa22b94..bcbba0bef1c2 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -513,15 +513,58 @@ static void genl_family_rcv_msg_attrs_free(const struct genl_family *family,
 		kfree(attrbuf);
 }
 
-static int genl_lock_start(struct netlink_callback *cb)
+struct genl_start_context {
+	const struct genl_family *family;
+	struct nlmsghdr *nlh;
+	struct netlink_ext_ack *extack;
+	const struct genl_ops *ops;
+	int hdrlen;
+};
+
+static int genl_start(struct netlink_callback *cb)
 {
-	const struct genl_ops *ops = genl_dumpit_info(cb)->ops;
+	struct genl_start_context *ctx = cb->data;
+	const struct genl_ops *ops = ctx->ops;
+	struct genl_dumpit_info *info;
+	struct nlattr **attrs = NULL;
 	int rc = 0;
 
+	if (ops->validate & GENL_DONT_VALIDATE_DUMP)
+		goto no_attrs;
+
+	if (ctx->nlh->nlmsg_len < nlmsg_msg_size(ctx->hdrlen))
+		return -EINVAL;
+
+	attrs = genl_family_rcv_msg_attrs_parse(ctx->family, ctx->nlh, ctx->extack,
+						ops, ctx->hdrlen,
+						GENL_DONT_VALIDATE_DUMP_STRICT,
+						true);
+	if (IS_ERR(attrs))
+		return PTR_ERR(attrs);
+
+no_attrs:
+	info = genl_dumpit_info_alloc();
+	if (!info) {
+		kfree(attrs);
+		return -ENOMEM;
+	}
+	info->family = ctx->family;
+	info->ops = ops;
+	info->attrs = attrs;
+
+	cb->data = info;
 	if (ops->start) {
-		genl_lock();
+		if (!ctx->family->parallel_ops)
+			genl_lock();
 		rc = ops->start(cb);
-		genl_unlock();
+		if (!ctx->family->parallel_ops)
+			genl_unlock();
+	}
+
+	if (rc) {
+		kfree(attrs);
+		genl_dumpit_info_free(info);
+		cb->data = NULL;
 	}
 	return rc;
 }
@@ -548,7 +591,7 @@ static int genl_lock_done(struct netlink_callback *cb)
 		rc = ops->done(cb);
 		genl_unlock();
 	}
-	genl_family_rcv_msg_attrs_free(info->family, info->attrs, true);
+	genl_family_rcv_msg_attrs_free(info->family, info->attrs, false);
 	genl_dumpit_info_free(info);
 	return rc;
 }
@@ -573,43 +616,23 @@ static int genl_family_rcv_msg_dumpit(const struct genl_family *family,
 				      const struct genl_ops *ops,
 				      int hdrlen, struct net *net)
 {
-	struct genl_dumpit_info *info;
-	struct nlattr **attrs = NULL;
+	struct genl_start_context ctx;
 	int err;
 
 	if (!ops->dumpit)
 		return -EOPNOTSUPP;
 
-	if (ops->validate & GENL_DONT_VALIDATE_DUMP)
-		goto no_attrs;
-
-	if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen))
-		return -EINVAL;
-
-	attrs = genl_family_rcv_msg_attrs_parse(family, nlh, extack,
-						ops, hdrlen,
-						GENL_DONT_VALIDATE_DUMP_STRICT,
-						true);
-	if (IS_ERR(attrs))
-		return PTR_ERR(attrs);
-
-no_attrs:
-	/* Allocate dumpit info. It is going to be freed by done() callback. */
-	info = genl_dumpit_info_alloc();
-	if (!info) {
-		genl_family_rcv_msg_attrs_free(family, attrs, true);
-		return -ENOMEM;
-	}
-
-	info->family = family;
-	info->ops = ops;
-	info->attrs = attrs;
+	ctx.family = family;
+	ctx.nlh = nlh;
+	ctx.extack = extack;
+	ctx.ops = ops;
+	ctx.hdrlen = hdrlen;
 
 	if (!family->parallel_ops) {
 		struct netlink_dump_control c = {
 			.module = family->module,
-			.data = info,
-			.start = genl_lock_start,
+			.data = &ctx,
+			.start = genl_start,
 			.dump = genl_lock_dumpit,
 			.done = genl_lock_done,
 		};
@@ -617,12 +640,11 @@ static int genl_family_rcv_msg_dumpit(const struct genl_family *family,
 		genl_unlock();
 		err = __netlink_dump_start(net->genl_sock, skb, nlh, &c);
 		genl_lock();
-
 	} else {
 		struct netlink_dump_control c = {
 			.module = family->module,
-			.data = info,
-			.start = ops->start,
+			.data = &ctx,
+			.start = genl_start,
 			.dump = ops->dumpit,
 			.done = genl_parallel_done,
 		};
-- 
2.26.2


From 56f1ff416af597c4008a00253cd183b7f29b2a66 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Michal=20Vok=C3=A1=C4=8D?= <michal.vokac@ysoft.com>
Date: Wed, 3 Jun 2020 13:31:39 +0200
Subject: [PATCH 10/11] net: dsa: qca8k: Fix "Unexpected gfp" kernel exception
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 67122a7910bf2135dc7f7ececfcf16a5bdb362c1 ]

Commit 7e99e3470172 ("net: dsa: remove dsa_switch_alloc helper")
replaced the dsa_switch_alloc helper by devm_kzalloc in all DSA
drivers. Unfortunately it introduced a typo in qca8k.c driver and
wrong argument is passed to the devm_kzalloc function.

This fix mitigates the following kernel exception:

  Unexpected gfp: 0x6 (__GFP_HIGHMEM|GFP_DMA32). Fixing up to gfp: 0x101 (GFP_DMA|__GFP_ZERO). Fix your code!
  CPU: 1 PID: 44 Comm: kworker/1:1 Not tainted 5.5.9-yocto-ua #1
  Hardware name: Freescale i.MX6 Quad/DualLite (Device Tree)
  Workqueue: events deferred_probe_work_func
  [<c0014924>] (unwind_backtrace) from [<c00123bc>] (show_stack+0x10/0x14)
  [<c00123bc>] (show_stack) from [<c04c8fb4>] (dump_stack+0x90/0xa4)
  [<c04c8fb4>] (dump_stack) from [<c00e1b10>] (new_slab+0x20c/0x214)
  [<c00e1b10>] (new_slab) from [<c00e1cd0>] (___slab_alloc.constprop.0+0x1b8/0x540)
  [<c00e1cd0>] (___slab_alloc.constprop.0) from [<c00e2074>] (__slab_alloc.constprop.0+0x1c/0x24)
  [<c00e2074>] (__slab_alloc.constprop.0) from [<c00e4538>] (__kmalloc_track_caller+0x1b0/0x298)
  [<c00e4538>] (__kmalloc_track_caller) from [<c02cccac>] (devm_kmalloc+0x24/0x70)
  [<c02cccac>] (devm_kmalloc) from [<c030d888>] (qca8k_sw_probe+0x94/0x1ac)
  [<c030d888>] (qca8k_sw_probe) from [<c0304788>] (mdio_probe+0x30/0x54)
  [<c0304788>] (mdio_probe) from [<c02c93bc>] (really_probe+0x1e0/0x348)
  [<c02c93bc>] (really_probe) from [<c02c9884>] (driver_probe_device+0x60/0x16c)
  [<c02c9884>] (driver_probe_device) from [<c02c7fb0>] (bus_for_each_drv+0x70/0x94)
  [<c02c7fb0>] (bus_for_each_drv) from [<c02c9708>] (__device_attach+0xb4/0x11c)
  [<c02c9708>] (__device_attach) from [<c02c8148>] (bus_probe_device+0x84/0x8c)
  [<c02c8148>] (bus_probe_device) from [<c02c8cec>] (deferred_probe_work_func+0x64/0x90)
  [<c02c8cec>] (deferred_probe_work_func) from [<c0033c14>] (process_one_work+0x1d4/0x41c)
  [<c0033c14>] (process_one_work) from [<c00340a4>] (worker_thread+0x248/0x528)
  [<c00340a4>] (worker_thread) from [<c0039148>] (kthread+0x124/0x150)
  [<c0039148>] (kthread) from [<c00090d8>] (ret_from_fork+0x14/0x3c)
  Exception stack(0xee1b5fb0 to 0xee1b5ff8)
  5fa0:                                     00000000 00000000 00000000 00000000
  5fc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
  5fe0: 00000000 00000000 00000000 00000000 00000013 00000000
  qca8k 2188000.ethernet-1:0a: Using legacy PHYLIB callbacks. Please migrate to PHYLINK!
  qca8k 2188000.ethernet-1:0a eth2 (uninitialized): PHY [2188000.ethernet-1:01] driver [Generic PHY]
  qca8k 2188000.ethernet-1:0a eth1 (uninitialized): PHY [2188000.ethernet-1:02] driver [Generic PHY]

Fixes: 7e99e3470172 ("net: dsa: remove dsa_switch_alloc helper")
Signed-off-by: Michal Vokáč <michal.vokac@ysoft.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/qca8k.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c
index 9f4205b4439b..d2b5ab403e06 100644
--- a/drivers/net/dsa/qca8k.c
+++ b/drivers/net/dsa/qca8k.c
@@ -1079,8 +1079,7 @@ qca8k_sw_probe(struct mdio_device *mdiodev)
 	if (id != QCA8K_ID_QCA8337)
 		return -ENODEV;
 
-	priv->ds = devm_kzalloc(&mdiodev->dev, sizeof(*priv->ds),
-				QCA8K_NUM_PORTS);
+	priv->ds = devm_kzalloc(&mdiodev->dev, sizeof(*priv->ds), GFP_KERNEL);
 	if (!priv->ds)
 		return -ENOMEM;
 
-- 
2.26.2


From f48ca9fbe2d18f77c6cf834f82b75287dd2ffcb5 Mon Sep 17 00:00:00 2001
From: Tuong Lien <tuong.t.lien@dektech.com.au>
Date: Wed, 3 Jun 2020 12:06:01 +0700
Subject: [PATCH 11/11] tipc: fix NULL pointer dereference in streaming

[ Upstream commit 5e9eeccc58f3e6bcc99b929670665d2ce047e9c9 ]

syzbot found the following crash:

general protection fault, probably for non-canonical address 0xdffffc0000000019: 0000 [#1] PREEMPT SMP KASAN
KASAN: null-ptr-deref in range [0x00000000000000c8-0x00000000000000cf]
CPU: 1 PID: 7060 Comm: syz-executor394 Not tainted 5.7.0-rc6-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:__tipc_sendstream+0xbde/0x11f0 net/tipc/socket.c:1591
Code: 00 00 00 00 48 39 5c 24 28 48 0f 44 d8 e8 fa 3e db f9 48 b8 00 00 00 00 00 fc ff df 48 8d bb c8 00 00 00 48 89 fa 48 c1 ea 03 <80> 3c 02 00 0f 85 e2 04 00 00 48 8b 9b c8 00 00 00 48 b8 00 00 00
RSP: 0018:ffffc90003ef7818 EFLAGS: 00010202
RAX: dffffc0000000000 RBX: 0000000000000000 RCX: ffffffff8797fd9d
RDX: 0000000000000019 RSI: ffffffff8797fde6 RDI: 00000000000000c8
RBP: ffff888099848040 R08: ffff88809a5f6440 R09: fffffbfff1860b4c
R10: ffffffff8c305a5f R11: fffffbfff1860b4b R12: ffff88809984857e
R13: 0000000000000000 R14: ffff888086aa4000 R15: 0000000000000000
FS:  00000000009b4880(0000) GS:ffff8880ae700000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000020000140 CR3: 00000000a7fdf000 CR4: 00000000001406e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 tipc_sendstream+0x4c/0x70 net/tipc/socket.c:1533
 sock_sendmsg_nosec net/socket.c:652 [inline]
 sock_sendmsg+0xcf/0x120 net/socket.c:672
 ____sys_sendmsg+0x32f/0x810 net/socket.c:2352
 ___sys_sendmsg+0x100/0x170 net/socket.c:2406
 __sys_sendmmsg+0x195/0x480 net/socket.c:2496
 __do_sys_sendmmsg net/socket.c:2525 [inline]
 __se_sys_sendmmsg net/socket.c:2522 [inline]
 __x64_sys_sendmmsg+0x99/0x100 net/socket.c:2522
 do_syscall_64+0xf6/0x7d0 arch/x86/entry/common.c:295
 entry_SYSCALL_64_after_hwframe+0x49/0xb3
RIP: 0033:0x440199
...

This bug was bisected to commit 0a3e060f340d ("tipc: add test for Nagle
algorithm effectiveness"). However, it is not the case, the trouble was
from the base in the case of zero data length message sending, we would
unexpectedly make an empty 'txq' queue after the 'tipc_msg_append()' in
Nagle mode.

A similar crash can be generated even without the bisected patch but at
the link layer when it accesses the empty queue.

We solve the issues by building at least one buffer to go with socket's
header and an optional data section that may be empty like what we had
with the 'tipc_msg_build()'.

Note: the previous commit 4c21daae3dbc ("tipc: Fix NULL pointer
dereference in __tipc_sendstream()") is obsoleted by this one since the
'txq' will be never empty and the check of 'skb != NULL' is unnecessary
but it is safe anyway.

Reported-by: syzbot+8eac6d030e7807c21d32@syzkaller.appspotmail.com
Fixes: c0bceb97db9e ("tipc: add smart nagle feature")
Acked-by: Jon Maloy <jmaloy@redhat.com>
Signed-off-by: Tuong Lien <tuong.t.lien@dektech.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/msg.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index 0d515d20b056..bf17b13009d1 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -221,7 +221,7 @@ int tipc_msg_append(struct tipc_msg *_hdr, struct msghdr *m, int dlen,
 	accounted = skb ? msg_blocks(buf_msg(skb)) : 0;
 	total = accounted;
 
-	while (rem) {
+	do {
 		if (!skb || skb->len >= mss) {
 			prev = skb;
 			skb = tipc_buf_acquire(mss, GFP_KERNEL);
@@ -249,7 +249,7 @@ int tipc_msg_append(struct tipc_msg *_hdr, struct msghdr *m, int dlen,
 		skb_put(skb, cpy);
 		rem -= cpy;
 		total += msg_blocks(hdr) - curr;
-	}
+	} while (rem);
 	return total - accounted;
 }
 
-- 
2.26.2


[-- Attachment #3: net_57.mbox --]
[-- Type: Application/Octet-Stream, Size: 31590 bytes --]

From 99ea2424c8bb0fb18ac4b64f2704e2d5fefa6ccd Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Mon, 1 Jun 2020 11:55:03 +0800
Subject: [PATCH 01/12] ipv6: fix IPV6_ADDRFORM operation logic

[ Upstream commit 79a1f0ccdbb4ad700590f61b00525b390cb53905 ]

Socket option IPV6_ADDRFORM supports UDP/UDPLITE and TCP at present.
Previously the checking logic looks like:
if (sk->sk_protocol == IPPROTO_UDP || sk->sk_protocol == IPPROTO_UDPLITE)
	do_some_check;
else if (sk->sk_protocol != IPPROTO_TCP)
	break;

After commit b6f6118901d1 ("ipv6: restrict IPV6_ADDRFORM operation"), TCP
was blocked as the logic changed to:
if (sk->sk_protocol == IPPROTO_UDP || sk->sk_protocol == IPPROTO_UDPLITE)
	do_some_check;
else if (sk->sk_protocol == IPPROTO_TCP)
	do_some_check;
	break;
else
	break;

Then after commit 82c9ae440857 ("ipv6: fix restrict IPV6_ADDRFORM operation")
UDP/UDPLITE were blocked as the logic changed to:
if (sk->sk_protocol == IPPROTO_UDP || sk->sk_protocol == IPPROTO_UDPLITE)
	do_some_check;
if (sk->sk_protocol == IPPROTO_TCP)
	do_some_check;

if (sk->sk_protocol != IPPROTO_TCP)
	break;

Fix it by using Eric's code and simply remove the break in TCP check, which
looks like:
if (sk->sk_protocol == IPPROTO_UDP || sk->sk_protocol == IPPROTO_UDPLITE)
	do_some_check;
else if (sk->sk_protocol == IPPROTO_TCP)
	do_some_check;
else
	break;

Fixes: 82c9ae440857 ("ipv6: fix restrict IPV6_ADDRFORM operation")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ipv6_sockglue.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 18d05403d3b5..5af97b4f5df3 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -183,14 +183,15 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 					retv = -EBUSY;
 					break;
 				}
-			}
-			if (sk->sk_protocol == IPPROTO_TCP &&
-			    sk->sk_prot != &tcpv6_prot) {
-				retv = -EBUSY;
+			} else if (sk->sk_protocol == IPPROTO_TCP) {
+				if (sk->sk_prot != &tcpv6_prot) {
+					retv = -EBUSY;
+					break;
+				}
+			} else {
 				break;
 			}
-			if (sk->sk_protocol != IPPROTO_TCP)
-				break;
+
 			if (sk->sk_state != TCP_ESTABLISHED) {
 				retv = -ENOTCONN;
 				break;
-- 
2.26.2


From 51299af814aceb3c5e7ed7c3b832c6f48637d6cb Mon Sep 17 00:00:00 2001
From: Vadim Pasternak <vadimp@mellanox.com>
Date: Sun, 7 Jun 2020 11:10:27 +0300
Subject: [PATCH 02/12] mlxsw: core: Use different get_trend() callbacks for
 different thermal zones

[ Upstream commit 2dc2f760052da4925482ecdcdc5c94d4a599153c ]

The driver registers three different types of thermal zones: For the
ASIC itself, for port modules and for gearboxes.

Currently, all three types use the same get_trend() callback which does
not work correctly for the ASIC thermal zone. The callback assumes that
the device data is of type 'struct mlxsw_thermal_module', whereas for
the ASIC thermal zone 'struct mlxsw_thermal' is passed as device data.

Fix this by using one get_trend() callback for the ASIC thermal zone and
another for the other two types.

Fixes: 6f73862fabd9 ("mlxsw: core: Add the hottest thermal zone detection")
Signed-off-by: Vadim Pasternak <vadimp@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/core_thermal.c    | 23 +++++++++++++++----
 1 file changed, 19 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index ce0a6837daa3..05f8d5a92862 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -391,8 +391,7 @@ static int mlxsw_thermal_set_trip_hyst(struct thermal_zone_device *tzdev,
 static int mlxsw_thermal_trend_get(struct thermal_zone_device *tzdev,
 				   int trip, enum thermal_trend *trend)
 {
-	struct mlxsw_thermal_module *tz = tzdev->devdata;
-	struct mlxsw_thermal *thermal = tz->parent;
+	struct mlxsw_thermal *thermal = tzdev->devdata;
 
 	if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS)
 		return -EINVAL;
@@ -593,6 +592,22 @@ mlxsw_thermal_module_trip_hyst_set(struct thermal_zone_device *tzdev, int trip,
 	return 0;
 }
 
+static int mlxsw_thermal_module_trend_get(struct thermal_zone_device *tzdev,
+					  int trip, enum thermal_trend *trend)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+	struct mlxsw_thermal *thermal = tz->parent;
+
+	if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS)
+		return -EINVAL;
+
+	if (tzdev == thermal->tz_highest_dev)
+		return 1;
+
+	*trend = THERMAL_TREND_STABLE;
+	return 0;
+}
+
 static struct thermal_zone_device_ops mlxsw_thermal_module_ops = {
 	.bind		= mlxsw_thermal_module_bind,
 	.unbind		= mlxsw_thermal_module_unbind,
@@ -604,7 +619,7 @@ static struct thermal_zone_device_ops mlxsw_thermal_module_ops = {
 	.set_trip_temp	= mlxsw_thermal_module_trip_temp_set,
 	.get_trip_hyst	= mlxsw_thermal_module_trip_hyst_get,
 	.set_trip_hyst	= mlxsw_thermal_module_trip_hyst_set,
-	.get_trend	= mlxsw_thermal_trend_get,
+	.get_trend	= mlxsw_thermal_module_trend_get,
 };
 
 static int mlxsw_thermal_gearbox_temp_get(struct thermal_zone_device *tzdev,
@@ -643,7 +658,7 @@ static struct thermal_zone_device_ops mlxsw_thermal_gearbox_ops = {
 	.set_trip_temp	= mlxsw_thermal_module_trip_temp_set,
 	.get_trip_hyst	= mlxsw_thermal_module_trip_hyst_get,
 	.set_trip_hyst	= mlxsw_thermal_module_trip_hyst_set,
-	.get_trend	= mlxsw_thermal_trend_get,
+	.get_trend	= mlxsw_thermal_module_trend_get,
 };
 
 static int mlxsw_thermal_get_max_state(struct thermal_cooling_device *cdev,
-- 
2.26.2


From 1a5d4b4653cea2102d5e4bad7c2d7137eacce30e Mon Sep 17 00:00:00 2001
From: Vasily Averin <vvs@virtuozzo.com>
Date: Tue, 2 Jun 2020 15:55:26 +0300
Subject: [PATCH 03/12] net_failover: fixed rollback in net_failover_open()

[ Upstream commit e8224bfe77293494626f6eec1884fee7b87d0ced ]

found by smatch:
drivers/net/net_failover.c:65 net_failover_open() error:
 we previously assumed 'primary_dev' could be null (see line 43)

Fixes: cfc80d9a1163 ("net: Introduce net_failover driver")
Signed-off-by: Vasily Averin <vvs@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/net_failover.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/net_failover.c b/drivers/net/net_failover.c
index b16a1221d19b..fb182bec8f06 100644
--- a/drivers/net/net_failover.c
+++ b/drivers/net/net_failover.c
@@ -61,7 +61,8 @@ static int net_failover_open(struct net_device *dev)
 	return 0;
 
 err_standby_open:
-	dev_close(primary_dev);
+	if (primary_dev)
+		dev_close(primary_dev);
 err_primary_open:
 	netif_tx_disable(dev);
 	return err;
-- 
2.26.2


From 2c464c9ac6788422973e8be7a2410dfcd9d7e13c Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Sat, 30 May 2020 15:41:31 -0400
Subject: [PATCH 04/12] tun: correct header offsets in napi frags mode

[ Upstream commit 96aa1b22bd6bb9fccf62f6261f390ed6f3e7967f ]

Tun in IFF_NAPI_FRAGS mode calls napi_gro_frags. Unlike netif_rx and
netif_gro_receive, this expects skb->data to point to the mac layer.

But skb_probe_transport_header, __skb_get_hash_symmetric, and
xdp_do_generic in tun_get_user need skb->data to point to the network
header. Flow dissection also needs skb->protocol set, so
eth_type_trans has to be called.

Ensure the link layer header lies in linear as eth_type_trans pulls
ETH_HLEN. Then take the same code paths for frags as for not frags.
Push the link layer header back just before calling napi_gro_frags.

By pulling up to ETH_HLEN from frag0 into linear, this disables the
frag0 optimization in the special case when IFF_NAPI_FRAGS is used
with zero length iov[0] (and thus empty skb->linear).

Fixes: 90e33d459407 ("tun: enable napi_gro_frags() for TUN/TAP driver")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Petar Penkov <ppenkov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 44889eba1dbc..b984733c6c31 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1871,8 +1871,11 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 		skb->dev = tun->dev;
 		break;
 	case IFF_TAP:
-		if (!frags)
-			skb->protocol = eth_type_trans(skb, tun->dev);
+		if (frags && !pskb_may_pull(skb, ETH_HLEN)) {
+			err = -ENOMEM;
+			goto drop;
+		}
+		skb->protocol = eth_type_trans(skb, tun->dev);
 		break;
 	}
 
@@ -1929,9 +1932,12 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	}
 
 	if (frags) {
+		u32 headlen;
+
 		/* Exercise flow dissector code path. */
-		u32 headlen = eth_get_headlen(tun->dev, skb->data,
-					      skb_headlen(skb));
+		skb_push(skb, ETH_HLEN);
+		headlen = eth_get_headlen(tun->dev, skb->data,
+					  skb_headlen(skb));
 
 		if (unlikely(headlen > skb_headlen(skb))) {
 			this_cpu_inc(tun->pcpu_stats->rx_dropped);
-- 
2.26.2


From 94e27601d318a877971a9c66771cc11b4e3c1eec Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Mon, 1 Jun 2020 15:58:54 +0300
Subject: [PATCH 05/12] bridge: Avoid infinite loop when suppressing NS
 messages with invalid options

[ Upstream commit 53fc685243bd6fb90d90305cea54598b78d3cbfc ]

When neighbor suppression is enabled the bridge device might reply to
Neighbor Solicitation (NS) messages on behalf of remote hosts.

In case the NS message includes the "Source link-layer address" option
[1], the bridge device will use the specified address as the link-layer
destination address in its reply.

To avoid an infinite loop, break out of the options parsing loop when
encountering an option with length zero and disregard the NS message.

This is consistent with the IPv6 ndisc code and RFC 4886 which states
that "Nodes MUST silently discard an ND packet that contains an option
with length zero" [2].

[1] https://tools.ietf.org/html/rfc4861#section-4.3
[2] https://tools.ietf.org/html/rfc4861#section-4.6

Fixes: ed842faeb2bd ("bridge: suppress nd pkts on BR_NEIGH_SUPPRESS ports")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Alla Segal <allas@mellanox.com>
Tested-by: Alla Segal <allas@mellanox.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_arp_nd_proxy.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/bridge/br_arp_nd_proxy.c b/net/bridge/br_arp_nd_proxy.c
index 37908561a64b..b18cdf03edb3 100644
--- a/net/bridge/br_arp_nd_proxy.c
+++ b/net/bridge/br_arp_nd_proxy.c
@@ -276,6 +276,10 @@ static void br_nd_send(struct net_bridge *br, struct net_bridge_port *p,
 	ns_olen = request->len - (skb_network_offset(request) +
 				  sizeof(struct ipv6hdr)) - sizeof(*ns);
 	for (i = 0; i < ns_olen - 1; i += (ns->opt[i + 1] << 3)) {
+		if (!ns->opt[i + 1]) {
+			kfree_skb(reply);
+			return;
+		}
 		if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) {
 			daddr = ns->opt + i + sizeof(struct nd_opt_hdr);
 			break;
-- 
2.26.2


From 82f4453f632f93ff11701ab064b223be8a8dbb3b Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Mon, 1 Jun 2020 15:58:55 +0300
Subject: [PATCH 06/12] vxlan: Avoid infinite loop when suppressing NS messages
 with invalid options

[ Upstream commit 8066e6b449e050675df48e7c4b16c29f00507ff0 ]

When proxy mode is enabled the vxlan device might reply to Neighbor
Solicitation (NS) messages on behalf of remote hosts.

In case the NS message includes the "Source link-layer address" option
[1], the vxlan device will use the specified address as the link-layer
destination address in its reply.

To avoid an infinite loop, break out of the options parsing loop when
encountering an option with length zero and disregard the NS message.

This is consistent with the IPv6 ndisc code and RFC 4886 which states
that "Nodes MUST silently discard an ND packet that contains an option
with length zero" [2].

[1] https://tools.ietf.org/html/rfc4861#section-4.3
[2] https://tools.ietf.org/html/rfc4861#section-4.6

Fixes: 4b29dba9c085 ("vxlan: fix nonfunctional neigh_reduce()")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index a5b415fed11e..779e56c43d27 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1924,6 +1924,10 @@ static struct sk_buff *vxlan_na_create(struct sk_buff *request,
 	ns_olen = request->len - skb_network_offset(request) -
 		sizeof(struct ipv6hdr) - sizeof(*ns);
 	for (i = 0; i < ns_olen-1; i += (ns->opt[i+1]<<3)) {
+		if (!ns->opt[i + 1]) {
+			kfree_skb(reply);
+			return NULL;
+		}
 		if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) {
 			daddr = ns->opt + i + sizeof(struct nd_opt_hdr);
 			break;
-- 
2.26.2


From e2d40a30e1ecf4965332ef845aba8d6962c0229d Mon Sep 17 00:00:00 2001
From: Sameeh Jubran <sameehj@amazon.com>
Date: Wed, 3 Jun 2020 08:50:22 +0000
Subject: [PATCH 07/12] net: ena: xdp: XDP_TX: fix memory leak

[ Upstream commit cd07ecccba13b8bd5023ffe7be57363d07e3105f ]

When sending very high packet rate, the XDP tx queues can get full and
start dropping packets. In this case we don't free the pages which
results in ena driver draining the system memory.

Fix:
Simply free the pages when necessary.

Fixes: 548c4940b9f1 ("net: ena: Implement XDP_TX action")
Signed-off-by: Sameeh Jubran <sameehj@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 2cc765df8da3..23f96d300bfa 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -355,7 +355,7 @@ static int ena_xdp_xmit_buff(struct net_device *dev,
 	ena_unmap_tx_buff(xdp_ring, tx_info);
 	tx_info->xdpf = NULL;
 error_drop_packet:
-
+	__free_page(tx_info->xdp_rx_page);
 	return NETDEV_TX_OK;
 }
 
-- 
2.26.2


From 8e971642c99b4a3acb17265d54bf536c7415ed1c Mon Sep 17 00:00:00 2001
From: Sameeh Jubran <sameehj@amazon.com>
Date: Wed, 3 Jun 2020 08:50:23 +0000
Subject: [PATCH 08/12] net: ena: xdp: update napi budget for DROP and ABORTED

[ Upstream commit 3921a81c31df6057183aeb7f7d204003bf699d6f ]

This patch fixes two issues with XDP:

1. If the XDP verdict is XDP_ABORTED we break the loop, which results in
   us handling one buffer per napi cycle instead of the total budget
   (usually 64). To overcome this simply change the xdp_verdict check to
   != XDP_PASS. When the verdict is XDP_PASS, the skb is not expected to
   be NULL.

2. Update the residual budget for XDP_DROP and XDP_ABORTED, since
   packets are handled in these cases.

Fixes: 548c4940b9f1 ("net: ena: Implement XDP_TX action")
Signed-off-by: Sameeh Jubran <sameehj@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 23f96d300bfa..15ce93be05ea 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -1638,11 +1638,9 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi,
 					 &next_to_clean);
 
 		if (unlikely(!skb)) {
-			if (xdp_verdict == XDP_TX) {
+			if (xdp_verdict == XDP_TX)
 				ena_free_rx_page(rx_ring,
 						 &rx_ring->rx_buffer_info[rx_ring->ena_bufs[0].req_id]);
-				res_budget--;
-			}
 			for (i = 0; i < ena_rx_ctx.descs; i++) {
 				rx_ring->free_ids[next_to_clean] =
 					rx_ring->ena_bufs[i].req_id;
@@ -1650,8 +1648,10 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi,
 					ENA_RX_RING_IDX_NEXT(next_to_clean,
 							     rx_ring->ring_size);
 			}
-			if (xdp_verdict == XDP_TX || xdp_verdict == XDP_DROP)
+			if (xdp_verdict != XDP_PASS) {
+				res_budget--;
 				continue;
+			}
 			break;
 		}
 
-- 
2.26.2


From ee6cf371f241f5e8c2814f2c5ab3c5ad0befdec4 Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliangtang@gmail.com>
Date: Mon, 8 Jun 2020 18:47:54 +0800
Subject: [PATCH 09/12] mptcp: bugfix for RM_ADDR option parsing

[ Upstream commit 8e60eed6b38e464e8c9d68f9caecafaa554dffe0 ]

In MPTCPOPT_RM_ADDR option parsing, the pointer "ptr" pointed to the
"Subtype" octet, the pointer "ptr+1" pointed to the "Address ID" octet:

  +-------+-------+---------------+
  |Subtype|(resvd)|   Address ID  |
  +-------+-------+---------------+
  |               |
 ptr            ptr+1

We should set mp_opt->rm_id to the value of "ptr+1", not "ptr". This patch
will fix this bug.

Fixes: 3df523ab582c ("mptcp: Add ADD_ADDR handling")
Signed-off-by: Geliang Tang <geliangtang@gmail.com>
Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/options.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 7793b6011fa7..1c20dd14b2aa 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -273,6 +273,8 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 		if (opsize != TCPOLEN_MPTCP_RM_ADDR_BASE)
 			break;
 
+		ptr++;
+
 		mp_opt->rm_addr = 1;
 		mp_opt->rm_id = *ptr++;
 		pr_debug("RM_ADDR: id=%d", mp_opt->rm_id);
-- 
2.26.2


From a31d098241827d95668f783a4a97cbd9d12c843d Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Tue, 2 Jun 2020 21:49:10 -0700
Subject: [PATCH 10/12] genetlink: fix memory leaks in
 genl_family_rcv_msg_dumpit()

[ Upstream commit c36f05559104b66bcd7f617e931e38c680227b74 ]

There are two kinds of memory leaks in genl_family_rcv_msg_dumpit():

1. Before we call ops->start(), whenever an error happens, we forget
   to free the memory allocated in genl_family_rcv_msg_dumpit().

2. When ops->start() fails, the 'info' has been already installed on
   the per socket control block, so we should not free it here. More
   importantly, nlk->cb_running is still false at this point, so
   netlink_sock_destruct() cannot free it either.

The first kind of memory leaks is easier to resolve, but the second
one requires some deeper thoughts.

After reviewing how netfilter handles this, the most elegant solution
I find is just to use a similar way to allocate the memory, that is,
moving memory allocations from caller into ops->start(). With this,
we can solve both kinds of memory leaks: for 1), no memory allocation
happens before ops->start(); for 2), ops->start() handles its own
failures and 'info' is installed to the socket control block only
when success. The only ugliness here is we have to pass all local
variables on stack via a struct, but this is not hard to understand.

Alternatively, we can introduce a ops->free() to solve this too,
but it is overkill as only genetlink has this problem so far.

Fixes: 1927f41a22a0 ("net: genetlink: introduce dump info struct to be available during dumpit op")
Reported-by: syzbot+21f04f481f449c8db840@syzkaller.appspotmail.com
Cc: "Jason A. Donenfeld" <Jason@zx2c4.com>
Cc: Florian Westphal <fw@strlen.de>
Cc: Pablo Neira Ayuso <pablo@netfilter.org>
Cc: Jiri Pirko <jiri@mellanox.com>
Cc: YueHaibing <yuehaibing@huawei.com>
Cc: Shaochun Chen <cscnull@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/genetlink.c | 94 +++++++++++++++++++++++++----------------
 1 file changed, 58 insertions(+), 36 deletions(-)

diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 9f357aa22b94..bcbba0bef1c2 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -513,15 +513,58 @@ static void genl_family_rcv_msg_attrs_free(const struct genl_family *family,
 		kfree(attrbuf);
 }
 
-static int genl_lock_start(struct netlink_callback *cb)
+struct genl_start_context {
+	const struct genl_family *family;
+	struct nlmsghdr *nlh;
+	struct netlink_ext_ack *extack;
+	const struct genl_ops *ops;
+	int hdrlen;
+};
+
+static int genl_start(struct netlink_callback *cb)
 {
-	const struct genl_ops *ops = genl_dumpit_info(cb)->ops;
+	struct genl_start_context *ctx = cb->data;
+	const struct genl_ops *ops = ctx->ops;
+	struct genl_dumpit_info *info;
+	struct nlattr **attrs = NULL;
 	int rc = 0;
 
+	if (ops->validate & GENL_DONT_VALIDATE_DUMP)
+		goto no_attrs;
+
+	if (ctx->nlh->nlmsg_len < nlmsg_msg_size(ctx->hdrlen))
+		return -EINVAL;
+
+	attrs = genl_family_rcv_msg_attrs_parse(ctx->family, ctx->nlh, ctx->extack,
+						ops, ctx->hdrlen,
+						GENL_DONT_VALIDATE_DUMP_STRICT,
+						true);
+	if (IS_ERR(attrs))
+		return PTR_ERR(attrs);
+
+no_attrs:
+	info = genl_dumpit_info_alloc();
+	if (!info) {
+		kfree(attrs);
+		return -ENOMEM;
+	}
+	info->family = ctx->family;
+	info->ops = ops;
+	info->attrs = attrs;
+
+	cb->data = info;
 	if (ops->start) {
-		genl_lock();
+		if (!ctx->family->parallel_ops)
+			genl_lock();
 		rc = ops->start(cb);
-		genl_unlock();
+		if (!ctx->family->parallel_ops)
+			genl_unlock();
+	}
+
+	if (rc) {
+		kfree(attrs);
+		genl_dumpit_info_free(info);
+		cb->data = NULL;
 	}
 	return rc;
 }
@@ -548,7 +591,7 @@ static int genl_lock_done(struct netlink_callback *cb)
 		rc = ops->done(cb);
 		genl_unlock();
 	}
-	genl_family_rcv_msg_attrs_free(info->family, info->attrs, true);
+	genl_family_rcv_msg_attrs_free(info->family, info->attrs, false);
 	genl_dumpit_info_free(info);
 	return rc;
 }
@@ -573,43 +616,23 @@ static int genl_family_rcv_msg_dumpit(const struct genl_family *family,
 				      const struct genl_ops *ops,
 				      int hdrlen, struct net *net)
 {
-	struct genl_dumpit_info *info;
-	struct nlattr **attrs = NULL;
+	struct genl_start_context ctx;
 	int err;
 
 	if (!ops->dumpit)
 		return -EOPNOTSUPP;
 
-	if (ops->validate & GENL_DONT_VALIDATE_DUMP)
-		goto no_attrs;
-
-	if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen))
-		return -EINVAL;
-
-	attrs = genl_family_rcv_msg_attrs_parse(family, nlh, extack,
-						ops, hdrlen,
-						GENL_DONT_VALIDATE_DUMP_STRICT,
-						true);
-	if (IS_ERR(attrs))
-		return PTR_ERR(attrs);
-
-no_attrs:
-	/* Allocate dumpit info. It is going to be freed by done() callback. */
-	info = genl_dumpit_info_alloc();
-	if (!info) {
-		genl_family_rcv_msg_attrs_free(family, attrs, true);
-		return -ENOMEM;
-	}
-
-	info->family = family;
-	info->ops = ops;
-	info->attrs = attrs;
+	ctx.family = family;
+	ctx.nlh = nlh;
+	ctx.extack = extack;
+	ctx.ops = ops;
+	ctx.hdrlen = hdrlen;
 
 	if (!family->parallel_ops) {
 		struct netlink_dump_control c = {
 			.module = family->module,
-			.data = info,
-			.start = genl_lock_start,
+			.data = &ctx,
+			.start = genl_start,
 			.dump = genl_lock_dumpit,
 			.done = genl_lock_done,
 		};
@@ -617,12 +640,11 @@ static int genl_family_rcv_msg_dumpit(const struct genl_family *family,
 		genl_unlock();
 		err = __netlink_dump_start(net->genl_sock, skb, nlh, &c);
 		genl_lock();
-
 	} else {
 		struct netlink_dump_control c = {
 			.module = family->module,
-			.data = info,
-			.start = ops->start,
+			.data = &ctx,
+			.start = genl_start,
 			.dump = ops->dumpit,
 			.done = genl_parallel_done,
 		};
-- 
2.26.2


From 393a03e848e3b1acce03a5f2a8aff8c135344fe1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Michal=20Vok=C3=A1=C4=8D?= <michal.vokac@ysoft.com>
Date: Wed, 3 Jun 2020 13:31:39 +0200
Subject: [PATCH 11/12] net: dsa: qca8k: Fix "Unexpected gfp" kernel exception
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 67122a7910bf2135dc7f7ececfcf16a5bdb362c1 ]

Commit 7e99e3470172 ("net: dsa: remove dsa_switch_alloc helper")
replaced the dsa_switch_alloc helper by devm_kzalloc in all DSA
drivers. Unfortunately it introduced a typo in qca8k.c driver and
wrong argument is passed to the devm_kzalloc function.

This fix mitigates the following kernel exception:

  Unexpected gfp: 0x6 (__GFP_HIGHMEM|GFP_DMA32). Fixing up to gfp: 0x101 (GFP_DMA|__GFP_ZERO). Fix your code!
  CPU: 1 PID: 44 Comm: kworker/1:1 Not tainted 5.5.9-yocto-ua #1
  Hardware name: Freescale i.MX6 Quad/DualLite (Device Tree)
  Workqueue: events deferred_probe_work_func
  [<c0014924>] (unwind_backtrace) from [<c00123bc>] (show_stack+0x10/0x14)
  [<c00123bc>] (show_stack) from [<c04c8fb4>] (dump_stack+0x90/0xa4)
  [<c04c8fb4>] (dump_stack) from [<c00e1b10>] (new_slab+0x20c/0x214)
  [<c00e1b10>] (new_slab) from [<c00e1cd0>] (___slab_alloc.constprop.0+0x1b8/0x540)
  [<c00e1cd0>] (___slab_alloc.constprop.0) from [<c00e2074>] (__slab_alloc.constprop.0+0x1c/0x24)
  [<c00e2074>] (__slab_alloc.constprop.0) from [<c00e4538>] (__kmalloc_track_caller+0x1b0/0x298)
  [<c00e4538>] (__kmalloc_track_caller) from [<c02cccac>] (devm_kmalloc+0x24/0x70)
  [<c02cccac>] (devm_kmalloc) from [<c030d888>] (qca8k_sw_probe+0x94/0x1ac)
  [<c030d888>] (qca8k_sw_probe) from [<c0304788>] (mdio_probe+0x30/0x54)
  [<c0304788>] (mdio_probe) from [<c02c93bc>] (really_probe+0x1e0/0x348)
  [<c02c93bc>] (really_probe) from [<c02c9884>] (driver_probe_device+0x60/0x16c)
  [<c02c9884>] (driver_probe_device) from [<c02c7fb0>] (bus_for_each_drv+0x70/0x94)
  [<c02c7fb0>] (bus_for_each_drv) from [<c02c9708>] (__device_attach+0xb4/0x11c)
  [<c02c9708>] (__device_attach) from [<c02c8148>] (bus_probe_device+0x84/0x8c)
  [<c02c8148>] (bus_probe_device) from [<c02c8cec>] (deferred_probe_work_func+0x64/0x90)
  [<c02c8cec>] (deferred_probe_work_func) from [<c0033c14>] (process_one_work+0x1d4/0x41c)
  [<c0033c14>] (process_one_work) from [<c00340a4>] (worker_thread+0x248/0x528)
  [<c00340a4>] (worker_thread) from [<c0039148>] (kthread+0x124/0x150)
  [<c0039148>] (kthread) from [<c00090d8>] (ret_from_fork+0x14/0x3c)
  Exception stack(0xee1b5fb0 to 0xee1b5ff8)
  5fa0:                                     00000000 00000000 00000000 00000000
  5fc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
  5fe0: 00000000 00000000 00000000 00000000 00000013 00000000
  qca8k 2188000.ethernet-1:0a: Using legacy PHYLIB callbacks. Please migrate to PHYLINK!
  qca8k 2188000.ethernet-1:0a eth2 (uninitialized): PHY [2188000.ethernet-1:01] driver [Generic PHY]
  qca8k 2188000.ethernet-1:0a eth1 (uninitialized): PHY [2188000.ethernet-1:02] driver [Generic PHY]

Fixes: 7e99e3470172 ("net: dsa: remove dsa_switch_alloc helper")
Signed-off-by: Michal Vokáč <michal.vokac@ysoft.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/qca8k.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c
index 9f4205b4439b..d2b5ab403e06 100644
--- a/drivers/net/dsa/qca8k.c
+++ b/drivers/net/dsa/qca8k.c
@@ -1079,8 +1079,7 @@ qca8k_sw_probe(struct mdio_device *mdiodev)
 	if (id != QCA8K_ID_QCA8337)
 		return -ENODEV;
 
-	priv->ds = devm_kzalloc(&mdiodev->dev, sizeof(*priv->ds),
-				QCA8K_NUM_PORTS);
+	priv->ds = devm_kzalloc(&mdiodev->dev, sizeof(*priv->ds), GFP_KERNEL);
 	if (!priv->ds)
 		return -ENOMEM;
 
-- 
2.26.2


From 7c62fa3f40f2588e8faab3d2f6b321637bb768a3 Mon Sep 17 00:00:00 2001
From: Tuong Lien <tuong.t.lien@dektech.com.au>
Date: Wed, 3 Jun 2020 12:06:01 +0700
Subject: [PATCH 12/12] tipc: fix NULL pointer dereference in streaming

[ Upstream commit 5e9eeccc58f3e6bcc99b929670665d2ce047e9c9 ]

syzbot found the following crash:

general protection fault, probably for non-canonical address 0xdffffc0000000019: 0000 [#1] PREEMPT SMP KASAN
KASAN: null-ptr-deref in range [0x00000000000000c8-0x00000000000000cf]
CPU: 1 PID: 7060 Comm: syz-executor394 Not tainted 5.7.0-rc6-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:__tipc_sendstream+0xbde/0x11f0 net/tipc/socket.c:1591
Code: 00 00 00 00 48 39 5c 24 28 48 0f 44 d8 e8 fa 3e db f9 48 b8 00 00 00 00 00 fc ff df 48 8d bb c8 00 00 00 48 89 fa 48 c1 ea 03 <80> 3c 02 00 0f 85 e2 04 00 00 48 8b 9b c8 00 00 00 48 b8 00 00 00
RSP: 0018:ffffc90003ef7818 EFLAGS: 00010202
RAX: dffffc0000000000 RBX: 0000000000000000 RCX: ffffffff8797fd9d
RDX: 0000000000000019 RSI: ffffffff8797fde6 RDI: 00000000000000c8
RBP: ffff888099848040 R08: ffff88809a5f6440 R09: fffffbfff1860b4c
R10: ffffffff8c305a5f R11: fffffbfff1860b4b R12: ffff88809984857e
R13: 0000000000000000 R14: ffff888086aa4000 R15: 0000000000000000
FS:  00000000009b4880(0000) GS:ffff8880ae700000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000020000140 CR3: 00000000a7fdf000 CR4: 00000000001406e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 tipc_sendstream+0x4c/0x70 net/tipc/socket.c:1533
 sock_sendmsg_nosec net/socket.c:652 [inline]
 sock_sendmsg+0xcf/0x120 net/socket.c:672
 ____sys_sendmsg+0x32f/0x810 net/socket.c:2352
 ___sys_sendmsg+0x100/0x170 net/socket.c:2406
 __sys_sendmmsg+0x195/0x480 net/socket.c:2496
 __do_sys_sendmmsg net/socket.c:2525 [inline]
 __se_sys_sendmmsg net/socket.c:2522 [inline]
 __x64_sys_sendmmsg+0x99/0x100 net/socket.c:2522
 do_syscall_64+0xf6/0x7d0 arch/x86/entry/common.c:295
 entry_SYSCALL_64_after_hwframe+0x49/0xb3
RIP: 0033:0x440199
...

This bug was bisected to commit 0a3e060f340d ("tipc: add test for Nagle
algorithm effectiveness"). However, it is not the case, the trouble was
from the base in the case of zero data length message sending, we would
unexpectedly make an empty 'txq' queue after the 'tipc_msg_append()' in
Nagle mode.

A similar crash can be generated even without the bisected patch but at
the link layer when it accesses the empty queue.

We solve the issues by building at least one buffer to go with socket's
header and an optional data section that may be empty like what we had
with the 'tipc_msg_build()'.

Note: the previous commit 4c21daae3dbc ("tipc: Fix NULL pointer
dereference in __tipc_sendstream()") is obsoleted by this one since the
'txq' will be never empty and the check of 'skb != NULL' is unnecessary
but it is safe anyway.

Reported-by: syzbot+8eac6d030e7807c21d32@syzkaller.appspotmail.com
Fixes: c0bceb97db9e ("tipc: add smart nagle feature")
Acked-by: Jon Maloy <jmaloy@redhat.com>
Signed-off-by: Tuong Lien <tuong.t.lien@dektech.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/msg.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index 4d0e0bdd997b..3ad411884e6c 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -221,7 +221,7 @@ int tipc_msg_append(struct tipc_msg *_hdr, struct msghdr *m, int dlen,
 	accounted = skb ? msg_blocks(buf_msg(skb)) : 0;
 	total = accounted;
 
-	while (rem) {
+	do {
 		if (!skb || skb->len >= mss) {
 			prev = skb;
 			skb = tipc_buf_acquire(mss, GFP_KERNEL);
@@ -249,7 +249,7 @@ int tipc_msg_append(struct tipc_msg *_hdr, struct msghdr *m, int dlen,
 		skb_put(skb, cpy);
 		rem -= cpy;
 		total += msg_blocks(hdr) - curr;
-	}
+	} while (rem);
 	return total - accounted;
 }
 
-- 
2.26.2

Re: [PATCHES] Networking

[Greg KH]

On Tue, Jun 09, 2020 at 05:08:26PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v5.6 and v5.7
> -stable, respectively.
> 
> Thank you!


All now applied, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 102 bytes --]


Please queue up the following networking bug fixes for v5.6 and
v5.7 -stable, respectively.

Thanks!

[-- Attachment #2: net_56.mbox --]
[-- Type: Application/Octet-Stream, Size: 26200 bytes --]

From e38e9d797167b9b817953ce21055ff7c97600250 Mon Sep 17 00:00:00 2001
From: Wang Hai <wanghai38@huawei.com>
Date: Tue, 9 Jun 2020 22:18:16 +0800
Subject: [PATCH 1/9] dccp: Fix possible memleak in dccp_init and dccp_fini

[ Upstream commit c96b6acc8f89a4a7f6258dfe1d077654c11415be ]

There are some memory leaks in dccp_init() and dccp_fini().

In dccp_fini() and the error handling path in dccp_init(), free lhash2
is missing. Add inet_hashinfo2_free_mod() to do it.

If inet_hashinfo2_init_mod() failed in dccp_init(),
percpu_counter_destroy() should be called to destroy dccp_orphan_count.
It need to goto out_free_percpu when inet_hashinfo2_init_mod() failed.

Fixes: c92c81df93df ("net: dccp: fix kernel crash on module load")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Wang Hai <wanghai38@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_hashtables.h | 6 ++++++
 net/dccp/proto.c              | 7 +++++--
 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index d0019d3395cf..59802eb8d2cc 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -185,6 +185,12 @@ static inline spinlock_t *inet_ehash_lockp(
 
 int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo);
 
+static inline void inet_hashinfo2_free_mod(struct inet_hashinfo *h)
+{
+	kfree(h->lhash2);
+	h->lhash2 = NULL;
+}
+
 static inline void inet_ehash_locks_free(struct inet_hashinfo *hashinfo)
 {
 	kvfree(hashinfo->ehash_locks);
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 4af8a98fe784..c13b6609474b 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -1139,14 +1139,14 @@ static int __init dccp_init(void)
 	inet_hashinfo_init(&dccp_hashinfo);
 	rc = inet_hashinfo2_init_mod(&dccp_hashinfo);
 	if (rc)
-		goto out_fail;
+		goto out_free_percpu;
 	rc = -ENOBUFS;
 	dccp_hashinfo.bind_bucket_cachep =
 		kmem_cache_create("dccp_bind_bucket",
 				  sizeof(struct inet_bind_bucket), 0,
 				  SLAB_HWCACHE_ALIGN, NULL);
 	if (!dccp_hashinfo.bind_bucket_cachep)
-		goto out_free_percpu;
+		goto out_free_hashinfo2;
 
 	/*
 	 * Size and allocate the main established and bind bucket
@@ -1242,6 +1242,8 @@ static int __init dccp_init(void)
 	free_pages((unsigned long)dccp_hashinfo.ehash, ehash_order);
 out_free_bind_bucket_cachep:
 	kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep);
+out_free_hashinfo2:
+	inet_hashinfo2_free_mod(&dccp_hashinfo);
 out_free_percpu:
 	percpu_counter_destroy(&dccp_orphan_count);
 out_fail:
@@ -1265,6 +1267,7 @@ static void __exit dccp_fini(void)
 	kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep);
 	dccp_ackvec_exit();
 	dccp_sysctl_exit();
+	inet_hashinfo2_free_mod(&dccp_hashinfo);
 	percpu_counter_destroy(&dccp_orphan_count);
 }
 
-- 
2.26.2


From bba96760433c5ebd5b98e47a9fb497ed9c810804 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 9 Jun 2020 00:02:39 +0200
Subject: [PATCH 2/9] net: mvneta: do not redirect frames during
 reconfiguration

[ Upstream commit 62a502cc91f97e3ffd312d9b42e8d01a137c63ff ]

Disable frames injection in mvneta_xdp_xmit routine during hw
re-configuration in order to avoid hardware hangs

Fixes: b0a43db9087a ("net: mvneta: add XDP_TX support")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 11babc79dc6c..14318dca6921 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -418,11 +418,17 @@ struct mvneta_pcpu_port {
 	u32			cause_rx_tx;
 };
 
+enum {
+	__MVNETA_DOWN,
+};
+
 struct mvneta_port {
 	u8 id;
 	struct mvneta_pcpu_port __percpu	*ports;
 	struct mvneta_pcpu_stats __percpu	*stats;
 
+	unsigned long state;
+
 	int pkt_size;
 	void __iomem *base;
 	struct mvneta_rx_queue *rxqs;
@@ -2066,6 +2072,9 @@ mvneta_xdp_xmit(struct net_device *dev, int num_frame,
 	int i, drops = 0;
 	u32 ret;
 
+	if (unlikely(test_bit(__MVNETA_DOWN, &pp->state)))
+		return -ENETDOWN;
+
 	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
 		return -EINVAL;
 
@@ -3489,12 +3498,16 @@ static void mvneta_start_dev(struct mvneta_port *pp)
 
 	phylink_start(pp->phylink);
 	netif_tx_start_all_queues(pp->dev);
+
+	clear_bit(__MVNETA_DOWN, &pp->state);
 }
 
 static void mvneta_stop_dev(struct mvneta_port *pp)
 {
 	unsigned int cpu;
 
+	set_bit(__MVNETA_DOWN, &pp->state);
+
 	phylink_stop(pp->phylink);
 
 	if (!pp->neta_armada3700) {
-- 
2.26.2


From d58905ad274e19f7042c6c1e0b6f1170f87b61c1 Mon Sep 17 00:00:00 2001
From: tannerlove <tannerlove@google.com>
Date: Tue, 9 Jun 2020 17:21:32 -0400
Subject: [PATCH 3/9] selftests/net: in rxtimestamp getopt_long needs
 terminating null entry

[ Upstream commit 865a6cbb2288f8af7f9dc3b153c61b7014fdcf1e ]

getopt_long requires the last element to be filled with zeros.
Otherwise, passing an unrecognized option can cause a segfault.

Fixes: 16e781224198 ("selftests/net: Add a test to validate behavior of rx timestamps")
Signed-off-by: Tanner Love <tannerlove@google.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/networking/timestamping/rxtimestamp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/networking/timestamping/rxtimestamp.c b/tools/testing/selftests/networking/timestamping/rxtimestamp.c
index 6dee9e636a95..422e7761254d 100644
--- a/tools/testing/selftests/networking/timestamping/rxtimestamp.c
+++ b/tools/testing/selftests/networking/timestamping/rxtimestamp.c
@@ -115,6 +115,7 @@ static struct option long_options[] = {
 	{ "tcp", no_argument, 0, 't' },
 	{ "udp", no_argument, 0, 'u' },
 	{ "ip", no_argument, 0, 'i' },
+	{ NULL, 0, NULL, 0 },
 };
 
 static int next_port = 19999;
-- 
2.26.2


From cae765cf91fb0ba6b36f49a60d22b92ae7dff6d7 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@mellanox.com>
Date: Wed, 6 May 2020 15:59:48 +0300
Subject: [PATCH 4/9] net/mlx5: drain health workqueue in case of driver load
 error

[ Upstream commit 42ea9f1b5c625fad225d4ac96a7e757dd4199d9c ]

In case there is a work in the health WQ when we teardown the driver,
in driver load error flow, the health work will try to read dev->iseg,
which was already unmap in mlx5_pci_close().
Fix it by draining the health workqueue first thing in mlx5_pci_close().

Trace of the error:
BUG: unable to handle page fault for address: ffffb5b141c18014
PF: supervisor read access in kernel mode
PF: error_code(0x0000) - not-present page
PGD 1fe95d067 P4D 1fe95d067 PUD 1fe95e067 PMD 1b7823067 PTE 0
Oops: 0000 [#1] SMP PTI
CPU: 3 PID: 6755 Comm: kworker/u128:2 Not tainted 5.2.0-net-next-mlx5-hv_stats-over-last-worked-hyperv #1
Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS 090006  04/28/2016
Workqueue: mlx5_healtha050:00:02.0 mlx5_fw_fatal_reporter_err_work [mlx5_core]
RIP: 0010:ioread32be+0x30/0x40
Code: 00 77 27 48 81 ff 00 00 01 00 76 07 0f b7 d7 ed 0f c8 c3 55 48 c7 c6 3b ee d5 9f 48 89 e5 e8 67 fc ff ff b8 ff ff ff ff 5d c3 <8b> 07 0f c8 c3 66 66 2e 0f 1f 84 00 00 00 00 00 48 81 fe ff ff 03
RSP: 0018:ffffb5b14c56fd78 EFLAGS: 00010292
RAX: ffffb5b141c18000 RBX: ffff8e9f78a801c0 RCX: 0000000000000000
RDX: 0000000000000001 RSI: ffff8e9f7ecd7628 RDI: ffffb5b141c18014
RBP: ffffb5b14c56fd90 R08: 0000000000000001 R09: 0000000000000000
R10: ffff8e9f372a2c30 R11: ffff8e9f87f4bc40 R12: ffff8e9f372a1fc0
R13: ffff8e9f78a80000 R14: ffffffffc07136a0 R15: ffff8e9f78ae6f20
FS:  0000000000000000(0000) GS:ffff8e9f7ecc0000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffffb5b141c18014 CR3: 00000001c8f82006 CR4: 00000000003606e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 ? mlx5_health_try_recover+0x4d/0x270 [mlx5_core]
 mlx5_fw_fatal_reporter_recover+0x16/0x20 [mlx5_core]
 devlink_health_reporter_recover+0x1c/0x50
 devlink_health_report+0xfb/0x240
 mlx5_fw_fatal_reporter_err_work+0x65/0xd0 [mlx5_core]
 process_one_work+0x1fb/0x4e0
 ? process_one_work+0x16b/0x4e0
 worker_thread+0x4f/0x3d0
 kthread+0x10d/0x140
 ? process_one_work+0x4e0/0x4e0
 ? kthread_cancel_delayed_work_sync+0x20/0x20
 ret_from_fork+0x1f/0x30
Modules linked in: nfsv3 rpcsec_gss_krb5 nfsv4 nfs fscache 8021q garp mrp stp llc ipmi_devintf ipmi_msghandler rpcrdma rdma_ucm ib_iser rdma_cm ib_umad iw_cm ib_ipoib libiscsi scsi_transport_iscsi ib_cm mlx5_ib ib_uverbs ib_core mlx5_core sb_edac crct10dif_pclmul crc32_pclmul ghash_clmulni_intel aesni_intel aes_x86_64 mlxfw crypto_simd cryptd glue_helper input_leds hyperv_fb intel_rapl_perf joydev serio_raw pci_hyperv pci_hyperv_mini mac_hid hv_balloon nfsd auth_rpcgss nfs_acl lockd grace sunrpc sch_fq_codel ip_tables x_tables autofs4 hv_utils hid_generic hv_storvsc ptp hid_hyperv hid hv_netvsc hyperv_keyboard pps_core scsi_transport_fc psmouse hv_vmbus i2c_piix4 floppy pata_acpi
CR2: ffffb5b141c18014
---[ end trace b12c5503157cad24 ]---
RIP: 0010:ioread32be+0x30/0x40
Code: 00 77 27 48 81 ff 00 00 01 00 76 07 0f b7 d7 ed 0f c8 c3 55 48 c7 c6 3b ee d5 9f 48 89 e5 e8 67 fc ff ff b8 ff ff ff ff 5d c3 <8b> 07 0f c8 c3 66 66 2e 0f 1f 84 00 00 00 00 00 48 81 fe ff ff 03
RSP: 0018:ffffb5b14c56fd78 EFLAGS: 00010292
RAX: ffffb5b141c18000 RBX: ffff8e9f78a801c0 RCX: 0000000000000000
RDX: 0000000000000001 RSI: ffff8e9f7ecd7628 RDI: ffffb5b141c18014
RBP: ffffb5b14c56fd90 R08: 0000000000000001 R09: 0000000000000000
R10: ffff8e9f372a2c30 R11: ffff8e9f87f4bc40 R12: ffff8e9f372a1fc0
R13: ffff8e9f78a80000 R14: ffffffffc07136a0 R15: ffff8e9f78ae6f20
FS:  0000000000000000(0000) GS:ffff8e9f7ecc0000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffffb5b141c18014 CR3: 00000001c8f82006 CR4: 00000000003606e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
BUG: sleeping function called from invalid context at ./include/linux/percpu-rwsem.h:38
in_atomic(): 0, irqs_disabled(): 1, pid: 6755, name: kworker/u128:2
INFO: lockdep is turned off.
CPU: 3 PID: 6755 Comm: kworker/u128:2 Tainted: G      D           5.2.0-net-next-mlx5-hv_stats-over-last-worked-hyperv #1
Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS 090006  04/28/2016
Workqueue: mlx5_healtha050:00:02.0 mlx5_fw_fatal_reporter_err_work [mlx5_core]
Call Trace:
 dump_stack+0x63/0x88
 ___might_sleep+0x10a/0x130
 __might_sleep+0x4a/0x80
 exit_signals+0x33/0x230
 ? blocking_notifier_call_chain+0x16/0x20
 do_exit+0xb1/0xc30
 ? kthread+0x10d/0x140
 ? process_one_work+0x4e0/0x4e0

Fixes: 52c368dc3da7 ("net/mlx5: Move health and page alloc init to mdev_init")
Signed-off-by: Shay Drory <shayd@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 20e12e14cfa8..d7986f64494b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -794,6 +794,11 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct pci_dev *pdev,
 
 static void mlx5_pci_close(struct mlx5_core_dev *dev)
 {
+	/* health work might still be active, and it needs pci bar in
+	 * order to know the NIC state. Therefore, drain the health WQ
+	 * before removing the pci bars
+	 */
+	mlx5_drain_health_wq(dev);
 	iounmap(dev->iseg);
 	pci_clear_master(dev->pdev);
 	release_bar(dev->pdev);
-- 
2.26.2


From 41480989ed1932e62e7e113d567b5d230793bff8 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@mellanox.com>
Date: Thu, 7 May 2020 09:32:53 +0300
Subject: [PATCH 5/9] net/mlx5: Fix fatal error handling during device load

[ Upstream commit b6e0b6bebe0732d5cac51f0791f269d2413b8980 ]

Currently, in case of fatal error during mlx5_load_one(), we cannot
enter error state until mlx5_load_one() is finished, what can take
several minutes until commands will get timeouts, because these commands
can't be processed due to the fatal error.
Fix it by setting dev->state as MLX5_DEVICE_STATE_INTERNAL_ERROR before
requesting the lock.

Fixes: c1d4d2e92ad6 ("net/mlx5: Avoid calling sleeping function by the health poll thread")
Signed-off-by: Shay Drory <shayd@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/health.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 68e7ef7ca52d..ffb360fe44d3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -193,15 +193,23 @@ static bool reset_fw_if_needed(struct mlx5_core_dev *dev)
 
 void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force)
 {
+	bool err_detected = false;
+
+	/* Mark the device as fatal in order to abort FW commands */
+	if ((check_fatal_sensors(dev) || force) &&
+	    dev->state == MLX5_DEVICE_STATE_UP) {
+		dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
+		err_detected = true;
+	}
 	mutex_lock(&dev->intf_state_mutex);
-	if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
-		goto unlock;
+	if (!err_detected && dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
+		goto unlock;/* a previous error is still being handled */
 	if (dev->state == MLX5_DEVICE_STATE_UNINITIALIZED) {
 		dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
 		goto unlock;
 	}
 
-	if (check_fatal_sensors(dev) || force) {
+	if (check_fatal_sensors(dev) || force) { /* protected state setting */
 		dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
 		mlx5_cmd_flush(dev);
 	}
-- 
2.26.2


From 36e5e43e4ab8cda5043736716a5ed14bf4e75b1e Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Mon, 1 Jun 2020 16:03:44 +0300
Subject: [PATCH 6/9] net/mlx5e: Fix repeated XSK usage on one channel

[ Upstream commit 36d45fb9d2fdf348d778bfe73f0427db1c6f9bc7 ]

After an XSK is closed, the relevant structures in the channel are not
zeroed. If an XSK is opened the second time on the same channel without
recreating channels, the stray values in the structures will lead to
incorrect operation of queues, which causes CQE errors, and the new
socket doesn't work at all.

This patch fixes the issue by explicitly zeroing XSK-related structs in
the channel on XSK close. Note that those structs are zeroed on channel
creation, and usually a configuration change (XDP program is set)
happens on XSK open, which leads to recreating channels, so typical XSK
usecases don't suffer from this issue. However, if XSKs are opened and
closed on the same channel without removing the XDP program, this bug
reproduces.

Fixes: db05815b36cb ("net/mlx5e: Add XSK zero-copy support")
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
index c28cbae42331..2c80205dc939 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
@@ -152,6 +152,10 @@ void mlx5e_close_xsk(struct mlx5e_channel *c)
 	mlx5e_close_cq(&c->xskicosq.cq);
 	mlx5e_close_xdpsq(&c->xsksq);
 	mlx5e_close_cq(&c->xsksq.cq);
+
+	memset(&c->xskrq, 0, sizeof(c->xskrq));
+	memset(&c->xsksq, 0, sizeof(c->xsksq));
+	memset(&c->xskicosq, 0, sizeof(c->xskicosq));
 }
 
 void mlx5e_activate_xsk(struct mlx5e_channel *c)
-- 
2.26.2


From 308ba307118c616ee6345ff768ae93d370ba4440 Mon Sep 17 00:00:00 2001
From: Corentin Labbe <clabbe@baylibre.com>
Date: Wed, 10 Jun 2020 09:53:44 +0000
Subject: [PATCH 7/9] net: cadence: macb: disable NAPI on error

[ Upstream commit 014406babc1f5f887a08737566b5b356c7018242 ]

When the PHY is not working, the macb driver crash on a second try to
setup it.
[   78.545994] macb e000b000.ethernet eth0: Could not attach PHY (-19)
ifconfig: SIOCSIFFLAGS: No such device
[   78.655457] ------------[ cut here ]------------
[   78.656014] kernel BUG at /linux-next/include/linux/netdevice.h:521!
[   78.656504] Internal error: Oops - BUG: 0 [#1] SMP ARM
[   78.657079] Modules linked in:
[   78.657795] CPU: 0 PID: 122 Comm: ifconfig Not tainted 5.7.0-next-20200609 #1
[   78.658202] Hardware name: Xilinx Zynq Platform
[   78.659632] PC is at macb_open+0x220/0x294
[   78.660160] LR is at 0x0
[   78.660373] pc : [<c0b0a634>]    lr : [<00000000>]    psr: 60000013
[   78.660716] sp : c89ffd70  ip : c8a28800  fp : c199bac0
[   78.661040] r10: 00000000  r9 : c8838540  r8 : c8838568
[   78.661362] r7 : 00000001  r6 : c8838000  r5 : c883c000  r4 : 00000000
[   78.661724] r3 : 00000010  r2 : 00000000  r1 : 00000000  r0 : 00000000
[   78.662187] Flags: nZCv  IRQs on  FIQs on  Mode SVC_32  ISA ARM  Segment none
[   78.662635] Control: 10c5387d  Table: 08b64059  DAC: 00000051
[   78.663035] Process ifconfig (pid: 122, stack limit = 0x(ptrval))
[   78.663476] Stack: (0xc89ffd70 to 0xc8a00000)
[   78.664121] fd60:                                     00000000 c89fe000 c8838000 c89fe000
[   78.664866] fd80: 00000000 c11ff9ac c8838028 00000000 00000000 c0de6f2c 00000001 c1804eec
[   78.665579] fda0: c19b8178 c8838000 00000000 ca760866 c8838000 00000001 00001043 c89fe000
[   78.666355] fdc0: 00001002 c0de72f4 c89fe000 c0de8dc0 00008914 c89fe000 c199bac0 ca760866
[   78.667111] fde0: c89ffddc c8838000 00001002 00000000 c8838138 c881010c 00008914 c0de7364
[   78.667862] fe00: 00000000 c89ffe70 c89fe000 ffffffff c881010c c0e8bd48 00000003 00000000
[   78.668601] fe20: c8838000 c8810100 39c1118f 00039c11 c89a0960 00001043 00000000 000a26d0
[   78.669343] fe40: b6f43000 ca760866 c89a0960 00000051 befe6c50 00008914 c8b2a3c0 befe6c50
[   78.670086] fe60: 00000003 ee610500 00000000 c0e8ef58 30687465 00000000 00000000 00000000
[   78.670865] fe80: 00001043 00000000 000a26d0 b6f43000 c89a0600 ee40ae7c c8870d00 c0ddabf4
[   78.671593] fea0: c89ffeec c0ddabf4 c89ffeec c199bac0 00008913 c0ddac48 c89ffeec c89fe000
[   78.672324] fec0: befe6c50 ca760866 befe6c50 00008914 c89fe000 befe6c50 c8b2a3c0 c0dc00e4
[   78.673088] fee0: c89a0480 00000201 00000cc0 30687465 00000000 00000000 00000000 00001002
[   78.673822] ff00: 00000000 000a26d0 b6f43000 ca760866 00008914 c8b2a3c0 000a0ec4 c8b2a3c0
[   78.674576] ff20: befe6c50 c04b21bc 000d5004 00000817 c89a0480 c0315f94 00000000 00000003
[   78.675415] ff40: c19a2bc8 c8a3cc00 c89fe000 00000255 00000000 00000000 00000000 000d5000
[   78.676182] ff60: 000f6000 c180b2a0 00000817 c0315e64 000d5004 c89fffb0 b6ec0c30 ca760866
[   78.676928] ff80: 00000000 000b609b befe6c50 000a0ec4 00000036 c03002c4 c89fe000 00000036
[   78.677673] ffa0: 00000000 c03000c0 000b609b befe6c50 00000003 00008914 befe6c50 000b609b
[   78.678415] ffc0: 000b609b befe6c50 000a0ec4 00000036 befe6e0c befe6f1a 000d5150 00000000
[   78.679154] ffe0: 000d41e4 befe6bf4 00019648 b6e4509c 20000010 00000003 00000000 00000000
[   78.681059] [<c0b0a634>] (macb_open) from [<c0de6f2c>] (__dev_open+0xd0/0x154)
[   78.681571] [<c0de6f2c>] (__dev_open) from [<c0de72f4>] (__dev_change_flags+0x16c/0x1c4)
[   78.682015] [<c0de72f4>] (__dev_change_flags) from [<c0de7364>] (dev_change_flags+0x18/0x48)
[   78.682493] [<c0de7364>] (dev_change_flags) from [<c0e8bd48>] (devinet_ioctl+0x5e4/0x75c)
[   78.682945] [<c0e8bd48>] (devinet_ioctl) from [<c0e8ef58>] (inet_ioctl+0x1f0/0x3b4)
[   78.683381] [<c0e8ef58>] (inet_ioctl) from [<c0dc00e4>] (sock_ioctl+0x39c/0x664)
[   78.683818] [<c0dc00e4>] (sock_ioctl) from [<c04b21bc>] (ksys_ioctl+0x2d8/0x9c0)
[   78.684343] [<c04b21bc>] (ksys_ioctl) from [<c03000c0>] (ret_fast_syscall+0x0/0x54)
[   78.684789] Exception stack(0xc89fffa8 to 0xc89ffff0)
[   78.685346] ffa0:                   000b609b befe6c50 00000003 00008914 befe6c50 000b609b
[   78.686106] ffc0: 000b609b befe6c50 000a0ec4 00000036 befe6e0c befe6f1a 000d5150 00000000
[   78.686710] ffe0: 000d41e4 befe6bf4 00019648 b6e4509c
[   78.687582] Code: 9a000003 e5983078 e3130001 1affffef (e7f001f2)
[   78.688788] ---[ end trace e3f2f6ab69754eae ]---

This is due to NAPI left enabled if macb_phylink_connect() fail.

Fixes: 7897b071ac3b ("net: macb: convert to phylink")
Signed-off-by: Corentin Labbe <clabbe@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index f42382c2ecd0..9b91a7b8a362 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -2545,13 +2545,16 @@ static int macb_open(struct net_device *dev)
 
 	err = macb_phylink_connect(bp);
 	if (err)
-		goto pm_exit;
+		goto napi_exit;
 
 	netif_tx_start_all_queues(dev);
 
 	if (bp->ptp_info)
 		bp->ptp_info->ptp_init(dev);
 
+napi_exit:
+	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
+		napi_disable(&queue->napi);
 pm_exit:
 	if (err) {
 		pm_runtime_put_sync(&bp->pdev->dev);
-- 
2.26.2


From e8e1aaafcc89f4d8843768ac1902cd303825896a Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.cirrus.com>
Date: Mon, 15 Jun 2020 14:18:54 +0100
Subject: [PATCH 8/9] net: macb: Only disable NAPI on the actual error path

[ Upstream commit 939a5bf7c9b7a1ad9c5d3481c93766a522773531 ]

A recent change added a disable to NAPI into macb_open, this was
intended to only happen on the error path but accidentally applies
to all paths. This causes NAPI to be disabled on the success path, which
leads to the network to no longer functioning.

Fixes: 014406babc1f ("net: cadence: macb: disable NAPI on error")
Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Tested-by: Corentin Labbe <clabbe@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 9b91a7b8a362..9067b413d6b7 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -2552,15 +2552,14 @@ static int macb_open(struct net_device *dev)
 	if (bp->ptp_info)
 		bp->ptp_info->ptp_init(dev);
 
+	return 0;
+
 napi_exit:
 	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
 		napi_disable(&queue->napi);
 pm_exit:
-	if (err) {
-		pm_runtime_put_sync(&bp->pdev->dev);
-		return err;
-	}
-	return 0;
+	pm_runtime_put_sync(&bp->pdev->dev);
+	return err;
 }
 
 static int macb_close(struct net_device *dev)
-- 
2.26.2


From 350270dba0124e4a244dcefd259ac287dcec07f6 Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@mellanox.com>
Date: Thu, 14 May 2020 05:12:56 -0500
Subject: [PATCH 9/9] net/mlx5: Disable reload while removing the device

[ Upstream commit 60904cd349abc98cb888fc28d1ca55a8e2cf87b3 ]

While unregistration is in progress, user might be reloading the
interface.
This can race with unregistration in below flow which uses the
resources which are getting disabled by reload flow.

Hence, disable the devlink reloading first when removing the device.

     CPU0                                   CPU1
     ----                                   ----
local_pci_remove()                  devlink_mutex
  remove_one()                       devlink_nl_cmd_reload()
    mlx5_unregister_device()           devlink_reload()
                                       ops->reload_down()
                                         mlx5_unload_one()

Fixes: 4383cfcc65e7 ("net/mlx5: Add devlink reload")
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/devlink.c | 2 --
 drivers/net/ethernet/mellanox/mlx5/core/main.c    | 2 ++
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index 184c3eaefbcb..c190eb267f3c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -256,7 +256,6 @@ int mlx5_devlink_register(struct devlink *devlink, struct device *dev)
 		goto params_reg_err;
 	mlx5_devlink_set_params_init_values(devlink);
 	devlink_params_publish(devlink);
-	devlink_reload_enable(devlink);
 	return 0;
 
 params_reg_err:
@@ -266,7 +265,6 @@ int mlx5_devlink_register(struct devlink *devlink, struct device *dev)
 
 void mlx5_devlink_unregister(struct devlink *devlink)
 {
-	devlink_reload_disable(devlink);
 	devlink_params_unregister(devlink, mlx5_devlink_params,
 				  ARRAY_SIZE(mlx5_devlink_params));
 	devlink_unregister(devlink);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index d7986f64494b..743491babf88 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1371,6 +1371,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 		dev_err(&pdev->dev, "mlx5_crdump_enable failed with error code %d\n", err);
 
 	pci_save_state(pdev);
+	devlink_reload_enable(devlink);
 	return 0;
 
 err_load_one:
@@ -1388,6 +1389,7 @@ static void remove_one(struct pci_dev *pdev)
 	struct mlx5_core_dev *dev  = pci_get_drvdata(pdev);
 	struct devlink *devlink = priv_to_devlink(dev);
 
+	devlink_reload_disable(devlink);
 	mlx5_crdump_disable(dev);
 	mlx5_devlink_unregister(devlink);
 
-- 
2.26.2


[-- Attachment #3: net_57.mbox --]
[-- Type: Application/Octet-Stream, Size: 40954 bytes --]

From 0e957172ba6f9880e9f92ebb15ff4140cc86b4b4 Mon Sep 17 00:00:00 2001
From: Wang Hai <wanghai38@huawei.com>
Date: Tue, 9 Jun 2020 22:18:16 +0800
Subject: [PATCH 01/16] dccp: Fix possible memleak in dccp_init and dccp_fini

[ Upstream commit c96b6acc8f89a4a7f6258dfe1d077654c11415be ]

There are some memory leaks in dccp_init() and dccp_fini().

In dccp_fini() and the error handling path in dccp_init(), free lhash2
is missing. Add inet_hashinfo2_free_mod() to do it.

If inet_hashinfo2_init_mod() failed in dccp_init(),
percpu_counter_destroy() should be called to destroy dccp_orphan_count.
It need to goto out_free_percpu when inet_hashinfo2_init_mod() failed.

Fixes: c92c81df93df ("net: dccp: fix kernel crash on module load")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Wang Hai <wanghai38@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_hashtables.h | 6 ++++++
 net/dccp/proto.c              | 7 +++++--
 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index ad64ba6a057f..92560974ea67 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -185,6 +185,12 @@ static inline spinlock_t *inet_ehash_lockp(
 
 int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo);
 
+static inline void inet_hashinfo2_free_mod(struct inet_hashinfo *h)
+{
+	kfree(h->lhash2);
+	h->lhash2 = NULL;
+}
+
 static inline void inet_ehash_locks_free(struct inet_hashinfo *hashinfo)
 {
 	kvfree(hashinfo->ehash_locks);
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 4af8a98fe784..c13b6609474b 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -1139,14 +1139,14 @@ static int __init dccp_init(void)
 	inet_hashinfo_init(&dccp_hashinfo);
 	rc = inet_hashinfo2_init_mod(&dccp_hashinfo);
 	if (rc)
-		goto out_fail;
+		goto out_free_percpu;
 	rc = -ENOBUFS;
 	dccp_hashinfo.bind_bucket_cachep =
 		kmem_cache_create("dccp_bind_bucket",
 				  sizeof(struct inet_bind_bucket), 0,
 				  SLAB_HWCACHE_ALIGN, NULL);
 	if (!dccp_hashinfo.bind_bucket_cachep)
-		goto out_free_percpu;
+		goto out_free_hashinfo2;
 
 	/*
 	 * Size and allocate the main established and bind bucket
@@ -1242,6 +1242,8 @@ static int __init dccp_init(void)
 	free_pages((unsigned long)dccp_hashinfo.ehash, ehash_order);
 out_free_bind_bucket_cachep:
 	kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep);
+out_free_hashinfo2:
+	inet_hashinfo2_free_mod(&dccp_hashinfo);
 out_free_percpu:
 	percpu_counter_destroy(&dccp_orphan_count);
 out_fail:
@@ -1265,6 +1267,7 @@ static void __exit dccp_fini(void)
 	kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep);
 	dccp_ackvec_exit();
 	dccp_sysctl_exit();
+	inet_hashinfo2_free_mod(&dccp_hashinfo);
 	percpu_counter_destroy(&dccp_orphan_count);
 }
 
-- 
2.26.2


From 1ba487ccaa0266875a18345853a5dc1fd4b67b54 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 9 Jun 2020 00:02:39 +0200
Subject: [PATCH 02/16] net: mvneta: do not redirect frames during
 reconfiguration

[ Upstream commit 62a502cc91f97e3ffd312d9b42e8d01a137c63ff ]

Disable frames injection in mvneta_xdp_xmit routine during hw
re-configuration in order to avoid hardware hangs

Fixes: b0a43db9087a ("net: mvneta: add XDP_TX support")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 51889770958d..43b44a1e8f69 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -451,11 +451,17 @@ struct mvneta_pcpu_port {
 	u32			cause_rx_tx;
 };
 
+enum {
+	__MVNETA_DOWN,
+};
+
 struct mvneta_port {
 	u8 id;
 	struct mvneta_pcpu_port __percpu	*ports;
 	struct mvneta_pcpu_stats __percpu	*stats;
 
+	unsigned long state;
+
 	int pkt_size;
 	void __iomem *base;
 	struct mvneta_rx_queue *rxqs;
@@ -2112,6 +2118,9 @@ mvneta_xdp_xmit(struct net_device *dev, int num_frame,
 	struct netdev_queue *nq;
 	u32 ret;
 
+	if (unlikely(test_bit(__MVNETA_DOWN, &pp->state)))
+		return -ENETDOWN;
+
 	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
 		return -EINVAL;
 
@@ -3562,12 +3571,16 @@ static void mvneta_start_dev(struct mvneta_port *pp)
 
 	phylink_start(pp->phylink);
 	netif_tx_start_all_queues(pp->dev);
+
+	clear_bit(__MVNETA_DOWN, &pp->state);
 }
 
 static void mvneta_stop_dev(struct mvneta_port *pp)
 {
 	unsigned int cpu;
 
+	set_bit(__MVNETA_DOWN, &pp->state);
+
 	phylink_stop(pp->phylink);
 
 	if (!pp->neta_armada3700) {
-- 
2.26.2


From 72db283350cf6e92ffd55d9e264c1816fbf6a150 Mon Sep 17 00:00:00 2001
From: tannerlove <tannerlove@google.com>
Date: Tue, 9 Jun 2020 17:21:32 -0400
Subject: [PATCH 03/16] selftests/net: in rxtimestamp getopt_long needs
 terminating null entry

[ Upstream commit 865a6cbb2288f8af7f9dc3b153c61b7014fdcf1e ]

getopt_long requires the last element to be filled with zeros.
Otherwise, passing an unrecognized option can cause a segfault.

Fixes: 16e781224198 ("selftests/net: Add a test to validate behavior of rx timestamps")
Signed-off-by: Tanner Love <tannerlove@google.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/rxtimestamp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/net/rxtimestamp.c b/tools/testing/selftests/net/rxtimestamp.c
index 6dee9e636a95..422e7761254d 100644
--- a/tools/testing/selftests/net/rxtimestamp.c
+++ b/tools/testing/selftests/net/rxtimestamp.c
@@ -115,6 +115,7 @@ static struct option long_options[] = {
 	{ "tcp", no_argument, 0, 't' },
 	{ "udp", no_argument, 0, 'u' },
 	{ "ip", no_argument, 0, 'i' },
+	{ NULL, 0, NULL, 0 },
 };
 
 static int next_port = 19999;
-- 
2.26.2


From f432ef4db06adb2755dadbe67d8d836d1601ad6b Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@mellanox.com>
Date: Wed, 6 May 2020 15:59:48 +0300
Subject: [PATCH 04/16] net/mlx5: drain health workqueue in case of driver load
 error

[ Upstream commit 42ea9f1b5c625fad225d4ac96a7e757dd4199d9c ]

In case there is a work in the health WQ when we teardown the driver,
in driver load error flow, the health work will try to read dev->iseg,
which was already unmap in mlx5_pci_close().
Fix it by draining the health workqueue first thing in mlx5_pci_close().

Trace of the error:
BUG: unable to handle page fault for address: ffffb5b141c18014
PF: supervisor read access in kernel mode
PF: error_code(0x0000) - not-present page
PGD 1fe95d067 P4D 1fe95d067 PUD 1fe95e067 PMD 1b7823067 PTE 0
Oops: 0000 [#1] SMP PTI
CPU: 3 PID: 6755 Comm: kworker/u128:2 Not tainted 5.2.0-net-next-mlx5-hv_stats-over-last-worked-hyperv #1
Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS 090006  04/28/2016
Workqueue: mlx5_healtha050:00:02.0 mlx5_fw_fatal_reporter_err_work [mlx5_core]
RIP: 0010:ioread32be+0x30/0x40
Code: 00 77 27 48 81 ff 00 00 01 00 76 07 0f b7 d7 ed 0f c8 c3 55 48 c7 c6 3b ee d5 9f 48 89 e5 e8 67 fc ff ff b8 ff ff ff ff 5d c3 <8b> 07 0f c8 c3 66 66 2e 0f 1f 84 00 00 00 00 00 48 81 fe ff ff 03
RSP: 0018:ffffb5b14c56fd78 EFLAGS: 00010292
RAX: ffffb5b141c18000 RBX: ffff8e9f78a801c0 RCX: 0000000000000000
RDX: 0000000000000001 RSI: ffff8e9f7ecd7628 RDI: ffffb5b141c18014
RBP: ffffb5b14c56fd90 R08: 0000000000000001 R09: 0000000000000000
R10: ffff8e9f372a2c30 R11: ffff8e9f87f4bc40 R12: ffff8e9f372a1fc0
R13: ffff8e9f78a80000 R14: ffffffffc07136a0 R15: ffff8e9f78ae6f20
FS:  0000000000000000(0000) GS:ffff8e9f7ecc0000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffffb5b141c18014 CR3: 00000001c8f82006 CR4: 00000000003606e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 ? mlx5_health_try_recover+0x4d/0x270 [mlx5_core]
 mlx5_fw_fatal_reporter_recover+0x16/0x20 [mlx5_core]
 devlink_health_reporter_recover+0x1c/0x50
 devlink_health_report+0xfb/0x240
 mlx5_fw_fatal_reporter_err_work+0x65/0xd0 [mlx5_core]
 process_one_work+0x1fb/0x4e0
 ? process_one_work+0x16b/0x4e0
 worker_thread+0x4f/0x3d0
 kthread+0x10d/0x140
 ? process_one_work+0x4e0/0x4e0
 ? kthread_cancel_delayed_work_sync+0x20/0x20
 ret_from_fork+0x1f/0x30
Modules linked in: nfsv3 rpcsec_gss_krb5 nfsv4 nfs fscache 8021q garp mrp stp llc ipmi_devintf ipmi_msghandler rpcrdma rdma_ucm ib_iser rdma_cm ib_umad iw_cm ib_ipoib libiscsi scsi_transport_iscsi ib_cm mlx5_ib ib_uverbs ib_core mlx5_core sb_edac crct10dif_pclmul crc32_pclmul ghash_clmulni_intel aesni_intel aes_x86_64 mlxfw crypto_simd cryptd glue_helper input_leds hyperv_fb intel_rapl_perf joydev serio_raw pci_hyperv pci_hyperv_mini mac_hid hv_balloon nfsd auth_rpcgss nfs_acl lockd grace sunrpc sch_fq_codel ip_tables x_tables autofs4 hv_utils hid_generic hv_storvsc ptp hid_hyperv hid hv_netvsc hyperv_keyboard pps_core scsi_transport_fc psmouse hv_vmbus i2c_piix4 floppy pata_acpi
CR2: ffffb5b141c18014
---[ end trace b12c5503157cad24 ]---
RIP: 0010:ioread32be+0x30/0x40
Code: 00 77 27 48 81 ff 00 00 01 00 76 07 0f b7 d7 ed 0f c8 c3 55 48 c7 c6 3b ee d5 9f 48 89 e5 e8 67 fc ff ff b8 ff ff ff ff 5d c3 <8b> 07 0f c8 c3 66 66 2e 0f 1f 84 00 00 00 00 00 48 81 fe ff ff 03
RSP: 0018:ffffb5b14c56fd78 EFLAGS: 00010292
RAX: ffffb5b141c18000 RBX: ffff8e9f78a801c0 RCX: 0000000000000000
RDX: 0000000000000001 RSI: ffff8e9f7ecd7628 RDI: ffffb5b141c18014
RBP: ffffb5b14c56fd90 R08: 0000000000000001 R09: 0000000000000000
R10: ffff8e9f372a2c30 R11: ffff8e9f87f4bc40 R12: ffff8e9f372a1fc0
R13: ffff8e9f78a80000 R14: ffffffffc07136a0 R15: ffff8e9f78ae6f20
FS:  0000000000000000(0000) GS:ffff8e9f7ecc0000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffffb5b141c18014 CR3: 00000001c8f82006 CR4: 00000000003606e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
BUG: sleeping function called from invalid context at ./include/linux/percpu-rwsem.h:38
in_atomic(): 0, irqs_disabled(): 1, pid: 6755, name: kworker/u128:2
INFO: lockdep is turned off.
CPU: 3 PID: 6755 Comm: kworker/u128:2 Tainted: G      D           5.2.0-net-next-mlx5-hv_stats-over-last-worked-hyperv #1
Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS 090006  04/28/2016
Workqueue: mlx5_healtha050:00:02.0 mlx5_fw_fatal_reporter_err_work [mlx5_core]
Call Trace:
 dump_stack+0x63/0x88
 ___might_sleep+0x10a/0x130
 __might_sleep+0x4a/0x80
 exit_signals+0x33/0x230
 ? blocking_notifier_call_chain+0x16/0x20
 do_exit+0xb1/0xc30
 ? kthread+0x10d/0x140
 ? process_one_work+0x4e0/0x4e0

Fixes: 52c368dc3da7 ("net/mlx5: Move health and page alloc init to mdev_init")
Signed-off-by: Shay Drory <shayd@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 17f818a54090..3b7d68df9cf2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -795,6 +795,11 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct pci_dev *pdev,
 
 static void mlx5_pci_close(struct mlx5_core_dev *dev)
 {
+	/* health work might still be active, and it needs pci bar in
+	 * order to know the NIC state. Therefore, drain the health WQ
+	 * before removing the pci bars
+	 */
+	mlx5_drain_health_wq(dev);
 	iounmap(dev->iseg);
 	pci_clear_master(dev->pdev);
 	release_bar(dev->pdev);
-- 
2.26.2


From 9a281917d2f8b76825e51d1df879dc26b71cff63 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@mellanox.com>
Date: Thu, 7 May 2020 09:32:53 +0300
Subject: [PATCH 05/16] net/mlx5: Fix fatal error handling during device load

[ Upstream commit b6e0b6bebe0732d5cac51f0791f269d2413b8980 ]

Currently, in case of fatal error during mlx5_load_one(), we cannot
enter error state until mlx5_load_one() is finished, what can take
several minutes until commands will get timeouts, because these commands
can't be processed due to the fatal error.
Fix it by setting dev->state as MLX5_DEVICE_STATE_INTERNAL_ERROR before
requesting the lock.

Fixes: c1d4d2e92ad6 ("net/mlx5: Avoid calling sleeping function by the health poll thread")
Signed-off-by: Shay Drory <shayd@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/health.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index f99e1752d4e5..e22b7ae11275 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -193,15 +193,23 @@ static bool reset_fw_if_needed(struct mlx5_core_dev *dev)
 
 void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force)
 {
+	bool err_detected = false;
+
+	/* Mark the device as fatal in order to abort FW commands */
+	if ((check_fatal_sensors(dev) || force) &&
+	    dev->state == MLX5_DEVICE_STATE_UP) {
+		dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
+		err_detected = true;
+	}
 	mutex_lock(&dev->intf_state_mutex);
-	if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
-		goto unlock;
+	if (!err_detected && dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
+		goto unlock;/* a previous error is still being handled */
 	if (dev->state == MLX5_DEVICE_STATE_UNINITIALIZED) {
 		dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
 		goto unlock;
 	}
 
-	if (check_fatal_sensors(dev) || force) {
+	if (check_fatal_sensors(dev) || force) { /* protected state setting */
 		dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
 		mlx5_cmd_flush(dev);
 	}
-- 
2.26.2


From c6714a1176fad553a1bd65e77e178ed6df759f5b Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Mon, 1 Jun 2020 16:03:44 +0300
Subject: [PATCH 06/16] net/mlx5e: Fix repeated XSK usage on one channel

[ Upstream commit 36d45fb9d2fdf348d778bfe73f0427db1c6f9bc7 ]

After an XSK is closed, the relevant structures in the channel are not
zeroed. If an XSK is opened the second time on the same channel without
recreating channels, the stray values in the structures will lead to
incorrect operation of queues, which causes CQE errors, and the new
socket doesn't work at all.

This patch fixes the issue by explicitly zeroing XSK-related structs in
the channel on XSK close. Note that those structs are zeroed on channel
creation, and usually a configuration change (XDP program is set)
happens on XSK open, which leads to recreating channels, so typical XSK
usecases don't suffer from this issue. However, if XSKs are opened and
closed on the same channel without removing the XDP program, this bug
reproduces.

Fixes: db05815b36cb ("net/mlx5e: Add XSK zero-copy support")
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
index c28cbae42331..2c80205dc939 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
@@ -152,6 +152,10 @@ void mlx5e_close_xsk(struct mlx5e_channel *c)
 	mlx5e_close_cq(&c->xskicosq.cq);
 	mlx5e_close_xdpsq(&c->xsksq);
 	mlx5e_close_cq(&c->xsksq.cq);
+
+	memset(&c->xskrq, 0, sizeof(c->xskrq));
+	memset(&c->xsksq, 0, sizeof(c->xsksq));
+	memset(&c->xskicosq, 0, sizeof(c->xskicosq));
 }
 
 void mlx5e_activate_xsk(struct mlx5e_channel *c)
-- 
2.26.2


From af47bf872485fac8aa259965c61af97d719f156d Mon Sep 17 00:00:00 2001
From: Corentin Labbe <clabbe@baylibre.com>
Date: Wed, 10 Jun 2020 09:53:44 +0000
Subject: [PATCH 07/16] net: cadence: macb: disable NAPI on error

[ Upstream commit 014406babc1f5f887a08737566b5b356c7018242 ]

When the PHY is not working, the macb driver crash on a second try to
setup it.
[   78.545994] macb e000b000.ethernet eth0: Could not attach PHY (-19)
ifconfig: SIOCSIFFLAGS: No such device
[   78.655457] ------------[ cut here ]------------
[   78.656014] kernel BUG at /linux-next/include/linux/netdevice.h:521!
[   78.656504] Internal error: Oops - BUG: 0 [#1] SMP ARM
[   78.657079] Modules linked in:
[   78.657795] CPU: 0 PID: 122 Comm: ifconfig Not tainted 5.7.0-next-20200609 #1
[   78.658202] Hardware name: Xilinx Zynq Platform
[   78.659632] PC is at macb_open+0x220/0x294
[   78.660160] LR is at 0x0
[   78.660373] pc : [<c0b0a634>]    lr : [<00000000>]    psr: 60000013
[   78.660716] sp : c89ffd70  ip : c8a28800  fp : c199bac0
[   78.661040] r10: 00000000  r9 : c8838540  r8 : c8838568
[   78.661362] r7 : 00000001  r6 : c8838000  r5 : c883c000  r4 : 00000000
[   78.661724] r3 : 00000010  r2 : 00000000  r1 : 00000000  r0 : 00000000
[   78.662187] Flags: nZCv  IRQs on  FIQs on  Mode SVC_32  ISA ARM  Segment none
[   78.662635] Control: 10c5387d  Table: 08b64059  DAC: 00000051
[   78.663035] Process ifconfig (pid: 122, stack limit = 0x(ptrval))
[   78.663476] Stack: (0xc89ffd70 to 0xc8a00000)
[   78.664121] fd60:                                     00000000 c89fe000 c8838000 c89fe000
[   78.664866] fd80: 00000000 c11ff9ac c8838028 00000000 00000000 c0de6f2c 00000001 c1804eec
[   78.665579] fda0: c19b8178 c8838000 00000000 ca760866 c8838000 00000001 00001043 c89fe000
[   78.666355] fdc0: 00001002 c0de72f4 c89fe000 c0de8dc0 00008914 c89fe000 c199bac0 ca760866
[   78.667111] fde0: c89ffddc c8838000 00001002 00000000 c8838138 c881010c 00008914 c0de7364
[   78.667862] fe00: 00000000 c89ffe70 c89fe000 ffffffff c881010c c0e8bd48 00000003 00000000
[   78.668601] fe20: c8838000 c8810100 39c1118f 00039c11 c89a0960 00001043 00000000 000a26d0
[   78.669343] fe40: b6f43000 ca760866 c89a0960 00000051 befe6c50 00008914 c8b2a3c0 befe6c50
[   78.670086] fe60: 00000003 ee610500 00000000 c0e8ef58 30687465 00000000 00000000 00000000
[   78.670865] fe80: 00001043 00000000 000a26d0 b6f43000 c89a0600 ee40ae7c c8870d00 c0ddabf4
[   78.671593] fea0: c89ffeec c0ddabf4 c89ffeec c199bac0 00008913 c0ddac48 c89ffeec c89fe000
[   78.672324] fec0: befe6c50 ca760866 befe6c50 00008914 c89fe000 befe6c50 c8b2a3c0 c0dc00e4
[   78.673088] fee0: c89a0480 00000201 00000cc0 30687465 00000000 00000000 00000000 00001002
[   78.673822] ff00: 00000000 000a26d0 b6f43000 ca760866 00008914 c8b2a3c0 000a0ec4 c8b2a3c0
[   78.674576] ff20: befe6c50 c04b21bc 000d5004 00000817 c89a0480 c0315f94 00000000 00000003
[   78.675415] ff40: c19a2bc8 c8a3cc00 c89fe000 00000255 00000000 00000000 00000000 000d5000
[   78.676182] ff60: 000f6000 c180b2a0 00000817 c0315e64 000d5004 c89fffb0 b6ec0c30 ca760866
[   78.676928] ff80: 00000000 000b609b befe6c50 000a0ec4 00000036 c03002c4 c89fe000 00000036
[   78.677673] ffa0: 00000000 c03000c0 000b609b befe6c50 00000003 00008914 befe6c50 000b609b
[   78.678415] ffc0: 000b609b befe6c50 000a0ec4 00000036 befe6e0c befe6f1a 000d5150 00000000
[   78.679154] ffe0: 000d41e4 befe6bf4 00019648 b6e4509c 20000010 00000003 00000000 00000000
[   78.681059] [<c0b0a634>] (macb_open) from [<c0de6f2c>] (__dev_open+0xd0/0x154)
[   78.681571] [<c0de6f2c>] (__dev_open) from [<c0de72f4>] (__dev_change_flags+0x16c/0x1c4)
[   78.682015] [<c0de72f4>] (__dev_change_flags) from [<c0de7364>] (dev_change_flags+0x18/0x48)
[   78.682493] [<c0de7364>] (dev_change_flags) from [<c0e8bd48>] (devinet_ioctl+0x5e4/0x75c)
[   78.682945] [<c0e8bd48>] (devinet_ioctl) from [<c0e8ef58>] (inet_ioctl+0x1f0/0x3b4)
[   78.683381] [<c0e8ef58>] (inet_ioctl) from [<c0dc00e4>] (sock_ioctl+0x39c/0x664)
[   78.683818] [<c0dc00e4>] (sock_ioctl) from [<c04b21bc>] (ksys_ioctl+0x2d8/0x9c0)
[   78.684343] [<c04b21bc>] (ksys_ioctl) from [<c03000c0>] (ret_fast_syscall+0x0/0x54)
[   78.684789] Exception stack(0xc89fffa8 to 0xc89ffff0)
[   78.685346] ffa0:                   000b609b befe6c50 00000003 00008914 befe6c50 000b609b
[   78.686106] ffc0: 000b609b befe6c50 000a0ec4 00000036 befe6e0c befe6f1a 000d5150 00000000
[   78.686710] ffe0: 000d41e4 befe6bf4 00019648 b6e4509c
[   78.687582] Code: 9a000003 e5983078 e3130001 1affffef (e7f001f2)
[   78.688788] ---[ end trace e3f2f6ab69754eae ]---

This is due to NAPI left enabled if macb_phylink_connect() fail.

Fixes: 7897b071ac3b ("net: macb: convert to phylink")
Signed-off-by: Corentin Labbe <clabbe@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 36290a8e2a84..5b9d7c60eebc 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -2558,13 +2558,16 @@ static int macb_open(struct net_device *dev)
 
 	err = macb_phylink_connect(bp);
 	if (err)
-		goto pm_exit;
+		goto napi_exit;
 
 	netif_tx_start_all_queues(dev);
 
 	if (bp->ptp_info)
 		bp->ptp_info->ptp_init(dev);
 
+napi_exit:
+	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
+		napi_disable(&queue->napi);
 pm_exit:
 	if (err) {
 		pm_runtime_put_sync(&bp->pdev->dev);
-- 
2.26.2


From 77f66dc2d4a06e7fe0c6defd772bc11cda4659b4 Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.cirrus.com>
Date: Mon, 15 Jun 2020 14:18:54 +0100
Subject: [PATCH 08/16] net: macb: Only disable NAPI on the actual error path

[ Upstream commit 939a5bf7c9b7a1ad9c5d3481c93766a522773531 ]

A recent change added a disable to NAPI into macb_open, this was
intended to only happen on the error path but accidentally applies
to all paths. This causes NAPI to be disabled on the success path, which
leads to the network to no longer functioning.

Fixes: 014406babc1f ("net: cadence: macb: disable NAPI on error")
Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Tested-by: Corentin Labbe <clabbe@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 5b9d7c60eebc..67933079aeea 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -2565,15 +2565,14 @@ static int macb_open(struct net_device *dev)
 	if (bp->ptp_info)
 		bp->ptp_info->ptp_init(dev);
 
+	return 0;
+
 napi_exit:
 	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
 		napi_disable(&queue->napi);
 pm_exit:
-	if (err) {
-		pm_runtime_put_sync(&bp->pdev->dev);
-		return err;
-	}
-	return 0;
+	pm_runtime_put_sync(&bp->pdev->dev);
+	return err;
 }
 
 static int macb_close(struct net_device *dev)
-- 
2.26.2


From 00d44c0b9a019ea695ebfe946a87f6fd4e4b8769 Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@mellanox.com>
Date: Thu, 14 May 2020 05:12:56 -0500
Subject: [PATCH 09/16] net/mlx5: Disable reload while removing the device

[ Upstream commit 60904cd349abc98cb888fc28d1ca55a8e2cf87b3 ]

While unregistration is in progress, user might be reloading the
interface.
This can race with unregistration in below flow which uses the
resources which are getting disabled by reload flow.

Hence, disable the devlink reloading first when removing the device.

     CPU0                                   CPU1
     ----                                   ----
local_pci_remove()                  devlink_mutex
  remove_one()                       devlink_nl_cmd_reload()
    mlx5_unregister_device()           devlink_reload()
                                       ops->reload_down()
                                         mlx5_unload_one()

Fixes: 4383cfcc65e7 ("net/mlx5: Add devlink reload")
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/devlink.c | 2 --
 drivers/net/ethernet/mellanox/mlx5/core/main.c    | 2 ++
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index e94f0c4d74a7..a99fe4b02b9b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -283,7 +283,6 @@ int mlx5_devlink_register(struct devlink *devlink, struct device *dev)
 		goto params_reg_err;
 	mlx5_devlink_set_params_init_values(devlink);
 	devlink_params_publish(devlink);
-	devlink_reload_enable(devlink);
 	return 0;
 
 params_reg_err:
@@ -293,7 +292,6 @@ int mlx5_devlink_register(struct devlink *devlink, struct device *dev)
 
 void mlx5_devlink_unregister(struct devlink *devlink)
 {
-	devlink_reload_disable(devlink);
 	devlink_params_unregister(devlink, mlx5_devlink_params,
 				  ARRAY_SIZE(mlx5_devlink_params));
 	devlink_unregister(devlink);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 3b7d68df9cf2..980f6b833cbe 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1373,6 +1373,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 		dev_err(&pdev->dev, "mlx5_crdump_enable failed with error code %d\n", err);
 
 	pci_save_state(pdev);
+	devlink_reload_enable(devlink);
 	return 0;
 
 err_load_one:
@@ -1390,6 +1391,7 @@ static void remove_one(struct pci_dev *pdev)
 	struct mlx5_core_dev *dev  = pci_get_drvdata(pdev);
 	struct devlink *devlink = priv_to_devlink(dev);
 
+	devlink_reload_disable(devlink);
 	mlx5_crdump_disable(dev);
 	mlx5_devlink_unregister(devlink);
 
-- 
2.26.2


From bd7652d8bc0446bf3847ba624fb3be7a9aedf8bc Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 10 Jun 2020 10:49:00 +0200
Subject: [PATCH 10/16] mptcp: don't leak msk in token container

[ Upstream commit 4b5af44129d0653a4df44e5511c7d480c61c8f3c ]

If a listening MPTCP socket has unaccepted sockets at close
time, the related msks are freed via mptcp_sock_destruct(),
which in turn does not invoke the proto->destroy() method
nor the mptcp_token_destroy() function.

Due to the above, the child msk socket is not removed from
the token container, leading to later UaF.

Address the issue explicitly removing the token even in the
above error path.

Fixes: 79c0949e9a09 ("mptcp: Add key generation and token tree")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/subflow.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 8968b2c065e7..e6feb05a93dc 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -393,6 +393,7 @@ static void mptcp_sock_destruct(struct sock *sk)
 		sock_orphan(sk);
 	}
 
+	mptcp_token_destroy(mptcp_sk(sk)->token);
 	inet_sock_destruct(sk);
 }
 
-- 
2.26.2


From 5679121a115076eced43fb8c0f2a7af77e685516 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <snelson@pensando.io>
Date: Mon, 8 Jun 2020 20:41:43 -0700
Subject: [PATCH 11/16] ionic: wait on queue start until after IFF_UP

[ Upstream commit 976ee3b21119dcf5c6d96233d688a1453f29fa83 ]

The netif_running() test looks at __LINK_STATE_START which
gets set before ndo_open() is called, there is a window of
time between that and when the queues are actually ready to
be run.  If ionic_check_link_status() notices that the link is
up very soon after netif_running() becomes true, it might try
to run the queues before they are ready, causing all manner of
potential issues.  Since the netdev->flags IFF_UP isn't set
until after ndo_open() returns, we can wait for that before
we allow ionic_check_link_status() to start the queues.

On the way back to close, __LINK_STATE_START is cleared before
calling ndo_stop(), and IFF_UP is cleared after.  Both of
these need to be true in order to safely stop the queues
from ionic_check_link_status().

Fixes: 49d3b493673a ("ionic: disable the queues on link down")
Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/pensando/ionic/ionic_lif.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index f8a9c1bcffc9..7aa037c3fe02 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -105,7 +105,7 @@ static void ionic_link_status_check(struct ionic_lif *lif)
 			netif_carrier_on(netdev);
 		}
 
-		if (netif_running(lif->netdev))
+		if (lif->netdev->flags & IFF_UP && netif_running(lif->netdev))
 			ionic_start_queues(lif);
 	} else {
 		if (netif_carrier_ok(netdev)) {
@@ -113,7 +113,7 @@ static void ionic_link_status_check(struct ionic_lif *lif)
 			netif_carrier_off(netdev);
 		}
 
-		if (netif_running(lif->netdev))
+		if (lif->netdev->flags & IFF_UP && netif_running(lif->netdev))
 			ionic_stop_queues(lif);
 	}
 
-- 
2.26.2


From 927a56609e7fa3822ccef43683b9a0bc572f500f Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 10 Jun 2020 10:47:41 +0200
Subject: [PATCH 12/16] mptcp: fix races between shutdown and recvmsg

[ Upstream commit 5969856ae8ce29c9d523a1a6145cbd9e87f7046c ]

The msk sk_shutdown flag is set by a workqueue, possibly
introducing some delay in user-space notification. If the last
subflow carries some data with the fin packet, the user space
can wake-up before RCV_SHUTDOWN is set. If it executes unblocking
recvmsg(), it may return with an error instead of eof.

Address the issue explicitly checking for eof in recvmsg(), when
no data is found.

Fixes: 59832e246515 ("mptcp: subflow: check parent mptcp socket on subflow state change")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/protocol.c | 45 +++++++++++++++++++++++---------------------
 1 file changed, 24 insertions(+), 21 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 34dd0e278a82..4bf4f629975d 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -357,6 +357,27 @@ void mptcp_subflow_eof(struct sock *sk)
 		sock_hold(sk);
 }
 
+static void mptcp_check_for_eof(struct mptcp_sock *msk)
+{
+	struct mptcp_subflow_context *subflow;
+	struct sock *sk = (struct sock *)msk;
+	int receivers = 0;
+
+	mptcp_for_each_subflow(msk, subflow)
+		receivers += !subflow->rx_eof;
+
+	if (!receivers && !(sk->sk_shutdown & RCV_SHUTDOWN)) {
+		/* hopefully temporary hack: propagate shutdown status
+		 * to msk, when all subflows agree on it
+		 */
+		sk->sk_shutdown |= RCV_SHUTDOWN;
+
+		smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
+		set_bit(MPTCP_DATA_READY, &msk->flags);
+		sk->sk_data_ready(sk);
+	}
+}
+
 static void mptcp_stop_timer(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
@@ -933,6 +954,9 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 				break;
 			}
 
+			if (test_and_clear_bit(MPTCP_WORK_EOF, &msk->flags))
+				mptcp_check_for_eof(msk);
+
 			if (sk->sk_shutdown & RCV_SHUTDOWN)
 				break;
 
@@ -1070,27 +1094,6 @@ static unsigned int mptcp_sync_mss(struct sock *sk, u32 pmtu)
 	return 0;
 }
 
-static void mptcp_check_for_eof(struct mptcp_sock *msk)
-{
-	struct mptcp_subflow_context *subflow;
-	struct sock *sk = (struct sock *)msk;
-	int receivers = 0;
-
-	mptcp_for_each_subflow(msk, subflow)
-		receivers += !subflow->rx_eof;
-
-	if (!receivers && !(sk->sk_shutdown & RCV_SHUTDOWN)) {
-		/* hopefully temporary hack: propagate shutdown status
-		 * to msk, when all subflows agree on it
-		 */
-		sk->sk_shutdown |= RCV_SHUTDOWN;
-
-		smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
-		set_bit(MPTCP_DATA_READY, &msk->flags);
-		sk->sk_data_ready(sk);
-	}
-}
-
 static void mptcp_worker(struct work_struct *work)
 {
 	struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work);
-- 
2.26.2


From 2a90c5fa9fa8b3e6e4e011009d8a4dc719eac616 Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Sat, 13 Jun 2020 17:54:14 +0300
Subject: [PATCH 13/16] net: ethernet: ti: ale: fix allmulti for nu type ale

[ Upstream commit bc139119a1708ae3db1ebb379630f286e28d06e8 ]

On AM65xx MCU CPSW2G NUSS and 66AK2E/L NUSS allmulti setting does not allow
unregistered mcast packets to pass.

This happens, because ALE VLAN entries on these SoCs do not contain port
masks for reg/unreg mcast packets, but instead store indexes of
ALE_VLAN_MASK_MUXx_REG registers which intended for store port masks for
reg/unreg mcast packets.
This path was missed by commit 9d1f6447274f ("net: ethernet: ti: ale: fix
seeing unreg mcast packets with promisc and allmulti disabled").

Hence, fix it by taking into account ALE type in cpsw_ale_set_allmulti().

Fixes: 9d1f6447274f ("net: ethernet: ti: ale: fix seeing unreg mcast packets with promisc and allmulti disabled")
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw_ale.c | 49 ++++++++++++++++++++++++------
 1 file changed, 40 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c
index 8dc6be11b2ff..9ad872bfae3a 100644
--- a/drivers/net/ethernet/ti/cpsw_ale.c
+++ b/drivers/net/ethernet/ti/cpsw_ale.c
@@ -604,10 +604,44 @@ void cpsw_ale_set_unreg_mcast(struct cpsw_ale *ale, int unreg_mcast_mask,
 	}
 }
 
+static void cpsw_ale_vlan_set_unreg_mcast(struct cpsw_ale *ale, u32 *ale_entry,
+					  int allmulti)
+{
+	int unreg_mcast;
+
+	unreg_mcast =
+		cpsw_ale_get_vlan_unreg_mcast(ale_entry,
+					      ale->vlan_field_bits);
+	if (allmulti)
+		unreg_mcast |= ALE_PORT_HOST;
+	else
+		unreg_mcast &= ~ALE_PORT_HOST;
+	cpsw_ale_set_vlan_unreg_mcast(ale_entry, unreg_mcast,
+				      ale->vlan_field_bits);
+}
+
+static void
+cpsw_ale_vlan_set_unreg_mcast_idx(struct cpsw_ale *ale, u32 *ale_entry,
+				  int allmulti)
+{
+	int unreg_mcast;
+	int idx;
+
+	idx = cpsw_ale_get_vlan_unreg_mcast_idx(ale_entry);
+
+	unreg_mcast = readl(ale->params.ale_regs + ALE_VLAN_MASK_MUX(idx));
+
+	if (allmulti)
+		unreg_mcast |= ALE_PORT_HOST;
+	else
+		unreg_mcast &= ~ALE_PORT_HOST;
+
+	writel(unreg_mcast, ale->params.ale_regs + ALE_VLAN_MASK_MUX(idx));
+}
+
 void cpsw_ale_set_allmulti(struct cpsw_ale *ale, int allmulti, int port)
 {
 	u32 ale_entry[ALE_ENTRY_WORDS];
-	int unreg_mcast = 0;
 	int type, idx;
 
 	for (idx = 0; idx < ale->params.ale_entries; idx++) {
@@ -624,15 +658,12 @@ void cpsw_ale_set_allmulti(struct cpsw_ale *ale, int allmulti, int port)
 		if (port != -1 && !(vlan_members & BIT(port)))
 			continue;
 
-		unreg_mcast =
-			cpsw_ale_get_vlan_unreg_mcast(ale_entry,
-						      ale->vlan_field_bits);
-		if (allmulti)
-			unreg_mcast |= ALE_PORT_HOST;
+		if (!ale->params.nu_switch_ale)
+			cpsw_ale_vlan_set_unreg_mcast(ale, ale_entry, allmulti);
 		else
-			unreg_mcast &= ~ALE_PORT_HOST;
-		cpsw_ale_set_vlan_unreg_mcast(ale_entry, unreg_mcast,
-					      ale->vlan_field_bits);
+			cpsw_ale_vlan_set_unreg_mcast_idx(ale, ale_entry,
+							  allmulti);
+
 		cpsw_ale_write(ale, idx, ale_entry);
 	}
 }
-- 
2.26.2


From 1ce4852a085afd271e3f56fb3b5ccd68fe01a4be Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Sat, 13 Jun 2020 17:52:59 +0300
Subject: [PATCH 14/16] net: ethernet: ti: am65-cpsw-nuss: fix ale parameters
 init

[ Upstream commit 2074f9eaa58795a99e9da61c10f93180f810cfd6 ]

The ALE parameters structure is created on stack, so it has to be reset
before passing to cpsw_ale_create() to avoid garbage values.

Fixes: 93a76530316a ("net: ethernet: ti: introduce am65x/j721e gigabit eth subsystem driver")
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/am65-cpsw-nuss.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index 88f52a2f85b3..3e4388e6b5fa 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -1804,7 +1804,7 @@ MODULE_DEVICE_TABLE(of, am65_cpsw_nuss_of_mtable);
 
 static int am65_cpsw_nuss_probe(struct platform_device *pdev)
 {
-	struct cpsw_ale_params ale_params;
+	struct cpsw_ale_params ale_params = { 0 };
 	const struct of_device_id *of_id;
 	struct device *dev = &pdev->dev;
 	struct am65_cpsw_common *common;
-- 
2.26.2


From 1a08dc2c655f61654965d88230abbdafed9bbc95 Mon Sep 17 00:00:00 2001
From: Valentin Longchamp <valentin@longchamp.me>
Date: Tue, 9 Jun 2020 22:11:54 +0200
Subject: [PATCH 15/16] net: sched: export __netdev_watchdog_up()

[ Upstream commit 1a3db27ad9a72d033235b9673653962c02e3486e ]

Since the quiesce/activate rework, __netdev_watchdog_up() is directly
called in the ucc_geth driver.

Unfortunately, this function is not available for modules and thus
ucc_geth cannot be built as a module anymore. Fix it by exporting
__netdev_watchdog_up().

Since the commit introducing the regression was backported to stable
branches, this one should ideally be as well.

Fixes: 79dde73cf9bc ("net/ethernet/freescale: rework quiesce/activate for ucc_geth")
Signed-off-by: Valentin Longchamp <valentin@longchamp.me>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_generic.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 2efd5b61acef..9763da6daa9f 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -464,6 +464,7 @@ void __netdev_watchdog_up(struct net_device *dev)
 			dev_hold(dev);
 	}
 }
+EXPORT_SYMBOL_GPL(__netdev_watchdog_up);
 
 static void dev_watchdog_up(struct net_device *dev)
 {
-- 
2.26.2


From 92942dd74d997710ba130616ad13a1d5fe5a3315 Mon Sep 17 00:00:00 2001
From: Oz Shlomo <ozsh@mellanox.com>
Date: Sun, 7 Jun 2020 15:40:40 +0000
Subject: [PATCH 16/16] net/mlx5e: CT: Fix ipv6 nat header rewrite actions

[ Upstream commit 0d156f2deda8675c29fa2b8b5ed9b374370e47f2 ]

Set the ipv6 word fields according to the hardware definitions.

Fixes: ac991b48d43c ("net/mlx5e: CT: Offload established flows")
Signed-off-by: Oz Shlomo <ozsh@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en/tc_ct.c   | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
index 4eb305af0106..153d6eb19d3c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
@@ -320,21 +320,21 @@ mlx5_tc_ct_parse_mangle_to_mod_act(struct flow_action_entry *act,
 
 	case FLOW_ACT_MANGLE_HDR_TYPE_IP6:
 		MLX5_SET(set_action_in, modact, length, 0);
-		if (offset == offsetof(struct ipv6hdr, saddr))
+		if (offset == offsetof(struct ipv6hdr, saddr) + 12)
 			field = MLX5_ACTION_IN_FIELD_OUT_SIPV6_31_0;
-		else if (offset == offsetof(struct ipv6hdr, saddr) + 4)
-			field = MLX5_ACTION_IN_FIELD_OUT_SIPV6_63_32;
 		else if (offset == offsetof(struct ipv6hdr, saddr) + 8)
+			field = MLX5_ACTION_IN_FIELD_OUT_SIPV6_63_32;
+		else if (offset == offsetof(struct ipv6hdr, saddr) + 4)
 			field = MLX5_ACTION_IN_FIELD_OUT_SIPV6_95_64;
-		else if (offset == offsetof(struct ipv6hdr, saddr) + 12)
+		else if (offset == offsetof(struct ipv6hdr, saddr))
 			field = MLX5_ACTION_IN_FIELD_OUT_SIPV6_127_96;
-		else if (offset == offsetof(struct ipv6hdr, daddr))
+		else if (offset == offsetof(struct ipv6hdr, daddr) + 12)
 			field = MLX5_ACTION_IN_FIELD_OUT_DIPV6_31_0;
-		else if (offset == offsetof(struct ipv6hdr, daddr) + 4)
-			field = MLX5_ACTION_IN_FIELD_OUT_DIPV6_63_32;
 		else if (offset == offsetof(struct ipv6hdr, daddr) + 8)
+			field = MLX5_ACTION_IN_FIELD_OUT_DIPV6_63_32;
+		else if (offset == offsetof(struct ipv6hdr, daddr) + 4)
 			field = MLX5_ACTION_IN_FIELD_OUT_DIPV6_95_64;
-		else if (offset == offsetof(struct ipv6hdr, daddr) + 12)
+		else if (offset == offsetof(struct ipv6hdr, daddr))
 			field = MLX5_ACTION_IN_FIELD_OUT_DIPV6_127_96;
 		else
 			return -EOPNOTSUPP;
-- 
2.26.2

Re: [PATCHES] Networking

[Greg KH]

On Mon, Jun 15, 2020 at 06:27:06PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v5.6 and
> v5.7 -stable, respectively.

All queued up now, thanks!

greg k-h

Re: [PATCHES] Networking

[Greg KH]

On Tue, Jun 16, 2020 at 09:43:56AM +0200, Greg KH wrote:
> On Mon, Jun 15, 2020 at 06:27:06PM -0700, David Miller wrote:
> > 
> > Please queue up the following networking bug fixes for v5.6 and
> > v5.7 -stable, respectively.
> 
> All queued up now, thanks!

Note, 5.6 is now end-of-life, so no need for any more stable patches for
that tree, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 105 bytes --]


Please queue up the following networking bug fixes for v5.4 and v5.7
-stable, respectively.

Thank you.

[-- Attachment #2: net_54.mbox --]
[-- Type: Application/Octet-Stream, Size: 72845 bytes --]

From 637f721ea216db1d087affcae1762ff9433ec372 Mon Sep 17 00:00:00 2001
From: Claudiu Manoil <claudiu.manoil@nxp.com>
Date: Fri, 26 Jun 2020 19:17:29 +0300
Subject: [PATCH 01/26] enetc: Fix tx rings bitmap iteration range, irq
 handling

[ Upstream commit 0574e2000fc3103cbc69ba82ec1175ce171fdf5e ]

The rings bitmap of an interrupt vector encodes
which of the device's rings were assigned to that
interrupt vector.
Hence the iteration range of the tx rings bitmap
(for_each_set_bit()) should be the total number of
Tx rings of that netdevice instead of the number of
rings assigned to the interrupt vector.
Since there are 2 cores, and one interrupt vector for
each core, the number of rings asigned to an interrupt
vector is half the number of available rings.
The impact of this error is that the upper half of the
tx rings could still generate interrupts during napi
polling.

Fixes: d4fd0404c1c9 ("enetc: Introduce basic PF and VF ENETC ethernet drivers")
Signed-off-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/enetc/enetc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index b6ff89307409..4ef4d41b0d8d 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -254,7 +254,7 @@ static irqreturn_t enetc_msix(int irq, void *data)
 	/* disable interrupts */
 	enetc_wr_reg(v->rbier, 0);
 
-	for_each_set_bit(i, &v->tx_rings_map, v->count_tx_rings)
+	for_each_set_bit(i, &v->tx_rings_map, ENETC_MAX_NUM_TXQS)
 		enetc_wr_reg(v->tbier_base + ENETC_BDR_OFF(i), 0);
 
 	napi_schedule_irqoff(&v->napi);
@@ -290,7 +290,7 @@ static int enetc_poll(struct napi_struct *napi, int budget)
 	/* enable interrupts */
 	enetc_wr_reg(v->rbier, ENETC_RBIER_RXTIE);
 
-	for_each_set_bit(i, &v->tx_rings_map, v->count_tx_rings)
+	for_each_set_bit(i, &v->tx_rings_map, ENETC_MAX_NUM_TXQS)
 		enetc_wr_reg(v->tbier_base + ENETC_BDR_OFF(i),
 			     ENETC_TBIER_TXTIE);
 
-- 
2.26.2


From ae51075e3a629e51832dd1208a0c80ba8578b708 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Thu, 18 Jun 2020 12:13:22 +0200
Subject: [PATCH 02/26] geneve: allow changing DF behavior after creation

[ Upstream commit 56c09de347e40804fc8dad155272fb9609e0a97b ]

Currently, trying to change the DF parameter of a geneve device does
nothing:

    # ip -d link show geneve1
    14: geneve1: <snip>
        link/ether <snip>
        geneve id 1 remote 10.0.0.1 ttl auto df set dstport 6081 <snip>
    # ip link set geneve1 type geneve id 1 df unset
    # ip -d link show geneve1
    14: geneve1: <snip>
        link/ether <snip>
        geneve id 1 remote 10.0.0.1 ttl auto df set dstport 6081 <snip>

We just need to update the value in geneve_changelink.

Fixes: a025fb5f49ad ("geneve: Allow configuration of DF behaviour")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index cac75c7d1d01..19d9d78a6df2 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1649,6 +1649,7 @@ static int geneve_changelink(struct net_device *dev, struct nlattr *tb[],
 	geneve->collect_md = metadata;
 	geneve->use_udp6_rx_checksums = use_udp6_rx_checksums;
 	geneve->ttl_inherit = ttl_inherit;
+	geneve->df = df;
 	geneve_unquiesce(geneve, gs4, gs6);
 
 	return 0;
-- 
2.26.2


From 3286d60bfb85a3279c6d5bd42f4b55d40ff46fbf Mon Sep 17 00:00:00 2001
From: Thomas Falcon <tlfalcon@linux.ibm.com>
Date: Thu, 18 Jun 2020 10:43:46 -0500
Subject: [PATCH 03/26] ibmveth: Fix max MTU limit

[ Upstream commit 5948378b26d89f8aa5eac37629dbd0616ce8d7a7 ]

The max MTU limit defined for ibmveth is not accounting for
virtual ethernet buffer overhead, which is twenty-two additional
bytes set aside for the ethernet header and eight additional bytes
of an opaque handle reserved for use by the hypervisor. Update the
max MTU to reflect this overhead.

Fixes: d894be57ca92 ("ethernet: use net core MTU range checking in more drivers")
Fixes: 110447f8269a ("ethernet: fix min/max MTU typos")
Signed-off-by: Thomas Falcon <tlfalcon@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ibm/ibmveth.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index c5be4ebd8437..aa32a5b04112 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -1682,7 +1682,7 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	}
 
 	netdev->min_mtu = IBMVETH_MIN_MTU;
-	netdev->max_mtu = ETH_MAX_MTU;
+	netdev->max_mtu = ETH_MAX_MTU - IBMVETH_BUFF_OH;
 
 	memcpy(netdev->dev_addr, mac_addr_p, ETH_ALEN);
 
-- 
2.26.2


From 6903cc61a2507b50c4dc3fe0137411aba5e43aa9 Mon Sep 17 00:00:00 2001
From: Wang Hai <wanghai38@huawei.com>
Date: Thu, 11 Jun 2020 15:57:50 +0800
Subject: [PATCH 04/26] mld: fix memory leak in ipv6_mc_destroy_dev()

[ Upstream commit ea2fce88d2fd678ed9d45354ff49b73f1d5615dd ]

Commit a84d01647989 ("mld: fix memory leak in mld_del_delrec()") fixed
the memory leak of MLD, but missing the ipv6_mc_destroy_dev() path, in
which mca_sources are leaked after ma_put().

Using ip6_mc_clear_src() to take care of the missing free.

BUG: memory leak
unreferenced object 0xffff8881113d3180 (size 64):
  comm "syz-executor071", pid 389, jiffies 4294887985 (age 17.943s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 ff 02 00 00 00 00 00 00  ................
    00 00 00 00 00 00 00 01 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<000000002cbc483c>] kmalloc include/linux/slab.h:555 [inline]
    [<000000002cbc483c>] kzalloc include/linux/slab.h:669 [inline]
    [<000000002cbc483c>] ip6_mc_add1_src net/ipv6/mcast.c:2237 [inline]
    [<000000002cbc483c>] ip6_mc_add_src+0x7f5/0xbb0 net/ipv6/mcast.c:2357
    [<0000000058b8b1ff>] ip6_mc_source+0xe0c/0x1530 net/ipv6/mcast.c:449
    [<000000000bfc4fb5>] do_ipv6_setsockopt.isra.12+0x1b2c/0x3b30 net/ipv6/ipv6_sockglue.c:754
    [<00000000e4e7a722>] ipv6_setsockopt+0xda/0x150 net/ipv6/ipv6_sockglue.c:950
    [<0000000029260d9a>] rawv6_setsockopt+0x45/0x100 net/ipv6/raw.c:1081
    [<000000005c1b46f9>] __sys_setsockopt+0x131/0x210 net/socket.c:2132
    [<000000008491f7db>] __do_sys_setsockopt net/socket.c:2148 [inline]
    [<000000008491f7db>] __se_sys_setsockopt net/socket.c:2145 [inline]
    [<000000008491f7db>] __x64_sys_setsockopt+0xba/0x150 net/socket.c:2145
    [<00000000c7bc11c5>] do_syscall_64+0xa1/0x530 arch/x86/entry/common.c:295
    [<000000005fb7a3f3>] entry_SYSCALL_64_after_hwframe+0x49/0xb3

Fixes: 1666d49e1d41 ("mld: do not remove mld souce list info when set link down")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Wang Hai <wanghai38@huawei.com>
Acked-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/mcast.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index eaa4c2cc2fbb..c875c9b6edbe 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -2618,6 +2618,7 @@ void ipv6_mc_destroy_dev(struct inet6_dev *idev)
 		idev->mc_list = i->next;
 
 		write_unlock_bh(&idev->lock);
+		ip6_mc_clear_src(i);
 		ma_put(i);
 		write_lock_bh(&idev->lock);
 	}
-- 
2.26.2


From 7a374fd30a50a568f0ecec6074e868a52a089dab Mon Sep 17 00:00:00 2001
From: Sven Auhagen <sven.auhagen@voleatech.de>
Date: Sun, 14 Jun 2020 09:19:17 +0200
Subject: [PATCH 05/26] mvpp2: ethtool rxtx stats fix

[ Upstream commit cc970925feb9a38c2f0d34305518e00a3084ce85 ]

The ethtool rx and tx queue statistics are reporting wrong values.
Fix reading out the correct ones.

Signed-off-by: Sven Auhagen <sven.auhagen@voleatech.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index cf5d447af7db..0f136f1af5d1 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -1541,7 +1541,7 @@ static void mvpp2_read_stats(struct mvpp2_port *port)
 	for (q = 0; q < port->ntxqs; q++)
 		for (i = 0; i < ARRAY_SIZE(mvpp2_ethtool_txq_regs); i++)
 			*pstats++ += mvpp2_read_index(port->priv,
-						      MVPP22_CTRS_TX_CTR(port->id, i),
+						      MVPP22_CTRS_TX_CTR(port->id, q),
 						      mvpp2_ethtool_txq_regs[i].offset);
 
 	/* Rxqs are numbered from 0 from the user standpoint, but not from the
@@ -1550,7 +1550,7 @@ static void mvpp2_read_stats(struct mvpp2_port *port)
 	for (q = 0; q < port->nrxqs; q++)
 		for (i = 0; i < ARRAY_SIZE(mvpp2_ethtool_rxq_regs); i++)
 			*pstats++ += mvpp2_read_index(port->priv,
-						      port->first_rxq + i,
+						      port->first_rxq + q,
 						      mvpp2_ethtool_rxq_regs[i].offset);
 }
 
-- 
2.26.2


From ddfbec47f74ca9be60ae630670912676a2b3037b Mon Sep 17 00:00:00 2001
From: Thomas Martitz <t.martitz@avm.de>
Date: Thu, 25 Jun 2020 14:26:03 +0200
Subject: [PATCH 06/26] net: bridge: enfore alignment for ethernet address

[ Upstream commit db7202dec92e6caa2706c21d6fc359af318bde2e ]

The eth_addr member is passed to ether_addr functions that require
2-byte alignment, therefore the member must be properly aligned
to avoid unaligned accesses.

The problem is in place since the initial merge of multicast to unicast:
commit 6db6f0eae6052b70885562e1733896647ec1d807 bridge: multicast to unicast

Fixes: 6db6f0eae605 ("bridge: multicast to unicast")
Cc: Roopa Prabhu <roopa@cumulusnetworks.com>
Cc: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Felix Fietkau <nbd@nbd.name>
Cc: stable@vger.kernel.org
Signed-off-by: Thomas Martitz <t.martitz@avm.de>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_private.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index ce2ab14ee605..cecb4223440e 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -208,8 +208,8 @@ struct net_bridge_port_group {
 	struct rcu_head			rcu;
 	struct timer_list		timer;
 	struct br_ip			addr;
+	unsigned char			eth_addr[ETH_ALEN] __aligned(2);
 	unsigned char			flags;
-	unsigned char			eth_addr[ETH_ALEN];
 };
 
 struct net_bridge_mdb_entry {
-- 
2.26.2


From 1d1b419e4d6bd33708e8ffb2a95ae04818ddcf0e Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Tue, 16 Jun 2020 15:52:05 +0000
Subject: [PATCH 07/26] net: core: reduce recursion limit value

[ Upstream commit fb7861d14c8d7edac65b2fcb6e8031cb138457b2 ]

In the current code, ->ndo_start_xmit() can be executed recursively only
10 times because of stack memory.
But, in the case of the vxlan, 10 recursion limit value results in
a stack overflow.
In the current code, the nested interface is limited by 8 depth.
There is no critical reason that the recursion limitation value should
be 10.
So, it would be good to be the same value with the limitation value of
nesting interface depth.

Test commands:
    ip link add vxlan10 type vxlan vni 10 dstport 4789 srcport 4789 4789
    ip link set vxlan10 up
    ip a a 192.168.10.1/24 dev vxlan10
    ip n a 192.168.10.2 dev vxlan10 lladdr fc:22:33:44:55:66 nud permanent

    for i in {9..0}
    do
        let A=$i+1
	ip link add vxlan$i type vxlan vni $i dstport 4789 srcport 4789 4789
	ip link set vxlan$i up
	ip a a 192.168.$i.1/24 dev vxlan$i
	ip n a 192.168.$i.2 dev vxlan$i lladdr fc:22:33:44:55:66 nud permanent
	bridge fdb add fc:22:33:44:55:66 dev vxlan$A dst 192.168.$i.2 self
    done
    hping3 192.168.10.2 -2 -d 60000

Splat looks like:
[  103.814237][ T1127] =============================================================================
[  103.871955][ T1127] BUG kmalloc-2k (Tainted: G    B            ): Padding overwritten. 0x00000000897a2e4f-0x000
[  103.873187][ T1127] -----------------------------------------------------------------------------
[  103.873187][ T1127]
[  103.874252][ T1127] INFO: Slab 0x000000005cccc724 objects=5 used=5 fp=0x0000000000000000 flags=0x10000000001020
[  103.881323][ T1127] CPU: 3 PID: 1127 Comm: hping3 Tainted: G    B             5.7.0+ #575
[  103.882131][ T1127] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[  103.883006][ T1127] Call Trace:
[  103.883324][ T1127]  dump_stack+0x96/0xdb
[  103.883716][ T1127]  slab_err+0xad/0xd0
[  103.884106][ T1127]  ? _raw_spin_unlock+0x1f/0x30
[  103.884620][ T1127]  ? get_partial_node.isra.78+0x140/0x360
[  103.885214][ T1127]  slab_pad_check.part.53+0xf7/0x160
[  103.885769][ T1127]  ? pskb_expand_head+0x110/0xe10
[  103.886316][ T1127]  check_slab+0x97/0xb0
[  103.886763][ T1127]  alloc_debug_processing+0x84/0x1a0
[  103.887308][ T1127]  ___slab_alloc+0x5a5/0x630
[  103.887765][ T1127]  ? pskb_expand_head+0x110/0xe10
[  103.888265][ T1127]  ? lock_downgrade+0x730/0x730
[  103.888762][ T1127]  ? pskb_expand_head+0x110/0xe10
[  103.889244][ T1127]  ? __slab_alloc+0x3e/0x80
[  103.889675][ T1127]  __slab_alloc+0x3e/0x80
[  103.890108][ T1127]  __kmalloc_node_track_caller+0xc7/0x420
[ ... ]

Fixes: 11a766ce915f ("net: Increase xmit RECURSION_LIMIT to 10.")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index b580a35f50ea..ec3081ab04c0 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3043,7 +3043,7 @@ static inline int dev_recursion_level(void)
 	return this_cpu_read(softnet_data.xmit.recursion);
 }
 
-#define XMIT_RECURSION_LIMIT	10
+#define XMIT_RECURSION_LIMIT	8
 static inline bool dev_xmit_recursion(void)
 {
 	return unlikely(__this_cpu_read(softnet_data.xmit.recursion) >
-- 
2.26.2


From f76ee2cbf468a057f1dd6319863fce13b08e49ae Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Mon, 22 Jun 2020 23:26:04 +0300
Subject: [PATCH 08/26] net: Do not clear the sock TX queue in sk_set_socket()

[ Upstream commit 41b14fb8724d5a4b382a63cb4a1a61880347ccb8 ]

Clearing the sock TX queue in sk_set_socket() might cause unexpected
out-of-order transmit when called from sock_orphan(), as outstanding
packets can pick a different TX queue and bypass the ones already queued.

This is undesired in general. More specifically, it breaks the in-order
scheduling property guarantee for device-offloaded TLS sockets.

Remove the call to sk_tx_queue_clear() in sk_set_socket(), and add it
explicitly only where needed.

Fixes: e022f0b4a03f ("net: Introduce sk_tx_queue_mapping")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h | 1 -
 net/core/sock.c    | 2 ++
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index 6c5a3809483e..8263bbf756a2 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1803,7 +1803,6 @@ static inline int sk_rx_queue_get(const struct sock *sk)
 
 static inline void sk_set_socket(struct sock *sk, struct socket *sock)
 {
-	sk_tx_queue_clear(sk);
 	sk->sk_socket = sock;
 }
 
diff --git a/net/core/sock.c b/net/core/sock.c
index 0adf7a9e5a90..0a2aef870d00 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1679,6 +1679,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
 		cgroup_sk_alloc(&sk->sk_cgrp_data);
 		sock_update_classid(&sk->sk_cgrp_data);
 		sock_update_netprioidx(&sk->sk_cgrp_data);
+		sk_tx_queue_clear(sk);
 	}
 
 	return sk;
@@ -1895,6 +1896,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		 */
 		sk_refcnt_debug_inc(newsk);
 		sk_set_socket(newsk, NULL);
+		sk_tx_queue_clear(newsk);
 		RCU_INIT_POINTER(newsk->sk_wq, NULL);
 
 		if (newsk->sk_prot->sockets_allocated)
-- 
2.26.2


From fbf807a44a31f76c8b2be9e4061d37b3e7213d81 Mon Sep 17 00:00:00 2001
From: Yang Yingliang <yangyingliang@huawei.com>
Date: Tue, 16 Jun 2020 09:39:21 +0000
Subject: [PATCH 09/26] net: fix memleak in register_netdevice()

[ Upstream commit 814152a89ed52c722ab92e9fbabcac3cb8a39245 ]

I got a memleak report when doing some fuzz test:

unreferenced object 0xffff888112584000 (size 13599):
  comm "ip", pid 3048, jiffies 4294911734 (age 343.491s)
  hex dump (first 32 bytes):
    74 61 70 30 00 00 00 00 00 00 00 00 00 00 00 00  tap0............
    00 ee d9 19 81 88 ff ff 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<000000002f60ba65>] __kmalloc_node+0x309/0x3a0
    [<0000000075b211ec>] kvmalloc_node+0x7f/0xc0
    [<00000000d3a97396>] alloc_netdev_mqs+0x76/0xfc0
    [<00000000609c3655>] __tun_chr_ioctl+0x1456/0x3d70
    [<000000001127ca24>] ksys_ioctl+0xe5/0x130
    [<00000000b7d5e66a>] __x64_sys_ioctl+0x6f/0xb0
    [<00000000e1023498>] do_syscall_64+0x56/0xa0
    [<000000009ec0eb12>] entry_SYSCALL_64_after_hwframe+0x44/0xa9
unreferenced object 0xffff888111845cc0 (size 8):
  comm "ip", pid 3048, jiffies 4294911734 (age 343.491s)
  hex dump (first 8 bytes):
    74 61 70 30 00 88 ff ff                          tap0....
  backtrace:
    [<000000004c159777>] kstrdup+0x35/0x70
    [<00000000d8b496ad>] kstrdup_const+0x3d/0x50
    [<00000000494e884a>] kvasprintf_const+0xf1/0x180
    [<0000000097880a2b>] kobject_set_name_vargs+0x56/0x140
    [<000000008fbdfc7b>] dev_set_name+0xab/0xe0
    [<000000005b99e3b4>] netdev_register_kobject+0xc0/0x390
    [<00000000602704fe>] register_netdevice+0xb61/0x1250
    [<000000002b7ca244>] __tun_chr_ioctl+0x1cd1/0x3d70
    [<000000001127ca24>] ksys_ioctl+0xe5/0x130
    [<00000000b7d5e66a>] __x64_sys_ioctl+0x6f/0xb0
    [<00000000e1023498>] do_syscall_64+0x56/0xa0
    [<000000009ec0eb12>] entry_SYSCALL_64_after_hwframe+0x44/0xa9
unreferenced object 0xffff88811886d800 (size 512):
  comm "ip", pid 3048, jiffies 4294911734 (age 343.491s)
  hex dump (first 32 bytes):
    00 00 00 00 ad 4e ad de ff ff ff ff 00 00 00 00  .....N..........
    ff ff ff ff ff ff ff ff c0 66 3d a3 ff ff ff ff  .........f=.....
  backtrace:
    [<0000000050315800>] device_add+0x61e/0x1950
    [<0000000021008dfb>] netdev_register_kobject+0x17e/0x390
    [<00000000602704fe>] register_netdevice+0xb61/0x1250
    [<000000002b7ca244>] __tun_chr_ioctl+0x1cd1/0x3d70
    [<000000001127ca24>] ksys_ioctl+0xe5/0x130
    [<00000000b7d5e66a>] __x64_sys_ioctl+0x6f/0xb0
    [<00000000e1023498>] do_syscall_64+0x56/0xa0
    [<000000009ec0eb12>] entry_SYSCALL_64_after_hwframe+0x44/0xa9

If call_netdevice_notifiers() failed, then rollback_registered()
calls netdev_unregister_kobject() which holds the kobject. The
reference cannot be put because the netdev won't be add to todo
list, so it will leads a memleak, we need put the reference to
avoid memleak.

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/net/core/dev.c b/net/core/dev.c
index 204d87e7c9b1..5b7d9c2b821d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -9114,6 +9114,13 @@ int register_netdevice(struct net_device *dev)
 		rcu_barrier();
 
 		dev->reg_state = NETREG_UNREGISTERED;
+		/* We should put the kobject that hold in
+		 * netdev_unregister_kobject(), otherwise
+		 * the net device cannot be freed when
+		 * driver calls free_netdev(), because the
+		 * kobject is being hold.
+		 */
+		kobject_put(&dev->dev.kobj);
 	}
 	/*
 	 *	Prevent userspace races by waiting until the network
-- 
2.26.2


From 8b4e2c89eac7bf09e0e34a844abf1dd22b296219 Mon Sep 17 00:00:00 2001
From: guodeqing <geffrey.guo@huawei.com>
Date: Wed, 17 Jun 2020 10:07:16 +0800
Subject: [PATCH 10/26] net: Fix the arp error in some cases

[ Upstream commit 5eea3a63ff4aba6a26002e657a6d21934b7e2b96 ]

ie.,
$ ifconfig eth0 6.6.6.6 netmask 255.255.255.0

$ ip rule add from 6.6.6.6 table 6666

$ ip route add 9.9.9.9 via 6.6.6.6

$ ping -I 6.6.6.6 9.9.9.9
PING 9.9.9.9 (9.9.9.9) from 6.6.6.6 : 56(84) bytes of data.

3 packets transmitted, 0 received, 100% packet loss, time 2079ms

$ arp
Address     HWtype  HWaddress           Flags Mask            Iface
6.6.6.6             (incomplete)                              eth0

The arp request address is error, this is because fib_table_lookup in
fib_check_nh lookup the destnation 9.9.9.9 nexthop, the scope of
the fib result is RT_SCOPE_LINK,the correct scope is RT_SCOPE_HOST.
Here I add a check of whether this is RT_TABLE_MAIN to solve this problem.

Fixes: 3bfd847203c6 ("net: Use passed in table for nexthop lookups")
Signed-off-by: guodeqing <geffrey.guo@huawei.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_semantics.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 01588eef0cee..b1b3220917ca 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1100,7 +1100,7 @@ static int fib_check_nh_v4_gw(struct net *net, struct fib_nh *nh, u32 table,
 		if (fl4.flowi4_scope < RT_SCOPE_LINK)
 			fl4.flowi4_scope = RT_SCOPE_LINK;
 
-		if (table)
+		if (table && table != RT_TABLE_MAIN)
 			tbl = fib_get_table(net, table);
 
 		if (tbl)
-- 
2.26.2


From 858622c28621f661d03de000156dad31db3643c2 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 17 Jun 2020 22:23:25 -0700
Subject: [PATCH 11/26] net: increment xmit_recursion level in
 dev_direct_xmit()

[ Upstream commit 0ad6f6e767ec2f613418cbc7ebe5ec4c35af540c ]

Back in commit f60e5990d9c1 ("ipv6: protect skb->sk accesses
from recursive dereference inside the stack") Hannes added code
so that IPv6 stack would not trust skb->sk for typical cases
where packet goes through 'standard' xmit path (__dev_queue_xmit())

Alas af_packet had a dev_direct_xmit() path that was not
dealing yet with xmit_recursion level.

Also change sk_mc_loop() to dump a stack once only.

Without this patch, syzbot was able to trigger :

[1]
[  153.567378] WARNING: CPU: 7 PID: 11273 at net/core/sock.c:721 sk_mc_loop+0x51/0x70
[  153.567378] Modules linked in: nfnetlink ip6table_raw ip6table_filter iptable_raw iptable_nat nf_nat nf_conntrack nf_defrag_ipv4 nf_defrag_ipv6 iptable_filter macsec macvtap tap macvlan 8021q hsr wireguard libblake2s blake2s_x86_64 libblake2s_generic udp_tunnel ip6_udp_tunnel libchacha20poly1305 poly1305_x86_64 chacha_x86_64 libchacha curve25519_x86_64 libcurve25519_generic netdevsim batman_adv dummy team bridge stp llc w1_therm wire i2c_mux_pca954x i2c_mux cdc_acm ehci_pci ehci_hcd mlx4_en mlx4_ib ib_uverbs ib_core mlx4_core
[  153.567386] CPU: 7 PID: 11273 Comm: b159172088 Not tainted 5.8.0-smp-DEV #273
[  153.567387] RIP: 0010:sk_mc_loop+0x51/0x70
[  153.567388] Code: 66 83 f8 0a 75 24 0f b6 4f 12 b8 01 00 00 00 31 d2 d3 e0 a9 bf ef ff ff 74 07 48 8b 97 f0 02 00 00 0f b6 42 3a 83 e0 01 5d c3 <0f> 0b b8 01 00 00 00 5d c3 0f b6 87 18 03 00 00 5d c0 e8 04 83 e0
[  153.567388] RSP: 0018:ffff95c69bb93990 EFLAGS: 00010212
[  153.567388] RAX: 0000000000000011 RBX: ffff95c6e0ee3e00 RCX: 0000000000000007
[  153.567389] RDX: ffff95c69ae50000 RSI: ffff95c6c30c3000 RDI: ffff95c6c30c3000
[  153.567389] RBP: ffff95c69bb93990 R08: ffff95c69a77f000 R09: 0000000000000008
[  153.567389] R10: 0000000000000040 R11: 00003e0e00026128 R12: ffff95c6c30c3000
[  153.567390] R13: ffff95c6cc4fd500 R14: ffff95c6f84500c0 R15: ffff95c69aa13c00
[  153.567390] FS:  00007fdc3a283700(0000) GS:ffff95c6ff9c0000(0000) knlGS:0000000000000000
[  153.567390] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  153.567391] CR2: 00007ffee758e890 CR3: 0000001f9ba20003 CR4: 00000000001606e0
[  153.567391] Call Trace:
[  153.567391]  ip6_finish_output2+0x34e/0x550
[  153.567391]  __ip6_finish_output+0xe7/0x110
[  153.567391]  ip6_finish_output+0x2d/0xb0
[  153.567392]  ip6_output+0x77/0x120
[  153.567392]  ? __ip6_finish_output+0x110/0x110
[  153.567392]  ip6_local_out+0x3d/0x50
[  153.567392]  ipvlan_queue_xmit+0x56c/0x5e0
[  153.567393]  ? ksize+0x19/0x30
[  153.567393]  ipvlan_start_xmit+0x18/0x50
[  153.567393]  dev_direct_xmit+0xf3/0x1c0
[  153.567393]  packet_direct_xmit+0x69/0xa0
[  153.567394]  packet_sendmsg+0xbf0/0x19b0
[  153.567394]  ? plist_del+0x62/0xb0
[  153.567394]  sock_sendmsg+0x65/0x70
[  153.567394]  sock_write_iter+0x93/0xf0
[  153.567394]  new_sync_write+0x18e/0x1a0
[  153.567395]  __vfs_write+0x29/0x40
[  153.567395]  vfs_write+0xb9/0x1b0
[  153.567395]  ksys_write+0xb1/0xe0
[  153.567395]  __x64_sys_write+0x1a/0x20
[  153.567395]  do_syscall_64+0x43/0x70
[  153.567396]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[  153.567396] RIP: 0033:0x453549
[  153.567396] Code: Bad RIP value.
[  153.567396] RSP: 002b:00007fdc3a282cc8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
[  153.567397] RAX: ffffffffffffffda RBX: 00000000004d32d0 RCX: 0000000000453549
[  153.567397] RDX: 0000000000000020 RSI: 0000000020000300 RDI: 0000000000000003
[  153.567398] RBP: 00000000004d32d8 R08: 0000000000000000 R09: 0000000000000000
[  153.567398] R10: 0000000000000000 R11: 0000000000000246 R12: 00000000004d32dc
[  153.567398] R13: 00007ffee742260f R14: 00007fdc3a282dc0 R15: 00007fdc3a283700
[  153.567399] ---[ end trace c1d5ae2b1059ec62 ]---

f60e5990d9c1 ("ipv6: protect skb->sk accesses from recursive dereference inside the stack")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c  | 2 ++
 net/core/sock.c | 2 +-
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 5b7d9c2b821d..727965565d31 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3832,10 +3832,12 @@ int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
 
 	local_bh_disable();
 
+	dev_xmit_recursion_inc();
 	HARD_TX_LOCK(dev, txq, smp_processor_id());
 	if (!netif_xmit_frozen_or_drv_stopped(txq))
 		ret = netdev_start_xmit(skb, dev, txq, false);
 	HARD_TX_UNLOCK(dev, txq);
+	dev_xmit_recursion_dec();
 
 	local_bh_enable();
 
diff --git a/net/core/sock.c b/net/core/sock.c
index 0a2aef870d00..078791a6649a 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -709,7 +709,7 @@ bool sk_mc_loop(struct sock *sk)
 		return inet6_sk(sk)->mc_loop;
 #endif
 	}
-	WARN_ON(1);
+	WARN_ON_ONCE(1);
 	return true;
 }
 EXPORT_SYMBOL(sk_mc_loop);
-- 
2.26.2


From 044629c5d9204d18308e4bfe81706fd3540e75be Mon Sep 17 00:00:00 2001
From: Jeremy Kerr <jk@ozlabs.org>
Date: Mon, 15 Jun 2020 10:54:56 +0800
Subject: [PATCH 12/26] net: usb: ax88179_178a: fix packet alignment padding

[ Upstream commit e869e7a17798d85829fa7d4f9bbe1eebd4b2d3f6 ]

Using a AX88179 device (0b95:1790), I see two bytes of appended data on
every RX packet. For example, this 48-byte ping, using 0xff as a
payload byte:

  04:20:22.528472 IP 192.168.1.1 > 192.168.1.2: ICMP echo request, id 2447, seq 1, length 64
	0x0000:  000a cd35 ea50 000a cd35 ea4f 0800 4500
	0x0010:  0054 c116 4000 4001 f63e c0a8 0101 c0a8
	0x0020:  0102 0800 b633 098f 0001 87ea cd5e 0000
	0x0030:  0000 dcf2 0600 0000 0000 ffff ffff ffff
	0x0040:  ffff ffff ffff ffff ffff ffff ffff ffff
	0x0050:  ffff ffff ffff ffff ffff ffff ffff ffff
	0x0060:  ffff 961f

Those last two bytes - 96 1f - aren't part of the original packet.

In the ax88179 RX path, the usbnet rx_fixup function trims a 2-byte
'alignment pseudo header' from the start of the packet, and sets the
length from a per-packet field populated by hardware. It looks like that
length field *includes* the 2-byte header; the current driver assumes
that it's excluded.

This change trims the 2-byte alignment header after we've set the packet
length, so the resulting packet length is correct. While we're moving
the comment around, this also fixes the spelling of 'pseudo'.

Signed-off-by: Jeremy Kerr <jk@ozlabs.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/ax88179_178a.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c
index daa54486ab09..df2f7cc6dc03 100644
--- a/drivers/net/usb/ax88179_178a.c
+++ b/drivers/net/usb/ax88179_178a.c
@@ -1387,10 +1387,10 @@ static int ax88179_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 		}
 
 		if (pkt_cnt == 0) {
-			/* Skip IP alignment psudo header */
-			skb_pull(skb, 2);
 			skb->len = pkt_len;
-			skb_set_tail_pointer(skb, pkt_len);
+			/* Skip IP alignment pseudo header */
+			skb_pull(skb, 2);
+			skb_set_tail_pointer(skb, skb->len);
 			skb->truesize = pkt_len + sizeof(struct sk_buff);
 			ax88179_rx_checksum(skb, pkt_hdr);
 			return 1;
@@ -1399,8 +1399,9 @@ static int ax88179_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 		ax_skb = skb_clone(skb, GFP_ATOMIC);
 		if (ax_skb) {
 			ax_skb->len = pkt_len;
-			ax_skb->data = skb->data + 2;
-			skb_set_tail_pointer(ax_skb, pkt_len);
+			/* Skip IP alignment pseudo header */
+			skb_pull(ax_skb, 2);
+			skb_set_tail_pointer(ax_skb, ax_skb->len);
 			ax_skb->truesize = pkt_len + sizeof(struct sk_buff);
 			ax88179_rx_checksum(ax_skb, pkt_hdr);
 			usbnet_skb_return(dev, ax_skb);
-- 
2.26.2


From 9a17bbedf00f4942ffac8deac771138e500fc333 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 23 Jun 2020 18:33:15 +0200
Subject: [PATCH 13/26] openvswitch: take into account
 de-fragmentation/gso_size in execute_check_pkt_len

[ Upstream commit 17843655708e1941c0653af3cd61be6948e36f43 ]

ovs connection tracking module performs de-fragmentation on incoming
fragmented traffic. Take info account if traffic has been de-fragmented
in execute_check_pkt_len action otherwise we will perform the wrong
nested action considering the original packet size. This issue typically
occurs if ovs-vswitchd adds a rule in the pipeline that requires connection
tracking (e.g. OVN stateful ACLs) before execute_check_pkt_len action.
Moreover take into account GSO fragment size for GSO packet in
execute_check_pkt_len routine

Fixes: 4d5ec89fc8d14 ("net: openvswitch: Add a new action check_pkt_len")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/actions.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 99352f09deaa..3d96dab10449 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -1146,9 +1146,10 @@ static int execute_check_pkt_len(struct datapath *dp, struct sk_buff *skb,
 				 struct sw_flow_key *key,
 				 const struct nlattr *attr, bool last)
 {
+	struct ovs_skb_cb *ovs_cb = OVS_CB(skb);
 	const struct nlattr *actions, *cpl_arg;
+	int len, max_len, rem = nla_len(attr);
 	const struct check_pkt_len_arg *arg;
-	int rem = nla_len(attr);
 	bool clone_flow_key;
 
 	/* The first netlink attribute in 'attr' is always
@@ -1157,7 +1158,11 @@ static int execute_check_pkt_len(struct datapath *dp, struct sk_buff *skb,
 	cpl_arg = nla_data(attr);
 	arg = nla_data(cpl_arg);
 
-	if (skb->len <= arg->pkt_len) {
+	len = ovs_cb->mru ? ovs_cb->mru + skb->mac_len : skb->len;
+	max_len = arg->pkt_len;
+
+	if ((skb_is_gso(skb) && skb_gso_validate_mac_len(skb, max_len)) ||
+	    len <= max_len) {
 		/* Second netlink attribute in 'attr' is always
 		 * 'OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL'.
 		 */
-- 
2.26.2


From 83d8d23cb8c2341a56b05504af2e25f49aeda70b Mon Sep 17 00:00:00 2001
From: Aditya Pakki <pakki001@umn.edu>
Date: Fri, 12 Jun 2020 15:27:55 -0500
Subject: [PATCH 14/26] rocker: fix incorrect error handling in dma_rings_init

[ Upstream commit 58d0c864e1a759a15c9df78f50ea5a5c32b3989e ]

In rocker_dma_rings_init, the goto blocks in case of errors
caused by the functions rocker_dma_cmd_ring_waits_alloc() and
rocker_dma_ring_create() are incorrect. The patch fixes the
order consistent with cleanup in rocker_dma_rings_fini().

Signed-off-by: Aditya Pakki <pakki001@umn.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/rocker/rocker_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index 786b158bd305..5abb3f9684ff 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -647,10 +647,10 @@ static int rocker_dma_rings_init(struct rocker *rocker)
 err_dma_event_ring_bufs_alloc:
 	rocker_dma_ring_destroy(rocker, &rocker->event_ring);
 err_dma_event_ring_create:
+	rocker_dma_cmd_ring_waits_free(rocker);
+err_dma_cmd_ring_waits_alloc:
 	rocker_dma_ring_bufs_free(rocker, &rocker->cmd_ring,
 				  PCI_DMA_BIDIRECTIONAL);
-err_dma_cmd_ring_waits_alloc:
-	rocker_dma_cmd_ring_waits_free(rocker);
 err_dma_cmd_ring_bufs_alloc:
 	rocker_dma_ring_destroy(rocker, &rocker->cmd_ring);
 	return err;
-- 
2.26.2


From 954cfc8ee817dffc17e0cf8f6e17da213aa5f372 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 19 Jun 2020 23:38:16 +0100
Subject: [PATCH 15/26] rxrpc: Fix notification call on completion of discarded
 calls

[ Upstream commit 0041cd5a50442db6e456b145892a0eaf2dff061f ]

When preallocated service calls are being discarded, they're passed to
->discard_new_call() to have the caller clean up any attached higher-layer
preallocated pieces before being marked completed.  However, the act of
marking them completed now invokes the call's notification function - which
causes a problem because that function might assume that the previously
freed pieces of memory are still there.

Fix this by setting a dummy notification function on the socket after
calling ->discard_new_call().

This results in the following kasan message when the kafs module is
removed.

==================================================================
BUG: KASAN: use-after-free in afs_wake_up_async_call+0x6aa/0x770 fs/afs/rxrpc.c:707
Write of size 1 at addr ffff8880946c39e4 by task kworker/u4:1/21

CPU: 0 PID: 21 Comm: kworker/u4:1 Not tainted 5.8.0-rc1-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Workqueue: netns cleanup_net
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x18f/0x20d lib/dump_stack.c:118
 print_address_description.constprop.0.cold+0xd3/0x413 mm/kasan/report.c:383
 __kasan_report mm/kasan/report.c:513 [inline]
 kasan_report.cold+0x1f/0x37 mm/kasan/report.c:530
 afs_wake_up_async_call+0x6aa/0x770 fs/afs/rxrpc.c:707
 rxrpc_notify_socket+0x1db/0x5d0 net/rxrpc/recvmsg.c:40
 __rxrpc_set_call_completion.part.0+0x172/0x410 net/rxrpc/recvmsg.c:76
 __rxrpc_call_completed net/rxrpc/recvmsg.c:112 [inline]
 rxrpc_call_completed+0xca/0xf0 net/rxrpc/recvmsg.c:111
 rxrpc_discard_prealloc+0x781/0xab0 net/rxrpc/call_accept.c:233
 rxrpc_listen+0x147/0x360 net/rxrpc/af_rxrpc.c:245
 afs_close_socket+0x95/0x320 fs/afs/rxrpc.c:110
 afs_net_exit+0x1bc/0x310 fs/afs/main.c:155
 ops_exit_list.isra.0+0xa8/0x150 net/core/net_namespace.c:186
 cleanup_net+0x511/0xa50 net/core/net_namespace.c:603
 process_one_work+0x965/0x1690 kernel/workqueue.c:2269
 worker_thread+0x96/0xe10 kernel/workqueue.c:2415
 kthread+0x3b5/0x4a0 kernel/kthread.c:291
 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:293

Allocated by task 6820:
 save_stack+0x1b/0x40 mm/kasan/common.c:48
 set_track mm/kasan/common.c:56 [inline]
 __kasan_kmalloc mm/kasan/common.c:494 [inline]
 __kasan_kmalloc.constprop.0+0xbf/0xd0 mm/kasan/common.c:467
 kmem_cache_alloc_trace+0x153/0x7d0 mm/slab.c:3551
 kmalloc include/linux/slab.h:555 [inline]
 kzalloc include/linux/slab.h:669 [inline]
 afs_alloc_call+0x55/0x630 fs/afs/rxrpc.c:141
 afs_charge_preallocation+0xe9/0x2d0 fs/afs/rxrpc.c:757
 afs_open_socket+0x292/0x360 fs/afs/rxrpc.c:92
 afs_net_init+0xa6c/0xe30 fs/afs/main.c:125
 ops_init+0xaf/0x420 net/core/net_namespace.c:151
 setup_net+0x2de/0x860 net/core/net_namespace.c:341
 copy_net_ns+0x293/0x590 net/core/net_namespace.c:482
 create_new_namespaces+0x3fb/0xb30 kernel/nsproxy.c:110
 unshare_nsproxy_namespaces+0xbd/0x1f0 kernel/nsproxy.c:231
 ksys_unshare+0x43d/0x8e0 kernel/fork.c:2983
 __do_sys_unshare kernel/fork.c:3051 [inline]
 __se_sys_unshare kernel/fork.c:3049 [inline]
 __x64_sys_unshare+0x2d/0x40 kernel/fork.c:3049
 do_syscall_64+0x60/0xe0 arch/x86/entry/common.c:359
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Freed by task 21:
 save_stack+0x1b/0x40 mm/kasan/common.c:48
 set_track mm/kasan/common.c:56 [inline]
 kasan_set_free_info mm/kasan/common.c:316 [inline]
 __kasan_slab_free+0xf7/0x140 mm/kasan/common.c:455
 __cache_free mm/slab.c:3426 [inline]
 kfree+0x109/0x2b0 mm/slab.c:3757
 afs_put_call+0x585/0xa40 fs/afs/rxrpc.c:190
 rxrpc_discard_prealloc+0x764/0xab0 net/rxrpc/call_accept.c:230
 rxrpc_listen+0x147/0x360 net/rxrpc/af_rxrpc.c:245
 afs_close_socket+0x95/0x320 fs/afs/rxrpc.c:110
 afs_net_exit+0x1bc/0x310 fs/afs/main.c:155
 ops_exit_list.isra.0+0xa8/0x150 net/core/net_namespace.c:186
 cleanup_net+0x511/0xa50 net/core/net_namespace.c:603
 process_one_work+0x965/0x1690 kernel/workqueue.c:2269
 worker_thread+0x96/0xe10 kernel/workqueue.c:2415
 kthread+0x3b5/0x4a0 kernel/kthread.c:291
 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:293

The buggy address belongs to the object at ffff8880946c3800
 which belongs to the cache kmalloc-1k of size 1024
The buggy address is located 484 bytes inside of
 1024-byte region [ffff8880946c3800, ffff8880946c3c00)
The buggy address belongs to the page:
page:ffffea000251b0c0 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0
flags: 0xfffe0000000200(slab)
raw: 00fffe0000000200 ffffea0002546508 ffffea00024fa248 ffff8880aa000c40
raw: 0000000000000000 ffff8880946c3000 0000000100000002 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff8880946c3880: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff8880946c3900: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff8880946c3980: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                                                       ^
 ffff8880946c3a00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff8880946c3a80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
==================================================================

Reported-by: syzbot+d3eccef36ddbd02713e9@syzkaller.appspotmail.com
Fixes: 5ac0d62226a0 ("rxrpc: Fix missing notification")
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/call_accept.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index b7611cc159e5..032ed76c0166 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -22,6 +22,11 @@
 #include <net/ip.h>
 #include "ar-internal.h"
 
+static void rxrpc_dummy_notify(struct sock *sk, struct rxrpc_call *call,
+			       unsigned long user_call_ID)
+{
+}
+
 /*
  * Preallocate a single service call, connection and peer and, if possible,
  * give them a user ID and attach the user's side of the ID to them.
@@ -228,6 +233,8 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx)
 		if (rx->discard_new_call) {
 			_debug("discard %lx", call->user_call_ID);
 			rx->discard_new_call(call, call->user_call_ID);
+			if (call->notify_rx)
+				call->notify_rx = rxrpc_dummy_notify;
 			rxrpc_put_call(call, rxrpc_call_put_kernel);
 		}
 		rxrpc_call_completed(call);
-- 
2.26.2


From dfb5e3bedace901471efd8f0dbbef39d220fd77d Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Wed, 24 Jun 2020 17:34:18 -0300
Subject: [PATCH 16/26] sctp: Don't advertise IPv4 addresses if ipv6only is set
 on the socket

[ Upstream commit 471e39df96b9a4c4ba88a2da9e25a126624d7a9c ]

If a socket is set ipv6only, it will still send IPv4 addresses in the
INIT and INIT_ACK packets. This potentially misleads the peer into using
them, which then would cause association termination.

The fix is to not add IPv4 addresses to ipv6only sockets.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: Corey Minyard <cminyard@mvista.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Tested-by: Corey Minyard <cminyard@mvista.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/constants.h | 8 +++++---
 net/sctp/associola.c         | 5 ++++-
 net/sctp/bind_addr.c         | 1 +
 net/sctp/protocol.c          | 3 ++-
 4 files changed, 12 insertions(+), 5 deletions(-)

diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h
index 823afc42a3aa..06e1deeef464 100644
--- a/include/net/sctp/constants.h
+++ b/include/net/sctp/constants.h
@@ -341,11 +341,13 @@ enum {
 	 ipv4_is_anycast_6to4(a))
 
 /* Flags used for the bind address copy functions.  */
-#define SCTP_ADDR6_ALLOWED	0x00000001	/* IPv6 address is allowed by
+#define SCTP_ADDR4_ALLOWED	0x00000001	/* IPv4 address is allowed by
 						   local sock family */
-#define SCTP_ADDR4_PEERSUPP	0x00000002	/* IPv4 address is supported by
+#define SCTP_ADDR6_ALLOWED	0x00000002	/* IPv6 address is allowed by
+						   local sock family */
+#define SCTP_ADDR4_PEERSUPP	0x00000004	/* IPv4 address is supported by
 						   peer */
-#define SCTP_ADDR6_PEERSUPP	0x00000004	/* IPv6 address is supported by
+#define SCTP_ADDR6_PEERSUPP	0x00000008	/* IPv6 address is supported by
 						   peer */
 
 /* Reasons to retransmit. */
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 41839b85c268..fb6f62264e87 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -1569,12 +1569,15 @@ void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned int len)
 int sctp_assoc_set_bind_addr_from_ep(struct sctp_association *asoc,
 				     enum sctp_scope scope, gfp_t gfp)
 {
+	struct sock *sk = asoc->base.sk;
 	int flags;
 
 	/* Use scoping rules to determine the subset of addresses from
 	 * the endpoint.
 	 */
-	flags = (PF_INET6 == asoc->base.sk->sk_family) ? SCTP_ADDR6_ALLOWED : 0;
+	flags = (PF_INET6 == sk->sk_family) ? SCTP_ADDR6_ALLOWED : 0;
+	if (!inet_v6_ipv6only(sk))
+		flags |= SCTP_ADDR4_ALLOWED;
 	if (asoc->peer.ipv4_address)
 		flags |= SCTP_ADDR4_PEERSUPP;
 	if (asoc->peer.ipv6_address)
diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c
index 53bc61537f44..701c5a4e441d 100644
--- a/net/sctp/bind_addr.c
+++ b/net/sctp/bind_addr.c
@@ -461,6 +461,7 @@ static int sctp_copy_one_addr(struct net *net, struct sctp_bind_addr *dest,
 		 * well as the remote peer.
 		 */
 		if ((((AF_INET == addr->sa.sa_family) &&
+		      (flags & SCTP_ADDR4_ALLOWED) &&
 		      (flags & SCTP_ADDR4_PEERSUPP))) ||
 		    (((AF_INET6 == addr->sa.sa_family) &&
 		      (flags & SCTP_ADDR6_ALLOWED) &&
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 237c88eeb538..981c7cbca46a 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -148,7 +148,8 @@ int sctp_copy_local_addr_list(struct net *net, struct sctp_bind_addr *bp,
 		 * sock as well as the remote peer.
 		 */
 		if (addr->a.sa.sa_family == AF_INET &&
-		    !(copy_flags & SCTP_ADDR4_PEERSUPP))
+		    (!(copy_flags & SCTP_ADDR4_ALLOWED) ||
+		     !(copy_flags & SCTP_ADDR4_PEERSUPP)))
 			continue;
 		if (addr->a.sa.sa_family == AF_INET6 &&
 		    (!(copy_flags & SCTP_ADDR6_ALLOWED) ||
-- 
2.26.2


From 1c04d3799f88e28fec92d32bcea9cd6b72170bee Mon Sep 17 00:00:00 2001
From: Denis Kirjanov <kda@linux-powerpc.org>
Date: Thu, 25 Jun 2020 14:51:06 +0300
Subject: [PATCH 17/26] tcp: don't ignore ECN CWR on pure ACK

[ Upstream commit 2570284060b48f3f79d8f1a2698792f36c385e9a ]

there is a problem with the CWR flag set in an incoming ACK segment
and it leads to the situation when the ECE flag is latched forever

the following packetdrill script shows what happens:

// Stack receives incoming segments with CE set
+0.1 <[ect0]  . 11001:12001(1000) ack 1001 win 65535
+0.0 <[ce]    . 12001:13001(1000) ack 1001 win 65535
+0.0 <[ect0] P. 13001:14001(1000) ack 1001 win 65535

// Stack repsonds with ECN ECHO
+0.0 >[noecn]  . 1001:1001(0) ack 12001
+0.0 >[noecn] E. 1001:1001(0) ack 13001
+0.0 >[noecn] E. 1001:1001(0) ack 14001

// Write a packet
+0.1 write(3, ..., 1000) = 1000
+0.0 >[ect0] PE. 1001:2001(1000) ack 14001

// Pure ACK received
+0.01 <[noecn] W. 14001:14001(0) ack 2001 win 65535

// Since CWR was sent, this packet should NOT have ECE set

+0.1 write(3, ..., 1000) = 1000
+0.0 >[ect0]  P. 2001:3001(1000) ack 14001
// but Linux will still keep ECE latched here, with packetdrill
// flagging a missing ECE flag, expecting
// >[ect0] PE. 2001:3001(1000) ack 14001
// in the script

In the situation above we will continue to send ECN ECHO packets
and trigger the peer to reduce the congestion window. To avoid that
we can check CWR on pure ACKs received.

v3:
- Add a sequence check to avoid sending an ACK to an ACK

v2:
- Adjusted the comment
- move CWR check before checking for unacknowledged packets

Signed-off-by: Denis Kirjanov <denis.kirjanov@suse.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 677facbeed26..cc8411c98f28 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -260,7 +260,8 @@ static void tcp_ecn_accept_cwr(struct sock *sk, const struct sk_buff *skb)
 		 * cwnd may be very low (even just 1 packet), so we should ACK
 		 * immediately.
 		 */
-		inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
+		if (TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq)
+			inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
 	}
 }
 
@@ -3682,6 +3683,15 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 		tcp_in_ack_event(sk, ack_ev_flags);
 	}
 
+	/* This is a deviation from RFC3168 since it states that:
+	 * "When the TCP data sender is ready to set the CWR bit after reducing
+	 * the congestion window, it SHOULD set the CWR bit only on the first
+	 * new data packet that it transmits."
+	 * We accept CWR on pure ACKs to be more robust
+	 * with widely-deployed TCP implementations that do this.
+	 */
+	tcp_ecn_accept_cwr(sk, skb);
+
 	/* We passed data and got it acked, remove any soft error
 	 * log. Something worked...
 	 */
@@ -4771,8 +4781,6 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 	skb_dst_drop(skb);
 	__skb_pull(skb, tcp_hdr(skb)->doff * 4);
 
-	tcp_ecn_accept_cwr(sk, skb);
-
 	tp->rx_opt.dsack = 0;
 
 	/*  Queue data for delivery to the user.
-- 
2.26.2


From 761670cf6d79d5f901465094f8876e2ab5187c82 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 15 Jun 2020 20:37:07 -0700
Subject: [PATCH 18/26] tcp: grow window for OOO packets only for SACK flows

[ Upstream commit 662051215c758ae8545451628816204ed6cd372d ]

Back in 2013, we made a change that broke fast retransmit
for non SACK flows.

Indeed, for these flows, a sender needs to receive three duplicate
ACK before starting fast retransmit. Sending ACK with different
receive window do not count.

Even if enabling SACK is strongly recommended these days,
there still are some cases where it has to be disabled.

Not increasing the window seems better than having to
rely on RTO.

After the fix, following packetdrill test gives :

// Initialize connection
    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
   +0 bind(3, ..., ...) = 0
   +0 listen(3, 1) = 0

   +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7>
   +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 8>
   +0 < . 1:1(0) ack 1 win 514

   +0 accept(3, ..., ...) = 4

   +0 < . 1:1001(1000) ack 1 win 514
// Quick ack
   +0 > . 1:1(0) ack 1001 win 264

   +0 < . 2001:3001(1000) ack 1 win 514
// DUPACK : Normally we should not change the window
   +0 > . 1:1(0) ack 1001 win 264

   +0 < . 3001:4001(1000) ack 1 win 514
// DUPACK : Normally we should not change the window
   +0 > . 1:1(0) ack 1001 win 264

   +0 < . 4001:5001(1000) ack 1 win 514
// DUPACK : Normally we should not change the window
    +0 > . 1:1(0) ack 1001 win 264

   +0 < . 1001:2001(1000) ack 1 win 514
// Hole is repaired.
   +0 > . 1:1(0) ack 5001 win 272

Fixes: 4e4f1fc22681 ("tcp: properly increase rcv_ssthresh for ofo packets")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Venkat Venkatsubra <venkat.x.venkatsubra@oracle.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index cc8411c98f28..3e63dc9c3eba 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4597,7 +4597,11 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 	if (tcp_ooo_try_coalesce(sk, tp->ooo_last_skb,
 				 skb, &fragstolen)) {
 coalesce_done:
-		tcp_grow_window(sk, skb);
+		/* For non sack flows, do not grow window to force DUPACK
+		 * and trigger fast retransmit.
+		 */
+		if (tcp_is_sack(tp))
+			tcp_grow_window(sk, skb);
 		kfree_skb_partial(skb, fragstolen);
 		skb = NULL;
 		goto add_sack;
@@ -4681,7 +4685,11 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 		tcp_sack_new_ofo_skb(sk, seq, end_seq);
 end:
 	if (skb) {
-		tcp_grow_window(sk, skb);
+		/* For non sack flows, do not grow window to force DUPACK
+		 * and trigger fast retransmit.
+		 */
+		if (tcp_is_sack(tp))
+			tcp_grow_window(sk, skb);
 		skb_condense(skb);
 		skb_set_owner_r(skb, sk);
 	}
-- 
2.26.2


From 8a93b2bb63c154337f946e9d005483d6fe30a534 Mon Sep 17 00:00:00 2001
From: David Christensen <drc@linux.vnet.ibm.com>
Date: Wed, 17 Jun 2020 11:51:17 -0700
Subject: [PATCH 19/26] tg3: driver sleeps indefinitely when EEH errors exceed
 eeh_max_freezes

[ Upstream commit 3a2656a211caf35e56afc9425e6e518fa52f7fbc ]

The driver function tg3_io_error_detected() calls napi_disable twice,
without an intervening napi_enable, when the number of EEH errors exceeds
eeh_max_freezes, resulting in an indefinite sleep while holding rtnl_lock.

Add check for pcierr_recovery which skips code already executed for the
"Frozen" state.

Signed-off-by: David Christensen <drc@linux.vnet.ibm.com>
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/tg3.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index ca3aa1250dd1..e12ba81288e6 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -18176,8 +18176,8 @@ static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev,
 
 	rtnl_lock();
 
-	/* We probably don't have netdev yet */
-	if (!netdev || !netif_running(netdev))
+	/* Could be second call or maybe we don't have netdev yet */
+	if (!netdev || tp->pcierr_recovery || !netif_running(netdev))
 		goto done;
 
 	/* We needn't recover from permanent error */
-- 
2.26.2


From a6e1eea0f4a4d7f43e53131032308639476f37e4 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Tue, 16 Jun 2020 16:04:00 +0000
Subject: [PATCH 20/26] ip6_gre: fix use-after-free in ip6gre_tunnel_lookup()

[ Upstream commit dafabb6590cb15f300b77c095d50312e2c7c8e0f ]

In the datapath, the ip6gre_tunnel_lookup() is used and it internally uses
fallback tunnel device pointer, which is fb_tunnel_dev.
This pointer variable should be set to NULL when a fb interface is deleted.
But there is no routine to set fb_tunnel_dev pointer to NULL.
So, this pointer will be still used after interface is deleted and
it eventually results in the use-after-free problem.

Test commands:
    ip netns add A
    ip netns add B
    ip link add eth0 type veth peer name eth1
    ip link set eth0 netns A
    ip link set eth1 netns B

    ip netns exec A ip link set lo up
    ip netns exec A ip link set eth0 up
    ip netns exec A ip link add ip6gre1 type ip6gre local fc:0::1 \
	    remote fc:0::2
    ip netns exec A ip -6 a a fc:100::1/64 dev ip6gre1
    ip netns exec A ip link set ip6gre1 up
    ip netns exec A ip -6 a a fc:0::1/64 dev eth0
    ip netns exec A ip link set ip6gre0 up

    ip netns exec B ip link set lo up
    ip netns exec B ip link set eth1 up
    ip netns exec B ip link add ip6gre1 type ip6gre local fc:0::2 \
	    remote fc:0::1
    ip netns exec B ip -6 a a fc:100::2/64 dev ip6gre1
    ip netns exec B ip link set ip6gre1 up
    ip netns exec B ip -6 a a fc:0::2/64 dev eth1
    ip netns exec B ip link set ip6gre0 up
    ip netns exec A ping fc:100::2 -s 60000 &
    ip netns del B

Splat looks like:
[   73.087285][    C1] BUG: KASAN: use-after-free in ip6gre_tunnel_lookup+0x1064/0x13f0 [ip6_gre]
[   73.088361][    C1] Read of size 4 at addr ffff888040559218 by task ping/1429
[   73.089317][    C1]
[   73.089638][    C1] CPU: 1 PID: 1429 Comm: ping Not tainted 5.7.0+ #602
[   73.090531][    C1] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[   73.091725][    C1] Call Trace:
[   73.092160][    C1]  <IRQ>
[   73.092556][    C1]  dump_stack+0x96/0xdb
[   73.093122][    C1]  print_address_description.constprop.6+0x2cc/0x450
[   73.094016][    C1]  ? ip6gre_tunnel_lookup+0x1064/0x13f0 [ip6_gre]
[   73.094894][    C1]  ? ip6gre_tunnel_lookup+0x1064/0x13f0 [ip6_gre]
[   73.095767][    C1]  ? ip6gre_tunnel_lookup+0x1064/0x13f0 [ip6_gre]
[   73.096619][    C1]  kasan_report+0x154/0x190
[   73.097209][    C1]  ? ip6gre_tunnel_lookup+0x1064/0x13f0 [ip6_gre]
[   73.097989][    C1]  ip6gre_tunnel_lookup+0x1064/0x13f0 [ip6_gre]
[   73.098750][    C1]  ? gre_del_protocol+0x60/0x60 [gre]
[   73.099500][    C1]  gre_rcv+0x1c5/0x1450 [ip6_gre]
[   73.100199][    C1]  ? ip6gre_header+0xf00/0xf00 [ip6_gre]
[   73.100985][    C1]  ? rcu_read_lock_sched_held+0xc0/0xc0
[   73.101830][    C1]  ? ip6_input_finish+0x5/0xf0
[   73.102483][    C1]  ip6_protocol_deliver_rcu+0xcbb/0x1510
[   73.103296][    C1]  ip6_input_finish+0x5b/0xf0
[   73.103920][    C1]  ip6_input+0xcd/0x2c0
[   73.104473][    C1]  ? ip6_input_finish+0xf0/0xf0
[   73.105115][    C1]  ? rcu_read_lock_held+0x90/0xa0
[   73.105783][    C1]  ? rcu_read_lock_sched_held+0xc0/0xc0
[   73.106548][    C1]  ipv6_rcv+0x1f1/0x300
[ ... ]

Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Fixes: c12b395a4664 ("gre: Support GRE over IPv6")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 9ec05a1df5e1..04d76f043e18 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -127,6 +127,7 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev,
 			gre_proto == htons(ETH_P_ERSPAN2)) ?
 		       ARPHRD_ETHER : ARPHRD_IP6GRE;
 	int score, cand_score = 4;
+	struct net_device *ndev;
 
 	for_each_ip_tunnel_rcu(t, ign->tunnels_r_l[h0 ^ h1]) {
 		if (!ipv6_addr_equal(local, &t->parms.laddr) ||
@@ -238,9 +239,9 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev,
 	if (t && t->dev->flags & IFF_UP)
 		return t;
 
-	dev = ign->fb_tunnel_dev;
-	if (dev && dev->flags & IFF_UP)
-		return netdev_priv(dev);
+	ndev = READ_ONCE(ign->fb_tunnel_dev);
+	if (ndev && ndev->flags & IFF_UP)
+		return netdev_priv(ndev);
 
 	return NULL;
 }
@@ -413,6 +414,8 @@ static void ip6gre_tunnel_uninit(struct net_device *dev)
 
 	ip6gre_tunnel_unlink_md(ign, t);
 	ip6gre_tunnel_unlink(ign, t);
+	if (ign->fb_tunnel_dev == dev)
+		WRITE_ONCE(ign->fb_tunnel_dev, NULL);
 	dst_cache_reset(&t->dst_cache);
 	dev_put(dev);
 }
-- 
2.26.2


From d8ff3e536477cdf6240531bfe8283baf703f0310 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 19 Jun 2020 11:47:47 -0700
Subject: [PATCH 21/26] net: phy: Check harder for errors in get_phy_id()

[ Upstream commit b2ffc75e2e990b09903f9d15ccd53bc5f3a4217c ]

Commit 02a6efcab675 ("net: phy: allow scanning busses with missing
phys") added a special condition to return -ENODEV in case -ENODEV or
-EIO was returned from the first read of the MII_PHYSID1 register.

In case the MDIO bus data line pull-up is not strong enough, the MDIO
bus controller will not flag this as a read error. This can happen when
a pluggable daughter card is not connected and weak internal pull-ups
are used (since that is the only option, otherwise the pins are
floating).

The second read of MII_PHYSID2 will be correctly flagged an error
though, but now we will return -EIO which will be treated as a hard
error, thus preventing MDIO bus scanning loops to continue succesfully.

Apply the same logic to both register reads, thus allowing the scanning
logic to proceed.

Fixes: 02a6efcab675 ("net: phy: allow scanning busses with missing phys")
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 0907c3d8d94a..dba52a5c378a 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -797,8 +797,10 @@ static int get_phy_id(struct mii_bus *bus, int addr, u32 *phy_id,
 
 	/* Grab the bits from PHYIR2, and put them in the lower half */
 	phy_reg = mdiobus_read(bus, addr, MII_PHYSID2);
-	if (phy_reg < 0)
-		return -EIO;
+	if (phy_reg < 0) {
+		/* returning -ENODEV doesn't stop bus scanning */
+		return (phy_reg == -EIO || phy_reg == -ENODEV) ? -ENODEV : -EIO;
+	}
 
 	*phy_id |= phy_reg;
 
-- 
2.26.2


From 5d992636eab88b2686ea14179c6646de13ca7447 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Tue, 16 Jun 2020 16:51:51 +0000
Subject: [PATCH 22/26] ip_tunnel: fix use-after-free in ip_tunnel_lookup()

[ Upstream commit ba61539c6ae57f4146284a5cb4f7b7ed8d42bf45 ]

In the datapath, the ip_tunnel_lookup() is used and it internally uses
fallback tunnel device pointer, which is fb_tunnel_dev.
This pointer variable should be set to NULL when a fb interface is deleted.
But there is no routine to set fb_tunnel_dev pointer to NULL.
So, this pointer will be still used after interface is deleted and
it eventually results in the use-after-free problem.

Test commands:
    ip netns add A
    ip netns add B
    ip link add eth0 type veth peer name eth1
    ip link set eth0 netns A
    ip link set eth1 netns B

    ip netns exec A ip link set lo up
    ip netns exec A ip link set eth0 up
    ip netns exec A ip link add gre1 type gre local 10.0.0.1 \
	    remote 10.0.0.2
    ip netns exec A ip link set gre1 up
    ip netns exec A ip a a 10.0.100.1/24 dev gre1
    ip netns exec A ip a a 10.0.0.1/24 dev eth0

    ip netns exec B ip link set lo up
    ip netns exec B ip link set eth1 up
    ip netns exec B ip link add gre1 type gre local 10.0.0.2 \
	    remote 10.0.0.1
    ip netns exec B ip link set gre1 up
    ip netns exec B ip a a 10.0.100.2/24 dev gre1
    ip netns exec B ip a a 10.0.0.2/24 dev eth1
    ip netns exec A hping3 10.0.100.2 -2 --flood -d 60000 &
    ip netns del B

Splat looks like:
[   77.793450][    C3] ==================================================================
[   77.794702][    C3] BUG: KASAN: use-after-free in ip_tunnel_lookup+0xcc4/0xf30
[   77.795573][    C3] Read of size 4 at addr ffff888060bd9c84 by task hping3/2905
[   77.796398][    C3]
[   77.796664][    C3] CPU: 3 PID: 2905 Comm: hping3 Not tainted 5.8.0-rc1+ #616
[   77.797474][    C3] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[   77.798453][    C3] Call Trace:
[   77.798815][    C3]  <IRQ>
[   77.799142][    C3]  dump_stack+0x9d/0xdb
[   77.799605][    C3]  print_address_description.constprop.7+0x2cc/0x450
[   77.800365][    C3]  ? ip_tunnel_lookup+0xcc4/0xf30
[   77.800908][    C3]  ? ip_tunnel_lookup+0xcc4/0xf30
[   77.801517][    C3]  ? ip_tunnel_lookup+0xcc4/0xf30
[   77.802145][    C3]  kasan_report+0x154/0x190
[   77.802821][    C3]  ? ip_tunnel_lookup+0xcc4/0xf30
[   77.803503][    C3]  ip_tunnel_lookup+0xcc4/0xf30
[   77.804165][    C3]  __ipgre_rcv+0x1ab/0xaa0 [ip_gre]
[   77.804862][    C3]  ? rcu_read_lock_sched_held+0xc0/0xc0
[   77.805621][    C3]  gre_rcv+0x304/0x1910 [ip_gre]
[   77.806293][    C3]  ? lock_acquire+0x1a9/0x870
[   77.806925][    C3]  ? gre_rcv+0xfe/0x354 [gre]
[   77.807559][    C3]  ? erspan_xmit+0x2e60/0x2e60 [ip_gre]
[   77.808305][    C3]  ? rcu_read_lock_sched_held+0xc0/0xc0
[   77.809032][    C3]  ? rcu_read_lock_held+0x90/0xa0
[   77.809713][    C3]  gre_rcv+0x1b8/0x354 [gre]
[ ... ]

Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Fixes: c54419321455 ("GRE: Refactor GRE tunneling code.")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_tunnel.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index cd4b84310d92..a0b4dc54f8a6 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -85,9 +85,10 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 				   __be32 remote, __be32 local,
 				   __be32 key)
 {
-	unsigned int hash;
 	struct ip_tunnel *t, *cand = NULL;
 	struct hlist_head *head;
+	struct net_device *ndev;
+	unsigned int hash;
 
 	hash = ip_tunnel_hash(key, remote);
 	head = &itn->tunnels[hash];
@@ -162,8 +163,9 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 	if (t && t->dev->flags & IFF_UP)
 		return t;
 
-	if (itn->fb_tunnel_dev && itn->fb_tunnel_dev->flags & IFF_UP)
-		return netdev_priv(itn->fb_tunnel_dev);
+	ndev = READ_ONCE(itn->fb_tunnel_dev);
+	if (ndev && ndev->flags & IFF_UP)
+		return netdev_priv(ndev);
 
 	return NULL;
 }
@@ -1245,9 +1247,9 @@ void ip_tunnel_uninit(struct net_device *dev)
 	struct ip_tunnel_net *itn;
 
 	itn = net_generic(net, tunnel->ip_tnl_net_id);
-	/* fb_tunnel_dev will be unregisted in net-exit call. */
-	if (itn->fb_tunnel_dev != dev)
-		ip_tunnel_del(itn, netdev_priv(dev));
+	ip_tunnel_del(itn, netdev_priv(dev));
+	if (itn->fb_tunnel_dev == dev)
+		WRITE_ONCE(itn->fb_tunnel_dev, NULL);
 
 	dst_cache_reset(&tunnel->dst_cache);
 }
-- 
2.26.2


From 41b0b92a21eddfe66c8a683001f3082d6d9f27c2 Mon Sep 17 00:00:00 2001
From: Ilya Ponetayev <i.ponetaev@ndmsystems.com>
Date: Thu, 25 Jun 2020 22:12:07 +0200
Subject: [PATCH 23/26] sch_cake: don't try to reallocate or unshare skb
 unconditionally
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 9208d2863ac689a563b92f2161d8d1e7127d0add ]

cake_handle_diffserv() tries to linearize mac and network header parts of
skb and to make it writable unconditionally. In some cases it leads to full
skb reallocation, which reduces throughput and increases CPU load. Some
measurements of IPv4 forward + NAPT on MIPS router with 580 MHz single-core
CPU was conducted. It appears that on kernel 4.9 skb_try_make_writable()
reallocates skb, if skb was allocated in ethernet driver via so-called
'build skb' method from page cache (it was discovered by strange increase
of kmalloc-2048 slab at first).

Obtain DSCP value via read-only skb_header_pointer() call, and leave
linearization only for DSCP bleaching or ECN CE setting. And, as an
additional optimisation, skip diffserv parsing entirely if it is not needed
by the current configuration.

Fixes: c87b4ecdbe8d ("sch_cake: Make sure we can write the IP header before changing DSCP bits")
Signed-off-by: Ilya Ponetayev <i.ponetaev@ndmsystems.com>
[ fix a few style issues, reflow commit message ]
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_cake.c | 41 ++++++++++++++++++++++++++++++-----------
 1 file changed, 30 insertions(+), 11 deletions(-)

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 2277369feae5..8020d0829f1a 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -1517,30 +1517,49 @@ static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free)
 
 static u8 cake_handle_diffserv(struct sk_buff *skb, u16 wash)
 {
-	int wlen = skb_network_offset(skb);
+	const int offset = skb_network_offset(skb);
+	u16 *buf, buf_;
 	u8 dscp;
 
 	switch (tc_skb_protocol(skb)) {
 	case htons(ETH_P_IP):
-		wlen += sizeof(struct iphdr);
-		if (!pskb_may_pull(skb, wlen) ||
-		    skb_try_make_writable(skb, wlen))
+		buf = skb_header_pointer(skb, offset, sizeof(buf_), &buf_);
+		if (unlikely(!buf))
 			return 0;
 
-		dscp = ipv4_get_dsfield(ip_hdr(skb)) >> 2;
-		if (wash && dscp)
+		/* ToS is in the second byte of iphdr */
+		dscp = ipv4_get_dsfield((struct iphdr *)buf) >> 2;
+
+		if (wash && dscp) {
+			const int wlen = offset + sizeof(struct iphdr);
+
+			if (!pskb_may_pull(skb, wlen) ||
+			    skb_try_make_writable(skb, wlen))
+				return 0;
+
 			ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, 0);
+		}
+
 		return dscp;
 
 	case htons(ETH_P_IPV6):
-		wlen += sizeof(struct ipv6hdr);
-		if (!pskb_may_pull(skb, wlen) ||
-		    skb_try_make_writable(skb, wlen))
+		buf = skb_header_pointer(skb, offset, sizeof(buf_), &buf_);
+		if (unlikely(!buf))
 			return 0;
 
-		dscp = ipv6_get_dsfield(ipv6_hdr(skb)) >> 2;
-		if (wash && dscp)
+		/* Traffic class is in the first and second bytes of ipv6hdr */
+		dscp = ipv6_get_dsfield((struct ipv6hdr *)buf) >> 2;
+
+		if (wash && dscp) {
+			const int wlen = offset + sizeof(struct ipv6hdr);
+
+			if (!pskb_may_pull(skb, wlen) ||
+			    skb_try_make_writable(skb, wlen))
+				return 0;
+
 			ipv6_change_dsfield(ipv6_hdr(skb), INET_ECN_MASK, 0);
+		}
+
 		return dscp;
 
 	case htons(ETH_P_ARP):
-- 
2.26.2


From 53d13becbdbcda527da2904456b0979bbdf51f3f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
Date: Thu, 25 Jun 2020 22:12:08 +0200
Subject: [PATCH 24/26] sch_cake: don't call diffserv parsing code when it is
 not needed
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 8c95eca0bb8c4bd2231a0d581f1ad0d50c90488c ]

As a further optimisation of the diffserv parsing codepath, we can skip it
entirely if CAKE is configured to neither use diffserv-based
classification, nor to zero out the diffserv bits.

Fixes: c87b4ecdbe8d ("sch_cake: Make sure we can write the IP header before changing DSCP bits")
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_cake.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 8020d0829f1a..e1b93ff79ab5 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -1515,7 +1515,7 @@ static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free)
 	return idx + (tin << 16);
 }
 
-static u8 cake_handle_diffserv(struct sk_buff *skb, u16 wash)
+static u8 cake_handle_diffserv(struct sk_buff *skb, bool wash)
 {
 	const int offset = skb_network_offset(skb);
 	u16 *buf, buf_;
@@ -1576,14 +1576,17 @@ static struct cake_tin_data *cake_select_tin(struct Qdisc *sch,
 {
 	struct cake_sched_data *q = qdisc_priv(sch);
 	u32 tin, mark;
+	bool wash;
 	u8 dscp;
 
 	/* Tin selection: Default to diffserv-based selection, allow overriding
-	 * using firewall marks or skb->priority.
+	 * using firewall marks or skb->priority. Call DSCP parsing early if
+	 * wash is enabled, otherwise defer to below to skip unneeded parsing.
 	 */
-	dscp = cake_handle_diffserv(skb,
-				    q->rate_flags & CAKE_FLAG_WASH);
 	mark = (skb->mark & q->fwmark_mask) >> q->fwmark_shft;
+	wash = !!(q->rate_flags & CAKE_FLAG_WASH);
+	if (wash)
+		dscp = cake_handle_diffserv(skb, wash);
 
 	if (q->tin_mode == CAKE_DIFFSERV_BESTEFFORT)
 		tin = 0;
@@ -1597,6 +1600,8 @@ static struct cake_tin_data *cake_select_tin(struct Qdisc *sch,
 		tin = q->tin_order[TC_H_MIN(skb->priority) - 1];
 
 	else {
+		if (!wash)
+			dscp = cake_handle_diffserv(skb, wash);
 		tin = q->tin_index[dscp];
 
 		if (unlikely(tin >= q->tin_cnt))
-- 
2.26.2


From fcdc2207aeea7a445caf97f9ccea3488fb897144 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
Date: Thu, 25 Jun 2020 22:12:09 +0200
Subject: [PATCH 25/26] sch_cake: fix a few style nits
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 3f608f0c41360b11b04c763f348b712f651c8bac ]

I spotted a few nits when comparing the in-tree version of sch_cake with
the out-of-tree one: A redundant error variable declaration shadowing an
outer declaration, and an indentation alignment issue. Fix both of these.

Fixes: 046f6fd5daef ("sched: Add Common Applications Kept Enhanced (cake) qdisc")
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_cake.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index e1b93ff79ab5..5d605bab9afc 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -2703,7 +2703,7 @@ static int cake_init(struct Qdisc *sch, struct nlattr *opt,
 	qdisc_watchdog_init(&q->watchdog, sch);
 
 	if (opt) {
-		int err = cake_change(sch, opt, extack);
+		err = cake_change(sch, opt, extack);
 
 		if (err)
 			return err;
@@ -3020,7 +3020,7 @@ static int cake_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 			PUT_STAT_S32(BLUE_TIMER_US,
 				     ktime_to_us(
 					     ktime_sub(now,
-						     flow->cvars.blue_timer)));
+						       flow->cvars.blue_timer)));
 		}
 		if (flow->cvars.dropping) {
 			PUT_STAT_S32(DROP_NEXT_US,
-- 
2.26.2


From 2bb91098e417ccb7197d5b0bf5169e205c127221 Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Wed, 24 Jun 2020 12:42:02 -0400
Subject: [PATCH 26/26] tcp_cubic: fix spurious HYSTART_DELAY exit upon drop in
 min RTT

[ Upstream commit b344579ca8478598937215f7005d6c7b84d28aee ]

Mirja Kuehlewind reported a bug in Linux TCP CUBIC Hystart, where
Hystart HYSTART_DELAY mechanism can exit Slow Start spuriously on an
ACK when the minimum rtt of a connection goes down. From inspection it
is clear from the existing code that this could happen in an example
like the following:

o The first 8 RTT samples in a round trip are 150ms, resulting in a
  curr_rtt of 150ms and a delay_min of 150ms.

o The 9th RTT sample is 100ms. The curr_rtt does not change after the
  first 8 samples, so curr_rtt remains 150ms. But delay_min can be
  lowered at any time, so delay_min falls to 100ms. The code executes
  the HYSTART_DELAY comparison between curr_rtt of 150ms and delay_min
  of 100ms, and the curr_rtt is declared far enough above delay_min to
  force a (spurious) exit of Slow start.

The fix here is simple: allow every RTT sample in a round trip to
lower the curr_rtt.

Fixes: ae27e98a5152 ("[TCP] CUBIC v2.3")
Reported-by: Mirja Kuehlewind <mirja.kuehlewind@ericsson.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_cubic.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 1b3d032a4df2..ee6c38a73325 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -404,6 +404,8 @@ static void hystart_update(struct sock *sk, u32 delay)
 
 	if (hystart_detect & HYSTART_DELAY) {
 		/* obtain the minimum delay of more than sampling packets */
+		if (ca->curr_rtt > delay)
+			ca->curr_rtt = delay;
 		if (ca->sample_cnt < HYSTART_MIN_SAMPLES) {
 			if (ca->curr_rtt == 0 || ca->curr_rtt > delay)
 				ca->curr_rtt = delay;
-- 
2.26.2


[-- Attachment #3: net_57.mbox --]
[-- Type: Application/Octet-Stream, Size: 130596 bytes --]

From 126ab0e22b135a8c2f2b0e455f86bf208337e4df Mon Sep 17 00:00:00 2001
From: Claudiu Manoil <claudiu.manoil@nxp.com>
Date: Fri, 26 Jun 2020 19:17:29 +0300
Subject: [PATCH 01/49] enetc: Fix tx rings bitmap iteration range, irq
 handling

[ Upstream commit 0574e2000fc3103cbc69ba82ec1175ce171fdf5e ]

The rings bitmap of an interrupt vector encodes
which of the device's rings were assigned to that
interrupt vector.
Hence the iteration range of the tx rings bitmap
(for_each_set_bit()) should be the total number of
Tx rings of that netdevice instead of the number of
rings assigned to the interrupt vector.
Since there are 2 cores, and one interrupt vector for
each core, the number of rings asigned to an interrupt
vector is half the number of available rings.
The impact of this error is that the upper half of the
tx rings could still generate interrupts during napi
polling.

Fixes: d4fd0404c1c9 ("enetc: Introduce basic PF and VF ENETC ethernet drivers")
Signed-off-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/enetc/enetc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index ccf2611f4a20..4486a0db8ef0 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -266,7 +266,7 @@ static irqreturn_t enetc_msix(int irq, void *data)
 	/* disable interrupts */
 	enetc_wr_reg(v->rbier, 0);
 
-	for_each_set_bit(i, &v->tx_rings_map, v->count_tx_rings)
+	for_each_set_bit(i, &v->tx_rings_map, ENETC_MAX_NUM_TXQS)
 		enetc_wr_reg(v->tbier_base + ENETC_BDR_OFF(i), 0);
 
 	napi_schedule_irqoff(&v->napi);
@@ -302,7 +302,7 @@ static int enetc_poll(struct napi_struct *napi, int budget)
 	/* enable interrupts */
 	enetc_wr_reg(v->rbier, ENETC_RBIER_RXTIE);
 
-	for_each_set_bit(i, &v->tx_rings_map, v->count_tx_rings)
+	for_each_set_bit(i, &v->tx_rings_map, ENETC_MAX_NUM_TXQS)
 		enetc_wr_reg(v->tbier_base + ENETC_BDR_OFF(i),
 			     ENETC_TBIER_TXTIE);
 
-- 
2.26.2


From b8f6c088aca044a0834b98a876efc8d84cd44c5b Mon Sep 17 00:00:00 2001
From: Gaurav Singh <gaurav1086@gmail.com>
Date: Sun, 21 Jun 2020 11:30:17 -0400
Subject: [PATCH 02/49] ethtool: Fix check in ethtool_rx_flow_rule_create

[ Upstream commit 21a739c64d3e9871186483a0cc3e7b52638c3d59 ]

Fix check in ethtool_rx_flow_rule_create

Fixes: eca4205f9ec3 ("ethtool: add ethtool_rx_flow_spec to flow_rule structure translator")
Signed-off-by: Gaurav Singh <gaurav1086@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ethtool/ioctl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 89d0b1827aaf..d3eeeb26396c 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -2957,7 +2957,7 @@ ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input)
 			       sizeof(match->mask.ipv6.dst));
 		}
 		if (memcmp(v6_m_spec->ip6src, &zero_addr, sizeof(zero_addr)) ||
-		    memcmp(v6_m_spec->ip6src, &zero_addr, sizeof(zero_addr))) {
+		    memcmp(v6_m_spec->ip6dst, &zero_addr, sizeof(zero_addr))) {
 			match->dissector.used_keys |=
 				BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS);
 			match->dissector.offset[FLOW_DISSECTOR_KEY_IPV6_ADDRS] =
-- 
2.26.2


From 78c95c5f3be137dc10d0e4691c397bae8e602687 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Thu, 18 Jun 2020 12:13:22 +0200
Subject: [PATCH 03/49] geneve: allow changing DF behavior after creation

[ Upstream commit 56c09de347e40804fc8dad155272fb9609e0a97b ]

Currently, trying to change the DF parameter of a geneve device does
nothing:

    # ip -d link show geneve1
    14: geneve1: <snip>
        link/ether <snip>
        geneve id 1 remote 10.0.0.1 ttl auto df set dstport 6081 <snip>
    # ip link set geneve1 type geneve id 1 df unset
    # ip -d link show geneve1
    14: geneve1: <snip>
        link/ether <snip>
        geneve id 1 remote 10.0.0.1 ttl auto df set dstport 6081 <snip>

We just need to update the value in geneve_changelink.

Fixes: a025fb5f49ad ("geneve: Allow configuration of DF behaviour")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 75266580b586..4661ef865807 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1649,6 +1649,7 @@ static int geneve_changelink(struct net_device *dev, struct nlattr *tb[],
 	geneve->collect_md = metadata;
 	geneve->use_udp6_rx_checksums = use_udp6_rx_checksums;
 	geneve->ttl_inherit = ttl_inherit;
+	geneve->df = df;
 	geneve_unquiesce(geneve, gs4, gs6);
 
 	return 0;
-- 
2.26.2


From 5c52c2337eb336b7de9faef64d05bd0c65e6178f Mon Sep 17 00:00:00 2001
From: Thomas Falcon <tlfalcon@linux.ibm.com>
Date: Thu, 18 Jun 2020 10:43:46 -0500
Subject: [PATCH 04/49] ibmveth: Fix max MTU limit

[ Upstream commit 5948378b26d89f8aa5eac37629dbd0616ce8d7a7 ]

The max MTU limit defined for ibmveth is not accounting for
virtual ethernet buffer overhead, which is twenty-two additional
bytes set aside for the ethernet header and eight additional bytes
of an opaque handle reserved for use by the hypervisor. Update the
max MTU to reflect this overhead.

Fixes: d894be57ca92 ("ethernet: use net core MTU range checking in more drivers")
Fixes: 110447f8269a ("ethernet: fix min/max MTU typos")
Signed-off-by: Thomas Falcon <tlfalcon@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ibm/ibmveth.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index 96d36ae5049e..c5c732601e35 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -1715,7 +1715,7 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	}
 
 	netdev->min_mtu = IBMVETH_MIN_MTU;
-	netdev->max_mtu = ETH_MAX_MTU;
+	netdev->max_mtu = ETH_MAX_MTU - IBMVETH_BUFF_OH;
 
 	memcpy(netdev->dev_addr, mac_addr_p, ETH_ALEN);
 
-- 
2.26.2


From 86ad08bea485c70a5e0ca129c5693d93d80c0ad5 Mon Sep 17 00:00:00 2001
From: Wang Hai <wanghai38@huawei.com>
Date: Thu, 11 Jun 2020 15:57:50 +0800
Subject: [PATCH 05/49] mld: fix memory leak in ipv6_mc_destroy_dev()

[ Upstream commit ea2fce88d2fd678ed9d45354ff49b73f1d5615dd ]

Commit a84d01647989 ("mld: fix memory leak in mld_del_delrec()") fixed
the memory leak of MLD, but missing the ipv6_mc_destroy_dev() path, in
which mca_sources are leaked after ma_put().

Using ip6_mc_clear_src() to take care of the missing free.

BUG: memory leak
unreferenced object 0xffff8881113d3180 (size 64):
  comm "syz-executor071", pid 389, jiffies 4294887985 (age 17.943s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 ff 02 00 00 00 00 00 00  ................
    00 00 00 00 00 00 00 01 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<000000002cbc483c>] kmalloc include/linux/slab.h:555 [inline]
    [<000000002cbc483c>] kzalloc include/linux/slab.h:669 [inline]
    [<000000002cbc483c>] ip6_mc_add1_src net/ipv6/mcast.c:2237 [inline]
    [<000000002cbc483c>] ip6_mc_add_src+0x7f5/0xbb0 net/ipv6/mcast.c:2357
    [<0000000058b8b1ff>] ip6_mc_source+0xe0c/0x1530 net/ipv6/mcast.c:449
    [<000000000bfc4fb5>] do_ipv6_setsockopt.isra.12+0x1b2c/0x3b30 net/ipv6/ipv6_sockglue.c:754
    [<00000000e4e7a722>] ipv6_setsockopt+0xda/0x150 net/ipv6/ipv6_sockglue.c:950
    [<0000000029260d9a>] rawv6_setsockopt+0x45/0x100 net/ipv6/raw.c:1081
    [<000000005c1b46f9>] __sys_setsockopt+0x131/0x210 net/socket.c:2132
    [<000000008491f7db>] __do_sys_setsockopt net/socket.c:2148 [inline]
    [<000000008491f7db>] __se_sys_setsockopt net/socket.c:2145 [inline]
    [<000000008491f7db>] __x64_sys_setsockopt+0xba/0x150 net/socket.c:2145
    [<00000000c7bc11c5>] do_syscall_64+0xa1/0x530 arch/x86/entry/common.c:295
    [<000000005fb7a3f3>] entry_SYSCALL_64_after_hwframe+0x49/0xb3

Fixes: 1666d49e1d41 ("mld: do not remove mld souce list info when set link down")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Wang Hai <wanghai38@huawei.com>
Acked-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/mcast.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index eaa4c2cc2fbb..c875c9b6edbe 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -2618,6 +2618,7 @@ void ipv6_mc_destroy_dev(struct inet6_dev *idev)
 		idev->mc_list = i->next;
 
 		write_unlock_bh(&idev->lock);
+		ip6_mc_clear_src(i);
 		ma_put(i);
 		write_lock_bh(&idev->lock);
 	}
-- 
2.26.2


From 93a306ca0d241059bf1f93de5546d6062c9d5b8d Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Sun, 21 Jun 2020 11:29:17 +0300
Subject: [PATCH 06/49] mlxsw: spectrum: Do not rely on machine endianness

[ Upstream commit f3fe412b0a634286a6a3753c3f9ff201e6bec716 ]

The second commit cited below performed a cast of 'u32 buffsize' to
'(u16 *)' when calling mlxsw_sp_port_headroom_8x_adjust():

mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, (u16 *) &buffsize);

Colin noted that this will behave differently on big endian
architectures compared to little endian architectures.

Fix this by following Colin's suggestion and have the function accept
and return 'u32' instead of passing the current size by reference.

Fixes: da382875c616 ("mlxsw: spectrum: Extend to support Spectrum-3 ASIC")
Fixes: 60833d54d56c ("mlxsw: spectrum: Adjust headroom buffers for 8x ports")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Colin Ian King <colin.king@canonical.com>
Suggested-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c         | 4 ++--
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h         | 8 +++-----
 drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c | 2 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c    | 2 +-
 4 files changed, 7 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 3e4199246a18..d9a2267aeaea 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -990,10 +990,10 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu,
 
 		lossy = !(pfc || pause_en);
 		thres_cells = mlxsw_sp_pg_buf_threshold_get(mlxsw_sp, mtu);
-		mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, &thres_cells);
+		thres_cells = mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, thres_cells);
 		delay_cells = mlxsw_sp_pg_buf_delay_get(mlxsw_sp, mtu, delay,
 							pfc, pause_en);
-		mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, &delay_cells);
+		delay_cells = mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, delay_cells);
 		total_cells = thres_cells + delay_cells;
 
 		taken_headroom_cells += total_cells;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index e28ecb84b816..6b2e4e730b18 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -395,17 +395,15 @@ mlxsw_sp_port_vlan_find_by_vid(const struct mlxsw_sp_port *mlxsw_sp_port,
 	return NULL;
 }
 
-static inline void
+static inline u32
 mlxsw_sp_port_headroom_8x_adjust(const struct mlxsw_sp_port *mlxsw_sp_port,
-				 u16 *p_size)
+				 u32 size_cells)
 {
 	/* Ports with eight lanes use two headroom buffers between which the
 	 * configured headroom size is split. Therefore, multiply the calculated
 	 * headroom size by two.
 	 */
-	if (mlxsw_sp_port->mapping.width != 8)
-		return;
-	*p_size *= 2;
+	return mlxsw_sp_port->mapping.width == 8 ? 2 * size_cells : size_cells;
 }
 
 enum mlxsw_sp_flood_type {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
index 19bf0768ed78..2fb2cbd4f229 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
@@ -312,7 +312,7 @@ static int mlxsw_sp_port_pb_init(struct mlxsw_sp_port *mlxsw_sp_port)
 
 		if (i == MLXSW_SP_PB_UNUSED)
 			continue;
-		mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, &size);
+		size = mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, size);
 		mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl, i, size);
 	}
 	mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
index 7c5032f9c8ff..76242c70d41a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
@@ -776,7 +776,7 @@ mlxsw_sp_span_port_buffsize_update(struct mlxsw_sp_port *mlxsw_sp_port, u16 mtu)
 		speed = 0;
 
 	buffsize = mlxsw_sp_span_buffsize_get(mlxsw_sp, speed, mtu);
-	mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, (u16 *) &buffsize);
+	buffsize = mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, buffsize);
 	mlxsw_reg_sbib_pack(sbib_pl, mlxsw_sp_port->local_port, buffsize);
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl);
 }
-- 
2.26.2


From 041b99a4237289deaf5f1140d322e2ab15326aac Mon Sep 17 00:00:00 2001
From: Sven Auhagen <sven.auhagen@voleatech.de>
Date: Sun, 14 Jun 2020 09:19:17 +0200
Subject: [PATCH 07/49] mvpp2: ethtool rxtx stats fix

[ Upstream commit cc970925feb9a38c2f0d34305518e00a3084ce85 ]

The ethtool rx and tx queue statistics are reporting wrong values.
Fix reading out the correct ones.

Signed-off-by: Sven Auhagen <sven.auhagen@voleatech.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index b7b553602ea9..24f4d8e0da98 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -1544,7 +1544,7 @@ static void mvpp2_read_stats(struct mvpp2_port *port)
 	for (q = 0; q < port->ntxqs; q++)
 		for (i = 0; i < ARRAY_SIZE(mvpp2_ethtool_txq_regs); i++)
 			*pstats++ += mvpp2_read_index(port->priv,
-						      MVPP22_CTRS_TX_CTR(port->id, i),
+						      MVPP22_CTRS_TX_CTR(port->id, q),
 						      mvpp2_ethtool_txq_regs[i].offset);
 
 	/* Rxqs are numbered from 0 from the user standpoint, but not from the
@@ -1553,7 +1553,7 @@ static void mvpp2_read_stats(struct mvpp2_port *port)
 	for (q = 0; q < port->nrxqs; q++)
 		for (i = 0; i < ARRAY_SIZE(mvpp2_ethtool_rxq_regs); i++)
 			*pstats++ += mvpp2_read_index(port->priv,
-						      port->first_rxq + i,
+						      port->first_rxq + q,
 						      mvpp2_ethtool_rxq_regs[i].offset);
 }
 
-- 
2.26.2


From 6ed9408e4082c775ea74ca70c7ced6d506b8cb24 Mon Sep 17 00:00:00 2001
From: Thomas Martitz <t.martitz@avm.de>
Date: Thu, 25 Jun 2020 14:26:03 +0200
Subject: [PATCH 08/49] net: bridge: enfore alignment for ethernet address

[ Upstream commit db7202dec92e6caa2706c21d6fc359af318bde2e ]

The eth_addr member is passed to ether_addr functions that require
2-byte alignment, therefore the member must be properly aligned
to avoid unaligned accesses.

The problem is in place since the initial merge of multicast to unicast:
commit 6db6f0eae6052b70885562e1733896647ec1d807 bridge: multicast to unicast

Fixes: 6db6f0eae605 ("bridge: multicast to unicast")
Cc: Roopa Prabhu <roopa@cumulusnetworks.com>
Cc: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Felix Fietkau <nbd@nbd.name>
Cc: stable@vger.kernel.org
Signed-off-by: Thomas Martitz <t.martitz@avm.de>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_private.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 1f97703a52ff..18430f79ac37 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -217,8 +217,8 @@ struct net_bridge_port_group {
 	struct rcu_head			rcu;
 	struct timer_list		timer;
 	struct br_ip			addr;
+	unsigned char			eth_addr[ETH_ALEN] __aligned(2);
 	unsigned char			flags;
-	unsigned char			eth_addr[ETH_ALEN];
 };
 
 struct net_bridge_mdb_entry {
-- 
2.26.2


From 66b6fa1c899364704791132cd13890da88785f67 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Tue, 16 Jun 2020 15:52:05 +0000
Subject: [PATCH 09/49] net: core: reduce recursion limit value

[ Upstream commit fb7861d14c8d7edac65b2fcb6e8031cb138457b2 ]

In the current code, ->ndo_start_xmit() can be executed recursively only
10 times because of stack memory.
But, in the case of the vxlan, 10 recursion limit value results in
a stack overflow.
In the current code, the nested interface is limited by 8 depth.
There is no critical reason that the recursion limitation value should
be 10.
So, it would be good to be the same value with the limitation value of
nesting interface depth.

Test commands:
    ip link add vxlan10 type vxlan vni 10 dstport 4789 srcport 4789 4789
    ip link set vxlan10 up
    ip a a 192.168.10.1/24 dev vxlan10
    ip n a 192.168.10.2 dev vxlan10 lladdr fc:22:33:44:55:66 nud permanent

    for i in {9..0}
    do
        let A=$i+1
	ip link add vxlan$i type vxlan vni $i dstport 4789 srcport 4789 4789
	ip link set vxlan$i up
	ip a a 192.168.$i.1/24 dev vxlan$i
	ip n a 192.168.$i.2 dev vxlan$i lladdr fc:22:33:44:55:66 nud permanent
	bridge fdb add fc:22:33:44:55:66 dev vxlan$A dst 192.168.$i.2 self
    done
    hping3 192.168.10.2 -2 -d 60000

Splat looks like:
[  103.814237][ T1127] =============================================================================
[  103.871955][ T1127] BUG kmalloc-2k (Tainted: G    B            ): Padding overwritten. 0x00000000897a2e4f-0x000
[  103.873187][ T1127] -----------------------------------------------------------------------------
[  103.873187][ T1127]
[  103.874252][ T1127] INFO: Slab 0x000000005cccc724 objects=5 used=5 fp=0x0000000000000000 flags=0x10000000001020
[  103.881323][ T1127] CPU: 3 PID: 1127 Comm: hping3 Tainted: G    B             5.7.0+ #575
[  103.882131][ T1127] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[  103.883006][ T1127] Call Trace:
[  103.883324][ T1127]  dump_stack+0x96/0xdb
[  103.883716][ T1127]  slab_err+0xad/0xd0
[  103.884106][ T1127]  ? _raw_spin_unlock+0x1f/0x30
[  103.884620][ T1127]  ? get_partial_node.isra.78+0x140/0x360
[  103.885214][ T1127]  slab_pad_check.part.53+0xf7/0x160
[  103.885769][ T1127]  ? pskb_expand_head+0x110/0xe10
[  103.886316][ T1127]  check_slab+0x97/0xb0
[  103.886763][ T1127]  alloc_debug_processing+0x84/0x1a0
[  103.887308][ T1127]  ___slab_alloc+0x5a5/0x630
[  103.887765][ T1127]  ? pskb_expand_head+0x110/0xe10
[  103.888265][ T1127]  ? lock_downgrade+0x730/0x730
[  103.888762][ T1127]  ? pskb_expand_head+0x110/0xe10
[  103.889244][ T1127]  ? __slab_alloc+0x3e/0x80
[  103.889675][ T1127]  __slab_alloc+0x3e/0x80
[  103.890108][ T1127]  __kmalloc_node_track_caller+0xc7/0x420
[ ... ]

Fixes: 11a766ce915f ("net: Increase xmit RECURSION_LIMIT to 10.")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 130a668049ab..36c7ad24d54d 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3125,7 +3125,7 @@ static inline int dev_recursion_level(void)
 	return this_cpu_read(softnet_data.xmit.recursion);
 }
 
-#define XMIT_RECURSION_LIMIT	10
+#define XMIT_RECURSION_LIMIT	8
 static inline bool dev_xmit_recursion(void)
 {
 	return unlikely(__this_cpu_read(softnet_data.xmit.recursion) >
-- 
2.26.2


From bd40c98de9aedd93078a35154ca9fe9b61aa3508 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Mon, 22 Jun 2020 23:26:04 +0300
Subject: [PATCH 10/49] net: Do not clear the sock TX queue in sk_set_socket()

[ Upstream commit 41b14fb8724d5a4b382a63cb4a1a61880347ccb8 ]

Clearing the sock TX queue in sk_set_socket() might cause unexpected
out-of-order transmit when called from sock_orphan(), as outstanding
packets can pick a different TX queue and bypass the ones already queued.

This is undesired in general. More specifically, it breaks the in-order
scheduling property guarantee for device-offloaded TLS sockets.

Remove the call to sk_tx_queue_clear() in sk_set_socket(), and add it
explicitly only where needed.

Fixes: e022f0b4a03f ("net: Introduce sk_tx_queue_mapping")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h | 1 -
 net/core/sock.c    | 2 ++
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index 3e8c6d4b4b59..46423e86dba5 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1846,7 +1846,6 @@ static inline int sk_rx_queue_get(const struct sock *sk)
 
 static inline void sk_set_socket(struct sock *sk, struct socket *sock)
 {
-	sk_tx_queue_clear(sk);
 	sk->sk_socket = sock;
 }
 
diff --git a/net/core/sock.c b/net/core/sock.c
index b714162213ae..da244f4d0036 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1678,6 +1678,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
 		cgroup_sk_alloc(&sk->sk_cgrp_data);
 		sock_update_classid(&sk->sk_cgrp_data);
 		sock_update_netprioidx(&sk->sk_cgrp_data);
+		sk_tx_queue_clear(sk);
 	}
 
 	return sk;
@@ -1901,6 +1902,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		 */
 		sk_refcnt_debug_inc(newsk);
 		sk_set_socket(newsk, NULL);
+		sk_tx_queue_clear(newsk);
 		RCU_INIT_POINTER(newsk->sk_wq, NULL);
 
 		if (newsk->sk_prot->sockets_allocated)
-- 
2.26.2


From 76fe726b82721c99163148db677adb4ff18fd0a3 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <alobakin@pm.me>
Date: Tue, 23 Jun 2020 10:43:48 +0000
Subject: [PATCH 11/49] net: ethtool: add missing string for
 NETIF_F_GSO_TUNNEL_REMCSUM

[ Upstream commit b4730ae6a443afe611afb4fb651c885c51003c15 ]

Commit e585f2363637 ("udp: Changes to udp_offload to support remote
checksum offload") added new GSO type and a corresponding netdev
feature, but missed Ethtool's 'netdev_features_strings' table.
Give it a name so it will be exposed to userspace and become available
for manual configuration.

v3:
 - decouple from "netdev_features_strings[] cleanup" series;
 - no functional changes.

v2:
 - don't split the "Fixes:" tag across lines;
 - no functional changes.

Fixes: e585f2363637 ("udp: Changes to udp_offload to support remote checksum offload")
Signed-off-by: Alexander Lobakin <alobakin@pm.me>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ethtool/common.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index 423e640e3876..7f7fff88c5d3 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -40,6 +40,7 @@ const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = {
 	[NETIF_F_GSO_UDP_TUNNEL_BIT] =	 "tx-udp_tnl-segmentation",
 	[NETIF_F_GSO_UDP_TUNNEL_CSUM_BIT] = "tx-udp_tnl-csum-segmentation",
 	[NETIF_F_GSO_PARTIAL_BIT] =	 "tx-gso-partial",
+	[NETIF_F_GSO_TUNNEL_REMCSUM_BIT] = "tx-tunnel-remcsum-segmentation",
 	[NETIF_F_GSO_SCTP_BIT] =	 "tx-sctp-segmentation",
 	[NETIF_F_GSO_ESP_BIT] =		 "tx-esp-segmentation",
 	[NETIF_F_GSO_UDP_L4_BIT] =	 "tx-udp-segmentation",
-- 
2.26.2


From 206f8d6ad015122daf3169cd1d55b053efaed40c Mon Sep 17 00:00:00 2001
From: Yang Yingliang <yangyingliang@huawei.com>
Date: Tue, 16 Jun 2020 09:39:21 +0000
Subject: [PATCH 12/49] net: fix memleak in register_netdevice()

[ Upstream commit 814152a89ed52c722ab92e9fbabcac3cb8a39245 ]

I got a memleak report when doing some fuzz test:

unreferenced object 0xffff888112584000 (size 13599):
  comm "ip", pid 3048, jiffies 4294911734 (age 343.491s)
  hex dump (first 32 bytes):
    74 61 70 30 00 00 00 00 00 00 00 00 00 00 00 00  tap0............
    00 ee d9 19 81 88 ff ff 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<000000002f60ba65>] __kmalloc_node+0x309/0x3a0
    [<0000000075b211ec>] kvmalloc_node+0x7f/0xc0
    [<00000000d3a97396>] alloc_netdev_mqs+0x76/0xfc0
    [<00000000609c3655>] __tun_chr_ioctl+0x1456/0x3d70
    [<000000001127ca24>] ksys_ioctl+0xe5/0x130
    [<00000000b7d5e66a>] __x64_sys_ioctl+0x6f/0xb0
    [<00000000e1023498>] do_syscall_64+0x56/0xa0
    [<000000009ec0eb12>] entry_SYSCALL_64_after_hwframe+0x44/0xa9
unreferenced object 0xffff888111845cc0 (size 8):
  comm "ip", pid 3048, jiffies 4294911734 (age 343.491s)
  hex dump (first 8 bytes):
    74 61 70 30 00 88 ff ff                          tap0....
  backtrace:
    [<000000004c159777>] kstrdup+0x35/0x70
    [<00000000d8b496ad>] kstrdup_const+0x3d/0x50
    [<00000000494e884a>] kvasprintf_const+0xf1/0x180
    [<0000000097880a2b>] kobject_set_name_vargs+0x56/0x140
    [<000000008fbdfc7b>] dev_set_name+0xab/0xe0
    [<000000005b99e3b4>] netdev_register_kobject+0xc0/0x390
    [<00000000602704fe>] register_netdevice+0xb61/0x1250
    [<000000002b7ca244>] __tun_chr_ioctl+0x1cd1/0x3d70
    [<000000001127ca24>] ksys_ioctl+0xe5/0x130
    [<00000000b7d5e66a>] __x64_sys_ioctl+0x6f/0xb0
    [<00000000e1023498>] do_syscall_64+0x56/0xa0
    [<000000009ec0eb12>] entry_SYSCALL_64_after_hwframe+0x44/0xa9
unreferenced object 0xffff88811886d800 (size 512):
  comm "ip", pid 3048, jiffies 4294911734 (age 343.491s)
  hex dump (first 32 bytes):
    00 00 00 00 ad 4e ad de ff ff ff ff 00 00 00 00  .....N..........
    ff ff ff ff ff ff ff ff c0 66 3d a3 ff ff ff ff  .........f=.....
  backtrace:
    [<0000000050315800>] device_add+0x61e/0x1950
    [<0000000021008dfb>] netdev_register_kobject+0x17e/0x390
    [<00000000602704fe>] register_netdevice+0xb61/0x1250
    [<000000002b7ca244>] __tun_chr_ioctl+0x1cd1/0x3d70
    [<000000001127ca24>] ksys_ioctl+0xe5/0x130
    [<00000000b7d5e66a>] __x64_sys_ioctl+0x6f/0xb0
    [<00000000e1023498>] do_syscall_64+0x56/0xa0
    [<000000009ec0eb12>] entry_SYSCALL_64_after_hwframe+0x44/0xa9

If call_netdevice_notifiers() failed, then rollback_registered()
calls netdev_unregister_kobject() which holds the kobject. The
reference cannot be put because the netdev won't be add to todo
list, so it will leads a memleak, we need put the reference to
avoid memleak.

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/net/core/dev.c b/net/core/dev.c
index 93a279ab4e97..096b0dfa9589 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -9435,6 +9435,13 @@ int register_netdevice(struct net_device *dev)
 		rcu_barrier();
 
 		dev->reg_state = NETREG_UNREGISTERED;
+		/* We should put the kobject that hold in
+		 * netdev_unregister_kobject(), otherwise
+		 * the net device cannot be freed when
+		 * driver calls free_netdev(), because the
+		 * kobject is being hold.
+		 */
+		kobject_put(&dev->dev.kobj);
 	}
 	/*
 	 *	Prevent userspace races by waiting until the network
-- 
2.26.2


From 9419cca540879280fac1f0729a22046a05eebf12 Mon Sep 17 00:00:00 2001
From: guodeqing <geffrey.guo@huawei.com>
Date: Wed, 17 Jun 2020 10:07:16 +0800
Subject: [PATCH 13/49] net: Fix the arp error in some cases

[ Upstream commit 5eea3a63ff4aba6a26002e657a6d21934b7e2b96 ]

ie.,
$ ifconfig eth0 6.6.6.6 netmask 255.255.255.0

$ ip rule add from 6.6.6.6 table 6666

$ ip route add 9.9.9.9 via 6.6.6.6

$ ping -I 6.6.6.6 9.9.9.9
PING 9.9.9.9 (9.9.9.9) from 6.6.6.6 : 56(84) bytes of data.

3 packets transmitted, 0 received, 100% packet loss, time 2079ms

$ arp
Address     HWtype  HWaddress           Flags Mask            Iface
6.6.6.6             (incomplete)                              eth0

The arp request address is error, this is because fib_table_lookup in
fib_check_nh lookup the destnation 9.9.9.9 nexthop, the scope of
the fib result is RT_SCOPE_LINK,the correct scope is RT_SCOPE_HOST.
Here I add a check of whether this is RT_TABLE_MAIN to solve this problem.

Fixes: 3bfd847203c6 ("net: Use passed in table for nexthop lookups")
Signed-off-by: guodeqing <geffrey.guo@huawei.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_semantics.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 55ca2e521828..871c035be31f 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1109,7 +1109,7 @@ static int fib_check_nh_v4_gw(struct net *net, struct fib_nh *nh, u32 table,
 		if (fl4.flowi4_scope < RT_SCOPE_LINK)
 			fl4.flowi4_scope = RT_SCOPE_LINK;
 
-		if (table)
+		if (table && table != RT_TABLE_MAIN)
 			tbl = fib_get_table(net, table);
 
 		if (tbl)
-- 
2.26.2


From 73bc704db20ef2b4c7321c72755da99b36454f20 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 17 Jun 2020 22:23:25 -0700
Subject: [PATCH 14/49] net: increment xmit_recursion level in
 dev_direct_xmit()

[ Upstream commit 0ad6f6e767ec2f613418cbc7ebe5ec4c35af540c ]

Back in commit f60e5990d9c1 ("ipv6: protect skb->sk accesses
from recursive dereference inside the stack") Hannes added code
so that IPv6 stack would not trust skb->sk for typical cases
where packet goes through 'standard' xmit path (__dev_queue_xmit())

Alas af_packet had a dev_direct_xmit() path that was not
dealing yet with xmit_recursion level.

Also change sk_mc_loop() to dump a stack once only.

Without this patch, syzbot was able to trigger :

[1]
[  153.567378] WARNING: CPU: 7 PID: 11273 at net/core/sock.c:721 sk_mc_loop+0x51/0x70
[  153.567378] Modules linked in: nfnetlink ip6table_raw ip6table_filter iptable_raw iptable_nat nf_nat nf_conntrack nf_defrag_ipv4 nf_defrag_ipv6 iptable_filter macsec macvtap tap macvlan 8021q hsr wireguard libblake2s blake2s_x86_64 libblake2s_generic udp_tunnel ip6_udp_tunnel libchacha20poly1305 poly1305_x86_64 chacha_x86_64 libchacha curve25519_x86_64 libcurve25519_generic netdevsim batman_adv dummy team bridge stp llc w1_therm wire i2c_mux_pca954x i2c_mux cdc_acm ehci_pci ehci_hcd mlx4_en mlx4_ib ib_uverbs ib_core mlx4_core
[  153.567386] CPU: 7 PID: 11273 Comm: b159172088 Not tainted 5.8.0-smp-DEV #273
[  153.567387] RIP: 0010:sk_mc_loop+0x51/0x70
[  153.567388] Code: 66 83 f8 0a 75 24 0f b6 4f 12 b8 01 00 00 00 31 d2 d3 e0 a9 bf ef ff ff 74 07 48 8b 97 f0 02 00 00 0f b6 42 3a 83 e0 01 5d c3 <0f> 0b b8 01 00 00 00 5d c3 0f b6 87 18 03 00 00 5d c0 e8 04 83 e0
[  153.567388] RSP: 0018:ffff95c69bb93990 EFLAGS: 00010212
[  153.567388] RAX: 0000000000000011 RBX: ffff95c6e0ee3e00 RCX: 0000000000000007
[  153.567389] RDX: ffff95c69ae50000 RSI: ffff95c6c30c3000 RDI: ffff95c6c30c3000
[  153.567389] RBP: ffff95c69bb93990 R08: ffff95c69a77f000 R09: 0000000000000008
[  153.567389] R10: 0000000000000040 R11: 00003e0e00026128 R12: ffff95c6c30c3000
[  153.567390] R13: ffff95c6cc4fd500 R14: ffff95c6f84500c0 R15: ffff95c69aa13c00
[  153.567390] FS:  00007fdc3a283700(0000) GS:ffff95c6ff9c0000(0000) knlGS:0000000000000000
[  153.567390] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  153.567391] CR2: 00007ffee758e890 CR3: 0000001f9ba20003 CR4: 00000000001606e0
[  153.567391] Call Trace:
[  153.567391]  ip6_finish_output2+0x34e/0x550
[  153.567391]  __ip6_finish_output+0xe7/0x110
[  153.567391]  ip6_finish_output+0x2d/0xb0
[  153.567392]  ip6_output+0x77/0x120
[  153.567392]  ? __ip6_finish_output+0x110/0x110
[  153.567392]  ip6_local_out+0x3d/0x50
[  153.567392]  ipvlan_queue_xmit+0x56c/0x5e0
[  153.567393]  ? ksize+0x19/0x30
[  153.567393]  ipvlan_start_xmit+0x18/0x50
[  153.567393]  dev_direct_xmit+0xf3/0x1c0
[  153.567393]  packet_direct_xmit+0x69/0xa0
[  153.567394]  packet_sendmsg+0xbf0/0x19b0
[  153.567394]  ? plist_del+0x62/0xb0
[  153.567394]  sock_sendmsg+0x65/0x70
[  153.567394]  sock_write_iter+0x93/0xf0
[  153.567394]  new_sync_write+0x18e/0x1a0
[  153.567395]  __vfs_write+0x29/0x40
[  153.567395]  vfs_write+0xb9/0x1b0
[  153.567395]  ksys_write+0xb1/0xe0
[  153.567395]  __x64_sys_write+0x1a/0x20
[  153.567395]  do_syscall_64+0x43/0x70
[  153.567396]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[  153.567396] RIP: 0033:0x453549
[  153.567396] Code: Bad RIP value.
[  153.567396] RSP: 002b:00007fdc3a282cc8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
[  153.567397] RAX: ffffffffffffffda RBX: 00000000004d32d0 RCX: 0000000000453549
[  153.567397] RDX: 0000000000000020 RSI: 0000000020000300 RDI: 0000000000000003
[  153.567398] RBP: 00000000004d32d8 R08: 0000000000000000 R09: 0000000000000000
[  153.567398] R10: 0000000000000000 R11: 0000000000000246 R12: 00000000004d32dc
[  153.567398] R13: 00007ffee742260f R14: 00007fdc3a282dc0 R15: 00007fdc3a283700
[  153.567399] ---[ end trace c1d5ae2b1059ec62 ]---

f60e5990d9c1 ("ipv6: protect skb->sk accesses from recursive dereference inside the stack")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c  | 2 ++
 net/core/sock.c | 2 +-
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 096b0dfa9589..c9ee5d80d5ea 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4109,10 +4109,12 @@ int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
 
 	local_bh_disable();
 
+	dev_xmit_recursion_inc();
 	HARD_TX_LOCK(dev, txq, smp_processor_id());
 	if (!netif_xmit_frozen_or_drv_stopped(txq))
 		ret = netdev_start_xmit(skb, dev, txq, false);
 	HARD_TX_UNLOCK(dev, txq);
+	dev_xmit_recursion_dec();
 
 	local_bh_enable();
 
diff --git a/net/core/sock.c b/net/core/sock.c
index da244f4d0036..afe4a62adf8f 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -707,7 +707,7 @@ bool sk_mc_loop(struct sock *sk)
 		return inet6_sk(sk)->mc_loop;
 #endif
 	}
-	WARN_ON(1);
+	WARN_ON_ONCE(1);
 	return true;
 }
 EXPORT_SYMBOL(sk_mc_loop);
-- 
2.26.2


From 3b6f565aaa792ee82fae41c01d48826558cacf96 Mon Sep 17 00:00:00 2001
From: Jeremy Kerr <jk@ozlabs.org>
Date: Mon, 15 Jun 2020 10:54:56 +0800
Subject: [PATCH 15/49] net: usb: ax88179_178a: fix packet alignment padding

[ Upstream commit e869e7a17798d85829fa7d4f9bbe1eebd4b2d3f6 ]

Using a AX88179 device (0b95:1790), I see two bytes of appended data on
every RX packet. For example, this 48-byte ping, using 0xff as a
payload byte:

  04:20:22.528472 IP 192.168.1.1 > 192.168.1.2: ICMP echo request, id 2447, seq 1, length 64
	0x0000:  000a cd35 ea50 000a cd35 ea4f 0800 4500
	0x0010:  0054 c116 4000 4001 f63e c0a8 0101 c0a8
	0x0020:  0102 0800 b633 098f 0001 87ea cd5e 0000
	0x0030:  0000 dcf2 0600 0000 0000 ffff ffff ffff
	0x0040:  ffff ffff ffff ffff ffff ffff ffff ffff
	0x0050:  ffff ffff ffff ffff ffff ffff ffff ffff
	0x0060:  ffff 961f

Those last two bytes - 96 1f - aren't part of the original packet.

In the ax88179 RX path, the usbnet rx_fixup function trims a 2-byte
'alignment pseudo header' from the start of the packet, and sets the
length from a per-packet field populated by hardware. It looks like that
length field *includes* the 2-byte header; the current driver assumes
that it's excluded.

This change trims the 2-byte alignment header after we've set the packet
length, so the resulting packet length is correct. While we're moving
the comment around, this also fixes the spelling of 'pseudo'.

Signed-off-by: Jeremy Kerr <jk@ozlabs.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/ax88179_178a.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c
index 93044cf1417a..1fe4cc28d154 100644
--- a/drivers/net/usb/ax88179_178a.c
+++ b/drivers/net/usb/ax88179_178a.c
@@ -1414,10 +1414,10 @@ static int ax88179_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 		}
 
 		if (pkt_cnt == 0) {
-			/* Skip IP alignment psudo header */
-			skb_pull(skb, 2);
 			skb->len = pkt_len;
-			skb_set_tail_pointer(skb, pkt_len);
+			/* Skip IP alignment pseudo header */
+			skb_pull(skb, 2);
+			skb_set_tail_pointer(skb, skb->len);
 			skb->truesize = pkt_len + sizeof(struct sk_buff);
 			ax88179_rx_checksum(skb, pkt_hdr);
 			return 1;
@@ -1426,8 +1426,9 @@ static int ax88179_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 		ax_skb = skb_clone(skb, GFP_ATOMIC);
 		if (ax_skb) {
 			ax_skb->len = pkt_len;
-			ax_skb->data = skb->data + 2;
-			skb_set_tail_pointer(ax_skb, pkt_len);
+			/* Skip IP alignment pseudo header */
+			skb_pull(ax_skb, 2);
+			skb_set_tail_pointer(ax_skb, ax_skb->len);
 			ax_skb->truesize = pkt_len + sizeof(struct sk_buff);
 			ax88179_rx_checksum(ax_skb, pkt_hdr);
 			usbnet_skb_return(dev, ax_skb);
-- 
2.26.2


From 3014f7f8fb3f5553b4696ea7d98e13a6d4adbe1d Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 23 Jun 2020 18:33:15 +0200
Subject: [PATCH 16/49] openvswitch: take into account
 de-fragmentation/gso_size in execute_check_pkt_len

[ Upstream commit 17843655708e1941c0653af3cd61be6948e36f43 ]

ovs connection tracking module performs de-fragmentation on incoming
fragmented traffic. Take info account if traffic has been de-fragmented
in execute_check_pkt_len action otherwise we will perform the wrong
nested action considering the original packet size. This issue typically
occurs if ovs-vswitchd adds a rule in the pipeline that requires connection
tracking (e.g. OVN stateful ACLs) before execute_check_pkt_len action.
Moreover take into account GSO fragment size for GSO packet in
execute_check_pkt_len routine

Fixes: 4d5ec89fc8d14 ("net: openvswitch: Add a new action check_pkt_len")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/actions.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index fc0efd8833c8..2611657f40ca 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -1169,9 +1169,10 @@ static int execute_check_pkt_len(struct datapath *dp, struct sk_buff *skb,
 				 struct sw_flow_key *key,
 				 const struct nlattr *attr, bool last)
 {
+	struct ovs_skb_cb *ovs_cb = OVS_CB(skb);
 	const struct nlattr *actions, *cpl_arg;
+	int len, max_len, rem = nla_len(attr);
 	const struct check_pkt_len_arg *arg;
-	int rem = nla_len(attr);
 	bool clone_flow_key;
 
 	/* The first netlink attribute in 'attr' is always
@@ -1180,7 +1181,11 @@ static int execute_check_pkt_len(struct datapath *dp, struct sk_buff *skb,
 	cpl_arg = nla_data(attr);
 	arg = nla_data(cpl_arg);
 
-	if (skb->len <= arg->pkt_len) {
+	len = ovs_cb->mru ? ovs_cb->mru + skb->mac_len : skb->len;
+	max_len = arg->pkt_len;
+
+	if ((skb_is_gso(skb) && skb_gso_validate_mac_len(skb, max_len)) ||
+	    len <= max_len) {
 		/* Second netlink attribute in 'attr' is always
 		 * 'OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL'.
 		 */
-- 
2.26.2


From 94498311db4bb6d5ee0b88ccf8759f70ebb3f796 Mon Sep 17 00:00:00 2001
From: Aditya Pakki <pakki001@umn.edu>
Date: Fri, 12 Jun 2020 15:27:55 -0500
Subject: [PATCH 17/49] rocker: fix incorrect error handling in dma_rings_init

[ Upstream commit 58d0c864e1a759a15c9df78f50ea5a5c32b3989e ]

In rocker_dma_rings_init, the goto blocks in case of errors
caused by the functions rocker_dma_cmd_ring_waits_alloc() and
rocker_dma_ring_create() are incorrect. The patch fixes the
order consistent with cleanup in rocker_dma_rings_fini().

Signed-off-by: Aditya Pakki <pakki001@umn.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/rocker/rocker_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index 7585cd2270ba..fc99e7118e49 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -647,10 +647,10 @@ static int rocker_dma_rings_init(struct rocker *rocker)
 err_dma_event_ring_bufs_alloc:
 	rocker_dma_ring_destroy(rocker, &rocker->event_ring);
 err_dma_event_ring_create:
+	rocker_dma_cmd_ring_waits_free(rocker);
+err_dma_cmd_ring_waits_alloc:
 	rocker_dma_ring_bufs_free(rocker, &rocker->cmd_ring,
 				  PCI_DMA_BIDIRECTIONAL);
-err_dma_cmd_ring_waits_alloc:
-	rocker_dma_cmd_ring_waits_free(rocker);
 err_dma_cmd_ring_bufs_alloc:
 	rocker_dma_ring_destroy(rocker, &rocker->cmd_ring);
 	return err;
-- 
2.26.2


From 5c2fd77e24866cfd867e812d276f6e14ccc4cefd Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 19 Jun 2020 23:38:16 +0100
Subject: [PATCH 18/49] rxrpc: Fix notification call on completion of discarded
 calls

[ Upstream commit 0041cd5a50442db6e456b145892a0eaf2dff061f ]

When preallocated service calls are being discarded, they're passed to
->discard_new_call() to have the caller clean up any attached higher-layer
preallocated pieces before being marked completed.  However, the act of
marking them completed now invokes the call's notification function - which
causes a problem because that function might assume that the previously
freed pieces of memory are still there.

Fix this by setting a dummy notification function on the socket after
calling ->discard_new_call().

This results in the following kasan message when the kafs module is
removed.

==================================================================
BUG: KASAN: use-after-free in afs_wake_up_async_call+0x6aa/0x770 fs/afs/rxrpc.c:707
Write of size 1 at addr ffff8880946c39e4 by task kworker/u4:1/21

CPU: 0 PID: 21 Comm: kworker/u4:1 Not tainted 5.8.0-rc1-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Workqueue: netns cleanup_net
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x18f/0x20d lib/dump_stack.c:118
 print_address_description.constprop.0.cold+0xd3/0x413 mm/kasan/report.c:383
 __kasan_report mm/kasan/report.c:513 [inline]
 kasan_report.cold+0x1f/0x37 mm/kasan/report.c:530
 afs_wake_up_async_call+0x6aa/0x770 fs/afs/rxrpc.c:707
 rxrpc_notify_socket+0x1db/0x5d0 net/rxrpc/recvmsg.c:40
 __rxrpc_set_call_completion.part.0+0x172/0x410 net/rxrpc/recvmsg.c:76
 __rxrpc_call_completed net/rxrpc/recvmsg.c:112 [inline]
 rxrpc_call_completed+0xca/0xf0 net/rxrpc/recvmsg.c:111
 rxrpc_discard_prealloc+0x781/0xab0 net/rxrpc/call_accept.c:233
 rxrpc_listen+0x147/0x360 net/rxrpc/af_rxrpc.c:245
 afs_close_socket+0x95/0x320 fs/afs/rxrpc.c:110
 afs_net_exit+0x1bc/0x310 fs/afs/main.c:155
 ops_exit_list.isra.0+0xa8/0x150 net/core/net_namespace.c:186
 cleanup_net+0x511/0xa50 net/core/net_namespace.c:603
 process_one_work+0x965/0x1690 kernel/workqueue.c:2269
 worker_thread+0x96/0xe10 kernel/workqueue.c:2415
 kthread+0x3b5/0x4a0 kernel/kthread.c:291
 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:293

Allocated by task 6820:
 save_stack+0x1b/0x40 mm/kasan/common.c:48
 set_track mm/kasan/common.c:56 [inline]
 __kasan_kmalloc mm/kasan/common.c:494 [inline]
 __kasan_kmalloc.constprop.0+0xbf/0xd0 mm/kasan/common.c:467
 kmem_cache_alloc_trace+0x153/0x7d0 mm/slab.c:3551
 kmalloc include/linux/slab.h:555 [inline]
 kzalloc include/linux/slab.h:669 [inline]
 afs_alloc_call+0x55/0x630 fs/afs/rxrpc.c:141
 afs_charge_preallocation+0xe9/0x2d0 fs/afs/rxrpc.c:757
 afs_open_socket+0x292/0x360 fs/afs/rxrpc.c:92
 afs_net_init+0xa6c/0xe30 fs/afs/main.c:125
 ops_init+0xaf/0x420 net/core/net_namespace.c:151
 setup_net+0x2de/0x860 net/core/net_namespace.c:341
 copy_net_ns+0x293/0x590 net/core/net_namespace.c:482
 create_new_namespaces+0x3fb/0xb30 kernel/nsproxy.c:110
 unshare_nsproxy_namespaces+0xbd/0x1f0 kernel/nsproxy.c:231
 ksys_unshare+0x43d/0x8e0 kernel/fork.c:2983
 __do_sys_unshare kernel/fork.c:3051 [inline]
 __se_sys_unshare kernel/fork.c:3049 [inline]
 __x64_sys_unshare+0x2d/0x40 kernel/fork.c:3049
 do_syscall_64+0x60/0xe0 arch/x86/entry/common.c:359
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Freed by task 21:
 save_stack+0x1b/0x40 mm/kasan/common.c:48
 set_track mm/kasan/common.c:56 [inline]
 kasan_set_free_info mm/kasan/common.c:316 [inline]
 __kasan_slab_free+0xf7/0x140 mm/kasan/common.c:455
 __cache_free mm/slab.c:3426 [inline]
 kfree+0x109/0x2b0 mm/slab.c:3757
 afs_put_call+0x585/0xa40 fs/afs/rxrpc.c:190
 rxrpc_discard_prealloc+0x764/0xab0 net/rxrpc/call_accept.c:230
 rxrpc_listen+0x147/0x360 net/rxrpc/af_rxrpc.c:245
 afs_close_socket+0x95/0x320 fs/afs/rxrpc.c:110
 afs_net_exit+0x1bc/0x310 fs/afs/main.c:155
 ops_exit_list.isra.0+0xa8/0x150 net/core/net_namespace.c:186
 cleanup_net+0x511/0xa50 net/core/net_namespace.c:603
 process_one_work+0x965/0x1690 kernel/workqueue.c:2269
 worker_thread+0x96/0xe10 kernel/workqueue.c:2415
 kthread+0x3b5/0x4a0 kernel/kthread.c:291
 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:293

The buggy address belongs to the object at ffff8880946c3800
 which belongs to the cache kmalloc-1k of size 1024
The buggy address is located 484 bytes inside of
 1024-byte region [ffff8880946c3800, ffff8880946c3c00)
The buggy address belongs to the page:
page:ffffea000251b0c0 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0
flags: 0xfffe0000000200(slab)
raw: 00fffe0000000200 ffffea0002546508 ffffea00024fa248 ffff8880aa000c40
raw: 0000000000000000 ffff8880946c3000 0000000100000002 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff8880946c3880: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff8880946c3900: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff8880946c3980: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                                                       ^
 ffff8880946c3a00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff8880946c3a80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
==================================================================

Reported-by: syzbot+d3eccef36ddbd02713e9@syzkaller.appspotmail.com
Fixes: 5ac0d62226a0 ("rxrpc: Fix missing notification")
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/call_accept.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index b7611cc159e5..032ed76c0166 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -22,6 +22,11 @@
 #include <net/ip.h>
 #include "ar-internal.h"
 
+static void rxrpc_dummy_notify(struct sock *sk, struct rxrpc_call *call,
+			       unsigned long user_call_ID)
+{
+}
+
 /*
  * Preallocate a single service call, connection and peer and, if possible,
  * give them a user ID and attach the user's side of the ID to them.
@@ -228,6 +233,8 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx)
 		if (rx->discard_new_call) {
 			_debug("discard %lx", call->user_call_ID);
 			rx->discard_new_call(call, call->user_call_ID);
+			if (call->notify_rx)
+				call->notify_rx = rxrpc_dummy_notify;
 			rxrpc_put_call(call, rxrpc_call_put_kernel);
 		}
 		rxrpc_call_completed(call);
-- 
2.26.2


From b784ed4b2ae828e53a2f57003dd431549d5894b8 Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Wed, 24 Jun 2020 17:34:18 -0300
Subject: [PATCH 19/49] sctp: Don't advertise IPv4 addresses if ipv6only is set
 on the socket

[ Upstream commit 471e39df96b9a4c4ba88a2da9e25a126624d7a9c ]

If a socket is set ipv6only, it will still send IPv4 addresses in the
INIT and INIT_ACK packets. This potentially misleads the peer into using
them, which then would cause association termination.

The fix is to not add IPv4 addresses to ipv6only sockets.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: Corey Minyard <cminyard@mvista.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Tested-by: Corey Minyard <cminyard@mvista.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/constants.h | 8 +++++---
 net/sctp/associola.c         | 5 ++++-
 net/sctp/bind_addr.c         | 1 +
 net/sctp/protocol.c          | 3 ++-
 4 files changed, 12 insertions(+), 5 deletions(-)

diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h
index 15b4d9aec7ff..122d9e2d8dfd 100644
--- a/include/net/sctp/constants.h
+++ b/include/net/sctp/constants.h
@@ -353,11 +353,13 @@ enum {
 	 ipv4_is_anycast_6to4(a))
 
 /* Flags used for the bind address copy functions.  */
-#define SCTP_ADDR6_ALLOWED	0x00000001	/* IPv6 address is allowed by
+#define SCTP_ADDR4_ALLOWED	0x00000001	/* IPv4 address is allowed by
 						   local sock family */
-#define SCTP_ADDR4_PEERSUPP	0x00000002	/* IPv4 address is supported by
+#define SCTP_ADDR6_ALLOWED	0x00000002	/* IPv6 address is allowed by
+						   local sock family */
+#define SCTP_ADDR4_PEERSUPP	0x00000004	/* IPv4 address is supported by
 						   peer */
-#define SCTP_ADDR6_PEERSUPP	0x00000004	/* IPv6 address is supported by
+#define SCTP_ADDR6_PEERSUPP	0x00000008	/* IPv6 address is supported by
 						   peer */
 
 /* Reasons to retransmit. */
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 437079a4883d..732bc9a45190 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -1565,12 +1565,15 @@ void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned int len)
 int sctp_assoc_set_bind_addr_from_ep(struct sctp_association *asoc,
 				     enum sctp_scope scope, gfp_t gfp)
 {
+	struct sock *sk = asoc->base.sk;
 	int flags;
 
 	/* Use scoping rules to determine the subset of addresses from
 	 * the endpoint.
 	 */
-	flags = (PF_INET6 == asoc->base.sk->sk_family) ? SCTP_ADDR6_ALLOWED : 0;
+	flags = (PF_INET6 == sk->sk_family) ? SCTP_ADDR6_ALLOWED : 0;
+	if (!inet_v6_ipv6only(sk))
+		flags |= SCTP_ADDR4_ALLOWED;
 	if (asoc->peer.ipv4_address)
 		flags |= SCTP_ADDR4_PEERSUPP;
 	if (asoc->peer.ipv6_address)
diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c
index 53bc61537f44..701c5a4e441d 100644
--- a/net/sctp/bind_addr.c
+++ b/net/sctp/bind_addr.c
@@ -461,6 +461,7 @@ static int sctp_copy_one_addr(struct net *net, struct sctp_bind_addr *dest,
 		 * well as the remote peer.
 		 */
 		if ((((AF_INET == addr->sa.sa_family) &&
+		      (flags & SCTP_ADDR4_ALLOWED) &&
 		      (flags & SCTP_ADDR4_PEERSUPP))) ||
 		    (((AF_INET6 == addr->sa.sa_family) &&
 		      (flags & SCTP_ADDR6_ALLOWED) &&
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 092d1afdee0d..cde29f3c7fb3 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -148,7 +148,8 @@ int sctp_copy_local_addr_list(struct net *net, struct sctp_bind_addr *bp,
 		 * sock as well as the remote peer.
 		 */
 		if (addr->a.sa.sa_family == AF_INET &&
-		    !(copy_flags & SCTP_ADDR4_PEERSUPP))
+		    (!(copy_flags & SCTP_ADDR4_ALLOWED) ||
+		     !(copy_flags & SCTP_ADDR4_PEERSUPP)))
 			continue;
 		if (addr->a.sa.sa_family == AF_INET6 &&
 		    (!(copy_flags & SCTP_ADDR6_ALLOWED) ||
-- 
2.26.2


From 6553186a42fc09287cc1d318ab050ef8b8c5c58f Mon Sep 17 00:00:00 2001
From: Denis Kirjanov <kda@linux-powerpc.org>
Date: Thu, 25 Jun 2020 14:51:06 +0300
Subject: [PATCH 20/49] tcp: don't ignore ECN CWR on pure ACK

[ Upstream commit 2570284060b48f3f79d8f1a2698792f36c385e9a ]

there is a problem with the CWR flag set in an incoming ACK segment
and it leads to the situation when the ECE flag is latched forever

the following packetdrill script shows what happens:

// Stack receives incoming segments with CE set
+0.1 <[ect0]  . 11001:12001(1000) ack 1001 win 65535
+0.0 <[ce]    . 12001:13001(1000) ack 1001 win 65535
+0.0 <[ect0] P. 13001:14001(1000) ack 1001 win 65535

// Stack repsonds with ECN ECHO
+0.0 >[noecn]  . 1001:1001(0) ack 12001
+0.0 >[noecn] E. 1001:1001(0) ack 13001
+0.0 >[noecn] E. 1001:1001(0) ack 14001

// Write a packet
+0.1 write(3, ..., 1000) = 1000
+0.0 >[ect0] PE. 1001:2001(1000) ack 14001

// Pure ACK received
+0.01 <[noecn] W. 14001:14001(0) ack 2001 win 65535

// Since CWR was sent, this packet should NOT have ECE set

+0.1 write(3, ..., 1000) = 1000
+0.0 >[ect0]  P. 2001:3001(1000) ack 14001
// but Linux will still keep ECE latched here, with packetdrill
// flagging a missing ECE flag, expecting
// >[ect0] PE. 2001:3001(1000) ack 14001
// in the script

In the situation above we will continue to send ECN ECHO packets
and trigger the peer to reduce the congestion window. To avoid that
we can check CWR on pure ACKs received.

v3:
- Add a sequence check to avoid sending an ACK to an ACK

v2:
- Adjusted the comment
- move CWR check before checking for unacknowledged packets

Signed-off-by: Denis Kirjanov <denis.kirjanov@suse.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 29c6fc8c7716..ccab8bc29e2b 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -261,7 +261,8 @@ static void tcp_ecn_accept_cwr(struct sock *sk, const struct sk_buff *skb)
 		 * cwnd may be very low (even just 1 packet), so we should ACK
 		 * immediately.
 		 */
-		inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
+		if (TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq)
+			inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
 	}
 }
 
@@ -3683,6 +3684,15 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 		tcp_in_ack_event(sk, ack_ev_flags);
 	}
 
+	/* This is a deviation from RFC3168 since it states that:
+	 * "When the TCP data sender is ready to set the CWR bit after reducing
+	 * the congestion window, it SHOULD set the CWR bit only on the first
+	 * new data packet that it transmits."
+	 * We accept CWR on pure ACKs to be more robust
+	 * with widely-deployed TCP implementations that do this.
+	 */
+	tcp_ecn_accept_cwr(sk, skb);
+
 	/* We passed data and got it acked, remove any soft error
 	 * log. Something worked...
 	 */
@@ -4780,8 +4790,6 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 	skb_dst_drop(skb);
 	__skb_pull(skb, tcp_hdr(skb)->doff * 4);
 
-	tcp_ecn_accept_cwr(sk, skb);
-
 	tp->rx_opt.dsack = 0;
 
 	/*  Queue data for delivery to the user.
-- 
2.26.2


From 3915b08713dd20bec0076deae3a65a4ad9748738 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 15 Jun 2020 20:37:07 -0700
Subject: [PATCH 21/49] tcp: grow window for OOO packets only for SACK flows

[ Upstream commit 662051215c758ae8545451628816204ed6cd372d ]

Back in 2013, we made a change that broke fast retransmit
for non SACK flows.

Indeed, for these flows, a sender needs to receive three duplicate
ACK before starting fast retransmit. Sending ACK with different
receive window do not count.

Even if enabling SACK is strongly recommended these days,
there still are some cases where it has to be disabled.

Not increasing the window seems better than having to
rely on RTO.

After the fix, following packetdrill test gives :

// Initialize connection
    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
   +0 bind(3, ..., ...) = 0
   +0 listen(3, 1) = 0

   +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7>
   +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 8>
   +0 < . 1:1(0) ack 1 win 514

   +0 accept(3, ..., ...) = 4

   +0 < . 1:1001(1000) ack 1 win 514
// Quick ack
   +0 > . 1:1(0) ack 1001 win 264

   +0 < . 2001:3001(1000) ack 1 win 514
// DUPACK : Normally we should not change the window
   +0 > . 1:1(0) ack 1001 win 264

   +0 < . 3001:4001(1000) ack 1 win 514
// DUPACK : Normally we should not change the window
   +0 > . 1:1(0) ack 1001 win 264

   +0 < . 4001:5001(1000) ack 1 win 514
// DUPACK : Normally we should not change the window
    +0 > . 1:1(0) ack 1001 win 264

   +0 < . 1001:2001(1000) ack 1 win 514
// Hole is repaired.
   +0 > . 1:1(0) ack 5001 win 272

Fixes: 4e4f1fc22681 ("tcp: properly increase rcv_ssthresh for ofo packets")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Venkat Venkatsubra <venkat.x.venkatsubra@oracle.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index ccab8bc29e2b..1fa009999f57 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4603,7 +4603,11 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 	if (tcp_ooo_try_coalesce(sk, tp->ooo_last_skb,
 				 skb, &fragstolen)) {
 coalesce_done:
-		tcp_grow_window(sk, skb);
+		/* For non sack flows, do not grow window to force DUPACK
+		 * and trigger fast retransmit.
+		 */
+		if (tcp_is_sack(tp))
+			tcp_grow_window(sk, skb);
 		kfree_skb_partial(skb, fragstolen);
 		skb = NULL;
 		goto add_sack;
@@ -4687,7 +4691,11 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 		tcp_sack_new_ofo_skb(sk, seq, end_seq);
 end:
 	if (skb) {
-		tcp_grow_window(sk, skb);
+		/* For non sack flows, do not grow window to force DUPACK
+		 * and trigger fast retransmit.
+		 */
+		if (tcp_is_sack(tp))
+			tcp_grow_window(sk, skb);
 		skb_condense(skb);
 		skb_set_owner_r(skb, sk);
 	}
-- 
2.26.2


From 454308e022bd1a882a8b0a7961c23167b2c72268 Mon Sep 17 00:00:00 2001
From: David Christensen <drc@linux.vnet.ibm.com>
Date: Wed, 17 Jun 2020 11:51:17 -0700
Subject: [PATCH 22/49] tg3: driver sleeps indefinitely when EEH errors exceed
 eeh_max_freezes

[ Upstream commit 3a2656a211caf35e56afc9425e6e518fa52f7fbc ]

The driver function tg3_io_error_detected() calls napi_disable twice,
without an intervening napi_enable, when the number of EEH errors exceeds
eeh_max_freezes, resulting in an indefinite sleep while holding rtnl_lock.

Add check for pcierr_recovery which skips code already executed for the
"Frozen" state.

Signed-off-by: David Christensen <drc@linux.vnet.ibm.com>
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/tg3.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index ff98a82b7bc4..d71ce7634ac1 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -18170,8 +18170,8 @@ static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev,
 
 	rtnl_lock();
 
-	/* We probably don't have netdev yet */
-	if (!netdev || !netif_running(netdev))
+	/* Could be second call or maybe we don't have netdev yet */
+	if (!netdev || tp->pcierr_recovery || !netif_running(netdev))
 		goto done;
 
 	/* We needn't recover from permanent error */
-- 
2.26.2


From 1c270062e1fab4f6180f7ff58dd9289a3a5de90e Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Tue, 16 Jun 2020 16:04:00 +0000
Subject: [PATCH 23/49] ip6_gre: fix use-after-free in ip6gre_tunnel_lookup()

[ Upstream commit dafabb6590cb15f300b77c095d50312e2c7c8e0f ]

In the datapath, the ip6gre_tunnel_lookup() is used and it internally uses
fallback tunnel device pointer, which is fb_tunnel_dev.
This pointer variable should be set to NULL when a fb interface is deleted.
But there is no routine to set fb_tunnel_dev pointer to NULL.
So, this pointer will be still used after interface is deleted and
it eventually results in the use-after-free problem.

Test commands:
    ip netns add A
    ip netns add B
    ip link add eth0 type veth peer name eth1
    ip link set eth0 netns A
    ip link set eth1 netns B

    ip netns exec A ip link set lo up
    ip netns exec A ip link set eth0 up
    ip netns exec A ip link add ip6gre1 type ip6gre local fc:0::1 \
	    remote fc:0::2
    ip netns exec A ip -6 a a fc:100::1/64 dev ip6gre1
    ip netns exec A ip link set ip6gre1 up
    ip netns exec A ip -6 a a fc:0::1/64 dev eth0
    ip netns exec A ip link set ip6gre0 up

    ip netns exec B ip link set lo up
    ip netns exec B ip link set eth1 up
    ip netns exec B ip link add ip6gre1 type ip6gre local fc:0::2 \
	    remote fc:0::1
    ip netns exec B ip -6 a a fc:100::2/64 dev ip6gre1
    ip netns exec B ip link set ip6gre1 up
    ip netns exec B ip -6 a a fc:0::2/64 dev eth1
    ip netns exec B ip link set ip6gre0 up
    ip netns exec A ping fc:100::2 -s 60000 &
    ip netns del B

Splat looks like:
[   73.087285][    C1] BUG: KASAN: use-after-free in ip6gre_tunnel_lookup+0x1064/0x13f0 [ip6_gre]
[   73.088361][    C1] Read of size 4 at addr ffff888040559218 by task ping/1429
[   73.089317][    C1]
[   73.089638][    C1] CPU: 1 PID: 1429 Comm: ping Not tainted 5.7.0+ #602
[   73.090531][    C1] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[   73.091725][    C1] Call Trace:
[   73.092160][    C1]  <IRQ>
[   73.092556][    C1]  dump_stack+0x96/0xdb
[   73.093122][    C1]  print_address_description.constprop.6+0x2cc/0x450
[   73.094016][    C1]  ? ip6gre_tunnel_lookup+0x1064/0x13f0 [ip6_gre]
[   73.094894][    C1]  ? ip6gre_tunnel_lookup+0x1064/0x13f0 [ip6_gre]
[   73.095767][    C1]  ? ip6gre_tunnel_lookup+0x1064/0x13f0 [ip6_gre]
[   73.096619][    C1]  kasan_report+0x154/0x190
[   73.097209][    C1]  ? ip6gre_tunnel_lookup+0x1064/0x13f0 [ip6_gre]
[   73.097989][    C1]  ip6gre_tunnel_lookup+0x1064/0x13f0 [ip6_gre]
[   73.098750][    C1]  ? gre_del_protocol+0x60/0x60 [gre]
[   73.099500][    C1]  gre_rcv+0x1c5/0x1450 [ip6_gre]
[   73.100199][    C1]  ? ip6gre_header+0xf00/0xf00 [ip6_gre]
[   73.100985][    C1]  ? rcu_read_lock_sched_held+0xc0/0xc0
[   73.101830][    C1]  ? ip6_input_finish+0x5/0xf0
[   73.102483][    C1]  ip6_protocol_deliver_rcu+0xcbb/0x1510
[   73.103296][    C1]  ip6_input_finish+0x5b/0xf0
[   73.103920][    C1]  ip6_input+0xcd/0x2c0
[   73.104473][    C1]  ? ip6_input_finish+0xf0/0xf0
[   73.105115][    C1]  ? rcu_read_lock_held+0x90/0xa0
[   73.105783][    C1]  ? rcu_read_lock_sched_held+0xc0/0xc0
[   73.106548][    C1]  ipv6_rcv+0x1f1/0x300
[ ... ]

Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Fixes: c12b395a4664 ("gre: Support GRE over IPv6")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 781ca8c07a0d..6532bde82b40 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -127,6 +127,7 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev,
 			gre_proto == htons(ETH_P_ERSPAN2)) ?
 		       ARPHRD_ETHER : ARPHRD_IP6GRE;
 	int score, cand_score = 4;
+	struct net_device *ndev;
 
 	for_each_ip_tunnel_rcu(t, ign->tunnels_r_l[h0 ^ h1]) {
 		if (!ipv6_addr_equal(local, &t->parms.laddr) ||
@@ -238,9 +239,9 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev,
 	if (t && t->dev->flags & IFF_UP)
 		return t;
 
-	dev = ign->fb_tunnel_dev;
-	if (dev && dev->flags & IFF_UP)
-		return netdev_priv(dev);
+	ndev = READ_ONCE(ign->fb_tunnel_dev);
+	if (ndev && ndev->flags & IFF_UP)
+		return netdev_priv(ndev);
 
 	return NULL;
 }
@@ -413,6 +414,8 @@ static void ip6gre_tunnel_uninit(struct net_device *dev)
 
 	ip6gre_tunnel_unlink_md(ign, t);
 	ip6gre_tunnel_unlink(ign, t);
+	if (ign->fb_tunnel_dev == dev)
+		WRITE_ONCE(ign->fb_tunnel_dev, NULL);
 	dst_cache_reset(&t->dst_cache);
 	dev_put(dev);
 }
-- 
2.26.2


From 2c3e0f0a155df9d0a375039bd34e00a7416b5578 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 19 Jun 2020 11:47:47 -0700
Subject: [PATCH 24/49] net: phy: Check harder for errors in get_phy_id()

[ Upstream commit b2ffc75e2e990b09903f9d15ccd53bc5f3a4217c ]

Commit 02a6efcab675 ("net: phy: allow scanning busses with missing
phys") added a special condition to return -ENODEV in case -ENODEV or
-EIO was returned from the first read of the MII_PHYSID1 register.

In case the MDIO bus data line pull-up is not strong enough, the MDIO
bus controller will not flag this as a read error. This can happen when
a pluggable daughter card is not connected and weak internal pull-ups
are used (since that is the only option, otherwise the pins are
floating).

The second read of MII_PHYSID2 will be correctly flagged an error
though, but now we will return -EIO which will be treated as a hard
error, thus preventing MDIO bus scanning loops to continue succesfully.

Apply the same logic to both register reads, thus allowing the scanning
logic to proceed.

Fixes: 02a6efcab675 ("net: phy: allow scanning busses with missing phys")
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 697c74deb222..0881b4b92363 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -798,8 +798,10 @@ static int get_phy_id(struct mii_bus *bus, int addr, u32 *phy_id,
 
 	/* Grab the bits from PHYIR2, and put them in the lower half */
 	phy_reg = mdiobus_read(bus, addr, MII_PHYSID2);
-	if (phy_reg < 0)
-		return -EIO;
+	if (phy_reg < 0) {
+		/* returning -ENODEV doesn't stop bus scanning */
+		return (phy_reg == -EIO || phy_reg == -ENODEV) ? -ENODEV : -EIO;
+	}
 
 	*phy_id |= phy_reg;
 
-- 
2.26.2


From b45c12166e71c4c149952bc673bcea646acd35f5 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Tue, 16 Jun 2020 16:51:51 +0000
Subject: [PATCH 25/49] ip_tunnel: fix use-after-free in ip_tunnel_lookup()

[ Upstream commit ba61539c6ae57f4146284a5cb4f7b7ed8d42bf45 ]

In the datapath, the ip_tunnel_lookup() is used and it internally uses
fallback tunnel device pointer, which is fb_tunnel_dev.
This pointer variable should be set to NULL when a fb interface is deleted.
But there is no routine to set fb_tunnel_dev pointer to NULL.
So, this pointer will be still used after interface is deleted and
it eventually results in the use-after-free problem.

Test commands:
    ip netns add A
    ip netns add B
    ip link add eth0 type veth peer name eth1
    ip link set eth0 netns A
    ip link set eth1 netns B

    ip netns exec A ip link set lo up
    ip netns exec A ip link set eth0 up
    ip netns exec A ip link add gre1 type gre local 10.0.0.1 \
	    remote 10.0.0.2
    ip netns exec A ip link set gre1 up
    ip netns exec A ip a a 10.0.100.1/24 dev gre1
    ip netns exec A ip a a 10.0.0.1/24 dev eth0

    ip netns exec B ip link set lo up
    ip netns exec B ip link set eth1 up
    ip netns exec B ip link add gre1 type gre local 10.0.0.2 \
	    remote 10.0.0.1
    ip netns exec B ip link set gre1 up
    ip netns exec B ip a a 10.0.100.2/24 dev gre1
    ip netns exec B ip a a 10.0.0.2/24 dev eth1
    ip netns exec A hping3 10.0.100.2 -2 --flood -d 60000 &
    ip netns del B

Splat looks like:
[   77.793450][    C3] ==================================================================
[   77.794702][    C3] BUG: KASAN: use-after-free in ip_tunnel_lookup+0xcc4/0xf30
[   77.795573][    C3] Read of size 4 at addr ffff888060bd9c84 by task hping3/2905
[   77.796398][    C3]
[   77.796664][    C3] CPU: 3 PID: 2905 Comm: hping3 Not tainted 5.8.0-rc1+ #616
[   77.797474][    C3] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[   77.798453][    C3] Call Trace:
[   77.798815][    C3]  <IRQ>
[   77.799142][    C3]  dump_stack+0x9d/0xdb
[   77.799605][    C3]  print_address_description.constprop.7+0x2cc/0x450
[   77.800365][    C3]  ? ip_tunnel_lookup+0xcc4/0xf30
[   77.800908][    C3]  ? ip_tunnel_lookup+0xcc4/0xf30
[   77.801517][    C3]  ? ip_tunnel_lookup+0xcc4/0xf30
[   77.802145][    C3]  kasan_report+0x154/0x190
[   77.802821][    C3]  ? ip_tunnel_lookup+0xcc4/0xf30
[   77.803503][    C3]  ip_tunnel_lookup+0xcc4/0xf30
[   77.804165][    C3]  __ipgre_rcv+0x1ab/0xaa0 [ip_gre]
[   77.804862][    C3]  ? rcu_read_lock_sched_held+0xc0/0xc0
[   77.805621][    C3]  gre_rcv+0x304/0x1910 [ip_gre]
[   77.806293][    C3]  ? lock_acquire+0x1a9/0x870
[   77.806925][    C3]  ? gre_rcv+0xfe/0x354 [gre]
[   77.807559][    C3]  ? erspan_xmit+0x2e60/0x2e60 [ip_gre]
[   77.808305][    C3]  ? rcu_read_lock_sched_held+0xc0/0xc0
[   77.809032][    C3]  ? rcu_read_lock_held+0x90/0xa0
[   77.809713][    C3]  gre_rcv+0x1b8/0x354 [gre]
[ ... ]

Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Fixes: c54419321455 ("GRE: Refactor GRE tunneling code.")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_tunnel.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index cd4b84310d92..a0b4dc54f8a6 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -85,9 +85,10 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 				   __be32 remote, __be32 local,
 				   __be32 key)
 {
-	unsigned int hash;
 	struct ip_tunnel *t, *cand = NULL;
 	struct hlist_head *head;
+	struct net_device *ndev;
+	unsigned int hash;
 
 	hash = ip_tunnel_hash(key, remote);
 	head = &itn->tunnels[hash];
@@ -162,8 +163,9 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 	if (t && t->dev->flags & IFF_UP)
 		return t;
 
-	if (itn->fb_tunnel_dev && itn->fb_tunnel_dev->flags & IFF_UP)
-		return netdev_priv(itn->fb_tunnel_dev);
+	ndev = READ_ONCE(itn->fb_tunnel_dev);
+	if (ndev && ndev->flags & IFF_UP)
+		return netdev_priv(ndev);
 
 	return NULL;
 }
@@ -1245,9 +1247,9 @@ void ip_tunnel_uninit(struct net_device *dev)
 	struct ip_tunnel_net *itn;
 
 	itn = net_generic(net, tunnel->ip_tnl_net_id);
-	/* fb_tunnel_dev will be unregisted in net-exit call. */
-	if (itn->fb_tunnel_dev != dev)
-		ip_tunnel_del(itn, netdev_priv(dev));
+	ip_tunnel_del(itn, netdev_priv(dev));
+	if (itn->fb_tunnel_dev == dev)
+		WRITE_ONCE(itn->fb_tunnel_dev, NULL);
 
 	dst_cache_reset(&tunnel->dst_cache);
 }
-- 
2.26.2


From 9374295165f13f558506a068ccf438483e87dfcc Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Tue, 23 Jun 2020 19:01:35 -0400
Subject: [PATCH 26/49] bnxt_en: Store the running firmware version code.

[ Upstream commit d0ad2ea2bc185835f8a749302ad07b70528d2a09 ]

We currently only store the firmware version as a string for ethtool
and devlink info.  Store it also as a version code.  The next 2
patches will need to check the firmware major version to determine
some workarounds.

We also use the 16-bit firmware version fields if the firmware is newer
and provides the 16-bit fields.

Reviewed-by: Edwin Peer <edwin.peer@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 22 ++++++++++++++++++----
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |  4 ++++
 2 files changed, 22 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 19c4a0a5727a..83ed6f31a1fa 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -7217,8 +7217,9 @@ static int __bnxt_hwrm_ver_get(struct bnxt *bp, bool silent)
 static int bnxt_hwrm_ver_get(struct bnxt *bp)
 {
 	struct hwrm_ver_get_output *resp = bp->hwrm_cmd_resp_addr;
+	u16 fw_maj, fw_min, fw_bld, fw_rsv;
 	u32 dev_caps_cfg, hwrm_ver;
-	int rc;
+	int rc, len;
 
 	bp->hwrm_max_req_len = HWRM_MAX_REQ_LEN;
 	mutex_lock(&bp->hwrm_cmd_lock);
@@ -7250,9 +7251,22 @@ static int bnxt_hwrm_ver_get(struct bnxt *bp)
 			 resp->hwrm_intf_maj_8b, resp->hwrm_intf_min_8b,
 			 resp->hwrm_intf_upd_8b);
 
-	snprintf(bp->fw_ver_str, BC_HWRM_STR_LEN, "%d.%d.%d.%d",
-		 resp->hwrm_fw_maj_8b, resp->hwrm_fw_min_8b,
-		 resp->hwrm_fw_bld_8b, resp->hwrm_fw_rsvd_8b);
+	fw_maj = le16_to_cpu(resp->hwrm_fw_major);
+	if (bp->hwrm_spec_code > 0x10803 && fw_maj) {
+		fw_min = le16_to_cpu(resp->hwrm_fw_minor);
+		fw_bld = le16_to_cpu(resp->hwrm_fw_build);
+		fw_rsv = le16_to_cpu(resp->hwrm_fw_patch);
+		len = FW_VER_STR_LEN;
+	} else {
+		fw_maj = resp->hwrm_fw_maj_8b;
+		fw_min = resp->hwrm_fw_min_8b;
+		fw_bld = resp->hwrm_fw_bld_8b;
+		fw_rsv = resp->hwrm_fw_rsvd_8b;
+		len = BC_HWRM_STR_LEN;
+	}
+	bp->fw_ver_code = BNXT_FW_VER_CODE(fw_maj, fw_min, fw_bld, fw_rsv);
+	snprintf(bp->fw_ver_str, len, "%d.%d.%d.%d", fw_maj, fw_min, fw_bld,
+		 fw_rsv);
 
 	if (strlen(resp->active_pkg_name)) {
 		int fw_ver_len = strlen(bp->fw_ver_str);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 3d39638521d6..a880aea0c20b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1729,6 +1729,10 @@ struct bnxt {
 #define PHY_VER_STR_LEN         (FW_VER_STR_LEN - BC_HWRM_STR_LEN)
 	char			fw_ver_str[FW_VER_STR_LEN];
 	char			hwrm_ver_supp[FW_VER_STR_LEN];
+	u64			fw_ver_code;
+#define BNXT_FW_VER_CODE(maj, min, bld, rsv)			\
+	((u64)(maj) << 48 | (u64)(min) << 32 | (u64)(bld) << 16 | (rsv))
+
 	__be16			vxlan_port;
 	u8			vxlan_port_cnt;
 	__le16			vxlan_fw_dst_port_id;
-- 
2.26.2


From e2ae989afd0e83a01c7991cb74e9308228fa764e Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Tue, 23 Jun 2020 19:01:36 -0400
Subject: [PATCH 27/49] bnxt_en: Do not enable legacy TX push on older
 firmware.

[ Upstream commit fed7edd18143c68c63ea049999a7e861123de6de ]

Older firmware may not support legacy TX push properly and may not
be disabling it.  So we check certain firmware versions that may
have this problem and disable legacy TX push unconditionally.

Fixes: c0c050c58d84 ("bnxt_en: New Broadcom ethernet driver.")
Reviewed-by: Edwin Peer <edwin.peer@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 3 ++-
 drivers/net/ethernet/broadcom/bnxt/bnxt.h | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 83ed6f31a1fa..6bf97b3acdad 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -6953,7 +6953,8 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp)
 		bp->fw_cap |= BNXT_FW_CAP_ERR_RECOVER_RELOAD;
 
 	bp->tx_push_thresh = 0;
-	if (flags & FUNC_QCAPS_RESP_FLAGS_PUSH_MODE_SUPPORTED)
+	if ((flags & FUNC_QCAPS_RESP_FLAGS_PUSH_MODE_SUPPORTED) &&
+	    BNXT_FW_MAJ(bp) > 217)
 		bp->tx_push_thresh = BNXT_TX_PUSH_THRESH;
 
 	hw_resc->max_rsscos_ctxs = le16_to_cpu(resp->max_rsscos_ctx);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index a880aea0c20b..23ee433db864 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1732,6 +1732,7 @@ struct bnxt {
 	u64			fw_ver_code;
 #define BNXT_FW_VER_CODE(maj, min, bld, rsv)			\
 	((u64)(maj) << 48 | (u64)(min) << 32 | (u64)(bld) << 16 | (rsv))
+#define BNXT_FW_MAJ(bp)		((bp)->fw_ver_code >> 48)
 
 	__be16			vxlan_port;
 	u8			vxlan_port_cnt;
-- 
2.26.2


From dbd4bc38c9d53b237950bfc6853ddc6edb8d3b4c Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Tue, 23 Jun 2020 19:01:37 -0400
Subject: [PATCH 28/49] bnxt_en: Fix statistics counters issue during ifdown
 with older firmware.

[ Upstream commit c2dec363feb41544a76c8083aca2378990e17166 ]

On older firmware, the hardware statistics are not cleared when the
driver frees the hardware stats contexts during ifdown.  The driver
expects these stats to be cleared and saves a copy before freeing
the stats contexts.  During the next ifup, the driver will likely
allocate the same hardware stats contexts and this will cause a big
increase in the counters as the old counters are added back to the
saved counters.

We fix it by making an additional firmware call to clear the counters
before freeing the hw stats contexts when the firmware is the older
20.x firmware.

Fixes: b8875ca356f1 ("bnxt_en: Save ring statistics before reset.")
Reported-by: Jakub Kicinski <kicinski@fb.com>
Reviewed-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Tested-by: Jakub Kicinski <kicinski@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 6bf97b3acdad..c202c2a3d140 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -6293,6 +6293,7 @@ int bnxt_hwrm_set_coal(struct bnxt *bp)
 
 static void bnxt_hwrm_stat_ctx_free(struct bnxt *bp)
 {
+	struct hwrm_stat_ctx_clr_stats_input req0 = {0};
 	struct hwrm_stat_ctx_free_input req = {0};
 	int i;
 
@@ -6302,6 +6303,7 @@ static void bnxt_hwrm_stat_ctx_free(struct bnxt *bp)
 	if (BNXT_CHIP_TYPE_NITRO_A0(bp))
 		return;
 
+	bnxt_hwrm_cmd_hdr_init(bp, &req0, HWRM_STAT_CTX_CLR_STATS, -1, -1);
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_STAT_CTX_FREE, -1, -1);
 
 	mutex_lock(&bp->hwrm_cmd_lock);
@@ -6311,7 +6313,11 @@ static void bnxt_hwrm_stat_ctx_free(struct bnxt *bp)
 
 		if (cpr->hw_stats_ctx_id != INVALID_STATS_CTX_ID) {
 			req.stat_ctx_id = cpu_to_le32(cpr->hw_stats_ctx_id);
-
+			if (BNXT_FW_MAJ(bp) <= 20) {
+				req0.stat_ctx_id = req.stat_ctx_id;
+				_hwrm_send_message(bp, &req0, sizeof(req0),
+						   HWRM_CMD_TIMEOUT);
+			}
 			_hwrm_send_message(bp, &req, sizeof(req),
 					   HWRM_CMD_TIMEOUT);
 
-- 
2.26.2


From 0a50d36aa99ffb41651dc136d99ffc0b5026f6c1 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Tue, 23 Jun 2020 19:01:38 -0400
Subject: [PATCH 29/49] bnxt_en: Read VPD info only for PFs

[ Upstream commit c55e28a8b43fcd7dc71868bd165705bc7741a7ca ]

Virtual functions does not have VPD information. This patch modifies
calling bnxt_read_vpd_info() only for PFs and avoids an unnecessary
error log.

Fixes: a0d0fd70fed5 ("bnxt_en: Read partno and serialno of the board from VPD")
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index c202c2a3d140..b6fb5a1709c0 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -11884,7 +11884,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	dev->ethtool_ops = &bnxt_ethtool_ops;
 	pci_set_drvdata(pdev, dev);
 
-	bnxt_vpd_read_info(bp);
+	if (BNXT_PF(bp))
+		bnxt_vpd_read_info(bp);
 
 	rc = bnxt_alloc_hwrm_resources(bp);
 	if (rc)
-- 
2.26.2


From 63a7e6647eaeae7cbb7df67ad17d5317d98d9cc9 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Tue, 23 Jun 2020 17:47:23 +0100
Subject: [PATCH 30/49] net: phylink: fix ethtool -A with attached PHYs

[ Upstream commit c718af2d00a37587b09e5958d142da7569f3d55b ]

Fix a phylink's ethtool set_pauseparam support deadlock caused by phylib
interacting with phylink: we must not hold the state lock while calling
phylib functions that may call into phylink_phy_change().

Fixes: f904f15ea9b5 ("net: phylink: allow ethtool -A to change flow control advertisement")
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phylink.c | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 34ca12aec61b..b0ddeab2a8d2 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -1519,18 +1519,20 @@ int phylink_ethtool_set_pauseparam(struct phylink *pl,
 	linkmode_set_pause(config->advertising, pause->tx_pause,
 			   pause->rx_pause);
 
-	/* If we have a PHY, phylib will call our link state function if the
-	 * mode has changed, which will trigger a resolve and update the MAC
-	 * configuration.
+	if (!pl->phydev && !test_bit(PHYLINK_DISABLE_STOPPED,
+				     &pl->phylink_disable_state))
+		phylink_pcs_config(pl, true, &pl->link_config);
+
+	mutex_unlock(&pl->state_mutex);
+
+	/* If we have a PHY, a change of the pause frame advertisement will
+	 * cause phylib to renegotiate (if AN is enabled) which will in turn
+	 * call our phylink_phy_change() and trigger a resolve.  Note that
+	 * we can't hold our state mutex while calling phy_set_asym_pause().
 	 */
-	if (pl->phydev) {
+	if (pl->phydev)
 		phy_set_asym_pause(pl->phydev, pause->rx_pause,
 				   pause->tx_pause);
-	} else if (!test_bit(PHYLINK_DISABLE_STOPPED,
-			     &pl->phylink_disable_state)) {
-		phylink_pcs_config(pl, true, &pl->link_config);
-	}
-	mutex_unlock(&pl->state_mutex);
 
 	return 0;
 }
-- 
2.26.2


From 8959ae3143269af2e7ab24930a6f9a7a3f6bea74 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Tue, 23 Jun 2020 17:47:29 +0100
Subject: [PATCH 31/49] net: phylink: ensure manual pause mode configuration
 takes effect

[ Upstream commit 2e919bc446faee429ac862a6cdb5e40017051f6b ]

We have been relying on link events and mac_config() when the manual
pause modes are changed.  With recent developments, such as moving
the programming of link state to mac_link_up(), this no longer works.

To ensure that we update the MAC, we must generate a link-down followed
by a link-up event; we can do that by setting mac_link_dropped and
triggering a resolve.

Fixes: 91a208f2185a ("net: phylink: propagate resolved link config via mac_link_up()")
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phylink.c | 27 ++++++++++++++++++++++-----
 1 file changed, 22 insertions(+), 5 deletions(-)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index b0ddeab2a8d2..ac38bead1cd2 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -1480,6 +1480,8 @@ int phylink_ethtool_set_pauseparam(struct phylink *pl,
 				   struct ethtool_pauseparam *pause)
 {
 	struct phylink_link_state *config = &pl->link_config;
+	bool manual_changed;
+	int pause_state;
 
 	ASSERT_RTNL();
 
@@ -1494,15 +1496,15 @@ int phylink_ethtool_set_pauseparam(struct phylink *pl,
 	    !pause->autoneg && pause->rx_pause != pause->tx_pause)
 		return -EINVAL;
 
-	mutex_lock(&pl->state_mutex);
-	config->pause = 0;
+	pause_state = 0;
 	if (pause->autoneg)
-		config->pause |= MLO_PAUSE_AN;
+		pause_state |= MLO_PAUSE_AN;
 	if (pause->rx_pause)
-		config->pause |= MLO_PAUSE_RX;
+		pause_state |= MLO_PAUSE_RX;
 	if (pause->tx_pause)
-		config->pause |= MLO_PAUSE_TX;
+		pause_state |= MLO_PAUSE_TX;
 
+	mutex_lock(&pl->state_mutex);
 	/*
 	 * See the comments for linkmode_set_pause(), wrt the deficiencies
 	 * with the current implementation.  A solution to this issue would
@@ -1519,6 +1521,12 @@ int phylink_ethtool_set_pauseparam(struct phylink *pl,
 	linkmode_set_pause(config->advertising, pause->tx_pause,
 			   pause->rx_pause);
 
+	manual_changed = (config->pause ^ pause_state) & MLO_PAUSE_AN ||
+			 (!(pause_state & MLO_PAUSE_AN) &&
+			   (config->pause ^ pause_state) & MLO_PAUSE_TXRX_MASK);
+
+	config->pause = pause_state;
+
 	if (!pl->phydev && !test_bit(PHYLINK_DISABLE_STOPPED,
 				     &pl->phylink_disable_state))
 		phylink_pcs_config(pl, true, &pl->link_config);
@@ -1534,6 +1542,15 @@ int phylink_ethtool_set_pauseparam(struct phylink *pl,
 		phy_set_asym_pause(pl->phydev, pause->rx_pause,
 				   pause->tx_pause);
 
+	/* If the manual pause settings changed, make sure we trigger a
+	 * resolve to update their state; we can not guarantee that the
+	 * link will cycle.
+	 */
+	if (manual_changed) {
+		pl->mac_link_dropped = true;
+		phylink_run_resolve(pl);
+	}
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(phylink_ethtool_set_pauseparam);
-- 
2.26.2


From bc7dc8b25a429d062a41c35a4719b42d446c1fc1 Mon Sep 17 00:00:00 2001
From: Ilya Ponetayev <i.ponetaev@ndmsystems.com>
Date: Thu, 25 Jun 2020 22:12:07 +0200
Subject: [PATCH 32/49] sch_cake: don't try to reallocate or unshare skb
 unconditionally
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 9208d2863ac689a563b92f2161d8d1e7127d0add ]

cake_handle_diffserv() tries to linearize mac and network header parts of
skb and to make it writable unconditionally. In some cases it leads to full
skb reallocation, which reduces throughput and increases CPU load. Some
measurements of IPv4 forward + NAPT on MIPS router with 580 MHz single-core
CPU was conducted. It appears that on kernel 4.9 skb_try_make_writable()
reallocates skb, if skb was allocated in ethernet driver via so-called
'build skb' method from page cache (it was discovered by strange increase
of kmalloc-2048 slab at first).

Obtain DSCP value via read-only skb_header_pointer() call, and leave
linearization only for DSCP bleaching or ECN CE setting. And, as an
additional optimisation, skip diffserv parsing entirely if it is not needed
by the current configuration.

Fixes: c87b4ecdbe8d ("sch_cake: Make sure we can write the IP header before changing DSCP bits")
Signed-off-by: Ilya Ponetayev <i.ponetaev@ndmsystems.com>
[ fix a few style issues, reflow commit message ]
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_cake.c | 41 ++++++++++++++++++++++++++++++-----------
 1 file changed, 30 insertions(+), 11 deletions(-)

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 1496e87cd07b..a92d6c57aa9a 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -1516,30 +1516,49 @@ static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free)
 
 static u8 cake_handle_diffserv(struct sk_buff *skb, u16 wash)
 {
-	int wlen = skb_network_offset(skb);
+	const int offset = skb_network_offset(skb);
+	u16 *buf, buf_;
 	u8 dscp;
 
 	switch (tc_skb_protocol(skb)) {
 	case htons(ETH_P_IP):
-		wlen += sizeof(struct iphdr);
-		if (!pskb_may_pull(skb, wlen) ||
-		    skb_try_make_writable(skb, wlen))
+		buf = skb_header_pointer(skb, offset, sizeof(buf_), &buf_);
+		if (unlikely(!buf))
 			return 0;
 
-		dscp = ipv4_get_dsfield(ip_hdr(skb)) >> 2;
-		if (wash && dscp)
+		/* ToS is in the second byte of iphdr */
+		dscp = ipv4_get_dsfield((struct iphdr *)buf) >> 2;
+
+		if (wash && dscp) {
+			const int wlen = offset + sizeof(struct iphdr);
+
+			if (!pskb_may_pull(skb, wlen) ||
+			    skb_try_make_writable(skb, wlen))
+				return 0;
+
 			ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, 0);
+		}
+
 		return dscp;
 
 	case htons(ETH_P_IPV6):
-		wlen += sizeof(struct ipv6hdr);
-		if (!pskb_may_pull(skb, wlen) ||
-		    skb_try_make_writable(skb, wlen))
+		buf = skb_header_pointer(skb, offset, sizeof(buf_), &buf_);
+		if (unlikely(!buf))
 			return 0;
 
-		dscp = ipv6_get_dsfield(ipv6_hdr(skb)) >> 2;
-		if (wash && dscp)
+		/* Traffic class is in the first and second bytes of ipv6hdr */
+		dscp = ipv6_get_dsfield((struct ipv6hdr *)buf) >> 2;
+
+		if (wash && dscp) {
+			const int wlen = offset + sizeof(struct ipv6hdr);
+
+			if (!pskb_may_pull(skb, wlen) ||
+			    skb_try_make_writable(skb, wlen))
+				return 0;
+
 			ipv6_change_dsfield(ipv6_hdr(skb), INET_ECN_MASK, 0);
+		}
+
 		return dscp;
 
 	case htons(ETH_P_ARP):
-- 
2.26.2


From 96add19d845711a7ed0de2ebcfc06debe0282bb2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
Date: Thu, 25 Jun 2020 22:12:08 +0200
Subject: [PATCH 33/49] sch_cake: don't call diffserv parsing code when it is
 not needed
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 8c95eca0bb8c4bd2231a0d581f1ad0d50c90488c ]

As a further optimisation of the diffserv parsing codepath, we can skip it
entirely if CAKE is configured to neither use diffserv-based
classification, nor to zero out the diffserv bits.

Fixes: c87b4ecdbe8d ("sch_cake: Make sure we can write the IP header before changing DSCP bits")
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_cake.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index a92d6c57aa9a..3482f9569dce 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -1514,7 +1514,7 @@ static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free)
 	return idx + (tin << 16);
 }
 
-static u8 cake_handle_diffserv(struct sk_buff *skb, u16 wash)
+static u8 cake_handle_diffserv(struct sk_buff *skb, bool wash)
 {
 	const int offset = skb_network_offset(skb);
 	u16 *buf, buf_;
@@ -1575,14 +1575,17 @@ static struct cake_tin_data *cake_select_tin(struct Qdisc *sch,
 {
 	struct cake_sched_data *q = qdisc_priv(sch);
 	u32 tin, mark;
+	bool wash;
 	u8 dscp;
 
 	/* Tin selection: Default to diffserv-based selection, allow overriding
-	 * using firewall marks or skb->priority.
+	 * using firewall marks or skb->priority. Call DSCP parsing early if
+	 * wash is enabled, otherwise defer to below to skip unneeded parsing.
 	 */
-	dscp = cake_handle_diffserv(skb,
-				    q->rate_flags & CAKE_FLAG_WASH);
 	mark = (skb->mark & q->fwmark_mask) >> q->fwmark_shft;
+	wash = !!(q->rate_flags & CAKE_FLAG_WASH);
+	if (wash)
+		dscp = cake_handle_diffserv(skb, wash);
 
 	if (q->tin_mode == CAKE_DIFFSERV_BESTEFFORT)
 		tin = 0;
@@ -1596,6 +1599,8 @@ static struct cake_tin_data *cake_select_tin(struct Qdisc *sch,
 		tin = q->tin_order[TC_H_MIN(skb->priority) - 1];
 
 	else {
+		if (!wash)
+			dscp = cake_handle_diffserv(skb, wash);
 		tin = q->tin_index[dscp];
 
 		if (unlikely(tin >= q->tin_cnt))
-- 
2.26.2


From 48b626a09df438b347d24e7b1600e83a5224094a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
Date: Thu, 25 Jun 2020 22:12:09 +0200
Subject: [PATCH 34/49] sch_cake: fix a few style nits
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 3f608f0c41360b11b04c763f348b712f651c8bac ]

I spotted a few nits when comparing the in-tree version of sch_cake with
the out-of-tree one: A redundant error variable declaration shadowing an
outer declaration, and an indentation alignment issue. Fix both of these.

Fixes: 046f6fd5daef ("sched: Add Common Applications Kept Enhanced (cake) qdisc")
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_cake.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 3482f9569dce..9475fa81ea7f 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -2678,7 +2678,7 @@ static int cake_init(struct Qdisc *sch, struct nlattr *opt,
 	qdisc_watchdog_init(&q->watchdog, sch);
 
 	if (opt) {
-		int err = cake_change(sch, opt, extack);
+		err = cake_change(sch, opt, extack);
 
 		if (err)
 			return err;
@@ -2995,7 +2995,7 @@ static int cake_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 			PUT_STAT_S32(BLUE_TIMER_US,
 				     ktime_to_us(
 					     ktime_sub(now,
-						     flow->cvars.blue_timer)));
+						       flow->cvars.blue_timer)));
 		}
 		if (flow->cvars.dropping) {
 			PUT_STAT_S32(DROP_NEXT_US,
-- 
2.26.2


From 37e7beeb943409cf5007ce5f337a2cc8de8b75bd Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Wed, 24 Jun 2020 12:42:02 -0400
Subject: [PATCH 35/49] tcp_cubic: fix spurious HYSTART_DELAY exit upon drop in
 min RTT

[ Upstream commit b344579ca8478598937215f7005d6c7b84d28aee ]

Mirja Kuehlewind reported a bug in Linux TCP CUBIC Hystart, where
Hystart HYSTART_DELAY mechanism can exit Slow Start spuriously on an
ACK when the minimum rtt of a connection goes down. From inspection it
is clear from the existing code that this could happen in an example
like the following:

o The first 8 RTT samples in a round trip are 150ms, resulting in a
  curr_rtt of 150ms and a delay_min of 150ms.

o The 9th RTT sample is 100ms. The curr_rtt does not change after the
  first 8 samples, so curr_rtt remains 150ms. But delay_min can be
  lowered at any time, so delay_min falls to 100ms. The code executes
  the HYSTART_DELAY comparison between curr_rtt of 150ms and delay_min
  of 100ms, and the curr_rtt is declared far enough above delay_min to
  force a (spurious) exit of Slow start.

The fix here is simple: allow every RTT sample in a round trip to
lower the curr_rtt.

Fixes: ae27e98a5152 ("[TCP] CUBIC v2.3")
Reported-by: Mirja Kuehlewind <mirja.kuehlewind@ericsson.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_cubic.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 8f8eefd3a3ce..c7bf5b26bf0c 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -432,10 +432,9 @@ static void hystart_update(struct sock *sk, u32 delay)
 
 	if (hystart_detect & HYSTART_DELAY) {
 		/* obtain the minimum delay of more than sampling packets */
+		if (ca->curr_rtt > delay)
+			ca->curr_rtt = delay;
 		if (ca->sample_cnt < HYSTART_MIN_SAMPLES) {
-			if (ca->curr_rtt > delay)
-				ca->curr_rtt = delay;
-
 			ca->sample_cnt++;
 		} else {
 			if (ca->curr_rtt > ca->delay_min +
-- 
2.26.2


From 084aa0ca0a5989242d46de5ab6db71517033beae Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Wed, 24 Jun 2020 12:42:03 -0400
Subject: [PATCH 36/49] bpf: tcp: bpf_cubic: fix spurious HYSTART_DELAY exit
 upon drop in min RTT

[ Upstream commit 7d21d54d624777358ab6c7be7ff778808fef70ba ]

Apply the fix from:
 "tcp_cubic: fix spurious HYSTART_DELAY exit upon drop in min RTT"
to the BPF implementation of TCP CUBIC congestion control.

Repeating the commit description here for completeness:

Mirja Kuehlewind reported a bug in Linux TCP CUBIC Hystart, where
Hystart HYSTART_DELAY mechanism can exit Slow Start spuriously on an
ACK when the minimum rtt of a connection goes down. From inspection it
is clear from the existing code that this could happen in an example
like the following:

o The first 8 RTT samples in a round trip are 150ms, resulting in a
  curr_rtt of 150ms and a delay_min of 150ms.

o The 9th RTT sample is 100ms. The curr_rtt does not change after the
  first 8 samples, so curr_rtt remains 150ms. But delay_min can be
  lowered at any time, so delay_min falls to 100ms. The code executes
  the HYSTART_DELAY comparison between curr_rtt of 150ms and delay_min
  of 100ms, and the curr_rtt is declared far enough above delay_min to
  force a (spurious) exit of Slow start.

The fix here is simple: allow every RTT sample in a round trip to
lower the curr_rtt.

Fixes: 6de4a9c430b5 ("bpf: tcp: Add bpf_cubic example")
Reported-by: Mirja Kuehlewind <mirja.kuehlewind@ericsson.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/bpf/progs/bpf_cubic.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/bpf_cubic.c b/tools/testing/selftests/bpf/progs/bpf_cubic.c
index 7897c8f4d363..ef574087f1e1 100644
--- a/tools/testing/selftests/bpf/progs/bpf_cubic.c
+++ b/tools/testing/selftests/bpf/progs/bpf_cubic.c
@@ -480,10 +480,9 @@ static __always_inline void hystart_update(struct sock *sk, __u32 delay)
 
 	if (hystart_detect & HYSTART_DELAY) {
 		/* obtain the minimum delay of more than sampling packets */
+		if (ca->curr_rtt > delay)
+			ca->curr_rtt = delay;
 		if (ca->sample_cnt < HYSTART_MIN_SAMPLES) {
-			if (ca->curr_rtt > delay)
-				ca->curr_rtt = delay;
-
 			ca->sample_cnt++;
 		} else {
 			if (ca->curr_rtt > ca->delay_min +
-- 
2.26.2


From 21428dbc326ddde0012445fc23a1251a59bca8ed Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@microchip.com>
Date: Thu, 18 Jun 2020 11:37:40 +0300
Subject: [PATCH 37/49] net: macb: undo operations in case of failure

[ Upstream commit faa620876b01d6744f1599e279042bb8149247ab ]

Undo previously done operation in case macb_phylink_connect()
fails. Since macb_reset_hw() is the 1st undo operation the
napi_exit label was renamed to reset_hw.

Fixes: 7897b071ac3b ("net: macb: convert to phylink")
Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Acked-by: Nicolas Ferre <nicolas.ferre@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 67933079aeea..257c4920cb88 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -2558,7 +2558,7 @@ static int macb_open(struct net_device *dev)
 
 	err = macb_phylink_connect(bp);
 	if (err)
-		goto napi_exit;
+		goto reset_hw;
 
 	netif_tx_start_all_queues(dev);
 
@@ -2567,9 +2567,11 @@ static int macb_open(struct net_device *dev)
 
 	return 0;
 
-napi_exit:
+reset_hw:
+	macb_reset_hw(bp);
 	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
 		napi_disable(&queue->napi);
+	macb_free_consistent(bp);
 pm_exit:
 	pm_runtime_put_sync(&bp->pdev->dev);
 	return err;
-- 
2.26.2


From 9c673af8b330b4a05ad69b3099c21a97d9d064e3 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 18 Jun 2020 23:25:50 +0200
Subject: [PATCH 38/49] r8169: fix firmware not resetting tp->ocp_base

[ Upstream commit 89fbd26cca7ec9e82ec4787a4b6e95939b57d073 ]

Typically the firmware takes care that tp->ocp_base is reset to its
default value. That's not the case (at least) for RTL8117.
As a result subsequent PHY access reads/writes the wrong page and
the link is broken. Fix this be resetting tp->ocp_base explicitly.

Fixes: 229c1e0dfd3d ("r8169: load firmware for RTL8168fp/RTL8117")
Reported-by: Aaron Ma <mapengyu@gmail.com>
Tested-by: Aaron Ma <mapengyu@gmail.com>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169_main.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index c51b48dc3639..7bda2671bd5b 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -2192,8 +2192,11 @@ static void rtl_release_firmware(struct rtl8169_private *tp)
 void r8169_apply_firmware(struct rtl8169_private *tp)
 {
 	/* TODO: release firmware if rtl_fw_write_firmware signals failure. */
-	if (tp->rtl_fw)
+	if (tp->rtl_fw) {
 		rtl_fw_write_firmware(tp, tp->rtl_fw);
+		/* At least one firmware doesn't reset tp->ocp_base. */
+		tp->ocp_base = OCP_STD_PHY_BASE;
+	}
 }
 
 static void rtl8168_config_eee_mac(struct rtl8169_private *tp)
-- 
2.26.2


From 8d000ada2c243ffac0baf7772ff3de9c73818648 Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliangtang@gmail.com>
Date: Mon, 22 Jun 2020 19:45:58 +0800
Subject: [PATCH 39/49] mptcp: drop sndr_key in mptcp_syn_options

[ Upstream commit b562f58bbc12444219b74a5d6524977a3d87a022 ]

In RFC 8684, we don't need to send sndr_key in SYN package anymore, so drop
it.

Fixes: cc7972ea1932 ("mptcp: parse and emit MP_CAPABLE option according to v1 spec")
Signed-off-by: Geliang Tang <geliangtang@gmail.com>
Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/options.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 1c20dd14b2aa..2430bbfa3405 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -336,9 +336,7 @@ bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb,
 	 */
 	subflow->snd_isn = TCP_SKB_CB(skb)->end_seq;
 	if (subflow->request_mptcp) {
-		pr_debug("local_key=%llu", subflow->local_key);
 		opts->suboptions = OPTION_MPTCP_MPC_SYN;
-		opts->sndr_key = subflow->local_key;
 		*size = TCPOLEN_MPTCP_MPC_SYN;
 		return true;
 	} else if (subflow->request_join) {
-- 
2.26.2


From 9eb4083b70eb825068cb507efb2dfaeb1e2575f1 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Mon, 15 Jun 2020 09:35:22 +0800
Subject: [PATCH 40/49] mptcp: fix memory leak in mptcp_subflow_create_socket()

[ Upstream commit b8ad540dd4e40566c520dff491fc06c71ae6b989 ]

socket malloced  by sock_create_kern() should be release before return
in the error handling, otherwise it cause memory leak.

unreferenced object 0xffff88810910c000 (size 1216):
  comm "00000003_test_m", pid 12238, jiffies 4295050289 (age 54.237s)
  hex dump (first 32 bytes):
    01 00 00 00 01 00 00 00 00 00 00 00 00 00 00 00  ................
    00 00 00 00 00 00 00 00 00 2f 30 0a 81 88 ff ff  ........./0.....
  backtrace:
    [<00000000e877f89f>] sock_alloc_inode+0x18/0x1c0
    [<0000000093d1dd51>] alloc_inode+0x63/0x1d0
    [<000000005673fec6>] new_inode_pseudo+0x14/0xe0
    [<00000000b5db6be8>] sock_alloc+0x3c/0x260
    [<00000000e7e3cbb2>] __sock_create+0x89/0x620
    [<0000000023e48593>] mptcp_subflow_create_socket+0xc0/0x5e0
    [<00000000419795e4>] __mptcp_socket_create+0x1ad/0x3f0
    [<00000000b2f942e8>] mptcp_stream_connect+0x281/0x4f0
    [<00000000c80cd5cc>] __sys_connect_file+0x14d/0x190
    [<00000000dc761f11>] __sys_connect+0x128/0x160
    [<000000008b14e764>] __x64_sys_connect+0x6f/0xb0
    [<000000007b4f93bd>] do_syscall_64+0xa1/0x530
    [<00000000d3e770b6>] entry_SYSCALL_64_after_hwframe+0x49/0xb3

Fixes: 2303f994b3e1 ("mptcp: Associate MPTCP context with TCP socket")
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/subflow.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index e6feb05a93dc..db3e4e74e785 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -1015,8 +1015,10 @@ int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock)
 	err = tcp_set_ulp(sf->sk, "mptcp");
 	release_sock(sf->sk);
 
-	if (err)
+	if (err) {
+		sock_release(sf);
 		return err;
+	}
 
 	/* the newly created socket really belongs to the owning MPTCP master
 	 * socket, even if for additional subflows the allocation is performed
-- 
2.26.2


From 8cd96b5a2e6301a681377497bad4251ab12aabf9 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <alobakin@pm.me>
Date: Wed, 17 Jun 2020 20:42:47 +0000
Subject: [PATCH 41/49] net: ethtool: add missing NETIF_F_GSO_FRAGLIST feature
 string

[ Upstream commit eddbf5d0204e550ee59de02bdc19fe90d4203dd6 ]

Commit 3b33583265ed ("net: Add fraglist GRO/GSO feature flags") missed
an entry for NETIF_F_GSO_FRAGLIST in netdev_features_strings array. As
a result, fraglist GSO feature is not shown in 'ethtool -k' output and
can't be toggled on/off.
The fix is trivial.

Fixes: 3b33583265ed ("net: Add fraglist GRO/GSO feature flags")
Signed-off-by: Alexander Lobakin <alobakin@pm.me>
Reviewed-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ethtool/common.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index 7f7fff88c5d3..aaecfc916a4d 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -44,6 +44,7 @@ const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = {
 	[NETIF_F_GSO_SCTP_BIT] =	 "tx-sctp-segmentation",
 	[NETIF_F_GSO_ESP_BIT] =		 "tx-esp-segmentation",
 	[NETIF_F_GSO_UDP_L4_BIT] =	 "tx-udp-segmentation",
+	[NETIF_F_GSO_FRAGLIST_BIT] =	 "tx-gso-list",
 
 	[NETIF_F_FCOE_CRC_BIT] =         "tx-checksum-fcoe-crc",
 	[NETIF_F_SCTP_CRC_BIT] =        "tx-checksum-sctp",
-- 
2.26.2


From af79226ce6ceff9c62e0bdc23bca4dd252707609 Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@microchip.com>
Date: Wed, 24 Jun 2020 13:08:17 +0300
Subject: [PATCH 42/49] net: macb: call pm_runtime_put_sync on failure path

[ Upstream commit 0eaf228d574bd82a9aed73e3953bfb81721f4227 ]

Call pm_runtime_put_sync() on failure path of at91ether_open.

Fixes: e6a41c23df0d ("net: macb: ensure interface is not suspended on at91rm9200")
Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 257c4920cb88..5705359a3612 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -3837,7 +3837,7 @@ static int at91ether_open(struct net_device *dev)
 
 	ret = at91ether_start(dev);
 	if (ret)
-		return ret;
+		goto pm_exit;
 
 	/* Enable MAC interrupts */
 	macb_writel(lp, IER, MACB_BIT(RCOMP)	|
@@ -3850,11 +3850,15 @@ static int at91ether_open(struct net_device *dev)
 
 	ret = macb_phylink_connect(lp);
 	if (ret)
-		return ret;
+		goto pm_exit;
 
 	netif_start_queue(dev);
 
 	return 0;
+
+pm_exit:
+	pm_runtime_put_sync(&lp->pdev->dev);
+	return ret;
 }
 
 /* Close the interface */
-- 
2.26.2


From fc37904036022be201801ad31687431a516fc811 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Thu, 25 Jun 2020 09:18:16 +0200
Subject: [PATCH 43/49] net: phy: mscc: avoid skcipher API for single block AES
 encryption

[ Upstream commit 8acd2edbe0e8e36261d98d89ce91b810dd7f4b0d ]

The skcipher API dynamically instantiates the transformation object
on request that implements the requested algorithm optimally on the
given platform. This notion of optimality only matters for cases like
bulk network or disk encryption, where performance can be a bottleneck,
or in cases where the algorithm itself is not known at compile time.

In the mscc case, we are dealing with AES encryption of a single
block, and so neither concern applies, and we are better off using
the AES library interface, which is lightweight and safe for this
kind of use.

Note that the scatterlist API does not permit references to buffers
that are located on the stack, so the existing code is incorrect in
any case, but avoiding the skcipher and scatterlist APIs entirely is
the most straight-forward approach to fixing this.

Cc: Antoine Tenart <antoine.tenart@bootlin.com>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: Heiner Kallweit <hkallweit1@gmail.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: <stable@vger.kernel.org>
Fixes: 28c5107aa904e ("net: phy: mscc: macsec support")
Reviewed-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Tested-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/Kconfig            |  3 +--
 drivers/net/phy/mscc/mscc_macsec.c | 40 +++++++-----------------------
 2 files changed, 10 insertions(+), 33 deletions(-)

diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index 3fa33d27eeba..d140e3c93fe3 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -461,8 +461,7 @@ config MICROCHIP_T1_PHY
 config MICROSEMI_PHY
 	tristate "Microsemi PHYs"
 	depends on MACSEC || MACSEC=n
-	select CRYPTO_AES
-	select CRYPTO_ECB
+	select CRYPTO_LIB_AES if MACSEC
 	---help---
 	  Currently supports VSC8514, VSC8530, VSC8531, VSC8540 and VSC8541 PHYs
 
diff --git a/drivers/net/phy/mscc/mscc_macsec.c b/drivers/net/phy/mscc/mscc_macsec.c
index b4d3dc4068e2..d53ca884b5c9 100644
--- a/drivers/net/phy/mscc/mscc_macsec.c
+++ b/drivers/net/phy/mscc/mscc_macsec.c
@@ -10,7 +10,7 @@
 #include <linux/phy.h>
 #include <dt-bindings/net/mscc-phy-vsc8531.h>
 
-#include <crypto/skcipher.h>
+#include <crypto/aes.h>
 
 #include <net/macsec.h>
 
@@ -500,39 +500,17 @@ static u32 vsc8584_macsec_flow_context_id(struct macsec_flow *flow)
 static int vsc8584_macsec_derive_key(const u8 key[MACSEC_KEYID_LEN],
 				     u16 key_len, u8 hkey[16])
 {
-	struct crypto_skcipher *tfm = crypto_alloc_skcipher("ecb(aes)", 0, 0);
-	struct skcipher_request *req = NULL;
-	struct scatterlist src, dst;
-	DECLARE_CRYPTO_WAIT(wait);
-	u32 input[4] = {0};
+	const u8 input[AES_BLOCK_SIZE] = {0};
+	struct crypto_aes_ctx ctx;
 	int ret;
 
-	if (IS_ERR(tfm))
-		return PTR_ERR(tfm);
-
-	req = skcipher_request_alloc(tfm, GFP_KERNEL);
-	if (!req) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG |
-				      CRYPTO_TFM_REQ_MAY_SLEEP, crypto_req_done,
-				      &wait);
-	ret = crypto_skcipher_setkey(tfm, key, key_len);
-	if (ret < 0)
-		goto out;
-
-	sg_init_one(&src, input, 16);
-	sg_init_one(&dst, hkey, 16);
-	skcipher_request_set_crypt(req, &src, &dst, 16, NULL);
-
-	ret = crypto_wait_req(crypto_skcipher_encrypt(req), &wait);
+	ret = aes_expandkey(&ctx, key, key_len);
+	if (ret)
+		return ret;
 
-out:
-	skcipher_request_free(req);
-	crypto_free_skcipher(tfm);
-	return ret;
+	aes_encrypt(&ctx, hkey, input);
+	memzero_explicit(&ctx, sizeof(ctx));
+	return 0;
 }
 
 static int vsc8584_macsec_transformation(struct phy_device *phydev,
-- 
2.26.2


From 627fefcd77b9f5074eae50f99777c6072b6276b1 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 19 Jun 2020 11:47:46 -0700
Subject: [PATCH 44/49] of: of_mdio: Correct loop scanning logic

[ Upstream commit 5a8d7f126c97d04d893f5e5be2b286437a0d01b0 ]

Commit 209c65b61d94 ("drivers/of/of_mdio.c:fix of_mdiobus_register()")
introduced a break of the loop on the premise that a successful
registration should exit the loop. The premise is correct but not to
code, because rc && rc != -ENODEV is just a special error condition,
that means we would exit the loop even with rc == -ENODEV which is
absolutely not correct since this is the error code to indicate to the
MDIO bus layer that scanning should continue.

Fix this by explicitly checking for rc = 0 as the only valid condition
to break out of the loop.

Fixes: 209c65b61d94 ("drivers/of/of_mdio.c:fix of_mdiobus_register()")
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/of/of_mdio.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c
index 9f982c0627a0..95a3bb2e5eab 100644
--- a/drivers/of/of_mdio.c
+++ b/drivers/of/of_mdio.c
@@ -303,10 +303,15 @@ int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np)
 				 child, addr);
 
 			if (of_mdiobus_child_is_phy(child)) {
+				/* -ENODEV is the return code that PHYLIB has
+				 * standardized on to indicate that bus
+				 * scanning should continue.
+				 */
 				rc = of_mdiobus_register_phy(mdio, child, addr);
-				if (rc && rc != -ENODEV)
+				if (!rc)
+					break;
+				if (rc != -ENODEV)
 					goto unregister;
-				break;
 			}
 		}
 	}
-- 
2.26.2


From 274e4ad60904901da8d96137f1b5dabdf1f47fb8 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Tue, 23 Jun 2020 03:59:45 -0600
Subject: [PATCH 45/49] wireguard: device: avoid circular netns references

[ Upstream commit 900575aa33a3eaaef802b31de187a85c4a4b4bd0 ]

Before, we took a reference to the creating netns if the new netns was
different. This caused issues with circular references, with two
wireguard interfaces swapping namespaces. The solution is to rather not
take any extra references at all, but instead simply invalidate the
creating netns pointer when that netns is deleted.

In order to prevent this from happening again, this commit improves the
rough object leak tracking by allowing it to account for created and
destroyed interfaces, aside from just peers and keys. That then makes it
possible to check for the object leak when having two interfaces take a
reference to each others' namespaces.

Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wireguard/device.c             | 58 ++++++++++------------
 drivers/net/wireguard/device.h             |  3 +-
 drivers/net/wireguard/netlink.c            | 14 ++++--
 drivers/net/wireguard/socket.c             | 25 +++++++---
 tools/testing/selftests/wireguard/netns.sh | 13 ++++-
 5 files changed, 67 insertions(+), 46 deletions(-)

diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c
index 3ac3f8570ca1..a8f151b1b5fa 100644
--- a/drivers/net/wireguard/device.c
+++ b/drivers/net/wireguard/device.c
@@ -45,17 +45,18 @@ static int wg_open(struct net_device *dev)
 	if (dev_v6)
 		dev_v6->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_NONE;
 
+	mutex_lock(&wg->device_update_lock);
 	ret = wg_socket_init(wg, wg->incoming_port);
 	if (ret < 0)
-		return ret;
-	mutex_lock(&wg->device_update_lock);
+		goto out;
 	list_for_each_entry(peer, &wg->peer_list, peer_list) {
 		wg_packet_send_staged_packets(peer);
 		if (peer->persistent_keepalive_interval)
 			wg_packet_send_keepalive(peer);
 	}
+out:
 	mutex_unlock(&wg->device_update_lock);
-	return 0;
+	return ret;
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -225,6 +226,7 @@ static void wg_destruct(struct net_device *dev)
 	list_del(&wg->device_list);
 	rtnl_unlock();
 	mutex_lock(&wg->device_update_lock);
+	rcu_assign_pointer(wg->creating_net, NULL);
 	wg->incoming_port = 0;
 	wg_socket_reinit(wg, NULL, NULL);
 	/* The final references are cleared in the below calls to destroy_workqueue. */
@@ -240,13 +242,11 @@ static void wg_destruct(struct net_device *dev)
 	skb_queue_purge(&wg->incoming_handshakes);
 	free_percpu(dev->tstats);
 	free_percpu(wg->incoming_handshakes_worker);
-	if (wg->have_creating_net_ref)
-		put_net(wg->creating_net);
 	kvfree(wg->index_hashtable);
 	kvfree(wg->peer_hashtable);
 	mutex_unlock(&wg->device_update_lock);
 
-	pr_debug("%s: Interface deleted\n", dev->name);
+	pr_debug("%s: Interface destroyed\n", dev->name);
 	free_netdev(dev);
 }
 
@@ -292,7 +292,7 @@ static int wg_newlink(struct net *src_net, struct net_device *dev,
 	struct wg_device *wg = netdev_priv(dev);
 	int ret = -ENOMEM;
 
-	wg->creating_net = src_net;
+	rcu_assign_pointer(wg->creating_net, src_net);
 	init_rwsem(&wg->static_identity.lock);
 	mutex_init(&wg->socket_update_lock);
 	mutex_init(&wg->device_update_lock);
@@ -393,30 +393,26 @@ static struct rtnl_link_ops link_ops __read_mostly = {
 	.newlink		= wg_newlink,
 };
 
-static int wg_netdevice_notification(struct notifier_block *nb,
-				     unsigned long action, void *data)
+static void wg_netns_pre_exit(struct net *net)
 {
-	struct net_device *dev = ((struct netdev_notifier_info *)data)->dev;
-	struct wg_device *wg = netdev_priv(dev);
-
-	ASSERT_RTNL();
-
-	if (action != NETDEV_REGISTER || dev->netdev_ops != &netdev_ops)
-		return 0;
+	struct wg_device *wg;
 
-	if (dev_net(dev) == wg->creating_net && wg->have_creating_net_ref) {
-		put_net(wg->creating_net);
-		wg->have_creating_net_ref = false;
-	} else if (dev_net(dev) != wg->creating_net &&
-		   !wg->have_creating_net_ref) {
-		wg->have_creating_net_ref = true;
-		get_net(wg->creating_net);
+	rtnl_lock();
+	list_for_each_entry(wg, &device_list, device_list) {
+		if (rcu_access_pointer(wg->creating_net) == net) {
+			pr_debug("%s: Creating namespace exiting\n", wg->dev->name);
+			netif_carrier_off(wg->dev);
+			mutex_lock(&wg->device_update_lock);
+			rcu_assign_pointer(wg->creating_net, NULL);
+			wg_socket_reinit(wg, NULL, NULL);
+			mutex_unlock(&wg->device_update_lock);
+		}
 	}
-	return 0;
+	rtnl_unlock();
 }
 
-static struct notifier_block netdevice_notifier = {
-	.notifier_call = wg_netdevice_notification
+static struct pernet_operations pernet_ops = {
+	.pre_exit = wg_netns_pre_exit
 };
 
 int __init wg_device_init(void)
@@ -429,18 +425,18 @@ int __init wg_device_init(void)
 		return ret;
 #endif
 
-	ret = register_netdevice_notifier(&netdevice_notifier);
+	ret = register_pernet_device(&pernet_ops);
 	if (ret)
 		goto error_pm;
 
 	ret = rtnl_link_register(&link_ops);
 	if (ret)
-		goto error_netdevice;
+		goto error_pernet;
 
 	return 0;
 
-error_netdevice:
-	unregister_netdevice_notifier(&netdevice_notifier);
+error_pernet:
+	unregister_pernet_device(&pernet_ops);
 error_pm:
 #ifdef CONFIG_PM_SLEEP
 	unregister_pm_notifier(&pm_notifier);
@@ -451,7 +447,7 @@ int __init wg_device_init(void)
 void wg_device_uninit(void)
 {
 	rtnl_link_unregister(&link_ops);
-	unregister_netdevice_notifier(&netdevice_notifier);
+	unregister_pernet_device(&pernet_ops);
 #ifdef CONFIG_PM_SLEEP
 	unregister_pm_notifier(&pm_notifier);
 #endif
diff --git a/drivers/net/wireguard/device.h b/drivers/net/wireguard/device.h
index b15a8be9d816..4d0144e16947 100644
--- a/drivers/net/wireguard/device.h
+++ b/drivers/net/wireguard/device.h
@@ -40,7 +40,7 @@ struct wg_device {
 	struct net_device *dev;
 	struct crypt_queue encrypt_queue, decrypt_queue;
 	struct sock __rcu *sock4, *sock6;
-	struct net *creating_net;
+	struct net __rcu *creating_net;
 	struct noise_static_identity static_identity;
 	struct workqueue_struct *handshake_receive_wq, *handshake_send_wq;
 	struct workqueue_struct *packet_crypt_wq;
@@ -56,7 +56,6 @@ struct wg_device {
 	unsigned int num_peers, device_update_gen;
 	u32 fwmark;
 	u16 incoming_port;
-	bool have_creating_net_ref;
 };
 
 int wg_device_init(void);
diff --git a/drivers/net/wireguard/netlink.c b/drivers/net/wireguard/netlink.c
index 802099c8828a..20a4f3c0a0a1 100644
--- a/drivers/net/wireguard/netlink.c
+++ b/drivers/net/wireguard/netlink.c
@@ -511,11 +511,15 @@ static int wg_set_device(struct sk_buff *skb, struct genl_info *info)
 	if (flags & ~__WGDEVICE_F_ALL)
 		goto out;
 
-	ret = -EPERM;
-	if ((info->attrs[WGDEVICE_A_LISTEN_PORT] ||
-	     info->attrs[WGDEVICE_A_FWMARK]) &&
-	    !ns_capable(wg->creating_net->user_ns, CAP_NET_ADMIN))
-		goto out;
+	if (info->attrs[WGDEVICE_A_LISTEN_PORT] || info->attrs[WGDEVICE_A_FWMARK]) {
+		struct net *net;
+		rcu_read_lock();
+		net = rcu_dereference(wg->creating_net);
+		ret = !net || !ns_capable(net->user_ns, CAP_NET_ADMIN) ? -EPERM : 0;
+		rcu_read_unlock();
+		if (ret)
+			goto out;
+	}
 
 	++wg->device_update_gen;
 
diff --git a/drivers/net/wireguard/socket.c b/drivers/net/wireguard/socket.c
index f9018027fc13..c33e2c81635f 100644
--- a/drivers/net/wireguard/socket.c
+++ b/drivers/net/wireguard/socket.c
@@ -347,6 +347,7 @@ static void set_sock_opts(struct socket *sock)
 
 int wg_socket_init(struct wg_device *wg, u16 port)
 {
+	struct net *net;
 	int ret;
 	struct udp_tunnel_sock_cfg cfg = {
 		.sk_user_data = wg,
@@ -371,37 +372,47 @@ int wg_socket_init(struct wg_device *wg, u16 port)
 	};
 #endif
 
+	rcu_read_lock();
+	net = rcu_dereference(wg->creating_net);
+	net = net ? maybe_get_net(net) : NULL;
+	rcu_read_unlock();
+	if (unlikely(!net))
+		return -ENONET;
+
 #if IS_ENABLED(CONFIG_IPV6)
 retry:
 #endif
 
-	ret = udp_sock_create(wg->creating_net, &port4, &new4);
+	ret = udp_sock_create(net, &port4, &new4);
 	if (ret < 0) {
 		pr_err("%s: Could not create IPv4 socket\n", wg->dev->name);
-		return ret;
+		goto out;
 	}
 	set_sock_opts(new4);
-	setup_udp_tunnel_sock(wg->creating_net, new4, &cfg);
+	setup_udp_tunnel_sock(net, new4, &cfg);
 
 #if IS_ENABLED(CONFIG_IPV6)
 	if (ipv6_mod_enabled()) {
 		port6.local_udp_port = inet_sk(new4->sk)->inet_sport;
-		ret = udp_sock_create(wg->creating_net, &port6, &new6);
+		ret = udp_sock_create(net, &port6, &new6);
 		if (ret < 0) {
 			udp_tunnel_sock_release(new4);
 			if (ret == -EADDRINUSE && !port && retries++ < 100)
 				goto retry;
 			pr_err("%s: Could not create IPv6 socket\n",
 			       wg->dev->name);
-			return ret;
+			goto out;
 		}
 		set_sock_opts(new6);
-		setup_udp_tunnel_sock(wg->creating_net, new6, &cfg);
+		setup_udp_tunnel_sock(net, new6, &cfg);
 	}
 #endif
 
 	wg_socket_reinit(wg, new4->sk, new6 ? new6->sk : NULL);
-	return 0;
+	ret = 0;
+out:
+	put_net(net);
+	return ret;
 }
 
 void wg_socket_reinit(struct wg_device *wg, struct sock *new4,
diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh
index 17a1f53ceba0..d77f4829f1e0 100755
--- a/tools/testing/selftests/wireguard/netns.sh
+++ b/tools/testing/selftests/wireguard/netns.sh
@@ -587,9 +587,20 @@ ip0 link set wg0 up
 kill $ncat_pid
 ip0 link del wg0
 
+# Ensure there aren't circular reference loops
+ip1 link add wg1 type wireguard
+ip2 link add wg2 type wireguard
+ip1 link set wg1 netns $netns2
+ip2 link set wg2 netns $netns1
+pp ip netns delete $netns1
+pp ip netns delete $netns2
+pp ip netns add $netns1
+pp ip netns add $netns2
+
+sleep 2 # Wait for cleanup and grace periods
 declare -A objects
 while read -t 0.1 -r line 2>/dev/null || [[ $? -ne 142 ]]; do
-	[[ $line =~ .*(wg[0-9]+:\ [A-Z][a-z]+\ [0-9]+)\ .*(created|destroyed).* ]] || continue
+	[[ $line =~ .*(wg[0-9]+:\ [A-Z][a-z]+\ ?[0-9]*)\ .*(created|destroyed).* ]] || continue
 	objects["${BASH_REMATCH[1]}"]+="${BASH_REMATCH[2]}"
 done < /dev/kmsg
 alldeleted=1
-- 
2.26.2


From e6bfec8fcd2a77e07341baab4cee71b54cfe4a3f Mon Sep 17 00:00:00 2001
From: Martin <martin.varghese@nokia.com>
Date: Wed, 17 Jun 2020 22:30:23 +0530
Subject: [PATCH 46/49] bareudp: Fixed multiproto mode configuration

[ Upstream commit 4c98045c9b74feab837be58986c0517d3cc661f1 ]

Code to handle multiproto configuration is missing.

Fixes: 4b5f67232d95 ("net: Special handling for IP & MPLS")
Signed-off-by: Martin <martin.varghese@nokia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bareudp.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c
index 5d3c691a1c66..3dd46cd55114 100644
--- a/drivers/net/bareudp.c
+++ b/drivers/net/bareudp.c
@@ -572,6 +572,9 @@ static int bareudp2info(struct nlattr *data[], struct bareudp_conf *conf,
 	if (data[IFLA_BAREUDP_SRCPORT_MIN])
 		conf->sport_min =  nla_get_u16(data[IFLA_BAREUDP_SRCPORT_MIN]);
 
+	if (data[IFLA_BAREUDP_MULTIPROTO_MODE])
+		conf->multi_proto_mode = true;
+
 	return 0;
 }
 
-- 
2.26.2


From 52a583b561336b05594be6f4484c70ab62c87cef Mon Sep 17 00:00:00 2001
From: Shannon Nelson <snelson@pensando.io>
Date: Thu, 25 Jun 2020 22:58:37 -0700
Subject: [PATCH 47/49] ionic: update the queue count on open

[ Upstream commit fa48494cce5f6360b0f8683cdf258fb45c666287 ]

Let the network stack know the real number of queues that
we are using.

v2: added error checking

Fixes: 49d3b493673a ("ionic: disable the queues on link down")
Signed-off-by: Shannon Nelson <snelson@pensando.io>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/pensando/ionic/ionic_lif.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index 7aa037c3fe02..2729b0bb1273 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -1653,6 +1653,14 @@ int ionic_open(struct net_device *netdev)
 	if (err)
 		goto err_out;
 
+	err = netif_set_real_num_tx_queues(netdev, lif->nxqs);
+	if (err)
+		goto err_txrx_deinit;
+
+	err = netif_set_real_num_rx_queues(netdev, lif->nxqs);
+	if (err)
+		goto err_txrx_deinit;
+
 	/* don't start the queues until we have link */
 	if (netif_carrier_ok(netdev)) {
 		err = ionic_start_queues(lif);
-- 
2.26.2


From a69bca20e9c438d1d702006e3bbc87a3f95494b1 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 17 Jun 2020 20:42:44 -0700
Subject: [PATCH 48/49] net: dsa: bcm_sf2: Fix node reference count

[ Upstream commit 8dbe4c5d5e40fe140221024f7b16bec9f310bf70 ]

of_find_node_by_name() will do an of_node_put() on the "from" argument.
With CONFIG_OF_DYNAMIC enabled which checks for device_node reference
counts, we would be getting a warning like this:

[    6.347230] refcount_t: increment on 0; use-after-free.
[    6.352498] WARNING: CPU: 3 PID: 77 at lib/refcount.c:156
refcount_inc_checked+0x38/0x44
[    6.360601] Modules linked in:
[    6.363661] CPU: 3 PID: 77 Comm: kworker/3:1 Tainted: G        W
5.4.46-gb78b3e9956e6 #13
[    6.372546] Hardware name: BCM97278SV (DT)
[    6.376649] Workqueue: events deferred_probe_work_func
[    6.381796] pstate: 60000005 (nZCv daif -PAN -UAO)
[    6.386595] pc : refcount_inc_checked+0x38/0x44
[    6.391133] lr : refcount_inc_checked+0x38/0x44
...
[    6.478791] Call trace:
[    6.481243]  refcount_inc_checked+0x38/0x44
[    6.485433]  kobject_get+0x3c/0x4c
[    6.488840]  of_node_get+0x24/0x34
[    6.492247]  of_irq_find_parent+0x3c/0xe0
[    6.496263]  of_irq_parse_one+0xe4/0x1d0
[    6.500191]  irq_of_parse_and_map+0x44/0x84
[    6.504381]  bcm_sf2_sw_probe+0x22c/0x844
[    6.508397]  platform_drv_probe+0x58/0xa8
[    6.512413]  really_probe+0x238/0x3fc
[    6.516081]  driver_probe_device+0x11c/0x12c
[    6.520358]  __device_attach_driver+0xa8/0x100
[    6.524808]  bus_for_each_drv+0xb4/0xd0
[    6.528650]  __device_attach+0xd0/0x164
[    6.532493]  device_initial_probe+0x24/0x30
[    6.536682]  bus_probe_device+0x38/0x98
[    6.540524]  deferred_probe_work_func+0xa8/0xd4
[    6.545061]  process_one_work+0x178/0x288
[    6.549078]  process_scheduled_works+0x44/0x48
[    6.553529]  worker_thread+0x218/0x270
[    6.557285]  kthread+0xdc/0xe4
[    6.560344]  ret_from_fork+0x10/0x18
[    6.563925] ---[ end trace 68f65caf69bb152a ]---

Fix this by adding a of_node_get() to increment the reference count
prior to the call.

Fixes: afa3b592953b ("net: dsa: bcm_sf2: Ensure correct sub-node is parsed")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index c7ac63f41918..946e41f020a5 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -1147,6 +1147,8 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev)
 	set_bit(0, priv->cfp.used);
 	set_bit(0, priv->cfp.unique);
 
+	/* Balance of_node_put() done by of_find_node_by_name() */
+	of_node_get(dn);
 	ports = of_find_node_by_name(dn, "ports");
 	if (ports) {
 		bcm_sf2_identify_ports(priv, ports);
-- 
2.26.2


From 77dc27da88bf00e11831457bbf0d10443ed29261 Mon Sep 17 00:00:00 2001
From: Dejin Zheng <zhengdejin5@gmail.com>
Date: Sat, 20 Jun 2020 22:55:34 +0800
Subject: [PATCH 49/49] net: phy: smsc: fix printing too many logs

[ Upstream commit 6d61f483f148b856d47a6c96d5d84054d5a9f849 ]

Commit 7ae7ad2f11ef47 ("net: phy: smsc: use phy_read_poll_timeout()
to simplify the code") will print a lot of logs as follows when Ethernet
cable is not connected:

[    4.473105] SMSC LAN8710/LAN8720 2188000.ethernet-1:00: lan87xx_read_status failed: -110

When wait 640 ms for check ENERGYON bit, the timeout should not be
regarded as an actual error and an error message also should not be
printed. due to a hardware bug in LAN87XX device, it leads to unstable
detection of plugging in Ethernet cable when LAN87xx is in Energy Detect
Power-Down mode. the workaround for it involves, when the link is down,
and at each read_status() call:

- disable EDPD mode, forcing the PHY out of low-power mode
- waiting 640ms to see if we have any energy detected from the media
- re-enable entry to EDPD mode

This is presumably enough to allow the PHY to notice that a cable is
connected, and resume normal operations to negotiate with the partner.
The problem is that when no media is detected, the 640ms wait times
out and this commit was modified to prints an error message. it is an
inappropriate conversion by used phy_read_poll_timeout() to introduce
this bug. so fix this issue by use read_poll_timeout() to replace
phy_read_poll_timeout().

Fixes: 7ae7ad2f11ef47 ("net: phy: smsc: use phy_read_poll_timeout() to simplify the code")
Reported-by: Kevin Groeneveld <kgroeneveld@gmail.com>
Signed-off-by: Dejin Zheng <zhengdejin5@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/smsc.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c
index 93da7d3d0954..74568ae16125 100644
--- a/drivers/net/phy/smsc.c
+++ b/drivers/net/phy/smsc.c
@@ -122,10 +122,13 @@ static int lan87xx_read_status(struct phy_device *phydev)
 		if (rc < 0)
 			return rc;
 
-		/* Wait max 640 ms to detect energy */
-		phy_read_poll_timeout(phydev, MII_LAN83C185_CTRL_STATUS, rc,
-				      rc & MII_LAN83C185_ENERGYON, 10000,
-				      640000, true);
+		/* Wait max 640 ms to detect energy and the timeout is not
+		 * an actual error.
+		 */
+		read_poll_timeout(phy_read, rc,
+				  rc & MII_LAN83C185_ENERGYON || rc < 0,
+				  10000, 640000, true, phydev,
+				  MII_LAN83C185_CTRL_STATUS);
 		if (rc < 0)
 			return rc;
 
-- 
2.26.2

Re: [PATCHES] Networking

[Greg KH]

On Sat, Jun 27, 2020 at 05:55:12PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v5.4 and v5.7
> -stable, respectively.

All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 105 bytes --]


Please queue up the following networking bug fixes for v5.4 and
v5.7 -stable, respectively.

Thank you!

[-- Attachment #2: net_54.mbox --]
[-- Type: Application/Octet-Stream, Size: 118501 bytes --]

From 9fc4b27d38c41f44167b5074500c040426f9ecad Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Fri, 10 Jul 2020 12:55:08 +0200
Subject: [PATCH 01/29] bnxt_en: fix NULL dereference in case SR-IOV
 configuration fails

[ Upstream commit c8b1d7436045d3599bae56aef1682813ecccaad7 ]

we need to set 'active_vfs' back to 0, if something goes wrong during the
allocation of SR-IOV resources: otherwise, further VF configurations will
wrongly assume that bp->pf.vf[x] are valid memory locations, and commands
like the ones in the following sequence:

 # echo 2 >/sys/bus/pci/devices/${ADDR}/sriov_numvfs
 # ip link set dev ens1f0np0 up
 # ip link set dev ens1f0np0 vf 0 trust on

will cause a kernel crash similar to this:

 bnxt_en 0000:3b:00.0: not enough MMIO resources for SR-IOV
 BUG: kernel NULL pointer dereference, address: 0000000000000014
 #PF: supervisor read access in kernel mode
 #PF: error_code(0x0000) - not-present page
 PGD 0 P4D 0
 Oops: 0000 [#1] SMP PTI
 CPU: 43 PID: 2059 Comm: ip Tainted: G          I       5.8.0-rc2.upstream+ #871
 Hardware name: Dell Inc. PowerEdge R740/08D89F, BIOS 2.2.11 06/13/2019
 RIP: 0010:bnxt_set_vf_trust+0x5b/0x110 [bnxt_en]
 Code: 44 24 58 31 c0 e8 f5 fb ff ff 85 c0 0f 85 b6 00 00 00 48 8d 1c 5b 41 89 c6 b9 0b 00 00 00 48 c1 e3 04 49 03 9c 24 f0 0e 00 00 <8b> 43 14 89 c2 83 c8 10 83 e2 ef 45 84 ed 49 89 e5 0f 44 c2 4c 89
 RSP: 0018:ffffac6246a1f570 EFLAGS: 00010246
 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 000000000000000b
 RDX: 0000000000000001 RSI: 0000000000000000 RDI: ffff98b28f538900
 RBP: ffff98b28f538900 R08: 0000000000000000 R09: 0000000000000008
 R10: ffffffffb9515be0 R11: ffffac6246a1f678 R12: ffff98b28f538000
 R13: 0000000000000001 R14: 0000000000000000 R15: ffffffffc05451e0
 FS:  00007fde0f688800(0000) GS:ffff98baffd40000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000000014 CR3: 000000104bb0a003 CR4: 00000000007606e0
 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
 PKRU: 55555554
 Call Trace:
  do_setlink+0x994/0xfe0
  __rtnl_newlink+0x544/0x8d0
  rtnl_newlink+0x47/0x70
  rtnetlink_rcv_msg+0x29f/0x350
  netlink_rcv_skb+0x4a/0x110
  netlink_unicast+0x21d/0x300
  netlink_sendmsg+0x329/0x450
  sock_sendmsg+0x5b/0x60
  ____sys_sendmsg+0x204/0x280
  ___sys_sendmsg+0x88/0xd0
  __sys_sendmsg+0x5e/0xa0
  do_syscall_64+0x47/0x80
  entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: c0c050c58d840 ("bnxt_en: New Broadcom ethernet driver.")
Reported-by: Fei Liu <feliu@redhat.com>
CC: Jonathan Toppins <jtoppins@redhat.com>
CC: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Acked-by: Jonathan Toppins <jtoppins@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index 1046b22220a3..452be9749827 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -398,6 +398,7 @@ static void bnxt_free_vf_resources(struct bnxt *bp)
 		}
 	}
 
+	bp->pf.active_vfs = 0;
 	kfree(bp->pf.vf);
 	bp->pf.vf = NULL;
 }
@@ -833,7 +834,6 @@ void bnxt_sriov_disable(struct bnxt *bp)
 
 	bnxt_free_vf_resources(bp);
 
-	bp->pf.active_vfs = 0;
 	/* Reclaim all resources for the PF. */
 	rtnl_lock();
 	bnxt_restore_pf_fw_resources(bp);
-- 
2.26.2


From 008a01234c6fcedd78398dd45529776f341cdb80 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Linus=20L=C3=BCssing?= <linus.luessing@c0d3.blue>
Date: Sun, 5 Jul 2020 21:10:17 +0200
Subject: [PATCH 02/29] bridge: mcast: Fix MLD2 Report IPv6 payload length
 check
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 5fc6266af7b427243da24f3443a50cd4584aac06 ]

Commit e57f61858b7c ("net: bridge: mcast: fix stale nsrcs pointer in
igmp3/mld2 report handling") introduced a bug in the IPv6 header payload
length check which would potentially lead to rejecting a valid MLD2 Report:

The check needs to take into account the 2 bytes for the "Number of
Sources" field in the "Multicast Address Record" before reading it.
And not the size of a pointer to this field.

Fixes: e57f61858b7c ("net: bridge: mcast: fix stale nsrcs pointer in igmp3/mld2 report handling")
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: Linus Lüssing <linus.luessing@c0d3.blue>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index ad12fe3fca8c..ee2902b51d45 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1007,7 +1007,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br,
 		nsrcs_offset = len + offsetof(struct mld2_grec, grec_nsrcs);
 
 		if (skb_transport_offset(skb) + ipv6_transport_len(skb) <
-		    nsrcs_offset + sizeof(_nsrcs))
+		    nsrcs_offset + sizeof(__nsrcs))
 			return -EINVAL;
 
 		_nsrcs = skb_header_pointer(skb, nsrcs_offset,
-- 
2.26.2


From d95ee18c258748d5b92313d01c32c35611612d37 Mon Sep 17 00:00:00 2001
From: Sean Tranchetti <stranche@codeaurora.org>
Date: Tue, 30 Jun 2020 11:50:17 -0600
Subject: [PATCH 03/29] genetlink: remove genl_bind

[ Upstream commit 1e82a62fec613844da9e558f3493540a5b7a7b67 ]

A potential deadlock can occur during registering or unregistering a
new generic netlink family between the main nl_table_lock and the
cb_lock where each thread wants the lock held by the other, as
demonstrated below.

1) Thread 1 is performing a netlink_bind() operation on a socket. As part
   of this call, it will call netlink_lock_table(), incrementing the
   nl_table_users count to 1.
2) Thread 2 is registering (or unregistering) a genl_family via the
   genl_(un)register_family() API. The cb_lock semaphore will be taken for
   writing.
3) Thread 1 will call genl_bind() as part of the bind operation to handle
   subscribing to GENL multicast groups at the request of the user. It will
   attempt to take the cb_lock semaphore for reading, but it will fail and
   be scheduled away, waiting for Thread 2 to finish the write.
4) Thread 2 will call netlink_table_grab() during the (un)registration
   call. However, as Thread 1 has incremented nl_table_users, it will not
   be able to proceed, and both threads will be stuck waiting for the
   other.

genl_bind() is a noop, unless a genl_family implements the mcast_bind()
function to handle setting up family-specific multicast operations. Since
no one in-tree uses this functionality as Cong pointed out, simply removing
the genl_bind() function will remove the possibility for deadlock, as there
is no attempt by Thread 1 above to take the cb_lock semaphore.

Fixes: c380d9a7afff ("genetlink: pass multicast bind/unbind to families")
Suggested-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Johannes Berg <johannes.berg@intel.com>
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Sean Tranchetti <stranche@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/genetlink.h |  8 -------
 net/netlink/genetlink.c | 49 -----------------------------------------
 2 files changed, 57 deletions(-)

diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 9292f1c588b7..2d9e67a69cbe 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -35,12 +35,6 @@ struct genl_info;
  *	do additional, common, filtering and return an error
  * @post_doit: called after an operation's doit callback, it may
  *	undo operations done by pre_doit, for example release locks
- * @mcast_bind: a socket bound to the given multicast group (which
- *	is given as the offset into the groups array)
- * @mcast_unbind: a socket was unbound from the given multicast group.
- *	Note that unbind() will not be called symmetrically if the
- *	generic netlink family is removed while there are still open
- *	sockets.
  * @attrbuf: buffer to store parsed attributes (private)
  * @mcgrps: multicast groups used by this family
  * @n_mcgrps: number of multicast groups
@@ -64,8 +58,6 @@ struct genl_family {
 	void			(*post_doit)(const struct genl_ops *ops,
 					     struct sk_buff *skb,
 					     struct genl_info *info);
-	int			(*mcast_bind)(struct net *net, int group);
-	void			(*mcast_unbind)(struct net *net, int group);
 	struct nlattr **	attrbuf;	/* private */
 	const struct genl_ops *	ops;
 	const struct genl_multicast_group *mcgrps;
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index efccd1ac9a66..102b8d6b5612 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -989,60 +989,11 @@ static struct genl_family genl_ctrl __ro_after_init = {
 	.netnsok = true,
 };
 
-static int genl_bind(struct net *net, int group)
-{
-	struct genl_family *f;
-	int err = -ENOENT;
-	unsigned int id;
-
-	down_read(&cb_lock);
-
-	idr_for_each_entry(&genl_fam_idr, f, id) {
-		if (group >= f->mcgrp_offset &&
-		    group < f->mcgrp_offset + f->n_mcgrps) {
-			int fam_grp = group - f->mcgrp_offset;
-
-			if (!f->netnsok && net != &init_net)
-				err = -ENOENT;
-			else if (f->mcast_bind)
-				err = f->mcast_bind(net, fam_grp);
-			else
-				err = 0;
-			break;
-		}
-	}
-	up_read(&cb_lock);
-
-	return err;
-}
-
-static void genl_unbind(struct net *net, int group)
-{
-	struct genl_family *f;
-	unsigned int id;
-
-	down_read(&cb_lock);
-
-	idr_for_each_entry(&genl_fam_idr, f, id) {
-		if (group >= f->mcgrp_offset &&
-		    group < f->mcgrp_offset + f->n_mcgrps) {
-			int fam_grp = group - f->mcgrp_offset;
-
-			if (f->mcast_unbind)
-				f->mcast_unbind(net, fam_grp);
-			break;
-		}
-	}
-	up_read(&cb_lock);
-}
-
 static int __net_init genl_pernet_init(struct net *net)
 {
 	struct netlink_kernel_cfg cfg = {
 		.input		= genl_rcv,
 		.flags		= NL_CFG_F_NONROOT_RECV,
-		.bind		= genl_bind,
-		.unbind		= genl_unbind,
 	};
 
 	/* we'll bump the group number right afterwards */
-- 
2.26.2


From e73ae39b5a156edcb9f1bc6ad0fca7fa5b388079 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 3 Jul 2020 17:00:32 +0200
Subject: [PATCH 04/29] ipv4: fill fl4_icmp_{type,code} in ping_v4_sendmsg

[ Upstream commit 5eff06902394425c722f0a44d9545909a8800f79 ]

IPv4 ping sockets don't set fl4.fl4_icmp_{type,code}, which leads to
incomplete IPsec ACQUIRE messages being sent to userspace. Currently,
both raw sockets and IPv6 ping sockets set those fields.

Expected output of "ip xfrm monitor":
    acquire proto esp
      sel src 10.0.2.15/32 dst 8.8.8.8/32 proto icmp type 8 code 0 dev ens4
      policy src 10.0.2.15/32 dst 8.8.8.8/32
        <snip>

Currently with ping sockets:
    acquire proto esp
      sel src 10.0.2.15/32 dst 8.8.8.8/32 proto icmp type 0 code 0 dev ens4
      policy src 10.0.2.15/32 dst 8.8.8.8/32
        <snip>

The Libreswan test suite found this problem after Fedora changed the
value for the sysctl net.ipv4.ping_group_range.

Fixes: c319b4d76b9e ("net: ipv4: add IPPROTO_ICMP socket kind")
Reported-by: Paul Wouters <pwouters@redhat.com>
Tested-by: Paul Wouters <pwouters@redhat.com>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ping.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 535427292194..df6fbefe44d4 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -786,6 +786,9 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 			   inet_sk_flowi_flags(sk), faddr, saddr, 0, 0,
 			   sk->sk_uid);
 
+	fl4.fl4_icmp_type = user_icmph.type;
+	fl4.fl4_icmp_code = user_icmph.code;
+
 	security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
 	rt = ip_route_output_flow(net, &fl4, sk);
 	if (IS_ERR(rt)) {
-- 
2.26.2


From 6db2e0893235385732823f42e7871418ab5906e7 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@kernel.org>
Date: Mon, 6 Jul 2020 11:45:07 -0600
Subject: [PATCH 05/29] ipv6: fib6_select_path can not use out path for nexthop
 objects

[ Upstream commit 34fe5a1cf95c3f114068fc16d919c9cf4b00e428 ]

Brian reported a crash in IPv6 code when using rpfilter with a setup
running FRR and external nexthop objects. The root cause of the crash
is fib6_select_path setting fib6_nh in the result to NULL because of
an improper check for nexthop objects.

More specifically, rpfilter invokes ip6_route_lookup with flowi6_oif
set causing fib6_select_path to be called with have_oif_match set.
fib6_select_path has early check on have_oif_match and jumps to the
out label which presumes a builtin fib6_nh. This path is invalid for
nexthop objects; for external nexthops fib6_select_path needs to just
return if the fib6_nh has already been set in the result otherwise it
returns after the call to nexthop_path_fib6_result. Update the check
on have_oif_match to not bail on external nexthops.

Update selftests for this problem.

Fixes: f88d8ea67fbd ("ipv6: Plumb support for nexthop object in a fib6_info")
Reported-by: Brian Rak <brak@choopa.com>
Signed-off-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c                            |  5 ++++-
 tools/testing/selftests/net/fib_nexthops.sh | 13 +++++++++++++
 2 files changed, 17 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 3b4af0a8bca6..90042cad61ec 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -431,9 +431,12 @@ void fib6_select_path(const struct net *net, struct fib6_result *res,
 	struct fib6_info *sibling, *next_sibling;
 	struct fib6_info *match = res->f6i;
 
-	if ((!match->fib6_nsiblings && !match->nh) || have_oif_match)
+	if (!match->nh && (!match->fib6_nsiblings || have_oif_match))
 		goto out;
 
+	if (match->nh && have_oif_match && res->nh)
+		return;
+
 	/* We might have already computed the hash for ICMPv6 errors. In such
 	 * case it will always be non-zero. Otherwise now is the time to do it.
 	 */
diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh
index 6560ed796ac4..09830b88ec8c 100755
--- a/tools/testing/selftests/net/fib_nexthops.sh
+++ b/tools/testing/selftests/net/fib_nexthops.sh
@@ -512,6 +512,19 @@ ipv6_fcnal_runtime()
 	run_cmd "$IP nexthop add id 86 via 2001:db8:91::2 dev veth1"
 	run_cmd "$IP ro add 2001:db8:101::1/128 nhid 81"
 
+	# rpfilter and default route
+	$IP nexthop flush >/dev/null 2>&1
+	run_cmd "ip netns exec me ip6tables -t mangle -I PREROUTING 1 -m rpfilter --invert -j DROP"
+	run_cmd "$IP nexthop add id 91 via 2001:db8:91::2 dev veth1"
+	run_cmd "$IP nexthop add id 92 via 2001:db8:92::2 dev veth3"
+	run_cmd "$IP nexthop add id 93 group 91/92"
+	run_cmd "$IP -6 ro add default nhid 91"
+	run_cmd "ip netns exec me ping -c1 -w1 2001:db8:101::1"
+	log_test $? 0 "Nexthop with default route and rpfilter"
+	run_cmd "$IP -6 ro replace default nhid 93"
+	run_cmd "ip netns exec me ping -c1 -w1 2001:db8:101::1"
+	log_test $? 0 "Nexthop with multipath default route and rpfilter"
+
 	# TO-DO:
 	# existing route with old nexthop; append route with new nexthop
 	# existing route with old nexthop; replace route with new
-- 
2.26.2


From c35d47aed855b1b1caadd7b52a3ea5afeb213059 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@kernel.org>
Date: Tue, 7 Jul 2020 07:39:24 -0600
Subject: [PATCH 06/29] ipv6: Fix use of anycast address with loopback

[ Upstream commit aea23c323d89836bcdcee67e49def997ffca043b ]

Thomas reported a regression with IPv6 and anycast using the following
reproducer:

    echo 1 >  /proc/sys/net/ipv6/conf/all/forwarding
    ip -6 a add fc12::1/16 dev lo
    sleep 2
    echo "pinging lo"
    ping6 -c 2 fc12::

The conversion of addrconf_f6i_alloc to use ip6_route_info_create missed
the use of fib6_is_reject which checks addresses added to the loopback
interface and sets the REJECT flag as needed. Update fib6_is_reject for
loopback checks to handle RTF_ANYCAST addresses.

Fixes: c7a1ce397ada ("ipv6: Change addrconf_f6i_alloc to use ip6_route_info_create")
Reported-by: thomas.gambier@nexedi.com
Signed-off-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 90042cad61ec..94ade43d5a45 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3409,7 +3409,7 @@ static bool fib6_is_reject(u32 flags, struct net_device *dev, int addr_type)
 	if ((flags & RTF_REJECT) ||
 	    (dev && (dev->flags & IFF_LOOPBACK) &&
 	     !(addr_type & IPV6_ADDR_LOOPBACK) &&
-	     !(flags & RTF_LOCAL)))
+	     !(flags & (RTF_ANYCAST | RTF_LOCAL))))
 		return true;
 
 	return false;
-- 
2.26.2


From 08a65507218100ba310dab2292fddcae26cb7aa0 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 7 Jul 2020 02:02:32 +0800
Subject: [PATCH 07/29] l2tp: remove skb_dst_set() from l2tp_xmit_skb()

[ Upstream commit 27d53323664c549b5bb2dfaaf6f7ad6e0376a64e ]

In the tx path of l2tp, l2tp_xmit_skb() calls skb_dst_set() to set
skb's dst. However, it will eventually call inet6_csk_xmit() or
ip_queue_xmit() where skb's dst will be overwritten by:

   skb_dst_set_noref(skb, dst);

without releasing the old dst in skb. Then it causes dst/dev refcnt leak:

  unregister_netdevice: waiting for eth0 to become free. Usage count = 1

This can be reproduced by simply running:

  # modprobe l2tp_eth && modprobe l2tp_ip
  # sh ./tools/testing/selftests/net/l2tp.sh

So before going to inet6_csk_xmit() or ip_queue_xmit(), skb's dst
should be dropped. This patch is to fix it by removing skb_dst_set()
from l2tp_xmit_skb() and moving skb_dst_drop() into l2tp_xmit_core().

Fixes: 3557baabf280 ("[L2TP]: PPP over L2TP driver core")
Reported-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: James Chapman <jchapman@katalix.com>
Tested-by: James Chapman <jchapman@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 6dc3bfa12b1e..95805a6331be 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1030,6 +1030,7 @@ static void l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb,
 
 	/* Queue the packet to IP for output */
 	skb->ignore_df = 1;
+	skb_dst_drop(skb);
 #if IS_ENABLED(CONFIG_IPV6)
 	if (l2tp_sk_is_v6(tunnel->sock))
 		error = inet6_csk_xmit(tunnel->sock, skb, NULL);
@@ -1101,10 +1102,6 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len
 		goto out_unlock;
 	}
 
-	/* Get routing info from the tunnel socket */
-	skb_dst_drop(skb);
-	skb_dst_set(skb, sk_dst_check(sk, 0));
-
 	inet = inet_sk(sk);
 	fl = &inet->cork.fl;
 	switch (tunnel->encap) {
-- 
2.26.2


From 23cd7301c7029478974b80f79983235b5ff687a7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 27 Jun 2020 13:31:50 -0700
Subject: [PATCH 08/29] llc: make sure applications use ARPHRD_ETHER

[ Upstream commit a9b1110162357689a34992d5c925852948e5b9fd ]

syzbot was to trigger a bug by tricking AF_LLC with
non sensible addr->sllc_arphrd

It seems clear LLC requires an Ethernet device.

Back in commit abf9d537fea2 ("llc: add support for SO_BINDTODEVICE")
Octavian Purdila added possibility for application to use a zero
value for sllc_arphrd, convert it to ARPHRD_ETHER to not cause
regressions on existing applications.

BUG: KASAN: use-after-free in __read_once_size include/linux/compiler.h:199 [inline]
BUG: KASAN: use-after-free in list_empty include/linux/list.h:268 [inline]
BUG: KASAN: use-after-free in waitqueue_active include/linux/wait.h:126 [inline]
BUG: KASAN: use-after-free in wq_has_sleeper include/linux/wait.h:160 [inline]
BUG: KASAN: use-after-free in skwq_has_sleeper include/net/sock.h:2092 [inline]
BUG: KASAN: use-after-free in sock_def_write_space+0x642/0x670 net/core/sock.c:2813
Read of size 8 at addr ffff88801e0b4078 by task ksoftirqd/3/27

CPU: 3 PID: 27 Comm: ksoftirqd/3 Not tainted 5.5.0-rc1-syzkaller #0
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x197/0x210 lib/dump_stack.c:118
 print_address_description.constprop.0.cold+0xd4/0x30b mm/kasan/report.c:374
 __kasan_report.cold+0x1b/0x41 mm/kasan/report.c:506
 kasan_report+0x12/0x20 mm/kasan/common.c:639
 __asan_report_load8_noabort+0x14/0x20 mm/kasan/generic_report.c:135
 __read_once_size include/linux/compiler.h:199 [inline]
 list_empty include/linux/list.h:268 [inline]
 waitqueue_active include/linux/wait.h:126 [inline]
 wq_has_sleeper include/linux/wait.h:160 [inline]
 skwq_has_sleeper include/net/sock.h:2092 [inline]
 sock_def_write_space+0x642/0x670 net/core/sock.c:2813
 sock_wfree+0x1e1/0x260 net/core/sock.c:1958
 skb_release_head_state+0xeb/0x260 net/core/skbuff.c:652
 skb_release_all+0x16/0x60 net/core/skbuff.c:663
 __kfree_skb net/core/skbuff.c:679 [inline]
 consume_skb net/core/skbuff.c:838 [inline]
 consume_skb+0xfb/0x410 net/core/skbuff.c:832
 __dev_kfree_skb_any+0xa4/0xd0 net/core/dev.c:2967
 dev_kfree_skb_any include/linux/netdevice.h:3650 [inline]
 e1000_unmap_and_free_tx_resource.isra.0+0x21b/0x3a0 drivers/net/ethernet/intel/e1000/e1000_main.c:1963
 e1000_clean_tx_irq drivers/net/ethernet/intel/e1000/e1000_main.c:3854 [inline]
 e1000_clean+0x4cc/0x1d10 drivers/net/ethernet/intel/e1000/e1000_main.c:3796
 napi_poll net/core/dev.c:6532 [inline]
 net_rx_action+0x508/0x1120 net/core/dev.c:6600
 __do_softirq+0x262/0x98c kernel/softirq.c:292
 run_ksoftirqd kernel/softirq.c:603 [inline]
 run_ksoftirqd+0x8e/0x110 kernel/softirq.c:595
 smpboot_thread_fn+0x6a3/0xa40 kernel/smpboot.c:165
 kthread+0x361/0x430 kernel/kthread.c:255
 ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:352

Allocated by task 8247:
 save_stack+0x23/0x90 mm/kasan/common.c:72
 set_track mm/kasan/common.c:80 [inline]
 __kasan_kmalloc mm/kasan/common.c:513 [inline]
 __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:486
 kasan_slab_alloc+0xf/0x20 mm/kasan/common.c:521
 slab_post_alloc_hook mm/slab.h:584 [inline]
 slab_alloc mm/slab.c:3320 [inline]
 kmem_cache_alloc+0x121/0x710 mm/slab.c:3484
 sock_alloc_inode+0x1c/0x1d0 net/socket.c:240
 alloc_inode+0x68/0x1e0 fs/inode.c:230
 new_inode_pseudo+0x19/0xf0 fs/inode.c:919
 sock_alloc+0x41/0x270 net/socket.c:560
 __sock_create+0xc2/0x730 net/socket.c:1384
 sock_create net/socket.c:1471 [inline]
 __sys_socket+0x103/0x220 net/socket.c:1513
 __do_sys_socket net/socket.c:1522 [inline]
 __se_sys_socket net/socket.c:1520 [inline]
 __ia32_sys_socket+0x73/0xb0 net/socket.c:1520
 do_syscall_32_irqs_on arch/x86/entry/common.c:337 [inline]
 do_fast_syscall_32+0x27b/0xe16 arch/x86/entry/common.c:408
 entry_SYSENTER_compat+0x70/0x7f arch/x86/entry/entry_64_compat.S:139

Freed by task 17:
 save_stack+0x23/0x90 mm/kasan/common.c:72
 set_track mm/kasan/common.c:80 [inline]
 kasan_set_free_info mm/kasan/common.c:335 [inline]
 __kasan_slab_free+0x102/0x150 mm/kasan/common.c:474
 kasan_slab_free+0xe/0x10 mm/kasan/common.c:483
 __cache_free mm/slab.c:3426 [inline]
 kmem_cache_free+0x86/0x320 mm/slab.c:3694
 sock_free_inode+0x20/0x30 net/socket.c:261
 i_callback+0x44/0x80 fs/inode.c:219
 __rcu_reclaim kernel/rcu/rcu.h:222 [inline]
 rcu_do_batch kernel/rcu/tree.c:2183 [inline]
 rcu_core+0x570/0x1540 kernel/rcu/tree.c:2408
 rcu_core_si+0x9/0x10 kernel/rcu/tree.c:2417
 __do_softirq+0x262/0x98c kernel/softirq.c:292

The buggy address belongs to the object at ffff88801e0b4000
 which belongs to the cache sock_inode_cache of size 1152
The buggy address is located 120 bytes inside of
 1152-byte region [ffff88801e0b4000, ffff88801e0b4480)
The buggy address belongs to the page:
page:ffffea0000782d00 refcount:1 mapcount:0 mapping:ffff88807aa59c40 index:0xffff88801e0b4ffd
raw: 00fffe0000000200 ffffea00008e6c88 ffffea0000782d48 ffff88807aa59c40
raw: ffff88801e0b4ffd ffff88801e0b4000 0000000100000003 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff88801e0b3f00: fb fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc
 ffff88801e0b3f80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
>ffff88801e0b4000: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                                                                ^
 ffff88801e0b4080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff88801e0b4100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb

Fixes: abf9d537fea2 ("llc: add support for SO_BINDTODEVICE")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/llc/af_llc.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index c74f44dfaa22..5abb7f9b7ee5 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -273,6 +273,10 @@ static int llc_ui_autobind(struct socket *sock, struct sockaddr_llc *addr)
 
 	if (!sock_flag(sk, SOCK_ZAPPED))
 		goto out;
+	if (!addr->sllc_arphrd)
+		addr->sllc_arphrd = ARPHRD_ETHER;
+	if (addr->sllc_arphrd != ARPHRD_ETHER)
+		goto out;
 	rc = -ENODEV;
 	if (sk->sk_bound_dev_if) {
 		llc->dev = dev_get_by_index(&init_net, sk->sk_bound_dev_if);
@@ -328,7 +332,9 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen)
 	if (unlikely(!sock_flag(sk, SOCK_ZAPPED) || addrlen != sizeof(*addr)))
 		goto out;
 	rc = -EAFNOSUPPORT;
-	if (unlikely(addr->sllc_family != AF_LLC))
+	if (!addr->sllc_arphrd)
+		addr->sllc_arphrd = ARPHRD_ETHER;
+	if (unlikely(addr->sllc_family != AF_LLC || addr->sllc_arphrd != ARPHRD_ETHER))
 		goto out;
 	dprintk("%s: binding %02X\n", __func__, addr->sllc_sap);
 	rc = -ENODEV;
@@ -336,8 +342,6 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen)
 	if (sk->sk_bound_dev_if) {
 		llc->dev = dev_get_by_index_rcu(&init_net, sk->sk_bound_dev_if);
 		if (llc->dev) {
-			if (!addr->sllc_arphrd)
-				addr->sllc_arphrd = llc->dev->type;
 			if (is_zero_ether_addr(addr->sllc_mac))
 				memcpy(addr->sllc_mac, llc->dev->dev_addr,
 				       IFHWADDRLEN);
-- 
2.26.2


From 3e8c8e28b56bfdc882bc513918561b2affaf6277 Mon Sep 17 00:00:00 2001
From: Martin Varghese <martin.varghese@nokia.com>
Date: Sun, 5 Jul 2020 14:23:49 +0530
Subject: [PATCH 09/29] net: Added pointer check for dst->ops->neigh_lookup in
 dst_neigh_lookup_skb

[ Upstream commit 394de110a73395de2ca4516b0de435e91b11b604 ]

The packets from tunnel devices (eg bareudp) may have only
metadata in the dst pointer of skb. Hence a pointer check of
neigh_lookup is needed in dst_neigh_lookup_skb

Kernel crashes when packets from bareudp device is processed in
the kernel neighbour subsytem.

[  133.384484] BUG: kernel NULL pointer dereference, address: 0000000000000000
[  133.385240] #PF: supervisor instruction fetch in kernel mode
[  133.385828] #PF: error_code(0x0010) - not-present page
[  133.386603] PGD 0 P4D 0
[  133.386875] Oops: 0010 [#1] SMP PTI
[  133.387275] CPU: 0 PID: 5045 Comm: ping Tainted: G        W         5.8.0-rc2+ #15
[  133.388052] Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
[  133.391076] RIP: 0010:0x0
[  133.392401] Code: Bad RIP value.
[  133.394029] RSP: 0018:ffffb79980003d50 EFLAGS: 00010246
[  133.396656] RAX: 0000000080000102 RBX: ffff9de2fe0d6600 RCX: ffff9de2fe5e9d00
[  133.399018] RDX: 0000000000000000 RSI: ffff9de2fe5e9d00 RDI: ffff9de2fc21b400
[  133.399685] RBP: ffff9de2fe5e9d00 R08: 0000000000000000 R09: 0000000000000000
[  133.400350] R10: ffff9de2fbc6be22 R11: ffff9de2fe0d6600 R12: ffff9de2fc21b400
[  133.401010] R13: ffff9de2fe0d6628 R14: 0000000000000001 R15: 0000000000000003
[  133.401667] FS:  00007fe014918740(0000) GS:ffff9de2fec00000(0000) knlGS:0000000000000000
[  133.402412] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  133.402948] CR2: ffffffffffffffd6 CR3: 000000003bb72000 CR4: 00000000000006f0
[  133.403611] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  133.404270] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[  133.404933] Call Trace:
[  133.405169]  <IRQ>
[  133.405367]  __neigh_update+0x5a4/0x8f0
[  133.405734]  arp_process+0x294/0x820
[  133.406076]  ? __netif_receive_skb_core+0x866/0xe70
[  133.406557]  arp_rcv+0x129/0x1c0
[  133.406882]  __netif_receive_skb_one_core+0x95/0xb0
[  133.407340]  process_backlog+0xa7/0x150
[  133.407705]  net_rx_action+0x2af/0x420
[  133.408457]  __do_softirq+0xda/0x2a8
[  133.408813]  asm_call_on_stack+0x12/0x20
[  133.409290]  </IRQ>
[  133.409519]  do_softirq_own_stack+0x39/0x50
[  133.410036]  do_softirq+0x50/0x60
[  133.410401]  __local_bh_enable_ip+0x50/0x60
[  133.410871]  ip_finish_output2+0x195/0x530
[  133.411288]  ip_output+0x72/0xf0
[  133.411673]  ? __ip_finish_output+0x1f0/0x1f0
[  133.412122]  ip_send_skb+0x15/0x40
[  133.412471]  raw_sendmsg+0x853/0xab0
[  133.412855]  ? insert_pfn+0xfe/0x270
[  133.413827]  ? vvar_fault+0xec/0x190
[  133.414772]  sock_sendmsg+0x57/0x80
[  133.415685]  __sys_sendto+0xdc/0x160
[  133.416605]  ? syscall_trace_enter+0x1d4/0x2b0
[  133.417679]  ? __audit_syscall_exit+0x1d9/0x280
[  133.418753]  ? __prepare_exit_to_usermode+0x5d/0x1a0
[  133.419819]  __x64_sys_sendto+0x24/0x30
[  133.420848]  do_syscall_64+0x4d/0x90
[  133.421768]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[  133.422833] RIP: 0033:0x7fe013689c03
[  133.423749] Code: Bad RIP value.
[  133.424624] RSP: 002b:00007ffc7288f418 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
[  133.425940] RAX: ffffffffffffffda RBX: 000056151fc63720 RCX: 00007fe013689c03
[  133.427225] RDX: 0000000000000040 RSI: 000056151fc63720 RDI: 0000000000000003
[  133.428481] RBP: 00007ffc72890b30 R08: 000056151fc60500 R09: 0000000000000010
[  133.429757] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000040
[  133.431041] R13: 000056151fc636e0 R14: 000056151fc616bc R15: 0000000000000080
[  133.432481] Modules linked in: mpls_iptunnel act_mirred act_tunnel_key cls_flower sch_ingress veth mpls_router ip_tunnel bareudp ip6_udp_tunnel udp_tunnel macsec udp_diag inet_diag unix_diag af_packet_diag netlink_diag binfmt_misc xt_MASQUERADE iptable_nat xt_addrtype xt_conntrack nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 br_netfilter bridge stp llc ebtable_filter ebtables overlay ip6table_filter ip6_tables iptable_filter sunrpc ext4 mbcache jbd2 pcspkr i2c_piix4 virtio_balloon joydev ip_tables xfs libcrc32c ata_generic qxl pata_acpi drm_ttm_helper ttm drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops drm ata_piix libata virtio_net net_failover virtio_console failover virtio_blk i2c_core virtio_pci virtio_ring serio_raw floppy virtio dm_mirror dm_region_hash dm_log dm_mod
[  133.444045] CR2: 0000000000000000
[  133.445082] ---[ end trace f4aeee1958fd1638 ]---
[  133.446236] RIP: 0010:0x0
[  133.447180] Code: Bad RIP value.
[  133.448152] RSP: 0018:ffffb79980003d50 EFLAGS: 00010246
[  133.449363] RAX: 0000000080000102 RBX: ffff9de2fe0d6600 RCX: ffff9de2fe5e9d00
[  133.450835] RDX: 0000000000000000 RSI: ffff9de2fe5e9d00 RDI: ffff9de2fc21b400
[  133.452237] RBP: ffff9de2fe5e9d00 R08: 0000000000000000 R09: 0000000000000000
[  133.453722] R10: ffff9de2fbc6be22 R11: ffff9de2fe0d6600 R12: ffff9de2fc21b400
[  133.455149] R13: ffff9de2fe0d6628 R14: 0000000000000001 R15: 0000000000000003
[  133.456520] FS:  00007fe014918740(0000) GS:ffff9de2fec00000(0000) knlGS:0000000000000000
[  133.458046] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  133.459342] CR2: ffffffffffffffd6 CR3: 000000003bb72000 CR4: 00000000000006f0
[  133.460782] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  133.462240] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[  133.463697] Kernel panic - not syncing: Fatal exception in interrupt
[  133.465226] Kernel Offset: 0xfa00000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff)
[  133.467025] ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]---

Fixes: aaa0c23cb901 ("Fix dst_neigh_lookup/dst_neigh_lookup_skb return value handling bug")
Signed-off-by: Martin Varghese <martin.varghese@nokia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst.h | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/include/net/dst.h b/include/net/dst.h
index 3448cf865ede..433f7c1ce8a9 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -401,7 +401,15 @@ static inline struct neighbour *dst_neigh_lookup(const struct dst_entry *dst, co
 static inline struct neighbour *dst_neigh_lookup_skb(const struct dst_entry *dst,
 						     struct sk_buff *skb)
 {
-	struct neighbour *n =  dst->ops->neigh_lookup(dst, skb, NULL);
+	struct neighbour *n = NULL;
+
+	/* The packets from tunnel devices (eg bareudp) may have only
+	 * metadata in the dst pointer of skb. Hence a pointer check of
+	 * neigh_lookup is needed.
+	 */
+	if (dst->ops->neigh_lookup)
+		n = dst->ops->neigh_lookup(dst, skb, NULL);
+
 	return IS_ERR(n) ? NULL : n;
 }
 
-- 
2.26.2


From cc25268ca6418ed9acb3c360edae3aa0d3f3be73 Mon Sep 17 00:00:00 2001
From: Codrin Ciubotariu <codrin.ciubotariu@microchip.com>
Date: Thu, 2 Jul 2020 12:44:50 +0300
Subject: [PATCH 10/29] net: dsa: microchip: set the correct number of ports

[ Upstream commit af199a1a9cb02ec0194804bd46c174b6db262075 ]

The number of ports is incorrectly set to the maximum available for a DSA
switch. Even if the extra ports are not used, this causes some functions
to be called later, like port_disable() and port_stp_state_set(). If the
driver doesn't check the port index, it will end up modifying unknown
registers.

Fixes: b987e98e50ab ("dsa: add DSA switch driver for Microchip KSZ9477")
Signed-off-by: Codrin Ciubotariu <codrin.ciubotariu@microchip.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/microchip/ksz8795.c | 3 +++
 drivers/net/dsa/microchip/ksz9477.c | 3 +++
 2 files changed, 6 insertions(+)

diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c
index 24a5e99f7fd5..84c4319e3b31 100644
--- a/drivers/net/dsa/microchip/ksz8795.c
+++ b/drivers/net/dsa/microchip/ksz8795.c
@@ -1267,6 +1267,9 @@ static int ksz8795_switch_init(struct ksz_device *dev)
 			return -ENOMEM;
 	}
 
+	/* set the real number of ports */
+	dev->ds->num_ports = dev->port_cnt;
+
 	return 0;
 }
 
diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c
index 50ffc63d6231..3afb596d8e43 100644
--- a/drivers/net/dsa/microchip/ksz9477.c
+++ b/drivers/net/dsa/microchip/ksz9477.c
@@ -1587,6 +1587,9 @@ static int ksz9477_switch_init(struct ksz_device *dev)
 			return -ENOMEM;
 	}
 
+	/* set the real number of ports */
+	dev->ds->num_ports = dev->port_cnt;
+
 	return 0;
 }
 
-- 
2.26.2


From 779afd123eb17634efb8c3d4b9f7e032af1f3ff7 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Tue, 30 Jun 2020 11:04:40 +0100
Subject: [PATCH 11/29] net: mvneta: fix use of state->speed

[ Upstream commit f2ca673d2cd5df9a76247b670e9ffd4d63682b3f ]

When support for short preambles was added, it incorrectly keyed its
decision off state->speed instead of state->interface.  state->speed
is not guaranteed to be correct for in-band modes, which can lead to
short preambles being unexpectedly disabled.

Fix this by keying off the interface mode, which is the only way that
mvneta can operate at 2.5Gbps.

Fixes: da58a931f248 ("net: mvneta: Add support for 2500Mbps SGMII")
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index a10ae28ebc8a..ae6f37b2322b 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -3558,7 +3558,7 @@ static void mvneta_mac_config(struct phylink_config *config, unsigned int mode,
 	/* When at 2.5G, the link partner can send frames with shortened
 	 * preambles.
 	 */
-	if (state->speed == SPEED_2500)
+	if (state->interface == PHY_INTERFACE_MODE_2500BASEX)
 		new_ctrl4 |= MVNETA_GMAC4_SHORT_PREAMBLE_ENABLE;
 
 	if (pp->comphy && pp->phy_interface != state->interface &&
-- 
2.26.2


From 3f7355c7a385d586d1684f1f84706f54b9c89a07 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Tue, 30 Jun 2020 14:46:15 +0300
Subject: [PATCH 12/29] net: qrtr: Fix an out of bounds read
 qrtr_endpoint_post()

[ Upstream commit 8ff41cc21714704ef0158a546c3c4d07fae2c952 ]

This code assumes that the user passed in enough data for a
qrtr_hdr_v1 or qrtr_hdr_v2 struct, but it's not necessarily true.  If
the buffer is too small then it will read beyond the end.

Reported-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Reported-by: syzbot+b8fe393f999a291a9ea6@syzkaller.appspotmail.com
Fixes: 194ccc88297a ("net: qrtr: Support decoding incoming v2 packets")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/qrtr/qrtr.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index 2a4d50e04441..14c101e104ce 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -259,7 +259,7 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len)
 	unsigned int ver;
 	size_t hdrlen;
 
-	if (len & 3)
+	if (len == 0 || len & 3)
 		return -EINVAL;
 
 	skb = netdev_alloc_skb(NULL, len);
@@ -273,6 +273,8 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len)
 
 	switch (ver) {
 	case QRTR_PROTO_VER_1:
+		if (len < sizeof(*v1))
+			goto err;
 		v1 = data;
 		hdrlen = sizeof(*v1);
 
@@ -286,6 +288,8 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len)
 		size = le32_to_cpu(v1->size);
 		break;
 	case QRTR_PROTO_VER_2:
+		if (len < sizeof(*v2))
+			goto err;
 		v2 = data;
 		hdrlen = sizeof(*v2) + v2->optlen;
 
-- 
2.26.2


From 9dea6ff39a6ca362563e9af2b60301585728ab3c Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Wed, 8 Jul 2020 20:13:59 -0700
Subject: [PATCH 13/29] net_sched: fix a memory leak in atm_tc_init()

[ Upstream commit 306381aec7c2b5a658eebca008c8a1b666536cba ]

When tcf_block_get() fails inside atm_tc_init(),
atm_tc_put() is called to release the qdisc p->link.q.
But the flow->ref prevents it to do so, as the flow->ref
is still zero.

Fix this by moving the p->link.ref initialization before
tcf_block_get().

Fixes: 6529eaba33f0 ("net: sched: introduce tcf block infractructure")
Reported-and-tested-by: syzbot+d411cff6ab29cc2c311b@syzkaller.appspotmail.com
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_atm.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index f4f9b8cdbffb..6385995dc700 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -553,16 +553,16 @@ static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt,
 	if (!p->link.q)
 		p->link.q = &noop_qdisc;
 	pr_debug("atm_tc_init: link (%p) qdisc %p\n", &p->link, p->link.q);
+	p->link.vcc = NULL;
+	p->link.sock = NULL;
+	p->link.common.classid = sch->handle;
+	p->link.ref = 1;
 
 	err = tcf_block_get(&p->link.block, &p->link.filter_list, sch,
 			    extack);
 	if (err)
 		return err;
 
-	p->link.vcc = NULL;
-	p->link.sock = NULL;
-	p->link.common.classid = sch->handle;
-	p->link.ref = 1;
 	tasklet_init(&p->task, sch_atm_dequeue, (unsigned long)sch);
 	return 0;
 }
-- 
2.26.2


From 131a50ee780d47e5829cd6f295cc8415aee6dc6e Mon Sep 17 00:00:00 2001
From: AceLan Kao <acelan.kao@canonical.com>
Date: Tue, 7 Jul 2020 16:14:45 +0800
Subject: [PATCH 14/29] net: usb: qmi_wwan: add support for Quectel EG95 LTE
 modem
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit f815dd5cf48b905eeecf0a2b990e9b7ab048b4f1 ]

Add support for Quectel Wireless Solutions Co., Ltd. EG95 LTE modem

T:  Bus=01 Lev=01 Prnt=01 Port=02 Cnt=02 Dev#=  5 Spd=480 MxCh= 0
D:  Ver= 2.00 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs=  1
P:  Vendor=2c7c ProdID=0195 Rev=03.18
S:  Manufacturer=Android
S:  Product=Android
C:  #Ifs= 5 Cfg#= 1 Atr=a0 MxPwr=500mA
I:  If#=0x0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none)
I:  If#=0x1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=(none)
I:  If#=0x2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=(none)
I:  If#=0x3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=(none)
I:  If#=0x4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none)

Signed-off-by: AceLan Kao <acelan.kao@canonical.com>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 4a2c7355be63..e57d59b0a7ae 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1370,6 +1370,7 @@ static const struct usb_device_id products[] = {
 	{QMI_QUIRK_SET_DTR(0x1e0e, 0x9001, 5)},	/* SIMCom 7100E, 7230E, 7600E ++ */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0121, 4)},	/* Quectel EC21 Mini PCIe */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0191, 4)},	/* Quectel EG91 */
+	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0195, 4)},	/* Quectel EG95 */
 	{QMI_FIXED_INTF(0x2c7c, 0x0296, 4)},	/* Quectel BG96 */
 	{QMI_QUIRK_SET_DTR(0x2cb7, 0x0104, 4)},	/* Fibocom NL678 series */
 	{QMI_FIXED_INTF(0x0489, 0xe0b4, 0)},	/* Foxconn T77W968 LTE */
-- 
2.26.2


From 0f87aa7bd399fc2fc6855931dc8514212aff35cd Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
Date: Fri, 3 Jul 2020 22:26:43 +0200
Subject: [PATCH 15/29] sched: consistently handle layer3 header accesses in
 the presence of VLANs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit d7bf2ebebc2bd61ab95e2a8e33541ef282f303d4 ]

There are a couple of places in net/sched/ that check skb->protocol and act
on the value there. However, in the presence of VLAN tags, the value stored
in skb->protocol can be inconsistent based on whether VLAN acceleration is
enabled. The commit quoted in the Fixes tag below fixed the users of
skb->protocol to use a helper that will always see the VLAN ethertype.

However, most of the callers don't actually handle the VLAN ethertype, but
expect to find the IP header type in the protocol field. This means that
things like changing the ECN field, or parsing diffserv values, stops
working if there's a VLAN tag, or if there are multiple nested VLAN
tags (QinQ).

To fix this, change the helper to take an argument that indicates whether
the caller wants to skip the VLAN tags or not. When skipping VLAN tags, we
make sure to skip all of them, so behaviour is consistent even in QinQ
mode.

To make the helper usable from the ECN code, move it to if_vlan.h instead
of pkt_sched.h.

v3:
- Remove empty lines
- Move vlan variable definitions inside loop in skb_protocol()
- Also use skb_protocol() helper in IP{,6}_ECN_decapsulate() and
  bpf_skb_ecn_set_ce()

v2:
- Use eth_type_vlan() helper in skb_protocol()
- Also fix code that reads skb->protocol directly
- Change a couple of 'if/else if' statements to switch constructs to avoid
  calling the helper twice

Reported-by: Ilya Ponetayev <i.ponetaev@ndmsystems.com>
Fixes: d8b9605d2697 ("net: sched: fix skb->protocol use in case of accelerated vlan path")
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_vlan.h  | 28 ++++++++++++++++++++++++++++
 include/net/inet_ecn.h   | 25 +++++++++++++++++--------
 include/net/pkt_sched.h  | 11 -----------
 net/core/filter.c        | 10 +++++++---
 net/sched/act_connmark.c |  9 ++++++---
 net/sched/act_csum.c     |  2 +-
 net/sched/act_ct.c       |  9 ++++-----
 net/sched/act_ctinfo.c   |  9 ++++++---
 net/sched/act_mpls.c     |  2 +-
 net/sched/act_skbedit.c  |  2 +-
 net/sched/cls_api.c      |  2 +-
 net/sched/cls_flow.c     |  8 ++++----
 net/sched/cls_flower.c   |  2 +-
 net/sched/em_ipset.c     |  2 +-
 net/sched/em_ipt.c       |  2 +-
 net/sched/em_meta.c      |  2 +-
 net/sched/sch_cake.c     |  4 ++--
 net/sched/sch_dsmark.c   |  6 +++---
 net/sched/sch_teql.c     |  2 +-
 19 files changed, 86 insertions(+), 51 deletions(-)

diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index b05e855f1ddd..427a5b8597c2 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -308,6 +308,34 @@ static inline bool eth_type_vlan(__be16 ethertype)
 	}
 }
 
+/* A getter for the SKB protocol field which will handle VLAN tags consistently
+ * whether VLAN acceleration is enabled or not.
+ */
+static inline __be16 skb_protocol(const struct sk_buff *skb, bool skip_vlan)
+{
+	unsigned int offset = skb_mac_offset(skb) + sizeof(struct ethhdr);
+	__be16 proto = skb->protocol;
+
+	if (!skip_vlan)
+		/* VLAN acceleration strips the VLAN header from the skb and
+		 * moves it to skb->vlan_proto
+		 */
+		return skb_vlan_tag_present(skb) ? skb->vlan_proto : proto;
+
+	while (eth_type_vlan(proto)) {
+		struct vlan_hdr vhdr, *vh;
+
+		vh = skb_header_pointer(skb, offset, sizeof(vhdr), &vhdr);
+		if (!vh)
+			break;
+
+		proto = vh->h_vlan_encapsulated_proto;
+		offset += sizeof(vhdr);
+	}
+
+	return proto;
+}
+
 static inline bool vlan_hw_offload_capable(netdev_features_t features,
 					   __be16 proto)
 {
diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h
index 0f0d1efe06dd..e1eaf1780288 100644
--- a/include/net/inet_ecn.h
+++ b/include/net/inet_ecn.h
@@ -4,6 +4,7 @@
 
 #include <linux/ip.h>
 #include <linux/skbuff.h>
+#include <linux/if_vlan.h>
 
 #include <net/inet_sock.h>
 #include <net/dsfield.h>
@@ -172,7 +173,7 @@ static inline void ipv6_copy_dscp(unsigned int dscp, struct ipv6hdr *inner)
 
 static inline int INET_ECN_set_ce(struct sk_buff *skb)
 {
-	switch (skb->protocol) {
+	switch (skb_protocol(skb, true)) {
 	case cpu_to_be16(ETH_P_IP):
 		if (skb_network_header(skb) + sizeof(struct iphdr) <=
 		    skb_tail_pointer(skb))
@@ -191,7 +192,7 @@ static inline int INET_ECN_set_ce(struct sk_buff *skb)
 
 static inline int INET_ECN_set_ect1(struct sk_buff *skb)
 {
-	switch (skb->protocol) {
+	switch (skb_protocol(skb, true)) {
 	case cpu_to_be16(ETH_P_IP):
 		if (skb_network_header(skb) + sizeof(struct iphdr) <=
 		    skb_tail_pointer(skb))
@@ -272,12 +273,16 @@ static inline int IP_ECN_decapsulate(const struct iphdr *oiph,
 {
 	__u8 inner;
 
-	if (skb->protocol == htons(ETH_P_IP))
+	switch (skb_protocol(skb, true)) {
+	case htons(ETH_P_IP):
 		inner = ip_hdr(skb)->tos;
-	else if (skb->protocol == htons(ETH_P_IPV6))
+		break;
+	case htons(ETH_P_IPV6):
 		inner = ipv6_get_dsfield(ipv6_hdr(skb));
-	else
+		break;
+	default:
 		return 0;
+	}
 
 	return INET_ECN_decapsulate(skb, oiph->tos, inner);
 }
@@ -287,12 +292,16 @@ static inline int IP6_ECN_decapsulate(const struct ipv6hdr *oipv6h,
 {
 	__u8 inner;
 
-	if (skb->protocol == htons(ETH_P_IP))
+	switch (skb_protocol(skb, true)) {
+	case htons(ETH_P_IP):
 		inner = ip_hdr(skb)->tos;
-	else if (skb->protocol == htons(ETH_P_IPV6))
+		break;
+	case htons(ETH_P_IPV6):
 		inner = ipv6_get_dsfield(ipv6_hdr(skb));
-	else
+		break;
+	default:
 		return 0;
+	}
 
 	return INET_ECN_decapsulate(skb, ipv6_get_dsfield(oipv6h), inner);
 }
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index 6a70845bd9ab..cee1c084e9f4 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -128,17 +128,6 @@ static inline void qdisc_run(struct Qdisc *q)
 	}
 }
 
-static inline __be16 tc_skb_protocol(const struct sk_buff *skb)
-{
-	/* We need to take extra care in case the skb came via
-	 * vlan accelerated path. In that case, use skb->vlan_proto
-	 * as the original vlan header was already stripped.
-	 */
-	if (skb_vlan_tag_present(skb))
-		return skb->vlan_proto;
-	return skb->protocol;
-}
-
 /* Calculate maximal size of packet seen by hard_start_xmit
    routine of this device.
  */
diff --git a/net/core/filter.c b/net/core/filter.c
index a0a492f7cf9c..bd1e46d61d8a 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5730,12 +5730,16 @@ BPF_CALL_1(bpf_skb_ecn_set_ce, struct sk_buff *, skb)
 {
 	unsigned int iphdr_len;
 
-	if (skb->protocol == cpu_to_be16(ETH_P_IP))
+	switch (skb_protocol(skb, true)) {
+	case cpu_to_be16(ETH_P_IP):
 		iphdr_len = sizeof(struct iphdr);
-	else if (skb->protocol == cpu_to_be16(ETH_P_IPV6))
+		break;
+	case cpu_to_be16(ETH_P_IPV6):
 		iphdr_len = sizeof(struct ipv6hdr);
-	else
+		break;
+	default:
 		return 0;
+	}
 
 	if (skb_headlen(skb) < iphdr_len)
 		return 0;
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index 2b43cacf82af..1a8f2f85ea1a 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -43,17 +43,20 @@ static int tcf_connmark_act(struct sk_buff *skb, const struct tc_action *a,
 	tcf_lastuse_update(&ca->tcf_tm);
 	bstats_update(&ca->tcf_bstats, skb);
 
-	if (skb->protocol == htons(ETH_P_IP)) {
+	switch (skb_protocol(skb, true)) {
+	case htons(ETH_P_IP):
 		if (skb->len < sizeof(struct iphdr))
 			goto out;
 
 		proto = NFPROTO_IPV4;
-	} else if (skb->protocol == htons(ETH_P_IPV6)) {
+		break;
+	case htons(ETH_P_IPV6):
 		if (skb->len < sizeof(struct ipv6hdr))
 			goto out;
 
 		proto = NFPROTO_IPV6;
-	} else {
+		break;
+	default:
 		goto out;
 	}
 
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index d3cfad88dc3a..428b1ae00123 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -587,7 +587,7 @@ static int tcf_csum_act(struct sk_buff *skb, const struct tc_action *a,
 		goto drop;
 
 	update_flags = params->update_flags;
-	protocol = tc_skb_protocol(skb);
+	protocol = skb_protocol(skb, false);
 again:
 	switch (protocol) {
 	case cpu_to_be16(ETH_P_IP):
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index 0586546c20d7..e0060aefbf9d 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -100,7 +100,7 @@ static u8 tcf_ct_skb_nf_family(struct sk_buff *skb)
 {
 	u8 family = NFPROTO_UNSPEC;
 
-	switch (skb->protocol) {
+	switch (skb_protocol(skb, true)) {
 	case htons(ETH_P_IP):
 		family = NFPROTO_IPV4;
 		break;
@@ -222,6 +222,7 @@ static int ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
 			  const struct nf_nat_range2 *range,
 			  enum nf_nat_manip_type maniptype)
 {
+	__be16 proto = skb_protocol(skb, true);
 	int hooknum, err = NF_ACCEPT;
 
 	/* See HOOK2MANIP(). */
@@ -233,14 +234,13 @@ static int ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
 	switch (ctinfo) {
 	case IP_CT_RELATED:
 	case IP_CT_RELATED_REPLY:
-		if (skb->protocol == htons(ETH_P_IP) &&
+		if (proto == htons(ETH_P_IP) &&
 		    ip_hdr(skb)->protocol == IPPROTO_ICMP) {
 			if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
 							   hooknum))
 				err = NF_DROP;
 			goto out;
-		} else if (IS_ENABLED(CONFIG_IPV6) &&
-			   skb->protocol == htons(ETH_P_IPV6)) {
+		} else if (IS_ENABLED(CONFIG_IPV6) && proto == htons(ETH_P_IPV6)) {
 			__be16 frag_off;
 			u8 nexthdr = ipv6_hdr(skb)->nexthdr;
 			int hdrlen = ipv6_skip_exthdr(skb,
@@ -993,4 +993,3 @@ MODULE_AUTHOR("Yossi Kuperman <yossiku@mellanox.com>");
 MODULE_AUTHOR("Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>");
 MODULE_DESCRIPTION("Connection tracking action");
 MODULE_LICENSE("GPL v2");
-
diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c
index f45995a6237a..a91fcee810ef 100644
--- a/net/sched/act_ctinfo.c
+++ b/net/sched/act_ctinfo.c
@@ -96,19 +96,22 @@ static int tcf_ctinfo_act(struct sk_buff *skb, const struct tc_action *a,
 	action = READ_ONCE(ca->tcf_action);
 
 	wlen = skb_network_offset(skb);
-	if (tc_skb_protocol(skb) == htons(ETH_P_IP)) {
+	switch (skb_protocol(skb, true)) {
+	case htons(ETH_P_IP):
 		wlen += sizeof(struct iphdr);
 		if (!pskb_may_pull(skb, wlen))
 			goto out;
 
 		proto = NFPROTO_IPV4;
-	} else if (tc_skb_protocol(skb) == htons(ETH_P_IPV6)) {
+		break;
+	case htons(ETH_P_IPV6):
 		wlen += sizeof(struct ipv6hdr);
 		if (!pskb_may_pull(skb, wlen))
 			goto out;
 
 		proto = NFPROTO_IPV6;
-	} else {
+		break;
+	default:
 		goto out;
 	}
 
diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c
index db570d2bd0e0..f786775699b5 100644
--- a/net/sched/act_mpls.c
+++ b/net/sched/act_mpls.c
@@ -82,7 +82,7 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a,
 			goto drop;
 		break;
 	case TCA_MPLS_ACT_PUSH:
-		new_lse = tcf_mpls_get_lse(NULL, p, !eth_p_mpls(skb->protocol));
+		new_lse = tcf_mpls_get_lse(NULL, p, !eth_p_mpls(skb_protocol(skb, true)));
 		if (skb_mpls_push(skb, new_lse, p->tcfm_proto, mac_len,
 				  skb->dev && skb->dev->type == ARPHRD_ETHER))
 			goto drop;
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 6a8d3337c577..f98b2791ecec 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -41,7 +41,7 @@ static int tcf_skbedit_act(struct sk_buff *skb, const struct tc_action *a,
 	if (params->flags & SKBEDIT_F_INHERITDSFIELD) {
 		int wlen = skb_network_offset(skb);
 
-		switch (tc_skb_protocol(skb)) {
+		switch (skb_protocol(skb, true)) {
 		case htons(ETH_P_IP):
 			wlen += sizeof(struct iphdr);
 			if (!pskb_may_pull(skb, wlen))
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 68c8fc6f535c..d7604417367d 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1571,7 +1571,7 @@ int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 reclassify:
 #endif
 	for (; tp; tp = rcu_dereference_bh(tp->next)) {
-		__be16 protocol = tc_skb_protocol(skb);
+		__be16 protocol = skb_protocol(skb, false);
 		int err;
 
 		if (tp->protocol != protocol &&
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index 80ae7b9fa90a..ab53a93b2f2b 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -80,7 +80,7 @@ static u32 flow_get_dst(const struct sk_buff *skb, const struct flow_keys *flow)
 	if (dst)
 		return ntohl(dst);
 
-	return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb);
+	return addr_fold(skb_dst(skb)) ^ (__force u16)skb_protocol(skb, true);
 }
 
 static u32 flow_get_proto(const struct sk_buff *skb,
@@ -104,7 +104,7 @@ static u32 flow_get_proto_dst(const struct sk_buff *skb,
 	if (flow->ports.ports)
 		return ntohs(flow->ports.dst);
 
-	return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb);
+	return addr_fold(skb_dst(skb)) ^ (__force u16)skb_protocol(skb, true);
 }
 
 static u32 flow_get_iif(const struct sk_buff *skb)
@@ -151,7 +151,7 @@ static u32 flow_get_nfct(const struct sk_buff *skb)
 static u32 flow_get_nfct_src(const struct sk_buff *skb,
 			     const struct flow_keys *flow)
 {
-	switch (tc_skb_protocol(skb)) {
+	switch (skb_protocol(skb, true)) {
 	case htons(ETH_P_IP):
 		return ntohl(CTTUPLE(skb, src.u3.ip));
 	case htons(ETH_P_IPV6):
@@ -164,7 +164,7 @@ static u32 flow_get_nfct_src(const struct sk_buff *skb,
 static u32 flow_get_nfct_dst(const struct sk_buff *skb,
 			     const struct flow_keys *flow)
 {
-	switch (tc_skb_protocol(skb)) {
+	switch (skb_protocol(skb, true)) {
 	case htons(ETH_P_IP):
 		return ntohl(CTTUPLE(skb, dst.u3.ip));
 	case htons(ETH_P_IPV6):
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 1d270540e74d..c5a0f2c2635e 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -310,7 +310,7 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 		/* skb_flow_dissect() does not set n_proto in case an unknown
 		 * protocol, so do it rather here.
 		 */
-		skb_key.basic.n_proto = skb->protocol;
+		skb_key.basic.n_proto = skb_protocol(skb, false);
 		skb_flow_dissect_tunnel_info(skb, &mask->dissector, &skb_key);
 		skb_flow_dissect_ct(skb, &mask->dissector, &skb_key,
 				    fl_ct_info_to_flower_map,
diff --git a/net/sched/em_ipset.c b/net/sched/em_ipset.c
index df00566d327d..c95cf86fb431 100644
--- a/net/sched/em_ipset.c
+++ b/net/sched/em_ipset.c
@@ -59,7 +59,7 @@ static int em_ipset_match(struct sk_buff *skb, struct tcf_ematch *em,
 	};
 	int ret, network_offset;
 
-	switch (tc_skb_protocol(skb)) {
+	switch (skb_protocol(skb, true)) {
 	case htons(ETH_P_IP):
 		state.pf = NFPROTO_IPV4;
 		if (!pskb_network_may_pull(skb, sizeof(struct iphdr)))
diff --git a/net/sched/em_ipt.c b/net/sched/em_ipt.c
index 9fff6480acc6..e2c157df3f8b 100644
--- a/net/sched/em_ipt.c
+++ b/net/sched/em_ipt.c
@@ -212,7 +212,7 @@ static int em_ipt_match(struct sk_buff *skb, struct tcf_ematch *em,
 	struct nf_hook_state state;
 	int ret;
 
-	switch (tc_skb_protocol(skb)) {
+	switch (skb_protocol(skb, true)) {
 	case htons(ETH_P_IP):
 		if (!pskb_network_may_pull(skb, sizeof(struct iphdr)))
 			return 0;
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index 3177dcb17316..ad007cdcec97 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -195,7 +195,7 @@ META_COLLECTOR(int_priority)
 META_COLLECTOR(int_protocol)
 {
 	/* Let userspace take care of the byte ordering */
-	dst->value = tc_skb_protocol(skb);
+	dst->value = skb_protocol(skb, false);
 }
 
 META_COLLECTOR(int_pkttype)
diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 5d605bab9afc..896c0562cb42 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -592,7 +592,7 @@ static void cake_update_flowkeys(struct flow_keys *keys,
 	struct nf_conntrack_tuple tuple = {};
 	bool rev = !skb->_nfct;
 
-	if (tc_skb_protocol(skb) != htons(ETH_P_IP))
+	if (skb_protocol(skb, true) != htons(ETH_P_IP))
 		return;
 
 	if (!nf_ct_get_tuple_skb(&tuple, skb))
@@ -1521,7 +1521,7 @@ static u8 cake_handle_diffserv(struct sk_buff *skb, bool wash)
 	u16 *buf, buf_;
 	u8 dscp;
 
-	switch (tc_skb_protocol(skb)) {
+	switch (skb_protocol(skb, true)) {
 	case htons(ETH_P_IP):
 		buf = skb_header_pointer(skb, offset, sizeof(buf_), &buf_);
 		if (unlikely(!buf))
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index 05605b30bef3..2b88710994d7 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -210,7 +210,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	if (p->set_tc_index) {
 		int wlen = skb_network_offset(skb);
 
-		switch (tc_skb_protocol(skb)) {
+		switch (skb_protocol(skb, true)) {
 		case htons(ETH_P_IP):
 			wlen += sizeof(struct iphdr);
 			if (!pskb_may_pull(skb, wlen) ||
@@ -303,7 +303,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch)
 	index = skb->tc_index & (p->indices - 1);
 	pr_debug("index %d->%d\n", skb->tc_index, index);
 
-	switch (tc_skb_protocol(skb)) {
+	switch (skb_protocol(skb, true)) {
 	case htons(ETH_P_IP):
 		ipv4_change_dsfield(ip_hdr(skb), p->mv[index].mask,
 				    p->mv[index].value);
@@ -320,7 +320,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch)
 		 */
 		if (p->mv[index].mask != 0xff || p->mv[index].value)
 			pr_warn("%s: unsupported protocol %d\n",
-				__func__, ntohs(tc_skb_protocol(skb)));
+				__func__, ntohs(skb_protocol(skb, true)));
 		break;
 	}
 
diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index 689ef6f3ded8..2f1f0a378408 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -239,7 +239,7 @@ __teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res,
 		char haddr[MAX_ADDR_LEN];
 
 		neigh_ha_snapshot(haddr, n, dev);
-		err = dev_hard_header(skb, dev, ntohs(tc_skb_protocol(skb)),
+		err = dev_hard_header(skb, dev, ntohs(skb_protocol(skb, false)),
 				      haddr, NULL, skb->len);
 
 		if (err < 0)
-- 
2.26.2


From 20ec4f5feb68d9796f607275ba9e42b5d6088d63 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 30 Jun 2020 13:51:28 -0700
Subject: [PATCH 16/29] tcp: fix SO_RCVLOWAT possible hangs under high mem
 pressure

[ Upstream commit ba3bb0e76ccd464bb66665a1941fabe55dadb3ba ]

Whenever tcp_try_rmem_schedule() returns an error, we are under
trouble and should make sure to wakeup readers so that they
can drain socket queues and eventually make room.

Fixes: 03f45c883c6f ("tcp: avoid extra wakeups for SO_RCVLOWAT users")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 3e63dc9c3eba..6d331307beca 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4564,6 +4564,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 
 	if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFODROP);
+		sk->sk_data_ready(sk);
 		tcp_drop(sk, skb);
 		return;
 	}
@@ -4807,6 +4808,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 			sk_forced_mem_schedule(sk, skb->truesize);
 		else if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) {
 			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP);
+			sk->sk_data_ready(sk);
 			goto drop;
 		}
 
-- 
2.26.2


From 3f695348725b895ea3585bd16cdddb62a054d6e3 Mon Sep 17 00:00:00 2001
From: Christoph Paasch <cpaasch@apple.com>
Date: Wed, 8 Jul 2020 16:18:34 -0700
Subject: [PATCH 17/29] tcp: make sure listeners don't initialize
 congestion-control state

[ Upstream commit ce69e563b325f620863830c246a8698ccea52048 ]

syzkaller found its way into setsockopt with TCP_CONGESTION "cdg".
tcp_cdg_init() does a kcalloc to store the gradients. As sk_clone_lock
just copies all the memory, the allocated pointer will be copied as
well, if the app called setsockopt(..., TCP_CONGESTION) on the listener.
If now the socket will be destroyed before the congestion-control
has properly been initialized (through a call to tcp_init_transfer), we
will end up freeing memory that does not belong to that particular
socket, opening the door to a double-free:

[   11.413102] ==================================================================
[   11.414181] BUG: KASAN: double-free or invalid-free in tcp_cleanup_congestion_control+0x58/0xd0
[   11.415329]
[   11.415560] CPU: 3 PID: 4884 Comm: syz-executor.5 Not tainted 5.8.0-rc2 #80
[   11.416544] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014
[   11.418148] Call Trace:
[   11.418534]  <IRQ>
[   11.418834]  dump_stack+0x7d/0xb0
[   11.419297]  print_address_description.constprop.0+0x1a/0x210
[   11.422079]  kasan_report_invalid_free+0x51/0x80
[   11.423433]  __kasan_slab_free+0x15e/0x170
[   11.424761]  kfree+0x8c/0x230
[   11.425157]  tcp_cleanup_congestion_control+0x58/0xd0
[   11.425872]  tcp_v4_destroy_sock+0x57/0x5a0
[   11.426493]  inet_csk_destroy_sock+0x153/0x2c0
[   11.427093]  tcp_v4_syn_recv_sock+0xb29/0x1100
[   11.427731]  tcp_get_cookie_sock+0xc3/0x4a0
[   11.429457]  cookie_v4_check+0x13d0/0x2500
[   11.433189]  tcp_v4_do_rcv+0x60e/0x780
[   11.433727]  tcp_v4_rcv+0x2869/0x2e10
[   11.437143]  ip_protocol_deliver_rcu+0x23/0x190
[   11.437810]  ip_local_deliver+0x294/0x350
[   11.439566]  __netif_receive_skb_one_core+0x15d/0x1a0
[   11.441995]  process_backlog+0x1b1/0x6b0
[   11.443148]  net_rx_action+0x37e/0xc40
[   11.445361]  __do_softirq+0x18c/0x61a
[   11.445881]  asm_call_on_stack+0x12/0x20
[   11.446409]  </IRQ>
[   11.446716]  do_softirq_own_stack+0x34/0x40
[   11.447259]  do_softirq.part.0+0x26/0x30
[   11.447827]  __local_bh_enable_ip+0x46/0x50
[   11.448406]  ip_finish_output2+0x60f/0x1bc0
[   11.450109]  __ip_queue_xmit+0x71c/0x1b60
[   11.451861]  __tcp_transmit_skb+0x1727/0x3bb0
[   11.453789]  tcp_rcv_state_process+0x3070/0x4d3a
[   11.456810]  tcp_v4_do_rcv+0x2ad/0x780
[   11.457995]  __release_sock+0x14b/0x2c0
[   11.458529]  release_sock+0x4a/0x170
[   11.459005]  __inet_stream_connect+0x467/0xc80
[   11.461435]  inet_stream_connect+0x4e/0xa0
[   11.462043]  __sys_connect+0x204/0x270
[   11.465515]  __x64_sys_connect+0x6a/0xb0
[   11.466088]  do_syscall_64+0x3e/0x70
[   11.466617]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[   11.467341] RIP: 0033:0x7f56046dc469
[   11.467844] Code: Bad RIP value.
[   11.468282] RSP: 002b:00007f5604dccdd8 EFLAGS: 00000246 ORIG_RAX: 000000000000002a
[   11.469326] RAX: ffffffffffffffda RBX: 000000000068bf00 RCX: 00007f56046dc469
[   11.470379] RDX: 0000000000000010 RSI: 0000000020000000 RDI: 0000000000000004
[   11.471311] RBP: 00000000ffffffff R08: 0000000000000000 R09: 0000000000000000
[   11.472286] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
[   11.473341] R13: 000000000041427c R14: 00007f5604dcd5c0 R15: 0000000000000003
[   11.474321]
[   11.474527] Allocated by task 4884:
[   11.475031]  save_stack+0x1b/0x40
[   11.475548]  __kasan_kmalloc.constprop.0+0xc2/0xd0
[   11.476182]  tcp_cdg_init+0xf0/0x150
[   11.476744]  tcp_init_congestion_control+0x9b/0x3a0
[   11.477435]  tcp_set_congestion_control+0x270/0x32f
[   11.478088]  do_tcp_setsockopt.isra.0+0x521/0x1a00
[   11.478744]  __sys_setsockopt+0xff/0x1e0
[   11.479259]  __x64_sys_setsockopt+0xb5/0x150
[   11.479895]  do_syscall_64+0x3e/0x70
[   11.480395]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[   11.481097]
[   11.481321] Freed by task 4872:
[   11.481783]  save_stack+0x1b/0x40
[   11.482230]  __kasan_slab_free+0x12c/0x170
[   11.482839]  kfree+0x8c/0x230
[   11.483240]  tcp_cleanup_congestion_control+0x58/0xd0
[   11.483948]  tcp_v4_destroy_sock+0x57/0x5a0
[   11.484502]  inet_csk_destroy_sock+0x153/0x2c0
[   11.485144]  tcp_close+0x932/0xfe0
[   11.485642]  inet_release+0xc1/0x1c0
[   11.486131]  __sock_release+0xc0/0x270
[   11.486697]  sock_close+0xc/0x10
[   11.487145]  __fput+0x277/0x780
[   11.487632]  task_work_run+0xeb/0x180
[   11.488118]  __prepare_exit_to_usermode+0x15a/0x160
[   11.488834]  do_syscall_64+0x4a/0x70
[   11.489326]  entry_SYSCALL_64_after_hwframe+0x44/0xa9

Wei Wang fixed a part of these CDG-malloc issues with commit c12014440750
("tcp: memset ca_priv data to 0 properly").

This patch here fixes the listener-scenario: We make sure that listeners
setting the congestion-control through setsockopt won't initialize it
(thus CDG never allocates on listeners). For those who use AF_UNSPEC to
reuse a socket, tcp_disconnect() is changed to cleanup afterwards.

(The issue can be reproduced at least down to v4.4.x.)

Cc: Wei Wang <weiwan@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Fixes: 2b0a8c9eee81 ("tcp: add CDG congestion control")
Signed-off-by: Christoph Paasch <cpaasch@apple.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c      | 3 +++
 net/ipv4/tcp_cong.c | 2 +-
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index fe3cdeddd097..a8910e2fcc78 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2631,6 +2631,9 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tp->window_clamp = 0;
 	tp->delivered = 0;
 	tp->delivered_ce = 0;
+	if (icsk->icsk_ca_ops->release)
+		icsk->icsk_ca_ops->release(sk);
+	memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
 	tcp_set_ca_state(sk, TCP_CA_Open);
 	tp->is_sack_reneg = 0;
 	tcp_clear_retrans(tp);
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index c445a81d144e..d7a1f2ef6c52 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -197,7 +197,7 @@ static void tcp_reinit_congestion_control(struct sock *sk,
 	icsk->icsk_ca_setsockopt = 1;
 	memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
 
-	if (sk->sk_state != TCP_CLOSE)
+	if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)))
 		tcp_init_congestion_control(sk);
 }
 
-- 
2.26.2


From 65e8f2b18e6d5a0d7d4cf3eadbb7fcc941d22a97 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 30 Jun 2020 16:41:01 -0700
Subject: [PATCH 18/29] tcp: md5: add missing memory barriers in
 tcp_md5_do_add()/tcp_md5_hash_key()

[ Upstream commit 6a2febec338df7e7699a52d00b2e1207dcf65b28 ]

MD5 keys are read with RCU protection, and tcp_md5_do_add()
might update in-place a prior key.

Normally, typical RCU updates would allocate a new piece
of memory. In this case only key->key and key->keylen might
be updated, and we do not care if an incoming packet could
see the old key, the new one, or some intermediate value,
since changing the key on a live flow is known to be problematic
anyway.

We only want to make sure that in the case key->keylen
is changed, cpus in tcp_md5_hash_key() wont try to use
uninitialized data, or crash because key->keylen was
read twice to feed sg_init_one() and ahash_request_set_crypt()

Fixes: 9ea88a153001 ("tcp: md5: check md5 signature without socket lock")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c      | 7 +++++--
 net/ipv4/tcp_ipv4.c | 3 +++
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index a8910e2fcc78..7de69e161c34 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3847,10 +3847,13 @@ EXPORT_SYMBOL(tcp_md5_hash_skb_data);
 
 int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, const struct tcp_md5sig_key *key)
 {
+	u8 keylen = key->keylen;
 	struct scatterlist sg;
 
-	sg_init_one(&sg, key->key, key->keylen);
-	ahash_request_set_crypt(hp->md5_req, &sg, NULL, key->keylen);
+	smp_rmb(); /* paired with smp_wmb() in tcp_md5_do_add() */
+
+	sg_init_one(&sg, key->key, keylen);
+	ahash_request_set_crypt(hp->md5_req, &sg, NULL, keylen);
 	return crypto_ahash_update(hp->md5_req);
 }
 EXPORT_SYMBOL(tcp_md5_hash_key);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index eda64871f983..7bb8747d86f1 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1079,6 +1079,9 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
 	if (key) {
 		/* Pre-existing entry - just update that one. */
 		memcpy(key->key, newkey, newkeylen);
+
+		smp_wmb(); /* pairs with smp_rmb() in tcp_md5_hash_key() */
+
 		key->keylen = newkeylen;
 		return 0;
 	}
-- 
2.26.2


From b93e6bfd3dcf6cc5e84cb97d75ddb62ed56b3494 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 1 Jul 2020 12:41:23 -0700
Subject: [PATCH 19/29] tcp: md5: do not send silly options in SYNCOOKIES

[ Upstream commit e114e1e8ac9d31f25b9dd873bab5d80c1fc482ca ]

Whenever cookie_init_timestamp() has been used to encode
ECN,SACK,WSCALE options, we can not remove the TS option in the SYNACK.

Otherwise, tcp_synack_options() will still advertize options like WSCALE
that we can not deduce later when receiving the packet from the client
to complete 3WHS.

Note that modern linux TCP stacks wont use MD5+TS+SACK in a SYN packet,
but we can not know for sure that all TCP stacks have the same logic.

Before the fix a tcpdump would exhibit this wrong exchange :

10:12:15.464591 IP C > S: Flags [S], seq 4202415601, win 65535, options [nop,nop,md5 valid,mss 1400,sackOK,TS val 456965269 ecr 0,nop,wscale 8], length 0
10:12:15.464602 IP S > C: Flags [S.], seq 253516766, ack 4202415602, win 65535, options [nop,nop,md5 valid,mss 1400,nop,nop,sackOK,nop,wscale 8], length 0
10:12:15.464611 IP C > S: Flags [.], ack 1, win 256, options [nop,nop,md5 valid], length 0
10:12:15.464678 IP C > S: Flags [P.], seq 1:13, ack 1, win 256, options [nop,nop,md5 valid], length 12
10:12:15.464685 IP S > C: Flags [.], ack 13, win 65535, options [nop,nop,md5 valid], length 0

After this patch the exchange looks saner :

11:59:59.882990 IP C > S: Flags [S], seq 517075944, win 65535, options [nop,nop,md5 valid,mss 1400,sackOK,TS val 1751508483 ecr 0,nop,wscale 8], length 0
11:59:59.883002 IP S > C: Flags [S.], seq 1902939253, ack 517075945, win 65535, options [nop,nop,md5 valid,mss 1400,sackOK,TS val 1751508479 ecr 1751508483,nop,wscale 8], length 0
11:59:59.883012 IP C > S: Flags [.], ack 1, win 256, options [nop,nop,md5 valid,nop,nop,TS val 1751508483 ecr 1751508479], length 0
11:59:59.883114 IP C > S: Flags [P.], seq 1:13, ack 1, win 256, options [nop,nop,md5 valid,nop,nop,TS val 1751508483 ecr 1751508479], length 12
11:59:59.883122 IP S > C: Flags [.], ack 13, win 256, options [nop,nop,md5 valid,nop,nop,TS val 1751508483 ecr 1751508483], length 0
11:59:59.883152 IP S > C: Flags [P.], seq 1:13, ack 13, win 256, options [nop,nop,md5 valid,nop,nop,TS val 1751508484 ecr 1751508483], length 12
11:59:59.883170 IP C > S: Flags [.], ack 13, win 256, options [nop,nop,md5 valid,nop,nop,TS val 1751508484 ecr 1751508484], length 0

Of course, no SACK block will ever be added later, but nothing should break.
Technically, we could remove the 4 nops included in MD5+TS options,
but again some stacks could break seeing not conventional alignment.

Fixes: 4957faade11b ("TCPCT part 1g: Responder Cookie => Initiator")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Florian Westphal <fw@strlen.de>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index c8d03c1b4c6b..5dc7485c4076 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -662,7 +662,8 @@ static unsigned int tcp_synack_options(const struct sock *sk,
 				       unsigned int mss, struct sk_buff *skb,
 				       struct tcp_out_options *opts,
 				       const struct tcp_md5sig_key *md5,
-				       struct tcp_fastopen_cookie *foc)
+				       struct tcp_fastopen_cookie *foc,
+				       enum tcp_synack_type synack_type)
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
 	unsigned int remaining = MAX_TCP_OPTION_SPACE;
@@ -677,7 +678,8 @@ static unsigned int tcp_synack_options(const struct sock *sk,
 		 * rather than TS in order to fit in better with old,
 		 * buggy kernels, but that was deemed to be unnecessary.
 		 */
-		ireq->tstamp_ok &= !ireq->sack_ok;
+		if (synack_type != TCP_SYNACK_COOKIE)
+			ireq->tstamp_ok &= !ireq->sack_ok;
 	}
 #endif
 
@@ -3326,7 +3328,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 #endif
 	skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4);
 	tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5,
-					     foc) + sizeof(*th);
+					     foc, synack_type) + sizeof(*th);
 
 	skb_push(skb, tcp_header_size);
 	skb_reset_transport_header(skb);
-- 
2.26.2


From af231625774f30299d8ffbd79620bdcf626713cd Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
Date: Tue, 7 Jul 2020 13:03:25 +0200
Subject: [PATCH 20/29] vlan: consolidate VLAN parsing code and limit max
 parsing depth
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 469aceddfa3ed16e17ee30533fae45e90f62efd8 ]

Toshiaki pointed out that we now have two very similar functions to extract
the L3 protocol number in the presence of VLAN tags. And Daniel pointed out
that the unbounded parsing loop makes it possible for maliciously crafted
packets to loop through potentially hundreds of tags.

Fix both of these issues by consolidating the two parsing functions and
limiting the VLAN tag parsing to a max depth of 8 tags. As part of this,
switch over __vlan_get_protocol() to use skb_header_pointer() instead of
pskb_may_pull(), to avoid the possible side effects of the latter and keep
the skb pointer 'const' through all the parsing functions.

v2:
- Use limit of 8 tags instead of 32 (matching XMIT_RECURSION_LIMIT)

Reported-by: Toshiaki Makita <toshiaki.makita1@gmail.com>
Reported-by: Daniel Borkmann <daniel@iogearbox.net>
Fixes: d7bf2ebebc2b ("sched: consistently handle layer3 header accesses in the presence of VLANs")
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_vlan.h | 57 ++++++++++++++++-------------------------
 1 file changed, 22 insertions(+), 35 deletions(-)

diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 427a5b8597c2..41a518336673 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -25,6 +25,8 @@
 #define VLAN_ETH_DATA_LEN	1500	/* Max. octets in payload	 */
 #define VLAN_ETH_FRAME_LEN	1518	/* Max. octets in frame sans FCS */
 
+#define VLAN_MAX_DEPTH	8		/* Max. number of nested VLAN tags parsed */
+
 /*
  * 	struct vlan_hdr - vlan header
  * 	@h_vlan_TCI: priority and VLAN ID
@@ -308,34 +310,6 @@ static inline bool eth_type_vlan(__be16 ethertype)
 	}
 }
 
-/* A getter for the SKB protocol field which will handle VLAN tags consistently
- * whether VLAN acceleration is enabled or not.
- */
-static inline __be16 skb_protocol(const struct sk_buff *skb, bool skip_vlan)
-{
-	unsigned int offset = skb_mac_offset(skb) + sizeof(struct ethhdr);
-	__be16 proto = skb->protocol;
-
-	if (!skip_vlan)
-		/* VLAN acceleration strips the VLAN header from the skb and
-		 * moves it to skb->vlan_proto
-		 */
-		return skb_vlan_tag_present(skb) ? skb->vlan_proto : proto;
-
-	while (eth_type_vlan(proto)) {
-		struct vlan_hdr vhdr, *vh;
-
-		vh = skb_header_pointer(skb, offset, sizeof(vhdr), &vhdr);
-		if (!vh)
-			break;
-
-		proto = vh->h_vlan_encapsulated_proto;
-		offset += sizeof(vhdr);
-	}
-
-	return proto;
-}
-
 static inline bool vlan_hw_offload_capable(netdev_features_t features,
 					   __be16 proto)
 {
@@ -605,10 +579,10 @@ static inline int vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci)
  * Returns the EtherType of the packet, regardless of whether it is
  * vlan encapsulated (normal or hardware accelerated) or not.
  */
-static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type,
+static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type,
 					 int *depth)
 {
-	unsigned int vlan_depth = skb->mac_len;
+	unsigned int vlan_depth = skb->mac_len, parse_depth = VLAN_MAX_DEPTH;
 
 	/* if type is 802.1Q/AD then the header should already be
 	 * present at mac_len - VLAN_HLEN (if mac_len > 0), or at
@@ -623,13 +597,12 @@ static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type,
 			vlan_depth = ETH_HLEN;
 		}
 		do {
-			struct vlan_hdr *vh;
+			struct vlan_hdr vhdr, *vh;
 
-			if (unlikely(!pskb_may_pull(skb,
-						    vlan_depth + VLAN_HLEN)))
+			vh = skb_header_pointer(skb, vlan_depth, sizeof(vhdr), &vhdr);
+			if (unlikely(!vh || !--parse_depth))
 				return 0;
 
-			vh = (struct vlan_hdr *)(skb->data + vlan_depth);
 			type = vh->h_vlan_encapsulated_proto;
 			vlan_depth += VLAN_HLEN;
 		} while (eth_type_vlan(type));
@@ -648,11 +621,25 @@ static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type,
  * Returns the EtherType of the packet, regardless of whether it is
  * vlan encapsulated (normal or hardware accelerated) or not.
  */
-static inline __be16 vlan_get_protocol(struct sk_buff *skb)
+static inline __be16 vlan_get_protocol(const struct sk_buff *skb)
 {
 	return __vlan_get_protocol(skb, skb->protocol, NULL);
 }
 
+/* A getter for the SKB protocol field which will handle VLAN tags consistently
+ * whether VLAN acceleration is enabled or not.
+ */
+static inline __be16 skb_protocol(const struct sk_buff *skb, bool skip_vlan)
+{
+	if (!skip_vlan)
+		/* VLAN acceleration strips the VLAN header from the skb and
+		 * moves it to skb->vlan_proto
+		 */
+		return skb_vlan_tag_present(skb) ? skb->vlan_proto : skb->protocol;
+
+	return vlan_get_protocol(skb);
+}
+
 static inline void vlan_set_encap_proto(struct sk_buff *skb,
 					struct vlan_hdr *vhdr)
 {
-- 
2.26.2


From eb9b8d657552010d6829600a50cca9f84939a1bd Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 1 Jul 2020 11:43:04 -0700
Subject: [PATCH 21/29] tcp: md5: refine tcp_md5_do_add()/tcp_md5_hash_key()
 barriers

[ Upstream commit e6ced831ef11a2a06e8d00aad9d4fc05b610bf38 ]

My prior fix went a bit too far, according to Herbert and Mathieu.

Since we accept that concurrent TCP MD5 lookups might see inconsistent
keys, we can use READ_ONCE()/WRITE_ONCE() instead of smp_rmb()/smp_wmb()

Clearing all key->key[] is needed to avoid possible KMSAN reports,
if key->keylen is increased. Since tcp_md5_do_add() is not fast path,
using __GFP_ZERO to clear all struct tcp_md5sig_key is simpler.

data_race() was added in linux-5.8 and will prevent KCSAN reports,
this can safely be removed in stable backports, if data_race() is
not yet backported.

v2: use data_race() both in tcp_md5_hash_key() and tcp_md5_do_add()

Fixes: 6a2febec338d ("tcp: md5: add missing memory barriers in tcp_md5_do_add()/tcp_md5_hash_key()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Marco Elver <elver@google.com>
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c      |  6 +++---
 net/ipv4/tcp_ipv4.c | 14 ++++++++++----
 2 files changed, 13 insertions(+), 7 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 7de69e161c34..a3a2b6df2ee2 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3847,13 +3847,13 @@ EXPORT_SYMBOL(tcp_md5_hash_skb_data);
 
 int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, const struct tcp_md5sig_key *key)
 {
-	u8 keylen = key->keylen;
+	u8 keylen = READ_ONCE(key->keylen); /* paired with WRITE_ONCE() in tcp_md5_do_add */
 	struct scatterlist sg;
 
-	smp_rmb(); /* paired with smp_wmb() in tcp_md5_do_add() */
-
 	sg_init_one(&sg, key->key, keylen);
 	ahash_request_set_crypt(hp->md5_req, &sg, NULL, keylen);
+
+	/* tcp_md5_do_add() might change key->key under us */
 	return crypto_ahash_update(hp->md5_req);
 }
 EXPORT_SYMBOL(tcp_md5_hash_key);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 7bb8747d86f1..35f963690a70 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1077,12 +1077,18 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
 
 	key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen);
 	if (key) {
-		/* Pre-existing entry - just update that one. */
+		/* Pre-existing entry - just update that one.
+		 * Note that the key might be used concurrently.
+		 */
 		memcpy(key->key, newkey, newkeylen);
 
-		smp_wmb(); /* pairs with smp_rmb() in tcp_md5_hash_key() */
+		/* Pairs with READ_ONCE() in tcp_md5_hash_key().
+		 * Also note that a reader could catch new key->keylen value
+		 * but old key->key[], this is the reason we use __GFP_ZERO
+		 * at sock_kmalloc() time below these lines.
+		 */
+		WRITE_ONCE(key->keylen, newkeylen);
 
-		key->keylen = newkeylen;
 		return 0;
 	}
 
@@ -1098,7 +1104,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
 		rcu_assign_pointer(tp->md5sig_info, md5sig);
 	}
 
-	key = sock_kmalloc(sk, sizeof(*key), gfp);
+	key = sock_kmalloc(sk, sizeof(*key), gfp | __GFP_ZERO);
 	if (!key)
 		return -ENOMEM;
 	if (!tcp_alloc_md5sig_pool()) {
-- 
2.26.2


From a9625836da6a36292b03ee3e52b15a3a949f9080 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 1 Jul 2020 18:39:33 -0700
Subject: [PATCH 22/29] tcp: md5: allow changing MD5 keys in all socket states

[ Upstream commit 1ca0fafd73c5268e8fc4b997094b8bb2bfe8deea ]

This essentially reverts commit 721230326891 ("tcp: md5: reject TCP_MD5SIG
or TCP_MD5SIG_EXT on established sockets")

Mathieu reported that many vendors BGP implementations can
actually switch TCP MD5 on established flows.

Quoting Mathieu :
   Here is a list of a few network vendors along with their behavior
   with respect to TCP MD5:

   - Cisco: Allows for password to be changed, but within the hold-down
     timer (~180 seconds).
   - Juniper: When password is initially set on active connection it will
     reset, but after that any subsequent password changes no network
     resets.
   - Nokia: No notes on if they flap the tcp connection or not.
   - Ericsson/RedBack: Allows for 2 password (old/new) to co-exist until
     both sides are ok with new passwords.
   - Meta-Switch: Expects the password to be set before a connection is
     attempted, but no further info on whether they reset the TCP
     connection on a change.
   - Avaya: Disable the neighbor, then set password, then re-enable.
   - Zebos: Would normally allow the change when socket connected.

We can revert my prior change because commit 9424e2e7ad93 ("tcp: md5: fix potential
overestimation of TCP option space") removed the leak of 4 kernel bytes to
the wire that was the main reason for my patch.

While doing my investigations, I found a bug when a MD5 key is changed, leading
to these commits that stable teams want to consider before backporting this revert :

 Commit 6a2febec338d ("tcp: md5: add missing memory barriers in tcp_md5_do_add()/tcp_md5_hash_key()")
 Commit e6ced831ef11 ("tcp: md5: refine tcp_md5_do_add()/tcp_md5_hash_key() barriers")

Fixes: 721230326891 "tcp: md5: reject TCP_MD5SIG or TCP_MD5SIG_EXT on established sockets"
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index a3a2b6df2ee2..840901154210 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3088,10 +3088,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 #ifdef CONFIG_TCP_MD5SIG
 	case TCP_MD5SIG:
 	case TCP_MD5SIG_EXT:
-		if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))
-			err = tp->af_specific->md5_parse(sk, optname, optval, optlen);
-		else
-			err = -EINVAL;
+		err = tp->af_specific->md5_parse(sk, optname, optval, optlen);
 		break;
 #endif
 	case TCP_USER_TIMEOUT:
-- 
2.26.2


From 62dfd3aa0c9a528ecb52a6cf45ab5fbf45e08668 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 2 Jul 2020 11:52:56 -0700
Subject: [PATCH 23/29] cgroup: fix cgroup_sk_alloc() for sk_clone_lock()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit ad0f75e5f57ccbceec13274e1e242f2b5a6397ed ]

When we clone a socket in sk_clone_lock(), its sk_cgrp_data is
copied, so the cgroup refcnt must be taken too. And, unlike the
sk_alloc() path, sock_update_netprioidx() is not called here.
Therefore, it is safe and necessary to grab the cgroup refcnt
even when cgroup_sk_alloc is disabled.

sk_clone_lock() is in BH context anyway, the in_interrupt()
would terminate this function if called there. And for sk_alloc()
skcd->val is always zero. So it's safe to factor out the code
to make it more readable.

The global variable 'cgroup_sk_alloc_disabled' is used to determine
whether to take these reference counts. It is impossible to make
the reference counting correct unless we save this bit of information
in skcd->val. So, add a new bit there to record whether the socket
has already taken the reference counts. This obviously relies on
kmalloc() to align cgroup pointers to at least 4 bytes,
ARCH_KMALLOC_MINALIGN is certainly larger than that.

This bug seems to be introduced since the beginning, commit
d979a39d7242 ("cgroup: duplicate cgroup reference when cloning sockets")
tried to fix it but not compeletely. It seems not easy to trigger until
the recent commit 090e28b229af
("netprio_cgroup: Fix unlimited memory leak of v2 cgroups") was merged.

Fixes: bd1060a1d671 ("sock, cgroup: add sock->sk_cgroup")
Reported-by: Cameron Berkenpas <cam@neo-zeon.de>
Reported-by: Peter Geis <pgwipeout@gmail.com>
Reported-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Reported-by: Daniël Sonck <dsonck92@gmail.com>
Reported-by: Zhang Qiang <qiang.zhang@windriver.com>
Tested-by: Cameron Berkenpas <cam@neo-zeon.de>
Tested-by: Peter Geis <pgwipeout@gmail.com>
Tested-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Zefan Li <lizefan@huawei.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Roman Gushchin <guro@fb.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/cgroup-defs.h |  6 ++++--
 include/linux/cgroup.h      |  4 +++-
 kernel/cgroup/cgroup.c      | 31 +++++++++++++++++++------------
 net/core/sock.c             |  2 +-
 4 files changed, 27 insertions(+), 16 deletions(-)

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 430e219e3aba..2ebacb7ef501 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -797,7 +797,8 @@ struct sock_cgroup_data {
 	union {
 #ifdef __LITTLE_ENDIAN
 		struct {
-			u8	is_data;
+			u8	is_data : 1;
+			u8	no_refcnt : 1;
 			u8	padding;
 			u16	prioidx;
 			u32	classid;
@@ -807,7 +808,8 @@ struct sock_cgroup_data {
 			u32	classid;
 			u16	prioidx;
 			u8	padding;
-			u8	is_data;
+			u8	no_refcnt : 1;
+			u8	is_data : 1;
 		} __packed;
 #endif
 		u64		val;
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 57577075d204..202852383ae9 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -822,6 +822,7 @@ extern spinlock_t cgroup_sk_update_lock;
 
 void cgroup_sk_alloc_disable(void);
 void cgroup_sk_alloc(struct sock_cgroup_data *skcd);
+void cgroup_sk_clone(struct sock_cgroup_data *skcd);
 void cgroup_sk_free(struct sock_cgroup_data *skcd);
 
 static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd)
@@ -835,7 +836,7 @@ static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd)
 	 */
 	v = READ_ONCE(skcd->val);
 
-	if (v & 1)
+	if (v & 3)
 		return &cgrp_dfl_root.cgrp;
 
 	return (struct cgroup *)(unsigned long)v ?: &cgrp_dfl_root.cgrp;
@@ -847,6 +848,7 @@ static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd)
 #else	/* CONFIG_CGROUP_DATA */
 
 static inline void cgroup_sk_alloc(struct sock_cgroup_data *skcd) {}
+static inline void cgroup_sk_clone(struct sock_cgroup_data *skcd) {}
 static inline void cgroup_sk_free(struct sock_cgroup_data *skcd) {}
 
 #endif	/* CONFIG_CGROUP_DATA */
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 7c9e97553a00..35faf082a709 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -6379,18 +6379,8 @@ void cgroup_sk_alloc_disable(void)
 
 void cgroup_sk_alloc(struct sock_cgroup_data *skcd)
 {
-	if (cgroup_sk_alloc_disabled)
-		return;
-
-	/* Socket clone path */
-	if (skcd->val) {
-		/*
-		 * We might be cloning a socket which is left in an empty
-		 * cgroup and the cgroup might have already been rmdir'd.
-		 * Don't use cgroup_get_live().
-		 */
-		cgroup_get(sock_cgroup_ptr(skcd));
-		cgroup_bpf_get(sock_cgroup_ptr(skcd));
+	if (cgroup_sk_alloc_disabled) {
+		skcd->no_refcnt = 1;
 		return;
 	}
 
@@ -6415,10 +6405,27 @@ void cgroup_sk_alloc(struct sock_cgroup_data *skcd)
 	rcu_read_unlock();
 }
 
+void cgroup_sk_clone(struct sock_cgroup_data *skcd)
+{
+	if (skcd->val) {
+		if (skcd->no_refcnt)
+			return;
+		/*
+		 * We might be cloning a socket which is left in an empty
+		 * cgroup and the cgroup might have already been rmdir'd.
+		 * Don't use cgroup_get_live().
+		 */
+		cgroup_get(sock_cgroup_ptr(skcd));
+		cgroup_bpf_get(sock_cgroup_ptr(skcd));
+	}
+}
+
 void cgroup_sk_free(struct sock_cgroup_data *skcd)
 {
 	struct cgroup *cgrp = sock_cgroup_ptr(skcd);
 
+	if (skcd->no_refcnt)
+		return;
 	cgroup_bpf_put(cgrp);
 	cgroup_put(cgrp);
 }
diff --git a/net/core/sock.c b/net/core/sock.c
index 078791a6649a..33a232974374 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1837,7 +1837,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		/* sk->sk_memcg will be populated at accept() time */
 		newsk->sk_memcg = NULL;
 
-		cgroup_sk_alloc(&newsk->sk_cgrp_data);
+		cgroup_sk_clone(&newsk->sk_cgrp_data);
 
 		rcu_read_lock();
 		filter = rcu_dereference(sk->sk_filter);
-- 
2.26.2


From 2f0be6058f3eeec46b4e2750a1a8e53bef1cfb73 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 9 Jul 2020 16:28:44 -0700
Subject: [PATCH 24/29] cgroup: Fix sock_cgroup_data on big-endian.

[ Upstream commit 14b032b8f8fce03a546dcf365454bec8c4a58d7d ]

In order for no_refcnt and is_data to be the lowest order two
bits in the 'val' we have to pad out the bitfield of the u8.

Fixes: ad0f75e5f57c ("cgroup: fix cgroup_sk_alloc() for sk_clone_lock()")
Reported-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/cgroup-defs.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 2ebacb7ef501..1ccfa3779e18 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -799,6 +799,7 @@ struct sock_cgroup_data {
 		struct {
 			u8	is_data : 1;
 			u8	no_refcnt : 1;
+			u8	unused : 6;
 			u8	padding;
 			u16	prioidx;
 			u32	classid;
@@ -808,6 +809,7 @@ struct sock_cgroup_data {
 			u32	classid;
 			u16	prioidx;
 			u8	padding;
+			u8	unused : 6;
 			u8	no_refcnt : 1;
 			u8	is_data : 1;
 		} __packed;
-- 
2.26.2


From 2ed0c236f99079b1a36405497a96120f89a16aec Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Fri, 10 Jul 2020 16:41:38 +0300
Subject: [PATCH 25/29] mlxsw: spectrum_router: Remove inappropriate usage of
 WARN_ON()

[ Upstream commit d9d5420273997664a1c09151ca86ac993f2f89c1 ]

We should not trigger a warning when a memory allocation fails. Remove
the WARN_ON().

The warning is constantly triggered by syzkaller when it is injecting
faults:

[ 2230.758664] FAULT_INJECTION: forcing a failure.
[ 2230.758664] name failslab, interval 1, probability 0, space 0, times 0
[ 2230.762329] CPU: 3 PID: 1407 Comm: syz-executor.0 Not tainted 5.8.0-rc2+ #28
...
[ 2230.898175] WARNING: CPU: 3 PID: 1407 at drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:6265 mlxsw_sp_router_fib_event+0xfad/0x13e0
[ 2230.898179] Kernel panic - not syncing: panic_on_warn set ...
[ 2230.898183] CPU: 3 PID: 1407 Comm: syz-executor.0 Not tainted 5.8.0-rc2+ #28
[ 2230.898190] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014

Fixes: 3057224e014c ("mlxsw: spectrum_router: Implement FIB offload in deferred work")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index efdf8cb5114c..2f013fc71698 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -6287,7 +6287,7 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb,
 	}
 
 	fib_work = kzalloc(sizeof(*fib_work), GFP_ATOMIC);
-	if (WARN_ON(!fib_work))
+	if (!fib_work)
 		return NOTIFY_BAD;
 
 	fib_work->mlxsw_sp = router->mlxsw_sp;
-- 
2.26.2


From c38d65760a74df59edda23b9c0386beb5c843030 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Fri, 10 Jul 2020 16:41:39 +0300
Subject: [PATCH 26/29] mlxsw: pci: Fix use-after-free in case of failed
 devlink reload

[ Upstream commit c4317b11675b99af6641662ebcbd3c6010600e64 ]

In case devlink reload failed, it is possible to trigger a
use-after-free when querying the kernel for device info via 'devlink dev
info' [1].

This happens because as part of the reload error path the PCI command
interface is de-initialized and its mailboxes are freed. When the
devlink '->info_get()' callback is invoked the device is queried via the
command interface and the freed mailboxes are accessed.

Fix this by initializing the command interface once during probe and not
during every reload.

This is consistent with the other bus used by mlxsw (i.e., 'mlxsw_i2c')
and also allows user space to query the running firmware version (for
example) from the device after a failed reload.

[1]
BUG: KASAN: use-after-free in memcpy include/linux/string.h:406 [inline]
BUG: KASAN: use-after-free in mlxsw_pci_cmd_exec+0x177/0xa60 drivers/net/ethernet/mellanox/mlxsw/pci.c:1675
Write of size 4096 at addr ffff88810ae32000 by task syz-executor.1/2355

CPU: 1 PID: 2355 Comm: syz-executor.1 Not tainted 5.8.0-rc2+ #29
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0xf6/0x16e lib/dump_stack.c:118
 print_address_description.constprop.0+0x1c/0x250 mm/kasan/report.c:383
 __kasan_report mm/kasan/report.c:513 [inline]
 kasan_report.cold+0x1f/0x37 mm/kasan/report.c:530
 check_memory_region_inline mm/kasan/generic.c:186 [inline]
 check_memory_region+0x14e/0x1b0 mm/kasan/generic.c:192
 memcpy+0x39/0x60 mm/kasan/common.c:106
 memcpy include/linux/string.h:406 [inline]
 mlxsw_pci_cmd_exec+0x177/0xa60 drivers/net/ethernet/mellanox/mlxsw/pci.c:1675
 mlxsw_cmd_exec+0x249/0x550 drivers/net/ethernet/mellanox/mlxsw/core.c:2335
 mlxsw_cmd_access_reg drivers/net/ethernet/mellanox/mlxsw/cmd.h:859 [inline]
 mlxsw_core_reg_access_cmd drivers/net/ethernet/mellanox/mlxsw/core.c:1938 [inline]
 mlxsw_core_reg_access+0x2f6/0x540 drivers/net/ethernet/mellanox/mlxsw/core.c:1985
 mlxsw_reg_query drivers/net/ethernet/mellanox/mlxsw/core.c:2000 [inline]
 mlxsw_devlink_info_get+0x17f/0x6e0 drivers/net/ethernet/mellanox/mlxsw/core.c:1090
 devlink_nl_info_fill.constprop.0+0x13c/0x2d0 net/core/devlink.c:4588
 devlink_nl_cmd_info_get_dumpit+0x246/0x460 net/core/devlink.c:4648
 genl_lock_dumpit+0x85/0xc0 net/netlink/genetlink.c:575
 netlink_dump+0x515/0xe50 net/netlink/af_netlink.c:2245
 __netlink_dump_start+0x53d/0x830 net/netlink/af_netlink.c:2353
 genl_family_rcv_msg_dumpit.isra.0+0x296/0x300 net/netlink/genetlink.c:638
 genl_family_rcv_msg net/netlink/genetlink.c:733 [inline]
 genl_rcv_msg+0x78d/0x9d0 net/netlink/genetlink.c:753
 netlink_rcv_skb+0x152/0x440 net/netlink/af_netlink.c:2469
 genl_rcv+0x24/0x40 net/netlink/genetlink.c:764
 netlink_unicast_kernel net/netlink/af_netlink.c:1303 [inline]
 netlink_unicast+0x53a/0x750 net/netlink/af_netlink.c:1329
 netlink_sendmsg+0x850/0xd90 net/netlink/af_netlink.c:1918
 sock_sendmsg_nosec net/socket.c:652 [inline]
 sock_sendmsg+0x150/0x190 net/socket.c:672
 ____sys_sendmsg+0x6d8/0x840 net/socket.c:2363
 ___sys_sendmsg+0xff/0x170 net/socket.c:2417
 __sys_sendmsg+0xe5/0x1b0 net/socket.c:2450
 do_syscall_64+0x56/0xa0 arch/x86/entry/common.c:359
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: a9c8336f6544 ("mlxsw: core: Add support for devlink info command")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/pci.c | 54 ++++++++++++++++-------
 1 file changed, 38 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index f3d1f9411d10..aa4fef789084 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -1401,23 +1401,12 @@ static int mlxsw_pci_init(void *bus_priv, struct mlxsw_core *mlxsw_core,
 	u16 num_pages;
 	int err;
 
-	mutex_init(&mlxsw_pci->cmd.lock);
-	init_waitqueue_head(&mlxsw_pci->cmd.wait);
-
 	mlxsw_pci->core = mlxsw_core;
 
 	mbox = mlxsw_cmd_mbox_alloc();
 	if (!mbox)
 		return -ENOMEM;
 
-	err = mlxsw_pci_mbox_alloc(mlxsw_pci, &mlxsw_pci->cmd.in_mbox);
-	if (err)
-		goto mbox_put;
-
-	err = mlxsw_pci_mbox_alloc(mlxsw_pci, &mlxsw_pci->cmd.out_mbox);
-	if (err)
-		goto err_out_mbox_alloc;
-
 	err = mlxsw_pci_sw_reset(mlxsw_pci, mlxsw_pci->id);
 	if (err)
 		goto err_sw_reset;
@@ -1524,9 +1513,6 @@ static int mlxsw_pci_init(void *bus_priv, struct mlxsw_core *mlxsw_core,
 	mlxsw_pci_free_irq_vectors(mlxsw_pci);
 err_alloc_irq:
 err_sw_reset:
-	mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.out_mbox);
-err_out_mbox_alloc:
-	mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.in_mbox);
 mbox_put:
 	mlxsw_cmd_mbox_free(mbox);
 	return err;
@@ -1540,8 +1526,6 @@ static void mlxsw_pci_fini(void *bus_priv)
 	mlxsw_pci_aqs_fini(mlxsw_pci);
 	mlxsw_pci_fw_area_fini(mlxsw_pci);
 	mlxsw_pci_free_irq_vectors(mlxsw_pci);
-	mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.out_mbox);
-	mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.in_mbox);
 }
 
 static struct mlxsw_pci_queue *
@@ -1755,6 +1739,37 @@ static const struct mlxsw_bus mlxsw_pci_bus = {
 	.features		= MLXSW_BUS_F_TXRX | MLXSW_BUS_F_RESET,
 };
 
+static int mlxsw_pci_cmd_init(struct mlxsw_pci *mlxsw_pci)
+{
+	int err;
+
+	mutex_init(&mlxsw_pci->cmd.lock);
+	init_waitqueue_head(&mlxsw_pci->cmd.wait);
+
+	err = mlxsw_pci_mbox_alloc(mlxsw_pci, &mlxsw_pci->cmd.in_mbox);
+	if (err)
+		goto err_in_mbox_alloc;
+
+	err = mlxsw_pci_mbox_alloc(mlxsw_pci, &mlxsw_pci->cmd.out_mbox);
+	if (err)
+		goto err_out_mbox_alloc;
+
+	return 0;
+
+err_out_mbox_alloc:
+	mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.in_mbox);
+err_in_mbox_alloc:
+	mutex_destroy(&mlxsw_pci->cmd.lock);
+	return err;
+}
+
+static void mlxsw_pci_cmd_fini(struct mlxsw_pci *mlxsw_pci)
+{
+	mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.out_mbox);
+	mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.in_mbox);
+	mutex_destroy(&mlxsw_pci->cmd.lock);
+}
+
 static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	const char *driver_name = pdev->driver->name;
@@ -1810,6 +1825,10 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	mlxsw_pci->pdev = pdev;
 	pci_set_drvdata(pdev, mlxsw_pci);
 
+	err = mlxsw_pci_cmd_init(mlxsw_pci);
+	if (err)
+		goto err_pci_cmd_init;
+
 	mlxsw_pci->bus_info.device_kind = driver_name;
 	mlxsw_pci->bus_info.device_name = pci_name(mlxsw_pci->pdev);
 	mlxsw_pci->bus_info.dev = &pdev->dev;
@@ -1827,6 +1846,8 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	return 0;
 
 err_bus_device_register:
+	mlxsw_pci_cmd_fini(mlxsw_pci);
+err_pci_cmd_init:
 	iounmap(mlxsw_pci->hw_addr);
 err_ioremap:
 err_pci_resource_len_check:
@@ -1844,6 +1865,7 @@ static void mlxsw_pci_remove(struct pci_dev *pdev)
 	struct mlxsw_pci *mlxsw_pci = pci_get_drvdata(pdev);
 
 	mlxsw_core_bus_device_unregister(mlxsw_pci->core, false);
+	mlxsw_pci_cmd_fini(mlxsw_pci);
 	iounmap(mlxsw_pci->hw_addr);
 	pci_release_regions(mlxsw_pci->pdev);
 	pci_disable_device(mlxsw_pci->pdev);
-- 
2.26.2


From 17c2243745b03d9df16030fdc8a8dc8503cb6cca Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Sun, 14 Jun 2020 17:31:26 +0300
Subject: [PATCH 27/29] net/mlx5: Fix eeprom support for SFP module

[ Upstream commit 47afbdd2fa4c5775c383ba376a3d1da7d7f694dc ]

Fix eeprom SFP query support by setting i2c_addr, offset and page number
correctly. Unlike QSFP modules, SFP eeprom params are as follow:
- i2c_addr is 0x50 for offset 0 - 255 and 0x51 for offset 256 - 511.
- Page number is always zero.
- Page offset is always relative to zero.

As part of eeprom query, query the module ID (SFP / QSFP*) via helper
function to set the params accordingly.

In addition, change mlx5_qsfp_eeprom_page() input type to be u16 to avoid
unnecessary casting.

Fixes: a708fb7b1f8d ("net/mlx5e: ethtool, Add support for EEPROM high pages query")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/port.c    | 93 +++++++++++++++----
 1 file changed, 77 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index cc262b30aed5..dc589322940c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -293,7 +293,40 @@ static int mlx5_query_module_num(struct mlx5_core_dev *dev, int *module_num)
 	return 0;
 }
 
-static int mlx5_eeprom_page(int offset)
+static int mlx5_query_module_id(struct mlx5_core_dev *dev, int module_num,
+				u8 *module_id)
+{
+	u32 in[MLX5_ST_SZ_DW(mcia_reg)] = {};
+	u32 out[MLX5_ST_SZ_DW(mcia_reg)];
+	int err, status;
+	u8 *ptr;
+
+	MLX5_SET(mcia_reg, in, i2c_device_address, MLX5_I2C_ADDR_LOW);
+	MLX5_SET(mcia_reg, in, module, module_num);
+	MLX5_SET(mcia_reg, in, device_address, 0);
+	MLX5_SET(mcia_reg, in, page_number, 0);
+	MLX5_SET(mcia_reg, in, size, 1);
+	MLX5_SET(mcia_reg, in, l, 0);
+
+	err = mlx5_core_access_reg(dev, in, sizeof(in), out,
+				   sizeof(out), MLX5_REG_MCIA, 0, 0);
+	if (err)
+		return err;
+
+	status = MLX5_GET(mcia_reg, out, status);
+	if (status) {
+		mlx5_core_err(dev, "query_mcia_reg failed: status: 0x%x\n",
+			      status);
+		return -EIO;
+	}
+	ptr = MLX5_ADDR_OF(mcia_reg, out, dword_0);
+
+	*module_id = ptr[0];
+
+	return 0;
+}
+
+static int mlx5_qsfp_eeprom_page(u16 offset)
 {
 	if (offset < MLX5_EEPROM_PAGE_LENGTH)
 		/* Addresses between 0-255 - page 00 */
@@ -307,7 +340,7 @@ static int mlx5_eeprom_page(int offset)
 		    MLX5_EEPROM_HIGH_PAGE_LENGTH);
 }
 
-static int mlx5_eeprom_high_page_offset(int page_num)
+static int mlx5_qsfp_eeprom_high_page_offset(int page_num)
 {
 	if (!page_num) /* Page 0 always start from low page */
 		return 0;
@@ -316,35 +349,62 @@ static int mlx5_eeprom_high_page_offset(int page_num)
 	return page_num * MLX5_EEPROM_HIGH_PAGE_LENGTH;
 }
 
+static void mlx5_qsfp_eeprom_params_set(u16 *i2c_addr, int *page_num, u16 *offset)
+{
+	*i2c_addr = MLX5_I2C_ADDR_LOW;
+	*page_num = mlx5_qsfp_eeprom_page(*offset);
+	*offset -=  mlx5_qsfp_eeprom_high_page_offset(*page_num);
+}
+
+static void mlx5_sfp_eeprom_params_set(u16 *i2c_addr, int *page_num, u16 *offset)
+{
+	*i2c_addr = MLX5_I2C_ADDR_LOW;
+	*page_num = 0;
+
+	if (*offset < MLX5_EEPROM_PAGE_LENGTH)
+		return;
+
+	*i2c_addr = MLX5_I2C_ADDR_HIGH;
+	*offset -= MLX5_EEPROM_PAGE_LENGTH;
+}
+
 int mlx5_query_module_eeprom(struct mlx5_core_dev *dev,
 			     u16 offset, u16 size, u8 *data)
 {
-	int module_num, page_num, status, err;
+	int module_num, status, err, page_num = 0;
+	u32 in[MLX5_ST_SZ_DW(mcia_reg)] = {};
 	u32 out[MLX5_ST_SZ_DW(mcia_reg)];
-	u32 in[MLX5_ST_SZ_DW(mcia_reg)];
-	u16 i2c_addr;
-	void *ptr = MLX5_ADDR_OF(mcia_reg, out, dword_0);
+	u16 i2c_addr = 0;
+	u8 module_id;
+	void *ptr;
 
 	err = mlx5_query_module_num(dev, &module_num);
 	if (err)
 		return err;
 
-	memset(in, 0, sizeof(in));
-	size = min_t(int, size, MLX5_EEPROM_MAX_BYTES);
-
-	/* Get the page number related to the given offset */
-	page_num = mlx5_eeprom_page(offset);
+	err = mlx5_query_module_id(dev, module_num, &module_id);
+	if (err)
+		return err;
 
-	/* Set the right offset according to the page number,
-	 * For page_num > 0, relative offset is always >= 128 (high page).
-	 */
-	offset -= mlx5_eeprom_high_page_offset(page_num);
+	switch (module_id) {
+	case MLX5_MODULE_ID_SFP:
+		mlx5_sfp_eeprom_params_set(&i2c_addr, &page_num, &offset);
+		break;
+	case MLX5_MODULE_ID_QSFP:
+	case MLX5_MODULE_ID_QSFP_PLUS:
+	case MLX5_MODULE_ID_QSFP28:
+		mlx5_qsfp_eeprom_params_set(&i2c_addr, &page_num, &offset);
+		break;
+	default:
+		mlx5_core_err(dev, "Module ID not recognized: 0x%x\n", module_id);
+		return -EINVAL;
+	}
 
 	if (offset + size > MLX5_EEPROM_PAGE_LENGTH)
 		/* Cross pages read, read until offset 256 in low page */
 		size -= offset + size - MLX5_EEPROM_PAGE_LENGTH;
 
-	i2c_addr = MLX5_I2C_ADDR_LOW;
+	size = min_t(int, size, MLX5_EEPROM_MAX_BYTES);
 
 	MLX5_SET(mcia_reg, in, l, 0);
 	MLX5_SET(mcia_reg, in, module, module_num);
@@ -365,6 +425,7 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev,
 		return -EIO;
 	}
 
+	ptr = MLX5_ADDR_OF(mcia_reg, out, dword_0);
 	memcpy(data, ptr, size);
 
 	return size;
-- 
2.26.2


From d4ed5ae8fd6f4b07aa798c588f6ab1478cf84e51 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 1 Jul 2020 16:00:06 -0400
Subject: [PATCH 28/29] ip: Fix SO_MARK in RST, ACK and ICMP packets

[ Upstream commit 0da7536fb47f51df89ccfcb1fa09f249d9accec5 ]

When no full socket is available, skbs are sent over a per-netns
control socket. Its sk_mark is temporarily adjusted to match that
of the real (request or timewait) socket or to reflect an incoming
skb, so that the outgoing skb inherits this in __ip_make_skb.

Introduction of the socket cookie mark field broke this. Now the
skb is set through the cookie and cork:

<caller>		# init sockc.mark from sk_mark or cmsg
ip_append_data
  ip_setup_cork		# convert sockc.mark to cork mark
ip_push_pending_frames
  ip_finish_skb
    __ip_make_skb	# set skb->mark to cork mark

But I missed these special control sockets. Update all callers of
__ip(6)_make_skb that were originally missed.

For IPv6, the same two icmp(v6) paths are affected. The third
case is not, as commit 92e55f412cff ("tcp: don't annotate
mark on control socket from tcp_v6_send_response()") replaced
the ctl_sk->sk_mark with passing the mark field directly as a
function argument. That commit predates the commit that
introduced the bug.

Fixes: c6af0c227a22 ("ip: support SO_MARK cmsg")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Reported-by: Martin KaFai Lau <kafai@fb.com>
Reviewed-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/icmp.c      | 4 ++--
 net/ipv4/ip_output.c | 2 +-
 net/ipv6/icmp.c      | 4 ++--
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index ac95ba78b903..73f46cb5e51d 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -427,7 +427,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 
 	ipcm_init(&ipc);
 	inet->tos = ip_hdr(skb)->tos;
-	sk->sk_mark = mark;
+	ipc.sockc.mark = mark;
 	daddr = ipc.addr = ip_hdr(skb)->saddr;
 	saddr = fib_compute_spec_dst(skb);
 
@@ -709,10 +709,10 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
 	icmp_param.skb	  = skb_in;
 	icmp_param.offset = skb_network_offset(skb_in);
 	inet_sk(sk)->tos = tos;
-	sk->sk_mark = mark;
 	ipcm_init(&ipc);
 	ipc.addr = iph->saddr;
 	ipc.opt = &icmp_param.replyopts.opt;
+	ipc.sockc.mark = mark;
 
 	rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, mark,
 			       type, code, &icmp_param);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index b268ee1c1b44..b36c4a3159e5 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1704,7 +1704,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 	sk->sk_protocol = ip_hdr(skb)->protocol;
 	sk->sk_bound_dev_if = arg->bound_dev_if;
 	sk->sk_sndbuf = sysctl_wmem_default;
-	sk->sk_mark = fl4.flowi4_mark;
+	ipc.sockc.mark = fl4.flowi4_mark;
 	err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base,
 			     len, 0, &ipc, &rt, MSG_DONTWAIT);
 	if (unlikely(err)) {
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 62c997201970..7d3a3894f785 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -535,7 +535,6 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 	if (!sk)
 		goto out_bh_enable;
 
-	sk->sk_mark = mark;
 	np = inet6_sk(sk);
 
 	if (!icmpv6_xrlim_allow(sk, type, &fl6))
@@ -552,6 +551,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 		fl6.flowi6_oif = np->ucast_oif;
 
 	ipcm6_init_sk(&ipc6, np);
+	ipc6.sockc.mark = mark;
 	fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
 
 	dst = icmpv6_route_lookup(net, skb, sk, &fl6);
@@ -720,7 +720,6 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	sk = icmpv6_xmit_lock(net);
 	if (!sk)
 		goto out_bh_enable;
-	sk->sk_mark = mark;
 	np = inet6_sk(sk);
 
 	if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
@@ -748,6 +747,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	ipcm6_init_sk(&ipc6, np);
 	ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
 	ipc6.tclass = ipv6_get_dsfield(ipv6_hdr(skb));
+	ipc6.sockc.mark = mark;
 
 	if (ip6_append_data(sk, icmpv6_getfrag, &msg,
 			    skb->len + sizeof(struct icmp6hdr),
-- 
2.26.2


From d505a3ed9cf5087ffc0b8cf43ba5f534460caca8 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Mon, 15 Jun 2020 12:48:47 +0300
Subject: [PATCH 29/29] net/mlx5e: Fix 50G per lane indication

[ Upstream commit 6a1cf4e443a3b0a4d690d3c93b84b1e9cbfcb1bd ]

Some released FW versions mistakenly don't set the capability that 50G
per lane link-modes are supported for VFs (ptys_extended_ethernet
capability bit). When the capability is unset, read
PTYS.ext_eth_proto_capability (always reliable).
If PTYS.ext_eth_proto_capability is valid (has a non-zero value)
conclude that the HCA supports 50G per lane. Otherwise, conclude that
the HCA doesn't support 50G per lane.

Fixes: a08b4ed1373d ("net/mlx5: Add support to ext_* fields introduced in Port Type and Speed register")
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en/port.c | 21 ++++++++++++++++---
 .../net/ethernet/mellanox/mlx5/core/en/port.h |  2 +-
 .../ethernet/mellanox/mlx5/core/en_ethtool.c  |  8 +++----
 3 files changed, 23 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
index fce6eccdcf8b..fa81a97f6ba9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
@@ -78,11 +78,26 @@ static const u32 mlx5e_ext_link_speed[MLX5E_EXT_LINK_MODES_NUMBER] = {
 	[MLX5E_400GAUI_8]			= 400000,
 };
 
+bool mlx5e_ptys_ext_supported(struct mlx5_core_dev *mdev)
+{
+	struct mlx5e_port_eth_proto eproto;
+	int err;
+
+	if (MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet))
+		return true;
+
+	err = mlx5_port_query_eth_proto(mdev, 1, true, &eproto);
+	if (err)
+		return false;
+
+	return !!eproto.cap;
+}
+
 static void mlx5e_port_get_speed_arr(struct mlx5_core_dev *mdev,
 				     const u32 **arr, u32 *size,
 				     bool force_legacy)
 {
-	bool ext = force_legacy ? false : MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+	bool ext = force_legacy ? false : mlx5e_ptys_ext_supported(mdev);
 
 	*size = ext ? ARRAY_SIZE(mlx5e_ext_link_speed) :
 		      ARRAY_SIZE(mlx5e_link_speed);
@@ -177,7 +192,7 @@ int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
 	bool ext;
 	int err;
 
-	ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+	ext = mlx5e_ptys_ext_supported(mdev);
 	err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto);
 	if (err)
 		goto out;
@@ -205,7 +220,7 @@ int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
 	int err;
 	int i;
 
-	ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+	ext = mlx5e_ptys_ext_supported(mdev);
 	err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto);
 	if (err)
 		return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
index 4a7f4497692b..e196888f7056 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
@@ -54,7 +54,7 @@ int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
 int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
 u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed,
 			       bool force_legacy);
-
+bool mlx5e_ptys_ext_supported(struct mlx5_core_dev *mdev);
 int mlx5e_port_query_pbmc(struct mlx5_core_dev *mdev, void *out);
 int mlx5e_port_set_pbmc(struct mlx5_core_dev *mdev, void *in);
 int mlx5e_port_query_priority2buffer(struct mlx5_core_dev *mdev, u8 *buffer);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 39ee32518b10..8cd529556b21 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -200,7 +200,7 @@ static void mlx5e_ethtool_get_speed_arr(struct mlx5_core_dev *mdev,
 					struct ptys2ethtool_config **arr,
 					u32 *size)
 {
-	bool ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+	bool ext = mlx5e_ptys_ext_supported(mdev);
 
 	*arr = ext ? ptys2ext_ethtool_table : ptys2legacy_ethtool_table;
 	*size = ext ? ARRAY_SIZE(ptys2ext_ethtool_table) :
@@ -871,7 +871,7 @@ static void get_lp_advertising(struct mlx5_core_dev *mdev, u32 eth_proto_lp,
 			       struct ethtool_link_ksettings *link_ksettings)
 {
 	unsigned long *lp_advertising = link_ksettings->link_modes.lp_advertising;
-	bool ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+	bool ext = mlx5e_ptys_ext_supported(mdev);
 
 	ptys2ethtool_adver_link(lp_advertising, eth_proto_lp, ext);
 }
@@ -900,7 +900,7 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv,
 			   __func__, err);
 		goto err_query_regs;
 	}
-	ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+	ext = !!MLX5_GET_ETH_PROTO(ptys_reg, out, true, eth_proto_capability);
 	eth_proto_cap    = MLX5_GET_ETH_PROTO(ptys_reg, out, ext,
 					      eth_proto_capability);
 	eth_proto_admin  = MLX5_GET_ETH_PROTO(ptys_reg, out, ext,
@@ -1052,7 +1052,7 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 	autoneg = link_ksettings->base.autoneg;
 	speed = link_ksettings->base.speed;
 
-	ext_supported = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+	ext_supported = mlx5e_ptys_ext_supported(mdev);
 	ext = ext_requested(autoneg, adver, ext_supported);
 	if (!ext_supported && ext)
 		return -EOPNOTSUPP;
-- 
2.26.2


[-- Attachment #3: net_57.mbox --]
[-- Type: Application/Octet-Stream, Size: 163990 bytes --]

From 2cd18c628c0f2c6c74be2be76136344047699def Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Fri, 10 Jul 2020 12:55:08 +0200
Subject: [PATCH 01/44] bnxt_en: fix NULL dereference in case SR-IOV
 configuration fails

[ Upstream commit c8b1d7436045d3599bae56aef1682813ecccaad7 ]

we need to set 'active_vfs' back to 0, if something goes wrong during the
allocation of SR-IOV resources: otherwise, further VF configurations will
wrongly assume that bp->pf.vf[x] are valid memory locations, and commands
like the ones in the following sequence:

 # echo 2 >/sys/bus/pci/devices/${ADDR}/sriov_numvfs
 # ip link set dev ens1f0np0 up
 # ip link set dev ens1f0np0 vf 0 trust on

will cause a kernel crash similar to this:

 bnxt_en 0000:3b:00.0: not enough MMIO resources for SR-IOV
 BUG: kernel NULL pointer dereference, address: 0000000000000014
 #PF: supervisor read access in kernel mode
 #PF: error_code(0x0000) - not-present page
 PGD 0 P4D 0
 Oops: 0000 [#1] SMP PTI
 CPU: 43 PID: 2059 Comm: ip Tainted: G          I       5.8.0-rc2.upstream+ #871
 Hardware name: Dell Inc. PowerEdge R740/08D89F, BIOS 2.2.11 06/13/2019
 RIP: 0010:bnxt_set_vf_trust+0x5b/0x110 [bnxt_en]
 Code: 44 24 58 31 c0 e8 f5 fb ff ff 85 c0 0f 85 b6 00 00 00 48 8d 1c 5b 41 89 c6 b9 0b 00 00 00 48 c1 e3 04 49 03 9c 24 f0 0e 00 00 <8b> 43 14 89 c2 83 c8 10 83 e2 ef 45 84 ed 49 89 e5 0f 44 c2 4c 89
 RSP: 0018:ffffac6246a1f570 EFLAGS: 00010246
 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 000000000000000b
 RDX: 0000000000000001 RSI: 0000000000000000 RDI: ffff98b28f538900
 RBP: ffff98b28f538900 R08: 0000000000000000 R09: 0000000000000008
 R10: ffffffffb9515be0 R11: ffffac6246a1f678 R12: ffff98b28f538000
 R13: 0000000000000001 R14: 0000000000000000 R15: ffffffffc05451e0
 FS:  00007fde0f688800(0000) GS:ffff98baffd40000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000000014 CR3: 000000104bb0a003 CR4: 00000000007606e0
 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
 PKRU: 55555554
 Call Trace:
  do_setlink+0x994/0xfe0
  __rtnl_newlink+0x544/0x8d0
  rtnl_newlink+0x47/0x70
  rtnetlink_rcv_msg+0x29f/0x350
  netlink_rcv_skb+0x4a/0x110
  netlink_unicast+0x21d/0x300
  netlink_sendmsg+0x329/0x450
  sock_sendmsg+0x5b/0x60
  ____sys_sendmsg+0x204/0x280
  ___sys_sendmsg+0x88/0xd0
  __sys_sendmsg+0x5e/0xa0
  do_syscall_64+0x47/0x80
  entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: c0c050c58d840 ("bnxt_en: New Broadcom ethernet driver.")
Reported-by: Fei Liu <feliu@redhat.com>
CC: Jonathan Toppins <jtoppins@redhat.com>
CC: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Acked-by: Jonathan Toppins <jtoppins@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index cea2f9958a1d..2295f539a641 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -396,6 +396,7 @@ static void bnxt_free_vf_resources(struct bnxt *bp)
 		}
 	}
 
+	bp->pf.active_vfs = 0;
 	kfree(bp->pf.vf);
 	bp->pf.vf = NULL;
 }
@@ -835,7 +836,6 @@ void bnxt_sriov_disable(struct bnxt *bp)
 
 	bnxt_free_vf_resources(bp);
 
-	bp->pf.active_vfs = 0;
 	/* Reclaim all resources for the PF. */
 	rtnl_lock();
 	bnxt_restore_pf_fw_resources(bp);
-- 
2.26.2


From b359d132c6f1c2a95d98a7567b1206f38ada1462 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Linus=20L=C3=BCssing?= <linus.luessing@c0d3.blue>
Date: Sun, 5 Jul 2020 21:10:17 +0200
Subject: [PATCH 02/44] bridge: mcast: Fix MLD2 Report IPv6 payload length
 check
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 5fc6266af7b427243da24f3443a50cd4584aac06 ]

Commit e57f61858b7c ("net: bridge: mcast: fix stale nsrcs pointer in
igmp3/mld2 report handling") introduced a bug in the IPv6 header payload
length check which would potentially lead to rejecting a valid MLD2 Report:

The check needs to take into account the 2 bytes for the "Number of
Sources" field in the "Multicast Address Record" before reading it.
And not the size of a pointer to this field.

Fixes: e57f61858b7c ("net: bridge: mcast: fix stale nsrcs pointer in igmp3/mld2 report handling")
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: Linus Lüssing <linus.luessing@c0d3.blue>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 83490bf73a13..4c4a93abde68 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1007,7 +1007,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br,
 		nsrcs_offset = len + offsetof(struct mld2_grec, grec_nsrcs);
 
 		if (skb_transport_offset(skb) + ipv6_transport_len(skb) <
-		    nsrcs_offset + sizeof(_nsrcs))
+		    nsrcs_offset + sizeof(__nsrcs))
 			return -EINVAL;
 
 		_nsrcs = skb_header_pointer(skb, nsrcs_offset,
-- 
2.26.2


From 48401085e3ce0c5a1200746fdca980080226b037 Mon Sep 17 00:00:00 2001
From: Sean Tranchetti <stranche@codeaurora.org>
Date: Tue, 30 Jun 2020 11:50:17 -0600
Subject: [PATCH 03/44] genetlink: remove genl_bind

[ Upstream commit 1e82a62fec613844da9e558f3493540a5b7a7b67 ]

A potential deadlock can occur during registering or unregistering a
new generic netlink family between the main nl_table_lock and the
cb_lock where each thread wants the lock held by the other, as
demonstrated below.

1) Thread 1 is performing a netlink_bind() operation on a socket. As part
   of this call, it will call netlink_lock_table(), incrementing the
   nl_table_users count to 1.
2) Thread 2 is registering (or unregistering) a genl_family via the
   genl_(un)register_family() API. The cb_lock semaphore will be taken for
   writing.
3) Thread 1 will call genl_bind() as part of the bind operation to handle
   subscribing to GENL multicast groups at the request of the user. It will
   attempt to take the cb_lock semaphore for reading, but it will fail and
   be scheduled away, waiting for Thread 2 to finish the write.
4) Thread 2 will call netlink_table_grab() during the (un)registration
   call. However, as Thread 1 has incremented nl_table_users, it will not
   be able to proceed, and both threads will be stuck waiting for the
   other.

genl_bind() is a noop, unless a genl_family implements the mcast_bind()
function to handle setting up family-specific multicast operations. Since
no one in-tree uses this functionality as Cong pointed out, simply removing
the genl_bind() function will remove the possibility for deadlock, as there
is no attempt by Thread 1 above to take the cb_lock semaphore.

Fixes: c380d9a7afff ("genetlink: pass multicast bind/unbind to families")
Suggested-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Johannes Berg <johannes.berg@intel.com>
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Sean Tranchetti <stranche@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/genetlink.h |  8 -------
 net/netlink/genetlink.c | 49 -----------------------------------------
 2 files changed, 57 deletions(-)

diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 74950663bb00..4cf703d8c30e 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -35,12 +35,6 @@ struct genl_info;
  *	do additional, common, filtering and return an error
  * @post_doit: called after an operation's doit callback, it may
  *	undo operations done by pre_doit, for example release locks
- * @mcast_bind: a socket bound to the given multicast group (which
- *	is given as the offset into the groups array)
- * @mcast_unbind: a socket was unbound from the given multicast group.
- *	Note that unbind() will not be called symmetrically if the
- *	generic netlink family is removed while there are still open
- *	sockets.
  * @attrbuf: buffer to store parsed attributes (private)
  * @mcgrps: multicast groups used by this family
  * @n_mcgrps: number of multicast groups
@@ -64,8 +58,6 @@ struct genl_family {
 	void			(*post_doit)(const struct genl_ops *ops,
 					     struct sk_buff *skb,
 					     struct genl_info *info);
-	int			(*mcast_bind)(struct net *net, int group);
-	void			(*mcast_unbind)(struct net *net, int group);
 	struct nlattr **	attrbuf;	/* private */
 	const struct genl_ops *	ops;
 	const struct genl_multicast_group *mcgrps;
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 9c1c27f3a089..f374a4038c03 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -1088,60 +1088,11 @@ static struct genl_family genl_ctrl __ro_after_init = {
 	.netnsok = true,
 };
 
-static int genl_bind(struct net *net, int group)
-{
-	struct genl_family *f;
-	int err = -ENOENT;
-	unsigned int id;
-
-	down_read(&cb_lock);
-
-	idr_for_each_entry(&genl_fam_idr, f, id) {
-		if (group >= f->mcgrp_offset &&
-		    group < f->mcgrp_offset + f->n_mcgrps) {
-			int fam_grp = group - f->mcgrp_offset;
-
-			if (!f->netnsok && net != &init_net)
-				err = -ENOENT;
-			else if (f->mcast_bind)
-				err = f->mcast_bind(net, fam_grp);
-			else
-				err = 0;
-			break;
-		}
-	}
-	up_read(&cb_lock);
-
-	return err;
-}
-
-static void genl_unbind(struct net *net, int group)
-{
-	struct genl_family *f;
-	unsigned int id;
-
-	down_read(&cb_lock);
-
-	idr_for_each_entry(&genl_fam_idr, f, id) {
-		if (group >= f->mcgrp_offset &&
-		    group < f->mcgrp_offset + f->n_mcgrps) {
-			int fam_grp = group - f->mcgrp_offset;
-
-			if (f->mcast_unbind)
-				f->mcast_unbind(net, fam_grp);
-			break;
-		}
-	}
-	up_read(&cb_lock);
-}
-
 static int __net_init genl_pernet_init(struct net *net)
 {
 	struct netlink_kernel_cfg cfg = {
 		.input		= genl_rcv,
 		.flags		= NL_CFG_F_NONROOT_RECV,
-		.bind		= genl_bind,
-		.unbind		= genl_unbind,
 	};
 
 	/* we'll bump the group number right afterwards */
-- 
2.26.2


From 785f64942db6dba6b7bf888a0f34cc5725e2acb6 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 3 Jul 2020 17:00:32 +0200
Subject: [PATCH 04/44] ipv4: fill fl4_icmp_{type,code} in ping_v4_sendmsg

[ Upstream commit 5eff06902394425c722f0a44d9545909a8800f79 ]

IPv4 ping sockets don't set fl4.fl4_icmp_{type,code}, which leads to
incomplete IPsec ACQUIRE messages being sent to userspace. Currently,
both raw sockets and IPv6 ping sockets set those fields.

Expected output of "ip xfrm monitor":
    acquire proto esp
      sel src 10.0.2.15/32 dst 8.8.8.8/32 proto icmp type 8 code 0 dev ens4
      policy src 10.0.2.15/32 dst 8.8.8.8/32
        <snip>

Currently with ping sockets:
    acquire proto esp
      sel src 10.0.2.15/32 dst 8.8.8.8/32 proto icmp type 0 code 0 dev ens4
      policy src 10.0.2.15/32 dst 8.8.8.8/32
        <snip>

The Libreswan test suite found this problem after Fedora changed the
value for the sysctl net.ipv4.ping_group_range.

Fixes: c319b4d76b9e ("net: ipv4: add IPPROTO_ICMP socket kind")
Reported-by: Paul Wouters <pwouters@redhat.com>
Tested-by: Paul Wouters <pwouters@redhat.com>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ping.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 535427292194..df6fbefe44d4 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -786,6 +786,9 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 			   inet_sk_flowi_flags(sk), faddr, saddr, 0, 0,
 			   sk->sk_uid);
 
+	fl4.fl4_icmp_type = user_icmph.type;
+	fl4.fl4_icmp_code = user_icmph.code;
+
 	security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
 	rt = ip_route_output_flow(net, &fl4, sk);
 	if (IS_ERR(rt)) {
-- 
2.26.2


From 883044e44567f38f81f4d33cee9608123adb7c1f Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@kernel.org>
Date: Mon, 6 Jul 2020 11:45:07 -0600
Subject: [PATCH 05/44] ipv6: fib6_select_path can not use out path for nexthop
 objects

[ Upstream commit 34fe5a1cf95c3f114068fc16d919c9cf4b00e428 ]

Brian reported a crash in IPv6 code when using rpfilter with a setup
running FRR and external nexthop objects. The root cause of the crash
is fib6_select_path setting fib6_nh in the result to NULL because of
an improper check for nexthop objects.

More specifically, rpfilter invokes ip6_route_lookup with flowi6_oif
set causing fib6_select_path to be called with have_oif_match set.
fib6_select_path has early check on have_oif_match and jumps to the
out label which presumes a builtin fib6_nh. This path is invalid for
nexthop objects; for external nexthops fib6_select_path needs to just
return if the fib6_nh has already been set in the result otherwise it
returns after the call to nexthop_path_fib6_result. Update the check
on have_oif_match to not bail on external nexthops.

Update selftests for this problem.

Fixes: f88d8ea67fbd ("ipv6: Plumb support for nexthop object in a fib6_info")
Reported-by: Brian Rak <brak@choopa.com>
Signed-off-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c                            |  5 ++++-
 tools/testing/selftests/net/fib_nexthops.sh | 13 +++++++++++++
 2 files changed, 17 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index ff847a324220..9c9cbba34dc3 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -431,9 +431,12 @@ void fib6_select_path(const struct net *net, struct fib6_result *res,
 	struct fib6_info *sibling, *next_sibling;
 	struct fib6_info *match = res->f6i;
 
-	if ((!match->fib6_nsiblings && !match->nh) || have_oif_match)
+	if (!match->nh && (!match->fib6_nsiblings || have_oif_match))
 		goto out;
 
+	if (match->nh && have_oif_match && res->nh)
+		return;
+
 	/* We might have already computed the hash for ICMPv6 errors. In such
 	 * case it will always be non-zero. Otherwise now is the time to do it.
 	 */
diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh
index 6560ed796ac4..09830b88ec8c 100755
--- a/tools/testing/selftests/net/fib_nexthops.sh
+++ b/tools/testing/selftests/net/fib_nexthops.sh
@@ -512,6 +512,19 @@ ipv6_fcnal_runtime()
 	run_cmd "$IP nexthop add id 86 via 2001:db8:91::2 dev veth1"
 	run_cmd "$IP ro add 2001:db8:101::1/128 nhid 81"
 
+	# rpfilter and default route
+	$IP nexthop flush >/dev/null 2>&1
+	run_cmd "ip netns exec me ip6tables -t mangle -I PREROUTING 1 -m rpfilter --invert -j DROP"
+	run_cmd "$IP nexthop add id 91 via 2001:db8:91::2 dev veth1"
+	run_cmd "$IP nexthop add id 92 via 2001:db8:92::2 dev veth3"
+	run_cmd "$IP nexthop add id 93 group 91/92"
+	run_cmd "$IP -6 ro add default nhid 91"
+	run_cmd "ip netns exec me ping -c1 -w1 2001:db8:101::1"
+	log_test $? 0 "Nexthop with default route and rpfilter"
+	run_cmd "$IP -6 ro replace default nhid 93"
+	run_cmd "ip netns exec me ping -c1 -w1 2001:db8:101::1"
+	log_test $? 0 "Nexthop with multipath default route and rpfilter"
+
 	# TO-DO:
 	# existing route with old nexthop; append route with new nexthop
 	# existing route with old nexthop; replace route with new
-- 
2.26.2


From f3039631c098b367dae51c4218cdd39beda4bc7b Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@kernel.org>
Date: Tue, 7 Jul 2020 07:39:24 -0600
Subject: [PATCH 06/44] ipv6: Fix use of anycast address with loopback

[ Upstream commit aea23c323d89836bcdcee67e49def997ffca043b ]

Thomas reported a regression with IPv6 and anycast using the following
reproducer:

    echo 1 >  /proc/sys/net/ipv6/conf/all/forwarding
    ip -6 a add fc12::1/16 dev lo
    sleep 2
    echo "pinging lo"
    ping6 -c 2 fc12::

The conversion of addrconf_f6i_alloc to use ip6_route_info_create missed
the use of fib6_is_reject which checks addresses added to the loopback
interface and sets the REJECT flag as needed. Update fib6_is_reject for
loopback checks to handle RTF_ANYCAST addresses.

Fixes: c7a1ce397ada ("ipv6: Change addrconf_f6i_alloc to use ip6_route_info_create")
Reported-by: thomas.gambier@nexedi.com
Signed-off-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 9c9cbba34dc3..e8a184acf668 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3402,7 +3402,7 @@ static bool fib6_is_reject(u32 flags, struct net_device *dev, int addr_type)
 	if ((flags & RTF_REJECT) ||
 	    (dev && (dev->flags & IFF_LOOPBACK) &&
 	     !(addr_type & IPV6_ADDR_LOOPBACK) &&
-	     !(flags & RTF_LOCAL)))
+	     !(flags & (RTF_ANYCAST | RTF_LOCAL))))
 		return true;
 
 	return false;
-- 
2.26.2


From 2e19720e13228a6cc396f4a872fdf9de95f05fde Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 7 Jul 2020 02:02:32 +0800
Subject: [PATCH 07/44] l2tp: remove skb_dst_set() from l2tp_xmit_skb()

[ Upstream commit 27d53323664c549b5bb2dfaaf6f7ad6e0376a64e ]

In the tx path of l2tp, l2tp_xmit_skb() calls skb_dst_set() to set
skb's dst. However, it will eventually call inet6_csk_xmit() or
ip_queue_xmit() where skb's dst will be overwritten by:

   skb_dst_set_noref(skb, dst);

without releasing the old dst in skb. Then it causes dst/dev refcnt leak:

  unregister_netdevice: waiting for eth0 to become free. Usage count = 1

This can be reproduced by simply running:

  # modprobe l2tp_eth && modprobe l2tp_ip
  # sh ./tools/testing/selftests/net/l2tp.sh

So before going to inet6_csk_xmit() or ip_queue_xmit(), skb's dst
should be dropped. This patch is to fix it by removing skb_dst_set()
from l2tp_xmit_skb() and moving skb_dst_drop() into l2tp_xmit_core().

Fixes: 3557baabf280 ("[L2TP]: PPP over L2TP driver core")
Reported-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: James Chapman <jchapman@katalix.com>
Tested-by: James Chapman <jchapman@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 6d7ef78c88af..6434d17e6e8e 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1028,6 +1028,7 @@ static void l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb,
 
 	/* Queue the packet to IP for output */
 	skb->ignore_df = 1;
+	skb_dst_drop(skb);
 #if IS_ENABLED(CONFIG_IPV6)
 	if (l2tp_sk_is_v6(tunnel->sock))
 		error = inet6_csk_xmit(tunnel->sock, skb, NULL);
@@ -1099,10 +1100,6 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len
 		goto out_unlock;
 	}
 
-	/* Get routing info from the tunnel socket */
-	skb_dst_drop(skb);
-	skb_dst_set(skb, sk_dst_check(sk, 0));
-
 	inet = inet_sk(sk);
 	fl = &inet->cork.fl;
 	switch (tunnel->encap) {
-- 
2.26.2


From 71b852bd61c7b896786e9fa9b7c0a603feb3b878 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 27 Jun 2020 13:31:50 -0700
Subject: [PATCH 08/44] llc: make sure applications use ARPHRD_ETHER

[ Upstream commit a9b1110162357689a34992d5c925852948e5b9fd ]

syzbot was to trigger a bug by tricking AF_LLC with
non sensible addr->sllc_arphrd

It seems clear LLC requires an Ethernet device.

Back in commit abf9d537fea2 ("llc: add support for SO_BINDTODEVICE")
Octavian Purdila added possibility for application to use a zero
value for sllc_arphrd, convert it to ARPHRD_ETHER to not cause
regressions on existing applications.

BUG: KASAN: use-after-free in __read_once_size include/linux/compiler.h:199 [inline]
BUG: KASAN: use-after-free in list_empty include/linux/list.h:268 [inline]
BUG: KASAN: use-after-free in waitqueue_active include/linux/wait.h:126 [inline]
BUG: KASAN: use-after-free in wq_has_sleeper include/linux/wait.h:160 [inline]
BUG: KASAN: use-after-free in skwq_has_sleeper include/net/sock.h:2092 [inline]
BUG: KASAN: use-after-free in sock_def_write_space+0x642/0x670 net/core/sock.c:2813
Read of size 8 at addr ffff88801e0b4078 by task ksoftirqd/3/27

CPU: 3 PID: 27 Comm: ksoftirqd/3 Not tainted 5.5.0-rc1-syzkaller #0
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x197/0x210 lib/dump_stack.c:118
 print_address_description.constprop.0.cold+0xd4/0x30b mm/kasan/report.c:374
 __kasan_report.cold+0x1b/0x41 mm/kasan/report.c:506
 kasan_report+0x12/0x20 mm/kasan/common.c:639
 __asan_report_load8_noabort+0x14/0x20 mm/kasan/generic_report.c:135
 __read_once_size include/linux/compiler.h:199 [inline]
 list_empty include/linux/list.h:268 [inline]
 waitqueue_active include/linux/wait.h:126 [inline]
 wq_has_sleeper include/linux/wait.h:160 [inline]
 skwq_has_sleeper include/net/sock.h:2092 [inline]
 sock_def_write_space+0x642/0x670 net/core/sock.c:2813
 sock_wfree+0x1e1/0x260 net/core/sock.c:1958
 skb_release_head_state+0xeb/0x260 net/core/skbuff.c:652
 skb_release_all+0x16/0x60 net/core/skbuff.c:663
 __kfree_skb net/core/skbuff.c:679 [inline]
 consume_skb net/core/skbuff.c:838 [inline]
 consume_skb+0xfb/0x410 net/core/skbuff.c:832
 __dev_kfree_skb_any+0xa4/0xd0 net/core/dev.c:2967
 dev_kfree_skb_any include/linux/netdevice.h:3650 [inline]
 e1000_unmap_and_free_tx_resource.isra.0+0x21b/0x3a0 drivers/net/ethernet/intel/e1000/e1000_main.c:1963
 e1000_clean_tx_irq drivers/net/ethernet/intel/e1000/e1000_main.c:3854 [inline]
 e1000_clean+0x4cc/0x1d10 drivers/net/ethernet/intel/e1000/e1000_main.c:3796
 napi_poll net/core/dev.c:6532 [inline]
 net_rx_action+0x508/0x1120 net/core/dev.c:6600
 __do_softirq+0x262/0x98c kernel/softirq.c:292
 run_ksoftirqd kernel/softirq.c:603 [inline]
 run_ksoftirqd+0x8e/0x110 kernel/softirq.c:595
 smpboot_thread_fn+0x6a3/0xa40 kernel/smpboot.c:165
 kthread+0x361/0x430 kernel/kthread.c:255
 ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:352

Allocated by task 8247:
 save_stack+0x23/0x90 mm/kasan/common.c:72
 set_track mm/kasan/common.c:80 [inline]
 __kasan_kmalloc mm/kasan/common.c:513 [inline]
 __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:486
 kasan_slab_alloc+0xf/0x20 mm/kasan/common.c:521
 slab_post_alloc_hook mm/slab.h:584 [inline]
 slab_alloc mm/slab.c:3320 [inline]
 kmem_cache_alloc+0x121/0x710 mm/slab.c:3484
 sock_alloc_inode+0x1c/0x1d0 net/socket.c:240
 alloc_inode+0x68/0x1e0 fs/inode.c:230
 new_inode_pseudo+0x19/0xf0 fs/inode.c:919
 sock_alloc+0x41/0x270 net/socket.c:560
 __sock_create+0xc2/0x730 net/socket.c:1384
 sock_create net/socket.c:1471 [inline]
 __sys_socket+0x103/0x220 net/socket.c:1513
 __do_sys_socket net/socket.c:1522 [inline]
 __se_sys_socket net/socket.c:1520 [inline]
 __ia32_sys_socket+0x73/0xb0 net/socket.c:1520
 do_syscall_32_irqs_on arch/x86/entry/common.c:337 [inline]
 do_fast_syscall_32+0x27b/0xe16 arch/x86/entry/common.c:408
 entry_SYSENTER_compat+0x70/0x7f arch/x86/entry/entry_64_compat.S:139

Freed by task 17:
 save_stack+0x23/0x90 mm/kasan/common.c:72
 set_track mm/kasan/common.c:80 [inline]
 kasan_set_free_info mm/kasan/common.c:335 [inline]
 __kasan_slab_free+0x102/0x150 mm/kasan/common.c:474
 kasan_slab_free+0xe/0x10 mm/kasan/common.c:483
 __cache_free mm/slab.c:3426 [inline]
 kmem_cache_free+0x86/0x320 mm/slab.c:3694
 sock_free_inode+0x20/0x30 net/socket.c:261
 i_callback+0x44/0x80 fs/inode.c:219
 __rcu_reclaim kernel/rcu/rcu.h:222 [inline]
 rcu_do_batch kernel/rcu/tree.c:2183 [inline]
 rcu_core+0x570/0x1540 kernel/rcu/tree.c:2408
 rcu_core_si+0x9/0x10 kernel/rcu/tree.c:2417
 __do_softirq+0x262/0x98c kernel/softirq.c:292

The buggy address belongs to the object at ffff88801e0b4000
 which belongs to the cache sock_inode_cache of size 1152
The buggy address is located 120 bytes inside of
 1152-byte region [ffff88801e0b4000, ffff88801e0b4480)
The buggy address belongs to the page:
page:ffffea0000782d00 refcount:1 mapcount:0 mapping:ffff88807aa59c40 index:0xffff88801e0b4ffd
raw: 00fffe0000000200 ffffea00008e6c88 ffffea0000782d48 ffff88807aa59c40
raw: ffff88801e0b4ffd ffff88801e0b4000 0000000100000003 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff88801e0b3f00: fb fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc
 ffff88801e0b3f80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
>ffff88801e0b4000: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                                                                ^
 ffff88801e0b4080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff88801e0b4100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb

Fixes: abf9d537fea2 ("llc: add support for SO_BINDTODEVICE")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/llc/af_llc.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 54fb8d452a7b..6e53e43c1907 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -273,6 +273,10 @@ static int llc_ui_autobind(struct socket *sock, struct sockaddr_llc *addr)
 
 	if (!sock_flag(sk, SOCK_ZAPPED))
 		goto out;
+	if (!addr->sllc_arphrd)
+		addr->sllc_arphrd = ARPHRD_ETHER;
+	if (addr->sllc_arphrd != ARPHRD_ETHER)
+		goto out;
 	rc = -ENODEV;
 	if (sk->sk_bound_dev_if) {
 		llc->dev = dev_get_by_index(&init_net, sk->sk_bound_dev_if);
@@ -328,7 +332,9 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen)
 	if (unlikely(!sock_flag(sk, SOCK_ZAPPED) || addrlen != sizeof(*addr)))
 		goto out;
 	rc = -EAFNOSUPPORT;
-	if (unlikely(addr->sllc_family != AF_LLC))
+	if (!addr->sllc_arphrd)
+		addr->sllc_arphrd = ARPHRD_ETHER;
+	if (unlikely(addr->sllc_family != AF_LLC || addr->sllc_arphrd != ARPHRD_ETHER))
 		goto out;
 	dprintk("%s: binding %02X\n", __func__, addr->sllc_sap);
 	rc = -ENODEV;
@@ -336,8 +342,6 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen)
 	if (sk->sk_bound_dev_if) {
 		llc->dev = dev_get_by_index_rcu(&init_net, sk->sk_bound_dev_if);
 		if (llc->dev) {
-			if (!addr->sllc_arphrd)
-				addr->sllc_arphrd = llc->dev->type;
 			if (is_zero_ether_addr(addr->sllc_mac))
 				memcpy(addr->sllc_mac, llc->dev->dev_addr,
 				       IFHWADDRLEN);
-- 
2.26.2


From 9c9c1de4eb3d69de977c874e9c88a2d73ead2fce Mon Sep 17 00:00:00 2001
From: Martin Varghese <martin.varghese@nokia.com>
Date: Sun, 5 Jul 2020 14:23:49 +0530
Subject: [PATCH 09/44] net: Added pointer check for dst->ops->neigh_lookup in
 dst_neigh_lookup_skb

[ Upstream commit 394de110a73395de2ca4516b0de435e91b11b604 ]

The packets from tunnel devices (eg bareudp) may have only
metadata in the dst pointer of skb. Hence a pointer check of
neigh_lookup is needed in dst_neigh_lookup_skb

Kernel crashes when packets from bareudp device is processed in
the kernel neighbour subsytem.

[  133.384484] BUG: kernel NULL pointer dereference, address: 0000000000000000
[  133.385240] #PF: supervisor instruction fetch in kernel mode
[  133.385828] #PF: error_code(0x0010) - not-present page
[  133.386603] PGD 0 P4D 0
[  133.386875] Oops: 0010 [#1] SMP PTI
[  133.387275] CPU: 0 PID: 5045 Comm: ping Tainted: G        W         5.8.0-rc2+ #15
[  133.388052] Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
[  133.391076] RIP: 0010:0x0
[  133.392401] Code: Bad RIP value.
[  133.394029] RSP: 0018:ffffb79980003d50 EFLAGS: 00010246
[  133.396656] RAX: 0000000080000102 RBX: ffff9de2fe0d6600 RCX: ffff9de2fe5e9d00
[  133.399018] RDX: 0000000000000000 RSI: ffff9de2fe5e9d00 RDI: ffff9de2fc21b400
[  133.399685] RBP: ffff9de2fe5e9d00 R08: 0000000000000000 R09: 0000000000000000
[  133.400350] R10: ffff9de2fbc6be22 R11: ffff9de2fe0d6600 R12: ffff9de2fc21b400
[  133.401010] R13: ffff9de2fe0d6628 R14: 0000000000000001 R15: 0000000000000003
[  133.401667] FS:  00007fe014918740(0000) GS:ffff9de2fec00000(0000) knlGS:0000000000000000
[  133.402412] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  133.402948] CR2: ffffffffffffffd6 CR3: 000000003bb72000 CR4: 00000000000006f0
[  133.403611] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  133.404270] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[  133.404933] Call Trace:
[  133.405169]  <IRQ>
[  133.405367]  __neigh_update+0x5a4/0x8f0
[  133.405734]  arp_process+0x294/0x820
[  133.406076]  ? __netif_receive_skb_core+0x866/0xe70
[  133.406557]  arp_rcv+0x129/0x1c0
[  133.406882]  __netif_receive_skb_one_core+0x95/0xb0
[  133.407340]  process_backlog+0xa7/0x150
[  133.407705]  net_rx_action+0x2af/0x420
[  133.408457]  __do_softirq+0xda/0x2a8
[  133.408813]  asm_call_on_stack+0x12/0x20
[  133.409290]  </IRQ>
[  133.409519]  do_softirq_own_stack+0x39/0x50
[  133.410036]  do_softirq+0x50/0x60
[  133.410401]  __local_bh_enable_ip+0x50/0x60
[  133.410871]  ip_finish_output2+0x195/0x530
[  133.411288]  ip_output+0x72/0xf0
[  133.411673]  ? __ip_finish_output+0x1f0/0x1f0
[  133.412122]  ip_send_skb+0x15/0x40
[  133.412471]  raw_sendmsg+0x853/0xab0
[  133.412855]  ? insert_pfn+0xfe/0x270
[  133.413827]  ? vvar_fault+0xec/0x190
[  133.414772]  sock_sendmsg+0x57/0x80
[  133.415685]  __sys_sendto+0xdc/0x160
[  133.416605]  ? syscall_trace_enter+0x1d4/0x2b0
[  133.417679]  ? __audit_syscall_exit+0x1d9/0x280
[  133.418753]  ? __prepare_exit_to_usermode+0x5d/0x1a0
[  133.419819]  __x64_sys_sendto+0x24/0x30
[  133.420848]  do_syscall_64+0x4d/0x90
[  133.421768]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[  133.422833] RIP: 0033:0x7fe013689c03
[  133.423749] Code: Bad RIP value.
[  133.424624] RSP: 002b:00007ffc7288f418 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
[  133.425940] RAX: ffffffffffffffda RBX: 000056151fc63720 RCX: 00007fe013689c03
[  133.427225] RDX: 0000000000000040 RSI: 000056151fc63720 RDI: 0000000000000003
[  133.428481] RBP: 00007ffc72890b30 R08: 000056151fc60500 R09: 0000000000000010
[  133.429757] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000040
[  133.431041] R13: 000056151fc636e0 R14: 000056151fc616bc R15: 0000000000000080
[  133.432481] Modules linked in: mpls_iptunnel act_mirred act_tunnel_key cls_flower sch_ingress veth mpls_router ip_tunnel bareudp ip6_udp_tunnel udp_tunnel macsec udp_diag inet_diag unix_diag af_packet_diag netlink_diag binfmt_misc xt_MASQUERADE iptable_nat xt_addrtype xt_conntrack nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 br_netfilter bridge stp llc ebtable_filter ebtables overlay ip6table_filter ip6_tables iptable_filter sunrpc ext4 mbcache jbd2 pcspkr i2c_piix4 virtio_balloon joydev ip_tables xfs libcrc32c ata_generic qxl pata_acpi drm_ttm_helper ttm drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops drm ata_piix libata virtio_net net_failover virtio_console failover virtio_blk i2c_core virtio_pci virtio_ring serio_raw floppy virtio dm_mirror dm_region_hash dm_log dm_mod
[  133.444045] CR2: 0000000000000000
[  133.445082] ---[ end trace f4aeee1958fd1638 ]---
[  133.446236] RIP: 0010:0x0
[  133.447180] Code: Bad RIP value.
[  133.448152] RSP: 0018:ffffb79980003d50 EFLAGS: 00010246
[  133.449363] RAX: 0000000080000102 RBX: ffff9de2fe0d6600 RCX: ffff9de2fe5e9d00
[  133.450835] RDX: 0000000000000000 RSI: ffff9de2fe5e9d00 RDI: ffff9de2fc21b400
[  133.452237] RBP: ffff9de2fe5e9d00 R08: 0000000000000000 R09: 0000000000000000
[  133.453722] R10: ffff9de2fbc6be22 R11: ffff9de2fe0d6600 R12: ffff9de2fc21b400
[  133.455149] R13: ffff9de2fe0d6628 R14: 0000000000000001 R15: 0000000000000003
[  133.456520] FS:  00007fe014918740(0000) GS:ffff9de2fec00000(0000) knlGS:0000000000000000
[  133.458046] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  133.459342] CR2: ffffffffffffffd6 CR3: 000000003bb72000 CR4: 00000000000006f0
[  133.460782] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  133.462240] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[  133.463697] Kernel panic - not syncing: Fatal exception in interrupt
[  133.465226] Kernel Offset: 0xfa00000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff)
[  133.467025] ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]---

Fixes: aaa0c23cb901 ("Fix dst_neigh_lookup/dst_neigh_lookup_skb return value handling bug")
Signed-off-by: Martin Varghese <martin.varghese@nokia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst.h | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/include/net/dst.h b/include/net/dst.h
index 07adfacd8088..852d8fb36ab7 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -400,7 +400,15 @@ static inline struct neighbour *dst_neigh_lookup(const struct dst_entry *dst, co
 static inline struct neighbour *dst_neigh_lookup_skb(const struct dst_entry *dst,
 						     struct sk_buff *skb)
 {
-	struct neighbour *n =  dst->ops->neigh_lookup(dst, skb, NULL);
+	struct neighbour *n = NULL;
+
+	/* The packets from tunnel devices (eg bareudp) may have only
+	 * metadata in the dst pointer of skb. Hence a pointer check of
+	 * neigh_lookup is needed.
+	 */
+	if (dst->ops->neigh_lookup)
+		n = dst->ops->neigh_lookup(dst, skb, NULL);
+
 	return IS_ERR(n) ? NULL : n;
 }
 
-- 
2.26.2


From 3aa6d1de248436128f115334e1ac286affd0e8cf Mon Sep 17 00:00:00 2001
From: Dmitry Bogdanov <dbogdanov@marvell.com>
Date: Wed, 8 Jul 2020 17:17:10 +0300
Subject: [PATCH 10/44] net: atlantic: fix ip dst and ipv6 address filters

[ Upstream commit a42e6aee7f47a8a68d09923c720fc8f605a04207 ]

This patch fixes ip dst and ipv6 address filters.
There were 2 mistakes in the code, which led to the issue:
* invalid register was used for ipv4 dst address;
* incorrect write order of dwords for ipv6 addresses.

Fixes: 23e7a718a49b ("net: aquantia: add rx-flow filter definitions")
Signed-off-by: Dmitry Bogdanov <dbogdanov@marvell.com>
Signed-off-by: Mark Starovoytov <mstarovoitov@marvell.com>
Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c    | 4 ++--
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h   | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
index d1f68fc16291..e6b1fb10ad91 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
@@ -1651,7 +1651,7 @@ void hw_atl_rpfl3l4_ipv6_src_addr_set(struct aq_hw_s *aq_hw, u8 location,
 	for (i = 0; i < 4; ++i)
 		aq_hw_write_reg(aq_hw,
 				HW_ATL_RPF_L3_SRCA_ADR(location + i),
-				ipv6_src[i]);
+				ipv6_src[3 - i]);
 }
 
 void hw_atl_rpfl3l4_ipv6_dest_addr_set(struct aq_hw_s *aq_hw, u8 location,
@@ -1662,7 +1662,7 @@ void hw_atl_rpfl3l4_ipv6_dest_addr_set(struct aq_hw_s *aq_hw, u8 location,
 	for (i = 0; i < 4; ++i)
 		aq_hw_write_reg(aq_hw,
 				HW_ATL_RPF_L3_DSTA_ADR(location + i),
-				ipv6_dest[i]);
+				ipv6_dest[3 - i]);
 }
 
 u32 hw_atl_sem_ram_get(struct aq_hw_s *self)
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h
index 18de2f7b8959..a7590b9ea2df 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h
@@ -1360,7 +1360,7 @@
  */
 
  /* Register address for bitfield pif_rpf_l3_da0_i[31:0] */
-#define HW_ATL_RPF_L3_DSTA_ADR(filter) (0x000053B0 + (filter) * 0x4)
+#define HW_ATL_RPF_L3_DSTA_ADR(filter) (0x000053D0 + (filter) * 0x4)
 /* Bitmask for bitfield l3_da0[1F:0] */
 #define HW_ATL_RPF_L3_DSTA_MSK 0xFFFFFFFFu
 /* Inverted bitmask for bitfield l3_da0[1F:0] */
-- 
2.26.2


From 1307668652b06f995cd0fffb190cfa600c761291 Mon Sep 17 00:00:00 2001
From: Codrin Ciubotariu <codrin.ciubotariu@microchip.com>
Date: Thu, 2 Jul 2020 12:44:50 +0300
Subject: [PATCH 11/44] net: dsa: microchip: set the correct number of ports

[ Upstream commit af199a1a9cb02ec0194804bd46c174b6db262075 ]

The number of ports is incorrectly set to the maximum available for a DSA
switch. Even if the extra ports are not used, this causes some functions
to be called later, like port_disable() and port_stp_state_set(). If the
driver doesn't check the port index, it will end up modifying unknown
registers.

Fixes: b987e98e50ab ("dsa: add DSA switch driver for Microchip KSZ9477")
Signed-off-by: Codrin Ciubotariu <codrin.ciubotariu@microchip.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/microchip/ksz8795.c | 3 +++
 drivers/net/dsa/microchip/ksz9477.c | 3 +++
 2 files changed, 6 insertions(+)

diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c
index 47d65b77caf7..7c17b0f705ec 100644
--- a/drivers/net/dsa/microchip/ksz8795.c
+++ b/drivers/net/dsa/microchip/ksz8795.c
@@ -1268,6 +1268,9 @@ static int ksz8795_switch_init(struct ksz_device *dev)
 			return -ENOMEM;
 	}
 
+	/* set the real number of ports */
+	dev->ds->num_ports = dev->port_cnt;
+
 	return 0;
 }
 
diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c
index 9a51b8a4de5d..8d15c3016024 100644
--- a/drivers/net/dsa/microchip/ksz9477.c
+++ b/drivers/net/dsa/microchip/ksz9477.c
@@ -1588,6 +1588,9 @@ static int ksz9477_switch_init(struct ksz_device *dev)
 			return -ENOMEM;
 	}
 
+	/* set the real number of ports */
+	dev->ds->num_ports = dev->port_cnt;
+
 	return 0;
 }
 
-- 
2.26.2


From 7afcd9ddef96cac91c7641795731798eaaba6e67 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Tue, 30 Jun 2020 11:04:40 +0100
Subject: [PATCH 12/44] net: mvneta: fix use of state->speed

[ Upstream commit f2ca673d2cd5df9a76247b670e9ffd4d63682b3f ]

When support for short preambles was added, it incorrectly keyed its
decision off state->speed instead of state->interface.  state->speed
is not guaranteed to be correct for in-band modes, which can lead to
short preambles being unexpectedly disabled.

Fix this by keying off the interface mode, which is the only way that
mvneta can operate at 2.5Gbps.

Fixes: da58a931f248 ("net: mvneta: Add support for 2500Mbps SGMII")
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 43b44a1e8f69..a1b6b48ba849 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -3917,7 +3917,7 @@ static void mvneta_mac_config(struct phylink_config *config, unsigned int mode,
 	/* When at 2.5G, the link partner can send frames with shortened
 	 * preambles.
 	 */
-	if (state->speed == SPEED_2500)
+	if (state->interface == PHY_INTERFACE_MODE_2500BASEX)
 		new_ctrl4 |= MVNETA_GMAC4_SHORT_PREAMBLE_ENABLE;
 
 	if (pp->comphy && pp->phy_interface != state->interface &&
-- 
2.26.2


From d92a26e0c38e85df8c6d6db4d04aa2e663b8aff4 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Tue, 30 Jun 2020 14:46:15 +0300
Subject: [PATCH 13/44] net: qrtr: Fix an out of bounds read
 qrtr_endpoint_post()

[ Upstream commit 8ff41cc21714704ef0158a546c3c4d07fae2c952 ]

This code assumes that the user passed in enough data for a
qrtr_hdr_v1 or qrtr_hdr_v2 struct, but it's not necessarily true.  If
the buffer is too small then it will read beyond the end.

Reported-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Reported-by: syzbot+b8fe393f999a291a9ea6@syzkaller.appspotmail.com
Fixes: 194ccc88297a ("net: qrtr: Support decoding incoming v2 packets")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/qrtr/qrtr.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index 2d8d6131bc5f..7eccbbf6f8ad 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -427,7 +427,7 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len)
 	unsigned int ver;
 	size_t hdrlen;
 
-	if (len & 3)
+	if (len == 0 || len & 3)
 		return -EINVAL;
 
 	skb = netdev_alloc_skb(NULL, len);
@@ -441,6 +441,8 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len)
 
 	switch (ver) {
 	case QRTR_PROTO_VER_1:
+		if (len < sizeof(*v1))
+			goto err;
 		v1 = data;
 		hdrlen = sizeof(*v1);
 
@@ -454,6 +456,8 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len)
 		size = le32_to_cpu(v1->size);
 		break;
 	case QRTR_PROTO_VER_2:
+		if (len < sizeof(*v2))
+			goto err;
 		v2 = data;
 		hdrlen = sizeof(*v2) + v2->optlen;
 
-- 
2.26.2


From 2dc14b45e8157f3bc5382438da82aa3bed3fd796 Mon Sep 17 00:00:00 2001
From: Carl Huang <cjhuang@codeaurora.org>
Date: Tue, 30 Jun 2020 14:52:51 +0800
Subject: [PATCH 14/44] net: qrtr: free flow in __qrtr_node_release

[ Upstream commit 28541f3d324f6de1e545e2875283b6cef95c5d36 ]

The flow is allocated in qrtr_tx_wait, but not freed when qrtr node
is released. (*slot) becomes NULL after radix_tree_iter_delete is
called in __qrtr_node_release. The fix is to save (*slot) to a
vairable and then free it.

This memory leak is catched when kmemleak is enabled in kernel,
the report looks like below:

unreferenced object 0xffffa0de69e08420 (size 32):
  comm "kworker/u16:3", pid 176, jiffies 4294918275 (age 82858.876s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 28 84 e0 69 de a0 ff ff  ........(..i....
    28 84 e0 69 de a0 ff ff 03 00 00 00 00 00 00 00  (..i............
  backtrace:
    [<00000000e252af0a>] qrtr_node_enqueue+0x38e/0x400 [qrtr]
    [<000000009cea437f>] qrtr_sendmsg+0x1e0/0x2a0 [qrtr]
    [<000000008bddbba4>] sock_sendmsg+0x5b/0x60
    [<0000000003beb43a>] qmi_send_message.isra.3+0xbe/0x110 [qmi_helpers]
    [<000000009c9ae7de>] qmi_send_request+0x1c/0x20 [qmi_helpers]

Signed-off-by: Carl Huang <cjhuang@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/qrtr/qrtr.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index 7eccbbf6f8ad..24a8c3c6da0d 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -166,6 +166,7 @@ static void __qrtr_node_release(struct kref *kref)
 {
 	struct qrtr_node *node = container_of(kref, struct qrtr_node, ref);
 	struct radix_tree_iter iter;
+	struct qrtr_tx_flow *flow;
 	unsigned long flags;
 	void __rcu **slot;
 
@@ -181,8 +182,9 @@ static void __qrtr_node_release(struct kref *kref)
 
 	/* Free tx flow counters */
 	radix_tree_for_each_slot(slot, &node->qrtr_tx_flow, &iter, 0) {
+		flow = *slot;
 		radix_tree_iter_delete(&node->qrtr_tx_flow, &iter, slot);
-		kfree(*slot);
+		kfree(flow);
 	}
 	kfree(node);
 }
-- 
2.26.2


From 6f2f0e8aaba601ff75cba5d36dbd8836d861785c Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Wed, 8 Jul 2020 20:13:59 -0700
Subject: [PATCH 15/44] net_sched: fix a memory leak in atm_tc_init()

[ Upstream commit 306381aec7c2b5a658eebca008c8a1b666536cba ]

When tcf_block_get() fails inside atm_tc_init(),
atm_tc_put() is called to release the qdisc p->link.q.
But the flow->ref prevents it to do so, as the flow->ref
is still zero.

Fix this by moving the p->link.ref initialization before
tcf_block_get().

Fixes: 6529eaba33f0 ("net: sched: introduce tcf block infractructure")
Reported-and-tested-by: syzbot+d411cff6ab29cc2c311b@syzkaller.appspotmail.com
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_atm.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index ee12ca9f55b4..1c281cc81f57 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -553,16 +553,16 @@ static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt,
 	if (!p->link.q)
 		p->link.q = &noop_qdisc;
 	pr_debug("atm_tc_init: link (%p) qdisc %p\n", &p->link, p->link.q);
+	p->link.vcc = NULL;
+	p->link.sock = NULL;
+	p->link.common.classid = sch->handle;
+	p->link.ref = 1;
 
 	err = tcf_block_get(&p->link.block, &p->link.filter_list, sch,
 			    extack);
 	if (err)
 		return err;
 
-	p->link.vcc = NULL;
-	p->link.sock = NULL;
-	p->link.common.classid = sch->handle;
-	p->link.ref = 1;
 	tasklet_init(&p->task, sch_atm_dequeue, (unsigned long)sch);
 	return 0;
 }
-- 
2.26.2


From 3e7776cd236c917555c9ded8bf03b0a0fca1b5c5 Mon Sep 17 00:00:00 2001
From: AceLan Kao <acelan.kao@canonical.com>
Date: Tue, 7 Jul 2020 16:14:45 +0800
Subject: [PATCH 16/44] net: usb: qmi_wwan: add support for Quectel EG95 LTE
 modem
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit f815dd5cf48b905eeecf0a2b990e9b7ab048b4f1 ]

Add support for Quectel Wireless Solutions Co., Ltd. EG95 LTE modem

T:  Bus=01 Lev=01 Prnt=01 Port=02 Cnt=02 Dev#=  5 Spd=480 MxCh= 0
D:  Ver= 2.00 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs=  1
P:  Vendor=2c7c ProdID=0195 Rev=03.18
S:  Manufacturer=Android
S:  Product=Android
C:  #Ifs= 5 Cfg#= 1 Atr=a0 MxPwr=500mA
I:  If#=0x0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none)
I:  If#=0x1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=(none)
I:  If#=0x2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=(none)
I:  If#=0x3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=(none)
I:  If#=0x4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none)

Signed-off-by: AceLan Kao <acelan.kao@canonical.com>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 4a2c7355be63..e57d59b0a7ae 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1370,6 +1370,7 @@ static const struct usb_device_id products[] = {
 	{QMI_QUIRK_SET_DTR(0x1e0e, 0x9001, 5)},	/* SIMCom 7100E, 7230E, 7600E ++ */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0121, 4)},	/* Quectel EC21 Mini PCIe */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0191, 4)},	/* Quectel EG91 */
+	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0195, 4)},	/* Quectel EG95 */
 	{QMI_FIXED_INTF(0x2c7c, 0x0296, 4)},	/* Quectel BG96 */
 	{QMI_QUIRK_SET_DTR(0x2cb7, 0x0104, 4)},	/* Fibocom NL678 series */
 	{QMI_FIXED_INTF(0x0489, 0xe0b4, 0)},	/* Foxconn T77W968 LTE */
-- 
2.26.2


From f016963e7b4d2ba027fb854a995e6ec47b26b427 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
Date: Fri, 3 Jul 2020 22:26:43 +0200
Subject: [PATCH 17/44] sched: consistently handle layer3 header accesses in
 the presence of VLANs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit d7bf2ebebc2bd61ab95e2a8e33541ef282f303d4 ]

There are a couple of places in net/sched/ that check skb->protocol and act
on the value there. However, in the presence of VLAN tags, the value stored
in skb->protocol can be inconsistent based on whether VLAN acceleration is
enabled. The commit quoted in the Fixes tag below fixed the users of
skb->protocol to use a helper that will always see the VLAN ethertype.

However, most of the callers don't actually handle the VLAN ethertype, but
expect to find the IP header type in the protocol field. This means that
things like changing the ECN field, or parsing diffserv values, stops
working if there's a VLAN tag, or if there are multiple nested VLAN
tags (QinQ).

To fix this, change the helper to take an argument that indicates whether
the caller wants to skip the VLAN tags or not. When skipping VLAN tags, we
make sure to skip all of them, so behaviour is consistent even in QinQ
mode.

To make the helper usable from the ECN code, move it to if_vlan.h instead
of pkt_sched.h.

v3:
- Remove empty lines
- Move vlan variable definitions inside loop in skb_protocol()
- Also use skb_protocol() helper in IP{,6}_ECN_decapsulate() and
  bpf_skb_ecn_set_ce()

v2:
- Use eth_type_vlan() helper in skb_protocol()
- Also fix code that reads skb->protocol directly
- Change a couple of 'if/else if' statements to switch constructs to avoid
  calling the helper twice

Reported-by: Ilya Ponetayev <i.ponetaev@ndmsystems.com>
Fixes: d8b9605d2697 ("net: sched: fix skb->protocol use in case of accelerated vlan path")
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_vlan.h  | 28 ++++++++++++++++++++++++++++
 include/net/inet_ecn.h   | 25 +++++++++++++++++--------
 include/net/pkt_sched.h  | 11 -----------
 net/core/filter.c        | 10 +++++++---
 net/sched/act_connmark.c |  9 ++++++---
 net/sched/act_csum.c     |  2 +-
 net/sched/act_ct.c       |  9 ++++-----
 net/sched/act_ctinfo.c   |  9 ++++++---
 net/sched/act_mpls.c     |  2 +-
 net/sched/act_skbedit.c  |  2 +-
 net/sched/cls_api.c      |  2 +-
 net/sched/cls_flow.c     |  8 ++++----
 net/sched/cls_flower.c   |  2 +-
 net/sched/em_ipset.c     |  2 +-
 net/sched/em_ipt.c       |  2 +-
 net/sched/em_meta.c      |  2 +-
 net/sched/sch_cake.c     |  4 ++--
 net/sched/sch_dsmark.c   |  6 +++---
 net/sched/sch_teql.c     |  2 +-
 19 files changed, 86 insertions(+), 51 deletions(-)

diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index b05e855f1ddd..427a5b8597c2 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -308,6 +308,34 @@ static inline bool eth_type_vlan(__be16 ethertype)
 	}
 }
 
+/* A getter for the SKB protocol field which will handle VLAN tags consistently
+ * whether VLAN acceleration is enabled or not.
+ */
+static inline __be16 skb_protocol(const struct sk_buff *skb, bool skip_vlan)
+{
+	unsigned int offset = skb_mac_offset(skb) + sizeof(struct ethhdr);
+	__be16 proto = skb->protocol;
+
+	if (!skip_vlan)
+		/* VLAN acceleration strips the VLAN header from the skb and
+		 * moves it to skb->vlan_proto
+		 */
+		return skb_vlan_tag_present(skb) ? skb->vlan_proto : proto;
+
+	while (eth_type_vlan(proto)) {
+		struct vlan_hdr vhdr, *vh;
+
+		vh = skb_header_pointer(skb, offset, sizeof(vhdr), &vhdr);
+		if (!vh)
+			break;
+
+		proto = vh->h_vlan_encapsulated_proto;
+		offset += sizeof(vhdr);
+	}
+
+	return proto;
+}
+
 static inline bool vlan_hw_offload_capable(netdev_features_t features,
 					   __be16 proto)
 {
diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h
index 0f0d1efe06dd..e1eaf1780288 100644
--- a/include/net/inet_ecn.h
+++ b/include/net/inet_ecn.h
@@ -4,6 +4,7 @@
 
 #include <linux/ip.h>
 #include <linux/skbuff.h>
+#include <linux/if_vlan.h>
 
 #include <net/inet_sock.h>
 #include <net/dsfield.h>
@@ -172,7 +173,7 @@ static inline void ipv6_copy_dscp(unsigned int dscp, struct ipv6hdr *inner)
 
 static inline int INET_ECN_set_ce(struct sk_buff *skb)
 {
-	switch (skb->protocol) {
+	switch (skb_protocol(skb, true)) {
 	case cpu_to_be16(ETH_P_IP):
 		if (skb_network_header(skb) + sizeof(struct iphdr) <=
 		    skb_tail_pointer(skb))
@@ -191,7 +192,7 @@ static inline int INET_ECN_set_ce(struct sk_buff *skb)
 
 static inline int INET_ECN_set_ect1(struct sk_buff *skb)
 {
-	switch (skb->protocol) {
+	switch (skb_protocol(skb, true)) {
 	case cpu_to_be16(ETH_P_IP):
 		if (skb_network_header(skb) + sizeof(struct iphdr) <=
 		    skb_tail_pointer(skb))
@@ -272,12 +273,16 @@ static inline int IP_ECN_decapsulate(const struct iphdr *oiph,
 {
 	__u8 inner;
 
-	if (skb->protocol == htons(ETH_P_IP))
+	switch (skb_protocol(skb, true)) {
+	case htons(ETH_P_IP):
 		inner = ip_hdr(skb)->tos;
-	else if (skb->protocol == htons(ETH_P_IPV6))
+		break;
+	case htons(ETH_P_IPV6):
 		inner = ipv6_get_dsfield(ipv6_hdr(skb));
-	else
+		break;
+	default:
 		return 0;
+	}
 
 	return INET_ECN_decapsulate(skb, oiph->tos, inner);
 }
@@ -287,12 +292,16 @@ static inline int IP6_ECN_decapsulate(const struct ipv6hdr *oipv6h,
 {
 	__u8 inner;
 
-	if (skb->protocol == htons(ETH_P_IP))
+	switch (skb_protocol(skb, true)) {
+	case htons(ETH_P_IP):
 		inner = ip_hdr(skb)->tos;
-	else if (skb->protocol == htons(ETH_P_IPV6))
+		break;
+	case htons(ETH_P_IPV6):
 		inner = ipv6_get_dsfield(ipv6_hdr(skb));
-	else
+		break;
+	default:
 		return 0;
+	}
 
 	return INET_ECN_decapsulate(skb, ipv6_get_dsfield(oipv6h), inner);
 }
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index 9092e697059e..ac8c890a2657 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -136,17 +136,6 @@ static inline void qdisc_run(struct Qdisc *q)
 	}
 }
 
-static inline __be16 tc_skb_protocol(const struct sk_buff *skb)
-{
-	/* We need to take extra care in case the skb came via
-	 * vlan accelerated path. In that case, use skb->vlan_proto
-	 * as the original vlan header was already stripped.
-	 */
-	if (skb_vlan_tag_present(skb))
-		return skb->vlan_proto;
-	return skb->protocol;
-}
-
 /* Calculate maximal size of packet seen by hard_start_xmit
    routine of this device.
  */
diff --git a/net/core/filter.c b/net/core/filter.c
index 45fa65a28983..cebbb6ba9ed9 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5724,12 +5724,16 @@ BPF_CALL_1(bpf_skb_ecn_set_ce, struct sk_buff *, skb)
 {
 	unsigned int iphdr_len;
 
-	if (skb->protocol == cpu_to_be16(ETH_P_IP))
+	switch (skb_protocol(skb, true)) {
+	case cpu_to_be16(ETH_P_IP):
 		iphdr_len = sizeof(struct iphdr);
-	else if (skb->protocol == cpu_to_be16(ETH_P_IPV6))
+		break;
+	case cpu_to_be16(ETH_P_IPV6):
 		iphdr_len = sizeof(struct ipv6hdr);
-	else
+		break;
+	default:
 		return 0;
+	}
 
 	if (skb_headlen(skb) < iphdr_len)
 		return 0;
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index 43a243081e7d..f901421b0634 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -43,17 +43,20 @@ static int tcf_connmark_act(struct sk_buff *skb, const struct tc_action *a,
 	tcf_lastuse_update(&ca->tcf_tm);
 	bstats_update(&ca->tcf_bstats, skb);
 
-	if (skb->protocol == htons(ETH_P_IP)) {
+	switch (skb_protocol(skb, true)) {
+	case htons(ETH_P_IP):
 		if (skb->len < sizeof(struct iphdr))
 			goto out;
 
 		proto = NFPROTO_IPV4;
-	} else if (skb->protocol == htons(ETH_P_IPV6)) {
+		break;
+	case htons(ETH_P_IPV6):
 		if (skb->len < sizeof(struct ipv6hdr))
 			goto out;
 
 		proto = NFPROTO_IPV6;
-	} else {
+		break;
+	default:
 		goto out;
 	}
 
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index cb8608f0a77a..c60674cf25c4 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -587,7 +587,7 @@ static int tcf_csum_act(struct sk_buff *skb, const struct tc_action *a,
 		goto drop;
 
 	update_flags = params->update_flags;
-	protocol = tc_skb_protocol(skb);
+	protocol = skb_protocol(skb, false);
 again:
 	switch (protocol) {
 	case cpu_to_be16(ETH_P_IP):
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index 20577355235a..6a114f80e54b 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -622,7 +622,7 @@ static u8 tcf_ct_skb_nf_family(struct sk_buff *skb)
 {
 	u8 family = NFPROTO_UNSPEC;
 
-	switch (skb->protocol) {
+	switch (skb_protocol(skb, true)) {
 	case htons(ETH_P_IP):
 		family = NFPROTO_IPV4;
 		break;
@@ -746,6 +746,7 @@ static int ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
 			  const struct nf_nat_range2 *range,
 			  enum nf_nat_manip_type maniptype)
 {
+	__be16 proto = skb_protocol(skb, true);
 	int hooknum, err = NF_ACCEPT;
 
 	/* See HOOK2MANIP(). */
@@ -757,14 +758,13 @@ static int ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
 	switch (ctinfo) {
 	case IP_CT_RELATED:
 	case IP_CT_RELATED_REPLY:
-		if (skb->protocol == htons(ETH_P_IP) &&
+		if (proto == htons(ETH_P_IP) &&
 		    ip_hdr(skb)->protocol == IPPROTO_ICMP) {
 			if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
 							   hooknum))
 				err = NF_DROP;
 			goto out;
-		} else if (IS_ENABLED(CONFIG_IPV6) &&
-			   skb->protocol == htons(ETH_P_IPV6)) {
+		} else if (IS_ENABLED(CONFIG_IPV6) && proto == htons(ETH_P_IPV6)) {
 			__be16 frag_off;
 			u8 nexthdr = ipv6_hdr(skb)->nexthdr;
 			int hdrlen = ipv6_skip_exthdr(skb,
@@ -1559,4 +1559,3 @@ MODULE_AUTHOR("Yossi Kuperman <yossiku@mellanox.com>");
 MODULE_AUTHOR("Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>");
 MODULE_DESCRIPTION("Connection tracking action");
 MODULE_LICENSE("GPL v2");
-
diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c
index 19649623493b..b5042f3ea079 100644
--- a/net/sched/act_ctinfo.c
+++ b/net/sched/act_ctinfo.c
@@ -96,19 +96,22 @@ static int tcf_ctinfo_act(struct sk_buff *skb, const struct tc_action *a,
 	action = READ_ONCE(ca->tcf_action);
 
 	wlen = skb_network_offset(skb);
-	if (tc_skb_protocol(skb) == htons(ETH_P_IP)) {
+	switch (skb_protocol(skb, true)) {
+	case htons(ETH_P_IP):
 		wlen += sizeof(struct iphdr);
 		if (!pskb_may_pull(skb, wlen))
 			goto out;
 
 		proto = NFPROTO_IPV4;
-	} else if (tc_skb_protocol(skb) == htons(ETH_P_IPV6)) {
+		break;
+	case htons(ETH_P_IPV6):
 		wlen += sizeof(struct ipv6hdr);
 		if (!pskb_may_pull(skb, wlen))
 			goto out;
 
 		proto = NFPROTO_IPV6;
-	} else {
+		break;
+	default:
 		goto out;
 	}
 
diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c
index be3f215cd027..8118e2640979 100644
--- a/net/sched/act_mpls.c
+++ b/net/sched/act_mpls.c
@@ -82,7 +82,7 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a,
 			goto drop;
 		break;
 	case TCA_MPLS_ACT_PUSH:
-		new_lse = tcf_mpls_get_lse(NULL, p, !eth_p_mpls(skb->protocol));
+		new_lse = tcf_mpls_get_lse(NULL, p, !eth_p_mpls(skb_protocol(skb, true)));
 		if (skb_mpls_push(skb, new_lse, p->tcfm_proto, mac_len,
 				  skb->dev && skb->dev->type == ARPHRD_ETHER))
 			goto drop;
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index b125b2be4467..b2b3faa57294 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -41,7 +41,7 @@ static int tcf_skbedit_act(struct sk_buff *skb, const struct tc_action *a,
 	if (params->flags & SKBEDIT_F_INHERITDSFIELD) {
 		int wlen = skb_network_offset(skb);
 
-		switch (tc_skb_protocol(skb)) {
+		switch (skb_protocol(skb, true)) {
 		case htons(ETH_P_IP):
 			wlen += sizeof(struct iphdr);
 			if (!pskb_may_pull(skb, wlen))
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 0a7ecc292bd3..58d469a66896 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1589,7 +1589,7 @@ static inline int __tcf_classify(struct sk_buff *skb,
 reclassify:
 #endif
 	for (; tp; tp = rcu_dereference_bh(tp->next)) {
-		__be16 protocol = tc_skb_protocol(skb);
+		__be16 protocol = skb_protocol(skb, false);
 		int err;
 
 		if (tp->protocol != protocol &&
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index 80ae7b9fa90a..ab53a93b2f2b 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -80,7 +80,7 @@ static u32 flow_get_dst(const struct sk_buff *skb, const struct flow_keys *flow)
 	if (dst)
 		return ntohl(dst);
 
-	return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb);
+	return addr_fold(skb_dst(skb)) ^ (__force u16)skb_protocol(skb, true);
 }
 
 static u32 flow_get_proto(const struct sk_buff *skb,
@@ -104,7 +104,7 @@ static u32 flow_get_proto_dst(const struct sk_buff *skb,
 	if (flow->ports.ports)
 		return ntohs(flow->ports.dst);
 
-	return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb);
+	return addr_fold(skb_dst(skb)) ^ (__force u16)skb_protocol(skb, true);
 }
 
 static u32 flow_get_iif(const struct sk_buff *skb)
@@ -151,7 +151,7 @@ static u32 flow_get_nfct(const struct sk_buff *skb)
 static u32 flow_get_nfct_src(const struct sk_buff *skb,
 			     const struct flow_keys *flow)
 {
-	switch (tc_skb_protocol(skb)) {
+	switch (skb_protocol(skb, true)) {
 	case htons(ETH_P_IP):
 		return ntohl(CTTUPLE(skb, src.u3.ip));
 	case htons(ETH_P_IPV6):
@@ -164,7 +164,7 @@ static u32 flow_get_nfct_src(const struct sk_buff *skb,
 static u32 flow_get_nfct_dst(const struct sk_buff *skb,
 			     const struct flow_keys *flow)
 {
-	switch (tc_skb_protocol(skb)) {
+	switch (skb_protocol(skb, true)) {
 	case htons(ETH_P_IP):
 		return ntohl(CTTUPLE(skb, dst.u3.ip));
 	case htons(ETH_P_IPV6):
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 74a0febcafb8..3b93d95d2a56 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -312,7 +312,7 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 		/* skb_flow_dissect() does not set n_proto in case an unknown
 		 * protocol, so do it rather here.
 		 */
-		skb_key.basic.n_proto = skb->protocol;
+		skb_key.basic.n_proto = skb_protocol(skb, false);
 		skb_flow_dissect_tunnel_info(skb, &mask->dissector, &skb_key);
 		skb_flow_dissect_ct(skb, &mask->dissector, &skb_key,
 				    fl_ct_info_to_flower_map,
diff --git a/net/sched/em_ipset.c b/net/sched/em_ipset.c
index df00566d327d..c95cf86fb431 100644
--- a/net/sched/em_ipset.c
+++ b/net/sched/em_ipset.c
@@ -59,7 +59,7 @@ static int em_ipset_match(struct sk_buff *skb, struct tcf_ematch *em,
 	};
 	int ret, network_offset;
 
-	switch (tc_skb_protocol(skb)) {
+	switch (skb_protocol(skb, true)) {
 	case htons(ETH_P_IP):
 		state.pf = NFPROTO_IPV4;
 		if (!pskb_network_may_pull(skb, sizeof(struct iphdr)))
diff --git a/net/sched/em_ipt.c b/net/sched/em_ipt.c
index eecfe072c508..9405b4d88002 100644
--- a/net/sched/em_ipt.c
+++ b/net/sched/em_ipt.c
@@ -212,7 +212,7 @@ static int em_ipt_match(struct sk_buff *skb, struct tcf_ematch *em,
 	struct nf_hook_state state;
 	int ret;
 
-	switch (tc_skb_protocol(skb)) {
+	switch (skb_protocol(skb, true)) {
 	case htons(ETH_P_IP):
 		if (!pskb_network_may_pull(skb, sizeof(struct iphdr)))
 			return 0;
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index d99966a55c84..46254968d390 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -195,7 +195,7 @@ META_COLLECTOR(int_priority)
 META_COLLECTOR(int_protocol)
 {
 	/* Let userspace take care of the byte ordering */
-	dst->value = tc_skb_protocol(skb);
+	dst->value = skb_protocol(skb, false);
 }
 
 META_COLLECTOR(int_pkttype)
diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 9475fa81ea7f..9bb2b8f73692 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -591,7 +591,7 @@ static void cake_update_flowkeys(struct flow_keys *keys,
 	struct nf_conntrack_tuple tuple = {};
 	bool rev = !skb->_nfct;
 
-	if (tc_skb_protocol(skb) != htons(ETH_P_IP))
+	if (skb_protocol(skb, true) != htons(ETH_P_IP))
 		return;
 
 	if (!nf_ct_get_tuple_skb(&tuple, skb))
@@ -1520,7 +1520,7 @@ static u8 cake_handle_diffserv(struct sk_buff *skb, bool wash)
 	u16 *buf, buf_;
 	u8 dscp;
 
-	switch (tc_skb_protocol(skb)) {
+	switch (skb_protocol(skb, true)) {
 	case htons(ETH_P_IP):
 		buf = skb_header_pointer(skb, offset, sizeof(buf_), &buf_);
 		if (unlikely(!buf))
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index 05605b30bef3..2b88710994d7 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -210,7 +210,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	if (p->set_tc_index) {
 		int wlen = skb_network_offset(skb);
 
-		switch (tc_skb_protocol(skb)) {
+		switch (skb_protocol(skb, true)) {
 		case htons(ETH_P_IP):
 			wlen += sizeof(struct iphdr);
 			if (!pskb_may_pull(skb, wlen) ||
@@ -303,7 +303,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch)
 	index = skb->tc_index & (p->indices - 1);
 	pr_debug("index %d->%d\n", skb->tc_index, index);
 
-	switch (tc_skb_protocol(skb)) {
+	switch (skb_protocol(skb, true)) {
 	case htons(ETH_P_IP):
 		ipv4_change_dsfield(ip_hdr(skb), p->mv[index].mask,
 				    p->mv[index].value);
@@ -320,7 +320,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch)
 		 */
 		if (p->mv[index].mask != 0xff || p->mv[index].value)
 			pr_warn("%s: unsupported protocol %d\n",
-				__func__, ntohs(tc_skb_protocol(skb)));
+				__func__, ntohs(skb_protocol(skb, true)));
 		break;
 	}
 
diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index 689ef6f3ded8..2f1f0a378408 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -239,7 +239,7 @@ __teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res,
 		char haddr[MAX_ADDR_LEN];
 
 		neigh_ha_snapshot(haddr, n, dev);
-		err = dev_hard_header(skb, dev, ntohs(tc_skb_protocol(skb)),
+		err = dev_hard_header(skb, dev, ntohs(skb_protocol(skb, false)),
 				      haddr, NULL, skb->len);
 
 		if (err < 0)
-- 
2.26.2


From 44768949aa283e2081af1b1f0d05dac7a5b158eb Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 30 Jun 2020 13:51:28 -0700
Subject: [PATCH 18/44] tcp: fix SO_RCVLOWAT possible hangs under high mem
 pressure

[ Upstream commit ba3bb0e76ccd464bb66665a1941fabe55dadb3ba ]

Whenever tcp_try_rmem_schedule() returns an error, we are under
trouble and should make sure to wakeup readers so that they
can drain socket queues and eventually make room.

Fixes: 03f45c883c6f ("tcp: avoid extra wakeups for SO_RCVLOWAT users")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 1fa009999f57..31c58e00d25b 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4570,6 +4570,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 
 	if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFODROP);
+		sk->sk_data_ready(sk);
 		tcp_drop(sk, skb);
 		return;
 	}
@@ -4816,6 +4817,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 			sk_forced_mem_schedule(sk, skb->truesize);
 		else if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) {
 			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP);
+			sk->sk_data_ready(sk);
 			goto drop;
 		}
 
-- 
2.26.2


From 63f8c2e93c4079227d3287f2ebc03de310f8a02d Mon Sep 17 00:00:00 2001
From: Christoph Paasch <cpaasch@apple.com>
Date: Wed, 8 Jul 2020 16:18:34 -0700
Subject: [PATCH 19/44] tcp: make sure listeners don't initialize
 congestion-control state

[ Upstream commit ce69e563b325f620863830c246a8698ccea52048 ]

syzkaller found its way into setsockopt with TCP_CONGESTION "cdg".
tcp_cdg_init() does a kcalloc to store the gradients. As sk_clone_lock
just copies all the memory, the allocated pointer will be copied as
well, if the app called setsockopt(..., TCP_CONGESTION) on the listener.
If now the socket will be destroyed before the congestion-control
has properly been initialized (through a call to tcp_init_transfer), we
will end up freeing memory that does not belong to that particular
socket, opening the door to a double-free:

[   11.413102] ==================================================================
[   11.414181] BUG: KASAN: double-free or invalid-free in tcp_cleanup_congestion_control+0x58/0xd0
[   11.415329]
[   11.415560] CPU: 3 PID: 4884 Comm: syz-executor.5 Not tainted 5.8.0-rc2 #80
[   11.416544] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014
[   11.418148] Call Trace:
[   11.418534]  <IRQ>
[   11.418834]  dump_stack+0x7d/0xb0
[   11.419297]  print_address_description.constprop.0+0x1a/0x210
[   11.422079]  kasan_report_invalid_free+0x51/0x80
[   11.423433]  __kasan_slab_free+0x15e/0x170
[   11.424761]  kfree+0x8c/0x230
[   11.425157]  tcp_cleanup_congestion_control+0x58/0xd0
[   11.425872]  tcp_v4_destroy_sock+0x57/0x5a0
[   11.426493]  inet_csk_destroy_sock+0x153/0x2c0
[   11.427093]  tcp_v4_syn_recv_sock+0xb29/0x1100
[   11.427731]  tcp_get_cookie_sock+0xc3/0x4a0
[   11.429457]  cookie_v4_check+0x13d0/0x2500
[   11.433189]  tcp_v4_do_rcv+0x60e/0x780
[   11.433727]  tcp_v4_rcv+0x2869/0x2e10
[   11.437143]  ip_protocol_deliver_rcu+0x23/0x190
[   11.437810]  ip_local_deliver+0x294/0x350
[   11.439566]  __netif_receive_skb_one_core+0x15d/0x1a0
[   11.441995]  process_backlog+0x1b1/0x6b0
[   11.443148]  net_rx_action+0x37e/0xc40
[   11.445361]  __do_softirq+0x18c/0x61a
[   11.445881]  asm_call_on_stack+0x12/0x20
[   11.446409]  </IRQ>
[   11.446716]  do_softirq_own_stack+0x34/0x40
[   11.447259]  do_softirq.part.0+0x26/0x30
[   11.447827]  __local_bh_enable_ip+0x46/0x50
[   11.448406]  ip_finish_output2+0x60f/0x1bc0
[   11.450109]  __ip_queue_xmit+0x71c/0x1b60
[   11.451861]  __tcp_transmit_skb+0x1727/0x3bb0
[   11.453789]  tcp_rcv_state_process+0x3070/0x4d3a
[   11.456810]  tcp_v4_do_rcv+0x2ad/0x780
[   11.457995]  __release_sock+0x14b/0x2c0
[   11.458529]  release_sock+0x4a/0x170
[   11.459005]  __inet_stream_connect+0x467/0xc80
[   11.461435]  inet_stream_connect+0x4e/0xa0
[   11.462043]  __sys_connect+0x204/0x270
[   11.465515]  __x64_sys_connect+0x6a/0xb0
[   11.466088]  do_syscall_64+0x3e/0x70
[   11.466617]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[   11.467341] RIP: 0033:0x7f56046dc469
[   11.467844] Code: Bad RIP value.
[   11.468282] RSP: 002b:00007f5604dccdd8 EFLAGS: 00000246 ORIG_RAX: 000000000000002a
[   11.469326] RAX: ffffffffffffffda RBX: 000000000068bf00 RCX: 00007f56046dc469
[   11.470379] RDX: 0000000000000010 RSI: 0000000020000000 RDI: 0000000000000004
[   11.471311] RBP: 00000000ffffffff R08: 0000000000000000 R09: 0000000000000000
[   11.472286] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
[   11.473341] R13: 000000000041427c R14: 00007f5604dcd5c0 R15: 0000000000000003
[   11.474321]
[   11.474527] Allocated by task 4884:
[   11.475031]  save_stack+0x1b/0x40
[   11.475548]  __kasan_kmalloc.constprop.0+0xc2/0xd0
[   11.476182]  tcp_cdg_init+0xf0/0x150
[   11.476744]  tcp_init_congestion_control+0x9b/0x3a0
[   11.477435]  tcp_set_congestion_control+0x270/0x32f
[   11.478088]  do_tcp_setsockopt.isra.0+0x521/0x1a00
[   11.478744]  __sys_setsockopt+0xff/0x1e0
[   11.479259]  __x64_sys_setsockopt+0xb5/0x150
[   11.479895]  do_syscall_64+0x3e/0x70
[   11.480395]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[   11.481097]
[   11.481321] Freed by task 4872:
[   11.481783]  save_stack+0x1b/0x40
[   11.482230]  __kasan_slab_free+0x12c/0x170
[   11.482839]  kfree+0x8c/0x230
[   11.483240]  tcp_cleanup_congestion_control+0x58/0xd0
[   11.483948]  tcp_v4_destroy_sock+0x57/0x5a0
[   11.484502]  inet_csk_destroy_sock+0x153/0x2c0
[   11.485144]  tcp_close+0x932/0xfe0
[   11.485642]  inet_release+0xc1/0x1c0
[   11.486131]  __sock_release+0xc0/0x270
[   11.486697]  sock_close+0xc/0x10
[   11.487145]  __fput+0x277/0x780
[   11.487632]  task_work_run+0xeb/0x180
[   11.488118]  __prepare_exit_to_usermode+0x15a/0x160
[   11.488834]  do_syscall_64+0x4a/0x70
[   11.489326]  entry_SYSCALL_64_after_hwframe+0x44/0xa9

Wei Wang fixed a part of these CDG-malloc issues with commit c12014440750
("tcp: memset ca_priv data to 0 properly").

This patch here fixes the listener-scenario: We make sure that listeners
setting the congestion-control through setsockopt won't initialize it
(thus CDG never allocates on listeners). For those who use AF_UNSPEC to
reuse a socket, tcp_disconnect() is changed to cleanup afterwards.

(The issue can be reproduced at least down to v4.4.x.)

Cc: Wei Wang <weiwan@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Fixes: 2b0a8c9eee81 ("tcp: add CDG congestion control")
Signed-off-by: Christoph Paasch <cpaasch@apple.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c      | 3 +++
 net/ipv4/tcp_cong.c | 2 +-
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index dd401757eea1..4f41299e4d58 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2635,6 +2635,9 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tp->window_clamp = 0;
 	tp->delivered = 0;
 	tp->delivered_ce = 0;
+	if (icsk->icsk_ca_ops->release)
+		icsk->icsk_ca_ops->release(sk);
+	memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
 	tcp_set_ca_state(sk, TCP_CA_Open);
 	tp->is_sack_reneg = 0;
 	tcp_clear_retrans(tp);
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 3172e31987be..62878cf26d9c 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -197,7 +197,7 @@ static void tcp_reinit_congestion_control(struct sock *sk,
 	icsk->icsk_ca_setsockopt = 1;
 	memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
 
-	if (sk->sk_state != TCP_CLOSE)
+	if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)))
 		tcp_init_congestion_control(sk);
 }
 
-- 
2.26.2


From 94d9bb098df7ad50500500bee653d22e99f5560b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 30 Jun 2020 16:41:01 -0700
Subject: [PATCH 20/44] tcp: md5: add missing memory barriers in
 tcp_md5_do_add()/tcp_md5_hash_key()

[ Upstream commit 6a2febec338df7e7699a52d00b2e1207dcf65b28 ]

MD5 keys are read with RCU protection, and tcp_md5_do_add()
might update in-place a prior key.

Normally, typical RCU updates would allocate a new piece
of memory. In this case only key->key and key->keylen might
be updated, and we do not care if an incoming packet could
see the old key, the new one, or some intermediate value,
since changing the key on a live flow is known to be problematic
anyway.

We only want to make sure that in the case key->keylen
is changed, cpus in tcp_md5_hash_key() wont try to use
uninitialized data, or crash because key->keylen was
read twice to feed sg_init_one() and ahash_request_set_crypt()

Fixes: 9ea88a153001 ("tcp: md5: check md5 signature without socket lock")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c      | 7 +++++--
 net/ipv4/tcp_ipv4.c | 3 +++
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 4f41299e4d58..74bfe9a3e2fa 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3880,10 +3880,13 @@ EXPORT_SYMBOL(tcp_md5_hash_skb_data);
 
 int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, const struct tcp_md5sig_key *key)
 {
+	u8 keylen = key->keylen;
 	struct scatterlist sg;
 
-	sg_init_one(&sg, key->key, key->keylen);
-	ahash_request_set_crypt(hp->md5_req, &sg, NULL, key->keylen);
+	smp_rmb(); /* paired with smp_wmb() in tcp_md5_do_add() */
+
+	sg_init_one(&sg, key->key, keylen);
+	ahash_request_set_crypt(hp->md5_req, &sg, NULL, keylen);
 	return crypto_ahash_update(hp->md5_req);
 }
 EXPORT_SYMBOL(tcp_md5_hash_key);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 83a5d24e13b8..2a7e215eb195 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1105,6 +1105,9 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
 	if (key) {
 		/* Pre-existing entry - just update that one. */
 		memcpy(key->key, newkey, newkeylen);
+
+		smp_wmb(); /* pairs with smp_rmb() in tcp_md5_hash_key() */
+
 		key->keylen = newkeylen;
 		return 0;
 	}
-- 
2.26.2


From d235d99b223f97ad930cb32b16d7efda7a168030 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 1 Jul 2020 12:41:23 -0700
Subject: [PATCH 21/44] tcp: md5: do not send silly options in SYNCOOKIES

[ Upstream commit e114e1e8ac9d31f25b9dd873bab5d80c1fc482ca ]

Whenever cookie_init_timestamp() has been used to encode
ECN,SACK,WSCALE options, we can not remove the TS option in the SYNACK.

Otherwise, tcp_synack_options() will still advertize options like WSCALE
that we can not deduce later when receiving the packet from the client
to complete 3WHS.

Note that modern linux TCP stacks wont use MD5+TS+SACK in a SYN packet,
but we can not know for sure that all TCP stacks have the same logic.

Before the fix a tcpdump would exhibit this wrong exchange :

10:12:15.464591 IP C > S: Flags [S], seq 4202415601, win 65535, options [nop,nop,md5 valid,mss 1400,sackOK,TS val 456965269 ecr 0,nop,wscale 8], length 0
10:12:15.464602 IP S > C: Flags [S.], seq 253516766, ack 4202415602, win 65535, options [nop,nop,md5 valid,mss 1400,nop,nop,sackOK,nop,wscale 8], length 0
10:12:15.464611 IP C > S: Flags [.], ack 1, win 256, options [nop,nop,md5 valid], length 0
10:12:15.464678 IP C > S: Flags [P.], seq 1:13, ack 1, win 256, options [nop,nop,md5 valid], length 12
10:12:15.464685 IP S > C: Flags [.], ack 13, win 65535, options [nop,nop,md5 valid], length 0

After this patch the exchange looks saner :

11:59:59.882990 IP C > S: Flags [S], seq 517075944, win 65535, options [nop,nop,md5 valid,mss 1400,sackOK,TS val 1751508483 ecr 0,nop,wscale 8], length 0
11:59:59.883002 IP S > C: Flags [S.], seq 1902939253, ack 517075945, win 65535, options [nop,nop,md5 valid,mss 1400,sackOK,TS val 1751508479 ecr 1751508483,nop,wscale 8], length 0
11:59:59.883012 IP C > S: Flags [.], ack 1, win 256, options [nop,nop,md5 valid,nop,nop,TS val 1751508483 ecr 1751508479], length 0
11:59:59.883114 IP C > S: Flags [P.], seq 1:13, ack 1, win 256, options [nop,nop,md5 valid,nop,nop,TS val 1751508483 ecr 1751508479], length 12
11:59:59.883122 IP S > C: Flags [.], ack 13, win 256, options [nop,nop,md5 valid,nop,nop,TS val 1751508483 ecr 1751508483], length 0
11:59:59.883152 IP S > C: Flags [P.], seq 1:13, ack 13, win 256, options [nop,nop,md5 valid,nop,nop,TS val 1751508484 ecr 1751508483], length 12
11:59:59.883170 IP C > S: Flags [.], ack 13, win 256, options [nop,nop,md5 valid,nop,nop,TS val 1751508484 ecr 1751508484], length 0

Of course, no SACK block will ever be added later, but nothing should break.
Technically, we could remove the 4 nops included in MD5+TS options,
but again some stacks could break seeing not conventional alignment.

Fixes: 4957faade11b ("TCPCT part 1g: Responder Cookie => Initiator")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Florian Westphal <fw@strlen.de>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 2f45cde168c4..bee2f9b8b8a1 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -700,7 +700,8 @@ static unsigned int tcp_synack_options(const struct sock *sk,
 				       unsigned int mss, struct sk_buff *skb,
 				       struct tcp_out_options *opts,
 				       const struct tcp_md5sig_key *md5,
-				       struct tcp_fastopen_cookie *foc)
+				       struct tcp_fastopen_cookie *foc,
+				       enum tcp_synack_type synack_type)
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
 	unsigned int remaining = MAX_TCP_OPTION_SPACE;
@@ -715,7 +716,8 @@ static unsigned int tcp_synack_options(const struct sock *sk,
 		 * rather than TS in order to fit in better with old,
 		 * buggy kernels, but that was deemed to be unnecessary.
 		 */
-		ireq->tstamp_ok &= !ireq->sack_ok;
+		if (synack_type != TCP_SYNACK_COOKIE)
+			ireq->tstamp_ok &= !ireq->sack_ok;
 	}
 #endif
 
@@ -3388,7 +3390,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 #endif
 	skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4);
 	tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5,
-					     foc) + sizeof(*th);
+					     foc, synack_type) + sizeof(*th);
 
 	skb_push(skb, tcp_header_size);
 	skb_reset_transport_header(skb);
-- 
2.26.2


From f567e2c827c5bbdf4eb31d8dd6f4f0b138cca279 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
Date: Tue, 7 Jul 2020 13:03:25 +0200
Subject: [PATCH 22/44] vlan: consolidate VLAN parsing code and limit max
 parsing depth
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 469aceddfa3ed16e17ee30533fae45e90f62efd8 ]

Toshiaki pointed out that we now have two very similar functions to extract
the L3 protocol number in the presence of VLAN tags. And Daniel pointed out
that the unbounded parsing loop makes it possible for maliciously crafted
packets to loop through potentially hundreds of tags.

Fix both of these issues by consolidating the two parsing functions and
limiting the VLAN tag parsing to a max depth of 8 tags. As part of this,
switch over __vlan_get_protocol() to use skb_header_pointer() instead of
pskb_may_pull(), to avoid the possible side effects of the latter and keep
the skb pointer 'const' through all the parsing functions.

v2:
- Use limit of 8 tags instead of 32 (matching XMIT_RECURSION_LIMIT)

Reported-by: Toshiaki Makita <toshiaki.makita1@gmail.com>
Reported-by: Daniel Borkmann <daniel@iogearbox.net>
Fixes: d7bf2ebebc2b ("sched: consistently handle layer3 header accesses in the presence of VLANs")
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_vlan.h | 57 ++++++++++++++++-------------------------
 1 file changed, 22 insertions(+), 35 deletions(-)

diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 427a5b8597c2..41a518336673 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -25,6 +25,8 @@
 #define VLAN_ETH_DATA_LEN	1500	/* Max. octets in payload	 */
 #define VLAN_ETH_FRAME_LEN	1518	/* Max. octets in frame sans FCS */
 
+#define VLAN_MAX_DEPTH	8		/* Max. number of nested VLAN tags parsed */
+
 /*
  * 	struct vlan_hdr - vlan header
  * 	@h_vlan_TCI: priority and VLAN ID
@@ -308,34 +310,6 @@ static inline bool eth_type_vlan(__be16 ethertype)
 	}
 }
 
-/* A getter for the SKB protocol field which will handle VLAN tags consistently
- * whether VLAN acceleration is enabled or not.
- */
-static inline __be16 skb_protocol(const struct sk_buff *skb, bool skip_vlan)
-{
-	unsigned int offset = skb_mac_offset(skb) + sizeof(struct ethhdr);
-	__be16 proto = skb->protocol;
-
-	if (!skip_vlan)
-		/* VLAN acceleration strips the VLAN header from the skb and
-		 * moves it to skb->vlan_proto
-		 */
-		return skb_vlan_tag_present(skb) ? skb->vlan_proto : proto;
-
-	while (eth_type_vlan(proto)) {
-		struct vlan_hdr vhdr, *vh;
-
-		vh = skb_header_pointer(skb, offset, sizeof(vhdr), &vhdr);
-		if (!vh)
-			break;
-
-		proto = vh->h_vlan_encapsulated_proto;
-		offset += sizeof(vhdr);
-	}
-
-	return proto;
-}
-
 static inline bool vlan_hw_offload_capable(netdev_features_t features,
 					   __be16 proto)
 {
@@ -605,10 +579,10 @@ static inline int vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci)
  * Returns the EtherType of the packet, regardless of whether it is
  * vlan encapsulated (normal or hardware accelerated) or not.
  */
-static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type,
+static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type,
 					 int *depth)
 {
-	unsigned int vlan_depth = skb->mac_len;
+	unsigned int vlan_depth = skb->mac_len, parse_depth = VLAN_MAX_DEPTH;
 
 	/* if type is 802.1Q/AD then the header should already be
 	 * present at mac_len - VLAN_HLEN (if mac_len > 0), or at
@@ -623,13 +597,12 @@ static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type,
 			vlan_depth = ETH_HLEN;
 		}
 		do {
-			struct vlan_hdr *vh;
+			struct vlan_hdr vhdr, *vh;
 
-			if (unlikely(!pskb_may_pull(skb,
-						    vlan_depth + VLAN_HLEN)))
+			vh = skb_header_pointer(skb, vlan_depth, sizeof(vhdr), &vhdr);
+			if (unlikely(!vh || !--parse_depth))
 				return 0;
 
-			vh = (struct vlan_hdr *)(skb->data + vlan_depth);
 			type = vh->h_vlan_encapsulated_proto;
 			vlan_depth += VLAN_HLEN;
 		} while (eth_type_vlan(type));
@@ -648,11 +621,25 @@ static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type,
  * Returns the EtherType of the packet, regardless of whether it is
  * vlan encapsulated (normal or hardware accelerated) or not.
  */
-static inline __be16 vlan_get_protocol(struct sk_buff *skb)
+static inline __be16 vlan_get_protocol(const struct sk_buff *skb)
 {
 	return __vlan_get_protocol(skb, skb->protocol, NULL);
 }
 
+/* A getter for the SKB protocol field which will handle VLAN tags consistently
+ * whether VLAN acceleration is enabled or not.
+ */
+static inline __be16 skb_protocol(const struct sk_buff *skb, bool skip_vlan)
+{
+	if (!skip_vlan)
+		/* VLAN acceleration strips the VLAN header from the skb and
+		 * moves it to skb->vlan_proto
+		 */
+		return skb_vlan_tag_present(skb) ? skb->vlan_proto : skb->protocol;
+
+	return vlan_get_protocol(skb);
+}
+
 static inline void vlan_set_encap_proto(struct sk_buff *skb,
 					struct vlan_hdr *vhdr)
 {
-- 
2.26.2


From c929dda54c2e1e7c03a37a799055f1be0bdc5b7d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 1 Jul 2020 11:43:04 -0700
Subject: [PATCH 23/44] tcp: md5: refine tcp_md5_do_add()/tcp_md5_hash_key()
 barriers

[ Upstream commit e6ced831ef11a2a06e8d00aad9d4fc05b610bf38 ]

My prior fix went a bit too far, according to Herbert and Mathieu.

Since we accept that concurrent TCP MD5 lookups might see inconsistent
keys, we can use READ_ONCE()/WRITE_ONCE() instead of smp_rmb()/smp_wmb()

Clearing all key->key[] is needed to avoid possible KMSAN reports,
if key->keylen is increased. Since tcp_md5_do_add() is not fast path,
using __GFP_ZERO to clear all struct tcp_md5sig_key is simpler.

data_race() was added in linux-5.8 and will prevent KCSAN reports,
this can safely be removed in stable backports, if data_race() is
not yet backported.

v2: use data_race() both in tcp_md5_hash_key() and tcp_md5_do_add()

Fixes: 6a2febec338d ("tcp: md5: add missing memory barriers in tcp_md5_do_add()/tcp_md5_hash_key()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Marco Elver <elver@google.com>
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c      |  6 +++---
 net/ipv4/tcp_ipv4.c | 14 ++++++++++----
 2 files changed, 13 insertions(+), 7 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 74bfe9a3e2fa..d679c91bb729 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3880,13 +3880,13 @@ EXPORT_SYMBOL(tcp_md5_hash_skb_data);
 
 int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, const struct tcp_md5sig_key *key)
 {
-	u8 keylen = key->keylen;
+	u8 keylen = READ_ONCE(key->keylen); /* paired with WRITE_ONCE() in tcp_md5_do_add */
 	struct scatterlist sg;
 
-	smp_rmb(); /* paired with smp_wmb() in tcp_md5_do_add() */
-
 	sg_init_one(&sg, key->key, keylen);
 	ahash_request_set_crypt(hp->md5_req, &sg, NULL, keylen);
+
+	/* tcp_md5_do_add() might change key->key under us */
 	return crypto_ahash_update(hp->md5_req);
 }
 EXPORT_SYMBOL(tcp_md5_hash_key);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 2a7e215eb195..4c2f2f2107a9 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1103,12 +1103,18 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
 
 	key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen, l3index);
 	if (key) {
-		/* Pre-existing entry - just update that one. */
+		/* Pre-existing entry - just update that one.
+		 * Note that the key might be used concurrently.
+		 */
 		memcpy(key->key, newkey, newkeylen);
 
-		smp_wmb(); /* pairs with smp_rmb() in tcp_md5_hash_key() */
+		/* Pairs with READ_ONCE() in tcp_md5_hash_key().
+		 * Also note that a reader could catch new key->keylen value
+		 * but old key->key[], this is the reason we use __GFP_ZERO
+		 * at sock_kmalloc() time below these lines.
+		 */
+		WRITE_ONCE(key->keylen, newkeylen);
 
-		key->keylen = newkeylen;
 		return 0;
 	}
 
@@ -1124,7 +1130,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
 		rcu_assign_pointer(tp->md5sig_info, md5sig);
 	}
 
-	key = sock_kmalloc(sk, sizeof(*key), gfp);
+	key = sock_kmalloc(sk, sizeof(*key), gfp | __GFP_ZERO);
 	if (!key)
 		return -ENOMEM;
 	if (!tcp_alloc_md5sig_pool()) {
-- 
2.26.2


From 2fe01871c7d742a4b397b5260849ed79b0fb88f4 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 1 Jul 2020 18:39:33 -0700
Subject: [PATCH 24/44] tcp: md5: allow changing MD5 keys in all socket states

[ Upstream commit 1ca0fafd73c5268e8fc4b997094b8bb2bfe8deea ]

This essentially reverts commit 721230326891 ("tcp: md5: reject TCP_MD5SIG
or TCP_MD5SIG_EXT on established sockets")

Mathieu reported that many vendors BGP implementations can
actually switch TCP MD5 on established flows.

Quoting Mathieu :
   Here is a list of a few network vendors along with their behavior
   with respect to TCP MD5:

   - Cisco: Allows for password to be changed, but within the hold-down
     timer (~180 seconds).
   - Juniper: When password is initially set on active connection it will
     reset, but after that any subsequent password changes no network
     resets.
   - Nokia: No notes on if they flap the tcp connection or not.
   - Ericsson/RedBack: Allows for 2 password (old/new) to co-exist until
     both sides are ok with new passwords.
   - Meta-Switch: Expects the password to be set before a connection is
     attempted, but no further info on whether they reset the TCP
     connection on a change.
   - Avaya: Disable the neighbor, then set password, then re-enable.
   - Zebos: Would normally allow the change when socket connected.

We can revert my prior change because commit 9424e2e7ad93 ("tcp: md5: fix potential
overestimation of TCP option space") removed the leak of 4 kernel bytes to
the wire that was the main reason for my patch.

While doing my investigations, I found a bug when a MD5 key is changed, leading
to these commits that stable teams want to consider before backporting this revert :

 Commit 6a2febec338d ("tcp: md5: add missing memory barriers in tcp_md5_do_add()/tcp_md5_hash_key()")
 Commit e6ced831ef11 ("tcp: md5: refine tcp_md5_do_add()/tcp_md5_hash_key() barriers")

Fixes: 721230326891 "tcp: md5: reject TCP_MD5SIG or TCP_MD5SIG_EXT on established sockets"
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index d679c91bb729..eee18259a24e 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3093,10 +3093,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 #ifdef CONFIG_TCP_MD5SIG
 	case TCP_MD5SIG:
 	case TCP_MD5SIG_EXT:
-		if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))
-			err = tp->af_specific->md5_parse(sk, optname, optval, optlen);
-		else
-			err = -EINVAL;
+		err = tp->af_specific->md5_parse(sk, optname, optval, optlen);
 		break;
 #endif
 	case TCP_USER_TIMEOUT:
-- 
2.26.2


From ab68b1fe337178149cc8e8205ac1eeb938d91fbd Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 2 Jul 2020 11:52:56 -0700
Subject: [PATCH 25/44] cgroup: fix cgroup_sk_alloc() for sk_clone_lock()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit ad0f75e5f57ccbceec13274e1e242f2b5a6397ed ]

When we clone a socket in sk_clone_lock(), its sk_cgrp_data is
copied, so the cgroup refcnt must be taken too. And, unlike the
sk_alloc() path, sock_update_netprioidx() is not called here.
Therefore, it is safe and necessary to grab the cgroup refcnt
even when cgroup_sk_alloc is disabled.

sk_clone_lock() is in BH context anyway, the in_interrupt()
would terminate this function if called there. And for sk_alloc()
skcd->val is always zero. So it's safe to factor out the code
to make it more readable.

The global variable 'cgroup_sk_alloc_disabled' is used to determine
whether to take these reference counts. It is impossible to make
the reference counting correct unless we save this bit of information
in skcd->val. So, add a new bit there to record whether the socket
has already taken the reference counts. This obviously relies on
kmalloc() to align cgroup pointers to at least 4 bytes,
ARCH_KMALLOC_MINALIGN is certainly larger than that.

This bug seems to be introduced since the beginning, commit
d979a39d7242 ("cgroup: duplicate cgroup reference when cloning sockets")
tried to fix it but not compeletely. It seems not easy to trigger until
the recent commit 090e28b229af
("netprio_cgroup: Fix unlimited memory leak of v2 cgroups") was merged.

Fixes: bd1060a1d671 ("sock, cgroup: add sock->sk_cgroup")
Reported-by: Cameron Berkenpas <cam@neo-zeon.de>
Reported-by: Peter Geis <pgwipeout@gmail.com>
Reported-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Reported-by: Daniël Sonck <dsonck92@gmail.com>
Reported-by: Zhang Qiang <qiang.zhang@windriver.com>
Tested-by: Cameron Berkenpas <cam@neo-zeon.de>
Tested-by: Peter Geis <pgwipeout@gmail.com>
Tested-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Zefan Li <lizefan@huawei.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Roman Gushchin <guro@fb.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/cgroup-defs.h |  6 ++++--
 include/linux/cgroup.h      |  4 +++-
 kernel/cgroup/cgroup.c      | 31 +++++++++++++++++++------------
 net/core/sock.c             |  2 +-
 4 files changed, 27 insertions(+), 16 deletions(-)

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 52661155f85f..4f1cd0edc57d 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -790,7 +790,8 @@ struct sock_cgroup_data {
 	union {
 #ifdef __LITTLE_ENDIAN
 		struct {
-			u8	is_data;
+			u8	is_data : 1;
+			u8	no_refcnt : 1;
 			u8	padding;
 			u16	prioidx;
 			u32	classid;
@@ -800,7 +801,8 @@ struct sock_cgroup_data {
 			u32	classid;
 			u16	prioidx;
 			u8	padding;
-			u8	is_data;
+			u8	no_refcnt : 1;
+			u8	is_data : 1;
 		} __packed;
 #endif
 		u64		val;
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 4598e4da6b1b..618838c48313 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -822,6 +822,7 @@ extern spinlock_t cgroup_sk_update_lock;
 
 void cgroup_sk_alloc_disable(void);
 void cgroup_sk_alloc(struct sock_cgroup_data *skcd);
+void cgroup_sk_clone(struct sock_cgroup_data *skcd);
 void cgroup_sk_free(struct sock_cgroup_data *skcd);
 
 static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd)
@@ -835,7 +836,7 @@ static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd)
 	 */
 	v = READ_ONCE(skcd->val);
 
-	if (v & 1)
+	if (v & 3)
 		return &cgrp_dfl_root.cgrp;
 
 	return (struct cgroup *)(unsigned long)v ?: &cgrp_dfl_root.cgrp;
@@ -847,6 +848,7 @@ static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd)
 #else	/* CONFIG_CGROUP_DATA */
 
 static inline void cgroup_sk_alloc(struct sock_cgroup_data *skcd) {}
+static inline void cgroup_sk_clone(struct sock_cgroup_data *skcd) {}
 static inline void cgroup_sk_free(struct sock_cgroup_data *skcd) {}
 
 #endif	/* CONFIG_CGROUP_DATA */
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 06b5ea9d899d..9b46a7604e7b 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -6447,18 +6447,8 @@ void cgroup_sk_alloc_disable(void)
 
 void cgroup_sk_alloc(struct sock_cgroup_data *skcd)
 {
-	if (cgroup_sk_alloc_disabled)
-		return;
-
-	/* Socket clone path */
-	if (skcd->val) {
-		/*
-		 * We might be cloning a socket which is left in an empty
-		 * cgroup and the cgroup might have already been rmdir'd.
-		 * Don't use cgroup_get_live().
-		 */
-		cgroup_get(sock_cgroup_ptr(skcd));
-		cgroup_bpf_get(sock_cgroup_ptr(skcd));
+	if (cgroup_sk_alloc_disabled) {
+		skcd->no_refcnt = 1;
 		return;
 	}
 
@@ -6483,10 +6473,27 @@ void cgroup_sk_alloc(struct sock_cgroup_data *skcd)
 	rcu_read_unlock();
 }
 
+void cgroup_sk_clone(struct sock_cgroup_data *skcd)
+{
+	if (skcd->val) {
+		if (skcd->no_refcnt)
+			return;
+		/*
+		 * We might be cloning a socket which is left in an empty
+		 * cgroup and the cgroup might have already been rmdir'd.
+		 * Don't use cgroup_get_live().
+		 */
+		cgroup_get(sock_cgroup_ptr(skcd));
+		cgroup_bpf_get(sock_cgroup_ptr(skcd));
+	}
+}
+
 void cgroup_sk_free(struct sock_cgroup_data *skcd)
 {
 	struct cgroup *cgrp = sock_cgroup_ptr(skcd);
 
+	if (skcd->no_refcnt)
+		return;
 	cgroup_bpf_put(cgrp);
 	cgroup_put(cgrp);
 }
diff --git a/net/core/sock.c b/net/core/sock.c
index afe4a62adf8f..bc6fe4114374 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1837,7 +1837,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		/* sk->sk_memcg will be populated at accept() time */
 		newsk->sk_memcg = NULL;
 
-		cgroup_sk_alloc(&newsk->sk_cgrp_data);
+		cgroup_sk_clone(&newsk->sk_cgrp_data);
 
 		rcu_read_lock();
 		filter = rcu_dereference(sk->sk_filter);
-- 
2.26.2


From d4550a92c2d70983fde30965cd3759156dd9214f Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 9 Jul 2020 16:28:44 -0700
Subject: [PATCH 26/44] cgroup: Fix sock_cgroup_data on big-endian.

[ Upstream commit 14b032b8f8fce03a546dcf365454bec8c4a58d7d ]

In order for no_refcnt and is_data to be the lowest order two
bits in the 'val' we have to pad out the bitfield of the u8.

Fixes: ad0f75e5f57c ("cgroup: fix cgroup_sk_alloc() for sk_clone_lock()")
Reported-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/cgroup-defs.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 4f1cd0edc57d..fee0b5547cd0 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -792,6 +792,7 @@ struct sock_cgroup_data {
 		struct {
 			u8	is_data : 1;
 			u8	no_refcnt : 1;
+			u8	unused : 6;
 			u8	padding;
 			u16	prioidx;
 			u32	classid;
@@ -801,6 +802,7 @@ struct sock_cgroup_data {
 			u32	classid;
 			u16	prioidx;
 			u8	padding;
+			u8	unused : 6;
 			u8	no_refcnt : 1;
 			u8	is_data : 1;
 		} __packed;
-- 
2.26.2


From 237b9f9c4f4c1f86732b361c0e1c33f1c06875ca Mon Sep 17 00:00:00 2001
From: Alex Elder <elder@linaro.org>
Date: Tue, 30 Jun 2020 07:44:42 -0500
Subject: [PATCH 27/44] net: ipa: always check for stopped channel

[ Upstream commit 5468cbcddf47f674829c6ada190283108a63d7b5 ]

In gsi_channel_stop(), there's a check to see if the channel might
have entered STOPPED state since a previous call, which might have
timed out before stopping completed.

That check actually belongs in gsi_channel_stop_command(), which is
called repeatedly by gsi_channel_stop() for RX channels.

Fixes: 650d1603825d ("soc: qcom: ipa: the generic software interface")
Signed-off-by: Alex Elder <elder@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ipa/gsi.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ipa/gsi.c b/drivers/net/ipa/gsi.c
index 043a675e1be1..6144a1ccc0f3 100644
--- a/drivers/net/ipa/gsi.c
+++ b/drivers/net/ipa/gsi.c
@@ -490,6 +490,12 @@ static int gsi_channel_stop_command(struct gsi_channel *channel)
 	enum gsi_channel_state state = channel->state;
 	int ret;
 
+	/* Channel could have entered STOPPED state since last call
+	 * if it timed out.  If so, we're done.
+	 */
+	if (state == GSI_CHANNEL_STATE_STOPPED)
+		return 0;
+
 	if (state != GSI_CHANNEL_STATE_STARTED &&
 	    state != GSI_CHANNEL_STATE_STOP_IN_PROC)
 		return -EINVAL;
@@ -773,13 +779,6 @@ int gsi_channel_stop(struct gsi *gsi, u32 channel_id)
 
 	gsi_channel_freeze(channel);
 
-	/* Channel could have entered STOPPED state since last call if the
-	 * STOP command timed out.  We won't stop a channel if stopping it
-	 * was successful previously (so we still want the freeze above).
-	 */
-	if (channel->state == GSI_CHANNEL_STATE_STOPPED)
-		return 0;
-
 	/* RX channels might require a little time to enter STOPPED state */
 	retries = channel->toward_ipa ? 0 : GSI_CHANNEL_STOP_RX_RETRIES;
 
-- 
2.26.2


From f275b7a75ec67d553cc19c817bac894adc8779d9 Mon Sep 17 00:00:00 2001
From: Alex Elder <elder@linaro.org>
Date: Tue, 30 Jun 2020 07:44:43 -0500
Subject: [PATCH 28/44] net: ipa: no checksum offload for SDM845 LAN RX

[ Upstream commit 41af5436e857ec64f302fcc9b6e4a8c526b6b402 ]

The AP LAN RX endpoint should not have download checksum offload
enabled.

The receive handler does properly accommodate the trailer that's
added by the hardware, but we ignore it.

Fixes: 1ed7d0c0fdba ("soc: qcom: ipa: configuration data")
Signed-off-by: Alex Elder <elder@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ipa/ipa_data-sdm845.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ipa/ipa_data-sdm845.c b/drivers/net/ipa/ipa_data-sdm845.c
index 0d9c36e1e806..0917c5b028f6 100644
--- a/drivers/net/ipa/ipa_data-sdm845.c
+++ b/drivers/net/ipa/ipa_data-sdm845.c
@@ -44,7 +44,6 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = {
 		.endpoint = {
 			.seq_type	= IPA_SEQ_INVALID,
 			.config = {
-				.checksum	= true,
 				.aggregation	= true,
 				.status_enable	= true,
 				.rx = {
-- 
2.26.2


From 9bf20cc8c7e7a11ca7e1fdad28a1c1296a7fc3e6 Mon Sep 17 00:00:00 2001
From: Alex Elder <elder@linaro.org>
Date: Tue, 30 Jun 2020 07:44:44 -0500
Subject: [PATCH 29/44] net: ipa: introduce ipa_cmd_tag_process()

[ Upstream commit 6cb63ea6a39eac9640d109f274a237b34350c183 ]

Create a new function ipa_cmd_tag_process() that simply allocates a
transaction, adds a tag process command to it to clear the hardware
pipeline, and commits the transaction.

Call it in from ipa_endpoint_suspend(), after suspending the modem
endpoints but before suspending the AP command TX and AP LAN RX
endpoints (which are used by the tag sequence).

Signed-off-by: Alex Elder <elder@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ipa/ipa_cmd.c      | 15 +++++++++++++++
 drivers/net/ipa/ipa_cmd.h      |  8 ++++++++
 drivers/net/ipa/ipa_endpoint.c |  2 ++
 3 files changed, 25 insertions(+)

diff --git a/drivers/net/ipa/ipa_cmd.c b/drivers/net/ipa/ipa_cmd.c
index cee417181f98..e4febda2d6b4 100644
--- a/drivers/net/ipa/ipa_cmd.c
+++ b/drivers/net/ipa/ipa_cmd.c
@@ -645,6 +645,21 @@ u32 ipa_cmd_tag_process_count(void)
 	return 4;
 }
 
+void ipa_cmd_tag_process(struct ipa *ipa)
+{
+	u32 count = ipa_cmd_tag_process_count();
+	struct gsi_trans *trans;
+
+	trans = ipa_cmd_trans_alloc(ipa, count);
+	if (trans) {
+		ipa_cmd_tag_process_add(trans);
+		gsi_trans_commit_wait(trans);
+	} else {
+		dev_err(&ipa->pdev->dev,
+			"error allocating %u entry tag transaction\n", count);
+	}
+}
+
 static struct ipa_cmd_info *
 ipa_cmd_info_alloc(struct ipa_endpoint *endpoint, u32 tre_count)
 {
diff --git a/drivers/net/ipa/ipa_cmd.h b/drivers/net/ipa/ipa_cmd.h
index 4917525b3a47..1ee9265651a1 100644
--- a/drivers/net/ipa/ipa_cmd.h
+++ b/drivers/net/ipa/ipa_cmd.h
@@ -182,6 +182,14 @@ void ipa_cmd_tag_process_add(struct gsi_trans *trans);
  */
 u32 ipa_cmd_tag_process_count(void);
 
+/**
+ * ipa_cmd_tag_process() - Perform a tag process
+ *
+ * @Return:	The number of elements to allocate in a transaction
+ *		to hold tag process commands
+ */
+void ipa_cmd_tag_process(struct ipa *ipa);
+
 /**
  * ipa_cmd_trans_alloc() - Allocate a transaction for the command TX endpoint
  * @ipa:	IPA pointer
diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c
index 1d823ac0f6d6..371c93953aea 100644
--- a/drivers/net/ipa/ipa_endpoint.c
+++ b/drivers/net/ipa/ipa_endpoint.c
@@ -1485,6 +1485,8 @@ void ipa_endpoint_suspend(struct ipa *ipa)
 	if (ipa->modem_netdev)
 		ipa_modem_suspend(ipa->modem_netdev);
 
+	ipa_cmd_tag_process(ipa);
+
 	ipa_endpoint_suspend_one(ipa->name_map[IPA_ENDPOINT_AP_LAN_RX]);
 	ipa_endpoint_suspend_one(ipa->name_map[IPA_ENDPOINT_AP_COMMAND_TX]);
 }
-- 
2.26.2


From d05738a952fde23d2dcd4408e367e1b7840a9b86 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Fri, 10 Jul 2020 16:41:38 +0300
Subject: [PATCH 30/44] mlxsw: spectrum_router: Remove inappropriate usage of
 WARN_ON()

[ Upstream commit d9d5420273997664a1c09151ca86ac993f2f89c1 ]

We should not trigger a warning when a memory allocation fails. Remove
the WARN_ON().

The warning is constantly triggered by syzkaller when it is injecting
faults:

[ 2230.758664] FAULT_INJECTION: forcing a failure.
[ 2230.758664] name failslab, interval 1, probability 0, space 0, times 0
[ 2230.762329] CPU: 3 PID: 1407 Comm: syz-executor.0 Not tainted 5.8.0-rc2+ #28
...
[ 2230.898175] WARNING: CPU: 3 PID: 1407 at drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:6265 mlxsw_sp_router_fib_event+0xfad/0x13e0
[ 2230.898179] Kernel panic - not syncing: panic_on_warn set ...
[ 2230.898183] CPU: 3 PID: 1407 Comm: syz-executor.0 Not tainted 5.8.0-rc2+ #28
[ 2230.898190] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014

Fixes: 3057224e014c ("mlxsw: spectrum_router: Implement FIB offload in deferred work")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index d5bca1be3ef5..84b3d78a9dd8 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -6256,7 +6256,7 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb,
 	}
 
 	fib_work = kzalloc(sizeof(*fib_work), GFP_ATOMIC);
-	if (WARN_ON(!fib_work))
+	if (!fib_work)
 		return NOTIFY_BAD;
 
 	fib_work->mlxsw_sp = router->mlxsw_sp;
-- 
2.26.2


From 14a069b7ac33f6dd39604217ba0e9a774ce3798c Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Fri, 10 Jul 2020 16:41:39 +0300
Subject: [PATCH 31/44] mlxsw: pci: Fix use-after-free in case of failed
 devlink reload

[ Upstream commit c4317b11675b99af6641662ebcbd3c6010600e64 ]

In case devlink reload failed, it is possible to trigger a
use-after-free when querying the kernel for device info via 'devlink dev
info' [1].

This happens because as part of the reload error path the PCI command
interface is de-initialized and its mailboxes are freed. When the
devlink '->info_get()' callback is invoked the device is queried via the
command interface and the freed mailboxes are accessed.

Fix this by initializing the command interface once during probe and not
during every reload.

This is consistent with the other bus used by mlxsw (i.e., 'mlxsw_i2c')
and also allows user space to query the running firmware version (for
example) from the device after a failed reload.

[1]
BUG: KASAN: use-after-free in memcpy include/linux/string.h:406 [inline]
BUG: KASAN: use-after-free in mlxsw_pci_cmd_exec+0x177/0xa60 drivers/net/ethernet/mellanox/mlxsw/pci.c:1675
Write of size 4096 at addr ffff88810ae32000 by task syz-executor.1/2355

CPU: 1 PID: 2355 Comm: syz-executor.1 Not tainted 5.8.0-rc2+ #29
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0xf6/0x16e lib/dump_stack.c:118
 print_address_description.constprop.0+0x1c/0x250 mm/kasan/report.c:383
 __kasan_report mm/kasan/report.c:513 [inline]
 kasan_report.cold+0x1f/0x37 mm/kasan/report.c:530
 check_memory_region_inline mm/kasan/generic.c:186 [inline]
 check_memory_region+0x14e/0x1b0 mm/kasan/generic.c:192
 memcpy+0x39/0x60 mm/kasan/common.c:106
 memcpy include/linux/string.h:406 [inline]
 mlxsw_pci_cmd_exec+0x177/0xa60 drivers/net/ethernet/mellanox/mlxsw/pci.c:1675
 mlxsw_cmd_exec+0x249/0x550 drivers/net/ethernet/mellanox/mlxsw/core.c:2335
 mlxsw_cmd_access_reg drivers/net/ethernet/mellanox/mlxsw/cmd.h:859 [inline]
 mlxsw_core_reg_access_cmd drivers/net/ethernet/mellanox/mlxsw/core.c:1938 [inline]
 mlxsw_core_reg_access+0x2f6/0x540 drivers/net/ethernet/mellanox/mlxsw/core.c:1985
 mlxsw_reg_query drivers/net/ethernet/mellanox/mlxsw/core.c:2000 [inline]
 mlxsw_devlink_info_get+0x17f/0x6e0 drivers/net/ethernet/mellanox/mlxsw/core.c:1090
 devlink_nl_info_fill.constprop.0+0x13c/0x2d0 net/core/devlink.c:4588
 devlink_nl_cmd_info_get_dumpit+0x246/0x460 net/core/devlink.c:4648
 genl_lock_dumpit+0x85/0xc0 net/netlink/genetlink.c:575
 netlink_dump+0x515/0xe50 net/netlink/af_netlink.c:2245
 __netlink_dump_start+0x53d/0x830 net/netlink/af_netlink.c:2353
 genl_family_rcv_msg_dumpit.isra.0+0x296/0x300 net/netlink/genetlink.c:638
 genl_family_rcv_msg net/netlink/genetlink.c:733 [inline]
 genl_rcv_msg+0x78d/0x9d0 net/netlink/genetlink.c:753
 netlink_rcv_skb+0x152/0x440 net/netlink/af_netlink.c:2469
 genl_rcv+0x24/0x40 net/netlink/genetlink.c:764
 netlink_unicast_kernel net/netlink/af_netlink.c:1303 [inline]
 netlink_unicast+0x53a/0x750 net/netlink/af_netlink.c:1329
 netlink_sendmsg+0x850/0xd90 net/netlink/af_netlink.c:1918
 sock_sendmsg_nosec net/socket.c:652 [inline]
 sock_sendmsg+0x150/0x190 net/socket.c:672
 ____sys_sendmsg+0x6d8/0x840 net/socket.c:2363
 ___sys_sendmsg+0xff/0x170 net/socket.c:2417
 __sys_sendmsg+0xe5/0x1b0 net/socket.c:2450
 do_syscall_64+0x56/0xa0 arch/x86/entry/common.c:359
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: a9c8336f6544 ("mlxsw: core: Add support for devlink info command")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/pci.c | 54 ++++++++++++++++-------
 1 file changed, 38 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index fd0e97de44e7..c04ec1a92826 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -1414,23 +1414,12 @@ static int mlxsw_pci_init(void *bus_priv, struct mlxsw_core *mlxsw_core,
 	u16 num_pages;
 	int err;
 
-	mutex_init(&mlxsw_pci->cmd.lock);
-	init_waitqueue_head(&mlxsw_pci->cmd.wait);
-
 	mlxsw_pci->core = mlxsw_core;
 
 	mbox = mlxsw_cmd_mbox_alloc();
 	if (!mbox)
 		return -ENOMEM;
 
-	err = mlxsw_pci_mbox_alloc(mlxsw_pci, &mlxsw_pci->cmd.in_mbox);
-	if (err)
-		goto mbox_put;
-
-	err = mlxsw_pci_mbox_alloc(mlxsw_pci, &mlxsw_pci->cmd.out_mbox);
-	if (err)
-		goto err_out_mbox_alloc;
-
 	err = mlxsw_pci_sw_reset(mlxsw_pci, mlxsw_pci->id);
 	if (err)
 		goto err_sw_reset;
@@ -1537,9 +1526,6 @@ static int mlxsw_pci_init(void *bus_priv, struct mlxsw_core *mlxsw_core,
 	mlxsw_pci_free_irq_vectors(mlxsw_pci);
 err_alloc_irq:
 err_sw_reset:
-	mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.out_mbox);
-err_out_mbox_alloc:
-	mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.in_mbox);
 mbox_put:
 	mlxsw_cmd_mbox_free(mbox);
 	return err;
@@ -1553,8 +1539,6 @@ static void mlxsw_pci_fini(void *bus_priv)
 	mlxsw_pci_aqs_fini(mlxsw_pci);
 	mlxsw_pci_fw_area_fini(mlxsw_pci);
 	mlxsw_pci_free_irq_vectors(mlxsw_pci);
-	mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.out_mbox);
-	mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.in_mbox);
 }
 
 static struct mlxsw_pci_queue *
@@ -1776,6 +1760,37 @@ static const struct mlxsw_bus mlxsw_pci_bus = {
 	.features		= MLXSW_BUS_F_TXRX | MLXSW_BUS_F_RESET,
 };
 
+static int mlxsw_pci_cmd_init(struct mlxsw_pci *mlxsw_pci)
+{
+	int err;
+
+	mutex_init(&mlxsw_pci->cmd.lock);
+	init_waitqueue_head(&mlxsw_pci->cmd.wait);
+
+	err = mlxsw_pci_mbox_alloc(mlxsw_pci, &mlxsw_pci->cmd.in_mbox);
+	if (err)
+		goto err_in_mbox_alloc;
+
+	err = mlxsw_pci_mbox_alloc(mlxsw_pci, &mlxsw_pci->cmd.out_mbox);
+	if (err)
+		goto err_out_mbox_alloc;
+
+	return 0;
+
+err_out_mbox_alloc:
+	mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.in_mbox);
+err_in_mbox_alloc:
+	mutex_destroy(&mlxsw_pci->cmd.lock);
+	return err;
+}
+
+static void mlxsw_pci_cmd_fini(struct mlxsw_pci *mlxsw_pci)
+{
+	mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.out_mbox);
+	mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.in_mbox);
+	mutex_destroy(&mlxsw_pci->cmd.lock);
+}
+
 static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	const char *driver_name = pdev->driver->name;
@@ -1831,6 +1846,10 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	mlxsw_pci->pdev = pdev;
 	pci_set_drvdata(pdev, mlxsw_pci);
 
+	err = mlxsw_pci_cmd_init(mlxsw_pci);
+	if (err)
+		goto err_pci_cmd_init;
+
 	mlxsw_pci->bus_info.device_kind = driver_name;
 	mlxsw_pci->bus_info.device_name = pci_name(mlxsw_pci->pdev);
 	mlxsw_pci->bus_info.dev = &pdev->dev;
@@ -1848,6 +1867,8 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	return 0;
 
 err_bus_device_register:
+	mlxsw_pci_cmd_fini(mlxsw_pci);
+err_pci_cmd_init:
 	iounmap(mlxsw_pci->hw_addr);
 err_ioremap:
 err_pci_resource_len_check:
@@ -1865,6 +1886,7 @@ static void mlxsw_pci_remove(struct pci_dev *pdev)
 	struct mlxsw_pci *mlxsw_pci = pci_get_drvdata(pdev);
 
 	mlxsw_core_bus_device_unregister(mlxsw_pci->core, false);
+	mlxsw_pci_cmd_fini(mlxsw_pci);
 	iounmap(mlxsw_pci->hw_addr);
 	pci_release_regions(mlxsw_pci->pdev);
 	pci_disable_device(mlxsw_pci->pdev);
-- 
2.26.2


From 147b0b8eb1bcaea620c67484bc892364c08eb298 Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Sun, 14 Jun 2020 17:31:26 +0300
Subject: [PATCH 32/44] net/mlx5: Fix eeprom support for SFP module

[ Upstream commit 47afbdd2fa4c5775c383ba376a3d1da7d7f694dc ]

Fix eeprom SFP query support by setting i2c_addr, offset and page number
correctly. Unlike QSFP modules, SFP eeprom params are as follow:
- i2c_addr is 0x50 for offset 0 - 255 and 0x51 for offset 256 - 511.
- Page number is always zero.
- Page offset is always relative to zero.

As part of eeprom query, query the module ID (SFP / QSFP*) via helper
function to set the params accordingly.

In addition, change mlx5_qsfp_eeprom_page() input type to be u16 to avoid
unnecessary casting.

Fixes: a708fb7b1f8d ("net/mlx5e: ethtool, Add support for EEPROM high pages query")
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/port.c    | 93 +++++++++++++++----
 1 file changed, 77 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index cc262b30aed5..dc589322940c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -293,7 +293,40 @@ static int mlx5_query_module_num(struct mlx5_core_dev *dev, int *module_num)
 	return 0;
 }
 
-static int mlx5_eeprom_page(int offset)
+static int mlx5_query_module_id(struct mlx5_core_dev *dev, int module_num,
+				u8 *module_id)
+{
+	u32 in[MLX5_ST_SZ_DW(mcia_reg)] = {};
+	u32 out[MLX5_ST_SZ_DW(mcia_reg)];
+	int err, status;
+	u8 *ptr;
+
+	MLX5_SET(mcia_reg, in, i2c_device_address, MLX5_I2C_ADDR_LOW);
+	MLX5_SET(mcia_reg, in, module, module_num);
+	MLX5_SET(mcia_reg, in, device_address, 0);
+	MLX5_SET(mcia_reg, in, page_number, 0);
+	MLX5_SET(mcia_reg, in, size, 1);
+	MLX5_SET(mcia_reg, in, l, 0);
+
+	err = mlx5_core_access_reg(dev, in, sizeof(in), out,
+				   sizeof(out), MLX5_REG_MCIA, 0, 0);
+	if (err)
+		return err;
+
+	status = MLX5_GET(mcia_reg, out, status);
+	if (status) {
+		mlx5_core_err(dev, "query_mcia_reg failed: status: 0x%x\n",
+			      status);
+		return -EIO;
+	}
+	ptr = MLX5_ADDR_OF(mcia_reg, out, dword_0);
+
+	*module_id = ptr[0];
+
+	return 0;
+}
+
+static int mlx5_qsfp_eeprom_page(u16 offset)
 {
 	if (offset < MLX5_EEPROM_PAGE_LENGTH)
 		/* Addresses between 0-255 - page 00 */
@@ -307,7 +340,7 @@ static int mlx5_eeprom_page(int offset)
 		    MLX5_EEPROM_HIGH_PAGE_LENGTH);
 }
 
-static int mlx5_eeprom_high_page_offset(int page_num)
+static int mlx5_qsfp_eeprom_high_page_offset(int page_num)
 {
 	if (!page_num) /* Page 0 always start from low page */
 		return 0;
@@ -316,35 +349,62 @@ static int mlx5_eeprom_high_page_offset(int page_num)
 	return page_num * MLX5_EEPROM_HIGH_PAGE_LENGTH;
 }
 
+static void mlx5_qsfp_eeprom_params_set(u16 *i2c_addr, int *page_num, u16 *offset)
+{
+	*i2c_addr = MLX5_I2C_ADDR_LOW;
+	*page_num = mlx5_qsfp_eeprom_page(*offset);
+	*offset -=  mlx5_qsfp_eeprom_high_page_offset(*page_num);
+}
+
+static void mlx5_sfp_eeprom_params_set(u16 *i2c_addr, int *page_num, u16 *offset)
+{
+	*i2c_addr = MLX5_I2C_ADDR_LOW;
+	*page_num = 0;
+
+	if (*offset < MLX5_EEPROM_PAGE_LENGTH)
+		return;
+
+	*i2c_addr = MLX5_I2C_ADDR_HIGH;
+	*offset -= MLX5_EEPROM_PAGE_LENGTH;
+}
+
 int mlx5_query_module_eeprom(struct mlx5_core_dev *dev,
 			     u16 offset, u16 size, u8 *data)
 {
-	int module_num, page_num, status, err;
+	int module_num, status, err, page_num = 0;
+	u32 in[MLX5_ST_SZ_DW(mcia_reg)] = {};
 	u32 out[MLX5_ST_SZ_DW(mcia_reg)];
-	u32 in[MLX5_ST_SZ_DW(mcia_reg)];
-	u16 i2c_addr;
-	void *ptr = MLX5_ADDR_OF(mcia_reg, out, dword_0);
+	u16 i2c_addr = 0;
+	u8 module_id;
+	void *ptr;
 
 	err = mlx5_query_module_num(dev, &module_num);
 	if (err)
 		return err;
 
-	memset(in, 0, sizeof(in));
-	size = min_t(int, size, MLX5_EEPROM_MAX_BYTES);
-
-	/* Get the page number related to the given offset */
-	page_num = mlx5_eeprom_page(offset);
+	err = mlx5_query_module_id(dev, module_num, &module_id);
+	if (err)
+		return err;
 
-	/* Set the right offset according to the page number,
-	 * For page_num > 0, relative offset is always >= 128 (high page).
-	 */
-	offset -= mlx5_eeprom_high_page_offset(page_num);
+	switch (module_id) {
+	case MLX5_MODULE_ID_SFP:
+		mlx5_sfp_eeprom_params_set(&i2c_addr, &page_num, &offset);
+		break;
+	case MLX5_MODULE_ID_QSFP:
+	case MLX5_MODULE_ID_QSFP_PLUS:
+	case MLX5_MODULE_ID_QSFP28:
+		mlx5_qsfp_eeprom_params_set(&i2c_addr, &page_num, &offset);
+		break;
+	default:
+		mlx5_core_err(dev, "Module ID not recognized: 0x%x\n", module_id);
+		return -EINVAL;
+	}
 
 	if (offset + size > MLX5_EEPROM_PAGE_LENGTH)
 		/* Cross pages read, read until offset 256 in low page */
 		size -= offset + size - MLX5_EEPROM_PAGE_LENGTH;
 
-	i2c_addr = MLX5_I2C_ADDR_LOW;
+	size = min_t(int, size, MLX5_EEPROM_MAX_BYTES);
 
 	MLX5_SET(mcia_reg, in, l, 0);
 	MLX5_SET(mcia_reg, in, module, module_num);
@@ -365,6 +425,7 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev,
 		return -EIO;
 	}
 
+	ptr = MLX5_ADDR_OF(mcia_reg, out, dword_0);
 	memcpy(data, ptr, size);
 
 	return size;
-- 
2.26.2


From 7b3ed72857c6d918a50b140f819fedab50885630 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 1 Jul 2020 16:00:06 -0400
Subject: [PATCH 33/44] ip: Fix SO_MARK in RST, ACK and ICMP packets

[ Upstream commit 0da7536fb47f51df89ccfcb1fa09f249d9accec5 ]

When no full socket is available, skbs are sent over a per-netns
control socket. Its sk_mark is temporarily adjusted to match that
of the real (request or timewait) socket or to reflect an incoming
skb, so that the outgoing skb inherits this in __ip_make_skb.

Introduction of the socket cookie mark field broke this. Now the
skb is set through the cookie and cork:

<caller>		# init sockc.mark from sk_mark or cmsg
ip_append_data
  ip_setup_cork		# convert sockc.mark to cork mark
ip_push_pending_frames
  ip_finish_skb
    __ip_make_skb	# set skb->mark to cork mark

But I missed these special control sockets. Update all callers of
__ip(6)_make_skb that were originally missed.

For IPv6, the same two icmp(v6) paths are affected. The third
case is not, as commit 92e55f412cff ("tcp: don't annotate
mark on control socket from tcp_v6_send_response()") replaced
the ctl_sk->sk_mark with passing the mark field directly as a
function argument. That commit predates the commit that
introduced the bug.

Fixes: c6af0c227a22 ("ip: support SO_MARK cmsg")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Reported-by: Martin KaFai Lau <kafai@fb.com>
Reviewed-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/icmp.c      | 4 ++--
 net/ipv4/ip_output.c | 2 +-
 net/ipv6/icmp.c      | 4 ++--
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index fc61f51d87a3..ca591051c656 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -427,7 +427,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 
 	ipcm_init(&ipc);
 	inet->tos = ip_hdr(skb)->tos;
-	sk->sk_mark = mark;
+	ipc.sockc.mark = mark;
 	daddr = ipc.addr = ip_hdr(skb)->saddr;
 	saddr = fib_compute_spec_dst(skb);
 
@@ -710,10 +710,10 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
 	icmp_param.skb	  = skb_in;
 	icmp_param.offset = skb_network_offset(skb_in);
 	inet_sk(sk)->tos = tos;
-	sk->sk_mark = mark;
 	ipcm_init(&ipc);
 	ipc.addr = iph->saddr;
 	ipc.opt = &icmp_param.replyopts.opt;
+	ipc.sockc.mark = mark;
 
 	rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, mark,
 			       type, code, &icmp_param);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 090d3097ee15..17206677d503 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1702,7 +1702,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 	sk->sk_protocol = ip_hdr(skb)->protocol;
 	sk->sk_bound_dev_if = arg->bound_dev_if;
 	sk->sk_sndbuf = sysctl_wmem_default;
-	sk->sk_mark = fl4.flowi4_mark;
+	ipc.sockc.mark = fl4.flowi4_mark;
 	err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base,
 			     len, 0, &ipc, &rt, MSG_DONTWAIT);
 	if (unlikely(err)) {
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index fc5000370030..9df8737ae0d3 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -566,7 +566,6 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 	fl6.mp_hash = rt6_multipath_hash(net, &fl6, skb, NULL);
 	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
 
-	sk->sk_mark = mark;
 	np = inet6_sk(sk);
 
 	if (!icmpv6_xrlim_allow(sk, type, &fl6))
@@ -583,6 +582,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 		fl6.flowi6_oif = np->ucast_oif;
 
 	ipcm6_init_sk(&ipc6, np);
+	ipc6.sockc.mark = mark;
 	fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
 
 	dst = icmpv6_route_lookup(net, skb, sk, &fl6);
@@ -751,7 +751,6 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	sk = icmpv6_xmit_lock(net);
 	if (!sk)
 		goto out_bh_enable;
-	sk->sk_mark = mark;
 	np = inet6_sk(sk);
 
 	if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
@@ -779,6 +778,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	ipcm6_init_sk(&ipc6, np);
 	ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
 	ipc6.tclass = ipv6_get_dsfield(ipv6_hdr(skb));
+	ipc6.sockc.mark = mark;
 
 	if (ip6_append_data(sk, icmpv6_getfrag, &msg,
 			    skb->len + sizeof(struct icmp6hdr),
-- 
2.26.2


From c2b7bbf091d61c07faff341fed85a5d0c114864e Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Mon, 15 Jun 2020 12:48:47 +0300
Subject: [PATCH 34/44] net/mlx5e: Fix 50G per lane indication

[ Upstream commit 6a1cf4e443a3b0a4d690d3c93b84b1e9cbfcb1bd ]

Some released FW versions mistakenly don't set the capability that 50G
per lane link-modes are supported for VFs (ptys_extended_ethernet
capability bit). When the capability is unset, read
PTYS.ext_eth_proto_capability (always reliable).
If PTYS.ext_eth_proto_capability is valid (has a non-zero value)
conclude that the HCA supports 50G per lane. Otherwise, conclude that
the HCA doesn't support 50G per lane.

Fixes: a08b4ed1373d ("net/mlx5: Add support to ext_* fields introduced in Port Type and Speed register")
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en/port.c | 21 ++++++++++++++++---
 .../net/ethernet/mellanox/mlx5/core/en/port.h |  2 +-
 .../ethernet/mellanox/mlx5/core/en_ethtool.c  |  8 +++----
 3 files changed, 23 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
index 2a8950b3056f..3cf3e35053f7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
@@ -78,11 +78,26 @@ static const u32 mlx5e_ext_link_speed[MLX5E_EXT_LINK_MODES_NUMBER] = {
 	[MLX5E_400GAUI_8]			= 400000,
 };
 
+bool mlx5e_ptys_ext_supported(struct mlx5_core_dev *mdev)
+{
+	struct mlx5e_port_eth_proto eproto;
+	int err;
+
+	if (MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet))
+		return true;
+
+	err = mlx5_port_query_eth_proto(mdev, 1, true, &eproto);
+	if (err)
+		return false;
+
+	return !!eproto.cap;
+}
+
 static void mlx5e_port_get_speed_arr(struct mlx5_core_dev *mdev,
 				     const u32 **arr, u32 *size,
 				     bool force_legacy)
 {
-	bool ext = force_legacy ? false : MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+	bool ext = force_legacy ? false : mlx5e_ptys_ext_supported(mdev);
 
 	*size = ext ? ARRAY_SIZE(mlx5e_ext_link_speed) :
 		      ARRAY_SIZE(mlx5e_link_speed);
@@ -177,7 +192,7 @@ int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
 	bool ext;
 	int err;
 
-	ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+	ext = mlx5e_ptys_ext_supported(mdev);
 	err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto);
 	if (err)
 		goto out;
@@ -205,7 +220,7 @@ int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
 	int err;
 	int i;
 
-	ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+	ext = mlx5e_ptys_ext_supported(mdev);
 	err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto);
 	if (err)
 		return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
index a2ddd446dd59..7a7defe60792 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
@@ -54,7 +54,7 @@ int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
 int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
 u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed,
 			       bool force_legacy);
-
+bool mlx5e_ptys_ext_supported(struct mlx5_core_dev *mdev);
 int mlx5e_port_query_pbmc(struct mlx5_core_dev *mdev, void *out);
 int mlx5e_port_set_pbmc(struct mlx5_core_dev *mdev, void *in);
 int mlx5e_port_query_priority2buffer(struct mlx5_core_dev *mdev, u8 *buffer);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index bc290ae80a53..1c491acd48f3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -200,7 +200,7 @@ static void mlx5e_ethtool_get_speed_arr(struct mlx5_core_dev *mdev,
 					struct ptys2ethtool_config **arr,
 					u32 *size)
 {
-	bool ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+	bool ext = mlx5e_ptys_ext_supported(mdev);
 
 	*arr = ext ? ptys2ext_ethtool_table : ptys2legacy_ethtool_table;
 	*size = ext ? ARRAY_SIZE(ptys2ext_ethtool_table) :
@@ -883,7 +883,7 @@ static void get_lp_advertising(struct mlx5_core_dev *mdev, u32 eth_proto_lp,
 			       struct ethtool_link_ksettings *link_ksettings)
 {
 	unsigned long *lp_advertising = link_ksettings->link_modes.lp_advertising;
-	bool ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+	bool ext = mlx5e_ptys_ext_supported(mdev);
 
 	ptys2ethtool_adver_link(lp_advertising, eth_proto_lp, ext);
 }
@@ -913,7 +913,7 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv,
 			   __func__, err);
 		goto err_query_regs;
 	}
-	ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+	ext = !!MLX5_GET_ETH_PROTO(ptys_reg, out, true, eth_proto_capability);
 	eth_proto_cap    = MLX5_GET_ETH_PROTO(ptys_reg, out, ext,
 					      eth_proto_capability);
 	eth_proto_admin  = MLX5_GET_ETH_PROTO(ptys_reg, out, ext,
@@ -1066,7 +1066,7 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 	autoneg = link_ksettings->base.autoneg;
 	speed = link_ksettings->base.speed;
 
-	ext_supported = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+	ext_supported = mlx5e_ptys_ext_supported(mdev);
 	ext = ext_requested(autoneg, adver, ext_supported);
 	if (!ext_supported && ext)
 		return -EOPNOTSUPP;
-- 
2.26.2


From e3e4129eb8eb867cb54324f793bfa5a9c5f73d77 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sat, 27 Jun 2020 00:12:24 -0700
Subject: [PATCH 35/44] genetlink: get rid of family->attrbuf

[ Upstream commit bf64ff4c2aac65d680dc639a511c781cf6b6ec08 ]

genl_family_rcv_msg_attrs_parse() reuses the global family->attrbuf
when family->parallel_ops is false. However, family->attrbuf is not
protected by any lock on the genl_family_rcv_msg_doit() code path.

This leads to several different consequences, one of them is UAF,
like the following:

genl_family_rcv_msg_doit():		genl_start():
					  genl_family_rcv_msg_attrs_parse()
					    attrbuf = family->attrbuf
					    __nlmsg_parse(attrbuf);
  genl_family_rcv_msg_attrs_parse()
    attrbuf = family->attrbuf
    __nlmsg_parse(attrbuf);
					  info->attrs = attrs;
					  cb->data = info;

netlink_unicast_kernel():
 consume_skb()
					genl_lock_dumpit():
					  genl_dumpit_info(cb)->attrs

Note family->attrbuf is an array of pointers to the skb data, once
the skb is freed, any dereference of family->attrbuf will be a UAF.

Maybe we could serialize the family->attrbuf with genl_mutex too, but
that would make the locking more complicated. Instead, we can just get
rid of family->attrbuf and always allocate attrbuf from heap like the
family->parallel_ops==true code path. This may add some performance
overhead but comparing with taking the global genl_mutex, it still
looks better.

Fixes: 75cdbdd08900 ("net: ieee802154: have genetlink code to parse the attrs during dumpit")
Fixes: 057af7071344 ("net: tipc: have genetlink code to parse the attrs during dumpit")
Reported-and-tested-by: syzbot+3039ddf6d7b13daf3787@syzkaller.appspotmail.com
Reported-and-tested-by: syzbot+80cad1e3cb4c41cde6ff@syzkaller.appspotmail.com
Reported-and-tested-by: syzbot+736bcbcb11b60d0c0792@syzkaller.appspotmail.com
Reported-and-tested-by: syzbot+520f8704db2b68091d44@syzkaller.appspotmail.com
Reported-and-tested-by: syzbot+c96e4dfb32f8987fdeed@syzkaller.appspotmail.com
Cc: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/genetlink.h |  2 --
 net/netlink/genetlink.c | 48 +++++++++++------------------------------
 2 files changed, 13 insertions(+), 37 deletions(-)

diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 4cf703d8c30e..6e5f1e1aa822 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -35,7 +35,6 @@ struct genl_info;
  *	do additional, common, filtering and return an error
  * @post_doit: called after an operation's doit callback, it may
  *	undo operations done by pre_doit, for example release locks
- * @attrbuf: buffer to store parsed attributes (private)
  * @mcgrps: multicast groups used by this family
  * @n_mcgrps: number of multicast groups
  * @mcgrp_offset: starting number of multicast group IDs in this family
@@ -58,7 +57,6 @@ struct genl_family {
 	void			(*post_doit)(const struct genl_ops *ops,
 					     struct sk_buff *skb,
 					     struct genl_info *info);
-	struct nlattr **	attrbuf;	/* private */
 	const struct genl_ops *	ops;
 	const struct genl_multicast_group *mcgrps;
 	unsigned int		n_ops;
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index f374a4038c03..cfcc518d77c0 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -351,22 +351,11 @@ int genl_register_family(struct genl_family *family)
 		start = end = GENL_ID_VFS_DQUOT;
 	}
 
-	if (family->maxattr && !family->parallel_ops) {
-		family->attrbuf = kmalloc_array(family->maxattr + 1,
-						sizeof(struct nlattr *),
-						GFP_KERNEL);
-		if (family->attrbuf == NULL) {
-			err = -ENOMEM;
-			goto errout_locked;
-		}
-	} else
-		family->attrbuf = NULL;
-
 	family->id = idr_alloc_cyclic(&genl_fam_idr, family,
 				      start, end + 1, GFP_KERNEL);
 	if (family->id < 0) {
 		err = family->id;
-		goto errout_free;
+		goto errout_locked;
 	}
 
 	err = genl_validate_assign_mc_groups(family);
@@ -385,8 +374,6 @@ int genl_register_family(struct genl_family *family)
 
 errout_remove:
 	idr_remove(&genl_fam_idr, family->id);
-errout_free:
-	kfree(family->attrbuf);
 errout_locked:
 	genl_unlock_all();
 	return err;
@@ -419,8 +406,6 @@ int genl_unregister_family(const struct genl_family *family)
 		   atomic_read(&genl_sk_destructing_cnt) == 0);
 	genl_unlock();
 
-	kfree(family->attrbuf);
-
 	genl_ctrl_event(CTRL_CMD_DELFAMILY, family, NULL, 0);
 
 	return 0;
@@ -485,30 +470,23 @@ genl_family_rcv_msg_attrs_parse(const struct genl_family *family,
 	if (!family->maxattr)
 		return NULL;
 
-	if (family->parallel_ops) {
-		attrbuf = kmalloc_array(family->maxattr + 1,
-					sizeof(struct nlattr *), GFP_KERNEL);
-		if (!attrbuf)
-			return ERR_PTR(-ENOMEM);
-	} else {
-		attrbuf = family->attrbuf;
-	}
+	attrbuf = kmalloc_array(family->maxattr + 1,
+				sizeof(struct nlattr *), GFP_KERNEL);
+	if (!attrbuf)
+		return ERR_PTR(-ENOMEM);
 
 	err = __nlmsg_parse(nlh, hdrlen, attrbuf, family->maxattr,
 			    family->policy, validate, extack);
 	if (err) {
-		if (family->parallel_ops)
-			kfree(attrbuf);
+		kfree(attrbuf);
 		return ERR_PTR(err);
 	}
 	return attrbuf;
 }
 
-static void genl_family_rcv_msg_attrs_free(const struct genl_family *family,
-					   struct nlattr **attrbuf)
+static void genl_family_rcv_msg_attrs_free(struct nlattr **attrbuf)
 {
-	if (family->parallel_ops)
-		kfree(attrbuf);
+	kfree(attrbuf);
 }
 
 struct genl_start_context {
@@ -542,7 +520,7 @@ static int genl_start(struct netlink_callback *cb)
 no_attrs:
 	info = genl_dumpit_info_alloc();
 	if (!info) {
-		genl_family_rcv_msg_attrs_free(ctx->family, attrs);
+		genl_family_rcv_msg_attrs_free(attrs);
 		return -ENOMEM;
 	}
 	info->family = ctx->family;
@@ -559,7 +537,7 @@ static int genl_start(struct netlink_callback *cb)
 	}
 
 	if (rc) {
-		genl_family_rcv_msg_attrs_free(info->family, info->attrs);
+		genl_family_rcv_msg_attrs_free(info->attrs);
 		genl_dumpit_info_free(info);
 		cb->data = NULL;
 	}
@@ -588,7 +566,7 @@ static int genl_lock_done(struct netlink_callback *cb)
 		rc = ops->done(cb);
 		genl_unlock();
 	}
-	genl_family_rcv_msg_attrs_free(info->family, info->attrs);
+	genl_family_rcv_msg_attrs_free(info->attrs);
 	genl_dumpit_info_free(info);
 	return rc;
 }
@@ -601,7 +579,7 @@ static int genl_parallel_done(struct netlink_callback *cb)
 
 	if (ops->done)
 		rc = ops->done(cb);
-	genl_family_rcv_msg_attrs_free(info->family, info->attrs);
+	genl_family_rcv_msg_attrs_free(info->attrs);
 	genl_dumpit_info_free(info);
 	return rc;
 }
@@ -694,7 +672,7 @@ static int genl_family_rcv_msg_doit(const struct genl_family *family,
 		family->post_doit(ops, skb, &info);
 
 out:
-	genl_family_rcv_msg_attrs_free(family, attrbuf);
+	genl_family_rcv_msg_attrs_free(attrbuf);
 
 	return err;
 }
-- 
2.26.2


From 534584eb5427bfe811326c0f7e2a8caf19a1c016 Mon Sep 17 00:00:00 2001
From: Miaohe Lin <linmiaohe@huawei.com>
Date: Sat, 27 Jun 2020 15:47:51 +0800
Subject: [PATCH 36/44] net: ipv4: Fix wrong type conversion from hint to rt in
 ip_route_use_hint()

[ Upstream commit 2ce578ca9444bb44da66b9a494f56e7ec12e6466 ]

We can't cast sk_buff to rtable by (struct rtable *)hint. Use skb_rtable().

Fixes: 02b24941619f ("ipv4: use dst hint for ipv4 list receive")
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index b73f540fa19b..abe12caf2451 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2027,7 +2027,7 @@ int ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 		      const struct sk_buff *hint)
 {
 	struct in_device *in_dev = __in_dev_get_rcu(dev);
-	struct rtable *rt = (struct rtable *)hint;
+	struct rtable *rt = skb_rtable(hint);
 	struct net *net = dev_net(dev);
 	int err = -EINVAL;
 	u32 tag = 0;
-- 
2.26.2


From 87bc9333fed658ba6c2e9edbcd1520a9b5215ba9 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Wed, 24 Jun 2020 19:04:03 +0300
Subject: [PATCH 37/44] net/mlx5e: Fix VXLAN configuration restore after
 function reload

[ Upstream commit b3c2ed21c0bdf35ba498a9974aa587f99a03b658 ]

When detaching netdev, remove vxlan port configuration using
udp_tunnel_drop_rx_info. During function reload, configuration will be
restored using udp_tunnel_get_rx_info. This ensures sync between
firmware and driver. Use udp_tunnel_get_rx_info even if its physical
interface is down.

Fixes: 4383cfcc65e7 ("net/mlx5: Add devlink reload")
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index bd8d0e096085..02f6b6bd2847 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3076,9 +3076,6 @@ int mlx5e_open(struct net_device *netdev)
 		mlx5_set_port_admin_status(priv->mdev, MLX5_PORT_UP);
 	mutex_unlock(&priv->state_lock);
 
-	if (mlx5_vxlan_allowed(priv->mdev->vxlan))
-		udp_tunnel_get_rx_info(netdev);
-
 	return err;
 }
 
@@ -5207,6 +5204,8 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 	rtnl_lock();
 	if (netif_running(netdev))
 		mlx5e_open(netdev);
+	if (mlx5_vxlan_allowed(priv->mdev->vxlan))
+		udp_tunnel_get_rx_info(netdev);
 	netif_device_attach(netdev);
 	rtnl_unlock();
 }
@@ -5223,6 +5222,8 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv)
 	rtnl_lock();
 	if (netif_running(priv->netdev))
 		mlx5e_close(priv->netdev);
+	if (mlx5_vxlan_allowed(priv->mdev->vxlan))
+		udp_tunnel_drop_rx_info(priv->netdev);
 	netif_device_detach(priv->netdev);
 	rtnl_unlock();
 
-- 
2.26.2


From 73752356db0c2db18e6df667dec13754da26d03e Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Wed, 20 May 2020 10:37:42 +0300
Subject: [PATCH 38/44] net/mlx5e: Fix CPU mapping after function reload to
 avoid aRFS RX crash

[ Upstream commit f4aebbfb56ed0c186adbeb2799df836da50f78e3 ]

After function reload, CPU mapping used by aRFS RX is broken, leading to
a kernel panic. Fix by moving initialization of rx_cpu_rmap from
netdev_init to netdev_attach. IRQ table is re-allocated on mlx5_load,
but netdev is not re-initialize.

Trace of the panic:
[ 22.055672] general protection fault, probably for non-canonical address 0x785634120000ff1c: 0000 [#1] SMP PTI
[ 22.065010] CPU: 4 PID: 0 Comm: swapper/4 Not tainted 5.7.0-rc2-for-upstream-perf-2020-04-21_16-34-03-31 #1
[ 22.067967] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014
[ 22.071174] RIP: 0010:get_rps_cpu+0x267/0x300
[ 22.075692] RSP: 0018:ffffc90000244d60 EFLAGS: 00010202
[ 22.076888] RAX: ffff888459b0e400 RBX: 0000000000000000 RCX:0000000000000007
[ 22.078364] RDX: 0000000000008884 RSI: ffff888467cb5b00 RDI:0000000000000000
[ 22.079815] RBP: 00000000ff342b27 R08: 0000000000000007 R09:0000000000000003
[ 22.081289] R10: ffffffffffffffff R11: 00000000000070cc R12:ffff888454900000
[ 22.082767] R13: ffffc90000e5a950 R14: ffffc90000244dc0 R15:0000000000000007
[ 22.084190] FS: 0000000000000000(0000) GS:ffff88846fc80000(0000)knlGS:0000000000000000
[ 22.086161] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 22.087427] CR2: ffffffffffffffff CR3: 0000000464426003 CR4:0000000000760ee0
[ 22.088888] DR0: 0000000000000000 DR1: 0000000000000000 DR2:0000000000000000
[ 22.090336] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7:0000000000000400
[ 22.091764] PKRU: 55555554
[ 22.092618] Call Trace:
[ 22.093442] <IRQ>
[ 22.094211] ? kvm_clock_get_cycles+0xd/0x10
[ 22.095272] netif_receive_skb_list_internal+0x258/0x2a0
[ 22.096460] gro_normal_list.part.137+0x19/0x40
[ 22.097547] napi_complete_done+0xc6/0x110
[ 22.098685] mlx5e_napi_poll+0x190/0x670 [mlx5_core]
[ 22.099859] net_rx_action+0x2a0/0x400
[ 22.100848] __do_softirq+0xd8/0x2a8
[ 22.101829] irq_exit+0xa5/0xb0
[ 22.102750] do_IRQ+0x52/0xd0
[ 22.103654] common_interrupt+0xf/0xf
[ 22.104641] </IRQ>

Fixes: 4383cfcc65e7 ("net/mlx5: Add devlink reload")
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 02f6b6bd2847..bc54913c5861 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -5119,6 +5119,10 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv)
 	if (err)
 		goto err_destroy_flow_steering;
 
+#ifdef CONFIG_MLX5_EN_ARFS
+	priv->netdev->rx_cpu_rmap =  mlx5_eq_table_get_rmap(priv->mdev);
+#endif
+
 	return 0;
 
 err_destroy_flow_steering:
@@ -5296,10 +5300,6 @@ int mlx5e_netdev_init(struct net_device *netdev,
 	/* netdev init */
 	netif_carrier_off(netdev);
 
-#ifdef CONFIG_MLX5_EN_ARFS
-	netdev->rx_cpu_rmap =  mlx5_eq_table_get_rmap(mdev);
-#endif
-
 	return 0;
 
 err_free_cpumask:
-- 
2.26.2


From 42b6cf4bc9e191a6fd78f207ae4b5cd9ec8401b1 Mon Sep 17 00:00:00 2001
From: Michal Kubecek <mkubecek@suse.cz>
Date: Thu, 9 Jul 2020 12:11:50 +0200
Subject: [PATCH 39/44] ethtool: fix genlmsg_put() failure handling in
 ethnl_default_dumpit()

[ Upstream commit 365f9ae4ee36037e2a9268fe7296065356840b4c ]

If the genlmsg_put() call in ethnl_default_dumpit() fails, we bail out
without checking if we already have some messages in current skb like we do
with ethnl_default_dump_one() failure later. Therefore if existing messages
almost fill up the buffer so that there is not enough space even for
netlink and genetlink header, we lose all prepared messages and return and
error.

Rather than duplicating the skb->len check, move the genlmsg_put(),
genlmsg_cancel() and genlmsg_end() calls into ethnl_default_dump_one().
This is also more logical as all message composition will be in
ethnl_default_dump_one() and only iteration logic will be left in
ethnl_default_dumpit().

Fixes: 728480f12442 ("ethtool: default handlers for GET requests")
Reported-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ethtool/netlink.c | 27 +++++++++++++--------------
 1 file changed, 13 insertions(+), 14 deletions(-)

diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index ed5357210193..0f4e2e106799 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -376,10 +376,17 @@ static int ethnl_default_doit(struct sk_buff *skb, struct genl_info *info)
 }
 
 static int ethnl_default_dump_one(struct sk_buff *skb, struct net_device *dev,
-				  const struct ethnl_dump_ctx *ctx)
+				  const struct ethnl_dump_ctx *ctx,
+				  struct netlink_callback *cb)
 {
+	void *ehdr;
 	int ret;
 
+	ehdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+			   &ethtool_genl_family, 0, ctx->ops->reply_cmd);
+	if (!ehdr)
+		return -EMSGSIZE;
+
 	ethnl_init_reply_data(ctx->reply_data, ctx->ops, dev);
 	rtnl_lock();
 	ret = ctx->ops->prepare_data(ctx->req_info, ctx->reply_data, NULL);
@@ -395,6 +402,10 @@ static int ethnl_default_dump_one(struct sk_buff *skb, struct net_device *dev,
 	if (ctx->ops->cleanup_data)
 		ctx->ops->cleanup_data(ctx->reply_data);
 	ctx->reply_data->dev = NULL;
+	if (ret < 0)
+		genlmsg_cancel(skb, ehdr);
+	else
+		genlmsg_end(skb, ehdr);
 	return ret;
 }
 
@@ -411,7 +422,6 @@ static int ethnl_default_dumpit(struct sk_buff *skb,
 	int s_idx = ctx->pos_idx;
 	int h, idx = 0;
 	int ret = 0;
-	void *ehdr;
 
 	rtnl_lock();
 	for (h = ctx->pos_hash; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
@@ -431,26 +441,15 @@ static int ethnl_default_dumpit(struct sk_buff *skb,
 			dev_hold(dev);
 			rtnl_unlock();
 
-			ehdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid,
-					   cb->nlh->nlmsg_seq,
-					   &ethtool_genl_family, 0,
-					   ctx->ops->reply_cmd);
-			if (!ehdr) {
-				dev_put(dev);
-				ret = -EMSGSIZE;
-				goto out;
-			}
-			ret = ethnl_default_dump_one(skb, dev, ctx);
+			ret = ethnl_default_dump_one(skb, dev, ctx, cb);
 			dev_put(dev);
 			if (ret < 0) {
-				genlmsg_cancel(skb, ehdr);
 				if (ret == -EOPNOTSUPP)
 					goto lock_and_cont;
 				if (likely(skb->len))
 					ret = skb->len;
 				goto out;
 			}
-			genlmsg_end(skb, ehdr);
 lock_and_cont:
 			rtnl_lock();
 			if (net->dev_base_seq != seq) {
-- 
2.26.2


From 2f732553da933f7ad30a79b09ba2de7ca64cc6ed Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 3 Jul 2020 18:06:04 +0200
Subject: [PATCH 40/44] mptcp: fix DSS map generation on fin retransmission

[ Upstream commit 9c29e36152748fd623fcff6cc8f538550f9eeafc ]

The RFC 8684 mandates that no-data DATA FIN packets should carry
a DSS with 0 sequence number and data len equal to 1. Currently,
on FIN retransmission we re-use the existing mapping; if the previous
fin transmission was part of a partially acked data packet, we could
end-up writing in the egress packet a non-compliant DSS.

The above will be detected by a "Bad mapping" warning on the receiver
side.

This change addresses the issue explicitly checking for 0 len packet
when adding the DATA_FIN option.

Fixes: 6d0060f600ad ("mptcp: Write MPTCP DSS headers to outgoing data packets")
Reported-by: syzbot+42a07faa5923cfaeb9c9@syzkaller.appspotmail.com
Tested-by: Christoph Paasch <cpaasch@apple.com>
Reviewed-by: Christoph Paasch <cpaasch@apple.com>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/options.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 2430bbfa3405..2b3ed0c5199d 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -449,9 +449,9 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb,
 }
 
 static void mptcp_write_data_fin(struct mptcp_subflow_context *subflow,
-				 struct mptcp_ext *ext)
+				 struct sk_buff *skb, struct mptcp_ext *ext)
 {
-	if (!ext->use_map) {
+	if (!ext->use_map || !skb->len) {
 		/* RFC6824 requires a DSS mapping with specific values
 		 * if DATA_FIN is set but no data payload is mapped
 		 */
@@ -503,7 +503,7 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
 			opts->ext_copy = *mpext;
 
 		if (skb && tcp_fin && subflow->data_fin_tx_enable)
-			mptcp_write_data_fin(subflow, &opts->ext_copy);
+			mptcp_write_data_fin(subflow, skb, &opts->ext_copy);
 		ret = true;
 	}
 
-- 
2.26.2


From a46f7b7761350761fbe6dd1987cc9388a2389949 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Thu, 2 Jul 2020 17:08:18 +0000
Subject: [PATCH 41/44] net: rmnet: fix lower interface leak

[ Upstream commit 2a762e9e8cd1cf1242e4269a2244666ed02eecd1 ]

There are two types of the lower interface of rmnet that are VND
and BRIDGE.
Each lower interface can have only one type either VND or BRIDGE.
But, there is a case, which uses both lower interface types.
Due to this unexpected behavior, lower interface leak occurs.

Test commands:
    ip link add dummy0 type dummy
    ip link add dummy1 type dummy
    ip link add rmnet0 link dummy0 type rmnet mux_id 1
    ip link set dummy1 master rmnet0
    ip link add rmnet1 link dummy1 type rmnet mux_id 2
    ip link del rmnet0

The dummy1 was attached as BRIDGE interface of rmnet0.
Then, it also was attached as VND interface of rmnet1.
This is unexpected behavior and there is no code for handling this case.
So that below splat occurs when the rmnet0 interface is deleted.

Splat looks like:
[   53.254112][    C1] WARNING: CPU: 1 PID: 1192 at net/core/dev.c:8992 rollback_registered_many+0x986/0xcf0
[   53.254117][    C1] Modules linked in: rmnet dummy openvswitch nsh nf_conncount nf_nat nf_conntrack nf_defrag_ipv6 nfx
[   53.254182][    C1] CPU: 1 PID: 1192 Comm: ip Not tainted 5.8.0-rc1+ #620
[   53.254188][    C1] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[   53.254192][    C1] RIP: 0010:rollback_registered_many+0x986/0xcf0
[   53.254200][    C1] Code: 41 8b 4e cc 45 31 c0 31 d2 4c 89 ee 48 89 df e8 e0 47 ff ff 85 c0 0f 84 cd fc ff ff 0f 0b e5
[   53.254205][    C1] RSP: 0018:ffff888050a5f2e0 EFLAGS: 00010287
[   53.254214][    C1] RAX: ffff88805756d658 RBX: ffff88804d99c000 RCX: ffffffff8329d323
[   53.254219][    C1] RDX: 1ffffffff0be6410 RSI: 0000000000000008 RDI: ffffffff85f32080
[   53.254223][    C1] RBP: dffffc0000000000 R08: fffffbfff0be6411 R09: fffffbfff0be6411
[   53.254228][    C1] R10: ffffffff85f32087 R11: 0000000000000001 R12: ffff888050a5f480
[   53.254233][    C1] R13: ffff88804d99c0b8 R14: ffff888050a5f400 R15: ffff8880548ebe40
[   53.254238][    C1] FS:  00007f6b86b370c0(0000) GS:ffff88806c200000(0000) knlGS:0000000000000000
[   53.254243][    C1] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   53.254248][    C1] CR2: 0000562c62438758 CR3: 000000003f600005 CR4: 00000000000606e0
[   53.254253][    C1] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[   53.254257][    C1] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[   53.254261][    C1] Call Trace:
[   53.254266][    C1]  ? lockdep_hardirqs_on_prepare+0x379/0x540
[   53.254270][    C1]  ? netif_set_real_num_tx_queues+0x780/0x780
[   53.254275][    C1]  ? rmnet_unregister_real_device+0x56/0x90 [rmnet]
[   53.254279][    C1]  ? __kasan_slab_free+0x126/0x150
[   53.254283][    C1]  ? kfree+0xdc/0x320
[   53.254288][    C1]  ? rmnet_unregister_real_device+0x56/0x90 [rmnet]
[   53.254293][    C1]  unregister_netdevice_many.part.135+0x13/0x1b0
[   53.254297][    C1]  rtnl_delete_link+0xbc/0x100
[   53.254301][    C1]  ? rtnl_af_register+0xc0/0xc0
[   53.254305][    C1]  rtnl_dellink+0x2dc/0x840
[   53.254309][    C1]  ? find_held_lock+0x39/0x1d0
[   53.254314][    C1]  ? valid_fdb_dump_strict+0x620/0x620
[   53.254318][    C1]  ? rtnetlink_rcv_msg+0x457/0x890
[   53.254322][    C1]  ? lock_contended+0xd20/0xd20
[   53.254326][    C1]  rtnetlink_rcv_msg+0x4a8/0x890
[ ... ]
[   73.813696][ T1192] unregister_netdevice: waiting for rmnet0 to become free. Usage count = 1

Fixes: 037f9cdf72fb ("net: rmnet: use upper/lower device infrastructure")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/qualcomm/rmnet/rmnet_config.c    | 21 +++++++++++--------
 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
index 40efe60eff8d..2c8c252b7b97 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
@@ -47,15 +47,23 @@ static int rmnet_unregister_real_device(struct net_device *real_dev)
 	return 0;
 }
 
-static int rmnet_register_real_device(struct net_device *real_dev)
+static int rmnet_register_real_device(struct net_device *real_dev,
+				      struct netlink_ext_ack *extack)
 {
 	struct rmnet_port *port;
 	int rc, entry;
 
 	ASSERT_RTNL();
 
-	if (rmnet_is_real_dev_registered(real_dev))
+	if (rmnet_is_real_dev_registered(real_dev)) {
+		port = rmnet_get_port_rtnl(real_dev);
+		if (port->rmnet_mode != RMNET_EPMODE_VND) {
+			NL_SET_ERR_MSG_MOD(extack, "bridge device already exists");
+			return -EINVAL;
+		}
+
 		return 0;
+	}
 
 	port = kzalloc(sizeof(*port), GFP_KERNEL);
 	if (!port)
@@ -133,7 +141,7 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev,
 
 	mux_id = nla_get_u16(data[IFLA_RMNET_MUX_ID]);
 
-	err = rmnet_register_real_device(real_dev);
+	err = rmnet_register_real_device(real_dev, extack);
 	if (err)
 		goto err0;
 
@@ -421,11 +429,6 @@ int rmnet_add_bridge(struct net_device *rmnet_dev,
 		return -EINVAL;
 	}
 
-	if (port->rmnet_mode != RMNET_EPMODE_VND) {
-		NL_SET_ERR_MSG_MOD(extack, "bridge device already exists");
-		return -EINVAL;
-	}
-
 	if (rmnet_is_real_dev_registered(slave_dev)) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "slave cannot be another rmnet dev");
@@ -433,7 +436,7 @@ int rmnet_add_bridge(struct net_device *rmnet_dev,
 		return -EBUSY;
 	}
 
-	err = rmnet_register_real_device(slave_dev);
+	err = rmnet_register_real_device(slave_dev, extack);
 	if (err)
 		return -EBUSY;
 
-- 
2.26.2


From d4383a57ab45ab62624a38cbe63581bc4ebf002f Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Thu, 2 Jul 2020 17:08:55 +0000
Subject: [PATCH 42/44] net: rmnet: do not allow to add multiple bridge
 interfaces

[ Upstream commit 2fb2799a2abb39d7dbb48abb3baa1133bf5e921a ]

rmnet can have only two bridge interface.
One of them is a link interface and another one is added by
the master operation.
rmnet interface shouldn't allow adding additional
bridge interfaces by mater operation.
But, there is no code to deny additional interfaces.
So, interface leak occurs.

Test commands:
    ip link add dummy0 type dummy
    ip link add dummy1 type dummy
    ip link add dummy2 type dummy
    ip link add rmnet0 link dummy0 type rmnet mux_id 1
    ip link set dummy1 master rmnet0
    ip link set dummy2 master rmnet0
    ip link del rmnet0

In the above test command, the dummy0 was attached to rmnet as VND mode.
Then, dummy1 was attached to rmnet0 as BRIDGE mode.
At this point, dummy0 mode is switched from VND to BRIDGE automatically.
Then, dummy2 is attached to rmnet as BRIDGE mode.
At this point, rmnet0 should deny this operation.
But, rmnet0 doesn't deny this.
So that below splat occurs when the rmnet0 interface is deleted.

Splat looks like:
[  186.684787][    C2] WARNING: CPU: 2 PID: 1009 at net/core/dev.c:8992 rollback_registered_many+0x986/0xcf0
[  186.684788][    C2] Modules linked in: rmnet dummy openvswitch nsh nf_conncount nf_nat nf_conntrack nf_defrag_x
[  186.684805][    C2] CPU: 2 PID: 1009 Comm: ip Not tainted 5.8.0-rc1+ #621
[  186.684807][    C2] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[  186.684808][    C2] RIP: 0010:rollback_registered_many+0x986/0xcf0
[  186.684811][    C2] Code: 41 8b 4e cc 45 31 c0 31 d2 4c 89 ee 48 89 df e8 e0 47 ff ff 85 c0 0f 84 cd fc ff ff 5
[  186.684812][    C2] RSP: 0018:ffff8880cd9472e0 EFLAGS: 00010287
[  186.684815][    C2] RAX: ffff8880cc56da58 RBX: ffff8880ab21c000 RCX: ffffffff9329d323
[  186.684816][    C2] RDX: 1ffffffff2be6410 RSI: 0000000000000008 RDI: ffffffff95f32080
[  186.684818][    C2] RBP: dffffc0000000000 R08: fffffbfff2be6411 R09: fffffbfff2be6411
[  186.684819][    C2] R10: ffffffff95f32087 R11: 0000000000000001 R12: ffff8880cd947480
[  186.684820][    C2] R13: ffff8880ab21c0b8 R14: ffff8880cd947400 R15: ffff8880cdf10640
[  186.684822][    C2] FS:  00007f00843890c0(0000) GS:ffff8880d4e00000(0000) knlGS:0000000000000000
[  186.684823][    C2] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  186.684825][    C2] CR2: 000055b8ab1077b8 CR3: 00000000ab612006 CR4: 00000000000606e0
[  186.684826][    C2] Call Trace:
[  186.684827][    C2]  ? lockdep_hardirqs_on_prepare+0x379/0x540
[  186.684829][    C2]  ? netif_set_real_num_tx_queues+0x780/0x780
[  186.684830][    C2]  ? rmnet_unregister_real_device+0x56/0x90 [rmnet]
[  186.684831][    C2]  ? __kasan_slab_free+0x126/0x150
[  186.684832][    C2]  ? kfree+0xdc/0x320
[  186.684834][    C2]  ? rmnet_unregister_real_device+0x56/0x90 [rmnet]
[  186.684835][    C2]  unregister_netdevice_many.part.135+0x13/0x1b0
[  186.684836][    C2]  rtnl_delete_link+0xbc/0x100
[ ... ]
[  238.440071][ T1009] unregister_netdevice: waiting for rmnet0 to become free. Usage count = 1

Fixes: 037f9cdf72fb ("net: rmnet: use upper/lower device infrastructure")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
index 2c8c252b7b97..fcdecddb2812 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
@@ -429,6 +429,11 @@ int rmnet_add_bridge(struct net_device *rmnet_dev,
 		return -EINVAL;
 	}
 
+	if (port->rmnet_mode != RMNET_EPMODE_VND) {
+		NL_SET_ERR_MSG_MOD(extack, "more than one bridge dev attached");
+		return -EINVAL;
+	}
+
 	if (rmnet_is_real_dev_registered(slave_dev)) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "slave cannot be another rmnet dev");
-- 
2.26.2


From 5383c96c9d657080232ae323f5f5651c40e8a279 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Thu, 2 Jul 2020 17:06:19 +0000
Subject: [PATCH 43/44] hsr: fix interface leak in error path of
 hsr_dev_finalize()

[ Upstream commit ccfc9df1352be5b2f391091e18c4b2395d30ce78 ]

To release hsr(upper) interface, it should release
its own lower interfaces first.
Then, hsr(upper) interface can be released safely.
In the current code of error path of hsr_dev_finalize(), it releases hsr
interface before releasing a lower interface.
So, a warning occurs, which warns about the leak of lower interfaces.
In order to fix this problem, changing the ordering of the error path of
hsr_dev_finalize() is needed.

Test commands:
    ip link add dummy0 type dummy
    ip link add dummy1 type dummy
    ip link add dummy2 type dummy
    ip link add hsr0 type hsr slave1 dummy0 slave2 dummy1
    ip link add hsr1 type hsr slave1 dummy2 slave2 dummy0

Splat looks like:
[  214.923127][    C2] WARNING: CPU: 2 PID: 1093 at net/core/dev.c:8992 rollback_registered_many+0x986/0xcf0
[  214.923129][    C2] Modules linked in: hsr dummy openvswitch nsh nf_conncount nf_nat nf_conntrack nf_defrag_ipx
[  214.923154][    C2] CPU: 2 PID: 1093 Comm: ip Not tainted 5.8.0-rc2+ #623
[  214.923156][    C2] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[  214.923157][    C2] RIP: 0010:rollback_registered_many+0x986/0xcf0
[  214.923160][    C2] Code: 41 8b 4e cc 45 31 c0 31 d2 4c 89 ee 48 89 df e8 e0 47 ff ff 85 c0 0f 84 cd fc ff ff 5
[  214.923162][    C2] RSP: 0018:ffff8880c5156f28 EFLAGS: 00010287
[  214.923165][    C2] RAX: ffff8880d1dad458 RBX: ffff8880bd1b9000 RCX: ffffffffb929d243
[  214.923167][    C2] RDX: 1ffffffff77e63f0 RSI: 0000000000000008 RDI: ffffffffbbf31f80
[  214.923168][    C2] RBP: dffffc0000000000 R08: fffffbfff77e63f1 R09: fffffbfff77e63f1
[  214.923170][    C2] R10: ffffffffbbf31f87 R11: 0000000000000001 R12: ffff8880c51570a0
[  214.923172][    C2] R13: ffff8880bd1b90b8 R14: ffff8880c5157048 R15: ffff8880d1dacc40
[  214.923174][    C2] FS:  00007fdd257a20c0(0000) GS:ffff8880da200000(0000) knlGS:0000000000000000
[  214.923175][    C2] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  214.923177][    C2] CR2: 00007ffd78beb038 CR3: 00000000be544005 CR4: 00000000000606e0
[  214.923179][    C2] Call Trace:
[  214.923180][    C2]  ? netif_set_real_num_tx_queues+0x780/0x780
[  214.923182][    C2]  ? dev_validate_mtu+0x140/0x140
[  214.923183][    C2]  ? synchronize_rcu.part.79+0x85/0xd0
[  214.923185][    C2]  ? synchronize_rcu_expedited+0xbb0/0xbb0
[  214.923187][    C2]  rollback_registered+0xc8/0x170
[  214.923188][    C2]  ? rollback_registered_many+0xcf0/0xcf0
[  214.923190][    C2]  unregister_netdevice_queue+0x18b/0x240
[  214.923191][    C2]  hsr_dev_finalize+0x56e/0x6e0 [hsr]
[  214.923192][    C2]  hsr_newlink+0x36b/0x450 [hsr]
[  214.923194][    C2]  ? hsr_dellink+0x70/0x70 [hsr]
[  214.923195][    C2]  ? rtnl_create_link+0x2e4/0xb00
[  214.923197][    C2]  ? __netlink_ns_capable+0xc3/0xf0
[  214.923198][    C2]  __rtnl_newlink+0xbdb/0x1270
[ ... ]

Fixes: e0a4b99773d3 ("hsr: use upper/lower device infrastructure")
Reported-by: syzbot+7f1c020f68dab95aab59@syzkaller.appspotmail.com
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/hsr/hsr_device.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index ef100cfd2ac1..56a11341f99c 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -417,6 +417,7 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2],
 		     unsigned char multicast_spec, u8 protocol_version,
 		     struct netlink_ext_ack *extack)
 {
+	bool unregister = false;
 	struct hsr_priv *hsr;
 	int res;
 
@@ -468,25 +469,27 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2],
 	if (res)
 		goto err_unregister;
 
+	unregister = true;
+
 	res = hsr_add_port(hsr, slave[0], HSR_PT_SLAVE_A, extack);
 	if (res)
-		goto err_add_slaves;
+		goto err_unregister;
 
 	res = hsr_add_port(hsr, slave[1], HSR_PT_SLAVE_B, extack);
 	if (res)
-		goto err_add_slaves;
+		goto err_unregister;
 
 	hsr_debugfs_init(hsr, hsr_dev);
 	mod_timer(&hsr->prune_timer, jiffies + msecs_to_jiffies(PRUNE_PERIOD));
 
 	return 0;
 
-err_add_slaves:
-	unregister_netdevice(hsr_dev);
 err_unregister:
 	hsr_del_ports(hsr);
 err_add_master:
 	hsr_del_self_node(hsr);
 
+	if (unregister)
+		unregister_netdevice(hsr_dev);
 	return res;
 }
-- 
2.26.2


From 792ba7492c301fc6de679797ad91332f135da1e4 Mon Sep 17 00:00:00 2001
From: Eli Britstein <elibr@mellanox.com>
Date: Sun, 28 Jun 2020 15:42:26 +0300
Subject: [PATCH 44/44] net/mlx5e: CT: Fix memory leak in cleanup

[ Upstream commit eb32b3f53d283e8d68b6d86c3a6ed859b24dacae ]

CT entries are deleted via a workqueue from netfilter. If removing the
module before that, the rules are cleaned by the driver itself, but the
memory entries for them are not freed. Fix that.

Fixes: ac991b48d43c ("net/mlx5e: CT: Offload established flows")
Signed-off-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
index 470282daed19..369a03771435 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
@@ -849,6 +849,7 @@ mlx5_tc_ct_flush_ft_entry(void *ptr, void *arg)
 	struct mlx5_ct_entry *entry = ptr;
 
 	mlx5_tc_ct_entry_del_rules(ct_priv, entry);
+	kfree(entry);
 }
 
 static void
-- 
2.26.2

Re: [PATCHES] Networking

[Greg KH]

On Thu, Jul 16, 2020 at 04:07:20PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v5.4 and
> v5.7 -stable, respectively.

All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 105 bytes --]


Please queue up the following networking bug fixes for v5.4 and
v5.7 -stable, respectively.

Thank you.

[-- Attachment #2: net_54.mbox --]
[-- Type: Application/Octet-Stream, Size: 66693 bytes --]

From f5cad846dee57270c6e270ba33faafeabfc4cf49 Mon Sep 17 00:00:00 2001
From: Peilin Ye <yepeilin.cs@gmail.com>
Date: Wed, 22 Jul 2020 11:19:01 -0400
Subject: [PATCH 01/29] AX.25: Fix out-of-bounds read in ax25_connect()

[ Upstream commit 2f2a7ffad5c6cbf3d438e813cfdc88230e185ba6 ]

Checks on `addr_len` and `fsa->fsa_ax25.sax25_ndigis` are insufficient.
ax25_connect() can go out of bounds when `fsa->fsa_ax25.sax25_ndigis`
equals to 7 or 8. Fix it.

This issue has been reported as a KMSAN uninit-value bug, because in such
a case, ax25_connect() reaches into the uninitialized portion of the
`struct sockaddr_storage` statically allocated in __sys_connect().

It is safe to remove `fsa->fsa_ax25.sax25_ndigis > AX25_MAX_DIGIS` because
`addr_len` is guaranteed to be less than or equal to
`sizeof(struct full_sockaddr_ax25)`.

Reported-by: syzbot+c82752228ed975b0a623@syzkaller.appspotmail.com
Link: https://syzkaller.appspot.com/bug?id=55ef9d629f3b3d7d70b69558015b63b48d01af66
Signed-off-by: Peilin Ye <yepeilin.cs@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ax25/af_ax25.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index e5a3dc28116d..085a6631eb22 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1187,7 +1187,9 @@ static int __must_check ax25_connect(struct socket *sock,
 	if (addr_len > sizeof(struct sockaddr_ax25) &&
 	    fsa->fsa_ax25.sax25_ndigis != 0) {
 		/* Valid number of digipeaters ? */
-		if (fsa->fsa_ax25.sax25_ndigis < 1 || fsa->fsa_ax25.sax25_ndigis > AX25_MAX_DIGIS) {
+		if (fsa->fsa_ax25.sax25_ndigis < 1 ||
+		    addr_len < sizeof(struct sockaddr_ax25) +
+		    sizeof(ax25_address) * fsa->fsa_ax25.sax25_ndigis) {
 			err = -EINVAL;
 			goto out_release;
 		}
-- 
2.26.2


From 0ee381d1d4b822f330df4101d5dcd909959c69b0 Mon Sep 17 00:00:00 2001
From: Peilin Ye <yepeilin.cs@gmail.com>
Date: Wed, 22 Jul 2020 12:05:12 -0400
Subject: [PATCH 02/29] AX.25: Prevent out-of-bounds read in ax25_sendmsg()

[ Upstream commit 8885bb0621f01a6c82be60a91e5fc0f6e2f71186 ]

Checks on `addr_len` and `usax->sax25_ndigis` are insufficient.
ax25_sendmsg() can go out of bounds when `usax->sax25_ndigis` equals to 7
or 8. Fix it.

It is safe to remove `usax->sax25_ndigis > AX25_MAX_DIGIS`, since
`addr_len` is guaranteed to be less than or equal to
`sizeof(struct full_sockaddr_ax25)`

Signed-off-by: Peilin Ye <yepeilin.cs@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ax25/af_ax25.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 085a6631eb22..dbe7ef2c7e75 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1509,7 +1509,8 @@ static int ax25_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 			struct full_sockaddr_ax25 *fsa = (struct full_sockaddr_ax25 *)usax;
 
 			/* Valid number of digipeaters ? */
-			if (usax->sax25_ndigis < 1 || usax->sax25_ndigis > AX25_MAX_DIGIS) {
+			if (usax->sax25_ndigis < 1 || addr_len < sizeof(struct sockaddr_ax25) +
+			    sizeof(ax25_address) * usax->sax25_ndigis) {
 				err = -EINVAL;
 				goto out;
 			}
-- 
2.26.2


From dc2063a9e3c7a85e1a904dbefef79e5a7da3b206 Mon Sep 17 00:00:00 2001
From: George Kennedy <george.kennedy@oracle.com>
Date: Wed, 15 Jul 2020 09:59:31 -0400
Subject: [PATCH 03/29] ax88172a: fix ax88172a_unbind() failures

[ Upstream commit c28d9a285668c799eeae2f7f93e929a6028a4d6d ]

If ax88172a_unbind() fails, make sure that the return code is
less than zero so that cleanup is done properly and avoid UAF.

Fixes: a9a51bd727d1 ("ax88172a: fix information leak on short answers")
Signed-off-by: George Kennedy <george.kennedy@oracle.com>
Reported-by: syzbot+4cd84f527bf4a10fc9c1@syzkaller.appspotmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/ax88172a.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/ax88172a.c b/drivers/net/usb/ax88172a.c
index af3994e0853b..6101d82102e7 100644
--- a/drivers/net/usb/ax88172a.c
+++ b/drivers/net/usb/ax88172a.c
@@ -198,6 +198,7 @@ static int ax88172a_bind(struct usbnet *dev, struct usb_interface *intf)
 	ret = asix_read_cmd(dev, AX_CMD_READ_NODE_ID, 0, 0, ETH_ALEN, buf, 0);
 	if (ret < ETH_ALEN) {
 		netdev_err(dev->net, "Failed to read MAC address: %d\n", ret);
+		ret = -EIO;
 		goto free;
 	}
 	memcpy(dev->net->dev_addr, buf, ETH_ALEN);
-- 
2.26.2


From 48911a1f85adc48ff42acfb7fd5fa28e067970e6 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Sun, 19 Jul 2020 12:11:24 +0000
Subject: [PATCH 04/29] bonding: check error value of register_netdevice()
 immediately

[ Upstream commit 544f287b84959203367cd29e16e772717612fab4 ]

If register_netdevice() is failed, net_device should not be used
because variables are uninitialized or freed.
So, the routine should be stopped immediately.
But, bond_create() doesn't check return value of register_netdevice()
immediately. That will result in a panic because of using uninitialized
or freed memory.

Test commands:
    modprobe netdev-notifier-error-inject
    echo -22 > /sys/kernel/debug/notifier-error-inject/netdev/\
actions/NETDEV_REGISTER/error
    modprobe bonding max_bonds=3

Splat looks like:
[  375.028492][  T193] general protection fault, probably for non-canonical address 0x6b6b6b6b6b6b6b6b: 0000 [#1] SMP DEBUG_PAGEALLOC PTI
[  375.033207][  T193] CPU: 2 PID: 193 Comm: kworker/2:2 Not tainted 5.8.0-rc4+ #645
[  375.036068][  T193] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014
[  375.039673][  T193] Workqueue: events linkwatch_event
[  375.041557][  T193] RIP: 0010:dev_activate+0x4a/0x340
[  375.043381][  T193] Code: 40 a8 04 0f 85 db 00 00 00 8b 83 08 04 00 00 85 c0 0f 84 0d 01 00 00 31 d2 89 d0 48 8d 04 40 48 c1 e0 07 48 03 83 00 04 00 00 <48> 8b 48 10 f6 41 10 01 75 08 f0 80 a1 a0 01 00 00 fd 48 89 48 08
[  375.050267][  T193] RSP: 0018:ffff9f8facfcfdd8 EFLAGS: 00010202
[  375.052410][  T193] RAX: 6b6b6b6b6b6b6b6b RBX: ffff9f8fae6ea000 RCX: 0000000000000006
[  375.055178][  T193] RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff9f8fae6ea000
[  375.057762][  T193] RBP: ffff9f8fae6ea000 R08: 0000000000000000 R09: 0000000000000000
[  375.059810][  T193] R10: 0000000000000001 R11: 0000000000000000 R12: ffff9f8facfcfe08
[  375.061892][  T193] R13: ffffffff883587e0 R14: 0000000000000000 R15: ffff9f8fae6ea580
[  375.063931][  T193] FS:  0000000000000000(0000) GS:ffff9f8fbae00000(0000) knlGS:0000000000000000
[  375.066239][  T193] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  375.067841][  T193] CR2: 00007f2f542167a0 CR3: 000000012cee6002 CR4: 00000000003606e0
[  375.069657][  T193] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  375.071471][  T193] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[  375.073269][  T193] Call Trace:
[  375.074005][  T193]  linkwatch_do_dev+0x4d/0x50
[  375.075052][  T193]  __linkwatch_run_queue+0x10b/0x200
[  375.076244][  T193]  linkwatch_event+0x21/0x30
[  375.077274][  T193]  process_one_work+0x252/0x600
[  375.078379][  T193]  ? process_one_work+0x600/0x600
[  375.079518][  T193]  worker_thread+0x3c/0x380
[  375.080534][  T193]  ? process_one_work+0x600/0x600
[  375.081668][  T193]  kthread+0x139/0x150
[  375.082567][  T193]  ? kthread_park+0x90/0x90
[  375.083567][  T193]  ret_from_fork+0x22/0x30

Fixes: e826eafa65c6 ("bonding: Call netif_carrier_off after register_netdevice")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 703c5c2c80e5..499845c32b1b 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -4864,15 +4864,19 @@ int bond_create(struct net *net, const char *name)
 	bond_dev->rtnl_link_ops = &bond_link_ops;
 
 	res = register_netdevice(bond_dev);
+	if (res < 0) {
+		free_netdev(bond_dev);
+		rtnl_unlock();
+
+		return res;
+	}
 
 	netif_carrier_off(bond_dev);
 
 	bond_work_init_all(bond);
 
 	rtnl_unlock();
-	if (res < 0)
-		free_netdev(bond_dev);
-	return res;
+	return 0;
 }
 
 static int __net_init bond_net_init(struct net *net)
-- 
2.26.2


From 702beb430599bbc769daa8cf8fdaa8d79e71adb5 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Wed, 22 Jul 2020 16:31:54 -0700
Subject: [PATCH 05/29] bonding: check return value of register_netdevice() in
 bond_newlink()

[ Upstream commit c75d1d5248c0c97996051809ad0e9f154ba5d76e ]

Very similar to commit 544f287b8495
("bonding: check error value of register_netdevice() immediately"),
we should immediately check the return value of register_netdevice()
before doing anything else.

Fixes: 005db31d5f5f ("bonding: set carrier off for devices created through netlink")
Reported-and-tested-by: syzbot+bbc3a11c4da63c1b74d6@syzkaller.appspotmail.com
Cc: Beniamino Galvani <bgalvani@redhat.com>
Cc: Taehee Yoo <ap420073@gmail.com>
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_netlink.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index b43b51646b11..f0f9138e967f 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -456,11 +456,10 @@ static int bond_newlink(struct net *src_net, struct net_device *bond_dev,
 		return err;
 
 	err = register_netdevice(bond_dev);
-
-	netif_carrier_off(bond_dev);
 	if (!err) {
 		struct bonding *bond = netdev_priv(bond_dev);
 
+		netif_carrier_off(bond_dev);
 		bond_work_init_all(bond);
 	}
 
-- 
2.26.2


From fb4c49a34442d970cd525044da9f1fbd2ac6d2d1 Mon Sep 17 00:00:00 2001
From: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Date: Thu, 23 Jul 2020 11:31:48 -0600
Subject: [PATCH 06/29] dev: Defer free of skbs in flush_backlog

[ Upstream commit 7df5cb75cfb8acf96c7f2342530eb41e0c11f4c3 ]

IRQs are disabled when freeing skbs in input queue.
Use the IRQ safe variant to free skbs here.

Fixes: 145dd5f9c88f ("net: flush the softnet backlog in process context")
Signed-off-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 727965565d31..25858f1f67cf 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5229,7 +5229,7 @@ static void flush_backlog(struct work_struct *work)
 	skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) {
 		if (skb->dev->reg_state == NETREG_UNREGISTERING) {
 			__skb_unlink(skb, &sd->input_pkt_queue);
-			kfree_skb(skb);
+			dev_kfree_skb_irq(skb);
 			input_queue_head_incr(sd);
 		}
 	}
-- 
2.26.2


From 65a713c9f041617fa0dd141270bd1331c394beeb Mon Sep 17 00:00:00 2001
From: Xie He <xie.he.0141@gmail.com>
Date: Thu, 16 Jul 2020 16:44:33 -0700
Subject: [PATCH 07/29] drivers/net/wan/x25_asy: Fix to make it work

[ Upstream commit 8fdcabeac39824fe67480fd9508d80161c541854 ]

This driver is not working because of problems of its receiving code.
This patch fixes it to make it work.

When the driver receives an LAPB frame, it should first pass the frame
to the LAPB module to process. After processing, the LAPB module passes
the data (the packet) back to the driver, the driver should then add a
one-byte pseudo header and pass the data to upper layers.

The changes to the "x25_asy_bump" function and the
"x25_asy_data_indication" function are to correctly implement this
procedure.

Also, the "x25_asy_unesc" function ignores any frame that is shorter
than 3 bytes. However the shortest frames are 2-byte long. So we need
to change it to allow 2-byte frames to pass.

Cc: Eric Dumazet <edumazet@google.com>
Cc: Martin Schiller <ms@dev.tdt.de>
Signed-off-by: Xie He <xie.he.0141@gmail.com>
Reviewed-by: Martin Schiller <ms@dev.tdt.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wan/x25_asy.c | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wan/x25_asy.c b/drivers/net/wan/x25_asy.c
index 914be5847386..cdcc380b4c26 100644
--- a/drivers/net/wan/x25_asy.c
+++ b/drivers/net/wan/x25_asy.c
@@ -183,7 +183,7 @@ static inline void x25_asy_unlock(struct x25_asy *sl)
 	netif_wake_queue(sl->dev);
 }
 
-/* Send one completely decapsulated IP datagram to the IP layer. */
+/* Send an LAPB frame to the LAPB module to process. */
 
 static void x25_asy_bump(struct x25_asy *sl)
 {
@@ -195,13 +195,12 @@ static void x25_asy_bump(struct x25_asy *sl)
 	count = sl->rcount;
 	dev->stats.rx_bytes += count;
 
-	skb = dev_alloc_skb(count+1);
+	skb = dev_alloc_skb(count);
 	if (skb == NULL) {
 		netdev_warn(sl->dev, "memory squeeze, dropping packet\n");
 		dev->stats.rx_dropped++;
 		return;
 	}
-	skb_push(skb, 1);	/* LAPB internal control */
 	skb_put_data(skb, sl->rbuff, count);
 	skb->protocol = x25_type_trans(skb, sl->dev);
 	err = lapb_data_received(skb->dev, skb);
@@ -209,7 +208,6 @@ static void x25_asy_bump(struct x25_asy *sl)
 		kfree_skb(skb);
 		printk(KERN_DEBUG "x25_asy: data received err - %d\n", err);
 	} else {
-		netif_rx(skb);
 		dev->stats.rx_packets++;
 	}
 }
@@ -356,12 +354,21 @@ static netdev_tx_t x25_asy_xmit(struct sk_buff *skb,
  */
 
 /*
- *	Called when I frame data arrives. We did the work above - throw it
- *	at the net layer.
+ *	Called when I frame data arrive. We add a pseudo header for upper
+ *	layers and pass it to upper layers.
  */
 
 static int x25_asy_data_indication(struct net_device *dev, struct sk_buff *skb)
 {
+	if (skb_cow(skb, 1)) {
+		kfree_skb(skb);
+		return NET_RX_DROP;
+	}
+	skb_push(skb, 1);
+	skb->data[0] = X25_IFACE_DATA;
+
+	skb->protocol = x25_type_trans(skb, dev);
+
 	return netif_rx(skb);
 }
 
@@ -657,7 +664,7 @@ static void x25_asy_unesc(struct x25_asy *sl, unsigned char s)
 	switch (s) {
 	case X25_END:
 		if (!test_and_clear_bit(SLF_ERROR, &sl->flags) &&
-		    sl->rcount > 2)
+		    sl->rcount >= 2)
 			x25_asy_bump(sl);
 		clear_bit(SLF_ESCAPE, &sl->flags);
 		sl->rcount = 0;
-- 
2.26.2


From a79f91103725fe9c5bef6105fb2ef35221739066 Mon Sep 17 00:00:00 2001
From: Claudiu Manoil <claudiu.manoil@nxp.com>
Date: Wed, 22 Jul 2020 17:40:12 +0300
Subject: [PATCH 08/29] enetc: Remove the mdio bus on PF probe bailout

[ Upstream commit 26cb7085c8984e5b71d65c374a135134ed8cabb3 ]

For ENETC ports that register an external MDIO bus,
the bus doesn't get removed on the error bailout path
of enetc_pf_probe().

This issue became much more visible after recent:
commit 07095c025ac2 ("net: enetc: Use DT protocol information to set up the ports")
Before this commit, one could make probing fail on the error
path only by having register_netdev() fail, which is unlikely.
But after this commit, because it moved the enetc_of_phy_get()
call up in the probing sequence, now we can trigger an mdiobus_free()
bug just by forcing enetc_alloc_msix() to return error, i.e. with the
'pci=nomsi' kernel bootarg (since ENETC relies on MSI support to work),
as the calltrace below shows:

kernel BUG at /home/eiz/work/enetc/net/drivers/net/phy/mdio_bus.c:648!
Internal error: Oops - BUG: 0 [#1] PREEMPT SMP
[...]
Hardware name: LS1028A RDB Board (DT)
pstate: 80000005 (Nzcv daif -PAN -UAO BTYPE=--)
pc : mdiobus_free+0x50/0x58
lr : devm_mdiobus_free+0x14/0x20
[...]
Call trace:
 mdiobus_free+0x50/0x58
 devm_mdiobus_free+0x14/0x20
 release_nodes+0x138/0x228
 devres_release_all+0x38/0x60
 really_probe+0x1c8/0x368
 driver_probe_device+0x5c/0xc0
 device_driver_attach+0x74/0x80
 __driver_attach+0x8c/0xd8
 bus_for_each_dev+0x7c/0xd8
 driver_attach+0x24/0x30
 bus_add_driver+0x154/0x200
 driver_register+0x64/0x120
 __pci_register_driver+0x44/0x50
 enetc_pf_driver_init+0x24/0x30
 do_one_initcall+0x60/0x1c0
 kernel_init_freeable+0x1fc/0x274
 kernel_init+0x14/0x110
 ret_from_fork+0x10/0x34

Fixes: ebfcb23d62ab ("enetc: Add ENETC PF level external MDIO support")
Signed-off-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/enetc/enetc_pf.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
index b73421c3e25b..74847aa644f1 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -885,6 +885,7 @@ static int enetc_pf_probe(struct pci_dev *pdev,
 	return 0;
 
 err_reg_netdev:
+	enetc_mdio_remove(pf);
 	enetc_of_put_phy(priv);
 	enetc_free_msix(priv);
 err_alloc_msix:
-- 
2.26.2


From 08212cc48e0829f78b5bc3f68662676aa9369a56 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Wed, 22 Jul 2020 18:56:25 -0700
Subject: [PATCH 09/29] geneve: fix an uninitialized value in
 geneve_changelink()

[ Upstream commit 32818c075c54bb0cae44dd6f7ab00b01c52b8372 ]

geneve_nl2info() sets 'df' conditionally, so we have to
initialize it by copying the value from existing geneve
device in geneve_changelink().

Fixes: 56c09de347e4 ("geneve: allow changing DF behavior after creation")
Reported-by: syzbot+7ebc2e088af5e4c0c9fa@syzkaller.appspotmail.com
Cc: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 19d9d78a6df2..adfdf6260b26 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1615,11 +1615,11 @@ static int geneve_changelink(struct net_device *dev, struct nlattr *tb[],
 			     struct netlink_ext_ack *extack)
 {
 	struct geneve_dev *geneve = netdev_priv(dev);
+	enum ifla_geneve_df df = geneve->df;
 	struct geneve_sock *gs4, *gs6;
 	struct ip_tunnel_info info;
 	bool metadata;
 	bool use_udp6_rx_checksums;
-	enum ifla_geneve_df df;
 	bool ttl_inherit;
 	int err;
 
-- 
2.26.2


From c0a7543c3b15b54f0ad08073791bce5140bdf968 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Tue, 14 Jul 2020 13:00:27 +0200
Subject: [PATCH 10/29] hippi: Fix a size used in a 'pci_free_consistent()' in
 an error handling path

[ Upstream commit 3195c4706b00106aa82c73acd28340fa8fc2bfc1 ]

The size used when calling 'pci_alloc_consistent()' and
'pci_free_consistent()' should match.

Fix it and have it consistent with the corresponding call in 'rr_close()'.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hippi/rrunner.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/hippi/rrunner.c b/drivers/net/hippi/rrunner.c
index 2a6ec5394966..a4b3fce69ecd 100644
--- a/drivers/net/hippi/rrunner.c
+++ b/drivers/net/hippi/rrunner.c
@@ -1242,7 +1242,7 @@ static int rr_open(struct net_device *dev)
 		rrpriv->info = NULL;
 	}
 	if (rrpriv->rx_ctrl) {
-		pci_free_consistent(pdev, sizeof(struct ring_ctrl),
+		pci_free_consistent(pdev, 256 * sizeof(struct ring_ctrl),
 				    rrpriv->rx_ctrl, rrpriv->rx_ctrl_dma);
 		rrpriv->rx_ctrl = NULL;
 	}
-- 
2.26.2


From 0eda1c795484965582b9cf4adc1f8384a686bfe8 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Mon, 13 Jul 2020 23:59:50 +0800
Subject: [PATCH 11/29] ip6_gre: fix null-ptr-deref in ip6gre_init_net()

[ Upstream commit 46ef5b89ec0ecf290d74c4aee844f063933c4da4 ]

KASAN report null-ptr-deref error when register_netdev() failed:

KASAN: null-ptr-deref in range [0x00000000000003c0-0x00000000000003c7]
CPU: 2 PID: 422 Comm: ip Not tainted 5.8.0-rc4+ #12
Call Trace:
 ip6gre_init_net+0x4ab/0x580
 ? ip6gre_tunnel_uninit+0x3f0/0x3f0
 ops_init+0xa8/0x3c0
 setup_net+0x2de/0x7e0
 ? rcu_read_lock_bh_held+0xb0/0xb0
 ? ops_init+0x3c0/0x3c0
 ? kasan_unpoison_shadow+0x33/0x40
 ? __kasan_kmalloc.constprop.0+0xc2/0xd0
 copy_net_ns+0x27d/0x530
 create_new_namespaces+0x382/0xa30
 unshare_nsproxy_namespaces+0xa1/0x1d0
 ksys_unshare+0x39c/0x780
 ? walk_process_tree+0x2a0/0x2a0
 ? trace_hardirqs_on+0x4a/0x1b0
 ? _raw_spin_unlock_irq+0x1f/0x30
 ? syscall_trace_enter+0x1a7/0x330
 ? do_syscall_64+0x1c/0xa0
 __x64_sys_unshare+0x2d/0x40
 do_syscall_64+0x56/0xa0
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

ip6gre_tunnel_uninit() has set 'ign->fb_tunnel_dev' to NULL, later
access to ign->fb_tunnel_dev cause null-ptr-deref. Fix it by saving
'ign->fb_tunnel_dev' to local variable ndev.

Fixes: dafabb6590cb ("ip6_gre: fix use-after-free in ip6gre_tunnel_lookup()")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 04d76f043e18..44876509d215 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1560,17 +1560,18 @@ static void ip6gre_destroy_tunnels(struct net *net, struct list_head *head)
 static int __net_init ip6gre_init_net(struct net *net)
 {
 	struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
+	struct net_device *ndev;
 	int err;
 
 	if (!net_has_fallback_tunnels(net))
 		return 0;
-	ign->fb_tunnel_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6gre0",
-					  NET_NAME_UNKNOWN,
-					  ip6gre_tunnel_setup);
-	if (!ign->fb_tunnel_dev) {
+	ndev = alloc_netdev(sizeof(struct ip6_tnl), "ip6gre0",
+			    NET_NAME_UNKNOWN, ip6gre_tunnel_setup);
+	if (!ndev) {
 		err = -ENOMEM;
 		goto err_alloc_dev;
 	}
+	ign->fb_tunnel_dev = ndev;
 	dev_net_set(ign->fb_tunnel_dev, net);
 	/* FB netdevice is special: we have one, and only one per netns.
 	 * Allowing to move it to another netns is clearly unsafe.
@@ -1590,7 +1591,7 @@ static int __net_init ip6gre_init_net(struct net *net)
 	return 0;
 
 err_reg_dev:
-	free_netdev(ign->fb_tunnel_dev);
+	free_netdev(ndev);
 err_alloc_dev:
 	return err;
 }
-- 
2.26.2


From 0895c1a70feba7d18c7f8348b6c24d51c9efc8d0 Mon Sep 17 00:00:00 2001
From: Liu Jian <liujian56@huawei.com>
Date: Mon, 20 Jul 2020 22:31:49 +0800
Subject: [PATCH 12/29] mlxsw: destroy workqueue when trap_register in
 mlxsw_emad_init

[ Upstream commit 5dbaeb87f2b309936be0aeae00cbc9e7f20ab296 ]

When mlxsw_core_trap_register fails in mlxsw_emad_init,
destroy_workqueue() shouled be called to destroy mlxsw_core->emad_wq.

Fixes: d965465b60ba ("mlxsw: core: Fix possible deadlock")
Signed-off-by: Liu Jian <liujian56@huawei.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index 0a0884d86d44..1b204ce30ee4 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -592,7 +592,7 @@ static int mlxsw_emad_init(struct mlxsw_core *mlxsw_core)
 	err = mlxsw_core_trap_register(mlxsw_core, &mlxsw_emad_rx_listener,
 				       mlxsw_core);
 	if (err)
-		return err;
+		goto err_trap_register;
 
 	err = mlxsw_core->driver->basic_trap_groups_set(mlxsw_core);
 	if (err)
@@ -604,6 +604,7 @@ static int mlxsw_emad_init(struct mlxsw_core *mlxsw_core)
 err_emad_trap_set:
 	mlxsw_core_trap_unregister(mlxsw_core, &mlxsw_emad_rx_listener,
 				   mlxsw_core);
+err_trap_register:
 	destroy_workqueue(mlxsw_core->emad_wq);
 	return err;
 }
-- 
2.26.2


From 61ad0d4a072b7809bf06665bbf422ef5e5cfb435 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Tue, 21 Jul 2020 14:51:50 +0000
Subject: [PATCH 13/29] netdevsim: fix unbalaced locking in nsim_create()

[ Upstream commit 2c9d8e01f0c6017317eee7638496173d4a64e6bc ]

In the nsim_create(), rtnl_lock() is called before nsim_bpf_init().
If nsim_bpf_init() is failed, rtnl_unlock() should be called,
but it isn't called.
So, unbalanced locking would occur.

Fixes: e05b2d141fef ("netdevsim: move netdev creation/destruction to dev probe")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/netdevsim/netdev.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index 55f57f76d01b..a6bbe93f29ef 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -301,7 +301,7 @@ nsim_create(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port)
 	rtnl_lock();
 	err = nsim_bpf_init(ns);
 	if (err)
-		goto err_free_netdev;
+		goto err_rtnl_unlock;
 
 	nsim_ipsec_init(ns);
 
@@ -315,8 +315,8 @@ nsim_create(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port)
 err_ipsec_teardown:
 	nsim_ipsec_teardown(ns);
 	nsim_bpf_uninit(ns);
+err_rtnl_unlock:
 	rtnl_unlock();
-err_free_netdev:
 	free_netdev(dev);
 	return ERR_PTR(err);
 }
-- 
2.26.2


From 5964d21eee92a6c0864672fbe408a572b3c0b58e Mon Sep 17 00:00:00 2001
From: Sergey Organov <sorganov@gmail.com>
Date: Wed, 15 Jul 2020 19:10:00 +0300
Subject: [PATCH 14/29] net: dp83640: fix SIOCSHWTSTAMP to update the struct
 with actual configuration

[ Upstream commit 473309fb8372365ad211f425bca760af800e10a7 ]

From Documentation/networking/timestamping.txt:

  A driver which supports hardware time stamping shall update the
  struct with the actual, possibly more permissive configuration.

Do update the struct passed when we upscale the requested time
stamping mode.

Fixes: cb646e2b02b2 ("ptp: Added a clock driver for the National Semiconductor PHYTER.")
Signed-off-by: Sergey Organov <sorganov@gmail.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/dp83640.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index 1c75b2627ca8..7d845117abb0 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -1348,6 +1348,7 @@ static int dp83640_hwtstamp(struct phy_device *phydev, struct ifreq *ifr)
 		dp83640->hwts_rx_en = 1;
 		dp83640->layer = PTP_CLASS_L4;
 		dp83640->version = PTP_CLASS_V1;
+		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
@@ -1355,6 +1356,7 @@ static int dp83640_hwtstamp(struct phy_device *phydev, struct ifreq *ifr)
 		dp83640->hwts_rx_en = 1;
 		dp83640->layer = PTP_CLASS_L4;
 		dp83640->version = PTP_CLASS_V2;
+		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT;
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
@@ -1362,6 +1364,7 @@ static int dp83640_hwtstamp(struct phy_device *phydev, struct ifreq *ifr)
 		dp83640->hwts_rx_en = 1;
 		dp83640->layer = PTP_CLASS_L2;
 		dp83640->version = PTP_CLASS_V2;
+		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT;
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
@@ -1369,6 +1372,7 @@ static int dp83640_hwtstamp(struct phy_device *phydev, struct ifreq *ifr)
 		dp83640->hwts_rx_en = 1;
 		dp83640->layer = PTP_CLASS_L4 | PTP_CLASS_L2;
 		dp83640->version = PTP_CLASS_V2;
+		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 		break;
 	default:
 		return -ERANGE;
-- 
2.26.2


From ce974f9ac919f189bb26371c9581ee6bd48a155c Mon Sep 17 00:00:00 2001
From: Helmut Grohne <helmut.grohne@intenta.de>
Date: Tue, 21 Jul 2020 13:07:39 +0200
Subject: [PATCH 15/29] net: dsa: microchip: call phy_remove_link_mode during
 probe

[ Upstream commit 3506b2f42dff66ea6814c3dfa1988bafb79e6f88 ]

When doing "ip link set dev ... up" for a ksz9477 backed link,
ksz9477_phy_setup is called and it calls phy_remove_link_mode to remove
1000baseT HDX. During phy_remove_link_mode, phy_advertise_supported is
called. Doing so reverts any previous change to advertised link modes
e.g. using a udevd .link file.

phy_remove_link_mode is not meant to be used while opening a link and
should be called during phy probe when the link is not yet available to
userspace.

Therefore move the phy_remove_link_mode calls into
ksz9477_switch_register. It indirectly calls dsa_register_switch, which
creates the relevant struct phy_devices and we update the link modes
right after that. At that time dev->features is already initialized by
ksz9477_switch_detect.

Remove phy_setup from ksz_dev_ops as no users remain.

Link: https://lore.kernel.org/netdev/20200715192722.GD1256692@lunn.ch/
Fixes: 42fc6a4c613019 ("net: dsa: microchip: prepare PHY for proper advertisement")
Signed-off-by: Helmut Grohne <helmut.grohne@intenta.de>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/microchip/ksz9477.c    | 42 ++++++++++++++------------
 drivers/net/dsa/microchip/ksz_common.c |  2 --
 drivers/net/dsa/microchip/ksz_common.h |  2 --
 3 files changed, 23 insertions(+), 23 deletions(-)

diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c
index f600874e2476..b15da9a8e3bb 100644
--- a/drivers/net/dsa/microchip/ksz9477.c
+++ b/drivers/net/dsa/microchip/ksz9477.c
@@ -976,23 +976,6 @@ static void ksz9477_port_mirror_del(struct dsa_switch *ds, int port,
 			     PORT_MIRROR_SNIFFER, false);
 }
 
-static void ksz9477_phy_setup(struct ksz_device *dev, int port,
-			      struct phy_device *phy)
-{
-	/* Only apply to port with PHY. */
-	if (port >= dev->phy_port_cnt)
-		return;
-
-	/* The MAC actually cannot run in 1000 half-duplex mode. */
-	phy_remove_link_mode(phy,
-			     ETHTOOL_LINK_MODE_1000baseT_Half_BIT);
-
-	/* PHY does not support gigabit. */
-	if (!(dev->features & GBIT_SUPPORT))
-		phy_remove_link_mode(phy,
-				     ETHTOOL_LINK_MODE_1000baseT_Full_BIT);
-}
-
 static bool ksz9477_get_gbit(struct ksz_device *dev, u8 data)
 {
 	bool gbit;
@@ -1605,7 +1588,6 @@ static const struct ksz_dev_ops ksz9477_dev_ops = {
 	.get_port_addr = ksz9477_get_port_addr,
 	.cfg_port_member = ksz9477_cfg_port_member,
 	.flush_dyn_mac_table = ksz9477_flush_dyn_mac_table,
-	.phy_setup = ksz9477_phy_setup,
 	.port_setup = ksz9477_port_setup,
 	.r_mib_cnt = ksz9477_r_mib_cnt,
 	.r_mib_pkt = ksz9477_r_mib_pkt,
@@ -1619,7 +1601,29 @@ static const struct ksz_dev_ops ksz9477_dev_ops = {
 
 int ksz9477_switch_register(struct ksz_device *dev)
 {
-	return ksz_switch_register(dev, &ksz9477_dev_ops);
+	int ret, i;
+	struct phy_device *phydev;
+
+	ret = ksz_switch_register(dev, &ksz9477_dev_ops);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < dev->phy_port_cnt; ++i) {
+		if (!dsa_is_user_port(dev->ds, i))
+			continue;
+
+		phydev = dsa_to_port(dev->ds, i)->slave->phydev;
+
+		/* The MAC actually cannot run in 1000 half-duplex mode. */
+		phy_remove_link_mode(phydev,
+				     ETHTOOL_LINK_MODE_1000baseT_Half_BIT);
+
+		/* PHY does not support gigabit. */
+		if (!(dev->features & GBIT_SUPPORT))
+			phy_remove_link_mode(phydev,
+					     ETHTOOL_LINK_MODE_1000baseT_Full_BIT);
+	}
+	return ret;
 }
 EXPORT_SYMBOL(ksz9477_switch_register);
 
diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index fe47180c908b..7fabc0e3d807 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -366,8 +366,6 @@ int ksz_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy)
 
 	/* setup slave port */
 	dev->dev_ops->port_setup(dev, port, false);
-	if (dev->dev_ops->phy_setup)
-		dev->dev_ops->phy_setup(dev, port, phy);
 
 	/* port_stp_state_set() will be called after to enable the port so
 	 * there is no need to do anything.
diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h
index a20ebb749377..061142b183cb 100644
--- a/drivers/net/dsa/microchip/ksz_common.h
+++ b/drivers/net/dsa/microchip/ksz_common.h
@@ -120,8 +120,6 @@ struct ksz_dev_ops {
 	u32 (*get_port_addr)(int port, int offset);
 	void (*cfg_port_member)(struct ksz_device *dev, int port, u8 member);
 	void (*flush_dyn_mac_table)(struct ksz_device *dev, int port);
-	void (*phy_setup)(struct ksz_device *dev, int port,
-			  struct phy_device *phy);
 	void (*port_cleanup)(struct ksz_device *dev, int port);
 	void (*port_setup)(struct ksz_device *dev, int port, bool cpu_port);
 	void (*r_phy)(struct ksz_device *dev, u16 phy, u16 reg, u16 *val);
-- 
2.26.2


From 4214eeda4cf979e392730853a81ae6fc39436daf Mon Sep 17 00:00:00 2001
From: Xiongfeng Wang <wangxiongfeng2@huawei.com>
Date: Tue, 21 Jul 2020 15:02:57 +0800
Subject: [PATCH 16/29] net-sysfs: add a newline when printing 'tx_timeout' by
 sysfs

[ Upstream commit 9bb5fbea59f36a589ef886292549ca4052fe676c ]

When I cat 'tx_timeout' by sysfs, it displays as follows. It's better to
add a newline for easy reading.

root@syzkaller:~# cat /sys/devices/virtual/net/lo/queues/tx-0/tx_timeout
0root@syzkaller:~#

Signed-off-by: Xiongfeng Wang <wangxiongfeng2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/net-sysfs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 4c826b8bf9b1..2ebf9b252779 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1036,7 +1036,7 @@ static ssize_t tx_timeout_show(struct netdev_queue *queue, char *buf)
 	trans_timeout = queue->trans_timeout;
 	spin_unlock_irq(&queue->_xmit_lock);
 
-	return sprintf(buf, "%lu", trans_timeout);
+	return sprintf(buf, fmt_ulong, trans_timeout);
 }
 
 static unsigned int get_netdev_queue_index(struct netdev_queue *queue)
-- 
2.26.2


From 667ea6f003627ff9c101841ca8e1380350b148e8 Mon Sep 17 00:00:00 2001
From: Miaohe Lin <linmiaohe@huawei.com>
Date: Tue, 21 Jul 2020 17:11:44 +0800
Subject: [PATCH 17/29] net: udp: Fix wrong clean up for IS_UDPLITE macro

[ Upstream commit b0a422772fec29811e293c7c0e6f991c0fd9241d ]

We can't use IS_UDPLITE to replace udp_sk->pcflag when UDPLITE_RECV_CC is
checked.

Fixes: b2bf1e2659b1 ("[UDP]: Clean up for IS_UDPLITE macro")
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 2 +-
 net/ipv6/udp.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index f3b7cb725c1b..b3320e42cbcb 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2045,7 +2045,7 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
 	/*
 	 * 	UDP-Lite specific tests, ignored on UDP sockets
 	 */
-	if ((is_udplite & UDPLITE_RECV_CC)  &&  UDP_SKB_CB(skb)->partial_cov) {
+	if ((up->pcflag & UDPLITE_RECV_CC)  &&  UDP_SKB_CB(skb)->partial_cov) {
 
 		/*
 		 * MIB statistics other than incrementing the error count are
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 9fec580c968e..ede3bed354a8 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -643,7 +643,7 @@ static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
 	/*
 	 * UDP-Lite specific tests, ignored on UDP sockets (see net/ipv4/udp.c).
 	 */
-	if ((is_udplite & UDPLITE_RECV_CC)  &&  UDP_SKB_CB(skb)->partial_cov) {
+	if ((up->pcflag & UDPLITE_RECV_CC)  &&  UDP_SKB_CB(skb)->partial_cov) {
 
 		if (up->pcrlen == 0) {          /* full coverage was set  */
 			net_dbg_ratelimited("UDPLITE6: partial coverage %d while full coverage %d requested\n",
-- 
2.26.2


From 2d86b0f2db1e1414b386e0fa3e6bb86afc85601c Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Fri, 24 Jul 2020 09:45:51 -0700
Subject: [PATCH 18/29] qrtr: orphan socket in qrtr_release()

[ Upstream commit af9f691f0f5bdd1ade65a7b84927639882d7c3e5 ]

We have to detach sock from socket in qrtr_release(),
otherwise skb->sk may still reference to this socket
when the skb is released in tun->queue, particularly
sk->sk_wq still points to &sock->wq, which leads to
a UAF.

Reported-and-tested-by: syzbot+6720d64f31c081c2f708@syzkaller.appspotmail.com
Fixes: 28fb4e59a47d ("net: qrtr: Expose tunneling endpoint to user space")
Cc: Bjorn Andersson <bjorn.andersson@linaro.org>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/qrtr/qrtr.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index 14c101e104ce..1ce1e710d025 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -1004,6 +1004,7 @@ static int qrtr_release(struct socket *sock)
 		sk->sk_state_change(sk);
 
 	sock_set_flag(sk, SOCK_DEAD);
+	sock_orphan(sk);
 	sock->sk = NULL;
 
 	if (!sock_flag(sk, SOCK_ZAPPED))
-- 
2.26.2


From e00454ef3984439cdce01ea6e6da7ae93ec947ac Mon Sep 17 00:00:00 2001
From: Weilong Chen <chenweilong@huawei.com>
Date: Wed, 15 Jul 2020 20:58:10 +0800
Subject: [PATCH 19/29] rtnetlink: Fix memory(net_device) leak when ->newlink
 fails

[ Upstream commit cebb69754f37d68e1355a5e726fdac317bcda302 ]

When vlan_newlink call register_vlan_dev fails, it might return error
with dev->reg_state = NETREG_UNREGISTERED. The rtnl_newlink should
free the memory. But currently rtnl_newlink only free the memory which
state is NETREG_UNINITIALIZED.

BUG: memory leak
unreferenced object 0xffff8881051de000 (size 4096):
  comm "syz-executor139", pid 560, jiffies 4294745346 (age 32.445s)
  hex dump (first 32 bytes):
    76 6c 61 6e 32 00 00 00 00 00 00 00 00 00 00 00  vlan2...........
    00 45 28 03 81 88 ff ff 00 00 00 00 00 00 00 00  .E(.............
  backtrace:
    [<0000000047527e31>] kmalloc_node include/linux/slab.h:578 [inline]
    [<0000000047527e31>] kvmalloc_node+0x33/0xd0 mm/util.c:574
    [<000000002b59e3bc>] kvmalloc include/linux/mm.h:753 [inline]
    [<000000002b59e3bc>] kvzalloc include/linux/mm.h:761 [inline]
    [<000000002b59e3bc>] alloc_netdev_mqs+0x83/0xd90 net/core/dev.c:9929
    [<000000006076752a>] rtnl_create_link+0x2c0/0xa20 net/core/rtnetlink.c:3067
    [<00000000572b3be5>] __rtnl_newlink+0xc9c/0x1330 net/core/rtnetlink.c:3329
    [<00000000e84ea553>] rtnl_newlink+0x66/0x90 net/core/rtnetlink.c:3397
    [<0000000052c7c0a9>] rtnetlink_rcv_msg+0x540/0x990 net/core/rtnetlink.c:5460
    [<000000004b5cb379>] netlink_rcv_skb+0x12b/0x3a0 net/netlink/af_netlink.c:2469
    [<00000000c71c20d3>] netlink_unicast_kernel net/netlink/af_netlink.c:1303 [inline]
    [<00000000c71c20d3>] netlink_unicast+0x4c6/0x690 net/netlink/af_netlink.c:1329
    [<00000000cca72fa9>] netlink_sendmsg+0x735/0xcc0 net/netlink/af_netlink.c:1918
    [<000000009221ebf7>] sock_sendmsg_nosec net/socket.c:652 [inline]
    [<000000009221ebf7>] sock_sendmsg+0x109/0x140 net/socket.c:672
    [<000000001c30ffe4>] ____sys_sendmsg+0x5f5/0x780 net/socket.c:2352
    [<00000000b71ca6f3>] ___sys_sendmsg+0x11d/0x1a0 net/socket.c:2406
    [<0000000007297384>] __sys_sendmsg+0xeb/0x1b0 net/socket.c:2439
    [<000000000eb29b11>] do_syscall_64+0x56/0xa0 arch/x86/entry/common.c:359
    [<000000006839b4d0>] entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: cb626bf566eb ("net-sysfs: Fix reference count leak")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Weilong Chen <chenweilong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 944acb1a9f29..b0c06a063776 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3231,7 +3231,8 @@ static int __rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 		 */
 		if (err < 0) {
 			/* If device is not registered at all, free it now */
-			if (dev->reg_state == NETREG_UNINITIALIZED)
+			if (dev->reg_state == NETREG_UNINITIALIZED ||
+			    dev->reg_state == NETREG_UNREGISTERED)
 				free_netdev(dev);
 			goto out;
 		}
-- 
2.26.2


From 1b4d7cdfc3303c46ca40b3c0d1c52a5cce79f666 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 20 Jul 2020 12:41:46 +0100
Subject: [PATCH 20/29] rxrpc: Fix sendmsg() returning EPIPE due to recvmsg()
 returning ENODATA

[ Upstream commit 639f181f0ee20d3249dbc55f740f0167267180f0 ]

rxrpc_sendmsg() returns EPIPE if there's an outstanding error, such as if
rxrpc_recvmsg() indicating ENODATA if there's nothing for it to read.

Change rxrpc_recvmsg() to return EAGAIN instead if there's nothing to read
as this particular error doesn't get stored in ->sk_err by the networking
core.

Also change rxrpc_sendmsg() so that it doesn't fail with delayed receive
errors (there's no way for it to report which call, if any, the error was
caused by).

Fixes: 17926a79320a ("[AF_RXRPC]: Provide secure RxRPC sockets for use by userspace and kernel both")
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/recvmsg.c | 2 +-
 net/rxrpc/sendmsg.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index 8578c39ec839..6896a33ef842 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -464,7 +464,7 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	    list_empty(&rx->recvmsg_q) &&
 	    rx->sk.sk_state != RXRPC_SERVER_LISTENING) {
 		release_sock(&rx->sk);
-		return -ENODATA;
+		return -EAGAIN;
 	}
 
 	if (list_empty(&rx->recvmsg_q)) {
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 5e9c43d4a314..49d03c8c64da 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -306,7 +306,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
 	/* this should be in poll */
 	sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
-	if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
+	if (sk->sk_shutdown & SEND_SHUTDOWN)
 		return -EPIPE;
 
 	more = msg->msg_flags & MSG_MORE;
-- 
2.26.2


From e58402a5a4793df3e8a8f7e5e842cb9e73745d2f Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Thu, 23 Jul 2020 12:00:06 -0700
Subject: [PATCH 21/29] tcp: allow at most one TLP probe per flight

[ Upstream commit 76be93fc0702322179bb0ea87295d820ee46ad14 ]

Previously TLP may send multiple probes of new data in one
flight. This happens when the sender is cwnd limited. After the
initial TLP containing new data is sent, the sender receives another
ACK that acks partial inflight.  It may re-arm another TLP timer
to send more, if no further ACK returns before the next TLP timeout
(PTO) expires. The sender may send in theory a large amount of TLP
until send queue is depleted. This only happens if the sender sees
such irregular uncommon ACK pattern. But it is generally undesirable
behavior during congestion especially.

The original TLP design restrict only one TLP probe per inflight as
published in "Reducing Web Latency: the Virtue of Gentle Aggression",
SIGCOMM 2013. This patch changes TLP to send at most one probe
per inflight.

Note that if the sender is app-limited, TLP retransmits old data
and did not have this issue.

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h   |  4 +++-
 net/ipv4/tcp_input.c  | 11 ++++++-----
 net/ipv4/tcp_output.c | 13 ++++++++-----
 3 files changed, 17 insertions(+), 11 deletions(-)

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 668e25a76d69..358deb4ff830 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -216,6 +216,8 @@ struct tcp_sock {
 	} rack;
 	u16	advmss;		/* Advertised MSS			*/
 	u8	compressed_ack;
+	u8	tlp_retrans:1,	/* TLP is a retransmission */
+		unused_1:7;
 	u32	chrono_start;	/* Start time in jiffies of a TCP chrono */
 	u32	chrono_stat[3];	/* Time in jiffies for chrono_stat stats */
 	u8	chrono_type:2,	/* current chronograph type */
@@ -238,7 +240,7 @@ struct tcp_sock {
 		save_syn:1,	/* Save headers of SYN packet */
 		is_cwnd_limited:1,/* forward progress limited by snd_cwnd? */
 		syn_smc:1;	/* SYN includes SMC */
-	u32	tlp_high_seq;	/* snd_nxt at the time of TLP retransmit. */
+	u32	tlp_high_seq;	/* snd_nxt at the time of TLP */
 
 	u32	tcp_tx_delay;	/* delay (in usec) added to TX packets */
 	u64	tcp_wstamp_ns;	/* departure time for next sent data packet */
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 6d331307beca..5040f7ca37ec 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3505,10 +3505,8 @@ static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq)
 	}
 }
 
-/* This routine deals with acks during a TLP episode.
- * We mark the end of a TLP episode on receiving TLP dupack or when
- * ack is after tlp_high_seq.
- * Ref: loss detection algorithm in draft-dukkipati-tcpm-tcp-loss-probe.
+/* This routine deals with acks during a TLP episode and ends an episode by
+ * resetting tlp_high_seq. Ref: TLP algorithm in draft-ietf-tcpm-rack
  */
 static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag)
 {
@@ -3517,7 +3515,10 @@ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag)
 	if (before(ack, tp->tlp_high_seq))
 		return;
 
-	if (flag & FLAG_DSACKING_ACK) {
+	if (!tp->tlp_retrans) {
+		/* TLP of new data has been acknowledged */
+		tp->tlp_high_seq = 0;
+	} else if (flag & FLAG_DSACKING_ACK) {
 		/* This DSACK means original and TLP probe arrived; no loss */
 		tp->tlp_high_seq = 0;
 	} else if (after(ack, tp->tlp_high_seq)) {
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 5dc7485c4076..4407193bd702 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2564,6 +2564,11 @@ void tcp_send_loss_probe(struct sock *sk)
 	int pcount;
 	int mss = tcp_current_mss(sk);
 
+	/* At most one outstanding TLP */
+	if (tp->tlp_high_seq)
+		goto rearm_timer;
+
+	tp->tlp_retrans = 0;
 	skb = tcp_send_head(sk);
 	if (skb && tcp_snd_wnd_test(tp, skb, mss)) {
 		pcount = tp->packets_out;
@@ -2581,10 +2586,6 @@ void tcp_send_loss_probe(struct sock *sk)
 		return;
 	}
 
-	/* At most one outstanding TLP retransmission. */
-	if (tp->tlp_high_seq)
-		goto rearm_timer;
-
 	if (skb_still_in_host_queue(sk, skb))
 		goto rearm_timer;
 
@@ -2606,10 +2607,12 @@ void tcp_send_loss_probe(struct sock *sk)
 	if (__tcp_retransmit_skb(sk, skb, 1))
 		goto rearm_timer;
 
+	tp->tlp_retrans = 1;
+
+probe_sent:
 	/* Record snd_nxt for loss detection. */
 	tp->tlp_high_seq = tp->snd_nxt;
 
-probe_sent:
 	NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPLOSSPROBES);
 	/* Reset s.t. tcp_rearm_rto will restart timer from now */
 	inet_csk(sk)->icsk_pending = 0;
-- 
2.26.2


From 291a4816b6f970aecc0f13dab3d4f95a6bb6eb1e Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Fri, 10 Jul 2020 14:12:43 +0200
Subject: [PATCH 22/29] vsock/virtio: annotate 'the_virtio_vsock' RCU pointer

[ Upstream commit f961134a612c793d5901a93d85a29337c74af978 ]

Commit 0deab087b16a ("vsock/virtio: use RCU to avoid use-after-free
on the_virtio_vsock") starts to use RCU to protect 'the_virtio_vsock'
pointer, but we forgot to annotate it.

This patch adds the annotation to fix the following sparse errors:

    net/vmw_vsock/virtio_transport.c:73:17: error: incompatible types in comparison expression (different address spaces):
    net/vmw_vsock/virtio_transport.c:73:17:    struct virtio_vsock [noderef] __rcu *
    net/vmw_vsock/virtio_transport.c:73:17:    struct virtio_vsock *
    net/vmw_vsock/virtio_transport.c:171:17: error: incompatible types in comparison expression (different address spaces):
    net/vmw_vsock/virtio_transport.c:171:17:    struct virtio_vsock [noderef] __rcu *
    net/vmw_vsock/virtio_transport.c:171:17:    struct virtio_vsock *
    net/vmw_vsock/virtio_transport.c:207:17: error: incompatible types in comparison expression (different address spaces):
    net/vmw_vsock/virtio_transport.c:207:17:    struct virtio_vsock [noderef] __rcu *
    net/vmw_vsock/virtio_transport.c:207:17:    struct virtio_vsock *
    net/vmw_vsock/virtio_transport.c:561:13: error: incompatible types in comparison expression (different address spaces):
    net/vmw_vsock/virtio_transport.c:561:13:    struct virtio_vsock [noderef] __rcu *
    net/vmw_vsock/virtio_transport.c:561:13:    struct virtio_vsock *
    net/vmw_vsock/virtio_transport.c:612:9: error: incompatible types in comparison expression (different address spaces):
    net/vmw_vsock/virtio_transport.c:612:9:    struct virtio_vsock [noderef] __rcu *
    net/vmw_vsock/virtio_transport.c:612:9:    struct virtio_vsock *
    net/vmw_vsock/virtio_transport.c:631:9: error: incompatible types in comparison expression (different address spaces):
    net/vmw_vsock/virtio_transport.c:631:9:    struct virtio_vsock [noderef] __rcu *
    net/vmw_vsock/virtio_transport.c:631:9:    struct virtio_vsock *

Fixes: 0deab087b16a ("vsock/virtio: use RCU to avoid use-after-free on the_virtio_vsock")
Reported-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/vmw_vsock/virtio_transport.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 082a30936690..861ec9a671f9 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -22,7 +22,7 @@
 #include <net/af_vsock.h>
 
 static struct workqueue_struct *virtio_vsock_workqueue;
-static struct virtio_vsock *the_virtio_vsock;
+static struct virtio_vsock __rcu *the_virtio_vsock;
 static DEFINE_MUTEX(the_virtio_vsock_mutex); /* protects the_virtio_vsock */
 
 struct virtio_vsock {
-- 
2.26.2


From 47c8abfc2fce56f403e1c3f795c4b9dc71c11a98 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Thu, 23 Jul 2020 17:49:57 +0300
Subject: [PATCH 23/29] AX.25: Prevent integer overflows in connect and sendmsg

[ Upstream commit 17ad73e941b71f3bec7523ea4e9cbc3752461c2d ]

We recently added some bounds checking in ax25_connect() and
ax25_sendmsg() and we so we removed the AX25_MAX_DIGIS checks because
they were no longer required.

Unfortunately, I believe they are required to prevent integer overflows
so I have added them back.

Fixes: 8885bb0621f0 ("AX.25: Prevent out-of-bounds read in ax25_sendmsg()")
Fixes: 2f2a7ffad5c6 ("AX.25: Fix out-of-bounds read in ax25_connect()")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ax25/af_ax25.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index dbe7ef2c7e75..2fdb1b573e8c 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1188,6 +1188,7 @@ static int __must_check ax25_connect(struct socket *sock,
 	    fsa->fsa_ax25.sax25_ndigis != 0) {
 		/* Valid number of digipeaters ? */
 		if (fsa->fsa_ax25.sax25_ndigis < 1 ||
+		    fsa->fsa_ax25.sax25_ndigis > AX25_MAX_DIGIS ||
 		    addr_len < sizeof(struct sockaddr_ax25) +
 		    sizeof(ax25_address) * fsa->fsa_ax25.sax25_ndigis) {
 			err = -EINVAL;
@@ -1509,7 +1510,9 @@ static int ax25_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 			struct full_sockaddr_ax25 *fsa = (struct full_sockaddr_ax25 *)usax;
 
 			/* Valid number of digipeaters ? */
-			if (usax->sax25_ndigis < 1 || addr_len < sizeof(struct sockaddr_ax25) +
+			if (usax->sax25_ndigis < 1 ||
+			    usax->sax25_ndigis > AX25_MAX_DIGIS ||
+			    addr_len < sizeof(struct sockaddr_ax25) +
 			    sizeof(ax25_address) * usax->sax25_ndigis) {
 				err = -EINVAL;
 				goto out;
-- 
2.26.2


From c0bf429434950a59841de32a38051c1af1fcd160 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Sat, 11 Jul 2020 20:48:23 -0400
Subject: [PATCH 24/29] bnxt_en: Fix race when modifying pause settings.

[ Upstream commit 163e9ef63641a02de4c95cd921577265c52e1ce2 ]

The driver was modified to not rely on rtnl lock to protect link
settings about 2 years ago.  The pause setting was missed when
making that change.  Fix it by acquiring link_lock mutex before
calling bnxt_hwrm_set_pause().

Fixes: e2dc9b6e38fa ("bnxt_en: Don't use rtnl lock to protect link change logic in workqueue.")
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Reviewed-by: Edwin Peer <edwin.peer@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index fb1ab58da9fa..1f512e7c3d43 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -1688,8 +1688,11 @@ static int bnxt_set_pauseparam(struct net_device *dev,
 	if (epause->tx_pause)
 		link_info->req_flow_ctrl |= BNXT_LINK_PAUSE_TX;
 
-	if (netif_running(dev))
+	if (netif_running(dev)) {
+		mutex_lock(&bp->link_lock);
 		rc = bnxt_hwrm_set_pause(bp);
+		mutex_unlock(&bp->link_lock);
+	}
 	return rc;
 }
 
-- 
2.26.2


From 3846791676fefd55eefbaf12eea17439e0791b3a Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sat, 11 Jul 2020 20:48:25 -0400
Subject: [PATCH 25/29] bnxt_en: Fix completion ring sizing with TPA enabled.

[ Upstream commit 27640ce68d21e556b66bc5fa022aacd26e53c947 ]

The current completion ring sizing formula is wrong with TPA enabled.
The formula assumes that the number of TPA completions are bound by the
RX ring size, but that's not true.  TPA_START completions are immediately
recycled so they are not bound by the RX ring size.  We must add
bp->max_tpa to the worst case maximum RX and TPA completions.

The completion ring can overflow because of this mistake.  This will
cause hardware to disable the completion ring when this happens,
leading to RX and TX traffic to stall on that ring.  This issue is
generally exposed only when the RX ring size is set very small.

Fix the formula by adding bp->max_tpa to the number of RX completions
if TPA is enabled.

Fixes: c0c050c58d84 ("bnxt_en: New Broadcom ethernet driver.");
Reviewed-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index b5147bd6cba6..2cbfe0cd7eef 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -3423,7 +3423,7 @@ void bnxt_set_tpa_flags(struct bnxt *bp)
  */
 void bnxt_set_ring_params(struct bnxt *bp)
 {
-	u32 ring_size, rx_size, rx_space;
+	u32 ring_size, rx_size, rx_space, max_rx_cmpl;
 	u32 agg_factor = 0, agg_ring_size = 0;
 
 	/* 8 for CRC and VLAN */
@@ -3479,7 +3479,15 @@ void bnxt_set_ring_params(struct bnxt *bp)
 	bp->tx_nr_pages = bnxt_calc_nr_ring_pages(ring_size, TX_DESC_CNT);
 	bp->tx_ring_mask = (bp->tx_nr_pages * TX_DESC_CNT) - 1;
 
-	ring_size = bp->rx_ring_size * (2 + agg_factor) + bp->tx_ring_size;
+	max_rx_cmpl = bp->rx_ring_size;
+	/* MAX TPA needs to be added because TPA_START completions are
+	 * immediately recycled, so the TPA completions are not bound by
+	 * the RX ring size.
+	 */
+	if (bp->flags & BNXT_FLAG_TPA)
+		max_rx_cmpl += bp->max_tpa;
+	/* RX and TPA completions are 32-byte, all others are 16-byte */
+	ring_size = max_rx_cmpl * 2 + agg_ring_size + bp->tx_ring_size;
 	bp->cp_ring_size = ring_size;
 
 	bp->cp_nr_pages = bnxt_calc_nr_ring_pages(ring_size, CP_DESC_CNT);
-- 
2.26.2


From 002a2cc4907bca160d878745c73fb1eb4fd9a717 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 22 Jul 2020 23:52:11 +0800
Subject: [PATCH 26/29] sctp: shrink stream outq only when new outcnt < old
 outcnt

[ Upstream commit 8f13399db22f909a35735bf8ae2f932e0c8f0e30 ]

It's not necessary to go list_for_each for outq->out_chunk_list
when new outcnt >= old outcnt, as no chunk with higher sid than
new (outcnt - 1) exists in the outqueue.

While at it, also move the list_for_each code in a new function
sctp_stream_shrink_out(), which will be used in the next patch.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/stream.c | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index c1a100d2fed3..9caa0f6e31bd 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -22,17 +22,11 @@
 #include <net/sctp/sm.h>
 #include <net/sctp/stream_sched.h>
 
-/* Migrates chunks from stream queues to new stream queues if needed,
- * but not across associations. Also, removes those chunks to streams
- * higher than the new max.
- */
-static void sctp_stream_outq_migrate(struct sctp_stream *stream,
-				     struct sctp_stream *new, __u16 outcnt)
+static void sctp_stream_shrink_out(struct sctp_stream *stream, __u16 outcnt)
 {
 	struct sctp_association *asoc;
 	struct sctp_chunk *ch, *temp;
 	struct sctp_outq *outq;
-	int i;
 
 	asoc = container_of(stream, struct sctp_association, stream);
 	outq = &asoc->outqueue;
@@ -56,6 +50,19 @@ static void sctp_stream_outq_migrate(struct sctp_stream *stream,
 
 		sctp_chunk_free(ch);
 	}
+}
+
+/* Migrates chunks from stream queues to new stream queues if needed,
+ * but not across associations. Also, removes those chunks to streams
+ * higher than the new max.
+ */
+static void sctp_stream_outq_migrate(struct sctp_stream *stream,
+				     struct sctp_stream *new, __u16 outcnt)
+{
+	int i;
+
+	if (stream->outcnt > outcnt)
+		sctp_stream_shrink_out(stream, outcnt);
 
 	if (new) {
 		/* Here we actually move the old ext stuff into the new
-- 
2.26.2


From d5741d11e508935775ae51cca227bd0219d0176c Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 22 Jul 2020 23:52:12 +0800
Subject: [PATCH 27/29] sctp: shrink stream outq when fails to do addstream
 reconf

[ Upstream commit 3ecdda3e9ad837cf9cb41b6faa11b1af3a5abc0c ]

When adding a stream with stream reconf, the new stream firstly is in
CLOSED state but new out chunks can still be enqueued. Then once gets
the confirmation from the peer, the state will change to OPEN.

However, if the peer denies, it needs to roll back the stream. But when
doing that, it only sets the stream outcnt back, and the chunks already
in the new stream don't get purged. It caused these chunks can still be
dequeued in sctp_outq_dequeue_data().

As its stream is still in CLOSE, the chunk will be enqueued to the head
again by sctp_outq_head_data(). This chunk will never be sent out, and
the chunks after it can never be dequeued. The assoc will be 'hung' in
a dead loop of sending this chunk.

To fix it, this patch is to purge these chunks already in the new
stream by calling sctp_stream_shrink_out() when failing to do the
addstream reconf.

Fixes: 11ae76e67a17 ("sctp: implement receiver-side procedures for the Reconf Response Parameter")
Reported-by: Ying Xu <yinxu@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/stream.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index 9caa0f6e31bd..e13cbd5c0193 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -1045,11 +1045,13 @@ struct sctp_chunk *sctp_process_strreset_resp(
 		nums = ntohs(addstrm->number_of_streams);
 		number = stream->outcnt - nums;
 
-		if (result == SCTP_STRRESET_PERFORMED)
+		if (result == SCTP_STRRESET_PERFORMED) {
 			for (i = number; i < stream->outcnt; i++)
 				SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN;
-		else
+		} else {
+			sctp_stream_shrink_out(stream, number);
 			stream->outcnt = number;
+		}
 
 		*evp = sctp_ulpevent_make_stream_change_event(asoc, flags,
 			0, nums, GFP_ATOMIC);
-- 
2.26.2


From 2bdb85a960efa65f5759e33a3e924ec6c52da276 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Date: Tue, 21 Jul 2020 15:15:30 +0900
Subject: [PATCH 28/29] udp: Copy has_conns in reuseport_grow().

[ Upstream commit f2b2c55e512879a05456eaf5de4d1ed2f7757509 ]

If an unconnected socket in a UDP reuseport group connect()s, has_conns is
set to 1. Then, when a packet is received, udp[46]_lib_lookup2() scans all
sockets in udp_hslot looking for the connected socket with the highest
score.

However, when the number of sockets bound to the port exceeds max_socks,
reuseport_grow() resets has_conns to 0. It can cause udp[46]_lib_lookup2()
to return without scanning all sockets, resulting in that packets sent to
connected sockets may be distributed to unconnected sockets.

Therefore, reuseport_grow() should copy has_conns.

Fixes: acdcecc61285 ("udp: correct reuseport selection with connected sockets")
CC: Willem de Bruijn <willemb@google.com>
Reviewed-by: Benjamin Herrenschmidt <benh@amazon.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock_reuseport.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index f3ceec93f392..40829111fe00 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -112,6 +112,7 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse)
 	more_reuse->prog = reuse->prog;
 	more_reuse->reuseport_id = reuse->reuseport_id;
 	more_reuse->bind_inany = reuse->bind_inany;
+	more_reuse->has_conns = reuse->has_conns;
 
 	memcpy(more_reuse->socks, reuse->socks,
 	       reuse->num_socks * sizeof(struct sock *));
-- 
2.26.2


From c28e8890eabf77c00c329d9fcbad7dceb749cd03 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Date: Tue, 21 Jul 2020 15:15:31 +0900
Subject: [PATCH 29/29] udp: Improve load balancing for SO_REUSEPORT.

[ Upstream commit efc6b6f6c3113e8b203b9debfb72d81e0f3dcace ]

Currently, SO_REUSEPORT does not work well if connected sockets are in a
UDP reuseport group.

Then reuseport_has_conns() returns true and the result of
reuseport_select_sock() is discarded. Also, unconnected sockets have the
same score, hence only does the first unconnected socket in udp_hslot
always receive all packets sent to unconnected sockets.

So, the result of reuseport_select_sock() should be used for load
balancing.

The noteworthy point is that the unconnected sockets placed after
connected sockets in sock_reuseport.socks will receive more packets than
others because of the algorithm in reuseport_select_sock().

    index | connected | reciprocal_scale | result
    ---------------------------------------------
    0     | no        | 20%              | 40%
    1     | no        | 20%              | 20%
    2     | yes       | 20%              | 0%
    3     | no        | 20%              | 40%
    4     | yes       | 20%              | 0%

If most of the sockets are connected, this can be a problem, but it still
works better than now.

Fixes: acdcecc61285 ("udp: correct reuseport selection with connected sockets")
CC: Willem de Bruijn <willemb@google.com>
Reviewed-by: Benjamin Herrenschmidt <benh@amazon.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 15 +++++++++------
 net/ipv6/udp.c | 15 +++++++++------
 2 files changed, 18 insertions(+), 12 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index b3320e42cbcb..5d016bbdf16e 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -413,7 +413,7 @@ static struct sock *udp4_lib_lookup2(struct net *net,
 				     struct udp_hslot *hslot2,
 				     struct sk_buff *skb)
 {
-	struct sock *sk, *result;
+	struct sock *sk, *result, *reuseport_result;
 	int score, badness;
 	u32 hash = 0;
 
@@ -423,17 +423,20 @@ static struct sock *udp4_lib_lookup2(struct net *net,
 		score = compute_score(sk, net, saddr, sport,
 				      daddr, hnum, dif, sdif);
 		if (score > badness) {
+			reuseport_result = NULL;
+
 			if (sk->sk_reuseport &&
 			    sk->sk_state != TCP_ESTABLISHED) {
 				hash = udp_ehashfn(net, daddr, hnum,
 						   saddr, sport);
-				result = reuseport_select_sock(sk, hash, skb,
-							sizeof(struct udphdr));
-				if (result && !reuseport_has_conns(sk, false))
-					return result;
+				reuseport_result = reuseport_select_sock(sk, hash, skb,
+									 sizeof(struct udphdr));
+				if (reuseport_result && !reuseport_has_conns(sk, false))
+					return reuseport_result;
 			}
+
+			result = reuseport_result ? : sk;
 			badness = score;
-			result = sk;
 		}
 	}
 	return result;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index ede3bed354a8..6762430280f5 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -148,7 +148,7 @@ static struct sock *udp6_lib_lookup2(struct net *net,
 		int dif, int sdif, struct udp_hslot *hslot2,
 		struct sk_buff *skb)
 {
-	struct sock *sk, *result;
+	struct sock *sk, *result, *reuseport_result;
 	int score, badness;
 	u32 hash = 0;
 
@@ -158,17 +158,20 @@ static struct sock *udp6_lib_lookup2(struct net *net,
 		score = compute_score(sk, net, saddr, sport,
 				      daddr, hnum, dif, sdif);
 		if (score > badness) {
+			reuseport_result = NULL;
+
 			if (sk->sk_reuseport &&
 			    sk->sk_state != TCP_ESTABLISHED) {
 				hash = udp6_ehashfn(net, daddr, hnum,
 						    saddr, sport);
 
-				result = reuseport_select_sock(sk, hash, skb,
-							sizeof(struct udphdr));
-				if (result && !reuseport_has_conns(sk, false))
-					return result;
+				reuseport_result = reuseport_select_sock(sk, hash, skb,
+									 sizeof(struct udphdr));
+				if (reuseport_result && !reuseport_has_conns(sk, false))
+					return reuseport_result;
 			}
-			result = sk;
+
+			result = reuseport_result ? : sk;
 			badness = score;
 		}
 	}
-- 
2.26.2


[-- Attachment #3: net_57.mbox --]
[-- Type: Application/Octet-Stream, Size: 90578 bytes --]

From be21fa2c4f0e243a6c5c074c00738e8ac789ace4 Mon Sep 17 00:00:00 2001
From: Peilin Ye <yepeilin.cs@gmail.com>
Date: Wed, 22 Jul 2020 11:19:01 -0400
Subject: [PATCH 01/38] AX.25: Fix out-of-bounds read in ax25_connect()

[ Upstream commit 2f2a7ffad5c6cbf3d438e813cfdc88230e185ba6 ]

Checks on `addr_len` and `fsa->fsa_ax25.sax25_ndigis` are insufficient.
ax25_connect() can go out of bounds when `fsa->fsa_ax25.sax25_ndigis`
equals to 7 or 8. Fix it.

This issue has been reported as a KMSAN uninit-value bug, because in such
a case, ax25_connect() reaches into the uninitialized portion of the
`struct sockaddr_storage` statically allocated in __sys_connect().

It is safe to remove `fsa->fsa_ax25.sax25_ndigis > AX25_MAX_DIGIS` because
`addr_len` is guaranteed to be less than or equal to
`sizeof(struct full_sockaddr_ax25)`.

Reported-by: syzbot+c82752228ed975b0a623@syzkaller.appspotmail.com
Link: https://syzkaller.appspot.com/bug?id=55ef9d629f3b3d7d70b69558015b63b48d01af66
Signed-off-by: Peilin Ye <yepeilin.cs@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ax25/af_ax25.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index fd91cd34f25e..ef5bf116157a 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1187,7 +1187,9 @@ static int __must_check ax25_connect(struct socket *sock,
 	if (addr_len > sizeof(struct sockaddr_ax25) &&
 	    fsa->fsa_ax25.sax25_ndigis != 0) {
 		/* Valid number of digipeaters ? */
-		if (fsa->fsa_ax25.sax25_ndigis < 1 || fsa->fsa_ax25.sax25_ndigis > AX25_MAX_DIGIS) {
+		if (fsa->fsa_ax25.sax25_ndigis < 1 ||
+		    addr_len < sizeof(struct sockaddr_ax25) +
+		    sizeof(ax25_address) * fsa->fsa_ax25.sax25_ndigis) {
 			err = -EINVAL;
 			goto out_release;
 		}
-- 
2.26.2


From 6999fe36a7e4deabefd0112d3cc12272ccd3ee47 Mon Sep 17 00:00:00 2001
From: Peilin Ye <yepeilin.cs@gmail.com>
Date: Wed, 22 Jul 2020 12:05:12 -0400
Subject: [PATCH 02/38] AX.25: Prevent out-of-bounds read in ax25_sendmsg()

[ Upstream commit 8885bb0621f01a6c82be60a91e5fc0f6e2f71186 ]

Checks on `addr_len` and `usax->sax25_ndigis` are insufficient.
ax25_sendmsg() can go out of bounds when `usax->sax25_ndigis` equals to 7
or 8. Fix it.

It is safe to remove `usax->sax25_ndigis > AX25_MAX_DIGIS`, since
`addr_len` is guaranteed to be less than or equal to
`sizeof(struct full_sockaddr_ax25)`

Signed-off-by: Peilin Ye <yepeilin.cs@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ax25/af_ax25.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index ef5bf116157a..0862fe49d434 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1509,7 +1509,8 @@ static int ax25_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 			struct full_sockaddr_ax25 *fsa = (struct full_sockaddr_ax25 *)usax;
 
 			/* Valid number of digipeaters ? */
-			if (usax->sax25_ndigis < 1 || usax->sax25_ndigis > AX25_MAX_DIGIS) {
+			if (usax->sax25_ndigis < 1 || addr_len < sizeof(struct sockaddr_ax25) +
+			    sizeof(ax25_address) * usax->sax25_ndigis) {
 				err = -EINVAL;
 				goto out;
 			}
-- 
2.26.2


From ecf3614ef76a57f24a08fb7748a9115a65fd6942 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Sun, 19 Jul 2020 12:11:24 +0000
Subject: [PATCH 03/38] bonding: check error value of register_netdevice()
 immediately

[ Upstream commit 544f287b84959203367cd29e16e772717612fab4 ]

If register_netdevice() is failed, net_device should not be used
because variables are uninitialized or freed.
So, the routine should be stopped immediately.
But, bond_create() doesn't check return value of register_netdevice()
immediately. That will result in a panic because of using uninitialized
or freed memory.

Test commands:
    modprobe netdev-notifier-error-inject
    echo -22 > /sys/kernel/debug/notifier-error-inject/netdev/\
actions/NETDEV_REGISTER/error
    modprobe bonding max_bonds=3

Splat looks like:
[  375.028492][  T193] general protection fault, probably for non-canonical address 0x6b6b6b6b6b6b6b6b: 0000 [#1] SMP DEBUG_PAGEALLOC PTI
[  375.033207][  T193] CPU: 2 PID: 193 Comm: kworker/2:2 Not tainted 5.8.0-rc4+ #645
[  375.036068][  T193] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014
[  375.039673][  T193] Workqueue: events linkwatch_event
[  375.041557][  T193] RIP: 0010:dev_activate+0x4a/0x340
[  375.043381][  T193] Code: 40 a8 04 0f 85 db 00 00 00 8b 83 08 04 00 00 85 c0 0f 84 0d 01 00 00 31 d2 89 d0 48 8d 04 40 48 c1 e0 07 48 03 83 00 04 00 00 <48> 8b 48 10 f6 41 10 01 75 08 f0 80 a1 a0 01 00 00 fd 48 89 48 08
[  375.050267][  T193] RSP: 0018:ffff9f8facfcfdd8 EFLAGS: 00010202
[  375.052410][  T193] RAX: 6b6b6b6b6b6b6b6b RBX: ffff9f8fae6ea000 RCX: 0000000000000006
[  375.055178][  T193] RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff9f8fae6ea000
[  375.057762][  T193] RBP: ffff9f8fae6ea000 R08: 0000000000000000 R09: 0000000000000000
[  375.059810][  T193] R10: 0000000000000001 R11: 0000000000000000 R12: ffff9f8facfcfe08
[  375.061892][  T193] R13: ffffffff883587e0 R14: 0000000000000000 R15: ffff9f8fae6ea580
[  375.063931][  T193] FS:  0000000000000000(0000) GS:ffff9f8fbae00000(0000) knlGS:0000000000000000
[  375.066239][  T193] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  375.067841][  T193] CR2: 00007f2f542167a0 CR3: 000000012cee6002 CR4: 00000000003606e0
[  375.069657][  T193] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  375.071471][  T193] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[  375.073269][  T193] Call Trace:
[  375.074005][  T193]  linkwatch_do_dev+0x4d/0x50
[  375.075052][  T193]  __linkwatch_run_queue+0x10b/0x200
[  375.076244][  T193]  linkwatch_event+0x21/0x30
[  375.077274][  T193]  process_one_work+0x252/0x600
[  375.078379][  T193]  ? process_one_work+0x600/0x600
[  375.079518][  T193]  worker_thread+0x3c/0x380
[  375.080534][  T193]  ? process_one_work+0x600/0x600
[  375.081668][  T193]  kthread+0x139/0x150
[  375.082567][  T193]  ? kthread_park+0x90/0x90
[  375.083567][  T193]  ret_from_fork+0x22/0x30

Fixes: e826eafa65c6 ("bonding: Call netif_carrier_off after register_netdevice")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 2e70e43c5df5..6b40b5ab143a 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -4953,15 +4953,19 @@ int bond_create(struct net *net, const char *name)
 	bond_dev->rtnl_link_ops = &bond_link_ops;
 
 	res = register_netdevice(bond_dev);
+	if (res < 0) {
+		free_netdev(bond_dev);
+		rtnl_unlock();
+
+		return res;
+	}
 
 	netif_carrier_off(bond_dev);
 
 	bond_work_init_all(bond);
 
 	rtnl_unlock();
-	if (res < 0)
-		free_netdev(bond_dev);
-	return res;
+	return 0;
 }
 
 static int __net_init bond_net_init(struct net *net)
-- 
2.26.2


From 0625bac66f701327391b3196f42a3e6ae225c811 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Wed, 22 Jul 2020 16:31:54 -0700
Subject: [PATCH 04/38] bonding: check return value of register_netdevice() in
 bond_newlink()

[ Upstream commit c75d1d5248c0c97996051809ad0e9f154ba5d76e ]

Very similar to commit 544f287b8495
("bonding: check error value of register_netdevice() immediately"),
we should immediately check the return value of register_netdevice()
before doing anything else.

Fixes: 005db31d5f5f ("bonding: set carrier off for devices created through netlink")
Reported-and-tested-by: syzbot+bbc3a11c4da63c1b74d6@syzkaller.appspotmail.com
Cc: Beniamino Galvani <bgalvani@redhat.com>
Cc: Taehee Yoo <ap420073@gmail.com>
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_netlink.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index b43b51646b11..f0f9138e967f 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -456,11 +456,10 @@ static int bond_newlink(struct net *src_net, struct net_device *bond_dev,
 		return err;
 
 	err = register_netdevice(bond_dev);
-
-	netif_carrier_off(bond_dev);
 	if (!err) {
 		struct bonding *bond = netdev_priv(bond_dev);
 
+		netif_carrier_off(bond_dev);
 		bond_work_init_all(bond);
 	}
 
-- 
2.26.2


From 075c36c472679d325fe5784637a68aa0e74d30d3 Mon Sep 17 00:00:00 2001
From: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Date: Thu, 23 Jul 2020 11:31:48 -0600
Subject: [PATCH 05/38] dev: Defer free of skbs in flush_backlog

[ Upstream commit 7df5cb75cfb8acf96c7f2342530eb41e0c11f4c3 ]

IRQs are disabled when freeing skbs in input queue.
Use the IRQ safe variant to free skbs here.

Fixes: 145dd5f9c88f ("net: flush the softnet backlog in process context")
Signed-off-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index c9ee5d80d5ea..c1c2688a955c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5504,7 +5504,7 @@ static void flush_backlog(struct work_struct *work)
 	skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) {
 		if (skb->dev->reg_state == NETREG_UNREGISTERING) {
 			__skb_unlink(skb, &sd->input_pkt_queue);
-			kfree_skb(skb);
+			dev_kfree_skb_irq(skb);
 			input_queue_head_incr(sd);
 		}
 	}
-- 
2.26.2


From 20773c9cf3a384df99a4e958dc9a2059db3db088 Mon Sep 17 00:00:00 2001
From: Xie He <xie.he.0141@gmail.com>
Date: Thu, 16 Jul 2020 16:44:33 -0700
Subject: [PATCH 06/38] drivers/net/wan/x25_asy: Fix to make it work

[ Upstream commit 8fdcabeac39824fe67480fd9508d80161c541854 ]

This driver is not working because of problems of its receiving code.
This patch fixes it to make it work.

When the driver receives an LAPB frame, it should first pass the frame
to the LAPB module to process. After processing, the LAPB module passes
the data (the packet) back to the driver, the driver should then add a
one-byte pseudo header and pass the data to upper layers.

The changes to the "x25_asy_bump" function and the
"x25_asy_data_indication" function are to correctly implement this
procedure.

Also, the "x25_asy_unesc" function ignores any frame that is shorter
than 3 bytes. However the shortest frames are 2-byte long. So we need
to change it to allow 2-byte frames to pass.

Cc: Eric Dumazet <edumazet@google.com>
Cc: Martin Schiller <ms@dev.tdt.de>
Signed-off-by: Xie He <xie.he.0141@gmail.com>
Reviewed-by: Martin Schiller <ms@dev.tdt.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wan/x25_asy.c | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wan/x25_asy.c b/drivers/net/wan/x25_asy.c
index 69773d228ec1..84640a0c13f3 100644
--- a/drivers/net/wan/x25_asy.c
+++ b/drivers/net/wan/x25_asy.c
@@ -183,7 +183,7 @@ static inline void x25_asy_unlock(struct x25_asy *sl)
 	netif_wake_queue(sl->dev);
 }
 
-/* Send one completely decapsulated IP datagram to the IP layer. */
+/* Send an LAPB frame to the LAPB module to process. */
 
 static void x25_asy_bump(struct x25_asy *sl)
 {
@@ -195,13 +195,12 @@ static void x25_asy_bump(struct x25_asy *sl)
 	count = sl->rcount;
 	dev->stats.rx_bytes += count;
 
-	skb = dev_alloc_skb(count+1);
+	skb = dev_alloc_skb(count);
 	if (skb == NULL) {
 		netdev_warn(sl->dev, "memory squeeze, dropping packet\n");
 		dev->stats.rx_dropped++;
 		return;
 	}
-	skb_push(skb, 1);	/* LAPB internal control */
 	skb_put_data(skb, sl->rbuff, count);
 	skb->protocol = x25_type_trans(skb, sl->dev);
 	err = lapb_data_received(skb->dev, skb);
@@ -209,7 +208,6 @@ static void x25_asy_bump(struct x25_asy *sl)
 		kfree_skb(skb);
 		printk(KERN_DEBUG "x25_asy: data received err - %d\n", err);
 	} else {
-		netif_rx(skb);
 		dev->stats.rx_packets++;
 	}
 }
@@ -356,12 +354,21 @@ static netdev_tx_t x25_asy_xmit(struct sk_buff *skb,
  */
 
 /*
- *	Called when I frame data arrives. We did the work above - throw it
- *	at the net layer.
+ *	Called when I frame data arrive. We add a pseudo header for upper
+ *	layers and pass it to upper layers.
  */
 
 static int x25_asy_data_indication(struct net_device *dev, struct sk_buff *skb)
 {
+	if (skb_cow(skb, 1)) {
+		kfree_skb(skb);
+		return NET_RX_DROP;
+	}
+	skb_push(skb, 1);
+	skb->data[0] = X25_IFACE_DATA;
+
+	skb->protocol = x25_type_trans(skb, dev);
+
 	return netif_rx(skb);
 }
 
@@ -657,7 +664,7 @@ static void x25_asy_unesc(struct x25_asy *sl, unsigned char s)
 	switch (s) {
 	case X25_END:
 		if (!test_and_clear_bit(SLF_ERROR, &sl->flags) &&
-		    sl->rcount > 2)
+		    sl->rcount >= 2)
 			x25_asy_bump(sl);
 		clear_bit(SLF_ESCAPE, &sl->flags);
 		sl->rcount = 0;
-- 
2.26.2


From bc71d0219402da4fcd147bd9fc452b6c338d767a Mon Sep 17 00:00:00 2001
From: Claudiu Manoil <claudiu.manoil@nxp.com>
Date: Wed, 22 Jul 2020 17:40:12 +0300
Subject: [PATCH 07/38] enetc: Remove the mdio bus on PF probe bailout

[ Upstream commit 26cb7085c8984e5b71d65c374a135134ed8cabb3 ]

For ENETC ports that register an external MDIO bus,
the bus doesn't get removed on the error bailout path
of enetc_pf_probe().

This issue became much more visible after recent:
commit 07095c025ac2 ("net: enetc: Use DT protocol information to set up the ports")
Before this commit, one could make probing fail on the error
path only by having register_netdev() fail, which is unlikely.
But after this commit, because it moved the enetc_of_phy_get()
call up in the probing sequence, now we can trigger an mdiobus_free()
bug just by forcing enetc_alloc_msix() to return error, i.e. with the
'pci=nomsi' kernel bootarg (since ENETC relies on MSI support to work),
as the calltrace below shows:

kernel BUG at /home/eiz/work/enetc/net/drivers/net/phy/mdio_bus.c:648!
Internal error: Oops - BUG: 0 [#1] PREEMPT SMP
[...]
Hardware name: LS1028A RDB Board (DT)
pstate: 80000005 (Nzcv daif -PAN -UAO BTYPE=--)
pc : mdiobus_free+0x50/0x58
lr : devm_mdiobus_free+0x14/0x20
[...]
Call trace:
 mdiobus_free+0x50/0x58
 devm_mdiobus_free+0x14/0x20
 release_nodes+0x138/0x228
 devres_release_all+0x38/0x60
 really_probe+0x1c8/0x368
 driver_probe_device+0x5c/0xc0
 device_driver_attach+0x74/0x80
 __driver_attach+0x8c/0xd8
 bus_for_each_dev+0x7c/0xd8
 driver_attach+0x24/0x30
 bus_add_driver+0x154/0x200
 driver_register+0x64/0x120
 __pci_register_driver+0x44/0x50
 enetc_pf_driver_init+0x24/0x30
 do_one_initcall+0x60/0x1c0
 kernel_init_freeable+0x1fc/0x274
 kernel_init+0x14/0x110
 ret_from_fork+0x10/0x34

Fixes: ebfcb23d62ab ("enetc: Add ENETC PF level external MDIO support")
Signed-off-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/enetc/enetc_pf.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
index 438648a06f2a..041e19895adf 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -919,6 +919,7 @@ static int enetc_pf_probe(struct pci_dev *pdev,
 	return 0;
 
 err_reg_netdev:
+	enetc_mdio_remove(pf);
 	enetc_of_put_phy(priv);
 	enetc_free_msix(priv);
 err_alloc_msix:
-- 
2.26.2


From de1244501c205619fb7066f152beee536f725d25 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Wed, 22 Jul 2020 18:56:25 -0700
Subject: [PATCH 08/38] geneve: fix an uninitialized value in
 geneve_changelink()

[ Upstream commit 32818c075c54bb0cae44dd6f7ab00b01c52b8372 ]

geneve_nl2info() sets 'df' conditionally, so we have to
initialize it by copying the value from existing geneve
device in geneve_changelink().

Fixes: 56c09de347e4 ("geneve: allow changing DF behavior after creation")
Reported-by: syzbot+7ebc2e088af5e4c0c9fa@syzkaller.appspotmail.com
Cc: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 4661ef865807..dec52b763d50 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1615,11 +1615,11 @@ static int geneve_changelink(struct net_device *dev, struct nlattr *tb[],
 			     struct netlink_ext_ack *extack)
 {
 	struct geneve_dev *geneve = netdev_priv(dev);
+	enum ifla_geneve_df df = geneve->df;
 	struct geneve_sock *gs4, *gs6;
 	struct ip_tunnel_info info;
 	bool metadata;
 	bool use_udp6_rx_checksums;
-	enum ifla_geneve_df df;
 	bool ttl_inherit;
 	int err;
 
-- 
2.26.2


From 90628d26a93f8c7b4235711d42830d4581fa0e41 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Tue, 14 Jul 2020 13:00:27 +0200
Subject: [PATCH 09/38] hippi: Fix a size used in a 'pci_free_consistent()' in
 an error handling path

[ Upstream commit 3195c4706b00106aa82c73acd28340fa8fc2bfc1 ]

The size used when calling 'pci_alloc_consistent()' and
'pci_free_consistent()' should match.

Fix it and have it consistent with the corresponding call in 'rr_close()'.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hippi/rrunner.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/hippi/rrunner.c b/drivers/net/hippi/rrunner.c
index 2a6ec5394966..a4b3fce69ecd 100644
--- a/drivers/net/hippi/rrunner.c
+++ b/drivers/net/hippi/rrunner.c
@@ -1242,7 +1242,7 @@ static int rr_open(struct net_device *dev)
 		rrpriv->info = NULL;
 	}
 	if (rrpriv->rx_ctrl) {
-		pci_free_consistent(pdev, sizeof(struct ring_ctrl),
+		pci_free_consistent(pdev, 256 * sizeof(struct ring_ctrl),
 				    rrpriv->rx_ctrl, rrpriv->rx_ctrl_dma);
 		rrpriv->rx_ctrl = NULL;
 	}
-- 
2.26.2


From 644b5e31ac816548e54c069886bd60b42f843f13 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Mon, 13 Jul 2020 23:59:50 +0800
Subject: [PATCH 10/38] ip6_gre: fix null-ptr-deref in ip6gre_init_net()

[ Upstream commit 46ef5b89ec0ecf290d74c4aee844f063933c4da4 ]

KASAN report null-ptr-deref error when register_netdev() failed:

KASAN: null-ptr-deref in range [0x00000000000003c0-0x00000000000003c7]
CPU: 2 PID: 422 Comm: ip Not tainted 5.8.0-rc4+ #12
Call Trace:
 ip6gre_init_net+0x4ab/0x580
 ? ip6gre_tunnel_uninit+0x3f0/0x3f0
 ops_init+0xa8/0x3c0
 setup_net+0x2de/0x7e0
 ? rcu_read_lock_bh_held+0xb0/0xb0
 ? ops_init+0x3c0/0x3c0
 ? kasan_unpoison_shadow+0x33/0x40
 ? __kasan_kmalloc.constprop.0+0xc2/0xd0
 copy_net_ns+0x27d/0x530
 create_new_namespaces+0x382/0xa30
 unshare_nsproxy_namespaces+0xa1/0x1d0
 ksys_unshare+0x39c/0x780
 ? walk_process_tree+0x2a0/0x2a0
 ? trace_hardirqs_on+0x4a/0x1b0
 ? _raw_spin_unlock_irq+0x1f/0x30
 ? syscall_trace_enter+0x1a7/0x330
 ? do_syscall_64+0x1c/0xa0
 __x64_sys_unshare+0x2d/0x40
 do_syscall_64+0x56/0xa0
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

ip6gre_tunnel_uninit() has set 'ign->fb_tunnel_dev' to NULL, later
access to ign->fb_tunnel_dev cause null-ptr-deref. Fix it by saving
'ign->fb_tunnel_dev' to local variable ndev.

Fixes: dafabb6590cb ("ip6_gre: fix use-after-free in ip6gre_tunnel_lookup()")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 6532bde82b40..3a57fb9ce049 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1562,17 +1562,18 @@ static void ip6gre_destroy_tunnels(struct net *net, struct list_head *head)
 static int __net_init ip6gre_init_net(struct net *net)
 {
 	struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
+	struct net_device *ndev;
 	int err;
 
 	if (!net_has_fallback_tunnels(net))
 		return 0;
-	ign->fb_tunnel_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6gre0",
-					  NET_NAME_UNKNOWN,
-					  ip6gre_tunnel_setup);
-	if (!ign->fb_tunnel_dev) {
+	ndev = alloc_netdev(sizeof(struct ip6_tnl), "ip6gre0",
+			    NET_NAME_UNKNOWN, ip6gre_tunnel_setup);
+	if (!ndev) {
 		err = -ENOMEM;
 		goto err_alloc_dev;
 	}
+	ign->fb_tunnel_dev = ndev;
 	dev_net_set(ign->fb_tunnel_dev, net);
 	/* FB netdevice is special: we have one, and only one per netns.
 	 * Allowing to move it to another netns is clearly unsafe.
@@ -1592,7 +1593,7 @@ static int __net_init ip6gre_init_net(struct net *net)
 	return 0;
 
 err_reg_dev:
-	free_netdev(ign->fb_tunnel_dev);
+	free_netdev(ndev);
 err_alloc_dev:
 	return err;
 }
-- 
2.26.2


From 14dc90ff4de0810b35b1a4f42244a1eefaa208eb Mon Sep 17 00:00:00 2001
From: Liu Jian <liujian56@huawei.com>
Date: Mon, 20 Jul 2020 22:31:49 +0800
Subject: [PATCH 11/38] mlxsw: destroy workqueue when trap_register in
 mlxsw_emad_init

[ Upstream commit 5dbaeb87f2b309936be0aeae00cbc9e7f20ab296 ]

When mlxsw_core_trap_register fails in mlxsw_emad_init,
destroy_workqueue() shouled be called to destroy mlxsw_core->emad_wq.

Fixes: d965465b60ba ("mlxsw: core: Fix possible deadlock")
Signed-off-by: Liu Jian <liujian56@huawei.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index e9ccd333f61d..d6d6fe64887b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -710,7 +710,7 @@ static int mlxsw_emad_init(struct mlxsw_core *mlxsw_core)
 	err = mlxsw_core_trap_register(mlxsw_core, &mlxsw_emad_rx_listener,
 				       mlxsw_core);
 	if (err)
-		return err;
+		goto err_trap_register;
 
 	err = mlxsw_core->driver->basic_trap_groups_set(mlxsw_core);
 	if (err)
@@ -722,6 +722,7 @@ static int mlxsw_emad_init(struct mlxsw_core *mlxsw_core)
 err_emad_trap_set:
 	mlxsw_core_trap_unregister(mlxsw_core, &mlxsw_emad_rx_listener,
 				   mlxsw_core);
+err_trap_register:
 	destroy_workqueue(mlxsw_core->emad_wq);
 	return err;
 }
-- 
2.26.2


From 39f6ce30a0cf185840255683d6d53a70377c00ed Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Tue, 21 Jul 2020 14:51:50 +0000
Subject: [PATCH 12/38] netdevsim: fix unbalaced locking in nsim_create()

[ Upstream commit 2c9d8e01f0c6017317eee7638496173d4a64e6bc ]

In the nsim_create(), rtnl_lock() is called before nsim_bpf_init().
If nsim_bpf_init() is failed, rtnl_unlock() should be called,
but it isn't called.
So, unbalanced locking would occur.

Fixes: e05b2d141fef ("netdevsim: move netdev creation/destruction to dev probe")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/netdevsim/netdev.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index 2908e0a0d6e1..23950e7a0f81 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -302,7 +302,7 @@ nsim_create(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port)
 	rtnl_lock();
 	err = nsim_bpf_init(ns);
 	if (err)
-		goto err_free_netdev;
+		goto err_rtnl_unlock;
 
 	nsim_ipsec_init(ns);
 
@@ -316,8 +316,8 @@ nsim_create(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port)
 err_ipsec_teardown:
 	nsim_ipsec_teardown(ns);
 	nsim_bpf_uninit(ns);
+err_rtnl_unlock:
 	rtnl_unlock();
-err_free_netdev:
 	free_netdev(dev);
 	return ERR_PTR(err);
 }
-- 
2.26.2


From 726ccd27fc53cdd0a1d66feb5b47c6908fd3a8d1 Mon Sep 17 00:00:00 2001
From: Helmut Grohne <helmut.grohne@intenta.de>
Date: Tue, 21 Jul 2020 13:07:39 +0200
Subject: [PATCH 13/38] net: dsa: microchip: call phy_remove_link_mode during
 probe

[ Upstream commit 3506b2f42dff66ea6814c3dfa1988bafb79e6f88 ]

When doing "ip link set dev ... up" for a ksz9477 backed link,
ksz9477_phy_setup is called and it calls phy_remove_link_mode to remove
1000baseT HDX. During phy_remove_link_mode, phy_advertise_supported is
called. Doing so reverts any previous change to advertised link modes
e.g. using a udevd .link file.

phy_remove_link_mode is not meant to be used while opening a link and
should be called during phy probe when the link is not yet available to
userspace.

Therefore move the phy_remove_link_mode calls into
ksz9477_switch_register. It indirectly calls dsa_register_switch, which
creates the relevant struct phy_devices and we update the link modes
right after that. At that time dev->features is already initialized by
ksz9477_switch_detect.

Remove phy_setup from ksz_dev_ops as no users remain.

Link: https://lore.kernel.org/netdev/20200715192722.GD1256692@lunn.ch/
Fixes: 42fc6a4c613019 ("net: dsa: microchip: prepare PHY for proper advertisement")
Signed-off-by: Helmut Grohne <helmut.grohne@intenta.de>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/microchip/ksz9477.c    | 42 ++++++++++++++------------
 drivers/net/dsa/microchip/ksz_common.c |  2 --
 drivers/net/dsa/microchip/ksz_common.h |  2 --
 3 files changed, 23 insertions(+), 23 deletions(-)

diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c
index 65701e65b6c2..95a406e2e373 100644
--- a/drivers/net/dsa/microchip/ksz9477.c
+++ b/drivers/net/dsa/microchip/ksz9477.c
@@ -977,23 +977,6 @@ static void ksz9477_port_mirror_del(struct dsa_switch *ds, int port,
 			     PORT_MIRROR_SNIFFER, false);
 }
 
-static void ksz9477_phy_setup(struct ksz_device *dev, int port,
-			      struct phy_device *phy)
-{
-	/* Only apply to port with PHY. */
-	if (port >= dev->phy_port_cnt)
-		return;
-
-	/* The MAC actually cannot run in 1000 half-duplex mode. */
-	phy_remove_link_mode(phy,
-			     ETHTOOL_LINK_MODE_1000baseT_Half_BIT);
-
-	/* PHY does not support gigabit. */
-	if (!(dev->features & GBIT_SUPPORT))
-		phy_remove_link_mode(phy,
-				     ETHTOOL_LINK_MODE_1000baseT_Full_BIT);
-}
-
 static bool ksz9477_get_gbit(struct ksz_device *dev, u8 data)
 {
 	bool gbit;
@@ -1606,7 +1589,6 @@ static const struct ksz_dev_ops ksz9477_dev_ops = {
 	.get_port_addr = ksz9477_get_port_addr,
 	.cfg_port_member = ksz9477_cfg_port_member,
 	.flush_dyn_mac_table = ksz9477_flush_dyn_mac_table,
-	.phy_setup = ksz9477_phy_setup,
 	.port_setup = ksz9477_port_setup,
 	.r_mib_cnt = ksz9477_r_mib_cnt,
 	.r_mib_pkt = ksz9477_r_mib_pkt,
@@ -1620,7 +1602,29 @@ static const struct ksz_dev_ops ksz9477_dev_ops = {
 
 int ksz9477_switch_register(struct ksz_device *dev)
 {
-	return ksz_switch_register(dev, &ksz9477_dev_ops);
+	int ret, i;
+	struct phy_device *phydev;
+
+	ret = ksz_switch_register(dev, &ksz9477_dev_ops);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < dev->phy_port_cnt; ++i) {
+		if (!dsa_is_user_port(dev->ds, i))
+			continue;
+
+		phydev = dsa_to_port(dev->ds, i)->slave->phydev;
+
+		/* The MAC actually cannot run in 1000 half-duplex mode. */
+		phy_remove_link_mode(phydev,
+				     ETHTOOL_LINK_MODE_1000baseT_Half_BIT);
+
+		/* PHY does not support gigabit. */
+		if (!(dev->features & GBIT_SUPPORT))
+			phy_remove_link_mode(phydev,
+					     ETHTOOL_LINK_MODE_1000baseT_Full_BIT);
+	}
+	return ret;
 }
 EXPORT_SYMBOL(ksz9477_switch_register);
 
diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index fd1d6676ae4f..7b6c0dce7536 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -358,8 +358,6 @@ int ksz_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy)
 
 	/* setup slave port */
 	dev->dev_ops->port_setup(dev, port, false);
-	if (dev->dev_ops->phy_setup)
-		dev->dev_ops->phy_setup(dev, port, phy);
 
 	/* port_stp_state_set() will be called after to enable the port so
 	 * there is no need to do anything.
diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h
index f2c9bb68fd33..7d11dd32ec0d 100644
--- a/drivers/net/dsa/microchip/ksz_common.h
+++ b/drivers/net/dsa/microchip/ksz_common.h
@@ -119,8 +119,6 @@ struct ksz_dev_ops {
 	u32 (*get_port_addr)(int port, int offset);
 	void (*cfg_port_member)(struct ksz_device *dev, int port, u8 member);
 	void (*flush_dyn_mac_table)(struct ksz_device *dev, int port);
-	void (*phy_setup)(struct ksz_device *dev, int port,
-			  struct phy_device *phy);
 	void (*port_cleanup)(struct ksz_device *dev, int port);
 	void (*port_setup)(struct ksz_device *dev, int port, bool cpu_port);
 	void (*r_phy)(struct ksz_device *dev, u16 phy, u16 reg, u16 *val);
-- 
2.26.2


From d4ee856122ae8dd647471168d1a1f033fdf0fd94 Mon Sep 17 00:00:00 2001
From: wenxu <wenxu@ucloud.cn>
Date: Sun, 19 Jul 2020 20:30:37 +0800
Subject: [PATCH 14/38] net/sched: act_ct: fix restore the qdisc_skb_cb after
 defrag

[ Upstream commit ae372cb1750f6c95370f92fe5f5620e0954663ba ]

The fragment packets do defrag in tcf_ct_handle_fragments
will clear the skb->cb which make the qdisc_skb_cb clear
too. So the qdsic_skb_cb should be store before defrag and
restore after that.
It also update the pkt_len after all the
fragments finish the defrag to one packet and make the
following actions counter correct.

Fixes: b57dc7c13ea9 ("net/sched: Introduce action ct")
Signed-off-by: wenxu <wenxu@ucloud.cn>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ct.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index 6a114f80e54b..e191f2728389 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -671,9 +671,10 @@ static int tcf_ct_ipv6_is_fragment(struct sk_buff *skb, bool *frag)
 }
 
 static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
-				   u8 family, u16 zone)
+				   u8 family, u16 zone, bool *defrag)
 {
 	enum ip_conntrack_info ctinfo;
+	struct qdisc_skb_cb cb;
 	struct nf_conn *ct;
 	int err = 0;
 	bool frag;
@@ -691,6 +692,7 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
 		return err;
 
 	skb_get(skb);
+	cb = *qdisc_skb_cb(skb);
 
 	if (family == NFPROTO_IPV4) {
 		enum ip_defrag_users user = IP_DEFRAG_CONNTRACK_IN + zone;
@@ -701,6 +703,9 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
 		local_bh_enable();
 		if (err && err != -EINPROGRESS)
 			goto out_free;
+
+		if (!err)
+			*defrag = true;
 	} else { /* NFPROTO_IPV6 */
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
 		enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone;
@@ -709,12 +714,16 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
 		err = nf_ct_frag6_gather(net, skb, user);
 		if (err && err != -EINPROGRESS)
 			goto out_free;
+
+		if (!err)
+			*defrag = true;
 #else
 		err = -EOPNOTSUPP;
 		goto out_free;
 #endif
 	}
 
+	*qdisc_skb_cb(skb) = cb;
 	skb_clear_hash(skb);
 	skb->ignore_df = 1;
 	return err;
@@ -912,6 +921,7 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a,
 	int nh_ofs, err, retval;
 	struct tcf_ct_params *p;
 	bool skip_add = false;
+	bool defrag = false;
 	struct nf_conn *ct;
 	u8 family;
 
@@ -942,7 +952,7 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a,
 	 */
 	nh_ofs = skb_network_offset(skb);
 	skb_pull_rcsum(skb, nh_ofs);
-	err = tcf_ct_handle_fragments(net, skb, family, p->zone);
+	err = tcf_ct_handle_fragments(net, skb, family, p->zone, &defrag);
 	if (err == -EINPROGRESS) {
 		retval = TC_ACT_STOLEN;
 		goto out;
@@ -1010,6 +1020,8 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a,
 
 out:
 	tcf_action_update_bstats(&c->common, skb);
+	if (defrag)
+		qdisc_skb_cb(skb)->pkt_len = skb->len;
 	return retval;
 
 drop:
-- 
2.26.2


From 45856f0b2281d8c81975e9c7be6702c5829ad41a Mon Sep 17 00:00:00 2001
From: Xiongfeng Wang <wangxiongfeng2@huawei.com>
Date: Tue, 21 Jul 2020 15:02:57 +0800
Subject: [PATCH 15/38] net-sysfs: add a newline when printing 'tx_timeout' by
 sysfs

[ Upstream commit 9bb5fbea59f36a589ef886292549ca4052fe676c ]

When I cat 'tx_timeout' by sysfs, it displays as follows. It's better to
add a newline for easy reading.

root@syzkaller:~# cat /sys/devices/virtual/net/lo/queues/tx-0/tx_timeout
0root@syzkaller:~#

Signed-off-by: Xiongfeng Wang <wangxiongfeng2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/net-sysfs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 4773ad6ec111..f67f5ca39d63 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1077,7 +1077,7 @@ static ssize_t tx_timeout_show(struct netdev_queue *queue, char *buf)
 	trans_timeout = queue->trans_timeout;
 	spin_unlock_irq(&queue->_xmit_lock);
 
-	return sprintf(buf, "%lu", trans_timeout);
+	return sprintf(buf, fmt_ulong, trans_timeout);
 }
 
 static unsigned int get_netdev_queue_index(struct netdev_queue *queue)
-- 
2.26.2


From bf786f20e1ec85a38f8781f33fc9e6a43a3c808d Mon Sep 17 00:00:00 2001
From: Miaohe Lin <linmiaohe@huawei.com>
Date: Tue, 21 Jul 2020 17:11:44 +0800
Subject: [PATCH 16/38] net: udp: Fix wrong clean up for IS_UDPLITE macro

[ Upstream commit b0a422772fec29811e293c7c0e6f991c0fd9241d ]

We can't use IS_UDPLITE to replace udp_sk->pcflag when UDPLITE_RECV_CC is
checked.

Fixes: b2bf1e2659b1 ("[UDP]: Clean up for IS_UDPLITE macro")
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 2 +-
 net/ipv6/udp.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 32564b350823..a27952bed2d3 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2048,7 +2048,7 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
 	/*
 	 * 	UDP-Lite specific tests, ignored on UDP sockets
 	 */
-	if ((is_udplite & UDPLITE_RECV_CC)  &&  UDP_SKB_CB(skb)->partial_cov) {
+	if ((up->pcflag & UDPLITE_RECV_CC)  &&  UDP_SKB_CB(skb)->partial_cov) {
 
 		/*
 		 * MIB statistics other than incrementing the error count are
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 7d4151747340..1164dfe53bb3 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -643,7 +643,7 @@ static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
 	/*
 	 * UDP-Lite specific tests, ignored on UDP sockets (see net/ipv4/udp.c).
 	 */
-	if ((is_udplite & UDPLITE_RECV_CC)  &&  UDP_SKB_CB(skb)->partial_cov) {
+	if ((up->pcflag & UDPLITE_RECV_CC)  &&  UDP_SKB_CB(skb)->partial_cov) {
 
 		if (up->pcrlen == 0) {          /* full coverage was set  */
 			net_dbg_ratelimited("UDPLITE6: partial coverage %d while full coverage %d requested\n",
-- 
2.26.2


From 904eec21a1fe7be18d33ea29b7f97a4733948f81 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Fri, 24 Jul 2020 09:45:51 -0700
Subject: [PATCH 17/38] qrtr: orphan socket in qrtr_release()

[ Upstream commit af9f691f0f5bdd1ade65a7b84927639882d7c3e5 ]

We have to detach sock from socket in qrtr_release(),
otherwise skb->sk may still reference to this socket
when the skb is released in tun->queue, particularly
sk->sk_wq still points to &sock->wq, which leads to
a UAF.

Reported-and-tested-by: syzbot+6720d64f31c081c2f708@syzkaller.appspotmail.com
Fixes: 28fb4e59a47d ("net: qrtr: Expose tunneling endpoint to user space")
Cc: Bjorn Andersson <bjorn.andersson@linaro.org>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/qrtr/qrtr.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index 24a8c3c6da0d..300a104b9a0f 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -1180,6 +1180,7 @@ static int qrtr_release(struct socket *sock)
 		sk->sk_state_change(sk);
 
 	sock_set_flag(sk, SOCK_DEAD);
+	sock_orphan(sk);
 	sock->sk = NULL;
 
 	if (!sock_flag(sk, SOCK_ZAPPED))
-- 
2.26.2


From 86d508c0cfc51ccc44357e2b541b7b635116822e Mon Sep 17 00:00:00 2001
From: Weilong Chen <chenweilong@huawei.com>
Date: Wed, 15 Jul 2020 20:58:10 +0800
Subject: [PATCH 18/38] rtnetlink: Fix memory(net_device) leak when ->newlink
 fails

[ Upstream commit cebb69754f37d68e1355a5e726fdac317bcda302 ]

When vlan_newlink call register_vlan_dev fails, it might return error
with dev->reg_state = NETREG_UNREGISTERED. The rtnl_newlink should
free the memory. But currently rtnl_newlink only free the memory which
state is NETREG_UNINITIALIZED.

BUG: memory leak
unreferenced object 0xffff8881051de000 (size 4096):
  comm "syz-executor139", pid 560, jiffies 4294745346 (age 32.445s)
  hex dump (first 32 bytes):
    76 6c 61 6e 32 00 00 00 00 00 00 00 00 00 00 00  vlan2...........
    00 45 28 03 81 88 ff ff 00 00 00 00 00 00 00 00  .E(.............
  backtrace:
    [<0000000047527e31>] kmalloc_node include/linux/slab.h:578 [inline]
    [<0000000047527e31>] kvmalloc_node+0x33/0xd0 mm/util.c:574
    [<000000002b59e3bc>] kvmalloc include/linux/mm.h:753 [inline]
    [<000000002b59e3bc>] kvzalloc include/linux/mm.h:761 [inline]
    [<000000002b59e3bc>] alloc_netdev_mqs+0x83/0xd90 net/core/dev.c:9929
    [<000000006076752a>] rtnl_create_link+0x2c0/0xa20 net/core/rtnetlink.c:3067
    [<00000000572b3be5>] __rtnl_newlink+0xc9c/0x1330 net/core/rtnetlink.c:3329
    [<00000000e84ea553>] rtnl_newlink+0x66/0x90 net/core/rtnetlink.c:3397
    [<0000000052c7c0a9>] rtnetlink_rcv_msg+0x540/0x990 net/core/rtnetlink.c:5460
    [<000000004b5cb379>] netlink_rcv_skb+0x12b/0x3a0 net/netlink/af_netlink.c:2469
    [<00000000c71c20d3>] netlink_unicast_kernel net/netlink/af_netlink.c:1303 [inline]
    [<00000000c71c20d3>] netlink_unicast+0x4c6/0x690 net/netlink/af_netlink.c:1329
    [<00000000cca72fa9>] netlink_sendmsg+0x735/0xcc0 net/netlink/af_netlink.c:1918
    [<000000009221ebf7>] sock_sendmsg_nosec net/socket.c:652 [inline]
    [<000000009221ebf7>] sock_sendmsg+0x109/0x140 net/socket.c:672
    [<000000001c30ffe4>] ____sys_sendmsg+0x5f5/0x780 net/socket.c:2352
    [<00000000b71ca6f3>] ___sys_sendmsg+0x11d/0x1a0 net/socket.c:2406
    [<0000000007297384>] __sys_sendmsg+0xeb/0x1b0 net/socket.c:2439
    [<000000000eb29b11>] do_syscall_64+0x56/0xa0 arch/x86/entry/common.c:359
    [<000000006839b4d0>] entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: cb626bf566eb ("net-sysfs: Fix reference count leak")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Weilong Chen <chenweilong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 709ebbf8ab5b..78345e39e54a 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3337,7 +3337,8 @@ static int __rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 		 */
 		if (err < 0) {
 			/* If device is not registered at all, free it now */
-			if (dev->reg_state == NETREG_UNINITIALIZED)
+			if (dev->reg_state == NETREG_UNINITIALIZED ||
+			    dev->reg_state == NETREG_UNREGISTERED)
 				free_netdev(dev);
 			goto out;
 		}
-- 
2.26.2


From 9065a15f152fe98c23b60b595c5155746d9032c9 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 20 Jul 2020 12:41:46 +0100
Subject: [PATCH 19/38] rxrpc: Fix sendmsg() returning EPIPE due to recvmsg()
 returning ENODATA

[ Upstream commit 639f181f0ee20d3249dbc55f740f0167267180f0 ]

rxrpc_sendmsg() returns EPIPE if there's an outstanding error, such as if
rxrpc_recvmsg() indicating ENODATA if there's nothing for it to read.

Change rxrpc_recvmsg() to return EAGAIN instead if there's nothing to read
as this particular error doesn't get stored in ->sk_err by the networking
core.

Also change rxrpc_sendmsg() so that it doesn't fail with delayed receive
errors (there's no way for it to report which call, if any, the error was
caused by).

Fixes: 17926a79320a ("[AF_RXRPC]: Provide secure RxRPC sockets for use by userspace and kernel both")
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/recvmsg.c | 2 +-
 net/rxrpc/sendmsg.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index 8578c39ec839..6896a33ef842 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -464,7 +464,7 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	    list_empty(&rx->recvmsg_q) &&
 	    rx->sk.sk_state != RXRPC_SERVER_LISTENING) {
 		release_sock(&rx->sk);
-		return -ENODATA;
+		return -EAGAIN;
 	}
 
 	if (list_empty(&rx->recvmsg_q)) {
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 5e9c43d4a314..49d03c8c64da 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -306,7 +306,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
 	/* this should be in poll */
 	sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
-	if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
+	if (sk->sk_shutdown & SEND_SHUTDOWN)
 		return -EPIPE;
 
 	more = msg->msg_flags & MSG_MORE;
-- 
2.26.2


From 3e5e44606230ee1a3a8166d0054b1632dbf2a1ae Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Thu, 23 Jul 2020 12:00:06 -0700
Subject: [PATCH 20/38] tcp: allow at most one TLP probe per flight

[ Upstream commit 76be93fc0702322179bb0ea87295d820ee46ad14 ]

Previously TLP may send multiple probes of new data in one
flight. This happens when the sender is cwnd limited. After the
initial TLP containing new data is sent, the sender receives another
ACK that acks partial inflight.  It may re-arm another TLP timer
to send more, if no further ACK returns before the next TLP timeout
(PTO) expires. The sender may send in theory a large amount of TLP
until send queue is depleted. This only happens if the sender sees
such irregular uncommon ACK pattern. But it is generally undesirable
behavior during congestion especially.

The original TLP design restrict only one TLP probe per inflight as
published in "Reducing Web Latency: the Virtue of Gentle Aggression",
SIGCOMM 2013. This patch changes TLP to send at most one probe
per inflight.

Note that if the sender is app-limited, TLP retransmits old data
and did not have this issue.

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h   |  4 +++-
 net/ipv4/tcp_input.c  | 11 ++++++-----
 net/ipv4/tcp_output.c | 13 ++++++++-----
 3 files changed, 17 insertions(+), 11 deletions(-)

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 4f8159e90ce1..0bba582e83ca 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -217,6 +217,8 @@ struct tcp_sock {
 	} rack;
 	u16	advmss;		/* Advertised MSS			*/
 	u8	compressed_ack;
+	u8	tlp_retrans:1,	/* TLP is a retransmission */
+		unused:7;
 	u32	chrono_start;	/* Start time in jiffies of a TCP chrono */
 	u32	chrono_stat[3];	/* Time in jiffies for chrono_stat stats */
 	u8	chrono_type:2,	/* current chronograph type */
@@ -239,7 +241,7 @@ struct tcp_sock {
 		save_syn:1,	/* Save headers of SYN packet */
 		is_cwnd_limited:1,/* forward progress limited by snd_cwnd? */
 		syn_smc:1;	/* SYN includes SMC */
-	u32	tlp_high_seq;	/* snd_nxt at the time of TLP retransmit. */
+	u32	tlp_high_seq;	/* snd_nxt at the time of TLP */
 
 	u32	tcp_tx_delay;	/* delay (in usec) added to TX packets */
 	u64	tcp_wstamp_ns;	/* departure time for next sent data packet */
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 31c58e00d25b..32ac66a8c657 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3506,10 +3506,8 @@ static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq)
 	}
 }
 
-/* This routine deals with acks during a TLP episode.
- * We mark the end of a TLP episode on receiving TLP dupack or when
- * ack is after tlp_high_seq.
- * Ref: loss detection algorithm in draft-dukkipati-tcpm-tcp-loss-probe.
+/* This routine deals with acks during a TLP episode and ends an episode by
+ * resetting tlp_high_seq. Ref: TLP algorithm in draft-ietf-tcpm-rack
  */
 static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag)
 {
@@ -3518,7 +3516,10 @@ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag)
 	if (before(ack, tp->tlp_high_seq))
 		return;
 
-	if (flag & FLAG_DSACKING_ACK) {
+	if (!tp->tlp_retrans) {
+		/* TLP of new data has been acknowledged */
+		tp->tlp_high_seq = 0;
+	} else if (flag & FLAG_DSACKING_ACK) {
 		/* This DSACK means original and TLP probe arrived; no loss */
 		tp->tlp_high_seq = 0;
 	} else if (after(ack, tp->tlp_high_seq)) {
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index bee2f9b8b8a1..b1c2484b4314 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2625,6 +2625,11 @@ void tcp_send_loss_probe(struct sock *sk)
 	int pcount;
 	int mss = tcp_current_mss(sk);
 
+	/* At most one outstanding TLP */
+	if (tp->tlp_high_seq)
+		goto rearm_timer;
+
+	tp->tlp_retrans = 0;
 	skb = tcp_send_head(sk);
 	if (skb && tcp_snd_wnd_test(tp, skb, mss)) {
 		pcount = tp->packets_out;
@@ -2642,10 +2647,6 @@ void tcp_send_loss_probe(struct sock *sk)
 		return;
 	}
 
-	/* At most one outstanding TLP retransmission. */
-	if (tp->tlp_high_seq)
-		goto rearm_timer;
-
 	if (skb_still_in_host_queue(sk, skb))
 		goto rearm_timer;
 
@@ -2667,10 +2668,12 @@ void tcp_send_loss_probe(struct sock *sk)
 	if (__tcp_retransmit_skb(sk, skb, 1))
 		goto rearm_timer;
 
+	tp->tlp_retrans = 1;
+
+probe_sent:
 	/* Record snd_nxt for loss detection. */
 	tp->tlp_high_seq = tp->snd_nxt;
 
-probe_sent:
 	NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPLOSSPROBES);
 	/* Reset s.t. tcp_rearm_rto will restart timer from now */
 	inet_csk(sk)->icsk_pending = 0;
-- 
2.26.2


From 2d637c53023baec8f0d2d7e8e2d93379859f0fff Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Thu, 23 Jul 2020 17:49:57 +0300
Subject: [PATCH 21/38] AX.25: Prevent integer overflows in connect and sendmsg

[ Upstream commit 17ad73e941b71f3bec7523ea4e9cbc3752461c2d ]

We recently added some bounds checking in ax25_connect() and
ax25_sendmsg() and we so we removed the AX25_MAX_DIGIS checks because
they were no longer required.

Unfortunately, I believe they are required to prevent integer overflows
so I have added them back.

Fixes: 8885bb0621f0 ("AX.25: Prevent out-of-bounds read in ax25_sendmsg()")
Fixes: 2f2a7ffad5c6 ("AX.25: Fix out-of-bounds read in ax25_connect()")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ax25/af_ax25.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 0862fe49d434..dec3f35467c9 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1188,6 +1188,7 @@ static int __must_check ax25_connect(struct socket *sock,
 	    fsa->fsa_ax25.sax25_ndigis != 0) {
 		/* Valid number of digipeaters ? */
 		if (fsa->fsa_ax25.sax25_ndigis < 1 ||
+		    fsa->fsa_ax25.sax25_ndigis > AX25_MAX_DIGIS ||
 		    addr_len < sizeof(struct sockaddr_ax25) +
 		    sizeof(ax25_address) * fsa->fsa_ax25.sax25_ndigis) {
 			err = -EINVAL;
@@ -1509,7 +1510,9 @@ static int ax25_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 			struct full_sockaddr_ax25 *fsa = (struct full_sockaddr_ax25 *)usax;
 
 			/* Valid number of digipeaters ? */
-			if (usax->sax25_ndigis < 1 || addr_len < sizeof(struct sockaddr_ax25) +
+			if (usax->sax25_ndigis < 1 ||
+			    usax->sax25_ndigis > AX25_MAX_DIGIS ||
+			    addr_len < sizeof(struct sockaddr_ax25) +
 			    sizeof(ax25_address) * usax->sax25_ndigis) {
 				err = -EINVAL;
 				goto out;
-- 
2.26.2


From 3db42aa1d4a7dc0a543e119a38f4948e67945b14 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Sat, 11 Jul 2020 20:48:23 -0400
Subject: [PATCH 22/38] bnxt_en: Fix race when modifying pause settings.

[ Upstream commit 163e9ef63641a02de4c95cd921577265c52e1ce2 ]

The driver was modified to not rely on rtnl lock to protect link
settings about 2 years ago.  The pause setting was missed when
making that change.  Fix it by acquiring link_lock mutex before
calling bnxt_hwrm_set_pause().

Fixes: e2dc9b6e38fa ("bnxt_en: Don't use rtnl lock to protect link change logic in workqueue.")
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Reviewed-by: Edwin Peer <edwin.peer@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 360f9a95c1d5..21cc2bd12760 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -1687,8 +1687,11 @@ static int bnxt_set_pauseparam(struct net_device *dev,
 	if (epause->tx_pause)
 		link_info->req_flow_ctrl |= BNXT_LINK_PAUSE_TX;
 
-	if (netif_running(dev))
+	if (netif_running(dev)) {
+		mutex_lock(&bp->link_lock);
 		rc = bnxt_hwrm_set_pause(bp);
+		mutex_unlock(&bp->link_lock);
+	}
 	return rc;
 }
 
-- 
2.26.2


From 81f7538d548d15c304cb65e305c9aaa37e4797be Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Sat, 11 Jul 2020 20:48:24 -0400
Subject: [PATCH 23/38] bnxt_en: Init ethtool link settings after reading
 updated PHY configuration.

[ Upstream commit ca0c753815fe4786b79a80abf0412eb5d52090b8 ]

In a shared port PHY configuration, async event is received when any of the
port modifies the configuration. Ethtool link settings should be
initialised after updated PHY configuration from firmware.

Fixes: b1613e78e98d ("bnxt_en: Add async. event logic for PHY configuration changes.")
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index b6fb5a1709c0..198bca9c1e2d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -10362,15 +10362,15 @@ static void bnxt_sp_task(struct work_struct *work)
 				       &bp->sp_event))
 			bnxt_hwrm_phy_qcaps(bp);
 
-		if (test_and_clear_bit(BNXT_LINK_CFG_CHANGE_SP_EVENT,
-				       &bp->sp_event))
-			bnxt_init_ethtool_link_settings(bp);
-
 		rc = bnxt_update_link(bp, true);
-		mutex_unlock(&bp->link_lock);
 		if (rc)
 			netdev_err(bp->dev, "SP task can't update link (rc: %x)\n",
 				   rc);
+
+		if (test_and_clear_bit(BNXT_LINK_CFG_CHANGE_SP_EVENT,
+				       &bp->sp_event))
+			bnxt_init_ethtool_link_settings(bp);
+		mutex_unlock(&bp->link_lock);
 	}
 	if (test_and_clear_bit(BNXT_UPDATE_PHY_SP_EVENT, &bp->sp_event)) {
 		int rc;
-- 
2.26.2


From cf71f671bc7f20bfd21d2a13aa42e04efd86d23d Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sat, 11 Jul 2020 20:48:25 -0400
Subject: [PATCH 24/38] bnxt_en: Fix completion ring sizing with TPA enabled.

[ Upstream commit 27640ce68d21e556b66bc5fa022aacd26e53c947 ]

The current completion ring sizing formula is wrong with TPA enabled.
The formula assumes that the number of TPA completions are bound by the
RX ring size, but that's not true.  TPA_START completions are immediately
recycled so they are not bound by the RX ring size.  We must add
bp->max_tpa to the worst case maximum RX and TPA completions.

The completion ring can overflow because of this mistake.  This will
cause hardware to disable the completion ring when this happens,
leading to RX and TX traffic to stall on that ring.  This issue is
generally exposed only when the RX ring size is set very small.

Fix the formula by adding bp->max_tpa to the number of RX completions
if TPA is enabled.

Fixes: c0c050c58d84 ("bnxt_en: New Broadcom ethernet driver.");
Reviewed-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 198bca9c1e2d..1656dc277af4 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -3418,7 +3418,7 @@ void bnxt_set_tpa_flags(struct bnxt *bp)
  */
 void bnxt_set_ring_params(struct bnxt *bp)
 {
-	u32 ring_size, rx_size, rx_space;
+	u32 ring_size, rx_size, rx_space, max_rx_cmpl;
 	u32 agg_factor = 0, agg_ring_size = 0;
 
 	/* 8 for CRC and VLAN */
@@ -3474,7 +3474,15 @@ void bnxt_set_ring_params(struct bnxt *bp)
 	bp->tx_nr_pages = bnxt_calc_nr_ring_pages(ring_size, TX_DESC_CNT);
 	bp->tx_ring_mask = (bp->tx_nr_pages * TX_DESC_CNT) - 1;
 
-	ring_size = bp->rx_ring_size * (2 + agg_factor) + bp->tx_ring_size;
+	max_rx_cmpl = bp->rx_ring_size;
+	/* MAX TPA needs to be added because TPA_START completions are
+	 * immediately recycled, so the TPA completions are not bound by
+	 * the RX ring size.
+	 */
+	if (bp->flags & BNXT_FLAG_TPA)
+		max_rx_cmpl += bp->max_tpa;
+	/* RX and TPA completions are 32-byte, all others are 16-byte */
+	ring_size = max_rx_cmpl * 2 + agg_ring_size + bp->tx_ring_size;
 	bp->cp_ring_size = ring_size;
 
 	bp->cp_nr_pages = bnxt_calc_nr_ring_pages(ring_size, CP_DESC_CNT);
-- 
2.26.2


From 06fb52a7f714590312dd77dbc18bd67bd77cdba9 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 22 Jul 2020 23:52:11 +0800
Subject: [PATCH 25/38] sctp: shrink stream outq only when new outcnt < old
 outcnt

[ Upstream commit 8f13399db22f909a35735bf8ae2f932e0c8f0e30 ]

It's not necessary to go list_for_each for outq->out_chunk_list
when new outcnt >= old outcnt, as no chunk with higher sid than
new (outcnt - 1) exists in the outqueue.

While at it, also move the list_for_each code in a new function
sctp_stream_shrink_out(), which will be used in the next patch.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/stream.c | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index 67f7e71f9129..4f87693cc036 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -22,17 +22,11 @@
 #include <net/sctp/sm.h>
 #include <net/sctp/stream_sched.h>
 
-/* Migrates chunks from stream queues to new stream queues if needed,
- * but not across associations. Also, removes those chunks to streams
- * higher than the new max.
- */
-static void sctp_stream_outq_migrate(struct sctp_stream *stream,
-				     struct sctp_stream *new, __u16 outcnt)
+static void sctp_stream_shrink_out(struct sctp_stream *stream, __u16 outcnt)
 {
 	struct sctp_association *asoc;
 	struct sctp_chunk *ch, *temp;
 	struct sctp_outq *outq;
-	int i;
 
 	asoc = container_of(stream, struct sctp_association, stream);
 	outq = &asoc->outqueue;
@@ -56,6 +50,19 @@ static void sctp_stream_outq_migrate(struct sctp_stream *stream,
 
 		sctp_chunk_free(ch);
 	}
+}
+
+/* Migrates chunks from stream queues to new stream queues if needed,
+ * but not across associations. Also, removes those chunks to streams
+ * higher than the new max.
+ */
+static void sctp_stream_outq_migrate(struct sctp_stream *stream,
+				     struct sctp_stream *new, __u16 outcnt)
+{
+	int i;
+
+	if (stream->outcnt > outcnt)
+		sctp_stream_shrink_out(stream, outcnt);
 
 	if (new) {
 		/* Here we actually move the old ext stuff into the new
-- 
2.26.2


From c1308c2e2031b8d6faf2355196074baffb7e9018 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 22 Jul 2020 23:52:12 +0800
Subject: [PATCH 26/38] sctp: shrink stream outq when fails to do addstream
 reconf

[ Upstream commit 3ecdda3e9ad837cf9cb41b6faa11b1af3a5abc0c ]

When adding a stream with stream reconf, the new stream firstly is in
CLOSED state but new out chunks can still be enqueued. Then once gets
the confirmation from the peer, the state will change to OPEN.

However, if the peer denies, it needs to roll back the stream. But when
doing that, it only sets the stream outcnt back, and the chunks already
in the new stream don't get purged. It caused these chunks can still be
dequeued in sctp_outq_dequeue_data().

As its stream is still in CLOSE, the chunk will be enqueued to the head
again by sctp_outq_head_data(). This chunk will never be sent out, and
the chunks after it can never be dequeued. The assoc will be 'hung' in
a dead loop of sending this chunk.

To fix it, this patch is to purge these chunks already in the new
stream by calling sctp_stream_shrink_out() when failing to do the
addstream reconf.

Fixes: 11ae76e67a17 ("sctp: implement receiver-side procedures for the Reconf Response Parameter")
Reported-by: Ying Xu <yinxu@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/stream.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index 4f87693cc036..bda2536dd740 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -1044,11 +1044,13 @@ struct sctp_chunk *sctp_process_strreset_resp(
 		nums = ntohs(addstrm->number_of_streams);
 		number = stream->outcnt - nums;
 
-		if (result == SCTP_STRRESET_PERFORMED)
+		if (result == SCTP_STRRESET_PERFORMED) {
 			for (i = number; i < stream->outcnt; i++)
 				SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN;
-		else
+		} else {
+			sctp_stream_shrink_out(stream, number);
 			stream->outcnt = number;
+		}
 
 		*evp = sctp_ulpevent_make_stream_change_event(asoc, flags,
 			0, nums, GFP_ATOMIC);
-- 
2.26.2


From 437e9a2522b12181bdb63fb669f97a7797a404d7 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Date: Tue, 21 Jul 2020 15:15:30 +0900
Subject: [PATCH 27/38] udp: Copy has_conns in reuseport_grow().

[ Upstream commit f2b2c55e512879a05456eaf5de4d1ed2f7757509 ]

If an unconnected socket in a UDP reuseport group connect()s, has_conns is
set to 1. Then, when a packet is received, udp[46]_lib_lookup2() scans all
sockets in udp_hslot looking for the connected socket with the highest
score.

However, when the number of sockets bound to the port exceeds max_socks,
reuseport_grow() resets has_conns to 0. It can cause udp[46]_lib_lookup2()
to return without scanning all sockets, resulting in that packets sent to
connected sockets may be distributed to unconnected sockets.

Therefore, reuseport_grow() should copy has_conns.

Fixes: acdcecc61285 ("udp: correct reuseport selection with connected sockets")
CC: Willem de Bruijn <willemb@google.com>
Reviewed-by: Benjamin Herrenschmidt <benh@amazon.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock_reuseport.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index adcb3aea576d..bbdd3c7b6cb5 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -101,6 +101,7 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse)
 	more_reuse->prog = reuse->prog;
 	more_reuse->reuseport_id = reuse->reuseport_id;
 	more_reuse->bind_inany = reuse->bind_inany;
+	more_reuse->has_conns = reuse->has_conns;
 
 	memcpy(more_reuse->socks, reuse->socks,
 	       reuse->num_socks * sizeof(struct sock *));
-- 
2.26.2


From 370dea78721bb93dd606c70b5a606f5ee7a0f605 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Date: Tue, 21 Jul 2020 15:15:31 +0900
Subject: [PATCH 28/38] udp: Improve load balancing for SO_REUSEPORT.

[ Upstream commit efc6b6f6c3113e8b203b9debfb72d81e0f3dcace ]

Currently, SO_REUSEPORT does not work well if connected sockets are in a
UDP reuseport group.

Then reuseport_has_conns() returns true and the result of
reuseport_select_sock() is discarded. Also, unconnected sockets have the
same score, hence only does the first unconnected socket in udp_hslot
always receive all packets sent to unconnected sockets.

So, the result of reuseport_select_sock() should be used for load
balancing.

The noteworthy point is that the unconnected sockets placed after
connected sockets in sock_reuseport.socks will receive more packets than
others because of the algorithm in reuseport_select_sock().

    index | connected | reciprocal_scale | result
    ---------------------------------------------
    0     | no        | 20%              | 40%
    1     | no        | 20%              | 20%
    2     | yes       | 20%              | 0%
    3     | no        | 20%              | 40%
    4     | yes       | 20%              | 0%

If most of the sockets are connected, this can be a problem, but it still
works better than now.

Fixes: acdcecc61285 ("udp: correct reuseport selection with connected sockets")
CC: Willem de Bruijn <willemb@google.com>
Reviewed-by: Benjamin Herrenschmidt <benh@amazon.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 15 +++++++++------
 net/ipv6/udp.c | 15 +++++++++------
 2 files changed, 18 insertions(+), 12 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index a27952bed2d3..6ffef9861fa9 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -413,7 +413,7 @@ static struct sock *udp4_lib_lookup2(struct net *net,
 				     struct udp_hslot *hslot2,
 				     struct sk_buff *skb)
 {
-	struct sock *sk, *result;
+	struct sock *sk, *result, *reuseport_result;
 	int score, badness;
 	u32 hash = 0;
 
@@ -423,17 +423,20 @@ static struct sock *udp4_lib_lookup2(struct net *net,
 		score = compute_score(sk, net, saddr, sport,
 				      daddr, hnum, dif, sdif);
 		if (score > badness) {
+			reuseport_result = NULL;
+
 			if (sk->sk_reuseport &&
 			    sk->sk_state != TCP_ESTABLISHED) {
 				hash = udp_ehashfn(net, daddr, hnum,
 						   saddr, sport);
-				result = reuseport_select_sock(sk, hash, skb,
-							sizeof(struct udphdr));
-				if (result && !reuseport_has_conns(sk, false))
-					return result;
+				reuseport_result = reuseport_select_sock(sk, hash, skb,
+									 sizeof(struct udphdr));
+				if (reuseport_result && !reuseport_has_conns(sk, false))
+					return reuseport_result;
 			}
+
+			result = reuseport_result ? : sk;
 			badness = score;
-			result = sk;
 		}
 	}
 	return result;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 1164dfe53bb3..a8d74f44056a 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -148,7 +148,7 @@ static struct sock *udp6_lib_lookup2(struct net *net,
 		int dif, int sdif, struct udp_hslot *hslot2,
 		struct sk_buff *skb)
 {
-	struct sock *sk, *result;
+	struct sock *sk, *result, *reuseport_result;
 	int score, badness;
 	u32 hash = 0;
 
@@ -158,17 +158,20 @@ static struct sock *udp6_lib_lookup2(struct net *net,
 		score = compute_score(sk, net, saddr, sport,
 				      daddr, hnum, dif, sdif);
 		if (score > badness) {
+			reuseport_result = NULL;
+
 			if (sk->sk_reuseport &&
 			    sk->sk_state != TCP_ESTABLISHED) {
 				hash = udp6_ehashfn(net, daddr, hnum,
 						    saddr, sport);
 
-				result = reuseport_select_sock(sk, hash, skb,
-							sizeof(struct udphdr));
-				if (result && !reuseport_has_conns(sk, false))
-					return result;
+				reuseport_result = reuseport_select_sock(sk, hash, skb,
+									 sizeof(struct udphdr));
+				if (reuseport_result && !reuseport_has_conns(sk, false))
+					return reuseport_result;
 			}
-			result = sk;
+
+			result = reuseport_result ? : sk;
 			badness = score;
 		}
 	}
-- 
2.26.2


From ec94468c4b9c13d0ffd200098f697cddbfc15913 Mon Sep 17 00:00:00 2001
From: Liu Jian <liujian56@huawei.com>
Date: Mon, 20 Jul 2020 22:28:29 +0800
Subject: [PATCH 29/38] dpaa_eth: Fix one possible memleak in dpaa_eth_probe

[ Upstream commit 6790711f8ac5faabc43237c0d05d93db431a1ecc ]

When dma_coerce_mask_and_coherent() fails, the alloced netdev need to be freed.

Fixes: 060ad66f9795 ("dpaa_eth: change DMA device")
Signed-off-by: Liu Jian <liujian56@huawei.com>
Acked-by: Madalin Bucur <madalin.bucur@oss.nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 6bfa7575af94..5f82c1f32f09 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -2938,7 +2938,7 @@ static int dpaa_eth_probe(struct platform_device *pdev)
 						   DMA_BIT_MASK(40));
 	if (err) {
 		netdev_err(net_dev, "dma_coerce_mask_and_coherent() failed\n");
-		return err;
+		goto free_netdev;
 	}
 
 	/* If fsl_fm_max_frm is set to a higher value than the all-common 1500,
-- 
2.26.2


From cde9786c1d7c40b61179eddacdb4af3d764043c5 Mon Sep 17 00:00:00 2001
From: Vadim Pasternak <vadimp@mellanox.com>
Date: Fri, 17 Jul 2020 22:01:43 +0300
Subject: [PATCH 30/38] mlxsw: core: Fix wrong SFP EEPROM reading for upper
 pages 1-3

[ Upstream commit 9b8737788af6c76ef93e3161ee2cdc4ddcc034ca ]

Fix wrong reading of upper pages for SFP EEPROM. According to "Memory
Organization" figure in SFF-8472 spec: When reading upper pages 1, 2 and
3 the offset should be set relative to zero and I2C high address 0x51
[1010001X (A2h)] is to be used.

Fixes: a45bfb5a5070 ("mlxsw: core: Extend QSFP EEPROM size for ethtool")
Signed-off-by: Vadim Pasternak <vadimp@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/core_env.c    | 48 ++++++++++++-------
 1 file changed, 32 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.c b/drivers/net/ethernet/mellanox/mlxsw/core_env.c
index 08215fed193d..a7d86df7123f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_env.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.c
@@ -45,7 +45,7 @@ static int mlxsw_env_validate_cable_ident(struct mlxsw_core *core, int id,
 static int
 mlxsw_env_query_module_eeprom(struct mlxsw_core *mlxsw_core, int module,
 			      u16 offset, u16 size, void *data,
-			      unsigned int *p_read_size)
+			      bool qsfp, unsigned int *p_read_size)
 {
 	char eeprom_tmp[MLXSW_REG_MCIA_EEPROM_SIZE];
 	char mcia_pl[MLXSW_REG_MCIA_LEN];
@@ -54,6 +54,10 @@ mlxsw_env_query_module_eeprom(struct mlxsw_core *mlxsw_core, int module,
 	int status;
 	int err;
 
+	/* MCIA register accepts buffer size <= 48. Page of size 128 should be
+	 * read by chunks of size 48, 48, 32. Align the size of the last chunk
+	 * to avoid reading after the end of the page.
+	 */
 	size = min_t(u16, size, MLXSW_REG_MCIA_EEPROM_SIZE);
 
 	if (offset < MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH &&
@@ -63,18 +67,25 @@ mlxsw_env_query_module_eeprom(struct mlxsw_core *mlxsw_core, int module,
 
 	i2c_addr = MLXSW_REG_MCIA_I2C_ADDR_LOW;
 	if (offset >= MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH) {
-		page = MLXSW_REG_MCIA_PAGE_GET(offset);
-		offset -= MLXSW_REG_MCIA_EEPROM_UP_PAGE_LENGTH * page;
-		/* When reading upper pages 1, 2 and 3 the offset starts at
-		 * 128. Please refer to "QSFP+ Memory Map" figure in SFF-8436
-		 * specification for graphical depiction.
-		 * MCIA register accepts buffer size <= 48. Page of size 128
-		 * should be read by chunks of size 48, 48, 32. Align the size
-		 * of the last chunk to avoid reading after the end of the
-		 * page.
-		 */
-		if (offset + size > MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH)
-			size = MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH - offset;
+		if (qsfp) {
+			/* When reading upper pages 1, 2 and 3 the offset
+			 * starts at 128. Please refer to "QSFP+ Memory Map"
+			 * figure in SFF-8436 specification for graphical
+			 * depiction.
+			 */
+			page = MLXSW_REG_MCIA_PAGE_GET(offset);
+			offset -= MLXSW_REG_MCIA_EEPROM_UP_PAGE_LENGTH * page;
+			if (offset + size > MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH)
+				size = MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH - offset;
+		} else {
+			/* When reading upper pages 1, 2 and 3 the offset
+			 * starts at 0 and I2C high address is used. Please refer
+			 * refer to "Memory Organization" figure in SFF-8472
+			 * specification for graphical depiction.
+			 */
+			i2c_addr = MLXSW_REG_MCIA_I2C_ADDR_HIGH;
+			offset -= MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH;
+		}
 	}
 
 	mlxsw_reg_mcia_pack(mcia_pl, module, 0, page, offset, size, i2c_addr);
@@ -166,7 +177,7 @@ int mlxsw_env_get_module_info(struct mlxsw_core *mlxsw_core, int module,
 	int err;
 
 	err = mlxsw_env_query_module_eeprom(mlxsw_core, module, 0, offset,
-					    module_info, &read_size);
+					    module_info, false, &read_size);
 	if (err)
 		return err;
 
@@ -197,7 +208,7 @@ int mlxsw_env_get_module_info(struct mlxsw_core *mlxsw_core, int module,
 		/* Verify if transceiver provides diagnostic monitoring page */
 		err = mlxsw_env_query_module_eeprom(mlxsw_core, module,
 						    SFP_DIAGMON, 1, &diag_mon,
-						    &read_size);
+						    false, &read_size);
 		if (err)
 			return err;
 
@@ -225,17 +236,22 @@ int mlxsw_env_get_module_eeprom(struct net_device *netdev,
 	int offset = ee->offset;
 	unsigned int read_size;
 	int i = 0;
+	bool qsfp;
 	int err;
 
 	if (!ee->len)
 		return -EINVAL;
 
 	memset(data, 0, ee->len);
+	/* Validate module identifier value. */
+	err = mlxsw_env_validate_cable_ident(mlxsw_core, module, &qsfp);
+	if (err)
+		return err;
 
 	while (i < ee->len) {
 		err = mlxsw_env_query_module_eeprom(mlxsw_core, module, offset,
 						    ee->len - i, data + i,
-						    &read_size);
+						    qsfp, &read_size);
 		if (err) {
 			netdev_err(netdev, "Eeprom query failed\n");
 			return err;
-- 
2.26.2


From d0c842dbfad0506c87ec9dfe99175916f68210b5 Mon Sep 17 00:00:00 2001
From: Tung Nguyen <tung.q.nguyen@dektech.com.au>
Date: Tue, 21 Jul 2020 08:57:05 +0700
Subject: [PATCH 31/38] tipc: allow to build NACK message in link timeout
 function

[ Upstream commit 6ef9dcb78046b346b5508ca1659848b136a343c2 ]

Commit 02288248b051 ("tipc: eliminate gap indicator from ACK messages")
eliminated sending of the 'gap' indicator in regular ACK messages and
only allowed to build NACK message with enabled probe/probe_reply.
However, necessary correction for building NACK message was missed
in tipc_link_timeout() function. This leads to significant delay and
link reset (due to retransmission failure) in lossy environment.

This commit fixes it by setting the 'probe' flag to 'true' when
the receive deferred queue is not empty. As a result, NACK message
will be built to send back to another peer.

Fixes: 02288248b051 ("tipc: eliminate gap indicator from ACK messages")
Acked-by: Jon Maloy <jmaloy@redhat.com>
Signed-off-by: Tung Nguyen <tung.q.nguyen@dektech.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/link.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/tipc/link.c b/net/tipc/link.c
index d4675e922a8f..e18369201a15 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -813,11 +813,11 @@ int tipc_link_timeout(struct tipc_link *l, struct sk_buff_head *xmitq)
 		state |= l->bc_rcvlink->rcv_unacked;
 		state |= l->rcv_unacked;
 		state |= !skb_queue_empty(&l->transmq);
-		state |= !skb_queue_empty(&l->deferdq);
 		probe = mstate->probing;
 		probe |= l->silent_intv_cnt;
 		if (probe || mstate->monitoring)
 			l->silent_intv_cnt++;
+		probe |= !skb_queue_empty(&l->deferdq);
 		if (l->snd_nxt == l->checkpoint) {
 			tipc_link_update_cwin(l, 0, 0);
 			probe = true;
-- 
2.26.2


From b0be672bc2d703fedf8789727c9ead6deecbff0a Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Sun, 19 Jul 2020 12:00:40 +0100
Subject: [PATCH 32/38] arm64: dts: clearfog-gt-8k: fix switch link
 configuration

[ Upstream commit 7c6719a1aaca51ffd7cdf3905e70aa8313f6ef26 ]

The commit below caused a regression for clearfog-gt-8k, where the link
between the switch and the host does not come up.

Investigation revealed two issues:
- MV88E6xxx DSA no longer allows an in-band link to come up as the link
  is programmed to be forced down. Commit "net: dsa: mv88e6xxx: fix
  in-band AN link establishment" addresses this.

- The dts configured dissimilar link modes at each end of the host to
  switch link; the host was configured using a fixed link (so has no
  in-band status) and the switch was configured to expect in-band
  status.

With both issues fixed, the regression is resolved.

Fixes: 34b5e6a33c1a ("net: dsa: mv88e6xxx: Configure MAC when using fixed link")
Reported-by: Martin Rowe <martin.p.rowe@gmail.com>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts b/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts
index b90d78a5724b..e32a491e909f 100644
--- a/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts
+++ b/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts
@@ -454,10 +454,7 @@ &cp1_eth2 {
 	status = "okay";
 	phy-mode = "2500base-x";
 	phys = <&cp1_comphy5 2>;
-	fixed-link {
-		speed = <2500>;
-		full-duplex;
-	};
+	managed = "in-band-status";
 };
 
 &cp1_spi1 {
-- 
2.26.2


From db2be22f0d868103e119ffbf6e1c66eaeb47b5d1 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Sun, 19 Jul 2020 12:00:35 +0100
Subject: [PATCH 33/38] net: dsa: mv88e6xxx: fix in-band AN link establishment

[ Upstream commit fad58190c0ffd72c394722928cd3e919b6e18357 ]

If in-band negotiation or fixed-link modes are specified for a DSA
port, the DSA code will force the link down during initialisation. For
fixed-link mode, this is fine, as phylink will manage the link state.
However, for in-band mode, phylink expects the PCS to detect link,
which will not happen if the link is forced down.

There is a related issue that in in-band mode, the link could come up
while we are making configuration changes, so we should force the link
down prior to reconfiguring the interface mode.

This patch addresses both issues.

Fixes: 3be98b2d5fbc ("net: dsa: Down cpu/dsa ports phylink will control")
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 22 +++++++++++++++++++---
 drivers/net/dsa/mv88e6xxx/chip.h |  1 +
 2 files changed, 20 insertions(+), 3 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 2b4a723c8306..e065be419a03 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -664,8 +664,11 @@ static void mv88e6xxx_mac_config(struct dsa_switch *ds, int port,
 				 const struct phylink_link_state *state)
 {
 	struct mv88e6xxx_chip *chip = ds->priv;
+	struct mv88e6xxx_port *p;
 	int err;
 
+	p = &chip->ports[port];
+
 	/* FIXME: is this the correct test? If we're in fixed mode on an
 	 * internal port, why should we process this any different from
 	 * PHY mode? On the other hand, the port may be automedia between
@@ -675,10 +678,14 @@ static void mv88e6xxx_mac_config(struct dsa_switch *ds, int port,
 		return;
 
 	mv88e6xxx_reg_lock(chip);
-	/* FIXME: should we force the link down here - but if we do, how
-	 * do we restore the link force/unforce state? The driver layering
-	 * gets in the way.
+	/* In inband mode, the link may come up at any time while the link
+	 * is not forced down. Force the link down while we reconfigure the
+	 * interface mode.
 	 */
+	if (mode == MLO_AN_INBAND && p->interface != state->interface &&
+	    chip->info->ops->port_set_link)
+		chip->info->ops->port_set_link(chip, port, LINK_FORCED_DOWN);
+
 	err = mv88e6xxx_port_config_interface(chip, port, state->interface);
 	if (err && err != -EOPNOTSUPP)
 		goto err_unlock;
@@ -691,6 +698,15 @@ static void mv88e6xxx_mac_config(struct dsa_switch *ds, int port,
 	if (err > 0)
 		err = 0;
 
+	/* Undo the forced down state above after completing configuration
+	 * irrespective of its state on entry, which allows the link to come up.
+	 */
+	if (mode == MLO_AN_INBAND && p->interface != state->interface &&
+	    chip->info->ops->port_set_link)
+		chip->info->ops->port_set_link(chip, port, LINK_UNFORCED);
+
+	p->interface = state->interface;
+
 err_unlock:
 	mv88e6xxx_reg_unlock(chip);
 
diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h
index e5430cf2ad71..6476524e8239 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.h
+++ b/drivers/net/dsa/mv88e6xxx/chip.h
@@ -232,6 +232,7 @@ struct mv88e6xxx_port {
 	u64 atu_full_violation;
 	u64 vtu_member_violation;
 	u64 vtu_miss_violation;
+	phy_interface_t interface;
 	u8 cmode;
 	bool mirror_ingress;
 	bool mirror_egress;
-- 
2.26.2


From 45f371892d46c770f9c7eb137f8a3f53e82d4036 Mon Sep 17 00:00:00 2001
From: Sergey Organov <sorganov@gmail.com>
Date: Wed, 15 Jul 2020 19:10:00 +0300
Subject: [PATCH 34/38] net: dp83640: fix SIOCSHWTSTAMP to update the struct
 with actual configuration

[ Upstream commit 473309fb8372365ad211f425bca760af800e10a7 ]

From Documentation/networking/timestamping.txt:

  A driver which supports hardware time stamping shall update the
  struct with the actual, possibly more permissive configuration.

Do update the struct passed when we upscale the requested time
stamping mode.

Fixes: cb646e2b02b2 ("ptp: Added a clock driver for the National Semiconductor PHYTER.")
Signed-off-by: Sergey Organov <sorganov@gmail.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/dp83640.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index ecbd5e0d685c..acb0aae60755 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -1260,6 +1260,7 @@ static int dp83640_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
 		dp83640->hwts_rx_en = 1;
 		dp83640->layer = PTP_CLASS_L4;
 		dp83640->version = PTP_CLASS_V1;
+		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
@@ -1267,6 +1268,7 @@ static int dp83640_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
 		dp83640->hwts_rx_en = 1;
 		dp83640->layer = PTP_CLASS_L4;
 		dp83640->version = PTP_CLASS_V2;
+		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT;
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
@@ -1274,6 +1276,7 @@ static int dp83640_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
 		dp83640->hwts_rx_en = 1;
 		dp83640->layer = PTP_CLASS_L2;
 		dp83640->version = PTP_CLASS_V2;
+		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT;
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
@@ -1281,6 +1284,7 @@ static int dp83640_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
 		dp83640->hwts_rx_en = 1;
 		dp83640->layer = PTP_CLASS_L4 | PTP_CLASS_L2;
 		dp83640->version = PTP_CLASS_V2;
+		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 		break;
 	default:
 		return -ERANGE;
-- 
2.26.2


From d17ec96931d555b596d1719c51f7b7d6013c40fd Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Fri, 10 Jul 2020 14:12:43 +0200
Subject: [PATCH 35/38] vsock/virtio: annotate 'the_virtio_vsock' RCU pointer

[ Upstream commit f961134a612c793d5901a93d85a29337c74af978 ]

Commit 0deab087b16a ("vsock/virtio: use RCU to avoid use-after-free
on the_virtio_vsock") starts to use RCU to protect 'the_virtio_vsock'
pointer, but we forgot to annotate it.

This patch adds the annotation to fix the following sparse errors:

    net/vmw_vsock/virtio_transport.c:73:17: error: incompatible types in comparison expression (different address spaces):
    net/vmw_vsock/virtio_transport.c:73:17:    struct virtio_vsock [noderef] __rcu *
    net/vmw_vsock/virtio_transport.c:73:17:    struct virtio_vsock *
    net/vmw_vsock/virtio_transport.c:171:17: error: incompatible types in comparison expression (different address spaces):
    net/vmw_vsock/virtio_transport.c:171:17:    struct virtio_vsock [noderef] __rcu *
    net/vmw_vsock/virtio_transport.c:171:17:    struct virtio_vsock *
    net/vmw_vsock/virtio_transport.c:207:17: error: incompatible types in comparison expression (different address spaces):
    net/vmw_vsock/virtio_transport.c:207:17:    struct virtio_vsock [noderef] __rcu *
    net/vmw_vsock/virtio_transport.c:207:17:    struct virtio_vsock *
    net/vmw_vsock/virtio_transport.c:561:13: error: incompatible types in comparison expression (different address spaces):
    net/vmw_vsock/virtio_transport.c:561:13:    struct virtio_vsock [noderef] __rcu *
    net/vmw_vsock/virtio_transport.c:561:13:    struct virtio_vsock *
    net/vmw_vsock/virtio_transport.c:612:9: error: incompatible types in comparison expression (different address spaces):
    net/vmw_vsock/virtio_transport.c:612:9:    struct virtio_vsock [noderef] __rcu *
    net/vmw_vsock/virtio_transport.c:612:9:    struct virtio_vsock *
    net/vmw_vsock/virtio_transport.c:631:9: error: incompatible types in comparison expression (different address spaces):
    net/vmw_vsock/virtio_transport.c:631:9:    struct virtio_vsock [noderef] __rcu *
    net/vmw_vsock/virtio_transport.c:631:9:    struct virtio_vsock *

Fixes: 0deab087b16a ("vsock/virtio: use RCU to avoid use-after-free on the_virtio_vsock")
Reported-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/vmw_vsock/virtio_transport.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index dfbaf6bd8b1c..2700a63ab095 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -22,7 +22,7 @@
 #include <net/af_vsock.h>
 
 static struct workqueue_struct *virtio_vsock_workqueue;
-static struct virtio_vsock *the_virtio_vsock;
+static struct virtio_vsock __rcu *the_virtio_vsock;
 static DEFINE_MUTEX(the_virtio_vsock_mutex); /* protects the_virtio_vsock */
 
 struct virtio_vsock {
-- 
2.26.2


From 0ceebac4dd87978e1a7a7761d5debde346bff148 Mon Sep 17 00:00:00 2001
From: George Kennedy <george.kennedy@oracle.com>
Date: Wed, 15 Jul 2020 09:59:31 -0400
Subject: [PATCH 36/38] ax88172a: fix ax88172a_unbind() failures

[ Upstream commit c28d9a285668c799eeae2f7f93e929a6028a4d6d ]

If ax88172a_unbind() fails, make sure that the return code is
less than zero so that cleanup is done properly and avoid UAF.

Fixes: a9a51bd727d1 ("ax88172a: fix information leak on short answers")
Signed-off-by: George Kennedy <george.kennedy@oracle.com>
Reported-by: syzbot+4cd84f527bf4a10fc9c1@syzkaller.appspotmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/ax88172a.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/ax88172a.c b/drivers/net/usb/ax88172a.c
index 4e514f5d7c6c..fd3a04d98dc1 100644
--- a/drivers/net/usb/ax88172a.c
+++ b/drivers/net/usb/ax88172a.c
@@ -187,6 +187,7 @@ static int ax88172a_bind(struct usbnet *dev, struct usb_interface *intf)
 	ret = asix_read_cmd(dev, AX_CMD_READ_NODE_ID, 0, 0, ETH_ALEN, buf, 0);
 	if (ret < ETH_ALEN) {
 		netdev_err(dev->net, "Failed to read MAC address: %d\n", ret);
+		ret = -EIO;
 		goto free;
 	}
 	memcpy(dev->net->dev_addr, buf, ETH_ALEN);
-- 
2.26.2


From c83163bab023080ff99256d7d90dd613b8002ac2 Mon Sep 17 00:00:00 2001
From: Ioana Ciornei <ioana.ciornei@nxp.com>
Date: Tue, 14 Jul 2020 15:08:16 +0300
Subject: [PATCH 37/38] dpaa2-eth: check fsl_mc_get_endpoint for
 IS_ERR_OR_NULL()

[ Upstream commit 841eb4012cef84820e5906527b31a854f42b0748 ]

The fsl_mc_get_endpoint() function can return an error or directly a
NULL pointer in case the peer device is not under the root DPRC
container. Treat this case also, otherwise it would lead to a NULL
pointer when trying to access the peer fsl_mc_device.

Fixes: 719479230893 ("dpaa2-eth: add MAC/PHY support through phylink")
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 569e06d2bab2..72fa9c4e058f 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -3383,7 +3383,7 @@ static int dpaa2_eth_connect_mac(struct dpaa2_eth_priv *priv)
 
 	dpni_dev = to_fsl_mc_device(priv->net_dev->dev.parent);
 	dpmac_dev = fsl_mc_get_endpoint(dpni_dev);
-	if (IS_ERR(dpmac_dev) || dpmac_dev->dev.type != &fsl_mc_bus_dpmac_type)
+	if (IS_ERR_OR_NULL(dpmac_dev) || dpmac_dev->dev.type != &fsl_mc_bus_dpmac_type)
 		return 0;
 
 	if (dpaa2_mac_is_type_fixed(dpmac_dev, priv->mc_io))
-- 
2.26.2


From 0e16f89877f830ccf8fd78dd01ef51db814d2fe4 Mon Sep 17 00:00:00 2001
From: Sergey Organov <sorganov@gmail.com>
Date: Tue, 14 Jul 2020 19:28:02 +0300
Subject: [PATCH 38/38] net: fec: fix hardware time stamping by external
 devices

[ Upstream commit 340746398b67e3ce5019698748ebaa7adf048114 ]

Fix support for external PTP-aware devices such as DSA or PTP PHY:

Make sure we never time stamp tx packets when hardware time stamping
is disabled.

Check for PTP PHY being in use and then pass ioctls related to time
stamping of Ethernet packets to the PTP PHY rather than handle them
ourselves. In addition, disable our own hardware time stamping in this
case.

Fixes: 6605b730c061 ("FEC: Add time stamping code and a PTP hardware clock")
Signed-off-by: Sergey Organov <sorganov@gmail.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Acked-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/fec.h      |  1 +
 drivers/net/ethernet/freescale/fec_main.c | 23 +++++++++++++++++------
 drivers/net/ethernet/freescale/fec_ptp.c  | 12 ++++++++++++
 3 files changed, 30 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index e74dd1f86bba..828eb8ce6631 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -597,6 +597,7 @@ struct fec_enet_private {
 void fec_ptp_init(struct platform_device *pdev, int irq_idx);
 void fec_ptp_stop(struct platform_device *pdev);
 void fec_ptp_start_cyclecounter(struct net_device *ndev);
+void fec_ptp_disable_hwts(struct net_device *ndev);
 int fec_ptp_set(struct net_device *ndev, struct ifreq *ifr);
 int fec_ptp_get(struct net_device *ndev, struct ifreq *ifr);
 
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index dc6f8763a5d4..bf73bc9bf35b 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -1302,8 +1302,13 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id)
 			ndev->stats.tx_bytes += skb->len;
 		}
 
-		if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS) &&
-			fep->bufdesc_ex) {
+		/* NOTE: SKBTX_IN_PROGRESS being set does not imply it's we who
+		 * are to time stamp the packet, so we still need to check time
+		 * stamping enabled flag.
+		 */
+		if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS &&
+			     fep->hwts_tx_en) &&
+		    fep->bufdesc_ex) {
 			struct skb_shared_hwtstamps shhwtstamps;
 			struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp;
 
@@ -2731,10 +2736,16 @@ static int fec_enet_ioctl(struct net_device *ndev, struct ifreq *rq, int cmd)
 		return -ENODEV;
 
 	if (fep->bufdesc_ex) {
-		if (cmd == SIOCSHWTSTAMP)
-			return fec_ptp_set(ndev, rq);
-		if (cmd == SIOCGHWTSTAMP)
-			return fec_ptp_get(ndev, rq);
+		bool use_fec_hwts = !phy_has_hwtstamp(phydev);
+
+		if (cmd == SIOCSHWTSTAMP) {
+			if (use_fec_hwts)
+				return fec_ptp_set(ndev, rq);
+			fec_ptp_disable_hwts(ndev);
+		} else if (cmd == SIOCGHWTSTAMP) {
+			if (use_fec_hwts)
+				return fec_ptp_get(ndev, rq);
+		}
 	}
 
 	return phy_mii_ioctl(phydev, rq, cmd);
diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
index 945643c02615..f8a592c96beb 100644
--- a/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/drivers/net/ethernet/freescale/fec_ptp.c
@@ -452,6 +452,18 @@ static int fec_ptp_enable(struct ptp_clock_info *ptp,
 	return -EOPNOTSUPP;
 }
 
+/**
+ * fec_ptp_disable_hwts - disable hardware time stamping
+ * @ndev: pointer to net_device
+ */
+void fec_ptp_disable_hwts(struct net_device *ndev)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+
+	fep->hwts_tx_en = 0;
+	fep->hwts_rx_en = 0;
+}
+
 int fec_ptp_set(struct net_device *ndev, struct ifreq *ifr)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
-- 
2.26.2

Re: [PATCHES] Networking

[Greg KH]

On Tue, Jul 28, 2020 at 08:12:25PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v5.4 and
> v5.7 -stable, respectively.

All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 105 bytes --]


Please queue up the following networking bug fixes for v5.4 and
v5.7 -stable, respectively.

Thank you!

[-- Attachment #2: net_54.mbox --]
[-- Type: Application/Octet-Stream, Size: 48560 bytes --]

From 2837f2ffb74eaaa06768751965558e8d368e8d47 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 29 Jul 2020 11:37:13 +0300
Subject: [PATCH 01/18] ipv4: Silence suspicious RCU usage warning

[ Upstream commit 83f3522860f702748143e022f1a546547314c715 ]

fib_trie_unmerge() is called with RTNL held, but not from an RCU
read-side critical section. This leads to the following warning [1] when
the FIB alias list in a leaf is traversed with
hlist_for_each_entry_rcu().

Since the function is always called with RTNL held and since
modification of the list is protected by RTNL, simply use
hlist_for_each_entry() and silence the warning.

[1]
WARNING: suspicious RCU usage
5.8.0-rc4-custom-01520-gc1f937f3f83b #30 Not tainted
-----------------------------
net/ipv4/fib_trie.c:1867 RCU-list traversed in non-reader section!!

other info that might help us debug this:

rcu_scheduler_active = 2, debug_locks = 1
1 lock held by ip/164:
 #0: ffffffff85a27850 (rtnl_mutex){+.+.}-{3:3}, at: rtnetlink_rcv_msg+0x49a/0xbd0

stack backtrace:
CPU: 0 PID: 164 Comm: ip Not tainted 5.8.0-rc4-custom-01520-gc1f937f3f83b #30
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-2.fc32 04/01/2014
Call Trace:
 dump_stack+0x100/0x184
 lockdep_rcu_suspicious+0x153/0x15d
 fib_trie_unmerge+0x608/0xdb0
 fib_unmerge+0x44/0x360
 fib4_rule_configure+0xc8/0xad0
 fib_nl_newrule+0x37a/0x1dd0
 rtnetlink_rcv_msg+0x4f7/0xbd0
 netlink_rcv_skb+0x17a/0x480
 rtnetlink_rcv+0x22/0x30
 netlink_unicast+0x5ae/0x890
 netlink_sendmsg+0x98a/0xf40
 ____sys_sendmsg+0x879/0xa00
 ___sys_sendmsg+0x122/0x190
 __sys_sendmsg+0x103/0x1d0
 __x64_sys_sendmsg+0x7d/0xb0
 do_syscall_64+0x54/0xa0
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x7fc80a234e97
Code: Bad RIP value.
RSP: 002b:00007ffef8b66798 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007fc80a234e97
RDX: 0000000000000000 RSI: 00007ffef8b66800 RDI: 0000000000000003
RBP: 000000005f141b1c R08: 0000000000000001 R09: 0000000000000000
R10: 00007fc80a2a8ac0 R11: 0000000000000246 R12: 0000000000000001
R13: 0000000000000000 R14: 00007ffef8b67008 R15: 0000556fccb10020

Fixes: 0ddcf43d5d4a ("ipv4: FIB Local/MAIN table collapse")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_trie.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 1b851fd82613..47b6d73d30e5 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1751,7 +1751,7 @@ struct fib_table *fib_trie_unmerge(struct fib_table *oldtb)
 	while ((l = leaf_walk_rcu(&tp, key)) != NULL) {
 		struct key_vector *local_l = NULL, *local_tp;
 
-		hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) {
+		hlist_for_each_entry(fa, &l->leaf, fa_list) {
 			struct fib_alias *new_fa;
 
 			if (local_tb->tb_id != fa->tb_id)
-- 
2.26.2


From fbab2a0dd73b9dc6bf3b47cc13dcfbbc11cd15b3 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sat, 25 Jul 2020 15:40:53 -0700
Subject: [PATCH 02/18] ipv6: fix memory leaks on IPV6_ADDRFORM path

[ Upstream commit 8c0de6e96c9794cb523a516c465991a70245da1c ]

IPV6_ADDRFORM causes resource leaks when converting an IPv6 socket
to IPv4, particularly struct ipv6_ac_socklist. Similar to
struct ipv6_mc_socklist, we should just close it on this path.

This bug can be easily reproduced with the following C program:

  #include <stdio.h>
  #include <string.h>
  #include <sys/types.h>
  #include <sys/socket.h>
  #include <arpa/inet.h>

  int main()
  {
    int s, value;
    struct sockaddr_in6 addr;
    struct ipv6_mreq m6;

    s = socket(AF_INET6, SOCK_DGRAM, 0);
    addr.sin6_family = AF_INET6;
    addr.sin6_port = htons(5000);
    inet_pton(AF_INET6, "::ffff:192.168.122.194", &addr.sin6_addr);
    connect(s, (struct sockaddr *)&addr, sizeof(addr));

    inet_pton(AF_INET6, "fe80::AAAA", &m6.ipv6mr_multiaddr);
    m6.ipv6mr_interface = 5;
    setsockopt(s, SOL_IPV6, IPV6_JOIN_ANYCAST, &m6, sizeof(m6));

    value = AF_INET;
    setsockopt(s, SOL_IPV6, IPV6_ADDRFORM, &value, sizeof(value));

    close(s);
    return 0;
  }

Reported-by: ch3332xr@gmail.com
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/addrconf.h   |  1 +
 net/ipv6/anycast.c       | 17 ++++++++++++-----
 net/ipv6/ipv6_sockglue.c |  1 +
 3 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 3f62b347b04a..ab8b3eb53d4b 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -273,6 +273,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex,
 		      const struct in6_addr *addr);
 int ipv6_sock_ac_drop(struct sock *sk, int ifindex,
 		      const struct in6_addr *addr);
+void __ipv6_sock_ac_close(struct sock *sk);
 void ipv6_sock_ac_close(struct sock *sk);
 
 int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr);
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index fed91ab7ec46..cf3a88a10ddd 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -183,7 +183,7 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	return 0;
 }
 
-void ipv6_sock_ac_close(struct sock *sk)
+void __ipv6_sock_ac_close(struct sock *sk)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct net_device *dev = NULL;
@@ -191,10 +191,7 @@ void ipv6_sock_ac_close(struct sock *sk)
 	struct net *net = sock_net(sk);
 	int	prev_index;
 
-	if (!np->ipv6_ac_list)
-		return;
-
-	rtnl_lock();
+	ASSERT_RTNL();
 	pac = np->ipv6_ac_list;
 	np->ipv6_ac_list = NULL;
 
@@ -211,6 +208,16 @@ void ipv6_sock_ac_close(struct sock *sk)
 		sock_kfree_s(sk, pac, sizeof(*pac));
 		pac = next;
 	}
+}
+
+void ipv6_sock_ac_close(struct sock *sk)
+{
+	struct ipv6_pinfo *np = inet6_sk(sk);
+
+	if (!np->ipv6_ac_list)
+		return;
+	rtnl_lock();
+	__ipv6_sock_ac_close(sk);
 	rtnl_unlock();
 }
 
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 5af97b4f5df3..5352c7e68c42 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -205,6 +205,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 
 			fl6_free_socklist(sk);
 			__ipv6_sock_mc_close(sk);
+			__ipv6_sock_ac_close(sk);
 
 			/*
 			 * Sock is moving from IPv6 to IPv4 (sk_prot), so
-- 
2.26.2


From 1e50259f5a54d8a3b9a1742f3685c5d775687e04 Mon Sep 17 00:00:00 2001
From: Xiyu Yang <xiyuyang19@fudan.edu.cn>
Date: Sat, 25 Jul 2020 16:02:18 +0800
Subject: [PATCH 03/18] ipv6: Fix nexthop refcnt leak when creating ipv6 route
 info

[ Upstream commit 706ec919164622ff5ce822065472d0f30a9e9dd2 ]

ip6_route_info_create() invokes nexthop_get(), which increases the
refcount of the "nh".

When ip6_route_info_create() returns, local variable "nh" becomes
invalid, so the refcount should be decreased to keep refcount balanced.

The reference counting issue happens in one exception handling path of
ip6_route_info_create(). When nexthops can not be used with source
routing, the function forgets to decrease the refcnt increased by
nexthop_get(), causing a refcnt leak.

Fix this issue by pulling up the error source routing handling when
nexthops can not be used with source routing.

Fixes: f88d8ea67fbd ("ipv6: Plumb support for nexthop object in a fib6_info")
Signed-off-by: Xiyu Yang <xiyuyang19@fudan.edu.cn>
Signed-off-by: Xin Tan <tanxin.ctf@gmail.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 94ade43d5a45..46df6345bb99 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3686,14 +3686,14 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 	rt->fib6_src.plen = cfg->fc_src_len;
 #endif
 	if (nh) {
-		if (!nexthop_get(nh)) {
-			NL_SET_ERR_MSG(extack, "Nexthop has been deleted");
-			goto out;
-		}
 		if (rt->fib6_src.plen) {
 			NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing");
 			goto out;
 		}
+		if (!nexthop_get(nh)) {
+			NL_SET_ERR_MSG(extack, "Nexthop has been deleted");
+			goto out;
+		}
 		rt->nh = nh;
 		fib6_nh = nexthop_fib6_nh(rt->nh);
 	} else {
-- 
2.26.2


From 9ee9379ef46c32eb7b384659b22d265c6d62026b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ren=C3=A9=20van=20Dorst?= <opensource@vdorst.com>
Date: Thu, 23 Jul 2020 20:07:10 +0100
Subject: [PATCH 04/18] net: ethernet: mtk_eth_soc: Always call
 mtk_gmac0_rgmii_adjust() for mt7623
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 19016d93bfc335f0c158c0d9e3b9d06c4dd53d39 ]

Modify mtk_gmac0_rgmii_adjust() so it can always be called.
mtk_gmac0_rgmii_adjust() sets-up the TRGMII clocks.

Signed-off-by: René van Dorst <opensource@vdorst.com>
Signed-off-By: David Woodhouse <dwmw2@infradead.org>
Tested-by: Frank Wunderlich <frank-w@public-files.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c | 19 ++++++++++++++-----
 1 file changed, 14 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 997dc811382a..be390c7e43b2 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -171,11 +171,21 @@ static int mt7621_gmac0_rgmii_adjust(struct mtk_eth *eth,
 	return 0;
 }
 
-static void mtk_gmac0_rgmii_adjust(struct mtk_eth *eth, int speed)
+static void mtk_gmac0_rgmii_adjust(struct mtk_eth *eth,
+				   phy_interface_t interface, int speed)
 {
 	u32 val;
 	int ret;
 
+	if (interface == PHY_INTERFACE_MODE_TRGMII) {
+		mtk_w32(eth, TRGMII_MODE, INTF_MODE);
+		val = 500000000;
+		ret = clk_set_rate(eth->clks[MTK_CLK_TRGPLL], val);
+		if (ret)
+			dev_err(eth->dev, "Failed to set trgmii pll: %d\n", ret);
+		return;
+	}
+
 	val = (speed == SPEED_1000) ?
 		INTF_MODE_RGMII_1000 : INTF_MODE_RGMII_10_100;
 	mtk_w32(eth, val, INTF_MODE);
@@ -262,10 +272,9 @@ static void mtk_mac_config(struct phylink_config *config, unsigned int mode,
 							      state->interface))
 					goto err_phy;
 			} else {
-				if (state->interface !=
-				    PHY_INTERFACE_MODE_TRGMII)
-					mtk_gmac0_rgmii_adjust(mac->hw,
-							       state->speed);
+				mtk_gmac0_rgmii_adjust(mac->hw,
+						       state->interface,
+						       state->speed);
 
 				/* mt7623_pad_clk_setup */
 				for (i = 0 ; i < NUM_TRGMII_CTRL; i++)
-- 
2.26.2


From f4a6dad600dedea6f29a9754692004b828d2e337 Mon Sep 17 00:00:00 2001
From: Landen Chao <landen.chao@mediatek.com>
Date: Wed, 29 Jul 2020 10:15:17 +0200
Subject: [PATCH 05/18] net: ethernet: mtk_eth_soc: fix MTU warnings

[ Upstream commit 555a893303872e044fb86f0a5834ce78d41ad2e2 ]

in recent kernel versions there are warnings about incorrect MTU size
like these:

eth0: mtu greater than device maximum
mtk_soc_eth 1b100000.ethernet eth0: error -22 setting MTU to include DSA overhead

Fixes: bfcb813203e6 ("net: dsa: configure the MTU for switch ports")
Fixes: 72579e14a1d3 ("net: dsa: don't fail to probe if we couldn't set the MTU")
Fixes: 7a4c53bee332 ("net: report invalid mtu value via netlink extack")
Signed-off-by: Landen Chao <landen.chao@mediatek.com>
Signed-off-by: Frank Wunderlich <frank-w@public-files.de>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index be390c7e43b2..d01b3a1b40f4 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -2878,6 +2878,8 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
 	eth->netdev[id]->irq = eth->irq[0];
 	eth->netdev[id]->dev.of_node = np;
 
+	eth->netdev[id]->max_mtu = MTK_MAX_RX_LENGTH - MTK_RX_ETH_HLEN;
+
 	return 0;
 
 free_netdev:
-- 
2.26.2


From 6cae726eb0ed0ebf7bed437fc46db73836f0af7f Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 29 Jul 2020 00:03:56 +0100
Subject: [PATCH 06/18] rxrpc: Fix race between recvmsg and sendmsg on
 immediate call failure

[ Upstream commit 65550098c1c4db528400c73acf3e46bfa78d9264 ]

There's a race between rxrpc_sendmsg setting up a call, but then failing to
send anything on it due to an error, and recvmsg() seeing the call
completion occur and trying to return the state to the user.

An assertion fails in rxrpc_recvmsg() because the call has already been
released from the socket and is about to be released again as recvmsg deals
with it.  (The recvmsg_q queue on the socket holds a ref, so there's no
problem with use-after-free.)

We also have to be careful not to end up reporting an error twice, in such
a way that both returns indicate to userspace that the user ID supplied
with the call is no longer in use - which could cause the client to
malfunction if it recycles the user ID fast enough.

Fix this by the following means:

 (1) When sendmsg() creates a call after the point that the call has been
     successfully added to the socket, don't return any errors through
     sendmsg(), but rather complete the call and let recvmsg() retrieve
     them.  Make sendmsg() return 0 at this point.  Further calls to
     sendmsg() for that call will fail with ESHUTDOWN.

     Note that at this point, we haven't send any packets yet, so the
     server doesn't yet know about the call.

 (2) If sendmsg() returns an error when it was expected to create a new
     call, it means that the user ID wasn't used.

 (3) Mark the call disconnected before marking it completed to prevent an
     oops in rxrpc_release_call().

 (4) recvmsg() will then retrieve the error and set MSG_EOR to indicate
     that the user ID is no longer known by the kernel.

An oops like the following is produced:

	kernel BUG at net/rxrpc/recvmsg.c:605!
	...
	RIP: 0010:rxrpc_recvmsg+0x256/0x5ae
	...
	Call Trace:
	 ? __init_waitqueue_head+0x2f/0x2f
	 ____sys_recvmsg+0x8a/0x148
	 ? import_iovec+0x69/0x9c
	 ? copy_msghdr_from_user+0x5c/0x86
	 ___sys_recvmsg+0x72/0xaa
	 ? __fget_files+0x22/0x57
	 ? __fget_light+0x46/0x51
	 ? fdget+0x9/0x1b
	 do_recvmmsg+0x15e/0x232
	 ? _raw_spin_unlock+0xa/0xb
	 ? vtime_delta+0xf/0x25
	 __x64_sys_recvmmsg+0x2c/0x2f
	 do_syscall_64+0x4c/0x78
	 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 357f5ef64628 ("rxrpc: Call rxrpc_release_call() on error in rxrpc_new_client_call()")
Reported-by: syzbot+b54969381df354936d96@syzkaller.appspotmail.com
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Marc Dionne <marc.dionne@auristor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/call_object.c | 27 +++++++++++++++++++--------
 net/rxrpc/conn_object.c |  8 +++++---
 net/rxrpc/recvmsg.c     |  2 +-
 net/rxrpc/sendmsg.c     |  3 +++
 4 files changed, 28 insertions(+), 12 deletions(-)

diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index f07970207b54..38a46167523f 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -288,7 +288,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
 	 */
 	ret = rxrpc_connect_call(rx, call, cp, srx, gfp);
 	if (ret < 0)
-		goto error;
+		goto error_attached_to_socket;
 
 	trace_rxrpc_call(call->debug_id, rxrpc_call_connected,
 			 atomic_read(&call->usage), here, NULL);
@@ -308,18 +308,29 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
 error_dup_user_ID:
 	write_unlock(&rx->call_lock);
 	release_sock(&rx->sk);
-	ret = -EEXIST;
-
-error:
 	__rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR,
-				    RX_CALL_DEAD, ret);
+				    RX_CALL_DEAD, -EEXIST);
 	trace_rxrpc_call(call->debug_id, rxrpc_call_error,
-			 atomic_read(&call->usage), here, ERR_PTR(ret));
+			 atomic_read(&call->usage), here, ERR_PTR(-EEXIST));
 	rxrpc_release_call(rx, call);
 	mutex_unlock(&call->user_mutex);
 	rxrpc_put_call(call, rxrpc_call_put);
-	_leave(" = %d", ret);
-	return ERR_PTR(ret);
+	_leave(" = -EEXIST");
+	return ERR_PTR(-EEXIST);
+
+	/* We got an error, but the call is attached to the socket and is in
+	 * need of release.  However, we might now race with recvmsg() when
+	 * completing the call queues it.  Return 0 from sys_sendmsg() and
+	 * leave the error to recvmsg() to deal with.
+	 */
+error_attached_to_socket:
+	trace_rxrpc_call(call->debug_id, rxrpc_call_error,
+			 atomic_read(&call->usage), here, ERR_PTR(ret));
+	set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
+	__rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR,
+				    RX_CALL_DEAD, ret);
+	_leave(" = c=%08x [err]", call->debug_id);
+	return call;
 }
 
 /*
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index 19e141eeed17..8cbe0bf20ed5 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -212,9 +212,11 @@ void rxrpc_disconnect_call(struct rxrpc_call *call)
 
 	call->peer->cong_cwnd = call->cong_cwnd;
 
-	spin_lock_bh(&conn->params.peer->lock);
-	hlist_del_rcu(&call->error_link);
-	spin_unlock_bh(&conn->params.peer->lock);
+	if (!hlist_unhashed(&call->error_link)) {
+		spin_lock_bh(&call->peer->lock);
+		hlist_del_rcu(&call->error_link);
+		spin_unlock_bh(&call->peer->lock);
+	}
 
 	if (rxrpc_is_client_call(call))
 		return rxrpc_disconnect_client_call(call);
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index 6896a33ef842..4f48e3bdd4b4 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -541,7 +541,7 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 			goto error_unlock_call;
 	}
 
-	if (msg->msg_name) {
+	if (msg->msg_name && call->peer) {
 		struct sockaddr_rxrpc *srx = msg->msg_name;
 		size_t len = sizeof(call->peer->srx);
 
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 49d03c8c64da..1a340eb0abf7 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -683,6 +683,9 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
 		if (IS_ERR(call))
 			return PTR_ERR(call);
 		/* ... and we have the call lock. */
+		ret = 0;
+		if (READ_ONCE(call->state) == RXRPC_CALL_COMPLETE)
+			goto out_put_unlock;
 	} else {
 		switch (READ_ONCE(call->state)) {
 		case RXRPC_CALL_UNINITIALISED:
-- 
2.26.2


From 262af293312416ad0fc39e315f28c8ab0a17c818 Mon Sep 17 00:00:00 2001
From: Rustam Kovhaev <rkovhaev@gmail.com>
Date: Mon, 27 Jul 2020 23:42:17 -0700
Subject: [PATCH 07/18] usb: hso: check for return value in
 hso_serial_common_create()

[ Upstream commit e911e99a0770f760377c263bc7bac1b1593c6147 ]

in case of an error tty_register_device_attr() returns ERR_PTR(),
add IS_ERR() check

Reported-and-tested-by: syzbot+67b2bd0e34f952d0321e@syzkaller.appspotmail.com
Link: https://syzkaller.appspot.com/bug?extid=67b2bd0e34f952d0321e
Signed-off-by: Rustam Kovhaev <rkovhaev@gmail.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/hso.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c
index 66a8b835aa94..7449b97a3c89 100644
--- a/drivers/net/usb/hso.c
+++ b/drivers/net/usb/hso.c
@@ -2260,12 +2260,14 @@ static int hso_serial_common_create(struct hso_serial *serial, int num_urbs,
 
 	minor = get_free_serial_index();
 	if (minor < 0)
-		goto exit;
+		goto exit2;
 
 	/* register our minor number */
 	serial->parent->dev = tty_port_register_device_attr(&serial->port,
 			tty_drv, minor, &serial->parent->interface->dev,
 			serial->parent, hso_serial_dev_groups);
+	if (IS_ERR(serial->parent->dev))
+		goto exit2;
 
 	/* fill in specific data for later use */
 	serial->minor = minor;
@@ -2310,6 +2312,7 @@ static int hso_serial_common_create(struct hso_serial *serial, int num_urbs,
 	return 0;
 exit:
 	hso_serial_tty_unregister(serial);
+exit2:
 	hso_serial_common_free(serial);
 	return -1;
 }
-- 
2.26.2


From fdc02c62976e244569673b0cc9eda1277a0dcd08 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 29 Jul 2020 11:34:36 +0300
Subject: [PATCH 08/18] vxlan: Ensure FDB dump is performed under RCU

[ Upstream commit b5141915b5aec3b29a63db869229e3741ebce258 ]

The commit cited below removed the RCU read-side critical section from
rtnl_fdb_dump() which means that the ndo_fdb_dump() callback is invoked
without RCU protection.

This results in the following warning [1] in the VXLAN driver, which
relied on the callback being invoked from an RCU read-side critical
section.

Fix this by calling rcu_read_lock() in the VXLAN driver, as already done
in the bridge driver.

[1]
WARNING: suspicious RCU usage
5.8.0-rc4-custom-01521-g481007553ce6 #29 Not tainted
-----------------------------
drivers/net/vxlan.c:1379 RCU-list traversed in non-reader section!!

other info that might help us debug this:

rcu_scheduler_active = 2, debug_locks = 1
1 lock held by bridge/166:
 #0: ffffffff85a27850 (rtnl_mutex){+.+.}-{3:3}, at: netlink_dump+0xea/0x1090

stack backtrace:
CPU: 1 PID: 166 Comm: bridge Not tainted 5.8.0-rc4-custom-01521-g481007553ce6 #29
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-2.fc32 04/01/2014
Call Trace:
 dump_stack+0x100/0x184
 lockdep_rcu_suspicious+0x153/0x15d
 vxlan_fdb_dump+0x51e/0x6d0
 rtnl_fdb_dump+0x4dc/0xad0
 netlink_dump+0x540/0x1090
 __netlink_dump_start+0x695/0x950
 rtnetlink_rcv_msg+0x802/0xbd0
 netlink_rcv_skb+0x17a/0x480
 rtnetlink_rcv+0x22/0x30
 netlink_unicast+0x5ae/0x890
 netlink_sendmsg+0x98a/0xf40
 __sys_sendto+0x279/0x3b0
 __x64_sys_sendto+0xe6/0x1a0
 do_syscall_64+0x54/0xa0
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x7fe14fa2ade0
Code: Bad RIP value.
RSP: 002b:00007fff75bb5b88 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 00005614b1ba0020 RCX: 00007fe14fa2ade0
RDX: 000000000000011c RSI: 00007fff75bb5b90 RDI: 0000000000000003
RBP: 00007fff75bb5b90 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00005614b1b89160
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000

Fixes: 5e6d24358799 ("bridge: netlink dump interface at par with brctl")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index b49b6f0cee50..401fb9697495 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1225,6 +1225,7 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
 	for (h = 0; h < FDB_HASH_SIZE; ++h) {
 		struct vxlan_fdb *f;
 
+		rcu_read_lock();
 		hlist_for_each_entry_rcu(f, &vxlan->fdb_head[h], hlist) {
 			struct vxlan_rdst *rd;
 
@@ -1237,12 +1238,15 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
 						     cb->nlh->nlmsg_seq,
 						     RTM_NEWNEIGH,
 						     NLM_F_MULTI, rd);
-				if (err < 0)
+				if (err < 0) {
+					rcu_read_unlock();
 					goto out;
+				}
 skip:
 				*idx += 1;
 			}
 		}
+		rcu_read_unlock();
 	}
 out:
 	return err;
-- 
2.26.2


From 380632f216896f27c97d77f617d1804d7ee6ebb9 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Tue, 28 Jul 2020 14:10:31 +0200
Subject: [PATCH 09/18] net: lan78xx: replace bogus endpoint lookup

[ Upstream commit ea060b352654a8de1e070140d25fe1b7e4d50310 ]

Drop the bogus endpoint-lookup helper which could end up accepting
interfaces based on endpoints belonging to unrelated altsettings.

Note that the returned bulk pipes and interrupt endpoint descriptor
were never actually used. Instead the bulk-endpoint numbers are
hardcoded to 1 and 2 (matching the specification), while the interrupt-
endpoint descriptor was assumed to be the third descriptor created by
USB core.

Try to bring some order to this by dropping the bogus lookup helper and
adding the missing endpoint sanity checks while keeping the interrupt-
descriptor assumption for now.

Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/lan78xx.c | 117 ++++++++++----------------------------
 1 file changed, 30 insertions(+), 87 deletions(-)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 1da99abc6ed1..71cc5b63d8ce 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -377,10 +377,6 @@ struct lan78xx_net {
 	struct tasklet_struct	bh;
 	struct delayed_work	wq;
 
-	struct usb_host_endpoint *ep_blkin;
-	struct usb_host_endpoint *ep_blkout;
-	struct usb_host_endpoint *ep_intr;
-
 	int			msg_enable;
 
 	struct urb		*urb_intr;
@@ -2868,78 +2864,12 @@ lan78xx_start_xmit(struct sk_buff *skb, struct net_device *net)
 	return NETDEV_TX_OK;
 }
 
-static int
-lan78xx_get_endpoints(struct lan78xx_net *dev, struct usb_interface *intf)
-{
-	int tmp;
-	struct usb_host_interface *alt = NULL;
-	struct usb_host_endpoint *in = NULL, *out = NULL;
-	struct usb_host_endpoint *status = NULL;
-
-	for (tmp = 0; tmp < intf->num_altsetting; tmp++) {
-		unsigned ep;
-
-		in = NULL;
-		out = NULL;
-		status = NULL;
-		alt = intf->altsetting + tmp;
-
-		for (ep = 0; ep < alt->desc.bNumEndpoints; ep++) {
-			struct usb_host_endpoint *e;
-			int intr = 0;
-
-			e = alt->endpoint + ep;
-			switch (e->desc.bmAttributes) {
-			case USB_ENDPOINT_XFER_INT:
-				if (!usb_endpoint_dir_in(&e->desc))
-					continue;
-				intr = 1;
-				/* FALLTHROUGH */
-			case USB_ENDPOINT_XFER_BULK:
-				break;
-			default:
-				continue;
-			}
-			if (usb_endpoint_dir_in(&e->desc)) {
-				if (!intr && !in)
-					in = e;
-				else if (intr && !status)
-					status = e;
-			} else {
-				if (!out)
-					out = e;
-			}
-		}
-		if (in && out)
-			break;
-	}
-	if (!alt || !in || !out)
-		return -EINVAL;
-
-	dev->pipe_in = usb_rcvbulkpipe(dev->udev,
-				       in->desc.bEndpointAddress &
-				       USB_ENDPOINT_NUMBER_MASK);
-	dev->pipe_out = usb_sndbulkpipe(dev->udev,
-					out->desc.bEndpointAddress &
-					USB_ENDPOINT_NUMBER_MASK);
-	dev->ep_intr = status;
-
-	return 0;
-}
-
 static int lan78xx_bind(struct lan78xx_net *dev, struct usb_interface *intf)
 {
 	struct lan78xx_priv *pdata = NULL;
 	int ret;
 	int i;
 
-	ret = lan78xx_get_endpoints(dev, intf);
-	if (ret) {
-		netdev_warn(dev->net, "lan78xx_get_endpoints failed: %d\n",
-			    ret);
-		return ret;
-	}
-
 	dev->data[0] = (unsigned long)kzalloc(sizeof(*pdata), GFP_KERNEL);
 
 	pdata = (struct lan78xx_priv *)(dev->data[0]);
@@ -3708,6 +3638,7 @@ static void lan78xx_stat_monitor(struct timer_list *t)
 static int lan78xx_probe(struct usb_interface *intf,
 			 const struct usb_device_id *id)
 {
+	struct usb_host_endpoint *ep_blkin, *ep_blkout, *ep_intr;
 	struct lan78xx_net *dev;
 	struct net_device *netdev;
 	struct usb_device *udev;
@@ -3756,6 +3687,34 @@ static int lan78xx_probe(struct usb_interface *intf,
 
 	mutex_init(&dev->stats.access_lock);
 
+	if (intf->cur_altsetting->desc.bNumEndpoints < 3) {
+		ret = -ENODEV;
+		goto out2;
+	}
+
+	dev->pipe_in = usb_rcvbulkpipe(udev, BULK_IN_PIPE);
+	ep_blkin = usb_pipe_endpoint(udev, dev->pipe_in);
+	if (!ep_blkin || !usb_endpoint_is_bulk_in(&ep_blkin->desc)) {
+		ret = -ENODEV;
+		goto out2;
+	}
+
+	dev->pipe_out = usb_sndbulkpipe(udev, BULK_OUT_PIPE);
+	ep_blkout = usb_pipe_endpoint(udev, dev->pipe_out);
+	if (!ep_blkout || !usb_endpoint_is_bulk_out(&ep_blkout->desc)) {
+		ret = -ENODEV;
+		goto out2;
+	}
+
+	ep_intr = &intf->cur_altsetting->endpoint[2];
+	if (!usb_endpoint_is_int_in(&ep_intr->desc)) {
+		ret = -ENODEV;
+		goto out2;
+	}
+
+	dev->pipe_intr = usb_rcvintpipe(dev->udev,
+					usb_endpoint_num(&ep_intr->desc));
+
 	ret = lan78xx_bind(dev, intf);
 	if (ret < 0)
 		goto out2;
@@ -3767,23 +3726,7 @@ static int lan78xx_probe(struct usb_interface *intf,
 	netdev->max_mtu = MAX_SINGLE_PACKET_SIZE;
 	netif_set_gso_max_size(netdev, MAX_SINGLE_PACKET_SIZE - MAX_HEADER);
 
-	if (intf->cur_altsetting->desc.bNumEndpoints < 3) {
-		ret = -ENODEV;
-		goto out3;
-	}
-
-	dev->ep_blkin = (intf->cur_altsetting)->endpoint + 0;
-	dev->ep_blkout = (intf->cur_altsetting)->endpoint + 1;
-	dev->ep_intr = (intf->cur_altsetting)->endpoint + 2;
-
-	dev->pipe_in = usb_rcvbulkpipe(udev, BULK_IN_PIPE);
-	dev->pipe_out = usb_sndbulkpipe(udev, BULK_OUT_PIPE);
-
-	dev->pipe_intr = usb_rcvintpipe(dev->udev,
-					dev->ep_intr->desc.bEndpointAddress &
-					USB_ENDPOINT_NUMBER_MASK);
-	period = dev->ep_intr->desc.bInterval;
-
+	period = ep_intr->desc.bInterval;
 	maxp = usb_maxpacket(dev->udev, dev->pipe_intr, 0);
 	buf = kmalloc(maxp, GFP_KERNEL);
 	if (buf) {
-- 
2.26.2


From 85f25e0c4218825ceb5e86734300e49e65178214 Mon Sep 17 00:00:00 2001
From: Vincent Duvert <vincent.ldev@duvert.net>
Date: Sun, 2 Aug 2020 07:06:51 +0200
Subject: [PATCH 10/18] appletalk: Fix atalk_proc_init() return path

[ Upstream commit d0f6ba2ef2c1c95069509e71402e7d6d43452512 ]

Add a missing return statement to atalk_proc_init so it doesn't return
-ENOMEM when successful.  This allows the appletalk module to load
properly.

Fixes: e2bcd8b0ce6e ("appletalk: use remove_proc_subtree to simplify procfs code")
Link: https://www.downtowndougbrown.com/2020/08/hacking-up-a-fix-for-the-broken-appletalk-kernel-module-in-linux-5-1-and-newer/
Reported-by: Christopher KOBAYASHI <chris@disavowed.jp>
Reported-by: Doug Brown <doug@downtowndougbrown.com>
Signed-off-by: Vincent Duvert <vincent.ldev@duvert.net>
[lukas: add missing tags]
Signed-off-by: Lukas Wunner <lukas@wunner.de>
Cc: stable@vger.kernel.org # v5.1+
Cc: Yue Haibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/appletalk/atalk_proc.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/appletalk/atalk_proc.c b/net/appletalk/atalk_proc.c
index 550c6ca007cc..9c1241292d1d 100644
--- a/net/appletalk/atalk_proc.c
+++ b/net/appletalk/atalk_proc.c
@@ -229,6 +229,8 @@ int __init atalk_proc_init(void)
 				     sizeof(struct aarp_iter_state), NULL))
 		goto out;
 
+	return 0;
+
 out:
 	remove_proc_subtree("atalk", init_net.proc_net);
 	return -ENOMEM;
-- 
2.26.2


From 07457be3584eb2b1d9b6368dbd541eb947fb3e90 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Tue, 4 Aug 2020 21:26:43 +0800
Subject: [PATCH 11/18] dpaa2-eth: Fix passing zero to 'PTR_ERR' warning

[ Upstream commit 02afa9c66bb954c6959877c70d9e128dcf0adce7 ]

Fix smatch warning:

drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c:2419
 alloc_channel() warn: passing zero to 'ERR_PTR'

setup_dpcon() should return ERR_PTR(err) instead of zero in error
handling case.

Fixes: d7f5a9d89a55 ("dpaa2-eth: defer probe on object allocate")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 3177dd8ede8e..7a248cc1055a 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -2090,7 +2090,7 @@ static struct fsl_mc_device *setup_dpcon(struct dpaa2_eth_priv *priv)
 free:
 	fsl_mc_object_free(dpcon);
 
-	return NULL;
+	return ERR_PTR(err);
 }
 
 static void free_dpcon(struct dpaa2_eth_priv *priv,
@@ -2114,8 +2114,8 @@ alloc_channel(struct dpaa2_eth_priv *priv)
 		return NULL;
 
 	channel->dpcon = setup_dpcon(priv);
-	if (IS_ERR_OR_NULL(channel->dpcon)) {
-		err = PTR_ERR_OR_ZERO(channel->dpcon);
+	if (IS_ERR(channel->dpcon)) {
+		err = PTR_ERR(channel->dpcon);
 		goto err_setup;
 	}
 
-- 
2.26.2


From e3c8073cb378e66a9c1d2c5f57c0344056fa0836 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Tue, 4 Aug 2020 09:54:15 -0700
Subject: [PATCH 12/18] hv_netvsc: do not use VF device if link is down

[ Upstream commit 7c9864bbccc23e1812ac82966555d68c13ea4006 ]

If the accelerated networking SRIOV VF device has lost carrier
use the synthetic network device which is available as backup
path. This is a rare case since if VF link goes down, normally
the VMBus device will also loose external connectivity as well.
But if the communication is between two VM's on the same host
the VMBus device will still work.

Reported-by: "Shah, Ashish N" <ashish.n.shah@intel.com>
Fixes: 0c195567a8f6 ("netvsc: transparent VF management")
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/netvsc_drv.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index ca16ae8c8332..24bb721a12bc 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -531,12 +531,13 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 	u32 hash;
 	struct hv_page_buffer pb[MAX_PAGE_BUFFER_COUNT];
 
-	/* if VF is present and up then redirect packets
-	 * already called with rcu_read_lock_bh
+	/* If VF is present and up then redirect packets to it.
+	 * Skip the VF if it is marked down or has no carrier.
+	 * If netpoll is in uses, then VF can not be used either.
 	 */
 	vf_netdev = rcu_dereference_bh(net_device_ctx->vf_netdev);
 	if (vf_netdev && netif_running(vf_netdev) &&
-	    !netpoll_tx_running(net))
+	    netif_carrier_ok(vf_netdev) && !netpoll_tx_running(net))
 		return netvsc_vf_xmit(net, vf_netdev, skb);
 
 	/* We will atmost need two pages to describe the rndis
-- 
2.26.2


From 817c0f49c372432551713eb8cd255762833af0bd Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Fri, 31 Jul 2020 20:12:05 +0200
Subject: [PATCH 13/18] net: gre: recompute gre csum for sctp over gre tunnels

[ Upstream commit 622e32b7d4a6492cf5c1f759ef833f817418f7b3 ]

The GRE tunnel can be used to transport traffic that does not rely on a
Internet checksum (e.g. SCTP). The issue can be triggered creating a GRE
or GRETAP tunnel and transmitting SCTP traffic ontop of it where CRC
offload has been disabled. In order to fix the issue we need to
recompute the GRE csum in gre_gso_segment() not relying on the inner
checksum.
The issue is still present when we have the CRC offload enabled.
In this case we need to disable the CRC offload if we require GRE
checksum since otherwise skb_checksum() will report a wrong value.

Fixes: 90017accff61 ("sctp: Add GSO support")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/gre_offload.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index 4de7e962d3da..c840141876bc 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -15,12 +15,12 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 				       netdev_features_t features)
 {
 	int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb);
+	bool need_csum, need_recompute_csum, gso_partial;
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	u16 mac_offset = skb->mac_header;
 	__be16 protocol = skb->protocol;
 	u16 mac_len = skb->mac_len;
 	int gre_offset, outer_hlen;
-	bool need_csum, gso_partial;
 
 	if (!skb->encapsulation)
 		goto out;
@@ -41,6 +41,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 	skb->protocol = skb->inner_protocol;
 
 	need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_GRE_CSUM);
+	need_recompute_csum = skb->csum_not_inet;
 	skb->encap_hdr_csum = need_csum;
 
 	features &= skb->dev->hw_enc_features;
@@ -98,7 +99,15 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 		}
 
 		*(pcsum + 1) = 0;
-		*pcsum = gso_make_checksum(skb, 0);
+		if (need_recompute_csum && !skb_is_gso(skb)) {
+			__wsum csum;
+
+			csum = skb_checksum(skb, gre_offset,
+					    skb->len - gre_offset, 0);
+			*pcsum = csum_fold(csum);
+		} else {
+			*pcsum = gso_make_checksum(skb, 0);
+		}
 	} while ((skb = skb->next));
 out:
 	return segs;
-- 
2.26.2


From 85df86263d6208997b56fc8a0787ccf875f99d3a Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 4 Aug 2020 15:02:30 +0800
Subject: [PATCH 14/18] net: thunderx: use spin_lock_bh in
 nicvf_set_rx_mode_task()

[ Upstream commit bab9693a9a8c6dd19f670408ec1e78e12a320682 ]

A dead lock was triggered on thunderx driver:

        CPU0                    CPU1
        ----                    ----
   [01] lock(&(&nic->rx_mode_wq_lock)->rlock);
                           [11] lock(&(&mc->mca_lock)->rlock);
                           [12] lock(&(&nic->rx_mode_wq_lock)->rlock);
   [02] <Interrupt> lock(&(&mc->mca_lock)->rlock);

The path for each is:

  [01] worker_thread() -> process_one_work() -> nicvf_set_rx_mode_task()
  [02] mld_ifc_timer_expire()
  [11] ipv6_add_dev() -> ipv6_dev_mc_inc() -> igmp6_group_added() ->
  [12] dev_mc_add() -> __dev_set_rx_mode() -> nicvf_set_rx_mode()

To fix it, it needs to disable bh on [1], so that the timer on [2]
wouldn't be triggered until rx_mode_wq_lock is released. So change
to use spin_lock_bh() instead of spin_lock().

Thanks to Paolo for helping with this.

v1->v2:
  - post to netdev.

Reported-by: Rafael P. <rparrazo@redhat.com>
Tested-by: Dean Nelson <dnelson@redhat.com>
Fixes: 469998c861fa ("net: thunderx: prevent concurrent data re-writing by nicvf_set_rx_mode")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/thunder/nicvf_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 40a44dcb3d9b..f414f5651dbd 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -2047,11 +2047,11 @@ static void nicvf_set_rx_mode_task(struct work_struct *work_arg)
 	/* Save message data locally to prevent them from
 	 * being overwritten by next ndo_set_rx_mode call().
 	 */
-	spin_lock(&nic->rx_mode_wq_lock);
+	spin_lock_bh(&nic->rx_mode_wq_lock);
 	mode = vf_work->mode;
 	mc = vf_work->mc;
 	vf_work->mc = NULL;
-	spin_unlock(&nic->rx_mode_wq_lock);
+	spin_unlock_bh(&nic->rx_mode_wq_lock);
 
 	__nicvf_set_rx_mode_task(mode, mc, nic);
 }
-- 
2.26.2


From 69ad62535bc778128297a86037d6ccde63732d9f Mon Sep 17 00:00:00 2001
From: Peilin Ye <yepeilin.cs@gmail.com>
Date: Fri, 31 Jul 2020 00:48:38 -0400
Subject: [PATCH 15/18] openvswitch: Prevent kernel-infoleak in
 ovs_ct_put_key()

[ Upstream commit 9aba6c5b49254d5bee927d81593ed4429e91d4ae ]

ovs_ct_put_key() is potentially copying uninitialized kernel stack memory
into socket buffers, since the compiler may leave a 3-byte hole at the end
of `struct ovs_key_ct_tuple_ipv4` and `struct ovs_key_ct_tuple_ipv6`. Fix
it by initializing `orig` with memset().

Fixes: 9dd7f8907c37 ("openvswitch: Add original direction conntrack tuple to sw_flow_key.")
Suggested-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Peilin Ye <yepeilin.cs@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/conntrack.c | 38 +++++++++++++++++++------------------
 1 file changed, 20 insertions(+), 18 deletions(-)

diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 8b70298857e3..c86e404cd65b 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -276,10 +276,6 @@ void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key)
 	ovs_ct_update_key(skb, NULL, key, false, false);
 }
 
-#define IN6_ADDR_INITIALIZER(ADDR) \
-	{ (ADDR).s6_addr32[0], (ADDR).s6_addr32[1], \
-	  (ADDR).s6_addr32[2], (ADDR).s6_addr32[3] }
-
 int ovs_ct_put_key(const struct sw_flow_key *swkey,
 		   const struct sw_flow_key *output, struct sk_buff *skb)
 {
@@ -301,24 +297,30 @@ int ovs_ct_put_key(const struct sw_flow_key *swkey,
 
 	if (swkey->ct_orig_proto) {
 		if (swkey->eth.type == htons(ETH_P_IP)) {
-			struct ovs_key_ct_tuple_ipv4 orig = {
-				output->ipv4.ct_orig.src,
-				output->ipv4.ct_orig.dst,
-				output->ct.orig_tp.src,
-				output->ct.orig_tp.dst,
-				output->ct_orig_proto,
-			};
+			struct ovs_key_ct_tuple_ipv4 orig;
+
+			memset(&orig, 0, sizeof(orig));
+			orig.ipv4_src = output->ipv4.ct_orig.src;
+			orig.ipv4_dst = output->ipv4.ct_orig.dst;
+			orig.src_port = output->ct.orig_tp.src;
+			orig.dst_port = output->ct.orig_tp.dst;
+			orig.ipv4_proto = output->ct_orig_proto;
+
 			if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4,
 				    sizeof(orig), &orig))
 				return -EMSGSIZE;
 		} else if (swkey->eth.type == htons(ETH_P_IPV6)) {
-			struct ovs_key_ct_tuple_ipv6 orig = {
-				IN6_ADDR_INITIALIZER(output->ipv6.ct_orig.src),
-				IN6_ADDR_INITIALIZER(output->ipv6.ct_orig.dst),
-				output->ct.orig_tp.src,
-				output->ct.orig_tp.dst,
-				output->ct_orig_proto,
-			};
+			struct ovs_key_ct_tuple_ipv6 orig;
+
+			memset(&orig, 0, sizeof(orig));
+			memcpy(orig.ipv6_src, output->ipv6.ct_orig.src.s6_addr32,
+			       sizeof(orig.ipv6_src));
+			memcpy(orig.ipv6_dst, output->ipv6.ct_orig.dst.s6_addr32,
+			       sizeof(orig.ipv6_dst));
+			orig.src_port = output->ct.orig_tp.src;
+			orig.dst_port = output->ct.orig_tp.dst;
+			orig.ipv6_proto = output->ct_orig_proto;
+
 			if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6,
 				    sizeof(orig), &orig))
 				return -EMSGSIZE;
-- 
2.26.2


From 1c062afbf8e71bb8d2624d0f9bba76cba17abfb2 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Wed, 5 Aug 2020 10:41:31 +0800
Subject: [PATCH 16/18] Revert "vxlan: fix tos value before xmit"

[ Upstream commit a0dced17ad9dc08b1b25e0065b54c97a318e6e8b ]

This reverts commit 71130f29979c7c7956b040673e6b9d5643003176.

In commit 71130f29979c ("vxlan: fix tos value before xmit") we want to
make sure the tos value are filtered by RT_TOS() based on RFC1349.

       0     1     2     3     4     5     6     7
    +-----+-----+-----+-----+-----+-----+-----+-----+
    |   PRECEDENCE    |          TOS          | MBZ |
    +-----+-----+-----+-----+-----+-----+-----+-----+

But RFC1349 has been obsoleted by RFC2474. The new DSCP field defined like

       0     1     2     3     4     5     6     7
    +-----+-----+-----+-----+-----+-----+-----+-----+
    |          DS FIELD, DSCP           | ECN FIELD |
    +-----+-----+-----+-----+-----+-----+-----+-----+

So with

IPTOS_TOS_MASK          0x1E
RT_TOS(tos)		((tos)&IPTOS_TOS_MASK)

the first 3 bits DSCP info will get lost.

To take all the DSCP info in xmit, we should revert the patch and just push
all tos bits to ip_tunnel_ecn_encap(), which will handling ECN field later.

Fixes: 71130f29979c ("vxlan: fix tos value before xmit")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Acked-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 401fb9697495..f9edc76580d9 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2550,7 +2550,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		ndst = &rt->dst;
 		skb_tunnel_check_pmtu(skb, ndst, VXLAN_HEADROOM);
 
-		tos = ip_tunnel_ecn_encap(RT_TOS(tos), old_iph, skb);
+		tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
 		ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
 		err = vxlan_build_skb(skb, ndst, sizeof(struct iphdr),
 				      vni, md, flags, udp_sum);
@@ -2590,7 +2590,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 
 		skb_tunnel_check_pmtu(skb, ndst, VXLAN6_HEADROOM);
 
-		tos = ip_tunnel_ecn_encap(RT_TOS(tos), old_iph, skb);
+		tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
 		ttl = ttl ? : ip6_dst_hoplimit(ndst);
 		skb_scrub_packet(skb, xnet);
 		err = vxlan_build_skb(skb, ndst, sizeof(struct ipv6hdr),
-- 
2.26.2


From 8f1b186a26b01888113ac7ce3d3b0f341d9c98d4 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 5 Aug 2020 04:40:45 -0400
Subject: [PATCH 17/18] selftests/net: relax cpu affinity requirement in
 msg_zerocopy test

[ Upstream commit 16f6458f2478b55e2b628797bc81a4455045c74e ]

The msg_zerocopy test pins the sender and receiver threads to separate
cores to reduce variance between runs.

But it hardcodes the cores and skips core 0, so it fails on machines
with the selected cores offline, or simply fewer cores.

The test mainly gives code coverage in automated runs. The throughput
of zerocopy ('-z') and non-zerocopy runs is logged for manual
inspection.

Continue even when sched_setaffinity fails. Just log to warn anyone
interpreting the data.

Fixes: 07b65c5b31ce ("test: add msg_zerocopy test")
Reported-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/msg_zerocopy.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/net/msg_zerocopy.c b/tools/testing/selftests/net/msg_zerocopy.c
index 4b02933cab8a..bdc03a2097e8 100644
--- a/tools/testing/selftests/net/msg_zerocopy.c
+++ b/tools/testing/selftests/net/msg_zerocopy.c
@@ -125,9 +125,8 @@ static int do_setcpu(int cpu)
 	CPU_ZERO(&mask);
 	CPU_SET(cpu, &mask);
 	if (sched_setaffinity(0, sizeof(mask), &mask))
-		error(1, 0, "setaffinity %d", cpu);
-
-	if (cfg_verbose)
+		fprintf(stderr, "cpu: unable to pin, may increase variance.\n");
+	else if (cfg_verbose)
 		fprintf(stderr, "cpu: %u\n", cpu);
 
 	return 0;
-- 
2.26.2


From 08c5b09937f6ed7fd9bd42987fa6810a9a5ee8e9 Mon Sep 17 00:00:00 2001
From: Jianfeng Wang <jfwang@google.com>
Date: Thu, 30 Jul 2020 23:49:16 +0000
Subject: [PATCH 18/18] tcp: apply a floor of 1 for RTT samples from TCP
 timestamps

[ Upstream commit 730e700e2c19d87e578ff0e7d8cb1d4a02b036d2 ]

For retransmitted packets, TCP needs to resort to using TCP timestamps
for computing RTT samples. In the common case where the data and ACK
fall in the same 1-millisecond interval, TCP senders with millisecond-
granularity TCP timestamps compute a ca_rtt_us of 0. This ca_rtt_us
of 0 propagates to rs->rtt_us.

This value of 0 can cause performance problems for congestion control
modules. For example, in BBR, the zero min_rtt sample can bring the
min_rtt and BDP estimate down to 0, reduce snd_cwnd and result in a
low throughput. It would be hard to mitigate this with filtering in
the congestion control module, because the proper floor to apply would
depend on the method of RTT sampling (using timestamp options or
internally-saved transmission timestamps).

This fix applies a floor of 1 for the RTT sample delta from TCP
timestamps, so that seq_rtt_us, ca_rtt_us, and rs->rtt_us will be at
least 1 * (USEC_PER_SEC / TCP_TS_HZ).

Note that the receiver RTT computation in tcp_rcv_rtt_measure() and
min_rtt computation in tcp_update_rtt_min() both already apply a floor
of 1 timestamp tick, so this commit makes the code more consistent in
avoiding this edge case of a value of 0.

Signed-off-by: Jianfeng Wang <jfwang@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Kevin Yang <yyd@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 5040f7ca37ec..ab5358281000 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2944,6 +2944,8 @@ static bool tcp_ack_update_rtt(struct sock *sk, const int flag,
 		u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr;
 
 		if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) {
+			if (!delta)
+				delta = 1;
 			seq_rtt_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
 			ca_rtt_us = seq_rtt_us;
 		}
-- 
2.26.2


[-- Attachment #3: net_57.mbox --]
[-- Type: Application/Octet-Stream, Size: 76583 bytes --]

From 3f3d91df7f616d4725fc126783ee832f9e65d548 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 29 Jul 2020 11:37:13 +0300
Subject: [PATCH 01/26] ipv4: Silence suspicious RCU usage warning

[ Upstream commit 83f3522860f702748143e022f1a546547314c715 ]

fib_trie_unmerge() is called with RTNL held, but not from an RCU
read-side critical section. This leads to the following warning [1] when
the FIB alias list in a leaf is traversed with
hlist_for_each_entry_rcu().

Since the function is always called with RTNL held and since
modification of the list is protected by RTNL, simply use
hlist_for_each_entry() and silence the warning.

[1]
WARNING: suspicious RCU usage
5.8.0-rc4-custom-01520-gc1f937f3f83b #30 Not tainted
-----------------------------
net/ipv4/fib_trie.c:1867 RCU-list traversed in non-reader section!!

other info that might help us debug this:

rcu_scheduler_active = 2, debug_locks = 1
1 lock held by ip/164:
 #0: ffffffff85a27850 (rtnl_mutex){+.+.}-{3:3}, at: rtnetlink_rcv_msg+0x49a/0xbd0

stack backtrace:
CPU: 0 PID: 164 Comm: ip Not tainted 5.8.0-rc4-custom-01520-gc1f937f3f83b #30
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-2.fc32 04/01/2014
Call Trace:
 dump_stack+0x100/0x184
 lockdep_rcu_suspicious+0x153/0x15d
 fib_trie_unmerge+0x608/0xdb0
 fib_unmerge+0x44/0x360
 fib4_rule_configure+0xc8/0xad0
 fib_nl_newrule+0x37a/0x1dd0
 rtnetlink_rcv_msg+0x4f7/0xbd0
 netlink_rcv_skb+0x17a/0x480
 rtnetlink_rcv+0x22/0x30
 netlink_unicast+0x5ae/0x890
 netlink_sendmsg+0x98a/0xf40
 ____sys_sendmsg+0x879/0xa00
 ___sys_sendmsg+0x122/0x190
 __sys_sendmsg+0x103/0x1d0
 __x64_sys_sendmsg+0x7d/0xb0
 do_syscall_64+0x54/0xa0
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x7fc80a234e97
Code: Bad RIP value.
RSP: 002b:00007ffef8b66798 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007fc80a234e97
RDX: 0000000000000000 RSI: 00007ffef8b66800 RDI: 0000000000000003
RBP: 000000005f141b1c R08: 0000000000000001 R09: 0000000000000000
R10: 00007fc80a2a8ac0 R11: 0000000000000246 R12: 0000000000000001
R13: 0000000000000000 R14: 00007ffef8b67008 R15: 0000556fccb10020

Fixes: 0ddcf43d5d4a ("ipv4: FIB Local/MAIN table collapse")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fib_trie.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 248f1c1959a6..3c65f71d0e82 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1864,7 +1864,7 @@ struct fib_table *fib_trie_unmerge(struct fib_table *oldtb)
 	while ((l = leaf_walk_rcu(&tp, key)) != NULL) {
 		struct key_vector *local_l = NULL, *local_tp;
 
-		hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) {
+		hlist_for_each_entry(fa, &l->leaf, fa_list) {
 			struct fib_alias *new_fa;
 
 			if (local_tb->tb_id != fa->tb_id)
-- 
2.26.2


From 893ea9580facf08713eb06b135322700094ecb47 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sat, 25 Jul 2020 15:40:53 -0700
Subject: [PATCH 02/26] ipv6: fix memory leaks on IPV6_ADDRFORM path

[ Upstream commit 8c0de6e96c9794cb523a516c465991a70245da1c ]

IPV6_ADDRFORM causes resource leaks when converting an IPv6 socket
to IPv4, particularly struct ipv6_ac_socklist. Similar to
struct ipv6_mc_socklist, we should just close it on this path.

This bug can be easily reproduced with the following C program:

  #include <stdio.h>
  #include <string.h>
  #include <sys/types.h>
  #include <sys/socket.h>
  #include <arpa/inet.h>

  int main()
  {
    int s, value;
    struct sockaddr_in6 addr;
    struct ipv6_mreq m6;

    s = socket(AF_INET6, SOCK_DGRAM, 0);
    addr.sin6_family = AF_INET6;
    addr.sin6_port = htons(5000);
    inet_pton(AF_INET6, "::ffff:192.168.122.194", &addr.sin6_addr);
    connect(s, (struct sockaddr *)&addr, sizeof(addr));

    inet_pton(AF_INET6, "fe80::AAAA", &m6.ipv6mr_multiaddr);
    m6.ipv6mr_interface = 5;
    setsockopt(s, SOL_IPV6, IPV6_JOIN_ANYCAST, &m6, sizeof(m6));

    value = AF_INET;
    setsockopt(s, SOL_IPV6, IPV6_ADDRFORM, &value, sizeof(value));

    close(s);
    return 0;
  }

Reported-by: ch3332xr@gmail.com
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/addrconf.h   |  1 +
 net/ipv6/anycast.c       | 17 ++++++++++++-----
 net/ipv6/ipv6_sockglue.c |  1 +
 3 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index e0eabe58aa8b..d9c76c6d8f72 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -276,6 +276,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex,
 		      const struct in6_addr *addr);
 int ipv6_sock_ac_drop(struct sock *sk, int ifindex,
 		      const struct in6_addr *addr);
+void __ipv6_sock_ac_close(struct sock *sk);
 void ipv6_sock_ac_close(struct sock *sk);
 
 int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr);
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index fed91ab7ec46..cf3a88a10ddd 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -183,7 +183,7 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	return 0;
 }
 
-void ipv6_sock_ac_close(struct sock *sk)
+void __ipv6_sock_ac_close(struct sock *sk)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct net_device *dev = NULL;
@@ -191,10 +191,7 @@ void ipv6_sock_ac_close(struct sock *sk)
 	struct net *net = sock_net(sk);
 	int	prev_index;
 
-	if (!np->ipv6_ac_list)
-		return;
-
-	rtnl_lock();
+	ASSERT_RTNL();
 	pac = np->ipv6_ac_list;
 	np->ipv6_ac_list = NULL;
 
@@ -211,6 +208,16 @@ void ipv6_sock_ac_close(struct sock *sk)
 		sock_kfree_s(sk, pac, sizeof(*pac));
 		pac = next;
 	}
+}
+
+void ipv6_sock_ac_close(struct sock *sk)
+{
+	struct ipv6_pinfo *np = inet6_sk(sk);
+
+	if (!np->ipv6_ac_list)
+		return;
+	rtnl_lock();
+	__ipv6_sock_ac_close(sk);
 	rtnl_unlock();
 }
 
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index ff187fd2083f..f99d1641f602 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -205,6 +205,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 
 			fl6_free_socklist(sk);
 			__ipv6_sock_mc_close(sk);
+			__ipv6_sock_ac_close(sk);
 
 			/*
 			 * Sock is moving from IPv6 to IPv4 (sk_prot), so
-- 
2.26.2


From 6515261286b7a97a1276fc45d910f8eac9fcae1e Mon Sep 17 00:00:00 2001
From: Xiyu Yang <xiyuyang19@fudan.edu.cn>
Date: Sat, 25 Jul 2020 16:02:18 +0800
Subject: [PATCH 03/26] ipv6: Fix nexthop refcnt leak when creating ipv6 route
 info

[ Upstream commit 706ec919164622ff5ce822065472d0f30a9e9dd2 ]

ip6_route_info_create() invokes nexthop_get(), which increases the
refcount of the "nh".

When ip6_route_info_create() returns, local variable "nh" becomes
invalid, so the refcount should be decreased to keep refcount balanced.

The reference counting issue happens in one exception handling path of
ip6_route_info_create(). When nexthops can not be used with source
routing, the function forgets to decrease the refcnt increased by
nexthop_get(), causing a refcnt leak.

Fix this issue by pulling up the error source routing handling when
nexthops can not be used with source routing.

Fixes: f88d8ea67fbd ("ipv6: Plumb support for nexthop object in a fib6_info")
Signed-off-by: Xiyu Yang <xiyuyang19@fudan.edu.cn>
Signed-off-by: Xin Tan <tanxin.ctf@gmail.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index e8a184acf668..de25836e4dde 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3677,14 +3677,14 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 	rt->fib6_src.plen = cfg->fc_src_len;
 #endif
 	if (nh) {
-		if (!nexthop_get(nh)) {
-			NL_SET_ERR_MSG(extack, "Nexthop has been deleted");
-			goto out;
-		}
 		if (rt->fib6_src.plen) {
 			NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing");
 			goto out;
 		}
+		if (!nexthop_get(nh)) {
+			NL_SET_ERR_MSG(extack, "Nexthop has been deleted");
+			goto out;
+		}
 		rt->nh = nh;
 		fib6_nh = nexthop_fib6_nh(rt->nh);
 	} else {
-- 
2.26.2


From 04b353314cdfa2140b7dd27c875116d8ae9b9bfc Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ren=C3=A9=20van=20Dorst?= <opensource@vdorst.com>
Date: Thu, 23 Jul 2020 20:07:10 +0100
Subject: [PATCH 04/26] net: ethernet: mtk_eth_soc: Always call
 mtk_gmac0_rgmii_adjust() for mt7623
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 19016d93bfc335f0c158c0d9e3b9d06c4dd53d39 ]

Modify mtk_gmac0_rgmii_adjust() so it can always be called.
mtk_gmac0_rgmii_adjust() sets-up the TRGMII clocks.

Signed-off-by: René van Dorst <opensource@vdorst.com>
Signed-off-By: David Woodhouse <dwmw2@infradead.org>
Tested-by: Frank Wunderlich <frank-w@public-files.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c | 19 ++++++++++++++-----
 1 file changed, 14 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index b743d8b56c84..82f5690ff4d3 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -171,11 +171,21 @@ static int mt7621_gmac0_rgmii_adjust(struct mtk_eth *eth,
 	return 0;
 }
 
-static void mtk_gmac0_rgmii_adjust(struct mtk_eth *eth, int speed)
+static void mtk_gmac0_rgmii_adjust(struct mtk_eth *eth,
+				   phy_interface_t interface, int speed)
 {
 	u32 val;
 	int ret;
 
+	if (interface == PHY_INTERFACE_MODE_TRGMII) {
+		mtk_w32(eth, TRGMII_MODE, INTF_MODE);
+		val = 500000000;
+		ret = clk_set_rate(eth->clks[MTK_CLK_TRGPLL], val);
+		if (ret)
+			dev_err(eth->dev, "Failed to set trgmii pll: %d\n", ret);
+		return;
+	}
+
 	val = (speed == SPEED_1000) ?
 		INTF_MODE_RGMII_1000 : INTF_MODE_RGMII_10_100;
 	mtk_w32(eth, val, INTF_MODE);
@@ -262,10 +272,9 @@ static void mtk_mac_config(struct phylink_config *config, unsigned int mode,
 							      state->interface))
 					goto err_phy;
 			} else {
-				if (state->interface !=
-				    PHY_INTERFACE_MODE_TRGMII)
-					mtk_gmac0_rgmii_adjust(mac->hw,
-							       state->speed);
+				mtk_gmac0_rgmii_adjust(mac->hw,
+						       state->interface,
+						       state->speed);
 
 				/* mt7623_pad_clk_setup */
 				for (i = 0 ; i < NUM_TRGMII_CTRL; i++)
-- 
2.26.2


From c5334aa658ff385be365eeaa7c509b24762d5fac Mon Sep 17 00:00:00 2001
From: laurent brando <laurent.brando@nxp.com>
Date: Mon, 27 Jul 2020 18:26:14 +0800
Subject: [PATCH 05/26] net: mscc: ocelot: fix hardware timestamp dequeue logic

[ Upstream commit 5fd82200d870a5dd3e509c98ef2041f580b2c0e1 ]

The next hw timestamp should be snapshoot to the read registers
only once the current timestamp has been read.
If none of the pending skbs matches the current HW timestamp
just gracefully flush the available timestamp by reading it.

Signed-off-by: laurent brando <laurent.brando@nxp.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: Yangbo Lu <yangbo.lu@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index efb3965a3e42..76dbf9ac8ad5 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -749,21 +749,21 @@ void ocelot_get_txtstamp(struct ocelot *ocelot)
 
 		spin_unlock_irqrestore(&port->tx_skbs.lock, flags);
 
-		/* Next ts */
-		ocelot_write(ocelot, SYS_PTP_NXT_PTP_NXT, SYS_PTP_NXT);
+		/* Get the h/w timestamp */
+		ocelot_get_hwtimestamp(ocelot, &ts);
 
 		if (unlikely(!skb_match))
 			continue;
 
-		/* Get the h/w timestamp */
-		ocelot_get_hwtimestamp(ocelot, &ts);
-
 		/* Set the timestamp into the skb */
 		memset(&shhwtstamps, 0, sizeof(shhwtstamps));
 		shhwtstamps.hwtstamp = ktime_set(ts.tv_sec, ts.tv_nsec);
 		skb_tstamp_tx(skb_match, &shhwtstamps);
 
 		dev_kfree_skb_any(skb_match);
+
+		/* Next ts */
+		ocelot_write(ocelot, SYS_PTP_NXT_PTP_NXT, SYS_PTP_NXT);
 	}
 }
 EXPORT_SYMBOL(ocelot_get_txtstamp);
-- 
2.26.2


From 22a608816c4a2bc438f460201da26d1f30e752c4 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 29 Jul 2020 00:03:56 +0100
Subject: [PATCH 06/26] rxrpc: Fix race between recvmsg and sendmsg on
 immediate call failure

[ Upstream commit 65550098c1c4db528400c73acf3e46bfa78d9264 ]

There's a race between rxrpc_sendmsg setting up a call, but then failing to
send anything on it due to an error, and recvmsg() seeing the call
completion occur and trying to return the state to the user.

An assertion fails in rxrpc_recvmsg() because the call has already been
released from the socket and is about to be released again as recvmsg deals
with it.  (The recvmsg_q queue on the socket holds a ref, so there's no
problem with use-after-free.)

We also have to be careful not to end up reporting an error twice, in such
a way that both returns indicate to userspace that the user ID supplied
with the call is no longer in use - which could cause the client to
malfunction if it recycles the user ID fast enough.

Fix this by the following means:

 (1) When sendmsg() creates a call after the point that the call has been
     successfully added to the socket, don't return any errors through
     sendmsg(), but rather complete the call and let recvmsg() retrieve
     them.  Make sendmsg() return 0 at this point.  Further calls to
     sendmsg() for that call will fail with ESHUTDOWN.

     Note that at this point, we haven't send any packets yet, so the
     server doesn't yet know about the call.

 (2) If sendmsg() returns an error when it was expected to create a new
     call, it means that the user ID wasn't used.

 (3) Mark the call disconnected before marking it completed to prevent an
     oops in rxrpc_release_call().

 (4) recvmsg() will then retrieve the error and set MSG_EOR to indicate
     that the user ID is no longer known by the kernel.

An oops like the following is produced:

	kernel BUG at net/rxrpc/recvmsg.c:605!
	...
	RIP: 0010:rxrpc_recvmsg+0x256/0x5ae
	...
	Call Trace:
	 ? __init_waitqueue_head+0x2f/0x2f
	 ____sys_recvmsg+0x8a/0x148
	 ? import_iovec+0x69/0x9c
	 ? copy_msghdr_from_user+0x5c/0x86
	 ___sys_recvmsg+0x72/0xaa
	 ? __fget_files+0x22/0x57
	 ? __fget_light+0x46/0x51
	 ? fdget+0x9/0x1b
	 do_recvmmsg+0x15e/0x232
	 ? _raw_spin_unlock+0xa/0xb
	 ? vtime_delta+0xf/0x25
	 __x64_sys_recvmmsg+0x2c/0x2f
	 do_syscall_64+0x4c/0x78
	 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 357f5ef64628 ("rxrpc: Call rxrpc_release_call() on error in rxrpc_new_client_call()")
Reported-by: syzbot+b54969381df354936d96@syzkaller.appspotmail.com
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Marc Dionne <marc.dionne@auristor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/call_object.c | 27 +++++++++++++++++++--------
 net/rxrpc/conn_object.c |  8 +++++---
 net/rxrpc/recvmsg.c     |  2 +-
 net/rxrpc/sendmsg.c     |  3 +++
 4 files changed, 28 insertions(+), 12 deletions(-)

diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index f07970207b54..38a46167523f 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -288,7 +288,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
 	 */
 	ret = rxrpc_connect_call(rx, call, cp, srx, gfp);
 	if (ret < 0)
-		goto error;
+		goto error_attached_to_socket;
 
 	trace_rxrpc_call(call->debug_id, rxrpc_call_connected,
 			 atomic_read(&call->usage), here, NULL);
@@ -308,18 +308,29 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
 error_dup_user_ID:
 	write_unlock(&rx->call_lock);
 	release_sock(&rx->sk);
-	ret = -EEXIST;
-
-error:
 	__rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR,
-				    RX_CALL_DEAD, ret);
+				    RX_CALL_DEAD, -EEXIST);
 	trace_rxrpc_call(call->debug_id, rxrpc_call_error,
-			 atomic_read(&call->usage), here, ERR_PTR(ret));
+			 atomic_read(&call->usage), here, ERR_PTR(-EEXIST));
 	rxrpc_release_call(rx, call);
 	mutex_unlock(&call->user_mutex);
 	rxrpc_put_call(call, rxrpc_call_put);
-	_leave(" = %d", ret);
-	return ERR_PTR(ret);
+	_leave(" = -EEXIST");
+	return ERR_PTR(-EEXIST);
+
+	/* We got an error, but the call is attached to the socket and is in
+	 * need of release.  However, we might now race with recvmsg() when
+	 * completing the call queues it.  Return 0 from sys_sendmsg() and
+	 * leave the error to recvmsg() to deal with.
+	 */
+error_attached_to_socket:
+	trace_rxrpc_call(call->debug_id, rxrpc_call_error,
+			 atomic_read(&call->usage), here, ERR_PTR(ret));
+	set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
+	__rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR,
+				    RX_CALL_DEAD, ret);
+	_leave(" = c=%08x [err]", call->debug_id);
+	return call;
 }
 
 /*
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index 19e141eeed17..8cbe0bf20ed5 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -212,9 +212,11 @@ void rxrpc_disconnect_call(struct rxrpc_call *call)
 
 	call->peer->cong_cwnd = call->cong_cwnd;
 
-	spin_lock_bh(&conn->params.peer->lock);
-	hlist_del_rcu(&call->error_link);
-	spin_unlock_bh(&conn->params.peer->lock);
+	if (!hlist_unhashed(&call->error_link)) {
+		spin_lock_bh(&call->peer->lock);
+		hlist_del_rcu(&call->error_link);
+		spin_unlock_bh(&call->peer->lock);
+	}
 
 	if (rxrpc_is_client_call(call))
 		return rxrpc_disconnect_client_call(call);
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index 6896a33ef842..4f48e3bdd4b4 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -541,7 +541,7 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 			goto error_unlock_call;
 	}
 
-	if (msg->msg_name) {
+	if (msg->msg_name && call->peer) {
 		struct sockaddr_rxrpc *srx = msg->msg_name;
 		size_t len = sizeof(call->peer->srx);
 
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 49d03c8c64da..1a340eb0abf7 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -683,6 +683,9 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
 		if (IS_ERR(call))
 			return PTR_ERR(call);
 		/* ... and we have the call lock. */
+		ret = 0;
+		if (READ_ONCE(call->state) == RXRPC_CALL_COMPLETE)
+			goto out_put_unlock;
 	} else {
 		switch (READ_ONCE(call->state)) {
 		case RXRPC_CALL_UNINITIALISED:
-- 
2.26.2


From 63572232c716b80880b9925920798488eb08a0ac Mon Sep 17 00:00:00 2001
From: Rustam Kovhaev <rkovhaev@gmail.com>
Date: Mon, 27 Jul 2020 23:42:17 -0700
Subject: [PATCH 07/26] usb: hso: check for return value in
 hso_serial_common_create()

[ Upstream commit e911e99a0770f760377c263bc7bac1b1593c6147 ]

in case of an error tty_register_device_attr() returns ERR_PTR(),
add IS_ERR() check

Reported-and-tested-by: syzbot+67b2bd0e34f952d0321e@syzkaller.appspotmail.com
Link: https://syzkaller.appspot.com/bug?extid=67b2bd0e34f952d0321e
Signed-off-by: Rustam Kovhaev <rkovhaev@gmail.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/hso.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c
index 5f123a8cf68e..d2fdb5430d27 100644
--- a/drivers/net/usb/hso.c
+++ b/drivers/net/usb/hso.c
@@ -2261,12 +2261,14 @@ static int hso_serial_common_create(struct hso_serial *serial, int num_urbs,
 
 	minor = get_free_serial_index();
 	if (minor < 0)
-		goto exit;
+		goto exit2;
 
 	/* register our minor number */
 	serial->parent->dev = tty_port_register_device_attr(&serial->port,
 			tty_drv, minor, &serial->parent->interface->dev,
 			serial->parent, hso_serial_dev_groups);
+	if (IS_ERR(serial->parent->dev))
+		goto exit2;
 
 	/* fill in specific data for later use */
 	serial->minor = minor;
@@ -2311,6 +2313,7 @@ static int hso_serial_common_create(struct hso_serial *serial, int num_urbs,
 	return 0;
 exit:
 	hso_serial_tty_unregister(serial);
+exit2:
 	hso_serial_common_free(serial);
 	return -1;
 }
-- 
2.26.2


From 7c9407793e5f94efc926155dc3f1f7b370a7d784 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 29 Jul 2020 11:34:36 +0300
Subject: [PATCH 08/26] vxlan: Ensure FDB dump is performed under RCU

[ Upstream commit b5141915b5aec3b29a63db869229e3741ebce258 ]

The commit cited below removed the RCU read-side critical section from
rtnl_fdb_dump() which means that the ndo_fdb_dump() callback is invoked
without RCU protection.

This results in the following warning [1] in the VXLAN driver, which
relied on the callback being invoked from an RCU read-side critical
section.

Fix this by calling rcu_read_lock() in the VXLAN driver, as already done
in the bridge driver.

[1]
WARNING: suspicious RCU usage
5.8.0-rc4-custom-01521-g481007553ce6 #29 Not tainted
-----------------------------
drivers/net/vxlan.c:1379 RCU-list traversed in non-reader section!!

other info that might help us debug this:

rcu_scheduler_active = 2, debug_locks = 1
1 lock held by bridge/166:
 #0: ffffffff85a27850 (rtnl_mutex){+.+.}-{3:3}, at: netlink_dump+0xea/0x1090

stack backtrace:
CPU: 1 PID: 166 Comm: bridge Not tainted 5.8.0-rc4-custom-01521-g481007553ce6 #29
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-2.fc32 04/01/2014
Call Trace:
 dump_stack+0x100/0x184
 lockdep_rcu_suspicious+0x153/0x15d
 vxlan_fdb_dump+0x51e/0x6d0
 rtnl_fdb_dump+0x4dc/0xad0
 netlink_dump+0x540/0x1090
 __netlink_dump_start+0x695/0x950
 rtnetlink_rcv_msg+0x802/0xbd0
 netlink_rcv_skb+0x17a/0x480
 rtnetlink_rcv+0x22/0x30
 netlink_unicast+0x5ae/0x890
 netlink_sendmsg+0x98a/0xf40
 __sys_sendto+0x279/0x3b0
 __x64_sys_sendto+0xe6/0x1a0
 do_syscall_64+0x54/0xa0
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x7fe14fa2ade0
Code: Bad RIP value.
RSP: 002b:00007fff75bb5b88 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 00005614b1ba0020 RCX: 00007fe14fa2ade0
RDX: 000000000000011c RSI: 00007fff75bb5b90 RDI: 0000000000000003
RBP: 00007fff75bb5b90 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00005614b1b89160
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000

Fixes: 5e6d24358799 ("bridge: netlink dump interface at par with brctl")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 6e64bc8d601f..7eab0dc27dd7 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1225,6 +1225,7 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
 	for (h = 0; h < FDB_HASH_SIZE; ++h) {
 		struct vxlan_fdb *f;
 
+		rcu_read_lock();
 		hlist_for_each_entry_rcu(f, &vxlan->fdb_head[h], hlist) {
 			struct vxlan_rdst *rd;
 
@@ -1237,12 +1238,15 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
 						     cb->nlh->nlmsg_seq,
 						     RTM_NEWNEIGH,
 						     NLM_F_MULTI, rd);
-				if (err < 0)
+				if (err < 0) {
+					rcu_read_unlock();
 					goto out;
+				}
 skip:
 				*idx += 1;
 			}
 		}
+		rcu_read_unlock();
 	}
 out:
 	return err;
-- 
2.26.2


From b2e50e99a7bcdae6f1c2f78ae1429de4d85dd5df Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Tue, 28 Jul 2020 14:10:31 +0200
Subject: [PATCH 09/26] net: lan78xx: replace bogus endpoint lookup

[ Upstream commit ea060b352654a8de1e070140d25fe1b7e4d50310 ]

Drop the bogus endpoint-lookup helper which could end up accepting
interfaces based on endpoints belonging to unrelated altsettings.

Note that the returned bulk pipes and interrupt endpoint descriptor
were never actually used. Instead the bulk-endpoint numbers are
hardcoded to 1 and 2 (matching the specification), while the interrupt-
endpoint descriptor was assumed to be the third descriptor created by
USB core.

Try to bring some order to this by dropping the bogus lookup helper and
adding the missing endpoint sanity checks while keeping the interrupt-
descriptor assumption for now.

Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/lan78xx.c | 117 ++++++++++----------------------------
 1 file changed, 30 insertions(+), 87 deletions(-)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index ee062b27cfa7..442507f25aad 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -377,10 +377,6 @@ struct lan78xx_net {
 	struct tasklet_struct	bh;
 	struct delayed_work	wq;
 
-	struct usb_host_endpoint *ep_blkin;
-	struct usb_host_endpoint *ep_blkout;
-	struct usb_host_endpoint *ep_intr;
-
 	int			msg_enable;
 
 	struct urb		*urb_intr;
@@ -2860,78 +2856,12 @@ lan78xx_start_xmit(struct sk_buff *skb, struct net_device *net)
 	return NETDEV_TX_OK;
 }
 
-static int
-lan78xx_get_endpoints(struct lan78xx_net *dev, struct usb_interface *intf)
-{
-	int tmp;
-	struct usb_host_interface *alt = NULL;
-	struct usb_host_endpoint *in = NULL, *out = NULL;
-	struct usb_host_endpoint *status = NULL;
-
-	for (tmp = 0; tmp < intf->num_altsetting; tmp++) {
-		unsigned ep;
-
-		in = NULL;
-		out = NULL;
-		status = NULL;
-		alt = intf->altsetting + tmp;
-
-		for (ep = 0; ep < alt->desc.bNumEndpoints; ep++) {
-			struct usb_host_endpoint *e;
-			int intr = 0;
-
-			e = alt->endpoint + ep;
-			switch (e->desc.bmAttributes) {
-			case USB_ENDPOINT_XFER_INT:
-				if (!usb_endpoint_dir_in(&e->desc))
-					continue;
-				intr = 1;
-				/* FALLTHROUGH */
-			case USB_ENDPOINT_XFER_BULK:
-				break;
-			default:
-				continue;
-			}
-			if (usb_endpoint_dir_in(&e->desc)) {
-				if (!intr && !in)
-					in = e;
-				else if (intr && !status)
-					status = e;
-			} else {
-				if (!out)
-					out = e;
-			}
-		}
-		if (in && out)
-			break;
-	}
-	if (!alt || !in || !out)
-		return -EINVAL;
-
-	dev->pipe_in = usb_rcvbulkpipe(dev->udev,
-				       in->desc.bEndpointAddress &
-				       USB_ENDPOINT_NUMBER_MASK);
-	dev->pipe_out = usb_sndbulkpipe(dev->udev,
-					out->desc.bEndpointAddress &
-					USB_ENDPOINT_NUMBER_MASK);
-	dev->ep_intr = status;
-
-	return 0;
-}
-
 static int lan78xx_bind(struct lan78xx_net *dev, struct usb_interface *intf)
 {
 	struct lan78xx_priv *pdata = NULL;
 	int ret;
 	int i;
 
-	ret = lan78xx_get_endpoints(dev, intf);
-	if (ret) {
-		netdev_warn(dev->net, "lan78xx_get_endpoints failed: %d\n",
-			    ret);
-		return ret;
-	}
-
 	dev->data[0] = (unsigned long)kzalloc(sizeof(*pdata), GFP_KERNEL);
 
 	pdata = (struct lan78xx_priv *)(dev->data[0]);
@@ -3700,6 +3630,7 @@ static void lan78xx_stat_monitor(struct timer_list *t)
 static int lan78xx_probe(struct usb_interface *intf,
 			 const struct usb_device_id *id)
 {
+	struct usb_host_endpoint *ep_blkin, *ep_blkout, *ep_intr;
 	struct lan78xx_net *dev;
 	struct net_device *netdev;
 	struct usb_device *udev;
@@ -3748,6 +3679,34 @@ static int lan78xx_probe(struct usb_interface *intf,
 
 	mutex_init(&dev->stats.access_lock);
 
+	if (intf->cur_altsetting->desc.bNumEndpoints < 3) {
+		ret = -ENODEV;
+		goto out2;
+	}
+
+	dev->pipe_in = usb_rcvbulkpipe(udev, BULK_IN_PIPE);
+	ep_blkin = usb_pipe_endpoint(udev, dev->pipe_in);
+	if (!ep_blkin || !usb_endpoint_is_bulk_in(&ep_blkin->desc)) {
+		ret = -ENODEV;
+		goto out2;
+	}
+
+	dev->pipe_out = usb_sndbulkpipe(udev, BULK_OUT_PIPE);
+	ep_blkout = usb_pipe_endpoint(udev, dev->pipe_out);
+	if (!ep_blkout || !usb_endpoint_is_bulk_out(&ep_blkout->desc)) {
+		ret = -ENODEV;
+		goto out2;
+	}
+
+	ep_intr = &intf->cur_altsetting->endpoint[2];
+	if (!usb_endpoint_is_int_in(&ep_intr->desc)) {
+		ret = -ENODEV;
+		goto out2;
+	}
+
+	dev->pipe_intr = usb_rcvintpipe(dev->udev,
+					usb_endpoint_num(&ep_intr->desc));
+
 	ret = lan78xx_bind(dev, intf);
 	if (ret < 0)
 		goto out2;
@@ -3759,23 +3718,7 @@ static int lan78xx_probe(struct usb_interface *intf,
 	netdev->max_mtu = MAX_SINGLE_PACKET_SIZE;
 	netif_set_gso_max_size(netdev, MAX_SINGLE_PACKET_SIZE - MAX_HEADER);
 
-	if (intf->cur_altsetting->desc.bNumEndpoints < 3) {
-		ret = -ENODEV;
-		goto out3;
-	}
-
-	dev->ep_blkin = (intf->cur_altsetting)->endpoint + 0;
-	dev->ep_blkout = (intf->cur_altsetting)->endpoint + 1;
-	dev->ep_intr = (intf->cur_altsetting)->endpoint + 2;
-
-	dev->pipe_in = usb_rcvbulkpipe(udev, BULK_IN_PIPE);
-	dev->pipe_out = usb_sndbulkpipe(udev, BULK_OUT_PIPE);
-
-	dev->pipe_intr = usb_rcvintpipe(dev->udev,
-					dev->ep_intr->desc.bEndpointAddress &
-					USB_ENDPOINT_NUMBER_MASK);
-	period = dev->ep_intr->desc.bInterval;
-
+	period = ep_intr->desc.bInterval;
 	maxp = usb_maxpacket(dev->udev, dev->pipe_intr, 0);
 	buf = kmalloc(maxp, GFP_KERNEL);
 	if (buf) {
-- 
2.26.2


From be097dab8fb7f670d897a44700a85ace72e73a9b Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Fri, 24 Jul 2020 20:14:34 +1000
Subject: [PATCH 10/26] rhashtable: Restore RCU marking on rhash_lock_head

[ Upstream commit ce9b362bf6db51a083c4221ef0f93c16cfb1facf ]

This patch restores the RCU marking on bucket_table->buckets as
it really does need RCU protection.  Its removal had led to a fatal
bug.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable.h | 56 ++++++++++++++++----------------------
 lib/rhashtable.c           | 35 +++++++++++-------------
 2 files changed, 40 insertions(+), 51 deletions(-)

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index e3def7bbe932..83ad875a7ea2 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -84,7 +84,7 @@ struct bucket_table {
 
 	struct lockdep_map	dep_map;
 
-	struct rhash_lock_head *buckets[] ____cacheline_aligned_in_smp;
+	struct rhash_lock_head __rcu *buckets[] ____cacheline_aligned_in_smp;
 };
 
 /*
@@ -261,13 +261,12 @@ void rhashtable_free_and_destroy(struct rhashtable *ht,
 				 void *arg);
 void rhashtable_destroy(struct rhashtable *ht);
 
-struct rhash_lock_head **rht_bucket_nested(const struct bucket_table *tbl,
-					   unsigned int hash);
-struct rhash_lock_head **__rht_bucket_nested(const struct bucket_table *tbl,
-					     unsigned int hash);
-struct rhash_lock_head **rht_bucket_nested_insert(struct rhashtable *ht,
-						  struct bucket_table *tbl,
-						  unsigned int hash);
+struct rhash_lock_head __rcu **rht_bucket_nested(
+	const struct bucket_table *tbl, unsigned int hash);
+struct rhash_lock_head __rcu **__rht_bucket_nested(
+	const struct bucket_table *tbl, unsigned int hash);
+struct rhash_lock_head __rcu **rht_bucket_nested_insert(
+	struct rhashtable *ht, struct bucket_table *tbl, unsigned int hash);
 
 #define rht_dereference(p, ht) \
 	rcu_dereference_protected(p, lockdep_rht_mutex_is_held(ht))
@@ -284,21 +283,21 @@ struct rhash_lock_head **rht_bucket_nested_insert(struct rhashtable *ht,
 #define rht_entry(tpos, pos, member) \
 	({ tpos = container_of(pos, typeof(*tpos), member); 1; })
 
-static inline struct rhash_lock_head *const *rht_bucket(
+static inline struct rhash_lock_head __rcu *const *rht_bucket(
 	const struct bucket_table *tbl, unsigned int hash)
 {
 	return unlikely(tbl->nest) ? rht_bucket_nested(tbl, hash) :
 				     &tbl->buckets[hash];
 }
 
-static inline struct rhash_lock_head **rht_bucket_var(
+static inline struct rhash_lock_head __rcu **rht_bucket_var(
 	struct bucket_table *tbl, unsigned int hash)
 {
 	return unlikely(tbl->nest) ? __rht_bucket_nested(tbl, hash) :
 				     &tbl->buckets[hash];
 }
 
-static inline struct rhash_lock_head **rht_bucket_insert(
+static inline struct rhash_lock_head __rcu **rht_bucket_insert(
 	struct rhashtable *ht, struct bucket_table *tbl, unsigned int hash)
 {
 	return unlikely(tbl->nest) ? rht_bucket_nested_insert(ht, tbl, hash) :
@@ -325,7 +324,7 @@ static inline struct rhash_lock_head **rht_bucket_insert(
  */
 
 static inline void rht_lock(struct bucket_table *tbl,
-			    struct rhash_lock_head **bkt)
+			    struct rhash_lock_head __rcu **bkt)
 {
 	local_bh_disable();
 	bit_spin_lock(0, (unsigned long *)bkt);
@@ -333,7 +332,7 @@ static inline void rht_lock(struct bucket_table *tbl,
 }
 
 static inline void rht_lock_nested(struct bucket_table *tbl,
-				   struct rhash_lock_head **bucket,
+				   struct rhash_lock_head __rcu **bucket,
 				   unsigned int subclass)
 {
 	local_bh_disable();
@@ -342,7 +341,7 @@ static inline void rht_lock_nested(struct bucket_table *tbl,
 }
 
 static inline void rht_unlock(struct bucket_table *tbl,
-			      struct rhash_lock_head **bkt)
+			      struct rhash_lock_head __rcu **bkt)
 {
 	lock_map_release(&tbl->dep_map);
 	bit_spin_unlock(0, (unsigned long *)bkt);
@@ -365,48 +364,41 @@ static inline struct rhash_head *__rht_ptr(
  *            access is guaranteed, such as when destroying the table.
  */
 static inline struct rhash_head *rht_ptr_rcu(
-	struct rhash_lock_head *const *p)
+	struct rhash_lock_head __rcu *const *bkt)
 {
-	struct rhash_lock_head __rcu *const *bkt = (void *)p;
 	return __rht_ptr(rcu_dereference(*bkt), bkt);
 }
 
 static inline struct rhash_head *rht_ptr(
-	struct rhash_lock_head *const *p,
+	struct rhash_lock_head __rcu *const *bkt,
 	struct bucket_table *tbl,
 	unsigned int hash)
 {
-	struct rhash_lock_head __rcu *const *bkt = (void *)p;
 	return __rht_ptr(rht_dereference_bucket(*bkt, tbl, hash), bkt);
 }
 
 static inline struct rhash_head *rht_ptr_exclusive(
-	struct rhash_lock_head *const *p)
+	struct rhash_lock_head __rcu *const *bkt)
 {
-	struct rhash_lock_head __rcu *const *bkt = (void *)p;
 	return __rht_ptr(rcu_dereference_protected(*bkt, 1), bkt);
 }
 
-static inline void rht_assign_locked(struct rhash_lock_head **bkt,
+static inline void rht_assign_locked(struct rhash_lock_head __rcu **bkt,
 				     struct rhash_head *obj)
 {
-	struct rhash_head __rcu **p = (struct rhash_head __rcu **)bkt;
-
 	if (rht_is_a_nulls(obj))
 		obj = NULL;
-	rcu_assign_pointer(*p, (void *)((unsigned long)obj | BIT(0)));
+	rcu_assign_pointer(*bkt, (void *)((unsigned long)obj | BIT(0)));
 }
 
 static inline void rht_assign_unlock(struct bucket_table *tbl,
-				     struct rhash_lock_head **bkt,
+				     struct rhash_lock_head __rcu **bkt,
 				     struct rhash_head *obj)
 {
-	struct rhash_head __rcu **p = (struct rhash_head __rcu **)bkt;
-
 	if (rht_is_a_nulls(obj))
 		obj = NULL;
 	lock_map_release(&tbl->dep_map);
-	rcu_assign_pointer(*p, obj);
+	rcu_assign_pointer(*bkt, (void *)obj);
 	preempt_enable();
 	__release(bitlock);
 	local_bh_enable();
@@ -594,7 +586,7 @@ static inline struct rhash_head *__rhashtable_lookup(
 		.ht = ht,
 		.key = key,
 	};
-	struct rhash_lock_head *const *bkt;
+	struct rhash_lock_head __rcu *const *bkt;
 	struct bucket_table *tbl;
 	struct rhash_head *he;
 	unsigned int hash;
@@ -710,7 +702,7 @@ static inline void *__rhashtable_insert_fast(
 		.ht = ht,
 		.key = key,
 	};
-	struct rhash_lock_head **bkt;
+	struct rhash_lock_head __rcu **bkt;
 	struct rhash_head __rcu **pprev;
 	struct bucket_table *tbl;
 	struct rhash_head *head;
@@ -996,7 +988,7 @@ static inline int __rhashtable_remove_fast_one(
 	struct rhash_head *obj, const struct rhashtable_params params,
 	bool rhlist)
 {
-	struct rhash_lock_head **bkt;
+	struct rhash_lock_head __rcu **bkt;
 	struct rhash_head __rcu **pprev;
 	struct rhash_head *he;
 	unsigned int hash;
@@ -1148,7 +1140,7 @@ static inline int __rhashtable_replace_fast(
 	struct rhash_head *obj_old, struct rhash_head *obj_new,
 	const struct rhashtable_params params)
 {
-	struct rhash_lock_head **bkt;
+	struct rhash_lock_head __rcu **bkt;
 	struct rhash_head __rcu **pprev;
 	struct rhash_head *he;
 	unsigned int hash;
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index bdb7e4cadf05..da531dacb496 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -31,7 +31,7 @@
 
 union nested_table {
 	union nested_table __rcu *table;
-	struct rhash_lock_head *bucket;
+	struct rhash_lock_head __rcu *bucket;
 };
 
 static u32 head_hashfn(struct rhashtable *ht,
@@ -213,7 +213,7 @@ static struct bucket_table *rhashtable_last_table(struct rhashtable *ht,
 }
 
 static int rhashtable_rehash_one(struct rhashtable *ht,
-				 struct rhash_lock_head **bkt,
+				 struct rhash_lock_head __rcu **bkt,
 				 unsigned int old_hash)
 {
 	struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht);
@@ -266,7 +266,7 @@ static int rhashtable_rehash_chain(struct rhashtable *ht,
 				    unsigned int old_hash)
 {
 	struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht);
-	struct rhash_lock_head **bkt = rht_bucket_var(old_tbl, old_hash);
+	struct rhash_lock_head __rcu **bkt = rht_bucket_var(old_tbl, old_hash);
 	int err;
 
 	if (!bkt)
@@ -476,7 +476,7 @@ static int rhashtable_insert_rehash(struct rhashtable *ht,
 }
 
 static void *rhashtable_lookup_one(struct rhashtable *ht,
-				   struct rhash_lock_head **bkt,
+				   struct rhash_lock_head __rcu **bkt,
 				   struct bucket_table *tbl, unsigned int hash,
 				   const void *key, struct rhash_head *obj)
 {
@@ -526,12 +526,10 @@ static void *rhashtable_lookup_one(struct rhashtable *ht,
 	return ERR_PTR(-ENOENT);
 }
 
-static struct bucket_table *rhashtable_insert_one(struct rhashtable *ht,
-						  struct rhash_lock_head **bkt,
-						  struct bucket_table *tbl,
-						  unsigned int hash,
-						  struct rhash_head *obj,
-						  void *data)
+static struct bucket_table *rhashtable_insert_one(
+	struct rhashtable *ht, struct rhash_lock_head __rcu **bkt,
+	struct bucket_table *tbl, unsigned int hash, struct rhash_head *obj,
+	void *data)
 {
 	struct bucket_table *new_tbl;
 	struct rhash_head *head;
@@ -582,7 +580,7 @@ static void *rhashtable_try_insert(struct rhashtable *ht, const void *key,
 {
 	struct bucket_table *new_tbl;
 	struct bucket_table *tbl;
-	struct rhash_lock_head **bkt;
+	struct rhash_lock_head __rcu **bkt;
 	unsigned int hash;
 	void *data;
 
@@ -1164,8 +1162,8 @@ void rhashtable_destroy(struct rhashtable *ht)
 }
 EXPORT_SYMBOL_GPL(rhashtable_destroy);
 
-struct rhash_lock_head **__rht_bucket_nested(const struct bucket_table *tbl,
-					     unsigned int hash)
+struct rhash_lock_head __rcu **__rht_bucket_nested(
+	const struct bucket_table *tbl, unsigned int hash)
 {
 	const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *));
 	unsigned int index = hash & ((1 << tbl->nest) - 1);
@@ -1193,10 +1191,10 @@ struct rhash_lock_head **__rht_bucket_nested(const struct bucket_table *tbl,
 }
 EXPORT_SYMBOL_GPL(__rht_bucket_nested);
 
-struct rhash_lock_head **rht_bucket_nested(const struct bucket_table *tbl,
-					   unsigned int hash)
+struct rhash_lock_head __rcu **rht_bucket_nested(
+	const struct bucket_table *tbl, unsigned int hash)
 {
-	static struct rhash_lock_head *rhnull;
+	static struct rhash_lock_head __rcu *rhnull;
 
 	if (!rhnull)
 		INIT_RHT_NULLS_HEAD(rhnull);
@@ -1204,9 +1202,8 @@ struct rhash_lock_head **rht_bucket_nested(const struct bucket_table *tbl,
 }
 EXPORT_SYMBOL_GPL(rht_bucket_nested);
 
-struct rhash_lock_head **rht_bucket_nested_insert(struct rhashtable *ht,
-						  struct bucket_table *tbl,
-						  unsigned int hash)
+struct rhash_lock_head __rcu **rht_bucket_nested_insert(
+	struct rhashtable *ht, struct bucket_table *tbl, unsigned int hash)
 {
 	const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *));
 	unsigned int index = hash & ((1 << tbl->nest) - 1);
-- 
2.26.2


From b1d020bd2803f75aa3c34843d98ad7e5fd710a1c Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 28 Jul 2020 16:15:07 -0700
Subject: [PATCH 11/26] devlink: ignore -EOPNOTSUPP errors on dumpit

[ Upstream commit 82274d075536322368ce710b211c41c37c4740b9 ]

Number of .dumpit functions try to ignore -EOPNOTSUPP errors.
Recent change missed that, and started reporting all errors
but -EMSGSIZE back from dumps. This leads to situation like
this:

$ devlink dev info
devlink answers: Operation not supported

Dump should not report an error just because the last device
to be queried could not provide an answer.

To fix this and avoid similar confusion make sure we clear
err properly, and not leave it set to an error if we don't
terminate the iteration.

Fixes: c62c2cfb801b ("net: devlink: don't ignore errors during dumpit")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/devlink.c | 24 ++++++++++++++++++------
 1 file changed, 18 insertions(+), 6 deletions(-)

diff --git a/net/core/devlink.c b/net/core/devlink.c
index 899edcee7dab..8547da27ea47 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -1065,7 +1065,9 @@ static int devlink_nl_cmd_sb_pool_get_dumpit(struct sk_buff *msg,
 						   devlink_sb,
 						   NETLINK_CB(cb->skb).portid,
 						   cb->nlh->nlmsg_seq);
-			if (err && err != -EOPNOTSUPP) {
+			if (err == -EOPNOTSUPP) {
+				err = 0;
+			} else if (err) {
 				mutex_unlock(&devlink->lock);
 				goto out;
 			}
@@ -1266,7 +1268,9 @@ static int devlink_nl_cmd_sb_port_pool_get_dumpit(struct sk_buff *msg,
 							devlink, devlink_sb,
 							NETLINK_CB(cb->skb).portid,
 							cb->nlh->nlmsg_seq);
-			if (err && err != -EOPNOTSUPP) {
+			if (err == -EOPNOTSUPP) {
+				err = 0;
+			} else if (err) {
 				mutex_unlock(&devlink->lock);
 				goto out;
 			}
@@ -1498,7 +1502,9 @@ devlink_nl_cmd_sb_tc_pool_bind_get_dumpit(struct sk_buff *msg,
 							   devlink_sb,
 							   NETLINK_CB(cb->skb).portid,
 							   cb->nlh->nlmsg_seq);
-			if (err && err != -EOPNOTSUPP) {
+			if (err == -EOPNOTSUPP) {
+				err = 0;
+			} else if (err) {
 				mutex_unlock(&devlink->lock);
 				goto out;
 			}
@@ -3299,7 +3305,9 @@ static int devlink_nl_cmd_param_get_dumpit(struct sk_buff *msg,
 						    NETLINK_CB(cb->skb).portid,
 						    cb->nlh->nlmsg_seq,
 						    NLM_F_MULTI);
-			if (err && err != -EOPNOTSUPP) {
+			if (err == -EOPNOTSUPP) {
+				err = 0;
+			} else if (err) {
 				mutex_unlock(&devlink->lock);
 				goto out;
 			}
@@ -3569,7 +3577,9 @@ static int devlink_nl_cmd_port_param_get_dumpit(struct sk_buff *msg,
 						NETLINK_CB(cb->skb).portid,
 						cb->nlh->nlmsg_seq,
 						NLM_F_MULTI);
-				if (err && err != -EOPNOTSUPP) {
+				if (err == -EOPNOTSUPP) {
+					err = 0;
+				} else if (err) {
 					mutex_unlock(&devlink->lock);
 					goto out;
 				}
@@ -4479,7 +4489,9 @@ static int devlink_nl_cmd_info_get_dumpit(struct sk_buff *msg,
 					   cb->nlh->nlmsg_seq, NLM_F_MULTI,
 					   cb->extack);
 		mutex_unlock(&devlink->lock);
-		if (err && err != -EOPNOTSUPP)
+		if (err == -EOPNOTSUPP)
+			err = 0;
+		else if (err)
 			break;
 		idx++;
 	}
-- 
2.26.2


From 8d9136fee21c4402d696d4221a9276c6bac236fa Mon Sep 17 00:00:00 2001
From: Vincent Duvert <vincent.ldev@duvert.net>
Date: Sun, 2 Aug 2020 07:06:51 +0200
Subject: [PATCH 12/26] appletalk: Fix atalk_proc_init() return path

[ Upstream commit d0f6ba2ef2c1c95069509e71402e7d6d43452512 ]

Add a missing return statement to atalk_proc_init so it doesn't return
-ENOMEM when successful.  This allows the appletalk module to load
properly.

Fixes: e2bcd8b0ce6e ("appletalk: use remove_proc_subtree to simplify procfs code")
Link: https://www.downtowndougbrown.com/2020/08/hacking-up-a-fix-for-the-broken-appletalk-kernel-module-in-linux-5-1-and-newer/
Reported-by: Christopher KOBAYASHI <chris@disavowed.jp>
Reported-by: Doug Brown <doug@downtowndougbrown.com>
Signed-off-by: Vincent Duvert <vincent.ldev@duvert.net>
[lukas: add missing tags]
Signed-off-by: Lukas Wunner <lukas@wunner.de>
Cc: stable@vger.kernel.org # v5.1+
Cc: Yue Haibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/appletalk/atalk_proc.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/appletalk/atalk_proc.c b/net/appletalk/atalk_proc.c
index 550c6ca007cc..9c1241292d1d 100644
--- a/net/appletalk/atalk_proc.c
+++ b/net/appletalk/atalk_proc.c
@@ -229,6 +229,8 @@ int __init atalk_proc_init(void)
 				     sizeof(struct aarp_iter_state), NULL))
 		goto out;
 
+	return 0;
+
 out:
 	remove_proc_subtree("atalk", init_net.proc_net);
 	return -ENOMEM;
-- 
2.26.2


From aa7d2a2dfdaa4584bca52e7c38214aad5c0d03fe Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Tue, 4 Aug 2020 21:26:43 +0800
Subject: [PATCH 13/26] dpaa2-eth: Fix passing zero to 'PTR_ERR' warning

[ Upstream commit 02afa9c66bb954c6959877c70d9e128dcf0adce7 ]

Fix smatch warning:

drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c:2419
 alloc_channel() warn: passing zero to 'ERR_PTR'

setup_dpcon() should return ERR_PTR(err) instead of zero in error
handling case.

Fixes: d7f5a9d89a55 ("dpaa2-eth: defer probe on object allocate")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 72fa9c4e058f..b7031f8562e0 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -2120,7 +2120,7 @@ static struct fsl_mc_device *setup_dpcon(struct dpaa2_eth_priv *priv)
 free:
 	fsl_mc_object_free(dpcon);
 
-	return NULL;
+	return ERR_PTR(err);
 }
 
 static void free_dpcon(struct dpaa2_eth_priv *priv,
@@ -2144,8 +2144,8 @@ alloc_channel(struct dpaa2_eth_priv *priv)
 		return NULL;
 
 	channel->dpcon = setup_dpcon(priv);
-	if (IS_ERR_OR_NULL(channel->dpcon)) {
-		err = PTR_ERR_OR_ZERO(channel->dpcon);
+	if (IS_ERR(channel->dpcon)) {
+		err = PTR_ERR(channel->dpcon);
 		goto err_setup;
 	}
 
-- 
2.26.2


From 52d070dc048efe31d9a2151ba7fe256ed94972da Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Tue, 4 Aug 2020 09:54:15 -0700
Subject: [PATCH 14/26] hv_netvsc: do not use VF device if link is down

[ Upstream commit 7c9864bbccc23e1812ac82966555d68c13ea4006 ]

If the accelerated networking SRIOV VF device has lost carrier
use the synthetic network device which is available as backup
path. This is a rare case since if VF link goes down, normally
the VMBus device will also loose external connectivity as well.
But if the communication is between two VM's on the same host
the VMBus device will still work.

Reported-by: "Shah, Ashish N" <ashish.n.shah@intel.com>
Fixes: 0c195567a8f6 ("netvsc: transparent VF management")
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/netvsc_drv.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index ebcfbae05690..b8b7fc13b3dc 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -532,12 +532,13 @@ static int netvsc_xmit(struct sk_buff *skb, struct net_device *net, bool xdp_tx)
 	u32 hash;
 	struct hv_page_buffer pb[MAX_PAGE_BUFFER_COUNT];
 
-	/* if VF is present and up then redirect packets
-	 * already called with rcu_read_lock_bh
+	/* If VF is present and up then redirect packets to it.
+	 * Skip the VF if it is marked down or has no carrier.
+	 * If netpoll is in uses, then VF can not be used either.
 	 */
 	vf_netdev = rcu_dereference_bh(net_device_ctx->vf_netdev);
 	if (vf_netdev && netif_running(vf_netdev) &&
-	    !netpoll_tx_running(net))
+	    netif_carrier_ok(vf_netdev) && !netpoll_tx_running(net))
 		return netvsc_vf_xmit(net, vf_netdev, skb);
 
 	/* We will atmost need two pages to describe the rndis
-- 
2.26.2


From ef40ac8c293d87befce0b281a7cbc47c05680b11 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Fri, 31 Jul 2020 19:26:16 +0300
Subject: [PATCH 15/26] net: bridge: clear bridge's private skb space on xmit

[ Upstream commit fd65e5a95d08389444e8591a20538b3edece0e15 ]

We need to clear all of the bridge private skb variables as they can be
stale due to the packet being recirculated through the stack and then
transmitted through the bridge device. Similar memset is already done on
bridge's input. We've seen cases where proxyarp_replied was 1 on routed
multicast packets transmitted through the bridge to ports with neigh
suppress which were getting dropped. Same thing can in theory happen with
the port isolation bit as well.

Fixes: 821f1b21cabb ("bridge: add new BR_NEIGH_SUPPRESS port flag to suppress arp and nd flood")
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_device.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 0e3dbc5f3c34..22a0b3173456 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -36,6 +36,8 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 	const unsigned char *dest;
 	u16 vid = 0;
 
+	memset(skb->cb, 0, sizeof(struct br_input_skb_cb));
+
 	rcu_read_lock();
 	nf_ops = rcu_dereference(nf_br_ops);
 	if (nf_ops && nf_ops->br_dev_xmit_hook(skb)) {
-- 
2.26.2


From c378631494741b5ed2bbd0e6f31fb108d42bfeff Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Fri, 31 Jul 2020 20:12:05 +0200
Subject: [PATCH 16/26] net: gre: recompute gre csum for sctp over gre tunnels

[ Upstream commit 622e32b7d4a6492cf5c1f759ef833f817418f7b3 ]

The GRE tunnel can be used to transport traffic that does not rely on a
Internet checksum (e.g. SCTP). The issue can be triggered creating a GRE
or GRETAP tunnel and transmitting SCTP traffic ontop of it where CRC
offload has been disabled. In order to fix the issue we need to
recompute the GRE csum in gre_gso_segment() not relying on the inner
checksum.
The issue is still present when we have the CRC offload enabled.
In this case we need to disable the CRC offload if we require GRE
checksum since otherwise skb_checksum() will report a wrong value.

Fixes: 90017accff61 ("sctp: Add GSO support")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/gre_offload.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index 2e6d1b7a7bc9..e0a246575887 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -15,12 +15,12 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 				       netdev_features_t features)
 {
 	int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb);
+	bool need_csum, need_recompute_csum, gso_partial;
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	u16 mac_offset = skb->mac_header;
 	__be16 protocol = skb->protocol;
 	u16 mac_len = skb->mac_len;
 	int gre_offset, outer_hlen;
-	bool need_csum, gso_partial;
 
 	if (!skb->encapsulation)
 		goto out;
@@ -41,6 +41,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 	skb->protocol = skb->inner_protocol;
 
 	need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_GRE_CSUM);
+	need_recompute_csum = skb->csum_not_inet;
 	skb->encap_hdr_csum = need_csum;
 
 	features &= skb->dev->hw_enc_features;
@@ -98,7 +99,15 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 		}
 
 		*(pcsum + 1) = 0;
-		*pcsum = gso_make_checksum(skb, 0);
+		if (need_recompute_csum && !skb_is_gso(skb)) {
+			__wsum csum;
+
+			csum = skb_checksum(skb, gre_offset,
+					    skb->len - gre_offset, 0);
+			*pcsum = csum_fold(csum);
+		} else {
+			*pcsum = gso_make_checksum(skb, 0);
+		}
 	} while ((skb = skb->next));
 out:
 	return segs;
-- 
2.26.2


From c708d4ddf5ad9c7291805b249b2f3293e6c31010 Mon Sep 17 00:00:00 2001
From: Stefan Roese <sr@denx.de>
Date: Tue, 4 Aug 2020 14:17:16 +0200
Subject: [PATCH 17/26] net: macb: Properly handle phylink on at91sam9x

[ Upstream commit f7ba7dbf4f7af67b5936ff1cbd40a3254b409ebf ]

I just recently noticed that ethernet does not work anymore since v5.5
on the GARDENA smart Gateway, which is based on the AT91SAM9G25.
Debugging showed that the "GEM bits" in the NCFGR register are now
unconditionally accessed, which is incorrect for the !macb_is_gem()
case.

This patch adds the macb_is_gem() checks back to the code
(in macb_mac_config() & macb_mac_link_up()), so that the GEM register
bits are not accessed in this case any more.

Fixes: 7897b071ac3b ("net: macb: convert to phylink")
Signed-off-by: Stefan Roese <sr@denx.de>
Cc: Reto Schneider <reto.schneider@husqvarnagroup.com>
Cc: Alexandre Belloni <alexandre.belloni@bootlin.com>
Cc: Nicolas Ferre <nicolas.ferre@microchip.com>
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index f1f0976e7669..3a157be857b0 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -578,7 +578,7 @@ static void macb_mac_config(struct phylink_config *config, unsigned int mode,
 	if (bp->caps & MACB_CAPS_MACB_IS_EMAC) {
 		if (state->interface == PHY_INTERFACE_MODE_RMII)
 			ctrl |= MACB_BIT(RM9200_RMII);
-	} else {
+	} else if (macb_is_gem(bp)) {
 		ctrl &= ~(GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL));
 
 		if (state->interface == PHY_INTERFACE_MODE_SGMII)
@@ -639,10 +639,13 @@ static void macb_mac_link_up(struct phylink_config *config,
 		ctrl |= MACB_BIT(FD);
 
 	if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC)) {
-		ctrl &= ~(GEM_BIT(GBE) | MACB_BIT(PAE));
+		ctrl &= ~MACB_BIT(PAE);
+		if (macb_is_gem(bp)) {
+			ctrl &= ~GEM_BIT(GBE);
 
-		if (speed == SPEED_1000)
-			ctrl |= GEM_BIT(GBE);
+			if (speed == SPEED_1000)
+				ctrl |= GEM_BIT(GBE);
+		}
 
 		/* We do not support MLO_PAUSE_RX yet */
 		if (tx_pause)
-- 
2.26.2


From c132b0fc5583e360c2a440b0b5353633140be16a Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Fri, 31 Jul 2020 10:38:32 +0200
Subject: [PATCH 18/26] net: mvpp2: fix memory leak in mvpp2_rx

[ Upstream commit d6526926de7397a97308780911565e31a6b67b59 ]

Release skb memory in mvpp2_rx() if mvpp2_rx_refill routine fails

Fixes: b5015854674b ("net: mvpp2: fix refilling BM pools in RX path")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Acked-by: Matteo Croce <mcroce@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 24f4d8e0da98..ee72397813d4 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -2981,6 +2981,7 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi,
 		err = mvpp2_rx_refill(port, bm_pool, pool);
 		if (err) {
 			netdev_err(port->dev, "failed to refill BM pools\n");
+			dev_kfree_skb_any(skb);
 			goto err_drop_frame;
 		}
 
-- 
2.26.2


From 1c5cd5d1e1d74f7f8837c5daff91bfed03a29df1 Mon Sep 17 00:00:00 2001
From: wenxu <wenxu@ucloud.cn>
Date: Fri, 31 Jul 2020 10:45:01 +0800
Subject: [PATCH 19/26] net/sched: act_ct: fix miss set mru for ovs after
 defrag in act_ct

[ Upstream commit 038ebb1a713d114d54dbf14868a73181c0c92758 ]

When openvswitch conntrack offload with act_ct action. Fragment packets
defrag in the ingress tc act_ct action and miss the next chain. Then the
packet pass to the openvswitch datapath without the mru. The over
mtu packet will be dropped in output action in openvswitch for over mtu.

"kernel: net2: dropped over-mtu packet: 1528 > 1500"

This patch add mru in the tc_skb_ext for adefrag and miss next chain
situation. And also add mru in the qdisc_skb_cb. The act_ct set the mru
to the qdisc_skb_cb when the packet defrag. And When the chain miss,
The mru is set to tc_skb_ext which can be got by ovs datapath.

Fixes: b57dc7c13ea9 ("net/sched: Introduce action ct")
Signed-off-by: wenxu <wenxu@ucloud.cn>
Reviewed-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h    | 1 +
 include/net/sch_generic.h | 3 ++-
 net/openvswitch/flow.c    | 1 +
 net/sched/act_ct.c        | 8 ++++++--
 net/sched/cls_api.c       | 1 +
 5 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 7e737a94bc63..7f348591647a 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -283,6 +283,7 @@ struct nf_bridge_info {
  */
 struct tc_skb_ext {
 	__u32 chain;
+	__u16 mru;
 };
 #endif
 
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 8428aa614265..f6bcd3960ba8 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -380,6 +380,7 @@ struct qdisc_skb_cb {
 	};
 #define QDISC_CB_PRIV_LEN 20
 	unsigned char		data[QDISC_CB_PRIV_LEN];
+	u16			mru;
 };
 
 typedef void tcf_chain_head_change_t(struct tcf_proto *tp_head, void *priv);
@@ -459,7 +460,7 @@ static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz)
 {
 	struct qdisc_skb_cb *qcb;
 
-	BUILD_BUG_ON(sizeof(skb->cb) < offsetof(struct qdisc_skb_cb, data) + sz);
+	BUILD_BUG_ON(sizeof(skb->cb) < sizeof(*qcb));
 	BUILD_BUG_ON(sizeof(qcb->data) < sz);
 }
 
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 9d375e74b607..03942c30d83e 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -890,6 +890,7 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
 	if (static_branch_unlikely(&tc_recirc_sharing_support)) {
 		tc_ext = skb_ext_find(skb, TC_SKB_EXT);
 		key->recirc_id = tc_ext ? tc_ext->chain : 0;
+		OVS_CB(skb)->mru = tc_ext ? tc_ext->mru : 0;
 	} else {
 		key->recirc_id = 0;
 	}
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index e191f2728389..417526d7741b 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -704,8 +704,10 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
 		if (err && err != -EINPROGRESS)
 			goto out_free;
 
-		if (!err)
+		if (!err) {
 			*defrag = true;
+			cb.mru = IPCB(skb)->frag_max_size;
+		}
 	} else { /* NFPROTO_IPV6 */
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
 		enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone;
@@ -715,8 +717,10 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
 		if (err && err != -EINPROGRESS)
 			goto out_free;
 
-		if (!err)
+		if (!err) {
 			*defrag = true;
+			cb.mru = IP6CB(skb)->frag_max_size;
+		}
 #else
 		err = -EOPNOTSUPP;
 		goto out_free;
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 58d469a66896..2ef39483a8bb 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1679,6 +1679,7 @@ int tcf_classify_ingress(struct sk_buff *skb,
 		if (WARN_ON_ONCE(!ext))
 			return TC_ACT_SHOT;
 		ext->chain = last_executed_chain;
+		ext->mru = qdisc_skb_cb(skb)->mru;
 	}
 
 	return ret;
-- 
2.26.2


From fc5ff7c39fc12f2935923dc2599ebc5840367728 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 4 Aug 2020 15:02:30 +0800
Subject: [PATCH 20/26] net: thunderx: use spin_lock_bh in
 nicvf_set_rx_mode_task()

[ Upstream commit bab9693a9a8c6dd19f670408ec1e78e12a320682 ]

A dead lock was triggered on thunderx driver:

        CPU0                    CPU1
        ----                    ----
   [01] lock(&(&nic->rx_mode_wq_lock)->rlock);
                           [11] lock(&(&mc->mca_lock)->rlock);
                           [12] lock(&(&nic->rx_mode_wq_lock)->rlock);
   [02] <Interrupt> lock(&(&mc->mca_lock)->rlock);

The path for each is:

  [01] worker_thread() -> process_one_work() -> nicvf_set_rx_mode_task()
  [02] mld_ifc_timer_expire()
  [11] ipv6_add_dev() -> ipv6_dev_mc_inc() -> igmp6_group_added() ->
  [12] dev_mc_add() -> __dev_set_rx_mode() -> nicvf_set_rx_mode()

To fix it, it needs to disable bh on [1], so that the timer on [2]
wouldn't be triggered until rx_mode_wq_lock is released. So change
to use spin_lock_bh() instead of spin_lock().

Thanks to Paolo for helping with this.

v1->v2:
  - post to netdev.

Reported-by: Rafael P. <rparrazo@redhat.com>
Tested-by: Dean Nelson <dnelson@redhat.com>
Fixes: 469998c861fa ("net: thunderx: prevent concurrent data re-writing by nicvf_set_rx_mode")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/thunder/nicvf_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index b4b33368698f..ae48f2e9265f 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -2041,11 +2041,11 @@ static void nicvf_set_rx_mode_task(struct work_struct *work_arg)
 	/* Save message data locally to prevent them from
 	 * being overwritten by next ndo_set_rx_mode call().
 	 */
-	spin_lock(&nic->rx_mode_wq_lock);
+	spin_lock_bh(&nic->rx_mode_wq_lock);
 	mode = vf_work->mode;
 	mc = vf_work->mc;
 	vf_work->mc = NULL;
-	spin_unlock(&nic->rx_mode_wq_lock);
+	spin_unlock_bh(&nic->rx_mode_wq_lock);
 
 	__nicvf_set_rx_mode_task(mode, mc, nic);
 }
-- 
2.26.2


From 17340a0e34c9ec3cc0a5a6820793c7f5b740b4be Mon Sep 17 00:00:00 2001
From: Peilin Ye <yepeilin.cs@gmail.com>
Date: Fri, 31 Jul 2020 00:48:38 -0400
Subject: [PATCH 21/26] openvswitch: Prevent kernel-infoleak in
 ovs_ct_put_key()

[ Upstream commit 9aba6c5b49254d5bee927d81593ed4429e91d4ae ]

ovs_ct_put_key() is potentially copying uninitialized kernel stack memory
into socket buffers, since the compiler may leave a 3-byte hole at the end
of `struct ovs_key_ct_tuple_ipv4` and `struct ovs_key_ct_tuple_ipv6`. Fix
it by initializing `orig` with memset().

Fixes: 9dd7f8907c37 ("openvswitch: Add original direction conntrack tuple to sw_flow_key.")
Suggested-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Peilin Ye <yepeilin.cs@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/openvswitch/conntrack.c | 38 +++++++++++++++++++------------------
 1 file changed, 20 insertions(+), 18 deletions(-)

diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 4340f25fe390..98d393e70de3 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -276,10 +276,6 @@ void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key)
 	ovs_ct_update_key(skb, NULL, key, false, false);
 }
 
-#define IN6_ADDR_INITIALIZER(ADDR) \
-	{ (ADDR).s6_addr32[0], (ADDR).s6_addr32[1], \
-	  (ADDR).s6_addr32[2], (ADDR).s6_addr32[3] }
-
 int ovs_ct_put_key(const struct sw_flow_key *swkey,
 		   const struct sw_flow_key *output, struct sk_buff *skb)
 {
@@ -301,24 +297,30 @@ int ovs_ct_put_key(const struct sw_flow_key *swkey,
 
 	if (swkey->ct_orig_proto) {
 		if (swkey->eth.type == htons(ETH_P_IP)) {
-			struct ovs_key_ct_tuple_ipv4 orig = {
-				output->ipv4.ct_orig.src,
-				output->ipv4.ct_orig.dst,
-				output->ct.orig_tp.src,
-				output->ct.orig_tp.dst,
-				output->ct_orig_proto,
-			};
+			struct ovs_key_ct_tuple_ipv4 orig;
+
+			memset(&orig, 0, sizeof(orig));
+			orig.ipv4_src = output->ipv4.ct_orig.src;
+			orig.ipv4_dst = output->ipv4.ct_orig.dst;
+			orig.src_port = output->ct.orig_tp.src;
+			orig.dst_port = output->ct.orig_tp.dst;
+			orig.ipv4_proto = output->ct_orig_proto;
+
 			if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4,
 				    sizeof(orig), &orig))
 				return -EMSGSIZE;
 		} else if (swkey->eth.type == htons(ETH_P_IPV6)) {
-			struct ovs_key_ct_tuple_ipv6 orig = {
-				IN6_ADDR_INITIALIZER(output->ipv6.ct_orig.src),
-				IN6_ADDR_INITIALIZER(output->ipv6.ct_orig.dst),
-				output->ct.orig_tp.src,
-				output->ct.orig_tp.dst,
-				output->ct_orig_proto,
-			};
+			struct ovs_key_ct_tuple_ipv6 orig;
+
+			memset(&orig, 0, sizeof(orig));
+			memcpy(orig.ipv6_src, output->ipv6.ct_orig.src.s6_addr32,
+			       sizeof(orig.ipv6_src));
+			memcpy(orig.ipv6_dst, output->ipv6.ct_orig.dst.s6_addr32,
+			       sizeof(orig.ipv6_dst));
+			orig.src_port = output->ct.orig_tp.src;
+			orig.dst_port = output->ct.orig_tp.dst;
+			orig.ipv6_proto = output->ct_orig_proto;
+
 			if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6,
 				    sizeof(orig), &orig))
 				return -EMSGSIZE;
-- 
2.26.2


From 08d6dee39a8e3acbc74b6c349ca7adac58a79c3b Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Wed, 5 Aug 2020 10:41:31 +0800
Subject: [PATCH 22/26] Revert "vxlan: fix tos value before xmit"

[ Upstream commit a0dced17ad9dc08b1b25e0065b54c97a318e6e8b ]

This reverts commit 71130f29979c7c7956b040673e6b9d5643003176.

In commit 71130f29979c ("vxlan: fix tos value before xmit") we want to
make sure the tos value are filtered by RT_TOS() based on RFC1349.

       0     1     2     3     4     5     6     7
    +-----+-----+-----+-----+-----+-----+-----+-----+
    |   PRECEDENCE    |          TOS          | MBZ |
    +-----+-----+-----+-----+-----+-----+-----+-----+

But RFC1349 has been obsoleted by RFC2474. The new DSCP field defined like

       0     1     2     3     4     5     6     7
    +-----+-----+-----+-----+-----+-----+-----+-----+
    |          DS FIELD, DSCP           | ECN FIELD |
    +-----+-----+-----+-----+-----+-----+-----+-----+

So with

IPTOS_TOS_MASK          0x1E
RT_TOS(tos)		((tos)&IPTOS_TOS_MASK)

the first 3 bits DSCP info will get lost.

To take all the DSCP info in xmit, we should revert the patch and just push
all tos bits to ip_tunnel_ecn_encap(), which will handling ECN field later.

Fixes: 71130f29979c ("vxlan: fix tos value before xmit")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Acked-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 7eab0dc27dd7..b78bb5c558ff 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2550,7 +2550,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		ndst = &rt->dst;
 		skb_tunnel_check_pmtu(skb, ndst, VXLAN_HEADROOM);
 
-		tos = ip_tunnel_ecn_encap(RT_TOS(tos), old_iph, skb);
+		tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
 		ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
 		err = vxlan_build_skb(skb, ndst, sizeof(struct iphdr),
 				      vni, md, flags, udp_sum);
@@ -2590,7 +2590,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 
 		skb_tunnel_check_pmtu(skb, ndst, VXLAN6_HEADROOM);
 
-		tos = ip_tunnel_ecn_encap(RT_TOS(tos), old_iph, skb);
+		tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
 		ttl = ttl ? : ip6_dst_hoplimit(ndst);
 		skb_scrub_packet(skb, xnet);
 		err = vxlan_build_skb(skb, ndst, sizeof(struct ipv6hdr),
-- 
2.26.2


From ce8f17a3b4deca8bf01cc013f232d63e58faeb74 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 5 Aug 2020 04:40:45 -0400
Subject: [PATCH 23/26] selftests/net: relax cpu affinity requirement in
 msg_zerocopy test

[ Upstream commit 16f6458f2478b55e2b628797bc81a4455045c74e ]

The msg_zerocopy test pins the sender and receiver threads to separate
cores to reduce variance between runs.

But it hardcodes the cores and skips core 0, so it fails on machines
with the selected cores offline, or simply fewer cores.

The test mainly gives code coverage in automated runs. The throughput
of zerocopy ('-z') and non-zerocopy runs is logged for manual
inspection.

Continue even when sched_setaffinity fails. Just log to warn anyone
interpreting the data.

Fixes: 07b65c5b31ce ("test: add msg_zerocopy test")
Reported-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/msg_zerocopy.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/net/msg_zerocopy.c b/tools/testing/selftests/net/msg_zerocopy.c
index 4b02933cab8a..bdc03a2097e8 100644
--- a/tools/testing/selftests/net/msg_zerocopy.c
+++ b/tools/testing/selftests/net/msg_zerocopy.c
@@ -125,9 +125,8 @@ static int do_setcpu(int cpu)
 	CPU_ZERO(&mask);
 	CPU_SET(cpu, &mask);
 	if (sched_setaffinity(0, sizeof(mask), &mask))
-		error(1, 0, "setaffinity %d", cpu);
-
-	if (cfg_verbose)
+		fprintf(stderr, "cpu: unable to pin, may increase variance.\n");
+	else if (cfg_verbose)
 		fprintf(stderr, "cpu: %u\n", cpu);
 
 	return 0;
-- 
2.26.2


From 25535cb708d3d4eb0c9a9658a94ec6417b29d24e Mon Sep 17 00:00:00 2001
From: Jianfeng Wang <jfwang@google.com>
Date: Thu, 30 Jul 2020 23:49:16 +0000
Subject: [PATCH 24/26] tcp: apply a floor of 1 for RTT samples from TCP
 timestamps

[ Upstream commit 730e700e2c19d87e578ff0e7d8cb1d4a02b036d2 ]

For retransmitted packets, TCP needs to resort to using TCP timestamps
for computing RTT samples. In the common case where the data and ACK
fall in the same 1-millisecond interval, TCP senders with millisecond-
granularity TCP timestamps compute a ca_rtt_us of 0. This ca_rtt_us
of 0 propagates to rs->rtt_us.

This value of 0 can cause performance problems for congestion control
modules. For example, in BBR, the zero min_rtt sample can bring the
min_rtt and BDP estimate down to 0, reduce snd_cwnd and result in a
low throughput. It would be hard to mitigate this with filtering in
the congestion control module, because the proper floor to apply would
depend on the method of RTT sampling (using timestamp options or
internally-saved transmission timestamps).

This fix applies a floor of 1 for the RTT sample delta from TCP
timestamps, so that seq_rtt_us, ca_rtt_us, and rs->rtt_us will be at
least 1 * (USEC_PER_SEC / TCP_TS_HZ).

Note that the receiver RTT computation in tcp_rcv_rtt_measure() and
min_rtt computation in tcp_update_rtt_min() both already apply a floor
of 1 timestamp tick, so this commit makes the code more consistent in
avoiding this edge case of a value of 0.

Signed-off-by: Jianfeng Wang <jfwang@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Kevin Yang <yyd@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 32ac66a8c657..afee982734be 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2945,6 +2945,8 @@ static bool tcp_ack_update_rtt(struct sock *sk, const int flag,
 		u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr;
 
 		if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) {
+			if (!delta)
+				delta = 1;
 			seq_rtt_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
 			ca_rtt_us = seq_rtt_us;
 		}
-- 
2.26.2


From b42d11d7f063b69f830e2aba84293737e5127cf9 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 4 Aug 2020 18:31:06 +0200
Subject: [PATCH 25/26] mptcp: be careful on subflow creation

[ Upstream commit adf7341064982de923a1f8a11bcdec48be6b3004 ]

Nicolas reported the following oops:

[ 1521.392541] BUG: kernel NULL pointer dereference, address: 00000000000000c0
[ 1521.394189] #PF: supervisor read access in kernel mode
[ 1521.395376] #PF: error_code(0x0000) - not-present page
[ 1521.396607] PGD 0 P4D 0
[ 1521.397156] Oops: 0000 [#1] SMP PTI
[ 1521.398020] CPU: 0 PID: 22986 Comm: kworker/0:2 Not tainted 5.8.0-rc4+ #109
[ 1521.399618] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014
[ 1521.401728] Workqueue: events mptcp_worker
[ 1521.402651] RIP: 0010:mptcp_subflow_create_socket+0xf1/0x1c0
[ 1521.403954] Code: 24 08 89 44 24 04 48 8b 7a 18 e8 2a 48 d4 ff 8b 44 24 04 85 c0 75 7a 48 8b 8b 78 02 00 00 48 8b 54 24 08 48 8d bb 80 00 00 00 <48> 8b 89 c0 00 00 00 48 89 8a c0 00 00 00 48 8b 8b 78 02 00 00 8b
[ 1521.408201] RSP: 0000:ffffabc4002d3c60 EFLAGS: 00010246
[ 1521.409433] RAX: 0000000000000000 RBX: ffffa0b9ad8c9a00 RCX: 0000000000000000
[ 1521.411096] RDX: ffffa0b9ae78a300 RSI: 00000000fffffe01 RDI: ffffa0b9ad8c9a80
[ 1521.412734] RBP: ffffa0b9adff2e80 R08: ffffa0b9af02d640 R09: ffffa0b9ad923a00
[ 1521.414333] R10: ffffabc4007139f8 R11: fefefefefefefeff R12: ffffabc4002d3cb0
[ 1521.415918] R13: ffffa0b9ad91fa58 R14: ffffa0b9ad8c9f9c R15: 0000000000000000
[ 1521.417592] FS:  0000000000000000(0000) GS:ffffa0b9af000000(0000) knlGS:0000000000000000
[ 1521.419490] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 1521.420839] CR2: 00000000000000c0 CR3: 000000002951e006 CR4: 0000000000160ef0
[ 1521.422511] Call Trace:
[ 1521.423103]  __mptcp_subflow_connect+0x94/0x1f0
[ 1521.425376]  mptcp_pm_create_subflow_or_signal_addr+0x200/0x2a0
[ 1521.426736]  mptcp_worker+0x31b/0x390
[ 1521.431324]  process_one_work+0x1fc/0x3f0
[ 1521.432268]  worker_thread+0x2d/0x3b0
[ 1521.434197]  kthread+0x117/0x130
[ 1521.435783]  ret_from_fork+0x22/0x30

on some unconventional configuration.

The MPTCP protocol is trying to create a subflow for an
unaccepted server socket. That is allowed by the RFC, even
if subflow creation will likely fail.
Unaccepted sockets have still a NULL sk_socket field,
avoid the issue by failing earlier.

Reported-and-tested-by: Nicolas Rybowski <nicolas.rybowski@tessares.net>
Fixes: 7d14b0d2b9b3 ("mptcp: set correct vfs info for subflows")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/subflow.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 0112ead58fd8..bb6ccde6bf49 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -999,6 +999,12 @@ int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock)
 	struct socket *sf;
 	int err;
 
+	/* un-accepted server sockets can reach here - on bad configuration
+	 * bail early to avoid greater trouble later
+	 */
+	if (unlikely(!sk->sk_socket))
+		return -EINVAL;
+
 	err = sock_create_kern(net, sk->sk_family, SOCK_STREAM, IPPROTO_TCP,
 			       &sf);
 	if (err)
-- 
2.26.2


From 244f8e034e30f2736219081af08b2e55d33eb713 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 3 Aug 2020 18:40:39 +0200
Subject: [PATCH 26/26] mptcp: fix bogus sendmsg() return code under pressure

[ Upstream commit 8555c6bfd5fddb1cf363d3cd157d70a1bb27f718 ]

In case of memory pressure, mptcp_sendmsg() may call
sk_stream_wait_memory() after succesfully xmitting some
bytes. If the latter fails we currently return to the
user-space the error code, ignoring the succeful xmit.

Address the issue always checking for the xmitted bytes
before mptcp_sendmsg() completes.

Fixes: f296234c98a8 ("mptcp: Add handling of incoming MP_JOIN requests")
Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/protocol.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 4bf4f629975d..54e200b1b742 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -802,7 +802,6 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	mptcp_set_timeout(sk, ssk);
 	if (copied) {
-		ret = copied;
 		tcp_push(ssk, msg->msg_flags, mss_now, tcp_sk(ssk)->nonagle,
 			 size_goal);
 
@@ -815,7 +814,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	release_sock(ssk);
 out:
 	release_sock(sk);
-	return ret;
+	return copied ? : ret;
 }
 
 static void mptcp_wait_data(struct sock *sk, long *timeo)
-- 
2.26.2

Re: [PATCHES] Networking

[Greg KH]

On Fri, Aug 07, 2020 at 06:53:27PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v5.4 and
> v5.7 -stable, respectively.
> 
> Thank you!

All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 105 bytes --]


Please queue up the following networking bug fixes for v5.7
and v5.8 -stable, respectively.

Thank you.

[-- Attachment #2: net_57.mbox --]
[-- Type: Application/Octet-Stream, Size: 34791 bytes --]

From 48a041a9b2f37615c8d848ec5c5b4d4215d278cc Mon Sep 17 00:00:00 2001
From: John Ogness <john.ogness@linutronix.de>
Date: Thu, 13 Aug 2020 21:45:25 +0206
Subject: [PATCH 01/13] af_packet: TPACKET_V3: fix fill status rwlock imbalance

[ Upstream commit 88fd1cb80daa20af063bce81e1fad14e945a8dc4 ]

After @blk_fill_in_prog_lock is acquired there is an early out vnet
situation that can occur. In that case, the rwlock needs to be
released.

Also, since @blk_fill_in_prog_lock is only acquired when @tp_version
is exactly TPACKET_V3, only release it on that exact condition as
well.

And finally, add sparse annotation so that it is clearer that
prb_fill_curr_block() and prb_clear_blk_fill_status() are acquiring
and releasing @blk_fill_in_prog_lock, respectively. sparse is still
unable to understand the balance, but the warnings are now on a
higher level that make more sense.

Fixes: 632ca50f2cbd ("af_packet: TPACKET_V3: replace busy-wait loop")
Signed-off-by: John Ogness <john.ogness@linutronix.de>
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 29bd405adbbd..301f41d4929b 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -942,6 +942,7 @@ static int prb_queue_frozen(struct tpacket_kbdq_core *pkc)
 }
 
 static void prb_clear_blk_fill_status(struct packet_ring_buffer *rb)
+	__releases(&pkc->blk_fill_in_prog_lock)
 {
 	struct tpacket_kbdq_core *pkc  = GET_PBDQC_FROM_RB(rb);
 	atomic_dec(&pkc->blk_fill_in_prog);
@@ -989,6 +990,7 @@ static void prb_fill_curr_block(char *curr,
 				struct tpacket_kbdq_core *pkc,
 				struct tpacket_block_desc *pbd,
 				unsigned int len)
+	__acquires(&pkc->blk_fill_in_prog_lock)
 {
 	struct tpacket3_hdr *ppd;
 
@@ -2286,8 +2288,11 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	if (do_vnet &&
 	    virtio_net_hdr_from_skb(skb, h.raw + macoff -
 				    sizeof(struct virtio_net_hdr),
-				    vio_le(), true, 0))
+				    vio_le(), true, 0)) {
+		if (po->tp_version == TPACKET_V3)
+			prb_clear_blk_fill_status(&po->rx_ring);
 		goto drop_n_account;
+	}
 
 	if (po->tp_version <= TPACKET_V2) {
 		packet_increment_rx_head(po, &po->rx_ring);
@@ -2393,7 +2398,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 		__clear_bit(slot_id, po->rx_ring.rx_owner_map);
 		spin_unlock(&sk->sk_receive_queue.lock);
 		sk->sk_data_ready(sk);
-	} else {
+	} else if (po->tp_version == TPACKET_V3) {
 		prb_clear_blk_fill_status(&po->rx_ring);
 	}
 
-- 
2.26.2


From 3f4e7d9ab7b3866804519710b2b1d1b2156fe191 Mon Sep 17 00:00:00 2001
From: Xie He <xie.he.0141@gmail.com>
Date: Wed, 5 Aug 2020 18:50:40 -0700
Subject: [PATCH 02/13] drivers/net/wan/lapbether: Added needed_headroom and a
 skb->len check

[ Upstream commit c7ca03c216acb14466a713fedf1b9f2c24994ef2 ]

1. Added a skb->len check

This driver expects upper layers to include a pseudo header of 1 byte
when passing down a skb for transmission. This driver will read this
1-byte header. This patch added a skb->len check before reading the
header to make sure the header exists.

2. Changed to use needed_headroom instead of hard_header_len to request
necessary headroom to be allocated

In net/packet/af_packet.c, the function packet_snd first reserves a
headroom of length (dev->hard_header_len + dev->needed_headroom).
Then if the socket is a SOCK_DGRAM socket, it calls dev_hard_header,
which calls dev->header_ops->create, to create the link layer header.
If the socket is a SOCK_RAW socket, it "un-reserves" a headroom of
length (dev->hard_header_len), and assumes the user to provide the
appropriate link layer header.

So according to the logic of af_packet.c, dev->hard_header_len should
be the length of the header that would be created by
dev->header_ops->create.

However, this driver doesn't provide dev->header_ops, so logically
dev->hard_header_len should be 0.

So we should use dev->needed_headroom instead of dev->hard_header_len
to request necessary headroom to be allocated.

This change fixes kernel panic when this driver is used with AF_PACKET
SOCK_RAW sockets.

Call stack when panic:

[  168.399197] skbuff: skb_under_panic: text:ffffffff819d95fb len:20
put:14 head:ffff8882704c0a00 data:ffff8882704c09fd tail:0x11 end:0xc0
dev:veth0
...
[  168.399255] Call Trace:
[  168.399259]  skb_push.cold+0x14/0x24
[  168.399262]  eth_header+0x2b/0xc0
[  168.399267]  lapbeth_data_transmit+0x9a/0xb0 [lapbether]
[  168.399275]  lapb_data_transmit+0x22/0x2c [lapb]
[  168.399277]  lapb_transmit_buffer+0x71/0xb0 [lapb]
[  168.399279]  lapb_kick+0xe3/0x1c0 [lapb]
[  168.399281]  lapb_data_request+0x76/0xc0 [lapb]
[  168.399283]  lapbeth_xmit+0x56/0x90 [lapbether]
[  168.399286]  dev_hard_start_xmit+0x91/0x1f0
[  168.399289]  ? irq_init_percpu_irqstack+0xc0/0x100
[  168.399291]  __dev_queue_xmit+0x721/0x8e0
[  168.399295]  ? packet_parse_headers.isra.0+0xd2/0x110
[  168.399297]  dev_queue_xmit+0x10/0x20
[  168.399298]  packet_sendmsg+0xbf0/0x19b0
......

Cc: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
Cc: Martin Schiller <ms@dev.tdt.de>
Cc: Brian Norris <briannorris@chromium.org>
Signed-off-by: Xie He <xie.he.0141@gmail.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wan/lapbether.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c
index b2868433718f..1ea15f2123ed 100644
--- a/drivers/net/wan/lapbether.c
+++ b/drivers/net/wan/lapbether.c
@@ -157,6 +157,12 @@ static netdev_tx_t lapbeth_xmit(struct sk_buff *skb,
 	if (!netif_running(dev))
 		goto drop;
 
+	/* There should be a pseudo header of 1 byte added by upper layers.
+	 * Check to make sure it is there before reading it.
+	 */
+	if (skb->len < 1)
+		goto drop;
+
 	switch (skb->data[0]) {
 	case X25_IFACE_DATA:
 		break;
@@ -305,6 +311,7 @@ static void lapbeth_setup(struct net_device *dev)
 	dev->netdev_ops	     = &lapbeth_netdev_ops;
 	dev->needs_free_netdev = true;
 	dev->type            = ARPHRD_X25;
+	dev->hard_header_len = 0;
 	dev->mtu             = 1000;
 	dev->addr_len        = 0;
 }
@@ -331,7 +338,8 @@ static int lapbeth_new_device(struct net_device *dev)
 	 * then this driver prepends a length field of 2 bytes,
 	 * then the underlying Ethernet device prepends its own header.
 	 */
-	ndev->hard_header_len = -1 + 3 + 2 + dev->hard_header_len;
+	ndev->needed_headroom = -1 + 3 + 2 + dev->hard_header_len
+					   + dev->needed_headroom;
 
 	lapbeth = netdev_priv(ndev);
 	lapbeth->axdev = ndev;
-- 
2.26.2


From cca1045109df9444c9c699e202f33a467d1660b7 Mon Sep 17 00:00:00 2001
From: Miaohe Lin <linmiaohe@huawei.com>
Date: Mon, 10 Aug 2020 08:16:58 -0400
Subject: [PATCH 03/13] net: Fix potential memory leak in proto_register()

[ Upstream commit 0f5907af39137f8183ed536aaa00f322d7365130 ]

If we failed to assign proto idx, we free the twsk_slab_name but forget to
free the twsk_slab. Add a helper function tw_prot_cleanup() to free these
together and also use this helper function in proto_unregister().

Fixes: b45ce32135d1 ("sock: fix potential memory leak in proto_register()")
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 25 +++++++++++++++----------
 1 file changed, 15 insertions(+), 10 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index bc6fe4114374..7b0feeea61b6 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -3354,6 +3354,16 @@ static void sock_inuse_add(struct net *net, int val)
 }
 #endif
 
+static void tw_prot_cleanup(struct timewait_sock_ops *twsk_prot)
+{
+	if (!twsk_prot)
+		return;
+	kfree(twsk_prot->twsk_slab_name);
+	twsk_prot->twsk_slab_name = NULL;
+	kmem_cache_destroy(twsk_prot->twsk_slab);
+	twsk_prot->twsk_slab = NULL;
+}
+
 static void req_prot_cleanup(struct request_sock_ops *rsk_prot)
 {
 	if (!rsk_prot)
@@ -3424,7 +3434,7 @@ int proto_register(struct proto *prot, int alloc_slab)
 						  prot->slab_flags,
 						  NULL);
 			if (prot->twsk_prot->twsk_slab == NULL)
-				goto out_free_timewait_sock_slab_name;
+				goto out_free_timewait_sock_slab;
 		}
 	}
 
@@ -3432,15 +3442,15 @@ int proto_register(struct proto *prot, int alloc_slab)
 	ret = assign_proto_idx(prot);
 	if (ret) {
 		mutex_unlock(&proto_list_mutex);
-		goto out_free_timewait_sock_slab_name;
+		goto out_free_timewait_sock_slab;
 	}
 	list_add(&prot->node, &proto_list);
 	mutex_unlock(&proto_list_mutex);
 	return ret;
 
-out_free_timewait_sock_slab_name:
+out_free_timewait_sock_slab:
 	if (alloc_slab && prot->twsk_prot)
-		kfree(prot->twsk_prot->twsk_slab_name);
+		tw_prot_cleanup(prot->twsk_prot);
 out_free_request_sock_slab:
 	if (alloc_slab) {
 		req_prot_cleanup(prot->rsk_prot);
@@ -3464,12 +3474,7 @@ void proto_unregister(struct proto *prot)
 	prot->slab = NULL;
 
 	req_prot_cleanup(prot->rsk_prot);
-
-	if (prot->twsk_prot != NULL && prot->twsk_prot->twsk_slab != NULL) {
-		kmem_cache_destroy(prot->twsk_prot->twsk_slab);
-		kfree(prot->twsk_prot->twsk_slab_name);
-		prot->twsk_prot->twsk_slab = NULL;
-	}
+	tw_prot_cleanup(prot->twsk_prot);
 }
 EXPORT_SYMBOL(proto_unregister);
 
-- 
2.26.2


From 276d7308fbb3e3d9ca58157b7973d843fdcd1e42 Mon Sep 17 00:00:00 2001
From: Qingyu Li <ieatmuttonchuan@gmail.com>
Date: Mon, 10 Aug 2020 09:51:00 +0800
Subject: [PATCH 04/13] net/nfc/rawsock.c: add CAP_NET_RAW check.

[ Upstream commit 26896f01467a28651f7a536143fe5ac8449d4041 ]

When creating a raw AF_NFC socket, CAP_NET_RAW needs to be checked first.

Signed-off-by: Qingyu Li <ieatmuttonchuan@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/nfc/rawsock.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c
index ba5ffd3badd3..b5c867fe3232 100644
--- a/net/nfc/rawsock.c
+++ b/net/nfc/rawsock.c
@@ -332,10 +332,13 @@ static int rawsock_create(struct net *net, struct socket *sock,
 	if ((sock->type != SOCK_SEQPACKET) && (sock->type != SOCK_RAW))
 		return -ESOCKTNOSUPPORT;
 
-	if (sock->type == SOCK_RAW)
+	if (sock->type == SOCK_RAW) {
+		if (!capable(CAP_NET_RAW))
+			return -EPERM;
 		sock->ops = &rawsock_raw_ops;
-	else
+	} else {
 		sock->ops = &rawsock_ops;
+	}
 
 	sk = sk_alloc(net, PF_NFC, GFP_ATOMIC, nfc_proto->proto, kern);
 	if (!sk)
-- 
2.26.2


From ce86d30f75ae6c1d2b0d7c5ed490f88846f8a717 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Thu, 6 Aug 2020 17:37:53 +0200
Subject: [PATCH 05/13] net: phy: fix memory leak in device-create error path

[ Upstream commit d02cbc46136105cf86f84ac355e16f04696f538d ]

A recent commit introduced a late error path in phy_device_create()
which fails to release the device name allocated by dev_set_name().

Fixes: 13d0ab6750b2 ("net: phy: check return code when requesting PHY driver module")
Cc: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 0881b4b92363..d9bdc19b01cc 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -616,7 +616,9 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id,
 	if (c45_ids)
 		dev->c45_ids = *c45_ids;
 	dev->irq = bus->irq[addr];
+
 	dev_set_name(&mdiodev->dev, PHY_ID_FMT, bus->id, addr);
+	device_initialize(&mdiodev->dev);
 
 	dev->state = PHY_DOWN;
 
@@ -650,10 +652,8 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id,
 		ret = phy_request_driver_module(dev, phy_id);
 	}
 
-	if (!ret) {
-		device_initialize(&mdiodev->dev);
-	} else {
-		kfree(dev);
+	if (ret) {
+		put_device(&mdiodev->dev);
 		dev = ERR_PTR(ret);
 	}
 
-- 
2.26.2


From e5504e7b2e18b6213b3266f6f32b0c040684f77c Mon Sep 17 00:00:00 2001
From: Miaohe Lin <linmiaohe@huawei.com>
Date: Thu, 6 Aug 2020 19:53:16 +0800
Subject: [PATCH 06/13] net: Set fput_needed iff FDPUT_FPUT is set

[ Upstream commit ce787a5a074a86f76f5d3fd804fa78e01bfb9e89 ]

We should fput() file iff FDPUT_FPUT is set. So we should set fput_needed
accordingly.

Fixes: 00e188ef6a7e ("sockfd_lookup_light(): switch to fdget^W^Waway from fget_light")
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/socket.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/socket.c b/net/socket.c
index 2dd739fba866..90e212410d37 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -500,7 +500,7 @@ static struct socket *sockfd_lookup_light(int fd, int *err, int *fput_needed)
 	if (f.file) {
 		sock = sock_from_file(f.file, err);
 		if (likely(sock)) {
-			*fput_needed = f.flags;
+			*fput_needed = f.flags & FDPUT_FPUT;
 			return sock;
 		}
 		fdput(f);
-- 
2.26.2


From e10557ade6ca94c5061fe68fdfadb812cbda9c06 Mon Sep 17 00:00:00 2001
From: Ira Weiny <ira.weiny@intel.com>
Date: Mon, 10 Aug 2020 17:02:58 -0700
Subject: [PATCH 07/13] net/tls: Fix kmap usage

[ Upstream commit b06c19d9f827f6743122795570bfc0c72db482b0 ]

When MSG_OOB is specified to tls_device_sendpage() the mapped page is
never unmapped.

Hold off mapping the page until after the flags are checked and the page
is actually needed.

Fixes: e8f69799810c ("net/tls: Add generic NIC offload infrastructure")
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_device.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index a562ebaaa33c..0ad8b53a8ca4 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -561,7 +561,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page,
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct iov_iter	msg_iter;
-	char *kaddr = kmap(page);
+	char *kaddr;
 	struct kvec iov;
 	int rc;
 
@@ -576,6 +576,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page,
 		goto out;
 	}
 
+	kaddr = kmap(page);
 	iov.iov_base = kaddr + offset;
 	iov.iov_len = size;
 	iov_iter_kvec(&msg_iter, WRITE, &iov, 1, size);
-- 
2.26.2


From 962ca05bea29c708707edff5c4ccf0171c3f592f Mon Sep 17 00:00:00 2001
From: Jason Baron <jbaron@akamai.com>
Date: Mon, 10 Aug 2020 13:38:39 -0400
Subject: [PATCH 08/13] tcp: correct read of TFO keys on big endian systems

[ Upstream commit f19008e676366c44e9241af57f331b6c6edf9552 ]

When TFO keys are read back on big endian systems either via the global
sysctl interface or via getsockopt() using TCP_FASTOPEN_KEY, the values
don't match what was written.

For example, on s390x:

# echo "1-2-3-4" > /proc/sys/net/ipv4/tcp_fastopen_key
# cat /proc/sys/net/ipv4/tcp_fastopen_key
02000000-01000000-04000000-03000000

Instead of:

# cat /proc/sys/net/ipv4/tcp_fastopen_key
00000001-00000002-00000003-00000004

Fix this by converting to the correct endianness on read. This was
reported by Colin Ian King when running the 'tcp_fastopen_backup_key' net
selftest on s390x, which depends on the read value matching what was
written. I've confirmed that the test now passes on big and little endian
systems.

Signed-off-by: Jason Baron <jbaron@akamai.com>
Fixes: 438ac88009bc ("net: fastopen: robustness and endianness fixes for SipHash")
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Eric Dumazet <edumazet@google.com>
Reported-and-tested-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h          |  2 ++
 net/ipv4/sysctl_net_ipv4.c | 16 ++++------------
 net/ipv4/tcp.c             | 16 ++++------------
 net/ipv4/tcp_fastopen.c    | 23 +++++++++++++++++++++++
 4 files changed, 33 insertions(+), 24 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 6f8e60c6fbc7..ecb66d01135e 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1669,6 +1669,8 @@ void tcp_fastopen_destroy_cipher(struct sock *sk);
 void tcp_fastopen_ctx_destroy(struct net *net);
 int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk,
 			      void *primary_key, void *backup_key);
+int tcp_fastopen_get_cipher(struct net *net, struct inet_connection_sock *icsk,
+			    u64 *key);
 void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb);
 struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
 			      struct request_sock *req,
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 81b267e990a1..e07c1b429b09 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -307,24 +307,16 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write,
 	struct ctl_table tbl = { .maxlen = ((TCP_FASTOPEN_KEY_LENGTH *
 					    2 * TCP_FASTOPEN_KEY_MAX) +
 					    (TCP_FASTOPEN_KEY_MAX * 5)) };
-	struct tcp_fastopen_context *ctx;
-	u32 user_key[TCP_FASTOPEN_KEY_MAX * 4];
-	__le32 key[TCP_FASTOPEN_KEY_MAX * 4];
+	u32 user_key[TCP_FASTOPEN_KEY_BUF_LENGTH / sizeof(u32)];
+	__le32 key[TCP_FASTOPEN_KEY_BUF_LENGTH / sizeof(__le32)];
 	char *backup_data;
-	int ret, i = 0, off = 0, n_keys = 0;
+	int ret, i = 0, off = 0, n_keys;
 
 	tbl.data = kmalloc(tbl.maxlen, GFP_KERNEL);
 	if (!tbl.data)
 		return -ENOMEM;
 
-	rcu_read_lock();
-	ctx = rcu_dereference(net->ipv4.tcp_fastopen_ctx);
-	if (ctx) {
-		n_keys = tcp_fastopen_context_len(ctx);
-		memcpy(&key[0], &ctx->key[0], TCP_FASTOPEN_KEY_LENGTH * n_keys);
-	}
-	rcu_read_unlock();
-
+	n_keys = tcp_fastopen_get_cipher(net, NULL, (u64 *)key);
 	if (!n_keys) {
 		memset(&key[0], 0, TCP_FASTOPEN_KEY_LENGTH);
 		n_keys = 1;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index eee18259a24e..4f11e68a4efa 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3538,22 +3538,14 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 		return 0;
 
 	case TCP_FASTOPEN_KEY: {
-		__u8 key[TCP_FASTOPEN_KEY_BUF_LENGTH];
-		struct tcp_fastopen_context *ctx;
-		unsigned int key_len = 0;
+		u64 key[TCP_FASTOPEN_KEY_BUF_LENGTH / sizeof(u64)];
+		unsigned int key_len;
 
 		if (get_user(len, optlen))
 			return -EFAULT;
 
-		rcu_read_lock();
-		ctx = rcu_dereference(icsk->icsk_accept_queue.fastopenq.ctx);
-		if (ctx) {
-			key_len = tcp_fastopen_context_len(ctx) *
-					TCP_FASTOPEN_KEY_LENGTH;
-			memcpy(&key[0], &ctx->key[0], key_len);
-		}
-		rcu_read_unlock();
-
+		key_len = tcp_fastopen_get_cipher(net, icsk, key) *
+				TCP_FASTOPEN_KEY_LENGTH;
 		len = min_t(unsigned int, len, key_len);
 		if (put_user(len, optlen))
 			return -EFAULT;
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 19ad9586c720..1bb85821f1e6 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -108,6 +108,29 @@ int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk,
 	return err;
 }
 
+int tcp_fastopen_get_cipher(struct net *net, struct inet_connection_sock *icsk,
+			    u64 *key)
+{
+	struct tcp_fastopen_context *ctx;
+	int n_keys = 0, i;
+
+	rcu_read_lock();
+	if (icsk)
+		ctx = rcu_dereference(icsk->icsk_accept_queue.fastopenq.ctx);
+	else
+		ctx = rcu_dereference(net->ipv4.tcp_fastopen_ctx);
+	if (ctx) {
+		n_keys = tcp_fastopen_context_len(ctx);
+		for (i = 0; i < n_keys; i++) {
+			put_unaligned_le64(ctx->key[i].key[0], key + (i * 2));
+			put_unaligned_le64(ctx->key[i].key[1], key + (i * 2) + 1);
+		}
+	}
+	rcu_read_unlock();
+
+	return n_keys;
+}
+
 static bool __tcp_fastopen_cookie_gen_cipher(struct request_sock *req,
 					     struct sk_buff *syn,
 					     const siphash_key_t *key,
-- 
2.26.2


From f284648b1a21957da38efd4e0aafbca945be6152 Mon Sep 17 00:00:00 2001
From: Ronak Doshi <doshir@vmware.com>
Date: Mon, 10 Aug 2020 09:55:55 -0700
Subject: [PATCH 09/13] vmxnet3: use correct tcp hdr length when packet is
 encapsulated

[ Upstream commit 8a7f280f29a80f6e0798f5d6e07c5dd8726620fe ]

Commit dacce2be3312 ("vmxnet3: add geneve and vxlan tunnel offload
support") added support for encapsulation offload. However, while
calculating tcp hdr length, it does not take into account if the
packet is encapsulated or not.

This patch fixes this issue by using correct reference for inner
tcp header.

Fixes: dacce2be3312 ("vmxnet3: add geneve and vxlan tunnel offload support")
Signed-off-by: Ronak Doshi <doshir@vmware.com>
Acked-by: Guolin Yang <gyang@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vmxnet3/vmxnet3_drv.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 722cb054a5cd..d42207dc25dd 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -861,7 +861,8 @@ vmxnet3_parse_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
 
 			switch (protocol) {
 			case IPPROTO_TCP:
-				ctx->l4_hdr_size = tcp_hdrlen(skb);
+				ctx->l4_hdr_size = skb->encapsulation ? inner_tcp_hdrlen(skb) :
+						   tcp_hdrlen(skb);
 				break;
 			case IPPROTO_UDP:
 				ctx->l4_hdr_size = sizeof(struct udphdr);
-- 
2.26.2


From 9848ebd258b26929472b7d669649e61e00cfb7b0 Mon Sep 17 00:00:00 2001
From: Tim Froidcoeur <tim.froidcoeur@tessares.net>
Date: Tue, 11 Aug 2020 20:33:23 +0200
Subject: [PATCH 10/13] net: refactor bind_bucket fastreuse into helper

[ Upstream commit 62ffc589abb176821662efc4525ee4ac0b9c3894 ]

Refactor the fastreuse update code in inet_csk_get_port into a small
helper function that can be called from other places.

Acked-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Tim Froidcoeur <tim.froidcoeur@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_connection_sock.h |  4 ++
 net/ipv4/inet_connection_sock.c    | 97 ++++++++++++++++--------------
 2 files changed, 57 insertions(+), 44 deletions(-)

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index a3f076befa4f..cceec467ed9e 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -309,6 +309,10 @@ int inet_csk_compat_getsockopt(struct sock *sk, int level, int optname,
 int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname,
 			       char __user *optval, unsigned int optlen);
 
+/* update the fast reuse flag when adding a socket */
+void inet_csk_update_fastreuse(struct inet_bind_bucket *tb,
+			       struct sock *sk);
+
 struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu);
 
 #define TCP_PINGPONG_THRESH	3
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 65c29f2bd89f..98aa90a28691 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -296,6 +296,57 @@ static inline int sk_reuseport_match(struct inet_bind_bucket *tb,
 				    ipv6_only_sock(sk), true, false);
 }
 
+void inet_csk_update_fastreuse(struct inet_bind_bucket *tb,
+			       struct sock *sk)
+{
+	kuid_t uid = sock_i_uid(sk);
+	bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN;
+
+	if (hlist_empty(&tb->owners)) {
+		tb->fastreuse = reuse;
+		if (sk->sk_reuseport) {
+			tb->fastreuseport = FASTREUSEPORT_ANY;
+			tb->fastuid = uid;
+			tb->fast_rcv_saddr = sk->sk_rcv_saddr;
+			tb->fast_ipv6_only = ipv6_only_sock(sk);
+			tb->fast_sk_family = sk->sk_family;
+#if IS_ENABLED(CONFIG_IPV6)
+			tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
+#endif
+		} else {
+			tb->fastreuseport = 0;
+		}
+	} else {
+		if (!reuse)
+			tb->fastreuse = 0;
+		if (sk->sk_reuseport) {
+			/* We didn't match or we don't have fastreuseport set on
+			 * the tb, but we have sk_reuseport set on this socket
+			 * and we know that there are no bind conflicts with
+			 * this socket in this tb, so reset our tb's reuseport
+			 * settings so that any subsequent sockets that match
+			 * our current socket will be put on the fast path.
+			 *
+			 * If we reset we need to set FASTREUSEPORT_STRICT so we
+			 * do extra checking for all subsequent sk_reuseport
+			 * socks.
+			 */
+			if (!sk_reuseport_match(tb, sk)) {
+				tb->fastreuseport = FASTREUSEPORT_STRICT;
+				tb->fastuid = uid;
+				tb->fast_rcv_saddr = sk->sk_rcv_saddr;
+				tb->fast_ipv6_only = ipv6_only_sock(sk);
+				tb->fast_sk_family = sk->sk_family;
+#if IS_ENABLED(CONFIG_IPV6)
+				tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
+#endif
+			}
+		} else {
+			tb->fastreuseport = 0;
+		}
+	}
+}
+
 /* Obtain a reference to a local port for the given sock,
  * if snum is zero it means select any available local port.
  * We try to allocate an odd port (and leave even ports for connect())
@@ -308,7 +359,6 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
 	struct inet_bind_hashbucket *head;
 	struct net *net = sock_net(sk);
 	struct inet_bind_bucket *tb = NULL;
-	kuid_t uid = sock_i_uid(sk);
 	int l3mdev;
 
 	l3mdev = inet_sk_bound_l3mdev(sk);
@@ -345,49 +395,8 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
 			goto fail_unlock;
 	}
 success:
-	if (hlist_empty(&tb->owners)) {
-		tb->fastreuse = reuse;
-		if (sk->sk_reuseport) {
-			tb->fastreuseport = FASTREUSEPORT_ANY;
-			tb->fastuid = uid;
-			tb->fast_rcv_saddr = sk->sk_rcv_saddr;
-			tb->fast_ipv6_only = ipv6_only_sock(sk);
-			tb->fast_sk_family = sk->sk_family;
-#if IS_ENABLED(CONFIG_IPV6)
-			tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
-#endif
-		} else {
-			tb->fastreuseport = 0;
-		}
-	} else {
-		if (!reuse)
-			tb->fastreuse = 0;
-		if (sk->sk_reuseport) {
-			/* We didn't match or we don't have fastreuseport set on
-			 * the tb, but we have sk_reuseport set on this socket
-			 * and we know that there are no bind conflicts with
-			 * this socket in this tb, so reset our tb's reuseport
-			 * settings so that any subsequent sockets that match
-			 * our current socket will be put on the fast path.
-			 *
-			 * If we reset we need to set FASTREUSEPORT_STRICT so we
-			 * do extra checking for all subsequent sk_reuseport
-			 * socks.
-			 */
-			if (!sk_reuseport_match(tb, sk)) {
-				tb->fastreuseport = FASTREUSEPORT_STRICT;
-				tb->fastuid = uid;
-				tb->fast_rcv_saddr = sk->sk_rcv_saddr;
-				tb->fast_ipv6_only = ipv6_only_sock(sk);
-				tb->fast_sk_family = sk->sk_family;
-#if IS_ENABLED(CONFIG_IPV6)
-				tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
-#endif
-			}
-		} else {
-			tb->fastreuseport = 0;
-		}
-	}
+	inet_csk_update_fastreuse(tb, sk);
+
 	if (!inet_csk(sk)->icsk_bind_hash)
 		inet_bind_hash(sk, tb, port);
 	WARN_ON(inet_csk(sk)->icsk_bind_hash != tb);
-- 
2.26.2


From a4ff964474ca26c27fe582b109d65ebf81742a56 Mon Sep 17 00:00:00 2001
From: Tim Froidcoeur <tim.froidcoeur@tessares.net>
Date: Tue, 11 Aug 2020 20:33:24 +0200
Subject: [PATCH 11/13] net: initialize fastreuse on inet_inherit_port

[ Upstream commit d76f3351cea2d927fdf70dd7c06898235035e84e ]

In the case of TPROXY, bind_conflict optimizations for SO_REUSEADDR or
SO_REUSEPORT are broken, possibly resulting in O(n) instead of O(1) bind
behaviour or in the incorrect reuse of a bind.

the kernel keeps track for each bind_bucket if all sockets in the
bind_bucket support SO_REUSEADDR or SO_REUSEPORT in two fastreuse flags.
These flags allow skipping the costly bind_conflict check when possible
(meaning when all sockets have the proper SO_REUSE option).

For every socket added to a bind_bucket, these flags need to be updated.
As soon as a socket that does not support reuse is added, the flag is
set to false and will never go back to true, unless the bind_bucket is
deleted.

Note that there is no mechanism to re-evaluate these flags when a socket
is removed (this might make sense when removing a socket that would not
allow reuse; this leaves room for a future patch).

For this optimization to work, it is mandatory that these flags are
properly initialized and updated.

When a child socket is created from a listen socket in
__inet_inherit_port, the TPROXY case could create a new bind bucket
without properly initializing these flags, thus preventing the
optimization to work. Alternatively, a socket not allowing reuse could
be added to an existing bind bucket without updating the flags, causing
bind_conflict to never be called as it should.

Call inet_csk_update_fastreuse when __inet_inherit_port decides to create
a new bind_bucket or use a different bind_bucket than the one of the
listen socket.

Fixes: 093d282321da ("tproxy: fix hash locking issue when using port redirection in __inet_inherit_port()")
Acked-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Tim Froidcoeur <tim.froidcoeur@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/inet_hashtables.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 2bbaaf0c7176..006a34b18537 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -163,6 +163,7 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child)
 				return -ENOMEM;
 			}
 		}
+		inet_csk_update_fastreuse(tb, child);
 	}
 	inet_bind_hash(child, tb, port);
 	spin_unlock(&head->lock);
-- 
2.26.2


From 2ad6ee9752bcbfb79c98f36de54c310505af09bd Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Wed, 12 Aug 2020 14:56:02 +0200
Subject: [PATCH 12/13] vsock: fix potential null pointer dereference in
 vsock_poll()

[ Upstream commit 1980c05844830a44708c98c96d600833aa3fae08 ]

syzbot reported this issue where in the vsock_poll() we find the
socket state at TCP_ESTABLISHED, but 'transport' is null:
  general protection fault, probably for non-canonical address 0xdffffc0000000012: 0000 [#1] PREEMPT SMP KASAN
  KASAN: null-ptr-deref in range [0x0000000000000090-0x0000000000000097]
  CPU: 0 PID: 8227 Comm: syz-executor.2 Not tainted 5.8.0-rc7-syzkaller #0
  Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
  RIP: 0010:vsock_poll+0x75a/0x8e0 net/vmw_vsock/af_vsock.c:1038
  Call Trace:
   sock_poll+0x159/0x460 net/socket.c:1266
   vfs_poll include/linux/poll.h:90 [inline]
   do_pollfd fs/select.c:869 [inline]
   do_poll fs/select.c:917 [inline]
   do_sys_poll+0x607/0xd40 fs/select.c:1011
   __do_sys_poll fs/select.c:1069 [inline]
   __se_sys_poll fs/select.c:1057 [inline]
   __x64_sys_poll+0x18c/0x440 fs/select.c:1057
   do_syscall_64+0x60/0xe0 arch/x86/entry/common.c:384
   entry_SYSCALL_64_after_hwframe+0x44/0xa9

This issue can happen if the TCP_ESTABLISHED state is set after we read
the vsk->transport in the vsock_poll().

We could put barriers to synchronize, but this can only happen during
connection setup, so we can simply check that 'transport' is valid.

Fixes: c0cfa2d8a788 ("vsock: add multi-transports support")
Reported-and-tested-by: syzbot+a61bac2fcc1a7c6623fe@syzkaller.appspotmail.com
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Reviewed-by: Jorgen Hansen <jhansen@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/vmw_vsock/af_vsock.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 626bf9044418..6cd0df1c5caf 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1032,7 +1032,7 @@ static __poll_t vsock_poll(struct file *file, struct socket *sock,
 		}
 
 		/* Connected sockets that can produce data can be written. */
-		if (sk->sk_state == TCP_ESTABLISHED) {
+		if (transport && sk->sk_state == TCP_ESTABLISHED) {
 			if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
 				bool space_avail_now = false;
 				int ret = transport->notify_poll_out(
-- 
2.26.2


From c06c28003cabfc6a9987c9b7dd714d5dc35de9b7 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Marek=20Beh=C3=BAn?= <marek.behun@nic.cz>
Date: Mon, 10 Aug 2020 17:01:58 +0200
Subject: [PATCH 13/13] net: phy: marvell10g: fix null pointer dereference
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 1b8ef1423dbfd34de2439a2db457b84480b7c8a8 ]

Commit c3e302edca24 ("net: phy: marvell10g: fix temperature sensor on 2110")
added a check for PHY ID via phydev->drv->phy_id in a function which is
called by devres at a time when phydev->drv is already set to null by
phy_remove function.

This null pointer dereference can be triggered via SFP subsystem with a
SFP module containing this Marvell PHY. When the SFP interface is put
down, the SFP subsystem removes the PHY.

Fixes: c3e302edca24 ("net: phy: marvell10g: fix temperature sensor on 2110")
Signed-off-by: Marek Behún <marek.behun@nic.cz>
Cc: Maxime Chevallier <maxime.chevallier@bootlin.com>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: Baruch Siach <baruch@tkos.co.il>
Cc: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/marvell10g.c | 18 +++++++-----------
 1 file changed, 7 insertions(+), 11 deletions(-)

diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c
index 1f1a01c98e44..06dfabe297af 100644
--- a/drivers/net/phy/marvell10g.c
+++ b/drivers/net/phy/marvell10g.c
@@ -205,13 +205,6 @@ static int mv3310_hwmon_config(struct phy_device *phydev, bool enable)
 			      MV_V2_TEMP_CTRL_MASK, val);
 }
 
-static void mv3310_hwmon_disable(void *data)
-{
-	struct phy_device *phydev = data;
-
-	mv3310_hwmon_config(phydev, false);
-}
-
 static int mv3310_hwmon_probe(struct phy_device *phydev)
 {
 	struct device *dev = &phydev->mdio.dev;
@@ -235,10 +228,6 @@ static int mv3310_hwmon_probe(struct phy_device *phydev)
 	if (ret)
 		return ret;
 
-	ret = devm_add_action_or_reset(dev, mv3310_hwmon_disable, phydev);
-	if (ret)
-		return ret;
-
 	priv->hwmon_dev = devm_hwmon_device_register_with_info(dev,
 				priv->hwmon_name, phydev,
 				&mv3310_hwmon_chip_info, NULL);
@@ -423,6 +412,11 @@ static int mv3310_probe(struct phy_device *phydev)
 	return phy_sfp_probe(phydev, &mv3310_sfp_ops);
 }
 
+static void mv3310_remove(struct phy_device *phydev)
+{
+	mv3310_hwmon_config(phydev, false);
+}
+
 static int mv3310_suspend(struct phy_device *phydev)
 {
 	return mv3310_power_down(phydev);
@@ -763,6 +757,7 @@ static struct phy_driver mv3310_drivers[] = {
 		.read_status	= mv3310_read_status,
 		.get_tunable	= mv3310_get_tunable,
 		.set_tunable	= mv3310_set_tunable,
+		.remove		= mv3310_remove,
 	},
 	{
 		.phy_id		= MARVELL_PHY_ID_88E2110,
@@ -778,6 +773,7 @@ static struct phy_driver mv3310_drivers[] = {
 		.read_status	= mv3310_read_status,
 		.get_tunable	= mv3310_get_tunable,
 		.set_tunable	= mv3310_set_tunable,
+		.remove		= mv3310_remove,
 	},
 };
 
-- 
2.26.2


[-- Attachment #3: net_58.mbox --]
[-- Type: Application/Octet-Stream, Size: 38262 bytes --]

From b951c67e34dbaaf498afe2301831c21b233f79e4 Mon Sep 17 00:00:00 2001
From: John Ogness <john.ogness@linutronix.de>
Date: Thu, 13 Aug 2020 21:45:25 +0206
Subject: [PATCH 01/15] af_packet: TPACKET_V3: fix fill status rwlock imbalance

[ Upstream commit 88fd1cb80daa20af063bce81e1fad14e945a8dc4 ]

After @blk_fill_in_prog_lock is acquired there is an early out vnet
situation that can occur. In that case, the rwlock needs to be
released.

Also, since @blk_fill_in_prog_lock is only acquired when @tp_version
is exactly TPACKET_V3, only release it on that exact condition as
well.

And finally, add sparse annotation so that it is clearer that
prb_fill_curr_block() and prb_clear_blk_fill_status() are acquiring
and releasing @blk_fill_in_prog_lock, respectively. sparse is still
unable to understand the balance, but the warnings are now on a
higher level that make more sense.

Fixes: 632ca50f2cbd ("af_packet: TPACKET_V3: replace busy-wait loop")
Signed-off-by: John Ogness <john.ogness@linutronix.de>
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 29bd405adbbd..301f41d4929b 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -942,6 +942,7 @@ static int prb_queue_frozen(struct tpacket_kbdq_core *pkc)
 }
 
 static void prb_clear_blk_fill_status(struct packet_ring_buffer *rb)
+	__releases(&pkc->blk_fill_in_prog_lock)
 {
 	struct tpacket_kbdq_core *pkc  = GET_PBDQC_FROM_RB(rb);
 	atomic_dec(&pkc->blk_fill_in_prog);
@@ -989,6 +990,7 @@ static void prb_fill_curr_block(char *curr,
 				struct tpacket_kbdq_core *pkc,
 				struct tpacket_block_desc *pbd,
 				unsigned int len)
+	__acquires(&pkc->blk_fill_in_prog_lock)
 {
 	struct tpacket3_hdr *ppd;
 
@@ -2286,8 +2288,11 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	if (do_vnet &&
 	    virtio_net_hdr_from_skb(skb, h.raw + macoff -
 				    sizeof(struct virtio_net_hdr),
-				    vio_le(), true, 0))
+				    vio_le(), true, 0)) {
+		if (po->tp_version == TPACKET_V3)
+			prb_clear_blk_fill_status(&po->rx_ring);
 		goto drop_n_account;
+	}
 
 	if (po->tp_version <= TPACKET_V2) {
 		packet_increment_rx_head(po, &po->rx_ring);
@@ -2393,7 +2398,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 		__clear_bit(slot_id, po->rx_ring.rx_owner_map);
 		spin_unlock(&sk->sk_receive_queue.lock);
 		sk->sk_data_ready(sk);
-	} else {
+	} else if (po->tp_version == TPACKET_V3) {
 		prb_clear_blk_fill_status(&po->rx_ring);
 	}
 
-- 
2.26.2


From b5b77ea59dda027a8426ef889f3212928aa16d07 Mon Sep 17 00:00:00 2001
From: Xie He <xie.he.0141@gmail.com>
Date: Wed, 5 Aug 2020 18:50:40 -0700
Subject: [PATCH 02/15] drivers/net/wan/lapbether: Added needed_headroom and a
 skb->len check

[ Upstream commit c7ca03c216acb14466a713fedf1b9f2c24994ef2 ]

1. Added a skb->len check

This driver expects upper layers to include a pseudo header of 1 byte
when passing down a skb for transmission. This driver will read this
1-byte header. This patch added a skb->len check before reading the
header to make sure the header exists.

2. Changed to use needed_headroom instead of hard_header_len to request
necessary headroom to be allocated

In net/packet/af_packet.c, the function packet_snd first reserves a
headroom of length (dev->hard_header_len + dev->needed_headroom).
Then if the socket is a SOCK_DGRAM socket, it calls dev_hard_header,
which calls dev->header_ops->create, to create the link layer header.
If the socket is a SOCK_RAW socket, it "un-reserves" a headroom of
length (dev->hard_header_len), and assumes the user to provide the
appropriate link layer header.

So according to the logic of af_packet.c, dev->hard_header_len should
be the length of the header that would be created by
dev->header_ops->create.

However, this driver doesn't provide dev->header_ops, so logically
dev->hard_header_len should be 0.

So we should use dev->needed_headroom instead of dev->hard_header_len
to request necessary headroom to be allocated.

This change fixes kernel panic when this driver is used with AF_PACKET
SOCK_RAW sockets.

Call stack when panic:

[  168.399197] skbuff: skb_under_panic: text:ffffffff819d95fb len:20
put:14 head:ffff8882704c0a00 data:ffff8882704c09fd tail:0x11 end:0xc0
dev:veth0
...
[  168.399255] Call Trace:
[  168.399259]  skb_push.cold+0x14/0x24
[  168.399262]  eth_header+0x2b/0xc0
[  168.399267]  lapbeth_data_transmit+0x9a/0xb0 [lapbether]
[  168.399275]  lapb_data_transmit+0x22/0x2c [lapb]
[  168.399277]  lapb_transmit_buffer+0x71/0xb0 [lapb]
[  168.399279]  lapb_kick+0xe3/0x1c0 [lapb]
[  168.399281]  lapb_data_request+0x76/0xc0 [lapb]
[  168.399283]  lapbeth_xmit+0x56/0x90 [lapbether]
[  168.399286]  dev_hard_start_xmit+0x91/0x1f0
[  168.399289]  ? irq_init_percpu_irqstack+0xc0/0x100
[  168.399291]  __dev_queue_xmit+0x721/0x8e0
[  168.399295]  ? packet_parse_headers.isra.0+0xd2/0x110
[  168.399297]  dev_queue_xmit+0x10/0x20
[  168.399298]  packet_sendmsg+0xbf0/0x19b0
......

Cc: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
Cc: Martin Schiller <ms@dev.tdt.de>
Cc: Brian Norris <briannorris@chromium.org>
Signed-off-by: Xie He <xie.he.0141@gmail.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wan/lapbether.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c
index b2868433718f..1ea15f2123ed 100644
--- a/drivers/net/wan/lapbether.c
+++ b/drivers/net/wan/lapbether.c
@@ -157,6 +157,12 @@ static netdev_tx_t lapbeth_xmit(struct sk_buff *skb,
 	if (!netif_running(dev))
 		goto drop;
 
+	/* There should be a pseudo header of 1 byte added by upper layers.
+	 * Check to make sure it is there before reading it.
+	 */
+	if (skb->len < 1)
+		goto drop;
+
 	switch (skb->data[0]) {
 	case X25_IFACE_DATA:
 		break;
@@ -305,6 +311,7 @@ static void lapbeth_setup(struct net_device *dev)
 	dev->netdev_ops	     = &lapbeth_netdev_ops;
 	dev->needs_free_netdev = true;
 	dev->type            = ARPHRD_X25;
+	dev->hard_header_len = 0;
 	dev->mtu             = 1000;
 	dev->addr_len        = 0;
 }
@@ -331,7 +338,8 @@ static int lapbeth_new_device(struct net_device *dev)
 	 * then this driver prepends a length field of 2 bytes,
 	 * then the underlying Ethernet device prepends its own header.
 	 */
-	ndev->hard_header_len = -1 + 3 + 2 + dev->hard_header_len;
+	ndev->needed_headroom = -1 + 3 + 2 + dev->hard_header_len
+					   + dev->needed_headroom;
 
 	lapbeth = netdev_priv(ndev);
 	lapbeth->axdev = ndev;
-- 
2.26.2


From bc8cb250a731665a806da93815a54c4e293f46a7 Mon Sep 17 00:00:00 2001
From: Miaohe Lin <linmiaohe@huawei.com>
Date: Mon, 10 Aug 2020 08:16:58 -0400
Subject: [PATCH 03/15] net: Fix potential memory leak in proto_register()

[ Upstream commit 0f5907af39137f8183ed536aaa00f322d7365130 ]

If we failed to assign proto idx, we free the twsk_slab_name but forget to
free the twsk_slab. Add a helper function tw_prot_cleanup() to free these
together and also use this helper function in proto_unregister().

Fixes: b45ce32135d1 ("sock: fix potential memory leak in proto_register()")
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 25 +++++++++++++++----------
 1 file changed, 15 insertions(+), 10 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index 2e5b7870e5d3..a14a8cb6ccca 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -3443,6 +3443,16 @@ static void sock_inuse_add(struct net *net, int val)
 }
 #endif
 
+static void tw_prot_cleanup(struct timewait_sock_ops *twsk_prot)
+{
+	if (!twsk_prot)
+		return;
+	kfree(twsk_prot->twsk_slab_name);
+	twsk_prot->twsk_slab_name = NULL;
+	kmem_cache_destroy(twsk_prot->twsk_slab);
+	twsk_prot->twsk_slab = NULL;
+}
+
 static void req_prot_cleanup(struct request_sock_ops *rsk_prot)
 {
 	if (!rsk_prot)
@@ -3513,7 +3523,7 @@ int proto_register(struct proto *prot, int alloc_slab)
 						  prot->slab_flags,
 						  NULL);
 			if (prot->twsk_prot->twsk_slab == NULL)
-				goto out_free_timewait_sock_slab_name;
+				goto out_free_timewait_sock_slab;
 		}
 	}
 
@@ -3521,15 +3531,15 @@ int proto_register(struct proto *prot, int alloc_slab)
 	ret = assign_proto_idx(prot);
 	if (ret) {
 		mutex_unlock(&proto_list_mutex);
-		goto out_free_timewait_sock_slab_name;
+		goto out_free_timewait_sock_slab;
 	}
 	list_add(&prot->node, &proto_list);
 	mutex_unlock(&proto_list_mutex);
 	return ret;
 
-out_free_timewait_sock_slab_name:
+out_free_timewait_sock_slab:
 	if (alloc_slab && prot->twsk_prot)
-		kfree(prot->twsk_prot->twsk_slab_name);
+		tw_prot_cleanup(prot->twsk_prot);
 out_free_request_sock_slab:
 	if (alloc_slab) {
 		req_prot_cleanup(prot->rsk_prot);
@@ -3553,12 +3563,7 @@ void proto_unregister(struct proto *prot)
 	prot->slab = NULL;
 
 	req_prot_cleanup(prot->rsk_prot);
-
-	if (prot->twsk_prot != NULL && prot->twsk_prot->twsk_slab != NULL) {
-		kmem_cache_destroy(prot->twsk_prot->twsk_slab);
-		kfree(prot->twsk_prot->twsk_slab_name);
-		prot->twsk_prot->twsk_slab = NULL;
-	}
+	tw_prot_cleanup(prot->twsk_prot);
 }
 EXPORT_SYMBOL(proto_unregister);
 
-- 
2.26.2


From 1ade44e614b01c0c81ca6e7818ea47f636e4500e Mon Sep 17 00:00:00 2001
From: Qingyu Li <ieatmuttonchuan@gmail.com>
Date: Mon, 10 Aug 2020 09:51:00 +0800
Subject: [PATCH 04/15] net/nfc/rawsock.c: add CAP_NET_RAW check.

[ Upstream commit 26896f01467a28651f7a536143fe5ac8449d4041 ]

When creating a raw AF_NFC socket, CAP_NET_RAW needs to be checked first.

Signed-off-by: Qingyu Li <ieatmuttonchuan@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/nfc/rawsock.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c
index ba5ffd3badd3..b5c867fe3232 100644
--- a/net/nfc/rawsock.c
+++ b/net/nfc/rawsock.c
@@ -332,10 +332,13 @@ static int rawsock_create(struct net *net, struct socket *sock,
 	if ((sock->type != SOCK_SEQPACKET) && (sock->type != SOCK_RAW))
 		return -ESOCKTNOSUPPORT;
 
-	if (sock->type == SOCK_RAW)
+	if (sock->type == SOCK_RAW) {
+		if (!capable(CAP_NET_RAW))
+			return -EPERM;
 		sock->ops = &rawsock_raw_ops;
-	else
+	} else {
 		sock->ops = &rawsock_ops;
+	}
 
 	sk = sk_alloc(net, PF_NFC, GFP_ATOMIC, nfc_proto->proto, kern);
 	if (!sk)
-- 
2.26.2


From 8f489c2a0cffe98ae7030515bd989284a265280b Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Thu, 6 Aug 2020 17:37:53 +0200
Subject: [PATCH 05/15] net: phy: fix memory leak in device-create error path

[ Upstream commit d02cbc46136105cf86f84ac355e16f04696f538d ]

A recent commit introduced a late error path in phy_device_create()
which fails to release the device name allocated by dev_set_name().

Fixes: 13d0ab6750b2 ("net: phy: check return code when requesting PHY driver module")
Cc: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index b4978c5fb2ca..98369430a3be 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -616,7 +616,9 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id,
 	if (c45_ids)
 		dev->c45_ids = *c45_ids;
 	dev->irq = bus->irq[addr];
+
 	dev_set_name(&mdiodev->dev, PHY_ID_FMT, bus->id, addr);
+	device_initialize(&mdiodev->dev);
 
 	dev->state = PHY_DOWN;
 
@@ -650,10 +652,8 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id,
 		ret = phy_request_driver_module(dev, phy_id);
 	}
 
-	if (!ret) {
-		device_initialize(&mdiodev->dev);
-	} else {
-		kfree(dev);
+	if (ret) {
+		put_device(&mdiodev->dev);
 		dev = ERR_PTR(ret);
 	}
 
-- 
2.26.2


From a91e2858759cca792703acab188b0f44c732d5a0 Mon Sep 17 00:00:00 2001
From: Miaohe Lin <linmiaohe@huawei.com>
Date: Thu, 6 Aug 2020 19:53:16 +0800
Subject: [PATCH 06/15] net: Set fput_needed iff FDPUT_FPUT is set

[ Upstream commit ce787a5a074a86f76f5d3fd804fa78e01bfb9e89 ]

We should fput() file iff FDPUT_FPUT is set. So we should set fput_needed
accordingly.

Fixes: 00e188ef6a7e ("sockfd_lookup_light(): switch to fdget^W^Waway from fget_light")
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/socket.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/socket.c b/net/socket.c
index 976426d03f09..481fd5f25669 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -500,7 +500,7 @@ static struct socket *sockfd_lookup_light(int fd, int *err, int *fput_needed)
 	if (f.file) {
 		sock = sock_from_file(f.file, err);
 		if (likely(sock)) {
-			*fput_needed = f.flags;
+			*fput_needed = f.flags & FDPUT_FPUT;
 			return sock;
 		}
 		fdput(f);
-- 
2.26.2


From 6fde4f75ccf7f8e3dbccbbd5ce2713f6c81986d4 Mon Sep 17 00:00:00 2001
From: Ira Weiny <ira.weiny@intel.com>
Date: Mon, 10 Aug 2020 17:02:58 -0700
Subject: [PATCH 07/15] net/tls: Fix kmap usage

[ Upstream commit b06c19d9f827f6743122795570bfc0c72db482b0 ]

When MSG_OOB is specified to tls_device_sendpage() the mapped page is
never unmapped.

Hold off mapping the page until after the flags are checked and the page
is actually needed.

Fixes: e8f69799810c ("net/tls: Add generic NIC offload infrastructure")
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_device.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 0e55f8365ce2..0cbad566f281 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -561,7 +561,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page,
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct iov_iter	msg_iter;
-	char *kaddr = kmap(page);
+	char *kaddr;
 	struct kvec iov;
 	int rc;
 
@@ -576,6 +576,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page,
 		goto out;
 	}
 
+	kaddr = kmap(page);
 	iov.iov_base = kaddr + offset;
 	iov.iov_len = size;
 	iov_iter_kvec(&msg_iter, WRITE, &iov, 1, size);
-- 
2.26.2


From 451e67a12c3edbfa73ef0f7d8c548cb7a7a56ccb Mon Sep 17 00:00:00 2001
From: Jason Baron <jbaron@akamai.com>
Date: Mon, 10 Aug 2020 13:38:39 -0400
Subject: [PATCH 08/15] tcp: correct read of TFO keys on big endian systems

[ Upstream commit f19008e676366c44e9241af57f331b6c6edf9552 ]

When TFO keys are read back on big endian systems either via the global
sysctl interface or via getsockopt() using TCP_FASTOPEN_KEY, the values
don't match what was written.

For example, on s390x:

# echo "1-2-3-4" > /proc/sys/net/ipv4/tcp_fastopen_key
# cat /proc/sys/net/ipv4/tcp_fastopen_key
02000000-01000000-04000000-03000000

Instead of:

# cat /proc/sys/net/ipv4/tcp_fastopen_key
00000001-00000002-00000003-00000004

Fix this by converting to the correct endianness on read. This was
reported by Colin Ian King when running the 'tcp_fastopen_backup_key' net
selftest on s390x, which depends on the read value matching what was
written. I've confirmed that the test now passes on big and little endian
systems.

Signed-off-by: Jason Baron <jbaron@akamai.com>
Fixes: 438ac88009bc ("net: fastopen: robustness and endianness fixes for SipHash")
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Eric Dumazet <edumazet@google.com>
Reported-and-tested-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h          |  2 ++
 net/ipv4/sysctl_net_ipv4.c | 16 ++++------------
 net/ipv4/tcp.c             | 16 ++++------------
 net/ipv4/tcp_fastopen.c    | 23 +++++++++++++++++++++++
 4 files changed, 33 insertions(+), 24 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 4de9485f73d9..0c1d2843a6d7 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1664,6 +1664,8 @@ void tcp_fastopen_destroy_cipher(struct sock *sk);
 void tcp_fastopen_ctx_destroy(struct net *net);
 int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk,
 			      void *primary_key, void *backup_key);
+int tcp_fastopen_get_cipher(struct net *net, struct inet_connection_sock *icsk,
+			    u64 *key);
 void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb);
 struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
 			      struct request_sock *req,
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 5653e3b011bf..54023a46db04 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -301,24 +301,16 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write,
 	struct ctl_table tbl = { .maxlen = ((TCP_FASTOPEN_KEY_LENGTH *
 					    2 * TCP_FASTOPEN_KEY_MAX) +
 					    (TCP_FASTOPEN_KEY_MAX * 5)) };
-	struct tcp_fastopen_context *ctx;
-	u32 user_key[TCP_FASTOPEN_KEY_MAX * 4];
-	__le32 key[TCP_FASTOPEN_KEY_MAX * 4];
+	u32 user_key[TCP_FASTOPEN_KEY_BUF_LENGTH / sizeof(u32)];
+	__le32 key[TCP_FASTOPEN_KEY_BUF_LENGTH / sizeof(__le32)];
 	char *backup_data;
-	int ret, i = 0, off = 0, n_keys = 0;
+	int ret, i = 0, off = 0, n_keys;
 
 	tbl.data = kmalloc(tbl.maxlen, GFP_KERNEL);
 	if (!tbl.data)
 		return -ENOMEM;
 
-	rcu_read_lock();
-	ctx = rcu_dereference(net->ipv4.tcp_fastopen_ctx);
-	if (ctx) {
-		n_keys = tcp_fastopen_context_len(ctx);
-		memcpy(&key[0], &ctx->key[0], TCP_FASTOPEN_KEY_LENGTH * n_keys);
-	}
-	rcu_read_unlock();
-
+	n_keys = tcp_fastopen_get_cipher(net, NULL, (u64 *)key);
 	if (!n_keys) {
 		memset(&key[0], 0, TCP_FASTOPEN_KEY_LENGTH);
 		n_keys = 1;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 6f0caf9a866d..30c1142584b1 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3694,22 +3694,14 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 		return 0;
 
 	case TCP_FASTOPEN_KEY: {
-		__u8 key[TCP_FASTOPEN_KEY_BUF_LENGTH];
-		struct tcp_fastopen_context *ctx;
-		unsigned int key_len = 0;
+		u64 key[TCP_FASTOPEN_KEY_BUF_LENGTH / sizeof(u64)];
+		unsigned int key_len;
 
 		if (get_user(len, optlen))
 			return -EFAULT;
 
-		rcu_read_lock();
-		ctx = rcu_dereference(icsk->icsk_accept_queue.fastopenq.ctx);
-		if (ctx) {
-			key_len = tcp_fastopen_context_len(ctx) *
-					TCP_FASTOPEN_KEY_LENGTH;
-			memcpy(&key[0], &ctx->key[0], key_len);
-		}
-		rcu_read_unlock();
-
+		key_len = tcp_fastopen_get_cipher(net, icsk, key) *
+				TCP_FASTOPEN_KEY_LENGTH;
 		len = min_t(unsigned int, len, key_len);
 		if (put_user(len, optlen))
 			return -EFAULT;
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 19ad9586c720..1bb85821f1e6 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -108,6 +108,29 @@ int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk,
 	return err;
 }
 
+int tcp_fastopen_get_cipher(struct net *net, struct inet_connection_sock *icsk,
+			    u64 *key)
+{
+	struct tcp_fastopen_context *ctx;
+	int n_keys = 0, i;
+
+	rcu_read_lock();
+	if (icsk)
+		ctx = rcu_dereference(icsk->icsk_accept_queue.fastopenq.ctx);
+	else
+		ctx = rcu_dereference(net->ipv4.tcp_fastopen_ctx);
+	if (ctx) {
+		n_keys = tcp_fastopen_context_len(ctx);
+		for (i = 0; i < n_keys; i++) {
+			put_unaligned_le64(ctx->key[i].key[0], key + (i * 2));
+			put_unaligned_le64(ctx->key[i].key[1], key + (i * 2) + 1);
+		}
+	}
+	rcu_read_unlock();
+
+	return n_keys;
+}
+
 static bool __tcp_fastopen_cookie_gen_cipher(struct request_sock *req,
 					     struct sk_buff *syn,
 					     const siphash_key_t *key,
-- 
2.26.2


From 5b6c52f12b74c2714d641f5ae9318abb71a8cd6b Mon Sep 17 00:00:00 2001
From: Ronak Doshi <doshir@vmware.com>
Date: Mon, 10 Aug 2020 09:55:55 -0700
Subject: [PATCH 09/15] vmxnet3: use correct tcp hdr length when packet is
 encapsulated

[ Upstream commit 8a7f280f29a80f6e0798f5d6e07c5dd8726620fe ]

Commit dacce2be3312 ("vmxnet3: add geneve and vxlan tunnel offload
support") added support for encapsulation offload. However, while
calculating tcp hdr length, it does not take into account if the
packet is encapsulated or not.

This patch fixes this issue by using correct reference for inner
tcp header.

Fixes: dacce2be3312 ("vmxnet3: add geneve and vxlan tunnel offload support")
Signed-off-by: Ronak Doshi <doshir@vmware.com>
Acked-by: Guolin Yang <gyang@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vmxnet3/vmxnet3_drv.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index ca395f9679d0..2818015324b8 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -886,7 +886,8 @@ vmxnet3_parse_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
 
 			switch (protocol) {
 			case IPPROTO_TCP:
-				ctx->l4_hdr_size = tcp_hdrlen(skb);
+				ctx->l4_hdr_size = skb->encapsulation ? inner_tcp_hdrlen(skb) :
+						   tcp_hdrlen(skb);
 				break;
 			case IPPROTO_UDP:
 				ctx->l4_hdr_size = sizeof(struct udphdr);
-- 
2.26.2


From d3106ff68f867ed0c14146d98f00b08f7e1cc73e Mon Sep 17 00:00:00 2001
From: Tim Froidcoeur <tim.froidcoeur@tessares.net>
Date: Tue, 11 Aug 2020 20:33:23 +0200
Subject: [PATCH 10/15] net: refactor bind_bucket fastreuse into helper

[ Upstream commit 62ffc589abb176821662efc4525ee4ac0b9c3894 ]

Refactor the fastreuse update code in inet_csk_get_port into a small
helper function that can be called from other places.

Acked-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Tim Froidcoeur <tim.froidcoeur@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_connection_sock.h |  4 ++
 net/ipv4/inet_connection_sock.c    | 97 ++++++++++++++++--------------
 2 files changed, 57 insertions(+), 44 deletions(-)

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index e5b388f5fa20..1d59bf55bb4d 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -316,6 +316,10 @@ int inet_csk_compat_getsockopt(struct sock *sk, int level, int optname,
 int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname,
 			       char __user *optval, unsigned int optlen);
 
+/* update the fast reuse flag when adding a socket */
+void inet_csk_update_fastreuse(struct inet_bind_bucket *tb,
+			       struct sock *sk);
+
 struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu);
 
 #define TCP_PINGPONG_THRESH	3
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index afaf582a5aa9..a1be020bde8e 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -296,6 +296,57 @@ static inline int sk_reuseport_match(struct inet_bind_bucket *tb,
 				    ipv6_only_sock(sk), true, false);
 }
 
+void inet_csk_update_fastreuse(struct inet_bind_bucket *tb,
+			       struct sock *sk)
+{
+	kuid_t uid = sock_i_uid(sk);
+	bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN;
+
+	if (hlist_empty(&tb->owners)) {
+		tb->fastreuse = reuse;
+		if (sk->sk_reuseport) {
+			tb->fastreuseport = FASTREUSEPORT_ANY;
+			tb->fastuid = uid;
+			tb->fast_rcv_saddr = sk->sk_rcv_saddr;
+			tb->fast_ipv6_only = ipv6_only_sock(sk);
+			tb->fast_sk_family = sk->sk_family;
+#if IS_ENABLED(CONFIG_IPV6)
+			tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
+#endif
+		} else {
+			tb->fastreuseport = 0;
+		}
+	} else {
+		if (!reuse)
+			tb->fastreuse = 0;
+		if (sk->sk_reuseport) {
+			/* We didn't match or we don't have fastreuseport set on
+			 * the tb, but we have sk_reuseport set on this socket
+			 * and we know that there are no bind conflicts with
+			 * this socket in this tb, so reset our tb's reuseport
+			 * settings so that any subsequent sockets that match
+			 * our current socket will be put on the fast path.
+			 *
+			 * If we reset we need to set FASTREUSEPORT_STRICT so we
+			 * do extra checking for all subsequent sk_reuseport
+			 * socks.
+			 */
+			if (!sk_reuseport_match(tb, sk)) {
+				tb->fastreuseport = FASTREUSEPORT_STRICT;
+				tb->fastuid = uid;
+				tb->fast_rcv_saddr = sk->sk_rcv_saddr;
+				tb->fast_ipv6_only = ipv6_only_sock(sk);
+				tb->fast_sk_family = sk->sk_family;
+#if IS_ENABLED(CONFIG_IPV6)
+				tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
+#endif
+			}
+		} else {
+			tb->fastreuseport = 0;
+		}
+	}
+}
+
 /* Obtain a reference to a local port for the given sock,
  * if snum is zero it means select any available local port.
  * We try to allocate an odd port (and leave even ports for connect())
@@ -308,7 +359,6 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
 	struct inet_bind_hashbucket *head;
 	struct net *net = sock_net(sk);
 	struct inet_bind_bucket *tb = NULL;
-	kuid_t uid = sock_i_uid(sk);
 	int l3mdev;
 
 	l3mdev = inet_sk_bound_l3mdev(sk);
@@ -345,49 +395,8 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
 			goto fail_unlock;
 	}
 success:
-	if (hlist_empty(&tb->owners)) {
-		tb->fastreuse = reuse;
-		if (sk->sk_reuseport) {
-			tb->fastreuseport = FASTREUSEPORT_ANY;
-			tb->fastuid = uid;
-			tb->fast_rcv_saddr = sk->sk_rcv_saddr;
-			tb->fast_ipv6_only = ipv6_only_sock(sk);
-			tb->fast_sk_family = sk->sk_family;
-#if IS_ENABLED(CONFIG_IPV6)
-			tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
-#endif
-		} else {
-			tb->fastreuseport = 0;
-		}
-	} else {
-		if (!reuse)
-			tb->fastreuse = 0;
-		if (sk->sk_reuseport) {
-			/* We didn't match or we don't have fastreuseport set on
-			 * the tb, but we have sk_reuseport set on this socket
-			 * and we know that there are no bind conflicts with
-			 * this socket in this tb, so reset our tb's reuseport
-			 * settings so that any subsequent sockets that match
-			 * our current socket will be put on the fast path.
-			 *
-			 * If we reset we need to set FASTREUSEPORT_STRICT so we
-			 * do extra checking for all subsequent sk_reuseport
-			 * socks.
-			 */
-			if (!sk_reuseport_match(tb, sk)) {
-				tb->fastreuseport = FASTREUSEPORT_STRICT;
-				tb->fastuid = uid;
-				tb->fast_rcv_saddr = sk->sk_rcv_saddr;
-				tb->fast_ipv6_only = ipv6_only_sock(sk);
-				tb->fast_sk_family = sk->sk_family;
-#if IS_ENABLED(CONFIG_IPV6)
-				tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
-#endif
-			}
-		} else {
-			tb->fastreuseport = 0;
-		}
-	}
+	inet_csk_update_fastreuse(tb, sk);
+
 	if (!inet_csk(sk)->icsk_bind_hash)
 		inet_bind_hash(sk, tb, port);
 	WARN_ON(inet_csk(sk)->icsk_bind_hash != tb);
-- 
2.26.2


From 2fba99b87747b52c627407a8e70209c62aef3803 Mon Sep 17 00:00:00 2001
From: Tim Froidcoeur <tim.froidcoeur@tessares.net>
Date: Tue, 11 Aug 2020 20:33:24 +0200
Subject: [PATCH 11/15] net: initialize fastreuse on inet_inherit_port

[ Upstream commit d76f3351cea2d927fdf70dd7c06898235035e84e ]

In the case of TPROXY, bind_conflict optimizations for SO_REUSEADDR or
SO_REUSEPORT are broken, possibly resulting in O(n) instead of O(1) bind
behaviour or in the incorrect reuse of a bind.

the kernel keeps track for each bind_bucket if all sockets in the
bind_bucket support SO_REUSEADDR or SO_REUSEPORT in two fastreuse flags.
These flags allow skipping the costly bind_conflict check when possible
(meaning when all sockets have the proper SO_REUSE option).

For every socket added to a bind_bucket, these flags need to be updated.
As soon as a socket that does not support reuse is added, the flag is
set to false and will never go back to true, unless the bind_bucket is
deleted.

Note that there is no mechanism to re-evaluate these flags when a socket
is removed (this might make sense when removing a socket that would not
allow reuse; this leaves room for a future patch).

For this optimization to work, it is mandatory that these flags are
properly initialized and updated.

When a child socket is created from a listen socket in
__inet_inherit_port, the TPROXY case could create a new bind bucket
without properly initializing these flags, thus preventing the
optimization to work. Alternatively, a socket not allowing reuse could
be added to an existing bind bucket without updating the flags, causing
bind_conflict to never be called as it should.

Call inet_csk_update_fastreuse when __inet_inherit_port decides to create
a new bind_bucket or use a different bind_bucket than the one of the
listen socket.

Fixes: 093d282321da ("tproxy: fix hash locking issue when using port redirection in __inet_inherit_port()")
Acked-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Tim Froidcoeur <tim.froidcoeur@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/inet_hashtables.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 2bbaaf0c7176..006a34b18537 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -163,6 +163,7 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child)
 				return -ENOMEM;
 			}
 		}
+		inet_csk_update_fastreuse(tb, child);
 	}
 	inet_bind_hash(child, tb, port);
 	spin_unlock(&head->lock);
-- 
2.26.2


From 47db6650a790e8c15c0d0e90d4952f858af3a43e Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Wed, 12 Aug 2020 14:56:02 +0200
Subject: [PATCH 12/15] vsock: fix potential null pointer dereference in
 vsock_poll()

[ Upstream commit 1980c05844830a44708c98c96d600833aa3fae08 ]

syzbot reported this issue where in the vsock_poll() we find the
socket state at TCP_ESTABLISHED, but 'transport' is null:
  general protection fault, probably for non-canonical address 0xdffffc0000000012: 0000 [#1] PREEMPT SMP KASAN
  KASAN: null-ptr-deref in range [0x0000000000000090-0x0000000000000097]
  CPU: 0 PID: 8227 Comm: syz-executor.2 Not tainted 5.8.0-rc7-syzkaller #0
  Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
  RIP: 0010:vsock_poll+0x75a/0x8e0 net/vmw_vsock/af_vsock.c:1038
  Call Trace:
   sock_poll+0x159/0x460 net/socket.c:1266
   vfs_poll include/linux/poll.h:90 [inline]
   do_pollfd fs/select.c:869 [inline]
   do_poll fs/select.c:917 [inline]
   do_sys_poll+0x607/0xd40 fs/select.c:1011
   __do_sys_poll fs/select.c:1069 [inline]
   __se_sys_poll fs/select.c:1057 [inline]
   __x64_sys_poll+0x18c/0x440 fs/select.c:1057
   do_syscall_64+0x60/0xe0 arch/x86/entry/common.c:384
   entry_SYSCALL_64_after_hwframe+0x44/0xa9

This issue can happen if the TCP_ESTABLISHED state is set after we read
the vsk->transport in the vsock_poll().

We could put barriers to synchronize, but this can only happen during
connection setup, so we can simply check that 'transport' is valid.

Fixes: c0cfa2d8a788 ("vsock: add multi-transports support")
Reported-and-tested-by: syzbot+a61bac2fcc1a7c6623fe@syzkaller.appspotmail.com
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Reviewed-by: Jorgen Hansen <jhansen@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/vmw_vsock/af_vsock.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 626bf9044418..6cd0df1c5caf 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1032,7 +1032,7 @@ static __poll_t vsock_poll(struct file *file, struct socket *sock,
 		}
 
 		/* Connected sockets that can produce data can be written. */
-		if (sk->sk_state == TCP_ESTABLISHED) {
+		if (transport && sk->sk_state == TCP_ESTABLISHED) {
 			if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
 				bool space_avail_now = false;
 				int ret = transport->notify_poll_out(
-- 
2.26.2


From e19516aa4cde8cd790c20a95e2acb41df1e7b01d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Marek=20Beh=C3=BAn?= <marek.behun@nic.cz>
Date: Mon, 10 Aug 2020 17:01:58 +0200
Subject: [PATCH 13/15] net: phy: marvell10g: fix null pointer dereference
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[ Upstream commit 1b8ef1423dbfd34de2439a2db457b84480b7c8a8 ]

Commit c3e302edca24 ("net: phy: marvell10g: fix temperature sensor on 2110")
added a check for PHY ID via phydev->drv->phy_id in a function which is
called by devres at a time when phydev->drv is already set to null by
phy_remove function.

This null pointer dereference can be triggered via SFP subsystem with a
SFP module containing this Marvell PHY. When the SFP interface is put
down, the SFP subsystem removes the PHY.

Fixes: c3e302edca24 ("net: phy: marvell10g: fix temperature sensor on 2110")
Signed-off-by: Marek Behún <marek.behun@nic.cz>
Cc: Maxime Chevallier <maxime.chevallier@bootlin.com>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: Baruch Siach <baruch@tkos.co.il>
Cc: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/marvell10g.c | 18 +++++++-----------
 1 file changed, 7 insertions(+), 11 deletions(-)

diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c
index d4c2e62b2439..179f5ea405d8 100644
--- a/drivers/net/phy/marvell10g.c
+++ b/drivers/net/phy/marvell10g.c
@@ -205,13 +205,6 @@ static int mv3310_hwmon_config(struct phy_device *phydev, bool enable)
 			      MV_V2_TEMP_CTRL_MASK, val);
 }
 
-static void mv3310_hwmon_disable(void *data)
-{
-	struct phy_device *phydev = data;
-
-	mv3310_hwmon_config(phydev, false);
-}
-
 static int mv3310_hwmon_probe(struct phy_device *phydev)
 {
 	struct device *dev = &phydev->mdio.dev;
@@ -235,10 +228,6 @@ static int mv3310_hwmon_probe(struct phy_device *phydev)
 	if (ret)
 		return ret;
 
-	ret = devm_add_action_or_reset(dev, mv3310_hwmon_disable, phydev);
-	if (ret)
-		return ret;
-
 	priv->hwmon_dev = devm_hwmon_device_register_with_info(dev,
 				priv->hwmon_name, phydev,
 				&mv3310_hwmon_chip_info, NULL);
@@ -423,6 +412,11 @@ static int mv3310_probe(struct phy_device *phydev)
 	return phy_sfp_probe(phydev, &mv3310_sfp_ops);
 }
 
+static void mv3310_remove(struct phy_device *phydev)
+{
+	mv3310_hwmon_config(phydev, false);
+}
+
 static int mv3310_suspend(struct phy_device *phydev)
 {
 	return mv3310_power_down(phydev);
@@ -762,6 +756,7 @@ static struct phy_driver mv3310_drivers[] = {
 		.read_status	= mv3310_read_status,
 		.get_tunable	= mv3310_get_tunable,
 		.set_tunable	= mv3310_set_tunable,
+		.remove		= mv3310_remove,
 	},
 	{
 		.phy_id		= MARVELL_PHY_ID_88E2110,
@@ -776,6 +771,7 @@ static struct phy_driver mv3310_drivers[] = {
 		.read_status	= mv3310_read_status,
 		.get_tunable	= mv3310_get_tunable,
 		.set_tunable	= mv3310_set_tunable,
+		.remove		= mv3310_remove,
 	},
 };
 
-- 
2.26.2


From 649a249d18cce0289be601bb49ceda33c0eca7c3 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 14 Aug 2020 15:56:34 +0200
Subject: [PATCH 14/15] mptcp: sendmsg: reset iter on error

[ Upstream commit 35759383133f64d90eba120a0d3efe8f71241650 ]

Once we've copied data from the iterator we need to revert in case we
end up not sending any data.

This bug doesn't trigger with normal 'poll' based tests, because
we only feed a small chunk of data to kernel after poll indicated
POLLOUT.  With blocking IO and large writes this triggers. Receiver
ends up with less data than it should get.

Fixes: 72511aab95c94d ("mptcp: avoid blocking in tcp_sendpages")
Signed-off-by: Florian Westphal <fw@strlen.de>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mptcp/protocol.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index c0abe738e7d3..ac8880514d5d 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -605,8 +605,10 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 		if (!psize)
 			return -EINVAL;
 
-		if (!sk_wmem_schedule(sk, psize + dfrag->overhead))
+		if (!sk_wmem_schedule(sk, psize + dfrag->overhead)) {
+			iov_iter_revert(&msg->msg_iter, psize);
 			return -ENOMEM;
+		}
 	} else {
 		offset = dfrag->offset;
 		psize = min_t(size_t, dfrag->data_len, avail_size);
@@ -617,8 +619,10 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 	 */
 	ret = do_tcp_sendpages(ssk, page, offset, psize,
 			       msg->msg_flags | MSG_SENDPAGE_NOTLAST | MSG_DONTWAIT);
-	if (ret <= 0)
+	if (ret <= 0) {
+		iov_iter_revert(&msg->msg_iter, psize);
 		return ret;
+	}
 
 	frag_truesize += ret;
 	if (!retransmission) {
-- 
2.26.2


From ab90acc288e9d8e3902f2017f741a3895a7f91b3 Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Fri, 7 Aug 2020 09:36:32 +0200
Subject: [PATCH 15/15] r8152: Use MAC address from correct device tree node

[ Upstream commit b9b40ee4db6cb186341b97bca4f0d7aa2a042a66 ]

Query the USB device's device tree node when looking for a MAC address.
The struct device embedded into the struct net_device does not have a
device tree node attached at all.

The reason why this went unnoticed is because the system where this was
tested was one of the few development units that had its OTP programmed,
as opposed to production systems where the MAC address is stored in a
separate EEPROM and is passed via device tree by the firmware.

Reported-by: EJ Hsu <ejh@nvidia.com>
Fixes: acb6d3771a03 ("r8152: Use MAC address from device tree if available")
Signed-off-by: Thierry Reding <treding@nvidia.com>
Reviewed-by: EJ Hsu <ejh@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 7d39f998535d..2b02fefd094d 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -1504,7 +1504,7 @@ static int determine_ethernet_addr(struct r8152 *tp, struct sockaddr *sa)
 
 	sa->sa_family = dev->type;
 
-	ret = eth_platform_get_mac_address(&dev->dev, sa->sa_data);
+	ret = eth_platform_get_mac_address(&tp->udev->dev, sa->sa_data);
 	if (ret < 0) {
 		if (tp->version == RTL_VER_01) {
 			ret = pla_ocp_read(tp, PLA_IDR, 8, sa->sa_data);
-- 
2.26.2

Re: [PATCHES] Networking

[Greg KH]

On Fri, Aug 14, 2020 at 06:36:07PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v5.7
> and v5.8 -stable, respectively.

All now queued up, thanks!

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 105 bytes --]


Please queue up the following networking bug fixes for v5.7
and v5.8 -stable, respectively.

Thank you!

[-- Attachment #2: net_57.mbox --]
[-- Type: Application/Octet-Stream, Size: 49992 bytes --]

From 67ffdaeb2251cacabc8f375cacb32b7fb0b80ca3 Mon Sep 17 00:00:00 2001
From: Jiri Wiesner <jwiesner@suse.com>
Date: Sun, 16 Aug 2020 20:52:44 +0200
Subject: [PATCH 01/22] bonding: fix active-backup failover for current ARP
 slave

[ Upstream commit 0410d07190961ac526f05085765a8d04d926545b ]

When the ARP monitor is used for link detection, ARP replies are
validated for all slaves (arp_validate=3) and fail_over_mac is set to
active, two slaves of an active-backup bond may get stuck in a state
where both of them are active and pass packets that they receive to
the bond. This state makes IPv6 duplicate address detection fail. The
state is reached thus:
1. The current active slave goes down because the ARP target
   is not reachable.
2. The current ARP slave is chosen and made active.
3. A new slave is enslaved. This new slave becomes the current active
   slave and can reach the ARP target.
As a result, the current ARP slave stays active after the enslave
action has finished and the log is littered with "PROBE BAD" messages:
> bond0: PROBE: c_arp ens10 && cas ens11 BAD
The workaround is to remove the slave with "going back" status from
the bond and re-enslave it. This issue was encountered when DPDK PMD
interfaces were being enslaved to an active-backup bond.

I would be possible to fix the issue in bond_enslave() or
bond_change_active_slave() but the ARP monitor was fixed instead to
keep most of the actions changing the current ARP slave in the ARP
monitor code. The current ARP slave is set as inactive and backup
during the commit phase. A new state, BOND_LINK_FAIL, has been
introduced for slaves in the context of the ARP monitor. This allows
administrators to see how slaves are rotated for sending ARP requests
and attempts are made to find a new active slave.

Fixes: b2220cad583c9 ("bonding: refactor ARP active-backup monitor")
Signed-off-by: Jiri Wiesner <jwiesner@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 6b40b5ab143a..dba3dfa2658f 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2824,6 +2824,9 @@ static int bond_ab_arp_inspect(struct bonding *bond)
 			if (bond_time_in_interval(bond, last_rx, 1)) {
 				bond_propose_link_state(slave, BOND_LINK_UP);
 				commit++;
+			} else if (slave->link == BOND_LINK_BACK) {
+				bond_propose_link_state(slave, BOND_LINK_FAIL);
+				commit++;
 			}
 			continue;
 		}
@@ -2932,6 +2935,19 @@ static void bond_ab_arp_commit(struct bonding *bond)
 
 			continue;
 
+		case BOND_LINK_FAIL:
+			bond_set_slave_link_state(slave, BOND_LINK_FAIL,
+						  BOND_SLAVE_NOTIFY_NOW);
+			bond_set_slave_inactive_flags(slave,
+						      BOND_SLAVE_NOTIFY_NOW);
+
+			/* A slave has just been enslaved and has become
+			 * the current active slave.
+			 */
+			if (rtnl_dereference(bond->curr_active_slave))
+				RCU_INIT_POINTER(bond->current_arp_slave, NULL);
+			continue;
+
 		default:
 			slave_err(bond->dev, slave->dev,
 				  "impossible: link_new_state %d on slave\n",
@@ -2982,8 +2998,6 @@ static bool bond_ab_arp_probe(struct bonding *bond)
 			return should_notify_rtnl;
 	}
 
-	bond_set_slave_inactive_flags(curr_arp_slave, BOND_SLAVE_NOTIFY_LATER);
-
 	bond_for_each_slave_rcu(bond, slave, iter) {
 		if (!found && !before && bond_slave_is_up(slave))
 			before = slave;
-- 
2.26.2


From cf3b4dfe8d2ed592baea5d3e7bf43788c643388f Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Fri, 14 Aug 2020 20:05:58 -0700
Subject: [PATCH 02/22] bonding: fix a potential double-unregister

[ Upstream commit 832707021666411d04795c564a4adea5d6b94f17 ]

When we tear down a network namespace, we unregister all
the netdevices within it. So we may queue a slave device
and a bonding device together in the same unregister queue.

If the only slave device is non-ethernet, it would
automatically unregister the bonding device as well. Thus,
we may end up unregistering the bonding device twice.

Workaround this special case by checking reg_state.

Fixes: 9b5e383c11b0 ("net: Introduce unregister_netdevice_many()")
Reported-by: syzbot+af23e7f3e0a7e10c8b67@syzkaller.appspotmail.com
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Andy Gospodarek <andy@greyhouse.net>
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index dba3dfa2658f..7949bbb0eaa7 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2084,7 +2084,8 @@ static int bond_release_and_destroy(struct net_device *bond_dev,
 	int ret;
 
 	ret = __bond_release_one(bond_dev, slave_dev, false, true);
-	if (ret == 0 && !bond_has_slaves(bond)) {
+	if (ret == 0 && !bond_has_slaves(bond) &&
+	    bond_dev->reg_state != NETREG_UNREGISTERING) {
 		bond_dev->priv_flags |= IFF_DISABLE_NETPOLL;
 		netdev_info(bond_dev, "Destroying bond\n");
 		bond_remove_proc_entry(bond);
-- 
2.26.2


From 4d960057ea2992a048949d3e37a4549a45cb5160 Mon Sep 17 00:00:00 2001
From: Jarod Wilson <jarod@redhat.com>
Date: Thu, 13 Aug 2020 10:09:00 -0400
Subject: [PATCH 03/22] bonding: show saner speed for broadcast mode

[ Upstream commit 4ca0d9ac3fd8f9f90b72a15d8da2aca3ffb58418 ]

Broadcast mode bonds transmit a copy of all traffic simultaneously out of
all interfaces, so the "speed" of the bond isn't really the aggregate of
all interfaces, but rather, the speed of the slowest active interface.

Also, the type of the speed field is u32, not unsigned long, so adjust
that accordingly, as required to make min() function here without
complaining about mismatching types.

Fixes: bb5b052f751b ("bond: add support to read speed and duplex via ethtool")
CC: Jay Vosburgh <j.vosburgh@gmail.com>
CC: Veaceslav Falico <vfalico@gmail.com>
CC: Andy Gospodarek <andy@greyhouse.net>
CC: "David S. Miller" <davem@davemloft.net>
CC: netdev@vger.kernel.org
Acked-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 21 ++++++++++++++++++---
 1 file changed, 18 insertions(+), 3 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 7949bbb0eaa7..07624e89b96d 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -4351,13 +4351,23 @@ static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	return ret;
 }
 
+static u32 bond_mode_bcast_speed(struct slave *slave, u32 speed)
+{
+	if (speed == 0 || speed == SPEED_UNKNOWN)
+		speed = slave->speed;
+	else
+		speed = min(speed, slave->speed);
+
+	return speed;
+}
+
 static int bond_ethtool_get_link_ksettings(struct net_device *bond_dev,
 					   struct ethtool_link_ksettings *cmd)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
-	unsigned long speed = 0;
 	struct list_head *iter;
 	struct slave *slave;
+	u32 speed = 0;
 
 	cmd->base.duplex = DUPLEX_UNKNOWN;
 	cmd->base.port = PORT_OTHER;
@@ -4369,8 +4379,13 @@ static int bond_ethtool_get_link_ksettings(struct net_device *bond_dev,
 	 */
 	bond_for_each_slave(bond, slave, iter) {
 		if (bond_slave_can_tx(slave)) {
-			if (slave->speed != SPEED_UNKNOWN)
-				speed += slave->speed;
+			if (slave->speed != SPEED_UNKNOWN) {
+				if (BOND_MODE(bond) == BOND_MODE_BROADCAST)
+					speed = bond_mode_bcast_speed(slave,
+								      speed);
+				else
+					speed += slave->speed;
+			}
 			if (cmd->base.duplex == DUPLEX_UNKNOWN &&
 			    slave->duplex != DUPLEX_UNKNOWN)
 				cmd->base.duplex = slave->duplex;
-- 
2.26.2


From 4fdb2f21ca879ea63639ee1c0aa765191440a3e7 Mon Sep 17 00:00:00 2001
From: Mark Tomlinson <mark.tomlinson@alliedtelesis.co.nz>
Date: Wed, 19 Aug 2020 13:53:58 +1200
Subject: [PATCH 04/22] gre6: Fix reception with IP6_TNL_F_RCV_DSCP_COPY

[ Upstream commit 272502fcb7cda01ab07fc2fcff82d1d2f73d43cc ]

When receiving an IPv4 packet inside an IPv6 GRE packet, and the
IP6_TNL_F_RCV_DSCP_COPY flag is set on the tunnel, the IPv4 header would
get corrupted. This is due to the common ip6_tnl_rcv() function assuming
that the inner header is always IPv6. This patch checks the tunnel
protocol for IPv4 inner packets, but still defaults to IPv6.

Fixes: 308edfdf1563 ("gre6: Cleanup GREv6 receive path, call common GRE functions")
Signed-off-by: Mark Tomlinson <mark.tomlinson@alliedtelesis.co.nz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 4703b09808d0..84f90b8b8890 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -886,7 +886,15 @@ int ip6_tnl_rcv(struct ip6_tnl *t, struct sk_buff *skb,
 		struct metadata_dst *tun_dst,
 		bool log_ecn_err)
 {
-	return __ip6_tnl_rcv(t, skb, tpi, tun_dst, ip6ip6_dscp_ecn_decapsulate,
+	int (*dscp_ecn_decapsulate)(const struct ip6_tnl *t,
+				    const struct ipv6hdr *ipv6h,
+				    struct sk_buff *skb);
+
+	dscp_ecn_decapsulate = ip6ip6_dscp_ecn_decapsulate;
+	if (tpi->proto == htons(ETH_P_IP))
+		dscp_ecn_decapsulate = ip4ip6_dscp_ecn_decapsulate;
+
+	return __ip6_tnl_rcv(t, skb, tpi, tun_dst, dscp_ecn_decapsulate,
 			     log_ecn_err);
 }
 EXPORT_SYMBOL(ip6_tnl_rcv);
-- 
2.26.2


From f243a56661d81495d31ea7545e3452eea3890ac1 Mon Sep 17 00:00:00 2001
From: Mahesh Bandewar <maheshb@google.com>
Date: Fri, 14 Aug 2020 22:53:24 -0700
Subject: [PATCH 05/22] ipvlan: fix device features

[ Upstream commit d0f5c7076e01fef6fcb86988d9508bf3ce258bd4 ]

Processing NETDEV_FEAT_CHANGE causes IPvlan links to lose
NETIF_F_LLTX feature because of the incorrect handling of
features in ipvlan_fix_features().

--before--
lpaa10:~# ethtool -k ipvl0 | grep tx-lockless
tx-lockless: on [fixed]
lpaa10:~# ethtool -K ipvl0 tso off
Cannot change tcp-segmentation-offload
Actual changes:
vlan-challenged: off [fixed]
tx-lockless: off [fixed]
lpaa10:~# ethtool -k ipvl0 | grep tx-lockless
tx-lockless: off [fixed]
lpaa10:~#

--after--
lpaa10:~# ethtool -k ipvl0 | grep tx-lockless
tx-lockless: on [fixed]
lpaa10:~# ethtool -K ipvl0 tso off
Cannot change tcp-segmentation-offload
Could not change any device features
lpaa10:~# ethtool -k ipvl0 | grep tx-lockless
tx-lockless: on [fixed]
lpaa10:~#

Fixes: 2ad7bf363841 ("ipvlan: Initial check-in of the IPVLAN driver.")
Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ipvlan/ipvlan_main.c | 27 ++++++++++++++++++++++-----
 1 file changed, 22 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index f195f278a83a..7768f1120c1f 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -106,12 +106,21 @@ static void ipvlan_port_destroy(struct net_device *dev)
 	kfree(port);
 }
 
+#define IPVLAN_ALWAYS_ON_OFLOADS \
+	(NETIF_F_SG | NETIF_F_HW_CSUM | \
+	 NETIF_F_GSO_ROBUST | NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL)
+
+#define IPVLAN_ALWAYS_ON \
+	(IPVLAN_ALWAYS_ON_OFLOADS | NETIF_F_LLTX | NETIF_F_VLAN_CHALLENGED)
+
 #define IPVLAN_FEATURES \
-	(NETIF_F_SG | NETIF_F_CSUM_MASK | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \
+	(NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \
 	 NETIF_F_GSO | NETIF_F_ALL_TSO | NETIF_F_GSO_ROBUST | \
 	 NETIF_F_GRO | NETIF_F_RXCSUM | \
 	 NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER)
 
+	/* NETIF_F_GSO_ENCAP_ALL NETIF_F_GSO_SOFTWARE Newly added */
+
 #define IPVLAN_STATE_MASK \
 	((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT))
 
@@ -125,7 +134,9 @@ static int ipvlan_init(struct net_device *dev)
 	dev->state = (dev->state & ~IPVLAN_STATE_MASK) |
 		     (phy_dev->state & IPVLAN_STATE_MASK);
 	dev->features = phy_dev->features & IPVLAN_FEATURES;
-	dev->features |= NETIF_F_LLTX | NETIF_F_VLAN_CHALLENGED;
+	dev->features |= IPVLAN_ALWAYS_ON;
+	dev->vlan_features = phy_dev->vlan_features & IPVLAN_FEATURES;
+	dev->vlan_features |= IPVLAN_ALWAYS_ON_OFLOADS;
 	dev->hw_enc_features |= dev->features;
 	dev->gso_max_size = phy_dev->gso_max_size;
 	dev->gso_max_segs = phy_dev->gso_max_segs;
@@ -225,7 +236,14 @@ static netdev_features_t ipvlan_fix_features(struct net_device *dev,
 {
 	struct ipvl_dev *ipvlan = netdev_priv(dev);
 
-	return features & (ipvlan->sfeatures | ~IPVLAN_FEATURES);
+	features |= NETIF_F_ALL_FOR_ALL;
+	features &= (ipvlan->sfeatures | ~IPVLAN_FEATURES);
+	features = netdev_increment_features(ipvlan->phy_dev->features,
+					     features, features);
+	features |= IPVLAN_ALWAYS_ON;
+	features &= (IPVLAN_FEATURES | IPVLAN_ALWAYS_ON);
+
+	return features;
 }
 
 static void ipvlan_change_rx_flags(struct net_device *dev, int change)
@@ -732,10 +750,9 @@ static int ipvlan_device_event(struct notifier_block *unused,
 
 	case NETDEV_FEAT_CHANGE:
 		list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
-			ipvlan->dev->features = dev->features & IPVLAN_FEATURES;
 			ipvlan->dev->gso_max_size = dev->gso_max_size;
 			ipvlan->dev->gso_max_segs = dev->gso_max_segs;
-			netdev_features_change(ipvlan->dev);
+			netdev_update_features(ipvlan->dev);
 		}
 		break;
 
-- 
2.26.2


From afa1200fa5e43ffcea1971627c65ce1dd450b04a Mon Sep 17 00:00:00 2001
From: Tom Rix <trix@redhat.com>
Date: Fri, 21 Aug 2020 06:56:00 -0700
Subject: [PATCH 06/22] net: dsa: b53: check for timeout

[ Upstream commit 774d977abfd024e6f73484544b9abe5a5cd62de7 ]

clang static analysis reports this problem

b53_common.c:1583:13: warning: The left expression of the compound
  assignment is an uninitialized value. The computed value will
  also be garbage
        ent.port &= ~BIT(port);
        ~~~~~~~~ ^

ent is set by a successful call to b53_arl_read().  Unsuccessful
calls are caught by an switch statement handling specific returns.
b32_arl_read() calls b53_arl_op_wait() which fails with the
unhandled -ETIMEDOUT.

So add -ETIMEDOUT to the switch statement.  Because
b53_arl_op_wait() already prints out a message, do not add another
one.

Fixes: 1da6df85c6fb ("net: dsa: b53: Implement ARL add/del/dump operations")
Signed-off-by: Tom Rix <trix@redhat.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/b53/b53_common.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index c283593bef17..dc1979096302 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -1556,6 +1556,8 @@ static int b53_arl_op(struct b53_device *dev, int op, int port,
 		return ret;
 
 	switch (ret) {
+	case -ETIMEDOUT:
+		return ret;
 	case -ENOSPC:
 		dev_dbg(dev->dev, "{%pM,%.4d} no space left in ARL\n",
 			addr, vid);
-- 
2.26.2


From afd4ace0ad32a9d8ff86bb5fc20db33a5d65a15c Mon Sep 17 00:00:00 2001
From: Fugang Duan <fugang.duan@nxp.com>
Date: Thu, 13 Aug 2020 15:13:14 +0800
Subject: [PATCH 07/22] net: fec: correct the error path for regulator disable
 in probe

[ Upstream commit c6165cf0dbb82ded90163dce3ac183fc7a913dc4 ]

Correct the error path for regulator disable.

Fixes: 9269e5560b26 ("net: fec: add phy-reset-gpios PROBE_DEFER check")
Signed-off-by: Fugang Duan <fugang.duan@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index bf73bc9bf35b..76abafd099e2 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -3719,11 +3719,11 @@ fec_probe(struct platform_device *pdev)
 failed_irq:
 failed_init:
 	fec_ptp_stop(pdev);
-	if (fep->reg_phy)
-		regulator_disable(fep->reg_phy);
 failed_reset:
 	pm_runtime_put_noidle(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
+	if (fep->reg_phy)
+		regulator_disable(fep->reg_phy);
 failed_regulator:
 	clk_disable_unprepare(fep->clk_ahb);
 failed_clk_ahb:
-- 
2.26.2


From cbe84ff9cdd615d97e9ca977b7dd7e61f65b0992 Mon Sep 17 00:00:00 2001
From: Miaohe Lin <linmiaohe@huawei.com>
Date: Sat, 15 Aug 2020 04:44:31 -0400
Subject: [PATCH 08/22] net: Fix potential wrong skb->protocol in
 skb_vlan_untag()

[ Upstream commit 55eff0eb7460c3d50716ed9eccf22257b046ca92 ]

We may access the two bytes after vlan_hdr in vlan_set_encap_proto(). So
we should pull VLAN_HLEN + sizeof(unsigned short) in skb_vlan_untag() or
we may access the wrong data.

Fixes: 0d5501c1c828 ("net: Always untag vlan-tagged traffic on input.")
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 7e29590482ce..115f3fde314f 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5421,8 +5421,8 @@ struct sk_buff *skb_vlan_untag(struct sk_buff *skb)
 	skb = skb_share_check(skb, GFP_ATOMIC);
 	if (unlikely(!skb))
 		goto err_free;
-
-	if (unlikely(!pskb_may_pull(skb, VLAN_HLEN)))
+	/* We may access the two bytes after vlan_hdr in vlan_set_encap_proto(). */
+	if (unlikely(!pskb_may_pull(skb, VLAN_HLEN + sizeof(unsigned short))))
 		goto err_free;
 
 	vhdr = (struct vlan_hdr *)skb->data;
-- 
2.26.2


From cca592cfae7f82242549d6cf9db4ecd6ed705dcc Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Sat, 22 Aug 2020 15:06:36 +0300
Subject: [PATCH 09/22] net: nexthop: don't allow empty NHA_GROUP

[ Upstream commit eeaac3634ee0e3f35548be35275efeca888e9b23 ]

Currently the nexthop code will use an empty NHA_GROUP attribute, but it
requires at least 1 entry in order to function properly. Otherwise we
end up derefencing null or random pointers all over the place due to not
having any nh_grp_entry members allocated, nexthop code relies on having at
least the first member present. Empty NHA_GROUP doesn't make any sense so
just disallow it.
Also add a WARN_ON for any future users of nexthop_create_group().

 BUG: kernel NULL pointer dereference, address: 0000000000000080
 #PF: supervisor read access in kernel mode
 #PF: error_code(0x0000) - not-present page
 PGD 0 P4D 0
 Oops: 0000 [#1] SMP
 CPU: 0 PID: 558 Comm: ip Not tainted 5.9.0-rc1+ #93
 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-2.fc32 04/01/2014
 RIP: 0010:fib_check_nexthop+0x4a/0xaa
 Code: 0f 84 83 00 00 00 48 c7 02 80 03 f7 81 c3 40 80 fe fe 75 12 b8 ea ff ff ff 48 85 d2 74 6b 48 c7 02 40 03 f7 81 c3 48 8b 40 10 <48> 8b 80 80 00 00 00 eb 36 80 78 1a 00 74 12 b8 ea ff ff ff 48 85
 RSP: 0018:ffff88807983ba00 EFLAGS: 00010213
 RAX: 0000000000000000 RBX: ffff88807983bc00 RCX: 0000000000000000
 RDX: ffff88807983bc00 RSI: 0000000000000000 RDI: ffff88807bdd0a80
 RBP: ffff88807983baf8 R08: 0000000000000dc0 R09: 000000000000040a
 R10: 0000000000000000 R11: ffff88807bdd0ae8 R12: 0000000000000000
 R13: 0000000000000000 R14: ffff88807bea3100 R15: 0000000000000001
 FS:  00007f10db393700(0000) GS:ffff88807dc00000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000000080 CR3: 000000007bd0f004 CR4: 00000000003706f0
 Call Trace:
  fib_create_info+0x64d/0xaf7
  fib_table_insert+0xf6/0x581
  ? __vma_adjust+0x3b6/0x4d4
  inet_rtm_newroute+0x56/0x70
  rtnetlink_rcv_msg+0x1e3/0x20d
  ? rtnl_calcit.isra.0+0xb8/0xb8
  netlink_rcv_skb+0x5b/0xac
  netlink_unicast+0xfa/0x17b
  netlink_sendmsg+0x334/0x353
  sock_sendmsg_nosec+0xf/0x3f
  ____sys_sendmsg+0x1a0/0x1fc
  ? copy_msghdr_from_user+0x4c/0x61
  ___sys_sendmsg+0x63/0x84
  ? handle_mm_fault+0xa39/0x11b5
  ? sockfd_lookup_light+0x72/0x9a
  __sys_sendmsg+0x50/0x6e
  do_syscall_64+0x54/0xbe
  entry_SYSCALL_64_after_hwframe+0x44/0xa9
 RIP: 0033:0x7f10dacc0bb7
 Code: d8 64 89 02 48 c7 c0 ff ff ff ff eb cd 66 0f 1f 44 00 00 8b 05 9a 4b 2b 00 85 c0 75 2e 48 63 ff 48 63 d2 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 01 c3 48 8b 15 b1 f2 2a 00 f7 d8 64 89 02 48
 RSP: 002b:00007ffcbe628bf8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
 RAX: ffffffffffffffda RBX: 00007ffcbe628f80 RCX: 00007f10dacc0bb7
 RDX: 0000000000000000 RSI: 00007ffcbe628c60 RDI: 0000000000000003
 RBP: 000000005f41099c R08: 0000000000000001 R09: 0000000000000008
 R10: 00000000000005e9 R11: 0000000000000246 R12: 0000000000000000
 R13: 0000000000000000 R14: 00007ffcbe628d70 R15: 0000563a86c6e440
 Modules linked in:
 CR2: 0000000000000080

CC: David Ahern <dsahern@gmail.com>
Fixes: 430a049190de ("nexthop: Add support for nexthop groups")
Reported-by: syzbot+a61aa19b0c14c8770bd9@syzkaller.appspotmail.com
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/nexthop.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 563f71bcb2d7..c97069e79981 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -402,7 +402,7 @@ static int nh_check_attr_group(struct net *net, struct nlattr *tb[],
 	struct nexthop_grp *nhg;
 	unsigned int i, j;
 
-	if (len & (sizeof(struct nexthop_grp) - 1)) {
+	if (!len || len & (sizeof(struct nexthop_grp) - 1)) {
 		NL_SET_ERR_MSG(extack,
 			       "Invalid length for nexthop group attribute");
 		return -EINVAL;
@@ -1104,6 +1104,9 @@ static struct nexthop *nexthop_create_group(struct net *net,
 	struct nexthop *nh;
 	int i;
 
+	if (WARN_ON(!num_nh))
+		return ERR_PTR(-EINVAL);
+
 	nh = nexthop_alloc();
 	if (!nh)
 		return ERR_PTR(-ENOMEM);
-- 
2.26.2


From 2fd56c9952e6c0a1270da711c3691711b379d7f8 Mon Sep 17 00:00:00 2001
From: Necip Fazil Yildiran <necip@google.com>
Date: Mon, 17 Aug 2020 15:54:48 +0000
Subject: [PATCH 10/22] net: qrtr: fix usage of idr in port assignment to
 socket

[ Upstream commit 8dfddfb79653df7c38a9c8c4c034f242a36acee9 ]

Passing large uint32 sockaddr_qrtr.port numbers for port allocation
triggers a warning within idr_alloc() since the port number is cast
to int, and thus interpreted as a negative number. This leads to
the rejection of such valid port numbers in qrtr_port_assign() as
idr_alloc() fails.

To avoid the problem, switch to idr_alloc_u32() instead.

Fixes: bdabad3e363d ("net: Add Qualcomm IPC router")
Reported-by: syzbot+f31428628ef672716ea8@syzkaller.appspotmail.com
Signed-off-by: Necip Fazil Yildiran <necip@google.com>
Reviewed-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/qrtr/qrtr.c | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index 300a104b9a0f..85ab4559f057 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -692,23 +692,25 @@ static void qrtr_port_remove(struct qrtr_sock *ipc)
  */
 static int qrtr_port_assign(struct qrtr_sock *ipc, int *port)
 {
+	u32 min_port;
 	int rc;
 
 	mutex_lock(&qrtr_port_lock);
 	if (!*port) {
-		rc = idr_alloc(&qrtr_ports, ipc,
-			       QRTR_MIN_EPH_SOCKET, QRTR_MAX_EPH_SOCKET + 1,
-			       GFP_ATOMIC);
-		if (rc >= 0)
-			*port = rc;
+		min_port = QRTR_MIN_EPH_SOCKET;
+		rc = idr_alloc_u32(&qrtr_ports, ipc, &min_port, QRTR_MAX_EPH_SOCKET, GFP_ATOMIC);
+		if (!rc)
+			*port = min_port;
 	} else if (*port < QRTR_MIN_EPH_SOCKET && !capable(CAP_NET_ADMIN)) {
 		rc = -EACCES;
 	} else if (*port == QRTR_PORT_CTRL) {
-		rc = idr_alloc(&qrtr_ports, ipc, 0, 1, GFP_ATOMIC);
+		min_port = 0;
+		rc = idr_alloc_u32(&qrtr_ports, ipc, &min_port, 0, GFP_ATOMIC);
 	} else {
-		rc = idr_alloc(&qrtr_ports, ipc, *port, *port + 1, GFP_ATOMIC);
-		if (rc >= 0)
-			*port = rc;
+		min_port = *port;
+		rc = idr_alloc_u32(&qrtr_ports, ipc, &min_port, *port, GFP_ATOMIC);
+		if (!rc)
+			*port = min_port;
 	}
 	mutex_unlock(&qrtr_port_lock);
 
-- 
2.26.2


From 291cc18052623f686a5283b6f6208e3f5e2c721c Mon Sep 17 00:00:00 2001
From: Alaa Hleihel <alaa@mellanox.com>
Date: Wed, 19 Aug 2020 18:24:10 +0300
Subject: [PATCH 11/22] net/sched: act_ct: Fix skb double-free in
 tcf_ct_handle_fragments() error flow

[ Upstream commit eda814b97dfb8d9f4808eb2f65af9bd3705c4cae ]

tcf_ct_handle_fragments() shouldn't free the skb when ip_defrag() call
fails. Otherwise, we will cause a double-free bug.
In such cases, just return the error to the caller.

Fixes: b57dc7c13ea9 ("net/sched: Introduce action ct")
Signed-off-by: Alaa Hleihel <alaa@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ct.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index 417526d7741b..16bc5b0d1eaa 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -702,7 +702,7 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
 		err = ip_defrag(net, skb, user);
 		local_bh_enable();
 		if (err && err != -EINPROGRESS)
-			goto out_free;
+			return err;
 
 		if (!err) {
 			*defrag = true;
-- 
2.26.2


From 4e5ffcfe3392b8d93e599c661ad178a0f02083fa Mon Sep 17 00:00:00 2001
From: David Laight <David.Laight@ACULAB.COM>
Date: Wed, 19 Aug 2020 14:40:52 +0000
Subject: [PATCH 12/22] net: sctp: Fix negotiation of the number of data
 streams.

[ Upstream commit ab921f3cdbec01c68705a7ade8bec628d541fc2b ]

The number of output and input streams was never being reduced, eg when
processing received INIT or INIT_ACK chunks.
The effect is that DATA chunks can be sent with invalid stream ids
and then discarded by the remote system.

Fixes: 2075e50caf5ea ("sctp: convert to genradix")
Signed-off-by: David Laight <david.laight@aculab.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/stream.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index bda2536dd740..6dc95dcc0ff4 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -88,12 +88,13 @@ static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt,
 	int ret;
 
 	if (outcnt <= stream->outcnt)
-		return 0;
+		goto out;
 
 	ret = genradix_prealloc(&stream->out, outcnt, gfp);
 	if (ret)
 		return ret;
 
+out:
 	stream->outcnt = outcnt;
 	return 0;
 }
@@ -104,12 +105,13 @@ static int sctp_stream_alloc_in(struct sctp_stream *stream, __u16 incnt,
 	int ret;
 
 	if (incnt <= stream->incnt)
-		return 0;
+		goto out;
 
 	ret = genradix_prealloc(&stream->in, incnt, gfp);
 	if (ret)
 		return ret;
 
+out:
 	stream->incnt = incnt;
 	return 0;
 }
-- 
2.26.2


From c692f7f7888aaa9f78347b85632aed5444b3f132 Mon Sep 17 00:00:00 2001
From: Peilin Ye <yepeilin.cs@gmail.com>
Date: Thu, 20 Aug 2020 16:30:52 +0200
Subject: [PATCH 13/22] net/smc: Prevent kernel-infoleak in __smc_diag_dump()

[ Upstream commit ce51f63e63c52a4e1eee4dd040fb0ba0af3b43ab ]

__smc_diag_dump() is potentially copying uninitialized kernel stack memory
into socket buffers, since the compiler may leave a 4-byte hole near the
beginning of `struct smcd_diag_dmbinfo`. Fix it by initializing `dinfo`
with memset().

Fixes: 4b1b7d3b30a6 ("net/smc: add SMC-D diag support")
Suggested-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Peilin Ye <yepeilin.cs@gmail.com>
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/smc_diag.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c
index e1f64f4ba236..da9ba6d1679b 100644
--- a/net/smc/smc_diag.c
+++ b/net/smc/smc_diag.c
@@ -170,13 +170,15 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb,
 	    (req->diag_ext & (1 << (SMC_DIAG_DMBINFO - 1))) &&
 	    !list_empty(&smc->conn.lgr->list)) {
 		struct smc_connection *conn = &smc->conn;
-		struct smcd_diag_dmbinfo dinfo = {
-			.linkid = *((u32 *)conn->lgr->id),
-			.peer_gid = conn->lgr->peer_gid,
-			.my_gid = conn->lgr->smcd->local_gid,
-			.token = conn->rmb_desc->token,
-			.peer_token = conn->peer_token
-		};
+		struct smcd_diag_dmbinfo dinfo;
+
+		memset(&dinfo, 0, sizeof(dinfo));
+
+		dinfo.linkid = *((u32 *)conn->lgr->id);
+		dinfo.peer_gid = conn->lgr->peer_gid;
+		dinfo.my_gid = conn->lgr->smcd->local_gid;
+		dinfo.token = conn->rmb_desc->token;
+		dinfo.peer_token = conn->peer_token;
 
 		if (nla_put(skb, SMC_DIAG_DMBINFO, sizeof(dinfo), &dinfo) < 0)
 			goto errout;
-- 
2.26.2


From b882f762c155201803dd77c6dcf126d635f556c5 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Sat, 15 Aug 2020 09:29:30 +0200
Subject: [PATCH 14/22] net: xdp: pull ethernet header off packet after
 computing skb->protocol

[ Upstream commit f8414a8d886b613b90d9fdf7cda6feea313b1069 ]

When an XDP program changes the ethernet header protocol field,
eth_type_trans is used to recalculate skb->protocol. In order for
eth_type_trans to work correctly, the ethernet header must actually be
part of the skb data segment, so the code first pushes that onto the
head of the skb. However, it subsequently forgets to pull it back off,
making the behavior of the passed-on packet inconsistent between the
protocol modifying case and the static protocol case. This patch fixes
the issue by simply pulling the ethernet header back off of the skb
head.

Fixes: 297249569932 ("net: fix generic XDP to handle if eth header was mangled")
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/core/dev.c b/net/core/dev.c
index c1c2688a955c..c35cc99ac7dd 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4586,6 +4586,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 	    (orig_bcast != is_multicast_ether_addr_64bits(eth->h_dest))) {
 		__skb_push(skb, ETH_HLEN);
 		skb->protocol = eth_type_trans(skb, skb->dev);
+		__skb_pull(skb, ETH_HLEN);
 	}
 
 	switch (act) {
-- 
2.26.2


From 80c5f36e8e79ff44cf0a9ef2dde10659e5a3a9a6 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 20 Aug 2020 15:34:47 +0800
Subject: [PATCH 15/22] tipc: call rcu_read_lock() in tipc_aead_encrypt_done()

[ Upstream commit f6db9096416209474090d64d8284e7c16c3d8873 ]

b->media->send_msg() requires rcu_read_lock(), as we can see
elsewhere in tipc,  tipc_bearer_xmit, tipc_bearer_xmit_skb
and tipc_bearer_bc_xmit().

Syzbot has reported this issue as:

  net/tipc/bearer.c:466 suspicious rcu_dereference_check() usage!
  Workqueue: cryptd cryptd_queue_worker
  Call Trace:
   tipc_l2_send_msg+0x354/0x420 net/tipc/bearer.c:466
   tipc_aead_encrypt_done+0x204/0x3a0 net/tipc/crypto.c:761
   cryptd_aead_crypt+0xe8/0x1d0 crypto/cryptd.c:739
   cryptd_queue_worker+0x118/0x1b0 crypto/cryptd.c:181
   process_one_work+0x94c/0x1670 kernel/workqueue.c:2269
   worker_thread+0x64c/0x1120 kernel/workqueue.c:2415
   kthread+0x3b5/0x4a0 kernel/kthread.c:291
   ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:293

So fix it by calling rcu_read_lock() in tipc_aead_encrypt_done()
for b->media->send_msg().

Fixes: fc1b6d6de220 ("tipc: introduce TIPC encryption & authentication")
Reported-by: syzbot+47bbc6b678d317cccbe0@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/crypto.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c
index 8c47ded2edb6..b214b898d11a 100644
--- a/net/tipc/crypto.c
+++ b/net/tipc/crypto.c
@@ -757,10 +757,12 @@ static void tipc_aead_encrypt_done(struct crypto_async_request *base, int err)
 	switch (err) {
 	case 0:
 		this_cpu_inc(tx->stats->stat[STAT_ASYNC_OK]);
+		rcu_read_lock();
 		if (likely(test_bit(0, &b->up)))
 			b->media->send_msg(net, skb, b, &tx_ctx->dst);
 		else
 			kfree_skb(skb);
+		rcu_read_unlock();
 		break;
 	case -EINPROGRESS:
 		return;
-- 
2.26.2


From ec076340b895b4a1e17327a290b09e564f26bee1 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sat, 15 Aug 2020 16:29:15 -0700
Subject: [PATCH 16/22] tipc: fix uninit skb->data in tipc_nl_compat_dumpit()

[ Upstream commit 47733f9daf4fe4f7e0eb9e273f21ad3a19130487 ]

__tipc_nl_compat_dumpit() has two callers, and it expects them to
pass a valid nlmsghdr via arg->data. This header is artificial and
crafted just for __tipc_nl_compat_dumpit().

tipc_nl_compat_publ_dump() does so by putting a genlmsghdr as well
as some nested attribute, TIPC_NLA_SOCK. But the other caller
tipc_nl_compat_dumpit() does not, this leaves arg->data uninitialized
on this call path.

Fix this by just adding a similar nlmsghdr without any payload in
tipc_nl_compat_dumpit().

This bug exists since day 1, but the recent commit 6ea67769ff33
("net: tipc: prepare attrs in __tipc_nl_compat_dumpit()") makes it
easier to appear.

Reported-and-tested-by: syzbot+0e7181deafa7e0b79923@syzkaller.appspotmail.com
Fixes: d0796d1ef63d ("tipc: convert legacy nl bearer dump to nl compat")
Cc: Jon Maloy <jmaloy@redhat.com>
Cc: Ying Xue <ying.xue@windriver.com>
Cc: Richard Alpe <richard.alpe@ericsson.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/netlink_compat.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 217516357ef2..90e3c70a91ad 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -275,8 +275,9 @@ static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd,
 static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd,
 				 struct tipc_nl_compat_msg *msg)
 {
-	int err;
+	struct nlmsghdr *nlh;
 	struct sk_buff *arg;
+	int err;
 
 	if (msg->req_type && (!msg->req_size ||
 			      !TLV_CHECK_TYPE(msg->req, msg->req_type)))
@@ -305,6 +306,15 @@ static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd,
 		return -ENOMEM;
 	}
 
+	nlh = nlmsg_put(arg, 0, 0, tipc_genl_family.id, 0, NLM_F_MULTI);
+	if (!nlh) {
+		kfree_skb(arg);
+		kfree_skb(msg->rep);
+		msg->rep = NULL;
+		return -EMSGSIZE;
+	}
+	nlmsg_end(arg, nlh);
+
 	err = __tipc_nl_compat_dumpit(cmd, msg, arg);
 	if (err) {
 		kfree_skb(msg->rep);
-- 
2.26.2


From 9e8dfaf1e45511adc0cfc34288095c8cddaf6910 Mon Sep 17 00:00:00 2001
From: Shay Agroskin <shayagr@amazon.com>
Date: Wed, 19 Aug 2020 20:28:36 +0300
Subject: [PATCH 17/22] net: ena: Prevent reset after device destruction

[ Upstream commit 63d4a4c145cca2e84dc6e62d2ef5cb990c9723c2 ]

The reset work is scheduled by the timer routine whenever it
detects that a device reset is required (e.g. when a keep_alive signal
is missing).
When releasing device resources in ena_destroy_device() the driver
cancels the scheduling of the timer routine without destroying the reset
work explicitly.

This creates the following bug:
    The driver is suspended and the ena_suspend() function is called
	-> This function calls ena_destroy_device() to free the net device
	   resources
	    -> The driver waits for the timer routine to finish
	    its execution and then cancels it, thus preventing from it
	    to be called again.

    If, in its final execution, the timer routine schedules a reset,
    the reset routine might be called afterwards,and a redundant call to
    ena_restore_device() would be made.

By changing the reset routine we allow it to read the device's state
accurately.
This is achieved by checking whether ENA_FLAG_TRIGGER_RESET flag is set
before resetting the device and making both the destruction function and
the flag check are under rtnl lock.
The ENA_FLAG_TRIGGER_RESET is cleared at the end of the destruction
routine. Also surround the flag check with 'likely' because
we expect that the reset routine would be called only when
ENA_FLAG_TRIGGER_RESET flag is set.

The destruction of the timer and reset services in __ena_shutoff() have to
stay, even though the timer routine is destroyed in ena_destroy_device().
This is to avoid a case in which the reset routine is scheduled after
free_netdev() in __ena_shutoff(), which would create an access to freed
memory in adapter->flags.

Fixes: 8c5c7abdeb2d ("net: ena: add power management ops to the ENA driver")
Signed-off-by: Shay Agroskin <shayagr@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 15ce93be05ea..dc3fda459924 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -3508,16 +3508,14 @@ static void ena_fw_reset_device(struct work_struct *work)
 {
 	struct ena_adapter *adapter =
 		container_of(work, struct ena_adapter, reset_task);
-	struct pci_dev *pdev = adapter->pdev;
 
-	if (unlikely(!test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))) {
-		dev_err(&pdev->dev,
-			"device reset schedule while reset bit is off\n");
-		return;
-	}
 	rtnl_lock();
-	ena_destroy_device(adapter, false);
-	ena_restore_device(adapter);
+
+	if (likely(test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))) {
+		ena_destroy_device(adapter, false);
+		ena_restore_device(adapter);
+	}
+
 	rtnl_unlock();
 }
 
@@ -4351,8 +4349,11 @@ static void __ena_shutoff(struct pci_dev *pdev, bool shutdown)
 		netdev->rx_cpu_rmap = NULL;
 	}
 #endif /* CONFIG_RFS_ACCEL */
-	del_timer_sync(&adapter->timer_service);
 
+	/* Make sure timer and reset routine won't be called after
+	 * freeing device resources.
+	 */
+	del_timer_sync(&adapter->timer_service);
 	cancel_work_sync(&adapter->reset_task);
 
 	rtnl_lock(); /* lock released inside the below if-else block */
-- 
2.26.2


From c6127087a89d6c84329a293c99e87b9147016f7a Mon Sep 17 00:00:00 2001
From: Shay Agroskin <shayagr@amazon.com>
Date: Wed, 19 Aug 2020 20:28:37 +0300
Subject: [PATCH 18/22] net: ena: Change WARN_ON expression in
 ena_del_napi_in_range()

[ Upstream commit 8b147f6f3e7de4e51113e3e9ec44aa2debc02c58 ]

The ena_del_napi_in_range() function unregisters the napi handler for
rings in a given range.
This function had the following WARN_ON macro:

    WARN_ON(ENA_IS_XDP_INDEX(adapter, i) &&
	    adapter->ena_napi[i].xdp_ring);

This macro prints the call stack if the expression inside of it is
true [1], but the expression inside of it is the wanted situation.
The expression checks whether the ring has an XDP queue and its index
corresponds to a XDP one.

This patch changes the expression to
    !ENA_IS_XDP_INDEX(adapter, i) && adapter->ena_napi[i].xdp_ring
which indicates an unwanted situation.

Also, change the structure of the function. The napi handler is
unregistered for all rings, and so there's no need to check whether the
index is an XDP index or not. By removing this check the code becomes
much more readable.

Fixes: 548c4940b9f1 ("net: ena: Implement XDP_TX action")
Signed-off-by: Shay Agroskin <shayagr@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index dc3fda459924..c501a4edc34d 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -2166,13 +2166,10 @@ static void ena_del_napi_in_range(struct ena_adapter *adapter,
 	int i;
 
 	for (i = first_index; i < first_index + count; i++) {
-		/* Check if napi was initialized before */
-		if (!ENA_IS_XDP_INDEX(adapter, i) ||
-		    adapter->ena_napi[i].xdp_ring)
-			netif_napi_del(&adapter->ena_napi[i].napi);
-		else
-			WARN_ON(ENA_IS_XDP_INDEX(adapter, i) &&
-				adapter->ena_napi[i].xdp_ring);
+		netif_napi_del(&adapter->ena_napi[i].napi);
+
+		WARN_ON(!ENA_IS_XDP_INDEX(adapter, i) &&
+			adapter->ena_napi[i].xdp_ring);
 	}
 }
 
-- 
2.26.2


From 5a41ae6634258e9bcfdf0e3f5d5cfe48e87b10a7 Mon Sep 17 00:00:00 2001
From: Shay Agroskin <shayagr@amazon.com>
Date: Wed, 19 Aug 2020 20:28:38 +0300
Subject: [PATCH 19/22] net: ena: Make missed_tx stat incremental

[ Upstream commit ccd143e5150f24b9ba15145c7221b61dd9e41021 ]

Most statistics in ena driver are incremented, meaning that a stat's
value is a sum of all increases done to it since driver/queue
initialization.

This patch makes all statistics this way, effectively making missed_tx
statistic incremental.
Also added a comment regarding rx_drops and tx_drops to make it
clearer how these counters are calculated.

Fixes: 11095fdb712b ("net: ena: add statistics for missed tx packets")
Signed-off-by: Shay Agroskin <shayagr@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index c501a4edc34d..51b9b49a295e 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -3594,7 +3594,7 @@ static int check_missing_comp_in_tx_queue(struct ena_adapter *adapter,
 	}
 
 	u64_stats_update_begin(&tx_ring->syncp);
-	tx_ring->tx_stats.missed_tx = missed_tx;
+	tx_ring->tx_stats.missed_tx += missed_tx;
 	u64_stats_update_end(&tx_ring->syncp);
 
 	return rc;
@@ -4519,6 +4519,9 @@ static void ena_keep_alive_wd(void *adapter_data,
 	rx_drops = ((u64)desc->rx_drops_high << 32) | desc->rx_drops_low;
 
 	u64_stats_update_begin(&adapter->syncp);
+	/* These stats are accumulated by the device, so the counters indicate
+	 * all drops since last reset.
+	 */
 	adapter->dev_stats.rx_drops = rx_drops;
 	u64_stats_update_end(&adapter->syncp);
 }
-- 
2.26.2


From 8d4ec7380d8c8e8b566d5551a3d6c35032e81c96 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Mon, 17 Aug 2020 16:34:05 +0300
Subject: [PATCH 20/22] ethtool: Fix preserving of wanted feature bits in
 netlink interface

[ Upstream commit 840110a4eae190dcbb9907d68216d5d1d9f25839 ]

Currently, ethtool-netlink calculates new wanted bits as:
(req_wanted & req_mask) | (old_active & ~req_mask)

It completely discards the old wanted bits, so they are forgotten with
the next ethtool command. Sample steps to reproduce:

1. ethtool -k eth0
   tx-tcp-segmentation: on # TSO is on from the beginning
2. ethtool -K eth0 tx off
   tx-tcp-segmentation: off [not requested]
3. ethtool -k eth0
   tx-tcp-segmentation: off [requested on]
4. ethtool -K eth0 rx off # Some change unrelated to TSO
5. ethtool -k eth0
   tx-tcp-segmentation: off # "Wanted on" is forgotten

This commit fixes it by changing the formula to:
(req_wanted & req_mask) | (old_wanted & ~req_mask),
where old_active was replaced by old_wanted to account for the wanted
bits.

The shortcut condition for the case where nothing was changed now
compares wanted bitmasks, instead of wanted to active.

Fixes: 0980bfcd6954 ("ethtool: set netdev features with FEATURES_SET request")
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ethtool/features.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/net/ethtool/features.c b/net/ethtool/features.c
index 4e632dc987d8..ec196f0fddc9 100644
--- a/net/ethtool/features.c
+++ b/net/ethtool/features.c
@@ -224,7 +224,9 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info)
 	DECLARE_BITMAP(wanted_diff_mask, NETDEV_FEATURE_COUNT);
 	DECLARE_BITMAP(active_diff_mask, NETDEV_FEATURE_COUNT);
 	DECLARE_BITMAP(old_active, NETDEV_FEATURE_COUNT);
+	DECLARE_BITMAP(old_wanted, NETDEV_FEATURE_COUNT);
 	DECLARE_BITMAP(new_active, NETDEV_FEATURE_COUNT);
+	DECLARE_BITMAP(new_wanted, NETDEV_FEATURE_COUNT);
 	DECLARE_BITMAP(req_wanted, NETDEV_FEATURE_COUNT);
 	DECLARE_BITMAP(req_mask, NETDEV_FEATURE_COUNT);
 	struct nlattr *tb[ETHTOOL_A_FEATURES_MAX + 1];
@@ -250,6 +252,7 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info)
 
 	rtnl_lock();
 	ethnl_features_to_bitmap(old_active, dev->features);
+	ethnl_features_to_bitmap(old_wanted, dev->wanted_features);
 	ret = ethnl_parse_bitset(req_wanted, req_mask, NETDEV_FEATURE_COUNT,
 				 tb[ETHTOOL_A_FEATURES_WANTED],
 				 netdev_features_strings, info->extack);
@@ -261,11 +264,11 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info)
 		goto out_rtnl;
 	}
 
-	/* set req_wanted bits not in req_mask from old_active */
+	/* set req_wanted bits not in req_mask from old_wanted */
 	bitmap_and(req_wanted, req_wanted, req_mask, NETDEV_FEATURE_COUNT);
-	bitmap_andnot(new_active, old_active, req_mask, NETDEV_FEATURE_COUNT);
-	bitmap_or(req_wanted, new_active, req_wanted, NETDEV_FEATURE_COUNT);
-	if (bitmap_equal(req_wanted, old_active, NETDEV_FEATURE_COUNT)) {
+	bitmap_andnot(new_wanted, old_wanted, req_mask, NETDEV_FEATURE_COUNT);
+	bitmap_or(req_wanted, new_wanted, req_wanted, NETDEV_FEATURE_COUNT);
+	if (bitmap_equal(req_wanted, old_wanted, NETDEV_FEATURE_COUNT)) {
 		ret = 0;
 		goto out_rtnl;
 	}
-- 
2.26.2


From 2591b236c1dc5d75826f5735ac69101aec956160 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Mon, 17 Aug 2020 16:34:06 +0300
Subject: [PATCH 21/22] ethtool: Account for hw_features in netlink interface

[ Upstream commit 2847bfed888fbb8bf4c8e8067fd6127538c2c700 ]

ethtool-netlink ignores dev->hw_features and may confuse the drivers by
asking them to enable features not in the hw_features bitmask. For
example:

1. ethtool -k eth0
   tls-hw-tx-offload: off [fixed]
2. ethtool -K eth0 tls-hw-tx-offload on
   tls-hw-tx-offload: on
3. ethtool -k eth0
   tls-hw-tx-offload: on [fixed]

Fitler out dev->hw_features from req_wanted to fix it and to resemble
the legacy ethtool behavior.

Fixes: 0980bfcd6954 ("ethtool: set netdev features with FEATURES_SET request")
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ethtool/features.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ethtool/features.c b/net/ethtool/features.c
index ec196f0fddc9..6b288bfd7678 100644
--- a/net/ethtool/features.c
+++ b/net/ethtool/features.c
@@ -273,7 +273,8 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info)
 		goto out_rtnl;
 	}
 
-	dev->wanted_features = ethnl_bitmap_to_features(req_wanted);
+	dev->wanted_features &= ~dev->hw_features;
+	dev->wanted_features |= ethnl_bitmap_to_features(req_wanted) & dev->hw_features;
 	__netdev_update_features(dev);
 	ethnl_features_to_bitmap(new_active, dev->features);
 	mod = !bitmap_equal(old_active, new_active, NETDEV_FEATURE_COUNT);
-- 
2.26.2


From 900f3dd70dc24d6907c973a451c67f90cfdd45de Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Mon, 17 Aug 2020 16:34:07 +0300
Subject: [PATCH 22/22] ethtool: Don't omit the netlink reply if no features
 were changed

[ Upstream commit f01204ec8be7ea5e8f0230a7d4200e338d563bde ]

The legacy ethtool userspace tool shows an error when no features could
be changed. It's useful to have a netlink reply to be able to show this
error when __netdev_update_features wasn't called, for example:

1. ethtool -k eth0
   large-receive-offload: off
2. ethtool -K eth0 rx-fcs on
3. ethtool -K eth0 lro on
   Could not change any device features
   rx-lro: off [requested on]
4. ethtool -K eth0 lro on
   # The output should be the same, but without this patch the kernel
   # doesn't send the reply, and ethtool is unable to detect the error.

This commit makes ethtool-netlink always return a reply when requested,
and it still avoids unnecessary calls to __netdev_update_features if the
wanted features haven't changed.

Fixes: 0980bfcd6954 ("ethtool: set netdev features with FEATURES_SET request")
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ethtool/features.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/net/ethtool/features.c b/net/ethtool/features.c
index 6b288bfd7678..495635f152ba 100644
--- a/net/ethtool/features.c
+++ b/net/ethtool/features.c
@@ -268,14 +268,11 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info)
 	bitmap_and(req_wanted, req_wanted, req_mask, NETDEV_FEATURE_COUNT);
 	bitmap_andnot(new_wanted, old_wanted, req_mask, NETDEV_FEATURE_COUNT);
 	bitmap_or(req_wanted, new_wanted, req_wanted, NETDEV_FEATURE_COUNT);
-	if (bitmap_equal(req_wanted, old_wanted, NETDEV_FEATURE_COUNT)) {
-		ret = 0;
-		goto out_rtnl;
+	if (!bitmap_equal(req_wanted, old_wanted, NETDEV_FEATURE_COUNT)) {
+		dev->wanted_features &= ~dev->hw_features;
+		dev->wanted_features |= ethnl_bitmap_to_features(req_wanted) & dev->hw_features;
+		__netdev_update_features(dev);
 	}
-
-	dev->wanted_features &= ~dev->hw_features;
-	dev->wanted_features |= ethnl_bitmap_to_features(req_wanted) & dev->hw_features;
-	__netdev_update_features(dev);
 	ethnl_features_to_bitmap(new_active, dev->features);
 	mod = !bitmap_equal(old_active, new_active, NETDEV_FEATURE_COUNT);
 
-- 
2.26.2


[-- Attachment #3: net_58.mbox --]
[-- Type: Application/Octet-Stream, Size: 51278 bytes --]

From 1f8a52d4784d3e65788eb7a7c3413597efdb35c9 Mon Sep 17 00:00:00 2001
From: Jiri Wiesner <jwiesner@suse.com>
Date: Sun, 16 Aug 2020 20:52:44 +0200
Subject: [PATCH 01/24] bonding: fix active-backup failover for current ARP
 slave

[ Upstream commit 0410d07190961ac526f05085765a8d04d926545b ]

When the ARP monitor is used for link detection, ARP replies are
validated for all slaves (arp_validate=3) and fail_over_mac is set to
active, two slaves of an active-backup bond may get stuck in a state
where both of them are active and pass packets that they receive to
the bond. This state makes IPv6 duplicate address detection fail. The
state is reached thus:
1. The current active slave goes down because the ARP target
   is not reachable.
2. The current ARP slave is chosen and made active.
3. A new slave is enslaved. This new slave becomes the current active
   slave and can reach the ARP target.
As a result, the current ARP slave stays active after the enslave
action has finished and the log is littered with "PROBE BAD" messages:
> bond0: PROBE: c_arp ens10 && cas ens11 BAD
The workaround is to remove the slave with "going back" status from
the bond and re-enslave it. This issue was encountered when DPDK PMD
interfaces were being enslaved to an active-backup bond.

I would be possible to fix the issue in bond_enslave() or
bond_change_active_slave() but the ARP monitor was fixed instead to
keep most of the actions changing the current ARP slave in the ARP
monitor code. The current ARP slave is set as inactive and backup
during the commit phase. A new state, BOND_LINK_FAIL, has been
introduced for slaves in the context of the ARP monitor. This allows
administrators to see how slaves are rotated for sending ARP requests
and attempts are made to find a new active slave.

Fixes: b2220cad583c9 ("bonding: refactor ARP active-backup monitor")
Signed-off-by: Jiri Wiesner <jwiesner@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index f88cb097b022..89849bacc01f 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2824,6 +2824,9 @@ static int bond_ab_arp_inspect(struct bonding *bond)
 			if (bond_time_in_interval(bond, last_rx, 1)) {
 				bond_propose_link_state(slave, BOND_LINK_UP);
 				commit++;
+			} else if (slave->link == BOND_LINK_BACK) {
+				bond_propose_link_state(slave, BOND_LINK_FAIL);
+				commit++;
 			}
 			continue;
 		}
@@ -2932,6 +2935,19 @@ static void bond_ab_arp_commit(struct bonding *bond)
 
 			continue;
 
+		case BOND_LINK_FAIL:
+			bond_set_slave_link_state(slave, BOND_LINK_FAIL,
+						  BOND_SLAVE_NOTIFY_NOW);
+			bond_set_slave_inactive_flags(slave,
+						      BOND_SLAVE_NOTIFY_NOW);
+
+			/* A slave has just been enslaved and has become
+			 * the current active slave.
+			 */
+			if (rtnl_dereference(bond->curr_active_slave))
+				RCU_INIT_POINTER(bond->current_arp_slave, NULL);
+			continue;
+
 		default:
 			slave_err(bond->dev, slave->dev,
 				  "impossible: link_new_state %d on slave\n",
@@ -2982,8 +2998,6 @@ static bool bond_ab_arp_probe(struct bonding *bond)
 			return should_notify_rtnl;
 	}
 
-	bond_set_slave_inactive_flags(curr_arp_slave, BOND_SLAVE_NOTIFY_LATER);
-
 	bond_for_each_slave_rcu(bond, slave, iter) {
 		if (!found && !before && bond_slave_is_up(slave))
 			before = slave;
-- 
2.26.2


From e38acf5ba47d0b5a333448f43602fbe3d0797cbf Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Fri, 14 Aug 2020 20:05:58 -0700
Subject: [PATCH 02/24] bonding: fix a potential double-unregister

[ Upstream commit 832707021666411d04795c564a4adea5d6b94f17 ]

When we tear down a network namespace, we unregister all
the netdevices within it. So we may queue a slave device
and a bonding device together in the same unregister queue.

If the only slave device is non-ethernet, it would
automatically unregister the bonding device as well. Thus,
we may end up unregistering the bonding device twice.

Workaround this special case by checking reg_state.

Fixes: 9b5e383c11b0 ("net: Introduce unregister_netdevice_many()")
Reported-by: syzbot+af23e7f3e0a7e10c8b67@syzkaller.appspotmail.com
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Andy Gospodarek <andy@greyhouse.net>
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 89849bacc01f..b634cc374029 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2084,7 +2084,8 @@ static int bond_release_and_destroy(struct net_device *bond_dev,
 	int ret;
 
 	ret = __bond_release_one(bond_dev, slave_dev, false, true);
-	if (ret == 0 && !bond_has_slaves(bond)) {
+	if (ret == 0 && !bond_has_slaves(bond) &&
+	    bond_dev->reg_state != NETREG_UNREGISTERING) {
 		bond_dev->priv_flags |= IFF_DISABLE_NETPOLL;
 		netdev_info(bond_dev, "Destroying bond\n");
 		bond_remove_proc_entry(bond);
-- 
2.26.2


From 888abb7f3795e849744c174ab560328a1d5c1dc0 Mon Sep 17 00:00:00 2001
From: Jarod Wilson <jarod@redhat.com>
Date: Thu, 13 Aug 2020 10:09:00 -0400
Subject: [PATCH 03/24] bonding: show saner speed for broadcast mode

[ Upstream commit 4ca0d9ac3fd8f9f90b72a15d8da2aca3ffb58418 ]

Broadcast mode bonds transmit a copy of all traffic simultaneously out of
all interfaces, so the "speed" of the bond isn't really the aggregate of
all interfaces, but rather, the speed of the slowest active interface.

Also, the type of the speed field is u32, not unsigned long, so adjust
that accordingly, as required to make min() function here without
complaining about mismatching types.

Fixes: bb5b052f751b ("bond: add support to read speed and duplex via ethtool")
CC: Jay Vosburgh <j.vosburgh@gmail.com>
CC: Veaceslav Falico <vfalico@gmail.com>
CC: Andy Gospodarek <andy@greyhouse.net>
CC: "David S. Miller" <davem@davemloft.net>
CC: netdev@vger.kernel.org
Acked-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 21 ++++++++++++++++++---
 1 file changed, 18 insertions(+), 3 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index b634cc374029..500aa3e19a4c 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -4446,13 +4446,23 @@ static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	return ret;
 }
 
+static u32 bond_mode_bcast_speed(struct slave *slave, u32 speed)
+{
+	if (speed == 0 || speed == SPEED_UNKNOWN)
+		speed = slave->speed;
+	else
+		speed = min(speed, slave->speed);
+
+	return speed;
+}
+
 static int bond_ethtool_get_link_ksettings(struct net_device *bond_dev,
 					   struct ethtool_link_ksettings *cmd)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
-	unsigned long speed = 0;
 	struct list_head *iter;
 	struct slave *slave;
+	u32 speed = 0;
 
 	cmd->base.duplex = DUPLEX_UNKNOWN;
 	cmd->base.port = PORT_OTHER;
@@ -4464,8 +4474,13 @@ static int bond_ethtool_get_link_ksettings(struct net_device *bond_dev,
 	 */
 	bond_for_each_slave(bond, slave, iter) {
 		if (bond_slave_can_tx(slave)) {
-			if (slave->speed != SPEED_UNKNOWN)
-				speed += slave->speed;
+			if (slave->speed != SPEED_UNKNOWN) {
+				if (BOND_MODE(bond) == BOND_MODE_BROADCAST)
+					speed = bond_mode_bcast_speed(slave,
+								      speed);
+				else
+					speed += slave->speed;
+			}
 			if (cmd->base.duplex == DUPLEX_UNKNOWN &&
 			    slave->duplex != DUPLEX_UNKNOWN)
 				cmd->base.duplex = slave->duplex;
-- 
2.26.2


From 90ba487ab87cea382989e69318385b7e6af37716 Mon Sep 17 00:00:00 2001
From: Mark Tomlinson <mark.tomlinson@alliedtelesis.co.nz>
Date: Wed, 19 Aug 2020 13:53:58 +1200
Subject: [PATCH 04/24] gre6: Fix reception with IP6_TNL_F_RCV_DSCP_COPY

[ Upstream commit 272502fcb7cda01ab07fc2fcff82d1d2f73d43cc ]

When receiving an IPv4 packet inside an IPv6 GRE packet, and the
IP6_TNL_F_RCV_DSCP_COPY flag is set on the tunnel, the IPv4 header would
get corrupted. This is due to the common ip6_tnl_rcv() function assuming
that the inner header is always IPv6. This patch checks the tunnel
protocol for IPv4 inner packets, but still defaults to IPv6.

Fixes: 308edfdf1563 ("gre6: Cleanup GREv6 receive path, call common GRE functions")
Signed-off-by: Mark Tomlinson <mark.tomlinson@alliedtelesis.co.nz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index a18c378ca5f4..d8f0102cec94 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -913,7 +913,15 @@ int ip6_tnl_rcv(struct ip6_tnl *t, struct sk_buff *skb,
 		struct metadata_dst *tun_dst,
 		bool log_ecn_err)
 {
-	return __ip6_tnl_rcv(t, skb, tpi, tun_dst, ip6ip6_dscp_ecn_decapsulate,
+	int (*dscp_ecn_decapsulate)(const struct ip6_tnl *t,
+				    const struct ipv6hdr *ipv6h,
+				    struct sk_buff *skb);
+
+	dscp_ecn_decapsulate = ip6ip6_dscp_ecn_decapsulate;
+	if (tpi->proto == htons(ETH_P_IP))
+		dscp_ecn_decapsulate = ip4ip6_dscp_ecn_decapsulate;
+
+	return __ip6_tnl_rcv(t, skb, tpi, tun_dst, dscp_ecn_decapsulate,
 			     log_ecn_err);
 }
 EXPORT_SYMBOL(ip6_tnl_rcv);
-- 
2.26.2


From e9ec7900aec38339076dd647864b6b2b5b76043e Mon Sep 17 00:00:00 2001
From: Mahesh Bandewar <maheshb@google.com>
Date: Fri, 14 Aug 2020 22:53:24 -0700
Subject: [PATCH 05/24] ipvlan: fix device features

[ Upstream commit d0f5c7076e01fef6fcb86988d9508bf3ce258bd4 ]

Processing NETDEV_FEAT_CHANGE causes IPvlan links to lose
NETIF_F_LLTX feature because of the incorrect handling of
features in ipvlan_fix_features().

--before--
lpaa10:~# ethtool -k ipvl0 | grep tx-lockless
tx-lockless: on [fixed]
lpaa10:~# ethtool -K ipvl0 tso off
Cannot change tcp-segmentation-offload
Actual changes:
vlan-challenged: off [fixed]
tx-lockless: off [fixed]
lpaa10:~# ethtool -k ipvl0 | grep tx-lockless
tx-lockless: off [fixed]
lpaa10:~#

--after--
lpaa10:~# ethtool -k ipvl0 | grep tx-lockless
tx-lockless: on [fixed]
lpaa10:~# ethtool -K ipvl0 tso off
Cannot change tcp-segmentation-offload
Could not change any device features
lpaa10:~# ethtool -k ipvl0 | grep tx-lockless
tx-lockless: on [fixed]
lpaa10:~#

Fixes: 2ad7bf363841 ("ipvlan: Initial check-in of the IPVLAN driver.")
Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ipvlan/ipvlan_main.c | 27 ++++++++++++++++++++++-----
 1 file changed, 22 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 15e87c097b0b..5bca94c99006 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -106,12 +106,21 @@ static void ipvlan_port_destroy(struct net_device *dev)
 	kfree(port);
 }
 
+#define IPVLAN_ALWAYS_ON_OFLOADS \
+	(NETIF_F_SG | NETIF_F_HW_CSUM | \
+	 NETIF_F_GSO_ROBUST | NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL)
+
+#define IPVLAN_ALWAYS_ON \
+	(IPVLAN_ALWAYS_ON_OFLOADS | NETIF_F_LLTX | NETIF_F_VLAN_CHALLENGED)
+
 #define IPVLAN_FEATURES \
-	(NETIF_F_SG | NETIF_F_CSUM_MASK | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \
+	(NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \
 	 NETIF_F_GSO | NETIF_F_ALL_TSO | NETIF_F_GSO_ROBUST | \
 	 NETIF_F_GRO | NETIF_F_RXCSUM | \
 	 NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER)
 
+	/* NETIF_F_GSO_ENCAP_ALL NETIF_F_GSO_SOFTWARE Newly added */
+
 #define IPVLAN_STATE_MASK \
 	((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT))
 
@@ -125,7 +134,9 @@ static int ipvlan_init(struct net_device *dev)
 	dev->state = (dev->state & ~IPVLAN_STATE_MASK) |
 		     (phy_dev->state & IPVLAN_STATE_MASK);
 	dev->features = phy_dev->features & IPVLAN_FEATURES;
-	dev->features |= NETIF_F_LLTX | NETIF_F_VLAN_CHALLENGED;
+	dev->features |= IPVLAN_ALWAYS_ON;
+	dev->vlan_features = phy_dev->vlan_features & IPVLAN_FEATURES;
+	dev->vlan_features |= IPVLAN_ALWAYS_ON_OFLOADS;
 	dev->hw_enc_features |= dev->features;
 	dev->gso_max_size = phy_dev->gso_max_size;
 	dev->gso_max_segs = phy_dev->gso_max_segs;
@@ -227,7 +238,14 @@ static netdev_features_t ipvlan_fix_features(struct net_device *dev,
 {
 	struct ipvl_dev *ipvlan = netdev_priv(dev);
 
-	return features & (ipvlan->sfeatures | ~IPVLAN_FEATURES);
+	features |= NETIF_F_ALL_FOR_ALL;
+	features &= (ipvlan->sfeatures | ~IPVLAN_FEATURES);
+	features = netdev_increment_features(ipvlan->phy_dev->features,
+					     features, features);
+	features |= IPVLAN_ALWAYS_ON;
+	features &= (IPVLAN_FEATURES | IPVLAN_ALWAYS_ON);
+
+	return features;
 }
 
 static void ipvlan_change_rx_flags(struct net_device *dev, int change)
@@ -734,10 +752,9 @@ static int ipvlan_device_event(struct notifier_block *unused,
 
 	case NETDEV_FEAT_CHANGE:
 		list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
-			ipvlan->dev->features = dev->features & IPVLAN_FEATURES;
 			ipvlan->dev->gso_max_size = dev->gso_max_size;
 			ipvlan->dev->gso_max_segs = dev->gso_max_segs;
-			netdev_features_change(ipvlan->dev);
+			netdev_update_features(ipvlan->dev);
 		}
 		break;
 
-- 
2.26.2


From 47641782dbb1ef45d22a50922d910720be1c48b3 Mon Sep 17 00:00:00 2001
From: Tom Rix <trix@redhat.com>
Date: Fri, 21 Aug 2020 06:56:00 -0700
Subject: [PATCH 06/24] net: dsa: b53: check for timeout

[ Upstream commit 774d977abfd024e6f73484544b9abe5a5cd62de7 ]

clang static analysis reports this problem

b53_common.c:1583:13: warning: The left expression of the compound
  assignment is an uninitialized value. The computed value will
  also be garbage
        ent.port &= ~BIT(port);
        ~~~~~~~~ ^

ent is set by a successful call to b53_arl_read().  Unsuccessful
calls are caught by an switch statement handling specific returns.
b32_arl_read() calls b53_arl_op_wait() which fails with the
unhandled -ETIMEDOUT.

So add -ETIMEDOUT to the switch statement.  Because
b53_arl_op_wait() already prints out a message, do not add another
one.

Fixes: 1da6df85c6fb ("net: dsa: b53: Implement ARL add/del/dump operations")
Signed-off-by: Tom Rix <trix@redhat.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/b53/b53_common.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 1df05841ab6b..86869337223a 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -1555,6 +1555,8 @@ static int b53_arl_op(struct b53_device *dev, int op, int port,
 		return ret;
 
 	switch (ret) {
+	case -ETIMEDOUT:
+		return ret;
 	case -ENOSPC:
 		dev_dbg(dev->dev, "{%pM,%.4d} no space left in ARL\n",
 			addr, vid);
-- 
2.26.2


From 25d723c07e2197b37b5ca4a2550b0ea9210f2ba3 Mon Sep 17 00:00:00 2001
From: Fugang Duan <fugang.duan@nxp.com>
Date: Thu, 13 Aug 2020 15:13:14 +0800
Subject: [PATCH 07/24] net: fec: correct the error path for regulator disable
 in probe

[ Upstream commit c6165cf0dbb82ded90163dce3ac183fc7a913dc4 ]

Correct the error path for regulator disable.

Fixes: 9269e5560b26 ("net: fec: add phy-reset-gpios PROBE_DEFER check")
Signed-off-by: Fugang Duan <fugang.duan@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index cc7fbfc09354..534fcc71a2a5 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -3714,11 +3714,11 @@ fec_probe(struct platform_device *pdev)
 failed_irq:
 failed_init:
 	fec_ptp_stop(pdev);
-	if (fep->reg_phy)
-		regulator_disable(fep->reg_phy);
 failed_reset:
 	pm_runtime_put_noidle(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
+	if (fep->reg_phy)
+		regulator_disable(fep->reg_phy);
 failed_regulator:
 	clk_disable_unprepare(fep->clk_ahb);
 failed_clk_ahb:
-- 
2.26.2


From 3a94b153c2d35995b9324562cf0d5aad60f6fc0c Mon Sep 17 00:00:00 2001
From: Miaohe Lin <linmiaohe@huawei.com>
Date: Sat, 15 Aug 2020 04:44:31 -0400
Subject: [PATCH 08/24] net: Fix potential wrong skb->protocol in
 skb_vlan_untag()

[ Upstream commit 55eff0eb7460c3d50716ed9eccf22257b046ca92 ]

We may access the two bytes after vlan_hdr in vlan_set_encap_proto(). So
we should pull VLAN_HLEN + sizeof(unsigned short) in skb_vlan_untag() or
we may access the wrong data.

Fixes: 0d5501c1c828 ("net: Always untag vlan-tagged traffic on input.")
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index b8afefe6f6b6..7afe52bd038b 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5419,8 +5419,8 @@ struct sk_buff *skb_vlan_untag(struct sk_buff *skb)
 	skb = skb_share_check(skb, GFP_ATOMIC);
 	if (unlikely(!skb))
 		goto err_free;
-
-	if (unlikely(!pskb_may_pull(skb, VLAN_HLEN)))
+	/* We may access the two bytes after vlan_hdr in vlan_set_encap_proto(). */
+	if (unlikely(!pskb_may_pull(skb, VLAN_HLEN + sizeof(unsigned short))))
 		goto err_free;
 
 	vhdr = (struct vlan_hdr *)skb->data;
-- 
2.26.2


From 16c6f6a7c330beab23f528ae9ae8531fbe7f69a0 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Sat, 22 Aug 2020 15:06:36 +0300
Subject: [PATCH 09/24] net: nexthop: don't allow empty NHA_GROUP

[ Upstream commit eeaac3634ee0e3f35548be35275efeca888e9b23 ]

Currently the nexthop code will use an empty NHA_GROUP attribute, but it
requires at least 1 entry in order to function properly. Otherwise we
end up derefencing null or random pointers all over the place due to not
having any nh_grp_entry members allocated, nexthop code relies on having at
least the first member present. Empty NHA_GROUP doesn't make any sense so
just disallow it.
Also add a WARN_ON for any future users of nexthop_create_group().

 BUG: kernel NULL pointer dereference, address: 0000000000000080
 #PF: supervisor read access in kernel mode
 #PF: error_code(0x0000) - not-present page
 PGD 0 P4D 0
 Oops: 0000 [#1] SMP
 CPU: 0 PID: 558 Comm: ip Not tainted 5.9.0-rc1+ #93
 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-2.fc32 04/01/2014
 RIP: 0010:fib_check_nexthop+0x4a/0xaa
 Code: 0f 84 83 00 00 00 48 c7 02 80 03 f7 81 c3 40 80 fe fe 75 12 b8 ea ff ff ff 48 85 d2 74 6b 48 c7 02 40 03 f7 81 c3 48 8b 40 10 <48> 8b 80 80 00 00 00 eb 36 80 78 1a 00 74 12 b8 ea ff ff ff 48 85
 RSP: 0018:ffff88807983ba00 EFLAGS: 00010213
 RAX: 0000000000000000 RBX: ffff88807983bc00 RCX: 0000000000000000
 RDX: ffff88807983bc00 RSI: 0000000000000000 RDI: ffff88807bdd0a80
 RBP: ffff88807983baf8 R08: 0000000000000dc0 R09: 000000000000040a
 R10: 0000000000000000 R11: ffff88807bdd0ae8 R12: 0000000000000000
 R13: 0000000000000000 R14: ffff88807bea3100 R15: 0000000000000001
 FS:  00007f10db393700(0000) GS:ffff88807dc00000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000000080 CR3: 000000007bd0f004 CR4: 00000000003706f0
 Call Trace:
  fib_create_info+0x64d/0xaf7
  fib_table_insert+0xf6/0x581
  ? __vma_adjust+0x3b6/0x4d4
  inet_rtm_newroute+0x56/0x70
  rtnetlink_rcv_msg+0x1e3/0x20d
  ? rtnl_calcit.isra.0+0xb8/0xb8
  netlink_rcv_skb+0x5b/0xac
  netlink_unicast+0xfa/0x17b
  netlink_sendmsg+0x334/0x353
  sock_sendmsg_nosec+0xf/0x3f
  ____sys_sendmsg+0x1a0/0x1fc
  ? copy_msghdr_from_user+0x4c/0x61
  ___sys_sendmsg+0x63/0x84
  ? handle_mm_fault+0xa39/0x11b5
  ? sockfd_lookup_light+0x72/0x9a
  __sys_sendmsg+0x50/0x6e
  do_syscall_64+0x54/0xbe
  entry_SYSCALL_64_after_hwframe+0x44/0xa9
 RIP: 0033:0x7f10dacc0bb7
 Code: d8 64 89 02 48 c7 c0 ff ff ff ff eb cd 66 0f 1f 44 00 00 8b 05 9a 4b 2b 00 85 c0 75 2e 48 63 ff 48 63 d2 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 01 c3 48 8b 15 b1 f2 2a 00 f7 d8 64 89 02 48
 RSP: 002b:00007ffcbe628bf8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
 RAX: ffffffffffffffda RBX: 00007ffcbe628f80 RCX: 00007f10dacc0bb7
 RDX: 0000000000000000 RSI: 00007ffcbe628c60 RDI: 0000000000000003
 RBP: 000000005f41099c R08: 0000000000000001 R09: 0000000000000008
 R10: 00000000000005e9 R11: 0000000000000246 R12: 0000000000000000
 R13: 0000000000000000 R14: 00007ffcbe628d70 R15: 0000563a86c6e440
 Modules linked in:
 CR2: 0000000000000080

CC: David Ahern <dsahern@gmail.com>
Fixes: 430a049190de ("nexthop: Add support for nexthop groups")
Reported-by: syzbot+a61aa19b0c14c8770bd9@syzkaller.appspotmail.com
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/nexthop.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index cc8049b100b2..134e92382275 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -446,7 +446,7 @@ static int nh_check_attr_group(struct net *net, struct nlattr *tb[],
 	unsigned int i, j;
 	u8 nhg_fdb = 0;
 
-	if (len & (sizeof(struct nexthop_grp) - 1)) {
+	if (!len || len & (sizeof(struct nexthop_grp) - 1)) {
 		NL_SET_ERR_MSG(extack,
 			       "Invalid length for nexthop group attribute");
 		return -EINVAL;
@@ -1187,6 +1187,9 @@ static struct nexthop *nexthop_create_group(struct net *net,
 	struct nexthop *nh;
 	int i;
 
+	if (WARN_ON(!num_nh))
+		return ERR_PTR(-EINVAL);
+
 	nh = nexthop_alloc();
 	if (!nh)
 		return ERR_PTR(-ENOMEM);
-- 
2.26.2


From 1924749ae3e4ff5a67db6c247e459b1c745f043c Mon Sep 17 00:00:00 2001
From: Necip Fazil Yildiran <necip@google.com>
Date: Mon, 17 Aug 2020 15:54:48 +0000
Subject: [PATCH 10/24] net: qrtr: fix usage of idr in port assignment to
 socket

[ Upstream commit 8dfddfb79653df7c38a9c8c4c034f242a36acee9 ]

Passing large uint32 sockaddr_qrtr.port numbers for port allocation
triggers a warning within idr_alloc() since the port number is cast
to int, and thus interpreted as a negative number. This leads to
the rejection of such valid port numbers in qrtr_port_assign() as
idr_alloc() fails.

To avoid the problem, switch to idr_alloc_u32() instead.

Fixes: bdabad3e363d ("net: Add Qualcomm IPC router")
Reported-by: syzbot+f31428628ef672716ea8@syzkaller.appspotmail.com
Signed-off-by: Necip Fazil Yildiran <necip@google.com>
Reviewed-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/qrtr/qrtr.c | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index 300a104b9a0f..85ab4559f057 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -692,23 +692,25 @@ static void qrtr_port_remove(struct qrtr_sock *ipc)
  */
 static int qrtr_port_assign(struct qrtr_sock *ipc, int *port)
 {
+	u32 min_port;
 	int rc;
 
 	mutex_lock(&qrtr_port_lock);
 	if (!*port) {
-		rc = idr_alloc(&qrtr_ports, ipc,
-			       QRTR_MIN_EPH_SOCKET, QRTR_MAX_EPH_SOCKET + 1,
-			       GFP_ATOMIC);
-		if (rc >= 0)
-			*port = rc;
+		min_port = QRTR_MIN_EPH_SOCKET;
+		rc = idr_alloc_u32(&qrtr_ports, ipc, &min_port, QRTR_MAX_EPH_SOCKET, GFP_ATOMIC);
+		if (!rc)
+			*port = min_port;
 	} else if (*port < QRTR_MIN_EPH_SOCKET && !capable(CAP_NET_ADMIN)) {
 		rc = -EACCES;
 	} else if (*port == QRTR_PORT_CTRL) {
-		rc = idr_alloc(&qrtr_ports, ipc, 0, 1, GFP_ATOMIC);
+		min_port = 0;
+		rc = idr_alloc_u32(&qrtr_ports, ipc, &min_port, 0, GFP_ATOMIC);
 	} else {
-		rc = idr_alloc(&qrtr_ports, ipc, *port, *port + 1, GFP_ATOMIC);
-		if (rc >= 0)
-			*port = rc;
+		min_port = *port;
+		rc = idr_alloc_u32(&qrtr_ports, ipc, &min_port, *port, GFP_ATOMIC);
+		if (!rc)
+			*port = min_port;
 	}
 	mutex_unlock(&qrtr_port_lock);
 
-- 
2.26.2


From 62c3cfef8908f66d4f52cc6574dafd768e28e129 Mon Sep 17 00:00:00 2001
From: Alaa Hleihel <alaa@mellanox.com>
Date: Wed, 19 Aug 2020 18:24:10 +0300
Subject: [PATCH 11/24] net/sched: act_ct: Fix skb double-free in
 tcf_ct_handle_fragments() error flow

[ Upstream commit eda814b97dfb8d9f4808eb2f65af9bd3705c4cae ]

tcf_ct_handle_fragments() shouldn't free the skb when ip_defrag() call
fails. Otherwise, we will cause a double-free bug.
In such cases, just return the error to the caller.

Fixes: b57dc7c13ea9 ("net/sched: Introduce action ct")
Signed-off-by: Alaa Hleihel <alaa@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ct.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index 6ed1652d1e26..41d8440deaf1 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -704,7 +704,7 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
 		err = ip_defrag(net, skb, user);
 		local_bh_enable();
 		if (err && err != -EINPROGRESS)
-			goto out_free;
+			return err;
 
 		if (!err)
 			*defrag = true;
-- 
2.26.2


From 59b178df9f08a4739f0b9c663b804f67e3481f50 Mon Sep 17 00:00:00 2001
From: David Laight <David.Laight@ACULAB.COM>
Date: Wed, 19 Aug 2020 14:40:52 +0000
Subject: [PATCH 12/24] net: sctp: Fix negotiation of the number of data
 streams.

[ Upstream commit ab921f3cdbec01c68705a7ade8bec628d541fc2b ]

The number of output and input streams was never being reduced, eg when
processing received INIT or INIT_ACK chunks.
The effect is that DATA chunks can be sent with invalid stream ids
and then discarded by the remote system.

Fixes: 2075e50caf5ea ("sctp: convert to genradix")
Signed-off-by: David Laight <david.laight@aculab.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/stream.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index bda2536dd740..6dc95dcc0ff4 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -88,12 +88,13 @@ static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt,
 	int ret;
 
 	if (outcnt <= stream->outcnt)
-		return 0;
+		goto out;
 
 	ret = genradix_prealloc(&stream->out, outcnt, gfp);
 	if (ret)
 		return ret;
 
+out:
 	stream->outcnt = outcnt;
 	return 0;
 }
@@ -104,12 +105,13 @@ static int sctp_stream_alloc_in(struct sctp_stream *stream, __u16 incnt,
 	int ret;
 
 	if (incnt <= stream->incnt)
-		return 0;
+		goto out;
 
 	ret = genradix_prealloc(&stream->in, incnt, gfp);
 	if (ret)
 		return ret;
 
+out:
 	stream->incnt = incnt;
 	return 0;
 }
-- 
2.26.2


From f53008efe15d808032c137b5022f248959721326 Mon Sep 17 00:00:00 2001
From: Peilin Ye <yepeilin.cs@gmail.com>
Date: Thu, 20 Aug 2020 16:30:52 +0200
Subject: [PATCH 13/24] net/smc: Prevent kernel-infoleak in __smc_diag_dump()

[ Upstream commit ce51f63e63c52a4e1eee4dd040fb0ba0af3b43ab ]

__smc_diag_dump() is potentially copying uninitialized kernel stack memory
into socket buffers, since the compiler may leave a 4-byte hole near the
beginning of `struct smcd_diag_dmbinfo`. Fix it by initializing `dinfo`
with memset().

Fixes: 4b1b7d3b30a6 ("net/smc: add SMC-D diag support")
Suggested-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Peilin Ye <yepeilin.cs@gmail.com>
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/smc_diag.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c
index e1f64f4ba236..da9ba6d1679b 100644
--- a/net/smc/smc_diag.c
+++ b/net/smc/smc_diag.c
@@ -170,13 +170,15 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb,
 	    (req->diag_ext & (1 << (SMC_DIAG_DMBINFO - 1))) &&
 	    !list_empty(&smc->conn.lgr->list)) {
 		struct smc_connection *conn = &smc->conn;
-		struct smcd_diag_dmbinfo dinfo = {
-			.linkid = *((u32 *)conn->lgr->id),
-			.peer_gid = conn->lgr->peer_gid,
-			.my_gid = conn->lgr->smcd->local_gid,
-			.token = conn->rmb_desc->token,
-			.peer_token = conn->peer_token
-		};
+		struct smcd_diag_dmbinfo dinfo;
+
+		memset(&dinfo, 0, sizeof(dinfo));
+
+		dinfo.linkid = *((u32 *)conn->lgr->id);
+		dinfo.peer_gid = conn->lgr->peer_gid;
+		dinfo.my_gid = conn->lgr->smcd->local_gid;
+		dinfo.token = conn->rmb_desc->token;
+		dinfo.peer_token = conn->peer_token;
 
 		if (nla_put(skb, SMC_DIAG_DMBINFO, sizeof(dinfo), &dinfo) < 0)
 			goto errout;
-- 
2.26.2


From b8bb66681990f7ee7e4f7e453cb7942c71ee7bfb Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Sat, 15 Aug 2020 09:29:30 +0200
Subject: [PATCH 14/24] net: xdp: pull ethernet header off packet after
 computing skb->protocol

[ Upstream commit f8414a8d886b613b90d9fdf7cda6feea313b1069 ]

When an XDP program changes the ethernet header protocol field,
eth_type_trans is used to recalculate skb->protocol. In order for
eth_type_trans to work correctly, the ethernet header must actually be
part of the skb data segment, so the code first pushes that onto the
head of the skb. However, it subsequently forgets to pull it back off,
making the behavior of the passed-on packet inconsistent between the
protocol modifying case and the static protocol case. This patch fixes
the issue by simply pulling the ethernet header back off of the skb
head.

Fixes: 297249569932 ("net: fix generic XDP to handle if eth header was mangled")
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/core/dev.c b/net/core/dev.c
index 7a774ebf64e2..84f507d9d59e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4671,6 +4671,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 	    (orig_bcast != is_multicast_ether_addr_64bits(eth->h_dest))) {
 		__skb_push(skb, ETH_HLEN);
 		skb->protocol = eth_type_trans(skb, skb->dev);
+		__skb_pull(skb, ETH_HLEN);
 	}
 
 	switch (act) {
-- 
2.26.2


From 9717c62d4aafa1bcaac6e14a351ee6da0bf7cc27 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 20 Aug 2020 15:34:47 +0800
Subject: [PATCH 15/24] tipc: call rcu_read_lock() in tipc_aead_encrypt_done()

[ Upstream commit f6db9096416209474090d64d8284e7c16c3d8873 ]

b->media->send_msg() requires rcu_read_lock(), as we can see
elsewhere in tipc,  tipc_bearer_xmit, tipc_bearer_xmit_skb
and tipc_bearer_bc_xmit().

Syzbot has reported this issue as:

  net/tipc/bearer.c:466 suspicious rcu_dereference_check() usage!
  Workqueue: cryptd cryptd_queue_worker
  Call Trace:
   tipc_l2_send_msg+0x354/0x420 net/tipc/bearer.c:466
   tipc_aead_encrypt_done+0x204/0x3a0 net/tipc/crypto.c:761
   cryptd_aead_crypt+0xe8/0x1d0 crypto/cryptd.c:739
   cryptd_queue_worker+0x118/0x1b0 crypto/cryptd.c:181
   process_one_work+0x94c/0x1670 kernel/workqueue.c:2269
   worker_thread+0x64c/0x1120 kernel/workqueue.c:2415
   kthread+0x3b5/0x4a0 kernel/kthread.c:291
   ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:293

So fix it by calling rcu_read_lock() in tipc_aead_encrypt_done()
for b->media->send_msg().

Fixes: fc1b6d6de220 ("tipc: introduce TIPC encryption & authentication")
Reported-by: syzbot+47bbc6b678d317cccbe0@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/crypto.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c
index c8c47fc72653..d6426b6cc9c5 100644
--- a/net/tipc/crypto.c
+++ b/net/tipc/crypto.c
@@ -757,10 +757,12 @@ static void tipc_aead_encrypt_done(struct crypto_async_request *base, int err)
 	switch (err) {
 	case 0:
 		this_cpu_inc(tx->stats->stat[STAT_ASYNC_OK]);
+		rcu_read_lock();
 		if (likely(test_bit(0, &b->up)))
 			b->media->send_msg(net, skb, b, &tx_ctx->dst);
 		else
 			kfree_skb(skb);
+		rcu_read_unlock();
 		break;
 	case -EINPROGRESS:
 		return;
-- 
2.26.2


From f91df0acac1f89e99c7017a3f24283b74b09f4a3 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sat, 15 Aug 2020 16:29:15 -0700
Subject: [PATCH 16/24] tipc: fix uninit skb->data in tipc_nl_compat_dumpit()

[ Upstream commit 47733f9daf4fe4f7e0eb9e273f21ad3a19130487 ]

__tipc_nl_compat_dumpit() has two callers, and it expects them to
pass a valid nlmsghdr via arg->data. This header is artificial and
crafted just for __tipc_nl_compat_dumpit().

tipc_nl_compat_publ_dump() does so by putting a genlmsghdr as well
as some nested attribute, TIPC_NLA_SOCK. But the other caller
tipc_nl_compat_dumpit() does not, this leaves arg->data uninitialized
on this call path.

Fix this by just adding a similar nlmsghdr without any payload in
tipc_nl_compat_dumpit().

This bug exists since day 1, but the recent commit 6ea67769ff33
("net: tipc: prepare attrs in __tipc_nl_compat_dumpit()") makes it
easier to appear.

Reported-and-tested-by: syzbot+0e7181deafa7e0b79923@syzkaller.appspotmail.com
Fixes: d0796d1ef63d ("tipc: convert legacy nl bearer dump to nl compat")
Cc: Jon Maloy <jmaloy@redhat.com>
Cc: Ying Xue <ying.xue@windriver.com>
Cc: Richard Alpe <richard.alpe@ericsson.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/netlink_compat.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 217516357ef2..90e3c70a91ad 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -275,8 +275,9 @@ static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd,
 static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd,
 				 struct tipc_nl_compat_msg *msg)
 {
-	int err;
+	struct nlmsghdr *nlh;
 	struct sk_buff *arg;
+	int err;
 
 	if (msg->req_type && (!msg->req_size ||
 			      !TLV_CHECK_TYPE(msg->req, msg->req_type)))
@@ -305,6 +306,15 @@ static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd,
 		return -ENOMEM;
 	}
 
+	nlh = nlmsg_put(arg, 0, 0, tipc_genl_family.id, 0, NLM_F_MULTI);
+	if (!nlh) {
+		kfree_skb(arg);
+		kfree_skb(msg->rep);
+		msg->rep = NULL;
+		return -EMSGSIZE;
+	}
+	nlmsg_end(arg, nlh);
+
 	err = __tipc_nl_compat_dumpit(cmd, msg, arg);
 	if (err) {
 		kfree_skb(msg->rep);
-- 
2.26.2


From f703b6fd6c36dca91a3a98bc63055ec1aca69d7f Mon Sep 17 00:00:00 2001
From: Shay Agroskin <shayagr@amazon.com>
Date: Wed, 19 Aug 2020 20:28:36 +0300
Subject: [PATCH 18/24] net: ena: Prevent reset after device destruction

[ Upstream commit 63d4a4c145cca2e84dc6e62d2ef5cb990c9723c2 ]

The reset work is scheduled by the timer routine whenever it
detects that a device reset is required (e.g. when a keep_alive signal
is missing).
When releasing device resources in ena_destroy_device() the driver
cancels the scheduling of the timer routine without destroying the reset
work explicitly.

This creates the following bug:
    The driver is suspended and the ena_suspend() function is called
	-> This function calls ena_destroy_device() to free the net device
	   resources
	    -> The driver waits for the timer routine to finish
	    its execution and then cancels it, thus preventing from it
	    to be called again.

    If, in its final execution, the timer routine schedules a reset,
    the reset routine might be called afterwards,and a redundant call to
    ena_restore_device() would be made.

By changing the reset routine we allow it to read the device's state
accurately.
This is achieved by checking whether ENA_FLAG_TRIGGER_RESET flag is set
before resetting the device and making both the destruction function and
the flag check are under rtnl lock.
The ENA_FLAG_TRIGGER_RESET is cleared at the end of the destruction
routine. Also surround the flag check with 'likely' because
we expect that the reset routine would be called only when
ENA_FLAG_TRIGGER_RESET flag is set.

The destruction of the timer and reset services in __ena_shutoff() have to
stay, even though the timer routine is destroyed in ena_destroy_device().
This is to avoid a case in which the reset routine is scheduled after
free_netdev() in __ena_shutoff(), which would create an access to freed
memory in adapter->flags.

Fixes: 8c5c7abdeb2d ("net: ena: add power management ops to the ENA driver")
Signed-off-by: Shay Agroskin <shayagr@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index dda4b8fc9525..1a2a464fb2f5 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -3523,16 +3523,14 @@ static void ena_fw_reset_device(struct work_struct *work)
 {
 	struct ena_adapter *adapter =
 		container_of(work, struct ena_adapter, reset_task);
-	struct pci_dev *pdev = adapter->pdev;
 
-	if (unlikely(!test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))) {
-		dev_err(&pdev->dev,
-			"device reset schedule while reset bit is off\n");
-		return;
-	}
 	rtnl_lock();
-	ena_destroy_device(adapter, false);
-	ena_restore_device(adapter);
+
+	if (likely(test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))) {
+		ena_destroy_device(adapter, false);
+		ena_restore_device(adapter);
+	}
+
 	rtnl_unlock();
 }
 
@@ -4366,8 +4364,11 @@ static void __ena_shutoff(struct pci_dev *pdev, bool shutdown)
 		netdev->rx_cpu_rmap = NULL;
 	}
 #endif /* CONFIG_RFS_ACCEL */
-	del_timer_sync(&adapter->timer_service);
 
+	/* Make sure timer and reset routine won't be called after
+	 * freeing device resources.
+	 */
+	del_timer_sync(&adapter->timer_service);
 	cancel_work_sync(&adapter->reset_task);
 
 	rtnl_lock(); /* lock released inside the below if-else block */
-- 
2.26.2


From 17359c06b345c93d309ccb3877aa483fcbe798e8 Mon Sep 17 00:00:00 2001
From: Shay Agroskin <shayagr@amazon.com>
Date: Wed, 19 Aug 2020 20:28:37 +0300
Subject: [PATCH 19/24] net: ena: Change WARN_ON expression in
 ena_del_napi_in_range()

[ Upstream commit 8b147f6f3e7de4e51113e3e9ec44aa2debc02c58 ]

The ena_del_napi_in_range() function unregisters the napi handler for
rings in a given range.
This function had the following WARN_ON macro:

    WARN_ON(ENA_IS_XDP_INDEX(adapter, i) &&
	    adapter->ena_napi[i].xdp_ring);

This macro prints the call stack if the expression inside of it is
true [1], but the expression inside of it is the wanted situation.
The expression checks whether the ring has an XDP queue and its index
corresponds to a XDP one.

This patch changes the expression to
    !ENA_IS_XDP_INDEX(adapter, i) && adapter->ena_napi[i].xdp_ring
which indicates an unwanted situation.

Also, change the structure of the function. The napi handler is
unregistered for all rings, and so there's no need to check whether the
index is an XDP index or not. By removing this check the code becomes
much more readable.

Fixes: 548c4940b9f1 ("net: ena: Implement XDP_TX action")
Signed-off-by: Shay Agroskin <shayagr@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 1a2a464fb2f5..000f57198352 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -2177,13 +2177,10 @@ static void ena_del_napi_in_range(struct ena_adapter *adapter,
 	int i;
 
 	for (i = first_index; i < first_index + count; i++) {
-		/* Check if napi was initialized before */
-		if (!ENA_IS_XDP_INDEX(adapter, i) ||
-		    adapter->ena_napi[i].xdp_ring)
-			netif_napi_del(&adapter->ena_napi[i].napi);
-		else
-			WARN_ON(ENA_IS_XDP_INDEX(adapter, i) &&
-				adapter->ena_napi[i].xdp_ring);
+		netif_napi_del(&adapter->ena_napi[i].napi);
+
+		WARN_ON(!ENA_IS_XDP_INDEX(adapter, i) &&
+			adapter->ena_napi[i].xdp_ring);
 	}
 }
 
-- 
2.26.2


From 2c4155dec18537e71ed982dace10308455e7a858 Mon Sep 17 00:00:00 2001
From: Shay Agroskin <shayagr@amazon.com>
Date: Wed, 19 Aug 2020 20:28:38 +0300
Subject: [PATCH 20/24] net: ena: Make missed_tx stat incremental

[ Upstream commit ccd143e5150f24b9ba15145c7221b61dd9e41021 ]

Most statistics in ena driver are incremented, meaning that a stat's
value is a sum of all increases done to it since driver/queue
initialization.

This patch makes all statistics this way, effectively making missed_tx
statistic incremental.
Also added a comment regarding rx_drops and tx_drops to make it
clearer how these counters are calculated.

Fixes: 11095fdb712b ("net: ena: add statistics for missed tx packets")
Signed-off-by: Shay Agroskin <shayagr@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 000f57198352..9f2c697ba0ac 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -3609,7 +3609,7 @@ static int check_missing_comp_in_tx_queue(struct ena_adapter *adapter,
 	}
 
 	u64_stats_update_begin(&tx_ring->syncp);
-	tx_ring->tx_stats.missed_tx = missed_tx;
+	tx_ring->tx_stats.missed_tx += missed_tx;
 	u64_stats_update_end(&tx_ring->syncp);
 
 	return rc;
@@ -4537,6 +4537,9 @@ static void ena_keep_alive_wd(void *adapter_data,
 	tx_drops = ((u64)desc->tx_drops_high << 32) | desc->tx_drops_low;
 
 	u64_stats_update_begin(&adapter->syncp);
+	/* These stats are accumulated by the device, so the counters indicate
+	 * all drops since last reset.
+	 */
 	adapter->dev_stats.rx_drops = rx_drops;
 	adapter->dev_stats.tx_drops = tx_drops;
 	u64_stats_update_end(&adapter->syncp);
-- 
2.26.2


From 8daa92d9f90f62b32a6e91ef8ffb84051019eb89 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Mon, 17 Aug 2020 16:34:05 +0300
Subject: [PATCH 21/24] ethtool: Fix preserving of wanted feature bits in
 netlink interface

[ Upstream commit 840110a4eae190dcbb9907d68216d5d1d9f25839 ]

Currently, ethtool-netlink calculates new wanted bits as:
(req_wanted & req_mask) | (old_active & ~req_mask)

It completely discards the old wanted bits, so they are forgotten with
the next ethtool command. Sample steps to reproduce:

1. ethtool -k eth0
   tx-tcp-segmentation: on # TSO is on from the beginning
2. ethtool -K eth0 tx off
   tx-tcp-segmentation: off [not requested]
3. ethtool -k eth0
   tx-tcp-segmentation: off [requested on]
4. ethtool -K eth0 rx off # Some change unrelated to TSO
5. ethtool -k eth0
   tx-tcp-segmentation: off # "Wanted on" is forgotten

This commit fixes it by changing the formula to:
(req_wanted & req_mask) | (old_wanted & ~req_mask),
where old_active was replaced by old_wanted to account for the wanted
bits.

The shortcut condition for the case where nothing was changed now
compares wanted bitmasks, instead of wanted to active.

Fixes: 0980bfcd6954 ("ethtool: set netdev features with FEATURES_SET request")
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ethtool/features.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/net/ethtool/features.c b/net/ethtool/features.c
index 4e632dc987d8..ec196f0fddc9 100644
--- a/net/ethtool/features.c
+++ b/net/ethtool/features.c
@@ -224,7 +224,9 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info)
 	DECLARE_BITMAP(wanted_diff_mask, NETDEV_FEATURE_COUNT);
 	DECLARE_BITMAP(active_diff_mask, NETDEV_FEATURE_COUNT);
 	DECLARE_BITMAP(old_active, NETDEV_FEATURE_COUNT);
+	DECLARE_BITMAP(old_wanted, NETDEV_FEATURE_COUNT);
 	DECLARE_BITMAP(new_active, NETDEV_FEATURE_COUNT);
+	DECLARE_BITMAP(new_wanted, NETDEV_FEATURE_COUNT);
 	DECLARE_BITMAP(req_wanted, NETDEV_FEATURE_COUNT);
 	DECLARE_BITMAP(req_mask, NETDEV_FEATURE_COUNT);
 	struct nlattr *tb[ETHTOOL_A_FEATURES_MAX + 1];
@@ -250,6 +252,7 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info)
 
 	rtnl_lock();
 	ethnl_features_to_bitmap(old_active, dev->features);
+	ethnl_features_to_bitmap(old_wanted, dev->wanted_features);
 	ret = ethnl_parse_bitset(req_wanted, req_mask, NETDEV_FEATURE_COUNT,
 				 tb[ETHTOOL_A_FEATURES_WANTED],
 				 netdev_features_strings, info->extack);
@@ -261,11 +264,11 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info)
 		goto out_rtnl;
 	}
 
-	/* set req_wanted bits not in req_mask from old_active */
+	/* set req_wanted bits not in req_mask from old_wanted */
 	bitmap_and(req_wanted, req_wanted, req_mask, NETDEV_FEATURE_COUNT);
-	bitmap_andnot(new_active, old_active, req_mask, NETDEV_FEATURE_COUNT);
-	bitmap_or(req_wanted, new_active, req_wanted, NETDEV_FEATURE_COUNT);
-	if (bitmap_equal(req_wanted, old_active, NETDEV_FEATURE_COUNT)) {
+	bitmap_andnot(new_wanted, old_wanted, req_mask, NETDEV_FEATURE_COUNT);
+	bitmap_or(req_wanted, new_wanted, req_wanted, NETDEV_FEATURE_COUNT);
+	if (bitmap_equal(req_wanted, old_wanted, NETDEV_FEATURE_COUNT)) {
 		ret = 0;
 		goto out_rtnl;
 	}
-- 
2.26.2


From b6467d8d6bd046c1fbb22ee9eea30d0296273e8e Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Mon, 17 Aug 2020 16:34:06 +0300
Subject: [PATCH 22/24] ethtool: Account for hw_features in netlink interface

[ Upstream commit 2847bfed888fbb8bf4c8e8067fd6127538c2c700 ]

ethtool-netlink ignores dev->hw_features and may confuse the drivers by
asking them to enable features not in the hw_features bitmask. For
example:

1. ethtool -k eth0
   tls-hw-tx-offload: off [fixed]
2. ethtool -K eth0 tls-hw-tx-offload on
   tls-hw-tx-offload: on
3. ethtool -k eth0
   tls-hw-tx-offload: on [fixed]

Fitler out dev->hw_features from req_wanted to fix it and to resemble
the legacy ethtool behavior.

Fixes: 0980bfcd6954 ("ethtool: set netdev features with FEATURES_SET request")
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ethtool/features.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ethtool/features.c b/net/ethtool/features.c
index ec196f0fddc9..6b288bfd7678 100644
--- a/net/ethtool/features.c
+++ b/net/ethtool/features.c
@@ -273,7 +273,8 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info)
 		goto out_rtnl;
 	}
 
-	dev->wanted_features = ethnl_bitmap_to_features(req_wanted);
+	dev->wanted_features &= ~dev->hw_features;
+	dev->wanted_features |= ethnl_bitmap_to_features(req_wanted) & dev->hw_features;
 	__netdev_update_features(dev);
 	ethnl_features_to_bitmap(new_active, dev->features);
 	mod = !bitmap_equal(old_active, new_active, NETDEV_FEATURE_COUNT);
-- 
2.26.2


From 834bcf70b235b00a606ac602e2ea899c12203751 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Mon, 17 Aug 2020 16:34:07 +0300
Subject: [PATCH 23/24] ethtool: Don't omit the netlink reply if no features
 were changed

[ Upstream commit f01204ec8be7ea5e8f0230a7d4200e338d563bde ]

The legacy ethtool userspace tool shows an error when no features could
be changed. It's useful to have a netlink reply to be able to show this
error when __netdev_update_features wasn't called, for example:

1. ethtool -k eth0
   large-receive-offload: off
2. ethtool -K eth0 rx-fcs on
3. ethtool -K eth0 lro on
   Could not change any device features
   rx-lro: off [requested on]
4. ethtool -K eth0 lro on
   # The output should be the same, but without this patch the kernel
   # doesn't send the reply, and ethtool is unable to detect the error.

This commit makes ethtool-netlink always return a reply when requested,
and it still avoids unnecessary calls to __netdev_update_features if the
wanted features haven't changed.

Fixes: 0980bfcd6954 ("ethtool: set netdev features with FEATURES_SET request")
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ethtool/features.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/net/ethtool/features.c b/net/ethtool/features.c
index 6b288bfd7678..495635f152ba 100644
--- a/net/ethtool/features.c
+++ b/net/ethtool/features.c
@@ -268,14 +268,11 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info)
 	bitmap_and(req_wanted, req_wanted, req_mask, NETDEV_FEATURE_COUNT);
 	bitmap_andnot(new_wanted, old_wanted, req_mask, NETDEV_FEATURE_COUNT);
 	bitmap_or(req_wanted, new_wanted, req_wanted, NETDEV_FEATURE_COUNT);
-	if (bitmap_equal(req_wanted, old_wanted, NETDEV_FEATURE_COUNT)) {
-		ret = 0;
-		goto out_rtnl;
+	if (!bitmap_equal(req_wanted, old_wanted, NETDEV_FEATURE_COUNT)) {
+		dev->wanted_features &= ~dev->hw_features;
+		dev->wanted_features |= ethnl_bitmap_to_features(req_wanted) & dev->hw_features;
+		__netdev_update_features(dev);
 	}
-
-	dev->wanted_features &= ~dev->hw_features;
-	dev->wanted_features |= ethnl_bitmap_to_features(req_wanted) & dev->hw_features;
-	__netdev_update_features(dev);
 	ethnl_features_to_bitmap(new_active, dev->features);
 	mod = !bitmap_equal(old_active, new_active, NETDEV_FEATURE_COUNT);
 
-- 
2.26.2


From 20efed1624cb9a573534df878140722aad91ace9 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 19 Aug 2020 21:52:38 +0200
Subject: [PATCH 24/24] netlink: fix state reallocation in policy export

[ Upstream commit d1fb55592909ea249af70170c7a52e637009564d ]

Evidently, when I did this previously, we didn't have more than
10 policies and didn't run into the reallocation path, because
it's missing a memset() for the unused policies. Fix that.

Fixes: d07dcf9aadd6 ("netlink: add infrastructure to expose policies to userspace")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/policy.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/netlink/policy.c b/net/netlink/policy.c
index f6491853c797..2b3e26f7496f 100644
--- a/net/netlink/policy.c
+++ b/net/netlink/policy.c
@@ -51,6 +51,9 @@ static int add_policy(struct nl_policy_dump **statep,
 	if (!state)
 		return -ENOMEM;
 
+	memset(&state->policies[state->n_alloc], 0,
+	       flex_array_size(state, policies, n_alloc - state->n_alloc));
+
 	state->policies[state->n_alloc].policy = policy;
 	state->policies[state->n_alloc].maxtype = maxtype;
 	state->n_alloc = n_alloc;
-- 
2.26.2

Re: [PATCHES] Networking

[Greg KH]

On Mon, Aug 24, 2020 at 09:52:29AM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v5.7
> and v5.8 -stable, respectively.

All now queued up, thanks.

Note, 5.7.y is now end-of-life after these patches are merged, so no
need to worry about that kernel tree anymore.

thanks,

greg k-h

[PATCHES] Networking

[David Miller]

[-- Attachment #1: Type: Text/Plain, Size: 105 bytes --]


Please queue up the following networking bug fixes for v5.4
and v5.8 -stable, respectively.

Thank you!

[-- Attachment #2: net_54.mbox --]
[-- Type: Application/Octet-Stream, Size: 98045 bytes --]

From 8b243263389f96c9c1d2767417c6ebc6b5a83ec4 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 3 Sep 2020 19:10:11 -0700
Subject: [PATCH 01/36] act_ife: load meta modules before tcf_idr_check_alloc()

[ Upstream commit cc8e58f8325cdf14b9516b61c384cdfd02a4f408 ]

The following deadlock scenario is triggered by syzbot:

Thread A:				Thread B:
tcf_idr_check_alloc()
...
populate_metalist()
  rtnl_unlock()
					rtnl_lock()
					...
  request_module()			tcf_idr_check_alloc()
  rtnl_lock()

At this point, thread A is waiting for thread B to release RTNL
lock, while thread B is waiting for thread A to commit the IDR
change with tcf_idr_insert() later.

Break this deadlock situation by preloading ife modules earlier,
before tcf_idr_check_alloc(), this is fine because we only need
to load modules we need potentially.

Reported-and-tested-by: syzbot+80e32b5d1f9923f8ace6@syzkaller.appspotmail.com
Fixes: 0190c1d452a9 ("net: sched: atomically check-allocate action")
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Vlad Buslov <vladbu@mellanox.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/act_ife.c | 44 ++++++++++++++++++++++++++++++++++----------
 1 file changed, 34 insertions(+), 10 deletions(-)

diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index a0cfb4793c93..778371bac93e 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -436,6 +436,25 @@ static void tcf_ife_cleanup(struct tc_action *a)
 		kfree_rcu(p, rcu);
 }
 
+static int load_metalist(struct nlattr **tb, bool rtnl_held)
+{
+	int i;
+
+	for (i = 1; i < max_metacnt; i++) {
+		if (tb[i]) {
+			void *val = nla_data(tb[i]);
+			int len = nla_len(tb[i]);
+			int rc;
+
+			rc = load_metaops_and_vet(i, val, len, rtnl_held);
+			if (rc != 0)
+				return rc;
+		}
+	}
+
+	return 0;
+}
+
 static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb,
 			     bool exists, bool rtnl_held)
 {
@@ -449,10 +468,6 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb,
 			val = nla_data(tb[i]);
 			len = nla_len(tb[i]);
 
-			rc = load_metaops_and_vet(i, val, len, rtnl_held);
-			if (rc != 0)
-				return rc;
-
 			rc = add_metainfo(ife, i, val, len, exists);
 			if (rc)
 				return rc;
@@ -508,6 +523,21 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	if (!p)
 		return -ENOMEM;
 
+	if (tb[TCA_IFE_METALST]) {
+		err = nla_parse_nested_deprecated(tb2, IFE_META_MAX,
+						  tb[TCA_IFE_METALST], NULL,
+						  NULL);
+		if (err) {
+			kfree(p);
+			return err;
+		}
+		err = load_metalist(tb2, rtnl_held);
+		if (err) {
+			kfree(p);
+			return err;
+		}
+	}
+
 	index = parm->index;
 	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (err < 0) {
@@ -569,15 +599,9 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	}
 
 	if (tb[TCA_IFE_METALST]) {
-		err = nla_parse_nested_deprecated(tb2, IFE_META_MAX,
-						  tb[TCA_IFE_METALST], NULL,
-						  NULL);
-		if (err)
-			goto metadata_parse_err;
 		err = populate_metalist(ife, tb2, exists, rtnl_held);
 		if (err)
 			goto metadata_parse_err;
-
 	} else {
 		/* if no passed metadata allow list or passed allow-all
 		 * then here we process by adding as many supported metadatum
-- 
2.26.2


From 491bcfc5a9a41bd82d3ac5988ebbd2ad301769a1 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Sat, 5 Sep 2020 22:55:36 -0400
Subject: [PATCH 02/36] bnxt_en: Avoid sending firmware messages when AER error
 is detected.

[ Upstream commit b340dc680ed48dcc05b56e1ebe1b9535813c3ee0 ]

When the driver goes through PCIe AER reset in error state, all
firmware messages will timeout because the PCIe bus is no longer
accessible.  This can lead to AER reset taking many minutes to
complete as each firmware command takes time to timeout.

Define a new macro BNXT_NO_FW_ACCESS() to skip these firmware messages
when either firmware is in fatal error state or when
pci_channel_offline() is true.  It now takes a more reasonable 20 to
30 seconds to complete AER recovery.

Fixes: b4fff2079d10 ("bnxt_en: Do not send firmware messages if firmware is in error state.")
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 6 +++---
 drivers/net/ethernet/broadcom/bnxt/bnxt.h | 4 ++++
 2 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 4030020f92be..00a2137c2b31 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -4204,7 +4204,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 	u32 bar_offset = BNXT_GRCPF_REG_CHIMP_COMM;
 	u16 dst = BNXT_HWRM_CHNL_CHIMP;
 
-	if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state))
+	if (BNXT_NO_FW_ACCESS(bp))
 		return -EBUSY;
 
 	if (msg_len > BNXT_HWRM_MAX_REQ_LEN) {
@@ -5539,7 +5539,7 @@ static int hwrm_ring_free_send_msg(struct bnxt *bp,
 	struct hwrm_ring_free_output *resp = bp->hwrm_cmd_resp_addr;
 	u16 error_code;
 
-	if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state))
+	if (BNXT_NO_FW_ACCESS(bp))
 		return 0;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_RING_FREE, cmpl_ring_id, -1);
@@ -7454,7 +7454,7 @@ static int bnxt_set_tpa(struct bnxt *bp, bool set_tpa)
 
 	if (set_tpa)
 		tpa_flags = bp->flags & BNXT_FLAG_TPA;
-	else if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state))
+	else if (BNXT_NO_FW_ACCESS(bp))
 		return 0;
 	for (i = 0; i < bp->nr_vnics; i++) {
 		rc = bnxt_hwrm_vnic_set_tpa(bp, i, tpa_flags);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index a61a5873ab0a..d2dd852d27da 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1628,6 +1628,10 @@ struct bnxt {
 #define BNXT_STATE_ABORT_ERR	5
 #define BNXT_STATE_FW_FATAL_COND	6
 
+#define BNXT_NO_FW_ACCESS(bp)					\
+	(test_bit(BNXT_STATE_FW_FATAL_COND, &(bp)->state) ||	\
+	 pci_channel_offline((bp)->pdev))
+
 	struct bnxt_irq	*irq_tbl;
 	int			total_irqs;
 	u8			mac_addr[ETH_ALEN];
-- 
2.26.2


From d153326c80ade8700bfcfbf2c1907e1f7356e8af Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Sat, 5 Sep 2020 22:55:37 -0400
Subject: [PATCH 03/36] bnxt_en: Fix NULL ptr dereference crash in
 bnxt_fw_reset_task()

[ Upstream commit b16939b59cc00231a75d224fd058d22c9d064976 ]

bnxt_fw_reset_task() which runs from a workqueue can race with
bnxt_remove_one().  For example, if firmware reset and VF FLR are
happening at about the same time.

bnxt_remove_one() already cancels the workqueue and waits for it
to finish, but we need to do this earlier before the devlink
reporters are destroyed.  This will guarantee that
the devlink reporters will always be valid when bnxt_fw_reset_task()
is still running.

Fixes: b148bb238c02 ("bnxt_en: Fix possible crash in bnxt_fw_reset_task().")
Reviewed-by: Edwin Peer <edwin.peer@broadcom.com>
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 00a2137c2b31..59257ee25168 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -11385,14 +11385,15 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 	if (BNXT_PF(bp))
 		bnxt_sriov_disable(bp);
 
+	clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
+	bnxt_cancel_sp_work(bp);
+	bp->sp_event = 0;
+
 	bnxt_dl_fw_reporters_destroy(bp, true);
 	pci_disable_pcie_error_reporting(pdev);
 	unregister_netdev(dev);
 	bnxt_dl_unregister(bp);
 	bnxt_shutdown_tc(bp);
-	clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
-	bnxt_cancel_sp_work(bp);
-	bp->sp_event = 0;
 
 	bnxt_clear_int_mode(bp);
 	bnxt_hwrm_func_drv_unrgtr(bp);
-- 
2.26.2


From 7986df5ebcd27adb80e466c7a07db196ccbadd07 Mon Sep 17 00:00:00 2001
From: Raju Rangoju <rajur@chelsio.com>
Date: Wed, 16 Sep 2020 21:50:39 +0530
Subject: [PATCH 04/36] cxgb4: fix memory leak during module unload

[ Upstream commit f4a26a9b311d7ff9db461278faf2869d06496ef8 ]

Fix the memory leak in mps during module unload
path by freeing mps reference entries if the list
adpter->mps_ref is not already empty

Fixes: 28b3870578ef ("cxgb4: Re-work the logic for mps refcounting")
Signed-off-by: Raju Rangoju <rajur@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_mps.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_mps.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_mps.c
index b1a073eea60b..a020e8490681 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_mps.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_mps.c
@@ -229,7 +229,7 @@ void cxgb4_free_mps_ref_entries(struct adapter *adap)
 {
 	struct mps_entries_ref *mps_entry, *tmp;
 
-	if (!list_empty(&adap->mps_ref))
+	if (list_empty(&adap->mps_ref))
 		return;
 
 	spin_lock(&adap->mps_ref_lock);
-- 
2.26.2


From 53e8fdbd5f539122ca2fa14478321b83ecbdd18c Mon Sep 17 00:00:00 2001
From: Ganji Aravind <ganji.aravind@chelsio.com>
Date: Fri, 4 Sep 2020 15:58:18 +0530
Subject: [PATCH 05/36] cxgb4: Fix offset when clearing filter byte counters

[ Upstream commit 94cc242a067a869c29800aa789d38b7676136e50 ]

Pass the correct offset to clear the stale filter hit
bytes counter. Otherwise, the counter starts incrementing
from the stale information, instead of 0.

Fixes: 12b276fbf6e0 ("cxgb4: add support to create hash filters")
Signed-off-by: Ganji Aravind <ganji.aravind@chelsio.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
index f459313357c7..137ff00605d9 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
@@ -1617,13 +1617,16 @@ int cxgb4_del_filter(struct net_device *dev, int filter_id,
 static int configure_filter_tcb(struct adapter *adap, unsigned int tid,
 				struct filter_entry *f)
 {
-	if (f->fs.hitcnts)
+	if (f->fs.hitcnts) {
 		set_tcb_field(adap, f, tid, TCB_TIMESTAMP_W,
-			      TCB_TIMESTAMP_V(TCB_TIMESTAMP_M) |
+			      TCB_TIMESTAMP_V(TCB_TIMESTAMP_M),
+			      TCB_TIMESTAMP_V(0ULL),
+			      1);
+		set_tcb_field(adap, f, tid, TCB_RTT_TS_RECENT_AGE_W,
 			      TCB_RTT_TS_RECENT_AGE_V(TCB_RTT_TS_RECENT_AGE_M),
-			      TCB_TIMESTAMP_V(0ULL) |
 			      TCB_RTT_TS_RECENT_AGE_V(0ULL),
 			      1);
+	}
 
 	if (f->fs.newdmac)
 		set_tcb_tflag(adap, f, tid, TF_CCTRL_ECE_S, 1,
-- 
2.26.2


From 8c37ec2c042502824c0c2970a3b689debed73b8a Mon Sep 17 00:00:00 2001
From: Mark Gray <mark.d.gray@redhat.com>
Date: Wed, 16 Sep 2020 05:19:35 -0400
Subject: [PATCH 06/36] geneve: add transport ports in route lookup for geneve

[ Upstream commit 34beb21594519ce64a55a498c2fe7d567bc1ca20 ]

This patch adds transport ports information for route lookup so that
IPsec can select Geneve tunnel traffic to do encryption. This is
needed for OVS/OVN IPsec with encrypted Geneve tunnels.

This can be tested by configuring a host-host VPN using an IKE
daemon and specifying port numbers. For example, for an
Openswan-type configuration, the following parameters should be
configured on both hosts and IPsec set up as-per normal:

$ cat /etc/ipsec.conf

conn in
...
left=$IP1
right=$IP2
...
leftprotoport=udp/6081
rightprotoport=udp
...
conn out
...
left=$IP1
right=$IP2
...
leftprotoport=udp
rightprotoport=udp/6081
...

The tunnel can then be setup using "ip" on both hosts (but
changing the relevant IP addresses):

$ ip link add tun type geneve id 1000 remote $IP2
$ ip addr add 192.168.0.1/24 dev tun
$ ip link set tun up

This can then be tested by pinging from $IP1:

$ ping 192.168.0.2

Without this patch the traffic is unencrypted on the wire.

Fixes: 2d07dc79fe04 ("geneve: add initial netdev driver for GENEVE tunnels")
Signed-off-by: Qiuyu Xiao <qiuyu.xiao.qyx@gmail.com>
Signed-off-by: Mark Gray <mark.d.gray@redhat.com>
Reviewed-by: Greg Rose <gvrose8192@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c | 37 +++++++++++++++++++++++++++----------
 1 file changed, 27 insertions(+), 10 deletions(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index adfdf6260b26..fcb7a6b4cc02 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -773,7 +773,8 @@ static struct rtable *geneve_get_v4_rt(struct sk_buff *skb,
 				       struct net_device *dev,
 				       struct geneve_sock *gs4,
 				       struct flowi4 *fl4,
-				       const struct ip_tunnel_info *info)
+				       const struct ip_tunnel_info *info,
+				       __be16 dport, __be16 sport)
 {
 	bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
 	struct geneve_dev *geneve = netdev_priv(dev);
@@ -789,6 +790,8 @@ static struct rtable *geneve_get_v4_rt(struct sk_buff *skb,
 	fl4->flowi4_proto = IPPROTO_UDP;
 	fl4->daddr = info->key.u.ipv4.dst;
 	fl4->saddr = info->key.u.ipv4.src;
+	fl4->fl4_dport = dport;
+	fl4->fl4_sport = sport;
 
 	tos = info->key.tos;
 	if ((tos == 1) && !geneve->collect_md) {
@@ -823,7 +826,8 @@ static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb,
 					   struct net_device *dev,
 					   struct geneve_sock *gs6,
 					   struct flowi6 *fl6,
-					   const struct ip_tunnel_info *info)
+					   const struct ip_tunnel_info *info,
+					   __be16 dport, __be16 sport)
 {
 	bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
 	struct geneve_dev *geneve = netdev_priv(dev);
@@ -839,6 +843,9 @@ static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb,
 	fl6->flowi6_proto = IPPROTO_UDP;
 	fl6->daddr = info->key.u.ipv6.dst;
 	fl6->saddr = info->key.u.ipv6.src;
+	fl6->fl6_dport = dport;
+	fl6->fl6_sport = sport;
+
 	prio = info->key.tos;
 	if ((prio == 1) && !geneve->collect_md) {
 		prio = ip_tunnel_get_dsfield(ip_hdr(skb), skb);
@@ -885,14 +892,15 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	__be16 sport;
 	int err;
 
-	rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info);
+	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
+	rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info,
+			      geneve->info.key.tp_dst, sport);
 	if (IS_ERR(rt))
 		return PTR_ERR(rt);
 
 	skb_tunnel_check_pmtu(skb, &rt->dst,
 			      GENEVE_IPV4_HLEN + info->options_len);
 
-	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
 	if (geneve->collect_md) {
 		tos = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb);
 		ttl = key->ttl;
@@ -947,13 +955,14 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	__be16 sport;
 	int err;
 
-	dst = geneve_get_v6_dst(skb, dev, gs6, &fl6, info);
+	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
+	dst = geneve_get_v6_dst(skb, dev, gs6, &fl6, info,
+				geneve->info.key.tp_dst, sport);
 	if (IS_ERR(dst))
 		return PTR_ERR(dst);
 
 	skb_tunnel_check_pmtu(skb, dst, GENEVE_IPV6_HLEN + info->options_len);
 
-	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
 	if (geneve->collect_md) {
 		prio = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb);
 		ttl = key->ttl;
@@ -1034,13 +1043,18 @@ static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 {
 	struct ip_tunnel_info *info = skb_tunnel_info(skb);
 	struct geneve_dev *geneve = netdev_priv(dev);
+	__be16 sport;
 
 	if (ip_tunnel_info_af(info) == AF_INET) {
 		struct rtable *rt;
 		struct flowi4 fl4;
+
 		struct geneve_sock *gs4 = rcu_dereference(geneve->sock4);
+		sport = udp_flow_src_port(geneve->net, skb,
+					  1, USHRT_MAX, true);
 
-		rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info);
+		rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info,
+				      geneve->info.key.tp_dst, sport);
 		if (IS_ERR(rt))
 			return PTR_ERR(rt);
 
@@ -1050,9 +1064,13 @@ static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 	} else if (ip_tunnel_info_af(info) == AF_INET6) {
 		struct dst_entry *dst;
 		struct flowi6 fl6;
+
 		struct geneve_sock *gs6 = rcu_dereference(geneve->sock6);
+		sport = udp_flow_src_port(geneve->net, skb,
+					  1, USHRT_MAX, true);
 
-		dst = geneve_get_v6_dst(skb, dev, gs6, &fl6, info);
+		dst = geneve_get_v6_dst(skb, dev, gs6, &fl6, info,
+					geneve->info.key.tp_dst, sport);
 		if (IS_ERR(dst))
 			return PTR_ERR(dst);
 
@@ -1063,8 +1081,7 @@ static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 		return -EINVAL;
 	}
 
-	info->key.tp_src = udp_flow_src_port(geneve->net, skb,
-					     1, USHRT_MAX, true);
+	info->key.tp_src = sport;
 	info->key.tp_dst = geneve->info.key.tp_dst;
 	return 0;
 }
-- 
2.26.2


From 246c130cd2d005175feb604bb809ddcce89a2e73 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 9 Sep 2020 12:46:48 +0300
Subject: [PATCH 07/36] hdlc_ppp: add range checks in ppp_cp_parse_cr()

[ Upstream commit 66d42ed8b25b64eb63111a2b8582c5afc8bf1105 ]

There are a couple bugs here:
1) If opt[1] is zero then this results in a forever loop.  If the value
   is less than 2 then it is invalid.
2) It assumes that "len" is more than sizeof(valid_accm) or 6 which can
   result in memory corruption.

In the case of LCP_OPTION_ACCM, then  we should check "opt[1]" instead
of "len" because, if "opt[1]" is less than sizeof(valid_accm) then
"nak_len" gets out of sync and it can lead to memory corruption in the
next iterations through the loop.  In case of LCP_OPTION_MAGIC, the
only valid value for opt[1] is 6, but the code is trying to log invalid
data so we should only discard the data when "len" is less than 6
because that leads to a read overflow.

Reported-by: ChenNan Of Chaitin Security Research Lab  <whutchennan@gmail.com>
Fixes: e022c2f07ae5 ("WAN: new synchronous PPP implementation for generic HDLC.")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wan/hdlc_ppp.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wan/hdlc_ppp.c b/drivers/net/wan/hdlc_ppp.c
index 48ced3912576..16f33d1ffbfb 100644
--- a/drivers/net/wan/hdlc_ppp.c
+++ b/drivers/net/wan/hdlc_ppp.c
@@ -383,11 +383,8 @@ static void ppp_cp_parse_cr(struct net_device *dev, u16 pid, u8 id,
 	}
 
 	for (opt = data; len; len -= opt[1], opt += opt[1]) {
-		if (len < 2 || len < opt[1]) {
-			dev->stats.rx_errors++;
-			kfree(out);
-			return; /* bad packet, drop silently */
-		}
+		if (len < 2 || opt[1] < 2 || len < opt[1])
+			goto err_out;
 
 		if (pid == PID_LCP)
 			switch (opt[0]) {
@@ -395,6 +392,8 @@ static void ppp_cp_parse_cr(struct net_device *dev, u16 pid, u8 id,
 				continue; /* MRU always OK and > 1500 bytes? */
 
 			case LCP_OPTION_ACCM: /* async control character map */
+				if (opt[1] < sizeof(valid_accm))
+					goto err_out;
 				if (!memcmp(opt, valid_accm,
 					    sizeof(valid_accm)))
 					continue;
@@ -406,6 +405,8 @@ static void ppp_cp_parse_cr(struct net_device *dev, u16 pid, u8 id,
 				}
 				break;
 			case LCP_OPTION_MAGIC:
+				if (len < 6)
+					goto err_out;
 				if (opt[1] != 6 || (!opt[2] && !opt[3] &&
 						    !opt[4] && !opt[5]))
 					break; /* reject invalid magic number */
@@ -424,6 +425,11 @@ static void ppp_cp_parse_cr(struct net_device *dev, u16 pid, u8 id,
 		ppp_cp_event(dev, pid, RCR_GOOD, CP_CONF_ACK, id, req_len, data);
 
 	kfree(out);
+	return;
+
+err_out:
+	dev->stats.rx_errors++;
+	kfree(out);
 }
 
 static int ppp_rx(struct sk_buff *skb)
-- 
2.26.2


From 63cce738578162b590af5d13dc10bfaf06834420 Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Tue, 8 Sep 2020 14:09:34 -0700
Subject: [PATCH 08/36] ip: fix tos reflection in ack and reset packets

[ Upstream commit ba9e04a7ddf4f22a10e05bf9403db6b97743c7bf ]

Currently, in tcp_v4_reqsk_send_ack() and tcp_v4_send_reset(), we
echo the TOS value of the received packets in the response.
However, we do not want to echo the lower 2 ECN bits in accordance
with RFC 3168 6.1.5 robustness principles.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")

Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_output.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index b36c4a3159e5..079dcf9f0c56 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -74,6 +74,7 @@
 #include <net/icmp.h>
 #include <net/checksum.h>
 #include <net/inetpeer.h>
+#include <net/inet_ecn.h>
 #include <net/lwtunnel.h>
 #include <linux/bpf-cgroup.h>
 #include <linux/igmp.h>
@@ -1699,7 +1700,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 	if (IS_ERR(rt))
 		return;
 
-	inet_sk(sk)->tos = arg->tos;
+	inet_sk(sk)->tos = arg->tos & ~INET_ECN_MASK;
 
 	sk->sk_protocol = ip_hdr(skb)->protocol;
 	sk->sk_bound_dev_if = arg->bound_dev_if;
-- 
2.26.2


From 709f01911afd3fe790179c34497ea21b295a3023 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Sun, 13 Sep 2020 12:43:39 -0600
Subject: [PATCH 09/36] ipv4: Initialize flowi4_multipath_hash in data path

[ Upstream commit 1869e226a7b3ef75b4f70ede2f1b7229f7157fa4 ]

flowi4_multipath_hash was added by the commit referenced below for
tunnels. Unfortunately, the patch did not initialize the new field
for several fast path lookups that do not initialize the entire flow
struct to 0. Fix those locations. Currently, flowi4_multipath_hash
is random garbage and affects the hash value computed by
fib_multipath_hash for multipath selection.

Fixes: 24ba14406c5c ("route: Add multipath_hash in flowi_common to make user-define hash")
Signed-off-by: David Ahern <dsahern@gmail.com>
Cc: wenxu <wenxu@ucloud.cn>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow.h      | 1 +
 net/core/filter.c       | 1 +
 net/ipv4/fib_frontend.c | 1 +
 net/ipv4/route.c        | 1 +
 4 files changed, 4 insertions(+)

diff --git a/include/net/flow.h b/include/net/flow.h
index a50fb77a0b27..d058e63fb59a 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -116,6 +116,7 @@ static inline void flowi4_init_output(struct flowi4 *fl4, int oif,
 	fl4->saddr = saddr;
 	fl4->fl4_dport = dport;
 	fl4->fl4_sport = sport;
+	fl4->flowi4_multipath_hash = 0;
 }
 
 /* Reset some input parameters after previous lookup */
diff --git a/net/core/filter.c b/net/core/filter.c
index 5c490d473df1..cf2a68513bfd 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4650,6 +4650,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	fl4.saddr = params->ipv4_src;
 	fl4.fl4_sport = params->sport;
 	fl4.fl4_dport = params->dport;
+	fl4.flowi4_multipath_hash = 0;
 
 	if (flags & BPF_FIB_LOOKUP_DIRECT) {
 		u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 2b0521feadaa..0a8220d30c99 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -372,6 +372,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 	fl4.flowi4_tun_key.tun_id = 0;
 	fl4.flowi4_flags = 0;
 	fl4.flowi4_uid = sock_net_uid(net, NULL);
+	fl4.flowi4_multipath_hash = 0;
 
 	no_addr = idev->ifa_list == NULL;
 
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index b3a8d32f7d8d..be004d59f3de 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2104,6 +2104,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	fl4.daddr = daddr;
 	fl4.saddr = saddr;
 	fl4.flowi4_uid = sock_net_uid(net, NULL);
+	fl4.flowi4_multipath_hash = 0;
 
 	if (fib4_rules_early_flow_dissect(net, skb, &fl4, &_flkeys)) {
 		flkeys = &_flkeys;
-- 
2.26.2


From 77cbc46aac9db19554f996722d8d9afc3828ddce Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@kernel.org>
Date: Mon, 14 Sep 2020 21:03:54 -0600
Subject: [PATCH 10/36] ipv4: Update exception handling for multipath routes
 via same device

[ Upstream commit 2fbc6e89b2f1403189e624cabaf73e189c5e50c6 ]

Kfir reported that pmtu exceptions are not created properly for
deployments where multipath routes use the same device.

After some digging I see 2 compounding problems:
1. ip_route_output_key_hash_rcu is updating the flowi4_oif *after*
   the route lookup. This is the second use case where this has
   been a problem (the first is related to use of vti devices with
   VRF). I can not find any reason for the oif to be changed after the
   lookup; the code goes back to the start of git. It does not seem
   logical so remove it.

2. fib_lookups for exceptions do not call fib_select_path to handle
   multipath route selection based on the hash.

The end result is that the fib_lookup used to add the exception
always creates it based using the first leg of the route.

An example topology showing the problem:

                 |  host1
             +------+
             | eth0 |  .209
             +------+
                 |
             +------+
     switch  | br0  |
             +------+
                 |
       +---------+---------+
       | host2             |  host3
   +------+             +------+
   | eth0 | .250        | eth0 | 192.168.252.252
   +------+             +------+

   +-----+             +-----+
   | vti | .2          | vti | 192.168.247.3
   +-----+             +-----+
       \                  /
 =================================
 tunnels
         192.168.247.1/24

for h in host1 host2 host3; do
        ip netns add ${h}
        ip -netns ${h} link set lo up
        ip netns exec ${h} sysctl -wq net.ipv4.ip_forward=1
done

ip netns add switch
ip -netns switch li set lo up
ip -netns switch link add br0 type bridge stp 0
ip -netns switch link set br0 up

for n in 1 2 3; do
        ip -netns switch link add eth-sw type veth peer name eth-h${n}
        ip -netns switch li set eth-h${n} master br0 up
        ip -netns switch li set eth-sw netns host${n} name eth0
done

ip -netns host1 addr add 192.168.252.209/24 dev eth0
ip -netns host1 link set dev eth0 up
ip -netns host1 route add 192.168.247.0/24 \
        nexthop via 192.168.252.250 dev eth0 nexthop via 192.168.252.252 dev eth0

ip -netns host2 addr add 192.168.252.250/24 dev eth0
ip -netns host2 link set dev eth0 up

ip -netns host2 addr add 192.168.252.252/24 dev eth0
ip -netns host3 link set dev eth0 up

ip netns add tunnel
ip -netns tunnel li set lo up
ip -netns tunnel li add br0 type bridge
ip -netns tunnel li set br0 up
for n in $(seq 11 20); do
        ip -netns tunnel addr add dev br0 192.168.247.${n}/24
done

for n in 2 3
do
        ip -netns tunnel link add vti${n} type veth peer name eth${n}
        ip -netns tunnel link set eth${n} mtu 1360 master br0 up
        ip -netns tunnel link set vti${n} netns host${n} mtu 1360 up
        ip -netns host${n} addr add dev vti${n} 192.168.247.${n}/24
done
ip -netns tunnel ro add default nexthop via 192.168.247.2 nexthop via 192.168.247.3

ip netns exec host1 ping -M do -s 1400 -c3 -I 192.168.252.209 192.168.247.11
ip netns exec host1 ping -M do -s 1400 -c3 -I 192.168.252.209 192.168.247.15
ip -netns host1 ro ls cache

Before this patch the cache always shows exceptions against the first
leg in the multipath route; 192.168.252.250 per this example. Since the
hash has an initial random seed, you may need to vary the final octet
more than what is listed. In my tests, using addresses between 11 and 19
usually found 1 that used both legs.

With this patch, the cache will have exceptions for both legs.

Fixes: 4895c771c7f0 ("ipv4: Add FIB nexthop exceptions")
Reported-by: Kfir Itzhak <mastertheknife@gmail.com>
Signed-off-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index be004d59f3de..aa77f989ba81 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -785,8 +785,10 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
 			neigh_event_send(n, NULL);
 		} else {
 			if (fib_lookup(net, fl4, &res, 0) == 0) {
-				struct fib_nh_common *nhc = FIB_RES_NHC(res);
+				struct fib_nh_common *nhc;
 
+				fib_select_path(net, &res, fl4, skb);
+				nhc = FIB_RES_NHC(res);
 				update_or_create_fnhe(nhc, fl4->daddr, new_gw,
 						0, false,
 						jiffies + ip_rt_gc_timeout);
@@ -1012,6 +1014,7 @@ out:	kfree_skb(skb);
 static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
 {
 	struct dst_entry *dst = &rt->dst;
+	struct net *net = dev_net(dst->dev);
 	u32 old_mtu = ipv4_mtu(dst);
 	struct fib_result res;
 	bool lock = false;
@@ -1032,9 +1035,11 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
 		return;
 
 	rcu_read_lock();
-	if (fib_lookup(dev_net(dst->dev), fl4, &res, 0) == 0) {
-		struct fib_nh_common *nhc = FIB_RES_NHC(res);
+	if (fib_lookup(net, fl4, &res, 0) == 0) {
+		struct fib_nh_common *nhc;
 
+		fib_select_path(net, &res, fl4, NULL);
+		nhc = FIB_RES_NHC(res);
 		update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock,
 				      jiffies + ip_rt_mtu_expires);
 	}
@@ -2626,8 +2631,6 @@ struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4,
 	fib_select_path(net, res, fl4, skb);
 
 	dev_out = FIB_RES_DEV(*res);
-	fl4->flowi4_oif = dev_out->ifindex;
-
 
 make_route:
 	rth = __mkroute_output(res, fl4, orig_oif, dev_out, flags);
-- 
2.26.2


From d71da5704c41992a9b2b37c6c24dc65df24eb103 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 8 Sep 2020 01:20:23 -0700
Subject: [PATCH 11/36] ipv6: avoid lockdep issue in fib6_del()

[ Upstream commit 843d926b003ea692468c8cc5bea1f9f58dfa8c75 ]

syzbot reported twice a lockdep issue in fib6_del() [1]
which I think is caused by net->ipv6.fib6_null_entry
having a NULL fib6_table pointer.

fib6_del() already checks for fib6_null_entry special
case, we only need to return earlier.

Bug seems to occur very rarely, I have thus chosen
a 'bug origin' that makes backports not too complex.

[1]
WARNING: suspicious RCU usage
5.9.0-rc4-syzkaller #0 Not tainted
-----------------------------
net/ipv6/ip6_fib.c:1996 suspicious rcu_dereference_protected() usage!

other info that might help us debug this:

rcu_scheduler_active = 2, debug_locks = 1
4 locks held by syz-executor.5/8095:
 #0: ffffffff8a7ea708 (rtnl_mutex){+.+.}-{3:3}, at: ppp_release+0x178/0x240 drivers/net/ppp/ppp_generic.c:401
 #1: ffff88804c422dd8 (&net->ipv6.fib6_gc_lock){+.-.}-{2:2}, at: spin_trylock_bh include/linux/spinlock.h:414 [inline]
 #1: ffff88804c422dd8 (&net->ipv6.fib6_gc_lock){+.-.}-{2:2}, at: fib6_run_gc+0x21b/0x2d0 net/ipv6/ip6_fib.c:2312
 #2: ffffffff89bd6a40 (rcu_read_lock){....}-{1:2}, at: __fib6_clean_all+0x0/0x290 net/ipv6/ip6_fib.c:2613
 #3: ffff8880a82e6430 (&tb->tb6_lock){+.-.}-{2:2}, at: spin_lock_bh include/linux/spinlock.h:359 [inline]
 #3: ffff8880a82e6430 (&tb->tb6_lock){+.-.}-{2:2}, at: __fib6_clean_all+0x107/0x290 net/ipv6/ip6_fib.c:2245

stack backtrace:
CPU: 1 PID: 8095 Comm: syz-executor.5 Not tainted 5.9.0-rc4-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x198/0x1fd lib/dump_stack.c:118
 fib6_del+0x12b4/0x1630 net/ipv6/ip6_fib.c:1996
 fib6_clean_node+0x39b/0x570 net/ipv6/ip6_fib.c:2180
 fib6_walk_continue+0x4aa/0x8e0 net/ipv6/ip6_fib.c:2102
 fib6_walk+0x182/0x370 net/ipv6/ip6_fib.c:2150
 fib6_clean_tree+0xdb/0x120 net/ipv6/ip6_fib.c:2230
 __fib6_clean_all+0x120/0x290 net/ipv6/ip6_fib.c:2246
 fib6_clean_all net/ipv6/ip6_fib.c:2257 [inline]
 fib6_run_gc+0x113/0x2d0 net/ipv6/ip6_fib.c:2320
 ndisc_netdev_event+0x217/0x350 net/ipv6/ndisc.c:1805
 notifier_call_chain+0xb5/0x200 kernel/notifier.c:83
 call_netdevice_notifiers_info+0xb5/0x130 net/core/dev.c:2033
 call_netdevice_notifiers_extack net/core/dev.c:2045 [inline]
 call_netdevice_notifiers net/core/dev.c:2059 [inline]
 dev_close_many+0x30b/0x650 net/core/dev.c:1634
 rollback_registered_many+0x3a8/0x1210 net/core/dev.c:9261
 rollback_registered net/core/dev.c:9329 [inline]
 unregister_netdevice_queue+0x2dd/0x570 net/core/dev.c:10410
 unregister_netdevice include/linux/netdevice.h:2774 [inline]
 ppp_release+0x216/0x240 drivers/net/ppp/ppp_generic.c:403
 __fput+0x285/0x920 fs/file_table.c:281
 task_work_run+0xdd/0x190 kernel/task_work.c:141
 tracehook_notify_resume include/linux/tracehook.h:188 [inline]
 exit_to_user_mode_loop kernel/entry/common.c:163 [inline]
 exit_to_user_mode_prepare+0x1e1/0x200 kernel/entry/common.c:190
 syscall_exit_to_user_mode+0x7e/0x2e0 kernel/entry/common.c:265
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 421842edeaf6 ("net/ipv6: Add fib6_null_entry")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: David Ahern <dsahern@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_fib.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 7a0c877ca306..96d80e50bf35 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1896,14 +1896,19 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
 /* Need to own table->tb6_lock */
 int fib6_del(struct fib6_info *rt, struct nl_info *info)
 {
-	struct fib6_node *fn = rcu_dereference_protected(rt->fib6_node,
-				    lockdep_is_held(&rt->fib6_table->tb6_lock));
-	struct fib6_table *table = rt->fib6_table;
 	struct net *net = info->nl_net;
 	struct fib6_info __rcu **rtp;
 	struct fib6_info __rcu **rtp_next;
+	struct fib6_table *table;
+	struct fib6_node *fn;
+
+	if (rt == net->ipv6.fib6_null_entry)
+		return -ENOENT;
 
-	if (!fn || rt == net->ipv6.fib6_null_entry)
+	table = rt->fib6_table;
+	fn = rcu_dereference_protected(rt->fib6_node,
+				       lockdep_is_held(&table->tb6_lock));
+	if (!fn)
 		return -ENOENT;
 
 	WARN_ON(!(fn->fn_flags & RTN_RTINFO));
-- 
2.26.2


From 9112e39a99c13189fe583e5592570d940d8c55bc Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Tue, 22 Sep 2020 01:07:09 +0300
Subject: [PATCH 12/36] net: bridge: br_vlan_get_pvid_rcu() should dereference
 the VLAN group under RCU

[ Upstream commit 99f62a746066fa436aa15d4606a538569540db08 ]

When calling the RCU brother of br_vlan_get_pvid(), lockdep warns:

=============================
WARNING: suspicious RCU usage
5.9.0-rc3-01631-g13c17acb8e38-dirty #814 Not tainted
-----------------------------
net/bridge/br_private.h:1054 suspicious rcu_dereference_protected() usage!

Call trace:
 lockdep_rcu_suspicious+0xd4/0xf8
 __br_vlan_get_pvid+0xc0/0x100
 br_vlan_get_pvid_rcu+0x78/0x108

The warning is because br_vlan_get_pvid_rcu() calls nbp_vlan_group()
which calls rtnl_dereference() instead of rcu_dereference(). In turn,
rtnl_dereference() calls rcu_dereference_protected() which assumes
operation under an RCU write-side critical section, which obviously is
not the case here. So, when the incorrect primitive is used to access
the RCU-protected VLAN group pointer, READ_ONCE() is not used, which may
cause various unexpected problems.

I'm sad to say that br_vlan_get_pvid() and br_vlan_get_pvid_rcu() cannot
share the same implementation. So fix the bug by splitting the 2
functions, and making br_vlan_get_pvid_rcu() retrieve the VLAN groups
under proper locking annotations.

Fixes: 7582f5b70f9a ("bridge: add br_vlan_get_pvid_rcu()")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_vlan.c | 27 +++++++++++++++++----------
 1 file changed, 17 insertions(+), 10 deletions(-)

diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index bb98984cd27d..48413b5eb61f 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -1229,11 +1229,13 @@ void br_vlan_get_stats(const struct net_bridge_vlan *v,
 	}
 }
 
-static int __br_vlan_get_pvid(const struct net_device *dev,
-			      struct net_bridge_port *p, u16 *p_pvid)
+int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid)
 {
 	struct net_bridge_vlan_group *vg;
+	struct net_bridge_port *p;
 
+	ASSERT_RTNL();
+	p = br_port_get_check_rtnl(dev);
 	if (p)
 		vg = nbp_vlan_group(p);
 	else if (netif_is_bridge_master(dev))
@@ -1244,18 +1246,23 @@ static int __br_vlan_get_pvid(const struct net_device *dev,
 	*p_pvid = br_get_pvid(vg);
 	return 0;
 }
-
-int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid)
-{
-	ASSERT_RTNL();
-
-	return __br_vlan_get_pvid(dev, br_port_get_check_rtnl(dev), p_pvid);
-}
 EXPORT_SYMBOL_GPL(br_vlan_get_pvid);
 
 int br_vlan_get_pvid_rcu(const struct net_device *dev, u16 *p_pvid)
 {
-	return __br_vlan_get_pvid(dev, br_port_get_check_rcu(dev), p_pvid);
+	struct net_bridge_vlan_group *vg;
+	struct net_bridge_port *p;
+
+	p = br_port_get_check_rcu(dev);
+	if (p)
+		vg = nbp_vlan_group_rcu(p);
+	else if (netif_is_bridge_master(dev))
+		vg = br_vlan_group_rcu(netdev_priv(dev));
+	else
+		return -EINVAL;
+
+	*p_pvid = br_get_pvid(vg);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(br_vlan_get_pvid_rcu);
 
-- 
2.26.2


From e542a1aa2eb6602b4a06b358590cb7f91d876847 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 10 Sep 2020 14:09:05 +0200
Subject: [PATCH 13/36] net: DCB: Validate DCB_ATTR_DCB_BUFFER argument

[ Upstream commit 297e77e53eadb332d5062913447b104a772dc33b ]

The parameter passed via DCB_ATTR_DCB_BUFFER is a struct dcbnl_buffer. The
field prio2buffer is an array of IEEE_8021Q_MAX_PRIORITIES bytes, where
each value is a number of a buffer to direct that priority's traffic to.
That value is however never validated to lie within the bounds set by
DCBX_MAX_BUFFERS. The only driver that currently implements the callback is
mlx5 (maintainers CCd), and that does not do any validation either, in
particual allowing incorrect configuration if the prio2buffer value does
not fit into 4 bits.

Instead of offloading the need to validate the buffer index to drivers, do
it right there in core, and bounce the request if the value is too large.

CC: Parav Pandit <parav@nvidia.com>
CC: Saeed Mahameed <saeedm@nvidia.com>
Fixes: e549f6f9c098 ("net/dcb: Add dcbnl buffer attribute")
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dcb/dcbnl.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index d2a4553bcf39..0fd1c2aa1361 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -1426,6 +1426,7 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh,
 {
 	const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops;
 	struct nlattr *ieee[DCB_ATTR_IEEE_MAX + 1];
+	int prio;
 	int err;
 
 	if (!ops)
@@ -1475,6 +1476,13 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh,
 		struct dcbnl_buffer *buffer =
 			nla_data(ieee[DCB_ATTR_DCB_BUFFER]);
 
+		for (prio = 0; prio < ARRAY_SIZE(buffer->prio2buffer); prio++) {
+			if (buffer->prio2buffer[prio] >= DCBX_MAX_BUFFERS) {
+				err = -EINVAL;
+				goto err;
+			}
+		}
+
 		err = ops->dcbnl_setbuffer(netdev, buffer);
 		if (err)
 			goto err;
-- 
2.26.2


From b59c95cae6829f4e1976ec3262802619c9af22b1 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Sat, 5 Sep 2020 12:32:33 +0200
Subject: [PATCH 14/36] net: dsa: rtl8366: Properly clear member config

[ Upstream commit 4ddcaf1ebb5e4e99240f29d531ee69d4244fe416 ]

When removing a port from a VLAN we are just erasing the
member config for the VLAN, which is wrong: other ports
can be using it.

Just mask off the port and only zero out the rest of the
member config once ports using of the VLAN are removed
from it.

Reported-by: Florian Fainelli <f.fainelli@gmail.com>
Fixes: d8652956cf37 ("net: dsa: realtek-smi: Add Realtek SMI driver")
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/rtl8366.c | 20 +++++++++++++-------
 1 file changed, 13 insertions(+), 7 deletions(-)

diff --git a/drivers/net/dsa/rtl8366.c b/drivers/net/dsa/rtl8366.c
index 1368816abaed..99cdb2f18fa2 100644
--- a/drivers/net/dsa/rtl8366.c
+++ b/drivers/net/dsa/rtl8366.c
@@ -452,13 +452,19 @@ int rtl8366_vlan_del(struct dsa_switch *ds, int port,
 				return ret;
 
 			if (vid == vlanmc.vid) {
-				/* clear VLAN member configurations */
-				vlanmc.vid = 0;
-				vlanmc.priority = 0;
-				vlanmc.member = 0;
-				vlanmc.untag = 0;
-				vlanmc.fid = 0;
-
+				/* Remove this port from the VLAN */
+				vlanmc.member &= ~BIT(port);
+				vlanmc.untag &= ~BIT(port);
+				/*
+				 * If no ports are members of this VLAN
+				 * anymore then clear the whole member
+				 * config so it can be reused.
+				 */
+				if (!vlanmc.member && vlanmc.untag) {
+					vlanmc.vid = 0;
+					vlanmc.priority = 0;
+					vlanmc.fid = 0;
+				}
 				ret = smi->ops->set_vlan_mc(smi, i, &vlanmc);
 				if (ret) {
 					dev_err(smi->dev,
-- 
2.26.2


From 5fb91cebc32635c82f925c7b753b0cedb3c0f306 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 10 Sep 2020 14:01:26 +0300
Subject: [PATCH 15/36] net: Fix bridge enslavement failure

[ Upstream commit e1b9efe6baebe79019a2183176686a0e709388ae ]

When a netdev is enslaved to a bridge, its parent identifier is queried.
This is done so that packets that were already forwarded in hardware
will not be forwarded again by the bridge device between netdevs
belonging to the same hardware instance.

The operation fails when the netdev is an upper of netdevs with
different parent identifiers.

Instead of failing the enslavement, have dev_get_port_parent_id() return
'-EOPNOTSUPP' which will signal the bridge to skip the query operation.
Other callers of the function are not affected by this change.

Fixes: 7e1146e8c10c ("net: devlink: introduce devlink_compat_switch_id_get() helper")
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reported-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Nikolay Aleksandrov <nikolay@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index cdc1c3a144e1..20c7fd7b8b4b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8241,7 +8241,7 @@ int dev_get_port_parent_id(struct net_device *dev,
 		if (!first.id_len)
 			first = *ppid;
 		else if (memcmp(&first, ppid, sizeof(*ppid)))
-			return -ENODATA;
+			return -EOPNOTSUPP;
 	}
 
 	return err;
-- 
2.26.2


From 0abc77d84ad1492b4c251058c4bda4554f08b26c Mon Sep 17 00:00:00 2001
From: Necip Fazil Yildiran <fazilyildiran@gmail.com>
Date: Thu, 17 Sep 2020 19:46:43 +0300
Subject: [PATCH 16/36] net: ipv6: fix kconfig dependency warning for
 IPV6_SEG6_HMAC

[ Upstream commit db7cd91a4be15e1485d6b58c6afc8761c59c4efb ]

When IPV6_SEG6_HMAC is enabled and CRYPTO is disabled, it results in the
following Kbuild warning:

WARNING: unmet direct dependencies detected for CRYPTO_HMAC
  Depends on [n]: CRYPTO [=n]
  Selected by [y]:
  - IPV6_SEG6_HMAC [=y] && NET [=y] && INET [=y] && IPV6 [=y]

WARNING: unmet direct dependencies detected for CRYPTO_SHA1
  Depends on [n]: CRYPTO [=n]
  Selected by [y]:
  - IPV6_SEG6_HMAC [=y] && NET [=y] && INET [=y] && IPV6 [=y]

WARNING: unmet direct dependencies detected for CRYPTO_SHA256
  Depends on [n]: CRYPTO [=n]
  Selected by [y]:
  - IPV6_SEG6_HMAC [=y] && NET [=y] && INET [=y] && IPV6 [=y]

The reason is that IPV6_SEG6_HMAC selects CRYPTO_HMAC, CRYPTO_SHA1, and
CRYPTO_SHA256 without depending on or selecting CRYPTO while those configs
are subordinate to CRYPTO.

Honor the kconfig menu hierarchy to remove kconfig dependency warnings.

Fixes: bf355b8d2c30 ("ipv6: sr: add core files for SR HMAC support")
Signed-off-by: Necip Fazil Yildiran <fazilyildiran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index ae1344e4cec5..dce14470b15a 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -289,6 +289,7 @@ config IPV6_SEG6_LWTUNNEL
 config IPV6_SEG6_HMAC
 	bool "IPv6: Segment Routing HMAC support"
 	depends on IPV6
+	select CRYPTO
 	select CRYPTO_HMAC
 	select CRYPTO_SHA1
 	select CRYPTO_SHA256
-- 
2.26.2


From 45008516b99e0d5f63243c13491224246e22e50d Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@nvidia.com>
Date: Mon, 31 Aug 2020 20:50:42 +0300
Subject: [PATCH 17/36] net/mlx5: Fix FTE cleanup

[ Upstream commit cefc23554fc259114e78a7b0908aac4610ee18eb ]

Currently, when an FTE is allocated, its refcount is decreased to 0
with the purpose it will not be a stand alone steering object and every
rule (destination) of the FTE would increase the refcount.
When mlx5_cleanup_fs is called while not all rules were deleted by the
steering users, it hit refcount underflow on the FTE once clean_tree
calls to tree_remove_node after the deleted rules already decreased
the refcount to 0.

FTE is no longer destroyed implicitly when the last rule (destination)
is deleted. mlx5_del_flow_rules avoids it by increasing the refcount on
the FTE and destroy it explicitly after all rules were deleted. So we
can avoid the refcount underflow by making FTE as stand alone object.
In addition need to set del_hw_func to FTE so the HW object will be
destroyed when the FTE is deleted from the cleanup_tree flow.

refcount_t: underflow; use-after-free.
WARNING: CPU: 2 PID: 15715 at lib/refcount.c:28 refcount_warn_saturate+0xd9/0xe0
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
Call Trace:
 tree_put_node+0xf2/0x140 [mlx5_core]
 clean_tree+0x4e/0xf0 [mlx5_core]
 clean_tree+0x4e/0xf0 [mlx5_core]
 clean_tree+0x4e/0xf0 [mlx5_core]
 clean_tree+0x5f/0xf0 [mlx5_core]
 clean_tree+0x4e/0xf0 [mlx5_core]
 clean_tree+0x5f/0xf0 [mlx5_core]
 mlx5_cleanup_fs+0x26/0x270 [mlx5_core]
 mlx5_unload+0x2e/0xa0 [mlx5_core]
 mlx5_unload_one+0x51/0x120 [mlx5_core]
 mlx5_devlink_reload_down+0x51/0x90 [mlx5_core]
 devlink_reload+0x39/0x120
 ? devlink_nl_cmd_reload+0x43/0x220
 genl_rcv_msg+0x1e4/0x420
 ? genl_family_rcv_msg_attrs_parse+0x100/0x100
 netlink_rcv_skb+0x47/0x110
 genl_rcv+0x24/0x40
 netlink_unicast+0x217/0x2f0
 netlink_sendmsg+0x30f/0x430
 sock_sendmsg+0x30/0x40
 __sys_sendto+0x10e/0x140
 ? handle_mm_fault+0xc4/0x1f0
 ? do_page_fault+0x33f/0x630
 __x64_sys_sendto+0x24/0x30
 do_syscall_64+0x48/0x130
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 718ce4d601db ("net/mlx5: Consolidate update FTE for all removal changes")
Fixes: bd71b08ec2ee ("net/mlx5: Support multiple updates of steering rules in parallel")
Signed-off-by: Maor Gottlieb <maorg@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index b66e5b6eecd9..9ac2f52187ea 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -629,7 +629,7 @@ static struct fs_fte *alloc_fte(struct mlx5_flow_table *ft,
 	fte->action = *flow_act;
 	fte->flow_context = spec->flow_context;
 
-	tree_init_node(&fte->node, NULL, del_sw_fte);
+	tree_init_node(&fte->node, del_hw_fte, del_sw_fte);
 
 	return fte;
 }
@@ -1737,7 +1737,6 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft,
 		up_write_ref_node(&g->node, false);
 		rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte);
 		up_write_ref_node(&fte->node, false);
-		tree_put_node(&fte->node, false);
 		return rule;
 	}
 	rule = ERR_PTR(-ENOENT);
@@ -1837,7 +1836,6 @@ _mlx5_add_flow_rules(struct mlx5_flow_table *ft,
 	up_write_ref_node(&g->node, false);
 	rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte);
 	up_write_ref_node(&fte->node, false);
-	tree_put_node(&fte->node, false);
 	tree_put_node(&g->node, false);
 	return rule;
 
@@ -1930,7 +1928,9 @@ void mlx5_del_flow_rules(struct mlx5_flow_handle *handle)
 		up_write_ref_node(&fte->node, false);
 	} else {
 		del_hw_fte(&fte->node);
-		up_write(&fte->node.lock);
+		/* Avoid double call to del_hw_fte */
+		fte->node.del_hw_func = NULL;
+		up_write_ref_node(&fte->node, false);
 		tree_put_node(&fte->node, false);
 	}
 	kfree(handle);
-- 
2.26.2


From 77113d7462b2d4b2103169f27567a58213f68a78 Mon Sep 17 00:00:00 2001
From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Tue, 8 Sep 2020 19:02:34 +0800
Subject: [PATCH 18/36] net: sch_generic: aviod concurrent reset and enqueue op
 for lockless qdisc

[ Upstream commit 2fb541c862c987d02dfdf28f1545016deecfa0d5 ]

Currently there is concurrent reset and enqueue operation for the
same lockless qdisc when there is no lock to synchronize the
q->enqueue() in __dev_xmit_skb() with the qdisc reset operation in
qdisc_deactivate() called by dev_deactivate_queue(), which may cause
out-of-bounds access for priv->ring[] in hns3 driver if user has
requested a smaller queue num when __dev_xmit_skb() still enqueue a
skb with a larger queue_mapping after the corresponding qdisc is
reset, and call hns3_nic_net_xmit() with that skb later.

Reused the existing synchronize_net() in dev_deactivate_many() to
make sure skb with larger queue_mapping enqueued to old qdisc(which
is saved in dev_queue->qdisc_sleeping) will always be reset when
dev_reset_queue() is called.

Fixes: 6b3ba9146fe6 ("net: sched: allow qdiscs to handle locking")
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_generic.c | 49 +++++++++++++++++++++++++++--------------
 1 file changed, 33 insertions(+), 16 deletions(-)

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 896c9037155a..0e275e11f511 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -1126,27 +1126,36 @@ static void dev_deactivate_queue(struct net_device *dev,
 				 struct netdev_queue *dev_queue,
 				 void *_qdisc_default)
 {
-	struct Qdisc *qdisc_default = _qdisc_default;
-	struct Qdisc *qdisc;
+	struct Qdisc *qdisc = rtnl_dereference(dev_queue->qdisc);
 
-	qdisc = rtnl_dereference(dev_queue->qdisc);
 	if (qdisc) {
-		bool nolock = qdisc->flags & TCQ_F_NOLOCK;
-
-		if (nolock)
-			spin_lock_bh(&qdisc->seqlock);
-		spin_lock_bh(qdisc_lock(qdisc));
-
 		if (!(qdisc->flags & TCQ_F_BUILTIN))
 			set_bit(__QDISC_STATE_DEACTIVATED, &qdisc->state);
+	}
+}
 
-		rcu_assign_pointer(dev_queue->qdisc, qdisc_default);
-		qdisc_reset(qdisc);
+static void dev_reset_queue(struct net_device *dev,
+			    struct netdev_queue *dev_queue,
+			    void *_unused)
+{
+	struct Qdisc *qdisc;
+	bool nolock;
 
-		spin_unlock_bh(qdisc_lock(qdisc));
-		if (nolock)
-			spin_unlock_bh(&qdisc->seqlock);
-	}
+	qdisc = dev_queue->qdisc_sleeping;
+	if (!qdisc)
+		return;
+
+	nolock = qdisc->flags & TCQ_F_NOLOCK;
+
+	if (nolock)
+		spin_lock_bh(&qdisc->seqlock);
+	spin_lock_bh(qdisc_lock(qdisc));
+
+	qdisc_reset(qdisc);
+
+	spin_unlock_bh(qdisc_lock(qdisc));
+	if (nolock)
+		spin_unlock_bh(&qdisc->seqlock);
 }
 
 static bool some_qdisc_is_busy(struct net_device *dev)
@@ -1207,12 +1216,20 @@ void dev_deactivate_many(struct list_head *head)
 		dev_watchdog_down(dev);
 	}
 
-	/* Wait for outstanding qdisc-less dev_queue_xmit calls.
+	/* Wait for outstanding qdisc-less dev_queue_xmit calls or
+	 * outstanding qdisc enqueuing calls.
 	 * This is avoided if all devices are in dismantle phase :
 	 * Caller will call synchronize_net() for us
 	 */
 	synchronize_net();
 
+	list_for_each_entry(dev, head, close_list) {
+		netdev_for_each_tx_queue(dev, dev_reset_queue, NULL);
+
+		if (dev_ingress_queue(dev))
+			dev_reset_queue(dev, dev_ingress_queue(dev), NULL);
+	}
+
 	/* Wait for outstanding qdisc_run calls. */
 	list_for_each_entry(dev, head, close_list) {
 		while (some_qdisc_is_busy(dev))
-- 
2.26.2


From 72f2f61eacd1b841e800bcf4195f9fe1ed3ea07b Mon Sep 17 00:00:00 2001
From: Henry Ptasinski <hptasinski@google.com>
Date: Sat, 19 Sep 2020 00:12:11 +0000
Subject: [PATCH 19/36] net: sctp: Fix IPv6 ancestor_size calc in
 sctp_copy_descendant

[ Upstream commit fe81d9f6182d1160e625894eecb3d7ff0222cac5 ]

When calculating ancestor_size with IPv6 enabled, simply using
sizeof(struct ipv6_pinfo) doesn't account for extra bytes needed for
alignment in the struct sctp6_sock. On x86, there aren't any extra
bytes, but on ARM the ipv6_pinfo structure is aligned on an 8-byte
boundary so there were 4 pad bytes that were omitted from the
ancestor_size calculation.  This would lead to corruption of the
pd_lobby pointers, causing an oops when trying to free the sctp
structure on socket close.

Fixes: 636d25d557d1 ("sctp: not copy sctp_sock pd_lobby in sctp_copy_descendant")
Signed-off-by: Henry Ptasinski <hptasinski@google.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/structs.h | 8 +++++---
 net/sctp/socket.c          | 9 +++------
 2 files changed, 8 insertions(+), 9 deletions(-)

diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 2b6f3f13d5bc..3e8f87a3c52f 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -224,12 +224,14 @@ struct sctp_sock {
 		data_ready_signalled:1;
 
 	atomic_t pd_mode;
+
+	/* Fields after this point will be skipped on copies, like on accept
+	 * and peeloff operations
+	 */
+
 	/* Receive to here while partial delivery is in effect. */
 	struct sk_buff_head pd_lobby;
 
-	/* These must be the last fields, as they will skipped on copies,
-	 * like on accept and peeloff operations
-	 */
 	struct list_head auto_asconf_list;
 	int do_auto_asconf;
 };
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 3a11212bb4c0..1fcc13f6073e 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -9337,13 +9337,10 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk,
 static inline void sctp_copy_descendant(struct sock *sk_to,
 					const struct sock *sk_from)
 {
-	int ancestor_size = sizeof(struct inet_sock) +
-			    sizeof(struct sctp_sock) -
-			    offsetof(struct sctp_sock, pd_lobby);
-
-	if (sk_from->sk_family == PF_INET6)
-		ancestor_size += sizeof(struct ipv6_pinfo);
+	size_t ancestor_size = sizeof(struct inet_sock);
 
+	ancestor_size += sk_from->sk_prot->obj_size;
+	ancestor_size -= offsetof(struct sctp_sock, pd_lobby);
 	__inet_sk_copy_descendant(sk_to, sk_from, ancestor_size);
 }
 
-- 
2.26.2


From b597200b55746ddbe59bce6ad6db3e30d8053175 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 17 Sep 2020 10:52:57 -0700
Subject: [PATCH 20/36] nfp: use correct define to return NONE fec

[ Upstream commit 5f6857e808a8bd078296575b417c4b9d160b9779 ]

struct ethtool_fecparam carries bitmasks not bit numbers.
We want to return 1 (NONE), not 0.

Fixes: 0d0870938337 ("nfp: implement ethtool FEC mode settings")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
index 1b840ee47339..17b91ed39369 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
@@ -731,8 +731,8 @@ nfp_port_get_fecparam(struct net_device *netdev,
 	struct nfp_eth_table_port *eth_port;
 	struct nfp_port *port;
 
-	param->active_fec = ETHTOOL_FEC_NONE_BIT;
-	param->fec = ETHTOOL_FEC_NONE_BIT;
+	param->active_fec = ETHTOOL_FEC_NONE;
+	param->fec = ETHTOOL_FEC_NONE;
 
 	port = nfp_port_from_netdev(netdev);
 	eth_port = nfp_port_get_eth_port(port);
-- 
2.26.2


From 86341adb96fa08303dfcb33bdb88f9af0c2fa566 Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Wed, 9 Sep 2020 17:03:11 -0700
Subject: [PATCH 21/36] taprio: Fix allowing too small intervals

[ Upstream commit b5b73b26b3ca34574124ed7ae9c5ba8391a7f176 ]

It's possible that the user specifies an interval that couldn't allow
any packet to be transmitted. This also avoids the issue of the
hrtimer handler starving the other threads because it's running too
often.

The solution is to reject interval sizes that according to the current
link speed wouldn't allow any packet to be transmitted.

Reported-by: syzbot+8267241609ae8c23b248@syzkaller.appspotmail.com
Fixes: 5a781ccbd19e ("tc: Add support for configuring the taprio scheduler")
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_taprio.c | 28 +++++++++++++++++-----------
 1 file changed, 17 insertions(+), 11 deletions(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 6a5086e586ef..2b797a71e9bd 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -777,9 +777,11 @@ static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = {
 	[TCA_TAPRIO_ATTR_TXTIME_DELAY]		     = { .type = NLA_U32 },
 };
 
-static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry,
+static int fill_sched_entry(struct taprio_sched *q, struct nlattr **tb,
+			    struct sched_entry *entry,
 			    struct netlink_ext_ack *extack)
 {
+	int min_duration = length_to_duration(q, ETH_ZLEN);
 	u32 interval = 0;
 
 	if (tb[TCA_TAPRIO_SCHED_ENTRY_CMD])
@@ -794,7 +796,10 @@ static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry,
 		interval = nla_get_u32(
 			tb[TCA_TAPRIO_SCHED_ENTRY_INTERVAL]);
 
-	if (interval == 0) {
+	/* The interval should allow at least the minimum ethernet
+	 * frame to go out.
+	 */
+	if (interval < min_duration) {
 		NL_SET_ERR_MSG(extack, "Invalid interval for schedule entry");
 		return -EINVAL;
 	}
@@ -804,8 +809,9 @@ static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry,
 	return 0;
 }
 
-static int parse_sched_entry(struct nlattr *n, struct sched_entry *entry,
-			     int index, struct netlink_ext_ack *extack)
+static int parse_sched_entry(struct taprio_sched *q, struct nlattr *n,
+			     struct sched_entry *entry, int index,
+			     struct netlink_ext_ack *extack)
 {
 	struct nlattr *tb[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = { };
 	int err;
@@ -819,10 +825,10 @@ static int parse_sched_entry(struct nlattr *n, struct sched_entry *entry,
 
 	entry->index = index;
 
-	return fill_sched_entry(tb, entry, extack);
+	return fill_sched_entry(q, tb, entry, extack);
 }
 
-static int parse_sched_list(struct nlattr *list,
+static int parse_sched_list(struct taprio_sched *q, struct nlattr *list,
 			    struct sched_gate_list *sched,
 			    struct netlink_ext_ack *extack)
 {
@@ -847,7 +853,7 @@ static int parse_sched_list(struct nlattr *list,
 			return -ENOMEM;
 		}
 
-		err = parse_sched_entry(n, entry, i, extack);
+		err = parse_sched_entry(q, n, entry, i, extack);
 		if (err < 0) {
 			kfree(entry);
 			return err;
@@ -862,7 +868,7 @@ static int parse_sched_list(struct nlattr *list,
 	return i;
 }
 
-static int parse_taprio_schedule(struct nlattr **tb,
+static int parse_taprio_schedule(struct taprio_sched *q, struct nlattr **tb,
 				 struct sched_gate_list *new,
 				 struct netlink_ext_ack *extack)
 {
@@ -883,8 +889,8 @@ static int parse_taprio_schedule(struct nlattr **tb,
 		new->cycle_time = nla_get_s64(tb[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME]);
 
 	if (tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST])
-		err = parse_sched_list(
-			tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST], new, extack);
+		err = parse_sched_list(q, tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST],
+				       new, extack);
 	if (err < 0)
 		return err;
 
@@ -1474,7 +1480,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 		goto free_sched;
 	}
 
-	err = parse_taprio_schedule(tb, new_admin, extack);
+	err = parse_taprio_schedule(q, tb, new_admin, extack);
 	if (err < 0)
 		goto free_sched;
 
-- 
2.26.2


From 5729a936734d36ef3105ae8c4b7c0381a6b6121f Mon Sep 17 00:00:00 2001
From: Peilin Ye <yepeilin.cs@gmail.com>
Date: Sun, 13 Sep 2020 04:06:05 -0400
Subject: [PATCH 22/36] tipc: Fix memory leak in tipc_group_create_member()

[ Upstream commit bb3a420d47ab00d7e1e5083286cab15235a96680 ]

tipc_group_add_to_tree() returns silently if `key` matches `nkey` of an
existing node, causing tipc_group_create_member() to leak memory. Let
tipc_group_add_to_tree() return an error in such a case, so that
tipc_group_create_member() can handle it properly.

Fixes: 75da2163dbb6 ("tipc: introduce communication groups")
Reported-and-tested-by: syzbot+f95d90c454864b3b5bc9@syzkaller.appspotmail.com
Cc: Hillf Danton <hdanton@sina.com>
Link: https://syzkaller.appspot.com/bug?id=048390604fe1b60df34150265479202f10e13aff
Signed-off-by: Peilin Ye <yepeilin.cs@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/group.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/net/tipc/group.c b/net/tipc/group.c
index 89257e2a980d..f53871baa42e 100644
--- a/net/tipc/group.c
+++ b/net/tipc/group.c
@@ -273,8 +273,8 @@ static struct tipc_member *tipc_group_find_node(struct tipc_group *grp,
 	return NULL;
 }
 
-static void tipc_group_add_to_tree(struct tipc_group *grp,
-				   struct tipc_member *m)
+static int tipc_group_add_to_tree(struct tipc_group *grp,
+				  struct tipc_member *m)
 {
 	u64 nkey, key = (u64)m->node << 32 | m->port;
 	struct rb_node **n, *parent = NULL;
@@ -291,10 +291,11 @@ static void tipc_group_add_to_tree(struct tipc_group *grp,
 		else if (key > nkey)
 			n = &(*n)->rb_right;
 		else
-			return;
+			return -EEXIST;
 	}
 	rb_link_node(&m->tree_node, parent, n);
 	rb_insert_color(&m->tree_node, &grp->members);
+	return 0;
 }
 
 static struct tipc_member *tipc_group_create_member(struct tipc_group *grp,
@@ -302,6 +303,7 @@ static struct tipc_member *tipc_group_create_member(struct tipc_group *grp,
 						    u32 instance, int state)
 {
 	struct tipc_member *m;
+	int ret;
 
 	m = kzalloc(sizeof(*m), GFP_ATOMIC);
 	if (!m)
@@ -314,8 +316,12 @@ static struct tipc_member *tipc_group_create_member(struct tipc_group *grp,
 	m->port = port;
 	m->instance = instance;
 	m->bc_acked = grp->bc_snd_nxt - 1;
+	ret = tipc_group_add_to_tree(grp, m);
+	if (ret < 0) {
+		kfree(m);
+		return NULL;
+	}
 	grp->member_cnt++;
-	tipc_group_add_to_tree(grp, m);
 	tipc_nlist_add(&grp->dests, m->node);
 	m->state = state;
 	return m;
-- 
2.26.2


From fb53edc8f433adf2a55889e3851ddba4731da0e6 Mon Sep 17 00:00:00 2001
From: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Date: Sat, 5 Sep 2020 15:14:47 +0900
Subject: [PATCH 23/36] tipc: fix shutdown() of connection oriented socket

[ Upstream commit a4b5cc9e10803ecba64a7d54c0f47e4564b4a980 ]

I confirmed that the problem fixed by commit 2a63866c8b51a3f7 ("tipc: fix
shutdown() of connectionless socket") also applies to stream socket.

----------
#include <sys/socket.h>
#include <unistd.h>
#include <sys/wait.h>

int main(int argc, char *argv[])
{
        int fds[2] = { -1, -1 };
        socketpair(PF_TIPC, SOCK_STREAM /* or SOCK_DGRAM */, 0, fds);
        if (fork() == 0)
                _exit(read(fds[0], NULL, 1));
        shutdown(fds[0], SHUT_RDWR); /* This must make read() return. */
        wait(NULL); /* To be woken up by _exit(). */
        return 0;
}
----------

Since shutdown(SHUT_RDWR) should affect all processes sharing that socket,
unconditionally setting sk->sk_shutdown to SHUTDOWN_MASK will be the right
behavior.

Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/socket.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 5318bb6611ab..959155c3a160 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2616,10 +2616,7 @@ static int tipc_shutdown(struct socket *sock, int how)
 
 	trace_tipc_sk_shutdown(sk, NULL, TIPC_DUMP_ALL, " ");
 	__tipc_shutdown(sock, TIPC_CONN_SHUTDOWN);
-	if (tipc_sk_type_connectionless(sk))
-		sk->sk_shutdown = SHUTDOWN_MASK;
-	else
-		sk->sk_shutdown = SEND_SHUTDOWN;
+	sk->sk_shutdown = SHUTDOWN_MASK;
 
 	if (sk->sk_state == TIPC_DISCONNECTING) {
 		/* Discard any unreceived messages */
-- 
2.26.2


From d11ffbfb43278bb688cf6ed782afaa6a37a94761 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 13 Sep 2020 19:37:31 +0800
Subject: [PATCH 24/36] tipc: use skb_unshare() instead in tipc_buf_append()

[ Upstream commit ff48b6222e65ebdba5a403ef1deba6214e749193 ]

In tipc_buf_append() it may change skb's frag_list, and it causes
problems when this skb is cloned. skb_unclone() doesn't really
make this skb's flag_list available to change.

Shuang Li has reported an use-after-free issue because of this
when creating quite a few macvlan dev over the same dev, where
the broadcast packets will be cloned and go up to the stack:

 [ ] BUG: KASAN: use-after-free in pskb_expand_head+0x86d/0xea0
 [ ] Call Trace:
 [ ]  dump_stack+0x7c/0xb0
 [ ]  print_address_description.constprop.7+0x1a/0x220
 [ ]  kasan_report.cold.10+0x37/0x7c
 [ ]  check_memory_region+0x183/0x1e0
 [ ]  pskb_expand_head+0x86d/0xea0
 [ ]  process_backlog+0x1df/0x660
 [ ]  net_rx_action+0x3b4/0xc90
 [ ]
 [ ] Allocated by task 1786:
 [ ]  kmem_cache_alloc+0xbf/0x220
 [ ]  skb_clone+0x10a/0x300
 [ ]  macvlan_broadcast+0x2f6/0x590 [macvlan]
 [ ]  macvlan_process_broadcast+0x37c/0x516 [macvlan]
 [ ]  process_one_work+0x66a/0x1060
 [ ]  worker_thread+0x87/0xb10
 [ ]
 [ ] Freed by task 3253:
 [ ]  kmem_cache_free+0x82/0x2a0
 [ ]  skb_release_data+0x2c3/0x6e0
 [ ]  kfree_skb+0x78/0x1d0
 [ ]  tipc_recvmsg+0x3be/0xa40 [tipc]

So fix it by using skb_unshare() instead, which would create a new
skb for the cloned frag and it'll be safe to change its frag_list.
The similar things were also done in sctp_make_reassembled_event(),
which is using skb_copy().

Reported-by: Shuang Li <shuali@redhat.com>
Fixes: 37e22164a8a3 ("tipc: rename and move message reassembly function")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/msg.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index 922d262e153f..ee4b2261e795 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -140,7 +140,8 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf)
 	if (fragid == FIRST_FRAGMENT) {
 		if (unlikely(head))
 			goto err;
-		if (unlikely(skb_unclone(frag, GFP_ATOMIC)))
+		frag = skb_unshare(frag, GFP_ATOMIC);
+		if (unlikely(!frag))
 			goto err;
 		head = *headbuf = frag;
 		*buf = NULL;
-- 
2.26.2


From 30a015b6e08d58a5d2eddf4c0d624e5052afa943 Mon Sep 17 00:00:00 2001
From: Maor Dickman <maord@mellanox.com>
Date: Wed, 5 Aug 2020 17:56:04 +0300
Subject: [PATCH 25/36] net/mlx5e: Enable adding peer miss rules only if merged
 eswitch is supported

[ Upstream commit 6cec0229ab1959259e71e9a5bbe47c04577950b1 ]

The cited commit creates peer miss group during switchdev mode
initialization in order to handle miss packets correctly while in VF
LAG mode. This is done regardless of FW support of such groups which
could cause rules setups failure later on.

Fix by adding FW capability check before creating peer groups/rule.

Fixes: ac004b832128 ("net/mlx5e: E-Switch, Add peer miss rules")
Signed-off-by: Maor Dickman <maord@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Raed Salem <raeds@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../mellanox/mlx5/core/eswitch_offloads.c     | 52 ++++++++++---------
 1 file changed, 28 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 5acfdea3a75a..7cc80dc4e6d8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -1143,35 +1143,37 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
 	}
 	esw->fdb_table.offloads.send_to_vport_grp = g;
 
-	/* create peer esw miss group */
-	memset(flow_group_in, 0, inlen);
+	if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) {
+		/* create peer esw miss group */
+		memset(flow_group_in, 0, inlen);
 
-	esw_set_flow_group_source_port(esw, flow_group_in);
+		esw_set_flow_group_source_port(esw, flow_group_in);
 
-	if (!mlx5_eswitch_vport_match_metadata_enabled(esw)) {
-		match_criteria = MLX5_ADDR_OF(create_flow_group_in,
-					      flow_group_in,
-					      match_criteria);
+		if (!mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+			match_criteria = MLX5_ADDR_OF(create_flow_group_in,
+						      flow_group_in,
+						      match_criteria);
 
-		MLX5_SET_TO_ONES(fte_match_param, match_criteria,
-				 misc_parameters.source_eswitch_owner_vhca_id);
+			MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+					 misc_parameters.source_eswitch_owner_vhca_id);
 
-		MLX5_SET(create_flow_group_in, flow_group_in,
-			 source_eswitch_owner_vhca_id_valid, 1);
-	}
+			MLX5_SET(create_flow_group_in, flow_group_in,
+				 source_eswitch_owner_vhca_id_valid, 1);
+		}
 
-	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix);
-	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index,
-		 ix + esw->total_vports - 1);
-	ix += esw->total_vports;
+		MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix);
+		MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index,
+			 ix + esw->total_vports - 1);
+		ix += esw->total_vports;
 
-	g = mlx5_create_flow_group(fdb, flow_group_in);
-	if (IS_ERR(g)) {
-		err = PTR_ERR(g);
-		esw_warn(dev, "Failed to create peer miss flow group err(%d)\n", err);
-		goto peer_miss_err;
+		g = mlx5_create_flow_group(fdb, flow_group_in);
+		if (IS_ERR(g)) {
+			err = PTR_ERR(g);
+			esw_warn(dev, "Failed to create peer miss flow group err(%d)\n", err);
+			goto peer_miss_err;
+		}
+		esw->fdb_table.offloads.peer_miss_grp = g;
 	}
-	esw->fdb_table.offloads.peer_miss_grp = g;
 
 	/* create miss group */
 	memset(flow_group_in, 0, inlen);
@@ -1206,7 +1208,8 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
 miss_rule_err:
 	mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp);
 miss_err:
-	mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp);
+	if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
+		mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp);
 peer_miss_err:
 	mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp);
 send_vport_err:
@@ -1229,7 +1232,8 @@ static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw)
 	mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule_multi);
 	mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule_uni);
 	mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp);
-	mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp);
+	if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
+		mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp);
 	mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp);
 
 	mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb);
-- 
2.26.2


From 58d504add1ea500fcca2160a971b61d014fe5178 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Sun, 28 Jun 2020 13:06:06 +0300
Subject: [PATCH 26/36] net/mlx5e: TLS, Do not expose FPGA TLS counter if not
 supported

[ Upstream commit 8f0bcd19b1da3f264223abea985b9462e85a3718 ]

The set of TLS TX global SW counters in mlx5e_tls_sw_stats_desc
is updated from all rings by using atomic ops.
This set of stats is used only in the FPGA TLS use case, not in
the Connect-X TLS one, where regular per-ring counters are used.

Do not expose them in the Connect-X use case, as this would cause
counter duplication. For example, tx_tls_drop_no_sync_data would
appear twice in the ethtool stats.

Fixes: d2ead1f360e8 ("net/mlx5e: Add kTLS TX HW offload support")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../ethernet/mellanox/mlx5/core/en_accel/tls_stats.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c
index 01468ec27446..b949b9a7538b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c
@@ -35,7 +35,6 @@
 #include <net/sock.h>
 
 #include "en.h"
-#include "accel/tls.h"
 #include "fpga/sdk.h"
 #include "en_accel/tls.h"
 
@@ -51,9 +50,14 @@ static const struct counter_desc mlx5e_tls_sw_stats_desc[] = {
 
 #define NUM_TLS_SW_COUNTERS ARRAY_SIZE(mlx5e_tls_sw_stats_desc)
 
+static bool is_tls_atomic_stats(struct mlx5e_priv *priv)
+{
+	return priv->tls && !mlx5_accel_is_ktls_device(priv->mdev);
+}
+
 int mlx5e_tls_get_count(struct mlx5e_priv *priv)
 {
-	if (!priv->tls)
+	if (!is_tls_atomic_stats(priv))
 		return 0;
 
 	return NUM_TLS_SW_COUNTERS;
@@ -63,7 +67,7 @@ int mlx5e_tls_get_strings(struct mlx5e_priv *priv, uint8_t *data)
 {
 	unsigned int i, idx = 0;
 
-	if (!priv->tls)
+	if (!is_tls_atomic_stats(priv))
 		return 0;
 
 	for (i = 0; i < NUM_TLS_SW_COUNTERS; i++)
@@ -77,7 +81,7 @@ int mlx5e_tls_get_stats(struct mlx5e_priv *priv, u64 *data)
 {
 	int i, idx = 0;
 
-	if (!priv->tls)
+	if (!is_tls_atomic_stats(priv))
 		return 0;
 
 	for (i = 0; i < NUM_TLS_SW_COUNTERS; i++)
-- 
2.26.2


From e1edae0492f68433e1bd1277104f37491352747b Mon Sep 17 00:00:00 2001
From: Edwin Peer <edwin.peer@broadcom.com>
Date: Sun, 20 Sep 2020 21:08:55 -0400
Subject: [PATCH 27/36] bnxt_en: return proper error codes in bnxt_show_temp

[ Upstream commit d69753fa1ecb3218b56b022722f7a5822735b876 ]

Returning "unknown" as a temperature value violates the hwmon interface
rules. Appropriate error codes should be returned via device_attribute
show instead. These will ultimately be propagated to the user via the
file system interface.

In addition to the corrected error handling, it is an even better idea to
not present the sensor in sysfs at all if it is known that the read will
definitely fail. Given that temp1_input is currently the only sensor
reported, ensure no hwmon registration if TEMP_MONITOR_QUERY is not
supported or if it will fail due to access permissions. Something smarter
may be needed if and when other sensors are added.

Fixes: 12cce90b934b ("bnxt_en: fix HWRM error when querying VF temperature")
Signed-off-by: Edwin Peer <edwin.peer@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 59257ee25168..4f4fd8076261 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -8939,18 +8939,16 @@ static ssize_t bnxt_show_temp(struct device *dev,
 	struct hwrm_temp_monitor_query_output *resp;
 	struct bnxt *bp = dev_get_drvdata(dev);
 	u32 len = 0;
+	int rc;
 
 	resp = bp->hwrm_cmd_resp_addr;
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_TEMP_MONITOR_QUERY, -1, -1);
 	mutex_lock(&bp->hwrm_cmd_lock);
-	if (!_hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT))
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (!rc)
 		len = sprintf(buf, "%u\n", resp->temp * 1000); /* display millidegree */
 	mutex_unlock(&bp->hwrm_cmd_lock);
-
-	if (len)
-		return len;
-
-	return sprintf(buf, "unknown\n");
+	return rc ?: len;
 }
 static SENSOR_DEVICE_ATTR(temp1_input, 0444, bnxt_show_temp, NULL, 0);
 
@@ -8970,7 +8968,16 @@ static void bnxt_hwmon_close(struct bnxt *bp)
 
 static void bnxt_hwmon_open(struct bnxt *bp)
 {
+	struct hwrm_temp_monitor_query_input req = {0};
 	struct pci_dev *pdev = bp->pdev;
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_TEMP_MONITOR_QUERY, -1, -1);
+	rc = hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc == -EACCES || rc == -EOPNOTSUPP) {
+		bnxt_hwmon_close(bp);
+		return;
+	}
 
 	if (bp->hwmon_dev)
 		return;
-- 
2.26.2


From c511f8519aac0c518c5b89537d09e3d2cfcf5050 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 20 Sep 2020 21:08:56 -0400
Subject: [PATCH 28/36] bnxt_en: Protect bnxt_set_eee() and
 bnxt_set_pauseparam() with mutex.

[ Upstream commit a53906908148d64423398a62c4435efb0d09652c ]

All changes related to bp->link_info require the protection of the
link_lock mutex.  It's not sufficient to rely just on RTNL.

Fixes: 163e9ef63641 ("bnxt_en: Fix race when modifying pause settings.")
Reviewed-by: Edwin Peer <edwin.peer@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 31 ++++++++++++-------
 1 file changed, 20 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index fd01bcc8e28d..1d15ff08f176 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -1665,9 +1665,12 @@ static int bnxt_set_pauseparam(struct net_device *dev,
 	if (!BNXT_SINGLE_PF(bp))
 		return -EOPNOTSUPP;
 
+	mutex_lock(&bp->link_lock);
 	if (epause->autoneg) {
-		if (!(link_info->autoneg & BNXT_AUTONEG_SPEED))
-			return -EINVAL;
+		if (!(link_info->autoneg & BNXT_AUTONEG_SPEED)) {
+			rc = -EINVAL;
+			goto pause_exit;
+		}
 
 		link_info->autoneg |= BNXT_AUTONEG_FLOW_CTRL;
 		if (bp->hwrm_spec_code >= 0x10201)
@@ -1688,11 +1691,11 @@ static int bnxt_set_pauseparam(struct net_device *dev,
 	if (epause->tx_pause)
 		link_info->req_flow_ctrl |= BNXT_LINK_PAUSE_TX;
 
-	if (netif_running(dev)) {
-		mutex_lock(&bp->link_lock);
+	if (netif_running(dev))
 		rc = bnxt_hwrm_set_pause(bp);
-		mutex_unlock(&bp->link_lock);
-	}
+
+pause_exit:
+	mutex_unlock(&bp->link_lock);
 	return rc;
 }
 
@@ -2397,8 +2400,7 @@ static int bnxt_set_eee(struct net_device *dev, struct ethtool_eee *edata)
 	struct bnxt *bp = netdev_priv(dev);
 	struct ethtool_eee *eee = &bp->eee;
 	struct bnxt_link_info *link_info = &bp->link_info;
-	u32 advertising =
-		 _bnxt_fw_to_ethtool_adv_spds(link_info->advertising, 0);
+	u32 advertising;
 	int rc = 0;
 
 	if (!BNXT_SINGLE_PF(bp))
@@ -2407,19 +2409,23 @@ static int bnxt_set_eee(struct net_device *dev, struct ethtool_eee *edata)
 	if (!(bp->flags & BNXT_FLAG_EEE_CAP))
 		return -EOPNOTSUPP;
 
+	mutex_lock(&bp->link_lock);
+	advertising = _bnxt_fw_to_ethtool_adv_spds(link_info->advertising, 0);
 	if (!edata->eee_enabled)
 		goto eee_ok;
 
 	if (!(link_info->autoneg & BNXT_AUTONEG_SPEED)) {
 		netdev_warn(dev, "EEE requires autoneg\n");
-		return -EINVAL;
+		rc = -EINVAL;
+		goto eee_exit;
 	}
 	if (edata->tx_lpi_enabled) {
 		if (bp->lpi_tmr_hi && (edata->tx_lpi_timer > bp->lpi_tmr_hi ||
 				       edata->tx_lpi_timer < bp->lpi_tmr_lo)) {
 			netdev_warn(dev, "Valid LPI timer range is %d and %d microsecs\n",
 				    bp->lpi_tmr_lo, bp->lpi_tmr_hi);
-			return -EINVAL;
+			rc = -EINVAL;
+			goto eee_exit;
 		} else if (!bp->lpi_tmr_hi) {
 			edata->tx_lpi_timer = eee->tx_lpi_timer;
 		}
@@ -2429,7 +2435,8 @@ static int bnxt_set_eee(struct net_device *dev, struct ethtool_eee *edata)
 	} else if (edata->advertised & ~advertising) {
 		netdev_warn(dev, "EEE advertised %x must be a subset of autoneg advertised speeds %x\n",
 			    edata->advertised, advertising);
-		return -EINVAL;
+		rc = -EINVAL;
+		goto eee_exit;
 	}
 
 	eee->advertised = edata->advertised;
@@ -2441,6 +2448,8 @@ static int bnxt_set_eee(struct net_device *dev, struct ethtool_eee *edata)
 	if (netif_running(dev))
 		rc = bnxt_hwrm_set_link_setting(bp, false, true);
 
+eee_exit:
+	mutex_unlock(&bp->link_lock);
 	return rc;
 }
 
-- 
2.26.2


From 9db1952a04a4dea500f47102cc97a3422f432cb8 Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens <hauke@hauke-m.de>
Date: Sat, 12 Sep 2020 21:36:26 +0200
Subject: [PATCH 29/36] net: lantiq: Wake TX queue again

[ Upstream commit dea36631e6f186d4b853af67a4aef2e35cfa8bb7 ]

The call to netif_wake_queue() when the TX descriptors were freed was
missing. When there are no TX buffers available the TX queue will be
stopped, but it was not started again when they are available again,
this is fixed in this patch.

Fixes: fe1a56420cf2 ("net: lantiq: Add Lantiq / Intel VRX200 Ethernet driver")
Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/lantiq_xrx200.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c
index 900affbdcc0e..1f968d0530a1 100644
--- a/drivers/net/ethernet/lantiq_xrx200.c
+++ b/drivers/net/ethernet/lantiq_xrx200.c
@@ -268,6 +268,9 @@ static int xrx200_tx_housekeeping(struct napi_struct *napi, int budget)
 	net_dev->stats.tx_bytes += bytes;
 	netdev_completed_queue(ch->priv->net_dev, pkts, bytes);
 
+	if (netif_queue_stopped(net_dev))
+		netif_wake_queue(net_dev);
+
 	if (pkts < budget) {
 		napi_complete(&ch->napi);
 		ltq_dma_enable_irq(&ch->dma);
-- 
2.26.2


From 20ee8c3e2a766eab578b30d04ae67348f05c1d25 Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens <hauke@hauke-m.de>
Date: Sat, 12 Sep 2020 21:36:27 +0200
Subject: [PATCH 30/36] net: lantiq: use netif_tx_napi_add() for TX NAPI

[ Upstream commit 74c7b80e222b58d3cea731d31e2a31a77fea8345 ]

netif_tx_napi_add() should be used for NAPI in the TX direction instead
of the netif_napi_add() function.

Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/lantiq_xrx200.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c
index 1f968d0530a1..6ecf266d22ce 100644
--- a/drivers/net/ethernet/lantiq_xrx200.c
+++ b/drivers/net/ethernet/lantiq_xrx200.c
@@ -501,7 +501,7 @@ static int xrx200_probe(struct platform_device *pdev)
 
 	/* setup NAPI */
 	netif_napi_add(net_dev, &priv->chan_rx.napi, xrx200_poll_rx, 32);
-	netif_napi_add(net_dev, &priv->chan_tx.napi, xrx200_tx_housekeeping, 32);
+	netif_tx_napi_add(net_dev, &priv->chan_tx.napi, xrx200_tx_housekeeping, 32);
 
 	platform_set_drvdata(pdev, priv);
 
-- 
2.26.2


From 8615a1b7a5c82eac13d203da630f633b76271197 Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens <hauke@hauke-m.de>
Date: Sat, 12 Sep 2020 21:36:28 +0200
Subject: [PATCH 31/36] net: lantiq: Use napi_complete_done()

[ Upstream commit c582a7fea9dad4d309437d1a7e22e6d2cb380e2e ]

Use napi_complete_done() and activate the interrupts when this function
returns true. This way the generic NAPI code can take care of activating
the interrupts.

Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/lantiq_xrx200.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c
index 6ecf266d22ce..d939b0e364bc 100644
--- a/drivers/net/ethernet/lantiq_xrx200.c
+++ b/drivers/net/ethernet/lantiq_xrx200.c
@@ -230,8 +230,8 @@ static int xrx200_poll_rx(struct napi_struct *napi, int budget)
 	}
 
 	if (rx < budget) {
-		napi_complete(&ch->napi);
-		ltq_dma_enable_irq(&ch->dma);
+		if (napi_complete_done(&ch->napi, rx))
+			ltq_dma_enable_irq(&ch->dma);
 	}
 
 	return rx;
@@ -272,8 +272,8 @@ static int xrx200_tx_housekeeping(struct napi_struct *napi, int budget)
 		netif_wake_queue(net_dev);
 
 	if (pkts < budget) {
-		napi_complete(&ch->napi);
-		ltq_dma_enable_irq(&ch->dma);
+		if (napi_complete_done(&ch->napi, pkts))
+			ltq_dma_enable_irq(&ch->dma);
 	}
 
 	return pkts;
-- 
2.26.2


From b25166da9fe1b6b933638f14006b1ec5cd7ed6a4 Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens <hauke@hauke-m.de>
Date: Sat, 12 Sep 2020 21:36:29 +0200
Subject: [PATCH 32/36] net: lantiq: Disable IRQs only if NAPI gets scheduled

[ Upstream commit 9423361da52356cb68642db5b2729b6b85aad330 ]

The napi_schedule() call will only schedule the NAPI if it is not
already running. To make sure that we do not deactivate interrupts
without scheduling NAPI only deactivate the interrupts in case NAPI also
gets scheduled.

Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/lantiq_xrx200.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c
index d939b0e364bc..96948276b2bc 100644
--- a/drivers/net/ethernet/lantiq_xrx200.c
+++ b/drivers/net/ethernet/lantiq_xrx200.c
@@ -344,10 +344,12 @@ static irqreturn_t xrx200_dma_irq(int irq, void *ptr)
 {
 	struct xrx200_chan *ch = ptr;
 
-	ltq_dma_disable_irq(&ch->dma);
-	ltq_dma_ack_irq(&ch->dma);
+	if (napi_schedule_prep(&ch->napi)) {
+		__napi_schedule(&ch->napi);
+		ltq_dma_disable_irq(&ch->dma);
+	}
 
-	napi_schedule(&ch->napi);
+	ltq_dma_ack_irq(&ch->dma);
 
 	return IRQ_HANDLED;
 }
-- 
2.26.2


From 11d4ed422eaf93a7dfc1bd50959dfd96693c63f9 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 16 Sep 2020 20:43:09 -0700
Subject: [PATCH 33/36] net: phy: Avoid NPD upon phy_detach() when driver is
 unbound

[ Upstream commit c2b727df7caa33876e7066bde090f40001b6d643 ]

If we have unbound the PHY driver prior to calling phy_detach() (often
via phy_disconnect()) then we can cause a NULL pointer de-reference
accessing the driver owner member. The steps to reproduce are:

echo unimac-mdio-0:01 > /sys/class/net/eth0/phydev/driver/unbind
ip link set eth0 down

Fixes: cafe8df8b9bc ("net: phy: Fix lack of reference count on PHY driver")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 110924d62744..9d0a306f0562 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1421,7 +1421,8 @@ void phy_detach(struct phy_device *phydev)
 
 	phy_led_triggers_unregister(phydev);
 
-	module_put(phydev->mdio.dev.driver->owner);
+	if (phydev->mdio.dev.driver)
+		module_put(phydev->mdio.dev.driver->owner);
 
 	/* If the device had no specific driver before (i.e. - it
 	 * was using the generic driver), we unbind the device
-- 
2.26.2


From 05cfd4222350bf3c0348628cb0e095c91045f084 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 16 Sep 2020 20:43:10 -0700
Subject: [PATCH 34/36] net: phy: Do not warn in phy_stop() on PHY_DOWN

[ Upstream commit 5116a8ade333b6c2e180782139c9c516a437b21c ]

When phy_is_started() was added to catch incorrect PHY states,
phy_stop() would not be qualified against PHY_DOWN. It is possible to
reach that state when the PHY driver has been unbound and the network
device is then brought down.

Fixes: 2b3e88ea6528 ("net: phy: improve phy state checking")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 54e5d4f9622c..b718b11607fc 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -834,7 +834,7 @@ EXPORT_SYMBOL(phy_free_interrupt);
  */
 void phy_stop(struct phy_device *phydev)
 {
-	if (!phy_is_started(phydev)) {
+	if (!phy_is_started(phydev) && phydev->state != PHY_DOWN) {
 		WARN(1, "called from state %s\n",
 		     phy_state_to_str(phydev->state));
 		return;
-- 
2.26.2


From 1dba909860bfffb8b0bee447d9778a5738388a79 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 9 Sep 2020 01:27:39 -0700
Subject: [PATCH 35/36] net: qrtr: check skb_put_padto() return value

[ Upstream commit 3ca1a42a52ca4b4f02061683851692ad65fefac8 ]

If skb_put_padto() returns an error, skb has been freed.
Better not touch it anymore, as reported by syzbot [1]

Note to qrtr maintainers : this suggests qrtr_sendmsg()
should adjust sock_alloc_send_skb() second parameter
to account for the potential added alignment to avoid
reallocation.

[1]

BUG: KASAN: use-after-free in __skb_insert include/linux/skbuff.h:1907 [inline]
BUG: KASAN: use-after-free in __skb_queue_before include/linux/skbuff.h:2016 [inline]
BUG: KASAN: use-after-free in __skb_queue_tail include/linux/skbuff.h:2049 [inline]
BUG: KASAN: use-after-free in skb_queue_tail+0x6b/0x120 net/core/skbuff.c:3146
Write of size 8 at addr ffff88804d8ab3c0 by task syz-executor.4/4316

CPU: 1 PID: 4316 Comm: syz-executor.4 Not tainted 5.9.0-rc4-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1d6/0x29e lib/dump_stack.c:118
 print_address_description+0x66/0x620 mm/kasan/report.c:383
 __kasan_report mm/kasan/report.c:513 [inline]
 kasan_report+0x132/0x1d0 mm/kasan/report.c:530
 __skb_insert include/linux/skbuff.h:1907 [inline]
 __skb_queue_before include/linux/skbuff.h:2016 [inline]
 __skb_queue_tail include/linux/skbuff.h:2049 [inline]
 skb_queue_tail+0x6b/0x120 net/core/skbuff.c:3146
 qrtr_tun_send+0x1a/0x40 net/qrtr/tun.c:23
 qrtr_node_enqueue+0x44f/0xc00 net/qrtr/qrtr.c:364
 qrtr_bcast_enqueue+0xbe/0x140 net/qrtr/qrtr.c:861
 qrtr_sendmsg+0x680/0x9c0 net/qrtr/qrtr.c:960
 sock_sendmsg_nosec net/socket.c:651 [inline]
 sock_sendmsg net/socket.c:671 [inline]
 sock_write_iter+0x317/0x470 net/socket.c:998
 call_write_iter include/linux/fs.h:1882 [inline]
 new_sync_write fs/read_write.c:503 [inline]
 vfs_write+0xa96/0xd10 fs/read_write.c:578
 ksys_write+0x11b/0x220 fs/read_write.c:631
 do_syscall_64+0x31/0x70 arch/x86/entry/common.c:46
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x45d5b9
Code: 5d b4 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 2b b4 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f84b5b81c78 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 0000000000038b40 RCX: 000000000045d5b9
RDX: 0000000000000055 RSI: 0000000020001240 RDI: 0000000000000003
RBP: 00007f84b5b81ca0 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 000000000000000f
R13: 00007ffcbbf86daf R14: 00007f84b5b829c0 R15: 000000000118cf4c

Allocated by task 4316:
 kasan_save_stack mm/kasan/common.c:48 [inline]
 kasan_set_track mm/kasan/common.c:56 [inline]
 __kasan_kmalloc+0x100/0x130 mm/kasan/common.c:461
 slab_post_alloc_hook+0x3e/0x290 mm/slab.h:518
 slab_alloc mm/slab.c:3312 [inline]
 kmem_cache_alloc+0x1c1/0x2d0 mm/slab.c:3482
 skb_clone+0x1b2/0x370 net/core/skbuff.c:1449
 qrtr_bcast_enqueue+0x6d/0x140 net/qrtr/qrtr.c:857
 qrtr_sendmsg+0x680/0x9c0 net/qrtr/qrtr.c:960
 sock_sendmsg_nosec net/socket.c:651 [inline]
 sock_sendmsg net/socket.c:671 [inline]
 sock_write_iter+0x317/0x470 net/socket.c:998
 call_write_iter include/linux/fs.h:1882 [inline]
 new_sync_write fs/read_write.c:503 [inline]
 vfs_write+0xa96/0xd10 fs/read_write.c:578
 ksys_write+0x11b/0x220 fs/read_write.c:631
 do_syscall_64+0x31/0x70 arch/x86/entry/common.c:46
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Freed by task 4316:
 kasan_save_stack mm/kasan/common.c:48 [inline]
 kasan_set_track+0x3d/0x70 mm/kasan/common.c:56
 kasan_set_free_info+0x17/0x30 mm/kasan/generic.c:355
 __kasan_slab_free+0xdd/0x110 mm/kasan/common.c:422
 __cache_free mm/slab.c:3418 [inline]
 kmem_cache_free+0x82/0xf0 mm/slab.c:3693
 __skb_pad+0x3f5/0x5a0 net/core/skbuff.c:1823
 __skb_put_padto include/linux/skbuff.h:3233 [inline]
 skb_put_padto include/linux/skbuff.h:3252 [inline]
 qrtr_node_enqueue+0x62f/0xc00 net/qrtr/qrtr.c:360
 qrtr_bcast_enqueue+0xbe/0x140 net/qrtr/qrtr.c:861
 qrtr_sendmsg+0x680/0x9c0 net/qrtr/qrtr.c:960
 sock_sendmsg_nosec net/socket.c:651 [inline]
 sock_sendmsg net/socket.c:671 [inline]
 sock_write_iter+0x317/0x470 net/socket.c:998
 call_write_iter include/linux/fs.h:1882 [inline]
 new_sync_write fs/read_write.c:503 [inline]
 vfs_write+0xa96/0xd10 fs/read_write.c:578
 ksys_write+0x11b/0x220 fs/read_write.c:631
 do_syscall_64+0x31/0x70 arch/x86/entry/common.c:46
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

The buggy address belongs to the object at ffff88804d8ab3c0
 which belongs to the cache skbuff_head_cache of size 224
The buggy address is located 0 bytes inside of
 224-byte region [ffff88804d8ab3c0, ffff88804d8ab4a0)
The buggy address belongs to the page:
page:00000000ea8cccfb refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff88804d8abb40 pfn:0x4d8ab
flags: 0xfffe0000000200(slab)
raw: 00fffe0000000200 ffffea0002237ec8 ffffea00029b3388 ffff88821bb66800
raw: ffff88804d8abb40 ffff88804d8ab000 000000010000000b 0000000000000000
page dumped because: kasan: bad access detected

Fixes: ce57785bf91b ("net: qrtr: fix len of skb_put_padto in qrtr_node_enqueue")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Carl Huang <cjhuang@codeaurora.org>
Cc: Wen Gong <wgong@codeaurora.org>
Cc: Bjorn Andersson <bjorn.andersson@linaro.org>
Cc: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Acked-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/qrtr/qrtr.c | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index a699e318b9a0..d6d2736ec927 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -178,7 +178,7 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb,
 {
 	struct qrtr_hdr_v1 *hdr;
 	size_t len = skb->len;
-	int rc = -ENODEV;
+	int rc;
 
 	hdr = skb_push(skb, sizeof(*hdr));
 	hdr->version = cpu_to_le32(QRTR_PROTO_VER_1);
@@ -196,15 +196,17 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb,
 	hdr->size = cpu_to_le32(len);
 	hdr->confirm_rx = 0;
 
-	skb_put_padto(skb, ALIGN(len, 4) + sizeof(*hdr));
-
-	mutex_lock(&node->ep_lock);
-	if (node->ep)
-		rc = node->ep->xmit(node->ep, skb);
-	else
-		kfree_skb(skb);
-	mutex_unlock(&node->ep_lock);
+	rc = skb_put_padto(skb, ALIGN(len, 4) + sizeof(*hdr));
 
+	if (!rc) {
+		mutex_lock(&node->ep_lock);
+		rc = -ENODEV;
+		if (node->ep)
+			rc = node->ep->xmit(node->ep, skb);
+		else
+			kfree_skb(skb);
+		mutex_unlock(&node->ep_lock);
+	}
 	return rc;
 }
 
-- 
2.26.2


From ae7a373fd4971db2e6e45bc5a198848b3b7d1652 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 9 Sep 2020 01:27:40 -0700
Subject: [PATCH 36/36] net: add __must_check to skb_put_padto()

[ Upstream commit 4a009cb04aeca0de60b73f37b102573354214b52 ]

skb_put_padto() and __skb_put_padto() callers
must check return values or risk use-after-free.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 955e1370f033..a62889c8bed7 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3185,8 +3185,9 @@ static inline int skb_padto(struct sk_buff *skb, unsigned int len)
  *	is untouched. Otherwise it is extended. Returns zero on
  *	success. The skb is freed on error if @free_on_error is true.
  */
-static inline int __skb_put_padto(struct sk_buff *skb, unsigned int len,
-				  bool free_on_error)
+static inline int __must_check __skb_put_padto(struct sk_buff *skb,
+					       unsigned int len,
+					       bool free_on_error)
 {
 	unsigned int size = skb->len;
 
@@ -3209,7 +3210,7 @@ static inline int __skb_put_padto(struct sk_buff *skb, unsigned int len,
  *	is untouched. Otherwise it is extended. Returns zero on
  *	success. The skb is freed on error.
  */
-static inline int skb_put_padto(struct sk_buff *skb, unsigned int len)
+static inline int __must_check skb_put_padto(struct sk_buff *skb, unsigned int len)
 {
 	return __skb_put_padto(skb, len, true);
 }
-- 
2.26.2


[-- Attachment #3: net_58.mbox --]
[-- Type: Application/Octet-Stream, Size: 161645 bytes --]

From 769b94fffab9c28d56f19fbe4afe5853d4dc0541 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 3 Sep 2020 19:10:11 -0700
Subject: [PATCH 01/54] act_ife: load meta modules before tcf_idr_check_alloc()

[ Upstream commit cc8e58f8325cdf14b9516b61c384cdfd02a4f408 ]

The following deadlock scenario is triggered by syzbot:

Thread A:				Thread B:
tcf_idr_check_alloc()
...
populate_metalist()
  rtnl_unlock()
					rtnl_lock()
					...
  request_module()			tcf_idr_check_alloc()
  rtnl_lock()

At this point, thread A is waiting for thread B to release RTNL
lock, while thread B is waiting for thread A to commit the IDR
change with tcf_idr_insert() later.

Break this deadlock situation by preloading ife modules earlier,
before tcf_idr_check_alloc(), this is fine because we only need
to load modules we need potentially.

Reported-and-tested-by: syzbot+80e32b5d1f9923f8ace6@syzkaller.appspotmail.com
Fixes: 0190c1d452a9 ("net: sched: atomically check-allocate action")
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Vlad Buslov <vladbu@mellanox.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/act_ife.c | 44 ++++++++++++++++++++++++++++++++++----------
 1 file changed, 34 insertions(+), 10 deletions(-)

diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index c1fcd85719d6..5c568757643b 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -436,6 +436,25 @@ static void tcf_ife_cleanup(struct tc_action *a)
 		kfree_rcu(p, rcu);
 }
 
+static int load_metalist(struct nlattr **tb, bool rtnl_held)
+{
+	int i;
+
+	for (i = 1; i < max_metacnt; i++) {
+		if (tb[i]) {
+			void *val = nla_data(tb[i]);
+			int len = nla_len(tb[i]);
+			int rc;
+
+			rc = load_metaops_and_vet(i, val, len, rtnl_held);
+			if (rc != 0)
+				return rc;
+		}
+	}
+
+	return 0;
+}
+
 static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb,
 			     bool exists, bool rtnl_held)
 {
@@ -449,10 +468,6 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb,
 			val = nla_data(tb[i]);
 			len = nla_len(tb[i]);
 
-			rc = load_metaops_and_vet(i, val, len, rtnl_held);
-			if (rc != 0)
-				return rc;
-
 			rc = add_metainfo(ife, i, val, len, exists);
 			if (rc)
 				return rc;
@@ -509,6 +524,21 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	if (!p)
 		return -ENOMEM;
 
+	if (tb[TCA_IFE_METALST]) {
+		err = nla_parse_nested_deprecated(tb2, IFE_META_MAX,
+						  tb[TCA_IFE_METALST], NULL,
+						  NULL);
+		if (err) {
+			kfree(p);
+			return err;
+		}
+		err = load_metalist(tb2, rtnl_held);
+		if (err) {
+			kfree(p);
+			return err;
+		}
+	}
+
 	index = parm->index;
 	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (err < 0) {
@@ -570,15 +600,9 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	}
 
 	if (tb[TCA_IFE_METALST]) {
-		err = nla_parse_nested_deprecated(tb2, IFE_META_MAX,
-						  tb[TCA_IFE_METALST], NULL,
-						  NULL);
-		if (err)
-			goto metadata_parse_err;
 		err = populate_metalist(ife, tb2, exists, rtnl_held);
 		if (err)
 			goto metadata_parse_err;
-
 	} else {
 		/* if no passed metadata allow list or passed allow-all
 		 * then here we process by adding as many supported metadatum
-- 
2.26.2


From e0be07c7d799a654b1f40083d979bd5ca83f6ebc Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Sat, 5 Sep 2020 22:55:36 -0400
Subject: [PATCH 02/54] bnxt_en: Avoid sending firmware messages when AER error
 is detected.

[ Upstream commit b340dc680ed48dcc05b56e1ebe1b9535813c3ee0 ]

When the driver goes through PCIe AER reset in error state, all
firmware messages will timeout because the PCIe bus is no longer
accessible.  This can lead to AER reset taking many minutes to
complete as each firmware command takes time to timeout.

Define a new macro BNXT_NO_FW_ACCESS() to skip these firmware messages
when either firmware is in fatal error state or when
pci_channel_offline() is true.  It now takes a more reasonable 20 to
30 seconds to complete AER recovery.

Fixes: b4fff2079d10 ("bnxt_en: Do not send firmware messages if firmware is in error state.")
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 6 +++---
 drivers/net/ethernet/broadcom/bnxt/bnxt.h | 4 ++++
 2 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index cd5c7a1412c6..58f8f05d4a66 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -4198,7 +4198,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 	u32 bar_offset = BNXT_GRCPF_REG_CHIMP_COMM;
 	u16 dst = BNXT_HWRM_CHNL_CHIMP;
 
-	if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state))
+	if (BNXT_NO_FW_ACCESS(bp))
 		return -EBUSY;
 
 	if (msg_len > BNXT_HWRM_MAX_REQ_LEN) {
@@ -5530,7 +5530,7 @@ static int hwrm_ring_free_send_msg(struct bnxt *bp,
 	struct hwrm_ring_free_output *resp = bp->hwrm_cmd_resp_addr;
 	u16 error_code;
 
-	if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state))
+	if (BNXT_NO_FW_ACCESS(bp))
 		return 0;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_RING_FREE, cmpl_ring_id, -1);
@@ -7502,7 +7502,7 @@ static int bnxt_set_tpa(struct bnxt *bp, bool set_tpa)
 
 	if (set_tpa)
 		tpa_flags = bp->flags & BNXT_FLAG_TPA;
-	else if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state))
+	else if (BNXT_NO_FW_ACCESS(bp))
 		return 0;
 	for (i = 0; i < bp->nr_vnics; i++) {
 		rc = bnxt_hwrm_vnic_set_tpa(bp, i, tpa_flags);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 78e2fd63ac3d..440b43c8068f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1673,6 +1673,10 @@ struct bnxt {
 #define BNXT_STATE_FW_FATAL_COND	6
 #define BNXT_STATE_DRV_REGISTERED	7
 
+#define BNXT_NO_FW_ACCESS(bp)					\
+	(test_bit(BNXT_STATE_FW_FATAL_COND, &(bp)->state) ||	\
+	 pci_channel_offline((bp)->pdev))
+
 	struct bnxt_irq	*irq_tbl;
 	int			total_irqs;
 	u8			mac_addr[ETH_ALEN];
-- 
2.26.2


From c3e9dac3f85a4e3ddc893e478f8cc1a454295cba Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Sat, 5 Sep 2020 22:55:37 -0400
Subject: [PATCH 03/54] bnxt_en: Fix NULL ptr dereference crash in
 bnxt_fw_reset_task()

[ Upstream commit b16939b59cc00231a75d224fd058d22c9d064976 ]

bnxt_fw_reset_task() which runs from a workqueue can race with
bnxt_remove_one().  For example, if firmware reset and VF FLR are
happening at about the same time.

bnxt_remove_one() already cancels the workqueue and waits for it
to finish, but we need to do this earlier before the devlink
reporters are destroyed.  This will guarantee that
the devlink reporters will always be valid when bnxt_fw_reset_task()
is still running.

Fixes: b148bb238c02 ("bnxt_en: Fix possible crash in bnxt_fw_reset_task().")
Reviewed-by: Edwin Peer <edwin.peer@broadcom.com>
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 58f8f05d4a66..3612039e7439 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -11498,6 +11498,10 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 	if (BNXT_PF(bp))
 		bnxt_sriov_disable(bp);
 
+	clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
+	bnxt_cancel_sp_work(bp);
+	bp->sp_event = 0;
+
 	bnxt_dl_fw_reporters_destroy(bp, true);
 	if (BNXT_PF(bp))
 		devlink_port_type_clear(&bp->dl_port);
@@ -11505,9 +11509,6 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 	unregister_netdev(dev);
 	bnxt_dl_unregister(bp);
 	bnxt_shutdown_tc(bp);
-	clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
-	bnxt_cancel_sp_work(bp);
-	bp->sp_event = 0;
 
 	bnxt_clear_int_mode(bp);
 	bnxt_hwrm_func_drv_unrgtr(bp);
-- 
2.26.2


From 163458c0adb7be6240869057117edd3f40bb3e01 Mon Sep 17 00:00:00 2001
From: Raju Rangoju <rajur@chelsio.com>
Date: Wed, 16 Sep 2020 21:50:39 +0530
Subject: [PATCH 04/54] cxgb4: fix memory leak during module unload

[ Upstream commit f4a26a9b311d7ff9db461278faf2869d06496ef8 ]

Fix the memory leak in mps during module unload
path by freeing mps reference entries if the list
adpter->mps_ref is not already empty

Fixes: 28b3870578ef ("cxgb4: Re-work the logic for mps refcounting")
Signed-off-by: Raju Rangoju <rajur@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_mps.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_mps.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_mps.c
index b1a073eea60b..a020e8490681 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_mps.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_mps.c
@@ -229,7 +229,7 @@ void cxgb4_free_mps_ref_entries(struct adapter *adap)
 {
 	struct mps_entries_ref *mps_entry, *tmp;
 
-	if (!list_empty(&adap->mps_ref))
+	if (list_empty(&adap->mps_ref))
 		return;
 
 	spin_lock(&adap->mps_ref_lock);
-- 
2.26.2


From c0de306e6e30666f99a8c19cace51d618f4e58ab Mon Sep 17 00:00:00 2001
From: Ganji Aravind <ganji.aravind@chelsio.com>
Date: Fri, 4 Sep 2020 15:58:18 +0530
Subject: [PATCH 05/54] cxgb4: Fix offset when clearing filter byte counters

[ Upstream commit 94cc242a067a869c29800aa789d38b7676136e50 ]

Pass the correct offset to clear the stale filter hit
bytes counter. Otherwise, the counter starts incrementing
from the stale information, instead of 0.

Fixes: 12b276fbf6e0 ("cxgb4: add support to create hash filters")
Signed-off-by: Ganji Aravind <ganji.aravind@chelsio.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
index d02d346629b3..ff0d82e2535d 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
@@ -1906,13 +1906,16 @@ int cxgb4_del_filter(struct net_device *dev, int filter_id,
 static int configure_filter_tcb(struct adapter *adap, unsigned int tid,
 				struct filter_entry *f)
 {
-	if (f->fs.hitcnts)
+	if (f->fs.hitcnts) {
 		set_tcb_field(adap, f, tid, TCB_TIMESTAMP_W,
-			      TCB_TIMESTAMP_V(TCB_TIMESTAMP_M) |
+			      TCB_TIMESTAMP_V(TCB_TIMESTAMP_M),
+			      TCB_TIMESTAMP_V(0ULL),
+			      1);
+		set_tcb_field(adap, f, tid, TCB_RTT_TS_RECENT_AGE_W,
 			      TCB_RTT_TS_RECENT_AGE_V(TCB_RTT_TS_RECENT_AGE_M),
-			      TCB_TIMESTAMP_V(0ULL) |
 			      TCB_RTT_TS_RECENT_AGE_V(0ULL),
 			      1);
+	}
 
 	if (f->fs.newdmac)
 		set_tcb_tflag(adap, f, tid, TF_CCTRL_ECE_S, 1,
-- 
2.26.2


From 098741ec996fcf07e29505d9d0ae307a644440c8 Mon Sep 17 00:00:00 2001
From: Mark Gray <mark.d.gray@redhat.com>
Date: Wed, 16 Sep 2020 05:19:35 -0400
Subject: [PATCH 06/54] geneve: add transport ports in route lookup for geneve

[ Upstream commit 34beb21594519ce64a55a498c2fe7d567bc1ca20 ]

This patch adds transport ports information for route lookup so that
IPsec can select Geneve tunnel traffic to do encryption. This is
needed for OVS/OVN IPsec with encrypted Geneve tunnels.

This can be tested by configuring a host-host VPN using an IKE
daemon and specifying port numbers. For example, for an
Openswan-type configuration, the following parameters should be
configured on both hosts and IPsec set up as-per normal:

$ cat /etc/ipsec.conf

conn in
...
left=$IP1
right=$IP2
...
leftprotoport=udp/6081
rightprotoport=udp
...
conn out
...
left=$IP1
right=$IP2
...
leftprotoport=udp
rightprotoport=udp/6081
...

The tunnel can then be setup using "ip" on both hosts (but
changing the relevant IP addresses):

$ ip link add tun type geneve id 1000 remote $IP2
$ ip addr add 192.168.0.1/24 dev tun
$ ip link set tun up

This can then be tested by pinging from $IP1:

$ ping 192.168.0.2

Without this patch the traffic is unencrypted on the wire.

Fixes: 2d07dc79fe04 ("geneve: add initial netdev driver for GENEVE tunnels")
Signed-off-by: Qiuyu Xiao <qiuyu.xiao.qyx@gmail.com>
Signed-off-by: Mark Gray <mark.d.gray@redhat.com>
Reviewed-by: Greg Rose <gvrose8192@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c | 37 +++++++++++++++++++++++++++----------
 1 file changed, 27 insertions(+), 10 deletions(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index dec52b763d50..deede92b17fc 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -773,7 +773,8 @@ static struct rtable *geneve_get_v4_rt(struct sk_buff *skb,
 				       struct net_device *dev,
 				       struct geneve_sock *gs4,
 				       struct flowi4 *fl4,
-				       const struct ip_tunnel_info *info)
+				       const struct ip_tunnel_info *info,
+				       __be16 dport, __be16 sport)
 {
 	bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
 	struct geneve_dev *geneve = netdev_priv(dev);
@@ -789,6 +790,8 @@ static struct rtable *geneve_get_v4_rt(struct sk_buff *skb,
 	fl4->flowi4_proto = IPPROTO_UDP;
 	fl4->daddr = info->key.u.ipv4.dst;
 	fl4->saddr = info->key.u.ipv4.src;
+	fl4->fl4_dport = dport;
+	fl4->fl4_sport = sport;
 
 	tos = info->key.tos;
 	if ((tos == 1) && !geneve->collect_md) {
@@ -823,7 +826,8 @@ static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb,
 					   struct net_device *dev,
 					   struct geneve_sock *gs6,
 					   struct flowi6 *fl6,
-					   const struct ip_tunnel_info *info)
+					   const struct ip_tunnel_info *info,
+					   __be16 dport, __be16 sport)
 {
 	bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
 	struct geneve_dev *geneve = netdev_priv(dev);
@@ -839,6 +843,9 @@ static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb,
 	fl6->flowi6_proto = IPPROTO_UDP;
 	fl6->daddr = info->key.u.ipv6.dst;
 	fl6->saddr = info->key.u.ipv6.src;
+	fl6->fl6_dport = dport;
+	fl6->fl6_sport = sport;
+
 	prio = info->key.tos;
 	if ((prio == 1) && !geneve->collect_md) {
 		prio = ip_tunnel_get_dsfield(ip_hdr(skb), skb);
@@ -885,14 +892,15 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	__be16 sport;
 	int err;
 
-	rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info);
+	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
+	rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info,
+			      geneve->info.key.tp_dst, sport);
 	if (IS_ERR(rt))
 		return PTR_ERR(rt);
 
 	skb_tunnel_check_pmtu(skb, &rt->dst,
 			      GENEVE_IPV4_HLEN + info->options_len);
 
-	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
 	if (geneve->collect_md) {
 		tos = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb);
 		ttl = key->ttl;
@@ -947,13 +955,14 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	__be16 sport;
 	int err;
 
-	dst = geneve_get_v6_dst(skb, dev, gs6, &fl6, info);
+	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
+	dst = geneve_get_v6_dst(skb, dev, gs6, &fl6, info,
+				geneve->info.key.tp_dst, sport);
 	if (IS_ERR(dst))
 		return PTR_ERR(dst);
 
 	skb_tunnel_check_pmtu(skb, dst, GENEVE_IPV6_HLEN + info->options_len);
 
-	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
 	if (geneve->collect_md) {
 		prio = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb);
 		ttl = key->ttl;
@@ -1034,13 +1043,18 @@ static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 {
 	struct ip_tunnel_info *info = skb_tunnel_info(skb);
 	struct geneve_dev *geneve = netdev_priv(dev);
+	__be16 sport;
 
 	if (ip_tunnel_info_af(info) == AF_INET) {
 		struct rtable *rt;
 		struct flowi4 fl4;
+
 		struct geneve_sock *gs4 = rcu_dereference(geneve->sock4);
+		sport = udp_flow_src_port(geneve->net, skb,
+					  1, USHRT_MAX, true);
 
-		rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info);
+		rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info,
+				      geneve->info.key.tp_dst, sport);
 		if (IS_ERR(rt))
 			return PTR_ERR(rt);
 
@@ -1050,9 +1064,13 @@ static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 	} else if (ip_tunnel_info_af(info) == AF_INET6) {
 		struct dst_entry *dst;
 		struct flowi6 fl6;
+
 		struct geneve_sock *gs6 = rcu_dereference(geneve->sock6);
+		sport = udp_flow_src_port(geneve->net, skb,
+					  1, USHRT_MAX, true);
 
-		dst = geneve_get_v6_dst(skb, dev, gs6, &fl6, info);
+		dst = geneve_get_v6_dst(skb, dev, gs6, &fl6, info,
+					geneve->info.key.tp_dst, sport);
 		if (IS_ERR(dst))
 			return PTR_ERR(dst);
 
@@ -1063,8 +1081,7 @@ static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 		return -EINVAL;
 	}
 
-	info->key.tp_src = udp_flow_src_port(geneve->net, skb,
-					     1, USHRT_MAX, true);
+	info->key.tp_src = sport;
 	info->key.tp_dst = geneve->info.key.tp_dst;
 	return 0;
 }
-- 
2.26.2


From 581a96bbda734dd6ede09995d3f769ae93a727da Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 9 Sep 2020 12:46:48 +0300
Subject: [PATCH 07/54] hdlc_ppp: add range checks in ppp_cp_parse_cr()

[ Upstream commit 66d42ed8b25b64eb63111a2b8582c5afc8bf1105 ]

There are a couple bugs here:
1) If opt[1] is zero then this results in a forever loop.  If the value
   is less than 2 then it is invalid.
2) It assumes that "len" is more than sizeof(valid_accm) or 6 which can
   result in memory corruption.

In the case of LCP_OPTION_ACCM, then  we should check "opt[1]" instead
of "len" because, if "opt[1]" is less than sizeof(valid_accm) then
"nak_len" gets out of sync and it can lead to memory corruption in the
next iterations through the loop.  In case of LCP_OPTION_MAGIC, the
only valid value for opt[1] is 6, but the code is trying to log invalid
data so we should only discard the data when "len" is less than 6
because that leads to a read overflow.

Reported-by: ChenNan Of Chaitin Security Research Lab  <whutchennan@gmail.com>
Fixes: e022c2f07ae5 ("WAN: new synchronous PPP implementation for generic HDLC.")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wan/hdlc_ppp.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wan/hdlc_ppp.c b/drivers/net/wan/hdlc_ppp.c
index 48ced3912576..16f33d1ffbfb 100644
--- a/drivers/net/wan/hdlc_ppp.c
+++ b/drivers/net/wan/hdlc_ppp.c
@@ -383,11 +383,8 @@ static void ppp_cp_parse_cr(struct net_device *dev, u16 pid, u8 id,
 	}
 
 	for (opt = data; len; len -= opt[1], opt += opt[1]) {
-		if (len < 2 || len < opt[1]) {
-			dev->stats.rx_errors++;
-			kfree(out);
-			return; /* bad packet, drop silently */
-		}
+		if (len < 2 || opt[1] < 2 || len < opt[1])
+			goto err_out;
 
 		if (pid == PID_LCP)
 			switch (opt[0]) {
@@ -395,6 +392,8 @@ static void ppp_cp_parse_cr(struct net_device *dev, u16 pid, u8 id,
 				continue; /* MRU always OK and > 1500 bytes? */
 
 			case LCP_OPTION_ACCM: /* async control character map */
+				if (opt[1] < sizeof(valid_accm))
+					goto err_out;
 				if (!memcmp(opt, valid_accm,
 					    sizeof(valid_accm)))
 					continue;
@@ -406,6 +405,8 @@ static void ppp_cp_parse_cr(struct net_device *dev, u16 pid, u8 id,
 				}
 				break;
 			case LCP_OPTION_MAGIC:
+				if (len < 6)
+					goto err_out;
 				if (opt[1] != 6 || (!opt[2] && !opt[3] &&
 						    !opt[4] && !opt[5]))
 					break; /* reject invalid magic number */
@@ -424,6 +425,11 @@ static void ppp_cp_parse_cr(struct net_device *dev, u16 pid, u8 id,
 		ppp_cp_event(dev, pid, RCR_GOOD, CP_CONF_ACK, id, req_len, data);
 
 	kfree(out);
+	return;
+
+err_out:
+	dev->stats.rx_errors++;
+	kfree(out);
 }
 
 static int ppp_rx(struct sk_buff *skb)
-- 
2.26.2


From 097d6989a7f4fa1887f2b5f3ca3917292f498c22 Mon Sep 17 00:00:00 2001
From: Luo bin <luobin9@huawei.com>
Date: Fri, 4 Sep 2020 16:37:28 +0800
Subject: [PATCH 08/54] hinic: bump up the timeout of SET_FUNC_STATE cmd

[ Upstream commit 4e4269ebe7e18038fffacf113e2dd5ded6d49942 ]

We free memory regardless of the return value of SET_FUNC_STATE
cmd in hinic_close function to avoid memory leak and this cmd may
timeout when fw is busy with handling other cmds, so we bump up the
timeout of this cmd to ensure it won't return failure.

Fixes: 00e57a6d4ad3 ("net-next/hinic: Add Tx operation")
Signed-off-by: Luo bin <luobin9@huawei.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/huawei/hinic/hinic_hw_mgmt.c    | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
index e0f5a81d8620..7fe39a155b32 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
@@ -45,6 +45,8 @@
 
 #define MGMT_MSG_TIMEOUT                5000
 
+#define SET_FUNC_PORT_MBOX_TIMEOUT	30000
+
 #define SET_FUNC_PORT_MGMT_TIMEOUT	25000
 
 #define mgmt_to_pfhwdev(pf_mgmt)        \
@@ -358,16 +360,20 @@ int hinic_msg_to_mgmt(struct hinic_pf_to_mgmt *pf_to_mgmt,
 		return -EINVAL;
 	}
 
-	if (cmd == HINIC_PORT_CMD_SET_FUNC_STATE)
-		timeout = SET_FUNC_PORT_MGMT_TIMEOUT;
+	if (HINIC_IS_VF(hwif)) {
+		if (cmd == HINIC_PORT_CMD_SET_FUNC_STATE)
+			timeout = SET_FUNC_PORT_MBOX_TIMEOUT;
 
-	if (HINIC_IS_VF(hwif))
 		return hinic_mbox_to_pf(pf_to_mgmt->hwdev, mod, cmd, buf_in,
-					in_size, buf_out, out_size, 0);
-	else
+					in_size, buf_out, out_size, timeout);
+	} else {
+		if (cmd == HINIC_PORT_CMD_SET_FUNC_STATE)
+			timeout = SET_FUNC_PORT_MGMT_TIMEOUT;
+
 		return msg_to_mgmt_sync(pf_to_mgmt, mod, cmd, buf_in, in_size,
 				buf_out, out_size, MGMT_DIRECT_SEND,
 				MSG_NOT_RESP, timeout);
+	}
 }
 
 static void recv_mgmt_msg_work_handler(struct work_struct *work)
-- 
2.26.2


From 77204ad493c585fde2adbd62056594f251644d42 Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Tue, 8 Sep 2020 14:09:34 -0700
Subject: [PATCH 09/54] ip: fix tos reflection in ack and reset packets

[ Upstream commit ba9e04a7ddf4f22a10e05bf9403db6b97743c7bf ]

Currently, in tcp_v4_reqsk_send_ack() and tcp_v4_send_reset(), we
echo the TOS value of the received packets in the response.
However, we do not want to echo the lower 2 ECN bits in accordance
with RFC 3168 6.1.5 robustness principles.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")

Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_output.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 17206677d503..f09a18839716 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -74,6 +74,7 @@
 #include <net/icmp.h>
 #include <net/checksum.h>
 #include <net/inetpeer.h>
+#include <net/inet_ecn.h>
 #include <net/lwtunnel.h>
 #include <linux/bpf-cgroup.h>
 #include <linux/igmp.h>
@@ -1697,7 +1698,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 	if (IS_ERR(rt))
 		return;
 
-	inet_sk(sk)->tos = arg->tos;
+	inet_sk(sk)->tos = arg->tos & ~INET_ECN_MASK;
 
 	sk->sk_protocol = ip_hdr(skb)->protocol;
 	sk->sk_bound_dev_if = arg->bound_dev_if;
-- 
2.26.2


From 6bdd7beac24809784083f10656140fa16ebea499 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Sun, 13 Sep 2020 12:43:39 -0600
Subject: [PATCH 10/54] ipv4: Initialize flowi4_multipath_hash in data path

[ Upstream commit 1869e226a7b3ef75b4f70ede2f1b7229f7157fa4 ]

flowi4_multipath_hash was added by the commit referenced below for
tunnels. Unfortunately, the patch did not initialize the new field
for several fast path lookups that do not initialize the entire flow
struct to 0. Fix those locations. Currently, flowi4_multipath_hash
is random garbage and affects the hash value computed by
fib_multipath_hash for multipath selection.

Fixes: 24ba14406c5c ("route: Add multipath_hash in flowi_common to make user-define hash")
Signed-off-by: David Ahern <dsahern@gmail.com>
Cc: wenxu <wenxu@ucloud.cn>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow.h      | 1 +
 net/core/filter.c       | 1 +
 net/ipv4/fib_frontend.c | 1 +
 net/ipv4/route.c        | 1 +
 4 files changed, 4 insertions(+)

diff --git a/include/net/flow.h b/include/net/flow.h
index a50fb77a0b27..d058e63fb59a 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -116,6 +116,7 @@ static inline void flowi4_init_output(struct flowi4 *fl4, int oif,
 	fl4->saddr = saddr;
 	fl4->fl4_dport = dport;
 	fl4->fl4_sport = sport;
+	fl4->flowi4_multipath_hash = 0;
 }
 
 /* Reset some input parameters after previous lookup */
diff --git a/net/core/filter.c b/net/core/filter.c
index a69e79327c29..d13ea1642b97 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4774,6 +4774,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	fl4.saddr = params->ipv4_src;
 	fl4.fl4_sport = params->sport;
 	fl4.fl4_dport = params->dport;
+	fl4.flowi4_multipath_hash = 0;
 
 	if (flags & BPF_FIB_LOOKUP_DIRECT) {
 		u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 41079490a118..86a23e4a6a50 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -362,6 +362,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 	fl4.flowi4_tun_key.tun_id = 0;
 	fl4.flowi4_flags = 0;
 	fl4.flowi4_uid = sock_net_uid(net, NULL);
+	fl4.flowi4_multipath_hash = 0;
 
 	no_addr = idev->ifa_list == NULL;
 
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index a01efa062f6b..467f0290dc56 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2142,6 +2142,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	fl4.daddr = daddr;
 	fl4.saddr = saddr;
 	fl4.flowi4_uid = sock_net_uid(net, NULL);
+	fl4.flowi4_multipath_hash = 0;
 
 	if (fib4_rules_early_flow_dissect(net, skb, &fl4, &_flkeys)) {
 		flkeys = &_flkeys;
-- 
2.26.2


From df200db821ee96e02b56141e022412ddd9507b89 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@kernel.org>
Date: Mon, 14 Sep 2020 21:03:54 -0600
Subject: [PATCH 11/54] ipv4: Update exception handling for multipath routes
 via same device

[ Upstream commit 2fbc6e89b2f1403189e624cabaf73e189c5e50c6 ]

Kfir reported that pmtu exceptions are not created properly for
deployments where multipath routes use the same device.

After some digging I see 2 compounding problems:
1. ip_route_output_key_hash_rcu is updating the flowi4_oif *after*
   the route lookup. This is the second use case where this has
   been a problem (the first is related to use of vti devices with
   VRF). I can not find any reason for the oif to be changed after the
   lookup; the code goes back to the start of git. It does not seem
   logical so remove it.

2. fib_lookups for exceptions do not call fib_select_path to handle
   multipath route selection based on the hash.

The end result is that the fib_lookup used to add the exception
always creates it based using the first leg of the route.

An example topology showing the problem:

                 |  host1
             +------+
             | eth0 |  .209
             +------+
                 |
             +------+
     switch  | br0  |
             +------+
                 |
       +---------+---------+
       | host2             |  host3
   +------+             +------+
   | eth0 | .250        | eth0 | 192.168.252.252
   +------+             +------+

   +-----+             +-----+
   | vti | .2          | vti | 192.168.247.3
   +-----+             +-----+
       \                  /
 =================================
 tunnels
         192.168.247.1/24

for h in host1 host2 host3; do
        ip netns add ${h}
        ip -netns ${h} link set lo up
        ip netns exec ${h} sysctl -wq net.ipv4.ip_forward=1
done

ip netns add switch
ip -netns switch li set lo up
ip -netns switch link add br0 type bridge stp 0
ip -netns switch link set br0 up

for n in 1 2 3; do
        ip -netns switch link add eth-sw type veth peer name eth-h${n}
        ip -netns switch li set eth-h${n} master br0 up
        ip -netns switch li set eth-sw netns host${n} name eth0
done

ip -netns host1 addr add 192.168.252.209/24 dev eth0
ip -netns host1 link set dev eth0 up
ip -netns host1 route add 192.168.247.0/24 \
        nexthop via 192.168.252.250 dev eth0 nexthop via 192.168.252.252 dev eth0

ip -netns host2 addr add 192.168.252.250/24 dev eth0
ip -netns host2 link set dev eth0 up

ip -netns host2 addr add 192.168.252.252/24 dev eth0
ip -netns host3 link set dev eth0 up

ip netns add tunnel
ip -netns tunnel li set lo up
ip -netns tunnel li add br0 type bridge
ip -netns tunnel li set br0 up
for n in $(seq 11 20); do
        ip -netns tunnel addr add dev br0 192.168.247.${n}/24
done

for n in 2 3
do
        ip -netns tunnel link add vti${n} type veth peer name eth${n}
        ip -netns tunnel link set eth${n} mtu 1360 master br0 up
        ip -netns tunnel link set vti${n} netns host${n} mtu 1360 up
        ip -netns host${n} addr add dev vti${n} 192.168.247.${n}/24
done
ip -netns tunnel ro add default nexthop via 192.168.247.2 nexthop via 192.168.247.3

ip netns exec host1 ping -M do -s 1400 -c3 -I 192.168.252.209 192.168.247.11
ip netns exec host1 ping -M do -s 1400 -c3 -I 192.168.252.209 192.168.247.15
ip -netns host1 ro ls cache

Before this patch the cache always shows exceptions against the first
leg in the multipath route; 192.168.252.250 per this example. Since the
hash has an initial random seed, you may need to vary the final octet
more than what is listed. In my tests, using addresses between 11 and 19
usually found 1 that used both legs.

With this patch, the cache will have exceptions for both legs.

Fixes: 4895c771c7f0 ("ipv4: Add FIB nexthop exceptions")
Reported-by: Kfir Itzhak <mastertheknife@gmail.com>
Signed-off-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 467f0290dc56..37f128889474 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -786,8 +786,10 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
 			neigh_event_send(n, NULL);
 		} else {
 			if (fib_lookup(net, fl4, &res, 0) == 0) {
-				struct fib_nh_common *nhc = FIB_RES_NHC(res);
+				struct fib_nh_common *nhc;
 
+				fib_select_path(net, &res, fl4, skb);
+				nhc = FIB_RES_NHC(res);
 				update_or_create_fnhe(nhc, fl4->daddr, new_gw,
 						0, false,
 						jiffies + ip_rt_gc_timeout);
@@ -1013,6 +1015,7 @@ out:	kfree_skb(skb);
 static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
 {
 	struct dst_entry *dst = &rt->dst;
+	struct net *net = dev_net(dst->dev);
 	u32 old_mtu = ipv4_mtu(dst);
 	struct fib_result res;
 	bool lock = false;
@@ -1033,9 +1036,11 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
 		return;
 
 	rcu_read_lock();
-	if (fib_lookup(dev_net(dst->dev), fl4, &res, 0) == 0) {
-		struct fib_nh_common *nhc = FIB_RES_NHC(res);
+	if (fib_lookup(net, fl4, &res, 0) == 0) {
+		struct fib_nh_common *nhc;
 
+		fib_select_path(net, &res, fl4, NULL);
+		nhc = FIB_RES_NHC(res);
 		update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock,
 				      jiffies + ip_rt_mtu_expires);
 	}
@@ -2663,8 +2668,6 @@ struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4,
 	fib_select_path(net, res, fl4, skb);
 
 	dev_out = FIB_RES_DEV(*res);
-	fl4->flowi4_oif = dev_out->ifindex;
-
 
 make_route:
 	rth = __mkroute_output(res, fl4, orig_oif, dev_out, flags);
-- 
2.26.2


From 9233e452e829984e82c36b6a1301d0e79b1693b8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 8 Sep 2020 01:20:23 -0700
Subject: [PATCH 12/54] ipv6: avoid lockdep issue in fib6_del()

[ Upstream commit 843d926b003ea692468c8cc5bea1f9f58dfa8c75 ]

syzbot reported twice a lockdep issue in fib6_del() [1]
which I think is caused by net->ipv6.fib6_null_entry
having a NULL fib6_table pointer.

fib6_del() already checks for fib6_null_entry special
case, we only need to return earlier.

Bug seems to occur very rarely, I have thus chosen
a 'bug origin' that makes backports not too complex.

[1]
WARNING: suspicious RCU usage
5.9.0-rc4-syzkaller #0 Not tainted
-----------------------------
net/ipv6/ip6_fib.c:1996 suspicious rcu_dereference_protected() usage!

other info that might help us debug this:

rcu_scheduler_active = 2, debug_locks = 1
4 locks held by syz-executor.5/8095:
 #0: ffffffff8a7ea708 (rtnl_mutex){+.+.}-{3:3}, at: ppp_release+0x178/0x240 drivers/net/ppp/ppp_generic.c:401
 #1: ffff88804c422dd8 (&net->ipv6.fib6_gc_lock){+.-.}-{2:2}, at: spin_trylock_bh include/linux/spinlock.h:414 [inline]
 #1: ffff88804c422dd8 (&net->ipv6.fib6_gc_lock){+.-.}-{2:2}, at: fib6_run_gc+0x21b/0x2d0 net/ipv6/ip6_fib.c:2312
 #2: ffffffff89bd6a40 (rcu_read_lock){....}-{1:2}, at: __fib6_clean_all+0x0/0x290 net/ipv6/ip6_fib.c:2613
 #3: ffff8880a82e6430 (&tb->tb6_lock){+.-.}-{2:2}, at: spin_lock_bh include/linux/spinlock.h:359 [inline]
 #3: ffff8880a82e6430 (&tb->tb6_lock){+.-.}-{2:2}, at: __fib6_clean_all+0x107/0x290 net/ipv6/ip6_fib.c:2245

stack backtrace:
CPU: 1 PID: 8095 Comm: syz-executor.5 Not tainted 5.9.0-rc4-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x198/0x1fd lib/dump_stack.c:118
 fib6_del+0x12b4/0x1630 net/ipv6/ip6_fib.c:1996
 fib6_clean_node+0x39b/0x570 net/ipv6/ip6_fib.c:2180
 fib6_walk_continue+0x4aa/0x8e0 net/ipv6/ip6_fib.c:2102
 fib6_walk+0x182/0x370 net/ipv6/ip6_fib.c:2150
 fib6_clean_tree+0xdb/0x120 net/ipv6/ip6_fib.c:2230
 __fib6_clean_all+0x120/0x290 net/ipv6/ip6_fib.c:2246
 fib6_clean_all net/ipv6/ip6_fib.c:2257 [inline]
 fib6_run_gc+0x113/0x2d0 net/ipv6/ip6_fib.c:2320
 ndisc_netdev_event+0x217/0x350 net/ipv6/ndisc.c:1805
 notifier_call_chain+0xb5/0x200 kernel/notifier.c:83
 call_netdevice_notifiers_info+0xb5/0x130 net/core/dev.c:2033
 call_netdevice_notifiers_extack net/core/dev.c:2045 [inline]
 call_netdevice_notifiers net/core/dev.c:2059 [inline]
 dev_close_many+0x30b/0x650 net/core/dev.c:1634
 rollback_registered_many+0x3a8/0x1210 net/core/dev.c:9261
 rollback_registered net/core/dev.c:9329 [inline]
 unregister_netdevice_queue+0x2dd/0x570 net/core/dev.c:10410
 unregister_netdevice include/linux/netdevice.h:2774 [inline]
 ppp_release+0x216/0x240 drivers/net/ppp/ppp_generic.c:403
 __fput+0x285/0x920 fs/file_table.c:281
 task_work_run+0xdd/0x190 kernel/task_work.c:141
 tracehook_notify_resume include/linux/tracehook.h:188 [inline]
 exit_to_user_mode_loop kernel/entry/common.c:163 [inline]
 exit_to_user_mode_prepare+0x1e1/0x200 kernel/entry/common.c:190
 syscall_exit_to_user_mode+0x7e/0x2e0 kernel/entry/common.c:265
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 421842edeaf6 ("net/ipv6: Add fib6_null_entry")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: David Ahern <dsahern@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_fib.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 49ee89bbcba0..3c32dcb5fd8e 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1992,14 +1992,19 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
 /* Need to own table->tb6_lock */
 int fib6_del(struct fib6_info *rt, struct nl_info *info)
 {
-	struct fib6_node *fn = rcu_dereference_protected(rt->fib6_node,
-				    lockdep_is_held(&rt->fib6_table->tb6_lock));
-	struct fib6_table *table = rt->fib6_table;
 	struct net *net = info->nl_net;
 	struct fib6_info __rcu **rtp;
 	struct fib6_info __rcu **rtp_next;
+	struct fib6_table *table;
+	struct fib6_node *fn;
+
+	if (rt == net->ipv6.fib6_null_entry)
+		return -ENOENT;
 
-	if (!fn || rt == net->ipv6.fib6_null_entry)
+	table = rt->fib6_table;
+	fn = rcu_dereference_protected(rt->fib6_node,
+				       lockdep_is_held(&table->tb6_lock));
+	if (!fn)
 		return -ENOENT;
 
 	WARN_ON(!(fn->fn_flags & RTN_RTINFO));
-- 
2.26.2


From d910c1f2d97011a85a19a0cb3be0e31ffc104573 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Tue, 22 Sep 2020 01:07:09 +0300
Subject: [PATCH 13/54] net: bridge: br_vlan_get_pvid_rcu() should dereference
 the VLAN group under RCU

[ Upstream commit 99f62a746066fa436aa15d4606a538569540db08 ]

When calling the RCU brother of br_vlan_get_pvid(), lockdep warns:

=============================
WARNING: suspicious RCU usage
5.9.0-rc3-01631-g13c17acb8e38-dirty #814 Not tainted
-----------------------------
net/bridge/br_private.h:1054 suspicious rcu_dereference_protected() usage!

Call trace:
 lockdep_rcu_suspicious+0xd4/0xf8
 __br_vlan_get_pvid+0xc0/0x100
 br_vlan_get_pvid_rcu+0x78/0x108

The warning is because br_vlan_get_pvid_rcu() calls nbp_vlan_group()
which calls rtnl_dereference() instead of rcu_dereference(). In turn,
rtnl_dereference() calls rcu_dereference_protected() which assumes
operation under an RCU write-side critical section, which obviously is
not the case here. So, when the incorrect primitive is used to access
the RCU-protected VLAN group pointer, READ_ONCE() is not used, which may
cause various unexpected problems.

I'm sad to say that br_vlan_get_pvid() and br_vlan_get_pvid_rcu() cannot
share the same implementation. So fix the bug by splitting the 2
functions, and making br_vlan_get_pvid_rcu() retrieve the VLAN groups
under proper locking annotations.

Fixes: 7582f5b70f9a ("bridge: add br_vlan_get_pvid_rcu()")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_vlan.c | 27 +++++++++++++++++----------
 1 file changed, 17 insertions(+), 10 deletions(-)

diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index f9092c71225f..61c94cefa843 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -1288,11 +1288,13 @@ void br_vlan_get_stats(const struct net_bridge_vlan *v,
 	}
 }
 
-static int __br_vlan_get_pvid(const struct net_device *dev,
-			      struct net_bridge_port *p, u16 *p_pvid)
+int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid)
 {
 	struct net_bridge_vlan_group *vg;
+	struct net_bridge_port *p;
 
+	ASSERT_RTNL();
+	p = br_port_get_check_rtnl(dev);
 	if (p)
 		vg = nbp_vlan_group(p);
 	else if (netif_is_bridge_master(dev))
@@ -1303,18 +1305,23 @@ static int __br_vlan_get_pvid(const struct net_device *dev,
 	*p_pvid = br_get_pvid(vg);
 	return 0;
 }
-
-int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid)
-{
-	ASSERT_RTNL();
-
-	return __br_vlan_get_pvid(dev, br_port_get_check_rtnl(dev), p_pvid);
-}
 EXPORT_SYMBOL_GPL(br_vlan_get_pvid);
 
 int br_vlan_get_pvid_rcu(const struct net_device *dev, u16 *p_pvid)
 {
-	return __br_vlan_get_pvid(dev, br_port_get_check_rcu(dev), p_pvid);
+	struct net_bridge_vlan_group *vg;
+	struct net_bridge_port *p;
+
+	p = br_port_get_check_rcu(dev);
+	if (p)
+		vg = nbp_vlan_group_rcu(p);
+	else if (netif_is_bridge_master(dev))
+		vg = br_vlan_group_rcu(netdev_priv(dev));
+	else
+		return -EINVAL;
+
+	*p_pvid = br_get_pvid(vg);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(br_vlan_get_pvid_rcu);
 
-- 
2.26.2


From 1a8a058ecc7907379e76f99762496b0863cfe93d Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Thu, 10 Sep 2020 14:09:05 +0200
Subject: [PATCH 14/54] net: DCB: Validate DCB_ATTR_DCB_BUFFER argument

[ Upstream commit 297e77e53eadb332d5062913447b104a772dc33b ]

The parameter passed via DCB_ATTR_DCB_BUFFER is a struct dcbnl_buffer. The
field prio2buffer is an array of IEEE_8021Q_MAX_PRIORITIES bytes, where
each value is a number of a buffer to direct that priority's traffic to.
That value is however never validated to lie within the bounds set by
DCBX_MAX_BUFFERS. The only driver that currently implements the callback is
mlx5 (maintainers CCd), and that does not do any validation either, in
particual allowing incorrect configuration if the prio2buffer value does
not fit into 4 bits.

Instead of offloading the need to validate the buffer index to drivers, do
it right there in core, and bounce the request if the value is too large.

CC: Parav Pandit <parav@nvidia.com>
CC: Saeed Mahameed <saeedm@nvidia.com>
Fixes: e549f6f9c098 ("net/dcb: Add dcbnl buffer attribute")
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dcb/dcbnl.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index d2a4553bcf39..0fd1c2aa1361 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -1426,6 +1426,7 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh,
 {
 	const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops;
 	struct nlattr *ieee[DCB_ATTR_IEEE_MAX + 1];
+	int prio;
 	int err;
 
 	if (!ops)
@@ -1475,6 +1476,13 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh,
 		struct dcbnl_buffer *buffer =
 			nla_data(ieee[DCB_ATTR_DCB_BUFFER]);
 
+		for (prio = 0; prio < ARRAY_SIZE(buffer->prio2buffer); prio++) {
+			if (buffer->prio2buffer[prio] >= DCBX_MAX_BUFFERS) {
+				err = -EINVAL;
+				goto err;
+			}
+		}
+
 		err = ops->dcbnl_setbuffer(netdev, buffer);
 		if (err)
 			goto err;
-- 
2.26.2


From f4bb64a1bb9365f4c7c3badc91e611f00a09c059 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Sat, 5 Sep 2020 12:32:33 +0200
Subject: [PATCH 15/54] net: dsa: rtl8366: Properly clear member config

[ Upstream commit 4ddcaf1ebb5e4e99240f29d531ee69d4244fe416 ]

When removing a port from a VLAN we are just erasing the
member config for the VLAN, which is wrong: other ports
can be using it.

Just mask off the port and only zero out the rest of the
member config once ports using of the VLAN are removed
from it.

Reported-by: Florian Fainelli <f.fainelli@gmail.com>
Fixes: d8652956cf37 ("net: dsa: realtek-smi: Add Realtek SMI driver")
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/rtl8366.c | 20 +++++++++++++-------
 1 file changed, 13 insertions(+), 7 deletions(-)

diff --git a/drivers/net/dsa/rtl8366.c b/drivers/net/dsa/rtl8366.c
index 1368816abaed..99cdb2f18fa2 100644
--- a/drivers/net/dsa/rtl8366.c
+++ b/drivers/net/dsa/rtl8366.c
@@ -452,13 +452,19 @@ int rtl8366_vlan_del(struct dsa_switch *ds, int port,
 				return ret;
 
 			if (vid == vlanmc.vid) {
-				/* clear VLAN member configurations */
-				vlanmc.vid = 0;
-				vlanmc.priority = 0;
-				vlanmc.member = 0;
-				vlanmc.untag = 0;
-				vlanmc.fid = 0;
-
+				/* Remove this port from the VLAN */
+				vlanmc.member &= ~BIT(port);
+				vlanmc.untag &= ~BIT(port);
+				/*
+				 * If no ports are members of this VLAN
+				 * anymore then clear the whole member
+				 * config so it can be reused.
+				 */
+				if (!vlanmc.member && vlanmc.untag) {
+					vlanmc.vid = 0;
+					vlanmc.priority = 0;
+					vlanmc.fid = 0;
+				}
 				ret = smi->ops->set_vlan_mc(smi, i, &vlanmc);
 				if (ret) {
 					dev_err(smi->dev,
-- 
2.26.2


From c993f13697a3eeb6d9e38adbc38f2192931c8b86 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 10 Sep 2020 14:01:26 +0300
Subject: [PATCH 16/54] net: Fix bridge enslavement failure

[ Upstream commit e1b9efe6baebe79019a2183176686a0e709388ae ]

When a netdev is enslaved to a bridge, its parent identifier is queried.
This is done so that packets that were already forwarded in hardware
will not be forwarded again by the bridge device between netdevs
belonging to the same hardware instance.

The operation fails when the netdev is an upper of netdevs with
different parent identifiers.

Instead of failing the enslavement, have dev_get_port_parent_id() return
'-EOPNOTSUPP' which will signal the bridge to skip the query operation.
Other callers of the function are not affected by this change.

Fixes: 7e1146e8c10c ("net: devlink: introduce devlink_compat_switch_id_get() helper")
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reported-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Nikolay Aleksandrov <nikolay@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 5bd0b550893f..181b13e02bdc 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8641,7 +8641,7 @@ int dev_get_port_parent_id(struct net_device *dev,
 		if (!first.id_len)
 			first = *ppid;
 		else if (memcmp(&first, ppid, sizeof(*ppid)))
-			return -ENODATA;
+			return -EOPNOTSUPP;
 	}
 
 	return err;
-- 
2.26.2


From 230bb5b28bddbb65d75f50db43086a02ad90ff9c Mon Sep 17 00:00:00 2001
From: Necip Fazil Yildiran <fazilyildiran@gmail.com>
Date: Thu, 17 Sep 2020 19:46:43 +0300
Subject: [PATCH 17/54] net: ipv6: fix kconfig dependency warning for
 IPV6_SEG6_HMAC

[ Upstream commit db7cd91a4be15e1485d6b58c6afc8761c59c4efb ]

When IPV6_SEG6_HMAC is enabled and CRYPTO is disabled, it results in the
following Kbuild warning:

WARNING: unmet direct dependencies detected for CRYPTO_HMAC
  Depends on [n]: CRYPTO [=n]
  Selected by [y]:
  - IPV6_SEG6_HMAC [=y] && NET [=y] && INET [=y] && IPV6 [=y]

WARNING: unmet direct dependencies detected for CRYPTO_SHA1
  Depends on [n]: CRYPTO [=n]
  Selected by [y]:
  - IPV6_SEG6_HMAC [=y] && NET [=y] && INET [=y] && IPV6 [=y]

WARNING: unmet direct dependencies detected for CRYPTO_SHA256
  Depends on [n]: CRYPTO [=n]
  Selected by [y]:
  - IPV6_SEG6_HMAC [=y] && NET [=y] && INET [=y] && IPV6 [=y]

The reason is that IPV6_SEG6_HMAC selects CRYPTO_HMAC, CRYPTO_SHA1, and
CRYPTO_SHA256 without depending on or selecting CRYPTO while those configs
are subordinate to CRYPTO.

Honor the kconfig menu hierarchy to remove kconfig dependency warnings.

Fixes: bf355b8d2c30 ("ipv6: sr: add core files for SR HMAC support")
Signed-off-by: Necip Fazil Yildiran <fazilyildiran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index f4f19e89af5e..9d66af9e4c7f 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -303,6 +303,7 @@ config IPV6_SEG6_LWTUNNEL
 config IPV6_SEG6_HMAC
 	bool "IPv6: Segment Routing HMAC support"
 	depends on IPV6
+	select CRYPTO
 	select CRYPTO_HMAC
 	select CRYPTO_SHA1
 	select CRYPTO_SHA256
-- 
2.26.2


From c209e314b282fdcaf9741fec4aafa4e1a8192afa Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@nvidia.com>
Date: Mon, 31 Aug 2020 20:50:42 +0300
Subject: [PATCH 18/54] net/mlx5: Fix FTE cleanup

[ Upstream commit cefc23554fc259114e78a7b0908aac4610ee18eb ]

Currently, when an FTE is allocated, its refcount is decreased to 0
with the purpose it will not be a stand alone steering object and every
rule (destination) of the FTE would increase the refcount.
When mlx5_cleanup_fs is called while not all rules were deleted by the
steering users, it hit refcount underflow on the FTE once clean_tree
calls to tree_remove_node after the deleted rules already decreased
the refcount to 0.

FTE is no longer destroyed implicitly when the last rule (destination)
is deleted. mlx5_del_flow_rules avoids it by increasing the refcount on
the FTE and destroy it explicitly after all rules were deleted. So we
can avoid the refcount underflow by making FTE as stand alone object.
In addition need to set del_hw_func to FTE so the HW object will be
destroyed when the FTE is deleted from the cleanup_tree flow.

refcount_t: underflow; use-after-free.
WARNING: CPU: 2 PID: 15715 at lib/refcount.c:28 refcount_warn_saturate+0xd9/0xe0
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
Call Trace:
 tree_put_node+0xf2/0x140 [mlx5_core]
 clean_tree+0x4e/0xf0 [mlx5_core]
 clean_tree+0x4e/0xf0 [mlx5_core]
 clean_tree+0x4e/0xf0 [mlx5_core]
 clean_tree+0x5f/0xf0 [mlx5_core]
 clean_tree+0x4e/0xf0 [mlx5_core]
 clean_tree+0x5f/0xf0 [mlx5_core]
 mlx5_cleanup_fs+0x26/0x270 [mlx5_core]
 mlx5_unload+0x2e/0xa0 [mlx5_core]
 mlx5_unload_one+0x51/0x120 [mlx5_core]
 mlx5_devlink_reload_down+0x51/0x90 [mlx5_core]
 devlink_reload+0x39/0x120
 ? devlink_nl_cmd_reload+0x43/0x220
 genl_rcv_msg+0x1e4/0x420
 ? genl_family_rcv_msg_attrs_parse+0x100/0x100
 netlink_rcv_skb+0x47/0x110
 genl_rcv+0x24/0x40
 netlink_unicast+0x217/0x2f0
 netlink_sendmsg+0x30f/0x430
 sock_sendmsg+0x30/0x40
 __sys_sendto+0x10e/0x140
 ? handle_mm_fault+0xc4/0x1f0
 ? do_page_fault+0x33f/0x630
 __x64_sys_sendto+0x24/0x30
 do_syscall_64+0x48/0x130
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 718ce4d601db ("net/mlx5: Consolidate update FTE for all removal changes")
Fixes: bd71b08ec2ee ("net/mlx5: Support multiple updates of steering rules in parallel")
Signed-off-by: Maor Gottlieb <maorg@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 2e5f7efb82a8..1f96f9efa3c1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -655,7 +655,7 @@ static struct fs_fte *alloc_fte(struct mlx5_flow_table *ft,
 	fte->action = *flow_act;
 	fte->flow_context = spec->flow_context;
 
-	tree_init_node(&fte->node, NULL, del_sw_fte);
+	tree_init_node(&fte->node, del_hw_fte, del_sw_fte);
 
 	return fte;
 }
@@ -1792,7 +1792,6 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft,
 		up_write_ref_node(&g->node, false);
 		rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte);
 		up_write_ref_node(&fte->node, false);
-		tree_put_node(&fte->node, false);
 		return rule;
 	}
 	rule = ERR_PTR(-ENOENT);
@@ -1891,7 +1890,6 @@ _mlx5_add_flow_rules(struct mlx5_flow_table *ft,
 	up_write_ref_node(&g->node, false);
 	rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte);
 	up_write_ref_node(&fte->node, false);
-	tree_put_node(&fte->node, false);
 	tree_put_node(&g->node, false);
 	return rule;
 
@@ -2001,7 +1999,9 @@ void mlx5_del_flow_rules(struct mlx5_flow_handle *handle)
 		up_write_ref_node(&fte->node, false);
 	} else {
 		del_hw_fte(&fte->node);
-		up_write(&fte->node.lock);
+		/* Avoid double call to del_hw_fte */
+		fte->node.del_hw_func = NULL;
+		up_write_ref_node(&fte->node, false);
 		tree_put_node(&fte->node, false);
 	}
 	kfree(handle);
-- 
2.26.2


From accccedb4f361dc7da4f722fba6806adfdb3395d Mon Sep 17 00:00:00 2001
From: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Date: Wed, 9 Sep 2020 14:43:14 +0900
Subject: [PATCH 19/54] net: phy: call phy_disable_interrupts() in
 phy_attach_direct() instead

[ Upstream commit 7d3ba9360c6dac7c077fbd6631e08f32ea2bcd53 ]

Since the micrel phy driver calls phy_init_hw() as a workaround,
the commit 9886a4dbd2aa ("net: phy: call phy_disable_interrupts()
in phy_init_hw()") disables the interrupt unexpectedly. So,
call phy_disable_interrupts() in phy_attach_direct() instead.
Otherwise, the phy cannot link up after the ethernet cable was
disconnected.

Note that other drivers (like at803x.c) also calls phy_init_hw().
So, perhaps, the driver caused a similar issue too.

Fixes: 9886a4dbd2aa ("net: phy: call phy_disable_interrupts() in phy_init_hw()")
Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 98369430a3be..aa23fd0ccc53 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1092,10 +1092,6 @@ int phy_init_hw(struct phy_device *phydev)
 	if (ret < 0)
 		return ret;
 
-	ret = phy_disable_interrupts(phydev);
-	if (ret)
-		return ret;
-
 	if (phydev->drv->config_init)
 		ret = phydev->drv->config_init(phydev);
 
@@ -1372,6 +1368,10 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
 	if (err)
 		goto error;
 
+	err = phy_disable_interrupts(phydev);
+	if (err)
+		return err;
+
 	phy_resume(phydev);
 	phy_led_triggers_register(phydev);
 
-- 
2.26.2


From 00908e52dd8694948ac002222400d65794afec71 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 13 Sep 2020 19:43:03 +0800
Subject: [PATCH 20/54] net: sched: initialize with 0 before setting erspan
 md->u

[ Upstream commit 8e1b3ac4786680c2d2b5a24e38a2d714c3bcd1ef ]

In fl_set_erspan_opt(), all bits of erspan md was set 1, as this
function is also used to set opt MASK. However, when setting for
md->u.index for opt VALUE, the rest bits of the union md->u will
be left 1. It would cause to fail the match of the whole md when
version is 1 and only index is set.

This patch is to fix by initializing with 0 before setting erspan
md->u.

Reported-by: Shuang Li <shuali@redhat.com>
Fixes: 79b1011cb33d ("net: sched: allow flower to match erspan options")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_flower.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index e30bd969fc48..5fe145d97f52 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -1215,6 +1215,7 @@ static int fl_set_erspan_opt(const struct nlattr *nla, struct fl_flow_key *key,
 		}
 		if (tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX]) {
 			nla = tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX];
+			memset(&md->u, 0x00, sizeof(md->u));
 			md->u.index = nla_get_be32(nla);
 		}
 	} else if (md->version == 2) {
-- 
2.26.2


From 989abade8d4ea4e330113b7d324998f66c24fb81 Mon Sep 17 00:00:00 2001
From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Tue, 8 Sep 2020 19:02:34 +0800
Subject: [PATCH 21/54] net: sch_generic: aviod concurrent reset and enqueue op
 for lockless qdisc

[ Upstream commit 2fb541c862c987d02dfdf28f1545016deecfa0d5 ]

Currently there is concurrent reset and enqueue operation for the
same lockless qdisc when there is no lock to synchronize the
q->enqueue() in __dev_xmit_skb() with the qdisc reset operation in
qdisc_deactivate() called by dev_deactivate_queue(), which may cause
out-of-bounds access for priv->ring[] in hns3 driver if user has
requested a smaller queue num when __dev_xmit_skb() still enqueue a
skb with a larger queue_mapping after the corresponding qdisc is
reset, and call hns3_nic_net_xmit() with that skb later.

Reused the existing synchronize_net() in dev_deactivate_many() to
make sure skb with larger queue_mapping enqueued to old qdisc(which
is saved in dev_queue->qdisc_sleeping) will always be reset when
dev_reset_queue() is called.

Fixes: 6b3ba9146fe6 ("net: sched: allow qdiscs to handle locking")
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_generic.c | 48 ++++++++++++++++++++++++++++-------------
 1 file changed, 33 insertions(+), 15 deletions(-)

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 265a61d011df..54c417244642 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -1131,24 +1131,10 @@ EXPORT_SYMBOL(dev_activate);
 
 static void qdisc_deactivate(struct Qdisc *qdisc)
 {
-	bool nolock = qdisc->flags & TCQ_F_NOLOCK;
-
 	if (qdisc->flags & TCQ_F_BUILTIN)
 		return;
-	if (test_bit(__QDISC_STATE_DEACTIVATED, &qdisc->state))
-		return;
-
-	if (nolock)
-		spin_lock_bh(&qdisc->seqlock);
-	spin_lock_bh(qdisc_lock(qdisc));
 
 	set_bit(__QDISC_STATE_DEACTIVATED, &qdisc->state);
-
-	qdisc_reset(qdisc);
-
-	spin_unlock_bh(qdisc_lock(qdisc));
-	if (nolock)
-		spin_unlock_bh(&qdisc->seqlock);
 }
 
 static void dev_deactivate_queue(struct net_device *dev,
@@ -1165,6 +1151,30 @@ static void dev_deactivate_queue(struct net_device *dev,
 	}
 }
 
+static void dev_reset_queue(struct net_device *dev,
+			    struct netdev_queue *dev_queue,
+			    void *_unused)
+{
+	struct Qdisc *qdisc;
+	bool nolock;
+
+	qdisc = dev_queue->qdisc_sleeping;
+	if (!qdisc)
+		return;
+
+	nolock = qdisc->flags & TCQ_F_NOLOCK;
+
+	if (nolock)
+		spin_lock_bh(&qdisc->seqlock);
+	spin_lock_bh(qdisc_lock(qdisc));
+
+	qdisc_reset(qdisc);
+
+	spin_unlock_bh(qdisc_lock(qdisc));
+	if (nolock)
+		spin_unlock_bh(&qdisc->seqlock);
+}
+
 static bool some_qdisc_is_busy(struct net_device *dev)
 {
 	unsigned int i;
@@ -1213,12 +1223,20 @@ void dev_deactivate_many(struct list_head *head)
 		dev_watchdog_down(dev);
 	}
 
-	/* Wait for outstanding qdisc-less dev_queue_xmit calls.
+	/* Wait for outstanding qdisc-less dev_queue_xmit calls or
+	 * outstanding qdisc enqueuing calls.
 	 * This is avoided if all devices are in dismantle phase :
 	 * Caller will call synchronize_net() for us
 	 */
 	synchronize_net();
 
+	list_for_each_entry(dev, head, close_list) {
+		netdev_for_each_tx_queue(dev, dev_reset_queue, NULL);
+
+		if (dev_ingress_queue(dev))
+			dev_reset_queue(dev, dev_ingress_queue(dev), NULL);
+	}
+
 	/* Wait for outstanding qdisc_run calls. */
 	list_for_each_entry(dev, head, close_list) {
 		while (some_qdisc_is_busy(dev)) {
-- 
2.26.2


From fd3eac43899d021d9c6102dee11a4fbb88e318b1 Mon Sep 17 00:00:00 2001
From: Henry Ptasinski <hptasinski@google.com>
Date: Sat, 19 Sep 2020 00:12:11 +0000
Subject: [PATCH 22/54] net: sctp: Fix IPv6 ancestor_size calc in
 sctp_copy_descendant

[ Upstream commit fe81d9f6182d1160e625894eecb3d7ff0222cac5 ]

When calculating ancestor_size with IPv6 enabled, simply using
sizeof(struct ipv6_pinfo) doesn't account for extra bytes needed for
alignment in the struct sctp6_sock. On x86, there aren't any extra
bytes, but on ARM the ipv6_pinfo structure is aligned on an 8-byte
boundary so there were 4 pad bytes that were omitted from the
ancestor_size calculation.  This would lead to corruption of the
pd_lobby pointers, causing an oops when trying to free the sctp
structure on socket close.

Fixes: 636d25d557d1 ("sctp: not copy sctp_sock pd_lobby in sctp_copy_descendant")
Signed-off-by: Henry Ptasinski <hptasinski@google.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/structs.h | 8 +++++---
 net/sctp/socket.c          | 9 +++------
 2 files changed, 8 insertions(+), 9 deletions(-)

diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index fb42c90348d3..f3c5d9d2f82d 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -226,12 +226,14 @@ struct sctp_sock {
 		data_ready_signalled:1;
 
 	atomic_t pd_mode;
+
+	/* Fields after this point will be skipped on copies, like on accept
+	 * and peeloff operations
+	 */
+
 	/* Receive to here while partial delivery is in effect. */
 	struct sk_buff_head pd_lobby;
 
-	/* These must be the last fields, as they will skipped on copies,
-	 * like on accept and peeloff operations
-	 */
 	struct list_head auto_asconf_list;
 	int do_auto_asconf;
 };
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index fa20e945700e..102aee4f7dfd 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -9457,13 +9457,10 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk,
 static inline void sctp_copy_descendant(struct sock *sk_to,
 					const struct sock *sk_from)
 {
-	int ancestor_size = sizeof(struct inet_sock) +
-			    sizeof(struct sctp_sock) -
-			    offsetof(struct sctp_sock, pd_lobby);
-
-	if (sk_from->sk_family == PF_INET6)
-		ancestor_size += sizeof(struct ipv6_pinfo);
+	size_t ancestor_size = sizeof(struct inet_sock);
 
+	ancestor_size += sk_from->sk_prot->obj_size;
+	ancestor_size -= offsetof(struct sctp_sock, pd_lobby);
 	__inet_sk_copy_descendant(sk_to, sk_from, ancestor_size);
 }
 
-- 
2.26.2


From 8cbe79c5df9468378400d5405fe926e834e5a7d1 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 17 Sep 2020 10:52:57 -0700
Subject: [PATCH 23/54] nfp: use correct define to return NONE fec

[ Upstream commit 5f6857e808a8bd078296575b417c4b9d160b9779 ]

struct ethtool_fecparam carries bitmasks not bit numbers.
We want to return 1 (NONE), not 0.

Fixes: 0d0870938337 ("nfp: implement ethtool FEC mode settings")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
index 6eb9fb9a1814..9c9ae33d84ce 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
@@ -829,8 +829,8 @@ nfp_port_get_fecparam(struct net_device *netdev,
 	struct nfp_eth_table_port *eth_port;
 	struct nfp_port *port;
 
-	param->active_fec = ETHTOOL_FEC_NONE_BIT;
-	param->fec = ETHTOOL_FEC_NONE_BIT;
+	param->active_fec = ETHTOOL_FEC_NONE;
+	param->fec = ETHTOOL_FEC_NONE;
 
 	port = nfp_port_from_netdev(netdev);
 	eth_port = nfp_port_get_eth_port(port);
-- 
2.26.2


From f89c503a6b2470c03db7bc267820ed8302899253 Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Wed, 9 Sep 2020 17:03:11 -0700
Subject: [PATCH 24/54] taprio: Fix allowing too small intervals

[ Upstream commit b5b73b26b3ca34574124ed7ae9c5ba8391a7f176 ]

It's possible that the user specifies an interval that couldn't allow
any packet to be transmitted. This also avoids the issue of the
hrtimer handler starving the other threads because it's running too
often.

The solution is to reject interval sizes that according to the current
link speed wouldn't allow any packet to be transmitted.

Reported-by: syzbot+8267241609ae8c23b248@syzkaller.appspotmail.com
Fixes: 5a781ccbd19e ("tc: Add support for configuring the taprio scheduler")
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_taprio.c | 28 +++++++++++++++++-----------
 1 file changed, 17 insertions(+), 11 deletions(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 6a5086e586ef..2b797a71e9bd 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -777,9 +777,11 @@ static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = {
 	[TCA_TAPRIO_ATTR_TXTIME_DELAY]		     = { .type = NLA_U32 },
 };
 
-static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry,
+static int fill_sched_entry(struct taprio_sched *q, struct nlattr **tb,
+			    struct sched_entry *entry,
 			    struct netlink_ext_ack *extack)
 {
+	int min_duration = length_to_duration(q, ETH_ZLEN);
 	u32 interval = 0;
 
 	if (tb[TCA_TAPRIO_SCHED_ENTRY_CMD])
@@ -794,7 +796,10 @@ static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry,
 		interval = nla_get_u32(
 			tb[TCA_TAPRIO_SCHED_ENTRY_INTERVAL]);
 
-	if (interval == 0) {
+	/* The interval should allow at least the minimum ethernet
+	 * frame to go out.
+	 */
+	if (interval < min_duration) {
 		NL_SET_ERR_MSG(extack, "Invalid interval for schedule entry");
 		return -EINVAL;
 	}
@@ -804,8 +809,9 @@ static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry,
 	return 0;
 }
 
-static int parse_sched_entry(struct nlattr *n, struct sched_entry *entry,
-			     int index, struct netlink_ext_ack *extack)
+static int parse_sched_entry(struct taprio_sched *q, struct nlattr *n,
+			     struct sched_entry *entry, int index,
+			     struct netlink_ext_ack *extack)
 {
 	struct nlattr *tb[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = { };
 	int err;
@@ -819,10 +825,10 @@ static int parse_sched_entry(struct nlattr *n, struct sched_entry *entry,
 
 	entry->index = index;
 
-	return fill_sched_entry(tb, entry, extack);
+	return fill_sched_entry(q, tb, entry, extack);
 }
 
-static int parse_sched_list(struct nlattr *list,
+static int parse_sched_list(struct taprio_sched *q, struct nlattr *list,
 			    struct sched_gate_list *sched,
 			    struct netlink_ext_ack *extack)
 {
@@ -847,7 +853,7 @@ static int parse_sched_list(struct nlattr *list,
 			return -ENOMEM;
 		}
 
-		err = parse_sched_entry(n, entry, i, extack);
+		err = parse_sched_entry(q, n, entry, i, extack);
 		if (err < 0) {
 			kfree(entry);
 			return err;
@@ -862,7 +868,7 @@ static int parse_sched_list(struct nlattr *list,
 	return i;
 }
 
-static int parse_taprio_schedule(struct nlattr **tb,
+static int parse_taprio_schedule(struct taprio_sched *q, struct nlattr **tb,
 				 struct sched_gate_list *new,
 				 struct netlink_ext_ack *extack)
 {
@@ -883,8 +889,8 @@ static int parse_taprio_schedule(struct nlattr **tb,
 		new->cycle_time = nla_get_s64(tb[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME]);
 
 	if (tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST])
-		err = parse_sched_list(
-			tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST], new, extack);
+		err = parse_sched_list(q, tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST],
+				       new, extack);
 	if (err < 0)
 		return err;
 
@@ -1474,7 +1480,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 		goto free_sched;
 	}
 
-	err = parse_taprio_schedule(tb, new_admin, extack);
+	err = parse_taprio_schedule(q, tb, new_admin, extack);
 	if (err < 0)
 		goto free_sched;
 
-- 
2.26.2


From 77e3227c4811399b762628b1e8a008509060fda3 Mon Sep 17 00:00:00 2001
From: Peilin Ye <yepeilin.cs@gmail.com>
Date: Sun, 13 Sep 2020 04:06:05 -0400
Subject: [PATCH 25/54] tipc: Fix memory leak in tipc_group_create_member()

[ Upstream commit bb3a420d47ab00d7e1e5083286cab15235a96680 ]

tipc_group_add_to_tree() returns silently if `key` matches `nkey` of an
existing node, causing tipc_group_create_member() to leak memory. Let
tipc_group_add_to_tree() return an error in such a case, so that
tipc_group_create_member() can handle it properly.

Fixes: 75da2163dbb6 ("tipc: introduce communication groups")
Reported-and-tested-by: syzbot+f95d90c454864b3b5bc9@syzkaller.appspotmail.com
Cc: Hillf Danton <hdanton@sina.com>
Link: https://syzkaller.appspot.com/bug?id=048390604fe1b60df34150265479202f10e13aff
Signed-off-by: Peilin Ye <yepeilin.cs@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/group.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/net/tipc/group.c b/net/tipc/group.c
index 89257e2a980d..f53871baa42e 100644
--- a/net/tipc/group.c
+++ b/net/tipc/group.c
@@ -273,8 +273,8 @@ static struct tipc_member *tipc_group_find_node(struct tipc_group *grp,
 	return NULL;
 }
 
-static void tipc_group_add_to_tree(struct tipc_group *grp,
-				   struct tipc_member *m)
+static int tipc_group_add_to_tree(struct tipc_group *grp,
+				  struct tipc_member *m)
 {
 	u64 nkey, key = (u64)m->node << 32 | m->port;
 	struct rb_node **n, *parent = NULL;
@@ -291,10 +291,11 @@ static void tipc_group_add_to_tree(struct tipc_group *grp,
 		else if (key > nkey)
 			n = &(*n)->rb_right;
 		else
-			return;
+			return -EEXIST;
 	}
 	rb_link_node(&m->tree_node, parent, n);
 	rb_insert_color(&m->tree_node, &grp->members);
+	return 0;
 }
 
 static struct tipc_member *tipc_group_create_member(struct tipc_group *grp,
@@ -302,6 +303,7 @@ static struct tipc_member *tipc_group_create_member(struct tipc_group *grp,
 						    u32 instance, int state)
 {
 	struct tipc_member *m;
+	int ret;
 
 	m = kzalloc(sizeof(*m), GFP_ATOMIC);
 	if (!m)
@@ -314,8 +316,12 @@ static struct tipc_member *tipc_group_create_member(struct tipc_group *grp,
 	m->port = port;
 	m->instance = instance;
 	m->bc_acked = grp->bc_snd_nxt - 1;
+	ret = tipc_group_add_to_tree(grp, m);
+	if (ret < 0) {
+		kfree(m);
+		return NULL;
+	}
 	grp->member_cnt++;
-	tipc_group_add_to_tree(grp, m);
 	tipc_nlist_add(&grp->dests, m->node);
 	m->state = state;
 	return m;
-- 
2.26.2


From 24f3d47529a464b859c55e256e8ba0b551267adc Mon Sep 17 00:00:00 2001
From: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Date: Sat, 5 Sep 2020 15:14:47 +0900
Subject: [PATCH 26/54] tipc: fix shutdown() of connection oriented socket

[ Upstream commit a4b5cc9e10803ecba64a7d54c0f47e4564b4a980 ]

I confirmed that the problem fixed by commit 2a63866c8b51a3f7 ("tipc: fix
shutdown() of connectionless socket") also applies to stream socket.

----------
#include <sys/socket.h>
#include <unistd.h>
#include <sys/wait.h>

int main(int argc, char *argv[])
{
        int fds[2] = { -1, -1 };
        socketpair(PF_TIPC, SOCK_STREAM /* or SOCK_DGRAM */, 0, fds);
        if (fork() == 0)
                _exit(read(fds[0], NULL, 1));
        shutdown(fds[0], SHUT_RDWR); /* This must make read() return. */
        wait(NULL); /* To be woken up by _exit(). */
        return 0;
}
----------

Since shutdown(SHUT_RDWR) should affect all processes sharing that socket,
unconditionally setting sk->sk_shutdown to SHUTDOWN_MASK will be the right
behavior.

Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/socket.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 79cc84393f93..59c9e592b0a2 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2773,10 +2773,7 @@ static int tipc_shutdown(struct socket *sock, int how)
 
 	trace_tipc_sk_shutdown(sk, NULL, TIPC_DUMP_ALL, " ");
 	__tipc_shutdown(sock, TIPC_CONN_SHUTDOWN);
-	if (tipc_sk_type_connectionless(sk))
-		sk->sk_shutdown = SHUTDOWN_MASK;
-	else
-		sk->sk_shutdown = SEND_SHUTDOWN;
+	sk->sk_shutdown = SHUTDOWN_MASK;
 
 	if (sk->sk_state == TIPC_DISCONNECTING) {
 		/* Discard any unreceived messages */
-- 
2.26.2


From a676deabd89ab25b4edeaa75411f24b87e84f1b8 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sun, 13 Sep 2020 19:37:31 +0800
Subject: [PATCH 27/54] tipc: use skb_unshare() instead in tipc_buf_append()

[ Upstream commit ff48b6222e65ebdba5a403ef1deba6214e749193 ]

In tipc_buf_append() it may change skb's frag_list, and it causes
problems when this skb is cloned. skb_unclone() doesn't really
make this skb's flag_list available to change.

Shuang Li has reported an use-after-free issue because of this
when creating quite a few macvlan dev over the same dev, where
the broadcast packets will be cloned and go up to the stack:

 [ ] BUG: KASAN: use-after-free in pskb_expand_head+0x86d/0xea0
 [ ] Call Trace:
 [ ]  dump_stack+0x7c/0xb0
 [ ]  print_address_description.constprop.7+0x1a/0x220
 [ ]  kasan_report.cold.10+0x37/0x7c
 [ ]  check_memory_region+0x183/0x1e0
 [ ]  pskb_expand_head+0x86d/0xea0
 [ ]  process_backlog+0x1df/0x660
 [ ]  net_rx_action+0x3b4/0xc90
 [ ]
 [ ] Allocated by task 1786:
 [ ]  kmem_cache_alloc+0xbf/0x220
 [ ]  skb_clone+0x10a/0x300
 [ ]  macvlan_broadcast+0x2f6/0x590 [macvlan]
 [ ]  macvlan_process_broadcast+0x37c/0x516 [macvlan]
 [ ]  process_one_work+0x66a/0x1060
 [ ]  worker_thread+0x87/0xb10
 [ ]
 [ ] Freed by task 3253:
 [ ]  kmem_cache_free+0x82/0x2a0
 [ ]  skb_release_data+0x2c3/0x6e0
 [ ]  kfree_skb+0x78/0x1d0
 [ ]  tipc_recvmsg+0x3be/0xa40 [tipc]

So fix it by using skb_unshare() instead, which would create a new
skb for the cloned frag and it'll be safe to change its frag_list.
The similar things were also done in sctp_make_reassembled_event(),
which is using skb_copy().

Reported-by: Shuang Li <shuali@redhat.com>
Fixes: 37e22164a8a3 ("tipc: rename and move message reassembly function")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/msg.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index 01b64869a173..2776a41e0dec 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -150,7 +150,8 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf)
 	if (fragid == FIRST_FRAGMENT) {
 		if (unlikely(head))
 			goto err;
-		if (unlikely(skb_unclone(frag, GFP_ATOMIC)))
+		frag = skb_unshare(frag, GFP_ATOMIC);
+		if (unlikely(!frag))
 			goto err;
 		head = *headbuf = frag;
 		*buf = NULL;
-- 
2.26.2


From 60c5fafc0ab1777ac62a1159c16e1a5d4a044840 Mon Sep 17 00:00:00 2001
From: Maor Dickman <maord@mellanox.com>
Date: Wed, 5 Aug 2020 17:56:04 +0300
Subject: [PATCH 28/54] net/mlx5e: Enable adding peer miss rules only if merged
 eswitch is supported

[ Upstream commit 6cec0229ab1959259e71e9a5bbe47c04577950b1 ]

The cited commit creates peer miss group during switchdev mode
initialization in order to handle miss packets correctly while in VF
LAG mode. This is done regardless of FW support of such groups which
could cause rules setups failure later on.

Fix by adding FW capability check before creating peer groups/rule.

Fixes: ac004b832128 ("net/mlx5e: E-Switch, Add peer miss rules")
Signed-off-by: Maor Dickman <maord@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Raed Salem <raeds@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../mellanox/mlx5/core/eswitch_offloads.c     | 52 ++++++++++---------
 1 file changed, 28 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index ed75353c56b8..f16610feab88 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -1219,35 +1219,37 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
 	}
 	esw->fdb_table.offloads.send_to_vport_grp = g;
 
-	/* create peer esw miss group */
-	memset(flow_group_in, 0, inlen);
+	if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) {
+		/* create peer esw miss group */
+		memset(flow_group_in, 0, inlen);
 
-	esw_set_flow_group_source_port(esw, flow_group_in);
+		esw_set_flow_group_source_port(esw, flow_group_in);
 
-	if (!mlx5_eswitch_vport_match_metadata_enabled(esw)) {
-		match_criteria = MLX5_ADDR_OF(create_flow_group_in,
-					      flow_group_in,
-					      match_criteria);
+		if (!mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+			match_criteria = MLX5_ADDR_OF(create_flow_group_in,
+						      flow_group_in,
+						      match_criteria);
 
-		MLX5_SET_TO_ONES(fte_match_param, match_criteria,
-				 misc_parameters.source_eswitch_owner_vhca_id);
+			MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+					 misc_parameters.source_eswitch_owner_vhca_id);
 
-		MLX5_SET(create_flow_group_in, flow_group_in,
-			 source_eswitch_owner_vhca_id_valid, 1);
-	}
+			MLX5_SET(create_flow_group_in, flow_group_in,
+				 source_eswitch_owner_vhca_id_valid, 1);
+		}
 
-	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix);
-	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index,
-		 ix + esw->total_vports - 1);
-	ix += esw->total_vports;
+		MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix);
+		MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index,
+			 ix + esw->total_vports - 1);
+		ix += esw->total_vports;
 
-	g = mlx5_create_flow_group(fdb, flow_group_in);
-	if (IS_ERR(g)) {
-		err = PTR_ERR(g);
-		esw_warn(dev, "Failed to create peer miss flow group err(%d)\n", err);
-		goto peer_miss_err;
+		g = mlx5_create_flow_group(fdb, flow_group_in);
+		if (IS_ERR(g)) {
+			err = PTR_ERR(g);
+			esw_warn(dev, "Failed to create peer miss flow group err(%d)\n", err);
+			goto peer_miss_err;
+		}
+		esw->fdb_table.offloads.peer_miss_grp = g;
 	}
-	esw->fdb_table.offloads.peer_miss_grp = g;
 
 	/* create miss group */
 	memset(flow_group_in, 0, inlen);
@@ -1282,7 +1284,8 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
 miss_rule_err:
 	mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp);
 miss_err:
-	mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp);
+	if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
+		mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp);
 peer_miss_err:
 	mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp);
 send_vport_err:
@@ -1306,7 +1309,8 @@ static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw)
 	mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule_multi);
 	mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule_uni);
 	mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp);
-	mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp);
+	if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
+		mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp);
 	mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp);
 
 	mlx5_esw_chains_destroy(esw);
-- 
2.26.2


From 46968f5c44b7223c656d4bf4113456f84d5993e0 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Sun, 28 Jun 2020 13:06:06 +0300
Subject: [PATCH 29/54] net/mlx5e: TLS, Do not expose FPGA TLS counter if not
 supported

[ Upstream commit 8f0bcd19b1da3f264223abea985b9462e85a3718 ]

The set of TLS TX global SW counters in mlx5e_tls_sw_stats_desc
is updated from all rings by using atomic ops.
This set of stats is used only in the FPGA TLS use case, not in
the Connect-X TLS one, where regular per-ring counters are used.

Do not expose them in the Connect-X use case, as this would cause
counter duplication. For example, tx_tls_drop_no_sync_data would
appear twice in the ethtool stats.

Fixes: d2ead1f360e8 ("net/mlx5e: Add kTLS TX HW offload support")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../ethernet/mellanox/mlx5/core/en_accel/tls_stats.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c
index 01468ec27446..b949b9a7538b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c
@@ -35,7 +35,6 @@
 #include <net/sock.h>
 
 #include "en.h"
-#include "accel/tls.h"
 #include "fpga/sdk.h"
 #include "en_accel/tls.h"
 
@@ -51,9 +50,14 @@ static const struct counter_desc mlx5e_tls_sw_stats_desc[] = {
 
 #define NUM_TLS_SW_COUNTERS ARRAY_SIZE(mlx5e_tls_sw_stats_desc)
 
+static bool is_tls_atomic_stats(struct mlx5e_priv *priv)
+{
+	return priv->tls && !mlx5_accel_is_ktls_device(priv->mdev);
+}
+
 int mlx5e_tls_get_count(struct mlx5e_priv *priv)
 {
-	if (!priv->tls)
+	if (!is_tls_atomic_stats(priv))
 		return 0;
 
 	return NUM_TLS_SW_COUNTERS;
@@ -63,7 +67,7 @@ int mlx5e_tls_get_strings(struct mlx5e_priv *priv, uint8_t *data)
 {
 	unsigned int i, idx = 0;
 
-	if (!priv->tls)
+	if (!is_tls_atomic_stats(priv))
 		return 0;
 
 	for (i = 0; i < NUM_TLS_SW_COUNTERS; i++)
@@ -77,7 +81,7 @@ int mlx5e_tls_get_stats(struct mlx5e_priv *priv, u64 *data)
 {
 	int i, idx = 0;
 
-	if (!priv->tls)
+	if (!is_tls_atomic_stats(priv))
 		return 0;
 
 	for (i = 0; i < NUM_TLS_SW_COUNTERS; i++)
-- 
2.26.2


From 092a2973d0cf877f6f8bc844f5d718a8522915fc Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Sun, 20 Sep 2020 21:08:54 -0400
Subject: [PATCH 30/54] bnxt_en: Use memcpy to copy VPD field info.

[ Upstream commit 492adcf481292521ee8df1a482dc12acdb28aa15 ]

Using strlcpy() to copy from VPD is not correct because VPD strings
are not necessarily NULL terminated.  Use memcpy() to copy the VPD
length up to the destination buffer size - 1.  The destination is
zeroed memory so it will always be NULL terminated.

Fixes: a0d0fd70fed5 ("bnxt_en: Read partno and serialno of the board from VPD")
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 3612039e7439..4e26a935b26f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -11807,7 +11807,7 @@ static int bnxt_init_mac_addr(struct bnxt *bp)
 static void bnxt_vpd_read_info(struct bnxt *bp)
 {
 	struct pci_dev *pdev = bp->pdev;
-	int i, len, pos, ro_size;
+	int i, len, pos, ro_size, size;
 	ssize_t vpd_size;
 	u8 *vpd_data;
 
@@ -11842,7 +11842,8 @@ static void bnxt_vpd_read_info(struct bnxt *bp)
 	if (len + pos > vpd_size)
 		goto read_sn;
 
-	strlcpy(bp->board_partno, &vpd_data[pos], min(len, BNXT_VPD_FLD_LEN));
+	size = min(len, BNXT_VPD_FLD_LEN - 1);
+	memcpy(bp->board_partno, &vpd_data[pos], size);
 
 read_sn:
 	pos = pci_vpd_find_info_keyword(vpd_data, i, ro_size,
@@ -11855,7 +11856,8 @@ static void bnxt_vpd_read_info(struct bnxt *bp)
 	if (len + pos > vpd_size)
 		goto exit;
 
-	strlcpy(bp->board_serialno, &vpd_data[pos], min(len, BNXT_VPD_FLD_LEN));
+	size = min(len, BNXT_VPD_FLD_LEN - 1);
+	memcpy(bp->board_serialno, &vpd_data[pos], size);
 exit:
 	kfree(vpd_data);
 }
-- 
2.26.2


From 5b327332d517317b8e809398a26d659096ee4dfb Mon Sep 17 00:00:00 2001
From: Edwin Peer <edwin.peer@broadcom.com>
Date: Sun, 20 Sep 2020 21:08:55 -0400
Subject: [PATCH 31/54] bnxt_en: return proper error codes in bnxt_show_temp

[ Upstream commit d69753fa1ecb3218b56b022722f7a5822735b876 ]

Returning "unknown" as a temperature value violates the hwmon interface
rules. Appropriate error codes should be returned via device_attribute
show instead. These will ultimately be propagated to the user via the
file system interface.

In addition to the corrected error handling, it is an even better idea to
not present the sensor in sysfs at all if it is known that the read will
definitely fail. Given that temp1_input is currently the only sensor
reported, ensure no hwmon registration if TEMP_MONITOR_QUERY is not
supported or if it will fail due to access permissions. Something smarter
may be needed if and when other sensors are added.

Fixes: 12cce90b934b ("bnxt_en: fix HWRM error when querying VF temperature")
Signed-off-by: Edwin Peer <edwin.peer@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 4e26a935b26f..dd07db656a5c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -8993,18 +8993,16 @@ static ssize_t bnxt_show_temp(struct device *dev,
 	struct hwrm_temp_monitor_query_output *resp;
 	struct bnxt *bp = dev_get_drvdata(dev);
 	u32 len = 0;
+	int rc;
 
 	resp = bp->hwrm_cmd_resp_addr;
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_TEMP_MONITOR_QUERY, -1, -1);
 	mutex_lock(&bp->hwrm_cmd_lock);
-	if (!_hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT))
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (!rc)
 		len = sprintf(buf, "%u\n", resp->temp * 1000); /* display millidegree */
 	mutex_unlock(&bp->hwrm_cmd_lock);
-
-	if (len)
-		return len;
-
-	return sprintf(buf, "unknown\n");
+	return rc ?: len;
 }
 static SENSOR_DEVICE_ATTR(temp1_input, 0444, bnxt_show_temp, NULL, 0);
 
@@ -9024,7 +9022,16 @@ static void bnxt_hwmon_close(struct bnxt *bp)
 
 static void bnxt_hwmon_open(struct bnxt *bp)
 {
+	struct hwrm_temp_monitor_query_input req = {0};
 	struct pci_dev *pdev = bp->pdev;
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_TEMP_MONITOR_QUERY, -1, -1);
+	rc = hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc == -EACCES || rc == -EOPNOTSUPP) {
+		bnxt_hwmon_close(bp);
+		return;
+	}
 
 	if (bp->hwmon_dev)
 		return;
-- 
2.26.2


From ef33601cacdce1a4fdd1cf02f58ef26ef168de85 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 20 Sep 2020 21:08:56 -0400
Subject: [PATCH 32/54] bnxt_en: Protect bnxt_set_eee() and
 bnxt_set_pauseparam() with mutex.

[ Upstream commit a53906908148d64423398a62c4435efb0d09652c ]

All changes related to bp->link_info require the protection of the
link_lock mutex.  It's not sufficient to rely just on RTNL.

Fixes: 163e9ef63641 ("bnxt_en: Fix race when modifying pause settings.")
Reviewed-by: Edwin Peer <edwin.peer@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 31 ++++++++++++-------
 1 file changed, 20 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index bc2c76fa54ca..f6e236a7bf18 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -1735,9 +1735,12 @@ static int bnxt_set_pauseparam(struct net_device *dev,
 	if (!BNXT_PHY_CFG_ABLE(bp))
 		return -EOPNOTSUPP;
 
+	mutex_lock(&bp->link_lock);
 	if (epause->autoneg) {
-		if (!(link_info->autoneg & BNXT_AUTONEG_SPEED))
-			return -EINVAL;
+		if (!(link_info->autoneg & BNXT_AUTONEG_SPEED)) {
+			rc = -EINVAL;
+			goto pause_exit;
+		}
 
 		link_info->autoneg |= BNXT_AUTONEG_FLOW_CTRL;
 		if (bp->hwrm_spec_code >= 0x10201)
@@ -1758,11 +1761,11 @@ static int bnxt_set_pauseparam(struct net_device *dev,
 	if (epause->tx_pause)
 		link_info->req_flow_ctrl |= BNXT_LINK_PAUSE_TX;
 
-	if (netif_running(dev)) {
-		mutex_lock(&bp->link_lock);
+	if (netif_running(dev))
 		rc = bnxt_hwrm_set_pause(bp);
-		mutex_unlock(&bp->link_lock);
-	}
+
+pause_exit:
+	mutex_unlock(&bp->link_lock);
 	return rc;
 }
 
@@ -2499,8 +2502,7 @@ static int bnxt_set_eee(struct net_device *dev, struct ethtool_eee *edata)
 	struct bnxt *bp = netdev_priv(dev);
 	struct ethtool_eee *eee = &bp->eee;
 	struct bnxt_link_info *link_info = &bp->link_info;
-	u32 advertising =
-		 _bnxt_fw_to_ethtool_adv_spds(link_info->advertising, 0);
+	u32 advertising;
 	int rc = 0;
 
 	if (!BNXT_PHY_CFG_ABLE(bp))
@@ -2509,19 +2511,23 @@ static int bnxt_set_eee(struct net_device *dev, struct ethtool_eee *edata)
 	if (!(bp->flags & BNXT_FLAG_EEE_CAP))
 		return -EOPNOTSUPP;
 
+	mutex_lock(&bp->link_lock);
+	advertising = _bnxt_fw_to_ethtool_adv_spds(link_info->advertising, 0);
 	if (!edata->eee_enabled)
 		goto eee_ok;
 
 	if (!(link_info->autoneg & BNXT_AUTONEG_SPEED)) {
 		netdev_warn(dev, "EEE requires autoneg\n");
-		return -EINVAL;
+		rc = -EINVAL;
+		goto eee_exit;
 	}
 	if (edata->tx_lpi_enabled) {
 		if (bp->lpi_tmr_hi && (edata->tx_lpi_timer > bp->lpi_tmr_hi ||
 				       edata->tx_lpi_timer < bp->lpi_tmr_lo)) {
 			netdev_warn(dev, "Valid LPI timer range is %d and %d microsecs\n",
 				    bp->lpi_tmr_lo, bp->lpi_tmr_hi);
-			return -EINVAL;
+			rc = -EINVAL;
+			goto eee_exit;
 		} else if (!bp->lpi_tmr_hi) {
 			edata->tx_lpi_timer = eee->tx_lpi_timer;
 		}
@@ -2531,7 +2537,8 @@ static int bnxt_set_eee(struct net_device *dev, struct ethtool_eee *edata)
 	} else if (edata->advertised & ~advertising) {
 		netdev_warn(dev, "EEE advertised %x must be a subset of autoneg advertised speeds %x\n",
 			    edata->advertised, advertising);
-		return -EINVAL;
+		rc = -EINVAL;
+		goto eee_exit;
 	}
 
 	eee->advertised = edata->advertised;
@@ -2543,6 +2550,8 @@ static int bnxt_set_eee(struct net_device *dev, struct ethtool_eee *edata)
 	if (netif_running(dev))
 		rc = bnxt_hwrm_set_link_setting(bp, false, true);
 
+eee_exit:
+	mutex_unlock(&bp->link_lock);
 	return rc;
 }
 
-- 
2.26.2


From deb393e11f0e58d8109902c3dddf2057754f6c63 Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens <hauke@hauke-m.de>
Date: Sat, 12 Sep 2020 21:36:26 +0200
Subject: [PATCH 33/54] net: lantiq: Wake TX queue again

[ Upstream commit dea36631e6f186d4b853af67a4aef2e35cfa8bb7 ]

The call to netif_wake_queue() when the TX descriptors were freed was
missing. When there are no TX buffers available the TX queue will be
stopped, but it was not started again when they are available again,
this is fixed in this patch.

Fixes: fe1a56420cf2 ("net: lantiq: Add Lantiq / Intel VRX200 Ethernet driver")
Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/lantiq_xrx200.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c
index 1645e4e7ebdb..1feb9fc710e0 100644
--- a/drivers/net/ethernet/lantiq_xrx200.c
+++ b/drivers/net/ethernet/lantiq_xrx200.c
@@ -268,6 +268,9 @@ static int xrx200_tx_housekeeping(struct napi_struct *napi, int budget)
 	net_dev->stats.tx_bytes += bytes;
 	netdev_completed_queue(ch->priv->net_dev, pkts, bytes);
 
+	if (netif_queue_stopped(net_dev))
+		netif_wake_queue(net_dev);
+
 	if (pkts < budget) {
 		napi_complete(&ch->napi);
 		ltq_dma_enable_irq(&ch->dma);
-- 
2.26.2


From e9c41c1642bf7046c6cded62c9b762965e968380 Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens <hauke@hauke-m.de>
Date: Sat, 12 Sep 2020 21:36:27 +0200
Subject: [PATCH 34/54] net: lantiq: use netif_tx_napi_add() for TX NAPI

[ Upstream commit 74c7b80e222b58d3cea731d31e2a31a77fea8345 ]

netif_tx_napi_add() should be used for NAPI in the TX direction instead
of the netif_napi_add() function.

Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/lantiq_xrx200.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c
index 1feb9fc710e0..f34e4dc8c661 100644
--- a/drivers/net/ethernet/lantiq_xrx200.c
+++ b/drivers/net/ethernet/lantiq_xrx200.c
@@ -502,7 +502,7 @@ static int xrx200_probe(struct platform_device *pdev)
 
 	/* setup NAPI */
 	netif_napi_add(net_dev, &priv->chan_rx.napi, xrx200_poll_rx, 32);
-	netif_napi_add(net_dev, &priv->chan_tx.napi, xrx200_tx_housekeeping, 32);
+	netif_tx_napi_add(net_dev, &priv->chan_tx.napi, xrx200_tx_housekeeping, 32);
 
 	platform_set_drvdata(pdev, priv);
 
-- 
2.26.2


From 6a177ed00a078c02d4848db94d501ff8e19f8d57 Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens <hauke@hauke-m.de>
Date: Sat, 12 Sep 2020 21:36:28 +0200
Subject: [PATCH 35/54] net: lantiq: Use napi_complete_done()

[ Upstream commit c582a7fea9dad4d309437d1a7e22e6d2cb380e2e ]

Use napi_complete_done() and activate the interrupts when this function
returns true. This way the generic NAPI code can take care of activating
the interrupts.

Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/lantiq_xrx200.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c
index f34e4dc8c661..abee7d61074c 100644
--- a/drivers/net/ethernet/lantiq_xrx200.c
+++ b/drivers/net/ethernet/lantiq_xrx200.c
@@ -230,8 +230,8 @@ static int xrx200_poll_rx(struct napi_struct *napi, int budget)
 	}
 
 	if (rx < budget) {
-		napi_complete(&ch->napi);
-		ltq_dma_enable_irq(&ch->dma);
+		if (napi_complete_done(&ch->napi, rx))
+			ltq_dma_enable_irq(&ch->dma);
 	}
 
 	return rx;
@@ -272,8 +272,8 @@ static int xrx200_tx_housekeeping(struct napi_struct *napi, int budget)
 		netif_wake_queue(net_dev);
 
 	if (pkts < budget) {
-		napi_complete(&ch->napi);
-		ltq_dma_enable_irq(&ch->dma);
+		if (napi_complete_done(&ch->napi, pkts))
+			ltq_dma_enable_irq(&ch->dma);
 	}
 
 	return pkts;
-- 
2.26.2


From 886ce820ac303471e96f1490e305b843db0f79a7 Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens <hauke@hauke-m.de>
Date: Sat, 12 Sep 2020 21:36:29 +0200
Subject: [PATCH 36/54] net: lantiq: Disable IRQs only if NAPI gets scheduled

[ Upstream commit 9423361da52356cb68642db5b2729b6b85aad330 ]

The napi_schedule() call will only schedule the NAPI if it is not
already running. To make sure that we do not deactivate interrupts
without scheduling NAPI only deactivate the interrupts in case NAPI also
gets scheduled.

Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/lantiq_xrx200.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c
index abee7d61074c..635ff3a5dcfb 100644
--- a/drivers/net/ethernet/lantiq_xrx200.c
+++ b/drivers/net/ethernet/lantiq_xrx200.c
@@ -345,10 +345,12 @@ static irqreturn_t xrx200_dma_irq(int irq, void *ptr)
 {
 	struct xrx200_chan *ch = ptr;
 
-	ltq_dma_disable_irq(&ch->dma);
-	ltq_dma_ack_irq(&ch->dma);
+	if (napi_schedule_prep(&ch->napi)) {
+		__napi_schedule(&ch->napi);
+		ltq_dma_disable_irq(&ch->dma);
+	}
 
-	napi_schedule(&ch->napi);
+	ltq_dma_ack_irq(&ch->dma);
 
 	return IRQ_HANDLED;
 }
-- 
2.26.2


From 94a3ebdc778265f2f2141cfa217c719ce59f49a1 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 16 Sep 2020 20:43:09 -0700
Subject: [PATCH 37/54] net: phy: Avoid NPD upon phy_detach() when driver is
 unbound

[ Upstream commit c2b727df7caa33876e7066bde090f40001b6d643 ]

If we have unbound the PHY driver prior to calling phy_detach() (often
via phy_disconnect()) then we can cause a NULL pointer de-reference
accessing the driver owner member. The steps to reproduce are:

echo unimac-mdio-0:01 > /sys/class/net/eth0/phydev/driver/unbind
ip link set eth0 down

Fixes: cafe8df8b9bc ("net: phy: Fix lack of reference count on PHY driver")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index aa23fd0ccc53..067910d242ab 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1631,7 +1631,8 @@ void phy_detach(struct phy_device *phydev)
 
 	phy_led_triggers_unregister(phydev);
 
-	module_put(phydev->mdio.dev.driver->owner);
+	if (phydev->mdio.dev.driver)
+		module_put(phydev->mdio.dev.driver->owner);
 
 	/* If the device had no specific driver before (i.e. - it
 	 * was using the generic driver), we unbind the device
-- 
2.26.2


From c594531e61f16936e6b2f1eee71f55da4d34c749 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Wed, 16 Sep 2020 20:43:10 -0700
Subject: [PATCH 38/54] net: phy: Do not warn in phy_stop() on PHY_DOWN

[ Upstream commit 5116a8ade333b6c2e180782139c9c516a437b21c ]

When phy_is_started() was added to catch incorrect PHY states,
phy_stop() would not be qualified against PHY_DOWN. It is possible to
reach that state when the PHY driver has been unbound and the network
device is then brought down.

Fixes: 2b3e88ea6528 ("net: phy: improve phy state checking")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 56cfae950472..f5620f91dbf3 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -948,7 +948,7 @@ void phy_stop(struct phy_device *phydev)
 {
 	struct net_device *dev = phydev->attached_dev;
 
-	if (!phy_is_started(phydev)) {
+	if (!phy_is_started(phydev) && phydev->state != PHY_DOWN) {
 		WARN(1, "called from state %s\n",
 		     phy_state_to_str(phydev->state));
 		return;
-- 
2.26.2


From a2398e6961f470591cca8664f603e56f07d0bba2 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 9 Sep 2020 01:27:39 -0700
Subject: [PATCH 39/54] net: qrtr: check skb_put_padto() return value

[ Upstream commit 3ca1a42a52ca4b4f02061683851692ad65fefac8 ]

If skb_put_padto() returns an error, skb has been freed.
Better not touch it anymore, as reported by syzbot [1]

Note to qrtr maintainers : this suggests qrtr_sendmsg()
should adjust sock_alloc_send_skb() second parameter
to account for the potential added alignment to avoid
reallocation.

[1]

BUG: KASAN: use-after-free in __skb_insert include/linux/skbuff.h:1907 [inline]
BUG: KASAN: use-after-free in __skb_queue_before include/linux/skbuff.h:2016 [inline]
BUG: KASAN: use-after-free in __skb_queue_tail include/linux/skbuff.h:2049 [inline]
BUG: KASAN: use-after-free in skb_queue_tail+0x6b/0x120 net/core/skbuff.c:3146
Write of size 8 at addr ffff88804d8ab3c0 by task syz-executor.4/4316

CPU: 1 PID: 4316 Comm: syz-executor.4 Not tainted 5.9.0-rc4-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1d6/0x29e lib/dump_stack.c:118
 print_address_description+0x66/0x620 mm/kasan/report.c:383
 __kasan_report mm/kasan/report.c:513 [inline]
 kasan_report+0x132/0x1d0 mm/kasan/report.c:530
 __skb_insert include/linux/skbuff.h:1907 [inline]
 __skb_queue_before include/linux/skbuff.h:2016 [inline]
 __skb_queue_tail include/linux/skbuff.h:2049 [inline]
 skb_queue_tail+0x6b/0x120 net/core/skbuff.c:3146
 qrtr_tun_send+0x1a/0x40 net/qrtr/tun.c:23
 qrtr_node_enqueue+0x44f/0xc00 net/qrtr/qrtr.c:364
 qrtr_bcast_enqueue+0xbe/0x140 net/qrtr/qrtr.c:861
 qrtr_sendmsg+0x680/0x9c0 net/qrtr/qrtr.c:960
 sock_sendmsg_nosec net/socket.c:651 [inline]
 sock_sendmsg net/socket.c:671 [inline]
 sock_write_iter+0x317/0x470 net/socket.c:998
 call_write_iter include/linux/fs.h:1882 [inline]
 new_sync_write fs/read_write.c:503 [inline]
 vfs_write+0xa96/0xd10 fs/read_write.c:578
 ksys_write+0x11b/0x220 fs/read_write.c:631
 do_syscall_64+0x31/0x70 arch/x86/entry/common.c:46
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x45d5b9
Code: 5d b4 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 2b b4 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f84b5b81c78 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 0000000000038b40 RCX: 000000000045d5b9
RDX: 0000000000000055 RSI: 0000000020001240 RDI: 0000000000000003
RBP: 00007f84b5b81ca0 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 000000000000000f
R13: 00007ffcbbf86daf R14: 00007f84b5b829c0 R15: 000000000118cf4c

Allocated by task 4316:
 kasan_save_stack mm/kasan/common.c:48 [inline]
 kasan_set_track mm/kasan/common.c:56 [inline]
 __kasan_kmalloc+0x100/0x130 mm/kasan/common.c:461
 slab_post_alloc_hook+0x3e/0x290 mm/slab.h:518
 slab_alloc mm/slab.c:3312 [inline]
 kmem_cache_alloc+0x1c1/0x2d0 mm/slab.c:3482
 skb_clone+0x1b2/0x370 net/core/skbuff.c:1449
 qrtr_bcast_enqueue+0x6d/0x140 net/qrtr/qrtr.c:857
 qrtr_sendmsg+0x680/0x9c0 net/qrtr/qrtr.c:960
 sock_sendmsg_nosec net/socket.c:651 [inline]
 sock_sendmsg net/socket.c:671 [inline]
 sock_write_iter+0x317/0x470 net/socket.c:998
 call_write_iter include/linux/fs.h:1882 [inline]
 new_sync_write fs/read_write.c:503 [inline]
 vfs_write+0xa96/0xd10 fs/read_write.c:578
 ksys_write+0x11b/0x220 fs/read_write.c:631
 do_syscall_64+0x31/0x70 arch/x86/entry/common.c:46
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Freed by task 4316:
 kasan_save_stack mm/kasan/common.c:48 [inline]
 kasan_set_track+0x3d/0x70 mm/kasan/common.c:56
 kasan_set_free_info+0x17/0x30 mm/kasan/generic.c:355
 __kasan_slab_free+0xdd/0x110 mm/kasan/common.c:422
 __cache_free mm/slab.c:3418 [inline]
 kmem_cache_free+0x82/0xf0 mm/slab.c:3693
 __skb_pad+0x3f5/0x5a0 net/core/skbuff.c:1823
 __skb_put_padto include/linux/skbuff.h:3233 [inline]
 skb_put_padto include/linux/skbuff.h:3252 [inline]
 qrtr_node_enqueue+0x62f/0xc00 net/qrtr/qrtr.c:360
 qrtr_bcast_enqueue+0xbe/0x140 net/qrtr/qrtr.c:861
 qrtr_sendmsg+0x680/0x9c0 net/qrtr/qrtr.c:960
 sock_sendmsg_nosec net/socket.c:651 [inline]
 sock_sendmsg net/socket.c:671 [inline]
 sock_write_iter+0x317/0x470 net/socket.c:998
 call_write_iter include/linux/fs.h:1882 [inline]
 new_sync_write fs/read_write.c:503 [inline]
 vfs_write+0xa96/0xd10 fs/read_write.c:578
 ksys_write+0x11b/0x220 fs/read_write.c:631
 do_syscall_64+0x31/0x70 arch/x86/entry/common.c:46
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

The buggy address belongs to the object at ffff88804d8ab3c0
 which belongs to the cache skbuff_head_cache of size 224
The buggy address is located 0 bytes inside of
 224-byte region [ffff88804d8ab3c0, ffff88804d8ab4a0)
The buggy address belongs to the page:
page:00000000ea8cccfb refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff88804d8abb40 pfn:0x4d8ab
flags: 0xfffe0000000200(slab)
raw: 00fffe0000000200 ffffea0002237ec8 ffffea00029b3388 ffff88821bb66800
raw: ffff88804d8abb40 ffff88804d8ab000 000000010000000b 0000000000000000
page dumped because: kasan: bad access detected

Fixes: ce57785bf91b ("net: qrtr: fix len of skb_put_padto in qrtr_node_enqueue")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Carl Huang <cjhuang@codeaurora.org>
Cc: Wen Gong <wgong@codeaurora.org>
Cc: Bjorn Andersson <bjorn.andersson@linaro.org>
Cc: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Acked-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/qrtr/qrtr.c | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index 85ab4559f057..0f77e24a5152 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -332,8 +332,7 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb,
 {
 	struct qrtr_hdr_v1 *hdr;
 	size_t len = skb->len;
-	int rc = -ENODEV;
-	int confirm_rx;
+	int rc, confirm_rx;
 
 	confirm_rx = qrtr_tx_wait(node, to->sq_node, to->sq_port, type);
 	if (confirm_rx < 0) {
@@ -357,15 +356,17 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb,
 	hdr->size = cpu_to_le32(len);
 	hdr->confirm_rx = !!confirm_rx;
 
-	skb_put_padto(skb, ALIGN(len, 4) + sizeof(*hdr));
-
-	mutex_lock(&node->ep_lock);
-	if (node->ep)
-		rc = node->ep->xmit(node->ep, skb);
-	else
-		kfree_skb(skb);
-	mutex_unlock(&node->ep_lock);
+	rc = skb_put_padto(skb, ALIGN(len, 4) + sizeof(*hdr));
 
+	if (!rc) {
+		mutex_lock(&node->ep_lock);
+		rc = -ENODEV;
+		if (node->ep)
+			rc = node->ep->xmit(node->ep, skb);
+		else
+			kfree_skb(skb);
+		mutex_unlock(&node->ep_lock);
+	}
 	/* Need to ensure that a subsequent message carries the otherwise lost
 	 * confirm_rx flag if we dropped this one */
 	if (rc && confirm_rx)
-- 
2.26.2


From 317498e7670c49079936985112b2addbfd87f9f5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 9 Sep 2020 01:27:40 -0700
Subject: [PATCH 40/54] net: add __must_check to skb_put_padto()

[ Upstream commit 4a009cb04aeca0de60b73f37b102573354214b52 ]

skb_put_padto() and __skb_put_padto() callers
must check return values or risk use-after-free.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 0c0377fc00c2..1119463cf242 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3208,8 +3208,9 @@ static inline int skb_padto(struct sk_buff *skb, unsigned int len)
  *	is untouched. Otherwise it is extended. Returns zero on
  *	success. The skb is freed on error if @free_on_error is true.
  */
-static inline int __skb_put_padto(struct sk_buff *skb, unsigned int len,
-				  bool free_on_error)
+static inline int __must_check __skb_put_padto(struct sk_buff *skb,
+					       unsigned int len,
+					       bool free_on_error)
 {
 	unsigned int size = skb->len;
 
@@ -3232,7 +3233,7 @@ static inline int __skb_put_padto(struct sk_buff *skb, unsigned int len,
  *	is untouched. Otherwise it is extended. Returns zero on
  *	success. The skb is freed on error.
  */
-static inline int skb_put_padto(struct sk_buff *skb, unsigned int len)
+static inline int __must_check skb_put_padto(struct sk_buff *skb, unsigned int len)
 {
 	return __skb_put_padto(skb, len, true);
 }
-- 
2.26.2


From e49a9b032153fd48f207313b19e8004dd29d5c79 Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Thu, 10 Sep 2020 23:52:29 +0300
Subject: [PATCH 41/54] net: ethernet: ti: cpsw_new: fix suspend/resume

[ Upstream commit 5760d9acbe9514eec68eb70821d6fa5764f57042 ]

Add missed suspend/resume callbacks to properly restore networking after
suspend/resume cycle.

Fixes: ed3525eda4c4 ("net: ethernet: ti: introduce cpsw switchdev based driver part 1 - dual-emac")
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw_new.c | 53 ++++++++++++++++++++++++++++++
 1 file changed, 53 insertions(+)

diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c
index 8ed78577cded..15672d0a4de6 100644
--- a/drivers/net/ethernet/ti/cpsw_new.c
+++ b/drivers/net/ethernet/ti/cpsw_new.c
@@ -17,6 +17,7 @@
 #include <linux/phy.h>
 #include <linux/phy/phy.h>
 #include <linux/delay.h>
+#include <linux/pinctrl/consumer.h>
 #include <linux/pm_runtime.h>
 #include <linux/gpio/consumer.h>
 #include <linux/of.h>
@@ -2070,9 +2071,61 @@ static int cpsw_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static int __maybe_unused cpsw_suspend(struct device *dev)
+{
+	struct cpsw_common *cpsw = dev_get_drvdata(dev);
+	int i;
+
+	rtnl_lock();
+
+	for (i = 0; i < cpsw->data.slaves; i++) {
+		struct net_device *ndev = cpsw->slaves[i].ndev;
+
+		if (!(ndev && netif_running(ndev)))
+			continue;
+
+		cpsw_ndo_stop(ndev);
+	}
+
+	rtnl_unlock();
+
+	/* Select sleep pin state */
+	pinctrl_pm_select_sleep_state(dev);
+
+	return 0;
+}
+
+static int __maybe_unused cpsw_resume(struct device *dev)
+{
+	struct cpsw_common *cpsw = dev_get_drvdata(dev);
+	int i;
+
+	/* Select default pin state */
+	pinctrl_pm_select_default_state(dev);
+
+	/* shut up ASSERT_RTNL() warning in netif_set_real_num_tx/rx_queues */
+	rtnl_lock();
+
+	for (i = 0; i < cpsw->data.slaves; i++) {
+		struct net_device *ndev = cpsw->slaves[i].ndev;
+
+		if (!(ndev && netif_running(ndev)))
+			continue;
+
+		cpsw_ndo_open(ndev);
+	}
+
+	rtnl_unlock();
+
+	return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(cpsw_pm_ops, cpsw_suspend, cpsw_resume);
+
 static struct platform_driver cpsw_driver = {
 	.driver = {
 		.name	 = "cpsw-switch",
+		.pm	 = &cpsw_pm_ops,
 		.of_match_table = cpsw_of_mtable,
 	},
 	.probe = cpsw_probe,
-- 
2.26.2


From f3f6ab80ba90755bc9d41dca784a097814455781 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Wed, 9 Sep 2020 13:58:14 +0200
Subject: [PATCH 42/54] wireguard: noise: take lock when removing handshake
 entry from table

[ Upstream commit 9179ba31367bcf481c3c79b5f028c94faad9f30a ]

Eric reported that syzkaller found a race of this variety:

CPU 1                                       CPU 2
-------------------------------------------|---------------------------------------
wg_index_hashtable_replace(old, ...)       |
  if (hlist_unhashed(&old->index_hash))    |
                                           | wg_index_hashtable_remove(old)
                                           |   hlist_del_init_rcu(&old->index_hash)
				           |     old->index_hash.pprev = NULL
  hlist_replace_rcu(&old->index_hash, ...) |
    *old->index_hash.pprev                 |

Syzbot wasn't actually able to reproduce this more than once or create a
reproducer, because the race window between checking "hlist_unhashed" and
calling "hlist_replace_rcu" is just so small. Adding an mdelay(5) or
similar there helps make this demonstrable using this simple script:

    #!/bin/bash
    set -ex
    trap 'kill $pid1; kill $pid2; ip link del wg0; ip link del wg1' EXIT
    ip link add wg0 type wireguard
    ip link add wg1 type wireguard
    wg set wg0 private-key <(wg genkey) listen-port 9999
    wg set wg1 private-key <(wg genkey) peer $(wg show wg0 public-key) endpoint 127.0.0.1:9999 persistent-keepalive 1
    wg set wg0 peer $(wg show wg1 public-key)
    ip link set wg0 up
    yes link set wg1 up | ip -force -batch - &
    pid1=$!
    yes link set wg1 down | ip -force -batch - &
    pid2=$!
    wait

The fundumental underlying problem is that we permit calls to wg_index_
hashtable_remove(handshake.entry) without requiring the caller to take
the handshake mutex that is intended to protect members of handshake
during mutations. This is consistently the case with calls to wg_index_
hashtable_insert(handshake.entry) and wg_index_hashtable_replace(
handshake.entry), but it's missing from a pertinent callsite of wg_
index_hashtable_remove(handshake.entry). So, this patch makes sure that
mutex is taken.

The original code was a little bit funky though, in the form of:

    remove(handshake.entry)
    lock(), memzero(handshake.some_members), unlock()
    remove(handshake.entry)

The original intention of that double removal pattern outside the lock
appears to be some attempt to prevent insertions that might happen while
locks are dropped during expensive crypto operations, but actually, all
callers of wg_index_hashtable_insert(handshake.entry) take the write
lock and then explicitly check handshake.state, as they should, which
the aforementioned memzero clears, which means an insertion should
already be impossible. And regardless, the original intention was
necessarily racy, since it wasn't guaranteed that something else would
run after the unlock() instead of after the remove(). So, from a
soundness perspective, it seems positive to remove what looks like a
hack at best.

The crash from both syzbot and from the script above is as follows:

  general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] PREEMPT SMP KASAN
  KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007]
  CPU: 0 PID: 7395 Comm: kworker/0:3 Not tainted 5.9.0-rc4-syzkaller #0
  Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
  Workqueue: wg-kex-wg1 wg_packet_handshake_receive_worker
  RIP: 0010:hlist_replace_rcu include/linux/rculist.h:505 [inline]
  RIP: 0010:wg_index_hashtable_replace+0x176/0x330 drivers/net/wireguard/peerlookup.c:174
  Code: 00 fc ff df 48 89 f9 48 c1 e9 03 80 3c 01 00 0f 85 44 01 00 00 48 b9 00 00 00 00 00 fc ff df 48 8b 45 10 48 89 c6 48 c1 ee 03 <80> 3c 0e 00 0f 85 06 01 00 00 48 85 d2 4c 89 28 74 47 e8 a3 4f b5
  RSP: 0018:ffffc90006a97bf8 EFLAGS: 00010246
  RAX: 0000000000000000 RBX: ffff888050ffc4f8 RCX: dffffc0000000000
  RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff88808e04e010
  RBP: ffff88808e04e000 R08: 0000000000000001 R09: ffff8880543d0000
  R10: ffffed100a87a000 R11: 000000000000016e R12: ffff8880543d0000
  R13: ffff88808e04e008 R14: ffff888050ffc508 R15: ffff888050ffc500
  FS:  0000000000000000(0000) GS:ffff8880ae600000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 00000000f5505db0 CR3: 0000000097cf7000 CR4: 00000000001526f0
  DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
  DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
  Call Trace:
  wg_noise_handshake_begin_session+0x752/0xc9a drivers/net/wireguard/noise.c:820
  wg_receive_handshake_packet drivers/net/wireguard/receive.c:183 [inline]
  wg_packet_handshake_receive_worker+0x33b/0x730 drivers/net/wireguard/receive.c:220
  process_one_work+0x94c/0x1670 kernel/workqueue.c:2269
  worker_thread+0x64c/0x1120 kernel/workqueue.c:2415
  kthread+0x3b5/0x4a0 kernel/kthread.c:292
  ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:294

Reported-by: syzbot <syzkaller@googlegroups.com>
Reported-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/wireguard/20200908145911.4090480-1-edumazet@google.com/
Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wireguard/noise.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/wireguard/noise.c b/drivers/net/wireguard/noise.c
index 201a22681945..27cb5045bed2 100644
--- a/drivers/net/wireguard/noise.c
+++ b/drivers/net/wireguard/noise.c
@@ -87,15 +87,12 @@ static void handshake_zero(struct noise_handshake *handshake)
 
 void wg_noise_handshake_clear(struct noise_handshake *handshake)
 {
+	down_write(&handshake->lock);
 	wg_index_hashtable_remove(
 			handshake->entry.peer->device->index_hashtable,
 			&handshake->entry);
-	down_write(&handshake->lock);
 	handshake_zero(handshake);
 	up_write(&handshake->lock);
-	wg_index_hashtable_remove(
-			handshake->entry.peer->device->index_hashtable,
-			&handshake->entry);
 }
 
 static struct noise_keypair *keypair_create(struct wg_peer *peer)
-- 
2.26.2


From 09c43fef5649a24643f10e53a9a8c3b3d26bbb43 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Wed, 9 Sep 2020 13:58:15 +0200
Subject: [PATCH 43/54] wireguard: peerlookup: take lock before checking hash
 in replace operation

[ Upstream commit 6147f7b1e90ff09bd52afc8b9206a7fcd133daf7 ]

Eric's suggested fix for the previous commit's mentioned race condition
was to simply take the table->lock in wg_index_hashtable_replace(). The
table->lock of the hash table is supposed to protect the bucket heads,
not the entires, but actually, since all the mutator functions are
already taking it, it makes sense to take it too for the test to
hlist_unhashed, as a defense in depth measure, so that it no longer
races with deletions, regardless of what other locks are protecting
individual entries. This is sensible from a performance perspective
because, as Eric pointed out, the case of being unhashed is already the
unlikely case, so this won't add common contention. And comparing
instructions, this basically doesn't make much of a difference other
than pushing and popping %r13, used by the new `bool ret`. More
generally, I like the idea of locking consistency across table mutator
functions, and this might let me rest slightly easier at night.

Suggested-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/wireguard/20200908145911.4090480-1-edumazet@google.com/
Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wireguard/peerlookup.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireguard/peerlookup.c b/drivers/net/wireguard/peerlookup.c
index e4deb331476b..f2783aa7a88f 100644
--- a/drivers/net/wireguard/peerlookup.c
+++ b/drivers/net/wireguard/peerlookup.c
@@ -167,9 +167,13 @@ bool wg_index_hashtable_replace(struct index_hashtable *table,
 				struct index_hashtable_entry *old,
 				struct index_hashtable_entry *new)
 {
-	if (unlikely(hlist_unhashed(&old->index_hash)))
-		return false;
+	bool ret;
+
 	spin_lock_bh(&table->lock);
+	ret = !hlist_unhashed(&old->index_hash);
+	if (unlikely(!ret))
+		goto out;
+
 	new->index = old->index;
 	hlist_replace_rcu(&old->index_hash, &new->index_hash);
 
@@ -180,8 +184,9 @@ bool wg_index_hashtable_replace(struct index_hashtable *table,
 	 * simply gets dropped, which isn't terrible.
 	 */
 	INIT_HLIST_NODE(&old->index_hash);
+out:
 	spin_unlock_bh(&table->lock);
-	return true;
+	return ret;
 }
 
 void wg_index_hashtable_remove(struct index_hashtable *table,
-- 
2.26.2


From 9f99735a753446b404104fb4f61b637d909f8c2d Mon Sep 17 00:00:00 2001
From: Vadym Kochan <vadym.kochan@plvision.eu>
Date: Thu, 10 Sep 2020 18:41:52 +0300
Subject: [PATCH 44/54] net: ipa: fix u32_replace_bits by u32p_xxx version

[ Upstream commit c047dc1d260f2593035d63747d616c3512f9d6b6 ]

Looks like u32p_replace_bits() should be used instead of
u32_replace_bits() which does not modifies the value but returns the
modified version.

Fixes: 2b9feef2b6c2 ("soc: qcom: ipa: filter and routing tables")
Signed-off-by: Vadym Kochan <vadym.kochan@plvision.eu>
Reviewed-by: Alex Elder <elder@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ipa/ipa_table.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ipa/ipa_table.c b/drivers/net/ipa/ipa_table.c
index 9df2a3e78c98..d08c626b2baa 100644
--- a/drivers/net/ipa/ipa_table.c
+++ b/drivers/net/ipa/ipa_table.c
@@ -521,7 +521,7 @@ static void ipa_filter_tuple_zero(struct ipa_endpoint *endpoint)
 	val = ioread32(endpoint->ipa->reg_virt + offset);
 
 	/* Zero all filter-related fields, preserving the rest */
-	u32_replace_bits(val, 0, IPA_REG_ENDP_FILTER_HASH_MSK_ALL);
+	u32p_replace_bits(&val, 0, IPA_REG_ENDP_FILTER_HASH_MSK_ALL);
 
 	iowrite32(val, endpoint->ipa->reg_virt + offset);
 }
@@ -572,7 +572,7 @@ static void ipa_route_tuple_zero(struct ipa *ipa, u32 route_id)
 	val = ioread32(ipa->reg_virt + offset);
 
 	/* Zero all route-related fields, preserving the rest */
-	u32_replace_bits(val, 0, IPA_REG_ENDP_ROUTER_HASH_MSK_ALL);
+	u32p_replace_bits(&val, 0, IPA_REG_ENDP_ROUTER_HASH_MSK_ALL);
 
 	iowrite32(val, ipa->reg_virt + offset);
 }
-- 
2.26.2


From bae4d70ba01ea41753c419beb4bed22bc8d521eb Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@mellanox.com>
Date: Tue, 7 Jul 2020 06:16:24 +0000
Subject: [PATCH 45/54] net/mlx5e: Fix memory leak of tunnel info when rule
 under multipath not ready

[ Upstream commit 12a240a41427d37b5e70570700704e84c827452f ]

When deleting vxlan flow rule under multipath, tun_info in parse_attr is
not freed when the rule is not ready.

Fixes: ef06c9ee8933 ("net/mlx5e: Allow one failure when offloading tc encap rules under multipath")
Signed-off-by: Jianbo Liu <jianbol@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index fcedb5bdca9e..f1701ee4619b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1399,11 +1399,8 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 
 	mlx5e_put_flow_tunnel_id(flow);
 
-	if (flow_flag_test(flow, NOT_READY)) {
+	if (flow_flag_test(flow, NOT_READY))
 		remove_unready_flow(flow);
-		kvfree(attr->parse_attr);
-		return;
-	}
 
 	if (mlx5e_is_offloaded_flow(flow)) {
 		if (flow_flag_test(flow, SLOW))
-- 
2.26.2


From 131f0dd798a5c5c983127276e02bc741ba66edb9 Mon Sep 17 00:00:00 2001
From: Luo bin <luobin9@huawei.com>
Date: Thu, 10 Sep 2020 22:04:40 +0800
Subject: [PATCH 46/54] hinic: fix rewaking txq after netif_tx_disable

[ Upstream commit a1b80e0143a1b878f8e21d82fd55f3f46f0014be ]

When calling hinic_close in hinic_set_channels, all queues are
stopped after netif_tx_disable, but some queue may be rewaken in
free_tx_poll by mistake while drv is handling tx irq. If one queue
is rewaken core may call hinic_xmit_frame to send pkt after
netif_tx_disable within a short time which may results in accessing
memory that has been already freed in hinic_close. So we call
napi_disable before netif_tx_disable in hinic_close to fix this bug.

Fixes: 2eed5a8b614b ("hinic: add set_channels ethtool_ops support")
Signed-off-by: Luo bin <luobin9@huawei.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/huawei/hinic/hinic_main.c    | 24 +++++++++++++++++++
 drivers/net/ethernet/huawei/hinic/hinic_tx.c  | 18 +++-----------
 2 files changed, 27 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c
index e9e6f4c9309a..c9d884049fd0 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_main.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c
@@ -168,6 +168,24 @@ static int create_txqs(struct hinic_dev *nic_dev)
 	return err;
 }
 
+static void enable_txqs_napi(struct hinic_dev *nic_dev)
+{
+	int num_txqs = hinic_hwdev_num_qps(nic_dev->hwdev);
+	int i;
+
+	for (i = 0; i < num_txqs; i++)
+		napi_enable(&nic_dev->txqs[i].napi);
+}
+
+static void disable_txqs_napi(struct hinic_dev *nic_dev)
+{
+	int num_txqs = hinic_hwdev_num_qps(nic_dev->hwdev);
+	int i;
+
+	for (i = 0; i < num_txqs; i++)
+		napi_disable(&nic_dev->txqs[i].napi);
+}
+
 /**
  * free_txqs - Free the Logical Tx Queues of specific NIC device
  * @nic_dev: the specific NIC device
@@ -394,6 +412,8 @@ int hinic_open(struct net_device *netdev)
 		goto err_create_txqs;
 	}
 
+	enable_txqs_napi(nic_dev);
+
 	err = create_rxqs(nic_dev);
 	if (err) {
 		netif_err(nic_dev, drv, netdev,
@@ -475,6 +495,7 @@ int hinic_open(struct net_device *netdev)
 	}
 
 err_create_rxqs:
+	disable_txqs_napi(nic_dev);
 	free_txqs(nic_dev);
 
 err_create_txqs:
@@ -488,6 +509,9 @@ int hinic_close(struct net_device *netdev)
 	struct hinic_dev *nic_dev = netdev_priv(netdev);
 	unsigned int flags;
 
+	/* Disable txq napi firstly to aviod rewaking txq in free_tx_poll */
+	disable_txqs_napi(nic_dev);
+
 	down(&nic_dev->mgmt_lock);
 
 	flags = nic_dev->flags;
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
index 4c66a0bc1b28..789aa278851e 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
@@ -684,18 +684,6 @@ static int free_tx_poll(struct napi_struct *napi, int budget)
 	return budget;
 }
 
-static void tx_napi_add(struct hinic_txq *txq, int weight)
-{
-	netif_napi_add(txq->netdev, &txq->napi, free_tx_poll, weight);
-	napi_enable(&txq->napi);
-}
-
-static void tx_napi_del(struct hinic_txq *txq)
-{
-	napi_disable(&txq->napi);
-	netif_napi_del(&txq->napi);
-}
-
 static irqreturn_t tx_irq(int irq, void *data)
 {
 	struct hinic_txq *txq = data;
@@ -724,7 +712,7 @@ static int tx_request_irq(struct hinic_txq *txq)
 	struct hinic_sq *sq = txq->sq;
 	int err;
 
-	tx_napi_add(txq, nic_dev->tx_weight);
+	netif_napi_add(txq->netdev, &txq->napi, free_tx_poll, nic_dev->tx_weight);
 
 	hinic_hwdev_msix_set(nic_dev->hwdev, sq->msix_entry,
 			     TX_IRQ_NO_PENDING, TX_IRQ_NO_COALESC,
@@ -734,7 +722,7 @@ static int tx_request_irq(struct hinic_txq *txq)
 	err = request_irq(sq->irq, tx_irq, 0, txq->irq_name, txq);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to request Tx irq\n");
-		tx_napi_del(txq);
+		netif_napi_del(&txq->napi);
 		return err;
 	}
 
@@ -746,7 +734,7 @@ static void tx_free_irq(struct hinic_txq *txq)
 	struct hinic_sq *sq = txq->sq;
 
 	free_irq(sq->irq, txq);
-	tx_napi_del(txq);
+	netif_napi_del(&txq->napi);
 }
 
 /**
-- 
2.26.2


From 17803b465a8ca125ff578470ed0ce6820f95e01e Mon Sep 17 00:00:00 2001
From: Dexuan Cui <decui@microsoft.com>
Date: Mon, 7 Sep 2020 00:13:39 -0700
Subject: [PATCH 47/54] hv_netvsc: Fix hibernation for mlx5 VF driver

[ Upstream commit 19162fd4063a3211843b997a454b505edb81d5ce ]

mlx5_suspend()/resume() keep the network interface, so during hibernation
netvsc_unregister_vf() and netvsc_register_vf() are not called, and hence
netvsc_resume() should call netvsc_vf_changed() to switch the data path
back to the VF after hibernation. Note: after we close and re-open the
vmbus channel of the netvsc NIC in netvsc_suspend() and netvsc_resume(),
the data path is implicitly switched to the netvsc NIC. Similarly,
netvsc_suspend() should not call netvsc_unregister_vf(), otherwise the VF
can no longer be used after hibernation.

For mlx4, since the VF network interafce is explicitly destroyed and
re-created during hibernation (see mlx4_suspend()/resume()), hv_netvsc
already explicitly switches the data path from and to the VF automatically
via netvsc_register_vf() and netvsc_unregister_vf(), so mlx4 doesn't need
this fix. Note: mlx4 can still work with the fix because in
netvsc_suspend()/resume() ndev_ctx->vf_netdev is NULL for mlx4.

Fixes: 0efeea5fb153 ("hv_netvsc: Add the support of hibernation")
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/hyperv/netvsc_drv.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 47159b31e6b3..8309194b351a 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -2544,8 +2544,8 @@ static int netvsc_remove(struct hv_device *dev)
 static int netvsc_suspend(struct hv_device *dev)
 {
 	struct net_device_context *ndev_ctx;
-	struct net_device *vf_netdev, *net;
 	struct netvsc_device *nvdev;
+	struct net_device *net;
 	int ret;
 
 	net = hv_get_drvdata(dev);
@@ -2561,10 +2561,6 @@ static int netvsc_suspend(struct hv_device *dev)
 		goto out;
 	}
 
-	vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev);
-	if (vf_netdev)
-		netvsc_unregister_vf(vf_netdev);
-
 	/* Save the current config info */
 	ndev_ctx->saved_netvsc_dev_info = netvsc_devinfo_get(nvdev);
 
@@ -2580,6 +2576,7 @@ static int netvsc_resume(struct hv_device *dev)
 	struct net_device *net = hv_get_drvdata(dev);
 	struct net_device_context *net_device_ctx;
 	struct netvsc_device_info *device_info;
+	struct net_device *vf_netdev;
 	int ret;
 
 	rtnl_lock();
@@ -2592,6 +2589,15 @@ static int netvsc_resume(struct hv_device *dev)
 	netvsc_devinfo_put(device_info);
 	net_device_ctx->saved_netvsc_dev_info = NULL;
 
+	/* A NIC driver (e.g. mlx5) may keep the VF network interface across
+	 * hibernation, but here the data path is implicitly switched to the
+	 * netvsc NIC since the vmbus channel is closed and re-opened, so
+	 * netvsc_vf_changed() must be used to switch the data path to the VF.
+	 */
+	vf_netdev = rtnl_dereference(net_device_ctx->vf_netdev);
+	if (vf_netdev && netvsc_vf_changed(vf_netdev) != NOTIFY_OK)
+		ret = -EINVAL;
+
 	rtnl_unlock();
 
 	return ret;
-- 
2.26.2


From c3ab0da882971a11f12d358739480132be7411a6 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Tue, 8 Sep 2020 02:48:42 +0300
Subject: [PATCH 48/54] net: dsa: link interfaces with the DSA master to get
 rid of lockdep warnings

[ Upstream commit 2f1e8ea726e9020e01e9e2ae29c2d5eb11133032 ]

Since commit 845e0ebb4408 ("net: change addr_list_lock back to static
key"), cascaded DSA setups (DSA switch port as DSA master for another
DSA switch port) are emitting this lockdep warning:

============================================
WARNING: possible recursive locking detected
5.8.0-rc1-00133-g923e4b5032dd-dirty #208 Not tainted
--------------------------------------------
dhcpcd/323 is trying to acquire lock:
ffff000066dd4268 (&dsa_master_addr_list_lock_key/1){+...}-{2:2}, at: dev_mc_sync+0x44/0x90

but task is already holding lock:
ffff00006608c268 (&dsa_master_addr_list_lock_key/1){+...}-{2:2}, at: dev_mc_sync+0x44/0x90

other info that might help us debug this:
 Possible unsafe locking scenario:

       CPU0
       ----
  lock(&dsa_master_addr_list_lock_key/1);
  lock(&dsa_master_addr_list_lock_key/1);

 *** DEADLOCK ***

 May be due to missing lock nesting notation

3 locks held by dhcpcd/323:
 #0: ffffdbd1381dda18 (rtnl_mutex){+.+.}-{3:3}, at: rtnl_lock+0x24/0x30
 #1: ffff00006614b268 (_xmit_ETHER){+...}-{2:2}, at: dev_set_rx_mode+0x28/0x48
 #2: ffff00006608c268 (&dsa_master_addr_list_lock_key/1){+...}-{2:2}, at: dev_mc_sync+0x44/0x90

stack backtrace:
Call trace:
 dump_backtrace+0x0/0x1e0
 show_stack+0x20/0x30
 dump_stack+0xec/0x158
 __lock_acquire+0xca0/0x2398
 lock_acquire+0xe8/0x440
 _raw_spin_lock_nested+0x64/0x90
 dev_mc_sync+0x44/0x90
 dsa_slave_set_rx_mode+0x34/0x50
 __dev_set_rx_mode+0x60/0xa0
 dev_mc_sync+0x84/0x90
 dsa_slave_set_rx_mode+0x34/0x50
 __dev_set_rx_mode+0x60/0xa0
 dev_set_rx_mode+0x30/0x48
 __dev_open+0x10c/0x180
 __dev_change_flags+0x170/0x1c8
 dev_change_flags+0x2c/0x70
 devinet_ioctl+0x774/0x878
 inet_ioctl+0x348/0x3b0
 sock_do_ioctl+0x50/0x310
 sock_ioctl+0x1f8/0x580
 ksys_ioctl+0xb0/0xf0
 __arm64_sys_ioctl+0x28/0x38
 el0_svc_common.constprop.0+0x7c/0x180
 do_el0_svc+0x2c/0x98
 el0_sync_handler+0x9c/0x1b8
 el0_sync+0x158/0x180

Since DSA never made use of the netdev API for describing links between
upper devices and lower devices, the dev->lower_level value of a DSA
switch interface would be 1, which would warn when it is a DSA master.

We can use netdev_upper_dev_link() to describe the relationship between
a DSA slave and a DSA master. To be precise, a DSA "slave" (switch port)
is an "upper" to a DSA "master" (host port). The relationship is "many
uppers to one lower", like in the case of VLAN. So, for that reason, we
use the same function as VLAN uses.

There might be a chance that somebody will try to take hold of this
interface and use it immediately after register_netdev() and before
netdev_upper_dev_link(). To avoid that, we do the registration and
linkage while holding the RTNL, and we use the RTNL-locked cousin of
register_netdev(), which is register_netdevice().

Since this warning was not there when lockdep was using dynamic keys for
addr_list_lock, we are blaming the lockdep patch itself. The network
stack _has_ been using static lockdep keys before, and it _is_ likely
that stacked DSA setups have been triggering these lockdep warnings
since forever, however I can't test very old kernels on this particular
stacked DSA setup, to ensure I'm not in fact introducing regressions.

Fixes: 845e0ebb4408 ("net: change addr_list_lock back to static key")
Suggested-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/slave.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 4c7f086a047b..3f7be8c64c50 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -1801,15 +1801,27 @@ int dsa_slave_create(struct dsa_port *port)
 
 	dsa_slave_notify(slave_dev, DSA_PORT_REGISTER);
 
-	ret = register_netdev(slave_dev);
+	rtnl_lock();
+
+	ret = register_netdevice(slave_dev);
 	if (ret) {
 		netdev_err(master, "error %d registering interface %s\n",
 			   ret, slave_dev->name);
+		rtnl_unlock();
 		goto out_phy;
 	}
 
+	ret = netdev_upper_dev_link(master, slave_dev, NULL);
+
+	rtnl_unlock();
+
+	if (ret)
+		goto out_unregister;
+
 	return 0;
 
+out_unregister:
+	unregister_netdev(slave_dev);
 out_phy:
 	rtnl_lock();
 	phylink_disconnect_phy(p->dp->pl);
@@ -1826,16 +1838,18 @@ int dsa_slave_create(struct dsa_port *port)
 
 void dsa_slave_destroy(struct net_device *slave_dev)
 {
+	struct net_device *master = dsa_slave_to_master(slave_dev);
 	struct dsa_port *dp = dsa_slave_to_port(slave_dev);
 	struct dsa_slave_priv *p = netdev_priv(slave_dev);
 
 	netif_carrier_off(slave_dev);
 	rtnl_lock();
+	netdev_upper_dev_unlink(master, slave_dev);
+	unregister_netdevice(slave_dev);
 	phylink_disconnect_phy(dp->pl);
 	rtnl_unlock();
 
 	dsa_slave_notify(slave_dev, DSA_PORT_UNREGISTER);
-	unregister_netdev(slave_dev);
 	phylink_destroy(dp->pl);
 	gro_cells_destroy(&p->gcells);
 	free_percpu(p->stats64);
-- 
2.26.2


From 673a22b14b288198119b8a7c6b9b7ae58f8f56ef Mon Sep 17 00:00:00 2001
From: Matthias Schiffer <matthias.schiffer@ew.tq-group.com>
Date: Wed, 16 Sep 2020 12:08:39 +0200
Subject: [PATCH 49/54] net: dsa: microchip: ksz8795: really set the correct
 number of ports

[ Upstream commit fd944dc24336922656a48f4608bfb41abdcdc4aa ]

The KSZ9477 and KSZ8795 use the port_cnt field differently: For the
KSZ9477, it includes the CPU port(s), while for the KSZ8795, it doesn't.

It would be a good cleanup to make the handling of both drivers match,
but as a first step, fix the recently broken assignment of num_ports in
the KSZ8795 driver (which completely broke probing, as the CPU port
index was always failing the num_ports check).

Fixes: af199a1a9cb0 ("net: dsa: microchip: set the correct number of ports")
Signed-off-by: Matthias Schiffer <matthias.schiffer@ew.tq-group.com>
Reviewed-by: Codrin Ciubotariu <codrin.ciubotariu@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/microchip/ksz8795.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c
index 7c17b0f705ec..87db588bcdd6 100644
--- a/drivers/net/dsa/microchip/ksz8795.c
+++ b/drivers/net/dsa/microchip/ksz8795.c
@@ -1269,7 +1269,7 @@ static int ksz8795_switch_init(struct ksz_device *dev)
 	}
 
 	/* set the real number of ports */
-	dev->ds->num_ports = dev->port_cnt;
+	dev->ds->num_ports = dev->port_cnt + 1;
 
 	return 0;
 }
-- 
2.26.2


From afa857c523093b3caffbfa3dbb32fdc51caafbc8 Mon Sep 17 00:00:00 2001
From: Parshuram Thombare <pthombar@cadence.com>
Date: Sat, 5 Sep 2020 10:21:33 +0200
Subject: [PATCH 50/54] net: macb: fix for pause frame receive enable bit

[ Upstream commit d7739b0b6d15ef9ad5c79424736b8ded5ed3e913 ]

PAE bit of NCFGR register, when set, pauses transmission
if a non-zero 802.3 classic pause frame is received.

Fixes: 7897b071ac3b ("net: macb: convert to phylink")
Signed-off-by: Parshuram Thombare <pthombar@cadence.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cadence/macb_main.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 4b1b5928b104..55347bcea228 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -647,8 +647,7 @@ static void macb_mac_link_up(struct phylink_config *config,
 				ctrl |= GEM_BIT(GBE);
 		}
 
-		/* We do not support MLO_PAUSE_RX yet */
-		if (tx_pause)
+		if (rx_pause)
 			ctrl |= MACB_BIT(PAE);
 
 		macb_set_tx_clk(bp->tx_clk, speed, ndev);
-- 
2.26.2


From fbd9ca0747874fe1e3fe11fd53d2901ee6262e96 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Mon, 7 Sep 2020 15:54:41 +0000
Subject: [PATCH 51/54] Revert "netns: don't disable BHs when locking
 "nsid_lock""

[ Upstream commit e1f469cd5866499ac40bfdca87411e1c525a10c7 ]

This reverts commit 8d7e5dee972f1cde2ba96c621f1541fa36e7d4f4.

To protect netns id, the nsid_lock is used when netns id is being
allocated and removed by peernet2id_alloc() and unhash_nsid().
The nsid_lock can be used in BH context but only spin_lock() is used
in this code.
Using spin_lock() instead of spin_lock_bh() can result in a deadlock in
the following scenario reported by the lockdep.
In order to avoid a deadlock, the spin_lock_bh() should be used instead
of spin_lock() to acquire nsid_lock.

Test commands:
    ip netns del nst
    ip netns add nst
    ip link add veth1 type veth peer name veth2
    ip link set veth1 netns nst
    ip netns exec nst ip link add name br1 type bridge vlan_filtering 1
    ip netns exec nst ip link set dev br1 up
    ip netns exec nst ip link set dev veth1 master br1
    ip netns exec nst ip link set dev veth1 up
    ip netns exec nst ip link add macvlan0 link br1 up type macvlan

Splat looks like:
[   33.615860][  T607] WARNING: SOFTIRQ-safe -> SOFTIRQ-unsafe lock order detected
[   33.617194][  T607] 5.9.0-rc1+ #665 Not tainted
[ ... ]
[   33.670615][  T607] Chain exists of:
[   33.670615][  T607]   &mc->mca_lock --> &bridge_netdev_addr_lock_key --> &net->nsid_lock
[   33.670615][  T607]
[   33.673118][  T607]  Possible interrupt unsafe locking scenario:
[   33.673118][  T607]
[   33.674599][  T607]        CPU0                    CPU1
[   33.675557][  T607]        ----                    ----
[   33.676516][  T607]   lock(&net->nsid_lock);
[   33.677306][  T607]                                local_irq_disable();
[   33.678517][  T607]                                lock(&mc->mca_lock);
[   33.679725][  T607]                                lock(&bridge_netdev_addr_lock_key);
[   33.681166][  T607]   <Interrupt>
[   33.681791][  T607]     lock(&mc->mca_lock);
[   33.682579][  T607]
[   33.682579][  T607]  *** DEADLOCK ***
[ ... ]
[   33.922046][  T607] stack backtrace:
[   33.922999][  T607] CPU: 3 PID: 607 Comm: ip Not tainted 5.9.0-rc1+ #665
[   33.924099][  T607] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014
[   33.925714][  T607] Call Trace:
[   33.926238][  T607]  dump_stack+0x78/0xab
[   33.926905][  T607]  check_irq_usage+0x70b/0x720
[   33.927708][  T607]  ? iterate_chain_key+0x60/0x60
[   33.928507][  T607]  ? check_path+0x22/0x40
[   33.929201][  T607]  ? check_noncircular+0xcf/0x180
[   33.930024][  T607]  ? __lock_acquire+0x1952/0x1f20
[   33.930860][  T607]  __lock_acquire+0x1952/0x1f20
[   33.931667][  T607]  lock_acquire+0xaf/0x3a0
[   33.932366][  T607]  ? peernet2id_alloc+0x3a/0x170
[   33.933147][  T607]  ? br_port_fill_attrs+0x54c/0x6b0 [bridge]
[   33.934140][  T607]  ? br_port_fill_attrs+0x5de/0x6b0 [bridge]
[   33.935113][  T607]  ? kvm_sched_clock_read+0x14/0x30
[   33.935974][  T607]  _raw_spin_lock+0x30/0x70
[   33.936728][  T607]  ? peernet2id_alloc+0x3a/0x170
[   33.937523][  T607]  peernet2id_alloc+0x3a/0x170
[   33.938313][  T607]  rtnl_fill_ifinfo+0xb5e/0x1400
[   33.939091][  T607]  rtmsg_ifinfo_build_skb+0x8a/0xf0
[   33.939953][  T607]  rtmsg_ifinfo_event.part.39+0x17/0x50
[   33.940863][  T607]  rtmsg_ifinfo+0x1f/0x30
[   33.941571][  T607]  __dev_notify_flags+0xa5/0xf0
[   33.942376][  T607]  ? __irq_work_queue_local+0x49/0x50
[   33.943249][  T607]  ? irq_work_queue+0x1d/0x30
[   33.943993][  T607]  ? __dev_set_promiscuity+0x7b/0x1a0
[   33.944878][  T607]  __dev_set_promiscuity+0x7b/0x1a0
[   33.945758][  T607]  dev_set_promiscuity+0x1e/0x50
[   33.946582][  T607]  br_port_set_promisc+0x1f/0x40 [bridge]
[   33.947487][  T607]  br_manage_promisc+0x8b/0xe0 [bridge]
[   33.948388][  T607]  __dev_set_promiscuity+0x123/0x1a0
[   33.949244][  T607]  __dev_set_rx_mode+0x68/0x90
[   33.950021][  T607]  dev_uc_add+0x50/0x60
[   33.950720][  T607]  macvlan_open+0x18e/0x1f0 [macvlan]
[   33.951601][  T607]  __dev_open+0xd6/0x170
[   33.952269][  T607]  __dev_change_flags+0x181/0x1d0
[   33.953056][  T607]  rtnl_configure_link+0x2f/0xa0
[   33.953884][  T607]  __rtnl_newlink+0x6b9/0x8e0
[   33.954665][  T607]  ? __lock_acquire+0x95d/0x1f20
[   33.955450][  T607]  ? lock_acquire+0xaf/0x3a0
[   33.956193][  T607]  ? is_bpf_text_address+0x5/0xe0
[   33.956999][  T607]  rtnl_newlink+0x47/0x70

Acked-by: Guillaume Nault <gnault@redhat.com>
Fixes: 8d7e5dee972f ("netns: don't disable BHs when locking "nsid_lock"")
Reported-by: syzbot+3f960c64a104eaa2c813@syzkaller.appspotmail.com
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/net_namespace.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index dcd61aca343e..944ab214e5ae 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -251,10 +251,10 @@ int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp)
 	if (refcount_read(&net->count) == 0)
 		return NETNSA_NSID_NOT_ASSIGNED;
 
-	spin_lock(&net->nsid_lock);
+	spin_lock_bh(&net->nsid_lock);
 	id = __peernet2id(net, peer);
 	if (id >= 0) {
-		spin_unlock(&net->nsid_lock);
+		spin_unlock_bh(&net->nsid_lock);
 		return id;
 	}
 
@@ -264,12 +264,12 @@ int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp)
 	 * just been idr_remove()'d from there in cleanup_net().
 	 */
 	if (!maybe_get_net(peer)) {
-		spin_unlock(&net->nsid_lock);
+		spin_unlock_bh(&net->nsid_lock);
 		return NETNSA_NSID_NOT_ASSIGNED;
 	}
 
 	id = alloc_netid(net, peer, -1);
-	spin_unlock(&net->nsid_lock);
+	spin_unlock_bh(&net->nsid_lock);
 
 	put_net(peer);
 	if (id < 0)
@@ -534,20 +534,20 @@ static void unhash_nsid(struct net *net, struct net *last)
 	for_each_net(tmp) {
 		int id;
 
-		spin_lock(&tmp->nsid_lock);
+		spin_lock_bh(&tmp->nsid_lock);
 		id = __peernet2id(tmp, net);
 		if (id >= 0)
 			idr_remove(&tmp->netns_ids, id);
-		spin_unlock(&tmp->nsid_lock);
+		spin_unlock_bh(&tmp->nsid_lock);
 		if (id >= 0)
 			rtnl_net_notifyid(tmp, RTM_DELNSID, id, 0, NULL,
 					  GFP_KERNEL);
 		if (tmp == last)
 			break;
 	}
-	spin_lock(&net->nsid_lock);
+	spin_lock_bh(&net->nsid_lock);
 	idr_destroy(&net->netns_ids);
-	spin_unlock(&net->nsid_lock);
+	spin_unlock_bh(&net->nsid_lock);
 }
 
 static LLIST_HEAD(cleanup_list);
@@ -760,9 +760,9 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh,
 		return PTR_ERR(peer);
 	}
 
-	spin_lock(&net->nsid_lock);
+	spin_lock_bh(&net->nsid_lock);
 	if (__peernet2id(net, peer) >= 0) {
-		spin_unlock(&net->nsid_lock);
+		spin_unlock_bh(&net->nsid_lock);
 		err = -EEXIST;
 		NL_SET_BAD_ATTR(extack, nla);
 		NL_SET_ERR_MSG(extack,
@@ -771,7 +771,7 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh,
 	}
 
 	err = alloc_netid(net, peer, nsid);
-	spin_unlock(&net->nsid_lock);
+	spin_unlock_bh(&net->nsid_lock);
 	if (err >= 0) {
 		rtnl_net_notifyid(net, RTM_NEWNSID, err, NETLINK_CB(skb).portid,
 				  nlh, GFP_KERNEL);
-- 
2.26.2


From e35d2c55eb264ddcd74ae98389b16e380535a2b4 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Thu, 11 Jun 2020 13:55:19 +0300
Subject: [PATCH 52/54] net/mlx5e: Use RCU to protect rq->xdp_prog

[ Upstream commit fe45386a208277cae4648106133c08246eecd012 ]

Currently, the RQs are temporarily deactivated while hot-replacing the
XDP program, and napi_synchronize is used to make sure rq->xdp_prog is
not in use. However, napi_synchronize is not ideal: instead of waiting
till the end of a NAPI cycle, it polls and waits until NAPI is not
running, sleeping for 1ms between the periodic checks. Under heavy
workloads, this loop will never end, which may even lead to a kernel
panic if the kernel detects the hangup. Such workloads include XSK TX
and possibly also heavy RX (XSK or normal).

The fix is inspired by commit 326fe02d1ed6 ("net/mlx4_en: protect
ring->xdp_prog with rcu_read_lock"). As mlx5e_xdp_handle is already
protected by rcu_read_lock, and bpf_prog_put uses call_rcu to free the
program, there is no need for additional synchronization if proper RCU
functions are used to access the pointer. This patch converts all
accesses to rq->xdp_prog to use RCU functions.

Fixes: 86994156c736 ("net/mlx5e: XDP fast RX drop bpf programs support")
Fixes: db05815b36cb ("net/mlx5e: Add XSK zero-copy support")
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h  |  2 +-
 .../net/ethernet/mellanox/mlx5/core/en/xdp.c  |  2 +-
 .../net/ethernet/mellanox/mlx5/core/en_main.c | 53 +++++++++----------
 3 files changed, 27 insertions(+), 30 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 842db20493df..76b23ba7a468 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -604,7 +604,7 @@ struct mlx5e_rq {
 	struct dim         dim; /* Dynamic Interrupt Moderation */
 
 	/* XDP */
-	struct bpf_prog       *xdp_prog;
+	struct bpf_prog __rcu *xdp_prog;
 	struct mlx5e_xdpsq    *xdpsq;
 	DECLARE_BITMAP(flags, 8);
 	struct page_pool      *page_pool;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index c9d308e91965..75ed820b0ad7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -121,7 +121,7 @@ mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq,
 bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
 		      u32 *len, struct xdp_buff *xdp)
 {
-	struct bpf_prog *prog = READ_ONCE(rq->xdp_prog);
+	struct bpf_prog *prog = rcu_dereference(rq->xdp_prog);
 	u32 act;
 	int err;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 3b892ec301b4..3e1434fb166e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -401,7 +401,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 
 	if (params->xdp_prog)
 		bpf_prog_inc(params->xdp_prog);
-	rq->xdp_prog = params->xdp_prog;
+	RCU_INIT_POINTER(rq->xdp_prog, params->xdp_prog);
 
 	rq_xdp_ix = rq->ix;
 	if (xsk)
@@ -410,7 +410,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	if (err < 0)
 		goto err_rq_wq_destroy;
 
-	rq->buff.map_dir = rq->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
+	rq->buff.map_dir = params->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
 	rq->buff.headroom = mlx5e_get_rq_headroom(mdev, params, xsk);
 	pool_size = 1 << params->log_rq_mtu_frames;
 
@@ -605,8 +605,8 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	}
 
 err_rq_wq_destroy:
-	if (rq->xdp_prog)
-		bpf_prog_put(rq->xdp_prog);
+	if (params->xdp_prog)
+		bpf_prog_put(params->xdp_prog);
 	xdp_rxq_info_unreg(&rq->xdp_rxq);
 	page_pool_destroy(rq->page_pool);
 	mlx5_wq_destroy(&rq->wq_ctrl);
@@ -616,10 +616,16 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 
 static void mlx5e_free_rq(struct mlx5e_rq *rq)
 {
+	struct mlx5e_channel *c = rq->channel;
+	struct bpf_prog *old_prog = NULL;
 	int i;
 
-	if (rq->xdp_prog)
-		bpf_prog_put(rq->xdp_prog);
+	/* drop_rq has neither channel nor xdp_prog. */
+	if (c)
+		old_prog = rcu_dereference_protected(rq->xdp_prog,
+						     lockdep_is_held(&c->priv->state_lock));
+	if (old_prog)
+		bpf_prog_put(old_prog);
 
 	switch (rq->wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
@@ -4423,6 +4429,16 @@ static int mlx5e_xdp_allowed(struct mlx5e_priv *priv, struct bpf_prog *prog)
 	return 0;
 }
 
+static void mlx5e_rq_replace_xdp_prog(struct mlx5e_rq *rq, struct bpf_prog *prog)
+{
+	struct bpf_prog *old_prog;
+
+	old_prog = rcu_replace_pointer(rq->xdp_prog, prog,
+				       lockdep_is_held(&rq->channel->priv->state_lock));
+	if (old_prog)
+		bpf_prog_put(old_prog);
+}
+
 static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -4481,29 +4497,10 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 	 */
 	for (i = 0; i < priv->channels.num; i++) {
 		struct mlx5e_channel *c = priv->channels.c[i];
-		bool xsk_open = test_bit(MLX5E_CHANNEL_STATE_XSK, c->state);
-
-		clear_bit(MLX5E_RQ_STATE_ENABLED, &c->rq.state);
-		if (xsk_open)
-			clear_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state);
-		napi_synchronize(&c->napi);
-		/* prevent mlx5e_poll_rx_cq from accessing rq->xdp_prog */
-
-		old_prog = xchg(&c->rq.xdp_prog, prog);
-		if (old_prog)
-			bpf_prog_put(old_prog);
-
-		if (xsk_open) {
-			old_prog = xchg(&c->xskrq.xdp_prog, prog);
-			if (old_prog)
-				bpf_prog_put(old_prog);
-		}
 
-		set_bit(MLX5E_RQ_STATE_ENABLED, &c->rq.state);
-		if (xsk_open)
-			set_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state);
-		/* napi_schedule in case we have missed anything */
-		napi_schedule(&c->napi);
+		mlx5e_rq_replace_xdp_prog(&c->rq, prog);
+		if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state))
+			mlx5e_rq_replace_xdp_prog(&c->xskrq, prog);
 	}
 
 unlock:
-- 
2.26.2


From 0ac61c28f2c8bb9dd157acba9a3d7566088a2e01 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Thu, 11 Jun 2020 14:25:19 +0300
Subject: [PATCH 53/54] net/mlx5e: Use synchronize_rcu to sync with NAPI

[ Upstream commit 9c25a22dfb00270372224721fed646965420323a ]

As described in the previous commit, napi_synchronize doesn't quite fit
the purpose when we just need to wait until the currently running NAPI
quits. Its implementation waits until NAPI is not running by polling and
waiting for 1ms in between. In cases where we need to deactivate one
queue (e.g., recovery flows) or where we deactivate them one-by-one
(deactivate channel flow), we may get stuck in napi_synchronize forever
if other queues keep NAPI active, causing a soft lockup. Depending on
kernel configuration (CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC), it may result
in a kernel panic.

To fix the issue, use synchronize_rcu to wait for NAPI to quit, and wrap
the whole NAPI in rcu_read_lock.

Fixes: acc6c5953af1 ("net/mlx5e: Split open/close channels to stages")
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en/xsk/rx.c | 14 ++------------
 .../ethernet/mellanox/mlx5/core/en/xsk/setup.c  |  3 +--
 .../net/ethernet/mellanox/mlx5/core/en_main.c   | 12 ++++--------
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 12 ++----------
 .../net/ethernet/mellanox/mlx5/core/en_txrx.c   | 17 +++++++++++++----
 5 files changed, 22 insertions(+), 36 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
index a33a1f762c70..40db27bf790b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
@@ -31,7 +31,6 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
 {
 	struct xdp_buff *xdp = wi->umr.dma_info[page_idx].xsk;
 	u32 cqe_bcnt32 = cqe_bcnt;
-	bool consumed;
 
 	/* Check packet size. Note LRO doesn't use linear SKB */
 	if (unlikely(cqe_bcnt > rq->hw_mtu)) {
@@ -51,10 +50,6 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
 	xsk_buff_dma_sync_for_cpu(xdp);
 	prefetch(xdp->data);
 
-	rcu_read_lock();
-	consumed = mlx5e_xdp_handle(rq, NULL, &cqe_bcnt32, xdp);
-	rcu_read_unlock();
-
 	/* Possible flows:
 	 * - XDP_REDIRECT to XSKMAP:
 	 *   The page is owned by the userspace from now.
@@ -70,7 +65,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
 	 * allocated first from the Reuse Ring, so it has enough space.
 	 */
 
-	if (likely(consumed)) {
+	if (likely(mlx5e_xdp_handle(rq, NULL, &cqe_bcnt32, xdp))) {
 		if (likely(__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)))
 			__set_bit(page_idx, wi->xdp_xmit_bitmap); /* non-atomic */
 		return NULL; /* page/packet was consumed by XDP */
@@ -88,7 +83,6 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq,
 					      u32 cqe_bcnt)
 {
 	struct xdp_buff *xdp = wi->di->xsk;
-	bool consumed;
 
 	/* wi->offset is not used in this function, because xdp->data and the
 	 * DMA address point directly to the necessary place. Furthermore, the
@@ -107,11 +101,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq,
 		return NULL;
 	}
 
-	rcu_read_lock();
-	consumed = mlx5e_xdp_handle(rq, NULL, &cqe_bcnt, xdp);
-	rcu_read_unlock();
-
-	if (likely(consumed))
+	if (likely(mlx5e_xdp_handle(rq, NULL, &cqe_bcnt, xdp)))
 		return NULL; /* page/packet was consumed by XDP */
 
 	/* XDP_PASS: copy the data from the UMEM to a new SKB. The frame reuse
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
index 2c80205dc939..3081cd74d651 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
@@ -143,8 +143,7 @@ int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params,
 void mlx5e_close_xsk(struct mlx5e_channel *c)
 {
 	clear_bit(MLX5E_CHANNEL_STATE_XSK, c->state);
-	napi_synchronize(&c->napi);
-	synchronize_rcu(); /* Sync with the XSK wakeup. */
+	synchronize_rcu(); /* Sync with the XSK wakeup and with NAPI. */
 
 	mlx5e_close_rq(&c->xskrq);
 	mlx5e_close_cq(&c->xskrq.cq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 3e1434fb166e..cccf65fc116e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -911,7 +911,7 @@ void mlx5e_activate_rq(struct mlx5e_rq *rq)
 void mlx5e_deactivate_rq(struct mlx5e_rq *rq)
 {
 	clear_bit(MLX5E_RQ_STATE_ENABLED, &rq->state);
-	napi_synchronize(&rq->channel->napi); /* prevent mlx5e_post_rx_wqes */
+	synchronize_rcu(); /* Sync with NAPI to prevent mlx5e_post_rx_wqes. */
 }
 
 void mlx5e_close_rq(struct mlx5e_rq *rq)
@@ -1356,12 +1356,10 @@ void mlx5e_tx_disable_queue(struct netdev_queue *txq)
 
 static void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq)
 {
-	struct mlx5e_channel *c = sq->channel;
 	struct mlx5_wq_cyc *wq = &sq->wq;
 
 	clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
-	/* prevent netif_tx_wake_queue */
-	napi_synchronize(&c->napi);
+	synchronize_rcu(); /* Sync with NAPI to prevent netif_tx_wake_queue. */
 
 	mlx5e_tx_disable_queue(sq->txq);
 
@@ -1436,10 +1434,8 @@ void mlx5e_activate_icosq(struct mlx5e_icosq *icosq)
 
 void mlx5e_deactivate_icosq(struct mlx5e_icosq *icosq)
 {
-	struct mlx5e_channel *c = icosq->channel;
-
 	clear_bit(MLX5E_SQ_STATE_ENABLED, &icosq->state);
-	napi_synchronize(&c->napi);
+	synchronize_rcu(); /* Sync with NAPI. */
 }
 
 void mlx5e_close_icosq(struct mlx5e_icosq *sq)
@@ -1517,7 +1513,7 @@ void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq)
 	struct mlx5e_channel *c = sq->channel;
 
 	clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
-	napi_synchronize(&c->napi);
+	synchronize_rcu(); /* Sync with NAPI. */
 
 	mlx5e_destroy_sq(c->mdev, sq->sqn);
 	mlx5e_free_xdpsq_descs(sq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index dbb1c6323967..409fecbcc5d2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1072,7 +1072,6 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 	struct xdp_buff xdp;
 	struct sk_buff *skb;
 	void *va, *data;
-	bool consumed;
 	u32 frag_size;
 
 	va             = page_address(di->page) + wi->offset;
@@ -1084,11 +1083,8 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 	prefetchw(va); /* xdp_frame data area */
 	prefetch(data);
 
-	rcu_read_lock();
 	mlx5e_fill_xdp_buff(rq, va, rx_headroom, cqe_bcnt, &xdp);
-	consumed = mlx5e_xdp_handle(rq, di, &cqe_bcnt, &xdp);
-	rcu_read_unlock();
-	if (consumed)
+	if (mlx5e_xdp_handle(rq, di, &cqe_bcnt, &xdp))
 		return NULL; /* page/packet was consumed by XDP */
 
 	rx_headroom = xdp.data - xdp.data_hard_start;
@@ -1369,7 +1365,6 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 	struct sk_buff *skb;
 	void *va, *data;
 	u32 frag_size;
-	bool consumed;
 
 	/* Check packet size. Note LRO doesn't use linear SKB */
 	if (unlikely(cqe_bcnt > rq->hw_mtu)) {
@@ -1386,11 +1381,8 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 	prefetchw(va); /* xdp_frame data area */
 	prefetch(data);
 
-	rcu_read_lock();
 	mlx5e_fill_xdp_buff(rq, va, rx_headroom, cqe_bcnt32, &xdp);
-	consumed = mlx5e_xdp_handle(rq, di, &cqe_bcnt32, &xdp);
-	rcu_read_unlock();
-	if (consumed) {
+	if (mlx5e_xdp_handle(rq, di, &cqe_bcnt32, &xdp)) {
 		if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags))
 			__set_bit(page_idx, wi->xdp_xmit_bitmap); /* non-atomic */
 		return NULL; /* page/packet was consumed by XDP */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
index 8480278f2ee2..954a2f0513d6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
@@ -121,13 +121,17 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 	struct mlx5e_xdpsq *xsksq = &c->xsksq;
 	struct mlx5e_rq *xskrq = &c->xskrq;
 	struct mlx5e_rq *rq = &c->rq;
-	bool xsk_open = test_bit(MLX5E_CHANNEL_STATE_XSK, c->state);
 	bool aff_change = false;
 	bool busy_xsk = false;
 	bool busy = false;
 	int work_done = 0;
+	bool xsk_open;
 	int i;
 
+	rcu_read_lock();
+
+	xsk_open = test_bit(MLX5E_CHANNEL_STATE_XSK, c->state);
+
 	ch_stats->poll++;
 
 	for (i = 0; i < c->num_tc; i++)
@@ -167,8 +171,10 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 	busy |= busy_xsk;
 
 	if (busy) {
-		if (likely(mlx5e_channel_no_affinity_change(c)))
-			return budget;
+		if (likely(mlx5e_channel_no_affinity_change(c))) {
+			work_done = budget;
+			goto out;
+		}
 		ch_stats->aff_change++;
 		aff_change = true;
 		if (budget && work_done == budget)
@@ -176,7 +182,7 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 	}
 
 	if (unlikely(!napi_complete_done(napi, work_done)))
-		return work_done;
+		goto out;
 
 	ch_stats->arm++;
 
@@ -203,6 +209,9 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 		ch_stats->force_irq++;
 	}
 
+out:
+	rcu_read_unlock();
+
 	return work_done;
 }
 
-- 
2.26.2


From f2cb38ab3d093bf9c6c0e6a6ff191837f9e2695d Mon Sep 17 00:00:00 2001
From: Maor Dickman <maord@nvidia.com>
Date: Wed, 2 Sep 2020 16:49:52 +0300
Subject: [PATCH 54/54] net/mlx5e: Fix endianness when calculating pedit mask
 first bit

[ Upstream commit 82198d8bcdeff01d19215d712aa55031e21bccbc ]

The field mask value is provided in network byte order and has to
be converted to host byte order before calculating pedit mask
first bit.

Fixes: 88f30bbcbaaa ("net/mlx5e: Bit sized fields rewrite support")
Signed-off-by: Maor Dickman <maord@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/en_tc.c   | 34 ++++++++++++-------
 1 file changed, 21 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index f1701ee4619b..7da1e7462f64 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2731,6 +2731,22 @@ static struct mlx5_fields fields[] = {
 	OFFLOAD(UDP_DPORT, 16, U16_MAX, udp.dest,   0, udp_dport),
 };
 
+static unsigned long mask_to_le(unsigned long mask, int size)
+{
+	__be32 mask_be32;
+	__be16 mask_be16;
+
+	if (size == 32) {
+		mask_be32 = (__force __be32)(mask);
+		mask = (__force unsigned long)cpu_to_le32(be32_to_cpu(mask_be32));
+	} else if (size == 16) {
+		mask_be32 = (__force __be32)(mask);
+		mask_be16 = *(__be16 *)&mask_be32;
+		mask = (__force unsigned long)cpu_to_le16(be16_to_cpu(mask_be16));
+	}
+
+	return mask;
+}
 static int offload_pedit_fields(struct mlx5e_priv *priv,
 				int namespace,
 				struct pedit_headers_action *hdrs,
@@ -2744,9 +2760,7 @@ static int offload_pedit_fields(struct mlx5e_priv *priv,
 	u32 *s_masks_p, *a_masks_p, s_mask, a_mask;
 	struct mlx5e_tc_mod_hdr_acts *mod_acts;
 	struct mlx5_fields *f;
-	unsigned long mask;
-	__be32 mask_be32;
-	__be16 mask_be16;
+	unsigned long mask, field_mask;
 	int err;
 	u8 cmd;
 
@@ -2812,14 +2826,7 @@ static int offload_pedit_fields(struct mlx5e_priv *priv,
 		if (skip)
 			continue;
 
-		if (f->field_bsize == 32) {
-			mask_be32 = (__force __be32)(mask);
-			mask = (__force unsigned long)cpu_to_le32(be32_to_cpu(mask_be32));
-		} else if (f->field_bsize == 16) {
-			mask_be32 = (__force __be32)(mask);
-			mask_be16 = *(__be16 *)&mask_be32;
-			mask = (__force unsigned long)cpu_to_le16(be16_to_cpu(mask_be16));
-		}
+		mask = mask_to_le(mask, f->field_bsize);
 
 		first = find_first_bit(&mask, f->field_bsize);
 		next_z = find_next_zero_bit(&mask, f->field_bsize, first);
@@ -2850,9 +2857,10 @@ static int offload_pedit_fields(struct mlx5e_priv *priv,
 		if (cmd == MLX5_ACTION_TYPE_SET) {
 			int start;
 
+			field_mask = mask_to_le(f->field_mask, f->field_bsize);
+
 			/* if field is bit sized it can start not from first bit */
-			start = find_first_bit((unsigned long *)&f->field_mask,
-					       f->field_bsize);
+			start = find_first_bit(&field_mask, f->field_bsize);
 
 			MLX5_SET(set_action_in, action, offset, first - start);
 			/* length is num of bits to be written, zero means length of 32 */
-- 
2.26.2

Re: [PATCHES] Networking

[Greg KH]

On Thu, Sep 24, 2020 at 02:40:01PM -0700, David Miller wrote:
> 
> Please queue up the following networking bug fixes for v5.4
> and v5.8 -stable, respectively.

Thanks for these, all now queued up.

greg k-h